From aefff4915632185e286c8c94f6f5ccb939fc51d7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 15 May 2018 09:54:33 +0100
Subject: drm/xen-front: fix spelling mistake: "conector" -> "connector"

Trivial fix to spelling mistake in DRM_INFO message.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180515085433.8245-1-colin.king@canonical.com
---
 drivers/gpu/drm/xen/xen_drm_front.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xen/xen_drm_front.c b/drivers/gpu/drm/xen/xen_drm_front.c
index 3345ac71b391..93bf9f092086 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.c
+++ b/drivers/gpu/drm/xen/xen_drm_front.c
@@ -623,7 +623,7 @@ static int displback_initwait(struct xen_drm_front_info *front_info)
 	if (ret < 0)
 		return ret;
 
-	DRM_INFO("Have %d conector(s)\n", cfg->num_connectors);
+	DRM_INFO("Have %d connector(s)\n", cfg->num_connectors);
 	/* Create event channels for all connectors and publish */
 	ret = xen_drm_front_evtchnl_create_all(front_info);
 	if (ret < 0)
-- 
cgit v1.2.3


From 584a0146ec4989f30d0aef46ce1ea6f6ba22a690 Mon Sep 17 00:00:00 2001
From: Philippe Cornu <philippe.cornu@st.com>
Date: Mon, 9 Apr 2018 17:24:27 +0200
Subject: drm: clarify adjusted_mode documentation for bridges

This patch clarifies the adjusted_mode documentation
for bridges.

Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Reviewed-by: Archit Taneja <architt@codeaurora.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180409152427.12449-1-philippe.cornu@st.com
---
 include/drm/drm_bridge.h | 16 ++++++++++++++++
 include/drm/drm_crtc.h   | 11 +++++++----
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h
index 3270fec46979..9917651a7fdd 100644
--- a/include/drm/drm_bridge.h
+++ b/include/drm/drm_bridge.h
@@ -178,6 +178,22 @@ struct drm_bridge_funcs {
 	 * then this would be &drm_encoder_helper_funcs.mode_set. The display
 	 * pipe (i.e.  clocks and timing signals) is off when this function is
 	 * called.
+	 *
+	 * The adjusted_mode parameter is the mode output by the CRTC for the
+	 * first bridge in the chain. It can be different from the mode
+	 * parameter that contains the desired mode for the connector at the end
+	 * of the bridges chain, for instance when the first bridge in the chain
+	 * performs scaling. The adjusted mode is mostly useful for the first
+	 * bridge in the chain and is likely irrelevant for the other bridges.
+	 *
+	 * For atomic drivers the adjusted_mode is the mode stored in
+	 * &drm_crtc_state.adjusted_mode.
+	 *
+	 * NOTE:
+	 *
+	 * If a need arises to store and access modes adjusted for other
+	 * locations than the connection between the CRTC and the first bridge,
+	 * the DRM framework will have to be extended with DRM bridge states.
 	 */
 	void (*mode_set)(struct drm_bridge *bridge,
 			 struct drm_display_mode *mode,
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index a2d81d2907a9..5cf7adeae6a5 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -134,10 +134,13 @@ struct drm_crtc_state {
 	 *
 	 * Internal display timings which can be used by the driver to handle
 	 * differences between the mode requested by userspace in @mode and what
-	 * is actually programmed into the hardware. It is purely driver
-	 * implementation defined what exactly this adjusted mode means. Usually
-	 * it is used to store the hardware display timings used between the
-	 * CRTC and encoder blocks.
+	 * is actually programmed into the hardware.
+	 *
+	 * For drivers using drm_bridge, this stores hardware display timings
+	 * used between the CRTC and the first bridge. For other drivers, the
+	 * meaning of the adjusted_mode field is purely driver implementation
+	 * defined information, and will usually be used to store the hardware
+	 * display timings used between the CRTC and encoder blocks.
 	 */
 	struct drm_display_mode adjusted_mode;
 
-- 
cgit v1.2.3


From 1c6ccad8a4b110bac3f9ff6db954ab5a74c2e861 Mon Sep 17 00:00:00 2001
From: Tina Zhang <tina.zhang@intel.com>
Date: Mon, 14 May 2018 13:59:18 +0800
Subject: drm/i915/gvt: Deliver guest cursor hotspot info

Guest OS driver uses PV info registers to deliver cursor hotspot info
to host. This patch is used to get cursor hotspot info from virtual
registers and deliver it to host userspace.

v4->v5:
- remove CI warning.

v3->v4:
- return UINT_MAX when x_hot/y_hot is invalid. (Zhenyu)
- correct version.

v2->v3:
- add validate_hotspot(). (Zhenyu)

v1->v2:
- name as cursor_x_hot/cursor_y_hot. (Zhenyu)
- use i915_reg_t definition instead of magic numbers. (Zhenyu)

Signed-off-by: Tina Zhang <tina.zhang@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/dmabuf.c     | 22 ++++++++++++++++------
 drivers/gpu/drm/i915/gvt/fb_decoder.c |  3 +++
 drivers/gpu/drm/i915/gvt/handlers.c   |  4 ++--
 drivers/gpu/drm/i915/gvt/vgpu.c       |  3 +++
 drivers/gpu/drm/i915/i915_pvinfo.h    |  5 ++++-
 5 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 6f4f8e941fc2..d2eb2f7754b9 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -192,6 +192,14 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 	return obj;
 }
 
+static bool validate_hotspot(struct intel_vgpu_cursor_plane_format *c)
+{
+	if (c && c->x_hot <= c->width && c->y_hot <= c->height)
+		return true;
+	else
+		return false;
+}
+
 static int vgpu_get_plane_info(struct drm_device *dev,
 		struct intel_vgpu *vgpu,
 		struct intel_vgpu_fb_info *info,
@@ -229,12 +237,14 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		info->x_pos = c.x_pos;
 		info->y_pos = c.y_pos;
 
-		/* The invalid cursor hotspot value is delivered to host
-		 * until we find a way to get the cursor hotspot info of
-		 * guest OS.
-		 */
-		info->x_hot = UINT_MAX;
-		info->y_hot = UINT_MAX;
+		if (validate_hotspot(&c)) {
+			info->x_hot = c.x_hot;
+			info->y_hot = c.y_hot;
+		} else {
+			info->x_hot = UINT_MAX;
+			info->y_hot = UINT_MAX;
+		}
+
 		info->size = (((info->stride * c.height * c.bpp) / 8)
 				+ (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	} else {
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c
index 1c120683e958..5e7468bd1b36 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.c
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c
@@ -36,6 +36,7 @@
 #include <uapi/drm/drm_fourcc.h>
 #include "i915_drv.h"
 #include "gvt.h"
+#include "i915_pvinfo.h"
 
 #define PRIMARY_FORMAT_NUM	16
 struct pixel_format {
@@ -384,6 +385,8 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu,
 	plane->y_pos = (val & _CURSOR_POS_Y_MASK) >> _CURSOR_POS_Y_SHIFT;
 	plane->y_sign = (val & _CURSOR_SIGN_Y_MASK) >> _CURSOR_SIGN_Y_SHIFT;
 
+	plane->x_hot = vgpu_vreg_t(vgpu, vgtif_reg(cursor_x_hot));
+	plane->y_hot = vgpu_vreg_t(vgpu, vgtif_reg(cursor_y_hot));
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 4b6532fb789a..d5e206661048 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1204,8 +1204,8 @@ static int pvinfo_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		ret = handle_g2v_notification(vgpu, data);
 		break;
 	/* add xhot and yhot to handled list to avoid error log */
-	case 0x78830:
-	case 0x78834:
+	case _vgtif_reg(cursor_x_hot):
+	case _vgtif_reg(cursor_y_hot):
 	case _vgtif_reg(pdp[0].lo):
 	case _vgtif_reg(pdp[0].hi):
 	case _vgtif_reg(pdp[1].lo):
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 2e0a02a80fe4..bf75300c1ec1 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -58,6 +58,9 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 
 	vgpu_vreg_t(vgpu, vgtif_reg(avail_rs.fence_num)) = vgpu_fence_sz(vgpu);
 
+	vgpu_vreg_t(vgpu, vgtif_reg(cursor_x_hot)) = UINT_MAX;
+	vgpu_vreg_t(vgpu, vgtif_reg(cursor_y_hot)) = UINT_MAX;
+
 	gvt_dbg_core("Populate PVINFO PAGE for vGPU %d\n", vgpu->id);
 	gvt_dbg_core("aperture base [GMADR] 0x%llx size 0x%llx\n",
 		vgpu_aperture_gmadr_base(vgpu), vgpu_aperture_sz(vgpu));
diff --git a/drivers/gpu/drm/i915/i915_pvinfo.h b/drivers/gpu/drm/i915/i915_pvinfo.h
index 195203f298df..d61914a11756 100644
--- a/drivers/gpu/drm/i915/i915_pvinfo.h
+++ b/drivers/gpu/drm/i915/i915_pvinfo.h
@@ -93,7 +93,10 @@ struct vgt_if {
 	u32 rsv5[4];
 
 	u32 g2v_notify;
-	u32 rsv6[7];
+	u32 rsv6[5];
+
+	u32 cursor_x_hot;
+	u32 cursor_y_hot;
 
 	struct {
 		u32 lo;
-- 
cgit v1.2.3


From f75f91574617a3c6fbc821c6b156f5777a59d0ed Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 15 May 2018 15:31:49 +0100
Subject: drm/i915: Shrink search list for active timelines

When switching to the kernel context, we force the switch to occur after
all currently active requests (so that we know the GPU won't switch
immediately away and the kernel context remains current as we work). To
do so we have to inspect all the timelines and add a fence from the
active work to queue our switch afterwards. We can use the tracked set
of active rings to shrink our search for active timelines.

v2: Use a local to shrink the list_for_each_entry()

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180515143149.4795-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_context.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 33f8a4b3c981..4bf18b5c6f1d 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -596,41 +596,44 @@ last_request_on_engine(struct i915_timeline *timeline,
 
 static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine)
 {
-	struct i915_timeline *timeline;
+	struct list_head * const active_rings = &engine->i915->gt.active_rings;
+	struct intel_ring *ring;
 
-	list_for_each_entry(timeline, &engine->i915->gt.timelines, link) {
-		if (last_request_on_engine(timeline, engine))
+	lockdep_assert_held(&engine->i915->drm.struct_mutex);
+
+	list_for_each_entry(ring, active_rings, active_link) {
+		if (last_request_on_engine(ring->timeline, engine))
 			return false;
 	}
 
 	return intel_engine_has_kernel_context(engine);
 }
 
-int i915_gem_switch_to_kernel_context(struct drm_i915_private *dev_priv)
+int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
-	struct i915_timeline *timeline;
 	enum intel_engine_id id;
 
-	lockdep_assert_held(&dev_priv->drm.struct_mutex);
+	lockdep_assert_held(&i915->drm.struct_mutex);
 
-	i915_retire_requests(dev_priv);
+	i915_retire_requests(i915);
 
-	for_each_engine(engine, dev_priv, id) {
+	for_each_engine(engine, i915, id) {
+		struct intel_ring *ring;
 		struct i915_request *rq;
 
 		if (engine_has_idle_kernel_context(engine))
 			continue;
 
-		rq = i915_request_alloc(engine, dev_priv->kernel_context);
+		rq = i915_request_alloc(engine, i915->kernel_context);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
 
 		/* Queue this switch after all other activity */
-		list_for_each_entry(timeline, &dev_priv->gt.timelines, link) {
+		list_for_each_entry(ring, &i915->gt.active_rings, active_link) {
 			struct i915_request *prev;
 
-			prev = last_request_on_engine(timeline, engine);
+			prev = last_request_on_engine(ring->timeline, engine);
 			if (prev)
 				i915_sw_fence_await_sw_fence_gfp(&rq->submit,
 								 &prev->submit,
-- 
cgit v1.2.3


From e7f2af7894b1ac76f2062f32724d51f23438249b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 9 May 2018 11:16:06 +0100
Subject: drm/i915/dp: fix spelling mistakes: "seqeuncer" and "seqeuencer"

Trivial fix to spelling mistakes in WARN warning message text and
in comments:

"seqeuncer", "seqeuencer" -> "sequencer"

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180509101606.17483-1-colin.king@canonical.com
---
 drivers/gpu/drm/i915/intel_dp.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index dde92e4af5d3..2cc58596ff5a 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -513,7 +513,7 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 	uint32_t DP;
 
 	if (WARN(I915_READ(intel_dp->output_reg) & DP_PORT_EN,
-		 "skipping pipe %c power seqeuncer kick due to port %c being active\n",
+		 "skipping pipe %c power sequencer kick due to port %c being active\n",
 		 pipe_name(pipe), port_name(intel_dig_port->base.port)))
 		return;
 
@@ -554,7 +554,7 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 	/*
 	 * Similar magic as in intel_dp_enable_port().
 	 * We _must_ do this port enable + disable trick
-	 * to make this power seqeuencer lock onto the port.
+	 * to make this power sequencer lock onto the port.
 	 * Otherwise even VDD force bit won't work.
 	 */
 	I915_WRITE(intel_dp->output_reg, DP);
@@ -3066,11 +3066,11 @@ static void vlv_detach_power_sequencer(struct intel_dp *intel_dp)
 	edp_panel_vdd_off_sync(intel_dp);
 
 	/*
-	 * VLV seems to get confused when multiple power seqeuencers
+	 * VLV seems to get confused when multiple power sequencers
 	 * have the same port selected (even if only one has power/vdd
 	 * enabled). The failure manifests as vlv_wait_port_ready() failing
 	 * CHV on the other hand doesn't seem to mind having the same port
-	 * selected in multiple power seqeuencers, but let's clear the
+	 * selected in multiple power sequencers, but let's clear the
 	 * port select always when logically disconnecting a power sequencer
 	 * from a port.
 	 */
@@ -5698,7 +5698,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 
 	/*
 	 * On some VLV machines the BIOS can leave the VDD
-	 * enabled even on power seqeuencers which aren't
+	 * enabled even on power sequencers which aren't
 	 * hooked up to any port. This would mess up the
 	 * power domain tracking the first time we pick
 	 * one of these power sequencers for use since
@@ -5706,7 +5706,7 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 	 * already on and therefore wouldn't grab the power
 	 * domain reference. Disable VDD first to avoid this.
 	 * This also avoids spuriously turning the VDD on as
-	 * soon as the new power seqeuencer gets initialized.
+	 * soon as the new power sequencer gets initialized.
 	 */
 	if (force_disable_vdd) {
 		u32 pp = ironlake_get_pp_control(intel_dp);
-- 
cgit v1.2.3


From b8444cf85b629413ad23f5b6ed9bf5267f38acab Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:48 +0100
Subject: drm/i915: Remove tasklet flush before disable

The idea was to try and let the existing tasklet run to completion
before we began the reset, but it involves a racy check against anything
else that tries to run the tasklet. Rather than acknowledge and ignore
the race, let it be and don't try and be too clever.

The tasklet will resume execution after reset (after spinning a bit
during reset), but before we allow it to resume we will have cleared all
the pending state.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0a2070112b66..0dc369a9ec4d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3035,16 +3035,7 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 	 * calling engine->init_hw() and also writing the ELSP.
 	 * Turning off the execlists->tasklet until the reset is over
 	 * prevents the race.
-	 *
-	 * Note that this needs to be a single atomic operation on the
-	 * tasklet (flush existing tasks, prevent new tasks) to prevent
-	 * a race between reset and set-wedged. It is not, so we do the best
-	 * we can atm and make sure we don't lock the machine up in the more
-	 * common case of recursively being called from set-wedged from inside
-	 * i915_reset.
 	 */
-	if (!atomic_read(&engine->execlists.tasklet.count))
-		tasklet_kill(&engine->execlists.tasklet);
 	tasklet_disable(&engine->execlists.tasklet);
 
 	/*
-- 
cgit v1.2.3


From f351d087d8329a08eca9e69872c3906c139e1f11 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:49 +0100
Subject: drm/i915: Only sync tasklets once for recursive reset preparation

When setting up reset, we may need to recursively prepare an engine. In
which case we should only synchronously flush the tasklets on the outer
most call, the inner calls will then be inside an atomic section where
the tasklet will never be run (and so the sync will never complete).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 2 +-
 drivers/gpu/drm/i915/i915_gem.h | 7 +++++++
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0dc369a9ec4d..982393907b80 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3036,7 +3036,7 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 	 * Turning off the execlists->tasklet until the reset is over
 	 * prevents the race.
 	 */
-	tasklet_disable(&engine->execlists.tasklet);
+	__tasklet_disable_sync_once(&engine->execlists.tasklet);
 
 	/*
 	 * We're using worker to queue preemption requests from the tasklet in
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 525920404ede..5bf24cfc218c 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -26,6 +26,7 @@
 #define __I915_GEM_H__
 
 #include <linux/bug.h>
+#include <linux/interrupt.h>
 
 struct drm_i915_private;
 
@@ -72,4 +73,10 @@ struct drm_i915_private;
 void i915_gem_park(struct drm_i915_private *i915);
 void i915_gem_unpark(struct drm_i915_private *i915);
 
+static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
+{
+	if (atomic_inc_return(&t->count) == 1)
+		tasklet_unlock_wait(t);
+}
+
 #endif /* __I915_GEM_H__ */
-- 
cgit v1.2.3


From ef2fb7204638f0c67446a90b75e1eae4330682f8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:50 +0100
Subject: drm/i915/execlists: Refactor out complete_preempt_context()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As a complement to inject_preempt_context(), follow up with the function
to handle its completion. This will be useful should we wish to extend
the duties of the preempt-context for execlists.

v2: And do the same for the guc.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Jeff McGee <jeff.mcgee@intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 26 +++++++++++++++++---------
 drivers/gpu/drm/i915/intel_lrc.c            | 23 +++++++++++++----------
 2 files changed, 30 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 2feb65096966..ca38ac9ff4fa 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -623,6 +623,21 @@ static void wait_for_guc_preempt_report(struct intel_engine_cs *engine)
 	report->report_return_status = INTEL_GUC_REPORT_STATUS_UNKNOWN;
 }
 
+static void complete_preempt_context(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists *execlists = &engine->execlists;
+
+	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
+
+	execlists_cancel_port_requests(execlists);
+	execlists_unwind_incomplete_requests(execlists);
+
+	wait_for_guc_preempt_report(engine);
+	intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0);
+
+	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
+}
+
 /**
  * guc_submit() - Submit commands through GuC
  * @engine: engine associated with the commands
@@ -793,15 +808,8 @@ static void guc_submission_tasklet(unsigned long data)
 
 	if (execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT) &&
 	    intel_read_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX) ==
-	    GUC_PREEMPT_FINISHED) {
-		execlists_cancel_port_requests(&engine->execlists);
-		execlists_unwind_incomplete_requests(execlists);
-
-		wait_for_guc_preempt_report(engine);
-
-		execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
-		intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0);
-	}
+	    GUC_PREEMPT_FINISHED)
+		complete_preempt_context(engine);
 
 	if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT))
 		guc_dequeue(engine);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 7c6164d14bd8..fafa0e9bd0cd 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -552,8 +552,18 @@ static void inject_preempt_context(struct intel_engine_cs *engine)
 	if (execlists->ctrl_reg)
 		writel(EL_CTRL_LOAD, execlists->ctrl_reg);
 
-	execlists_clear_active(&engine->execlists, EXECLISTS_ACTIVE_HWACK);
-	execlists_set_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT);
+	execlists_clear_active(execlists, EXECLISTS_ACTIVE_HWACK);
+	execlists_set_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
+}
+
+static void complete_preempt_context(struct intel_engine_execlists *execlists)
+{
+	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
+
+	execlists_cancel_port_requests(execlists);
+	execlists_unwind_incomplete_requests(execlists);
+
+	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
 static bool __execlists_dequeue(struct intel_engine_cs *engine)
@@ -1064,14 +1074,7 @@ static void execlists_submission_tasklet(unsigned long data)
 			if (status & GEN8_CTX_STATUS_COMPLETE &&
 			    buf[2*head + 1] == execlists->preempt_complete_status) {
 				GEM_TRACE("%s preempt-idle\n", engine->name);
-
-				execlists_cancel_port_requests(execlists);
-				execlists_unwind_incomplete_requests(execlists);
-
-				GEM_BUG_ON(!execlists_is_active(execlists,
-								EXECLISTS_ACTIVE_PREEMPT));
-				execlists_clear_active(execlists,
-						       EXECLISTS_ACTIVE_PREEMPT);
+				complete_preempt_context(execlists);
 				continue;
 			}
 
-- 
cgit v1.2.3


From 5adfb772f8ac1224fe4d651f3628a2e03190f5af Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:51 +0100
Subject: drm/i915: Move engine reset prepare/finish to backends
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation to more carefully handling incomplete preemption during
reset by execlists, we move the existing code wholesale to the backends
under a couple of new reset vfuncs.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
CC: Michel Thierry <michel.thierry@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Reviewed-by: Jeff McGee <jeff.mcgee@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c         | 38 ++++----------------------
 drivers/gpu/drm/i915/intel_lrc.c        | 47 ++++++++++++++++++++++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 23 +++++++++++++---
 drivers/gpu/drm/i915/intel_ringbuffer.h |  9 +++++--
 4 files changed, 76 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 982393907b80..abf661d40641 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3004,7 +3004,7 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 struct i915_request *
 i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 {
-	struct i915_request *request = NULL;
+	struct i915_request *request;
 
 	/*
 	 * During the reset sequence, we must prevent the engine from
@@ -3027,31 +3027,7 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 	 */
 	kthread_park(engine->breadcrumbs.signaler);
 
-	/*
-	 * Prevent request submission to the hardware until we have
-	 * completed the reset in i915_gem_reset_finish(). If a request
-	 * is completed by one engine, it may then queue a request
-	 * to a second via its execlists->tasklet *just* as we are
-	 * calling engine->init_hw() and also writing the ELSP.
-	 * Turning off the execlists->tasklet until the reset is over
-	 * prevents the race.
-	 */
-	__tasklet_disable_sync_once(&engine->execlists.tasklet);
-
-	/*
-	 * We're using worker to queue preemption requests from the tasklet in
-	 * GuC submission mode.
-	 * Even though tasklet was disabled, we may still have a worker queued.
-	 * Let's make sure that all workers scheduled before disabling the
-	 * tasklet are completed before continuing with the reset.
-	 */
-	if (engine->i915->guc.preempt_wq)
-		flush_workqueue(engine->i915->guc.preempt_wq);
-
-	if (engine->irq_seqno_barrier)
-		engine->irq_seqno_barrier(engine);
-
-	request = i915_gem_find_active_request(engine);
+	request = engine->reset.prepare(engine);
 	if (request && request->fence.error == -EIO)
 		request = ERR_PTR(-EIO); /* Previous reset failed! */
 
@@ -3202,13 +3178,8 @@ void i915_gem_reset_engine(struct intel_engine_cs *engine,
 	if (request)
 		request = i915_gem_reset_request(engine, request, stalled);
 
-	if (request) {
-		DRM_DEBUG_DRIVER("resetting %s to restart from tail of request 0x%x\n",
-				 engine->name, request->global_seqno);
-	}
-
 	/* Setup the CS to resume from the breadcrumb of the hung request */
-	engine->reset_hw(engine, request);
+	engine->reset.reset(engine, request);
 }
 
 void i915_gem_reset(struct drm_i915_private *dev_priv,
@@ -3256,7 +3227,8 @@ void i915_gem_reset(struct drm_i915_private *dev_priv,
 
 void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
 {
-	tasklet_enable(&engine->execlists.tasklet);
+	engine->reset.finish(engine);
+
 	kthread_unpark(engine->breadcrumbs.signaler);
 
 	intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index fafa0e9bd0cd..a8f2704e377c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1827,8 +1827,39 @@ static int gen9_init_render_ring(struct intel_engine_cs *engine)
 	return 0;
 }
 
-static void reset_common_ring(struct intel_engine_cs *engine,
-			      struct i915_request *request)
+static struct i915_request *
+execlists_reset_prepare(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	/*
+	 * Prevent request submission to the hardware until we have
+	 * completed the reset in i915_gem_reset_finish(). If a request
+	 * is completed by one engine, it may then queue a request
+	 * to a second via its execlists->tasklet *just* as we are
+	 * calling engine->init_hw() and also writing the ELSP.
+	 * Turning off the execlists->tasklet until the reset is over
+	 * prevents the race.
+	 */
+	__tasklet_disable_sync_once(&execlists->tasklet);
+
+	/*
+	 * We're using worker to queue preemption requests from the tasklet in
+	 * GuC submission mode.
+	 * Even though tasklet was disabled, we may still have a worker queued.
+	 * Let's make sure that all workers scheduled before disabling the
+	 * tasklet are completed before continuing with the reset.
+	 */
+	if (engine->i915->guc.preempt_wq)
+		flush_workqueue(engine->i915->guc.preempt_wq);
+
+	return i915_gem_find_active_request(engine);
+}
+
+static void execlists_reset(struct intel_engine_cs *engine,
+			    struct i915_request *request)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned long flags;
@@ -1908,6 +1939,13 @@ static void reset_common_ring(struct intel_engine_cs *engine,
 	unwind_wa_tail(request);
 }
 
+static void execlists_reset_finish(struct intel_engine_cs *engine)
+{
+	tasklet_enable(&engine->execlists.tasklet);
+
+	GEM_TRACE("%s\n", engine->name);
+}
+
 static int intel_logical_ring_emit_pdps(struct i915_request *rq)
 {
 	struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt;
@@ -2237,7 +2275,10 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 {
 	/* Default vfuncs which can be overriden by each engine. */
 	engine->init_hw = gen8_init_common_ring;
-	engine->reset_hw = reset_common_ring;
+
+	engine->reset.prepare = execlists_reset_prepare;
+	engine->reset.reset = execlists_reset;
+	engine->reset.finish = execlists_reset_finish;
 
 	engine->context_pin = execlists_context_pin;
 	engine->context_unpin = execlists_context_unpin;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 8f19349a6055..af5a178366ed 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -531,9 +531,20 @@ out:
 	return ret;
 }
 
-static void reset_ring_common(struct intel_engine_cs *engine,
-			      struct i915_request *request)
+static struct i915_request *reset_prepare(struct intel_engine_cs *engine)
 {
+	if (engine->irq_seqno_barrier)
+		engine->irq_seqno_barrier(engine);
+
+	return i915_gem_find_active_request(engine);
+}
+
+static void reset_ring(struct intel_engine_cs *engine,
+		       struct i915_request *request)
+{
+	GEM_TRACE("%s seqno=%x\n",
+		  engine->name, request ? request->global_seqno : 0);
+
 	/*
 	 * RC6 must be prevented until the reset is complete and the engine
 	 * reinitialised. If it occurs in the middle of this sequence, the
@@ -597,6 +608,10 @@ static void reset_ring_common(struct intel_engine_cs *engine,
 	}
 }
 
+static void reset_finish(struct intel_engine_cs *engine)
+{
+}
+
 static int intel_rcs_ctx_init(struct i915_request *rq)
 {
 	int ret;
@@ -2006,7 +2021,9 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv,
 	intel_ring_init_semaphores(dev_priv, engine);
 
 	engine->init_hw = init_ring_common;
-	engine->reset_hw = reset_ring_common;
+	engine->reset.prepare = reset_prepare;
+	engine->reset.reset = reset_ring;
+	engine->reset.finish = reset_finish;
 
 	engine->context_pin = intel_ring_context_pin;
 	engine->context_unpin = intel_ring_context_unpin;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 010750e8ee44..1e8bacba7754 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -423,8 +423,13 @@ struct intel_engine_cs {
 	void		(*irq_disable)(struct intel_engine_cs *engine);
 
 	int		(*init_hw)(struct intel_engine_cs *engine);
-	void		(*reset_hw)(struct intel_engine_cs *engine,
-				    struct i915_request *rq);
+
+	struct {
+		struct i915_request *(*prepare)(struct intel_engine_cs *engine);
+		void (*reset)(struct intel_engine_cs *engine,
+			      struct i915_request *rq);
+		void (*finish)(struct intel_engine_cs *engine);
+	} reset;
 
 	void		(*park)(struct intel_engine_cs *engine);
 	void		(*unpark)(struct intel_engine_cs *engine);
-- 
cgit v1.2.3


From 1329115c6c4370e93813b44084ee06610c3279bd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:52 +0100
Subject: drm/i915: Split execlists/guc reset preparations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the next patch, we will make the execlists reset prepare callback
take into account preemption by flushing the context-switch handler.
This is not applicable to the GuC submission backend, so split the two
into their own backend callbacks.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
CC: Michel Thierry <michel.thierry@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Reviewed-by: Jeff McGee <jeff.mcgee@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 34 +++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c            | 12 ++--------
 2 files changed, 36 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index ca38ac9ff4fa..637e852888ec 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -815,6 +815,37 @@ static void guc_submission_tasklet(unsigned long data)
 		guc_dequeue(engine);
 }
 
+static struct i915_request *
+guc_reset_prepare(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	/*
+	 * Prevent request submission to the hardware until we have
+	 * completed the reset in i915_gem_reset_finish(). If a request
+	 * is completed by one engine, it may then queue a request
+	 * to a second via its execlists->tasklet *just* as we are
+	 * calling engine->init_hw() and also writing the ELSP.
+	 * Turning off the execlists->tasklet until the reset is over
+	 * prevents the race.
+	 */
+	__tasklet_disable_sync_once(&execlists->tasklet);
+
+	/*
+	 * We're using worker to queue preemption requests from the tasklet in
+	 * GuC submission mode.
+	 * Even though tasklet was disabled, we may still have a worker queued.
+	 * Let's make sure that all workers scheduled before disabling the
+	 * tasklet are completed before continuing with the reset.
+	 */
+	if (engine->i915->guc.preempt_wq)
+		flush_workqueue(engine->i915->guc.preempt_wq);
+
+	return i915_gem_find_active_request(engine);
+}
+
 /*
  * Everything below here is concerned with setup & teardown, and is
  * therefore not part of the somewhat time-critical batch-submission
@@ -1275,6 +1306,9 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 			&engine->execlists;
 
 		execlists->tasklet.func = guc_submission_tasklet;
+
+		engine->reset.prepare = guc_reset_prepare;
+
 		engine->park = guc_submission_park;
 		engine->unpark = guc_submission_unpark;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index a8f2704e377c..acbdf36d1c28 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1845,16 +1845,6 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	 */
 	__tasklet_disable_sync_once(&execlists->tasklet);
 
-	/*
-	 * We're using worker to queue preemption requests from the tasklet in
-	 * GuC submission mode.
-	 * Even though tasklet was disabled, we may still have a worker queued.
-	 * Let's make sure that all workers scheduled before disabling the
-	 * tasklet are completed before continuing with the reset.
-	 */
-	if (engine->i915->guc.preempt_wq)
-		flush_workqueue(engine->i915->guc.preempt_wq);
-
 	return i915_gem_find_active_request(engine);
 }
 
@@ -2256,6 +2246,8 @@ static void execlists_set_default_submission(struct intel_engine_cs *engine)
 	engine->schedule = execlists_schedule;
 	engine->execlists.tasklet.func = execlists_submission_tasklet;
 
+	engine->reset.prepare = execlists_reset_prepare;
+
 	engine->park = NULL;
 	engine->unpark = NULL;
 
-- 
cgit v1.2.3


From 73377dbcc754f1e673b60f238c237c5e909f92b1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:53 +0100
Subject: drm/i915/execlists: Split out CSB processing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pull the CSB event processing into its own routine so that we can reuse
it during reset to flush any missed interrupts/events.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
CC: Michel Thierry <michel.thierry@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-6-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 91 +++++++++++++++++++++++-----------------
 1 file changed, 52 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index acbdf36d1c28..f38391e6431a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -958,34 +958,14 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	local_irq_restore(flags);
 }
 
-/*
- * Check the unread Context Status Buffers and manage the submission of new
- * contexts to the ELSP accordingly.
- */
-static void execlists_submission_tasklet(unsigned long data)
+static void process_csb(struct intel_engine_cs *engine)
 {
-	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
-	struct drm_i915_private *dev_priv = engine->i915;
+	struct drm_i915_private *i915 = engine->i915;
 	bool fw = false;
 
-	/*
-	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
-	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
-	 * not be relinquished until the device is idle (see
-	 * i915_gem_idle_work_handler()). As a precaution, we make sure
-	 * that all ELSP are drained i.e. we have processed the CSB,
-	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
-	 */
-	GEM_BUG_ON(!dev_priv->gt.awake);
-
-	/*
-	 * Prefer doing test_and_clear_bit() as a two stage operation to avoid
-	 * imposing the cost of a locked atomic transaction when submitting a
-	 * new request (outside of the context-switch interrupt).
-	 */
-	while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted)) {
+	do {
 		/* The HWSP contains a (cacheable) mirror of the CSB */
 		const u32 *buf =
 			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
@@ -993,28 +973,27 @@ static void execlists_submission_tasklet(unsigned long data)
 
 		if (unlikely(execlists->csb_use_mmio)) {
 			buf = (u32 * __force)
-				(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
-			execlists->csb_head = -1; /* force mmio read of CSB ptrs */
+				(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+			execlists->csb_head = -1; /* force mmio read of CSB */
 		}
 
 		/* Clear before reading to catch new interrupts */
 		clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 		smp_mb__after_atomic();
 
-		if (unlikely(execlists->csb_head == -1)) { /* following a reset */
+		if (unlikely(execlists->csb_head == -1)) { /* after a reset */
 			if (!fw) {
-				intel_uncore_forcewake_get(dev_priv,
-							   execlists->fw_domains);
+				intel_uncore_forcewake_get(i915, execlists->fw_domains);
 				fw = true;
 			}
 
-			head = readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
+			head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
 			tail = GEN8_CSB_WRITE_PTR(head);
 			head = GEN8_CSB_READ_PTR(head);
 			execlists->csb_head = head;
 		} else {
 			const int write_idx =
-				intel_hws_csb_write_index(dev_priv) -
+				intel_hws_csb_write_index(i915) -
 				I915_HWS_CSB_BUF0_INDEX;
 
 			head = execlists->csb_head;
@@ -1023,8 +1002,8 @@ static void execlists_submission_tasklet(unsigned long data)
 		}
 		GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
 			  engine->name,
-			  head, GEN8_CSB_READ_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
-			  tail, GEN8_CSB_WRITE_PTR(readl(dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
+			  head, GEN8_CSB_READ_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
+			  tail, GEN8_CSB_WRITE_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
 
 		while (head != tail) {
 			struct i915_request *rq;
@@ -1034,7 +1013,8 @@ static void execlists_submission_tasklet(unsigned long data)
 			if (++head == GEN8_CSB_ENTRIES)
 				head = 0;
 
-			/* We are flying near dragons again.
+			/*
+			 * We are flying near dragons again.
 			 *
 			 * We hold a reference to the request in execlist_port[]
 			 * but no more than that. We are operating in softirq
@@ -1143,15 +1123,48 @@ static void execlists_submission_tasklet(unsigned long data)
 		if (head != execlists->csb_head) {
 			execlists->csb_head = head;
 			writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
-			       dev_priv->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
+			       i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
 		}
-	}
+	} while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted));
 
-	if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT))
-		execlists_dequeue(engine);
+	if (unlikely(fw))
+		intel_uncore_forcewake_put(i915, execlists->fw_domains);
+}
 
-	if (fw)
-		intel_uncore_forcewake_put(dev_priv, execlists->fw_domains);
+/*
+ * Check the unread Context Status Buffers and manage the submission of new
+ * contexts to the ELSP accordingly.
+ */
+static void execlists_submission_tasklet(unsigned long data)
+{
+	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+
+	GEM_TRACE("%s awake?=%d, active=%x, irq-posted?=%d\n",
+		  engine->name,
+		  engine->i915->gt.awake,
+		  engine->execlists.active,
+		  test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted));
+
+	/*
+	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
+	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
+	 * not be relinquished until the device is idle (see
+	 * i915_gem_idle_work_handler()). As a precaution, we make sure
+	 * that all ELSP are drained i.e. we have processed the CSB,
+	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
+	 */
+	GEM_BUG_ON(!engine->i915->gt.awake);
+
+	/*
+	 * Prefer doing test_and_clear_bit() as a two stage operation to avoid
+	 * imposing the cost of a locked atomic transaction when submitting a
+	 * new request (outside of the context-switch interrupt).
+	 */
+	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
+		process_csb(engine);
+
+	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
+		execlists_dequeue(engine);
 
 	/* If the engine is now idle, so should be the flag; and vice versa. */
 	GEM_BUG_ON(execlists_is_active(&engine->execlists,
-- 
cgit v1.2.3


From 63572937cebf5d229a87fb11b201864f7d0b8171 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:54 +0100
Subject: drm/i915/execlists: Flush pending preemption events during reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Catch up with the inflight CSB events, after disabling the tasklet
before deciding which request was truly guilty of hanging the GPU.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
CC: Michel Thierry <michel.thierry@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-7-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 36 +++++++++++++++++++++++++++++++++++-
 1 file changed, 35 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f38391e6431a..a83273c66d49 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1844,6 +1844,7 @@ static struct i915_request *
 execlists_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
+	struct i915_request *request, *active;
 
 	GEM_TRACE("%s\n", engine->name);
 
@@ -1858,7 +1859,40 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	 */
 	__tasklet_disable_sync_once(&execlists->tasklet);
 
-	return i915_gem_find_active_request(engine);
+	/*
+	 * We want to flush the pending context switches, having disabled
+	 * the tasklet above, we can assume exclusive access to the execlists.
+	 * For this allows us to catch up with an inflight preemption event,
+	 * and avoid blaming an innocent request if the stall was due to the
+	 * preemption itself.
+	 */
+	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
+		process_csb(engine);
+
+	/*
+	 * The last active request can then be no later than the last request
+	 * now in ELSP[0]. So search backwards from there, so that if the GPU
+	 * has advanced beyond the last CSB update, it will be pardoned.
+	 */
+	active = NULL;
+	request = port_request(execlists->port);
+	if (request) {
+		unsigned long flags;
+
+		spin_lock_irqsave(&engine->timeline.lock, flags);
+		list_for_each_entry_from_reverse(request,
+						 &engine->timeline.requests,
+						 link) {
+			if (__i915_request_completed(request,
+						     request->global_seqno))
+				break;
+
+			active = request;
+		}
+		spin_unlock_irqrestore(&engine->timeline.lock, flags);
+	}
+
+	return active;
 }
 
 static void execlists_reset(struct intel_engine_cs *engine,
-- 
cgit v1.2.3


From 3f6e9822308127104a7bb007ca569f2c57d03b67 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 16 May 2018 19:33:55 +0100
Subject: drm/i915: Stop parking the signaler around reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We cannot call kthread_park() from softirq context, so let's avoid it
entirely during the reset. We wanted to suspend the signaler so that it
would not mark a request as complete at the same time as we marked it as
being in error. Instead of parking the signaling, stop the engine from
advancing so that the GPU doesn't emit the breadcrumb for our chosen
"guilty" request.

v2: Refactor setting STOP_RING so that we don't have the same code thrice

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michałt Winiarski <michal.winiarski@intel.com>
CC: Michel Thierry <michel.thierry@intel.com>
Cc: Jeff McGee <jeff.mcgee@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516183355.10553-8-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c         | 14 --------------
 drivers/gpu/drm/i915/intel_engine_cs.c  | 29 +++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c        |  6 ++++++
 drivers/gpu/drm/i915/intel_ringbuffer.c |  2 ++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 ++
 drivers/gpu/drm/i915/intel_uncore.c     | 12 +++---------
 6 files changed, 42 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index abf661d40641..b0fe452ce17c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3015,18 +3015,6 @@ i915_gem_reset_prepare_engine(struct intel_engine_cs *engine)
 	 */
 	intel_uncore_forcewake_get(engine->i915, FORCEWAKE_ALL);
 
-	/*
-	 * Prevent the signaler thread from updating the request
-	 * state (by calling dma_fence_signal) as we are processing
-	 * the reset. The write from the GPU of the seqno is
-	 * asynchronous and the signaler thread may see a different
-	 * value to us and declare the request complete, even though
-	 * the reset routine have picked that request as the active
-	 * (incomplete) request. This conflict is not handled
-	 * gracefully!
-	 */
-	kthread_park(engine->breadcrumbs.signaler);
-
 	request = engine->reset.prepare(engine);
 	if (request && request->fence.error == -EIO)
 		request = ERR_PTR(-EIO); /* Previous reset failed! */
@@ -3229,8 +3217,6 @@ void i915_gem_reset_finish_engine(struct intel_engine_cs *engine)
 {
 	engine->reset.finish(engine);
 
-	kthread_unpark(engine->breadcrumbs.signaler);
-
 	intel_uncore_forcewake_put(engine->i915, FORCEWAKE_ALL);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 6bfd7e3ed152..d4e159ae65a6 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -769,6 +769,35 @@ u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine)
 	return bbaddr;
 }
 
+int intel_engine_stop_cs(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	const u32 base = engine->mmio_base;
+	const i915_reg_t mode = RING_MI_MODE(base);
+	int err;
+
+	if (INTEL_GEN(dev_priv) < 3)
+		return -ENODEV;
+
+	GEM_TRACE("%s\n", engine->name);
+
+	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
+
+	err = 0;
+	if (__intel_wait_for_register_fw(dev_priv,
+					 mode, MODE_IDLE, MODE_IDLE,
+					 1000, 0,
+					 NULL)) {
+		GEM_TRACE("%s: timed out on STOP_RING -> IDLE\n", engine->name);
+		err = -ETIMEDOUT;
+	}
+
+	/* A final mmio read to let GPU writes be hopefully flushed to memory */
+	POSTING_READ_FW(mode);
+
+	return err;
+}
+
 const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 {
 	switch (type) {
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index a83273c66d49..493e6bd9e28a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1879,6 +1879,12 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	if (request) {
 		unsigned long flags;
 
+		/*
+		 * Prevent the breadcrumb from advancing before we decide
+		 * which request is currently active.
+		 */
+		intel_engine_stop_cs(engine);
+
 		spin_lock_irqsave(&engine->timeline.lock, flags);
 		list_for_each_entry_from_reverse(request,
 						 &engine->timeline.requests,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index af5a178366ed..6f200a747176 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -533,6 +533,8 @@ out:
 
 static struct i915_request *reset_prepare(struct intel_engine_cs *engine)
 {
+	intel_engine_stop_cs(engine);
+
 	if (engine->irq_seqno_barrier)
 		engine->irq_seqno_barrier(engine);
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 1e8bacba7754..61f385a92484 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -878,6 +878,8 @@ int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_blt_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_vebox_ring_buffer(struct intel_engine_cs *engine);
 
+int intel_engine_stop_cs(struct intel_engine_cs *engine);
+
 u64 intel_engine_get_active_head(const struct intel_engine_cs *engine);
 u64 intel_engine_get_last_batch_head(const struct intel_engine_cs *engine);
 
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index 448293eb638d..b36a3b5736a0 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1702,15 +1702,9 @@ static void gen3_stop_engine(struct intel_engine_cs *engine)
 {
 	struct drm_i915_private *dev_priv = engine->i915;
 	const u32 base = engine->mmio_base;
-	const i915_reg_t mode = RING_MI_MODE(base);
-
-	I915_WRITE_FW(mode, _MASKED_BIT_ENABLE(STOP_RING));
-	if (__intel_wait_for_register_fw(dev_priv,
-					 mode, MODE_IDLE, MODE_IDLE,
-					 500, 0,
-					 NULL))
-		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n",
-				 engine->name);
+
+	if (intel_engine_stop_cs(engine))
+		DRM_DEBUG_DRIVER("%s: timed out on STOP_RING\n", engine->name);
 
 	I915_WRITE_FW(RING_HEAD(base), I915_READ_FW(RING_TAIL(base)));
 	POSTING_READ_FW(RING_HEAD(base)); /* paranoia */
-- 
cgit v1.2.3


From 579e2f6d999991d2d2dd39c7185cba0a97137cee Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 15 Mar 2017 17:39:50 +0000
Subject: drm/i915/gvt: Use offsetofend() rather than offsetof + sizeof

Compute the offset of the end of the crc32 field using offsetofend()
rather than open-coding.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/firmware.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/firmware.c b/drivers/gpu/drm/i915/gvt/firmware.c
index a73e1d418c22..4ac18b447247 100644
--- a/drivers/gpu/drm/i915/gvt/firmware.c
+++ b/drivers/gpu/drm/i915/gvt/firmware.c
@@ -162,7 +162,7 @@ static int verify_firmware(struct intel_gvt *gvt,
 
 	h = (struct gvt_firmware_header *)fw->data;
 
-	crc32_start = offsetof(struct gvt_firmware_header, crc32) + 4;
+	crc32_start = offsetofend(struct gvt_firmware_header, crc32);
 	mem = fw->data + crc32_start;
 
 #define VERIFY(s, a, b) do { \
-- 
cgit v1.2.3


From 3257ec797d3a8c5232389eb1952d4451e80f3931 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@bootlin.com>
Date: Thu, 17 May 2018 15:37:59 +0200
Subject: drm/vc4: plane: Expand the lower bits by repeating the higher bits

The vc4 HVS uses an internal RGB888 representation of the frames, and will
by default expand formats using a lower depth using zeros.

This causes an issue when we try to use other compositing software such as
pixman that fill the missing bits by repeating the higher significant bits.
As such, we can't check the display output in a reliable way by doing a
software composition and an hardware one and compare both.

To prevent this, force the same behaviour so that we can do such things.

Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517133759.25626-1-maxime.ripard@bootlin.com
---
 drivers/gpu/drm/vc4/vc4_plane.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 3483c05cc3d6..6e8984aee613 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -544,6 +544,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	/* Control word */
 	vc4_dlist_write(vc4_state,
 			SCALER_CTL0_VALID |
+			VC4_SET_FIELD(SCALER_CTL0_RGBA_EXPAND_ROUND, SCALER_CTL0_RGBA_EXPAND) |
 			(format->pixel_order << SCALER_CTL0_ORDER_SHIFT) |
 			(format->hvs << SCALER_CTL0_PIXEL_FORMAT_SHIFT) |
 			VC4_SET_FIELD(tiling, SCALER_CTL0_TILING) |
-- 
cgit v1.2.3


From 5d435b46fa68c53af8dc3a69ff2936b8f17aa294 Mon Sep 17 00:00:00 2001
From: Philippe Cornu <philippe.cornu@st.com>
Date: Tue, 15 May 2018 22:37:36 +0200
Subject: drm/bridge: spelling and coding style minor fixes

Minor fixes detected with "scripts/checkpatch.pl --strict"

Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180515203736.9224-1-philippe.cornu@st.com
---
 include/drm/drm_bridge.h | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h
index 9917651a7fdd..70131ab57e8f 100644
--- a/include/drm/drm_bridge.h
+++ b/include/drm/drm_bridge.h
@@ -97,7 +97,7 @@ struct drm_bridge_funcs {
 	/**
 	 * @mode_fixup:
 	 *
-	 * This callback is used to validate and adjust a mode. The paramater
+	 * This callback is used to validate and adjust a mode. The parameter
 	 * mode is the display mode that should be fed to the next element in
 	 * the display chain, either the final &drm_connector or the next
 	 * &drm_bridge. The parameter adjusted_mode is the input mode the bridge
@@ -301,15 +301,15 @@ int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge,
 		      struct drm_bridge *previous);
 
 bool drm_bridge_mode_fixup(struct drm_bridge *bridge,
-			const struct drm_display_mode *mode,
-			struct drm_display_mode *adjusted_mode);
+			   const struct drm_display_mode *mode,
+			   struct drm_display_mode *adjusted_mode);
 enum drm_mode_status drm_bridge_mode_valid(struct drm_bridge *bridge,
 					   const struct drm_display_mode *mode);
 void drm_bridge_disable(struct drm_bridge *bridge);
 void drm_bridge_post_disable(struct drm_bridge *bridge);
 void drm_bridge_mode_set(struct drm_bridge *bridge,
-			struct drm_display_mode *mode,
-			struct drm_display_mode *adjusted_mode);
+			 struct drm_display_mode *mode,
+			 struct drm_display_mode *adjusted_mode);
 void drm_bridge_pre_enable(struct drm_bridge *bridge);
 void drm_bridge_enable(struct drm_bridge *bridge);
 
-- 
cgit v1.2.3


From 50525c332b55f899fb231d786931d0b45a3f3d41 Mon Sep 17 00:00:00 2001
From: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Date: Tue, 15 May 2018 16:59:27 +0300
Subject: drm: content-type property for HDMI connector
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Added content_type property to drm_connector_state
in order to properly handle external HDMI TV content-type setting.

v2:
 * Moved helper function which attaches content type property
   to the drm core, as was suggested.
   Removed redundant connector state initialization.

v3:
 * Removed caps in drm_content_type_enum_list.
   After some discussion it turned out that HDMI Spec 1.4
   was wrongly assuming that IT Content(itc) bit doesn't affect
   Content type states, however itc bit needs to be manupulated
   as well. In order to not expose additional property for itc,
   for sake of simplicity it was decided to bind those together
   in same "content type" property.

v4:
 * Added it_content checking in intel_digital_connector_atomic_check.
   Fixed documentation for new content type enum.

v5:
 * Moved patch revision's description to commit messages.

v6:
 * Minor naming fix for the content type enumeration string.

v7:
 * Fix parameter name for documentation and parameter alignment
   in order not to get warning. Added Content Type description to
   new HDMI connector properties section.

v8:
 * Thrown away unneeded numbers from HDMI content-type property
   description. Switch to strings desription instead of plain
   definitions.

v9:
 * Moved away hdmi specific content-type enum from
   drm_connector_state. Content type property should probably not
   be bound to any specific connector interface in
   drm_connector_state.
   Same probably should be done to hdmi_picture_aspect_ration enum
   which is also contained in drm_connector_state. Added special
   helper function to get derive hdmi specific relevant infoframe
   fields.

v10:
 * Added usage description to HDMI properties kernel doc.

v11:
 * Created centralized function for filling HDMI AVI infoframe, based
   on correspondent DRM property value.

Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180515135928.31092-2-stanislav.lisovskiy@intel.com
[vsyrjala: clean up checkpatch multiple blank lines warnings]
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 Documentation/gpu/drm-kms.rst        |   6 ++
 Documentation/gpu/kms-properties.csv |   1 +
 drivers/gpu/drm/drm_atomic.c         |   4 ++
 drivers/gpu/drm/drm_connector.c      | 113 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/drm_edid.c           |   8 +++
 include/drm/drm_connector.h          |  13 ++++
 include/drm/drm_mode_config.h        |   5 ++
 include/uapi/drm/drm_mode.h          |   7 +++
 8 files changed, 157 insertions(+)

diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 1dffd1ac4cd4..e233c2626bd0 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -517,6 +517,12 @@ Standard Connector Properties
 .. kernel-doc:: drivers/gpu/drm/drm_connector.c
    :doc: standard connector properties
 
+HDMI Specific Connector Properties
+-----------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_connector.c
+   :doc: HDMI connector properties
+
 Plane Composition Properties
 ----------------------------
 
diff --git a/Documentation/gpu/kms-properties.csv b/Documentation/gpu/kms-properties.csv
index 07ed22ea3bd6..bfde04eddd14 100644
--- a/Documentation/gpu/kms-properties.csv
+++ b/Documentation/gpu/kms-properties.csv
@@ -17,6 +17,7 @@ Owner Module/Drivers,Group,Property Name,Type,Property Values,Object attached,De
 ,Virtual GPU,“suggested X”,RANGE,"Min=0, Max=0xffffffff",Connector,property to suggest an X offset for a connector
 ,,“suggested Y”,RANGE,"Min=0, Max=0xffffffff",Connector,property to suggest an Y offset for a connector
 ,Optional,"""aspect ratio""",ENUM,"{ ""None"", ""4:3"", ""16:9"" }",Connector,TDB
+,Optional,"""content type""",ENUM,"{ ""No Data"", ""Graphics"", ""Photo"", ""Cinema"", ""Game"" }",Connector,TBD
 i915,Generic,"""Broadcast RGB""",ENUM,"{ ""Automatic"", ""Full"", ""Limited 16:235"" }",Connector,"When this property is set to Limited 16:235 and CTM is set, the hardware will be programmed with the result of the multiplication of CTM by the limited range matrix to ensure the pixels normaly in the range 0..1.0 are remapped to the range 16/255..235/255."
 ,,“audio”,ENUM,"{ ""force-dvi"", ""off"", ""auto"", ""on"" }",Connector,TBD
 ,SDVO-TV,“mode”,ENUM,"{ ""NTSC_M"", ""NTSC_J"", ""NTSC_443"", ""PAL_B"" } etc.",Connector,TBD
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index dc850b4b6e21..07fef42869aa 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1270,6 +1270,8 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 			state->link_status = val;
 	} else if (property == config->aspect_ratio_property) {
 		state->picture_aspect_ratio = val;
+	} else if (property == config->content_type_property) {
+		state->content_type = val;
 	} else if (property == connector->scaling_mode_property) {
 		state->scaling_mode = val;
 	} else if (property == connector->content_protection_property) {
@@ -1355,6 +1357,8 @@ drm_atomic_connector_get_property(struct drm_connector *connector,
 		*val = state->link_status;
 	} else if (property == config->aspect_ratio_property) {
 		*val = state->picture_aspect_ratio;
+	} else if (property == config->content_type_property) {
+		*val = state->content_type;
 	} else if (property == connector->scaling_mode_property) {
 		*val = state->scaling_mode;
 	} else if (property == connector->content_protection_property) {
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 9b9ba5d5ec0c..002b244391f9 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -720,6 +720,14 @@ static const struct drm_prop_enum_list drm_aspect_ratio_enum_list[] = {
 	{ DRM_MODE_PICTURE_ASPECT_16_9, "16:9" },
 };
 
+static const struct drm_prop_enum_list drm_content_type_enum_list[] = {
+	{ DRM_MODE_CONTENT_TYPE_NO_DATA, "No Data" },
+	{ DRM_MODE_CONTENT_TYPE_GRAPHICS, "Graphics" },
+	{ DRM_MODE_CONTENT_TYPE_PHOTO, "Photo" },
+	{ DRM_MODE_CONTENT_TYPE_CINEMA, "Cinema" },
+	{ DRM_MODE_CONTENT_TYPE_GAME, "Game" },
+};
+
 static const struct drm_prop_enum_list drm_panel_orientation_enum_list[] = {
 	{ DRM_MODE_PANEL_ORIENTATION_NORMAL,	"Normal"	},
 	{ DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP,	"Upside Down"	},
@@ -996,6 +1004,84 @@ int drm_mode_create_dvi_i_properties(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_mode_create_dvi_i_properties);
 
+/**
+ * DOC: HDMI connector properties
+ *
+ * content type (HDMI specific):
+ *	Indicates content type setting to be used in HDMI infoframes to indicate
+ *	content type for the external device, so that it adjusts it's display
+ *	settings accordingly.
+ *
+ *	The value of this property can be one of the following:
+ *
+ *	No Data:
+ *		Content type is unknown
+ *	Graphics:
+ *		Content type is graphics
+ *	Photo:
+ *		Content type is photo
+ *	Cinema:
+ *		Content type is cinema
+ *	Game:
+ *		Content type is game
+ *
+ *	Drivers can set up this property by calling
+ *	drm_connector_attach_content_type_property(). Decoding to
+ *	infoframe values is done through
+ *	drm_hdmi_get_content_type_from_property() and
+ *	drm_hdmi_get_itc_bit_from_property().
+ */
+
+/**
+ * drm_connector_attach_content_type_property - attach content-type property
+ * @connector: connector to attach content type property on.
+ *
+ * Called by a driver the first time a HDMI connector is made.
+ */
+int drm_connector_attach_content_type_property(struct drm_connector *connector)
+{
+	if (!drm_mode_create_content_type_property(connector->dev))
+		drm_object_attach_property(&connector->base,
+					   connector->dev->mode_config.content_type_property,
+					   DRM_MODE_CONTENT_TYPE_NO_DATA);
+	return 0;
+}
+EXPORT_SYMBOL(drm_connector_attach_content_type_property);
+
+
+/**
+ * drm_hdmi_avi_infoframe_content_type() - fill the HDMI AVI infoframe
+ *                                         content type information, based
+ *                                         on correspondent DRM property.
+ * @frame: HDMI AVI infoframe
+ * @conn_state: DRM display connector state
+ *
+ */
+void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame,
+					 const struct drm_connector_state *conn_state)
+{
+	switch (conn_state->content_type) {
+	case DRM_MODE_CONTENT_TYPE_GRAPHICS:
+		frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS;
+		break;
+	case DRM_MODE_CONTENT_TYPE_CINEMA:
+		frame->content_type = HDMI_CONTENT_TYPE_CINEMA;
+		break;
+	case DRM_MODE_CONTENT_TYPE_GAME:
+		frame->content_type = HDMI_CONTENT_TYPE_GAME;
+		break;
+	case DRM_MODE_CONTENT_TYPE_PHOTO:
+		frame->content_type = HDMI_CONTENT_TYPE_PHOTO;
+		break;
+	default:
+		/* Graphics is the default(0) */
+		frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS;
+	}
+
+	frame->itc = conn_state->content_type != DRM_MODE_CONTENT_TYPE_NO_DATA;
+}
+EXPORT_SYMBOL(drm_hdmi_avi_infoframe_content_type);
+
 /**
  * drm_create_tv_properties - create TV specific connector properties
  * @dev: DRM device
@@ -1260,6 +1346,33 @@ int drm_mode_create_aspect_ratio_property(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_mode_create_aspect_ratio_property);
 
+/**
+ * drm_mode_create_content_type_property - create content type property
+ * @dev: DRM device
+ *
+ * Called by a driver the first time it's needed, must be attached to desired
+ * connectors.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
+int drm_mode_create_content_type_property(struct drm_device *dev)
+{
+	if (dev->mode_config.content_type_property)
+		return 0;
+
+	dev->mode_config.content_type_property =
+		drm_property_create_enum(dev, 0, "content type",
+					 drm_content_type_enum_list,
+					 ARRAY_SIZE(drm_content_type_enum_list));
+
+	if (dev->mode_config.content_type_property == NULL)
+		return -ENOMEM;
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_mode_create_content_type_property);
+
 /**
  * drm_mode_create_suggested_offset_properties - create suggests offset properties
  * @dev: DRM device
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 40e1e24f2ff0..82f1ab09169d 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -4872,6 +4872,14 @@ drm_hdmi_avi_infoframe_from_display_mode(struct hdmi_avi_infoframe *frame,
 
 	frame->picture_aspect = HDMI_PICTURE_ASPECT_NONE;
 
+	/*
+	 * As some drivers don't support atomic, we can't use connector state.
+	 * So just initialize the frame with default values, just the same way
+	 * as it's done with other properties here.
+	 */
+	frame->content_type = HDMI_CONTENT_TYPE_GRAPHICS;
+	frame->itc = 0;
+
 	/*
 	 * Populate picture aspect ratio from either
 	 * user input (if specified) or from the CEA mode list.
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index 675cc3f8cf85..ee4c48218c85 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -418,6 +418,14 @@ struct drm_connector_state {
 	 */
 	enum hdmi_picture_aspect picture_aspect_ratio;
 
+	/**
+	 * @content_type: Connector property to control the
+	 * HDMI infoframe content type setting.
+	 * The %DRM_MODE_CONTENT_TYPE_\* values much
+	 * match the values.
+	 */
+	unsigned int content_type;
+
 	/**
 	 * @scaling_mode: Connector property to control the
 	 * upscaling, mostly used for built-in panels.
@@ -1089,11 +1097,16 @@ int drm_mode_create_tv_properties(struct drm_device *dev,
 				  unsigned int num_modes,
 				  const char * const modes[]);
 int drm_mode_create_scaling_mode_property(struct drm_device *dev);
+int drm_connector_attach_content_type_property(struct drm_connector *dev);
 int drm_connector_attach_scaling_mode_property(struct drm_connector *connector,
 					       u32 scaling_mode_mask);
 int drm_connector_attach_content_protection_property(
 		struct drm_connector *connector);
 int drm_mode_create_aspect_ratio_property(struct drm_device *dev);
+int drm_mode_create_content_type_property(struct drm_device *dev);
+void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame,
+					 const struct drm_connector_state *conn_state);
+
 int drm_mode_create_suggested_offset_properties(struct drm_device *dev);
 
 int drm_mode_connector_set_path_property(struct drm_connector *connector,
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index 33b3a96d66d0..fb45839179dd 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -726,6 +726,11 @@ struct drm_mode_config {
 	 * HDMI infoframe aspect ratio setting.
 	 */
 	struct drm_property *aspect_ratio_property;
+	/**
+	 * @content_type_property: Optional connector property to control the
+	 * HDMI infoframe content type setting.
+	 */
+	struct drm_property *content_type_property;
 	/**
 	 * @degamma_lut_property: Optional CRTC property to set the LUT used to
 	 * convert the framebuffer's colors to linear gamma.
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 4b3a1bb58e68..971c016b368c 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -96,6 +96,13 @@ extern "C" {
 #define DRM_MODE_PICTURE_ASPECT_64_27		3
 #define DRM_MODE_PICTURE_ASPECT_256_135		4
 
+/* Content type options */
+#define DRM_MODE_CONTENT_TYPE_NO_DATA		0
+#define DRM_MODE_CONTENT_TYPE_GRAPHICS		1
+#define DRM_MODE_CONTENT_TYPE_PHOTO		2
+#define DRM_MODE_CONTENT_TYPE_CINEMA		3
+#define DRM_MODE_CONTENT_TYPE_GAME		4
+
 /* Aspect ratio flag bitmask (4 bits 22:19) */
 #define DRM_MODE_FLAG_PIC_AR_MASK		(0x0F<<19)
 #define  DRM_MODE_FLAG_PIC_AR_NONE \
-- 
cgit v1.2.3


From 6553b123eae8dd117f6adb4a42e2e6ef8bff321d Mon Sep 17 00:00:00 2001
From: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Date: Tue, 15 May 2018 16:59:28 +0300
Subject: i915: content-type property for HDMI connector
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Added encoding of drm content_type property from drm_connector_state
within AVI infoframe in order to properly handle external HDMI TV
content-type setting.

This requires also manipulationg ITC bit, as stated in
HDMI spec.

v2:
 * Moved helper function which attaches content type property
   to the drm core, as was suggested.
   Removed redundant connector state initialization.

v3:
 * Removed caps in drm_content_type_enum_list.
   After some discussion it turned out that HDMI Spec 1.4
   was wrongly assuming that IT Content(itc) bit doesn't affect
   Content type states, however itc bit needs to be manupulated
   as well. In order to not expose additional property for itc,
   for sake of simplicity it was decided to bind those together
   in same "content type" property.

v4:
 * Added it_content checking in intel_digital_connector_atomic_check.
   Fixed documentation for new content type enum.

v5:
 * Moved patch revision's description to commit messages.

v6:
 * Minor naming fix for the content type enumeration string.

v7:
 * Fix parameter name for documentation and parameter alignment
   in order not to get warning. Added Content Type description to
   new HDMI connector properties section.

v8:
 * Thrown away unneeded numbers from HDMI content-type property
   description. Switch to strings desription instead of plain
   definitions.

v9:
 * Moved away hdmi specific content-type enum from
   drm_connector_state. Content type property should probably not
   be bound to any specific connector interface in
   drm_connector_state.
   Same probably should be done to hdmi_picture_aspect_ration enum
   which is also contained in drm_connector_state. Added special
   helper function to get derive hdmi specific relevant infoframe
   fields.

v10:
 * Added usage description to HDMI properties kernel doc.

v11:
 * Created centralized function for filling HDMI AVI infoframe, based
   on correspondent DRM property value.

Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180515135928.31092-3-stanislav.lisovskiy@intel.com
[vsyrjala: clean up checkpatch multiple blank lines warnings]
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_atomic.c |  1 +
 drivers/gpu/drm/i915/intel_hdmi.c   | 17 +++++++++++------
 2 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 40285d1b91b7..61ddb5871d8a 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -124,6 +124,7 @@ int intel_digital_connector_atomic_check(struct drm_connector *conn,
 	if (new_conn_state->force_audio != old_conn_state->force_audio ||
 	    new_conn_state->broadcast_rgb != old_conn_state->broadcast_rgb ||
 	    new_conn_state->base.picture_aspect_ratio != old_conn_state->base.picture_aspect_ratio ||
+	    new_conn_state->base.content_type != old_conn_state->base.content_type ||
 	    new_conn_state->base.scaling_mode != old_conn_state->base.scaling_mode)
 		crtc_state->mode_changed = true;
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ee929f31f7db..ea958ed0777d 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -461,7 +461,8 @@ static void intel_write_infoframe(struct drm_encoder *encoder,
 }
 
 static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder,
-					 const struct intel_crtc_state *crtc_state)
+					 const struct intel_crtc_state *crtc_state,
+					 const struct drm_connector_state *conn_state)
 {
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	const struct drm_display_mode *adjusted_mode =
@@ -491,6 +492,9 @@ static void intel_hdmi_set_avi_infoframe(struct drm_encoder *encoder,
 					   intel_hdmi->rgb_quant_range_selectable,
 					   is_hdmi2_sink);
 
+	drm_hdmi_avi_infoframe_content_type(&frame.avi,
+					    conn_state);
+
 	/* TODO: handle pixel repetition for YCBCR420 outputs */
 	intel_write_infoframe(encoder, crtc_state, &frame);
 }
@@ -586,7 +590,7 @@ static void g4x_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -727,7 +731,7 @@ static void ibx_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -770,7 +774,7 @@ static void cpt_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -823,7 +827,7 @@ static void vlv_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -856,7 +860,7 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 	I915_WRITE(reg, val);
 	POSTING_READ(reg);
 
-	intel_hdmi_set_avi_infoframe(encoder, crtc_state);
+	intel_hdmi_set_avi_infoframe(encoder, crtc_state, conn_state);
 	intel_hdmi_set_spd_infoframe(encoder, crtc_state);
 	intel_hdmi_set_hdmi_infoframe(encoder, crtc_state, conn_state);
 }
@@ -2065,6 +2069,7 @@ intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *c
 	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 	intel_attach_aspect_ratio_property(connector);
+	drm_connector_attach_content_type_property(connector);
 	connector->state->picture_aspect_ratio = HDMI_PICTURE_ASPECT_NONE;
 }
 
-- 
cgit v1.2.3


From 6102a8ee8ad60c51b5194e425c3cc8ce43aca384 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 14 May 2018 20:24:19 +0300
Subject: drm/i915: Clean up ADPA pipe select bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clean up the ADPA pipe select bits. To make the whole situation a bit
less ugly we'll start to share the same code between .get_hw_state()
and the port state asserts.

v2: Order the defines shift,mask,value (Jani)

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180514172423.9302-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_reg.h      | 11 +++++-----
 drivers/gpu/drm/i915/intel_crt.c     | 40 ++++++++++++++++++------------------
 drivers/gpu/drm/i915/intel_display.c | 24 +++++-----------------
 drivers/gpu/drm/i915/intel_drv.h     |  2 ++
 4 files changed, 33 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f11bb213ec07..ae3c26216996 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4133,11 +4133,12 @@ enum {
 
 #define   ADPA_DAC_ENABLE	(1<<31)
 #define   ADPA_DAC_DISABLE	0
-#define   ADPA_PIPE_SELECT_MASK	(1<<30)
-#define   ADPA_PIPE_A_SELECT	0
-#define   ADPA_PIPE_B_SELECT	(1<<30)
-#define   ADPA_PIPE_SELECT(pipe) ((pipe) << 30)
-/* CPT uses bits 29:30 for pch transcoder select */
+#define   ADPA_PIPE_SEL_SHIFT		30
+#define   ADPA_PIPE_SEL_MASK		(1<<30)
+#define   ADPA_PIPE_SEL(pipe)		((pipe) << 30)
+#define   ADPA_PIPE_SEL_SHIFT_CPT	29
+#define   ADPA_PIPE_SEL_MASK_CPT	(3<<29)
+#define   ADPA_PIPE_SEL_CPT(pipe)	((pipe) << 29)
 #define   ADPA_CRT_HOTPLUG_MASK  0x03ff0000 /* bit 25-16 */
 #define   ADPA_CRT_HOTPLUG_MONITOR_NONE  (0<<24)
 #define   ADPA_CRT_HOTPLUG_MONITOR_MASK  (3<<24)
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index de0e22322c76..211d601cd1b1 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -63,33 +63,35 @@ static struct intel_crt *intel_attached_crt(struct drm_connector *connector)
 	return intel_encoder_to_crt(intel_attached_encoder(connector));
 }
 
+bool intel_crt_port_enabled(struct drm_i915_private *dev_priv,
+			    i915_reg_t adpa_reg, enum pipe *pipe)
+{
+	u32 val;
+
+	val = I915_READ(adpa_reg);
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (HAS_PCH_CPT(dev_priv))
+		*pipe = (val & ADPA_PIPE_SEL_MASK_CPT) >> ADPA_PIPE_SEL_SHIFT_CPT;
+	else
+		*pipe = (val & ADPA_PIPE_SEL_MASK) >> ADPA_PIPE_SEL_SHIFT;
+
+	return val & ADPA_DAC_ENABLE;
+}
+
 static bool intel_crt_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crt *crt = intel_encoder_to_crt(encoder);
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
-
-	tmp = I915_READ(crt->adpa_reg);
-
-	if (!(tmp & ADPA_DAC_ENABLE))
-		goto out;
+	ret = intel_crt_port_enabled(dev_priv, crt->adpa_reg, pipe);
 
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
-
-	ret = true;
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -168,11 +170,9 @@ static void intel_crt_set_dpms(struct intel_encoder *encoder,
 	if (HAS_PCH_LPT(dev_priv))
 		; /* Those bits don't exist here */
 	else if (HAS_PCH_CPT(dev_priv))
-		adpa |= PORT_TRANS_SEL_CPT(crtc->pipe);
-	else if (crtc->pipe == 0)
-		adpa |= ADPA_PIPE_A_SELECT;
+		adpa |= ADPA_PIPE_SEL_CPT(crtc->pipe);
 	else
-		adpa |= ADPA_PIPE_B_SELECT;
+		adpa |= ADPA_PIPE_SEL(crtc->pipe);
 
 	if (!HAS_PCH_SPLIT(dev_priv))
 		I915_WRITE(BCLRPAT(crtc->pipe), 0);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index ad588d564198..6daa8d97a0aa 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1360,21 +1360,6 @@ static bool lvds_pipe_enabled(struct drm_i915_private *dev_priv,
 	return true;
 }
 
-static bool adpa_pipe_enabled(struct drm_i915_private *dev_priv,
-			      enum pipe pipe, u32 val)
-{
-	if ((val & ADPA_DAC_ENABLE) == 0)
-		return false;
-	if (HAS_PCH_CPT(dev_priv)) {
-		if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe))
-			return false;
-	} else {
-		if ((val & ADPA_PIPE_SELECT_MASK) != ADPA_PIPE_SELECT(pipe))
-			return false;
-	}
-	return true;
-}
-
 static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
 				   enum pipe pipe, i915_reg_t reg,
 				   u32 port_sel)
@@ -1405,16 +1390,17 @@ static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv,
 static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 				      enum pipe pipe)
 {
+	enum pipe port_pipe;
 	u32 val;
 
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL_B);
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL_C);
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_D, TRANS_DP_PORT_SEL_D);
 
-	val = I915_READ(PCH_ADPA);
-	I915_STATE_WARN(adpa_pipe_enabled(dev_priv, pipe, val),
-	     "PCH VGA enabled on transcoder %c, should be disabled\n",
-	     pipe_name(pipe));
+	I915_STATE_WARN(intel_crt_port_enabled(dev_priv, PCH_ADPA, &port_pipe) &&
+			port_pipe == pipe,
+			"PCH VGA enabled on transcoder %c, should be disabled\n",
+			pipe_name(pipe));
 
 	val = I915_READ(PCH_LVDS);
 	I915_STATE_WARN(lvds_pipe_enabled(dev_priv, pipe, val),
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index d7dbca1aabff..423795050970 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1377,6 +1377,8 @@ void gen9_enable_guc_interrupts(struct drm_i915_private *dev_priv);
 void gen9_disable_guc_interrupts(struct drm_i915_private *dev_priv);
 
 /* intel_crt.c */
+bool intel_crt_port_enabled(struct drm_i915_private *dev_priv,
+			    i915_reg_t adpa_reg, enum pipe *pipe);
 void intel_crt_init(struct drm_i915_private *dev_priv);
 void intel_crt_reset(struct drm_encoder *encoder);
 
-- 
cgit v1.2.3


From a44628b9293b81b53b00adbf90b3dd6e3b9dbc32 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 14 May 2018 21:28:27 +0300
Subject: drm/i915: Clean up LVDS pipe select bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clean up the LVDS pipe select bits. To make the whole situation a bit
less ugly we'll start to share the same code between .get_hw_state()
and the port state asserts.

v2: Order the defines shift,mask,value (Jani)
    Drop ruperfluous braces and whitesapce changes (Jani)
    Combine masks in compute_is_dual_link_lvds() (Jani)
v3: Fix LVDS_PIPE_SEL_MASK_CPT

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180514182827.28629-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_reg.h      |  9 ++++---
 drivers/gpu/drm/i915/intel_display.c | 33 +++++------------------
 drivers/gpu/drm/i915/intel_drv.h     |  2 ++
 drivers/gpu/drm/i915/intel_lvds.c    | 52 +++++++++++++++++++-----------------
 4 files changed, 42 insertions(+), 54 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index ae3c26216996..753b8f110e2e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4392,9 +4392,12 @@ enum {
  */
 #define   LVDS_PORT_EN			(1 << 31)
 /* Selects pipe B for LVDS data.  Must be set on pre-965. */
-#define   LVDS_PIPEB_SELECT		(1 << 30)
-#define   LVDS_PIPE_MASK		(1 << 30)
-#define   LVDS_PIPE(pipe)		((pipe) << 30)
+#define   LVDS_PIPE_SEL_SHIFT		30
+#define   LVDS_PIPE_SEL_MASK		(1 << 30)
+#define   LVDS_PIPE_SEL(pipe)		((pipe) << 30)
+#define   LVDS_PIPE_SEL_SHIFT_CPT	29
+#define   LVDS_PIPE_SEL_MASK_CPT	(3 << 29)
+#define   LVDS_PIPE_SEL_CPT(pipe)	((pipe) << 29)
 /* LVDS dithering flag on 965/g4x platform */
 #define   LVDS_ENABLE_DITHER		(1 << 25)
 /* LVDS sync polarity flags. Set to invert (i.e. negative) */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 6daa8d97a0aa..a1c6cc75f49c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1214,9 +1214,8 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 		pp_reg = PP_CONTROL(0);
 		port_sel = I915_READ(PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK;
 
-		if (port_sel == PANEL_PORT_SELECT_LVDS &&
-		    I915_READ(PCH_LVDS) & LVDS_PIPEB_SELECT)
-			panel_pipe = PIPE_B;
+		if (port_sel == PANEL_PORT_SELECT_LVDS)
+			intel_lvds_port_enabled(dev_priv, PCH_LVDS, &panel_pipe);
 		/* XXX: else fix for eDP */
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		/* presumably write lock depends on pipe, not port select */
@@ -1224,8 +1223,7 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 		panel_pipe = pipe;
 	} else {
 		pp_reg = PP_CONTROL(0);
-		if (I915_READ(LVDS) & LVDS_PIPEB_SELECT)
-			panel_pipe = PIPE_B;
+		intel_lvds_port_enabled(dev_priv, LVDS, &panel_pipe);
 	}
 
 	val = I915_READ(pp_reg);
@@ -1344,22 +1342,6 @@ static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv,
 	return true;
 }
 
-static bool lvds_pipe_enabled(struct drm_i915_private *dev_priv,
-			      enum pipe pipe, u32 val)
-{
-	if ((val & LVDS_PORT_EN) == 0)
-		return false;
-
-	if (HAS_PCH_CPT(dev_priv)) {
-		if ((val & PORT_TRANS_SEL_MASK) != PORT_TRANS_SEL_CPT(pipe))
-			return false;
-	} else {
-		if ((val & LVDS_PIPE_MASK) != LVDS_PIPE(pipe))
-			return false;
-	}
-	return true;
-}
-
 static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
 				   enum pipe pipe, i915_reg_t reg,
 				   u32 port_sel)
@@ -1391,7 +1373,6 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 				      enum pipe pipe)
 {
 	enum pipe port_pipe;
-	u32 val;
 
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL_B);
 	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL_C);
@@ -1402,10 +1383,10 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 			"PCH VGA enabled on transcoder %c, should be disabled\n",
 			pipe_name(pipe));
 
-	val = I915_READ(PCH_LVDS);
-	I915_STATE_WARN(lvds_pipe_enabled(dev_priv, pipe, val),
-	     "PCH LVDS enabled on transcoder %c, should be disabled\n",
-	     pipe_name(pipe));
+	I915_STATE_WARN(intel_lvds_port_enabled(dev_priv, PCH_LVDS, &port_pipe) &&
+			port_pipe == pipe,
+			"PCH LVDS enabled on transcoder %c, should be disabled\n",
+			pipe_name(pipe));
 
 	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIB);
 	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIC);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 423795050970..911d4960ba7a 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1824,6 +1824,8 @@ void intel_infoframe_init(struct intel_digital_port *intel_dig_port);
 
 
 /* intel_lvds.c */
+bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t lvds_reg, enum pipe *pipe);
 void intel_lvds_init(struct drm_i915_private *dev_priv);
 struct intel_encoder *intel_get_lvds_encoder(struct drm_device *dev);
 bool intel_is_dual_link_lvds(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 8691c86f579c..cc4cc8669af3 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -85,34 +85,35 @@ static struct intel_lvds_connector *to_lvds_connector(struct drm_connector *conn
 	return container_of(connector, struct intel_lvds_connector, base.base);
 }
 
+bool intel_lvds_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t lvds_reg, enum pipe *pipe)
+{
+	u32 val;
+
+	val = I915_READ(lvds_reg);
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (HAS_PCH_CPT(dev_priv))
+		*pipe = (val & LVDS_PIPE_SEL_MASK_CPT) >> LVDS_PIPE_SEL_SHIFT_CPT;
+	else
+		*pipe = (val & LVDS_PIPE_SEL_MASK) >> LVDS_PIPE_SEL_SHIFT;
+
+	return val & LVDS_PORT_EN;
+}
+
 static bool intel_lvds_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_lvds_encoder *lvds_encoder = to_lvds_encoder(&encoder->base);
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
+	ret = intel_lvds_port_enabled(dev_priv, lvds_encoder->reg, pipe);
 
-	tmp = I915_READ(lvds_encoder->reg);
-
-	if (!(tmp & LVDS_PORT_EN))
-		goto out;
-
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
-
-	ret = true;
-
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -255,14 +256,11 @@ static void intel_pre_enable_lvds(struct intel_encoder *encoder,
 	temp |= LVDS_PORT_EN | LVDS_A0A2_CLKA_POWER_UP;
 
 	if (HAS_PCH_CPT(dev_priv)) {
-		temp &= ~PORT_TRANS_SEL_MASK;
-		temp |= PORT_TRANS_SEL_CPT(pipe);
+		temp &= ~LVDS_PIPE_SEL_MASK_CPT;
+		temp |= LVDS_PIPE_SEL_CPT(pipe);
 	} else {
-		if (pipe == 1) {
-			temp |= LVDS_PIPEB_SELECT;
-		} else {
-			temp &= ~LVDS_PIPEB_SELECT;
-		}
+		temp &= ~LVDS_PIPE_SEL_MASK;
+		temp |= LVDS_PIPE_SEL(pipe);
 	}
 
 	/* set the corresponsding LVDS_BORDER bit */
@@ -908,7 +906,11 @@ static bool compute_is_dual_link_lvds(struct intel_lvds_encoder *lvds_encoder)
 	 * register is uninitialized.
 	 */
 	val = I915_READ(lvds_encoder->reg);
-	if (!(val & ~(LVDS_PIPE_MASK | LVDS_DETECTED)))
+	if (HAS_PCH_CPT(dev_priv))
+		val &= ~(LVDS_DETECTED | LVDS_PIPE_SEL_MASK_CPT);
+	else
+		val &= ~(LVDS_DETECTED | LVDS_PIPE_SEL_MASK);
+	if (val == 0)
 		val = dev_priv->vbt.bios_lvds_val;
 
 	return (val & LVDS_CLKB_POWER_MASK) == LVDS_CLKB_POWER_UP;
-- 
cgit v1.2.3


From 762034675ee7476180eb3e7fc6c7b52db71654ed Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 14 May 2018 20:24:21 +0300
Subject: drm/i915: Clean up SDVO pipe select bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clean up the SDVO pipe select bits. To make the whole situation a bit
less ugly we'll start to share the same code between .get_hw_state()
and the port state asserts.

v2: Order the defines shift,mask,value (Jani)

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180514172423.9302-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_reg.h      | 10 ++++----
 drivers/gpu/drm/i915/intel_display.c | 46 +++++++++++++-----------------------
 drivers/gpu/drm/i915/intel_drv.h     |  2 ++
 drivers/gpu/drm/i915/intel_hdmi.c    | 25 ++++----------------
 drivers/gpu/drm/i915/intel_sdvo.c    | 38 ++++++++++++++++++-----------
 5 files changed, 52 insertions(+), 69 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 753b8f110e2e..f1c83233a70a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4297,9 +4297,9 @@ enum {
 
 /* Gen 3 SDVO bits: */
 #define   SDVO_ENABLE				(1 << 31)
-#define   SDVO_PIPE_SEL(pipe)			((pipe) << 30)
+#define   SDVO_PIPE_SEL_SHIFT			30
 #define   SDVO_PIPE_SEL_MASK			(1 << 30)
-#define   SDVO_PIPE_B_SELECT			(1 << 30)
+#define   SDVO_PIPE_SEL(pipe)			((pipe) << 30)
 #define   SDVO_STALL_SELECT			(1 << 29)
 #define   SDVO_INTERRUPT_ENABLE			(1 << 26)
 /*
@@ -4339,12 +4339,14 @@ enum {
 #define   SDVOB_HOTPLUG_ENABLE			(1 << 23) /* SDVO only */
 
 /* Gen 6 (CPT) SDVO/HDMI bits: */
-#define   SDVO_PIPE_SEL_CPT(pipe)		((pipe) << 29)
+#define   SDVO_PIPE_SEL_SHIFT_CPT		29
 #define   SDVO_PIPE_SEL_MASK_CPT		(3 << 29)
+#define   SDVO_PIPE_SEL_CPT(pipe)		((pipe) << 29)
 
 /* CHV SDVO/HDMI bits: */
-#define   SDVO_PIPE_SEL_CHV(pipe)		((pipe) << 24)
+#define   SDVO_PIPE_SEL_SHIFT_CHV		24
 #define   SDVO_PIPE_SEL_MASK_CHV		(3 << 24)
+#define   SDVO_PIPE_SEL_CHV(pipe)		((pipe) << 24)
 
 
 /* DVO port control */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index a1c6cc75f49c..817d5d3f65eb 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1323,25 +1323,6 @@ static bool dp_pipe_enabled(struct drm_i915_private *dev_priv,
 	return true;
 }
 
-static bool hdmi_pipe_enabled(struct drm_i915_private *dev_priv,
-			      enum pipe pipe, u32 val)
-{
-	if ((val & SDVO_ENABLE) == 0)
-		return false;
-
-	if (HAS_PCH_CPT(dev_priv)) {
-		if ((val & SDVO_PIPE_SEL_MASK_CPT) != SDVO_PIPE_SEL_CPT(pipe))
-			return false;
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		if ((val & SDVO_PIPE_SEL_MASK_CHV) != SDVO_PIPE_SEL_CHV(pipe))
-			return false;
-	} else {
-		if ((val & SDVO_PIPE_SEL_MASK) != SDVO_PIPE_SEL(pipe))
-			return false;
-	}
-	return true;
-}
-
 static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
 				   enum pipe pipe, i915_reg_t reg,
 				   u32 port_sel)
@@ -1357,16 +1338,21 @@ static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
 }
 
 static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv,
-				     enum pipe pipe, i915_reg_t reg)
+				     enum pipe pipe, enum port port,
+				     i915_reg_t hdmi_reg)
 {
-	u32 val = I915_READ(reg);
-	I915_STATE_WARN(hdmi_pipe_enabled(dev_priv, pipe, val),
-	     "PCH HDMI (0x%08x) enabled on transcoder %c, should be disabled\n",
-	     i915_mmio_reg_offset(reg), pipe_name(pipe));
+	enum pipe port_pipe;
+	bool state;
+
+	state = intel_sdvo_port_enabled(dev_priv, hdmi_reg, &port_pipe);
+
+	I915_STATE_WARN(state && port_pipe == pipe,
+			"PCH HDMI %c enabled on transcoder %c, should be disabled\n",
+			port_name(port), pipe_name(pipe));
 
-	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && (val & SDVO_ENABLE) == 0
-	     && (val & SDVO_PIPE_B_SELECT),
-	     "IBX PCH hdmi port still using transcoder B\n");
+	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B,
+			"IBX PCH HDMI %c still using transcoder B\n",
+			port_name(port));
 }
 
 static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
@@ -1388,9 +1374,9 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 			"PCH LVDS enabled on transcoder %c, should be disabled\n",
 			pipe_name(pipe));
 
-	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIB);
-	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMIC);
-	assert_pch_hdmi_disabled(dev_priv, pipe, PCH_HDMID);
+	assert_pch_hdmi_disabled(dev_priv, pipe, PORT_B, PCH_HDMIB);
+	assert_pch_hdmi_disabled(dev_priv, pipe, PORT_C, PCH_HDMIC);
+	assert_pch_hdmi_disabled(dev_priv, pipe, PORT_D, PCH_HDMID);
 }
 
 static void _vlv_enable_pll(struct intel_crtc *crtc,
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 911d4960ba7a..12002fc77235 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -2064,6 +2064,8 @@ void intel_init_ipc(struct drm_i915_private *dev_priv);
 void intel_enable_ipc(struct drm_i915_private *dev_priv);
 
 /* intel_sdvo.c */
+bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t sdvo_reg, enum pipe *pipe);
 bool intel_sdvo_init(struct drm_i915_private *dev_priv,
 		     i915_reg_t reg, enum port port);
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ee929f31f7db..ba5ea61fb7b9 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1161,33 +1161,16 @@ static void intel_hdmi_prepare(struct intel_encoder *encoder,
 static bool intel_hdmi_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(&encoder->base);
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
-
-	tmp = I915_READ(intel_hdmi->hdmi_reg);
-
-	if (!(tmp & SDVO_ENABLE))
-		goto out;
-
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else if (IS_CHERRYVIEW(dev_priv))
-		*pipe = SDVO_PORT_TO_PIPE_CHV(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
-
-	ret = true;
+	ret = intel_sdvo_port_enabled(dev_priv, intel_hdmi->hdmi_reg, pipe);
 
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -1421,8 +1404,8 @@ static void intel_disable_hdmi(struct intel_encoder *encoder,
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 
-		temp &= ~SDVO_PIPE_B_SELECT;
-		temp |= SDVO_ENABLE;
+		temp &= ~SDVO_PIPE_SEL_MASK;
+		temp |= SDVO_ENABLE | SDVO_PIPE_SEL(PIPE_A);
 		/*
 		 * HW workaround, need to write this twice for issue
 		 * that may result in first write getting masked.
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 96e213ec202d..848b03a542d6 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1403,27 +1403,37 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector)
 		return false;
 }
 
+bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv,
+			     i915_reg_t sdvo_reg, enum pipe *pipe)
+{
+	u32 val;
+
+	val = I915_READ(sdvo_reg);
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (HAS_PCH_CPT(dev_priv))
+		*pipe = (val & SDVO_PIPE_SEL_MASK_CPT) >> SDVO_PIPE_SEL_SHIFT_CPT;
+	else if (IS_CHERRYVIEW(dev_priv))
+		*pipe = (val & SDVO_PIPE_SEL_MASK_CHV) >> SDVO_PIPE_SEL_SHIFT_CHV;
+	else
+		*pipe = (val & SDVO_PIPE_SEL_MASK) >> SDVO_PIPE_SEL_SHIFT;
+
+	return val & SDVO_ENABLE;
+}
+
 static bool intel_sdvo_get_hw_state(struct intel_encoder *encoder,
 				    enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_sdvo *intel_sdvo = to_sdvo(encoder);
 	u16 active_outputs = 0;
-	u32 tmp;
+	bool ret;
 
-	tmp = I915_READ(intel_sdvo->sdvo_reg);
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
-	if (!(tmp & SDVO_ENABLE) && (active_outputs == 0))
-		return false;
-
-	if (HAS_PCH_CPT(dev_priv))
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	else
-		*pipe = PORT_TO_PIPE(tmp);
+	ret = intel_sdvo_port_enabled(dev_priv, intel_sdvo->sdvo_reg, pipe);
 
-	return true;
+	return ret || active_outputs;
 }
 
 static void intel_sdvo_get_config(struct intel_encoder *encoder,
@@ -1550,8 +1560,8 @@ static void intel_disable_sdvo(struct intel_encoder *encoder,
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 
-		temp &= ~SDVO_PIPE_B_SELECT;
-		temp |= SDVO_ENABLE;
+		temp &= ~SDVO_PIPE_SEL_MASK;
+		temp |= SDVO_ENABLE | SDVO_PIPE_SEL(PIPE_A);
 		intel_sdvo_write_sdvox(intel_sdvo, temp);
 
 		temp &= ~SDVO_ENABLE;
-- 
cgit v1.2.3


From 4add0f6bde0506677a224e761cc9f764d24dbe96 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 14 May 2018 20:24:22 +0300
Subject: drm/i915: Clean up TV pipe select bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Parametrize the TV pipe select bits.

For consistency with the new way of doing things, let's read out the
pipe select bits even when the port is disable, even though we don't
need that behaviour for asserts in this case.

v2: Order the defines shift,mask,value (Jani)
    Clear the stale pipe select bit in load detection (Jani)

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180514172423.9302-4-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_reg.h |  4 +++-
 drivers/gpu/drm/i915/intel_tv.c | 20 ++++++--------------
 2 files changed, 9 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f1c83233a70a..dae213d4c13a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4696,7 +4696,9 @@ enum {
 /* Enables the TV encoder */
 # define TV_ENC_ENABLE			(1 << 31)
 /* Sources the TV encoder input from pipe B instead of A. */
-# define TV_ENC_PIPEB_SELECT		(1 << 30)
+# define TV_ENC_PIPE_SEL_SHIFT		30
+# define TV_ENC_PIPE_SEL_MASK		(1 << 30)
+# define TV_ENC_PIPE_SEL(pipe)		((pipe) << 30)
 /* Outputs composite video (DAC A only) */
 # define TV_ENC_OUTPUT_COMPOSITE	(0 << 28)
 /* Outputs SVideo video (DAC B/C) */
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 885fc3809f7f..99bc2368dda0 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -798,16 +798,12 @@ static struct intel_tv *intel_attached_tv(struct drm_connector *connector)
 static bool
 intel_tv_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 tmp = I915_READ(TV_CTL);
 
-	if (!(tmp & TV_ENC_ENABLE))
-		return false;
+	*pipe = (tmp & TV_ENC_PIPE_SEL_MASK) >> TV_ENC_PIPE_SEL_SHIFT;
 
-	*pipe = PORT_TO_PIPE(tmp);
-
-	return true;
+	return tmp & TV_ENC_ENABLE;
 }
 
 static void
@@ -1024,8 +1020,7 @@ static void intel_tv_pre_enable(struct intel_encoder *encoder,
 		break;
 	}
 
-	if (intel_crtc->pipe == 1)
-		tv_ctl |= TV_ENC_PIPEB_SELECT;
+	tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe);
 	tv_ctl |= tv_mode->oversample;
 
 	if (tv_mode->progressive)
@@ -1149,12 +1144,9 @@ intel_tv_detect_type(struct intel_tv *intel_tv,
 	save_tv_ctl = tv_ctl = I915_READ(TV_CTL);
 
 	/* Poll for TV detection */
-	tv_ctl &= ~(TV_ENC_ENABLE | TV_TEST_MODE_MASK);
+	tv_ctl &= ~(TV_ENC_ENABLE | TV_ENC_PIPE_SEL_MASK | TV_TEST_MODE_MASK);
 	tv_ctl |= TV_TEST_MODE_MONITOR_DETECT;
-	if (intel_crtc->pipe == 1)
-		tv_ctl |= TV_ENC_PIPEB_SELECT;
-	else
-		tv_ctl &= ~TV_ENC_PIPEB_SELECT;
+	tv_ctl |= TV_ENC_PIPE_SEL(intel_crtc->pipe);
 
 	tv_dac &= ~(TVDAC_SENSE_MASK | DAC_A_MASK | DAC_B_MASK | DAC_C_MASK);
 	tv_dac |= (TVDAC_STATE_CHG_EN |
-- 
cgit v1.2.3


From b45a258897a4a37b6cbc0bf1dc21354432f3e8c1 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 14 May 2018 20:24:23 +0300
Subject: drm/i915: Clean up DVO pipe select bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Parametrize the DVO pipe select bits.

For consistency with the new way of doing things, let's read out the
pipe select bits even when the port is disable, even though we don't
need that behaviour for asserts in this case.

v2: Order the defines shift,mask,value (Jani)

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180514172423.9302-5-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_reg.h  |  4 +++-
 drivers/gpu/drm/i915/intel_dvo.c | 13 ++++---------
 2 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index dae213d4c13a..196a0eb79272 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4357,7 +4357,9 @@ enum {
 #define _DVOC			0x61160
 #define DVOC			_MMIO(_DVOC)
 #define   DVO_ENABLE			(1 << 31)
-#define   DVO_PIPE_B_SELECT		(1 << 30)
+#define   DVO_PIPE_SEL_SHIFT		30
+#define   DVO_PIPE_SEL_MASK		(1 << 30)
+#define   DVO_PIPE_SEL(pipe)		((pipe) << 30)
 #define   DVO_PIPE_STALL_UNUSED		(0 << 28)
 #define   DVO_PIPE_STALL		(1 << 28)
 #define   DVO_PIPE_STALL_TV		(2 << 28)
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index eb0c559b2715..a86f0398570f 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -137,19 +137,15 @@ static bool intel_dvo_connector_get_hw_state(struct intel_connector *connector)
 static bool intel_dvo_get_hw_state(struct intel_encoder *encoder,
 				   enum pipe *pipe)
 {
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dvo *intel_dvo = enc_to_dvo(encoder);
 	u32 tmp;
 
 	tmp = I915_READ(intel_dvo->dev.dvo_reg);
 
-	if (!(tmp & DVO_ENABLE))
-		return false;
-
-	*pipe = PORT_TO_PIPE(tmp);
+	*pipe = (tmp & DVO_PIPE_SEL_MASK) >> DVO_PIPE_SEL_SHIFT;
 
-	return true;
+	return tmp & DVO_ENABLE;
 }
 
 static void intel_dvo_get_config(struct intel_encoder *encoder,
@@ -276,8 +272,7 @@ static void intel_dvo_pre_enable(struct intel_encoder *encoder,
 	dvo_val |= DVO_DATA_ORDER_FP | DVO_BORDER_ENABLE |
 		   DVO_BLANK_ACTIVE_HIGH;
 
-	if (pipe == 1)
-		dvo_val |= DVO_PIPE_B_SELECT;
+	dvo_val |= DVO_PIPE_SEL(pipe);
 	dvo_val |= DVO_PIPE_STALL;
 	if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
 		dvo_val |= DVO_HSYNC_ACTIVE_HIGH;
-- 
cgit v1.2.3


From 57877b70739a5d49d95bedf94218ba125e8afef3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 12:56:47 +0100
Subject: drm/i915/execlists: HWACK checking superseded checking port[0].count

The HWACK bit more generically solves the problem of resubmitting ESLP
while the hardware is still processing the current ELSP write. We no
longer need to check port[0].count itself.

References: ba74cb10c775 ("drm/i915/execlists: Delay writing to ELSP until HW has processed the previous write")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517115647.17205-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 493e6bd9e28a..ae5adad7cc63 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -612,8 +612,6 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		GEM_BUG_ON(!execlists_is_active(execlists,
 						EXECLISTS_ACTIVE_USER));
 		GEM_BUG_ON(!port_count(&port[0]));
-		if (port_count(&port[0]) > 1)
-			return false;
 
 		/*
 		 * If we write to ELSP a second time before the HW has had
-- 
cgit v1.2.3


From 96d4f03c20d04c80026b1ec3643c090cf4f0eb20 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 16:28:24 +0100
Subject: drm/i915: Nul-terminate legacy debug string
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make sure that when we don't have any scheduler attributes for the
request, the string is terminated.

Fixes: 247870ac8ea7 ("drm/i915: Build request info on stack before printk")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517152824.11619-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index d4e159ae65a6..e78c6e769e8c 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1143,7 +1143,7 @@ static void print_request(struct drm_printer *m,
 			  const char *prefix)
 {
 	const char *name = rq->fence.ops->get_timeline_name(&rq->fence);
-	char buf[80];
+	char buf[80] = "";
 	int x = 0;
 
 	x = print_sched_attr(rq->i915, &rq->sched.attr, buf, x, sizeof(buf));
-- 
cgit v1.2.3


From 560f6ad8edeaab1b14f1cb86083c7e0c1d37c749 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 16:07:27 +0100
Subject: drm/i915: Remove unused enable_cmd_parser modparam

The command parser is feature complete, stable and required by
userspace. In commit 41736a8e3331 ("drm/i915: Use the precomputed value
for whether to enable command parsing") I accidentally removed control
from the modparam, and as no one has complained, remove the left
over modparam completely!

References: 41736a8e3331 ("drm/i915: Use the precomputed value for whether to enable command parsing")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517150727.10431-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_params.c | 3 ---
 drivers/gpu/drm/i915/i915_params.h | 1 -
 2 files changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 66ea3552c63e..49fcc4679db6 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -130,9 +130,6 @@ i915_param_named_unsafe(invert_brightness, int, 0600,
 i915_param_named(disable_display, bool, 0400,
 	"Disable display (default: false)");
 
-i915_param_named_unsafe(enable_cmd_parser, bool, 0400,
-	"Enable command parsing (true=enabled [default], false=disabled)");
-
 i915_param_named(mmio_debug, int, 0600,
 	"Enable the MMIO debug code for the first N failures (default: off). "
 	"This may negatively affect performance.");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index 6684025b7af8..aebe0469ddaa 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -58,7 +58,6 @@ struct drm_printer;
 	param(unsigned int, inject_load_failure, 0) \
 	/* leave bools at the end to not create holes */ \
 	param(bool, alpha_support, IS_ENABLED(CONFIG_DRM_I915_ALPHA_SUPPORT)) \
-	param(bool, enable_cmd_parser, true) \
 	param(bool, enable_hangcheck, true) \
 	param(bool, fastboot, false) \
 	param(bool, prefault_disable, false) \
-- 
cgit v1.2.3


From 6b7a6a7b4ba12715fabde30fea96f9df3df2da93 Mon Sep 17 00:00:00 2001
From: Oscar Mateo <oscar.mateo@intel.com>
Date: Thu, 10 May 2018 14:59:55 -0700
Subject: drm/i915/icl: Read the correct Gen11 interrupt registers

Stop reading some now deprecated interrupt registers in both
debugfs and error state. Instead, read the new equivalents in the
Gen11 interrupt repartitioning scheme.

Note that the equivalent to the PM ISR & IIR cannot be read without
affecting the current state of the system, so I've opted for leaving
them out. See gen11_reset_one_iir() for more info.

v2: else if !!! (Paulo)
v3: another else if (Vinay)
v4:
  - Rebased
  - Renamed patch
  - Improved the ordering of GENs
  - Improved the printing of per-GEN info
v5: Avoid maybe-unitialized & add comment explaining the lack
    of PM ISR & IIR

Suggested-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Reviewed-by: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
[Paulo: fix commit message and coding style.]
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1525989595-18220-1-git-send-email-oscar.mateo@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c   | 33 +++++++++++++++++++++++----------
 drivers/gpu/drm/i915/i915_gpu_error.c | 11 ++++++++++-
 drivers/gpu/drm/i915/i915_gpu_error.h |  2 +-
 3 files changed, 34 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 13e7b9e4a6e6..d78beaabc051 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1162,19 +1162,28 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
-		if (IS_GEN6(dev_priv) || IS_GEN7(dev_priv)) {
-			pm_ier = I915_READ(GEN6_PMIER);
-			pm_imr = I915_READ(GEN6_PMIMR);
-			pm_isr = I915_READ(GEN6_PMISR);
-			pm_iir = I915_READ(GEN6_PMIIR);
-			pm_mask = I915_READ(GEN6_PMINTRMSK);
-		} else {
+		if (INTEL_GEN(dev_priv) >= 11) {
+			pm_ier = I915_READ(GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+			pm_imr = I915_READ(GEN11_GPM_WGBOXPERF_INTR_MASK);
+			/*
+			 * The equivalent to the PM ISR & IIR cannot be read
+			 * without affecting the current state of the system
+			 */
+			pm_isr = 0;
+			pm_iir = 0;
+		} else if (INTEL_GEN(dev_priv) >= 8) {
 			pm_ier = I915_READ(GEN8_GT_IER(2));
 			pm_imr = I915_READ(GEN8_GT_IMR(2));
 			pm_isr = I915_READ(GEN8_GT_ISR(2));
 			pm_iir = I915_READ(GEN8_GT_IIR(2));
-			pm_mask = I915_READ(GEN6_PMINTRMSK);
+		} else {
+			pm_ier = I915_READ(GEN6_PMIER);
+			pm_imr = I915_READ(GEN6_PMIMR);
+			pm_isr = I915_READ(GEN6_PMISR);
+			pm_iir = I915_READ(GEN6_PMIIR);
 		}
+		pm_mask = I915_READ(GEN6_PMINTRMSK);
+
 		seq_printf(m, "Video Turbo Mode: %s\n",
 			   yesno(rpmodectl & GEN6_RP_MEDIA_TURBO));
 		seq_printf(m, "HW control enabled: %s\n",
@@ -1182,8 +1191,12 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		seq_printf(m, "SW control enabled: %s\n",
 			   yesno((rpmodectl & GEN6_RP_MEDIA_MODE_MASK) ==
 				  GEN6_RP_MEDIA_SW_MODE));
-		seq_printf(m, "PM IER=0x%08x IMR=0x%08x ISR=0x%08x IIR=0x%08x, MASK=0x%08x\n",
-			   pm_ier, pm_imr, pm_isr, pm_iir, pm_mask);
+
+		seq_printf(m, "PM IER=0x%08x IMR=0x%08x, MASK=0x%08x\n",
+			   pm_ier, pm_imr, pm_mask);
+		if (INTEL_GEN(dev_priv) <= 10)
+			seq_printf(m, "PM ISR=0x%08x IIR=0x%08x\n",
+				   pm_isr, pm_iir);
 		seq_printf(m, "pm_intrmsk_mbz: 0x%08x\n",
 			   rps->pm_intrmsk_mbz);
 		seq_printf(m, "GT_PERF_STATUS: 0x%08x\n", gt_perf_status);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index df234dc23274..efb808272460 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1667,7 +1667,16 @@ static void capture_reg_state(struct i915_gpu_state *error)
 	}
 
 	/* 4: Everything else */
-	if (INTEL_GEN(dev_priv) >= 8) {
+	if (INTEL_GEN(dev_priv) >= 11) {
+		error->ier = I915_READ(GEN8_DE_MISC_IER);
+		error->gtier[0] = I915_READ(GEN11_RENDER_COPY_INTR_ENABLE);
+		error->gtier[1] = I915_READ(GEN11_VCS_VECS_INTR_ENABLE);
+		error->gtier[2] = I915_READ(GEN11_GUC_SG_INTR_ENABLE);
+		error->gtier[3] = I915_READ(GEN11_GPM_WGBOXPERF_INTR_ENABLE);
+		error->gtier[4] = I915_READ(GEN11_CRYPTO_RSVD_INTR_ENABLE);
+		error->gtier[5] = I915_READ(GEN11_GUNIT_CSME_INTR_ENABLE);
+		error->ngtier = 6;
+	} else if (INTEL_GEN(dev_priv) >= 8) {
 		error->ier = I915_READ(GEN8_DE_MISC_IER);
 		for (i = 0; i < 4; i++)
 			error->gtier[i] = I915_READ(GEN8_GT_IER(i));
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index dac0f8c4c1cf..58910f1dc67c 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -58,7 +58,7 @@ struct i915_gpu_state {
 	u32 eir;
 	u32 pgtbl_er;
 	u32 ier;
-	u32 gtier[4], ngtier;
+	u32 gtier[6], ngtier;
 	u32 ccid;
 	u32 derrmr;
 	u32 forcewake;
-- 
cgit v1.2.3


From c8af5274c3cbacb0905a26bcdef85901216e1134 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Wed, 2 May 2018 14:58:51 -0700
Subject: drm/i915: enable the pipe/transcoder/planes later on HSW+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For all platforms that run haswell_crtc_enable, our spec tells us to
configure the transcoder clocks and do link training before it tells
us to set pipeconf and the other pipe/transcoder/plane registers.

Starting from Icelake, we get machine hangs if we try to touch the
pipe/transcoder registers without having the clocks configured and not
having some chicken bits set. So this patch changes
haswell_crtc_enable() to issue the calls at the appropriate order
mandated by the spec.

While setting the appropriate chicken bits would also work here, it's
better if we actually program the hardware the way it is intended to
be programmed. And the chicken bit also has some theoretical downsides
that may or may not affect us. Also, correctly programming the
hardware does not prevent us from setting the chicken bits in a later
patch in case we decide to.

v2: Don't forget link training (Ville).

Cc: Arthur J Runyan <arthur.j.runyan@intel.com>
Cc: James Ausmus <james.ausmus@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180502215851.30736-1-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_display.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 817d5d3f65eb..c9ec88acad9c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5581,6 +5581,11 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	if (INTEL_GEN(dev_priv) >= 11)
 		icl_map_plls_to_ports(crtc, pipe_config, old_state);
 
+	intel_encoders_pre_enable(crtc, pipe_config, old_state);
+
+	if (!transcoder_is_dsi(cpu_transcoder))
+		intel_ddi_enable_pipe_clock(pipe_config);
+
 	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
@@ -5609,11 +5614,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 
 	intel_crtc->active = true;
 
-	intel_encoders_pre_enable(crtc, pipe_config, old_state);
-
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_enable_pipe_clock(pipe_config);
-
 	/* Display WA #1180: WaDisableScalarClockGating: glk, cnl */
 	psl_clkgate_wa = (IS_GEMINILAKE(dev_priv) || IS_CANNONLAKE(dev_priv)) &&
 			 intel_crtc->config->pch_pfit.enabled;
-- 
cgit v1.2.3


From f25a49ab8ab9c1b5587837c8a386b276403f315c Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Sat, 19 May 2018 12:28:54 +0800
Subject: drm/i915/gvt: Use vgpu_lock to protect per vgpu access

The patch set splits out 2 small locks from the original big gvt lock:
  - vgpu_lock protects per-vGPU data and logic, especially the vGPU
    trap emulation path.
  - sched_lock protects gvt scheudler structure, context schedule logic
    and vGPU's schedule data.

Use vgpu_lock to replace the gvt big lock. By doing this, the
mmio read/write trap path, vgpu virtual event emulation and other
vgpu related process, would be protected under per vgpu_lock.

v9:
  - Change commit author since the patches are improved a lot compared
    with original version.
    Original author: Pei Zhang <pei.zhang@intel.com>
  - Rebase to latest gvt-staging.
v8:
  - Correct coding and comment style.
  - Rebase to latest gvt-staging.
v7:
  - Remove gtt_lock since already proteced by gvt_lock and vgpu_lock.
  - Fix a typo in intel_gvt_deactivate_vgpu, unlock the wrong lock.
v6:
  - Rebase to latest gvt-staging.
v5:
  - Rebase to latest gvt-staging.
  - intel_vgpu_page_track_handler should use vgpu_lock.
v4:
  - Rebase to latest gvt-staging.
  - Protect vgpu->active access with vgpu_lock.
  - Do not wait gpu idle in vgpu_lock.
v3: update to latest code base
v2: add gvt->lock in function gvt_check_vblank_emulation

Performance comparison on Kabylake platform.
  - Configuration:
    Host: Ubuntu 16.04.
    Guest 1 & 2: Ubuntu 16.04.

glmark2 score comparison:
  - Configuration:
    Host: glxgears.
    Guests: glmark2.
+--------------------------------+-----------------+
| Setup                          | glmark2 score   |
+--------------------------------+-----------------+
| unified lock, iommu=on         | 58~62 (avg. 60) |
+--------------------------------+-----------------+
| unified lock, iommu=igfx_off   | 57~61 (avg. 59) |
+--------------------------------+-----------------+
| per-logic lock, iommu=on       | 60~68 (avg. 64) |
+--------------------------------+-----------------+
| per-logic lock, iommu=igfx_off | 61~67 (avg. 64) |
+--------------------------------+-----------------+

lock_stat comparison:
  - Configuration:
    Stop lock stat immediately after boot up.
    Boot 2 VM Guests.
    Run glmark2 in guests.
    Start perf lock_stat for 20 seconds and stop again.
  - Legend: c - contentions; w - waittime-avg
+------------+-----------------+-----------+---------------+------------+
|            | gvt_lock        |sched_lock | vgpu_lock     | gtt_lock   |
+ lock type; +-----------------+-----------+---------------+------------+
| iommu set  | c     | w       | c  | w    | c    | w      | c   | w    |
+------------+-------+---------+----+------+------+--------+-----+------+
| unified;   | 20697 | 839     |N/A | N/A  | N/A  | N/A    | N/A | N/A  |
| on         |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| unified;   | 21838 | 658.15  |N/A | N/A  | N/A  | N/A    | N/A | N/A  |
| igfx_off   |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| per-logic; | 1553  | 1599.96 |9458|429.97| 5846 | 274.33 | 0   | 0.00 |
| on         |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+
| per-logic; | 1911  | 1678.32 |8335|445.16| 5451 | 244.80 | 0   | 0.00 |
| igfx_off   |       |         |    |      |      |        |     |      |
+------------+-------+---------+----+------+------+--------+-----+------+

Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/display.c    | 35 ++++++++++++-----------
 drivers/gpu/drm/i915/gvt/gvt.c        |  5 +---
 drivers/gpu/drm/i915/gvt/gvt.h        |  8 ++++++
 drivers/gpu/drm/i915/gvt/handlers.c   |  4 +++
 drivers/gpu/drm/i915/gvt/mmio.c       | 12 ++++----
 drivers/gpu/drm/i915/gvt/page_track.c |  5 ++--
 drivers/gpu/drm/i915/gvt/scheduler.c  |  9 +++---
 drivers/gpu/drm/i915/gvt/vgpu.c       | 53 ++++++++++++++++++-----------------
 8 files changed, 72 insertions(+), 59 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8180e8d1e2..8e4a63c5b7d1 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -337,26 +337,28 @@ void intel_gvt_check_vblank_emulation(struct intel_gvt *gvt)
 	struct intel_gvt_irq *irq = &gvt->irq;
 	struct intel_vgpu *vgpu;
 	int pipe, id;
+	int found = false;
 
-	if (WARN_ON(!mutex_is_locked(&gvt->lock)))
-		return;
-
+	mutex_lock(&gvt->lock);
 	for_each_active_vgpu(gvt, vgpu, id) {
 		for (pipe = 0; pipe < I915_MAX_PIPES; pipe++) {
-			if (pipe_is_enabled(vgpu, pipe))
-				goto out;
+			if (pipe_is_enabled(vgpu, pipe)) {
+				found = true;
+				break;
+			}
 		}
+		if (found)
+			break;
 	}
 
 	/* all the pipes are disabled */
-	hrtimer_cancel(&irq->vblank_timer.timer);
-	return;
-
-out:
-	hrtimer_start(&irq->vblank_timer.timer,
-		ktime_add_ns(ktime_get(), irq->vblank_timer.period),
-		HRTIMER_MODE_ABS);
-
+	if (!found)
+		hrtimer_cancel(&irq->vblank_timer.timer);
+	else
+		hrtimer_start(&irq->vblank_timer.timer,
+			ktime_add_ns(ktime_get(), irq->vblank_timer.period),
+			HRTIMER_MODE_ABS);
+	mutex_unlock(&gvt->lock);
 }
 
 static void emulate_vblank_on_pipe(struct intel_vgpu *vgpu, int pipe)
@@ -393,8 +395,10 @@ static void emulate_vblank(struct intel_vgpu *vgpu)
 {
 	int pipe;
 
+	mutex_lock(&vgpu->vgpu_lock);
 	for_each_pipe(vgpu->gvt->dev_priv, pipe)
 		emulate_vblank_on_pipe(vgpu, pipe);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 /**
@@ -409,11 +413,10 @@ void intel_gvt_emulate_vblank(struct intel_gvt *gvt)
 	struct intel_vgpu *vgpu;
 	int id;
 
-	if (WARN_ON(!mutex_is_locked(&gvt->lock)))
-		return;
-
+	mutex_lock(&gvt->lock);
 	for_each_active_vgpu(gvt, vgpu, id)
 		emulate_vblank(vgpu);
+	mutex_unlock(&gvt->lock);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 61bd14fcb649..769e06c3ae23 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -271,11 +271,8 @@ static int gvt_service_thread(void *data)
 			continue;
 
 		if (test_and_clear_bit(INTEL_GVT_REQUEST_EMULATE_VBLANK,
-					(void *)&gvt->service_request)) {
-			mutex_lock(&gvt->lock);
+					(void *)&gvt->service_request))
 			intel_gvt_emulate_vblank(gvt);
-			mutex_unlock(&gvt->lock);
-		}
 
 		if (test_bit(INTEL_GVT_REQUEST_SCHED,
 				(void *)&gvt->service_request) ||
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 05d15a095310..3600553c8b56 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -170,6 +170,7 @@ struct intel_vgpu_submission {
 
 struct intel_vgpu {
 	struct intel_gvt *gvt;
+	struct mutex vgpu_lock;
 	int id;
 	unsigned long handle; /* vGPU handle used by hypervisor MPT modules */
 	bool active;
@@ -294,6 +295,9 @@ struct intel_vgpu_type {
 };
 
 struct intel_gvt {
+	/* GVT scope lock, protect GVT itself, and all resource currently
+	 * not yet protected by special locks(vgpu and scheduler lock).
+	 */
 	struct mutex lock;
 	struct drm_i915_private *dev_priv;
 	struct idr vgpu_idr;	/* vGPU IDR pool */
@@ -314,6 +318,10 @@ struct intel_gvt {
 
 	struct task_struct *service_thread;
 	wait_queue_head_t service_thread_wq;
+
+	/* service_request is always used in bit operation, we should always
+	 * use it with atomic bit ops so that no need to use gvt big lock.
+	 */
 	unsigned long service_request;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index d5e206661048..d60c2bee00fb 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -316,6 +316,7 @@ static int gdrst_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		}
 	}
 
+	/* vgpu_lock already hold by emulate mmio r/w */
 	intel_gvt_reset_vgpu_locked(vgpu, false, engine_mask);
 
 	/* sw will wait for the device to ack the reset request */
@@ -420,7 +421,10 @@ static int pipeconf_mmio_write(struct intel_vgpu *vgpu, unsigned int offset,
 		vgpu_vreg(vgpu, offset) |= I965_PIPECONF_ACTIVE;
 	else
 		vgpu_vreg(vgpu, offset) &= ~I965_PIPECONF_ACTIVE;
+	/* vgpu_lock already hold by emulate mmio r/w */
+	mutex_unlock(&vgpu->vgpu_lock);
 	intel_gvt_check_vblank_emulation(vgpu->gvt);
+	mutex_lock(&vgpu->vgpu_lock);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/mmio.c b/drivers/gpu/drm/i915/gvt/mmio.c
index e4960aff68bd..2be1be2cf49a 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.c
+++ b/drivers/gpu/drm/i915/gvt/mmio.c
@@ -67,7 +67,7 @@ static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
 		return;
 
 	gvt = vgpu->gvt;
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 	if (reg_is_mmio(gvt, offset)) {
 		if (read)
@@ -85,7 +85,7 @@ static void failsafe_emulate_mmio_rw(struct intel_vgpu *vgpu, uint64_t pa,
 			memcpy(pt, p_data, bytes);
 
 	}
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 /**
@@ -109,7 +109,7 @@ int intel_vgpu_emulate_mmio_read(struct intel_vgpu *vgpu, uint64_t pa,
 		failsafe_emulate_mmio_rw(vgpu, pa, p_data, bytes, true);
 		return 0;
 	}
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 
@@ -156,7 +156,7 @@ err:
 	gvt_vgpu_err("fail to emulate MMIO read %08x len %d\n",
 			offset, bytes);
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
 
@@ -182,7 +182,7 @@ int intel_vgpu_emulate_mmio_write(struct intel_vgpu *vgpu, uint64_t pa,
 		return 0;
 	}
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	offset = intel_vgpu_gpa_to_mmio_offset(vgpu, pa);
 
@@ -220,7 +220,7 @@ err:
 	gvt_vgpu_err("fail to emulate MMIO write %08x len %d\n", offset,
 		     bytes);
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/page_track.c b/drivers/gpu/drm/i915/gvt/page_track.c
index 53e2bd79c97d..256d0db8bbb1 100644
--- a/drivers/gpu/drm/i915/gvt/page_track.c
+++ b/drivers/gpu/drm/i915/gvt/page_track.c
@@ -157,11 +157,10 @@ int intel_vgpu_disable_page_track(struct intel_vgpu *vgpu, unsigned long gfn)
 int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa,
 		void *data, unsigned int bytes)
 {
-	struct intel_gvt *gvt = vgpu->gvt;
 	struct intel_vgpu_page_track *page_track;
 	int ret = 0;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	page_track = intel_vgpu_find_page_track(vgpu, gpa >> PAGE_SHIFT);
 	if (!page_track) {
@@ -179,6 +178,6 @@ int intel_vgpu_page_track_handler(struct intel_vgpu *vgpu, u64 gpa,
 	}
 
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index c2d183b91500..c0848dcf79c7 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -680,6 +680,7 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 	gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n",
 		ring_id, workload);
 
+	mutex_lock(&vgpu->vgpu_lock);
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
 	ret = intel_gvt_scan_and_shadow_workload(workload);
@@ -704,6 +705,7 @@ out:
 	}
 
 	mutex_unlock(&dev_priv->drm.struct_mutex);
+	mutex_unlock(&vgpu->vgpu_lock);
 	return ret;
 }
 
@@ -861,14 +863,14 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	int event;
 
 	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	/* For the workload w/ request, needs to wait for the context
 	 * switch to make sure request is completed.
 	 * For the workload w/o request, directly complete the workload.
 	 */
 	if (workload->req) {
-		struct drm_i915_private *dev_priv =
-			workload->vgpu->gvt->dev_priv;
+		struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 		struct intel_engine_cs *engine =
 			dev_priv->engine[workload->ring_id];
 		wait_event(workload->shadow_ctx_status_wq,
@@ -939,6 +941,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	if (gvt->scheduler.need_reschedule)
 		intel_gvt_request_service(gvt, INTEL_GVT_REQUEST_EVENT_SCHED);
 
+	mutex_unlock(&vgpu->vgpu_lock);
 	mutex_unlock(&gvt->lock);
 }
 
@@ -991,9 +994,7 @@ static int workload_thread(void *priv)
 			intel_uncore_forcewake_get(gvt->dev_priv,
 					FORCEWAKE_ALL);
 
-		mutex_lock(&gvt->lock);
 		ret = dispatch_workload(workload);
-		mutex_unlock(&gvt->lock);
 
 		if (ret) {
 			vgpu = workload->vgpu;
diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index bf75300c1ec1..889d10f8ee96 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -226,22 +226,20 @@ void intel_gvt_activate_vgpu(struct intel_vgpu *vgpu)
  */
 void intel_gvt_deactivate_vgpu(struct intel_vgpu *vgpu)
 {
-	struct intel_gvt *gvt = vgpu->gvt;
-
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	vgpu->active = false;
 
 	if (atomic_read(&vgpu->submission.running_workload_num)) {
-		mutex_unlock(&gvt->lock);
+		mutex_unlock(&vgpu->vgpu_lock);
 		intel_gvt_wait_vgpu_idle(vgpu);
-		mutex_lock(&gvt->lock);
+		mutex_lock(&vgpu->vgpu_lock);
 	}
 
 	intel_vgpu_stop_schedule(vgpu);
 	intel_vgpu_dmabuf_cleanup(vgpu);
 
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
 
 /**
@@ -255,14 +253,11 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 {
 	struct intel_gvt *gvt = vgpu->gvt;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 
 	WARN(vgpu->active, "vGPU is still active!\n");
 
 	intel_gvt_debugfs_remove_vgpu(vgpu);
-	idr_remove(&gvt->vgpu_idr, vgpu->id);
-	if (idr_is_empty(&gvt->vgpu_idr))
-		intel_gvt_clean_irq(gvt);
 	intel_vgpu_clean_sched_policy(vgpu);
 	intel_vgpu_clean_submission(vgpu);
 	intel_vgpu_clean_display(vgpu);
@@ -272,10 +267,16 @@ void intel_gvt_destroy_vgpu(struct intel_vgpu *vgpu)
 	intel_vgpu_free_resource(vgpu);
 	intel_vgpu_clean_mmio(vgpu);
 	intel_vgpu_dmabuf_cleanup(vgpu);
-	vfree(vgpu);
+	mutex_unlock(&vgpu->vgpu_lock);
 
+	mutex_lock(&gvt->lock);
+	idr_remove(&gvt->vgpu_idr, vgpu->id);
+	if (idr_is_empty(&gvt->vgpu_idr))
+		intel_gvt_clean_irq(gvt);
 	intel_gvt_update_vgpu_types(gvt);
 	mutex_unlock(&gvt->lock);
+
+	vfree(vgpu);
 }
 
 #define IDLE_VGPU_IDR 0
@@ -301,6 +302,7 @@ struct intel_vgpu *intel_gvt_create_idle_vgpu(struct intel_gvt *gvt)
 
 	vgpu->id = IDLE_VGPU_IDR;
 	vgpu->gvt = gvt;
+	mutex_init(&vgpu->vgpu_lock);
 
 	for (i = 0; i < I915_NUM_ENGINES; i++)
 		INIT_LIST_HEAD(&vgpu->submission.workload_q_head[i]);
@@ -327,7 +329,10 @@ out_free_vgpu:
  */
 void intel_gvt_destroy_idle_vgpu(struct intel_vgpu *vgpu)
 {
+	mutex_lock(&vgpu->vgpu_lock);
 	intel_vgpu_clean_sched_policy(vgpu);
+	mutex_unlock(&vgpu->vgpu_lock);
+
 	vfree(vgpu);
 }
 
@@ -345,8 +350,6 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (!vgpu)
 		return ERR_PTR(-ENOMEM);
 
-	mutex_lock(&gvt->lock);
-
 	ret = idr_alloc(&gvt->vgpu_idr, vgpu, IDLE_VGPU_IDR + 1, GVT_MAX_VGPU,
 		GFP_KERNEL);
 	if (ret < 0)
@@ -356,6 +359,7 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	vgpu->handle = param->handle;
 	vgpu->gvt = gvt;
 	vgpu->sched_ctl.weight = param->weight;
+	mutex_init(&vgpu->vgpu_lock);
 	INIT_LIST_HEAD(&vgpu->dmabuf_obj_list_head);
 	INIT_RADIX_TREE(&vgpu->page_track_tree, GFP_KERNEL);
 	idr_init(&vgpu->object_idr);
@@ -403,8 +407,6 @@ static struct intel_vgpu *__intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	if (ret)
 		goto out_clean_sched_policy;
 
-	mutex_unlock(&gvt->lock);
-
 	return vgpu;
 
 out_clean_sched_policy:
@@ -427,7 +429,6 @@ out_clean_idr:
 	idr_remove(&gvt->vgpu_idr, vgpu->id);
 out_free_vgpu:
 	vfree(vgpu);
-	mutex_unlock(&gvt->lock);
 	return ERR_PTR(ret);
 }
 
@@ -459,12 +460,12 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
 	param.low_gm_sz = BYTES_TO_MB(param.low_gm_sz);
 	param.high_gm_sz = BYTES_TO_MB(param.high_gm_sz);
 
+	mutex_lock(&gvt->lock);
 	vgpu = __intel_gvt_create_vgpu(gvt, &param);
-	if (IS_ERR(vgpu))
-		return vgpu;
-
-	/* calculate left instance change for types */
-	intel_gvt_update_vgpu_types(gvt);
+	if (!IS_ERR(vgpu))
+		/* calculate left instance change for types */
+		intel_gvt_update_vgpu_types(gvt);
+	mutex_unlock(&gvt->lock);
 
 	return vgpu;
 }
@@ -476,7 +477,7 @@ struct intel_vgpu *intel_gvt_create_vgpu(struct intel_gvt *gvt,
  * @engine_mask: engines to reset for GT reset
  *
  * This function is called when user wants to reset a virtual GPU through
- * device model reset or GT reset. The caller should hold the gvt lock.
+ * device model reset or GT reset. The caller should hold the vgpu lock.
  *
  * vGPU Device Model Level Reset (DMLR) simulates the PCI level reset to reset
  * the whole vGPU to default state as when it is created. This vGPU function
@@ -516,9 +517,9 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
 	 * scheduler when the reset is triggered by current vgpu.
 	 */
 	if (scheduler->current_vgpu == NULL) {
-		mutex_unlock(&gvt->lock);
+		mutex_unlock(&vgpu->vgpu_lock);
 		intel_gvt_wait_vgpu_idle(vgpu);
-		mutex_lock(&gvt->lock);
+		mutex_lock(&vgpu->vgpu_lock);
 	}
 
 	intel_vgpu_reset_submission(vgpu, resetting_eng);
@@ -558,7 +559,7 @@ void intel_gvt_reset_vgpu_locked(struct intel_vgpu *vgpu, bool dmlr,
  */
 void intel_gvt_reset_vgpu(struct intel_vgpu *vgpu)
 {
-	mutex_lock(&vgpu->gvt->lock);
+	mutex_lock(&vgpu->vgpu_lock);
 	intel_gvt_reset_vgpu_locked(vgpu, true, 0);
-	mutex_unlock(&vgpu->gvt->lock);
+	mutex_unlock(&vgpu->vgpu_lock);
 }
-- 
cgit v1.2.3


From 9a512e23f173a3598709b74d6ccf9a6616403967 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Sat, 19 May 2018 12:28:55 +0800
Subject: drm/i915/gvt: Use sched_lock to protect gvt scheduler logic.

The scheduler lock(gvt->sched_lock) is used to protect gvt
scheduler logic, including the gvt scheduler structure(gvt->scheduler
and per vgpu schedule data(vgpu->sched_data, vgpu->sched_ctl).

v9:
  - Change commit author since the patches are improved a lot compared
    with original version.
    Original author: Pei Zhang <pei.zhang@intel.com>
  - Rebase to latest gvt-staging.
v8:
  - Correct coding wqstyle.
  - Rebase to latest gvt-staging.
v7:
  - Remove gtt_lock since already proteced by gvt_lock and vgpu_lock.
v6:
  - Rebase to latest gvt-staging.
v5:
  - Rebase to latest gvt-staging.
v4:
  - Rebase to latest gvt-staging.
v3: update to latest code base

Signed-off-by: Pei Zhang <pei.zhang@intel.com>
Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gvt.c          |  1 +
 drivers/gpu/drm/i915/gvt/gvt.h          |  8 ++++++++
 drivers/gpu/drm/i915/gvt/sched_policy.c | 36 +++++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/gvt/scheduler.c    |  8 ++++----
 4 files changed, 45 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 769e06c3ae23..22a3ddff38a3 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -376,6 +376,7 @@ int intel_gvt_init_device(struct drm_i915_private *dev_priv)
 	idr_init(&gvt->vgpu_idr);
 	spin_lock_init(&gvt->scheduler.mmio_context_lock);
 	mutex_init(&gvt->lock);
+	mutex_init(&gvt->sched_lock);
 	gvt->dev_priv = dev_priv;
 
 	init_device_info(gvt);
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 3600553c8b56..362e3d506d2d 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -177,6 +177,11 @@ struct intel_vgpu {
 	bool pv_notified;
 	bool failsafe;
 	unsigned int resetting_eng;
+
+	/* Both sched_data and sched_ctl can be seen a part of the global gvt
+	 * scheduler structure. So below 2 vgpu data are protected
+	 * by sched_lock, not vgpu_lock.
+	 */
 	void *sched_data;
 	struct vgpu_sched_ctl sched_ctl;
 
@@ -299,6 +304,9 @@ struct intel_gvt {
 	 * not yet protected by special locks(vgpu and scheduler lock).
 	 */
 	struct mutex lock;
+	/* scheduler scope lock, protect gvt and vgpu schedule related data */
+	struct mutex sched_lock;
+
 	struct drm_i915_private *dev_priv;
 	struct idr vgpu_idr;	/* vGPU IDR pool */
 
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index d053cbe1dc94..09d7bb72b4ff 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -228,7 +228,7 @@ void intel_gvt_schedule(struct intel_gvt *gvt)
 	struct gvt_sched_data *sched_data = gvt->scheduler.sched_data;
 	ktime_t cur_time;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&gvt->sched_lock);
 	cur_time = ktime_get();
 
 	if (test_and_clear_bit(INTEL_GVT_REQUEST_SCHED,
@@ -244,7 +244,7 @@ void intel_gvt_schedule(struct intel_gvt *gvt)
 	vgpu_update_timeslice(gvt->scheduler.current_vgpu, cur_time);
 	tbs_sched_func(sched_data);
 
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&gvt->sched_lock);
 }
 
 static enum hrtimer_restart tbs_timer_fn(struct hrtimer *timer_data)
@@ -359,39 +359,65 @@ static struct intel_gvt_sched_policy_ops tbs_schedule_ops = {
 
 int intel_gvt_init_sched_policy(struct intel_gvt *gvt)
 {
+	int ret;
+
+	mutex_lock(&gvt->sched_lock);
 	gvt->scheduler.sched_ops = &tbs_schedule_ops;
+	ret = gvt->scheduler.sched_ops->init(gvt);
+	mutex_unlock(&gvt->sched_lock);
 
-	return gvt->scheduler.sched_ops->init(gvt);
+	return ret;
 }
 
 void intel_gvt_clean_sched_policy(struct intel_gvt *gvt)
 {
+	mutex_lock(&gvt->sched_lock);
 	gvt->scheduler.sched_ops->clean(gvt);
+	mutex_unlock(&gvt->sched_lock);
 }
 
+/* for per-vgpu scheduler policy, there are 2 per-vgpu data:
+ * sched_data, and sched_ctl. We see these 2 data as part of
+ * the global scheduler which are proteced by gvt->sched_lock.
+ * Caller should make their decision if the vgpu_lock should
+ * be hold outside.
+ */
+
 int intel_vgpu_init_sched_policy(struct intel_vgpu *vgpu)
 {
-	return vgpu->gvt->scheduler.sched_ops->init_vgpu(vgpu);
+	int ret;
+
+	mutex_lock(&vgpu->gvt->sched_lock);
+	ret = vgpu->gvt->scheduler.sched_ops->init_vgpu(vgpu);
+	mutex_unlock(&vgpu->gvt->sched_lock);
+
+	return ret;
 }
 
 void intel_vgpu_clean_sched_policy(struct intel_vgpu *vgpu)
 {
+	mutex_lock(&vgpu->gvt->sched_lock);
 	vgpu->gvt->scheduler.sched_ops->clean_vgpu(vgpu);
+	mutex_unlock(&vgpu->gvt->sched_lock);
 }
 
 void intel_vgpu_start_schedule(struct intel_vgpu *vgpu)
 {
 	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
 
+	mutex_lock(&vgpu->gvt->sched_lock);
 	if (!vgpu_data->active) {
 		gvt_dbg_core("vgpu%d: start schedule\n", vgpu->id);
 		vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);
 	}
+	mutex_unlock(&vgpu->gvt->sched_lock);
 }
 
 void intel_gvt_kick_schedule(struct intel_gvt *gvt)
 {
+	mutex_lock(&gvt->sched_lock);
 	intel_gvt_request_service(gvt, INTEL_GVT_REQUEST_EVENT_SCHED);
+	mutex_unlock(&gvt->sched_lock);
 }
 
 void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
@@ -406,6 +432,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 
 	gvt_dbg_core("vgpu%d: stop schedule\n", vgpu->id);
 
+	mutex_lock(&vgpu->gvt->sched_lock);
 	scheduler->sched_ops->stop_schedule(vgpu);
 
 	if (scheduler->next_vgpu == vgpu)
@@ -425,4 +452,5 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 		}
 	}
 	spin_unlock_bh(&scheduler->mmio_context_lock);
+	mutex_unlock(&vgpu->gvt->sched_lock);
 }
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index c0848dcf79c7..847f295e6755 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -715,7 +715,7 @@ static struct intel_vgpu_workload *pick_next_workload(
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct intel_vgpu_workload *workload = NULL;
 
-	mutex_lock(&gvt->lock);
+	mutex_lock(&gvt->sched_lock);
 
 	/*
 	 * no current vgpu / will be scheduled out / no workload
@@ -761,7 +761,7 @@ static struct intel_vgpu_workload *pick_next_workload(
 
 	atomic_inc(&workload->vgpu->submission.running_workload_num);
 out:
-	mutex_unlock(&gvt->lock);
+	mutex_unlock(&gvt->sched_lock);
 	return workload;
 }
 
@@ -862,8 +862,8 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	int event;
 
-	mutex_lock(&gvt->lock);
 	mutex_lock(&vgpu->vgpu_lock);
+	mutex_lock(&gvt->sched_lock);
 
 	/* For the workload w/ request, needs to wait for the context
 	 * switch to make sure request is completed.
@@ -941,8 +941,8 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	if (gvt->scheduler.need_reschedule)
 		intel_gvt_request_service(gvt, INTEL_GVT_REQUEST_EVENT_SCHED);
 
+	mutex_unlock(&gvt->sched_lock);
 	mutex_unlock(&vgpu->vgpu_lock);
-	mutex_unlock(&gvt->lock);
 }
 
 struct workload_thread_param {
-- 
cgit v1.2.3


From 4e0d64dba816adf18c17488d38ede67a3d0e9b40 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 22:26:30 +0100
Subject: drm/i915: Move request->ctx aside

In the next patch, we want to store the intel_context pointer inside
i915_request, as it is frequently access via a convoluted dance when
submitting the request to hw. Having two context pointers inside
i915_request leads to confusion so first rename the existing
i915_gem_context pointer to i915_request.gem_context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517212633.24934-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gvt/scheduler.c             |  4 +--
 drivers/gpu/drm/i915/i915_debugfs.c              |  4 +--
 drivers/gpu/drm/i915/i915_gem.c                  | 10 ++++----
 drivers/gpu/drm/i915/i915_gpu_error.c            | 18 ++++++++------
 drivers/gpu/drm/i915/i915_request.c              | 12 ++++-----
 drivers/gpu/drm/i915/i915_request.h              |  2 +-
 drivers/gpu/drm/i915/i915_trace.h                | 10 ++++----
 drivers/gpu/drm/i915/intel_engine_cs.c           |  2 +-
 drivers/gpu/drm/i915/intel_guc_submission.c      |  7 +++---
 drivers/gpu/drm/i915/intel_lrc.c                 | 31 +++++++++++++-----------
 drivers/gpu/drm/i915/intel_ringbuffer.c          | 12 ++++-----
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c |  5 +++-
 drivers/gpu/drm/i915/selftests/intel_lrc.c       |  2 +-
 13 files changed, 64 insertions(+), 55 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index c2d183b91500..17f9f8d7e148 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -205,7 +205,7 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 
 static inline bool is_gvt_request(struct i915_request *req)
 {
-	return i915_gem_context_force_single_submission(req->ctx);
+	return i915_gem_context_force_single_submission(req->gem_context);
 }
 
 static void save_ring_hw_state(struct intel_vgpu *vgpu, int ring_id)
@@ -305,7 +305,7 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	struct i915_request *req = workload->req;
 
 	if (IS_KABYLAKE(req->i915) &&
-	    is_inhibit_context(req->ctx, req->engine->id))
+	    is_inhibit_context(req->gem_context, req->engine->id))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/* allocate shadow ring buffer */
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index d78beaabc051..52515445ac40 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -542,8 +542,8 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 						   struct i915_request,
 						   client_link);
 		rcu_read_lock();
-		task = pid_task(request && request->ctx->pid ?
-				request->ctx->pid : file->pid,
+		task = pid_task(request && request->gem_context->pid ?
+				request->gem_context->pid : file->pid,
 				PIDTYPE_PID);
 		print_file_stats(m, task ? task->comm : "<unknown>", stats);
 		rcu_read_unlock();
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b0fe452ce17c..a20f8db5729d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3067,7 +3067,7 @@ static void skip_request(struct i915_request *request)
 static void engine_skip_context(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
-	struct i915_gem_context *hung_ctx = request->ctx;
+	struct i915_gem_context *hung_ctx = request->gem_context;
 	struct i915_timeline *timeline = request->timeline;
 	unsigned long flags;
 
@@ -3077,7 +3077,7 @@ static void engine_skip_context(struct i915_request *request)
 	spin_lock_nested(&timeline->lock, SINGLE_DEPTH_NESTING);
 
 	list_for_each_entry_continue(request, &engine->timeline.requests, link)
-		if (request->ctx == hung_ctx)
+		if (request->gem_context == hung_ctx)
 			skip_request(request);
 
 	list_for_each_entry(request, &timeline->requests, link)
@@ -3123,11 +3123,11 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 	}
 
 	if (stalled) {
-		i915_gem_context_mark_guilty(request->ctx);
+		i915_gem_context_mark_guilty(request->gem_context);
 		skip_request(request);
 
 		/* If this context is now banned, skip all pending requests. */
-		if (i915_gem_context_is_banned(request->ctx))
+		if (i915_gem_context_is_banned(request->gem_context))
 			engine_skip_context(request);
 	} else {
 		/*
@@ -3137,7 +3137,7 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 		 */
 		request = i915_gem_find_active_request(engine);
 		if (request) {
-			i915_gem_context_mark_innocent(request->ctx);
+			i915_gem_context_mark_innocent(request->gem_context);
 			dma_fence_set_error(&request->fence, -EAGAIN);
 
 			/* Rewind the engine to replay the incomplete rq */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index efb808272460..37c9a42654ba 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1287,9 +1287,11 @@ static void error_record_engine_registers(struct i915_gpu_state *error,
 static void record_request(struct i915_request *request,
 			   struct drm_i915_error_request *erq)
 {
-	erq->context = request->ctx->hw_id;
+	struct i915_gem_context *ctx = request->gem_context;
+
+	erq->context = ctx->hw_id;
 	erq->sched_attr = request->sched.attr;
-	erq->ban_score = atomic_read(&request->ctx->ban_score);
+	erq->ban_score = atomic_read(&ctx->ban_score);
 	erq->seqno = request->global_seqno;
 	erq->jiffies = request->emitted_jiffies;
 	erq->start = i915_ggtt_offset(request->ring->vma);
@@ -1297,7 +1299,7 @@ static void record_request(struct i915_request *request,
 	erq->tail = request->tail;
 
 	rcu_read_lock();
-	erq->pid = request->ctx->pid ? pid_nr(request->ctx->pid) : 0;
+	erq->pid = ctx->pid ? pid_nr(ctx->pid) : 0;
 	rcu_read_unlock();
 }
 
@@ -1461,12 +1463,12 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 		request = i915_gem_find_active_request(engine);
 		if (request) {
+			struct i915_gem_context *ctx = request->gem_context;
 			struct intel_ring *ring;
 
-			ee->vm = request->ctx->ppgtt ?
-				&request->ctx->ppgtt->base : &ggtt->base;
+			ee->vm = ctx->ppgtt ? &ctx->ppgtt->base : &ggtt->base;
 
-			record_context(&ee->context, request->ctx);
+			record_context(&ee->context, ctx);
 
 			/* We need to copy these to an anonymous buffer
 			 * as the simplest method to avoid being overwritten
@@ -1483,11 +1485,11 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 			ee->ctx =
 				i915_error_object_create(i915,
-							 to_intel_context(request->ctx,
+							 to_intel_context(ctx,
 									  engine)->state);
 
 			error->simulated |=
-				i915_gem_context_no_error_capture(request->ctx);
+				i915_gem_context_no_error_capture(ctx);
 
 			ee->rq_head = request->head;
 			ee->rq_post = request->postfix;
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 8928894dd9c7..fe8810a6a339 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -384,7 +384,7 @@ static void __retire_engine_request(struct intel_engine_cs *engine,
 	 */
 	if (engine->last_retired_context)
 		intel_context_unpin(engine->last_retired_context, engine);
-	engine->last_retired_context = rq->ctx;
+	engine->last_retired_context = rq->gem_context;
 }
 
 static void __retire_engine_upto(struct intel_engine_cs *engine,
@@ -455,8 +455,8 @@ static void i915_request_retire(struct i915_request *request)
 	i915_request_remove_from_client(request);
 
 	/* Retirement decays the ban score as it is a sign of ctx progress */
-	atomic_dec_if_positive(&request->ctx->ban_score);
-	intel_context_unpin(request->ctx, request->engine);
+	atomic_dec_if_positive(&request->gem_context->ban_score);
+	intel_context_unpin(request->gem_context, request->engine);
 
 	__retire_engine_upto(request->engine, request);
 
@@ -760,7 +760,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	INIT_LIST_HEAD(&rq->active_list);
 	rq->i915 = i915;
 	rq->engine = engine;
-	rq->ctx = ctx;
+	rq->gem_context = ctx;
 	rq->ring = ring;
 	rq->timeline = ring->timeline;
 	GEM_BUG_ON(rq->timeline == &engine->timeline);
@@ -814,7 +814,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		goto err_unwind;
 
 	/* Keep a second pin for the dual retirement along engine and ring */
-	__intel_context_pin(rq->ctx, engine);
+	__intel_context_pin(rq->gem_context, engine);
 
 	/* Check that we didn't interrupt ourselves with a new request */
 	GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno);
@@ -1113,7 +1113,7 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	local_bh_disable();
 	rcu_read_lock(); /* RCU serialisation for set-wedged protection */
 	if (engine->schedule)
-		engine->schedule(request, &request->ctx->sched);
+		engine->schedule(request, &request->gem_context->sched);
 	rcu_read_unlock();
 	i915_sw_fence_commit(&request->submit);
 	local_bh_enable(); /* Kick the execlists tasklet if just scheduled */
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index eddbd4245cb3..dddecd9ffd0c 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -93,7 +93,7 @@ struct i915_request {
 	 * i915_request_free() will then decrement the refcount on the
 	 * context.
 	 */
-	struct i915_gem_context *ctx;
+	struct i915_gem_context *gem_context;
 	struct intel_engine_cs *engine;
 	struct intel_ring *ring;
 	struct i915_timeline *timeline;
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 8cc3a256f29d..5d4f78765083 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -624,7 +624,7 @@ TRACE_EVENT(i915_request_queue,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
+			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->ring = rq->engine->id;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
@@ -651,7 +651,7 @@ DECLARE_EVENT_CLASS(i915_request,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
+			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->ring = rq->engine->id;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
@@ -696,7 +696,7 @@ TRACE_EVENT(i915_request_in,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
+			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->ring = rq->engine->id;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
@@ -727,7 +727,7 @@ TRACE_EVENT(i915_request_out,
 
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
+			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->ring = rq->engine->id;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
@@ -815,7 +815,7 @@ TRACE_EVENT(i915_request_wait_begin,
 	     */
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
-			   __entry->hw_id = rq->ctx->hw_id;
+			   __entry->hw_id = rq->gem_context->hw_id;
 			   __entry->ring = rq->engine->id;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index e78c6e769e8c..7983b8a1ad44 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1020,7 +1020,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 */
 	rq = __i915_gem_active_peek(&engine->timeline.last_request);
 	if (rq)
-		return rq->ctx == kernel_context;
+		return rq->gem_context == kernel_context;
 	else
 		return engine->last_retired_context == kernel_context;
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 637e852888ec..a432a193f3c4 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -513,8 +513,9 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	struct intel_guc_client *client = guc->execbuf_client;
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc = lower_32_bits(intel_lr_context_descriptor(rq->ctx,
-								 engine));
+	u32 ctx_desc =
+		lower_32_bits(intel_lr_context_descriptor(rq->gem_context,
+							  engine));
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
 	spin_lock(&client->wq_lock);
@@ -725,7 +726,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 		struct i915_request *rq, *rn;
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
-			if (last && rq->ctx != last->ctx) {
+			if (last && rq->gem_context != last->gem_context) {
 				if (port == last_port) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ae5adad7cc63..1e9cc55d785c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -418,9 +418,10 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce = to_intel_context(rq->ctx, rq->engine);
+	struct intel_context *ce =
+		to_intel_context(rq->gem_context, rq->engine);
 	struct i915_hw_ppgtt *ppgtt =
-		rq->ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
+		rq->gem_context->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
 	u32 *reg_state = ce->lrc_reg_state;
 
 	reg_state[CTX_RING_TAIL+1] = intel_ring_set_tail(rq->ring, rq->tail);
@@ -679,7 +680,8 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 			 * second request, and so we never need to tell the
 			 * hardware about the first.
 			 */
-			if (last && !can_merge_ctx(rq->ctx, last->ctx)) {
+			if (last && !can_merge_ctx(rq->gem_context,
+						   last->gem_context)) {
 				/*
 				 * If we are on the second port and cannot
 				 * combine this request with the last, then we
@@ -698,14 +700,14 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 				 * the same context (even though a different
 				 * request) to the second port.
 				 */
-				if (ctx_single_port_submission(last->ctx) ||
-				    ctx_single_port_submission(rq->ctx)) {
+				if (ctx_single_port_submission(last->gem_context) ||
+				    ctx_single_port_submission(rq->gem_context)) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);
 					goto done;
 				}
 
-				GEM_BUG_ON(last->ctx == rq->ctx);
+				GEM_BUG_ON(last->gem_context == rq->gem_context);
 
 				if (submit)
 					port_assign(port, last);
@@ -1437,7 +1439,7 @@ static void execlists_context_unpin(struct intel_engine_cs *engine,
 static int execlists_request_alloc(struct i915_request *request)
 {
 	struct intel_context *ce =
-		to_intel_context(request->ctx, request->engine);
+		to_intel_context(request->gem_context, request->engine);
 	int ret;
 
 	GEM_BUG_ON(!ce->pin_count);
@@ -1954,7 +1956,7 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	 * future request will be after userspace has had the opportunity
 	 * to recreate its own state.
 	 */
-	regs = to_intel_context(request->ctx, engine)->lrc_reg_state;
+	regs = to_intel_context(request->gem_context, engine)->lrc_reg_state;
 	if (engine->default_state) {
 		void *defaults;
 
@@ -1967,7 +1969,8 @@ static void execlists_reset(struct intel_engine_cs *engine,
 			i915_gem_object_unpin_map(engine->default_state);
 		}
 	}
-	execlists_init_reg_state(regs, request->ctx, engine, request->ring);
+	execlists_init_reg_state(regs,
+				 request->gem_context, engine, request->ring);
 
 	/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
 	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma);
@@ -1989,7 +1992,7 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 
 static int intel_logical_ring_emit_pdps(struct i915_request *rq)
 {
-	struct i915_hw_ppgtt *ppgtt = rq->ctx->ppgtt;
+	struct i915_hw_ppgtt *ppgtt = rq->gem_context->ppgtt;
 	struct intel_engine_cs *engine = rq->engine;
 	const int num_lri_cmds = GEN8_3LVL_PDPES * 2;
 	u32 *cs;
@@ -2028,15 +2031,15 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 	 * it is unsafe in case of lite-restore (because the ctx is
 	 * not idle). PML4 is allocated during ppgtt init so this is
 	 * not needed in 48-bit.*/
-	if (rq->ctx->ppgtt &&
-	    (intel_engine_flag(rq->engine) & rq->ctx->ppgtt->pd_dirty_rings) &&
-	    !i915_vm_is_48bit(&rq->ctx->ppgtt->base) &&
+	if (rq->gem_context->ppgtt &&
+	    (intel_engine_flag(rq->engine) & rq->gem_context->ppgtt->pd_dirty_rings) &&
+	    !i915_vm_is_48bit(&rq->gem_context->ppgtt->base) &&
 	    !intel_vgpu_active(rq->i915)) {
 		ret = intel_logical_ring_emit_pdps(rq);
 		if (ret)
 			return ret;
 
-		rq->ctx->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine);
+		rq->gem_context->ppgtt->pd_dirty_rings &= ~intel_engine_flag(rq->engine);
 	}
 
 	cs = intel_ring_begin(rq, 6);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 6f200a747176..53703012ec75 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -571,8 +571,8 @@ static void reset_ring(struct intel_engine_cs *engine,
 	 */
 	if (request) {
 		struct drm_i915_private *dev_priv = request->i915;
-		struct intel_context *ce = to_intel_context(request->ctx,
-							    engine);
+		struct intel_context *ce =
+			to_intel_context(request->gem_context, engine);
 		struct i915_hw_ppgtt *ppgtt;
 
 		if (ce->state) {
@@ -584,7 +584,7 @@ static void reset_ring(struct intel_engine_cs *engine,
 				   CCID_EN);
 		}
 
-		ppgtt = request->ctx->ppgtt ?: engine->i915->mm.aliasing_ppgtt;
+		ppgtt = request->gem_context->ppgtt ?: engine->i915->mm.aliasing_ppgtt;
 		if (ppgtt) {
 			u32 pd_offset = ppgtt->pd.base.ggtt_offset << 10;
 
@@ -1458,7 +1458,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(to_intel_context(rq->ctx, engine)->state) | flags;
+	*cs++ = i915_ggtt_offset(to_intel_context(rq->gem_context, engine)->state) | flags;
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -1526,7 +1526,7 @@ static int remap_l3(struct i915_request *rq, int slice)
 static int switch_context(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	struct i915_gem_context *to_ctx = rq->ctx;
+	struct i915_gem_context *to_ctx = rq->gem_context;
 	struct i915_hw_ppgtt *to_mm =
 		to_ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
 	struct i915_gem_context *from_ctx = engine->legacy_active_context;
@@ -1597,7 +1597,7 @@ static int ring_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!to_intel_context(request->ctx, request->engine)->pin_count);
+	GEM_BUG_ON(!to_intel_context(request->gem_context, request->engine)->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 438e0b045a2c..2c4e77c050dc 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -105,7 +105,10 @@ static int emit_recurse_batch(struct hang *h,
 			      struct i915_request *rq)
 {
 	struct drm_i915_private *i915 = h->i915;
-	struct i915_address_space *vm = rq->ctx->ppgtt ? &rq->ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		rq->gem_context->ppgtt ?
+		&rq->gem_context->ppgtt->base :
+		&i915->ggtt.base;
 	struct i915_vma *hws, *vma;
 	unsigned int flags;
 	u32 *batch;
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index 1b8a07125150..68cb9126b3e1 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -83,7 +83,7 @@ static int emit_recurse_batch(struct spinner *spin,
 			      struct i915_request *rq,
 			      u32 arbitration_command)
 {
-	struct i915_address_space *vm = &rq->ctx->ppgtt->base;
+	struct i915_address_space *vm = &rq->gem_context->ppgtt->base;
 	struct i915_vma *hws, *vma;
 	u32 *batch;
 	int err;
-- 
cgit v1.2.3


From 01278cb143955f4b592568d1756f1baf506245c2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 22:26:31 +0100
Subject: drm/i915: Move fiddling with engine->last_retired_context

Move the knowledge about resetting the current context tracking on the
engine from inside i915_gem_context.c into intel_engine_cs.c

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517212633.24934-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_context.c | 12 ++----------
 drivers/gpu/drm/i915/intel_engine_cs.c  | 23 +++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 3 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 4bf18b5c6f1d..9e70f4dfa703 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -514,16 +514,8 @@ void i915_gem_contexts_lost(struct drm_i915_private *dev_priv)
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	for_each_engine(engine, dev_priv, id) {
-		engine->legacy_active_context = NULL;
-		engine->legacy_active_ppgtt = NULL;
-
-		if (!engine->last_retired_context)
-			continue;
-
-		intel_context_unpin(engine->last_retired_context, engine);
-		engine->last_retired_context = NULL;
-	}
+	for_each_engine(engine, dev_priv, id)
+		intel_engine_lost_context(engine);
 }
 
 void i915_gem_contexts_fini(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 7983b8a1ad44..9e618aab6568 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1096,6 +1096,29 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	}
 }
 
+/**
+ * intel_engine_lost_context: called when the GPU is reset into unknown state
+ * @engine: the engine
+ *
+ * We have either reset the GPU or otherwise about to lose state tracking of
+ * the current GPU logical state (e.g. suspend). On next use, it is therefore
+ * imperative that we make no presumptions about the current state and load
+ * from scratch.
+ */
+void intel_engine_lost_context(struct intel_engine_cs *engine)
+{
+	struct i915_gem_context *ctx;
+
+	lockdep_assert_held(&engine->i915->drm.struct_mutex);
+
+	engine->legacy_active_context = NULL;
+	engine->legacy_active_ppgtt = NULL;
+
+	ctx = fetch_and_zero(&engine->last_retired_context);
+	if (ctx)
+		intel_context_unpin(ctx, engine);
+}
+
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
 {
 	switch (INTEL_GEN(engine->i915)) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 61f385a92484..2b16185e36c4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -1053,6 +1053,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 
 bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine);
+void intel_engine_lost_context(struct intel_engine_cs *engine);
 
 void intel_engines_park(struct drm_i915_private *i915);
 void intel_engines_unpark(struct drm_i915_private *i915);
-- 
cgit v1.2.3


From 1fc44d9b1afb0afe46acd99bdfdf793805a850e1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 22:26:32 +0100
Subject: drm/i915: Store a pointer to intel_context in i915_request

To ease the frequent and ugly pointer dance of
&request->gem_context->engine[request->engine->id] during request
submission, store that pointer as request->hw_context. One major
advantage that we will exploit later is that this decouples the logical
context state from the engine itself.

v2: Set mock_context->ops so we don't crash and burn in selftests.
    Cleanups from Tvrtko.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517212633.24934-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gvt/mmio_context.c       |   6 +-
 drivers/gpu/drm/i915/gvt/mmio_context.h       |   2 +-
 drivers/gpu/drm/i915/gvt/scheduler.c          | 141 ++++++++++----------------
 drivers/gpu/drm/i915/gvt/scheduler.h          |   1 -
 drivers/gpu/drm/i915/i915_drv.h               |   1 +
 drivers/gpu/drm/i915/i915_gem.c               |  12 +--
 drivers/gpu/drm/i915/i915_gem_context.c       |  17 ++--
 drivers/gpu/drm/i915/i915_gem_context.h       |  21 ++--
 drivers/gpu/drm/i915/i915_gpu_error.c         |   3 +-
 drivers/gpu/drm/i915/i915_perf.c              |  25 ++---
 drivers/gpu/drm/i915/i915_request.c           |  34 +++----
 drivers/gpu/drm/i915/i915_request.h           |   1 +
 drivers/gpu/drm/i915/intel_engine_cs.c        |  54 ++++++----
 drivers/gpu/drm/i915/intel_guc_submission.c   |  10 +-
 drivers/gpu/drm/i915/intel_lrc.c              | 125 +++++++++++++----------
 drivers/gpu/drm/i915/intel_lrc.h              |   7 --
 drivers/gpu/drm/i915/intel_ringbuffer.c       | 100 +++++++++++-------
 drivers/gpu/drm/i915/intel_ringbuffer.h       |   9 +-
 drivers/gpu/drm/i915/selftests/mock_context.c |   7 ++
 drivers/gpu/drm/i915/selftests/mock_engine.c  |  41 +++++---
 20 files changed, 321 insertions(+), 296 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 0f949554d118..708170e61625 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -446,9 +446,9 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 
 #define CTX_CONTEXT_CONTROL_VAL	0x03
 
-bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id)
+bool is_inhibit_context(struct intel_context *ce)
 {
-	u32 *reg_state = ctx->__engine[ring_id].lrc_reg_state;
+	const u32 *reg_state = ce->lrc_reg_state;
 	u32 inhibit_mask =
 		_MASKED_BIT_ENABLE(CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT);
 
@@ -501,7 +501,7 @@ static void switch_mmio(struct intel_vgpu *pre,
 			 * itself.
 			 */
 			if (mmio->in_context &&
-			    !is_inhibit_context(s->shadow_ctx, ring_id))
+			    !is_inhibit_context(&s->shadow_ctx->__engine[ring_id]))
 				continue;
 
 			if (mmio->mask)
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.h b/drivers/gpu/drm/i915/gvt/mmio_context.h
index 0439eb8057a8..5c3b9ff9f96a 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.h
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.h
@@ -49,7 +49,7 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre,
 
 void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt);
 
-bool is_inhibit_context(struct i915_gem_context *ctx, int ring_id);
+bool is_inhibit_context(struct intel_context *ce);
 
 int intel_vgpu_restore_inhibit_context(struct intel_vgpu *vgpu,
 				       struct i915_request *req);
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 17f9f8d7e148..e1760030dda1 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -54,11 +54,8 @@ static void set_context_pdp_root_pointer(
 
 static void update_shadow_pdps(struct intel_vgpu_workload *workload)
 {
-	struct intel_vgpu *vgpu = workload->vgpu;
-	int ring_id = workload->ring_id;
-	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+		workload->req->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 
@@ -128,9 +125,8 @@ static int populate_shadow_context(struct intel_vgpu_workload *workload)
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
 	int ring_id = workload->ring_id;
-	struct i915_gem_context *shadow_ctx = vgpu->submission.shadow_ctx;
 	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+		workload->req->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *dst;
@@ -280,10 +276,8 @@ static int shadow_context_status_change(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
-static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
-		struct intel_engine_cs *engine)
+static void shadow_context_descriptor_update(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc = 0;
 
 	desc = ce->lrc_desc;
@@ -292,7 +286,7 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
 	 * like GEN8_CTX_* cached in desc_template
 	 */
 	desc &= U64_MAX << 12;
-	desc |= ctx->desc_template & ((1ULL << 12) - 1);
+	desc |= ce->gem_context->desc_template & ((1ULL << 12) - 1);
 
 	ce->lrc_desc = desc;
 }
@@ -300,12 +294,11 @@ static void shadow_context_descriptor_update(struct i915_gem_context *ctx,
 static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
+	struct i915_request *req = workload->req;
 	void *shadow_ring_buffer_va;
 	u32 *cs;
-	struct i915_request *req = workload->req;
 
-	if (IS_KABYLAKE(req->i915) &&
-	    is_inhibit_context(req->gem_context, req->engine->id))
+	if (IS_KABYLAKE(req->i915) && is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/* allocate shadow ring buffer */
@@ -353,60 +346,56 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	struct intel_vgpu_submission *s = &vgpu->submission;
 	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
-	int ring_id = workload->ring_id;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	struct intel_ring *ring;
+	struct intel_engine_cs *engine = dev_priv->engine[workload->ring_id];
+	struct intel_context *ce;
 	int ret;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
 
-	if (workload->shadowed)
+	if (workload->req)
 		return 0;
 
+	/* pin shadow context by gvt even the shadow context will be pinned
+	 * when i915 alloc request. That is because gvt will update the guest
+	 * context from shadow context when workload is completed, and at that
+	 * moment, i915 may already unpined the shadow context to make the
+	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
+	 * the guest context, gvt can unpin the shadow_ctx safely.
+	 */
+	ce = intel_context_pin(shadow_ctx, engine);
+	if (IS_ERR(ce)) {
+		gvt_vgpu_err("fail to pin shadow context\n");
+		return PTR_ERR(ce);
+	}
+
 	shadow_ctx->desc_template &= ~(0x3 << GEN8_CTX_ADDRESSING_MODE_SHIFT);
 	shadow_ctx->desc_template |= workload->ctx_desc.addressing_mode <<
 				    GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
-	if (!test_and_set_bit(ring_id, s->shadow_ctx_desc_updated))
-		shadow_context_descriptor_update(shadow_ctx,
-					dev_priv->engine[ring_id]);
+	if (!test_and_set_bit(workload->ring_id, s->shadow_ctx_desc_updated))
+		shadow_context_descriptor_update(ce);
 
 	ret = intel_gvt_scan_and_shadow_ringbuffer(workload);
 	if (ret)
-		goto err_scan;
+		goto err_unpin;
 
 	if ((workload->ring_id == RCS) &&
 	    (workload->wa_ctx.indirect_ctx.size != 0)) {
 		ret = intel_gvt_scan_and_shadow_wa_ctx(&workload->wa_ctx);
 		if (ret)
-			goto err_scan;
-	}
-
-	/* pin shadow context by gvt even the shadow context will be pinned
-	 * when i915 alloc request. That is because gvt will update the guest
-	 * context from shadow context when workload is completed, and at that
-	 * moment, i915 may already unpined the shadow context to make the
-	 * shadow_ctx pages invalid. So gvt need to pin itself. After update
-	 * the guest context, gvt can unpin the shadow_ctx safely.
-	 */
-	ring = intel_context_pin(shadow_ctx, engine);
-	if (IS_ERR(ring)) {
-		ret = PTR_ERR(ring);
-		gvt_vgpu_err("fail to pin shadow context\n");
-		goto err_shadow;
+			goto err_shadow;
 	}
 
 	ret = populate_shadow_context(workload);
 	if (ret)
-		goto err_unpin;
-	workload->shadowed = true;
+		goto err_shadow;
+
 	return 0;
 
-err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
 err_shadow:
 	release_shadow_wa_ctx(&workload->wa_ctx);
-err_scan:
+err_unpin:
+	intel_context_unpin(ce);
 	return ret;
 }
 
@@ -414,7 +403,6 @@ static int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
 {
 	int ring_id = workload->ring_id;
 	struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
 	struct i915_request *rq;
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
@@ -437,7 +425,6 @@ static int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
 	return 0;
 
 err_unpin:
-	intel_context_unpin(shadow_ctx, engine);
 	release_shadow_wa_ctx(&workload->wa_ctx);
 	return ret;
 }
@@ -517,21 +504,13 @@ err:
 	return ret;
 }
 
-static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
+static void update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 {
-	struct intel_vgpu_workload *workload = container_of(wa_ctx,
-					struct intel_vgpu_workload,
-					wa_ctx);
-	int ring_id = workload->ring_id;
-	struct intel_vgpu_submission *s = &workload->vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
-	struct execlist_ring_context *shadow_ring_context;
-	struct page *page;
-
-	page = i915_gem_object_get_page(ctx_obj, LRC_STATE_PN);
-	shadow_ring_context = kmap_atomic(page);
+	struct intel_vgpu_workload *workload =
+		container_of(wa_ctx, struct intel_vgpu_workload, wa_ctx);
+	struct i915_request *rq = workload->req;
+	struct execlist_ring_context *shadow_ring_context =
+		(struct execlist_ring_context *)rq->hw_context->lrc_reg_state;
 
 	shadow_ring_context->bb_per_ctx_ptr.val =
 		(shadow_ring_context->bb_per_ctx_ptr.val &
@@ -539,9 +518,6 @@ static int update_wa_ctx_2_shadow_ctx(struct intel_shadow_wa_ctx *wa_ctx)
 	shadow_ring_context->rcs_indirect_ctx.val =
 		(shadow_ring_context->rcs_indirect_ctx.val &
 		(~INDIRECT_CTX_ADDR_MASK)) | wa_ctx->indirect_ctx.shadow_gma;
-
-	kunmap_atomic(shadow_ring_context);
-	return 0;
 }
 
 static int prepare_shadow_wa_ctx(struct intel_shadow_wa_ctx *wa_ctx)
@@ -670,12 +646,9 @@ err_unpin_mm:
 static int dispatch_workload(struct intel_vgpu_workload *workload)
 {
 	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int ring_id = workload->ring_id;
-	struct intel_engine_cs *engine = dev_priv->engine[ring_id];
-	int ret = 0;
+	int ret;
 
 	gvt_dbg_sched("ring id %d prepare to dispatch workload %p\n",
 		ring_id, workload);
@@ -687,10 +660,6 @@ static int dispatch_workload(struct intel_vgpu_workload *workload)
 		goto out;
 
 	ret = prepare_workload(workload);
-	if (ret) {
-		intel_context_unpin(shadow_ctx, engine);
-		goto out;
-	}
 
 out:
 	if (ret)
@@ -765,27 +734,23 @@ out:
 
 static void update_guest_context(struct intel_vgpu_workload *workload)
 {
+	struct i915_request *rq = workload->req;
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_gvt *gvt = vgpu->gvt;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	int ring_id = workload->ring_id;
-	struct drm_i915_gem_object *ctx_obj =
-		shadow_ctx->__engine[ring_id].state->obj;
+	struct drm_i915_gem_object *ctx_obj = rq->hw_context->state->obj;
 	struct execlist_ring_context *shadow_ring_context;
 	struct page *page;
 	void *src;
 	unsigned long context_gpa, context_page_num;
 	int i;
 
-	gvt_dbg_sched("ring id %d workload lrca %x\n", ring_id,
-			workload->ctx_desc.lrca);
-
-	context_page_num = gvt->dev_priv->engine[ring_id]->context_size;
+	gvt_dbg_sched("ring id %d workload lrca %x\n", rq->engine->id,
+		      workload->ctx_desc.lrca);
 
+	context_page_num = rq->engine->context_size;
 	context_page_num = context_page_num >> PAGE_SHIFT;
 
-	if (IS_BROADWELL(gvt->dev_priv) && ring_id == RCS)
+	if (IS_BROADWELL(gvt->dev_priv) && rq->engine->id == RCS)
 		context_page_num = 19;
 
 	i = 2;
@@ -858,6 +823,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 		scheduler->current_workload[ring_id];
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
+	struct i915_request *rq;
 	int event;
 
 	mutex_lock(&gvt->lock);
@@ -866,11 +832,8 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	 * switch to make sure request is completed.
 	 * For the workload w/o request, directly complete the workload.
 	 */
-	if (workload->req) {
-		struct drm_i915_private *dev_priv =
-			workload->vgpu->gvt->dev_priv;
-		struct intel_engine_cs *engine =
-			dev_priv->engine[workload->ring_id];
+	rq = fetch_and_zero(&workload->req);
+	if (rq) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
 
@@ -886,8 +849,6 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 				workload->status = 0;
 		}
 
-		i915_request_put(fetch_and_zero(&workload->req));
-
 		if (!workload->status && !(vgpu->resetting_eng &
 					   ENGINE_MASK(ring_id))) {
 			update_guest_context(workload);
@@ -896,10 +857,13 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 					 INTEL_GVT_EVENT_MAX)
 				intel_vgpu_trigger_virtual_event(vgpu, event);
 		}
-		mutex_lock(&dev_priv->drm.struct_mutex);
+
 		/* unpin shadow ctx as the shadow_ctx update is done */
-		intel_context_unpin(s->shadow_ctx, engine);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
+		mutex_lock(&rq->i915->drm.struct_mutex);
+		intel_context_unpin(rq->hw_context);
+		mutex_unlock(&rq->i915->drm.struct_mutex);
+
+		i915_request_put(rq);
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
@@ -1270,7 +1234,6 @@ alloc_workload(struct intel_vgpu *vgpu)
 	atomic_set(&workload->shadow_ctx_active, 0);
 
 	workload->status = -EINPROGRESS;
-	workload->shadowed = false;
 	workload->vgpu = vgpu;
 
 	return workload;
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.h b/drivers/gpu/drm/i915/gvt/scheduler.h
index 6c644782193e..21eddab4a9cd 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.h
+++ b/drivers/gpu/drm/i915/gvt/scheduler.h
@@ -83,7 +83,6 @@ struct intel_vgpu_workload {
 	struct i915_request *req;
 	/* if this workload has been dispatched to i915? */
 	bool dispatched;
-	bool shadowed;
 	int status;
 
 	struct intel_vgpu_mm *shadow_mm;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 34c125e2d90c..e33c380b43e3 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1950,6 +1950,7 @@ struct drm_i915_private {
 			 */
 			struct i915_perf_stream *exclusive_stream;
 
+			struct intel_context *pinned_ctx;
 			u32 specific_ctx_id;
 
 			struct hrtimer poll_check_timer;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index a20f8db5729d..03874b50ada9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3181,14 +3181,14 @@ void i915_gem_reset(struct drm_i915_private *dev_priv,
 	i915_retire_requests(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
-		struct i915_gem_context *ctx;
+		struct intel_context *ce;
 
 		i915_gem_reset_engine(engine,
 				      engine->hangcheck.active_request,
 				      stalled_mask & ENGINE_MASK(id));
-		ctx = fetch_and_zero(&engine->last_retired_context);
-		if (ctx)
-			intel_context_unpin(ctx, engine);
+		ce = fetch_and_zero(&engine->last_retired_context);
+		if (ce)
+			intel_context_unpin(ce);
 
 		/*
 		 * Ostensibily, we always want a context loaded for powersaving,
@@ -4897,13 +4897,13 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 
 static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 {
-	struct i915_gem_context *kernel_context = i915->kernel_context;
+	struct i915_gem_context *kctx = i915->kernel_context;
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
 	for_each_engine(engine, i915, id) {
 		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
-		GEM_BUG_ON(engine->last_retired_context != kernel_context);
+		GEM_BUG_ON(engine->last_retired_context->gem_context != kctx);
 	}
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 9e70f4dfa703..b69b18ef8120 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -127,14 +127,8 @@ static void i915_gem_context_free(struct i915_gem_context *ctx)
 	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
 		struct intel_context *ce = &ctx->__engine[n];
 
-		if (!ce->state)
-			continue;
-
-		WARN_ON(ce->pin_count);
-		if (ce->ring)
-			intel_ring_free(ce->ring);
-
-		__i915_gem_object_release_unless_active(ce->state->obj);
+		if (ce->ops)
+			ce->ops->destroy(ce);
 	}
 
 	kfree(ctx->name);
@@ -266,6 +260,7 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 		    struct drm_i915_file_private *file_priv)
 {
 	struct i915_gem_context *ctx;
+	unsigned int n;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -283,6 +278,12 @@ __create_hw_context(struct drm_i915_private *dev_priv,
 	ctx->i915 = dev_priv;
 	ctx->sched.priority = I915_PRIORITY_NORMAL;
 
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
+		struct intel_context *ce = &ctx->__engine[n];
+
+		ce->gem_context = ctx;
+	}
+
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index ace3b129c189..749a4ff566f5 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -45,6 +45,11 @@ struct intel_ring;
 
 #define DEFAULT_CONTEXT_HANDLE 0
 
+struct intel_context_ops {
+	void (*unpin)(struct intel_context *ce);
+	void (*destroy)(struct intel_context *ce);
+};
+
 /**
  * struct i915_gem_context - client state
  *
@@ -144,11 +149,14 @@ struct i915_gem_context {
 
 	/** engine: per-engine logical HW state */
 	struct intel_context {
+		struct i915_gem_context *gem_context;
 		struct i915_vma *state;
 		struct intel_ring *ring;
 		u32 *lrc_reg_state;
 		u64 lrc_desc;
 		int pin_count;
+
+		const struct intel_context_ops *ops;
 	} __engine[I915_NUM_ENGINES];
 
 	/** ring_size: size for allocating the per-engine ring buffer */
@@ -263,25 +271,22 @@ to_intel_context(struct i915_gem_context *ctx,
 	return &ctx->__engine[engine->id];
 }
 
-static inline struct intel_ring *
+static inline struct intel_context *
 intel_context_pin(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 {
 	return engine->context_pin(engine, ctx);
 }
 
-static inline void __intel_context_pin(struct i915_gem_context *ctx,
-				       const struct intel_engine_cs *engine)
+static inline void __intel_context_pin(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
-
 	GEM_BUG_ON(!ce->pin_count);
 	ce->pin_count++;
 }
 
-static inline void intel_context_unpin(struct i915_gem_context *ctx,
-				       struct intel_engine_cs *engine)
+static inline void intel_context_unpin(struct intel_context *ce)
 {
-	engine->context_unpin(engine, ctx);
+	GEM_BUG_ON(!ce->ops);
+	ce->ops->unpin(ce);
 }
 
 /* i915_gem_context.c */
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 37c9a42654ba..47721437a4c5 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1485,8 +1485,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
 
 			ee->ctx =
 				i915_error_object_create(i915,
-							 to_intel_context(ctx,
-									  engine)->state);
+							 request->hw_context->state);
 
 			error->simulated |=
 				i915_gem_context_no_error_capture(ctx);
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 019bd2d073ad..4f0eb84b3c00 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1221,7 +1221,7 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		dev_priv->perf.oa.specific_ctx_id = stream->ctx->hw_id;
 	} else {
 		struct intel_engine_cs *engine = dev_priv->engine[RCS];
-		struct intel_ring *ring;
+		struct intel_context *ce;
 		int ret;
 
 		ret = i915_mutex_lock_interruptible(&dev_priv->drm);
@@ -1234,19 +1234,19 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		 *
 		 * NB: implied RCS engine...
 		 */
-		ring = intel_context_pin(stream->ctx, engine);
+		ce = intel_context_pin(stream->ctx, engine);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
-		if (IS_ERR(ring))
-			return PTR_ERR(ring);
+		if (IS_ERR(ce))
+			return PTR_ERR(ce);
 
+		dev_priv->perf.oa.pinned_ctx = ce;
 
 		/*
 		 * Explicitly track the ID (instead of calling
 		 * i915_ggtt_offset() on the fly) considering the difference
 		 * with gen8+ and execlists
 		 */
-		dev_priv->perf.oa.specific_ctx_id =
-			i915_ggtt_offset(to_intel_context(stream->ctx, engine)->state);
+		dev_priv->perf.oa.specific_ctx_id = i915_ggtt_offset(ce->state);
 	}
 
 	return 0;
@@ -1262,17 +1262,14 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 {
 	struct drm_i915_private *dev_priv = stream->dev_priv;
+	struct intel_context *ce;
 
-	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
-		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
-	} else {
-		struct intel_engine_cs *engine = dev_priv->engine[RCS];
+	dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
 
+	ce = fetch_and_zero(&dev_priv->perf.oa.pinned_ctx);
+	if (ce) {
 		mutex_lock(&dev_priv->drm.struct_mutex);
-
-		dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
-		intel_context_unpin(stream->ctx, engine);
-
+		intel_context_unpin(ce);
 		mutex_unlock(&dev_priv->drm.struct_mutex);
 	}
 }
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index fe8810a6a339..fc499bcbd105 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -383,8 +383,8 @@ static void __retire_engine_request(struct intel_engine_cs *engine,
 	 * the subsequent request.
 	 */
 	if (engine->last_retired_context)
-		intel_context_unpin(engine->last_retired_context, engine);
-	engine->last_retired_context = rq->gem_context;
+		intel_context_unpin(engine->last_retired_context);
+	engine->last_retired_context = rq->hw_context;
 }
 
 static void __retire_engine_upto(struct intel_engine_cs *engine,
@@ -456,7 +456,7 @@ static void i915_request_retire(struct i915_request *request)
 
 	/* Retirement decays the ban score as it is a sign of ctx progress */
 	atomic_dec_if_positive(&request->gem_context->ban_score);
-	intel_context_unpin(request->gem_context, request->engine);
+	intel_context_unpin(request->hw_context);
 
 	__retire_engine_upto(request->engine, request);
 
@@ -657,7 +657,7 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 {
 	struct drm_i915_private *i915 = engine->i915;
 	struct i915_request *rq;
-	struct intel_ring *ring;
+	struct intel_context *ce;
 	int ret;
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
@@ -681,22 +681,21 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	 * GGTT space, so do this first before we reserve a seqno for
 	 * ourselves.
 	 */
-	ring = intel_context_pin(ctx, engine);
-	if (IS_ERR(ring))
-		return ERR_CAST(ring);
-	GEM_BUG_ON(!ring);
+	ce = intel_context_pin(ctx, engine);
+	if (IS_ERR(ce))
+		return ERR_CAST(ce);
 
 	ret = reserve_gt(i915);
 	if (ret)
 		goto err_unpin;
 
-	ret = intel_ring_wait_for_space(ring, MIN_SPACE_FOR_ADD_REQUEST);
+	ret = intel_ring_wait_for_space(ce->ring, MIN_SPACE_FOR_ADD_REQUEST);
 	if (ret)
 		goto err_unreserve;
 
 	/* Move our oldest request to the slab-cache (if not in use!) */
-	rq = list_first_entry(&ring->request_list, typeof(*rq), ring_link);
-	if (!list_is_last(&rq->ring_link, &ring->request_list) &&
+	rq = list_first_entry(&ce->ring->request_list, typeof(*rq), ring_link);
+	if (!list_is_last(&rq->ring_link, &ce->ring->request_list) &&
 	    i915_request_completed(rq))
 		i915_request_retire(rq);
 
@@ -761,8 +760,9 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	rq->i915 = i915;
 	rq->engine = engine;
 	rq->gem_context = ctx;
-	rq->ring = ring;
-	rq->timeline = ring->timeline;
+	rq->hw_context = ce;
+	rq->ring = ce->ring;
+	rq->timeline = ce->ring->timeline;
 	GEM_BUG_ON(rq->timeline == &engine->timeline);
 
 	spin_lock_init(&rq->lock);
@@ -814,14 +814,14 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		goto err_unwind;
 
 	/* Keep a second pin for the dual retirement along engine and ring */
-	__intel_context_pin(rq->gem_context, engine);
+	__intel_context_pin(ce);
 
 	/* Check that we didn't interrupt ourselves with a new request */
 	GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno);
 	return rq;
 
 err_unwind:
-	rq->ring->emit = rq->head;
+	ce->ring->emit = rq->head;
 
 	/* Make sure we didn't add ourselves to external state before freeing */
 	GEM_BUG_ON(!list_empty(&rq->active_list));
@@ -832,7 +832,7 @@ err_unwind:
 err_unreserve:
 	unreserve_gt(i915);
 err_unpin:
-	intel_context_unpin(ctx, engine);
+	intel_context_unpin(ce);
 	return ERR_PTR(ret);
 }
 
@@ -1018,8 +1018,8 @@ i915_request_await_object(struct i915_request *to,
 void __i915_request_add(struct i915_request *request, bool flush_caches)
 {
 	struct intel_engine_cs *engine = request->engine;
-	struct intel_ring *ring = request->ring;
 	struct i915_timeline *timeline = request->timeline;
+	struct intel_ring *ring = request->ring;
 	struct i915_request *prev;
 	u32 *cs;
 	int err;
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index dddecd9ffd0c..1bbbb7a9fa03 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -95,6 +95,7 @@ struct i915_request {
 	 */
 	struct i915_gem_context *gem_context;
 	struct intel_engine_cs *engine;
+	struct intel_context *hw_context;
 	struct intel_ring *ring;
 	struct i915_timeline *timeline;
 	struct intel_signal_node signaling;
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 9e618aab6568..26f9f8aab949 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -645,6 +645,12 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
 	return 0;
 }
 
+static void __intel_context_unpin(struct i915_gem_context *ctx,
+				  struct intel_engine_cs *engine)
+{
+	intel_context_unpin(to_intel_context(ctx, engine));
+}
+
 /**
  * intel_engines_init_common - initialize cengine state which might require hw access
  * @engine: Engine to initialize.
@@ -658,7 +664,8 @@ static int init_phys_status_page(struct intel_engine_cs *engine)
  */
 int intel_engine_init_common(struct intel_engine_cs *engine)
 {
-	struct intel_ring *ring;
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_context *ce;
 	int ret;
 
 	engine->set_default_submission(engine);
@@ -670,18 +677,18 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	 * be available. To avoid this we always pin the default
 	 * context.
 	 */
-	ring = intel_context_pin(engine->i915->kernel_context, engine);
-	if (IS_ERR(ring))
-		return PTR_ERR(ring);
+	ce = intel_context_pin(i915->kernel_context, engine);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
 	/*
 	 * Similarly the preempt context must always be available so that
 	 * we can interrupt the engine at any time.
 	 */
-	if (engine->i915->preempt_context) {
-		ring = intel_context_pin(engine->i915->preempt_context, engine);
-		if (IS_ERR(ring)) {
-			ret = PTR_ERR(ring);
+	if (i915->preempt_context) {
+		ce = intel_context_pin(i915->preempt_context, engine);
+		if (IS_ERR(ce)) {
+			ret = PTR_ERR(ce);
 			goto err_unpin_kernel;
 		}
 	}
@@ -690,7 +697,7 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 	if (ret)
 		goto err_unpin_preempt;
 
-	if (HWS_NEEDS_PHYSICAL(engine->i915))
+	if (HWS_NEEDS_PHYSICAL(i915))
 		ret = init_phys_status_page(engine);
 	else
 		ret = init_status_page(engine);
@@ -702,10 +709,11 @@ int intel_engine_init_common(struct intel_engine_cs *engine)
 err_breadcrumbs:
 	intel_engine_fini_breadcrumbs(engine);
 err_unpin_preempt:
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+
 err_unpin_kernel:
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 	return ret;
 }
 
@@ -718,6 +726,8 @@ err_unpin_kernel:
  */
 void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+
 	intel_engine_cleanup_scratch(engine);
 
 	if (HWS_NEEDS_PHYSICAL(engine->i915))
@@ -732,9 +742,9 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine)
 	if (engine->default_state)
 		i915_gem_object_put(engine->default_state);
 
-	if (engine->i915->preempt_context)
-		intel_context_unpin(engine->i915->preempt_context, engine);
-	intel_context_unpin(engine->i915->kernel_context, engine);
+	if (i915->preempt_context)
+		__intel_context_unpin(i915->preempt_context, engine);
+	__intel_context_unpin(i915->kernel_context, engine);
 
 	i915_timeline_fini(&engine->timeline);
 }
@@ -1007,8 +1017,8 @@ bool intel_engines_are_idle(struct drm_i915_private *dev_priv)
  */
 bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 {
-	const struct i915_gem_context * const kernel_context =
-		engine->i915->kernel_context;
+	const struct intel_context *kernel_context =
+		to_intel_context(engine->i915->kernel_context, engine);
 	struct i915_request *rq;
 
 	lockdep_assert_held(&engine->i915->drm.struct_mutex);
@@ -1020,7 +1030,7 @@ bool intel_engine_has_kernel_context(const struct intel_engine_cs *engine)
 	 */
 	rq = __i915_gem_active_peek(&engine->timeline.last_request);
 	if (rq)
-		return rq->gem_context == kernel_context;
+		return rq->hw_context == kernel_context;
 	else
 		return engine->last_retired_context == kernel_context;
 }
@@ -1107,16 +1117,16 @@ void intel_engines_unpark(struct drm_i915_private *i915)
  */
 void intel_engine_lost_context(struct intel_engine_cs *engine)
 {
-	struct i915_gem_context *ctx;
+	struct intel_context *ce;
 
 	lockdep_assert_held(&engine->i915->drm.struct_mutex);
 
 	engine->legacy_active_context = NULL;
 	engine->legacy_active_ppgtt = NULL;
 
-	ctx = fetch_and_zero(&engine->last_retired_context);
-	if (ctx)
-		intel_context_unpin(ctx, engine);
+	ce = fetch_and_zero(&engine->last_retired_context);
+	if (ce)
+		intel_context_unpin(ce);
 }
 
 bool intel_engine_can_store_dword(struct intel_engine_cs *engine)
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index a432a193f3c4..133367a17863 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -513,9 +513,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
 {
 	struct intel_guc_client *client = guc->execbuf_client;
 	struct intel_engine_cs *engine = rq->engine;
-	u32 ctx_desc =
-		lower_32_bits(intel_lr_context_descriptor(rq->gem_context,
-							  engine));
+	u32 ctx_desc = lower_32_bits(rq->hw_context->lrc_desc);
 	u32 ring_tail = intel_ring_set_tail(rq->ring, rq->tail) / sizeof(u64);
 
 	spin_lock(&client->wq_lock);
@@ -553,8 +551,8 @@ static void inject_preempt_context(struct work_struct *work)
 					     preempt_work[engine->id]);
 	struct intel_guc_client *client = guc->preempt_client;
 	struct guc_stage_desc *stage_desc = __get_stage_desc(client);
-	u32 ctx_desc = lower_32_bits(intel_lr_context_descriptor(client->owner,
-								 engine));
+	u32 ctx_desc = lower_32_bits(to_intel_context(client->owner,
+						      engine)->lrc_desc);
 	u32 data[7];
 
 	/*
@@ -726,7 +724,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 		struct i915_request *rq, *rn;
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
-			if (last && rq->gem_context != last->gem_context) {
+			if (last && rq->hw_context != last->hw_context) {
 				if (port == last_port) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 1e9cc55d785c..b97c5d4c7877 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -164,7 +164,8 @@
 #define WA_TAIL_BYTES (sizeof(u32) * WA_TAIL_DWORDS)
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
-					    struct intel_engine_cs *engine);
+					    struct intel_engine_cs *engine,
+					    struct intel_context *ce);
 static void execlists_init_reg_state(u32 *reg_state,
 				     struct i915_gem_context *ctx,
 				     struct intel_engine_cs *engine,
@@ -189,12 +190,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
 		!i915_request_completed(last));
 }
 
-/**
- * intel_lr_context_descriptor_update() - calculate & cache the descriptor
- * 					  descriptor for a pinned context
- * @ctx: Context to work on
- * @engine: Engine the descriptor will be used with
- *
+/*
  * The context descriptor encodes various attributes of a context,
  * including its GTT address and some flags. Because it's fairly
  * expensive to calculate, we'll just do it once and cache the result,
@@ -222,9 +218,9 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
  */
 static void
 intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
-				   struct intel_engine_cs *engine)
+				   struct intel_engine_cs *engine,
+				   struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	u64 desc;
 
 	BUILD_BUG_ON(MAX_CONTEXT_HW_ID > (BIT(GEN8_CTX_ID_WIDTH)));
@@ -418,8 +414,7 @@ execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
 
 static u64 execlists_update_context(struct i915_request *rq)
 {
-	struct intel_context *ce =
-		to_intel_context(rq->gem_context, rq->engine);
+	struct intel_context *ce = rq->hw_context;
 	struct i915_hw_ppgtt *ppgtt =
 		rq->gem_context->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
 	u32 *reg_state = ce->lrc_reg_state;
@@ -496,14 +491,14 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 	execlists_clear_active(execlists, EXECLISTS_ACTIVE_HWACK);
 }
 
-static bool ctx_single_port_submission(const struct i915_gem_context *ctx)
+static bool ctx_single_port_submission(const struct intel_context *ce)
 {
 	return (IS_ENABLED(CONFIG_DRM_I915_GVT) &&
-		i915_gem_context_force_single_submission(ctx));
+		i915_gem_context_force_single_submission(ce->gem_context));
 }
 
-static bool can_merge_ctx(const struct i915_gem_context *prev,
-			  const struct i915_gem_context *next)
+static bool can_merge_ctx(const struct intel_context *prev,
+			  const struct intel_context *next)
 {
 	if (prev != next)
 		return false;
@@ -680,8 +675,8 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 			 * second request, and so we never need to tell the
 			 * hardware about the first.
 			 */
-			if (last && !can_merge_ctx(rq->gem_context,
-						   last->gem_context)) {
+			if (last &&
+			    !can_merge_ctx(rq->hw_context, last->hw_context)) {
 				/*
 				 * If we are on the second port and cannot
 				 * combine this request with the last, then we
@@ -700,14 +695,14 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 				 * the same context (even though a different
 				 * request) to the second port.
 				 */
-				if (ctx_single_port_submission(last->gem_context) ||
-				    ctx_single_port_submission(rq->gem_context)) {
+				if (ctx_single_port_submission(last->hw_context) ||
+				    ctx_single_port_submission(rq->hw_context)) {
 					__list_del_many(&p->requests,
 							&rq->sched.link);
 					goto done;
 				}
 
-				GEM_BUG_ON(last->gem_context == rq->gem_context);
+				GEM_BUG_ON(last->hw_context == rq->hw_context);
 
 				if (submit)
 					port_assign(port, last);
@@ -1339,6 +1334,37 @@ static void execlists_schedule(struct i915_request *request,
 	spin_unlock_irq(&engine->timeline.lock);
 }
 
+static void execlists_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(!ce->state);
+	GEM_BUG_ON(ce->pin_count);
+
+	intel_ring_free(ce->ring);
+	__i915_gem_object_release_unless_active(ce->state->obj);
+}
+
+static void __execlists_context_unpin(struct intel_context *ce)
+{
+	intel_ring_unpin(ce->ring);
+
+	ce->state->obj->pin_global--;
+	i915_gem_object_unpin_map(ce->state->obj);
+	i915_vma_unpin(ce->state);
+
+	i915_gem_context_put(ce->gem_context);
+}
+
+static void execlists_context_unpin(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->gem_context->i915->drm.struct_mutex);
+	GEM_BUG_ON(ce->pin_count == 0);
+
+	if (--ce->pin_count)
+		return;
+
+	__execlists_context_unpin(ce);
+}
+
 static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 {
 	unsigned int flags;
@@ -1362,21 +1388,15 @@ static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 	return i915_vma_pin(vma, 0, GEN8_LR_CONTEXT_ALIGN, flags);
 }
 
-static struct intel_ring *
-execlists_context_pin(struct intel_engine_cs *engine,
-		      struct i915_gem_context *ctx)
+static struct intel_context *
+__execlists_context_pin(struct intel_engine_cs *engine,
+			struct i915_gem_context *ctx,
+			struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	void *vaddr;
 	int ret;
 
-	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-
-	if (likely(ce->pin_count++))
-		goto out;
-	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
-
-	ret = execlists_context_deferred_alloc(ctx, engine);
+	ret = execlists_context_deferred_alloc(ctx, engine, ce);
 	if (ret)
 		goto err;
 	GEM_BUG_ON(!ce->state);
@@ -1395,7 +1415,7 @@ execlists_context_pin(struct intel_engine_cs *engine,
 	if (ret)
 		goto unpin_map;
 
-	intel_lr_context_descriptor_update(ctx, engine);
+	intel_lr_context_descriptor_update(ctx, engine, ce);
 
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
@@ -1404,8 +1424,7 @@ execlists_context_pin(struct intel_engine_cs *engine,
 
 	ce->state->obj->pin_global++;
 	i915_gem_context_get(ctx);
-out:
-	return ce->ring;
+	return ce;
 
 unpin_map:
 	i915_gem_object_unpin_map(ce->state->obj);
@@ -1416,33 +1435,33 @@ err:
 	return ERR_PTR(ret);
 }
 
-static void execlists_context_unpin(struct intel_engine_cs *engine,
-				    struct i915_gem_context *ctx)
+static const struct intel_context_ops execlists_context_ops = {
+	.unpin = execlists_context_unpin,
+	.destroy = execlists_context_destroy,
+};
+
+static struct intel_context *
+execlists_context_pin(struct intel_engine_cs *engine,
+		      struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
 
-	if (--ce->pin_count)
-		return;
-
-	intel_ring_unpin(ce->ring);
+	if (likely(ce->pin_count++))
+		return ce;
+	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
 
-	ce->state->obj->pin_global--;
-	i915_gem_object_unpin_map(ce->state->obj);
-	i915_vma_unpin(ce->state);
+	ce->ops = &execlists_context_ops;
 
-	i915_gem_context_put(ctx);
+	return __execlists_context_pin(engine, ctx, ce);
 }
 
 static int execlists_request_alloc(struct i915_request *request)
 {
-	struct intel_context *ce =
-		to_intel_context(request->gem_context, request->engine);
 	int ret;
 
-	GEM_BUG_ON(!ce->pin_count);
+	GEM_BUG_ON(!request->hw_context->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
@@ -1956,7 +1975,7 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	 * future request will be after userspace has had the opportunity
 	 * to recreate its own state.
 	 */
-	regs = to_intel_context(request->gem_context, engine)->lrc_reg_state;
+	regs = request->hw_context->lrc_reg_state;
 	if (engine->default_state) {
 		void *defaults;
 
@@ -2327,8 +2346,6 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->reset.finish = execlists_reset_finish;
 
 	engine->context_pin = execlists_context_pin;
-	engine->context_unpin = execlists_context_unpin;
-
 	engine->request_alloc = execlists_request_alloc;
 
 	engine->emit_flush = gen8_emit_flush;
@@ -2563,7 +2580,7 @@ static void execlists_init_reg_state(u32 *regs,
 	struct drm_i915_private *dev_priv = engine->i915;
 	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt ?: dev_priv->mm.aliasing_ppgtt;
 	u32 base = engine->mmio_base;
-	bool rcs = engine->id == RCS;
+	bool rcs = engine->class == RENDER_CLASS;
 
 	/* A context is actually a big batch buffer with several
 	 * MI_LOAD_REGISTER_IMM commands followed by (reg, value) pairs. The
@@ -2710,10 +2727,10 @@ err_unpin_ctx:
 }
 
 static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
-					    struct intel_engine_cs *engine)
+					    struct intel_engine_cs *engine,
+					    struct intel_context *ce)
 {
 	struct drm_i915_gem_object *ctx_obj;
-	struct intel_context *ce = to_intel_context(ctx, engine);
 	struct i915_vma *vma;
 	uint32_t context_size;
 	struct intel_ring *ring;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 4ec7d8dd13c8..1593194e930c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -104,11 +104,4 @@ struct i915_gem_context;
 
 void intel_lr_context_resume(struct drm_i915_private *dev_priv);
 
-static inline uint64_t
-intel_lr_context_descriptor(struct i915_gem_context *ctx,
-			    struct intel_engine_cs *engine)
-{
-	return to_intel_context(ctx, engine)->lrc_desc;
-}
-
 #endif /* _INTEL_LRC_H_ */
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 53703012ec75..0c0c9f531e4e 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -571,8 +571,7 @@ static void reset_ring(struct intel_engine_cs *engine,
 	 */
 	if (request) {
 		struct drm_i915_private *dev_priv = request->i915;
-		struct intel_context *ce =
-			to_intel_context(request->gem_context, engine);
+		struct intel_context *ce = request->hw_context;
 		struct i915_hw_ppgtt *ppgtt;
 
 		if (ce->state) {
@@ -1186,7 +1185,31 @@ intel_ring_free(struct intel_ring *ring)
 	kfree(ring);
 }
 
-static int context_pin(struct intel_context *ce)
+static void intel_ring_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(ce->pin_count);
+
+	if (ce->state)
+		__i915_gem_object_release_unless_active(ce->state->obj);
+}
+
+static void intel_ring_context_unpin(struct intel_context *ce)
+{
+	lockdep_assert_held(&ce->gem_context->i915->drm.struct_mutex);
+	GEM_BUG_ON(ce->pin_count == 0);
+
+	if (--ce->pin_count)
+		return;
+
+	if (ce->state) {
+		ce->state->obj->pin_global--;
+		i915_vma_unpin(ce->state);
+	}
+
+	i915_gem_context_put(ce->gem_context);
+}
+
+static int __context_pin(struct intel_context *ce)
 {
 	struct i915_vma *vma = ce->state;
 	int ret;
@@ -1275,25 +1298,19 @@ err_obj:
 	return ERR_PTR(err);
 }
 
-static struct intel_ring *
-intel_ring_context_pin(struct intel_engine_cs *engine,
-		       struct i915_gem_context *ctx)
+static struct intel_context *
+__ring_context_pin(struct intel_engine_cs *engine,
+		   struct i915_gem_context *ctx,
+		   struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
-	int ret;
-
-	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-
-	if (likely(ce->pin_count++))
-		goto out;
-	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
+	int err;
 
 	if (!ce->state && engine->context_size) {
 		struct i915_vma *vma;
 
 		vma = alloc_context_vma(engine);
 		if (IS_ERR(vma)) {
-			ret = PTR_ERR(vma);
+			err = PTR_ERR(vma);
 			goto err;
 		}
 
@@ -1301,8 +1318,8 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 	}
 
 	if (ce->state) {
-		ret = context_pin(ce);
-		if (ret)
+		err = __context_pin(ce);
+		if (err)
 			goto err;
 
 		ce->state->obj->pin_global++;
@@ -1310,32 +1327,37 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 
 	i915_gem_context_get(ctx);
 
-out:
 	/* One ringbuffer to rule them all */
-	return engine->buffer;
+	GEM_BUG_ON(!engine->buffer);
+	ce->ring = engine->buffer;
+
+	return ce;
 
 err:
 	ce->pin_count = 0;
-	return ERR_PTR(ret);
+	return ERR_PTR(err);
 }
 
-static void intel_ring_context_unpin(struct intel_engine_cs *engine,
-				     struct i915_gem_context *ctx)
+static const struct intel_context_ops ring_context_ops = {
+	.unpin = intel_ring_context_unpin,
+	.destroy = intel_ring_context_destroy,
+};
+
+static struct intel_context *
+intel_ring_context_pin(struct intel_engine_cs *engine,
+		       struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
 	lockdep_assert_held(&ctx->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
 
-	if (--ce->pin_count)
-		return;
+	if (likely(ce->pin_count++))
+		return ce;
+	GEM_BUG_ON(!ce->pin_count); /* no overflow please! */
 
-	if (ce->state) {
-		ce->state->obj->pin_global--;
-		i915_vma_unpin(ce->state);
-	}
+	ce->ops = &ring_context_ops;
 
-	i915_gem_context_put(ctx);
+	return __ring_context_pin(engine, ctx, ce);
 }
 
 static int intel_init_ring_buffer(struct intel_engine_cs *engine)
@@ -1346,10 +1368,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 
 	intel_engine_setup_common(engine);
 
-	err = intel_engine_init_common(engine);
-	if (err)
-		goto err;
-
 	timeline = i915_timeline_create(engine->i915, engine->name);
 	if (IS_ERR(timeline)) {
 		err = PTR_ERR(timeline);
@@ -1371,8 +1389,14 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->buffer);
 	engine->buffer = ring;
 
+	err = intel_engine_init_common(engine);
+	if (err)
+		goto err_unpin;
+
 	return 0;
 
+err_unpin:
+	intel_ring_unpin(ring);
 err_ring:
 	intel_ring_free(ring);
 err:
@@ -1458,7 +1482,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
-	*cs++ = i915_ggtt_offset(to_intel_context(rq->gem_context, engine)->state) | flags;
+	*cs++ = i915_ggtt_offset(rq->hw_context->state) | flags;
 	/*
 	 * w/a: MI_SET_CONTEXT must always be followed by MI_NOOP
 	 * WaMiSetContext_Hang:snb,ivb,vlv
@@ -1549,7 +1573,7 @@ static int switch_context(struct i915_request *rq)
 		hw_flags = MI_FORCE_RESTORE;
 	}
 
-	if (to_intel_context(to_ctx, engine)->state &&
+	if (rq->hw_context->state &&
 	    (to_ctx != from_ctx || hw_flags & MI_FORCE_RESTORE)) {
 		GEM_BUG_ON(engine->id != RCS);
 
@@ -1597,7 +1621,7 @@ static int ring_request_alloc(struct i915_request *request)
 {
 	int ret;
 
-	GEM_BUG_ON(!to_intel_context(request->gem_context, request->engine)->pin_count);
+	GEM_BUG_ON(!request->hw_context->pin_count);
 
 	/* Flush enough space to reduce the likelihood of waiting after
 	 * we start building the request - in which case we will just
@@ -2028,8 +2052,6 @@ static void intel_ring_default_vfuncs(struct drm_i915_private *dev_priv,
 	engine->reset.finish = reset_finish;
 
 	engine->context_pin = intel_ring_context_pin;
-	engine->context_unpin = intel_ring_context_unpin;
-
 	engine->request_alloc = ring_request_alloc;
 
 	engine->emit_breadcrumb = i9xx_emit_breadcrumb;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2b16185e36c4..20c4e13efc0d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -436,10 +436,9 @@ struct intel_engine_cs {
 
 	void		(*set_default_submission)(struct intel_engine_cs *engine);
 
-	struct intel_ring *(*context_pin)(struct intel_engine_cs *engine,
-					  struct i915_gem_context *ctx);
-	void		(*context_unpin)(struct intel_engine_cs *engine,
-					 struct i915_gem_context *ctx);
+	struct intel_context *(*context_pin)(struct intel_engine_cs *engine,
+					     struct i915_gem_context *ctx);
+
 	int		(*request_alloc)(struct i915_request *rq);
 	int		(*init_context)(struct i915_request *rq);
 
@@ -555,7 +554,7 @@ struct intel_engine_cs {
 	 * to the kernel context and trash it as the save may not happen
 	 * before the hardware is powered down.
 	 */
-	struct i915_gem_context *last_retired_context;
+	struct intel_context *last_retired_context;
 
 	/* We track the current MI_SET_CONTEXT in order to eliminate
 	 * redudant context switches. This presumes that requests are not
diff --git a/drivers/gpu/drm/i915/selftests/mock_context.c b/drivers/gpu/drm/i915/selftests/mock_context.c
index 501becc47c0c..8904f1ce64e3 100644
--- a/drivers/gpu/drm/i915/selftests/mock_context.c
+++ b/drivers/gpu/drm/i915/selftests/mock_context.c
@@ -30,6 +30,7 @@ mock_context(struct drm_i915_private *i915,
 	     const char *name)
 {
 	struct i915_gem_context *ctx;
+	unsigned int n;
 	int ret;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -43,6 +44,12 @@ mock_context(struct drm_i915_private *i915,
 	INIT_RADIX_TREE(&ctx->handles_vma, GFP_KERNEL);
 	INIT_LIST_HEAD(&ctx->handles_list);
 
+	for (n = 0; n < ARRAY_SIZE(ctx->__engine); n++) {
+		struct intel_context *ce = &ctx->__engine[n];
+
+		ce->gem_context = ctx;
+	}
+
 	ret = ida_simple_get(&i915->contexts.hw_ida,
 			     0, MAX_CONTEXT_HW_ID, GFP_KERNEL);
 	if (ret < 0)
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index 26bf29d97007..33eddfc1f8ce 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -72,25 +72,37 @@ static void hw_delay_complete(struct timer_list *t)
 	spin_unlock(&engine->hw_lock);
 }
 
-static struct intel_ring *
-mock_context_pin(struct intel_engine_cs *engine,
-		 struct i915_gem_context *ctx)
+static void mock_context_unpin(struct intel_context *ce)
 {
-	struct intel_context *ce = to_intel_context(ctx, engine);
+	if (--ce->pin_count)
+		return;
 
-	if (!ce->pin_count++)
-		i915_gem_context_get(ctx);
+	i915_gem_context_put(ce->gem_context);
+}
 
-	return engine->buffer;
+static void mock_context_destroy(struct intel_context *ce)
+{
+	GEM_BUG_ON(ce->pin_count);
 }
 
-static void mock_context_unpin(struct intel_engine_cs *engine,
-			       struct i915_gem_context *ctx)
+static const struct intel_context_ops mock_context_ops = {
+	.unpin = mock_context_unpin,
+	.destroy = mock_context_destroy,
+};
+
+static struct intel_context *
+mock_context_pin(struct intel_engine_cs *engine,
+		 struct i915_gem_context *ctx)
 {
 	struct intel_context *ce = to_intel_context(ctx, engine);
 
-	if (!--ce->pin_count)
-		i915_gem_context_put(ctx);
+	if (!ce->pin_count++) {
+		i915_gem_context_get(ctx);
+		ce->ring = engine->buffer;
+		ce->ops = &mock_context_ops;
+	}
+
+	return ce;
 }
 
 static int mock_request_alloc(struct i915_request *request)
@@ -185,7 +197,6 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.status_page.page_addr = (void *)(engine + 1);
 
 	engine->base.context_pin = mock_context_pin;
-	engine->base.context_unpin = mock_context_unpin;
 	engine->base.request_alloc = mock_request_alloc;
 	engine->base.emit_flush = mock_emit_flush;
 	engine->base.emit_breadcrumb = mock_emit_breadcrumb;
@@ -238,11 +249,13 @@ void mock_engine_free(struct intel_engine_cs *engine)
 {
 	struct mock_engine *mock =
 		container_of(engine, typeof(*mock), base);
+	struct intel_context *ce;
 
 	GEM_BUG_ON(timer_pending(&mock->hw_delay));
 
-	if (engine->last_retired_context)
-		intel_context_unpin(engine->last_retired_context, engine);
+	ce = fetch_and_zero(&engine->last_retired_context);
+	if (ce)
+		intel_context_unpin(ce);
 
 	mock_ring_free(engine->buffer);
 
-- 
cgit v1.2.3


From 867985d4a4319819a971645a262f3340f7d30343 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 22:26:33 +0100
Subject: drm/i915: Pull the context->pin_count dec into the common
 intel_context_unpin

As all backends implement the same pin_count mechanism and do a
dec-and-test as their first step, pull that into the common
intel_context_unpin(). This also pulls into the caller, eliminating the
indirect call in the usual steady state case. The intel_context_pin()
side is a little more complicated as it combines the lookup/alloc as
well as pinning the state, and so is left for a later date.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517212633.24934-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_context.h      |  4 ++++
 drivers/gpu/drm/i915/intel_lrc.c             | 13 +------------
 drivers/gpu/drm/i915/intel_ringbuffer.c      |  6 ------
 drivers/gpu/drm/i915/selftests/mock_engine.c |  3 ---
 4 files changed, 5 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 749a4ff566f5..c3262b4dd2ee 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -285,6 +285,10 @@ static inline void __intel_context_pin(struct intel_context *ce)
 
 static inline void intel_context_unpin(struct intel_context *ce)
 {
+	GEM_BUG_ON(!ce->pin_count);
+	if (--ce->pin_count)
+		return;
+
 	GEM_BUG_ON(!ce->ops);
 	ce->ops->unpin(ce);
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index b97c5d4c7877..9abd26f22b47 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1343,7 +1343,7 @@ static void execlists_context_destroy(struct intel_context *ce)
 	__i915_gem_object_release_unless_active(ce->state->obj);
 }
 
-static void __execlists_context_unpin(struct intel_context *ce)
+static void execlists_context_unpin(struct intel_context *ce)
 {
 	intel_ring_unpin(ce->ring);
 
@@ -1354,17 +1354,6 @@ static void __execlists_context_unpin(struct intel_context *ce)
 	i915_gem_context_put(ce->gem_context);
 }
 
-static void execlists_context_unpin(struct intel_context *ce)
-{
-	lockdep_assert_held(&ce->gem_context->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
-
-	if (--ce->pin_count)
-		return;
-
-	__execlists_context_unpin(ce);
-}
-
 static int __context_pin(struct i915_gem_context *ctx, struct i915_vma *vma)
 {
 	unsigned int flags;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 0c0c9f531e4e..001cf6bcb349 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1195,12 +1195,6 @@ static void intel_ring_context_destroy(struct intel_context *ce)
 
 static void intel_ring_context_unpin(struct intel_context *ce)
 {
-	lockdep_assert_held(&ce->gem_context->i915->drm.struct_mutex);
-	GEM_BUG_ON(ce->pin_count == 0);
-
-	if (--ce->pin_count)
-		return;
-
 	if (ce->state) {
 		ce->state->obj->pin_global--;
 		i915_vma_unpin(ce->state);
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index 33eddfc1f8ce..f1ac7453053e 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -74,9 +74,6 @@ static void hw_delay_complete(struct timer_list *t)
 
 static void mock_context_unpin(struct intel_context *ce)
 {
-	if (--ce->pin_count)
-		return;
-
 	i915_gem_context_put(ce->gem_context);
 }
 
-- 
cgit v1.2.3


From 38992c57c9c8425dc9cb75efe6f9b9255ea627a0 Mon Sep 17 00:00:00 2001
From: Jyri Sarha <jsarha@ti.com>
Date: Thu, 26 Apr 2018 11:06:59 +0300
Subject: drm/panel: Remove drm_panel_detach() calls from all panel drivers

Remove all drm_panel_detach() calls from all panel drivers and update
the kerneldoc for drm_panel_detach().

Setting the connector and drm to NULL when the DRM panel device is going
away hardly serves any purpose. Usually the whole memory structure is
freed right after the remove call. However, calling the detach function
from the master DRM device, and setting the connector pointer to NULL,
has the logic of marking the panel again as available for another DRM
master to attach. The usual situation would be the same DRM master
device binding again.

Signed-off-by: Jyri Sarha <jsarha@ti.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/464b8d330d6b4c94cfb5aad2ca9ea7eb2c52d934.1524727888.git.jsarha@ti.com
---
 drivers/gpu/drm/drm_panel.c                          | 6 ++++++
 drivers/gpu/drm/panel/panel-innolux-p079zca.c        | 1 -
 drivers/gpu/drm/panel/panel-jdi-lt070me05000.c       | 1 -
 drivers/gpu/drm/panel/panel-lvds.c                   | 1 -
 drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c | 1 -
 drivers/gpu/drm/panel/panel-seiko-43wvf1g.c          | 1 -
 drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c      | 1 -
 drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c      | 1 -
 drivers/gpu/drm/panel/panel-simple.c                 | 1 -
 drivers/gpu/drm/panel/panel-sitronix-st7789v.c       | 1 -
 10 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 308d442a531b..71e407574276 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -94,6 +94,9 @@ EXPORT_SYMBOL(drm_panel_remove);
  *
  * An error is returned if the panel is already attached to another connector.
  *
+ * When unloading, the driver should detach from the panel by calling
+ * drm_panel_detach().
+ *
  * Return: 0 on success or a negative error code on failure.
  */
 int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
@@ -115,6 +118,9 @@ EXPORT_SYMBOL(drm_panel_attach);
  * Detaches a panel from the connector it is attached to. If a panel is not
  * attached to any connector this is effectively a no-op.
  *
+ * This function should not be called by the panel device itself. It
+ * is only for the drm device that called drm_panel_attach().
+ *
  * Return: 0 on success or a negative error code on failure.
  */
 int drm_panel_detach(struct drm_panel *panel)
diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index 57df39b5c589..bb53e0850764 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -292,7 +292,6 @@ static int innolux_panel_remove(struct mipi_dsi_device *dsi)
 		DRM_DEV_ERROR(&dsi->dev, "failed to detach from DSI host: %d\n",
 			      err);
 
-	drm_panel_detach(&innolux->base);
 	innolux_panel_del(innolux);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
index 0a94ab79a6c0..99caa7835e7b 100644
--- a/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
+++ b/drivers/gpu/drm/panel/panel-jdi-lt070me05000.c
@@ -500,7 +500,6 @@ static int jdi_panel_remove(struct mipi_dsi_device *dsi)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n",
 			ret);
 
-	drm_panel_detach(&jdi->base);
 	jdi_panel_del(jdi);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-lvds.c b/drivers/gpu/drm/panel/panel-lvds.c
index 5185819c5b79..8a1687887ae9 100644
--- a/drivers/gpu/drm/panel/panel-lvds.c
+++ b/drivers/gpu/drm/panel/panel-lvds.c
@@ -282,7 +282,6 @@ static int panel_lvds_remove(struct platform_device *pdev)
 {
 	struct panel_lvds *lvds = dev_get_drvdata(&pdev->dev);
 
-	drm_panel_detach(&lvds->panel);
 	drm_panel_remove(&lvds->panel);
 
 	panel_lvds_disable(&lvds->panel);
diff --git a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
index 74a806121f80..cb4dfb98be0f 100644
--- a/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
+++ b/drivers/gpu/drm/panel/panel-panasonic-vvx10f034n00.c
@@ -299,7 +299,6 @@ static int wuxga_nt_panel_remove(struct mipi_dsi_device *dsi)
 	if (ret < 0)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n", ret);
 
-	drm_panel_detach(&wuxga_nt->base);
 	wuxga_nt_panel_del(wuxga_nt);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
index 71c09ed436ae..75f925390551 100644
--- a/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
+++ b/drivers/gpu/drm/panel/panel-seiko-43wvf1g.c
@@ -292,7 +292,6 @@ static int seiko_panel_remove(struct platform_device *pdev)
 {
 	struct seiko_panel *panel = dev_get_drvdata(&pdev->dev);
 
-	drm_panel_detach(&panel->base);
 	drm_panel_remove(&panel->base);
 
 	seiko_panel_disable(&panel->base);
diff --git a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
index 6bf8730f1a21..02fc0f5423d4 100644
--- a/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-lq101r1sx01.c
@@ -418,7 +418,6 @@ static int sharp_panel_remove(struct mipi_dsi_device *dsi)
 	if (err < 0)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n", err);
 
-	drm_panel_detach(&sharp->base);
 	sharp_panel_del(sharp);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
index 494aa9b1628a..e5cae0050f52 100644
--- a/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
+++ b/drivers/gpu/drm/panel/panel-sharp-ls043t1le01.c
@@ -327,7 +327,6 @@ static int sharp_nt_panel_remove(struct mipi_dsi_device *dsi)
 	if (ret < 0)
 		dev_err(&dsi->dev, "failed to detach from DSI host: %d\n", ret);
 
-	drm_panel_detach(&sharp_nt->base);
 	sharp_nt_panel_del(sharp_nt);
 
 	return 0;
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index cbf1ab404ee7..062b6b416b89 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -364,7 +364,6 @@ static int panel_simple_remove(struct device *dev)
 {
 	struct panel_simple *panel = dev_get_drvdata(dev);
 
-	drm_panel_detach(&panel->base);
 	drm_panel_remove(&panel->base);
 
 	panel_simple_disable(&panel->base);
diff --git a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
index 358c64ef1922..74284e5afc5d 100644
--- a/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
+++ b/drivers/gpu/drm/panel/panel-sitronix-st7789v.c
@@ -419,7 +419,6 @@ static int st7789v_remove(struct spi_device *spi)
 {
 	struct st7789v *ctx = spi_get_drvdata(spi);
 
-	drm_panel_detach(&ctx->panel);
 	drm_panel_remove(&ctx->panel);
 
 	if (ctx->backlight)
-- 
cgit v1.2.3


From 0c08754b59da5557532d946599854e6df28edc22 Mon Sep 17 00:00:00 2001
From: Jyri Sarha <jsarha@ti.com>
Date: Thu, 26 Apr 2018 11:07:00 +0300
Subject: drm/panel: Add device_link from panel device to DRM device

Add device_link from panel device (supplier) to DRM device (consumer)
when drm_panel_attach() is called. This patch should protect the master
DRM driver if an attached panel driver unbinds while it is in use. The
device_link should make sure the DRM device is unbound before the panel
driver becomes unavailable.

The device_link is removed when drm_panel_detach() is called. The
drm_panel_detach() should be called by the consumer DRM driver, not the
panel driver, otherwise both drivers are racing to delete the same link.

Signed-off-by: Jyri Sarha <jsarha@ti.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/b53584fd988d045c13de22d81825395b0ae0aad7.1524727888.git.jsarha@ti.com
---
 drivers/gpu/drm/drm_panel.c | 10 ++++++++++
 include/drm/drm_panel.h     |  1 +
 2 files changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 71e407574276..965530a6f4cd 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -24,6 +24,7 @@
 #include <linux/err.h>
 #include <linux/module.h>
 
+#include <drm/drm_device.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_panel.h>
 
@@ -104,6 +105,13 @@ int drm_panel_attach(struct drm_panel *panel, struct drm_connector *connector)
 	if (panel->connector)
 		return -EBUSY;
 
+	panel->link = device_link_add(connector->dev->dev, panel->dev, 0);
+	if (!panel->link) {
+		dev_err(panel->dev, "failed to link panel to %s\n",
+			dev_name(connector->dev->dev));
+		return -EINVAL;
+	}
+
 	panel->connector = connector;
 	panel->drm = connector->dev;
 
@@ -125,6 +133,8 @@ EXPORT_SYMBOL(drm_panel_attach);
  */
 int drm_panel_detach(struct drm_panel *panel)
 {
+	device_link_del(panel->link);
+
 	panel->connector = NULL;
 	panel->drm = NULL;
 
diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h
index 14ac240a1f64..26a1b5fd8796 100644
--- a/include/drm/drm_panel.h
+++ b/include/drm/drm_panel.h
@@ -89,6 +89,7 @@ struct drm_panel {
 	struct drm_device *drm;
 	struct drm_connector *connector;
 	struct device *dev;
+	struct device_link *link;
 
 	const struct drm_panel_funcs *funcs;
 
-- 
cgit v1.2.3


From d9f9565c1f7f51904a5009671595a50b8ab0462b Mon Sep 17 00:00:00 2001
From: Philippe CORNU <philippe.cornu@st.com>
Date: Mon, 23 Apr 2018 16:10:50 +0200
Subject: drm/panel: otm8009a: Fix backlight updates

Backlight updates was not working anymore since the good implementation
of the DSI low-power mode in the DSI host driver. After a longer
analysis, the backlight updates in DSI video mode require the DSI high-
speed mode.

Note: it is important to keep the DSI low-power mode for the rest of the
driver as init sequence, sleep in/out... DSI commands work in low-power
mode.

Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180423141054.13128-2-philippe.cornu@st.com
---
 drivers/gpu/drm/panel/panel-orisetech-otm8009a.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
index 90f1ae4af93c..0fd2e0144d2b 100644
--- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
+++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
@@ -98,6 +98,20 @@ static void otm8009a_dcs_write_buf(struct otm8009a *ctx, const void *data,
 		DRM_WARN("mipi dsi dcs write buffer failed\n");
 }
 
+static void otm8009a_dcs_write_buf_hs(struct otm8009a *ctx, const void *data,
+				      size_t len)
+{
+	struct mipi_dsi_device *dsi = to_mipi_dsi_device(ctx->dev);
+
+	/* data will be sent in dsi hs mode (ie. no lpm) */
+	dsi->mode_flags &= ~MIPI_DSI_MODE_LPM;
+
+	otm8009a_dcs_write_buf(ctx, data, len);
+
+	/* restore back the dsi lpm mode */
+	dsi->mode_flags |= MIPI_DSI_MODE_LPM;
+}
+
 #define dcs_write_seq(ctx, seq...)			\
 ({							\
 	static const u8 d[] = { seq };			\
@@ -387,7 +401,7 @@ static int otm8009a_backlight_update_status(struct backlight_device *bd)
 		 */
 		data[0] = MIPI_DCS_SET_DISPLAY_BRIGHTNESS;
 		data[1] = bd->props.brightness;
-		otm8009a_dcs_write_buf(ctx, data, ARRAY_SIZE(data));
+		otm8009a_dcs_write_buf_hs(ctx, data, ARRAY_SIZE(data));
 
 		/* set Brightness Control & Backlight on */
 		data[1] = 0x24;
@@ -399,7 +413,7 @@ static int otm8009a_backlight_update_status(struct backlight_device *bd)
 
 	/* Update Brightness Control & Backlight */
 	data[0] = MIPI_DCS_WRITE_CONTROL_DISPLAY;
-	otm8009a_dcs_write_buf(ctx, data, ARRAY_SIZE(data));
+	otm8009a_dcs_write_buf_hs(ctx, data, ARRAY_SIZE(data));
 
 	return 0;
 }
-- 
cgit v1.2.3


From 36830ce4eb2b5f6fe796c457b4043160c0e1e1fe Mon Sep 17 00:00:00 2001
From: Philippe CORNU <philippe.cornu@st.com>
Date: Mon, 23 Apr 2018 16:10:51 +0200
Subject: drm/panel: otm8009a: Fix glitches by moving backlight enable to
 otm8009a_enable()

The backlight 1st update was in the otm8009a_prepare() function for a
bad reason: backlight was not working in video mode and the
otm8009a_prepare() is in command mode for the init sequence. As the
backlight is now fixed (no low-power mode), it is good to put it back
in the otm8009a_enable() function, avoiding also image glitches visible
on some "slow" devices.

Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180423141054.13128-3-philippe.cornu@st.com
---
 drivers/gpu/drm/panel/panel-orisetech-otm8009a.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
index 0fd2e0144d2b..de4a16d5275c 100644
--- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
+++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
@@ -330,13 +330,6 @@ static int otm8009a_prepare(struct drm_panel *panel)
 
 	ctx->prepared = true;
 
-	/*
-	 * Power on the backlight. Note: end-user still controls brightness
-	 * Note: ctx->prepared must be true before updating the backlight.
-	 */
-	ctx->bl_dev->props.power = FB_BLANK_UNBLANK;
-	backlight_update_status(ctx->bl_dev);
-
 	return 0;
 }
 
@@ -344,6 +337,16 @@ static int otm8009a_enable(struct drm_panel *panel)
 {
 	struct otm8009a *ctx = panel_to_otm8009a(panel);
 
+	if (ctx->enabled)
+		return 0;
+
+	/*
+	 * Power on the backlight. Note: end-user still controls brightness
+	 * Note: ctx->prepared must be true before updating the backlight.
+	 */
+	ctx->bl_dev->props.power = FB_BLANK_UNBLANK;
+	backlight_update_status(ctx->bl_dev);
+
 	ctx->enabled = true;
 
 	return 0;
-- 
cgit v1.2.3


From 6982b943123d5867997a6d0f8b5976ac3ddb2fa6 Mon Sep 17 00:00:00 2001
From: Philippe CORNU <philippe.cornu@st.com>
Date: Mon, 23 Apr 2018 16:10:52 +0200
Subject: drm/panel: otm8009a: No message if probe success

Remove the message in case of probe success. This comes from a
suggestion followed in the recent integration of the raydium rm68200
panel.

Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180423141054.13128-4-philippe.cornu@st.com
---
 drivers/gpu/drm/panel/panel-orisetech-otm8009a.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
index de4a16d5275c..4c638b7b9943 100644
--- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
+++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
@@ -14,8 +14,6 @@
 #include <linux/regulator/consumer.h>
 #include <video/mipi_display.h>
 
-#define DRV_NAME "orisetech_otm8009a"
-
 #define OTM8009A_BACKLIGHT_DEFAULT	240
 #define OTM8009A_BACKLIGHT_MAX		255
 
@@ -461,7 +459,7 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi)
 	ctx->panel.dev = dev;
 	ctx->panel.funcs = &otm8009a_drm_funcs;
 
-	ctx->bl_dev = backlight_device_register(DRV_NAME "_backlight", dev, ctx,
+	ctx->bl_dev = backlight_device_register(dev_name(dev), dev, ctx,
 						&otm8009a_backlight_ops, NULL);
 	if (IS_ERR(ctx->bl_dev)) {
 		dev_err(dev, "failed to register backlight device\n");
@@ -483,11 +481,6 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi)
 		return ret;
 	}
 
-	DRM_INFO(DRV_NAME "_panel %ux%u@%u %ubpp dsi %udl - ready\n",
-		 default_mode.hdisplay, default_mode.vdisplay,
-		 default_mode.vrefresh,
-		 mipi_dsi_pixel_format_to_bpp(dsi->format), dsi->lanes);
-
 	return 0;
 }
 
@@ -513,7 +506,7 @@ static struct mipi_dsi_driver orisetech_otm8009a_driver = {
 	.probe  = otm8009a_probe,
 	.remove = otm8009a_remove,
 	.driver = {
-		.name = DRV_NAME "_panel",
+		.name = "panel-orisetech-otm8009a",
 		.of_match_table = orisetech_otm8009a_of_match,
 	},
 };
-- 
cgit v1.2.3


From 12a6cbd4f3f10b01b8a190de3766e70492df316b Mon Sep 17 00:00:00 2001
From: Philippe CORNU <philippe.cornu@st.com>
Date: Mon, 23 Apr 2018 16:10:53 +0200
Subject: drm/panel: otm8009a: Use new backlight API

The backlight API provides new functions to enable and disable the
backlight and which hide the intricacies of achieving the correct
result.

Signed-off-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180423141054.13128-5-philippe.cornu@st.com
---
 drivers/gpu/drm/panel/panel-orisetech-otm8009a.c | 26 ++++++++----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
index 4c638b7b9943..87fa316e1d7b 100644
--- a/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
+++ b/drivers/gpu/drm/panel/panel-orisetech-otm8009a.c
@@ -260,11 +260,7 @@ static int otm8009a_disable(struct drm_panel *panel)
 	if (!ctx->enabled)
 		return 0; /* This is not an issue so we return 0 here */
 
-	/* Power off the backlight. Note: end-user still controls brightness */
-	ctx->bl_dev->props.power = FB_BLANK_POWERDOWN;
-	ret = backlight_update_status(ctx->bl_dev);
-	if (ret)
-		return ret;
+	backlight_disable(ctx->bl_dev);
 
 	ret = mipi_dsi_dcs_set_display_off(dsi);
 	if (ret)
@@ -338,12 +334,7 @@ static int otm8009a_enable(struct drm_panel *panel)
 	if (ctx->enabled)
 		return 0;
 
-	/*
-	 * Power on the backlight. Note: end-user still controls brightness
-	 * Note: ctx->prepared must be true before updating the backlight.
-	 */
-	ctx->bl_dev->props.power = FB_BLANK_UNBLANK;
-	backlight_update_status(ctx->bl_dev);
+	backlight_enable(ctx->bl_dev);
 
 	ctx->enabled = true;
 
@@ -459,11 +450,14 @@ static int otm8009a_probe(struct mipi_dsi_device *dsi)
 	ctx->panel.dev = dev;
 	ctx->panel.funcs = &otm8009a_drm_funcs;
 
-	ctx->bl_dev = backlight_device_register(dev_name(dev), dev, ctx,
-						&otm8009a_backlight_ops, NULL);
+	ctx->bl_dev = devm_backlight_device_register(dev, dev_name(dev),
+						     dsi->host->dev, ctx,
+						     &otm8009a_backlight_ops,
+						     NULL);
 	if (IS_ERR(ctx->bl_dev)) {
-		dev_err(dev, "failed to register backlight device\n");
-		return PTR_ERR(ctx->bl_dev);
+		ret = PTR_ERR(ctx->bl_dev);
+		dev_err(dev, "failed to register backlight: %d\n", ret);
+		return ret;
 	}
 
 	ctx->bl_dev->props.max_brightness = OTM8009A_BACKLIGHT_MAX;
@@ -491,8 +485,6 @@ static int otm8009a_remove(struct mipi_dsi_device *dsi)
 	mipi_dsi_detach(dsi);
 	drm_panel_remove(&ctx->panel);
 
-	backlight_device_unregister(ctx->bl_dev);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From eea740a98df9ff914001bd066389b6e8f1024991 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Thu, 26 Apr 2018 15:58:53 +0200
Subject: drm/bridge: cdns: Mark runtime PM operations as maybe unused

Building the driver in a configuration with !PM currently causes a
warning about these operations being unused. Mark them as such to shut
up the compiler.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180426135853.30895-1-thierry.reding@gmail.com
---
 drivers/gpu/drm/bridge/cdns-dsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index c255fc3e1be5..f2d43f24acfb 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -1337,7 +1337,7 @@ static const struct mipi_dsi_host_ops cdns_dsi_ops = {
 	.transfer = cdns_dsi_transfer,
 };
 
-static int cdns_dsi_resume(struct device *dev)
+static int __maybe_unused cdns_dsi_resume(struct device *dev)
 {
 	struct cdns_dsi *dsi = dev_get_drvdata(dev);
 
@@ -1350,7 +1350,7 @@ static int cdns_dsi_resume(struct device *dev)
 	return 0;
 }
 
-static int cdns_dsi_suspend(struct device *dev)
+static int __maybe_unused cdns_dsi_suspend(struct device *dev)
 {
 	struct cdns_dsi *dsi = dev_get_drvdata(dev);
 
-- 
cgit v1.2.3


From 9c04400f7ea6bbdfd0f069f082188c34c2d6a929 Mon Sep 17 00:00:00 2001
From: "spanda@codeaurora.org" <spanda@codeaurora.org>
Date: Tue, 15 May 2018 11:22:44 +0530
Subject: dt-bindings: drm/panel: Document Innolux TV123WAM panel bindings

Innolux TV123WAM is a 12.3" eDP display panel with
2160x1440 resolution, which can be supported by simple
panel driver.

Changes in v1:
 - Make use of simple panel driver instead of creating
   a new driver for this panel (Sean Paul).
 - Combine dt-binding and driver changes into one patch
   as done by other existing panel support changes.

Changes in v2:
 - Separate driver change from dt-binding documentation (Rob Herring).
 - Add the properties from simple-panel binding that are applicable to
   this panel (Rob Herring).

Signed-off-by: Sandeep Panda <spanda@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1526363564-13823-5-git-send-email-spanda@codeaurora.org
---
 .../bindings/display/panel/innolux,tv123wam.txt      | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/innolux,tv123wam.txt

diff --git a/Documentation/devicetree/bindings/display/panel/innolux,tv123wam.txt b/Documentation/devicetree/bindings/display/panel/innolux,tv123wam.txt
new file mode 100644
index 000000000000..a9b35265fa13
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/innolux,tv123wam.txt
@@ -0,0 +1,20 @@
+Innolux TV123WAM 12.3 inch eDP 2K display panel
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
+
+Required properties:
+- compatible: should be "innolux,tv123wam"
+- power-supply: regulator to provide the supply voltage
+
+Optional properties:
+- enable-gpios: GPIO pin to enable or disable the panel
+- backlight: phandle of the backlight device attached to the panel
+
+Example:
+	panel_edp: panel-edp {
+		compatible = "innolux,tv123wam";
+		enable-gpios = <&msmgpio 31 GPIO_ACTIVE_LOW>;
+		power-supply = <&pm8916_l2>;
+		backlight = <&backlight>;
+	};
-- 
cgit v1.2.3


From da50bd4258db62810de4e0f3d75cf7d3d67466b1 Mon Sep 17 00:00:00 2001
From: "spanda@codeaurora.org" <spanda@codeaurora.org>
Date: Tue, 15 May 2018 11:22:43 +0530
Subject: drm/panel: simple: Add Innolux TV123WAM panel driver support

Add support for Innolux TV123WAM, which is a 12.3" eDP display panel
with 2160x1440 resolution.

Changes in v1:
 - Add the compatibility string, display_mode and panel_desc
   structures in alphabetical order (Sean Paul).

Signed-off-by: Sandeep Panda <spanda@codeaurora.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1526363564-13823-4-git-send-email-spanda@codeaurora.org
---
 drivers/gpu/drm/panel/panel-simple.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 062b6b416b89..2209aeddae3c 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1216,6 +1216,30 @@ static const struct panel_desc innolux_n156bge_l21 = {
 	},
 };
 
+static const struct drm_display_mode innolux_tv123wam_mode = {
+	.clock = 206016,
+	.hdisplay = 2160,
+	.hsync_start = 2160 + 48,
+	.hsync_end = 2160 + 48 + 32,
+	.htotal = 2160 + 48 + 32 + 80,
+	.vdisplay = 1440,
+	.vsync_start = 1440 + 3,
+	.vsync_end = 1440 + 3 + 10,
+	.vtotal = 1440 + 3 + 10 + 27,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC,
+};
+
+static const struct panel_desc innolux_tv123wam = {
+	.modes = &innolux_tv123wam_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 259,
+		.height = 173,
+	},
+};
+
 static const struct drm_display_mode innolux_zj070na_01p_mode = {
 	.clock = 51501,
 	.hdisplay = 1024,
@@ -2168,6 +2192,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "innolux,n156bge-l21",
 		.data = &innolux_n156bge_l21,
+	}, {
+		.compatible = "innolux,tv123wam",
+		.data = &innolux_tv123wam,
 	}, {
 		.compatible = "innolux,zj070na-01p",
 		.data = &innolux_zj070na_01p,
-- 
cgit v1.2.3


From 2554f154b46f7d8a933f0616e8170bf4d970a2bf Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Wed, 11 Apr 2018 17:27:41 +0200
Subject: drm/panel: simple: AUO P320HVN03 uses SPWG data ordering

The patch adding support for the AUO P320HVN03 panel was written against a
preliminary datasheet, which specified JEIDA data ordering. Testing with
real hardware has shown that the actually used data ordering is SPWG.

Fixes: 70c0d5b783f5 (drm/panel: simple: add support for AUO P320HVN03)
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180411152741.22483-1-l.stach@pengutronix.de
---
 drivers/gpu/drm/panel/panel-simple.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 2209aeddae3c..ba2631a7de0b 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -686,7 +686,7 @@ static const struct panel_desc auo_p320hvn03 = {
 		.enable = 450,
 		.unprepare = 500,
 	},
-	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_JEIDA,
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
 };
 
 static const struct drm_display_mode auo_t215hvn01_mode = {
-- 
cgit v1.2.3


From c9b6be7dc13e2f87592ee4c9812cb450dba484d5 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Thu, 19 Apr 2018 23:20:03 +0200
Subject: drm/panel: simple: Fix data type in KEO TX31D200VM0BAA timings

All values in a struct struct timing_entry (every entry in
struct display_timing) require an integer. Choose the closest
safe integer of 32.

This avoids a warning seen with clang:
  drivers/gpu/drm/panel/panel-simple.c:1250:27: warning: implicit
       conversion from 'double' to 'u32' (aka 'unsigned int')
       changes value from 33.5 to 33 [-Wliteral-conversion]
         .vfront_porch = { 6, 21, 33.5 },
                         ~        ^~~~
  drivers/gpu/drm/panel/panel-simple.c:1251:26: warning: implicit
        conversion from 'double' to 'u32' (aka 'unsigned int')
        changes value from 33.5 to 33 [-Wliteral-conversion]
          .vback_porch = { 6, 21, 33.5 },
                         ~        ^~~~

Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180419212003.8155-1-stefan@agner.ch
---
 drivers/gpu/drm/panel/panel-simple.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index ba2631a7de0b..964c261cfb78 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1270,8 +1270,8 @@ static const struct display_timing koe_tx31d200vm0baa_timing = {
 	.hback_porch = { 16, 36, 56 },
 	.hsync_len = { 8, 8, 8 },
 	.vactive = { 480, 480, 480 },
-	.vfront_porch = { 6, 21, 33.5 },
-	.vback_porch = { 6, 21, 33.5 },
+	.vfront_porch = { 6, 21, 33 },
+	.vback_porch = { 6, 21, 33 },
 	.vsync_len = { 8, 8, 8 },
 	.flags = DISPLAY_FLAGS_DE_HIGH,
 };
-- 
cgit v1.2.3


From 9d7e70020c244940dc34f19b8d2da6b3f6516946 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:15 +0100
Subject: drm/cirrus: Place GEM BOs in drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-1-daniels@collabora.com
---
 drivers/gpu/drm/cirrus/cirrus_drv.h   |  1 -
 drivers/gpu/drm/cirrus/cirrus_fbdev.c |  8 ++++----
 drivers/gpu/drm/cirrus/cirrus_main.c  | 25 ++++---------------------
 drivers/gpu/drm/cirrus/cirrus_mode.c  |  4 ++--
 4 files changed, 10 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index be2d7e488062..70b23629be0a 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -119,7 +119,6 @@ struct cirrus_connector {
 
 struct cirrus_framebuffer {
 	struct drm_framebuffer		base;
-	struct drm_gem_object *obj;
 };
 
 struct cirrus_mc {
diff --git a/drivers/gpu/drm/cirrus/cirrus_fbdev.c b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
index 32fbfba2c623..a74d32846958 100644
--- a/drivers/gpu/drm/cirrus/cirrus_fbdev.c
+++ b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
@@ -29,7 +29,7 @@ static void cirrus_dirty_update(struct cirrus_fbdev *afbdev,
 	int x2, y2;
 	unsigned long flags;
 
-	obj = afbdev->gfb.obj;
+	obj = afbdev->gfb.base.obj[0];
 	bo = gem_to_cirrus_bo(obj);
 
 	/*
@@ -250,9 +250,9 @@ static int cirrus_fbdev_destroy(struct drm_device *dev,
 
 	drm_fb_helper_unregister_fbi(&gfbdev->helper);
 
-	if (gfb->obj) {
-		drm_gem_object_put_unlocked(gfb->obj);
-		gfb->obj = NULL;
+	if (gfb->base.obj[0]) {
+		drm_gem_object_put_unlocked(gfb->base.obj[0]);
+		gfb->base.obj[0] = NULL;
 	}
 
 	vfree(gfbdev->sysram);
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 26df1e8cd490..f1ee4139ff19 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -10,30 +10,13 @@
  */
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "cirrus_drv.h"
 
-static int cirrus_create_handle(struct drm_framebuffer *fb,
-				struct drm_file* file_priv,
-				unsigned int* handle)
-{
-	struct cirrus_framebuffer *cirrus_fb = to_cirrus_framebuffer(fb);
-
-	return drm_gem_handle_create(file_priv, cirrus_fb->obj, handle);
-}
-
-static void cirrus_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct cirrus_framebuffer *cirrus_fb = to_cirrus_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(cirrus_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(fb);
-}
-
 static const struct drm_framebuffer_funcs cirrus_fb_funcs = {
-	.create_handle = cirrus_create_handle,
-	.destroy = cirrus_user_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
 int cirrus_framebuffer_init(struct drm_device *dev,
@@ -44,7 +27,7 @@ int cirrus_framebuffer_init(struct drm_device *dev,
 	int ret;
 
 	drm_helper_mode_fill_fb_struct(dev, &gfb->base, mode_cmd);
-	gfb->obj = obj;
+	gfb->base.obj[0] = obj;
 	ret = drm_framebuffer_init(dev, &gfb->base, &cirrus_fb_funcs);
 	if (ret) {
 		DRM_ERROR("drm_framebuffer_init failed: %d\n", ret);
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index c91b9b054e3f..91b9c42013ff 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -110,7 +110,7 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 	/* push the previous fb to system ram */
 	if (!atomic && fb) {
 		cirrus_fb = to_cirrus_framebuffer(fb);
-		obj = cirrus_fb->obj;
+		obj = cirrus_fb->base.obj[0];
 		bo = gem_to_cirrus_bo(obj);
 		ret = cirrus_bo_reserve(bo, false);
 		if (ret)
@@ -120,7 +120,7 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 	}
 
 	cirrus_fb = to_cirrus_framebuffer(crtc->primary->fb);
-	obj = cirrus_fb->obj;
+	obj = cirrus_fb->base.obj[0];
 	bo = gem_to_cirrus_bo(obj);
 
 	ret = cirrus_bo_reserve(bo, false);
-- 
cgit v1.2.3


From 121df61e5a301a6b4ef9efd4d1b190f73ef01419 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:16 +0100
Subject: drm/cirrus: cirrus_framebuffer -> drm_framebuffer

Now cirrus_framebuffer is just an empty wrapper around drm_framebuffer,
we can drop it.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-2-daniels@collabora.com
---
 drivers/gpu/drm/cirrus/cirrus_drv.h   |  9 ++-------
 drivers/gpu/drm/cirrus/cirrus_fbdev.c | 20 ++++++++++----------
 drivers/gpu/drm/cirrus/cirrus_main.c  | 20 ++++++++++----------
 drivers/gpu/drm/cirrus/cirrus_mode.c  | 12 +++---------
 4 files changed, 25 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index 70b23629be0a..ce9db7aab225 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -92,7 +92,6 @@
 
 #define to_cirrus_crtc(x) container_of(x, struct cirrus_crtc, base)
 #define to_cirrus_encoder(x) container_of(x, struct cirrus_encoder, base)
-#define to_cirrus_framebuffer(x) container_of(x, struct cirrus_framebuffer, base)
 
 struct cirrus_crtc {
 	struct drm_crtc			base;
@@ -117,10 +116,6 @@ struct cirrus_connector {
 	struct drm_connector		base;
 };
 
-struct cirrus_framebuffer {
-	struct drm_framebuffer		base;
-};
-
 struct cirrus_mc {
 	resource_size_t			vram_size;
 	resource_size_t			vram_base;
@@ -151,7 +146,7 @@ struct cirrus_device {
 
 struct cirrus_fbdev {
 	struct drm_fb_helper helper;
-	struct cirrus_framebuffer gfb;
+	struct drm_framebuffer gfb;
 	void *sysram;
 	int size;
 	int x1, y1, x2, y2; /* dirty rect */
@@ -197,7 +192,7 @@ int cirrus_dumb_create(struct drm_file *file,
 		       struct drm_mode_create_dumb *args);
 
 int cirrus_framebuffer_init(struct drm_device *dev,
-			   struct cirrus_framebuffer *gfb,
+			    struct drm_framebuffer *gfb,
 			    const struct drm_mode_fb_cmd2 *mode_cmd,
 			    struct drm_gem_object *obj);
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_fbdev.c b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
index a74d32846958..b643ac92801c 100644
--- a/drivers/gpu/drm/cirrus/cirrus_fbdev.c
+++ b/drivers/gpu/drm/cirrus/cirrus_fbdev.c
@@ -22,14 +22,14 @@ static void cirrus_dirty_update(struct cirrus_fbdev *afbdev,
 	struct drm_gem_object *obj;
 	struct cirrus_bo *bo;
 	int src_offset, dst_offset;
-	int bpp = afbdev->gfb.base.format->cpp[0];
+	int bpp = afbdev->gfb.format->cpp[0];
 	int ret = -EBUSY;
 	bool unmap = false;
 	bool store_for_later = false;
 	int x2, y2;
 	unsigned long flags;
 
-	obj = afbdev->gfb.base.obj[0];
+	obj = afbdev->gfb.obj[0];
 	bo = gem_to_cirrus_bo(obj);
 
 	/*
@@ -82,7 +82,7 @@ static void cirrus_dirty_update(struct cirrus_fbdev *afbdev,
 	}
 	for (i = y; i < y + height; i++) {
 		/* assume equal stride for now */
-		src_offset = dst_offset = i * afbdev->gfb.base.pitches[0] + (x * bpp);
+		src_offset = dst_offset = i * afbdev->gfb.pitches[0] + (x * bpp);
 		memcpy_toio(bo->kmap.virtual + src_offset, afbdev->sysram + src_offset, width * bpp);
 
 	}
@@ -204,7 +204,7 @@ static int cirrusfb_create(struct drm_fb_helper *helper,
 	gfbdev->sysram = sysram;
 	gfbdev->size = size;
 
-	fb = &gfbdev->gfb.base;
+	fb = &gfbdev->gfb;
 	if (!fb) {
 		DRM_INFO("fb is NULL\n");
 		return -EINVAL;
@@ -246,19 +246,19 @@ static int cirrusfb_create(struct drm_fb_helper *helper,
 static int cirrus_fbdev_destroy(struct drm_device *dev,
 				struct cirrus_fbdev *gfbdev)
 {
-	struct cirrus_framebuffer *gfb = &gfbdev->gfb;
+	struct drm_framebuffer *gfb = &gfbdev->gfb;
 
 	drm_fb_helper_unregister_fbi(&gfbdev->helper);
 
-	if (gfb->base.obj[0]) {
-		drm_gem_object_put_unlocked(gfb->base.obj[0]);
-		gfb->base.obj[0] = NULL;
+	if (gfb->obj[0]) {
+		drm_gem_object_put_unlocked(gfb->obj[0]);
+		gfb->obj[0] = NULL;
 	}
 
 	vfree(gfbdev->sysram);
 	drm_fb_helper_fini(&gfbdev->helper);
-	drm_framebuffer_unregister_private(&gfb->base);
-	drm_framebuffer_cleanup(&gfb->base);
+	drm_framebuffer_unregister_private(gfb);
+	drm_framebuffer_cleanup(gfb);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index f1ee4139ff19..60d54e10a34d 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -20,15 +20,15 @@ static const struct drm_framebuffer_funcs cirrus_fb_funcs = {
 };
 
 int cirrus_framebuffer_init(struct drm_device *dev,
-			    struct cirrus_framebuffer *gfb,
+			    struct drm_framebuffer *gfb,
 			    const struct drm_mode_fb_cmd2 *mode_cmd,
 			    struct drm_gem_object *obj)
 {
 	int ret;
 
-	drm_helper_mode_fill_fb_struct(dev, &gfb->base, mode_cmd);
-	gfb->base.obj[0] = obj;
-	ret = drm_framebuffer_init(dev, &gfb->base, &cirrus_fb_funcs);
+	drm_helper_mode_fill_fb_struct(dev, gfb, mode_cmd);
+	gfb->obj[0] = obj;
+	ret = drm_framebuffer_init(dev, gfb, &cirrus_fb_funcs);
 	if (ret) {
 		DRM_ERROR("drm_framebuffer_init failed: %d\n", ret);
 		return ret;
@@ -43,7 +43,7 @@ cirrus_user_framebuffer_create(struct drm_device *dev,
 {
 	struct cirrus_device *cdev = dev->dev_private;
 	struct drm_gem_object *obj;
-	struct cirrus_framebuffer *cirrus_fb;
+	struct drm_framebuffer *fb;
 	u32 bpp;
 	int ret;
 
@@ -57,19 +57,19 @@ cirrus_user_framebuffer_create(struct drm_device *dev,
 	if (obj == NULL)
 		return ERR_PTR(-ENOENT);
 
-	cirrus_fb = kzalloc(sizeof(*cirrus_fb), GFP_KERNEL);
-	if (!cirrus_fb) {
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb) {
 		drm_gem_object_put_unlocked(obj);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	ret = cirrus_framebuffer_init(dev, cirrus_fb, mode_cmd, obj);
+	ret = cirrus_framebuffer_init(dev, fb, mode_cmd, obj);
 	if (ret) {
 		drm_gem_object_put_unlocked(obj);
-		kfree(cirrus_fb);
+		kfree(fb);
 		return ERR_PTR(ret);
 	}
-	return &cirrus_fb->base;
+	return fb;
 }
 
 static const struct drm_mode_config_funcs cirrus_mode_funcs = {
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 91b9c42013ff..b529f8c8e2a6 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -101,17 +101,13 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 				int x, int y, int atomic)
 {
 	struct cirrus_device *cdev = crtc->dev->dev_private;
-	struct drm_gem_object *obj;
-	struct cirrus_framebuffer *cirrus_fb;
 	struct cirrus_bo *bo;
 	int ret;
 	u64 gpu_addr;
 
 	/* push the previous fb to system ram */
 	if (!atomic && fb) {
-		cirrus_fb = to_cirrus_framebuffer(fb);
-		obj = cirrus_fb->base.obj[0];
-		bo = gem_to_cirrus_bo(obj);
+		bo = gem_to_cirrus_bo(fb->obj[0]);
 		ret = cirrus_bo_reserve(bo, false);
 		if (ret)
 			return ret;
@@ -119,9 +115,7 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 		cirrus_bo_unreserve(bo);
 	}
 
-	cirrus_fb = to_cirrus_framebuffer(crtc->primary->fb);
-	obj = cirrus_fb->base.obj[0];
-	bo = gem_to_cirrus_bo(obj);
+	bo = gem_to_cirrus_bo(crtc->primary->fb->obj[0]);
 
 	ret = cirrus_bo_reserve(bo, false);
 	if (ret)
@@ -133,7 +127,7 @@ static int cirrus_crtc_do_set_base(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	if (&cdev->mode_info.gfbdev->gfb == cirrus_fb) {
+	if (&cdev->mode_info.gfbdev->gfb == crtc->primary->fb) {
 		/* if pushing console in kmap it */
 		ret = ttm_bo_kmap(&bo->bo, 0, bo->bo.num_pages, &bo->kmap);
 		if (ret)
-- 
cgit v1.2.3


From 3823da3aeb47c1b5f07974cf7c87443da2a93ad0 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:17 +0100
Subject: drm/virtio: Place GEM BOs in drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-3-daniels@collabora.com
---
 drivers/gpu/drm/virtio/virtgpu_display.c | 30 +++++-------------------------
 drivers/gpu/drm/virtio/virtgpu_drv.h     |  1 -
 drivers/gpu/drm/virtio/virtgpu_fb.c      |  8 ++++----
 drivers/gpu/drm/virtio/virtgpu_plane.c   |  4 ++--
 4 files changed, 11 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index a5edd86603d9..d6dd769a7ad3 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -28,6 +28,7 @@
 #include "virtgpu_drv.h"
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #define XRES_MIN    32
 #define YRES_MIN    32
@@ -48,16 +49,6 @@ static const struct drm_crtc_funcs virtio_gpu_crtc_funcs = {
 	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
 };
 
-static void virtio_gpu_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct virtio_gpu_framebuffer *virtio_gpu_fb
-		= to_virtio_gpu_framebuffer(fb);
-
-	drm_gem_object_put_unlocked(virtio_gpu_fb->obj);
-	drm_framebuffer_cleanup(fb);
-	kfree(virtio_gpu_fb);
-}
-
 static int
 virtio_gpu_framebuffer_surface_dirty(struct drm_framebuffer *fb,
 				     struct drm_file *file_priv,
@@ -71,20 +62,9 @@ virtio_gpu_framebuffer_surface_dirty(struct drm_framebuffer *fb,
 	return virtio_gpu_surface_dirty(virtio_gpu_fb, clips, num_clips);
 }
 
-static int
-virtio_gpu_framebuffer_create_handle(struct drm_framebuffer *fb,
-				     struct drm_file *file_priv,
-				     unsigned int *handle)
-{
-	struct virtio_gpu_framebuffer *virtio_gpu_fb =
-		to_virtio_gpu_framebuffer(fb);
-
-	return drm_gem_handle_create(file_priv, virtio_gpu_fb->obj, handle);
-}
-
 static const struct drm_framebuffer_funcs virtio_gpu_fb_funcs = {
-	.create_handle = virtio_gpu_framebuffer_create_handle,
-	.destroy = virtio_gpu_user_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 	.dirty = virtio_gpu_framebuffer_surface_dirty,
 };
 
@@ -97,7 +77,7 @@ virtio_gpu_framebuffer_init(struct drm_device *dev,
 	int ret;
 	struct virtio_gpu_object *bo;
 
-	vgfb->obj = obj;
+	vgfb->base.obj[0] = obj;
 
 	bo = gem_to_virtio_gpu_obj(obj);
 
@@ -105,7 +85,7 @@ virtio_gpu_framebuffer_init(struct drm_device *dev,
 
 	ret = drm_framebuffer_init(dev, &vgfb->base, &virtio_gpu_fb_funcs);
 	if (ret) {
-		vgfb->obj = NULL;
+		vgfb->base.obj[0] = NULL;
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_drv.h b/drivers/gpu/drm/virtio/virtgpu_drv.h
index d25c8ca224aa..65605e207bbe 100644
--- a/drivers/gpu/drm/virtio/virtgpu_drv.h
+++ b/drivers/gpu/drm/virtio/virtgpu_drv.h
@@ -124,7 +124,6 @@ struct virtio_gpu_output {
 
 struct virtio_gpu_framebuffer {
 	struct drm_framebuffer base;
-	struct drm_gem_object *obj;
 	int x1, y1, x2, y2; /* dirty rect */
 	spinlock_t dirty_lock;
 	uint32_t hw_res_handle;
diff --git a/drivers/gpu/drm/virtio/virtgpu_fb.c b/drivers/gpu/drm/virtio/virtgpu_fb.c
index 8af69ab58b89..a121b1c79522 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fb.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fb.c
@@ -46,7 +46,7 @@ static int virtio_gpu_dirty_update(struct virtio_gpu_framebuffer *fb,
 	int bpp = fb->base.format->cpp[0];
 	int x2, y2;
 	unsigned long flags;
-	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(fb->obj);
+	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(fb->base.obj[0]);
 
 	if ((width <= 0) ||
 	    (x + width > fb->base.width) ||
@@ -121,7 +121,7 @@ int virtio_gpu_surface_dirty(struct virtio_gpu_framebuffer *vgfb,
 			     unsigned int num_clips)
 {
 	struct virtio_gpu_device *vgdev = vgfb->base.dev->dev_private;
-	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(vgfb->obj);
+	struct virtio_gpu_object *obj = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 	struct drm_clip_rect norect;
 	struct drm_clip_rect *clips_ptr;
 	int left, right, top, bottom;
@@ -305,8 +305,8 @@ static int virtio_gpu_fbdev_destroy(struct drm_device *dev,
 
 	drm_fb_helper_unregister_fbi(&vgfbdev->helper);
 
-	if (vgfb->obj)
-		vgfb->obj = NULL;
+	if (vgfb->base.obj[0])
+		vgfb->base.obj[0] = NULL;
 	drm_fb_helper_fini(&vgfbdev->helper);
 	drm_framebuffer_cleanup(&vgfb->base);
 
diff --git a/drivers/gpu/drm/virtio/virtgpu_plane.c b/drivers/gpu/drm/virtio/virtgpu_plane.c
index 71ba455af915..dc5b5b2b7aab 100644
--- a/drivers/gpu/drm/virtio/virtgpu_plane.c
+++ b/drivers/gpu/drm/virtio/virtgpu_plane.c
@@ -154,7 +154,7 @@ static void virtio_gpu_primary_plane_update(struct drm_plane *plane,
 
 	if (plane->state->fb) {
 		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
-		bo = gem_to_virtio_gpu_obj(vgfb->obj);
+		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 		handle = bo->hw_res_handle;
 		if (bo->dumb) {
 			virtio_gpu_cmd_transfer_to_host_2d
@@ -208,7 +208,7 @@ static void virtio_gpu_cursor_plane_update(struct drm_plane *plane,
 
 	if (plane->state->fb) {
 		vgfb = to_virtio_gpu_framebuffer(plane->state->fb);
-		bo = gem_to_virtio_gpu_obj(vgfb->obj);
+		bo = gem_to_virtio_gpu_obj(vgfb->base.obj[0]);
 		handle = bo->hw_res_handle;
 	} else {
 		handle = 0;
-- 
cgit v1.2.3


From ecb8a947855c9658cd0382f3cab39f91a7ebe86a Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:33 +0100
Subject: drm/armada: Move GEM BO to drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Russell King <linux@armlinux.org.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-19-daniels@collabora.com
---
 drivers/gpu/drm/armada/armada_fb.c | 23 ++++-------------------
 drivers/gpu/drm/armada/armada_fb.h |  3 +--
 2 files changed, 5 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_fb.c b/drivers/gpu/drm/armada/armada_fb.c
index ac92bce07ecd..edd15126bde9 100644
--- a/drivers/gpu/drm/armada/armada_fb.c
+++ b/drivers/gpu/drm/armada/armada_fb.c
@@ -7,30 +7,15 @@
  */
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include "armada_drm.h"
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
 
-static void armada_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(fb);
-
-	drm_framebuffer_cleanup(&dfb->fb);
-	drm_gem_object_put_unlocked(&dfb->obj->obj);
-	kfree(dfb);
-}
-
-static int armada_fb_create_handle(struct drm_framebuffer *fb,
-	struct drm_file *dfile, unsigned int *handle)
-{
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(fb);
-	return drm_gem_handle_create(dfile, &dfb->obj->obj, handle);
-}
-
 static const struct drm_framebuffer_funcs armada_fb_funcs = {
-	.destroy	= armada_fb_destroy,
-	.create_handle	= armada_fb_create_handle,
+	.destroy	= drm_gem_fb_destroy,
+	.create_handle	= drm_gem_fb_create_handle,
 };
 
 struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
@@ -78,7 +63,7 @@ struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
 
 	dfb->fmt = format;
 	dfb->mod = config;
-	dfb->obj = obj;
+	dfb->fb.obj[0] = &obj->obj;
 
 	drm_helper_mode_fill_fb_struct(dev, &dfb->fb, mode);
 
diff --git a/drivers/gpu/drm/armada/armada_fb.h b/drivers/gpu/drm/armada/armada_fb.h
index 48073c4f54d8..5c130ff5da77 100644
--- a/drivers/gpu/drm/armada/armada_fb.h
+++ b/drivers/gpu/drm/armada/armada_fb.h
@@ -10,13 +10,12 @@
 
 struct armada_framebuffer {
 	struct drm_framebuffer	fb;
-	struct armada_gem_object *obj;
 	uint8_t			fmt;
 	uint8_t			mod;
 };
 #define drm_fb_to_armada_fb(dfb) \
 	container_of(dfb, struct armada_framebuffer, fb)
-#define drm_fb_obj(fb) drm_fb_to_armada_fb(fb)->obj
+#define drm_fb_obj(fb) drm_to_armada_gem((fb)->obj[0])
 
 struct armada_framebuffer *armada_framebuffer_create(struct drm_device *,
 	const struct drm_mode_fb_cmd2 *, struct armada_gem_object *);
-- 
cgit v1.2.3


From bc61c97502e26af1be54022883d14ee0c03379fc Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:34 +0100
Subject: drm/gma500: Move GEM BO to drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Cc: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-20-daniels@collabora.com
---
 drivers/gpu/drm/gma500/accel_2d.c      |  2 +-
 drivers/gpu/drm/gma500/framebuffer.c   | 62 ++++++----------------------------
 drivers/gpu/drm/gma500/framebuffer.h   |  1 -
 drivers/gpu/drm/gma500/gma_display.c   | 10 +++---
 drivers/gpu/drm/gma500/gtt.h           |  2 ++
 drivers/gpu/drm/gma500/oaktrail_crtc.c |  3 +-
 6 files changed, 20 insertions(+), 60 deletions(-)

diff --git a/drivers/gpu/drm/gma500/accel_2d.c b/drivers/gpu/drm/gma500/accel_2d.c
index c51d9259c7a7..204c8e452eb7 100644
--- a/drivers/gpu/drm/gma500/accel_2d.c
+++ b/drivers/gpu/drm/gma500/accel_2d.c
@@ -251,7 +251,7 @@ static void psbfb_copyarea_accel(struct fb_info *info,
 	if (!fb)
 		return;
 
-	offset = psbfb->gtt->offset;
+	offset = to_gtt_range(fb->obj[0])->offset;
 	stride = fb->pitches[0];
 
 	switch (fb->format->depth) {
diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index cb0a2ae916e0..8fa4ef192c1e 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -33,6 +33,7 @@
 #include <drm/drm.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "psb_drv.h"
 #include "psb_intel_reg.h"
@@ -40,14 +41,9 @@
 #include "framebuffer.h"
 #include "gtt.h"
 
-static void psb_user_framebuffer_destroy(struct drm_framebuffer *fb);
-static int psb_user_framebuffer_create_handle(struct drm_framebuffer *fb,
-					      struct drm_file *file_priv,
-					      unsigned int *handle);
-
 static const struct drm_framebuffer_funcs psb_fb_funcs = {
-	.destroy = psb_user_framebuffer_destroy,
-	.create_handle = psb_user_framebuffer_create_handle,
+	.destroy = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
 };
 
 #define CMAP_TOHW(_val, _width) ((((_val) << (_width)) + 0x7FFF - (_val)) >> 16)
@@ -96,17 +92,18 @@ static int psbfb_pan(struct fb_var_screeninfo *var, struct fb_info *info)
 	struct psb_fbdev *fbdev = info->par;
 	struct psb_framebuffer *psbfb = &fbdev->pfb;
 	struct drm_device *dev = psbfb->base.dev;
+	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
 
 	/*
 	 *	We have to poke our nose in here. The core fb code assumes
 	 *	panning is part of the hardware that can be invoked before
 	 *	the actual fb is mapped. In our case that isn't quite true.
 	 */
-	if (psbfb->gtt->npage) {
+	if (gtt->npage) {
 		/* GTT roll shifts in 4K pages, we need to shift the right
 		   number of pages */
 		int pages = info->fix.line_length >> 12;
-		psb_gtt_roll(dev, psbfb->gtt, var->yoffset * pages);
+		psb_gtt_roll(dev, gtt, var->yoffset * pages);
 	}
         return 0;
 }
@@ -117,13 +114,14 @@ static int psbfb_vm_fault(struct vm_fault *vmf)
 	struct psb_framebuffer *psbfb = vma->vm_private_data;
 	struct drm_device *dev = psbfb->base.dev;
 	struct drm_psb_private *dev_priv = dev->dev_private;
+	struct gtt_range *gtt = to_gtt_range(psbfb->base.obj[0]);
 	int page_num;
 	int i;
 	unsigned long address;
 	int ret;
 	unsigned long pfn;
 	unsigned long phys_addr = (unsigned long)dev_priv->stolen_base +
-				  psbfb->gtt->offset;
+				  gtt->offset;
 
 	page_num = vma_pages(vma);
 	address = vmf->address - (vmf->pgoff << PAGE_SHIFT);
@@ -246,7 +244,7 @@ static int psb_framebuffer_init(struct drm_device *dev,
 		return -EINVAL;
 
 	drm_helper_mode_fill_fb_struct(dev, &fb->base, mode_cmd);
-	fb->gtt = gt;
+	fb->base.obj[0] = &gt->gem;
 	ret = drm_framebuffer_init(dev, &fb->base, &psb_fb_funcs);
 	if (ret) {
 		dev_err(dev->dev, "framebuffer init failed: %d\n", ret);
@@ -518,8 +516,8 @@ static int psb_fbdev_destroy(struct drm_device *dev, struct psb_fbdev *fbdev)
 	drm_framebuffer_unregister_private(&psbfb->base);
 	drm_framebuffer_cleanup(&psbfb->base);
 
-	if (psbfb->gtt)
-		drm_gem_object_unreference_unlocked(&psbfb->gtt->gem);
+	if (psbfb->base.obj[0])
+		drm_gem_object_unreference_unlocked(psbfb->base.obj[0]);
 	return 0;
 }
 
@@ -576,44 +574,6 @@ static void psb_fbdev_fini(struct drm_device *dev)
 	dev_priv->fbdev = NULL;
 }
 
-/**
- *	psb_user_framebuffer_create_handle - add hamdle to a framebuffer
- *	@fb: framebuffer
- *	@file_priv: our DRM file
- *	@handle: returned handle
- *
- *	Our framebuffer object is a GTT range which also contains a GEM
- *	object. We need to turn it into a handle for userspace. GEM will do
- *	the work for us
- */
-static int psb_user_framebuffer_create_handle(struct drm_framebuffer *fb,
-					      struct drm_file *file_priv,
-					      unsigned int *handle)
-{
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
-	struct gtt_range *r = psbfb->gtt;
-	return drm_gem_handle_create(file_priv, &r->gem, handle);
-}
-
-/**
- *	psb_user_framebuffer_destroy	-	destruct user created fb
- *	@fb: framebuffer
- *
- *	User framebuffers are backed by GEM objects so all we have to do is
- *	clean up a bit and drop the reference, GEM will handle the fallout
- */
-static void psb_user_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
-	struct gtt_range *r = psbfb->gtt;
-
-	/* Let DRM do its clean up */
-	drm_framebuffer_cleanup(fb);
-	/*  We are no longer using the resource in GEM */
-	drm_gem_object_unreference_unlocked(&r->gem);
-	kfree(fb);
-}
-
 static const struct drm_mode_config_funcs psb_mode_funcs = {
 	.fb_create = psb_user_framebuffer_create,
 	.output_poll_changed = drm_fb_helper_output_poll_changed,
diff --git a/drivers/gpu/drm/gma500/framebuffer.h b/drivers/gpu/drm/gma500/framebuffer.h
index 395f20b07aab..23dc3c5f8f0d 100644
--- a/drivers/gpu/drm/gma500/framebuffer.h
+++ b/drivers/gpu/drm/gma500/framebuffer.h
@@ -31,7 +31,6 @@ struct psb_framebuffer {
 	struct drm_framebuffer base;
 	struct address_space *addr_space;
 	struct fb_info *fbdev;
-	struct gtt_range *gtt;
 };
 
 struct psb_fbdev {
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index f3c48a2be71b..c8f071c47daf 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -60,7 +60,7 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_framebuffer *fb = crtc->primary->fb;
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
+	struct gtt_range *gtt = to_gtt_range(fb->obj[0]);
 	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
@@ -78,10 +78,10 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 
 	/* We are displaying this buffer, make sure it is actually loaded
 	   into the GTT */
-	ret = psb_gtt_pin(psbfb->gtt);
+	ret = psb_gtt_pin(gtt);
 	if (ret < 0)
 		goto gma_pipe_set_base_exit;
-	start = psbfb->gtt->offset;
+	start = gtt->offset;
 	offset = y * fb->pitches[0] + x * fb->format->cpp[0];
 
 	REG_WRITE(map->stride, fb->pitches[0]);
@@ -129,7 +129,7 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 gma_pipe_cleaner:
 	/* If there was a previous display we can now unpin it */
 	if (old_fb)
-		psb_gtt_unpin(to_psb_fb(old_fb)->gtt);
+		psb_gtt_unpin(to_gtt_range(old_fb->obj[0]));
 
 gma_pipe_set_base_exit:
 	gma_power_end(dev);
@@ -491,7 +491,7 @@ void gma_crtc_disable(struct drm_crtc *crtc)
 	crtc_funcs->dpms(crtc, DRM_MODE_DPMS_OFF);
 
 	if (crtc->primary->fb) {
-		gt = to_psb_fb(crtc->primary->fb)->gtt;
+		gt = to_gtt_range(crtc->primary->fb->obj[0]);
 		psb_gtt_unpin(gt);
 	}
 }
diff --git a/drivers/gpu/drm/gma500/gtt.h b/drivers/gpu/drm/gma500/gtt.h
index cdbb350c9d5d..cb0c3a2a1fd4 100644
--- a/drivers/gpu/drm/gma500/gtt.h
+++ b/drivers/gpu/drm/gma500/gtt.h
@@ -53,6 +53,8 @@ struct gtt_range {
 	int roll;			/* Roll applied to the GTT entries */
 };
 
+#define to_gtt_range(x) container_of(x, struct gtt_range, gem)
+
 extern struct gtt_range *psb_gtt_alloc_range(struct drm_device *dev, int len,
 					     const char *name, int backed,
 					     u32 align);
diff --git a/drivers/gpu/drm/gma500/oaktrail_crtc.c b/drivers/gpu/drm/gma500/oaktrail_crtc.c
index 0fff269d3fe6..1b7fd6a9d8a5 100644
--- a/drivers/gpu/drm/gma500/oaktrail_crtc.c
+++ b/drivers/gpu/drm/gma500/oaktrail_crtc.c
@@ -600,7 +600,6 @@ static int oaktrail_pipe_set_base(struct drm_crtc *crtc,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_framebuffer *fb = crtc->primary->fb;
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
 	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
@@ -617,7 +616,7 @@ static int oaktrail_pipe_set_base(struct drm_crtc *crtc,
 	if (!gma_power_begin(dev, true))
 		return 0;
 
-	start = psbfb->gtt->offset;
+	start = to_gtt_range(fb->obj[0])->offset;
 	offset = y * fb->pitches[0] + x * fb->format->cpp[0];
 
 	REG_WRITE(map->stride, fb->pitches[0]);
-- 
cgit v1.2.3


From 080205096579a07fa1b18fcd28ff4d41c3c6e4d7 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:35 +0100
Subject: drm/msm: Move GEM BOs to drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle function the same as the GEM framebuffer helper, we
can reuse that.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Cc: Rob Clark <robdclark@gmail.com>
Cc: linux-arm-msm@vger.kernel.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-21-daniels@collabora.com
---
 drivers/gpu/drm/msm/msm_fb.c | 54 +++++++++-----------------------------------
 1 file changed, 11 insertions(+), 43 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_fb.c b/drivers/gpu/drm/msm/msm_fb.c
index 7a16242bf8bf..2a7348aeb38d 100644
--- a/drivers/gpu/drm/msm/msm_fb.c
+++ b/drivers/gpu/drm/msm/msm_fb.c
@@ -17,6 +17,7 @@
 
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "msm_drv.h"
 #include "msm_kms.h"
@@ -25,49 +26,20 @@
 struct msm_framebuffer {
 	struct drm_framebuffer base;
 	const struct msm_format *format;
-	struct drm_gem_object *planes[MAX_PLANE];
 };
 #define to_msm_framebuffer(x) container_of(x, struct msm_framebuffer, base)
 
 static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 		const struct drm_mode_fb_cmd2 *mode_cmd, struct drm_gem_object **bos);
 
-static int msm_framebuffer_create_handle(struct drm_framebuffer *fb,
-		struct drm_file *file_priv,
-		unsigned int *handle)
-{
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	return drm_gem_handle_create(file_priv,
-			msm_fb->planes[0], handle);
-}
-
-static void msm_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	int i, n = fb->format->num_planes;
-
-	DBG("destroy: FB ID: %d (%p)", fb->base.id, fb);
-
-	drm_framebuffer_cleanup(fb);
-
-	for (i = 0; i < n; i++) {
-		struct drm_gem_object *bo = msm_fb->planes[i];
-
-		drm_gem_object_put_unlocked(bo);
-	}
-
-	kfree(msm_fb);
-}
-
 static const struct drm_framebuffer_funcs msm_framebuffer_funcs = {
-	.create_handle = msm_framebuffer_create_handle,
-	.destroy = msm_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
 #ifdef CONFIG_DEBUG_FS
 void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
 	seq_printf(m, "fb: %dx%d@%4.4s (%2d, ID:%d)\n",
@@ -77,7 +49,7 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 	for (i = 0; i < n; i++) {
 		seq_printf(m, "   %d: offset=%d pitch=%d, obj: ",
 				i, fb->offsets[i], fb->pitches[i]);
-		msm_gem_describe(msm_fb->planes[i], m);
+		msm_gem_describe(fb->obj[i], m);
 	}
 }
 #endif
@@ -90,12 +62,11 @@ void msm_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int ret, i, n = fb->format->num_planes;
 	uint64_t iova;
 
 	for (i = 0; i < n; i++) {
-		ret = msm_gem_get_iova(msm_fb->planes[i], aspace, &iova);
+		ret = msm_gem_get_iova(fb->obj[i], aspace, &iova);
 		DBG("FB[%u]: iova[%d]: %08llx (%d)", fb->base.id, i, iova, ret);
 		if (ret)
 			return ret;
@@ -107,26 +78,23 @@ int msm_framebuffer_prepare(struct drm_framebuffer *fb,
 void msm_framebuffer_cleanup(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
 	for (i = 0; i < n; i++)
-		msm_gem_put_iova(msm_fb->planes[i], aspace);
+		msm_gem_put_iova(fb->obj[i], aspace);
 }
 
 uint32_t msm_framebuffer_iova(struct drm_framebuffer *fb,
 		struct msm_gem_address_space *aspace, int plane)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	if (!msm_fb->planes[plane])
+	if (!fb->obj[plane])
 		return 0;
-	return msm_gem_iova(msm_fb->planes[plane], aspace) + fb->offsets[plane];
+	return msm_gem_iova(fb->obj[plane], aspace) + fb->offsets[plane];
 }
 
 struct drm_gem_object *msm_framebuffer_bo(struct drm_framebuffer *fb, int plane)
 {
-	struct msm_framebuffer *msm_fb = to_msm_framebuffer(fb);
-	return msm_fb->planes[plane];
+	return drm_gem_fb_get_obj(fb, plane);
 }
 
 const struct msm_format *msm_framebuffer_format(struct drm_framebuffer *fb)
@@ -202,7 +170,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 
 	msm_fb->format = format;
 
-	if (n > ARRAY_SIZE(msm_fb->planes)) {
+	if (n > ARRAY_SIZE(fb->obj)) {
 		ret = -EINVAL;
 		goto fail;
 	}
@@ -221,7 +189,7 @@ static struct drm_framebuffer *msm_framebuffer_init(struct drm_device *dev,
 			goto fail;
 		}
 
-		msm_fb->planes[i] = bos[i];
+		msm_fb->base.obj[i] = bos[i];
 	}
 
 	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
-- 
cgit v1.2.3


From 7f7105f99b75aca4f8c2a748ed6b82c7f8be3293 Mon Sep 17 00:00:00 2001
From: Ondrej Zary <linux@rainbow-software.org>
Date: Fri, 9 Mar 2018 23:22:04 +0100
Subject: drm/i915: Disable LVDS on Radiant P845
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Radiant P845 does not have LVDS, only VGA.

Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105468
Signed-off-by: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180309222204.4771-1-linux@rainbow-software.org
---
 drivers/gpu/drm/i915/intel_lvds.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index cc4cc8669af3..907d0bf853ef 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -825,6 +825,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_EXACT_MATCH(DMI_BOARD_NAME, "D525MW"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Radiant P845",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Radiant Systems Inc"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "P845"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
-- 
cgit v1.2.3


From a393e9649582894078130f5741877bbafa0bd8a9 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 17 May 2018 20:03:05 +0300
Subject: drm/i915: Use intel_ddi_dp_voltage_max() for HSW/BDW too
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use intel_ddi_dp_voltage_max() for HSW/BDW too instead of letting these
fall through the if ladder in a weird way. This function will look at
the actual buf trans tables we have for HSW/BDW to determine the max
vswing level.

It looks to me like the current code leads HSW port A down the IVB port
A path, HSW port B+ and BDW fall through to the very end. Both cases do
result in the correct max vswing level 2, but it's very hard to see that
from the code.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517170309.28630-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_dp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2cc58596ff5a..4755bb1b0b40 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3220,12 +3220,12 @@ uint8_t
 intel_dp_voltage_max(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum port port = dp_to_dig_port(intel_dp)->base.port;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	enum port port = encoder->port;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	if (HAS_DDI(dev_priv))
 		return intel_ddi_dp_voltage_max(encoder);
-	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
 	else if (IS_GEN7(dev_priv) && port == PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_2;
-- 
cgit v1.2.3


From 4718a365cf12094ed131089518003ac7ecb66743 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 17 May 2018 20:03:06 +0300
Subject: drm/i915: Use the same vswing->max_preemph mapping on HSW/BDW as on
 SKL+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All DDI platforms support the full set of preemph settings for each
supported vswing, so let's use the same code for them. We'll also move
the code into intel_ddi.c so that it sits closer to the actual buf trans
tables.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517170309.28630-2-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_ddi.c | 20 ++++++++++++++++++++
 drivers/gpu/drm/i915/intel_dp.c  | 30 ++++--------------------------
 drivers/gpu/drm/i915/intel_drv.h |  2 ++
 3 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index b98ac0541f19..1665bc588241 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -2115,6 +2115,26 @@ u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder)
 		DP_TRAIN_VOLTAGE_SWING_MASK;
 }
 
+/*
+ * We assume that the full set of pre-emphasis values can be
+ * used on all DDI platforms. Should that change we need to
+ * rethink this code.
+ */
+u8 intel_ddi_dp_pre_emphasis_max(struct intel_encoder *encoder, u8 voltage_swing)
+{
+	switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
+		return DP_TRAIN_PRE_EMPH_LEVEL_3;
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
+		return DP_TRAIN_PRE_EMPH_LEVEL_2;
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
+		return DP_TRAIN_PRE_EMPH_LEVEL_1;
+	case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
+	default:
+		return DP_TRAIN_PRE_EMPH_LEVEL_0;
+	}
+}
+
 static void cnl_ddi_vswing_program(struct intel_encoder *encoder,
 				   int level, enum intel_output_type type)
 {
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 4755bb1b0b40..538b10084a9d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3239,33 +3239,11 @@ uint8_t
 intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum port port = dp_to_dig_port(intel_dp)->base.port;
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	enum port port = encoder->port;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
-			return DP_TRAIN_PRE_EMPH_LEVEL_3;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
-			return DP_TRAIN_PRE_EMPH_LEVEL_2;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
-			return DP_TRAIN_PRE_EMPH_LEVEL_1;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
-			return DP_TRAIN_PRE_EMPH_LEVEL_0;
-		default:
-			return DP_TRAIN_PRE_EMPH_LEVEL_0;
-		}
-	} else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
-		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
-			return DP_TRAIN_PRE_EMPH_LEVEL_3;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_1:
-			return DP_TRAIN_PRE_EMPH_LEVEL_2;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_2:
-			return DP_TRAIN_PRE_EMPH_LEVEL_1;
-		case DP_TRAIN_VOLTAGE_SWING_LEVEL_3:
-		default:
-			return DP_TRAIN_PRE_EMPH_LEVEL_0;
-		}
+	if (HAS_DDI(dev_priv)) {
+		return intel_ddi_dp_pre_emphasis_max(encoder, voltage_swing);
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
 		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 12002fc77235..22af249393a4 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1410,6 +1410,8 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 u32 bxt_signal_levels(struct intel_dp *intel_dp);
 uint32_t ddi_signal_levels(struct intel_dp *intel_dp);
 u8 intel_ddi_dp_voltage_max(struct intel_encoder *encoder);
+u8 intel_ddi_dp_pre_emphasis_max(struct intel_encoder *encoder,
+				 u8 voltage_swing);
 int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
 				     bool enable);
 void icl_map_plls_to_ports(struct drm_crtc *crtc,
-- 
cgit v1.2.3


From b752e995829e3644015300103a31c48de2634169 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 17 May 2018 20:03:07 +0300
Subject: drm/i915: Check for IVB instead of gen7 when we think about IVB CPU
 eDP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Almost all of the GEN7 checks in the DP code are actually looking for
IVB. HSW doesn't even take these codepaths, and VLV is excluded on
account of not having port A. So let's change the checks to IS_IVB to
make the code less confusing.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517170309.28630-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/intel_dp.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 538b10084a9d..263e4b1d1db9 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1989,7 +1989,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 
 	/* Split out the IBX/CPU vs CPT settings */
 
-	if (IS_GEN7(dev_priv) && port == PORT_A) {
+	if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PHSYNC)
 			intel_dp->DP |= DP_SYNC_HS_HIGH;
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
@@ -2669,7 +2669,7 @@ static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 	if (!(tmp & DP_PORT_EN))
 		goto out;
 
-	if (IS_GEN7(dev_priv) && port == PORT_A) {
+	if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
 		*pipe = PORT_TO_PIPE_CPT(tmp);
 	} else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) {
 		enum pipe p;
@@ -2908,7 +2908,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 		}
 		I915_WRITE(DP_TP_CTL(port), temp);
 
-	} else if ((IS_GEN7(dev_priv) && port == PORT_A) ||
+	} else if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) ||
 		   (HAS_PCH_CPT(dev_priv) && port != PORT_A)) {
 		*DP &= ~DP_LINK_TRAIN_MASK_CPT;
 
@@ -3227,7 +3227,7 @@ intel_dp_voltage_max(struct intel_dp *intel_dp)
 		return intel_ddi_dp_voltage_max(encoder);
 	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
-	else if (IS_GEN7(dev_priv) && port == PORT_A)
+	else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_2;
 	else if (HAS_PCH_CPT(dev_priv) && port != PORT_A)
 		return DP_TRAIN_VOLTAGE_SWING_LEVEL_3;
@@ -3256,7 +3256,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing)
 		default:
 			return DP_TRAIN_PRE_EMPH_LEVEL_0;
 		}
-	} else if (IS_GEN7(dev_priv) && port == PORT_A) {
+	} else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
 		switch (voltage_swing & DP_TRAIN_VOLTAGE_SWING_MASK) {
 		case DP_TRAIN_VOLTAGE_SWING_LEVEL_0:
 			return DP_TRAIN_PRE_EMPH_LEVEL_2;
@@ -3565,7 +3565,7 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp)
 		signal_levels = chv_signal_levels(intel_dp);
 	} else if (IS_VALLEYVIEW(dev_priv)) {
 		signal_levels = vlv_signal_levels(intel_dp);
-	} else if (IS_GEN7(dev_priv) && port == PORT_A) {
+	} else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
 		signal_levels = gen7_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB;
 	} else if (IS_GEN6(dev_priv) && port == PORT_A) {
@@ -3655,7 +3655,7 @@ intel_dp_link_down(struct intel_encoder *encoder,
 
 	DRM_DEBUG_KMS("\n");
 
-	if ((IS_GEN7(dev_priv) && port == PORT_A) ||
+	if ((IS_IVYBRIDGE(dev_priv) && port == PORT_A) ||
 	    (HAS_PCH_CPT(dev_priv) && port != PORT_A)) {
 		DP &= ~DP_LINK_TRAIN_MASK_CPT;
 		DP |= DP_LINK_TRAIN_PAT_IDLE_CPT;
-- 
cgit v1.2.3


From 4d82c2b5f09f5b09ac55e557c0436eb4b29c07fe Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 17 May 2018 20:03:08 +0300
Subject: drm/i915: Rename SNB/IVB CPU eDP signal level funcs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To make the intent more clear, let's rename the signal level funcs for
the SNB/IVB CPU eDP.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517170309.28630-4-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_dp.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 263e4b1d1db9..cd4c60bfc4c2 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3488,9 +3488,9 @@ gen4_signal_levels(uint8_t train_set)
 	return signal_levels;
 }
 
-/* Gen6's DP voltage swing and pre-emphasis control */
+/* SNB CPU eDP voltage swing and pre-emphasis control */
 static uint32_t
-gen6_edp_signal_levels(uint8_t train_set)
+snb_cpu_edp_signal_levels(uint8_t train_set)
 {
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
@@ -3516,9 +3516,9 @@ gen6_edp_signal_levels(uint8_t train_set)
 	}
 }
 
-/* Gen7's DP voltage swing and pre-emphasis control */
+/* IVB CPU eDP voltage swing and pre-emphasis control */
 static uint32_t
-gen7_edp_signal_levels(uint8_t train_set)
+ivb_cpu_edp_signal_levels(uint8_t train_set)
 {
 	int signal_levels = train_set & (DP_TRAIN_VOLTAGE_SWING_MASK |
 					 DP_TRAIN_PRE_EMPHASIS_MASK);
@@ -3566,10 +3566,10 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp)
 	} else if (IS_VALLEYVIEW(dev_priv)) {
 		signal_levels = vlv_signal_levels(intel_dp);
 	} else if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
-		signal_levels = gen7_edp_signal_levels(train_set);
+		signal_levels = ivb_cpu_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_IVB;
 	} else if (IS_GEN6(dev_priv) && port == PORT_A) {
-		signal_levels = gen6_edp_signal_levels(train_set);
+		signal_levels = snb_cpu_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_SNB;
 	} else {
 		signal_levels = gen4_signal_levels(train_set);
-- 
cgit v1.2.3


From 45101e939ea34c3f0794175845eb946e839e7873 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 17 May 2018 20:03:09 +0300
Subject: drm/i915: Rename the remaining gen4 references to g4x in the DP code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

i965 does not have native DP. Let's rename the remaining gen4 references
in the DP code to g4x.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517170309.28630-5-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_dp.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index cd4c60bfc4c2..102070940095 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -56,7 +56,7 @@ struct dp_link_dpll {
 	struct dpll dpll;
 };
 
-static const struct dp_link_dpll gen4_dpll[] = {
+static const struct dp_link_dpll g4x_dpll[] = {
 	{ 162000,
 		{ .p1 = 2, .p2 = 10, .n = 2, .m1 = 23, .m2 = 8 } },
 	{ 270000,
@@ -1550,8 +1550,8 @@ intel_dp_set_clock(struct intel_encoder *encoder,
 	int i, count = 0;
 
 	if (IS_G4X(dev_priv)) {
-		divisor = gen4_dpll;
-		count = ARRAY_SIZE(gen4_dpll);
+		divisor = g4x_dpll;
+		count = ARRAY_SIZE(g4x_dpll);
 	} else if (HAS_PCH_SPLIT(dev_priv)) {
 		divisor = pch_dpll;
 		count = ARRAY_SIZE(pch_dpll);
@@ -3451,7 +3451,7 @@ static uint32_t chv_signal_levels(struct intel_dp *intel_dp)
 }
 
 static uint32_t
-gen4_signal_levels(uint8_t train_set)
+g4x_signal_levels(uint8_t train_set)
 {
 	uint32_t	signal_levels = 0;
 
@@ -3572,7 +3572,7 @@ intel_dp_set_signal_levels(struct intel_dp *intel_dp)
 		signal_levels = snb_cpu_edp_signal_levels(train_set);
 		mask = EDP_LINK_TRAIN_VOL_EMP_MASK_SNB;
 	} else {
-		signal_levels = gen4_signal_levels(train_set);
+		signal_levels = g4x_signal_levels(train_set);
 		mask = DP_VOLTAGE_MASK | DP_PRE_EMPHASIS_MASK;
 	}
 
-- 
cgit v1.2.3


From c734f496770801f97ae1a59607634b972b002cdf Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 14:47:03 +0100
Subject: drm/mtk: Remove impossible internal error

We cannot create a framebuffer with no objects, so there's no point
testing for it.

v2: Remove the error entirely. (Sean, CK, Thierry)

Signed-off-by: Daniel Stone <daniels@collabora.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: CK Hu <ck.hu@mediatek.com>
Cc: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518134705.12533-1-daniels@collabora.com
---
 drivers/gpu/drm/mediatek/mtk_drm_plane.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 2f4b0ffee598..149fc4372917 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -95,11 +95,6 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 	if (!fb)
 		return 0;
 
-	if (!mtk_fb_get_gem_obj(fb)) {
-		DRM_DEBUG_KMS("buffer is null\n");
-		return -EFAULT;
-	}
-
 	if (!state->crtc)
 		return 0;
 
-- 
cgit v1.2.3


From 81a073d14c7a46f6e7282a5ffc24f112ac5429ed Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 14:47:04 +0100
Subject: drm/mtk: Move GEM BO to drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Cc: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518134705.12533-2-daniels@collabora.com
---
 drivers/gpu/drm/mediatek/mtk_drm_fb.c    | 38 +++++---------------------------
 drivers/gpu/drm/mediatek/mtk_drm_fb.h    |  1 -
 drivers/gpu/drm/mediatek/mtk_drm_plane.c |  2 +-
 3 files changed, 6 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.c b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
index 0d8d506695f9..f130e37123b5 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
@@ -15,6 +15,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <linux/dma-buf.h>
 #include <linux/reservation.h>
 
@@ -30,42 +31,13 @@
  */
 struct mtk_drm_fb {
 	struct drm_framebuffer	base;
-	/* For now we only support a single plane */
-	struct drm_gem_object	*gem_obj;
 };
 
 #define to_mtk_fb(x) container_of(x, struct mtk_drm_fb, base)
 
-struct drm_gem_object *mtk_fb_get_gem_obj(struct drm_framebuffer *fb)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	return mtk_fb->gem_obj;
-}
-
-static int mtk_drm_fb_create_handle(struct drm_framebuffer *fb,
-				    struct drm_file *file_priv,
-				    unsigned int *handle)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	return drm_gem_handle_create(file_priv, mtk_fb->gem_obj, handle);
-}
-
-static void mtk_drm_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	drm_framebuffer_cleanup(fb);
-
-	drm_gem_object_put_unlocked(mtk_fb->gem_obj);
-
-	kfree(mtk_fb);
-}
-
 static const struct drm_framebuffer_funcs mtk_drm_fb_funcs = {
-	.create_handle = mtk_drm_fb_create_handle,
-	.destroy = mtk_drm_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
 static struct mtk_drm_fb *mtk_drm_framebuffer_init(struct drm_device *dev,
@@ -84,7 +56,7 @@ static struct mtk_drm_fb *mtk_drm_framebuffer_init(struct drm_device *dev,
 
 	drm_helper_mode_fill_fb_struct(dev, &mtk_fb->base, mode);
 
-	mtk_fb->gem_obj = obj;
+	mtk_fb->base.obj[0] = obj;
 
 	ret = drm_framebuffer_init(dev, &mtk_fb->base, &mtk_drm_fb_funcs);
 	if (ret) {
@@ -110,7 +82,7 @@ int mtk_fb_wait(struct drm_framebuffer *fb)
 	if (!fb)
 		return 0;
 
-	gem = mtk_fb_get_gem_obj(fb);
+	gem = fb->obj[0];
 	if (!gem || !gem->dma_buf || !gem->dma_buf->resv)
 		return 0;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.h b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
index 9b2ae345a4e9..7f976b196a15 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
@@ -14,7 +14,6 @@
 #ifndef MTK_DRM_FB_H
 #define MTK_DRM_FB_H
 
-struct drm_gem_object *mtk_fb_get_gem_obj(struct drm_framebuffer *fb);
 int mtk_fb_wait(struct drm_framebuffer *fb);
 struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 					       struct drm_file *file,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 149fc4372917..f7e6aa1b5b7d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -122,7 +122,7 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	if (!crtc || WARN_ON(!fb))
 		return;
 
-	gem = mtk_fb_get_gem_obj(fb);
+	gem = fb->obj[0];
 	mtk_gem = to_mtk_gem_obj(gem);
 	addr = mtk_gem->dma_addr;
 	pitch = fb->pitches[0];
-- 
cgit v1.2.3


From 6a3e913cb8d5fb792782beb8766c0b81e8bfe1ac Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 14:47:05 +0100
Subject: drm/mtk: mtk_drm_fb -> drm_framebuffer

Now that mtk_drm_fb is an empty wrapper around drm_framebuffer, we can
just delete it.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Cc: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518134705.12533-3-daniels@collabora.com
---
 drivers/gpu/drm/mediatek/mtk_drm_fb.c | 40 ++++++++++++-----------------------
 1 file changed, 14 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.c b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
index f130e37123b5..be5f6f1daf55 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
@@ -23,49 +23,37 @@
 #include "mtk_drm_fb.h"
 #include "mtk_drm_gem.h"
 
-/*
- * mtk specific framebuffer structure.
- *
- * @fb: drm framebuffer object.
- * @gem_obj: array of gem objects.
- */
-struct mtk_drm_fb {
-	struct drm_framebuffer	base;
-};
-
-#define to_mtk_fb(x) container_of(x, struct mtk_drm_fb, base)
-
 static const struct drm_framebuffer_funcs mtk_drm_fb_funcs = {
 	.create_handle = drm_gem_fb_create_handle,
 	.destroy = drm_gem_fb_destroy,
 };
 
-static struct mtk_drm_fb *mtk_drm_framebuffer_init(struct drm_device *dev,
+static struct drm_framebuffer *mtk_drm_framebuffer_init(struct drm_device *dev,
 					const struct drm_mode_fb_cmd2 *mode,
 					struct drm_gem_object *obj)
 {
-	struct mtk_drm_fb *mtk_fb;
+	struct drm_framebuffer *fb;
 	int ret;
 
 	if (drm_format_num_planes(mode->pixel_format) != 1)
 		return ERR_PTR(-EINVAL);
 
-	mtk_fb = kzalloc(sizeof(*mtk_fb), GFP_KERNEL);
-	if (!mtk_fb)
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	drm_helper_mode_fill_fb_struct(dev, &mtk_fb->base, mode);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode);
 
-	mtk_fb->base.obj[0] = obj;
+	fb->obj[0] = obj;
 
-	ret = drm_framebuffer_init(dev, &mtk_fb->base, &mtk_drm_fb_funcs);
+	ret = drm_framebuffer_init(dev, fb, &mtk_drm_fb_funcs);
 	if (ret) {
 		DRM_ERROR("failed to initialize framebuffer\n");
-		kfree(mtk_fb);
+		kfree(fb);
 		return ERR_PTR(ret);
 	}
 
-	return mtk_fb;
+	return fb;
 }
 
 /*
@@ -100,7 +88,7 @@ struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 					       struct drm_file *file,
 					       const struct drm_mode_fb_cmd2 *cmd)
 {
-	struct mtk_drm_fb *mtk_fb;
+	struct drm_framebuffer *fb;
 	struct drm_gem_object *gem;
 	unsigned int width = cmd->width;
 	unsigned int height = cmd->height;
@@ -123,13 +111,13 @@ struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 		goto unreference;
 	}
 
-	mtk_fb = mtk_drm_framebuffer_init(dev, cmd, gem);
-	if (IS_ERR(mtk_fb)) {
-		ret = PTR_ERR(mtk_fb);
+	fb = mtk_drm_framebuffer_init(dev, cmd, gem);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto unreference;
 	}
 
-	return &mtk_fb->base;
+	return fb;
 
 unreference:
 	drm_gem_object_put_unlocked(gem);
-- 
cgit v1.2.3


From 4c7c9a63f215da5576460b3a526e23d564de1360 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:18 +0100
Subject: drm/rockchip: Place GEM BOs in drm_framebuffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Acked-by: Heiko Stübner <heiko@sntech.de>
Tested-by: Heiko Stübner <heiko@sntech.de>
Cc: Sandy Huang <hjc@rock-chips.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-4-daniels@collabora.com
---
 drivers/gpu/drm/rockchip/rockchip_drm_fb.c | 36 +++++-------------------------
 1 file changed, 6 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index d4f4118b482d..d1820d09075e 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -18,6 +18,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "rockchip_drm_drv.h"
 #include "rockchip_drm_fb.h"
@@ -28,40 +29,15 @@
 
 struct rockchip_drm_fb {
 	struct drm_framebuffer fb;
-	struct drm_gem_object *obj[ROCKCHIP_MAX_FB_BUFFER];
 };
 
 struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb,
 					       unsigned int plane)
 {
-	struct rockchip_drm_fb *rk_fb = to_rockchip_fb(fb);
-
 	if (plane >= ROCKCHIP_MAX_FB_BUFFER)
 		return NULL;
 
-	return rk_fb->obj[plane];
-}
-
-static void rockchip_drm_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct rockchip_drm_fb *rockchip_fb = to_rockchip_fb(fb);
-	int i;
-
-	for (i = 0; i < ROCKCHIP_MAX_FB_BUFFER; i++)
-		drm_gem_object_put_unlocked(rockchip_fb->obj[i]);
-
-	drm_framebuffer_cleanup(fb);
-	kfree(rockchip_fb);
-}
-
-static int rockchip_drm_fb_create_handle(struct drm_framebuffer *fb,
-					 struct drm_file *file_priv,
-					 unsigned int *handle)
-{
-	struct rockchip_drm_fb *rockchip_fb = to_rockchip_fb(fb);
-
-	return drm_gem_handle_create(file_priv,
-				     rockchip_fb->obj[0], handle);
+	return fb->obj[plane];
 }
 
 static int rockchip_drm_fb_dirty(struct drm_framebuffer *fb,
@@ -75,9 +51,9 @@ static int rockchip_drm_fb_dirty(struct drm_framebuffer *fb,
 }
 
 static const struct drm_framebuffer_funcs rockchip_drm_fb_funcs = {
-	.destroy	= rockchip_drm_fb_destroy,
-	.create_handle	= rockchip_drm_fb_create_handle,
-	.dirty		= rockchip_drm_fb_dirty,
+	.destroy       = drm_gem_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.dirty	       = rockchip_drm_fb_dirty,
 };
 
 static struct rockchip_drm_fb *
@@ -95,7 +71,7 @@ rockchip_fb_alloc(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cm
 	drm_helper_mode_fill_fb_struct(dev, &rockchip_fb->fb, mode_cmd);
 
 	for (i = 0; i < num_planes; i++)
-		rockchip_fb->obj[i] = obj[i];
+		rockchip_fb->fb.obj[i] = obj[i];
 
 	ret = drm_framebuffer_init(dev, &rockchip_fb->fb,
 				   &rockchip_drm_fb_funcs);
-- 
cgit v1.2.3


From 957428f9935ac6f41443431f61478023261c8d36 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:19 +0100
Subject: drm/rockchip: rockchip_drm_fb -> drm_framebuffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that rockchip_drm_fb is just a wrapper around drm_framebuffer, we
can remove it.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Acked-by: Heiko Stübner <heiko@sntech.de>
Tested-by: Heiko Stübner <heiko@sntech.de>
Cc: Sandy Huang <hjc@rock-chips.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-5-daniels@collabora.com
---
 drivers/gpu/drm/rockchip/rockchip_drm_fb.c  | 54 ++++++++++-------------------
 drivers/gpu/drm/rockchip/rockchip_drm_fb.h  |  3 --
 drivers/gpu/drm/rockchip/rockchip_drm_vop.c |  4 +--
 3 files changed, 21 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
index d1820d09075e..ea18cb2a76c0 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.c
@@ -25,21 +25,6 @@
 #include "rockchip_drm_gem.h"
 #include "rockchip_drm_psr.h"
 
-#define to_rockchip_fb(x) container_of(x, struct rockchip_drm_fb, fb)
-
-struct rockchip_drm_fb {
-	struct drm_framebuffer fb;
-};
-
-struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb,
-					       unsigned int plane)
-{
-	if (plane >= ROCKCHIP_MAX_FB_BUFFER)
-		return NULL;
-
-	return fb->obj[plane];
-}
-
 static int rockchip_drm_fb_dirty(struct drm_framebuffer *fb,
 				 struct drm_file *file,
 				 unsigned int flags, unsigned int color,
@@ -56,41 +41,40 @@ static const struct drm_framebuffer_funcs rockchip_drm_fb_funcs = {
 	.dirty	       = rockchip_drm_fb_dirty,
 };
 
-static struct rockchip_drm_fb *
+static struct drm_framebuffer *
 rockchip_fb_alloc(struct drm_device *dev, const struct drm_mode_fb_cmd2 *mode_cmd,
 		  struct drm_gem_object **obj, unsigned int num_planes)
 {
-	struct rockchip_drm_fb *rockchip_fb;
+	struct drm_framebuffer *fb;
 	int ret;
 	int i;
 
-	rockchip_fb = kzalloc(sizeof(*rockchip_fb), GFP_KERNEL);
-	if (!rockchip_fb)
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	drm_helper_mode_fill_fb_struct(dev, &rockchip_fb->fb, mode_cmd);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode_cmd);
 
 	for (i = 0; i < num_planes; i++)
-		rockchip_fb->fb.obj[i] = obj[i];
+		fb->obj[i] = obj[i];
 
-	ret = drm_framebuffer_init(dev, &rockchip_fb->fb,
-				   &rockchip_drm_fb_funcs);
+	ret = drm_framebuffer_init(dev, fb, &rockchip_drm_fb_funcs);
 	if (ret) {
 		DRM_DEV_ERROR(dev->dev,
 			      "Failed to initialize framebuffer: %d\n",
 			      ret);
-		kfree(rockchip_fb);
+		kfree(fb);
 		return ERR_PTR(ret);
 	}
 
-	return rockchip_fb;
+	return fb;
 }
 
 static struct drm_framebuffer *
 rockchip_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 			const struct drm_mode_fb_cmd2 *mode_cmd)
 {
-	struct rockchip_drm_fb *rockchip_fb;
+	struct drm_framebuffer *fb;
 	struct drm_gem_object *objs[ROCKCHIP_MAX_FB_BUFFER];
 	struct drm_gem_object *obj;
 	unsigned int hsub;
@@ -129,13 +113,13 @@ rockchip_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		objs[i] = obj;
 	}
 
-	rockchip_fb = rockchip_fb_alloc(dev, mode_cmd, objs, i);
-	if (IS_ERR(rockchip_fb)) {
-		ret = PTR_ERR(rockchip_fb);
+	fb = rockchip_fb_alloc(dev, mode_cmd, objs, i);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto err_gem_object_unreference;
 	}
 
-	return &rockchip_fb->fb;
+	return fb;
 
 err_gem_object_unreference:
 	for (i--; i >= 0; i--)
@@ -218,13 +202,13 @@ rockchip_drm_framebuffer_init(struct drm_device *dev,
 			      const struct drm_mode_fb_cmd2 *mode_cmd,
 			      struct drm_gem_object *obj)
 {
-	struct rockchip_drm_fb *rockchip_fb;
+	struct drm_framebuffer *fb;
 
-	rockchip_fb = rockchip_fb_alloc(dev, mode_cmd, &obj, 1);
-	if (IS_ERR(rockchip_fb))
-		return ERR_CAST(rockchip_fb);
+	fb = rockchip_fb_alloc(dev, mode_cmd, &obj, 1);
+	if (IS_ERR(fb))
+		return ERR_CAST(fb);
 
-	return &rockchip_fb->fb;
+	return fb;
 }
 
 void rockchip_drm_mode_config_init(struct drm_device *dev)
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_fb.h b/drivers/gpu/drm/rockchip/rockchip_drm_fb.h
index 2fe47f1ee98f..f1265cb1aee8 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_fb.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_fb.h
@@ -22,7 +22,4 @@ rockchip_drm_framebuffer_init(struct drm_device *dev,
 void rockchip_drm_framebuffer_fini(struct drm_framebuffer *fb);
 
 void rockchip_drm_mode_config_init(struct drm_device *dev);
-
-struct drm_gem_object *rockchip_fb_get_gem_obj(struct drm_framebuffer *fb,
-					       unsigned int plane);
 #endif /* _ROCKCHIP_DRM_FB_H */
diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 2121345a61af..45847d4a2e14 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -728,7 +728,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 		return;
 	}
 
-	obj = rockchip_fb_get_gem_obj(fb, 0);
+	obj = fb->obj[0];
 	rk_obj = to_rockchip_obj(obj);
 
 	actual_w = drm_rect_width(src) >> 16;
@@ -758,7 +758,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 		int vsub = drm_format_vert_chroma_subsampling(fb->format->format);
 		int bpp = fb->format->cpp[1];
 
-		uv_obj = rockchip_fb_get_gem_obj(fb, 1);
+		uv_obj = fb->obj[1];
 		rk_uv_obj = to_rockchip_obj(uv_obj);
 
 		offset = (src->x1 >> 16) * bpp / hsub;
-- 
cgit v1.2.3


From e578a570dc7c20475774d1ff993825e3bd7a7011 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 May 2018 08:48:40 +0100
Subject: drm/i915/lvds: Move acpi lid notification registration to
 registration phase
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Delay registering ourselves with the acpi lid notification mechanism
until we are registering the connectors after initialisation is
complete. This prevents a possibility of trying to handle the lid
notification before we are ready with the danger of chasing
uninitialised function pointers.

 BUG: unable to handle kernel NULL pointer dereference at 0000000000000000
 IP:           (null)
 PGD 0 P4D 0
 Oops: 0010 [#1] PREEMPT SMP PTI
 Modules linked in: arc4(+) iwldvm(+) i915(+) mac80211 i2c_algo_bit coretemp mei_wdt iwlwifi drm_kms_helper kvm_intel wmi_bmof iTCO_wdt iTCO_vendor_support kvm snd_hda_codec_conexant snd_hda_codec_generic drm psmouse cfg80211 irqbypass input_leds pcspkr i2c_i801 snd_hda_intel snd_hda_codec thinkpad_acpi snd_hda_core mei_me lpc_ich snd_hwdep e1000e wmi nvram snd_pcm mei snd_timer shpchp ptp pps_core rfkill syscopyarea snd intel_agp sysfillrect intel_gtt soundcore sysimgblt battery led_class fb_sys_fops ac rtc_cmos agpgart evdev mac_hid acpi_cpufreq ip_tables x_tables ext4 crc32c_generic crc16 mbcache jbd2 fscrypto crypto_simd glue_helper cryptd aes_x86_64 xts algif_skcipher af_alg dm_crypt dm_mod sd_mod uas usb_storage serio_raw atkbd libps2 ahci libahci uhci_hcd libata scsi_mod ehci_pci
  ehci_hcd usbcore usb_common i8042 serio
 CPU: 1 PID: 378 Comm: systemd-logind Not tainted 4.16.8-1-ARCH #1
 Hardware name: LENOVO 7454CTO/7454CTO, BIOS 6DET72WW (3.22 ) 10/25/2012
 RIP: 0010:          (null)
 RSP: 0018:ffffaf4580c33a18 EFLAGS: 00010287
 RAX: 0000000000000000 RBX: ffff947533558000 RCX: 000000000000003e
 RDX: ffffffffc0aa80c0 RSI: ffffaf4580c33a3c RDI: ffff947534e4c000
 RBP: ffff947533558338 R08: ffff947534598930 R09: ffffffffc0a928b1
 R10: ffffd8f181d5fd40 R11: 0000000000000000 R12: ffffffffc0a928b1
 R13: ffff947533558368 R14: ffffffffc0a928a9 R15: ffff947534e4c000
 FS:  00007f3dc4ddb940(0000) GS:ffff947539280000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 000000006e214000 CR4: 00000000000406e0
 Call Trace:
  ?  intel_modeset_setup_hw_state+0x385/0xf60 [i915]
  ? __intel_display_resume+0x1e/0xc0 [i915]
  ? intel_display_resume+0xcc/0x120 [i915]
  ? intel_lid_notify+0xbc/0xc0 [i915]
  ? notifier_call_chain+0x47/0x70
  ? blocking_notifier_call_chain+0x3e/0x60
  ? acpi_lid_notify_state+0x8f/0x1d0
  ? acpi_lid_update_state+0x49/0x70
  ? acpi_lid_input_open+0x60/0x90
  ? input_open_device+0x5d/0xa0
  ? evdev_open+0x1ba/0x1e0 [evdev]
  ? chrdev_open+0xa3/0x1b0
  ? cdev_put.part.0+0x20/0x20
  ? do_dentry_open+0x14c/0x300
  ? path_openat+0x30c/0x1240
  ? current_time+0x16/0x60
  ? do_filp_open+0x93/0x100
  ? __check_object_size+0xfb/0x180
  ? do_sys_open+0x186/0x210
  ? do_syscall_64+0x74/0x190
  ?  entry_SYSCALL_64_after_hwframe+0x3d/0xa2
 Code:  Bad RIP value.
 RIP:           (null) RSP: ffffaf4580c33a18
 CR2: 0000000000000000

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106559
Fixes: c1c7af608920 ("drm/i915: force mode set at lid open time")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518074840.16194-1-chris@chris-wilson.co.uk
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/i915/intel_lvds.c | 43 +++++++++++++++++++++++++++++----------
 1 file changed, 32 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 907d0bf853ef..a92bb63b2f2d 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -572,6 +572,36 @@ exit:
 	return NOTIFY_OK;
 }
 
+static int
+intel_lvds_connector_register(struct drm_connector *connector)
+{
+	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
+	int ret;
+
+	ret = intel_connector_register(connector);
+	if (ret)
+		return ret;
+
+	lvds->lid_notifier.notifier_call = intel_lid_notify;
+	if (acpi_lid_notifier_register(&lvds->lid_notifier)) {
+		DRM_DEBUG_KMS("lid notifier registration failed\n");
+		lvds->lid_notifier.notifier_call = NULL;
+	}
+
+	return 0;
+}
+
+static void
+intel_lvds_connector_unregister(struct drm_connector *connector)
+{
+	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
+
+	if (lvds->lid_notifier.notifier_call)
+		acpi_lid_notifier_unregister(&lvds->lid_notifier);
+
+	intel_connector_unregister(connector);
+}
+
 /**
  * intel_lvds_destroy - unregister and free LVDS structures
  * @connector: connector to free
@@ -584,9 +614,6 @@ static void intel_lvds_destroy(struct drm_connector *connector)
 	struct intel_lvds_connector *lvds_connector =
 		to_lvds_connector(connector);
 
-	if (lvds_connector->lid_notifier.notifier_call)
-		acpi_lid_notifier_unregister(&lvds_connector->lid_notifier);
-
 	if (!IS_ERR_OR_NULL(lvds_connector->base.edid))
 		kfree(lvds_connector->base.edid);
 
@@ -607,8 +634,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_digital_connector_atomic_get_property,
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
-	.late_register = intel_connector_register,
-	.early_unregister = intel_connector_unregister,
+	.late_register = intel_lvds_connector_register,
+	.early_unregister = intel_lvds_connector_unregister,
 	.destroy = intel_lvds_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
@@ -1160,12 +1187,6 @@ out:
 
 	lvds_encoder->a3_power = lvds & LVDS_A3_POWER_MASK;
 
-	lvds_connector->lid_notifier.notifier_call = intel_lid_notify;
-	if (acpi_lid_notifier_register(&lvds_connector->lid_notifier)) {
-		DRM_DEBUG_KMS("lid notifier registration failed\n");
-		lvds_connector->lid_notifier.notifier_call = NULL;
-	}
-
 	return;
 
 failed:
-- 
cgit v1.2.3


From dd0cf235d81f24c1ba80c4a000bafc9f2dce3840 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 6 May 2018 18:13:28 +0100
Subject: drm/i915: Speed up idle detection by kicking the tasklets

We rely on ksoftirqd to run in a timely fashion in order to drain the
execlists queue. Quite frequently, it does not. In some cases we may see
latencies of over 200ms triggering our idle timeouts and forcing us to
declare the driver wedged!

Thus we can speed up idle detection by bypassing ksoftirqd in these
cases and flush our tasklet to confirm if we are indeed still waiting
for the ELSP to drain.

v2: Put the execlists.first check back; it is required for handling
reset!

References: https://bugs.freedesktop.org/show_bug.cgi?id=106373
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180506171328.30034-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 26f9f8aab949..a2173e66a63b 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -973,10 +973,19 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 		return true;
 
 	/* Waiting to drain ELSP? */
-	if (READ_ONCE(engine->execlists.active))
-		return false;
+	if (READ_ONCE(engine->execlists.active)) {
+		struct intel_engine_execlists *execlists = &engine->execlists;
+
+		if (tasklet_trylock(&execlists->tasklet)) {
+			execlists->tasklet.func(execlists->tasklet.data);
+			tasklet_unlock(&execlists->tasklet);
+		}
+
+		if (READ_ONCE(execlists->active))
+			return false;
+	}
 
-	/* ELSP is empty, but there are ready requests? */
+	/* ELSP is empty, but there are ready requests? E.g. after reset */
 	if (READ_ONCE(engine->execlists.first))
 		return false;
 
-- 
cgit v1.2.3


From d6d12ec081776bdea7e0ad58f2a7e7f92e414e7f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 May 2018 10:02:10 +0100
Subject: drm/i915: Make intel_engine_dump irqsafe

To be useful later, enable intel_engine_dump() to be called from irq
context (i.e. using saving and restoring irq start rather than assuming
we enter with irqs enabled).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518090212.5349-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index a2173e66a63b..847797215a73 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1367,6 +1367,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	const struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_gpu_error * const error = &engine->i915->gpu_error;
 	struct i915_request *rq, *last;
+	unsigned long flags;
 	struct rb_node *rb;
 	int count;
 
@@ -1433,7 +1434,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		drm_printf(m, "\tDevice is asleep; skipping register dump\n");
 	}
 
-	spin_lock_irq(&engine->timeline.lock);
+	local_irq_save(flags);
+	spin_lock(&engine->timeline.lock);
 
 	last = NULL;
 	count = 0;
@@ -1475,16 +1477,17 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		print_request(m, last, "\t\tQ ");
 	}
 
-	spin_unlock_irq(&engine->timeline.lock);
+	spin_unlock(&engine->timeline.lock);
 
-	spin_lock_irq(&b->rb_lock);
+	spin_lock(&b->rb_lock);
 	for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
 		struct intel_wait *w = rb_entry(rb, typeof(*w), node);
 
 		drm_printf(m, "\t%s [%d] waiting for %x\n",
 			   w->tsk->comm, w->tsk->pid, w->seqno);
 	}
-	spin_unlock_irq(&b->rb_lock);
+	spin_unlock(&b->rb_lock);
+	local_irq_restore(flags);
 
 	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n",
 		   engine->irq_posted,
-- 
cgit v1.2.3


From fe0c493538f42ee1cbc4701dc6f9eb2b82d856cf Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 May 2018 10:02:11 +0100
Subject: drm/i915/execlists: Handle copying default context state for atomic
 reset

We want to be able to reset the GPU from inside a timer callback
(hardirq context). One step requires us to copy the default context
state over to the guilty context, which means we need to plan in advance
to have that object accessible from within an atomic context. The atomic
context prevents us from pinning the object or from peeking into the
shmemfs backing store (all may sleep), so we choose to pin the
default_state into memory when the engine becomes active. This
compromise allows us to swap out the default state when idle, when
required.

References: 5692251c254a ("drm/i915/lrc: Scrub the GPU state of the guilty hanging request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518090212.5349-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c  | 15 +++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c        | 15 ++++-----------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 +
 3 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 847797215a73..0c1f084ee593 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1091,6 +1091,11 @@ void intel_engines_park(struct drm_i915_private *i915)
 		if (engine->park)
 			engine->park(engine);
 
+		if (engine->pinned_default_state) {
+			i915_gem_object_unpin_map(engine->default_state);
+			engine->pinned_default_state = NULL;
+		}
+
 		i915_gem_batch_pool_fini(&engine->batch_pool);
 		engine->execlists.no_priolist = false;
 	}
@@ -1108,6 +1113,16 @@ void intel_engines_unpark(struct drm_i915_private *i915)
 	enum intel_engine_id id;
 
 	for_each_engine(engine, i915, id) {
+		void *map;
+
+		/* Pin the default state for fast resets from atomic context. */
+		map = NULL;
+		if (engine->default_state)
+			map = i915_gem_object_pin_map(engine->default_state,
+						      I915_MAP_WB);
+		if (!IS_ERR_OR_NULL(map))
+			engine->pinned_default_state = map;
+
 		if (engine->unpark)
 			engine->unpark(engine);
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 9abd26f22b47..46e7bf4a30a9 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1965,17 +1965,10 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	 * to recreate its own state.
 	 */
 	regs = request->hw_context->lrc_reg_state;
-	if (engine->default_state) {
-		void *defaults;
-
-		defaults = i915_gem_object_pin_map(engine->default_state,
-						   I915_MAP_WB);
-		if (!IS_ERR(defaults)) {
-			memcpy(regs, /* skip restoring the vanilla PPHWSP */
-			       defaults + LRC_STATE_PN * PAGE_SIZE,
-			       engine->context_size - PAGE_SIZE);
-			i915_gem_object_unpin_map(engine->default_state);
-		}
+	if (engine->pinned_default_state) {
+		memcpy(regs, /* skip restoring the vanilla PPHWSP */
+		       engine->pinned_default_state + LRC_STATE_PN * PAGE_SIZE,
+		       engine->context_size - PAGE_SIZE);
 	}
 	execlists_init_reg_state(regs,
 				 request->gem_context, engine, request->ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 20c4e13efc0d..acef385c4c80 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -342,6 +342,7 @@ struct intel_engine_cs {
 	struct i915_timeline timeline;
 
 	struct drm_i915_gem_object *default_state;
+	void *pinned_default_state;
 
 	atomic_t irq_count;
 	unsigned long irq_posted;
-- 
cgit v1.2.3


From 2399a4a6f5dff645d7890135db1c965592e1b8f3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 May 2018 10:02:12 +0100
Subject: drm/i915: Allow init_breadcrumbs to be used from irq context

In order to support engine reset from irq (timer) context, we need to be
able to re-initialise the breadcrumbs. So we need to promote the plain
spin_lock_irq to a safe spin_lock_irqsave.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518090212.5349-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_breadcrumbs.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 18e643df523e..86a987b8ac66 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -846,8 +846,9 @@ static void cancel_fake_irq(struct intel_engine_cs *engine)
 void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 {
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	unsigned long flags;
 
-	spin_lock_irq(&b->irq_lock);
+	spin_lock_irqsave(&b->irq_lock, flags);
 
 	/*
 	 * Leave the fake_irq timer enabled (if it is running), but clear the
@@ -871,7 +872,7 @@ void intel_engine_reset_breadcrumbs(struct intel_engine_cs *engine)
 	 */
 	clear_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
 
-	spin_unlock_irq(&b->irq_lock);
+	spin_unlock_irqrestore(&b->irq_lock, flags);
 }
 
 void intel_engine_fini_breadcrumbs(struct intel_engine_cs *engine)
-- 
cgit v1.2.3


From 39d3cc03e9ddd3c7b564acd07ba1691ba817837d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 17 May 2018 15:24:41 +0100
Subject: drm/i915/selftests: Wait longer for the old active request

When testing reset, we wait for 1s on the main thread for the hang to
start. Meanwhile, we continue submitting requests on all the background
threads, and we may have more threads than cores and so potentially
starve the waiter from being woken within the timeout. As the hang
timeout and the active timeouts are the same, it is hard to distinguish
which caused the timeout. Bump the active thread timeouts to 5s,
compared to the 1s timeout for the hang, so that we preferentially
report the hang timing out, while hopefully ensuring that we do at least
wake up the hang thread first before declaring the background active
timeout.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517142442.16979-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 48 +++++++++++++++++-------
 1 file changed, 34 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 2c4e77c050dc..2091e3a6a5be 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -563,6 +563,30 @@ struct active_engine {
 #define TEST_SELF	BIT(2)
 #define TEST_PRIORITY	BIT(3)
 
+static int active_request_put(struct i915_request *rq)
+{
+	int err = 0;
+
+	if (!rq)
+		return 0;
+
+	if (i915_request_wait(rq, 0, 5 * HZ) < 0) {
+		GEM_TRACE("%s timed out waiting for completion of fence %llx:%d, seqno %d.\n",
+			  rq->engine->name,
+			  rq->fence.context,
+			  rq->fence.seqno,
+			  i915_request_global_seqno(rq));
+		GEM_TRACE_DUMP();
+
+		i915_gem_set_wedged(rq->i915);
+		err = -EIO;
+	}
+
+	i915_request_put(rq);
+
+	return err;
+}
+
 static int active_engine(void *data)
 {
 	I915_RND_STATE(prng);
@@ -611,24 +635,20 @@ static int active_engine(void *data)
 		i915_request_add(new);
 		mutex_unlock(&engine->i915->drm.struct_mutex);
 
-		if (old) {
-			if (i915_request_wait(old, 0, HZ) < 0) {
-				GEM_TRACE("%s timed out.\n", engine->name);
-				GEM_TRACE_DUMP();
-
-				i915_gem_set_wedged(engine->i915);
-				i915_request_put(old);
-				err = -EIO;
-				break;
-			}
-			i915_request_put(old);
-		}
+		err = active_request_put(old);
+		if (err)
+			break;
 
 		cond_resched();
 	}
 
-	for (count = 0; count < ARRAY_SIZE(rq); count++)
-		i915_request_put(rq[count]);
+	for (count = 0; count < ARRAY_SIZE(rq); count++) {
+		int err__ = active_request_put(rq[count]);
+
+		/* Keep the first error */
+		if (!err)
+			err = err__;
+	}
 
 err_file:
 	mock_file_free(engine->i915, file);
-- 
cgit v1.2.3


From 2773397171ac4b6e794ba0b3e34c06cbaf29897a Mon Sep 17 00:00:00 2001
From: Dou Liyang <douly.fnst@cn.fujitsu.com>
Date: Fri, 11 May 2018 16:09:56 +0800
Subject: x86/vector: Merge allocate_vector() into assign_vector_locked()

assign_vector_locked() calls allocate_vector() to get a real vector for an
IRQ. If the current target CPU is online and in the new requested affinity
mask, allocate_vector() will return 0 and nothing should be done. But,
assign_vector_locked() calls apic_update_irq_cfg() even in that case which
is pointless.

allocate_vector() is not called from anything else, so the functions can be
merged and in case of no change the apic_update_irq_cfg() can be avoided.

[ tglx: Massaged changelog ]

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/20180511080956.6316-1-douly.fnst@cn.fujitsu.com
---
 arch/x86/kernel/apic/vector.c | 17 ++++-------------
 1 file changed, 4 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index bb6f7a2148d7..a75de0792942 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -218,7 +218,8 @@ static int reserve_irq_vector(struct irq_data *irqd)
 	return 0;
 }
 
-static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest)
+static int
+assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest)
 {
 	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	bool resvd = apicd->has_reserved;
@@ -236,22 +237,12 @@ static int allocate_vector(struct irq_data *irqd, const struct cpumask *dest)
 		return 0;
 
 	vector = irq_matrix_alloc(vector_matrix, dest, resvd, &cpu);
-	if (vector > 0)
-		apic_update_vector(irqd, vector, cpu);
 	trace_vector_alloc(irqd->irq, vector, resvd, vector);
-	return vector;
-}
-
-static int assign_vector_locked(struct irq_data *irqd,
-				const struct cpumask *dest)
-{
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
-	int vector = allocate_vector(irqd, dest);
-
 	if (vector < 0)
 		return vector;
+	apic_update_vector(irqd, vector, cpu);
+	apic_update_irq_cfg(irqd, vector, cpu);
 
-	apic_update_irq_cfg(irqd, apicd->vector, apicd->cpu);
 	return 0;
 }
 
-- 
cgit v1.2.3


From e8b58d6de1fe9119018ed9bbeecf373dcc397b8d Mon Sep 17 00:00:00 2001
From: Peter Rosin <peda@axentia.se>
Date: Wed, 2 May 2018 09:40:24 +0200
Subject: drm/rockchip: lvds: avoid duplicating drm_bridge_attach

drm_bridge_attach takes care of these assignments, so there is no need
to open-code them a second time.

Signed-off-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20180502074025.12421-3-peda@axentia.se
---
 drivers/gpu/drm/rockchip/rockchip_lvds.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index e67f4ea28c0e..4bd94b167d2c 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -446,14 +446,12 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 			goto err_free_connector;
 		}
 	} else {
-		lvds->bridge->encoder = encoder;
 		ret = drm_bridge_attach(encoder, lvds->bridge, NULL);
 		if (ret) {
 			DRM_DEV_ERROR(drm_dev->dev,
 				      "failed to attach bridge: %d\n", ret);
 			goto err_free_encoder;
 		}
-		encoder->bridge = lvds->bridge;
 	}
 
 	pm_runtime_enable(dev);
-- 
cgit v1.2.3


From 6bb2a2af8b1b38a5e33984f5fdda2638317ed8fd Mon Sep 17 00:00:00 2001
From: Zhenyu Wang <zhenyuw@linux.intel.com>
Date: Mon, 21 May 2018 16:17:52 +0800
Subject: drm/i915/gvt: Fix crash after request->hw_context change

When we do shadowing, workload's request might not be allocated yet,
so we still require shadow context's object. And when complete workload,
delay to zero workload's request pointer after used for update guest context.

v2: Move request alloc earlier as already try to track shadow status
depending on request state, which also facilitate to use request->hw_context
for target engine context reference.

Fixes: 1fc44d9b1afb ("drm/i915: Store a pointer to intel_context in i915_request")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Zhi Wang <zhi.a.wang@intel.com>
Cc: Weinan Li <weinan.z.li@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521081752.31056-1-zhenyuw@linux.intel.com
---
 drivers/gpu/drm/i915/gvt/scheduler.c | 52 +++++++++++-------------------------
 1 file changed, 16 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index e1760030dda1..7f5e01df95ee 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -348,6 +348,7 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	struct intel_engine_cs *engine = dev_priv->engine[workload->ring_id];
 	struct intel_context *ce;
+	struct i915_request *rq;
 	int ret;
 
 	lockdep_assert_held(&dev_priv->drm.struct_mutex);
@@ -386,46 +387,26 @@ int intel_gvt_scan_and_shadow_workload(struct intel_vgpu_workload *workload)
 			goto err_shadow;
 	}
 
-	ret = populate_shadow_context(workload);
-	if (ret)
-		goto err_shadow;
-
-	return 0;
-
-err_shadow:
-	release_shadow_wa_ctx(&workload->wa_ctx);
-err_unpin:
-	intel_context_unpin(ce);
-	return ret;
-}
-
-static int intel_gvt_generate_request(struct intel_vgpu_workload *workload)
-{
-	int ring_id = workload->ring_id;
-	struct drm_i915_private *dev_priv = workload->vgpu->gvt->dev_priv;
-	struct i915_request *rq;
-	struct intel_vgpu *vgpu = workload->vgpu;
-	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_gem_context *shadow_ctx = s->shadow_ctx;
-	int ret;
-
-	rq = i915_request_alloc(dev_priv->engine[ring_id], shadow_ctx);
+	rq = i915_request_alloc(engine, shadow_ctx);
 	if (IS_ERR(rq)) {
 		gvt_vgpu_err("fail to allocate gem request\n");
 		ret = PTR_ERR(rq);
-		goto err_unpin;
+		goto err_shadow;
 	}
-
-	gvt_dbg_sched("ring id %d get i915 gem request %p\n", ring_id, rq);
-
 	workload->req = i915_request_get(rq);
-	ret = copy_workload_to_ring_buffer(workload);
+
+	ret = populate_shadow_context(workload);
 	if (ret)
-		goto err_unpin;
-	return 0;
+		goto err_req;
 
-err_unpin:
+	return 0;
+err_req:
+	rq = fetch_and_zero(&workload->req);
+	i915_request_put(rq);
+err_shadow:
 	release_shadow_wa_ctx(&workload->wa_ctx);
+err_unpin:
+	intel_context_unpin(ce);
 	return ret;
 }
 
@@ -609,7 +590,7 @@ static int prepare_workload(struct intel_vgpu_workload *workload)
 		goto err_unpin_mm;
 	}
 
-	ret = intel_gvt_generate_request(workload);
+	ret = copy_workload_to_ring_buffer(workload);
 	if (ret) {
 		gvt_vgpu_err("fail to generate request\n");
 		goto err_unpin_mm;
@@ -823,7 +804,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 		scheduler->current_workload[ring_id];
 	struct intel_vgpu *vgpu = workload->vgpu;
 	struct intel_vgpu_submission *s = &vgpu->submission;
-	struct i915_request *rq;
+	struct i915_request *rq = workload->req;
 	int event;
 
 	mutex_lock(&gvt->lock);
@@ -832,7 +813,6 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 	 * switch to make sure request is completed.
 	 * For the workload w/o request, directly complete the workload.
 	 */
-	rq = fetch_and_zero(&workload->req);
 	if (rq) {
 		wait_event(workload->shadow_ctx_status_wq,
 			   !atomic_read(&workload->shadow_ctx_active));
@@ -863,7 +843,7 @@ static void complete_current_workload(struct intel_gvt *gvt, int ring_id)
 		intel_context_unpin(rq->hw_context);
 		mutex_unlock(&rq->i915->drm.struct_mutex);
 
-		i915_request_put(rq);
+		i915_request_put(fetch_and_zero(&workload->req));
 	}
 
 	gvt_dbg_sched("ring id %d complete workload %p status %d\n",
-- 
cgit v1.2.3


From 17e23993f297467bae946a46e44f945d8dae93f8 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 18 May 2018 11:10:41 +0300
Subject: drm/v3d: Checking for NULL vs IS_ERR()

The v3d_fence_create() only returns error pointers on error.  It never
returns NULL.

Fixes: 57692c94dcbe ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518081041.GC28335@mwanda
---
 drivers/gpu/drm/v3d/v3d_sched.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index b07bece9417d..808bc901f567 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -114,8 +114,8 @@ static struct dma_fence *v3d_job_run(struct drm_sched_job *sched_job)
 	v3d_invalidate_caches(v3d);
 
 	fence = v3d_fence_create(v3d, q);
-	if (!fence)
-		return fence;
+	if (IS_ERR(fence))
+		return NULL;
 
 	if (job->done_fence)
 		dma_fence_put(job->done_fence);
-- 
cgit v1.2.3


From a5ff7a45c9c8fc4d2d9484c028a9d882da6d5f48 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 15:30:07 +0100
Subject: drm/i915: Use intel_fb_obj() everywhere
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We already have a macro to pull the GEM object from a FB, so use it
everywhere. We'll make use of this later to move the object storage.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180518143008.4120-1-daniels@collabora.com
---
 drivers/gpu/drm/i915/i915_debugfs.c  |  4 ++--
 drivers/gpu/drm/i915/intel_display.c | 19 ++++++++++---------
 drivers/gpu/drm/i915/intel_fbdev.c   |  9 +++++----
 3 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 52515445ac40..e9b1b8df6ef5 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1908,7 +1908,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 			   fbdev_fb->base.format->cpp[0] * 8,
 			   fbdev_fb->base.modifier,
 			   drm_framebuffer_read_refcount(&fbdev_fb->base));
-		describe_obj(m, fbdev_fb->obj);
+		describe_obj(m, intel_fb_obj(&fbdev_fb->base));
 		seq_putc(m, '\n');
 	}
 #endif
@@ -1926,7 +1926,7 @@ static int i915_gem_framebuffer_info(struct seq_file *m, void *data)
 			   fb->base.format->cpp[0] * 8,
 			   fb->base.modifier,
 			   drm_framebuffer_read_refcount(&fb->base));
-		describe_obj(m, fb->obj);
+		describe_obj(m, intel_fb_obj(&fb->base));
 		seq_putc(m, '\n');
 	}
 	mutex_unlock(&dev->mode_config.fb_lock);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index c9ec88acad9c..1b2cf631305e 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2474,6 +2474,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
 	struct intel_rotation_info *rot_info = &intel_fb->rot_info;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 	u32 gtt_offset_rotated = 0;
 	unsigned int max_size = 0;
 	int i, num_planes = fb->format->num_planes;
@@ -2538,7 +2539,7 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		 * fb layout agrees with the fence layout. We already check that the
 		 * fb stride matches the fence stride elsewhere.
 		 */
-		if (i == 0 && i915_gem_object_is_tiled(intel_fb->obj) &&
+		if (i == 0 && i915_gem_object_is_tiled(obj) &&
 		    (x + width) * cpp > fb->pitches[i]) {
 			DRM_DEBUG_KMS("bad fb plane %d offset: 0x%x\n",
 				      i, fb->offsets[i]);
@@ -2623,9 +2624,9 @@ intel_fill_fb_info(struct drm_i915_private *dev_priv,
 		max_size = max(max_size, offset + size);
 	}
 
-	if (max_size * tile_size > intel_fb->obj->base.size) {
+	if (max_size * tile_size > obj->base.size) {
 		DRM_DEBUG_KMS("fb too big for bo (need %u bytes, have %zu bytes)\n",
-			      max_size * tile_size, intel_fb->obj->base.size);
+			      max_size * tile_size, obj->base.size);
 		return -EINVAL;
 	}
 
@@ -14082,14 +14083,15 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 static void intel_user_framebuffer_destroy(struct drm_framebuffer *fb)
 {
 	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 
 	drm_framebuffer_cleanup(fb);
 
-	i915_gem_object_lock(intel_fb->obj);
-	WARN_ON(!intel_fb->obj->framebuffer_references--);
-	i915_gem_object_unlock(intel_fb->obj);
+	i915_gem_object_lock(obj);
+	WARN_ON(!obj->framebuffer_references--);
+	i915_gem_object_unlock(obj);
 
-	i915_gem_object_put(intel_fb->obj);
+	i915_gem_object_put(obj);
 
 	kfree(intel_fb);
 }
@@ -14098,8 +14100,7 @@ static int intel_user_framebuffer_create_handle(struct drm_framebuffer *fb,
 						struct drm_file *file,
 						unsigned int *handle)
 {
-	struct intel_framebuffer *intel_fb = to_intel_framebuffer(fb);
-	struct drm_i915_gem_object *obj = intel_fb->obj;
+	struct drm_i915_gem_object *obj = intel_fb_obj(fb);
 
 	if (obj->userptr.mm) {
 		DRM_DEBUG("attempting to use a userptr for a framebuffer, denied\n");
diff --git a/drivers/gpu/drm/i915/intel_fbdev.c b/drivers/gpu/drm/i915/intel_fbdev.c
index e9e02b58b7be..fb2f9fce34cd 100644
--- a/drivers/gpu/drm/i915/intel_fbdev.c
+++ b/drivers/gpu/drm/i915/intel_fbdev.c
@@ -47,7 +47,7 @@
 
 static void intel_fbdev_invalidate(struct intel_fbdev *ifbdev)
 {
-	struct drm_i915_gem_object *obj = ifbdev->fb->obj;
+	struct drm_i915_gem_object *obj = intel_fb_obj(&ifbdev->fb->base);
 	unsigned int origin =
 		ifbdev->vma_flags & PLANE_HAS_FENCE ? ORIGIN_GTT : ORIGIN_CPU;
 
@@ -193,7 +193,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 		drm_framebuffer_put(&intel_fb->base);
 		intel_fb = ifbdev->fb = NULL;
 	}
-	if (!intel_fb || WARN_ON(!intel_fb->obj)) {
+	if (!intel_fb || WARN_ON(!intel_fb_obj(&intel_fb->base))) {
 		DRM_DEBUG_KMS("no BIOS fb, allocating a new one\n");
 		ret = intelfb_alloc(helper, sizes);
 		if (ret)
@@ -265,7 +265,7 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	 * If the object is stolen however, it will be full of whatever
 	 * garbage was left in there.
 	 */
-	if (intel_fb->obj->stolen && !prealloc)
+	if (intel_fb_obj(fb)->stolen && !prealloc)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
@@ -792,7 +792,8 @@ void intel_fbdev_set_suspend(struct drm_device *dev, int state, bool synchronous
 	 * been restored from swap. If the object is stolen however, it will be
 	 * full of whatever garbage was left in there.
 	 */
-	if (state == FBINFO_STATE_RUNNING && ifbdev->fb->obj->stolen)
+	if (state == FBINFO_STATE_RUNNING &&
+	    intel_fb_obj(&ifbdev->fb->base)->stolen)
 		memset_io(info->screen_base, 0, info->screen_size);
 
 	drm_fb_helper_set_suspend(&ifbdev->helper, state);
-- 
cgit v1.2.3


From a268bcd7647d2c22bffdfbb111e5f7291b8494a6 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 15:30:08 +0100
Subject: drm/i915: Move GEM BO inside drm_framebuffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass.

v2: Only hold a single reference per framebuffer, not per plane. (Ville)
v3: Drop NULL check in intel_fb_obj. (Ville)

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180518143008.4120-2-daniels@collabora.com
---
 drivers/gpu/drm/i915/intel_display.c | 4 ++--
 drivers/gpu/drm/i915/intel_drv.h     | 3 +--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 1b2cf631305e..12226a2c8d39 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -14370,9 +14370,9 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 				      i, fb->pitches[i], stride_alignment);
 			goto err;
 		}
-	}
 
-	intel_fb->obj = obj;
+		fb->obj[i] = &obj->base;
+	}
 
 	ret = intel_fill_fb_info(dev_priv, fb);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 22af249393a4..ac19da7f8790 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -194,7 +194,6 @@ enum intel_output_type {
 
 struct intel_framebuffer {
 	struct drm_framebuffer base;
-	struct drm_i915_gem_object *obj;
 	struct intel_rotation_info rot_info;
 
 	/* for each plane in the normal GTT view */
@@ -1005,7 +1004,7 @@ struct cxsr_latency {
 #define to_intel_framebuffer(x) container_of(x, struct intel_framebuffer, base)
 #define to_intel_plane(x) container_of(x, struct intel_plane, base)
 #define to_intel_plane_state(x) container_of(x, struct intel_plane_state, base)
-#define intel_fb_obj(x) (x ? to_intel_framebuffer(x)->obj : NULL)
+#define intel_fb_obj(x) ((x) ? to_intel_bo((x)->obj[0]) : NULL)
 
 struct intel_hdmi {
 	i915_reg_t hdmi_reg;
-- 
cgit v1.2.3


From 3e44255260dc3c329a92cf0aa64495951ccc4fb7 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:20 +0100
Subject: drm/omap: Move GEM BO to drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-6-daniels@collabora.com
---
 drivers/gpu/drm/omapdrm/omap_fb.c | 60 ++++++++++-----------------------------
 1 file changed, 15 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 5fd22ca73913..3d6b6f3d6808 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -19,6 +19,7 @@
 
 #include <drm/drm_crtc.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 
 #include "omap_dmm_tiler.h"
 #include "omap_drv.h"
@@ -51,7 +52,6 @@ static const u32 formats[] = {
 
 /* per-plane info for the fb: */
 struct plane {
-	struct drm_gem_object *bo;
 	u32 pitch;
 	u32 offset;
 	dma_addr_t dma_addr;
@@ -68,36 +68,9 @@ struct omap_framebuffer {
 	struct mutex lock;
 };
 
-static int omap_framebuffer_create_handle(struct drm_framebuffer *fb,
-		struct drm_file *file_priv,
-		unsigned int *handle)
-{
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	return drm_gem_handle_create(file_priv,
-			omap_fb->planes[0].bo, handle);
-}
-
-static void omap_framebuffer_destroy(struct drm_framebuffer *fb)
-{
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	int i, n = fb->format->num_planes;
-
-	DBG("destroy: FB ID: %d (%p)", fb->base.id, fb);
-
-	drm_framebuffer_cleanup(fb);
-
-	for (i = 0; i < n; i++) {
-		struct plane *plane = &omap_fb->planes[i];
-
-		drm_gem_object_unreference_unlocked(plane->bo);
-	}
-
-	kfree(omap_fb);
-}
-
 static const struct drm_framebuffer_funcs omap_framebuffer_funcs = {
-	.create_handle = omap_framebuffer_create_handle,
-	.destroy = omap_framebuffer_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
 static u32 get_linear_addr(struct plane *plane,
@@ -114,10 +87,7 @@ static u32 get_linear_addr(struct plane *plane,
 
 bool omap_framebuffer_supports_rotation(struct drm_framebuffer *fb)
 {
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
-	struct plane *plane = &omap_fb->planes[0];
-
-	return omap_gem_flags(plane->bo) & OMAP_BO_TILED;
+	return omap_gem_flags(fb->obj[0]) & OMAP_BO_TILED;
 }
 
 /* Note: DRM rotates counter-clockwise, TILER & DSS rotates clockwise */
@@ -176,7 +146,7 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 	x = state->src_x >> 16;
 	y = state->src_y >> 16;
 
-	if (omap_gem_flags(plane->bo) & OMAP_BO_TILED) {
+	if (omap_gem_flags(fb->obj[0]) & OMAP_BO_TILED) {
 		u32 w = state->src_w >> 16;
 		u32 h = state->src_h >> 16;
 
@@ -201,12 +171,12 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 			x += w - 1;
 
 		/* Note: x and y are in TILER units, not pixels */
-		omap_gem_rotated_dma_addr(plane->bo, orient, x, y,
+		omap_gem_rotated_dma_addr(fb->obj[0], orient, x, y,
 					  &info->paddr);
 		info->rotation_type = OMAP_DSS_ROT_TILER;
 		info->rotation = state->rotation ?: DRM_MODE_ROTATE_0;
 		/* Note: stride in TILER units, not pixels */
-		info->screen_width  = omap_gem_tiled_stride(plane->bo, orient);
+		info->screen_width  = omap_gem_tiled_stride(fb->obj[0], orient);
 	} else {
 		switch (state->rotation & DRM_MODE_ROTATE_MASK) {
 		case 0:
@@ -234,8 +204,8 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 		plane = &omap_fb->planes[1];
 
 		if (info->rotation_type == OMAP_DSS_ROT_TILER) {
-			WARN_ON(!(omap_gem_flags(plane->bo) & OMAP_BO_TILED));
-			omap_gem_rotated_dma_addr(plane->bo, orient, x/2, y/2,
+			WARN_ON(!(omap_gem_flags(fb->obj[1]) & OMAP_BO_TILED));
+			omap_gem_rotated_dma_addr(fb->obj[1], orient, x/2, y/2,
 						  &info->p_uv_addr);
 		} else {
 			info->p_uv_addr = get_linear_addr(plane, format, 1, x, y);
@@ -261,10 +231,10 @@ int omap_framebuffer_pin(struct drm_framebuffer *fb)
 
 	for (i = 0; i < n; i++) {
 		struct plane *plane = &omap_fb->planes[i];
-		ret = omap_gem_pin(plane->bo, &plane->dma_addr);
+		ret = omap_gem_pin(fb->obj[i], &plane->dma_addr);
 		if (ret)
 			goto fail;
-		omap_gem_dma_sync_buffer(plane->bo, DMA_TO_DEVICE);
+		omap_gem_dma_sync_buffer(fb->obj[i], DMA_TO_DEVICE);
 	}
 
 	omap_fb->pin_count++;
@@ -276,7 +246,7 @@ int omap_framebuffer_pin(struct drm_framebuffer *fb)
 fail:
 	for (i--; i >= 0; i--) {
 		struct plane *plane = &omap_fb->planes[i];
-		omap_gem_unpin(plane->bo);
+		omap_gem_unpin(fb->obj[i]);
 		plane->dma_addr = 0;
 	}
 
@@ -302,7 +272,7 @@ void omap_framebuffer_unpin(struct drm_framebuffer *fb)
 
 	for (i = 0; i < n; i++) {
 		struct plane *plane = &omap_fb->planes[i];
-		omap_gem_unpin(plane->bo);
+		omap_gem_unpin(fb->obj[i]);
 		plane->dma_addr = 0;
 	}
 
@@ -349,7 +319,7 @@ void omap_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 		struct plane *plane = &omap_fb->planes[i];
 		seq_printf(m, "   %d: offset=%d pitch=%d, obj: ",
 				i, plane->offset, plane->pitch);
-		omap_gem_describe(plane->bo, m);
+		omap_gem_describe(fb->obj[i], m);
 	}
 }
 #endif
@@ -454,7 +424,7 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev,
 			goto fail;
 		}
 
-		plane->bo     = bos[i];
+		fb->obj[i]    = bos[i];
 		plane->offset = mode_cmd->offsets[i];
 		plane->pitch  = pitch;
 		plane->dma_addr  = 0;
-- 
cgit v1.2.3


From 2ecceeb53b19455ffa50b31fd3c20fe2974508a6 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 30 Mar 2018 15:11:21 +0100
Subject: drm/omap: Move buffer pitch/offset to drm_framebuffer

drm_framebuffer already holds per-plane pitch and offsets, which is
filled out for us when we create the framebuffer. Nuke our local copy in
the plane struct.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180330141138.28987-7-daniels@collabora.com
---
 drivers/gpu/drm/omapdrm/omap_fb.c | 22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 3d6b6f3d6808..9d75eab0d164 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -52,8 +52,6 @@ static const u32 formats[] = {
 
 /* per-plane info for the fb: */
 struct plane {
-	u32 pitch;
-	u32 offset;
 	dma_addr_t dma_addr;
 };
 
@@ -73,14 +71,16 @@ static const struct drm_framebuffer_funcs omap_framebuffer_funcs = {
 	.destroy = drm_gem_fb_destroy,
 };
 
-static u32 get_linear_addr(struct plane *plane,
+static u32 get_linear_addr(struct drm_framebuffer *fb,
 		const struct drm_format_info *format, int n, int x, int y)
 {
+	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
+	struct plane *plane = &omap_fb->planes[n];
 	u32 offset;
 
-	offset = plane->offset
+	offset = fb->offsets[n]
 	       + (x * format->cpp[n] / (n == 0 ? 1 : format->hsub))
-	       + (y * plane->pitch / (n == 0 ? 1 : format->vsub));
+	       + (y * fb->pitches[n] / (n == 0 ? 1 : format->vsub));
 
 	return plane->dma_addr + offset;
 }
@@ -191,10 +191,10 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 			break;
 		}
 
-		info->paddr         = get_linear_addr(plane, format, 0, x, y);
+		info->paddr         = get_linear_addr(fb, format, 0, x, y);
 		info->rotation_type = OMAP_DSS_ROT_NONE;
 		info->rotation      = DRM_MODE_ROTATE_0;
-		info->screen_width  = plane->pitch;
+		info->screen_width  = fb->pitches[0];
 	}
 
 	/* convert to pixels: */
@@ -208,7 +208,7 @@ void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 			omap_gem_rotated_dma_addr(fb->obj[1], orient, x/2, y/2,
 						  &info->p_uv_addr);
 		} else {
-			info->p_uv_addr = get_linear_addr(plane, format, 1, x, y);
+			info->p_uv_addr = get_linear_addr(fb, format, 1, x, y);
 		}
 	} else {
 		info->p_uv_addr = 0;
@@ -309,16 +309,14 @@ struct drm_connector *omap_framebuffer_get_next_connector(
 #ifdef CONFIG_DEBUG_FS
 void omap_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 {
-	struct omap_framebuffer *omap_fb = to_omap_framebuffer(fb);
 	int i, n = fb->format->num_planes;
 
 	seq_printf(m, "fb: %dx%d@%4.4s\n", fb->width, fb->height,
 			(char *)&fb->format->format);
 
 	for (i = 0; i < n; i++) {
-		struct plane *plane = &omap_fb->planes[i];
 		seq_printf(m, "   %d: offset=%d pitch=%d, obj: ",
-				i, plane->offset, plane->pitch);
+				i, fb->offsets[n], fb->pitches[i]);
 		omap_gem_describe(fb->obj[i], m);
 	}
 }
@@ -425,8 +423,6 @@ struct drm_framebuffer *omap_framebuffer_init(struct drm_device *dev,
 		}
 
 		fb->obj[i]    = bos[i];
-		plane->offset = mode_cmd->offsets[i];
-		plane->pitch  = pitch;
 		plane->dma_addr  = 0;
 	}
 
-- 
cgit v1.2.3


From c7cbed560ce24a87eccf219bc4c78a19961a6074 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Mon, 21 May 2018 15:24:49 +0100
Subject: drm/gma500: Fix Medfield for drm_framebuffer move

Commit bc61c97502e2 ("drm/gma500: Move GEM BO to drm_framebuffer") moved
the gtt_range structure, from being in psb_framebuffer and embedding the
GEM object, to being placed in the drm_framebuffer with the gtt_range
being derived from the GEM object.

The conversion missed out the Medfield subdriver, which was not being
built in the default drm-misc config. Do the trivial fixup here.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Fixes: bc61c97502e2 ("drm/gma500: Move GEM BO to drm_framebuffer")
Cc: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521142449.20800-1-daniels@collabora.com
---
 drivers/gpu/drm/gma500/mdfld_intel_display.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/gma500/mdfld_intel_display.c b/drivers/gpu/drm/gma500/mdfld_intel_display.c
index 5c066448be5b..881d613cc2e5 100644
--- a/drivers/gpu/drm/gma500/mdfld_intel_display.c
+++ b/drivers/gpu/drm/gma500/mdfld_intel_display.c
@@ -196,7 +196,7 @@ static int mdfld__intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	if (!gma_power_begin(dev, true))
 		return 0;
 
-	start = psbfb->gtt->offset;
+	start = to_gtt_range(fb->obj[0])->offset;
 	offset = y * fb->pitches[0] + x * fb->format->cpp[0];
 
 	REG_WRITE(map->stride, fb->pitches[0]);
-- 
cgit v1.2.3


From d93fa1b47b8fcd149b5091f18385304f402a8e15 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 16 May 2018 11:01:10 +0300
Subject: Revert "drm/i915/edp: Allow alternate fixed mode for eDP if
 available."

This reverts commit dc911f5bd8aacfcf8aabd5c26c88e04c837a938e.

Per the report, no matter what display mode you select with xrandr, the
i915 driver will always select the alternate fixed mode. For the
reporter this means that the display will always run at 40Hz which is
quite annoying. This may be due to the mode comparison.

But there are some other potential issues. The choice of alt_fixed_mode
seems dubious. It's the first non-preferred mode, but there are no
guarantees that the only difference would be refresh rate. Similarly,
there may be more than one preferred mode in the probed modes list, and
the commit changes the preferred mode selection to choose the last one
on the list instead of the first.

(Note that the probed modes list is the raw, unfiltered, unsorted list
of modes from drm_add_edid_modes(), not the pretty result after a
drm_helper_probe_single_connector_modes() call.)

Finally, we already have eerily similar code in place to find the
downclock mode for DRRS that seems like could be reused here.

Back to the drawing board.

Note: This is a hand-crafted revert due to conflicts. If it fails to
backport, please just try reverting the original commit directly.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105469
Reported-by: Rune Petersen <rune@megahurts.dk>
Reported-by: Mark Spencer <n7u4722r35@ynzlx.anonbox.net>
Fixes: dc911f5bd8aa ("drm/i915/edp: Allow alternate fixed mode for eDP if available.")
Cc: Clint Taylor <clinton.a.taylor@intel.com>
Cc: David Weinehall <david.weinehall@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jim Bride <jim.bride@linux.intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: intel-gfx@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v4.14+
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516080110.22770-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_dp.c    | 38 +++++---------------------------------
 drivers/gpu/drm/i915/intel_drv.h   |  2 --
 drivers/gpu/drm/i915/intel_dsi.c   |  2 +-
 drivers/gpu/drm/i915/intel_dvo.c   |  2 +-
 drivers/gpu/drm/i915/intel_lvds.c  |  3 +--
 drivers/gpu/drm/i915/intel_panel.c |  6 ------
 6 files changed, 8 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 102070940095..be99e56cf7d9 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1679,23 +1679,6 @@ static int intel_dp_compute_bpp(struct intel_dp *intel_dp,
 	return bpp;
 }
 
-static bool intel_edp_compare_alt_mode(struct drm_display_mode *m1,
-				       struct drm_display_mode *m2)
-{
-	bool bres = false;
-
-	if (m1 && m2)
-		bres = (m1->hdisplay == m2->hdisplay &&
-			m1->hsync_start == m2->hsync_start &&
-			m1->hsync_end == m2->hsync_end &&
-			m1->htotal == m2->htotal &&
-			m1->vdisplay == m2->vdisplay &&
-			m1->vsync_start == m2->vsync_start &&
-			m1->vsync_end == m2->vsync_end &&
-			m1->vtotal == m2->vtotal);
-	return bres;
-}
-
 /* Adjust link config limits based on compliance test requests. */
 static void
 intel_dp_adjust_compliance_config(struct intel_dp *intel_dp,
@@ -1860,16 +1843,8 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 		pipe_config->has_audio = intel_conn_state->force_audio == HDMI_AUDIO_ON;
 
 	if (intel_dp_is_edp(intel_dp) && intel_connector->panel.fixed_mode) {
-		struct drm_display_mode *panel_mode =
-			intel_connector->panel.alt_fixed_mode;
-		struct drm_display_mode *req_mode = &pipe_config->base.mode;
-
-		if (!intel_edp_compare_alt_mode(req_mode, panel_mode))
-			panel_mode = intel_connector->panel.fixed_mode;
-
-		drm_mode_debug_printmodeline(panel_mode);
-
-		intel_fixed_panel_mode(panel_mode, adjusted_mode);
+		intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
+				       adjusted_mode);
 
 		if (INTEL_GEN(dev_priv) >= 9) {
 			int ret;
@@ -6137,7 +6112,6 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct drm_connector *connector = &intel_connector->base;
 	struct drm_display_mode *fixed_mode = NULL;
-	struct drm_display_mode *alt_fixed_mode = NULL;
 	struct drm_display_mode *downclock_mode = NULL;
 	bool has_dpcd;
 	struct drm_display_mode *scan;
@@ -6192,14 +6166,13 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	}
 	intel_connector->edid = edid;
 
-	/* prefer fixed mode from EDID if available, save an alt mode also */
+	/* prefer fixed mode from EDID if available */
 	list_for_each_entry(scan, &connector->probed_modes, head) {
 		if ((scan->type & DRM_MODE_TYPE_PREFERRED)) {
 			fixed_mode = drm_mode_duplicate(dev, scan);
 			downclock_mode = intel_dp_drrs_init(
 						intel_connector, fixed_mode);
-		} else if (!alt_fixed_mode) {
-			alt_fixed_mode = drm_mode_duplicate(dev, scan);
+			break;
 		}
 	}
 
@@ -6236,8 +6209,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 			      pipe_name(pipe));
 	}
 
-	intel_panel_init(&intel_connector->panel, fixed_mode, alt_fixed_mode,
-			 downclock_mode);
+	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
 	intel_connector->panel.backlight.power = intel_edp_backlight_power;
 	intel_panel_setup_backlight(connector, pipe);
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index ac19da7f8790..2bf383bb4b8d 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -276,7 +276,6 @@ struct intel_encoder {
 
 struct intel_panel {
 	struct drm_display_mode *fixed_mode;
-	struct drm_display_mode *alt_fixed_mode;
 	struct drm_display_mode *downclock_mode;
 
 	/* backlight */
@@ -1855,7 +1854,6 @@ void intel_overlay_reset(struct drm_i915_private *dev_priv);
 /* intel_panel.c */
 int intel_panel_init(struct intel_panel *panel,
 		     struct drm_display_mode *fixed_mode,
-		     struct drm_display_mode *alt_fixed_mode,
 		     struct drm_display_mode *downclock_mode);
 void intel_panel_fini(struct intel_panel *panel);
 void intel_fixed_panel_mode(const struct drm_display_mode *fixed_mode,
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index 51a1d6868b1e..cf39ca90d887 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -1846,7 +1846,7 @@ void intel_dsi_init(struct drm_i915_private *dev_priv)
 	connector->display_info.width_mm = fixed_mode->width_mm;
 	connector->display_info.height_mm = fixed_mode->height_mm;
 
-	intel_panel_init(&intel_connector->panel, fixed_mode, NULL, NULL);
+	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
 	intel_panel_setup_backlight(connector, INVALID_PIPE);
 
 	intel_dsi_add_properties(intel_connector);
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index a86f0398570f..7b942b6c1700 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -531,7 +531,7 @@ void intel_dvo_init(struct drm_i915_private *dev_priv)
 			 */
 			intel_panel_init(&intel_connector->panel,
 					 intel_dvo_get_current_mode(intel_encoder),
-					 NULL, NULL);
+					 NULL);
 			intel_dvo->panel_wants_dither = true;
 		}
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index a92bb63b2f2d..17f297dca296 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -1177,8 +1177,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 out:
 	mutex_unlock(&dev->mode_config.mutex);
 
-	intel_panel_init(&intel_connector->panel, fixed_mode, NULL,
-			 downclock_mode);
+	intel_panel_init(&intel_connector->panel, fixed_mode, downclock_mode);
 	intel_panel_setup_backlight(connector, INVALID_PIPE);
 
 	lvds_encoder->is_dual_link = compute_is_dual_link_lvds(lvds_encoder);
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 41d00b1603e3..b443278e569c 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -1928,13 +1928,11 @@ intel_panel_init_backlight_funcs(struct intel_panel *panel)
 
 int intel_panel_init(struct intel_panel *panel,
 		     struct drm_display_mode *fixed_mode,
-		     struct drm_display_mode *alt_fixed_mode,
 		     struct drm_display_mode *downclock_mode)
 {
 	intel_panel_init_backlight_funcs(panel);
 
 	panel->fixed_mode = fixed_mode;
-	panel->alt_fixed_mode = alt_fixed_mode;
 	panel->downclock_mode = downclock_mode;
 
 	return 0;
@@ -1948,10 +1946,6 @@ void intel_panel_fini(struct intel_panel *panel)
 	if (panel->fixed_mode)
 		drm_mode_destroy(intel_connector->base.dev, panel->fixed_mode);
 
-	if (panel->alt_fixed_mode)
-		drm_mode_destroy(intel_connector->base.dev,
-				panel->alt_fixed_mode);
-
 	if (panel->downclock_mode)
 		drm_mode_destroy(intel_connector->base.dev,
 				panel->downclock_mode);
-- 
cgit v1.2.3


From 84b510e22da7926522a257cfe295d3695346a0bd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 21 May 2018 22:05:30 +0100
Subject: drm/i915/query: Protect tainted function pointer lookup

Smatch identifies i915_query_ioctl() as being a potential victim of
Spectre due to its use of a tainted user index into a function pointer
array. Use array_index_nospec() to defang the user index before using it
to lookup the function pointer.

Fixes: a446ae2c6e65 ("drm/i915: add query uAPI")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521210530.26008-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_query.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 3ace929dd90f..95f9d179afc4 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -4,6 +4,8 @@
  * Copyright © 2018 Intel Corporation
  */
 
+#include <linux/nospec.h>
+
 #include "i915_drv.h"
 #include "i915_query.h"
 #include <uapi/drm/i915_drm.h>
@@ -111,10 +113,12 @@ int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 		func_idx = item.query_id - 1;
 
-		if (func_idx < ARRAY_SIZE(i915_query_funcs))
+		ret = -EINVAL;
+		if (func_idx < ARRAY_SIZE(i915_query_funcs)) {
+			func_idx = array_index_nospec(func_idx,
+						      ARRAY_SIZE(i915_query_funcs));
 			ret = i915_query_funcs[func_idx](dev_priv, &item);
-		else
-			ret = -EINVAL;
+		}
 
 		/* Only write the length back to userspace if they differ. */
 		if (ret != item.length && put_user(ret, &user_item_ptr->length))
-- 
cgit v1.2.3


From 1abb70f5955d1a9021f96359a2c6502ca569b68d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 22 May 2018 09:36:43 +0100
Subject: drm/i915/gtt: Allow pagedirectory allocations to fail

As we handle the allocation failure of the page directory and tables by
propagating the failure back to userspace, allow it to fail if direct
reclaim is unable to satisfy the request (i.e. disable the oomkiller).
The premise being that if we are unable to allocate a single page for
the pagetable, we will not be able to handle the multitude of pages
required for the gfx operation and we should back off to allow the
system to recover.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106609
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522083643.29601-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 996ab2ad6c45..fc5c0f746f26 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -42,7 +42,7 @@
 #include "intel_drv.h"
 #include "intel_frontbuffer.h"
 
-#define I915_GFP_DMA (GFP_KERNEL | __GFP_HIGHMEM)
+#define I915_GFP_ALLOW_FAIL (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_NOWARN)
 
 /**
  * DOC: Global GTT views
@@ -489,7 +489,7 @@ static int __setup_page_dma(struct i915_address_space *vm,
 			    struct i915_page_dma *p,
 			    gfp_t gfp)
 {
-	p->page = vm_alloc_page(vm, gfp | __GFP_NOWARN | __GFP_NORETRY);
+	p->page = vm_alloc_page(vm, gfp | I915_GFP_ALLOW_FAIL);
 	if (unlikely(!p->page))
 		return -ENOMEM;
 
@@ -506,7 +506,7 @@ static int __setup_page_dma(struct i915_address_space *vm,
 static int setup_page_dma(struct i915_address_space *vm,
 			  struct i915_page_dma *p)
 {
-	return __setup_page_dma(vm, p, I915_GFP_DMA);
+	return __setup_page_dma(vm, p, __GFP_HIGHMEM);
 }
 
 static void cleanup_page_dma(struct i915_address_space *vm,
@@ -614,7 +614,7 @@ static struct i915_page_table *alloc_pt(struct i915_address_space *vm)
 {
 	struct i915_page_table *pt;
 
-	pt = kmalloc(sizeof(*pt), GFP_KERNEL | __GFP_NOWARN);
+	pt = kmalloc(sizeof(*pt), I915_GFP_ALLOW_FAIL);
 	if (unlikely(!pt))
 		return ERR_PTR(-ENOMEM);
 
@@ -651,7 +651,7 @@ static struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
 {
 	struct i915_page_directory *pd;
 
-	pd = kzalloc(sizeof(*pd), GFP_KERNEL | __GFP_NOWARN);
+	pd = kzalloc(sizeof(*pd), I915_GFP_ALLOW_FAIL);
 	if (unlikely(!pd))
 		return ERR_PTR(-ENOMEM);
 
@@ -685,7 +685,7 @@ static int __pdp_init(struct i915_address_space *vm,
 	const unsigned int pdpes = i915_pdpes_per_pdp(vm);
 
 	pdp->page_directory = kmalloc_array(pdpes, sizeof(*pdp->page_directory),
-					    GFP_KERNEL | __GFP_NOWARN);
+					    I915_GFP_ALLOW_FAIL);
 	if (unlikely(!pdp->page_directory))
 		return -ENOMEM;
 
@@ -1229,7 +1229,7 @@ static int gen8_init_scratch(struct i915_address_space *vm)
 {
 	int ret;
 
-	ret = setup_scratch_page(vm, I915_GFP_DMA);
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
 	if (ret)
 		return ret;
 
@@ -1974,7 +1974,7 @@ static int gen6_init_scratch(struct i915_address_space *vm)
 {
 	int ret;
 
-	ret = setup_scratch_page(vm, I915_GFP_DMA);
+	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 5255e2f8d1177f3eddeae930dda58e4dc7b4373d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 8 May 2018 17:08:14 +0300
Subject: drm/i915: Replace vbt edp.support with int_lvds_support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace dev_priv->vbt.edp.support with
dev_priv->vbt.int_lvds_support. We'll want to extend its
use beyond the LVDS vs. eDP case in the future.

v2: Nuke the edp.support from parse_edp() (Jani)
    Only clear int_lvds_support for gen5+ to preserve
    the current behaviour (Jani)

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180508140814.20105-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h   |  2 +-
 drivers/gpu/drm/i915/intel_bios.c | 13 +++++++------
 drivers/gpu/drm/i915/intel_lvds.c |  9 +++++----
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e33c380b43e3..3302b3d4d974 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1052,6 +1052,7 @@ struct intel_vbt_data {
 	unsigned int lvds_vbt:1;
 	unsigned int int_crt_support:1;
 	unsigned int lvds_use_ssc:1;
+	unsigned int int_lvds_support:1;
 	unsigned int display_clock_mode:1;
 	unsigned int fdi_rx_polarity_inverted:1;
 	unsigned int panel_type:4;
@@ -1067,7 +1068,6 @@ struct intel_vbt_data {
 		int vswing;
 		bool low_vswing;
 		bool initialized;
-		bool support;
 		int bpp;
 		struct edp_power_seq pps;
 	} edp;
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 54270bdde100..5c863e2714ec 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -518,8 +518,9 @@ parse_driver_features(struct drm_i915_private *dev_priv,
 	if (!driver)
 		return;
 
-	if (driver->lvds_config == BDB_DRIVER_FEATURE_EDP)
-		dev_priv->vbt.edp.support = 1;
+	if (INTEL_GEN(dev_priv) >= 5 &&
+	    driver->lvds_config == BDB_DRIVER_FEATURE_EDP)
+		dev_priv->vbt.int_lvds_support = 0;
 
 	DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
 	/*
@@ -542,11 +543,8 @@ parse_edp(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 	int panel_type = dev_priv->vbt.panel_type;
 
 	edp = find_section(bdb, BDB_EDP);
-	if (!edp) {
-		if (dev_priv->vbt.edp.support)
-			DRM_DEBUG_KMS("No eDP BDB found but eDP panel supported.\n");
+	if (!edp)
 		return;
-	}
 
 	switch ((edp->color_depth >> (panel_type * 2)) & 3) {
 	case EDP_18BPP:
@@ -1513,6 +1511,9 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 	dev_priv->vbt.int_tv_support = 1;
 	dev_priv->vbt.int_crt_support = 1;
 
+	/* driver features */
+	dev_priv->vbt.int_lvds_support = 1;
+
 	/* Default to using SSC */
 	dev_priv->vbt.lvds_use_ssc = 1;
 	/*
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 17f297dca296..bacad88ad7ae 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -1003,6 +1003,11 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	if (dmi_check_system(intel_no_lvds))
 		return;
 
+	if (!dev_priv->vbt.int_lvds_support) {
+		DRM_DEBUG_KMS("Internal LVDS support disabled by VBT\n");
+		return;
+	}
+
 	if (HAS_PCH_SPLIT(dev_priv))
 		lvds_reg = PCH_LVDS;
 	else
@@ -1013,10 +1018,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	if (HAS_PCH_SPLIT(dev_priv)) {
 		if ((lvds & LVDS_DETECTED) == 0)
 			return;
-		if (dev_priv->vbt.edp.support) {
-			DRM_DEBUG_KMS("disable LVDS for eDP support\n");
-			return;
-		}
 	}
 
 	pin = GMBUS_PIN_PANEL;
-- 
cgit v1.2.3


From 59462a00cc88bc45eaed069942362839ccb0b3de Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 8 May 2018 15:41:36 +0300
Subject: drm/i915: Eliminate the unused dev_priv->vbt.lvds_vbt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dev_priv->vbt.lvds_vbt is set but never actually used. Kill it.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180508124136.10969-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_drv.h   | 1 -
 drivers/gpu/drm/i915/intel_bios.c | 3 ---
 2 files changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 3302b3d4d974..b86ed6401120 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1049,7 +1049,6 @@ struct intel_vbt_data {
 	/* Feature bits */
 	unsigned int int_tv_support:1;
 	unsigned int lvds_dither:1;
-	unsigned int lvds_vbt:1;
 	unsigned int int_crt_support:1;
 	unsigned int lvds_use_ssc:1;
 	unsigned int int_lvds_support:1;
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 5c863e2714ec..34c805970d7c 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -267,8 +267,6 @@ parse_lfp_panel_data(struct drm_i915_private *dev_priv,
 	if (!lvds_lfp_data_ptrs)
 		return;
 
-	dev_priv->vbt.lvds_vbt = 1;
-
 	panel_dvo_timing = get_lvds_dvo_timing(lvds_lfp_data,
 					       lvds_lfp_data_ptrs,
 					       panel_type);
@@ -1502,7 +1500,6 @@ init_vbt_defaults(struct drm_i915_private *dev_priv)
 
 	/* LFP panel data */
 	dev_priv->vbt.lvds_dither = 1;
-	dev_priv->vbt.lvds_vbt = 0;
 
 	/* SDVO panel data */
 	dev_priv->vbt.sdvo_lvds_vbt_mode = NULL;
-- 
cgit v1.2.3


From a33b1dc8a732144e11cb4bf067d24ba51e6b8ab0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 22 May 2018 13:10:18 +0100
Subject: drm/i915/query: nospec expects no more than an unsigned long

nospec quite reasonably asserts that it will never be used with an index
larger than unsigned long (that being the largest possibly index into an
C array). However, our ubi uses the convention of u64 for any large
integer, running afoul of the assertion on 32b. Reduce our index to an
unsigned long, checking for type overflow first.

  drivers/gpu/drm/i915/i915_query.c: In function 'i915_query_ioctl':
  include/linux/compiler.h:339:38: error: call to '__compiletime_assert_119' declared with attribute error: BUILD_BUG_ON failed: sizeof(_s) > sizeof(long)

Reported-by: kbuild-all@01.org
Fixes: 84b510e22da7 ("drm/i915/query: Protect tainted function pointer lookup")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522121018.15199-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_query.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_query.c b/drivers/gpu/drm/i915/i915_query.c
index 95f9d179afc4..3f502eef2431 100644
--- a/drivers/gpu/drm/i915/i915_query.c
+++ b/drivers/gpu/drm/i915/i915_query.c
@@ -102,7 +102,7 @@ int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 	for (i = 0; i < args->num_items; i++, user_item_ptr++) {
 		struct drm_i915_query_item item;
-		u64 func_idx;
+		unsigned long func_idx;
 		int ret;
 
 		if (copy_from_user(&item, user_item_ptr, sizeof(item)))
@@ -111,6 +111,9 @@ int i915_query_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		if (item.query_id == 0)
 			return -EINVAL;
 
+		if (overflows_type(item.query_id - 1, unsigned long))
+			return -EINVAL;
+
 		func_idx = item.query_id - 1;
 
 		ret = -EINVAL;
-- 
cgit v1.2.3


From 520ea9347505f5eb90a6162385cf821e80b6c233 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Mon, 9 Apr 2018 14:06:47 -0700
Subject: drm/gma500: Remove VLA

There's an ongoing effort to remove VLAs[1] from the kernel to eventually
turn on -Wvla. Switch to a reasonable upper bound for the VLAs in
the gma500 driver.

[1] https://lkml.org/lkml/2018/3/7/621

Signed-off-by: Laura Abbott <labbott@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180409210647.3718-1-labbott@redhat.com
---
 drivers/gpu/drm/gma500/psb_intel_sdvo.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index f2ee6aa10afa..1d40746ab625 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -429,13 +429,20 @@ static const char *cmd_status_names[] = {
 	"Scaling not supported"
 };
 
+#define MAX_ARG_LEN 32
+
 static bool psb_intel_sdvo_write_cmd(struct psb_intel_sdvo *psb_intel_sdvo, u8 cmd,
 				 const void *args, int args_len)
 {
-	u8 buf[args_len*2 + 2], status;
-	struct i2c_msg msgs[args_len + 3];
+	u8 buf[MAX_ARG_LEN*2 + 2], status;
+	struct i2c_msg msgs[MAX_ARG_LEN + 3];
 	int i, ret;
 
+	if (args_len > MAX_ARG_LEN) {
+		DRM_ERROR("Need to increase arg length\n");
+		return false;
+	}
+
 	psb_intel_sdvo_debug_write(psb_intel_sdvo, cmd, args, args_len);
 
 	for (i = 0; i < args_len; i++) {
-- 
cgit v1.2.3


From ca510ead96d78c5379db5d36ffbdf5382f36db6d Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Tue, 10 Apr 2018 18:03:30 -0700
Subject: drm/i2c: tda998x: Remove VLA usage

There's an ongoing effort to remove VLAs[1] from the kernel to eventually
turn on -Wvla. The vla in reg_write_range is based on the length of data
passed. The one use of a non-constant size for this range is bounded by
the size buffer passed to hdmi_infoframe_pack which is a fixed size.
Switch to this upper bound.

[1] https://lkml.org/lkml/2018/3/7/621

Signed-off-by: Laura Abbott <labbott@redhat.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180411010330.17866-1-labbott@redhat.com
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 421c8a72369e..0068d714d1bd 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -466,13 +466,22 @@ out:
 	return ret;
 }
 
+#define MAX_WRITE_RANGE_BUF 32
+
 static void
 reg_write_range(struct tda998x_priv *priv, u16 reg, u8 *p, int cnt)
 {
 	struct i2c_client *client = priv->hdmi;
-	u8 buf[cnt+1];
+	/* This is the maximum size of the buffer passed in */
+	u8 buf[MAX_WRITE_RANGE_BUF + 1];
 	int ret;
 
+	if (cnt > MAX_WRITE_RANGE_BUF) {
+		dev_err(&client->dev, "Fixed write buffer too small (%d)\n",
+				MAX_WRITE_RANGE_BUF);
+		return;
+	}
+
 	buf[0] = REG2ADDR(reg);
 	memcpy(&buf[1], p, cnt);
 
@@ -679,7 +688,7 @@ static void
 tda998x_write_if(struct tda998x_priv *priv, u8 bit, u16 addr,
 		 union hdmi_infoframe *frame)
 {
-	u8 buf[32];
+	u8 buf[MAX_WRITE_RANGE_BUF];
 	ssize_t len;
 
 	len = hdmi_infoframe_pack(frame, buf, sizeof(buf));
-- 
cgit v1.2.3


From 3c5f134ac9d0e405a15af652c3ce8cbaa9bf1bc7 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Wed, 25 Apr 2018 10:29:22 +0530
Subject: gpu: drm: udl: Adding new typedef vm_fault_t

Use new return type vm_fault_t for fault and huge_fault
handler. For now, this is just documenting that the
function returns a VM_FAULT value rather than an errno.
Once all instances are converted, vm_fault_t will become
a distinct type.

Commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Previously vm_insert_page() returns err which driver
mapped into VM_FAULT_* type. The new function vmf_
insert_page() will replace this inefficiency by
returning VM_FAULT_* type.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180425045922.GA21590@jordon-HP-15-Notebook-PC
---
 drivers/gpu/drm/udl/udl_drv.h |  3 ++-
 drivers/gpu/drm/udl/udl_gem.c | 15 ++-------------
 2 files changed, 4 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 55c0cc309198..072582570a4f 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -16,6 +16,7 @@
 
 #include <linux/usb.h>
 #include <drm/drm_gem.h>
+#include <linux/mm_types.h>
 
 #define DRIVER_NAME		"udl"
 #define DRIVER_DESC		"DisplayLink"
@@ -136,7 +137,7 @@ void udl_gem_put_pages(struct udl_gem_object *obj);
 int udl_gem_vmap(struct udl_gem_object *obj);
 void udl_gem_vunmap(struct udl_gem_object *obj);
 int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-int udl_gem_fault(struct vm_fault *vmf);
+vm_fault_t udl_gem_fault(struct vm_fault *vmf);
 
 int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 		      int width, int height);
diff --git a/drivers/gpu/drm/udl/udl_gem.c b/drivers/gpu/drm/udl/udl_gem.c
index 9a15cce22cce..d5a23295dd80 100644
--- a/drivers/gpu/drm/udl/udl_gem.c
+++ b/drivers/gpu/drm/udl/udl_gem.c
@@ -100,13 +100,12 @@ int udl_drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	return ret;
 }
 
-int udl_gem_fault(struct vm_fault *vmf)
+vm_fault_t udl_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct udl_gem_object *obj = to_udl_bo(vma->vm_private_data);
 	struct page *page;
 	unsigned int page_offset;
-	int ret = 0;
 
 	page_offset = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
 
@@ -114,17 +113,7 @@ int udl_gem_fault(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	page = obj->pages[page_offset];
-	ret = vm_insert_page(vma, vmf->address, page);
-	switch (ret) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_page(vma, vmf->address, page);
 }
 
 int udl_gem_get_pages(struct udl_gem_object *obj)
-- 
cgit v1.2.3


From f606bc6d9d416504596844d513474791cdbb3993 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:29:25 +0300
Subject: drm/i915: Move intel_ddi_get_crtc_new_encoder() out from ddi code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ddi code no longer uses intel_ddi_get_crtc_new_encoder(). Move it
elsewhere where we have some users left.

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518152931.13104-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/intel_ddi.c     | 29 -----------------------------
 drivers/gpu/drm/i915/intel_display.c | 31 ++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_drv.h     |  2 --
 3 files changed, 30 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 1665bc588241..3b8f12883ca7 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1243,35 +1243,6 @@ intel_ddi_get_crtc_encoder(struct intel_crtc *crtc)
 	return ret;
 }
 
-/* Finds the only possible encoder associated with the given CRTC. */
-struct intel_encoder *
-intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_encoder *ret = NULL;
-	struct drm_atomic_state *state;
-	struct drm_connector *connector;
-	struct drm_connector_state *connector_state;
-	int num_encoders = 0;
-	int i;
-
-	state = crtc_state->base.state;
-
-	for_each_new_connector_in_state(state, connector, connector_state, i) {
-		if (connector_state->crtc != crtc_state->base.crtc)
-			continue;
-
-		ret = to_intel_encoder(connector_state->best_encoder);
-		num_encoders++;
-	}
-
-	WARN(num_encoders != 1, "%d encoders on crtc for pipe %c\n", num_encoders,
-	     pipe_name(crtc->pipe));
-
-	BUG_ON(ret == NULL);
-	return ret;
-}
-
 #define LC_FREQ 2700
 
 static int hsw_ddi_calc_wrpll_link(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 12226a2c8d39..16f9a9b3364a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4590,6 +4590,35 @@ static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc)
 	}
 }
 
+/*
+ * Finds the encoder associated with the given CRTC. This can only be
+ * used when we know that the CRTC isn't feeding multiple encoders!
+ */
+static struct intel_encoder *
+intel_get_crtc_new_encoder(const struct intel_crtc_state *crtc_state)
+{
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	const struct drm_atomic_state *state = crtc_state->base.state;
+	const struct drm_connector_state *connector_state;
+	const struct drm_connector *connector;
+	struct intel_encoder *encoder = NULL;
+	int num_encoders = 0;
+	int i;
+
+	for_each_new_connector_in_state(state, connector, connector_state, i) {
+		if (connector_state->crtc != &crtc->base)
+			continue;
+
+		encoder = to_intel_encoder(connector_state->best_encoder);
+		num_encoders++;
+	}
+
+	WARN(num_encoders != 1, "%d encoders for pipe %c\n",
+	     num_encoders, pipe_name(crtc->pipe));
+
+	return encoder;
+}
+
 /* Return which DP Port should be selected for Transcoder DP control */
 static enum port
 intel_trans_dp_port_sel(struct intel_crtc *crtc)
@@ -9103,7 +9132,7 @@ static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
 {
 	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) {
 		struct intel_encoder *encoder =
-			intel_ddi_get_crtc_new_encoder(crtc_state);
+			intel_get_crtc_new_encoder(crtc_state);
 
 		if (!intel_get_shared_dpll(crtc, crtc_state, encoder)) {
 			DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n",
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 2bf383bb4b8d..e919e0099ad6 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1393,8 +1393,6 @@ void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
 				       enum transcoder cpu_transcoder);
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state);
 void intel_ddi_disable_pipe_clock(const  struct intel_crtc_state *crtc_state);
-struct intel_encoder *
-intel_ddi_get_crtc_new_encoder(struct intel_crtc_state *crtc_state);
 void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state);
 void intel_ddi_prepare_link_retrain(struct intel_dp *intel_dp);
 bool intel_ddi_connector_get_hw_state(struct intel_connector *intel_connector);
-- 
cgit v1.2.3


From f67dc6d8869fd29fb1635119e3210bf92ce983a2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:29:26 +0300
Subject: drm/i915: Parametrize TRANS_DP_PORT_SEL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Parametrize the TRANS_DP_PORT_SEL macros.

v2: WARN for bogus ports (Jani)
    Order the defines mask,value (Jani)

Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518152931.13104-2-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_reg.h      |  8 +++-----
 drivers/gpu/drm/i915/intel_display.c | 24 ++++++++----------------
 2 files changed, 11 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 196a0eb79272..5a103496423c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7887,11 +7887,9 @@ enum {
 #define _TRANS_DP_CTL_C		0xe2300
 #define TRANS_DP_CTL(pipe)	_MMIO_PIPE(pipe, _TRANS_DP_CTL_A, _TRANS_DP_CTL_B)
 #define  TRANS_DP_OUTPUT_ENABLE	(1<<31)
-#define  TRANS_DP_PORT_SEL_B	(0<<29)
-#define  TRANS_DP_PORT_SEL_C	(1<<29)
-#define  TRANS_DP_PORT_SEL_D	(2<<29)
-#define  TRANS_DP_PORT_SEL_NONE	(3<<29)
-#define  TRANS_DP_PORT_SEL_MASK	(3<<29)
+#define  TRANS_DP_PORT_SEL_MASK		(3 << 29)
+#define  TRANS_DP_PORT_SEL_NONE		(3 << 29)
+#define  TRANS_DP_PORT_SEL(port)	(((port) - PORT_B) << 29)
 #define  TRANS_DP_PIPE_TO_PORT(val)	((((val) & TRANS_DP_PORT_SEL_MASK) >> 29) + PORT_B)
 #define  TRANS_DP_AUDIO_ONLY	(1<<26)
 #define  TRANS_DP_ENH_FRAMING	(1<<18)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 16f9a9b3364a..68d48b7445e9 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1360,9 +1360,9 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 {
 	enum pipe port_pipe;
 
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL_B);
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL_C);
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_D, TRANS_DP_PORT_SEL_D);
+	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL(PORT_B));
+	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL(PORT_C));
+	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_D, TRANS_DP_PORT_SEL(PORT_D));
 
 	I915_STATE_WARN(intel_crt_port_enabled(dev_priv, PCH_ADPA, &port_pipe) &&
 			port_pipe == pipe,
@@ -4702,6 +4702,8 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
 			&crtc_state->base.adjusted_mode;
 		u32 bpc = (I915_READ(PIPECONF(pipe)) & PIPECONF_BPC_MASK) >> 5;
 		i915_reg_t reg = TRANS_DP_CTL(pipe);
+		enum port port;
+
 		temp = I915_READ(reg);
 		temp &= ~(TRANS_DP_PORT_SEL_MASK |
 			  TRANS_DP_SYNC_MASK |
@@ -4714,19 +4716,9 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
 			temp |= TRANS_DP_VSYNC_ACTIVE_HIGH;
 
-		switch (intel_trans_dp_port_sel(crtc)) {
-		case PORT_B:
-			temp |= TRANS_DP_PORT_SEL_B;
-			break;
-		case PORT_C:
-			temp |= TRANS_DP_PORT_SEL_C;
-			break;
-		case PORT_D:
-			temp |= TRANS_DP_PORT_SEL_D;
-			break;
-		default:
-			BUG();
-		}
+		port = intel_trans_dp_port_sel(crtc);
+		WARN_ON(port < PORT_B || port > PORT_D);
+		temp |= TRANS_DP_PORT_SEL(port);
 
 		I915_WRITE(reg, temp);
 	}
-- 
cgit v1.2.3


From 5a0b385e1cb6a8289e01367710035e18d72794cd Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:29:27 +0300
Subject: drm/i915: Nuke intel_trans_dp_port_sel()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

for_each_encoder_on_crtc() is legacy and shouldn't be used by atomic
drivers. Let's throw out intel_trans_dp_port_sel() and replace it
with intel_get_crtc_new_encoder() which looks the atomic state instead.

Since we now have to call intel_get_crtc_new_encoder() during the commit
phase we'll need to plumb in the top level atomic state. The
crtc_state->state pointers are no longer valid at that point.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518152931.13104-3-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 39 +++++++++++++-----------------------
 1 file changed, 14 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 68d48b7445e9..b60b28feb864 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4595,17 +4595,17 @@ static void ivybridge_update_fdi_bc_bifurcation(struct intel_crtc *intel_crtc)
  * used when we know that the CRTC isn't feeding multiple encoders!
  */
 static struct intel_encoder *
-intel_get_crtc_new_encoder(const struct intel_crtc_state *crtc_state)
+intel_get_crtc_new_encoder(const struct intel_atomic_state *state,
+			   const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	const struct drm_atomic_state *state = crtc_state->base.state;
 	const struct drm_connector_state *connector_state;
 	const struct drm_connector *connector;
 	struct intel_encoder *encoder = NULL;
 	int num_encoders = 0;
 	int i;
 
-	for_each_new_connector_in_state(state, connector, connector_state, i) {
+	for_each_new_connector_in_state(&state->base, connector, connector_state, i) {
 		if (connector_state->crtc != &crtc->base)
 			continue;
 
@@ -4619,22 +4619,6 @@ intel_get_crtc_new_encoder(const struct intel_crtc_state *crtc_state)
 	return encoder;
 }
 
-/* Return which DP Port should be selected for Transcoder DP control */
-static enum port
-intel_trans_dp_port_sel(struct intel_crtc *crtc)
-{
-	struct drm_device *dev = crtc->base.dev;
-	struct intel_encoder *encoder;
-
-	for_each_encoder_on_crtc(dev, &crtc->base, encoder) {
-		if (encoder->type == INTEL_OUTPUT_DP ||
-		    encoder->type == INTEL_OUTPUT_EDP)
-			return encoder->port;
-	}
-
-	return -1;
-}
-
 /*
  * Enable PCH resources required for PCH ports:
  *   - PCH PLLs
@@ -4643,7 +4627,8 @@ intel_trans_dp_port_sel(struct intel_crtc *crtc)
  *   - DP transcoding bits
  *   - transcoder
  */
-static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
+static void ironlake_pch_enable(const struct intel_atomic_state *state,
+				const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_device *dev = crtc->base.dev;
@@ -4716,7 +4701,7 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
 		if (adjusted_mode->flags & DRM_MODE_FLAG_PVSYNC)
 			temp |= TRANS_DP_VSYNC_ACTIVE_HIGH;
 
-		port = intel_trans_dp_port_sel(crtc);
+		port = intel_get_crtc_new_encoder(state, crtc_state)->port;
 		WARN_ON(port < PORT_B || port > PORT_D);
 		temp |= TRANS_DP_PORT_SEL(port);
 
@@ -4726,7 +4711,8 @@ static void ironlake_pch_enable(const struct intel_crtc_state *crtc_state)
 	ironlake_enable_pch_transcoder(dev_priv, pipe);
 }
 
-static void lpt_pch_enable(const struct intel_crtc_state *crtc_state)
+static void lpt_pch_enable(const struct intel_atomic_state *state,
+			   const struct intel_crtc_state *crtc_state)
 {
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
@@ -5529,7 +5515,7 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	intel_enable_pipe(pipe_config);
 
 	if (intel_crtc->config->has_pch_encoder)
-		ironlake_pch_enable(pipe_config);
+		ironlake_pch_enable(old_intel_state, pipe_config);
 
 	assert_vblank_disabled(crtc);
 	drm_crtc_vblank_on(crtc);
@@ -5668,7 +5654,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 		intel_enable_pipe(pipe_config);
 
 	if (intel_crtc->config->has_pch_encoder)
-		lpt_pch_enable(pipe_config);
+		lpt_pch_enable(old_intel_state, pipe_config);
 
 	if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_DP_MST))
 		intel_ddi_set_vc_payload_alloc(pipe_config, true);
@@ -9122,9 +9108,12 @@ void hsw_disable_pc8(struct drm_i915_private *dev_priv)
 static int haswell_crtc_compute_clock(struct intel_crtc *crtc,
 				      struct intel_crtc_state *crtc_state)
 {
+	struct intel_atomic_state *state =
+		to_intel_atomic_state(crtc_state->base.state);
+
 	if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DSI)) {
 		struct intel_encoder *encoder =
-			intel_get_crtc_new_encoder(crtc_state);
+			intel_get_crtc_new_encoder(state, crtc_state);
 
 		if (!intel_get_shared_dpll(crtc, crtc_state, encoder)) {
 			DRM_DEBUG_DRIVER("failed to find PLL for pipe %c\n",
-- 
cgit v1.2.3


From 59b74c497ae4e9d703307bc9b7b20566588d1ccf Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:29:28 +0300
Subject: drm/i915: Clean up DP pipe select bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clean up the DP pipe select bits. To make the whole situation a bit
less ugly we'll start to share the same code between .get_hw_state(),
the port state asserts, and the VLV power sequencer code.

v2: Return PIPE_A for cpt/ppt when the port isn't selected by
    any transcoder. Returning INVALID_PIPE explodes *somewhere*
    on some machines (can't immediately see where though). This
    now matches the old behaviour.
v3: Order the defines shift,mask,value (Jani)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518152931.13104-4-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h      |  24 +++-----
 drivers/gpu/drm/i915/intel_display.c |  46 +++++---------
 drivers/gpu/drm/i915/intel_dp.c      | 113 ++++++++++++++++++++---------------
 drivers/gpu/drm/i915/intel_drv.h     |   3 +
 4 files changed, 91 insertions(+), 95 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5a103496423c..b888da96caf7 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5182,10 +5182,15 @@ enum {
 #define CHV_DP_D		_MMIO(VLV_DISPLAY_BASE + 0x64300)
 
 #define   DP_PORT_EN			(1 << 31)
-#define   DP_PIPEB_SELECT		(1 << 30)
-#define   DP_PIPE_MASK			(1 << 30)
-#define   DP_PIPE_SELECT_CHV(pipe)	((pipe) << 16)
-#define   DP_PIPE_MASK_CHV		(3 << 16)
+#define   DP_PIPE_SEL_SHIFT		30
+#define   DP_PIPE_SEL_MASK		(1 << 30)
+#define   DP_PIPE_SEL(pipe)		((pipe) << 30)
+#define   DP_PIPE_SEL_SHIFT_IVB		29
+#define   DP_PIPE_SEL_MASK_IVB		(3 << 29)
+#define   DP_PIPE_SEL_IVB(pipe)		((pipe) << 29)
+#define   DP_PIPE_SEL_SHIFT_CHV		16
+#define   DP_PIPE_SEL_MASK_CHV		(3 << 16)
+#define   DP_PIPE_SEL_CHV(pipe)		((pipe) << 16)
 
 /* Link training mode - select a suitable mode for each stage */
 #define   DP_LINK_TRAIN_PAT_1		(0 << 28)
@@ -7872,16 +7877,6 @@ enum {
 #define PCH_DP_AUX_CH_DATA(aux_ch, i)	_MMIO(_PORT((aux_ch) - AUX_CH_B, _PCH_DPB_AUX_CH_DATA1, _PCH_DPC_AUX_CH_DATA1) + (i) * 4) /* 5 registers */
 
 /* CPT */
-#define  PORT_TRANS_A_SEL_CPT	0
-#define  PORT_TRANS_B_SEL_CPT	(1<<29)
-#define  PORT_TRANS_C_SEL_CPT	(2<<29)
-#define  PORT_TRANS_SEL_MASK	(3<<29)
-#define  PORT_TRANS_SEL_CPT(pipe)	((pipe) << 29)
-#define  PORT_TO_PIPE(val)	(((val) & (1<<30)) >> 30)
-#define  PORT_TO_PIPE_CPT(val)	(((val) & PORT_TRANS_SEL_MASK) >> 29)
-#define  SDVO_PORT_TO_PIPE_CHV(val)	(((val) & (3<<24)) >> 24)
-#define  DP_PORT_TO_PIPE_CHV(val)	(((val) & (3<<16)) >> 16)
-
 #define _TRANS_DP_CTL_A		0xe0300
 #define _TRANS_DP_CTL_B		0xe1300
 #define _TRANS_DP_CTL_C		0xe2300
@@ -7890,7 +7885,6 @@ enum {
 #define  TRANS_DP_PORT_SEL_MASK		(3 << 29)
 #define  TRANS_DP_PORT_SEL_NONE		(3 << 29)
 #define  TRANS_DP_PORT_SEL(port)	(((port) - PORT_B) << 29)
-#define  TRANS_DP_PIPE_TO_PORT(val)	((((val) & TRANS_DP_PORT_SEL_MASK) >> 29) + PORT_B)
 #define  TRANS_DP_AUDIO_ONLY	(1<<26)
 #define  TRANS_DP_ENH_FRAMING	(1<<18)
 #define  TRANS_DP_8BPC		(0<<9)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b60b28feb864..7126ddf224f6 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1303,38 +1303,22 @@ void assert_pch_transcoder_disabled(struct drm_i915_private *dev_priv,
 	     pipe_name(pipe));
 }
 
-static bool dp_pipe_enabled(struct drm_i915_private *dev_priv,
-			    enum pipe pipe, u32 port_sel, u32 val)
+static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
+				   enum pipe pipe, enum port port,
+				   i915_reg_t dp_reg)
 {
-	if ((val & DP_PORT_EN) == 0)
-		return false;
+	enum pipe port_pipe;
+	bool state;
 
-	if (HAS_PCH_CPT(dev_priv)) {
-		u32 trans_dp_ctl = I915_READ(TRANS_DP_CTL(pipe));
-		if ((trans_dp_ctl & TRANS_DP_PORT_SEL_MASK) != port_sel)
-			return false;
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		if ((val & DP_PIPE_MASK_CHV) != DP_PIPE_SELECT_CHV(pipe))
-			return false;
-	} else {
-		if ((val & DP_PIPE_MASK) != (pipe << 30))
-			return false;
-	}
-	return true;
-}
+	state = intel_dp_port_enabled(dev_priv, dp_reg, port, &port_pipe);
 
-static void assert_pch_dp_disabled(struct drm_i915_private *dev_priv,
-				   enum pipe pipe, i915_reg_t reg,
-				   u32 port_sel)
-{
-	u32 val = I915_READ(reg);
-	I915_STATE_WARN(dp_pipe_enabled(dev_priv, pipe, port_sel, val),
-	     "PCH DP (0x%08x) enabled on transcoder %c, should be disabled\n",
-	     i915_mmio_reg_offset(reg), pipe_name(pipe));
+	I915_STATE_WARN(state && port_pipe == pipe,
+			"PCH DP %c enabled on transcoder %c, should be disabled\n",
+			port_name(port), pipe_name(pipe));
 
-	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && (val & DP_PORT_EN) == 0
-	     && (val & DP_PIPEB_SELECT),
-	     "IBX PCH dp port still using transcoder B\n");
+	I915_STATE_WARN(HAS_PCH_IBX(dev_priv) && !state && port_pipe == PIPE_B,
+			"IBX PCH DP %c still using transcoder B\n",
+			port_name(port));
 }
 
 static void assert_pch_hdmi_disabled(struct drm_i915_private *dev_priv,
@@ -1360,9 +1344,9 @@ static void assert_pch_ports_disabled(struct drm_i915_private *dev_priv,
 {
 	enum pipe port_pipe;
 
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_B, TRANS_DP_PORT_SEL(PORT_B));
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_C, TRANS_DP_PORT_SEL(PORT_C));
-	assert_pch_dp_disabled(dev_priv, pipe, PCH_DP_D, TRANS_DP_PORT_SEL(PORT_D));
+	assert_pch_dp_disabled(dev_priv, pipe, PORT_B, PCH_DP_B);
+	assert_pch_dp_disabled(dev_priv, pipe, PORT_C, PCH_DP_C);
+	assert_pch_dp_disabled(dev_priv, pipe, PORT_D, PCH_DP_D);
 
 	I915_STATE_WARN(intel_crt_port_enabled(dev_priv, PCH_ADPA, &port_pipe) &&
 			port_pipe == pipe,
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index be99e56cf7d9..b7d3cf27d5e2 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -529,9 +529,9 @@ vlv_power_sequencer_kick(struct intel_dp *intel_dp)
 	DP |= DP_LINK_TRAIN_PAT_1;
 
 	if (IS_CHERRYVIEW(dev_priv))
-		DP |= DP_PIPE_SELECT_CHV(pipe);
-	else if (pipe == PIPE_B)
-		DP |= DP_PIPEB_SELECT;
+		DP |= DP_PIPE_SEL_CHV(pipe);
+	else
+		DP |= DP_PIPE_SEL(pipe);
 
 	pll_enabled = I915_READ(DPLL(pipe)) & DPLL_VCO_ENABLE;
 
@@ -1974,7 +1974,7 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 		if (drm_dp_enhanced_frame_cap(intel_dp->dpcd))
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
-		intel_dp->DP |= crtc->pipe << 29;
+		intel_dp->DP |= DP_PIPE_SEL_IVB(crtc->pipe);
 	} else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) {
 		u32 trans_dp;
 
@@ -2000,9 +2000,9 @@ static void intel_dp_prepare(struct intel_encoder *encoder,
 			intel_dp->DP |= DP_ENHANCED_FRAMING;
 
 		if (IS_CHERRYVIEW(dev_priv))
-			intel_dp->DP |= DP_PIPE_SELECT_CHV(crtc->pipe);
-		else if (crtc->pipe == PIPE_B)
-			intel_dp->DP |= DP_PIPEB_SELECT;
+			intel_dp->DP |= DP_PIPE_SEL_CHV(crtc->pipe);
+		else
+			intel_dp->DP |= DP_PIPE_SEL(crtc->pipe);
 	}
 }
 
@@ -2624,52 +2624,66 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode)
 			      mode == DRM_MODE_DPMS_ON ? "enable" : "disable");
 }
 
+static bool cpt_dp_port_selected(struct drm_i915_private *dev_priv,
+				 enum port port, enum pipe *pipe)
+{
+	enum pipe p;
+
+	for_each_pipe(dev_priv, p) {
+		u32 val = I915_READ(TRANS_DP_CTL(p));
+
+		if ((val & TRANS_DP_PORT_SEL_MASK) == TRANS_DP_PORT_SEL(port)) {
+			*pipe = p;
+			return true;
+		}
+	}
+
+	DRM_DEBUG_KMS("No pipe for DP port %c found\n", port_name(port));
+
+	/* must initialize pipe to something for the asserts */
+	*pipe = PIPE_A;
+
+	return false;
+}
+
+bool intel_dp_port_enabled(struct drm_i915_private *dev_priv,
+			   i915_reg_t dp_reg, enum port port,
+			   enum pipe *pipe)
+{
+	bool ret;
+	u32 val;
+
+	val = I915_READ(dp_reg);
+
+	ret = val & DP_PORT_EN;
+
+	/* asserts want to know the pipe even if the port is disabled */
+	if (IS_IVYBRIDGE(dev_priv) && port == PORT_A)
+		*pipe = (val & DP_PIPE_SEL_MASK_IVB) >> DP_PIPE_SEL_SHIFT_IVB;
+	else if (HAS_PCH_CPT(dev_priv) && port != PORT_A)
+		ret &= cpt_dp_port_selected(dev_priv, port, pipe);
+	else if (IS_CHERRYVIEW(dev_priv))
+		*pipe = (val & DP_PIPE_SEL_MASK_CHV) >> DP_PIPE_SEL_SHIFT_CHV;
+	else
+		*pipe = (val & DP_PIPE_SEL_MASK) >> DP_PIPE_SEL_SHIFT;
+
+	return ret;
+}
+
 static bool intel_dp_get_hw_state(struct intel_encoder *encoder,
 				  enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-	enum port port = encoder->port;
-	u32 tmp;
 	bool ret;
 
 	if (!intel_display_power_get_if_enabled(dev_priv,
 						encoder->power_domain))
 		return false;
 
-	ret = false;
+	ret = intel_dp_port_enabled(dev_priv, intel_dp->output_reg,
+				    encoder->port, pipe);
 
-	tmp = I915_READ(intel_dp->output_reg);
-
-	if (!(tmp & DP_PORT_EN))
-		goto out;
-
-	if (IS_IVYBRIDGE(dev_priv) && port == PORT_A) {
-		*pipe = PORT_TO_PIPE_CPT(tmp);
-	} else if (HAS_PCH_CPT(dev_priv) && port != PORT_A) {
-		enum pipe p;
-
-		for_each_pipe(dev_priv, p) {
-			u32 trans_dp = I915_READ(TRANS_DP_CTL(p));
-			if (TRANS_DP_PIPE_TO_PORT(trans_dp) == port) {
-				*pipe = p;
-				ret = true;
-
-				goto out;
-			}
-		}
-
-		DRM_DEBUG_KMS("No pipe for dp port 0x%x found\n",
-			      i915_mmio_reg_offset(intel_dp->output_reg));
-	} else if (IS_CHERRYVIEW(dev_priv)) {
-		*pipe = DP_PORT_TO_PIPE_CHV(tmp);
-	} else {
-		*pipe = PORT_TO_PIPE(tmp);
-	}
-
-	ret = true;
-
-out:
 	intel_display_power_put(dev_priv, encoder->power_domain);
 
 	return ret;
@@ -3659,8 +3673,9 @@ intel_dp_link_down(struct intel_encoder *encoder,
 		intel_set_pch_fifo_underrun_reporting(dev_priv, PIPE_A, false);
 
 		/* always enable with pattern 1 (as per spec) */
-		DP &= ~(DP_PIPEB_SELECT | DP_LINK_TRAIN_MASK);
-		DP |= DP_PORT_EN | DP_LINK_TRAIN_PAT_1;
+		DP &= ~(DP_PIPE_SEL_MASK | DP_LINK_TRAIN_MASK);
+		DP |= DP_PORT_EN | DP_PIPE_SEL(PIPE_A) |
+			DP_LINK_TRAIN_PAT_1;
 		I915_WRITE(intel_dp->output_reg, DP);
 		POSTING_READ(intel_dp->output_reg);
 
@@ -5295,14 +5310,14 @@ static void intel_edp_panel_vdd_sanitize(struct intel_dp *intel_dp)
 static enum pipe vlv_active_pipe(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
+	struct intel_encoder *encoder = &dp_to_dig_port(intel_dp)->base;
+	enum pipe pipe;
 
-	if ((intel_dp->DP & DP_PORT_EN) == 0)
-		return INVALID_PIPE;
+	if (intel_dp_port_enabled(dev_priv, intel_dp->output_reg,
+				  encoder->port, &pipe))
+		return pipe;
 
-	if (IS_CHERRYVIEW(dev_priv))
-		return DP_PORT_TO_PIPE_CHV(intel_dp->DP);
-	else
-		return PORT_TO_PIPE(intel_dp->DP);
+	return INVALID_PIPE;
 }
 
 void intel_dp_encoder_reset(struct drm_encoder *encoder)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index e919e0099ad6..2855363f5b6c 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1645,6 +1645,9 @@ void intel_csr_ucode_suspend(struct drm_i915_private *);
 void intel_csr_ucode_resume(struct drm_i915_private *);
 
 /* intel_dp.c */
+bool intel_dp_port_enabled(struct drm_i915_private *dev_priv,
+			   i915_reg_t dp_reg, enum port port,
+			   enum pipe *pipe);
 bool intel_dp_init(struct drm_i915_private *dev_priv, i915_reg_t output_reg,
 		   enum port port);
 bool intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
-- 
cgit v1.2.3


From 05bf51d3b5750f3b47c241e094b9c2230a9c1a93 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:29:29 +0300
Subject: drm/i915: Allow eDP on port C in theory
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The power sequencer has bits to allow DP C to be used for eDP.
Currently we assume this will never happen, but I guess it could
theoretically be a thing. Make the code do the right thing in that
case, and toss in a MISSING_CASE() for any other port.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518152931.13104-5-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_dp.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index b7d3cf27d5e2..ce07bd794aed 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -5712,10 +5712,20 @@ intel_dp_init_panel_power_sequencer_registers(struct intel_dp *intel_dp,
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		port_sel = PANEL_PORT_SELECT_VLV(port);
 	} else if (HAS_PCH_IBX(dev_priv) || HAS_PCH_CPT(dev_priv)) {
-		if (port == PORT_A)
+		switch (port) {
+		case PORT_A:
 			port_sel = PANEL_PORT_SELECT_DPA;
-		else
+			break;
+		case PORT_C:
+			port_sel = PANEL_PORT_SELECT_DPC;
+			break;
+		case PORT_D:
 			port_sel = PANEL_PORT_SELECT_DPD;
+			break;
+		default:
+			MISSING_CASE(port);
+			break;
+		}
 	}
 
 	pp_on |= port_sel;
-- 
cgit v1.2.3


From 4c23dea48b0d8d9da2ac0911f8cee105f4394281 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:29:30 +0300
Subject: drm/i915: Implement the missing bits of assert_panel_unlocked()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the missing eDP port handling into assert_panel_unlocked(). We now
have intel_dp_port_enabled() which makes this trivial.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518152931.13104-6-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 7126ddf224f6..3a0709a6e4a0 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1214,9 +1214,23 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 		pp_reg = PP_CONTROL(0);
 		port_sel = I915_READ(PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK;
 
-		if (port_sel == PANEL_PORT_SELECT_LVDS)
+		switch (port_sel) {
+		case PANEL_PORT_SELECT_LVDS:
 			intel_lvds_port_enabled(dev_priv, PCH_LVDS, &panel_pipe);
-		/* XXX: else fix for eDP */
+			break;
+		case PANEL_PORT_SELECT_DPA:
+			intel_dp_port_enabled(dev_priv, DP_A, PORT_A, &panel_pipe);
+			break;
+		case PANEL_PORT_SELECT_DPC:
+			intel_dp_port_enabled(dev_priv, PCH_DP_C, PORT_C, &panel_pipe);
+			break;
+		case PANEL_PORT_SELECT_DPD:
+			intel_dp_port_enabled(dev_priv, PCH_DP_D, PORT_D, &panel_pipe);
+			break;
+		default:
+			MISSING_CASE(port_sel);
+			break;
+		}
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		/* presumably write lock depends on pipe, not port select */
 		pp_reg = PP_CONTROL(pipe);
-- 
cgit v1.2.3


From f0d2b758e05e209f4572182afade180cda22c9c8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:29:31 +0300
Subject: drm/i915: WARN if power sequencer is not connected to the LVDS port
 on pre-ilk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We don't support using the power sequencer with other ports besides LVDS
on pre-ilk platforms. WARN if someone has mistakenly connected the power
sequencer to the wrong port.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518152931.13104-7-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3a0709a6e4a0..aab1c6c58edf 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1236,7 +1236,12 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 		pp_reg = PP_CONTROL(pipe);
 		panel_pipe = pipe;
 	} else {
+		u32 port_sel;
+
 		pp_reg = PP_CONTROL(0);
+		port_sel = I915_READ(PP_ON_DELAYS(0)) & PANEL_PORT_SELECT_MASK;
+
+		WARN_ON(port_sel != PANEL_PORT_SELECT_LVDS);
 		intel_lvds_port_enabled(dev_priv, LVDS, &panel_pipe);
 	}
 
-- 
cgit v1.2.3


From 4a774ee35c9f57feaf332b252ecb2d4275521c8a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 23 May 2018 15:23:46 +0100
Subject: drm/i915/selftests: Pin the mock kernel context

The driver assumes that the kernel context is pinned and always
available for use from any process or atomic context. Make it so for
selftesting as well!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180523142346.27953-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/mock_engine.c     |  7 +++++++
 drivers/gpu/drm/i915/selftests/mock_gem_device.c | 17 +++++++----------
 2 files changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index f1ac7453053e..c2a0451336cf 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -212,8 +212,13 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	if (!engine->base.buffer)
 		goto err_breadcrumbs;
 
+	if (IS_ERR(intel_context_pin(i915->kernel_context, &engine->base)))
+		goto err_ring;
+
 	return &engine->base;
 
+err_ring:
+	mock_ring_free(engine->base.buffer);
 err_breadcrumbs:
 	intel_engine_fini_breadcrumbs(&engine->base);
 	i915_timeline_fini(&engine->base.timeline);
@@ -254,6 +259,8 @@ void mock_engine_free(struct intel_engine_cs *engine)
 	if (ce)
 		intel_context_unpin(ce);
 
+	__intel_context_unpin(engine->i915->kernel_context, engine);
+
 	mock_ring_free(engine->buffer);
 
 	intel_engine_fini_breadcrumbs(engine);
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index 94baedfa0f74..c97075c5ccaf 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -136,8 +136,6 @@ static struct dev_pm_domain pm_domain = {
 struct drm_i915_private *mock_gem_device(void)
 {
 	struct drm_i915_private *i915;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
 	struct pci_dev *pdev;
 	int err;
 
@@ -233,13 +231,13 @@ struct drm_i915_private *mock_gem_device(void)
 	mock_init_ggtt(i915);
 
 	mkwrite_device_info(i915)->ring_mask = BIT(0);
-	i915->engine[RCS] = mock_engine(i915, "mock", RCS);
-	if (!i915->engine[RCS])
-		goto err_unlock;
-
 	i915->kernel_context = mock_context(i915, NULL);
 	if (!i915->kernel_context)
-		goto err_engine;
+		goto err_unlock;
+
+	i915->engine[RCS] = mock_engine(i915, "mock", RCS);
+	if (!i915->engine[RCS])
+		goto err_context;
 
 	mutex_unlock(&i915->drm.struct_mutex);
 
@@ -247,9 +245,8 @@ struct drm_i915_private *mock_gem_device(void)
 
 	return i915;
 
-err_engine:
-	for_each_engine(engine, i915, id)
-		mock_engine_free(engine);
+err_context:
+	i915_gem_contexts_fini(i915);
 err_unlock:
 	mutex_unlock(&i915->drm.struct_mutex);
 	kmem_cache_destroy(i915->priorities);
-- 
cgit v1.2.3


From c894d63c6b36de20f0248d88801be5ace8e6bee8 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Fri, 18 May 2018 13:15:47 -0700
Subject: drm/i915/icl: Disable pipe CSC and gamma in cursor plane
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'Pipe CSC enable' bit is more than just deprecated in ICL+, it was
disabled in commit 077ef1f09c25 ("drm/i915/icl: Don't set pipe
CSC/Gamma in PLANE_COLOR_CTL") for primary and sprite planes as it was
causing those planes to be rendered as always black but it was not
disabled in cursor plane, also causing it to be rendered as black.

As mentioned in the commit referenced above, this is a workaround
too and the CSC and gamma per plane values needs to be setup before
enable CSC and gamma again.

BSpec: 4278 and 7635

Cc: James Ausmus <james.ausmus@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518201547.15793-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/intel_display.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index aab1c6c58edf..8b385176ce3c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9687,12 +9687,14 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 	struct drm_i915_private *dev_priv =
 		to_i915(plane_state->base.plane->dev);
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	u32 cntl;
+	u32 cntl = 0;
 
-	cntl = MCURSOR_GAMMA_ENABLE;
+	if (INTEL_GEN(dev_priv) <= 10) {
+		cntl |= MCURSOR_GAMMA_ENABLE;
 
-	if (HAS_DDI(dev_priv))
-		cntl |= CURSOR_PIPE_CSC_ENABLE;
+		if (HAS_DDI(dev_priv))
+			cntl |= CURSOR_PIPE_CSC_ENABLE;
+	}
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv))
 		cntl |= MCURSOR_PIPE_SELECT(crtc->pipe);
-- 
cgit v1.2.3


From 1e40d4aea57bbbd277777dd1fe18599dd77c55ab Mon Sep 17 00:00:00 2001
From: Yunwei Zhang <yunwei.zhang@intel.com>
Date: Fri, 18 May 2018 15:39:57 -0700
Subject: drm/i915/cnl: Implement WaProgramMgsrForCorrectSliceSpecificMmioReads

WaProgramMgsrForCorrectSliceSpecificMmioReads dictate that before any MMIO
read into Slice/Subslice specific registers, MCR packet control
register(0xFDC) needs to be programmed to point to any enabled
slice/subslice pair. Otherwise, incorrect value will be returned.

However, that means each subsequent MMIO read will be forwarded to a
specific slice/subslice combination as read is unicast. This is OK since
slice/subslice specific register values are consistent in almost all cases
across slice/subslice. There are rare occasions such as INSTDONE that this
value will be dependent on slice/subslice combo, in such cases, we need to
program 0xFDC and recover this after. This is already covered by
read_subslice_reg.

Also, 0xFDC will lose its information after TDR/engine reset/power state
change.

References: HSD#1405586840, BSID#0575

v2:
 - use fls() instead of find_last_bit() (Chris)
 - added INTEL_SSEU to extract sseu from device info. (Chris)
v3:
 - rebase on latest tip
v5:
 - Added references (Mika)
 - Change the ordered of passing arguments and etc. (Ursulin)
v7:
 - Moved WA explanation Comments(Oscar)
 - Rebased.
v8:
 - Renamed sanitize_mcr to calculate_s_ss_select. (Oscar)
 - calculate s/ss selector instead of whole mcr. (Oscar)
v9:
 - Updated function name (Oscar)
 - Remove redundant variables (Oscar)
v10:
 - Separate pre-GEN10 and GEN11 mask. (Oscar)

Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Yunwei Zhang <yunwei.zhang@intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1526683197-24656-1-git-send-email-yunwei.zhang@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h          |  2 ++
 drivers/gpu/drm/i915/intel_engine_cs.c   | 30 +++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/intel_workarounds.c | 27 +++++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b86ed6401120..1b8bd84f0799 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2743,6 +2743,8 @@ int vlv_force_gfx_clock(struct drm_i915_private *dev_priv, bool on);
 int intel_engines_init_mmio(struct drm_i915_private *dev_priv);
 int intel_engines_init(struct drm_i915_private *dev_priv);
 
+u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv);
+
 /* intel_hotplug.c */
 void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 0c1f084ee593..ad28680390b8 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -819,12 +819,29 @@ const char *i915_cache_level_str(struct drm_i915_private *i915, int type)
 	}
 }
 
+u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
+{
+	const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu);
+	u32 mcr_s_ss_select;
+	u32 slice = fls(sseu->slice_mask);
+	u32 subslice = fls(sseu->subslice_mask[slice]);
+
+	if (INTEL_GEN(dev_priv) == 10)
+		mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
+				  GEN8_MCR_SUBSLICE(subslice);
+	else
+		mcr_s_ss_select = 0;
+
+	return mcr_s_ss_select;
+}
+
 static inline uint32_t
 read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 		  int subslice, i915_reg_t reg)
 {
 	uint32_t mcr_slice_subslice_mask;
 	uint32_t mcr_slice_subslice_select;
+	uint32_t default_mcr_s_ss_select;
 	uint32_t mcr;
 	uint32_t ret;
 	enum forcewake_domains fw_domains;
@@ -841,6 +858,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 					    GEN8_MCR_SUBSLICE(subslice);
 	}
 
+	default_mcr_s_ss_select = intel_calculate_mcr_s_ss_select(dev_priv);
+
 	fw_domains = intel_uncore_forcewake_for_reg(dev_priv, reg,
 						    FW_REG_READ);
 	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
@@ -851,11 +870,10 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 	intel_uncore_forcewake_get__locked(dev_priv, fw_domains);
 
 	mcr = I915_READ_FW(GEN8_MCR_SELECTOR);
-	/*
-	 * The HW expects the slice and sublice selectors to be reset to 0
-	 * after reading out the registers.
-	 */
-	WARN_ON_ONCE(mcr & mcr_slice_subslice_mask);
+
+	WARN_ON_ONCE((mcr & mcr_slice_subslice_mask) !=
+		     default_mcr_s_ss_select);
+
 	mcr &= ~mcr_slice_subslice_mask;
 	mcr |= mcr_slice_subslice_select;
 	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
@@ -863,6 +881,8 @@ read_subslice_reg(struct drm_i915_private *dev_priv, int slice,
 	ret = I915_READ_FW(reg);
 
 	mcr &= ~mcr_slice_subslice_mask;
+	mcr |= default_mcr_s_ss_select;
+
 	I915_WRITE_FW(GEN8_MCR_SELECTOR, mcr);
 
 	intel_uncore_forcewake_put__locked(dev_priv, fw_domains);
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 2df3538ceba5..720d8635c2cf 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -672,8 +672,35 @@ static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
 }
 
+static void wa_init_mcr(struct drm_i915_private *dev_priv)
+{
+	u32 mcr;
+	u32 mcr_slice_subslice_mask;
+
+	mcr = I915_READ(GEN8_MCR_SELECTOR);
+
+	mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
+				  GEN8_MCR_SUBSLICE_MASK;
+	/*
+	 * WaProgramMgsrForCorrectSliceSpecificMmioReads:cnl
+	 * Before any MMIO read into slice/subslice specific registers, MCR
+	 * packet control register needs to be programmed to point to any
+	 * enabled s/ss pair. Otherwise, incorrect values will be returned.
+	 * This means each subsequent MMIO read will be forwarded to an
+	 * specific s/ss combination, but this is OK since these registers
+	 * are consistent across s/ss in almost all cases. In the rare
+	 * occasions, such as INSTDONE, where this value is dependent
+	 * on s/ss combo, the read should be done with read_subslice_reg.
+	 */
+	mcr &= ~mcr_slice_subslice_mask;
+	mcr |= intel_calculate_mcr_s_ss_select(dev_priv);
+	I915_WRITE(GEN8_MCR_SELECTOR, mcr);
+}
+
 static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 {
+	wa_init_mcr(dev_priv);
+
 	/* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */
 	if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0))
 		I915_WRITE(GAMT_CHKN_BIT_REG,
-- 
cgit v1.2.3


From d78fa508f08d7d91d8ce9e2cec1f04bd2d63f0a1 Mon Sep 17 00:00:00 2001
From: Yunwei Zhang <yunwei.zhang@intel.com>
Date: Fri, 18 May 2018 15:40:32 -0700
Subject: drm/i915/icl: Enable WaProgramMgsrForCorrectSliceSpecificMmioReads

WaProgramMgsrForCorrectSliceSpecificMmioReads applies for Icelake as
well.

References: HSD#1405586840, BSID#0575

v2:
 - GEN11 mask is different from its predecessors. (Oscar)
 - Better separate GEN10 and GEN11. (Oscar)

Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Yunwei Zhang <yunwei.zhang@intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1526683232-24753-1-git-send-email-yunwei.zhang@intel.com
---
 drivers/gpu/drm/i915/intel_engine_cs.c   |  3 +++
 drivers/gpu/drm/i915/intel_workarounds.c | 12 +++++++++---
 2 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index ad28680390b8..13448ea76f57 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -829,6 +829,9 @@ u32 intel_calculate_mcr_s_ss_select(struct drm_i915_private *dev_priv)
 	if (INTEL_GEN(dev_priv) == 10)
 		mcr_s_ss_select = GEN8_MCR_SLICE(slice) |
 				  GEN8_MCR_SUBSLICE(subslice);
+	else if (INTEL_GEN(dev_priv) >= 11)
+		mcr_s_ss_select = GEN11_MCR_SLICE(slice) |
+				  GEN11_MCR_SUBSLICE(subslice);
 	else
 		mcr_s_ss_select = 0;
 
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 720d8635c2cf..2deec58e97dd 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -679,10 +679,14 @@ static void wa_init_mcr(struct drm_i915_private *dev_priv)
 
 	mcr = I915_READ(GEN8_MCR_SELECTOR);
 
-	mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
-				  GEN8_MCR_SUBSLICE_MASK;
+	if (INTEL_GEN(dev_priv) >= 11)
+		mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK |
+					  GEN11_MCR_SUBSLICE_MASK;
+	else
+		mcr_slice_subslice_mask = GEN8_MCR_SLICE_MASK |
+					  GEN8_MCR_SUBSLICE_MASK;
 	/*
-	 * WaProgramMgsrForCorrectSliceSpecificMmioReads:cnl
+	 * WaProgramMgsrForCorrectSliceSpecificMmioReads:cnl,icl
 	 * Before any MMIO read into slice/subslice specific registers, MCR
 	 * packet control register needs to be programmed to point to any
 	 * enabled s/ss pair. Otherwise, incorrect values will be returned.
@@ -719,6 +723,8 @@ static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 
 static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 {
+	wa_init_mcr(dev_priv);
+
 	/* This is not an Wa. Enable for better image quality */
 	I915_WRITE(_3D_CHICKEN3,
 		   _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE));
-- 
cgit v1.2.3


From fe864b76c2ab9503b4ff90d5d8785716a0b8d815 Mon Sep 17 00:00:00 2001
From: Yunwei Zhang <yunwei.zhang@intel.com>
Date: Fri, 18 May 2018 15:41:25 -0700
Subject: drm/i915: Implement WaProgramMgsrForL3BankSpecificMmioReads

L3Bank could be fused off in hardware for debug purpose, and it
is possible that subslice is enabled while its corresponding L3Bank pairs
are disabled. In such case, if MCR packet control register(0xFDC) is
programed to point to a disabled bank pair, a MMIO read into L3Bank range
will return 0 instead of correct values.

However, this is not going to be the case in any production silicon.
Therefore, we only check at initialization and issue a warning should
this really happen.

References: HSDES#1405586840

v2:
 - use fls instead of find_last_bit (Chris)
 - use is_power_of_2() instead of counting bit set (Chris)
v3:
 - rebase on latest tip
v5:
 - Added references (Mika)
 - Move local variable into scope where they are used (Ursulin)
 - use a new local variable to reduce long line of code (Ursulin)
v6:
 - Some coding style and use more local variables for clearer
   logic (Ursulin)

Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Signed-off-by: Yunwei Zhang <yunwei.zhang@intel.com>
Reviewed-by: Oscar Mateo <oscar.mateo@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1526683285-24861-1-git-send-email-yunwei.zhang@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h          |  4 ++++
 drivers/gpu/drm/i915/intel_workarounds.c | 35 ++++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b888da96caf7..d52a11c2c73c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2709,6 +2709,10 @@ enum i915_power_well_id {
 #define   GEN10_F2_SS_DIS_SHIFT		18
 #define   GEN10_F2_SS_DIS_MASK		(0xf << GEN10_F2_SS_DIS_SHIFT)
 
+#define	GEN10_MIRROR_FUSE3		_MMIO(0x9118)
+#define GEN10_L3BANK_PAIR_COUNT     4
+#define GEN10_L3BANK_MASK   0x0F
+
 #define GEN8_EU_DISABLE0		_MMIO(0x9134)
 #define   GEN8_EU_DIS0_S0_MASK		0xffffff
 #define   GEN8_EU_DIS0_S1_SHIFT		24
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 2deec58e97dd..cea57104de13 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -674,9 +674,44 @@ static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 
 static void wa_init_mcr(struct drm_i915_private *dev_priv)
 {
+	const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu);
 	u32 mcr;
 	u32 mcr_slice_subslice_mask;
 
+	/*
+	 * WaProgramMgsrForL3BankSpecificMmioReads: cnl,icl
+	 * L3Banks could be fused off in single slice scenario. If that is
+	 * the case, we might need to program MCR select to a valid L3Bank
+	 * by default, to make sure we correctly read certain registers
+	 * later on (in the range 0xB100 - 0xB3FF).
+	 * This might be incompatible with
+	 * WaProgramMgsrForCorrectSliceSpecificMmioReads.
+	 * Fortunately, this should not happen in production hardware, so
+	 * we only assert that this is the case (instead of implementing
+	 * something more complex that requires checking the range of every
+	 * MMIO read).
+	 */
+	if (INTEL_GEN(dev_priv) >= 10 &&
+	    is_power_of_2(sseu->slice_mask)) {
+		/*
+		 * read FUSE3 for enabled L3 Bank IDs, if L3 Bank matches
+		 * enabled subslice, no need to redirect MCR packet
+		 */
+		u32 slice = fls(sseu->slice_mask);
+		u32 fuse3 = I915_READ(GEN10_MIRROR_FUSE3);
+		u8 ss_mask = sseu->subslice_mask[slice];
+
+		u8 enabled_mask = (ss_mask | ss_mask >>
+				   GEN10_L3BANK_PAIR_COUNT) & GEN10_L3BANK_MASK;
+		u8 disabled_mask = fuse3 & GEN10_L3BANK_MASK;
+
+		/*
+		 * Production silicon should have matched L3Bank and
+		 * subslice enabled
+		 */
+		WARN_ON((enabled_mask & disabled_mask) != enabled_mask);
+	}
+
 	mcr = I915_READ(GEN8_MCR_SELECTOR);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-- 
cgit v1.2.3


From 1d1a4f6dd1645fba6533c7884582006d13664748 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Mon, 16 Apr 2018 20:32:32 +0530
Subject: gpu: drm: vgem: Change return type to vm_fault_t

Use new return type vm_fault_t for fault handler.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180416150232.GA26745@jordon-HP-15-Notebook-PC
---
 drivers/gpu/drm/vgem/vgem_drv.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index 2524ff116f00..c64a85950c82 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -61,13 +61,13 @@ static void vgem_gem_free_object(struct drm_gem_object *obj)
 	kfree(vgem_obj);
 }
 
-static int vgem_gem_fault(struct vm_fault *vmf)
+static vm_fault_t vgem_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_vgem_gem_object *obj = vma->vm_private_data;
 	/* We don't use vmf->pgoff since that has the fake offset */
 	unsigned long vaddr = vmf->address;
-	int ret;
+	vm_fault_t ret = VM_FAULT_SIGBUS;
 	loff_t num_pages;
 	pgoff_t page_offset;
 	page_offset = (vaddr - vma->vm_start) >> PAGE_SHIFT;
@@ -77,7 +77,6 @@ static int vgem_gem_fault(struct vm_fault *vmf)
 	if (page_offset > num_pages)
 		return VM_FAULT_SIGBUS;
 
-	ret = -ENOENT;
 	mutex_lock(&obj->pages_lock);
 	if (obj->pages) {
 		get_page(obj->pages[page_offset]);
-- 
cgit v1.2.3


From 77312ae8f071fb389d9982ce743b72975990c4d9 Mon Sep 17 00:00:00 2001
From: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Date: Tue, 22 May 2018 14:57:23 +0530
Subject: drm/i915/psr: vbt change for psr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For psr block #9, the vbt description has moved to options [0-3] for
TP1,TP2,TP3 Wakeup time from decimal value without any change to vbt
structure. Since spec does not  mention from which VBT version this
change was added to vbt.bsf file, we cannot depend on bdb->version check
to change for all the platforms.

There is RCR inplace for GOP team to  provide the version number
to make generic change. Since Kabylake with bdb version 209 is having this
change, limiting this change to gen9_bc and version 209+ to unblock google.

Tested on skl(bdb version 203,without options) and
kabylake(bdb version 209,212) having new options.

bspec 20131

v2: (Jani and Rodrigo)
    move the 165 version check to intel_bios.c
v3: Jani
    Move the abstraction to intel_bios.
v4: Jani
    Rename tp*_wakeup_time to have "us" suffix.
    For values outside range[0-3],default to max 2500us.
    Old decimal value was wake up time in multiples of 100us.
v5: Jani and Rodrigo
    Handle option 2 in default condition.
    Print oustide range value.
    For negetive values default to 2500us.
v6: Jani
    Handle default first and then fall through for case 2.
v7: Rodrigo
    Apply this change for IS_GEN9_BC and vbt version > 209
v8: Puthik
    Add new function vbt_psr_to_us.
v9: Jani
    Change to v7 version as it's more readable.
    DK
    add comment /*fall through*/ after case2.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Puthikorn Voravootivat <puthik@chromium.org>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Maulik V Vaghela <maulik.v.vaghela@intel.com>
Signed-off-by: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1526981243-2745-1-git-send-email-vathsala.nagaraju@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h   |  4 ++--
 drivers/gpu/drm/i915/i915_reg.h   |  8 +++----
 drivers/gpu/drm/i915/intel_bios.c | 48 +++++++++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_psr.c  | 39 +++++++++++++++----------------
 4 files changed, 72 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1b8bd84f0799..a7a563ed0fd8 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1077,8 +1077,8 @@ struct intel_vbt_data {
 		bool require_aux_wakeup;
 		int idle_frames;
 		enum psr_lines_to_wait lines_to_wait;
-		int tp1_wakeup_time;
-		int tp2_tp3_wakeup_time;
+		int tp1_wakeup_time_us;
+		int tp2_tp3_wakeup_time_us;
 	} psr;
 
 	struct {
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index d52a11c2c73c..6953419881c4 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4092,10 +4092,10 @@ enum {
 #define   EDP_Y_COORDINATE_ENABLE	(1<<25) /* GLK and CNL+ */
 #define   EDP_MAX_SU_DISABLE_TIME(t)	((t)<<20)
 #define   EDP_MAX_SU_DISABLE_TIME_MASK	(0x1f<<20)
-#define   EDP_PSR2_TP2_TIME_500		(0<<8)
-#define   EDP_PSR2_TP2_TIME_100		(1<<8)
-#define   EDP_PSR2_TP2_TIME_2500	(2<<8)
-#define   EDP_PSR2_TP2_TIME_50		(3<<8)
+#define   EDP_PSR2_TP2_TIME_500us	(0<<8)
+#define   EDP_PSR2_TP2_TIME_100us	(1<<8)
+#define   EDP_PSR2_TP2_TIME_2500us	(2<<8)
+#define   EDP_PSR2_TP2_TIME_50us	(3<<8)
 #define   EDP_PSR2_TP2_TIME_MASK	(3<<8)
 #define   EDP_PSR2_FRAME_BEFORE_SU_SHIFT 4
 #define   EDP_PSR2_FRAME_BEFORE_SU_MASK	(0xf<<4)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 34c805970d7c..ea7ae8bc0ea0 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -684,8 +684,52 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 		break;
 	}
 
-	dev_priv->vbt.psr.tp1_wakeup_time = psr_table->tp1_wakeup_time;
-	dev_priv->vbt.psr.tp2_tp3_wakeup_time = psr_table->tp2_tp3_wakeup_time;
+	/*
+	 * New psr options 0=500us, 1=100us, 2=2500us, 3=0us
+	 * Old decimal value is wake up time in multiples of 100 us.
+	 */
+	if (bdb->version >= 209 && IS_GEN9_BC(dev_priv)) {
+		switch (psr_table->tp1_wakeup_time) {
+		case 0:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 500;
+			break;
+		case 1:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 100;
+			break;
+		case 3:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 0;
+			break;
+		default:
+			DRM_DEBUG_KMS("VBT tp1 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n",
+					psr_table->tp1_wakeup_time);
+			/* fallthrough */
+		case 2:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 2500;
+			break;
+		}
+
+		switch (psr_table->tp2_tp3_wakeup_time) {
+		case 0:
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 500;
+			break;
+		case 1:
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 100;
+			break;
+		case 3:
+			dev_priv->vbt.psr.tp1_wakeup_time_us = 0;
+			break;
+		default:
+			DRM_DEBUG_KMS("VBT tp2_tp3 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n",
+					psr_table->tp2_tp3_wakeup_time);
+			/* fallthrough */
+		case 2:
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 2500;
+		break;
+		}
+	} else {
+		dev_priv->vbt.psr.tp1_wakeup_time_us = psr_table->tp1_wakeup_time * 100;
+		dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = psr_table->tp2_tp3_wakeup_time * 100;
+	}
 }
 
 static void parse_dsi_backlight_ports(struct drm_i915_private *dev_priv,
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index db27f2faa1de..d64f03949d9a 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -461,23 +461,23 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp)
 	if (dev_priv->psr.link_standby)
 		val |= EDP_PSR_LINK_STANDBY;
 
-	if (dev_priv->vbt.psr.tp1_wakeup_time > 5)
-		val |= EDP_PSR_TP1_TIME_2500us;
-	else if (dev_priv->vbt.psr.tp1_wakeup_time > 1)
-		val |= EDP_PSR_TP1_TIME_500us;
-	else if (dev_priv->vbt.psr.tp1_wakeup_time > 0)
+	if (dev_priv->vbt.psr.tp1_wakeup_time_us == 0)
+		val |=  EDP_PSR_TP1_TIME_0us;
+	else if (dev_priv->vbt.psr.tp1_wakeup_time_us <= 100)
 		val |= EDP_PSR_TP1_TIME_100us;
+	else if (dev_priv->vbt.psr.tp1_wakeup_time_us <= 500)
+		val |= EDP_PSR_TP1_TIME_500us;
 	else
-		val |= EDP_PSR_TP1_TIME_0us;
+		val |= EDP_PSR_TP1_TIME_2500us;
 
-	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
-		val |= EDP_PSR_TP2_TP3_TIME_2500us;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
-		val |= EDP_PSR_TP2_TP3_TIME_500us;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
+	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us == 0)
+		val |=  EDP_PSR_TP2_TP3_TIME_0us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 100)
 		val |= EDP_PSR_TP2_TP3_TIME_100us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 500)
+		val |= EDP_PSR_TP2_TP3_TIME_500us;
 	else
-		val |= EDP_PSR_TP2_TP3_TIME_0us;
+		val |= EDP_PSR_TP2_TP3_TIME_2500us;
 
 	if (intel_dp_source_supports_hbr2(intel_dp) &&
 	    drm_dp_tps3_supported(intel_dp->dpcd))
@@ -513,14 +513,15 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 
 	val |= EDP_PSR2_FRAME_BEFORE_SU(dev_priv->psr.sink_sync_latency + 1);
 
-	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 5)
-		val |= EDP_PSR2_TP2_TIME_2500;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 1)
-		val |= EDP_PSR2_TP2_TIME_500;
-	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time > 0)
-		val |= EDP_PSR2_TP2_TIME_100;
+	if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us >= 0 &&
+	    dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 50)
+		val |= EDP_PSR2_TP2_TIME_50us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 100)
+		val |= EDP_PSR2_TP2_TIME_100us;
+	else if (dev_priv->vbt.psr.tp2_tp3_wakeup_time_us <= 500)
+		val |= EDP_PSR2_TP2_TIME_500us;
 	else
-		val |= EDP_PSR2_TP2_TIME_50;
+		val |= EDP_PSR2_TP2_TIME_2500us;
 
 	I915_WRITE(EDP_PSR2_CTL, val);
 }
-- 
cgit v1.2.3


From ce3508fd2a778e9366ab638f4e1dbe6dab874c5b Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 11 May 2018 16:00:59 -0700
Subject: drm/i915/psr: Nuke PSR support for VLV and CHV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSR hardware and hence the driver code for VLV and CHV deviates a lot from
their DDI counterparts. While the feature has been disabled for a long time
now, retaining support for these platforms is a maintenance burden. There
have been multiple refactoring commits to just keep the existing code for
these platforms in line with the rest. There are known issues that need to
be fixed to enable PSR on these platforms, and there is no PSR capable
platform in CI to ensure the code does not break again if we get around to
fixing the existing issues. On account of all these reasons, let's nuke
this code for now and bring it back if a need arises in the future.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180511230059.19387-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c      |  42 +-----
 drivers/gpu/drm/i915/i915_drv.h          |   1 -
 drivers/gpu/drm/i915/i915_pci.c          |   2 -
 drivers/gpu/drm/i915/intel_drv.h         |   2 -
 drivers/gpu/drm/i915/intel_frontbuffer.c |   2 -
 drivers/gpu/drm/i915/intel_psr.c         | 248 +++----------------------------
 6 files changed, 27 insertions(+), 270 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index e9b1b8df6ef5..a8e7761cdc7d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2643,8 +2643,6 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
 	u32 psrperf = 0;
-	u32 stat[3];
-	enum pipe pipe;
 	bool enabled = false;
 	bool sink_support;
 
@@ -2665,47 +2663,17 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	seq_printf(m, "Re-enable work scheduled: %s\n",
 		   yesno(work_busy(&dev_priv->psr.work.work)));
 
-	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_enabled)
-			enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE;
-		else
-			enabled = I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE;
-	} else {
-		for_each_pipe(dev_priv, pipe) {
-			enum transcoder cpu_transcoder =
-				intel_pipe_to_cpu_transcoder(dev_priv, pipe);
-			enum intel_display_power_domain power_domain;
-
-			power_domain = POWER_DOMAIN_TRANSCODER(cpu_transcoder);
-			if (!intel_display_power_get_if_enabled(dev_priv,
-								power_domain))
-				continue;
-
-			stat[pipe] = I915_READ(VLV_PSRSTAT(pipe)) &
-				VLV_EDP_PSR_CURR_STATE_MASK;
-			if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) ||
-			    (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE))
-				enabled = true;
-
-			intel_display_power_put(dev_priv, power_domain);
-		}
-	}
+	if (dev_priv->psr.psr2_enabled)
+		enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE;
+	else
+		enabled = I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE;
 
 	seq_printf(m, "Main link in standby mode: %s\n",
 		   yesno(dev_priv->psr.link_standby));
 
-	seq_printf(m, "HW Enabled & Active bit: %s", yesno(enabled));
-
-	if (!HAS_DDI(dev_priv))
-		for_each_pipe(dev_priv, pipe) {
-			if ((stat[pipe] == VLV_EDP_PSR_ACTIVE_NORFB_UP) ||
-			    (stat[pipe] == VLV_EDP_PSR_ACTIVE_SF_UPDATE))
-				seq_printf(m, " pipe %c", pipe_name(pipe));
-		}
-	seq_puts(m, "\n");
+	seq_printf(m, "HW Enabled & Active bit: %s\n", yesno(enabled));
 
 	/*
-	 * VLV/CHV PSR has no kind of performance counter
 	 * SKL+ Perf counter is reset to 0 everytime DC state is entered
 	 */
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a7a563ed0fd8..487922f88b76 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -607,7 +607,6 @@ struct i915_psr {
 	bool link_standby;
 	bool colorimetry_support;
 	bool alpm;
-	bool has_hw_tracking;
 	bool psr2_enabled;
 	u8 sink_sync_latency;
 	bool debug;
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 4364922e935d..97a91e6af7e3 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -340,7 +340,6 @@ static const struct intel_device_info intel_valleyview_info = {
 	GEN(7),
 	.is_lp = 1,
 	.num_pipes = 2,
-	.has_psr = 1,
 	.has_runtime_pm = 1,
 	.has_rc6 = 1,
 	.has_gmch_display = 1,
@@ -433,7 +432,6 @@ static const struct intel_device_info intel_cherryview_info = {
 	.is_lp = 1,
 	.ring_mask = RENDER_RING | BSD_RING | BLT_RING | VEBOX_RING,
 	.has_64bit_reloc = 1,
-	.has_psr = 1,
 	.has_runtime_pm = 1,
 	.has_resource_streamer = 1,
 	.has_rc6 = 1,
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 2855363f5b6c..fd6256632482 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1917,8 +1917,6 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 		     unsigned frontbuffer_bits,
 		     enum fb_op_origin origin);
 void intel_psr_init(struct drm_i915_private *dev_priv);
-void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
-				   unsigned frontbuffer_bits);
 void intel_psr_compute_config(struct intel_dp *intel_dp,
 			      struct intel_crtc_state *crtc_state);
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug);
diff --git a/drivers/gpu/drm/i915/intel_frontbuffer.c b/drivers/gpu/drm/i915/intel_frontbuffer.c
index 7fff0a0eceb4..c3379bde266f 100644
--- a/drivers/gpu/drm/i915/intel_frontbuffer.c
+++ b/drivers/gpu/drm/i915/intel_frontbuffer.c
@@ -153,8 +153,6 @@ void intel_frontbuffer_flip_prepare(struct drm_i915_private *dev_priv,
 	/* Remove stale busy bits due to the old buffer. */
 	dev_priv->fb_tracking.busy_bits &= ~frontbuffer_bits;
 	spin_unlock(&dev_priv->fb_tracking.lock);
-
-	intel_psr_single_frame_update(dev_priv, frontbuffer_bits);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index d64f03949d9a..c08e4b4c07e1 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -97,10 +97,6 @@ void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug)
 {
 	u32 debug_mask, mask;
 
-	/* No PSR interrupts on VLV/CHV */
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return;
-
 	mask = EDP_PSR_ERROR(TRANSCODER_EDP);
 	debug_mask = EDP_PSR_POST_EXIT(TRANSCODER_EDP) |
 		     EDP_PSR_PRE_ENTRY(TRANSCODER_EDP);
@@ -284,31 +280,6 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	}
 }
 
-static bool vlv_is_psr_active_on_pipe(struct drm_device *dev, int pipe)
-{
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t val;
-
-	val = I915_READ(VLV_PSRSTAT(pipe)) &
-	      VLV_EDP_PSR_CURR_STATE_MASK;
-	return (val == VLV_EDP_PSR_ACTIVE_NORFB_UP) ||
-	       (val == VLV_EDP_PSR_ACTIVE_SF_UPDATE);
-}
-
-static void vlv_psr_setup_vsc(struct intel_dp *intel_dp,
-			      const struct intel_crtc_state *crtc_state)
-{
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	uint32_t val;
-
-	/* VLV auto-generate VSC package as per EDP 1.3 spec, Table 3.10 */
-	val  = I915_READ(VLV_VSCSDP(crtc->pipe));
-	val &= ~VLV_EDP_PSR_SDP_FREQ_MASK;
-	val |= VLV_EDP_PSR_SDP_FREQ_EVFRAME;
-	I915_WRITE(VLV_VSCSDP(crtc->pipe), val);
-}
-
 static void hsw_psr_setup_vsc(struct intel_dp *intel_dp,
 			      const struct intel_crtc_state *crtc_state)
 {
@@ -341,12 +312,6 @@ static void hsw_psr_setup_vsc(struct intel_dp *intel_dp,
 					DP_SDP_VSC, &psr_vsc, sizeof(psr_vsc));
 }
 
-static void vlv_psr_enable_sink(struct intel_dp *intel_dp)
-{
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG,
-			   DP_PSR_ENABLE | DP_PSR_MAIN_LINK_ACTIVE);
-}
-
 static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
@@ -403,38 +368,6 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
 }
 
-static void vlv_psr_enable_source(struct intel_dp *intel_dp,
-				  const struct intel_crtc_state *crtc_state)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-
-	/* Transition from PSR_state 0 (disabled) to PSR_state 1 (inactive) */
-	I915_WRITE(VLV_PSRCTL(crtc->pipe),
-		   VLV_EDP_PSR_MODE_SW_TIMER |
-		   VLV_EDP_PSR_SRC_TRANSMITTER_STATE |
-		   VLV_EDP_PSR_ENABLE);
-}
-
-static void vlv_psr_activate(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_crtc *crtc = dig_port->base.base.crtc;
-	enum pipe pipe = to_intel_crtc(crtc)->pipe;
-
-	/*
-	 * Let's do the transition from PSR_state 1 (inactive) to
-	 * PSR_state 2 (transition to active - static frame transmission).
-	 * Then Hardware is responsible for the transition to
-	 * PSR_state 3 (active - no Remote Frame Buffer (RFB) update).
-	 */
-	I915_WRITE(VLV_PSRCTL(pipe), I915_READ(VLV_PSRCTL(pipe)) |
-		   VLV_EDP_PSR_ACTIVE_ENTRY);
-}
-
 static void hsw_activate_psr1(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
@@ -603,17 +536,11 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 	 * ones. Since by Display design transcoder EDP is tied to port A
 	 * we can safely escape based on the port A.
 	 */
-	if (HAS_DDI(dev_priv) && dig_port->base.port != PORT_A) {
+	if (dig_port->base.port != PORT_A) {
 		DRM_DEBUG_KMS("PSR condition failed: Port not supported\n");
 		return;
 	}
 
-	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
-	    !dev_priv->psr.link_standby) {
-		DRM_ERROR("PSR condition failed: Link off requested but not supported on this platform\n");
-		return;
-	}
-
 	if (IS_HASWELL(dev_priv) &&
 	    I915_READ(HSW_STEREO_3D_CTL(crtc_state->cpu_transcoder)) &
 		      S3D_ENABLE) {
@@ -761,7 +688,6 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 		 * enabled.
 		 * However on some platforms we face issues when first
 		 * activation follows a modeset so quickly.
-		 *     - On VLV/CHV we get bank screen on first activation
 		 *     - On HSW/BDW we get a recoverable frozen screen until
 		 *       next exit-activate sequence.
 		 */
@@ -773,36 +699,6 @@ unlock:
 	mutex_unlock(&dev_priv->psr.lock);
 }
 
-static void vlv_psr_disable(struct intel_dp *intel_dp,
-			    const struct intel_crtc_state *old_crtc_state)
-{
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = intel_dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
-	uint32_t val;
-
-	if (dev_priv->psr.active) {
-		/* Put VLV PSR back to PSR_state 0 (disabled). */
-		if (intel_wait_for_register(dev_priv,
-					    VLV_PSRSTAT(crtc->pipe),
-					    VLV_EDP_PSR_IN_TRANS,
-					    0,
-					    1))
-			WARN(1, "PSR transition took longer than expected\n");
-
-		val = I915_READ(VLV_PSRCTL(crtc->pipe));
-		val &= ~VLV_EDP_PSR_ACTIVE_ENTRY;
-		val &= ~VLV_EDP_PSR_ENABLE;
-		val &= ~VLV_EDP_PSR_MODE_MASK;
-		I915_WRITE(VLV_PSRCTL(crtc->pipe), val);
-
-		dev_priv->psr.active = false;
-	} else {
-		WARN_ON(vlv_is_psr_active_on_pipe(dev, crtc->pipe));
-	}
-}
-
 static void hsw_psr_disable(struct intel_dp *intel_dp,
 			    const struct intel_crtc_state *old_crtc_state)
 {
@@ -895,21 +791,12 @@ static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
 	if (!intel_dp)
 		return false;
 
-	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_enabled) {
-			reg = EDP_PSR2_STATUS;
-			mask = EDP_PSR2_STATUS_STATE_MASK;
-		} else {
-			reg = EDP_PSR_STATUS;
-			mask = EDP_PSR_STATUS_STATE_MASK;
-		}
+	if (dev_priv->psr.psr2_enabled) {
+		reg = EDP_PSR2_STATUS;
+		mask = EDP_PSR2_STATUS_STATE_MASK;
 	} else {
-		struct drm_crtc *crtc =
-			dp_to_dig_port(intel_dp)->base.base.crtc;
-		enum pipe pipe = to_intel_crtc(crtc)->pipe;
-
-		reg = VLV_PSRSTAT(pipe);
-		mask = VLV_EDP_PSR_IN_TRANS;
+		reg = EDP_PSR_STATUS;
+		mask = EDP_PSR_STATUS_STATE_MASK;
 	}
 
 	mutex_unlock(&dev_priv->psr.lock);
@@ -954,102 +841,23 @@ unlock:
 
 static void intel_psr_exit(struct drm_i915_private *dev_priv)
 {
-	struct intel_dp *intel_dp = dev_priv->psr.enabled;
-	struct drm_crtc *crtc = dp_to_dig_port(intel_dp)->base.base.crtc;
-	enum pipe pipe = to_intel_crtc(crtc)->pipe;
 	u32 val;
 
 	if (!dev_priv->psr.active)
 		return;
 
-	if (HAS_DDI(dev_priv)) {
-		if (dev_priv->psr.psr2_enabled) {
-			val = I915_READ(EDP_PSR2_CTL);
-			WARN_ON(!(val & EDP_PSR2_ENABLE));
-			I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE);
-		} else {
-			val = I915_READ(EDP_PSR_CTL);
-			WARN_ON(!(val & EDP_PSR_ENABLE));
-			I915_WRITE(EDP_PSR_CTL, val & ~EDP_PSR_ENABLE);
-		}
+	if (dev_priv->psr.psr2_enabled) {
+		val = I915_READ(EDP_PSR2_CTL);
+		WARN_ON(!(val & EDP_PSR2_ENABLE));
+		I915_WRITE(EDP_PSR2_CTL, val & ~EDP_PSR2_ENABLE);
 	} else {
-		val = I915_READ(VLV_PSRCTL(pipe));
-
-		/*
-		 * Here we do the transition drirectly from
-		 * PSR_state 3 (active - no Remote Frame Buffer (RFB) update) to
-		 * PSR_state 5 (exit).
-		 * PSR State 4 (active with single frame update) can be skipped.
-		 * On PSR_state 5 (exit) Hardware is responsible to transition
-		 * back to PSR_state 1 (inactive).
-		 * Now we are at Same state after vlv_psr_enable_source.
-		 */
-		val &= ~VLV_EDP_PSR_ACTIVE_ENTRY;
-		I915_WRITE(VLV_PSRCTL(pipe), val);
-
-		/*
-		 * Send AUX wake up - Spec says after transitioning to PSR
-		 * active we have to send AUX wake up by writing 01h in DPCD
-		 * 600h of sink device.
-		 * XXX: This might slow down the transition, but without this
-		 * HW doesn't complete the transition to PSR_state 1 and we
-		 * never get the screen updated.
-		 */
-		drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER,
-				   DP_SET_POWER_D0);
+		val = I915_READ(EDP_PSR_CTL);
+		WARN_ON(!(val & EDP_PSR_ENABLE));
+		I915_WRITE(EDP_PSR_CTL, val & ~EDP_PSR_ENABLE);
 	}
-
 	dev_priv->psr.active = false;
 }
 
-/**
- * intel_psr_single_frame_update - Single Frame Update
- * @dev_priv: i915 device
- * @frontbuffer_bits: frontbuffer plane tracking bits
- *
- * Some platforms support a single frame update feature that is used to
- * send and update only one frame on Remote Frame Buffer.
- * So far it is only implemented for Valleyview and Cherryview because
- * hardware requires this to be done before a page flip.
- */
-void intel_psr_single_frame_update(struct drm_i915_private *dev_priv,
-				   unsigned frontbuffer_bits)
-{
-	struct drm_crtc *crtc;
-	enum pipe pipe;
-	u32 val;
-
-	if (!CAN_PSR(dev_priv))
-		return;
-
-	/*
-	 * Single frame update is already supported on BDW+ but it requires
-	 * many W/A and it isn't really needed.
-	 */
-	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
-		return;
-
-	mutex_lock(&dev_priv->psr.lock);
-	if (!dev_priv->psr.enabled) {
-		mutex_unlock(&dev_priv->psr.lock);
-		return;
-	}
-
-	crtc = dp_to_dig_port(dev_priv->psr.enabled)->base.base.crtc;
-	pipe = to_intel_crtc(crtc)->pipe;
-
-	if (frontbuffer_bits & INTEL_FRONTBUFFER_ALL_MASK(pipe)) {
-		val = I915_READ(VLV_PSRCTL(pipe));
-
-		/*
-		 * We need to set this bit before writing registers for a flip.
-		 * This bit will be self-clear when it gets to the PSR active state.
-		 */
-		I915_WRITE(VLV_PSRCTL(pipe), val | VLV_EDP_PSR_SINGLE_FRAME_UPDATE);
-	}
-	mutex_unlock(&dev_priv->psr.lock);
-}
-
 /**
  * intel_psr_invalidate - Invalidade PSR
  * @dev_priv: i915 device
@@ -1072,7 +880,7 @@ void intel_psr_invalidate(struct drm_i915_private *dev_priv,
 	if (!CAN_PSR(dev_priv))
 		return;
 
-	if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP)
+	if (origin == ORIGIN_FLIP)
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
@@ -1115,7 +923,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	if (!CAN_PSR(dev_priv))
 		return;
 
-	if (dev_priv->psr.has_hw_tracking && origin == ORIGIN_FLIP)
+	if (origin == ORIGIN_FLIP)
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
@@ -1132,8 +940,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 
 	/* By definition flush = invalidate + flush */
 	if (frontbuffer_bits) {
-		if (dev_priv->psr.psr2_enabled ||
-		    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		if (dev_priv->psr.psr2_enabled) {
 			intel_psr_exit(dev_priv);
 		} else {
 			/*
@@ -1185,9 +992,6 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
 		/* HSW and BDW require workarounds that we don't implement. */
 		dev_priv->psr.link_standby = false;
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		/* On VLV and CHV only standby mode is supported. */
-		dev_priv->psr.link_standby = true;
 	else
 		/* For new platforms let's respect VBT back again */
 		dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link;
@@ -1205,18 +1009,10 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	INIT_DELAYED_WORK(&dev_priv->psr.work, intel_psr_work);
 	mutex_init(&dev_priv->psr.lock);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->psr.enable_source = vlv_psr_enable_source;
-		dev_priv->psr.disable_source = vlv_psr_disable;
-		dev_priv->psr.enable_sink = vlv_psr_enable_sink;
-		dev_priv->psr.activate = vlv_psr_activate;
-		dev_priv->psr.setup_vsc = vlv_psr_setup_vsc;
-	} else {
-		dev_priv->psr.has_hw_tracking = true;
-		dev_priv->psr.enable_source = hsw_psr_enable_source;
-		dev_priv->psr.disable_source = hsw_psr_disable;
-		dev_priv->psr.enable_sink = hsw_psr_enable_sink;
-		dev_priv->psr.activate = hsw_psr_activate;
-		dev_priv->psr.setup_vsc = hsw_psr_setup_vsc;
-	}
+	dev_priv->psr.enable_source = hsw_psr_enable_source;
+	dev_priv->psr.disable_source = hsw_psr_disable;
+	dev_priv->psr.enable_sink = hsw_psr_enable_sink;
+	dev_priv->psr.activate = hsw_psr_activate;
+	dev_priv->psr.setup_vsc = hsw_psr_setup_vsc;
+
 }
-- 
cgit v1.2.3


From 8cf6da7ef755c8e09094baae941134b771bd4344 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 11 May 2018 12:51:40 -0700
Subject: drm/i915/psr: Avoid DPCD reads when panel does not support PSR
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Ville noticed that we are unncessarily reading DPCD's after knowing
panel did not support PSR. Looks like this check that was present
earlier got removed unintentionally, let's put it back.

While we do this, add the PSR version number in the debug print.

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Tarun Vyas <tarun.vyas@intel.com>
Reviewed-by: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180511195145.3829-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index c08e4b4c07e1..f0ff005bc86a 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -246,10 +246,12 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	drm_dp_dpcd_read(&intel_dp->aux, DP_PSR_SUPPORT, intel_dp->psr_dpcd,
 			 sizeof(intel_dp->psr_dpcd));
 
-	if (intel_dp->psr_dpcd[0]) {
-		dev_priv->psr.sink_support = true;
-		DRM_DEBUG_KMS("Detected EDP PSR Panel.\n");
-	}
+	if (!intel_dp->psr_dpcd[0])
+		return;
+
+	DRM_DEBUG_KMS("eDP panel supports PSR version %x\n",
+		      intel_dp->psr_dpcd[0]);
+	dev_priv->psr.sink_support = true;
 
 	if (INTEL_GEN(dev_priv) >= 9 &&
 	    (intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_IS_SUPPORTED)) {
@@ -266,8 +268,8 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 		 */
 		dev_priv->psr.sink_psr2_support =
 				intel_dp_get_y_coord_required(intel_dp);
-		DRM_DEBUG_KMS("PSR2 %s on sink", dev_priv->psr.sink_psr2_support
-			      ? "supported" : "not supported");
+		DRM_DEBUG_KMS("PSR2 %ssupported\n",
+			      dev_priv->psr.sink_psr2_support ? "" : "not ");
 
 		if (dev_priv->psr.sink_psr2_support) {
 			dev_priv->psr.colorimetry_support =
-- 
cgit v1.2.3


From 84bb2916a6835636fe28e8db192c3293f2d4df21 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 11 May 2018 12:51:41 -0700
Subject: drm/i915/psr: Check for SET_POWER_CAPABLE bit at PSR init time.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

By moving the check from psr_compute_config() to psr_init_dpcd(), we get
to set the dev_priv->psr.sink_support flag only when the panel is
capable of changing power state. An additional benefit is that the check
will be performed only at init time instead of every atomic_check.

This should change the psr_basic IGT failures on HSW to skips.

v2: Return early when SET_POWER_CAPABLE bit is 0 (Jose)

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106217
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106346
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180511195145.3829-2-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_dp.c  |  8 ++++++--
 drivers/gpu/drm/i915/intel_psr.c | 11 +++++------
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index ce07bd794aed..37b9f62aeb6e 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3730,8 +3730,6 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 		dev_priv->no_aux_handshake = intel_dp->dpcd[DP_MAX_DOWNSPREAD] &
 			DP_NO_AUX_HANDSHAKE_LINK_TRAINING;
 
-	intel_psr_init_dpcd(intel_dp);
-
 	/*
 	 * Read the eDP display control registers.
 	 *
@@ -3747,6 +3745,12 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp)
 		DRM_DEBUG_KMS("eDP DPCD: %*ph\n", (int) sizeof(intel_dp->edp_dpcd),
 			      intel_dp->edp_dpcd);
 
+	/*
+	 * This has to be called after intel_dp->edp_dpcd is filled, PSR checks
+	 * for SET_POWER_CAPABLE bit in intel_dp->edp_dpcd[1]
+	 */
+	intel_psr_init_dpcd(intel_dp);
+
 	/* Read the eDP 1.4+ supported link rates. */
 	if (intel_dp->edp_dpcd[0] >= DP_EDP_14) {
 		__le16 sink_rates[DP_MAX_SUPPORTED_RATES];
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index f0ff005bc86a..26dbb6097981 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -248,9 +248,13 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 
 	if (!intel_dp->psr_dpcd[0])
 		return;
-
 	DRM_DEBUG_KMS("eDP panel supports PSR version %x\n",
 		      intel_dp->psr_dpcd[0]);
+
+	if (!(intel_dp->edp_dpcd[1] & DP_EDP_SET_POWER_CAP)) {
+		DRM_DEBUG_KMS("Panel lacks power state control, PSR cannot be enabled\n");
+		return;
+	}
 	dev_priv->psr.sink_support = true;
 
 	if (INTEL_GEN(dev_priv) >= 9 &&
@@ -570,11 +574,6 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 		return;
 	}
 
-	if (!(intel_dp->edp_dpcd[1] & DP_EDP_SET_POWER_CAP)) {
-		DRM_DEBUG_KMS("PSR condition failed: panel lacks power state control\n");
-		return;
-	}
-
 	crtc_state->has_psr = true;
 	crtc_state->has_psr2 = intel_psr2_config_valid(intel_dp, crtc_state);
 	DRM_DEBUG_KMS("Enabling PSR%s\n", crtc_state->has_psr2 ? "2" : "");
-- 
cgit v1.2.3


From 1e8b251ebcbbfc6bfa826bca4d91a8e1bcad2e5f Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 11 May 2018 12:51:43 -0700
Subject: drm/i915/psr: Avoid unnecessary DPCD read of DP_PSR_CAPS

intel_dp->psr_dpcd already has the required values.

Cc: Jose Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Tarun Vyas <tarun.vyas@intel.com>
Reviewed-by: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180511195145.3829-4-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 26dbb6097981..4f34abcacacf 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -197,15 +197,6 @@ void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir)
 	}
 }
 
-static bool intel_dp_get_y_coord_required(struct intel_dp *intel_dp)
-{
-	uint8_t psr_caps = 0;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_CAPS, &psr_caps) != 1)
-		return false;
-	return psr_caps & DP_PSR2_SU_Y_COORDINATE_REQUIRED;
-}
-
 static bool intel_dp_get_colorimetry_status(struct intel_dp *intel_dp)
 {
 	uint8_t dprx = 0;
@@ -271,7 +262,7 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 		 * GTC first.
 		 */
 		dev_priv->psr.sink_psr2_support =
-				intel_dp_get_y_coord_required(intel_dp);
+			intel_dp->psr_dpcd[1] & DP_PSR2_SU_Y_COORDINATE_REQUIRED;
 		DRM_DEBUG_KMS("PSR2 %ssupported\n",
 			      dev_priv->psr.sink_psr2_support ? "" : "not ");
 
-- 
cgit v1.2.3


From 264ff016cf0672f99f98ea853dbc7e45c3527bc2 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 11 May 2018 12:51:44 -0700
Subject: drm/i915/psr: Fall back to max. synchronization latency if DPCD read
 fails
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Noticed that we assume the best case of 0 latency when the DPCD read
fails, reasonable pessimism is safer.

eDP spec does say that if latency is greater than 8, the panel
supplier needs to provide it. I didn't see anything specific in the VBT
for this, so let's go with 8 frames as a fallback.

Cc: Jose Roberto de Souza <jose.souza@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180511195145.3829-5-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 4f34abcacacf..09f5962a19aa 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -219,13 +219,13 @@ static bool intel_dp_get_alpm_status(struct intel_dp *intel_dp)
 
 static u8 intel_dp_get_sink_sync_latency(struct intel_dp *intel_dp)
 {
-	u8 val = 0;
+	u8 val = 8; /* assume the worst if we can't read the value */
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			      DP_SYNCHRONIZATION_LATENCY_IN_SINK, &val) == 1)
 		val &= DP_MAX_RESYNC_FRAME_COUNT_MASK;
 	else
-		DRM_ERROR("Unable to get sink synchronization latency\n");
+		DRM_DEBUG_KMS("Unable to get sink synchronization latency, assuming 8 frames\n");
 	return val;
 }
 
-- 
cgit v1.2.3


From 97c9de66ca8075871b31f4af05593e027e880e67 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 11 May 2018 12:51:45 -0700
Subject: drm/i915/psr: Fix ALPM cap check for PSR2

While touching the code around this, I noticed that absence of ALPM
capability does not stop us from enabling PSR2. But, the spec
unambiguously states that ALPM is required for PSR2 and so does this
commit that introduced this code

drm/i915/psr: enable ALPM for psr2

    As per edp1.4 spec , alpm is required for psr2 operation as it's
    used for all psr2  main link power down management and alpm enable
    bit must be set for psr2 operation.

Cc: Jose Roberto de Souza <jose.souza@intel.com>
Cc: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Reviewed-by: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Reviewed-by: Tarun Vyas <tarun.vyas@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180511195145.3829-6-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 09f5962a19aa..ebc483f06c6f 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -250,6 +250,10 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 
 	if (INTEL_GEN(dev_priv) >= 9 &&
 	    (intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_IS_SUPPORTED)) {
+		bool y_req = intel_dp->psr_dpcd[1] &
+			     DP_PSR2_SU_Y_COORDINATE_REQUIRED;
+		bool alpm = intel_dp_get_alpm_status(intel_dp);
+
 		/*
 		 * All panels that supports PSR version 03h (PSR2 +
 		 * Y-coordinate) can handle Y-coordinates in VSC but we are
@@ -261,16 +265,13 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 		 * Y-coordinate requirement panels we would need to enable
 		 * GTC first.
 		 */
-		dev_priv->psr.sink_psr2_support =
-			intel_dp->psr_dpcd[1] & DP_PSR2_SU_Y_COORDINATE_REQUIRED;
+		dev_priv->psr.sink_psr2_support = y_req && alpm;
 		DRM_DEBUG_KMS("PSR2 %ssupported\n",
 			      dev_priv->psr.sink_psr2_support ? "" : "not ");
 
 		if (dev_priv->psr.sink_psr2_support) {
 			dev_priv->psr.colorimetry_support =
 				intel_dp_get_colorimetry_status(intel_dp);
-			dev_priv->psr.alpm =
-				intel_dp_get_alpm_status(intel_dp);
 			dev_priv->psr.sink_sync_latency =
 				intel_dp_get_sink_sync_latency(intel_dp);
 		}
@@ -351,13 +352,12 @@ static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
 	u8 dpcd_val = DP_PSR_ENABLE;
 
 	/* Enable ALPM at sink for psr2 */
-	if (dev_priv->psr.psr2_enabled && dev_priv->psr.alpm)
-		drm_dp_dpcd_writeb(&intel_dp->aux,
-				DP_RECEIVER_ALPM_CONFIG,
-				DP_ALPM_ENABLE);
-
-	if (dev_priv->psr.psr2_enabled)
+	if (dev_priv->psr.psr2_enabled) {
+		drm_dp_dpcd_writeb(&intel_dp->aux, DP_RECEIVER_ALPM_CONFIG,
+				   DP_ALPM_ENABLE);
 		dpcd_val |= DP_PSR_ENABLE_PSR2;
+	}
+
 	if (dev_priv->psr.link_standby)
 		dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE;
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val);
-- 
cgit v1.2.3


From 2f7e87692e0441abf27a9714991edd136e87363a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 21 May 2018 09:21:28 +0100
Subject: drm/mm: Reject over-sized allocation requests early

As we keep an rbtree of available holes sorted by their size, we can
very easily determine if there is any hole large enough that might
satisfy the allocation request. This helps when dealing with a highly
fragmented address space and a request for a search by address.

To cache the largest size, we convert into the cached rbtree variant
which tracks the leftmost node for us. However, currently we sorted into
ascending size order so the leftmost node is the smallest, and so to
make it the largest hole we need to invert our sorting.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521082131.13744-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/drm_mm.c | 82 +++++++++++++++++++++++++++++++++---------------
 include/drm/drm_mm.h     |  2 +-
 2 files changed, 58 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 3166026a1874..7b4ad05fe1c0 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -239,6 +239,32 @@ static void drm_mm_interval_tree_add_node(struct drm_mm_node *hole_node,
 #define HOLE_SIZE(NODE) ((NODE)->hole_size)
 #define HOLE_ADDR(NODE) (__drm_mm_hole_node_start(NODE))
 
+static u64 rb_to_hole_size(struct rb_node *rb)
+{
+	return rb_entry(rb, struct drm_mm_node, rb_hole_size)->hole_size;
+}
+
+static void insert_hole_size(struct rb_root_cached *root,
+			     struct drm_mm_node *node)
+{
+	struct rb_node **link = &root->rb_root.rb_node, *rb = NULL;
+	u64 x = node->hole_size;
+	bool first = true;
+
+	while (*link) {
+		rb = *link;
+		if (x > rb_to_hole_size(rb)) {
+			link = &rb->rb_left;
+		} else {
+			link = &rb->rb_right;
+			first = false;
+		}
+	}
+
+	rb_link_node(&node->rb_hole_size, rb, link);
+	rb_insert_color_cached(&node->rb_hole_size, root, first);
+}
+
 static void add_hole(struct drm_mm_node *node)
 {
 	struct drm_mm *mm = node->mm;
@@ -247,7 +273,7 @@ static void add_hole(struct drm_mm_node *node)
 		__drm_mm_hole_node_end(node) - __drm_mm_hole_node_start(node);
 	DRM_MM_BUG_ON(!drm_mm_hole_follows(node));
 
-	RB_INSERT(mm->holes_size, rb_hole_size, HOLE_SIZE);
+	insert_hole_size(&mm->holes_size, node);
 	RB_INSERT(mm->holes_addr, rb_hole_addr, HOLE_ADDR);
 
 	list_add(&node->hole_stack, &mm->hole_stack);
@@ -258,7 +284,7 @@ static void rm_hole(struct drm_mm_node *node)
 	DRM_MM_BUG_ON(!drm_mm_hole_follows(node));
 
 	list_del(&node->hole_stack);
-	rb_erase(&node->rb_hole_size, &node->mm->holes_size);
+	rb_erase_cached(&node->rb_hole_size, &node->mm->holes_size);
 	rb_erase(&node->rb_hole_addr, &node->mm->holes_addr);
 	node->hole_size = 0;
 
@@ -282,38 +308,39 @@ static inline u64 rb_hole_size(struct rb_node *rb)
 
 static struct drm_mm_node *best_hole(struct drm_mm *mm, u64 size)
 {
-	struct rb_node *best = NULL;
-	struct rb_node **link = &mm->holes_size.rb_node;
+	struct rb_node *rb = mm->holes_size.rb_root.rb_node;
+	struct drm_mm_node *best = NULL;
 
-	while (*link) {
-		struct rb_node *rb = *link;
+	do {
+		struct drm_mm_node *node =
+			rb_entry(rb, struct drm_mm_node, rb_hole_size);
 
-		if (size <= rb_hole_size(rb)) {
-			link = &rb->rb_left;
-			best = rb;
+		if (size <= node->hole_size) {
+			best = node;
+			rb = rb->rb_right;
 		} else {
-			link = &rb->rb_right;
+			rb = rb->rb_left;
 		}
-	}
+	} while (rb);
 
-	return rb_hole_size_to_node(best);
+	return best;
 }
 
 static struct drm_mm_node *find_hole(struct drm_mm *mm, u64 addr)
 {
+	struct rb_node *rb = mm->holes_addr.rb_node;
 	struct drm_mm_node *node = NULL;
-	struct rb_node **link = &mm->holes_addr.rb_node;
 
-	while (*link) {
+	while (rb) {
 		u64 hole_start;
 
-		node = rb_hole_addr_to_node(*link);
+		node = rb_hole_addr_to_node(rb);
 		hole_start = __drm_mm_hole_node_start(node);
 
 		if (addr < hole_start)
-			link = &node->rb_hole_addr.rb_left;
+			rb = node->rb_hole_addr.rb_left;
 		else if (addr > hole_start + node->hole_size)
-			link = &node->rb_hole_addr.rb_right;
+			rb = node->rb_hole_addr.rb_right;
 		else
 			break;
 	}
@@ -326,9 +353,6 @@ first_hole(struct drm_mm *mm,
 	   u64 start, u64 end, u64 size,
 	   enum drm_mm_insert_mode mode)
 {
-	if (RB_EMPTY_ROOT(&mm->holes_size))
-		return NULL;
-
 	switch (mode) {
 	default:
 	case DRM_MM_INSERT_BEST:
@@ -355,7 +379,7 @@ next_hole(struct drm_mm *mm,
 	switch (mode) {
 	default:
 	case DRM_MM_INSERT_BEST:
-		return rb_hole_size_to_node(rb_next(&node->rb_hole_size));
+		return rb_hole_size_to_node(rb_prev(&node->rb_hole_size));
 
 	case DRM_MM_INSERT_LOW:
 		return rb_hole_addr_to_node(rb_next(&node->rb_hole_addr));
@@ -426,6 +450,11 @@ int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node)
 }
 EXPORT_SYMBOL(drm_mm_reserve_node);
 
+static u64 rb_to_hole_size_or_zero(struct rb_node *rb)
+{
+	return rb ? rb_to_hole_size(rb) : 0;
+}
+
 /**
  * drm_mm_insert_node_in_range - ranged search for space and insert @node
  * @mm: drm_mm to allocate from
@@ -457,6 +486,9 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
 	if (unlikely(size == 0 || range_end - range_start < size))
 		return -ENOSPC;
 
+	if (rb_to_hole_size_or_zero(rb_first_cached(&mm->holes_size)) < size)
+		return -ENOSPC;
+
 	if (alignment <= 1)
 		alignment = 0;
 
@@ -587,9 +619,9 @@ void drm_mm_replace_node(struct drm_mm_node *old, struct drm_mm_node *new)
 
 	if (drm_mm_hole_follows(old)) {
 		list_replace(&old->hole_stack, &new->hole_stack);
-		rb_replace_node(&old->rb_hole_size,
-				&new->rb_hole_size,
-				&mm->holes_size);
+		rb_replace_node_cached(&old->rb_hole_size,
+				       &new->rb_hole_size,
+				       &mm->holes_size);
 		rb_replace_node(&old->rb_hole_addr,
 				&new->rb_hole_addr,
 				&mm->holes_addr);
@@ -885,7 +917,7 @@ void drm_mm_init(struct drm_mm *mm, u64 start, u64 size)
 
 	INIT_LIST_HEAD(&mm->hole_stack);
 	mm->interval_tree = RB_ROOT_CACHED;
-	mm->holes_size = RB_ROOT;
+	mm->holes_size = RB_ROOT_CACHED;
 	mm->holes_addr = RB_ROOT;
 
 	/* Clever trick to avoid a special case in the free hole tracking. */
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index 101f566ae43d..e3aa3bfd4860 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -173,7 +173,7 @@ struct drm_mm {
 	struct drm_mm_node head_node;
 	/* Keep an interval_tree for fast lookup of drm_mm_nodes by address. */
 	struct rb_root_cached interval_tree;
-	struct rb_root holes_size;
+	struct rb_root_cached holes_size;
 	struct rb_root holes_addr;
 
 	unsigned long scan_active;
-- 
cgit v1.2.3


From 83bc4ec37210b17bd611a58968b2ce0e9cc7f251 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 21 May 2018 09:21:29 +0100
Subject: drm/mm: Add a search-by-address variant to only inspect a single hole

Searching for an available hole by address is slow, as there no
guarantee that a hole will be available and so we must walk over all
nodes in the rbtree before we determine the search was futile. In many
cases, the caller doesn't strictly care for the highest available hole
and was just opportunistically laying out the address space in a
preferred order. In such cases, the caller can accept any address and
would rather do so then do a slow walk.

To be able to mix search strategies, the caller wants to tell the drm_mm
how long to spend on the search. Without a good guide for what should be
the best split, start with a request to try once at most. That is return
the top-most (or lowest) hole if it fulfils the alignment and size
requirements.

v2: Documentation, by why of example (selftests) and kerneldoc.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521082131.13744-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/drm_mm.c                     |  9 +++-
 drivers/gpu/drm/selftests/drm_mm_selftests.h |  2 +
 drivers/gpu/drm/selftests/test-drm_mm.c      | 71 ++++++++++++++++++++++++++++
 include/drm/drm_mm.h                         | 32 +++++++++++++
 4 files changed, 112 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_mm.c b/drivers/gpu/drm/drm_mm.c
index 7b4ad05fe1c0..3cc5fbd78ee2 100644
--- a/drivers/gpu/drm/drm_mm.c
+++ b/drivers/gpu/drm/drm_mm.c
@@ -480,6 +480,7 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
 {
 	struct drm_mm_node *hole;
 	u64 remainder_mask;
+	bool once;
 
 	DRM_MM_BUG_ON(range_start >= range_end);
 
@@ -492,9 +493,13 @@ int drm_mm_insert_node_in_range(struct drm_mm * const mm,
 	if (alignment <= 1)
 		alignment = 0;
 
+	once = mode & DRM_MM_INSERT_ONCE;
+	mode &= ~DRM_MM_INSERT_ONCE;
+
 	remainder_mask = is_power_of_2(alignment) ? alignment - 1 : 0;
-	for (hole = first_hole(mm, range_start, range_end, size, mode); hole;
-	     hole = next_hole(mm, hole, mode)) {
+	for (hole = first_hole(mm, range_start, range_end, size, mode);
+	     hole;
+	     hole = once ? NULL : next_hole(mm, hole, mode)) {
 		u64 hole_start = __drm_mm_hole_node_start(hole);
 		u64 hole_end = hole_start + hole->hole_size;
 		u64 adj_start, adj_end;
diff --git a/drivers/gpu/drm/selftests/drm_mm_selftests.h b/drivers/gpu/drm/selftests/drm_mm_selftests.h
index 54acc117550c..6b943ea1c57d 100644
--- a/drivers/gpu/drm/selftests/drm_mm_selftests.h
+++ b/drivers/gpu/drm/selftests/drm_mm_selftests.h
@@ -19,7 +19,9 @@ selftest(align64, igt_align64)
 selftest(evict, igt_evict)
 selftest(evict_range, igt_evict_range)
 selftest(bottomup, igt_bottomup)
+selftest(lowest, igt_lowest)
 selftest(topdown, igt_topdown)
+selftest(highest, igt_highest)
 selftest(color, igt_color)
 selftest(color_evict, igt_color_evict)
 selftest(color_evict_range, igt_color_evict_range)
diff --git a/drivers/gpu/drm/selftests/test-drm_mm.c b/drivers/gpu/drm/selftests/test-drm_mm.c
index 7cc935d7b7aa..f69d8da222b0 100644
--- a/drivers/gpu/drm/selftests/test-drm_mm.c
+++ b/drivers/gpu/drm/selftests/test-drm_mm.c
@@ -1825,6 +1825,77 @@ err:
 	return ret;
 }
 
+static int __igt_once(unsigned int mode)
+{
+	struct drm_mm mm;
+	struct drm_mm_node rsvd_lo, rsvd_hi, node;
+	int err;
+
+	drm_mm_init(&mm, 0, 7);
+
+	memset(&rsvd_lo, 0, sizeof(rsvd_lo));
+	rsvd_lo.start = 1;
+	rsvd_lo.size = 1;
+	err = drm_mm_reserve_node(&mm, &rsvd_lo);
+	if (err) {
+		pr_err("Could not reserve low node\n");
+		goto err;
+	}
+
+	memset(&rsvd_hi, 0, sizeof(rsvd_hi));
+	rsvd_hi.start = 5;
+	rsvd_hi.size = 1;
+	err = drm_mm_reserve_node(&mm, &rsvd_hi);
+	if (err) {
+		pr_err("Could not reserve low node\n");
+		goto err_lo;
+	}
+
+	if (!drm_mm_hole_follows(&rsvd_lo) || !drm_mm_hole_follows(&rsvd_hi)) {
+		pr_err("Expected a hole after lo and high nodes!\n");
+		err = -EINVAL;
+		goto err_hi;
+	}
+
+	memset(&node, 0, sizeof(node));
+	err = drm_mm_insert_node_generic(&mm, &node,
+					 2, 0, 0,
+					 mode | DRM_MM_INSERT_ONCE);
+	if (!err) {
+		pr_err("Unexpectedly inserted the node into the wrong hole: node.start=%llx\n",
+		       node.start);
+		err = -EINVAL;
+		goto err_node;
+	}
+
+	err = drm_mm_insert_node_generic(&mm, &node, 2, 0, 0, mode);
+	if (err) {
+		pr_err("Could not insert the node into the available hole!\n");
+		err = -EINVAL;
+		goto err_hi;
+	}
+
+err_node:
+	drm_mm_remove_node(&node);
+err_hi:
+	drm_mm_remove_node(&rsvd_hi);
+err_lo:
+	drm_mm_remove_node(&rsvd_lo);
+err:
+	drm_mm_takedown(&mm);
+	return err;
+}
+
+static int igt_lowest(void *ignored)
+{
+	return __igt_once(DRM_MM_INSERT_LOW);
+}
+
+static int igt_highest(void *ignored)
+{
+	return __igt_once(DRM_MM_INSERT_HIGH);
+}
+
 static void separate_adjacent_colors(const struct drm_mm_node *node,
 				     unsigned long color,
 				     u64 *start,
diff --git a/include/drm/drm_mm.h b/include/drm/drm_mm.h
index e3aa3bfd4860..2c3bbb43c7d1 100644
--- a/include/drm/drm_mm.h
+++ b/include/drm/drm_mm.h
@@ -109,6 +109,38 @@ enum drm_mm_insert_mode {
 	 * Allocates the node from the bottom of the found hole.
 	 */
 	DRM_MM_INSERT_EVICT,
+
+	/**
+	 * @DRM_MM_INSERT_ONCE:
+	 *
+	 * Only check the first hole for suitablity and report -ENOSPC
+	 * immediately otherwise, rather than check every hole until a
+	 * suitable one is found. Can only be used in conjunction with another
+	 * search method such as DRM_MM_INSERT_HIGH or DRM_MM_INSERT_LOW.
+	 */
+	DRM_MM_INSERT_ONCE = BIT(31),
+
+	/**
+	 * @DRM_MM_INSERT_HIGHEST:
+	 *
+	 * Only check the highest hole (the hole with the largest address) and
+	 * insert the node at the top of the hole or report -ENOSPC if
+	 * unsuitable.
+	 *
+	 * Does not search all holes.
+	 */
+	DRM_MM_INSERT_HIGHEST = DRM_MM_INSERT_HIGH | DRM_MM_INSERT_ONCE,
+
+	/**
+	 * @DRM_MM_INSERT_LOWEST:
+	 *
+	 * Only check the lowest hole (the hole with the smallest address) and
+	 * insert the node at the bottom of the hole or report -ENOSPC if
+	 * unsuitable.
+	 *
+	 * Does not search all holes.
+	 */
+	DRM_MM_INSERT_LOWEST  = DRM_MM_INSERT_LOW | DRM_MM_INSERT_ONCE,
 };
 
 /**
-- 
cgit v1.2.3


From eb479f86397923cdb82dabae4ca33dc4fec18968 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 21 May 2018 09:21:30 +0100
Subject: drm/i915: Limit searching for PIN_HIGH

To no surprise (since we've flip-flopped over the use of PIN_HIGH a few
times), doing a search by address over a pathologically fragmented
address space is exceeding slow. To protect ourselves from nearly
unbounded latency (think searching a million holes while under
struct_mutex), limit the search for the highest available hole and
fallback to best-fit if it fails.

In the pathologically fragmented case, such as igt/gem_ctx_thrash, the
effect is dramatic, bringing the runtime down from hours to seconds
(depending on how many other slow searches you hit, e.g. alloc_iova()
and alloc_vmap_area() both degrade to a slow rbtree walk after their
small cache is exhausted). For the real world, the number of search
steps is unlikely to be significant as we should only need to search
once per new context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521082131.13744-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 21d72f695adb..c8eaeacd3471 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3972,7 +3972,7 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 
 	mode = DRM_MM_INSERT_BEST;
 	if (flags & PIN_HIGH)
-		mode = DRM_MM_INSERT_HIGH;
+		mode = DRM_MM_INSERT_HIGHEST;
 	if (flags & PIN_MAPPABLE)
 		mode = DRM_MM_INSERT_LOW;
 
@@ -3992,6 +3992,15 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 	if (err != -ENOSPC)
 		return err;
 
+	if (mode & DRM_MM_INSERT_ONCE) {
+		err = drm_mm_insert_node_in_range(&vm->mm, node,
+						  size, alignment, color,
+						  start, end,
+						  DRM_MM_INSERT_BEST);
+		if (err != -ENOSPC)
+			return err;
+	}
+
 	if (flags & PIN_NOEVICT)
 		return -ENOSPC;
 
-- 
cgit v1.2.3


From 2edd4e698dc8a0c497a502c75561c87be0e8a9a6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 21 May 2018 09:21:31 +0100
Subject: drm/i915: Pin the ring high

If we can use an unmappable ring, try to pin it out of the mappable
aperture. This simple layout preference is to try and keep the mappable
aperture reserved and available to handle GGTT mmapping requests from
userspace without causing evictions and GPU stalls.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521082131.13744-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 757bb0990c07..8948b30ea5d6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1034,6 +1034,8 @@ int intel_ring_pin(struct intel_ring *ring,
 		flags |= PIN_OFFSET_BIAS | offset_bias;
 	if (vma->obj->stolen)
 		flags |= PIN_MAPPABLE;
+	else
+		flags |= PIN_HIGH;
 
 	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
 		if (flags & PIN_MAPPABLE || map == I915_MAP_WC)
-- 
cgit v1.2.3


From 09a4c02e58c1b3d9748f78242962b7f63c68477e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 24 May 2018 09:11:35 +0100
Subject: drm/i915: Look for an active kernel context before switching

We were not very carefully checking to see if an older request on the
engine was an earlier switch-to-kernel-context before deciding to emit a
new switch. The end result would be that we could get into a permanent
loop of trying to emit a new request to perform the switch simply to
flush the existing switch.

What we need is a means of tracking the completion of each timeline
versus the kernel context, that is to detect if a more recent request
has been submitted that would result in a switch away from the kernel
context. To realise this, we need only to look in our syncmap on the
kernel context and check that we have synchronized against all active
rings.

v2: Since all ringbuffer clients currently share the same timeline, we do
have to use the gem_context to distinguish clients.

As a bonus, include all the tracing used to debug the death inside
suspend.

v3: Test, test, test. Construct a selftest to exercise and assert the
expected behaviour that multiple switch-to-contexts do not emit
redundant requests.

Reported-by: Mika Kuoppala <mika.kuoppala@intel.com>
Fixes: a89d1f921c15 ("drm/i915: Split i915_gem_timeline into individual timelines")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524081135.15278-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c                    |   7 +
 drivers/gpu/drm/i915/i915_gem.h                    |   3 +
 drivers/gpu/drm/i915/i915_gem_context.c            |  86 ++++++++++--
 drivers/gpu/drm/i915/i915_request.c                |   5 +-
 drivers/gpu/drm/i915/selftests/i915_gem_context.c  | 144 +++++++++++++++++++++
 .../gpu/drm/i915/selftests/i915_mock_selftests.h   |   1 +
 6 files changed, 231 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 03874b50ada9..05f44ca35a06 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3703,6 +3703,9 @@ static int wait_for_engines(struct drm_i915_private *i915)
 
 int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 {
+	GEM_TRACE("flags=%x (%s)\n",
+		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked");
+
 	/* If the device is asleep, we have no requests outstanding */
 	if (!READ_ONCE(i915->gt.awake))
 		return 0;
@@ -3719,6 +3722,7 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 				return err;
 		}
 		i915_retire_requests(i915);
+		GEM_BUG_ON(i915->gt.active_requests);
 
 		return wait_for_engines(i915);
 	} else {
@@ -4901,6 +4905,7 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	GEM_BUG_ON(i915->gt.active_requests);
 	for_each_engine(engine, i915, id) {
 		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
 		GEM_BUG_ON(engine->last_retired_context->gem_context != kctx);
@@ -4932,6 +4937,8 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = &dev_priv->drm;
 	int ret;
 
+	GEM_TRACE("\n");
+
 	intel_runtime_pm_get(dev_priv);
 	intel_suspend_gt_powersave(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 5bf24cfc218c..62ee4e385365 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -63,9 +63,12 @@ struct drm_i915_private;
 #if IS_ENABLED(CONFIG_DRM_I915_TRACE_GEM)
 #define GEM_TRACE(...) trace_printk(__VA_ARGS__)
 #define GEM_TRACE_DUMP() ftrace_dump(DUMP_ALL)
+#define GEM_TRACE_DUMP_ON(expr) \
+	do { if (expr) ftrace_dump(DUMP_ALL); } while (0)
 #else
 #define GEM_TRACE(...) do { } while (0)
 #define GEM_TRACE_DUMP() do { } while (0)
+#define GEM_TRACE_DUMP_ON(expr) BUILD_BUG_ON_INVALID(expr)
 #endif
 
 #define I915_NUM_ENGINES 8
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index b69b18ef8120..45393f6e0208 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -576,30 +576,72 @@ last_request_on_engine(struct i915_timeline *timeline,
 {
 	struct i915_request *rq;
 
-	if (timeline == &engine->timeline)
-		return NULL;
+	GEM_BUG_ON(timeline == &engine->timeline);
 
 	rq = i915_gem_active_raw(&timeline->last_request,
 				 &engine->i915->drm.struct_mutex);
-	if (rq && rq->engine == engine)
+	if (rq && rq->engine == engine) {
+		GEM_TRACE("last request for %s on engine %s: %llx:%d\n",
+			  timeline->name, engine->name,
+			  rq->fence.context, rq->fence.seqno);
+		GEM_BUG_ON(rq->timeline != timeline);
 		return rq;
+	}
 
 	return NULL;
 }
 
-static bool engine_has_idle_kernel_context(struct intel_engine_cs *engine)
+static bool engine_has_kernel_context_barrier(struct intel_engine_cs *engine)
 {
-	struct list_head * const active_rings = &engine->i915->gt.active_rings;
+	struct drm_i915_private *i915 = engine->i915;
+	const struct intel_context * const ce =
+		to_intel_context(i915->kernel_context, engine);
+	struct i915_timeline *barrier = ce->ring->timeline;
 	struct intel_ring *ring;
+	bool any_active = false;
 
-	lockdep_assert_held(&engine->i915->drm.struct_mutex);
+	lockdep_assert_held(&i915->drm.struct_mutex);
+	list_for_each_entry(ring, &i915->gt.active_rings, active_link) {
+		struct i915_request *rq;
+
+		rq = last_request_on_engine(ring->timeline, engine);
+		if (!rq)
+			continue;
 
-	list_for_each_entry(ring, active_rings, active_link) {
-		if (last_request_on_engine(ring->timeline, engine))
+		any_active = true;
+
+		if (rq->gem_context == i915->kernel_context)
+			continue;
+
+		/*
+		 * Was this request submitted after the previous
+		 * switch-to-kernel-context?
+		 */
+		if (!i915_timeline_sync_is_later(barrier, &rq->fence)) {
+			GEM_TRACE("%s needs barrier for %llx:%d\n",
+				  ring->timeline->name,
+				  rq->fence.context,
+				  rq->fence.seqno);
 			return false;
+		}
+
+		GEM_TRACE("%s has barrier after %llx:%d\n",
+			  ring->timeline->name,
+			  rq->fence.context,
+			  rq->fence.seqno);
 	}
 
-	return intel_engine_has_kernel_context(engine);
+	/*
+	 * If any other timeline was still active and behind the last barrier,
+	 * then our last switch-to-kernel-context must still be queued and
+	 * will run last (leaving the engine in the kernel context when it
+	 * eventually idles).
+	 */
+	if (any_active)
+		return true;
+
+	/* The engine is idle; check that it is idling in the kernel context. */
+	return engine->last_retired_context == ce;
 }
 
 int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
@@ -607,7 +649,10 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
+	GEM_TRACE("\n");
+
 	lockdep_assert_held(&i915->drm.struct_mutex);
+	GEM_BUG_ON(!i915->kernel_context);
 
 	i915_retire_requests(i915);
 
@@ -615,9 +660,12 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 		struct intel_ring *ring;
 		struct i915_request *rq;
 
-		if (engine_has_idle_kernel_context(engine))
+		GEM_BUG_ON(!to_intel_context(i915->kernel_context, engine));
+		if (engine_has_kernel_context_barrier(engine))
 			continue;
 
+		GEM_TRACE("emit barrier on %s\n", engine->name);
+
 		rq = i915_request_alloc(engine, i915->kernel_context);
 		if (IS_ERR(rq))
 			return PTR_ERR(rq);
@@ -627,10 +675,20 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 			struct i915_request *prev;
 
 			prev = last_request_on_engine(ring->timeline, engine);
-			if (prev)
-				i915_sw_fence_await_sw_fence_gfp(&rq->submit,
-								 &prev->submit,
-								 I915_FENCE_GFP);
+			if (!prev)
+				continue;
+
+			if (prev->gem_context == i915->kernel_context)
+				continue;
+
+			GEM_TRACE("add barrier on %s for %llx:%d\n",
+				  engine->name,
+				  prev->fence.context,
+				  prev->fence.seqno);
+			i915_sw_fence_await_sw_fence_gfp(&rq->submit,
+							 &prev->submit,
+							 I915_FENCE_GFP);
+			i915_timeline_sync_set(rq->timeline, &prev->fence);
 		}
 
 		/*
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index fc499bcbd105..f187250e60c6 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -320,6 +320,7 @@ static void advance_ring(struct i915_request *request)
 		 * is just about to be. Either works, if we miss the last two
 		 * noops - they are safe to be replayed on a reset.
 		 */
+		GEM_TRACE("marking %s as inactive\n", ring->timeline->name);
 		tail = READ_ONCE(request->tail);
 		list_del(&ring->active_link);
 	} else {
@@ -1095,8 +1096,10 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	i915_gem_active_set(&timeline->last_request, request);
 
 	list_add_tail(&request->ring_link, &ring->request_list);
-	if (list_is_first(&request->ring_link, &ring->request_list))
+	if (list_is_first(&request->ring_link, &ring->request_list)) {
+		GEM_TRACE("marking %s as active\n", ring->timeline->name);
 		list_add(&ring->active_link, &request->i915->gt.active_rings);
+	}
 	request->emitted_jiffies = jiffies;
 
 	/*
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index ddb03f009232..b39392a00a6f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -26,6 +26,7 @@
 #include "igt_flush_test.h"
 
 #include "mock_drm.h"
+#include "mock_gem_device.h"
 #include "huge_gem_object.h"
 
 #define DW_PER_PAGE (PAGE_SIZE / sizeof(u32))
@@ -420,6 +421,130 @@ out_unlock:
 	return err;
 }
 
+static __maybe_unused const char *
+__engine_name(struct drm_i915_private *i915, unsigned int engines)
+{
+	struct intel_engine_cs *engine;
+	unsigned int tmp;
+
+	if (engines == ALL_ENGINES)
+		return "all";
+
+	for_each_engine_masked(engine, i915, engines, tmp)
+		return engine->name;
+
+	return "none";
+}
+
+static int __igt_switch_to_kernel_context(struct drm_i915_private *i915,
+					  struct i915_gem_context *ctx,
+					  unsigned int engines)
+{
+	struct intel_engine_cs *engine;
+	unsigned int tmp;
+	int err;
+
+	GEM_TRACE("Testing %s\n", __engine_name(i915, engines));
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		struct i915_request *rq;
+
+		rq = i915_request_alloc(engine, ctx);
+		if (IS_ERR(rq))
+			return PTR_ERR(rq);
+
+		i915_request_add(rq);
+	}
+
+	err = i915_gem_switch_to_kernel_context(i915);
+	if (err)
+		return err;
+
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		if (!engine_has_kernel_context_barrier(engine)) {
+			pr_err("kernel context not last on engine %s!\n",
+			       engine->name);
+			return -EINVAL;
+		}
+	}
+
+	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	if (err)
+		return err;
+
+	GEM_BUG_ON(i915->gt.active_requests);
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		if (engine->last_retired_context->gem_context != i915->kernel_context) {
+			pr_err("engine %s not idling in kernel context!\n",
+			       engine->name);
+			return -EINVAL;
+		}
+	}
+
+	err = i915_gem_switch_to_kernel_context(i915);
+	if (err)
+		return err;
+
+	if (i915->gt.active_requests) {
+		pr_err("switch-to-kernel-context emitted %d requests even though it should already be idling in the kernel context\n",
+		       i915->gt.active_requests);
+		return -EINVAL;
+	}
+
+	for_each_engine_masked(engine, i915, engines, tmp) {
+		if (!intel_engine_has_kernel_context(engine)) {
+			pr_err("kernel context not last on engine %s!\n",
+			       engine->name);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int igt_switch_to_kernel_context(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct intel_engine_cs *engine;
+	struct i915_gem_context *ctx;
+	enum intel_engine_id id;
+	int err;
+
+	/*
+	 * A core premise of switching to the kernel context is that
+	 * if an engine is already idling in the kernel context, we
+	 * do not emit another request and wake it up. The other being
+	 * that we do indeed end up idling in the kernel context.
+	 */
+
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = kernel_context(i915);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_unlock;
+	}
+
+	/* First check idling each individual engine */
+	for_each_engine(engine, i915, id) {
+		err = __igt_switch_to_kernel_context(i915, ctx, BIT(id));
+		if (err)
+			goto out_unlock;
+	}
+
+	/* Now en masse */
+	err = __igt_switch_to_kernel_context(i915, ctx, ALL_ENGINES);
+	if (err)
+		goto out_unlock;
+
+out_unlock:
+	GEM_TRACE_DUMP_ON(err);
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	kernel_context_close(ctx);
+	return err;
+}
+
 static int fake_aliasing_ppgtt_enable(struct drm_i915_private *i915)
 {
 	struct drm_i915_gem_object *obj;
@@ -447,9 +572,28 @@ static void fake_aliasing_ppgtt_disable(struct drm_i915_private *i915)
 	i915_gem_fini_aliasing_ppgtt(i915);
 }
 
+int i915_gem_context_mock_selftests(void)
+{
+	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_switch_to_kernel_context),
+	};
+	struct drm_i915_private *i915;
+	int err;
+
+	i915 = mock_gem_device();
+	if (!i915)
+		return -ENOMEM;
+
+	err = i915_subtests(tests, i915);
+
+	drm_dev_unref(&i915->drm);
+	return err;
+}
+
 int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
 {
 	static const struct i915_subtest tests[] = {
+		SUBTEST(igt_switch_to_kernel_context),
 		SUBTEST(igt_ctx_exec),
 	};
 	bool fake_alias = false;
diff --git a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
index d16d74178e9d..1b70208eeea7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
+++ b/drivers/gpu/drm/i915/selftests/i915_mock_selftests.h
@@ -24,3 +24,4 @@ selftest(vma, i915_vma_mock_selftests)
 selftest(evict, i915_gem_evict_mock_selftests)
 selftest(gtt, i915_gem_gtt_mock_selftests)
 selftest(hugepages, i915_gem_huge_page_mock_selftests)
+selftest(contexts, i915_gem_context_mock_selftests)
-- 
cgit v1.2.3


From 9eece5d9c6e0316f17091e37ff3ec87331bdedf3 Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Wed, 23 May 2018 14:36:30 +0300
Subject: drm/xen-front: fix pointer casts

Building for a 32-bit target results in warnings from casting
between a 32-bit pointer and a 64-bit integer. Fix the warnings
by casting those pointers to uintptr_t first.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180523113630.29811-1-andr2000@gmail.com
---
 drivers/gpu/drm/xen/xen_drm_front.h       | 4 ++--
 drivers/gpu/drm/xen/xen_drm_front_shbuf.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xen/xen_drm_front.h b/drivers/gpu/drm/xen/xen_drm_front.h
index 2c2479b571ae..5693b4a4b02b 100644
--- a/drivers/gpu/drm/xen/xen_drm_front.h
+++ b/drivers/gpu/drm/xen/xen_drm_front.h
@@ -126,12 +126,12 @@ struct xen_drm_front_drm_info {
 
 static inline u64 xen_drm_front_fb_to_cookie(struct drm_framebuffer *fb)
 {
-	return (u64)fb;
+	return (uintptr_t)fb;
 }
 
 static inline u64 xen_drm_front_dbuf_to_cookie(struct drm_gem_object *gem_obj)
 {
-	return (u64)gem_obj;
+	return (uintptr_t)gem_obj;
 }
 
 int xen_drm_front_mode_set(struct xen_drm_front_drm_pipeline *pipeline,
diff --git a/drivers/gpu/drm/xen/xen_drm_front_shbuf.c b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
index 8099cb343ae3..d333b67cc1a0 100644
--- a/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
+++ b/drivers/gpu/drm/xen/xen_drm_front_shbuf.c
@@ -122,7 +122,7 @@ static void guest_calc_num_grefs(struct xen_drm_front_shbuf *buf)
 }
 
 #define xen_page_to_vaddr(page) \
-		((phys_addr_t)pfn_to_kaddr(page_to_xen_pfn(page)))
+		((uintptr_t)pfn_to_kaddr(page_to_xen_pfn(page)))
 
 static int backend_unmap(struct xen_drm_front_shbuf *buf)
 {
-- 
cgit v1.2.3


From c5d1f5562ea7f83fe911d6f9fcb3a32a8e1139ae Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Thu, 24 May 2018 16:06:20 +0100
Subject: drm/i915: Include i915_scheduler.h from i915_gem_context.h

struct i915_gem_context embeds struct i915_sched_attr so needs to include
the respective header.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524150621.17332-1-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_gem_context.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index c3262b4dd2ee..84fef3b1e6e4 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -30,6 +30,7 @@
 #include <linux/radix-tree.h>
 
 #include "i915_gem.h"
+#include "i915_scheduler.h"
 
 struct pid;
 
-- 
cgit v1.2.3


From 8359768c5c325f841473343288fc4d55a256954f Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Thu, 24 May 2018 16:06:21 +0100
Subject: drm/i915: Forward declare struct intel_context

This is to avoid an error with structure declared in parameter list if the
include ordering changes.

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524150621.17332-2-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_gem_context.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.h b/drivers/gpu/drm/i915/i915_gem_context.h
index 84fef3b1e6e4..b116e4942c10 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.h
+++ b/drivers/gpu/drm/i915/i915_gem_context.h
@@ -46,6 +46,8 @@ struct intel_ring;
 
 #define DEFAULT_CONTEXT_HANDLE 0
 
+struct intel_context;
+
 struct intel_context_ops {
 	void (*unpin)(struct intel_context *ce);
 	void (*destroy)(struct intel_context *ce);
-- 
cgit v1.2.3


From 9a4dc80399b1630cea0f1ad8ef0417436cbb95d0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 18 May 2018 11:09:33 +0100
Subject: drm/i915: Flush the ring stop bit after clearing RING_HEAD in reset

Inside the live_hangcheck (reset) selftests, we occasionally see
failures like

<7>[  239.094840] i915_gem_set_wedged rcs0
<7>[  239.094843] i915_gem_set_wedged 	current seqno 19a98, last 19a9a, hangcheck 0 [5158 ms]
<7>[  239.094846] i915_gem_set_wedged 	Reset count: 6239 (global 1)
<7>[  239.094848] i915_gem_set_wedged 	Requests:
<7>[  239.095052] i915_gem_set_wedged 		first  19a99 [e8c:5f] prio=1024 @ 5159ms: (null)
<7>[  239.095056] i915_gem_set_wedged 		last   19a9a [e81:1a] prio=139 @ 5159ms: igt/rcs0[5977]/1
<7>[  239.095059] i915_gem_set_wedged 		active 19a99 [e8c:5f] prio=1024 @ 5159ms: (null)
<7>[  239.095062] i915_gem_set_wedged 		[head 0220, postfix 0280, tail 02a8, batch 0xffffffff_ffffffff]
<7>[  239.100050] i915_gem_set_wedged 		ring->start:  0x00283000
<7>[  239.100053] i915_gem_set_wedged 		ring->head:   0x000001f8
<7>[  239.100055] i915_gem_set_wedged 		ring->tail:   0x000002a8
<7>[  239.100057] i915_gem_set_wedged 		ring->emit:   0x000002a8
<7>[  239.100059] i915_gem_set_wedged 		ring->space:  0x00000f10
<7>[  239.100085] i915_gem_set_wedged 	RING_START: 0x00283000
<7>[  239.100088] i915_gem_set_wedged 	RING_HEAD:  0x00000260
<7>[  239.100091] i915_gem_set_wedged 	RING_TAIL:  0x000002a8
<7>[  239.100094] i915_gem_set_wedged 	RING_CTL:   0x00000001
<7>[  239.100097] i915_gem_set_wedged 	RING_MODE:  0x00000300 [idle]
<7>[  239.100100] i915_gem_set_wedged 	RING_IMR: fffffefe
<7>[  239.100104] i915_gem_set_wedged 	ACTHD:  0x00000000_0000609c
<7>[  239.100108] i915_gem_set_wedged 	BBADDR: 0x00000000_0000609d
<7>[  239.100111] i915_gem_set_wedged 	DMA_FADDR: 0x00000000_00283260
<7>[  239.100114] i915_gem_set_wedged 	IPEIR: 0x00000000
<7>[  239.100117] i915_gem_set_wedged 	IPEHR: 0x02800000
<7>[  239.100120] i915_gem_set_wedged 	Execlist status: 0x00044052 00000002
<7>[  239.100124] i915_gem_set_wedged 	Execlist CSB read 5 [5 cached], write 5 [5 from hws], interrupt posted? no, tasklet queued? no (enabled)
<7>[  239.100128] i915_gem_set_wedged 		ELSP[0] count=1, ring->start=00283000, rq: 19a99 [e8c:5f] prio=1024 @ 5164ms: (null)
<7>[  239.100132] i915_gem_set_wedged 		ELSP[1] count=1, ring->start=00257000, rq: 19a9a [e81:1a] prio=139 @ 5164ms: igt/rcs0[5977]/1
<7>[  239.100135] i915_gem_set_wedged 		HW active? 0x5
<7>[  239.100250] i915_gem_set_wedged 		E 19a99 [e8c:5f] prio=1024 @ 5164ms: (null)
<7>[  239.100338] i915_gem_set_wedged 		E 19a9a [e81:1a] prio=139 @ 5164ms: igt/rcs0[5977]/1
<7>[  239.100340] i915_gem_set_wedged 		Queue priority: 139
<7>[  239.100343] i915_gem_set_wedged 		Q 0 [e98:19] prio=132 @ 5164ms: igt/rcs0[5977]/8
<7>[  239.100346] i915_gem_set_wedged 		Q 0 [e84:19] prio=121 @ 5165ms: igt/rcs0[5977]/2
<7>[  239.100349] i915_gem_set_wedged 		Q 0 [e87:19] prio=82 @ 5165ms: igt/rcs0[5977]/3
<7>[  239.100352] i915_gem_set_wedged 		Q 0 [e84:1a] prio=44 @ 5164ms: igt/rcs0[5977]/2
<7>[  239.100356] i915_gem_set_wedged 		Q 0 [e8b:19] prio=20 @ 5165ms: igt/rcs0[5977]/4
<7>[  239.100362] i915_gem_set_wedged 	drv_selftest [5894] waiting for 19a99

where the GPU saw an arbitration point and idles; AND HAS NOT BEEN RESET!
The RING_MODE indicates that is idle and has the STOP_RING bit set, so
try clearing it.

v2: Only clear the bit on restarting the ring, as we want to be sure the
STOP_RING bit is kept if reset fails on wedging.
v3: Spot when the ring state doesn't make sense when re-initialising the
engine and dump it to the logs so that we don't have to wait for an
error later and try to guess what happened earlier.
v4: Prepare to print all the unexpected state, not just the first.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518100933.2239-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 46e7bf4a30a9..302af60415a3 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1782,6 +1782,9 @@ static void enable_execlists(struct intel_engine_cs *engine)
 		I915_WRITE(RING_MODE_GEN7(engine),
 			   _MASKED_BIT_ENABLE(GFX_RUN_LIST_ENABLE));
 
+	I915_WRITE(RING_MI_MODE(engine->mmio_base),
+		   _MASKED_BIT_DISABLE(STOP_RING));
+
 	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
 		   engine->status_page.ggtt_offset);
 	POSTING_READ(RING_HWS_PGA(engine->mmio_base));
@@ -1790,6 +1793,19 @@ static void enable_execlists(struct intel_engine_cs *engine)
 	engine->execlists.csb_head = -1;
 }
 
+static bool unexpected_starting_state(struct intel_engine_cs *engine)
+{
+	struct drm_i915_private *dev_priv = engine->i915;
+	bool unexpected = false;
+
+	if (I915_READ(RING_MI_MODE(engine->mmio_base)) & STOP_RING) {
+		DRM_DEBUG_DRIVER("STOP_RING still set in RING_MI_MODE\n");
+		unexpected = true;
+	}
+
+	return unexpected;
+}
+
 static int gen8_init_common_ring(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1802,6 +1818,12 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 	intel_engine_reset_breadcrumbs(engine);
 	intel_engine_init_hangcheck(engine);
 
+	if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) {
+		struct drm_printer p = drm_debug_printer(__func__);
+
+		intel_engine_dump(engine, &p, NULL);
+	}
+
 	enable_execlists(engine);
 
 	/* After a GPU reset, we may have requests to replay */
-- 
cgit v1.2.3


From fe25f3048322f32131a151ebe213f52821322f9c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 22 May 2018 11:19:37 +0100
Subject: drm/i915/execlists: Wait for ELSP submission on restart

After a reset, we will ensure that there is at least one request
submitted to HW to ensure that a context is loaded for powersaving.
Let's wait for this submission via a tasklet to complete before we drop
our forcewake, ensuring the system is ready for rc6 before we let it
possibly sleep.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522101937.7738-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.h  |  6 ++++++
 drivers/gpu/drm/i915/intel_lrc.c | 11 ++++++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 62ee4e385365..261da577829a 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -82,4 +82,10 @@ static inline void __tasklet_disable_sync_once(struct tasklet_struct *t)
 		tasklet_unlock_wait(t);
 }
 
+static inline void __tasklet_enable_sync_once(struct tasklet_struct *t)
+{
+	if (atomic_dec_return(&t->count) == 0)
+		tasklet_kill(t);
+}
+
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 302af60415a3..4bcd3206991d 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2008,7 +2008,16 @@ static void execlists_reset(struct intel_engine_cs *engine,
 
 static void execlists_reset_finish(struct intel_engine_cs *engine)
 {
-	tasklet_enable(&engine->execlists.tasklet);
+	/*
+	 * Flush the tasklet while we still have the forcewake to be sure
+	 * that it is not allowed to sleep before we restart and reload a
+	 * context.
+	 *
+	 * As before (with execlists_reset_prepare) we rely on the caller
+	 * serialising multiple attempts to reset so that we know that we
+	 * are the only one manipulating tasklet state.
+	 */
+	__tasklet_enable_sync_once(&engine->execlists.tasklet);
 
 	GEM_TRACE("%s\n", engine->name);
 }
-- 
cgit v1.2.3


From 73b66f8731573a5fa74799dfabb4cdfe513b9241 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 25 May 2018 10:26:29 +0100
Subject: drm/i915: Prepare GEM for suspend earlier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In order to prepare the GPU for sleeping, we may want to submit commands
to it. This is a complicated process that may even require some swapping
in from shmemfs, if the GPU was in the wrong state. As such, we need to
do this preparation step synchronously before the rest of the system has
started to turn off (e.g. swapin fails if scsi is suspended).
Fortunately, we are provided with a such a hook, pm_ops.prepare().

v2: Compile cleanup
v3: Fewer asserts, fewer problems?

v4: Ville pointed out that in some circumstances (such as switching off
the overlay) the display code may issue a GPU request. This is
unexpected, and will result in us going to sleep with us believing the
GPU is still awake (though all user work has been saved). Add a comment
to remind our future selves of what trouble brews.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106640
Testcase: igt/drv_suspend after igt/gem_tiled_swapping
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525092629.1456-1-chris@chris-wilson.co.uk
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 47 ++++++++++++++++++++++++++++++++---------
 1 file changed, 37 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 2a96d082addf..fb39e40c0847 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1553,12 +1553,30 @@ static bool suspend_to_idle(struct drm_i915_private *dev_priv)
 	return false;
 }
 
+static int i915_drm_prepare(struct drm_device *dev)
+{
+	struct drm_i915_private *i915 = to_i915(dev);
+	int err;
+
+	/*
+	 * NB intel_display_suspend() may issue new requests after we've
+	 * ostensibly marked the GPU as ready-to-sleep here. We need to
+	 * split out that work and pull it forward so that after point,
+	 * the GPU is not woken again.
+	 */
+	err = i915_gem_suspend(i915);
+	if (err)
+		dev_err(&i915->drm.pdev->dev,
+			"GEM idle failed, suspend/resume might fail\n");
+
+	return err;
+}
+
 static int i915_drm_suspend(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	pci_power_t opregion_target_state;
-	int error;
 
 	/* ignore lid events during suspend */
 	mutex_lock(&dev_priv->modeset_restore_lock);
@@ -1575,13 +1593,6 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	pci_save_state(pdev);
 
-	error = i915_gem_suspend(dev_priv);
-	if (error) {
-		dev_err(&pdev->dev,
-			"GEM idle failed, resume might fail\n");
-		goto out;
-	}
-
 	intel_display_suspend(dev);
 
 	intel_dp_mst_suspend(dev);
@@ -1609,10 +1620,9 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	intel_csr_ucode_suspend(dev_priv);
 
-out:
 	enable_rpm_wakeref_asserts(dev_priv);
 
-	return error;
+	return 0;
 }
 
 static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
@@ -2081,6 +2091,22 @@ out:
 	return ret;
 }
 
+static int i915_pm_prepare(struct device *kdev)
+{
+	struct pci_dev *pdev = to_pci_dev(kdev);
+	struct drm_device *dev = pci_get_drvdata(pdev);
+
+	if (!dev) {
+		dev_err(kdev, "DRM not initialized, aborting suspend.\n");
+		return -ENODEV;
+	}
+
+	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
+		return 0;
+
+	return i915_drm_prepare(dev);
+}
+
 static int i915_pm_suspend(struct device *kdev)
 {
 	struct pci_dev *pdev = to_pci_dev(kdev);
@@ -2731,6 +2757,7 @@ const struct dev_pm_ops i915_pm_ops = {
 	 * S0ix (via system suspend) and S3 event handlers [PMSG_SUSPEND,
 	 * PMSG_RESUME]
 	 */
+	.prepare = i915_pm_prepare,
 	.suspend = i915_pm_suspend,
 	.suspend_late = i915_pm_suspend_late,
 	.resume_early = i915_pm_resume_early,
-- 
cgit v1.2.3


From 7869196000080ace29ddd1f05153d23fa1734d79 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 24 May 2018 22:20:35 +0300
Subject: drm/edid: Fix up edid_cea_modes[] formatting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix up a bunch of bad indentation and insconsistent comments
in edid_cea_modes[].

v2: Instead of stripping the aspect ratio comments let's
    add them to all modes

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524192035.9776-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/drm_edid.c | 268 ++++++++++++++++++++++-----------------------
 1 file changed, 134 insertions(+), 134 deletions(-)

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 82f1ab09169d..634a68a03b07 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -687,562 +687,562 @@ static const struct minimode extra_modes[] = {
 static const struct drm_display_mode edid_cea_modes[] = {
 	/* 0 - dummy, VICs start at 1 */
 	{ },
-	/* 1 - 640x480@60Hz */
+	/* 1 - 640x480@60Hz 4:3 */
 	{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656,
 		   752, 800, 0, 480, 490, 492, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 2 - 720x480@60Hz */
+	/* 2 - 720x480@60Hz 4:3 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 27000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 3 - 720x480@60Hz */
+	/* 3 - 720x480@60Hz 16:9 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 27000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 4 - 1280x720@60Hz */
+	/* 4 - 1280x720@60Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 5 - 1920x1080i@60Hz */
+	/* 5 - 1920x1080i@60Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 6 - 720(1440)x480i@60Hz */
+	/* 6 - 720(1440)x480i@60Hz 4:3 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 7 - 720(1440)x480i@60Hz */
+	/* 7 - 720(1440)x480i@60Hz 16:9 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 8 - 720(1440)x240@60Hz */
+	/* 8 - 720(1440)x240@60Hz 4:3 */
 	{ DRM_MODE("720x240", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 9 - 720(1440)x240@60Hz */
+	/* 9 - 720(1440)x240@60Hz 16:9 */
 	{ DRM_MODE("720x240", DRM_MODE_TYPE_DRIVER, 13500, 720, 739,
 		   801, 858, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 10 - 2880x480i@60Hz */
+	/* 10 - 2880x480i@60Hz 4:3 */
 	{ DRM_MODE("2880x480i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 11 - 2880x480i@60Hz */
+	/* 11 - 2880x480i@60Hz 16:9 */
 	{ DRM_MODE("2880x480i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 12 - 2880x240@60Hz */
+	/* 12 - 2880x240@60Hz 4:3 */
 	{ DRM_MODE("2880x240", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 13 - 2880x240@60Hz */
+	/* 13 - 2880x240@60Hz 16:9 */
 	{ DRM_MODE("2880x240", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2956,
 		   3204, 3432, 0, 240, 244, 247, 262, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 14 - 1440x480@60Hz */
+	/* 14 - 1440x480@60Hz 4:3 */
 	{ DRM_MODE("1440x480", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1472,
 		   1596, 1716, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 15 - 1440x480@60Hz */
+	/* 15 - 1440x480@60Hz 16:9 */
 	{ DRM_MODE("1440x480", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1472,
 		   1596, 1716, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 16 - 1920x1080@60Hz */
+	/* 16 - 1920x1080@60Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 17 - 720x576@50Hz */
+	/* 17 - 720x576@50Hz 4:3 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 18 - 720x576@50Hz */
+	/* 18 - 720x576@50Hz 16:9 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 19 - 1280x720@50Hz */
+	/* 19 - 1280x720@50Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 20 - 1920x1080i@50Hz */
+	/* 20 - 1920x1080i@50Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 21 - 720(1440)x576i@50Hz */
+	/* 21 - 720(1440)x576i@50Hz 4:3 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 22 - 720(1440)x576i@50Hz */
+	/* 22 - 720(1440)x576i@50Hz 16:9 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 23 - 720(1440)x288@50Hz */
+	/* 23 - 720(1440)x288@50Hz 4:3 */
 	{ DRM_MODE("720x288", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 24 - 720(1440)x288@50Hz */
+	/* 24 - 720(1440)x288@50Hz 16:9 */
 	{ DRM_MODE("720x288", DRM_MODE_TYPE_DRIVER, 13500, 720, 732,
 		   795, 864, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 25 - 2880x576i@50Hz */
+	/* 25 - 2880x576i@50Hz 4:3 */
 	{ DRM_MODE("2880x576i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 26 - 2880x576i@50Hz */
+	/* 26 - 2880x576i@50Hz 16:9 */
 	{ DRM_MODE("2880x576i", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 27 - 2880x288@50Hz */
+	/* 27 - 2880x288@50Hz 4:3 */
 	{ DRM_MODE("2880x288", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 28 - 2880x288@50Hz */
+	/* 28 - 2880x288@50Hz 16:9 */
 	{ DRM_MODE("2880x288", DRM_MODE_TYPE_DRIVER, 54000, 2880, 2928,
 		   3180, 3456, 0, 288, 290, 293, 312, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 29 - 1440x576@50Hz */
+	/* 29 - 1440x576@50Hz 4:3 */
 	{ DRM_MODE("1440x576", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1464,
 		   1592, 1728, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 30 - 1440x576@50Hz */
+	/* 30 - 1440x576@50Hz 16:9 */
 	{ DRM_MODE("1440x576", DRM_MODE_TYPE_DRIVER, 54000, 1440, 1464,
 		   1592, 1728, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 31 - 1920x1080@50Hz */
+	/* 31 - 1920x1080@50Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 32 - 1920x1080@24Hz */
+	/* 32 - 1920x1080@24Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2558,
 		   2602, 2750, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 33 - 1920x1080@25Hz */
+	/* 33 - 1920x1080@25Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 34 - 1920x1080@30Hz */
+	/* 34 - 1920x1080@30Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 35 - 2880x480@60Hz */
+	/* 35 - 2880x480@60Hz 4:3 */
 	{ DRM_MODE("2880x480", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2944,
 		   3192, 3432, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 36 - 2880x480@60Hz */
+	/* 36 - 2880x480@60Hz 16:9 */
 	{ DRM_MODE("2880x480", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2944,
 		   3192, 3432, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 37 - 2880x576@50Hz */
+	/* 37 - 2880x576@50Hz 4:3 */
 	{ DRM_MODE("2880x576", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2928,
 		   3184, 3456, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 38 - 2880x576@50Hz */
+	/* 38 - 2880x576@50Hz 16:9 */
 	{ DRM_MODE("2880x576", DRM_MODE_TYPE_DRIVER, 108000, 2880, 2928,
 		   3184, 3456, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 39 - 1920x1080i@50Hz */
+	/* 39 - 1920x1080i@50Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 72000, 1920, 1952,
 		   2120, 2304, 0, 1080, 1126, 1136, 1250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 40 - 1920x1080i@100Hz */
+	/* 40 - 1920x1080i@100Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 41 - 1280x720@100Hz */
+	/* 41 - 1280x720@100Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 42 - 720x576@100Hz */
+	/* 42 - 720x576@100Hz 4:3 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 43 - 720x576@100Hz */
+	/* 43 - 720x576@100Hz 16:9 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 44 - 720(1440)x576i@100Hz */
+	/* 44 - 720(1440)x576i@100Hz 4:3 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 45 - 720(1440)x576i@100Hz */
+	/* 45 - 720(1440)x576i@100Hz 16:9 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 27000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 46 - 1920x1080i@120Hz */
+	/* 46 - 1920x1080i@120Hz 16:9 */
 	{ DRM_MODE("1920x1080i", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1094, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC |
-			DRM_MODE_FLAG_INTERLACE),
+		   DRM_MODE_FLAG_INTERLACE),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 47 - 1280x720@120Hz */
+	/* 47 - 1280x720@120Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 48 - 720x480@120Hz */
+	/* 48 - 720x480@120Hz 4:3 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 54000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 49 - 720x480@120Hz */
+	/* 49 - 720x480@120Hz 16:9 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 54000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 50 - 720(1440)x480i@120Hz */
+	/* 50 - 720(1440)x480i@120Hz 4:3 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 27000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 51 - 720(1440)x480i@120Hz */
+	/* 51 - 720(1440)x480i@120Hz 16:9 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 27000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 52 - 720x576@200Hz */
+	/* 52 - 720x576@200Hz 4:3 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 108000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 53 - 720x576@200Hz */
+	/* 53 - 720x576@200Hz 16:9 */
 	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 108000, 720, 732,
 		   796, 864, 0, 576, 581, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 54 - 720(1440)x576i@200Hz */
+	/* 54 - 720(1440)x576i@200Hz 4:3 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 55 - 720(1440)x576i@200Hz */
+	/* 55 - 720(1440)x576i@200Hz 16:9 */
 	{ DRM_MODE("720x576i", DRM_MODE_TYPE_DRIVER, 54000, 720, 732,
 		   795, 864, 0, 576, 580, 586, 625, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 200, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 56 - 720x480@240Hz */
+	/* 56 - 720x480@240Hz 4:3 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 108000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 57 - 720x480@240Hz */
+	/* 57 - 720x480@240Hz 16:9 */
 	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 108000, 720, 736,
 		   798, 858, 0, 480, 489, 495, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 58 - 720(1440)x480i@240Hz */
+	/* 58 - 720(1440)x480i@240Hz 4:3 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 54000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_4_3, },
-	/* 59 - 720(1440)x480i@240Hz */
+	/* 59 - 720(1440)x480i@240Hz 16:9 */
 	{ DRM_MODE("720x480i", DRM_MODE_TYPE_DRIVER, 54000, 720, 739,
 		   801, 858, 0, 480, 488, 494, 525, 0,
 		   DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC |
-			DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
+		   DRM_MODE_FLAG_INTERLACE | DRM_MODE_FLAG_DBLCLK),
 	  .vrefresh = 240, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 60 - 1280x720@24Hz */
+	/* 60 - 1280x720@24Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 59400, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 61 - 1280x720@25Hz */
+	/* 61 - 1280x720@25Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3700,
 		   3740, 3960, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 62 - 1280x720@30Hz */
+	/* 62 - 1280x720@30Hz 16:9 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 63 - 1920x1080@120Hz */
+	/* 63 - 1920x1080@120Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	 .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 64 - 1920x1080@100Hz */
+	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 64 - 1920x1080@100Hz 16:9 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-	 .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 65 - 1280x720@24Hz */
+	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
+	/* 65 - 1280x720@24Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 59400, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 66 - 1280x720@25Hz */
+	/* 66 - 1280x720@25Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3700,
 		   3740, 3960, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 67 - 1280x720@30Hz */
+	/* 67 - 1280x720@30Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 68 - 1280x720@50Hz */
+	/* 68 - 1280x720@50Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 69 - 1280x720@60Hz */
+	/* 69 - 1280x720@60Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 74250, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 70 - 1280x720@100Hz */
+	/* 70 - 1280x720@100Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1720,
 		   1760, 1980, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 71 - 1280x720@120Hz */
+	/* 71 - 1280x720@120Hz 64:27 */
 	{ DRM_MODE("1280x720", DRM_MODE_TYPE_DRIVER, 148500, 1280, 1390,
 		   1430, 1650, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 72 - 1920x1080@24Hz */
+	/* 72 - 1920x1080@24Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2558,
 		   2602, 2750, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 73 - 1920x1080@25Hz */
+	/* 73 - 1920x1080@25Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 74 - 1920x1080@30Hz */
+	/* 74 - 1920x1080@30Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 74250, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 75 - 1920x1080@50Hz */
+	/* 75 - 1920x1080@50Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 76 - 1920x1080@60Hz */
+	/* 76 - 1920x1080@60Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 77 - 1920x1080@100Hz */
+	/* 77 - 1920x1080@100Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2448,
 		   2492, 2640, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 78 - 1920x1080@120Hz */
+	/* 78 - 1920x1080@120Hz 64:27 */
 	{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 297000, 1920, 2008,
 		   2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 79 - 1680x720@24Hz */
+	/* 79 - 1680x720@24Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 59400, 1680, 3040,
 		   3080, 3300, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 80 - 1680x720@25Hz */
+	/* 80 - 1680x720@25Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 59400, 1680, 2908,
 		   2948, 3168, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 81 - 1680x720@30Hz */
+	/* 81 - 1680x720@30Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 59400, 1680, 2380,
 		   2420, 2640, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 82 - 1680x720@50Hz */
+	/* 82 - 1680x720@50Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 82500, 1680, 1940,
 		   1980, 2200, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 83 - 1680x720@60Hz */
+	/* 83 - 1680x720@60Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 99000, 1680, 1940,
 		   1980, 2200, 0, 720, 725, 730, 750, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 84 - 1680x720@100Hz */
+	/* 84 - 1680x720@100Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 165000, 1680, 1740,
 		   1780, 2000, 0, 720, 725, 730, 825, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 85 - 1680x720@120Hz */
+	/* 85 - 1680x720@120Hz 64:27 */
 	{ DRM_MODE("1680x720", DRM_MODE_TYPE_DRIVER, 198000, 1680, 1740,
 		   1780, 2000, 0, 720, 725, 730, 825, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 86 - 2560x1080@24Hz */
+	/* 86 - 2560x1080@24Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 99000, 2560, 3558,
 		   3602, 3750, 0, 1080, 1084, 1089, 1100, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 87 - 2560x1080@25Hz */
+	/* 87 - 2560x1080@25Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 90000, 2560, 3008,
 		   3052, 3200, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 88 - 2560x1080@30Hz */
+	/* 88 - 2560x1080@30Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 118800, 2560, 3328,
 		   3372, 3520, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 89 - 2560x1080@50Hz */
+	/* 89 - 2560x1080@50Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 185625, 2560, 3108,
 		   3152, 3300, 0, 1080, 1084, 1089, 1125, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 90 - 2560x1080@60Hz */
+	/* 90 - 2560x1080@60Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 198000, 2560, 2808,
 		   2852, 3000, 0, 1080, 1084, 1089, 1100, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 91 - 2560x1080@100Hz */
+	/* 91 - 2560x1080@100Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 371250, 2560, 2778,
 		   2822, 2970, 0, 1080, 1084, 1089, 1250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 100, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 92 - 2560x1080@120Hz */
+	/* 92 - 2560x1080@120Hz 64:27 */
 	{ DRM_MODE("2560x1080", DRM_MODE_TYPE_DRIVER, 495000, 2560, 3108,
 		   3152, 3300, 0, 1080, 1084, 1089, 1250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 120, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 93 - 3840x2160p@24Hz 16:9 */
+	/* 93 - 3840x2160@24Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 5116,
 		   5204, 5500, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 94 - 3840x2160p@25Hz 16:9 */
+	/* 94 - 3840x2160@25Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 95 - 3840x2160p@30Hz 16:9 */
+	/* 95 - 3840x2160@30Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 96 - 3840x2160p@50Hz 16:9 */
+	/* 96 - 3840x2160@50Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 97 - 3840x2160p@60Hz 16:9 */
+	/* 97 - 3840x2160@60Hz 16:9 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_16_9, },
-	/* 98 - 4096x2160p@24Hz 256:135 */
+	/* 98 - 4096x2160@24Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000, 4096, 5116,
 		   5204, 5500, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 99 - 4096x2160p@25Hz 256:135 */
+	/* 99 - 4096x2160@25Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000, 4096, 5064,
 		   5152, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 100 - 4096x2160p@30Hz 256:135 */
+	/* 100 - 4096x2160@30Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 297000, 4096, 4184,
 		   4272, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 101 - 4096x2160p@50Hz 256:135 */
+	/* 101 - 4096x2160@50Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 594000, 4096, 5064,
 		   5152, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 102 - 4096x2160p@60Hz 256:135 */
+	/* 102 - 4096x2160@60Hz 256:135 */
 	{ DRM_MODE("4096x2160", DRM_MODE_TYPE_DRIVER, 594000, 4096, 4184,
 		   4272, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 60, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_256_135, },
-	/* 103 - 3840x2160p@24Hz 64:27 */
+	/* 103 - 3840x2160@24Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 5116,
 		   5204, 5500, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 24, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 104 - 3840x2160p@25Hz 64:27 */
+	/* 104 - 3840x2160@25Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 25, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 105 - 3840x2160p@30Hz 64:27 */
+	/* 105 - 3840x2160@30Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 297000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 30, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 106 - 3840x2160p@50Hz 64:27 */
+	/* 106 - 3840x2160@50Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4896,
 		   4984, 5280, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
 	  .vrefresh = 50, .picture_aspect_ratio = HDMI_PICTURE_ASPECT_64_27, },
-	/* 107 - 3840x2160p@60Hz 64:27 */
+	/* 107 - 3840x2160@60Hz 64:27 */
 	{ DRM_MODE("3840x2160", DRM_MODE_TYPE_DRIVER, 594000, 3840, 4016,
 		   4104, 4400, 0, 2160, 2168, 2178, 2250, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC),
-- 
cgit v1.2.3


From 10ed55e4d94c39cf32058cc0a2a7935b67e4bc9c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 23 May 2018 17:57:18 +0300
Subject: drm/i915: Initialize panel_pipe to INVALID_PIPE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can always figure out which pipe is affected by the panel power
sequencer lockout mechanism. So no need for the pipe A fallback
anymore. The only case we may have to worry about is an invalid
port select in the power sequencer, but INVALID_PIPE is just fine
in that case. We'll get the WARN about the bogus pps port select
anyway.

Cc: Jani Nikula <jani.nikula@intel.com>
Suggested-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180523145718.22932-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 8b385176ce3c..b0e8e3061631 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1202,7 +1202,7 @@ void assert_panel_unlocked(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
 	i915_reg_t pp_reg;
 	u32 val;
-	enum pipe panel_pipe = PIPE_A;
+	enum pipe panel_pipe = INVALID_PIPE;
 	bool locked = true;
 
 	if (WARN_ON(HAS_DDI(dev_priv)))
-- 
cgit v1.2.3


From ea80a661fe56f27821a4fc40f8149be650ec913d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 24 May 2018 22:04:05 +0300
Subject: drm/i915: Try to suppress more spurious PCH underruns on ILK-IVB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

My ILK seems to generate a spurious PCH underrun with most interlaced
HDMI modes. Add a second vblank wait to avoid it.

We have seen some spurious PCH underruns still in CI as well, some
of which seem to be progressive DP. The logs also point towards some
spurious underrins with progressive HDMI on SNB. While I don't have
a solid explanation for those let's try to kill all the birds with one
stone and always do the double wait.

Buzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106387
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524190406.2973-1-ville.syrjala@linux.intel.com
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_display.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b0e8e3061631..90a6ff00c79d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5528,9 +5528,16 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	if (HAS_PCH_CPT(dev_priv))
 		cpt_verify_modeset(dev, intel_crtc->pipe);
 
-	/* Must wait for vblank to avoid spurious PCH FIFO underruns */
-	if (intel_crtc->config->has_pch_encoder)
+	/*
+	 * Must wait for vblank to avoid spurious PCH FIFO underruns.
+	 * And a second vblank wait is needed at least on ILK with
+	 * some interlaced HDMI modes. Let's do the double wait always
+	 * in case there are more corner cases we don't know about.
+	 */
+	if (intel_crtc->config->has_pch_encoder) {
+		intel_wait_for_vblank(dev_priv, pipe);
 		intel_wait_for_vblank(dev_priv, pipe);
+	}
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
 	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, true);
 }
-- 
cgit v1.2.3


From ca3b3fa344476c640712aa9c49b5bc3b350f2584 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 18:01:38 +0300
Subject: drm/i915: Consult VBT "LVDS config" bits to determine whether
 internal LVDS is present
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

VBT seems to have some bits to tell us whether the internal LVDS port
has something hooked up. In theory one might expect the VBT to not have
a child device for the LVDS port if there's no panel hooked up, but
in practice many VBTs still add the child device. The "LVDS config" bits
seem more reliable though, so let's check those.

So far we've used the "LVDS config" bits to check for eDP support on
ILK+, and disable the internal LVDS when the value is 3. That value
is actually documented as "Both internal LVDS and SDVO LVDS", but in
practice it looks to mean "eDP" on all the ilk+ VBTs I've seen. So let's
keep that interpretation, but for pre-ILK we will consider the value
3 to also indicate the presence of the internal LVDS.

Currently we have 25 DMI matches for the "no internal LVDS" quirk. In an
effort to reduce that let's toss in a WARN when the DMI match and VBT
both tell us that the internal LVDS is not present. The hope is that
people will report a bug, and then we can just nuke the corresponding
entry from the DMI quirk list. Credits to Jani for this idea.

v2: Split the basic int_lvds_support thing to a separate patch (Jani)
v3: Rebase
v4: Limit this to VBT version >= 134

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Ondrej Zary <linux@rainbow-software.org>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518150138.18361-1-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_bios.c     | 28 +++++++++++++++++++++++++---
 drivers/gpu/drm/i915/intel_lvds.c     |  5 ++++-
 drivers/gpu/drm/i915/intel_vbt_defs.h |  2 +-
 3 files changed, 30 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index ea7ae8bc0ea0..1cf073b6ac8a 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -516,9 +516,31 @@ parse_driver_features(struct drm_i915_private *dev_priv,
 	if (!driver)
 		return;
 
-	if (INTEL_GEN(dev_priv) >= 5 &&
-	    driver->lvds_config == BDB_DRIVER_FEATURE_EDP)
-		dev_priv->vbt.int_lvds_support = 0;
+	if (INTEL_GEN(dev_priv) >= 5) {
+		/*
+		 * Note that we consider BDB_DRIVER_FEATURE_INT_SDVO_LVDS
+		 * to mean "eDP". The VBT spec doesn't agree with that
+		 * interpretation, but real world VBTs seem to.
+		 */
+		if (driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS)
+			dev_priv->vbt.int_lvds_support = 0;
+	} else {
+		/*
+		 * FIXME it's not clear which BDB version has the LVDS config
+		 * bits defined. Revision history in the VBT spec says:
+		 * "0.92 | Add two definitions for VBT value of LVDS Active
+		 *  Config (00b and 11b values defined) | 06/13/2005"
+		 * but does not the specify the BDB version.
+		 *
+		 * So far version 134 (on i945gm) is the oldest VBT observed
+		 * in the wild with the bits correctly populated. Version
+		 * 108 (on i85x) does not have the bits correctly populated.
+		 */
+		if (bdb->version >= 134 &&
+		    driver->lvds_config != BDB_DRIVER_FEATURE_INT_LVDS &&
+		    driver->lvds_config != BDB_DRIVER_FEATURE_INT_SDVO_LVDS)
+			dev_priv->vbt.int_lvds_support = 0;
+	}
 
 	DRM_DEBUG_KMS("DRRS State Enabled:%d\n", driver->drrs_enabled);
 	/*
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index bacad88ad7ae..e05c12e7629c 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -1000,8 +1000,11 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 		return;
 
 	/* Skip init on machines we know falsely report LVDS */
-	if (dmi_check_system(intel_no_lvds))
+	if (dmi_check_system(intel_no_lvds)) {
+		WARN(!dev_priv->vbt.int_lvds_support,
+		     "Useless DMI match. Internal LVDS support disabled by VBT\n");
 		return;
+	}
 
 	if (!dev_priv->vbt.int_lvds_support) {
 		DRM_DEBUG_KMS("Internal LVDS support disabled by VBT\n");
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index 458468237b5f..39c804624179 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -635,7 +635,7 @@ struct bdb_sdvo_lvds_options {
 #define BDB_DRIVER_FEATURE_NO_LVDS		0
 #define BDB_DRIVER_FEATURE_INT_LVDS		1
 #define BDB_DRIVER_FEATURE_SDVO_LVDS		2
-#define BDB_DRIVER_FEATURE_EDP			3
+#define BDB_DRIVER_FEATURE_INT_SDVO_LVDS	3
 
 struct bdb_driver_features {
 	u8 boot_dev_algorithm:1;
-- 
cgit v1.2.3


From 1add20eb0068fb4526b946e8ae0a94676438a6fa Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Apr 2018 22:50:29 +0300
Subject: drm/arc: Stop consulting plane->fb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to stop using plane->fb with atomic driver, so stop looking at
it.

I have no idea what this code is trying to achieve. There is no
corresponding check in the enable path. Also since
arc_pgu_set_pxl_fmt() will anyway oops if there is no fb I'm going
to assuming that I can just remove the check entirely. There seems
to be a general shortage of .atomic_check() in this driver...

Cc: Alexey Brodkin <abrodkin@synopsys.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405195035.24722-1-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Alexey Brodkin <abrodkin@synopys.com>
---
 drivers/gpu/drm/arc/arcpgu_crtc.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/arc/arcpgu_crtc.c b/drivers/gpu/drm/arc/arcpgu_crtc.c
index 16903dc7fe0d..c3349b8fb58b 100644
--- a/drivers/gpu/drm/arc/arcpgu_crtc.c
+++ b/drivers/gpu/drm/arc/arcpgu_crtc.c
@@ -136,9 +136,6 @@ static void arc_pgu_crtc_atomic_disable(struct drm_crtc *crtc,
 {
 	struct arcpgu_drm_private *arcpgu = crtc_to_arcpgu_priv(crtc);
 
-	if (!crtc->primary->fb)
-		return;
-
 	clk_disable_unprepare(arcpgu->clk);
 	arc_pgu_write(arcpgu, ARCPGU_REG_CTRL,
 			      arc_pgu_read(arcpgu, ARCPGU_REG_CTRL) &
-- 
cgit v1.2.3


From 42eb2f729e55a521e10dbb6dea6d736e0ad6df2a Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Apr 2018 18:13:48 +0300
Subject: drm/msm: Stop consulting plane->fb/crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->fb/crtc on atomic drivers. Stop
looking at them.

v2: Catch the plane->crtc case too

Cc: Rob Clark <robdclark@gmail.com>
Cc: linux-arm-msm@vger.kernel.org
Cc: freedreno@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20180405151400.11326-1-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c  | 2 +-
 drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
index b001699297c4..20f9e5de5f19 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
@@ -201,7 +201,7 @@ static void blend_setup(struct drm_crtc *crtc)
 		int idx = idxs[pipe_id];
 		if (idx > 0) {
 			const struct mdp_format *format =
-					to_mdp_format(msm_framebuffer_format(plane->fb));
+					to_mdp_format(msm_framebuffer_format(plane->state->fb));
 			alpha[idx-1] = format->alpha_enable;
 		}
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index a9f31da7d45a..f2361f79fdce 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -526,7 +526,7 @@ static void mdp5_plane_atomic_async_update(struct drm_plane *plane,
 	if (plane_enabled(new_state)) {
 		struct mdp5_ctl *ctl;
 		struct mdp5_pipeline *pipeline =
-					mdp5_crtc_get_pipeline(plane->crtc);
+					mdp5_crtc_get_pipeline(new_state->crtc);
 		int ret;
 
 		ret = mdp5_plane_mode_set(plane, new_state->crtc, new_state->fb,
-- 
cgit v1.2.3


From df751849219b1be87c86b3224cf07fd0de4c5228 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Apr 2018 18:13:49 +0300
Subject: drm/sti: Stop consulting plane->crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->crtc on atomic drivers. Stop looking at it.

Cc: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Cc: Vincent Abriou <vincent.abriou@st.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405151400.11326-2-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/sti/sti_gdp.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c
index 9b2c47051b51..49813d34bdf0 100644
--- a/drivers/gpu/drm/sti/sti_gdp.c
+++ b/drivers/gpu/drm/sti/sti_gdp.c
@@ -211,7 +211,11 @@ static int gdp_dbg_show(struct seq_file *s, void *data)
 	struct drm_info_node *node = s->private;
 	struct sti_gdp *gdp = (struct sti_gdp *)node->info_ent->data;
 	struct drm_plane *drm_plane = &gdp->plane.drm_plane;
-	struct drm_crtc *crtc = drm_plane->crtc;
+	struct drm_crtc *crtc;
+
+	drm_modeset_lock(&drm_plane->mutex, NULL);
+	crtc = drm_plane->state->crtc;
+	drm_modeset_unlock(&drm_plane->mutex);
 
 	seq_printf(s, "%s: (vaddr = 0x%p)",
 		   sti_plane_to_str(&gdp->plane), gdp->regs);
-- 
cgit v1.2.3


From 0010ac3ffc0e2638b08869bef2588673e04b257d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Apr 2018 18:13:50 +0300
Subject: drm/atmel-hlcdc: Stop consulting plane->crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->crtc on atomic drivers. Stop looking at it.

Cc: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405151400.11326-3-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index 73c875db45f4..15c74527ba49 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -412,9 +412,10 @@ static void atmel_hlcdc_plane_update_format(struct atmel_hlcdc_plane *plane,
 				    ATMEL_HLCDC_LAYER_FORMAT_CFG, cfg);
 }
 
-static void atmel_hlcdc_plane_update_clut(struct atmel_hlcdc_plane *plane)
+static void atmel_hlcdc_plane_update_clut(struct atmel_hlcdc_plane *plane,
+					  struct atmel_hlcdc_plane_state *state)
 {
-	struct drm_crtc *crtc = plane->base.crtc;
+	struct drm_crtc *crtc = state->base.crtc;
 	struct drm_color_lut *lut;
 	int idx;
 
@@ -779,7 +780,7 @@ static void atmel_hlcdc_plane_atomic_update(struct drm_plane *p,
 	atmel_hlcdc_plane_update_pos_and_size(plane, state);
 	atmel_hlcdc_plane_update_general_settings(plane, state);
 	atmel_hlcdc_plane_update_format(plane, state);
-	atmel_hlcdc_plane_update_clut(plane);
+	atmel_hlcdc_plane_update_clut(plane, state);
 	atmel_hlcdc_plane_update_buffers(plane, state);
 	atmel_hlcdc_plane_update_disc_area(plane, state);
 
-- 
cgit v1.2.3


From 3ed70ecd865943a2cbe9b1631f33c9370bc03578 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Apr 2018 18:14:00 +0300
Subject: drm: Add local 'plane' variable for tmp->primary
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Clean up the ugly tmp->primary-> stuff in
__drm_mode_set_config_internal() with a local plane variable.

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405151400.11326-13-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_crtc.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 98a36e6c69ad..237bd34212db 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -469,8 +469,11 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 	 * connectors from it), hence we need to refcount the fbs across all
 	 * crtcs. Atomic modeset will have saner semantics ...
 	 */
-	drm_for_each_crtc(tmp, crtc->dev)
-		tmp->primary->old_fb = tmp->primary->fb;
+	drm_for_each_crtc(tmp, crtc->dev) {
+		struct drm_plane *plane = tmp->primary;
+
+		plane->old_fb = plane->fb;
+	}
 
 	fb = set->fb;
 
@@ -481,11 +484,13 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 	}
 
 	drm_for_each_crtc(tmp, crtc->dev) {
-		if (tmp->primary->fb)
-			drm_framebuffer_get(tmp->primary->fb);
-		if (tmp->primary->old_fb)
-			drm_framebuffer_put(tmp->primary->old_fb);
-		tmp->primary->old_fb = NULL;
+		struct drm_plane *plane = tmp->primary;
+
+		if (plane->fb)
+			drm_framebuffer_get(plane->fb);
+		if (plane->old_fb)
+			drm_framebuffer_put(plane->old_fb);
+		plane->old_fb = NULL;
 	}
 
 	return ret;
-- 
cgit v1.2.3


From b79df2767cc6bcb5da169d147fc199512a527d4b Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Apr 2018 18:13:58 +0300
Subject: drm/omapdrm: Nuke omap_framebuffer_get_next_connector()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

omap_framebuffer_get_next_connector() uses plane->fb which we want to
deprecate for atomic drivers. As omap_framebuffer_get_next_connector()
is unused just nuke the entire function.

Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405151400.11326-11-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_fb.c | 27 ---------------------------
 drivers/gpu/drm/omapdrm/omap_fb.h |  2 --
 2 files changed, 29 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_fb.c b/drivers/gpu/drm/omapdrm/omap_fb.c
index 9d75eab0d164..9f1e3d8f8488 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.c
+++ b/drivers/gpu/drm/omapdrm/omap_fb.c
@@ -279,33 +279,6 @@ void omap_framebuffer_unpin(struct drm_framebuffer *fb)
 	mutex_unlock(&omap_fb->lock);
 }
 
-/* iterate thru all the connectors, returning ones that are attached
- * to the same fb..
- */
-struct drm_connector *omap_framebuffer_get_next_connector(
-		struct drm_framebuffer *fb, struct drm_connector *from)
-{
-	struct drm_device *dev = fb->dev;
-	struct list_head *connector_list = &dev->mode_config.connector_list;
-	struct drm_connector *connector = from;
-
-	if (!from)
-		return list_first_entry_or_null(connector_list, typeof(*from),
-						head);
-
-	list_for_each_entry_from(connector, connector_list, head) {
-		if (connector != from) {
-			struct drm_encoder *encoder = connector->encoder;
-			struct drm_crtc *crtc = encoder ? encoder->crtc : NULL;
-			if (crtc && crtc->primary->fb == fb)
-				return connector;
-
-		}
-	}
-
-	return NULL;
-}
-
 #ifdef CONFIG_DEBUG_FS
 void omap_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m)
 {
diff --git a/drivers/gpu/drm/omapdrm/omap_fb.h b/drivers/gpu/drm/omapdrm/omap_fb.h
index 94ad5f9e4404..c20cb4bc714d 100644
--- a/drivers/gpu/drm/omapdrm/omap_fb.h
+++ b/drivers/gpu/drm/omapdrm/omap_fb.h
@@ -38,8 +38,6 @@ int omap_framebuffer_pin(struct drm_framebuffer *fb);
 void omap_framebuffer_unpin(struct drm_framebuffer *fb);
 void omap_framebuffer_update_scanout(struct drm_framebuffer *fb,
 		struct drm_plane_state *state, struct omap_overlay_info *info);
-struct drm_connector *omap_framebuffer_get_next_connector(
-		struct drm_framebuffer *fb, struct drm_connector *from);
 bool omap_framebuffer_supports_rotation(struct drm_framebuffer *fb);
 void omap_framebuffer_describe(struct drm_framebuffer *fb, struct seq_file *m);
 
-- 
cgit v1.2.3


From 952a08a21ac537c2a0e5c481e8cf3a2426311f56 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Apr 2018 18:13:57 +0300
Subject: drm/atmel-hlcdc: Stop using plane->fb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->fb on atomic drivers. Stop looking at it.

Daniel pointed out that the drm_framebuffer_put() in the plane cleanup
indicates that the driver doesn't shut things down cleanly. To do
that we should be able to just call drm_atomic_helper_shutdown(). Not
really sure the current cleanup sequence is actually sane, but whatever.

v2: Replace the drm_framebuffer_put() with
    drm_atomic_helper_shutdown() (Daniel)

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Boris Brezillon <boris.brezillon@free-electrons.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405151400.11326-10-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c    |  1 +
 drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c | 12 +-----------
 2 files changed, 2 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
index c1ea5c36b006..843cac222e60 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_dc.c
@@ -681,6 +681,7 @@ static void atmel_hlcdc_dc_unload(struct drm_device *dev)
 	drm_fb_cma_fbdev_fini(dev);
 	flush_workqueue(dc->wq);
 	drm_kms_helper_poll_fini(dev);
+	drm_atomic_helper_shutdown(dev);
 	drm_mode_config_cleanup(dev);
 
 	pm_runtime_get_sync(dev->dev);
diff --git a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
index 15c74527ba49..1aecc74cc463 100644
--- a/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
+++ b/drivers/gpu/drm/atmel-hlcdc/atmel_hlcdc_plane.c
@@ -817,16 +817,6 @@ static void atmel_hlcdc_plane_atomic_disable(struct drm_plane *p,
 	atmel_hlcdc_layer_read_reg(&plane->layer, ATMEL_HLCDC_LAYER_ISR);
 }
 
-static void atmel_hlcdc_plane_destroy(struct drm_plane *p)
-{
-	struct atmel_hlcdc_plane *plane = drm_plane_to_atmel_hlcdc_plane(p);
-
-	if (plane->base.fb)
-		drm_framebuffer_put(plane->base.fb);
-
-	drm_plane_cleanup(p);
-}
-
 static int atmel_hlcdc_plane_init_properties(struct atmel_hlcdc_plane *plane)
 {
 	const struct atmel_hlcdc_layer_desc *desc = plane->layer.desc;
@@ -1003,7 +993,7 @@ static void atmel_hlcdc_plane_atomic_destroy_state(struct drm_plane *p,
 static const struct drm_plane_funcs layer_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
-	.destroy = atmel_hlcdc_plane_destroy,
+	.destroy = drm_plane_cleanup,
 	.reset = atmel_hlcdc_plane_reset,
 	.atomic_duplicate_state = atmel_hlcdc_plane_atomic_duplicate_state,
 	.atomic_destroy_state = atmel_hlcdc_plane_atomic_destroy_state,
-- 
cgit v1.2.3


From 2b5b63126ef4037a576bc8f9954629dc22274ad2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 24 May 2018 22:04:06 +0300
Subject: drm/i915: Simplify ilk-ivb underrun suppression
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's suppress the underruns around every modeset sequence instead
of trying to avoid it. Planes are disabled at this point anyway so
we don't really gain anything from keeping the underrun reporting
enabled. Also for PCH ports we already suppress all underruns here
anyway so trying avoid it for the CPU eDP doesn't seem all that
important.

Maybe this gets rid of some lingering spurious underruns?

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524190406.2973-2-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_display.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 90a6ff00c79d..8d4c9e249c44 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5470,10 +5470,8 @@ static void ironlake_crtc_enable(struct intel_crtc_state *pipe_config,
 	 *
 	 * Spurious PCH underruns also occur during PCH enabling.
 	 */
-	if (intel_crtc->config->has_pch_encoder || IS_GEN5(dev_priv))
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
-	if (intel_crtc->config->has_pch_encoder)
-		intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
+	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
+	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	if (intel_crtc->config->has_pch_encoder)
 		intel_prepare_shared_dpll(intel_crtc);
@@ -5717,10 +5715,8 @@ static void ironlake_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	 * pipe is already disabled, but FDI RX/TX is still enabled.
 	 * Happens at least with VGA+HDMI cloning. Suppress them.
 	 */
-	if (intel_crtc->config->has_pch_encoder) {
-		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
-		intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
-	}
+	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
+	intel_set_pch_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	intel_encoders_disable(crtc, old_crtc_state, old_state);
 
-- 
cgit v1.2.3


From 8f1ad1ef1e7ac916a0b344e5e473f52b9159fc87 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Fri, 25 May 2018 12:18:58 +0000
Subject: drm/i915/uc: Trivial s/dev_priv/i915 in intel_uc.c

Some functions already use i915 name instead of dev_priv.
Let's rename this param in all remaining functions, except
those that still use legacy macros.

v2: don't forget about function descriptions (Sagar)
v3: rebased
v4: rebased
v5: rebased, pulled out from the series

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525121858.53928-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/intel_uc.c | 129 ++++++++++++++++++++--------------------
 1 file changed, 64 insertions(+), 65 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 1cffaf7b5dbe..6a73e81f373b 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -50,10 +50,10 @@ static int __intel_uc_reset_hw(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
-static int __get_platform_enable_guc(struct drm_i915_private *dev_priv)
+static int __get_platform_enable_guc(struct drm_i915_private *i915)
 {
-	struct intel_uc_fw *guc_fw = &dev_priv->guc.fw;
-	struct intel_uc_fw *huc_fw = &dev_priv->huc.fw;
+	struct intel_uc_fw *guc_fw = &i915->guc.fw;
+	struct intel_uc_fw *huc_fw = &i915->huc.fw;
 	int enable_guc = 0;
 
 	/* Default is to enable GuC/HuC if we know their firmwares */
@@ -67,11 +67,11 @@ static int __get_platform_enable_guc(struct drm_i915_private *dev_priv)
 	return enable_guc;
 }
 
-static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
+static int __get_default_guc_log_level(struct drm_i915_private *i915)
 {
 	int guc_log_level;
 
-	if (!HAS_GUC(dev_priv) || !intel_uc_is_using_guc())
+	if (!HAS_GUC(i915) || !intel_uc_is_using_guc())
 		guc_log_level = GUC_LOG_LEVEL_DISABLED;
 	else if (IS_ENABLED(CONFIG_DRM_I915_DEBUG) ||
 		 IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM))
@@ -86,7 +86,7 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
 
 /**
  * sanitize_options_early - sanitize uC related modparam options
- * @dev_priv: device private
+ * @i915: device private
  *
  * In case of "enable_guc" option this function will attempt to modify
  * it only if it was initially set to "auto(-1)". Default value for this
@@ -101,14 +101,14 @@ static int __get_default_guc_log_level(struct drm_i915_private *dev_priv)
  * unless GuC is enabled on given platform and the driver is compiled with
  * debug config when this modparam will default to "enable(1..4)".
  */
-static void sanitize_options_early(struct drm_i915_private *dev_priv)
+static void sanitize_options_early(struct drm_i915_private *i915)
 {
-	struct intel_uc_fw *guc_fw = &dev_priv->guc.fw;
-	struct intel_uc_fw *huc_fw = &dev_priv->huc.fw;
+	struct intel_uc_fw *guc_fw = &i915->guc.fw;
+	struct intel_uc_fw *huc_fw = &i915->huc.fw;
 
 	/* A negative value means "use platform default" */
 	if (i915_modparams.enable_guc < 0)
-		i915_modparams.enable_guc = __get_platform_enable_guc(dev_priv);
+		i915_modparams.enable_guc = __get_platform_enable_guc(i915);
 
 	DRM_DEBUG_DRIVER("enable_guc=%d (submission:%s huc:%s)\n",
 			 i915_modparams.enable_guc,
@@ -119,28 +119,28 @@ static void sanitize_options_early(struct drm_i915_private *dev_priv)
 	if (intel_uc_is_using_guc() && !intel_uc_fw_is_selected(guc_fw)) {
 		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
 			 "enable_guc", i915_modparams.enable_guc,
-			 !HAS_GUC(dev_priv) ? "no GuC hardware" :
-					      "no GuC firmware");
+			 !HAS_GUC(i915) ? "no GuC hardware" :
+					  "no GuC firmware");
 	}
 
 	/* Verify HuC firmware availability */
 	if (intel_uc_is_using_huc() && !intel_uc_fw_is_selected(huc_fw)) {
 		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
 			 "enable_guc", i915_modparams.enable_guc,
-			 !HAS_HUC(dev_priv) ? "no HuC hardware" :
-					      "no HuC firmware");
+			 !HAS_HUC(i915) ? "no HuC hardware" :
+					  "no HuC firmware");
 	}
 
 	/* A negative value means "use platform/config default" */
 	if (i915_modparams.guc_log_level < 0)
 		i915_modparams.guc_log_level =
-			__get_default_guc_log_level(dev_priv);
+			__get_default_guc_log_level(i915);
 
 	if (i915_modparams.guc_log_level > 0 && !intel_uc_is_using_guc()) {
 		DRM_WARN("Incompatible option detected: %s=%d, %s!\n",
 			 "guc_log_level", i915_modparams.guc_log_level,
-			 !HAS_GUC(dev_priv) ? "no GuC hardware" :
-					      "GuC not enabled");
+			 !HAS_GUC(i915) ? "no GuC hardware" :
+					  "GuC not enabled");
 		i915_modparams.guc_log_level = 0;
 	}
 
@@ -195,15 +195,14 @@ void intel_uc_cleanup_early(struct drm_i915_private *i915)
 
 /**
  * intel_uc_init_mmio - setup uC MMIO access
- *
- * @dev_priv: device private
+ * @i915: device private
  *
  * Setup minimal state necessary for MMIO accesses later in the
  * initialization sequence.
  */
-void intel_uc_init_mmio(struct drm_i915_private *dev_priv)
+void intel_uc_init_mmio(struct drm_i915_private *i915)
 {
-	intel_guc_init_send_regs(&dev_priv->guc);
+	intel_guc_init_send_regs(&i915->guc);
 }
 
 static void guc_capture_load_err_log(struct intel_guc *guc)
@@ -225,11 +224,11 @@ static void guc_free_load_err_log(struct intel_guc *guc)
 
 static int guc_enable_communication(struct intel_guc *guc)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
-	gen9_enable_guc_interrupts(dev_priv);
+	gen9_enable_guc_interrupts(i915);
 
-	if (HAS_GUC_CT(dev_priv))
+	if (HAS_GUC_CT(i915))
 		return intel_guc_ct_enable(&guc->ct);
 
 	guc->send = intel_guc_send_mmio;
@@ -239,23 +238,23 @@ static int guc_enable_communication(struct intel_guc *guc)
 
 static void guc_disable_communication(struct intel_guc *guc)
 {
-	struct drm_i915_private *dev_priv = guc_to_i915(guc);
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 
-	if (HAS_GUC_CT(dev_priv))
+	if (HAS_GUC_CT(i915))
 		intel_guc_ct_disable(&guc->ct);
 
-	gen9_disable_guc_interrupts(dev_priv);
+	gen9_disable_guc_interrupts(i915);
 
 	guc->send = intel_guc_send_nop;
 	guc->handler = intel_guc_to_host_event_handler_nop;
 }
 
-int intel_uc_init_misc(struct drm_i915_private *dev_priv)
+int intel_uc_init_misc(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 	int ret;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return 0;
 
 	intel_guc_init_ggtt_pin_bias(guc);
@@ -267,32 +266,32 @@ int intel_uc_init_misc(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-void intel_uc_fini_misc(struct drm_i915_private *dev_priv)
+void intel_uc_fini_misc(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return;
 
 	intel_guc_fini_wq(guc);
 }
 
-int intel_uc_init(struct drm_i915_private *dev_priv)
+int intel_uc_init(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 	int ret;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return 0;
 
-	if (!HAS_GUC(dev_priv))
+	if (!HAS_GUC(i915))
 		return -ENODEV;
 
 	ret = intel_guc_init(guc);
 	if (ret)
 		return ret;
 
-	if (USES_GUC_SUBMISSION(dev_priv)) {
+	if (USES_GUC_SUBMISSION(i915)) {
 		/*
 		 * This is stuff we need to have available at fw load time
 		 * if we are planning to enable submission later
@@ -307,16 +306,16 @@ int intel_uc_init(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-void intel_uc_fini(struct drm_i915_private *dev_priv)
+void intel_uc_fini(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return;
 
-	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	GEM_BUG_ON(!HAS_GUC(i915));
 
-	if (USES_GUC_SUBMISSION(dev_priv))
+	if (USES_GUC_SUBMISSION(i915))
 		intel_guc_submission_fini(guc);
 
 	intel_guc_fini(guc);
@@ -340,22 +339,22 @@ void intel_uc_sanitize(struct drm_i915_private *i915)
 	__intel_uc_reset_hw(i915);
 }
 
-int intel_uc_init_hw(struct drm_i915_private *dev_priv)
+int intel_uc_init_hw(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
-	struct intel_huc *huc = &dev_priv->huc;
+	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 	int ret, attempts;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return 0;
 
-	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	GEM_BUG_ON(!HAS_GUC(i915));
 
-	gen9_reset_guc_interrupts(dev_priv);
+	gen9_reset_guc_interrupts(i915);
 
 	/* WaEnableuKernelHeaderValidFix:skl */
 	/* WaEnableGuCBootHashCheckNotSet:skl,bxt,kbl */
-	if (IS_GEN9(dev_priv))
+	if (IS_GEN9(i915))
 		attempts = 3;
 	else
 		attempts = 1;
@@ -365,11 +364,11 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 		 * Always reset the GuC just before (re)loading, so
 		 * that the state and timing are fairly predictable
 		 */
-		ret = __intel_uc_reset_hw(dev_priv);
+		ret = __intel_uc_reset_hw(i915);
 		if (ret)
 			goto err_out;
 
-		if (USES_HUC(dev_priv)) {
+		if (USES_HUC(i915)) {
 			ret = intel_huc_fw_upload(huc);
 			if (ret)
 				goto err_out;
@@ -392,24 +391,24 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	if (ret)
 		goto err_log_capture;
 
-	if (USES_HUC(dev_priv)) {
+	if (USES_HUC(i915)) {
 		ret = intel_huc_auth(huc);
 		if (ret)
 			goto err_communication;
 	}
 
-	if (USES_GUC_SUBMISSION(dev_priv)) {
+	if (USES_GUC_SUBMISSION(i915)) {
 		ret = intel_guc_submission_enable(guc);
 		if (ret)
 			goto err_communication;
 	}
 
-	dev_info(dev_priv->drm.dev, "GuC firmware version %u.%u\n",
+	dev_info(i915->drm.dev, "GuC firmware version %u.%u\n",
 		 guc->fw.major_ver_found, guc->fw.minor_ver_found);
-	dev_info(dev_priv->drm.dev, "GuC submission %s\n",
-		 enableddisabled(USES_GUC_SUBMISSION(dev_priv)));
-	dev_info(dev_priv->drm.dev, "HuC %s\n",
-		 enableddisabled(USES_HUC(dev_priv)));
+	dev_info(i915->drm.dev, "GuC submission %s\n",
+		 enableddisabled(USES_GUC_SUBMISSION(i915)));
+	dev_info(i915->drm.dev, "HuC %s\n",
+		 enableddisabled(USES_HUC(i915)));
 
 	return 0;
 
@@ -428,20 +427,20 @@ err_out:
 	if (GEM_WARN_ON(ret == -EIO))
 		ret = -EINVAL;
 
-	dev_err(dev_priv->drm.dev, "GuC initialization failed %d\n", ret);
+	dev_err(i915->drm.dev, "GuC initialization failed %d\n", ret);
 	return ret;
 }
 
-void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
+void intel_uc_fini_hw(struct drm_i915_private *i915)
 {
-	struct intel_guc *guc = &dev_priv->guc;
+	struct intel_guc *guc = &i915->guc;
 
-	if (!USES_GUC(dev_priv))
+	if (!USES_GUC(i915))
 		return;
 
-	GEM_BUG_ON(!HAS_GUC(dev_priv));
+	GEM_BUG_ON(!HAS_GUC(i915));
 
-	if (USES_GUC_SUBMISSION(dev_priv))
+	if (USES_GUC_SUBMISSION(i915))
 		intel_guc_submission_disable(guc);
 
 	guc_disable_communication(guc);
-- 
cgit v1.2.3


From 6b1c5eaf5cfd994bc364ce367ab4cd1f572cc476 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 25 May 2018 17:50:08 +0200
Subject: drm/sun4i: mark PM functions as __maybe_unused

Disabling CONFIG_PM produces a compile time warning when these
functions are not referenced:

drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c:1072:12: error: 'sun6i_dsi_runtime_suspend' defined but not used [-Werror=unused-function]
 static int sun6i_dsi_runtime_suspend(struct device *dev)
            ^~~~~~~~~~~~~~~~~~~~~~~~~
drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c:1043:12: error: 'sun6i_dsi_runtime_resume' defined but not used [-Werror=unused-function]
 static int sun6i_dsi_runtime_resume(struct device *dev)
            ^~~~~~~~~~~~~~~~~~~~~~~~

Fixes: 133add5b5ad4 ("drm/sun4i: Add Allwinner A31 MIPI-DSI controller support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525155030.3667352-1-arnd@arndb.de
---
 drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index bfbf761f0c1d..d4e7d16a2514 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -1040,7 +1040,7 @@ static int sun6i_dsi_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int sun6i_dsi_runtime_resume(struct device *dev)
+static int __maybe_unused sun6i_dsi_runtime_resume(struct device *dev)
 {
 	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
 
@@ -1069,7 +1069,7 @@ static int sun6i_dsi_runtime_resume(struct device *dev)
 	return 0;
 }
 
-static int sun6i_dsi_runtime_suspend(struct device *dev)
+static int __maybe_unused sun6i_dsi_runtime_suspend(struct device *dev)
 {
 	struct sun6i_dsi *dsi = dev_get_drvdata(dev);
 
-- 
cgit v1.2.3


From d104328ce352eec23e608dab875f2ad2fead60fb Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 24 May 2018 11:01:05 +0200
Subject: drm/fb-helper: Fix typo on kerneldoc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Copypasta mistake.

Fixes: 742547b73d27 ("drm/fb_helper: Create wrappers for blit, copyarea and fillrect funcs")
Cc: Archit Taneja <architt@codeaurora.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: David Airlie <airlied@linux.ie>
Cc: dri-devel@lists.freedesktop.org
Acked-by: Noralf Trønnes <noralf@tronnes.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524090105.21196-1-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/drm_fb_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 2ee1eaa66188..91f051e5e130 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -1164,7 +1164,7 @@ EXPORT_SYMBOL(drm_fb_helper_sys_imageblit);
  * @info: fbdev registered by the helper
  * @rect: info about rectangle to fill
  *
- * A wrapper around cfb_imageblit implemented by fbdev core
+ * A wrapper around cfb_fillrect implemented by fbdev core
  */
 void drm_fb_helper_cfb_fillrect(struct fb_info *info,
 				const struct fb_fillrect *rect)
-- 
cgit v1.2.3


From 6c2590914cffa9212874da5c1eddfcfe6553bda6 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Thu, 10 May 2018 19:12:04 +0530
Subject: gpu: drm: drm_vm: Adding new typedef vm_fault_t

Use new return type vm_fault_t for fault handler. For
now, this is just documenting that the function returns
a VM_FAULT value rather than an errno. Once all instances
are converted, vm_fault_t will become a distinct type.

commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180510134203.GA25166@jordon-HP-15-Notebook-PC
---
 drivers/gpu/drm/drm_vm.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_vm.c b/drivers/gpu/drm/drm_vm.c
index 2660543ad86a..c3301046dfaa 100644
--- a/drivers/gpu/drm/drm_vm.c
+++ b/drivers/gpu/drm/drm_vm.c
@@ -100,7 +100,7 @@ static pgprot_t drm_dma_prot(uint32_t map_type, struct vm_area_struct *vma)
  * map, get the page, increment the use count and return it.
  */
 #if IS_ENABLED(CONFIG_AGP)
-static int drm_vm_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_file *priv = vma->vm_file->private_data;
@@ -173,7 +173,7 @@ vm_fault_error:
 	return VM_FAULT_SIGBUS;	/* Disallow mremap */
 }
 #else
-static int drm_vm_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_fault(struct vm_fault *vmf)
 {
 	return VM_FAULT_SIGBUS;
 }
@@ -189,7 +189,7 @@ static int drm_vm_fault(struct vm_fault *vmf)
  * Get the mapping, find the real physical page to map, get the page, and
  * return it.
  */
-static int drm_vm_shm_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_shm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_local_map *map = vma->vm_private_data;
@@ -291,7 +291,7 @@ static void drm_vm_shm_close(struct vm_area_struct *vma)
  *
  * Determine the page number from the page offset and get it from drm_device_dma::pagelist.
  */
-static int drm_vm_dma_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_dma_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_file *priv = vma->vm_file->private_data;
@@ -326,7 +326,7 @@ static int drm_vm_dma_fault(struct vm_fault *vmf)
  *
  * Determine the map offset from the page offset and get it from drm_sg_mem::pagelist.
  */
-static int drm_vm_sg_fault(struct vm_fault *vmf)
+static vm_fault_t drm_vm_sg_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_local_map *map = vma->vm_private_data;
-- 
cgit v1.2.3


From 3c7ab27896804ebda7499969befbdbfbc4edaa53 Mon Sep 17 00:00:00 2001
From: Oscar Mateo <oscar.mateo@intel.com>
Date: Fri, 25 May 2018 15:05:29 -0700
Subject: drm/i915/icl: WaDisableImprovedTdlClkGating

Revert to the legacy implementation.

v2: GEN7_ROW_CHICKEN2 is masked
v3:
  - Rebased
  - Renamed to Wa_2006611047
  - A0 and B0 only
v4:
  - Add spaces around '<<' (and fix the surrounding code as well)
  - Mark the WA as pre-prod
v5: Rebased on top of the WA refactoring
v6: Added References (Mika)
v7: Fixed in B0

References: HSDES#2006611047
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527285939-20113-2-git-send-email-oscar.mateo@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h          | 5 +++--
 drivers/gpu/drm/i915/intel_workarounds.c | 7 +++++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6953419881c4..4eb159faf06d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8328,8 +8328,9 @@ enum {
 
 #define GEN7_ROW_CHICKEN2		_MMIO(0xe4f4)
 #define GEN7_ROW_CHICKEN2_GT2		_MMIO(0xf4f4)
-#define   DOP_CLOCK_GATING_DISABLE	(1<<0)
-#define   PUSH_CONSTANT_DEREF_DISABLE	(1<<8)
+#define   DOP_CLOCK_GATING_DISABLE	(1 << 0)
+#define   PUSH_CONSTANT_DEREF_DISABLE	(1 << 8)
+#define   GEN11_TDL_CLOCK_GATING_FIX_DISABLE	(1 << 1)
 
 #define HSW_ROW_CHICKEN3		_MMIO(0xe49c)
 #define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index cea57104de13..04aa88506edc 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -463,6 +463,13 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
 	 */
 	WA_SET_BIT_MASKED(ICL_HDC_MODE, HDC_FORCE_NON_COHERENT);
 
+	/* Wa_2006611047:icl (pre-prod)
+	 * Formerly known as WaDisableImprovedTdlClkGating
+	 */
+	if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0))
+		WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
+				  GEN11_TDL_CLOCK_GATING_FIX_DISABLE);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From f63c7b4880aabaf7423b301be438bd47a6720ddc Mon Sep 17 00:00:00 2001
From: Oscar Mateo <oscar.mateo@intel.com>
Date: Fri, 25 May 2018 15:05:30 -0700
Subject: drm/i915/icl: WaEnableStateCacheRedirectToCS

Redirects the state cache to the CS Command buffer section for
performance reasons.

v2: Rebased
v3: Rebased on top of the WA refactoring
v3: Added References (Mika)

References: HSDES#1604325460
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527285939-20113-3-git-send-email-oscar.mateo@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h          | 1 +
 drivers/gpu/drm/i915/intel_workarounds.c | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4eb159faf06d..924b9a6b1cd0 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7227,6 +7227,7 @@ enum {
 #define  DISABLE_PIXEL_MASK_CAMMING		(1<<14)
 
 #define GEN9_SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
+#define   GEN11_STATE_CACHE_REDIRECT_TO_CS	(1 << 11)
 
 #define GEN7_L3SQCREG1				_MMIO(0xB010)
 #define  VLV_B0_WA_L3SQCREG1_VALUE		0x00D30000
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 04aa88506edc..1d298035b1d2 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -470,6 +470,10 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
 		WA_SET_BIT_MASKED(GEN7_ROW_CHICKEN2,
 				  GEN11_TDL_CLOCK_GATING_FIX_DISABLE);
 
+	/* WaEnableStateCacheRedirectToCS:icl */
+	WA_SET_BIT_MASKED(GEN9_SLICE_COMMON_ECO_CHICKEN1,
+			  GEN11_STATE_CACHE_REDIRECT_TO_CS);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From b1f88820f4d7ea5b98f331abb50588cdc77b248a Mon Sep 17 00:00:00 2001
From: Oscar Mateo <oscar.mateo@intel.com>
Date: Fri, 25 May 2018 15:05:31 -0700
Subject: drm/i915/icl: Wa_2006665173

Disable blend embellishment in RCC.

Also, some other registers style fixed in passing.

v2: Rebased on top of the WA refactoring
v3: Added References (Mika)
v4:
  - Fixed in B0
  - Mentioned style fixes in commit message

References: HSDES#2006665173
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527285939-20113-4-git-send-email-oscar.mateo@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h          | 18 +++++++++++-------
 drivers/gpu/drm/i915/intel_workarounds.c |  5 +++++
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 924b9a6b1cd0..6e88c6bf3911 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7211,13 +7211,17 @@ enum {
 
 /* GEN7 chicken */
 #define GEN7_COMMON_SLICE_CHICKEN1		_MMIO(0x7010)
-# define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1<<10) | (1<<26))
-# define GEN9_RHWO_OPTIMIZATION_DISABLE		(1<<14)
-#define COMMON_SLICE_CHICKEN2			_MMIO(0x7014)
-# define GEN9_PBE_COMPRESSED_HASH_SELECTION	(1<<13)
-# define GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE (1<<12)
-# define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION (1<<8)
-# define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE	(1<<0)
+  #define GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC	((1 << 10) | (1 << 26))
+  #define GEN9_RHWO_OPTIMIZATION_DISABLE	(1 << 14)
+
+#define COMMON_SLICE_CHICKEN2					_MMIO(0x7014)
+  #define GEN9_PBE_COMPRESSED_HASH_SELECTION			(1 << 13)
+  #define GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE	(1 << 12)
+  #define GEN8_SBE_DISABLE_REPLAY_BUF_OPTIMIZATION		(1 << 8)
+  #define GEN8_CSC2_SBE_VUE_CACHE_CONSERVATIVE			(1 << 0)
+
+#define GEN11_COMMON_SLICE_CHICKEN3		_MMIO(0x7304)
+  #define GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC	(1 << 11)
 
 #define HIZ_CHICKEN					_MMIO(0x7018)
 # define CHV_HZ_8X8_MODE_IN_1X				(1<<15)
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 1d298035b1d2..33a1a0cd2a84 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -474,6 +474,11 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
 	WA_SET_BIT_MASKED(GEN9_SLICE_COMMON_ECO_CHICKEN1,
 			  GEN11_STATE_CACHE_REDIRECT_TO_CS);
 
+	/* Wa_2006665173:icl (pre-prod) */
+	if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0))
+		WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
+				  GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 0bf059f3532bb39c52d917142206a8554fc2f1c5 Mon Sep 17 00:00:00 2001
From: Oscar Mateo <oscar.mateo@intel.com>
Date: Fri, 25 May 2018 15:05:32 -0700
Subject: drm/i915/icl: WaEnableFloatBlendOptimization

Enables blend optimization for floating point RTs

v2: Rebased on top of the WA refactoring
v3: Added References (Mika)

References: HSDES#1406393558
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527285939-20113-5-git-send-email-oscar.mateo@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h          | 3 +++
 drivers/gpu/drm/i915/intel_workarounds.c | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 6e88c6bf3911..f123c3e821fc 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2663,6 +2663,9 @@ enum i915_power_well_id {
 #define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1<<6)
 #define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1<<1)
 
+#define GEN10_CACHE_MODE_SS			_MMIO(0xe420)
+#define   FLOAT_BLEND_OPTIMIZATION_ENABLE	(1 << 4)
+
 #define GEN6_BLITTER_ECOSKPD	_MMIO(0x221d0)
 #define   GEN6_BLITTER_LOCK_SHIFT			16
 #define   GEN6_BLITTER_FBC_NOTIFY			(1<<3)
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 33a1a0cd2a84..e9c00b004c09 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -479,6 +479,9 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
 		WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 				  GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC);
 
+	/* WaEnableFloatBlendOptimization:icl */
+	WA_SET_BIT_MASKED(GEN10_CACHE_MODE_SS, FLOAT_BLEND_OPTIMIZATION_ENABLE);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 4ece66b149a38c7b52ead463fb608f2aad39c20e Mon Sep 17 00:00:00 2001
From: Oscar Mateo <oscar.mateo@intel.com>
Date: Fri, 25 May 2018 15:05:39 -0700
Subject: drm/i915/icl: Wa_1406463099

Prevents an error in the GAM unit. Also known as WaGamTlbPendError

References: HSDES#1406463099
References: HSDES#1406465643
Signed-off-by: Oscar Mateo <oscar.mateo@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527285939-20113-12-git-send-email-oscar.mateo@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h          | 5 +++--
 drivers/gpu/drm/i915/intel_workarounds.c | 7 +++++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f123c3e821fc..f238b7b33cd9 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2306,8 +2306,9 @@ enum i915_power_well_id {
 #define   GAMW_ECO_ENABLE_64K_IPS_FIELD 0xF
 
 #define GAMT_CHKN_BIT_REG	_MMIO(0x4ab8)
-#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1<<28)
-#define   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT	(1<<24)
+#define   GAMT_CHKN_DISABLE_L3_COH_PIPE			(1 << 31)
+#define   GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING	(1 << 28)
+#define   GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT	(1 << 24)
 
 #if 0
 #define PRB0_TAIL	_MMIO(0x2030)
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index e9c00b004c09..b1ab56a1ec31 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -859,6 +859,13 @@ static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 		   PMFLUSHDONE_LNICRSDROP |
 		   PMFLUSH_GAPL3UNBLOCK |
 		   PMFLUSHDONE_LNEBLK);
+
+	/* Wa_1406463099:icl
+	 * Formerly known as WaGamTlbPendError
+	 */
+	I915_WRITE(GAMT_CHKN_BIT_REG,
+		   I915_READ(GAMT_CHKN_BIT_REG) |
+		   GAMT_CHKN_DISABLE_L3_COH_PIPE);
 }
 
 void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From bccfaffb76a8974ca275b99e9293a2594ae75f31 Mon Sep 17 00:00:00 2001
From: Lukasz Majewski <lukma@denx.de>
Date: Mon, 14 May 2018 21:08:49 +0200
Subject: display: panel: Add AUO g070vvn01 display support (800x480)

This commit adds support for AUO's 7.0" display.

Signed-off-by: Lukasz Majewski <lukma@denx.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180514190849.18723-1-lukma@denx.de
---
 .../bindings/display/panel/auo,g070vvn01.txt       | 29 ++++++++++++++++++++
 drivers/gpu/drm/panel/panel-simple.c               | 31 ++++++++++++++++++++++
 2 files changed, 60 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/auo,g070vvn01.txt

diff --git a/Documentation/devicetree/bindings/display/panel/auo,g070vvn01.txt b/Documentation/devicetree/bindings/display/panel/auo,g070vvn01.txt
new file mode 100644
index 000000000000..49e4105378f6
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/auo,g070vvn01.txt
@@ -0,0 +1,29 @@
+AU Optronics Corporation 7.0" FHD (800 x 480) TFT LCD panel
+
+Required properties:
+- compatible: should be "auo,g070vvn01"
+- backlight: phandle of the backlight device attached to the panel
+- power-supply: single regulator to provide the supply voltage
+
+Required nodes:
+- port: Parallel port mapping to connect this display
+
+This panel needs single power supply voltage. Its backlight is conntrolled
+via PWM signal.
+
+Example:
+--------
+
+Example device-tree definition when connected to iMX6Q based board
+
+	lcd_panel: lcd-panel {
+		compatible = "auo,g070vvn01";
+		backlight = <&backlight_lcd>;
+		power-supply = <&reg_display>;
+
+		port {
+			lcd_panel_in: endpoint {
+				remote-endpoint = <&lcd_display_out>;
+			};
+		};
+	};
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 964c261cfb78..ac6aaa174c0b 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -580,6 +580,34 @@ static const struct panel_desc auo_b133htn01 = {
 	},
 };
 
+static const struct display_timing auo_g070vvn01_timings = {
+	.pixelclock = { 33300000, 34209000, 45000000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 20, 40, 200 },
+	.hback_porch = { 87, 40, 1 },
+	.hsync_len = { 1, 48, 87 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 5, 13, 200 },
+	.vback_porch = { 31, 31, 29 },
+	.vsync_len = { 1, 1, 3 },
+};
+
+static const struct panel_desc auo_g070vvn01 = {
+	.timings = &auo_g070vvn01_timings,
+	.num_timings = 1,
+	.bpc = 8,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.delay = {
+		.prepare = 200,
+		.enable = 50,
+		.disable = 50,
+		.unprepare = 1000,
+	},
+};
+
 static const struct drm_display_mode auo_g104sn02_mode = {
 	.clock = 40000,
 	.hdisplay = 800,
@@ -2117,6 +2145,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "auo,b133xtn01",
 		.data = &auo_b133xtn01,
+	}, {
+		.compatible = "auo,g070vvn01",
+		.data = &auo_g070vvn01,
 	}, {
 		.compatible = "auo,g104sn02",
 		.data = &auo_g104sn02,
-- 
cgit v1.2.3


From a3db142829e68e2619207306a7b83e8ed47466a6 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@gmail.com>
Date: Thu, 24 May 2018 20:30:47 -0700
Subject: drm/i915/psr: Set idle frame count based on sink synchronization
 latency

DPCD 2009h "Synchronization latency in sink" has bits that tell us the
maximum number of frames sink can take to resynchronize to source timing
when exiting PSR. More importantly, as per eDP 1.4b, this is the "Minimum
number of frames following PSR exit that the Source device needs to
wait for PSR entry."

We currently use this value only to setup the number frames to wait before
PSR2 selective update. But, based on the above description it makes more
sense to use this to configure idle frames for both PSR1 and and PSR2. This
will ensure we wait the required number of frames before
activation whether it is PSR1 or PSR2.

The minimum number of idle frames remains 6, while allowing sink
synchronization latency and VBT to increase this value.

This also solves the flip-flop between sink and source frames that I
noticed on my Thinkpad X260 during PSR exit. This specific panel has a
value of 8h, which according to the spec means the "Source device must
wait for more than eight active frames after PSR exit before initiating PSR
entry. (In this case, should be provided by the panel supplier.)" VBT
however has a value of 0.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Jose Roberto de Souza <jose.souza@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525033047.7596-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index ebc483f06c6f..71dfe541740f 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -247,6 +247,8 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 		return;
 	}
 	dev_priv->psr.sink_support = true;
+	dev_priv->psr.sink_sync_latency =
+		intel_dp_get_sink_sync_latency(intel_dp);
 
 	if (INTEL_GEN(dev_priv) >= 9 &&
 	    (intel_dp->psr_dpcd[0] == DP_PSR2_WITH_Y_COORD_IS_SUPPORTED)) {
@@ -272,8 +274,6 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 		if (dev_priv->psr.sink_psr2_support) {
 			dev_priv->psr.colorimetry_support =
 				intel_dp_get_colorimetry_status(intel_dp);
-			dev_priv->psr.sink_sync_latency =
-				intel_dp_get_sink_sync_latency(intel_dp);
 		}
 	}
 }
@@ -370,21 +370,21 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp)
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 max_sleep_time = 0x1f;
+	u32 val = EDP_PSR_ENABLE;
 
-	uint32_t max_sleep_time = 0x1f;
-	/*
-	 * Let's respect VBT in case VBT asks a higher idle_frame value.
-	 * Let's use 6 as the minimum to cover all known cases including
-	 * the off-by-one issue that HW has in some cases. Also there are
-	 * cases where sink should be able to train
-	 * with the 5 or 6 idle patterns.
+	/* Let's use 6 as the minimum to cover all known cases including the
+	 * off-by-one issue that HW has in some cases.
 	 */
-	uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
-	uint32_t val = EDP_PSR_ENABLE;
+	int idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
 
-	val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
+	/* sink_sync_latency of 8 means source has to wait for more than 8
+	 * frames, we'll go with 9 frames for now
+	 */
+	idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1);
 	val |= idle_frames << EDP_PSR_IDLE_FRAME_SHIFT;
 
+	val |= max_sleep_time << EDP_PSR_MAX_SLEEP_TIME_SHIFT;
 	if (IS_HASWELL(dev_priv))
 		val |= EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES;
 
@@ -424,15 +424,15 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	/*
-	 * Let's respect VBT in case VBT asks a higher idle_frame value.
-	 * Let's use 6 as the minimum to cover all known cases including
-	 * the off-by-one issue that HW has in some cases. Also there are
-	 * cases where sink should be able to train
-	 * with the 5 or 6 idle patterns.
+	u32 val;
+
+	/* Let's use 6 as the minimum to cover all known cases including the
+	 * off-by-one issue that HW has in some cases.
 	 */
-	uint32_t idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
-	u32 val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT;
+	int idle_frames = max(6, dev_priv->vbt.psr.idle_frames);
+
+	idle_frames = max(idle_frames, dev_priv->psr.sink_sync_latency + 1);
+	val = idle_frames << EDP_PSR2_IDLE_FRAME_SHIFT;
 
 	/* FIXME: selective update is probably totally broken because it doesn't
 	 * mesh at all with our frontbuffer tracking. And the hw alone isn't
-- 
cgit v1.2.3


From cc7cc5343584d90e74b7c929ff2c9a2ec8b49cfe Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 29 May 2018 14:29:18 +0100
Subject: drm/i915: Remove stale asserts from i915_gem_find_active_request()

Since we use i915_gem_find_active_request() from inside
intel_engine_dump() and may call that at any time, we do not guarantee
that the engine is paused nor that the signal kthreads and irq handler
are suspended, so we cannot assert that the breadcrumb doesn't advance
and that the irq hasn't happened on another CPU signaling the request we
believe to be idle.

The second assert removed (that request->engine == engine) remains
valid, but is now more rigorously checked during retirement.

Fixes: f636edb214a5 ("drm/i915: Make i915_engine_info pretty printer to standalone")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180529132922.6831-1-chris@chris-wilson.co.uk
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 05f44ca35a06..530d6d0109b4 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2972,23 +2972,22 @@ i915_gem_find_active_request(struct intel_engine_cs *engine)
 	struct i915_request *request, *active = NULL;
 	unsigned long flags;
 
-	/* We are called by the error capture and reset at a random
-	 * point in time. In particular, note that neither is crucially
-	 * ordered with an interrupt. After a hang, the GPU is dead and we
-	 * assume that no more writes can happen (we waited long enough for
-	 * all writes that were in transaction to be flushed) - adding an
+	/*
+	 * We are called by the error capture, reset and to dump engine
+	 * state at random points in time. In particular, note that neither is
+	 * crucially ordered with an interrupt. After a hang, the GPU is dead
+	 * and we assume that no more writes can happen (we waited long enough
+	 * for all writes that were in transaction to be flushed) - adding an
 	 * extra delay for a recent interrupt is pointless. Hence, we do
 	 * not need an engine->irq_seqno_barrier() before the seqno reads.
+	 * At all other times, we must assume the GPU is still running, but
+	 * we only care about the snapshot of this moment.
 	 */
 	spin_lock_irqsave(&engine->timeline.lock, flags);
 	list_for_each_entry(request, &engine->timeline.requests, link) {
 		if (__i915_request_completed(request, request->global_seqno))
 			continue;
 
-		GEM_BUG_ON(request->engine != engine);
-		GEM_BUG_ON(test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
-				    &request->fence.flags));
-
 		active = request;
 		break;
 	}
-- 
cgit v1.2.3


From a38189c5f79d486cb6193a3965dad98d1b0a17b2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 18 May 2018 19:21:59 +0300
Subject: drm/i915: Promote .format_mod_supported() to the lead role
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Up to now we've used the plane's modifier list as the primary
source of information for which modifiers are supported by a
given plane. In order to allow auxiliary metadata to be embedded
within the bits of the modifier we need to stop doing that.

Thus we have to make .format_mod_supported() aware of the plane's
capabilities and gracefully deal with any modifier being passed
in directly from userspace.

v2: Rebase after NV12
    Simplify

Cc: Eric Anholt <eric@anholt.net>
References: https://lists.freedesktop.org/archives/dri-devel/2018-March/169782.html
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180518162159.30305-1-ville.syrjala@linux.intel.com
Reviewed-by: Eric Anholt <eric@anholt.net>
---
 drivers/gpu/drm/i915/intel_display.c | 116 +++++++++++++++++++---------
 drivers/gpu/drm/i915/intel_drv.h     |   1 +
 drivers/gpu/drm/i915/intel_sprite.c  | 141 ++++++++++++++++++++++++++---------
 3 files changed, 186 insertions(+), 72 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 020900e08d42..00b030b08a6a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13067,8 +13067,17 @@ void intel_plane_destroy(struct drm_plane *plane)
 	kfree(to_intel_plane(plane));
 }
 
-static bool i8xx_mod_supported(uint32_t format, uint64_t modifier)
+static bool i8xx_plane_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_C8:
 	case DRM_FORMAT_RGB565:
@@ -13081,8 +13090,17 @@ static bool i8xx_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool i965_mod_supported(uint32_t format, uint64_t modifier)
+static bool i965_plane_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_C8:
 	case DRM_FORMAT_RGB565:
@@ -13097,8 +13115,26 @@ static bool i965_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool skl_mod_supported(uint32_t format, uint64_t modifier)
+static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
+					   u32 format, u64 modifier)
 {
+	struct intel_plane *plane = to_intel_plane(_plane);
+
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Yf_TILED:
+		break;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		if (!plane->has_ccs)
+			return false;
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
@@ -13129,38 +13165,36 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool intel_primary_plane_format_mod_supported(struct drm_plane *plane,
-						     uint32_t format,
-						     uint64_t modifier)
+static bool intel_cursor_format_mod_supported(struct drm_plane *_plane,
+					      u32 format, u64 modifier)
 {
-	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-
-	if (WARN_ON(modifier == DRM_FORMAT_MOD_INVALID))
-		return false;
-
-	if ((modifier >> 56) != DRM_FORMAT_MOD_VENDOR_INTEL &&
-	    modifier != DRM_FORMAT_MOD_LINEAR)
-		return false;
-
-	if (INTEL_GEN(dev_priv) >= 9)
-		return skl_mod_supported(format, modifier);
-	else if (INTEL_GEN(dev_priv) >= 4)
-		return i965_mod_supported(format, modifier);
-	else
-		return i8xx_mod_supported(format, modifier);
+	return modifier == DRM_FORMAT_MOD_LINEAR &&
+		format == DRM_FORMAT_ARGB8888;
 }
 
-static bool intel_cursor_plane_format_mod_supported(struct drm_plane *plane,
-						    uint32_t format,
-						    uint64_t modifier)
-{
-	if (WARN_ON(modifier == DRM_FORMAT_MOD_INVALID))
-		return false;
+static struct drm_plane_funcs skl_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = skl_plane_format_mod_supported,
+};
 
-	return modifier == DRM_FORMAT_MOD_LINEAR && format == DRM_FORMAT_ARGB8888;
-}
+static struct drm_plane_funcs i965_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = i965_plane_format_mod_supported,
+};
 
-static struct drm_plane_funcs intel_plane_funcs = {
+static struct drm_plane_funcs i8xx_plane_funcs = {
 	.update_plane = drm_atomic_helper_update_plane,
 	.disable_plane = drm_atomic_helper_disable_plane,
 	.destroy = intel_plane_destroy,
@@ -13168,7 +13202,7 @@ static struct drm_plane_funcs intel_plane_funcs = {
 	.atomic_set_property = intel_plane_atomic_set_property,
 	.atomic_duplicate_state = intel_plane_duplicate_state,
 	.atomic_destroy_state = intel_plane_destroy_state,
-	.format_mod_supported = intel_primary_plane_format_mod_supported,
+	.format_mod_supported = i8xx_plane_format_mod_supported,
 };
 
 static int
@@ -13293,7 +13327,7 @@ static const struct drm_plane_funcs intel_cursor_plane_funcs = {
 	.atomic_set_property = intel_plane_atomic_set_property,
 	.atomic_duplicate_state = intel_plane_duplicate_state,
 	.atomic_destroy_state = intel_plane_destroy_state,
-	.format_mod_supported = intel_cursor_plane_format_mod_supported,
+	.format_mod_supported = intel_cursor_format_mod_supported,
 };
 
 static bool i9xx_plane_has_fbc(struct drm_i915_private *dev_priv,
@@ -13327,6 +13361,7 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 {
 	struct intel_plane *primary = NULL;
 	struct intel_plane_state *state = NULL;
+	const struct drm_plane_funcs *plane_funcs;
 	const uint32_t *intel_primary_formats;
 	unsigned int supported_rotations;
 	unsigned int num_formats;
@@ -13382,10 +13417,13 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 	primary->check_plane = intel_check_primary_plane;
 
 	if (INTEL_GEN(dev_priv) >= 9) {
+		primary->has_ccs = skl_plane_has_ccs(dev_priv, pipe,
+						     PLANE_PRIMARY);
+
 		intel_primary_formats = skl_primary_formats;
 		num_formats = ARRAY_SIZE(skl_primary_formats);
 
-		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_PRIMARY))
+		if (primary->has_ccs)
 			modifiers = skl_format_modifiers_ccs;
 		else
 			modifiers = skl_format_modifiers_noccs;
@@ -13393,6 +13431,8 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		primary->update_plane = skl_update_plane;
 		primary->disable_plane = skl_disable_plane;
 		primary->get_hw_state = skl_plane_get_hw_state;
+
+		plane_funcs = &skl_plane_funcs;
 	} else if (INTEL_GEN(dev_priv) >= 4) {
 		intel_primary_formats = i965_primary_formats;
 		num_formats = ARRAY_SIZE(i965_primary_formats);
@@ -13401,6 +13441,8 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		primary->update_plane = i9xx_update_plane;
 		primary->disable_plane = i9xx_disable_plane;
 		primary->get_hw_state = i9xx_plane_get_hw_state;
+
+		plane_funcs = &i965_plane_funcs;
 	} else {
 		intel_primary_formats = i8xx_primary_formats;
 		num_formats = ARRAY_SIZE(i8xx_primary_formats);
@@ -13409,25 +13451,27 @@ intel_primary_plane_create(struct drm_i915_private *dev_priv, enum pipe pipe)
 		primary->update_plane = i9xx_update_plane;
 		primary->disable_plane = i9xx_disable_plane;
 		primary->get_hw_state = i9xx_plane_get_hw_state;
+
+		plane_funcs = &i8xx_plane_funcs;
 	}
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		ret = drm_universal_plane_init(&dev_priv->drm, &primary->base,
-					       0, &intel_plane_funcs,
+					       0, plane_funcs,
 					       intel_primary_formats, num_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "plane 1%c", pipe_name(pipe));
 	else if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
 		ret = drm_universal_plane_init(&dev_priv->drm, &primary->base,
-					       0, &intel_plane_funcs,
+					       0, plane_funcs,
 					       intel_primary_formats, num_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
 					       "primary %c", pipe_name(pipe));
 	else
 		ret = drm_universal_plane_init(&dev_priv->drm, &primary->base,
-					       0, &intel_plane_funcs,
+					       0, plane_funcs,
 					       intel_primary_formats, num_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_PRIMARY,
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 6bd7bff0947a..3c7921ecf6f4 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -945,6 +945,7 @@ struct intel_plane {
 	enum pipe pipe;
 	bool can_scale;
 	bool has_fbc;
+	bool has_ccs;
 	int max_downscale;
 	uint32_t frontbuffer_bit;
 
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 970015dcc6f1..04428cea8f3b 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -1197,8 +1197,17 @@ static const uint64_t skl_plane_format_modifiers_ccs[] = {
 	DRM_FORMAT_MOD_INVALID
 };
 
-static bool g4x_mod_supported(uint32_t format, uint64_t modifier)
+static bool g4x_sprite_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_YUYV:
@@ -1214,8 +1223,17 @@ static bool g4x_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool snb_mod_supported(uint32_t format, uint64_t modifier)
+static bool snb_sprite_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
@@ -1232,8 +1250,17 @@ static bool snb_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool vlv_mod_supported(uint32_t format, uint64_t modifier)
+static bool vlv_sprite_format_mod_supported(struct drm_plane *_plane,
+					    u32 format, u64 modifier)
 {
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_RGB565:
 	case DRM_FORMAT_ABGR8888:
@@ -1255,8 +1282,26 @@ static bool vlv_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool skl_mod_supported(uint32_t format, uint64_t modifier)
+static bool skl_plane_format_mod_supported(struct drm_plane *_plane,
+					   u32 format, u64 modifier)
 {
+	struct intel_plane *plane = to_intel_plane(_plane);
+
+	switch (modifier) {
+	case DRM_FORMAT_MOD_LINEAR:
+	case I915_FORMAT_MOD_X_TILED:
+	case I915_FORMAT_MOD_Y_TILED:
+	case I915_FORMAT_MOD_Yf_TILED:
+		break;
+	case I915_FORMAT_MOD_Y_TILED_CCS:
+	case I915_FORMAT_MOD_Yf_TILED_CCS:
+		if (!plane->has_ccs)
+			return false;
+		break;
+	default:
+		return false;
+	}
+
 	switch (format) {
 	case DRM_FORMAT_XRGB8888:
 	case DRM_FORMAT_XBGR8888:
@@ -1287,38 +1332,48 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 	}
 }
 
-static bool intel_sprite_plane_format_mod_supported(struct drm_plane *plane,
-                                                    uint32_t format,
-                                                    uint64_t modifier)
-{
-	struct drm_i915_private *dev_priv = to_i915(plane->dev);
-
-	if (WARN_ON(modifier == DRM_FORMAT_MOD_INVALID))
-		return false;
+static const struct drm_plane_funcs g4x_sprite_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = g4x_sprite_format_mod_supported,
+};
 
-	if ((modifier >> 56) != DRM_FORMAT_MOD_VENDOR_INTEL &&
-	    modifier != DRM_FORMAT_MOD_LINEAR)
-		return false;
+static const struct drm_plane_funcs snb_sprite_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = snb_sprite_format_mod_supported,
+};
 
-	if (INTEL_GEN(dev_priv) >= 9)
-		return skl_mod_supported(format, modifier);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_mod_supported(format, modifier);
-	else if (INTEL_GEN(dev_priv) >= 6)
-		return snb_mod_supported(format, modifier);
-	else
-		return g4x_mod_supported(format, modifier);
-}
+static const struct drm_plane_funcs vlv_sprite_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = vlv_sprite_format_mod_supported,
+};
 
-static const struct drm_plane_funcs intel_sprite_plane_funcs = {
-        .update_plane = drm_atomic_helper_update_plane,
-        .disable_plane = drm_atomic_helper_disable_plane,
-        .destroy = intel_plane_destroy,
-        .atomic_get_property = intel_plane_atomic_get_property,
-        .atomic_set_property = intel_plane_atomic_set_property,
-        .atomic_duplicate_state = intel_plane_duplicate_state,
-        .atomic_destroy_state = intel_plane_destroy_state,
-        .format_mod_supported = intel_sprite_plane_format_mod_supported,
+static const struct drm_plane_funcs skl_plane_funcs = {
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = skl_plane_format_mod_supported,
 };
 
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
@@ -1344,6 +1399,7 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 {
 	struct intel_plane *intel_plane = NULL;
 	struct intel_plane_state *state = NULL;
+	const struct drm_plane_funcs *plane_funcs;
 	unsigned long possible_crtcs;
 	const uint32_t *plane_formats;
 	const uint64_t *modifiers;
@@ -1368,6 +1424,9 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		intel_plane->can_scale = true;
 		state->scaler_id = -1;
 
+		intel_plane->has_ccs = skl_plane_has_ccs(dev_priv, pipe,
+							 PLANE_SPRITE0 + plane);
+
 		intel_plane->update_plane = skl_update_plane;
 		intel_plane->disable_plane = skl_disable_plane;
 		intel_plane->get_hw_state = skl_plane_get_hw_state;
@@ -1375,10 +1434,12 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane_formats = skl_plane_formats;
 		num_plane_formats = ARRAY_SIZE(skl_plane_formats);
 
-		if (skl_plane_has_ccs(dev_priv, pipe, PLANE_SPRITE0 + plane))
+		if (intel_plane->has_ccs)
 			modifiers = skl_plane_format_modifiers_ccs;
 		else
 			modifiers = skl_plane_format_modifiers_noccs;
+
+		plane_funcs = &skl_plane_funcs;
 	} else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		intel_plane->can_scale = false;
 		intel_plane->max_downscale = 1;
@@ -1390,6 +1451,8 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane_formats = vlv_plane_formats;
 		num_plane_formats = ARRAY_SIZE(vlv_plane_formats);
 		modifiers = i9xx_plane_format_modifiers;
+
+		plane_funcs = &vlv_sprite_funcs;
 	} else if (INTEL_GEN(dev_priv) >= 7) {
 		if (IS_IVYBRIDGE(dev_priv)) {
 			intel_plane->can_scale = true;
@@ -1406,6 +1469,8 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		plane_formats = snb_plane_formats;
 		num_plane_formats = ARRAY_SIZE(snb_plane_formats);
 		modifiers = i9xx_plane_format_modifiers;
+
+		plane_funcs = &snb_sprite_funcs;
 	} else {
 		intel_plane->can_scale = true;
 		intel_plane->max_downscale = 16;
@@ -1418,9 +1483,13 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 		if (IS_GEN6(dev_priv)) {
 			plane_formats = snb_plane_formats;
 			num_plane_formats = ARRAY_SIZE(snb_plane_formats);
+
+			plane_funcs = &snb_sprite_funcs;
 		} else {
 			plane_formats = g4x_plane_formats;
 			num_plane_formats = ARRAY_SIZE(g4x_plane_formats);
+
+			plane_funcs = &g4x_sprite_funcs;
 		}
 	}
 
@@ -1447,14 +1516,14 @@ intel_sprite_plane_create(struct drm_i915_private *dev_priv,
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		ret = drm_universal_plane_init(&dev_priv->drm, &intel_plane->base,
-					       possible_crtcs, &intel_sprite_plane_funcs,
+					       possible_crtcs, plane_funcs,
 					       plane_formats, num_plane_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_OVERLAY,
 					       "plane %d%c", plane + 2, pipe_name(pipe));
 	else
 		ret = drm_universal_plane_init(&dev_priv->drm, &intel_plane->base,
-					       possible_crtcs, &intel_sprite_plane_funcs,
+					       possible_crtcs, plane_funcs,
 					       plane_formats, num_plane_formats,
 					       modifiers,
 					       DRM_PLANE_TYPE_OVERLAY,
-- 
cgit v1.2.3


From 9d570dbfc095de08e401d6a627c9c212ab7aaa80 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Wed, 30 May 2018 15:00:51 -0700
Subject: drm/i915: Update DRIVER_DATE to 20180530

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 487922f88b76..32a65de7222d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -85,8 +85,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180514"
-#define DRIVER_TIMESTAMP	1526300884
+#define DRIVER_DATE		"20180530"
+#define DRIVER_TIMESTAMP	1527717651
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
-- 
cgit v1.2.3


From d6cae4aa30ce551dfa2872f793f64d39719da6b7 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Wed, 16 May 2018 10:50:38 +0200
Subject: drm/i915: Call intel_opregion_notify_encoder in
 intel_sanitize_encoder, v2.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Normally this is called on a modeset, but the call is missing when
we inherit the mode from the BIOS, so make sure it's called somewhere
in hardware readout.

Changes since v1:
- Unconditionally call intel_opregion_notify_encoder. (Ville)

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180516085038.36785-1-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 8d4c9e249c44..da251ff6aca9 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15251,6 +15251,9 @@ static void intel_sanitize_encoder(struct intel_encoder *encoder)
 		connector->base.dpms = DRM_MODE_DPMS_OFF;
 		connector->base.encoder = NULL;
 	}
+
+	/* notify opregion of the sanitized encoder state */
+	intel_opregion_notify_encoder(encoder, connector && has_active_crtc);
 }
 
 void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From 8fb756dfa273bcb42bdaff65baae83548b6c326d Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Fri, 16 Mar 2018 15:04:33 -0700
Subject: drm: Trust format_mod_supported() when it OKs a plane modifier.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For parameterized modifiers (Broadcom's SAND and UIF), we need to
allow the parameter fields to be filled in, while exposing only the
variant of the modifier with the parameter unfilled in the internal
arrays and the format blob.

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-1-eric@anholt.net
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/drm_plane.c | 23 ++++++++++++-----------
 include/drm/drm_plane.h     |  5 ++++-
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 035054455301..7ce88dff871d 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -561,19 +561,20 @@ int drm_plane_check_pixel_format(struct drm_plane *plane,
 	if (i == plane->format_count)
 		return -EINVAL;
 
-	if (!plane->modifier_count)
-		return 0;
+	if (plane->funcs->format_mod_supported) {
+		if (!plane->funcs->format_mod_supported(plane, format, modifier))
+			return -EINVAL;
+	} else {
+		if (!plane->modifier_count)
+			return 0;
 
-	for (i = 0; i < plane->modifier_count; i++) {
-		if (modifier == plane->modifiers[i])
-			break;
+		for (i = 0; i < plane->modifier_count; i++) {
+			if (modifier == plane->modifiers[i])
+				break;
+		}
+		if (i == plane->modifier_count)
+			return -EINVAL;
 	}
-	if (i == plane->modifier_count)
-		return -EINVAL;
-
-	if (plane->funcs->format_mod_supported &&
-	    !plane->funcs->format_mod_supported(plane, format, modifier))
-		return -EINVAL;
 
 	return 0;
 }
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 26fa50c2a50e..14b1607aba4b 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -431,7 +431,10 @@ struct drm_plane_funcs {
 	 * This optional hook is used for the DRM to determine if the given
 	 * format/modifier combination is valid for the plane. This allows the
 	 * DRM to generate the correct format bitmask (which formats apply to
-	 * which modifier).
+	 * which modifier), and to valdiate modifiers at atomic_check time.
+	 *
+	 * If not present, then any modifier in the plane's modifier
+	 * list is allowed with any of the plane's formats.
 	 *
 	 * Returns:
 	 *
-- 
cgit v1.2.3


From 13295bd887d07a9d904401808f41a8d35946d8c2 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Mon, 28 May 2018 17:16:18 +0000
Subject: drm/i915/guc: Don't read SOFT_SCRATCH(15) on MMIO error

SOFT_SCRATCH(15) is used by GuC for sending MMIO GuC events to host and
those events are now handled by intel_guc_to_host_event_handler_mmio().

We should not try to read it on MMIO action error as 1) we may be using
different set of registers for GuC MMIO communication, and 2) GuC may
use CTB mechanism for sending events to host.

While here, upgrade error message to DRM_ERROR.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180528171618.10436-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 116f4ccf1bbd..e28a996b9604 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -346,10 +346,8 @@ int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
 		ret = -EIO;
 
 	if (ret) {
-		DRM_DEBUG_DRIVER("INTEL_GUC_SEND: Action 0x%X failed;"
-				 " ret=%d status=0x%08X response=0x%08X\n",
-				 action[0], ret, status,
-				 I915_READ(SOFT_SCRATCH(15)));
+		DRM_ERROR("MMIO: GuC action %#x failed with error %d %#x\n",
+			  action[0], ret, status);
 		goto out;
 	}
 
-- 
cgit v1.2.3


From 4dfacb0bcbee79fa2ef4b2e9e64a8f8a28598934 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 31 May 2018 09:22:43 +0100
Subject: drm/i915: Switch to kernel context before idling at runtime

We can reduce our exposure to random neutrinos by resting on the kernel
context having flushed out the user contexts to system memory and
beyond. The corollary is that we then we require two passes through the
idle handler to go to sleep, which on a truly idle system involves an
extra pass through the slow and irregular retire work handler.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180531082246.9763-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c     |  9 +++++++--
 drivers/gpu/drm/i915/i915_gem.c         | 36 ++++++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_gem_context.c |  2 +-
 3 files changed, 39 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index a8e7761cdc7d..15e86d34a81c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4226,8 +4226,13 @@ i915_drop_caches_set(void *data, u64 val)
 		i915_gem_shrink_all(dev_priv);
 	fs_reclaim_release(GFP_KERNEL);
 
-	if (val & DROP_IDLE)
-		drain_delayed_work(&dev_priv->gt.idle_work);
+	if (val & DROP_IDLE) {
+		do {
+			if (READ_ONCE(dev_priv->gt.active_requests))
+				flush_delayed_work(&dev_priv->gt.retire_work);
+			drain_delayed_work(&dev_priv->gt.idle_work);
+		} while (READ_ONCE(dev_priv->gt.awake));
+	}
 
 	if (val & DROP_FREED)
 		i915_gem_drain_freed_objects(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 530d6d0109b4..173d1e4ad963 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -139,6 +139,8 @@ int i915_mutex_lock_interruptible(struct drm_device *dev)
 
 static u32 __i915_gem_park(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(i915->gt.active_requests);
 	GEM_BUG_ON(!list_empty(&i915->gt.active_rings));
@@ -181,6 +183,8 @@ static u32 __i915_gem_park(struct drm_i915_private *i915)
 
 void i915_gem_park(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(i915->gt.active_requests);
 
@@ -193,6 +197,8 @@ void i915_gem_park(struct drm_i915_private *i915)
 
 void i915_gem_unpark(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915->gt.active_requests);
 
@@ -3503,6 +3509,24 @@ i915_gem_idle_work_handler(struct work_struct *work)
 	if (!READ_ONCE(dev_priv->gt.awake))
 		return;
 
+	if (READ_ONCE(dev_priv->gt.active_requests))
+		return;
+
+	/*
+	 * Flush out the last user context, leaving only the pinned
+	 * kernel context resident. When we are idling on the kernel_context,
+	 * no more new requests (with a context switch) are emitted and we
+	 * can finally rest. A consequence is that the idle work handler is
+	 * always called at least twice before idling (and if the system is
+	 * idle that implies a round trip through the retire worker).
+	 */
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_gem_switch_to_kernel_context(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	GEM_TRACE("active_requests=%d (after switch-to-kernel-context)\n",
+		  READ_ONCE(dev_priv->gt.active_requests));
+
 	/*
 	 * Wait for last execlists context complete, but bail out in case a
 	 * new request is submitted. As we don't trust the hardware, we
@@ -4913,11 +4937,9 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
-	if (i915_terminally_wedged(&i915->gpu_error)) {
-		mutex_lock(&i915->drm.struct_mutex);
+	mutex_lock(&i915->drm.struct_mutex);
+	if (i915_terminally_wedged(&i915->gpu_error))
 		i915_gem_unset_wedged(i915);
-		mutex_unlock(&i915->drm.struct_mutex);
-	}
 
 	/*
 	 * If we inherit context state from the BIOS or earlier occupants
@@ -4929,6 +4951,9 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	 */
 	if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915))
 		WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
+
+	i915_gem_contexts_lost(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
 }
 
 int i915_gem_suspend(struct drm_i915_private *dev_priv)
@@ -4964,7 +4989,6 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 
 		assert_kernel_context_is_current(dev_priv);
 	}
-	i915_gem_contexts_lost(dev_priv);
 	mutex_unlock(&dev->struct_mutex);
 
 	intel_uc_suspend(dev_priv);
@@ -5017,6 +5041,8 @@ err_unlock:
 
 void i915_gem_resume(struct drm_i915_private *i915)
 {
+	GEM_TRACE("\n");
+
 	WARN_ON(i915->gt.awake);
 
 	mutex_lock(&i915->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 45393f6e0208..81f086397d10 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -649,7 +649,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
 
-	GEM_TRACE("\n");
+	GEM_TRACE("awake?=%s\n", yesno(i915->gt.awake));
 
 	lockdep_assert_held(&i915->drm.struct_mutex);
 	GEM_BUG_ON(!i915->kernel_context);
-- 
cgit v1.2.3


From 0606035fcab6b2630b0d95a5b31e235ec9ad5642 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 31 May 2018 09:22:44 +0100
Subject: drm/i915: "Race-to-idle" after switching to the kernel context

During suspend we want to flush out all active contexts and their
rendering. To do so we queue a request from the kernel's context, once
we know that request is done, we know the GPU is completely idle. To
speed up that switch bump the GPU clocks.

Switching to the kernel context prior to idling is also used to enforce
a barrier before changing OA properties, and when evicting active
rendering from the global GTT. All cases where we do want to
race-to-idle.

v2: Limit the boosting to only the switch before suspend.
v3: Limit it to the wait-for-idle on suspend.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: David Weinehall <david.weinehall@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Tested-by: David Weinehall <david.weinehall@linux.intel.com> #v1
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180531082246.9763-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c     | 27 +++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_request.h |  1 +
 2 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 173d1e4ad963..b312ac006d24 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3708,7 +3708,29 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 
 static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags)
 {
-	return i915_gem_active_wait(&tl->last_request, flags);
+	struct i915_request *rq;
+	long ret;
+
+	rq = i915_gem_active_get_unlocked(&tl->last_request);
+	if (!rq)
+		return 0;
+
+	/*
+	 * "Race-to-idle".
+	 *
+	 * Switching to the kernel context is often used a synchronous
+	 * step prior to idling, e.g. in suspend for flushing all
+	 * current operations to memory before sleeping. These we
+	 * want to complete as quickly as possible to avoid prolonged
+	 * stalls, so allow the gpu to boost to maximum clocks.
+	 */
+	if (flags & I915_WAIT_FOR_IDLE_BOOST)
+		gen6_rps_boost(rq, NULL);
+
+	ret = i915_request_wait(rq, flags, MAX_SCHEDULE_TIMEOUT);
+	i915_request_put(rq);
+
+	return ret < 0 ? ret : 0;
 }
 
 static int wait_for_engines(struct drm_i915_private *i915)
@@ -4983,7 +5005,8 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 
 		ret = i915_gem_wait_for_idle(dev_priv,
 					     I915_WAIT_INTERRUPTIBLE |
-					     I915_WAIT_LOCKED);
+					     I915_WAIT_LOCKED |
+					     I915_WAIT_FOR_IDLE_BOOST);
 		if (ret && ret != -EIO)
 			goto err_unlock;
 
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 1bbbb7a9fa03..491ff81d0fea 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -267,6 +267,7 @@ long i915_request_wait(struct i915_request *rq,
 #define I915_WAIT_INTERRUPTIBLE	BIT(0)
 #define I915_WAIT_LOCKED	BIT(1) /* struct_mutex held, handle GPU reset */
 #define I915_WAIT_ALL		BIT(2) /* used by i915_gem_object_wait() */
+#define I915_WAIT_FOR_IDLE_BOOST BIT(3)
 
 static inline u32 intel_engine_get_seqno(struct intel_engine_cs *engine);
 
-- 
cgit v1.2.3


From c3160da9a6af0e2d8f4fb3410df9d027a178ca3d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 31 May 2018 09:22:45 +0100
Subject: drm/i915: After reset on sanitization, reset the engine backends

As we reset the GPU on suspend/resume, we also do need to reset the
engine state tracking so call into the engine backends. This is
especially important so that we can also sanitize the state tracking
across resume.

References: https://bugs.freedesktop.org/show_bug.cgi?id=106702
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180531082246.9763-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c  | 24 ++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_lrc.c |  8 +++++---
 2 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b312ac006d24..9b8fa1866cc9 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4959,7 +4959,22 @@ static void assert_kernel_context_is_current(struct drm_i915_private *i915)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	GEM_TRACE("\n");
+
 	mutex_lock(&i915->drm.struct_mutex);
+
+	intel_runtime_pm_get(i915);
+	intel_uncore_forcewake_get(i915, FORCEWAKE_ALL);
+
+	/*
+	 * As we have just resumed the machine and woken the device up from
+	 * deep PCI sleep (presumably D3_cold), assume the HW has been reset
+	 * back to defaults, recovering from whatever wedged state we left it
+	 * in and so worth trying to use the device once more.
+	 */
 	if (i915_terminally_wedged(&i915->gpu_error))
 		i915_gem_unset_wedged(i915);
 
@@ -4974,6 +4989,15 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915))
 		WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
 
+	/* Reset the submission backend after resume as well as the GPU reset */
+	for_each_engine(engine, i915, id) {
+		if (engine->reset.reset)
+			engine->reset.reset(engine, NULL);
+	}
+
+	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
+	intel_runtime_pm_put(i915);
+
 	i915_gem_contexts_lost(i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 4bcd3206991d..38696d9cc02e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1788,9 +1788,6 @@ static void enable_execlists(struct intel_engine_cs *engine)
 	I915_WRITE(RING_HWS_PGA(engine->mmio_base),
 		   engine->status_page.ggtt_offset);
 	POSTING_READ(RING_HWS_PGA(engine->mmio_base));
-
-	/* Following the reset, we need to reload the CSB read/write pointers */
-	engine->execlists.csb_head = -1;
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)
@@ -1962,6 +1959,9 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	__unwind_incomplete_requests(engine);
 	spin_unlock(&engine->timeline.lock);
 
+	/* Following the reset, we need to reload the CSB read/write pointers */
+	engine->execlists.csb_head = -1;
+
 	local_irq_restore(flags);
 
 	/*
@@ -2461,6 +2461,8 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 			upper_32_bits(ce->lrc_desc);
 	}
 
+	engine->execlists.csb_head = -1;
+
 	return 0;
 
 error:
-- 
cgit v1.2.3


From ec92ad00a393d07f7f6c1c9a0ff65141f2173050 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 31 May 2018 09:22:46 +0100
Subject: drm/i915: Only sanitize GEM from late suspend

During testing we encounter a conflict between SUSPEND_TEST_DEVICES and
disabling reset (gem_eio/suspend). This results in the device continuing
on without being reset, but since it has gone through HW sanitization to
account for the suspend/resume cycle, we have to assume the device has
been reset to its defaults. A simple way around this is to skip the
sanitize phase for SUSPEND_TEST_DEVICES by moving it to suspend-late.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180531082246.9763-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.c |  6 +++++-
 drivers/gpu/drm/i915/i915_drv.h |  1 +
 drivers/gpu/drm/i915/i915_gem.c | 22 +++++++++++++---------
 3 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index fb39e40c0847..fe92665c8482 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -636,6 +636,8 @@ static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
 
 static void i915_gem_fini(struct drm_i915_private *dev_priv)
 {
+	i915_gem_suspend_late(dev_priv);
+
 	/* Flush any outstanding unpin_work. */
 	i915_gem_drain_workqueue(dev_priv);
 
@@ -1611,7 +1613,6 @@ static int i915_drm_suspend(struct drm_device *dev)
 	opregion_target_state = suspend_to_idle(dev_priv) ? PCI_D1 : PCI_D3cold;
 	intel_opregion_notify_adapter(dev_priv, opregion_target_state);
 
-	intel_uncore_suspend(dev_priv);
 	intel_opregion_unregister(dev_priv);
 
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_SUSPENDED, true);
@@ -1633,7 +1634,10 @@ static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 	disable_rpm_wakeref_asserts(dev_priv);
 
+	i915_gem_suspend_late(dev_priv);
+
 	intel_display_set_init_power(dev_priv, false);
+	intel_uncore_suspend(dev_priv);
 
 	/*
 	 * In case of firmware assisted context save/restore don't manually
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 32a65de7222d..38157df6ff5c 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3169,6 +3169,7 @@ void i915_gem_cleanup_engines(struct drm_i915_private *dev_priv);
 int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
 			   unsigned int flags);
 int __must_check i915_gem_suspend(struct drm_i915_private *dev_priv);
+void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
 int i915_gem_fault(struct vm_fault *vmf);
 int i915_gem_object_wait(struct drm_i915_gem_object *obj,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 9b8fa1866cc9..f5c4ef052001 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5055,6 +5055,17 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	if (WARN_ON(!intel_engines_are_idle(dev_priv)))
 		i915_gem_set_wedged(dev_priv); /* no hope, discard everything */
 
+	intel_runtime_pm_put(dev_priv);
+	return 0;
+
+err_unlock:
+	mutex_unlock(&dev->struct_mutex);
+	intel_runtime_pm_put(dev_priv);
+	return ret;
+}
+
+void i915_gem_suspend_late(struct drm_i915_private *i915)
+{
 	/*
 	 * Neither the BIOS, ourselves or any other kernel
 	 * expects the system to be in execlists mode on startup,
@@ -5074,16 +5085,9 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 	 * machines is a good idea, we don't - just in case it leaves the
 	 * machine in an unusable condition.
 	 */
-	intel_uc_sanitize(dev_priv);
-	i915_gem_sanitize(dev_priv);
 
-	intel_runtime_pm_put(dev_priv);
-	return 0;
-
-err_unlock:
-	mutex_unlock(&dev->struct_mutex);
-	intel_runtime_pm_put(dev_priv);
-	return ret;
+	intel_uc_sanitize(i915);
+	i915_gem_sanitize(i915);
 }
 
 void i915_gem_resume(struct drm_i915_private *i915)
-- 
cgit v1.2.3


From 1e871d65e375280757833d9fce91dda71980bdf5 Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Fri, 16 Mar 2018 15:04:34 -0700
Subject: drm/vc4: Add missing formats to vc4_format_mod_supported().

Daniel's format_mod_supported() patch predated Dave's for NV21/61, and
I didn't catch that when rebasing.  This is a problem since the
formats are now getting validated before being passed to the driver's
atomic hooks.

Signed-off-by: Eric Anholt <eric@anholt.net>
Acked-by: Daniel Stone <daniels@collabora.com>
Cc: Dave Stevenson <dave.stevenson@raspberrypi.org>
Fixes: 423ad7b3cbd1 ("drm/vc4: Advertise supported modifiers for planes")
Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-2-eric@anholt.net
---
 drivers/gpu/drm/vc4/vc4_plane.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 6e8984aee613..6efd55bae8db 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -873,7 +873,9 @@ static bool vc4_format_mod_supported(struct drm_plane *plane,
 	case DRM_FORMAT_YUV420:
 	case DRM_FORMAT_YVU420:
 	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
 	case DRM_FORMAT_NV16:
+	case DRM_FORMAT_NV61:
 	default:
 		return (modifier == DRM_FORMAT_MOD_LINEAR);
 	}
-- 
cgit v1.2.3


From e065a8dd30af703b4794dc740c0825ee12b92efd Mon Sep 17 00:00:00 2001
From: Dave Stevenson <dave.stevenson@raspberrypi.org>
Date: Fri, 16 Mar 2018 15:04:35 -0700
Subject: drm/vc4: Add support for SAND modifier.

This is the format generated by VC4's H.264 engine, and preferred by
the ISP as well.  By displaying SAND buffers directly, we can avoid
needing to use the ISP to rewrite the SAND H.264 output to linear
before display.

This is a joint effort by Dave Stevenson (who wrote the initial patch
and DRM demo) and Eric Anholt (drm_fourcc.h generalization, safety
checks, RGBA support).

v2: Make the parameter macro give all of the middle 48 bits (suggested
    by Daniels).  Fix fourcc_mod_broadcom_mod()'s bits/shift being
    swapped.  Mark NV12/21 as supported, not YUV420.

Signed-off-by: Dave Stevenson <dave.stevenson@raspberrypi.org>
Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Daniel Vetter <daniel@ffwll.ch>
Acked-by: Daniel Stone <daniels@collabora.com> (v1)
Cc: Boris Brezillon <boris.brezillon@bootlin.com>
Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180316220435.31416-3-eric@anholt.net
---
 drivers/gpu/drm/vc4/vc4_plane.c | 84 +++++++++++++++++++++++++++++++++++++----
 drivers/gpu/drm/vc4/vc4_regs.h  |  6 +++
 include/uapi/drm/drm_fourcc.h   | 59 +++++++++++++++++++++++++++++
 3 files changed, 142 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 6efd55bae8db..2575bd81a010 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -467,12 +467,14 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	struct drm_framebuffer *fb = state->fb;
 	u32 ctl0_offset = vc4_state->dlist_count;
 	const struct hvs_format *format = vc4_get_hvs_format(fb->format->format);
+	u64 base_format_mod = fourcc_mod_broadcom_mod(fb->modifier);
 	int num_planes = drm_format_num_planes(format->drm);
 	bool mix_plane_alpha;
 	bool covers_screen;
 	u32 scl0, scl1, pitch0;
 	u32 lbm_size, tiling;
 	unsigned long irqflags;
+	u32 hvs_format = format->hvs;
 	int ret, i;
 
 	ret = vc4_plane_setup_clipping_and_scaling(state);
@@ -512,7 +514,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 		scl1 = vc4_get_scl_field(state, 0);
 	}
 
-	switch (fb->modifier) {
+	switch (base_format_mod) {
 	case DRM_FORMAT_MOD_LINEAR:
 		tiling = SCALER_CTL0_TILING_LINEAR;
 		pitch0 = VC4_SET_FIELD(fb->pitches[0], SCALER_SRC_PITCH);
@@ -535,6 +537,49 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 		break;
 	}
 
+	case DRM_FORMAT_MOD_BROADCOM_SAND64:
+	case DRM_FORMAT_MOD_BROADCOM_SAND128:
+	case DRM_FORMAT_MOD_BROADCOM_SAND256: {
+		uint32_t param = fourcc_mod_broadcom_param(fb->modifier);
+
+		/* Column-based NV12 or RGBA.
+		 */
+		if (fb->format->num_planes > 1) {
+			if (hvs_format != HVS_PIXEL_FORMAT_YCBCR_YUV420_2PLANE) {
+				DRM_DEBUG_KMS("SAND format only valid for NV12/21");
+				return -EINVAL;
+			}
+			hvs_format = HVS_PIXEL_FORMAT_H264;
+		} else {
+			if (base_format_mod == DRM_FORMAT_MOD_BROADCOM_SAND256) {
+				DRM_DEBUG_KMS("SAND256 format only valid for H.264");
+				return -EINVAL;
+			}
+		}
+
+		switch (base_format_mod) {
+		case DRM_FORMAT_MOD_BROADCOM_SAND64:
+			tiling = SCALER_CTL0_TILING_64B;
+			break;
+		case DRM_FORMAT_MOD_BROADCOM_SAND128:
+			tiling = SCALER_CTL0_TILING_128B;
+			break;
+		case DRM_FORMAT_MOD_BROADCOM_SAND256:
+			tiling = SCALER_CTL0_TILING_256B_OR_T;
+			break;
+		default:
+			break;
+		}
+
+		if (param > SCALER_TILE_HEIGHT_MASK) {
+			DRM_DEBUG_KMS("SAND height too large (%d)\n", param);
+			return -EINVAL;
+		}
+
+		pitch0 = VC4_SET_FIELD(param, SCALER_TILE_HEIGHT);
+		break;
+	}
+
 	default:
 		DRM_DEBUG_KMS("Unsupported FB tiling flag 0x%16llx",
 			      (long long)fb->modifier);
@@ -546,7 +591,7 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 			SCALER_CTL0_VALID |
 			VC4_SET_FIELD(SCALER_CTL0_RGBA_EXPAND_ROUND, SCALER_CTL0_RGBA_EXPAND) |
 			(format->pixel_order << SCALER_CTL0_ORDER_SHIFT) |
-			(format->hvs << SCALER_CTL0_PIXEL_FORMAT_SHIFT) |
+			(hvs_format << SCALER_CTL0_PIXEL_FORMAT_SHIFT) |
 			VC4_SET_FIELD(tiling, SCALER_CTL0_TILING) |
 			(vc4_state->is_unity ? SCALER_CTL0_UNITY : 0) |
 			VC4_SET_FIELD(scl0, SCALER_CTL0_SCL0) |
@@ -608,8 +653,13 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 
 	/* Pitch word 1/2 */
 	for (i = 1; i < num_planes; i++) {
-		vc4_dlist_write(vc4_state,
-				VC4_SET_FIELD(fb->pitches[i], SCALER_SRC_PITCH));
+		if (hvs_format != HVS_PIXEL_FORMAT_H264) {
+			vc4_dlist_write(vc4_state,
+					VC4_SET_FIELD(fb->pitches[i],
+						      SCALER_SRC_PITCH));
+		} else {
+			vc4_dlist_write(vc4_state, pitch0);
+		}
 	}
 
 	/* Colorspace conversion words */
@@ -867,13 +917,30 @@ static bool vc4_format_mod_supported(struct drm_plane *plane,
 	case DRM_FORMAT_BGR565:
 	case DRM_FORMAT_ARGB1555:
 	case DRM_FORMAT_XRGB1555:
-		return true;
+		switch (fourcc_mod_broadcom_mod(modifier)) {
+		case DRM_FORMAT_MOD_LINEAR:
+		case DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED:
+		case DRM_FORMAT_MOD_BROADCOM_SAND64:
+		case DRM_FORMAT_MOD_BROADCOM_SAND128:
+			return true;
+		default:
+			return false;
+		}
+	case DRM_FORMAT_NV12:
+	case DRM_FORMAT_NV21:
+		switch (fourcc_mod_broadcom_mod(modifier)) {
+		case DRM_FORMAT_MOD_LINEAR:
+		case DRM_FORMAT_MOD_BROADCOM_SAND64:
+		case DRM_FORMAT_MOD_BROADCOM_SAND128:
+		case DRM_FORMAT_MOD_BROADCOM_SAND256:
+			return true;
+		default:
+			return false;
+		}
 	case DRM_FORMAT_YUV422:
 	case DRM_FORMAT_YVU422:
 	case DRM_FORMAT_YUV420:
 	case DRM_FORMAT_YVU420:
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV21:
 	case DRM_FORMAT_NV16:
 	case DRM_FORMAT_NV61:
 	default:
@@ -903,6 +970,9 @@ struct drm_plane *vc4_plane_init(struct drm_device *dev,
 	unsigned i;
 	static const uint64_t modifiers[] = {
 		DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED,
+		DRM_FORMAT_MOD_BROADCOM_SAND128,
+		DRM_FORMAT_MOD_BROADCOM_SAND64,
+		DRM_FORMAT_MOD_BROADCOM_SAND256,
 		DRM_FORMAT_MOD_LINEAR,
 		DRM_FORMAT_MOD_INVALID
 	};
diff --git a/drivers/gpu/drm/vc4/vc4_regs.h b/drivers/gpu/drm/vc4/vc4_regs.h
index d1fb6fec46eb..d6864fa4bd14 100644
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -1031,6 +1031,12 @@ enum hvs_pixel_format {
 #define SCALER_SRC_PITCH_MASK			VC4_MASK(15, 0)
 #define SCALER_SRC_PITCH_SHIFT			0
 
+/* PITCH0/1/2 fields for tiled (SAND). */
+#define SCALER_TILE_SKIP_0_MASK			VC4_MASK(18, 16)
+#define SCALER_TILE_SKIP_0_SHIFT		16
+#define SCALER_TILE_HEIGHT_MASK			VC4_MASK(15, 0)
+#define SCALER_TILE_HEIGHT_SHIFT		0
+
 /* PITCH0 fields for T-tiled. */
 #define SCALER_PITCH0_TILE_WIDTH_L_MASK		VC4_MASK(22, 16)
 #define SCALER_PITCH0_TILE_WIDTH_L_SHIFT	16
diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index e04613d30a13..64bf67abff7e 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -384,6 +384,23 @@ extern "C" {
 #define DRM_FORMAT_MOD_NVIDIA_16BX2_BLOCK_THIRTYTWO_GOB \
 	fourcc_mod_code(NVIDIA, 0x15)
 
+/*
+ * Some Broadcom modifiers take parameters, for example the number of
+ * vertical lines in the image. Reserve the lower 32 bits for modifier
+ * type, and the next 24 bits for parameters. Top 8 bits are the
+ * vendor code.
+ */
+#define __fourcc_mod_broadcom_param_shift 8
+#define __fourcc_mod_broadcom_param_bits 48
+#define fourcc_mod_broadcom_code(val, params) \
+	fourcc_mod_code(BROADCOM, ((((__u64)params) << __fourcc_mod_broadcom_param_shift) | val))
+#define fourcc_mod_broadcom_param(m) \
+	((int)(((m) >> __fourcc_mod_broadcom_param_shift) &	\
+	       ((1ULL << __fourcc_mod_broadcom_param_bits) - 1)))
+#define fourcc_mod_broadcom_mod(m) \
+	((m) & ~(((1ULL << __fourcc_mod_broadcom_param_bits) - 1) <<	\
+		 __fourcc_mod_broadcom_param_shift))
+
 /*
  * Broadcom VC4 "T" format
  *
@@ -405,6 +422,48 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_BROADCOM_VC4_T_TILED fourcc_mod_code(BROADCOM, 1)
 
+/*
+ * Broadcom SAND format
+ *
+ * This is the native format that the H.264 codec block uses.  For VC4
+ * HVS, it is only valid for H.264 (NV12/21) and RGBA modes.
+ *
+ * The image can be considered to be split into columns, and the
+ * columns are placed consecutively into memory.  The width of those
+ * columns can be either 32, 64, 128, or 256 pixels, but in practice
+ * only 128 pixel columns are used.
+ *
+ * The pitch between the start of each column is set to optimally
+ * switch between SDRAM banks. This is passed as the number of lines
+ * of column width in the modifier (we can't use the stride value due
+ * to various core checks that look at it , so you should set the
+ * stride to width*cpp).
+ *
+ * Note that the column height for this format modifier is the same
+ * for all of the planes, assuming that each column contains both Y
+ * and UV.  Some SAND-using hardware stores UV in a separate tiled
+ * image from Y to reduce the column height, which is not supported
+ * with these modifiers.
+ */
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(2, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(3, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(4, v)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(v) \
+	fourcc_mod_broadcom_code(5, v)
+
+#define DRM_FORMAT_MOD_BROADCOM_SAND32 \
+	DRM_FORMAT_MOD_BROADCOM_SAND32_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND64 \
+	DRM_FORMAT_MOD_BROADCOM_SAND64_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND128 \
+	DRM_FORMAT_MOD_BROADCOM_SAND128_COL_HEIGHT(0)
+#define DRM_FORMAT_MOD_BROADCOM_SAND256 \
+	DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(0)
+
 #if defined(__cplusplus)
 }
 #endif
-- 
cgit v1.2.3


From 09ea0dfbf972c63dfea8cf46f2fb67f39e4d833b Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Tue, 29 May 2018 15:59:18 +0200
Subject: dma-buf: make map_atomic and map function pointers optional

So drivers don't need dummy functions just returning NULL.

Cc: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20180529135918.19729-1-kraxel@redhat.com
---
 drivers/dma-buf/dma-buf.c | 4 ++++
 include/linux/dma-buf.h   | 4 ++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index d78d5fc173dc..4c45e31258f0 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -872,6 +872,8 @@ void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num)
 {
 	WARN_ON(!dmabuf);
 
+	if (!dmabuf->ops->map_atomic)
+		return NULL;
 	return dmabuf->ops->map_atomic(dmabuf, page_num);
 }
 EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic);
@@ -907,6 +909,8 @@ void *dma_buf_kmap(struct dma_buf *dmabuf, unsigned long page_num)
 {
 	WARN_ON(!dmabuf);
 
+	if (!dmabuf->ops->map)
+		return NULL;
 	return dmabuf->ops->map(dmabuf, page_num);
 }
 EXPORT_SYMBOL_GPL(dma_buf_kmap);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 085db2fee2d7..88917fa796e4 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -39,12 +39,12 @@ struct dma_buf_attachment;
 
 /**
  * struct dma_buf_ops - operations possible on struct dma_buf
- * @map_atomic: maps a page from the buffer into kernel address
+ * @map_atomic: [optional] maps a page from the buffer into kernel address
  *		space, users may not block until the subsequent unmap call.
  *		This callback must not sleep.
  * @unmap_atomic: [optional] unmaps a atomically mapped page from the buffer.
  *		  This Callback must not sleep.
- * @map: maps a page from the buffer into kernel address space.
+ * @map: [optional] maps a page from the buffer into kernel address space.
  * @unmap: [optional] unmaps a page from the buffer.
  * @vmap: [optional] creates a virtual mapping for the buffer into kernel
  *	  address space. Same restrictions as for vmap and friends apply.
-- 
cgit v1.2.3


From 1934f5deaf8f53e0af0b55f87b7fc519b76515a0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 31 May 2018 23:40:57 +0100
Subject: drm/i915: Assert we idle in the kernel context

Now that we always switch to the kernel context upon idling, we can
make that assertion.

References: 4dfacb0bcbee ("drm/i915: Switch to kernel context before idling at runtime")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180531224057.6036-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f5c4ef052001..c85951f2b15a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3498,6 +3498,22 @@ new_requests_since_last_retire(const struct drm_i915_private *i915)
 		work_pending(&i915->gt.idle_work.work));
 }
 
+static void assert_kernel_context_is_current(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return;
+
+	GEM_BUG_ON(i915->gt.active_requests);
+	for_each_engine(engine, i915, id) {
+		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
+		GEM_BUG_ON(engine->last_retired_context !=
+			   to_intel_context(i915->kernel_context, engine));
+	}
+}
+
 static void
 i915_gem_idle_work_handler(struct work_struct *work)
 {
@@ -3560,6 +3576,8 @@ i915_gem_idle_work_handler(struct work_struct *work)
 
 	epoch = __i915_gem_park(dev_priv);
 
+	assert_kernel_context_is_current(dev_priv);
+
 	rearm_hangcheck = false;
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
@@ -4944,19 +4962,6 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 		i915_gem_object_put(obj);
 }
 
-static void assert_kernel_context_is_current(struct drm_i915_private *i915)
-{
-	struct i915_gem_context *kctx = i915->kernel_context;
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
-
-	GEM_BUG_ON(i915->gt.active_requests);
-	for_each_engine(engine, i915, id) {
-		GEM_BUG_ON(__i915_gem_active_peek(&engine->timeline.last_request));
-		GEM_BUG_ON(engine->last_retired_context->gem_context != kctx);
-	}
-}
-
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
 	struct intel_engine_cs *engine;
-- 
cgit v1.2.3


From e312b689a92d82d2b67f8b58b307fe5b79019d60 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 1 Jun 2018 10:40:02 +0100
Subject: drm/i915: Check intel_contexts to avoid one extra pointer chase

As we store the intel_context on the request (rq->hw_context), we can
simply compare that against the local intel_context for the
i915->kernel_context rather than using the rq->gem_context.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180601094002.13329-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 81f086397d10..94e4db1870aa 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -610,7 +610,7 @@ static bool engine_has_kernel_context_barrier(struct intel_engine_cs *engine)
 
 		any_active = true;
 
-		if (rq->gem_context == i915->kernel_context)
+		if (rq->hw_context == ce)
 			continue;
 
 		/*
-- 
cgit v1.2.3


From 37800ca8037adeeb1ccd23dc15f6452b395e3101 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 1 Jun 2018 10:35:49 +0100
Subject: drm/i915/gtt: Avoid calling non-existent allocate_va_range

On hsw and older, we do not need to allocate the ppgtt on the fly and so
ppgtt->allocate_va_range() is NULL. Fixup ppgtt_bind_vma not to call it,
in that case!

v2: PIN_UPDATE still exists.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180601093554.13083-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180601093554.13083-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 34 +++++++++++++++++++++-------------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index fc5c0f746f26..ec60be48919b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -190,19 +190,11 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 	return 1;
 }
 
-static int ppgtt_bind_vma(struct i915_vma *vma,
-			  enum i915_cache_level cache_level,
-			  u32 unused)
+static int gen6_ppgtt_bind_vma(struct i915_vma *vma,
+			       enum i915_cache_level cache_level,
+			       u32 unused)
 {
 	u32 pte_flags;
-	int ret;
-
-	if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
-		ret = vma->vm->allocate_va_range(vma->vm, vma->node.start,
-						 vma->size);
-		if (ret)
-			return ret;
-	}
 
 	/* Currently applicable only to VLV */
 	pte_flags = 0;
@@ -214,6 +206,22 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 	return 0;
 }
 
+static int gen8_ppgtt_bind_vma(struct i915_vma *vma,
+			       enum i915_cache_level cache_level,
+			       u32 unused)
+{
+	int ret;
+
+	if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
+		ret = vma->vm->allocate_va_range(vma->vm,
+						 vma->node.start, vma->size);
+		if (ret)
+			return ret;
+	}
+
+	return gen6_ppgtt_bind_vma(vma, cache_level, unused);
+}
+
 static void ppgtt_unbind_vma(struct i915_vma *vma)
 {
 	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
@@ -1657,8 +1665,8 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
 	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
+	ppgtt->base.bind_vma = gen8_ppgtt_bind_vma;
 	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->base.bind_vma = ppgtt_bind_vma;
 	ppgtt->base.set_pages = ppgtt_set_pages;
 	ppgtt->base.clear_pages = clear_pages;
 	ppgtt->debug_dump = gen8_dump_ppgtt;
@@ -2100,8 +2108,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 
 	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
+	ppgtt->base.bind_vma = gen6_ppgtt_bind_vma;
 	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->base.bind_vma = ppgtt_bind_vma;
 	ppgtt->base.set_pages = ppgtt_set_pages;
 	ppgtt->base.clear_pages = clear_pages;
 	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
-- 
cgit v1.2.3


From 3df845e7528b4f337e5cf91f3fd75610a646b259 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 1 Jun 2018 10:35:50 +0100
Subject: drm/i915/gtt: Don't restore the non-existent PDE for GGTT

On resume, we have to rewrite all the PDE entries for gen7 ppgtts. If we
switch on full-ppgtt, there is then one address space with no PDE, the
GGTT. Currently under aliasing-ppgtt, the GGTT address space does have
an associated ppgtt and so the restore works just fine. We would have a
similar problem if we tried disabling aliasing-ppgtt
(i915.enable_ppgtt=0). So skip the empty ppgtt, as being non-existent it
doesn't need restoring.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180601093554.13083-2-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ec60be48919b..d032069819cc 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3665,6 +3665,8 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 				ppgtt = dev_priv->mm.aliasing_ppgtt;
 			else
 				ppgtt = i915_vm_to_ppgtt(vm);
+			if (!ppgtt)
+				continue;
 
 			gen6_write_page_range(ppgtt, 0, ppgtt->base.total);
 		}
-- 
cgit v1.2.3


From eade6c894498c12c2940e7fbe598dc08a292994f Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 30 Jan 2018 22:38:03 +0200
Subject: drm/i915: Have plane->get_hw_state() return the current pipe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Like we do for encoder let's make the plane->get_hw_state() return
the pipe to which the plane is currently attached. We don't currently
allow planes to move between the pipes, but perhaps one day we will.

In either case this makes the code more uniform and perhaps makes
intel_plane_mapping_ok() slightly more clear.

Note that for i965 and g4x planes A and B still have pipe select bits
but they're hardwired to pipe A and B respectively. This means we can
safely interpret those bits just like on gen2/3. This allows the
same readout code work for plane C (which can still be assigned
to eiter pipe on i965) should we ever expose it.

g4x no longer allows moving the cursor planes between the pipes,
but the pipe select bits can still be set in the register. Thus
we have to ignore those bits. OTOH i965 still allows the cursors
to move between pipes thus we have to trust the bits there.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180130203807.13721-3-ville.syrjala@linux.intel.com
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h      |  2 +
 drivers/gpu/drm/i915/intel_display.c | 71 ++++++++++++++++++++++++++----------
 drivers/gpu/drm/i915/intel_drv.h     |  4 +-
 drivers/gpu/drm/i915/intel_sprite.c  | 40 ++++++++++++--------
 4 files changed, 79 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f238b7b33cd9..be8a19472755 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5936,6 +5936,8 @@ enum {
 #define   CURSOR_MODE_128_ARGB_AX ((1 << 5) | CURSOR_MODE_128_32B_AX)
 #define   CURSOR_MODE_256_ARGB_AX ((1 << 5) | CURSOR_MODE_256_32B_AX)
 #define   CURSOR_MODE_64_ARGB_AX ((1 << 5) | CURSOR_MODE_64_32B_AX)
+#define   MCURSOR_PIPE_SELECT_MASK	(0x3 << 28)
+#define   MCURSOR_PIPE_SELECT_SHIFT	28
 #define   MCURSOR_PIPE_SELECT(pipe)	((pipe) << 28)
 #define   MCURSOR_GAMMA_ENABLE  (1 << 26)
 #define   CURSOR_ROTATE_180	(1<<15)
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index da251ff6aca9..136f129f71c4 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1284,7 +1284,10 @@ void assert_pipe(struct drm_i915_private *dev_priv,
 
 static void assert_plane(struct intel_plane *plane, bool state)
 {
-	bool cur_state = plane->get_hw_state(plane);
+	enum pipe pipe;
+	bool cur_state;
+
+	cur_state = plane->get_hw_state(plane, &pipe);
 
 	I915_STATE_WARN(cur_state != state,
 			"%s assertion failure (expected %s, current %s)\n",
@@ -3387,24 +3390,33 @@ static void i9xx_disable_plane(struct intel_plane *plane,
 	spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
 }
 
-static bool i9xx_plane_get_hw_state(struct intel_plane *plane)
+static bool i9xx_plane_get_hw_state(struct intel_plane *plane,
+				    enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
-	enum pipe pipe = plane->pipe;
 	bool ret;
+	u32 val;
 
 	/*
 	 * Not 100% correct for planes that can move between pipes,
 	 * but that's only the case for gen2-4 which don't have any
 	 * display power wells.
 	 */
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(DSPCNTR(i9xx_plane)) & DISPLAY_PLANE_ENABLE;
+	val = I915_READ(DSPCNTR(i9xx_plane));
+
+	ret = val & DISPLAY_PLANE_ENABLE;
+
+	if (INTEL_GEN(dev_priv) >= 5)
+		*pipe = plane->pipe;
+	else
+		*pipe = (val & DISPPLANE_SEL_PIPE_MASK) >>
+			DISPPLANE_SEL_PIPE_SHIFT;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -7647,16 +7659,18 @@ i9xx_get_initial_plane_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
-	enum pipe pipe = crtc->pipe;
+	enum pipe pipe;
 	u32 val, base, offset;
 	int fourcc, pixel_format;
 	unsigned int aligned_height;
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
-	if (!plane->get_hw_state(plane))
+	if (!plane->get_hw_state(plane, &pipe))
 		return;
 
+	WARN_ON(pipe != crtc->pipe);
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -8677,16 +8691,18 @@ skylake_get_initial_plane_config(struct intel_crtc *crtc,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_plane *plane = to_intel_plane(crtc->base.primary);
 	enum plane_id plane_id = plane->id;
-	enum pipe pipe = crtc->pipe;
+	enum pipe pipe;
 	u32 val, base, offset, stride_mult, tiling, alpha;
 	int fourcc, pixel_format;
 	unsigned int aligned_height;
 	struct drm_framebuffer *fb;
 	struct intel_framebuffer *intel_fb;
 
-	if (!plane->get_hw_state(plane))
+	if (!plane->get_hw_state(plane, &pipe))
 		return;
 
+	WARN_ON(pipe != crtc->pipe);
+
 	intel_fb = kzalloc(sizeof(*intel_fb), GFP_KERNEL);
 	if (!intel_fb) {
 		DRM_DEBUG_KMS("failed to alloc fb\n");
@@ -9667,7 +9683,8 @@ static void i845_disable_cursor(struct intel_plane *plane,
 	i845_update_cursor(plane, NULL, NULL);
 }
 
-static bool i845_cursor_get_hw_state(struct intel_plane *plane)
+static bool i845_cursor_get_hw_state(struct intel_plane *plane,
+				     enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
@@ -9679,6 +9696,8 @@ static bool i845_cursor_get_hw_state(struct intel_plane *plane)
 
 	ret = I915_READ(CURCNTR(PIPE_A)) & CURSOR_ENABLE;
 
+	*pipe = PIPE_A;
+
 	intel_display_power_put(dev_priv, power_domain);
 
 	return ret;
@@ -9880,23 +9899,32 @@ static void i9xx_disable_cursor(struct intel_plane *plane,
 	i9xx_update_cursor(plane, NULL, NULL);
 }
 
-static bool i9xx_cursor_get_hw_state(struct intel_plane *plane)
+static bool i9xx_cursor_get_hw_state(struct intel_plane *plane,
+				     enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
-	enum pipe pipe = plane->pipe;
 	bool ret;
+	u32 val;
 
 	/*
 	 * Not 100% correct for planes that can move between pipes,
 	 * but that's only the case for gen2-3 which don't have any
 	 * display power wells.
 	 */
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(CURCNTR(pipe)) & CURSOR_MODE;
+	val = I915_READ(CURCNTR(plane->pipe));
+
+	ret = val & CURSOR_MODE;
+
+	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
+		*pipe = plane->pipe;
+	else
+		*pipe = (val & MCURSOR_PIPE_SELECT_MASK) >>
+			MCURSOR_PIPE_SELECT_SHIFT;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -15087,12 +15115,12 @@ void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe)
 static bool intel_plane_mapping_ok(struct intel_crtc *crtc,
 				   struct intel_plane *plane)
 {
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	enum i9xx_plane_id i9xx_plane = plane->i9xx_plane;
-	u32 val = I915_READ(DSPCNTR(i9xx_plane));
+	enum pipe pipe;
 
-	return (val & DISPLAY_PLANE_ENABLE) == 0 ||
-		(val & DISPPLANE_SEL_PIPE_MASK) == DISPPLANE_SEL_PIPE(crtc->pipe);
+	if (!plane->get_hw_state(plane, &pipe))
+		return true;
+
+	return pipe == crtc->pipe;
 }
 
 static void
@@ -15294,7 +15322,10 @@ static void readout_plane_state(struct intel_crtc *crtc)
 	for_each_intel_plane_on_crtc(&dev_priv->drm, crtc, plane) {
 		struct intel_plane_state *plane_state =
 			to_intel_plane_state(plane->base.state);
-		bool visible = plane->get_hw_state(plane);
+		enum pipe pipe;
+		bool visible;
+
+		visible = plane->get_hw_state(plane, &pipe);
 
 		intel_set_plane_visible(crtc_state, plane_state, visible);
 	}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index fd6256632482..1a4659a2e000 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -970,7 +970,7 @@ struct intel_plane {
 			     const struct intel_plane_state *plane_state);
 	void (*disable_plane)(struct intel_plane *plane,
 			      struct intel_crtc *crtc);
-	bool (*get_hw_state)(struct intel_plane *plane);
+	bool (*get_hw_state)(struct intel_plane *plane, enum pipe *pipe);
 	int (*check_plane)(struct intel_plane *plane,
 			   struct intel_crtc_state *crtc_state,
 			   struct intel_plane_state *state);
@@ -2082,7 +2082,7 @@ void skl_update_plane(struct intel_plane *plane,
 		      const struct intel_crtc_state *crtc_state,
 		      const struct intel_plane_state *plane_state);
 void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc);
-bool skl_plane_get_hw_state(struct intel_plane *plane);
+bool skl_plane_get_hw_state(struct intel_plane *plane, enum pipe *pipe);
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, enum plane_id plane_id);
 bool intel_format_is_yuv(uint32_t format);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 1597938d2451..fe2b44844e8a 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -327,19 +327,21 @@ skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 bool
-skl_plane_get_hw_state(struct intel_plane *plane)
+skl_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum plane_id plane_id = plane->id;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(PLANE_CTL(pipe, plane_id)) & PLANE_CTL_ENABLE;
+	ret = I915_READ(PLANE_CTL(plane->pipe, plane_id)) & PLANE_CTL_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -588,19 +590,21 @@ vlv_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 static bool
-vlv_plane_get_hw_state(struct intel_plane *plane)
+vlv_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
 	enum plane_id plane_id = plane->id;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(SPCNTR(pipe, plane_id)) & SP_ENABLE;
+	ret = I915_READ(SPCNTR(plane->pipe, plane_id)) & SP_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -754,18 +758,20 @@ ivb_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 static bool
-ivb_plane_get_hw_state(struct intel_plane *plane)
+ivb_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret =  I915_READ(SPRCTL(pipe)) & SPRITE_ENABLE;
+	ret =  I915_READ(SPRCTL(plane->pipe)) & SPRITE_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
@@ -910,18 +916,20 @@ g4x_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc)
 }
 
 static bool
-g4x_plane_get_hw_state(struct intel_plane *plane)
+g4x_plane_get_hw_state(struct intel_plane *plane,
+		       enum pipe *pipe)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
 	enum intel_display_power_domain power_domain;
-	enum pipe pipe = plane->pipe;
 	bool ret;
 
-	power_domain = POWER_DOMAIN_PIPE(pipe);
+	power_domain = POWER_DOMAIN_PIPE(plane->pipe);
 	if (!intel_display_power_get_if_enabled(dev_priv, power_domain))
 		return false;
 
-	ret = I915_READ(DVSCNTR(pipe)) & DVS_ENABLE;
+	ret = I915_READ(DVSCNTR(plane->pipe)) & DVS_ENABLE;
+
+	*pipe = plane->pipe;
 
 	intel_display_power_put(dev_priv, power_domain);
 
-- 
cgit v1.2.3


From b99b9ec1d374fd0354691d94ddb87b593f700f3e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 31 Jan 2018 16:37:09 +0200
Subject: drm/i915: Clean up cursor defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use MCURSOR_ instead of CURSOR_ as the prefix for the non-845/865
cursor defines consistently, and move the pipe CSC enable bit next
to the other non-845/865 cursor defines.

v2: Take care of gvt uses as well
v3: Another gvt use popped up

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180131143709.875-1-ville.syrjala@linux.intel.com
Reviewed-by: Mika Kahola <mika.kahola@intel.com> #v2
---
 drivers/gpu/drm/i915/gvt/display.c    |  4 ++--
 drivers/gpu/drm/i915/gvt/fb_decoder.c | 12 ++++++------
 drivers/gpu/drm/i915/i915_reg.h       | 22 +++++++++++-----------
 drivers/gpu/drm/i915/intel_display.c  | 16 ++++++++--------
 4 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 6d8180e8d1e2..120e24c3fc62 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -273,8 +273,8 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	for_each_pipe(dev_priv, pipe) {
 		vgpu_vreg_t(vgpu, DSPCNTR(pipe)) &= ~DISPLAY_PLANE_ENABLE;
 		vgpu_vreg_t(vgpu, SPRCTL(pipe)) &= ~SPRITE_ENABLE;
-		vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~CURSOR_MODE;
-		vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= CURSOR_MODE_DISABLE;
+		vgpu_vreg_t(vgpu, CURCNTR(pipe)) &= ~MCURSOR_MODE;
+		vgpu_vreg_t(vgpu, CURCNTR(pipe)) |= MCURSOR_MODE_DISABLE;
 	}
 
 	vgpu_vreg_t(vgpu, PIPECONF(PIPE_A)) |= PIPECONF_ENABLE;
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c
index 1c120683e958..00b788cf8b13 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.c
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c
@@ -300,16 +300,16 @@ static int cursor_mode_to_drm(int mode)
 	int cursor_pixel_formats_index = 4;
 
 	switch (mode) {
-	case CURSOR_MODE_128_ARGB_AX:
+	case MCURSOR_MODE_128_ARGB_AX:
 		cursor_pixel_formats_index = 0;
 		break;
-	case CURSOR_MODE_256_ARGB_AX:
+	case MCURSOR_MODE_256_ARGB_AX:
 		cursor_pixel_formats_index = 1;
 		break;
-	case CURSOR_MODE_64_ARGB_AX:
+	case MCURSOR_MODE_64_ARGB_AX:
 		cursor_pixel_formats_index = 2;
 		break;
-	case CURSOR_MODE_64_32B_AX:
+	case MCURSOR_MODE_64_32B_AX:
 		cursor_pixel_formats_index = 3;
 		break;
 
@@ -342,8 +342,8 @@ int intel_vgpu_decode_cursor_plane(struct intel_vgpu *vgpu,
 		return -ENODEV;
 
 	val = vgpu_vreg_t(vgpu, CURCNTR(pipe));
-	mode = val & CURSOR_MODE;
-	plane->enabled = (mode != CURSOR_MODE_DISABLE);
+	mode = val & MCURSOR_MODE;
+	plane->enabled = (mode != MCURSOR_MODE_DISABLE);
 	if (!plane->enabled)
 		return -ENODEV;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index be8a19472755..749d23811749 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5919,7 +5919,6 @@ enum {
 #define   CURSOR_GAMMA_ENABLE	0x40000000
 #define   CURSOR_STRIDE_SHIFT	28
 #define   CURSOR_STRIDE(x)	((ffs(x)-9) << CURSOR_STRIDE_SHIFT) /* 256,512,1k,2k */
-#define   CURSOR_PIPE_CSC_ENABLE (1<<24)
 #define   CURSOR_FORMAT_SHIFT	24
 #define   CURSOR_FORMAT_MASK	(0x07 << CURSOR_FORMAT_SHIFT)
 #define   CURSOR_FORMAT_2C	(0x00 << CURSOR_FORMAT_SHIFT)
@@ -5928,20 +5927,21 @@ enum {
 #define   CURSOR_FORMAT_ARGB	(0x04 << CURSOR_FORMAT_SHIFT)
 #define   CURSOR_FORMAT_XRGB	(0x05 << CURSOR_FORMAT_SHIFT)
 /* New style CUR*CNTR flags */
-#define   CURSOR_MODE		0x27
-#define   CURSOR_MODE_DISABLE   0x00
-#define   CURSOR_MODE_128_32B_AX 0x02
-#define   CURSOR_MODE_256_32B_AX 0x03
-#define   CURSOR_MODE_64_32B_AX 0x07
-#define   CURSOR_MODE_128_ARGB_AX ((1 << 5) | CURSOR_MODE_128_32B_AX)
-#define   CURSOR_MODE_256_ARGB_AX ((1 << 5) | CURSOR_MODE_256_32B_AX)
-#define   CURSOR_MODE_64_ARGB_AX ((1 << 5) | CURSOR_MODE_64_32B_AX)
+#define   MCURSOR_MODE		0x27
+#define   MCURSOR_MODE_DISABLE   0x00
+#define   MCURSOR_MODE_128_32B_AX 0x02
+#define   MCURSOR_MODE_256_32B_AX 0x03
+#define   MCURSOR_MODE_64_32B_AX 0x07
+#define   MCURSOR_MODE_128_ARGB_AX ((1 << 5) | MCURSOR_MODE_128_32B_AX)
+#define   MCURSOR_MODE_256_ARGB_AX ((1 << 5) | MCURSOR_MODE_256_32B_AX)
+#define   MCURSOR_MODE_64_ARGB_AX ((1 << 5) | MCURSOR_MODE_64_32B_AX)
 #define   MCURSOR_PIPE_SELECT_MASK	(0x3 << 28)
 #define   MCURSOR_PIPE_SELECT_SHIFT	28
 #define   MCURSOR_PIPE_SELECT(pipe)	((pipe) << 28)
 #define   MCURSOR_GAMMA_ENABLE  (1 << 26)
-#define   CURSOR_ROTATE_180	(1<<15)
-#define   CURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
+#define   MCURSOR_PIPE_CSC_ENABLE (1<<24)
+#define   MCURSOR_ROTATE_180	(1<<15)
+#define   MCURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
 #define _CURABASE		0x70084
 #define _CURAPOS		0x70088
 #define   CURSOR_POS_MASK       0x007FF
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 136f129f71c4..3f94fd3e8df2 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9715,7 +9715,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 		cntl |= MCURSOR_GAMMA_ENABLE;
 
 		if (HAS_DDI(dev_priv))
-			cntl |= CURSOR_PIPE_CSC_ENABLE;
+			cntl |= MCURSOR_PIPE_CSC_ENABLE;
 	}
 
 	if (INTEL_GEN(dev_priv) < 5 && !IS_G4X(dev_priv))
@@ -9723,13 +9723,13 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 
 	switch (plane_state->base.crtc_w) {
 	case 64:
-		cntl |= CURSOR_MODE_64_ARGB_AX;
+		cntl |= MCURSOR_MODE_64_ARGB_AX;
 		break;
 	case 128:
-		cntl |= CURSOR_MODE_128_ARGB_AX;
+		cntl |= MCURSOR_MODE_128_ARGB_AX;
 		break;
 	case 256:
-		cntl |= CURSOR_MODE_256_ARGB_AX;
+		cntl |= MCURSOR_MODE_256_ARGB_AX;
 		break;
 	default:
 		MISSING_CASE(plane_state->base.crtc_w);
@@ -9737,7 +9737,7 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 	}
 
 	if (plane_state->base.rotation & DRM_MODE_ROTATE_180)
-		cntl |= CURSOR_ROTATE_180;
+		cntl |= MCURSOR_ROTATE_180;
 
 	return cntl;
 }
@@ -9918,7 +9918,7 @@ static bool i9xx_cursor_get_hw_state(struct intel_plane *plane,
 
 	val = I915_READ(CURCNTR(plane->pipe));
 
-	ret = val & CURSOR_MODE;
+	ret = val & MCURSOR_MODE;
 
 	if (INTEL_GEN(dev_priv) >= 5 || IS_G4X(dev_priv))
 		*pipe = plane->pipe;
@@ -15100,8 +15100,8 @@ void i830_disable_pipe(struct drm_i915_private *dev_priv, enum pipe pipe)
 	WARN_ON(I915_READ(DSPCNTR(PLANE_A)) & DISPLAY_PLANE_ENABLE);
 	WARN_ON(I915_READ(DSPCNTR(PLANE_B)) & DISPLAY_PLANE_ENABLE);
 	WARN_ON(I915_READ(DSPCNTR(PLANE_C)) & DISPLAY_PLANE_ENABLE);
-	WARN_ON(I915_READ(CURCNTR(PIPE_A)) & CURSOR_MODE);
-	WARN_ON(I915_READ(CURCNTR(PIPE_B)) & CURSOR_MODE);
+	WARN_ON(I915_READ(CURCNTR(PIPE_A)) & MCURSOR_MODE);
+	WARN_ON(I915_READ(CURCNTR(PIPE_B)) & MCURSOR_MODE);
 
 	I915_WRITE(PIPECONF(pipe), 0);
 	POSTING_READ(PIPECONF(pipe));
-- 
cgit v1.2.3


From e876b78c5fbf1ef1b5eded8bd4d7ae045ade589a Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 30 Jan 2018 22:38:05 +0200
Subject: drm/i915: Disable trickle feed for SNB/IVB cursors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We disable trickle feed whenever possible, except for the cursors
on SNB/IVB. Let's try disabling it there too if for no other reason
than consistency.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180130203807.13721-5-ville.syrjala@linux.intel.com
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3f94fd3e8df2..0fcad0f0f175 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9711,6 +9711,9 @@ static u32 i9xx_cursor_ctl(const struct intel_crtc_state *crtc_state,
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	u32 cntl = 0;
 
+	if (IS_GEN6(dev_priv) || IS_IVYBRIDGE(dev_priv))
+		cntl |= MCURSOR_TRICKLE_FEED_DISABLE;
+
 	if (INTEL_GEN(dev_priv) <= 10) {
 		cntl |= MCURSOR_GAMMA_ENABLE;
 
-- 
cgit v1.2.3


From 6380db61c54f6e5d6b05598eeb9beaf54c3e21a4 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 30 Jan 2018 22:38:07 +0200
Subject: drm/i915: s/plane/i9xx_plane/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Call the enum i9xx_plane_id variable i9xx_plane like we do elsewhere.

Cc: Hans de Goede <j.w.r.degoede@gmail.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180130203807.13721-7-ville.syrjala@linux.intel.com
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
---
 drivers/gpu/drm/i915/intel_dsi.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index cf39ca90d887..cf1231f9c33b 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -1665,16 +1665,16 @@ static int intel_dsi_get_panel_orientation(struct intel_connector *connector)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
 	int orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
-	enum i9xx_plane_id plane;
+	enum i9xx_plane_id i9xx_plane;
 	u32 val;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
 		if (connector->encoder->crtc_mask == BIT(PIPE_B))
-			plane = PLANE_B;
+			i9xx_plane = PLANE_B;
 		else
-			plane = PLANE_A;
+			i9xx_plane = PLANE_A;
 
-		val = I915_READ(DSPCNTR(plane));
+		val = I915_READ(DSPCNTR(i9xx_plane));
 		if (val & DISPPLANE_ROTATE_180)
 			orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP;
 	}
-- 
cgit v1.2.3


From b4686c481b9b60f9dea12a3001ddbaad6291dc79 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 30 May 2018 19:59:22 +0300
Subject: drm/i915: Fix tabs vs. spaces in sprite code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sprite code has a bunch of spaces where tabs should be used. Fix it
up.

v2: Make the patch subject more specific (Jani)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180530165933.11424-3-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_sprite.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index fe2b44844e8a..350c61cfd1e7 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -1385,8 +1385,8 @@ static bool skl_mod_supported(uint32_t format, uint64_t modifier)
 }
 
 static bool intel_sprite_plane_format_mod_supported(struct drm_plane *plane,
-                                                    uint32_t format,
-                                                    uint64_t modifier)
+						    uint32_t format,
+						    uint64_t modifier)
 {
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
 
@@ -1408,14 +1408,14 @@ static bool intel_sprite_plane_format_mod_supported(struct drm_plane *plane,
 }
 
 static const struct drm_plane_funcs intel_sprite_plane_funcs = {
-        .update_plane = drm_atomic_helper_update_plane,
-        .disable_plane = drm_atomic_helper_disable_plane,
-        .destroy = intel_plane_destroy,
-        .atomic_get_property = intel_plane_atomic_get_property,
-        .atomic_set_property = intel_plane_atomic_set_property,
-        .atomic_duplicate_state = intel_plane_duplicate_state,
-        .atomic_destroy_state = intel_plane_destroy_state,
-        .format_mod_supported = intel_sprite_plane_format_mod_supported,
+	.update_plane = drm_atomic_helper_update_plane,
+	.disable_plane = drm_atomic_helper_disable_plane,
+	.destroy = intel_plane_destroy,
+	.atomic_get_property = intel_plane_atomic_get_property,
+	.atomic_set_property = intel_plane_atomic_set_property,
+	.atomic_duplicate_state = intel_plane_duplicate_state,
+	.atomic_destroy_state = intel_plane_destroy_state,
+	.format_mod_supported = intel_sprite_plane_format_mod_supported,
 };
 
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
-- 
cgit v1.2.3


From 012d79e6a33f095c293fe2a02b2b3b26d8c6402c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 21 May 2018 21:56:12 +0300
Subject: drm/i915: Remove bogus NV12 PLANE_COLOR_CTL setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We already handle the color encoding mode properly. Remove the broken
NV12 special case.

Cc: Vidya Srinivas <vidya.srinivas@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Fixes: 8ed30ab6aced ("drm/i915: Enable YUV to RGB for Gen10 in Plane Ctrl Reg")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521185613.5097-1-ville.syrjala@linux.intel.com
Reviewed-By: Vidya Srinivas <vidya.srinivas@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 0fcad0f0f175..b42231280418 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3659,11 +3659,6 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 	plane_color_ctl |= glk_plane_color_ctl_alpha(fb->format->format);
 
 	if (intel_format_is_yuv(fb->format->format)) {
-		if (fb->format->format == DRM_FORMAT_NV12) {
-			plane_color_ctl |=
-				PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
-			goto out;
-		}
 		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
 		else
@@ -3672,7 +3667,7 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 		if (plane_state->base.color_range == DRM_COLOR_YCBCR_FULL_RANGE)
 			plane_color_ctl |= PLANE_COLOR_YUV_RANGE_CORRECTION_DISABLE;
 	}
-out:
+
 	return plane_color_ctl;
 }
 
-- 
cgit v1.2.3


From 0a59952b24e24e153b8d1cbd781c8d264257b1b3 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 21 May 2018 21:56:13 +0300
Subject: drm/i915: Configure SKL+ scaler initial phase correctly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set up the SKL+ scaler initial phase registers correctly. Otherwise
we start fetching the data from the center of the first pixel instead
of the top-left corner, which obviously then leads to right/bottom edges
replicating data excessively as the data runs out half a pixel too soon.

Cc: Vidya Srinivas <vidya.srinivas@intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180521185613.5097-2-ville.syrjala@linux.intel.com
Reviewed-By: Vidya Srinivas <vidya.srinivas@intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h      |  4 ++++
 drivers/gpu/drm/i915/intel_display.c | 41 ++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_drv.h     |  1 +
 drivers/gpu/drm/i915/intel_sprite.c  | 26 +++++++++++++++++++++--
 4 files changed, 70 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 749d23811749..43397e50fec3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -6789,6 +6789,10 @@ enum {
 #define _PS_VPHASE_1B       0x68988
 #define _PS_VPHASE_2B       0x68A88
 #define _PS_VPHASE_1C       0x69188
+#define  PS_Y_PHASE(x)		((x) << 16)
+#define  PS_UV_RGB_PHASE(x)	((x) << 0)
+#define   PS_PHASE_MASK	(0x7fff << 1) /* u2.13 */
+#define   PS_PHASE_TRIP	(1 << 0)
 
 #define _PS_HPHASE_1A       0x68194
 #define _PS_HPHASE_2A       0x68294
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b42231280418..141ded524482 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -4752,6 +4752,39 @@ static void cpt_verify_modeset(struct drm_device *dev, int pipe)
 	}
 }
 
+/*
+ * The hardware phase 0.0 refers to the center of the pixel.
+ * We want to start from the top/left edge which is phase
+ * -0.5. That matches how the hardware calculates the scaling
+ * factors (from top-left of the first pixel to bottom-right
+ * of the last pixel, as opposed to the pixel centers).
+ *
+ * For 4:2:0 subsampled chroma planes we obviously have to
+ * adjust that so that the chroma sample position lands in
+ * the right spot.
+ *
+ * Note that for packed YCbCr 4:2:2 formats there is no way to
+ * control chroma siting. The hardware simply replicates the
+ * chroma samples for both of the luma samples, and thus we don't
+ * actually get the expected MPEG2 chroma siting convention :(
+ * The same behaviour is observed on pre-SKL platforms as well.
+ */
+u16 skl_scaler_calc_phase(int sub, bool chroma_cosited)
+{
+	int phase = -0x8000;
+	u16 trip = 0;
+
+	if (chroma_cosited)
+		phase += (sub - 1) * 0x8000 / sub;
+
+	if (phase < 0)
+		phase = 0x10000 + phase;
+	else
+		trip = PS_PHASE_TRIP;
+
+	return ((phase >> 2) & PS_PHASE_MASK) | trip;
+}
+
 static int
 skl_update_scaler(struct intel_crtc_state *crtc_state, bool force_detach,
 		  unsigned int scaler_user, int *scaler_id,
@@ -4951,14 +4984,22 @@ static void skylake_pfit_enable(struct intel_crtc *crtc)
 		&crtc->config->scaler_state;
 
 	if (crtc->config->pch_pfit.enabled) {
+		u16 uv_rgb_hphase, uv_rgb_vphase;
 		int id;
 
 		if (WARN_ON(crtc->config->scaler_state.scaler_id < 0))
 			return;
 
+		uv_rgb_hphase = skl_scaler_calc_phase(1, false);
+		uv_rgb_vphase = skl_scaler_calc_phase(1, false);
+
 		id = scaler_state->scaler_id;
 		I915_WRITE(SKL_PS_CTRL(pipe, id), PS_SCALER_EN |
 			PS_FILTER_MEDIUM | scaler_state->scalers[id].mode);
+		I915_WRITE_FW(SKL_PS_VPHASE(pipe, id),
+			      PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+		I915_WRITE_FW(SKL_PS_HPHASE(pipe, id),
+			      PS_Y_PHASE(0) | PS_UV_RGB_PHASE(uv_rgb_hphase));
 		I915_WRITE(SKL_PS_WIN_POS(pipe, id), crtc->config->pch_pfit.pos);
 		I915_WRITE(SKL_PS_WIN_SZ(pipe, id), crtc->config->pch_pfit.size);
 	}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 1a4659a2e000..b1bb1a9d61f8 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1616,6 +1616,7 @@ void intel_mode_from_pipe_config(struct drm_display_mode *mode,
 void intel_crtc_arm_fifo_underrun(struct intel_crtc *crtc,
 				  struct intel_crtc_state *crtc_state);
 
+u16 skl_scaler_calc_phase(int sub, bool chroma_center);
 int skl_update_scaler_crtc(struct intel_crtc_state *crtc_state);
 int skl_max_scale(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 		  uint32_t pixel_format);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 350c61cfd1e7..24f86c4375cf 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -284,13 +284,35 @@ skl_update_plane(struct intel_plane *plane,
 	/* program plane scaler */
 	if (plane_state->scaler_id >= 0) {
 		int scaler_id = plane_state->scaler_id;
-		const struct intel_scaler *scaler;
+		const struct intel_scaler *scaler =
+			&crtc_state->scaler_state.scalers[scaler_id];
+		u16 y_hphase, uv_rgb_hphase;
+		u16 y_vphase, uv_rgb_vphase;
+
+		/* TODO: handle sub-pixel coordinates */
+		if (fb->format->format == DRM_FORMAT_NV12) {
+			y_hphase = skl_scaler_calc_phase(1, false);
+			y_vphase = skl_scaler_calc_phase(1, false);
+
+			/* MPEG2 chroma siting convention */
+			uv_rgb_hphase = skl_scaler_calc_phase(2, true);
+			uv_rgb_vphase = skl_scaler_calc_phase(2, false);
+		} else {
+			/* not used */
+			y_hphase = 0;
+			y_vphase = 0;
 
-		scaler = &crtc_state->scaler_state.scalers[scaler_id];
+			uv_rgb_hphase = skl_scaler_calc_phase(1, false);
+			uv_rgb_vphase = skl_scaler_calc_phase(1, false);
+		}
 
 		I915_WRITE_FW(SKL_PS_CTRL(pipe, scaler_id),
 			      PS_SCALER_EN | PS_PLANE_SEL(plane_id) | scaler->mode);
 		I915_WRITE_FW(SKL_PS_PWR_GATE(pipe, scaler_id), 0);
+		I915_WRITE_FW(SKL_PS_VPHASE(pipe, scaler_id),
+			      PS_Y_PHASE(y_vphase) | PS_UV_RGB_PHASE(uv_rgb_vphase));
+		I915_WRITE_FW(SKL_PS_HPHASE(pipe, scaler_id),
+			      PS_Y_PHASE(y_hphase) | PS_UV_RGB_PHASE(uv_rgb_hphase));
 		I915_WRITE_FW(SKL_PS_WIN_POS(pipe, scaler_id), (crtc_x << 16) | crtc_y);
 		I915_WRITE_FW(SKL_PS_WIN_SZ(pipe, scaler_id),
 			      ((crtc_w + 1) << 16)|(crtc_h + 1));
-- 
cgit v1.2.3


From 9776f47253c3d953db8f9e33b3d75105f293ca70 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 1 Jun 2018 15:41:24 +0100
Subject: drm/i915: Flush all writes before suspend

As we have already suspended the device, this should be a no-op except
for marking that all writes are indeed complete. The downside is that
we then have to walk all the lists of objects for what should be a no-op
(in some cases they will be mmio read to ensure the GGTT writes are
indeed flushed, and clflushes to ensure that cpu writes are in memory).

It seems prudent and the safer course for us to ensure all writes are
flushed to memory before suspend.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180601144125.18026-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c85951f2b15a..f77cffcd8792 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5071,6 +5071,13 @@ err_unlock:
 
 void i915_gem_suspend_late(struct drm_i915_private *i915)
 {
+	struct drm_i915_gem_object *obj;
+	struct list_head *phases[] = {
+		&i915->mm.unbound_list,
+		&i915->mm.bound_list,
+		NULL
+	}, **phase;
+
 	/*
 	 * Neither the BIOS, ourselves or any other kernel
 	 * expects the system to be in execlists mode on startup,
@@ -5091,6 +5098,13 @@ void i915_gem_suspend_late(struct drm_i915_private *i915)
 	 * machine in an unusable condition.
 	 */
 
+	mutex_lock(&i915->drm.struct_mutex);
+	for (phase = phases; *phase; phase++) {
+		list_for_each_entry(obj, *phase, mm.link)
+			WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
+	}
+	mutex_unlock(&i915->drm.struct_mutex);
+
 	intel_uc_sanitize(i915);
 	i915_gem_sanitize(i915);
 }
-- 
cgit v1.2.3


From 95c778daecb5cd5aafcc09ebf1353fdc759b6fd7 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 1 Jun 2018 15:41:25 +0100
Subject: drm/i915: Apply the full CPU domain markup before freezing

Let's not take any chances by using a shortcut to mark the objects as in
the CPU domain upon freezing (all pages will be written to disk and so
on restore all objects will start from the CPU domain). Currently, we
simply mark the objects as being in the CPU domain, bypassing the
flushes. Let's call the full domain transfer function so that we have
less special case code (and symmetry with the suspend path) even though
it will be mostly redundant.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180601144125.18026-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index f77cffcd8792..62974e8862d5 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5718,16 +5718,17 @@ int i915_gem_freeze(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
-int i915_gem_freeze_late(struct drm_i915_private *dev_priv)
+int i915_gem_freeze_late(struct drm_i915_private *i915)
 {
 	struct drm_i915_gem_object *obj;
 	struct list_head *phases[] = {
-		&dev_priv->mm.unbound_list,
-		&dev_priv->mm.bound_list,
+		&i915->mm.unbound_list,
+		&i915->mm.bound_list,
 		NULL
-	}, **p;
+	}, **phase;
 
-	/* Called just before we write the hibernation image.
+	/*
+	 * Called just before we write the hibernation image.
 	 *
 	 * We need to update the domain tracking to reflect that the CPU
 	 * will be accessing all the pages to create and restore from the
@@ -5741,15 +5742,15 @@ int i915_gem_freeze_late(struct drm_i915_private *dev_priv)
 	 * the objects as well, see i915_gem_freeze()
 	 */
 
-	i915_gem_shrink(dev_priv, -1UL, NULL, I915_SHRINK_UNBOUND);
-	i915_gem_drain_freed_objects(dev_priv);
+	i915_gem_shrink(i915, -1UL, NULL, I915_SHRINK_UNBOUND);
+	i915_gem_drain_freed_objects(i915);
 
-	spin_lock(&dev_priv->mm.obj_lock);
-	for (p = phases; *p; p++) {
-		list_for_each_entry(obj, *p, mm.link)
-			__start_cpu_write(obj);
+	mutex_lock(&i915->drm.struct_mutex);
+	for (phase = phases; *phase; phase++) {
+		list_for_each_entry(obj, *phase, mm.link)
+			WARN_ON(i915_gem_object_set_to_cpu_domain(obj, true));
 	}
-	spin_unlock(&dev_priv->mm.obj_lock);
+	mutex_unlock(&i915->drm.struct_mutex);
 
 	return 0;
 }
-- 
cgit v1.2.3


From c46ef57d2008e5195f086a538550488b49644db7 Mon Sep 17 00:00:00 2001
From: Mahesh Kumar <mahesh1.kumar@intel.com>
Date: Fri, 25 May 2018 08:52:38 -0700
Subject: drm/i915/icl: fix icl_unmap/map_plls_to_ports

All connectors may not have best_encoder attached, so don't dereference
encoder pointer for each connector.

Fixes: c27e917e2bda ("drm/i915/icl: add basic support for the ICL clocks")
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525155238.7054-1-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/intel_ddi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 3b8f12883ca7..c33b19705e39 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -2444,12 +2444,13 @@ void icl_map_plls_to_ports(struct drm_crtc *crtc,
 	for_each_new_connector_in_state(old_state, conn, conn_state, i) {
 		struct intel_encoder *encoder =
 			to_intel_encoder(conn_state->best_encoder);
-		enum port port = encoder->port;
+		enum port port;
 		uint32_t val;
 
 		if (conn_state->crtc != crtc)
 			continue;
 
+		port = encoder->port;
 		mutex_lock(&dev_priv->dpll_lock);
 
 		val = I915_READ(DPCLKA_CFGCR0_ICL);
@@ -2481,11 +2482,12 @@ void icl_unmap_plls_to_ports(struct drm_crtc *crtc,
 	for_each_old_connector_in_state(old_state, conn, old_conn_state, i) {
 		struct intel_encoder *encoder =
 			to_intel_encoder(old_conn_state->best_encoder);
-		enum port port = encoder->port;
+		enum port port;
 
 		if (old_conn_state->crtc != crtc)
 			continue;
 
+		port = encoder->port;
 		mutex_lock(&dev_priv->dpll_lock);
 		I915_WRITE(DPCLKA_CFGCR0_ICL,
 			   I915_READ(DPCLKA_CFGCR0_ICL) |
-- 
cgit v1.2.3


From 9bb635d9e7dbfd8e0bc352457c70e75d612c7edb Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Mon, 21 May 2018 17:25:35 -0700
Subject: drm/i915/icl: Extend AUX F interrupts to ICL

ICL has AUX F.

Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-2-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_irq.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index f9bc3aaa90d0..2fd92a886789 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2640,7 +2640,8 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 					    GEN9_AUX_CHANNEL_C |
 					    GEN9_AUX_CHANNEL_D;
 
-			if (IS_CNL_WITH_PORT_F(dev_priv))
+			if (IS_CNL_WITH_PORT_F(dev_priv) ||
+			    INTEL_GEN(dev_priv) >= 11)
 				tmp_mask |= CNL_AUX_CHANNEL_F;
 
 			if (iir & tmp_mask) {
@@ -3920,7 +3921,7 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 		de_pipe_masked |= GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
 	}
 
-	if (IS_CNL_WITH_PORT_F(dev_priv))
+	if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11)
 		de_port_masked |= CNL_AUX_CHANNEL_F;
 
 	de_pipe_enables = de_pipe_masked | GEN8_PIPE_VBLANK |
-- 
cgit v1.2.3


From ac213c1b45f7dcedb71d955c2321cbb4a2b6558e Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Mon, 21 May 2018 17:25:37 -0700
Subject: drm/i915/icl: introduce tc_port

Add and enum for TC ports and auxiliary functions to handle them.
Icelake brings a lot of registers and other things that only apply to
the TC ports and are indexed starting from 0, so having an enum for
tc_ports that starts at 0 really helps the indexing.

This patch is based on previous patches written by Dhinakaran Pandiyan
and Mahesh Kumar.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Mahesh Kumar <mahesh1.kumar@intel.com>
Reviewed-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-4-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_display.c | 16 ++++++++++++++++
 drivers/gpu/drm/i915/intel_display.h | 11 +++++++++++
 drivers/gpu/drm/i915/intel_drv.h     |  3 +++
 3 files changed, 30 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 141ded524482..17c590b42fd7 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5869,6 +5869,22 @@ static void i9xx_pfit_enable(struct intel_crtc *crtc)
 	I915_WRITE(BCLRPAT(crtc->pipe), 0);
 }
 
+bool intel_port_is_tc(struct drm_i915_private *dev_priv, enum port port)
+{
+	if (IS_ICELAKE(dev_priv))
+		return port >= PORT_C && port <= PORT_F;
+
+	return false;
+}
+
+enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv, enum port port)
+{
+	if (!intel_port_is_tc(dev_priv, port))
+		return PORT_TC_NONE;
+
+	return port - PORT_C;
+}
+
 enum intel_display_power_domain intel_port_to_power_domain(enum port port)
 {
 	switch (port) {
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index 2ef31617614a..c88185ed7594 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -126,6 +126,17 @@ enum port {
 
 #define port_name(p) ((p) + 'A')
 
+enum tc_port {
+	PORT_TC_NONE = -1,
+
+	PORT_TC1 = 0,
+	PORT_TC2,
+	PORT_TC3,
+	PORT_TC4,
+
+	I915_MAX_TC_PORTS
+};
+
 enum dpio_channel {
 	DPIO_CH0,
 	DPIO_CH1
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index b1bb1a9d61f8..8641583842be 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1489,6 +1489,9 @@ void intel_connector_attach_encoder(struct intel_connector *connector,
 				    struct intel_encoder *encoder);
 struct drm_display_mode *
 intel_encoder_current_mode(struct intel_encoder *encoder);
+bool intel_port_is_tc(struct drm_i915_private *dev_priv, enum port port);
+enum tc_port intel_port_to_tc(struct drm_i915_private *dev_priv,
+			      enum port port);
 
 enum pipe intel_get_pipe_from_connector(struct intel_connector *connector);
 int intel_get_pipe_from_crtc_id_ioctl(struct drm_device *dev, void *data,
-- 
cgit v1.2.3


From a2bc69a1a9d6820976dfa014a6e7dcc53c585793 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Fri, 25 May 2018 12:03:52 -0700
Subject: drm/i915/icl: Add register definition for DFLEXDPMLE

DFLEXDPMLE register is required to tell the FIA hardware which
main links of DP are enabled on TCC Connectors. FIA uses this
information to program PHY to Controller signal mapping.
This register is applicable in both TC connector's Alternate mode
as well as DP connector mode.

v2:
* Remove _ICL prefix since the reg is first introduced
in ICL (Paulo)
* s/ICL/icl in commit message (Lucas)

Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527275032-4555-1-git-send-email-manasi.d.navare@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 43397e50fec3..5866b7d0ad81 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1990,6 +1990,11 @@ enum i915_power_well_id {
 						   _ICL_PORT_COMP_DW10_A, \
 						   _ICL_PORT_COMP_DW10_B)
 
+/* ICL PHY DFLEX registers */
+#define PORT_TX_DFLEXDPMLE1		_MMIO(0x1638C0)
+#define   DFLEXDPMLE1_DPMLETC_MASK(n)	(0xf << (4 * (n)))
+#define   DFLEXDPMLE1_DPMLETC(n, x)	((x) << (4 * (n)))
+
 /* BXT PHY Ref registers */
 #define _PORT_REF_DW3_A			0x16218C
 #define _PORT_REF_DW3_BC		0x6C18C
-- 
cgit v1.2.3


From 3937eb1a076f251ecc29330a0b6ca10dbe2e633b Mon Sep 17 00:00:00 2001
From: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Date: Mon, 21 May 2018 17:25:42 -0700
Subject: drm/i915/icl: Map VBT DDC Pin to BSpec DDC Pin
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ICL we need to map VBT DDC Pin to BSpec DDC Pin.
Adding ICL Pin Values.

According to VBT
Block 2 (General Bytes Definition)
DDC Bus

+----------+-----------+--------------------+
| DDI Type | VBT Value | BSpec Mapped Value |
+----------+-----------+--------------------+
| DDI-A    | 0x1       | 0x1                |
| DDI-B    | 0x2       | 0x2                |
| PORT-1   | 0x4       | 0x9                |
| PORT-2   | 0x5       | 0xA                |
| PORT-3   | 0x6       | 0xB                |
| PORT-4   | 0x7       | 0xC                |
+----------+-----------+--------------------+

Cc: James Ausmus <james.ausmus@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Clinton Taylor <clinton.a.taylor@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
[Paulo: checkpatch fixes.]
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-9-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_bios.c     | 35 +++++++++++++++++++++++++++--------
 drivers/gpu/drm/i915/intel_vbt_defs.h |  6 ++++++
 2 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 1cf073b6ac8a..465dff4780fe 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1259,18 +1259,37 @@ static const u8 cnp_ddc_pin_map[] = {
 	[DDC_BUS_DDI_F] = GMBUS_PIN_3_BXT, /* sic */
 };
 
+static const u8 icp_ddc_pin_map[] = {
+	[ICL_DDC_BUS_DDI_A] = GMBUS_PIN_1_BXT,
+	[ICL_DDC_BUS_DDI_B] = GMBUS_PIN_2_BXT,
+	[ICL_DDC_BUS_PORT_1] = GMBUS_PIN_9_TC1_ICP,
+	[ICL_DDC_BUS_PORT_2] = GMBUS_PIN_10_TC2_ICP,
+	[ICL_DDC_BUS_PORT_3] = GMBUS_PIN_11_TC3_ICP,
+	[ICL_DDC_BUS_PORT_4] = GMBUS_PIN_12_TC4_ICP,
+};
+
 static u8 map_ddc_pin(struct drm_i915_private *dev_priv, u8 vbt_pin)
 {
-	if (HAS_PCH_CNP(dev_priv)) {
-		if (vbt_pin < ARRAY_SIZE(cnp_ddc_pin_map)) {
-			return cnp_ddc_pin_map[vbt_pin];
-		} else {
-			DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n", vbt_pin);
-			return 0;
-		}
+	const u8 *ddc_pin_map;
+	int n_entries;
+
+	if (HAS_PCH_ICP(dev_priv)) {
+		ddc_pin_map = icp_ddc_pin_map;
+		n_entries = ARRAY_SIZE(icp_ddc_pin_map);
+	} else if (HAS_PCH_CNP(dev_priv)) {
+		ddc_pin_map = cnp_ddc_pin_map;
+		n_entries = ARRAY_SIZE(cnp_ddc_pin_map);
+	} else {
+		/* Assuming direct map */
+		return vbt_pin;
 	}
 
-	return vbt_pin;
+	if (vbt_pin < n_entries && ddc_pin_map[vbt_pin] != 0)
+		return ddc_pin_map[vbt_pin];
+
+	DRM_DEBUG_KMS("Ignoring alternate pin: VBT claims DDC pin %d, which is not valid for this platform\n",
+		      vbt_pin);
+	return 0;
 }
 
 static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index 39c804624179..c132d0c3a500 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -318,6 +318,12 @@ enum vbt_gmbus_ddi {
 	DDC_BUS_DDI_C,
 	DDC_BUS_DDI_D,
 	DDC_BUS_DDI_F,
+	ICL_DDC_BUS_DDI_A = 0x1,
+	ICL_DDC_BUS_DDI_B,
+	ICL_DDC_BUS_PORT_1 = 0x4,
+	ICL_DDC_BUS_PORT_2,
+	ICL_DDC_BUS_PORT_3,
+	ICL_DDC_BUS_PORT_4,
 };
 
 #define VBT_DP_MAX_LINK_RATE_HBR3	0
-- 
cgit v1.2.3


From f17ca5010c34e99e4035f22437f8b83452584a26 Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Mon, 21 May 2018 17:25:43 -0700
Subject: drm/i915/icl: Add Icelake PCH detection

This patch adds the support to detect PCH_ICP.

Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Suggested-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-10-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index fe92665c8482..915758a65c96 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -233,6 +233,8 @@ intel_virt_detect_pch(const struct drm_i915_private *dev_priv)
 		id = INTEL_PCH_SPT_DEVICE_ID_TYPE;
 	else if (IS_COFFEELAKE(dev_priv) || IS_CANNONLAKE(dev_priv))
 		id = INTEL_PCH_CNP_DEVICE_ID_TYPE;
+	else if (IS_ICELAKE(dev_priv))
+		id = INTEL_PCH_ICP_DEVICE_ID_TYPE;
 
 	if (id)
 		DRM_DEBUG_KMS("Assuming PCH ID %04x\n", id);
-- 
cgit v1.2.3


From 51c83cfaf96382ab65717d694f80af86482ba795 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Wed, 23 May 2018 15:44:44 -0700
Subject: drm/i915/icl: Get DDI clock for ICL based on PLLs.

PLLs are the source clocks for the DDIs so in order
to determine the ddi clock we need to check the PLL
configuration.

This gets a little tricky for ICL since there is
no register bit that maps directly to the link clock.
So this patch creates a separate function in intel_dpll_mgr.c
to obtain the write array PLL Params and compares the set
pll_params with the table to get the corresponding link
clock.

v2:
  - Fix the encoder type check (DK).
  - Improve our error checking, return a sane value (Mika, Paulo).
  - Fix table entries (Paulo).

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Mika Kahola <mika.kahola@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Mika Kahola <mika.kahola@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
[Paulo: implement v2]
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180523224444.19017-1-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h       |  3 ++
 drivers/gpu/drm/i915/intel_ddi.c      | 26 +++++++++++++
 drivers/gpu/drm/i915/intel_dpll_mgr.c | 70 +++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_dpll_mgr.h |  2 +
 4 files changed, 101 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5866b7d0ad81..f0317bde3aab 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9127,13 +9127,16 @@ enum skl_power_gate {
 #define  DPLL_CFGCR1_QDIV_RATIO_MASK	(0xff << 10)
 #define  DPLL_CFGCR1_QDIV_RATIO_SHIFT	(10)
 #define  DPLL_CFGCR1_QDIV_RATIO(x)	((x) << 10)
+#define  DPLL_CFGCR1_QDIV_MODE_SHIFT	(9)
 #define  DPLL_CFGCR1_QDIV_MODE(x)	((x) << 9)
 #define  DPLL_CFGCR1_KDIV_MASK		(7 << 6)
+#define  DPLL_CFGCR1_KDIV_SHIFT		(6)
 #define  DPLL_CFGCR1_KDIV(x)		((x) << 6)
 #define  DPLL_CFGCR1_KDIV_1		(1 << 6)
 #define  DPLL_CFGCR1_KDIV_2		(2 << 6)
 #define  DPLL_CFGCR1_KDIV_4		(4 << 6)
 #define  DPLL_CFGCR1_PDIV_MASK		(0xf << 2)
+#define  DPLL_CFGCR1_PDIV_SHIFT		(2)
 #define  DPLL_CFGCR1_PDIV(x)		((x) << 2)
 #define  DPLL_CFGCR1_PDIV_2		(1 << 2)
 #define  DPLL_CFGCR1_PDIV_3		(2 << 2)
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index c33b19705e39..3f042c505430 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1422,6 +1422,30 @@ static void ddi_dotclock_get(struct intel_crtc_state *pipe_config)
 	pipe_config->base.adjusted_mode.crtc_clock = dotclock;
 }
 
+static void icl_ddi_clock_get(struct intel_encoder *encoder,
+			      struct intel_crtc_state *pipe_config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	enum port port = encoder->port;
+	int link_clock = 0;
+	uint32_t pll_id;
+
+	pll_id = intel_get_shared_dpll_id(dev_priv, pipe_config->shared_dpll);
+	if (port == PORT_A || port == PORT_B) {
+		if (intel_crtc_has_type(pipe_config, INTEL_OUTPUT_HDMI))
+			link_clock = cnl_calc_wrpll_link(dev_priv, pll_id);
+		else
+			link_clock = icl_calc_dp_combo_pll_link(dev_priv,
+								pll_id);
+	} else {
+		/* FIXME - Add for MG PLL */
+		WARN(1, "MG PLL clock_get code not implemented yet\n");
+	}
+
+	pipe_config->port_clock = link_clock;
+	ddi_dotclock_get(pipe_config);
+}
+
 static void cnl_ddi_clock_get(struct intel_encoder *encoder,
 			      struct intel_crtc_state *pipe_config)
 {
@@ -1615,6 +1639,8 @@ static void intel_ddi_clock_get(struct intel_encoder *encoder,
 		bxt_ddi_clock_get(encoder, pipe_config);
 	else if (IS_CANNONLAKE(dev_priv))
 		cnl_ddi_clock_get(encoder, pipe_config);
+	else if (IS_ICELAKE(dev_priv))
+		icl_ddi_clock_get(encoder, pipe_config);
 }
 
 void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state)
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 383fbc15113d..07bdbf2582ba 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -2525,6 +2525,76 @@ static bool icl_calc_dpll_state(struct intel_crtc_state *crtc_state,
 	return true;
 }
 
+int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv,
+			       uint32_t pll_id)
+{
+	uint32_t cfgcr0, cfgcr1;
+	uint32_t pdiv, kdiv, qdiv_mode, qdiv_ratio, dco_integer, dco_fraction;
+	const struct skl_wrpll_params *params;
+	int index, n_entries, link_clock;
+
+	/* Read back values from DPLL CFGCR registers */
+	cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(pll_id));
+	cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(pll_id));
+
+	dco_integer = cfgcr0 & DPLL_CFGCR0_DCO_INTEGER_MASK;
+	dco_fraction = (cfgcr0 & DPLL_CFGCR0_DCO_FRACTION_MASK) >>
+		DPLL_CFGCR0_DCO_FRACTION_SHIFT;
+	pdiv = (cfgcr1 & DPLL_CFGCR1_PDIV_MASK) >> DPLL_CFGCR1_PDIV_SHIFT;
+	kdiv = (cfgcr1 & DPLL_CFGCR1_KDIV_MASK) >> DPLL_CFGCR1_KDIV_SHIFT;
+	qdiv_mode = (cfgcr1 & DPLL_CFGCR1_QDIV_MODE(1)) >>
+		DPLL_CFGCR1_QDIV_MODE_SHIFT;
+	qdiv_ratio = (cfgcr1 & DPLL_CFGCR1_QDIV_RATIO_MASK) >>
+		DPLL_CFGCR1_QDIV_RATIO_SHIFT;
+
+	params = dev_priv->cdclk.hw.ref == 24000 ?
+		icl_dp_combo_pll_24MHz_values :
+		icl_dp_combo_pll_19_2MHz_values;
+	n_entries = ARRAY_SIZE(icl_dp_combo_pll_24MHz_values);
+
+	for (index = 0; index < n_entries; index++) {
+		if (dco_integer == params[index].dco_integer &&
+		    dco_fraction == params[index].dco_fraction &&
+		    pdiv == params[index].pdiv &&
+		    kdiv == params[index].kdiv &&
+		    qdiv_mode == params[index].qdiv_mode &&
+		    qdiv_ratio == params[index].qdiv_ratio)
+			break;
+	}
+
+	/* Map PLL Index to Link Clock */
+	switch (index) {
+	default:
+		MISSING_CASE(index);
+	case 0:
+		link_clock = 540000;
+		break;
+	case 1:
+		link_clock = 270000;
+		break;
+	case 2:
+		link_clock = 162000;
+		break;
+	case 3:
+		link_clock = 324000;
+		break;
+	case 4:
+		link_clock = 216000;
+		break;
+	case 5:
+		link_clock = 432000;
+		break;
+	case 6:
+		link_clock = 648000;
+		break;
+	case 7:
+		link_clock = 810000;
+		break;
+	}
+
+	return link_clock;
+}
+
 static enum port icl_mg_pll_id_to_port(enum intel_dpll_id id)
 {
 	return id - DPLL_ID_ICL_MGPLL1 + PORT_C;
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h
index 7a0cd564a9ee..78915057d2e6 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h
@@ -336,5 +336,7 @@ void intel_shared_dpll_init(struct drm_device *dev);
 
 void intel_dpll_dump_hw_state(struct drm_i915_private *dev_priv,
 			      struct intel_dpll_hw_state *hw_state);
+int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv,
+			       uint32_t pll_id);
 
 #endif /* _INTEL_DPLL_MGR_H_ */
-- 
cgit v1.2.3


From 5428bf5a9a9f28fae1ba2c57ba4ea8f8d358d10c Mon Sep 17 00:00:00 2001
From: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Date: Mon, 21 May 2018 17:25:46 -0700
Subject: drm/i915/icl: Calculate link clock using the new registers

Start using the new registers for ICL and on.

Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Arkadiusz Hiler <arkadiusz.hiler@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-13-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_ddi.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 3f042c505430..b344e0fe08fd 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1345,8 +1345,13 @@ static int cnl_calc_wrpll_link(struct drm_i915_private *dev_priv,
 	uint32_t cfgcr0, cfgcr1;
 	uint32_t p0, p1, p2, dco_freq, ref_clock;
 
-	cfgcr0 = I915_READ(CNL_DPLL_CFGCR0(pll_id));
-	cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(pll_id));
+	if (INTEL_GEN(dev_priv) >= 11) {
+		cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(pll_id));
+		cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(pll_id));
+	} else {
+		cfgcr0 = I915_READ(CNL_DPLL_CFGCR0(pll_id));
+		cfgcr1 = I915_READ(CNL_DPLL_CFGCR1(pll_id));
+	}
 
 	p0 = cfgcr1 & DPLL_CFGCR1_PDIV_MASK;
 	p2 = cfgcr1 & DPLL_CFGCR1_KDIV_MASK;
-- 
cgit v1.2.3


From 6931317c714885f2d792e8150ef6715d416ac681 Mon Sep 17 00:00:00 2001
From: Lubosz Sarnecki <lubosz.sarnecki@collabora.com>
Date: Tue, 29 May 2018 13:52:15 +0200
Subject: drm/edid: Quirk Vive Pro VR headset non-desktop.

This adds the Vive Pro's EDID information and
sets EDID_QUIRK_NON_DESKTOP.

Signed-off-by: Lubosz Sarnecki <lubosz.sarnecki@collabora.com>
Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Daniel Stone <daniels@collabora.com>
Cc: <stable@vger.kernel.org> # v4.15+
Link: https://patchwork.freedesktop.org/patch/msgid/20180529115215.4526-1-lubosz.sarnecki@collabora.com
---
 drivers/gpu/drm/drm_edid.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index 634a68a03b07..87654b8b279c 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -163,8 +163,9 @@ static const struct edid_quirk {
 	/* Rotel RSX-1058 forwards sink's EDID but only does HDMI 1.1*/
 	{ "ETR", 13896, EDID_QUIRK_FORCE_8BPC },
 
-	/* HTC Vive VR Headset */
+	/* HTC Vive and Vive Pro VR Headsets */
 	{ "HVR", 0xaa01, EDID_QUIRK_NON_DESKTOP },
+	{ "HVR", 0xaa02, EDID_QUIRK_NON_DESKTOP },
 
 	/* Oculus Rift DK1, DK2, and CV1 VR Headsets */
 	{ "OVR", 0x0001, EDID_QUIRK_NON_DESKTOP },
-- 
cgit v1.2.3


From 8979187a8cfa1fd221a17a06a9ce76e72ae52a05 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Mon, 4 Jun 2018 09:00:32 +0000
Subject: drm/i915: Move i915_gem_fini to i915_gem.c

We should keep i915_gem_init/fini functions together for easier
tracking of their symmetry.

v2: rebased, pulled out from the series

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604090032.20840-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 22 ----------------------
 drivers/gpu/drm/i915/i915_drv.h |  1 +
 drivers/gpu/drm/i915/i915_gem.c | 22 ++++++++++++++++++++++
 3 files changed, 23 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 915758a65c96..83ce9c1ec170 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -636,28 +636,6 @@ static const struct vga_switcheroo_client_ops i915_switcheroo_ops = {
 	.can_switch = i915_switcheroo_can_switch,
 };
 
-static void i915_gem_fini(struct drm_i915_private *dev_priv)
-{
-	i915_gem_suspend_late(dev_priv);
-
-	/* Flush any outstanding unpin_work. */
-	i915_gem_drain_workqueue(dev_priv);
-
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	intel_uc_fini_hw(dev_priv);
-	intel_uc_fini(dev_priv);
-	i915_gem_cleanup_engines(dev_priv);
-	i915_gem_contexts_fini(dev_priv);
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
-	intel_uc_fini_misc(dev_priv);
-	i915_gem_cleanup_userptr(dev_priv);
-
-	i915_gem_drain_freed_objects(dev_priv);
-
-	WARN_ON(!list_empty(&dev_priv->contexts.list));
-}
-
 static int i915_load_modeset_init(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 38157df6ff5c..ecc888a97279 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3165,6 +3165,7 @@ void i915_gem_init_mmio(struct drm_i915_private *i915);
 int __must_check i915_gem_init(struct drm_i915_private *dev_priv);
 int __must_check i915_gem_init_hw(struct drm_i915_private *dev_priv);
 void i915_gem_init_swizzling(struct drm_i915_private *dev_priv);
+void i915_gem_fini(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_engines(struct drm_i915_private *dev_priv);
 int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
 			   unsigned int flags);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 62974e8862d5..cb680ddafa0c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5554,6 +5554,28 @@ err_unlock:
 	return ret;
 }
 
+void i915_gem_fini(struct drm_i915_private *dev_priv)
+{
+	i915_gem_suspend_late(dev_priv);
+
+	/* Flush any outstanding unpin_work. */
+	i915_gem_drain_workqueue(dev_priv);
+
+	mutex_lock(&dev_priv->drm.struct_mutex);
+	intel_uc_fini_hw(dev_priv);
+	intel_uc_fini(dev_priv);
+	i915_gem_cleanup_engines(dev_priv);
+	i915_gem_contexts_fini(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	intel_uc_fini_misc(dev_priv);
+	i915_gem_cleanup_userptr(dev_priv);
+
+	i915_gem_drain_freed_objects(dev_priv);
+
+	WARN_ON(!list_empty(&dev_priv->contexts.list));
+}
+
 void i915_gem_init_mmio(struct drm_i915_private *i915)
 {
 	i915_gem_sanitize(i915);
-- 
cgit v1.2.3


From 30aacd3fe7f16bc577c612b710de8f047c2c492a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 4 Jun 2018 14:15:52 +0100
Subject: drm/i915/gtt: Remove obsolete switch_mm hooks for gen8+

As the ppgtt for execlists is tightly coupled to the executing context,
and not switch separately, we no longer use the ppgtt->switch_mm hooks
on gen8+. Remove them.

References: 79e6770cb1f5 ("drm/i915: Remove obsolete ringbuffer emission for gen8+")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604131552.29370-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 49 -------------------------------------
 1 file changed, 49 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d032069819cc..96c48decbb73 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -773,53 +773,6 @@ static void gen8_initialize_pml4(struct i915_address_space *vm,
 	memset_p((void **)pml4->pdps, vm->scratch_pdp, GEN8_PML4ES_PER_PML4);
 }
 
-/* Broadwell Page Directory Pointer Descriptors */
-static int gen8_write_pdp(struct i915_request *rq,
-			  unsigned entry,
-			  dma_addr_t addr)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	u32 *cs;
-
-	BUG_ON(entry >= 4);
-
-	cs = intel_ring_begin(rq, 6);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(1);
-	*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_UDW(engine, entry));
-	*cs++ = upper_32_bits(addr);
-	*cs++ = MI_LOAD_REGISTER_IMM(1);
-	*cs++ = i915_mmio_reg_offset(GEN8_RING_PDP_LDW(engine, entry));
-	*cs++ = lower_32_bits(addr);
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
-static int gen8_mm_switch_3lvl(struct i915_hw_ppgtt *ppgtt,
-			       struct i915_request *rq)
-{
-	int i, ret;
-
-	for (i = GEN8_3LVL_PDPES - 1; i >= 0; i--) {
-		const dma_addr_t pd_daddr = i915_page_dir_dma_addr(ppgtt, i);
-
-		ret = gen8_write_pdp(rq, i, pd_daddr);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
-static int gen8_mm_switch_4lvl(struct i915_hw_ppgtt *ppgtt,
-			       struct i915_request *rq)
-{
-	return gen8_write_pdp(rq, 0, px_dma(&ppgtt->pml4));
-}
-
 /* PDE TLBs are a pain to invalidate on GEN8+. When we modify
  * the page table structures, we mark them dirty so that
  * context switching/execlist queuing code takes extra steps
@@ -1638,7 +1591,6 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 
 		gen8_initialize_pml4(&ppgtt->base, &ppgtt->pml4);
 
-		ppgtt->switch_mm = gen8_mm_switch_4lvl;
 		ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_4lvl;
 		ppgtt->base.insert_entries = gen8_ppgtt_insert_4lvl;
 		ppgtt->base.clear_range = gen8_ppgtt_clear_4lvl;
@@ -1655,7 +1607,6 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 			}
 		}
 
-		ppgtt->switch_mm = gen8_mm_switch_3lvl;
 		ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_3lvl;
 		ppgtt->base.insert_entries = gen8_ppgtt_insert_3lvl;
 		ppgtt->base.clear_range = gen8_ppgtt_clear_3lvl;
-- 
cgit v1.2.3


From 218b5000982b7c5e7433b86819be92f95984a1ae Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Sat, 2 Jun 2018 12:29:45 +0100
Subject: drm/i915: drop one bit on the hw_id when using guc

We currently using GuC as a proxy to the hardware. When Guc is used in
such mode, it consumes the bit 20 of the hw_id to indicate that the
workload was submitted by proxy.

So far we probably haven't seen the issue because we need to allocate
1048576+ contexts to hit this issue. Still, we should avoid allocating
the hw_id on that bit and restriction to bits [0:19] (i.e 20bits
instead of 21).

v2: Leave the max hw_id computation in i915_gem_context.c (Michel)

v3: Be consistent on if/else usage (Chris)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
BSpec: 1237
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180602112946.30803-2-lionel.g.landwerlin@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h         |  1 +
 drivers/gpu/drm/i915/i915_gem_context.c | 15 ++++++++++++---
 drivers/gpu/drm/i915/intel_lrc.c        |  2 +-
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ecc888a97279..b5b09c8a327f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1841,6 +1841,7 @@ struct drm_i915_private {
 		 */
 		struct ida hw_ida;
 #define MAX_CONTEXT_HW_ID (1<<21) /* exclusive */
+#define MAX_GUC_CONTEXT_HW_ID (1 << 20) /* exclusive */
 #define GEN11_MAX_CONTEXT_HW_ID (1<<11) /* exclusive */
 	} contexts;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 94e4db1870aa..38c6e9e4e91b 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -208,10 +208,19 @@ static int assign_hw_id(struct drm_i915_private *dev_priv, unsigned *out)
 	int ret;
 	unsigned int max;
 
-	if (INTEL_GEN(dev_priv) >= 11)
+	if (INTEL_GEN(dev_priv) >= 11) {
 		max = GEN11_MAX_CONTEXT_HW_ID;
-	else
-		max = MAX_CONTEXT_HW_ID;
+	} else {
+		/*
+		 * When using GuC in proxy submission, GuC consumes the
+		 * highest bit in the context id to indicate proxy submission.
+		 */
+		if (USES_GUC_SUBMISSION(dev_priv))
+			max = MAX_GUC_CONTEXT_HW_ID;
+		else
+			max = MAX_CONTEXT_HW_ID;
+	}
+
 
 	ret = ida_simple_get(&dev_priv->contexts.hw_ida,
 			     0, max, GFP_KERNEL);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 38696d9cc02e..cbc2a8d4dc9c 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -200,7 +200,7 @@ static inline bool need_preempt(const struct intel_engine_cs *engine,
  *
  *      bits  0-11:    flags, GEN8_CTX_* (cached in ctx->desc_template)
  *      bits 12-31:    LRCA, GTT address of (the HWSP of) this context
- *      bits 32-52:    ctx ID, a globally unique tag
+ *      bits 32-52:    ctx ID, a globally unique tag (highest bit used by GuC)
  *      bits 53-54:    mbz, reserved for use by hardware
  *      bits 55-63:    group ID, currently unused and set to 0
  *
-- 
cgit v1.2.3


From 61d5676b5561d61e3fdd9e88fc2b549b9b4df08f Mon Sep 17 00:00:00 2001
From: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Date: Sat, 2 Jun 2018 12:29:46 +0100
Subject: drm/i915/perf: fix ctx_id read with GuC & ICL

One thing we didn't really understand about the OA report is that the
ContextID field (dword 2) is copy of the context descriptor (dword 1).

On Gen8->10 and without using GuC we didn't notice the issue because
we only checked the 21bits of the ContextID field in the OA reports
which matches exactly the hw_id stored into the context descriptor.

When using GuC submission we have an issue of a non matching hw_id
because GuC uses bit 20 of the hw_id to signal proxy submission. This
change introduces a mask to compare only the relevant bits.

On ICL the context descriptor format has changed and we failed to
address this. On top of using a mask we also need to shift the bits
properly.

v2: Reuse lrc_desc rather than recomputing part of it (Chris/Michel)

v3: Always pin the context we're filtering with (Chris)

Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 1de401c08fa805 ("drm/i915/perf: enable perf support on ICL")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104252
BSpec: 1237
Testcase: igt/perf/gen8-unprivileged-single-ctx-counters
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180602112946.30803-3-lionel.g.landwerlin@intel.com
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-gfx@lists.freedesktop.org
---
 drivers/gpu/drm/i915/i915_drv.h  |   1 +
 drivers/gpu/drm/i915/i915_perf.c | 123 +++++++++++++++++++++++++++++----------
 drivers/gpu/drm/i915/intel_lrc.c |   5 ++
 3 files changed, 97 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index b5b09c8a327f..06ecac4c3253 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1951,6 +1951,7 @@ struct drm_i915_private {
 
 			struct intel_context *pinned_ctx;
 			u32 specific_ctx_id;
+			u32 specific_ctx_id_mask;
 
 			struct hrtimer poll_check_timer;
 			wait_queue_head_t poll_wq;
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 4f0eb84b3c00..a6c8d61add0c 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -737,12 +737,7 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream,
 			continue;
 		}
 
-		/*
-		 * XXX: Just keep the lower 21 bits for now since I'm not
-		 * entirely sure if the HW touches any of the higher bits in
-		 * this field
-		 */
-		ctx_id = report32[2] & 0x1fffff;
+		ctx_id = report32[2] & dev_priv->perf.oa.specific_ctx_id_mask;
 
 		/*
 		 * Squash whatever is in the CTX_ID field if it's marked as
@@ -1203,6 +1198,33 @@ static int i915_oa_read(struct i915_perf_stream *stream,
 	return dev_priv->perf.oa.ops.read(stream, buf, count, offset);
 }
 
+static struct intel_context *oa_pin_context(struct drm_i915_private *i915,
+					    struct i915_gem_context *ctx)
+{
+	struct intel_engine_cs *engine = i915->engine[RCS];
+	struct intel_context *ce;
+	int ret;
+
+	ret = i915_mutex_lock_interruptible(&i915->drm);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/*
+	 * As the ID is the gtt offset of the context's vma we
+	 * pin the vma to ensure the ID remains fixed.
+	 *
+	 * NB: implied RCS engine...
+	 */
+	ce = intel_context_pin(ctx, engine);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (IS_ERR(ce))
+		return ce;
+
+	i915->perf.oa.pinned_ctx = ce;
+
+	return ce;
+}
+
 /**
  * oa_get_render_ctx_id - determine and hold ctx hw id
  * @stream: An i915-perf stream opened for OA metrics
@@ -1215,40 +1237,76 @@ static int i915_oa_read(struct i915_perf_stream *stream,
  */
 static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 {
-	struct drm_i915_private *dev_priv = stream->dev_priv;
-
-	if (HAS_LOGICAL_RING_CONTEXTS(dev_priv)) {
-		dev_priv->perf.oa.specific_ctx_id = stream->ctx->hw_id;
-	} else {
-		struct intel_engine_cs *engine = dev_priv->engine[RCS];
-		struct intel_context *ce;
-		int ret;
+	struct drm_i915_private *i915 = stream->dev_priv;
+	struct intel_context *ce;
 
-		ret = i915_mutex_lock_interruptible(&dev_priv->drm);
-		if (ret)
-			return ret;
+	ce = oa_pin_context(i915, stream->ctx);
+	if (IS_ERR(ce))
+		return PTR_ERR(ce);
 
+	switch (INTEL_GEN(i915)) {
+	case 7: {
 		/*
-		 * As the ID is the gtt offset of the context's vma we
-		 * pin the vma to ensure the ID remains fixed.
-		 *
-		 * NB: implied RCS engine...
+		 * On Haswell we don't do any post processing of the reports
+		 * and don't need to use the mask.
 		 */
-		ce = intel_context_pin(stream->ctx, engine);
-		mutex_unlock(&dev_priv->drm.struct_mutex);
-		if (IS_ERR(ce))
-			return PTR_ERR(ce);
+		i915->perf.oa.specific_ctx_id = i915_ggtt_offset(ce->state);
+		i915->perf.oa.specific_ctx_id_mask = 0;
+		break;
+	}
 
-		dev_priv->perf.oa.pinned_ctx = ce;
+	case 8:
+	case 9:
+	case 10:
+		if (USES_GUC_SUBMISSION(i915)) {
+			/*
+			 * When using GuC, the context descriptor we write in
+			 * i915 is read by GuC and rewritten before it's
+			 * actually written into the hardware. The LRCA is
+			 * what is put into the context id field of the
+			 * context descriptor by GuC. Because it's aligned to
+			 * a page, the lower 12bits are always at 0 and
+			 * dropped by GuC. They won't be part of the context
+			 * ID in the OA reports, so squash those lower bits.
+			 */
+			i915->perf.oa.specific_ctx_id =
+				lower_32_bits(ce->lrc_desc) >> 12;
 
-		/*
-		 * Explicitly track the ID (instead of calling
-		 * i915_ggtt_offset() on the fly) considering the difference
-		 * with gen8+ and execlists
-		 */
-		dev_priv->perf.oa.specific_ctx_id = i915_ggtt_offset(ce->state);
+			/*
+			 * GuC uses the top bit to signal proxy submission, so
+			 * ignore that bit.
+			 */
+			i915->perf.oa.specific_ctx_id_mask =
+				(1U << (GEN8_CTX_ID_WIDTH - 1)) - 1;
+		} else {
+			i915->perf.oa.specific_ctx_id = stream->ctx->hw_id;
+			i915->perf.oa.specific_ctx_id_mask =
+				(1U << GEN8_CTX_ID_WIDTH) - 1;
+		}
+		break;
+
+	case 11: {
+		struct intel_engine_cs *engine = i915->engine[RCS];
+
+		i915->perf.oa.specific_ctx_id =
+			stream->ctx->hw_id << (GEN11_SW_CTX_ID_SHIFT - 32) |
+			engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32) |
+			engine->class << (GEN11_ENGINE_INSTANCE_SHIFT - 32);
+		i915->perf.oa.specific_ctx_id_mask =
+			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32) |
+			((1U << GEN11_ENGINE_INSTANCE_WIDTH) - 1) << (GEN11_ENGINE_INSTANCE_SHIFT - 32) |
+			((1 << GEN11_ENGINE_CLASS_WIDTH) - 1) << (GEN11_ENGINE_CLASS_SHIFT - 32);
+		break;
+	}
+
+	default:
+		MISSING_CASE(INTEL_GEN(i915));
 	}
 
+	DRM_DEBUG_DRIVER("filtering on ctx_id=0x%x ctx_id_mask=0x%x\n",
+			 i915->perf.oa.specific_ctx_id,
+			 i915->perf.oa.specific_ctx_id_mask);
+
 	return 0;
 }
 
@@ -1265,6 +1323,7 @@ static void oa_put_render_ctx_id(struct i915_perf_stream *stream)
 	struct intel_context *ce;
 
 	dev_priv->perf.oa.specific_ctx_id = INVALID_CTX_ID;
+	dev_priv->perf.oa.specific_ctx_id_mask = 0;
 
 	ce = fetch_and_zero(&dev_priv->perf.oa.pinned_ctx);
 	if (ce) {
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index cbc2a8d4dc9c..f6f09f808f74 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -233,6 +233,11 @@ intel_lr_context_descriptor_update(struct i915_gem_context *ctx,
 								/* bits 12-31 */
 	GEM_BUG_ON(desc & GENMASK_ULL(63, 32));
 
+	/*
+	 * The following 32bits are copied into the OA reports (dword 2).
+	 * Consider updating oa_get_render_ctx_id in i915_perf.c when changing
+	 * anything below.
+	 */
 	if (INTEL_GEN(ctx->i915) >= 11) {
 		GEM_BUG_ON(ctx->hw_id >= BIT(GEN11_SW_CTX_ID_WIDTH));
 		desc |= (u64)ctx->hw_id << GEN11_SW_CTX_ID_SHIFT;
-- 
cgit v1.2.3


From 6ceb7277173597eeed8d635e08db51e35235ab21 Mon Sep 17 00:00:00 2001
From: Mahesh Kumar <mahesh1.kumar@intel.com>
Date: Thu, 17 May 2018 18:56:26 +0530
Subject: drm/i915/icl: Don't update enabled dbuf slices struct until updated
 in hw

Do not update number of enabled dbuf slices in dev_priv struct until we
actually enable/disable dbuf slice in hw. This is leading to never
updating dbuf slices and resulting in DBuf slice mismatch warning.

Fixes: aa9664ffe863 ("drm/i915/icl: Enable 2nd DBuf slice only when needed")
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180517132626.5885-1-mahesh1.kumar@intel.com
---
 drivers/gpu/drm/i915/intel_pm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index b85229e153c4..53aaaa3e6886 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -5150,7 +5150,6 @@ skl_copy_ddb_for_pipe(struct skl_ddb_values *dst,
 	       sizeof(dst->ddb.uv_plane[pipe]));
 	memcpy(dst->ddb.plane[pipe], src->ddb.plane[pipe],
 	       sizeof(dst->ddb.plane[pipe]));
-	dst->ddb.enabled_slices = src->ddb.enabled_slices;
 }
 
 static void
-- 
cgit v1.2.3


From 52b2416ceb72e8f757eb56de5a98ade04d9b062d Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 8 May 2018 17:07:05 +0800
Subject: drm/i915: Add new vGPU cap info bit VGT_CAPS_HUGE_GTT

This adds a new vGPU cap info bit VGT_CAPS_HUGE_GTT, which is to detect
whether the host supports shadowing of huge gtt pages. If host does
support it, remove the page sizes restriction for vGPU.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1525770425-5373-1-git-send-email-changbin.du@intel.com
---
 drivers/gpu/drm/i915/i915_gem.c    | 8 ++------
 drivers/gpu/drm/i915/i915_pvinfo.h | 1 +
 drivers/gpu/drm/i915/i915_vgpu.h   | 6 ++++++
 3 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index cb680ddafa0c..2a51a2b6d22c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5409,12 +5409,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
-	/*
-	 * We need to fallback to 4K pages since gvt gtt handling doesn't
-	 * support huge page entries - we will need to check either hypervisor
-	 * mm can support huge guest page or just do emulation in gvt.
-	 */
-	if (intel_vgpu_active(dev_priv))
+	/* We need to fallback to 4K pages if host doesn't support huge gtt. */
+	if (intel_vgpu_active(dev_priv) && !intel_vgpu_has_huge_gtt(dev_priv))
 		mkwrite_device_info(dev_priv)->page_sizes =
 			I915_GTT_PAGE_SIZE_4K;
 
diff --git a/drivers/gpu/drm/i915/i915_pvinfo.h b/drivers/gpu/drm/i915/i915_pvinfo.h
index 195203f298df..55bde4a02289 100644
--- a/drivers/gpu/drm/i915/i915_pvinfo.h
+++ b/drivers/gpu/drm/i915/i915_pvinfo.h
@@ -54,6 +54,7 @@ enum vgt_g2v_type {
  */
 #define VGT_CAPS_FULL_48BIT_PPGTT	BIT(2)
 #define VGT_CAPS_HWSP_EMULATION		BIT(3)
+#define VGT_CAPS_HUGE_GTT		BIT(4)
 
 struct vgt_if {
 	u64 magic;		/* VGT_MAGIC */
diff --git a/drivers/gpu/drm/i915/i915_vgpu.h b/drivers/gpu/drm/i915/i915_vgpu.h
index bb8338450dc1..551acc390046 100644
--- a/drivers/gpu/drm/i915/i915_vgpu.h
+++ b/drivers/gpu/drm/i915/i915_vgpu.h
@@ -36,6 +36,12 @@ intel_vgpu_has_hwsp_emulation(struct drm_i915_private *dev_priv)
 	return dev_priv->vgpu.caps & VGT_CAPS_HWSP_EMULATION;
 }
 
+static inline bool
+intel_vgpu_has_huge_gtt(struct drm_i915_private *dev_priv)
+{
+	return dev_priv->vgpu.caps & VGT_CAPS_HUGE_GTT;
+}
+
 int intel_vgt_balloon(struct drm_i915_private *dev_priv);
 void intel_vgt_deballoon(struct drm_i915_private *dev_priv);
 
-- 
cgit v1.2.3


From d901e8e6733544e772713a23ab345eb79153de8c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 5 Jun 2018 09:53:48 +0100
Subject: drm/i915/ringbuffer: Make context pin/unpin symmetric

Currently, we have a special routine for pinning the context state at
the start of activity tracking, but lack the complementary unpin
routine. Create it to to ease later patches that want to do partial
teardown on error, and, not least, to improve the readability of the
code.

Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605085348.3018-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 67 +++++++++++++++++++++------------
 1 file changed, 43 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 001cf6bcb349..3f0eb538df09 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1193,20 +1193,14 @@ static void intel_ring_context_destroy(struct intel_context *ce)
 		__i915_gem_object_release_unless_active(ce->state->obj);
 }
 
-static void intel_ring_context_unpin(struct intel_context *ce)
-{
-	if (ce->state) {
-		ce->state->obj->pin_global--;
-		i915_vma_unpin(ce->state);
-	}
-
-	i915_gem_context_put(ce->gem_context);
-}
-
 static int __context_pin(struct intel_context *ce)
 {
-	struct i915_vma *vma = ce->state;
-	int ret;
+	struct i915_vma *vma;
+	int err;
+
+	vma = ce->state;
+	if (!vma)
+		return 0;
 
 	/*
 	 * Clear this page out of any CPU caches for coherent swap-in/out.
@@ -1214,13 +1208,42 @@ static int __context_pin(struct intel_context *ce)
 	 * on an active context (which by nature is already on the GPU).
 	 */
 	if (!(vma->flags & I915_VMA_GLOBAL_BIND)) {
-		ret = i915_gem_object_set_to_gtt_domain(vma->obj, true);
-		if (ret)
-			return ret;
+		err = i915_gem_object_set_to_gtt_domain(vma->obj, true);
+		if (err)
+			return err;
 	}
 
-	return i915_vma_pin(vma, 0, I915_GTT_MIN_ALIGNMENT,
-			    PIN_GLOBAL | PIN_HIGH);
+	err = i915_vma_pin(vma, 0, I915_GTT_MIN_ALIGNMENT,
+			   PIN_GLOBAL | PIN_HIGH);
+	if (err)
+		return err;
+
+	/*
+	 * And mark is as a globally pinned object to let the shrinker know
+	 * it cannot reclaim the object until we release it.
+	 */
+	vma->obj->pin_global++;
+
+	return 0;
+}
+
+static void __context_unpin(struct intel_context *ce)
+{
+	struct i915_vma *vma;
+
+	vma = ce->state;
+	if (!vma)
+		return;
+
+	vma->obj->pin_global--;
+	i915_vma_unpin(vma);
+}
+
+static void intel_ring_context_unpin(struct intel_context *ce)
+{
+	__context_unpin(ce);
+
+	i915_gem_context_put(ce->gem_context);
 }
 
 static struct i915_vma *
@@ -1311,13 +1334,9 @@ __ring_context_pin(struct intel_engine_cs *engine,
 		ce->state = vma;
 	}
 
-	if (ce->state) {
-		err = __context_pin(ce);
-		if (err)
-			goto err;
-
-		ce->state->obj->pin_global++;
-	}
+	err = __context_pin(ce);
+	if (err)
+		goto err;
 
 	i915_gem_context_get(ctx);
 
-- 
cgit v1.2.3


From 744799850ef1cb053457a8a7652165e895ea26a0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 5 Jun 2018 09:28:56 +0100
Subject: drm/i915/gtt: Teach restore-gtt to walk the ggtt vma list not the
 object list

In preparation, for having non-vma objects stored inside the ggtt, to
handle restoration of the GGTT following resume, we need to walk over
the ggtt address space rebinding vma, as opposed to walking over bound
objects looking for ggtt entries.

v2: Skip objects only bound for the aliasing_ppgtt

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> #v1
Link: https://patchwork.freedesktop.org/patch/msgid/20180605082856.19221-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 96c48decbb73..9302ee6e717d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3569,7 +3569,7 @@ void i915_ggtt_disable_guc(struct drm_i915_private *i915)
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	struct drm_i915_gem_object *obj, *on;
+	struct i915_vma *vma, *vn;
 
 	i915_check_and_clear_faults(dev_priv);
 
@@ -3579,21 +3579,18 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 	ggtt->base.closed = true; /* skip rewriting PTE on VMA unbind */
 
 	/* clflush objects bound into the GGTT and rebind them. */
-	list_for_each_entry_safe(obj, on, &dev_priv->mm.bound_list, mm.link) {
-		bool ggtt_bound = false;
-		struct i915_vma *vma;
+	GEM_BUG_ON(!list_empty(&ggtt->base.active_list));
+	list_for_each_entry_safe(vma, vn, &ggtt->base.inactive_list, vm_link) {
+		struct drm_i915_gem_object *obj = vma->obj;
 
-		for_each_ggtt_vma(vma, obj) {
-			if (!i915_vma_unbind(vma))
-				continue;
+		if (!(vma->flags & I915_VMA_GLOBAL_BIND))
+			continue;
 
-			WARN_ON(i915_vma_bind(vma, obj->cache_level,
-					      PIN_UPDATE));
-			ggtt_bound = true;
-		}
+		if (!i915_vma_unbind(vma))
+			continue;
 
-		if (ggtt_bound)
-			WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
+		WARN_ON(i915_vma_bind(vma, obj->cache_level, PIN_UPDATE));
+		WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
 	}
 
 	ggtt->base.closed = false;
-- 
cgit v1.2.3


From 83d317adfb4b27ec589b59548cf52e3b63a39fc9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 5 Jun 2018 10:41:07 +0100
Subject: drm/i915/vma: Move the bind_count vs pin_count assertion to a helper

To spare ourselves a long line later, refactor the repeated check of
bind_count vs pin_count to a helper.

v2: Fix up the commentary!

Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605094107.31367-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_vma.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 9324d476e0a7..10bf654cd023 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -459,6 +459,18 @@ bool i915_gem_valid_gtt_space(struct i915_vma *vma, unsigned long cache_level)
 	return true;
 }
 
+static void assert_bind_count(const struct drm_i915_gem_object *obj)
+{
+	/*
+	 * Combine the assertion that the object is bound and that we have
+	 * pinned its pages. But we should never have bound the object
+	 * more than we have pinned its pages. (For complete accuracy, we
+	 * assume that no else is pinning the pages, but as a rough assertion
+	 * that we will not run into problems later, this will do!)
+	 */
+	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+}
+
 /**
  * i915_vma_insert - finds a slot for the vma in its address space
  * @vma: the vma
@@ -595,7 +607,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	obj->bind_count++;
 	spin_unlock(&dev_priv->mm.obj_lock);
 
-	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+	assert_bind_count(obj);
 
 	return 0;
 
@@ -633,7 +645,7 @@ i915_vma_remove(struct i915_vma *vma)
 	 * reaped by the shrinker.
 	 */
 	i915_gem_object_unpin_pages(obj);
-	GEM_BUG_ON(atomic_read(&obj->mm.pages_pin_count) < obj->bind_count);
+	assert_bind_count(obj);
 }
 
 int __i915_vma_do_pin(struct i915_vma *vma,
-- 
cgit v1.2.3


From b96f6ebfd02444b290ff5048c1ae61f5d3d52319 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 5 Jun 2018 12:24:43 +0000
Subject: drm/i915: Correctly handle error path in i915_gem_init_hw

In function gem_init_hw() we are calling uc_init_hw() but in case
of error later in function, we missed to call matching uc_fini_hw()

v2: pulled out from the series

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605122443.23776-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/i915_gem.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 2a51a2b6d22c..c41997595183 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5286,9 +5286,15 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv)
 
 	/* Only when the HW is re-initialised, can we replay the requests */
 	ret = __i915_gem_restart_engines(dev_priv);
+	if (ret)
+		goto cleanup_uc;
 out:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	return ret;
+
+cleanup_uc:
+	intel_uc_fini_hw(dev_priv);
+	goto out;
 }
 
 static int __intel_engines_record_defaults(struct drm_i915_private *i915)
-- 
cgit v1.2.3


From 420980ca79bcac50cab5bfd20c3d7e5425b1f3d6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 5 Jun 2018 14:57:46 +0100
Subject: drm/i915: Swap magics and use SZ_1M

Since the kernel provides SZ_1M, use it in preference of 1 << 20.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605135746.8020-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index c41997595183..23374f3dd79d 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1999,7 +1999,7 @@ compute_partial_view(struct drm_i915_gem_object *obj,
  */
 int i915_gem_fault(struct vm_fault *vmf)
 {
-#define MIN_CHUNK_PAGES ((1 << 20) >> PAGE_SHIFT) /* 1 MiB */
+#define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT)
 	struct vm_area_struct *area = vmf->vma;
 	struct drm_i915_gem_object *obj = to_intel_bo(area->vm_private_data);
 	struct drm_device *dev = obj->base.dev;
-- 
cgit v1.2.3


From 2956e970f0b5f760a7c595730bac81d2f5e6250c Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Fri, 25 May 2018 09:26:40 +0100
Subject: drm/i915/trace: Describe engines as class:instance pairs

Instead of using the engine->id, use uabi_class:instance pairs in trace-
points including engine info.

This will be more readable, more future proof and more stable for
userspace consumption.

v2:
 * Use u16 for class and instance. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: svetlana.kukanova@intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525082642.18246-1-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_trace.h | 107 +++++++++++++++++++++++---------------
 1 file changed, 65 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 5d4f78765083..7acea4052798 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -591,21 +591,26 @@ TRACE_EVENT(i915_gem_ring_sync_to,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, sync_from)
-			     __field(u32, sync_to)
+			     __field(u32, from_class)
+			     __field(u32, from_instance)
+			     __field(u32, to_class)
+			     __field(u32, to_instance)
 			     __field(u32, seqno)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = from->i915->drm.primary->index;
-			   __entry->sync_from = from->engine->id;
-			   __entry->sync_to = to->engine->id;
+			   __entry->from_class = from->engine->uabi_class;
+			   __entry->from_instance = from->engine->instance;
+			   __entry->to_class = to->engine->uabi_class;
+			   __entry->to_instance = to->engine->instance;
 			   __entry->seqno = from->global_seqno;
 			   ),
 
-	    TP_printk("dev=%u, sync-from=%u, sync-to=%u, seqno=%u",
+	    TP_printk("dev=%u, sync-from=%u:%u, sync-to=%u:%u, seqno=%u",
 		      __entry->dev,
-		      __entry->sync_from, __entry->sync_to,
+		      __entry->from_class, __entry->from_instance,
+		      __entry->to_class, __entry->to_instance,
 		      __entry->seqno)
 );
 
@@ -616,7 +621,8 @@ TRACE_EVENT(i915_request_queue,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, flags)
@@ -625,15 +631,17 @@ TRACE_EVENT(i915_request_queue,
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
 			   __entry->hw_id = rq->gem_context->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, flags=0x%x",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->flags)
+	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, flags=0x%x",
+		      __entry->dev, __entry->hw_id, __entry->class,
+		      __entry->instance, __entry->ctx, __entry->seqno,
+		      __entry->flags)
 );
 
 DECLARE_EVENT_CLASS(i915_request,
@@ -643,7 +651,8 @@ DECLARE_EVENT_CLASS(i915_request,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global)
@@ -652,15 +661,17 @@ DECLARE_EVENT_CLASS(i915_request,
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
 			   __entry->hw_id = rq->gem_context->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global = rq->global_seqno;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->global)
+	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, global=%u",
+		      __entry->dev, __entry->hw_id, __entry->class,
+		      __entry->instance, __entry->ctx, __entry->seqno,
+		      __entry->global)
 );
 
 DEFINE_EVENT(i915_request, i915_request_add,
@@ -686,7 +697,8 @@ TRACE_EVENT(i915_request_in,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global_seqno)
@@ -697,7 +709,8 @@ TRACE_EVENT(i915_request_in,
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
 			   __entry->hw_id = rq->gem_context->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global_seqno = rq->global_seqno;
@@ -705,10 +718,10 @@ TRACE_EVENT(i915_request_in,
 			   __entry->port = port;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->prio, __entry->global_seqno,
-		      __entry->port)
+	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u",
+		      __entry->dev, __entry->hw_id, __entry->class,
+		      __entry->instance, __entry->ctx, __entry->seqno,
+		      __entry->prio, __entry->global_seqno, __entry->port)
 );
 
 TRACE_EVENT(i915_request_out,
@@ -718,7 +731,8 @@ TRACE_EVENT(i915_request_out,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global_seqno)
@@ -728,16 +742,17 @@ TRACE_EVENT(i915_request_out,
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
 			   __entry->hw_id = rq->gem_context->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global_seqno = rq->global_seqno;
 			   __entry->completed = i915_request_completed(rq);
 			   ),
 
-		    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, completed?=%u",
-			      __entry->dev, __entry->hw_id, __entry->ring,
-			      __entry->ctx, __entry->seqno,
+		    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, global=%u, completed?=%u",
+			      __entry->dev, __entry->hw_id, __entry->class,
+			      __entry->instance, __entry->ctx, __entry->seqno,
 			      __entry->global_seqno, __entry->completed)
 );
 
@@ -771,21 +786,23 @@ TRACE_EVENT(intel_engine_notify,
 
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
-			     __field(u32, ring)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, seqno)
 			     __field(bool, waiters)
 			     ),
 
 	    TP_fast_assign(
 			   __entry->dev = engine->i915->drm.primary->index;
-			   __entry->ring = engine->id;
+			   __entry->class = engine->uabi_class;
+			   __entry->instance = engine->instance;
 			   __entry->seqno = intel_engine_get_seqno(engine);
 			   __entry->waiters = waiters;
 			   ),
 
-	    TP_printk("dev=%u, ring=%u, seqno=%u, waiters=%u",
-		      __entry->dev, __entry->ring, __entry->seqno,
-		      __entry->waiters)
+	    TP_printk("dev=%u, engine=%u:%u, seqno=%u, waiters=%u",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->seqno, __entry->waiters)
 );
 
 DEFINE_EVENT(i915_request, i915_request_retire,
@@ -800,7 +817,8 @@ TRACE_EVENT(i915_request_wait_begin,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
-			     __field(u32, ring)
+			     __field(u16, class)
+			     __field(u16, instance)
 			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global)
@@ -816,17 +834,19 @@ TRACE_EVENT(i915_request_wait_begin,
 	    TP_fast_assign(
 			   __entry->dev = rq->i915->drm.primary->index;
 			   __entry->hw_id = rq->gem_context->hw_id;
-			   __entry->ring = rq->engine->id;
+			   __entry->class = rq->engine->uabi_class;
+			   __entry->instance = rq->engine->instance;
 			   __entry->ctx = rq->fence.context;
 			   __entry->seqno = rq->fence.seqno;
 			   __entry->global = rq->global_seqno;
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, ring=%u, ctx=%u, seqno=%u, global=%u, blocking=%u, flags=0x%x",
-		      __entry->dev, __entry->hw_id, __entry->ring, __entry->ctx,
-		      __entry->seqno, __entry->global,
-		      !!(__entry->flags & I915_WAIT_LOCKED), __entry->flags)
+	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, global=%u, blocking=%u, flags=0x%x",
+		      __entry->dev, __entry->hw_id, __entry->class,
+		      __entry->instance, __entry->ctx, __entry->seqno,
+		      __entry->global, !!(__entry->flags & I915_WAIT_LOCKED),
+		      __entry->flags)
 );
 
 DEFINE_EVENT(i915_request, i915_request_wait_end,
@@ -966,21 +986,24 @@ TRACE_EVENT(switch_mm,
 	TP_ARGS(engine, to),
 
 	TP_STRUCT__entry(
-			__field(u32, ring)
+			__field(u16, class)
+			__field(u16, instance)
 			__field(struct i915_gem_context *, to)
 			__field(struct i915_address_space *, vm)
 			__field(u32, dev)
 	),
 
 	TP_fast_assign(
-			__entry->ring = engine->id;
+			__entry->class = engine->uabi_class;
+			__entry->instance = engine->instance;
 			__entry->to = to;
 			__entry->vm = to->ppgtt? &to->ppgtt->base : NULL;
 			__entry->dev = engine->i915->drm.primary->index;
 	),
 
-	TP_printk("dev=%u, ring=%u, ctx=%p, ctx_vm=%p",
-		  __entry->dev, __entry->ring, __entry->to, __entry->vm)
+	TP_printk("dev=%u, engine=%u:%u, ctx=%p, ctx_vm=%p",
+		  __entry->dev, __entry->class, __entry->instance, __entry->to,
+		  __entry->vm)
 );
 
 #endif /* _I915_TRACE_H_ */
-- 
cgit v1.2.3


From f24e74a7b73953b0b0a7afcddfa26c298b20c7c8 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Fri, 25 May 2018 09:26:41 +0100
Subject: drm/i915/trace: Remove engine out of the context sandwich

In the string tracepoint representation we ended up with the engine
sandwiched between context hardware id and context fence id.

Move the two pieces of context data together for redability.

Binary records are left as is, that is both fields remaing under the
existing name and ordering.

v2:
 * Do not consolidate the printk format, just reorder. (Lionel)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525082642.18246-2-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_trace.h | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 7acea4052798..bac582ed3a0b 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -638,9 +638,9 @@ TRACE_EVENT(i915_request_queue,
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, flags=0x%x",
-		      __entry->dev, __entry->hw_id, __entry->class,
-		      __entry->instance, __entry->ctx, __entry->seqno,
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, flags=0x%x",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->flags)
 );
 
@@ -668,9 +668,9 @@ DECLARE_EVENT_CLASS(i915_request,
 			   __entry->global = rq->global_seqno;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, global=%u",
-		      __entry->dev, __entry->hw_id, __entry->class,
-		      __entry->instance, __entry->ctx, __entry->seqno,
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, global=%u",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->global)
 );
 
@@ -718,9 +718,9 @@ TRACE_EVENT(i915_request_in,
 			   __entry->port = port;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u",
-		      __entry->dev, __entry->hw_id, __entry->class,
-		      __entry->instance, __entry->ctx, __entry->seqno,
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->prio, __entry->global_seqno, __entry->port)
 );
 
@@ -750,9 +750,9 @@ TRACE_EVENT(i915_request_out,
 			   __entry->completed = i915_request_completed(rq);
 			   ),
 
-		    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, global=%u, completed?=%u",
-			      __entry->dev, __entry->hw_id, __entry->class,
-			      __entry->instance, __entry->ctx, __entry->seqno,
+		    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, global=%u, completed?=%u",
+			      __entry->dev, __entry->class, __entry->instance,
+			      __entry->hw_id, __entry->ctx, __entry->seqno,
 			      __entry->global_seqno, __entry->completed)
 );
 
@@ -842,9 +842,9 @@ TRACE_EVENT(i915_request_wait_begin,
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, hw_id=%u, engine=%u:%u, ctx=%u, seqno=%u, global=%u, blocking=%u, flags=0x%x",
-		      __entry->dev, __entry->hw_id, __entry->class,
-		      __entry->instance, __entry->ctx, __entry->seqno,
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, global=%u, blocking=%u, flags=0x%x",
+		      __entry->dev, __entry->class, __entry->instance,
+		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->global, !!(__entry->flags & I915_WAIT_LOCKED),
 		      __entry->flags)
 );
-- 
cgit v1.2.3


From 57d7116c472cd32ab167f208e1dec100596ce949 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue, 5 Jun 2018 14:41:24 +0100
Subject: drm/i915/trace: Context field needs to be 64-bit wide

Underlaying field is u64 so the tracepoint needs to be as well.

v2:
 * Re-order binary packet for 64-bit alignment. (Chris Wilson)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605134124.25672-1-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_trace.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index bac582ed3a0b..3d5716d86e27 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -621,9 +621,9 @@ TRACE_EVENT(i915_request_queue,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
+			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
-			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, flags)
 			     ),
@@ -638,7 +638,7 @@ TRACE_EVENT(i915_request_queue,
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, flags=0x%x",
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, flags=0x%x",
 		      __entry->dev, __entry->class, __entry->instance,
 		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->flags)
@@ -651,9 +651,9 @@ DECLARE_EVENT_CLASS(i915_request,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
+			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
-			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global)
 			     ),
@@ -668,7 +668,7 @@ DECLARE_EVENT_CLASS(i915_request,
 			   __entry->global = rq->global_seqno;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, global=%u",
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u",
 		      __entry->dev, __entry->class, __entry->instance,
 		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->global)
@@ -697,9 +697,9 @@ TRACE_EVENT(i915_request_in,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
+			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
-			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global_seqno)
 			     __field(u32, port)
@@ -718,7 +718,7 @@ TRACE_EVENT(i915_request_in,
 			   __entry->port = port;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, prio=%u, global=%u, port=%u",
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, prio=%u, global=%u, port=%u",
 		      __entry->dev, __entry->class, __entry->instance,
 		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->prio, __entry->global_seqno, __entry->port)
@@ -731,9 +731,9 @@ TRACE_EVENT(i915_request_out,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
+			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
-			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global_seqno)
 			     __field(u32, completed)
@@ -750,7 +750,7 @@ TRACE_EVENT(i915_request_out,
 			   __entry->completed = i915_request_completed(rq);
 			   ),
 
-		    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, global=%u, completed?=%u",
+		    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, completed?=%u",
 			      __entry->dev, __entry->class, __entry->instance,
 			      __entry->hw_id, __entry->ctx, __entry->seqno,
 			      __entry->global_seqno, __entry->completed)
@@ -817,9 +817,9 @@ TRACE_EVENT(i915_request_wait_begin,
 	    TP_STRUCT__entry(
 			     __field(u32, dev)
 			     __field(u32, hw_id)
+			     __field(u64, ctx)
 			     __field(u16, class)
 			     __field(u16, instance)
-			     __field(u32, ctx)
 			     __field(u32, seqno)
 			     __field(u32, global)
 			     __field(unsigned int, flags)
@@ -842,7 +842,7 @@ TRACE_EVENT(i915_request_wait_begin,
 			   __entry->flags = flags;
 			   ),
 
-	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%u, seqno=%u, global=%u, blocking=%u, flags=0x%x",
+	    TP_printk("dev=%u, engine=%u:%u, hw_id=%u, ctx=%llu, seqno=%u, global=%u, blocking=%u, flags=0x%x",
 		      __entry->dev, __entry->class, __entry->instance,
 		      __entry->hw_id, __entry->ctx, __entry->seqno,
 		      __entry->global, !!(__entry->flags & I915_WAIT_LOCKED),
-- 
cgit v1.2.3


From 9f473ecfe7a8520de359ed20bf95a1628e85e650 Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Date: Tue, 5 Jun 2018 15:02:53 +0100
Subject: drm/i915/pmu: Do not assume fixed hrtimer period

As Chris has discovered on his Ivybridge, and later automated test runs
have confirmed, on most of our platforms hrtimer faced with heavy GPU load
can occasionally become sufficiently imprecise to affect PMU sampling
calculations.

This means we cannot assume sampling frequency is what we asked for, but
we need to measure the interval ourselves.

This patch is similar to Chris' original proposal for per-engine counters,
but instead of introducing a new set to work around the problem with
frequency sampling, it swaps around the way internal frequency accounting
is done. Instead of accumulating current frequency and dividing by
sampling frequency on readout, it accumulates frequency scaled by each
period.

v2:
 * Typo in commit message, comment on period calculation and USEC_PER_SEC.
   (Chris Wilson)

Testcase: igt/perf_pmu/*busy* # snb, ivb, hsw
Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Suggested-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605140253.3541-1-tvrtko.ursulin@linux.intel.com
---
 drivers/gpu/drm/i915/i915_pmu.c | 67 +++++++++++++++++++++++++++++------------
 drivers/gpu/drm/i915/i915_pmu.h |  8 +++++
 2 files changed, 55 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index dc87797db500..c39541ed2219 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -127,6 +127,7 @@ static void __i915_pmu_maybe_start_timer(struct drm_i915_private *i915)
 {
 	if (!i915->pmu.timer_enabled && pmu_needs_timer(i915, true)) {
 		i915->pmu.timer_enabled = true;
+		i915->pmu.timer_last = ktime_get();
 		hrtimer_start_range_ns(&i915->pmu.timer,
 				       ns_to_ktime(PERIOD), 0,
 				       HRTIMER_MODE_REL_PINNED);
@@ -155,12 +156,13 @@ static bool grab_forcewake(struct drm_i915_private *i915, bool fw)
 }
 
 static void
-update_sample(struct i915_pmu_sample *sample, u32 unit, u32 val)
+add_sample(struct i915_pmu_sample *sample, u32 val)
 {
-	sample->cur += mul_u32_u32(val, unit);
+	sample->cur += val;
 }
 
-static void engines_sample(struct drm_i915_private *dev_priv)
+static void
+engines_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 {
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
@@ -182,8 +184,9 @@ static void engines_sample(struct drm_i915_private *dev_priv)
 
 		val = !i915_seqno_passed(current_seqno, last_seqno);
 
-		update_sample(&engine->pmu.sample[I915_SAMPLE_BUSY],
-			      PERIOD, val);
+		if (val)
+			add_sample(&engine->pmu.sample[I915_SAMPLE_BUSY],
+				   period_ns);
 
 		if (val && (engine->pmu.enable &
 		    (BIT(I915_SAMPLE_WAIT) | BIT(I915_SAMPLE_SEMA)))) {
@@ -194,11 +197,13 @@ static void engines_sample(struct drm_i915_private *dev_priv)
 			val = 0;
 		}
 
-		update_sample(&engine->pmu.sample[I915_SAMPLE_WAIT],
-			      PERIOD, !!(val & RING_WAIT));
+		if (val & RING_WAIT)
+			add_sample(&engine->pmu.sample[I915_SAMPLE_WAIT],
+				   period_ns);
 
-		update_sample(&engine->pmu.sample[I915_SAMPLE_SEMA],
-			      PERIOD, !!(val & RING_WAIT_SEMAPHORE));
+		if (val & RING_WAIT_SEMAPHORE)
+			add_sample(&engine->pmu.sample[I915_SAMPLE_SEMA],
+				   period_ns);
 	}
 
 	if (fw)
@@ -207,7 +212,14 @@ static void engines_sample(struct drm_i915_private *dev_priv)
 	intel_runtime_pm_put(dev_priv);
 }
 
-static void frequency_sample(struct drm_i915_private *dev_priv)
+static void
+add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul)
+{
+	sample->cur += mul_u32_u32(val, mul);
+}
+
+static void
+frequency_sample(struct drm_i915_private *dev_priv, unsigned int period_ns)
 {
 	if (dev_priv->pmu.enable &
 	    config_enabled_mask(I915_PMU_ACTUAL_FREQUENCY)) {
@@ -221,15 +233,17 @@ static void frequency_sample(struct drm_i915_private *dev_priv)
 			intel_runtime_pm_put(dev_priv);
 		}
 
-		update_sample(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT],
-			      1, intel_gpu_freq(dev_priv, val));
+		add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_ACT],
+				intel_gpu_freq(dev_priv, val),
+				period_ns / 1000);
 	}
 
 	if (dev_priv->pmu.enable &
 	    config_enabled_mask(I915_PMU_REQUESTED_FREQUENCY)) {
-		update_sample(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_REQ], 1,
-			      intel_gpu_freq(dev_priv,
-					     dev_priv->gt_pm.rps.cur_freq));
+		add_sample_mult(&dev_priv->pmu.sample[__I915_SAMPLE_FREQ_REQ],
+				intel_gpu_freq(dev_priv,
+					       dev_priv->gt_pm.rps.cur_freq),
+				period_ns / 1000);
 	}
 }
 
@@ -237,14 +251,27 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 {
 	struct drm_i915_private *i915 =
 		container_of(hrtimer, struct drm_i915_private, pmu.timer);
+	unsigned int period_ns;
+	ktime_t now;
 
 	if (!READ_ONCE(i915->pmu.timer_enabled))
 		return HRTIMER_NORESTART;
 
-	engines_sample(i915);
-	frequency_sample(i915);
+	now = ktime_get();
+	period_ns = ktime_to_ns(ktime_sub(now, i915->pmu.timer_last));
+	i915->pmu.timer_last = now;
+
+	/*
+	 * Strictly speaking the passed in period may not be 100% accurate for
+	 * all internal calculation, since some amount of time can be spent on
+	 * grabbing the forcewake. However the potential error from timer call-
+	 * back delay greatly dominates this so we keep it simple.
+	 */
+	engines_sample(i915, period_ns);
+	frequency_sample(i915, period_ns);
+
+	hrtimer_forward(hrtimer, now, ns_to_ktime(PERIOD));
 
-	hrtimer_forward_now(hrtimer, ns_to_ktime(PERIOD));
 	return HRTIMER_RESTART;
 }
 
@@ -519,12 +546,12 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 		case I915_PMU_ACTUAL_FREQUENCY:
 			val =
 			   div_u64(i915->pmu.sample[__I915_SAMPLE_FREQ_ACT].cur,
-				   FREQUENCY);
+				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_REQUESTED_FREQUENCY:
 			val =
 			   div_u64(i915->pmu.sample[__I915_SAMPLE_FREQ_REQ].cur,
-				   FREQUENCY);
+				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_INTERRUPTS:
 			val = count_interrupts(i915);
diff --git a/drivers/gpu/drm/i915/i915_pmu.h b/drivers/gpu/drm/i915/i915_pmu.h
index 2ba735299f7c..7f164ca3db12 100644
--- a/drivers/gpu/drm/i915/i915_pmu.h
+++ b/drivers/gpu/drm/i915/i915_pmu.h
@@ -65,6 +65,14 @@ struct i915_pmu {
 	 * event types.
 	 */
 	u64 enable;
+
+	/**
+	 * @timer_last:
+	 *
+	 * Timestmap of the previous timer invocation.
+	 */
+	ktime_t timer_last;
+
 	/**
 	 * @enable_count: Reference counts for the enabled events.
 	 *
-- 
cgit v1.2.3


From 70be8b3dab43497718a2260f1daf47d378815d90 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Tue, 5 Jun 2018 12:05:47 +0000
Subject: drm/i915/guc: Don't leak stage descriptor pool on init failure

In case of failure during GuC clients creation, we forget to
cleanup earlier pool allocation. Use proper teardown to fix that.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605120547.16468-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 133367a17863..23e9f2023bc5 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -1157,7 +1157,7 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	WARN_ON(!guc_verify_doorbells(guc));
 	ret = guc_clients_create(guc);
 	if (ret)
-		return ret;
+		goto err_pool;
 
 	for_each_engine(engine, dev_priv, id) {
 		guc->preempt_work[id].engine = engine;
@@ -1166,6 +1166,9 @@ int intel_guc_submission_init(struct intel_guc *guc)
 
 	return 0;
 
+err_pool:
+	guc_stage_desc_pool_destroy(guc);
+	return ret;
 }
 
 void intel_guc_submission_fini(struct intel_guc *guc)
-- 
cgit v1.2.3


From cd68e04cf56a38029940a33cbc834b4ab15b2bdb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 5 Jun 2018 17:06:23 +0100
Subject: drm/i915/error: Fixup inactive/active counting

The inactive counter was over the active list, and vice versa.
Fortuitously this should not cause a problem in practice as they shared
the same array and clamped the number of entries they would write.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605160623.30163-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 47721437a4c5..6702776303bf 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1570,11 +1570,11 @@ static void capture_pinned_buffers(struct i915_gpu_state *error)
 	int count_inactive, count_active;
 
 	count_inactive = 0;
-	list_for_each_entry(vma, &vm->active_list, vm_link)
+	list_for_each_entry(vma, &vm->inactive_list, vm_link)
 		count_inactive++;
 
 	count_active = 0;
-	list_for_each_entry(vma, &vm->inactive_list, vm_link)
+	list_for_each_entry(vma, &vm->active_list, vm_link)
 		count_active++;
 
 	bo = NULL;
-- 
cgit v1.2.3


From 82ad6443a55ea274ab2f0e24ada71f0529f3238b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 5 Jun 2018 16:37:58 +0100
Subject: drm/i915/gtt: Rename i915_hw_ppgtt base member

In the near future, I want to subclass gen6_hw_ppgtt as it contains a
few specialised members and I wish to add more. To avoid the ugliness of
using ppgtt->base.base, rename the i915_hw_ppgtt base member
(i915_address_space) as vm, which is our common shorthand for an
i915_address_space local.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605153758.18422-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gvt/aperture_gm.c             |   2 +-
 drivers/gpu/drm/i915/gvt/gvt.h                     |   4 +-
 drivers/gpu/drm/i915/i915_debugfs.c                |   4 +-
 drivers/gpu/drm/i915/i915_drv.h                    |   2 +-
 drivers/gpu/drm/i915/i915_gem.c                    |  30 +-
 drivers/gpu/drm/i915/i915_gem_context.c            |  10 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c         |  16 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c                | 333 ++++++++++-----------
 drivers/gpu/drm/i915/i915_gem_gtt.h                |   8 +-
 drivers/gpu/drm/i915/i915_gem_render_state.c       |   2 +-
 drivers/gpu/drm/i915/i915_gem_shrinker.c           |   2 +-
 drivers/gpu/drm/i915/i915_gem_stolen.c             |   6 +-
 drivers/gpu/drm/i915/i915_gpu_error.c              |   9 +-
 drivers/gpu/drm/i915/i915_trace.h                  |   4 +-
 drivers/gpu/drm/i915/i915_vgpu.c                   |   8 +-
 drivers/gpu/drm/i915/i915_vma.c                    |   2 +-
 drivers/gpu/drm/i915/intel_engine_cs.c             |   4 +-
 drivers/gpu/drm/i915/intel_guc.c                   |   2 +-
 drivers/gpu/drm/i915/intel_guc_submission.c        |   2 +-
 drivers/gpu/drm/i915/intel_lrc.c                   |  10 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c            |   4 +-
 drivers/gpu/drm/i915/selftests/huge_pages.c        |  50 ++--
 drivers/gpu/drm/i915/selftests/i915_gem_context.c  |   6 +-
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c    |  34 +--
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c      | 110 +++----
 drivers/gpu/drm/i915/selftests/i915_gem_object.c   |   6 +-
 drivers/gpu/drm/i915/selftests/i915_request.c      |   5 +-
 drivers/gpu/drm/i915/selftests/i915_vma.c          |  31 +-
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c   |   4 +-
 drivers/gpu/drm/i915/selftests/intel_lrc.c         |   2 +-
 drivers/gpu/drm/i915/selftests/intel_workarounds.c |   2 +-
 drivers/gpu/drm/i915/selftests/mock_gtt.c          |  66 ++--
 32 files changed, 390 insertions(+), 390 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/aperture_gm.c b/drivers/gpu/drm/i915/gvt/aperture_gm.c
index 7c9ec4f4f36c..380eeb2a0e83 100644
--- a/drivers/gpu/drm/i915/gvt/aperture_gm.c
+++ b/drivers/gpu/drm/i915/gvt/aperture_gm.c
@@ -61,7 +61,7 @@ static int alloc_gm(struct intel_vgpu *vgpu, bool high_gm)
 	}
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ret = i915_gem_gtt_insert(&dev_priv->ggtt.base, node,
+	ret = i915_gem_gtt_insert(&dev_priv->ggtt.vm, node,
 				  size, I915_GTT_PAGE_SIZE,
 				  I915_COLOR_UNEVICTABLE,
 				  start, end, flags);
diff --git a/drivers/gpu/drm/i915/gvt/gvt.h b/drivers/gpu/drm/i915/gvt/gvt.h
index 05d15a095310..2ff0d40281a9 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.h
+++ b/drivers/gpu/drm/i915/gvt/gvt.h
@@ -361,9 +361,9 @@ int intel_gvt_load_firmware(struct intel_gvt *gvt);
 #define gvt_aperture_sz(gvt)	  (gvt->dev_priv->ggtt.mappable_end)
 #define gvt_aperture_pa_base(gvt) (gvt->dev_priv->ggtt.gmadr.start)
 
-#define gvt_ggtt_gm_sz(gvt)	  (gvt->dev_priv->ggtt.base.total)
+#define gvt_ggtt_gm_sz(gvt)	  (gvt->dev_priv->ggtt.vm.total)
 #define gvt_ggtt_sz(gvt) \
-	((gvt->dev_priv->ggtt.base.total >> PAGE_SHIFT) << 3)
+	((gvt->dev_priv->ggtt.vm.total >> PAGE_SHIFT) << 3)
 #define gvt_hidden_sz(gvt)	  (gvt_ggtt_gm_sz(gvt) - gvt_aperture_sz(gvt))
 
 #define gvt_aperture_gmadr_base(gvt) (0)
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 15e86d34a81c..698af45e229c 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -328,7 +328,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 		} else {
 			struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vma->vm);
 
-			if (ppgtt->base.file != stats->file_priv)
+			if (ppgtt->vm.file != stats->file_priv)
 				continue;
 		}
 
@@ -508,7 +508,7 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 		   dpy_count, dpy_size);
 
 	seq_printf(m, "%llu [%pa] gtt total\n",
-		   ggtt->base.total, &ggtt->mappable_end);
+		   ggtt->vm.total, &ggtt->mappable_end);
 	seq_printf(m, "Supported page sizes: %s\n",
 		   stringify_page_sizes(INTEL_INFO(dev_priv)->page_sizes,
 					buf, sizeof(buf)));
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 06ecac4c3253..a4bb30c32a52 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3213,7 +3213,7 @@ struct dma_buf *i915_gem_prime_export(struct drm_device *dev,
 static inline struct i915_hw_ppgtt *
 i915_vm_to_ppgtt(struct i915_address_space *vm)
 {
-	return container_of(vm, struct i915_hw_ppgtt, base);
+	return container_of(vm, struct i915_hw_ppgtt, vm);
 }
 
 /* i915_gem_fence_reg.c */
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 23374f3dd79d..86f1f9aaa119 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -65,7 +65,7 @@ insert_mappable_node(struct i915_ggtt *ggtt,
                      struct drm_mm_node *node, u32 size)
 {
 	memset(node, 0, sizeof(*node));
-	return drm_mm_insert_node_in_range(&ggtt->base.mm, node,
+	return drm_mm_insert_node_in_range(&ggtt->vm.mm, node,
 					   size, 0, I915_COLOR_UNEVICTABLE,
 					   0, ggtt->mappable_end,
 					   DRM_MM_INSERT_LOW);
@@ -249,17 +249,17 @@ i915_gem_get_aperture_ioctl(struct drm_device *dev, void *data,
 	struct i915_vma *vma;
 	u64 pinned;
 
-	pinned = ggtt->base.reserved;
+	pinned = ggtt->vm.reserved;
 	mutex_lock(&dev->struct_mutex);
-	list_for_each_entry(vma, &ggtt->base.active_list, vm_link)
+	list_for_each_entry(vma, &ggtt->vm.active_list, vm_link)
 		if (i915_vma_is_pinned(vma))
 			pinned += vma->node.size;
-	list_for_each_entry(vma, &ggtt->base.inactive_list, vm_link)
+	list_for_each_entry(vma, &ggtt->vm.inactive_list, vm_link)
 		if (i915_vma_is_pinned(vma))
 			pinned += vma->node.size;
 	mutex_unlock(&dev->struct_mutex);
 
-	args->aper_size = ggtt->base.total;
+	args->aper_size = ggtt->vm.total;
 	args->aper_available_size = args->aper_size - pinned;
 
 	return 0;
@@ -1223,9 +1223,9 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 		page_length = remain < page_length ? remain : page_length;
 		if (node.allocated) {
 			wmb();
-			ggtt->base.insert_page(&ggtt->base,
-					       i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
-					       node.start, I915_CACHE_NONE, 0);
+			ggtt->vm.insert_page(&ggtt->vm,
+					     i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
+					     node.start, I915_CACHE_NONE, 0);
 			wmb();
 		} else {
 			page_base += offset & PAGE_MASK;
@@ -1246,8 +1246,7 @@ i915_gem_gtt_pread(struct drm_i915_gem_object *obj,
 out_unpin:
 	if (node.allocated) {
 		wmb();
-		ggtt->base.clear_range(&ggtt->base,
-				       node.start, node.size);
+		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(&node);
 	} else {
 		i915_vma_unpin(vma);
@@ -1426,9 +1425,9 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 		page_length = remain < page_length ? remain : page_length;
 		if (node.allocated) {
 			wmb(); /* flush the write before we modify the GGTT */
-			ggtt->base.insert_page(&ggtt->base,
-					       i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
-					       node.start, I915_CACHE_NONE, 0);
+			ggtt->vm.insert_page(&ggtt->vm,
+					     i915_gem_object_get_dma_address(obj, offset >> PAGE_SHIFT),
+					     node.start, I915_CACHE_NONE, 0);
 			wmb(); /* flush modifications to the GGTT (insert_page) */
 		} else {
 			page_base += offset & PAGE_MASK;
@@ -1455,8 +1454,7 @@ i915_gem_gtt_pwrite_fast(struct drm_i915_gem_object *obj,
 out_unpin:
 	if (node.allocated) {
 		wmb();
-		ggtt->base.clear_range(&ggtt->base,
-				       node.start, node.size);
+		ggtt->vm.clear_range(&ggtt->vm, node.start, node.size);
 		remove_mappable_node(&node);
 	} else {
 		i915_vma_unpin(vma);
@@ -4374,7 +4372,7 @@ i915_gem_object_ggtt_pin(struct drm_i915_gem_object *obj,
 			 u64 flags)
 {
 	struct drm_i915_private *dev_priv = to_i915(obj->base.dev);
-	struct i915_address_space *vm = &dev_priv->ggtt.base;
+	struct i915_address_space *vm = &dev_priv->ggtt.vm;
 	struct i915_vma *vma;
 	int ret;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 38c6e9e4e91b..b2c7ac1b074d 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -197,7 +197,7 @@ static void context_close(struct i915_gem_context *ctx)
 	 */
 	lut_close(ctx);
 	if (ctx->ppgtt)
-		i915_ppgtt_close(&ctx->ppgtt->base);
+		i915_ppgtt_close(&ctx->ppgtt->vm);
 
 	ctx->file_priv = ERR_PTR(-EBADF);
 	i915_gem_context_put(ctx);
@@ -249,7 +249,7 @@ static u32 default_desc_template(const struct drm_i915_private *i915,
 	desc = GEN8_CTX_VALID | GEN8_CTX_PRIVILEGE;
 
 	address_mode = INTEL_LEGACY_32B_CONTEXT;
-	if (ppgtt && i915_vm_is_48bit(&ppgtt->base))
+	if (ppgtt && i915_vm_is_48bit(&ppgtt->vm))
 		address_mode = INTEL_LEGACY_64B_CONTEXT;
 	desc |= address_mode << GEN8_CTX_ADDRESSING_MODE_SHIFT;
 
@@ -810,11 +810,11 @@ int i915_gem_context_getparam_ioctl(struct drm_device *dev, void *data,
 		break;
 	case I915_CONTEXT_PARAM_GTT_SIZE:
 		if (ctx->ppgtt)
-			args->value = ctx->ppgtt->base.total;
+			args->value = ctx->ppgtt->vm.total;
 		else if (to_i915(dev)->mm.aliasing_ppgtt)
-			args->value = to_i915(dev)->mm.aliasing_ppgtt->base.total;
+			args->value = to_i915(dev)->mm.aliasing_ppgtt->vm.total;
 		else
-			args->value = to_i915(dev)->ggtt.base.total;
+			args->value = to_i915(dev)->ggtt.vm.total;
 		break;
 	case I915_CONTEXT_PARAM_NO_ERROR_CAPTURE:
 		args->value = i915_gem_context_no_error_capture(ctx);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index f627a8c47c58..eefd449502e2 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -703,7 +703,7 @@ static int eb_select_context(struct i915_execbuffer *eb)
 		return -ENOENT;
 
 	eb->ctx = ctx;
-	eb->vm = ctx->ppgtt ? &ctx->ppgtt->base : &eb->i915->ggtt.base;
+	eb->vm = ctx->ppgtt ? &ctx->ppgtt->vm : &eb->i915->ggtt.vm;
 
 	eb->context_flags = 0;
 	if (ctx->flags & CONTEXT_NO_ZEROMAP)
@@ -943,9 +943,9 @@ static void reloc_cache_reset(struct reloc_cache *cache)
 		if (cache->node.allocated) {
 			struct i915_ggtt *ggtt = cache_to_ggtt(cache);
 
-			ggtt->base.clear_range(&ggtt->base,
-					       cache->node.start,
-					       cache->node.size);
+			ggtt->vm.clear_range(&ggtt->vm,
+					     cache->node.start,
+					     cache->node.size);
 			drm_mm_remove_node(&cache->node);
 		} else {
 			i915_vma_unpin((struct i915_vma *)cache->node.mm);
@@ -1016,7 +1016,7 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj,
 		if (IS_ERR(vma)) {
 			memset(&cache->node, 0, sizeof(cache->node));
 			err = drm_mm_insert_node_in_range
-				(&ggtt->base.mm, &cache->node,
+				(&ggtt->vm.mm, &cache->node,
 				 PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
 				 0, ggtt->mappable_end,
 				 DRM_MM_INSERT_LOW);
@@ -1037,9 +1037,9 @@ static void *reloc_iomap(struct drm_i915_gem_object *obj,
 	offset = cache->node.start;
 	if (cache->node.allocated) {
 		wmb();
-		ggtt->base.insert_page(&ggtt->base,
-				       i915_gem_object_get_dma_address(obj, page),
-				       offset, I915_CACHE_NONE, 0);
+		ggtt->vm.insert_page(&ggtt->vm,
+				     i915_gem_object_get_dma_address(obj, page),
+				     offset, I915_CACHE_NONE, 0);
 	} else {
 		offset += page << PAGE_SHIFT;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 9302ee6e717d..029a5f4fbd92 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -780,7 +780,7 @@ static void gen8_initialize_pml4(struct i915_address_space *vm,
  */
 static void mark_tlbs_dirty(struct i915_hw_ppgtt *ppgtt)
 {
-	ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->base.i915)->ring_mask;
+	ppgtt->pd_dirty_rings = INTEL_INFO(ppgtt->vm.i915)->ring_mask;
 }
 
 /* Removes entries from a single page table, releasing it if it's empty.
@@ -973,7 +973,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 	gen8_pte_t *vaddr;
 	bool ret;
 
-	GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base));
+	GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->vm));
 	pd = pdp->page_directory[idx->pdpe];
 	vaddr = kmap_atomic_px(pd->page_table[idx->pde]);
 	do {
@@ -1004,7 +1004,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 					break;
 				}
 
-				GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->base));
+				GEM_BUG_ON(idx->pdpe >= i915_pdpes_per_pdp(&ppgtt->vm));
 				pd = pdp->page_directory[idx->pdpe];
 			}
 
@@ -1233,7 +1233,7 @@ free_scratch_page:
 
 static int gen8_ppgtt_notify_vgt(struct i915_hw_ppgtt *ppgtt, bool create)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct drm_i915_private *dev_priv = vm->i915;
 	enum vgt_g2v_type msg;
 	int i;
@@ -1294,13 +1294,13 @@ static void gen8_ppgtt_cleanup_4lvl(struct i915_hw_ppgtt *ppgtt)
 	int i;
 
 	for (i = 0; i < GEN8_PML4ES_PER_PML4; i++) {
-		if (ppgtt->pml4.pdps[i] == ppgtt->base.scratch_pdp)
+		if (ppgtt->pml4.pdps[i] == ppgtt->vm.scratch_pdp)
 			continue;
 
-		gen8_ppgtt_cleanup_3lvl(&ppgtt->base, ppgtt->pml4.pdps[i]);
+		gen8_ppgtt_cleanup_3lvl(&ppgtt->vm, ppgtt->pml4.pdps[i]);
 	}
 
-	cleanup_px(&ppgtt->base, &ppgtt->pml4);
+	cleanup_px(&ppgtt->vm, &ppgtt->pml4);
 }
 
 static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
@@ -1314,7 +1314,7 @@ static void gen8_ppgtt_cleanup(struct i915_address_space *vm)
 	if (use_4lvl(vm))
 		gen8_ppgtt_cleanup_4lvl(ppgtt);
 	else
-		gen8_ppgtt_cleanup_3lvl(&ppgtt->base, &ppgtt->pdp);
+		gen8_ppgtt_cleanup_3lvl(&ppgtt->vm, &ppgtt->pdp);
 
 	gen8_free_scratch(vm);
 }
@@ -1450,7 +1450,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 			  gen8_pte_t scratch_pte,
 			  struct seq_file *m)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct i915_page_directory *pd;
 	u32 pdpe;
 
@@ -1460,7 +1460,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 		u64 pd_start = start;
 		u32 pde;
 
-		if (pdp->page_directory[pdpe] == ppgtt->base.scratch_pd)
+		if (pdp->page_directory[pdpe] == ppgtt->vm.scratch_pd)
 			continue;
 
 		seq_printf(m, "\tPDPE #%d\n", pdpe);
@@ -1468,7 +1468,7 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 			u32 pte;
 			gen8_pte_t *pt_vaddr;
 
-			if (pd->page_table[pde] == ppgtt->base.scratch_pt)
+			if (pd->page_table[pde] == ppgtt->vm.scratch_pt)
 				continue;
 
 			pt_vaddr = kmap_atomic_px(pt);
@@ -1501,10 +1501,10 @@ static void gen8_dump_pdp(struct i915_hw_ppgtt *ppgtt,
 
 static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	const gen8_pte_t scratch_pte =
 		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
-	u64 start = 0, length = ppgtt->base.total;
+	u64 start = 0, length = ppgtt->vm.total;
 
 	if (use_4lvl(vm)) {
 		u64 pml4e;
@@ -1512,7 +1512,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 		struct i915_page_directory_pointer *pdp;
 
 		gen8_for_each_pml4e(pdp, pml4, start, length, pml4e) {
-			if (pml4->pdps[pml4e] == ppgtt->base.scratch_pdp)
+			if (pml4->pdps[pml4e] == ppgtt->vm.scratch_pdp)
 				continue;
 
 			seq_printf(m, "    PML4E #%llu\n", pml4e);
@@ -1525,10 +1525,10 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 
 static int gen8_preallocate_top_level_pdp(struct i915_hw_ppgtt *ppgtt)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct i915_page_directory_pointer *pdp = &ppgtt->pdp;
 	struct i915_page_directory *pd;
-	u64 start = 0, length = ppgtt->base.total;
+	u64 start = 0, length = ppgtt->vm.total;
 	u64 from = start;
 	unsigned int pdpe;
 
@@ -1564,11 +1564,11 @@ unwind:
  */
 static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct drm_i915_private *dev_priv = vm->i915;
 	int ret;
 
-	ppgtt->base.total = USES_FULL_48BIT_PPGTT(dev_priv) ?
+	ppgtt->vm.total = USES_FULL_48BIT_PPGTT(dev_priv) ?
 		1ULL << 48 :
 		1ULL << 32;
 
@@ -1576,26 +1576,26 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	 * And we are not sure about the latter so play safe for now.
 	 */
 	if (IS_CHERRYVIEW(dev_priv) || IS_BROXTON(dev_priv))
-		ppgtt->base.pt_kmap_wc = true;
+		ppgtt->vm.pt_kmap_wc = true;
 
-	ret = gen8_init_scratch(&ppgtt->base);
+	ret = gen8_init_scratch(&ppgtt->vm);
 	if (ret) {
-		ppgtt->base.total = 0;
+		ppgtt->vm.total = 0;
 		return ret;
 	}
 
 	if (use_4lvl(vm)) {
-		ret = setup_px(&ppgtt->base, &ppgtt->pml4);
+		ret = setup_px(&ppgtt->vm, &ppgtt->pml4);
 		if (ret)
 			goto free_scratch;
 
-		gen8_initialize_pml4(&ppgtt->base, &ppgtt->pml4);
+		gen8_initialize_pml4(&ppgtt->vm, &ppgtt->pml4);
 
-		ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_4lvl;
-		ppgtt->base.insert_entries = gen8_ppgtt_insert_4lvl;
-		ppgtt->base.clear_range = gen8_ppgtt_clear_4lvl;
+		ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc_4lvl;
+		ppgtt->vm.insert_entries = gen8_ppgtt_insert_4lvl;
+		ppgtt->vm.clear_range = gen8_ppgtt_clear_4lvl;
 	} else {
-		ret = __pdp_init(&ppgtt->base, &ppgtt->pdp);
+		ret = __pdp_init(&ppgtt->vm, &ppgtt->pdp);
 		if (ret)
 			goto free_scratch;
 
@@ -1607,35 +1607,35 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 			}
 		}
 
-		ppgtt->base.allocate_va_range = gen8_ppgtt_alloc_3lvl;
-		ppgtt->base.insert_entries = gen8_ppgtt_insert_3lvl;
-		ppgtt->base.clear_range = gen8_ppgtt_clear_3lvl;
+		ppgtt->vm.allocate_va_range = gen8_ppgtt_alloc_3lvl;
+		ppgtt->vm.insert_entries = gen8_ppgtt_insert_3lvl;
+		ppgtt->vm.clear_range = gen8_ppgtt_clear_3lvl;
 	}
 
 	if (intel_vgpu_active(dev_priv))
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
-	ppgtt->base.cleanup = gen8_ppgtt_cleanup;
-	ppgtt->base.bind_vma = gen8_ppgtt_bind_vma;
-	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->base.set_pages = ppgtt_set_pages;
-	ppgtt->base.clear_pages = clear_pages;
+	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
+	ppgtt->vm.bind_vma = gen8_ppgtt_bind_vma;
+	ppgtt->vm.unbind_vma = ppgtt_unbind_vma;
+	ppgtt->vm.set_pages = ppgtt_set_pages;
+	ppgtt->vm.clear_pages = clear_pages;
 	ppgtt->debug_dump = gen8_dump_ppgtt;
 
 	return 0;
 
 free_scratch:
-	gen8_free_scratch(&ppgtt->base);
+	gen8_free_scratch(&ppgtt->vm);
 	return ret;
 }
 
 static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 {
-	struct i915_address_space *vm = &ppgtt->base;
+	struct i915_address_space *vm = &ppgtt->vm;
 	struct i915_page_table *unused;
 	gen6_pte_t scratch_pte;
 	u32 pd_entry, pte, pde;
-	u32 start = 0, length = ppgtt->base.total;
+	u32 start = 0, length = ppgtt->vm.total;
 
 	scratch_pte = vm->pte_encode(vm->scratch_page.daddr,
 				     I915_CACHE_LLC, 0);
@@ -1972,8 +1972,8 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 
 static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
 {
-	struct i915_address_space *vm = &ppgtt->base;
-	struct drm_i915_private *dev_priv = ppgtt->base.i915;
+	struct i915_address_space *vm = &ppgtt->vm;
+	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
@@ -1981,16 +1981,16 @@ static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
 	 * allocator works in address space sizes, so it's multiplied by page
 	 * size. We allocate at the top of the GTT to avoid fragmentation.
 	 */
-	BUG_ON(!drm_mm_initialized(&ggtt->base.mm));
+	BUG_ON(!drm_mm_initialized(&ggtt->vm.mm));
 
 	ret = gen6_init_scratch(vm);
 	if (ret)
 		return ret;
 
-	ret = i915_gem_gtt_insert(&ggtt->base, &ppgtt->node,
+	ret = i915_gem_gtt_insert(&ggtt->vm, &ppgtt->node,
 				  GEN6_PD_SIZE, GEN6_PD_ALIGN,
 				  I915_COLOR_UNEVICTABLE,
-				  0, ggtt->base.total,
+				  0, ggtt->vm.total,
 				  PIN_HIGH);
 	if (ret)
 		goto err_out;
@@ -2023,16 +2023,16 @@ static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
 	u32 pde;
 
 	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde)
-		ppgtt->pd.page_table[pde] = ppgtt->base.scratch_pt;
+		ppgtt->pd.page_table[pde] = ppgtt->vm.scratch_pt;
 }
 
 static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 {
-	struct drm_i915_private *dev_priv = ppgtt->base.i915;
+	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
-	ppgtt->base.pte_encode = ggtt->base.pte_encode;
+	ppgtt->vm.pte_encode = ggtt->vm.pte_encode;
 	if (intel_vgpu_active(dev_priv) || IS_GEN6(dev_priv))
 		ppgtt->switch_mm = gen6_mm_switch;
 	else if (IS_HASWELL(dev_priv))
@@ -2046,24 +2046,24 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	if (ret)
 		return ret;
 
-	ppgtt->base.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
+	ppgtt->vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
 
-	gen6_scratch_va_range(ppgtt, 0, ppgtt->base.total);
-	gen6_write_page_range(ppgtt, 0, ppgtt->base.total);
+	gen6_scratch_va_range(ppgtt, 0, ppgtt->vm.total);
+	gen6_write_page_range(ppgtt, 0, ppgtt->vm.total);
 
-	ret = gen6_alloc_va_range(&ppgtt->base, 0, ppgtt->base.total);
+	ret = gen6_alloc_va_range(&ppgtt->vm, 0, ppgtt->vm.total);
 	if (ret) {
-		gen6_ppgtt_cleanup(&ppgtt->base);
+		gen6_ppgtt_cleanup(&ppgtt->vm);
 		return ret;
 	}
 
-	ppgtt->base.clear_range = gen6_ppgtt_clear_range;
-	ppgtt->base.insert_entries = gen6_ppgtt_insert_entries;
-	ppgtt->base.bind_vma = gen6_ppgtt_bind_vma;
-	ppgtt->base.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->base.set_pages = ppgtt_set_pages;
-	ppgtt->base.clear_pages = clear_pages;
-	ppgtt->base.cleanup = gen6_ppgtt_cleanup;
+	ppgtt->vm.clear_range = gen6_ppgtt_clear_range;
+	ppgtt->vm.insert_entries = gen6_ppgtt_insert_entries;
+	ppgtt->vm.bind_vma = gen6_ppgtt_bind_vma;
+	ppgtt->vm.unbind_vma = ppgtt_unbind_vma;
+	ppgtt->vm.set_pages = ppgtt_set_pages;
+	ppgtt->vm.clear_pages = clear_pages;
+	ppgtt->vm.cleanup = gen6_ppgtt_cleanup;
 	ppgtt->debug_dump = gen6_dump_ppgtt;
 
 	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
@@ -2079,8 +2079,8 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 static int __hw_ppgtt_init(struct i915_hw_ppgtt *ppgtt,
 			   struct drm_i915_private *dev_priv)
 {
-	ppgtt->base.i915 = dev_priv;
-	ppgtt->base.dma = &dev_priv->drm.pdev->dev;
+	ppgtt->vm.i915 = dev_priv;
+	ppgtt->vm.dma = &dev_priv->drm.pdev->dev;
 
 	if (INTEL_GEN(dev_priv) < 8)
 		return gen6_ppgtt_init(ppgtt);
@@ -2190,10 +2190,10 @@ i915_ppgtt_create(struct drm_i915_private *dev_priv,
 	}
 
 	kref_init(&ppgtt->ref);
-	i915_address_space_init(&ppgtt->base, dev_priv, name);
-	ppgtt->base.file = fpriv;
+	i915_address_space_init(&ppgtt->vm, dev_priv, name);
+	ppgtt->vm.file = fpriv;
 
-	trace_i915_ppgtt_create(&ppgtt->base);
+	trace_i915_ppgtt_create(&ppgtt->vm);
 
 	return ppgtt;
 }
@@ -2227,16 +2227,16 @@ void i915_ppgtt_release(struct kref *kref)
 	struct i915_hw_ppgtt *ppgtt =
 		container_of(kref, struct i915_hw_ppgtt, ref);
 
-	trace_i915_ppgtt_release(&ppgtt->base);
+	trace_i915_ppgtt_release(&ppgtt->vm);
 
-	ppgtt_destroy_vma(&ppgtt->base);
+	ppgtt_destroy_vma(&ppgtt->vm);
 
-	GEM_BUG_ON(!list_empty(&ppgtt->base.active_list));
-	GEM_BUG_ON(!list_empty(&ppgtt->base.inactive_list));
-	GEM_BUG_ON(!list_empty(&ppgtt->base.unbound_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->vm.active_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->vm.inactive_list));
+	GEM_BUG_ON(!list_empty(&ppgtt->vm.unbound_list));
 
-	ppgtt->base.cleanup(&ppgtt->base);
-	i915_address_space_fini(&ppgtt->base);
+	ppgtt->vm.cleanup(&ppgtt->vm);
+	i915_address_space_fini(&ppgtt->vm);
 	kfree(ppgtt);
 }
 
@@ -2332,7 +2332,7 @@ void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv)
 
 	i915_check_and_clear_faults(dev_priv);
 
-	ggtt->base.clear_range(&ggtt->base, 0, ggtt->base.total);
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
 
 	i915_ggtt_invalidate(dev_priv);
 }
@@ -2675,16 +2675,16 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 		struct i915_hw_ppgtt *appgtt = i915->mm.aliasing_ppgtt;
 
 		if (!(vma->flags & I915_VMA_LOCAL_BIND) &&
-		    appgtt->base.allocate_va_range) {
-			ret = appgtt->base.allocate_va_range(&appgtt->base,
-							     vma->node.start,
-							     vma->size);
+		    appgtt->vm.allocate_va_range) {
+			ret = appgtt->vm.allocate_va_range(&appgtt->vm,
+							   vma->node.start,
+							   vma->size);
 			if (ret)
 				return ret;
 		}
 
-		appgtt->base.insert_entries(&appgtt->base, vma, cache_level,
-					    pte_flags);
+		appgtt->vm.insert_entries(&appgtt->vm, vma, cache_level,
+					  pte_flags);
 	}
 
 	if (flags & I915_VMA_GLOBAL_BIND) {
@@ -2707,7 +2707,7 @@ static void aliasing_gtt_unbind_vma(struct i915_vma *vma)
 	}
 
 	if (vma->flags & I915_VMA_LOCAL_BIND) {
-		struct i915_address_space *vm = &i915->mm.aliasing_ppgtt->base;
+		struct i915_address_space *vm = &i915->mm.aliasing_ppgtt->vm;
 
 		vm->clear_range(vm, vma->node.start, vma->size);
 	}
@@ -2774,30 +2774,30 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
-	if (WARN_ON(ppgtt->base.total < ggtt->base.total)) {
+	if (WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
 		err = -ENODEV;
 		goto err_ppgtt;
 	}
 
-	if (ppgtt->base.allocate_va_range) {
+	if (ppgtt->vm.allocate_va_range) {
 		/* Note we only pre-allocate as far as the end of the global
 		 * GTT. On 48b / 4-level page-tables, the difference is very,
 		 * very significant! We have to preallocate as GVT/vgpu does
 		 * not like the page directory disappearing.
 		 */
-		err = ppgtt->base.allocate_va_range(&ppgtt->base,
-						    0, ggtt->base.total);
+		err = ppgtt->vm.allocate_va_range(&ppgtt->vm,
+						  0, ggtt->vm.total);
 		if (err)
 			goto err_ppgtt;
 	}
 
 	i915->mm.aliasing_ppgtt = ppgtt;
 
-	GEM_BUG_ON(ggtt->base.bind_vma != ggtt_bind_vma);
-	ggtt->base.bind_vma = aliasing_gtt_bind_vma;
+	GEM_BUG_ON(ggtt->vm.bind_vma != ggtt_bind_vma);
+	ggtt->vm.bind_vma = aliasing_gtt_bind_vma;
 
-	GEM_BUG_ON(ggtt->base.unbind_vma != ggtt_unbind_vma);
-	ggtt->base.unbind_vma = aliasing_gtt_unbind_vma;
+	GEM_BUG_ON(ggtt->vm.unbind_vma != ggtt_unbind_vma);
+	ggtt->vm.unbind_vma = aliasing_gtt_unbind_vma;
 
 	return 0;
 
@@ -2817,8 +2817,8 @@ void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915)
 
 	i915_ppgtt_put(ppgtt);
 
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
+	ggtt->vm.bind_vma = ggtt_bind_vma;
+	ggtt->vm.unbind_vma = ggtt_unbind_vma;
 }
 
 int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
@@ -2842,7 +2842,7 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 		return ret;
 
 	/* Reserve a mappable slot for our lockless error capture */
-	ret = drm_mm_insert_node_in_range(&ggtt->base.mm, &ggtt->error_capture,
+	ret = drm_mm_insert_node_in_range(&ggtt->vm.mm, &ggtt->error_capture,
 					  PAGE_SIZE, 0, I915_COLOR_UNEVICTABLE,
 					  0, ggtt->mappable_end,
 					  DRM_MM_INSERT_LOW);
@@ -2850,16 +2850,15 @@ int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
 		return ret;
 
 	/* Clear any non-preallocated blocks */
-	drm_mm_for_each_hole(entry, &ggtt->base.mm, hole_start, hole_end) {
+	drm_mm_for_each_hole(entry, &ggtt->vm.mm, hole_start, hole_end) {
 		DRM_DEBUG_KMS("clearing unused GTT space: [%lx, %lx]\n",
 			      hole_start, hole_end);
-		ggtt->base.clear_range(&ggtt->base, hole_start,
-				       hole_end - hole_start);
+		ggtt->vm.clear_range(&ggtt->vm, hole_start,
+				     hole_end - hole_start);
 	}
 
 	/* And finally clear the reserved guard page */
-	ggtt->base.clear_range(&ggtt->base,
-			       ggtt->base.total - PAGE_SIZE, PAGE_SIZE);
+	ggtt->vm.clear_range(&ggtt->vm, ggtt->vm.total - PAGE_SIZE, PAGE_SIZE);
 
 	if (USES_PPGTT(dev_priv) && !USES_FULL_PPGTT(dev_priv)) {
 		ret = i915_gem_init_aliasing_ppgtt(dev_priv);
@@ -2884,11 +2883,11 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 	struct i915_vma *vma, *vn;
 	struct pagevec *pvec;
 
-	ggtt->base.closed = true;
+	ggtt->vm.closed = true;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	GEM_BUG_ON(!list_empty(&ggtt->base.active_list));
-	list_for_each_entry_safe(vma, vn, &ggtt->base.inactive_list, vm_link)
+	GEM_BUG_ON(!list_empty(&ggtt->vm.active_list));
+	list_for_each_entry_safe(vma, vn, &ggtt->vm.inactive_list, vm_link)
 		WARN_ON(i915_vma_unbind(vma));
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
@@ -2900,12 +2899,12 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 	if (drm_mm_node_allocated(&ggtt->error_capture))
 		drm_mm_remove_node(&ggtt->error_capture);
 
-	if (drm_mm_initialized(&ggtt->base.mm)) {
+	if (drm_mm_initialized(&ggtt->vm.mm)) {
 		intel_vgt_deballoon(dev_priv);
-		i915_address_space_fini(&ggtt->base);
+		i915_address_space_fini(&ggtt->vm);
 	}
 
-	ggtt->base.cleanup(&ggtt->base);
+	ggtt->vm.cleanup(&ggtt->vm);
 
 	pvec = &dev_priv->mm.wc_stash;
 	if (pvec->nr) {
@@ -2955,7 +2954,7 @@ static unsigned int chv_get_total_gtt_size(u16 gmch_ctrl)
 
 static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	phys_addr_t phys_addr;
 	int ret;
@@ -2979,7 +2978,7 @@ static int ggtt_probe_common(struct i915_ggtt *ggtt, u64 size)
 		return -ENOMEM;
 	}
 
-	ret = setup_scratch_page(&ggtt->base, GFP_DMA32);
+	ret = setup_scratch_page(&ggtt->vm, GFP_DMA32);
 	if (ret) {
 		DRM_ERROR("Scratch setup failed\n");
 		/* iounmap will also get called at remove, but meh */
@@ -3285,7 +3284,7 @@ static void setup_private_pat(struct drm_i915_private *dev_priv)
 
 static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	unsigned int size;
 	u16 snb_gmch_ctl;
@@ -3309,25 +3308,25 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 	else
 		size = gen8_get_total_gtt_size(snb_gmch_ctl);
 
-	ggtt->base.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
-	ggtt->base.cleanup = gen6_gmch_remove;
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.insert_page = gen8_ggtt_insert_page;
-	ggtt->base.clear_range = nop_clear_range;
+	ggtt->vm.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
+	ggtt->vm.cleanup = gen6_gmch_remove;
+	ggtt->vm.bind_vma = ggtt_bind_vma;
+	ggtt->vm.unbind_vma = ggtt_unbind_vma;
+	ggtt->vm.set_pages = ggtt_set_pages;
+	ggtt->vm.clear_pages = clear_pages;
+	ggtt->vm.insert_page = gen8_ggtt_insert_page;
+	ggtt->vm.clear_range = nop_clear_range;
 	if (!USES_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
-		ggtt->base.clear_range = gen8_ggtt_clear_range;
+		ggtt->vm.clear_range = gen8_ggtt_clear_range;
 
-	ggtt->base.insert_entries = gen8_ggtt_insert_entries;
+	ggtt->vm.insert_entries = gen8_ggtt_insert_entries;
 
 	/* Serialize GTT updates with aperture access on BXT if VT-d is on. */
 	if (intel_ggtt_update_needs_vtd_wa(dev_priv)) {
-		ggtt->base.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
-		ggtt->base.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
-		if (ggtt->base.clear_range != nop_clear_range)
-			ggtt->base.clear_range = bxt_vtd_ggtt_clear_range__BKL;
+		ggtt->vm.insert_entries = bxt_vtd_ggtt_insert_entries__BKL;
+		ggtt->vm.insert_page    = bxt_vtd_ggtt_insert_page__BKL;
+		if (ggtt->vm.clear_range != nop_clear_range)
+			ggtt->vm.clear_range = bxt_vtd_ggtt_clear_range__BKL;
 	}
 
 	ggtt->invalidate = gen6_ggtt_invalidate;
@@ -3339,7 +3338,7 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	unsigned int size;
 	u16 snb_gmch_ctl;
@@ -3366,29 +3365,29 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	pci_read_config_word(pdev, SNB_GMCH_CTRL, &snb_gmch_ctl);
 
 	size = gen6_get_total_gtt_size(snb_gmch_ctl);
-	ggtt->base.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT;
+	ggtt->vm.total = (size / sizeof(gen6_pte_t)) << PAGE_SHIFT;
 
-	ggtt->base.clear_range = gen6_ggtt_clear_range;
-	ggtt->base.insert_page = gen6_ggtt_insert_page;
-	ggtt->base.insert_entries = gen6_ggtt_insert_entries;
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.cleanup = gen6_gmch_remove;
+	ggtt->vm.clear_range = gen6_ggtt_clear_range;
+	ggtt->vm.insert_page = gen6_ggtt_insert_page;
+	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
+	ggtt->vm.bind_vma = ggtt_bind_vma;
+	ggtt->vm.unbind_vma = ggtt_unbind_vma;
+	ggtt->vm.set_pages = ggtt_set_pages;
+	ggtt->vm.clear_pages = clear_pages;
+	ggtt->vm.cleanup = gen6_gmch_remove;
 
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
 	if (HAS_EDRAM(dev_priv))
-		ggtt->base.pte_encode = iris_pte_encode;
+		ggtt->vm.pte_encode = iris_pte_encode;
 	else if (IS_HASWELL(dev_priv))
-		ggtt->base.pte_encode = hsw_pte_encode;
+		ggtt->vm.pte_encode = hsw_pte_encode;
 	else if (IS_VALLEYVIEW(dev_priv))
-		ggtt->base.pte_encode = byt_pte_encode;
+		ggtt->vm.pte_encode = byt_pte_encode;
 	else if (INTEL_GEN(dev_priv) >= 7)
-		ggtt->base.pte_encode = ivb_pte_encode;
+		ggtt->vm.pte_encode = ivb_pte_encode;
 	else
-		ggtt->base.pte_encode = snb_pte_encode;
+		ggtt->vm.pte_encode = snb_pte_encode;
 
 	return ggtt_probe_common(ggtt, size);
 }
@@ -3400,7 +3399,7 @@ static void i915_gmch_remove(struct i915_address_space *vm)
 
 static int i915_gmch_probe(struct i915_ggtt *ggtt)
 {
-	struct drm_i915_private *dev_priv = ggtt->base.i915;
+	struct drm_i915_private *dev_priv = ggtt->vm.i915;
 	phys_addr_t gmadr_base;
 	int ret;
 
@@ -3410,23 +3409,21 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 		return -EIO;
 	}
 
-	intel_gtt_get(&ggtt->base.total,
-		      &gmadr_base,
-		      &ggtt->mappable_end);
+	intel_gtt_get(&ggtt->vm.total, &gmadr_base, &ggtt->mappable_end);
 
 	ggtt->gmadr =
 		(struct resource) DEFINE_RES_MEM(gmadr_base,
 						 ggtt->mappable_end);
 
 	ggtt->do_idle_maps = needs_idle_maps(dev_priv);
-	ggtt->base.insert_page = i915_ggtt_insert_page;
-	ggtt->base.insert_entries = i915_ggtt_insert_entries;
-	ggtt->base.clear_range = i915_ggtt_clear_range;
-	ggtt->base.bind_vma = ggtt_bind_vma;
-	ggtt->base.unbind_vma = ggtt_unbind_vma;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.cleanup = i915_gmch_remove;
+	ggtt->vm.insert_page = i915_ggtt_insert_page;
+	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
+	ggtt->vm.clear_range = i915_ggtt_clear_range;
+	ggtt->vm.bind_vma = ggtt_bind_vma;
+	ggtt->vm.unbind_vma = ggtt_unbind_vma;
+	ggtt->vm.set_pages = ggtt_set_pages;
+	ggtt->vm.clear_pages = clear_pages;
+	ggtt->vm.cleanup = i915_gmch_remove;
 
 	ggtt->invalidate = gmch_ggtt_invalidate;
 
@@ -3445,8 +3442,8 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv)
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
-	ggtt->base.i915 = dev_priv;
-	ggtt->base.dma = &dev_priv->drm.pdev->dev;
+	ggtt->vm.i915 = dev_priv;
+	ggtt->vm.dma = &dev_priv->drm.pdev->dev;
 
 	if (INTEL_GEN(dev_priv) <= 5)
 		ret = i915_gmch_probe(ggtt);
@@ -3463,27 +3460,29 @@ int i915_ggtt_probe_hw(struct drm_i915_private *dev_priv)
 	 * restriction!
 	 */
 	if (USES_GUC(dev_priv)) {
-		ggtt->base.total = min_t(u64, ggtt->base.total, GUC_GGTT_TOP);
-		ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total);
+		ggtt->vm.total = min_t(u64, ggtt->vm.total, GUC_GGTT_TOP);
+		ggtt->mappable_end =
+			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
 	}
 
-	if ((ggtt->base.total - 1) >> 32) {
+	if ((ggtt->vm.total - 1) >> 32) {
 		DRM_ERROR("We never expected a Global GTT with more than 32bits"
 			  " of address space! Found %lldM!\n",
-			  ggtt->base.total >> 20);
-		ggtt->base.total = 1ULL << 32;
-		ggtt->mappable_end = min_t(u64, ggtt->mappable_end, ggtt->base.total);
+			  ggtt->vm.total >> 20);
+		ggtt->vm.total = 1ULL << 32;
+		ggtt->mappable_end =
+			min_t(u64, ggtt->mappable_end, ggtt->vm.total);
 	}
 
-	if (ggtt->mappable_end > ggtt->base.total) {
+	if (ggtt->mappable_end > ggtt->vm.total) {
 		DRM_ERROR("mappable aperture extends past end of GGTT,"
 			  " aperture=%pa, total=%llx\n",
-			  &ggtt->mappable_end, ggtt->base.total);
-		ggtt->mappable_end = ggtt->base.total;
+			  &ggtt->mappable_end, ggtt->vm.total);
+		ggtt->mappable_end = ggtt->vm.total;
 	}
 
 	/* GMADR is the PCI mmio aperture into the global GTT. */
-	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->base.total >> 20);
+	DRM_DEBUG_DRIVER("GGTT size = %lluM\n", ggtt->vm.total >> 20);
 	DRM_DEBUG_DRIVER("GMADR size = %lluM\n", (u64)ggtt->mappable_end >> 20);
 	DRM_DEBUG_DRIVER("DSM size = %lluM\n",
 			 (u64)resource_size(&intel_graphics_stolen_res) >> 20);
@@ -3510,9 +3509,9 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	 * and beyond the end of the GTT if we do not provide a guard.
 	 */
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	i915_address_space_init(&ggtt->base, dev_priv, "[global]");
+	i915_address_space_init(&ggtt->vm, dev_priv, "[global]");
 	if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv))
-		ggtt->base.mm.color_adjust = i915_gtt_color_adjust;
+		ggtt->vm.mm.color_adjust = i915_gtt_color_adjust;
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 	if (!io_mapping_init_wc(&dev_priv->ggtt.iomap,
@@ -3535,7 +3534,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	return 0;
 
 out_gtt_cleanup:
-	ggtt->base.cleanup(&ggtt->base);
+	ggtt->vm.cleanup(&ggtt->vm);
 	return ret;
 }
 
@@ -3574,13 +3573,13 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 	i915_check_and_clear_faults(dev_priv);
 
 	/* First fill our portion of the GTT with scratch pages */
-	ggtt->base.clear_range(&ggtt->base, 0, ggtt->base.total);
+	ggtt->vm.clear_range(&ggtt->vm, 0, ggtt->vm.total);
 
-	ggtt->base.closed = true; /* skip rewriting PTE on VMA unbind */
+	ggtt->vm.closed = true; /* skip rewriting PTE on VMA unbind */
 
 	/* clflush objects bound into the GGTT and rebind them. */
-	GEM_BUG_ON(!list_empty(&ggtt->base.active_list));
-	list_for_each_entry_safe(vma, vn, &ggtt->base.inactive_list, vm_link) {
+	GEM_BUG_ON(!list_empty(&ggtt->vm.active_list));
+	list_for_each_entry_safe(vma, vn, &ggtt->vm.inactive_list, vm_link) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
 		if (!(vma->flags & I915_VMA_GLOBAL_BIND))
@@ -3593,7 +3592,7 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 		WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
 	}
 
-	ggtt->base.closed = false;
+	ggtt->vm.closed = false;
 
 	if (INTEL_GEN(dev_priv) >= 8) {
 		struct intel_ppat *ppat = &dev_priv->ppat;
@@ -3616,7 +3615,7 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 			if (!ppgtt)
 				continue;
 
-			gen6_write_page_range(ppgtt, 0, ppgtt->base.total);
+			gen6_write_page_range(ppgtt, 0, ppgtt->vm.total);
 		}
 	}
 
@@ -3838,7 +3837,7 @@ int i915_gem_gtt_reserve(struct i915_address_space *vm,
 	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(!IS_ALIGNED(offset, I915_GTT_MIN_ALIGNMENT));
 	GEM_BUG_ON(range_overflows(offset, size, vm->total));
-	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base);
+	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
 	GEM_BUG_ON(drm_mm_node_allocated(node));
 
 	node->size = size;
@@ -3935,7 +3934,7 @@ int i915_gem_gtt_insert(struct i915_address_space *vm,
 	GEM_BUG_ON(start >= end);
 	GEM_BUG_ON(start > 0  && !IS_ALIGNED(start, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(end < U64_MAX && !IS_ALIGNED(end, I915_GTT_PAGE_SIZE));
-	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base);
+	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
 	GEM_BUG_ON(drm_mm_node_allocated(node));
 
 	if (unlikely(range_overflows(start, size, end)))
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index aec4f73574f4..197c2c06ecb7 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -65,7 +65,7 @@ typedef u64 gen8_pde_t;
 typedef u64 gen8_ppgtt_pdpe_t;
 typedef u64 gen8_ppgtt_pml4e_t;
 
-#define ggtt_total_entries(ggtt) ((ggtt)->base.total >> PAGE_SHIFT)
+#define ggtt_total_entries(ggtt) ((ggtt)->vm.total >> PAGE_SHIFT)
 
 /* gen6-hsw has bit 11-4 for physical addr bit 39-32 */
 #define GEN6_GTT_ADDR_ENCODE(addr)	((addr) | (((addr) >> 28) & 0xff0))
@@ -367,7 +367,7 @@ i915_vm_has_scratch_64K(struct i915_address_space *vm)
  * the spec.
  */
 struct i915_ggtt {
-	struct i915_address_space base;
+	struct i915_address_space vm;
 
 	struct io_mapping iomap;	/* Mapping to our CPU mappable region */
 	struct resource gmadr;          /* GMADR resource */
@@ -385,7 +385,7 @@ struct i915_ggtt {
 };
 
 struct i915_hw_ppgtt {
-	struct i915_address_space base;
+	struct i915_address_space vm;
 	struct kref ref;
 	struct drm_mm_node node;
 	unsigned long pd_dirty_rings;
@@ -543,7 +543,7 @@ static inline struct i915_ggtt *
 i915_vm_to_ggtt(struct i915_address_space *vm)
 {
 	GEM_BUG_ON(!i915_is_ggtt(vm));
-	return container_of(vm, struct i915_ggtt, base);
+	return container_of(vm, struct i915_ggtt, vm);
 }
 
 #define INTEL_MAX_PPAT_ENTRIES 8
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 1036e8686916..3210cedfa46c 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -194,7 +194,7 @@ int i915_gem_render_state_emit(struct i915_request *rq)
 	if (IS_ERR(so.obj))
 		return PTR_ERR(so.obj);
 
-	so.vma = i915_vma_instance(so.obj, &engine->i915->ggtt.base, NULL);
+	so.vma = i915_vma_instance(so.obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(so.vma)) {
 		err = PTR_ERR(so.vma);
 		goto err_obj;
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 5757fb7c4b5a..55e84e71f526 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -480,7 +480,7 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 
 	/* We also want to clear any cached iomaps as they wrap vmap */
 	list_for_each_entry_safe(vma, next,
-				 &i915->ggtt.base.inactive_list, vm_link) {
+				 &i915->ggtt.vm.inactive_list, vm_link) {
 		unsigned long count = vma->node.size >> PAGE_SHIFT;
 		if (vma->iomap && i915_vma_unbind(vma) == 0)
 			freed_pages += count;
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index ad949cc30928..79a347295e00 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -642,7 +642,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	if (ret)
 		goto err;
 
-	vma = i915_vma_instance(obj, &ggtt->base, NULL);
+	vma = i915_vma_instance(obj, &ggtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_pages;
@@ -653,7 +653,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	 * setting up the GTT space. The actual reservation will occur
 	 * later.
 	 */
-	ret = i915_gem_gtt_reserve(&ggtt->base, &vma->node,
+	ret = i915_gem_gtt_reserve(&ggtt->vm, &vma->node,
 				   size, gtt_offset, obj->cache_level,
 				   0);
 	if (ret) {
@@ -666,7 +666,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_i915_private *dev_priv
 	vma->pages = obj->mm.pages;
 	vma->flags |= I915_VMA_GLOBAL_BIND;
 	__i915_vma_set_map_and_fenceable(vma);
-	list_move_tail(&vma->vm_link, &ggtt->base.inactive_list);
+	list_move_tail(&vma->vm_link, &ggtt->vm.inactive_list);
 
 	spin_lock(&dev_priv->mm.obj_lock);
 	list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list);
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 6702776303bf..758234d20f4e 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -973,8 +973,7 @@ i915_error_object_create(struct drm_i915_private *i915,
 		void __iomem *s;
 		int ret;
 
-		ggtt->base.insert_page(&ggtt->base, dma, slot,
-				       I915_CACHE_NONE, 0);
+		ggtt->vm.insert_page(&ggtt->vm, dma, slot, I915_CACHE_NONE, 0);
 
 		s = io_mapping_map_atomic_wc(&ggtt->iomap, slot);
 		ret = compress_page(&compress, (void  __force *)s, dst);
@@ -993,7 +992,7 @@ unwind:
 
 out:
 	compress_fini(&compress, dst);
-	ggtt->base.clear_range(&ggtt->base, slot, PAGE_SIZE);
+	ggtt->vm.clear_range(&ggtt->vm, slot, PAGE_SIZE);
 	return dst;
 }
 
@@ -1466,7 +1465,7 @@ static void gem_record_rings(struct i915_gpu_state *error)
 			struct i915_gem_context *ctx = request->gem_context;
 			struct intel_ring *ring;
 
-			ee->vm = ctx->ppgtt ? &ctx->ppgtt->base : &ggtt->base;
+			ee->vm = ctx->ppgtt ? &ctx->ppgtt->vm : &ggtt->vm;
 
 			record_context(&ee->context, ctx);
 
@@ -1564,7 +1563,7 @@ static void capture_active_buffers(struct i915_gpu_state *error)
 
 static void capture_pinned_buffers(struct i915_gpu_state *error)
 {
-	struct i915_address_space *vm = &error->i915->ggtt.base;
+	struct i915_address_space *vm = &error->i915->ggtt.vm;
 	struct drm_i915_error_buffer *bo;
 	struct i915_vma *vma;
 	int count_inactive, count_active;
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 3d5716d86e27..1472f48ab2e8 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -956,7 +956,7 @@ DECLARE_EVENT_CLASS(i915_context,
 			__entry->dev = ctx->i915->drm.primary->index;
 			__entry->ctx = ctx;
 			__entry->hw_id = ctx->hw_id;
-			__entry->vm = ctx->ppgtt ? &ctx->ppgtt->base : NULL;
+			__entry->vm = ctx->ppgtt ? &ctx->ppgtt->vm : NULL;
 	),
 
 	TP_printk("dev=%u, ctx=%p, ctx_vm=%p, hw_id=%u",
@@ -997,7 +997,7 @@ TRACE_EVENT(switch_mm,
 			__entry->class = engine->uabi_class;
 			__entry->instance = engine->instance;
 			__entry->to = to;
-			__entry->vm = to->ppgtt? &to->ppgtt->base : NULL;
+			__entry->vm = to->ppgtt ? &to->ppgtt->vm : NULL;
 			__entry->dev = engine->i915->drm.primary->index;
 	),
 
diff --git a/drivers/gpu/drm/i915/i915_vgpu.c b/drivers/gpu/drm/i915/i915_vgpu.c
index 5fe9f3f39467..869cf4a3b6de 100644
--- a/drivers/gpu/drm/i915/i915_vgpu.c
+++ b/drivers/gpu/drm/i915/i915_vgpu.c
@@ -105,7 +105,7 @@ static void vgt_deballoon_space(struct i915_ggtt *ggtt,
 			 node->start + node->size,
 			 node->size / 1024);
 
-	ggtt->base.reserved -= node->size;
+	ggtt->vm.reserved -= node->size;
 	drm_mm_remove_node(node);
 }
 
@@ -141,11 +141,11 @@ static int vgt_balloon_space(struct i915_ggtt *ggtt,
 
 	DRM_INFO("balloon space: range [ 0x%lx - 0x%lx ] %lu KiB.\n",
 		 start, end, size / 1024);
-	ret = i915_gem_gtt_reserve(&ggtt->base, node,
+	ret = i915_gem_gtt_reserve(&ggtt->vm, node,
 				   size, start, I915_COLOR_UNEVICTABLE,
 				   0);
 	if (!ret)
-		ggtt->base.reserved += size;
+		ggtt->vm.reserved += size;
 
 	return ret;
 }
@@ -197,7 +197,7 @@ static int vgt_balloon_space(struct i915_ggtt *ggtt,
 int intel_vgt_balloon(struct drm_i915_private *dev_priv)
 {
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	unsigned long ggtt_end = ggtt->base.total;
+	unsigned long ggtt_end = ggtt->vm.total;
 
 	unsigned long mappable_base, mappable_size, mappable_end;
 	unsigned long unmappable_base, unmappable_size, unmappable_end;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 10bf654cd023..912f16ffe7ee 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -85,7 +85,7 @@ vma_create(struct drm_i915_gem_object *obj,
 	int i;
 
 	/* The aliasing_ppgtt should never be used directly! */
-	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->base);
+	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
 
 	vma = kmem_cache_zalloc(vm->i915->vmas, GFP_KERNEL);
 	if (vma == NULL)
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 13448ea76f57..2ec2e60dc670 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -515,7 +515,7 @@ int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
 		return PTR_ERR(obj);
 	}
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err_unref;
@@ -585,7 +585,7 @@ static int init_status_page(struct intel_engine_cs *engine)
 	if (ret)
 		goto err;
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err;
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index e28a996b9604..29fd95c1306b 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -570,7 +570,7 @@ struct i915_vma *intel_guc_allocate_vma(struct intel_guc *guc, u32 size)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL);
 	if (IS_ERR(vma))
 		goto err;
 
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 23e9f2023bc5..f3945258fe1b 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -536,7 +536,7 @@ static void guc_add_request(struct intel_guc *guc, struct i915_request *rq)
  */
 static void flush_ggtt_writes(struct i915_vma *vma)
 {
-	struct drm_i915_private *dev_priv = to_i915(vma->obj->base.dev);
+	struct drm_i915_private *dev_priv = vma->vm->i915;
 
 	if (i915_vma_is_map_and_fenceable(vma))
 		POSTING_READ_FW(GUC_STATUS);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index f6f09f808f74..0935a19aca96 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -431,7 +431,7 @@ static u64 execlists_update_context(struct i915_request *rq)
 	 * PML4 is allocated during ppgtt init, so this is not needed
 	 * in 48-bit mode.
 	 */
-	if (ppgtt && !i915_vm_is_48bit(&ppgtt->base))
+	if (ppgtt && !i915_vm_is_48bit(&ppgtt->vm))
 		execlists_update_context_pdps(ppgtt, reg_state);
 
 	return ce->lrc_desc;
@@ -1672,7 +1672,7 @@ static int lrc_setup_wa_ctx(struct intel_engine_cs *engine)
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	vma = i915_vma_instance(obj, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err;
@@ -2070,7 +2070,7 @@ static int gen8_emit_bb_start(struct i915_request *rq,
 	 * not needed in 48-bit.*/
 	if (rq->gem_context->ppgtt &&
 	    (intel_engine_flag(rq->engine) & rq->gem_context->ppgtt->pd_dirty_rings) &&
-	    !i915_vm_is_48bit(&rq->gem_context->ppgtt->base) &&
+	    !i915_vm_is_48bit(&rq->gem_context->ppgtt->vm) &&
 	    !intel_vgpu_active(rq->i915)) {
 		ret = intel_logical_ring_emit_pdps(rq);
 		if (ret)
@@ -2668,7 +2668,7 @@ static void execlists_init_reg_state(u32 *regs,
 	CTX_REG(regs, CTX_PDP0_UDW, GEN8_RING_PDP_UDW(engine, 0), 0);
 	CTX_REG(regs, CTX_PDP0_LDW, GEN8_RING_PDP_LDW(engine, 0), 0);
 
-	if (ppgtt && i915_vm_is_48bit(&ppgtt->base)) {
+	if (ppgtt && i915_vm_is_48bit(&ppgtt->vm)) {
 		/* 64b PPGTT (48bit canonical)
 		 * PDP0_DESCRIPTOR contains the base address to PML4 and
 		 * other PDP Descriptors are ignored.
@@ -2774,7 +2774,7 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 		goto error_deref_obj;
 	}
 
-	vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto error_deref_obj;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 3f0eb538df09..6496c1d00dbb 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1121,7 +1121,7 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 	/* mark ring buffers as read-only from GPU side by default */
 	obj->gt_ro = 1;
 
-	vma = i915_vma_instance(obj, &dev_priv->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL);
 	if (IS_ERR(vma))
 		goto err;
 
@@ -1300,7 +1300,7 @@ alloc_context_vma(struct intel_engine_cs *engine)
 		i915_gem_object_set_cache_level(obj, I915_CACHE_L3_LLC);
 	}
 
-	vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 91c72911be3c..7846ea4a99bc 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -338,7 +338,7 @@ fake_huge_pages_object(struct drm_i915_private *i915, u64 size, bool single)
 
 static int igt_check_page_sizes(struct i915_vma *vma)
 {
-	struct drm_i915_private *i915 = to_i915(vma->obj->base.dev);
+	struct drm_i915_private *i915 = vma->vm->i915;
 	unsigned int supported = INTEL_INFO(i915)->page_sizes;
 	struct drm_i915_gem_object *obj = vma->obj;
 	int err = 0;
@@ -379,7 +379,7 @@ static int igt_check_page_sizes(struct i915_vma *vma)
 static int igt_mock_exhaust_device_supported_pages(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
 	unsigned int saved_mask = INTEL_INFO(i915)->page_sizes;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
@@ -415,7 +415,7 @@ static int igt_mock_exhaust_device_supported_pages(void *arg)
 				goto out_put;
 			}
 
-			vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+			vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 			if (IS_ERR(vma)) {
 				err = PTR_ERR(vma);
 				goto out_put;
@@ -458,7 +458,7 @@ out_device:
 static int igt_mock_ppgtt_misaligned_dma(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
 	unsigned long supported = INTEL_INFO(i915)->page_sizes;
 	struct drm_i915_gem_object *obj;
 	int bit;
@@ -500,7 +500,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		/* Force the page size for this object */
 		obj->mm.page_sizes.sg = page_size;
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out_unpin;
@@ -591,7 +591,7 @@ static void close_object_list(struct list_head *objects,
 	list_for_each_entry_safe(obj, on, objects, st_link) {
 		struct i915_vma *vma;
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (!IS_ERR(vma))
 			i915_vma_close(vma);
 
@@ -604,8 +604,8 @@ static void close_object_list(struct list_head *objects,
 static int igt_mock_ppgtt_huge_fill(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
-	unsigned long max_pages = ppgtt->base.total >> PAGE_SHIFT;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
+	unsigned long max_pages = ppgtt->vm.total >> PAGE_SHIFT;
 	unsigned long page_num;
 	bool single = false;
 	LIST_HEAD(objects);
@@ -641,7 +641,7 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			break;
@@ -725,7 +725,7 @@ static int igt_mock_ppgtt_huge_fill(void *arg)
 static int igt_mock_ppgtt_64K(void *arg)
 {
 	struct i915_hw_ppgtt *ppgtt = arg;
-	struct drm_i915_private *i915 = ppgtt->base.i915;
+	struct drm_i915_private *i915 = ppgtt->vm.i915;
 	struct drm_i915_gem_object *obj;
 	const struct object_info {
 		unsigned int size;
@@ -819,7 +819,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 			 */
 			obj->mm.page_sizes.sg &= ~I915_GTT_PAGE_SIZE_2M;
 
-			vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+			vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 			if (IS_ERR(vma)) {
 				err = PTR_ERR(vma);
 				goto out_object_unpin;
@@ -887,8 +887,8 @@ out_object_put:
 static struct i915_vma *
 gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val)
 {
-	struct drm_i915_private *i915 = to_i915(vma->obj->base.dev);
-	const int gen = INTEL_GEN(vma->vm->i915);
+	struct drm_i915_private *i915 = vma->vm->i915;
+	const int gen = INTEL_GEN(i915);
 	unsigned int count = vma->size >> PAGE_SHIFT;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *batch;
@@ -1047,7 +1047,8 @@ static int __igt_write_huge(struct i915_gem_context *ctx,
 			    u32 dword, u32 val)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	unsigned int flags = PIN_USER | PIN_OFFSET_FIXED;
 	struct i915_vma *vma;
 	int err;
@@ -1100,7 +1101,8 @@ static int igt_write_huge(struct i915_gem_context *ctx,
 			  struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	static struct intel_engine_cs *engines[I915_NUM_ENGINES];
 	struct intel_engine_cs *engine;
 	I915_RND_STATE(prng);
@@ -1439,7 +1441,7 @@ static int igt_ppgtt_pin_update(void *arg)
 		if (IS_ERR(obj))
 			return PTR_ERR(obj);
 
-		vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+		vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out_put;
@@ -1493,7 +1495,7 @@ static int igt_ppgtt_pin_update(void *arg)
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	vma = i915_vma_instance(obj, &ppgtt->base, NULL);
+	vma = i915_vma_instance(obj, &ppgtt->vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto out_put;
@@ -1531,7 +1533,8 @@ static int igt_tmpfs_fallback(void *arg)
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
 	struct vfsmount *gemfs = i915->mm.gemfs;
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	u32 *vaddr;
@@ -1587,7 +1590,8 @@ static int igt_shrink_thp(void *arg)
 {
 	struct i915_gem_context *ctx = arg;
 	struct drm_i915_private *i915 = ctx->i915;
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 	unsigned int flags = PIN_USER;
@@ -1696,14 +1700,14 @@ int i915_gem_huge_page_mock_selftests(void)
 		goto out_unlock;
 	}
 
-	if (!i915_vm_is_48bit(&ppgtt->base)) {
+	if (!i915_vm_is_48bit(&ppgtt->vm)) {
 		pr_err("failed to create 48b PPGTT\n");
 		err = -EINVAL;
 		goto out_close;
 	}
 
 	/* If we were ever hit this then it's time to mock the 64K scratch */
-	if (!i915_vm_has_scratch_64K(&ppgtt->base)) {
+	if (!i915_vm_has_scratch_64K(&ppgtt->vm)) {
 		pr_err("PPGTT missing 64K scratch page\n");
 		err = -EINVAL;
 		goto out_close;
@@ -1712,7 +1716,7 @@ int i915_gem_huge_page_mock_selftests(void)
 	err = i915_subtests(tests, ppgtt);
 
 out_close:
-	i915_ppgtt_close(&ppgtt->base);
+	i915_ppgtt_close(&ppgtt->vm);
 	i915_ppgtt_put(ppgtt);
 
 out_unlock:
@@ -1758,7 +1762,7 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 	}
 
 	if (ctx->ppgtt)
-		ctx->ppgtt->base.scrub_64K = true;
+		ctx->ppgtt->vm.scrub_64K = true;
 
 	err = i915_subtests(tests, ctx);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index b39392a00a6f..708e8d721448 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -115,7 +115,7 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct i915_address_space *vm =
-		ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct i915_request *rq;
 	struct i915_vma *vma;
 	struct i915_vma *batch;
@@ -290,7 +290,7 @@ create_test_object(struct i915_gem_context *ctx,
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm =
-		ctx->ppgtt ? &ctx->ppgtt->base : &ctx->i915->ggtt.base;
+		ctx->ppgtt ? &ctx->ppgtt->vm : &ctx->i915->ggtt.vm;
 	u64 size;
 	int err;
 
@@ -557,7 +557,7 @@ static int fake_aliasing_ppgtt_enable(struct drm_i915_private *i915)
 	list_for_each_entry(obj, &i915->mm.bound_list, mm.link) {
 		struct i915_vma *vma;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index ab9d7bee0aae..2dc72a984d45 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -35,7 +35,7 @@ static int populate_ggtt(struct drm_i915_private *i915)
 	u64 size;
 
 	for (size = 0;
-	     size + I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     size + I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     size += I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -57,7 +57,7 @@ static int populate_ggtt(struct drm_i915_private *i915)
 		return -EINVAL;
 	}
 
-	if (list_empty(&i915->ggtt.base.inactive_list)) {
+	if (list_empty(&i915->ggtt.vm.inactive_list)) {
 		pr_err("No objects on the GGTT inactive list!\n");
 		return -EINVAL;
 	}
@@ -69,7 +69,7 @@ static void unpin_ggtt(struct drm_i915_private *i915)
 {
 	struct i915_vma *vma;
 
-	list_for_each_entry(vma, &i915->ggtt.base.inactive_list, vm_link)
+	list_for_each_entry(vma, &i915->ggtt.vm.inactive_list, vm_link)
 		i915_vma_unpin(vma);
 }
 
@@ -103,7 +103,7 @@ static int igt_evict_something(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
-	err = i915_gem_evict_something(&ggtt->base,
+	err = i915_gem_evict_something(&ggtt->vm,
 				       I915_GTT_PAGE_SIZE, 0, 0,
 				       0, U64_MAX,
 				       0);
@@ -116,7 +116,7 @@ static int igt_evict_something(void *arg)
 	unpin_ggtt(i915);
 
 	/* Everything is unpinned, we should be able to evict something */
-	err = i915_gem_evict_something(&ggtt->base,
+	err = i915_gem_evict_something(&ggtt->vm,
 				       I915_GTT_PAGE_SIZE, 0, 0,
 				       0, U64_MAX,
 				       0);
@@ -181,7 +181,7 @@ static int igt_evict_for_vma(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (err != -ENOSPC) {
 		pr_err("i915_gem_evict_for_node on a full GGTT returned err=%d\n",
 		       err);
@@ -191,7 +191,7 @@ static int igt_evict_for_vma(void *arg)
 	unpin_ggtt(i915);
 
 	/* Everything is unpinned, we should be able to evict the node */
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (err) {
 		pr_err("i915_gem_evict_for_node returned err=%d\n",
 		       err);
@@ -229,7 +229,7 @@ static int igt_evict_for_cache_color(void *arg)
 	 * i915_gtt_color_adjust throughout our driver, so using a mock color
 	 * adjust will work just fine for our purposes.
 	 */
-	ggtt->base.mm.color_adjust = mock_color_adjust;
+	ggtt->vm.mm.color_adjust = mock_color_adjust;
 
 	obj = i915_gem_object_create_internal(i915, I915_GTT_PAGE_SIZE);
 	if (IS_ERR(obj)) {
@@ -265,7 +265,7 @@ static int igt_evict_for_cache_color(void *arg)
 	i915_vma_unpin(vma);
 
 	/* Remove just the second vma */
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (err) {
 		pr_err("[0]i915_gem_evict_for_node returned err=%d\n", err);
 		goto cleanup;
@@ -276,7 +276,7 @@ static int igt_evict_for_cache_color(void *arg)
 	 */
 	target.color = I915_CACHE_L3_LLC;
 
-	err = i915_gem_evict_for_node(&ggtt->base, &target, 0);
+	err = i915_gem_evict_for_node(&ggtt->vm, &target, 0);
 	if (!err) {
 		pr_err("[1]i915_gem_evict_for_node returned err=%d\n", err);
 		err = -EINVAL;
@@ -288,7 +288,7 @@ static int igt_evict_for_cache_color(void *arg)
 cleanup:
 	unpin_ggtt(i915);
 	cleanup_objects(i915);
-	ggtt->base.mm.color_adjust = NULL;
+	ggtt->vm.mm.color_adjust = NULL;
 	return err;
 }
 
@@ -305,7 +305,7 @@ static int igt_evict_vm(void *arg)
 		goto cleanup;
 
 	/* Everything is pinned, nothing should happen */
-	err = i915_gem_evict_vm(&ggtt->base);
+	err = i915_gem_evict_vm(&ggtt->vm);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
 		       err);
@@ -314,7 +314,7 @@ static int igt_evict_vm(void *arg)
 
 	unpin_ggtt(i915);
 
-	err = i915_gem_evict_vm(&ggtt->base);
+	err = i915_gem_evict_vm(&ggtt->vm);
 	if (err) {
 		pr_err("i915_gem_evict_vm on a full GGTT returned err=%d]\n",
 		       err);
@@ -359,9 +359,9 @@ static int igt_evict_contexts(void *arg)
 
 	/* Reserve a block so that we know we have enough to fit a few rq */
 	memset(&hole, 0, sizeof(hole));
-	err = i915_gem_gtt_insert(&i915->ggtt.base, &hole,
+	err = i915_gem_gtt_insert(&i915->ggtt.vm, &hole,
 				  PRETEND_GGTT_SIZE, 0, I915_COLOR_UNEVICTABLE,
-				  0, i915->ggtt.base.total,
+				  0, i915->ggtt.vm.total,
 				  PIN_NOEVICT);
 	if (err)
 		goto out_locked;
@@ -377,9 +377,9 @@ static int igt_evict_contexts(void *arg)
 			goto out_locked;
 		}
 
-		if (i915_gem_gtt_insert(&i915->ggtt.base, &r->node,
+		if (i915_gem_gtt_insert(&i915->ggtt.vm, &r->node,
 					1ul << 20, 0, I915_COLOR_UNEVICTABLE,
-					0, i915->ggtt.base.total,
+					0, i915->ggtt.vm.total,
 					PIN_NOEVICT)) {
 			kfree(r);
 			break;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index f7dc926f4ef1..58ab5e84ceb7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -151,14 +151,14 @@ static int igt_ppgtt_alloc(void *arg)
 	if (err)
 		goto err_ppgtt;
 
-	if (!ppgtt->base.allocate_va_range)
+	if (!ppgtt->vm.allocate_va_range)
 		goto err_ppgtt_cleanup;
 
 	/* Check we can allocate the entire range */
 	for (size = 4096;
-	     size <= ppgtt->base.total;
+	     size <= ppgtt->vm.total;
 	     size <<= 2) {
-		err = ppgtt->base.allocate_va_range(&ppgtt->base, 0, size);
+		err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, size);
 		if (err) {
 			if (err == -ENOMEM) {
 				pr_info("[1] Ran out of memory for va_range [0 + %llx] [bit %d]\n",
@@ -168,15 +168,15 @@ static int igt_ppgtt_alloc(void *arg)
 			goto err_ppgtt_cleanup;
 		}
 
-		ppgtt->base.clear_range(&ppgtt->base, 0, size);
+		ppgtt->vm.clear_range(&ppgtt->vm, 0, size);
 	}
 
 	/* Check we can incrementally allocate the entire range */
 	for (last = 0, size = 4096;
-	     size <= ppgtt->base.total;
+	     size <= ppgtt->vm.total;
 	     last = size, size <<= 2) {
-		err = ppgtt->base.allocate_va_range(&ppgtt->base,
-						    last, size - last);
+		err = ppgtt->vm.allocate_va_range(&ppgtt->vm,
+						  last, size - last);
 		if (err) {
 			if (err == -ENOMEM) {
 				pr_info("[2] Ran out of memory for va_range [%llx + %llx] [bit %d]\n",
@@ -188,7 +188,7 @@ static int igt_ppgtt_alloc(void *arg)
 	}
 
 err_ppgtt_cleanup:
-	ppgtt->base.cleanup(&ppgtt->base);
+	ppgtt->vm.cleanup(&ppgtt->vm);
 err_ppgtt:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 	kfree(ppgtt);
@@ -987,12 +987,12 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
 	}
-	GEM_BUG_ON(offset_in_page(ppgtt->base.total));
-	GEM_BUG_ON(ppgtt->base.closed);
+	GEM_BUG_ON(offset_in_page(ppgtt->vm.total));
+	GEM_BUG_ON(ppgtt->vm.closed);
 
-	err = func(dev_priv, &ppgtt->base, 0, ppgtt->base.total, end_time);
+	err = func(dev_priv, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
 
-	i915_ppgtt_close(&ppgtt->base);
+	i915_ppgtt_close(&ppgtt->vm);
 	i915_ppgtt_put(ppgtt);
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
@@ -1061,18 +1061,18 @@ static int exercise_ggtt(struct drm_i915_private *i915,
 
 	mutex_lock(&i915->drm.struct_mutex);
 restart:
-	list_sort(NULL, &ggtt->base.mm.hole_stack, sort_holes);
-	drm_mm_for_each_hole(node, &ggtt->base.mm, hole_start, hole_end) {
+	list_sort(NULL, &ggtt->vm.mm.hole_stack, sort_holes);
+	drm_mm_for_each_hole(node, &ggtt->vm.mm, hole_start, hole_end) {
 		if (hole_start < last)
 			continue;
 
-		if (ggtt->base.mm.color_adjust)
-			ggtt->base.mm.color_adjust(node, 0,
-						   &hole_start, &hole_end);
+		if (ggtt->vm.mm.color_adjust)
+			ggtt->vm.mm.color_adjust(node, 0,
+						 &hole_start, &hole_end);
 		if (hole_start >= hole_end)
 			continue;
 
-		err = func(i915, &ggtt->base, hole_start, hole_end, end_time);
+		err = func(i915, &ggtt->vm, hole_start, hole_end, end_time);
 		if (err)
 			break;
 
@@ -1134,7 +1134,7 @@ static int igt_ggtt_page(void *arg)
 		goto out_free;
 
 	memset(&tmp, 0, sizeof(tmp));
-	err = drm_mm_insert_node_in_range(&ggtt->base.mm, &tmp,
+	err = drm_mm_insert_node_in_range(&ggtt->vm.mm, &tmp,
 					  count * PAGE_SIZE, 0,
 					  I915_COLOR_UNEVICTABLE,
 					  0, ggtt->mappable_end,
@@ -1147,9 +1147,9 @@ static int igt_ggtt_page(void *arg)
 	for (n = 0; n < count; n++) {
 		u64 offset = tmp.start + n * PAGE_SIZE;
 
-		ggtt->base.insert_page(&ggtt->base,
-				       i915_gem_object_get_dma_address(obj, 0),
-				       offset, I915_CACHE_NONE, 0);
+		ggtt->vm.insert_page(&ggtt->vm,
+				     i915_gem_object_get_dma_address(obj, 0),
+				     offset, I915_CACHE_NONE, 0);
 	}
 
 	order = i915_random_order(count, &prng);
@@ -1188,7 +1188,7 @@ static int igt_ggtt_page(void *arg)
 
 	kfree(order);
 out_remove:
-	ggtt->base.clear_range(&ggtt->base, tmp.start, tmp.size);
+	ggtt->vm.clear_range(&ggtt->vm, tmp.start, tmp.size);
 	intel_runtime_pm_put(i915);
 	drm_mm_remove_node(&tmp);
 out_unpin:
@@ -1229,7 +1229,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 	ppgtt = ctx->ppgtt;
 	GEM_BUG_ON(!ppgtt);
 
-	err = func(i915, &ppgtt->base, 0, ppgtt->base.total, end_time);
+	err = func(i915, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
 
 	mock_context_close(ctx);
 	return err;
@@ -1270,7 +1270,7 @@ static int igt_gtt_reserve(void *arg)
 
 	/* Start by filling the GGTT */
 	for (total = 0;
-	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += 2*I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1288,20 +1288,20 @@ static int igt_gtt_reserve(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node,
 					   obj->base.size,
 					   total,
 					   obj->cache_level,
 					   0);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 1) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1319,7 +1319,7 @@ static int igt_gtt_reserve(void *arg)
 
 	/* Now we start forcing evictions */
 	for (total = I915_GTT_PAGE_SIZE;
-	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += 2*I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1337,20 +1337,20 @@ static int igt_gtt_reserve(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node,
 					   obj->base.size,
 					   total,
 					   obj->cache_level,
 					   0);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 2) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1371,7 +1371,7 @@ static int igt_gtt_reserve(void *arg)
 		struct i915_vma *vma;
 		u64 offset;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
@@ -1383,18 +1383,18 @@ static int igt_gtt_reserve(void *arg)
 			goto out;
 		}
 
-		offset = random_offset(0, i915->ggtt.base.total,
+		offset = random_offset(0, i915->ggtt.vm.total,
 				       2*I915_GTT_PAGE_SIZE,
 				       I915_GTT_MIN_ALIGNMENT);
 
-		err = i915_gem_gtt_reserve(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_reserve(&i915->ggtt.vm, &vma->node,
 					   obj->base.size,
 					   offset,
 					   obj->cache_level,
 					   0);
 		if (err) {
 			pr_err("i915_gem_gtt_reserve (pass 3) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1429,8 +1429,8 @@ static int igt_gtt_insert(void *arg)
 		u64 start, end;
 	} invalid_insert[] = {
 		{
-			i915->ggtt.base.total + I915_GTT_PAGE_SIZE, 0,
-			0, i915->ggtt.base.total,
+			i915->ggtt.vm.total + I915_GTT_PAGE_SIZE, 0,
+			0, i915->ggtt.vm.total,
 		},
 		{
 			2*I915_GTT_PAGE_SIZE, 0,
@@ -1460,7 +1460,7 @@ static int igt_gtt_insert(void *arg)
 
 	/* Check a couple of obviously invalid requests */
 	for (ii = invalid_insert; ii->size; ii++) {
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &tmp,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &tmp,
 					  ii->size, ii->alignment,
 					  I915_COLOR_UNEVICTABLE,
 					  ii->start, ii->end,
@@ -1475,7 +1475,7 @@ static int igt_gtt_insert(void *arg)
 
 	/* Start by filling the GGTT */
 	for (total = 0;
-	     total + I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1493,15 +1493,15 @@ static int igt_gtt_insert(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
-					  0, i915->ggtt.base.total,
+					  0, i915->ggtt.vm.total,
 					  0);
 		if (err == -ENOSPC) {
 			/* maxed out the GGTT space */
@@ -1510,7 +1510,7 @@ static int igt_gtt_insert(void *arg)
 		}
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 1) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1522,7 +1522,7 @@ static int igt_gtt_insert(void *arg)
 	list_for_each_entry(obj, &objects, st_link) {
 		struct i915_vma *vma;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
@@ -1542,7 +1542,7 @@ static int igt_gtt_insert(void *arg)
 		struct i915_vma *vma;
 		u64 offset;
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
@@ -1557,13 +1557,13 @@ static int igt_gtt_insert(void *arg)
 			goto out;
 		}
 
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
-					  0, i915->ggtt.base.total,
+					  0, i915->ggtt.vm.total,
 					  0);
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 2) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1579,7 +1579,7 @@ static int igt_gtt_insert(void *arg)
 
 	/* And then force evictions */
 	for (total = 0;
-	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.base.total;
+	     total + 2*I915_GTT_PAGE_SIZE <= i915->ggtt.vm.total;
 	     total += 2*I915_GTT_PAGE_SIZE) {
 		struct i915_vma *vma;
 
@@ -1597,19 +1597,19 @@ static int igt_gtt_insert(void *arg)
 
 		list_add(&obj->st_link, &objects);
 
-		vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+		vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 		if (IS_ERR(vma)) {
 			err = PTR_ERR(vma);
 			goto out;
 		}
 
-		err = i915_gem_gtt_insert(&i915->ggtt.base, &vma->node,
+		err = i915_gem_gtt_insert(&i915->ggtt.vm, &vma->node,
 					  obj->base.size, 0, obj->cache_level,
-					  0, i915->ggtt.base.total,
+					  0, i915->ggtt.vm.total,
 					  0);
 		if (err) {
 			pr_err("i915_gem_gtt_insert (pass 3) failed at %llu/%llu with err=%d\n",
-			       total, i915->ggtt.base.total, err);
+			       total, i915->ggtt.vm.total, err);
 			goto out;
 		}
 		track_vma_bind(vma);
@@ -1669,7 +1669,7 @@ int i915_gem_gtt_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_ggtt_page),
 	};
 
-	GEM_BUG_ON(offset_in_page(i915->ggtt.base.total));
+	GEM_BUG_ON(offset_in_page(i915->ggtt.vm.total));
 
 	return i915_subtests(tests, i915);
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index fbdb2419d418..2b2dde94526f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -113,7 +113,7 @@ static int igt_gem_huge(void *arg)
 
 	obj = huge_gem_object(i915,
 			      nreal * PAGE_SIZE,
-			      i915->ggtt.base.total + PAGE_SIZE);
+			      i915->ggtt.vm.total + PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -311,7 +311,7 @@ static int igt_partial_tiling(void *arg)
 
 	obj = huge_gem_object(i915,
 			      nreal << PAGE_SHIFT,
-			      (1 + next_prime_number(i915->ggtt.base.total >> PAGE_SHIFT)) << PAGE_SHIFT);
+			      (1 + next_prime_number(i915->ggtt.vm.total >> PAGE_SHIFT)) << PAGE_SHIFT);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
@@ -440,7 +440,7 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 	struct i915_vma *vma;
 	int err;
 
-	vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma))
 		return PTR_ERR(vma);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 94bc2e1898a4..a3a89aadeccb 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -430,7 +430,7 @@ static struct i915_vma *empty_batch(struct drm_i915_private *i915)
 	if (err)
 		goto err;
 
-	vma = i915_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err;
@@ -555,7 +555,8 @@ out_unlock:
 static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 {
 	struct i915_gem_context *ctx = i915->kernel_context;
-	struct i915_address_space *vm = ctx->ppgtt ? &ctx->ppgtt->base : &i915->ggtt.base;
+	struct i915_address_space *vm =
+		ctx->ppgtt ? &ctx->ppgtt->vm : &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	const int gen = INTEL_GEN(i915);
 	struct i915_vma *vma;
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index e90f97236e50..8400a8cc5cf2 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -35,7 +35,7 @@ static bool assert_vma(struct i915_vma *vma,
 {
 	bool ok = true;
 
-	if (vma->vm != &ctx->ppgtt->base) {
+	if (vma->vm != &ctx->ppgtt->vm) {
 		pr_err("VMA created with wrong VM\n");
 		ok = false;
 	}
@@ -110,8 +110,7 @@ static int create_vmas(struct drm_i915_private *i915,
 	list_for_each_entry(obj, objects, st_link) {
 		for (pinned = 0; pinned <= 1; pinned++) {
 			list_for_each_entry(ctx, contexts, link) {
-				struct i915_address_space *vm =
-					&ctx->ppgtt->base;
+				struct i915_address_space *vm = &ctx->ppgtt->vm;
 				struct i915_vma *vma;
 				int err;
 
@@ -259,12 +258,12 @@ static int igt_vma_pin1(void *arg)
 		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | 8192),
 		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
 		VALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
-		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.base.total - 4096)),
+		VALID(0, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.vm.total - 4096)),
 
 		VALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | (i915->ggtt.mappable_end - 4096)),
 		INVALID(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | i915->ggtt.mappable_end),
-		VALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.base.total - 4096)),
-		INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | i915->ggtt.base.total),
+		VALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.vm.total - 4096)),
+		INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | i915->ggtt.vm.total),
 		INVALID(0, PIN_GLOBAL | PIN_OFFSET_FIXED | round_down(U64_MAX, PAGE_SIZE)),
 
 		VALID(4096, PIN_GLOBAL),
@@ -272,12 +271,12 @@ static int igt_vma_pin1(void *arg)
 		VALID(i915->ggtt.mappable_end - 4096, PIN_GLOBAL | PIN_MAPPABLE),
 		VALID(i915->ggtt.mappable_end, PIN_GLOBAL | PIN_MAPPABLE),
 		NOSPACE(i915->ggtt.mappable_end + 4096, PIN_GLOBAL | PIN_MAPPABLE),
-		VALID(i915->ggtt.base.total - 4096, PIN_GLOBAL),
-		VALID(i915->ggtt.base.total, PIN_GLOBAL),
-		NOSPACE(i915->ggtt.base.total + 4096, PIN_GLOBAL),
+		VALID(i915->ggtt.vm.total - 4096, PIN_GLOBAL),
+		VALID(i915->ggtt.vm.total, PIN_GLOBAL),
+		NOSPACE(i915->ggtt.vm.total + 4096, PIN_GLOBAL),
 		NOSPACE(round_down(U64_MAX, PAGE_SIZE), PIN_GLOBAL),
 		INVALID(8192, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_FIXED | (i915->ggtt.mappable_end - 4096)),
-		INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.base.total - 4096)),
+		INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (i915->ggtt.vm.total - 4096)),
 		INVALID(8192, PIN_GLOBAL | PIN_OFFSET_FIXED | (round_down(U64_MAX, PAGE_SIZE) - 4096)),
 
 		VALID(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
@@ -289,9 +288,9 @@ static int igt_vma_pin1(void *arg)
 		 * variable start, end and size.
 		 */
 		NOSPACE(0, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | i915->ggtt.mappable_end),
-		NOSPACE(0, PIN_GLOBAL | PIN_OFFSET_BIAS | i915->ggtt.base.total),
+		NOSPACE(0, PIN_GLOBAL | PIN_OFFSET_BIAS | i915->ggtt.vm.total),
 		NOSPACE(8192, PIN_GLOBAL | PIN_MAPPABLE | PIN_OFFSET_BIAS | (i915->ggtt.mappable_end - 4096)),
-		NOSPACE(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.base.total - 4096)),
+		NOSPACE(8192, PIN_GLOBAL | PIN_OFFSET_BIAS | (i915->ggtt.vm.total - 4096)),
 #endif
 		{ },
 #undef NOSPACE
@@ -307,13 +306,13 @@ static int igt_vma_pin1(void *arg)
 	 * focusing on error handling of boundary conditions.
 	 */
 
-	GEM_BUG_ON(!drm_mm_clean(&i915->ggtt.base.mm));
+	GEM_BUG_ON(!drm_mm_clean(&i915->ggtt.vm.mm));
 
 	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 	if (IS_ERR(obj))
 		return PTR_ERR(obj);
 
-	vma = checked_vma_instance(obj, &i915->ggtt.base, NULL);
+	vma = checked_vma_instance(obj, &i915->ggtt.vm, NULL);
 	if (IS_ERR(vma))
 		goto out;
 
@@ -405,7 +404,7 @@ static unsigned int rotated_size(const struct intel_rotation_plane_info *a,
 static int igt_vma_rotate(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct i915_address_space *vm = &i915->ggtt.base;
+	struct i915_address_space *vm = &i915->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	const struct intel_rotation_plane_info planes[] = {
 		{ .width = 1, .height = 1, .stride = 1 },
@@ -604,7 +603,7 @@ static bool assert_pin(struct i915_vma *vma,
 static int igt_vma_partial(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
-	struct i915_address_space *vm = &i915->ggtt.base;
+	struct i915_address_space *vm = &i915->ggtt.vm;
 	const unsigned int npages = 1021; /* prime! */
 	struct drm_i915_gem_object *obj;
 	const struct phase {
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 2091e3a6a5be..390a157b37c3 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -107,8 +107,8 @@ static int emit_recurse_batch(struct hang *h,
 	struct drm_i915_private *i915 = h->i915;
 	struct i915_address_space *vm =
 		rq->gem_context->ppgtt ?
-		&rq->gem_context->ppgtt->base :
-		&i915->ggtt.base;
+		&rq->gem_context->ppgtt->vm :
+		&i915->ggtt.vm;
 	struct i915_vma *hws, *vma;
 	unsigned int flags;
 	u32 *batch;
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index 68cb9126b3e1..0b6da08c8cae 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -83,7 +83,7 @@ static int emit_recurse_batch(struct spinner *spin,
 			      struct i915_request *rq,
 			      u32 arbitration_command)
 {
-	struct i915_address_space *vm = &rq->gem_context->ppgtt->base;
+	struct i915_address_space *vm = &rq->gem_context->ppgtt->vm;
 	struct i915_vma *hws, *vma;
 	u32 *batch;
 	int err;
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index 17444a3abbb9..f1cfb0fb6bea 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -33,7 +33,7 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	memset(cs, 0xc5, PAGE_SIZE);
 	i915_gem_object_unpin_map(result);
 
-	vma = i915_vma_instance(result, &engine->i915->ggtt.base, NULL);
+	vma = i915_vma_instance(result, &engine->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
 		err = PTR_ERR(vma);
 		goto err_obj;
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 36c112088940..556c546f2715 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -66,25 +66,25 @@ mock_ppgtt(struct drm_i915_private *i915,
 		return NULL;
 
 	kref_init(&ppgtt->ref);
-	ppgtt->base.i915 = i915;
-	ppgtt->base.total = round_down(U64_MAX, PAGE_SIZE);
-	ppgtt->base.file = ERR_PTR(-ENODEV);
-
-	INIT_LIST_HEAD(&ppgtt->base.active_list);
-	INIT_LIST_HEAD(&ppgtt->base.inactive_list);
-	INIT_LIST_HEAD(&ppgtt->base.unbound_list);
-
-	INIT_LIST_HEAD(&ppgtt->base.global_link);
-	drm_mm_init(&ppgtt->base.mm, 0, ppgtt->base.total);
-
-	ppgtt->base.clear_range = nop_clear_range;
-	ppgtt->base.insert_page = mock_insert_page;
-	ppgtt->base.insert_entries = mock_insert_entries;
-	ppgtt->base.bind_vma = mock_bind_ppgtt;
-	ppgtt->base.unbind_vma = mock_unbind_ppgtt;
-	ppgtt->base.set_pages = ppgtt_set_pages;
-	ppgtt->base.clear_pages = clear_pages;
-	ppgtt->base.cleanup = mock_cleanup;
+	ppgtt->vm.i915 = i915;
+	ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE);
+	ppgtt->vm.file = ERR_PTR(-ENODEV);
+
+	INIT_LIST_HEAD(&ppgtt->vm.active_list);
+	INIT_LIST_HEAD(&ppgtt->vm.inactive_list);
+	INIT_LIST_HEAD(&ppgtt->vm.unbound_list);
+
+	INIT_LIST_HEAD(&ppgtt->vm.global_link);
+	drm_mm_init(&ppgtt->vm.mm, 0, ppgtt->vm.total);
+
+	ppgtt->vm.clear_range = nop_clear_range;
+	ppgtt->vm.insert_page = mock_insert_page;
+	ppgtt->vm.insert_entries = mock_insert_entries;
+	ppgtt->vm.bind_vma = mock_bind_ppgtt;
+	ppgtt->vm.unbind_vma = mock_unbind_ppgtt;
+	ppgtt->vm.set_pages = ppgtt_set_pages;
+	ppgtt->vm.clear_pages = clear_pages;
+	ppgtt->vm.cleanup = mock_cleanup;
 
 	return ppgtt;
 }
@@ -107,27 +107,27 @@ void mock_init_ggtt(struct drm_i915_private *i915)
 
 	INIT_LIST_HEAD(&i915->vm_list);
 
-	ggtt->base.i915 = i915;
+	ggtt->vm.i915 = i915;
 
 	ggtt->gmadr = (struct resource) DEFINE_RES_MEM(0, 2048 * PAGE_SIZE);
 	ggtt->mappable_end = resource_size(&ggtt->gmadr);
-	ggtt->base.total = 4096 * PAGE_SIZE;
-
-	ggtt->base.clear_range = nop_clear_range;
-	ggtt->base.insert_page = mock_insert_page;
-	ggtt->base.insert_entries = mock_insert_entries;
-	ggtt->base.bind_vma = mock_bind_ggtt;
-	ggtt->base.unbind_vma = mock_unbind_ggtt;
-	ggtt->base.set_pages = ggtt_set_pages;
-	ggtt->base.clear_pages = clear_pages;
-	ggtt->base.cleanup = mock_cleanup;
-
-	i915_address_space_init(&ggtt->base, i915, "global");
+	ggtt->vm.total = 4096 * PAGE_SIZE;
+
+	ggtt->vm.clear_range = nop_clear_range;
+	ggtt->vm.insert_page = mock_insert_page;
+	ggtt->vm.insert_entries = mock_insert_entries;
+	ggtt->vm.bind_vma = mock_bind_ggtt;
+	ggtt->vm.unbind_vma = mock_unbind_ggtt;
+	ggtt->vm.set_pages = ggtt_set_pages;
+	ggtt->vm.clear_pages = clear_pages;
+	ggtt->vm.cleanup = mock_cleanup;
+
+	i915_address_space_init(&ggtt->vm, i915, "global");
 }
 
 void mock_fini_ggtt(struct drm_i915_private *i915)
 {
 	struct i915_ggtt *ggtt = &i915->ggtt;
 
-	i915_address_space_fini(&ggtt->base);
+	i915_address_space_fini(&ggtt->vm);
 }
-- 
cgit v1.2.3


From cf68f0c3a07b092bca92e7b4f1b3893ab454bd38 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 6 Jun 2018 15:41:53 +0100
Subject: drm/i915: Mark i915.inject_load_failure as being hit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When we reach the magic value and do inject a fault into our module load,
mark the module option as being hit. Since we fail from inside pci
probe, the module load isn't actually aborted and the module (and
parameters) are left lingering. igt can then inspect the parameter on its
synchronous completion of modprobe to see if the fault injection was
successful, and will keeping on injecting new faults until the module
succeeds in loading having surpassed the number of fault points.

v2: Reset to 0 after being hit;

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Imre Deak <imre.deak@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180606144153.4244-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 83ce9c1ec170..0a1b09bb658f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -67,6 +67,7 @@ bool __i915_inject_load_failure(const char *func, int line)
 	if (++i915_load_fail_count == i915_modparams.inject_load_failure) {
 		DRM_INFO("Injecting failure at checkpoint %u [%s:%d]\n",
 			 i915_modparams.inject_load_failure, func, line);
+		i915_modparams.inject_load_failure = 0;
 		return true;
 	}
 
@@ -117,16 +118,15 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 static bool i915_error_injected(struct drm_i915_private *dev_priv)
 {
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
-	return i915_modparams.inject_load_failure &&
-	       i915_load_fail_count == i915_modparams.inject_load_failure;
+	return i915_load_fail_count && !i915_modparams.inject_load_failure;
 #else
 	return false;
 #endif
 }
 
-#define i915_load_error(dev_priv, fmt, ...)				     \
-	__i915_printk(dev_priv,						     \
-		      i915_error_injected(dev_priv) ? KERN_DEBUG : KERN_ERR, \
+#define i915_load_error(i915, fmt, ...)					 \
+	__i915_printk(i915,						 \
+		      i915_error_injected(i915) ? KERN_DEBUG : KERN_ERR, \
 		      fmt, ##__VA_ARGS__)
 
 /* Map PCH device id to PCH type, or PCH_NONE if unknown. */
-- 
cgit v1.2.3


From 64b3c93649a652c2e4a25569f167378333338347 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 6 Jun 2018 21:51:28 +0100
Subject: drm/i915/gtt: Fix typo in fill_px() macro

The macro declared the ppgtt parameter but implicitly used the local vm
instead.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180606205128.25952-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 029a5f4fbd92..2b4a40a32b76 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -528,8 +528,8 @@ static void cleanup_page_dma(struct i915_address_space *vm,
 
 #define setup_px(vm, px) setup_page_dma((vm), px_base(px))
 #define cleanup_px(vm, px) cleanup_page_dma((vm), px_base(px))
-#define fill_px(ppgtt, px, v) fill_page_dma((vm), px_base(px), (v))
-#define fill32_px(ppgtt, px, v) fill_page_dma_32((vm), px_base(px), (v))
+#define fill_px(vm, px, v) fill_page_dma((vm), px_base(px), (v))
+#define fill32_px(vm, px, v) fill_page_dma_32((vm), px_base(px), (v))
 
 static void fill_page_dma(struct i915_address_space *vm,
 			  struct i915_page_dma *p,
-- 
cgit v1.2.3


From 14c3f8425080a1ff97df7b81f7c339bf42c427a3 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Wed, 6 Jun 2018 15:10:47 -0700
Subject: drm/i915: Update DRIVER_DATE to 20180606

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a4bb30c32a52..79209ee25c21 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -85,8 +85,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180530"
-#define DRIVER_TIMESTAMP	1527717651
+#define DRIVER_DATE		"20180606"
+#define DRIVER_TIMESTAMP	1528323047
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
-- 
cgit v1.2.3


From 8571a05a9dd0986a788f03e4de1a42fc9235959f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 6 Jun 2018 15:54:41 +0100
Subject: drm/i915: Use GEM suspend when aborting initialisation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As part of our GEM initialisation now, we send a request to the hardware
in order to record the initial GPU state. This coupled with deferred
idle workers, makes aborting on error tricky. We already have the
mechanism in place to wait on the GPU and cancel all the deferred
workers for suspend, so let's reuse it during the error teardown. It is
already used in places for later init error handling, but doing so at
this point is slightly ugly due to the mutex dance (it's ok, the module
load is still single threaded).

Testcase: igt/drv_module_reload/basic-reload-inject
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180606145441.4460-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 86f1f9aaa119..1074f47e6cda 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5514,8 +5514,12 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	 * driver doesn't explode during runtime.
 	 */
 err_init_hw:
-	i915_gem_wait_for_idle(dev_priv, I915_WAIT_LOCKED);
-	i915_gem_contexts_lost(dev_priv);
+	mutex_unlock(&dev_priv->drm.struct_mutex);
+
+	WARN_ON(i915_gem_suspend(dev_priv));
+	i915_gem_suspend_late(dev_priv);
+
+	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uc_fini_hw(dev_priv);
 err_uc_init:
 	intel_uc_fini(dev_priv);
-- 
cgit v1.2.3


From 521370106d0d614fca76c7001bf5a82e1250fa27 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 6 Jun 2018 22:45:20 +0100
Subject: drm/i915: Change i915_gem_fault() to return vm_fault_t

In preparation for vm_fault_t becoming a distinct type, convert the
fault handler (i915_gem_fault()) over to the new interface.

Based on a patch by Souptick Joarder

References: 1c8f422059ae ("mm: change return type to vm_fault_t")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Souptick Joarder <jrdr.linux@gmail.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180606214520.20220-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.h |  3 ++-
 drivers/gpu/drm/i915/i915_gem.c | 21 +++++++--------------
 2 files changed, 9 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 79209ee25c21..c4073666f1ca 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -40,6 +40,7 @@
 #include <linux/hash.h>
 #include <linux/intel-iommu.h>
 #include <linux/kref.h>
+#include <linux/mm_types.h>
 #include <linux/perf_event.h>
 #include <linux/pm_qos.h>
 #include <linux/reservation.h>
@@ -3174,7 +3175,7 @@ int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
 int __must_check i915_gem_suspend(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
-int i915_gem_fault(struct vm_fault *vmf);
+vm_fault_t i915_gem_fault(struct vm_fault *vmf);
 int i915_gem_object_wait(struct drm_i915_gem_object *obj,
 			 unsigned int flags,
 			 long timeout,
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1074f47e6cda..fd882eb389d2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1995,7 +1995,7 @@ compute_partial_view(struct drm_i915_gem_object *obj,
  * The current feature set supported by i915_gem_fault() and thus GTT mmaps
  * is exposed via I915_PARAM_MMAP_GTT_VERSION (see i915_gem_mmap_gtt_version).
  */
-int i915_gem_fault(struct vm_fault *vmf)
+vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 {
 #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT)
 	struct vm_area_struct *area = vmf->vma;
@@ -2112,10 +2112,8 @@ err:
 		 * fail). But any other -EIO isn't ours (e.g. swap in failure)
 		 * and so needs to be reported.
 		 */
-		if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
-			ret = VM_FAULT_SIGBUS;
-			break;
-		}
+		if (!i915_terminally_wedged(&dev_priv->gpu_error))
+			return VM_FAULT_SIGBUS;
 	case -EAGAIN:
 		/*
 		 * EAGAIN means the gpu is hung and we'll wait for the error
@@ -2130,21 +2128,16 @@ err:
 		 * EBUSY is ok: this just means that another thread
 		 * already did the job.
 		 */
-		ret = VM_FAULT_NOPAGE;
-		break;
+		return VM_FAULT_NOPAGE;
 	case -ENOMEM:
-		ret = VM_FAULT_OOM;
-		break;
+		return VM_FAULT_OOM;
 	case -ENOSPC:
 	case -EFAULT:
-		ret = VM_FAULT_SIGBUS;
-		break;
+		return VM_FAULT_SIGBUS;
 	default:
 		WARN_ONCE(ret, "unhandled error in i915_gem_fault: %i\n", ret);
-		ret = VM_FAULT_SIGBUS;
-		break;
+		return VM_FAULT_SIGBUS;
 	}
-	return ret;
 }
 
 static void __i915_gem_object_release_mmap(struct drm_i915_gem_object *obj)
-- 
cgit v1.2.3


From 520ea7c581bf3ba4761c1fb61c53b11767665b62 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 7 Jun 2018 16:40:45 +0100
Subject: drm/i915: Prepare for non-object vma

In order to allow ourselves to use VMA to wrap other entities other than
GEM objects, we need to allow for the vma->obj backpointer to be NULL.
In most cases, we know we are operating on a GEM object and its vma, but
we need the core code (such as i915_vma_pin/insert/bind/unbind) to work
regardless of the innards.

The remaining eyesore here is vma->obj->cache_level and related (but
less of an issue) vma->obj->gt_ro. With a bit of care we should mirror
those on the vma itself.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180607154047.9171-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c   |  7 ++-
 drivers/gpu/drm/i915/i915_gpu_error.c |  3 ++
 drivers/gpu/drm/i915/i915_vma.c       | 96 ++++++++++++++++++++---------------
 drivers/gpu/drm/i915/i915_vma.h       |  2 +-
 4 files changed, 65 insertions(+), 43 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 2b4a40a32b76..7c45a516aa6b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -3588,8 +3588,11 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 		if (!i915_vma_unbind(vma))
 			continue;
 
-		WARN_ON(i915_vma_bind(vma, obj->cache_level, PIN_UPDATE));
-		WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
+		WARN_ON(i915_vma_bind(vma,
+				      obj ? obj->cache_level : 0,
+				      PIN_UPDATE));
+		if (obj)
+			WARN_ON(i915_gem_object_set_to_gtt_domain(obj, false));
 	}
 
 	ggtt->vm.closed = false;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 758234d20f4e..df524c9cad40 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1050,6 +1050,9 @@ static u32 capture_error_bo(struct drm_i915_error_buffer *err,
 	int i = 0;
 
 	list_for_each_entry(vma, head, vm_link) {
+		if (!vma->obj)
+			continue;
+
 		if (pinned_only && !i915_vma_is_pinned(vma))
 			continue;
 
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 912f16ffe7ee..b71265066cd1 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -345,7 +345,7 @@ void i915_vma_flush_writes(struct i915_vma *vma)
 
 void i915_vma_unpin_iomap(struct i915_vma *vma)
 {
-	lockdep_assert_held(&vma->obj->base.dev->struct_mutex);
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
 
 	GEM_BUG_ON(vma->iomap == NULL);
 
@@ -365,6 +365,7 @@ void i915_vma_unpin_and_release(struct i915_vma **p_vma)
 		return;
 
 	obj = vma->obj;
+	GEM_BUG_ON(!obj);
 
 	i915_vma_unpin(vma);
 	i915_vma_close(vma);
@@ -489,7 +490,7 @@ static int
 i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 {
 	struct drm_i915_private *dev_priv = vma->vm->i915;
-	struct drm_i915_gem_object *obj = vma->obj;
+	unsigned int cache_level;
 	u64 start, end;
 	int ret;
 
@@ -524,16 +525,21 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	 * attempt to find space.
 	 */
 	if (size > end) {
-		DRM_DEBUG("Attempting to bind an object larger than the aperture: request=%llu [object=%zd] > %s aperture=%llu\n",
-			  size, obj->base.size,
-			  flags & PIN_MAPPABLE ? "mappable" : "total",
+		DRM_DEBUG("Attempting to bind an object larger than the aperture: request=%llu > %s aperture=%llu\n",
+			  size, flags & PIN_MAPPABLE ? "mappable" : "total",
 			  end);
 		return -ENOSPC;
 	}
 
-	ret = i915_gem_object_pin_pages(obj);
-	if (ret)
-		return ret;
+	if (vma->obj) {
+		ret = i915_gem_object_pin_pages(vma->obj);
+		if (ret)
+			return ret;
+
+		cache_level = vma->obj->cache_level;
+	} else {
+		cache_level = 0;
+	}
 
 	GEM_BUG_ON(vma->pages);
 
@@ -550,7 +556,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 
 		ret = i915_gem_gtt_reserve(vma->vm, &vma->node,
-					   size, offset, obj->cache_level,
+					   size, offset, cache_level,
 					   flags);
 		if (ret)
 			goto err_clear;
@@ -589,7 +595,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		}
 
 		ret = i915_gem_gtt_insert(vma->vm, &vma->node,
-					  size, alignment, obj->cache_level,
+					  size, alignment, cache_level,
 					  start, end, flags);
 		if (ret)
 			goto err_clear;
@@ -598,23 +604,28 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 		GEM_BUG_ON(vma->node.start + vma->node.size > end);
 	}
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, obj->cache_level));
+	GEM_BUG_ON(!i915_gem_valid_gtt_space(vma, cache_level));
 
 	list_move_tail(&vma->vm_link, &vma->vm->inactive_list);
 
-	spin_lock(&dev_priv->mm.obj_lock);
-	list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list);
-	obj->bind_count++;
-	spin_unlock(&dev_priv->mm.obj_lock);
+	if (vma->obj) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		spin_lock(&dev_priv->mm.obj_lock);
+		list_move_tail(&obj->mm.link, &dev_priv->mm.bound_list);
+		obj->bind_count++;
+		spin_unlock(&dev_priv->mm.obj_lock);
 
-	assert_bind_count(obj);
+		assert_bind_count(obj);
+	}
 
 	return 0;
 
 err_clear:
 	vma->vm->clear_pages(vma);
 err_unpin:
-	i915_gem_object_unpin_pages(obj);
+	if (vma->obj)
+		i915_gem_object_unpin_pages(vma->obj);
 	return ret;
 }
 
@@ -622,7 +633,6 @@ static void
 i915_vma_remove(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
-	struct drm_i915_gem_object *obj = vma->obj;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
@@ -632,20 +642,26 @@ i915_vma_remove(struct i915_vma *vma)
 	drm_mm_remove_node(&vma->node);
 	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
 
-	/* Since the unbound list is global, only move to that list if
+	/*
+	 * Since the unbound list is global, only move to that list if
 	 * no more VMAs exist.
 	 */
-	spin_lock(&i915->mm.obj_lock);
-	if (--obj->bind_count == 0)
-		list_move_tail(&obj->mm.link, &i915->mm.unbound_list);
-	spin_unlock(&i915->mm.obj_lock);
-
-	/* And finally now the object is completely decoupled from this vma,
-	 * we can drop its hold on the backing storage and allow it to be
-	 * reaped by the shrinker.
-	 */
-	i915_gem_object_unpin_pages(obj);
-	assert_bind_count(obj);
+	if (vma->obj) {
+		struct drm_i915_gem_object *obj = vma->obj;
+
+		spin_lock(&i915->mm.obj_lock);
+		if (--obj->bind_count == 0)
+			list_move_tail(&obj->mm.link, &i915->mm.unbound_list);
+		spin_unlock(&i915->mm.obj_lock);
+
+		/*
+		 * And finally now the object is completely decoupled from this
+		 * vma, we can drop its hold on the backing storage and allow
+		 * it to be reaped by the shrinker.
+		 */
+		i915_gem_object_unpin_pages(obj);
+		assert_bind_count(obj);
+	}
 }
 
 int __i915_vma_do_pin(struct i915_vma *vma,
@@ -670,7 +686,7 @@ int __i915_vma_do_pin(struct i915_vma *vma,
 	}
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 
-	ret = i915_vma_bind(vma, vma->obj->cache_level, flags);
+	ret = i915_vma_bind(vma, vma->obj ? vma->obj->cache_level : 0, flags);
 	if (ret)
 		goto err_remove;
 
@@ -727,6 +743,7 @@ void i915_vma_reopen(struct i915_vma *vma)
 
 static void __i915_vma_destroy(struct i915_vma *vma)
 {
+	struct drm_i915_private *i915 = vma->vm->i915;
 	int i;
 
 	GEM_BUG_ON(vma->node.allocated);
@@ -738,12 +755,13 @@ static void __i915_vma_destroy(struct i915_vma *vma)
 
 	list_del(&vma->obj_link);
 	list_del(&vma->vm_link);
-	rb_erase(&vma->obj_node, &vma->obj->vma_tree);
+	if (vma->obj)
+		rb_erase(&vma->obj_node, &vma->obj->vma_tree);
 
 	if (!i915_vma_is_ggtt(vma))
 		i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm));
 
-	kmem_cache_free(to_i915(vma->obj->base.dev)->vmas, vma);
+	kmem_cache_free(i915->vmas, vma);
 }
 
 void i915_vma_destroy(struct i915_vma *vma)
@@ -809,13 +827,13 @@ void i915_vma_revoke_mmap(struct i915_vma *vma)
 
 int i915_vma_unbind(struct i915_vma *vma)
 {
-	struct drm_i915_gem_object *obj = vma->obj;
 	unsigned long active;
 	int ret;
 
-	lockdep_assert_held(&obj->base.dev->struct_mutex);
+	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
 
-	/* First wait upon any activity as retiring the request may
+	/*
+	 * First wait upon any activity as retiring the request may
 	 * have side-effects such as unpinning or even unbinding this vma.
 	 */
 	might_sleep();
@@ -823,7 +841,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 	if (active) {
 		int idx;
 
-		/* When a closed VMA is retired, it is unbound - eek.
+		/*
+		 * When a closed VMA is retired, it is unbound - eek.
 		 * In order to prevent it from being recursively closed,
 		 * take a pin on the vma so that the second unbind is
 		 * aborted.
@@ -861,9 +880,6 @@ int i915_vma_unbind(struct i915_vma *vma)
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
 
-	GEM_BUG_ON(obj->bind_count == 0);
-	GEM_BUG_ON(!i915_gem_object_has_pinned_pages(obj));
-
 	if (i915_vma_is_map_and_fenceable(vma)) {
 		/*
 		 * Check that we have flushed all writes through the GGTT
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index fc4294cfaa91..f0532f1a4953 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -407,7 +407,7 @@ static inline void __i915_vma_unpin_fence(struct i915_vma *vma)
 static inline void
 i915_vma_unpin_fence(struct i915_vma *vma)
 {
-	lockdep_assert_held(&vma->obj->base.dev->struct_mutex);
+	/* lockdep_assert_held(&vma->vm->i915->drm.struct_mutex); */
 	if (vma->fence)
 		__i915_vma_unpin_fence(vma);
 }
-- 
cgit v1.2.3


From 93f2cde2a4f7947f6330ecfb9b27d13e2f4d43af Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 7 Jun 2018 16:40:46 +0100
Subject: drm/i915: Decouple vma vfuncs from vm

To allow for future non-object backed vma, we need to be able to
specialise the callbacks for binding, et al, the vma. For example,
instead of calling vma->vm->bind_vma(), we now call
vma->ops->bind_vma(). This gives us the opportunity to later override the
operation for a custom vma.

v2: flip order of unbind/bind

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180607154047.9171-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c       | 57 +++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_gem_gtt.h       | 27 ++++++++++-----
 drivers/gpu/drm/i915/i915_vma.c           | 11 +++---
 drivers/gpu/drm/i915/i915_vma.h           |  1 +
 drivers/gpu/drm/i915/selftests/mock_gtt.c | 18 +++++-----
 5 files changed, 66 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7c45a516aa6b..d841bf296d19 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1616,12 +1616,13 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
 	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
-	ppgtt->vm.bind_vma = gen8_ppgtt_bind_vma;
-	ppgtt->vm.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->vm.set_pages = ppgtt_set_pages;
-	ppgtt->vm.clear_pages = clear_pages;
 	ppgtt->debug_dump = gen8_dump_ppgtt;
 
+	ppgtt->vm.vma_ops.bind_vma    = gen8_ppgtt_bind_vma;
+	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
+	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->vm.vma_ops.clear_pages = clear_pages;
+
 	return 0;
 
 free_scratch:
@@ -2059,13 +2060,14 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 
 	ppgtt->vm.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->vm.insert_entries = gen6_ppgtt_insert_entries;
-	ppgtt->vm.bind_vma = gen6_ppgtt_bind_vma;
-	ppgtt->vm.unbind_vma = ppgtt_unbind_vma;
-	ppgtt->vm.set_pages = ppgtt_set_pages;
-	ppgtt->vm.clear_pages = clear_pages;
 	ppgtt->vm.cleanup = gen6_ppgtt_cleanup;
 	ppgtt->debug_dump = gen6_dump_ppgtt;
 
+	ppgtt->vm.vma_ops.bind_vma    = gen6_ppgtt_bind_vma;
+	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
+	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->vm.vma_ops.clear_pages = clear_pages;
+
 	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
 			 ppgtt->node.size >> 20,
 			 ppgtt->node.start / PAGE_SIZE);
@@ -2793,11 +2795,11 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 
 	i915->mm.aliasing_ppgtt = ppgtt;
 
-	GEM_BUG_ON(ggtt->vm.bind_vma != ggtt_bind_vma);
-	ggtt->vm.bind_vma = aliasing_gtt_bind_vma;
+	GEM_BUG_ON(ggtt->vm.vma_ops.bind_vma != ggtt_bind_vma);
+	ggtt->vm.vma_ops.bind_vma = aliasing_gtt_bind_vma;
 
-	GEM_BUG_ON(ggtt->vm.unbind_vma != ggtt_unbind_vma);
-	ggtt->vm.unbind_vma = aliasing_gtt_unbind_vma;
+	GEM_BUG_ON(ggtt->vm.vma_ops.unbind_vma != ggtt_unbind_vma);
+	ggtt->vm.vma_ops.unbind_vma = aliasing_gtt_unbind_vma;
 
 	return 0;
 
@@ -2817,8 +2819,8 @@ void i915_gem_fini_aliasing_ppgtt(struct drm_i915_private *i915)
 
 	i915_ppgtt_put(ppgtt);
 
-	ggtt->vm.bind_vma = ggtt_bind_vma;
-	ggtt->vm.unbind_vma = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.bind_vma   = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma = ggtt_unbind_vma;
 }
 
 int i915_gem_init_ggtt(struct drm_i915_private *dev_priv)
@@ -3310,10 +3312,6 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->vm.total = (size / sizeof(gen8_pte_t)) << PAGE_SHIFT;
 	ggtt->vm.cleanup = gen6_gmch_remove;
-	ggtt->vm.bind_vma = ggtt_bind_vma;
-	ggtt->vm.unbind_vma = ggtt_unbind_vma;
-	ggtt->vm.set_pages = ggtt_set_pages;
-	ggtt->vm.clear_pages = clear_pages;
 	ggtt->vm.insert_page = gen8_ggtt_insert_page;
 	ggtt->vm.clear_range = nop_clear_range;
 	if (!USES_FULL_PPGTT(dev_priv) || intel_scanout_needs_vtd_wa(dev_priv))
@@ -3331,6 +3329,11 @@ static int gen8_gmch_probe(struct i915_ggtt *ggtt)
 
 	ggtt->invalidate = gen6_ggtt_invalidate;
 
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
 	setup_private_pat(dev_priv);
 
 	return ggtt_probe_common(ggtt, size);
@@ -3370,10 +3373,6 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.clear_range = gen6_ggtt_clear_range;
 	ggtt->vm.insert_page = gen6_ggtt_insert_page;
 	ggtt->vm.insert_entries = gen6_ggtt_insert_entries;
-	ggtt->vm.bind_vma = ggtt_bind_vma;
-	ggtt->vm.unbind_vma = ggtt_unbind_vma;
-	ggtt->vm.set_pages = ggtt_set_pages;
-	ggtt->vm.clear_pages = clear_pages;
 	ggtt->vm.cleanup = gen6_gmch_remove;
 
 	ggtt->invalidate = gen6_ggtt_invalidate;
@@ -3389,6 +3388,11 @@ static int gen6_gmch_probe(struct i915_ggtt *ggtt)
 	else
 		ggtt->vm.pte_encode = snb_pte_encode;
 
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
 	return ggtt_probe_common(ggtt, size);
 }
 
@@ -3419,14 +3423,15 @@ static int i915_gmch_probe(struct i915_ggtt *ggtt)
 	ggtt->vm.insert_page = i915_ggtt_insert_page;
 	ggtt->vm.insert_entries = i915_ggtt_insert_entries;
 	ggtt->vm.clear_range = i915_ggtt_clear_range;
-	ggtt->vm.bind_vma = ggtt_bind_vma;
-	ggtt->vm.unbind_vma = ggtt_unbind_vma;
-	ggtt->vm.set_pages = ggtt_set_pages;
-	ggtt->vm.clear_pages = clear_pages;
 	ggtt->vm.cleanup = i915_gmch_remove;
 
 	ggtt->invalidate = gmch_ggtt_invalidate;
 
+	ggtt->vm.vma_ops.bind_vma    = ggtt_bind_vma;
+	ggtt->vm.vma_ops.unbind_vma  = ggtt_unbind_vma;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
 	if (unlikely(ggtt->do_idle_maps))
 		DRM_INFO("applying Ironlake quirks for intel_iommu\n");
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 197c2c06ecb7..16307ba7e303 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -58,6 +58,7 @@
 
 struct drm_i915_file_private;
 struct drm_i915_fence_reg;
+struct i915_vma;
 
 typedef u32 gen6_pte_t;
 typedef u64 gen8_pte_t;
@@ -254,6 +255,21 @@ struct i915_pml4 {
 	struct i915_page_directory_pointer *pdps[GEN8_PML4ES_PER_PML4];
 };
 
+struct i915_vma_ops {
+	/* Map an object into an address space with the given cache flags. */
+	int (*bind_vma)(struct i915_vma *vma,
+			enum i915_cache_level cache_level,
+			u32 flags);
+	/*
+	 * Unmap an object from an address space. This usually consists of
+	 * setting the valid PTE entries to a reserved scratch page.
+	 */
+	void (*unbind_vma)(struct i915_vma *vma);
+
+	int (*set_pages)(struct i915_vma *vma);
+	void (*clear_pages)(struct i915_vma *vma);
+};
+
 struct i915_address_space {
 	struct drm_mm mm;
 	struct drm_i915_private *i915;
@@ -331,15 +347,8 @@ struct i915_address_space {
 			       enum i915_cache_level cache_level,
 			       u32 flags);
 	void (*cleanup)(struct i915_address_space *vm);
-	/** Unmap an object from an address space. This usually consists of
-	 * setting the valid PTE entries to a reserved scratch page. */
-	void (*unbind_vma)(struct i915_vma *vma);
-	/* Map an object into an address space with the given cache flags. */
-	int (*bind_vma)(struct i915_vma *vma,
-			enum i915_cache_level cache_level,
-			u32 flags);
-	int (*set_pages)(struct i915_vma *vma);
-	void (*clear_pages)(struct i915_vma *vma);
+
+	struct i915_vma_ops vma_ops;
 
 	I915_SELFTEST_DECLARE(struct fault_attr fault_attr);
 	I915_SELFTEST_DECLARE(bool scrub_64K);
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index b71265066cd1..e82aa804cdba 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -95,6 +95,7 @@ vma_create(struct drm_i915_gem_object *obj,
 		init_request_active(&vma->last_read[i], i915_vma_retire);
 	init_request_active(&vma->last_fence, NULL);
 	vma->vm = vm;
+	vma->ops = &vm->vma_ops;
 	vma->obj = obj;
 	vma->resv = obj->resv;
 	vma->size = obj->base.size;
@@ -280,7 +281,7 @@ int i915_vma_bind(struct i915_vma *vma, enum i915_cache_level cache_level,
 	GEM_BUG_ON(!vma->pages);
 
 	trace_i915_vma_bind(vma, bind_flags);
-	ret = vma->vm->bind_vma(vma, cache_level, bind_flags);
+	ret = vma->ops->bind_vma(vma, cache_level, bind_flags);
 	if (ret)
 		return ret;
 
@@ -543,7 +544,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 
 	GEM_BUG_ON(vma->pages);
 
-	ret = vma->vm->set_pages(vma);
+	ret = vma->ops->set_pages(vma);
 	if (ret)
 		goto err_unpin;
 
@@ -622,7 +623,7 @@ i915_vma_insert(struct i915_vma *vma, u64 size, u64 alignment, u64 flags)
 	return 0;
 
 err_clear:
-	vma->vm->clear_pages(vma);
+	vma->ops->clear_pages(vma);
 err_unpin:
 	if (vma->obj)
 		i915_gem_object_unpin_pages(vma->obj);
@@ -637,7 +638,7 @@ i915_vma_remove(struct i915_vma *vma)
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 	GEM_BUG_ON(vma->flags & (I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND));
 
-	vma->vm->clear_pages(vma);
+	vma->ops->clear_pages(vma);
 
 	drm_mm_remove_node(&vma->node);
 	list_move_tail(&vma->vm_link, &vma->vm->unbound_list);
@@ -906,7 +907,7 @@ int i915_vma_unbind(struct i915_vma *vma)
 
 	if (likely(!vma->vm->closed)) {
 		trace_i915_vma_unbind(vma);
-		vma->vm->unbind_vma(vma);
+		vma->ops->unbind_vma(vma);
 	}
 	vma->flags &= ~(I915_VMA_GLOBAL_BIND | I915_VMA_LOCAL_BIND);
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index f0532f1a4953..4321476a6a32 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -49,6 +49,7 @@ struct i915_vma {
 	struct drm_mm_node node;
 	struct drm_i915_gem_object *obj;
 	struct i915_address_space *vm;
+	const struct i915_vma_ops *ops;
 	struct drm_i915_fence_reg *fence;
 	struct reservation_object *resv; /** Alias of obj->resv */
 	struct sg_table *pages;
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 556c546f2715..6a7f4da7b523 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -80,12 +80,13 @@ mock_ppgtt(struct drm_i915_private *i915,
 	ppgtt->vm.clear_range = nop_clear_range;
 	ppgtt->vm.insert_page = mock_insert_page;
 	ppgtt->vm.insert_entries = mock_insert_entries;
-	ppgtt->vm.bind_vma = mock_bind_ppgtt;
-	ppgtt->vm.unbind_vma = mock_unbind_ppgtt;
-	ppgtt->vm.set_pages = ppgtt_set_pages;
-	ppgtt->vm.clear_pages = clear_pages;
 	ppgtt->vm.cleanup = mock_cleanup;
 
+	ppgtt->vm.vma_ops.bind_vma    = mock_bind_ppgtt;
+	ppgtt->vm.vma_ops.unbind_vma  = mock_unbind_ppgtt;
+	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->vm.vma_ops.clear_pages = clear_pages;
+
 	return ppgtt;
 }
 
@@ -116,12 +117,13 @@ void mock_init_ggtt(struct drm_i915_private *i915)
 	ggtt->vm.clear_range = nop_clear_range;
 	ggtt->vm.insert_page = mock_insert_page;
 	ggtt->vm.insert_entries = mock_insert_entries;
-	ggtt->vm.bind_vma = mock_bind_ggtt;
-	ggtt->vm.unbind_vma = mock_unbind_ggtt;
-	ggtt->vm.set_pages = ggtt_set_pages;
-	ggtt->vm.clear_pages = clear_pages;
 	ggtt->vm.cleanup = mock_cleanup;
 
+	ggtt->vm.vma_ops.bind_vma    = mock_bind_ggtt;
+	ggtt->vm.vma_ops.unbind_vma  = mock_unbind_ggtt;
+	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
+	ggtt->vm.vma_ops.clear_pages = clear_pages;
+
 	i915_address_space_init(&ggtt->vm, i915, "global");
 }
 
-- 
cgit v1.2.3


From 17f297b427a32ef5524a494de331c68366e8226d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 7 Jun 2018 17:30:40 +0100
Subject: drm/i915/gtt: Push allocation to hw ppgtt constructor

In the next patch, we will subclass the gen6 hw_ppgtt. In order, for the
two different generations of hw ppgtt stucts to be of different size,
push the allocation down to the constructor.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180607163040.9781-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c           | 140 ++++++++++++++------------
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c |  16 +--
 2 files changed, 83 insertions(+), 73 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index d841bf296d19..912d6c4ba336 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1562,32 +1562,36 @@ unwind:
  * space.
  *
  */
-static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 {
-	struct i915_address_space *vm = &ppgtt->vm;
-	struct drm_i915_private *dev_priv = vm->i915;
-	int ret;
+	struct i915_hw_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
 
-	ppgtt->vm.total = USES_FULL_48BIT_PPGTT(dev_priv) ?
+	ppgtt->vm.i915 = i915;
+	ppgtt->vm.dma = &i915->drm.pdev->dev;
+
+	ppgtt->vm.total = USES_FULL_48BIT_PPGTT(i915) ?
 		1ULL << 48 :
 		1ULL << 32;
 
 	/* There are only few exceptions for gen >=6. chv and bxt.
 	 * And we are not sure about the latter so play safe for now.
 	 */
-	if (IS_CHERRYVIEW(dev_priv) || IS_BROXTON(dev_priv))
+	if (IS_CHERRYVIEW(i915) || IS_BROXTON(i915))
 		ppgtt->vm.pt_kmap_wc = true;
 
-	ret = gen8_init_scratch(&ppgtt->vm);
-	if (ret) {
-		ppgtt->vm.total = 0;
-		return ret;
-	}
+	err = gen8_init_scratch(&ppgtt->vm);
+	if (err)
+		goto err_free;
 
-	if (use_4lvl(vm)) {
-		ret = setup_px(&ppgtt->vm, &ppgtt->pml4);
-		if (ret)
-			goto free_scratch;
+	if (use_4lvl(&ppgtt->vm)) {
+		err = setup_px(&ppgtt->vm, &ppgtt->pml4);
+		if (err)
+			goto err_scratch;
 
 		gen8_initialize_pml4(&ppgtt->vm, &ppgtt->pml4);
 
@@ -1595,15 +1599,15 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		ppgtt->vm.insert_entries = gen8_ppgtt_insert_4lvl;
 		ppgtt->vm.clear_range = gen8_ppgtt_clear_4lvl;
 	} else {
-		ret = __pdp_init(&ppgtt->vm, &ppgtt->pdp);
-		if (ret)
-			goto free_scratch;
+		err = __pdp_init(&ppgtt->vm, &ppgtt->pdp);
+		if (err)
+			goto err_scratch;
 
-		if (intel_vgpu_active(dev_priv)) {
-			ret = gen8_preallocate_top_level_pdp(ppgtt);
-			if (ret) {
+		if (intel_vgpu_active(i915)) {
+			err = gen8_preallocate_top_level_pdp(ppgtt);
+			if (err) {
 				__pdp_fini(&ppgtt->pdp);
-				goto free_scratch;
+				goto err_scratch;
 			}
 		}
 
@@ -1612,7 +1616,7 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 		ppgtt->vm.clear_range = gen8_ppgtt_clear_3lvl;
 	}
 
-	if (intel_vgpu_active(dev_priv))
+	if (intel_vgpu_active(i915))
 		gen8_ppgtt_notify_vgt(ppgtt, true);
 
 	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
@@ -1623,11 +1627,13 @@ static int gen8_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
 	ppgtt->vm.vma_ops.clear_pages = clear_pages;
 
-	return 0;
+	return ppgtt;
 
-free_scratch:
+err_scratch:
 	gen8_free_scratch(&ppgtt->vm);
-	return ret;
+err_free:
+	kfree(ppgtt);
+	return ERR_PTR(err);
 }
 
 static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
@@ -1638,8 +1644,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 	u32 pd_entry, pte, pde;
 	u32 start = 0, length = ppgtt->vm.total;
 
-	scratch_pte = vm->pte_encode(vm->scratch_page.daddr,
-				     I915_CACHE_LLC, 0);
+	scratch_pte = vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 
 	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde) {
 		u32 expected;
@@ -2027,36 +2032,41 @@ static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
 		ppgtt->pd.page_table[pde] = ppgtt->vm.scratch_pt;
 }
 
-static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
+static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 {
-	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	int ret;
+	struct i915_ggtt * const ggtt = &i915->ggtt;
+	struct i915_hw_ppgtt *ppgtt;
+	int err;
+
+	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
+	if (!ppgtt)
+		return ERR_PTR(-ENOMEM);
+
+	ppgtt->vm.i915 = i915;
+	ppgtt->vm.dma = &i915->drm.pdev->dev;
 
 	ppgtt->vm.pte_encode = ggtt->vm.pte_encode;
-	if (intel_vgpu_active(dev_priv) || IS_GEN6(dev_priv))
+	if (intel_vgpu_active(i915) || IS_GEN6(i915))
 		ppgtt->switch_mm = gen6_mm_switch;
-	else if (IS_HASWELL(dev_priv))
+	else if (IS_HASWELL(i915))
 		ppgtt->switch_mm = hsw_mm_switch;
-	else if (IS_GEN7(dev_priv))
+	else if (IS_GEN7(i915))
 		ppgtt->switch_mm = gen7_mm_switch;
 	else
 		BUG();
 
-	ret = gen6_ppgtt_alloc(ppgtt);
-	if (ret)
-		return ret;
+	err = gen6_ppgtt_alloc(ppgtt);
+	if (err)
+		goto err_free;
 
 	ppgtt->vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
 
 	gen6_scratch_va_range(ppgtt, 0, ppgtt->vm.total);
 	gen6_write_page_range(ppgtt, 0, ppgtt->vm.total);
 
-	ret = gen6_alloc_va_range(&ppgtt->vm, 0, ppgtt->vm.total);
-	if (ret) {
-		gen6_ppgtt_cleanup(&ppgtt->vm);
-		return ret;
-	}
+	err = gen6_alloc_va_range(&ppgtt->vm, 0, ppgtt->vm.total);
+	if (err)
+		goto err_cleanup;
 
 	ppgtt->vm.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->vm.insert_entries = gen6_ppgtt_insert_entries;
@@ -2075,19 +2085,13 @@ static int gen6_ppgtt_init(struct i915_hw_ppgtt *ppgtt)
 	DRM_DEBUG_DRIVER("Adding PPGTT at offset %x\n",
 			 ppgtt->pd.base.ggtt_offset << 10);
 
-	return 0;
-}
-
-static int __hw_ppgtt_init(struct i915_hw_ppgtt *ppgtt,
-			   struct drm_i915_private *dev_priv)
-{
-	ppgtt->vm.i915 = dev_priv;
-	ppgtt->vm.dma = &dev_priv->drm.pdev->dev;
+	return ppgtt;
 
-	if (INTEL_GEN(dev_priv) < 8)
-		return gen6_ppgtt_init(ppgtt);
-	else
-		return gen8_ppgtt_init(ppgtt);
+err_cleanup:
+	gen6_ppgtt_cleanup(&ppgtt->vm);
+err_free:
+	kfree(ppgtt);
+	return ERR_PTR(err);
 }
 
 static void i915_address_space_init(struct i915_address_space *vm,
@@ -2173,26 +2177,28 @@ int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv)
 	return 0;
 }
 
+static struct i915_hw_ppgtt *
+__hw_ppgtt_create(struct drm_i915_private *i915)
+{
+	if (INTEL_GEN(i915) < 8)
+		return gen6_ppgtt_create(i915);
+	else
+		return gen8_ppgtt_create(i915);
+}
+
 struct i915_hw_ppgtt *
-i915_ppgtt_create(struct drm_i915_private *dev_priv,
+i915_ppgtt_create(struct drm_i915_private *i915,
 		  struct drm_i915_file_private *fpriv,
 		  const char *name)
 {
 	struct i915_hw_ppgtt *ppgtt;
-	int ret;
 
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return ERR_PTR(-ENOMEM);
-
-	ret = __hw_ppgtt_init(ppgtt, dev_priv);
-	if (ret) {
-		kfree(ppgtt);
-		return ERR_PTR(ret);
-	}
+	ppgtt = __hw_ppgtt_create(i915);
+	if (IS_ERR(ppgtt))
+		return ppgtt;
 
 	kref_init(&ppgtt->ref);
-	i915_address_space_init(&ppgtt->vm, dev_priv, name);
+	i915_address_space_init(&ppgtt->vm, i915, name);
 	ppgtt->vm.file = fpriv;
 
 	trace_i915_ppgtt_create(&ppgtt->vm);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 58ab5e84ceb7..f80cf7ce3fa9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -147,12 +147,16 @@ static int igt_ppgtt_alloc(void *arg)
 		return -ENOMEM;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	err = __hw_ppgtt_init(ppgtt, dev_priv);
-	if (err)
-		goto err_ppgtt;
+	ppgtt = __hw_ppgtt_create(dev_priv);
+	if (IS_ERR(ppgtt)) {
+		err = PTR_ERR(ppgtt);
+		goto err_unlock;
+	}
 
-	if (!ppgtt->vm.allocate_va_range)
+	if (!ppgtt->vm.allocate_va_range) {
+		err = 0;
 		goto err_ppgtt_cleanup;
+	}
 
 	/* Check we can allocate the entire range */
 	for (size = 4096;
@@ -189,9 +193,9 @@ static int igt_ppgtt_alloc(void *arg)
 
 err_ppgtt_cleanup:
 	ppgtt->vm.cleanup(&ppgtt->vm);
-err_ppgtt:
-	mutex_unlock(&dev_priv->drm.struct_mutex);
 	kfree(ppgtt);
+err_unlock:
+	mutex_unlock(&dev_priv->drm.struct_mutex);
 	return err;
 }
 
-- 
cgit v1.2.3


From c30acb04e7c401d5b412ec925ff4b862bc77b0b8 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Tue, 5 Jun 2018 19:03:56 +0300
Subject: drm/i915: Cancel reset preparations on failed resets

Our reset handling has a retry layer further up in the
chain. As we have told the engine to prepare for reset,
and failed it, make sure to remove that preparation so
that the next attempted reset has a clean slate by triggering
another full prepare cycle for the engines.

v2: ret as int, simplified cleanup (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605160357.32591-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/intel_uncore.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index b36a3b5736a0..bb03f6d8b3d1 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -2093,21 +2093,25 @@ static int gen8_reset_engines(struct drm_i915_private *dev_priv,
 {
 	struct intel_engine_cs *engine;
 	unsigned int tmp;
+	int ret;
 
-	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
-		if (gen8_reset_engine_start(engine))
+	for_each_engine_masked(engine, dev_priv, engine_mask, tmp) {
+		if (gen8_reset_engine_start(engine)) {
+			ret = -EIO;
 			goto not_ready;
+		}
+	}
 
 	if (INTEL_GEN(dev_priv) >= 11)
-		return gen11_reset_engines(dev_priv, engine_mask);
+		ret = gen11_reset_engines(dev_priv, engine_mask);
 	else
-		return gen6_reset_engines(dev_priv, engine_mask);
+		ret = gen6_reset_engines(dev_priv, engine_mask);
 
 not_ready:
 	for_each_engine_masked(engine, dev_priv, engine_mask, tmp)
 		gen8_reset_engine_cancel(engine);
 
-	return -EIO;
+	return ret;
 }
 
 typedef int (*reset_func)(struct drm_i915_private *, unsigned engine_mask);
-- 
cgit v1.2.3


From 39e78234b0be7ae543db8c8ea3cd2e433b8a7bec Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Thu, 7 Jun 2018 20:24:44 +0300
Subject: drm/i915: Add WaKBLVECSSemaphoreWaitPoll

There is a problem with kbl up to rev E0 where a heavy
memory/fabric traffic from adjacent engine(s) can cause an engine
reset to fail. This traffic can be from normal memory accesses
or it can be from heavy polling on a semaphore wait.

For engine hogging causing a fail, we already fallback to
full reset. Which effectively stops all engines and thus
we only add a workaround documentation.

For the semaphore wait loop poll case, we add one microsecond
poll interval to semaphore wait to guarantee bandwidth for
the reset preration. The side effect is that we make semaphore
completion latencies also 1us longer.

v2: Let full reset handle the adjacent engine idling (Chris)
v3: Skip render engine (Joonas), please checkpatch on define (Mika)

References: https://bugs.freedesktop.org/show_bug.cgi?id=106684
References: VTHSD#2227190, HSDES#1604216706, BSID#0917
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180607172444.17080-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_reg.h          |  1 +
 drivers/gpu/drm/i915/intel_uncore.c      |  2 ++
 drivers/gpu/drm/i915/intel_workarounds.c | 13 +++++++++++++
 3 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index f0317bde3aab..987def26ce82 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2242,6 +2242,7 @@ enum i915_power_well_id {
 #define RING_RESET_CTL(base)	_MMIO((base)+0xd0)
 #define   RESET_CTL_REQUEST_RESET  (1 << 0)
 #define   RESET_CTL_READY_TO_RESET (1 << 1)
+#define RING_SEMA_WAIT_POLL(base) _MMIO((base) + 0x24c)
 
 #define HSW_GTT_CACHE_EN	_MMIO(0x4024)
 #define   GTT_CACHE_EN_ALL	0xF0007FFF
diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index bb03f6d8b3d1..b892ca8396e8 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -2174,6 +2174,8 @@ int intel_gpu_reset(struct drm_i915_private *dev_priv, unsigned engine_mask)
 		 * Thus assume it is best to stop engines on all gens
 		 * where we have a gpu reset.
 		 *
+		 * WaKBLVECSSemaphoreWaitPoll:kbl (on ALL_ENGINES)
+		 *
 		 * WaMediaResetMainRingCleanup:ctg,elk (presumably)
 		 *
 		 * FIXME: Wa for more modern gens needs to be validated
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index b1ab56a1ec31..24b929ce3341 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -666,6 +666,19 @@ static void kbl_gt_workarounds_apply(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA,
 		   I915_READ(GEN9_GAMT_ECO_REG_RW_IA) |
 		   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS);
+
+	/* WaKBLVECSSemaphoreWaitPoll:kbl */
+	if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_E0)) {
+		struct intel_engine_cs *engine;
+		unsigned int tmp;
+
+		for_each_engine(engine, dev_priv, tmp) {
+			if (engine->id == RCS)
+				continue;
+
+			I915_WRITE(RING_SEMA_WAIT_POLL(engine->mmio_base), 1);
+		}
+	}
 }
 
 static void glk_gt_workarounds_apply(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From 51e645b6652c997a68cbadf70e62a7b0c49e63a2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 7 Jun 2018 14:45:58 +0100
Subject: drm/i915: Mark the GPU as wedged without error on fault injection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If we have been instructed (by CI) to inject a fault to load the module
with a wedged GPU, do so quietly less we upset CI.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180607134558.31150-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index fd882eb389d2..4187e0688e50 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5491,6 +5491,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	}
 
 	if (i915_inject_load_failure()) {
+		DRM_DEBUG_DRIVER("Marking the driver as wedged\n");
+		i915_gem_set_wedged(dev_priv);  /* Fail silently! */
 		ret = -EIO;
 		goto err_init_hw;
 	}
-- 
cgit v1.2.3


From 672b3c4bc3d157078c00146c2d20bdd3aeec38e6 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 29 May 2018 21:28:00 +0300
Subject: drm/i915: Fix sprite destination colorkeying on SKL+
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On SKL+ the dst colorkey must be configured on the lower
plane that contains the colorkey. This is in contrast to
most earlier platforms where the dst colorkey is configured
on the plane above.

The hardware will peform dst keying only between two immediately
adjacent (in zorder) planes. Plane 2 will be keyed against plane 1,
plane 3 againts plane 2, and so on. There is no way to key arbitrary
planes against plane 1. Thus offering dst color keying on plane 3+
is pointless. In fact it can be harmful since enabling dst keying on
more than one plane on the same pipe leads to only the top-most of
the planes performing the keying. For any plane lower in zorder the
dst key enable is simply ignored.

v2: s/plane 0/plane 1/ etc. since the hw plane names start from 1
    Don't break dst colorkey on pre-SKL sprites (hunk ended in the
    wrong patch)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180529182804.8571-1-ville.syrjala@linux.intel.com
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com> #v1
---
 drivers/gpu/drm/i915/intel_sprite.c | 64 +++++++++++++++++++++++++++++++++++--
 1 file changed, 61 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 24f86c4375cf..d9e7f4fb5096 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -1175,6 +1175,37 @@ intel_check_sprite_plane(struct intel_plane *plane,
 	return 0;
 }
 
+static bool has_dst_key_in_primary_plane(struct drm_i915_private *dev_priv)
+{
+	return INTEL_GEN(dev_priv) >= 9;
+}
+
+static void intel_plane_set_ckey(struct intel_plane_state *plane_state,
+				 const struct drm_intel_sprite_colorkey *set)
+{
+	struct intel_plane *plane = to_intel_plane(plane_state->base.plane);
+	struct drm_i915_private *dev_priv = to_i915(plane->base.dev);
+	struct drm_intel_sprite_colorkey *key = &plane_state->ckey;
+
+	*key = *set;
+
+	/*
+	 * We want src key enabled on the
+	 * sprite and not on the primary.
+	 */
+	if (plane->id == PLANE_PRIMARY &&
+	    set->flags & I915_SET_COLORKEY_SOURCE)
+		key->flags = 0;
+
+	/*
+	 * On SKL+ we want dst key enabled on
+	 * the primary and not on the sprite.
+	 */
+	if (INTEL_GEN(dev_priv) >= 9 && plane->id != PLANE_PRIMARY &&
+	    set->flags & I915_SET_COLORKEY_DESTINATION)
+		key->flags = 0;
+}
+
 int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data,
 				    struct drm_file *file_priv)
 {
@@ -1204,6 +1235,16 @@ int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data,
 	if (!plane || plane->type != DRM_PLANE_TYPE_OVERLAY)
 		return -ENOENT;
 
+	/*
+	 * SKL+ only plane 2 can do destination keying against plane 1.
+	 * Also multiple planes can't do destination keying on the same
+	 * pipe simultaneously.
+	 */
+	if (INTEL_GEN(dev_priv) >= 9 &&
+	    to_intel_plane(plane)->id >= PLANE_SPRITE1 &&
+	    set->flags & I915_SET_COLORKEY_DESTINATION)
+		return -EINVAL;
+
 	drm_modeset_acquire_init(&ctx, 0);
 
 	state = drm_atomic_state_alloc(plane->dev);
@@ -1216,11 +1257,28 @@ int intel_sprite_set_colorkey_ioctl(struct drm_device *dev, void *data,
 	while (1) {
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		ret = PTR_ERR_OR_ZERO(plane_state);
-		if (!ret) {
-			to_intel_plane_state(plane_state)->ckey = *set;
-			ret = drm_atomic_commit(state);
+		if (!ret)
+			intel_plane_set_ckey(to_intel_plane_state(plane_state), set);
+
+		/*
+		 * On some platforms we have to configure
+		 * the dst colorkey on the primary plane.
+		 */
+		if (!ret && has_dst_key_in_primary_plane(dev_priv)) {
+			struct intel_crtc *crtc =
+				intel_get_crtc_for_pipe(dev_priv,
+							to_intel_plane(plane)->pipe);
+
+			plane_state = drm_atomic_get_plane_state(state,
+								 crtc->base.primary);
+			ret = PTR_ERR_OR_ZERO(plane_state);
+			if (!ret)
+				intel_plane_set_ckey(to_intel_plane_state(plane_state), set);
 		}
 
+		if (!ret)
+			ret = drm_atomic_commit(state);
+
 		if (ret != -EDEADLK)
 			break;
 
-- 
cgit v1.2.3


From b4e2727df2713a5aea9de6364f7a943147ceef92 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 8 Jun 2018 18:32:21 +0100
Subject: drm/i915/gtt: Fix unwind length passed to gen6_ppgtt_clear_range

When we want to unwind an error when allocating the PD for gen6, we call
gen6_ppgtt_clear_range() telling to clear upto the PD we've previously
allocated. However, we passed it an incorrect length, passing it the
endpoint instead. Fortunately, as the start was always 0, this has no
impact today, but tomorrow we want to start using non-zero origins.

Reported-by: Matthew Auld <matthew.william.auld@gmail.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608173221.10455-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 912d6c4ba336..ae3b24095d04 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1931,7 +1931,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 	return 0;
 
 unwind_out:
-	gen6_ppgtt_clear_range(vm, from, start);
+	gen6_ppgtt_clear_range(vm, from, start - from);
 	return -ENOMEM;
 }
 
-- 
cgit v1.2.3


From f6b1e35f3e47f40d18fe50a52c09a618ec703c1b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 8 Jun 2018 16:04:34 +0100
Subject: drm/i915/gtt: Remove redundant hsw_mm_switch()

hsw_mm_switch() and gen7_mm_switch() are identical, so let's remove the
redundant specialism.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608150435.15010-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 24 ------------------------
 1 file changed, 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ae3b24095d04..df0ea66ba68c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1718,28 +1718,6 @@ static inline u32 get_pd_offset(struct i915_hw_ppgtt *ppgtt)
 	return ppgtt->pd.base.ggtt_offset << 10;
 }
 
-static int hsw_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			 struct i915_request *rq)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	u32 *cs;
-
-	/* NB: TLBs must be flushed and invalidated before a switch */
-	cs = intel_ring_begin(rq, 6);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(2);
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine));
-	*cs++ = PP_DIR_DCLV_2G;
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
-	*cs++ = get_pd_offset(ppgtt);
-	*cs++ = MI_NOOP;
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
 static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
 			  struct i915_request *rq)
 {
@@ -2048,8 +2026,6 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt->vm.pte_encode = ggtt->vm.pte_encode;
 	if (intel_vgpu_active(i915) || IS_GEN6(i915))
 		ppgtt->switch_mm = gen6_mm_switch;
-	else if (IS_HASWELL(i915))
-		ppgtt->switch_mm = hsw_mm_switch;
 	else if (IS_GEN7(i915))
 		ppgtt->switch_mm = gen7_mm_switch;
 	else
-- 
cgit v1.2.3


From e1f8789883a1bfdb4bfa8b638eeb24eb089c5836 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 8 Jun 2018 16:04:35 +0100
Subject: drm/i915/gtt: Remove vgpu check for gen6

Since vgpu is not supported on Haswell or any other gen6/7, we do not
need to check and act upon it's enablement.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608150435.15010-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index df0ea66ba68c..a8cfe3c413c1 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2024,7 +2024,7 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt->vm.dma = &i915->drm.pdev->dev;
 
 	ppgtt->vm.pte_encode = ggtt->vm.pte_encode;
-	if (intel_vgpu_active(i915) || IS_GEN6(i915))
+	if (IS_GEN6(i915))
 		ppgtt->switch_mm = gen6_mm_switch;
 	else if (IS_GEN7(i915))
 		ppgtt->switch_mm = gen7_mm_switch;
-- 
cgit v1.2.3


From eed2890374446ff67fe5b14517d0b2b08a1a11d2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 9 Jun 2018 10:01:51 +0100
Subject: drm/i915/gtt: Reorder aliasing_ppgtt fini

To allow ourselves to use a first class vma for the aliasing_ppgtt page
directory, we have to reorder the shutdown on module unload to remove
and unpin the aliasing_ppgtt before complaining about any objects left
in the GGTT.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180609090151.22007-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index a8cfe3c413c1..7ccfdbc8f9b4 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2870,15 +2870,11 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 	ggtt->vm.closed = true;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
+	i915_gem_fini_aliasing_ppgtt(dev_priv);
+
 	GEM_BUG_ON(!list_empty(&ggtt->vm.active_list));
 	list_for_each_entry_safe(vma, vn, &ggtt->vm.inactive_list, vm_link)
 		WARN_ON(i915_vma_unbind(vma));
-	mutex_unlock(&dev_priv->drm.struct_mutex);
-
-	i915_gem_cleanup_stolen(&dev_priv->drm);
-
-	mutex_lock(&dev_priv->drm.struct_mutex);
-	i915_gem_fini_aliasing_ppgtt(dev_priv);
 
 	if (drm_mm_node_allocated(&ggtt->error_capture))
 		drm_mm_remove_node(&ggtt->error_capture);
@@ -2900,6 +2896,8 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 
 	arch_phys_wc_del(ggtt->mtrr);
 	io_mapping_fini(&ggtt->iomap);
+
+	i915_gem_cleanup_stolen(&dev_priv->drm);
 }
 
 static unsigned int gen6_get_total_gtt_size(u16 snb_gmch_ctl)
-- 
cgit v1.2.3


From 1f1c60d5b577377d07863f3e0891e63a0a56a3ad Mon Sep 17 00:00:00 2001
From: Xinyun Liu <xinyun.liu@intel.com>
Date: Thu, 7 Jun 2018 22:48:40 +0800
Subject: drm/i915/gvt: Avoid dereference a potential null pointer

Add sanity check for up_irq_info.

Signed-off-by: Xinyun Liu <xinyun.liu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/interrupt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index 7a041b368f68..1d79596da510 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -350,7 +350,8 @@ static void update_upstream_irq(struct intel_vgpu *vgpu,
 			clear_bits |= (1 << bit);
 	}
 
-	WARN_ON(!up_irq_info);
+	if (WARN_ON(!up_irq_info))
+		return;
 
 	if (up_irq_info->group == INTEL_GVT_IRQ_INFO_MASTER) {
 		u32 isr = i915_mmio_reg_offset(up_irq_info->reg_base);
-- 
cgit v1.2.3


From 659571953d315b36204acac508ef8d477044d260 Mon Sep 17 00:00:00 2001
From: Xinyun Liu <xinyun.liu@intel.com>
Date: Thu, 7 Jun 2018 22:48:41 +0800
Subject: drm/i915/gvt: removed unnecessary boundary check

type is already checked in the function entry. So it is unnecessary
to check it again.

Signed-off-by: Xinyun Liu <xinyun.liu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 78e55aafc8bc..49400ab129ff 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1972,7 +1972,7 @@ static int alloc_scratch_pages(struct intel_vgpu *vgpu,
 	 * GTT_TYPE_PPGTT_PDE_PT level pt, that means this scratch_pt it self
 	 * is GTT_TYPE_PPGTT_PTE_PT, and full filled by scratch page mfn.
 	 */
-	if (type > GTT_TYPE_PPGTT_PTE_PT && type < GTT_TYPE_MAX) {
+	if (type > GTT_TYPE_PPGTT_PTE_PT) {
 		struct intel_gvt_gtt_entry se;
 
 		memset(&se, 0, sizeof(struct intel_gvt_gtt_entry));
-- 
cgit v1.2.3


From 1417fad75cb4eddc8d50604be88ca9a8a8de4c71 Mon Sep 17 00:00:00 2001
From: Xinyun Liu <xinyun.liu@intel.com>
Date: Thu, 7 Jun 2018 22:48:42 +0800
Subject: drm/i915/gvt: use array to avoid potential buffer overflow
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Array 'pdp_pair' of size 1 may use index value(s) 1..7.
Changed to pdps[8] to avoid confusion.

Signed-off-by: Xinyun Liu <xinyun.liu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/execlist.h  | 13 +++++--------
 drivers/gpu/drm/i915/gvt/scheduler.c |  5 ++---
 2 files changed, 7 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/execlist.h b/drivers/gpu/drm/i915/gvt/execlist.h
index 427e40e64d41..714d709829a2 100644
--- a/drivers/gpu/drm/i915/gvt/execlist.h
+++ b/drivers/gpu/drm/i915/gvt/execlist.h
@@ -146,14 +146,11 @@ struct execlist_ring_context {
 	u32 nop4;
 	u32 lri_cmd_2;
 	struct execlist_mmio_pair ctx_timestamp;
-	struct execlist_mmio_pair pdp3_UDW;
-	struct execlist_mmio_pair pdp3_LDW;
-	struct execlist_mmio_pair pdp2_UDW;
-	struct execlist_mmio_pair pdp2_LDW;
-	struct execlist_mmio_pair pdp1_UDW;
-	struct execlist_mmio_pair pdp1_LDW;
-	struct execlist_mmio_pair pdp0_UDW;
-	struct execlist_mmio_pair pdp0_LDW;
+	/*
+	 * pdps[8]={ pdp3_UDW, pdp3_LDW, pdp2_UDW, pdp2_LDW,
+	 *           pdp1_UDW, pdp1_LDW, pdp0_UDW, pdp0_LDW}
+	 */
+	struct execlist_mmio_pair pdps[8];
 };
 
 struct intel_vgpu_elsp_dwords {
diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index cf5a22cb6e06..462cf560492e 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -45,11 +45,10 @@ static void set_context_pdp_root_pointer(
 		struct execlist_ring_context *ring_context,
 		u32 pdp[8])
 {
-	struct execlist_mmio_pair *pdp_pair = &ring_context->pdp3_UDW;
 	int i;
 
 	for (i = 0; i < 8; i++)
-		pdp_pair[i].val = pdp[7 - i];
+		ring_context->pdps[i].val = pdp[7 - i];
 }
 
 static void update_shadow_pdps(struct intel_vgpu_workload *workload)
@@ -1230,7 +1229,7 @@ static void read_guest_pdps(struct intel_vgpu *vgpu,
 	u64 gpa;
 	int i;
 
-	gpa = ring_context_gpa + RING_CTX_OFF(pdp3_UDW.val);
+	gpa = ring_context_gpa + RING_CTX_OFF(pdps[0].val);
 
 	for (i = 0; i < 8; i++)
 		intel_gvt_hypervisor_read_gpa(vgpu,
-- 
cgit v1.2.3


From 78ef3faff9ea557e54b053234b6c9461d3ea183f Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 8 Jun 2018 15:33:26 +0300
Subject: drm/i915: fix guest virtual PCH detection on non-PCH systems
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Virtualized non-PCH systems such as Broxton or Geminilake should use
PCH_NONE to indicate no PCH rather than PCH_NOP. The latter is a
specific case to indicate a PCH system without south display.

Reported-by: Colin Xu <Colin.Xu@intel.com>
Cc: Colin Xu <Colin.Xu@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Colin Xu <Colin.Xu@intel.com>
Reviewed-by: Colin Xu <Colin.Xu@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608123330.31003-2-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 0a1b09bb658f..8f22ae8925fc 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -289,7 +289,7 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 				if (WARN_ON(pch_type == PCH_NONE))
 					pch_type = PCH_NOP;
 			} else {
-				pch_type = PCH_NOP;
+				pch_type = PCH_NONE;
 			}
 			dev_priv->pch_type = pch_type;
 			dev_priv->pch_id = id;
-- 
cgit v1.2.3


From b8bf31d82d22ee06e7bb4802c2ce93ccb4b8ee5b Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.de.marchi@gmail.com>
Date: Fri, 8 Jun 2018 15:33:27 +0300
Subject: drm/i915: document PCH_NOP

There's a difference between PCH_NONE and PCH_NOP: the former means we
don't have a PCH while in the latter we do, but it doesn't have the
south display.

Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608123330.31003-3-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c4073666f1ca..71651ca7a8b1 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -632,7 +632,7 @@ enum intel_pch {
 	PCH_KBP,        /* Kaby Lake PCH */
 	PCH_CNP,        /* Cannon Lake PCH */
 	PCH_ICP,	/* Ice Lake PCH */
-	PCH_NOP,
+	PCH_NOP,	/* PCH without south display */
 };
 
 enum intel_sbi_destination {
-- 
cgit v1.2.3


From 85b17e6e4d3f288cc757ff5407b2ca6604673d74 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 8 Jun 2018 15:33:28 +0300
Subject: drm/i915: clean up virtual PCH special case handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use intel_pch_type() also for mapping the no PCH case (PCH id 0) to
PCH_NONE to simplify code.

Also make sure that intel_pch_type() knows all the PCH ids returned by
intel_virt_detect_pch(). Loudly fail if this isn't the case; this
shouldn't happen anyway.

Cc: Colin Xu <Colin.Xu@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Tested-by: Colin Xu <Colin.Xu@intel.com>
Reviewed-by: Colin Xu <Colin.Xu@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608123330.31003-4-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 8f22ae8925fc..9aba419e5d8b 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -284,13 +284,12 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 		} else if (intel_is_virt_pch(id, pch->subsystem_vendor,
 					 pch->subsystem_device)) {
 			id = intel_virt_detect_pch(dev_priv);
-			if (id) {
-				pch_type = intel_pch_type(dev_priv, id);
-				if (WARN_ON(pch_type == PCH_NONE))
-					pch_type = PCH_NOP;
-			} else {
-				pch_type = PCH_NONE;
-			}
+			pch_type = intel_pch_type(dev_priv, id);
+
+			/* Sanity check virtual PCH id */
+			if (WARN_ON(id && pch_type == PCH_NONE))
+				id = 0;
+
 			dev_priv->pch_type = pch_type;
 			dev_priv->pch_id = id;
 			break;
-- 
cgit v1.2.3


From 13d0464b3240429234c34b39b819fe6f088fc3c8 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 8 Jun 2018 15:33:29 +0300
Subject: drm/i915: be more strict about HAS_PCH_NOP() usage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

HAS_PCH_NOP() implies a PCH platform without south display, not generic
disabled display. Prefer num_pipes == 0 for PCH independent checks.

Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608123330.31003-5-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_bios.c | 2 +-
 drivers/gpu/drm/i915/intel_i2c.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 465dff4780fe..18b9e0444116 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1719,7 +1719,7 @@ void intel_bios_init(struct drm_i915_private *dev_priv)
 	const struct bdb_header *bdb;
 	u8 __iomem *bios = NULL;
 
-	if (HAS_PCH_NOP(dev_priv)) {
+	if (INTEL_INFO(dev_priv)->num_pipes == 0) {
 		DRM_DEBUG_KMS("Skipping VBT init due to disabled display.\n");
 		return;
 	}
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index e6875509bcd9..61729bf84e08 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -771,7 +771,7 @@ int intel_setup_gmbus(struct drm_i915_private *dev_priv)
 	unsigned int pin;
 	int ret;
 
-	if (HAS_PCH_NOP(dev_priv))
+	if (INTEL_INFO(dev_priv)->num_pipes == 0)
 		return 0;
 
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-- 
cgit v1.2.3


From 07ba0a82536e4955682b3b9077957ae1421d94bf Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 8 Jun 2018 15:33:30 +0300
Subject: drm/i915: fix PCH_NOP setting for non-PCH platforms
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Setting PCH type to PCH_NOP before checking whether we actually have a
PCH ends up returning true for HAS_PCH_SPLIT() on all non-PCH split
platforms. Fix this by using PCH_NOP only for platforms that actually
have a PCH.

Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608123330.31003-6-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 9aba419e5d8b..d258388605d6 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -248,14 +248,6 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 {
 	struct pci_dev *pch = NULL;
 
-	/* In all current cases, num_pipes is equivalent to the PCH_NOP setting
-	 * (which really amounts to a PCH but no South Display).
-	 */
-	if (INTEL_INFO(dev_priv)->num_pipes == 0) {
-		dev_priv->pch_type = PCH_NOP;
-		return;
-	}
-
 	/*
 	 * The reason to probe ISA bridge instead of Dev31:Fun0 is to
 	 * make graphics device passthrough work easy for VMM, that only
@@ -295,6 +287,17 @@ static void intel_detect_pch(struct drm_i915_private *dev_priv)
 			break;
 		}
 	}
+
+	/*
+	 * Use PCH_NOP (PCH but no South Display) for PCH platforms without
+	 * display.
+	 */
+	if (pch && INTEL_INFO(dev_priv)->num_pipes == 0) {
+		DRM_DEBUG_KMS("Display disabled, reverting to NOP PCH\n");
+		dev_priv->pch_type = PCH_NOP;
+		dev_priv->pch_id = 0;
+	}
+
 	if (!pch)
 		DRM_DEBUG_KMS("No PCH found.\n");
 
-- 
cgit v1.2.3


From 51c18bf7fdbe3c0546e86cb0fa5866fee07c5261 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 9 Jun 2018 12:10:58 +0100
Subject: drm/i915: Squash GEM load failure message (again)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Due to a silent conflict (silent because we are trying to fix the CI
test that is meant to exercising these failures!) between commit
51e645b6652c ("drm/i915: Mark the GPU as wedged without error on fault
injection") and commit 8571a05a9dd0 ("drm/i915: Use GEM suspend when
aborting initialisation"), we failed to actually squash the error
message after injecting the load failure.

Rearrange the code to export i915_load_failure() for better logging of
real errors (and quiet logging of injected errors).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180609111058.2660-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.c | 20 ++++++--------------
 drivers/gpu/drm/i915/i915_drv.h | 11 +++++++++++
 drivers/gpu/drm/i915/i915_gem.c |  5 ++---
 3 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index d258388605d6..4cdd70de5ed0 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -73,6 +73,12 @@ bool __i915_inject_load_failure(const char *func, int line)
 
 	return false;
 }
+
+bool i915_error_injected(void)
+{
+	return i915_load_fail_count && !i915_modparams.inject_load_failure;
+}
+
 #endif
 
 #define FDO_BUG_URL "https://bugs.freedesktop.org/enter_bug.cgi?product=DRI"
@@ -115,20 +121,6 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 	va_end(args);
 }
 
-static bool i915_error_injected(struct drm_i915_private *dev_priv)
-{
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
-	return i915_load_fail_count && !i915_modparams.inject_load_failure;
-#else
-	return false;
-#endif
-}
-
-#define i915_load_error(i915, fmt, ...)					 \
-	__i915_printk(i915,						 \
-		      i915_error_injected(i915) ? KERN_DEBUG : KERN_ERR, \
-		      fmt, ##__VA_ARGS__)
-
 /* Map PCH device id to PCH type, or PCH_NONE if unknown. */
 static enum intel_pch
 intel_pch_type(const struct drm_i915_private *dev_priv, unsigned short id)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 71651ca7a8b1..6104d7115054 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -108,13 +108,24 @@
 	I915_STATE_WARN((x), "%s", "WARN_ON(" __stringify(x) ")")
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
+
 bool __i915_inject_load_failure(const char *func, int line);
 #define i915_inject_load_failure() \
 	__i915_inject_load_failure(__func__, __LINE__)
+
+bool i915_error_injected(void);
+
 #else
+
 #define i915_inject_load_failure() false
+#define i915_error_injected() false
+
 #endif
 
+#define i915_load_error(i915, fmt, ...)					 \
+	__i915_printk(i915, i915_error_injected() ? KERN_DEBUG : KERN_ERR, \
+		      fmt, ##__VA_ARGS__)
+
 typedef struct {
 	uint32_t val;
 } uint_fixed_16_16_t;
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 4187e0688e50..0f28b5ddfd15 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5491,8 +5491,6 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	}
 
 	if (i915_inject_load_failure()) {
-		DRM_DEBUG_DRIVER("Marking the driver as wedged\n");
-		i915_gem_set_wedged(dev_priv);  /* Fail silently! */
 		ret = -EIO;
 		goto err_init_hw;
 	}
@@ -5543,7 +5541,8 @@ err_unlock:
 		 * for all other failure, such as an allocation failure, bail.
 		 */
 		if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
-			DRM_ERROR("Failed to initialize GPU, declaring it wedged\n");
+			i915_load_error(dev_priv,
+					"Failed to initialize GPU, declaring it wedged!\n");
 			i915_gem_set_wedged(dev_priv);
 		}
 		ret = 0;
-- 
cgit v1.2.3


From acd1c1e621fcd90bf94e31b0c871cd241c9153ef Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Jun 2018 08:55:32 +0100
Subject: drm/i915: Refactor unsettting obj->mm.pages

As i915_gem_object_phys_attach() wants to play dirty and mess around
with obj->mm.pages itself (replacing the shmemfs with a DMA allocation),
refactor the gubbins so into i915_gem_object_unset_pages() that we don't
have to duplicate all the secrets.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611075532.26534-1-chris@chris-wilson.co.uk
Link: https://patchwork.freedesktop.org/patch/msgid/152871104647.1718.8796913290418060204@jlahtine-desk.ger.corp.intel.com
---
 drivers/gpu/drm/i915/i915_gem.c | 68 ++++++++++++++++++++++-------------------
 1 file changed, 37 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0f28b5ddfd15..93efd92362db 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2401,29 +2401,15 @@ static void __i915_gem_object_reset_page_iter(struct drm_i915_gem_object *obj)
 	rcu_read_unlock();
 }
 
-void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
-				 enum i915_mm_subclass subclass)
+static struct sg_table *
+__i915_gem_object_unset_pages(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_private *i915 = to_i915(obj->base.dev);
 	struct sg_table *pages;
 
-	if (i915_gem_object_has_pinned_pages(obj))
-		return;
-
-	GEM_BUG_ON(obj->bind_count);
-	if (!i915_gem_object_has_pages(obj))
-		return;
-
-	/* May be called by shrinker from within get_pages() (on another bo) */
-	mutex_lock_nested(&obj->mm.lock, subclass);
-	if (unlikely(atomic_read(&obj->mm.pages_pin_count)))
-		goto unlock;
-
-	/* ->put_pages might need to allocate memory for the bit17 swizzle
-	 * array, hence protect them from being reaped by removing them from gtt
-	 * lists early. */
 	pages = fetch_and_zero(&obj->mm.pages);
-	GEM_BUG_ON(!pages);
+	if (!pages)
+		return NULL;
 
 	spin_lock(&i915->mm.obj_lock);
 	list_del(&obj->mm.link);
@@ -2442,12 +2428,37 @@ void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
 	}
 
 	__i915_gem_object_reset_page_iter(obj);
+	obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0;
+
+	return pages;
+}
 
+void __i915_gem_object_put_pages(struct drm_i915_gem_object *obj,
+				 enum i915_mm_subclass subclass)
+{
+	struct sg_table *pages;
+
+	if (i915_gem_object_has_pinned_pages(obj))
+		return;
+
+	GEM_BUG_ON(obj->bind_count);
+	if (!i915_gem_object_has_pages(obj))
+		return;
+
+	/* May be called by shrinker from within get_pages() (on another bo) */
+	mutex_lock_nested(&obj->mm.lock, subclass);
+	if (unlikely(atomic_read(&obj->mm.pages_pin_count)))
+		goto unlock;
+
+	/*
+	 * ->put_pages might need to allocate memory for the bit17 swizzle
+	 * array, hence protect them from being reaped by removing them from gtt
+	 * lists early.
+	 */
+	pages = __i915_gem_object_unset_pages(obj);
 	if (!IS_ERR(pages))
 		obj->ops->put_pages(obj, pages);
 
-	obj->mm.page_sizes.phys = obj->mm.page_sizes.sg = 0;
-
 unlock:
 	mutex_unlock(&obj->mm.lock);
 }
@@ -6089,16 +6100,7 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 		goto err_unlock;
 	}
 
-	pages = fetch_and_zero(&obj->mm.pages);
-	if (pages) {
-		struct drm_i915_private *i915 = to_i915(obj->base.dev);
-
-		__i915_gem_object_reset_page_iter(obj);
-
-		spin_lock(&i915->mm.obj_lock);
-		list_del(&obj->mm.link);
-		spin_unlock(&i915->mm.obj_lock);
-	}
+	pages = __i915_gem_object_unset_pages(obj);
 
 	obj->ops = &i915_gem_phys_ops;
 
@@ -6116,7 +6118,11 @@ int i915_gem_object_attach_phys(struct drm_i915_gem_object *obj, int align)
 
 err_xfer:
 	obj->ops = &i915_gem_object_ops;
-	obj->mm.pages = pages;
+	if (!IS_ERR_OR_NULL(pages)) {
+		unsigned int sg_page_sizes = i915_sg_page_sizes(pages->sgl);
+
+		__i915_gem_object_set_pages(obj, pages, sg_page_sizes);
+	}
 err_unlock:
 	mutex_unlock(&obj->mm.lock);
 	return err;
-- 
cgit v1.2.3


From 746c8f143afad7aaa66c484485fc39888d437a3f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sun, 10 Jun 2018 20:43:09 +0100
Subject: drm/i915: Apply batch location restrictions before pinning

We special case the position of the batch within the GTT to prevent
negative self-relocation deltas from underflowing. However, that
restriction is being applied after a trial pin of the batch in its
current position. Thus we are not rejecting an invalid location if the
batch has been used before, leading to an assertion if we happen to need
to rearrange the entire payload. In the worst case, this may cause a GPU
hang on gen7 or perhaps missing state.

References: https://bugs.freedesktop.org/show_bug.cgi?id=105720
Fixes: 2889caa92321 ("drm/i915: Eliminate lots of iterations over the execobjects array")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Martin Peres <martin.peres@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180610194325.13467-2-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 49 ++++++++++++++++--------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index eefd449502e2..2d2eb3075960 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -489,7 +489,9 @@ eb_validate_vma(struct i915_execbuffer *eb,
 }
 
 static int
-eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma)
+eb_add_vma(struct i915_execbuffer *eb,
+	   unsigned int i, unsigned batch_idx,
+	   struct i915_vma *vma)
 {
 	struct drm_i915_gem_exec_object2 *entry = &eb->exec[i];
 	int err;
@@ -522,6 +524,24 @@ eb_add_vma(struct i915_execbuffer *eb, unsigned int i, struct i915_vma *vma)
 	eb->flags[i] = entry->flags;
 	vma->exec_flags = &eb->flags[i];
 
+	/*
+	 * SNA is doing fancy tricks with compressing batch buffers, which leads
+	 * to negative relocation deltas. Usually that works out ok since the
+	 * relocate address is still positive, except when the batch is placed
+	 * very low in the GTT. Ensure this doesn't happen.
+	 *
+	 * Note that actual hangs have only been observed on gen7, but for
+	 * paranoia do it everywhere.
+	 */
+	if (i == batch_idx) {
+		if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
+			eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
+		if (eb->reloc_cache.has_fence)
+			eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
+
+		eb->batch = vma;
+	}
+
 	err = 0;
 	if (eb_pin_vma(eb, entry, vma)) {
 		if (entry->offset != vma->node.start) {
@@ -716,7 +736,7 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 {
 	struct radix_tree_root *handles_vma = &eb->ctx->handles_vma;
 	struct drm_i915_gem_object *obj;
-	unsigned int i;
+	unsigned int i, batch;
 	int err;
 
 	if (unlikely(i915_gem_context_is_closed(eb->ctx)))
@@ -728,6 +748,8 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 	INIT_LIST_HEAD(&eb->relocs);
 	INIT_LIST_HEAD(&eb->unbound);
 
+	batch = eb_batch_index(eb);
+
 	for (i = 0; i < eb->buffer_count; i++) {
 		u32 handle = eb->exec[i].handle;
 		struct i915_lut_handle *lut;
@@ -770,33 +792,16 @@ static int eb_lookup_vmas(struct i915_execbuffer *eb)
 		lut->handle = handle;
 
 add_vma:
-		err = eb_add_vma(eb, i, vma);
+		err = eb_add_vma(eb, i, batch, vma);
 		if (unlikely(err))
 			goto err_vma;
 
 		GEM_BUG_ON(vma != eb->vma[i]);
 		GEM_BUG_ON(vma->exec_flags != &eb->flags[i]);
+		GEM_BUG_ON(drm_mm_node_allocated(&vma->node) &&
+			   eb_vma_misplaced(&eb->exec[i], vma, eb->flags[i]));
 	}
 
-	/* take note of the batch buffer before we might reorder the lists */
-	i = eb_batch_index(eb);
-	eb->batch = eb->vma[i];
-	GEM_BUG_ON(eb->batch->exec_flags != &eb->flags[i]);
-
-	/*
-	 * SNA is doing fancy tricks with compressing batch buffers, which leads
-	 * to negative relocation deltas. Usually that works out ok since the
-	 * relocate address is still positive, except when the batch is placed
-	 * very low in the GTT. Ensure this doesn't happen.
-	 *
-	 * Note that actual hangs have only been observed on gen7, but for
-	 * paranoia do it everywhere.
-	 */
-	if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
-		eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
-	if (eb->reloc_cache.has_fence)
-		eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
-
 	eb->args->flags |= __EXEC_VALIDATED;
 	return eb_reserve(eb);
 
-- 
cgit v1.2.3


From 9904b1560e4a2e7c956004f9843939e23d84cd7b Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Mon, 4 Jun 2018 16:32:49 -0700
Subject: drm/i915/perf: use the lrc_desc to get the ctx hw id in gen8-10

The upper 32 bits of the lrc_desc (bits 52-32 to be precise) are the
context hw id in GEN8-10, so use them and have one less thing to
maintain in the unlikely case we change the descriptor sw fields.

v2: If we use the lrc_desc, we must apply the ctx_id_mask too (Lionel)

Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604233250.609-1-michel.thierry@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index a6c8d61add0c..6aba30cb40ea 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1279,9 +1279,12 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 			i915->perf.oa.specific_ctx_id_mask =
 				(1U << (GEN8_CTX_ID_WIDTH - 1)) - 1;
 		} else {
-			i915->perf.oa.specific_ctx_id = stream->ctx->hw_id;
 			i915->perf.oa.specific_ctx_id_mask =
 				(1U << GEN8_CTX_ID_WIDTH) - 1;
+			i915->perf.oa.specific_ctx_id =
+				upper_32_bits(ce->lrc_desc);
+			i915->perf.oa.specific_ctx_id &=
+				i915->perf.oa.specific_ctx_id_mask;
 		}
 		break;
 
-- 
cgit v1.2.3


From 2b9a820318ebdf81f666be4daf7414d98123fefb Mon Sep 17 00:00:00 2001
From: Michel Thierry <michel.thierry@intel.com>
Date: Mon, 4 Jun 2018 16:32:50 -0700
Subject: drm/i915/perf: fix gen11 engine class shift

Use the correct engine class shift value while storing the ctx hw id.
Fixes the copy+paste error from commit 61d5676b5561 ("drm/i915/perf: fix
ctx_id read with GuC & ICL").

Apologies for not spotting this in the original review, the
specific_ctx_id_mask is correct, only the specific_ctx_id had this
problem.

v2: Just use the upper 32 bits of lrc_desc (Chris)
v3: If we use the lrc_desc, we must apply the ctx_id_mask too (Lionel)

Fixes: 61d5676b5561 ("drm/i915/perf: fix ctx_id read with GuC & ICL")
Signed-off-by: Michel Thierry <michel.thierry@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: intel-gfx@lists.freedesktop.org
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604233250.609-2-michel.thierry@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 6aba30cb40ea..881a992305ec 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1289,16 +1289,13 @@ static int oa_get_render_ctx_id(struct i915_perf_stream *stream)
 		break;
 
 	case 11: {
-		struct intel_engine_cs *engine = i915->engine[RCS];
-
-		i915->perf.oa.specific_ctx_id =
-			stream->ctx->hw_id << (GEN11_SW_CTX_ID_SHIFT - 32) |
-			engine->instance << (GEN11_ENGINE_INSTANCE_SHIFT - 32) |
-			engine->class << (GEN11_ENGINE_INSTANCE_SHIFT - 32);
 		i915->perf.oa.specific_ctx_id_mask =
 			((1U << GEN11_SW_CTX_ID_WIDTH) - 1) << (GEN11_SW_CTX_ID_SHIFT - 32) |
 			((1U << GEN11_ENGINE_INSTANCE_WIDTH) - 1) << (GEN11_ENGINE_INSTANCE_SHIFT - 32) |
 			((1 << GEN11_ENGINE_CLASS_WIDTH) - 1) << (GEN11_ENGINE_CLASS_SHIFT - 32);
+		i915->perf.oa.specific_ctx_id = upper_32_bits(ce->lrc_desc);
+		i915->perf.oa.specific_ctx_id &=
+			i915->perf.oa.specific_ctx_id_mask;
 		break;
 	}
 
-- 
cgit v1.2.3


From 602a9de513d5a43ecaf7d0443eca41656165d3c4 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 8 Jun 2018 17:41:37 +0300
Subject: drm/i915/skl: Add warn about unsupported CDCLK rates
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While checking workarounds related to the CDCLK PLL, I noticed that the
DMC firmware bits for WA#1183 are missing for SKL. After that I
clarified with HW people that it's not needed on SKL, since it doesn't
support eDP1.4 which would be the only thing requiring the problematic
CDCLK clock rates. So in theory we shouldn't ever choose these
frequencies, but add an assert in any case for catching such cases and
for documentation.

v2:
- Move the check to skl_set_cdclk and warn whenever using the
  corresponding VCO freq. (Ville)

v3:
- Actually check for the platform. (Ville)

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180608144137.7943-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_cdclk.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 704ddb4d3ca7..8ed7bd052e46 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -991,6 +991,16 @@ static void skl_set_cdclk(struct drm_i915_private *dev_priv,
 	u32 freq_select, cdclk_ctl;
 	int ret;
 
+	/*
+	 * Based on WA#1183 CDCLK rates 308 and 617MHz CDCLK rates are
+	 * unsupported on SKL. In theory this should never happen since only
+	 * the eDP1.4 2.16 and 4.32Gbps rates require it, but eDP1.4 is not
+	 * supported on SKL either, see the above WA. WARN whenever trying to
+	 * use the corresponding VCO freq as that always leads to using the
+	 * minimum 308MHz CDCLK.
+	 */
+	WARN_ON_ONCE(IS_SKYLAKE(dev_priv) && vco == 8640000);
+
 	mutex_lock(&dev_priv->pcu_lock);
 	ret = skl_pcode_request(dev_priv, SKL_PCODE_CDCLK_CONTROL,
 				SKL_CDCLK_PREPARE_FOR_CHANGE,
-- 
cgit v1.2.3


From 1fc719d13ac07b082ff9daa8f40254680cade111 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Jun 2018 11:48:08 +0100
Subject: drm/i915/ringbuffer: Brute force context restore

An issue encountered with switching mm on gen7 is that the GPU likes to
hang (with the VS unit busy) when told to force restore the current
context. We can simply workaround this by substituting the
MI_FORCE_RESTORE flag with a round-trip through the kernel_context,
forcing the context to be saved and restored; thereby reloading the
PP_DIR registers and updating the modified page directory!

v2: Undo attempted optimisation in caller (Tvrtko)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611104808.24295-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_ringbuffer.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 6496c1d00dbb..5bc53a5f4504 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1456,6 +1456,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 		(HAS_LEGACY_SEMAPHORES(i915) && IS_GEN7(i915)) ?
 		INTEL_INFO(i915)->num_rings - 1 :
 		0;
+	bool force_restore = false;
 	int len;
 	u32 *cs;
 
@@ -1469,6 +1470,12 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 	len = 4;
 	if (IS_GEN7(i915))
 		len += 2 + (num_rings ? 4*num_rings + 6 : 0);
+	if (flags & MI_FORCE_RESTORE) {
+		GEM_BUG_ON(flags & MI_RESTORE_INHIBIT);
+		flags &= ~MI_FORCE_RESTORE;
+		force_restore = true;
+		len += 2;
+	}
 
 	cs = intel_ring_begin(rq, len);
 	if (IS_ERR(cs))
@@ -1493,6 +1500,26 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags)
 		}
 	}
 
+	if (force_restore) {
+		/*
+		 * The HW doesn't handle being told to restore the current
+		 * context very well. Quite often it likes goes to go off and
+		 * sulk, especially when it is meant to be reloading PP_DIR.
+		 * A very simple fix to force the reload is to simply switch
+		 * away from the current context and back again.
+		 *
+		 * Note that the kernel_context will contain random state
+		 * following the INHIBIT_RESTORE. We accept this since we
+		 * never use the kernel_context state; it is merely a
+		 * placeholder we use to flush other contexts.
+		 */
+		*cs++ = MI_SET_CONTEXT;
+		*cs++ = i915_ggtt_offset(to_intel_context(i915->kernel_context,
+							  engine)->state) |
+			MI_MM_SPACE_GTT |
+			MI_RESTORE_INHIBIT;
+	}
+
 	*cs++ = MI_NOOP;
 	*cs++ = MI_SET_CONTEXT;
 	*cs++ = i915_ggtt_offset(rq->hw_context->state) | flags;
-- 
cgit v1.2.3


From b3ee09a4de33259a89d30aca6b2ebb0bc26640af Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Jun 2018 12:08:44 +0100
Subject: drm/i915/ringbuffer: Fix context restore upon reset

The discovery with trying to enable full-ppgtt was that we were
completely failing to the load both the mm and context following the
reset. Although we were performing mmio to set the PP_DIR (per-process
GTT) and CCID (context), these were taking no effect (the assumption was
that this would trigger reload of the context and restore the page
tables). It was not until we performed the LRI + MI_SET_CONTEXT in a
following context switch would anything occur.

Since we are then required to reset the context image and PP_DIR using
CS commands, we place those commands into every batch. The hardware
should recognise the no-ops and eliminate the expensive context loads,
but we still have to pay the cost of using cross-powerwell register
writes. In practice, this has no effect on actual context switch times,
and only adds a few hundred nanoseconds to no-op switches. We can improve
the latter by eliminating the w/a around known no-op switches, but there
is an ulterior motive to keeping them.

Always emitting the context switch at the beginning of the request (and
relying on HW to skip unneeded switches) does have one key advantage.
Should we implement request reordering on Haswell, we will not know in
advance what the previous executing context was on the GPU and so we
would not be able to elide the MI_SET_CONTEXT commands ourselves and
always have to emit them. Having our hand forced now actually prepares
us for later.

Now since that context and mm follow the request, we no longer (and not
for a long time since requests took over!) require a trace point to tell
when we write the switch into the ring, since it is always. (This is
even more important when you remember that simply writing into the ring
bears no relation to the current mm.)

v2: Sandybridge has to agree to use LRI as well.

Testcase: igt/drv_selftests/live_hangcheck
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611110845.31890-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c     |  45 ------------
 drivers/gpu/drm/i915/i915_gem_gtt.h     |   2 -
 drivers/gpu/drm/i915/i915_request.c     |   2 +
 drivers/gpu/drm/i915/i915_request.h     |   3 +
 drivers/gpu/drm/i915/i915_trace.h       |  33 ---------
 drivers/gpu/drm/i915/intel_engine_cs.c  |   3 -
 drivers/gpu/drm/i915/intel_ringbuffer.c | 125 ++++++++++++++++----------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |   9 ---
 8 files changed, 66 insertions(+), 156 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 7ccfdbc8f9b4..ac75e0c5735c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1712,45 +1712,6 @@ static void gen6_write_page_range(struct i915_hw_ppgtt *ppgtt,
 	wmb();
 }
 
-static inline u32 get_pd_offset(struct i915_hw_ppgtt *ppgtt)
-{
-	GEM_BUG_ON(ppgtt->pd.base.ggtt_offset & 0x3f);
-	return ppgtt->pd.base.ggtt_offset << 10;
-}
-
-static int gen7_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct i915_request *rq)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	u32 *cs;
-
-	/* NB: TLBs must be flushed and invalidated before a switch */
-	cs = intel_ring_begin(rq, 6);
-	if (IS_ERR(cs))
-		return PTR_ERR(cs);
-
-	*cs++ = MI_LOAD_REGISTER_IMM(2);
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine));
-	*cs++ = PP_DIR_DCLV_2G;
-	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
-	*cs++ = get_pd_offset(ppgtt);
-	*cs++ = MI_NOOP;
-	intel_ring_advance(rq, cs);
-
-	return 0;
-}
-
-static int gen6_mm_switch(struct i915_hw_ppgtt *ppgtt,
-			  struct i915_request *rq)
-{
-	struct intel_engine_cs *engine = rq->engine;
-	struct drm_i915_private *dev_priv = rq->i915;
-
-	I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
-	I915_WRITE(RING_PP_DIR_BASE(engine), get_pd_offset(ppgtt));
-	return 0;
-}
-
 static void gen8_ppgtt_enable(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
@@ -2024,12 +1985,6 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt->vm.dma = &i915->drm.pdev->dev;
 
 	ppgtt->vm.pte_encode = ggtt->vm.pte_encode;
-	if (IS_GEN6(i915))
-		ppgtt->switch_mm = gen6_mm_switch;
-	else if (IS_GEN7(i915))
-		ppgtt->switch_mm = gen7_mm_switch;
-	else
-		BUG();
 
 	err = gen6_ppgtt_alloc(ppgtt);
 	if (err)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 16307ba7e303..e70f6abcd0f2 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -406,8 +406,6 @@ struct i915_hw_ppgtt {
 
 	gen6_pte_t __iomem *pd_addr;
 
-	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
-			 struct i915_request *rq);
 	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
 };
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index f187250e60c6..9092f5464c24 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -817,6 +817,8 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 	/* Keep a second pin for the dual retirement along engine and ring */
 	__intel_context_pin(ce);
 
+	rq->infix = rq->ring->emit; /* end of header; start of user payload */
+
 	/* Check that we didn't interrupt ourselves with a new request */
 	GEM_BUG_ON(rq->timeline->seqno != rq->fence.seqno);
 	return rq;
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 491ff81d0fea..0e9aba53d0e4 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -134,6 +134,9 @@ struct i915_request {
 	/** Position in the ring of the start of the request */
 	u32 head;
 
+	/** Position in the ring of the start of the user packets */
+	u32 infix;
+
 	/**
 	 * Position in the ring of the start of the postfix.
 	 * This is required to calculate the maximum available ring space
diff --git a/drivers/gpu/drm/i915/i915_trace.h b/drivers/gpu/drm/i915/i915_trace.h
index 1472f48ab2e8..b50c6b829715 100644
--- a/drivers/gpu/drm/i915/i915_trace.h
+++ b/drivers/gpu/drm/i915/i915_trace.h
@@ -973,39 +973,6 @@ DEFINE_EVENT(i915_context, i915_context_free,
 	TP_ARGS(ctx)
 );
 
-/**
- * DOC: switch_mm tracepoint
- *
- * This tracepoint allows tracking of the mm switch, which is an important point
- * in the lifetime of the vm in the legacy submission path. This tracepoint is
- * called only if full ppgtt is enabled.
- */
-TRACE_EVENT(switch_mm,
-	TP_PROTO(struct intel_engine_cs *engine, struct i915_gem_context *to),
-
-	TP_ARGS(engine, to),
-
-	TP_STRUCT__entry(
-			__field(u16, class)
-			__field(u16, instance)
-			__field(struct i915_gem_context *, to)
-			__field(struct i915_address_space *, vm)
-			__field(u32, dev)
-	),
-
-	TP_fast_assign(
-			__entry->class = engine->uabi_class;
-			__entry->instance = engine->instance;
-			__entry->to = to;
-			__entry->vm = to->ppgtt ? &to->ppgtt->vm : NULL;
-			__entry->dev = engine->i915->drm.primary->index;
-	),
-
-	TP_printk("dev=%u, engine=%u:%u, ctx=%p, ctx_vm=%p",
-		  __entry->dev, __entry->class, __entry->instance, __entry->to,
-		  __entry->vm)
-);
-
 #endif /* _I915_TRACE_H_ */
 
 /* This part must be outside protection */
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 2ec2e60dc670..d1cf8b4926ab 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1168,9 +1168,6 @@ void intel_engine_lost_context(struct intel_engine_cs *engine)
 
 	lockdep_assert_held(&engine->i915->drm.struct_mutex);
 
-	engine->legacy_active_context = NULL;
-	engine->legacy_active_ppgtt = NULL;
-
 	ce = fetch_and_zero(&engine->last_retired_context);
 	if (ce)
 		intel_context_unpin(ce);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 5bc53a5f4504..d72a6a5ff3ac 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -541,11 +541,23 @@ static struct i915_request *reset_prepare(struct intel_engine_cs *engine)
 	return i915_gem_find_active_request(engine);
 }
 
-static void reset_ring(struct intel_engine_cs *engine,
-		       struct i915_request *request)
+static void skip_request(struct i915_request *rq)
 {
-	GEM_TRACE("%s seqno=%x\n",
-		  engine->name, request ? request->global_seqno : 0);
+	void *vaddr = rq->ring->vaddr;
+	u32 head;
+
+	head = rq->infix;
+	if (rq->postfix < head) {
+		memset32(vaddr + head, MI_NOOP,
+			 (rq->ring->size - head) / sizeof(u32));
+		head = 0;
+	}
+	memset32(vaddr + head, MI_NOOP, (rq->postfix - head) / sizeof(u32));
+}
+
+static void reset_ring(struct intel_engine_cs *engine, struct i915_request *rq)
+{
+	GEM_TRACE("%s seqno=%x\n", engine->name, rq ? rq->global_seqno : 0);
 
 	/*
 	 * RC6 must be prevented until the reset is complete and the engine
@@ -569,43 +581,11 @@ static void reset_ring(struct intel_engine_cs *engine,
 	 * If the request was innocent, we try to replay the request with
 	 * the restored context.
 	 */
-	if (request) {
-		struct drm_i915_private *dev_priv = request->i915;
-		struct intel_context *ce = request->hw_context;
-		struct i915_hw_ppgtt *ppgtt;
-
-		if (ce->state) {
-			I915_WRITE(CCID,
-				   i915_ggtt_offset(ce->state) |
-				   BIT(8) /* must be set! */ |
-				   CCID_EXTENDED_STATE_SAVE |
-				   CCID_EXTENDED_STATE_RESTORE |
-				   CCID_EN);
-		}
-
-		ppgtt = request->gem_context->ppgtt ?: engine->i915->mm.aliasing_ppgtt;
-		if (ppgtt) {
-			u32 pd_offset = ppgtt->pd.base.ggtt_offset << 10;
-
-			I915_WRITE(RING_PP_DIR_DCLV(engine), PP_DIR_DCLV_2G);
-			I915_WRITE(RING_PP_DIR_BASE(engine), pd_offset);
-
-			/* Wait for the PD reload to complete */
-			if (intel_wait_for_register(dev_priv,
-						    RING_PP_DIR_BASE(engine),
-						    BIT(0), 0,
-						    10))
-				DRM_ERROR("Wait for reload of ppgtt page-directory timed out\n");
-
-			ppgtt->pd_dirty_rings &= ~intel_engine_flag(engine);
-		}
-
+	if (rq) {
 		/* If the rq hung, jump to its breadcrumb and skip the batch */
-		if (request->fence.error == -EIO)
-			request->ring->head = request->postfix;
-	} else {
-		engine->legacy_active_context = NULL;
-		engine->legacy_active_ppgtt = NULL;
+		rq->ring->head = intel_ring_wrap(rq->ring, rq->head);
+		if (rq->fence.error == -EIO)
+			skip_request(rq);
 	}
 }
 
@@ -1446,6 +1426,29 @@ void intel_legacy_submission_resume(struct drm_i915_private *dev_priv)
 		intel_ring_reset(engine->buffer, 0);
 }
 
+static int load_pd_dir(struct i915_request *rq,
+		       const struct i915_hw_ppgtt *ppgtt)
+{
+	const struct intel_engine_cs * const engine = rq->engine;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 6);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_DCLV(engine));
+	*cs++ = PP_DIR_DCLV_2G;
+
+	*cs++ = MI_LOAD_REGISTER_IMM(1);
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
+	*cs++ = ppgtt->pd.base.ggtt_offset << 10;
+
+	intel_ring_advance(rq, cs);
+
+	return 0;
+}
+
 static inline int mi_set_context(struct i915_request *rq, u32 flags)
 {
 	struct drm_i915_private *i915 = rq->i915;
@@ -1590,31 +1593,28 @@ static int remap_l3(struct i915_request *rq, int slice)
 static int switch_context(struct i915_request *rq)
 {
 	struct intel_engine_cs *engine = rq->engine;
-	struct i915_gem_context *to_ctx = rq->gem_context;
-	struct i915_hw_ppgtt *to_mm =
-		to_ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
-	struct i915_gem_context *from_ctx = engine->legacy_active_context;
-	struct i915_hw_ppgtt *from_mm = engine->legacy_active_ppgtt;
+	struct i915_gem_context *ctx = rq->gem_context;
+	struct i915_hw_ppgtt *ppgtt = ctx->ppgtt ?: rq->i915->mm.aliasing_ppgtt;
+	unsigned int unwind_mm = 0;
 	u32 hw_flags = 0;
 	int ret, i;
 
 	lockdep_assert_held(&rq->i915->drm.struct_mutex);
 	GEM_BUG_ON(HAS_EXECLISTS(rq->i915));
 
-	if (to_mm != from_mm ||
-	    (to_mm && intel_engine_flag(engine) & to_mm->pd_dirty_rings)) {
-		trace_switch_mm(engine, to_ctx);
-		ret = to_mm->switch_mm(to_mm, rq);
+	if (ppgtt) {
+		ret = load_pd_dir(rq, ppgtt);
 		if (ret)
 			goto err;
 
-		to_mm->pd_dirty_rings &= ~intel_engine_flag(engine);
-		engine->legacy_active_ppgtt = to_mm;
-		hw_flags = MI_FORCE_RESTORE;
+		if (intel_engine_flag(engine) & ppgtt->pd_dirty_rings) {
+			unwind_mm = intel_engine_flag(engine);
+			ppgtt->pd_dirty_rings &= ~unwind_mm;
+			hw_flags = MI_FORCE_RESTORE;
+		}
 	}
 
-	if (rq->hw_context->state &&
-	    (to_ctx != from_ctx || hw_flags & MI_FORCE_RESTORE)) {
+	if (rq->hw_context->state) {
 		GEM_BUG_ON(engine->id != RCS);
 
 		/*
@@ -1624,35 +1624,32 @@ static int switch_context(struct i915_request *rq)
 		 * as nothing actually executes using the kernel context; it
 		 * is purely used for flushing user contexts.
 		 */
-		if (i915_gem_context_is_kernel(to_ctx))
+		if (i915_gem_context_is_kernel(ctx))
 			hw_flags = MI_RESTORE_INHIBIT;
 
 		ret = mi_set_context(rq, hw_flags);
 		if (ret)
 			goto err_mm;
-
-		engine->legacy_active_context = to_ctx;
 	}
 
-	if (to_ctx->remap_slice) {
+	if (ctx->remap_slice) {
 		for (i = 0; i < MAX_L3_SLICES; i++) {
-			if (!(to_ctx->remap_slice & BIT(i)))
+			if (!(ctx->remap_slice & BIT(i)))
 				continue;
 
 			ret = remap_l3(rq, i);
 			if (ret)
-				goto err_ctx;
+				goto err_mm;
 		}
 
-		to_ctx->remap_slice = 0;
+		ctx->remap_slice = 0;
 	}
 
 	return 0;
 
-err_ctx:
-	engine->legacy_active_context = from_ctx;
 err_mm:
-	engine->legacy_active_ppgtt = from_mm;
+	if (unwind_mm)
+		ppgtt->pd_dirty_rings |= unwind_mm;
 err:
 	return ret;
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index acef385c4c80..b44c67849749 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -557,15 +557,6 @@ struct intel_engine_cs {
 	 */
 	struct intel_context *last_retired_context;
 
-	/* We track the current MI_SET_CONTEXT in order to eliminate
-	 * redudant context switches. This presumes that requests are not
-	 * reordered! Or when they are the tracking is updated along with
-	 * the emission of individual requests into the legacy command
-	 * stream (ring).
-	 */
-	struct i915_gem_context *legacy_active_context;
-	struct i915_hw_ppgtt *legacy_active_ppgtt;
-
 	/* status_notifier: list of callbacks for context-switch changes */
 	struct atomic_notifier_head context_status_notifier;
 
-- 
cgit v1.2.3


From 41d37680ca0b157ad1ed29409bcdc2b0bc21d11f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Jun 2018 12:08:45 +0100
Subject: drm/i915: Wrap around the tail offset before setting ring->tail

The HW only accepts offsets within ring->size, and fails peculiarly if
the RING_HEAD or RING_TAIL is set to ring->size. Therefore whenever we
set ring->head/ring->tail we want to make sure it is within value (using
intel_ring_wrap()).

v2: Double check execlists as well
v3: Remove redundancy with assert_ring_tail_valid()
v4: Just assert in intel_ring_reset() rather than be over-defensive.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> #v2
Link: https://patchwork.freedesktop.org/patch/msgid/20180611110845.31890-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c        |  6 ++++--
 drivers/gpu/drm/i915/intel_ringbuffer.c |  6 ++++++
 drivers/gpu/drm/i915/intel_ringbuffer.h | 20 ++++++++++++++------
 3 files changed, 24 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0935a19aca96..3401889e5121 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1414,6 +1414,7 @@ __execlists_context_pin(struct intel_engine_cs *engine,
 	ce->lrc_reg_state = vaddr + LRC_STATE_PN * PAGE_SIZE;
 	ce->lrc_reg_state[CTX_RING_BUFFER_START+1] =
 		i915_ggtt_offset(ce->ring->vma);
+	GEM_BUG_ON(!intel_ring_offset_valid(ce->ring, ce->ring->head));
 	ce->lrc_reg_state[CTX_RING_HEAD+1] = ce->ring->head;
 
 	ce->state->obj->pin_global++;
@@ -2002,9 +2003,10 @@ static void execlists_reset(struct intel_engine_cs *engine,
 
 	/* Move the RING_HEAD onto the breadcrumb, past the hanging batch */
 	regs[CTX_RING_BUFFER_START + 1] = i915_ggtt_offset(request->ring->vma);
-	regs[CTX_RING_HEAD + 1] = request->postfix;
 
-	request->ring->head = request->postfix;
+	request->ring->head = intel_ring_wrap(request->ring, request->postfix);
+	regs[CTX_RING_HEAD + 1] = request->ring->head;
+
 	intel_ring_update_space(request->ring);
 
 	/* Reset WaIdleLiteRestore:bdw,skl as well */
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d72a6a5ff3ac..bb4af8f84a22 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -496,6 +496,10 @@ static int init_ring_common(struct intel_engine_cs *engine)
 		DRM_DEBUG_DRIVER("%s initialization failed [head=%08x], fudging\n",
 				 engine->name, I915_READ_HEAD(engine));
 
+	/* Check that the ring offsets point within the ring! */
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->head));
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, ring->tail));
+
 	intel_ring_update_space(ring);
 	I915_WRITE_HEAD(engine, ring->head);
 	I915_WRITE_TAIL(engine, ring->tail);
@@ -1062,6 +1066,8 @@ err:
 
 void intel_ring_reset(struct intel_ring *ring, u32 tail)
 {
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
+
 	ring->tail = tail;
 	ring->head = tail;
 	ring->emit = tail;
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index b44c67849749..e9494557aaa1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -805,6 +805,19 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
 	return pos & (ring->size - 1);
 }
 
+static inline bool
+intel_ring_offset_valid(const struct intel_ring *ring,
+			unsigned int pos)
+{
+	if (pos & -ring->size) /* must be strictly within the ring */
+		return false;
+
+	if (!IS_ALIGNED(pos, 8)) /* must be qword aligned */
+		return false;
+
+	return true;
+}
+
 static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
 {
 	/* Don't write ring->size (equivalent to 0) as that hangs some GPUs. */
@@ -816,12 +829,7 @@ static inline u32 intel_ring_offset(const struct i915_request *rq, void *addr)
 static inline void
 assert_ring_tail_valid(const struct intel_ring *ring, unsigned int tail)
 {
-	/* We could combine these into a single tail operation, but keeping
-	 * them as seperate tests will help identify the cause should one
-	 * ever fire.
-	 */
-	GEM_BUG_ON(!IS_ALIGNED(tail, 8));
-	GEM_BUG_ON(tail >= ring->size);
+	GEM_BUG_ON(!intel_ring_offset_valid(ring, tail));
 
 	/*
 	 * "Ring Buffer Use"
-- 
cgit v1.2.3


From 467d35789e5a4f47428b65ef711b30fdabbb0fd4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Jun 2018 16:33:32 +0100
Subject: drm/i915/execlists: Avoid putting the error pointer

On allocation error, do not jump to the unwind handler that tries to
free the error pointer.

Reported-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: a89d1f921c15 ("drm/i915: Split i915_gem_timeline into individual timelines")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611153332.14824-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 3401889e5121..44e4c9e07571 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2771,10 +2771,8 @@ static int execlists_context_deferred_alloc(struct i915_gem_context *ctx,
 	context_size += LRC_HEADER_PAGES * PAGE_SIZE;
 
 	ctx_obj = i915_gem_object_create(ctx->i915, context_size);
-	if (IS_ERR(ctx_obj)) {
-		ret = PTR_ERR(ctx_obj);
-		goto error_deref_obj;
-	}
+	if (IS_ERR(ctx_obj))
+		return PTR_ERR(ctx_obj);
 
 	vma = i915_vma_instance(ctx_obj, &ctx->i915->ggtt.vm, NULL);
 	if (IS_ERR(vma)) {
-- 
cgit v1.2.3


From 06168448733a82da165981115d61b5d2faa82761 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:33 +0300
Subject: drm/vmwgfx: Stop using plane->fb in vmw_kms_atomic_check_modeset()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of looking at plane->fb let's look at the proper new
plane state.

Not that the code makes a ton of sense. It's only going through the
crtcs in the atomic state, so assuming not all of them are included
we're not even calculating the total bandwidth here. Also we're
not considering whether each crtc is actually enabled or not.

Cc: Deepak Rawat <drawat@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-2-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 6728c6247b4b..a2a796b4cc23 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1536,9 +1536,13 @@ vmw_kms_atomic_check_modeset(struct drm_device *dev,
 		unsigned long requested_bb_mem = 0;
 
 		if (dev_priv->active_display_unit == vmw_du_screen_target) {
-			if (crtc->primary->fb) {
-				int cpp = crtc->primary->fb->pitches[0] /
-					  crtc->primary->fb->width;
+			struct drm_plane *plane = crtc->primary;
+			struct drm_plane_state *plane_state;
+
+			plane_state = drm_atomic_get_new_plane_state(state, plane);
+
+			if (plane_state && plane_state->fb) {
+				int cpp = plane_state->fb->format->cpp[0];
 
 				requested_bb_mem += crtc->mode.hdisplay * cpp *
 						    crtc->mode.vdisplay;
-- 
cgit v1.2.3


From 464ce098e69cf886ce99a08cb3ebf5f8c53820b5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:34 +0300
Subject: drm/vmwgfx: Stop using plane->fb in vmw_kms_helper_dirty()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of plane->fb (which we're going to deprecate for atomic drivers)
we need to look at plane->state->fb. The maze of code leading to
vmw_kms_helper_dirty() wasn't particularly clear, but my analysis
concluded that the calls originating from vmw_*_primary_plane_atomic_update()
all pass in the crtc which means we'll never end up in this branch
of the function. All other callers use drm_modeset_lock_all() somewhere
higher up, which means accessing plane->state is safe.

v2: Drop the comment and make the code do what it did before (Thomas)
v3: Drop the bogus lockdep assert

Cc: Deepak Rawat <drawat@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-3-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index a2a796b4cc23..146ea18d765e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2326,9 +2326,10 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 	} else {
 		list_for_each_entry(crtc, &dev_priv->dev->mode_config.crtc_list,
 				    head) {
-			if (crtc->primary->fb != &framebuffer->base)
-				continue;
-			units[num_units++] = vmw_crtc_to_du(crtc);
+			struct drm_plane *plane = crtc->primary;
+
+			if (plane->state->fb == &framebuffer->base)
+				units[num_units++] = vmw_crtc_to_du(crtc);
 		}
 	}
 
-- 
cgit v1.2.3


From ec8a31a7d0eb9f2bc675bf4ad6bdcc9cc84e6221 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:35 +0300
Subject: drm/vmwgfx: Stop using plane->fb in vmw_kms_update_implicit_fb()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only caller of vmw_kms_update_implicit_fb() is the page_flip
hook which itself gets called with the plane mutex already held.
Hence we can look at plane->state safely.

v2: Drop the bogus lockdep assert

Cc: Deepak Rawat <drawat@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-4-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 146ea18d765e..e6889682205f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2803,6 +2803,7 @@ void vmw_kms_update_implicit_fb(struct vmw_private *dev_priv,
 				struct drm_crtc *crtc)
 {
 	struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+	struct drm_plane *plane = crtc->primary;
 	struct vmw_framebuffer *vfb;
 
 	mutex_lock(&dev_priv->global_kms_state_mutex);
@@ -2810,7 +2811,7 @@ void vmw_kms_update_implicit_fb(struct vmw_private *dev_priv,
 	if (!du->is_implicit)
 		goto out_unlock;
 
-	vfb = vmw_framebuffer_to_vfb(crtc->primary->fb);
+	vfb = vmw_framebuffer_to_vfb(plane->state->fb);
 	WARN_ON_ONCE(dev_priv->num_implicit != 1 &&
 		     dev_priv->implicit_fb != vfb);
 
-- 
cgit v1.2.3


From e1cd4f8e45937ce7bbf2613de2c9503d3cda6c12 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:36 +0300
Subject: drm/vmwgfx: Stop updating plane->fb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->fb on atomic drivers. Stop setting it.

Cc: Deepak Rawat <drawat@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-5-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 2 --
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 648f8127f65a..bbd3f19b1a0b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -525,8 +525,6 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane,
 		 */
 		if (ret != 0)
 			DRM_ERROR("Failed to update screen.\n");
-
-		crtc->primary->fb = plane->state->fb;
 	} else {
 		/*
 		 * When disabling a plane, CRTC and FB should always be NULL
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 67331f01ef32..90445bc590cb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1285,8 +1285,6 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
 							 1, 1, NULL, crtc);
 		if (ret)
 			DRM_ERROR("Failed to update STDU.\n");
-
-		crtc->primary->fb = plane->state->fb;
 	} else {
 		crtc = old_state->crtc;
 		stdu = vmw_crtc_to_stdu(crtc);
-- 
cgit v1.2.3


From 0d45d79de22feb4f32de08249e93d878fa6fdab8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:37 +0300
Subject: drm/vmwgfx: Stop using plane->fb in atomic_enable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of looking at the (soon to be deprecated) plane->fb we'll
examing plane->state->fb instead. We can do this because
vmw_du_crtc_atomic_check() prevents us from enabling a crtc
without the primary plane also being enabled.

Due to that same reason, I'm actually not sure what the checks here are
for NULL fb. If we can't enable the crtc without an enabled plane
we should always have an fb. But I'll leave that for someone else
to figure out.

Cc: Deepak Rawat <drawat@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-6-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 90445bc590cb..152e96cb1c01 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -414,6 +414,7 @@ static void vmw_stdu_crtc_helper_prepare(struct drm_crtc *crtc)
 static void vmw_stdu_crtc_atomic_enable(struct drm_crtc *crtc,
 					struct drm_crtc_state *old_state)
 {
+	struct drm_plane_state *plane_state = crtc->primary->state;
 	struct vmw_private *dev_priv;
 	struct vmw_screen_target_display_unit *stdu;
 	struct vmw_framebuffer *vfb;
@@ -422,7 +423,7 @@ static void vmw_stdu_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	stdu     = vmw_crtc_to_stdu(crtc);
 	dev_priv = vmw_priv(crtc->dev);
-	fb       = crtc->primary->fb;
+	fb       = plane_state->fb;
 
 	vfb = (fb) ? vmw_framebuffer_to_vfb(fb) : NULL;
 
-- 
cgit v1.2.3


From 93b21226bbff59e00b1b08caa4bf64325a3991b7 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:38 +0300
Subject: drm/vmwgfx: Stop messing about with plane->fb/old_fb/crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

plane->fb/old_fb/crtc should no longer be used by atomic
drivers. Stop messing about with them.

Cc: Deepak Rawat <drawat@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-7-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_fb.c | 24 ------------------------
 1 file changed, 24 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 2582ffd36bb5..3c5935f3d49e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -439,8 +439,6 @@ static int vmw_fb_compute_depth(struct fb_var_screeninfo *var,
 static int vmwgfx_set_config_internal(struct drm_mode_set *set)
 {
 	struct drm_crtc *crtc = set->crtc;
-	struct drm_framebuffer *fb;
-	struct drm_crtc *tmp;
 	struct drm_modeset_acquire_ctx *ctx;
 	struct drm_device *dev = set->crtc->dev;
 	int ret;
@@ -448,29 +446,7 @@ static int vmwgfx_set_config_internal(struct drm_mode_set *set)
 	ctx = dev->mode_config.acquire_ctx;
 
 restart:
-	/*
-	 * NOTE: ->set_config can also disable other crtcs (if we steal all
-	 * connectors from it), hence we need to refcount the fbs across all
-	 * crtcs. Atomic modeset will have saner semantics ...
-	 */
-	drm_for_each_crtc(tmp, dev)
-		tmp->primary->old_fb = tmp->primary->fb;
-
-	fb = set->fb;
-
 	ret = crtc->funcs->set_config(set, ctx);
-	if (ret == 0) {
-		crtc->primary->crtc = crtc;
-		crtc->primary->fb = fb;
-	}
-
-	drm_for_each_crtc(tmp, dev) {
-		if (tmp->primary->fb)
-			drm_framebuffer_get(tmp->primary->fb);
-		if (tmp->primary->old_fb)
-			drm_framebuffer_put(tmp->primary->old_fb);
-		tmp->primary->old_fb = NULL;
-	}
 
 	if (ret == -EDEADLK) {
 		dev->mode_config.acquire_ctx = NULL;
-- 
cgit v1.2.3


From 9e5c947cb7c11211bb5ca55bf209730c684fe43b Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:39 +0300
Subject: drm/amdgpu/dc: Stop updating plane->fb
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->fb on atomic drivers. Stop setting it.

Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-8-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1dd1142246c2..3263031db44b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3951,8 +3951,6 @@ static void amdgpu_dm_do_flip(struct drm_crtc *crtc,
 
 	/* Flip */
 	spin_lock_irqsave(&crtc->dev->event_lock, flags);
-	/* update crtc fb */
-	crtc->primary->fb = fb;
 
 	WARN_ON(acrtc->pflip_status != AMDGPU_FLIP_NONE);
 	WARN_ON(!acrtc_state->stream);
-- 
cgit v1.2.3


From cd30fbca9713d225bc61ff9a2d5f1fbaff9df2f2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:40 +0300
Subject: drm/i915: Stop updating plane->fb/crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->fb/crtc on atomic drivers. Stop setting
them.

v2: Fix up the comment in intel_crtc_active() and
    nuke the rest of the stale comments (Daniel)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> #v1
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-9-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/i915/intel_atomic_plane.c | 12 ------------
 drivers/gpu/drm/i915/intel_display.c      |  7 +++----
 2 files changed, 3 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index 7481ce85746b..eb0579fb5e54 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -120,12 +120,6 @@ int intel_plane_atomic_check_with_state(const struct intel_crtc_state *old_crtc_
 		&crtc_state->base.adjusted_mode;
 	int ret;
 
-	/*
-	 * Both crtc and plane->crtc could be NULL if we're updating a
-	 * property while the plane is disabled.  We don't actually have
-	 * anything driver-specific we need to test in that case, so
-	 * just return success.
-	 */
 	if (!intel_state->base.crtc && !old_plane_state->base.crtc)
 		return 0;
 
@@ -204,12 +198,6 @@ static int intel_plane_atomic_check(struct drm_plane *plane,
 	const struct drm_crtc_state *old_crtc_state;
 	struct drm_crtc_state *new_crtc_state;
 
-	/*
-	 * Both crtc and plane->crtc could be NULL if we're updating a
-	 * property while the plane is disabled.  We don't actually have
-	 * anything driver-specific we need to test in that case, so
-	 * just return success.
-	 */
 	if (!crtc)
 		return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 00b030b08a6a..91eb47a1c922 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -994,7 +994,7 @@ bool intel_crtc_active(struct intel_crtc *crtc)
 	 * We can ditch the adjusted_mode.crtc_clock check as soon
 	 * as Haswell has gained clock readout/fastboot support.
 	 *
-	 * We can ditch the crtc->primary->fb check as soon as we can
+	 * We can ditch the crtc->primary->state->fb check as soon as we can
 	 * properly reconstruct framebuffers.
 	 *
 	 * FIXME: The intel_crtc->active here should be switched to
@@ -2894,9 +2894,8 @@ valid_fb:
 	if (i915_gem_object_is_tiled(obj))
 		dev_priv->preserve_bios_swizzle = true;
 
-	drm_framebuffer_get(fb);
-	primary->fb = primary->state->fb = fb;
-	primary->crtc = primary->state->crtc = &intel_crtc->base;
+	plane_state->fb = fb;
+	plane_state->crtc = &intel_crtc->base;
 
 	intel_set_plane_visible(to_intel_crtc_state(crtc_state),
 				to_intel_plane_state(plane_state),
-- 
cgit v1.2.3


From 67ba0c56a807912b4254da043b9b47c90a391eb6 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:41 +0300
Subject: drm/exynos: Stop updating plane->crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->crtc on atomic drivers. Stop setting it.

Cc: Inki Dae <inki.dae@samsung.com>
Cc: Joonyoung Shim <jy0922.shim@samsung.com>
Cc: Seung-Woo Kim <sw0312.kim@samsung.com>
Cc: Kyungmin Park <kyungmin.park@samsung.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Inki Dae <inki.dae@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-10-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/exynos/exynos_drm_plane.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_plane.c b/drivers/gpu/drm/exynos/exynos_drm_plane.c
index d2a90dae5c71..1b1af359c303 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_plane.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_plane.c
@@ -263,8 +263,6 @@ static void exynos_plane_atomic_update(struct drm_plane *plane,
 	if (!state->crtc)
 		return;
 
-	plane->crtc = state->crtc;
-
 	if (exynos_crtc->ops->update_plane)
 		exynos_crtc->ops->update_plane(exynos_crtc, exynos_plane);
 }
-- 
cgit v1.2.3


From d0766b0047c2161ae2261865297992f570e63cfa Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:42 +0300
Subject: drm/msm: Stop updating plane->fb/crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->fb/crtc on atomic drivers. Stop setting
them.

v2: Catch a few more cases

Cc: Rob Clark <robdclark@gmail.com>
Cc: linux-arm-msm@vger.kernel.org
Cc: freedreno@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com> #v1
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-11-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c  | 1 -
 drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c | 2 --
 drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c  | 1 -
 drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c | 2 --
 4 files changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
index 20f9e5de5f19..457c29dba4a1 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_crtc.c
@@ -665,7 +665,6 @@ struct drm_crtc *mdp4_crtc_init(struct drm_device *dev,
 	drm_crtc_init_with_planes(dev, crtc, plane, NULL, &mdp4_crtc_funcs,
 				  NULL);
 	drm_crtc_helper_add(crtc, &mdp4_crtc_helper_funcs);
-	plane->crtc = crtc;
 
 	return crtc;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
index 7a1ad3af08e3..782b1e27f040 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
@@ -182,8 +182,6 @@ static void mdp4_plane_set_scanout(struct drm_plane *plane,
 			msm_framebuffer_iova(fb, kms->aspace, 2));
 	mdp4_write(mdp4_kms, REG_MDP4_PIPE_SRCP3_BASE(pipe),
 			msm_framebuffer_iova(fb, kms->aspace, 3));
-
-	plane->fb = fb;
 }
 
 static void mdp4_write_csc_config(struct mdp4_kms *mdp4_kms,
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 76b96081916f..efedcac6e641 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -1198,7 +1198,6 @@ struct drm_crtc *mdp5_crtc_init(struct drm_device *dev,
 			"unref cursor", unref_cursor_worker);
 
 	drm_crtc_helper_add(crtc, &mdp5_crtc_helper_funcs);
-	plane->crtc = crtc;
 
 	return crtc;
 }
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index f2361f79fdce..6826aa10f3ac 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -1043,8 +1043,6 @@ static int mdp5_plane_mode_set(struct drm_plane *plane,
 				     src_img_w, src_img_h,
 				     src_x + src_w, src_y, src_w, src_h);
 
-	plane->fb = fb;
-
 	return ret;
 }
 
-- 
cgit v1.2.3


From 50dcd554181e57c2352b387a0d0fb8cf4a1aa555 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:43 +0300
Subject: drm/virtio: Stop updating plane->crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->crtc on atomic drivers. Stop setting it.

v2: s/fb/crtc/ in the commit message (Gerd)

Cc: David Airlie <airlied@linux.ie>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-12-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/virtio/virtgpu_display.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index d6dd769a7ad3..ff9933e79416 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -282,8 +282,6 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index)
 	drm_crtc_init_with_planes(dev, crtc, primary, cursor,
 				  &virtio_gpu_crtc_funcs, NULL);
 	drm_crtc_helper_add(crtc, &virtio_gpu_crtc_helper_funcs);
-	primary->crtc = crtc;
-	cursor->crtc = crtc;
 
 	drm_connector_init(dev, connector, &virtio_gpu_connector_funcs,
 			   DRM_MODE_CONNECTOR_VIRTUAL);
-- 
cgit v1.2.3


From 2f958af7fc2483e09a048308fe55399343d8f20c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:44 +0300
Subject: drm/vc4: Stop updating plane->fb/crtc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We want to get rid of plane->fb/crtc on atomic drivers. Stop setting
them.

Cc: Eric Anholt <eric@anholt.net>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-13-ville.syrjala@linux.intel.com
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vc4/vc4_crtc.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index 83d3b7912fc2..868f39a9ae8a 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -818,7 +818,6 @@ static int vc4_async_page_flip(struct drm_crtc *crtc,
 	 * is released.
 	 */
 	drm_atomic_set_fb_for_plane(plane->state, fb);
-	plane->fb = fb;
 
 	vc4_queue_seqno_cb(dev, &flip_state->cb, bo->seqno,
 			   vc4_async_page_flip_complete);
@@ -1013,7 +1012,6 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	drm_crtc_init_with_planes(drm, crtc, primary_plane, NULL,
 				  &vc4_crtc_funcs, NULL);
 	drm_crtc_helper_add(crtc, &vc4_crtc_helper_funcs);
-	primary_plane->crtc = crtc;
 	vc4_crtc->channel = vc4_crtc->data->hvs_channel;
 	drm_mode_crtc_set_gamma_size(crtc, ARRAY_SIZE(vc4_crtc->lut_r));
 	drm_crtc_enable_color_mgmt(crtc, 0, false, crtc->gamma_size);
@@ -1049,7 +1047,6 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR);
 	if (!IS_ERR(cursor_plane)) {
 		cursor_plane->possible_crtcs = 1 << drm_crtc_index(crtc);
-		cursor_plane->crtc = crtc;
 		crtc->cursor = cursor_plane;
 	}
 
-- 
cgit v1.2.3


From e00fb8564ee98c5c3a72c74b1a27e441abff6cca Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 25 May 2018 21:50:45 +0300
Subject: drm: Stop updating plane->crtc/fb/old_fb on atomic drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Stop playing around with plane->crtc/fb/old_fb with atomic
drivers. Make life a lot simpler when we don't have to do the
magic old_fb vs. fb dance around plane updates. That way we
can't risk plane->fb getting out of sync with plane->state->fb
and we're less likely to leak any refcounts as well.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525185045.29689-14-ville.syrjala@linux.intel.com
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/drm_atomic.c        | 55 ++++---------------------------------
 drivers/gpu/drm/drm_atomic_helper.c | 15 +---------
 drivers/gpu/drm/drm_crtc.c          |  8 ++++--
 drivers/gpu/drm/drm_fb_helper.c     |  7 -----
 drivers/gpu/drm/drm_framebuffer.c   |  5 ----
 drivers/gpu/drm/drm_plane.c         | 14 ++++++----
 drivers/gpu/drm/drm_plane_helper.c  |  4 ++-
 include/drm/drm_atomic.h            |  3 --
 8 files changed, 24 insertions(+), 87 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 07fef42869aa..11059d556dbd 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -692,6 +692,11 @@ drm_atomic_get_plane_state(struct drm_atomic_state *state,
 
 	WARN_ON(!state->acquire_ctx);
 
+	/* the legacy pointers should never be set */
+	WARN_ON(plane->fb);
+	WARN_ON(plane->old_fb);
+	WARN_ON(plane->crtc);
+
 	plane_state = drm_atomic_get_existing_plane_state(state, plane);
 	if (plane_state)
 		return plane_state;
@@ -2039,45 +2044,6 @@ int drm_atomic_set_property(struct drm_atomic_state *state,
 	return ret;
 }
 
-/**
- * drm_atomic_clean_old_fb -- Unset old_fb pointers and set plane->fb pointers.
- *
- * @dev: drm device to check.
- * @plane_mask: plane mask for planes that were updated.
- * @ret: return value, can be -EDEADLK for a retry.
- *
- * Before doing an update &drm_plane.old_fb is set to &drm_plane.fb, but before
- * dropping the locks old_fb needs to be set to NULL and plane->fb updated. This
- * is a common operation for each atomic update, so this call is split off as a
- * helper.
- */
-void drm_atomic_clean_old_fb(struct drm_device *dev,
-			     unsigned plane_mask,
-			     int ret)
-{
-	struct drm_plane *plane;
-
-	/* if succeeded, fixup legacy plane crtc/fb ptrs before dropping
-	 * locks (ie. while it is still safe to deref plane->state).  We
-	 * need to do this here because the driver entry points cannot
-	 * distinguish between legacy and atomic ioctls.
-	 */
-	drm_for_each_plane_mask(plane, dev, plane_mask) {
-		if (ret == 0) {
-			struct drm_framebuffer *new_fb = plane->state->fb;
-			if (new_fb)
-				drm_framebuffer_get(new_fb);
-			plane->fb = new_fb;
-			plane->crtc = plane->state->crtc;
-
-			if (plane->old_fb)
-				drm_framebuffer_put(plane->old_fb);
-		}
-		plane->old_fb = NULL;
-	}
-}
-EXPORT_SYMBOL(drm_atomic_clean_old_fb);
-
 /**
  * DOC: explicit fencing properties
  *
@@ -2298,9 +2264,7 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	unsigned int copied_objs, copied_props;
 	struct drm_atomic_state *state;
 	struct drm_modeset_acquire_ctx ctx;
-	struct drm_plane *plane;
 	struct drm_out_fence_state *fence_state;
-	unsigned plane_mask;
 	int ret = 0;
 	unsigned int i, j, num_fences;
 
@@ -2340,7 +2304,6 @@ int drm_mode_atomic_ioctl(struct drm_device *dev,
 	state->allow_modeset = !!(arg->flags & DRM_MODE_ATOMIC_ALLOW_MODESET);
 
 retry:
-	plane_mask = 0;
 	copied_objs = 0;
 	copied_props = 0;
 	fence_state = NULL;
@@ -2411,12 +2374,6 @@ retry:
 			copied_props++;
 		}
 
-		if (obj->type == DRM_MODE_OBJECT_PLANE && count_props &&
-		    !(arg->flags & DRM_MODE_ATOMIC_TEST_ONLY)) {
-			plane = obj_to_plane(obj);
-			plane_mask |= (1 << drm_plane_index(plane));
-			plane->old_fb = plane->fb;
-		}
 		drm_mode_object_put(obj);
 	}
 
@@ -2437,8 +2394,6 @@ retry:
 	}
 
 out:
-	drm_atomic_clean_old_fb(dev, plane_mask, ret);
-
 	complete_crtc_signaling(dev, state, fence_state, num_fences, !ret);
 
 	if (ret == -EDEADLK) {
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 130da5195f3b..232fa11a5e31 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2914,7 +2914,6 @@ static int __drm_atomic_helper_disable_all(struct drm_device *dev,
 	struct drm_plane *plane;
 	struct drm_crtc_state *crtc_state;
 	struct drm_crtc *crtc;
-	unsigned plane_mask = 0;
 	int ret, i;
 
 	state = drm_atomic_state_alloc(dev);
@@ -2957,17 +2956,10 @@ static int __drm_atomic_helper_disable_all(struct drm_device *dev,
 			goto free;
 
 		drm_atomic_set_fb_for_plane(plane_state, NULL);
-
-		if (clean_old_fbs) {
-			plane->old_fb = plane->fb;
-			plane_mask |= BIT(drm_plane_index(plane));
-		}
 	}
 
 	ret = drm_atomic_commit(state);
 free:
-	if (plane_mask)
-		drm_atomic_clean_old_fb(dev, plane_mask, ret);
 	drm_atomic_state_put(state);
 	return ret;
 }
@@ -3129,13 +3121,8 @@ int drm_atomic_helper_commit_duplicated_state(struct drm_atomic_state *state,
 
 	state->acquire_ctx = ctx;
 
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		WARN_ON(plane->crtc != new_plane_state->crtc);
-		WARN_ON(plane->fb != new_plane_state->fb);
-		WARN_ON(plane->old_fb);
-
+	for_each_new_plane_in_state(state, plane, new_plane_state, i)
 		state->planes[i].old_state = plane->state;
-	}
 
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i)
 		state->crtcs[i].old_state = crtc->state;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 237bd34212db..53828fc8d911 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -479,8 +479,12 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 
 	ret = crtc->funcs->set_config(set, ctx);
 	if (ret == 0) {
-		crtc->primary->crtc = fb ? crtc : NULL;
-		crtc->primary->fb = fb;
+		struct drm_plane *plane = crtc->primary;
+
+		if (!plane->state) {
+			plane->crtc = fb ? crtc : NULL;
+			plane->fb = fb;
+		}
 	}
 
 	drm_for_each_crtc(tmp, crtc->dev) {
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 91f051e5e130..cab14f253384 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -368,7 +368,6 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper, bool activ
 	struct drm_plane *plane;
 	struct drm_atomic_state *state;
 	int i, ret;
-	unsigned int plane_mask;
 	struct drm_modeset_acquire_ctx ctx;
 
 	drm_modeset_acquire_init(&ctx, 0);
@@ -381,7 +380,6 @@ static int restore_fbdev_mode_atomic(struct drm_fb_helper *fb_helper, bool activ
 
 	state->acquire_ctx = &ctx;
 retry:
-	plane_mask = 0;
 	drm_for_each_plane(plane, dev) {
 		plane_state = drm_atomic_get_plane_state(state, plane);
 		if (IS_ERR(plane_state)) {
@@ -391,9 +389,6 @@ retry:
 
 		plane_state->rotation = DRM_MODE_ROTATE_0;
 
-		plane->old_fb = plane->fb;
-		plane_mask |= 1 << drm_plane_index(plane);
-
 		/* disable non-primary: */
 		if (plane->type == DRM_PLANE_TYPE_PRIMARY)
 			continue;
@@ -430,8 +425,6 @@ retry:
 	ret = drm_atomic_commit(state);
 
 out_state:
-	drm_atomic_clean_old_fb(dev, plane_mask, ret);
-
 	if (ret == -EDEADLK)
 		goto backoff;
 
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index bfedceff87bb..46b11e46edbd 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -836,8 +836,6 @@ retry:
 			goto unlock;
 
 		plane_mask |= BIT(drm_plane_index(plane));
-
-		plane->old_fb = plane->fb;
 	}
 
 	/* This list is only filled when disable_crtcs is set. */
@@ -852,9 +850,6 @@ retry:
 		ret = drm_atomic_commit(state);
 
 unlock:
-	if (plane_mask)
-		drm_atomic_clean_old_fb(dev, plane_mask, ret);
-
 	if (ret == -EDEADLK) {
 		drm_atomic_state_clear(state);
 		drm_modeset_backoff(&ctx);
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 7ce88dff871d..534b57933576 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -651,9 +651,11 @@ static int __setplane_internal(struct drm_plane *plane,
 					 crtc_x, crtc_y, crtc_w, crtc_h,
 					 src_x, src_y, src_w, src_h, ctx);
 	if (!ret) {
-		plane->crtc = crtc;
-		plane->fb = fb;
-		drm_framebuffer_get(plane->fb);
+		if (!plane->state) {
+			plane->crtc = crtc;
+			plane->fb = fb;
+			drm_framebuffer_get(plane->fb);
+		}
 	} else {
 		plane->old_fb = NULL;
 	}
@@ -1093,8 +1095,10 @@ retry:
 		/* Keep the old fb, don't unref it. */
 		plane->old_fb = NULL;
 	} else {
-		plane->fb = fb;
-		drm_framebuffer_get(fb);
+		if (!plane->state) {
+			plane->fb = fb;
+			drm_framebuffer_get(fb);
+		}
 	}
 
 out:
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index f88f68161519..2010794943bc 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -502,6 +502,7 @@ EXPORT_SYMBOL(drm_plane_helper_update);
 int drm_plane_helper_disable(struct drm_plane *plane)
 {
 	struct drm_plane_state *plane_state;
+	struct drm_framebuffer *old_fb;
 
 	/* crtc helpers love to call disable functions for already disabled hw
 	 * functions. So cope with that. */
@@ -521,8 +522,9 @@ int drm_plane_helper_disable(struct drm_plane *plane)
 	plane_state->plane = plane;
 
 	plane_state->crtc = NULL;
+	old_fb = plane_state->fb;
 	drm_atomic_set_fb_for_plane(plane_state, NULL);
 
-	return drm_plane_helper_commit(plane, plane_state, plane->fb);
+	return drm_plane_helper_commit(plane, plane_state, old_fb);
 }
 EXPORT_SYMBOL(drm_plane_helper_disable);
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index a57a8aa90ffb..ca461b6cf71f 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -601,9 +601,6 @@ int __must_check
 drm_atomic_add_affected_planes(struct drm_atomic_state *state,
 			       struct drm_crtc *crtc);
 
-void
-drm_atomic_clean_old_fb(struct drm_device *dev, unsigned plane_mask, int ret);
-
 int __must_check drm_atomic_check_only(struct drm_atomic_state *state);
 int __must_check drm_atomic_commit(struct drm_atomic_state *state);
 int __must_check drm_atomic_nonblocking_commit(struct drm_atomic_state *state);
-- 
cgit v1.2.3


From 68a8570375df647cf8b6626d63917b564dd9390e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Jun 2018 18:18:24 +0100
Subject: drm/i915/gtt: Invalidate GGTT caches after writing the gen6 page
 directories

When we update the gen6 ppgtt page directories, we do so by writing the
new address into a reserved slot in the GGTT. It appears that when the
GPU reads that entry from the gsm, it uses its small cache and that we
need to invalidate that cache after writing. We don't see an issue
currently as we prefill the ppgtt page directories on creation; and only
create the single aliasing_ppgtt long before we start using the GGTT
(and so before the cache may have a conflicting entry).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611171825.13678-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ac75e0c5735c..905a58b6ddf8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1693,8 +1693,8 @@ static inline void gen6_write_pde(const struct i915_hw_ppgtt *ppgtt,
 				  const struct i915_page_table *pt)
 {
 	/* Caller needs to make sure the write completes if necessary */
-	writel_relaxed(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
-		       ppgtt->pd_addr + pde);
+	iowrite32(GEN6_PDE_ADDR_ENCODE(px_dma(pt)) | GEN6_PDE_VALID,
+		  ppgtt->pd_addr + pde);
 }
 
 /* Write all the page tables found in the ppgtt structure to incrementing page
@@ -1709,7 +1709,7 @@ static void gen6_write_page_range(struct i915_hw_ppgtt *ppgtt,
 		gen6_write_pde(ppgtt, pde, pt);
 
 	mark_tlbs_dirty(ppgtt);
-	wmb();
+	gen6_ggtt_invalidate(ppgtt->vm.i915);
 }
 
 static void gen8_ppgtt_enable(struct drm_i915_private *dev_priv)
@@ -1864,7 +1864,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 
 	if (flush) {
 		mark_tlbs_dirty(ppgtt);
-		wmb();
+		gen6_ggtt_invalidate(ppgtt->vm.i915);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From d9d117e40d4ffc03438177eeac83d96dfeee76be Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 11 Jun 2018 18:18:25 +0100
Subject: drm/i915/ringbuffer: Serialize load of PD_DIR

After triggering the mm switch with a load of PD_DIR, which may be
deferred unto the MI_SET_CONTEXT on rcs, serialise the next commands
with that load by posting a read of PD_DIR (or else those subsequent
commands may access the stale page tables).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611171825.13678-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c  |  5 ++--
 drivers/gpu/drm/i915/intel_ringbuffer.c | 49 +++++++++++++++++++++++++--------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  5 +++-
 3 files changed, 44 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index d1cf8b4926ab..d278fed8cb31 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -499,7 +499,8 @@ void intel_engine_setup_common(struct intel_engine_cs *engine)
 	intel_engine_init_cmd_parser(engine);
 }
 
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size)
+int intel_engine_create_scratch(struct intel_engine_cs *engine,
+				unsigned int size)
 {
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
@@ -533,7 +534,7 @@ err_unref:
 	return ret;
 }
 
-static void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine)
 {
 	i915_vma_unpin_and_release(&engine->scratch);
 }
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index bb4af8f84a22..735622dc73ec 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1361,8 +1361,9 @@ intel_ring_context_pin(struct intel_engine_cs *engine,
 
 static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 {
-	struct intel_ring *ring;
 	struct i915_timeline *timeline;
+	struct intel_ring *ring;
+	unsigned int size;
 	int err;
 
 	intel_engine_setup_common(engine);
@@ -1388,12 +1389,21 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine)
 	GEM_BUG_ON(engine->buffer);
 	engine->buffer = ring;
 
-	err = intel_engine_init_common(engine);
+	size = PAGE_SIZE;
+	if (HAS_BROKEN_CS_TLB(engine->i915))
+		size = I830_WA_SIZE;
+	err = intel_engine_create_scratch(engine, size);
 	if (err)
 		goto err_unpin;
 
+	err = intel_engine_init_common(engine);
+	if (err)
+		goto err_scratch;
+
 	return 0;
 
+err_scratch:
+	intel_engine_cleanup_scratch(engine);
 err_unpin:
 	intel_ring_unpin(ring);
 err_ring:
@@ -1455,6 +1465,25 @@ static int load_pd_dir(struct i915_request *rq,
 	return 0;
 }
 
+static int flush_pd_dir(struct i915_request *rq)
+{
+	const struct intel_engine_cs * const engine = rq->engine;
+	u32 *cs;
+
+	cs = intel_ring_begin(rq, 4);
+	if (IS_ERR(cs))
+		return PTR_ERR(cs);
+
+	/* Stall until the page table load is complete */
+	*cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
+	*cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine));
+	*cs++ = i915_ggtt_offset(engine->scratch);
+	*cs++ = MI_NOOP;
+
+	intel_ring_advance(rq, cs);
+	return 0;
+}
+
 static inline int mi_set_context(struct i915_request *rq, u32 flags)
 {
 	struct drm_i915_private *i915 = rq->i915;
@@ -1638,6 +1667,12 @@ static int switch_context(struct i915_request *rq)
 			goto err_mm;
 	}
 
+	if (ppgtt) {
+		ret = flush_pd_dir(rq);
+		if (ret)
+			goto err_mm;
+	}
+
 	if (ctx->remap_slice) {
 		for (i = 0; i < MAX_L3_SLICES; i++) {
 			if (!(ctx->remap_slice & BIT(i)))
@@ -2158,16 +2193,6 @@ int intel_init_render_ring_buffer(struct intel_engine_cs *engine)
 	if (ret)
 		return ret;
 
-	if (INTEL_GEN(dev_priv) >= 6) {
-		ret = intel_engine_create_scratch(engine, PAGE_SIZE);
-		if (ret)
-			return ret;
-	} else if (HAS_BROKEN_CS_TLB(dev_priv)) {
-		ret = intel_engine_create_scratch(engine, I830_WA_SIZE);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index e9494557aaa1..2c35dd3525a6 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -869,9 +869,12 @@ void intel_engine_init_global_seqno(struct intel_engine_cs *engine, u32 seqno);
 
 void intel_engine_setup_common(struct intel_engine_cs *engine);
 int intel_engine_init_common(struct intel_engine_cs *engine);
-int intel_engine_create_scratch(struct intel_engine_cs *engine, int size);
 void intel_engine_cleanup_common(struct intel_engine_cs *engine);
 
+int intel_engine_create_scratch(struct intel_engine_cs *engine,
+				unsigned int size);
+void intel_engine_cleanup_scratch(struct intel_engine_cs *engine);
+
 int intel_init_render_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine);
 int intel_init_blt_ring_buffer(struct intel_engine_cs *engine);
-- 
cgit v1.2.3


From 35ac40d8b65ab5bd09b683720bca96a1f5a0625b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 12 Jun 2018 09:18:14 +0100
Subject: drm/i915/gtt: Subclass gen6_hw_ppgtt

The legacy gen6 ppgtt needs a little more hand holding than gen8+, and
so requires a larger structure. As I intend to make this slightly more
complicated in the future, separate the gen6 from the core gen8 hw
struct by subclassing. This patch moves the gen6 only features out to
gen6_hw_ppgtt and pipes the new type everywhere that needs it.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612081815.3585-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c           | 94 +++++++++++++--------------
 drivers/gpu/drm/i915/i915_gem_gtt.h           | 19 +++++-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 10 +--
 3 files changed, 65 insertions(+), 58 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 905a58b6ddf8..62991e6cf1d5 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1636,20 +1636,20 @@ err_free:
 	return ERR_PTR(err);
 }
 
-static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
+static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
 {
-	struct i915_address_space *vm = &ppgtt->vm;
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
+	struct i915_address_space *vm = &base->vm;
 	struct i915_page_table *unused;
 	gen6_pte_t scratch_pte;
 	u32 pd_entry, pte, pde;
-	u32 start = 0, length = ppgtt->vm.total;
 
 	scratch_pte = vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 
-	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde) {
+	gen6_for_all_pdes(unused, &base->pd, pde) {
 		u32 expected;
 		gen6_pte_t *pt_vaddr;
-		const dma_addr_t pt_addr = px_dma(ppgtt->pd.page_table[pde]);
+		const dma_addr_t pt_addr = px_dma(base->pd.page_table[pde]);
 		pd_entry = readl(ppgtt->pd_addr + pde);
 		expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);
 
@@ -1660,7 +1660,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 				   expected);
 		seq_printf(m, "\tPDE: %x\n", pd_entry);
 
-		pt_vaddr = kmap_atomic_px(ppgtt->pd.page_table[pde]);
+		pt_vaddr = kmap_atomic_px(base->pd.page_table[pde]);
 
 		for (pte = 0; pte < GEN6_PTES; pte+=4) {
 			unsigned long va =
@@ -1688,7 +1688,7 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 }
 
 /* Write pde (index) from the page directory @pd to the page table @pt */
-static inline void gen6_write_pde(const struct i915_hw_ppgtt *ppgtt,
+static inline void gen6_write_pde(const struct gen6_hw_ppgtt *ppgtt,
 				  const unsigned int pde,
 				  const struct i915_page_table *pt)
 {
@@ -1699,17 +1699,18 @@ static inline void gen6_write_pde(const struct i915_hw_ppgtt *ppgtt,
 
 /* Write all the page tables found in the ppgtt structure to incrementing page
  * directories. */
-static void gen6_write_page_range(struct i915_hw_ppgtt *ppgtt,
+static void gen6_write_page_range(struct i915_hw_ppgtt *base,
 				  u32 start, u32 length)
 {
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
 	struct i915_page_table *pt;
 	unsigned int pde;
 
-	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde)
+	gen6_for_each_pde(pt, &base->pd, start, length, pde)
 		gen6_write_pde(ppgtt, pde, pt);
 
-	mark_tlbs_dirty(ppgtt);
-	gen6_ggtt_invalidate(ppgtt->vm.i915);
+	mark_tlbs_dirty(base);
+	gen6_ggtt_invalidate(base->vm.i915);
 }
 
 static void gen8_ppgtt_enable(struct drm_i915_private *dev_priv)
@@ -1843,28 +1844,28 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 static int gen6_alloc_va_range(struct i915_address_space *vm,
 			       u64 start, u64 length)
 {
-	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	struct i915_page_table *pt;
 	u64 from = start;
 	unsigned int pde;
 	bool flush = false;
 
-	gen6_for_each_pde(pt, &ppgtt->pd, start, length, pde) {
+	gen6_for_each_pde(pt, &ppgtt->base.pd, start, length, pde) {
 		if (pt == vm->scratch_pt) {
 			pt = alloc_pt(vm);
 			if (IS_ERR(pt))
 				goto unwind_out;
 
 			gen6_initialize_pt(vm, pt);
-			ppgtt->pd.page_table[pde] = pt;
+			ppgtt->base.pd.page_table[pde] = pt;
 			gen6_write_pde(ppgtt, pde, pt);
 			flush = true;
 		}
 	}
 
 	if (flush) {
-		mark_tlbs_dirty(ppgtt);
-		gen6_ggtt_invalidate(ppgtt->vm.i915);
+		mark_tlbs_dirty(&ppgtt->base);
+		gen6_ggtt_invalidate(ppgtt->base.vm.i915);
 	}
 
 	return 0;
@@ -1901,24 +1902,23 @@ static void gen6_free_scratch(struct i915_address_space *vm)
 
 static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 {
-	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
-	struct i915_page_directory *pd = &ppgtt->pd;
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	struct i915_page_table *pt;
 	u32 pde;
 
 	drm_mm_remove_node(&ppgtt->node);
 
-	gen6_for_all_pdes(pt, pd, pde)
+	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde)
 		if (pt != vm->scratch_pt)
 			free_pt(vm, pt);
 
 	gen6_free_scratch(vm);
 }
 
-static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
+static int gen6_ppgtt_allocate_page_directories(struct gen6_hw_ppgtt *ppgtt)
 {
-	struct i915_address_space *vm = &ppgtt->vm;
-	struct drm_i915_private *dev_priv = ppgtt->vm.i915;
+	struct i915_address_space *vm = &ppgtt->base.vm;
+	struct drm_i915_private *dev_priv = ppgtt->base.vm.i915;
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
@@ -1943,11 +1943,11 @@ static int gen6_ppgtt_allocate_page_directories(struct i915_hw_ppgtt *ppgtt)
 	if (ppgtt->node.start < ggtt->mappable_end)
 		DRM_DEBUG("Forced to use aperture for PDEs\n");
 
-	ppgtt->pd.base.ggtt_offset =
+	ppgtt->base.pd.base.ggtt_offset =
 		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);
 
 	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm +
-		ppgtt->pd.base.ggtt_offset / sizeof(gen6_pte_t);
+		ppgtt->base.pd.base.ggtt_offset / sizeof(gen6_pte_t);
 
 	return 0;
 
@@ -1956,70 +1956,70 @@ err_out:
 	return ret;
 }
 
-static int gen6_ppgtt_alloc(struct i915_hw_ppgtt *ppgtt)
+static int gen6_ppgtt_alloc(struct gen6_hw_ppgtt *ppgtt)
 {
 	return gen6_ppgtt_allocate_page_directories(ppgtt);
 }
 
-static void gen6_scratch_va_range(struct i915_hw_ppgtt *ppgtt,
+static void gen6_scratch_va_range(struct gen6_hw_ppgtt *ppgtt,
 				  u64 start, u64 length)
 {
 	struct i915_page_table *unused;
 	u32 pde;
 
-	gen6_for_each_pde(unused, &ppgtt->pd, start, length, pde)
-		ppgtt->pd.page_table[pde] = ppgtt->vm.scratch_pt;
+	gen6_for_each_pde(unused, &ppgtt->base.pd, start, length, pde)
+		ppgtt->base.pd.page_table[pde] = ppgtt->base.vm.scratch_pt;
 }
 
 static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 {
 	struct i915_ggtt * const ggtt = &i915->ggtt;
-	struct i915_hw_ppgtt *ppgtt;
+	struct gen6_hw_ppgtt *ppgtt;
 	int err;
 
 	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
 	if (!ppgtt)
 		return ERR_PTR(-ENOMEM);
 
-	ppgtt->vm.i915 = i915;
-	ppgtt->vm.dma = &i915->drm.pdev->dev;
+	ppgtt->base.vm.i915 = i915;
+	ppgtt->base.vm.dma = &i915->drm.pdev->dev;
 
-	ppgtt->vm.pte_encode = ggtt->vm.pte_encode;
+	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
 
 	err = gen6_ppgtt_alloc(ppgtt);
 	if (err)
 		goto err_free;
 
-	ppgtt->vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
+	ppgtt->base.vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
 
-	gen6_scratch_va_range(ppgtt, 0, ppgtt->vm.total);
-	gen6_write_page_range(ppgtt, 0, ppgtt->vm.total);
+	gen6_scratch_va_range(ppgtt, 0, ppgtt->base.vm.total);
+	gen6_write_page_range(&ppgtt->base, 0, ppgtt->base.vm.total);
 
-	err = gen6_alloc_va_range(&ppgtt->vm, 0, ppgtt->vm.total);
+	err = gen6_alloc_va_range(&ppgtt->base.vm, 0, ppgtt->base.vm.total);
 	if (err)
 		goto err_cleanup;
 
-	ppgtt->vm.clear_range = gen6_ppgtt_clear_range;
-	ppgtt->vm.insert_entries = gen6_ppgtt_insert_entries;
-	ppgtt->vm.cleanup = gen6_ppgtt_cleanup;
-	ppgtt->debug_dump = gen6_dump_ppgtt;
+	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
+	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
+	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
+	ppgtt->base.debug_dump = gen6_dump_ppgtt;
 
-	ppgtt->vm.vma_ops.bind_vma    = gen6_ppgtt_bind_vma;
-	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
-	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
-	ppgtt->vm.vma_ops.clear_pages = clear_pages;
+	ppgtt->base.vm.vma_ops.bind_vma    = gen6_ppgtt_bind_vma;
+	ppgtt->base.vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
+	ppgtt->base.vm.vma_ops.set_pages   = ppgtt_set_pages;
+	ppgtt->base.vm.vma_ops.clear_pages = clear_pages;
 
 	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
 			 ppgtt->node.size >> 20,
 			 ppgtt->node.start / PAGE_SIZE);
 
 	DRM_DEBUG_DRIVER("Adding PPGTT at offset %x\n",
-			 ppgtt->pd.base.ggtt_offset << 10);
+			 ppgtt->base.pd.base.ggtt_offset << 10);
 
-	return ppgtt;
+	return &ppgtt->base;
 
 err_cleanup:
-	gen6_ppgtt_cleanup(&ppgtt->vm);
+	gen6_ppgtt_cleanup(&ppgtt->base.vm);
 err_free:
 	kfree(ppgtt);
 	return ERR_PTR(err);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index e70f6abcd0f2..7d65d813eff0 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -396,7 +396,7 @@ struct i915_ggtt {
 struct i915_hw_ppgtt {
 	struct i915_address_space vm;
 	struct kref ref;
-	struct drm_mm_node node;
+
 	unsigned long pd_dirty_rings;
 	union {
 		struct i915_pml4 pml4;		/* GEN8+ & 48b PPGTT */
@@ -404,11 +404,24 @@ struct i915_hw_ppgtt {
 		struct i915_page_directory pd;		/* GEN6-7 */
 	};
 
-	gen6_pte_t __iomem *pd_addr;
-
 	void (*debug_dump)(struct i915_hw_ppgtt *ppgtt, struct seq_file *m);
 };
 
+struct gen6_hw_ppgtt {
+	struct i915_hw_ppgtt base;
+
+	struct drm_mm_node node;
+	gen6_pte_t __iomem *pd_addr;
+};
+
+#define __to_gen6_ppgtt(base) container_of(base, struct gen6_hw_ppgtt, base)
+
+static inline struct gen6_hw_ppgtt *to_gen6_ppgtt(struct i915_hw_ppgtt *base)
+{
+	BUILD_BUG_ON(offsetof(struct gen6_hw_ppgtt, base));
+	return __to_gen6_ppgtt(base);
+}
+
 /*
  * gen6_for_each_pde() iterates over every pde from start until start+length.
  * If start and start+length are not perfectly divisible, the macro will round
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index f80cf7ce3fa9..a4060238bef0 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -135,17 +135,13 @@ static int igt_ppgtt_alloc(void *arg)
 	struct drm_i915_private *dev_priv = arg;
 	struct i915_hw_ppgtt *ppgtt;
 	u64 size, last;
-	int err;
+	int err = 0;
 
 	/* Allocate a ppggt and try to fill the entire range */
 
 	if (!USES_PPGTT(dev_priv))
 		return 0;
 
-	ppgtt = kzalloc(sizeof(*ppgtt), GFP_KERNEL);
-	if (!ppgtt)
-		return -ENOMEM;
-
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	ppgtt = __hw_ppgtt_create(dev_priv);
 	if (IS_ERR(ppgtt)) {
@@ -153,10 +149,8 @@ static int igt_ppgtt_alloc(void *arg)
 		goto err_unlock;
 	}
 
-	if (!ppgtt->vm.allocate_va_range) {
-		err = 0;
+	if (!ppgtt->vm.allocate_va_range)
 		goto err_ppgtt_cleanup;
-	}
 
 	/* Check we can allocate the entire range */
 	for (size = 4096;
-- 
cgit v1.2.3


From a9ded78535a109389cd2ca38a22c8d5c0099f71e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 12 Jun 2018 09:18:15 +0100
Subject: drm/i915/gtt: Onionify error handling for gen6_ppgtt_create

Pull the empty stubs together into the top level gen6_ppgtt_create, and
tear each one down on error in proper onion order (rather than use
Joonas' pet hate of calling the cleanup function in indeterminable
state).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612081815.3585-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 81 ++++++++++++++++++-------------------
 1 file changed, 39 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 62991e6cf1d5..40a839119d23 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1875,7 +1875,7 @@ unwind_out:
 	return -ENOMEM;
 }
 
-static int gen6_init_scratch(struct i915_address_space *vm)
+static int gen6_ppgtt_init_scratch(struct i915_address_space *vm)
 {
 	int ret;
 
@@ -1894,33 +1894,37 @@ static int gen6_init_scratch(struct i915_address_space *vm)
 	return 0;
 }
 
-static void gen6_free_scratch(struct i915_address_space *vm)
+static void gen6_ppgtt_free_scratch(struct i915_address_space *vm)
 {
 	free_pt(vm, vm->scratch_pt);
 	cleanup_scratch_page(vm);
 }
 
-static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+static void gen6_ppgtt_free_pd(struct gen6_hw_ppgtt *ppgtt)
 {
-	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	struct i915_page_table *pt;
 	u32 pde;
 
-	drm_mm_remove_node(&ppgtt->node);
-
 	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde)
-		if (pt != vm->scratch_pt)
-			free_pt(vm, pt);
+		if (pt != ppgtt->base.vm.scratch_pt)
+			free_pt(&ppgtt->base.vm, pt);
+}
 
-	gen6_free_scratch(vm);
+static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
+{
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
+
+	drm_mm_remove_node(&ppgtt->node);
+
+	gen6_ppgtt_free_pd(ppgtt);
+	gen6_ppgtt_free_scratch(vm);
 }
 
 static int gen6_ppgtt_allocate_page_directories(struct gen6_hw_ppgtt *ppgtt)
 {
-	struct i915_address_space *vm = &ppgtt->base.vm;
 	struct drm_i915_private *dev_priv = ppgtt->base.vm.i915;
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	int ret;
+	int err;
 
 	/* PPGTT PDEs reside in the GGTT and consists of 512 entries. The
 	 * allocator works in address space sizes, so it's multiplied by page
@@ -1928,17 +1932,13 @@ static int gen6_ppgtt_allocate_page_directories(struct gen6_hw_ppgtt *ppgtt)
 	 */
 	BUG_ON(!drm_mm_initialized(&ggtt->vm.mm));
 
-	ret = gen6_init_scratch(vm);
-	if (ret)
-		return ret;
-
-	ret = i915_gem_gtt_insert(&ggtt->vm, &ppgtt->node,
+	err = i915_gem_gtt_insert(&ggtt->vm, &ppgtt->node,
 				  GEN6_PD_SIZE, GEN6_PD_ALIGN,
 				  I915_COLOR_UNEVICTABLE,
 				  0, ggtt->vm.total,
 				  PIN_HIGH);
-	if (ret)
-		goto err_out;
+	if (err)
+		return err;
 
 	if (ppgtt->node.start < ggtt->mappable_end)
 		DRM_DEBUG("Forced to use aperture for PDEs\n");
@@ -1950,15 +1950,6 @@ static int gen6_ppgtt_allocate_page_directories(struct gen6_hw_ppgtt *ppgtt)
 		ppgtt->base.pd.base.ggtt_offset / sizeof(gen6_pte_t);
 
 	return 0;
-
-err_out:
-	gen6_free_scratch(vm);
-	return ret;
-}
-
-static int gen6_ppgtt_alloc(struct gen6_hw_ppgtt *ppgtt)
-{
-	return gen6_ppgtt_allocate_page_directories(ppgtt);
 }
 
 static void gen6_scratch_va_range(struct gen6_hw_ppgtt *ppgtt,
@@ -1984,21 +1975,8 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt->base.vm.i915 = i915;
 	ppgtt->base.vm.dma = &i915->drm.pdev->dev;
 
-	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
-
-	err = gen6_ppgtt_alloc(ppgtt);
-	if (err)
-		goto err_free;
-
 	ppgtt->base.vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
 
-	gen6_scratch_va_range(ppgtt, 0, ppgtt->base.vm.total);
-	gen6_write_page_range(&ppgtt->base, 0, ppgtt->base.vm.total);
-
-	err = gen6_alloc_va_range(&ppgtt->base.vm, 0, ppgtt->base.vm.total);
-	if (err)
-		goto err_cleanup;
-
 	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
@@ -2009,6 +1987,23 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt->base.vm.vma_ops.set_pages   = ppgtt_set_pages;
 	ppgtt->base.vm.vma_ops.clear_pages = clear_pages;
 
+	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
+
+	err = gen6_ppgtt_init_scratch(&ppgtt->base.vm);
+	if (err)
+		goto err_free;
+
+	err = gen6_ppgtt_allocate_page_directories(ppgtt);
+	if (err)
+		goto err_scratch;
+
+	gen6_scratch_va_range(ppgtt, 0, ppgtt->base.vm.total);
+	gen6_write_page_range(&ppgtt->base, 0, ppgtt->base.vm.total);
+
+	err = gen6_alloc_va_range(&ppgtt->base.vm, 0, ppgtt->base.vm.total);
+	if (err)
+		goto err_pd;
+
 	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
 			 ppgtt->node.size >> 20,
 			 ppgtt->node.start / PAGE_SIZE);
@@ -2018,8 +2013,10 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 
 	return &ppgtt->base;
 
-err_cleanup:
-	gen6_ppgtt_cleanup(&ppgtt->base.vm);
+err_pd:
+	gen6_ppgtt_free_pd(ppgtt);
+err_scratch:
+	gen6_ppgtt_free_scratch(&ppgtt->base.vm);
 err_free:
 	kfree(ppgtt);
 	return ERR_PTR(err);
-- 
cgit v1.2.3


From 50935ac767cab5494b4e15f3a95aa9e10513d82d Mon Sep 17 00:00:00 2001
From: Piotr Piórkowski <piotr.piorkowski@intel.com>
Date: Mon, 4 Jun 2018 16:19:41 +0200
Subject: drm/i915/guc: Don't store runtime GuC log level in modparam
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we are using modparam as placeholder for GuC log level.
Stop doing this and keep runtime GuC level in intel_guc_log struct.

v2:
- rename functions intel_guc_log_level_[get|set] to
intel_guc_log_[get|set]_level (Michał Wajdeczko)
- remove GEM_BUG_ON from intel_guc_log_get_level() (Michał Wajdeczko)

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604141947.8299-1-piotr.piorkowski@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c  |  4 ++--
 drivers/gpu/drm/i915/intel_guc.c     |  8 +++-----
 drivers/gpu/drm/i915/intel_guc_log.c | 28 ++++++++++------------------
 drivers/gpu/drm/i915/intel_guc_log.h | 10 ++++++++--
 drivers/gpu/drm/i915/intel_uc.c      |  2 +-
 5 files changed, 24 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 698af45e229c..769ab9745834 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2536,7 +2536,7 @@ static int i915_guc_log_level_get(void *data, u64 *val)
 	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
-	*val = intel_guc_log_level_get(&dev_priv->guc.log);
+	*val = intel_guc_log_get_level(&dev_priv->guc.log);
 
 	return 0;
 }
@@ -2548,7 +2548,7 @@ static int i915_guc_log_level_set(void *data, u64 val)
 	if (!USES_GUC(dev_priv))
 		return -ENODEV;
 
-	return intel_guc_log_level_set(&dev_priv->guc.log, val);
+	return intel_guc_log_set_level(&dev_priv->guc.log, val);
 }
 
 DEFINE_SIMPLE_ATTRIBUTE(i915_guc_log_level_fops,
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 29fd95c1306b..98b7c121162a 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -203,13 +203,11 @@ void intel_guc_fini(struct intel_guc *guc)
 	guc_shared_data_destroy(guc);
 }
 
-static u32 get_log_control_flags(void)
+static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 {
-	u32 level = i915_modparams.guc_log_level;
+	u32 level = intel_guc_log_get_level(&guc->log);
 	u32 flags = 0;
 
-	GEM_BUG_ON(level < 0);
-
 	if (!GUC_LOG_LEVEL_IS_ENABLED(level))
 		flags |= GUC_LOG_DEFAULT_DISABLED;
 
@@ -250,7 +248,7 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	params[GUC_CTL_LOG_PARAMS] = guc->log.flags;
 
-	params[GUC_CTL_DEBUG] = get_log_control_flags();
+	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
 
 	/* If GuC submission is enabled, set up additional parameters here */
 	if (USES_GUC_SUBMISSION(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index 401e1704d61e..d35d883d48e1 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -475,11 +475,12 @@ int intel_guc_log_create(struct intel_guc_log *log)
 	offset = intel_guc_ggtt_offset(guc, vma) >> PAGE_SHIFT;
 	log->flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
 
+	log->level = i915_modparams.guc_log_level;
+
 	return 0;
 
 err:
-	/* logging will be off */
-	i915_modparams.guc_log_level = 0;
+	DRM_ERROR("Failed to allocate GuC log buffer. %d\n", ret);
 	return ret;
 }
 
@@ -488,15 +489,7 @@ void intel_guc_log_destroy(struct intel_guc_log *log)
 	i915_vma_unpin_and_release(&log->vma);
 }
 
-int intel_guc_log_level_get(struct intel_guc_log *log)
-{
-	GEM_BUG_ON(!log->vma);
-	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
-
-	return i915_modparams.guc_log_level;
-}
-
-int intel_guc_log_level_set(struct intel_guc_log *log, u64 val)
+int intel_guc_log_set_level(struct intel_guc_log *log, u32 level)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -504,33 +497,32 @@ int intel_guc_log_level_set(struct intel_guc_log *log, u64 val)
 
 	BUILD_BUG_ON(GUC_LOG_VERBOSITY_MIN != 0);
 	GEM_BUG_ON(!log->vma);
-	GEM_BUG_ON(i915_modparams.guc_log_level < 0);
 
 	/*
 	 * GuC is recognizing log levels starting from 0 to max, we're using 0
 	 * as indication that logging should be disabled.
 	 */
-	if (val < GUC_LOG_LEVEL_DISABLED || val > GUC_LOG_LEVEL_MAX)
+	if (level < GUC_LOG_LEVEL_DISABLED || level > GUC_LOG_LEVEL_MAX)
 		return -EINVAL;
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
 
-	if (i915_modparams.guc_log_level == val) {
+	if (log->level == level) {
 		ret = 0;
 		goto out_unlock;
 	}
 
 	intel_runtime_pm_get(dev_priv);
-	ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(val),
-				     GUC_LOG_LEVEL_IS_ENABLED(val),
-				     GUC_LOG_LEVEL_TO_VERBOSITY(val));
+	ret = guc_action_control_log(guc, GUC_LOG_LEVEL_IS_VERBOSE(level),
+				     GUC_LOG_LEVEL_IS_ENABLED(level),
+				     GUC_LOG_LEVEL_TO_VERBOSITY(level));
 	intel_runtime_pm_put(dev_priv);
 	if (ret) {
 		DRM_DEBUG_DRIVER("guc_log_control action failed %d\n", ret);
 		goto out_unlock;
 	}
 
-	i915_modparams.guc_log_level = val;
+	log->level = level;
 
 out_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/intel_guc_log.h b/drivers/gpu/drm/i915/intel_guc_log.h
index fa80535a6f9d..f38c48950ed4 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/intel_guc_log.h
@@ -30,6 +30,7 @@
 #include <linux/workqueue.h>
 
 #include "intel_guc_fwif.h"
+#include "i915_gem.h"
 
 struct intel_guc;
 
@@ -58,6 +59,7 @@ struct intel_guc;
 #define GUC_LOG_LEVEL_MAX GUC_VERBOSITY_TO_LOG_LEVEL(GUC_LOG_VERBOSITY_MAX)
 
 struct intel_guc_log {
+	u32 level;
 	u32 flags;
 	struct i915_vma *vma;
 	struct {
@@ -80,8 +82,7 @@ void intel_guc_log_init_early(struct intel_guc_log *log);
 int intel_guc_log_create(struct intel_guc_log *log);
 void intel_guc_log_destroy(struct intel_guc_log *log);
 
-int intel_guc_log_level_get(struct intel_guc_log *log);
-int intel_guc_log_level_set(struct intel_guc_log *log, u64 control_val);
+int intel_guc_log_set_level(struct intel_guc_log *log, u32 level);
 bool intel_guc_log_relay_enabled(const struct intel_guc_log *log);
 int intel_guc_log_relay_open(struct intel_guc_log *log);
 void intel_guc_log_relay_flush(struct intel_guc_log *log);
@@ -89,4 +90,9 @@ void intel_guc_log_relay_close(struct intel_guc_log *log);
 
 void intel_guc_log_handle_flush_event(struct intel_guc_log *log);
 
+static inline u32 intel_guc_log_get_level(struct intel_guc_log *log)
+{
+	return log->level;
+}
+
 #endif
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 6a73e81f373b..94e8863bd97c 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -207,7 +207,7 @@ void intel_uc_init_mmio(struct drm_i915_private *i915)
 
 static void guc_capture_load_err_log(struct intel_guc *guc)
 {
-	if (!guc->log.vma || !i915_modparams.guc_log_level)
+	if (!guc->log.vma || !intel_guc_log_get_level(&guc->log))
 		return;
 
 	if (!guc->load_err_log)
-- 
cgit v1.2.3


From 24d891d81312ab3921ce735952d8d2ad34dd90fb Mon Sep 17 00:00:00 2001
From: Piotr Piorkowski <piotr.piorkowski@intel.com>
Date: Mon, 4 Jun 2018 16:19:42 +0200
Subject: drm/i915/guc: Refactoring preparation of the GUC_CTL_DEBUG parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At the moment, the preparation of GUC_CTL_DEBUG is disordered.
Lets move all GUC_CTL_DEBUG related operations to one place.

v2:
- move 'ads' declaration to USES_GUC_SUBMISSION case (Michał Wajdeczko)

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604141947.8299-2-piotr.piorkowski@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 98b7c121162a..843dfe6b58e2 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -217,6 +217,13 @@ static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 		flags |= GUC_LOG_LEVEL_TO_VERBOSITY(level) <<
 			 GUC_LOG_VERBOSITY_SHIFT;
 
+	if (USES_GUC_SUBMISSION(guc_to_i915(guc))) {
+		u32 ads = intel_guc_ggtt_offset(guc, guc->ads_vma)
+			>> PAGE_SHIFT;
+
+		flags |= ads << GUC_ADS_ADDR_SHIFT | GUC_ADS_ENABLED;
+	}
+
 	return flags;
 }
 
@@ -252,14 +259,9 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	/* If GuC submission is enabled, set up additional parameters here */
 	if (USES_GUC_SUBMISSION(dev_priv)) {
-		u32 ads = intel_guc_ggtt_offset(guc,
-						guc->ads_vma) >> PAGE_SHIFT;
 		u32 pgs = intel_guc_ggtt_offset(guc, guc->stage_desc_pool);
 		u32 ctx_in_16 = GUC_MAX_STAGE_DESCRIPTORS / 16;
 
-		params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
-		params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED;
-
 		pgs >>= PAGE_SHIFT;
 		params[GUC_CTL_CTXINFO] = (pgs << GUC_CTL_BASE_ADDR_SHIFT) |
 			(ctx_in_16 << GUC_CTL_CTXNUM_IN16_SHIFT);
-- 
cgit v1.2.3


From dc755faef2640ea3d9ef3714c4ac5ece28bfe5a3 Mon Sep 17 00:00:00 2001
From: Piotr Piorkowski <piotr.piorkowski@intel.com>
Date: Mon, 4 Jun 2018 16:19:43 +0200
Subject: drm/i915/guc: Refactoring preparation of the GUC_CTL_FEATURE
 parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At the moment, the preparation of GUC_CTL_FEATURE is disordered.
Lets move all GUC_CTL_FEATURE related operations to one place.

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604141947.8299-3-piotr.piorkowski@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 843dfe6b58e2..dfc5ef8be9f0 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -227,6 +227,19 @@ static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 	return flags;
 }
 
+static u32 guc_ctl_feature_flags(struct intel_guc *guc)
+{
+	u32 flags = 0;
+
+	flags |=  GUC_CTL_VCS2_ENABLED;
+
+	if (USES_GUC_SUBMISSION(guc_to_i915(guc)))
+		flags |= GUC_CTL_KERNEL_SUBMISSIONS;
+	else
+		flags |= GUC_CTL_DISABLE_SCHEDULER;
+
+	return flags;
+}
 /*
  * Initialise the GuC parameter block before starting the firmware
  * transfer. These parameters are read by the firmware on startup
@@ -250,9 +263,7 @@ void intel_guc_init_params(struct intel_guc *guc)
 
 	params[GUC_CTL_WA] |= GUC_CTL_WA_UK_BY_DRIVER;
 
-	params[GUC_CTL_FEATURE] |= GUC_CTL_DISABLE_SCHEDULER |
-			GUC_CTL_VCS2_ENABLED;
-
+	params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc);
 	params[GUC_CTL_LOG_PARAMS] = guc->log.flags;
 
 	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
@@ -265,11 +276,6 @@ void intel_guc_init_params(struct intel_guc *guc)
 		pgs >>= PAGE_SHIFT;
 		params[GUC_CTL_CTXINFO] = (pgs << GUC_CTL_BASE_ADDR_SHIFT) |
 			(ctx_in_16 << GUC_CTL_CTXNUM_IN16_SHIFT);
-
-		params[GUC_CTL_FEATURE] |= GUC_CTL_KERNEL_SUBMISSIONS;
-
-		/* Unmask this bit to enable the GuC's internal scheduler */
-		params[GUC_CTL_FEATURE] &= ~GUC_CTL_DISABLE_SCHEDULER;
 	}
 
 	/*
-- 
cgit v1.2.3


From 532717b90bd0159f221a6f5f1d0b35514e88192b Mon Sep 17 00:00:00 2001
From: Piotr Piorkowski <piotr.piorkowski@intel.com>
Date: Mon, 4 Jun 2018 16:19:44 +0200
Subject: drm/i915/guc: Refactoring preparation of the GUC_CTL_LOG_PARAMS
 parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At the moment, the preparation of GUC_CTL_LOG_PARAMS is disordered.
Additionally, in struct intel_guc_log we have an unnecessary field
'flags' which we use only to assign value to GuC parameter.
Lets move all GUC_CTL_LOG_PARAMS related operations to one place,
and lets remove field 'flags' from struct intel_guc_log.

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604141947.8299-4-piotr.piorkowski@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c     | 19 +++++++++++++++++--
 drivers/gpu/drm/i915/intel_guc_log.c | 11 -----------
 drivers/gpu/drm/i915/intel_guc_log.h |  1 -
 3 files changed, 17 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index dfc5ef8be9f0..d2d2cc1d6d46 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -240,6 +240,22 @@ static u32 guc_ctl_feature_flags(struct intel_guc *guc)
 
 	return flags;
 }
+
+static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
+{
+	u32 offset = intel_guc_ggtt_offset(guc, guc->log.vma) >> PAGE_SHIFT;
+	u32 flags;
+
+	/* each allocated unit is a page */
+	flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL |
+		(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT) |
+		(GUC_LOG_DPC_PAGES << GUC_LOG_DPC_SHIFT) |
+		(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
+		(offset << GUC_LOG_BUF_ADDR_SHIFT);
+
+	return flags;
+}
+
 /*
  * Initialise the GuC parameter block before starting the firmware
  * transfer. These parameters are read by the firmware on startup
@@ -264,8 +280,7 @@ void intel_guc_init_params(struct intel_guc *guc)
 	params[GUC_CTL_WA] |= GUC_CTL_WA_UK_BY_DRIVER;
 
 	params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc);
-	params[GUC_CTL_LOG_PARAMS] = guc->log.flags;
-
+	params[GUC_CTL_LOG_PARAMS]  = guc_ctl_log_params_flags(guc);
 	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
 
 	/* If GuC submission is enabled, set up additional parameters here */
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index d35d883d48e1..b921c948c7f5 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -452,8 +452,6 @@ int intel_guc_log_create(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct i915_vma *vma;
-	unsigned long offset;
-	u32 flags;
 	int ret;
 
 	GEM_BUG_ON(log->vma);
@@ -466,15 +464,6 @@ int intel_guc_log_create(struct intel_guc_log *log)
 
 	log->vma = vma;
 
-	/* each allocated unit is a page */
-	flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL |
-		(GUC_LOG_DPC_PAGES << GUC_LOG_DPC_SHIFT) |
-		(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
-		(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT);
-
-	offset = intel_guc_ggtt_offset(guc, vma) >> PAGE_SHIFT;
-	log->flags = (offset << GUC_LOG_BUF_ADDR_SHIFT) | flags;
-
 	log->level = i915_modparams.guc_log_level;
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/intel_guc_log.h b/drivers/gpu/drm/i915/intel_guc_log.h
index f38c48950ed4..196e2199a3e2 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/intel_guc_log.h
@@ -60,7 +60,6 @@ struct intel_guc;
 
 struct intel_guc_log {
 	u32 level;
-	u32 flags;
 	struct i915_vma *vma;
 	struct {
 		void *buf_addr;
-- 
cgit v1.2.3


From 741cebee0aa59cdaafb798c66171c2a863c3fa32 Mon Sep 17 00:00:00 2001
From: Piotr Piorkowski <piotr.piorkowski@intel.com>
Date: Mon, 4 Jun 2018 16:19:45 +0200
Subject: drm/i915/guc: Refactoring preparation of the GUC_CTL_CTXINFO
 parameter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At the moment, the preparation of GUC_CTL_CTXINFO is disordered.
Lets move all  GUC_CTL_CTXINFO related operations to one place.

v2:
- move 'ctxnum' and 'base' declarations to USES_GUC_SUBMISSION case
(Michał Wajdeczko)

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604141947.8299-5-piotr.piorkowski@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index d2d2cc1d6d46..dce475eaa39b 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -241,6 +241,23 @@ static u32 guc_ctl_feature_flags(struct intel_guc *guc)
 	return flags;
 }
 
+static u32 guc_ctl_ctxinfo_flags(struct intel_guc *guc)
+{
+	u32 flags = 0;
+
+	if (USES_GUC_SUBMISSION(guc_to_i915(guc))) {
+		u32 ctxnum, base;
+
+		base = intel_guc_ggtt_offset(guc, guc->stage_desc_pool);
+		ctxnum = GUC_MAX_STAGE_DESCRIPTORS / 16;
+
+		base >>= PAGE_SHIFT;
+		flags |= (base << GUC_CTL_BASE_ADDR_SHIFT) |
+			(ctxnum << GUC_CTL_CTXNUM_IN16_SHIFT);
+	}
+	return flags;
+}
+
 static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
 {
 	u32 offset = intel_guc_ggtt_offset(guc, guc->log.vma) >> PAGE_SHIFT;
@@ -282,16 +299,7 @@ void intel_guc_init_params(struct intel_guc *guc)
 	params[GUC_CTL_FEATURE] = guc_ctl_feature_flags(guc);
 	params[GUC_CTL_LOG_PARAMS]  = guc_ctl_log_params_flags(guc);
 	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
-
-	/* If GuC submission is enabled, set up additional parameters here */
-	if (USES_GUC_SUBMISSION(dev_priv)) {
-		u32 pgs = intel_guc_ggtt_offset(guc, guc->stage_desc_pool);
-		u32 ctx_in_16 = GUC_MAX_STAGE_DESCRIPTORS / 16;
-
-		pgs >>= PAGE_SHIFT;
-		params[GUC_CTL_CTXINFO] = (pgs << GUC_CTL_BASE_ADDR_SHIFT) |
-			(ctx_in_16 << GUC_CTL_CTXNUM_IN16_SHIFT);
-	}
+	params[GUC_CTL_CTXINFO] = guc_ctl_ctxinfo_flags(guc);
 
 	/*
 	 * All SOFT_SCRATCH registers are in FORCEWAKE_BLITTER domain and
-- 
cgit v1.2.3


From 5288c7182dd389bb03b0a1aa38550b344fe5bf97 Mon Sep 17 00:00:00 2001
From: Piotr Piorkowski <piotr.piorkowski@intel.com>
Date: Tue, 5 Jun 2018 17:13:29 +0200
Subject: drm/i915/guc: Move defines with size of GuC logs to intel_guc_log.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At this moment, we have defined GuC logs sizes in intel_guc_fwif.h, but
as these values are related directly to the GuC logs, and not to API of
GuC parameters, we should move these defines to intel_guc_log.h.

v2:
- change buffers size to more friendly (Michał Wajdeczko)
- remove GUC_LOG_SIZE define (Michał Wajdeczko)
v3:
- use SZ_* macros to define buffers sizes (Michał Wajdeczko)

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605151330.9954-1-piotr.piorkowski@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c      | 28 +++++++++++++++++++++++-----
 drivers/gpu/drm/i915/intel_guc_fwif.h | 20 +++-----------------
 drivers/gpu/drm/i915/intel_guc_log.c  | 33 ++++++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/intel_guc_log.h  |  9 +++------
 4 files changed, 57 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index dce475eaa39b..4101264cf566 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -263,13 +263,31 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
 	u32 offset = intel_guc_ggtt_offset(guc, guc->log.vma) >> PAGE_SHIFT;
 	u32 flags;
 
-	/* each allocated unit is a page */
-	flags = GUC_LOG_VALID | GUC_LOG_NOTIFY_ON_HALF_FULL |
-		(GUC_LOG_CRASH_PAGES << GUC_LOG_CRASH_SHIFT) |
-		(GUC_LOG_DPC_PAGES << GUC_LOG_DPC_SHIFT) |
-		(GUC_LOG_ISR_PAGES << GUC_LOG_ISR_SHIFT) |
+	#define UNIT SZ_4K
+
+	BUILD_BUG_ON(!CRASH_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, UNIT));
+	BUILD_BUG_ON(!DPC_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(DPC_BUFFER_SIZE, UNIT));
+	BUILD_BUG_ON(!ISR_BUFFER_SIZE);
+	BUILD_BUG_ON(!IS_ALIGNED(ISR_BUFFER_SIZE, UNIT));
+
+	BUILD_BUG_ON((CRASH_BUFFER_SIZE / UNIT - 1) >
+			(GUC_LOG_CRASH_MASK >> GUC_LOG_CRASH_SHIFT));
+	BUILD_BUG_ON((DPC_BUFFER_SIZE / UNIT - 1) >
+			(GUC_LOG_DPC_MASK >> GUC_LOG_DPC_SHIFT));
+	BUILD_BUG_ON((ISR_BUFFER_SIZE / UNIT - 1) >
+			(GUC_LOG_ISR_MASK >> GUC_LOG_ISR_SHIFT));
+
+	flags = GUC_LOG_VALID |
+		GUC_LOG_NOTIFY_ON_HALF_FULL |
+		((CRASH_BUFFER_SIZE / UNIT - 1) << GUC_LOG_CRASH_SHIFT) |
+		((DPC_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DPC_SHIFT) |
+		((ISR_BUFFER_SIZE / UNIT - 1) << GUC_LOG_ISR_SHIFT) |
 		(offset << GUC_LOG_BUF_ADDR_SHIFT);
 
+	#undef UNIT
+
 	return flags;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_guc_fwif.h b/drivers/gpu/drm/i915/intel_guc_fwif.h
index 0867ba76d445..1a0f2a39cef9 100644
--- a/drivers/gpu/drm/i915/intel_guc_fwif.h
+++ b/drivers/gpu/drm/i915/intel_guc_fwif.h
@@ -84,12 +84,12 @@
 #define   GUC_LOG_VALID			(1 << 0)
 #define   GUC_LOG_NOTIFY_ON_HALF_FULL	(1 << 1)
 #define   GUC_LOG_ALLOC_IN_MEGABYTE	(1 << 3)
-#define   GUC_LOG_CRASH_PAGES		1
 #define   GUC_LOG_CRASH_SHIFT		4
-#define   GUC_LOG_DPC_PAGES		7
+#define   GUC_LOG_CRASH_MASK		(0x1 << GUC_LOG_CRASH_SHIFT)
 #define   GUC_LOG_DPC_SHIFT		6
-#define   GUC_LOG_ISR_PAGES		7
+#define   GUC_LOG_DPC_MASK	        (0x7 << GUC_LOG_DPC_SHIFT)
 #define   GUC_LOG_ISR_SHIFT		9
+#define   GUC_LOG_ISR_MASK	        (0x7 << GUC_LOG_ISR_SHIFT)
 #define   GUC_LOG_BUF_ADDR_SHIFT	12
 
 #define GUC_CTL_PAGE_FAULT_CONTROL	5
@@ -532,20 +532,6 @@ enum guc_log_buffer_type {
 };
 
 /**
- * DOC: GuC Log buffer Layout
- *
- * Page0  +-------------------------------+
- *        |   ISR state header (32 bytes) |
- *        |      DPC state header         |
- *        |   Crash dump state header     |
- * Page1  +-------------------------------+
- *        |           ISR logs            |
- * Page9  +-------------------------------+
- *        |           DPC logs            |
- * Page17 +-------------------------------+
- *        |         Crash Dump logs       |
- *        +-------------------------------+
- *
  * Below state structure is used for coordination of retrieval of GuC firmware
  * logs. Separate state is maintained for each log buffer type.
  * read_ptr points to the location where i915 read last in log buffer and
diff --git a/drivers/gpu/drm/i915/intel_guc_log.c b/drivers/gpu/drm/i915/intel_guc_log.c
index b921c948c7f5..6da61a71d28f 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/intel_guc_log.c
@@ -215,11 +215,11 @@ static unsigned int guc_get_log_buffer_size(enum guc_log_buffer_type type)
 {
 	switch (type) {
 	case GUC_ISR_LOG_BUFFER:
-		return (GUC_LOG_ISR_PAGES + 1) * PAGE_SIZE;
+		return ISR_BUFFER_SIZE;
 	case GUC_DPC_LOG_BUFFER:
-		return (GUC_LOG_DPC_PAGES + 1) * PAGE_SIZE;
+		return DPC_BUFFER_SIZE;
 	case GUC_CRASH_DUMP_LOG_BUFFER:
-		return (GUC_LOG_CRASH_PAGES + 1) * PAGE_SIZE;
+		return CRASH_BUFFER_SIZE;
 	default:
 		MISSING_CASE(type);
 	}
@@ -397,7 +397,7 @@ static int guc_log_relay_create(struct intel_guc_log *log)
 	lockdep_assert_held(&log->relay.lock);
 
 	 /* Keep the size of sub buffers same as shared log buffer */
-	subbuf_size = GUC_LOG_SIZE;
+	subbuf_size = log->vma->size;
 
 	/*
 	 * Store up to 8 snapshots, which is large enough to buffer sufficient
@@ -452,11 +452,34 @@ int intel_guc_log_create(struct intel_guc_log *log)
 {
 	struct intel_guc *guc = log_to_guc(log);
 	struct i915_vma *vma;
+	u32 guc_log_size;
 	int ret;
 
 	GEM_BUG_ON(log->vma);
 
-	vma = intel_guc_allocate_vma(guc, GUC_LOG_SIZE);
+	/*
+	 *  GuC Log buffer Layout
+	 *
+	 *  +===============================+ 00B
+	 *  |    Crash dump state header    |
+	 *  +-------------------------------+ 32B
+	 *  |       DPC state header        |
+	 *  +-------------------------------+ 64B
+	 *  |       ISR state header        |
+	 *  +-------------------------------+ 96B
+	 *  |                               |
+	 *  +===============================+ PAGE_SIZE (4KB)
+	 *  |        Crash Dump logs        |
+	 *  +===============================+ + CRASH_SIZE
+	 *  |           DPC logs            |
+	 *  +===============================+ + DPC_SIZE
+	 *  |           ISR logs            |
+	 *  +===============================+ + ISR_SIZE
+	 */
+	guc_log_size = PAGE_SIZE + CRASH_BUFFER_SIZE + DPC_BUFFER_SIZE +
+			ISR_BUFFER_SIZE;
+
+	vma = intel_guc_allocate_vma(guc, guc_log_size);
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
 		goto err;
diff --git a/drivers/gpu/drm/i915/intel_guc_log.h b/drivers/gpu/drm/i915/intel_guc_log.h
index 196e2199a3e2..dfc07210a107 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/intel_guc_log.h
@@ -34,12 +34,9 @@
 
 struct intel_guc;
 
-/*
- * The first page is to save log buffer state. Allocate one
- * extra page for others in case for overlap
- */
-#define GUC_LOG_SIZE	((1 + GUC_LOG_DPC_PAGES + 1 + GUC_LOG_ISR_PAGES + \
-			  1 + GUC_LOG_CRASH_PAGES + 1) << PAGE_SHIFT)
+#define CRASH_BUFFER_SIZE	SZ_8K
+#define DPC_BUFFER_SIZE		SZ_32K
+#define ISR_BUFFER_SIZE		SZ_32K
 
 /*
  * While we're using plain log level in i915, GuC controls are much more...
-- 
cgit v1.2.3


From 3d6d62eae7d75a902f4eacdbb2d775c7c27f3987 Mon Sep 17 00:00:00 2001
From: Piotr Piorkowski <piotr.piorkowski@intel.com>
Date: Tue, 5 Jun 2018 17:13:30 +0200
Subject: drm/i915/guc: Add support for define guc_log_size in megabytes.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At this moment we can define GuC logs sizes only using pages.
But GuC also allows use for this values expressed in megabytes.
Lets add support for define guc_log_size in megabytes when we
debug of GuC.

v2:
- change buffers size to more friendly (Michał Wajdeczko)
- merge statements in guc_ctl_log_params_flags() (Michał Wajdeczko)
v3:
- fix ifdef (rename DRM_I915_DEBUG_GUC to CONFIG_DRM_I915_DEBUG_GUC)
(Michał Wajdeczko)
- use SZ_* macros to define buffers sizes (Michał Wajdeczko)

Signed-off-by: Piotr Piórkowski <piotr.piorkowski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605151330.9954-2-piotr.piorkowski@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c     | 8 ++++++++
 drivers/gpu/drm/i915/intel_guc_log.h | 6 ++++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 4101264cf566..1aff30b0870c 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -263,7 +263,13 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
 	u32 offset = intel_guc_ggtt_offset(guc, guc->log.vma) >> PAGE_SHIFT;
 	u32 flags;
 
+	#if (((CRASH_BUFFER_SIZE) % SZ_1M) == 0)
+	#define UNIT SZ_1M
+	#define FLAG GUC_LOG_ALLOC_IN_MEGABYTE
+	#else
 	#define UNIT SZ_4K
+	#define FLAG 0
+	#endif
 
 	BUILD_BUG_ON(!CRASH_BUFFER_SIZE);
 	BUILD_BUG_ON(!IS_ALIGNED(CRASH_BUFFER_SIZE, UNIT));
@@ -281,12 +287,14 @@ static u32 guc_ctl_log_params_flags(struct intel_guc *guc)
 
 	flags = GUC_LOG_VALID |
 		GUC_LOG_NOTIFY_ON_HALF_FULL |
+		FLAG |
 		((CRASH_BUFFER_SIZE / UNIT - 1) << GUC_LOG_CRASH_SHIFT) |
 		((DPC_BUFFER_SIZE / UNIT - 1) << GUC_LOG_DPC_SHIFT) |
 		((ISR_BUFFER_SIZE / UNIT - 1) << GUC_LOG_ISR_SHIFT) |
 		(offset << GUC_LOG_BUF_ADDR_SHIFT);
 
 	#undef UNIT
+	#undef FLAG
 
 	return flags;
 }
diff --git a/drivers/gpu/drm/i915/intel_guc_log.h b/drivers/gpu/drm/i915/intel_guc_log.h
index dfc07210a107..7bc763f10c03 100644
--- a/drivers/gpu/drm/i915/intel_guc_log.h
+++ b/drivers/gpu/drm/i915/intel_guc_log.h
@@ -34,9 +34,15 @@
 
 struct intel_guc;
 
+#ifdef CONFIG_DRM_I915_DEBUG_GUC
+#define CRASH_BUFFER_SIZE	SZ_2M
+#define DPC_BUFFER_SIZE		SZ_8M
+#define ISR_BUFFER_SIZE		SZ_8M
+#else
 #define CRASH_BUFFER_SIZE	SZ_8K
 #define DPC_BUFFER_SIZE		SZ_32K
 #define ISR_BUFFER_SIZE		SZ_32K
+#endif
 
 /*
  * While we're using plain log level in i915, GuC controls are much more...
-- 
cgit v1.2.3


From e9e7dc4144cd6d4ba873fd506fe38bccb9dbbd85 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 12 Jun 2018 13:04:46 +0100
Subject: drm/i915/gtt: Make gen6 page directories evictable

Currently all page directories are bound at creation using an
unevictable node in the GGTT. This severely limits us as we cannot
remove any inactive ppgtt for new contexts, or under aperture pressure.
To fix this we need to make the page directory into a first class and
unbindable vma. Hence, the creation of a custom vma to wrap the page
directory as opposed to a GEM object.

In this patch, we leave the page directories pinned upon creation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612120446.13901-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 257 +++++++++++++++++++++---------------
 drivers/gpu/drm/i915/i915_gem_gtt.h |   2 +-
 drivers/gpu/drm/i915/i915_vma.h     |   7 +
 3 files changed, 155 insertions(+), 111 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 40a839119d23..267f1f97b9f0 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1640,50 +1640,55 @@ static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
 	struct i915_address_space *vm = &base->vm;
-	struct i915_page_table *unused;
-	gen6_pte_t scratch_pte;
-	u32 pd_entry, pte, pde;
-
-	scratch_pte = vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
-
-	gen6_for_all_pdes(unused, &base->pd, pde) {
-		u32 expected;
-		gen6_pte_t *pt_vaddr;
-		const dma_addr_t pt_addr = px_dma(base->pd.page_table[pde]);
-		pd_entry = readl(ppgtt->pd_addr + pde);
-		expected = (GEN6_PDE_ADDR_ENCODE(pt_addr) | GEN6_PDE_VALID);
-
-		if (pd_entry != expected)
-			seq_printf(m, "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
-				   pde,
-				   pd_entry,
-				   expected);
-		seq_printf(m, "\tPDE: %x\n", pd_entry);
-
-		pt_vaddr = kmap_atomic_px(base->pd.page_table[pde]);
-
-		for (pte = 0; pte < GEN6_PTES; pte+=4) {
-			unsigned long va =
-				(pde * PAGE_SIZE * GEN6_PTES) +
-				(pte * PAGE_SIZE);
+	const gen6_pte_t scratch_pte =
+		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
+	struct i915_page_table *pt;
+	u32 pte, pde;
+
+	gen6_for_all_pdes(pt, &base->pd, pde) {
+		gen6_pte_t *vaddr;
+
+		if (pt == base->vm.scratch_pt)
+			continue;
+
+		if (i915_vma_is_bound(ppgtt->vma, I915_VMA_GLOBAL_BIND)) {
+			u32 expected =
+				GEN6_PDE_ADDR_ENCODE(px_dma(pt)) |
+				GEN6_PDE_VALID;
+			u32 pd_entry = readl(ppgtt->pd_addr + pde);
+
+			if (pd_entry != expected)
+				seq_printf(m,
+					   "\tPDE #%d mismatch: Actual PDE: %x Expected PDE: %x\n",
+					   pde,
+					   pd_entry,
+					   expected);
+
+			seq_printf(m, "\tPDE: %x\n", pd_entry);
+		}
+
+		vaddr = kmap_atomic_px(base->pd.page_table[pde]);
+		for (pte = 0; pte < GEN6_PTES; pte += 4) {
 			int i;
-			bool found = false;
+
 			for (i = 0; i < 4; i++)
-				if (pt_vaddr[pte + i] != scratch_pte)
-					found = true;
-			if (!found)
+				if (vaddr[pte + i] != scratch_pte)
+					break;
+			if (i == 4)
 				continue;
 
-			seq_printf(m, "\t\t0x%lx [%03d,%04d]: =", va, pde, pte);
+			seq_printf(m, "\t\t(%03d, %04d) %08lx: ",
+				   pde, pte,
+				   (pde * GEN6_PTES + pte) * PAGE_SIZE);
 			for (i = 0; i < 4; i++) {
-				if (pt_vaddr[pte + i] != scratch_pte)
-					seq_printf(m, " %08x", pt_vaddr[pte + i]);
+				if (vaddr[pte + i] != scratch_pte)
+					seq_printf(m, " %08x", vaddr[pte + i]);
 				else
-					seq_puts(m, "  SCRATCH ");
+					seq_puts(m, "  SCRATCH");
 			}
 			seq_puts(m, "\n");
 		}
-		kunmap_atomic(pt_vaddr);
+		kunmap_atomic(vaddr);
 	}
 }
 
@@ -1697,22 +1702,6 @@ static inline void gen6_write_pde(const struct gen6_hw_ppgtt *ppgtt,
 		  ppgtt->pd_addr + pde);
 }
 
-/* Write all the page tables found in the ppgtt structure to incrementing page
- * directories. */
-static void gen6_write_page_range(struct i915_hw_ppgtt *base,
-				  u32 start, u32 length)
-{
-	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
-	struct i915_page_table *pt;
-	unsigned int pde;
-
-	gen6_for_each_pde(pt, &base->pd, start, length, pde)
-		gen6_write_pde(ppgtt, pde, pt);
-
-	mark_tlbs_dirty(base);
-	gen6_ggtt_invalidate(base->vm.i915);
-}
-
 static void gen8_ppgtt_enable(struct drm_i915_private *dev_priv)
 {
 	struct intel_engine_cs *engine;
@@ -1858,8 +1847,12 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 
 			gen6_initialize_pt(vm, pt);
 			ppgtt->base.pd.page_table[pde] = pt;
-			gen6_write_pde(ppgtt, pde, pt);
-			flush = true;
+
+			if (i915_vma_is_bound(ppgtt->vma,
+					      I915_VMA_GLOBAL_BIND)) {
+				gen6_write_pde(ppgtt, pde, pt);
+				flush = true;
+			}
 		}
 	}
 
@@ -1875,8 +1868,11 @@ unwind_out:
 	return -ENOMEM;
 }
 
-static int gen6_ppgtt_init_scratch(struct i915_address_space *vm)
+static int gen6_ppgtt_init_scratch(struct gen6_hw_ppgtt *ppgtt)
 {
+	struct i915_address_space * const vm = &ppgtt->base.vm;
+	struct i915_page_table *unused;
+	u32 pde;
 	int ret;
 
 	ret = setup_scratch_page(vm, __GFP_HIGHMEM);
@@ -1890,6 +1886,8 @@ static int gen6_ppgtt_init_scratch(struct i915_address_space *vm)
 	}
 
 	gen6_initialize_pt(vm, vm->scratch_pt);
+	gen6_for_all_pdes(unused, &ppgtt->base.pd, pde)
+		ppgtt->base.pd.page_table[pde] = vm->scratch_pt;
 
 	return 0;
 }
@@ -1914,52 +1912,104 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 
-	drm_mm_remove_node(&ppgtt->node);
+	i915_vma_unpin(ppgtt->vma);
+	i915_vma_destroy(ppgtt->vma);
 
 	gen6_ppgtt_free_pd(ppgtt);
 	gen6_ppgtt_free_scratch(vm);
 }
 
-static int gen6_ppgtt_allocate_page_directories(struct gen6_hw_ppgtt *ppgtt)
+static int pd_vma_set_pages(struct i915_vma *vma)
 {
-	struct drm_i915_private *dev_priv = ppgtt->base.vm.i915;
-	struct i915_ggtt *ggtt = &dev_priv->ggtt;
-	int err;
+	vma->pages = ERR_PTR(-ENODEV);
+	return 0;
+}
 
-	/* PPGTT PDEs reside in the GGTT and consists of 512 entries. The
-	 * allocator works in address space sizes, so it's multiplied by page
-	 * size. We allocate at the top of the GTT to avoid fragmentation.
-	 */
-	BUG_ON(!drm_mm_initialized(&ggtt->vm.mm));
+static void pd_vma_clear_pages(struct i915_vma *vma)
+{
+	GEM_BUG_ON(!vma->pages);
 
-	err = i915_gem_gtt_insert(&ggtt->vm, &ppgtt->node,
-				  GEN6_PD_SIZE, GEN6_PD_ALIGN,
-				  I915_COLOR_UNEVICTABLE,
-				  0, ggtt->vm.total,
-				  PIN_HIGH);
-	if (err)
-		return err;
+	vma->pages = NULL;
+}
+
+static int pd_vma_bind(struct i915_vma *vma,
+		       enum i915_cache_level cache_level,
+		       u32 unused)
+{
+	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vma->vm);
+	struct gen6_hw_ppgtt *ppgtt = vma->private;
+	u32 ggtt_offset = i915_ggtt_offset(vma) / PAGE_SIZE;
+	struct i915_page_table *pt;
+	unsigned int pde;
 
-	if (ppgtt->node.start < ggtt->mappable_end)
-		DRM_DEBUG("Forced to use aperture for PDEs\n");
+	ppgtt->base.pd.base.ggtt_offset = ggtt_offset * sizeof(gen6_pte_t);
+	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm + ggtt_offset;
 
-	ppgtt->base.pd.base.ggtt_offset =
-		ppgtt->node.start / PAGE_SIZE * sizeof(gen6_pte_t);
+	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde)
+		gen6_write_pde(ppgtt, pde, pt);
 
-	ppgtt->pd_addr = (gen6_pte_t __iomem *)ggtt->gsm +
-		ppgtt->base.pd.base.ggtt_offset / sizeof(gen6_pte_t);
+	mark_tlbs_dirty(&ppgtt->base);
+	gen6_ggtt_invalidate(ppgtt->base.vm.i915);
 
 	return 0;
 }
 
-static void gen6_scratch_va_range(struct gen6_hw_ppgtt *ppgtt,
-				  u64 start, u64 length)
+static void pd_vma_unbind(struct i915_vma *vma)
 {
-	struct i915_page_table *unused;
-	u32 pde;
+}
 
-	gen6_for_each_pde(unused, &ppgtt->base.pd, start, length, pde)
-		ppgtt->base.pd.page_table[pde] = ppgtt->base.vm.scratch_pt;
+static const struct i915_vma_ops pd_vma_ops = {
+	.set_pages = pd_vma_set_pages,
+	.clear_pages = pd_vma_clear_pages,
+	.bind_vma = pd_vma_bind,
+	.unbind_vma = pd_vma_unbind,
+};
+
+static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
+{
+	struct drm_i915_private *i915 = ppgtt->base.vm.i915;
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct i915_vma *vma;
+	int i;
+
+	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
+	GEM_BUG_ON(size > ggtt->vm.total);
+
+	vma = kmem_cache_zalloc(i915->vmas, GFP_KERNEL);
+	if (!vma)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
+		init_request_active(&vma->last_read[i], NULL);
+	init_request_active(&vma->last_fence, NULL);
+
+	vma->vm = &ggtt->vm;
+	vma->ops = &pd_vma_ops;
+	vma->private = ppgtt;
+
+	vma->size = size;
+	vma->fence_size = size;
+	vma->flags = I915_VMA_GGTT;
+	vma->ggtt_view.type = I915_GGTT_VIEW_ROTATED; /* prevent fencing */
+
+	INIT_LIST_HEAD(&vma->obj_link);
+	list_add(&vma->vm_link, &vma->vm->unbound_list);
+
+	return vma;
+}
+
+static int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
+{
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
+
+	/*
+	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
+	 * allocator works in address space sizes, so it's multiplied by page
+	 * size. We allocate at the top of the GTT to avoid fragmentation.
+	 */
+	return i915_vma_pin(ppgtt->vma,
+			    0, GEN6_PD_ALIGN,
+			    PIN_GLOBAL | PIN_HIGH);
 }
 
 static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
@@ -1989,24 +2039,27 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 
 	ppgtt->base.vm.pte_encode = ggtt->vm.pte_encode;
 
-	err = gen6_ppgtt_init_scratch(&ppgtt->base.vm);
+	err = gen6_ppgtt_init_scratch(ppgtt);
 	if (err)
 		goto err_free;
 
-	err = gen6_ppgtt_allocate_page_directories(ppgtt);
-	if (err)
+	ppgtt->vma = pd_vma_create(ppgtt, GEN6_PD_SIZE);
+	if (IS_ERR(ppgtt->vma)) {
+		err = PTR_ERR(ppgtt->vma);
 		goto err_scratch;
-
-	gen6_scratch_va_range(ppgtt, 0, ppgtt->base.vm.total);
-	gen6_write_page_range(&ppgtt->base, 0, ppgtt->base.vm.total);
+	}
 
 	err = gen6_alloc_va_range(&ppgtt->base.vm, 0, ppgtt->base.vm.total);
+	if (err)
+		goto err_vma;
+
+	err = gen6_ppgtt_pin(&ppgtt->base);
 	if (err)
 		goto err_pd;
 
 	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
-			 ppgtt->node.size >> 20,
-			 ppgtt->node.start / PAGE_SIZE);
+			 ppgtt->vma->node.size >> 20,
+			 ppgtt->vma->node.start / PAGE_SIZE);
 
 	DRM_DEBUG_DRIVER("Adding PPGTT at offset %x\n",
 			 ppgtt->base.pd.base.ggtt_offset << 10);
@@ -2015,6 +2068,8 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 
 err_pd:
 	gen6_ppgtt_free_pd(ppgtt);
+err_vma:
+	i915_vma_destroy(ppgtt->vma);
 err_scratch:
 	gen6_ppgtt_free_scratch(&ppgtt->base.vm);
 err_free:
@@ -3533,6 +3588,7 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 	}
 
 	ggtt->vm.closed = false;
+	i915_ggtt_invalidate(dev_priv);
 
 	if (INTEL_GEN(dev_priv) >= 8) {
 		struct intel_ppat *ppat = &dev_priv->ppat;
@@ -3541,25 +3597,6 @@ void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv)
 		dev_priv->ppat.update_hw(dev_priv);
 		return;
 	}
-
-	if (USES_PPGTT(dev_priv)) {
-		struct i915_address_space *vm;
-
-		list_for_each_entry(vm, &dev_priv->vm_list, global_link) {
-			struct i915_hw_ppgtt *ppgtt;
-
-			if (i915_is_ggtt(vm))
-				ppgtt = dev_priv->mm.aliasing_ppgtt;
-			else
-				ppgtt = i915_vm_to_ppgtt(vm);
-			if (!ppgtt)
-				continue;
-
-			gen6_write_page_range(ppgtt, 0, ppgtt->vm.total);
-		}
-	}
-
-	i915_ggtt_invalidate(dev_priv);
 }
 
 static struct scatterlist *
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 7d65d813eff0..6e9acd99ecc6 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -410,7 +410,7 @@ struct i915_hw_ppgtt {
 struct gen6_hw_ppgtt {
 	struct i915_hw_ppgtt base;
 
-	struct drm_mm_node node;
+	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
 };
 
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 4321476a6a32..66a228931517 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -54,6 +54,7 @@ struct i915_vma {
 	struct reservation_object *resv; /** Alias of obj->resv */
 	struct sg_table *pages;
 	void __iomem *iomap;
+	void *private; /* owned by creator */
 	u64 size;
 	u64 display_alignment;
 	struct i915_page_sizes page_sizes;
@@ -340,6 +341,12 @@ static inline void i915_vma_unpin(struct i915_vma *vma)
 	__i915_vma_unpin(vma);
 }
 
+static inline bool i915_vma_is_bound(const struct i915_vma *vma,
+				     unsigned int where)
+{
+	return vma->flags & where;
+}
+
 /**
  * i915_vma_pin_iomap - calls ioremap_wc to map the GGTT VMA via the aperture
  * @vma: VMA to iomap
-- 
cgit v1.2.3


From dccc7228b5de7658f79ad0074a57a8798462c533 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Mon, 21 May 2018 17:25:41 -0700
Subject: drm/i915/icl: Add DDI HDMI level selection for ICL

This patch adds a proper HDMI DDI entry level for vswing
programming sequences on ICL.

Spec doesn't specify any default for HDMI tables,
so let's pick the last entry as the default for now
to stay consistent with older platform like CNL.

Cc: Rakshmi Bhatia <rakshmi.bhatia@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-8-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_ddi.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index b344e0fe08fd..ca73387bd596 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -915,7 +915,14 @@ static int intel_ddi_hdmi_level(struct drm_i915_private *dev_priv, enum port por
 
 	level = dev_priv->vbt.ddi_port_info[port].hdmi_level_shift;
 
-	if (IS_CANNONLAKE(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		if (port == PORT_A || port == PORT_B)
+			icl_get_combo_buf_trans(dev_priv, port,
+						INTEL_OUTPUT_HDMI, &n_entries);
+		else
+			n_entries = ARRAY_SIZE(icl_mg_phy_ddi_translations);
+		default_entry = n_entries - 1;
+	} else if (IS_CANNONLAKE(dev_priv)) {
 		cnl_get_buf_trans_hdmi(dev_priv, &n_entries);
 		default_entry = n_entries - 1;
 	} else if (IS_GEN9_LP(dev_priv)) {
-- 
cgit v1.2.3


From af1f1b81130e82a1ee62fe48aa09e6bdab6e68f4 Mon Sep 17 00:00:00 2001
From: Mahesh Kumar <mahesh1.kumar@intel.com>
Date: Mon, 11 Jun 2018 17:25:11 -0700
Subject: drm/i915/icl: fix gmbus gpio pin mapping

ICP has GPIO pin 1/2 mapped to combo-phy ports & GPIO pins 9/10/11/12
mapped to tc ports[1-4].
This patch defines GPIOCTL registers for GPIO pins 9-12 & uses them in GPIO
pin mapping table.

Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Mahesh Kumar <mahesh1.kumar@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612002512.29783-1-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h   |  4 ++++
 drivers/gpu/drm/i915/intel_hdmi.c |  2 +-
 drivers/gpu/drm/i915/intel_i2c.c  | 12 ++++++------
 3 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 987def26ce82..c96a3aec086c 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2988,6 +2988,10 @@ enum i915_power_well_id {
 #define GPIOF			_MMIO(0x5024)
 #define GPIOG			_MMIO(0x5028)
 #define GPIOH			_MMIO(0x502c)
+#define GPIOJ			_MMIO(0x5034)
+#define GPIOK			_MMIO(0x5038)
+#define GPIOL			_MMIO(0x503C)
+#define GPIOM			_MMIO(0x5040)
 # define GPIO_CLOCK_DIR_MASK		(1 << 0)
 # define GPIO_CLOCK_DIR_IN		(0 << 1)
 # define GPIO_CLOCK_DIR_OUT		(1 << 1)
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ba5ea61fb7b9..ef4de5a02cb5 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -2234,7 +2234,7 @@ static u8 intel_hdmi_ddc_pin(struct drm_i915_private *dev_priv,
 		ddc_pin = bxt_port_to_ddc_pin(dev_priv, port);
 	else if (HAS_PCH_CNP(dev_priv))
 		ddc_pin = cnp_port_to_ddc_pin(dev_priv, port);
-	else if (IS_ICELAKE(dev_priv))
+	else if (HAS_PCH_ICP(dev_priv))
 		ddc_pin = icl_port_to_ddc_pin(dev_priv, port);
 	else
 		ddc_pin = g4x_port_to_ddc_pin(dev_priv, port);
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 61729bf84e08..97606c1be70d 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -77,12 +77,12 @@ static const struct gmbus_pin gmbus_pins_cnp[] = {
 };
 
 static const struct gmbus_pin gmbus_pins_icp[] = {
-	[GMBUS_PIN_1_BXT] = { "dpa", GPIOA },
-	[GMBUS_PIN_2_BXT] = { "dpb", GPIOB },
-	[GMBUS_PIN_9_TC1_ICP] = { "tc1", GPIOC },
-	[GMBUS_PIN_10_TC2_ICP] = { "tc2", GPIOD },
-	[GMBUS_PIN_11_TC3_ICP] = { "tc3", GPIOE },
-	[GMBUS_PIN_12_TC4_ICP] = { "tc4", GPIOF },
+	[GMBUS_PIN_1_BXT] = { "dpa", GPIOB },
+	[GMBUS_PIN_2_BXT] = { "dpb", GPIOC },
+	[GMBUS_PIN_9_TC1_ICP] = { "tc1", GPIOJ },
+	[GMBUS_PIN_10_TC2_ICP] = { "tc2", GPIOK },
+	[GMBUS_PIN_11_TC3_ICP] = { "tc3", GPIOL },
+	[GMBUS_PIN_12_TC4_ICP] = { "tc4", GPIOM },
 };
 
 /* pin is expected to be valid */
-- 
cgit v1.2.3


From bb187e93e48d3a3f1e3c9bcae76c5b13d3529391 Mon Sep 17 00:00:00 2001
From: James Ausmus <james.ausmus@intel.com>
Date: Mon, 11 Jun 2018 17:25:12 -0700
Subject: drm/i915/icl: DP_AUX_E is valid on ICL+

Add support for DP_AUX_E. Here we also introduce the bits for the AUX
power well E, however ICL power well support is still not enabled yet,
so the power well is not used.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612002512.29783-2-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h         | 1 +
 drivers/gpu/drm/i915/i915_irq.c         | 6 ++++++
 drivers/gpu/drm/i915/i915_reg.h         | 8 ++++++++
 drivers/gpu/drm/i915/intel_display.h    | 3 ++-
 drivers/gpu/drm/i915/intel_dp.c         | 7 +++++++
 drivers/gpu/drm/i915/intel_runtime_pm.c | 2 ++
 6 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6104d7115054..be8c2f0823c4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1016,6 +1016,7 @@ enum modeset_restore {
 #define DP_AUX_B 0x10
 #define DP_AUX_C 0x20
 #define DP_AUX_D 0x30
+#define DP_AUX_E 0x50
 #define DP_AUX_F 0x60
 
 #define DDC_PIN_B  0x05
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 2fd92a886789..c52060a35317 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2640,6 +2640,9 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 					    GEN9_AUX_CHANNEL_C |
 					    GEN9_AUX_CHANNEL_D;
 
+			if (INTEL_GEN(dev_priv) >= 11)
+				tmp_mask |= ICL_AUX_CHANNEL_E;
+
 			if (IS_CNL_WITH_PORT_F(dev_priv) ||
 			    INTEL_GEN(dev_priv) >= 11)
 				tmp_mask |= CNL_AUX_CHANNEL_F;
@@ -3921,6 +3924,9 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 		de_pipe_masked |= GEN8_DE_PIPE_IRQ_FAULT_ERRORS;
 	}
 
+	if (INTEL_GEN(dev_priv) >= 11)
+		de_port_masked |= ICL_AUX_CHANNEL_E;
+
 	if (IS_CNL_WITH_PORT_F(dev_priv) || INTEL_GEN(dev_priv) >= 11)
 		de_port_masked |= CNL_AUX_CHANNEL_F;
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c96a3aec086c..140f6a27d696 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -5315,6 +5315,13 @@ enum {
 #define _DPD_AUX_CH_DATA4	(dev_priv->info.display_mmio_offset + 0x64320)
 #define _DPD_AUX_CH_DATA5	(dev_priv->info.display_mmio_offset + 0x64324)
 
+#define _DPE_AUX_CH_CTL		(dev_priv->info.display_mmio_offset + 0x64410)
+#define _DPE_AUX_CH_DATA1	(dev_priv->info.display_mmio_offset + 0x64414)
+#define _DPE_AUX_CH_DATA2	(dev_priv->info.display_mmio_offset + 0x64418)
+#define _DPE_AUX_CH_DATA3	(dev_priv->info.display_mmio_offset + 0x6441c)
+#define _DPE_AUX_CH_DATA4	(dev_priv->info.display_mmio_offset + 0x64420)
+#define _DPE_AUX_CH_DATA5	(dev_priv->info.display_mmio_offset + 0x64424)
+
 #define _DPF_AUX_CH_CTL		(dev_priv->info.display_mmio_offset + 0x64510)
 #define _DPF_AUX_CH_DATA1	(dev_priv->info.display_mmio_offset + 0x64514)
 #define _DPF_AUX_CH_DATA2	(dev_priv->info.display_mmio_offset + 0x64518)
@@ -7019,6 +7026,7 @@ enum {
 #define GEN8_DE_PORT_IMR _MMIO(0x44444)
 #define GEN8_DE_PORT_IIR _MMIO(0x44448)
 #define GEN8_DE_PORT_IER _MMIO(0x4444c)
+#define  ICL_AUX_CHANNEL_E		(1 << 29)
 #define  CNL_AUX_CHANNEL_F		(1 << 28)
 #define  GEN9_AUX_CHANNEL_D		(1 << 27)
 #define  GEN9_AUX_CHANNEL_C		(1 << 26)
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index c88185ed7594..dfb02da73ac8 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -155,7 +155,7 @@ enum aux_ch {
 	AUX_CH_B,
 	AUX_CH_C,
 	AUX_CH_D,
-	_AUX_CH_E, /* does not exist */
+	AUX_CH_E, /* ICL+ */
 	AUX_CH_F,
 };
 
@@ -196,6 +196,7 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_AUX_B,
 	POWER_DOMAIN_AUX_C,
 	POWER_DOMAIN_AUX_D,
+	POWER_DOMAIN_AUX_E,
 	POWER_DOMAIN_AUX_F,
 	POWER_DOMAIN_AUX_IO_A,
 	POWER_DOMAIN_GMBUS,
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 37b9f62aeb6e..40ffd9163175 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1347,6 +1347,9 @@ static enum aux_ch intel_aux_ch(struct intel_dp *intel_dp)
 	case DP_AUX_D:
 		aux_ch = AUX_CH_D;
 		break;
+	case DP_AUX_E:
+		aux_ch = AUX_CH_E;
+		break;
 	case DP_AUX_F:
 		aux_ch = AUX_CH_F;
 		break;
@@ -1374,6 +1377,8 @@ intel_aux_power_domain(struct intel_dp *intel_dp)
 		return POWER_DOMAIN_AUX_C;
 	case AUX_CH_D:
 		return POWER_DOMAIN_AUX_D;
+	case AUX_CH_E:
+		return POWER_DOMAIN_AUX_E;
 	case AUX_CH_F:
 		return POWER_DOMAIN_AUX_F;
 	default:
@@ -1460,6 +1465,7 @@ static i915_reg_t skl_aux_ctl_reg(struct intel_dp *intel_dp)
 	case AUX_CH_B:
 	case AUX_CH_C:
 	case AUX_CH_D:
+	case AUX_CH_E:
 	case AUX_CH_F:
 		return DP_AUX_CH_CTL(aux_ch);
 	default:
@@ -1478,6 +1484,7 @@ static i915_reg_t skl_aux_data_reg(struct intel_dp *intel_dp, int index)
 	case AUX_CH_B:
 	case AUX_CH_C:
 	case AUX_CH_D:
+	case AUX_CH_E:
 	case AUX_CH_F:
 		return DP_AUX_CH_DATA(aux_ch, index);
 	default:
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 53a6eaa9671a..de3a81034f77 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -128,6 +128,8 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "AUX_C";
 	case POWER_DOMAIN_AUX_D:
 		return "AUX_D";
+	case POWER_DOMAIN_AUX_E:
+		return "AUX_E";
 	case POWER_DOMAIN_AUX_F:
 		return "AUX_F";
 	case POWER_DOMAIN_AUX_IO_A:
-- 
cgit v1.2.3


From 2939db9e2879a1f80bcf863ccbd4919b3eef0d91 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:29 +0800
Subject: drm/i915/gvt: Add D_BXT device type define for BXT.

Broxton belongs to GEN9 family so add to SKL and GEN9 plus.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c |  2 ++
 drivers/gpu/drm/i915/gvt/mmio.h     | 11 ++++++-----
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index d60c2bee00fb..4dfe8ba55849 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -55,6 +55,8 @@ unsigned long intel_gvt_get_device_type(struct intel_gvt *gvt)
 		return D_SKL;
 	else if (IS_KABYLAKE(gvt->dev_priv))
 		return D_KBL;
+	else if (IS_BROXTON(gvt->dev_priv))
+		return D_BXT;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/gvt/mmio.h b/drivers/gpu/drm/i915/gvt/mmio.h
index 71b620875943..e474188b46d2 100644
--- a/drivers/gpu/drm/i915/gvt/mmio.h
+++ b/drivers/gpu/drm/i915/gvt/mmio.h
@@ -42,15 +42,16 @@ struct intel_vgpu;
 #define D_BDW   (1 << 0)
 #define D_SKL	(1 << 1)
 #define D_KBL	(1 << 2)
+#define D_BXT	(1 << 3)
 
-#define D_GEN9PLUS	(D_SKL | D_KBL)
-#define D_GEN8PLUS	(D_BDW | D_SKL | D_KBL)
+#define D_GEN9PLUS	(D_SKL | D_KBL | D_BXT)
+#define D_GEN8PLUS	(D_BDW | D_SKL | D_KBL | D_BXT)
 
-#define D_SKL_PLUS	(D_SKL | D_KBL)
-#define D_BDW_PLUS	(D_BDW | D_SKL | D_KBL)
+#define D_SKL_PLUS	(D_SKL | D_KBL | D_BXT)
+#define D_BDW_PLUS	(D_BDW | D_SKL | D_KBL | D_BXT)
 
 #define D_PRE_SKL	(D_BDW)
-#define D_ALL		(D_BDW | D_SKL | D_KBL)
+#define D_ALL		(D_BDW | D_SKL | D_KBL | D_BXT)
 
 typedef int (*gvt_mmio_func)(struct intel_vgpu *, unsigned int, void *,
 			     unsigned int);
-- 
cgit v1.2.3


From 02b966c12b49ba6dae627c2135b7c1a258e32303 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:30 +0800
Subject: drm/i915/gvt: Add MEDIA_POOL_STATE for BXT.

As referred in PRM for Broxton Graphics on 01.org

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/cmd_parser.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 718ca08f9575..2b8e6e15e936 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -172,6 +172,7 @@ struct decode_info {
 #define OP_MEDIA_INTERFACE_DESCRIPTOR_LOAD      OP_3D_MEDIA(0x2, 0x0, 0x2)
 #define OP_MEDIA_GATEWAY_STATE                  OP_3D_MEDIA(0x2, 0x0, 0x3)
 #define OP_MEDIA_STATE_FLUSH                    OP_3D_MEDIA(0x2, 0x0, 0x4)
+#define OP_MEDIA_POOL_STATE                     OP_3D_MEDIA(0x2, 0x0, 0x5)
 
 #define OP_MEDIA_OBJECT                         OP_3D_MEDIA(0x2, 0x1, 0x0)
 #define OP_MEDIA_OBJECT_PRT                     OP_3D_MEDIA(0x2, 0x1, 0x2)
@@ -2349,6 +2350,9 @@ static struct cmd_info cmd_info[] = {
 	{"MEDIA_STATE_FLUSH", OP_MEDIA_STATE_FLUSH, F_LEN_VAR, R_RCS, D_ALL,
 		0, 16, NULL},
 
+	{"MEDIA_POOL_STATE", OP_MEDIA_POOL_STATE, F_LEN_VAR, R_RCS, D_ALL,
+		0, 16, NULL},
+
 	{"MEDIA_OBJECT", OP_MEDIA_OBJECT, F_LEN_VAR, R_RCS, D_ALL, 0, 16, NULL},
 
 	{"MEDIA_CURBE_LOAD", OP_MEDIA_CURBE_LOAD, F_LEN_VAR, R_RCS, D_ALL,
-- 
cgit v1.2.3


From 6fa6616b8f7adaf8380d72e53733bc2472b0d157 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:31 +0800
Subject: drm/i915/gvt: Enable device info initialization for BXT.

Initialize BXT device info as SKL/KBL.

v2: All supported platforms share the same device configuration.
    Remove the platform check by now and let is_supported_device()
    be the gate keeper.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gvt.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 22a3ddff38a3..4e65266e7b95 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -238,18 +238,15 @@ static void init_device_info(struct intel_gvt *gvt)
 	struct intel_gvt_device_info *info = &gvt->device_info;
 	struct pci_dev *pdev = gvt->dev_priv->drm.pdev;
 
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		info->max_support_vgpus = 8;
-		info->cfg_space_size = PCI_CFG_SPACE_EXP_SIZE;
-		info->mmio_size = 2 * 1024 * 1024;
-		info->mmio_bar = 0;
-		info->gtt_start_offset = 8 * 1024 * 1024;
-		info->gtt_entry_size = 8;
-		info->gtt_entry_size_shift = 3;
-		info->gmadr_bytes_in_cmd = 8;
-		info->max_surface_size = 36 * 1024 * 1024;
-	}
+	info->max_support_vgpus = 8;
+	info->cfg_space_size = PCI_CFG_SPACE_EXP_SIZE;
+	info->mmio_size = 2 * 1024 * 1024;
+	info->mmio_bar = 0;
+	info->gtt_start_offset = 8 * 1024 * 1024;
+	info->gtt_entry_size = 8;
+	info->gtt_entry_size_shift = 3;
+	info->gmadr_bytes_in_cmd = 8;
+	info->max_surface_size = 36 * 1024 * 1024;
 	info->msi_cap_offset = pdev->msi_cap;
 }
 
-- 
cgit v1.2.3


From 665004b8f50612d1e354eb9abd6d97e6eb85a619 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:32 +0800
Subject: drm/i915/gvt: Enable gtt initialization for BXT.

Initialize BXT gtt as SKL/KBL.

v2: All supported platforms share the same gtt ops.
    Remove the platform check by now and let is_supported_device()
    be the gate keeper.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 49400ab129ff..6a8a9868bcfb 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -2256,13 +2256,8 @@ int intel_gvt_init_gtt(struct intel_gvt *gvt)
 
 	gvt_dbg_core("init gtt\n");
 
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		gvt->gtt.pte_ops = &gen8_gtt_pte_ops;
-		gvt->gtt.gma_ops = &gen8_gtt_gma_ops;
-	} else {
-		return -ENODEV;
-	}
+	gvt->gtt.pte_ops = &gen8_gtt_pte_ops;
+	gvt->gtt.gma_ops = &gen8_gtt_gma_ops;
 
 	page = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!page) {
-- 
cgit v1.2.3


From d0f827bb18fe2ceb39707718334b636b89be4af0 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:33 +0800
Subject: drm/i915/gvt: Enable irq initialization for BXT.

Initialize BXT irq handler as SKL/KBL.

v2: All supported platforms share the same irq ops and map.
    Remove the platform check by now and let is_supported_device()
    be the gate keeper.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/interrupt.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/interrupt.c b/drivers/gpu/drm/i915/gvt/interrupt.c
index 1d79596da510..5daa23ae566b 100644
--- a/drivers/gpu/drm/i915/gvt/interrupt.c
+++ b/drivers/gpu/drm/i915/gvt/interrupt.c
@@ -581,7 +581,9 @@ static void gen8_init_irq(
 
 		SET_BIT_INFO(irq, 4, PRIMARY_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C);
 		SET_BIT_INFO(irq, 5, SPRITE_C_FLIP_DONE, INTEL_GVT_IRQ_INFO_DE_PIPE_C);
-	} else if (IS_SKYLAKE(gvt->dev_priv) || IS_KABYLAKE(gvt->dev_priv)) {
+	} else if (IS_SKYLAKE(gvt->dev_priv)
+			|| IS_KABYLAKE(gvt->dev_priv)
+			|| IS_BROXTON(gvt->dev_priv)) {
 		SET_BIT_INFO(irq, 25, AUX_CHANNEL_B, INTEL_GVT_IRQ_INFO_DE_PORT);
 		SET_BIT_INFO(irq, 26, AUX_CHANNEL_C, INTEL_GVT_IRQ_INFO_DE_PORT);
 		SET_BIT_INFO(irq, 27, AUX_CHANNEL_D, INTEL_GVT_IRQ_INFO_DE_PORT);
@@ -691,14 +693,8 @@ int intel_gvt_init_irq(struct intel_gvt *gvt)
 
 	gvt_dbg_core("init irq framework\n");
 
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		irq->ops = &gen8_irq_ops;
-		irq->irq_map = gen8_irq_map;
-	} else {
-		WARN_ON(1);
-		return -ENODEV;
-	}
+	irq->ops = &gen8_irq_ops;
+	irq->irq_map = gen8_irq_map;
 
 	/* common event initialization */
 	init_events(irq);
-- 
cgit v1.2.3


From a94cf2e0ef7fef5cb42ed96f73c18c3ad4f0d170 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:34 +0800
Subject: drm/i915/gvt: Enable mmio context init and switch for BXT.

Handle pending tlb flush, mocs/mmio switch and context as KBL.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/mmio_context.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 708170e61625..20be9a92600f 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -364,7 +364,8 @@ static void handle_tlb_pending_event(struct intel_vgpu *vgpu, int ring_id)
 	 */
 	fw = intel_uncore_forcewake_for_reg(dev_priv, reg,
 					    FW_REG_READ | FW_REG_WRITE);
-	if (ring_id == RCS && (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)))
+	if (ring_id == RCS && (IS_SKYLAKE(dev_priv) ||
+			IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)))
 		fw |= FORCEWAKE_RENDER;
 
 	intel_uncore_forcewake_get(dev_priv, fw);
@@ -401,7 +402,7 @@ static void switch_mocs(struct intel_vgpu *pre, struct intel_vgpu *next,
 	if (WARN_ON(ring_id >= ARRAY_SIZE(regs)))
 		return;
 
-	if (IS_KABYLAKE(dev_priv) && ring_id == RCS)
+	if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv)) && ring_id == RCS)
 		return;
 
 	if (!pre && !gen9_render_mocs.initialized)
@@ -467,7 +468,9 @@ static void switch_mmio(struct intel_vgpu *pre,
 	u32 old_v, new_v;
 
 	dev_priv = pre ? pre->gvt->dev_priv : next->gvt->dev_priv;
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv))
 		switch_mocs(pre, next, ring_id);
 
 	for (mmio = dev_priv->gvt->engine_mmio_list.mmio;
@@ -479,7 +482,8 @@ static void switch_mmio(struct intel_vgpu *pre,
 		 * state image on kabylake, it's initialized by lri command and
 		 * save or restore with context together.
 		 */
-		if (IS_KABYLAKE(dev_priv) && mmio->in_context)
+		if ((IS_KABYLAKE(dev_priv) || IS_BROXTON(dev_priv))
+			&& mmio->in_context)
 			continue;
 
 		// save
@@ -574,7 +578,9 @@ void intel_gvt_init_engine_mmio_context(struct intel_gvt *gvt)
 {
 	struct engine_mmio *mmio;
 
-	if (IS_SKYLAKE(gvt->dev_priv) || IS_KABYLAKE(gvt->dev_priv))
+	if (IS_SKYLAKE(gvt->dev_priv) ||
+		IS_KABYLAKE(gvt->dev_priv) ||
+		IS_BROXTON(gvt->dev_priv))
 		gvt->engine_mmio_list.mmio = gen9_engine_mmio_list;
 	else
 		gvt->engine_mmio_list.mmio = gen8_engine_mmio_list;
-- 
cgit v1.2.3


From f093f182ace9ce3c618c110e316cc1e22d0c9d3b Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:35 +0800
Subject: drm/i915/gvt: Enable cmd_parser support for BXT.

Handle BXT cmd_parser as SKL/KBL.

v2: All supported platforms share the same routines.
    Remove the platform check by now and let is_supported_device()
    be the gate keeper.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/cmd_parser.c | 39 +++++++++++++----------------------
 1 file changed, 14 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/cmd_parser.c b/drivers/gpu/drm/i915/gvt/cmd_parser.c
index 2b8e6e15e936..0dd88fe2e39a 100644
--- a/drivers/gpu/drm/i915/gvt/cmd_parser.c
+++ b/drivers/gpu/drm/i915/gvt/cmd_parser.c
@@ -1257,7 +1257,9 @@ static int gen8_check_mi_display_flip(struct parser_exec_state *s,
 	if (!info->async_flip)
 		return 0;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		stride = vgpu_vreg_t(s->vgpu, info->stride_reg) & GENMASK(9, 0);
 		tile = (vgpu_vreg_t(s->vgpu, info->ctrl_reg) &
 				GENMASK(12, 10)) >> 10;
@@ -1285,7 +1287,9 @@ static int gen8_update_plane_mmio_from_mi_display_flip(
 
 	set_mask_bits(&vgpu_vreg_t(vgpu, info->surf_reg), GENMASK(31, 12),
 		      info->surf_val << 12);
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		set_mask_bits(&vgpu_vreg_t(vgpu, info->stride_reg), GENMASK(9, 0),
 			      info->stride_val);
 		set_mask_bits(&vgpu_vreg_t(vgpu, info->ctrl_reg), GENMASK(12, 10),
@@ -1309,7 +1313,9 @@ static int decode_mi_display_flip(struct parser_exec_state *s,
 
 	if (IS_BROADWELL(dev_priv))
 		return gen8_decode_mi_display_flip(s, info);
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv))
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv))
 		return skl_decode_mi_display_flip(s, info);
 
 	return -ENODEV;
@@ -1318,26 +1324,14 @@ static int decode_mi_display_flip(struct parser_exec_state *s,
 static int check_mi_display_flip(struct parser_exec_state *s,
 		struct mi_display_flip_command_info *info)
 {
-	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
-
-	if (IS_BROADWELL(dev_priv)
-		|| IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv))
-		return gen8_check_mi_display_flip(s, info);
-	return -ENODEV;
+	return gen8_check_mi_display_flip(s, info);
 }
 
 static int update_plane_mmio_from_mi_display_flip(
 		struct parser_exec_state *s,
 		struct mi_display_flip_command_info *info)
 {
-	struct drm_i915_private *dev_priv = s->vgpu->gvt->dev_priv;
-
-	if (IS_BROADWELL(dev_priv)
-		|| IS_SKYLAKE(dev_priv)
-		|| IS_KABYLAKE(dev_priv))
-		return gen8_update_plane_mmio_from_mi_display_flip(s, info);
-	return -ENODEV;
+	return gen8_update_plane_mmio_from_mi_display_flip(s, info);
 }
 
 static int cmd_handler_mi_display_flip(struct parser_exec_state *s)
@@ -1616,15 +1610,10 @@ static int copy_gma_to_hva(struct intel_vgpu *vgpu, struct intel_vgpu_mm *mm,
  */
 static int batch_buffer_needs_scan(struct parser_exec_state *s)
 {
-	struct intel_gvt *gvt = s->vgpu->gvt;
-
-	if (IS_BROADWELL(gvt->dev_priv) || IS_SKYLAKE(gvt->dev_priv)
-		|| IS_KABYLAKE(gvt->dev_priv)) {
-		/* BDW decides privilege based on address space */
-		if (cmd_val(s, 0) & (1 << 8) &&
+	/* Decide privilege based on address space */
+	if (cmd_val(s, 0) & (1 << 8) &&
 			!(s->vgpu->scan_nonprivbb & (1 << s->ring_id)))
-			return 0;
-	}
+		return 0;
 	return 1;
 }
 
-- 
cgit v1.2.3


From 47d9d3be5925688dfcc7407b0ae70013ba2dce2e Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:36 +0800
Subject: drm/i915/gvt: Enable force wake support for BXT.

BXT forcewake is handled in the same way as SKL/KBL.

v2: Add missing inhibit_context restore for BXT.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/scheduler.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 462cf560492e..928818f218f7 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -297,7 +297,8 @@ static int copy_workload_to_ring_buffer(struct intel_vgpu_workload *workload)
 	void *shadow_ring_buffer_va;
 	u32 *cs;
 
-	if (IS_KABYLAKE(req->i915) && is_inhibit_context(req->hw_context))
+	if ((IS_KABYLAKE(req->i915) || IS_BROXTON(req->i915))
+		&& is_inhibit_context(req->hw_context))
 		intel_vgpu_restore_inhibit_context(vgpu, req);
 
 	/* allocate shadow ring buffer */
@@ -904,7 +905,8 @@ static int workload_thread(void *priv)
 	struct intel_vgpu *vgpu = NULL;
 	int ret;
 	bool need_force_wake = IS_SKYLAKE(gvt->dev_priv)
-			|| IS_KABYLAKE(gvt->dev_priv);
+			|| IS_KABYLAKE(gvt->dev_priv)
+			|| IS_BROXTON(gvt->dev_priv);
 	DEFINE_WAIT_FUNC(wait, woken_wake_function);
 
 	kfree(p);
-- 
cgit v1.2.3


From 72bad9972876933b3c428fcee122bb1dcbf8cf5a Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:37 +0800
Subject: drm/i915/gvt: Enable virtual display support for BXT.

Virtual monitor on BXT start from port B.
Unlike SKL/KBL, digital display port connectivity is detected via
GEN8_DE_PORT_ISR so emulate monitor state change by setting it.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/display.c | 23 +++++++++++++++++++++++
 drivers/gpu/drm/i915/gvt/edid.c    | 20 +++++++++++++++++++-
 2 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/display.c b/drivers/gpu/drm/i915/gvt/display.c
index 38521fa81bf9..6ee50cb328f8 100644
--- a/drivers/gpu/drm/i915/gvt/display.c
+++ b/drivers/gpu/drm/i915/gvt/display.c
@@ -171,6 +171,29 @@ static void emulate_monitor_status_change(struct intel_vgpu *vgpu)
 	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int pipe;
 
+	if (IS_BROXTON(dev_priv)) {
+		vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) &= ~(BXT_DE_PORT_HP_DDIA |
+			BXT_DE_PORT_HP_DDIB |
+			BXT_DE_PORT_HP_DDIC);
+
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_A)) {
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+				BXT_DE_PORT_HP_DDIA;
+		}
+
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_B)) {
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+				BXT_DE_PORT_HP_DDIB;
+		}
+
+		if (intel_vgpu_has_monitor_on_port(vgpu, PORT_C)) {
+			vgpu_vreg_t(vgpu, GEN8_DE_PORT_ISR) |=
+				BXT_DE_PORT_HP_DDIC;
+		}
+
+		return;
+	}
+
 	vgpu_vreg_t(vgpu, SDEISR) &= ~(SDE_PORTB_HOTPLUG_CPT |
 			SDE_PORTC_HOTPLUG_CPT |
 			SDE_PORTD_HOTPLUG_CPT);
diff --git a/drivers/gpu/drm/i915/gvt/edid.c b/drivers/gpu/drm/i915/gvt/edid.c
index f61337632969..4b98539025c5 100644
--- a/drivers/gpu/drm/i915/gvt/edid.c
+++ b/drivers/gpu/drm/i915/gvt/edid.c
@@ -77,6 +77,20 @@ static unsigned char edid_get_byte(struct intel_vgpu *vgpu)
 	return chr;
 }
 
+static inline int bxt_get_port_from_gmbus0(u32 gmbus0)
+{
+	int port_select = gmbus0 & _GMBUS_PIN_SEL_MASK;
+	int port = -EINVAL;
+
+	if (port_select == 1)
+		port = PORT_B;
+	else if (port_select == 2)
+		port = PORT_C;
+	else if (port_select == 3)
+		port = PORT_D;
+	return port;
+}
+
 static inline int get_port_from_gmbus0(u32 gmbus0)
 {
 	int port_select = gmbus0 & _GMBUS_PIN_SEL_MASK;
@@ -105,6 +119,7 @@ static void reset_gmbus_controller(struct intel_vgpu *vgpu)
 static int gmbus0_mmio_write(struct intel_vgpu *vgpu,
 			unsigned int offset, void *p_data, unsigned int bytes)
 {
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 	int port, pin_select;
 
 	memcpy(&vgpu_vreg(vgpu, offset), p_data, bytes);
@@ -116,7 +131,10 @@ static int gmbus0_mmio_write(struct intel_vgpu *vgpu,
 	if (pin_select == 0)
 		return 0;
 
-	port = get_port_from_gmbus0(pin_select);
+	if (IS_BROXTON(dev_priv))
+		port = bxt_get_port_from_gmbus0(pin_select);
+	else
+		port = get_port_from_gmbus0(pin_select);
 	if (WARN_ON(port < 0))
 		return 0;
 
-- 
cgit v1.2.3


From 84eb04f6d77a824b33da11a08118ed2766038f13 Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:38 +0800
Subject: drm/i915/gvt: Enable dma_buf support for BXT.

Handle dma_buf on BXT as SKL and KBL.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/dmabuf.c     |  4 +++-
 drivers/gpu/drm/i915/gvt/fb_decoder.c | 12 +++++++++---
 2 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index d2eb2f7754b9..6e3f56684f4e 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -164,7 +164,9 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 
 	obj->read_domains = I915_GEM_DOMAIN_GTT;
 	obj->write_domain = 0;
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		unsigned int tiling_mode = 0;
 		unsigned int stride = 0;
 
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c
index 20b502c44eae..face664be3e8 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.c
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c
@@ -151,7 +151,9 @@ static u32 intel_vgpu_get_stride(struct intel_vgpu *vgpu, int pipe,
 	u32 stride_reg = vgpu_vreg_t(vgpu, DSPSTRIDE(pipe)) & stride_mask;
 	u32 stride = stride_reg;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		switch (tiled) {
 		case PLANE_CTL_TILED_LINEAR:
 			stride = stride_reg * 64;
@@ -215,7 +217,9 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	if (!plane->enabled)
 		return -ENODEV;
 
-	if (IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) {
+	if (IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) {
 		plane->tiled = (val & PLANE_CTL_TILED_MASK) >>
 		_PLANE_CTL_TILED_SHIFT;
 		fmt = skl_format_to_drm(
@@ -257,7 +261,9 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	}
 
 	plane->stride = intel_vgpu_get_stride(vgpu, pipe, (plane->tiled << 10),
-		(IS_SKYLAKE(dev_priv) || IS_KABYLAKE(dev_priv)) ?
+		(IS_SKYLAKE(dev_priv)
+		|| IS_KABYLAKE(dev_priv)
+		|| IS_BROXTON(dev_priv)) ?
 			(_PRI_PLANE_STRIDE_MASK >> 6) :
 				_PRI_PLANE_STRIDE_MASK, plane->bpp);
 
-- 
cgit v1.2.3


From d71cb7129e7cf038ed1444781a50766e486bb2bd Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:39 +0800
Subject: drm/i915/gvt: Add mmio handler for for BXT.

Leverage most SKL/KBL mmio init info and add different mmio to
BXT specific function init_bxt_mmio_info().

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 389 +++++++++++++++++++++++++++++++-----
 1 file changed, 344 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 4dfe8ba55849..0bc0c5418adb 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -257,7 +257,8 @@ static int mul_force_wake_write(struct intel_vgpu *vgpu,
 	new = CALC_MODE_MASK_REG(old, *(u32 *)p_data);
 
 	if (IS_SKYLAKE(vgpu->gvt->dev_priv)
-		|| IS_KABYLAKE(vgpu->gvt->dev_priv)) {
+		|| IS_KABYLAKE(vgpu->gvt->dev_priv)
+		|| IS_BROXTON(vgpu->gvt->dev_priv)) {
 		switch (offset) {
 		case FORCEWAKE_RENDER_GEN9_REG:
 			ack_reg_offset = FORCEWAKE_ACK_RENDER_GEN9_REG;
@@ -863,7 +864,8 @@ static int dp_aux_ch_ctl_mmio_write(struct intel_vgpu *vgpu,
 	data = vgpu_vreg(vgpu, offset);
 
 	if ((IS_SKYLAKE(vgpu->gvt->dev_priv)
-		|| IS_KABYLAKE(vgpu->gvt->dev_priv))
+		|| IS_KABYLAKE(vgpu->gvt->dev_priv)
+		|| IS_BROXTON(vgpu->gvt->dev_priv))
 		&& offset != _REG_SKL_DP_AUX_CH_CTL(port_index)) {
 		/* SKL DPB/C/D aux ctl register changed */
 		return 0;
@@ -1370,6 +1372,16 @@ static int mailbox_write(struct intel_vgpu *vgpu, unsigned int offset,
 				*data0 = 0x1e1a1100;
 			else
 				*data0 = 0x61514b3d;
+		} else if (IS_BROXTON(vgpu->gvt->dev_priv)) {
+			/**
+			 * "Read memory latency" command on gen9.
+			 * Below memory latency values are read
+			 * from Broxton MRB.
+			 */
+			if (!*data0)
+				*data0 = 0x16080707;
+			else
+				*data0 = 0x16161616;
 		}
 		break;
 	case SKL_PCODE_CDCLK_CONTROL:
@@ -1427,8 +1439,11 @@ static int skl_power_well_ctl_write(struct intel_vgpu *vgpu,
 {
 	u32 v = *(u32 *)p_data;
 
-	v &= (1 << 31) | (1 << 29) | (1 << 9) |
-	     (1 << 7) | (1 << 5) | (1 << 3) | (1 << 1);
+	if (IS_BROXTON(vgpu->gvt->dev_priv))
+		v &= (1 << 31) | (1 << 29);
+	else
+		v &= (1 << 31) | (1 << 29) | (1 << 9) |
+			(1 << 7) | (1 << 5) | (1 << 3) | (1 << 1);
 	v |= (v >> 1);
 
 	return intel_vgpu_default_mmio_write(vgpu, offset, &v, bytes);
@@ -1448,6 +1463,102 @@ static int skl_lcpll_write(struct intel_vgpu *vgpu, unsigned int offset,
 	return 0;
 }
 
+static int bxt_de_pll_enable_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (v & BXT_DE_PLL_PLL_ENABLE)
+		v |= BXT_DE_PLL_LOCK;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_port_pll_enable_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (v & PORT_PLL_ENABLE)
+		v |= PORT_PLL_LOCK;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_phy_ctl_family_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+	u32 data = v & COMMON_RESET_DIS ? BXT_PHY_LANE_ENABLED : 0;
+
+	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data;
+	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data;
+	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_port_tx_dw3_read(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = vgpu_vreg(vgpu, offset);
+
+	v &= ~UNIQUE_TRANGE_EN_METHOD;
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return intel_vgpu_default_mmio_read(vgpu, offset, p_data, bytes);
+}
+
+static int bxt_pcs_dw12_grp_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (offset == _PORT_PCS_DW12_GRP_A || offset == _PORT_PCS_DW12_GRP_B) {
+		vgpu_vreg(vgpu, offset - 0x600) = v;
+		vgpu_vreg(vgpu, offset - 0x800) = v;
+	} else {
+		vgpu_vreg(vgpu, offset - 0x400) = v;
+		vgpu_vreg(vgpu, offset - 0x600) = v;
+	}
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
+static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 v = *(u32 *)p_data;
+
+	if (v & BIT(0)) {
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) &=
+			~PHY_RESERVED;
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY0)) |=
+			PHY_POWER_GOOD;
+	}
+
+	if (v & BIT(1)) {
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) &=
+			~PHY_RESERVED;
+		vgpu_vreg_t(vgpu, BXT_PORT_CL1CM_DW0(DPIO_PHY1)) |=
+			PHY_POWER_GOOD;
+	}
+
+
+	vgpu_vreg(vgpu, offset) = v;
+
+	return 0;
+}
+
 static int mmio_read_from_hw(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
@@ -2671,17 +2782,17 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_MMIO(0x45504), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x45520), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x46000), D_SKL_PLUS);
-	MMIO_DH(_MMIO(0x46010), D_SKL | D_KBL, NULL, skl_lcpll_write);
-	MMIO_DH(_MMIO(0x46014), D_SKL | D_KBL, NULL, skl_lcpll_write);
-	MMIO_D(_MMIO(0x6C040), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C048), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C050), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C044), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C04C), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6C054), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6c058), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6c05c), D_SKL | D_KBL);
-	MMIO_DH(_MMIO(0x6c060), D_SKL | D_KBL, dpll_status_read, NULL);
+	MMIO_DH(_MMIO(0x46010), D_SKL_PLUS, NULL, skl_lcpll_write);
+	MMIO_DH(_MMIO(0x46014), D_SKL_PLUS, NULL, skl_lcpll_write);
+	MMIO_D(_MMIO(0x6C040), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C048), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C050), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C044), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C04C), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6C054), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6c058), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6c05c), D_SKL_PLUS);
+	MMIO_DH(_MMIO(0x6c060), D_SKL_PLUS, dpll_status_read, NULL);
 
 	MMIO_DH(SKL_PS_WIN_POS(PIPE_A, 0), D_SKL_PLUS, NULL, pf_write);
 	MMIO_DH(SKL_PS_WIN_POS(PIPE_A, 1), D_SKL_PLUS, NULL, pf_write);
@@ -2806,53 +2917,57 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_MMIO(0x7239c), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x7039c), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x8f074), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x8f004), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x8f034), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x8f074), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x8f004), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x8f034), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0xb11c), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0xb11c), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x51000), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x51000), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x6c00c), D_SKL_PLUS);
 
-	MMIO_F(_MMIO(0xc800), 0x7f8, F_CMD_ACCESS, 0, 0, D_SKL | D_KBL, NULL, NULL);
-	MMIO_F(_MMIO(0xb020), 0x80, F_CMD_ACCESS, 0, 0, D_SKL | D_KBL, NULL, NULL);
+	MMIO_F(_MMIO(0xc800), 0x7f8, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
+		NULL, NULL);
+	MMIO_F(_MMIO(0xb020), 0x80, F_CMD_ACCESS, 0, 0, D_SKL_PLUS,
+		NULL, NULL);
 
 	MMIO_D(RPM_CONFIG0, D_SKL_PLUS);
 	MMIO_D(_MMIO(0xd08), D_SKL_PLUS);
 	MMIO_D(RC6_LOCATION, D_SKL_PLUS);
 	MMIO_DFH(_MMIO(0x20e0), D_SKL_PLUS, F_MODE_MASK, NULL, NULL);
-	MMIO_DFH(_MMIO(0x20ec), D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x20ec), D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+		NULL, NULL);
 
 	/* TRTT */
-	MMIO_DFH(_MMIO(0x4de0), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4de4), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4de8), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4dec), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4df0), D_SKL | D_KBL, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(_MMIO(0x4df4), D_SKL | D_KBL, F_CMD_ACCESS, NULL, gen9_trtte_write);
-	MMIO_DH(_MMIO(0x4dfc), D_SKL | D_KBL, NULL, gen9_trtt_chicken_write);
+	MMIO_DFH(_MMIO(0x4de0), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4de4), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4de8), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4dec), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4df0), D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
+	MMIO_DFH(_MMIO(0x4df4), D_SKL_PLUS, F_CMD_ACCESS,
+		NULL, gen9_trtte_write);
+	MMIO_DH(_MMIO(0x4dfc), D_SKL_PLUS, NULL, gen9_trtt_chicken_write);
 
-	MMIO_D(_MMIO(0x45008), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x45008), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x46430), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x46430), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0x46520), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x46520), D_SKL_PLUS);
 
-	MMIO_D(_MMIO(0xc403c), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0xc403c), D_SKL_PLUS);
 	MMIO_D(_MMIO(0xb004), D_SKL_PLUS);
 	MMIO_DH(DMA_CTRL, D_SKL_PLUS, NULL, dma_ctrl_write);
 
 	MMIO_D(_MMIO(0x65900), D_SKL_PLUS);
-	MMIO_D(_MMIO(0x1082c0), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x4068), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x67054), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6e560), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x6e554), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x2b20), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x65f00), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x65f08), D_SKL | D_KBL);
-	MMIO_D(_MMIO(0x320f0), D_SKL | D_KBL);
+	MMIO_D(_MMIO(0x1082c0), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x4068), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x67054), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6e560), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x6e554), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x2b20), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x65f00), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x65f08), D_SKL_PLUS);
+	MMIO_D(_MMIO(0x320f0), D_SKL_PLUS);
 
 	MMIO_D(_MMIO(0x70034), D_SKL_PLUS);
 	MMIO_D(_MMIO(0x71034), D_SKL_PLUS);
@@ -2870,11 +2985,185 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_D(_MMIO(0x44500), D_SKL_PLUS);
 	MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
-	MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL | D_KBL, F_MODE_MASK | F_CMD_ACCESS,
+	MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
 		NULL, NULL);
 
 	MMIO_D(_MMIO(0x4ab8), D_KBL);
-	MMIO_D(_MMIO(0x2248), D_SKL_PLUS | D_KBL);
+	MMIO_D(_MMIO(0x2248), D_KBL | D_SKL);
+
+	return 0;
+}
+
+static int init_bxt_mmio_info(struct intel_gvt *gvt)
+{
+	struct drm_i915_private *dev_priv = gvt->dev_priv;
+	int ret;
+
+	MMIO_F(_MMIO(0x80000), 0x3000, 0, 0, 0, D_BXT, NULL, NULL);
+
+	MMIO_D(GEN7_SAMPLER_INSTDONE, D_BXT);
+	MMIO_D(GEN7_ROW_INSTDONE, D_BXT);
+	MMIO_D(GEN8_FAULT_TLB_DATA0, D_BXT);
+	MMIO_D(GEN8_FAULT_TLB_DATA1, D_BXT);
+	MMIO_D(ERROR_GEN6, D_BXT);
+	MMIO_D(DONE_REG, D_BXT);
+	MMIO_D(EIR, D_BXT);
+	MMIO_D(PGTBL_ER, D_BXT);
+	MMIO_D(_MMIO(0x4194), D_BXT);
+	MMIO_D(_MMIO(0x4294), D_BXT);
+	MMIO_D(_MMIO(0x4494), D_BXT);
+
+	MMIO_RING_D(RING_PSMI_CTL, D_BXT);
+	MMIO_RING_D(RING_DMA_FADD, D_BXT);
+	MMIO_RING_D(RING_DMA_FADD_UDW, D_BXT);
+	MMIO_RING_D(RING_IPEHR, D_BXT);
+	MMIO_RING_D(RING_INSTPS, D_BXT);
+	MMIO_RING_D(RING_BBADDR_UDW, D_BXT);
+	MMIO_RING_D(RING_BBSTATE, D_BXT);
+	MMIO_RING_D(RING_IPEIR, D_BXT);
+
+	MMIO_F(SOFT_SCRATCH(0), 16 * 4, 0, 0, 0, D_BXT, NULL, NULL);
+
+	MMIO_DH(BXT_P_CR_GT_DISP_PWRON, D_BXT, NULL, bxt_gt_disp_pwron_write);
+	MMIO_D(BXT_RP_STATE_CAP, D_BXT);
+	MMIO_DH(BXT_PHY_CTL_FAMILY(DPIO_PHY0), D_BXT,
+		NULL, bxt_phy_ctl_family_write);
+	MMIO_DH(BXT_PHY_CTL_FAMILY(DPIO_PHY1), D_BXT,
+		NULL, bxt_phy_ctl_family_write);
+	MMIO_D(BXT_PHY_CTL(PORT_A), D_BXT);
+	MMIO_D(BXT_PHY_CTL(PORT_B), D_BXT);
+	MMIO_D(BXT_PHY_CTL(PORT_C), D_BXT);
+	MMIO_DH(BXT_PORT_PLL_ENABLE(PORT_A), D_BXT,
+		NULL, bxt_port_pll_enable_write);
+	MMIO_DH(BXT_PORT_PLL_ENABLE(PORT_B), D_BXT,
+		NULL, bxt_port_pll_enable_write);
+	MMIO_DH(BXT_PORT_PLL_ENABLE(PORT_C), D_BXT, NULL,
+		bxt_port_pll_enable_write);
+
+	MMIO_D(BXT_PORT_CL1CM_DW0(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW9(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW10(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW28(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW30(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_CL2CM_DW6(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW3(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW6(DPIO_PHY0), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW8(DPIO_PHY0), D_BXT);
+
+	MMIO_D(BXT_PORT_CL1CM_DW0(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW9(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW10(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW28(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL1CM_DW30(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_CL2CM_DW6(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW3(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW6(DPIO_PHY1), D_BXT);
+	MMIO_D(BXT_PORT_REF_DW8(DPIO_PHY1), D_BXT);
+
+	MMIO_D(BXT_PORT_PLL_EBB_0(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PLL_EBB_4(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_LN01(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN01(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN23(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_PCS_DW12_GRP(DPIO_PHY0, DPIO_CH0), D_BXT,
+		NULL, bxt_pcs_dw12_grp_write);
+	MMIO_D(BXT_PORT_TX_DW2_LN0(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW2_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_TX_DW3_LN0(DPIO_PHY0, DPIO_CH0), D_BXT,
+		bxt_port_tx_dw3_read, NULL);
+	MMIO_D(BXT_PORT_TX_DW3_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_LN0(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_GRP(DPIO_PHY0, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 6), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 8), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 9), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH0, 10), D_BXT);
+
+	MMIO_D(BXT_PORT_PLL_EBB_0(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PLL_EBB_4(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_LN01(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN01(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN23(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_DH(BXT_PORT_PCS_DW12_GRP(DPIO_PHY0, DPIO_CH1), D_BXT,
+		NULL, bxt_pcs_dw12_grp_write);
+	MMIO_D(BXT_PORT_TX_DW2_LN0(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW2_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_DH(BXT_PORT_TX_DW3_LN0(DPIO_PHY0, DPIO_CH1), D_BXT,
+		bxt_port_tx_dw3_read, NULL);
+	MMIO_D(BXT_PORT_TX_DW3_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_LN0(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_GRP(DPIO_PHY0, DPIO_CH1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 2), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY0, DPIO_CH1, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 0), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 1), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 2), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 6), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 8), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 9), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY0, DPIO_CH1, 10), D_BXT);
+
+	MMIO_D(BXT_PORT_PLL_EBB_0(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PLL_EBB_4(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_LN01(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW10_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN01(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_PCS_DW12_LN23(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_PCS_DW12_GRP(DPIO_PHY1, DPIO_CH0), D_BXT,
+		NULL, bxt_pcs_dw12_grp_write);
+	MMIO_D(BXT_PORT_TX_DW2_LN0(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW2_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_DH(BXT_PORT_TX_DW3_LN0(DPIO_PHY1, DPIO_CH0), D_BXT,
+		bxt_port_tx_dw3_read, NULL);
+	MMIO_D(BXT_PORT_TX_DW3_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_LN0(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW4_GRP(DPIO_PHY1, DPIO_CH0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_TX_DW14_LN(DPIO_PHY1, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 0), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 1), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 2), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 3), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 6), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 8), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 9), D_BXT);
+	MMIO_D(BXT_PORT_PLL(DPIO_PHY1, DPIO_CH0, 10), D_BXT);
+
+	MMIO_D(BXT_DE_PLL_CTL, D_BXT);
+	MMIO_DH(BXT_DE_PLL_ENABLE, D_BXT, NULL, bxt_de_pll_enable_write);
+	MMIO_D(BXT_DSI_PLL_CTL, D_BXT);
+	MMIO_D(BXT_DSI_PLL_ENABLE, D_BXT);
+
+	MMIO_D(GEN9_CLKGATE_DIS_0, D_BXT);
+
+	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_A), D_BXT);
+	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT);
+	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT);
+
+	MMIO_D(RC6_CTX_BASE, D_BXT);
+
+	MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT);
+	MMIO_D(GEN8_PUSHBUS_ENABLE, D_BXT);
+	MMIO_D(GEN8_PUSHBUS_SHIFT, D_BXT);
+	MMIO_D(GEN6_GFXPAUSE, D_BXT);
+	MMIO_D(GEN8_L3SQCREG1, D_BXT);
+
+	MMIO_DFH(GEN9_CTX_PREEMPT_REG, D_BXT, F_CMD_ACCESS, NULL, NULL);
 
 	return 0;
 }
@@ -2966,6 +3255,16 @@ int intel_gvt_setup_mmio_info(struct intel_gvt *gvt)
 		ret = init_skl_mmio_info(gvt);
 		if (ret)
 			goto err;
+	} else if (IS_BROXTON(dev_priv)) {
+		ret = init_broadwell_mmio_info(gvt);
+		if (ret)
+			goto err;
+		ret = init_skl_mmio_info(gvt);
+		if (ret)
+			goto err;
+		ret = init_bxt_mmio_info(gvt);
+		if (ret)
+			goto err;
 	}
 
 	gvt->mmio.mmio_block = mmio_blocks;
-- 
cgit v1.2.3


From 57c8a484a9cbf1315b5299702d12aef04867eeee Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 11 Jun 2018 15:39:40 +0800
Subject: drm/i915: Enable KVMGT for BXT.

Enable KVMGT for BXT.
is_supported_device() acting as the gatekeeper of GVT-g init.
If all supported platforms share the same configurations for some
specific feature, platform check will rely on this check only.

Signed-off-by: Colin Xu <colin.xu@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_gvt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index a2fe7c8d4477..a6291f60545b 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -47,6 +47,8 @@ static bool is_supported_device(struct drm_i915_private *dev_priv)
 		return true;
 	if (IS_KABYLAKE(dev_priv))
 		return true;
+	if (IS_BROXTON(dev_priv))
+		return true;
 	return false;
 }
 
-- 
cgit v1.2.3


From f1d270ae10ffc8d4f9726cc8b654e4e8cda294b5 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 24 May 2018 17:59:28 -0500
Subject: ath10k: htt_tx: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I replaced "pass through" with
a proper "fall through" comment, which is what GCC is expecting
to find.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htt_tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 5d8b97a0ccaa..89157c5b5e5f 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -1202,7 +1202,7 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt,
 	case ATH10K_HW_TXRX_RAW:
 	case ATH10K_HW_TXRX_NATIVE_WIFI:
 		flags0 |= HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT;
-		/* pass through */
+		/* fall through */
 	case ATH10K_HW_TXRX_ETHERNET:
 		if (ar->hw_params.continuous_frag_desc) {
 			ext_desc_t = htt->frag_desc.vaddr_desc_32;
@@ -1404,7 +1404,7 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt,
 	case ATH10K_HW_TXRX_RAW:
 	case ATH10K_HW_TXRX_NATIVE_WIFI:
 		flags0 |= HTT_DATA_TX_DESC_FLAGS0_MAC_HDR_PRESENT;
-		/* pass through */
+		/* fall through */
 	case ATH10K_HW_TXRX_ETHERNET:
 		if (ar->hw_params.continuous_frag_desc) {
 			ext_desc_t = htt->frag_desc.vaddr_desc_64;
-- 
cgit v1.2.3


From aae28cefc279203c1d1bc460c831b0a557662945 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 24 May 2018 18:07:00 -0500
Subject: ath5k: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath5k/pcu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath5k/pcu.c b/drivers/net/wireless/ath/ath5k/pcu.c
index f23c851765df..05140d8baa36 100644
--- a/drivers/net/wireless/ath/ath5k/pcu.c
+++ b/drivers/net/wireless/ath/ath5k/pcu.c
@@ -670,6 +670,7 @@ ath5k_hw_init_beacon_timers(struct ath5k_hw *ah, u32 next_beacon, u32 interval)
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		AR5K_REG_ENABLE_BITS(ah, AR5K_TXCFG, AR5K_TXCFG_ADHOC_BCN_ATIM);
+		/* fall through */
 	default:
 		/* On non-STA modes timer1 is used as next DMA
 		 * beacon alert (DBA) timer and timer2 as next
-- 
cgit v1.2.3


From 87b466f42e8fa8c0297b23c4b9776bd4e5d9d029 Mon Sep 17 00:00:00 2001
From: Guy Chronister <guylovesbritt@gmail.com>
Date: Mon, 21 May 2018 16:26:44 -0500
Subject: ath6kl: add support for Dell Wireless 1537

This is a Qualcomm Atheros AR6004X with an sdio ID of 0x19 and hardware ID of
0271:0419. Tested on a Dell Venue 11 Pro 7130 with a self compiled kernel.

Signed-off-by: Guy Chronister <guylovesbritt@gmail.com>
[kvalo@codeaurora.org: cleanup commit log]
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/sdio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath6kl/sdio.c b/drivers/net/wireless/ath/ath6kl/sdio.c
index 2195b1b7a8a6..bb50680580f3 100644
--- a/drivers/net/wireless/ath/ath6kl/sdio.c
+++ b/drivers/net/wireless/ath/ath6kl/sdio.c
@@ -1415,6 +1415,7 @@ static const struct sdio_device_id ath6kl_sdio_devices[] = {
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x1))},
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x2))},
 	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x18))},
+	{SDIO_DEVICE(MANUFACTURER_CODE, (MANUFACTURER_ID_AR6004_BASE | 0x19))},
 	{},
 };
 
-- 
cgit v1.2.3


From 4de30c906ef08af67c6d81c03e3505ee467db026 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 25 May 2018 13:23:11 -0500
Subject: ath6kl: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Steve deRosier <derosier@cal-sierra.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/cfg80211.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 2ba8cf3f38af..a16ee5d6e507 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -3899,16 +3899,19 @@ int ath6kl_cfg80211_init(struct ath6kl *ar)
 	switch (ar->hw.cap) {
 	case WMI_11AN_CAP:
 		ht = true;
+		/* fall through */
 	case WMI_11A_CAP:
 		band_5gig = true;
 		break;
 	case WMI_11GN_CAP:
 		ht = true;
+		/* fall through */
 	case WMI_11G_CAP:
 		band_2gig = true;
 		break;
 	case WMI_11AGN_CAP:
 		ht = true;
+		/* fall through */
 	case WMI_11AG_CAP:
 		band_2gig = true;
 		band_5gig = true;
-- 
cgit v1.2.3


From 12b67b0d6bcbe91d8b0682610f43d1cd8cdf280e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 25 May 2018 16:22:07 -0500
Subject: ath9k: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ar5008_phy.c | 2 ++
 drivers/net/wireless/ath/ath9k/ar9002_phy.c | 1 +
 drivers/net/wireless/ath/ath9k/main.c       | 1 +
 3 files changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ath/ath9k/ar5008_phy.c b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
index 7922550c2159..ef2dd68d3f77 100644
--- a/drivers/net/wireless/ath/ath9k/ar5008_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar5008_phy.c
@@ -583,12 +583,14 @@ static void ar5008_hw_init_chain_masks(struct ath_hw *ah)
 	case 0x5:
 		REG_SET_BIT(ah, AR_PHY_ANALOG_SWAP,
 			    AR_PHY_SWAP_ALT_CHAIN);
+		/* fall through */
 	case 0x3:
 		if (ah->hw_version.macVersion == AR_SREV_REVISION_5416_10) {
 			REG_WRITE(ah, AR_PHY_RX_CHAINMASK, 0x7);
 			REG_WRITE(ah, AR_PHY_CAL_CHAINMASK, 0x7);
 			break;
 		}
+		/* else: fall through */
 	case 0x1:
 	case 0x2:
 	case 0x7:
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_phy.c b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
index 61a9b85045d2..713291881208 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_phy.c
@@ -119,6 +119,7 @@ static int ar9002_hw_set_channel(struct ath_hw *ah, struct ath9k_channel *chan)
 				aModeRefSel = 2;
 			if (aModeRefSel)
 				break;
+			/* else: fall through */
 		case 1:
 		default:
 			aModeRefSel = 0;
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index a3be8add56e1..11d84f467203 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1928,6 +1928,7 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw,
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		flush = true;
+		/* fall through */
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		ath9k_ps_wakeup(sc);
 		ath_tx_aggr_stop(sc, sta, tid);
-- 
cgit v1.2.3


From 260e629bbf441585860e21d5e10d2e88437f47c8 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sun, 27 May 2018 22:17:02 +0100
Subject: ath10k: fix memory leak of tpc_stats

Currently tpc_stats is allocated and is leaked on the return
path if num_tx_chain is greater than WMI_TPC_TX_N_CHAIN. Avoid
this leak by performing the check on num_tx_chain before the
allocation of tpc_stats.

Detected by CoverityScan, CID#1469422 ("Resource Leak")
Fixes: 4b190675ad06 ("ath10k: fix kernel panic while reading tpc_stats")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index f97ab795cf2e..2319f79b34f0 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -4602,10 +4602,6 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb)
 
 	ev = (struct wmi_pdev_tpc_config_event *)skb->data;
 
-	tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC);
-	if (!tpc_stats)
-		return;
-
 	num_tx_chain = __le32_to_cpu(ev->num_tx_chain);
 
 	if (num_tx_chain > WMI_TPC_TX_N_CHAIN) {
@@ -4614,6 +4610,10 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb)
 		return;
 	}
 
+	tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC);
+	if (!tpc_stats)
+		return;
+
 	ath10k_wmi_tpc_config_get_rate_code(rate_code, pream_table,
 					    num_tx_chain);
 
-- 
cgit v1.2.3


From e4dd27aadd205417a2e9ea9902b698a0252ec3a0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 24 May 2018 15:54:03 +0300
Subject: drm/i915: Allow DBLSCAN user modes with eDP/LVDS/DSI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When encountering a connector with the scaling mode property both
intel and modesetting ddxs sometimes add tons of DBLSCAN modes
to the output's mode list. The idea presumably being that since the
output will be going through the panel fitter anyway we can pretend
to use any kind of mode.

Sadly that means we can't reject user modes with the DBLSCAN flag
until we know whether we're going to be using the panel's native
mode or the user mode directly. Doing otherwise means X clients using
xf86vidmode/xrandr will get a protocol error (and often self
terminate as a result) when the kernel refuses to use the requested
mode with the DBLSCAN flag.

To undo the regression we'll move the DBLSCAN checks into the
connector->mode_valid() and encoder->compute_config() hooks.

Cc: stable@vger.kernel.org
Cc: Vito Caputo <vcaputo@pengaru.com>
Reported-by: Vito Caputo <vcaputo@pengaru.com>
Fixes: e995ca0b8139 ("drm/i915: Provide a device level .mode_valid() hook")
References: https://lkml.org/lkml/2018/5/21/715
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180524125403.23445-1-ville.syrjala@linux.intel.com
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106804
Tested-by: Arkadiusz Miskiewicz <arekm@maven.pl>
---
 drivers/gpu/drm/i915/intel_crt.c     | 20 ++++++++++++++++++++
 drivers/gpu/drm/i915/intel_display.c | 16 +++++++++++++---
 drivers/gpu/drm/i915/intel_dp.c      |  6 ++++++
 drivers/gpu/drm/i915/intel_dp_mst.c  |  6 ++++++
 drivers/gpu/drm/i915/intel_dsi.c     |  6 ++++++
 drivers/gpu/drm/i915/intel_dvo.c     |  6 ++++++
 drivers/gpu/drm/i915/intel_hdmi.c    |  6 ++++++
 drivers/gpu/drm/i915/intel_lvds.c    |  5 +++++
 drivers/gpu/drm/i915/intel_sdvo.c    |  6 ++++++
 drivers/gpu/drm/i915/intel_tv.c      | 12 ++++++++++--
 10 files changed, 84 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 211d601cd1b1..95aa29cf2d9c 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -304,6 +304,9 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	int max_dotclk = dev_priv->max_dotclk_freq;
 	int max_clock;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (mode->clock < 25000)
 		return MODE_CLOCK_LOW;
 
@@ -337,6 +340,12 @@ static bool intel_crt_compute_config(struct intel_encoder *encoder,
 				     struct intel_crtc_state *pipe_config,
 				     struct drm_connector_state *conn_state)
 {
+	struct drm_display_mode *adjusted_mode =
+		&pipe_config->base.adjusted_mode;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	return true;
 }
 
@@ -344,6 +353,12 @@ static bool pch_crt_compute_config(struct intel_encoder *encoder,
 				   struct intel_crtc_state *pipe_config,
 				   struct drm_connector_state *conn_state)
 {
+	struct drm_display_mode *adjusted_mode =
+		&pipe_config->base.adjusted_mode;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	pipe_config->has_pch_encoder = true;
 
 	return true;
@@ -354,6 +369,11 @@ static bool hsw_crt_compute_config(struct intel_encoder *encoder,
 				   struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct drm_display_mode *adjusted_mode =
+		&pipe_config->base.adjusted_mode;
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
 
 	pipe_config->has_pch_encoder = true;
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 17c590b42fd7..3323470596ca 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -14529,12 +14529,22 @@ static enum drm_mode_status
 intel_mode_valid(struct drm_device *dev,
 		 const struct drm_display_mode *mode)
 {
+	/*
+	 * Can't reject DBLSCAN here because Xorg ddxen can add piles
+	 * of DBLSCAN modes to the output's mode list when they detect
+	 * the scaling mode property on the connector. And they don't
+	 * ask the kernel to validate those modes in any way until
+	 * modeset time at which point the client gets a protocol error.
+	 * So in order to not upset those clients we silently ignore the
+	 * DBLSCAN flag on such connectors. For other connectors we will
+	 * reject modes with the DBLSCAN flag in encoder->compute_config().
+	 * And we always reject DBLSCAN modes in connector->mode_valid()
+	 * as we never want such modes on the connector's mode list.
+	 */
+
 	if (mode->vscan > 1)
 		return MODE_NO_VSCAN;
 
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return MODE_NO_DBLESCAN;
-
 	if (mode->flags & DRM_MODE_FLAG_HSKEW)
 		return MODE_H_ILLEGAL;
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 40ffd9163175..a58bac01aeea 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -420,6 +420,9 @@ intel_dp_mode_valid(struct drm_connector *connector,
 	int max_rate, mode_rate, max_lanes, max_link_clock;
 	int max_dotclk;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	max_dotclk = intel_dp_downstream_max_dotclock(intel_dp);
 
 	if (intel_dp_is_edp(intel_dp) && fixed_mode) {
@@ -1869,6 +1872,9 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 						conn_state->scaling_mode);
 	}
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
 	    adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
 		return false;
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 9e6956c08688..5890500a3a8b 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -48,6 +48,9 @@ static bool intel_dp_mst_compute_config(struct intel_encoder *encoder,
 	bool reduce_m_n = drm_dp_has_quirk(&intel_dp->desc,
 					   DP_DPCD_QUIRK_LIMITED_M_N);
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	pipe_config->has_pch_encoder = false;
 	bpp = 24;
 	if (intel_dp->compliance.test_data.bpc) {
@@ -366,6 +369,9 @@ intel_dp_mst_mode_valid(struct drm_connector *connector,
 	if (!intel_dp)
 		return MODE_ERROR;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	max_link_clock = intel_dp_max_link_rate(intel_dp);
 	max_lanes = intel_dp_max_lane_count(intel_dp);
 
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
index cf1231f9c33b..3b7acb5a70b3 100644
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ b/drivers/gpu/drm/i915/intel_dsi.c
@@ -326,6 +326,9 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 						conn_state->scaling_mode);
 	}
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	/* DSI uses short packets for sync events, so clear mode flags for DSI */
 	adjusted_mode->flags = 0;
 
@@ -1266,6 +1269,9 @@ intel_dsi_mode_valid(struct drm_connector *connector,
 
 	DRM_DEBUG_KMS("\n");
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (fixed_mode) {
 		if (mode->hdisplay > fixed_mode->hdisplay)
 			return MODE_PANEL;
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 7b942b6c1700..27f16db8953a 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -215,6 +215,9 @@ intel_dvo_mode_valid(struct drm_connector *connector,
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 	int target_clock = mode->clock;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	/* XXX: Validate clock range */
 
 	if (fixed_mode) {
@@ -250,6 +253,9 @@ static bool intel_dvo_compute_config(struct intel_encoder *encoder,
 	if (fixed_mode)
 		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	return true;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index ef4de5a02cb5..447ffe590e55 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1540,6 +1540,9 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	bool force_dvi =
 		READ_ONCE(to_intel_digital_connector_state(connector->state)->force_audio) == HDMI_AUDIO_OFF_DVI;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	clock = mode->clock;
 
 	if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING)
@@ -1660,6 +1663,9 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	int desired_bpp;
 	bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI;
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	pipe_config->has_hdmi_sink = !force_dvi && intel_hdmi->has_hdmi_sink;
 
 	if (pipe_config->has_hdmi_sink)
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index e05c12e7629c..bb06744d28a4 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -378,6 +378,8 @@ intel_lvds_mode_valid(struct drm_connector *connector,
 	struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
 	int max_pixclk = to_i915(connector->dev)->max_dotclk_freq;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
 	if (mode->hdisplay > fixed_mode->hdisplay)
 		return MODE_PANEL;
 	if (mode->vdisplay > fixed_mode->vdisplay)
@@ -427,6 +429,9 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	intel_fixed_panel_mode(intel_connector->panel.fixed_mode,
 			       adjusted_mode);
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	if (HAS_PCH_SPLIT(dev_priv)) {
 		pipe_config->has_pch_encoder = true;
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 848b03a542d6..9d9229a1f36c 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1160,6 +1160,9 @@ static bool intel_sdvo_compute_config(struct intel_encoder *encoder,
 							   adjusted_mode);
 	}
 
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
 	/*
 	 * Make the CRTC code factor in the SDVO pixel multiplier.  The
 	 * SDVO device will factor out the multiplier during mode_set.
@@ -1631,6 +1634,9 @@ intel_sdvo_mode_valid(struct drm_connector *connector,
 	struct intel_sdvo *intel_sdvo = intel_attached_sdvo(connector);
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (intel_sdvo->pixel_clock_min > mode->clock)
 		return MODE_CLOCK_LOW;
 
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 99bc2368dda0..24dc368fdaa1 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -846,6 +846,9 @@ intel_tv_mode_valid(struct drm_connector *connector,
 	const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state);
 	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
 
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
 	if (mode->clock > max_dotclk)
 		return MODE_CLOCK_HIGH;
 
@@ -873,16 +876,21 @@ intel_tv_compute_config(struct intel_encoder *encoder,
 			struct drm_connector_state *conn_state)
 {
 	const struct tv_mode *tv_mode = intel_tv_mode_find(conn_state);
+	struct drm_display_mode *adjusted_mode =
+		&pipe_config->base.adjusted_mode;
 
 	if (!tv_mode)
 		return false;
 
-	pipe_config->base.adjusted_mode.crtc_clock = tv_mode->clock;
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
+	adjusted_mode->crtc_clock = tv_mode->clock;
 	DRM_DEBUG_KMS("forcing bpc to 8 for TV\n");
 	pipe_config->pipe_bpp = 8*3;
 
 	/* TV has it's own notion of sync and other mode flags, so clear them. */
-	pipe_config->base.adjusted_mode.flags = 0;
+	adjusted_mode->flags = 0;
 
 	/*
 	 * FIXME: We don't check whether the input mode is actually what we want
-- 
cgit v1.2.3


From 697b9a8714cb4631fd0526b3c78955d5422c24ba Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 12 Jun 2018 11:51:35 +0100
Subject: drm/i915: Make closing request flush mandatory

For symmetry, simplicity and ensuring the request is always truly idle
upon its completion, always emit the closing flush prior to emitting the
request breadcrumb. Previously, we would only emit the flush if we had
started a user batch, but this just leaves all the other paths open to
speculation (do they affect the GPU caches or not?) With mm switching, a
key requirement is that the GPU is flushed and invalidated before hand,
so for absolute safety, we want that closing flush be mandatory.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612105135.4459-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c                     |  4 ++--
 drivers/gpu/drm/i915/i915_gem_context.c             |  9 +--------
 drivers/gpu/drm/i915/i915_gem_execbuffer.c          |  4 ++--
 drivers/gpu/drm/i915/i915_request.c                 | 18 ++----------------
 drivers/gpu/drm/i915/i915_request.h                 |  4 +---
 drivers/gpu/drm/i915/selftests/huge_pages.c         |  2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_coherency.c |  4 ++--
 drivers/gpu/drm/i915/selftests/i915_gem_context.c   |  4 ++--
 drivers/gpu/drm/i915/selftests/i915_request.c       |  2 +-
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c    | 16 ++++++++--------
 drivers/gpu/drm/i915/selftests/intel_lrc.c          |  2 +-
 drivers/gpu/drm/i915/selftests/intel_workarounds.c  |  2 +-
 12 files changed, 24 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 93efd92362db..8dd4d35655af 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3213,7 +3213,7 @@ void i915_gem_reset(struct drm_i915_private *dev_priv,
 			rq = i915_request_alloc(engine,
 						dev_priv->kernel_context);
 			if (!IS_ERR(rq))
-				__i915_request_add(rq, false);
+				i915_request_add(rq);
 		}
 	}
 
@@ -5332,7 +5332,7 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 		if (engine->init_context)
 			err = engine->init_context(rq);
 
-		__i915_request_add(rq, true);
+		i915_request_add(rq);
 		if (err)
 			goto err_active;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index b2c7ac1b074d..ef6ea4bcd773 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -700,14 +700,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 			i915_timeline_sync_set(rq->timeline, &prev->fence);
 		}
 
-		/*
-		 * Force a flush after the switch to ensure that all rendering
-		 * and operations prior to switching to the kernel context hits
-		 * memory. This should be guaranteed by the previous request,
-		 * but an extra layer of paranoia before we declare the system
-		 * idle (on suspend etc) is advisable!
-		 */
-		__i915_request_add(rq, true);
+		i915_request_add(rq);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 2d2eb3075960..60dc2a865f5f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -921,7 +921,7 @@ static void reloc_gpu_flush(struct reloc_cache *cache)
 	i915_gem_object_unpin_map(cache->rq->batch->obj);
 	i915_gem_chipset_flush(cache->rq->i915);
 
-	__i915_request_add(cache->rq, true);
+	i915_request_add(cache->rq);
 	cache->rq = NULL;
 }
 
@@ -2438,7 +2438,7 @@ i915_gem_do_execbuffer(struct drm_device *dev,
 	trace_i915_request_queue(eb.request, eb.batch_flags);
 	err = eb_submit(&eb);
 err_request:
-	__i915_request_add(eb.request, err == 0);
+	i915_request_add(eb.request);
 	add_to_client(eb.request, file);
 
 	if (fences)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 9092f5464c24..e1dbb544046f 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1018,14 +1018,13 @@ i915_request_await_object(struct i915_request *to,
  * request is not being tracked for completion but the work itself is
  * going to happen on the hardware. This would be a Bad Thing(tm).
  */
-void __i915_request_add(struct i915_request *request, bool flush_caches)
+void i915_request_add(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
 	struct i915_timeline *timeline = request->timeline;
 	struct intel_ring *ring = request->ring;
 	struct i915_request *prev;
 	u32 *cs;
-	int err;
 
 	GEM_TRACE("%s fence %llx:%d\n",
 		  engine->name, request->fence.context, request->fence.seqno);
@@ -1046,20 +1045,7 @@ void __i915_request_add(struct i915_request *request, bool flush_caches)
 	 * know that it is time to use that space up.
 	 */
 	request->reserved_space = 0;
-
-	/*
-	 * Emit any outstanding flushes - execbuf can fail to emit the flush
-	 * after having emitted the batchbuffer command. Hence we need to fix
-	 * things up similar to emitting the lazy request. The difference here
-	 * is that the flush _must_ happen before the next request, no matter
-	 * what.
-	 */
-	if (flush_caches) {
-		err = engine->emit_flush(request, EMIT_FLUSH);
-
-		/* Not allowed to fail! */
-		WARN(err, "engine->emit_flush() failed: %d!\n", err);
-	}
+	engine->emit_flush(request, EMIT_FLUSH);
 
 	/*
 	 * Record the position of the start of the breadcrumb so that
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 0e9aba53d0e4..7ee220ded9c9 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -253,9 +253,7 @@ int i915_request_await_object(struct i915_request *to,
 int i915_request_await_dma_fence(struct i915_request *rq,
 				 struct dma_fence *fence);
 
-void __i915_request_add(struct i915_request *rq, bool flush_caches);
-#define i915_request_add(rq) \
-	__i915_request_add(rq, false)
+void i915_request_add(struct i915_request *rq);
 
 void __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 7846ea4a99bc..fbe4324116d7 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -1003,7 +1003,7 @@ static int gpu_write(struct i915_vma *vma,
 	reservation_object_unlock(vma->resv);
 
 err_request:
-	__i915_request_add(rq, err == 0);
+	i915_request_add(rq);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index 340a98c0c804..a4900091ae3d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -199,7 +199,7 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 
 	cs = intel_ring_begin(rq, 4);
 	if (IS_ERR(cs)) {
-		__i915_request_add(rq, false);
+		i915_request_add(rq);
 		i915_vma_unpin(vma);
 		return PTR_ERR(cs);
 	}
@@ -229,7 +229,7 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 	reservation_object_add_excl_fence(obj->resv, &rq->fence);
 	reservation_object_unlock(obj->resv);
 
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 708e8d721448..836f1af8b833 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -182,12 +182,12 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 	reservation_object_add_excl_fence(obj->resv, &rq->fence);
 	reservation_object_unlock(obj->resv);
 
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
 	return 0;
 
 err_request:
-	__i915_request_add(rq, false);
+	i915_request_add(rq);
 err_batch:
 	i915_vma_unpin(batch);
 err_vma:
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index a3a89aadeccb..f5d00332bb31 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -466,7 +466,7 @@ empty_request(struct intel_engine_cs *engine,
 		goto out_request;
 
 out_request:
-	__i915_request_add(request, err == 0);
+	i915_request_add(request);
 	return err ? ERR_PTR(err) : request;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 390a157b37c3..fe7d3190ebfe 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -245,7 +245,7 @@ hang_create_request(struct hang *h, struct intel_engine_cs *engine)
 
 	err = emit_recurse_batch(h, rq);
 	if (err) {
-		__i915_request_add(rq, false);
+		i915_request_add(rq);
 		return ERR_PTR(err);
 	}
 
@@ -318,7 +318,7 @@ static int igt_hang_sanitycheck(void *arg)
 		*h.batch = MI_BATCH_BUFFER_END;
 		i915_gem_chipset_flush(i915);
 
-		__i915_request_add(rq, true);
+		i915_request_add(rq);
 
 		timeout = i915_request_wait(rq,
 					    I915_WAIT_LOCKED,
@@ -464,7 +464,7 @@ static int __igt_reset_engine(struct drm_i915_private *i915, bool active)
 				}
 
 				i915_request_get(rq);
-				__i915_request_add(rq, true);
+				i915_request_add(rq);
 				mutex_unlock(&i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
@@ -742,7 +742,7 @@ static int __igt_reset_engines(struct drm_i915_private *i915,
 				}
 
 				i915_request_get(rq);
-				__i915_request_add(rq, true);
+				i915_request_add(rq);
 				mutex_unlock(&i915->drm.struct_mutex);
 
 				if (!wait_until_running(&h, rq)) {
@@ -942,7 +942,7 @@ static int igt_wait_reset(void *arg)
 	}
 
 	i915_request_get(rq);
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
 	if (!wait_until_running(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
@@ -1037,7 +1037,7 @@ static int igt_reset_queue(void *arg)
 		}
 
 		i915_request_get(prev);
-		__i915_request_add(prev, true);
+		i915_request_add(prev);
 
 		count = 0;
 		do {
@@ -1051,7 +1051,7 @@ static int igt_reset_queue(void *arg)
 			}
 
 			i915_request_get(rq);
-			__i915_request_add(rq, true);
+			i915_request_add(rq);
 
 			/*
 			 * XXX We don't handle resetting the kernel context
@@ -1184,7 +1184,7 @@ static int igt_handle_error(void *arg)
 	}
 
 	i915_request_get(rq);
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 
 	if (!wait_until_running(&h, rq)) {
 		struct drm_printer p = drm_info_printer(i915->drm.dev);
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index 0b6da08c8cae..ea27c7cfbf96 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -155,7 +155,7 @@ spinner_create_request(struct spinner *spin,
 
 	err = emit_recurse_batch(spin, rq, arbitration_command);
 	if (err) {
-		__i915_request_add(rq, false);
+		i915_request_add(rq);
 		return ERR_PTR(err);
 	}
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index f1cfb0fb6bea..e1ea2d2bedd2 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -75,7 +75,7 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	i915_gem_object_get(result);
 	i915_gem_object_set_active_reference(result);
 
-	__i915_request_add(rq, true);
+	i915_request_add(rq);
 	i915_vma_unpin(vma);
 
 	return result;
-- 
cgit v1.2.3


From 6ebb6d8ebe56135b06b1427ecaa712580b878ea2 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 13 Jun 2018 14:49:29 +0300
Subject: drm/i915/perf: make oa format tables const

No reason not to be const.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613114929.14541-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_perf.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 881a992305ec..447407fee3b8 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -315,7 +315,7 @@ static u32 i915_oa_max_sample_rate = 100000;
  * code assumes all reports have a power-of-two size and ~(size - 1) can
  * be used as a mask to align the OA tail pointer.
  */
-static struct i915_oa_format hsw_oa_formats[I915_OA_FORMAT_MAX] = {
+static const struct i915_oa_format hsw_oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_A13]	    = { 0, 64 },
 	[I915_OA_FORMAT_A29]	    = { 1, 128 },
 	[I915_OA_FORMAT_A13_B8_C8]  = { 2, 128 },
@@ -326,7 +326,7 @@ static struct i915_oa_format hsw_oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_C4_B8]	    = { 7, 64 },
 };
 
-static struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
+static const struct i915_oa_format gen8_plus_oa_formats[I915_OA_FORMAT_MAX] = {
 	[I915_OA_FORMAT_A12]		    = { 0, 64 },
 	[I915_OA_FORMAT_A12_B8_C8]	    = { 2, 128 },
 	[I915_OA_FORMAT_A32u40_A4u32_B8_C8] = { 5, 256 },
-- 
cgit v1.2.3


From 2e932b9cdecebe3f41eaa86f8cec15c42fc62d41 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 13 Jun 2018 14:39:27 +0300
Subject: drm/i915/opregion: move acpi notifier to dev_priv

Get rid of the silly static variable.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613113927.30033-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_opregion.c | 31 ++++++++++++-------------------
 drivers/gpu/drm/i915/intel_opregion.h |  1 +
 2 files changed, 13 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_opregion.c b/drivers/gpu/drm/i915/intel_opregion.c
index c58e5f53bab0..e034b4166d32 100644
--- a/drivers/gpu/drm/i915/intel_opregion.c
+++ b/drivers/gpu/drm/i915/intel_opregion.c
@@ -608,16 +608,16 @@ void intel_opregion_asle_intr(struct drm_i915_private *dev_priv)
 #define ACPI_EV_LID            (1<<1)
 #define ACPI_EV_DOCK           (1<<2)
 
-static struct intel_opregion *system_opregion;
-
+/*
+ * The only video events relevant to opregion are 0x80. These indicate either a
+ * docking event, lid switch or display switch request. In Linux, these are
+ * handled by the dock, button and video drivers.
+ */
 static int intel_opregion_video_event(struct notifier_block *nb,
 				      unsigned long val, void *data)
 {
-	/* The only video events relevant to opregion are 0x80. These indicate
-	   either a docking event, lid switch or display switch request. In
-	   Linux, these are handled by the dock, button and video drivers.
-	*/
-
+	struct intel_opregion *opregion = container_of(nb, struct intel_opregion,
+						       acpi_notifier);
 	struct acpi_bus_event *event = data;
 	struct opregion_acpi *acpi;
 	int ret = NOTIFY_OK;
@@ -625,10 +625,7 @@ static int intel_opregion_video_event(struct notifier_block *nb,
 	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
 		return NOTIFY_DONE;
 
-	if (!system_opregion)
-		return NOTIFY_DONE;
-
-	acpi = system_opregion->acpi;
+	acpi = opregion->acpi;
 
 	if (event->type == 0x80 && ((acpi->cevt & 1) == 0))
 		ret = NOTIFY_BAD;
@@ -638,10 +635,6 @@ static int intel_opregion_video_event(struct notifier_block *nb,
 	return ret;
 }
 
-static struct notifier_block intel_opregion_notifier = {
-	.notifier_call = intel_opregion_video_event,
-};
-
 /*
  * Initialise the DIDL field in opregion. This passes a list of devices to
  * the firmware. Values are defined by section B.4.2 of the ACPI specification
@@ -797,8 +790,8 @@ void intel_opregion_register(struct drm_i915_private *dev_priv)
 		opregion->acpi->csts = 0;
 		opregion->acpi->drdy = 1;
 
-		system_opregion = opregion;
-		register_acpi_notifier(&intel_opregion_notifier);
+		opregion->acpi_notifier.notifier_call = intel_opregion_video_event;
+		register_acpi_notifier(&opregion->acpi_notifier);
 	}
 
 	if (opregion->asle) {
@@ -822,8 +815,8 @@ void intel_opregion_unregister(struct drm_i915_private *dev_priv)
 	if (opregion->acpi) {
 		opregion->acpi->drdy = 0;
 
-		system_opregion = NULL;
-		unregister_acpi_notifier(&intel_opregion_notifier);
+		unregister_acpi_notifier(&opregion->acpi_notifier);
+		opregion->acpi_notifier.notifier_call = NULL;
 	}
 
 	/* just clear all opregion memory pointers now */
diff --git a/drivers/gpu/drm/i915/intel_opregion.h b/drivers/gpu/drm/i915/intel_opregion.h
index e0e437ba9e51..e8498a8cda3d 100644
--- a/drivers/gpu/drm/i915/intel_opregion.h
+++ b/drivers/gpu/drm/i915/intel_opregion.h
@@ -49,6 +49,7 @@ struct intel_opregion {
 	u32 vbt_size;
 	u32 *lid_state;
 	struct work_struct asle_work;
+	struct notifier_block acpi_notifier;
 };
 
 #define OPREGION_SIZE            (8 * 1024)
-- 
cgit v1.2.3


From 826d7bc9f013d01e92997883d2fd0c25f4af1f1c Mon Sep 17 00:00:00 2001
From: Konstantin Khorenko <khorenko@virtuozzo.com>
Date: Fri, 8 Jun 2018 17:27:11 +0300
Subject: fs/lock: skip lock owner pid translation in case we are in
 init_pid_ns

If the flock owner process is dead and its pid has been already freed,
pid translation won't work, but we still want to show flock owner pid
number when expecting /proc/$PID/fdinfo/$FD in init pidns.

Reproducer:
process A	process A1	process A2
fork()--------->
exit()		open()
		flock()
		fork()--------->
		exit()		sleep()

Before the patch:
================
(root@vz7)/: cat /proc/${PID_A2}/fdinfo/3
pos:    4
flags:  02100002
mnt_id: 257
lock:   (root@vz7)/:

After the patch:
===============
(root@vz7)/:cat /proc/${PID_A2}/fdinfo/3
pos:    4
flags:  02100002
mnt_id: 295
lock:   1: FLOCK  ADVISORY  WRITE ${PID_A1} b6:f8a61:529946 0 EOF

Fixes: 9d5b86ac13c5 ("fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks")
Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com>
Acked-by: Andrey Vagin <avagin@openvz.org>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
 fs/locks.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/fs/locks.c b/fs/locks.c
index 05e211be8684..bfee5b7f2862 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2072,6 +2072,13 @@ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns)
 		return -1;
 	if (IS_REMOTELCK(fl))
 		return fl->fl_pid;
+	/*
+	 * If the flock owner process is dead and its pid has been already
+	 * freed, the translation below won't work, but we still want to show
+	 * flock owner pid number in init pidns.
+	 */
+	if (ns == &init_pid_ns)
+		return (pid_t)fl->fl_pid;
 
 	rcu_read_lock();
 	pid = find_pid_ns(fl->fl_pid, &init_pid_ns);
-- 
cgit v1.2.3


From 1cf8e5de4055f85383405a21a0a7c3c4348bf2ed Mon Sep 17 00:00:00 2001
From: Konstantin Khorenko <khorenko@virtuozzo.com>
Date: Fri, 8 Jun 2018 17:27:12 +0300
Subject: fs/lock: show locks taken by processes from another pidns

Currently if we face a lock taken by a process invisible in the current
pidns we skip the lock completely, but this

1) makes the output not that nice
    (root@vz7)/: cat /proc/${PID_A2}/fdinfo/3
    pos:    4
    flags:  02100002
    mnt_id: 257
    lock:   (root@vz7)/:

2) makes it more difficult to debug issues with leaked flocks
   if you get error on lock, but don't see any locks in /proc/$id/fdinfo/$file

Let's show information about such locks again as previously, but
show zero in the owner pid field.

After the patch:
===============
(root@vz7)/:cat /proc/${PID_A2}/fdinfo/3
pos:    4
flags:  02100002
mnt_id: 295
lock:   1: FLOCK  ADVISORY  WRITE 0 b6:f8a61:529946 0 EOF

Fixes: 9d5b86ac13c5 ("fs/locks: Remove fl_nspid and use fs-specific l_pid for remote locks")
Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com>
Acked-by: Andrey Vagin <avagin@openvz.org>
Reviewed-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Jeff Layton <jlayton@redhat.com>
---
 fs/locks.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/locks.c b/fs/locks.c
index bfee5b7f2862..e533623e2e99 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -2633,12 +2633,10 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl,
 
 	fl_pid = locks_translate_pid(fl, proc_pidns);
 	/*
-	 * If there isn't a fl_pid don't display who is waiting on
-	 * the lock if we are called from locks_show, or if we are
-	 * called from __show_fd_info - skip lock entirely
+	 * If lock owner is dead (and pid is freed) or not visible in current
+	 * pidns, zero is shown as a pid value. Check lock info from
+	 * init_pid_ns to get saved lock pid value.
 	 */
-	if (fl_pid == 0)
-		return;
 
 	if (fl->fl_file != NULL)
 		inode = locks_inode(fl->fl_file);
-- 
cgit v1.2.3


From 1288786b18f7d979f1f9bcb0134ee5fbfcc8e3d1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 10:40:59 +0100
Subject: drm/i915: Move GEM sanitize from resume_early to resume

This should be a no-op in terms of our control flow, we move the
sanitization (GPU reset) from the bottom of the early resume phase to
the top of the next. However, following hibernation debug, the power
code skips the early resume phase, but as we are about to completely
restore the GTT mappings, we first need to stop the GPU using them i.e.
perform a GPU reset (i915_gem_sanitize()).

Testcase: igt/gem_exec_suspend/basic-S4-devices
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Imre Deak <imre.deak@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614094103.18025-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 4cdd70de5ed0..a9c8c66bb525 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1698,6 +1698,8 @@ static int i915_drm_resume(struct drm_device *dev)
 	disable_rpm_wakeref_asserts(dev_priv);
 	intel_sanitize_gt_powersave(dev_priv);
 
+	i915_gem_sanitize(dev_priv);
+
 	ret = i915_ggtt_enable_hw(dev_priv);
 	if (ret)
 		DRM_ERROR("failed to re-enable GGTT\n");
@@ -1839,8 +1841,6 @@ static int i915_drm_resume_early(struct drm_device *dev)
 	else
 		intel_display_set_init_power(dev_priv, true);
 
-	i915_gem_sanitize(dev_priv);
-
 	enable_rpm_wakeref_asserts(dev_priv);
 
 out:
-- 
cgit v1.2.3


From d6abe6df706c66d803e6dd4fe98c1b6b7f125a56 Mon Sep 17 00:00:00 2001
From: Inki Dae <inki.dae@samsung.com>
Date: Thu, 24 May 2018 18:32:59 +0900
Subject: drm/bridge: sil_sii8620: do not have a dependency of RC_CORE

This patch makes RC_CORE to be selected with this driver.

sil_sii8620 driver calls remote controller interfaces directly
so RC_CORE should be enabled mandatorily.

And some boards not using remote controller device don't really
need to know that RC_CORE config should be enabled to use sil_sii8620
driver only for HDMI.

Changelog v2:
- select INPUT because compiling will fail without INPUT.

Signed-off-by: Inki Dae <inki.dae@samsung.com>
Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527154379-31886-1-git-send-email-inki.dae@samsung.com
---
 drivers/gpu/drm/bridge/Kconfig | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/bridge/Kconfig b/drivers/gpu/drm/bridge/Kconfig
index 1d75d3a1f951..5cc4a51e1e92 100644
--- a/drivers/gpu/drm/bridge/Kconfig
+++ b/drivers/gpu/drm/bridge/Kconfig
@@ -82,8 +82,10 @@ config DRM_PARADE_PS8622
 
 config DRM_SIL_SII8620
 	tristate "Silicon Image SII8620 HDMI/MHL bridge"
-	depends on OF && RC_CORE
+	depends on OF
 	select DRM_KMS_HELPER
+	select INPUT
+	select RC_CORE
 	help
 	  Silicon Image SII8620 HDMI/MHL bridge chip driver.
 
-- 
cgit v1.2.3


From 856e1b175650816dce554d2865ec258aa3b72098 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 14 Jun 2018 13:47:09 +0300
Subject: drm/i915/dsm: remove unnecessary dsm priv structure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pass a local acpi_handle around instead of having a static dsm priv
structure. If we need it later, we can always move it to dev_priv, and
the change at hand will make that easier as well.

Care is taken to preserve old behaviour, particularly using the last
non-NULL acpi handle, whether it makes sense or not.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614104709.2808-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_acpi.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_acpi.c b/drivers/gpu/drm/i915/intel_acpi.c
index d1abf4bb7c81..6ba478e57b9b 100644
--- a/drivers/gpu/drm/i915/intel_acpi.c
+++ b/drivers/gpu/drm/i915/intel_acpi.c
@@ -12,10 +12,6 @@
 #define INTEL_DSM_REVISION_ID 1 /* For Calpella anyway... */
 #define INTEL_DSM_FN_PLATFORM_MUX_INFO 1 /* No args */
 
-static struct intel_dsm_priv {
-	acpi_handle dhandle;
-} intel_dsm_priv;
-
 static const guid_t intel_dsm_guid =
 	GUID_INIT(0x7ed873d3, 0xc2d0, 0x4e4f,
 		  0xa8, 0x54, 0x0f, 0x13, 0x17, 0xb0, 0x1c, 0x2c);
@@ -72,12 +68,12 @@ static char *intel_dsm_mux_type(u8 type)
 	}
 }
 
-static void intel_dsm_platform_mux_info(void)
+static void intel_dsm_platform_mux_info(acpi_handle dhandle)
 {
 	int i;
 	union acpi_object *pkg, *connector_count;
 
-	pkg = acpi_evaluate_dsm_typed(intel_dsm_priv.dhandle, &intel_dsm_guid,
+	pkg = acpi_evaluate_dsm_typed(dhandle, &intel_dsm_guid,
 			INTEL_DSM_REVISION_ID, INTEL_DSM_FN_PLATFORM_MUX_INFO,
 			NULL, ACPI_TYPE_PACKAGE);
 	if (!pkg) {
@@ -107,41 +103,40 @@ static void intel_dsm_platform_mux_info(void)
 	ACPI_FREE(pkg);
 }
 
-static bool intel_dsm_pci_probe(struct pci_dev *pdev)
+static acpi_handle intel_dsm_pci_probe(struct pci_dev *pdev)
 {
 	acpi_handle dhandle;
 
 	dhandle = ACPI_HANDLE(&pdev->dev);
 	if (!dhandle)
-		return false;
+		return NULL;
 
 	if (!acpi_check_dsm(dhandle, &intel_dsm_guid, INTEL_DSM_REVISION_ID,
 			    1 << INTEL_DSM_FN_PLATFORM_MUX_INFO)) {
 		DRM_DEBUG_KMS("no _DSM method for intel device\n");
-		return false;
+		return NULL;
 	}
 
-	intel_dsm_priv.dhandle = dhandle;
-	intel_dsm_platform_mux_info();
+	intel_dsm_platform_mux_info(dhandle);
 
-	return true;
+	return dhandle;
 }
 
 static bool intel_dsm_detect(void)
 {
+	acpi_handle dhandle = NULL;
 	char acpi_method_name[255] = { 0 };
 	struct acpi_buffer buffer = {sizeof(acpi_method_name), acpi_method_name};
 	struct pci_dev *pdev = NULL;
-	bool has_dsm = false;
 	int vga_count = 0;
 
 	while ((pdev = pci_get_class(PCI_CLASS_DISPLAY_VGA << 8, pdev)) != NULL) {
 		vga_count++;
-		has_dsm |= intel_dsm_pci_probe(pdev);
+		dhandle = intel_dsm_pci_probe(pdev) ?: dhandle;
 	}
 
-	if (vga_count == 2 && has_dsm) {
-		acpi_get_name(intel_dsm_priv.dhandle, ACPI_FULL_PATHNAME, &buffer);
+	if (vga_count == 2 && dhandle) {
+		acpi_get_name(dhandle, ACPI_FULL_PATHNAME, &buffer);
 		DRM_DEBUG_DRIVER("vga_switcheroo: detected DSM switching method %s handle\n",
 				 acpi_method_name);
 		return true;
-- 
cgit v1.2.3


From 83c317832eb1862e27f872606ee1a2fed6ab638f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 13:21:50 +0100
Subject: drm/i915: Dump the ringbuffer of the active request for debugging

Sometimes we need to see what instructions we emitted for a request to
try and gather a glimmer of insight into what the GPU is doing when it
stops responding.

v2: Move ring dumping into its own routine

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614122150.17552-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 41 +++++++++++++++++++++++++++++-----
 1 file changed, 36 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index d278fed8cb31..0ffce14ab08d 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1394,6 +1394,39 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 	}
 }
 
+static void print_request_ring(struct drm_printer *m, struct i915_request *rq)
+{
+	void *ring;
+	int size;
+
+	drm_printf(m,
+		   "[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]:\n",
+		   rq->head, rq->postfix, rq->tail,
+		   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
+		   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+
+	size = rq->tail - rq->head;
+	if (rq->tail < rq->head)
+		size += rq->ring->size;
+
+	ring = kmalloc(size, GFP_ATOMIC);
+	if (ring) {
+		const void *vaddr = rq->ring->vaddr;
+		unsigned int head = rq->head;
+		unsigned int len = 0;
+
+		if (rq->tail < head) {
+			len = rq->ring->size - head;
+			memcpy(ring, vaddr + head, len);
+			head = 0;
+		}
+		memcpy(ring + len, vaddr + head, size - len);
+
+		hexdump(m, ring, size);
+		kfree(ring);
+	}
+}
+
 void intel_engine_dump(struct intel_engine_cs *engine,
 		       struct drm_printer *m,
 		       const char *header, ...)
@@ -1444,11 +1477,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	rq = i915_gem_find_active_request(engine);
 	if (rq) {
 		print_request(m, rq, "\t\tactive ");
-		drm_printf(m,
-			   "\t\t[head %04x, postfix %04x, tail %04x, batch 0x%08x_%08x]\n",
-			   rq->head, rq->postfix, rq->tail,
-			   rq->batch ? upper_32_bits(rq->batch->node.start) : ~0u,
-			   rq->batch ? lower_32_bits(rq->batch->node.start) : ~0u);
+
 		drm_printf(m, "\t\tring->start:  0x%08x\n",
 			   i915_ggtt_offset(rq->ring->vma));
 		drm_printf(m, "\t\tring->head:   0x%08x\n",
@@ -1459,6 +1488,8 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 			   rq->ring->emit);
 		drm_printf(m, "\t\tring->space:  0x%08x\n",
 			   rq->ring->space);
+
+		print_request_ring(m, rq);
 	}
 
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 286e615356000ae51fac0e497247543724414d52 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 10:41:01 +0100
Subject: drm/i915: Make the hexdump row offset visually distinct

Currently we use %08x for the row offset, and %08x for the binary
contents of the buffer. This makes it very easily to confuse the two, so
switch to using [%04x] for the start-of-row offset.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614094103.18025-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 0ffce14ab08d..8b3d7aa3dfde 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1258,7 +1258,7 @@ static void hexdump(struct drm_printer *m, const void *buf, size_t len)
 						rowsize, sizeof(u32),
 						line, sizeof(line),
 						false) >= sizeof(line));
-		drm_printf(m, "%08zx %s\n", pos, line);
+		drm_printf(m, "[%04zx] %s\n", pos, line);
 
 		prev = buf + pos;
 		skip = false;
-- 
cgit v1.2.3


From e62230deeeae1f096a4be2360204536caf9ad8b6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 10:41:02 +0100
Subject: drm/i915: Show CCID in engine dumps

For debugging context issues, knowing what context the GPU is
loading/using is helpful.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614094103.18025-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 8b3d7aa3dfde..13bb8c7d2621 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1273,6 +1273,8 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		&engine->execlists;
 	u64 addr;
 
+	if (engine->id == RCS && IS_GEN(dev_priv, 4, 7))
+		drm_printf(m, "\tCCID: 0x%08x\n", I915_READ(CCID));
 	drm_printf(m, "\tRING_START: 0x%08x\n",
 		   I915_READ(RING_START(engine->mmio_base)));
 	drm_printf(m, "\tRING_HEAD:  0x%08x\n",
-- 
cgit v1.2.3


From a2bbf714834288da0ed4668d4e4d895ffef73de2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 10:41:03 +0100
Subject: drm/i915/gtt: Only keep gen6 page directories pinned while active

In order to be able to evict the gen6 ppgtt, we have to unpin it at some
point. We can simply use our context activity tracking to know when the
ppgtt is no longer in use by hardware, and so only keep it pinned while
being used a request.

For the kernel_context (and thus aliasing_ppgtt), it remains pinned at
all times, as the kernel_context itself is pinned at all times.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614094103.18025-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c     | 36 +++++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_gem_gtt.h     |  5 +++++
 drivers/gpu/drm/i915/intel_ringbuffer.c | 28 +++++++++++++++++++++++++
 3 files changed, 54 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 267f1f97b9f0..0ee9e154359f 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1912,7 +1912,6 @@ static void gen6_ppgtt_cleanup(struct i915_address_space *vm)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 
-	i915_vma_unpin(ppgtt->vma);
 	i915_vma_destroy(ppgtt->vma);
 
 	gen6_ppgtt_free_pd(ppgtt);
@@ -1998,10 +1997,19 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	return vma;
 }
 
-static int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
+int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
 
+	/*
+	 * Workaround the limited maximum vma->pin_count and the aliasing_ppgtt
+	 * which will be pinned into every active context.
+	 * (When vma->pin_count becomes atomic, I expect we will naturally
+	 * need a larger, unpacked, type and kill this redundancy.)
+	 */
+	if (ppgtt->pin_count++)
+		return 0;
+
 	/*
 	 * PPGTT PDEs reside in the GGTT and consists of 512 entries. The
 	 * allocator works in address space sizes, so it's multiplied by page
@@ -2012,6 +2020,17 @@ static int gen6_ppgtt_pin(struct i915_hw_ppgtt *base)
 			    PIN_GLOBAL | PIN_HIGH);
 }
 
+void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base)
+{
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
+
+	GEM_BUG_ON(!ppgtt->pin_count);
+	if (--ppgtt->pin_count)
+		return;
+
+	i915_vma_unpin(ppgtt->vma);
+}
+
 static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 {
 	struct i915_ggtt * const ggtt = &i915->ggtt;
@@ -2053,21 +2072,8 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	if (err)
 		goto err_vma;
 
-	err = gen6_ppgtt_pin(&ppgtt->base);
-	if (err)
-		goto err_pd;
-
-	DRM_DEBUG_DRIVER("Allocated pde space (%lldM) at GTT entry: %llx\n",
-			 ppgtt->vma->node.size >> 20,
-			 ppgtt->vma->node.start / PAGE_SIZE);
-
-	DRM_DEBUG_DRIVER("Adding PPGTT at offset %x\n",
-			 ppgtt->base.pd.base.ggtt_offset << 10);
-
 	return &ppgtt->base;
 
-err_pd:
-	gen6_ppgtt_free_pd(ppgtt);
 err_vma:
 	i915_vma_destroy(ppgtt->vma);
 err_scratch:
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 6e9acd99ecc6..d7b7b4afe060 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -412,6 +412,8 @@ struct gen6_hw_ppgtt {
 
 	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
+
+	unsigned int pin_count;
 };
 
 #define __to_gen6_ppgtt(base) container_of(base, struct gen6_hw_ppgtt, base)
@@ -625,6 +627,9 @@ static inline void i915_ppgtt_put(struct i915_hw_ppgtt *ppgtt)
 		kref_put(&ppgtt->ref, i915_ppgtt_release);
 }
 
+int gen6_ppgtt_pin(struct i915_hw_ppgtt *base);
+void gen6_ppgtt_unpin(struct i915_hw_ppgtt *base);
+
 void i915_check_and_clear_faults(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_gtt_mappings(struct drm_i915_private *dev_priv);
 void i915_gem_restore_gtt_mappings(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 735622dc73ec..6a937a896651 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1179,6 +1179,27 @@ static void intel_ring_context_destroy(struct intel_context *ce)
 		__i915_gem_object_release_unless_active(ce->state->obj);
 }
 
+static int __context_pin_ppgtt(struct i915_gem_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt;
+	int err = 0;
+
+	ppgtt = ctx->ppgtt ?: ctx->i915->mm.aliasing_ppgtt;
+	if (ppgtt)
+		err = gen6_ppgtt_pin(ppgtt);
+
+	return err;
+}
+
+static void __context_unpin_ppgtt(struct i915_gem_context *ctx)
+{
+	struct i915_hw_ppgtt *ppgtt;
+
+	ppgtt = ctx->ppgtt ?: ctx->i915->mm.aliasing_ppgtt;
+	if (ppgtt)
+		gen6_ppgtt_unpin(ppgtt);
+}
+
 static int __context_pin(struct intel_context *ce)
 {
 	struct i915_vma *vma;
@@ -1227,6 +1248,7 @@ static void __context_unpin(struct intel_context *ce)
 
 static void intel_ring_context_unpin(struct intel_context *ce)
 {
+	__context_unpin_ppgtt(ce->gem_context);
 	__context_unpin(ce);
 
 	i915_gem_context_put(ce->gem_context);
@@ -1324,6 +1346,10 @@ __ring_context_pin(struct intel_engine_cs *engine,
 	if (err)
 		goto err;
 
+	err = __context_pin_ppgtt(ce->gem_context);
+	if (err)
+		goto err_unpin;
+
 	i915_gem_context_get(ctx);
 
 	/* One ringbuffer to rule them all */
@@ -1332,6 +1358,8 @@ __ring_context_pin(struct intel_engine_cs *engine,
 
 	return ce;
 
+err_unpin:
+	__context_unpin(ce);
 err:
 	ce->pin_count = 0;
 	return ERR_PTR(err);
-- 
cgit v1.2.3


From 38441fb6fcbb97817dff5c012609860a2b39c3e9 Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Tue, 2 Jan 2018 16:51:01 -0800
Subject: ath10k: support use of channel 173

The India regulatory domain allows CH 173, so add that to the
available channel list.  I verified basic connectivity between
a 9880 and 9984 NIC.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.h | 3 ++-
 drivers/net/wireless/ath/ath10k/mac.c  | 3 +++
 drivers/net/wireless/ath/ath10k/wmi.c  | 2 +-
 3 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 951dbdd1c9eb..427ee5752bb0 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -48,7 +48,8 @@
 #define WMI_READY_TIMEOUT (5 * HZ)
 #define ATH10K_FLUSH_TIMEOUT_HZ (5 * HZ)
 #define ATH10K_CONNECTION_LOSS_HZ (3 * HZ)
-#define ATH10K_NUM_CHANS 40
+#define ATH10K_NUM_CHANS 41
+#define ATH10K_MAX_5G_CHAN 173
 
 /* Antenna noise floor */
 #define ATH10K_DEFAULT_NOISE_FLOOR -95
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index e9c2fb318c03..f31ae3be4778 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -7858,6 +7858,9 @@ static const struct ieee80211_channel ath10k_5ghz_channels[] = {
 	CHAN5G(161, 5805, 0),
 	CHAN5G(165, 5825, 0),
 	CHAN5G(169, 5845, 0),
+	CHAN5G(173, 5865, 0),
+	/* If you add more, you may need to change ATH10K_MAX_5G_CHAN */
+	/* And you will definitely need to change ATH10K_NUM_CHANS in core.h */
 };
 
 struct ath10k *ath10k_mac_create(size_t priv_size)
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 2319f79b34f0..be841cbf8099 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2366,7 +2366,7 @@ int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb)
 	 */
 	if (channel >= 1 && channel <= 14) {
 		status->band = NL80211_BAND_2GHZ;
-	} else if (channel >= 36 && channel <= 169) {
+	} else if (channel >= 36 && channel <= ATH10K_MAX_5G_CHAN) {
 		status->band = NL80211_BAND_5GHZ;
 	} else {
 		/* Shouldn't happen unless list of advertised channels to
-- 
cgit v1.2.3


From 2e9bcd0d73243f5e49daf92508d64cc33c30da01 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <periyasa@codeaurora.org>
Date: Tue, 29 May 2018 17:01:13 +0530
Subject: ath10k: fix spectral scan for QCA9984 and QCA9888 chipsets

The spectral scan has been always broken on QCA9984 and QCA9888.

Introduce a hardware parameter 'spectral_bin_offset' to resolve this issue for
QCA9984 and QCA9888 chipsets. For other chipsets, the hardware parameter
'spectral_bin_offset' is zero so that existing behaviour is retained as it is.

In QCA9984 and QCA9888 chipsets, hardware param value 'spectral_bin_discard'
is 12 bytes. This 12 bytes is derived as the sum of segment index (4 bytes),
extra bins before the actual data (4 bytes) and extra bins after the actual
data (4 bytes). Always discarding (12 bytes) happens at end of the samples and
incorrect samples got dumped, so that user can find incorrect arrangement
samples in spectral scan dump.

To fix this issue, we have to discard first 8 bytes and last 4 bytes in every
samples, so totally 12 bytes are discarded. In every sample we need to consider
the offset while taking the actual spectral data. For QCA9984, QCA9888 the
offset is 8 bytes (segment index + extra bins before actual data).

Hardware tested: QCA9984 and QCA9888
Firmware tested: 10.4-3.5.3-00053

Signed-off-by: Karthikeyan Periyasamy <periyasa@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c     | 13 +++++++++++++
 drivers/net/wireless/ath/ath10k/hw.h       |  3 +++
 drivers/net/wireless/ath/ath10k/spectral.c |  2 +-
 3 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 4cf54a7ef09a..25ecf7402984 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -82,6 +82,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -113,6 +114,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -145,6 +147,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -176,6 +179,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -207,6 +211,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -238,6 +243,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -272,6 +278,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.target_cpu_freq = 176000000,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -309,6 +316,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 4,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 11,
@@ -347,6 +355,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 12,
+		.spectral_bin_offset = 8,
 
 		/* Can do only 2x2 VHT160 or 80+80. 1560Mbps is 4x4 80Mhz
 		 * or 2x2 160Mhz, long-guard-interval.
@@ -388,6 +397,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 12,
+		.spectral_bin_offset = 8,
 
 		/* Can do only 1x1 VHT160 or 80+80. 780Mbps is 2x2 80Mhz or
 		 * 1x1 160Mhz, long-guard-interval.
@@ -423,6 +433,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca988x_ops,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -456,6 +467,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.target_cpu_freq = 176000000,
 		.decap_align_bytes = 4,
 		.spectral_bin_discard = 0,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 8,
@@ -494,6 +506,7 @@ static const struct ath10k_hw_params ath10k_hw_params_list[] = {
 		.hw_ops = &qca99x0_ops,
 		.decap_align_bytes = 1,
 		.spectral_bin_discard = 4,
+		.spectral_bin_offset = 0,
 		.vht160_mcs_rx_highest = 0,
 		.vht160_mcs_tx_highest = 0,
 		.n_cipher_suites = 11,
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index 23467e9fefeb..a274bd809a08 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -586,6 +586,9 @@ struct ath10k_hw_params {
 
 	/* target supporting retention restore on ddr */
 	bool rri_on_ddr;
+
+	/* Number of bytes to be the offset for each FFT sample */
+	int spectral_bin_offset;
 };
 
 struct htt_rx_desc;
diff --git a/drivers/net/wireless/ath/ath10k/spectral.c b/drivers/net/wireless/ath/ath10k/spectral.c
index af6995de7e00..653b6d013207 100644
--- a/drivers/net/wireless/ath/ath10k/spectral.c
+++ b/drivers/net/wireless/ath/ath10k/spectral.c
@@ -145,7 +145,7 @@ int ath10k_spectral_process_fft(struct ath10k *ar,
 	fft_sample->noise = __cpu_to_be16(phyerr->nf_chains[chain_idx]);
 
 	bins = (u8 *)fftr;
-	bins += sizeof(*fftr);
+	bins += sizeof(*fftr) + ar->hw_params.spectral_bin_offset;
 
 	fft_sample->tsf = __cpu_to_be64(tsf);
 
-- 
cgit v1.2.3


From 6ee0e175a33deea08354bc8a91b743f0ec8c8a0a Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Thu, 31 May 2018 02:33:14 +0000
Subject: ath10k: make some functions static

Fixes the following sparse warnings:

drivers/net/wireless/ath/ath10k/snoc.c:823:5: warning:
 symbol 'ath10k_snoc_get_ce_id_from_irq' was not declared. Should it be static?
drivers/net/wireless/ath/ath10k/snoc.c:871:6: warning:
 symbol 'ath10k_snoc_init_napi' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index a3a7042fe13a..92ddb1c38c06 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -820,7 +820,7 @@ static const struct ath10k_bus_ops ath10k_snoc_bus_ops = {
 	.write32	= ath10k_snoc_write32,
 };
 
-int ath10k_snoc_get_ce_id_from_irq(struct ath10k *ar, int irq)
+static int ath10k_snoc_get_ce_id_from_irq(struct ath10k *ar, int irq)
 {
 	struct ath10k_snoc *ar_snoc = ath10k_snoc_priv(ar);
 	int i;
@@ -868,7 +868,7 @@ static int ath10k_snoc_napi_poll(struct napi_struct *ctx, int budget)
 	return done;
 }
 
-void ath10k_snoc_init_napi(struct ath10k *ar)
+static void ath10k_snoc_init_napi(struct ath10k *ar)
 {
 	netif_napi_add(&ar->napi_dev, &ar->napi, ath10k_snoc_napi_poll,
 		       ATH10K_NAPI_BUDGET);
-- 
cgit v1.2.3


From 5a211627004e2cddd0ab8b9df19e5fb0bbe97634 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 1 Jun 2018 19:25:48 +0800
Subject: ath10k: fix incorrect size of dma_free_coherent in
 ath10k_ce_alloc_src_ring_64

sizeof(struct ce_desc) should be a copy-paste mistake
just use sizeof(struct ce_desc_64) to avoid mem leak

Fixes: b7ba83f7c414 ("ath10k: add support for shadow register for WNC3990")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/ce.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/ce.c b/drivers/net/wireless/ath/ath10k/ce.c
index 3b96a43fbda4..18c709c484e7 100644
--- a/drivers/net/wireless/ath/ath10k/ce.c
+++ b/drivers/net/wireless/ath/ath10k/ce.c
@@ -1512,7 +1512,7 @@ ath10k_ce_alloc_src_ring_64(struct ath10k *ar, unsigned int ce_id,
 		ret = ath10k_ce_alloc_shadow_base(ar, src_ring, nentries);
 		if (ret) {
 			dma_free_coherent(ar->dev,
-					  (nentries * sizeof(struct ce_desc) +
+					  (nentries * sizeof(struct ce_desc_64) +
 					   CE_DESC_RING_ALIGN),
 					  src_ring->base_addr_owner_space_unaligned,
 					  base_addr);
-- 
cgit v1.2.3


From 9fb31b66b91ff4e6c38fa0a10e517f4282e380e7 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 4 Jun 2018 20:35:42 +0800
Subject: ath10k: use dma_zalloc_coherent instead of allocator/memset

Use dma_zalloc_coherent instead of dma_alloc_coherent
followed by memset 0.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index be841cbf8099..877249ac6fd4 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -5018,13 +5018,11 @@ static int ath10k_wmi_alloc_chunk(struct ath10k *ar, u32 req_id,
 	void *vaddr;
 
 	pool_size = num_units * round_up(unit_len, 4);
-	vaddr = dma_alloc_coherent(ar->dev, pool_size, &paddr, GFP_KERNEL);
+	vaddr = dma_zalloc_coherent(ar->dev, pool_size, &paddr, GFP_KERNEL);
 
 	if (!vaddr)
 		return -ENOMEM;
 
-	memset(vaddr, 0, pool_size);
-
 	ar->wmi.mem_chunks[idx].vaddr = vaddr;
 	ar->wmi.mem_chunks[idx].paddr = paddr;
 	ar->wmi.mem_chunks[idx].len = pool_size;
-- 
cgit v1.2.3


From 7f8f72d8511a7f57595ce166cd9fc7da94a8faf4 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 11 Jun 2018 11:19:35 -0700
Subject: ath10k: use crash_dump enum instead of magic numbers

The comments are telling you what the enum could tell you instead.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 25ecf7402984..983eb6a1aa95 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -41,10 +41,8 @@ static bool uart_print;
 static bool skip_otp;
 static bool rawmode;
 
-/* Enable ATH10K_FW_CRASH_DUMP_REGISTERS and ATH10K_FW_CRASH_DUMP_CE_DATA
- * by default.
- */
-unsigned long ath10k_coredump_mask = 0x3;
+unsigned long ath10k_coredump_mask = BIT(ATH10K_FW_CRASH_DUMP_REGISTERS) |
+				     BIT(ATH10K_FW_CRASH_DUMP_CE_DATA);
 
 /* FIXME: most of these should be readonly */
 module_param_named(debug_mask, ath10k_debug_mask, uint, 0644);
-- 
cgit v1.2.3


From 0644fef97451908ef1048043b0a60d1324d8a522 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 11 Jun 2018 12:35:40 -0700
Subject: ath10k: snoc: use module_platform_driver() macro

ath10k_snoc_init()/ath10k_snoc_exit() don't add much value;
module_platform_driver() can remove the boilerplate.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 20 +-------------------
 1 file changed, 1 insertion(+), 19 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 92ddb1c38c06..31d1e3af85a2 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1388,25 +1388,7 @@ static struct platform_driver ath10k_snoc_driver = {
 			.of_match_table = ath10k_snoc_dt_match,
 		},
 };
-
-static int __init ath10k_snoc_init(void)
-{
-	int ret;
-
-	ret = platform_driver_register(&ath10k_snoc_driver);
-	if (ret)
-		pr_err("failed to register ath10k snoc driver: %d\n",
-		       ret);
-
-	return ret;
-}
-module_init(ath10k_snoc_init);
-
-static void __exit ath10k_snoc_exit(void)
-{
-	platform_driver_unregister(&ath10k_snoc_driver);
-}
-module_exit(ath10k_snoc_exit);
+module_platform_driver(ath10k_snoc_driver);
 
 MODULE_AUTHOR("Qualcomm");
 MODULE_LICENSE("Dual BSD/GPL");
-- 
cgit v1.2.3


From 426a0f0b5a2fe1df3496ba299ee3521159dba302 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 11 Jun 2018 14:09:43 -0700
Subject: ath10k: snoc: use correct bus-specific pointer in RX retry

We're 'ath10k_snoc', not 'ath10k_pci'. This probably means we're
accessing junk data in ath10k_snoc_rx_replenish_retry(), unless
'ath10k_snoc' and 'ath10k_pci' happen to have very similar struct
layouts.

Noticed by inspection.

Fixes: d915105231ca ("ath10k: add hif rx methods for wcn3990")
Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 31d1e3af85a2..42aa1d57a485 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -449,7 +449,7 @@ static void ath10k_snoc_htt_rx_cb(struct ath10k_ce_pipe *ce_state)
 
 static void ath10k_snoc_rx_replenish_retry(struct timer_list *t)
 {
-	struct ath10k_pci *ar_snoc = from_timer(ar_snoc, t, rx_post_retry);
+	struct ath10k_snoc *ar_snoc = from_timer(ar_snoc, t, rx_post_retry);
 	struct ath10k *ar = ar_snoc->ar;
 
 	ath10k_snoc_rx_post(ar);
-- 
cgit v1.2.3


From 8ac5fe8e3d110eaff47dd2becf98b08762c84c75 Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 11 Jun 2018 14:09:44 -0700
Subject: ath10k: snoc: stop including pci.h

It's easier to violate abstractions and introduce bugs when snoc.h is
including pci.h. Let's not do that.

I'm not extremely familiar with this driver yet, but several of the
shared PCI/SNOC bits seem to be related to the Copy Engine, so move them
to ce.h.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/ce.h   | 42 ++++++++++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath10k/pci.h  | 42 ----------------------------------
 drivers/net/wireless/ath/ath10k/snoc.h |  1 -
 3 files changed, 42 insertions(+), 43 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/ce.h b/drivers/net/wireless/ath/ath10k/ce.h
index dbeffaef6024..b8fb5382dede 100644
--- a/drivers/net/wireless/ath/ath10k/ce.h
+++ b/drivers/net/wireless/ath/ath10k/ce.h
@@ -383,4 +383,46 @@ static inline u32 ath10k_ce_interrupt_summary(struct ath10k *ar)
 		return CE_INTERRUPT_SUMMARY;
 }
 
+/* Host software's Copy Engine configuration. */
+#define CE_ATTR_FLAGS 0
+
+/*
+ * Configuration information for a Copy Engine pipe.
+ * Passed from Host to Target during startup (one per CE).
+ *
+ * NOTE: Structure is shared between Host software and Target firmware!
+ */
+struct ce_pipe_config {
+	__le32 pipenum;
+	__le32 pipedir;
+	__le32 nentries;
+	__le32 nbytes_max;
+	__le32 flags;
+	__le32 reserved;
+};
+
+/*
+ * Directions for interconnect pipe configuration.
+ * These definitions may be used during configuration and are shared
+ * between Host and Target.
+ *
+ * Pipe Directions are relative to the Host, so PIPEDIR_IN means
+ * "coming IN over air through Target to Host" as with a WiFi Rx operation.
+ * Conversely, PIPEDIR_OUT means "going OUT from Host through Target over air"
+ * as with a WiFi Tx operation. This is somewhat awkward for the "middle-man"
+ * Target since things that are "PIPEDIR_OUT" are coming IN to the Target
+ * over the interconnect.
+ */
+#define PIPEDIR_NONE    0
+#define PIPEDIR_IN      1  /* Target-->Host, WiFi Rx direction */
+#define PIPEDIR_OUT     2  /* Host->Target, WiFi Tx direction */
+#define PIPEDIR_INOUT   3  /* bidirectional */
+
+/* Establish a mapping between a service/direction and a pipe. */
+struct service_to_pipe {
+	__le32 service_id;
+	__le32 pipedir;
+	__le32 pipenum;
+};
+
 #endif /* _CE_H_ */
diff --git a/drivers/net/wireless/ath/ath10k/pci.h b/drivers/net/wireless/ath/ath10k/pci.h
index e52fd83156b6..0ed436657108 100644
--- a/drivers/net/wireless/ath/ath10k/pci.h
+++ b/drivers/net/wireless/ath/ath10k/pci.h
@@ -86,48 +86,6 @@ struct pcie_state {
 /* PCIE_CONFIG_FLAG definitions */
 #define PCIE_CONFIG_FLAG_ENABLE_L1  0x0000001
 
-/* Host software's Copy Engine configuration. */
-#define CE_ATTR_FLAGS 0
-
-/*
- * Configuration information for a Copy Engine pipe.
- * Passed from Host to Target during startup (one per CE).
- *
- * NOTE: Structure is shared between Host software and Target firmware!
- */
-struct ce_pipe_config {
-	__le32 pipenum;
-	__le32 pipedir;
-	__le32 nentries;
-	__le32 nbytes_max;
-	__le32 flags;
-	__le32 reserved;
-};
-
-/*
- * Directions for interconnect pipe configuration.
- * These definitions may be used during configuration and are shared
- * between Host and Target.
- *
- * Pipe Directions are relative to the Host, so PIPEDIR_IN means
- * "coming IN over air through Target to Host" as with a WiFi Rx operation.
- * Conversely, PIPEDIR_OUT means "going OUT from Host through Target over air"
- * as with a WiFi Tx operation. This is somewhat awkward for the "middle-man"
- * Target since things that are "PIPEDIR_OUT" are coming IN to the Target
- * over the interconnect.
- */
-#define PIPEDIR_NONE    0
-#define PIPEDIR_IN      1  /* Target-->Host, WiFi Rx direction */
-#define PIPEDIR_OUT     2  /* Host->Target, WiFi Tx direction */
-#define PIPEDIR_INOUT   3  /* bidirectional */
-
-/* Establish a mapping between a service/direction and a pipe. */
-struct service_to_pipe {
-	__le32 service_id;
-	__le32 pipedir;
-	__le32 pipenum;
-};
-
 /* Per-pipe state. */
 struct ath10k_pci_pipe {
 	/* Handle of underlying Copy Engine */
diff --git a/drivers/net/wireless/ath/ath10k/snoc.h b/drivers/net/wireless/ath/ath10k/snoc.h
index 05dc98f46ccd..f9e530189d48 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.h
+++ b/drivers/net/wireless/ath/ath10k/snoc.h
@@ -19,7 +19,6 @@
 
 #include "hw.h"
 #include "ce.h"
-#include "pci.h"
 
 struct ath10k_snoc_drv_priv {
 	enum ath10k_hw_rev hw_rev;
-- 
cgit v1.2.3


From 13e6cc0bd4effa9fc4b03fb9b1baf0e26e2e217d Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 11 Jun 2018 14:09:45 -0700
Subject: ath10k: snoc: drop unused WCN3990_CE_ATTR_FLAGS

We started using a common CE_ATTR_FLAGS definition, so drop this one.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 42aa1d57a485..ece002c13035 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -26,7 +26,7 @@
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/clk.h>
-#define  WCN3990_CE_ATTR_FLAGS 0
+
 #define ATH10K_SNOC_RX_POST_RETRY_MS 50
 #define CE_POLL_PIPE 4
 
-- 
cgit v1.2.3


From c9f3e7fa8bcb63a52531bf7e02bf53e0d177f3dc Mon Sep 17 00:00:00 2001
From: Brian Norris <briannorris@chromium.org>
Date: Mon, 11 Jun 2018 14:09:46 -0700
Subject: ath10k: snoc: sort include files

Sort these alphabetically, with local includes in a separate section.

Signed-off-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index ece002c13035..f3db08d98810 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -14,18 +14,19 @@
  * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
  */
 
-#include <linux/module.h>
+#include <linux/clk.h>
 #include <linux/kernel.h>
-#include "debug.h"
-#include "hif.h"
-#include "htc.h"
-#include "ce.h"
-#include "snoc.h"
+#include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
-#include <linux/clk.h>
+
+#include "ce.h"
+#include "debug.h"
+#include "hif.h"
+#include "htc.h"
+#include "snoc.h"
 
 #define ATH10K_SNOC_RX_POST_RETRY_MS 50
 #define CE_POLL_PIPE 4
-- 
cgit v1.2.3


From 50c51f394e685c450276e1ae5b91405ad55d8570 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Tue, 12 Jun 2018 13:39:05 +0200
Subject: ath10k: do not mix spaces and tabs in Kconfig

Do not mix spaces and tabs in Kconfig.

Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/Kconfig | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/Kconfig b/drivers/net/wireless/ath/ath10k/Kconfig
index 84f071ac0d84..54ff5930126c 100644
--- a/drivers/net/wireless/ath/ath10k/Kconfig
+++ b/drivers/net/wireless/ath/ath10k/Kconfig
@@ -1,15 +1,15 @@
 config ATH10K
-        tristate "Atheros 802.11ac wireless cards support"
-        depends on MAC80211 && HAS_DMA
+	tristate "Atheros 802.11ac wireless cards support"
+	depends on MAC80211 && HAS_DMA
 	select ATH_COMMON
 	select CRC32
 	select WANT_DEV_COREDUMP
 	select ATH10K_CE
-        ---help---
-          This module adds support for wireless adapters based on
-          Atheros IEEE 802.11ac family of chipsets.
+	---help---
+	  This module adds support for wireless adapters based on
+	  Atheros IEEE 802.11ac family of chipsets.
 
-          If you choose to build a module, it'll be called ath10k.
+	  If you choose to build a module, it'll be called ath10k.
 
 config ATH10K_CE
 	bool
@@ -41,12 +41,12 @@ config ATH10K_USB
 	  work in progress and will not fully work.
 
 config ATH10K_SNOC
-        tristate "Qualcomm ath10k SNOC support (EXPERIMENTAL)"
-        depends on ATH10K && ARCH_QCOM
-        ---help---
-          This module adds support for integrated WCN3990 chip connected
-          to system NOC(SNOC). Currently work in progress and will not
-          fully work.
+	tristate "Qualcomm ath10k SNOC support (EXPERIMENTAL)"
+	depends on ATH10K && ARCH_QCOM
+	---help---
+	  This module adds support for integrated WCN3990 chip connected
+	  to system NOC(SNOC). Currently work in progress and will not
+	  fully work.
 
 config ATH10K_DEBUG
 	bool "Atheros ath10k debugging"
-- 
cgit v1.2.3


From 5db98aee93cd1ba5b94b1a9bc9057c98e2a36fd6 Mon Sep 17 00:00:00 2001
From: Surabhi Vishnoi <svishnoi@codeaurora.org>
Date: Wed, 13 Jun 2018 10:33:35 +0530
Subject: ath10k: skip data calibration for non-bmi target

In non-bmi target ex. WCN3990, data calibration
is handled via QMI.

Skip data calibration in debug routine to enable ath10k
debugfs for non bmi targets.

Signed-off-by: Surabhi Vishnoi <svishnoi@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/debug.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 0d98c93a3aba..4926722e0c0d 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -1727,7 +1727,9 @@ int ath10k_debug_start(struct ath10k *ar)
 			ath10k_warn(ar, "failed to disable pktlog: %d\n", ret);
 	}
 
-	if (ar->debug.nf_cal_period) {
+	if (ar->debug.nf_cal_period &&
+	    !test_bit(ATH10K_FW_FEATURE_NON_BMI,
+		      ar->normal_mode_fw.fw_file.fw_features)) {
 		ret = ath10k_wmi_pdev_set_param(ar,
 						ar->wmi.pdev_param->cal_period,
 						ar->debug.nf_cal_period);
@@ -1744,7 +1746,9 @@ void ath10k_debug_stop(struct ath10k *ar)
 {
 	lockdep_assert_held(&ar->conf_mutex);
 
-	ath10k_debug_cal_data_fetch(ar);
+	if (!test_bit(ATH10K_FW_FEATURE_NON_BMI,
+		      ar->normal_mode_fw.fw_file.fw_features))
+		ath10k_debug_cal_data_fetch(ar);
 
 	/* Must not use _sync to avoid deadlock, we do that in
 	 * ath10k_debug_destroy(). The check for htt_stats_mask is to avoid
@@ -2367,15 +2371,18 @@ int ath10k_debug_register(struct ath10k *ar)
 	debugfs_create_file("fw_dbglog", 0600, ar->debug.debugfs_phy, ar,
 			    &fops_fw_dbglog);
 
-	debugfs_create_file("cal_data", 0400, ar->debug.debugfs_phy, ar,
-			    &fops_cal_data);
+	if (!test_bit(ATH10K_FW_FEATURE_NON_BMI,
+		      ar->normal_mode_fw.fw_file.fw_features)) {
+		debugfs_create_file("cal_data", 0400, ar->debug.debugfs_phy, ar,
+				    &fops_cal_data);
+
+		debugfs_create_file("nf_cal_period", 0600, ar->debug.debugfs_phy, ar,
+				    &fops_nf_cal_period);
+	}
 
 	debugfs_create_file("ani_enable", 0600, ar->debug.debugfs_phy, ar,
 			    &fops_ani_enable);
 
-	debugfs_create_file("nf_cal_period", 0600, ar->debug.debugfs_phy, ar,
-			    &fops_nf_cal_period);
-
 	if (IS_ENABLED(CONFIG_ATH10K_DFS_CERTIFIED)) {
 		debugfs_create_file("dfs_simulate_radar", 0200, ar->debug.debugfs_phy,
 				    ar, &fops_simulate_radar);
-- 
cgit v1.2.3


From d16a7ab20ac9861979c83d7fce8f5edc48daada6 Mon Sep 17 00:00:00 2001
From: Govind Singh <govinds@codeaurora.org>
Date: Wed, 13 Jun 2018 12:18:06 +0530
Subject: ath10k: handle resource init failure case

Return type of resource init method is not assigned.
Handle resource init failures for graceful exit.

Signed-off-by: Govind Singh <govinds@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/snoc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index f3db08d98810..fa1843a7e0fd 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -1304,13 +1304,13 @@ static int ath10k_snoc_probe(struct platform_device *pdev)
 	ar_snoc->ce.bus_ops = &ath10k_snoc_bus_ops;
 	ar->ce_priv = &ar_snoc->ce;
 
-	ath10k_snoc_resource_init(ar);
+	ret = ath10k_snoc_resource_init(ar);
 	if (ret) {
 		ath10k_warn(ar, "failed to initialize resource: %d\n", ret);
 		goto err_core_destroy;
 	}
 
-	ath10k_snoc_setup_resource(ar);
+	ret = ath10k_snoc_setup_resource(ar);
 	if (ret) {
 		ath10k_warn(ar, "failed to setup resource: %d\n", ret);
 		goto err_core_destroy;
-- 
cgit v1.2.3


From d5e5f6855aab87dd54ff3a33c6a3ccdc9f97fbcc Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 30 May 2018 10:25:03 +0100
Subject: ath9k: debug: fix spelling mistake "WATHDOG" -> "WATCHDOG"

Trivial fix to spelling mistake in PR_IS message text.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
index f685843a2ff3..0a6eb8a8c1ed 100644
--- a/drivers/net/wireless/ath/ath9k/debug.c
+++ b/drivers/net/wireless/ath/ath9k/debug.c
@@ -538,7 +538,7 @@ static int read_file_interrupt(struct seq_file *file, void *data)
 	if (sc->sc_ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) {
 		PR_IS("RXLP", rxlp);
 		PR_IS("RXHP", rxhp);
-		PR_IS("WATHDOG", bb_watchdog);
+		PR_IS("WATCHDOG", bb_watchdog);
 	} else {
 		PR_IS("RX", rxok);
 	}
-- 
cgit v1.2.3


From 5422b37c907e7c00a15d5298d6717c6f7ba1403f Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Wed, 13 Jun 2018 12:26:00 -0700
Subject: drm/i915/psr: Kill delays when activating psr back.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The immediate enabling was actually not an issue for the
HW perspective for core platforms that have HW tracking.
HW will wait few identical idle frames before transitioning
to actual psr active anyways.

Now that we removed VLV/CHV out of the picture completely
we can safely remove any delays.

Note that this patch also remove the delayed activation
on HSW and BDW introduced by commit 'd0ac896a477d
("drm/i915: Delay first PSR activation.")'. This was
introduced to fix a blank screen on VLV/CHV and also
masked some frozen screens on other core platforms.
Probably the same that we are now properly hunting and fixing.

v2:(DK): Remove unnecessary WARN_ONs and make some other
         VLV | CHV more readable.
v3: Do it regardless the timer rework.
v4: (DK/CI): Add VLV || CHV check on cancel work at psr_disable.
v5: Kill remaining items and fully rework activation functions.
v6: Rebase on top of VLV/CHV clean-up and keep the reactivation
    on a regular non-delayed work to avoid extra delays on exit
    calls and allow us to add few more safety checks before
    real activation.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613192600.3955-1-rodrigo.vivi@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c |  2 --
 drivers/gpu/drm/i915/i915_drv.h     |  2 +-
 drivers/gpu/drm/i915/intel_psr.c    | 29 +++++++----------------------
 3 files changed, 8 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 769ab9745834..948b973af067 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2660,8 +2660,6 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	seq_printf(m, "Enabled: %s\n", yesno((bool)dev_priv->psr.enabled));
 	seq_printf(m, "Busy frontbuffer bits: 0x%03x\n",
 		   dev_priv->psr.busy_frontbuffer_bits);
-	seq_printf(m, "Re-enable work scheduled: %s\n",
-		   yesno(work_busy(&dev_priv->psr.work.work)));
 
 	if (dev_priv->psr.psr2_enabled)
 		enabled = I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index be8c2f0823c4..19defe73b156 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -613,7 +613,7 @@ struct i915_psr {
 	bool sink_support;
 	struct intel_dp *enabled;
 	bool active;
-	struct delayed_work work;
+	struct work_struct work;
 	unsigned busy_frontbuffer_bits;
 	bool sink_psr2_support;
 	bool link_standby;
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 71dfe541740f..ef0f4741a95d 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -671,21 +671,7 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 	dev_priv->psr.enable_source(intel_dp, crtc_state);
 	dev_priv->psr.enabled = intel_dp;
 
-	if (INTEL_GEN(dev_priv) >= 9) {
-		intel_psr_activate(intel_dp);
-	} else {
-		/*
-		 * FIXME: Activation should happen immediately since this
-		 * function is just called after pipe is fully trained and
-		 * enabled.
-		 * However on some platforms we face issues when first
-		 * activation follows a modeset so quickly.
-		 *     - On HSW/BDW we get a recoverable frozen screen until
-		 *       next exit-activate sequence.
-		 */
-		schedule_delayed_work(&dev_priv->psr.work,
-				      msecs_to_jiffies(intel_dp->panel_power_cycle_delay * 5));
-	}
+	intel_psr_activate(intel_dp);
 
 unlock:
 	mutex_unlock(&dev_priv->psr.lock);
@@ -768,8 +754,6 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 
 	dev_priv->psr.enabled = NULL;
 	mutex_unlock(&dev_priv->psr.lock);
-
-	cancel_delayed_work_sync(&dev_priv->psr.work);
 }
 
 static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
@@ -805,10 +789,13 @@ static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
 static void intel_psr_work(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
-		container_of(work, typeof(*dev_priv), psr.work.work);
+		container_of(work, typeof(*dev_priv), psr.work);
 
 	mutex_lock(&dev_priv->psr.lock);
 
+	if (!dev_priv->psr.enabled)
+		goto unlock;
+
 	/*
 	 * We have to make sure PSR is ready for re-enable
 	 * otherwise it keeps disabled until next full enable/disable cycle.
@@ -949,9 +936,7 @@ void intel_psr_flush(struct drm_i915_private *dev_priv,
 	}
 
 	if (!dev_priv->psr.active && !dev_priv->psr.busy_frontbuffer_bits)
-		if (!work_busy(&dev_priv->psr.work.work))
-			schedule_delayed_work(&dev_priv->psr.work,
-					      msecs_to_jiffies(100));
+		schedule_work(&dev_priv->psr.work);
 	mutex_unlock(&dev_priv->psr.lock);
 }
 
@@ -998,7 +983,7 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 		dev_priv->psr.link_standby = false;
 	}
 
-	INIT_DELAYED_WORK(&dev_priv->psr.work, intel_psr_work);
+	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
 	mutex_init(&dev_priv->psr.lock);
 
 	dev_priv->psr.enable_source = hsw_psr_enable_source;
-- 
cgit v1.2.3


From 24a28179ecc0011e41a0fc8034a1a8e0fefbb406 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 13 Jun 2018 20:07:06 +0300
Subject: drm/i915/ddi: s/crtc->config/old_crtc_state in haswell_crtc_disable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

crtc->config points to the old crtc state at the point
display.crtc_disable() is called, so use the more descriptive pointer
instead.

v2:
- Convert one remaining instance of the ptr in the function. (Ville)

Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613170710.15080-2-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_display.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 3323470596ca..59dd97a939ce 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5814,7 +5814,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	struct drm_crtc *crtc = old_crtc_state->base.crtc;
 	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	enum transcoder cpu_transcoder = intel_crtc->config->cpu_transcoder;
+	enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
 
 	intel_encoders_disable(crtc, old_crtc_state, old_state);
 
@@ -5825,8 +5825,8 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_disable_pipe(old_crtc_state);
 
-	if (intel_crtc_has_type(intel_crtc->config, INTEL_OUTPUT_DP_MST))
-		intel_ddi_set_vc_payload_alloc(intel_crtc->config, false);
+	if (intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
+		intel_ddi_set_vc_payload_alloc(old_crtc_state, false);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
@@ -5837,7 +5837,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 		ironlake_pfit_disable(intel_crtc, false);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_pipe_clock(intel_crtc->config);
+		intel_ddi_disable_pipe_clock(old_crtc_state);
 
 	intel_encoders_post_disable(crtc, old_crtc_state, old_state);
 
-- 
cgit v1.2.3


From afb2c4437daeed2d0c49e246ad1ad4def5d913cd Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 13 Jun 2018 20:27:46 +0300
Subject: drm/i915/ddi: Push pipe clock enabling to encoders
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ICL the pipe clock needs to be enabled before setting the HDMI
infoframe, but these steps are in the reverse order atm. Move the pipe
clock enabling to the encoders, so reordering of the two steps can be
done in a clean way.

No functional change.

v2:
- Rebased on drm-tip.

Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613172746.18525-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_crt.c     | 4 ++++
 drivers/gpu/drm/i915/intel_ddi.c     | 8 ++++++++
 drivers/gpu/drm/i915/intel_display.c | 6 ------
 3 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 95aa29cf2d9c..87c72c39f409 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -232,6 +232,8 @@ static void hsw_post_disable_crt(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
+	intel_ddi_disable_pipe_clock(old_crtc_state);
+
 	pch_post_disable_crt(encoder, old_crtc_state, old_conn_state);
 
 	lpt_disable_pch_transcoder(dev_priv);
@@ -268,6 +270,8 @@ static void hsw_pre_enable_crt(struct intel_encoder *encoder,
 	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
 
 	dev_priv->display.fdi_link_train(crtc, crtc_state);
+
+	intel_ddi_enable_pipe_clock(crtc_state);
 }
 
 static void hsw_enable_crt(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index ca73387bd596..df0e64a9721a 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -2639,6 +2639,8 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 	intel_dp_start_link_train(intel_dp);
 	if (port != PORT_A || INTEL_GEN(dev_priv) >= 9)
 		intel_dp_stop_link_train(intel_dp);
+
+	intel_ddi_enable_pipe_clock(crtc_state);
 }
 
 static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
@@ -2672,6 +2674,8 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	intel_dig_port->set_infoframes(&encoder->base,
 				       crtc_state->has_infoframe,
 				       crtc_state, conn_state);
+
+	intel_ddi_enable_pipe_clock(crtc_state);
 }
 
 static void intel_ddi_pre_enable(struct intel_encoder *encoder,
@@ -2738,6 +2742,8 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	bool is_mst = intel_crtc_has_type(old_crtc_state,
 					  INTEL_OUTPUT_DP_MST);
 
+	intel_ddi_disable_pipe_clock(old_crtc_state);
+
 	/*
 	 * Power down sink before disabling the port, otherwise we end
 	 * up getting interrupts from the sink on detecting link loss.
@@ -2763,6 +2769,8 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
 	struct intel_hdmi *intel_hdmi = &dig_port->hdmi;
 
+	intel_ddi_disable_pipe_clock(old_crtc_state);
+
 	intel_disable_ddi_buf(encoder);
 
 	dig_port->set_infoframes(&encoder->base, false,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 59dd97a939ce..05abd23b526f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5647,9 +5647,6 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 
 	intel_encoders_pre_enable(crtc, pipe_config, old_state);
 
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_enable_pipe_clock(pipe_config);
-
 	if (intel_crtc_has_dp_encoder(intel_crtc->config))
 		intel_dp_set_m_n(intel_crtc, M1_N1);
 
@@ -5836,9 +5833,6 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 	else
 		ironlake_pfit_disable(intel_crtc, false);
 
-	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_pipe_clock(old_crtc_state);
-
 	intel_encoders_post_disable(crtc, old_crtc_state, old_state);
 
 	if (INTEL_GEN(dev_priv) >= 11)
-- 
cgit v1.2.3


From 8fc0aa6eaa568caf72adb8482bf33738d579c32d Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 13 Jun 2018 20:07:08 +0300
Subject: drm/i915/ddi: Check transcoder instead of port when setting HDMI
 infoframe
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only requirement by BSpec for setting the HDMI infoframes is on DDI
platforms to do that before enabling the HDMI transcoder function, see
VIDEO_DIP_CTL bit 16. Accordingly check for the transcoder function
disabled state instead of the port's disabled state on DDI platforms.
This is needed by the next patch as it will set the infoframe during
crtc disabling where the port is still enabled.

Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613170710.15080-4-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_hdmi.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 447ffe590e55..e88cdd9ab1b1 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -59,6 +59,15 @@ assert_hdmi_port_disabled(struct intel_hdmi *intel_hdmi)
 	     "HDMI port enabled, expecting disabled\n");
 }
 
+static void
+assert_hdmi_transcoder_func_disabled(struct drm_i915_private *dev_priv,
+				     enum transcoder cpu_transcoder)
+{
+	WARN(I915_READ(TRANS_DDI_FUNC_CTL(cpu_transcoder)) &
+	     TRANS_DDI_FUNC_ENABLE,
+	     "HDMI transcoder function enabled, expecting disabled\n");
+}
+
 struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder)
 {
 	struct intel_digital_port *intel_dig_port =
@@ -834,11 +843,11 @@ static void hsw_set_infoframes(struct drm_encoder *encoder,
 			       const struct drm_connector_state *conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->dev);
-	struct intel_hdmi *intel_hdmi = enc_to_intel_hdmi(encoder);
 	i915_reg_t reg = HSW_TVIDEO_DIP_CTL(crtc_state->cpu_transcoder);
 	u32 val = I915_READ(reg);
 
-	assert_hdmi_port_disabled(intel_hdmi);
+	assert_hdmi_transcoder_func_disabled(dev_priv,
+					     crtc_state->cpu_transcoder);
 
 	val &= ~(VIDEO_DIP_ENABLE_VSC_HSW | VIDEO_DIP_ENABLE_AVI_HSW |
 		 VIDEO_DIP_ENABLE_GCP_HSW | VIDEO_DIP_ENABLE_VS_HSW |
-- 
cgit v1.2.3


From c737376442e26c84ef188e7c829e15d42928fc03 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 13 Jun 2018 20:07:09 +0300
Subject: drm/i915/ddi: Set HDMI infoframes with pipe clocks enabled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On ICL for setting the HDMI infoframe the pipe clock needs to be
enabled, otherwise accessing the VIDEO_DIP_CTL register will hang the
machine.

Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613170710.15080-5-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_ddi.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index df0e64a9721a..936ff5a0b522 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -2671,11 +2671,11 @@ static void intel_ddi_pre_enable_hdmi(struct intel_encoder *encoder,
 	if (IS_GEN9_BC(dev_priv))
 		skl_ddi_set_iboost(encoder, level, INTEL_OUTPUT_HDMI);
 
+	intel_ddi_enable_pipe_clock(crtc_state);
+
 	intel_dig_port->set_infoframes(&encoder->base,
 				       crtc_state->has_infoframe,
 				       crtc_state, conn_state);
-
-	intel_ddi_enable_pipe_clock(crtc_state);
 }
 
 static void intel_ddi_pre_enable(struct intel_encoder *encoder,
@@ -2769,13 +2769,13 @@ static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
 	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
 	struct intel_hdmi *intel_hdmi = &dig_port->hdmi;
 
+	dig_port->set_infoframes(&encoder->base, false,
+				 old_crtc_state, old_conn_state);
+
 	intel_ddi_disable_pipe_clock(old_crtc_state);
 
 	intel_disable_ddi_buf(encoder);
 
-	dig_port->set_infoframes(&encoder->base, false,
-				 old_crtc_state, old_conn_state);
-
 	intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
-- 
cgit v1.2.3


From 3b567bb059b960a222c08d4d795360beb97e8551 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Wed, 13 Jun 2018 20:07:10 +0300
Subject: drm/i915/ddi: Removed unused var from hsw_write_infoframe()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613170710.15080-6-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_hdmi.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index e88cdd9ab1b1..9a33432c1f6b 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -390,14 +390,11 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	i915_reg_t ctl_reg = HSW_TVIDEO_DIP_CTL(cpu_transcoder);
-	i915_reg_t data_reg;
 	int data_size = type == DP_SDP_VSC ?
 		VIDEO_DIP_VSC_DATA_SIZE : VIDEO_DIP_DATA_SIZE;
 	int i;
 	u32 val = I915_READ(ctl_reg);
 
-	data_reg = hsw_dip_data_reg(dev_priv, cpu_transcoder, type, 0);
-
 	val &= ~hsw_infoframe_enable(type);
 	I915_WRITE(ctl_reg, val);
 
-- 
cgit v1.2.3


From 132c27c97cb958f637dc05adc35a61b47779bcd8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 11 Jun 2018 23:02:55 +0300
Subject: drm/i915: Fix PIPESTAT irq ack on i965/g4x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On i965/g4x IIR is edge triggered. So in order for IIR to notice that
there is still a pending interrupt we have to force and edge in ISR.
For the ISR/IIR pipe event bits we can do that by temporarily
clearing all the PIPESTAT enable bits when we ack the status bits.
This will force the ISR pipe event bit low, and it can then go back
high when we restore the PIPESTAT enable bits.

This avoids the following race:
1. stat = read(PIPESTAT)
2. an enabled PIPESTAT status bit goes high
3. write(PIPESTAT, enable|stat);
4. write(IIR, PIPE_EVENT)

The end result is IIR==0 and ISR!=0. This can lead to nasty
vblank wait/flip_done timeouts if another interrupt source
doesn't trick us into looking at the PIPESTAT status bits despite
the IIR PIPE_EVENT bit being low.

Before i965 IIR was level triggered so this problem can't actually
happen there. And curiously VLV/CHV went back to the level triggered
scheme as well. But for simplicity we'll use the same i965/g4x
compatible code for all platforms.

Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106033
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105225
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106030
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611200258.27121-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_irq.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c52060a35317..d5aee0b74f4b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1893,9 +1893,17 @@ static void i9xx_pipestat_irq_ack(struct drm_i915_private *dev_priv,
 
 		/*
 		 * Clear the PIPE*STAT regs before the IIR
+		 *
+		 * Toggle the enable bits to make sure we get an
+		 * edge in the ISR pipe event bit if we don't clear
+		 * all the enabled status bits. Otherwise the edge
+		 * triggered IIR on i965/g4x wouldn't notice that
+		 * an interrupt is still pending.
 		 */
-		if (pipe_stats[pipe])
-			I915_WRITE(reg, enable_mask | pipe_stats[pipe]);
+		if (pipe_stats[pipe]) {
+			I915_WRITE(reg, pipe_stats[pipe]);
+			I915_WRITE(reg, enable_mask);
+		}
 	}
 	spin_unlock(&dev_priv->irq_lock);
 }
-- 
cgit v1.2.3


From 929168c5f3df5d9ea0ef426c33e971157d045eab Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 13 Jun 2018 19:05:52 +0300
Subject: drm/i915: Disallow interlaced modes on g4x DP outputs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Looks like interlaced DP output doesn't work on g4x either. Not all
that surprising considering we already established that interlaced
DP output is busted on VLV/CHV.

Cc: stable@vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613160553.11664-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/intel_dp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index a58bac01aeea..2fe85c63d5ce 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1875,7 +1875,7 @@ intel_dp_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return false;
 
-	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	if (HAS_GMCH_DISPLAY(dev_priv) &&
 	    adjusted_mode->flags & DRM_MODE_FLAG_INTERLACE)
 		return false;
 
@@ -6357,7 +6357,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	drm_connector_init(dev, connector, &intel_dp_connector_funcs, type);
 	drm_connector_helper_add(connector, &intel_dp_connector_helper_funcs);
 
-	if (!IS_VALLEYVIEW(dev_priv) && !IS_CHERRYVIEW(dev_priv))
+	if (!HAS_GMCH_DISPLAY(dev_priv))
 		connector->interlace_allowed = true;
 	connector->doublescan_allowed = 0;
 
-- 
cgit v1.2.3


From 51a9f6dfc00d35f927ecfaf6f0ae8ebaba39b3fe Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Wed, 13 Jun 2018 19:05:53 +0300
Subject: drm/i915: Turn off g4x DP port in .post_disable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While Bspec doesn't list a specific sequence for turning off the DP port
on g4x we are getting an underrun if the port is disabled in the
.disable() hook. Looks like the pipe stops when the port stops, and by
that time the plane disable may not have completed yet. Also the plane(s)
seem to end up in some wonky state when this happens as they also signal
another underrun immediately after we turn them back on during the next
enable sequence.

We could add a vblank wait in .disable() to avoid wedging the planes,
but I assume we're still tripping up the pipe in some way. So it seems
better to me to just follow the ILK+ sequence and turn off the DP port
in .post_disable() instead. This sequence doesn't seem to suffer from
this problem. Could be it was always the intended sequence for DP and
the gen4 bspec was just never updated to include it.

Originally we used the bad sequence even on ilk+, but I changed that
in commit 08aff3fe26ae ("drm/i915: Move DP port disable to post_disable
for pch platforms") as it was causing issues on those platforms as well.
I left out g4x then only because I didn't have the hardware to test it.
Now that I do it's fairly clear that the ilk+ sequence is also the
right choice for g4x.

v2: Fix whitespace fail (Jani)
    Mention the ilk+ commit (Jani)

Cc: stable@vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180613160553.11664-2-ville.syrjala@linux.intel.com
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
---
 drivers/gpu/drm/i915/intel_dp.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 2fe85c63d5ce..67875b00c8df 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2809,16 +2809,6 @@ static void intel_disable_dp(struct intel_encoder *encoder,
 static void g4x_disable_dp(struct intel_encoder *encoder,
 			   const struct intel_crtc_state *old_crtc_state,
 			   const struct drm_connector_state *old_conn_state)
-{
-	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
-
-	/* disable the port before the pipe on g4x */
-	intel_dp_link_down(encoder, old_crtc_state);
-}
-
-static void ilk_disable_dp(struct intel_encoder *encoder,
-			   const struct intel_crtc_state *old_crtc_state,
-			   const struct drm_connector_state *old_conn_state)
 {
 	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
 }
@@ -2834,13 +2824,19 @@ static void vlv_disable_dp(struct intel_encoder *encoder,
 	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
 }
 
-static void ilk_post_disable_dp(struct intel_encoder *encoder,
+static void g4x_post_disable_dp(struct intel_encoder *encoder,
 				const struct intel_crtc_state *old_crtc_state,
 				const struct drm_connector_state *old_conn_state)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 	enum port port = encoder->port;
 
+	/*
+	 * Bspec does not list a specific disable sequence for g4x DP.
+	 * Follow the ilk+ sequence (disable pipe before the port) for
+	 * g4x DP as it does not suffer from underruns like the normal
+	 * g4x modeset sequence (disable pipe after the port).
+	 */
 	intel_dp_link_down(encoder, old_crtc_state);
 
 	/* Only ilk+ has port A */
@@ -6456,15 +6452,11 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 		intel_encoder->enable = vlv_enable_dp;
 		intel_encoder->disable = vlv_disable_dp;
 		intel_encoder->post_disable = vlv_post_disable_dp;
-	} else if (INTEL_GEN(dev_priv) >= 5) {
-		intel_encoder->pre_enable = g4x_pre_enable_dp;
-		intel_encoder->enable = g4x_enable_dp;
-		intel_encoder->disable = ilk_disable_dp;
-		intel_encoder->post_disable = ilk_post_disable_dp;
 	} else {
 		intel_encoder->pre_enable = g4x_pre_enable_dp;
 		intel_encoder->enable = g4x_enable_dp;
 		intel_encoder->disable = g4x_disable_dp;
+		intel_encoder->post_disable = g4x_post_disable_dp;
 	}
 
 	intel_dig_port->dp.output_reg = output_reg;
-- 
cgit v1.2.3


From 920d3fb1a00c3d7bb24c9b396c8b2950192c5ad8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 13:49:23 +0100
Subject: drm/i915/selftests: Initialise request to silence a compiler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With an old (4.7.3 on 32bit) gcc, it emits a warning for

In file included from drivers/gpu/drm/i915/i915_request.c:1425:0:
drivers/gpu/drm/i915/selftests/i915_request.c: In function ‘live_nop_request’:
drivers/gpu/drm/i915/selftests/i915_request.c:380:21: error: ‘request’ may be used uninitialized in this function [-Werror=maybe-uninitialized]

Silence it by just setting it to NULL on initialisation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614124923.18071-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_request.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index f5d00332bb31..63cd9486cc13 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -342,9 +342,9 @@ static int live_nop_request(void *arg)
 	mutex_lock(&i915->drm.struct_mutex);
 
 	for_each_engine(engine, i915, id) {
-		IGT_TIMEOUT(end_time);
-		struct i915_request *request;
+		struct i915_request *request = NULL;
 		unsigned long n, prime;
+		IGT_TIMEOUT(end_time);
 		ktime_t times[2] = {};
 
 		err = begin_live_test(&t, i915, __func__, engine->name);
-- 
cgit v1.2.3


From 5db1d4ea91b6ee447c4ae01f7f56803e32e690b1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 4 Jun 2018 08:34:40 +0100
Subject: drm/i915/execlists: Push the tasklet kick after reset to reset_finish

In the unlikely case where we have failed to keep submitting to the GPU,
we end up with the ELSP queue empty but a pending queue of requests.
Here, we skip the per-engine reset as there is no guilty request, but in
doing so we also skip the engine restart leaving ourselves with a
permanently hung engine. A quick way to recover is by moving the tasklet
kick to execlists_reset_finish() (from init_hw). We still emit the error
on hanging, so the error is not lost but we should be able to recover.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180604073441.6737-2-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/intel_lrc.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 44e4c9e07571..8d56bcb00979 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1811,7 +1811,6 @@ static bool unexpected_starting_state(struct intel_engine_cs *engine)
 
 static int gen8_init_common_ring(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	int ret;
 
 	ret = intel_mocs_init_engine(engine);
@@ -1829,10 +1828,6 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 
 	enable_execlists(engine);
 
-	/* After a GPU reset, we may have requests to replay */
-	if (execlists->first)
-		tasklet_schedule(&execlists->tasklet);
-
 	return 0;
 }
 
@@ -2015,6 +2010,12 @@ static void execlists_reset(struct intel_engine_cs *engine,
 
 static void execlists_reset_finish(struct intel_engine_cs *engine)
 {
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	/* After a GPU reset, we may have requests to replay */
+	if (execlists->first)
+		tasklet_schedule(&execlists->tasklet);
+
 	/*
 	 * Flush the tasklet while we still have the forcewake to be sure
 	 * that it is not allowed to sleep before we restart and reload a
@@ -2024,7 +2025,7 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	 * serialising multiple attempts to reset so that we know that we
 	 * are the only one manipulating tasklet state.
 	 */
-	__tasklet_enable_sync_once(&engine->execlists.tasklet);
+	__tasklet_enable_sync_once(&execlists->tasklet);
 
 	GEM_TRACE("%s\n", engine->name);
 }
-- 
cgit v1.2.3


From 1fd00c0faeec0a89dfe97de842facbecc8a04efb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 2 Jun 2018 11:48:53 +0100
Subject: drm/i915: Declare the driver wedged if hangcheck makes no progress

Hangcheck is our back up in case the GPU or the driver gets stuck. It
detects when the GPU is not making any progress and issues a GPU reset.
However, if the driver is failing to make any progress, we can get
ourselves into a situation where we continually try resetting the GPU to
no avail. Employ a second timeout such that if we continue to see the
same seqno (the stalled engine has made no progress at all) over the
course of several hangchecks, declare the driver wedged and attempt to
start afresh.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180602104853.17140-1-chris@chris-wilson.co.uk
Reviewed-by: Mika Kuoppala <mika.kuoppala@intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c     |  5 +++--
 drivers/gpu/drm/i915/i915_drv.h         |  2 ++
 drivers/gpu/drm/i915/intel_hangcheck.c  | 17 ++++++++++++++++-
 drivers/gpu/drm/i915/intel_ringbuffer.h |  3 ++-
 4 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 948b973af067..99d3272d82d8 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1359,11 +1359,12 @@ static int i915_hangcheck_info(struct seq_file *m, void *unused)
 		seq_printf(m, "\tseqno = %x [current %x, last %x]\n",
 			   engine->hangcheck.seqno, seqno[id],
 			   intel_engine_last_submit(engine));
-		seq_printf(m, "\twaiters? %s, fake irq active? %s, stalled? %s\n",
+		seq_printf(m, "\twaiters? %s, fake irq active? %s, stalled? %s, wedged? %s\n",
 			   yesno(intel_engine_has_waiter(engine)),
 			   yesno(test_bit(engine->id,
 					  &dev_priv->gpu_error.missed_irq_rings)),
-			   yesno(engine->hangcheck.stalled));
+			   yesno(engine->hangcheck.stalled),
+			   yesno(engine->hangcheck.wedged));
 
 		spin_lock_irq(&b->rb_lock);
 		for (rb = rb_first(&b->waiters); rb; rb = rb_next(rb)) {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 19defe73b156..74dd88d8563e 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1006,6 +1006,8 @@ struct i915_gem_mm {
 #define I915_ENGINE_DEAD_TIMEOUT  (4 * HZ)  /* Seqno, head and subunits dead */
 #define I915_SEQNO_DEAD_TIMEOUT   (12 * HZ) /* Seqno dead with active head */
 
+#define I915_ENGINE_WEDGED_TIMEOUT  (60 * HZ)  /* Reset but no recovery? */
+
 enum modeset_restore {
 	MODESET_ON_LID_OPEN,
 	MODESET_DONE,
diff --git a/drivers/gpu/drm/i915/intel_hangcheck.c b/drivers/gpu/drm/i915/intel_hangcheck.c
index d47e346bd49e..2fc7a0dd0df9 100644
--- a/drivers/gpu/drm/i915/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/intel_hangcheck.c
@@ -294,6 +294,7 @@ static void hangcheck_store_sample(struct intel_engine_cs *engine,
 	engine->hangcheck.seqno = hc->seqno;
 	engine->hangcheck.action = hc->action;
 	engine->hangcheck.stalled = hc->stalled;
+	engine->hangcheck.wedged = hc->wedged;
 }
 
 static enum intel_engine_hangcheck_action
@@ -368,6 +369,9 @@ static void hangcheck_accumulate_sample(struct intel_engine_cs *engine,
 
 	hc->stalled = time_after(jiffies,
 				 engine->hangcheck.action_timestamp + timeout);
+	hc->wedged = time_after(jiffies,
+				 engine->hangcheck.action_timestamp +
+				 I915_ENGINE_WEDGED_TIMEOUT);
 }
 
 static void hangcheck_declare_hang(struct drm_i915_private *i915,
@@ -409,7 +413,7 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			     gpu_error.hangcheck_work.work);
 	struct intel_engine_cs *engine;
 	enum intel_engine_id id;
-	unsigned int hung = 0, stuck = 0;
+	unsigned int hung = 0, stuck = 0, wedged = 0;
 
 	if (!i915_modparams.enable_hangcheck)
 		return;
@@ -440,6 +444,17 @@ static void i915_hangcheck_elapsed(struct work_struct *work)
 			if (hc.action != ENGINE_DEAD)
 				stuck |= intel_engine_flag(engine);
 		}
+
+		if (engine->hangcheck.wedged)
+			wedged |= intel_engine_flag(engine);
+	}
+
+	if (wedged) {
+		dev_err(dev_priv->drm.dev,
+			"GPU recovery timed out,"
+			" cancelling all in-flight rendering.\n");
+		GEM_TRACE_DUMP();
+		i915_gem_set_wedged(dev_priv);
 	}
 
 	if (hung)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 2c35dd3525a6..4003f3ebe3d1 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -122,7 +122,8 @@ struct intel_engine_hangcheck {
 	int deadlock;
 	struct intel_instdone instdone;
 	struct i915_request *active_request;
-	bool stalled;
+	bool stalled:1;
+	bool wedged:1;
 };
 
 struct intel_ring {
-- 
cgit v1.2.3


From 549fe88bf71d30563f20dcfd7970b7424bf07907 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 14:43:14 +0100
Subject: drm/i915/gtt: Lazily allocate page directories for gen7

As we were only supporting aliasing_ppgtt on gen7 for some time, we
saved a few checks by preallocating the page directories on creation.
However, since we need 2MiB of page directories for each ppgtt, to
support arbitrary numbers of user contexts, we need to be more prudent
in our allocations, and defer the page allocation until it is used. We
don't recover unused pages yet as we found that doing so on the fly
(i.e. altering TLB entries) would confuse the GPU.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614134315.5900-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 67 ++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 0ee9e154359f..6a62c40b241c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -190,11 +190,19 @@ int intel_sanitize_enable_ppgtt(struct drm_i915_private *dev_priv,
 	return 1;
 }
 
-static int gen6_ppgtt_bind_vma(struct i915_vma *vma,
-			       enum i915_cache_level cache_level,
-			       u32 unused)
+static int ppgtt_bind_vma(struct i915_vma *vma,
+			  enum i915_cache_level cache_level,
+			  u32 unused)
 {
 	u32 pte_flags;
+	int err;
+
+	if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
+		err = vma->vm->allocate_va_range(vma->vm,
+						 vma->node.start, vma->size);
+		if (err)
+			return err;
+	}
 
 	/* Currently applicable only to VLV */
 	pte_flags = 0;
@@ -206,22 +214,6 @@ static int gen6_ppgtt_bind_vma(struct i915_vma *vma,
 	return 0;
 }
 
-static int gen8_ppgtt_bind_vma(struct i915_vma *vma,
-			       enum i915_cache_level cache_level,
-			       u32 unused)
-{
-	int ret;
-
-	if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
-		ret = vma->vm->allocate_va_range(vma->vm,
-						 vma->node.start, vma->size);
-		if (ret)
-			return ret;
-	}
-
-	return gen6_ppgtt_bind_vma(vma, cache_level, unused);
-}
-
 static void ppgtt_unbind_vma(struct i915_vma *vma)
 {
 	vma->vm->clear_range(vma->vm, vma->node.start, vma->size);
@@ -1622,7 +1614,7 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	ppgtt->vm.cleanup = gen8_ppgtt_cleanup;
 	ppgtt->debug_dump = gen8_dump_ppgtt;
 
-	ppgtt->vm.vma_ops.bind_vma    = gen8_ppgtt_bind_vma;
+	ppgtt->vm.vma_ops.bind_vma    = ppgtt_bind_vma;
 	ppgtt->vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
 	ppgtt->vm.vma_ops.set_pages   = ppgtt_set_pages;
 	ppgtt->vm.vma_ops.clear_pages = clear_pages;
@@ -1776,7 +1768,8 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 
 		num_entries -= end - pte;
 
-		/* Note that the hw doesn't support removing PDE on the fly
+		/*
+		 * Note that the hw doesn't support removing PDE on the fly
 		 * (they are cached inside the context with no means to
 		 * invalidate the cache), so we can only reset the PTE
 		 * entries back to scratch.
@@ -2046,12 +2039,13 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 
 	ppgtt->base.vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
 
+	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
 	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
 	ppgtt->base.vm.cleanup = gen6_ppgtt_cleanup;
 	ppgtt->base.debug_dump = gen6_dump_ppgtt;
 
-	ppgtt->base.vm.vma_ops.bind_vma    = gen6_ppgtt_bind_vma;
+	ppgtt->base.vm.vma_ops.bind_vma    = ppgtt_bind_vma;
 	ppgtt->base.vm.vma_ops.unbind_vma  = ppgtt_unbind_vma;
 	ppgtt->base.vm.vma_ops.set_pages   = ppgtt_set_pages;
 	ppgtt->base.vm.vma_ops.clear_pages = clear_pages;
@@ -2068,14 +2062,8 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 		goto err_scratch;
 	}
 
-	err = gen6_alloc_va_range(&ppgtt->base.vm, 0, ppgtt->base.vm.total);
-	if (err)
-		goto err_vma;
-
 	return &ppgtt->base;
 
-err_vma:
-	i915_vma_destroy(ppgtt->vma);
 err_scratch:
 	gen6_ppgtt_free_scratch(&ppgtt->base.vm);
 err_free:
@@ -2671,8 +2659,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 	if (flags & I915_VMA_LOCAL_BIND) {
 		struct i915_hw_ppgtt *appgtt = i915->mm.aliasing_ppgtt;
 
-		if (!(vma->flags & I915_VMA_LOCAL_BIND) &&
-		    appgtt->vm.allocate_va_range) {
+		if (!(vma->flags & I915_VMA_LOCAL_BIND)) {
 			ret = appgtt->vm.allocate_va_range(&appgtt->vm,
 							   vma->node.start,
 							   vma->size);
@@ -2776,17 +2763,15 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 		goto err_ppgtt;
 	}
 
-	if (ppgtt->vm.allocate_va_range) {
-		/* Note we only pre-allocate as far as the end of the global
-		 * GTT. On 48b / 4-level page-tables, the difference is very,
-		 * very significant! We have to preallocate as GVT/vgpu does
-		 * not like the page directory disappearing.
-		 */
-		err = ppgtt->vm.allocate_va_range(&ppgtt->vm,
-						  0, ggtt->vm.total);
-		if (err)
-			goto err_ppgtt;
-	}
+	/*
+	 * Note we only pre-allocate as far as the end of the global
+	 * GTT. On 48b / 4-level page-tables, the difference is very,
+	 * very significant! We have to preallocate as GVT/vgpu does
+	 * not like the page directory disappearing.
+	 */
+	err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, ggtt->vm.total);
+	if (err)
+		goto err_ppgtt;
 
 	i915->mm.aliasing_ppgtt = ppgtt;
 
-- 
cgit v1.2.3


From 4a192c7e8b14a2bf8f30b1fac3599a7d391dfcf9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 14:43:15 +0100
Subject: drm/i915/gtt: Free unused page tables on unbind the context

As we cannot reliably change used page tables while the context is
active, the earliest opportunity we have to recover excess pages is when
the context becomes idle. So whenever we unbind the context (it must be
idle, and indeed being evicted) free the unused ptes.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614134315.5900-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 44 ++++++++++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/i915_gem_gtt.h |  1 +
 2 files changed, 40 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 6a62c40b241c..50160be6357e 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1753,20 +1753,28 @@ static void gen6_ppgtt_enable(struct drm_i915_private *dev_priv)
 static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 				   u64 start, u64 length)
 {
-	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
+	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(i915_vm_to_ppgtt(vm));
 	unsigned int first_entry = start >> PAGE_SHIFT;
 	unsigned int pde = first_entry / GEN6_PTES;
 	unsigned int pte = first_entry % GEN6_PTES;
 	unsigned int num_entries = length >> PAGE_SHIFT;
-	gen6_pte_t scratch_pte =
+	const gen6_pte_t scratch_pte =
 		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 
 	while (num_entries) {
-		struct i915_page_table *pt = ppgtt->pd.page_table[pde++];
-		unsigned int end = min(pte + num_entries, GEN6_PTES);
+		struct i915_page_table *pt = ppgtt->base.pd.page_table[pde++];
+		const unsigned int end = min(pte + num_entries, GEN6_PTES);
+		const unsigned int count = end - pte;
 		gen6_pte_t *vaddr;
 
-		num_entries -= end - pte;
+		GEM_BUG_ON(pt == vm->scratch_pt);
+
+		num_entries -= count;
+
+		GEM_BUG_ON(count > pt->used_ptes);
+		pt->used_ptes -= count;
+		if (!pt->used_ptes)
+			ppgtt->scan_for_unused_pt = true;
 
 		/*
 		 * Note that the hw doesn't support removing PDE on the fly
@@ -1798,6 +1806,8 @@ static void gen6_ppgtt_insert_entries(struct i915_address_space *vm,
 	struct sgt_dma iter = sgt_dma(vma);
 	gen6_pte_t *vaddr;
 
+	GEM_BUG_ON(ppgtt->pd.page_table[act_pt] == vm->scratch_pt);
+
 	vaddr = kmap_atomic_px(ppgtt->pd.page_table[act_pt]);
 	do {
 		vaddr[act_pte] = pte_encode | GEN6_PTE_ADDR_ENCODE(iter.dma);
@@ -1833,6 +1843,8 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 	bool flush = false;
 
 	gen6_for_each_pde(pt, &ppgtt->base.pd, start, length, pde) {
+		const unsigned int count = gen6_pte_count(start, length);
+
 		if (pt == vm->scratch_pt) {
 			pt = alloc_pt(vm);
 			if (IS_ERR(pt))
@@ -1846,7 +1858,11 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 				gen6_write_pde(ppgtt, pde, pt);
 				flush = true;
 			}
+
+			GEM_BUG_ON(pt->used_ptes);
 		}
+
+		pt->used_ptes += count;
 	}
 
 	if (flush) {
@@ -1948,6 +1964,24 @@ static int pd_vma_bind(struct i915_vma *vma,
 
 static void pd_vma_unbind(struct i915_vma *vma)
 {
+	struct gen6_hw_ppgtt *ppgtt = vma->private;
+	struct i915_page_table * const scratch_pt = ppgtt->base.vm.scratch_pt;
+	struct i915_page_table *pt;
+	unsigned int pde;
+
+	if (!ppgtt->scan_for_unused_pt)
+		return;
+
+	/* Free all no longer used page tables */
+	gen6_for_all_pdes(pt, &ppgtt->base.pd, pde) {
+		if (pt->used_ptes || pt == scratch_pt)
+			continue;
+
+		free_pt(&ppgtt->base.vm, pt);
+		ppgtt->base.pd.page_table[pde] = scratch_pt;
+	}
+
+	ppgtt->scan_for_unused_pt = false;
 }
 
 static const struct i915_vma_ops pd_vma_ops = {
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index d7b7b4afe060..46c95d188580 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -414,6 +414,7 @@ struct gen6_hw_ppgtt {
 	gen6_pte_t __iomem *pd_addr;
 
 	unsigned int pin_count;
+	bool scan_for_unused_pt;
 };
 
 #define __to_gen6_ppgtt(base) container_of(base, struct gen6_hw_ppgtt, base)
-- 
cgit v1.2.3


From 986dbac4803c7eb2be0d0dac7bc642744502d080 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 19:42:17 +0100
Subject: drm/i915/gtt: Cache the PTE encoding of the scratch page

As the most frequent PTE encoding is for the scratch page, cache it upon
creation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614184218.1606-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 20 ++++++++++----------
 drivers/gpu/drm/i915/i915_gem_gtt.h |  1 +
 2 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 50160be6357e..dec8a8401c2d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -640,11 +640,10 @@ static void gen8_initialize_pt(struct i915_address_space *vm,
 		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC));
 }
 
-static void gen6_initialize_pt(struct i915_address_space *vm,
+static void gen6_initialize_pt(struct gen6_hw_ppgtt *ppgtt,
 			       struct i915_page_table *pt)
 {
-	fill32_px(vm, pt,
-		  vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0));
+	fill32_px(&ppgtt->base.vm, pt, ppgtt->scratch_pte);
 }
 
 static struct i915_page_directory *alloc_pd(struct i915_address_space *vm)
@@ -1631,9 +1630,7 @@ err_free:
 static void gen6_dump_ppgtt(struct i915_hw_ppgtt *base, struct seq_file *m)
 {
 	struct gen6_hw_ppgtt *ppgtt = to_gen6_ppgtt(base);
-	struct i915_address_space *vm = &base->vm;
-	const gen6_pte_t scratch_pte =
-		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
+	const gen6_pte_t scratch_pte = ppgtt->scratch_pte;
 	struct i915_page_table *pt;
 	u32 pte, pde;
 
@@ -1758,8 +1755,7 @@ static void gen6_ppgtt_clear_range(struct i915_address_space *vm,
 	unsigned int pde = first_entry / GEN6_PTES;
 	unsigned int pte = first_entry % GEN6_PTES;
 	unsigned int num_entries = length >> PAGE_SHIFT;
-	const gen6_pte_t scratch_pte =
-		vm->pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
+	const gen6_pte_t scratch_pte = ppgtt->scratch_pte;
 
 	while (num_entries) {
 		struct i915_page_table *pt = ppgtt->base.pd.page_table[pde++];
@@ -1850,7 +1846,7 @@ static int gen6_alloc_va_range(struct i915_address_space *vm,
 			if (IS_ERR(pt))
 				goto unwind_out;
 
-			gen6_initialize_pt(vm, pt);
+			gen6_initialize_pt(ppgtt, pt);
 			ppgtt->base.pd.page_table[pde] = pt;
 
 			if (i915_vma_is_bound(ppgtt->vma,
@@ -1888,13 +1884,17 @@ static int gen6_ppgtt_init_scratch(struct gen6_hw_ppgtt *ppgtt)
 	if (ret)
 		return ret;
 
+	ppgtt->scratch_pte =
+		vm->pte_encode(vm->scratch_page.daddr,
+			       I915_CACHE_NONE, PTE_READ_ONLY);
+
 	vm->scratch_pt = alloc_pt(vm);
 	if (IS_ERR(vm->scratch_pt)) {
 		cleanup_scratch_page(vm);
 		return PTR_ERR(vm->scratch_pt);
 	}
 
-	gen6_initialize_pt(vm, vm->scratch_pt);
+	gen6_initialize_pt(ppgtt, vm->scratch_pt);
 	gen6_for_all_pdes(unused, &ppgtt->base.pd, pde)
 		ppgtt->base.pd.page_table[pde] = vm->scratch_pt;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 46c95d188580..7ff5cc612771 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -412,6 +412,7 @@ struct gen6_hw_ppgtt {
 
 	struct i915_vma *vma;
 	gen6_pte_t __iomem *pd_addr;
+	gen6_pte_t scratch_pte;
 
 	unsigned int pin_count;
 	bool scan_for_unused_pt;
-- 
cgit v1.2.3


From a0fbacb58ce1b5885475d38338b8ad3e8c86e5e9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 14 Jun 2018 19:42:18 +0100
Subject: drm/i915/gtt: Reduce a pair of runtime asserts

We can stop asserting using WARN_ON as given sufficient CI coverage, we
can rely on using GEM_BUG_ON() to catch problems before merging.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614184218.1606-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.h | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index dec8a8401c2d..ba1aed07d6dc 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2792,7 +2792,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
-	if (WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
+	if (GEM_WARN_ON(ppgtt->vm.total < ggtt->vm.total)) {
 		err = -ENODEV;
 		goto err_ppgtt;
 	}
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 7ff5cc612771..9a4824cae68d 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -464,8 +464,8 @@ static inline u32 i915_pte_count(u64 addr, u64 length, unsigned int pde_shift)
 	const u64 mask = ~((1ULL << pde_shift) - 1);
 	u64 end;
 
-	WARN_ON(length == 0);
-	WARN_ON(offset_in_page(addr|length));
+	GEM_BUG_ON(length == 0);
+	GEM_BUG_ON(offset_in_page(addr | length));
 
 	end = addr + length;
 
-- 
cgit v1.2.3


From 970888e7d130f19affc72ffbadf05b40b7693a27 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Mon, 21 May 2018 17:25:44 -0700
Subject: drm/i915/icl: add icelake_get_ddi_pll()

Implement the hardware state readout code.

Thanks to Animesh Manna for spotting this problem.

Cc: Animesh Manna <animesh.manna@intel.com>
Credits-to: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-11-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_display.c | 42 +++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 05abd23b526f..1ac375879510 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9209,6 +9209,44 @@ static void cannonlake_get_ddi_pll(struct drm_i915_private *dev_priv,
 	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
 }
 
+static void icelake_get_ddi_pll(struct drm_i915_private *dev_priv,
+				enum port port,
+				struct intel_crtc_state *pipe_config)
+{
+	enum intel_dpll_id id;
+	u32 temp;
+
+	/* TODO: TBT pll not implemented. */
+	switch (port) {
+	case PORT_A:
+	case PORT_B:
+		temp = I915_READ(DPCLKA_CFGCR0_ICL) &
+		       DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port);
+		id = temp >> DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port);
+
+		if (WARN_ON(id != DPLL_ID_ICL_DPLL0 && id != DPLL_ID_ICL_DPLL1))
+			return;
+		break;
+	case PORT_C:
+		id = DPLL_ID_ICL_MGPLL1;
+		break;
+	case PORT_D:
+		id = DPLL_ID_ICL_MGPLL2;
+		break;
+	case PORT_E:
+		id = DPLL_ID_ICL_MGPLL3;
+		break;
+	case PORT_F:
+		id = DPLL_ID_ICL_MGPLL4;
+		break;
+	default:
+		MISSING_CASE(port);
+		return;
+	}
+
+	pipe_config->shared_dpll = intel_get_shared_dpll_by_id(dev_priv, id);
+}
+
 static void bxt_get_ddi_pll(struct drm_i915_private *dev_priv,
 				enum port port,
 				struct intel_crtc_state *pipe_config)
@@ -9396,7 +9434,9 @@ static void haswell_get_ddi_port_state(struct intel_crtc *crtc,
 
 	port = (tmp & TRANS_DDI_PORT_MASK) >> TRANS_DDI_PORT_SHIFT;
 
-	if (IS_CANNONLAKE(dev_priv))
+	if (IS_ICELAKE(dev_priv))
+		icelake_get_ddi_pll(dev_priv, port, pipe_config);
+	else if (IS_CANNONLAKE(dev_priv))
 		cannonlake_get_ddi_pll(dev_priv, port, pipe_config);
 	else if (IS_GEN9_BC(dev_priv))
 		skylake_get_ddi_pll(dev_priv, port, pipe_config);
-- 
cgit v1.2.3


From 00c92d929ac36848fbe88567ef14af947ab636e4 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Mon, 21 May 2018 17:25:47 -0700
Subject: drm/i915/icl: unconditionally init DDI for every port

On ICP, port present straps (from SFUSE_STRAP PCH register) are no
longer supported. Software should determine the presence through BIOS
VBT, hotplug or other mechanisms.

v2: Improve commit message (Lucas).

Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-14-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_display.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 1ac375879510..9939e092d9aa 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -14045,7 +14045,14 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 	if (intel_crt_present(dev_priv))
 		intel_crt_init(dev_priv);
 
-	if (IS_GEN9_LP(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		intel_ddi_init(dev_priv, PORT_A);
+		intel_ddi_init(dev_priv, PORT_B);
+		intel_ddi_init(dev_priv, PORT_C);
+		intel_ddi_init(dev_priv, PORT_D);
+		intel_ddi_init(dev_priv, PORT_E);
+		intel_ddi_init(dev_priv, PORT_F);
+	} else if (IS_GEN9_LP(dev_priv)) {
 		/*
 		 * FIXME: Broxton doesn't support port detection via the
 		 * DDI_BUF_CTL_A or SFUSE_STRAP registers, find another way to
-- 
cgit v1.2.3


From 1fa11ee2d9d0ccd58a6b56a9e490e336c99e98bf Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Mon, 21 May 2018 17:25:48 -0700
Subject: drm/i915/icl: start adding the TBT pll

This commit just adds the register addresses and the basic skeleton of
the code. The next commits will expand on more specific functions.

Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-15-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h       |  6 ++++++
 drivers/gpu/drm/i915/intel_ddi.c      | 16 ++++++++++++++++
 drivers/gpu/drm/i915/intel_dpll_mgr.c | 20 ++++++++++++++++----
 drivers/gpu/drm/i915/intel_dpll_mgr.h | 14 +++++++++-----
 4 files changed, 47 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 140f6a27d696..dd6076188319 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8836,6 +8836,10 @@ enum skl_power_gate {
 #define DDI_CLK_SEL(port)		PORT_CLK_SEL(port)
 #define  DDI_CLK_SEL_NONE		(0x0 << 28)
 #define  DDI_CLK_SEL_MG			(0x8 << 28)
+#define  DDI_CLK_SEL_TBT_162		(0xC << 28)
+#define  DDI_CLK_SEL_TBT_270		(0xD << 28)
+#define  DDI_CLK_SEL_TBT_540		(0xE << 28)
+#define  DDI_CLK_SEL_TBT_810		(0xF << 28)
 #define  DDI_CLK_SEL_MASK		(0xF << 28)
 
 /* Transcoder clock selection */
@@ -8985,6 +8989,8 @@ enum skl_power_gate {
 #define  PLL_POWER_STATE	(1 << 26)
 #define CNL_DPLL_ENABLE(pll)	_MMIO_PLL(pll, DPLL0_ENABLE, DPLL1_ENABLE)
 
+#define TBT_PLL_ENABLE		_MMIO(0x46020)
+
 #define _MG_PLL1_ENABLE		0x46030
 #define _MG_PLL2_ENABLE		0x46034
 #define _MG_PLL3_ENABLE		0x46038
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 936ff5a0b522..ce153b11c765 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1062,6 +1062,8 @@ static uint32_t hsw_pll_to_ddi_pll_sel(const struct intel_shared_dpll *pll)
 static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder,
 				       const struct intel_shared_dpll *pll)
 {
+	struct intel_crtc *crtc = to_intel_crtc(encoder->base.crtc);
+	int clock = crtc->config->port_clock;
 	const enum intel_dpll_id id = pll->info->id;
 
 	switch (id) {
@@ -1070,6 +1072,20 @@ static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder,
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return DDI_CLK_SEL_NONE;
+	case DPLL_ID_ICL_TBTPLL:
+		switch (clock) {
+		case 162000:
+			return DDI_CLK_SEL_TBT_162;
+		case 270000:
+			return DDI_CLK_SEL_TBT_270;
+		case 540000:
+			return DDI_CLK_SEL_TBT_540;
+		case 810000:
+			return DDI_CLK_SEL_TBT_810;
+		default:
+			MISSING_CASE(clock);
+			break;
+		}
 	case DPLL_ID_ICL_MGPLL1:
 	case DPLL_ID_ICL_MGPLL2:
 	case DPLL_ID_ICL_MGPLL3:
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 07bdbf2582ba..132fe63e042a 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -2857,10 +2857,17 @@ icl_get_dpll(struct intel_crtc *crtc, struct intel_crtc_state *crtc_state,
 	case PORT_D:
 	case PORT_E:
 	case PORT_F:
-		min = icl_port_to_mg_pll_id(port);
-		max = min;
-		ret = icl_calc_mg_pll_state(crtc_state, encoder, clock,
-					    &pll_state);
+		if (0 /* TODO: TBT PLLs */) {
+			min = DPLL_ID_ICL_TBTPLL;
+			max = min;
+			ret = icl_calc_dpll_state(crtc_state, encoder, clock,
+						  &pll_state);
+		} else {
+			min = icl_port_to_mg_pll_id(port);
+			max = min;
+			ret = icl_calc_mg_pll_state(crtc_state, encoder, clock,
+						    &pll_state);
+		}
 		break;
 	default:
 		MISSING_CASE(port);
@@ -2893,6 +2900,8 @@ static i915_reg_t icl_pll_id_to_enable_reg(enum intel_dpll_id id)
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return CNL_DPLL_ENABLE(id);
+	case DPLL_ID_ICL_TBTPLL:
+		return TBT_PLL_ENABLE;
 	case DPLL_ID_ICL_MGPLL1:
 	case DPLL_ID_ICL_MGPLL2:
 	case DPLL_ID_ICL_MGPLL3:
@@ -2920,6 +2929,7 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	switch (id) {
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
+	case DPLL_ID_ICL_TBTPLL:
 		hw_state->cfgcr0 = I915_READ(ICL_DPLL_CFGCR0(id));
 		hw_state->cfgcr1 = I915_READ(ICL_DPLL_CFGCR1(id));
 		break;
@@ -3006,6 +3016,7 @@ static void icl_pll_enable(struct drm_i915_private *dev_priv,
 	switch (id) {
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
+	case DPLL_ID_ICL_TBTPLL:
 		icl_dpll_write(dev_priv, pll);
 		break;
 	case DPLL_ID_ICL_MGPLL1:
@@ -3104,6 +3115,7 @@ static const struct intel_shared_dpll_funcs icl_pll_funcs = {
 static const struct dpll_info icl_plls[] = {
 	{ "DPLL 0",   &icl_pll_funcs, DPLL_ID_ICL_DPLL0,  0 },
 	{ "DPLL 1",   &icl_pll_funcs, DPLL_ID_ICL_DPLL1,  0 },
+	{ "TBT PLL",  &icl_pll_funcs, DPLL_ID_ICL_TBTPLL, 0 },
 	{ "MG PLL 1", &icl_pll_funcs, DPLL_ID_ICL_MGPLL1, 0 },
 	{ "MG PLL 2", &icl_pll_funcs, DPLL_ID_ICL_MGPLL2, 0 },
 	{ "MG PLL 3", &icl_pll_funcs, DPLL_ID_ICL_MGPLL3, 0 },
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h
index 78915057d2e6..ba925c7ee482 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h
@@ -113,24 +113,28 @@ enum intel_dpll_id {
 	 * @DPLL_ID_ICL_DPLL1: ICL combo PHY DPLL1
 	 */
 	DPLL_ID_ICL_DPLL1 = 1,
+	/**
+	 * @DPLL_ID_ICL_TBTPLL: ICL TBT PLL
+	 */
+	DPLL_ID_ICL_TBTPLL = 2,
 	/**
 	 * @DPLL_ID_ICL_MGPLL1: ICL MG PLL 1 port 1 (C)
 	 */
-	DPLL_ID_ICL_MGPLL1 = 2,
+	DPLL_ID_ICL_MGPLL1 = 3,
 	/**
 	 * @DPLL_ID_ICL_MGPLL2: ICL MG PLL 1 port 2 (D)
 	 */
-	DPLL_ID_ICL_MGPLL2 = 3,
+	DPLL_ID_ICL_MGPLL2 = 4,
 	/**
 	 * @DPLL_ID_ICL_MGPLL3: ICL MG PLL 1 port 3 (E)
 	 */
-	DPLL_ID_ICL_MGPLL3 = 4,
+	DPLL_ID_ICL_MGPLL3 = 5,
 	/**
 	 * @DPLL_ID_ICL_MGPLL4: ICL MG PLL 1 port 4 (F)
 	 */
-	DPLL_ID_ICL_MGPLL4 = 5,
+	DPLL_ID_ICL_MGPLL4 = 6,
 };
-#define I915_NUM_PLLS 6
+#define I915_NUM_PLLS 7
 
 struct intel_dpll_hw_state {
 	/* i9xx, pch plls */
-- 
cgit v1.2.3


From 46b527d19c4327897197d09748a8b332e322a1d7 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Mon, 11 Jun 2018 15:26:54 -0700
Subject: drm/i915/icl: Add allowed DP rates for Icelake

For ICL, on Combo PHY the allowed max rates are:
 - HBR3 8.1 eDP (DDIA)
 - HBR2 5.4 DisplayPort (DDIB)
and for MG PHY/TC DDI Ports allowed DP rates are:
 - HBR3 8.1 DisplayPort (DP alternate mode, DP over TBT,
 - DP on legacy connector - DDIC/D/E/F)

v2 (from Paulo): Remove misleading comment (Ville).

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Reviewed-by: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: James Ausmus <james.ausmus@intel.com>
[Paulo: bikeshed to keep future platforms on "else", v2.]
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611222655.5696-1-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_dp.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 67875b00c8df..af5314229ffe 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -256,6 +256,17 @@ static int cnl_max_source_rate(struct intel_dp *intel_dp)
 	return 810000;
 }
 
+static int icl_max_source_rate(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
+	enum port port = dig_port->base.port;
+
+	if (port == PORT_B)
+		return 540000;
+
+	return 810000;
+}
+
 static void
 intel_dp_set_source_rates(struct intel_dp *intel_dp)
 {
@@ -285,10 +296,13 @@ intel_dp_set_source_rates(struct intel_dp *intel_dp)
 	/* This should only be done once */
 	WARN_ON(intel_dp->source_rates || intel_dp->num_source_rates);
 
-	if (IS_CANNONLAKE(dev_priv)) {
+	if (INTEL_GEN(dev_priv) >= 10) {
 		source_rates = cnl_rates;
 		size = ARRAY_SIZE(cnl_rates);
-		max_rate = cnl_max_source_rate(intel_dp);
+		if (INTEL_GEN(dev_priv) == 10)
+			max_rate = cnl_max_source_rate(intel_dp);
+		else
+			max_rate = icl_max_source_rate(intel_dp);
 	} else if (IS_GEN9_LP(dev_priv)) {
 		source_rates = bxt_rates;
 		size = ARRAY_SIZE(bxt_rates);
-- 
cgit v1.2.3


From 2edd53272120ea3fd32193ef7f921580a534e218 Mon Sep 17 00:00:00 2001
From: Manasi Navare <manasi.d.navare@intel.com>
Date: Mon, 11 Jun 2018 15:26:55 -0700
Subject: drm/i915/dp: Add support for HBR3 and TPS4 during link training

DP spec 1.4 supports training pattern set 4 (TPS4) for HBR3 link
rate. This will be used in link training's channel equalization
phase if supported by both source and sink.
This patch adds the helpers to check if HBR3 is supported and uses
TPS4 in training pattern selection during link training.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Reviewed-by: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611222655.5696-2-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h               |  1 +
 drivers/gpu/drm/i915/intel_dp.c               | 17 +++++++++---
 drivers/gpu/drm/i915/intel_dp_link_training.c | 39 +++++++++++++++++++--------
 drivers/gpu/drm/i915/intel_drv.h              |  1 +
 4 files changed, 44 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index dd6076188319..b8c0ebd50889 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -8703,6 +8703,7 @@ enum skl_power_gate {
 #define  DP_TP_CTL_LINK_TRAIN_PAT1		(0<<8)
 #define  DP_TP_CTL_LINK_TRAIN_PAT2		(1<<8)
 #define  DP_TP_CTL_LINK_TRAIN_PAT3		(4<<8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT4		(5<<8)
 #define  DP_TP_CTL_LINK_TRAIN_IDLE		(2<<8)
 #define  DP_TP_CTL_LINK_TRAIN_NORMAL		(3<<8)
 #define  DP_TP_CTL_SCRAMBLE_DISABLE		(1<<7)
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index af5314229ffe..afa0574c1908 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -1565,6 +1565,13 @@ bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp)
 	return max_rate >= 540000;
 }
 
+bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp)
+{
+	int max_rate = intel_dp->source_rates[intel_dp->num_source_rates - 1];
+
+	return max_rate >= 810000;
+}
+
 static void
 intel_dp_set_clock(struct intel_encoder *encoder,
 		   struct intel_crtc_state *pipe_config)
@@ -2889,10 +2896,11 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	enum port port = intel_dig_port->base.port;
+	uint8_t train_pat_mask = drm_dp_training_pattern_mask(intel_dp->dpcd);
 
-	if (dp_train_pat & DP_TRAINING_PATTERN_MASK)
+	if (dp_train_pat & train_pat_mask)
 		DRM_DEBUG_KMS("Using DP training pattern TPS%d\n",
-			      dp_train_pat & DP_TRAINING_PATTERN_MASK);
+			      dp_train_pat & train_pat_mask);
 
 	if (HAS_DDI(dev_priv)) {
 		uint32_t temp = I915_READ(DP_TP_CTL(port));
@@ -2903,7 +2911,7 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 			temp &= ~DP_TP_CTL_SCRAMBLE_DISABLE;
 
 		temp &= ~DP_TP_CTL_LINK_TRAIN_MASK;
-		switch (dp_train_pat & DP_TRAINING_PATTERN_MASK) {
+		switch (dp_train_pat & train_pat_mask) {
 		case DP_TRAINING_PATTERN_DISABLE:
 			temp |= DP_TP_CTL_LINK_TRAIN_NORMAL;
 
@@ -2917,6 +2925,9 @@ _intel_dp_set_link_train(struct intel_dp *intel_dp,
 		case DP_TRAINING_PATTERN_3:
 			temp |= DP_TP_CTL_LINK_TRAIN_PAT3;
 			break;
+		case DP_TRAINING_PATTERN_4:
+			temp |= DP_TP_CTL_LINK_TRAIN_PAT4;
+			break;
 		}
 		I915_WRITE(DP_TP_CTL(port), temp);
 
diff --git a/drivers/gpu/drm/i915/intel_dp_link_training.c b/drivers/gpu/drm/i915/intel_dp_link_training.c
index 3fcaa98b9055..4da6e33c7fa1 100644
--- a/drivers/gpu/drm/i915/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/intel_dp_link_training.c
@@ -219,14 +219,30 @@ intel_dp_link_training_clock_recovery(struct intel_dp *intel_dp)
 }
 
 /*
- * Pick training pattern for channel equalization. Training Pattern 3 for HBR2
+ * Pick training pattern for channel equalization. Training pattern 4 for HBR3
+ * or for 1.4 devices that support it, training Pattern 3 for HBR2
  * or 1.2 devices that support it, Training Pattern 2 otherwise.
  */
 static u32 intel_dp_training_pattern(struct intel_dp *intel_dp)
 {
-	u32 training_pattern = DP_TRAINING_PATTERN_2;
-	bool source_tps3, sink_tps3;
+	bool source_tps3, sink_tps3, source_tps4, sink_tps4;
 
+	/*
+	 * Intel platforms that support HBR3 also support TPS4. It is mandatory
+	 * for all downstream devices that support HBR3. There are no known eDP
+	 * panels that support TPS4 as of Feb 2018 as per VESA eDP_v1.4b_E1
+	 * specification.
+	 */
+	source_tps4 = intel_dp_source_supports_hbr3(intel_dp);
+	sink_tps4 = drm_dp_tps4_supported(intel_dp->dpcd);
+	if (source_tps4 && sink_tps4) {
+		return DP_TRAINING_PATTERN_4;
+	} else if (intel_dp->link_rate == 810000) {
+		if (!source_tps4)
+			DRM_DEBUG_KMS("8.1 Gbps link rate without source HBR3/TPS4 support\n");
+		if (!sink_tps4)
+			DRM_DEBUG_KMS("8.1 Gbps link rate without sink TPS4 support\n");
+	}
 	/*
 	 * Intel platforms that support HBR2 also support TPS3. TPS3 support is
 	 * also mandatory for downstream devices that support HBR2. However, not
@@ -234,17 +250,16 @@ static u32 intel_dp_training_pattern(struct intel_dp *intel_dp)
 	 */
 	source_tps3 = intel_dp_source_supports_hbr2(intel_dp);
 	sink_tps3 = drm_dp_tps3_supported(intel_dp->dpcd);
-
 	if (source_tps3 && sink_tps3) {
-		training_pattern = DP_TRAINING_PATTERN_3;
-	} else if (intel_dp->link_rate == 540000) {
+		return  DP_TRAINING_PATTERN_3;
+	} else if (intel_dp->link_rate >= 540000) {
 		if (!source_tps3)
-			DRM_DEBUG_KMS("5.4 Gbps link rate without source HBR2/TPS3 support\n");
+			DRM_DEBUG_KMS(">=5.4/6.48 Gbps link rate without source HBR2/TPS3 support\n");
 		if (!sink_tps3)
-			DRM_DEBUG_KMS("5.4 Gbps link rate without sink TPS3 support\n");
+			DRM_DEBUG_KMS(">=5.4/6.48 Gbps link rate without sink TPS3 support\n");
 	}
 
-	return training_pattern;
+	return DP_TRAINING_PATTERN_2;
 }
 
 static bool
@@ -256,11 +271,13 @@ intel_dp_link_training_channel_equalization(struct intel_dp *intel_dp)
 	bool channel_eq = false;
 
 	training_pattern = intel_dp_training_pattern(intel_dp);
+	/* Scrambling is disabled for TPS2/3 and enabled for TPS4 */
+	if (training_pattern != DP_TRAINING_PATTERN_4)
+		training_pattern |= DP_LINK_SCRAMBLING_DISABLE;
 
 	/* channel equalization */
 	if (!intel_dp_set_link_train(intel_dp,
-				     training_pattern |
-				     DP_LINK_SCRAMBLING_DISABLE)) {
+				     training_pattern)) {
 		DRM_ERROR("failed to start channel equalization\n");
 		return false;
 	}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 8641583842be..fd2e4de77697 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1715,6 +1715,7 @@ intel_dp_pre_emphasis_max(struct intel_dp *intel_dp, uint8_t voltage_swing);
 void intel_dp_compute_rate(struct intel_dp *intel_dp, int port_clock,
 			   uint8_t *link_bw, uint8_t *rate_select);
 bool intel_dp_source_supports_hbr2(struct intel_dp *intel_dp);
+bool intel_dp_source_supports_hbr3(struct intel_dp *intel_dp);
 bool
 intel_dp_get_link_status(struct intel_dp *intel_dp, uint8_t link_status[DP_LINK_STATUS_SIZE]);
 
-- 
cgit v1.2.3


From 1d211d43167690f94f1bcadf44395799382d85d0 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 23 May 2018 14:53:41 +0200
Subject: cfg80211: use better order for kcalloc() arguments

The arguments should be (# of elements, size of each) instead
of the other way around, which really ends up being mostly
equivalent but smatch complains about it, so swap them.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 net/wireless/util.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/wireless/util.c b/net/wireless/util.c
index b5bb1c309914..b91597a8baa2 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -1789,8 +1789,9 @@ bool cfg80211_does_bw_fit_range(const struct ieee80211_freq_range *freq_range,
 
 int cfg80211_sinfo_alloc_tid_stats(struct station_info *sinfo, gfp_t gfp)
 {
-	sinfo->pertid = kcalloc(sizeof(*(sinfo->pertid)),
-				IEEE80211_NUM_TIDS + 1, gfp);
+	sinfo->pertid = kcalloc(IEEE80211_NUM_TIDS + 1,
+				sizeof(*(sinfo->pertid)),
+				gfp);
 	if (!sinfo->pertid)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From db0a4ad80d3aee6f6e96eddc7ef6a88f4e38d357 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 28 May 2018 15:47:37 +0200
Subject: nl80211: refactor common code in scan flags checks

There's a very common pattern to check for a scan flag and
then reject it if an extended feature flag isn't set, factor
this out into a helper function.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 net/wireless/nl80211.c | 60 ++++++++++++++++++++++++++------------------------
 1 file changed, 31 insertions(+), 29 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 07514ca011b2..6c3ded1223fb 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6861,6 +6861,16 @@ static bool cfg80211_off_channel_oper_allowed(struct wireless_dev *wdev)
 	return regulatory_pre_cac_allowed(wdev->wiphy);
 }
 
+static bool nl80211_check_scan_feat(struct wiphy *wiphy, u32 flags, u32 flag,
+				    enum nl80211_ext_feature_index feat)
+{
+	if (!(flags & flag))
+		return true;
+	if (wiphy_ext_feature_isset(wiphy, feat))
+		return true;
+	return false;
+}
+
 static int
 nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev,
 			 void *request, struct nlattr **attrs,
@@ -6895,15 +6905,27 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev,
 
 	if (((*flags & NL80211_SCAN_FLAG_LOW_PRIORITY) &&
 	     !(wiphy->features & NL80211_FEATURE_LOW_PRIORITY_SCAN)) ||
-	    ((*flags & NL80211_SCAN_FLAG_LOW_SPAN) &&
-	     !wiphy_ext_feature_isset(wiphy,
-				      NL80211_EXT_FEATURE_LOW_SPAN_SCAN)) ||
-	    ((*flags & NL80211_SCAN_FLAG_LOW_POWER) &&
-	     !wiphy_ext_feature_isset(wiphy,
-				      NL80211_EXT_FEATURE_LOW_POWER_SCAN)) ||
-	    ((*flags & NL80211_SCAN_FLAG_HIGH_ACCURACY) &&
-	     !wiphy_ext_feature_isset(wiphy,
-				      NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN)))
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_LOW_SPAN,
+				     NL80211_EXT_FEATURE_LOW_SPAN_SCAN) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_LOW_POWER,
+				     NL80211_EXT_FEATURE_LOW_POWER_SCAN) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_HIGH_ACCURACY,
+				     NL80211_EXT_FEATURE_HIGH_ACCURACY_SCAN) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME,
+				     NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP,
+				     NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION,
+				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE,
+				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE))
 		return -EOPNOTSUPP;
 
 	if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
@@ -6918,26 +6940,6 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev,
 			return err;
 	}
 
-	if ((*flags & NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME) &&
-	    !wiphy_ext_feature_isset(wiphy,
-				     NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME))
-		return -EOPNOTSUPP;
-
-	if ((*flags & NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP) &&
-	   !wiphy_ext_feature_isset(wiphy,
-				    NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP))
-		return -EOPNOTSUPP;
-
-	if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) &&
-	    !wiphy_ext_feature_isset(wiphy,
-				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION))
-		return -EOPNOTSUPP;
-
-	if ((*flags & NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE) &&
-	    !wiphy_ext_feature_isset(wiphy,
-				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE))
-		return -EOPNOTSUPP;
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 00387f321537395f62d5c0eca64c2d7838f39ac3 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 28 May 2018 15:47:38 +0200
Subject: mac80211: add probe request building flags

Add flags to pass through to probe request building and
change the "bool directed" to be one of them.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 net/mac80211/ieee80211_i.h | 12 +++++++++---
 net/mac80211/mlme.c        |  5 +++--
 net/mac80211/scan.c        |  7 ++++---
 net/mac80211/util.c        | 18 ++++++++++--------
 4 files changed, 26 insertions(+), 16 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index d1978aa1c15d..ee2a25d6ecf2 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2031,24 +2031,30 @@ void ieee80211_send_auth(struct ieee80211_sub_if_data *sdata,
 void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata,
 				    const u8 *bssid, u16 stype, u16 reason,
 				    bool send_frame, u8 *frame_buf);
+
+enum {
+	IEEE80211_PROBE_FLAG_DIRECTED		= BIT(0),
+};
+
 int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 			     size_t buffer_len,
 			     struct ieee80211_scan_ies *ie_desc,
 			     const u8 *ie, size_t ie_len,
 			     u8 bands_used, u32 *rate_masks,
-			     struct cfg80211_chan_def *chandef);
+			     struct cfg80211_chan_def *chandef,
+			     u32 flags);
 struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 					  const u8 *src, const u8 *dst,
 					  u32 ratemask,
 					  struct ieee80211_channel *chan,
 					  const u8 *ssid, size_t ssid_len,
 					  const u8 *ie, size_t ie_len,
-					  bool directed);
+					  u32 flags);
 void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
 			      const u8 *src, const u8 *dst,
 			      const u8 *ssid, size_t ssid_len,
 			      const u8 *ie, size_t ie_len,
-			      u32 ratemask, bool directed, u32 tx_flags,
+			      u32 ratemask, u32 flags, u32 tx_flags,
 			      struct ieee80211_channel *channel, bool scan);
 
 u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a59187c016e0..c3f2883cc0ec 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2267,7 +2267,8 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 
 		ieee80211_send_probe_req(sdata, sdata->vif.addr, dst,
 					 ssid + 2, ssid_len, NULL,
-					 0, (u32) -1, true, 0,
+					 0, (u32) -1,
+					 IEEE80211_PROBE_FLAG_DIRECTED, 0,
 					 ifmgd->associated->channel, false);
 		rcu_read_unlock();
 	}
@@ -2370,7 +2371,7 @@ struct sk_buff *ieee80211_ap_probereq_get(struct ieee80211_hw *hw,
 	skb = ieee80211_build_probe_req(sdata, sdata->vif.addr, cbss->bssid,
 					(u32) -1, cbss->channel,
 					ssid + 2, ssid_len,
-					NULL, 0, true);
+					NULL, 0, IEEE80211_PROBE_FLAG_DIRECTED);
 	rcu_read_unlock();
 
 	return skb;
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index a3b1bcc2b461..8e28d8de26aa 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -336,7 +336,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 					 local->hw_scan_ies_bufsize,
 					 &local->hw_scan_req->ies,
 					 req->ie, req->ie_len,
-					 bands_used, req->rates, &chandef);
+					 bands_used, req->rates, &chandef, 0);
 	local->hw_scan_req->req.ie_len = ielen;
 	local->hw_scan_req->req.no_cck = req->no_cck;
 	ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr);
@@ -552,7 +552,7 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 			sdata, local->scan_addr, scan_req->bssid,
 			scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len,
 			scan_req->ie, scan_req->ie_len,
-			scan_req->rates[band], false,
+			scan_req->rates[band], 0,
 			tx_flags, local->hw.conf.chandef.chan, true);
 
 	/*
@@ -1167,7 +1167,8 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 
 	ieee80211_build_preq_ies(local, ie, num_bands * iebufsz,
 				 &sched_scan_ies, req->ie,
-				 req->ie_len, bands_used, rate_masks, &chandef);
+				 req->ie_len, bands_used, rate_masks, &chandef,
+				 0);
 
 	ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies);
 	if (ret == 0) {
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 2d82c88efd0b..fb7264edecad 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1353,7 +1353,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 					 enum nl80211_band band,
 					 u32 rate_mask,
 					 struct cfg80211_chan_def *chandef,
-					 size_t *offset)
+					 size_t *offset, u32 flags)
 {
 	struct ieee80211_supported_band *sband;
 	u8 *pos = buffer, *end = buffer + buffer_len;
@@ -1518,7 +1518,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 			     struct ieee80211_scan_ies *ie_desc,
 			     const u8 *ie, size_t ie_len,
 			     u8 bands_used, u32 *rate_masks,
-			     struct cfg80211_chan_def *chandef)
+			     struct cfg80211_chan_def *chandef,
+			     u32 flags)
 {
 	size_t pos = 0, old_pos = 0, custom_ie_offset = 0;
 	int i;
@@ -1533,7 +1534,8 @@ int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
 							     ie, ie_len, i,
 							     rate_masks[i],
 							     chandef,
-							     &custom_ie_offset);
+							     &custom_ie_offset,
+							     flags);
 			ie_desc->ies[i] = buffer + old_pos;
 			ie_desc->len[i] = pos - old_pos;
 			old_pos = pos;
@@ -1561,7 +1563,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 					  struct ieee80211_channel *chan,
 					  const u8 *ssid, size_t ssid_len,
 					  const u8 *ie, size_t ie_len,
-					  bool directed)
+					  u32 flags)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct cfg80211_chan_def chandef;
@@ -1577,7 +1579,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	 * badly-behaved APs don't respond when this parameter is included.
 	 */
 	chandef.width = sdata->vif.bss_conf.chandef.width;
-	if (directed)
+	if (flags & IEEE80211_PROBE_FLAG_DIRECTED)
 		chandef.chan = NULL;
 	else
 		chandef.chan = chan;
@@ -1591,7 +1593,7 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	ies_len = ieee80211_build_preq_ies(local, skb_tail_pointer(skb),
 					   skb_tailroom(skb), &dummy_ie_desc,
 					   ie, ie_len, BIT(chan->band),
-					   rate_masks, &chandef);
+					   rate_masks, &chandef, flags);
 	skb_put(skb, ies_len);
 
 	if (dst) {
@@ -1609,14 +1611,14 @@ void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
 			      const u8 *src, const u8 *dst,
 			      const u8 *ssid, size_t ssid_len,
 			      const u8 *ie, size_t ie_len,
-			      u32 ratemask, bool directed, u32 tx_flags,
+			      u32 ratemask, u32 flags, u32 tx_flags,
 			      struct ieee80211_channel *channel, bool scan)
 {
 	struct sk_buff *skb;
 
 	skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
 					ssid, ssid_len,
-					ie, ie_len, directed);
+					ie, ie_len, flags);
 	if (skb) {
 		IEEE80211_SKB_CB(skb)->flags |= tx_flags;
 		if (scan)
-- 
cgit v1.2.3


From 45ad683484b61b5859ccb5a93a8254e1b4d20a29 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 28 May 2018 15:47:39 +0200
Subject: mac80211: split ieee80211_send_probe_req()

This function is passed many more parameters in the scan case
than in the MLME case, and differentiates the two cases inside.
Split it up and make both versions static to simplify things.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 net/mac80211/ieee80211_i.h |  7 -------
 net/mac80211/mlme.c        | 22 +++++++++++++++++-----
 net/mac80211/scan.c        | 22 ++++++++++++++++++++--
 net/mac80211/util.c        | 21 ---------------------
 4 files changed, 37 insertions(+), 35 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index ee2a25d6ecf2..2851245c569a 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2050,13 +2050,6 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 					  const u8 *ssid, size_t ssid_len,
 					  const u8 *ie, size_t ie_len,
 					  u32 flags);
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
-			      const u8 *src, const u8 *dst,
-			      const u8 *ssid, size_t ssid_len,
-			      const u8 *ie, size_t ie_len,
-			      u32 ratemask, u32 flags, u32 tx_flags,
-			      struct ieee80211_channel *channel, bool scan);
-
 u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 			    struct ieee802_11_elems *elems,
 			    enum nl80211_band band, u32 *basic_rates);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index c3f2883cc0ec..a44e5b4aaeda 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -2219,6 +2219,20 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata,
 		ieee80211_sta_reset_conn_monitor(sdata);
 }
 
+static void ieee80211_mlme_send_probe_req(struct ieee80211_sub_if_data *sdata,
+					  const u8 *src, const u8 *dst,
+					  const u8 *ssid, size_t ssid_len,
+					  struct ieee80211_channel *channel)
+{
+	struct sk_buff *skb;
+
+	skb = ieee80211_build_probe_req(sdata, src, dst, (u32)-1, channel,
+					ssid, ssid_len, NULL, 0,
+					IEEE80211_PROBE_FLAG_DIRECTED);
+	if (skb)
+		ieee80211_tx_skb(sdata, skb);
+}
+
 static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -2265,11 +2279,9 @@ static void ieee80211_mgd_probe_ap_send(struct ieee80211_sub_if_data *sdata)
 		else
 			ssid_len = ssid[1];
 
-		ieee80211_send_probe_req(sdata, sdata->vif.addr, dst,
-					 ssid + 2, ssid_len, NULL,
-					 0, (u32) -1,
-					 IEEE80211_PROBE_FLAG_DIRECTED, 0,
-					 ifmgd->associated->channel, false);
+		ieee80211_mlme_send_probe_req(sdata, sdata->vif.addr, dst,
+					      ssid + 2, ssid_len,
+					      ifmgd->associated->channel);
 		rcu_read_unlock();
 	}
 
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 8e28d8de26aa..03f66f31c5b4 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -528,6 +528,24 @@ void ieee80211_run_deferred_scan(struct ieee80211_local *local)
 				     round_jiffies_relative(0));
 }
 
+static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata,
+					  const u8 *src, const u8 *dst,
+					  const u8 *ssid, size_t ssid_len,
+					  const u8 *ie, size_t ie_len,
+					  u32 ratemask, u32 flags, u32 tx_flags,
+					  struct ieee80211_channel *channel)
+{
+	struct sk_buff *skb;
+
+	skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
+					ssid, ssid_len,
+					ie, ie_len, flags);
+	if (skb) {
+		IEEE80211_SKB_CB(skb)->flags |= tx_flags;
+		ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band);
+	}
+}
+
 static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 					    unsigned long *next_delay)
 {
@@ -548,12 +566,12 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 					  lockdep_is_held(&local->mtx));
 
 	for (i = 0; i < scan_req->n_ssids; i++)
-		ieee80211_send_probe_req(
+		ieee80211_send_scan_probe_req(
 			sdata, local->scan_addr, scan_req->bssid,
 			scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len,
 			scan_req->ie, scan_req->ie_len,
 			scan_req->rates[band], 0,
-			tx_flags, local->hw.conf.chandef.chan, true);
+			tx_flags, local->hw.conf.chandef.chan);
 
 	/*
 	 * After sending probe requests, wait for probe responses
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index fb7264edecad..0325133552ad 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1607,27 +1607,6 @@ struct sk_buff *ieee80211_build_probe_req(struct ieee80211_sub_if_data *sdata,
 	return skb;
 }
 
-void ieee80211_send_probe_req(struct ieee80211_sub_if_data *sdata,
-			      const u8 *src, const u8 *dst,
-			      const u8 *ssid, size_t ssid_len,
-			      const u8 *ie, size_t ie_len,
-			      u32 ratemask, u32 flags, u32 tx_flags,
-			      struct ieee80211_channel *channel, bool scan)
-{
-	struct sk_buff *skb;
-
-	skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
-					ssid, ssid_len,
-					ie, ie_len, flags);
-	if (skb) {
-		IEEE80211_SKB_CB(skb)->flags |= tx_flags;
-		if (scan)
-			ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band);
-		else
-			ieee80211_tx_skb(sdata, skb);
-	}
-}
-
 u32 ieee80211_sta_get_rates(struct ieee80211_sub_if_data *sdata,
 			    struct ieee802_11_elems *elems,
 			    enum nl80211_band band, u32 *basic_rates)
-- 
cgit v1.2.3


From 2e076f199097d670ce5e5492cea57f552b93bba9 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 28 May 2018 15:47:40 +0200
Subject: nl80211: add scan features for improved scan privacy

Add the scan flags for randomized SN and minimized probe request
content for improved scan privacy.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 include/uapi/linux/nl80211.h | 15 +++++++++++++++
 net/wireless/nl80211.c       |  8 +++++++-
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 28b36545de24..49f718e821a3 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -5133,6 +5133,11 @@ enum nl80211_feature_flags {
  *	support to nl80211.
  * @NL80211_EXT_FEATURE_TXQS: Driver supports FQ-CoDel-enabled intermediate
  *      TXQs.
+ * @NL80211_EXT_FEATURE_SCAN_RANDOM_SN: Driver/device supports randomizing the
+ *	SN in probe request frames if requested by %NL80211_SCAN_FLAG_RANDOM_SN.
+ * @NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT: Driver/device can omit all data
+ *	except for supported rates from the probe request content if requested
+ *	by the %NL80211_SCAN_FLAG_MIN_PREQ_CONTENT flag.
  *
  * @NUM_NL80211_EXT_FEATURES: number of extended features.
  * @MAX_NL80211_EXT_FEATURES: highest extended feature index.
@@ -5167,6 +5172,8 @@ enum nl80211_ext_feature_index {
 	NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211,
 	NL80211_EXT_FEATURE_DATA_ACK_SIGNAL_SUPPORT,
 	NL80211_EXT_FEATURE_TXQS,
+	NL80211_EXT_FEATURE_SCAN_RANDOM_SN,
+	NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT,
 
 	/* add new features before the definition below */
 	NUM_NL80211_EXT_FEATURES,
@@ -5272,6 +5279,12 @@ enum nl80211_timeout_reason {
  *	possible scan results. This flag hints the driver to use the best
  *	possible scan configuration to improve the accuracy in scanning.
  *	Latency and power use may get impacted with this flag.
+ * @NL80211_SCAN_FLAG_RANDOM_SN: randomize the sequence number in probe
+ *	request frames from this scan to avoid correlation/tracking being
+ *	possible.
+ * @NL80211_SCAN_FLAG_MIN_PREQ_CONTENT: minimize probe request content to
+ *	only have supported rates and no additional capabilities (unless
+ *	added by userspace explicitly.)
  */
 enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_LOW_PRIORITY				= 1<<0,
@@ -5285,6 +5298,8 @@ enum nl80211_scan_flags {
 	NL80211_SCAN_FLAG_LOW_SPAN				= 1<<8,
 	NL80211_SCAN_FLAG_LOW_POWER				= 1<<9,
 	NL80211_SCAN_FLAG_HIGH_ACCURACY				= 1<<10,
+	NL80211_SCAN_FLAG_RANDOM_SN				= 1<<11,
+	NL80211_SCAN_FLAG_MIN_PREQ_CONTENT			= 1<<12,
 };
 
 /**
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 6c3ded1223fb..d2677259e13e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6925,7 +6925,13 @@ nl80211_check_scan_flags(struct wiphy *wiphy, struct wireless_dev *wdev,
 				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_DEFERRAL_SUPPRESSION) ||
 	    !nl80211_check_scan_feat(wiphy, *flags,
 				     NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE,
-				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE))
+				     NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_RANDOM_SN,
+				     NL80211_EXT_FEATURE_SCAN_RANDOM_SN) ||
+	    !nl80211_check_scan_feat(wiphy, *flags,
+				     NL80211_SCAN_FLAG_MIN_PREQ_CONTENT,
+				     NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT))
 		return -EOPNOTSUPP;
 
 	if (*flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
-- 
cgit v1.2.3


From b9771d41aee7aa3207b985422a1cc19e8342bc50 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 28 May 2018 15:47:41 +0200
Subject: mac80211: support scan features for improved scan privacy

Support the new random SN and minimal probe request contents
scan flags for the case of software scan - for hardware scan
the drivers need to opt in, but may need to do only that,
depending on their implementation.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 net/mac80211/cfg.c         |  2 +-
 net/mac80211/ieee80211_i.h | 14 +++++++++-----
 net/mac80211/main.c        | 13 +++++++++++--
 net/mac80211/offchannel.c  |  2 +-
 net/mac80211/rx.c          |  2 +-
 net/mac80211/scan.c        | 35 ++++++++++++++++++++++++++++++-----
 net/mac80211/sta_info.c    |  2 +-
 net/mac80211/tx.c          | 21 +++++++++++++--------
 net/mac80211/util.c        |  4 ++++
 9 files changed, 71 insertions(+), 24 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index bdf6fa78d0d2..c4e2f7d2bcb8 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -3486,7 +3486,7 @@ static int ieee80211_probe_client(struct wiphy *wiphy, struct net_device *dev,
 	}
 
 	local_bh_disable();
-	ieee80211_xmit(sdata, sta, skb);
+	ieee80211_xmit(sdata, sta, skb, 0);
 	local_bh_enable();
 
 	ret = 0;
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 2851245c569a..a6c12c104c38 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -165,6 +165,7 @@ typedef unsigned __bitwise ieee80211_tx_result;
 #define TX_DROP		((__force ieee80211_tx_result) 1u)
 #define TX_QUEUED	((__force ieee80211_tx_result) 2u)
 
+#define IEEE80211_TX_NO_SEQNO		BIT(0)
 #define IEEE80211_TX_UNICAST		BIT(1)
 #define IEEE80211_TX_PS_BUFFERED	BIT(2)
 
@@ -1880,19 +1881,20 @@ void ieee80211_regulatory_limit_wmm_params(struct ieee80211_sub_if_data *sdata,
 void ieee80211_set_wmm_default(struct ieee80211_sub_if_data *sdata,
 			       bool bss_notify, bool enable_qos);
 void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
-		    struct sta_info *sta, struct sk_buff *skb);
+		    struct sta_info *sta, struct sk_buff *skb,
+		    u32 txdata_flags);
 
 void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 				 struct sk_buff *skb, int tid,
-				 enum nl80211_band band);
+				 enum nl80211_band band, u32 txdata_flags);
 
 static inline void
 ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 			  struct sk_buff *skb, int tid,
-			  enum nl80211_band band)
+			  enum nl80211_band band, u32 txdata_flags)
 {
 	rcu_read_lock();
-	__ieee80211_tx_skb_tid_band(sdata, skb, tid, band);
+	__ieee80211_tx_skb_tid_band(sdata, skb, tid, band, txdata_flags);
 	rcu_read_unlock();
 }
 
@@ -1910,7 +1912,7 @@ static inline void ieee80211_tx_skb_tid(struct ieee80211_sub_if_data *sdata,
 	}
 
 	__ieee80211_tx_skb_tid_band(sdata, skb, tid,
-				    chanctx_conf->def.chan->band);
+				    chanctx_conf->def.chan->band, 0);
 	rcu_read_unlock();
 }
 
@@ -2034,6 +2036,8 @@ void ieee80211_send_deauth_disassoc(struct ieee80211_sub_if_data *sdata,
 
 enum {
 	IEEE80211_PROBE_FLAG_DIRECTED		= BIT(0),
+	IEEE80211_PROBE_FLAG_MIN_CONTENT	= BIT(1),
+	IEEE80211_PROBE_FLAG_RANDOM_SN		= BIT(2),
 };
 
 int ieee80211_build_preq_ies(struct ieee80211_local *local, u8 *buffer,
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 4d2e797e3f16..a6f8e3a646d4 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -557,10 +557,19 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
 	wiphy_ext_feature_set(wiphy,
 			      NL80211_EXT_FEATURE_CONTROL_PORT_OVER_NL80211);
 
-	if (!ops->hw_scan)
+	if (!ops->hw_scan) {
 		wiphy->features |= NL80211_FEATURE_LOW_PRIORITY_SCAN |
 				   NL80211_FEATURE_AP_SCAN;
-
+		/*
+		 * if the driver behaves correctly using the probe request
+		 * (template) from mac80211, then both of these should be
+		 * supported even with hw scan - but let drivers opt in.
+		 */
+		wiphy_ext_feature_set(wiphy,
+				      NL80211_EXT_FEATURE_SCAN_RANDOM_SN);
+		wiphy_ext_feature_set(wiphy,
+				      NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT);
+	}
 
 	if (!ops->set_key)
 		wiphy->flags |= WIPHY_FLAG_IBSS_RSN;
diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
index f1d40b6645ff..8ef4153cd299 100644
--- a/net/mac80211/offchannel.c
+++ b/net/mac80211/offchannel.c
@@ -262,7 +262,7 @@ static void ieee80211_handle_roc_started(struct ieee80211_roc_work *roc,
 	if (roc->mgmt_tx_cookie) {
 		if (!WARN_ON(!roc->frame)) {
 			ieee80211_tx_skb_tid_band(roc->sdata, roc->frame, 7,
-						  roc->chan->band);
+						  roc->chan->band, 0);
 			roc->frame = NULL;
 		}
 	} else {
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 0a38cc1cbebc..756ba176db1e 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3241,7 +3241,7 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx)
 		}
 
 		__ieee80211_tx_skb_tid_band(rx->sdata, nskb, 7,
-					    status->band);
+					    status->band, 0);
 	}
 	dev_kfree_skb(rx->skb);
 	return RX_QUEUED;
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 03f66f31c5b4..ae77d1c12856 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -20,6 +20,7 @@
 #include <net/sch_generic.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/random.h>
 #include <net/mac80211.h>
 
 #include "ieee80211_i.h"
@@ -293,6 +294,7 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 	struct cfg80211_chan_def chandef;
 	u8 bands_used = 0;
 	int i, ielen, n_chans;
+	u32 flags = 0;
 
 	req = rcu_dereference_protected(local->scan_req,
 					lockdep_is_held(&local->mtx));
@@ -331,12 +333,16 @@ static bool ieee80211_prep_hw_scan(struct ieee80211_local *local)
 	local->hw_scan_req->req.n_channels = n_chans;
 	ieee80211_prepare_scan_chandef(&chandef, req->scan_width);
 
+	if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT)
+		flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT;
+
 	ielen = ieee80211_build_preq_ies(local,
 					 (u8 *)local->hw_scan_req->req.ie,
 					 local->hw_scan_ies_bufsize,
 					 &local->hw_scan_req->ies,
 					 req->ie, req->ie_len,
-					 bands_used, req->rates, &chandef, 0);
+					 bands_used, req->rates, &chandef,
+					 flags);
 	local->hw_scan_req->req.ie_len = ielen;
 	local->hw_scan_req->req.no_cck = req->no_cck;
 	ether_addr_copy(local->hw_scan_req->req.mac_addr, req->mac_addr);
@@ -536,13 +542,24 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata,
 					  struct ieee80211_channel *channel)
 {
 	struct sk_buff *skb;
+	u32 txdata_flags = 0;
 
 	skb = ieee80211_build_probe_req(sdata, src, dst, ratemask, channel,
 					ssid, ssid_len,
 					ie, ie_len, flags);
+
 	if (skb) {
+		if (flags & IEEE80211_PROBE_FLAG_RANDOM_SN) {
+			struct ieee80211_hdr *hdr = (void *)skb->data;
+			u16 sn = get_random_u32();
+
+			txdata_flags |= IEEE80211_TX_NO_SEQNO;
+			hdr->seq_ctrl =
+				cpu_to_le16(IEEE80211_SN_TO_SEQ(sn));
+		}
 		IEEE80211_SKB_CB(skb)->flags |= tx_flags;
-		ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band);
+		ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band,
+					  txdata_flags);
 	}
 }
 
@@ -553,7 +570,7 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 	struct ieee80211_sub_if_data *sdata;
 	struct cfg80211_scan_request *scan_req;
 	enum nl80211_band band = local->hw.conf.chandef.chan->band;
-	u32 tx_flags;
+	u32 flags = 0, tx_flags;
 
 	scan_req = rcu_dereference_protected(local->scan_req,
 					     lockdep_is_held(&local->mtx));
@@ -561,6 +578,10 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 	tx_flags = IEEE80211_TX_INTFL_OFFCHAN_TX_OK;
 	if (scan_req->no_cck)
 		tx_flags |= IEEE80211_TX_CTL_NO_CCK_RATE;
+	if (scan_req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT)
+		flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT;
+	if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_SN)
+		flags |= IEEE80211_PROBE_FLAG_RANDOM_SN;
 
 	sdata = rcu_dereference_protected(local->scan_sdata,
 					  lockdep_is_held(&local->mtx));
@@ -570,7 +591,7 @@ static void ieee80211_scan_state_send_probe(struct ieee80211_local *local,
 			sdata, local->scan_addr, scan_req->bssid,
 			scan_req->ssids[i].ssid, scan_req->ssids[i].ssid_len,
 			scan_req->ie, scan_req->ie_len,
-			scan_req->rates[band], 0,
+			scan_req->rates[band], flags,
 			tx_flags, local->hw.conf.chandef.chan);
 
 	/*
@@ -1159,6 +1180,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 	u32 rate_masks[NUM_NL80211_BANDS] = {};
 	u8 bands_used = 0;
 	u8 *ie;
+	u32 flags = 0;
 
 	iebufsz = local->scan_ies_len + req->ie_len;
 
@@ -1175,6 +1197,9 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	if (req->flags & NL80211_SCAN_FLAG_MIN_PREQ_CONTENT)
+		flags |= IEEE80211_PROBE_FLAG_MIN_CONTENT;
+
 	ie = kzalloc(num_bands * iebufsz, GFP_KERNEL);
 	if (!ie) {
 		ret = -ENOMEM;
@@ -1186,7 +1211,7 @@ int __ieee80211_request_sched_scan_start(struct ieee80211_sub_if_data *sdata,
 	ieee80211_build_preq_ies(local, ie, num_bands * iebufsz,
 				 &sched_scan_ies, req->ie,
 				 req->ie_len, bands_used, rate_masks, &chandef,
-				 0);
+				 flags);
 
 	ret = drv_sched_scan_start(local, sdata, req, &sched_scan_ies);
 	if (ret == 0) {
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 6428f1ac37b6..aa96fddfbfc2 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1391,7 +1391,7 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid,
 	}
 
 	info->band = chanctx_conf->def.chan->band;
-	ieee80211_xmit(sdata, sta, skb);
+	ieee80211_xmit(sdata, sta, skb, 0);
 	rcu_read_unlock();
 }
 
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 44b5dfe8727d..5b93bde248fd 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -825,6 +825,8 @@ ieee80211_tx_h_sequence(struct ieee80211_tx_data *tx)
 	 */
 	if (!ieee80211_is_data_qos(hdr->frame_control) ||
 	    is_multicast_ether_addr(hdr->addr1)) {
+		if (tx->flags & IEEE80211_TX_NO_SEQNO)
+			return TX_CONTINUE;
 		/* driver should assign sequence number */
 		info->flags |= IEEE80211_TX_CTL_ASSIGN_SEQ;
 		/* for pure STA mode without beacons, we can do it */
@@ -1854,7 +1856,7 @@ EXPORT_SYMBOL(ieee80211_tx_prepare_skb);
  */
 static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 			 struct sta_info *sta, struct sk_buff *skb,
-			 bool txpending)
+			 bool txpending, u32 txdata_flags)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_data tx;
@@ -1872,6 +1874,8 @@ static bool ieee80211_tx(struct ieee80211_sub_if_data *sdata,
 	led_len = skb->len;
 	res_prepare = ieee80211_tx_prepare(sdata, &tx, sta, skb);
 
+	tx.flags |= txdata_flags;
+
 	if (unlikely(res_prepare == TX_DROP)) {
 		ieee80211_free_txskb(&local->hw, skb);
 		return true;
@@ -1933,7 +1937,8 @@ static int ieee80211_skb_resize(struct ieee80211_sub_if_data *sdata,
 }
 
 void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
-		    struct sta_info *sta, struct sk_buff *skb)
+		    struct sta_info *sta, struct sk_buff *skb,
+		    u32 txdata_flags)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -1968,7 +1973,7 @@ void ieee80211_xmit(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ieee80211_set_qos_hdr(sdata, skb);
-	ieee80211_tx(sdata, sta, skb, false);
+	ieee80211_tx(sdata, sta, skb, false, txdata_flags);
 }
 
 static bool ieee80211_parse_tx_radiotap(struct ieee80211_local *local,
@@ -2289,7 +2294,7 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb,
 	if (!ieee80211_parse_tx_radiotap(local, skb))
 		goto fail_rcu;
 
-	ieee80211_xmit(sdata, NULL, skb);
+	ieee80211_xmit(sdata, NULL, skb, 0);
 	rcu_read_unlock();
 
 	return NETDEV_TX_OK;
@@ -3648,7 +3653,7 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb,
 
 		ieee80211_tx_stats(dev, skb->len);
 
-		ieee80211_xmit(sdata, sta, skb);
+		ieee80211_xmit(sdata, sta, skb, 0);
 	}
 	goto out;
  out_free:
@@ -3867,7 +3872,7 @@ static bool ieee80211_tx_pending_skb(struct ieee80211_local *local,
 			return true;
 		}
 		info->band = chanctx_conf->def.chan->band;
-		result = ieee80211_tx(sdata, NULL, skb, true);
+		result = ieee80211_tx(sdata, NULL, skb, true, 0);
 	} else {
 		struct sk_buff_head skbs;
 
@@ -4783,7 +4788,7 @@ EXPORT_SYMBOL(ieee80211_unreserve_tid);
 
 void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 				 struct sk_buff *skb, int tid,
-				 enum nl80211_band band)
+				 enum nl80211_band band, u32 txdata_flags)
 {
 	int ac = ieee80211_ac_from_tid(tid);
 
@@ -4800,7 +4805,7 @@ void __ieee80211_tx_skb_tid_band(struct ieee80211_sub_if_data *sdata,
 	 */
 	local_bh_disable();
 	IEEE80211_SKB_CB(skb)->band = band;
-	ieee80211_xmit(sdata, NULL, skb);
+	ieee80211_xmit(sdata, NULL, skb, txdata_flags);
 	local_bh_enable();
 }
 
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 0325133552ad..b744b10465c3 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1433,6 +1433,9 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 				chandef->chan->center_freq);
 	}
 
+	if (flags & IEEE80211_PROBE_FLAG_MIN_CONTENT)
+		goto done;
+
 	/* insert custom IEs that go before HT */
 	if (ie && ie_len) {
 		static const u8 before_ht[] = {
@@ -1510,6 +1513,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 	return pos - buffer;
  out_err:
 	WARN_ONCE(1, "not enough space for preq IEs\n");
+ done:
 	return pos - buffer;
 }
 
-- 
cgit v1.2.3


From e529f4d651595fa6c007d3ddeaccf22babbf083c Mon Sep 17 00:00:00 2001
From: Peter Meerwald <pmeerw@pmeerw.net>
Date: Mon, 4 Jun 2018 22:32:43 +0200
Subject: rfkill: Correctly document rkill subfolder range as >= 0 in
 sysfs-class-rfkill

The first subfolder is rfkill0, hence rfkillX (X >= 0).
Also fix two trivial typos.

Signed-off-by: Peter Meerwald-Stadler <pmeerw@pmeerw.net>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 Documentation/ABI/stable/sysfs-class-rfkill | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/ABI/stable/sysfs-class-rfkill b/Documentation/ABI/stable/sysfs-class-rfkill
index e1ba4a104753..80151a409d67 100644
--- a/Documentation/ABI/stable/sysfs-class-rfkill
+++ b/Documentation/ABI/stable/sysfs-class-rfkill
@@ -11,7 +11,7 @@ KernelVersion:	v2.6.22
 Contact:	linux-wireless@vger.kernel.org,
 Description: 	The rfkill class subsystem folder.
 		Each registered rfkill driver is represented by an rfkillX
-		subfolder (X being an integer > 0).
+		subfolder (X being an integer >= 0).
 
 
 What:		/sys/class/rfkill/rfkill[0-9]+/name
@@ -48,8 +48,8 @@ Contact:	linux-wireless@vger.kernel.org
 Description: 	Current state of the transmitter.
 		This file was scheduled to be removed in 2014, but due to its
 		large number of users it will be sticking around for a bit
-		longer. Despite it being marked as stabe, the newer "hard" and
-		"soft" interfaces should be preffered, since it is not possible
+		longer. Despite it being marked as stable, the newer "hard" and
+		"soft" interfaces should be preferred, since it is not possible
 		to express the 'soft and hard block' state of the rfkill driver
 		through this interface. There will likely be another attempt to
 		remove it in the future.
-- 
cgit v1.2.3


From cba340fa89bc9834cf8ac648c060f45ee955beb4 Mon Sep 17 00:00:00 2001
From: Peter Meerwald <pmeerw@pmeerw.net>
Date: Mon, 4 Jun 2018 23:02:03 +0200
Subject: rfkill: Fix several typos in documentation

Signed-off-by: Peter Meerwald-Stadler <pmeerw@pmeerw.net>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 Documentation/rfkill.txt | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/Documentation/rfkill.txt b/Documentation/rfkill.txt
index a289285d2412..7d3684e81df6 100644
--- a/Documentation/rfkill.txt
+++ b/Documentation/rfkill.txt
@@ -9,7 +9,7 @@ rfkill - RF kill switch support
 Introduction
 ============
 
-The rfkill subsystem provides a generic interface to disabling any radio
+The rfkill subsystem provides a generic interface for disabling any radio
 transmitter in the system. When a transmitter is blocked, it shall not
 radiate any power.
 
@@ -45,7 +45,7 @@ The rfkill subsystem is composed of three main components:
  * the rfkill drivers.
 
 The rfkill core provides API for kernel drivers to register their radio
-transmitter with the kernel, methods for turning it on and off and, letting
+transmitter with the kernel, methods for turning it on and off, and letting
 the system know about hardware-disabled states that may be implemented on
 the device.
 
@@ -54,7 +54,7 @@ ways for userspace to query the current states. See the "Userspace support"
 section below.
 
 When the device is hard-blocked (either by a call to rfkill_set_hw_state()
-or from query_hw_block) set_block() will be invoked for additional software
+or from query_hw_block), set_block() will be invoked for additional software
 block, but drivers can ignore the method call since they can use the return
 value of the function rfkill_set_hw_state() to sync the software state
 instead of keeping track of calls to set_block(). In fact, drivers should
@@ -65,7 +65,6 @@ keeps track of soft and hard block separately.
 Kernel API
 ==========
 
-
 Drivers for radio transmitters normally implement an rfkill driver.
 
 Platform drivers might implement input devices if the rfkill button is just
@@ -75,14 +74,14 @@ a way to turn on/off the transmitter(s).
 
 For some platforms, it is possible that the hardware state changes during
 suspend/hibernation, in which case it will be necessary to update the rfkill
-core with the current state is at resume time.
+core with the current state at resume time.
 
 To create an rfkill driver, driver's Kconfig needs to have::
 
 	depends on RFKILL || !RFKILL
 
 to ensure the driver cannot be built-in when rfkill is modular. The !RFKILL
-case allows the driver to be built when rfkill is not configured, which
+case allows the driver to be built when rfkill is not configured, in which
 case all rfkill API can still be used but will be provided by static inlines
 which compile to almost nothing.
 
@@ -91,7 +90,7 @@ rfkill drivers that control devices that can be hard-blocked unless they also
 assign the poll_hw_block() callback (then the rfkill core will poll the
 device). Don't do this unless you cannot get the event in any other way.
 
-RFKill provides per-switch LED triggers, which can be used to drive LEDs
+rfkill provides per-switch LED triggers, which can be used to drive LEDs
 according to the switch state (LED_FULL when blocked, LED_OFF otherwise).
 
 
@@ -114,7 +113,7 @@ a specified type) into a state which also updates the default state for
 hotplugged devices.
 
 After an application opens /dev/rfkill, it can read the current state of all
-devices. Changes can be either obtained by either polling the descriptor for
+devices. Changes can be obtained by either polling the descriptor for
 hotplug or state change events or by listening for uevents emitted by the
 rfkill core framework.
 
@@ -127,8 +126,7 @@ environment variables set::
 	RFKILL_STATE
 	RFKILL_TYPE
 
-The contents of these variables corresponds to the "name", "state" and
+The content of these variables corresponds to the "name", "state" and
 "type" sysfs files explained above.
 
-
 For further details consult Documentation/ABI/stable/sysfs-class-rfkill.
-- 
cgit v1.2.3


From 2d4f545cb14fa2d9865124183f3100d46dc9b3b5 Mon Sep 17 00:00:00 2001
From: Peter Meerwald <pmeerw@pmeerw.net>
Date: Mon, 4 Jun 2018 23:34:06 +0200
Subject: rfkill: Fixes and cleanup of kernel-doc in the header file

Fixes kerneldoc parameter names to match implementation,
rfkill_set_hw_state(), rfkill_set_sw_state().
Fix description of rfkill_resume_polling().
Fix typos in documentation of rfkill_find_type().
Consistently start kerneldoc description with uppercase
letter.

Signed-off-by: Peter Meerwald-Stadler <pmeerw@pmeerw.net>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 include/linux/rfkill.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h
index e6a0031d1b1f..8ad2487a86d5 100644
--- a/include/linux/rfkill.h
+++ b/include/linux/rfkill.h
@@ -66,7 +66,7 @@ struct rfkill_ops {
 
 #if defined(CONFIG_RFKILL) || defined(CONFIG_RFKILL_MODULE)
 /**
- * rfkill_alloc - allocate rfkill structure
+ * rfkill_alloc - Allocate rfkill structure
  * @name: name of the struct -- the string is not copied internally
  * @parent: device that has rf switch on it
  * @type: type of the switch (RFKILL_TYPE_*)
@@ -112,7 +112,7 @@ void rfkill_pause_polling(struct rfkill *rfkill);
 /**
  * rfkill_resume_polling(struct rfkill *rfkill)
  *
- * Pause polling -- say transmitter is off for other reasons.
+ * Resume polling
  * NOTE: not necessary for suspend/resume -- in that case the
  * core stops polling anyway
  */
@@ -130,7 +130,7 @@ void rfkill_resume_polling(struct rfkill *rfkill);
 void rfkill_unregister(struct rfkill *rfkill);
 
 /**
- * rfkill_destroy - free rfkill structure
+ * rfkill_destroy - Free rfkill structure
  * @rfkill: rfkill structure to be destroyed
  *
  * Destroys the rfkill structure.
@@ -140,7 +140,7 @@ void rfkill_destroy(struct rfkill *rfkill);
 /**
  * rfkill_set_hw_state - Set the internal rfkill hardware block state
  * @rfkill: pointer to the rfkill class to modify.
- * @state: the current hardware block state to set
+ * @blocked: the current hardware block state to set
  *
  * rfkill drivers that get events when the hard-blocked state changes
  * use this function to notify the rfkill core (and through that also
@@ -161,7 +161,7 @@ bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked);
 /**
  * rfkill_set_sw_state - Set the internal rfkill software block state
  * @rfkill: pointer to the rfkill class to modify.
- * @state: the current software block state to set
+ * @blocked: the current software block state to set
  *
  * rfkill drivers that get events when the soft-blocked state changes
  * (yes, some platforms directly act on input but allow changing again)
@@ -183,7 +183,7 @@ bool rfkill_set_sw_state(struct rfkill *rfkill, bool blocked);
 /**
  * rfkill_init_sw_state - Initialize persistent software block state
  * @rfkill: pointer to the rfkill class to modify.
- * @state: the current software block state to set
+ * @blocked: the current software block state to set
  *
  * rfkill drivers that preserve their software block state over power off
  * use this function to notify the rfkill core (and through that also
@@ -208,17 +208,17 @@ void rfkill_init_sw_state(struct rfkill *rfkill, bool blocked);
 void rfkill_set_states(struct rfkill *rfkill, bool sw, bool hw);
 
 /**
- * rfkill_blocked - query rfkill block
+ * rfkill_blocked - Query rfkill block state
  *
  * @rfkill: rfkill struct to query
  */
 bool rfkill_blocked(struct rfkill *rfkill);
 
 /**
- * rfkill_find_type - Helpper for finding rfkill type by name
+ * rfkill_find_type - Helper for finding rfkill type by name
  * @name: the name of the type
  *
- * Returns enum rfkill_type that conrresponds the name.
+ * Returns enum rfkill_type that corresponds to the name.
  */
 enum rfkill_type rfkill_find_type(const char *name);
 
@@ -296,7 +296,7 @@ static inline enum rfkill_type rfkill_find_type(const char *name)
 const char *rfkill_get_led_trigger_name(struct rfkill *rfkill);
 
 /**
- * rfkill_set_led_trigger_name -- set the LED trigger name
+ * rfkill_set_led_trigger_name - Set the LED trigger name
  * @rfkill: rfkill struct
  * @name: LED trigger name
  *
-- 
cgit v1.2.3


From 446faa15c6e80620826edd659e63c6760137975a Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <a@unstable.cc>
Date: Thu, 14 Jun 2018 09:43:06 +0800
Subject: nl80211: report 4ADDR status with GET_INTERFACE

User space tools might be interested in knowing the current
status of the 4ADDR property of an interface (when supported).

Send the status along with the other attributes when replying
to a GET_INTERFACE netlink query.

Signed-off-by: Antonio Quartulli <a@unstable.cc>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 net/wireless/nl80211.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d2677259e13e..7b21914ae18b 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2757,7 +2757,8 @@ static int nl80211_send_iface(struct sk_buff *msg, u32 portid, u32 seq, int flag
 	    nla_put(msg, NL80211_ATTR_MAC, ETH_ALEN, wdev_address(wdev)) ||
 	    nla_put_u32(msg, NL80211_ATTR_GENERATION,
 			rdev->devlist_generation ^
-			(cfg80211_rdev_list_generation << 2)))
+			(cfg80211_rdev_list_generation << 2)) ||
+	    nla_put_u8(msg, NL80211_ATTR_4ADDR, wdev->use_4addr))
 		goto nla_put_failure;
 
 	if (rdev->ops->get_channel) {
-- 
cgit v1.2.3


From c4cbaf7973a794839af080f13748335976cf3f3f Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sat, 9 Jun 2018 09:14:42 +0300
Subject: cfg80211: Add support for HE

Add support for the HE in cfg80211 and also add userspace API to
nl80211 to send rate information out, conforming with P802.11ax_D2.0.

Signed-off-by: Liad Kaufman <liad.kaufman@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Ido Yariv <idox.yariv@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 include/linux/ieee80211.h    | 427 +++++++++++++++++++++++++++++++++++++++++++
 include/net/cfg80211.h       | 106 ++++++++++-
 include/uapi/linux/nl80211.h |  87 ++++++++-
 net/wireless/core.c          |  21 ++-
 net/wireless/nl80211.c       |  99 +++++++++-
 net/wireless/util.c          |  82 +++++++++
 6 files changed, 817 insertions(+), 5 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 8fe7e4306816..e6a6503bfa33 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1539,6 +1539,106 @@ struct ieee80211_vht_operation {
 	__le16 basic_mcs_set;
 } __packed;
 
+/**
+ * struct ieee80211_he_cap_elem - HE capabilities element
+ *
+ * This structure is the "HE capabilities element" fixed fields as
+ * described in P802.11ax_D2.0 section 9.4.2.237.2 and 9.4.2.237.3
+ */
+struct ieee80211_he_cap_elem {
+	u8 mac_cap_info[5];
+	u8 phy_cap_info[9];
+} __packed;
+
+#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN	5
+
+/**
+ * enum ieee80211_he_mcs_support - HE MCS support definitions
+ * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the
+ *	number of streams
+ * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported
+ * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported
+ * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported
+ *
+ * These definitions are used in each 2-bit subfield of the rx_mcs_*
+ * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are
+ * both split into 8 subfields by number of streams. These values indicate
+ * which MCSes are supported for the number of streams the value appears
+ * for.
+ */
+enum ieee80211_he_mcs_support {
+	IEEE80211_HE_MCS_SUPPORT_0_7	= 0,
+	IEEE80211_HE_MCS_SUPPORT_0_9	= 1,
+	IEEE80211_HE_MCS_SUPPORT_0_11	= 2,
+	IEEE80211_HE_MCS_NOT_SUPPORTED	= 3,
+};
+
+/**
+ * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field
+ *
+ * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field
+ * described in P802.11ax_D2.0 section 9.4.2.237.4
+ *
+ * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     widths less than 80MHz.
+ * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     widths less than 80MHz.
+ * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     width 160MHz.
+ * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     width 160MHz.
+ * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for
+ *     channel width 80p80MHz.
+ * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for
+ *     channel width 80p80MHz.
+ */
+struct ieee80211_he_mcs_nss_supp {
+	__le16 rx_mcs_80;
+	__le16 tx_mcs_80;
+	__le16 rx_mcs_160;
+	__le16 tx_mcs_160;
+	__le16 rx_mcs_80p80;
+	__le16 tx_mcs_80p80;
+} __packed;
+
+/**
+ * struct ieee80211_he_operation - HE capabilities element
+ *
+ * This structure is the "HE operation element" fields as
+ * described in P802.11ax_D2.0 section 9.4.2.238
+ */
+struct ieee80211_he_operation {
+	__le32 he_oper_params;
+	__le16 he_mcs_nss_set;
+	/* Optional 0,1,3 or 4 bytes: depends on @he_oper_params */
+	u8 optional[0];
+} __packed;
+
+/**
+ * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field
+ *
+ * This structure is the "MU AC Parameter Record" fields as
+ * described in P802.11ax_D2.0 section 9.4.2.240
+ */
+struct ieee80211_he_mu_edca_param_ac_rec {
+	u8 aifsn;
+	u8 ecw_min_max;
+	u8 mu_edca_timer;
+} __packed;
+
+/**
+ * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element
+ *
+ * This structure is the "MU EDCA Parameter Set element" fields as
+ * described in P802.11ax_D2.0 section 9.4.2.240
+ */
+struct ieee80211_mu_edca_param_set {
+	u8 mu_qos_info;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_be;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_bk;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_vi;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_vo;
+} __packed;
 
 /* 802.11ac VHT Capabilities */
 #define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895			0x00000000
@@ -1577,6 +1677,328 @@ struct ieee80211_vht_operation {
 #define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN			0x10000000
 #define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN			0x20000000
 
+/* 802.11ax HE MAC capabilities */
+#define IEEE80211_HE_MAC_CAP0_HTC_HE				0x01
+#define IEEE80211_HE_MAC_CAP0_TWT_REQ				0x02
+#define IEEE80211_HE_MAC_CAP0_TWT_RES				0x04
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP		0x00
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1		0x08
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2		0x10
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3		0x18
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK			0x18
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1		0x00
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2		0x20
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4		0x40
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8		0x60
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16		0x80
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32		0xa0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64		0xc0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED	0xe0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK		0xe0
+
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED		0x00
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128			0x01
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256			0x02
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512			0x03
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK		0x03
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US		0x00
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US		0x04
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US		0x08
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK		0x0c
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_1		0x00
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_2		0x10
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_3		0x20
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_4		0x30
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_5		0x40
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_6		0x50
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_7		0x60
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8		0x70
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_MASK		0x70
+
+/* Link adaptation is split between byte HE_MAC_CAP1 and
+ * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE
+ * in which case the following values apply:
+ * 0 = No feedback.
+ * 1 = reserved.
+ * 2 = Unsolicited feedback.
+ * 3 = both
+ */
+#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION			0x80
+
+#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION			0x01
+#define IEEE80211_HE_MAC_CAP2_ALL_ACK				0x02
+#define IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED			0x04
+#define IEEE80211_HE_MAC_CAP2_BSR				0x08
+#define IEEE80211_HE_MAC_CAP2_BCAST_TWT				0x10
+#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP			0x20
+#define IEEE80211_HE_MAC_CAP2_MU_CASCADING			0x40
+#define IEEE80211_HE_MAC_CAP2_ACK_EN				0x80
+
+#define IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU	0x01
+#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL			0x02
+#define IEEE80211_HE_MAC_CAP3_OFDMA_RA				0x04
+
+/* The maximum length of an A-MDPU is defined by the combination of the Maximum
+ * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the
+ * same field in the HE capabilities.
+ */
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_USE_VHT	0x00
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_1		0x08
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2		0x10
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_RESERVED	0x18
+#define IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_MASK		0x18
+#define IEEE80211_HE_MAC_CAP3_A_AMSDU_FRAG			0x20
+#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED			0x40
+#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS		0x80
+
+#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG		0x01
+#define IEEE80211_HE_MAC_CAP4_QTP				0x02
+#define IEEE80211_HE_MAC_CAP4_BQR				0x04
+#define IEEE80211_HE_MAC_CAP4_SR_RESP				0x08
+#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP			0x10
+#define IEEE80211_HE_MAC_CAP4_OPS				0x20
+#define IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU			0x40
+
+/* 802.11ax HE PHY capabilities */
+#define IEEE80211_HE_PHY_CAP0_DUAL_BAND					0x01
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G		0x02
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G	0x04
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G		0x08
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G	0x10
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G	0x20
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G	0x40
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK			0xfe
+
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ	0x01
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ	0x02
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ	0x04
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ	0x08
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK			0x0f
+#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A				0x10
+#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD			0x20
+#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US		0x40
+/* Midamble RX Max NSTS is split between byte #2 and byte #3 */
+#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS			0x80
+
+#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS			0x01
+#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US			0x02
+#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ			0x04
+#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ			0x08
+#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX				0x10
+#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX				0x20
+
+/* Note that the meaning of UL MU below is different between an AP and a non-AP
+ * sta, where in the AP case it indicates support for Rx and in the non-AP sta
+ * case it indicates support for Tx.
+ */
+#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO			0x40
+#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO			0x80
+
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM			0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK			0x01
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK			0x02
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM			0x03
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK			0x03
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1				0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2				0x04
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM			0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK			0x08
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK			0x10
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM			0x18
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK			0x18
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1				0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2				0x20
+#define IEEE80211_HE_PHY_CAP3_RX_HE_MU_PPDU_FROM_NON_AP_STA		0x40
+#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER				0x80
+
+#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE				0x01
+#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER				0x02
+
+/* Minimal allowed value of Max STS under 80MHz is 3 */
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4		0x0c
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5		0x10
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6		0x14
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7		0x18
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8		0x1c
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK	0x1c
+
+/* Minimal allowed value of Max STS above 80MHz is 3 */
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4		0x60
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5		0x80
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6		0xa0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7		0xc0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8		0xe0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK	0xe0
+
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1	0x00
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2	0x01
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3	0x02
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4	0x03
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5	0x04
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6	0x05
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7	0x06
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8	0x07
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK	0x07
+
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1	0x00
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2	0x08
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3	0x10
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4	0x18
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5	0x20
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6	0x28
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7	0x30
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8	0x38
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK	0x38
+
+#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK				0x40
+#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK				0x80
+
+#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU			0x01
+#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU			0x02
+#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMER_FB			0x04
+#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMER_FB			0x08
+#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB				0x10
+#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE			0x20
+#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO		0x40
+#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT			0x80
+
+#define IEEE80211_HE_PHY_CAP7_SRP_BASED_SR				0x01
+#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR			0x02
+#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI		0x04
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_1					0x08
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_2					0x10
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_3					0x18
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_4					0x20
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_5					0x28
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_6					0x30
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_7					0x38
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK				0x38
+#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ			0x40
+#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ			0x80
+
+#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI		0x01
+#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G		0x02
+#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU			0x04
+#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU			0x08
+#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI		0x10
+#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_2X_AND_1XLTF			0x20
+
+/* 802.11ax HE TX/RX MCS NSS Support  */
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS			(3)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS			(6)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS			(11)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK			0x07c0
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK			0xf800
+
+/* TX/RX HE MCS Support field Highest MCS subfield encoding */
+enum ieee80211_he_highest_mcs_supported_subfield_enc {
+	HIGHEST_MCS_SUPPORTED_MCS7 = 0,
+	HIGHEST_MCS_SUPPORTED_MCS8,
+	HIGHEST_MCS_SUPPORTED_MCS9,
+	HIGHEST_MCS_SUPPORTED_MCS10,
+	HIGHEST_MCS_SUPPORTED_MCS11,
+};
+
+/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */
+static inline u8
+ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap)
+{
+	u8 count = 4;
+
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
+		count += 4;
+
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)
+		count += 4;
+
+	return count;
+}
+
+/* 802.11ax HE PPE Thresholds */
+#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS			(1)
+#define IEEE80211_PPE_THRES_NSS_POS				(0)
+#define IEEE80211_PPE_THRES_NSS_MASK				(7)
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU	\
+	(BIT(5) | BIT(6))
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK		0x78
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS		(3)
+#define IEEE80211_PPE_THRES_INFO_PPET_SIZE			(3)
+
+/*
+ * Calculate 802.11ax HE capabilities IE PPE field size
+ * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8*
+ */
+static inline u8
+ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
+{
+	u8 n;
+
+	if ((phy_cap_info[6] &
+	     IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0)
+		return 0;
+
+	n = hweight8(ppe_thres_hdr &
+		     IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK);
+	n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >>
+		   IEEE80211_PPE_THRES_NSS_POS));
+
+	/*
+	 * Each pair is 6 bits, and we need to add the 7 "header" bits to the
+	 * total size.
+	 */
+	n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7;
+	n = DIV_ROUND_UP(n, 8);
+
+	return n;
+}
+
+/* HE Operation defines */
+#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK			0x0000003f
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x000001c0
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET		6
+#define IEEE80211_HE_OPERATION_TWT_REQUIRED			0x00000200
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK		0x000ffc00
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET		10
+#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR		0x000100000
+#define IEEE80211_HE_OPERATION_VHT_OPER_INFO			0x000200000
+#define IEEE80211_HE_OPERATION_MULTI_BSSID_AP			0x10000000
+#define IEEE80211_HE_OPERATION_TX_BSSID_INDICATOR		0x20000000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED		0x40000000
+
+/*
+ * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size
+ * @he_oper_ie: byte data of the He Operations IE, stating from the the byte
+ *	after the ext ID byte. It is assumed that he_oper_ie has at least
+ *	sizeof(struct ieee80211_he_operation) bytes, checked already in
+ *	ieee802_11_parse_elems_crc()
+ * @return the actual size of the IE data (not including header), or 0 on error
+ */
+static inline u8
+ieee80211_he_oper_size(const u8 *he_oper_ie)
+{
+	struct ieee80211_he_operation *he_oper = (void *)he_oper_ie;
+	u8 oper_len = sizeof(struct ieee80211_he_operation);
+	u32 he_oper_params;
+
+	/* Make sure the input is not NULL */
+	if (!he_oper_ie)
+		return 0;
+
+	/* Calc required length */
+	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
+	if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO)
+		oper_len += 3;
+	if (he_oper_params & IEEE80211_HE_OPERATION_MULTI_BSSID_AP)
+		oper_len++;
+
+	/* Add the first byte (extension ID) to the total length */
+	oper_len++;
+
+	return oper_len;
+}
+
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
 #define WLAN_AUTH_SHARED_KEY 1
@@ -1992,6 +2414,11 @@ enum ieee80211_eid_ext {
 	WLAN_EID_EXT_FILS_WRAPPED_DATA = 8,
 	WLAN_EID_EXT_FILS_PUBLIC_KEY = 12,
 	WLAN_EID_EXT_FILS_NONCE = 13,
+	WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14,
+	WLAN_EID_EXT_HE_CAPABILITY = 35,
+	WLAN_EID_EXT_HE_OPERATION = 36,
+	WLAN_EID_EXT_UORA = 37,
+	WLAN_EID_EXT_HE_MU_EDCA = 38,
 };
 
 /* Action category code */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 5fbfe61f41c6..9ba1f289c439 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -285,6 +285,41 @@ struct ieee80211_sta_vht_cap {
 	struct ieee80211_vht_mcs_info vht_mcs;
 };
 
+#define IEEE80211_HE_PPE_THRES_MAX_LEN		25
+
+/**
+ * struct ieee80211_sta_he_cap - STA's HE capabilities
+ *
+ * This structure describes most essential parameters needed
+ * to describe 802.11ax HE capabilities for a STA.
+ *
+ * @has_he: true iff HE data is valid.
+ * @he_cap_elem: Fixed portion of the HE capabilities element.
+ * @he_mcs_nss_supp: The supported NSS/MCS combinations.
+ * @ppe_thres: Holds the PPE Thresholds data.
+ */
+struct ieee80211_sta_he_cap {
+	bool has_he;
+	struct ieee80211_he_cap_elem he_cap_elem;
+	struct ieee80211_he_mcs_nss_supp he_mcs_nss_supp;
+	u8 ppe_thres[IEEE80211_HE_PPE_THRES_MAX_LEN];
+};
+
+/**
+ * struct ieee80211_sband_iftype_data
+ *
+ * This structure encapsulates sband data that is relevant for the
+ * interface types defined in @types_mask.  Each type in the
+ * @types_mask must be unique across all instances of iftype_data.
+ *
+ * @types_mask: interface types mask
+ * @he_cap: holds the HE capabilities
+ */
+struct ieee80211_sband_iftype_data {
+	u16 types_mask;
+	struct ieee80211_sta_he_cap he_cap;
+};
+
 /**
  * struct ieee80211_supported_band - frequency band definition
  *
@@ -301,6 +336,11 @@ struct ieee80211_sta_vht_cap {
  * @n_bitrates: Number of bitrates in @bitrates
  * @ht_cap: HT capabilities in this band
  * @vht_cap: VHT capabilities in this band
+ * @n_iftype_data: number of iftype data entries
+ * @iftype_data: interface type data entries.  Note that the bits in
+ *	@types_mask inside this structure cannot overlap (i.e. only
+ *	one occurrence of each type is allowed across all instances of
+ *	iftype_data).
  */
 struct ieee80211_supported_band {
 	struct ieee80211_channel *channels;
@@ -310,8 +350,55 @@ struct ieee80211_supported_band {
 	int n_bitrates;
 	struct ieee80211_sta_ht_cap ht_cap;
 	struct ieee80211_sta_vht_cap vht_cap;
+	u16 n_iftype_data;
+	const struct ieee80211_sband_iftype_data *iftype_data;
 };
 
+/**
+ * ieee80211_get_sband_iftype_data - return sband data for a given iftype
+ * @sband: the sband to search for the STA on
+ * @iftype: enum nl80211_iftype
+ *
+ * Return: pointer to struct ieee80211_sband_iftype_data, or NULL is none found
+ */
+static inline const struct ieee80211_sband_iftype_data *
+ieee80211_get_sband_iftype_data(const struct ieee80211_supported_band *sband,
+				u8 iftype)
+{
+	int i;
+
+	if (WARN_ON(iftype >= NL80211_IFTYPE_MAX))
+		return NULL;
+
+	for (i = 0; i < sband->n_iftype_data; i++)  {
+		const struct ieee80211_sband_iftype_data *data =
+			&sband->iftype_data[i];
+
+		if (data->types_mask & BIT(iftype))
+			return data;
+	}
+
+	return NULL;
+}
+
+/**
+ * ieee80211_get_he_sta_cap - return HE capabilities for an sband's STA
+ * @sband: the sband to search for the STA on
+ *
+ * Return: pointer to the struct ieee80211_sta_he_cap, or NULL is none found
+ */
+static inline const struct ieee80211_sta_he_cap *
+ieee80211_get_he_sta_cap(const struct ieee80211_supported_band *sband)
+{
+	const struct ieee80211_sband_iftype_data *data =
+		ieee80211_get_sband_iftype_data(sband, NL80211_IFTYPE_STATION);
+
+	if (data && data->he_cap.has_he)
+		return &data->he_cap;
+
+	return NULL;
+}
+
 /**
  * wiphy_read_of_freq_limits - read frequency limits from device tree
  *
@@ -899,6 +986,8 @@ enum station_parameters_apply_mask {
  * @opmode_notif: operating mode field from Operating Mode Notification
  * @opmode_notif_used: information if operating mode field is used
  * @support_p2p_ps: information if station supports P2P PS mechanism
+ * @he_capa: HE capabilities of station
+ * @he_capa_len: the length of the HE capabilities
  */
 struct station_parameters {
 	const u8 *supported_rates;
@@ -926,6 +1015,8 @@ struct station_parameters {
 	u8 opmode_notif;
 	bool opmode_notif_used;
 	int support_p2p_ps;
+	const struct ieee80211_he_cap_elem *he_capa;
+	u8 he_capa_len;
 };
 
 /**
@@ -1000,12 +1091,14 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
  * @RATE_INFO_FLAGS_VHT_MCS: mcs field filled with VHT MCS
  * @RATE_INFO_FLAGS_SHORT_GI: 400ns guard interval
  * @RATE_INFO_FLAGS_60G: 60GHz MCS
+ * @RATE_INFO_FLAGS_HE_MCS: HE MCS information
  */
 enum rate_info_flags {
 	RATE_INFO_FLAGS_MCS			= BIT(0),
 	RATE_INFO_FLAGS_VHT_MCS			= BIT(1),
 	RATE_INFO_FLAGS_SHORT_GI		= BIT(2),
 	RATE_INFO_FLAGS_60G			= BIT(3),
+	RATE_INFO_FLAGS_HE_MCS			= BIT(4),
 };
 
 /**
@@ -1019,6 +1112,7 @@ enum rate_info_flags {
  * @RATE_INFO_BW_40: 40 MHz bandwidth
  * @RATE_INFO_BW_80: 80 MHz bandwidth
  * @RATE_INFO_BW_160: 160 MHz bandwidth
+ * @RATE_INFO_BW_HE_RU: bandwidth determined by HE RU allocation
  */
 enum rate_info_bw {
 	RATE_INFO_BW_20 = 0,
@@ -1027,6 +1121,7 @@ enum rate_info_bw {
 	RATE_INFO_BW_40,
 	RATE_INFO_BW_80,
 	RATE_INFO_BW_160,
+	RATE_INFO_BW_HE_RU,
 };
 
 /**
@@ -1035,10 +1130,14 @@ enum rate_info_bw {
  * Information about a receiving or transmitting bitrate
  *
  * @flags: bitflag of flags from &enum rate_info_flags
- * @mcs: mcs index if struct describes a 802.11n bitrate
+ * @mcs: mcs index if struct describes an HT/VHT/HE rate
  * @legacy: bitrate in 100kbit/s for 802.11abg
- * @nss: number of streams (VHT only)
+ * @nss: number of streams (VHT & HE only)
  * @bw: bandwidth (from &enum rate_info_bw)
+ * @he_gi: HE guard interval (from &enum nl80211_he_gi)
+ * @he_dcm: HE DCM value
+ * @he_ru_alloc: HE RU allocation (from &enum nl80211_he_ru_alloc,
+ *	only valid if bw is %RATE_INFO_BW_HE_RU)
  */
 struct rate_info {
 	u8 flags;
@@ -1046,6 +1145,9 @@ struct rate_info {
 	u16 legacy;
 	u8 nss;
 	u8 bw;
+	u8 he_gi;
+	u8 he_dcm;
+	u8 he_ru_alloc;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 49f718e821a3..f82ce3c89ab7 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2237,6 +2237,9 @@ enum nl80211_commands {
  *      enforced.
  * @NL80211_ATTR_TXQ_QUANTUM: TXQ scheduler quantum (bytes). Number of bytes
  *      a flow is assigned on each round of the DRR scheduler.
+ * @NL80211_ATTR_HE_CAPABILITY: HE Capability information element (from
+ *	association request when used with NL80211_CMD_NEW_STATION). Can be set
+ *	only if %NL80211_STA_FLAG_WME is set.
  *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
@@ -2677,6 +2680,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_TXQ_MEMORY_LIMIT,
 	NL80211_ATTR_TXQ_QUANTUM,
 
+	NL80211_ATTR_HE_CAPABILITY,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
@@ -2726,7 +2731,8 @@ enum nl80211_attrs {
 #define NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY	24
 #define NL80211_HT_CAPABILITY_LEN		26
 #define NL80211_VHT_CAPABILITY_LEN		12
-
+#define NL80211_HE_MIN_CAPABILITY_LEN           16
+#define NL80211_HE_MAX_CAPABILITY_LEN           51
 #define NL80211_MAX_NR_CIPHER_SUITES		5
 #define NL80211_MAX_NR_AKM_SUITES		2
 
@@ -2853,6 +2859,38 @@ struct nl80211_sta_flag_update {
 	__u32 set;
 } __attribute__((packed));
 
+/**
+ * enum nl80211_he_gi - HE guard interval
+ * @NL80211_RATE_INFO_HE_GI_0_8: 0.8 usec
+ * @NL80211_RATE_INFO_HE_GI_1_6: 1.6 usec
+ * @NL80211_RATE_INFO_HE_GI_3_2: 3.2 usec
+ */
+enum nl80211_he_gi {
+	NL80211_RATE_INFO_HE_GI_0_8,
+	NL80211_RATE_INFO_HE_GI_1_6,
+	NL80211_RATE_INFO_HE_GI_3_2,
+};
+
+/**
+ * enum nl80211_he_ru_alloc - HE RU allocation values
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_26: 26-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_52: 52-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_106: 106-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_242: 242-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_484: 484-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_996: 996-tone RU allocation
+ * @NL80211_RATE_INFO_HE_RU_ALLOC_2x996: 2x996-tone RU allocation
+ */
+enum nl80211_he_ru_alloc {
+	NL80211_RATE_INFO_HE_RU_ALLOC_26,
+	NL80211_RATE_INFO_HE_RU_ALLOC_52,
+	NL80211_RATE_INFO_HE_RU_ALLOC_106,
+	NL80211_RATE_INFO_HE_RU_ALLOC_242,
+	NL80211_RATE_INFO_HE_RU_ALLOC_484,
+	NL80211_RATE_INFO_HE_RU_ALLOC_996,
+	NL80211_RATE_INFO_HE_RU_ALLOC_2x996,
+};
+
 /**
  * enum nl80211_rate_info - bitrate information
  *
@@ -2885,6 +2923,13 @@ struct nl80211_sta_flag_update {
  * @NL80211_RATE_INFO_5_MHZ_WIDTH: 5 MHz width - note that this is
  *	a legacy rate and will be reported as the actual bitrate, i.e.
  *	a quarter of the base (20 MHz) rate
+ * @NL80211_RATE_INFO_HE_MCS: HE MCS index (u8, 0-11)
+ * @NL80211_RATE_INFO_HE_NSS: HE NSS value (u8, 1-8)
+ * @NL80211_RATE_INFO_HE_GI: HE guard interval identifier
+ *	(u8, see &enum nl80211_he_gi)
+ * @NL80211_RATE_INFO_HE_DCM: HE DCM value (u8, 0/1)
+ * @NL80211_RATE_INFO_RU_ALLOC: HE RU allocation, if not present then
+ *	non-OFDMA was used (u8, see &enum nl80211_he_ru_alloc)
  * @__NL80211_RATE_INFO_AFTER_LAST: internal use
  */
 enum nl80211_rate_info {
@@ -2901,6 +2946,11 @@ enum nl80211_rate_info {
 	NL80211_RATE_INFO_160_MHZ_WIDTH,
 	NL80211_RATE_INFO_10_MHZ_WIDTH,
 	NL80211_RATE_INFO_5_MHZ_WIDTH,
+	NL80211_RATE_INFO_HE_MCS,
+	NL80211_RATE_INFO_HE_NSS,
+	NL80211_RATE_INFO_HE_GI,
+	NL80211_RATE_INFO_HE_DCM,
+	NL80211_RATE_INFO_HE_RU_ALLOC,
 
 	/* keep last */
 	__NL80211_RATE_INFO_AFTER_LAST,
@@ -3166,6 +3216,38 @@ enum nl80211_mpath_info {
 	NL80211_MPATH_INFO_MAX = __NL80211_MPATH_INFO_AFTER_LAST - 1
 };
 
+/**
+ * enum nl80211_band_iftype_attr - Interface type data attributes
+ *
+ * @__NL80211_BAND_IFTYPE_ATTR_INVALID: attribute number 0 is reserved
+ * @NL80211_BAND_IFTYPE_ATTR_IFTYPES: nested attribute containing a flag attribute
+ *     for each interface type that supports the band data
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC: HE MAC capabilities as in HE
+ *     capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY: HE PHY capabilities as in HE
+ *     capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET: HE supported NSS/MCS as in HE
+ *     capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE: HE PPE thresholds information as
+ *     defined in HE capabilities IE
+ * @NL80211_BAND_IFTYPE_ATTR_MAX: highest band HE capability attribute currently
+ *     defined
+ * @__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST: internal use
+ */
+enum nl80211_band_iftype_attr {
+	__NL80211_BAND_IFTYPE_ATTR_INVALID,
+
+	NL80211_BAND_IFTYPE_ATTR_IFTYPES,
+	NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC,
+	NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY,
+	NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET,
+	NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE,
+
+	/* keep last */
+	__NL80211_BAND_IFTYPE_ATTR_AFTER_LAST,
+	NL80211_BAND_IFTYPE_ATTR_MAX = __NL80211_BAND_IFTYPE_ATTR_AFTER_LAST - 1
+};
+
 /**
  * enum nl80211_band_attr - band attributes
  * @__NL80211_BAND_ATTR_INVALID: attribute number 0 is reserved
@@ -3181,6 +3263,8 @@ enum nl80211_mpath_info {
  * @NL80211_BAND_ATTR_VHT_MCS_SET: 32-byte attribute containing the MCS set as
  *	defined in 802.11ac
  * @NL80211_BAND_ATTR_VHT_CAPA: VHT capabilities, as in the HT information IE
+ * @NL80211_BAND_ATTR_IFTYPE_DATA: nested array attribute, with each entry using
+ *	attributes from &enum nl80211_band_iftype_attr
  * @NL80211_BAND_ATTR_MAX: highest band attribute currently defined
  * @__NL80211_BAND_ATTR_AFTER_LAST: internal use
  */
@@ -3196,6 +3280,7 @@ enum nl80211_band_attr {
 
 	NL80211_BAND_ATTR_VHT_MCS_SET,
 	NL80211_BAND_ATTR_VHT_CAPA,
+	NL80211_BAND_ATTR_IFTYPE_DATA,
 
 	/* keep last */
 	__NL80211_BAND_ATTR_AFTER_LAST,
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 5fe35aafdd9c..d23abc619e77 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -3,7 +3,7 @@
  *
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright 2015	Intel Deutschland GmbH
+ * Copyright 2015-2017	Intel Deutschland GmbH
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -744,6 +744,8 @@ int wiphy_register(struct wiphy *wiphy)
 
 	/* sanity check supported bands/channels */
 	for (band = 0; band < NUM_NL80211_BANDS; band++) {
+		u16 types = 0;
+
 		sband = wiphy->bands[band];
 		if (!sband)
 			continue;
@@ -788,6 +790,23 @@ int wiphy_register(struct wiphy *wiphy)
 			sband->channels[i].band = band;
 		}
 
+		for (i = 0; i < sband->n_iftype_data; i++) {
+			const struct ieee80211_sband_iftype_data *iftd;
+
+			iftd = &sband->iftype_data[i];
+
+			if (WARN_ON(!iftd->types_mask))
+				return -EINVAL;
+			if (WARN_ON(types & iftd->types_mask))
+				return -EINVAL;
+
+			/* at least one piece of information must be present */
+			if (WARN_ON(!iftd->he_cap.has_he))
+				return -EINVAL;
+
+			types |= iftd->types_mask;
+		}
+
 		have_band = true;
 	}
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 7b21914ae18b..0ccce338a66e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -428,6 +428,8 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 	[NL80211_ATTR_TXQ_LIMIT] = { .type = NLA_U32 },
 	[NL80211_ATTR_TXQ_MEMORY_LIMIT] = { .type = NLA_U32 },
 	[NL80211_ATTR_TXQ_QUANTUM] = { .type = NLA_U32 },
+	[NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY,
+					 .len = NL80211_HE_MAX_CAPABILITY_LEN },
 };
 
 /* policy for the key attributes */
@@ -1324,6 +1326,34 @@ static int nl80211_send_coalesce(struct sk_buff *msg,
 	return 0;
 }
 
+static int
+nl80211_send_iftype_data(struct sk_buff *msg,
+			 const struct ieee80211_sband_iftype_data *iftdata)
+{
+	const struct ieee80211_sta_he_cap *he_cap = &iftdata->he_cap;
+
+	if (nl80211_put_iftypes(msg, NL80211_BAND_IFTYPE_ATTR_IFTYPES,
+				iftdata->types_mask))
+		return -ENOBUFS;
+
+	if (he_cap->has_he) {
+		if (nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MAC,
+			    sizeof(he_cap->he_cap_elem.mac_cap_info),
+			    he_cap->he_cap_elem.mac_cap_info) ||
+		    nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PHY,
+			    sizeof(he_cap->he_cap_elem.phy_cap_info),
+			    he_cap->he_cap_elem.phy_cap_info) ||
+		    nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_MCS_SET,
+			    sizeof(he_cap->he_mcs_nss_supp),
+			    &he_cap->he_mcs_nss_supp) ||
+		    nla_put(msg, NL80211_BAND_IFTYPE_ATTR_HE_CAP_PPE,
+			    sizeof(he_cap->ppe_thres), he_cap->ppe_thres))
+			return -ENOBUFS;
+	}
+
+	return 0;
+}
+
 static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 				      struct ieee80211_supported_band *sband)
 {
@@ -1353,6 +1383,32 @@ static int nl80211_send_band_rateinfo(struct sk_buff *msg,
 			 sband->vht_cap.cap)))
 		return -ENOBUFS;
 
+	if (sband->n_iftype_data) {
+		struct nlattr *nl_iftype_data =
+			nla_nest_start(msg, NL80211_BAND_ATTR_IFTYPE_DATA);
+		int err;
+
+		if (!nl_iftype_data)
+			return -ENOBUFS;
+
+		for (i = 0; i < sband->n_iftype_data; i++) {
+			struct nlattr *iftdata;
+
+			iftdata = nla_nest_start(msg, i + 1);
+			if (!iftdata)
+				return -ENOBUFS;
+
+			err = nl80211_send_iftype_data(msg,
+						       &sband->iftype_data[i]);
+			if (err)
+				return err;
+
+			nla_nest_end(msg, iftdata);
+		}
+
+		nla_nest_end(msg, nl_iftype_data);
+	}
+
 	/* add bitrates */
 	nl_rates = nla_nest_start(msg, NL80211_BAND_ATTR_RATES);
 	if (!nl_rates)
@@ -4472,6 +4528,9 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 	case RATE_INFO_BW_160:
 		rate_flg = NL80211_RATE_INFO_160_MHZ_WIDTH;
 		break;
+	case RATE_INFO_BW_HE_RU:
+		rate_flg = 0;
+		WARN_ON(!(info->flags & RATE_INFO_FLAGS_HE_MCS));
 	}
 
 	if (rate_flg && nla_put_flag(msg, rate_flg))
@@ -4491,6 +4550,19 @@ static bool nl80211_put_sta_rate(struct sk_buff *msg, struct rate_info *info,
 		if (info->flags & RATE_INFO_FLAGS_SHORT_GI &&
 		    nla_put_flag(msg, NL80211_RATE_INFO_SHORT_GI))
 			return false;
+	} else if (info->flags & RATE_INFO_FLAGS_HE_MCS) {
+		if (nla_put_u8(msg, NL80211_RATE_INFO_HE_MCS, info->mcs))
+			return false;
+		if (nla_put_u8(msg, NL80211_RATE_INFO_HE_NSS, info->nss))
+			return false;
+		if (nla_put_u8(msg, NL80211_RATE_INFO_HE_GI, info->he_gi))
+			return false;
+		if (nla_put_u8(msg, NL80211_RATE_INFO_HE_DCM, info->he_dcm))
+			return false;
+		if (info->bw == RATE_INFO_BW_HE_RU &&
+		    nla_put_u8(msg, NL80211_RATE_INFO_HE_RU_ALLOC,
+			       info->he_ru_alloc))
+			return false;
 	}
 
 	nla_nest_end(msg, rate);
@@ -4887,7 +4959,8 @@ int cfg80211_check_station_change(struct wiphy *wiphy,
 			return -EINVAL;
 		if (params->supported_rates)
 			return -EINVAL;
-		if (params->ext_capab || params->ht_capa || params->vht_capa)
+		if (params->ext_capab || params->ht_capa || params->vht_capa ||
+		    params->he_capa)
 			return -EINVAL;
 	}
 
@@ -5093,6 +5166,15 @@ static int nl80211_set_station_tdls(struct genl_info *info,
 	if (info->attrs[NL80211_ATTR_VHT_CAPABILITY])
 		params->vht_capa =
 			nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
+	if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) {
+		params->he_capa =
+			nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+		params->he_capa_len =
+			nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+
+		if (params->he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN)
+			return -EINVAL;
+	}
 
 	err = nl80211_parse_sta_channel_info(info, params);
 	if (err)
@@ -5320,6 +5402,17 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 		params.vht_capa =
 			nla_data(info->attrs[NL80211_ATTR_VHT_CAPABILITY]);
 
+	if (info->attrs[NL80211_ATTR_HE_CAPABILITY]) {
+		params.he_capa =
+			nla_data(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+		params.he_capa_len =
+			nla_len(info->attrs[NL80211_ATTR_HE_CAPABILITY]);
+
+		/* max len is validated in nla policy */
+		if (params.he_capa_len < NL80211_HE_MIN_CAPABILITY_LEN)
+			return -EINVAL;
+	}
+
 	if (info->attrs[NL80211_ATTR_OPMODE_NOTIF]) {
 		params.opmode_notif_used = true;
 		params.opmode_notif =
@@ -5352,6 +5445,10 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info)
 	if (!(params.sta_flags_set & BIT(NL80211_STA_FLAG_WME))) {
 		params.ht_capa = NULL;
 		params.vht_capa = NULL;
+
+		/* HE requires WME */
+		if (params.he_capa_len)
+			return -EINVAL;
 	}
 
 	/* When you run into this, adjust the code below for the new flag */
diff --git a/net/wireless/util.c b/net/wireless/util.c
index b91597a8baa2..4ed06b271f32 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -4,6 +4,7 @@
  *
  * Copyright 2007-2009	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
+ * Copyright 2017	Intel Deutschland GmbH
  */
 #include <linux/export.h>
 #include <linux/bitops.h>
@@ -1142,6 +1143,85 @@ static u32 cfg80211_calculate_bitrate_vht(struct rate_info *rate)
 	return 0;
 }
 
+static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
+{
+#define SCALE 2048
+	u16 mcs_divisors[12] = {
+		34133, /* 16.666666... */
+		17067, /*  8.333333... */
+		11378, /*  5.555555... */
+		 8533, /*  4.166666... */
+		 5689, /*  2.777777... */
+		 4267, /*  2.083333... */
+		 3923, /*  1.851851... */
+		 3413, /*  1.666666... */
+		 2844, /*  1.388888... */
+		 2560, /*  1.250000... */
+		 2276, /*  1.111111... */
+		 2048, /*  1.000000... */
+	};
+	u32 rates_160M[3] = { 960777777, 907400000, 816666666 };
+	u32 rates_969[3] =  { 480388888, 453700000, 408333333 };
+	u32 rates_484[3] =  { 229411111, 216666666, 195000000 };
+	u32 rates_242[3] =  { 114711111, 108333333,  97500000 };
+	u32 rates_106[3] =  {  40000000,  37777777,  34000000 };
+	u32 rates_52[3]  =  {  18820000,  17777777,  16000000 };
+	u32 rates_26[3]  =  {   9411111,   8888888,   8000000 };
+	u64 tmp;
+	u32 result;
+
+	if (WARN_ON_ONCE(rate->mcs > 11))
+		return 0;
+
+	if (WARN_ON_ONCE(rate->he_gi > NL80211_RATE_INFO_HE_GI_3_2))
+		return 0;
+	if (WARN_ON_ONCE(rate->he_ru_alloc >
+			 NL80211_RATE_INFO_HE_RU_ALLOC_2x996))
+		return 0;
+	if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8))
+		return 0;
+
+	if (rate->bw == RATE_INFO_BW_160)
+		result = rates_160M[rate->he_gi];
+	else if (rate->bw == RATE_INFO_BW_80 ||
+		 (rate->bw == RATE_INFO_BW_HE_RU &&
+		  rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996))
+		result = rates_969[rate->he_gi];
+	else if (rate->bw == RATE_INFO_BW_40 ||
+		 (rate->bw == RATE_INFO_BW_HE_RU &&
+		  rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484))
+		result = rates_484[rate->he_gi];
+	else if (rate->bw == RATE_INFO_BW_20 ||
+		 (rate->bw == RATE_INFO_BW_HE_RU &&
+		  rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_242))
+		result = rates_242[rate->he_gi];
+	else if (rate->bw == RATE_INFO_BW_HE_RU &&
+		 rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_106)
+		result = rates_106[rate->he_gi];
+	else if (rate->bw == RATE_INFO_BW_HE_RU &&
+		 rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_52)
+		result = rates_52[rate->he_gi];
+	else if (rate->bw == RATE_INFO_BW_HE_RU &&
+		 rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_26)
+		result = rates_26[rate->he_gi];
+	else if (WARN(1, "invalid HE MCS: bw:%d, ru:%d\n",
+		      rate->bw, rate->he_ru_alloc))
+		return 0;
+
+	/* now scale to the appropriate MCS */
+	tmp = result;
+	tmp *= SCALE;
+	do_div(tmp, mcs_divisors[rate->mcs]);
+	result = tmp;
+
+	/* and take NSS, DCM into account */
+	result = (result * rate->nss) / 8;
+	if (rate->he_dcm)
+		result /= 2;
+
+	return result;
+}
+
 u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 {
 	if (rate->flags & RATE_INFO_FLAGS_MCS)
@@ -1150,6 +1230,8 @@ u32 cfg80211_calculate_bitrate(struct rate_info *rate)
 		return cfg80211_calculate_bitrate_60g(rate);
 	if (rate->flags & RATE_INFO_FLAGS_VHT_MCS)
 		return cfg80211_calculate_bitrate_vht(rate);
+	if (rate->flags & RATE_INFO_FLAGS_HE_MCS)
+		return cfg80211_calculate_bitrate_he(rate);
 
 	return rate->legacy;
 }
-- 
cgit v1.2.3


From 95a28eeaf1491bcb8bf521bad4784683333705ee Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sat, 9 Jun 2018 09:14:43 +0300
Subject: radiotap: add structs for HE

Add radiotap structures for HE.

Signed-off-by: Liad Kaufman <liad.kaufman@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Ido Yariv <idox.yariv@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
---
 include/net/ieee80211_radiotap.h | 123 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 123 insertions(+)

diff --git a/include/net/ieee80211_radiotap.h b/include/net/ieee80211_radiotap.h
index 960236fb1681..feef706e1158 100644
--- a/include/net/ieee80211_radiotap.h
+++ b/include/net/ieee80211_radiotap.h
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2017		Intel Deutschland GmbH
+ * Copyright (c) 2018		Intel Corporation
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -72,6 +73,8 @@ enum ieee80211_radiotap_presence {
 	IEEE80211_RADIOTAP_AMPDU_STATUS = 20,
 	IEEE80211_RADIOTAP_VHT = 21,
 	IEEE80211_RADIOTAP_TIMESTAMP = 22,
+	IEEE80211_RADIOTAP_HE = 23,
+	IEEE80211_RADIOTAP_HE_MU = 24,
 
 	/* valid in every it_present bitmap, even vendor namespaces */
 	IEEE80211_RADIOTAP_RADIOTAP_NAMESPACE = 29,
@@ -202,6 +205,126 @@ enum ieee80211_radiotap_timestamp_flags {
 	IEEE80211_RADIOTAP_TIMESTAMP_FLAG_ACCURACY = 0x02,
 };
 
+struct ieee80211_radiotap_he {
+	__le16 data1, data2, data3, data4, data5, data6;
+};
+
+enum ieee80211_radiotap_he_bits {
+	IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MASK		= 3,
+	IEEE80211_RADIOTAP_HE_DATA1_FORMAT_SU		= 0,
+	IEEE80211_RADIOTAP_HE_DATA1_FORMAT_EXT_SU	= 1,
+	IEEE80211_RADIOTAP_HE_DATA1_FORMAT_MU		= 2,
+	IEEE80211_RADIOTAP_HE_DATA1_FORMAT_TRIG		= 3,
+
+	IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN	= 0x0004,
+	IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN	= 0x0008,
+	IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN		= 0x0010,
+	IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN	= 0x0020,
+	IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN	= 0x0040,
+	IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN	= 0x0080,
+	IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN	= 0x0100,
+	IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN		= 0x0200,
+	IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN	= 0x0400,
+	IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN	= 0x0800,
+	IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN	= 0x1000,
+	IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN	= 0x2000,
+	IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN	= 0x4000,
+	IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN	= 0x8000,
+
+	IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN	= 0x0001,
+	IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN		= 0x0002,
+	IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN	= 0x0004,
+	IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN	= 0x0008,
+	IEEE80211_RADIOTAP_HE_DATA2_TXBF_KNOWN		= 0x0010,
+	IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN	= 0x0020,
+	IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN		= 0x0040,
+	IEEE80211_RADIOTAP_HE_DATA2_MIDAMBLE_KNOWN	= 0x0080,
+	IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET		= 0x3f00,
+	IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN	= 0x4000,
+	IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC	= 0x8000,
+
+	IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR		= 0x003f,
+	IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE		= 0x0040,
+	IEEE80211_RADIOTAP_HE_DATA3_UL_DL		= 0x0080,
+	IEEE80211_RADIOTAP_HE_DATA3_DATA_MCS		= 0x0f00,
+	IEEE80211_RADIOTAP_HE_DATA3_DATA_DCM		= 0x1000,
+	IEEE80211_RADIOTAP_HE_DATA3_CODING		= 0x2000,
+	IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG	= 0x4000,
+	IEEE80211_RADIOTAP_HE_DATA3_STBC		= 0x8000,
+
+	IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE	= 0x000f,
+	IEEE80211_RADIOTAP_HE_DATA4_MU_STA_ID		= 0x7ff0,
+	IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1	= 0x000f,
+	IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2	= 0x00f0,
+	IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3	= 0x0f00,
+	IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4	= 0xf000,
+
+	IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC	= 0x000f,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ	= 0,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ	= 1,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ	= 2,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ	= 3,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_26T	= 4,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_52T	= 5,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_106T	= 6,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_242T	= 7,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_484T	= 8,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_996T	= 9,
+		IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_2x996T	= 10,
+
+	IEEE80211_RADIOTAP_HE_DATA5_GI			= 0x0030,
+		IEEE80211_RADIOTAP_HE_DATA5_GI_0_8			= 0,
+		IEEE80211_RADIOTAP_HE_DATA5_GI_1_6			= 1,
+		IEEE80211_RADIOTAP_HE_DATA5_GI_3_2			= 2,
+
+	IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE		= 0x00c0,
+		IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN		= 0,
+		IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_1X			= 1,
+		IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X			= 2,
+		IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X			= 3,
+	IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS	= 0x0700,
+	IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD		= 0x3000,
+	IEEE80211_RADIOTAP_HE_DATA5_TXBF		= 0x4000,
+	IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG		= 0x8000,
+
+	IEEE80211_RADIOTAP_HE_DATA6_NSTS		= 0x000f,
+	IEEE80211_RADIOTAP_HE_DATA6_DOPPLER		= 0x0010,
+	IEEE80211_RADIOTAP_HE_DATA6_TXOP		= 0x7f00,
+	IEEE80211_RADIOTAP_HE_DATA6_MIDAMBLE_PDCTY	= 0x8000,
+};
+
+struct ieee80211_radiotap_he_mu {
+	__le16 flags1, flags2;
+	u8 ru_ch1[4];
+	u8 ru_ch2[4];
+};
+
+enum ieee80211_radiotap_he_mu_bits {
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS		= 0x000f,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS_KNOWN		= 0x0010,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM		= 0x0020,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM_KNOWN		= 0x0040,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_CTR_26T_RU_KNOWN	= 0x0080,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_RU_KNOWN		= 0x0100,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_RU_KNOWN		= 0x0200,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU_KNOWN	= 0x1000,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU		= 0x2000,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_COMP_KNOWN	= 0x4000,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN	= 0x8000,
+
+	IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW	= 0x0003,
+		IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_20MHZ	= 0x0000,
+		IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_40MHZ	= 0x0001,
+		IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_80MHZ	= 0x0002,
+		IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_160MHZ	= 0x0003,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN	= 0x0004,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP		= 0x0008,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS	= 0x00f0,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW	= 0x0300,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN= 0x0400,
+	IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU		= 0x0800,
+};
+
 /**
  * ieee80211_get_radiotap_len - get radiotap header length
  */
-- 
cgit v1.2.3


From 548764bb7ce050afdba15892fb4add79d15974db Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 15 Jun 2018 13:02:07 +0100
Subject: drm/i915: Keep the ctx workarounds tightly packed

For each platform, we have a few registers that are rewritten with
different values -- they are not part of a sequence, just different parts
of a masked register set at different times (e.g. platform and gen
workarounds). Consolidate these into a single register write to keep the
table compact, important since we are running of room in the current
fixed sized buffer.

While adjusting the construction of the wa table, make it non fatal so
that the driver still loads but keeping the warning and extra details
for inspection.

Inspecting the changes for a Kabylake system,
Before:
	Address	val		mask		read
	0x07014	0x20002000	0x00002000	0x00002100
	0x0E194	0x01000100	0x00000100	0x00000114
	0x0E4F0	0x81008100	0x00008100	0xFFFF8120
	0x0E184	0x00200020	0x00000020	0x00000022
	0x0E194	0x00140014	0x00000014	0x00000114
	0x07004	0x00420042	0x00000042	0x000029C2
	0x0E188	0x00080000	0x00000008	0x00008030
	0x07300	0x80208020	0x00008020	0x00008830
	0x07300	0x00100010	0x00000010	0x00008830
	0x0E184	0x00020002	0x00000002	0x00000022
	0x0E180	0x20002000	0x00002000	0x00002000
	0x02580	0x00010000	0x00000001	0x00000004
	0x02580	0x00060004	0x00000006	0x00000004
	0x07014	0x01000100	0x00000100	0x00002100
	0x0E100	0x00100010	0x00000010	0x00008050

After:
	Address	val		mask		read
	0x02580	0x00070004	0x00000007	0x00000004
	0x07004	0x00420042	0x00000042	0x000029C2
	0x07014	0x21002100	0x00002100	0x00002100
	0x07300	0x80308030	0x00008030	0x00008830
	0x0E100	0x00100010	0x00000010	0x00008050
	0x0E180	0x20002000	0x00002000	0x00002000
	0x0E184	0x00220022	0x00000022	0x00000022
	0x0E188	0x00080000	0x00000008	0x00008030
	0x0E194	0x01140114	0x00000114	0x00000114
	0x0E4F0	0x81008100	0x00008100	0xFFFF8120

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615120207.13952-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c      | 25 +++----------
 drivers/gpu/drm/i915/i915_drv.h          |  2 +-
 drivers/gpu/drm/i915/intel_workarounds.c | 63 +++++++++++++++++++++++---------
 3 files changed, 52 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 99d3272d82d8..c400f42a54ec 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -3378,28 +3378,13 @@ static int i915_shared_dplls_info(struct seq_file *m, void *unused)
 
 static int i915_wa_registers(struct seq_file *m, void *unused)
 {
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct i915_workarounds *workarounds = &dev_priv->workarounds;
+	struct i915_workarounds *wa = &node_to_i915(m->private)->workarounds;
 	int i;
 
-	intel_runtime_pm_get(dev_priv);
-
-	seq_printf(m, "Workarounds applied: %d\n", workarounds->count);
-	for (i = 0; i < workarounds->count; ++i) {
-		i915_reg_t addr;
-		u32 mask, value, read;
-		bool ok;
-
-		addr = workarounds->reg[i].addr;
-		mask = workarounds->reg[i].mask;
-		value = workarounds->reg[i].value;
-		read = I915_READ(addr);
-		ok = (value & mask) == (read & mask);
-		seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X, read: 0x%08x, status: %s\n",
-			   i915_mmio_reg_offset(addr), value, mask, read, ok ? "OK" : "FAIL");
-	}
-
-	intel_runtime_pm_put(dev_priv);
+	seq_printf(m, "Workarounds applied: %d\n", wa->count);
+	for (i = 0; i < wa->count; ++i)
+		seq_printf(m, "0x%X: 0x%08X, mask: 0x%08X\n",
+			   wa->reg[i].addr, wa->reg[i].value, wa->reg[i].mask);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 74dd88d8563e..ea389771f917 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1305,7 +1305,7 @@ struct i915_frontbuffer_tracking {
 };
 
 struct i915_wa_reg {
-	i915_reg_t addr;
+	u32 addr;
 	u32 value;
 	/* bitmask representing WA bits */
 	u32 mask;
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index 24b929ce3341..f8bb32e974f6 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -48,29 +48,58 @@
  * - Public functions to init or apply the given workaround type.
  */
 
-static int wa_add(struct drm_i915_private *dev_priv,
-		  i915_reg_t addr,
-		  const u32 mask, const u32 val)
+static void wa_add(struct drm_i915_private *i915,
+		   i915_reg_t reg, const u32 mask, const u32 val)
 {
-	const unsigned int idx = dev_priv->workarounds.count;
+	struct i915_workarounds *wa = &i915->workarounds;
+	unsigned int start = 0, end = wa->count;
+	unsigned int addr = i915_mmio_reg_offset(reg);
+	struct i915_wa_reg *r;
+
+	while (start < end) {
+		unsigned int mid = start + (end - start) / 2;
+
+		if (wa->reg[mid].addr < addr) {
+			start = mid + 1;
+		} else if (wa->reg[mid].addr > addr) {
+			end = mid;
+		} else {
+			r = &wa->reg[mid];
+
+			if ((mask & ~r->mask) == 0) {
+				DRM_ERROR("Discarding overwritten w/a for reg %04x (mask: %08x, value: %08x)\n",
+					  addr, r->mask, r->value);
+
+				r->value &= ~mask;
+			}
+
+			r->value |= val;
+			r->mask  |= mask;
+			return;
+		}
+	}
 
-	if (WARN_ON(idx >= I915_MAX_WA_REGS))
-		return -ENOSPC;
+	if (WARN_ON_ONCE(wa->count >= I915_MAX_WA_REGS)) {
+		DRM_ERROR("Dropping w/a for reg %04x (mask: %08x, value: %08x)\n",
+			  addr, mask, val);
+		return;
+	}
 
-	dev_priv->workarounds.reg[idx].addr = addr;
-	dev_priv->workarounds.reg[idx].value = val;
-	dev_priv->workarounds.reg[idx].mask = mask;
+	r = &wa->reg[wa->count++];
+	r->addr  = addr;
+	r->value = val;
+	r->mask  = mask;
 
-	dev_priv->workarounds.count++;
+	while (r-- > wa->reg) {
+		GEM_BUG_ON(r[0].addr == r[1].addr);
+		if (r[1].addr > r[0].addr)
+			break;
 
-	return 0;
+		swap(r[1], r[0]);
+	}
 }
 
-#define WA_REG(addr, mask, val) do { \
-		const int r = wa_add(dev_priv, (addr), (mask), (val)); \
-		if (r) \
-			return r; \
-	} while (0)
+#define WA_REG(addr, mask, val) wa_add(dev_priv, (addr), (mask), (val))
 
 #define WA_SET_BIT_MASKED(addr, mask) \
 	WA_REG(addr, (mask), _MASKED_BIT_ENABLE(mask))
@@ -540,7 +569,7 @@ int intel_ctx_workarounds_emit(struct i915_request *rq)
 
 	*cs++ = MI_LOAD_REGISTER_IMM(w->count);
 	for (i = 0; i < w->count; i++) {
-		*cs++ = i915_mmio_reg_offset(w->reg[i].addr);
+		*cs++ = w->reg[i].addr;
 		*cs++ = w->reg[i].value;
 	}
 	*cs++ = MI_NOOP;
-- 
cgit v1.2.3


From ce041c43f22298485122bab15c14d062383fbc67 Mon Sep 17 00:00:00 2001
From: Thierry Escande <thierry.escande@linaro.org>
Date: Wed, 13 Jun 2018 19:18:40 +0200
Subject: lib/test_printf.c: accept "ptrval" as valid result for plain 'p'
 tests

If the test_printf module is loaded before the crng is initialized, the
plain 'p' tests will fail because the printed address will not be hashed
and the buffer will contain "(____ptrval____)" or "(ptrval)" instead
(64-bit vs 32-bit).
Since we cannot wait for the crng to be initialized for an undefined
time, both plain 'p' tests now accept the strings "(____ptrval____)" or
"(ptrval)" as a valid result and print a warning message.

Link: http://lkml.kernel.org/r/20180613171840.29827-1-thierry.escande@linaro.org
Fixes: ad67b74d2469d9b82 ("printk: hash addresses printed with %p")
To: Andrew Morton <akpm@linux-foundation.org>
To: David Miller <davem@davemloft.net>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: "Tobin C . Harding" <me@tobin.cc>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Thierry Escande <thierry.escande@linaro.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 lib/test_printf.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/lib/test_printf.c b/lib/test_printf.c
index cea592f402ed..53527ea822b5 100644
--- a/lib/test_printf.c
+++ b/lib/test_printf.c
@@ -206,6 +206,7 @@ test_string(void)
 #define PTR_WIDTH 16
 #define PTR ((void *)0xffff0123456789abUL)
 #define PTR_STR "ffff0123456789ab"
+#define PTR_VAL_NO_CRNG "(____ptrval____)"
 #define ZEROS "00000000"	/* hex 32 zero bits */
 
 static int __init
@@ -216,7 +217,16 @@ plain_format(void)
 
 	nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR);
 
-	if (nchars != PTR_WIDTH || strncmp(buf, ZEROS, strlen(ZEROS)) != 0)
+	if (nchars != PTR_WIDTH)
+		return -1;
+
+	if (strncmp(buf, PTR_VAL_NO_CRNG, PTR_WIDTH) == 0) {
+		pr_warn("crng possibly not yet initialized. plain 'p' buffer contains \"%s\"",
+			PTR_VAL_NO_CRNG);
+		return 0;
+	}
+
+	if (strncmp(buf, ZEROS, strlen(ZEROS)) != 0)
 		return -1;
 
 	return 0;
@@ -227,6 +237,7 @@ plain_format(void)
 #define PTR_WIDTH 8
 #define PTR ((void *)0x456789ab)
 #define PTR_STR "456789ab"
+#define PTR_VAL_NO_CRNG "(ptrval)"
 
 static int __init
 plain_format(void)
@@ -245,7 +256,16 @@ plain_hash(void)
 
 	nchars = snprintf(buf, PLAIN_BUF_SIZE, "%p", PTR);
 
-	if (nchars != PTR_WIDTH || strncmp(buf, PTR_STR, PTR_WIDTH) == 0)
+	if (nchars != PTR_WIDTH)
+		return -1;
+
+	if (strncmp(buf, PTR_VAL_NO_CRNG, PTR_WIDTH) == 0) {
+		pr_warn("crng possibly not yet initialized. plain 'p' buffer contains \"%s\"",
+			PTR_VAL_NO_CRNG);
+		return 0;
+	}
+
+	if (strncmp(buf, PTR_STR, PTR_WIDTH) == 0)
 		return -1;
 
 	return 0;
-- 
cgit v1.2.3


From 14921f3cef85b0167a9145e5f29b9dfc3b2a84dc Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Fri, 15 Jun 2018 13:44:29 +0300
Subject: drm/i915: Fix context ban and hang accounting for client

If client is smart or lucky enough to create a new context
after each hang, our context banning mechanism will never
catch up, and as a result of that it will be saved from
client banning. This can result in a never ending streak of
gpu hangs caused by bad or malicious client, preventing
access from other legit gpu clients.

Fix this by always incrementing per client ban score if
it hangs in short successions regardless of context ban
scoring. The exception are non bannable contexts. They remain
detached from client ban scoring mechanism.

v2: xchg timestamp, tidyup (Chris)
v3: comment, bannable & banned together (Chris)

Fixes: b083a0870c79 ("drm/i915: Add per client max context ban limit")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615104429.31477-1-mika.kuoppala@linux.intel.com
---
 drivers/gpu/drm/i915/i915_drv.h         | 21 ++++++++----
 drivers/gpu/drm/i915/i915_gem.c         | 57 +++++++++++++++++++++++----------
 drivers/gpu/drm/i915/i915_gem_context.c |  2 +-
 3 files changed, 55 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ea389771f917..d00761a06f05 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -352,14 +352,21 @@ struct drm_i915_file_private {
 
 	unsigned int bsd_engine;
 
-/* Client can have a maximum of 3 contexts banned before
- * it is denied of creating new contexts. As one context
- * ban needs 4 consecutive hangs, and more if there is
- * progress in between, this is a last resort stop gap measure
- * to limit the badly behaving clients access to gpu.
+/*
+ * Every context ban increments per client ban score. Also
+ * hangs in short succession increments ban score. If ban threshold
+ * is reached, client is considered banned and submitting more work
+ * will fail. This is a stop gap measure to limit the badly behaving
+ * clients access to gpu. Note that unbannable contexts never increment
+ * the client ban score.
  */
-#define I915_MAX_CLIENT_CONTEXT_BANS 3
-	atomic_t context_bans;
+#define I915_CLIENT_SCORE_HANG_FAST	1
+#define   I915_CLIENT_FAST_HANG_JIFFIES (60 * HZ)
+#define I915_CLIENT_SCORE_CONTEXT_BAN   3
+#define I915_CLIENT_SCORE_BANNED	9
+	/** ban_score: Accumulated score of all ctx bans and fast hangs. */
+	atomic_t ban_score;
+	unsigned long hang_timestamp;
 };
 
 /* Interface history:
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 8dd4d35655af..977982a987c8 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2941,32 +2941,54 @@ i915_gem_object_pwrite_gtt(struct drm_i915_gem_object *obj,
 	return 0;
 }
 
+static void i915_gem_client_mark_guilty(struct drm_i915_file_private *file_priv,
+					const struct i915_gem_context *ctx)
+{
+	unsigned int score;
+	unsigned long prev_hang;
+
+	if (i915_gem_context_is_banned(ctx))
+		score = I915_CLIENT_SCORE_CONTEXT_BAN;
+	else
+		score = 0;
+
+	prev_hang = xchg(&file_priv->hang_timestamp, jiffies);
+	if (time_before(jiffies, prev_hang + I915_CLIENT_FAST_HANG_JIFFIES))
+		score += I915_CLIENT_SCORE_HANG_FAST;
+
+	if (score) {
+		atomic_add(score, &file_priv->ban_score);
+
+		DRM_DEBUG_DRIVER("client %s: gained %u ban score, now %u\n",
+				 ctx->name, score,
+				 atomic_read(&file_priv->ban_score));
+	}
+}
+
 static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 {
-	bool banned;
+	unsigned int score;
+	bool banned, bannable;
 
 	atomic_inc(&ctx->guilty_count);
 
-	banned = false;
-	if (i915_gem_context_is_bannable(ctx)) {
-		unsigned int score;
+	bannable = i915_gem_context_is_bannable(ctx);
+	score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
+	banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
 
-		score = atomic_add_return(CONTEXT_SCORE_GUILTY,
-					  &ctx->ban_score);
-		banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
+	DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
+			 ctx->name, atomic_read(&ctx->guilty_count),
+			 score, yesno(banned && bannable));
 
-		DRM_DEBUG_DRIVER("context %s marked guilty (score %d) banned? %s\n",
-				 ctx->name, score, yesno(banned));
-	}
-	if (!banned)
+	/* Cool contexts don't accumulate client ban score */
+	if (!bannable)
 		return;
 
-	i915_gem_context_set_banned(ctx);
-	if (!IS_ERR_OR_NULL(ctx->file_priv)) {
-		atomic_inc(&ctx->file_priv->context_bans);
-		DRM_DEBUG_DRIVER("client %s has had %d context banned\n",
-				 ctx->name, atomic_read(&ctx->file_priv->context_bans));
-	}
+	if (banned)
+		i915_gem_context_set_banned(ctx);
+
+	if (!IS_ERR_OR_NULL(ctx->file_priv))
+		i915_gem_client_mark_guilty(ctx->file_priv, ctx);
 }
 
 static void i915_gem_context_mark_innocent(struct i915_gem_context *ctx)
@@ -5820,6 +5842,7 @@ int i915_gem_open(struct drm_i915_private *i915, struct drm_file *file)
 	INIT_LIST_HEAD(&file_priv->mm.request_list);
 
 	file_priv->bsd_engine = -1;
+	file_priv->hang_timestamp = jiffies;
 
 	ret = i915_gem_context_open(i915, file);
 	if (ret)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index ef6ea4bcd773..ccf463ab6562 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -708,7 +708,7 @@ int i915_gem_switch_to_kernel_context(struct drm_i915_private *i915)
 
 static bool client_is_banned(struct drm_i915_file_private *file_priv)
 {
-	return atomic_read(&file_priv->context_bans) > I915_MAX_CLIENT_CONTEXT_BANS;
+	return atomic_read(&file_priv->ban_score) >= I915_CLIENT_SCORE_BANNED;
 }
 
 int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
-- 
cgit v1.2.3


From b1dc9d8755d9ee605990f32d82ca39b57c7cdcbb Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 11 Jun 2018 15:10:02 +0200
Subject: drm/amdgpu: allocate shared fence slot in VA IOCTL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Per VM BOs share the reservation object with the PD and so need to
reserve a shared fence slot for the update.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 5fb156a01774..7f27cdb7afe2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -612,7 +612,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 			return -ENOENT;
 		abo = gem_to_amdgpu_bo(gobj);
 		tv.bo = &abo->tbo;
-		tv.shared = false;
+		tv.shared = !!(abo->flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID);
 		list_add(&tv.head, &list);
 	} else {
 		gobj = NULL;
-- 
cgit v1.2.3


From ecfee95a8ae7f35d43b8f63d61220e70ec8d2ea8 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Wed, 13 Jun 2018 18:26:38 +0800
Subject: drm/amd/pp: Add S3 support for OD feature

make custom values survive when S3 sleep transitions.
so not reset the od table if it is not null.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c   | 126 +++++++++++----------
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c |  79 +++++++------
 2 files changed, 107 insertions(+), 98 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index f8e866ceda02..fdb20db9c147 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -885,6 +885,60 @@ static void smu7_setup_voltage_range_from_vbios(struct pp_hwmgr *hwmgr)
 	data->odn_dpm_table.max_vddc = max_vddc;
 }
 
+static void smu7_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
+{
+	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
+	struct smu7_odn_dpm_table *odn_table = &(data->odn_dpm_table);
+	struct phm_ppt_v1_information *table_info =
+			(struct phm_ppt_v1_information *)(hwmgr->pptable);
+	uint32_t i;
+
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
+	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
+
+	if (table_info == NULL)
+		return;
+
+	for (i = 0; i < data->dpm_table.sclk_table.count; i++) {
+		if (odn_table->odn_core_clock_dpm_levels.entries[i].clock !=
+					data->dpm_table.sclk_table.dpm_levels[i].value) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
+			break;
+		}
+	}
+
+	for (i = 0; i < data->dpm_table.mclk_table.count; i++) {
+		if (odn_table->odn_memory_clock_dpm_levels.entries[i].clock !=
+					data->dpm_table.mclk_table.dpm_levels[i].value) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
+			break;
+		}
+	}
+
+	dep_table = table_info->vdd_dep_on_mclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_mclk);
+
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+			return;
+		}
+	}
+
+	dep_table = table_info->vdd_dep_on_sclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk);
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+			return;
+		}
+	}
+	if (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
+		data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+	}
+}
+
 static int smu7_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
@@ -904,10 +958,13 @@ static int smu7_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 
 	/* initialize ODN table */
 	if (hwmgr->od_enabled) {
-		smu7_setup_voltage_range_from_vbios(hwmgr);
-		smu7_odn_initial_default_setting(hwmgr);
+		if (data->odn_dpm_table.max_vddc) {
+			smu7_check_dpm_table_updated(hwmgr);
+		} else {
+			smu7_setup_voltage_range_from_vbios(hwmgr);
+			smu7_odn_initial_default_setting(hwmgr);
+		}
 	}
-
 	return 0;
 }
 
@@ -3717,8 +3774,9 @@ static int smu7_trim_single_dpm_states(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dpm_table->count; i++) {
-		if ((dpm_table->dpm_levels[i].value < low_limit)
-		|| (dpm_table->dpm_levels[i].value > high_limit))
+	/*skip the trim if od is enabled*/
+		if (!hwmgr->od_enabled && (dpm_table->dpm_levels[i].value < low_limit
+			|| dpm_table->dpm_levels[i].value > high_limit))
 			dpm_table->dpm_levels[i].enabled = false;
 		else
 			dpm_table->dpm_levels[i].enabled = true;
@@ -3762,10 +3820,8 @@ static int smu7_generate_dpm_level_enable_mask(
 	const struct smu7_power_state *smu7_ps =
 			cast_const_phw_smu7_power_state(states->pnew_state);
 
-	/*skip the trim if od is enabled*/
-	if (!hwmgr->od_enabled)
-		result = smu7_trim_dpm_states(hwmgr, smu7_ps);
 
+	result = smu7_trim_dpm_states(hwmgr, smu7_ps);
 	if (result)
 		return result;
 
@@ -4739,60 +4795,6 @@ static bool smu7_check_clk_voltage_valid(struct pp_hwmgr *hwmgr,
 	return true;
 }
 
-static void smu7_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
-{
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	struct smu7_odn_dpm_table *odn_table = &(data->odn_dpm_table);
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	uint32_t i;
-
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
-	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
-
-	if (table_info == NULL)
-		return;
-
-	for (i=0; i<data->dpm_table.sclk_table.count; i++) {
-		if (odn_table->odn_core_clock_dpm_levels.entries[i].clock !=
-					data->dpm_table.sclk_table.dpm_levels[i].value) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK;
-			break;
-		}
-	}
-
-	for (i=0; i<data->dpm_table.mclk_table.count; i++) {
-		if (odn_table->odn_memory_clock_dpm_levels.entries[i].clock !=
-					data->dpm_table.mclk_table.dpm_levels[i].value) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_MCLK;
-			break;
-		}
-	}
-
-	dep_table = table_info->vdd_dep_on_mclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_mclk);
-
-	for (i=0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
-			return;
-		}
-	}
-
-	dep_table = table_info->vdd_dep_on_sclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dependency_on_sclk);
-	for (i=0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
-			return;
-		}
-	}
-	if (data->need_update_smu7_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
-		data->need_update_smu7_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
-		data->need_update_smu7_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
-	}
-}
-
 static int smu7_odn_edit_dpm_table(struct pp_hwmgr *hwmgr,
 					enum PP_OD_DPM_TABLE_COMMAND type,
 					long *input, uint32_t size)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 05e680d55dbb..66fd1a43e346 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -2414,6 +2414,40 @@ static int vega10_populate_and_upload_avfs_fuse_override(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+static void vega10_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
+{
+	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
+	struct phm_ppt_v2_information *table_info = hwmgr->pptable;
+	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
+	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
+	uint32_t i;
+
+	dep_table = table_info->vdd_dep_on_mclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_mclk);
+
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
+			return;
+		}
+	}
+
+	dep_table = table_info->vdd_dep_on_sclk;
+	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_sclk);
+	for (i = 0; i < dep_table->count; i++) {
+		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
+			return;
+		}
+	}
+
+	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
+		data->need_update_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
+		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+	}
+}
+
 /**
 * Initializes the SMC table and uploads it
 *
@@ -2430,6 +2464,7 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 	PPTable_t *pp_table = &(data->smc_state_table.pp_table);
 	struct pp_atomfwctrl_voltage_table voltage_table;
 	struct pp_atomfwctrl_bios_boot_up_values boot_up_values;
+	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
 
 	result = vega10_setup_default_dpm_tables(hwmgr);
 	PP_ASSERT_WITH_CODE(!result,
@@ -2437,8 +2472,14 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
 			return result);
 
 	/* initialize ODN table */
-	if (hwmgr->od_enabled)
-		vega10_odn_initial_default_setting(hwmgr);
+	if (hwmgr->od_enabled) {
+		if (odn_table->max_vddc) {
+			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
+			vega10_check_dpm_table_updated(hwmgr);
+		} else {
+			vega10_odn_initial_default_setting(hwmgr);
+		}
+	}
 
 	pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC,
 			VOLTAGE_OBJ_SVID2,  &voltage_table);
@@ -4695,40 +4736,6 @@ static bool vega10_check_clk_voltage_valid(struct pp_hwmgr *hwmgr,
 	return true;
 }
 
-static void vega10_check_dpm_table_updated(struct pp_hwmgr *hwmgr)
-{
-	struct vega10_hwmgr *data = hwmgr->backend;
-	struct vega10_odn_dpm_table *odn_table = &(data->odn_dpm_table);
-	struct phm_ppt_v2_information *table_info = hwmgr->pptable;
-	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table;
-	struct phm_ppt_v1_clock_voltage_dependency_table *odn_dep_table;
-	uint32_t i;
-
-	dep_table = table_info->vdd_dep_on_mclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_mclk);
-
-	for (i = 0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_MCLK;
-			return;
-		}
-	}
-
-	dep_table = table_info->vdd_dep_on_sclk;
-	odn_dep_table = (struct phm_ppt_v1_clock_voltage_dependency_table *)&(odn_table->vdd_dep_on_sclk);
-	for (i = 0; i < dep_table->count; i++) {
-		if (dep_table->entries[i].vddc != odn_dep_table->entries[i].vddc) {
-			data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC | DPMTABLE_OD_UPDATE_SCLK;
-			return;
-		}
-	}
-
-	if (data->need_update_dpm_table & DPMTABLE_OD_UPDATE_VDDC) {
-		data->need_update_dpm_table &= ~DPMTABLE_OD_UPDATE_VDDC;
-		data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_SCLK | DPMTABLE_OD_UPDATE_MCLK;
-	}
-}
-
 static void vega10_odn_update_soc_table(struct pp_hwmgr *hwmgr,
 						enum PP_OD_DPM_TABLE_COMMAND type)
 {
-- 
cgit v1.2.3


From e1fa921f022d2401f3e3328ebf0c2ded84d4924a Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Wed, 13 Jun 2018 18:53:49 +0800
Subject: drm/amd/pp: Make sure clock_voltage_limit_table on dc is valid

if vbios not set the max clock voltage limit table for DC mode,
Set the table as sama as the table for AC mode.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index e63bc47dc715..4ef77cebc628 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -236,6 +236,11 @@ int hwmgr_hw_init(struct pp_hwmgr *hwmgr)
 	ret = hwmgr->hwmgr_func->backend_init(hwmgr);
 	if (ret)
 		goto err1;
+ /* make sure dc limits are valid */
+	if ((hwmgr->dyn_state.max_clock_voltage_on_dc.sclk == 0) ||
+			(hwmgr->dyn_state.max_clock_voltage_on_dc.mclk == 0))
+			hwmgr->dyn_state.max_clock_voltage_on_dc =
+					hwmgr->dyn_state.max_clock_voltage_on_ac;
 
 	ret = psm_init_power_state_table(hwmgr);
 	if (ret)
-- 
cgit v1.2.3


From dd06eecb73d2e5f5c4039bcd9d83d4f7e0156d6f Mon Sep 17 00:00:00 2001
From: James Zhu <James.Zhu@amd.com>
Date: Wed, 6 Jun 2018 14:38:14 -0400
Subject: drm/amdgpu/vg20:support new UVD FW version naming convention

Vega20 UVD Firmware has a new version naming convention:
  [31, 30] for encode interface major
  [29, 24] for encode interface minor
  [15, 8] for decode interface minor
  [7, 0] for hardware family id

Signed-off-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index bcf68f80bbf0..630e273c16ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -208,10 +208,21 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 
 	hdr = (const struct common_firmware_header *)adev->uvd.fw->data;
 	family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
-	version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
-	version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
-	DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
-		version_major, version_minor, family_id);
+
+	if (adev->asic_type < CHIP_VEGA20) {
+		version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
+		version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
+		DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
+			version_major, version_minor, family_id);
+	} else {
+		unsigned int enc_major, enc_minor, dec_minor;
+
+		dec_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
+		enc_minor = (le32_to_cpu(hdr->ucode_version) >> 24) & 0x3f;
+		enc_major = (le32_to_cpu(hdr->ucode_version) >> 30) & 0x3;
+		DRM_INFO("Found UVD firmware ENC: %hu.%hu DEC: .%hu Family ID: %hu\n",
+			enc_major, enc_minor, dec_minor, family_id);
+	}
 
 	/*
 	 * Limit the number of UVD handles depending on microcode major
@@ -219,7 +230,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	 * instances support is 1.80. So all subsequent versions should
 	 * also have the same support.
 	 */
-	if ((version_major > 0x01) ||
+	if (adev->asic_type >= CHIP_VEGA20 || (version_major > 0x01) ||
 	    ((version_major == 0x01) && (version_minor >= 0x50)))
 		adev->uvd.max_handles = AMDGPU_MAX_UVD_HANDLES;
 
-- 
cgit v1.2.3


From 5c2199270275581a06571960e7d6abac008ff060 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 14 Jun 2018 10:24:06 -0500
Subject: drm/amdgpu: Fix uvd firmware version information for vega20 (v2)

The uvd version information was not set correctly for vega20.
Rearrange the logic to set it correctly and fix the warnings
as a result.

v2: fix version formatting for userspace based on feedback from Leo

Fixes: 96ca7f298f (drm/amdgpu/vg20:support new UVD FW version naming convention)
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 42 +++++++++++++++++++--------------
 1 file changed, 24 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 630e273c16ce..04d77f19acc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -127,7 +127,7 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	unsigned long bo_size;
 	const char *fw_name;
 	const struct common_firmware_header *hdr;
-	unsigned version_major, version_minor, family_id;
+	unsigned family_id;
 	int i, j, r;
 
 	INIT_DELAYED_WORK(&adev->uvd.inst->idle_work, amdgpu_uvd_idle_work_handler);
@@ -210,10 +210,31 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 	family_id = le32_to_cpu(hdr->ucode_version) & 0xff;
 
 	if (adev->asic_type < CHIP_VEGA20) {
+		unsigned version_major, version_minor;
+
 		version_major = (le32_to_cpu(hdr->ucode_version) >> 24) & 0xff;
 		version_minor = (le32_to_cpu(hdr->ucode_version) >> 8) & 0xff;
 		DRM_INFO("Found UVD firmware Version: %hu.%hu Family ID: %hu\n",
 			version_major, version_minor, family_id);
+
+		/*
+		 * Limit the number of UVD handles depending on microcode major
+		 * and minor versions. The firmware version which has 40 UVD
+		 * instances support is 1.80. So all subsequent versions should
+		 * also have the same support.
+		 */
+		if ((version_major > 0x01) ||
+		    ((version_major == 0x01) && (version_minor >= 0x50)))
+			adev->uvd.max_handles = AMDGPU_MAX_UVD_HANDLES;
+
+		adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
+					(family_id << 8));
+
+		if ((adev->asic_type == CHIP_POLARIS10 ||
+		     adev->asic_type == CHIP_POLARIS11) &&
+		    (adev->uvd.fw_version < FW_1_66_16))
+			DRM_ERROR("POLARIS10/11 UVD firmware version %hu.%hu is too old.\n",
+				  version_major, version_minor);
 	} else {
 		unsigned int enc_major, enc_minor, dec_minor;
 
@@ -222,26 +243,11 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 		enc_major = (le32_to_cpu(hdr->ucode_version) >> 30) & 0x3;
 		DRM_INFO("Found UVD firmware ENC: %hu.%hu DEC: .%hu Family ID: %hu\n",
 			enc_major, enc_minor, dec_minor, family_id);
-	}
 
-	/*
-	 * Limit the number of UVD handles depending on microcode major
-	 * and minor versions. The firmware version which has 40 UVD
-	 * instances support is 1.80. So all subsequent versions should
-	 * also have the same support.
-	 */
-	if (adev->asic_type >= CHIP_VEGA20 || (version_major > 0x01) ||
-	    ((version_major == 0x01) && (version_minor >= 0x50)))
 		adev->uvd.max_handles = AMDGPU_MAX_UVD_HANDLES;
 
-	adev->uvd.fw_version = ((version_major << 24) | (version_minor << 16) |
-				(family_id << 8));
-
-	if ((adev->asic_type == CHIP_POLARIS10 ||
-	     adev->asic_type == CHIP_POLARIS11) &&
-	    (adev->uvd.fw_version < FW_1_66_16))
-		DRM_ERROR("POLARIS10/11 UVD firmware version %hu.%hu is too old.\n",
-			  version_major, version_minor);
+		adev->uvd.fw_version = le32_to_cpu(hdr->ucode_version);
+	}
 
 	bo_size = AMDGPU_UVD_STACK_SIZE + AMDGPU_UVD_HEAP_SIZE
 		  +  AMDGPU_UVD_SESSION_SIZE * adev->uvd.max_handles;
-- 
cgit v1.2.3


From fe78627d430435d22316fe39f2012ece31bf23c2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 15 Jun 2018 08:32:28 -0500
Subject: drm/amd/display: fix type of variable

Currently, the maximum value that *counter* can reach is 255, and
code at line 150: while (counter < 1000) { implies a bigger value
could be expected.

Fix this by changing the type of variable *counter* from uint8_t
to uint16_t.

Addresses-Coverity-ID: 1470030 ("Operands don't affect result")
Fixes: 2b6199a1d1b7 ("drm/amd/display: replace msleep with udelay in fbc path")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
index e2994d337044..111c4921987f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
@@ -143,7 +143,7 @@ static void wait_for_fbc_state_changed(
 	struct dce110_compressor *cp110,
 	bool enabled)
 {
-	uint8_t counter = 0;
+	uint16_t counter = 0;
 	uint32_t addr = mmFBC_STATUS;
 	uint32_t value;
 
-- 
cgit v1.2.3


From 2d33948e4e00b501b91367fed21243a948426591 Mon Sep 17 00:00:00 2001
From: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Date: Tue, 29 May 2018 11:23:07 +0530
Subject: drm/scheduler: add documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

convert existing raw comments into kernel-doc format as well
as add new documentation

v2: reword the overview

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 214 ++++++++++++++++++++++++------
 include/drm/gpu_scheduler.h               | 153 +++++++++++++++++----
 2 files changed, 296 insertions(+), 71 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 44d480768dfe..8c1e80c9b674 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -21,6 +21,29 @@
  *
  */
 
+/**
+ * DOC: Overview
+ *
+ * The GPU scheduler provides entities which allow userspace to push jobs
+ * into software queues which are then scheduled on a hardware run queue.
+ * The software queues have a priority among them. The scheduler selects the entities
+ * from the run queue using a FIFO. The scheduler provides dependency handling
+ * features among jobs. The driver is supposed to provide callback functions for
+ * backend operations to the scheduler like submitting a job to hardware run queue,
+ * returning the dependencies of a job etc.
+ *
+ * The organisation of the scheduler is the following:
+ *
+ * 1. Each hw run queue has one scheduler
+ * 2. Each scheduler has multiple run queues with different priorities
+ *    (e.g., HIGH_HW,HIGH_SW, KERNEL, NORMAL)
+ * 3. Each scheduler run queue has a queue of entities to schedule
+ * 4. Entities themselves maintain a queue of jobs that will be scheduled on
+ *    the hardware.
+ *
+ * The jobs in a entity are always scheduled in the order that they were pushed.
+ */
+
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/sched.h>
@@ -39,7 +62,13 @@ static bool drm_sched_entity_is_ready(struct drm_sched_entity *entity);
 static void drm_sched_wakeup(struct drm_gpu_scheduler *sched);
 static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
 
-/* Initialize a given run queue struct */
+/**
+ * drm_sched_rq_init - initialize a given run queue struct
+ *
+ * @rq: scheduler run queue
+ *
+ * Initializes a scheduler runqueue.
+ */
 static void drm_sched_rq_init(struct drm_sched_rq *rq)
 {
 	spin_lock_init(&rq->lock);
@@ -47,6 +76,14 @@ static void drm_sched_rq_init(struct drm_sched_rq *rq)
 	rq->current_entity = NULL;
 }
 
+/**
+ * drm_sched_rq_add_entity - add an entity
+ *
+ * @rq: scheduler run queue
+ * @entity: scheduler entity
+ *
+ * Adds a scheduler entity to the run queue.
+ */
 static void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 				    struct drm_sched_entity *entity)
 {
@@ -57,6 +94,14 @@ static void drm_sched_rq_add_entity(struct drm_sched_rq *rq,
 	spin_unlock(&rq->lock);
 }
 
+/**
+ * drm_sched_rq_remove_entity - remove an entity
+ *
+ * @rq: scheduler run queue
+ * @entity: scheduler entity
+ *
+ * Removes a scheduler entity from the run queue.
+ */
 static void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 				       struct drm_sched_entity *entity)
 {
@@ -70,9 +115,9 @@ static void drm_sched_rq_remove_entity(struct drm_sched_rq *rq,
 }
 
 /**
- * Select an entity which could provide a job to run
+ * drm_sched_rq_select_entity - Select an entity which could provide a job to run
  *
- * @rq		The run queue to check.
+ * @rq: scheduler run queue to check.
  *
  * Try to find a ready entity, returns NULL if none found.
  */
@@ -112,15 +157,16 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
 }
 
 /**
- * Init a context entity used by scheduler when submit to HW ring.
+ * drm_sched_entity_init - Init a context entity used by scheduler when
+ * submit to HW ring.
  *
- * @sched	The pointer to the scheduler
- * @entity	The pointer to a valid drm_sched_entity
- * @rq		The run queue this entity belongs
- * @guilty      atomic_t set to 1 when a job on this queue
- *              is found to be guilty causing a timeout
+ * @sched: scheduler instance
+ * @entity: scheduler entity to init
+ * @rq: the run queue this entity belongs
+ * @guilty: atomic_t set to 1 when a job on this queue
+ *          is found to be guilty causing a timeout
  *
- * return 0 if succeed. negative error code on failure
+ * Returns 0 on success or a negative error code on failure.
 */
 int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 			  struct drm_sched_entity *entity,
@@ -149,10 +195,10 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 EXPORT_SYMBOL(drm_sched_entity_init);
 
 /**
- * Query if entity is initialized
+ * drm_sched_entity_is_initialized - Query if entity is initialized
  *
- * @sched       Pointer to scheduler instance
- * @entity	The pointer to a valid scheduler entity
+ * @sched: Pointer to scheduler instance
+ * @entity: The pointer to a valid scheduler entity
  *
  * return true if entity is initialized, false otherwise
 */
@@ -164,11 +210,11 @@ static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched,
 }
 
 /**
- * Check if entity is idle
+ * drm_sched_entity_is_idle - Check if entity is idle
  *
- * @entity	The pointer to a valid scheduler entity
+ * @entity: scheduler entity
  *
- * Return true if entity don't has any unscheduled jobs.
+ * Returns true if the entity does not have any unscheduled jobs.
  */
 static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
 {
@@ -180,9 +226,9 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
 }
 
 /**
- * Check if entity is ready
+ * drm_sched_entity_is_ready - Check if entity is ready
  *
- * @entity	The pointer to a valid scheduler entity
+ * @entity: scheduler entity
  *
  * Return true if entity could provide a job.
  */
@@ -210,12 +256,12 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 
 
 /**
- * Destroy a context entity
+ * drm_sched_entity_do_release - Destroy a context entity
  *
- * @sched       Pointer to scheduler instance
- * @entity	The pointer to a valid scheduler entity
+ * @sched: scheduler instance
+ * @entity: scheduler entity
  *
- * Splitting drm_sched_entity_fini() into two functions, The first one is does the waiting,
+ * Splitting drm_sched_entity_fini() into two functions, The first one does the waiting,
  * removes the entity from the runqueue and returns an error when the process was killed.
  */
 void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
@@ -237,12 +283,13 @@ void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
 EXPORT_SYMBOL(drm_sched_entity_do_release);
 
 /**
- * Destroy a context entity
+ * drm_sched_entity_cleanup - Destroy a context entity
  *
- * @sched       Pointer to scheduler instance
- * @entity	The pointer to a valid scheduler entity
+ * @sched: scheduler instance
+ * @entity: scheduler entity
  *
- * The second one then goes over the entity and signals all jobs with an error code.
+ * This should be called after @drm_sched_entity_do_release. It goes over the
+ * entity and signals all jobs with an error code if the process was killed.
  */
 void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity)
@@ -281,6 +328,14 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 }
 EXPORT_SYMBOL(drm_sched_entity_cleanup);
 
+/**
+ * drm_sched_entity_fini - Destroy a context entity
+ *
+ * @sched: scheduler instance
+ * @entity: scheduler entity
+ *
+ * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup()
+ */
 void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
 				struct drm_sched_entity *entity)
 {
@@ -306,6 +361,15 @@ static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb
 	dma_fence_put(f);
 }
 
+/**
+ * drm_sched_entity_set_rq - Sets the run queue for an entity
+ *
+ * @entity: scheduler entity
+ * @rq: scheduler run queue
+ *
+ * Sets the run queue for an entity and removes the entity from the previous
+ * run queue in which was present.
+ */
 void drm_sched_entity_set_rq(struct drm_sched_entity *entity,
 			     struct drm_sched_rq *rq)
 {
@@ -325,6 +389,14 @@ void drm_sched_entity_set_rq(struct drm_sched_entity *entity,
 }
 EXPORT_SYMBOL(drm_sched_entity_set_rq);
 
+/**
+ * drm_sched_dependency_optimized
+ *
+ * @fence: the dependency fence
+ * @entity: the entity which depends on the above fence
+ *
+ * Returns true if the dependency can be optimized and false otherwise
+ */
 bool drm_sched_dependency_optimized(struct dma_fence* fence,
 				    struct drm_sched_entity *entity)
 {
@@ -413,9 +485,10 @@ drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 }
 
 /**
- * Submit a job to the job queue
+ * drm_sched_entity_push_job - Submit a job to the entity's job queue
  *
- * @sched_job		The pointer to job required to submit
+ * @sched_job: job to submit
+ * @entity: scheduler entity
  *
  * Note: To guarantee that the order of insertion to queue matches
  * the job's fence sequence number this function should be
@@ -506,6 +579,13 @@ static void drm_sched_job_timedout(struct work_struct *work)
 	job->sched->ops->timedout_job(job);
 }
 
+/**
+ * drm_sched_hw_job_reset - stop the scheduler if it contains the bad job
+ *
+ * @sched: scheduler instance
+ * @bad: bad scheduler job
+ *
+ */
 void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_job *bad)
 {
 	struct drm_sched_job *s_job;
@@ -550,6 +630,12 @@ void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched, struct drm_sched_jo
 }
 EXPORT_SYMBOL(drm_sched_hw_job_reset);
 
+/**
+ * drm_sched_job_recovery - recover jobs after a reset
+ *
+ * @sched: scheduler instance
+ *
+ */
 void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 {
 	struct drm_sched_job *s_job, *tmp;
@@ -599,10 +685,17 @@ void drm_sched_job_recovery(struct drm_gpu_scheduler *sched)
 EXPORT_SYMBOL(drm_sched_job_recovery);
 
 /**
- * Init a sched_job with basic field
+ * drm_sched_job_init - init a scheduler job
  *
- * Note: Refer to drm_sched_entity_push_job documentation
+ * @job: scheduler job to init
+ * @sched: scheduler instance
+ * @entity: scheduler entity to use
+ * @owner: job owner for debugging
+ *
+ * Refer to drm_sched_entity_push_job() documentation
  * for locking considerations.
+ *
+ * Returns 0 for success, negative error code otherwise.
  */
 int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_gpu_scheduler *sched,
@@ -626,7 +719,11 @@ int drm_sched_job_init(struct drm_sched_job *job,
 EXPORT_SYMBOL(drm_sched_job_init);
 
 /**
- * Return ture if we can push more jobs to the hw.
+ * drm_sched_ready - is the scheduler ready
+ *
+ * @sched: scheduler instance
+ *
+ * Return true if we can push more jobs to the hw, otherwise false.
  */
 static bool drm_sched_ready(struct drm_gpu_scheduler *sched)
 {
@@ -635,7 +732,10 @@ static bool drm_sched_ready(struct drm_gpu_scheduler *sched)
 }
 
 /**
- * Wake up the scheduler when it is ready
+ * drm_sched_wakeup - Wake up the scheduler when it is ready
+ *
+ * @sched: scheduler instance
+ *
  */
 static void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
 {
@@ -644,8 +744,12 @@ static void drm_sched_wakeup(struct drm_gpu_scheduler *sched)
 }
 
 /**
- * Select next entity to process
-*/
+ * drm_sched_select_entity - Select next entity to process
+ *
+ * @sched: scheduler instance
+ *
+ * Returns the entity to process or NULL if none are found.
+ */
 static struct drm_sched_entity *
 drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 {
@@ -665,6 +769,14 @@ drm_sched_select_entity(struct drm_gpu_scheduler *sched)
 	return entity;
 }
 
+/**
+ * drm_sched_process_job - process a job
+ *
+ * @f: fence
+ * @cb: fence callbacks
+ *
+ * Called after job has finished execution.
+ */
 static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 {
 	struct drm_sched_fence *s_fence =
@@ -680,6 +792,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb)
 	wake_up_interruptible(&sched->wake_up_worker);
 }
 
+/**
+ * drm_sched_blocked - check if the scheduler is blocked
+ *
+ * @sched: scheduler instance
+ *
+ * Returns true if blocked, otherwise false.
+ */
 static bool drm_sched_blocked(struct drm_gpu_scheduler *sched)
 {
 	if (kthread_should_park()) {
@@ -690,6 +809,13 @@ static bool drm_sched_blocked(struct drm_gpu_scheduler *sched)
 	return false;
 }
 
+/**
+ * drm_sched_main - main scheduler thread
+ *
+ * @param: scheduler instance
+ *
+ * Returns 0.
+ */
 static int drm_sched_main(void *param)
 {
 	struct sched_param sparam = {.sched_priority = 1};
@@ -744,15 +870,17 @@ static int drm_sched_main(void *param)
 }
 
 /**
- * Init a gpu scheduler instance
+ * drm_sched_init - Init a gpu scheduler instance
  *
- * @sched		The pointer to the scheduler
- * @ops			The backend operations for this scheduler.
- * @hw_submissions	Number of hw submissions to do.
- * @name		Name used for debugging
+ * @sched: scheduler instance
+ * @ops: backend operations for this scheduler
+ * @hw_submission: number of hw submissions that can be in flight
+ * @hang_limit: number of times to allow a job to hang before dropping it
+ * @timeout: timeout value in jiffies for the scheduler
+ * @name: name used for debugging
  *
  * Return 0 on success, otherwise error code.
-*/
+ */
 int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const struct drm_sched_backend_ops *ops,
 		   unsigned hw_submission,
@@ -788,9 +916,11 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 EXPORT_SYMBOL(drm_sched_init);
 
 /**
- * Destroy a gpu scheduler
+ * drm_sched_fini - Destroy a gpu scheduler
+ *
+ * @sched: scheduler instance
  *
- * @sched	The pointer to the scheduler
+ * Tears down and cleans up the scheduler.
  */
 void drm_sched_fini(struct drm_gpu_scheduler *sched)
 {
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index dec655894d08..496442f12bff 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -43,13 +43,33 @@ enum drm_sched_priority {
 };
 
 /**
- * drm_sched_entity - A wrapper around a job queue (typically attached
- * to the DRM file_priv).
+ * struct drm_sched_entity - A wrapper around a job queue (typically
+ * attached to the DRM file_priv).
+ *
+ * @list: used to append this struct to the list of entities in the
+ *        runqueue.
+ * @rq: runqueue to which this entity belongs.
+ * @rq_lock: lock to modify the runqueue to which this entity belongs.
+ * @sched: the scheduler instance to which this entity is enqueued.
+ * @job_queue: the list of jobs of this entity.
+ * @fence_seq: a linearly increasing seqno incremented with each
+ *             new &drm_sched_fence which is part of the entity.
+ * @fence_context: a unique context for all the fences which belong
+ *                 to this entity.
+ *                 The &drm_sched_fence.scheduled uses the
+ *                 fence_context but &drm_sched_fence.finished uses
+ *                 fence_context + 1.
+ * @dependency: the dependency fence of the job which is on the top
+ *              of the job queue.
+ * @cb: callback for the dependency fence above.
+ * @guilty: points to ctx's guilty.
+ * @fini_status: contains the exit status in case the process was signalled.
+ * @last_scheduled: points to the finished fence of the last scheduled job.
  *
  * Entities will emit jobs in order to their corresponding hardware
  * ring, and the scheduler will alternate between entities based on
  * scheduling policy.
-*/
+ */
 struct drm_sched_entity {
 	struct list_head		list;
 	struct drm_sched_rq		*rq;
@@ -63,47 +83,96 @@ struct drm_sched_entity {
 
 	struct dma_fence		*dependency;
 	struct dma_fence_cb		cb;
-	atomic_t			*guilty; /* points to ctx's guilty */
-	int            fini_status;
-	struct dma_fence    *last_scheduled;
+	atomic_t			*guilty;
+	int                             fini_status;
+	struct dma_fence                *last_scheduled;
 };
 
 /**
+ * struct drm_sched_rq - queue of entities to be scheduled.
+ *
+ * @lock: to modify the entities list.
+ * @entities: list of the entities to be scheduled.
+ * @current_entity: the entity which is to be scheduled.
+ *
  * Run queue is a set of entities scheduling command submissions for
  * one specific ring. It implements the scheduling policy that selects
  * the next entity to emit commands from.
-*/
+ */
 struct drm_sched_rq {
 	spinlock_t			lock;
 	struct list_head		entities;
 	struct drm_sched_entity		*current_entity;
 };
 
+/**
+ * struct drm_sched_fence - fences corresponding to the scheduling of a job.
+ */
 struct drm_sched_fence {
+        /**
+         * @scheduled: this fence is what will be signaled by the scheduler
+         * when the job is scheduled.
+         */
 	struct dma_fence		scheduled;
 
-	/* This fence is what will be signaled by the scheduler when
-	 * the job is completed.
-	 *
-	 * When setting up an out fence for the job, you should use
-	 * this, since it's available immediately upon
-	 * drm_sched_job_init(), and the fence returned by the driver
-	 * from run_job() won't be created until the dependencies have
-	 * resolved.
-	 */
+        /**
+         * @finished: this fence is what will be signaled by the scheduler
+         * when the job is completed.
+         *
+         * When setting up an out fence for the job, you should use
+         * this, since it's available immediately upon
+         * drm_sched_job_init(), and the fence returned by the driver
+         * from run_job() won't be created until the dependencies have
+         * resolved.
+         */
 	struct dma_fence		finished;
 
+        /**
+         * @cb: the callback for the parent fence below.
+         */
 	struct dma_fence_cb		cb;
+        /**
+         * @parent: the fence returned by &drm_sched_backend_ops.run_job
+         * when scheduling the job on hardware. We signal the
+         * &drm_sched_fence.finished fence once parent is signalled.
+         */
 	struct dma_fence		*parent;
+        /**
+         * @sched: the scheduler instance to which the job having this struct
+         * belongs to.
+         */
 	struct drm_gpu_scheduler	*sched;
+        /**
+         * @lock: the lock used by the scheduled and the finished fences.
+         */
 	spinlock_t			lock;
+        /**
+         * @owner: job owner for debugging
+         */
 	void				*owner;
 };
 
 struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f);
 
 /**
- * drm_sched_job - A job to be run by an entity.
+ * struct drm_sched_job - A job to be run by an entity.
+ *
+ * @queue_node: used to append this struct to the queue of jobs in an entity.
+ * @sched: the scheduler instance on which this job is scheduled.
+ * @s_fence: contains the fences for the scheduling of job.
+ * @finish_cb: the callback for the finished fence.
+ * @finish_work: schedules the function @drm_sched_job_finish once the job has
+ *               finished to remove the job from the
+ *               @drm_gpu_scheduler.ring_mirror_list.
+ * @node: used to append this struct to the @drm_gpu_scheduler.ring_mirror_list.
+ * @work_tdr: schedules a delayed call to @drm_sched_job_timedout after the timeout
+ *            interval is over.
+ * @id: a unique id assigned to each job scheduled on the scheduler.
+ * @karma: increment on every hang caused by this job. If this exceeds the hang
+ *         limit of the scheduler then the job is marked guilty and will not
+ *         be scheduled further.
+ * @s_priority: the priority of the job.
+ * @entity: the entity to which this job belongs.
  *
  * A job is created by the driver using drm_sched_job_init(), and
  * should call drm_sched_entity_push_job() once it wants the scheduler
@@ -130,38 +199,64 @@ static inline bool drm_sched_invalidate_job(struct drm_sched_job *s_job,
 }
 
 /**
+ * struct drm_sched_backend_ops
+ *
  * Define the backend operations called by the scheduler,
- * these functions should be implemented in driver side
-*/
+ * these functions should be implemented in driver side.
+ */
 struct drm_sched_backend_ops {
-	/* Called when the scheduler is considering scheduling this
-	 * job next, to get another struct dma_fence for this job to
+	/**
+         * @dependency: Called when the scheduler is considering scheduling
+         * this job next, to get another struct dma_fence for this job to
 	 * block on.  Once it returns NULL, run_job() may be called.
 	 */
 	struct dma_fence *(*dependency)(struct drm_sched_job *sched_job,
 					struct drm_sched_entity *s_entity);
 
-	/* Called to execute the job once all of the dependencies have
-	 * been resolved.  This may be called multiple times, if
+	/**
+         * @run_job: Called to execute the job once all of the dependencies
+         * have been resolved.  This may be called multiple times, if
 	 * timedout_job() has happened and drm_sched_job_recovery()
 	 * decides to try it again.
 	 */
 	struct dma_fence *(*run_job)(struct drm_sched_job *sched_job);
 
-	/* Called when a job has taken too long to execute, to trigger
-	 * GPU recovery.
+	/**
+         * @timedout_job: Called when a job has taken too long to execute,
+         * to trigger GPU recovery.
 	 */
 	void (*timedout_job)(struct drm_sched_job *sched_job);
 
-	/* Called once the job's finished fence has been signaled and
-	 * it's time to clean it up.
+	/**
+         * @free_job: Called once the job's finished fence has been signaled
+         * and it's time to clean it up.
 	 */
 	void (*free_job)(struct drm_sched_job *sched_job);
 };
 
 /**
- * One scheduler is implemented for each hardware ring
-*/
+ * struct drm_gpu_scheduler
+ *
+ * @ops: backend operations provided by the driver.
+ * @hw_submission_limit: the max size of the hardware queue.
+ * @timeout: the time after which a job is removed from the scheduler.
+ * @name: name of the ring for which this scheduler is being used.
+ * @sched_rq: priority wise array of run queues.
+ * @wake_up_worker: the wait queue on which the scheduler sleeps until a job
+ *                  is ready to be scheduled.
+ * @job_scheduled: once @drm_sched_entity_do_release is called the scheduler
+ *                 waits on this wait queue until all the scheduled jobs are
+ *                 finished.
+ * @hw_rq_count: the number of jobs currently in the hardware queue.
+ * @job_id_count: used to assign unique id to the each job.
+ * @thread: the kthread on which the scheduler which run.
+ * @ring_mirror_list: the list of jobs which are currently in the job queue.
+ * @job_list_lock: lock to protect the ring_mirror_list.
+ * @hang_limit: once the hangs by a job crosses this limit then it is marked
+ *              guilty and it will be considered for scheduling further.
+ *
+ * One scheduler is implemented for each hardware ring.
+ */
 struct drm_gpu_scheduler {
 	const struct drm_sched_backend_ops	*ops;
 	uint32_t			hw_submission_limit;
-- 
cgit v1.2.3


From 677e8622a9ae8cd9d351f98ecf120fb1c83b59d1 Mon Sep 17 00:00:00 2001
From: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Date: Fri, 25 May 2018 10:15:48 +0530
Subject: drm/doc: add a chapter for gpu scheduler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/drm-mm.rst | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
index b08e9dcd9177..96ebcc2a7b41 100644
--- a/Documentation/gpu/drm-mm.rst
+++ b/Documentation/gpu/drm-mm.rst
@@ -496,3 +496,21 @@ DRM Sync Objects
 
 .. kernel-doc:: drivers/gpu/drm/drm_syncobj.c
    :export:
+
+GPU Scheduler
+=============
+
+Overview
+--------
+
+.. kernel-doc:: drivers/gpu/drm/scheduler/gpu_scheduler.c
+   :doc: Overview
+
+Scheduler Function References
+-----------------------------
+
+.. kernel-doc:: include/drm/gpu_scheduler.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/scheduler/gpu_scheduler.c
+   :export:
-- 
cgit v1.2.3


From ea4a202053c94b1be0e056b66032961523cc9aa3 Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Tue, 1 May 2018 15:21:42 -0400
Subject: drm/amd/display: pass pipe_ctx straight to blank_pixel_data

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 10 +++++-----
 drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h         |  3 +--
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index f8e0576af6e0..52924ef50db6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2063,12 +2063,13 @@ static void update_dchubp_dpp(
 
 static void dcn10_blank_pixel_data(
 		struct dc *dc,
-		struct stream_resource *stream_res,
-		struct dc_stream_state *stream,
+		struct pipe_ctx *pipe_ctx,
 		bool blank)
 {
 	enum dc_color_space color_space;
 	struct tg_color black_color = {0};
+	struct stream_resource *stream_res = &pipe_ctx->stream_res;
+	struct dc_stream_state *stream = pipe_ctx->stream;
 
 	/* program otg blank color */
 	color_space = stream->output_color_space;
@@ -2127,8 +2128,7 @@ static void program_all_pipe_in_tree(
 		pipe_ctx->stream_res.tg->funcs->program_global_sync(
 				pipe_ctx->stream_res.tg);
 
-		dc->hwss.blank_pixel_data(dc, &pipe_ctx->stream_res,
-				pipe_ctx->stream, blank);
+		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
 	}
 
 	if (pipe_ctx->plane_state != NULL) {
@@ -2247,7 +2247,7 @@ static void dcn10_apply_ctx_for_surface(
 
 	if (num_planes == 0) {
 		/* OTG blank before remove all front end */
-		dc->hwss.blank_pixel_data(dc, &top_pipe_to_program->stream_res, top_pipe_to_program->stream, true);
+		dc->hwss.blank_pixel_data(dc, top_pipe_to_program, true);
 	}
 
 	/* Disconnect unused mpcc */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 63fc6c499789..52db80fbe987 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -160,8 +160,7 @@ struct hw_sequencer_funcs {
 				bool lock);
 	void (*blank_pixel_data)(
 			struct dc *dc,
-			struct stream_resource *stream_res,
-			struct dc_stream_state *stream,
+			struct pipe_ctx *pipe_ctx,
 			bool blank);
 
 	void (*set_bandwidth)(
-- 
cgit v1.2.3


From 66e48cd37147e153cef61bcbfbfa4771fe632207 Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Thu, 3 May 2018 17:51:07 -0400
Subject: drm/amd/display: Clean up submit_channel_request

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Vitaly Prosyak <Vitaly.Prosyak@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../display/dc/i2caux/dce110/aux_engine_dce110.c   | 34 +++++++++++-----------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
index 5f47f6c007ac..90535787a461 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
@@ -198,27 +198,27 @@ static void submit_channel_request(
 		((request->type == AUX_TRANSACTION_TYPE_I2C) &&
 		((request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE) ||
 		 (request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT)));
+	if (REG(AUXN_IMPCAL)) {
+		/* clear_aux_error */
+		REG_UPDATE_SEQ(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK,
+				1,
+				0);
 
-	/* clear_aux_error */
-	REG_UPDATE_SEQ(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK,
-			1,
-			0);
-
-	REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK,
-			1,
-			0);
-
-	/* force_default_calibrate */
-	REG_UPDATE_1BY1_2(AUXN_IMPCAL,
-			AUXN_IMPCAL_ENABLE, 1,
-			AUXN_IMPCAL_OVERRIDE_ENABLE, 0);
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK,
+				1,
+				0);
 
-	/* bug? why AUXN update EN and OVERRIDE_EN 1 by 1 while AUX P toggles OVERRIDE? */
+		/* force_default_calibrate */
+		REG_UPDATE_1BY1_2(AUXN_IMPCAL,
+				AUXN_IMPCAL_ENABLE, 1,
+				AUXN_IMPCAL_OVERRIDE_ENABLE, 0);
 
-	REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE,
-			1,
-			0);
+		/* bug? why AUXN update EN and OVERRIDE_EN 1 by 1 while AUX P toggles OVERRIDE? */
 
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE,
+				1,
+				0);
+	}
 	/* set the delay and the number of bytes to write */
 
 	/* The length include
-- 
cgit v1.2.3


From 9a08f51fa737d6cc167beb98bc21db8821b2dff2 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 3 May 2018 13:42:43 -0400
Subject: drm/amd/display: upgrade scaler math

This change will allow the viewport overlap to apply to rotated/
mirrored surfaces. Viewport overlap results in extra pixels being
added to viewport allowing the first few pixels to be scaled as
if there is no cut-off(mpo or pipe split) and allows us to get matching
crc's between scaled split and unsplit outputs of the same thing.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 419 +++++++++++++++-------
 1 file changed, 289 insertions(+), 130 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 751f3ac9d921..1d716171e581 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -522,13 +522,12 @@ static void calculate_viewport(struct pipe_ctx *pipe_ctx)
 	}
 }
 
-static void calculate_recout(struct pipe_ctx *pipe_ctx, struct view *recout_skip)
+static void calculate_recout(struct pipe_ctx *pipe_ctx, struct rect *recout_full)
 {
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	const struct dc_stream_state *stream = pipe_ctx->stream;
 	struct rect surf_src = plane_state->src_rect;
 	struct rect surf_clip = plane_state->clip_rect;
-	int recout_full_x, recout_full_y;
 	bool pri_split = pipe_ctx->bottom_pipe &&
 			pipe_ctx->bottom_pipe->plane_state == pipe_ctx->plane_state;
 	bool sec_split = pipe_ctx->top_pipe &&
@@ -597,20 +596,22 @@ static void calculate_recout(struct pipe_ctx *pipe_ctx, struct view *recout_skip
 		}
 	}
 	/* Unclipped recout offset = stream dst offset + ((surf dst offset - stream surf_src offset)
-	 * 				* 1/ stream scaling ratio) - (surf surf_src offset * 1/ full scl
-	 * 				ratio)
+	 *			* 1/ stream scaling ratio) - (surf surf_src offset * 1/ full scl
+	 *			ratio)
 	 */
-	recout_full_x = stream->dst.x + (plane_state->dst_rect.x - stream->src.x)
+	recout_full->x = stream->dst.x + (plane_state->dst_rect.x - stream->src.x)
 					* stream->dst.width / stream->src.width -
 			surf_src.x * plane_state->dst_rect.width / surf_src.width
 					* stream->dst.width / stream->src.width;
-	recout_full_y = stream->dst.y + (plane_state->dst_rect.y - stream->src.y)
+	recout_full->y = stream->dst.y + (plane_state->dst_rect.y - stream->src.y)
 					* stream->dst.height / stream->src.height -
 			surf_src.y * plane_state->dst_rect.height / surf_src.height
 					* stream->dst.height / stream->src.height;
 
-	recout_skip->width = pipe_ctx->plane_res.scl_data.recout.x - recout_full_x;
-	recout_skip->height = pipe_ctx->plane_res.scl_data.recout.y - recout_full_y;
+	recout_full->width = plane_state->dst_rect.width
+					* stream->dst.width / stream->src.width;
+	recout_full->height = plane_state->dst_rect.height
+					* stream->dst.height / stream->src.height;
 }
 
 static void calculate_scaling_ratios(struct pipe_ctx *pipe_ctx)
@@ -662,7 +663,7 @@ static void calculate_scaling_ratios(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.scl_data.ratios.vert_c, 19);
 }
 
-static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *recout_skip)
+static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct rect *recout_full)
 {
 	struct scaler_data *data = &pipe_ctx->plane_res.scl_data;
 	struct rect src = pipe_ctx->plane_state->src_rect;
@@ -680,15 +681,14 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 		flip_vert_scan_dir = true;
 	else if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270)
 		flip_horz_scan_dir = true;
-	if (pipe_ctx->plane_state->horizontal_mirror)
-		flip_horz_scan_dir = !flip_horz_scan_dir;
 
 	if (pipe_ctx->plane_state->rotation == ROTATION_ANGLE_90 ||
 			pipe_ctx->plane_state->rotation == ROTATION_ANGLE_270) {
 		rect_swap_helper(&src);
 		rect_swap_helper(&data->viewport_c);
 		rect_swap_helper(&data->viewport);
-	}
+	} else if (pipe_ctx->plane_state->horizontal_mirror)
+			flip_horz_scan_dir = !flip_horz_scan_dir;
 
 	/*
 	 * Init calculated according to formula:
@@ -708,127 +708,286 @@ static void calculate_inits_and_adj_vp(struct pipe_ctx *pipe_ctx, struct view *r
 	data->inits.v_c = dc_fixpt_truncate(dc_fixpt_add(data->inits.v_c, dc_fixpt_div_int(
 			dc_fixpt_add_int(data->ratios.vert_c, data->taps.v_taps_c + 1), 2)), 19);
 
+	if (!flip_horz_scan_dir) {
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.x + data->viewport.width) < (src.x + src.width)) {
+			int vp_clip = src.x + src.width - data->viewport.width - data->viewport.x;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h, data->ratios.horz));
 
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.width += int_part < vp_clip ? int_part : vp_clip;
+		}
+		if ((data->viewport_c.x + data->viewport_c.width) < (src.x + src.width) / vpc_div) {
+			int vp_clip = (src.x + src.width) / vpc_div -
+					data->viewport_c.width - data->viewport_c.x;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h_c, data->ratios.horz_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.width += int_part < vp_clip ? int_part : vp_clip;
+		}
 
-	/* Adjust for viewport end clip-off */
-	if ((data->viewport.x + data->viewport.width) < (src.x + src.width) && !flip_horz_scan_dir) {
-		int vp_clip = src.x + src.width - data->viewport.width - data->viewport.x;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.h, data->ratios.horz));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport.width += int_part < vp_clip ? int_part : vp_clip;
-	}
-	if ((data->viewport.y + data->viewport.height) < (src.y + src.height) && !flip_vert_scan_dir) {
-		int vp_clip = src.y + src.height - data->viewport.height - data->viewport.y;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.v, data->ratios.vert));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport.height += int_part < vp_clip ? int_part : vp_clip;
-	}
-	if ((data->viewport_c.x + data->viewport_c.width) < (src.x + src.width) / vpc_div && !flip_horz_scan_dir) {
-		int vp_clip = (src.x + src.width) / vpc_div -
-				data->viewport_c.width - data->viewport_c.x;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.h_c, data->ratios.horz_c));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport_c.width += int_part < vp_clip ? int_part : vp_clip;
-	}
-	if ((data->viewport_c.y + data->viewport_c.height) < (src.y + src.height) / vpc_div && !flip_vert_scan_dir) {
-		int vp_clip = (src.y + src.height) / vpc_div -
-				data->viewport_c.height - data->viewport_c.y;
-		int int_part = dc_fixpt_floor(
-				dc_fixpt_sub(data->inits.v_c, data->ratios.vert_c));
-
-		int_part = int_part > 0 ? int_part : 0;
-		data->viewport_c.height += int_part < vp_clip ? int_part : vp_clip;
-	}
-
-	/* Adjust for non-0 viewport offset */
-	if (data->viewport.x && !flip_horz_scan_dir) {
-		int int_part;
-
-		data->inits.h = dc_fixpt_add(data->inits.h, dc_fixpt_mul_int(
-				data->ratios.horz, recout_skip->width));
-		int_part = dc_fixpt_floor(data->inits.h) - data->viewport.x;
-		if (int_part < data->taps.h_taps) {
-			int int_adj = data->viewport.x >= (data->taps.h_taps - int_part) ?
-						(data->taps.h_taps - int_part) : data->viewport.x;
-			data->viewport.x -= int_adj;
-			data->viewport.width += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.h_taps) {
-			data->viewport.x += int_part - data->taps.h_taps;
-			data->viewport.width -= int_part - data->taps.h_taps;
-			int_part = data->taps.h_taps;
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.x) {
+			int int_part;
+
+			data->inits.h = dc_fixpt_add(data->inits.h, dc_fixpt_mul_int(
+					data->ratios.horz, data->recout.x - recout_full->x));
+			int_part = dc_fixpt_floor(data->inits.h) - data->viewport.x;
+			if (int_part < data->taps.h_taps) {
+				int int_adj = data->viewport.x >= (data->taps.h_taps - int_part) ?
+							(data->taps.h_taps - int_part) : data->viewport.x;
+				data->viewport.x -= int_adj;
+				data->viewport.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps) {
+				data->viewport.x += int_part - data->taps.h_taps;
+				data->viewport.width -= int_part - data->taps.h_taps;
+				int_part = data->taps.h_taps;
+			}
+			data->inits.h.value &= 0xffffffff;
+			data->inits.h = dc_fixpt_add_int(data->inits.h, int_part);
 		}
-		data->inits.h.value &= 0xffffffff;
-		data->inits.h = dc_fixpt_add_int(data->inits.h, int_part);
-	}
-
-	if (data->viewport_c.x && !flip_horz_scan_dir) {
-		int int_part;
-
-		data->inits.h_c = dc_fixpt_add(data->inits.h_c, dc_fixpt_mul_int(
-				data->ratios.horz_c, recout_skip->width));
-		int_part = dc_fixpt_floor(data->inits.h_c) - data->viewport_c.x;
-		if (int_part < data->taps.h_taps_c) {
-			int int_adj = data->viewport_c.x >= (data->taps.h_taps_c - int_part) ?
-					(data->taps.h_taps_c - int_part) : data->viewport_c.x;
-			data->viewport_c.x -= int_adj;
-			data->viewport_c.width += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.h_taps_c) {
-			data->viewport_c.x += int_part - data->taps.h_taps_c;
-			data->viewport_c.width -= int_part - data->taps.h_taps_c;
-			int_part = data->taps.h_taps_c;
+
+		if (data->viewport_c.x) {
+			int int_part;
+
+			data->inits.h_c = dc_fixpt_add(data->inits.h_c, dc_fixpt_mul_int(
+					data->ratios.horz_c, data->recout.x - recout_full->x));
+			int_part = dc_fixpt_floor(data->inits.h_c) - data->viewport_c.x;
+			if (int_part < data->taps.h_taps_c) {
+				int int_adj = data->viewport_c.x >= (data->taps.h_taps_c - int_part) ?
+						(data->taps.h_taps_c - int_part) : data->viewport_c.x;
+				data->viewport_c.x -= int_adj;
+				data->viewport_c.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps_c) {
+				data->viewport_c.x += int_part - data->taps.h_taps_c;
+				data->viewport_c.width -= int_part - data->taps.h_taps_c;
+				int_part = data->taps.h_taps_c;
+			}
+			data->inits.h_c.value &= 0xffffffff;
+			data->inits.h_c = dc_fixpt_add_int(data->inits.h_c, int_part);
 		}
-		data->inits.h_c.value &= 0xffffffff;
-		data->inits.h_c = dc_fixpt_add_int(data->inits.h_c, int_part);
-	}
-
-	if (data->viewport.y && !flip_vert_scan_dir) {
-		int int_part;
-
-		data->inits.v = dc_fixpt_add(data->inits.v, dc_fixpt_mul_int(
-				data->ratios.vert, recout_skip->height));
-		int_part = dc_fixpt_floor(data->inits.v) - data->viewport.y;
-		if (int_part < data->taps.v_taps) {
-			int int_adj = data->viewport.y >= (data->taps.v_taps - int_part) ?
-						(data->taps.v_taps - int_part) : data->viewport.y;
-			data->viewport.y -= int_adj;
-			data->viewport.height += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.v_taps) {
-			data->viewport.y += int_part - data->taps.v_taps;
-			data->viewport.height -= int_part - data->taps.v_taps;
-			int_part = data->taps.v_taps;
+	} else {
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.x) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h, data->ratios.horz));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.width += int_part < data->viewport.x ? int_part : data->viewport.x;
+			data->viewport.x -= int_part < data->viewport.x ? int_part : data->viewport.x;
+		}
+		if (data->viewport_c.x) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.h_c, data->ratios.horz_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.width += int_part < data->viewport_c.x ? int_part : data->viewport_c.x;
+			data->viewport_c.x -= int_part < data->viewport_c.x ? int_part : data->viewport_c.x;
 		}
-		data->inits.v.value &= 0xffffffff;
-		data->inits.v = dc_fixpt_add_int(data->inits.v, int_part);
-	}
-
-	if (data->viewport_c.y && !flip_vert_scan_dir) {
-		int int_part;
-
-		data->inits.v_c = dc_fixpt_add(data->inits.v_c, dc_fixpt_mul_int(
-				data->ratios.vert_c, recout_skip->height));
-		int_part = dc_fixpt_floor(data->inits.v_c) - data->viewport_c.y;
-		if (int_part < data->taps.v_taps_c) {
-			int int_adj = data->viewport_c.y >= (data->taps.v_taps_c - int_part) ?
-					(data->taps.v_taps_c - int_part) : data->viewport_c.y;
-			data->viewport_c.y -= int_adj;
-			data->viewport_c.height += int_adj;
-			int_part += int_adj;
-		} else if (int_part > data->taps.v_taps_c) {
-			data->viewport_c.y += int_part - data->taps.v_taps_c;
-			data->viewport_c.height -= int_part - data->taps.v_taps_c;
-			int_part = data->taps.v_taps_c;
+
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.x + data->viewport.width) < (src.x + src.width)) {
+			int int_part;
+			int end_offset = src.x + src.width
+					- data->viewport.x - data->viewport.width;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.h = dc_fixpt_add(data->inits.h, dc_fixpt_mul_int(
+					data->ratios.horz, data->recout.x - recout_full->x));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, takning into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.h) - end_offset;
+			if (int_part < data->taps.h_taps) {
+				int int_adj = end_offset >= (data->taps.h_taps - int_part) ?
+							(data->taps.h_taps - int_part) : end_offset;
+				data->viewport.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps) {
+				data->viewport.width += int_part - data->taps.h_taps;
+				int_part = data->taps.h_taps;
+			}
+			data->inits.h.value &= 0xffffffff;
+			data->inits.h = dc_fixpt_add_int(data->inits.h, int_part);
+		}
+
+		if ((data->viewport_c.x + data->viewport_c.width) < (src.x + src.width) / vpc_div) {
+			int int_part;
+			int end_offset = (src.x + src.width) / vpc_div
+					- data->viewport_c.x - data->viewport_c.width;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.h_c = dc_fixpt_add(data->inits.h_c, dc_fixpt_mul_int(
+					data->ratios.horz_c, data->recout.x - recout_full->x));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, takning into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.h_c) - end_offset;
+			if (int_part < data->taps.h_taps_c) {
+				int int_adj = end_offset >= (data->taps.h_taps_c - int_part) ?
+							(data->taps.h_taps_c - int_part) : end_offset;
+				data->viewport_c.width += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.h_taps_c) {
+				data->viewport_c.width += int_part - data->taps.h_taps_c;
+				int_part = data->taps.h_taps_c;
+			}
+			data->inits.h_c.value &= 0xffffffff;
+			data->inits.h_c = dc_fixpt_add_int(data->inits.h_c, int_part);
+		}
+
+	}
+	if (!flip_vert_scan_dir) {
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.y + data->viewport.height) < (src.y + src.height)) {
+			int vp_clip = src.y + src.height - data->viewport.height - data->viewport.y;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v, data->ratios.vert));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.height += int_part < vp_clip ? int_part : vp_clip;
+		}
+		if ((data->viewport_c.y + data->viewport_c.height) < (src.y + src.height) / vpc_div) {
+			int vp_clip = (src.y + src.height) / vpc_div -
+					data->viewport_c.height - data->viewport_c.y;
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v_c, data->ratios.vert_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.height += int_part < vp_clip ? int_part : vp_clip;
+		}
+
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.y) {
+			int int_part;
+
+			data->inits.v = dc_fixpt_add(data->inits.v, dc_fixpt_mul_int(
+					data->ratios.vert, data->recout.y - recout_full->y));
+			int_part = dc_fixpt_floor(data->inits.v) - data->viewport.y;
+			if (int_part < data->taps.v_taps) {
+				int int_adj = data->viewport.y >= (data->taps.v_taps - int_part) ?
+							(data->taps.v_taps - int_part) : data->viewport.y;
+				data->viewport.y -= int_adj;
+				data->viewport.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps) {
+				data->viewport.y += int_part - data->taps.v_taps;
+				data->viewport.height -= int_part - data->taps.v_taps;
+				int_part = data->taps.v_taps;
+			}
+			data->inits.v.value &= 0xffffffff;
+			data->inits.v = dc_fixpt_add_int(data->inits.v, int_part);
+		}
+
+		if (data->viewport_c.y) {
+			int int_part;
+
+			data->inits.v_c = dc_fixpt_add(data->inits.v_c, dc_fixpt_mul_int(
+					data->ratios.vert_c, data->recout.y - recout_full->y));
+			int_part = dc_fixpt_floor(data->inits.v_c) - data->viewport_c.y;
+			if (int_part < data->taps.v_taps_c) {
+				int int_adj = data->viewport_c.y >= (data->taps.v_taps_c - int_part) ?
+						(data->taps.v_taps_c - int_part) : data->viewport_c.y;
+				data->viewport_c.y -= int_adj;
+				data->viewport_c.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps_c) {
+				data->viewport_c.y += int_part - data->taps.v_taps_c;
+				data->viewport_c.height -= int_part - data->taps.v_taps_c;
+				int_part = data->taps.v_taps_c;
+			}
+			data->inits.v_c.value &= 0xffffffff;
+			data->inits.v_c = dc_fixpt_add_int(data->inits.v_c, int_part);
+		}
+	} else {
+		/* Adjust for non-0 viewport offset */
+		if (data->viewport.y) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v, data->ratios.vert));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport.height += int_part < data->viewport.y ? int_part : data->viewport.y;
+			data->viewport.y -= int_part < data->viewport.y ? int_part : data->viewport.y;
+		}
+		if (data->viewport_c.y) {
+			int int_part = dc_fixpt_floor(
+					dc_fixpt_sub(data->inits.v_c, data->ratios.vert_c));
+
+			int_part = int_part > 0 ? int_part : 0;
+			data->viewport_c.height += int_part < data->viewport_c.y ? int_part : data->viewport_c.y;
+			data->viewport_c.y -= int_part < data->viewport_c.y ? int_part : data->viewport_c.y;
+		}
+
+		/* Adjust for viewport end clip-off */
+		if ((data->viewport.y + data->viewport.height) < (src.y + src.height)) {
+			int int_part;
+			int end_offset = src.y + src.height
+					- data->viewport.y - data->viewport.height;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.v = dc_fixpt_add(data->inits.v, dc_fixpt_mul_int(
+					data->ratios.vert, data->recout.y - recout_full->y));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, taking into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.v) - end_offset;
+			if (int_part < data->taps.v_taps) {
+				int int_adj = end_offset >= (data->taps.v_taps - int_part) ?
+							(data->taps.v_taps - int_part) : end_offset;
+				data->viewport.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps) {
+				data->viewport.height += int_part - data->taps.v_taps;
+				int_part = data->taps.v_taps;
+			}
+			data->inits.v.value &= 0xffffffff;
+			data->inits.v = dc_fixpt_add_int(data->inits.v, int_part);
+		}
+
+		if ((data->viewport_c.y + data->viewport_c.height) < (src.y + src.height) / vpc_div) {
+			int int_part;
+			int end_offset = (src.y + src.height) / vpc_div
+					- data->viewport_c.y - data->viewport_c.height;
+
+			/*
+			 * this is init if vp had no offset, keep in mind this is from the
+			 * right side of vp due to scan direction
+			 */
+			data->inits.v_c = dc_fixpt_add(data->inits.v_c, dc_fixpt_mul_int(
+					data->ratios.vert_c, data->recout.y - recout_full->y));
+			/*
+			 * this is the difference between first pixel of viewport available to read
+			 * and init position, taking into account scan direction
+			 */
+			int_part = dc_fixpt_floor(data->inits.v_c) - end_offset;
+			if (int_part < data->taps.v_taps_c) {
+				int int_adj = end_offset >= (data->taps.v_taps_c - int_part) ?
+							(data->taps.v_taps_c - int_part) : end_offset;
+				data->viewport_c.height += int_adj;
+				int_part += int_adj;
+			} else if (int_part > data->taps.v_taps_c) {
+				data->viewport_c.height += int_part - data->taps.v_taps_c;
+				int_part = data->taps.v_taps_c;
+			}
+			data->inits.v_c.value &= 0xffffffff;
+			data->inits.v_c = dc_fixpt_add_int(data->inits.v_c, int_part);
 		}
-		data->inits.v_c.value &= 0xffffffff;
-		data->inits.v_c = dc_fixpt_add_int(data->inits.v_c, int_part);
 	}
 
 	/* Interlaced inits based on final vert inits */
@@ -846,7 +1005,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 {
 	const struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct dc_crtc_timing *timing = &pipe_ctx->stream->timing;
-	struct view recout_skip = { 0 };
+	struct rect recout_full = { 0 };
 	bool res = false;
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 	/* Important: scaling ratio calculation requires pixel format,
@@ -866,7 +1025,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	if (pipe_ctx->plane_res.scl_data.viewport.height < 16 || pipe_ctx->plane_res.scl_data.viewport.width < 16)
 		return false;
 
-	calculate_recout(pipe_ctx, &recout_skip);
+	calculate_recout(pipe_ctx, &recout_full);
 
 	/**
 	 * Setting line buffer pixel depth to 24bpp yields banding
@@ -910,7 +1069,7 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 
 	if (res)
 		/* May need to re-check lb size after this in some obscure scenario */
-		calculate_inits_and_adj_vp(pipe_ctx, &recout_skip);
+		calculate_inits_and_adj_vp(pipe_ctx, &recout_full);
 
 	DC_LOG_SCALER(
 				"%s: Viewport:\nheight:%d width:%d x:%d "
-- 
cgit v1.2.3


From ae2389e0fc3d4608ebb212c5c655ac964a4ee501 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Mon, 16 Apr 2018 13:31:05 -0400
Subject: drm/amd/display: dal 3.1.45

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9cfde0ccf4e9..f01c6c1711d7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.44"
+#define DC_VER "3.1.45"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From f9430b235dd46c7753a018fa39e3c31981b0a54d Mon Sep 17 00:00:00 2001
From: Anthony Koo <Anthony.Koo@amd.com>
Date: Tue, 8 May 2018 11:24:05 -0400
Subject: drm/amd/display: Prefix event prints with ==Event==

Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/modules/stats/stats.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/modules/stats/stats.c b/drivers/gpu/drm/amd/display/modules/stats/stats.c
index 3f7d47fdc367..fa0665d09075 100644
--- a/drivers/gpu/drm/amd/display/modules/stats/stats.c
+++ b/drivers/gpu/drm/amd/display/modules/stats/stats.c
@@ -240,7 +240,7 @@ void mod_stats_dump(struct mod_stats *mod_stats)
 	for (int i = 0; i < core_stats->entry_id; i++) {
 		if (event_index < core_stats->event_index &&
 				i == events[event_index].entry_id) {
-			DISPLAY_STATS("%s\n", events[event_index].event_string);
+			DISPLAY_STATS("==Event==%s\n", events[event_index].event_string);
 			event_index++;
 		} else if (time_index < core_stats->index &&
 				i == time[time_index].entry_id) {
-- 
cgit v1.2.3


From 73770ca53f63489b32175ab8b5ddd4632b747275 Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Mon, 23 Apr 2018 19:21:45 -0400
Subject: drm/amd/display: AUX will exit when HPD LOW detected

This change shorten wait time when HPD LOW. With HPD LOW, without this
change, AUX routine delay is 450us. With this change, it is 42us.

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c | 16 ++++++++++++++++
 drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h |  5 ++++-
 .../display/dc/i2caux/dce110/aux_engine_dce110.c   | 22 +++++++++++++++++-----
 drivers/gpu/drm/amd/display/dc/i2caux/engine.h     |  3 ++-
 .../drm/amd/display/include/ddc_service_types.h    |  3 ++-
 5 files changed, 41 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
index bb526ad326e5..1d7309611978 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
@@ -157,6 +157,10 @@ static void process_read_reply(
 			ctx->operation_succeeded = false;
 		}
 	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
@@ -215,6 +219,10 @@ static void process_read_request(
 			 * so we should not wait here */
 		}
 	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
@@ -370,6 +378,10 @@ static void process_write_reply(
 			ctx->operation_succeeded = false;
 		}
 	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
@@ -422,6 +434,10 @@ static void process_write_request(
 			 * so we should not wait here */
 		}
 	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
 	default:
 		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
 		ctx->operation_succeeded = false;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
index 8e71324ccb10..b9e35d0474c6 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
@@ -51,6 +51,8 @@ enum aux_transaction_reply {
 	AUX_TRANSACTION_REPLY_I2C_NACK = 0x10,
 	AUX_TRANSACTION_REPLY_I2C_DEFER = 0x20,
 
+	AUX_TRANSACTION_REPLY_HPD_DISCON = 0x40,
+
 	AUX_TRANSACTION_REPLY_INVALID = 0xFF
 };
 
@@ -64,7 +66,8 @@ enum aux_channel_operation_result {
 	AUX_CHANNEL_OPERATION_SUCCEEDED,
 	AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN,
 	AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY,
-	AUX_CHANNEL_OPERATION_FAILED_TIMEOUT
+	AUX_CHANNEL_OPERATION_FAILED_TIMEOUT,
+	AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON
 };
 
 struct aux_engine;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
index 90535787a461..2b927f25937b 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
@@ -291,6 +291,12 @@ static void process_channel_reply(
 	value = REG_GET(AUX_SW_STATUS,
 			AUX_SW_REPLY_BYTE_COUNT, &bytes_replied);
 
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+		reply->status = AUX_TRANSACTION_REPLY_HPD_DISCON;
+		return;
+	}
+
 	if (bytes_replied) {
 		uint32_t reply_result;
 
@@ -347,8 +353,10 @@ static void process_channel_reply(
 		 * because there was surely an error that was asserted
 		 * that should have been handled
 		 * for hot plug case, this could happens*/
-		if (!(value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		if (!(value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
 			ASSERT_CRITICAL(false);
+		}
 	}
 }
 
@@ -371,6 +379,10 @@ static enum aux_channel_operation_result get_channel_status(
 	value = REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 1,
 				10, aux110->timeout_period/10);
 
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+
 	/* Note that the following bits are set in 'status.bits'
 	 * during CTS 4.2.1.2 (FW 3.3.1):
 	 * AUX_SW_RX_MIN_COUNT_VIOL, AUX_SW_RX_INVALID_STOP,
@@ -402,10 +414,10 @@ static enum aux_channel_operation_result get_channel_status(
 			return AUX_CHANNEL_OPERATION_SUCCEEDED;
 		}
 	} else {
-		/*time_elapsed >= aux_engine->timeout_period */
-		if (!(value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
-			ASSERT_CRITICAL(false);
-
+		/*time_elapsed >= aux_engine->timeout_period
+		 *  AUX_SW_STATUS__AUX_SW_HPD_DISCON = at this point
+		 */
+		ASSERT_CRITICAL(false);
 		return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
index 33de8a8834dc..c1109706a880 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
@@ -53,7 +53,8 @@ enum i2caux_transaction_status {
 	I2CAUX_TRANSACTION_STATUS_FAILED_INCOMPLETE,
 	I2CAUX_TRANSACTION_STATUS_FAILED_OPERATION,
 	I2CAUX_TRANSACTION_STATUS_FAILED_INVALID_OPERATION,
-	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW
+	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW,
+	I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON
 };
 
 struct i2caux_transaction_request {
diff --git a/drivers/gpu/drm/amd/display/include/ddc_service_types.h b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
index 019e7a095ea1..d968956a10cd 100644
--- a/drivers/gpu/drm/amd/display/include/ddc_service_types.h
+++ b/drivers/gpu/drm/amd/display/include/ddc_service_types.h
@@ -40,7 +40,8 @@ enum ddc_result {
 	DDC_RESULT_FAILED_INCOMPLETE,
 	DDC_RESULT_FAILED_OPERATION,
 	DDC_RESULT_FAILED_INVALID_OPERATION,
-	DDC_RESULT_FAILED_BUFFER_OVERFLOW
+	DDC_RESULT_FAILED_BUFFER_OVERFLOW,
+	DDC_RESULT_FAILED_HPD_DISCON
 };
 
 enum ddc_service_type {
-- 
cgit v1.2.3


From 0f6ca3bac44dd6c16e3b4c484243bbb1dad3f6a7 Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Tue, 8 May 2018 16:20:52 -0400
Subject: drm/amd/display: Add function to get optc active size

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c  | 32 ++++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h  |  4 +++
 .../drm/amd/display/dc/inc/hw/timing_generator.h   |  3 ++
 3 files changed, 39 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index f2fbce0e3fc5..e6a3ade154b9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -1257,6 +1257,37 @@ void optc1_read_otg_state(struct optc *optc1,
 			OPTC_UNDERFLOW_OCCURRED_STATUS, &s->underflow_occurred_status);
 }
 
+bool optc1_get_otg_active_size(struct timing_generator *optc,
+		uint32_t *otg_active_width,
+		uint32_t *otg_active_height)
+{
+	uint32_t otg_enabled;
+	uint32_t v_blank_start;
+	uint32_t v_blank_end;
+	uint32_t h_blank_start;
+	uint32_t h_blank_end;
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+
+	REG_GET(OTG_CONTROL,
+			OTG_MASTER_EN, &otg_enabled);
+
+	if (otg_enabled == 0)
+		return false;
+
+	REG_GET_2(OTG_V_BLANK_START_END,
+			OTG_V_BLANK_START, &v_blank_start,
+			OTG_V_BLANK_END, &v_blank_end);
+
+	REG_GET_2(OTG_H_BLANK_START_END,
+			OTG_H_BLANK_START, &h_blank_start,
+			OTG_H_BLANK_END, &h_blank_end);
+
+	*otg_active_width = v_blank_start - v_blank_end;
+	*otg_active_height = h_blank_start - h_blank_end;
+	return true;
+}
+
 void optc1_clear_optc_underflow(struct timing_generator *optc)
 {
 	struct optc *optc1 = DCN10TG_FROM_TG(optc);
@@ -1305,6 +1336,7 @@ static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.get_position = optc1_get_position,
 		.get_frame_count = optc1_get_vblank_counter,
 		.get_scanoutpos = optc1_get_crtc_scanoutpos,
+		.get_otg_active_size = optc1_get_otg_active_size,
 		.set_early_control = optc1_set_early_control,
 		/* used by enable_timing_synchronization. Not need for FPGA */
 		.wait_for_state = optc1_wait_for_state,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index c62052f46460..59ed272e0c49 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -507,4 +507,8 @@ bool optc1_is_optc_underflow_occurred(struct timing_generator *optc);
 
 void optc1_set_blank_data_double_buffer(struct timing_generator *optc, bool enable);
 
+bool optc1_get_otg_active_size(struct timing_generator *optc,
+		uint32_t *otg_active_width,
+		uint32_t *otg_active_height);
+
 #endif /* __DC_TIMING_GENERATOR_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
index 69cb0a105300..af700c7dac50 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h
@@ -156,6 +156,9 @@ struct timing_generator_funcs {
 		uint32_t *v_blank_end,
 		uint32_t *h_position,
 		uint32_t *v_position);
+	bool (*get_otg_active_size)(struct timing_generator *optc,
+			uint32_t *otg_active_width,
+			uint32_t *otg_active_height);
 	void (*set_early_control)(struct timing_generator *tg,
 							   uint32_t early_cntl);
 	void (*wait_for_state)(struct timing_generator *tg,
-- 
cgit v1.2.3


From 8ca809008571f87e7d73535175601328175dac81 Mon Sep 17 00:00:00 2001
From: Anthony Koo <Anthony.Koo@amd.com>
Date: Tue, 8 May 2018 17:08:57 -0400
Subject: drm/amd/display: add DPCD read for Sink ieee OUI

Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 7857cb42b3e6..1a42ee5113a9 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2305,6 +2305,7 @@ static bool retrieve_link_cap(struct dc_link *link)
 {
 	uint8_t dpcd_data[DP_ADAPTER_CAP - DP_DPCD_REV + 1];
 
+	struct dp_device_vendor_id sink_id;
 	union down_stream_port_count down_strm_port_count;
 	union edp_configuration_cap edp_config_cap;
 	union dp_downstream_port_present ds_port = { 0 };
@@ -2391,6 +2392,17 @@ static bool retrieve_link_cap(struct dc_link *link)
 			&link->dpcd_caps.sink_count.raw,
 			sizeof(link->dpcd_caps.sink_count.raw));
 
+	/* read sink ieee oui */
+	core_link_read_dpcd(link,
+			DP_SINK_OUI,
+			(uint8_t *)(&sink_id),
+			sizeof(sink_id));
+
+	link->dpcd_caps.sink_dev_id =
+			(sink_id.ieee_oui[0] << 16) +
+			(sink_id.ieee_oui[1] << 8) +
+			(sink_id.ieee_oui[2]);
+
 	/* Connectivity log: detection */
 	CONN_DATA_DETECT(link, dpcd_data, sizeof(dpcd_data), "Rx Caps: ");
 
-- 
cgit v1.2.3


From cb1d7eacb58f7d1b7d0e57b26dc02d45eada4a3c Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Tue, 8 May 2018 16:35:09 -0400
Subject: drm/amd/display: Fix indentation in dcn10 resource constructor

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index df5cb2d1d164..99c223bcad71 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1004,7 +1004,8 @@ static bool construct(
 
 	ctx->dc_bios->regs = &bios_regs;
 
-	pool->base.res_cap = &res_cap;
+		pool->base.res_cap = &res_cap;
+
 	pool->base.funcs = &dcn10_res_pool_funcs;
 
 	/*
-- 
cgit v1.2.3


From bf58968647729ce320a7ef27077d60b7b2cdcd00 Mon Sep 17 00:00:00 2001
From: Aric Cyr <aric.cyr@amd.com>
Date: Wed, 9 May 2018 14:36:50 -0400
Subject: drm/amd/display: Default log masks should include all connectivity
 events

Signed-off-by: Aric Cyr <aric.cyr@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/basics/log_helpers.c    |  2 +
 drivers/gpu/drm/amd/display/dc/basics/logger.c     | 83 +++++++++++-----------
 .../gpu/drm/amd/display/include/logger_interface.h |  2 +
 3 files changed, 46 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
index 021451549ff7..f6c00a51d51a 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
@@ -78,6 +78,8 @@ void dc_conn_log(struct dc_context *ctx,
 	if (i == NUM_ELEMENTS(signal_type_info_tbl))
 		goto fail;
 
+	dm_logger_append_heading(&entry);
+
 	dm_logger_append(&entry, "[%s][ConnIdx:%d] ",
 			signal_type_info_tbl[i].name,
 			link->link_index);
diff --git a/drivers/gpu/drm/amd/display/dc/basics/logger.c b/drivers/gpu/drm/amd/display/dc/basics/logger.c
index 738a818d58d1..733bc5bd760b 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/logger.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/logger.c
@@ -32,8 +32,9 @@
 static const struct dc_log_type_info log_type_info_tbl[] = {
 		{LOG_ERROR,                 "Error"},
 		{LOG_WARNING,               "Warning"},
-		{LOG_DEBUG,		    "Debug"},
+		{LOG_DEBUG,                 "Debug"},
 		{LOG_DC,                    "DC_Interface"},
+		{LOG_DTN,                   "DTN"},
 		{LOG_SURFACE,               "Surface"},
 		{LOG_HW_HOTPLUG,            "HW_Hotplug"},
 		{LOG_HW_LINK_TRAINING,      "HW_LKTN"},
@@ -60,7 +61,7 @@ static const struct dc_log_type_info log_type_info_tbl[] = {
 		{LOG_EVENT_LINK_LOSS,       "LinkLoss"},
 		{LOG_EVENT_UNDERFLOW,       "Underflow"},
 		{LOG_IF_TRACE,              "InterfaceTrace"},
-		{LOG_DTN,                   "DTN"},
+		{LOG_PERF_TRACE,            "PerfTrace"},
 		{LOG_DISPLAYSTATS,          "DisplayStats"}
 };
 
@@ -128,8 +129,45 @@ uint32_t dal_logger_destroy(struct dal_logger **logger)
 }
 
 /* ------------------------------------------------------------------------ */
+void dm_logger_append_heading(struct log_entry *entry)
+{
+	int j;
+
+	for (j = 0; j < NUM_ELEMENTS(log_type_info_tbl); j++) {
 
+		const struct dc_log_type_info *info = &log_type_info_tbl[j];
 
+		if (info->type == entry->type)
+			dm_logger_append(entry, "[%s]\t", info->name);
+	}
+}
+
+
+/* Print everything unread existing in log_buffer to debug console*/
+void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn)
+{
+	char *string_start = &logger->log_buffer[logger->buffer_read_offset];
+
+	if (should_warn)
+		dm_output_to_console(
+			"---------------- FLUSHING LOG BUFFER ----------------\n");
+	while (logger->buffer_read_offset < logger->buffer_write_offset) {
+
+		if (logger->log_buffer[logger->buffer_read_offset] == '\0') {
+			dm_output_to_console("%s", string_start);
+			string_start = logger->log_buffer + logger->buffer_read_offset + 1;
+		}
+		logger->buffer_read_offset++;
+	}
+	if (should_warn)
+		dm_output_to_console(
+			"-------------- END FLUSHING LOG BUFFER --------------\n\n");
+}
+/* ------------------------------------------------------------------------ */
+
+/* Warning: Be careful that 'msg' is null terminated and the total size is
+ * less than DAL_LOGGER_BUFFER_MAX_LOG_LINE_SIZE (256) including '\0'
+ */
 static bool dal_logger_should_log(
 	struct dal_logger *logger,
 	enum dc_log_type log_type)
@@ -159,26 +197,6 @@ static void log_to_debug_console(struct log_entry *entry)
 	}
 }
 
-/* Print everything unread existing in log_buffer to debug console*/
-void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn)
-{
-	char *string_start = &logger->log_buffer[logger->buffer_read_offset];
-
-	if (should_warn)
-		dm_output_to_console(
-			"---------------- FLUSHING LOG BUFFER ----------------\n");
-	while (logger->buffer_read_offset < logger->buffer_write_offset) {
-
-		if (logger->log_buffer[logger->buffer_read_offset] == '\0') {
-			dm_output_to_console("%s", string_start);
-			string_start = logger->log_buffer + logger->buffer_read_offset + 1;
-		}
-		logger->buffer_read_offset++;
-	}
-	if (should_warn)
-		dm_output_to_console(
-			"-------------- END FLUSHING LOG BUFFER --------------\n\n");
-}
 
 static void log_to_internal_buffer(struct log_entry *entry)
 {
@@ -229,19 +247,6 @@ static void log_to_internal_buffer(struct log_entry *entry)
 	}
 }
 
-static void log_heading(struct log_entry *entry)
-{
-	int j;
-
-	for (j = 0; j < NUM_ELEMENTS(log_type_info_tbl); j++) {
-
-		const struct dc_log_type_info *info = &log_type_info_tbl[j];
-
-		if (info->type == entry->type)
-			dm_logger_append(entry, "[%s]\t", info->name);
-	}
-}
-
 static void append_entry(
 		struct log_entry *entry,
 		char *buffer,
@@ -259,11 +264,7 @@ static void append_entry(
 	entry->buf_offset += buf_size;
 }
 
-/* ------------------------------------------------------------------------ */
 
-/* Warning: Be careful that 'msg' is null terminated and the total size is
- * less than DAL_LOGGER_BUFFER_MAX_LOG_LINE_SIZE (256) including '\0'
- */
 void dm_logger_write(
 	struct dal_logger *logger,
 	enum dc_log_type log_type,
@@ -287,7 +288,7 @@ void dm_logger_write(
 
 		entry.type = log_type;
 
-		log_heading(&entry);
+		dm_logger_append_heading(&entry);
 
 		size = dm_log_to_buffer(
 			buffer, LOG_MAX_LINE_SIZE - 1, msg, args);
@@ -372,7 +373,7 @@ void dm_logger_open(
 
 	logger->open_count++;
 
-	log_heading(entry);
+	dm_logger_append_heading(entry);
 }
 
 void dm_logger_close(struct log_entry *entry)
diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h
index dc98d6d4b2bd..0f10ed710e0d 100644
--- a/drivers/gpu/drm/amd/display/include/logger_interface.h
+++ b/drivers/gpu/drm/amd/display/include/logger_interface.h
@@ -62,6 +62,8 @@ void dm_logger_append_va(
 		const char *msg,
 		va_list args);
 
+void dm_logger_append_heading(struct log_entry *entry);
+
 void dm_logger_open(
 		struct dal_logger *logger,
 		struct log_entry *entry,
-- 
cgit v1.2.3


From 3c8e4316a0bf6f65e8fbcf777abbc3b0e629e800 Mon Sep 17 00:00:00 2001
From: Nikola Cornij <nikola.cornij@amd.com>
Date: Wed, 9 May 2018 17:07:36 -0400
Subject: drm/amd/display: Optimize DP_SINK_STATUS_ESI range read on HPD

DP_SINK_STATUS_ESI range data is not continual, but rather than
getting it in two AUX reads, it's quicker to read more bytes in a
AUX read and then memcpy the required fields (it's only 8 more
bytes to read).

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 1a42ee5113a9..509f265663d2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1647,22 +1647,26 @@ static enum dc_status read_hpd_rx_irq_data(
 			irq_data->raw,
 			sizeof(union hpd_irq_data));
 	else {
-		/* Read 2 bytes at this location,... */
+		/* Read 14 bytes in a single read and then copy only the required fields.
+		 * This is more efficient than doing it in two separate AUX reads. */
+
+		uint8_t tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI + 1];
+
 		retval = core_link_read_dpcd(
 			link,
 			DP_SINK_COUNT_ESI,
-			irq_data->raw,
-			2);
+			tmp,
+			sizeof(tmp));
 
 		if (retval != DC_OK)
 			return retval;
 
-		/* ... then read remaining 4 at the other location */
-		retval = core_link_read_dpcd(
-			link,
-			DP_LANE0_1_STATUS_ESI,
-			&irq_data->raw[2],
-			4);
+		irq_data->bytes.sink_cnt.raw = tmp[DP_SINK_COUNT_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.device_service_irq.raw = tmp[DP_DEVICE_SERVICE_IRQ_VECTOR_ESI0 - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane01_status.raw = tmp[DP_LANE0_1_STATUS_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane23_status.raw = tmp[DP_LANE2_3_STATUS_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.lane_status_updated.raw = tmp[DP_LANE_ALIGN_STATUS_UPDATED_ESI - DP_SINK_COUNT_ESI];
+		irq_data->bytes.sink_status.raw = tmp[DP_SINK_STATUS_ESI - DP_SINK_COUNT_ESI];
 	}
 
 	return retval;
-- 
cgit v1.2.3


From 4ea209073d229a0cb65f9978e83fa7c044026416 Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Tue, 8 May 2018 16:03:58 -0400
Subject: drm/amd/display: Dynamic HDR metadata mem buffer

Basic framework:
- caps for reporting dynamic HDR metadata support
- allocation of frame buffer memory and storage

Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h        | 1 +
 drivers/gpu/drm/amd/display/dc/dc_stream.h | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index f01c6c1711d7..22d113eca452 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -68,6 +68,7 @@ struct dc_caps {
 	uint32_t max_planes;
 	uint32_t max_downscale_ratio;
 	uint32_t i2c_speed_in_khz;
+	uint32_t dmdata_alloc_size;
 	unsigned int max_cursor_size;
 	unsigned int max_video_width;
 	int linear_pitch_alignment;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index d7e6d53bb383..e6e944423b3c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -59,6 +59,8 @@ struct dc_stream_state {
 	struct freesync_context freesync_ctx;
 
 	struct dc_info_packet hdr_static_metadata;
+	PHYSICAL_ADDRESS_LOC dmdata_address;
+
 	struct dc_transfer_func *out_transfer_func;
 	struct colorspace_transform gamut_remap_matrix;
 	struct dc_csc_transform csc_color_matrix;
-- 
cgit v1.2.3


From 1a05873f21d6192575382afd2feb18df935e46f0 Mon Sep 17 00:00:00 2001
From: Anthony Koo <Anthony.Koo@amd.com>
Date: Thu, 10 May 2018 14:21:47 -0400
Subject: drm/amd/display: Refactor audio programming

Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c      |  24 +-
 .../amd/display/dc/dce110/dce110_hw_sequencer.c    | 256 ++++++++++++---------
 .../amd/display/dc/dce110/dce110_hw_sequencer.h    |   4 +
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  |  16 +-
 drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h  |   5 +
 5 files changed, 163 insertions(+), 142 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 2fa521812d23..a9485c10fd77 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1861,28 +1861,6 @@ static enum dc_status enable_link(
 		break;
 	}
 
-	if (pipe_ctx->stream_res.audio && status == DC_OK) {
-		struct dc *core_dc = pipe_ctx->stream->ctx->dc;
-		/* notify audio driver for audio modes of monitor */
-		struct pp_smu_funcs_rv *pp_smu = core_dc->res_pool->pp_smu;
-		unsigned int i, num_audio = 1;
-		for (i = 0; i < MAX_PIPES; i++) {
-			/*current_state not updated yet*/
-			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
-				num_audio++;
-		}
-
-		pipe_ctx->stream_res.audio->funcs->az_enable(pipe_ctx->stream_res.audio);
-
-		if (num_audio == 1 && pp_smu != NULL && pp_smu->set_pme_wa_enable != NULL)
-			/*this is the first audio. apply the PME w/a in order to wake AZ from D3*/
-			pp_smu->set_pme_wa_enable(&pp_smu->pp_smu);
-		/* un-mute audio */
-		/* TODO: audio should be per stream rather than per link */
-		pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
-			pipe_ctx->stream_res.stream_enc, false);
-	}
-
 	return status;
 }
 
@@ -2415,6 +2393,8 @@ void core_link_enable_stream(
 			}
 	}
 
+	core_dc->hwss.enable_audio_stream(pipe_ctx);
+
 	/* turn off otg test pattern if enable */
 	pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 			CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index c29052b6da5a..cae0054c102a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -972,19 +972,35 @@ void hwss_edp_backlight_control(
 		edp_receiver_ready_T9(link);
 }
 
-void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
+void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx)
 {
-	struct dc_stream_state *stream = pipe_ctx->stream;
-	struct dc_link *link = stream->sink->link;
-	struct dc *dc = pipe_ctx->stream->ctx->dc;
+	struct dc *core_dc = pipe_ctx->stream->ctx->dc;
+	/* notify audio driver for audio modes of monitor */
+	struct pp_smu_funcs_rv *pp_smu = core_dc->res_pool->pp_smu;
+	unsigned int i, num_audio = 1;
 
-	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
-		pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
-			pipe_ctx->stream_res.stream_enc);
+	if (pipe_ctx->stream_res.audio) {
+		for (i = 0; i < MAX_PIPES; i++) {
+			/*current_state not updated yet*/
+			if (core_dc->current_state->res_ctx.pipe_ctx[i].stream_res.audio != NULL)
+				num_audio++;
+		}
 
-	if (dc_is_dp_signal(pipe_ctx->stream->signal))
-		pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
-			pipe_ctx->stream_res.stream_enc);
+		pipe_ctx->stream_res.audio->funcs->az_enable(pipe_ctx->stream_res.audio);
+
+		if (num_audio == 1 && pp_smu != NULL && pp_smu->set_pme_wa_enable != NULL)
+			/*this is the first audio. apply the PME w/a in order to wake AZ from D3*/
+			pp_smu->set_pme_wa_enable(&pp_smu->pp_smu);
+		/* un-mute audio */
+		/* TODO: audio should be per stream rather than per link */
+		pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
+			pipe_ctx->stream_res.stream_enc, false);
+	}
+}
+
+void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option)
+{
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
 
 	pipe_ctx->stream_res.stream_enc->funcs->audio_mute_control(
 			pipe_ctx->stream_res.stream_enc, true);
@@ -1015,7 +1031,23 @@ void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
 		 * stream->stream_engine_id);
 		 */
 	}
+}
 
+void dce110_disable_stream(struct pipe_ctx *pipe_ctx, int option)
+{
+	struct dc_stream_state *stream = pipe_ctx->stream;
+	struct dc_link *link = stream->sink->link;
+	struct dc *dc = pipe_ctx->stream->ctx->dc;
+
+	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+		pipe_ctx->stream_res.stream_enc->funcs->stop_hdmi_info_packets(
+			pipe_ctx->stream_res.stream_enc);
+
+	if (dc_is_dp_signal(pipe_ctx->stream->signal))
+		pipe_ctx->stream_res.stream_enc->funcs->stop_dp_info_packets(
+			pipe_ctx->stream_res.stream_enc);
+
+	dc->hwss.disable_audio_stream(pipe_ctx, option);
 
 	link->link_enc->funcs->connect_dig_be_to_fe(
 			link->link_enc,
@@ -1298,6 +1330,30 @@ static enum dc_status apply_single_controller_ctx_to_hw(
 	struct pipe_ctx *pipe_ctx_old = &dc->current_state->res_ctx.
 			pipe_ctx[pipe_ctx->pipe_idx];
 
+	if (pipe_ctx->stream_res.audio != NULL) {
+		struct audio_output audio_output;
+
+		build_audio_output(context, pipe_ctx, &audio_output);
+
+		if (dc_is_dp_signal(pipe_ctx->stream->signal))
+			pipe_ctx->stream_res.stream_enc->funcs->dp_audio_setup(
+					pipe_ctx->stream_res.stream_enc,
+					pipe_ctx->stream_res.audio->inst,
+					&pipe_ctx->stream->audio_info);
+		else
+			pipe_ctx->stream_res.stream_enc->funcs->hdmi_audio_setup(
+					pipe_ctx->stream_res.stream_enc,
+					pipe_ctx->stream_res.audio->inst,
+					&pipe_ctx->stream->audio_info,
+					&audio_output.crtc_info);
+
+		pipe_ctx->stream_res.audio->funcs->az_configure(
+				pipe_ctx->stream_res.audio,
+				pipe_ctx->stream->signal,
+				&audio_output.crtc_info,
+				&pipe_ctx->stream->audio_info);
+	}
+
 	/*  */
 	dc->hwss.enable_stream_timing(pipe_ctx, context, dc);
 
@@ -1949,6 +2005,86 @@ static void dce110_reset_hw_ctx_wrap(
 	}
 }
 
+static void dce110_setup_audio_dto(
+		struct dc *dc,
+		struct dc_state *context)
+{
+	int i;
+
+	/* program audio wall clock. use HDMI as clock source if HDMI
+	 * audio active. Otherwise, use DP as clock source
+	 * first, loop to find any HDMI audio, if not, loop find DP audio
+	 */
+	/* Setup audio rate clock source */
+	/* Issue:
+	* Audio lag happened on DP monitor when unplug a HDMI monitor
+	*
+	* Cause:
+	* In case of DP and HDMI connected or HDMI only, DCCG_AUDIO_DTO_SEL
+	* is set to either dto0 or dto1, audio should work fine.
+	* In case of DP connected only, DCCG_AUDIO_DTO_SEL should be dto1,
+	* set to dto0 will cause audio lag.
+	*
+	* Solution:
+	* Not optimized audio wall dto setup. When mode set, iterate pipe_ctx,
+	* find first available pipe with audio, setup audio wall DTO per topology
+	* instead of per pipe.
+	*/
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		if (pipe_ctx->top_pipe)
+			continue;
+
+		if (pipe_ctx->stream->signal != SIGNAL_TYPE_HDMI_TYPE_A)
+			continue;
+
+		if (pipe_ctx->stream_res.audio != NULL) {
+			struct audio_output audio_output;
+
+			build_audio_output(context, pipe_ctx, &audio_output);
+
+			pipe_ctx->stream_res.audio->funcs->wall_dto_setup(
+				pipe_ctx->stream_res.audio,
+				pipe_ctx->stream->signal,
+				&audio_output.crtc_info,
+				&audio_output.pll_info);
+			break;
+		}
+	}
+
+	/* no HDMI audio is found, try DP audio */
+	if (i == dc->res_pool->pipe_count) {
+		for (i = 0; i < dc->res_pool->pipe_count; i++) {
+			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+			if (pipe_ctx->stream == NULL)
+				continue;
+
+			if (pipe_ctx->top_pipe)
+				continue;
+
+			if (!dc_is_dp_signal(pipe_ctx->stream->signal))
+				continue;
+
+			if (pipe_ctx->stream_res.audio != NULL) {
+				struct audio_output audio_output;
+
+				build_audio_output(context, pipe_ctx, &audio_output);
+
+				pipe_ctx->stream_res.audio->funcs->wall_dto_setup(
+					pipe_ctx->stream_res.audio,
+					pipe_ctx->stream->signal,
+					&audio_output.crtc_info,
+					&audio_output.pll_info);
+				break;
+			}
+		}
+	}
+}
 
 enum dc_status dce110_apply_ctx_to_hw(
 		struct dc *dc,
@@ -2040,79 +2176,8 @@ enum dc_status dce110_apply_ctx_to_hw(
 				dc->res_pool->display_clock,
 				context->bw.dce.dispclk_khz * 115 / 100);
 	}
-	/* program audio wall clock. use HDMI as clock source if HDMI
-	 * audio active. Otherwise, use DP as clock source
-	 * first, loop to find any HDMI audio, if not, loop find DP audio
-	 */
-	/* Setup audio rate clock source */
-	/* Issue:
-	* Audio lag happened on DP monitor when unplug a HDMI monitor
-	*
-	* Cause:
-	* In case of DP and HDMI connected or HDMI only, DCCG_AUDIO_DTO_SEL
-	* is set to either dto0 or dto1, audio should work fine.
-	* In case of DP connected only, DCCG_AUDIO_DTO_SEL should be dto1,
-	* set to dto0 will cause audio lag.
-	*
-	* Solution:
-	* Not optimized audio wall dto setup. When mode set, iterate pipe_ctx,
-	* find first available pipe with audio, setup audio wall DTO per topology
-	* instead of per pipe.
-	*/
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-		if (pipe_ctx->stream == NULL)
-			continue;
-
-		if (pipe_ctx->top_pipe)
-			continue;
-
-		if (pipe_ctx->stream->signal != SIGNAL_TYPE_HDMI_TYPE_A)
-			continue;
-
-		if (pipe_ctx->stream_res.audio != NULL) {
-			struct audio_output audio_output;
-
-			build_audio_output(context, pipe_ctx, &audio_output);
-
-			pipe_ctx->stream_res.audio->funcs->wall_dto_setup(
-				pipe_ctx->stream_res.audio,
-				pipe_ctx->stream->signal,
-				&audio_output.crtc_info,
-				&audio_output.pll_info);
-			break;
-		}
-	}
-
-	/* no HDMI audio is found, try DP audio */
-	if (i == dc->res_pool->pipe_count) {
-		for (i = 0; i < dc->res_pool->pipe_count; i++) {
-			struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-			if (pipe_ctx->stream == NULL)
-				continue;
-
-			if (pipe_ctx->top_pipe)
-				continue;
-
-			if (!dc_is_dp_signal(pipe_ctx->stream->signal))
-				continue;
-
-			if (pipe_ctx->stream_res.audio != NULL) {
-				struct audio_output audio_output;
-
-				build_audio_output(context, pipe_ctx, &audio_output);
 
-				pipe_ctx->stream_res.audio->funcs->wall_dto_setup(
-					pipe_ctx->stream_res.audio,
-					pipe_ctx->stream->signal,
-					&audio_output.crtc_info,
-					&audio_output.pll_info);
-				break;
-			}
-		}
-	}
+	dce110_setup_audio_dto(dc, context);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		struct pipe_ctx *pipe_ctx_old =
@@ -2131,31 +2196,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 		if (pipe_ctx->top_pipe)
 			continue;
 
-		if (context->res_ctx.pipe_ctx[i].stream_res.audio != NULL) {
-
-			struct audio_output audio_output;
-
-			build_audio_output(context, pipe_ctx, &audio_output);
-
-			if (dc_is_dp_signal(pipe_ctx->stream->signal))
-				pipe_ctx->stream_res.stream_enc->funcs->dp_audio_setup(
-						pipe_ctx->stream_res.stream_enc,
-						pipe_ctx->stream_res.audio->inst,
-						&pipe_ctx->stream->audio_info);
-			else
-				pipe_ctx->stream_res.stream_enc->funcs->hdmi_audio_setup(
-						pipe_ctx->stream_res.stream_enc,
-						pipe_ctx->stream_res.audio->inst,
-						&pipe_ctx->stream->audio_info,
-						&audio_output.crtc_info);
-
-			pipe_ctx->stream_res.audio->funcs->az_configure(
-					pipe_ctx->stream_res.audio,
-					pipe_ctx->stream->signal,
-					&audio_output.crtc_info,
-					&pipe_ctx->stream->audio_info);
-		}
-
 		status = apply_single_controller_ctx_to_hw(
 				pipe_ctx,
 				context,
@@ -2968,6 +3008,8 @@ static const struct hw_sequencer_funcs dce110_funcs = {
 	.disable_stream = dce110_disable_stream,
 	.unblank_stream = dce110_unblank_stream,
 	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
 	.enable_display_pipe_clock_gating = enable_display_pipe_clock_gating,
 	.enable_display_power_gating = dce110_enable_display_power_gating,
 	.disable_plane = dce110_power_down_fe,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
index 5d7e9f516827..f48d5a68d238 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
@@ -49,6 +49,10 @@ void dce110_unblank_stream(struct pipe_ctx *pipe_ctx,
 		struct dc_link_settings *link_settings);
 
 void dce110_blank_stream(struct pipe_ctx *pipe_ctx);
+
+void dce110_enable_audio_stream(struct pipe_ctx *pipe_ctx);
+void dce110_disable_audio_stream(struct pipe_ctx *pipe_ctx, int option);
+
 void dce110_update_info_frame(struct pipe_ctx *pipe_ctx);
 
 void dce110_set_avmute(struct pipe_ctx *pipe_ctx, bool enable);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 52924ef50db6..03eb736a312f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -719,19 +719,7 @@ static void reset_back_end_for_pipe(
 		if (!pipe_ctx->stream->dpms_off)
 			core_link_disable_stream(pipe_ctx, FREE_ACQUIRED_RESOURCE);
 		else if (pipe_ctx->stream_res.audio) {
-			/*
-			 * if stream is already disabled outside of commit streams path,
-			 * audio disable was skipped. Need to do it here
-			 */
-			pipe_ctx->stream_res.audio->funcs->az_disable(pipe_ctx->stream_res.audio);
-
-			if (dc->caps.dynamic_audio == true) {
-				/*we have to dynamic arbitrate the audio endpoints*/
-				pipe_ctx->stream_res.audio = NULL;
-				/*we free the resource, need reset is_audio_acquired*/
-				update_audio_usage(&dc->current_state->res_ctx, dc->res_pool, pipe_ctx->stream_res.audio, false);
-			}
-
+			dc->hwss.disable_audio_stream(pipe_ctx, FREE_ACQUIRED_RESOURCE);
 		}
 
 	}
@@ -2778,6 +2766,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.disable_stream = dce110_disable_stream,
 	.unblank_stream = dce110_unblank_stream,
 	.blank_stream = dce110_blank_stream,
+	.enable_audio_stream = dce110_enable_audio_stream,
+	.disable_audio_stream = dce110_disable_audio_stream,
 	.enable_display_power_gating = dcn10_dummy_display_power_gating,
 	.disable_plane = dcn10_disable_plane,
 	.blank_pixel_data = dcn10_blank_pixel_data,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 52db80fbe987..a71770ed4b9f 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -154,6 +154,11 @@ struct hw_sequencer_funcs {
 			struct dc_link_settings *link_settings);
 
 	void (*blank_stream)(struct pipe_ctx *pipe_ctx);
+
+	void (*enable_audio_stream)(struct pipe_ctx *pipe_ctx);
+
+	void (*disable_audio_stream)(struct pipe_ctx *pipe_ctx, int option);
+
 	void (*pipe_control_lock)(
 				struct dc *dc,
 				struct pipe_ctx *pipe,
-- 
cgit v1.2.3


From 43610a9be188ca67189363334833c5e815e5e86c Mon Sep 17 00:00:00 2001
From: Vitaly Prosyak <vitaly.prosyak@amd.com>
Date: Thu, 10 May 2018 12:37:35 -0500
Subject: drm/amd/display: HLG support

Low level calculation methods.

Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                |   2 +
 .../drm/amd/display/modules/color/color_gamma.c    | 137 +++++++++++++++++++++
 2 files changed, 139 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 22d113eca452..7a70a24ef736 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -378,6 +378,8 @@ enum dc_transfer_func_predefined {
 	TRANSFER_FUNCTION_PQ,
 	TRANSFER_FUNCTION_LINEAR,
 	TRANSFER_FUNCTION_UNITY,
+	TRANSFER_FUNCTION_HLG,
+	TRANSFER_FUNCTION_HLG12
 };
 
 struct dc_transfer_func {
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 0cd111d59018..b422fa2c6a79 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -131,6 +131,63 @@ static void compute_de_pq(struct fixed31_32 in_x, struct fixed31_32 *out_y)
 			dc_fixpt_div(dc_fixpt_one, m1));
 
 }
+
+/*de gamma, none linear to linear*/
+static void compute_hlg_oetf(struct fixed31_32 in_x, bool is_light0_12, struct fixed31_32 *out_y)
+{
+	struct fixed31_32 a;
+	struct fixed31_32 b;
+	struct fixed31_32 c;
+	struct fixed31_32 threshold;
+	struct fixed31_32 reference_white_level;
+
+	a = dc_fixpt_from_fraction(17883277, 100000000);
+	if (is_light0_12) {
+		/*light 0-12*/
+		b = dc_fixpt_from_fraction(28466892, 100000000);
+		c = dc_fixpt_from_fraction(55991073, 100000000);
+		threshold = dc_fixpt_one;
+		reference_white_level = dc_fixpt_half;
+	} else {
+		/*light 0-1*/
+		b = dc_fixpt_from_fraction(2372241, 100000000);
+		c = dc_fixpt_add(dc_fixpt_one, dc_fixpt_from_fraction(429347, 100000000));
+		threshold = dc_fixpt_from_fraction(1, 12);
+		reference_white_level = dc_fixpt_pow(dc_fixpt_from_fraction(3, 1), dc_fixpt_half);
+	}
+	if (dc_fixpt_lt(threshold, in_x))
+		*out_y = dc_fixpt_add(c, dc_fixpt_mul(a, dc_fixpt_log(dc_fixpt_sub(in_x, b))));
+	else
+		*out_y = dc_fixpt_mul(dc_fixpt_pow(in_x, dc_fixpt_half), reference_white_level);
+}
+
+/*re gamma, linear to none linear*/
+static void compute_hlg_eotf(struct fixed31_32 in_x, bool is_light0_12, struct fixed31_32 *out_y)
+{
+	struct fixed31_32 a;
+	struct fixed31_32 b;
+	struct fixed31_32 c;
+	struct fixed31_32 reference_white_level;
+
+	a = dc_fixpt_from_fraction(17883277, 100000000);
+	if (is_light0_12) {
+		/*light 0-12*/
+		b = dc_fixpt_from_fraction(28466892, 100000000);
+		c = dc_fixpt_from_fraction(55991073, 100000000);
+		reference_white_level = dc_fixpt_from_fraction(4, 1);
+	} else {
+		/*light 0-1*/
+		b = dc_fixpt_from_fraction(2372241, 100000000);
+		c = dc_fixpt_add(dc_fixpt_one, dc_fixpt_from_fraction(429347, 100000000));
+		reference_white_level = dc_fixpt_from_fraction(1, 3);
+	}
+	if (dc_fixpt_lt(dc_fixpt_half, in_x))
+		*out_y = dc_fixpt_add(dc_fixpt_exp(dc_fixpt_div(dc_fixpt_sub(in_x, c), a)), b);
+	else
+		*out_y = dc_fixpt_mul(dc_fixpt_pow(in_x, dc_fixpt_from_fraction(2, 1)), reference_white_level);
+}
+
+
 /* one-time pre-compute PQ values - only for sdr_white_level 80 */
 void precompute_pq(void)
 {
@@ -691,6 +748,48 @@ static void build_degamma(struct pwl_float_data_ex *curve,
 	}
 }
 
+static void build_hlg_degamma(struct pwl_float_data_ex *degamma,
+		uint32_t hw_points_num,
+		const struct hw_x_point *coordinate_x, bool is_light0_12)
+{
+	uint32_t i;
+
+	struct pwl_float_data_ex *rgb = degamma;
+	const struct hw_x_point *coord_x = coordinate_x;
+
+	i = 0;
+
+	while (i != hw_points_num + 1) {
+		compute_hlg_oetf(coord_x->x, is_light0_12, &rgb->r);
+		rgb->g = rgb->r;
+		rgb->b = rgb->r;
+		++coord_x;
+		++rgb;
+		++i;
+	}
+}
+
+static void build_hlg_regamma(struct pwl_float_data_ex *regamma,
+		uint32_t hw_points_num,
+		const struct hw_x_point *coordinate_x, bool is_light0_12)
+{
+	uint32_t i;
+
+	struct pwl_float_data_ex *rgb = regamma;
+	const struct hw_x_point *coord_x = coordinate_x;
+
+	i = 0;
+
+	while (i != hw_points_num + 1) {
+		compute_hlg_eotf(coord_x->x, is_light0_12, &rgb->r);
+		rgb->g = rgb->r;
+		rgb->b = rgb->r;
+		++coord_x;
+		++rgb;
+		++i;
+	}
+}
+
 static void scale_gamma(struct pwl_float_data *pwl_rgb,
 		const struct dc_gamma *ramp,
 		struct dividers dividers)
@@ -1614,6 +1713,25 @@ bool  mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 
+		kvfree(rgb_regamma);
+	} else if (trans == TRANSFER_FUNCTION_HLG ||
+		trans == TRANSFER_FUNCTION_HLG12) {
+		rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
+				       (MAX_HW_POINTS + _EXTRA_POINTS),
+				       GFP_KERNEL);
+		if (!rgb_regamma)
+			goto rgb_regamma_alloc_fail;
+
+		build_hlg_regamma(rgb_regamma,
+				MAX_HW_POINTS,
+				coordinates_x,
+				trans == TRANSFER_FUNCTION_HLG12 ? true:false);
+		for (i = 0; i <= MAX_HW_POINTS ; i++) {
+			points->red[i]    = rgb_regamma[i].r;
+			points->green[i]  = rgb_regamma[i].g;
+			points->blue[i]   = rgb_regamma[i].b;
+		}
+		ret = true;
 		kvfree(rgb_regamma);
 	}
 rgb_regamma_alloc_fail:
@@ -1674,6 +1792,25 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 		}
 		ret = true;
 
+		kvfree(rgb_degamma);
+	} else if (trans == TRANSFER_FUNCTION_HLG ||
+		trans == TRANSFER_FUNCTION_HLG12) {
+		rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
+				       (MAX_HW_POINTS + _EXTRA_POINTS),
+				       GFP_KERNEL);
+		if (!rgb_degamma)
+			goto rgb_degamma_alloc_fail;
+
+		build_hlg_degamma(rgb_degamma,
+				MAX_HW_POINTS,
+				coordinates_x,
+				trans == TRANSFER_FUNCTION_HLG12 ? true:false);
+		for (i = 0; i <= MAX_HW_POINTS ; i++) {
+			points->red[i]    = rgb_degamma[i].r;
+			points->green[i]  = rgb_degamma[i].g;
+			points->blue[i]   = rgb_degamma[i].b;
+		}
+		ret = true;
 		kvfree(rgb_degamma);
 	}
 	points->end_exponent = 0;
-- 
cgit v1.2.3


From a27f1996778363adc5ca3a31f6306edd8fa54350 Mon Sep 17 00:00:00 2001
From: Yasir Al Shekerchi <YasirAl.Shekerchi@amd.com>
Date: Fri, 4 May 2018 16:53:03 -0400
Subject: drm/amd/display: Added documentation for some DC interface functions

Signed-off-by: Yasir Al Shekerchi <YasirAl.Shekerchi@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c         | 16 ++++++++++++++++
 drivers/gpu/drm/amd/display/dc/core/dc_link.c    | 16 ++++++++++++++++
 drivers/gpu/drm/amd/display/dc/core/dc_surface.c | 11 +++++++++++
 3 files changed, 43 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 644b2187507b..2b1a92844c38 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -169,6 +169,22 @@ failed_alloc:
 	return false;
 }
 
+/**
+ *****************************************************************************
+ *  Function: dc_stream_adjust_vmin_vmax
+ *
+ *  @brief
+ *     Looks up the pipe context of dc_stream_state and updates the
+ *     vertical_total_min and vertical_total_max of the DRR, Dynamic Refresh
+ *     Rate, which is a power-saving feature that targets reducing panel
+ *     refresh rate while the screen is static
+ *
+ *  @param [in] dc: dc reference
+ *  @param [in] stream: Initial dc stream state
+ *  @param [in] adjust: Updated parameters for vertical_total_min and
+ *  vertical_total_max
+ *****************************************************************************
+ */
 bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 		struct dc_stream_state **streams, int num_streams,
 		int vmin, int vmax)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index a9485c10fd77..08b7ee526f0f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2433,6 +2433,22 @@ void core_link_set_avmute(struct pipe_ctx *pipe_ctx, bool enable)
 	core_dc->hwss.set_avmute(pipe_ctx, enable);
 }
 
+/**
+ *****************************************************************************
+ *  Function: dc_link_enable_hpd_filter
+ *
+ *  @brief
+ *     If enable is true, programs HPD filter on associated HPD line using
+ *     delay_on_disconnect/delay_on_connect values dependent on
+ *     link->connector_signal
+ *
+ *     If enable is false, programs HPD filter on associated HPD line with no
+ *     delays on connect or disconnect
+ *
+ *  @param [in] link: pointer to the dc link
+ *  @param [in] enable: boolean specifying whether to enable hbd
+ *****************************************************************************
+ */
 void dc_link_enable_hpd_filter(struct dc_link *link, bool enable)
 {
 	struct gpio *hpd;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index 68a71adeb12e..815dfb50089b 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -84,6 +84,17 @@ struct dc_plane_state *dc_create_plane_state(struct dc *dc)
 	return plane_state;
 }
 
+/**
+ *****************************************************************************
+ *  Function: dc_plane_get_status
+ *
+ *  @brief
+ *     Looks up the pipe context of plane_state and updates the pending status
+ *     of the pipe context. Then returns plane_state->status
+ *
+ *  @param [in] plane_state: pointer to the plane_state to get the status of
+ *****************************************************************************
+ */
 const struct dc_plane_status *dc_plane_get_status(
 		const struct dc_plane_state *plane_state)
 {
-- 
cgit v1.2.3


From e0d4234982b3e9ce7eaa6c1726ceb04efd0b800f Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 8 May 2018 12:24:40 -0400
Subject: drm/amd/display: dal 3.1.46

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 7a70a24ef736..74fc4f6d9cdf 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.45"
+#define DC_VER "3.1.46"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 8de94233f4cdcd5b3065fa9b9af3edc10874a120 Mon Sep 17 00:00:00 2001
From: Reza Amini <Reza.Amini@amd.com>
Date: Wed, 9 May 2018 15:41:47 -0400
Subject: drm/amd/display: Prefix TIMING_STANDARD entries with DC_

Signed-off-by: Reza Amini <Reza.Amini@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c         |  2 +-
 drivers/gpu/drm/amd/display/dc/dc_ddc_types.h    |  2 +-
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h     | 34 ++++++++++++------------
 drivers/gpu/drm/amd/display/dc/dc_types.h        | 18 ++++++-------
 drivers/gpu/drm/amd/display/include/fixed31_32.h |  7 +++++
 5 files changed, 35 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 2b1a92844c38..2c05630e78fb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -1564,7 +1564,7 @@ struct dc_sink *dc_link_add_remote_sink(
 	struct dc_sink *dc_sink;
 	enum dc_edid_status edid_status;
 
-	if (len > MAX_EDID_BUFFER_SIZE) {
+	if (len > DC_MAX_EDID_BUFFER_SIZE) {
 		dm_error("Max EDID buffer size breached!\n");
 		return NULL;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
index e1affeb5cc51..ee04812b4492 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
@@ -109,7 +109,7 @@ struct ddc_service {
 
 	uint32_t address;
 	uint32_t edid_buf_len;
-	uint8_t edid_buf[MAX_EDID_BUFFER_SIZE];
+	uint8_t edid_buf[DC_MAX_EDID_BUFFER_SIZE];
 };
 
 #endif /* DC_DDC_TYPES_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index b1f70579d61b..d31023d57b58 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -567,25 +567,25 @@ struct scaling_taps {
 };
 
 enum dc_timing_standard {
-	TIMING_STANDARD_UNDEFINED,
-	TIMING_STANDARD_DMT,
-	TIMING_STANDARD_GTF,
-	TIMING_STANDARD_CVT,
-	TIMING_STANDARD_CVT_RB,
-	TIMING_STANDARD_CEA770,
-	TIMING_STANDARD_CEA861,
-	TIMING_STANDARD_HDMI,
-	TIMING_STANDARD_TV_NTSC,
-	TIMING_STANDARD_TV_NTSC_J,
-	TIMING_STANDARD_TV_PAL,
-	TIMING_STANDARD_TV_PAL_M,
-	TIMING_STANDARD_TV_PAL_CN,
-	TIMING_STANDARD_TV_SECAM,
-	TIMING_STANDARD_EXPLICIT,
+	DC_TIMING_STANDARD_UNDEFINED,
+	DC_TIMING_STANDARD_DMT,
+	DC_TIMING_STANDARD_GTF,
+	DC_TIMING_STANDARD_CVT,
+	DC_TIMING_STANDARD_CVT_RB,
+	DC_TIMING_STANDARD_CEA770,
+	DC_TIMING_STANDARD_CEA861,
+	DC_TIMING_STANDARD_HDMI,
+	DC_TIMING_STANDARD_TV_NTSC,
+	DC_TIMING_STANDARD_TV_NTSC_J,
+	DC_TIMING_STANDARD_TV_PAL,
+	DC_TIMING_STANDARD_TV_PAL_M,
+	DC_TIMING_STANDARD_TV_PAL_CN,
+	DC_TIMING_STANDARD_TV_SECAM,
+	DC_TIMING_STANDARD_EXPLICIT,
 	/*!< For explicit timings from EDID, VBIOS, etc.*/
-	TIMING_STANDARD_USER_OVERRIDE,
+	DC_TIMING_STANDARD_USER_OVERRIDE,
 	/*!< For mode timing override by user*/
-	TIMING_STANDARD_MAX
+	DC_TIMING_STANDARD_MAX
 };
 
 enum dc_color_depth {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 76df2534c4a4..7d603c53e45e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -98,7 +98,7 @@ struct dc_context {
 };
 
 
-#define MAX_EDID_BUFFER_SIZE 512
+#define DC_MAX_EDID_BUFFER_SIZE 512
 #define EDID_BLOCK_SIZE 128
 #define MAX_SURFACE_NUM 4
 #define NUM_PIXEL_FORMATS 10
@@ -137,13 +137,13 @@ enum plane_stereo_format {
  */
 
 enum dc_edid_connector_type {
-	EDID_CONNECTOR_UNKNOWN = 0,
-	EDID_CONNECTOR_ANALOG = 1,
-	EDID_CONNECTOR_DIGITAL = 10,
-	EDID_CONNECTOR_DVI = 11,
-	EDID_CONNECTOR_HDMIA = 12,
-	EDID_CONNECTOR_MDDI = 14,
-	EDID_CONNECTOR_DISPLAYPORT = 15
+	DC_EDID_CONNECTOR_UNKNOWN = 0,
+	DC_EDID_CONNECTOR_ANALOG = 1,
+	DC_EDID_CONNECTOR_DIGITAL = 10,
+	DC_EDID_CONNECTOR_DVI = 11,
+	DC_EDID_CONNECTOR_HDMIA = 12,
+	DC_EDID_CONNECTOR_MDDI = 14,
+	DC_EDID_CONNECTOR_DISPLAYPORT = 15
 };
 
 enum dc_edid_status {
@@ -169,7 +169,7 @@ struct dc_cea_audio_mode {
 
 struct dc_edid {
 	uint32_t length;
-	uint8_t raw_edid[MAX_EDID_BUFFER_SIZE];
+	uint8_t raw_edid[DC_MAX_EDID_BUFFER_SIZE];
 };
 
 /* When speaker location data block is not available, DEFAULT_SPEAKER_LOCATION
diff --git a/drivers/gpu/drm/amd/display/include/fixed31_32.h b/drivers/gpu/drm/amd/display/include/fixed31_32.h
index a981b3e99ab3..52a73332befb 100644
--- a/drivers/gpu/drm/amd/display/include/fixed31_32.h
+++ b/drivers/gpu/drm/amd/display/include/fixed31_32.h
@@ -26,6 +26,13 @@
 #ifndef __DAL_FIXED31_32_H__
 #define __DAL_FIXED31_32_H__
 
+#ifndef LLONG_MAX
+#define LLONG_MAX 9223372036854775807ll
+#endif
+#ifndef LLONG_MIN
+#define LLONG_MIN (-LLONG_MAX - 1ll)
+#endif
+
 #define FIXED31_32_BITS_PER_FRACTIONAL_PART 32
 #ifndef LLONG_MIN
 #define LLONG_MIN (1LL<<63)
-- 
cgit v1.2.3


From 0b126112e90a96907aa14c39374fc7bfdbba131a Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Mon, 14 May 2018 17:01:00 -0400
Subject: drm/amd/display: DP YCbCr 4:2:0 support

Update MSA MISC1 bit 6 programming to handle YCbCr 4:2:0
and BT2020 cases.

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Hersen Wu <hersenxs.wu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c    | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index c928ee4cd382..147f61416fa5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -298,9 +298,20 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	}
 
 	misc1 = REG_READ(DP_MSA_MISC);
+	/* For YCbCr420 and BT2020 Colorimetry Formats, VSC SDP shall be used.
+	 * When MISC1, bit 6, is Set to 1, a Source device uses a VSC SDP to indicate the
+	 * Pixel Encoding/Colorimetry Format and that a Sink device shall ignore MISC1, bit 7,
+	 * and MISC0, bits 7:1 (MISC1, bit 7, and MISC0, bits 7:1, become “don’t care”).
+	 */
+	if ((crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) ||
+			(output_color_space == COLOR_SPACE_2020_YCBCR) ||
+			(output_color_space == COLOR_SPACE_2020_RGB_FULLRANGE) ||
+			(output_color_space == COLOR_SPACE_2020_RGB_LIMITEDRANGE))
+		misc1 = misc1 | 0x40;
+	else
+		misc1 = misc1 & ~0x40;
 
 	/* set color depth */
-
 	switch (crtc_timing->display_color_depth) {
 	case COLOR_DEPTH_666:
 		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
@@ -354,7 +365,6 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 
 	switch (output_color_space) {
 	case COLOR_SPACE_SRGB:
-		misc0 = misc0 | 0x0;
 		misc1 = misc1 & ~0x80; /* bit7 = 0*/
 		dynamic_range_rgb = 0; /*full range*/
 		break;
-- 
cgit v1.2.3


From 0dd6cfe15cbd888e7e43ec1bb28f372de7d1b3e1 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 16 May 2018 08:51:11 -0400
Subject: drm/amd/display: add dentist frequency to resource pool

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/inc/core_types.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index a94942d4e66b..4beddca0180c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -148,6 +148,7 @@ struct resource_pool {
 	unsigned int underlay_pipe_index;
 	unsigned int stream_enc_count;
 	unsigned int ref_clock_inKhz;
+	unsigned int dentist_vco_freq_khz;
 	unsigned int timing_generator_count;
 
 	/*
-- 
cgit v1.2.3


From 0ce55b4676f2e237e46d9196eb84fe35499a0d2e Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 8 May 2018 12:25:02 -0400
Subject: drm/amd/display: dal 3.1.47

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 74fc4f6d9cdf..be0dee18e09f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.46"
+#define DC_VER "3.1.47"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 6f4e8d6e592a5ca998337525b6f5133555228326 Mon Sep 17 00:00:00 2001
From: Samuel Li <Samuel.Li@amd.com>
Date: Thu, 17 May 2018 17:58:45 -0400
Subject: drm/amdgpu: add kernel doc for amdgpu_object.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the amdgpu buffer object API.

v2: Add a DOC section and some more clarification.
v3: Add some clarification and fix a spelling.

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Samuel Li <Samuel.Li@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 269 +++++++++++++++++++++++++++++
 1 file changed, 269 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 5e4e1bd90383..78d75ae5932f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -38,6 +38,19 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
 
+/**
+ * DOC: amdgpu_object
+ *
+ * This defines the interfaces to operate on an &amdgpu_bo buffer object which
+ * represents memory used by driver (VRAM, system memory, etc.). The driver
+ * provides DRM/GEM APIs to userspace. DRM/GEM APIs then use these interfaces
+ * to create/destroy/set buffer object which are then managed by the kernel TTM
+ * memory manager.
+ * The interfaces are also used internally by kernel clients, including gfx,
+ * uvd, etc. for kernel managed allocations used by the GPU.
+ *
+ */
+
 static bool amdgpu_need_backup(struct amdgpu_device *adev)
 {
 	if (adev->flags & AMD_IS_APU)
@@ -73,6 +86,15 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	kfree(bo);
 }
 
+/**
+ * amdgpu_ttm_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo
+ * @bo: buffer object to be checked
+ *
+ * Uses destroy function associated with the object to determine if this is
+ * an &amdgpu_bo.
+ *
+ * Returns true if the object belongs to &amdgpu_bo, false if not.
+ */
 bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
 {
 	if (bo->destroy == &amdgpu_ttm_bo_destroy)
@@ -80,6 +102,14 @@ bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
 	return false;
 }
 
+/**
+ * amdgpu_ttm_placement_from_domain - set buffer's placement
+ * @abo: &amdgpu_bo buffer object whose placement is to be set
+ * @domain: requested domain
+ *
+ * Sets buffer's placement according to requested domain and the buffer's
+ * flags.
+ */
 void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
@@ -498,6 +528,19 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
 	return r;
 }
 
+/**
+ * amdgpu_bo_create - create an &amdgpu_bo buffer object
+ * @adev: amdgpu device object
+ * @bp: parameters to be used for the buffer object
+ * @bo_ptr: pointer to the buffer object pointer
+ *
+ * Creates an &amdgpu_bo buffer object; and if requested, also creates a
+ * shadow object.
+ * Shadow object is used to backup the original buffer object, and is always
+ * in GTT.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     struct amdgpu_bo_param *bp,
 		     struct amdgpu_bo **bo_ptr)
@@ -527,6 +570,20 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	return r;
 }
 
+/**
+ * amdgpu_bo_backup_to_shadow - Backs up an &amdgpu_bo buffer object
+ * @adev: amdgpu device object
+ * @ring: amdgpu_ring for the engine handling the buffer operations
+ * @bo: &amdgpu_bo buffer to be backed up
+ * @resv: reservation object with embedded fence
+ * @fence: dma_fence associated with the operation
+ * @direct: whether to submit the job directly
+ *
+ * Copies an &amdgpu_bo buffer object to its shadow object.
+ * Not used for now.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_backup_to_shadow(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring,
 			       struct amdgpu_bo *bo,
@@ -559,6 +616,17 @@ err:
 	return r;
 }
 
+/**
+ * amdgpu_bo_validate - validate an &amdgpu_bo buffer object
+ * @bo: pointer to the buffer object
+ *
+ * Sets placement according to domain; and changes placement and caching
+ * policy of the buffer object according to the placement.
+ * This is used for validating shadow bos.  It calls ttm_bo_validate() to
+ * make sure the buffer is resident where it needs to be.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_validate(struct amdgpu_bo *bo)
 {
 	struct ttm_operation_ctx ctx = { false, false };
@@ -581,6 +649,21 @@ retry:
 	return r;
 }
 
+/**
+ * amdgpu_bo_restore_from_shadow - restore an &amdgpu_bo buffer object
+ * @adev: amdgpu device object
+ * @ring: amdgpu_ring for the engine handling the buffer operations
+ * @bo: &amdgpu_bo buffer to be restored
+ * @resv: reservation object with embedded fence
+ * @fence: dma_fence associated with the operation
+ * @direct: whether to submit the job directly
+ *
+ * Copies a buffer object's shadow content back to the object.
+ * This is used for recovering a buffer from its shadow in case of a gpu
+ * reset where vram context may be lost.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_restore_from_shadow(struct amdgpu_device *adev,
 				  struct amdgpu_ring *ring,
 				  struct amdgpu_bo *bo,
@@ -613,6 +696,16 @@ err:
 	return r;
 }
 
+/**
+ * amdgpu_bo_kmap - map an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be mapped
+ * @ptr: kernel virtual address to be returned
+ *
+ * Calls ttm_bo_kmap() to set up the kernel virtual mapping; calls
+ * amdgpu_bo_kptr() to get the kernel virtual address.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
 {
 	void *kptr;
@@ -643,6 +736,14 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
 	return 0;
 }
 
+/**
+ * amdgpu_bo_kptr - returns a kernel virtual address of the buffer object
+ * @bo: &amdgpu_bo buffer object
+ *
+ * Calls ttm_kmap_obj_virtual() to get the kernel virtual address
+ *
+ * Returns the virtual address of a buffer object area.
+ */
 void *amdgpu_bo_kptr(struct amdgpu_bo *bo)
 {
 	bool is_iomem;
@@ -650,12 +751,26 @@ void *amdgpu_bo_kptr(struct amdgpu_bo *bo)
 	return ttm_kmap_obj_virtual(&bo->kmap, &is_iomem);
 }
 
+/**
+ * amdgpu_bo_kunmap - unmap an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be unmapped
+ *
+ * Unmaps a kernel map set up by amdgpu_bo_kmap().
+ */
 void amdgpu_bo_kunmap(struct amdgpu_bo *bo)
 {
 	if (bo->kmap.bo)
 		ttm_bo_kunmap(&bo->kmap);
 }
 
+/**
+ * amdgpu_bo_ref - reference an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object
+ *
+ * References the contained &ttm_buffer_object.
+ *
+ * Returns a refcounted pointer to the &amdgpu_bo buffer object.
+ */
 struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo)
 {
 	if (bo == NULL)
@@ -665,6 +780,12 @@ struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo)
 	return bo;
 }
 
+/**
+ * amdgpu_bo_unref - unreference an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object
+ *
+ * Unreferences the contained &ttm_buffer_object and clear the pointer
+ */
 void amdgpu_bo_unref(struct amdgpu_bo **bo)
 {
 	struct ttm_buffer_object *tbo;
@@ -678,6 +799,28 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
 		*bo = NULL;
 }
 
+/**
+ * amdgpu_bo_pin_restricted - pin an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be pinned
+ * @domain: domain to be pinned to
+ * @min_offset: the start of requested address range
+ * @max_offset: the end of requested address range
+ * @gpu_addr: GPU offset of the &amdgpu_bo buffer object
+ *
+ * Pins the buffer object according to requested domain and address range. If
+ * the memory is unbound gart memory, binds the pages into gart table. Adjusts
+ * pin_count and pin_size accordingly.
+ *
+ * Pinning means to lock pages in memory along with keeping them at a fixed
+ * offset. It is required when a buffer can not be moved, for example, when
+ * a display buffer is being scanned out.
+ *
+ * Compared with amdgpu_bo_pin(), this function gives more flexibility on
+ * where to pin a buffer if there are specific restrictions on where a buffer
+ * must be located.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			     u64 min_offset, u64 max_offset,
 			     u64 *gpu_addr)
@@ -772,11 +915,32 @@ error:
 	return r;
 }
 
+/**
+ * amdgpu_bo_pin - pin an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be pinned
+ * @domain: domain to be pinned to
+ * @gpu_addr: GPU offset of the &amdgpu_bo buffer object
+ *
+ * A simple wrapper to amdgpu_bo_pin_restricted().
+ * Provides a simpler API for buffers that do not have any strict restrictions
+ * on where a buffer must be located.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
 {
 	return amdgpu_bo_pin_restricted(bo, domain, 0, 0, gpu_addr);
 }
 
+/**
+ * amdgpu_bo_unpin - unpin an &amdgpu_bo buffer object
+ * @bo: &amdgpu_bo buffer object to be unpinned
+ *
+ * Decreases the pin_count, and clears the flags if pin_count reaches 0.
+ * Changes placement and pin size accordingly.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
@@ -812,6 +976,15 @@ error:
 	return r;
 }
 
+/**
+ * amdgpu_bo_evict_vram - evict VRAM buffers
+ * @adev: amdgpu device object
+ *
+ * Evicts all VRAM buffers on the lru list of the memory type.
+ * Mainly used for evicting vram at suspend time.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_evict_vram(struct amdgpu_device *adev)
 {
 	/* late 2.6.33 fix IGP hibernate - we need pm ops to do this correct */
@@ -834,6 +1007,14 @@ static const char *amdgpu_vram_names[] = {
 	"DDR4",
 };
 
+/**
+ * amdgpu_bo_init - initialize memory manager
+ * @adev: amdgpu device object
+ *
+ * Calls amdgpu_ttm_init() to initialize amdgpu memory manager.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_init(struct amdgpu_device *adev)
 {
 	/* reserve PAT memory space to WC for VRAM */
@@ -851,6 +1032,15 @@ int amdgpu_bo_init(struct amdgpu_device *adev)
 	return amdgpu_ttm_init(adev);
 }
 
+/**
+ * amdgpu_bo_late_init - late init
+ * @adev: amdgpu device object
+ *
+ * Calls amdgpu_ttm_late_init() to free resources used earlier during
+ * initialization.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_late_init(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_late_init(adev);
@@ -858,6 +1048,12 @@ int amdgpu_bo_late_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_bo_fini - tear down memory manager
+ * @adev: amdgpu device object
+ *
+ * Reverses amdgpu_bo_init() to tear down memory manager.
+ */
 void amdgpu_bo_fini(struct amdgpu_device *adev)
 {
 	amdgpu_ttm_fini(adev);
@@ -865,12 +1061,31 @@ void amdgpu_bo_fini(struct amdgpu_device *adev)
 	arch_io_free_memtype_wc(adev->gmc.aper_base, adev->gmc.aper_size);
 }
 
+/**
+ * amdgpu_bo_fbdev_mmap - mmap fbdev memory
+ * @bo: &amdgpu_bo buffer object
+ * @vma: vma as input from the fbdev mmap method
+ *
+ * Calls ttm_fbdev_mmap() to mmap fbdev memory if it is backed by a bo.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
 			     struct vm_area_struct *vma)
 {
 	return ttm_fbdev_mmap(vma, &bo->tbo);
 }
 
+/**
+ * amdgpu_bo_set_tiling_flags - set tiling flags
+ * @bo: &amdgpu_bo buffer object
+ * @tiling_flags: new flags
+ *
+ * Sets buffer object's tiling flags with the new one. Used by GEM ioctl or
+ * kernel driver to set the tiling flags on a buffer.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
@@ -883,6 +1098,14 @@ int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags)
 	return 0;
 }
 
+/**
+ * amdgpu_bo_get_tiling_flags - get tiling flags
+ * @bo: &amdgpu_bo buffer object
+ * @tiling_flags: returned flags
+ *
+ * Gets buffer object's tiling flags. Used by GEM ioctl or kernel driver to
+ * set the tiling flags on a buffer.
+ */
 void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags)
 {
 	lockdep_assert_held(&bo->tbo.resv->lock.base);
@@ -891,6 +1114,18 @@ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags)
 		*tiling_flags = bo->tiling_flags;
 }
 
+/**
+ * amdgpu_bo_set_metadata - set metadata
+ * @bo: &amdgpu_bo buffer object
+ * @metadata: new metadata
+ * @metadata_size: size of the new metadata
+ * @flags: flags of the new metadata
+ *
+ * Sets buffer object's metadata, its size and flags.
+ * Used via GEM ioctl.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 			    uint32_t metadata_size, uint64_t flags)
 {
@@ -920,6 +1155,20 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 	return 0;
 }
 
+/**
+ * amdgpu_bo_get_metadata - get metadata
+ * @bo: &amdgpu_bo buffer object
+ * @buffer: returned metadata
+ * @buffer_size: size of the buffer
+ * @metadata_size: size of the returned metadata
+ * @flags: flags of the returned metadata
+ *
+ * Gets buffer object's metadata, its size and flags. buffer_size shall not be
+ * less than metadata_size.
+ * Used via GEM ioctl.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   size_t buffer_size, uint32_t *metadata_size,
 			   uint64_t *flags)
@@ -943,6 +1192,16 @@ int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 	return 0;
 }
 
+/**
+ * amdgpu_bo_move_notify - notification about a memory move
+ * @bo: pointer to a buffer object
+ * @evict: if this move is evicting the buffer from the graphics address space
+ * @new_mem: new information of the bufer object
+ *
+ * Marks the corresponding &amdgpu_bo buffer object as invalid, also performs
+ * bookkeeping.
+ * TTM driver callback which is called when ttm moves a buffer.
+ */
 void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 			   bool evict,
 			   struct ttm_mem_reg *new_mem)
@@ -971,6 +1230,16 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	trace_amdgpu_ttm_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
+/**
+ * amdgpu_bo_fault_reserve_notify - notification about a memory fault
+ * @bo: pointer to a buffer object
+ *
+ * Notifies the driver we are taking a fault on this BO and have reserved it,
+ * also performs bookkeeping.
+ * TTM driver callback for dealing with vm faults.
+ *
+ * Returns 0 for success or a negative error code on failure.
+ */
 int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->bdev);
-- 
cgit v1.2.3


From b646c1dc835b6b73884a88643c2534f1a4a1928f Mon Sep 17 00:00:00 2001
From: Samuel Li <Samuel.Li@amd.com>
Date: Thu, 24 May 2018 14:32:49 -0400
Subject: drm/amdgpu: add kernel doc for memory domains.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the GEM domains exposed to userspace.

Suggested-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Samuel Li <Samuel.Li@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/uapi/drm/amdgpu_drm.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 78b4dd89fcb4..0dc9e606114e 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -72,6 +72,29 @@ extern "C" {
 #define DRM_IOCTL_AMDGPU_FENCE_TO_HANDLE DRM_IOWR(DRM_COMMAND_BASE + DRM_AMDGPU_FENCE_TO_HANDLE, union drm_amdgpu_fence_to_handle)
 #define DRM_IOCTL_AMDGPU_SCHED		DRM_IOW(DRM_COMMAND_BASE + DRM_AMDGPU_SCHED, union drm_amdgpu_sched)
 
+/**
+ * DOC: memory domains
+ *
+ * %AMDGPU_GEM_DOMAIN_CPU	System memory that is not GPU accessible.
+ * Memory in this pool could be swapped out to disk if there is pressure.
+ *
+ * %AMDGPU_GEM_DOMAIN_GTT	GPU accessible system memory, mapped into the
+ * GPU's virtual address space via gart. Gart memory linearizes non-contiguous
+ * pages of system memory, allows GPU access system memory in a linezrized
+ * fashion.
+ *
+ * %AMDGPU_GEM_DOMAIN_VRAM	Local video memory. For APUs, it is memory
+ * carved out by the BIOS.
+ *
+ * %AMDGPU_GEM_DOMAIN_GDS	Global on-chip data storage used to share data
+ * across shader threads.
+ *
+ * %AMDGPU_GEM_DOMAIN_GWS	Global wave sync, used to synchronize the
+ * execution of all the waves on a device.
+ *
+ * %AMDGPU_GEM_DOMAIN_OA	Ordered append, used by 3D or Compute engines
+ * for appending data.
+ */
 #define AMDGPU_GEM_DOMAIN_CPU		0x1
 #define AMDGPU_GEM_DOMAIN_GTT		0x2
 #define AMDGPU_GEM_DOMAIN_VRAM		0x4
-- 
cgit v1.2.3


From 5099114ba3b2e5ae9fb487aeb3ae0434fe38a7da Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 31 May 2018 09:09:59 -0500
Subject: drm/amdgpu/display: drop DRM_AMD_DC_FBC kconfig option

Just enable it always.  This was leftover from feature
bring up.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/Kconfig                | 10 ----------
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c  |  5 +----
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h  |  5 +----
 drivers/gpu/drm/amd/display/dc/dc.h                |  2 --
 drivers/gpu/drm/amd/display/dc/dc_types.h          |  2 --
 .../drm/amd/display/dc/dce110/dce110_compressor.c  |  2 --
 .../amd/display/dc/dce110/dce110_hw_sequencer.c    | 22 ++--------------------
 .../drm/amd/display/dc/dce110/dce110_resource.c    |  7 +------
 8 files changed, 5 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index d5d4586e6176..9d56889279b3 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -9,16 +9,6 @@ config DRM_AMD_DC
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-config DRM_AMD_DC_FBC
-	bool "AMD FBC - Enable Frame Buffer Compression"
-	depends on DRM_AMD_DC
-	help
-	  Choose this option if you want to use frame buffer compression
-	  support.
-	  This is a power optimisation feature, check its availability
-	  on your hardware before enabling this option.
-
-
 config DRM_AMD_DC_DCN1_0
 	bool "DCN 1.0 Raven family"
 	depends on DRM_AMD_DC && X86
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d7d1245c1050..adeb795d80f6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -347,7 +347,6 @@ static void hotplug_notify_work_func(struct work_struct *work)
 	drm_kms_helper_hotplug_event(dev);
 }
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 /* Allocate memory for FBC compressed data  */
 static void amdgpu_dm_fbc_init(struct drm_connector *connector)
 {
@@ -388,7 +387,6 @@ static void amdgpu_dm_fbc_init(struct drm_connector *connector)
 	}
 
 }
-#endif
 
 
 /* Init display KMS
@@ -3429,9 +3427,8 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 	amdgpu_dm_connector_ddc_get_modes(connector, edid);
 	amdgpu_dm_connector_add_common_modes(encoder, connector);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	amdgpu_dm_fbc_init(connector);
-#endif
+
 	return amdgpu_dm_connector->num_modes;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
index d5aa89ad5571..a29dc35954c9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
@@ -72,13 +72,11 @@ struct irq_list_head {
 	struct work_struct work;
 };
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 struct dm_comressor_info {
 	void *cpu_addr;
 	struct amdgpu_bo *bo_ptr;
 	uint64_t gpu_addr;
 };
-#endif
 
 
 struct amdgpu_display_manager {
@@ -129,9 +127,8 @@ struct amdgpu_display_manager {
 	 * Caches device atomic state for suspend/resume
 	 */
 	struct drm_atomic_state *cached_state;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+
 	struct dm_comressor_info compressor;
-#endif
 };
 
 struct amdgpu_dm_connector {
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index be0dee18e09f..f09fa4722fc9 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -289,9 +289,7 @@ struct dc {
 	bool apply_edp_fast_boot_optimization;
 
 	/* FBC compressor */
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	struct compressor *fbc_compressor;
-#endif
 };
 
 enum frame_buffer_mode {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 7d603c53e45e..e026ce5ac78f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -92,9 +92,7 @@ struct dc_context {
 	bool created_bios;
 	struct gpio_service *gpio_service;
 	struct i2caux *i2caux;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	uint64_t fbc_gpu_addr;
-#endif
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
index 111c4921987f..df027013e50c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
@@ -551,9 +551,7 @@ void dce110_compressor_construct(struct dce110_compressor *compressor,
 	compressor->base.lpt_channels_num = 0;
 	compressor->base.attached_inst = 0;
 	compressor->base.is_enabled = false;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	compressor->base.funcs = &dce110_compressor_funcs;
 
-#endif
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index cae0054c102a..1dd2ae46d505 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -34,9 +34,7 @@
 #include "dce/dce_hwseq.h"
 #include "gpio_service_interface.h"
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 #include "dce110_compressor.h"
-#endif
 
 #include "bios/bios_parser_helper.h"
 #include "timing_generator.h"
@@ -1497,10 +1495,8 @@ static void power_down_all_hw_blocks(struct dc *dc)
 
 	power_down_clock_sources(dc);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
-#endif
 }
 
 static void disable_vga_and_power_gate_all_controllers(
@@ -1742,9 +1738,7 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
 	if (events->force_trigger)
 		value |= 0x1;
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	value |= 0x84;
-#endif
 
 	for (i = 0; i < num_pipes; i++)
 		pipe_ctx[i]->stream_res.tg->funcs->
@@ -1872,8 +1866,6 @@ static void apply_min_clocks(
 	}
 }
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
-
 /*
  *  Check if FBC can be enabled
  */
@@ -1952,7 +1944,6 @@ static void enable_fbc(struct dc *dc,
 		compr->funcs->enable_fbc(compr, &params);
 	}
 }
-#endif
 
 static void dce110_reset_hw_ctx_wrap(
 		struct dc *dc,
@@ -2129,10 +2120,9 @@ enum dc_status dce110_apply_ctx_to_hw(
 
 	set_safe_displaymarks(&context->res_ctx, dc->res_pool);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
-#endif
+
 	/*TODO: when pplib works*/
 	apply_min_clocks(dc, context, &clocks_state, true);
 
@@ -2210,12 +2200,9 @@ enum dc_status dce110_apply_ctx_to_hw(
 
 	dcb->funcs->set_scratch_critical_state(dcb, false);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	if (dc->fbc_compressor)
 		enable_fbc(dc, context);
 
-#endif
-
 	return DC_OK;
 }
 
@@ -2530,10 +2517,9 @@ static void init_hw(struct dc *dc)
 		abm->funcs->init_backlight(abm);
 		abm->funcs->abm_init(abm);
 	}
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->power_up_fbc(dc->fbc_compressor);
-#endif
 
 }
 
@@ -2719,9 +2705,7 @@ static void dce110_program_front_end_for_pipe(
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct xfm_grph_csc_adjustment adjust;
 	struct out_csc_color_matrix tbl_entry;
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	unsigned int underlay_idx = dc->res_pool->underlay_pipe_index;
-#endif
 	unsigned int i;
 	DC_LOGGER_INIT();
 	memset(&tbl_entry, 0, sizeof(tbl_entry));
@@ -2762,7 +2746,6 @@ static void dce110_program_front_end_for_pipe(
 
 	program_scaler(dc, pipe_ctx);
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	/* fbc not applicable on Underlay pipe */
 	if (dc->fbc_compressor && old_pipe->stream &&
 	    pipe_ctx->pipe_idx != underlay_idx) {
@@ -2771,7 +2754,6 @@ static void dce110_program_front_end_for_pipe(
 		else
 			enable_fbc(dc, dc->current_state);
 	}
-#endif
 
 	mi->funcs->mem_input_program_surface_config(
 			mi,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index ee33786bdef6..20c029089551 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -54,9 +54,8 @@
 
 #define DC_LOGGER \
 		dc->ctx->logger
-#if defined(CONFIG_DRM_AMD_DC_FBC)
+
 #include "dce110/dce110_compressor.h"
-#endif
 
 #include "reg_helper.h"
 
@@ -1267,12 +1266,8 @@ static bool construct(
 		}
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_FBC)
 	dc->fbc_compressor = dce110_compressor_create(ctx);
 
-
-
-#endif
 	if (!underlay_create(ctx, &pool->base))
 		goto res_create_fail;
 
-- 
cgit v1.2.3


From d1a9146b3a98a139c79b79c7e1426f1128e2bbdf Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 31 May 2018 09:28:47 -0500
Subject: drm/amdgpu/display: enable CONFIG_DRM_AMD_DC_DCN1_0 by default

It's required for displays on Raven.  The DCN bandwidth calcs use
floating point, but DCN is APU only and it already depends on
X86.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 9d56889279b3..4c35625eb2c7 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -12,6 +12,7 @@ config DRM_AMD_DC
 config DRM_AMD_DC_DCN1_0
 	bool "DCN 1.0 Raven family"
 	depends on DRM_AMD_DC && X86
+	default y
 	help
 	  Choose this option if you want to have
 	  RV family for display engine
-- 
cgit v1.2.3


From 3120e2a390a9322a8247d7e9b8be52a7efc26dab Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 31 May 2018 12:46:08 -0500
Subject: drm/amdgpu/pp: switch the default dpm implementation for CI

Switch hawaii and bonaire to use powerplay rather than the old
dpm implementation.  Powerplay supports more features and is
better maintained.  Ultimately, we can drop the older dpm
implementation like we did for other older asics.

Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Rex Zhu <rezhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/cik.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 8ff4c60d1b59..702e257a483f 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -2003,9 +2003,9 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
 		if (amdgpu_dpm == -1)
-			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
-		else
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		else
+			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
@@ -2024,9 +2024,9 @@ int cik_set_ip_blocks(struct amdgpu_device *adev)
 		amdgpu_device_ip_block_add(adev, &gmc_v7_0_ip_block);
 		amdgpu_device_ip_block_add(adev, &cik_ih_ip_block);
 		if (amdgpu_dpm == -1)
-			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
-		else
 			amdgpu_device_ip_block_add(adev, &pp_smu_ip_block);
+		else
+			amdgpu_device_ip_block_add(adev, &ci_smu_ip_block);
 		if (adev->enable_virtual_display)
 			amdgpu_device_ip_block_add(adev, &dce_virtual_ip_block);
 #if defined(CONFIG_DRM_AMD_DC)
-- 
cgit v1.2.3


From 41f507080e45010f916698165420640422942f7c Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Wed, 30 May 2018 13:00:46 +0200
Subject: drm/doc: Add a label for the PRIME Buffer Sharing chapter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

So that it can be referenced from e.g. DOC comments.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/drm-mm.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
index 96ebcc2a7b41..21b6b72a9ba8 100644
--- a/Documentation/gpu/drm-mm.rst
+++ b/Documentation/gpu/drm-mm.rst
@@ -395,6 +395,8 @@ VMA Offset Manager
 .. kernel-doc:: drivers/gpu/drm/drm_vma_manager.c
    :export:
 
+.. _prime_buffer_sharing:
+
 PRIME Buffer Sharing
 ====================
 
-- 
cgit v1.2.3


From 99fa7ce3a82bf8047b6104682da6ae276beb22d8 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Tue, 29 May 2018 18:39:04 +0200
Subject: drm/doc: Add initial amdgpu driver documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst  | 6 ++++++
 Documentation/gpu/drivers.rst | 1 +
 2 files changed, 7 insertions(+)
 create mode 100644 Documentation/gpu/amdgpu.rst

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
new file mode 100644
index 000000000000..41a14e4aa4ac
--- /dev/null
+++ b/Documentation/gpu/amdgpu.rst
@@ -0,0 +1,6 @@
+=========================
+ drm/amdgpu AMDgpu driver
+=========================
+
+The drm/amdgpu driver supports all AMD Radeon GPUs based on the Graphics Core
+Next (GCN) architecture.
diff --git a/Documentation/gpu/drivers.rst b/Documentation/gpu/drivers.rst
index f982558fc25d..65be325bf282 100644
--- a/Documentation/gpu/drivers.rst
+++ b/Documentation/gpu/drivers.rst
@@ -4,6 +4,7 @@ GPU Driver Documentation
 
 .. toctree::
 
+   amdgpu
    i915
    meson
    pl111
-- 
cgit v1.2.3


From baca30fabdc9ba2712481e1b9e14ded1de6cfa3a Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Tue, 29 May 2018 18:33:41 +0200
Subject: drm/amdgpu: Add documentation for PRIME related code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst              |  14 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 119 ++++++++++++++++++++++++++++++
 2 files changed, 133 insertions(+)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 41a14e4aa4ac..f557866f6788 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -4,3 +4,17 @@
 
 The drm/amdgpu driver supports all AMD Radeon GPUs based on the Graphics Core
 Next (GCN) architecture.
+
+Core Driver Infrastructure
+==========================
+
+This section covers core driver infrastructure.
+
+PRIME Buffer Sharing
+--------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+   :doc: PRIME Buffer Sharing
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+   :internal:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 4683626b065f..d1f05489595b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -23,6 +23,14 @@
  *
  * Authors: Alex Deucher
  */
+
+/**
+ * DOC: PRIME Buffer Sharing
+ *
+ * The following callback implementations are used for :ref:`sharing GEM buffer
+ * objects between different devices via PRIME <prime_buffer_sharing>`.
+ */
+
 #include <drm/drmP.h>
 
 #include "amdgpu.h"
@@ -32,6 +40,14 @@
 
 static const struct dma_buf_ops amdgpu_dmabuf_ops;
 
+/**
+ * amdgpu_gem_prime_get_sg_table - &drm_driver.gem_prime_get_sg_table
+ * implementation
+ * @obj: GEM buffer object
+ *
+ * Returns:
+ * A scatter/gather table for the pinned pages of the buffer object's memory.
+ */
 struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -40,6 +56,15 @@ struct sg_table *amdgpu_gem_prime_get_sg_table(struct drm_gem_object *obj)
 	return drm_prime_pages_to_sg(bo->tbo.ttm->pages, npages);
 }
 
+/**
+ * amdgpu_gem_prime_vmap - &dma_buf_ops.vmap implementation
+ * @obj: GEM buffer object
+ *
+ * Sets up an in-kernel virtual mapping of the buffer object's memory.
+ *
+ * Returns:
+ * The virtual address of the mapping or an error pointer.
+ */
 void *amdgpu_gem_prime_vmap(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -53,6 +78,13 @@ void *amdgpu_gem_prime_vmap(struct drm_gem_object *obj)
 	return bo->dma_buf_vmap.virtual;
 }
 
+/**
+ * amdgpu_gem_prime_vunmap - &dma_buf_ops.vunmap implementation
+ * @obj: GEM buffer object
+ * @vaddr: virtual address (unused)
+ *
+ * Tears down the in-kernel virtual mapping of the buffer object's memory.
+ */
 void amdgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -60,6 +92,17 @@ void amdgpu_gem_prime_vunmap(struct drm_gem_object *obj, void *vaddr)
 	ttm_bo_kunmap(&bo->dma_buf_vmap);
 }
 
+/**
+ * amdgpu_gem_prime_mmap - &drm_driver.gem_prime_mmap implementation
+ * @obj: GEM buffer object
+ * @vma: virtual memory area
+ *
+ * Sets up a userspace mapping of the buffer object's memory in the given
+ * virtual memory area.
+ *
+ * Returns:
+ * 0 on success or negative error code.
+ */
 int amdgpu_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -94,6 +137,19 @@ int amdgpu_gem_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma
 	return ret;
 }
 
+/**
+ * amdgpu_gem_prime_import_sg_table - &drm_driver.gem_prime_import_sg_table
+ * implementation
+ * @dev: DRM device
+ * @attach: DMA-buf attachment
+ * @sg: Scatter/gather table
+ *
+ * Import shared DMA buffer memory exported by another device.
+ *
+ * Returns:
+ * A new GEM buffer object of the given DRM device, representing the memory
+ * described by the given DMA-buf attachment and scatter/gather table.
+ */
 struct drm_gem_object *
 amdgpu_gem_prime_import_sg_table(struct drm_device *dev,
 				 struct dma_buf_attachment *attach,
@@ -132,6 +188,19 @@ error:
 	return ERR_PTR(ret);
 }
 
+/**
+ * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation
+ * @dma_buf: shared DMA buffer
+ * @target_dev: target device
+ * @attach: DMA-buf attachment
+ *
+ * Makes sure that the shared DMA buffer can be accessed by the target device.
+ * For now, simply pins it to the GTT domain, where it should be accessible by
+ * all DMA devices.
+ *
+ * Returns:
+ * 0 on success or negative error code.
+ */
 static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 				 struct device *target_dev,
 				 struct dma_buf_attachment *attach)
@@ -181,6 +250,14 @@ error_detach:
 	return r;
 }
 
+/**
+ * amdgpu_gem_map_detach - &dma_buf_ops.detach implementation
+ * @dma_buf: shared DMA buffer
+ * @attach: DMA-buf attachment
+ *
+ * This is called when a shared DMA buffer no longer needs to be accessible by
+ * the other device. For now, simply unpins the buffer from GTT.
+ */
 static void amdgpu_gem_map_detach(struct dma_buf *dma_buf,
 				  struct dma_buf_attachment *attach)
 {
@@ -202,6 +279,13 @@ error:
 	drm_gem_map_detach(dma_buf, attach);
 }
 
+/**
+ * amdgpu_gem_prime_res_obj - &drm_driver.gem_prime_res_obj implementation
+ * @obj: GEM buffer object
+ *
+ * Returns:
+ * The buffer object's reservation object.
+ */
 struct reservation_object *amdgpu_gem_prime_res_obj(struct drm_gem_object *obj)
 {
 	struct amdgpu_bo *bo = gem_to_amdgpu_bo(obj);
@@ -209,6 +293,18 @@ struct reservation_object *amdgpu_gem_prime_res_obj(struct drm_gem_object *obj)
 	return bo->tbo.resv;
 }
 
+/**
+ * amdgpu_gem_begin_cpu_access - &dma_buf_ops.begin_cpu_access implementation
+ * @dma_buf: shared DMA buffer
+ * @direction: direction of DMA transfer
+ *
+ * This is called before CPU access to the shared DMA buffer's memory. If it's
+ * a read access, the buffer is moved to the GTT domain if possible, for optimal
+ * CPU read performance.
+ *
+ * Returns:
+ * 0 on success or negative error code.
+ */
 static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 				       enum dma_data_direction direction)
 {
@@ -253,6 +349,18 @@ static const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.vunmap = drm_gem_dmabuf_vunmap,
 };
 
+/**
+ * amdgpu_gem_prime_export - &drm_driver.gem_prime_export implementation
+ * @dev: DRM device
+ * @gobj: GEM buffer object
+ * @flags: flags like DRM_CLOEXEC and DRM_RDWR
+ *
+ * The main work is done by the &drm_gem_prime_export helper, which in turn
+ * uses &amdgpu_gem_prime_res_obj.
+ *
+ * Returns:
+ * Shared DMA buffer representing the GEM buffer object from the given device.
+ */
 struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 					struct drm_gem_object *gobj,
 					int flags)
@@ -273,6 +381,17 @@ struct dma_buf *amdgpu_gem_prime_export(struct drm_device *dev,
 	return buf;
 }
 
+/**
+ * amdgpu_gem_prime_import - &drm_driver.gem_prime_import implementation
+ * @dev: DRM device
+ * @dma_buf: Shared DMA buffer
+ *
+ * The main work is done by the &drm_gem_prime_import helper, which in turn
+ * uses &amdgpu_gem_prime_import_sg_table.
+ *
+ * Returns:
+ * GEM buffer object representing the shared DMA buffer for the given device.
+ */
 struct drm_gem_object *amdgpu_gem_prime_import(struct drm_device *dev,
 					    struct dma_buf *dma_buf)
 {
-- 
cgit v1.2.3


From 8f4805a265fd710a2827b2c0e10c08ef2b526870 Mon Sep 17 00:00:00 2001
From: Shirish S <shirish.s@amd.com>
Date: Tue, 29 May 2018 09:23:53 +0530
Subject: drm/amdgpu: avoid sleep while executing atombios table (V2)

This patch replaces kzalloc's flag from GFP_KERNEL to
GFP_ATOMIC to avoid sleeping in atomic context.

Below is the stack trace:

BUG: sleeping function called from invalid context at mm/slab.h:***
in_atomic(): 1, irqs_disabled(): 0, pid: 1137, name: DrmThread
CPU: 1 PID: 1137 Comm: DrmThread Tainted: G        W       4.14.43 #10
Call Trace:
 dump_stack+0x4d/0x63
 ___might_sleep+0x11f/0x12e
 __kmalloc+0x76/0x126
 amdgpu_atom_execute_table_locked+0xfc/0x285
 amdgpu_atom_execute_table+0x5d/0x72
 transmitter_control_v1_5+0xef/0x11a
 hwss_edp_backlight_control+0x132/0x151
 dce110_disable_stream+0x133/0x16e
 core_link_disable_stream+0x1c5/0x23b
 dce110_reset_hw_ctx_wrap+0xb4/0x1aa
 dce110_apply_ctx_to_hw+0x4e/0x6da
 ? generic_reg_get+0x1f/0x33
 dc_commit_state+0x33f/0x3d2
 amdgpu_dm_atomic_commit_tail+0x2cf/0x5d2
 ? wait_for_common+0x5b/0x69
 commit_tail+0x42/0x64
 drm_atomic_helper_commit+0xdc/0xf9
 drm_atomic_helper_set_config+0x5c/0x76
 __drm_mode_set_config_internal+0x64/0x105
 drm_mode_setcrtc+0x474/0x56f
 ? drm_mode_getcrtc+0x155/0x155
 drm_ioctl_kernel+0x6c/0xa8
 drm_ioctl+0x267/0x353
 ? drm_mode_getcrtc+0x155/0x155
 amdgpu_drm_ioctl+0x4f/0x7f
 vfs_ioctl+0x21/0x2f
 do_vfs_ioctl+0x4c4/0x4e7
 ? security_file_ioctl+0x3b/0x4f
 SyS_ioctl+0x57/0x79
 do_syscall_64+0x64/0x72
 entry_SYSCALL_64_after_hwframe+0x3d/0xa2

V2: Added stack trace in commit message.

Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/atom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index 69500a8b4e2d..6cd518f6f7a4 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -1221,7 +1221,7 @@ static int amdgpu_atom_execute_table_locked(struct atom_context *ctx, int index,
 	ectx.abort = false;
 	ectx.last_jump = 0;
 	if (ws)
-		ectx.ws = kzalloc(4 * ws, GFP_KERNEL);
+		ectx.ws = kzalloc(4 * ws, GFP_ATOMIC);
 	else
 		ectx.ws = NULL;
 
-- 
cgit v1.2.3


From 0152ac16522b6c6dd9319e005bf2945f585328d4 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Fri, 1 Jun 2018 12:10:02 +0200
Subject: drm/amdgpu: Hook up documentation about memory domains
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index f557866f6788..ad3711fd2a28 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -10,6 +10,14 @@ Core Driver Infrastructure
 
 This section covers core driver infrastructure.
 
+.. _amdgpu_memory_domains:
+
+Memory Domains
+--------------
+
+.. kernel-doc:: include/uapi/drm/amdgpu_drm.h
+   :doc: memory domains
+
 PRIME Buffer Sharing
 --------------------
 
-- 
cgit v1.2.3


From 2472e11b85f08e56519b988c4b76c610c818b1b0 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Fri, 1 Jun 2018 12:29:45 +0200
Subject: drm/amdgpu: Fix-ups for amdgpu_object.c documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Fix format of return value descriptions
* Document all parameters of amdgpu_bo_free_kernel
* Document amdgpu_bo_get_preferred_pin_domain

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 78 +++++++++++++++++++++---------
 1 file changed, 55 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 78d75ae5932f..987a9fa33d35 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -93,7 +93,8 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
  * Uses destroy function associated with the object to determine if this is
  * an &amdgpu_bo.
  *
- * Returns true if the object belongs to &amdgpu_bo, false if not.
+ * Returns:
+ * true if the object belongs to &amdgpu_bo, false if not.
  */
 bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
 {
@@ -214,7 +215,8 @@ void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
  *
  * Note: For bo_ptr new BO is only created if bo_ptr points to NULL.
  *
- * Returns 0 on success, negative error code otherwise.
+ * Returns:
+ * 0 on success, negative error code otherwise.
  */
 int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 			      unsigned long size, int align,
@@ -291,7 +293,8 @@ error_free:
  *
  * Note: For bo_ptr new BO is only created if bo_ptr points to NULL.
  *
- * Returns 0 on success, negative error code otherwise.
+ * Returns:
+ * 0 on success, negative error code otherwise.
  */
 int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
 			    unsigned long size, int align,
@@ -315,6 +318,8 @@ int amdgpu_bo_create_kernel(struct amdgpu_device *adev,
  * amdgpu_bo_free_kernel - free BO for kernel use
  *
  * @bo: amdgpu BO to free
+ * @gpu_addr: pointer to where the BO's GPU memory space address was stored
+ * @cpu_addr: pointer to where the BO's CPU memory space address was stored
  *
  * unmaps and unpin a BO for kernel internal use.
  */
@@ -539,7 +544,8 @@ static int amdgpu_bo_create_shadow(struct amdgpu_device *adev,
  * Shadow object is used to backup the original buffer object, and is always
  * in GTT.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     struct amdgpu_bo_param *bp,
@@ -582,7 +588,8 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
  * Copies an &amdgpu_bo buffer object to its shadow object.
  * Not used for now.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_backup_to_shadow(struct amdgpu_device *adev,
 			       struct amdgpu_ring *ring,
@@ -625,7 +632,8 @@ err:
  * This is used for validating shadow bos.  It calls ttm_bo_validate() to
  * make sure the buffer is resident where it needs to be.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_validate(struct amdgpu_bo *bo)
 {
@@ -662,7 +670,8 @@ retry:
  * This is used for recovering a buffer from its shadow in case of a gpu
  * reset where vram context may be lost.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_restore_from_shadow(struct amdgpu_device *adev,
 				  struct amdgpu_ring *ring,
@@ -704,7 +713,8 @@ err:
  * Calls ttm_bo_kmap() to set up the kernel virtual mapping; calls
  * amdgpu_bo_kptr() to get the kernel virtual address.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
 {
@@ -742,7 +752,8 @@ int amdgpu_bo_kmap(struct amdgpu_bo *bo, void **ptr)
  *
  * Calls ttm_kmap_obj_virtual() to get the kernel virtual address
  *
- * Returns the virtual address of a buffer object area.
+ * Returns:
+ * the virtual address of a buffer object area.
  */
 void *amdgpu_bo_kptr(struct amdgpu_bo *bo)
 {
@@ -769,7 +780,8 @@ void amdgpu_bo_kunmap(struct amdgpu_bo *bo)
  *
  * References the contained &ttm_buffer_object.
  *
- * Returns a refcounted pointer to the &amdgpu_bo buffer object.
+ * Returns:
+ * a refcounted pointer to the &amdgpu_bo buffer object.
  */
 struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo)
 {
@@ -819,7 +831,8 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
  * where to pin a buffer if there are specific restrictions on where a buffer
  * must be located.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			     u64 min_offset, u64 max_offset,
@@ -925,7 +938,8 @@ error:
  * Provides a simpler API for buffers that do not have any strict restrictions
  * on where a buffer must be located.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
 {
@@ -939,7 +953,8 @@ int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
  * Decreases the pin_count, and clears the flags if pin_count reaches 0.
  * Changes placement and pin size accordingly.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 {
@@ -983,7 +998,8 @@ error:
  * Evicts all VRAM buffers on the lru list of the memory type.
  * Mainly used for evicting vram at suspend time.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_evict_vram(struct amdgpu_device *adev)
 {
@@ -1013,7 +1029,8 @@ static const char *amdgpu_vram_names[] = {
  *
  * Calls amdgpu_ttm_init() to initialize amdgpu memory manager.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_init(struct amdgpu_device *adev)
 {
@@ -1039,7 +1056,8 @@ int amdgpu_bo_init(struct amdgpu_device *adev)
  * Calls amdgpu_ttm_late_init() to free resources used earlier during
  * initialization.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_late_init(struct amdgpu_device *adev)
 {
@@ -1068,7 +1086,8 @@ void amdgpu_bo_fini(struct amdgpu_device *adev)
  *
  * Calls ttm_fbdev_mmap() to mmap fbdev memory if it is backed by a bo.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
 			     struct vm_area_struct *vma)
@@ -1084,7 +1103,8 @@ int amdgpu_bo_fbdev_mmap(struct amdgpu_bo *bo,
  * Sets buffer object's tiling flags with the new one. Used by GEM ioctl or
  * kernel driver to set the tiling flags on a buffer.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_set_tiling_flags(struct amdgpu_bo *bo, u64 tiling_flags)
 {
@@ -1124,7 +1144,8 @@ void amdgpu_bo_get_tiling_flags(struct amdgpu_bo *bo, u64 *tiling_flags)
  * Sets buffer object's metadata, its size and flags.
  * Used via GEM ioctl.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
 			    uint32_t metadata_size, uint64_t flags)
@@ -1167,7 +1188,8 @@ int amdgpu_bo_set_metadata (struct amdgpu_bo *bo, void *metadata,
  * less than metadata_size.
  * Used via GEM ioctl.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_get_metadata(struct amdgpu_bo *bo, void *buffer,
 			   size_t buffer_size, uint32_t *metadata_size,
@@ -1238,7 +1260,8 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
  * also performs bookkeeping.
  * TTM driver callback for dealing with vm faults.
  *
- * Returns 0 for success or a negative error code on failure.
+ * Returns:
+ * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 {
@@ -1313,10 +1336,11 @@ void amdgpu_bo_fence(struct amdgpu_bo *bo, struct dma_fence *fence,
  * amdgpu_bo_gpu_offset - return GPU offset of bo
  * @bo:	amdgpu object for which we query the offset
  *
- * Returns current GPU offset of the object.
- *
  * Note: object should either be pinned or reserved when calling this
  * function, it might be useful to add check for this for debugging.
+ *
+ * Returns:
+ * current GPU offset of the object.
  */
 u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 {
@@ -1332,6 +1356,14 @@ u64 amdgpu_bo_gpu_offset(struct amdgpu_bo *bo)
 	return bo->tbo.offset;
 }
 
+/**
+ * amdgpu_bo_get_preferred_pin_domain - get preferred domain for scanout
+ * @adev: amdgpu device object
+ * @domain: allowed :ref:`memory domains <amdgpu_memory_domains>`
+ *
+ * Returns:
+ * Which of the allowed domains is preferred for pinning the BO for scanout.
+ */
 uint32_t amdgpu_bo_get_preferred_pin_domain(struct amdgpu_device *adev,
 					    uint32_t domain)
 {
-- 
cgit v1.2.3


From a2d19d66b1454b88bfcf1929837b329378d3377f Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Fri, 1 Jun 2018 12:30:44 +0200
Subject: drm/amdgpu: Hook up amdgpu_object.c documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index ad3711fd2a28..1fbf3876a3d8 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -18,6 +18,15 @@ Memory Domains
 .. kernel-doc:: include/uapi/drm/amdgpu_drm.h
    :doc: memory domains
 
+Buffer Objects
+--------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+   :doc: amdgpu_object
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+   :internal:
+
 PRIME Buffer Sharing
 --------------------
 
-- 
cgit v1.2.3


From 741f01e636b72ff3f81204fd595ac1078907671b Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Wed, 30 May 2018 15:11:01 -0400
Subject: drm/scheduler: Avoid using wait_event_killable for dying process (V4)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Dying process might be blocked from receiving any more signals
so avoid using it.

Also retire enity->fini_status and just check the SW queue,
if it's not empty do the fallback cleanup.

Also handle entity->last_scheduled == NULL use case which
happens when HW ring is already hangged whem a  new entity
tried to enqeue jobs.

v2:
Return the remaining timeout and use that as parameter for the next call.
This way when we need to cleanup multiple queues we don't wait for the
entire TO period for each queue but rather in total.
Styling comments.
Rebase.

v3:
Update types from unsigned to long.
Work with jiffies instead of ms.
Return 0 when TO expires.
Rebase.

v4:
Remove unnecessary timeout calculation.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 67 ++++++++++++++++++++++---------
 include/drm/gpu_scheduler.h               |  7 ++--
 2 files changed, 53 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 8c1e80c9b674..6a316701da73 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -181,7 +181,6 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 	entity->rq = rq;
 	entity->sched = sched;
 	entity->guilty = guilty;
-	entity->fini_status = 0;
 	entity->last_scheduled = NULL;
 
 	spin_lock_init(&entity->rq_lock);
@@ -219,7 +218,8 @@ static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched,
 static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
 {
 	rmb();
-	if (spsc_queue_peek(&entity->job_queue) == NULL)
+
+	if (!entity->rq || spsc_queue_peek(&entity->job_queue) == NULL)
 		return true;
 
 	return false;
@@ -260,25 +260,39 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
  *
  * @sched: scheduler instance
  * @entity: scheduler entity
+ * @timeout: time to wait in for Q to become empty in jiffies.
  *
  * Splitting drm_sched_entity_fini() into two functions, The first one does the waiting,
  * removes the entity from the runqueue and returns an error when the process was killed.
+ *
+ * Returns the remaining time in jiffies left from the input timeout
  */
-void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity)
+long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
+			   struct drm_sched_entity *entity, long timeout)
 {
+	long ret = timeout;
+
 	if (!drm_sched_entity_is_initialized(sched, entity))
-		return;
+		return ret;
 	/**
 	 * The client will not queue more IBs during this fini, consume existing
 	 * queued IBs or discard them on SIGKILL
 	*/
-	if ((current->flags & PF_SIGNALED) && current->exit_code == SIGKILL)
-		entity->fini_status = -ERESTARTSYS;
-	else
-		entity->fini_status = wait_event_killable(sched->job_scheduled,
-					drm_sched_entity_is_idle(entity));
-	drm_sched_entity_set_rq(entity, NULL);
+	if (current->flags & PF_EXITING) {
+		if (timeout)
+			ret = wait_event_timeout(
+					sched->job_scheduled,
+					drm_sched_entity_is_idle(entity),
+					timeout);
+	} else
+		wait_event_killable(sched->job_scheduled, drm_sched_entity_is_idle(entity));
+
+
+	/* For killed process disable any more IBs enqueue right now */
+	if ((current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
+		drm_sched_entity_set_rq(entity, NULL);
+
+	return ret;
 }
 EXPORT_SYMBOL(drm_sched_entity_do_release);
 
@@ -290,11 +304,18 @@ EXPORT_SYMBOL(drm_sched_entity_do_release);
  *
  * This should be called after @drm_sched_entity_do_release. It goes over the
  * entity and signals all jobs with an error code if the process was killed.
+ *
  */
 void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity)
 {
-	if (entity->fini_status) {
+
+	drm_sched_entity_set_rq(entity, NULL);
+
+	/* Consumption of existing IBs wasn't completed. Forcefully
+	 * remove them here.
+	 */
+	if (spsc_queue_peek(&entity->job_queue)) {
 		struct drm_sched_job *job;
 		int r;
 
@@ -314,12 +335,22 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 			struct drm_sched_fence *s_fence = job->s_fence;
 			drm_sched_fence_scheduled(s_fence);
 			dma_fence_set_error(&s_fence->finished, -ESRCH);
-			r = dma_fence_add_callback(entity->last_scheduled, &job->finish_cb,
-							drm_sched_entity_kill_jobs_cb);
-			if (r == -ENOENT)
+
+			/*
+			 * When pipe is hanged by older entity, new entity might
+			 * not even have chance to submit it's first job to HW
+			 * and so entity->last_scheduled will remain NULL
+			 */
+			if (!entity->last_scheduled) {
 				drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
-			else if (r)
-				DRM_ERROR("fence add callback failed (%d)\n", r);
+			} else {
+				r = dma_fence_add_callback(entity->last_scheduled, &job->finish_cb,
+								drm_sched_entity_kill_jobs_cb);
+				if (r == -ENOENT)
+					drm_sched_entity_kill_jobs_cb(NULL, &job->finish_cb);
+				else if (r)
+					DRM_ERROR("fence add callback failed (%d)\n", r);
+			}
 		}
 	}
 
@@ -339,7 +370,7 @@ EXPORT_SYMBOL(drm_sched_entity_cleanup);
 void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
 				struct drm_sched_entity *entity)
 {
-	drm_sched_entity_do_release(sched, entity);
+	drm_sched_entity_do_release(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
 	drm_sched_entity_cleanup(sched, entity);
 }
 EXPORT_SYMBOL(drm_sched_entity_fini);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 496442f12bff..7c2dfd6cc1af 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -27,6 +27,8 @@
 #include <drm/spsc_queue.h>
 #include <linux/dma-fence.h>
 
+#define MAX_WAIT_SCHED_ENTITY_Q_EMPTY msecs_to_jiffies(1000)
+
 struct drm_gpu_scheduler;
 struct drm_sched_rq;
 
@@ -84,7 +86,6 @@ struct drm_sched_entity {
 	struct dma_fence		*dependency;
 	struct dma_fence_cb		cb;
 	atomic_t			*guilty;
-	int                             fini_status;
 	struct dma_fence                *last_scheduled;
 };
 
@@ -283,8 +284,8 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 			  struct drm_sched_entity *entity,
 			  struct drm_sched_rq *rq,
 			  atomic_t *guilty);
-void drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity);
+long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
+			   struct drm_sched_entity *entity, long timeout);
 void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity);
 void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
-- 
cgit v1.2.3


From 48ad368a8a3ab2fd3c2bc2ccccc6e29b1acda1bb Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Wed, 30 May 2018 15:28:52 -0400
Subject: drm/amdgpu: move amdgpu_ctx_mgr_entity_fini to f_ops flush hook (V4)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With this we can now terminate jobs enqueue into SW queue the moment
the task is being killed instead of waiting for last user of
drm file to release it.

Also stop checking for kref_read(&ctx->refcount) == 1 when
calling drm_sched_entity_do_release since other task
might still hold a reference to this entity but we don't
care since KILL means terminate job submission regardless
of what other tasks are doing.

v2:
Use returned remaining timeout as parameter for the next call.
Rebase.

v3:
Switch to working with jiffies.
Streamline remainder TO usage.
Rebase.

v4:
Rebase.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 14 ++++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 12 ++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c |  1 -
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index c5bb36275e93..64b3a1ed04dc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -449,26 +449,28 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
 	uint32_t id, i;
+	long max_wait = MAX_WAIT_SCHED_ENTITY_Q_EMPTY;
 
 	idp = &mgr->ctx_handles;
 
+	mutex_lock(&mgr->lock);
 	idr_for_each_entry(idp, ctx, id) {
 
-		if (!ctx->adev)
+		if (!ctx->adev) {
+			mutex_unlock(&mgr->lock);
 			return;
+		}
 
 		for (i = 0; i < ctx->adev->num_rings; i++) {
 
 			if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 				continue;
 
-			if (kref_read(&ctx->refcount) == 1)
-				drm_sched_entity_do_release(&ctx->adev->rings[i]->sched,
-						  &ctx->rings[i].entity);
-			else
-				DRM_ERROR("ctx %p is still alive\n", ctx);
+			max_wait = drm_sched_entity_do_release(&ctx->adev->rings[i]->sched,
+					  &ctx->rings[i].entity, max_wait);
 		}
 	}
+	mutex_unlock(&mgr->lock);
 }
 
 void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index b0bf2f24da48..a549483032b0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -855,9 +855,21 @@ static const struct dev_pm_ops amdgpu_pm_ops = {
 	.runtime_idle = amdgpu_pmops_runtime_idle,
 };
 
+static int amdgpu_flush(struct file *f, fl_owner_t id)
+{
+	struct drm_file *file_priv = f->private_data;
+	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
+
+	amdgpu_ctx_mgr_entity_fini(&fpriv->ctx_mgr);
+
+	return 0;
+}
+
+
 static const struct file_operations amdgpu_driver_kms_fops = {
 	.owner = THIS_MODULE,
 	.open = drm_open,
+	.flush = amdgpu_flush,
 	.release = drm_release,
 	.unlocked_ioctl = amdgpu_drm_ioctl,
 	.mmap = amdgpu_mmap,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 91517b166a3b..c472bb53e41d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -930,7 +930,6 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 		return;
 
 	pm_runtime_get_sync(dev->dev);
-	amdgpu_ctx_mgr_entity_fini(&fpriv->ctx_mgr);
 
 	if (adev->asic_type != CHIP_RAVEN) {
 		amdgpu_uvd_free_handles(adev, file_priv);
-- 
cgit v1.2.3


From 8e0fce5a96cfcce77cda3f0fccc2799d6be2524d Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Mon, 30 Apr 2018 16:35:34 -0400
Subject: drm/amdgpu: define vcn jpeg ring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add AMDGPU_RING_TYPE_VCN_JPEG ring define

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 1513124c5659..a3908efabb66 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -53,7 +53,8 @@ enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_KIQ,
 	AMDGPU_RING_TYPE_UVD_ENC,
 	AMDGPU_RING_TYPE_VCN_DEC,
-	AMDGPU_RING_TYPE_VCN_ENC
+	AMDGPU_RING_TYPE_VCN_ENC,
+	AMDGPU_RING_TYPE_VCN_JPEG
 };
 
 struct amdgpu_device;
-- 
cgit v1.2.3


From fa3087f7682e714af30c1dd8a7cdf95da38e43ff Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 14:13:33 -0400
Subject: drm/amdgpu: add vcn jpeg ring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add jpeg to amdgpu_vcn

v2: remove unnecessary scheduler entity

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 773010b9ff15..6f3bed1cc1b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -66,6 +66,7 @@ struct amdgpu_vcn {
 	const struct firmware	*fw;	/* VCN firmware */
 	struct amdgpu_ring	ring_dec;
 	struct amdgpu_ring	ring_enc[AMDGPU_VCN_MAX_ENC_RINGS];
+	struct amdgpu_ring	ring_jpeg;
 	struct amdgpu_irq_src	irq;
 	unsigned		num_enc_rings;
 };
-- 
cgit v1.2.3


From d521093a5f84cacf9935e8c9834ad3054b423ee1 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Mon, 30 Apr 2018 16:51:33 -0400
Subject: drm/amdgpu: add jpeg packet defines to soc15d.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new packet for vcn jpeg, including condition checks, types and packet

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/soc15d.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h
index 8dc29107228f..edfe50821cd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/soc15d.h
+++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h
@@ -53,6 +53,29 @@
 
 #define PACKET3_COMPUTE(op, n) (PACKET3(op, n) | 1 << 1)
 
+#define	PACKETJ_CONDITION_CHECK0	0
+#define	PACKETJ_CONDITION_CHECK1	1
+#define	PACKETJ_CONDITION_CHECK2	2
+#define	PACKETJ_CONDITION_CHECK3	3
+#define	PACKETJ_CONDITION_CHECK4	4
+#define	PACKETJ_CONDITION_CHECK5	5
+#define	PACKETJ_CONDITION_CHECK6	6
+#define	PACKETJ_CONDITION_CHECK7	7
+
+#define	PACKETJ_TYPE0	0
+#define	PACKETJ_TYPE1	1
+#define	PACKETJ_TYPE2	2
+#define	PACKETJ_TYPE3	3
+#define	PACKETJ_TYPE4	4
+#define	PACKETJ_TYPE5	5
+#define	PACKETJ_TYPE6	6
+#define	PACKETJ_TYPE7	7
+
+#define PACKETJ(reg, r, cond, type)	((reg & 0x3FFFF) |			\
+			 ((r & 0x3F) << 18) |			\
+			 ((cond & 0xF) << 24) |				\
+			 ((type & 0xF) << 28))
+
 /* Packet 3 types */
 #define	PACKET3_NOP					0x10
 #define	PACKET3_SET_BASE				0x11
-- 
cgit v1.2.3


From 50613395abc00f150f051d6bc440877741b6fae9 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Mon, 30 Apr 2018 16:55:39 -0400
Subject: drm/amdgpu: add more jpeg register offset headers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add more jpeg registers defines that are needed for jpeg ring functions

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h    | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h
index 18a32477ed1d..fe0cbaade3c3 100644
--- a/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h
+++ b/drivers/gpu/drm/amd/include/asic_reg/vcn/vcn_1_0_offset.h
@@ -89,6 +89,8 @@
 #define mmUVD_JPEG_RB_SIZE_BASE_IDX                                                                    1
 #define mmUVD_JPEG_ADDR_CONFIG                                                                         0x021f
 #define mmUVD_JPEG_ADDR_CONFIG_BASE_IDX                                                                1
+#define mmUVD_JPEG_PITCH                                                                               0x0222
+#define mmUVD_JPEG_PITCH_BASE_IDX                                                                      1
 #define mmUVD_JPEG_GPCOM_CMD                                                                           0x022c
 #define mmUVD_JPEG_GPCOM_CMD_BASE_IDX                                                                  1
 #define mmUVD_JPEG_GPCOM_DATA0                                                                         0x022d
@@ -203,6 +205,8 @@
 #define mmUVD_RB_WPTR4_BASE_IDX                                                                        1
 #define mmUVD_JRBC_RB_RPTR                                                                             0x0457
 #define mmUVD_JRBC_RB_RPTR_BASE_IDX                                                                    1
+#define mmUVD_LMI_JPEG_VMID                                                                            0x045d
+#define mmUVD_LMI_JPEG_VMID_BASE_IDX                                                                   1
 #define mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH                                                            0x045e
 #define mmUVD_LMI_VCPU_CACHE_64BIT_BAR_HIGH_BASE_IDX                                                   1
 #define mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW                                                             0x045f
@@ -231,6 +235,8 @@
 #define mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH_BASE_IDX                                                      1
 #define mmUVD_LMI_JRBC_IB_VMID                                                                         0x0507
 #define mmUVD_LMI_JRBC_IB_VMID_BASE_IDX                                                                1
+#define mmUVD_LMI_JRBC_RB_VMID                                                                         0x0508
+#define mmUVD_LMI_JRBC_RB_VMID_BASE_IDX                                                                1
 #define mmUVD_JRBC_RB_WPTR                                                                             0x0509
 #define mmUVD_JRBC_RB_WPTR_BASE_IDX                                                                    1
 #define mmUVD_JRBC_RB_CNTL                                                                             0x050a
@@ -239,6 +245,20 @@
 #define mmUVD_JRBC_IB_SIZE_BASE_IDX                                                                    1
 #define mmUVD_JRBC_LMI_SWAP_CNTL                                                                       0x050d
 #define mmUVD_JRBC_LMI_SWAP_CNTL_BASE_IDX                                                              1
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW                                                         0x050e
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW_BASE_IDX                                                1
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH                                                        0x050f
+#define mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH_BASE_IDX                                               1
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW                                                         0x0510
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW_BASE_IDX                                                1
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH                                                        0x0511
+#define mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH_BASE_IDX                                               1
+#define mmUVD_JRBC_RB_REF_DATA                                                                         0x0512
+#define mmUVD_JRBC_RB_REF_DATA_BASE_IDX                                                                1
+#define mmUVD_JRBC_RB_COND_RD_TIMER                                                                    0x0513
+#define mmUVD_JRBC_RB_COND_RD_TIMER_BASE_IDX                                                           1
+#define mmUVD_JRBC_EXTERNAL_REG_BASE                                                                   0x0517
+#define mmUVD_JRBC_EXTERNAL_REG_BASE_BASE_IDX                                                          1
 #define mmUVD_JRBC_SOFT_RESET                                                                          0x0519
 #define mmUVD_JRBC_SOFT_RESET_BASE_IDX                                                                 1
 #define mmUVD_JRBC_STATUS                                                                              0x051a
-- 
cgit v1.2.3


From 221f36c460d7d671e9d19d0d8184225aa068d3a8 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 14:39:07 -0400
Subject: drm/amdgpu: implement jpeg ring functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement all ring functions needed for jpeg ring

v2: remove unnecessary mem read function.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 286 ++++++++++++++++++++++++++++++++++
 1 file changed, 286 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 29684c3ea4ef..4f15833df8aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1126,6 +1126,292 @@ static void vcn_v1_0_enc_ring_emit_wreg(struct amdgpu_ring *ring,
 	amdgpu_ring_write(ring, val);
 }
 
+
+/**
+ * vcn_v1_0_jpeg_ring_get_rptr - get read pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware read pointer
+ */
+static uint64_t vcn_v1_0_jpeg_ring_get_rptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_get_wptr - get write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Returns the current hardware write pointer
+ */
+static uint64_t vcn_v1_0_jpeg_ring_get_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	return RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_set_wptr - set write pointer
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Commits the write pointer to the hardware
+ */
+static void vcn_v1_0_jpeg_ring_set_wptr(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, lower_32_bits(ring->wptr));
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_insert_start - insert a start command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a start command to the ring.
+ */
+static void vcn_v1_0_jpeg_ring_insert_start(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x80010000);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_insert_end - insert a end command
+ *
+ * @ring: amdgpu_ring pointer
+ *
+ * Write a end command to the ring.
+ */
+static void vcn_v1_0_jpeg_ring_insert_end(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x68e04);
+
+	amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x00010000);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_emit_fence - emit an fence & trap command
+ *
+ * @ring: amdgpu_ring pointer
+ * @fence: fence to emit
+ *
+ * Write a fence and a trap command to the ring.
+ */
+static void vcn_v1_0_jpeg_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+				     unsigned flags)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	WARN_ON(flags & AMDGPU_FENCE_FLAG_64BIT);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA0), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_DATA1), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_WR_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x8);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_GPCOM_CMD), 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE4));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, seq);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0xffffffff);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x3fbc);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x1);
+}
+
+/**
+ * vcn_v1_0_jpeg_ring_emit_ib - execute indirect buffer
+ *
+ * @ring: amdgpu_ring pointer
+ * @ib: indirect buffer to execute
+ *
+ * Write ring commands to execute the indirect buffer.
+ */
+static void vcn_v1_0_jpeg_ring_emit_ib(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib,
+				  unsigned vmid, bool ctx_switch)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_IB_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_IB_SIZE), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, ib->length_dw);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, lower_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, upper_32_bits(ring->gpu_addr));
+
+	amdgpu_ring_write(ring,
+		PACKETJ(0, 0, PACKETJ_CONDITION_CHECK0, PACKETJ_TYPE2));
+	amdgpu_ring_write(ring, 0);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_STATUS), 0, PACKETJ_CONDITION_CHECK3, PACKETJ_TYPE3));
+	amdgpu_ring_write(ring, 0x2);
+}
+
+static void vcn_v1_0_jpeg_ring_emit_reg_wait(struct amdgpu_ring *ring,
+					    uint32_t reg, uint32_t val,
+					    uint32_t mask)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, 0x01400200);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0));
+	amdgpu_ring_write(ring, val);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE3));
+	}
+	amdgpu_ring_write(ring, mask);
+}
+
+static void vcn_v1_0_jpeg_ring_emit_vm_flush(struct amdgpu_ring *ring,
+		unsigned vmid, uint64_t pd_addr)
+{
+	struct amdgpu_vmhub *hub = &ring->adev->vmhub[ring->funcs->vmhub];
+	uint32_t data0, data1, mask;
+
+	pd_addr = amdgpu_gmc_emit_flush_gpu_tlb(ring, vmid, pd_addr);
+
+	/* wait for register write */
+	data0 = hub->ctx0_ptb_addr_lo32 + vmid * 2;
+	data1 = lower_32_bits(pd_addr);
+	mask = 0xffffffff;
+	vcn_v1_0_jpeg_ring_emit_reg_wait(ring, data0, data1, mask);
+}
+
+static void vcn_v1_0_jpeg_ring_emit_wreg(struct amdgpu_ring *ring,
+					uint32_t reg, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t reg_offset = (reg << 2);
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0));
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+			((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		amdgpu_ring_write(ring, 0);
+		amdgpu_ring_write(ring,
+			PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0));
+	} else {
+		amdgpu_ring_write(ring, reg_offset);
+		amdgpu_ring_write(ring,
+			PACKETJ(0, 0, 0, PACKETJ_TYPE0));
+	}
+	amdgpu_ring_write(ring, val);
+}
+
+static void vcn_v1_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
+{
+	int i;
+
+	WARN_ON(ring->wptr % 2 || count % 2);
+
+	for (i = 0; i < count / 2; i++) {
+		amdgpu_ring_write(ring, PACKETJ(0, 0, 0, PACKETJ_TYPE6));
+		amdgpu_ring_write(ring, 0);
+	}
+}
+
 static int vcn_v1_0_set_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
-- 
cgit v1.2.3


From e612bcc3abbb10b6a2204e17849f9aed8627a46e Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 14:23:33 -0400
Subject: drm/amdgpu: set jpeg ring functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set all vcn jpeg ring function pointers.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 40 +++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 4f15833df8aa..8b29f471dad1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -38,6 +38,7 @@
 static int vcn_v1_0_stop(struct amdgpu_device *adev);
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
+static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev);
 
 /**
@@ -55,6 +56,7 @@ static int vcn_v1_0_early_init(void *handle)
 
 	vcn_v1_0_set_dec_ring_funcs(adev);
 	vcn_v1_0_set_enc_ring_funcs(adev);
+	vcn_v1_0_set_jpeg_ring_funcs(adev);
 	vcn_v1_0_set_irq_funcs(adev);
 
 	return 0;
@@ -1559,6 +1561,38 @@ static const struct amdgpu_ring_funcs vcn_v1_0_enc_ring_vm_funcs = {
 	.emit_reg_write_reg_wait = amdgpu_ring_emit_reg_write_reg_wait_helper,
 };
 
+static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
+	.type = AMDGPU_RING_TYPE_VCN_JPEG,
+	.align_mask = 0xf,
+	.nop = PACKET0(0x81ff, 0),
+	.support_64bit_ptrs = false,
+	.vmhub = AMDGPU_MMHUB,
+	.get_rptr = vcn_v1_0_jpeg_ring_get_rptr,
+	.get_wptr = vcn_v1_0_jpeg_ring_get_wptr,
+	.set_wptr = vcn_v1_0_jpeg_ring_set_wptr,
+	.emit_frame_size =
+		6 + 6 + /* hdp invalidate / flush */
+		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+		SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+		8 + /* vcn_v1_0_dec_ring_emit_vm_flush */
+		14 + 14 + /* vcn_v1_0_dec_ring_emit_fence x2 vm fence */
+		6,
+	.emit_ib_size = 22, /* vcn_v1_0_dec_ring_emit_ib */
+	.emit_ib = vcn_v1_0_jpeg_ring_emit_ib,
+	.emit_fence = vcn_v1_0_jpeg_ring_emit_fence,
+	.emit_vm_flush = vcn_v1_0_jpeg_ring_emit_vm_flush,
+	//.test_ring
+	//.test_ib
+	.insert_nop = vcn_v1_0_jpeg_ring_nop,
+	.insert_start = vcn_v1_0_jpeg_ring_insert_start,
+	.insert_end = vcn_v1_0_jpeg_ring_insert_end,
+	.pad_ib = amdgpu_ring_generic_pad_ib,
+	.begin_use = amdgpu_vcn_ring_begin_use,
+	.end_use = amdgpu_vcn_ring_end_use,
+	.emit_wreg = vcn_v1_0_jpeg_ring_emit_wreg,
+	.emit_reg_wait = vcn_v1_0_jpeg_ring_emit_reg_wait,
+};
+
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev)
 {
 	adev->vcn.ring_dec.funcs = &vcn_v1_0_dec_ring_vm_funcs;
@@ -1575,6 +1609,12 @@ static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	DRM_INFO("VCN encode is enabled in VM mode\n");
 }
 
+static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev)
+{
+	adev->vcn.ring_jpeg.funcs = &vcn_v1_0_jpeg_ring_vm_funcs;
+	DRM_INFO("VCN jpeg decode is enabled in VM mode\n");
+}
+
 static const struct amdgpu_irq_src_funcs vcn_v1_0_irq_funcs = {
 	.set = vcn_v1_0_set_interrupt_state,
 	.process = vcn_v1_0_process_interrupt,
-- 
cgit v1.2.3


From 59dd2b883fcd50d76b644d2ade084dae0137a8f7 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 14:42:33 -0400
Subject: drm/amdgpu: add vcn jpeg irq support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add vcn jpeg irq support.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 8b29f471dad1..076c49c91c2a 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -88,6 +88,11 @@ static int vcn_v1_0_sw_init(void *handle)
 			return r;
 	}
 
+	/* VCN JPEG TRAP */
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 126, &adev->vcn.irq);
+	if (r)
+		return r;
+
 	r = amdgpu_vcn_sw_init(adev);
 	if (r)
 		return r;
@@ -1438,6 +1443,9 @@ static int vcn_v1_0_process_interrupt(struct amdgpu_device *adev,
 	case 120:
 		amdgpu_fence_process(&adev->vcn.ring_enc[1]);
 		break;
+	case 126:
+		amdgpu_fence_process(&adev->vcn.ring_jpeg);
+		break;
 	default:
 		DRM_ERROR("Unhandled interrupt: %d %d\n",
 			  entry->src_id, entry->src_data[0]);
-- 
cgit v1.2.3


From d2314b48d62110d5ce9aebcc8900bc44eed72700 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 14:47:39 -0400
Subject: drm/amdgpu: initialize vcn jpeg ring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add implementations for vcn jpeg ring initialization

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 076c49c91c2a..ea1d677d02c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -115,6 +115,12 @@ static int vcn_v1_0_sw_init(void *handle)
 			return r;
 	}
 
+	ring = &adev->vcn.ring_jpeg;
+	sprintf(ring->name, "vcn_jpeg");
+	r = amdgpu_ring_init(adev, ring, 512, &adev->vcn.irq, 0);
+	if (r)
+		return r;
+
 	return r;
 }
 
@@ -169,6 +175,14 @@ static int vcn_v1_0_hw_init(void *handle)
 		}
 	}
 
+	ring = &adev->vcn.ring_jpeg;
+	ring->ready = true;
+	r = amdgpu_ring_test_ring(ring);
+	if (r) {
+		ring->ready = false;
+		goto done;
+	}
+
 done:
 	if (!r)
 		DRM_INFO("VCN decode and encode initialized successfully.\n");
@@ -736,6 +750,15 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_RB_BASE_HI2, upper_32_bits(ring->gpu_addr));
 	WREG32_SOC15(UVD, 0, mmUVD_RB_SIZE2, ring->ring_size / 4);
 
+	ring = &adev->vcn.ring_jpeg;
+	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_VMID, 0);
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, (0x00000001L | 0x00000002L));
+	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_LOW, lower_32_bits(ring->gpu_addr));
+	WREG32_SOC15(UVD, 0, mmUVD_LMI_JRBC_RB_64BIT_BAR_HIGH, upper_32_bits(ring->gpu_addr));
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_RPTR, 0);
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
+	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 8a998052f29b811497b004b87dfe1ea1dfef75d1 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 14:57:16 -0400
Subject: drm/amdgpu: implement patch for fixing a known bug
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement a patch to maunally reset read pointer

v2: using ring assignment instead of amdgpu_ring_write. adding comments
for each steps in the patch function.
v3: fixing a typo bug.
v4: fixing a bug in v3.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 92 +++++++++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index ea1d677d02c8..92f78c559fc5 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -40,6 +40,7 @@ static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_jpeg_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr);
 
 /**
  * vcn_v1_0_early_init - set function pointers
@@ -1442,6 +1443,97 @@ static void vcn_v1_0_jpeg_ring_nop(struct amdgpu_ring *ring, uint32_t count)
 	}
 }
 
+static void vcn_v1_0_jpeg_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
+{
+	struct amdgpu_device *adev = ring->adev;
+	ring->ring[(*ptr)++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[(*ptr)++] = 0;
+		ring->ring[(*ptr)++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE0);
+	} else {
+		ring->ring[(*ptr)++] = reg_offset;
+		ring->ring[(*ptr)++] = PACKETJ(0, 0, 0, PACKETJ_TYPE0);
+	}
+	ring->ring[(*ptr)++] = val;
+}
+
+static void vcn_v1_0_jpeg_ring_set_patch_ring(struct amdgpu_ring *ring, uint32_t ptr)
+{
+	struct amdgpu_device *adev = ring->adev;
+
+	uint32_t reg, reg_offset, val, mask, i;
+
+	// 1st: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_LOW);
+	reg_offset = (reg << 2);
+	val = lower_32_bits(ring->gpu_addr);
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 2nd: program mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_LMI_JRBC_RB_MEM_RD_64BIT_BAR_HIGH);
+	reg_offset = (reg << 2);
+	val = upper_32_bits(ring->gpu_addr);
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 3rd to 5th: issue MEM_READ commands
+	for (i = 0; i <= 2; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE2);
+		ring->ring[ptr++] = 0;
+	}
+
+	// 6th: program mmUVD_JRBC_RB_CNTL register to enable NO_FETCH and RPTR write ability
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x13;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 7th: program mmUVD_JRBC_RB_REF_DATA
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	// 8th: issue conditional register read mmUVD_JRBC_RB_CNTL
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x1;
+	mask = 0x1;
+
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_COND_RD_TIMER), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = 0x01400200;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_REF_DATA), 0, 0, PACKETJ_TYPE0);
+	ring->ring[ptr++] = val;
+	ring->ring[ptr++] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_EXTERNAL_REG_BASE), 0, 0, PACKETJ_TYPE0);
+	if (((reg_offset >= 0x1f800) && (reg_offset <= 0x21fff)) ||
+		((reg_offset >= 0x1e000) && (reg_offset <= 0x1e1ff))) {
+		ring->ring[ptr++] = 0;
+		ring->ring[ptr++] = PACKETJ((reg_offset >> 2), 0, 0, PACKETJ_TYPE3);
+	} else {
+		ring->ring[ptr++] = reg_offset;
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE3);
+	}
+	ring->ring[ptr++] = mask;
+
+	//9th to 21st: insert no-op
+	for (i = 0; i <= 12; i++) {
+		ring->ring[ptr++] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ring->ring[ptr++] = 0;
+	}
+
+	//22nd: reset mmUVD_JRBC_RB_RPTR
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_RPTR);
+	reg_offset = (reg << 2);
+	val = 0;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+
+	//23rd: program mmUVD_JRBC_RB_CNTL to disable no_fetch
+	reg = SOC15_REG_OFFSET(UVD, 0, mmUVD_JRBC_RB_CNTL);
+	reg_offset = (reg << 2);
+	val = 0x12;
+	vcn_v1_0_jpeg_ring_patch_wreg(ring, &ptr, reg_offset, val);
+}
+
 static int vcn_v1_0_set_interrupt_state(struct amdgpu_device *adev,
 					struct amdgpu_irq_src *source,
 					unsigned type,
-- 
cgit v1.2.3


From c8c1a1d2ef040d2661fc9c7f0b32aec5b1058ae3 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Fri, 1 Jun 2018 12:30:17 -0400
Subject: drm/amdgpu: define and add extra dword for jpeg ring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Define extra dword for jpeg ring. Jpeg ring will allocate extra dword to store
the patch commands for fixing the known issue.

v2: dropping extra_dw for rings other than jpeg.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 1 +
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c    | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index c6850b629d0e..19e45a3953e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -304,7 +304,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
 		0xffffffffffffffff : ring->buf_mask;
 	/* Allocate ring buffer */
 	if (ring->ring_obj == NULL) {
-		r = amdgpu_bo_create_kernel(adev, ring->ring_size, PAGE_SIZE,
+		r = amdgpu_bo_create_kernel(adev, ring->ring_size + ring->funcs->extra_dw, PAGE_SIZE,
 					    AMDGPU_GEM_DOMAIN_GTT,
 					    &ring->ring_obj,
 					    &ring->gpu_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index a3908efabb66..a293f4e6760d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -113,6 +113,7 @@ struct amdgpu_ring_funcs {
 	u32			nop;
 	bool			support_64bit_ptrs;
 	unsigned		vmhub;
+	unsigned		extra_dw;
 
 	/* ring read/write ptr handling */
 	u64 (*get_rptr)(struct amdgpu_ring *ring);
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 92f78c559fc5..8fecdc5cef43 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1690,6 +1690,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
 	.nop = PACKET0(0x81ff, 0),
 	.support_64bit_ptrs = false,
 	.vmhub = AMDGPU_MMHUB,
+	.extra_dw = 64,
 	.get_rptr = vcn_v1_0_jpeg_ring_get_rptr,
 	.get_wptr = vcn_v1_0_jpeg_ring_get_wptr,
 	.set_wptr = vcn_v1_0_jpeg_ring_set_wptr,
-- 
cgit v1.2.3


From b7fe681e35aaf8c844755297777bdceae030f6c3 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 15:19:52 -0400
Subject: drm/amdgpu: add patch to jpeg ring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add patch commands to jepg ring by calling set patch ring function.

v2: remove modifications on max_dw, buf_mask and ptr_mask, since we are
now using extra_dw for jpeg ring.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 8fecdc5cef43..32b70049fd91 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -760,6 +760,13 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
 	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR, 0);
 	WREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_CNTL, 0x00000002L);
 
+	/* initialize wptr */
+	ring->wptr = RREG32_SOC15(UVD, 0, mmUVD_JRBC_RB_WPTR);
+
+	/* copy patch commands to the jpeg ring */
+	vcn_v1_0_jpeg_ring_set_patch_ring(ring,
+		(ring->wptr + ring->max_dw * amdgpu_sched_hw_submission));
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 0c5e4b3e1e8a13cf918c1d2197e5b91fd865138a Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 15:32:16 -0400
Subject: drm/amdgpu: add vcn jpeg sw finish
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add software finish for vcn jpeg ring.

v2: remove unnecessary scheduler entity.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 127e87b470ff..d485a74de44d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -119,6 +119,8 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i)
 		amdgpu_ring_fini(&adev->vcn.ring_enc[i]);
 
+	amdgpu_ring_fini(&adev->vcn.ring_jpeg);
+
 	release_firmware(adev->vcn.fw);
 
 	return 0;
-- 
cgit v1.2.3


From b1d3760645acd7f16c377499460305d8f35bad00 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 15:49:51 -0400
Subject: drm/amdgpu: add vcn jpeg ring test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a ring test for vcn jpeg.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 40 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h |  2 ++
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c   |  2 +-
 3 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index d485a74de44d..0b97a72cc202 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -578,3 +578,43 @@ error:
 	dma_fence_put(fence);
 	return r;
 }
+
+int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	int r;
+
+	WREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID), 0xCAFEDEAD);
+	r = amdgpu_ring_alloc(ring, 3);
+
+	if (r) {
+		DRM_ERROR("amdgpu: cp failed to lock ring %d (%d).\n",
+				  ring->idx, r);
+		return r;
+	}
+
+	amdgpu_ring_write(ring,
+		PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID), 0, 0, 0));
+	amdgpu_ring_write(ring, 0xDEADBEEF);
+	amdgpu_ring_commit(ring);
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_CONTEXT_ID));
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+
+	if (i < adev->usec_timeout) {
+		DRM_DEBUG("ring test on %d succeeded in %d usecs\n",
+				  ring->idx, i);
+	} else {
+		DRM_ERROR("amdgpu: ring %d test failed (0x%08X)\n",
+				  ring->idx, tmp);
+		r = -EINVAL;
+	}
+
+	return r;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 6f3bed1cc1b3..0447faefb95a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -84,4 +84,6 @@ int amdgpu_vcn_dec_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring);
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
+int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring);
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 32b70049fd91..5fc58de0c402 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1712,7 +1712,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
 	.emit_ib = vcn_v1_0_jpeg_ring_emit_ib,
 	.emit_fence = vcn_v1_0_jpeg_ring_emit_fence,
 	.emit_vm_flush = vcn_v1_0_jpeg_ring_emit_vm_flush,
-	//.test_ring
+	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
 	//.test_ib
 	.insert_nop = vcn_v1_0_jpeg_ring_nop,
 	.insert_start = vcn_v1_0_jpeg_ring_insert_start,
-- 
cgit v1.2.3


From 6173040f167e2529c514765c6343abb55a4e0b44 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Wed, 30 May 2018 15:56:43 -0400
Subject: drm/amdgpu: add vcn jpeg ib test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add an ib test for vcn jpeg.

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 86 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h |  1 +
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c   |  2 +-
 3 files changed, 88 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 0b97a72cc202..3f2a5e73e69f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -618,3 +618,89 @@ int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring)
 
 	return r;
 }
+
+static int amdgpu_vcn_jpeg_set_reg(struct amdgpu_ring *ring, uint32_t handle,
+		struct dma_fence **fence)
+{
+	struct amdgpu_device *adev = ring->adev;
+	struct amdgpu_job *job;
+	struct amdgpu_ib *ib;
+	struct dma_fence *f = NULL;
+	const unsigned ib_size_dw = 16;
+	int i, r;
+
+	r = amdgpu_job_alloc_with_ib(ring->adev, ib_size_dw * 4, &job);
+	if (r)
+		return r;
+
+	ib = &job->ibs[0];
+
+	ib->ptr[0] = PACKETJ(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH), 0, 0, PACKETJ_TYPE0);
+	ib->ptr[1] = 0xDEADBEEF;
+	for (i = 2; i < 16; i += 2) {
+		ib->ptr[i] = PACKETJ(0, 0, 0, PACKETJ_TYPE6);
+		ib->ptr[i+1] = 0;
+	}
+	ib->length_dw = 16;
+
+	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
+	job->fence = dma_fence_get(f);
+	if (r)
+		goto err;
+
+	amdgpu_job_free(job);
+	if (fence)
+		*fence = dma_fence_get(f);
+	dma_fence_put(f);
+
+	return 0;
+
+err:
+	amdgpu_job_free(job);
+	return r;
+}
+
+int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout)
+{
+	struct amdgpu_device *adev = ring->adev;
+	uint32_t tmp = 0;
+	unsigned i;
+	struct dma_fence *fence = NULL;
+	long r = 0;
+
+	r = amdgpu_vcn_jpeg_set_reg(ring, 1, &fence);
+	if (r) {
+		DRM_ERROR("amdgpu: failed to set jpeg register (%ld).\n", r);
+		goto error;
+	}
+
+	r = dma_fence_wait_timeout(fence, false, timeout);
+	if (r == 0) {
+		DRM_ERROR("amdgpu: IB test timed out.\n");
+		r = -ETIMEDOUT;
+		goto error;
+	} else if (r < 0) {
+		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
+		goto error;
+	} else
+		r = 0;
+
+	for (i = 0; i < adev->usec_timeout; i++) {
+		tmp = RREG32(SOC15_REG_OFFSET(UVD, 0, mmUVD_JPEG_PITCH));
+		if (tmp == 0xDEADBEEF)
+			break;
+		DRM_UDELAY(1);
+	}
+
+	if (i < adev->usec_timeout)
+		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
+	else {
+		DRM_ERROR("ib test failed (0x%08X)\n", tmp);
+		r = -EINVAL;
+	}
+
+	dma_fence_put(fence);
+
+error:
+	return r;
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
index 0447faefb95a..0b0b8638d73f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
@@ -85,5 +85,6 @@ int amdgpu_vcn_enc_ring_test_ring(struct amdgpu_ring *ring);
 int amdgpu_vcn_enc_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
 int amdgpu_vcn_jpeg_ring_test_ring(struct amdgpu_ring *ring);
+int amdgpu_vcn_jpeg_ring_test_ib(struct amdgpu_ring *ring, long timeout);
 
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index 5fc58de0c402..b82c92084b6f 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -1713,7 +1713,7 @@ static const struct amdgpu_ring_funcs vcn_v1_0_jpeg_ring_vm_funcs = {
 	.emit_fence = vcn_v1_0_jpeg_ring_emit_fence,
 	.emit_vm_flush = vcn_v1_0_jpeg_ring_emit_vm_flush,
 	.test_ring = amdgpu_vcn_jpeg_ring_test_ring,
-	//.test_ib
+	.test_ib = amdgpu_vcn_jpeg_ring_test_ib,
 	.insert_nop = vcn_v1_0_jpeg_ring_nop,
 	.insert_start = vcn_v1_0_jpeg_ring_insert_start,
 	.insert_end = vcn_v1_0_jpeg_ring_insert_end,
-- 
cgit v1.2.3


From 5b2329b61875e7118a599f2f1cf6d23c8ac75a69 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Tue, 1 May 2018 14:40:24 -0400
Subject: drm/amdgpu: enable vcn jpeg ib test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Enable vcn jpeg ib ring test in amdgpu_ib.c

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index f70eeed9ed76..31f8170313b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -353,7 +353,8 @@ int amdgpu_ib_ring_tests(struct amdgpu_device *adev)
 			ring->funcs->type == AMDGPU_RING_TYPE_VCE ||
 			ring->funcs->type == AMDGPU_RING_TYPE_UVD_ENC ||
 			ring->funcs->type == AMDGPU_RING_TYPE_VCN_DEC ||
-			ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
+			ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC ||
+			ring->funcs->type == AMDGPU_RING_TYPE_VCN_JPEG)
 			tmo = tmo_mm;
 		else
 			tmo = tmo_gfx;
-- 
cgit v1.2.3


From 81d350144bd4590ae546d83344421106e8faf69a Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Tue, 1 May 2018 14:47:31 -0400
Subject: uapi/drm: add AMDGPU_HW_IP_VCN_JPEG for jpeg CS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add AMDGPU_HW_IP_VCN_JPEG define for jpeg CS

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/uapi/drm/amdgpu_drm.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 0dc9e606114e..784b0fe470ee 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -506,7 +506,8 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_HW_IP_UVD_ENC      5
 #define AMDGPU_HW_IP_VCN_DEC      6
 #define AMDGPU_HW_IP_VCN_ENC      7
-#define AMDGPU_HW_IP_NUM          8
+#define AMDGPU_HW_IP_VCN_JPEG     8
+#define AMDGPU_HW_IP_NUM          9
 
 #define AMDGPU_HW_IP_INSTANCE_MAX_COUNT 1
 
-- 
cgit v1.2.3


From 4bafe44024295f087fd633a16e100a34ca363e7c Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Tue, 1 May 2018 14:58:25 -0400
Subject: drm/amdgpu: add AMDGPU_HW_IP_VCN_JPEG to info query
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add AMDGPU_HW_IP_VCN_JPEG to info query

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index c472bb53e41d..ec1060a5eab3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -383,6 +383,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
 			ib_size_alignment = 1;
 			break;
+		case AMDGPU_HW_IP_VCN_JPEG:
+			type = AMD_IP_BLOCK_TYPE_VCN;
+			ring_mask = adev->vcn.ring_jpeg.ready ? 1 : 0;
+			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+			ib_size_alignment = 16;
+			break;
 		default:
 			return -EINVAL;
 		}
@@ -427,6 +433,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 		case AMDGPU_HW_IP_VCN_ENC:
+		case AMDGPU_HW_IP_VCN_JPEG:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			break;
 		default:
-- 
cgit v1.2.3


From b7e6cd57027f5151d4f330dfabb0182f78d26e83 Mon Sep 17 00:00:00 2001
From: Boyuan Zhang <boyuan.zhang@amd.com>
Date: Tue, 1 May 2018 14:59:12 -0400
Subject: drm/amdgpu: add AMDGPU_HW_IP_VCN_JPEG to queue mgr
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add AMDGPU_HW_IP_VCN_JPEG to queue mgr

Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index 8af16e81c7d4..ea9850c9224d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -96,6 +96,9 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 	case AMDGPU_HW_IP_VCN_ENC:
 		*out_ring = &adev->vcn.ring_enc[ring];
 		break;
+	case AMDGPU_HW_IP_VCN_JPEG:
+		*out_ring = &adev->vcn.ring_jpeg;
+		break;
 	default:
 		*out_ring = NULL;
 		DRM_ERROR("unknown HW IP type: %d\n", mapper->hw_ip);
@@ -260,6 +263,9 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 	case AMDGPU_HW_IP_VCN_ENC:
 		ip_num_rings = adev->vcn.num_enc_rings;
 		break;
+	case AMDGPU_HW_IP_VCN_JPEG:
+		ip_num_rings = 1;
+		break;
 	default:
 		DRM_DEBUG("unknown ip type: %d\n", hw_ip);
 		return -EINVAL;
@@ -287,6 +293,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 	case AMDGPU_HW_IP_UVD_ENC:
 	case AMDGPU_HW_IP_VCN_DEC:
 	case AMDGPU_HW_IP_VCN_ENC:
+	case AMDGPU_HW_IP_VCN_JPEG:
 		r = amdgpu_identity_map(adev, mapper, ring, out_ring);
 		break;
 	case AMDGPU_HW_IP_DMA:
-- 
cgit v1.2.3


From 11528640c77891363bc7dea749ced64607aa1b22 Mon Sep 17 00:00:00 2001
From: Emily Deng <Emily.Deng@amd.com>
Date: Fri, 8 Jun 2018 16:36:22 +0800
Subject: drm/amdgpu: Correct the ndw of bo update mapping.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For buffer object that has shadow buffer, need twice commands.

Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index b0eb2f537392..d88687b617e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1324,7 +1324,10 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 		ndw += ncmds * 10;
 
 		/* extra commands for begin/end fragments */
-		ndw += 2 * 10 * adev->vm_manager.fragment_size;
+		if (vm->root.base.bo->shadow)
+		        ndw += 2 * 10 * adev->vm_manager.fragment_size * 2;
+		else
+		        ndw += 2 * 10 * adev->vm_manager.fragment_size;
 
 		params.func = amdgpu_vm_do_set_ptes;
 	}
-- 
cgit v1.2.3


From 8f4039fefd94a0ca2c61507975f6d47f9fc9943a Mon Sep 17 00:00:00 2001
From: Shirish S <shirish.s@amd.com>
Date: Fri, 8 Jun 2018 10:15:42 +0530
Subject: drm/amdgpu: change gfx8 ib test to use WB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch is extends the usage of WB in
gfx8's ib test which was originally
implemented in the below upstream patch
"ed9324a drm/amdgpu: change gfx9 ib test to use WB"

For reference below are the reasons for switching
to WB:

1)Because when doing IB test we don't want to involve KIQ health
status affect, and since SCRATCH register access is go through
KIQ that way GFX IB test would failed due to KIQ fail.

2)acccessing SCRATCH register cost much more time than WB method
because SCRATCH register access runs through KIQ which at least could
begin after GPU world switch back to current Guest VF

Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 818874b13c99..61452c7c4024 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -866,26 +866,32 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 	struct amdgpu_device *adev = ring->adev;
 	struct amdgpu_ib ib;
 	struct dma_fence *f = NULL;
-	uint32_t scratch;
-	uint32_t tmp = 0;
+
+	unsigned int index;
+	uint64_t gpu_addr;
+	uint32_t tmp;
 	long r;
 
-	r = amdgpu_gfx_scratch_get(adev, &scratch);
+	r = amdgpu_device_wb_get(adev, &index);
 	if (r) {
-		DRM_ERROR("amdgpu: failed to get scratch reg (%ld).\n", r);
+		dev_err(adev->dev, "(%ld) failed to allocate wb slot\n", r);
 		return r;
 	}
-	WREG32(scratch, 0xCAFEDEAD);
+
+	gpu_addr = adev->wb.gpu_addr + (index * 4);
+	adev->wb.wb[index] = cpu_to_le32(0xCAFEDEAD);
 	memset(&ib, 0, sizeof(ib));
-	r = amdgpu_ib_get(adev, NULL, 256, &ib);
+	r = amdgpu_ib_get(adev, NULL, 16, &ib);
 	if (r) {
 		DRM_ERROR("amdgpu: failed to get ib (%ld).\n", r);
 		goto err1;
 	}
-	ib.ptr[0] = PACKET3(PACKET3_SET_UCONFIG_REG, 1);
-	ib.ptr[1] = ((scratch - PACKET3_SET_UCONFIG_REG_START));
-	ib.ptr[2] = 0xDEADBEEF;
-	ib.length_dw = 3;
+	ib.ptr[0] = PACKET3(PACKET3_WRITE_DATA, 3);
+	ib.ptr[1] = WRITE_DATA_DST_SEL(5) | WR_CONFIRM;
+	ib.ptr[2] = lower_32_bits(gpu_addr);
+	ib.ptr[3] = upper_32_bits(gpu_addr);
+	ib.ptr[4] = 0xDEADBEEF;
+	ib.length_dw = 5;
 
 	r = amdgpu_ib_schedule(ring, 1, &ib, NULL, &f);
 	if (r)
@@ -900,20 +906,21 @@ static int gfx_v8_0_ring_test_ib(struct amdgpu_ring *ring, long timeout)
 		DRM_ERROR("amdgpu: fence wait failed (%ld).\n", r);
 		goto err2;
 	}
-	tmp = RREG32(scratch);
+
+	tmp = adev->wb.wb[index];
 	if (tmp == 0xDEADBEEF) {
 		DRM_DEBUG("ib test on ring %d succeeded\n", ring->idx);
 		r = 0;
 	} else {
-		DRM_ERROR("amdgpu: ib test failed (scratch(0x%04X)=0x%08X)\n",
-			  scratch, tmp);
+		DRM_ERROR("ib test on ring %d failed\n", ring->idx);
 		r = -EINVAL;
 	}
+
 err2:
 	amdgpu_ib_free(adev, &ib, NULL);
 	dma_fence_put(f);
 err1:
-	amdgpu_gfx_scratch_free(adev, scratch);
+	amdgpu_device_wb_free(adev, index);
 	return r;
 }
 
-- 
cgit v1.2.3


From 5a2f291343bc349aef45b9fdbe73332b933fa92b Mon Sep 17 00:00:00 2001
From: David Panariti <David.Panariti@amd.com>
Date: Tue, 15 May 2018 11:45:11 -0400
Subject: drm/amdgpu: Added ISR for CP ECC/EDC interrupt v2.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ISR will DRM_ERROR ECC error message.

v2:
Remove CZ only limitation.
Rebase.

Signed-off-by: David Panariti <David.Panariti@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h   |  1 +
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 75 +++++++++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index a59c07590cee..54be18b1ac94 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -968,6 +968,7 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		eop_irq;
 	struct amdgpu_irq_src		priv_reg_irq;
 	struct amdgpu_irq_src		priv_inst_irq;
+	struct amdgpu_irq_src		cp_ecc_error_irq;
 	/* gfx status */
 	uint32_t			gfx_current_status;
 	/* ce ram size*/
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 61452c7c4024..dbc47a727fe7 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2055,6 +2055,12 @@ static int gfx_v8_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	/* Add CP EDC/ECC irq  */
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 197,
+			      &adev->gfx.cp_ecc_error_irq);
+	if (r)
+		return r;
+
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
 	gfx_v8_0_scratch_init(adev);
@@ -5118,6 +5124,8 @@ static int gfx_v8_0_hw_fini(void *handle)
 	amdgpu_irq_put(adev, &adev->gfx.priv_reg_irq, 0);
 	amdgpu_irq_put(adev, &adev->gfx.priv_inst_irq, 0);
 
+	amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0);
+
 	/* disable KCQ to avoid CPC touch memory not valid anymore */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
 		gfx_v8_0_kcq_disable(&adev->gfx.kiq.ring, &adev->gfx.compute_ring[i]);
@@ -5549,6 +5557,12 @@ static int gfx_v8_0_late_init(void *handle)
 	if (r)
 		return r;
 
+	r = amdgpu_irq_get(adev, &adev->gfx.cp_ecc_error_irq, 0);
+	if (r) {
+		DRM_ERROR("amdgpu_irq_get() failed to get IRQ for EDC, r: %d.\n", r);
+		return r;
+	}
+
 	amdgpu_device_ip_set_powergating_state(adev,
 					       AMD_IP_BLOCK_TYPE_GFX,
 					       AMD_PG_STATE_GATE);
@@ -6794,6 +6808,51 @@ static int gfx_v8_0_set_eop_interrupt_state(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int gfx_v8_0_set_cp_ecc_int_state(struct amdgpu_device *adev,
+					 struct amdgpu_irq_src *source,
+					 unsigned int type,
+					 enum amdgpu_interrupt_state state)
+{
+	int enable_flag;
+
+	switch (state) {
+	case AMDGPU_IRQ_STATE_DISABLE:
+		enable_flag = 0;
+		break;
+
+	case AMDGPU_IRQ_STATE_ENABLE:
+		enable_flag = 1;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	WREG32_FIELD(CP_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_INT_CNTL_RING0, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_INT_CNTL_RING1, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_INT_CNTL_RING2, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CPC_INT_CNTL, CP_ECC_ERROR_INT_ENABLE, enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE1_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE2_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME1_PIPE3_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE0_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE1_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE2_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+	WREG32_FIELD(CP_ME2_PIPE3_INT_CNTL, CP_ECC_ERROR_INT_ENABLE,
+		     enable_flag);
+
+	return 0;
+}
+
 static int gfx_v8_0_eop_irq(struct amdgpu_device *adev,
 			    struct amdgpu_irq_src *source,
 			    struct amdgpu_iv_entry *entry)
@@ -6844,6 +6903,14 @@ static int gfx_v8_0_priv_inst_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int gfx_v8_0_cp_ecc_error_irq(struct amdgpu_device *adev,
+				     struct amdgpu_irq_src *source,
+				     struct amdgpu_iv_entry *entry)
+{
+	DRM_ERROR("ECC error detected.");
+	return 0;
+}
+
 static int gfx_v8_0_kiq_set_interrupt_state(struct amdgpu_device *adev,
 					    struct amdgpu_irq_src *src,
 					    unsigned int type,
@@ -7044,6 +7111,11 @@ static const struct amdgpu_irq_src_funcs gfx_v8_0_kiq_irq_funcs = {
 	.process = gfx_v8_0_kiq_irq,
 };
 
+static const struct amdgpu_irq_src_funcs gfx_v8_0_cp_ecc_error_irq_funcs = {
+	.set = gfx_v8_0_set_cp_ecc_int_state,
+	.process = gfx_v8_0_cp_ecc_error_irq,
+};
+
 static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->gfx.eop_irq.num_types = AMDGPU_CP_IRQ_LAST;
@@ -7057,6 +7129,9 @@ static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 
 	adev->gfx.kiq.irq.num_types = AMDGPU_CP_KIQ_IRQ_LAST;
 	adev->gfx.kiq.irq.funcs = &gfx_v8_0_kiq_irq_funcs;
+
+	adev->gfx.cp_ecc_error_irq.num_types = 1;
+	adev->gfx.cp_ecc_error_irq.funcs = &gfx_v8_0_cp_ecc_error_irq_funcs;
 }
 
 static void gfx_v8_0_set_rlc_funcs(struct amdgpu_device *adev)
-- 
cgit v1.2.3


From 981658c67a97591ce03b5b94f7be9f5f92720e8d Mon Sep 17 00:00:00 2001
From: David Panariti <David.Panariti@amd.com>
Date: Tue, 22 May 2018 14:09:06 -0400
Subject: drm/amdgpu: Add interrupt SQ source struct to amdgpu_gfx struct v2.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SQ can generate interrupts on EDC/ECC errors and this struct controls
how the interrupt is handled.  The guts are filled in in the
gf_v<major>_<minor>.c files.

v2:
Rebase.

Signed-off-by: David Panariti <David.Panariti@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 54be18b1ac94..71b9b861f60e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -969,6 +969,7 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_reg_irq;
 	struct amdgpu_irq_src		priv_inst_irq;
 	struct amdgpu_irq_src		cp_ecc_error_irq;
+	struct amdgpu_irq_src		sq_irq;
 	/* gfx status */
 	uint32_t			gfx_current_status;
 	/* ce ram size*/
-- 
cgit v1.2.3


From 04ad26bbc41edea0529aed9a92e146e46b6efe5e Mon Sep 17 00:00:00 2001
From: David Panariti <David.Panariti@amd.com>
Date: Tue, 22 May 2018 14:25:49 -0400
Subject: drm/amdgpu: Add plumbing for handling SQ EDC/ECC interrupts v2.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SQ can generate interrupts and installs the ISR to
handle the SQ interrupts.

Add parsing SQ data in interrupt handler.

v2:
Remove CZ only limitation.
Rebase.

Signed-off-by: David Panariti <David.Panariti@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 109 +++++++++++++++++++++++++++++++++-
 1 file changed, 108 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index dbc47a727fe7..807ee0dd623c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -2061,6 +2061,14 @@ static int gfx_v8_0_sw_init(void *handle)
 	if (r)
 		return r;
 
+	/* SQ interrupts. */
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 239,
+			      &adev->gfx.sq_irq);
+	if (r) {
+		DRM_ERROR("amdgpu_irq_add() for SQ failed: %d\n", r);
+		return r;
+	}
+
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
 	gfx_v8_0_scratch_init(adev);
@@ -5126,6 +5134,8 @@ static int gfx_v8_0_hw_fini(void *handle)
 
 	amdgpu_irq_put(adev, &adev->gfx.cp_ecc_error_irq, 0);
 
+	amdgpu_irq_put(adev, &adev->gfx.sq_irq, 0);
+
 	/* disable KCQ to avoid CPC touch memory not valid anymore */
 	for (i = 0; i < adev->gfx.num_compute_rings; i++)
 		gfx_v8_0_kcq_disable(&adev->gfx.kiq.ring, &adev->gfx.compute_ring[i]);
@@ -5563,6 +5573,14 @@ static int gfx_v8_0_late_init(void *handle)
 		return r;
 	}
 
+	r = amdgpu_irq_get(adev, &adev->gfx.sq_irq, 0);
+	if (r) {
+		DRM_ERROR(
+			"amdgpu_irq_get() failed to get IRQ for SQ, r: %d.\n",
+			r);
+		return r;
+	}
+
 	amdgpu_device_ip_set_powergating_state(adev,
 					       AMD_IP_BLOCK_TYPE_GFX,
 					       AMD_PG_STATE_GATE);
@@ -6853,6 +6871,32 @@ static int gfx_v8_0_set_cp_ecc_int_state(struct amdgpu_device *adev,
 	return 0;
 }
 
+static int gfx_v8_0_set_sq_int_state(struct amdgpu_device *adev,
+				     struct amdgpu_irq_src *source,
+				     unsigned int type,
+				     enum amdgpu_interrupt_state state)
+{
+	int enable_flag;
+
+	switch (state) {
+	case AMDGPU_IRQ_STATE_DISABLE:
+		enable_flag = 1;
+		break;
+
+	case AMDGPU_IRQ_STATE_ENABLE:
+		enable_flag = 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	WREG32_FIELD(SQ_INTERRUPT_MSG_CTRL, STALL,
+		     enable_flag);
+
+	return 0;
+}
+
 static int gfx_v8_0_eop_irq(struct amdgpu_device *adev,
 			    struct amdgpu_irq_src *source,
 			    struct amdgpu_iv_entry *entry)
@@ -6907,7 +6951,62 @@ static int gfx_v8_0_cp_ecc_error_irq(struct amdgpu_device *adev,
 				     struct amdgpu_irq_src *source,
 				     struct amdgpu_iv_entry *entry)
 {
-	DRM_ERROR("ECC error detected.");
+	DRM_ERROR("CP EDC/ECC error detected.");
+	return 0;
+}
+
+static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
+			   struct amdgpu_irq_src *source,
+			   struct amdgpu_iv_entry *entry)
+{
+	u8 enc, se_id;
+	char type[20];
+
+	/* Parse all fields according to SQ_INTERRUPT* registers */
+	enc = (entry->src_data[0] >> 26) & 0x3;
+	se_id = (entry->src_data[0] >> 24) & 0x3;
+
+	switch (enc) {
+		case 0:
+			DRM_INFO("SQ general purpose intr detected:"
+					"se_id %d, immed_overflow %d, host_reg_overflow %d,"
+					"host_cmd_overflow %d, cmd_timestamp %d,"
+					"reg_timestamp %d, thread_trace_buff_full %d,"
+					"wlt %d, thread_trace %d.\n",
+					se_id,
+					(entry->src_data[0] >> 7) & 0x1,
+					(entry->src_data[0] >> 6) & 0x1,
+					(entry->src_data[0] >> 5) & 0x1,
+					(entry->src_data[0] >> 4) & 0x1,
+					(entry->src_data[0] >> 3) & 0x1,
+					(entry->src_data[0] >> 2) & 0x1,
+					(entry->src_data[0] >> 1) & 0x1,
+					entry->src_data[0] & 0x1
+					);
+			break;
+		case 1:
+		case 2:
+
+			if (enc == 1)
+				sprintf(type, "instruction intr");
+			else
+				sprintf(type, "EDC/ECC error");
+
+			DRM_INFO(
+				"SQ %s detected: "
+					"se_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d\n",
+					type, se_id,
+					(entry->src_data[0] >> 20) & 0xf,
+					(entry->src_data[0] >> 18) & 0x3,
+					(entry->src_data[0] >> 14) & 0xf,
+					(entry->src_data[0] >> 10) & 0xf
+					);
+			break;
+		default:
+			DRM_ERROR("SQ invalid encoding type\n.");
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -7116,6 +7215,11 @@ static const struct amdgpu_irq_src_funcs gfx_v8_0_cp_ecc_error_irq_funcs = {
 	.process = gfx_v8_0_cp_ecc_error_irq,
 };
 
+static const struct amdgpu_irq_src_funcs gfx_v8_0_sq_irq_funcs = {
+	.set = gfx_v8_0_set_sq_int_state,
+	.process = gfx_v8_0_sq_irq,
+};
+
 static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 {
 	adev->gfx.eop_irq.num_types = AMDGPU_CP_IRQ_LAST;
@@ -7132,6 +7236,9 @@ static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev)
 
 	adev->gfx.cp_ecc_error_irq.num_types = 1;
 	adev->gfx.cp_ecc_error_irq.funcs = &gfx_v8_0_cp_ecc_error_irq_funcs;
+
+	adev->gfx.sq_irq.num_types = 1;
+	adev->gfx.sq_irq.funcs = &gfx_v8_0_sq_irq_funcs;
 }
 
 static void gfx_v8_0_set_rlc_funcs(struct amdgpu_device *adev)
-- 
cgit v1.2.3


From 59d61be2229fcb8d52db6ba3f82658f501c06333 Mon Sep 17 00:00:00 2001
From: Junwei Zhang <Jerry.Zhang@amd.com>
Date: Tue, 12 Jun 2018 13:57:45 +0800
Subject: drm/amdgpu: remove unused parameter for va update
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Don't need validation list any more

Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: David Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 7f27cdb7afe2..89743cdc1c2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -510,7 +510,6 @@ out:
  * @adev: amdgpu_device pointer
  * @vm: vm to update
  * @bo_va: bo_va to update
- * @list: validation list
  * @operation: map, unmap or clear
  *
  * Update the bo_va directly after setting its address. Errors are not
@@ -519,7 +518,6 @@ out:
 static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
 				    struct amdgpu_vm *vm,
 				    struct amdgpu_bo_va *bo_va,
-				    struct list_head *list,
 				    uint32_t operation)
 {
 	int r;
@@ -673,7 +671,7 @@ int amdgpu_gem_va_ioctl(struct drm_device *dev, void *data,
 		break;
 	}
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE) && !amdgpu_vm_debug)
-		amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va, &list,
+		amdgpu_gem_va_update_vm(adev, &fpriv->vm, bo_va,
 					args->operation);
 
 error_backoff:
-- 
cgit v1.2.3


From abea57d70e90b0c41b9a3b9d7b7d39ab81146e19 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Thu, 7 Jun 2018 15:45:08 -0400
Subject: drm/amdgpu: Add BRACKET_LAYOUT_ENUMs to ObjectID.h

DC has an upcoming change that requires these to read the board layout.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/ObjectID.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/ObjectID.h b/drivers/gpu/drm/amd/amdgpu/ObjectID.h
index 06192698bd96..5b393622f592 100644
--- a/drivers/gpu/drm/amd/amdgpu/ObjectID.h
+++ b/drivers/gpu/drm/amd/amdgpu/ObjectID.h
@@ -136,6 +136,7 @@
 #define GENERIC_OBJECT_ID_PX2_NON_DRIVABLE        0x02
 #define GENERIC_OBJECT_ID_MXM_OPM                 0x03
 #define GENERIC_OBJECT_ID_STEREO_PIN              0x04        //This object could show up from Misc Object table, it follows ATOM_OBJECT format, and contains one ATOM_OBJECT_GPIO_CNTL_RECORD for the stereo pin
+#define GENERIC_OBJECT_ID_BRACKET_LAYOUT          0x05
 
 /****************************************************/
 /* Graphics Object ENUM ID Definition               */
@@ -714,6 +715,13 @@
                                                  GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
                                                  GENERIC_OBJECT_ID_STEREO_PIN << OBJECT_ID_SHIFT)
 
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1    (GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
+                                                 GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2    (GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+                                                 GRAPH_OBJECT_ENUM_ID2 << ENUM_ID_SHIFT |\
+                                                 GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
 /****************************************************/
 /* Object Cap definition - Shared with BIOS         */
 /****************************************************/
-- 
cgit v1.2.3


From 528e083d85bd0306e056fe1bdfd05493ebbff9cc Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 13 Jun 2018 14:55:20 -0500
Subject: drm/amdgpu: rename rmn to amn in the MMU notifier code (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just a copy&paste leftover from radeon.

v2: rebase (Alex)

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 140 ++++++++++++++++-----------------
 1 file changed, 70 insertions(+), 70 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 83e344fbb50a..37570a1c6db8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -64,7 +64,7 @@ struct amdgpu_mn_node {
 };
 
 /**
- * amdgpu_mn_destroy - destroy the rmn
+ * amdgpu_mn_destroy - destroy the amn
  *
  * @work: previously sheduled work item
  *
@@ -72,26 +72,26 @@ struct amdgpu_mn_node {
  */
 static void amdgpu_mn_destroy(struct work_struct *work)
 {
-	struct amdgpu_mn *rmn = container_of(work, struct amdgpu_mn, work);
-	struct amdgpu_device *adev = rmn->adev;
+	struct amdgpu_mn *amn = container_of(work, struct amdgpu_mn, work);
+	struct amdgpu_device *adev = amn->adev;
 	struct amdgpu_mn_node *node, *next_node;
 	struct amdgpu_bo *bo, *next_bo;
 
 	mutex_lock(&adev->mn_lock);
-	down_write(&rmn->lock);
-	hash_del(&rmn->node);
+	down_write(&amn->lock);
+	hash_del(&amn->node);
 	rbtree_postorder_for_each_entry_safe(node, next_node,
-					     &rmn->objects.rb_root, it.rb) {
+					     &amn->objects.rb_root, it.rb) {
 		list_for_each_entry_safe(bo, next_bo, &node->bos, mn_list) {
 			bo->mn = NULL;
 			list_del_init(&bo->mn_list);
 		}
 		kfree(node);
 	}
-	up_write(&rmn->lock);
+	up_write(&amn->lock);
 	mutex_unlock(&adev->mn_lock);
-	mmu_notifier_unregister_no_release(&rmn->mn, rmn->mm);
-	kfree(rmn);
+	mmu_notifier_unregister_no_release(&amn->mn, amn->mm);
+	kfree(amn);
 }
 
 /**
@@ -105,9 +105,9 @@ static void amdgpu_mn_destroy(struct work_struct *work)
 static void amdgpu_mn_release(struct mmu_notifier *mn,
 			      struct mm_struct *mm)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
-	INIT_WORK(&rmn->work, amdgpu_mn_destroy);
-	schedule_work(&rmn->work);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
+	INIT_WORK(&amn->work, amdgpu_mn_destroy);
+	schedule_work(&amn->work);
 }
 
 
@@ -130,31 +130,31 @@ void amdgpu_mn_unlock(struct amdgpu_mn *mn)
 }
 
 /**
- * amdgpu_mn_read_lock - take the rmn read lock
+ * amdgpu_mn_read_lock - take the amn read lock
  *
- * @rmn: our notifier
+ * @amn: our notifier
  *
- * Take the rmn read side lock.
+ * Take the amn read side lock.
  */
-static void amdgpu_mn_read_lock(struct amdgpu_mn *rmn)
+static void amdgpu_mn_read_lock(struct amdgpu_mn *amn)
 {
-	mutex_lock(&rmn->read_lock);
-	if (atomic_inc_return(&rmn->recursion) == 1)
-		down_read_non_owner(&rmn->lock);
-	mutex_unlock(&rmn->read_lock);
+	mutex_lock(&amn->read_lock);
+	if (atomic_inc_return(&amn->recursion) == 1)
+		down_read_non_owner(&amn->lock);
+	mutex_unlock(&amn->read_lock);
 }
 
 /**
- * amdgpu_mn_read_unlock - drop the rmn read lock
+ * amdgpu_mn_read_unlock - drop the amn read lock
  *
- * @rmn: our notifier
+ * @amn: our notifier
  *
- * Drop the rmn read side lock.
+ * Drop the amn read side lock.
  */
-static void amdgpu_mn_read_unlock(struct amdgpu_mn *rmn)
+static void amdgpu_mn_read_unlock(struct amdgpu_mn *amn)
 {
-	if (atomic_dec_return(&rmn->recursion) == 0)
-		up_read_non_owner(&rmn->lock);
+	if (atomic_dec_return(&amn->recursion) == 0)
+		up_read_non_owner(&amn->lock);
 }
 
 /**
@@ -202,15 +202,15 @@ static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
 						 unsigned long start,
 						 unsigned long end)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
 	struct interval_tree_node *it;
 
 	/* notification is exclusive, but interval is inclusive */
 	end -= 1;
 
-	amdgpu_mn_read_lock(rmn);
+	amdgpu_mn_read_lock(amn);
 
-	it = interval_tree_iter_first(&rmn->objects, start, end);
+	it = interval_tree_iter_first(&amn->objects, start, end);
 	while (it) {
 		struct amdgpu_mn_node *node;
 
@@ -238,15 +238,15 @@ static void amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
 						 unsigned long start,
 						 unsigned long end)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
 	struct interval_tree_node *it;
 
 	/* notification is exclusive, but interval is inclusive */
 	end -= 1;
 
-	amdgpu_mn_read_lock(rmn);
+	amdgpu_mn_read_lock(amn);
 
-	it = interval_tree_iter_first(&rmn->objects, start, end);
+	it = interval_tree_iter_first(&amn->objects, start, end);
 	while (it) {
 		struct amdgpu_mn_node *node;
 		struct amdgpu_bo *bo;
@@ -279,9 +279,9 @@ static void amdgpu_mn_invalidate_range_end(struct mmu_notifier *mn,
 					   unsigned long start,
 					   unsigned long end)
 {
-	struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
 
-	amdgpu_mn_read_unlock(rmn);
+	amdgpu_mn_read_unlock(amn);
 }
 
 static const struct mmu_notifier_ops amdgpu_mn_ops[] = {
@@ -315,7 +315,7 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
 				enum amdgpu_mn_type type)
 {
 	struct mm_struct *mm = current->mm;
-	struct amdgpu_mn *rmn;
+	struct amdgpu_mn *amn;
 	unsigned long key = AMDGPU_MN_KEY(mm, type);
 	int r;
 
@@ -325,41 +325,41 @@ struct amdgpu_mn *amdgpu_mn_get(struct amdgpu_device *adev,
 		return ERR_PTR(-EINTR);
 	}
 
-	hash_for_each_possible(adev->mn_hash, rmn, node, key)
-		if (AMDGPU_MN_KEY(rmn->mm, rmn->type) == key)
+	hash_for_each_possible(adev->mn_hash, amn, node, key)
+		if (AMDGPU_MN_KEY(amn->mm, amn->type) == key)
 			goto release_locks;
 
-	rmn = kzalloc(sizeof(*rmn), GFP_KERNEL);
-	if (!rmn) {
-		rmn = ERR_PTR(-ENOMEM);
+	amn = kzalloc(sizeof(*amn), GFP_KERNEL);
+	if (!amn) {
+		amn = ERR_PTR(-ENOMEM);
 		goto release_locks;
 	}
 
-	rmn->adev = adev;
-	rmn->mm = mm;
-	init_rwsem(&rmn->lock);
-	rmn->type = type;
-	rmn->mn.ops = &amdgpu_mn_ops[type];
-	rmn->objects = RB_ROOT_CACHED;
-	mutex_init(&rmn->read_lock);
-	atomic_set(&rmn->recursion, 0);
+	amn->adev = adev;
+	amn->mm = mm;
+	init_rwsem(&amn->lock);
+	amn->type = type;
+	amn->mn.ops = &amdgpu_mn_ops[type];
+	amn->objects = RB_ROOT_CACHED;
+	mutex_init(&amn->read_lock);
+	atomic_set(&amn->recursion, 0);
 
-	r = __mmu_notifier_register(&rmn->mn, mm);
+	r = __mmu_notifier_register(&amn->mn, mm);
 	if (r)
-		goto free_rmn;
+		goto free_amn;
 
-	hash_add(adev->mn_hash, &rmn->node, AMDGPU_MN_KEY(mm, type));
+	hash_add(adev->mn_hash, &amn->node, AMDGPU_MN_KEY(mm, type));
 
 release_locks:
 	up_write(&mm->mmap_sem);
 	mutex_unlock(&adev->mn_lock);
 
-	return rmn;
+	return amn;
 
-free_rmn:
+free_amn:
 	up_write(&mm->mmap_sem);
 	mutex_unlock(&adev->mn_lock);
-	kfree(rmn);
+	kfree(amn);
 
 	return ERR_PTR(r);
 }
@@ -379,14 +379,14 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	enum amdgpu_mn_type type =
 		bo->kfd_bo ? AMDGPU_MN_TYPE_HSA : AMDGPU_MN_TYPE_GFX;
-	struct amdgpu_mn *rmn;
+	struct amdgpu_mn *amn;
 	struct amdgpu_mn_node *node = NULL, *new_node;
 	struct list_head bos;
 	struct interval_tree_node *it;
 
-	rmn = amdgpu_mn_get(adev, type);
-	if (IS_ERR(rmn))
-		return PTR_ERR(rmn);
+	amn = amdgpu_mn_get(adev, type);
+	if (IS_ERR(amn))
+		return PTR_ERR(amn);
 
 	new_node = kmalloc(sizeof(*new_node), GFP_KERNEL);
 	if (!new_node)
@@ -394,12 +394,12 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 
 	INIT_LIST_HEAD(&bos);
 
-	down_write(&rmn->lock);
+	down_write(&amn->lock);
 
-	while ((it = interval_tree_iter_first(&rmn->objects, addr, end))) {
+	while ((it = interval_tree_iter_first(&amn->objects, addr, end))) {
 		kfree(node);
 		node = container_of(it, struct amdgpu_mn_node, it);
-		interval_tree_remove(&node->it, &rmn->objects);
+		interval_tree_remove(&node->it, &amn->objects);
 		addr = min(it->start, addr);
 		end = max(it->last, end);
 		list_splice(&node->bos, &bos);
@@ -410,7 +410,7 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 	else
 		kfree(new_node);
 
-	bo->mn = rmn;
+	bo->mn = amn;
 
 	node->it.start = addr;
 	node->it.last = end;
@@ -418,9 +418,9 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 	list_splice(&bos, &node->bos);
 	list_add(&bo->mn_list, &node->bos);
 
-	interval_tree_insert(&node->it, &rmn->objects);
+	interval_tree_insert(&node->it, &amn->objects);
 
-	up_write(&rmn->lock);
+	up_write(&amn->lock);
 
 	return 0;
 }
@@ -435,18 +435,18 @@ int amdgpu_mn_register(struct amdgpu_bo *bo, unsigned long addr)
 void amdgpu_mn_unregister(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
-	struct amdgpu_mn *rmn;
+	struct amdgpu_mn *amn;
 	struct list_head *head;
 
 	mutex_lock(&adev->mn_lock);
 
-	rmn = bo->mn;
-	if (rmn == NULL) {
+	amn = bo->mn;
+	if (amn == NULL) {
 		mutex_unlock(&adev->mn_lock);
 		return;
 	}
 
-	down_write(&rmn->lock);
+	down_write(&amn->lock);
 
 	/* save the next list entry for later */
 	head = bo->mn_list.next;
@@ -457,11 +457,11 @@ void amdgpu_mn_unregister(struct amdgpu_bo *bo)
 	if (list_empty(head)) {
 		struct amdgpu_mn_node *node;
 		node = container_of(head, struct amdgpu_mn_node, bos);
-		interval_tree_remove(&node->it, &rmn->objects);
+		interval_tree_remove(&node->it, &amn->objects);
 		kfree(node);
 	}
 
-	up_write(&rmn->lock);
+	up_write(&amn->lock);
 	mutex_unlock(&adev->mn_lock);
 }
 
-- 
cgit v1.2.3


From ad7f0b6334fe3cf52f2d79345791a4ef4547353f Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 5 Jun 2018 11:47:43 +0200
Subject: drm/amdgpu: fix documentation of amdgpu_mn.c v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

And wire it up as well.

v2: improve the wording, fix label mismatch

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst           |  9 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 74 ++++++++++++++++++++++++++--------
 2 files changed, 67 insertions(+), 16 deletions(-)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 1fbf3876a3d8..a4852f9a6141 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -35,3 +35,12 @@ PRIME Buffer Sharing
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
    :internal:
+
+MMU Notifier
+------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+   :doc: MMU Notifier
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+   :internal:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 37570a1c6db8..40fcb2af2914 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -28,6 +28,21 @@
  *    Christian König <christian.koenig@amd.com>
  */
 
+/**
+ * DOC: MMU Notifier
+ *
+ * For coherent userptr handling registers an MMU notifier to inform the driver
+ * about updates on the page tables of a process.
+ *
+ * When somebody tries to invalidate the page tables we block the update until
+ * all operations on the pages in question are completed, then those pages are
+ * marked as accessed and also dirty if it wasn't a read only access.
+ *
+ * New command submissions using the userptrs in question are delayed until all
+ * page table invalidation are completed and we once more see a coherent process
+ * address space.
+ */
+
 #include <linux/firmware.h>
 #include <linux/module.h>
 #include <linux/mmu_notifier.h>
@@ -38,6 +53,21 @@
 #include "amdgpu.h"
 #include "amdgpu_amdkfd.h"
 
+/**
+ * struct amdgpu_mn
+ *
+ * @adev: amdgpu device pointer
+ * @mm: process address space
+ * @mn: MMU notifier structur
+ * @work: destrution work item
+ * @node: hash table node to find structure by adev and mn
+ * @lock: rw semaphore protecting the notifier nodes
+ * @objects: interval tree containing amdgpu_mn_nodes
+ * @read_lock: mutex for recursive locking of @lock
+ * @recursion: depth of recursion
+ *
+ * Data for each amdgpu device and process address space.
+ */
 struct amdgpu_mn {
 	/* constant after initialisation */
 	struct amdgpu_device	*adev;
@@ -58,13 +88,21 @@ struct amdgpu_mn {
 	atomic_t		recursion;
 };
 
+/**
+ * struct amdgpu_mn_node
+ *
+ * @it: interval node defining start-last of the affected address range
+ * @bos: list of all BOs in the affected address range
+ *
+ * Manages all BOs which are affected of a certain range of address space.
+ */
 struct amdgpu_mn_node {
 	struct interval_tree_node	it;
 	struct list_head		bos;
 };
 
 /**
- * amdgpu_mn_destroy - destroy the amn
+ * amdgpu_mn_destroy - destroy the MMU notifier
  *
  * @work: previously sheduled work item
  *
@@ -98,7 +136,7 @@ static void amdgpu_mn_destroy(struct work_struct *work)
  * amdgpu_mn_release - callback to notify about mm destruction
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  *
  * Shedule a work item to lazy destroy our notifier.
  */
@@ -106,13 +144,16 @@ static void amdgpu_mn_release(struct mmu_notifier *mn,
 			      struct mm_struct *mm)
 {
 	struct amdgpu_mn *amn = container_of(mn, struct amdgpu_mn, mn);
+
 	INIT_WORK(&amn->work, amdgpu_mn_destroy);
 	schedule_work(&amn->work);
 }
 
 
 /**
- * amdgpu_mn_lock - take the write side lock for this mn
+ * amdgpu_mn_lock - take the write side lock for this notifier
+ *
+ * @mn: our notifier
  */
 void amdgpu_mn_lock(struct amdgpu_mn *mn)
 {
@@ -121,7 +162,9 @@ void amdgpu_mn_lock(struct amdgpu_mn *mn)
 }
 
 /**
- * amdgpu_mn_unlock - drop the write side lock for this mn
+ * amdgpu_mn_unlock - drop the write side lock for this notifier
+ *
+ * @mn: our notifier
  */
 void amdgpu_mn_unlock(struct amdgpu_mn *mn)
 {
@@ -130,11 +173,9 @@ void amdgpu_mn_unlock(struct amdgpu_mn *mn)
 }
 
 /**
- * amdgpu_mn_read_lock - take the amn read lock
+ * amdgpu_mn_read_lock - take the read side lock for this notifier
  *
  * @amn: our notifier
- *
- * Take the amn read side lock.
  */
 static void amdgpu_mn_read_lock(struct amdgpu_mn *amn)
 {
@@ -145,11 +186,9 @@ static void amdgpu_mn_read_lock(struct amdgpu_mn *amn)
 }
 
 /**
- * amdgpu_mn_read_unlock - drop the amn read lock
+ * amdgpu_mn_read_unlock - drop the read side lock for this notifier
  *
  * @amn: our notifier
- *
- * Drop the amn read side lock.
  */
 static void amdgpu_mn_read_unlock(struct amdgpu_mn *amn)
 {
@@ -161,9 +200,11 @@ static void amdgpu_mn_read_unlock(struct amdgpu_mn *amn)
  * amdgpu_mn_invalidate_node - unmap all BOs of a node
  *
  * @node: the node with the BOs to unmap
+ * @start: start of address range affected
+ * @end: end of address range affected
  *
- * We block for all BOs and unmap them by move them
- * into system domain again.
+ * Block for operations on BOs to finish and mark pages as accessed and
+ * potentially dirty.
  */
 static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
 				      unsigned long start,
@@ -190,12 +231,12 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
  * amdgpu_mn_invalidate_range_start_gfx - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  * @start: start of updated range
  * @end: end of updated range
  *
- * We block for all BOs between start and end to be idle and
- * unmap them by move them into system domain again.
+ * Block for operations on BOs to finish and mark pages as accessed and
+ * potentially dirty.
  */
 static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
 						 struct mm_struct *mm,
@@ -268,7 +309,7 @@ static void amdgpu_mn_invalidate_range_start_hsa(struct mmu_notifier *mn,
  * amdgpu_mn_invalidate_range_end - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  * @start: start of updated range
  * @end: end of updated range
  *
@@ -456,6 +497,7 @@ void amdgpu_mn_unregister(struct amdgpu_bo *bo)
 
 	if (list_empty(head)) {
 		struct amdgpu_mn_node *node;
+
 		node = container_of(head, struct amdgpu_mn_node, bos);
 		interval_tree_remove(&node->it, &amn->objects);
 		kfree(node);
-- 
cgit v1.2.3


From f4557923b5d3bd5aaa4177ea184c4389175cc92f Mon Sep 17 00:00:00 2001
From: Slava Abramov <slava.abramov@amd.com>
Date: Wed, 13 Jun 2018 10:50:31 -0400
Subject: drm/amdgpu: fix typo in amdgpu_mn.c comments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In doc comments for struct amdgpu_mn: destrution -> destruction

Signed-off-by: Slava Abramov <slava.abramov@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 40fcb2af2914..72a3e8c68876 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -59,7 +59,7 @@
  * @adev: amdgpu device pointer
  * @mm: process address space
  * @mn: MMU notifier structur
- * @work: destrution work item
+ * @work: destruction work item
  * @node: hash table node to find structure by adev and mn
  * @lock: rw semaphore protecting the notifier nodes
  * @objects: interval tree containing amdgpu_mn_nodes
-- 
cgit v1.2.3


From 7fc48e5912795caf78b1e2fb86d5f6ee02fbdb8c Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Mon, 11 Jun 2018 11:11:24 -0400
Subject: drm/amdgpu: Update function level documentation for GPUVM v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add/update function level documentation and add reference to amdgpu_vm.c
in amdgpu.rst

v2:
Fix reference in rst file.
Fix compilation warnings.
Add space between function names and params list where
it's missing.

v3:
Fix some funtion comments.
Add formatted documentation to structs.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst           |   9 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 253 ++++++++++++++++++++++++++++-----
 2 files changed, 224 insertions(+), 38 deletions(-)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index a4852f9a6141..3ffb2a226fae 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -44,3 +44,12 @@ MMU Notifier
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
    :internal:
+
+AMDGPU Virtual Memory
+---------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+   :doc: GPUVM
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+   :internal:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d88687b617e2..7f03f8c38708 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -34,8 +34,9 @@
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
 
-/*
- * GPUVM
+/**
+ * DOC: GPUVM
+ *
  * GPUVM is similar to the legacy gart on older asics, however
  * rather than there being a single global gart table
  * for the entire GPU, there are multiple VM page tables active
@@ -63,37 +64,84 @@ INTERVAL_TREE_DEFINE(struct amdgpu_bo_va_mapping, rb, uint64_t, __subtree_last,
 #undef START
 #undef LAST
 
-/* Local structure. Encapsulate some VM table update parameters to reduce
+/**
+ * struct amdgpu_pte_update_params - Local structure
+ *
+ * Encapsulate some VM table update parameters to reduce
  * the number of function parameters
+ *
  */
 struct amdgpu_pte_update_params {
-	/* amdgpu device we do this update for */
+
+	/**
+	 * @adev: amdgpu device we do this update for
+	 */
 	struct amdgpu_device *adev;
-	/* optional amdgpu_vm we do this update for */
+
+	/**
+	 * @vm: optional amdgpu_vm we do this update for
+	 */
 	struct amdgpu_vm *vm;
-	/* address where to copy page table entries from */
+
+	/**
+	 * @src: address where to copy page table entries from
+	 */
 	uint64_t src;
-	/* indirect buffer to fill with commands */
+
+	/**
+	 * @ib: indirect buffer to fill with commands
+	 */
 	struct amdgpu_ib *ib;
-	/* Function which actually does the update */
+
+	/**
+	 * @func: Function which actually does the update
+	 */
 	void (*func)(struct amdgpu_pte_update_params *params,
 		     struct amdgpu_bo *bo, uint64_t pe,
 		     uint64_t addr, unsigned count, uint32_t incr,
 		     uint64_t flags);
-	/* The next two are used during VM update by CPU
-	 *  DMA addresses to use for mapping
-	 *  Kernel pointer of PD/PT BO that needs to be updated
+	/**
+	 * @pages_addr:
+	 *
+	 * DMA addresses to use for mapping, used during VM update by CPU
 	 */
 	dma_addr_t *pages_addr;
+
+	/**
+	 * @kptr:
+	 *
+	 * Kernel pointer of PD/PT BO that needs to be updated,
+	 * used during VM update by CPU
+	 */
 	void *kptr;
 };
 
-/* Helper to disable partial resident texture feature from a fence callback */
+/**
+ * struct amdgpu_prt_cb - Helper to disable partial resident texture feature from a fence callback
+ */
 struct amdgpu_prt_cb {
+
+	/**
+	 * @adev: amdgpu device
+	 */
 	struct amdgpu_device *adev;
+
+	/**
+	 * @cb: callback
+	 */
 	struct dma_fence_cb cb;
 };
 
+/**
+ * amdgpu_vm_bo_base_init - Adds bo to the list of bos associated with the vm
+ *
+ * @base: base structure for tracking BO usage in a VM
+ * @vm: vm to which bo is to be added
+ * @bo: amdgpu buffer object
+ *
+ * Initialize a bo_va_base structure and add it to the appropriate lists
+ *
+ */
 static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 				   struct amdgpu_vm *vm,
 				   struct amdgpu_bo *bo)
@@ -126,8 +174,10 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
  * amdgpu_vm_level_shift - return the addr shift for each level
  *
  * @adev: amdgpu_device pointer
+ * @level: VMPT level
  *
- * Returns the number of bits the pfn needs to be right shifted for a level.
+ * Returns:
+ * The number of bits the pfn needs to be right shifted for a level.
  */
 static unsigned amdgpu_vm_level_shift(struct amdgpu_device *adev,
 				      unsigned level)
@@ -155,8 +205,10 @@ static unsigned amdgpu_vm_level_shift(struct amdgpu_device *adev,
  * amdgpu_vm_num_entries - return the number of entries in a PD/PT
  *
  * @adev: amdgpu_device pointer
+ * @level: VMPT level
  *
- * Calculate the number of entries in a page directory or page table.
+ * Returns:
+ * The number of entries in a page directory or page table.
  */
 static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
 				      unsigned level)
@@ -179,8 +231,10 @@ static unsigned amdgpu_vm_num_entries(struct amdgpu_device *adev,
  * amdgpu_vm_bo_size - returns the size of the BOs in bytes
  *
  * @adev: amdgpu_device pointer
+ * @level: VMPT level
  *
- * Calculate the size of the BO for a page directory or page table in bytes.
+ * Returns:
+ * The size of the BO for a page directory or page table in bytes.
  */
 static unsigned amdgpu_vm_bo_size(struct amdgpu_device *adev, unsigned level)
 {
@@ -218,6 +272,9 @@ void amdgpu_vm_get_pd_bo(struct amdgpu_vm *vm,
  * @param: parameter for the validation callback
  *
  * Validate the page table BOs on command submission if neccessary.
+ *
+ * Returns:
+ * Validation result.
  */
 int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			      int (*validate)(void *p, struct amdgpu_bo *bo),
@@ -273,6 +330,9 @@ int amdgpu_vm_validate_pt_bos(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  * @vm: VM to check
  *
  * Check if all VM PDs/PTs are ready for updates
+ *
+ * Returns:
+ * True if eviction list is empty.
  */
 bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 {
@@ -283,10 +343,14 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
  * amdgpu_vm_clear_bo - initially clear the PDs/PTs
  *
  * @adev: amdgpu_device pointer
+ * @vm: VM to clear BO from
  * @bo: BO to clear
  * @level: level this BO is at
  *
  * Root PD needs to be reserved when calling this.
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 			      struct amdgpu_vm *vm, struct amdgpu_bo *bo,
@@ -382,10 +446,16 @@ error:
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
+ * @parent: parent PT
  * @saddr: start of the address range
  * @eaddr: end of the address range
+ * @level: VMPT level
+ * @ats: indicate ATS support from PTE
  *
  * Make sure the page directories and page tables are allocated
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 				  struct amdgpu_vm *vm,
@@ -494,6 +564,9 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
  * @size: Size from start address we need.
  *
  * Make sure the page tables are allocated.
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 int amdgpu_vm_alloc_pts(struct amdgpu_device *adev,
 			struct amdgpu_vm *vm,
@@ -559,6 +632,15 @@ void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev)
 	}
 }
 
+/**
+ * amdgpu_vm_need_pipeline_sync - Check if pipe sync is needed for job.
+ *
+ * @ring: ring on which the job will be submitted
+ * @job: job to submit
+ *
+ * Returns:
+ * True if sync is needed.
+ */
 bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job)
 {
@@ -586,6 +668,14 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 	return vm_flush_needed || gds_switch_needed;
 }
 
+/**
+ * amdgpu_vm_is_large_bar - Check if BAR is large enough
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Returns:
+ * True if BAR is large enough.
+ */
 static bool amdgpu_vm_is_large_bar(struct amdgpu_device *adev)
 {
 	return (adev->gmc.real_vram_size == adev->gmc.visible_vram_size);
@@ -595,10 +685,12 @@ static bool amdgpu_vm_is_large_bar(struct amdgpu_device *adev)
  * amdgpu_vm_flush - hardware flush the vm
  *
  * @ring: ring to use for flush
- * @vmid: vmid number to use
- * @pd_addr: address of the page directory
+ * @need_pipe_sync: is pipe sync needed
  *
  * Emit a VM flush when it is necessary.
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
  */
 int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_pipe_sync)
 {
@@ -706,6 +798,9 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job, bool need_
  * Returns the found bo_va or NULL if none is found
  *
  * Object has to be reserved!
+ *
+ * Returns:
+ * Found bo_va or NULL.
  */
 struct amdgpu_bo_va *amdgpu_vm_bo_find(struct amdgpu_vm *vm,
 				       struct amdgpu_bo *bo)
@@ -787,7 +882,10 @@ static void amdgpu_vm_do_copy_ptes(struct amdgpu_pte_update_params *params,
  * @addr: the unmapped addr
  *
  * Look up the physical address of the page that the pte resolves
- * to and return the pointer for the page table entry.
+ * to.
+ *
+ * Returns:
+ * The pointer for the page table entry.
  */
 static uint64_t amdgpu_vm_map_gart(const dma_addr_t *pages_addr, uint64_t addr)
 {
@@ -840,6 +938,17 @@ static void amdgpu_vm_cpu_set_ptes(struct amdgpu_pte_update_params *params,
 	}
 }
 
+
+/**
+ * amdgpu_vm_wait_pd - Wait for PT BOs to be free.
+ *
+ * @adev: amdgpu_device pointer
+ * @vm: related vm
+ * @owner: fence owner
+ *
+ * Returns:
+ * 0 on success, errno otherwise.
+ */
 static int amdgpu_vm_wait_pd(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 			     void *owner)
 {
@@ -893,7 +1002,10 @@ static void amdgpu_vm_update_pde(struct amdgpu_pte_update_params *params,
 /*
  * amdgpu_vm_invalidate_level - mark all PD levels as invalid
  *
+ * @adev: amdgpu_device pointer
+ * @vm: related vm
  * @parent: parent PD
+ * @level: VMPT level
  *
  * Mark all PD level as invalid after an error.
  */
@@ -928,7 +1040,9 @@ static void amdgpu_vm_invalidate_level(struct amdgpu_device *adev,
  * @vm: requested vm
  *
  * Makes sure all directories are up to date.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  */
 int amdgpu_vm_update_directories(struct amdgpu_device *adev,
 				 struct amdgpu_vm *vm)
@@ -1115,14 +1229,15 @@ static void amdgpu_vm_handle_huge_pages(struct amdgpu_pte_update_params *p,
  * amdgpu_vm_update_ptes - make sure that page tables are valid
  *
  * @params: see amdgpu_pte_update_params definition
- * @vm: requested vm
  * @start: start of GPU address range
  * @end: end of GPU address range
  * @dst: destination address to map to, the next dst inside the function
  * @flags: mapping flags
  *
  * Update the page tables in the range @start - @end.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
 				  uint64_t start, uint64_t end,
@@ -1176,7 +1291,9 @@ static int amdgpu_vm_update_ptes(struct amdgpu_pte_update_params *params,
  * @end: last PTE to handle
  * @dst: addr those PTEs should point to
  * @flags: hw mapping flags
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params	*params,
 				uint64_t start, uint64_t end,
@@ -1248,7 +1365,9 @@ static int amdgpu_vm_frag_ptes(struct amdgpu_pte_update_params	*params,
  * @fence: optional resulting fence
  *
  * Fill in the page table entries between @start and @last.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 				       struct dma_fence *exclusive,
@@ -1403,7 +1522,9 @@ error_free:
  *
  * Split the mapping into smaller chunks so that each update fits
  * into a SDMA IB.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 				      struct dma_fence *exclusive,
@@ -1514,7 +1635,9 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
  * @clear: if true clear the entries
  *
  * Fill in the page table entries for @bo_va.
- * Returns 0 for success, -EINVAL for failure.
+ *
+ * Returns:
+ * 0 for success, -EINVAL for failure.
  */
 int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 			struct amdgpu_bo_va *bo_va,
@@ -1609,6 +1732,8 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 
 /**
  * amdgpu_vm_update_prt_state - update the global PRT state
+ *
+ * @adev: amdgpu_device pointer
  */
 static void amdgpu_vm_update_prt_state(struct amdgpu_device *adev)
 {
@@ -1623,6 +1748,8 @@ static void amdgpu_vm_update_prt_state(struct amdgpu_device *adev)
 
 /**
  * amdgpu_vm_prt_get - add a PRT user
+ *
+ * @adev: amdgpu_device pointer
  */
 static void amdgpu_vm_prt_get(struct amdgpu_device *adev)
 {
@@ -1635,6 +1762,8 @@ static void amdgpu_vm_prt_get(struct amdgpu_device *adev)
 
 /**
  * amdgpu_vm_prt_put - drop a PRT user
+ *
+ * @adev: amdgpu_device pointer
  */
 static void amdgpu_vm_prt_put(struct amdgpu_device *adev)
 {
@@ -1644,6 +1773,8 @@ static void amdgpu_vm_prt_put(struct amdgpu_device *adev)
 
 /**
  * amdgpu_vm_prt_cb - callback for updating the PRT status
+ *
+ * @fence: fence for the callback
  */
 static void amdgpu_vm_prt_cb(struct dma_fence *fence, struct dma_fence_cb *_cb)
 {
@@ -1655,6 +1786,9 @@ static void amdgpu_vm_prt_cb(struct dma_fence *fence, struct dma_fence_cb *_cb)
 
 /**
  * amdgpu_vm_add_prt_cb - add callback for updating the PRT status
+ *
+ * @adev: amdgpu_device pointer
+ * @fence: fence for the callback
  */
 static void amdgpu_vm_add_prt_cb(struct amdgpu_device *adev,
 				 struct dma_fence *fence)
@@ -1746,9 +1880,11 @@ static void amdgpu_vm_prt_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
  * or if an error occurred)
  *
  * Make sure all freed BOs are cleared in the PT.
- * Returns 0 for success.
- *
  * PTs have to be reserved and mutex must be locked!
+ *
+ * Returns:
+ * 0 for success.
+ *
  */
 int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
 			  struct amdgpu_vm *vm,
@@ -1793,10 +1929,11 @@ int amdgpu_vm_clear_freed(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device pointer
  * @vm: requested vm
- * @sync: sync object to add fences to
  *
  * Make sure all BOs which are moved are updated in the PTs.
- * Returns 0 for success.
+ *
+ * Returns:
+ * 0 for success.
  *
  * PTs have to be reserved!
  */
@@ -1851,7 +1988,9 @@ int amdgpu_vm_handle_moved(struct amdgpu_device *adev,
  *
  * Add @bo into the requested vm.
  * Add @bo to the list of bos associated with the vm
- * Returns newly added bo_va or NULL for failure
+ *
+ * Returns:
+ * Newly added bo_va or NULL for failure
  *
  * Object has to be reserved!
  */
@@ -1917,7 +2056,9 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
  * @flags: attributes of pages (read/write/valid/etc.)
  *
  * Add a mapping of the BO at the specefied addr into the VM.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  *
  * Object has to be reserved and unreserved outside!
  */
@@ -1979,7 +2120,9 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
  *
  * Add a mapping of the BO at the specefied addr into the VM. Replace existing
  * mappings as we do so.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  *
  * Object has to be reserved and unreserved outside!
  */
@@ -2036,7 +2179,9 @@ int amdgpu_vm_bo_replace_map(struct amdgpu_device *adev,
  * @saddr: where to the BO is mapped
  *
  * Remove a mapping of the BO at the specefied addr from the VM.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  *
  * Object has to be reserved and unreserved outside!
  */
@@ -2090,7 +2235,9 @@ int amdgpu_vm_bo_unmap(struct amdgpu_device *adev,
  * @size: size of the range
  *
  * Remove all mappings in a range, split them as appropriate.
- * Returns 0 for success, error for failure.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  */
 int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 				struct amdgpu_vm *vm,
@@ -2189,6 +2336,10 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
  * @vm: the requested VM
  *
  * Find a mapping by it's address.
+ *
+ * Returns:
+ * The amdgpu_bo_va_mapping matching for addr or NULL
+ *
  */
 struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
 							 uint64_t addr)
@@ -2240,7 +2391,6 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
  * amdgpu_vm_bo_invalidate - mark the bo as invalid
  *
  * @adev: amdgpu_device pointer
- * @vm: requested vm
  * @bo: amdgpu buffer object
  *
  * Mark @bo as invalid.
@@ -2281,6 +2431,14 @@ void amdgpu_vm_bo_invalidate(struct amdgpu_device *adev,
 	}
 }
 
+/**
+ * amdgpu_vm_get_block_size - calculate VM page table size as power of two
+ *
+ * @vm_size: VM size
+ *
+ * Returns:
+ * VM page table as power of two
+ */
 static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size)
 {
 	/* Total bits covered by PD + PTs */
@@ -2368,6 +2526,9 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
  * @vm_context: Indicates if it GFX or Compute context
  *
  * Init @vm fields.
+ *
+ * Returns:
+ * 0 for success, error for failure.
  */
 int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 		   int vm_context, unsigned int pasid)
@@ -2488,6 +2649,9 @@ error_free_sched_entity:
 /**
  * amdgpu_vm_make_compute - Turn a GFX VM into a compute VM
  *
+ * @adev: amdgpu_device pointer
+ * @vm: requested vm
+ *
  * This only works on GFX VMs that don't have any BOs added and no
  * page tables allocated yet.
  *
@@ -2500,7 +2664,8 @@ error_free_sched_entity:
  * setting. May leave behind an unused shadow BO for the page
  * directory when switching from SDMA updates to CPU updates.
  *
- * Returns 0 for success, -errno for errors.
+ * Returns:
+ * 0 for success, -errno for errors.
  */
 int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 {
@@ -2655,8 +2820,10 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
  * @adev: amdgpu_device pointer
  * @pasid: PASID do identify the VM
  *
- * This function is expected to be called in interrupt context. Returns
- * true if there was fault credit, false otherwise
+ * This function is expected to be called in interrupt context.
+ *
+ * Returns:
+ * True if there was fault credit, false otherwise
  */
 bool amdgpu_vm_pasid_fault_credit(struct amdgpu_device *adev,
 				  unsigned int pasid)
@@ -2740,6 +2907,16 @@ void amdgpu_vm_manager_fini(struct amdgpu_device *adev)
 	amdgpu_vmid_mgr_fini(adev);
 }
 
+/**
+ * amdgpu_vm_ioctl - Manages VMID reservation for vm hubs.
+ *
+ * @dev: drm device pointer
+ * @data: drm_amdgpu_vm
+ * @filp: drm file pointer
+ *
+ * Returns:
+ * 0 for success, -errno for errors.
+ */
 int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 {
 	union drm_amdgpu_vm *args = data;
-- 
cgit v1.2.3


From 923ff76eb035b0de3725edd7c13cda3b068ba197 Mon Sep 17 00:00:00 2001
From: Slava Abramov <slava.abramov@amd.com>
Date: Thu, 7 Jun 2018 17:27:07 -0400
Subject: drm/amdgpu: update documentation for amdgpu_irq.c v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add/update function level documentation and add reference to amdgpu_irq.c
in amdgpu.rst

v2:
Added DOC comment
Added more explanations for amdgpu_hotplug_work_func
Properly formatted unused parameters
Properly formatted return values
Fixed usage of acronyms
More consistent styling

v3:
Removed duplicate "not"
Using '&' to refer to functions and types

Signed-off-by: Slava Abramov <slava.abramov@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst            |   8 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c | 202 ++++++++++++++++++++++----------
 2 files changed, 147 insertions(+), 63 deletions(-)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 3ffb2a226fae..abf87360ab15 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -52,4 +52,12 @@ AMDGPU Virtual Memory
    :doc: GPUVM
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+
+Interrupt Handling
+------------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+   :doc: Interrupt Handling
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
    :internal:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
index 3a5ca462abf0..1abf5b5bac9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -25,6 +25,23 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+
+/**
+ * DOC: Interrupt Handling
+ *
+ * Interrupts generated within GPU hardware raise interrupt requests that are
+ * passed to amdgpu IRQ handler which is responsible for detecting source and
+ * type of the interrupt and dispatching matching handlers. If handling an
+ * interrupt requires calling kernel functions that may sleep processing is
+ * dispatched to work handlers.
+ *
+ * If MSI functionality is not disabled by module parameter then MSI
+ * support will be enabled.
+ *
+ * For GPU interrupt sources that may be driven by another driver, IRQ domain
+ * support is used (with mapping between virtual and hardware IRQs).
+ */
+
 #include <linux/irq.h>
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
@@ -43,19 +60,21 @@
 
 #define AMDGPU_WAIT_IDLE_TIMEOUT 200
 
-/*
- * Handle hotplug events outside the interrupt handler proper.
- */
 /**
- * amdgpu_hotplug_work_func - display hotplug work handler
+ * amdgpu_hotplug_work_func - work handler for display hotplug event
  *
- * @work: work struct
+ * @work: work struct pointer
  *
- * This is the hot plug event work handler (all asics).
- * The work gets scheduled from the irq handler if there
- * was a hot plug interrupt.  It walks the connector table
- * and calls the hotplug handler for each one, then sends
- * a drm hotplug event to alert userspace.
+ * This is the hotplug event work handler (all ASICs).
+ * The work gets scheduled from the IRQ handler if there
+ * was a hotplug interrupt.  It walks through the connector table
+ * and calls hotplug handler for each connector. After this, it sends
+ * a DRM hotplug event to alert userspace.
+ *
+ * This design approach is required in order to defer hotplug event handling
+ * from the IRQ handler to a work handler because hotplug handler has to use
+ * mutexes which cannot be locked in an IRQ handler (since &mutex_lock may
+ * sleep).
  */
 static void amdgpu_hotplug_work_func(struct work_struct *work)
 {
@@ -74,13 +93,12 @@ static void amdgpu_hotplug_work_func(struct work_struct *work)
 }
 
 /**
- * amdgpu_irq_reset_work_func - execute gpu reset
+ * amdgpu_irq_reset_work_func - execute GPU reset
  *
- * @work: work struct
+ * @work: work struct pointer
  *
- * Execute scheduled gpu reset (cayman+).
- * This function is called when the irq handler
- * thinks we need a gpu reset.
+ * Execute scheduled GPU reset (Cayman+).
+ * This function is called when the IRQ handler thinks we need a GPU reset.
  */
 static void amdgpu_irq_reset_work_func(struct work_struct *work)
 {
@@ -91,7 +109,13 @@ static void amdgpu_irq_reset_work_func(struct work_struct *work)
 		amdgpu_device_gpu_recover(adev, NULL, false);
 }
 
-/* Disable *all* interrupts */
+/**
+ * amdgpu_irq_disable_all - disable *all* interrupts
+ *
+ * @adev: amdgpu device pointer
+ *
+ * Disable all types of interrupts from all sources.
+ */
 void amdgpu_irq_disable_all(struct amdgpu_device *adev)
 {
 	unsigned long irqflags;
@@ -123,11 +147,15 @@ void amdgpu_irq_disable_all(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_handler - irq handler
+ * amdgpu_irq_handler - IRQ handler
+ *
+ * @irq: IRQ number (unused)
+ * @arg: pointer to DRM device
  *
- * @int irq, void *arg: args
+ * IRQ handler for amdgpu driver (all ASICs).
  *
- * This is the irq handler for the amdgpu driver (all asics).
+ * Returns:
+ * result of handling the IRQ, as defined by &irqreturn_t
  */
 irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 {
@@ -142,18 +170,18 @@ irqreturn_t amdgpu_irq_handler(int irq, void *arg)
 }
 
 /**
- * amdgpu_msi_ok - asic specific msi checks
+ * amdgpu_msi_ok - check whether MSI functionality is enabled
  *
- * @adev: amdgpu device pointer
+ * @adev: amdgpu device pointer (unused)
+ *
+ * Checks whether MSI functionality has been disabled via module parameter
+ * (all ASICs).
  *
- * Handles asic specific MSI checks to determine if
- * MSIs should be enabled on a particular chip (all asics).
- * Returns true if MSIs should be enabled, false if MSIs
- * should not be enabled.
+ * Returns:
+ * *true* if MSIs are allowed to be enabled or *false* otherwise
  */
 static bool amdgpu_msi_ok(struct amdgpu_device *adev)
 {
-	/* force MSI on */
 	if (amdgpu_msi == 1)
 		return true;
 	else if (amdgpu_msi == 0)
@@ -163,12 +191,15 @@ static bool amdgpu_msi_ok(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_init - init driver interrupt info
+ * amdgpu_irq_init - initialize interrupt handling
  *
  * @adev: amdgpu device pointer
  *
- * Sets up the work irq handlers, vblank init, MSIs, etc. (all asics).
- * Returns 0 for success, error for failure.
+ * Sets up work functions for hotplug and reset interrupts, enables MSI
+ * functionality, initializes vblank, hotplug and reset interrupt handling.
+ *
+ * Returns:
+ * 0 on success or error code on failure
  */
 int amdgpu_irq_init(struct amdgpu_device *adev)
 {
@@ -176,7 +207,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 
 	spin_lock_init(&adev->irq.lock);
 
-	/* enable msi */
+	/* Enable MSI if not disabled by module parameter */
 	adev->irq.msi_enabled = false;
 
 	if (amdgpu_msi_ok(adev)) {
@@ -189,7 +220,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 
 	if (!amdgpu_device_has_dc_support(adev)) {
 		if (!adev->enable_virtual_display)
-			/* Disable vblank irqs aggressively for power-saving */
+			/* Disable vblank IRQs aggressively for power-saving */
 			/* XXX: can this be enabled for DC? */
 			adev->ddev->vblank_disable_immediate = true;
 
@@ -197,7 +228,7 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 		if (r)
 			return r;
 
-		/* pre DCE11 */
+		/* Pre-DCE11 */
 		INIT_WORK(&adev->hotplug_work,
 				amdgpu_hotplug_work_func);
 	}
@@ -220,11 +251,13 @@ int amdgpu_irq_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_fini - tear down driver interrupt info
+ * amdgpu_irq_fini - shut down interrupt handling
  *
  * @adev: amdgpu device pointer
  *
- * Tears down the work irq handlers, vblank handlers, MSIs, etc. (all asics).
+ * Tears down work functions for hotplug and reset interrupts, disables MSI
+ * functionality, shuts down vblank, hotplug and reset interrupt handling,
+ * turns off interrupts from all sources (all ASICs).
  */
 void amdgpu_irq_fini(struct amdgpu_device *adev)
 {
@@ -264,12 +297,17 @@ void amdgpu_irq_fini(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_add_id - register irq source
+ * amdgpu_irq_add_id - register IRQ source
  *
  * @adev: amdgpu device pointer
- * @src_id: source id for this source
- * @source: irq source
+ * @client_id: client id
+ * @src_id: source id
+ * @source: IRQ source pointer
+ *
+ * Registers IRQ source on a client.
  *
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_add_id(struct amdgpu_device *adev,
 		      unsigned client_id, unsigned src_id,
@@ -312,12 +350,12 @@ int amdgpu_irq_add_id(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_irq_dispatch - dispatch irq to IP blocks
+ * amdgpu_irq_dispatch - dispatch IRQ to IP blocks
  *
  * @adev: amdgpu device pointer
- * @entry: interrupt vector
+ * @entry: interrupt vector pointer
  *
- * Dispatches the irq to the different IP blocks
+ * Dispatches IRQ to IP blocks.
  */
 void amdgpu_irq_dispatch(struct amdgpu_device *adev,
 			 struct amdgpu_iv_entry *entry)
@@ -361,13 +399,13 @@ void amdgpu_irq_dispatch(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_irq_update - update hw interrupt state
+ * amdgpu_irq_update - update hardware interrupt state
  *
  * @adev: amdgpu device pointer
- * @src: interrupt src you want to enable
- * @type: type of interrupt you want to update
+ * @src: interrupt source pointer
+ * @type: type of interrupt
  *
- * Updates the interrupt state for a specific src (all asics).
+ * Updates interrupt state for the specific source (all ASICs).
  */
 int amdgpu_irq_update(struct amdgpu_device *adev,
 			     struct amdgpu_irq_src *src, unsigned type)
@@ -378,7 +416,7 @@ int amdgpu_irq_update(struct amdgpu_device *adev,
 
 	spin_lock_irqsave(&adev->irq.lock, irqflags);
 
-	/* we need to determine after taking the lock, otherwise
+	/* We need to determine after taking the lock, otherwise
 	   we might disable just enabled interrupts again */
 	if (amdgpu_irq_enabled(adev, src, type))
 		state = AMDGPU_IRQ_STATE_ENABLE;
@@ -390,6 +428,14 @@ int amdgpu_irq_update(struct amdgpu_device *adev,
 	return r;
 }
 
+/**
+ * amdgpu_irq_gpu_reset_resume_helper - update interrupt states on all sources
+ *
+ * @adev: amdgpu device pointer
+ *
+ * Updates state of all types of interrupts on all sources on resume after
+ * reset.
+ */
 void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
 {
 	int i, j, k;
@@ -413,10 +459,13 @@ void amdgpu_irq_gpu_reset_resume_helper(struct amdgpu_device *adev)
  * amdgpu_irq_get - enable interrupt
  *
  * @adev: amdgpu device pointer
- * @src: interrupt src you want to enable
- * @type: type of interrupt you want to enable
+ * @src: interrupt source pointer
+ * @type: type of interrupt
  *
- * Enables the interrupt type for a specific src (all asics).
+ * Enables specified type of interrupt on the specified source (all ASICs).
+ *
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
@@ -440,10 +489,13 @@ int amdgpu_irq_get(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
  * amdgpu_irq_put - disable interrupt
  *
  * @adev: amdgpu device pointer
- * @src: interrupt src you want to disable
- * @type: type of interrupt you want to disable
+ * @src: interrupt source pointer
+ * @type: type of interrupt
+ *
+ * Enables specified type of interrupt on the specified source (all ASICs).
  *
- * Disables the interrupt type for a specific src (all asics).
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 		   unsigned type)
@@ -464,12 +516,17 @@ int amdgpu_irq_put(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 }
 
 /**
- * amdgpu_irq_enabled - test if irq is enabled or not
+ * amdgpu_irq_enabled - check whether interrupt is enabled or not
  *
  * @adev: amdgpu device pointer
- * @idx: interrupt src you want to test
+ * @src: interrupt source pointer
+ * @type: type of interrupt
  *
- * Tests if the given interrupt source is enabled or not
+ * Checks whether the given type of interrupt is enabled on the given source.
+ *
+ * Returns:
+ * *true* if interrupt is enabled, *false* if interrupt is disabled or on
+ * invalid parameters
  */
 bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 			unsigned type)
@@ -486,7 +543,7 @@ bool amdgpu_irq_enabled(struct amdgpu_device *adev, struct amdgpu_irq_src *src,
 	return !!atomic_read(&src->enabled_types[type]);
 }
 
-/* gen irq */
+/* XXX: Generic IRQ handling */
 static void amdgpu_irq_mask(struct irq_data *irqd)
 {
 	/* XXX */
@@ -497,12 +554,26 @@ static void amdgpu_irq_unmask(struct irq_data *irqd)
 	/* XXX */
 }
 
+/* amdgpu hardware interrupt chip descriptor */
 static struct irq_chip amdgpu_irq_chip = {
 	.name = "amdgpu-ih",
 	.irq_mask = amdgpu_irq_mask,
 	.irq_unmask = amdgpu_irq_unmask,
 };
 
+/**
+ * amdgpu_irqdomain_map - create mapping between virtual and hardware IRQ numbers
+ *
+ * @d: amdgpu IRQ domain pointer (unused)
+ * @irq: virtual IRQ number
+ * @hwirq: hardware irq number
+ *
+ * Current implementation assigns simple interrupt handler to the given virtual
+ * IRQ.
+ *
+ * Returns:
+ * 0 on success or error code otherwise
+ */
 static int amdgpu_irqdomain_map(struct irq_domain *d,
 				unsigned int irq, irq_hw_number_t hwirq)
 {
@@ -514,17 +585,21 @@ static int amdgpu_irqdomain_map(struct irq_domain *d,
 	return 0;
 }
 
+/* Implementation of methods for amdgpu IRQ domain */
 static const struct irq_domain_ops amdgpu_hw_irqdomain_ops = {
 	.map = amdgpu_irqdomain_map,
 };
 
 /**
- * amdgpu_irq_add_domain - create a linear irq domain
+ * amdgpu_irq_add_domain - create a linear IRQ domain
  *
  * @adev: amdgpu device pointer
  *
- * Create an irq domain for GPU interrupt sources
+ * Creates an IRQ domain for GPU interrupt sources
  * that may be driven by another driver (e.g., ACP).
+ *
+ * Returns:
+ * 0 on success or error code otherwise
  */
 int amdgpu_irq_add_domain(struct amdgpu_device *adev)
 {
@@ -539,11 +614,11 @@ int amdgpu_irq_add_domain(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_remove_domain - remove the irq domain
+ * amdgpu_irq_remove_domain - remove the IRQ domain
  *
  * @adev: amdgpu device pointer
  *
- * Remove the irq domain for GPU interrupt sources
+ * Removes the IRQ domain for GPU interrupt sources
  * that may be driven by another driver (e.g., ACP).
  */
 void amdgpu_irq_remove_domain(struct amdgpu_device *adev)
@@ -555,16 +630,17 @@ void amdgpu_irq_remove_domain(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_irq_create_mapping - create a mapping between a domain irq and a
- *                             Linux irq
+ * amdgpu_irq_create_mapping - create mapping between domain Linux IRQs
  *
  * @adev: amdgpu device pointer
  * @src_id: IH source id
  *
- * Create a mapping between a domain irq (GPU IH src id) and a Linux irq
+ * Creates mapping between a domain IRQ (GPU IH src id) and a Linux IRQ
  * Use this for components that generate a GPU interrupt, but are driven
  * by a different driver (e.g., ACP).
- * Returns the Linux irq.
+ *
+ * Returns:
+ * Linux IRQ
  */
 unsigned amdgpu_irq_create_mapping(struct amdgpu_device *adev, unsigned src_id)
 {
-- 
cgit v1.2.3


From c8c5e569c5b0c9ad523c35497af2ae5788a29581 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Tue, 12 Jun 2018 14:28:20 -0400
Subject: drm/amdgpu: Consolidate visible vs. real vram check v2.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move all instnaces of this check into a function in amdgpu_gmc.h
Rename the original function to a more proper name.

v2:
Add more places to cleanup.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c     | 11 ++++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h    | 15 +++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c     | 20 ++++----------------
 5 files changed, 27 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 82312a7bc6ad..7a625f3989a0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -31,6 +31,7 @@
 #include <drm/drm_syncobj.h>
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
+#include "amdgpu_gmc.h"
 
 static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 				      struct drm_amdgpu_cs_chunk_fence *data,
@@ -302,7 +303,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 	*max_bytes = us_to_bytes(adev, adev->mm_stats.accum_us);
 
 	/* Do the same for visible VRAM if half of it is free */
-	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size) {
+	if (!amdgpu_gmc_vram_full_visible(&adev->gmc)) {
 		u64 total_vis_vram = adev->gmc.visible_vram_size;
 		u64 used_vis_vram =
 			amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
@@ -359,7 +360,7 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 	 * to move it. Don't move anything if the threshold is zero.
 	 */
 	if (p->bytes_moved < p->bytes_moved_threshold) {
-		if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+		if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 		    (bo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED)) {
 			/* And don't move a CPU_ACCESS_REQUIRED BO to limited
 			 * visible VRAM if we've depleted our allowance to do
@@ -381,7 +382,7 @@ retry:
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 
 	p->bytes_moved += ctx.bytes_moved;
-	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 	    amdgpu_bo_in_cpu_visible_vram(bo))
 		p->bytes_moved_vis += ctx.bytes_moved;
 
@@ -434,8 +435,8 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 
 		/* Good we can try to move this BO somewhere else */
 		update_bytes_moved_vis =
-			adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
-			amdgpu_bo_in_cpu_visible_vram(bo);
+				!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
+				amdgpu_bo_in_cpu_visible_vram(bo);
 		amdgpu_ttm_placement_from_domain(bo, other);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		p->bytes_moved += ctx.bytes_moved;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 893c2490b783..6cb4948233cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -109,4 +109,19 @@ struct amdgpu_gmc {
 	const struct amdgpu_gmc_funcs	*gmc_funcs;
 };
 
+/**
+ * amdgpu_gmc_vram_full_visible - Check if full VRAM is visible through the BAR
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Returns:
+ * True if full VRAM is visible through the BAR
+ */
+static inline bool amdgpu_gmc_vram_full_visible(struct amdgpu_gmc *gmc)
+{
+	WARN_ON(gmc->real_vram_size < gmc->visible_vram_size);
+
+	return (gmc->real_vram_size == gmc->visible_vram_size);
+}
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 987a9fa33d35..f5b0b180a6cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -463,7 +463,7 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 	if (unlikely(r != 0))
 		return r;
 
-	if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+	if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 	    bo->tbo.mem.mem_type == TTM_PL_VRAM &&
 	    bo->tbo.mem.start < adev->gmc.visible_vram_size >> PAGE_SHIFT)
 		amdgpu_cs_report_moved_bytes(adev, ctx.bytes_moved,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index e93a0a237dc3..0c084d3d0865 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -277,7 +277,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 		if (!adev->mman.buffer_funcs_enabled) {
 			/* Move to system memory */
 			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
-		} else if (adev->gmc.visible_vram_size < adev->gmc.real_vram_size &&
+		} else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
 			   amdgpu_bo_in_cpu_visible_vram(abo)) {
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 7f03f8c38708..6d2294203bd7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -33,6 +33,7 @@
 #include "amdgpu.h"
 #include "amdgpu_trace.h"
 #include "amdgpu_amdkfd.h"
+#include "amdgpu_gmc.h"
 
 /**
  * DOC: GPUVM
@@ -668,19 +669,6 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 	return vm_flush_needed || gds_switch_needed;
 }
 
-/**
- * amdgpu_vm_is_large_bar - Check if BAR is large enough
- *
- * @adev: amdgpu_device pointer
- *
- * Returns:
- * True if BAR is large enough.
- */
-static bool amdgpu_vm_is_large_bar(struct amdgpu_device *adev)
-{
-	return (adev->gmc.real_vram_size == adev->gmc.visible_vram_size);
-}
-
 /**
  * amdgpu_vm_flush - hardware flush the vm
  *
@@ -2579,7 +2567,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	}
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_vm_is_large_bar(adev)),
+	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 	vm->last_update = NULL;
 
@@ -2699,7 +2687,7 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 	vm->pte_support_ats = pte_support_ats;
 	DRM_DEBUG_DRIVER("VM update mode is %s\n",
 			 vm->use_cpu_for_update ? "CPU" : "SDMA");
-	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_vm_is_large_bar(adev)),
+	WARN_ONCE((vm->use_cpu_for_update & !amdgpu_gmc_vram_full_visible(&adev->gmc)),
 		  "CPU update of VM recommended only for large BAR system\n");
 
 	if (vm->pasid) {
@@ -2877,7 +2865,7 @@ void amdgpu_vm_manager_init(struct amdgpu_device *adev)
 	 */
 #ifdef CONFIG_X86_64
 	if (amdgpu_vm_update_mode == -1) {
-		if (amdgpu_vm_is_large_bar(adev))
+		if (amdgpu_gmc_vram_full_visible(&adev->gmc))
 			adev->vm_manager.vm_update_mode =
 				AMDGPU_VM_USE_CPU_FOR_COMPUTE;
 		else
-- 
cgit v1.2.3


From dc85db256d47062955145264df5923f03b85b0c6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 1 Jun 2018 12:28:14 -0500
Subject: drm/doc: Add amdgpu hwmon/power documentation (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the hwmon and power control interfaces exposed
by the amdgpu driver.

v2: use section rather than chapter for now

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst           | 53 ++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 45 ++++++++++++++++++++++++-----
 2 files changed, 90 insertions(+), 8 deletions(-)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index abf87360ab15..e1656fe8f247 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -61,3 +61,56 @@ Interrupt Handling
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
    :internal:
+
+GPU Power/Thermal Controls and Monitoring
+=========================================
+
+This section covers hwmon and power/thermal controls.
+
+HWMON Interfaces
+----------------
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: hwmon
+
+GPU sysfs Power State Interfaces
+--------------------------------
+
+GPU power controls are exposed via sysfs files.
+
+power_dpm_state
+~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: power_dpm_state
+
+power_dpm_force_performance_level
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: power_dpm_force_performance_level
+
+pp_table
+~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: pp_table
+
+pp_od_clk_voltage
+~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: pp_od_clk_voltage
+
+pp_dpm_sclk pp_dpm_mclk pp_dpm_pcie
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: pp_dpm_sclk pp_dpm_mclk pp_dpm_pcie
+
+pp_power_profile_mode
+~~~~~~~~~~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: pp_power_profile_mode
+
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index b455da487782..f667cb9eb614 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -80,12 +80,15 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
 /**
  * DOC: power_dpm_state
  *
- * This is a legacy interface and is only provided for backwards compatibility.
- * The amdgpu driver provides a sysfs API for adjusting certain power
- * related parameters.  The file power_dpm_state is used for this.
+ * The power_dpm_state file is a legacy interface and is only provided for
+ * backwards compatibility. The amdgpu driver provides a sysfs API for adjusting
+ * certain power related parameters.  The file power_dpm_state is used for this.
  * It accepts the following arguments:
+ *
  * - battery
+ *
  * - balanced
+ *
  * - performance
  *
  * battery
@@ -169,14 +172,21 @@ fail:
  * The amdgpu driver provides a sysfs API for adjusting certain power
  * related parameters.  The file power_dpm_force_performance_level is
  * used for this.  It accepts the following arguments:
+ *
  * - auto
+ *
  * - low
+ *
  * - high
+ *
  * - manual
- * - GPU fan
+ *
  * - profile_standard
+ *
  * - profile_min_sclk
+ *
  * - profile_min_mclk
+ *
  * - profile_peak
  *
  * auto
@@ -463,8 +473,11 @@ static ssize_t amdgpu_set_pp_table(struct device *dev,
  * this.
  *
  * Reading the file will display:
+ *
  * - a list of engine clock levels and voltages labeled OD_SCLK
+ *
  * - a list of memory clock levels and voltages labeled OD_MCLK
+ *
  * - a list of valid ranges for sclk, mclk, and voltage labeled OD_RANGE
  *
  * To manually adjust these settings, first select manual using
@@ -1285,35 +1298,51 @@ static ssize_t amdgpu_hwmon_set_power_cap(struct device *dev,
  * DOC: hwmon
  *
  * The amdgpu driver exposes the following sensor interfaces:
+ *
  * - GPU temperature (via the on-die sensor)
+ *
  * - GPU voltage
+ *
  * - Northbridge voltage (APUs only)
+ *
  * - GPU power
+ *
  * - GPU fan
  *
  * hwmon interfaces for GPU temperature:
+ *
  * - temp1_input: the on die GPU temperature in millidegrees Celsius
+ *
  * - temp1_crit: temperature critical max value in millidegrees Celsius
+ *
  * - temp1_crit_hyst: temperature hysteresis for critical limit in millidegrees Celsius
  *
  * hwmon interfaces for GPU voltage:
+ *
  * - in0_input: the voltage on the GPU in millivolts
+ *
  * - in1_input: the voltage on the Northbridge in millivolts
  *
  * hwmon interfaces for GPU power:
+ *
  * - power1_average: average power used by the GPU in microWatts
+ *
  * - power1_cap_min: minimum cap supported in microWatts
+ *
  * - power1_cap_max: maximum cap supported in microWatts
+ *
  * - power1_cap: selected power cap in microWatts
  *
  * hwmon interfaces for GPU fan:
+ *
  * - pwm1: pulse width modulation fan level (0-255)
- * - pwm1_enable: pulse width modulation fan control method
- *                0: no fan speed control
- *                1: manual fan speed control using pwm interface
- *                2: automatic fan speed control
+ *
+ * - pwm1_enable: pulse width modulation fan control method (0: no fan speed control, 1: manual fan speed control using pwm interface, 2: automatic fan speed control)
+ *
  * - pwm1_min: pulse width modulation fan control minimum level (0)
+ *
  * - pwm1_max: pulse width modulation fan control maximum level (255)
+ *
  * - fan1_input: fan speed in RPM
  *
  * You can use hwmon tools like sensors to view this information on your system.
-- 
cgit v1.2.3


From c5792d7776e61737af200bf6f0d15354b5a3d205 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Mon, 4 Jun 2018 13:33:14 +0800
Subject: drm/amd/pp: Remove SAMU support in powerplay

As the SAMU ip was not supported in linux,
so delete the SAMU support in powerplay on
asics Bonarire/Hawwii/Tonga/Fiji/Polaris/vegam.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/powerplay/hwmgr/smu7_clockpowergating.c    | 54 --------------
 .../amd/powerplay/hwmgr/smu7_clockpowergating.h    |  1 -
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c   |  1 -
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h   |  1 -
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h |  1 -
 drivers/gpu/drm/amd/powerplay/inc/smumgr.h         |  2 -
 drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c   | 35 ---------
 drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c | 74 -------------------
 .../gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c  | 10 ---
 .../drm/amd/powerplay/smumgr/polaris10_smumgr.c    | 86 ----------------------
 .../gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c    | 80 --------------------
 .../gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c    | 85 ---------------------
 12 files changed, 430 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index 6d72a5600917..41495621d94a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -39,13 +39,6 @@ static int smu7_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable)
 			PPSMC_MSG_VCEDPM_Disable);
 }
 
-static int smu7_enable_disable_samu_dpm(struct pp_hwmgr *hwmgr, bool enable)
-{
-	return smum_send_msg_to_smc(hwmgr, enable ?
-			PPSMC_MSG_SAMUDPM_Enable :
-			PPSMC_MSG_SAMUDPM_Disable);
-}
-
 static int smu7_update_uvd_dpm(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	if (!bgate)
@@ -60,13 +53,6 @@ static int smu7_update_vce_dpm(struct pp_hwmgr *hwmgr, bool bgate)
 	return smu7_enable_disable_vce_dpm(hwmgr, !bgate);
 }
 
-static int smu7_update_samu_dpm(struct pp_hwmgr *hwmgr, bool bgate)
-{
-	if (!bgate)
-		smum_update_smc_table(hwmgr, SMU_SAMU_TABLE);
-	return smu7_enable_disable_samu_dpm(hwmgr, !bgate);
-}
-
 int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr)
 {
 	if (phm_cf_want_uvd_power_gating(hwmgr))
@@ -107,35 +93,15 @@ static int smu7_powerup_vce(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int smu7_powerdown_samu(struct pp_hwmgr *hwmgr)
-{
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_SamuPowerGating))
-		return smum_send_msg_to_smc(hwmgr,
-				PPSMC_MSG_SAMPowerOFF);
-	return 0;
-}
-
-static int smu7_powerup_samu(struct pp_hwmgr *hwmgr)
-{
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_SamuPowerGating))
-		return smum_send_msg_to_smc(hwmgr,
-				PPSMC_MSG_SAMPowerON);
-	return 0;
-}
-
 int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
 
 	data->uvd_power_gated = false;
 	data->vce_power_gated = false;
-	data->samu_power_gated = false;
 
 	smu7_powerup_uvd(hwmgr);
 	smu7_powerup_vce(hwmgr);
-	smu7_powerup_samu(hwmgr);
 
 	return 0;
 }
@@ -195,26 +161,6 @@ void smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 	}
 }
 
-int smu7_powergate_samu(struct pp_hwmgr *hwmgr, bool bgate)
-{
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-
-	if (data->samu_power_gated == bgate)
-		return 0;
-
-	data->samu_power_gated = bgate;
-
-	if (bgate) {
-		smu7_update_samu_dpm(hwmgr, true);
-		smu7_powerdown_samu(hwmgr);
-	} else {
-		smu7_powerup_samu(hwmgr);
-		smu7_update_samu_dpm(hwmgr, false);
-	}
-
-	return 0;
-}
-
 int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
 					const uint32_t *msg_id)
 {
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
index 1ddce023218a..be7f66d2b234 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
@@ -29,7 +29,6 @@
 void smu7_powergate_vce(struct pp_hwmgr *hwmgr, bool bgate);
 void smu7_powergate_uvd(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_powerdown_uvd(struct pp_hwmgr *hwmgr);
-int smu7_powergate_samu(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_powergate_acp(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr);
 int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index fdb20db9c147..24d20d9c74b4 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -4300,7 +4300,6 @@ static int smu7_init_power_gate_state(struct pp_hwmgr *hwmgr)
 
 	data->uvd_power_gated = false;
 	data->vce_power_gated = false;
-	data->samu_power_gated = false;
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
index c91e75db6a8e..3784ce6e50ab 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.h
@@ -310,7 +310,6 @@ struct smu7_hwmgr {
 	/* ---- Power Gating States ---- */
 	bool                           uvd_power_gated;
 	bool                           vce_power_gated;
-	bool                           samu_power_gated;
 	bool                           need_long_memory_training;
 
 	/* Application power optimization parameters */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
index aadd6cbc7e85..339820da9e6a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.h
@@ -370,7 +370,6 @@ struct vega10_hwmgr {
 	/* ---- Power Gating States ---- */
 	bool                           uvd_power_gated;
 	bool                           vce_power_gated;
-	bool                           samu_power_gated;
 	bool                           need_long_memory_training;
 
 	/* Internal settings to apply the application power optimization parameters */
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
index 6c22ed9249bf..89dfbf53c7e6 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
@@ -29,7 +29,6 @@
 enum SMU_TABLE {
 	SMU_UVD_TABLE = 0,
 	SMU_VCE_TABLE,
-	SMU_SAMU_TABLE,
 	SMU_BIF_TABLE,
 };
 
@@ -47,7 +46,6 @@ enum SMU_MEMBER {
 	UcodeLoadStatus,
 	UvdBootLevel,
 	VceBootLevel,
-	SamuBootLevel,
 	LowSclkInterruptThreshold,
 	DRAM_LOG_ADDR_H,
 	DRAM_LOG_ADDR_L,
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 2d4ec8ac3a08..8cd21ac6ceda 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -1614,37 +1614,6 @@ static int ci_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int ci_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-					SMU7_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_samu_clock_voltage_dependency_table *samu_table =
-				hwmgr->dyn_state.samu_clock_voltage_dependency_table;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(samu_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		table->SamuLevel[count].Frequency = samu_table->entries[count].samclk;
-		table->SamuLevel[count].MinVoltage = samu_table->entries[count].v * VOLTAGE_SCALE;
-		table->SamuLevel[count].MinPhases = 1;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_US(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int ci_populate_memory_timing_parameters(
 		struct pp_hwmgr *hwmgr,
 		uint32_t engine_clock,
@@ -2026,10 +1995,6 @@ static int ci_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 		"Failed to initialize ACP Level!", return result);
 
-	result = ci_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-		"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point (the other states are just copies of the boot state) we only */
 	/* need to populate the  ARB settings for the initial state. */
 	result = ci_program_memory_timing_parameters(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
index 53df9405f43a..18048f8e2f13 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/fiji_smumgr.c
@@ -1503,44 +1503,6 @@ static int fiji_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int fiji_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU73_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-			table_info->mm_dep_table;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].MinVoltage = 0;
-		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
-				VOLTAGE_SCALE) << VDDC_SHIFT;
-		table->SamuLevel[count].MinVoltage |= ((mm_table->entries[count].vddc -
-				VDDC_VDDCI_DELTA) * VOLTAGE_SCALE) << VDDCI_SHIFT;
-		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int fiji_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 		int32_t eng_clock, int32_t mem_clock,
 		struct SMU73_Discrete_MCArbDramTimingTableEntry *arb_regs)
@@ -2028,10 +1990,6 @@ static int fiji_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 			"Failed to initialize ACP Level!", return result);
 
-	result = fiji_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-			"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point
 	 * (the other states are just copies of the boot state) we only
 	 * need to populate the  ARB settings for the initial state.
@@ -2378,8 +2336,6 @@ static uint32_t fiji_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU73_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU73_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU73_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU73_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
@@ -2478,33 +2434,6 @@ static int fiji_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int fiji_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct fiji_smumgr *smu_data = (struct fiji_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU73_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
 static int fiji_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 {
 	switch (type) {
@@ -2514,9 +2443,6 @@ static int fiji_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		fiji_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		fiji_update_samu_smc_table(hwmgr);
-		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
index 415f691c3fa9..9299b93aa09a 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/iceland_smumgr.c
@@ -1578,12 +1578,6 @@ static int iceland_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static int iceland_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-	SMU71_Discrete_DpmTable *table)
-{
-	return 0;
-}
-
 static int iceland_populate_memory_timing_parameters(
 		struct pp_hwmgr *hwmgr,
 		uint32_t engine_clock,
@@ -1992,10 +1986,6 @@ static int iceland_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 		"Failed to initialize ACP Level!", return result;);
 
-	result = iceland_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-		"Failed to initialize SAMU Level!", return result;);
-
 	/* Since only the initial state is completely set up at this point (the other states are just copies of the boot state) we only */
 	/* need to populate the  ARB settings for the initial state. */
 	result = iceland_program_memory_timing_parameters(hwmgr);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index a8c6524f07e4..a4ce199af475 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -1337,55 +1337,6 @@ static int polaris10_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-
-static int polaris10_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU74_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-			table_info->mm_dep_table;
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	uint32_t vddci;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].MinVoltage = 0;
-		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
-				VOLTAGE_SCALE) << VDDC_SHIFT;
-
-		if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
-			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
-						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
-		else if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
-			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
-		else
-			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
-
-		table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
-		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int polaris10_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 		int32_t eng_clock, int32_t mem_clock,
 		SMU74_Discrete_MCArbDramTimingTableEntry *arb_regs)
@@ -1865,10 +1816,6 @@ static int polaris10_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(0 == result,
 			"Failed to initialize VCE Level!", return result);
 
-	result = polaris10_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(0 == result,
-			"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point
 	 * (the other states are just copies of the boot state) we only
 	 * need to populate the  ARB settings for the initial state.
@@ -2222,34 +2169,6 @@ static int polaris10_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int polaris10_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU74_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
-
 static int polaris10_update_bif_smc_table(struct pp_hwmgr *hwmgr)
 {
 	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend);
@@ -2276,9 +2195,6 @@ static int polaris10_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		polaris10_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		polaris10_update_samu_smc_table(hwmgr);
-		break;
 	case SMU_BIF_TABLE:
 		polaris10_update_bif_smc_table(hwmgr);
 	default:
@@ -2357,8 +2273,6 @@ static uint32_t polaris10_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU74_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU74_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU74_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU74_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
index 782b19fc2e70..7dabc6c456e1 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/tonga_smumgr.c
@@ -1443,51 +1443,6 @@ static int tonga_populate_smc_acp_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int tonga_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU72_Discrete_DpmTable *table)
-{
-	int result = 0;
-	uint8_t count;
-	pp_atomctrl_clock_dividers_vi dividers;
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	struct phm_ppt_v1_information *pptable_info =
-			     (struct phm_ppt_v1_information *)(hwmgr->pptable);
-	phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-						    pptable_info->mm_dep_table;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t) (mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].Frequency =
-			pptable_info->mm_dep_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage.Vddc =
-			phm_get_voltage_index(pptable_info->vddc_lookup_table,
-				mm_table->entries[count].vddc);
-		table->SamuLevel[count].MinVoltage.VddGfx =
-			(data->vdd_gfx_control == SMU7_VOLTAGE_CONTROL_BY_SVID2) ?
-			phm_get_voltage_index(pptable_info->vddgfx_lookup_table,
-				mm_table->entries[count].vddgfx) : 0;
-		table->SamuLevel[count].MinVoltage.Vddci =
-			phm_get_voltage_id(&data->vddci_voltage_table,
-				mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
-		table->SamuLevel[count].MinVoltage.Phases = 1;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-					table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((!result),
-			"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-	}
-
-	return result;
-}
-
 static int tonga_populate_memory_timing_parameters(
 		struct pp_hwmgr *hwmgr,
 		uint32_t engine_clock,
@@ -2323,10 +2278,6 @@ static int tonga_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(!result,
 		"Failed to initialize ACP Level !", return result);
 
-	result = tonga_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(!result,
-		"Failed to initialize SAMU Level !", return result);
-
 	/* Since only the initial state is completely set up at this
 	* point (the other states are just copies of the boot state) we only
 	* need to populate the  ARB settings for the initial state.
@@ -2673,8 +2624,6 @@ static uint32_t tonga_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU72_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU72_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU72_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU72_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
@@ -2773,32 +2722,6 @@ static int tonga_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int tonga_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct tonga_smumgr *smu_data = (struct tonga_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU72_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
 static int tonga_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 {
 	switch (type) {
@@ -2808,9 +2731,6 @@ static int tonga_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		tonga_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		tonga_update_samu_smc_table(hwmgr);
-		break;
 	default:
 		break;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
index 2de48959ac93..57420d7caa4e 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vegam_smumgr.c
@@ -393,34 +393,6 @@ static int vegam_update_vce_smc_table(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int vegam_update_samu_smc_table(struct pp_hwmgr *hwmgr)
-{
-	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
-	uint32_t mm_boot_level_offset, mm_boot_level_value;
-
-
-	smu_data->smc_state_table.SamuBootLevel = 0;
-	mm_boot_level_offset = smu_data->smu7_data.dpm_table_start +
-				offsetof(SMU75_Discrete_DpmTable, SamuBootLevel);
-
-	mm_boot_level_offset /= 4;
-	mm_boot_level_offset *= 4;
-	mm_boot_level_value = cgs_read_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset);
-	mm_boot_level_value &= 0xFFFFFF00;
-	mm_boot_level_value |= smu_data->smc_state_table.SamuBootLevel << 0;
-	cgs_write_ind_register(hwmgr->device,
-			CGS_IND_REG__SMC, mm_boot_level_offset, mm_boot_level_value);
-
-	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps,
-			PHM_PlatformCaps_StablePState))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_SAMUDPM_SetEnabledMask,
-				(uint32_t)(1 << smu_data->smc_state_table.SamuBootLevel));
-	return 0;
-}
-
-
 static int vegam_update_bif_smc_table(struct pp_hwmgr *hwmgr)
 {
 	struct vegam_smumgr *smu_data = (struct vegam_smumgr *)(hwmgr->smu_backend);
@@ -447,9 +419,6 @@ static int vegam_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
 	case SMU_VCE_TABLE:
 		vegam_update_vce_smc_table(hwmgr);
 		break;
-	case SMU_SAMU_TABLE:
-		vegam_update_samu_smc_table(hwmgr);
-		break;
 	case SMU_BIF_TABLE:
 		vegam_update_bif_smc_table(hwmgr);
 		break;
@@ -1281,54 +1250,6 @@ static int vegam_populate_smc_vce_level(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
-static int vegam_populate_smc_samu_level(struct pp_hwmgr *hwmgr,
-		SMU75_Discrete_DpmTable *table)
-{
-	int result = -EINVAL;
-	uint8_t count;
-	struct pp_atomctrl_clock_dividers_vi dividers;
-	struct phm_ppt_v1_information *table_info =
-			(struct phm_ppt_v1_information *)(hwmgr->pptable);
-	struct phm_ppt_v1_mm_clock_voltage_dependency_table *mm_table =
-			table_info->mm_dep_table;
-	struct smu7_hwmgr *data = (struct smu7_hwmgr *)(hwmgr->backend);
-	uint32_t vddci;
-
-	table->SamuBootLevel = 0;
-	table->SamuLevelCount = (uint8_t)(mm_table->count);
-
-	for (count = 0; count < table->SamuLevelCount; count++) {
-		/* not sure whether we need evclk or not */
-		table->SamuLevel[count].MinVoltage = 0;
-		table->SamuLevel[count].Frequency = mm_table->entries[count].samclock;
-		table->SamuLevel[count].MinVoltage |= (mm_table->entries[count].vddc *
-				VOLTAGE_SCALE) << VDDC_SHIFT;
-
-		if (SMU7_VOLTAGE_CONTROL_BY_GPIO == data->vddci_control)
-			vddci = (uint32_t)phm_find_closest_vddci(&(data->vddci_voltage_table),
-						mm_table->entries[count].vddc - VDDC_VDDCI_DELTA);
-		else if (SMU7_VOLTAGE_CONTROL_BY_SVID2 == data->vddci_control)
-			vddci = mm_table->entries[count].vddc - VDDC_VDDCI_DELTA;
-		else
-			vddci = (data->vbios_boot_state.vddci_bootup_value * VOLTAGE_SCALE) << VDDCI_SHIFT;
-
-		table->SamuLevel[count].MinVoltage |= (vddci * VOLTAGE_SCALE) << VDDCI_SHIFT;
-		table->SamuLevel[count].MinVoltage |= 1 << PHASES_SHIFT;
-
-		/* retrieve divider value for VBIOS */
-		result = atomctrl_get_dfs_pll_dividers_vi(hwmgr,
-				table->SamuLevel[count].Frequency, &dividers);
-		PP_ASSERT_WITH_CODE((0 == result),
-				"can not find divide id for samu clock", return result);
-
-		table->SamuLevel[count].Divider = (uint8_t)dividers.pll_post_divider;
-
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].Frequency);
-		CONVERT_FROM_HOST_TO_SMC_UL(table->SamuLevel[count].MinVoltage);
-	}
-	return result;
-}
-
 static int vegam_populate_memory_timing_parameters(struct pp_hwmgr *hwmgr,
 		int32_t eng_clock, int32_t mem_clock,
 		SMU75_Discrete_MCArbDramTimingTableEntry *arb_regs)
@@ -2062,10 +1983,6 @@ static int vegam_init_smc_table(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to initialize VCE Level!", return result);
 
-	result = vegam_populate_smc_samu_level(hwmgr, table);
-	PP_ASSERT_WITH_CODE(!result,
-			"Failed to initialize SAMU Level!", return result);
-
 	/* Since only the initial state is completely set up at this point
 	 * (the other states are just copies of the boot state) we only
 	 * need to populate the  ARB settings for the initial state.
@@ -2273,8 +2190,6 @@ static uint32_t vegam_get_offsetof(uint32_t type, uint32_t member)
 			return offsetof(SMU75_Discrete_DpmTable, UvdBootLevel);
 		case VceBootLevel:
 			return offsetof(SMU75_Discrete_DpmTable, VceBootLevel);
-		case SamuBootLevel:
-			return offsetof(SMU75_Discrete_DpmTable, SamuBootLevel);
 		case LowSclkInterruptThreshold:
 			return offsetof(SMU75_Discrete_DpmTable, LowSclkInterruptThreshold);
 		}
-- 
cgit v1.2.3


From 600ae890be59910e65b75fe25a1b900d83c0329c Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Mon, 4 Jun 2018 16:39:38 +0800
Subject: drm/amdgpu: Use real power source in powerplay instand of hardcode

1. move ac_power to struct pm from dpm, so can be shared with powerplay
2. remove power_source in powerplay, use adev->pm.ac_power instand.
3. update ac_power before dispatch power task.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h            |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c             | 21 +++++++------
 drivers/gpu/drm/amd/amdgpu/ci_dpm.c                | 12 ++++----
 drivers/gpu/drm/amd/amdgpu/kv_dpm.c                |  2 +-
 drivers/gpu/drm/amd/amdgpu/si_dpm.c                |  4 +--
 drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c        |  1 -
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c   |  6 ++--
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c |  5 +--
 drivers/gpu/drm/amd/powerplay/inc/hwmgr.h          |  2 --
 .../gpu/drm/amd/powerplay/inc/pp_power_source.h    | 36 ----------------------
 10 files changed, 27 insertions(+), 64 deletions(-)
 delete mode 100644 drivers/gpu/drm/amd/powerplay/inc/pp_power_source.h

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index dd6203a0a6b7..9acfbee91c40 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -402,7 +402,6 @@ struct amdgpu_dpm {
 	u32 tdp_adjustment;
 	u16 load_line_slope;
 	bool power_control;
-	bool ac_power;
 	/* special states active */
 	bool                    thermal_active;
 	bool                    uvd_active;
@@ -439,6 +438,7 @@ struct amdgpu_pm {
 	struct amd_pp_display_configuration pm_display_cfg;/* set by dc */
 	uint32_t                smu_prv_buffer_size;
 	struct amdgpu_bo        *smu_prv_buffer;
+	bool ac_power;
 };
 
 #define R600_SSTU_DFLT                               0
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index f667cb9eb614..113edffb5960 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -68,11 +68,11 @@ void amdgpu_pm_acpi_event_handler(struct amdgpu_device *adev)
 	if (adev->pm.dpm_enabled) {
 		mutex_lock(&adev->pm.mutex);
 		if (power_supply_is_system_supplied() > 0)
-			adev->pm.dpm.ac_power = true;
+			adev->pm.ac_power = true;
 		else
-			adev->pm.dpm.ac_power = false;
+			adev->pm.ac_power = false;
 		if (adev->powerplay.pp_funcs->enable_bapm)
-			amdgpu_dpm_enable_bapm(adev, adev->pm.dpm.ac_power);
+			amdgpu_dpm_enable_bapm(adev, adev->pm.ac_power);
 		mutex_unlock(&adev->pm.mutex);
 	}
 }
@@ -1907,6 +1907,14 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 			amdgpu_fence_wait_empty(ring);
 	}
 
+	mutex_lock(&adev->pm.mutex);
+	/* update battery/ac status */
+	if (power_supply_is_system_supplied() > 0)
+		adev->pm.ac_power = true;
+	else
+		adev->pm.ac_power = false;
+	mutex_unlock(&adev->pm.mutex);
+
 	if (adev->powerplay.pp_funcs->dispatch_tasks) {
 		if (!amdgpu_device_has_dc_support(adev)) {
 			mutex_lock(&adev->pm.mutex);
@@ -1927,14 +1935,7 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 	} else {
 		mutex_lock(&adev->pm.mutex);
 		amdgpu_dpm_get_active_displays(adev);
-		/* update battery/ac status */
-		if (power_supply_is_system_supplied() > 0)
-			adev->pm.dpm.ac_power = true;
-		else
-			adev->pm.dpm.ac_power = false;
-
 		amdgpu_dpm_change_power_state_locked(adev);
-
 		mutex_unlock(&adev->pm.mutex);
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index a266dcf5daed..b6248c0578a1 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -951,12 +951,12 @@ static void ci_apply_state_adjust_rules(struct amdgpu_device *adev,
 	else
 		pi->battery_state = false;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
 
-	if (adev->pm.dpm.ac_power == false) {
+	if (adev->pm.ac_power == false) {
 		for (i = 0; i < ps->performance_level_count; i++) {
 			if (ps->performance_levels[i].mclk > max_limits->mclk)
 				ps->performance_levels[i].mclk = max_limits->mclk;
@@ -4078,7 +4078,7 @@ static int ci_enable_uvd_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -4127,7 +4127,7 @@ static int ci_enable_vce_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -4160,7 +4160,7 @@ static int ci_enable_samu_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -4191,7 +4191,7 @@ static int ci_enable_acp_dpm(struct amdgpu_device *adev, bool enable)
 	const struct amdgpu_clock_and_voltage_limits *max_limits;
 	int i;
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 17f7f074cedc..d79e6f5234da 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -1921,7 +1921,7 @@ static int kv_dpm_set_power_state(void *handle)
 	int ret;
 
 	if (pi->bapm_enable) {
-		ret = amdgpu_kv_smc_bapm_enable(adev, adev->pm.dpm.ac_power);
+		ret = amdgpu_kv_smc_bapm_enable(adev, adev->pm.ac_power);
 		if (ret) {
 			DRM_ERROR("amdgpu_kv_smc_bapm_enable failed\n");
 			return ret;
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index b12d7c9d42a0..9567dd0a01bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -3480,7 +3480,7 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		disable_sclk_switching = true;
 	}
 
-	if (adev->pm.dpm.ac_power)
+	if (adev->pm.ac_power)
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_ac;
 	else
 		max_limits = &adev->pm.dpm.dyn_state.max_clock_voltage_on_dc;
@@ -3489,7 +3489,7 @@ static void si_apply_state_adjust_rules(struct amdgpu_device *adev,
 		if (ps->performance_levels[i].vddc > ps->performance_levels[i+1].vddc)
 			ps->performance_levels[i].vddc = ps->performance_levels[i+1].vddc;
 	}
-	if (adev->pm.dpm.ac_power == false) {
+	if (adev->pm.ac_power == false) {
 		for (i = 0; i < ps->performance_level_count; i++) {
 			if (ps->performance_levels[i].mclk > max_limits->mclk)
 				ps->performance_levels[i].mclk = max_limits->mclk;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 4ef77cebc628..9b675d9bd162 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -81,7 +81,6 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 		return -EINVAL;
 
 	hwmgr->usec_timeout = AMD_MAX_USEC_TIMEOUT;
-	hwmgr->power_source = PP_PowerSource_AC;
 	hwmgr->pp_table_version = PP_TABLE_V1;
 	hwmgr->dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
 	hwmgr->request_dpm_level = AMD_DPM_FORCED_LEVEL_AUTO;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 24d20d9c74b4..b89d6fb8559b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -2877,7 +2877,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				struct pp_power_state *request_ps,
 			const struct pp_power_state *current_ps)
 {
-
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct smu7_power_state *smu7_ps =
 				cast_phw_smu7_power_state(&request_ps->hardware);
 	uint32_t sclk;
@@ -2900,12 +2900,12 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				 "VI should always have 2 performance levels",
 				);
 
-	max_limits = (PP_PowerSource_AC == hwmgr->power_source) ?
+	max_limits = adev->pm.ac_power ?
 			&(hwmgr->dyn_state.max_clock_voltage_on_ac) :
 			&(hwmgr->dyn_state.max_clock_voltage_on_dc);
 
 	/* Cap clock DPM tables at DC MAX if it is in DC. */
-	if (PP_PowerSource_DC == hwmgr->power_source) {
+	if (!adev->pm.ac_power) {
 		for (i = 0; i < smu7_ps->performance_level_count; i++) {
 			if (smu7_ps->performance_levels[i].memory_clock > max_limits->mclk)
 				smu7_ps->performance_levels[i].memory_clock = max_limits->mclk;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 66fd1a43e346..3b8d36df52e9 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3102,6 +3102,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 				struct pp_power_state  *request_ps,
 			const struct pp_power_state *current_ps)
 {
+	struct amdgpu_device *adev = hwmgr->adev;
 	struct vega10_power_state *vega10_ps =
 				cast_phw_vega10_power_state(&request_ps->hardware);
 	uint32_t sclk;
@@ -3127,12 +3128,12 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 	if (vega10_ps->performance_level_count != 2)
 		pr_info("VI should always have 2 performance levels");
 
-	max_limits = (PP_PowerSource_AC == hwmgr->power_source) ?
+	max_limits = adev->pm.ac_power ?
 			&(hwmgr->dyn_state.max_clock_voltage_on_ac) :
 			&(hwmgr->dyn_state.max_clock_voltage_on_dc);
 
 	/* Cap clock DPM tables at DC MAX if it is in DC. */
-	if (PP_PowerSource_DC == hwmgr->power_source) {
+	if (!adev->pm.ac_power) {
 		for (i = 0; i < vega10_ps->performance_level_count; i++) {
 			if (vega10_ps->performance_levels[i].mem_clock >
 				max_limits->mclk)
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index b99fb8ac822c..40c98ca5feb7 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -26,7 +26,6 @@
 #include <linux/seq_file.h>
 #include "amd_powerplay.h"
 #include "hardwaremanager.h"
-#include "pp_power_source.h"
 #include "hwmgr_ppt.h"
 #include "ppatomctrl.h"
 #include "hwmgr_ppt.h"
@@ -741,7 +740,6 @@ struct pp_hwmgr {
 	const struct pp_table_func *pptable_func;
 
 	struct pp_power_state    *ps;
-	enum pp_power_source  power_source;
 	uint32_t num_ps;
 	struct pp_thermal_controller_info thermal_controller;
 	bool fan_ctrl_is_in_default_mode;
diff --git a/drivers/gpu/drm/amd/powerplay/inc/pp_power_source.h b/drivers/gpu/drm/amd/powerplay/inc/pp_power_source.h
deleted file mode 100644
index b43315cc5d58..000000000000
--- a/drivers/gpu/drm/amd/powerplay/inc/pp_power_source.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * Copyright 2015 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- */
-
-#ifndef PP_POWERSOURCE_H
-#define PP_POWERSOURCE_H
-
-enum pp_power_source {
-	PP_PowerSource_AC = 0,
-	PP_PowerSource_DC,
-	PP_PowerSource_LimitedPower,
-	PP_PowerSource_LimitedPower_2,
-	PP_PowerSource_Max
-};
-
-
-#endif
-- 
cgit v1.2.3


From e1e36485e9f398be7207630d866810df485fbf34 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Mon, 4 Jun 2018 18:12:31 +0800
Subject: drm/amd/pp: Implement update_smc_table for CI.

driver need to update uvd/vce smc table before enable
uvd/vce dpm.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c | 84 ++++++++++++++++++++++++
 1 file changed, 84 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
index 8cd21ac6ceda..fbe3ef4ee45c 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/ci_smumgr.c
@@ -2846,6 +2846,89 @@ static int ci_update_dpm_settings(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static int ci_update_uvd_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	struct smu7_hwmgr *data = hwmgr->backend;
+	struct ci_smumgr *smu_data = hwmgr->smu_backend;
+	struct phm_uvd_clock_voltage_dependency_table *uvd_table =
+			hwmgr->dyn_state.uvd_clock_voltage_dependency_table;
+	uint32_t profile_mode_mask = AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_PEAK;
+	uint32_t max_vddc = adev->pm.ac_power ? hwmgr->dyn_state.max_clock_voltage_on_ac.vddc :
+						hwmgr->dyn_state.max_clock_voltage_on_dc.vddc;
+	int32_t i;
+
+	if (PP_CAP(PHM_PlatformCaps_UVDDPM) || uvd_table->count <= 0)
+		smu_data->smc_state_table.UvdBootLevel = 0;
+	else
+		smu_data->smc_state_table.UvdBootLevel = uvd_table->count - 1;
+
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, DPM_TABLE_475,
+				UvdBootLevel, smu_data->smc_state_table.UvdBootLevel);
+
+	data->dpm_level_enable_mask.uvd_dpm_enable_mask = 0;
+
+	for (i = uvd_table->count - 1; i >= 0; i--) {
+		if (uvd_table->entries[i].v <= max_vddc)
+			data->dpm_level_enable_mask.uvd_dpm_enable_mask |= 1 << i;
+		if (hwmgr->dpm_level & profile_mode_mask || !PP_CAP(PHM_PlatformCaps_UVDDPM))
+			break;
+	}
+	ci_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_UVDDPM_SetEnabledMask,
+				data->dpm_level_enable_mask.uvd_dpm_enable_mask);
+
+	return 0;
+}
+
+static int ci_update_vce_smc_table(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	struct smu7_hwmgr *data = hwmgr->backend;
+	struct phm_vce_clock_voltage_dependency_table *vce_table =
+			hwmgr->dyn_state.vce_clock_voltage_dependency_table;
+	uint32_t profile_mode_mask = AMD_DPM_FORCED_LEVEL_PROFILE_STANDARD |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK |
+					AMD_DPM_FORCED_LEVEL_PROFILE_PEAK;
+	uint32_t max_vddc = adev->pm.ac_power ? hwmgr->dyn_state.max_clock_voltage_on_ac.vddc :
+						hwmgr->dyn_state.max_clock_voltage_on_dc.vddc;
+	int32_t i;
+
+	PHM_WRITE_INDIRECT_FIELD(hwmgr->device, CGS_IND_REG__SMC, DPM_TABLE_475,
+				VceBootLevel, 0); /* temp hard code to level 0, vce can set min evclk*/
+
+	data->dpm_level_enable_mask.vce_dpm_enable_mask = 0;
+
+	for (i = vce_table->count - 1; i >= 0; i--) {
+		if (vce_table->entries[i].v <= max_vddc)
+			data->dpm_level_enable_mask.vce_dpm_enable_mask |= 1 << i;
+		if (hwmgr->dpm_level & profile_mode_mask || !PP_CAP(PHM_PlatformCaps_VCEDPM))
+			break;
+	}
+	ci_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_VCEDPM_SetEnabledMask,
+				data->dpm_level_enable_mask.vce_dpm_enable_mask);
+
+	return 0;
+}
+
+static int ci_update_smc_table(struct pp_hwmgr *hwmgr, uint32_t type)
+{
+	switch (type) {
+	case SMU_UVD_TABLE:
+		ci_update_uvd_smc_table(hwmgr);
+		break;
+	case SMU_VCE_TABLE:
+		ci_update_vce_smc_table(hwmgr);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 const struct pp_smumgr_func ci_smu_funcs = {
 	.smu_init = ci_smu_init,
 	.smu_fini = ci_smu_fini,
@@ -2868,4 +2951,5 @@ const struct pp_smumgr_func ci_smu_funcs = {
 	.initialize_mc_reg_table = ci_initialize_mc_reg_table,
 	.is_dpm_running = ci_is_dpm_running,
 	.update_dpm_settings = ci_update_dpm_settings,
+	.update_smc_table = ci_update_smc_table,
 };
-- 
cgit v1.2.3


From b1ddf5484727296f8812118a6042c76ebd1faff4 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Mon, 4 Jun 2018 18:26:18 +0800
Subject: drm/amdgpu: Get real power source to initizlize ac_power

driver need to know the real power source to do some power
related configuration when initialize.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 3317d1536f4f..fe76ec1f9737 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -25,6 +25,7 @@
  *          Alex Deucher
  *          Jerome Glisse
  */
+#include <linux/power_supply.h>
 #include <linux/kthread.h>
 #include <linux/console.h>
 #include <linux/slab.h>
@@ -2293,6 +2294,8 @@ int amdgpu_device_init(struct amdgpu_device *adev,
 	INIT_DELAYED_WORK(&adev->late_init_work,
 			  amdgpu_device_ip_late_init_func_handler);
 
+	adev->pm.ac_power = power_supply_is_system_supplied() > 0 ? true : false;
+
 	/* Registers mapping */
 	/* TODO: block userspace mapping of io register */
 	if (adev->asic_type >= CHIP_BONAIRE) {
-- 
cgit v1.2.3


From ab3ec8a1a9f1c785103f395e9502ab5804705134 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Thu, 14 Jun 2018 11:59:20 +0200
Subject: drm/amdgpu: Restore :internal: for amdgpu_vm.c documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This was accidentally dropped by the "drm/amdgpu: update documentation
for amdgpu_irq.c v3" change, resulting in the GPUVM documentation body
being included twice in the generated documentation.

Trivial.

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index e1656fe8f247..e52d0ce186fe 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -52,6 +52,7 @@ AMDGPU Virtual Memory
    :doc: GPUVM
 
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+   :internal:
 
 Interrupt Handling
 ------------------
-- 
cgit v1.2.3


From 00553cf8116e041c75c6c201bdf6d4e006fcf956 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Wed, 13 Jun 2018 16:01:38 -0400
Subject: drm/amdgpu: Update function level documentation for GPUVM.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add documentation for missed parameters.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6d2294203bd7..819949418495 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -347,6 +347,7 @@ bool amdgpu_vm_ready(struct amdgpu_vm *vm)
  * @vm: VM to clear BO from
  * @bo: BO to clear
  * @level: level this BO is at
+ * @pte_support_ats: indicate ATS support from PTE
  *
  * Root PD needs to be reserved when calling this.
  *
@@ -673,6 +674,7 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
  * amdgpu_vm_flush - hardware flush the vm
  *
  * @ring: ring to use for flush
+ * @job:  related job
  * @need_pipe_sync: is pipe sync needed
  *
  * Emit a VM flush when it is necessary.
@@ -1763,6 +1765,7 @@ static void amdgpu_vm_prt_put(struct amdgpu_device *adev)
  * amdgpu_vm_prt_cb - callback for updating the PRT status
  *
  * @fence: fence for the callback
+ * @_cb: the callback function
  */
 static void amdgpu_vm_prt_cb(struct dma_fence *fence, struct dma_fence_cb *_cb)
 {
@@ -2041,6 +2044,7 @@ static void amdgpu_vm_bo_insert_map(struct amdgpu_device *adev,
  * @bo_va: bo_va to store the address
  * @saddr: where to map the BO
  * @offset: requested offset in the BO
+ * @size: BO size in bytes
  * @flags: attributes of pages (read/write/valid/etc.)
  *
  * Add a mapping of the BO at the specefied addr into the VM.
@@ -2104,6 +2108,7 @@ int amdgpu_vm_bo_map(struct amdgpu_device *adev,
  * @bo_va: bo_va to store the address
  * @saddr: where to map the BO
  * @offset: requested offset in the BO
+ * @size: BO size in bytes
  * @flags: attributes of pages (read/write/valid/etc.)
  *
  * Add a mapping of the BO at the specefied addr into the VM. Replace existing
@@ -2322,6 +2327,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
  * amdgpu_vm_bo_lookup_mapping - find mapping by address
  *
  * @vm: the requested VM
+ * @addr: the address
  *
  * Find a mapping by it's address.
  *
@@ -2380,6 +2386,7 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
  *
  * @adev: amdgpu_device pointer
  * @bo: amdgpu buffer object
+ * @evicted: is the BO evicted
  *
  * Mark @bo as invalid.
  */
@@ -2445,6 +2452,10 @@ static uint32_t amdgpu_vm_get_block_size(uint64_t vm_size)
  *
  * @adev: amdgpu_device pointer
  * @vm_size: the default vm size if it's set auto
+ * @fragment_size_default: Default PTE fragment size
+ * @max_level: max VMPT level
+ * @max_bits: max address space size in bits
+ *
  */
 void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
 			   uint32_t fragment_size_default, unsigned max_level,
@@ -2512,6 +2523,7 @@ void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
  * @adev: amdgpu_device pointer
  * @vm: requested vm
  * @vm_context: Indicates if it GFX or Compute context
+ * @pasid: Process address space identifier
  *
  * Init @vm fields.
  *
-- 
cgit v1.2.3


From 3b070c60ea511a0d103b39de3122d3bad0de45ab Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Tue, 22 May 2018 15:55:43 -0400
Subject: drm/amd/display: Drop to fail-safe mode if edid is bad

Provide the connector with a single fail-safe mode of 640x480 for CTS
tests instead of providing a list of possible base modes.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index adeb795d80f6..b1b8d1914b31 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3424,6 +3424,10 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 	struct edid *edid = amdgpu_dm_connector->edid;
 
 	encoder = helper->best_encoder(connector);
+
+	if (!edid || !drm_edid_is_valid(edid))
+		return drm_add_modes_noedid(connector, 640, 480);
+
 	amdgpu_dm_connector_ddc_get_modes(connector, edid);
 	amdgpu_dm_connector_add_common_modes(encoder, connector);
 
-- 
cgit v1.2.3


From 6e0ef9d85b99baeeea4b9c4a9777809cb0c6040a Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Thu, 17 May 2018 15:44:20 -0400
Subject: drm/amd/display: Write TEST_EDID_CHECKSUM_WRITE for EDID tests

Extract edid's checksum and send it back for verification if EDID_TEST
is requested.

Also added a flag for EDID checksum write in TEST_RESPONSE structure,
and simple spelling fix.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c  | 28 ++++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/dc_dp_types.h       |  5 ++--
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index bd449351803f..dea49dc9b518 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -497,6 +497,34 @@ enum dc_edid_status dm_helpers_read_local_edid(
 		DRM_ERROR("EDID err: %d, on connector: %s",
 				edid_status,
 				aconnector->base.name);
+	if (link->aux_mode) {
+		union test_request test_request = {0};
+		union test_response test_response = {0};
+
+		dm_helpers_dp_read_dpcd(ctx,
+					link,
+					DP_TEST_REQUEST,
+					&test_request.raw,
+					sizeof(union test_request));
+
+		if (!test_request.bits.EDID_READ)
+			return edid_status;
+
+		test_response.bits.EDID_CHECKSUM_WRITE = 1;
+
+		dm_helpers_dp_write_dpcd(ctx,
+					link,
+					DP_TEST_EDID_CHECKSUM,
+					&sink->dc_edid.raw_edid[sink->dc_edid.length-1],
+					1);
+
+		dm_helpers_dp_write_dpcd(ctx,
+					link,
+					DP_TEST_RESPONSE,
+					&test_response.raw,
+					sizeof(test_response));
+
+	}
 
 	return edid_status;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
index 90bccd5ccaa2..da93ab43f2d8 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_dp_types.h
@@ -430,7 +430,7 @@ union test_request {
 	struct {
 	uint8_t LINK_TRAINING         :1;
 	uint8_t LINK_TEST_PATTRN      :1;
-	uint8_t EDID_REAT             :1;
+	uint8_t EDID_READ             :1;
 	uint8_t PHY_TEST_PATTERN      :1;
 	uint8_t AUDIO_TEST_PATTERN    :1;
 	uint8_t RESERVED              :1;
@@ -443,7 +443,8 @@ union test_response {
 	struct {
 		uint8_t ACK         :1;
 		uint8_t NO_ACK      :1;
-		uint8_t RESERVED    :6;
+		uint8_t EDID_CHECKSUM_WRITE:1;
+		uint8_t RESERVED    :5;
 	} bits;
 	uint8_t raw;
 };
-- 
cgit v1.2.3


From b4f84bdf579eb654add9a4c257b97af499c23e03 Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Tue, 22 May 2018 15:16:33 -0400
Subject: drm/amd/display: Stream encoder update

Update stream encoder based on feedback from HW team.

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/dc/dcn10/dcn10_stream_encoder.c    | 30 +---------------------
 1 file changed, 1 insertion(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 147f61416fa5..32a4997714c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -1097,27 +1097,6 @@ static union audio_cea_channels speakers_to_channels(
 	return cea_channels;
 }
 
-static uint32_t calc_max_audio_packets_per_line(
-	const struct audio_crtc_info *crtc_info)
-{
-	uint32_t max_packets_per_line;
-
-	max_packets_per_line =
-		crtc_info->h_total - crtc_info->h_active;
-
-	if (crtc_info->pixel_repetition)
-		max_packets_per_line *= crtc_info->pixel_repetition;
-
-	/* for other hdmi features */
-	max_packets_per_line -= 58;
-	/* for Control Period */
-	max_packets_per_line -= 16;
-	/* Number of Audio Packets per Line */
-	max_packets_per_line /= 32;
-
-	return max_packets_per_line;
-}
-
 static void get_audio_clock_info(
 	enum dc_color_depth color_depth,
 	uint32_t crtc_pixel_clock_in_khz,
@@ -1211,16 +1190,9 @@ static void enc1_se_setup_hdmi_audio(
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
 	struct audio_clock_info audio_clock_info = {0};
-	uint32_t max_packets_per_line;
-
-	/* For now still do calculation, although this field is ignored when
-	 * above HDMI_PACKET_GEN_VERSION set to 1
-	 */
-	max_packets_per_line = calc_max_audio_packets_per_line(crtc_info);
 
 	/* HDMI_AUDIO_PACKET_CONTROL */
-	REG_UPDATE_2(HDMI_AUDIO_PACKET_CONTROL,
-			HDMI_AUDIO_PACKETS_PER_LINE, max_packets_per_line,
+	REG_UPDATE(HDMI_AUDIO_PACKET_CONTROL,
 			HDMI_AUDIO_DELAY_EN, 1);
 
 	/* AFMT_AUDIO_PACKET_CONTROL */
-- 
cgit v1.2.3


From 973d42c79e99aedd767071407ce286bb7eefe202 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Wed, 9 May 2018 11:35:21 -0400
Subject: drm/amd/display: Move i2c and aux structs into dc_ddc_types.h

We'd like to use some of them in dc_link_ddc and amdgpu_dm and should
have them available in dc_ddc_types.h.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_ddc_types.h      | 59 ++++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h | 44 +---------------
 drivers/gpu/drm/amd/display/dc/i2caux/engine.h     | 15 +-----
 3 files changed, 62 insertions(+), 56 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
index ee04812b4492..05c8c31d8b31 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_ddc_types.h
@@ -25,6 +25,65 @@
 #ifndef DC_DDC_TYPES_H_
 #define DC_DDC_TYPES_H_
 
+enum aux_transaction_type {
+	AUX_TRANSACTION_TYPE_DP,
+	AUX_TRANSACTION_TYPE_I2C
+};
+
+
+enum i2caux_transaction_action {
+	I2CAUX_TRANSACTION_ACTION_I2C_WRITE = 0x00,
+	I2CAUX_TRANSACTION_ACTION_I2C_READ = 0x10,
+	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST = 0x20,
+
+	I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT = 0x40,
+	I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT = 0x50,
+	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT = 0x60,
+
+	I2CAUX_TRANSACTION_ACTION_DP_WRITE = 0x80,
+	I2CAUX_TRANSACTION_ACTION_DP_READ = 0x90
+};
+
+enum aux_channel_operation_result {
+	AUX_CHANNEL_OPERATION_SUCCEEDED,
+	AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN,
+	AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY,
+	AUX_CHANNEL_OPERATION_FAILED_TIMEOUT,
+	AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON
+};
+
+
+struct aux_request_transaction_data {
+	enum aux_transaction_type type;
+	enum i2caux_transaction_action action;
+	/* 20-bit AUX channel transaction address */
+	uint32_t address;
+	/* delay, in 100-microsecond units */
+	uint8_t delay;
+	uint32_t length;
+	uint8_t *data;
+};
+
+enum aux_transaction_reply {
+	AUX_TRANSACTION_REPLY_AUX_ACK = 0x00,
+	AUX_TRANSACTION_REPLY_AUX_NACK = 0x01,
+	AUX_TRANSACTION_REPLY_AUX_DEFER = 0x02,
+
+	AUX_TRANSACTION_REPLY_I2C_ACK = 0x00,
+	AUX_TRANSACTION_REPLY_I2C_NACK = 0x10,
+	AUX_TRANSACTION_REPLY_I2C_DEFER = 0x20,
+
+	AUX_TRANSACTION_REPLY_HPD_DISCON = 0x40,
+
+	AUX_TRANSACTION_REPLY_INVALID = 0xFF
+};
+
+struct aux_reply_transaction_data {
+	enum aux_transaction_reply status;
+	uint32_t length;
+	uint8_t *data;
+};
+
 struct i2c_payload {
 	bool write;
 	uint8_t address;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
index b9e35d0474c6..b01488f710d5 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
@@ -26,49 +26,7 @@
 #ifndef __DAL_AUX_ENGINE_H__
 #define __DAL_AUX_ENGINE_H__
 
-enum aux_transaction_type {
-	AUX_TRANSACTION_TYPE_DP,
-	AUX_TRANSACTION_TYPE_I2C
-};
-
-struct aux_request_transaction_data {
-	enum aux_transaction_type type;
-	enum i2caux_transaction_action action;
-	/* 20-bit AUX channel transaction address */
-	uint32_t address;
-	/* delay, in 100-microsecond units */
-	uint8_t delay;
-	uint32_t length;
-	uint8_t *data;
-};
-
-enum aux_transaction_reply {
-	AUX_TRANSACTION_REPLY_AUX_ACK = 0x00,
-	AUX_TRANSACTION_REPLY_AUX_NACK = 0x01,
-	AUX_TRANSACTION_REPLY_AUX_DEFER = 0x02,
-
-	AUX_TRANSACTION_REPLY_I2C_ACK = 0x00,
-	AUX_TRANSACTION_REPLY_I2C_NACK = 0x10,
-	AUX_TRANSACTION_REPLY_I2C_DEFER = 0x20,
-
-	AUX_TRANSACTION_REPLY_HPD_DISCON = 0x40,
-
-	AUX_TRANSACTION_REPLY_INVALID = 0xFF
-};
-
-struct aux_reply_transaction_data {
-	enum aux_transaction_reply status;
-	uint32_t length;
-	uint8_t *data;
-};
-
-enum aux_channel_operation_result {
-	AUX_CHANNEL_OPERATION_SUCCEEDED,
-	AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN,
-	AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY,
-	AUX_CHANNEL_OPERATION_FAILED_TIMEOUT,
-	AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON
-};
+#include "dc_ddc_types.h"
 
 struct aux_engine;
 
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
index c1109706a880..1e8a1585e401 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
@@ -26,6 +26,8 @@
 #ifndef __DAL_ENGINE_H__
 #define __DAL_ENGINE_H__
 
+#include "dc_ddc_types.h"
+
 enum i2caux_transaction_operation {
 	I2CAUX_TRANSACTION_READ,
 	I2CAUX_TRANSACTION_WRITE
@@ -76,19 +78,6 @@ enum i2c_default_speed {
 	I2CAUX_DEFAULT_I2C_SW_SPEED = 50
 };
 
-enum i2caux_transaction_action {
-	I2CAUX_TRANSACTION_ACTION_I2C_WRITE = 0x00,
-	I2CAUX_TRANSACTION_ACTION_I2C_READ = 0x10,
-	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST = 0x20,
-
-	I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT = 0x40,
-	I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT = 0x50,
-	I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT = 0x60,
-
-	I2CAUX_TRANSACTION_ACTION_DP_WRITE = 0x80,
-	I2CAUX_TRANSACTION_ACTION_DP_READ = 0x90
-};
-
 struct engine;
 
 struct engine_funcs {
-- 
cgit v1.2.3


From a10dc97ab8e9b5560fc47d57d2048c7455774472 Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Thu, 17 May 2018 14:50:12 -0400
Subject: drm/amd/display: Add use_dynamic_meta flag to stream_state

Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 3 ++-
 drivers/gpu/drm/amd/display/dc/dc_stream.h        | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 1d716171e581..fca22550417a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -2506,7 +2506,8 @@ static void set_hdr_static_info_packet(
 {
 	/* HDR Static Metadata info packet for HDR10 */
 
-	if (!stream->hdr_static_metadata.valid)
+	if (!stream->hdr_static_metadata.valid ||
+			stream->use_dynamic_meta)
 		return;
 
 	*info_packet = stream->hdr_static_metadata;
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index e6e944423b3c..065450c445c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -60,6 +60,7 @@ struct dc_stream_state {
 
 	struct dc_info_packet hdr_static_metadata;
 	PHYSICAL_ADDRESS_LOC dmdata_address;
+	bool   use_dynamic_meta;
 
 	struct dc_transfer_func *out_transfer_func;
 	struct colorspace_transform gamut_remap_matrix;
-- 
cgit v1.2.3


From 2cbe6d9be5a4ea5a6aff064a3bcca2ef92921993 Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Wed, 30 May 2018 10:56:32 -0400
Subject: drm/amd/display: Drop duplicate dc_stream_set_static_screen_events
 definition

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_stream.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 065450c445c5..af503e0286a7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -302,9 +302,4 @@ bool dc_stream_get_crtc_position(struct dc *dc,
 				 unsigned int *v_pos,
 				 unsigned int *nom_v_pos);
 
-void dc_stream_set_static_screen_events(struct dc *dc,
-					struct dc_stream_state **stream,
-					int num_streams,
-					const struct dc_static_screen_events *events);
-
 #endif /* DC_STREAM_H_ */
-- 
cgit v1.2.3


From 6f0db2dc02def18ee6fb93f408a847077addb4fc Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Wed, 30 May 2018 10:57:32 -0400
Subject: drm/amd/display: Make it more clear when info frames affect DP or
 HDMI

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 1dd2ae46d505..353ffcbdf5ba 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -665,16 +665,25 @@ static enum dc_status bios_parser_crtc_source_select(
 
 void dce110_update_info_frame(struct pipe_ctx *pipe_ctx)
 {
+	bool is_hdmi;
+	bool is_dp;
+
 	ASSERT(pipe_ctx->stream);
 
 	if (pipe_ctx->stream_res.stream_enc == NULL)
 		return;  /* this is not root pipe */
 
-	if (dc_is_hdmi_signal(pipe_ctx->stream->signal))
+	is_hdmi = dc_is_hdmi_signal(pipe_ctx->stream->signal);
+	is_dp = dc_is_dp_signal(pipe_ctx->stream->signal);
+
+	if (!is_hdmi && !is_dp)
+		return;
+
+	if (is_hdmi)
 		pipe_ctx->stream_res.stream_enc->funcs->update_hdmi_info_packets(
 			pipe_ctx->stream_res.stream_enc,
 			&pipe_ctx->stream_res.encoder_info_frame);
-	else if (dc_is_dp_signal(pipe_ctx->stream->signal))
+	else
 		pipe_ctx->stream_res.stream_enc->funcs->update_dp_info_packets(
 			pipe_ctx->stream_res.stream_enc,
 			&pipe_ctx->stream_res.encoder_info_frame);
-- 
cgit v1.2.3


From b73552323a5d089ab29342803f04fb32b0a0a2a5 Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Wed, 30 May 2018 10:59:11 -0400
Subject: drm/amd/display: Convert quotes to Ascii quotes

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index 32a4997714c1..c6a13d0486bb 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -301,7 +301,7 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	/* For YCbCr420 and BT2020 Colorimetry Formats, VSC SDP shall be used.
 	 * When MISC1, bit 6, is Set to 1, a Source device uses a VSC SDP to indicate the
 	 * Pixel Encoding/Colorimetry Format and that a Sink device shall ignore MISC1, bit 7,
-	 * and MISC0, bits 7:1 (MISC1, bit 7, and MISC0, bits 7:1, become “don’t care”).
+	 * and MISC0, bits 7:1 (MISC1, bit 7, and MISC0, bits 7:1, become "don't care").
 	 */
 	if ((crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420) ||
 			(output_color_space == COLOR_SPACE_2020_YCBCR) ||
-- 
cgit v1.2.3


From 6aa57bb8e4d47b442c01f5cf361d7b0efe619f6c Mon Sep 17 00:00:00 2001
From: Anthony Koo <Anthony.Koo@amd.com>
Date: Thu, 24 May 2018 11:25:00 -0400
Subject: drm/amd/display: Disable stats by default

Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/modules/stats/stats.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/modules/stats/stats.c b/drivers/gpu/drm/amd/display/modules/stats/stats.c
index fa0665d09075..480eb2cdd55d 100644
--- a/drivers/gpu/drm/amd/display/modules/stats/stats.c
+++ b/drivers/gpu/drm/amd/display/modules/stats/stats.c
@@ -29,7 +29,7 @@
 #include "core_types.h"
 
 #define DAL_STATS_ENABLE_REGKEY			"DalStatsEnable"
-#define DAL_STATS_ENABLE_REGKEY_DEFAULT		0x00000001
+#define DAL_STATS_ENABLE_REGKEY_DEFAULT		0x00000000
 #define DAL_STATS_ENABLE_REGKEY_ENABLED		0x00000001
 
 #define DAL_STATS_ENTRIES_REGKEY		"DalStatsEntries"
-- 
cgit v1.2.3


From 74167ad60c04c45e991af59ee5c7f62aff5c4c38 Mon Sep 17 00:00:00 2001
From: Vitaly Prosyak <vitaly.prosyak@amd.com>
Date: Fri, 25 May 2018 08:37:36 -0500
Subject: drm/amd/display: Add new transfer type HWPWL

It is used when curve register settings are generated
by 'matlab', i.e. bypass color module calculation.

Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index f09fa4722fc9..9954d0eadfbc 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -357,6 +357,7 @@ enum dc_transfer_func_type {
 	TF_TYPE_PREDEFINED,
 	TF_TYPE_DISTRIBUTED_POINTS,
 	TF_TYPE_BYPASS,
+	TF_TYPE_HWPWL
 };
 
 struct dc_transfer_func_distributed_points {
@@ -382,12 +383,15 @@ enum dc_transfer_func_predefined {
 
 struct dc_transfer_func {
 	struct kref refcount;
-	struct dc_transfer_func_distributed_points tf_pts;
 	enum dc_transfer_func_type type;
 	enum dc_transfer_func_predefined tf;
 	/* FP16 1.0 reference level in nits, default is 80 nits, only for PQ*/
 	uint32_t sdr_ref_white_level;
 	struct dc_context *ctx;
+	union {
+		struct pwl_params pwl;
+		struct dc_transfer_func_distributed_points tf_pts;
+	};
 };
 
 /*
-- 
cgit v1.2.3


From ce3f6e82249cccbbfd919ad30d256ec62d06b4af Mon Sep 17 00:00:00 2001
From: Alvin lee <alvin.lee3@amd.com>
Date: Fri, 18 May 2018 14:14:38 -0400
Subject: drm/amd/display: create sink_id in dc_sink structure to idenitify all
 sinks

Signed-off-by: Alvin lee <alvin.lee3@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c      | 1 +
 drivers/gpu/drm/amd/display/dc/core/dc_sink.c | 4 ++++
 drivers/gpu/drm/amd/display/dc/dc.h           | 6 +++++-
 drivers/gpu/drm/amd/display/dc/dc_types.h     | 1 +
 4 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 2c05630e78fb..53ce7fa864b4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -481,6 +481,7 @@ static bool construct(struct dc *dc,
 	dc_ctx->driver_context = init_params->driver;
 	dc_ctx->dc = dc;
 	dc_ctx->asic_id = init_params->asic_id;
+	dc_ctx->dc_sink_id_count = 0;
 	dc->ctx = dc_ctx;
 
 	dc->current_state = dc_create_state();
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
index 25fae38409ab..9971b515c3eb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_sink.c
@@ -53,6 +53,10 @@ static bool construct(struct dc_sink *sink, const struct dc_sink_init_data *init
 	sink->dongle_max_pix_clk = init_params->dongle_max_pix_clk;
 	sink->converter_disable_audio = init_params->converter_disable_audio;
 	sink->dc_container_id = NULL;
+	sink->sink_id = init_params->link->ctx->dc_sink_id_count;
+	// increment dc_sink_id_count because we don't want two sinks with same ID
+	// unless they are actually the same
+	init_params->link->ctx->dc_sink_id_count++;
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 9954d0eadfbc..7ebce7669eea 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -666,9 +666,13 @@ struct dc_sink {
 	struct dc_link *link;
 	struct dc_context *ctx;
 
+	uint32_t sink_id;
+
 	/* private to dc_sink.c */
+	// refcount must be the last member in dc_sink, since we want the
+	// sink structure to be logically cloneable up to (but not including)
+	// refcount
 	struct kref refcount;
-
 };
 
 void dc_sink_retain(struct dc_sink *sink);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index e026ce5ac78f..c96e526d07bb 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -92,6 +92,7 @@ struct dc_context {
 	bool created_bios;
 	struct gpio_service *gpio_service;
 	struct i2caux *i2caux;
+	uint32_t dc_sink_id_count;
 	uint64_t fbc_gpu_addr;
 };
 
-- 
cgit v1.2.3


From 12036586a368b8c949d4e6e57ae3b40c41daf17a Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Fri, 25 May 2018 11:57:26 -0400
Subject: drm/amd/display: Allow DP register double buffer

Remove setting DP_DB_DISABLE to avoid issues when changing
bit depth after vbios take over.
Refactor code to perform single register update for both
pixel encoding and component depth fields.

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dce/dce_stream_encoder.c    |  5 ---
 .../amd/display/dc/dcn10/dcn10_stream_encoder.c    | 44 ++++++++++------------
 2 files changed, 19 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index c0e813c7ddd4..91642e684858 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -289,11 +289,6 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 
 	struct dce110_stream_encoder *enc110 = DCE110STRENC_FROM_STRENC(enc);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	if (REG(DP_DB_CNTL))
-		REG_UPDATE(DP_DB_CNTL, DP_DB_DISABLE, 1);
-#endif
-
 	/* set pixel encoding */
 	switch (crtc_timing->pixel_encoding) {
 	case PIXEL_ENCODING_YCBCR422:
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
index c6a13d0486bb..6f9078f3c4d3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_stream_encoder.c
@@ -257,20 +257,18 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	uint8_t colorimetry_bpc;
 	uint8_t dynamic_range_rgb = 0; /*full range*/
 	uint8_t dynamic_range_ycbcr = 1; /*bt709*/
+	uint8_t dp_pixel_encoding = 0;
+	uint8_t dp_component_depth = 0;
 
 	struct dcn10_stream_encoder *enc1 = DCN10STRENC_FROM_STRENC(enc);
 
-	REG_UPDATE(DP_DB_CNTL, DP_DB_DISABLE, 1);
-
 	/* set pixel encoding */
 	switch (crtc_timing->pixel_encoding) {
 	case PIXEL_ENCODING_YCBCR422:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_YCBCR422);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_YCBCR422;
 		break;
 	case PIXEL_ENCODING_YCBCR444:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_YCBCR444);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_YCBCR444;
 
 		if (crtc_timing->flags.Y_ONLY)
 			if (crtc_timing->display_color_depth != COLOR_DEPTH_666)
@@ -278,8 +276,8 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 				 * Color depth of Y-only could be
 				 * 8, 10, 12, 16 bits
 				 */
-				REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-						DP_PIXEL_ENCODING_TYPE_Y_ONLY);
+				dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_Y_ONLY;
+
 		/* Note: DP_MSA_MISC1 bit 7 is the indicator
 		 * of Y-only mode.
 		 * This bit is set in HW if register
@@ -287,13 +285,11 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 		 */
 		break;
 	case PIXEL_ENCODING_YCBCR420:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_YCBCR420);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_YCBCR420;
 		REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
 		break;
 	default:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_PIXEL_ENCODING,
-				DP_PIXEL_ENCODING_TYPE_RGB444);
+		dp_pixel_encoding = DP_PIXEL_ENCODING_TYPE_RGB444;
 		break;
 	}
 
@@ -314,32 +310,30 @@ void enc1_stream_encoder_dp_set_stream_attribute(
 	/* set color depth */
 	switch (crtc_timing->display_color_depth) {
 	case COLOR_DEPTH_666:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				0);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_6BPC;
 		break;
 	case COLOR_DEPTH_888:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_8BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_8BPC;
 		break;
 	case COLOR_DEPTH_101010:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_10BPC);
-
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_10BPC;
 		break;
 	case COLOR_DEPTH_121212:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_12BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_12BPC;
 		break;
 	case COLOR_DEPTH_161616:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_16BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_16BPC;
 		break;
 	default:
-		REG_UPDATE(DP_PIXEL_FORMAT, DP_COMPONENT_DEPTH,
-				DP_COMPONENT_PIXEL_DEPTH_6BPC);
+		dp_component_depth = DP_COMPONENT_PIXEL_DEPTH_6BPC;
 		break;
 	}
 
+	/* Set DP pixel encoding and component depth */
+	REG_UPDATE_2(DP_PIXEL_FORMAT,
+			DP_PIXEL_ENCODING, dp_pixel_encoding,
+			DP_COMPONENT_DEPTH, dp_component_depth);
+
 	/* set dynamic range and YCbCr range */
 
 	switch (crtc_timing->display_color_depth) {
-- 
cgit v1.2.3


From e9522309efb31423a450c32f433dd95bfb8b5787 Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Fri, 18 May 2018 10:49:33 -0400
Subject: drm/amd/display: Add num_opp to resource_caps

Number of OPPs to be instantiated is based on number
of timing generators, not number of pipes.

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 1 +
 drivers/gpu/drm/amd/display/dc/inc/resource.h         | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 99c223bcad71..2da325ce781b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -417,6 +417,7 @@ static const struct dce110_clk_src_mask cs_mask = {
 
 static const struct resource_caps res_cap = {
 		.num_timing_generator = 4,
+		.num_opp = 4,
 		.num_video_plane = 4,
 		.num_audio = 4,
 		.num_stream_encoder = 4,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h
index 640a647f4611..e92facbd038f 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/resource.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h
@@ -38,6 +38,7 @@ enum dce_version resource_parse_asic_id(
 
 struct resource_caps {
 	int num_timing_generator;
+	int num_opp;
 	int num_video_plane;
 	int num_audio;
 	int num_stream_encoder;
-- 
cgit v1.2.3


From 85ee15d6a3d3c55e3e653426cc32e138ee515585 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Mon, 28 May 2018 10:08:30 -0400
Subject: drm/amd/display: Do not skip FBC init in failsafe mode

Initially FBC would be initialized if display's edid was correct
and all the modes acquired from it, but n case when edid is corrupted
or non-existant we must still initialize FBC.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index b1b8d1914b31..a1c912bc959a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3425,12 +3425,12 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
 
 	encoder = helper->best_encoder(connector);
 
-	if (!edid || !drm_edid_is_valid(edid))
-		return drm_add_modes_noedid(connector, 640, 480);
-
-	amdgpu_dm_connector_ddc_get_modes(connector, edid);
-	amdgpu_dm_connector_add_common_modes(encoder, connector);
-
+	if (!edid || !drm_edid_is_valid(edid)) {
+		drm_add_modes_noedid(connector, 640, 480);
+	} else {
+		amdgpu_dm_connector_ddc_get_modes(connector, edid);
+		amdgpu_dm_connector_add_common_modes(encoder, connector);
+	}
 	amdgpu_dm_fbc_init(connector);
 
 	return amdgpu_dm_connector->num_modes;
-- 
cgit v1.2.3


From 042ed2dbe5b294e6c225e12d380062ee6adb3ac0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 15 Jun 2018 10:31:36 +0100
Subject: drm/i915: Be irqsafe inside reset

As we want to be able to call i915_reset_engine and co from a softirq or
timer context, we need to be irqsafe at all times. So we have to forgo
the simple spin_lock_irq for the full spin_lock_irqsave.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615093137.14270-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 977982a987c8..5155e458b11e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3166,15 +3166,17 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 		 */
 		request = i915_gem_find_active_request(engine);
 		if (request) {
+			unsigned long flags;
+
 			i915_gem_context_mark_innocent(request->gem_context);
 			dma_fence_set_error(&request->fence, -EAGAIN);
 
 			/* Rewind the engine to replay the incomplete rq */
-			spin_lock_irq(&engine->timeline.lock);
+			spin_lock_irqsave(&engine->timeline.lock, flags);
 			request = list_prev_entry(request, link);
 			if (&request->link == &engine->timeline.requests)
 				request = NULL;
-			spin_unlock_irq(&engine->timeline.lock);
+			spin_unlock_irqrestore(&engine->timeline.lock, flags);
 		}
 	}
 
-- 
cgit v1.2.3


From b2209e62a4507f6649233eaf0675de3ad86bd868 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 15 Jun 2018 10:31:37 +0100
Subject: drm/i915/execlists: Reset the CSB head tracking on reset/sanitization

We can avoid the mmio read of the CSB pointers after reset based on the
knowledge that the HW always start writing at entry 0 in the CSB buffer.
We need to reset our CSB head tracking after GPU reset (and on
sanitization after resume) so that we are expecting to read from entry
0, hence we reset our head tracking back to the entry before (the last
entry in the ring).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615093137.14270-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 8d56bcb00979..50e141ca1f7a 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -971,22 +971,19 @@ static void process_csb(struct intel_engine_cs *engine)
 			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
 		unsigned int head, tail;
 
-		if (unlikely(execlists->csb_use_mmio)) {
-			buf = (u32 * __force)
-				(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
-			execlists->csb_head = -1; /* force mmio read of CSB */
-		}
-
 		/* Clear before reading to catch new interrupts */
 		clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 		smp_mb__after_atomic();
 
-		if (unlikely(execlists->csb_head == -1)) { /* after a reset */
+		if (unlikely(execlists->csb_use_mmio)) {
 			if (!fw) {
 				intel_uncore_forcewake_get(i915, execlists->fw_domains);
 				fw = true;
 			}
 
+			buf = (u32 * __force)
+				(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+
 			head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
 			tail = GEN8_CSB_WRITE_PTR(head);
 			head = GEN8_CSB_READ_PTR(head);
@@ -1961,7 +1958,7 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	spin_unlock(&engine->timeline.lock);
 
 	/* Following the reset, we need to reload the CSB read/write pointers */
-	engine->execlists.csb_head = -1;
+	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
 
 	local_irq_restore(flags);
 
@@ -2469,7 +2466,7 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 			upper_32_bits(ce->lrc_desc);
 	}
 
-	engine->execlists.csb_head = -1;
+	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
 
 	return 0;
 
-- 
cgit v1.2.3


From 1c0f1b3db7a647ef8962fb4186105e91710a3ade Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 14 Jun 2018 21:05:00 +0300
Subject: drm/i915: s/IS_G4X && !IS_GM45/IS_G45/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have IS_G45 these days. Let's use it instead of the
'IS_G4X && !IS_GM45' construct.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614180500.2565-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_crt.c  | 2 +-
 drivers/gpu/drm/i915/intel_dp.c   | 2 +-
 drivers/gpu/drm/i915/intel_hdmi.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 87c72c39f409..a1ddd9f62bb8 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -517,7 +517,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 	 * to get a reliable result.
 	 */
 
-	if (IS_G4X(dev_priv) && !IS_GM45(dev_priv))
+	if (IS_G45(dev_priv))
 		tries = 2;
 	else
 		tries = 1;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index afa0574c1908..6ac6c8787dcf 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -6421,7 +6421,7 @@ intel_dp_init_connector(struct intel_digital_port *intel_dig_port,
 	 * 0xd.  Failure to do so will result in spurious interrupts being
 	 * generated on the port when a cable is not attached.
 	 */
-	if (IS_G4X(dev_priv) && !IS_GM45(dev_priv)) {
+	if (IS_G45(dev_priv)) {
 		u32 temp = I915_READ(PEG_BAND_GAP_DATA);
 		I915_WRITE(PEG_BAND_GAP_DATA, (temp & ~0xf) | 0xd);
 	}
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 9a33432c1f6b..3dd3ee259e7f 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -2341,7 +2341,7 @@ void intel_hdmi_init_connector(struct intel_digital_port *intel_dig_port,
 	 * 0xd.  Failure to do so will result in spurious interrupts being
 	 * generated on the port when a cable is not attached.
 	 */
-	if (IS_G4X(dev_priv) && !IS_GM45(dev_priv)) {
+	if (IS_G45(dev_priv)) {
 		u32 temp = I915_READ(PEG_BAND_GAP_DATA);
 		I915_WRITE(PEG_BAND_GAP_DATA, (temp & ~0xf) | 0xd);
 	}
-- 
cgit v1.2.3


From b6f690ab237d801cbf881be4bc164062727053fd Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 11 Jun 2018 22:34:01 +0300
Subject: drm/atomic: Improve debug messages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Print the id/name of the object we're dealing with. Makes it easier to
figure out what's going on. Also toss in a few extra debug prints that
might be useful.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611193403.16118-1-ville.syrjala@linux.intel.com
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
---
 drivers/gpu/drm/drm_atomic.c | 88 ++++++++++++++++++++++++++++++--------------
 1 file changed, 61 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 11059d556dbd..0ae280aaa124 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -331,6 +331,7 @@ static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
 int drm_atomic_set_mode_for_crtc(struct drm_crtc_state *state,
 				 const struct drm_display_mode *mode)
 {
+	struct drm_crtc *crtc = state->crtc;
 	struct drm_mode_modeinfo umode;
 
 	/* Early return for no change. */
@@ -351,13 +352,13 @@ int drm_atomic_set_mode_for_crtc(struct drm_crtc_state *state,
 
 		drm_mode_copy(&state->mode, mode);
 		state->enable = true;
-		DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
-				 mode->name, state);
+		DRM_DEBUG_ATOMIC("Set [MODE:%s] for [CRTC:%d:%s] state %p\n",
+				 mode->name, crtc->base.id, crtc->name, state);
 	} else {
 		memset(&state->mode, 0, sizeof(state->mode));
 		state->enable = false;
-		DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
-				 state);
+		DRM_DEBUG_ATOMIC("Set [NOMODE] for [CRTC:%d:%s] state %p\n",
+				 crtc->base.id, crtc->name, state);
 	}
 
 	return 0;
@@ -380,6 +381,8 @@ EXPORT_SYMBOL(drm_atomic_set_mode_for_crtc);
 int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
                                       struct drm_property_blob *blob)
 {
+	struct drm_crtc *crtc = state->crtc;
+
 	if (blob == state->mode_blob)
 		return 0;
 
@@ -396,12 +399,13 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 
 		state->mode_blob = drm_property_blob_get(blob);
 		state->enable = true;
-		DRM_DEBUG_ATOMIC("Set [MODE:%s] for CRTC state %p\n",
-				 state->mode.name, state);
+		DRM_DEBUG_ATOMIC("Set [MODE:%s] for [CRTC:%d:%s] state %p\n",
+				 state->mode.name, crtc->base.id, crtc->name,
+				 state);
 	} else {
 		state->enable = false;
-		DRM_DEBUG_ATOMIC("Set [NOMODE] for CRTC state %p\n",
-				 state);
+		DRM_DEBUG_ATOMIC("Set [NOMODE] for [CRTC:%d:%s] state %p\n",
+				 crtc->base.id, crtc->name, state);
 	}
 
 	return 0;
@@ -531,10 +535,14 @@ int drm_atomic_crtc_set_property(struct drm_crtc *crtc,
 			return -EFAULT;
 
 		set_out_fence_for_crtc(state->state, crtc, fence_ptr);
-	} else if (crtc->funcs->atomic_set_property)
+	} else if (crtc->funcs->atomic_set_property) {
 		return crtc->funcs->atomic_set_property(crtc, state, property, val);
-	else
+	} else {
+		DRM_DEBUG_ATOMIC("[CRTC:%d:%s] unknown property [PROP:%d:%s]]\n",
+				 crtc->base.id, crtc->name,
+				 property->base.id, property->name);
 		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -791,8 +799,11 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane,
 	} else if (property == plane->alpha_property) {
 		state->alpha = val;
 	} else if (property == plane->rotation_property) {
-		if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK))
+		if (!is_power_of_2(val & DRM_MODE_ROTATE_MASK)) {
+			DRM_DEBUG_ATOMIC("[PLANE:%d:%s] bad rotation bitmask: 0x%llx\n",
+					 plane->base.id, plane->name, val);
 			return -EINVAL;
+		}
 		state->rotation = val;
 	} else if (property == plane->zpos_property) {
 		state->zpos = val;
@@ -804,6 +815,9 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane,
 		return plane->funcs->atomic_set_property(plane, state,
 				property, val);
 	} else {
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] unknown property [PROP:%d:%s]]\n",
+				 plane->base.id, plane->name,
+				 property->base.id, property->name);
 		return -EINVAL;
 	}
 
@@ -911,10 +925,12 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 
 	/* either *both* CRTC and FB must be set, or neither */
 	if (state->crtc && !state->fb) {
-		DRM_DEBUG_ATOMIC("CRTC set but no FB\n");
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] CRTC set but no FB\n",
+				 plane->base.id, plane->name);
 		return -EINVAL;
 	} else if (state->fb && !state->crtc) {
-		DRM_DEBUG_ATOMIC("FB set but no CRTC\n");
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] FB set but no CRTC\n",
+				 plane->base.id, plane->name);
 		return -EINVAL;
 	}
 
@@ -924,7 +940,9 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 
 	/* Check whether this plane is usable on this CRTC */
 	if (!(plane->possible_crtcs & drm_crtc_mask(state->crtc))) {
-		DRM_DEBUG_ATOMIC("Invalid crtc for plane\n");
+		DRM_DEBUG_ATOMIC("Invalid [CRTC:%d:%s] for [PLANE:%d:%s]\n",
+				 state->crtc->base.id, state->crtc->name,
+				 plane->base.id, plane->name);
 		return -EINVAL;
 	}
 
@@ -933,7 +951,8 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 					   state->fb->modifier);
 	if (ret) {
 		struct drm_format_name_buf format_name;
-		DRM_DEBUG_ATOMIC("Invalid pixel format %s, modifier 0x%llx\n",
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] invalid pixel format %s, modifier 0x%llx\n",
+				 plane->base.id, plane->name,
 				 drm_get_format_name(state->fb->format->format,
 						     &format_name),
 				 state->fb->modifier);
@@ -945,7 +964,8 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 	    state->crtc_x > INT_MAX - (int32_t) state->crtc_w ||
 	    state->crtc_h > INT_MAX ||
 	    state->crtc_y > INT_MAX - (int32_t) state->crtc_h) {
-		DRM_DEBUG_ATOMIC("Invalid CRTC coordinates %ux%u+%d+%d\n",
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] invalid CRTC coordinates %ux%u+%d+%d\n",
+				 plane->base.id, plane->name,
 				 state->crtc_w, state->crtc_h,
 				 state->crtc_x, state->crtc_y);
 		return -ERANGE;
@@ -959,8 +979,9 @@ static int drm_atomic_plane_check(struct drm_plane *plane,
 	    state->src_x > fb_width - state->src_w ||
 	    state->src_h > fb_height ||
 	    state->src_y > fb_height - state->src_h) {
-		DRM_DEBUG_ATOMIC("Invalid source coordinates "
+		DRM_DEBUG_ATOMIC("[PLANE:%d:%s] invalid source coordinates "
 				 "%u.%06ux%u.%06u+%u.%06u+%u.%06u (fb %ux%u)\n",
+				 plane->base.id, plane->name,
 				 state->src_w >> 16, ((state->src_w & 0xffff) * 15625) >> 10,
 				 state->src_h >> 16, ((state->src_h & 0xffff) * 15625) >> 10,
 				 state->src_x >> 16, ((state->src_x & 0xffff) * 15625) >> 10,
@@ -1289,6 +1310,9 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 		return connector->funcs->atomic_set_property(connector,
 				state, property, val);
 	} else {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] unknown property [PROP:%d:%s]]\n",
+				 connector->base.id, connector->name,
+				 property->base.id, property->name);
 		return -EINVAL;
 	}
 
@@ -1457,11 +1481,12 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state,
 	}
 
 	if (crtc)
-		DRM_DEBUG_ATOMIC("Link plane state %p to [CRTC:%d:%s]\n",
-				 plane_state, crtc->base.id, crtc->name);
+		DRM_DEBUG_ATOMIC("Link [PLANE:%d:%s] state %p to [CRTC:%d:%s]\n",
+				 plane->base.id, plane->name, plane_state,
+				 crtc->base.id, crtc->name);
 	else
-		DRM_DEBUG_ATOMIC("Link plane state %p to [NOCRTC]\n",
-				 plane_state);
+		DRM_DEBUG_ATOMIC("Link [PLANE:%d:%s] state %p to [NOCRTC]\n",
+				 plane->base.id, plane->name, plane_state);
 
 	return 0;
 }
@@ -1481,12 +1506,15 @@ void
 drm_atomic_set_fb_for_plane(struct drm_plane_state *plane_state,
 			    struct drm_framebuffer *fb)
 {
+	struct drm_plane *plane = plane_state->plane;
+
 	if (fb)
-		DRM_DEBUG_ATOMIC("Set [FB:%d] for plane state %p\n",
-				 fb->base.id, plane_state);
-	else
-		DRM_DEBUG_ATOMIC("Set [NOFB] for plane state %p\n",
+		DRM_DEBUG_ATOMIC("Set [FB:%d] for [PLANE:%d:%s] state %p\n",
+				 fb->base.id, plane->base.id, plane->name,
 				 plane_state);
+	else
+		DRM_DEBUG_ATOMIC("Set [NOFB] for [PLANE:%d:%s] state %p\n",
+				 plane->base.id, plane->name, plane_state);
 
 	drm_framebuffer_assign(&plane_state->fb, fb);
 }
@@ -1547,6 +1575,7 @@ int
 drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 				  struct drm_crtc *crtc)
 {
+	struct drm_connector *connector = conn_state->connector;
 	struct drm_crtc_state *crtc_state;
 
 	if (conn_state->crtc == crtc)
@@ -1574,10 +1603,12 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 		drm_connector_get(conn_state->connector);
 		conn_state->crtc = crtc;
 
-		DRM_DEBUG_ATOMIC("Link connector state %p to [CRTC:%d:%s]\n",
+		DRM_DEBUG_ATOMIC("Link [CONNECTOR:%d:%s] state %p to [CRTC:%d:%s]\n",
+				 connector->base.id, connector->name,
 				 conn_state, crtc->base.id, crtc->name);
 	} else {
-		DRM_DEBUG_ATOMIC("Link connector state %p to [NOCRTC]\n",
+		DRM_DEBUG_ATOMIC("Link [CONNECTOR:%d:%s] state %p to [NOCRTC]\n",
+				 connector->base.id, connector->name,
 				 conn_state);
 	}
 
@@ -1673,6 +1704,9 @@ drm_atomic_add_affected_planes(struct drm_atomic_state *state,
 
 	WARN_ON(!drm_atomic_get_new_crtc_state(state, crtc));
 
+	DRM_DEBUG_ATOMIC("Adding all current planes for [CRTC:%d:%s] to %p\n",
+			 crtc->base.id, crtc->name, state);
+
 	drm_for_each_plane_mask(plane, state->dev, crtc->state->plane_mask) {
 		struct drm_plane_state *plane_state =
 			drm_atomic_get_plane_state(state, plane);
-- 
cgit v1.2.3


From 6ab0edf4e79c42e3dc9c47e060a68d337af51be0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 11 Jun 2018 22:34:02 +0300
Subject: drm: Print bad user modes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Print out the modeline when we reject a bad user mode. Avoids having to
guess why it was rejected.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611193403.16118-2-ville.syrjala@linux.intel.com
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
---
 drivers/gpu/drm/drm_atomic.c        | 20 +++++++++++++++++---
 drivers/gpu/drm/drm_crtc.c          |  4 +++-
 drivers/gpu/drm/drm_crtc_internal.h |  3 +++
 drivers/gpu/drm/drm_modes.c         |  2 +-
 4 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 0ae280aaa124..0fb25bfe381d 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -392,10 +392,24 @@ int drm_atomic_set_mode_prop_for_crtc(struct drm_crtc_state *state,
 	memset(&state->mode, 0, sizeof(state->mode));
 
 	if (blob) {
-		if (blob->length != sizeof(struct drm_mode_modeinfo) ||
-		    drm_mode_convert_umode(state->crtc->dev, &state->mode,
-					   blob->data))
+		int ret;
+
+		if (blob->length != sizeof(struct drm_mode_modeinfo)) {
+			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] bad mode blob length: %zu\n",
+					 crtc->base.id, crtc->name,
+					 blob->length);
+			return -EINVAL;
+		}
+
+		ret = drm_mode_convert_umode(crtc->dev,
+					     &state->mode, blob->data);
+		if (ret) {
+			DRM_DEBUG_ATOMIC("[CRTC:%d:%s] invalid mode (ret=%d, status=%s):\n",
+					 crtc->base.id, crtc->name,
+					 ret, drm_get_mode_status_name(state->mode.status));
+			drm_mode_debug_printmodeline(&state->mode);
 			return -EINVAL;
+		}
 
 		state->mode_blob = drm_property_blob_get(blob);
 		state->enable = true;
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 53828fc8d911..163d82ac7d76 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -649,7 +649,9 @@ retry:
 
 		ret = drm_mode_convert_umode(dev, mode, &crtc_req->mode);
 		if (ret) {
-			DRM_DEBUG_KMS("Invalid mode\n");
+			DRM_DEBUG_KMS("Invalid mode (ret=%d, status=%s)\n",
+				      ret, drm_get_mode_status_name(mode->status));
+			drm_mode_debug_printmodeline(mode);
 			goto out;
 		}
 
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 5d307b23a4e6..34499800932a 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -56,6 +56,9 @@ int drm_mode_setcrtc(struct drm_device *dev,
 int drm_modeset_register_all(struct drm_device *dev);
 void drm_modeset_unregister_all(struct drm_device *dev);
 
+/* drm_modes.c */
+const char *drm_get_mode_status_name(enum drm_mode_status status);
+
 /* IOCTLs */
 int drm_mode_getresources(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv);
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index c78ca0e84ffd..7f552d5fa88e 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1257,7 +1257,7 @@ static const char * const drm_mode_status_names[] = {
 
 #undef MODE_STATUS
 
-static const char *drm_get_mode_status_name(enum drm_mode_status status)
+const char *drm_get_mode_status_name(enum drm_mode_status status)
 {
 	int index = status + 3;
 
-- 
cgit v1.2.3


From e89ea355966182007712c396a3b8e78255f17c32 Mon Sep 17 00:00:00 2001
From: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Date: Wed, 30 May 2018 18:30:52 +0100
Subject: drm/atomic: Set current atomic state in drm_private_state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drm_private_state has a back pointer to the drm_atomic_state,
however that was not initialized in drm_atomic_get_private_obj_state
after duplication, as it is the case for other drm atomic getters

Signed-off-by: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1527701452-1934-1-git-send-email-alexandru-cosmin.gheorghe@arm.com
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/drm_atomic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 0fb25bfe381d..9ec5c865a043 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1152,6 +1152,7 @@ drm_atomic_get_private_obj_state(struct drm_atomic_state *state,
 	state->private_objs[index].old_state = obj->state;
 	state->private_objs[index].new_state = obj_state;
 	state->private_objs[index].ptr = obj;
+	obj_state->state = state;
 
 	state->num_private_objs = num_objs;
 
-- 
cgit v1.2.3


From 9378985eb05c486b32a61b69945df3297c6e854d Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Thu, 14 Jun 2018 15:10:17 -0700
Subject: drm/i915/icl: implement DVFS for ICL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ICL DVFS is almost the same as CNL, except for the CDCLK/DDICLK
table. Implement it just like CNL does.

References: commit 48469eced282 ("drm/i915: Use cdclk_state->voltage
 on CNL")
References: commit 53e9bf5e8159 ("drm/i915: Adjust system agent
 voltage on CNL if required by DDI ports")
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614221018.19044-1-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_cdclk.c | 46 +++++++++++++++++++++++++++++++++++---
 drivers/gpu/drm/i915/intel_ddi.c   |  2 ++
 2 files changed, 45 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index 8ed7bd052e46..bf9433d7964d 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -1871,11 +1871,35 @@ static void icl_set_cdclk(struct drm_i915_private *dev_priv,
 			      skl_cdclk_decimal(cdclk));
 
 	mutex_lock(&dev_priv->pcu_lock);
-	/* TODO: add proper DVFS support. */
-	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL, 2);
+	sandybridge_pcode_write(dev_priv, SKL_PCODE_CDCLK_CONTROL,
+				cdclk_state->voltage_level);
 	mutex_unlock(&dev_priv->pcu_lock);
 
 	intel_update_cdclk(dev_priv);
+
+	/*
+	 * Can't read out the voltage level :(
+	 * Let's just assume everything is as expected.
+	 */
+	dev_priv->cdclk.hw.voltage_level = cdclk_state->voltage_level;
+}
+
+static u8 icl_calc_voltage_level(int cdclk)
+{
+	switch (cdclk) {
+	case 50000:
+	case 307200:
+	case 312000:
+		return 0;
+	case 556800:
+	case 552000:
+		return 1;
+	default:
+		MISSING_CASE(cdclk);
+	case 652800:
+	case 648000:
+		return 2;
+	}
 }
 
 static void icl_get_cdclk(struct drm_i915_private *dev_priv,
@@ -1909,7 +1933,7 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 		 */
 		cdclk_state->vco = 0;
 		cdclk_state->cdclk = cdclk_state->bypass;
-		return;
+		goto out;
 	}
 
 	cdclk_state->vco = (val & BXT_DE_PLL_RATIO_MASK) * cdclk_state->ref;
@@ -1918,6 +1942,14 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 	WARN_ON((val & BXT_CDCLK_CD2X_DIV_SEL_MASK) != 0);
 
 	cdclk_state->cdclk = cdclk_state->vco / 2;
+
+out:
+	/*
+	 * Can't read this out :( Let's assume it's
+	 * at least what the CDCLK frequency requires.
+	 */
+	cdclk_state->voltage_level =
+		icl_calc_voltage_level(cdclk_state->cdclk);
 }
 
 /**
@@ -1960,6 +1992,8 @@ sanitize:
 	sanitized_state.cdclk = icl_calc_cdclk(0, sanitized_state.ref);
 	sanitized_state.vco = icl_calc_cdclk_pll_vco(dev_priv,
 						     sanitized_state.cdclk);
+	sanitized_state.voltage_level =
+				icl_calc_voltage_level(sanitized_state.cdclk);
 
 	icl_set_cdclk(dev_priv, &sanitized_state);
 }
@@ -1977,6 +2011,7 @@ void icl_uninit_cdclk(struct drm_i915_private *dev_priv)
 
 	cdclk_state.cdclk = cdclk_state.bypass;
 	cdclk_state.vco = 0;
+	cdclk_state.voltage_level = icl_calc_voltage_level(cdclk_state.cdclk);
 
 	icl_set_cdclk(dev_priv, &cdclk_state);
 }
@@ -2480,6 +2515,9 @@ static int icl_modeset_calc_cdclk(struct drm_atomic_state *state)
 
 	intel_state->cdclk.logical.vco = vco;
 	intel_state->cdclk.logical.cdclk = cdclk;
+	intel_state->cdclk.logical.voltage_level =
+		max(icl_calc_voltage_level(cdclk),
+		    cnl_compute_min_voltage_level(intel_state));
 
 	if (!intel_state->active_crtcs) {
 		cdclk = icl_calc_cdclk(0, ref);
@@ -2487,6 +2525,8 @@ static int icl_modeset_calc_cdclk(struct drm_atomic_state *state)
 
 		intel_state->cdclk.actual.vco = vco;
 		intel_state->cdclk.actual.cdclk = cdclk;
+		intel_state->cdclk.actual.voltage_level =
+			icl_calc_voltage_level(cdclk);
 	} else {
 		intel_state->cdclk.actual = intel_state->cdclk.logical;
 	}
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index ce153b11c765..044fe1fb9872 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -3078,6 +3078,8 @@ void intel_ddi_compute_min_voltage_level(struct drm_i915_private *dev_priv,
 {
 	if (IS_CANNONLAKE(dev_priv) && crtc_state->port_clock > 594000)
 		crtc_state->min_voltage_level = 2;
+	else if (IS_ICELAKE(dev_priv) && crtc_state->port_clock > 594000)
+		crtc_state->min_voltage_level = 1;
 }
 
 void intel_ddi_get_config(struct intel_encoder *encoder,
-- 
cgit v1.2.3


From f677bd558de2e98b70b7f8c522024b26d2d1120d Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Thu, 14 Jun 2018 15:10:18 -0700
Subject: drm/i915/icl: update VBT's child_device_config flags2 field

Some bits from the flags2 field are going to be used in the next
patches, so replace the whole-byte definition with the actual bits and
document their versions.

This patch is based on a patch by Animesh Manna.

Cc: Animesh Manna <animesh.manna@intel.com>
Credits-to: Animesh Manna <animesh.manna@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614221018.19044-2-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_vbt_defs.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index c132d0c3a500..c614c9f3f28b 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -420,7 +420,9 @@ struct child_device_config {
 	u16 extended_type;
 	u8 dvo_function;
 	u8 dp_usb_type_c:1;					/* 195 */
-	u8 flags2_reserved:7;					/* 195 */
+	u8 tbt:1;						/* 209 */
+	u8 flags2_reserved:2;					/* 195 */
+	u8 dp_port_trace_length:4;				/* 209 */
 	u8 dp_gpio_index;					/* 195 */
 	u16 dp_gpio_pin_num;					/* 195 */
 	u8 dp_iboost_level:4;					/* 196 */
-- 
cgit v1.2.3


From ebfb081edc8afd250a6d290c37481bfb2262e7cb Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Wed, 23 May 2018 21:07:16 +0200
Subject: drm/rockchip: lvds: add missing of_node_put

The device node iterators perform an of_node_get on each iteration, so a
jump out of the loop requires an of_node_put.

The semantic patch that fixes this problem is as follows
(http://coccinelle.lip6.fr):

// <smpl>
@@
expression root,e;
local idexpression child;
iterator name for_each_child_of_node;
@@

 for_each_child_of_node(root, child) {
   ... when != of_node_put(child)
       when != e = child
+  of_node_put(child);
?  break;
   ...
}
... when != child
// </smpl>

Fixes: 34cc0aa25456 ("drm/rockchip: Add support for Rockchip Soc LVDS")
Cc: stable@vger.kernel.org
Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/1527102436-13447-6-git-send-email-Julia.Lawall@lip6.fr
---
 drivers/gpu/drm/rockchip/rockchip_lvds.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index 4bd94b167d2c..b3f6f524b402 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -363,8 +363,10 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		of_property_read_u32(endpoint, "reg", &endpoint_id);
 		ret = drm_of_find_panel_or_bridge(dev->of_node, 1, endpoint_id,
 						  &lvds->panel, &lvds->bridge);
-		if (!ret)
+		if (!ret) {
+			of_node_put(endpoint);
 			break;
+		}
 	}
 	if (!child_count) {
 		DRM_DEV_ERROR(dev, "lvds port does not have any children\n");
-- 
cgit v1.2.3


From 0baf5cc971fc21ff55d75183dd1fe3afb505bff8 Mon Sep 17 00:00:00 2001
From: Lin Huang <hl@rock-chips.com>
Date: Tue, 22 May 2018 16:53:41 +0800
Subject: drm/rockchip: cnd-dp: adjust spdif register setting

We use jitter bypass mode for spdif, so do not need to set jitter mode
related bit in SPDIF_CTRL_ADDR register. But of course we need to keep
the SPDIF_ENABLE bit.

Signed-off-by: Chris Zhong <zyw@rock-chips.com>
Signed-off-by: Lin Huang <hl@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/1526979222-32478-1-git-send-email-hl@rock-chips.com
---
 drivers/gpu/drm/rockchip/cdn-dp-reg.c | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/cdn-dp-reg.c b/drivers/gpu/drm/rockchip/cdn-dp-reg.c
index eb3042c6d1b2..3105965fc260 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-reg.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-reg.c
@@ -792,7 +792,6 @@ err_config_video:
 
 int cdn_dp_audio_stop(struct cdn_dp_device *dp, struct audio_info *audio)
 {
-	u32 val;
 	int ret;
 
 	ret = cdn_dp_reg_write(dp, AUDIO_PACK_CONTROL, 0);
@@ -801,11 +800,7 @@ int cdn_dp_audio_stop(struct cdn_dp_device *dp, struct audio_info *audio)
 		return ret;
 	}
 
-	val = SPDIF_AVG_SEL | SPDIF_JITTER_BYPASS;
-	val |= SPDIF_FIFO_MID_RANGE(0xe0);
-	val |= SPDIF_JITTER_THRSH(0xe0);
-	val |= SPDIF_JITTER_AVG_WIN(7);
-	writel(val, dp->regs + SPDIF_CTRL_ADDR);
+	writel(0, dp->regs + SPDIF_CTRL_ADDR);
 
 	/* clearn the audio config and reset */
 	writel(0, dp->regs + AUDIO_SRC_CNTL);
@@ -929,12 +924,6 @@ static void cdn_dp_audio_config_spdif(struct cdn_dp_device *dp)
 {
 	u32 val;
 
-	val = SPDIF_AVG_SEL | SPDIF_JITTER_BYPASS;
-	val |= SPDIF_FIFO_MID_RANGE(0xe0);
-	val |= SPDIF_JITTER_THRSH(0xe0);
-	val |= SPDIF_JITTER_AVG_WIN(7);
-	writel(val, dp->regs + SPDIF_CTRL_ADDR);
-
 	writel(SYNC_WR_TO_CH_ZERO, dp->regs + FIFO_CNTL);
 
 	val = MAX_NUM_CH(2) | AUDIO_TYPE_LPCM | CFG_SUB_PCKT_NUM(4);
@@ -942,9 +931,6 @@ static void cdn_dp_audio_config_spdif(struct cdn_dp_device *dp)
 	writel(SMPL2PKT_EN, dp->regs + SMPL2PKT_CNTL);
 
 	val = SPDIF_ENABLE | SPDIF_AVG_SEL | SPDIF_JITTER_BYPASS;
-	val |= SPDIF_FIFO_MID_RANGE(0xe0);
-	val |= SPDIF_JITTER_THRSH(0xe0);
-	val |= SPDIF_JITTER_AVG_WIN(7);
 	writel(val, dp->regs + SPDIF_CTRL_ADDR);
 
 	clk_prepare_enable(dp->spdif_clk);
-- 
cgit v1.2.3


From 9d72fe1ce81bc757ecb6d57b58e5fd95b9ad1b26 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 10 Jun 2018 19:45:32 +0200
Subject: EDAC, altera: Fix an error handling path in altr_s10_sdram_probe()

If regmap_write() fails, we should release some resources as done in all
the other error handling paths of the function.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Thor Thayer <thor.thayer@linux.intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/20180610174532.22071-1-christophe.jaillet@wanadoo.fr
Fixes: e9918d7fafae ("EDAC, altera: Handle SDRAM Uncorrectable Errors on Stratix10")
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/altera_edac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c
index d0d5c4dbe097..5762c3c383f2 100644
--- a/drivers/edac/altera_edac.c
+++ b/drivers/edac/altera_edac.c
@@ -730,7 +730,8 @@ static int altr_s10_sdram_probe(struct platform_device *pdev)
 			 S10_DDR0_IRQ_MASK)) {
 		edac_printk(KERN_ERR, EDAC_MC,
 			    "Error clearing SDRAM ECC count\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto err2;
 	}
 
 	if (regmap_update_bits(drvdata->mc_vbase, priv->ecc_irq_en_offset,
-- 
cgit v1.2.3


From 4708aa85d50cc6e962dfa8acf5ad4e0d290a21db Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 12 Jun 2018 14:43:34 +0200
Subject: EDAC: Fix memleak in module init error path

Make sure to use put_device() to free the initialised struct device so
that resources managed by driver core also gets released in the event of
a registration failure.

Signed-off-by: Johan Hovold <johan@kernel.org>
Cc: Denis Kirjanov <kirjanov@gmail.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Fixes: 2d56b109e3a5 ("EDAC: Handle error path in edac_mc_sysfs_init() properly")
Link: http://lkml.kernel.org/r/20180612124335.6420-1-johan@kernel.org
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/edac_mc_sysfs.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 7481955160a4..20374b8248f0 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -1075,14 +1075,14 @@ int __init edac_mc_sysfs_init(void)
 
 	err = device_add(mci_pdev);
 	if (err < 0)
-		goto out_dev_free;
+		goto out_put_device;
 
 	edac_dbg(0, "device %s created\n", dev_name(mci_pdev));
 
 	return 0;
 
- out_dev_free:
-	kfree(mci_pdev);
+ out_put_device:
+	put_device(mci_pdev);
  out:
 	return err;
 }
-- 
cgit v1.2.3


From 7279d9917560bbd0d82813d6bf00490a82c06783 Mon Sep 17 00:00:00 2001
From: Nadav Amit <namit@vmware.com>
Date: Mon, 4 Jun 2018 06:58:14 -0700
Subject: gpio: Fix wrong rounding in gpio-menz127

men_z127_debounce() tries to round up and down, but uses functions which
are only suitable when the divider is a power of two, which is not the
case. Use the appropriate ones.

Found by static check. Compile tested.

Fixes: f436bc2726c64 ("gpio: add driver for MEN 16Z127 GPIO controller")
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-menz127.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-menz127.c b/drivers/gpio/gpio-menz127.c
index e1037582e34d..b2635326546e 100644
--- a/drivers/gpio/gpio-menz127.c
+++ b/drivers/gpio/gpio-menz127.c
@@ -56,9 +56,9 @@ static int men_z127_debounce(struct gpio_chip *gc, unsigned gpio,
 		rnd = fls(debounce) - 1;
 
 		if (rnd && (debounce & BIT(rnd - 1)))
-			debounce = round_up(debounce, MEN_Z127_DB_MIN_US);
+			debounce = roundup(debounce, MEN_Z127_DB_MIN_US);
 		else
-			debounce = round_down(debounce, MEN_Z127_DB_MIN_US);
+			debounce = rounddown(debounce, MEN_Z127_DB_MIN_US);
 
 		if (debounce > MEN_Z127_DB_MAX_US)
 			debounce = MEN_Z127_DB_MAX_US;
-- 
cgit v1.2.3


From 29d43c22e480b150e00f1ac28a6653efca31cce4 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Fri, 1 Jun 2018 23:13:47 +0300
Subject: gpio-rcar: document R8A77980 bindings

Renesas R-Car V3H (R8A77980) SoC also has the R-Car gen3 compatible GPIO
controllers, so document the SoC specific bindings.

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index 378f1322211e..cd5ccdc5e66f 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -17,6 +17,7 @@ Required Properties:
     - "renesas,gpio-r8a7796": for R8A7796 (R-Car M3-W) compatible GPIO controller.
     - "renesas,gpio-r8a77965": for R8A77965 (R-Car M3-N) compatible GPIO controller.
     - "renesas,gpio-r8a77970": for R8A77970 (R-Car V3M) compatible GPIO controller.
+    - "renesas,gpio-r8a77980": for R8A77980 (R-Car V3H) compatible GPIO controller.
     - "renesas,gpio-r8a77990": for R8A77990 (R-Car E3) compatible GPIO controller.
     - "renesas,gpio-r8a77995": for R8A77995 (R-Car D3) compatible GPIO controller.
     - "renesas,rcar-gen1-gpio": for a generic R-Car Gen1 GPIO controller.
-- 
cgit v1.2.3


From c1d013a70f557e0d6db29398c955b2ec87db1ff8 Mon Sep 17 00:00:00 2001
From: Keerthy <j-keerthy@ti.com>
Date: Wed, 13 Jun 2018 09:10:36 +0530
Subject: gpio: davinci: Shuffle IRQ resource fetching from DT to beginning of
 probe

This is needed in case of PROBE_DEFER if IRQ resource is not yet ready.

Signed-off-by: Keerthy <j-keerthy@ti.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-davinci.c | 29 +++++++++++------------------
 1 file changed, 11 insertions(+), 18 deletions(-)

diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index 035a454eca43..423d37c95e6b 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -55,7 +55,7 @@ static inline struct davinci_gpio_regs __iomem *irq2regs(struct irq_data *d)
 	return g;
 }
 
-static int davinci_gpio_irq_setup(struct platform_device *pdev);
+static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq);
 
 /*--------------------------------------------------------------------------*/
 
@@ -167,7 +167,7 @@ of_err:
 static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	static int ctrl_num, bank_base;
-	int gpio, bank, ret = 0;
+	int gpio, bank, bank_irq, ret = 0;
 	unsigned ngpio, nbank;
 	struct davinci_gpio_controller *chips;
 	struct davinci_gpio_platform_data *pdata;
@@ -209,6 +209,12 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(gpio_base))
 		return PTR_ERR(gpio_base);
 
+	bank_irq = platform_get_irq(pdev, 0);
+	if (bank_irq < 0) {
+		dev_dbg(dev, "IRQ not populated\n");
+		return bank_irq;
+	}
+
 	snprintf(label, MAX_LABEL_SIZE, "davinci_gpio.%d", ctrl_num++);
 	chips->chip.label = devm_kstrdup(dev, label, GFP_KERNEL);
 		if (!chips->chip.label)
@@ -243,7 +249,7 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 		goto err;
 
 	platform_set_drvdata(pdev, chips);
-	ret = davinci_gpio_irq_setup(pdev);
+	ret = davinci_gpio_irq_setup(pdev, bank_irq);
 	if (ret)
 		goto err;
 
@@ -452,16 +458,15 @@ static const struct of_device_id davinci_gpio_ids[];
  * (dm6446) can be set appropriately for GPIOV33 pins.
  */
 
-static int davinci_gpio_irq_setup(struct platform_device *pdev)
+static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq)
 {
 	unsigned	gpio, bank;
 	int		irq;
 	int		ret;
 	struct clk	*clk;
 	u32		binten = 0;
-	unsigned	ngpio, bank_irq;
+	unsigned	ngpio;
 	struct device *dev = &pdev->dev;
-	struct resource	*res;
 	struct davinci_gpio_controller *chips = platform_get_drvdata(pdev);
 	struct davinci_gpio_platform_data *pdata = dev->platform_data;
 	struct davinci_gpio_regs __iomem *g;
@@ -481,18 +486,6 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev)
 		gpio_get_irq_chip = (gpio_get_irq_chip_cb_t)match->data;
 
 	ngpio = pdata->ngpio;
-	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
-	if (!res) {
-		dev_err(dev, "Invalid IRQ resource\n");
-		return -EBUSY;
-	}
-
-	bank_irq = res->start;
-
-	if (!bank_irq) {
-		dev_err(dev, "Invalid IRQ resource\n");
-		return -ENODEV;
-	}
 
 	clk = devm_clk_get(dev, "gpio");
 	if (IS_ERR(clk)) {
-- 
cgit v1.2.3


From eb3744a2dd01cb07ce9f556d56d6fe451f0c313a Mon Sep 17 00:00:00 2001
From: Keerthy <j-keerthy@ti.com>
Date: Wed, 13 Jun 2018 09:10:37 +0530
Subject: gpio: davinci: Do not assume continuous IRQ numbering

Currently the driver assumes that the interrupts are continuous
and does platform_get_irq only once and assumes the rest are continuous,
instead call platform_get_irq for all the interrupts and store them
in an array for later use.

Signed-off-by: Keerthy <j-keerthy@ti.com>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-davinci.c                | 63 ++++++++++++++++++++----------
 include/linux/platform_data/gpio-davinci.h |  3 +-
 2 files changed, 44 insertions(+), 22 deletions(-)

diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index 423d37c95e6b..a5ece8ea79bc 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -55,7 +55,7 @@ static inline struct davinci_gpio_regs __iomem *irq2regs(struct irq_data *d)
 	return g;
 }
 
-static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq);
+static int davinci_gpio_irq_setup(struct platform_device *pdev);
 
 /*--------------------------------------------------------------------------*/
 
@@ -167,8 +167,8 @@ of_err:
 static int davinci_gpio_probe(struct platform_device *pdev)
 {
 	static int ctrl_num, bank_base;
-	int gpio, bank, bank_irq, ret = 0;
-	unsigned ngpio, nbank;
+	int gpio, bank, i, ret = 0;
+	unsigned int ngpio, nbank, nirq;
 	struct davinci_gpio_controller *chips;
 	struct davinci_gpio_platform_data *pdata;
 	struct device *dev = &pdev->dev;
@@ -197,6 +197,16 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (WARN_ON(ARCH_NR_GPIOS < ngpio))
 		ngpio = ARCH_NR_GPIOS;
 
+	/*
+	 * If there are unbanked interrupts then the number of
+	 * interrupts is equal to number of gpios else all are banked so
+	 * number of interrupts is equal to number of banks(each with 16 gpios)
+	 */
+	if (pdata->gpio_unbanked)
+		nirq = pdata->gpio_unbanked;
+	else
+		nirq = DIV_ROUND_UP(ngpio, 16);
+
 	nbank = DIV_ROUND_UP(ngpio, 32);
 	chips = devm_kcalloc(dev,
 			     nbank, sizeof(struct davinci_gpio_controller),
@@ -209,10 +219,13 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(gpio_base))
 		return PTR_ERR(gpio_base);
 
-	bank_irq = platform_get_irq(pdev, 0);
-	if (bank_irq < 0) {
-		dev_dbg(dev, "IRQ not populated\n");
-		return bank_irq;
+	for (i = 0; i < nirq; i++) {
+		chips->irqs[i] = platform_get_irq(pdev, i);
+		if (chips->irqs[i] < 0) {
+			dev_info(dev, "IRQ not populated, err = %d\n",
+				 chips->irqs[i]);
+			return chips->irqs[i];
+		}
 	}
 
 	snprintf(label, MAX_LABEL_SIZE, "davinci_gpio.%d", ctrl_num++);
@@ -249,7 +262,7 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 		goto err;
 
 	platform_set_drvdata(pdev, chips);
-	ret = davinci_gpio_irq_setup(pdev, bank_irq);
+	ret = davinci_gpio_irq_setup(pdev);
 	if (ret)
 		goto err;
 
@@ -383,7 +396,7 @@ static int gpio_to_irq_unbanked(struct gpio_chip *chip, unsigned offset)
 	 * can provide direct-mapped IRQs to AINTC (up to 32 GPIOs).
 	 */
 	if (offset < d->gpio_unbanked)
-		return d->base_irq + offset;
+		return d->irqs[offset];
 	else
 		return -ENODEV;
 }
@@ -392,11 +405,18 @@ static int gpio_irq_type_unbanked(struct irq_data *data, unsigned trigger)
 {
 	struct davinci_gpio_controller *d;
 	struct davinci_gpio_regs __iomem *g;
-	u32 mask;
+	u32 mask, i;
 
 	d = (struct davinci_gpio_controller *)irq_data_get_irq_handler_data(data);
 	g = (struct davinci_gpio_regs __iomem *)d->regs[0];
-	mask = __gpio_mask(data->irq - d->base_irq);
+	for (i = 0; i < MAX_INT_PER_BANK; i++)
+		if (data->irq == d->irqs[i])
+			break;
+
+	if (i == MAX_INT_PER_BANK)
+		return -EINVAL;
+
+	mask = __gpio_mask(i);
 
 	if (trigger & ~(IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
 		return -EINVAL;
@@ -458,7 +478,7 @@ static const struct of_device_id davinci_gpio_ids[];
  * (dm6446) can be set appropriately for GPIOV33 pins.
  */
 
-static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq)
+static int davinci_gpio_irq_setup(struct platform_device *pdev)
 {
 	unsigned	gpio, bank;
 	int		irq;
@@ -492,6 +512,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq)
 		dev_err(dev, "Error %ld getting gpio clock\n", PTR_ERR(clk));
 		return PTR_ERR(clk);
 	}
+
 	ret = clk_prepare_enable(clk);
 	if (ret)
 		return ret;
@@ -531,12 +552,11 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq)
 	if (pdata->gpio_unbanked) {
 		/* pass "bank 0" GPIO IRQs to AINTC */
 		chips->chip.to_irq = gpio_to_irq_unbanked;
-		chips->base_irq = bank_irq;
 		chips->gpio_unbanked = pdata->gpio_unbanked;
 		binten = GENMASK(pdata->gpio_unbanked / 16, 0);
 
 		/* AINTC handles mask/unmask; GPIO handles triggering */
-		irq = bank_irq;
+		irq = chips->irqs[0];
 		irq_chip = gpio_get_irq_chip(irq);
 		irq_chip->name = "GPIO-AINTC";
 		irq_chip->irq_set_type = gpio_irq_type_unbanked;
@@ -547,10 +567,11 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq)
 		writel_relaxed(~0, &g->set_rising);
 
 		/* set the direct IRQs up to use that irqchip */
-		for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++, irq++) {
-			irq_set_chip(irq, irq_chip);
-			irq_set_handler_data(irq, chips);
-			irq_set_status_flags(irq, IRQ_TYPE_EDGE_BOTH);
+		for (gpio = 0; gpio < pdata->gpio_unbanked; gpio++) {
+			irq_set_chip(chips->irqs[gpio], irq_chip);
+			irq_set_handler_data(chips->irqs[gpio], chips);
+			irq_set_status_flags(chips->irqs[gpio],
+					     IRQ_TYPE_EDGE_BOTH);
 		}
 
 		goto done;
@@ -560,7 +581,7 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq)
 	 * Or, AINTC can handle IRQs for banks of 16 GPIO IRQs, which we
 	 * then chain through our own handler.
 	 */
-	for (gpio = 0, bank = 0; gpio < ngpio; bank++, bank_irq++, gpio += 16) {
+	for (gpio = 0, bank = 0; gpio < ngpio; bank++, gpio += 16) {
 		/* disabled by default, enabled only as needed
 		 * There are register sets for 32 GPIOs. 2 banks of 16
 		 * GPIOs are covered by each set of registers hence divide by 2
@@ -587,8 +608,8 @@ static int davinci_gpio_irq_setup(struct platform_device *pdev, int bank_irq)
 		irqdata->bank_num = bank;
 		irqdata->chip = chips;
 
-		irq_set_chained_handler_and_data(bank_irq, gpio_irq_handler,
-						 irqdata);
+		irq_set_chained_handler_and_data(chips->irqs[bank],
+						 gpio_irq_handler, irqdata);
 
 		binten |= BIT(bank);
 	}
diff --git a/include/linux/platform_data/gpio-davinci.h b/include/linux/platform_data/gpio-davinci.h
index 90ae19ca828f..57a5a35e0073 100644
--- a/include/linux/platform_data/gpio-davinci.h
+++ b/include/linux/platform_data/gpio-davinci.h
@@ -22,6 +22,7 @@
 #include <asm-generic/gpio.h>
 
 #define MAX_REGS_BANKS		5
+#define MAX_INT_PER_BANK 32
 
 struct davinci_gpio_platform_data {
 	u32	ngpio;
@@ -41,7 +42,7 @@ struct davinci_gpio_controller {
 	spinlock_t		lock;
 	void __iomem		*regs[MAX_REGS_BANKS];
 	int			gpio_unbanked;
-	unsigned int		base_irq;
+	int			irqs[MAX_INT_PER_BANK];
 	unsigned int		base;
 };
 
-- 
cgit v1.2.3


From f3a049e784b337e9fa08f2f9046c955cc80af535 Mon Sep 17 00:00:00 2001
From: Zhouyang Jia <jiazhouyang09@gmail.com>
Date: Tue, 12 Jun 2018 11:28:52 +0800
Subject: gpio: max732x: add error handling for i2c_new_dummy

When i2c_new_dummy fails, the lack of error-handling code may
cause unexpected results.

This patch adds error-handling code after calling i2c_new_dummy.

Signed-off-by: Zhouyang Jia <jiazhouyang09@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-max732x.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index 9d8bcc69f245..f03cb0ba7726 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -653,6 +653,12 @@ static int max732x_probe(struct i2c_client *client,
 		chip->client_group_a = client;
 		if (nr_port > 8) {
 			c = i2c_new_dummy(client->adapter, addr_b);
+			if (!c) {
+				dev_err(&client->dev,
+					"Failed to allocate I2C device\n");
+				ret = -ENODEV;
+				goto out_failed;
+			}
 			chip->client_group_b = chip->client_dummy = c;
 		}
 		break;
@@ -660,6 +666,12 @@ static int max732x_probe(struct i2c_client *client,
 		chip->client_group_b = client;
 		if (nr_port > 8) {
 			c = i2c_new_dummy(client->adapter, addr_a);
+			if (!c) {
+				dev_err(&client->dev,
+					"Failed to allocate I2C device\n");
+				ret = -ENODEV;
+				goto out_failed;
+			}
 			chip->client_group_a = chip->client_dummy = c;
 		}
 		break;
-- 
cgit v1.2.3


From 90b39402e9f31c4aab48dc1a43d85a724065793f Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 1 Jun 2018 13:21:27 +0200
Subject: gpio: Add API to explicitly name a consumer

The GPIO (descriptor) API registers a "label" naming what is
currently using the GPIO line. Typically this is taken from
things like the device tree node, so "reset-gpios" will result
in he line being labeled "reset".

The technical effect is pretty much zero: the use is for
debug and introspection, such as "lsgpio" and debugfs files.

However sometimes the user want this cuddly feeling of
listing all GPIO lines and seeing exactly what they are for
and it gives a very fulfilling sense of control. Especially
in the cases when the device tree node doesn't provide a
good name, or anonymous GPIO lines assigned just to
"gpios" in the device tree because the usage is implicit.

For these cases it may be nice to be able to label the
line directly and explicitly.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c        | 13 +++++++++++++
 include/linux/gpio/consumer.h |  7 +++++++
 2 files changed, 20 insertions(+)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index e11a3bb03820..c6f77e806cb8 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3193,6 +3193,19 @@ int gpiod_cansleep(const struct gpio_desc *desc)
 }
 EXPORT_SYMBOL_GPL(gpiod_cansleep);
 
+/**
+ * gpiod_set_consumer_name() - set the consumer name for the descriptor
+ * @desc: gpio to set the consumer name on
+ * @name: the new consumer name
+ */
+void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name)
+{
+	VALIDATE_DESC_VOID(desc);
+	/* Just overwrite whatever the previous name was */
+	desc->label = name;
+}
+EXPORT_SYMBOL_GPL(gpiod_set_consumer_name);
+
 /**
  * gpiod_to_irq() - return the IRQ corresponding to a GPIO
  * @desc: gpio whose IRQ will be returned (already requested)
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 243112c7fa7d..e8aaf34dd65d 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -145,6 +145,7 @@ int gpiod_is_active_low(const struct gpio_desc *desc);
 int gpiod_cansleep(const struct gpio_desc *desc);
 
 int gpiod_to_irq(const struct gpio_desc *desc);
+void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name);
 
 /* Convert between the old gpio_ and new gpiod_ interfaces */
 struct gpio_desc *gpio_to_desc(unsigned gpio);
@@ -467,6 +468,12 @@ static inline int gpiod_to_irq(const struct gpio_desc *desc)
 	return -EINVAL;
 }
 
+static inline void gpiod_set_consumer_name(struct gpio_desc *desc, const char *name)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(1);
+}
+
 static inline struct gpio_desc *gpio_to_desc(unsigned gpio)
 {
 	return ERR_PTR(-EINVAL);
-- 
cgit v1.2.3


From 6ff45566554ace49f8db45734dc6ce59e02487f5 Mon Sep 17 00:00:00 2001
From: Jan Kundrát <jan.kundrat@cesnet.cz>
Date: Thu, 15 Feb 2018 15:56:03 +0100
Subject: pinctrl: mcp23s08: Kconfig: update to reflect supported features
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit d8f4494e70ae removed comments which described this limitation.
The code supported interrupts even before.

Also add some spacing so that the chip IDs are a bit more readable.

Signed-off-by: Jan Kundrát <jan.kundrat@cesnet.cz>
Reviewed-by: Phil Reid <preid@electromag.com.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index dd50371225bc..522782d1ea49 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -161,10 +161,10 @@ config PINCTRL_MCP23S08
 	select REGMAP_SPI if SPI_MASTER
 	select GENERIC_PINCONF
 	help
-	  SPI/I2C driver for Microchip MCP23S08/MCP23S17/MCP23008/MCP23017
-	  I/O expanders.
-	  This provides a GPIO interface supporting inputs and outputs.
-	  The I2C versions of the chips can be used as interrupt-controller.
+	  SPI/I2C driver for Microchip MCP23S08 / MCP23S17 / MCP23S18 /
+	  MCP23008 / MCP23017 / MCP23018 I/O expanders.
+	  This provides a GPIO interface supporting inputs and outputs and a
+	  corresponding interrupt-controller.
 
 config PINCTRL_OXNAS
 	bool
-- 
cgit v1.2.3


From 7547b5969e069520d4cf23ba43b4ac889f8bd0ef Mon Sep 17 00:00:00 2001
From: Jan Kundrát <jan.kundrat@cesnet.cz>
Date: Tue, 20 Feb 2018 19:04:47 +0100
Subject: pinctrl: mcp23s08: debugfs: Do not restore the INTF register
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apart from the usual stuff, the debugfs code is currently also used for
one non-obvious side effect. It attempts to check whether the chip's
registers are still set to an expected value, and if not, re-initializes
them. It seems that the driver has "always" done so.

The code, however, also checks the INTF register which normally
indicates which pins have caused the recent interrupt. That's a volatile
register, and the datasheet says that writes are ignored in there.

When I'm just cat-ing /sys/kernel/debug/gpio with no SPI traffic and no
nosie on the GPIO lines, I'm not getting any warnings. Once I actually
use these GPIOs and cat that file in parallel, I always seem to get a:

  mcp23s08 spi1.1: restoring reg 0x07 from 0x0000 to 0xffff (power-loss?)

This might be a sign that I should not leave my unused inputs floating,
but the code should not be checking a volatile register, anyway. Let's
simply skip this last item in the iteration. I was also considering
removing this enitre re-initialization because it's non-obvious, but the
code survived various refactorings already and has sign-offs by people
who know more than I do, so let's leave it as-is. For now :).

Signed-off-by: Jan Kundrát <jan.kundrat@cesnet.cz>
Reviewed-by: Phil Reid <preid@electromag.com.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-mcp23s08.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index 022307dd4b54..4a8a8efadefa 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -666,7 +666,7 @@ static int mcp23s08_irq_setup(struct mcp23s08 *mcp)
  * can be used to fix state for MCP23xxx, that temporary
  * lost its power supply.
  */
-#define MCP23S08_CONFIG_REGS 8
+#define MCP23S08_CONFIG_REGS 7
 static int __check_mcp23s08_reg_cache(struct mcp23s08 *mcp)
 {
 	int cached[MCP23S08_CONFIG_REGS];
-- 
cgit v1.2.3


From 7d71b5f4b2fb5b2a38794fe029d6245c86244de6 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 7 Jun 2018 14:24:34 +0200
Subject: pinctrl: pinctrl-single: Avoid divisions in context save/restore

The divisions (and multiplications) can be avoided by changing the loops
to use increments of mux_bytes instead of 1.
While at it, remove the unneeded casts when assigning void pointers.

This saves +100 bytes of kernel size on arm32/arm64.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Tony Lindgren <tony@atomide.com>
Tested-by: Keerthy <j-keerthy@ti.com>
Reviewed-by: Keerthy <j-keerthy@ti.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-single.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index b3153c095199..92b694675a56 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1595,19 +1595,19 @@ static int pcs_save_context(struct pcs_device *pcs)
 
 	switch (pcs->width) {
 	case 64:
-		regsl = (u64 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regsl[i] = pcs->read(pcs->base + i * mux_bytes);
+		regsl = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regsl++ = pcs->read(pcs->base + i);
 		break;
 	case 32:
-		regsw = (u32 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regsw[i] = pcs->read(pcs->base + i * mux_bytes);
+		regsw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regsw++ = pcs->read(pcs->base + i);
 		break;
 	case 16:
-		regshw = (u16 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			regshw[i] = pcs->read(pcs->base + i * mux_bytes);
+		regshw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			*regshw++ = pcs->read(pcs->base + i);
 		break;
 	}
 
@@ -1625,19 +1625,19 @@ static void pcs_restore_context(struct pcs_device *pcs)
 
 	switch (pcs->width) {
 	case 64:
-		regsl = (u64 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regsl[i], pcs->base + i * mux_bytes);
+		regsl = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regsl++, pcs->base + i);
 		break;
 	case 32:
-		regsw = (u32 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regsw[i], pcs->base + i * mux_bytes);
+		regsw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regsw++, pcs->base + i);
 		break;
 	case 16:
-		regshw = (u16 *)pcs->saved_vals;
-		for (i = 0; i < pcs->size / mux_bytes; i++)
-			pcs->write(regshw[i], pcs->base + i * mux_bytes);
+		regshw = pcs->saved_vals;
+		for (i = 0; i < pcs->size; i += mux_bytes)
+			pcs->write(*regshw++, pcs->base + i);
 		break;
 	}
 }
-- 
cgit v1.2.3


From 96b0686dca33970c89f8cf37cf47aec94e6f10f5 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <swboyd@chromium.org>
Date: Tue, 12 Jun 2018 16:06:04 -0700
Subject: pinctrl: qcom: spmi-gpio: Add pm8998 and pm8005 to binding

Update the binding for two more PMICs supported by the same driver.
While we're here, remove the duplicate pmi8994 lines because that
support got merged twice.

Cc: Rajendra Nayak <rnayak@codeaurora.org>
Cc: <devicetree@vger.kernel.org>
Signed-off-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Vivek Gautam <vivek.gautam@codeaurora.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
index 5c25fcb29fb5..ffd4345415f3 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,pmic-gpio.txt
@@ -7,6 +7,7 @@ PMIC's from Qualcomm.
 	Usage: required
 	Value type: <string>
 	Definition: must be one of:
+		    "qcom,pm8005-gpio"
 		    "qcom,pm8018-gpio"
 		    "qcom,pm8038-gpio"
 		    "qcom,pm8058-gpio"
@@ -15,7 +16,7 @@ PMIC's from Qualcomm.
 		    "qcom,pm8921-gpio"
 		    "qcom,pm8941-gpio"
 		    "qcom,pm8994-gpio"
-		    "qcom,pmi8994-gpio"
+		    "qcom,pm8998-gpio"
 		    "qcom,pma8084-gpio"
 		    "qcom,pmi8994-gpio"
 
@@ -78,6 +79,7 @@ to specify in a pin configuration subnode:
 	Value type: <string-array>
 	Definition: List of gpio pins affected by the properties specified in
 		    this subnode.  Valid pins are:
+		    gpio1-gpio4 for pm8005
 		    gpio1-gpio6 for pm8018
 		    gpio1-gpio12 for pm8038
 		    gpio1-gpio40 for pm8058
@@ -86,7 +88,7 @@ to specify in a pin configuration subnode:
 		    gpio1-gpio44 for pm8921
 		    gpio1-gpio36 for pm8941
 		    gpio1-gpio22 for pm8994
-		    gpio1-gpio10 for pmi8994
+		    gpio1-gpio26 for pm8998
 		    gpio1-gpio22 for pma8084
 		    gpio1-gpio10 for pmi8994
 
-- 
cgit v1.2.3


From c969cb2f70aedf2159bc64073d012618506ef18f Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 15 Jun 2018 15:23:07 +0200
Subject: pinctrl: Cut unused sysfs includes

We simply don't use sysfs.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c   | 1 -
 drivers/pinctrl/pinmux.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index e5a303002021..9fa6c1608b80 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -21,7 +21,6 @@
 #include <linux/slab.h>
 #include <linux/err.h>
 #include <linux/list.h>
-#include <linux/sysfs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/pinctrl/consumer.h>
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index b8e9bda8ec98..d7c5b4abd741 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -22,7 +22,6 @@
 #include <linux/err.h>
 #include <linux/list.h>
 #include <linux/string.h>
-#include <linux/sysfs.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
 #include <linux/pinctrl/machine.h>
-- 
cgit v1.2.3


From 65793f3cd93abf4ca1109f78e07c1b7193abdfec Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Wed, 13 Jun 2018 16:26:46 -0400
Subject: MAINTAINERS: remove the outdated "LINUX SECURITY MODULE (LSM)
 FRAMEWORK" entry

This has been replaced with the "SECURITY SUBSYSTEM" entry.

Signed-off-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 MAINTAINERS | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 79bb02ff812f..6d2340f572e2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8229,11 +8229,6 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	tools/memory-model/
 F:	Documentation/memory-barriers.txt
 
-LINUX SECURITY MODULE (LSM) FRAMEWORK
-M:	Chris Wright <chrisw@sous-sol.org>
-L:	linux-security-module@vger.kernel.org
-S:	Supported
-
 LIS3LV02D ACCELEROMETER DRIVER
 M:	Eric Piel <eric.piel@tremplin-utc.net>
 S:	Maintained
-- 
cgit v1.2.3


From ba1f665f161ce112a2703649317bfdc9b6521613 Mon Sep 17 00:00:00 2001
From: Haneen Mohammed <hamohammed.sa@gmail.com>
Date: Fri, 25 May 2018 04:25:55 +0300
Subject: drm: Add checks for atomic_[duplicate/destroy]_state with atomic
 drivers

This patch add checks for atomic_[duplicate/destroy]_state of
drm_[connector/crtc/plane]_funcs for atomic drivers in the relevant
drm_*_init functions since these callback are mandatory for atomic drivers.

Update the kerneldoc comments for those callbacks.

Signed-off-by: Haneen Mohammed <hamohammed.sa@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525012555.GA8448@haneen-vb
---
 drivers/gpu/drm/drm_connector.c | 4 ++++
 drivers/gpu/drm/drm_crtc.c      | 4 ++++
 drivers/gpu/drm/drm_plane.c     | 4 ++++
 include/drm/drm_connector.h     | 4 ++++
 include/drm/drm_crtc.h          | 4 ++++
 include/drm/drm_plane.h         | 4 ++++
 6 files changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 002b244391f9..549b89501e01 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -195,6 +195,10 @@ int drm_connector_init(struct drm_device *dev,
 	struct ida *connector_ida =
 		&drm_connector_enum_list[connector_type].ida;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(dev) &&
+		(!funcs->atomic_destroy_state ||
+		 !funcs->atomic_duplicate_state));
+
 	ret = __drm_mode_object_add(dev, &connector->base,
 				    DRM_MODE_OBJECT_CONNECTOR,
 				    false, drm_connector_free);
diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index 163d82ac7d76..f45e7a8d4acd 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -286,6 +286,10 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	if (WARN_ON(config->num_crtc >= 32))
 		return -EINVAL;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(dev) &&
+		(!funcs->atomic_destroy_state ||
+		 !funcs->atomic_duplicate_state));
+
 	crtc->dev = dev;
 	crtc->funcs = funcs;
 
diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 534b57933576..df0b4ebbedbf 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -177,6 +177,10 @@ int drm_universal_plane_init(struct drm_device *dev, struct drm_plane *plane,
 	if (WARN_ON(config->num_total_plane >= 32))
 		return -EINVAL;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(dev) &&
+		(!funcs->atomic_destroy_state ||
+		 !funcs->atomic_duplicate_state));
+
 	ret = drm_mode_object_add(dev, &plane->base, DRM_MODE_OBJECT_PLANE);
 	if (ret)
 		return ret;
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index ee4c48218c85..c5797c24edd3 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -616,6 +616,8 @@ struct drm_connector_funcs {
 	 * cleaned up by calling the @atomic_destroy_state hook in this
 	 * structure.
 	 *
+	 * This callback is mandatory for atomic drivers.
+	 *
 	 * Atomic drivers which don't subclass &struct drm_connector_state should use
 	 * drm_atomic_helper_connector_duplicate_state(). Drivers that subclass the
 	 * state structure to extend it with driver-private state should use
@@ -642,6 +644,8 @@ struct drm_connector_funcs {
 	 *
 	 * Destroy a state duplicated with @atomic_duplicate_state and release
 	 * or unreference all resources it references
+	 *
+	 * This callback is mandatory for atomic drivers.
 	 */
 	void (*atomic_destroy_state)(struct drm_connector *connector,
 				     struct drm_connector_state *state);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 5cf7adeae6a5..23eddbccab10 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -506,6 +506,8 @@ struct drm_crtc_funcs {
 	 * cleaned up by calling the @atomic_destroy_state hook in this
 	 * structure.
 	 *
+	 * This callback is mandatory for atomic drivers.
+	 *
 	 * Atomic drivers which don't subclass &struct drm_crtc_state should use
 	 * drm_atomic_helper_crtc_duplicate_state(). Drivers that subclass the
 	 * state structure to extend it with driver-private state should use
@@ -532,6 +534,8 @@ struct drm_crtc_funcs {
 	 *
 	 * Destroy a state duplicated with @atomic_duplicate_state and release
 	 * or unreference all resources it references
+	 *
+	 * This callback is mandatory for atomic drivers.
 	 */
 	void (*atomic_destroy_state)(struct drm_crtc *crtc,
 				     struct drm_crtc_state *state);
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 14b1607aba4b..7d4d6c7f0afd 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -288,6 +288,8 @@ struct drm_plane_funcs {
 	 * cleaned up by calling the @atomic_destroy_state hook in this
 	 * structure.
 	 *
+	 * This callback is mandatory for atomic drivers.
+	 *
 	 * Atomic drivers which don't subclass &struct drm_plane_state should use
 	 * drm_atomic_helper_plane_duplicate_state(). Drivers that subclass the
 	 * state structure to extend it with driver-private state should use
@@ -314,6 +316,8 @@ struct drm_plane_funcs {
 	 *
 	 * Destroy a state duplicated with @atomic_duplicate_state and release
 	 * or unreference all resources it references
+	 *
+	 * This callback is mandatory for atomic drivers.
 	 */
 	void (*atomic_destroy_state)(struct drm_plane *plane,
 				     struct drm_plane_state *state);
-- 
cgit v1.2.3


From b77422f80337d363eed60c8c48db9cb6e33085c9 Mon Sep 17 00:00:00 2001
From: Kenneth Graunke <kenneth@whitecape.org>
Date: Fri, 15 Jun 2018 20:06:05 +0100
Subject: drm/i915: Enable provoking vertex fix on Gen9 systems.

The SF and clipper units mishandle the provoking vertex in some cases,
which can cause misrendering with shaders that use flat shaded inputs.

There are chicken bits in 3D_CHICKEN3 (for SF) and FF_SLICE_CHICKEN
(for the clipper) that work around the issue.  These registers are
unfortunately not part of the logical context (even the power context),
and so we must reload them every time we start executing in a context.

Bugzilla: https://bugs.freedesktop.org/103047
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615190605.16238-1-chris@chris-wilson.co.uk
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/i915/i915_reg.h  |  5 +++++
 drivers/gpu/drm/i915/intel_lrc.c | 12 +++++++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b8c0ebd50889..54ec7ab57ce8 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2432,12 +2432,17 @@ enum i915_power_well_id {
 #define _3D_CHICKEN	_MMIO(0x2084)
 #define  _3D_CHICKEN_HIZ_PLANE_DISABLE_MSAA_4X_SNB	(1 << 10)
 #define _3D_CHICKEN2	_MMIO(0x208c)
+
+#define FF_SLICE_CHICKEN	_MMIO(0x2088)
+#define  FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX	(1 << 1)
+
 /* Disables pipelining of read flushes past the SF-WIZ interface.
  * Required on all Ironlake steppings according to the B-Spec, but the
  * particular danger of not doing so is not specified.
  */
 # define _3D_CHICKEN2_WM_READ_PIPELINED			(1 << 14)
 #define _3D_CHICKEN3	_MMIO(0x2090)
+#define  _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX		(1 << 12)
 #define  _3D_CHICKEN_SF_DISABLE_OBJEND_CULL		(1 << 10)
 #define  _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE	(1 << 5)
 #define  _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL		(1 << 5)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 50e141ca1f7a..b6c230bd7d6e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1573,11 +1573,21 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
 	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
 
+	*batch++ = MI_LOAD_REGISTER_IMM(3);
+
 	/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
-	*batch++ = MI_LOAD_REGISTER_IMM(1);
 	*batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2);
 	*batch++ = _MASKED_BIT_DISABLE(
 			GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE);
+
+	/* BSpec: 11391 */
+	*batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN);
+	*batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX);
+
+	/* BSpec: 11299 */
+	*batch++ = i915_mmio_reg_offset(_3D_CHICKEN3);
+	*batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX);
+
 	*batch++ = MI_NOOP;
 
 	/* WaClearSlmSpaceAtContextSwitch:kbl */
-- 
cgit v1.2.3


From 4fdd5b4e9aba5fbbc6d3072a5a87fa1d3f3fc030 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 16 Jun 2018 21:25:34 +0100
Subject: drm/i915: Fix fallout of fake reset along resume

commit b2209e62a450 ("drm/i915/execlists: Reset the CSB head tracking on
reset/sanitization") and commit 1288786b18f7 ("drm/i915: Move GEM sanitize
from resume_early to resume") show the conflicting requirements on the
code. We must reset the GPU before trashing live state on a fast resume
(hibernation debug, or error paths), but we must only reset our state
tracking iff the GPU is reset (or power cycled). This is tricky if we
are disabling GPU reset to simulate broken hardware; we reset our state
tracking but the GPU is left intact and recovers from its stale state.

v2: Again without the assertion for forcewake, no longer required since
commit b3ee09a4de33 ("drm/i915/ringbuffer: Fix context restore upon reset")
as the contexts are reset from the CS ensuring everything is powered up.

Fixes: b2209e62a450 ("drm/i915/execlists: Reset the CSB head tracking on reset/sanitization")
Fixes: 1288786b18f7 ("drm/i915: Move GEM sanitize from resume_early to resume")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180616202534.18767-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.c         |  2 ++
 drivers/gpu/drm/i915/i915_gem.c         | 14 +++++---------
 drivers/gpu/drm/i915/intel_engine_cs.c  | 22 ++++++++++++++++++++++
 drivers/gpu/drm/i915/intel_ringbuffer.c |  8 --------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 ++
 5 files changed, 31 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index a9c8c66bb525..33453d56c386 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1841,6 +1841,8 @@ static int i915_drm_resume_early(struct drm_device *dev)
 	else
 		intel_display_set_init_power(dev_priv, true);
 
+	intel_engines_sanitize(dev_priv);
+
 	enable_rpm_wakeref_asserts(dev_priv);
 
 out:
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5155e458b11e..822abf444378 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4990,8 +4990,7 @@ void __i915_gem_object_release_unless_active(struct drm_i915_gem_object *obj)
 
 void i915_gem_sanitize(struct drm_i915_private *i915)
 {
-	struct intel_engine_cs *engine;
-	enum intel_engine_id id;
+	int err;
 
 	GEM_TRACE("\n");
 
@@ -5017,14 +5016,11 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	 * it may impact the display and we are uncertain about the stability
 	 * of the reset, so this could be applied to even earlier gen.
 	 */
+	err = -ENODEV;
 	if (INTEL_GEN(i915) >= 5 && intel_has_gpu_reset(i915))
-		WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
-
-	/* Reset the submission backend after resume as well as the GPU reset */
-	for_each_engine(engine, i915, id) {
-		if (engine->reset.reset)
-			engine->reset.reset(engine, NULL);
-	}
+		err = WARN_ON(intel_gpu_reset(i915, ALL_ENGINES));
+	if (!err)
+		intel_engines_sanitize(i915);
 
 	intel_uncore_forcewake_put(i915, FORCEWAKE_ALL);
 	intel_runtime_pm_put(i915);
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 13bb8c7d2621..32bf3a408d46 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1077,6 +1077,28 @@ void intel_engines_reset_default_submission(struct drm_i915_private *i915)
 		engine->set_default_submission(engine);
 }
 
+/**
+ * intel_engines_sanitize: called after the GPU has lost power
+ * @i915: the i915 device
+ *
+ * Anytime we reset the GPU, either with an explicit GPU reset or through a
+ * PCI power cycle, the GPU loses state and we must reset our state tracking
+ * to match. Note that calling intel_engines_sanitize() if the GPU has not
+ * been reset results in much confusion!
+ */
+void intel_engines_sanitize(struct drm_i915_private *i915)
+{
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
+	GEM_TRACE("\n");
+
+	for_each_engine(engine, i915, id) {
+		if (engine->reset.reset)
+			engine->reset.reset(engine, NULL);
+	}
+}
+
 /**
  * intel_engines_park: called when the GT is transitioning from busy->idle
  * @i915: the i915 device
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 6a937a896651..4dae23885006 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -563,14 +563,6 @@ static void reset_ring(struct intel_engine_cs *engine, struct i915_request *rq)
 {
 	GEM_TRACE("%s seqno=%x\n", engine->name, rq ? rq->global_seqno : 0);
 
-	/*
-	 * RC6 must be prevented until the reset is complete and the engine
-	 * reinitialised. If it occurs in the middle of this sequence, the
-	 * state written to/loaded from the power context is ill-defined (e.g.
-	 * the PP_BASE_DIR may be lost).
-	 */
-	assert_forcewakes_active(engine->i915, FORCEWAKE_ALL);
-
 	/*
 	 * Try to restore the logical GPU state to match the continuation
 	 * of the request queue. If we skip the context/PD restore, then
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 4003f3ebe3d1..a0bc7a8222b4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -1052,6 +1052,8 @@ gen8_emit_ggtt_write(u32 *cs, u32 value, u32 gtt_offset)
 	return cs;
 }
 
+void intel_engines_sanitize(struct drm_i915_private *i915);
+
 bool intel_engine_is_idle(struct intel_engine_cs *engine);
 bool intel_engines_are_idle(struct drm_i915_private *dev_priv);
 
-- 
cgit v1.2.3


From 00a5762b45250ebde8920d3cf68ca3974a0253b2 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 1 Jun 2018 12:03:24 +0200
Subject: mtd: m25p80: Remove unneeded m25p->command field

The ->command field is no longer used, remove it.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Marek Vasut <marek.vasut@gmail.com>
---
 drivers/mtd/devices/m25p80.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index e84563d2067f..3fc5ef4ebb16 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -28,11 +28,9 @@
 #include <linux/spi/flash.h>
 #include <linux/mtd/spi-nor.h>
 
-#define	MAX_CMD_SIZE		6
 struct m25p {
 	struct spi_mem		*spimem;
 	struct spi_nor		spi_nor;
-	u8			command[MAX_CMD_SIZE];
 };
 
 static int m25p80_read_reg(struct spi_nor *nor, u8 code, u8 *val, int len)
-- 
cgit v1.2.3


From 9882b5375df532acb2c2399a90d882461112e612 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 1 Jun 2018 12:03:25 +0200
Subject: mtd: m25p80: Use SPI_MEM_OP_NO_DUMMY instead of SPI_MEM_OP_DUMMY(0,
 x)

SPI_MEM_OP_DUMMY(0, x) means there's 0 dummy bytes to send, which is
similar to SPI_MEM_OP_NO_DUMMY except it's less clear. Use
SPI_MEM_OP_NO_DUMMY instead of SPI_MEM_OP_DUMMY(0, x) in
m25p80_write().
Also stop updating op.dummy.buswidth since this value is only
meaningful if you have dummy bytes.

Reported-by: Cyrille Pitchen <cyrille.pitchen@microchip.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Marek Vasut <marek.vasut@gmail.com>
---
 drivers/mtd/devices/m25p80.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index 3fc5ef4ebb16..fe260ccb2d7d 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -68,7 +68,7 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	struct spi_mem_op op =
 			SPI_MEM_OP(SPI_MEM_OP_CMD(nor->program_opcode, 1),
 				   SPI_MEM_OP_ADDR(nor->addr_width, to, 1),
-				   SPI_MEM_OP_DUMMY(0, 1),
+				   SPI_MEM_OP_NO_DUMMY,
 				   SPI_MEM_OP_DATA_OUT(len, buf, 1));
 	size_t remaining = len;
 	int ret;
@@ -76,7 +76,6 @@ static ssize_t m25p80_write(struct spi_nor *nor, loff_t to, size_t len,
 	/* get transfer protocols. */
 	op.cmd.buswidth = spi_nor_get_protocol_inst_nbits(nor->write_proto);
 	op.addr.buswidth = spi_nor_get_protocol_addr_nbits(nor->write_proto);
-	op.dummy.buswidth = op.addr.buswidth;
 	op.data.buswidth = spi_nor_get_protocol_data_nbits(nor->write_proto);
 
 	if (nor->program_opcode == SPINOR_OP_AAI_WP && nor->sst_write_second)
-- 
cgit v1.2.3


From e01b4f624278d5efe5fb5da585ca371947b16680 Mon Sep 17 00:00:00 2001
From: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Date: Thu, 14 Jun 2018 20:26:42 +0100
Subject: ASoC: dapm: Fix potential DAI widget pointer deref when linking DAIs

Sometime a component or topology may configure a DAI widget with no
private data leading to a dev_dbg() dereferencne of this data.

Fix this to check for non NULL private data and let users know if widget
is missing DAI.

Signed-off-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-dapm.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 36a39ba30226..8ede773b1db8 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -4073,6 +4073,13 @@ int snd_soc_dapm_link_dai_widgets(struct snd_soc_card *card)
 			continue;
 		}
 
+		/* let users know there is no DAI to link */
+		if (!dai_w->priv) {
+			dev_dbg(card->dev, "dai widget %s has no DAI\n",
+				dai_w->name);
+			continue;
+		}
+
 		dai = dai_w->priv;
 
 		/* ...find all widgets with the same stream and link them */
-- 
cgit v1.2.3


From c60b613a7097cff20fdd05e2891ce69542f0d5a3 Mon Sep 17 00:00:00 2001
From: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Date: Thu, 14 Jun 2018 20:50:37 +0100
Subject: ASoC: topology: Give more data to clients via callbacks

Give topology clients more access to the topology data by passing index,
pcm, link_config and dai_driver to clients. This allows clients to fully
instantiate and track topology objects.

The SOF driver is the first user of these new APIs and needs them to build
component topology driver and FW objects.

Signed-off-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-topology.h           | 23 ++++++++++++++---------
 sound/soc/intel/skylake/skl-pcm.c      |  7 ++++---
 sound/soc/intel/skylake/skl-topology.c |  5 +++--
 sound/soc/intel/skylake/skl-topology.h |  5 +++--
 sound/soc/soc-topology.c               | 31 ++++++++++++++++++-------------
 5 files changed, 42 insertions(+), 29 deletions(-)

diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h
index f552c3f56368..e1f265e21ee1 100644
--- a/include/sound/soc-topology.h
+++ b/include/sound/soc-topology.h
@@ -30,6 +30,8 @@ struct snd_soc_dapm_context;
 struct snd_soc_card;
 struct snd_kcontrol_new;
 struct snd_soc_dai_link;
+struct snd_soc_dai_driver;
+struct snd_soc_dai;
 
 /* object scan be loaded and unloaded in groups with identfying indexes */
 #define SND_SOC_TPLG_INDEX_ALL	0	/* ID that matches all FW objects */
@@ -109,35 +111,38 @@ struct snd_soc_tplg_widget_events {
 struct snd_soc_tplg_ops {
 
 	/* external kcontrol init - used for any driver specific init */
-	int (*control_load)(struct snd_soc_component *,
+	int (*control_load)(struct snd_soc_component *, int index,
 		struct snd_kcontrol_new *, struct snd_soc_tplg_ctl_hdr *);
 	int (*control_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
 	/* external widget init - used for any driver specific init */
-	int (*widget_load)(struct snd_soc_component *,
+	int (*widget_load)(struct snd_soc_component *, int index,
 		struct snd_soc_dapm_widget *,
 		struct snd_soc_tplg_dapm_widget *);
-	int (*widget_ready)(struct snd_soc_component *,
+	int (*widget_ready)(struct snd_soc_component *, int index,
 		struct snd_soc_dapm_widget *,
 		struct snd_soc_tplg_dapm_widget *);
 	int (*widget_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
 	/* FE DAI - used for any driver specific init */
-	int (*dai_load)(struct snd_soc_component *,
-		struct snd_soc_dai_driver *dai_drv);
+	int (*dai_load)(struct snd_soc_component *, int index,
+		struct snd_soc_dai_driver *dai_drv,
+		struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai);
+
 	int (*dai_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
 	/* DAI link - used for any driver specific init */
-	int (*link_load)(struct snd_soc_component *,
-		struct snd_soc_dai_link *link);
+	int (*link_load)(struct snd_soc_component *, int index,
+		struct snd_soc_dai_link *link,
+		struct snd_soc_tplg_link_config *cfg);
 	int (*link_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
 	/* callback to handle vendor bespoke data */
-	int (*vendor_load)(struct snd_soc_component *,
+	int (*vendor_load)(struct snd_soc_component *, int index,
 		struct snd_soc_tplg_hdr *);
 	int (*vendor_unload)(struct snd_soc_component *,
 		struct snd_soc_tplg_hdr *);
@@ -146,7 +151,7 @@ struct snd_soc_tplg_ops {
 	void (*complete)(struct snd_soc_component *);
 
 	/* manifest - optional to inform component of manifest */
-	int (*manifest)(struct snd_soc_component *,
+	int (*manifest)(struct snd_soc_component *, int index,
 		struct snd_soc_tplg_manifest *);
 
 	/* vendor specific kcontrol handlers available for binding */
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index afa86b9e4dcf..1f4dd08d36c5 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -1017,10 +1017,11 @@ static struct snd_soc_dai_driver skl_platform_dai[] = {
 },
 };
 
-int skl_dai_load(struct snd_soc_component *cmp,
-		 struct snd_soc_dai_driver *pcm_dai)
+int skl_dai_load(struct snd_soc_component *cmp, int index,
+			struct snd_soc_dai_driver *dai_drv,
+			struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai)
 {
-	pcm_dai->ops = &skl_pcm_dai_ops;
+	dai_drv->ops = &skl_pcm_dai_ops;
 
 	return 0;
 }
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index fcdc716754b6..647e52aecdc3 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -3024,7 +3024,7 @@ void skl_cleanup_resources(struct skl *skl)
  * information to the driver about module and pipeline parameters which DSP
  * FW expects like ids, resource values, formats etc
  */
-static int skl_tplg_widget_load(struct snd_soc_component *cmpnt,
+static int skl_tplg_widget_load(struct snd_soc_component *cmpnt, int index,
 				struct snd_soc_dapm_widget *w,
 				struct snd_soc_tplg_dapm_widget *tplg_w)
 {
@@ -3131,6 +3131,7 @@ static int skl_init_enum_data(struct device *dev, struct soc_enum *se,
 }
 
 static int skl_tplg_control_load(struct snd_soc_component *cmpnt,
+				int index,
 				struct snd_kcontrol_new *kctl,
 				struct snd_soc_tplg_ctl_hdr *hdr)
 {
@@ -3619,7 +3620,7 @@ static int skl_tplg_get_manifest_data(struct snd_soc_tplg_manifest *manifest,
 	return 0;
 }
 
-static int skl_manifest_load(struct snd_soc_component *cmpnt,
+static int skl_manifest_load(struct snd_soc_component *cmpnt, int index,
 				struct snd_soc_tplg_manifest *manifest)
 {
 	struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt);
diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h
index 6d7e0569695f..af198ea0379e 100644
--- a/sound/soc/intel/skylake/skl-topology.h
+++ b/sound/soc/intel/skylake/skl-topology.h
@@ -512,8 +512,9 @@ int skl_pcm_host_dma_prepare(struct device *dev,
 int skl_pcm_link_dma_prepare(struct device *dev,
 			struct skl_pipe_params *params);
 
-int skl_dai_load(struct snd_soc_component *cmp,
-		 struct snd_soc_dai_driver *pcm_dai);
+int skl_dai_load(struct snd_soc_component *cmp, int index,
+		struct snd_soc_dai_driver *dai_drv,
+		struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai);
 void skl_tplg_add_moduleid_in_bind_params(struct skl *skl,
 				struct snd_soc_dapm_widget *w);
 #endif
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 53f121a50c97..9b33260fd537 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -259,7 +259,7 @@ static int soc_tplg_vendor_load_(struct soc_tplg *tplg,
 	int ret = 0;
 
 	if (tplg->comp && tplg->ops && tplg->ops->vendor_load)
-		ret = tplg->ops->vendor_load(tplg->comp, hdr);
+		ret = tplg->ops->vendor_load(tplg->comp, tplg->index, hdr);
 	else {
 		dev_err(tplg->dev, "ASoC: no vendor load callback for ID %d\n",
 			hdr->vendor_type);
@@ -291,7 +291,8 @@ static int soc_tplg_widget_load(struct soc_tplg *tplg,
 	struct snd_soc_dapm_widget *w, struct snd_soc_tplg_dapm_widget *tplg_w)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->widget_load)
-		return tplg->ops->widget_load(tplg->comp, w, tplg_w);
+		return tplg->ops->widget_load(tplg->comp, tplg->index, w,
+			tplg_w);
 
 	return 0;
 }
@@ -302,27 +303,30 @@ static int soc_tplg_widget_ready(struct soc_tplg *tplg,
 	struct snd_soc_dapm_widget *w, struct snd_soc_tplg_dapm_widget *tplg_w)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->widget_ready)
-		return tplg->ops->widget_ready(tplg->comp, w, tplg_w);
+		return tplg->ops->widget_ready(tplg->comp, tplg->index, w,
+			tplg_w);
 
 	return 0;
 }
 
 /* pass DAI configurations to component driver for extra initialization */
 static int soc_tplg_dai_load(struct soc_tplg *tplg,
-	struct snd_soc_dai_driver *dai_drv)
+	struct snd_soc_dai_driver *dai_drv,
+	struct snd_soc_tplg_pcm *pcm, struct snd_soc_dai *dai)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->dai_load)
-		return tplg->ops->dai_load(tplg->comp, dai_drv);
+		return tplg->ops->dai_load(tplg->comp, tplg->index, dai_drv,
+			pcm, dai);
 
 	return 0;
 }
 
 /* pass link configurations to component driver for extra initialization */
 static int soc_tplg_dai_link_load(struct soc_tplg *tplg,
-	struct snd_soc_dai_link *link)
+	struct snd_soc_dai_link *link, struct snd_soc_tplg_link_config *cfg)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->link_load)
-		return tplg->ops->link_load(tplg->comp, link);
+		return tplg->ops->link_load(tplg->comp, tplg->index, link, cfg);
 
 	return 0;
 }
@@ -643,7 +647,8 @@ static int soc_tplg_init_kcontrol(struct soc_tplg *tplg,
 	struct snd_kcontrol_new *k, struct snd_soc_tplg_ctl_hdr *hdr)
 {
 	if (tplg->comp && tplg->ops && tplg->ops->control_load)
-		return tplg->ops->control_load(tplg->comp, k, hdr);
+		return tplg->ops->control_load(tplg->comp, tplg->index, k,
+			hdr);
 
 	return 0;
 }
@@ -1702,7 +1707,7 @@ static int soc_tplg_dai_create(struct soc_tplg *tplg,
 		dai_drv->compress_new = snd_soc_new_compress;
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_load(tplg, dai_drv);
+	ret = soc_tplg_dai_load(tplg, dai_drv, pcm, NULL);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n");
 		kfree(dai_drv);
@@ -1772,7 +1777,7 @@ static int soc_tplg_fe_link_create(struct soc_tplg *tplg,
 		set_link_flags(link, pcm->flag_mask, pcm->flags);
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_link_load(tplg, link);
+	ret = soc_tplg_dai_link_load(tplg, link, NULL);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: FE link loading failed\n");
 		kfree(link);
@@ -2080,7 +2085,7 @@ static int soc_tplg_link_config(struct soc_tplg *tplg,
 		set_link_flags(link, cfg->flag_mask, cfg->flags);
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_link_load(tplg, link);
+	ret = soc_tplg_dai_link_load(tplg, link, cfg);
 	if (ret < 0) {
 		dev_err(tplg->dev, "ASoC: physical link loading failed\n");
 		return ret;
@@ -2202,7 +2207,7 @@ static int soc_tplg_dai_config(struct soc_tplg *tplg,
 		set_dai_flags(dai_drv, d->flag_mask, d->flags);
 
 	/* pass control to component driver for optional further init */
-	ret = soc_tplg_dai_load(tplg, dai_drv);
+	ret = soc_tplg_dai_load(tplg, dai_drv, NULL, dai);
 	if (ret < 0) {
 		dev_err(tplg->comp->dev, "ASoC: DAI loading failed\n");
 		return ret;
@@ -2311,7 +2316,7 @@ static int soc_tplg_manifest_load(struct soc_tplg *tplg,
 
 	/* pass control to component driver for optional further init */
 	if (tplg->comp && tplg->ops && tplg->ops->manifest)
-		return tplg->ops->manifest(tplg->comp, _manifest);
+		return tplg->ops->manifest(tplg->comp, tplg->index, _manifest);
 
 	if (!abi_match)	/* free the duplicated one */
 		kfree(_manifest);
-- 
cgit v1.2.3


From 503e79b793fea5de626db73accf8e8994bc4289d Mon Sep 17 00:00:00 2001
From: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Date: Thu, 14 Jun 2018 20:53:59 +0100
Subject: ASoC: topology: Add callback for DAPM route load/unload

Add a callback fro clients for notification about DAPM route loading and
unloading.

Signed-off-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-topology.h |  7 +++++++
 sound/soc/soc-topology.c     | 13 +++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h
index e1f265e21ee1..401ef2c45d6c 100644
--- a/include/sound/soc-topology.h
+++ b/include/sound/soc-topology.h
@@ -32,6 +32,7 @@ struct snd_kcontrol_new;
 struct snd_soc_dai_link;
 struct snd_soc_dai_driver;
 struct snd_soc_dai;
+struct snd_soc_dapm_route;
 
 /* object scan be loaded and unloaded in groups with identfying indexes */
 #define SND_SOC_TPLG_INDEX_ALL	0	/* ID that matches all FW objects */
@@ -116,6 +117,12 @@ struct snd_soc_tplg_ops {
 	int (*control_unload)(struct snd_soc_component *,
 		struct snd_soc_dobj *);
 
+	/* DAPM graph route element loading and unloading */
+	int (*dapm_route_load)(struct snd_soc_component *, int index,
+		struct snd_soc_dapm_route *route);
+	int (*dapm_route_unload)(struct snd_soc_component *,
+		struct snd_soc_dobj *);
+
 	/* external widget init - used for any driver specific init */
 	int (*widget_load)(struct snd_soc_component *, int index,
 		struct snd_soc_dapm_widget *,
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 9b33260fd537..05d177d689e2 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1105,6 +1105,17 @@ static int soc_tplg_kcontrol_elems_load(struct soc_tplg *tplg,
 	return 0;
 }
 
+/* optionally pass new dynamic kcontrol to component driver. */
+static int soc_tplg_add_route(struct soc_tplg *tplg,
+	struct snd_soc_dapm_route *route)
+{
+	if (tplg->comp && tplg->ops && tplg->ops->dapm_route_load)
+		return tplg->ops->dapm_route_load(tplg->comp, tplg->index,
+			route);
+
+	return 0;
+}
+
 static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg,
 	struct snd_soc_tplg_hdr *hdr)
 {
@@ -1153,6 +1164,8 @@ static int soc_tplg_dapm_graph_elems_load(struct soc_tplg *tplg,
 		else
 			route.control = elem->control;
 
+		soc_tplg_add_route(tplg, &route);
+
 		/* add route, but keep going if some fail */
 		snd_soc_dapm_add_routes(dapm, &route, 1);
 	}
-- 
cgit v1.2.3


From 134c875bff58ac988c64a1ea2a337acba1711d4b Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:56:51 +0000
Subject: ASoC: fsi: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/fsi.c | 22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

diff --git a/sound/soc/sh/fsi.c b/sound/soc/sh/fsi.c
index 3bae06dd121f..aa7e902f0c02 100644
--- a/sound/soc/sh/fsi.c
+++ b/sound/soc/sh/fsi.c
@@ -1,16 +1,12 @@
-/*
- * Fifo-attached Serial Interface (FSI) support for SH7724
- *
- * Copyright (C) 2009 Renesas Solutions Corp.
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * Based on ssi.c
- * Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Fifo-attached Serial Interface (FSI) support for SH7724
+//
+// Copyright (C) 2009 Renesas Solutions Corp.
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
+//
+// Based on ssi.c
+// Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
 
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
-- 
cgit v1.2.3


From cb006e7b1712bb9507a218be7ed811ca8e65fc4d Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:57:13 +0000
Subject: ASoC: hac: convert to SPDX identifiers

Tidyup incoherence between MODULE_LICENSE and header license, too

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/hac.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/sound/soc/sh/hac.c b/sound/soc/sh/hac.c
index 624aaf569fef..c2b496398e6b 100644
--- a/sound/soc/sh/hac.c
+++ b/sound/soc/sh/hac.c
@@ -1,13 +1,11 @@
-/*
- * Hitachi Audio Controller (AC97) support for SH7760/SH7780
- *
- * Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *  licensed under the terms outlined in the file COPYING at the root
- *  of the linux kernel sources.
- *
- * dont forget to set IPSEL/OMSEL register bits (in your board code) to
- * enable HAC output pins!
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Hitachi Audio Controller (AC97) support for SH7760/SH7780
+//
+// Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
+//
+// dont forget to set IPSEL/OMSEL register bits (in your board code) to
+// enable HAC output pins!
 
 /* BIG FAT FIXME: although the SH7760 has 2 independent AC97 units, only
  * the FIRST can be used since ASoC does not pass any information to the
@@ -343,6 +341,6 @@ static struct platform_driver hac_pcm_driver = {
 
 module_platform_driver(hac_pcm_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SuperH onchip HAC (AC97) audio driver");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
-- 
cgit v1.2.3


From 217bc8c898b24fa2098a375a575f6170cfac45a9 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:57:47 +0000
Subject: ASoC: ssi: convert to SPDX identifiers

Tidyup incoherence between MODULE_LICENSE and header license, too

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/ssi.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/sound/soc/sh/ssi.c b/sound/soc/sh/ssi.c
index 89ed1b107ac5..8125fa3840b6 100644
--- a/sound/soc/sh/ssi.c
+++ b/sound/soc/sh/ssi.c
@@ -1,14 +1,11 @@
-/*
- * Serial Sound Interface (I2S) support for SH7760/SH7780
- *
- * Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *
- *  licensed under the terms outlined in the file COPYING at the root
- *  of the linux kernel sources.
- *
- * dont forget to set IPSEL/OMSEL register bits (in your board code) to
- * enable SSI output pins!
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Serial Sound Interface (I2S) support for SH7760/SH7780
+//
+// Copyright (c) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
+//
+// dont forget to set IPSEL/OMSEL register bits (in your board code) to
+// enable SSI output pins!
 
 /*
  * LIMITATIONS:
@@ -400,6 +397,6 @@ static struct platform_driver sh4_ssi_driver = {
 
 module_platform_driver(sh4_ssi_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SuperH onchip SSI (I2S) audio driver");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
-- 
cgit v1.2.3


From 4e6fdaf1bd334e7e3ad9d6ef7aef4a433c770952 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:58:07 +0000
Subject: ASoC: siu: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/siu.h     | 26 ++++++--------------------
 sound/soc/sh/siu_dai.c | 26 ++++++--------------------
 sound/soc/sh/siu_pcm.c | 27 +++++++--------------------
 3 files changed, 19 insertions(+), 60 deletions(-)

diff --git a/sound/soc/sh/siu.h b/sound/soc/sh/siu.h
index 6088d627c0e4..63a508fdfe78 100644
--- a/sound/soc/sh/siu.h
+++ b/sound/soc/sh/siu.h
@@ -1,23 +1,9 @@
-/*
- * siu.h - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- * Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// siu.h - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+// Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
 
 #ifndef SIU_H
 #define SIU_H
diff --git a/sound/soc/sh/siu_dai.c b/sound/soc/sh/siu_dai.c
index ee2211635e92..f2a386fcd92e 100644
--- a/sound/soc/sh/siu_dai.c
+++ b/sound/soc/sh/siu_dai.c
@@ -1,23 +1,9 @@
-/*
- * siu_dai.c - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- * Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// siu_dai.c - ALSA SoC driver for Renesas SH7343, SH7722 SIU peripheral.
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+// Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
 
 #include <linux/delay.h>
 #include <linux/firmware.h>
diff --git a/sound/soc/sh/siu_pcm.c b/sound/soc/sh/siu_pcm.c
index 172909570ed5..e263757e4a69 100644
--- a/sound/soc/sh/siu_pcm.c
+++ b/sound/soc/sh/siu_pcm.c
@@ -1,23 +1,10 @@
-/*
- * siu_pcm.c - ALSA driver for Renesas SH7343, SH7722 SIU peripheral.
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- * Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// siu_pcm.c - ALSA driver for Renesas SH7343, SH7722 SIU peripheral.
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+// Copyright (C) 2006 Carlos Munoz <carlos@kenati.com>
+
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
-- 
cgit v1.2.3


From 1e0edd4deadbbacd3b35179c233efa26624ab2af Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:58:38 +0000
Subject: ASoC: rsnd: convert to SPDX identifiers

Tidyup incoherence between MODULE_LICENSE and header license, too

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/rcar/Makefile |  1 +
 sound/soc/sh/rcar/adg.c    | 15 ++++++---------
 sound/soc/sh/rcar/cmd.c    | 17 +++++++----------
 sound/soc/sh/rcar/core.c   | 24 ++++++++++--------------
 sound/soc/sh/rcar/ctu.c    | 15 ++++++---------
 sound/soc/sh/rcar/dma.c    | 17 +++++++----------
 sound/soc/sh/rcar/dvc.c    | 16 ++++++----------
 sound/soc/sh/rcar/gen.c    | 16 ++++++----------
 sound/soc/sh/rcar/mix.c    | 14 +++++---------
 sound/soc/sh/rcar/rsnd.h   | 17 +++++++----------
 sound/soc/sh/rcar/src.c    | 16 ++++++----------
 sound/soc/sh/rcar/ssi.c    | 22 +++++++++-------------
 sound/soc/sh/rcar/ssiu.c   | 15 ++++++---------
 13 files changed, 82 insertions(+), 123 deletions(-)

diff --git a/sound/soc/sh/rcar/Makefile b/sound/soc/sh/rcar/Makefile
index 9c3d5aed99d1..5d1ff8ef26f9 100644
--- a/sound/soc/sh/rcar/Makefile
+++ b/sound/soc/sh/rcar/Makefile
@@ -1,2 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
 snd-soc-rcar-objs	:= core.o gen.o dma.o adg.o ssi.o ssiu.o src.o ctu.o mix.o dvc.o cmd.o
 obj-$(CONFIG_SND_SOC_RCAR)	+= snd-soc-rcar.o
diff --git a/sound/soc/sh/rcar/adg.c b/sound/soc/sh/rcar/adg.c
index 4672688cac32..3a3064dda57f 100644
--- a/sound/soc/sh/rcar/adg.c
+++ b/sound/soc/sh/rcar/adg.c
@@ -1,12 +1,9 @@
-/*
- * Helper routines for R-Car sound ADG.
- *
- *  Copyright (C) 2013  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Helper routines for R-Car sound ADG.
+//
+//  Copyright (C) 2013  Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/clk-provider.h>
 #include "rsnd.h"
 
diff --git a/sound/soc/sh/rcar/cmd.c b/sound/soc/sh/rcar/cmd.c
index 5900fb535a2b..d8043ad33540 100644
--- a/sound/soc/sh/rcar/cmd.c
+++ b/sound/soc/sh/rcar/cmd.c
@@ -1,13 +1,10 @@
-/*
- * Renesas R-Car CMD support
- *
- * Copyright (C) 2015 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car CMD support
+//
+// Copyright (C) 2015 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include "rsnd.h"
 
 struct rsnd_cmd {
diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index f237002180c0..eac22fef4543 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -1,16 +1,12 @@
-/*
- * Renesas R-Car SRU/SCU/SSIU/SSI support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * Based on fsi.c
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SRU/SCU/SSIU/SSI support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// Based on fsi.c
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
 
 /*
  * Renesas R-Car sound device structure
@@ -1606,7 +1602,7 @@ static struct platform_driver rsnd_driver = {
 };
 module_platform_driver(rsnd_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Renesas R-Car audio driver");
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
 MODULE_ALIAS("platform:rcar-pcm-audio");
diff --git a/sound/soc/sh/rcar/ctu.c b/sound/soc/sh/rcar/ctu.c
index 83be7d3ae0a8..6a55aa753003 100644
--- a/sound/soc/sh/rcar/ctu.c
+++ b/sound/soc/sh/rcar/ctu.c
@@ -1,12 +1,9 @@
-/*
- * ctu.c
- *
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ctu.c
+//
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include "rsnd.h"
 
 #define CTU_NAME_SIZE	16
diff --git a/sound/soc/sh/rcar/dma.c b/sound/soc/sh/rcar/dma.c
index ef82b94d038b..fe63ef8600d0 100644
--- a/sound/soc/sh/rcar/dma.c
+++ b/sound/soc/sh/rcar/dma.c
@@ -1,13 +1,10 @@
-/*
- * Renesas R-Car Audio DMAC support
- *
- * Copyright (C) 2015 Renesas Electronics Corp.
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car Audio DMAC support
+//
+// Copyright (C) 2015 Renesas Electronics Corp.
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/delay.h>
 #include <linux/of_dma.h>
 #include "rsnd.h"
diff --git a/sound/soc/sh/rcar/dvc.c b/sound/soc/sh/rcar/dvc.c
index ca1780e0b830..2b16e0ce6bc5 100644
--- a/sound/soc/sh/rcar/dvc.c
+++ b/sound/soc/sh/rcar/dvc.c
@@ -1,13 +1,9 @@
-/*
- * Renesas R-Car DVC support
- *
- * Copyright (C) 2014 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car DVC support
+//
+// Copyright (C) 2014 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  * Playback Volume
diff --git a/sound/soc/sh/rcar/gen.c b/sound/soc/sh/rcar/gen.c
index 25642e92dae0..0230301fe078 100644
--- a/sound/soc/sh/rcar/gen.c
+++ b/sound/soc/sh/rcar/gen.c
@@ -1,13 +1,9 @@
-/*
- * Renesas R-Car Gen1 SRU/SSI support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car Gen1 SRU/SSI support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  * #define DEBUG
diff --git a/sound/soc/sh/rcar/mix.c b/sound/soc/sh/rcar/mix.c
index 1881b2de9126..8e3b57eaa708 100644
--- a/sound/soc/sh/rcar/mix.c
+++ b/sound/soc/sh/rcar/mix.c
@@ -1,12 +1,8 @@
-/*
- * mix.c
- *
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// mix.c
+//
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  *		    CTUn	MIXn
diff --git a/sound/soc/sh/rcar/rsnd.h b/sound/soc/sh/rcar/rsnd.h
index 6d7280d2d9be..96d93330b1e1 100644
--- a/sound/soc/sh/rcar/rsnd.h
+++ b/sound/soc/sh/rcar/rsnd.h
@@ -1,13 +1,10 @@
-/*
- * Renesas R-Car
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #ifndef RSND_H
 #define RSND_H
 
diff --git a/sound/soc/sh/rcar/src.c b/sound/soc/sh/rcar/src.c
index 6c72d1a81cf5..beccfbac7581 100644
--- a/sound/soc/sh/rcar/src.c
+++ b/sound/soc/sh/rcar/src.c
@@ -1,13 +1,9 @@
-/*
- * Renesas R-Car SRC support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SRC support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 /*
  * you can enable below define if you don't need
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 6e1166ec24a0..3d9ea100a64f 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -1,16 +1,12 @@
-/*
- * Renesas R-Car SSIU/SSI support
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * Based on fsi.c
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SSIU/SSI support
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// Based on fsi.c
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
 
 /*
  * you can enable below define if you don't need
diff --git a/sound/soc/sh/rcar/ssiu.c b/sound/soc/sh/rcar/ssiu.c
index 47bdba9fc582..016fbf5ac242 100644
--- a/sound/soc/sh/rcar/ssiu.c
+++ b/sound/soc/sh/rcar/ssiu.c
@@ -1,12 +1,9 @@
-/*
- * Renesas R-Car SSIU support
- *
- * Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Renesas R-Car SSIU support
+//
+// Copyright (c) 2015 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include "rsnd.h"
 
 #define SSIU_NAME "ssiu"
-- 
cgit v1.2.3


From 0026c551bacd9654eaa6ee8e4aa19d52730e74f4 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:58:54 +0000
Subject: ASoC: migor: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/migor.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/sound/soc/sh/migor.c b/sound/soc/sh/migor.c
index ecb057ff9fbb..8739c9f60672 100644
--- a/sound/soc/sh/migor.c
+++ b/sound/soc/sh/migor.c
@@ -1,12 +1,8 @@
-/*
- * ALSA SoC driver for Migo-R
- *
- * Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ALSA SoC driver for Migo-R
+//
+// Copyright (C) 2009-2010 Guennadi Liakhovetski <g.liakhovetski@gmx.de>
 
 #include <linux/clkdev.h>
 #include <linux/device.h>
-- 
cgit v1.2.3


From ddfe227c0cbfb97b37afe123e014b9bc4df217b5 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:59:11 +0000
Subject: ASoC: dma-sh7760: convert to SPDX identifiers

Tidyup incoherence between MODULE_LICENSE and header license, too

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/dma-sh7760.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/sound/soc/sh/dma-sh7760.c b/sound/soc/sh/dma-sh7760.c
index 2dc3b762fdd9..922fb6aa3ed1 100644
--- a/sound/soc/sh/dma-sh7760.c
+++ b/sound/soc/sh/dma-sh7760.c
@@ -1,16 +1,14 @@
-/*
- * SH7760 ("camelot") DMABRG audio DMA unit support
- *
- * Copyright (C) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
- *  licensed under the terms outlined in the file COPYING at the root
- *  of the linux kernel sources.
- *
- * The SH7760 DMABRG provides 4 dma channels (2x rec, 2x play), which
- * trigger an interrupt when one half of the programmed transfer size
- * has been xmitted.
- *
- * FIXME: little-endian only for now
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// SH7760 ("camelot") DMABRG audio DMA unit support
+//
+// Copyright (C) 2007 Manuel Lauss <mano@roarinelk.homelinux.net>
+//
+// The SH7760 DMABRG provides 4 dma channels (2x rec, 2x play), which
+// trigger an interrupt when one half of the programmed transfer size
+// has been xmitted.
+//
+// FIXME: little-endian only for now
 
 #include <linux/module.h>
 #include <linux/gfp.h>
@@ -341,6 +339,6 @@ static struct platform_driver sh7760_pcm_driver = {
 
 module_platform_driver(sh7760_pcm_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SH7760 Audio DMA (DMABRG) driver");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
-- 
cgit v1.2.3


From 04433977b164c8ed0b65cd023c87c74da0fff2bf Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:59:27 +0000
Subject: ASoC: sh7760-ac97: convert to SPDX identifiers

Tidyup incoherence between MODULE_LICENSE and header license, too

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/sh7760-ac97.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/sound/soc/sh/sh7760-ac97.c b/sound/soc/sh/sh7760-ac97.c
index 4a3568a9bf59..4bb4c13cf860 100644
--- a/sound/soc/sh/sh7760-ac97.c
+++ b/sound/soc/sh/sh7760-ac97.c
@@ -1,10 +1,8 @@
-/*
- * Generic AC97 sound support for SH7760
- *
- * (c) 2007 Manuel Lauss
- *
- * Licensed under the GPLv2.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Generic AC97 sound support for SH7760
+//
+// (c) 2007 Manuel Lauss
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
@@ -68,6 +66,6 @@ static void __exit sh7760_ac97_exit(void)
 module_init(sh7760_ac97_init);
 module_exit(sh7760_ac97_exit);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("Generic SH7760 AC97 sound machine");
 MODULE_AUTHOR("Manuel Lauss <mano@roarinelk.homelinux.net>");
-- 
cgit v1.2.3


From 5986f83efab0435918e58416f89a5d82adc11f5d Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Fri, 15 Jun 2018 13:44:52 +0200
Subject: regulator: pfuze100: add pfuze3001 support

This patch extends binding according to support the pfuze3001 chip.

Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/regulator/pfuze100.txt     | 77 +++++++++++++++++++++-
 1 file changed, 76 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt
index f0ada3b14d70..672c939045ff 100644
--- a/Documentation/devicetree/bindings/regulator/pfuze100.txt
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt
@@ -1,7 +1,7 @@
 PFUZE100 family of regulators
 
 Required properties:
-- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000"
+- compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000", "fsl,pfuze3001"
 - reg: I2C slave address
 
 Required child node:
@@ -16,6 +16,8 @@ Required child node:
   sw1ab,sw2,sw3a,sw3b,swbst,vsnvs,vrefddr,vgen1~vgen6,coin
   --PFUZE3000
   sw1a,sw1b,sw2,sw3,swbst,vsnvs,vrefddr,vldo1,vldo2,vccsd,v33,vldo3,vldo4
+  --PFUZE3001
+  sw1,sw2,sw3,vsnvs,vldo1,vldo2,vccsd,v33,vldo3,vldo4
 
 Each regulator is defined using the standard binding for regulators.
 
@@ -303,3 +305,76 @@ Example 3: PFUZE3000
 			};
 		};
 	};
+
+Example 4: PFUZE 3001
+
+	pfuze3001: pmic@8 {
+		compatible = "fsl,pfuze3001";
+		reg = <0x08>;
+
+		regulators {
+			sw1_reg: sw1 {
+				regulator-min-microvolt = <700000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw2_reg: sw2 {
+				regulator-min-microvolt = <1500000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			sw3_reg: sw3 {
+				regulator-min-microvolt = <900000>;
+				regulator-max-microvolt = <1650000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			snvs_reg: vsnvs {
+				regulator-min-microvolt = <1000000>;
+				regulator-max-microvolt = <3000000>;
+				regulator-boot-on;
+				regulator-always-on;
+			};
+
+			vgen1_reg: vldo1 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen2_reg: vldo2 {
+				regulator-min-microvolt = <800000>;
+				regulator-max-microvolt = <1550000>;
+				regulator-always-on;
+			};
+
+			vgen3_reg: vccsd {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen4_reg: v33 {
+				regulator-min-microvolt = <2850000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen5_reg: vldo3 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+
+			vgen6_reg: vldo4 {
+				regulator-min-microvolt = <1800000>;
+				regulator-max-microvolt = <3300000>;
+				regulator-always-on;
+			};
+		};
+	};
-- 
cgit v1.2.3


From 297101ab85841319aac2c7843ca755d650c1964f Mon Sep 17 00:00:00 2001
From: Stefan Wahren <stefan.wahren@i2se.com>
Date: Fri, 15 Jun 2018 13:44:53 +0200
Subject: regulator: pfuze100: add pfuze3001 support

This extends the pfuze100 driver with pfuze3001 support.

Latest datasheet:
https://www.nxp.com/docs/en/data-sheet/PF3001.pdf

Signed-off-by: Robin Gong <yibin.gong@nxp.com>
Signed-off-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig              |  4 +-
 drivers/regulator/pfuze100-regulator.c | 78 +++++++++++++++++++++++++++++++---
 include/linux/regulator/pfuze100.h     | 11 +++++
 3 files changed, 84 insertions(+), 9 deletions(-)

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 5dbccf5f3037..2964eaea94c0 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -633,12 +633,12 @@ config REGULATOR_PCF50633
 	 on PCF50633
 
 config REGULATOR_PFUZE100
-	tristate "Freescale PFUZE100/200/3000 regulator driver"
+	tristate "Freescale PFUZE100/200/3000/3001 regulator driver"
 	depends on I2C
 	select REGMAP_I2C
 	help
 	  Say y here to support the regulators found on the Freescale
-	  PFUZE100/200/3000 PMIC.
+	  PFUZE100/200/3000/3001 PMIC.
 
 config REGULATOR_PV88060
 	tristate "Powerventure Semiconductor PV88060 regulator"
diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 8d9dbcc775ea..32f9af7f87c4 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -44,7 +44,7 @@
 #define PFUZE100_VGEN5VOL	0x70
 #define PFUZE100_VGEN6VOL	0x71
 
-enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3 };
+enum chips { PFUZE100, PFUZE200, PFUZE3000 = 3, PFUZE3001 = 0x31, };
 
 struct pfuze_regulator {
 	struct regulator_desc desc;
@@ -92,6 +92,7 @@ static const struct i2c_device_id pfuze_device_id[] = {
 	{.name = "pfuze100", .driver_data = PFUZE100},
 	{.name = "pfuze200", .driver_data = PFUZE200},
 	{.name = "pfuze3000", .driver_data = PFUZE3000},
+	{.name = "pfuze3001", .driver_data = PFUZE3001},
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, pfuze_device_id);
@@ -100,6 +101,7 @@ static const struct of_device_id pfuze_dt_ids[] = {
 	{ .compatible = "fsl,pfuze100", .data = (void *)PFUZE100},
 	{ .compatible = "fsl,pfuze200", .data = (void *)PFUZE200},
 	{ .compatible = "fsl,pfuze3000", .data = (void *)PFUZE3000},
+	{ .compatible = "fsl,pfuze3001", .data = (void *)PFUZE3001},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, pfuze_dt_ids);
@@ -108,10 +110,28 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay)
 {
 	struct pfuze_chip *pfuze100 = rdev_get_drvdata(rdev);
 	int id = rdev_get_id(rdev);
+	bool reg_has_ramp_delay;
 	unsigned int ramp_bits;
 	int ret;
 
-	if (id < PFUZE100_SWBST) {
+	switch (pfuze100->chip_id) {
+	case PFUZE3001:
+		/* no dynamic voltage scaling for PF3001 */
+		reg_has_ramp_delay = false;
+		break;
+	case PFUZE3000:
+		reg_has_ramp_delay = (id < PFUZE3000_SWBST);
+		break;
+	case PFUZE200:
+		reg_has_ramp_delay = (id < PFUZE200_SWBST);
+		break;
+	case PFUZE100:
+	default:
+		reg_has_ramp_delay = (id < PFUZE100_SWBST);
+		break;
+	}
+
+	if (reg_has_ramp_delay) {
 		ramp_delay = 12500 / ramp_delay;
 		ramp_bits = (ramp_delay >> 1) - (ramp_delay >> 3);
 		ret = regmap_update_bits(pfuze100->regmap,
@@ -119,8 +139,9 @@ static int pfuze100_set_ramp_delay(struct regulator_dev *rdev, int ramp_delay)
 					 0xc0, ramp_bits << 6);
 		if (ret < 0)
 			dev_err(pfuze100->dev, "ramp failed, err %d\n", ret);
-	} else
+	} else {
 		ret = -EACCES;
+	}
 
 	return ret;
 }
@@ -361,6 +382,19 @@ static struct pfuze_regulator pfuze3000_regulators[] = {
 	PFUZE100_VGEN_REG(PFUZE3000, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
 };
 
+static struct pfuze_regulator pfuze3001_regulators[] = {
+	PFUZE100_SWB_REG(PFUZE3001, SW1, PFUZE100_SW1ABVOL, 0x1f, pfuze3000_sw1a),
+	PFUZE100_SWB_REG(PFUZE3001, SW2, PFUZE100_SW2VOL, 0x7, pfuze3000_sw2lo),
+	PFUZE3000_SW3_REG(PFUZE3001, SW3, PFUZE100_SW3AVOL, 900000, 1650000, 50000),
+	PFUZE100_SWB_REG(PFUZE3001, VSNVS, PFUZE100_VSNVSVOL, 0x7, pfuze100_vsnvs),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO1, PFUZE100_VGEN1VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO2, PFUZE100_VGEN2VOL, 800000, 1550000, 50000),
+	PFUZE3000_VCC_REG(PFUZE3001, VCCSD, PFUZE100_VGEN3VOL, 2850000, 3300000, 150000),
+	PFUZE3000_VCC_REG(PFUZE3001, V33, PFUZE100_VGEN4VOL, 2850000, 3300000, 150000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO3, PFUZE100_VGEN5VOL, 1800000, 3300000, 100000),
+	PFUZE100_VGEN_REG(PFUZE3001, VLDO4, PFUZE100_VGEN6VOL, 1800000, 3300000, 100000),
+};
+
 #ifdef CONFIG_OF
 /* PFUZE100 */
 static struct of_regulator_match pfuze100_matches[] = {
@@ -418,6 +452,21 @@ static struct of_regulator_match pfuze3000_matches[] = {
 	{ .name = "vldo4",	},
 };
 
+/* PFUZE3001 */
+static struct of_regulator_match pfuze3001_matches[] = {
+
+	{ .name = "sw1",	},
+	{ .name = "sw2",	},
+	{ .name = "sw3",	},
+	{ .name = "vsnvs",	},
+	{ .name = "vldo1",	},
+	{ .name = "vldo2",	},
+	{ .name = "vccsd",	},
+	{ .name = "v33",	},
+	{ .name = "vldo3",	},
+	{ .name = "vldo4",	},
+};
+
 static struct of_regulator_match *pfuze_matches;
 
 static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
@@ -437,6 +486,11 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 	}
 
 	switch (chip->chip_id) {
+	case PFUZE3001:
+		pfuze_matches = pfuze3001_matches;
+		ret = of_regulator_match(dev, parent, pfuze3001_matches,
+					 ARRAY_SIZE(pfuze3001_matches));
+		break;
 	case PFUZE3000:
 		pfuze_matches = pfuze3000_matches;
 		ret = of_regulator_match(dev, parent, pfuze3000_matches,
@@ -508,7 +562,8 @@ static int pfuze_identify(struct pfuze_chip *pfuze_chip)
 		 */
 		dev_info(pfuze_chip->dev, "Assuming misprogrammed ID=0x8");
 	} else if ((value & 0x0f) != pfuze_chip->chip_id &&
-		   (value & 0xf0) >> 4 != pfuze_chip->chip_id) {
+		   (value & 0xf0) >> 4 != pfuze_chip->chip_id &&
+		   (value != pfuze_chip->chip_id)) {
 		/* device id NOT match with your setting */
 		dev_warn(pfuze_chip->dev, "Illegal ID: %x\n", value);
 		return -ENODEV;
@@ -588,6 +643,13 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 
 	/* use the right regulators after identify the right device */
 	switch (pfuze_chip->chip_id) {
+	case PFUZE3001:
+		pfuze_chip->pfuze_regulators = pfuze3001_regulators;
+		regulator_num = ARRAY_SIZE(pfuze3001_regulators);
+		sw_check_start = PFUZE3001_SW2;
+		sw_check_end = PFUZE3001_SW2;
+		sw_hi = 1 << 3;
+		break;
 	case PFUZE3000:
 		pfuze_chip->pfuze_regulators = pfuze3000_regulators;
 		regulator_num = ARRAY_SIZE(pfuze3000_regulators);
@@ -611,7 +673,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 	}
 	dev_info(&client->dev, "pfuze%s found.\n",
 		(pfuze_chip->chip_id == PFUZE100) ? "100" :
-		((pfuze_chip->chip_id == PFUZE200) ? "200" : "3000"));
+		(((pfuze_chip->chip_id == PFUZE200) ? "200" :
+		((pfuze_chip->chip_id == PFUZE3000) ? "3000" : "3001"))));
 
 	memcpy(pfuze_chip->regulator_descs, pfuze_chip->pfuze_regulators,
 		sizeof(pfuze_chip->regulator_descs));
@@ -636,7 +699,8 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 		if (i >= sw_check_start && i <= sw_check_end) {
 			regmap_read(pfuze_chip->regmap, desc->vsel_reg, &val);
 			if (val & sw_hi) {
-				if (pfuze_chip->chip_id == PFUZE3000) {
+				if (pfuze_chip->chip_id == PFUZE3000 ||
+					pfuze_chip->chip_id == PFUZE3001) {
 					desc->volt_table = pfuze3000_sw2hi;
 					desc->n_voltages = ARRAY_SIZE(pfuze3000_sw2hi);
 				} else {
@@ -675,5 +739,5 @@ static struct i2c_driver pfuze_driver = {
 module_i2c_driver(pfuze_driver);
 
 MODULE_AUTHOR("Robin Gong <b38343@freescale.com>");
-MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000 PMIC");
+MODULE_DESCRIPTION("Regulator Driver for Freescale PFUZE100/200/3000/3001 PMIC");
 MODULE_LICENSE("GPL v2");
diff --git a/include/linux/regulator/pfuze100.h b/include/linux/regulator/pfuze100.h
index e0ccf46f66cf..cb5aecd40f07 100644
--- a/include/linux/regulator/pfuze100.h
+++ b/include/linux/regulator/pfuze100.h
@@ -64,6 +64,17 @@
 #define PFUZE3000_VLDO3		11
 #define PFUZE3000_VLDO4		12
 
+#define PFUZE3001_SW1		0
+#define PFUZE3001_SW2		1
+#define PFUZE3001_SW3		2
+#define PFUZE3001_VSNVS		3
+#define PFUZE3001_VLDO1		4
+#define PFUZE3001_VLDO2		5
+#define PFUZE3001_VCCSD		6
+#define PFUZE3001_V33		7
+#define PFUZE3001_VLDO3		8
+#define PFUZE3001_VLDO4		9
+
 struct regulator_init_data;
 
 struct pfuze_regulator_platform_data {
-- 
cgit v1.2.3


From 7bd0c7ba62e8a9840f15fc4ff0122b29fe1b6413 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Thu, 7 Jun 2018 16:51:38 -0700
Subject: regulator: Fix typo in comment of struct regulator_linear_range

regulator_map_linar_range() => regulator_map_linear_range()

Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regulator/driver.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index fc2dc8df476f..dea96ee39fdc 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -46,7 +46,7 @@ enum regulator_status {
 /**
  * struct regulator_linear_range - specify linear voltage ranges
  *
- * Specify a range of voltages for regulator_map_linar_range() and
+ * Specify a range of voltages for regulator_map_linear_range() and
  * regulator_list_linear_range().
  *
  * @min_uV:  Lowest voltage in range
-- 
cgit v1.2.3


From 6c974d4dfafe5e9ee754f2a6fba0eb1864f1649e Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 12 Jun 2018 14:43:35 +0200
Subject: EDAC, i7core: Fix memleaks and use-after-free on probe and remove

Make sure to free and deregister the addrmatch and chancounts devices
allocated during probe in all error paths. Also fix use-after-free in a
probe error path and in the remove success path where the devices were
being put before before deregistration.

Signed-off-by: Johan Hovold <johan@kernel.org>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Fixes: 356f0a30860d ("i7core_edac: change the mem allocation scheme to make Documentation/kobject.txt happy")
Link: http://lkml.kernel.org/r/20180612124335.6420-2-johan@kernel.org
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/i7core_edac.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c
index 8ed4dd9c571b..8e120bf60624 100644
--- a/drivers/edac/i7core_edac.c
+++ b/drivers/edac/i7core_edac.c
@@ -1177,15 +1177,14 @@ static int i7core_create_sysfs_devices(struct mem_ctl_info *mci)
 
 	rc = device_add(pvt->addrmatch_dev);
 	if (rc < 0)
-		return rc;
+		goto err_put_addrmatch;
 
 	if (!pvt->is_registered) {
 		pvt->chancounts_dev = kzalloc(sizeof(*pvt->chancounts_dev),
 					      GFP_KERNEL);
 		if (!pvt->chancounts_dev) {
-			put_device(pvt->addrmatch_dev);
-			device_del(pvt->addrmatch_dev);
-			return -ENOMEM;
+			rc = -ENOMEM;
+			goto err_del_addrmatch;
 		}
 
 		pvt->chancounts_dev->type = &all_channel_counts_type;
@@ -1199,9 +1198,18 @@ static int i7core_create_sysfs_devices(struct mem_ctl_info *mci)
 
 		rc = device_add(pvt->chancounts_dev);
 		if (rc < 0)
-			return rc;
+			goto err_put_chancounts;
 	}
 	return 0;
+
+err_put_chancounts:
+	put_device(pvt->chancounts_dev);
+err_del_addrmatch:
+	device_del(pvt->addrmatch_dev);
+err_put_addrmatch:
+	put_device(pvt->addrmatch_dev);
+
+	return rc;
 }
 
 static void i7core_delete_sysfs_devices(struct mem_ctl_info *mci)
@@ -1211,11 +1219,11 @@ static void i7core_delete_sysfs_devices(struct mem_ctl_info *mci)
 	edac_dbg(1, "\n");
 
 	if (!pvt->is_registered) {
-		put_device(pvt->chancounts_dev);
 		device_del(pvt->chancounts_dev);
+		put_device(pvt->chancounts_dev);
 	}
-	put_device(pvt->addrmatch_dev);
 	device_del(pvt->addrmatch_dev);
+	put_device(pvt->addrmatch_dev);
 }
 
 /****************************************************************************
-- 
cgit v1.2.3


From 7cc90a5cadb1733d95d3c2bc147cbcf7843aa585 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:52:00 +0000
Subject: ASoC: rsnd: has .symmetric_rates if SSIs are sharing WS pin

If SSIs are sharing WS pin, it should has .symmetric_rates.
This patch sets it.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Tested-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/rcar/core.c | 6 ++++++
 sound/soc/sh/rcar/ssi.c  | 5 +++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index af04d41a4274..6bbdddef426e 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -1085,6 +1085,12 @@ static void __rsnd_dai_probe(struct rsnd_priv *priv,
 		of_node_put(capture);
 	}
 
+	if (rsnd_ssi_is_pin_sharing(io_capture) ||
+	    rsnd_ssi_is_pin_sharing(io_playback)) {
+		/* should have symmetric_rates if pin sharing */
+		drv->symmetric_rates = 1;
+	}
+
 	dev_dbg(dev, "%s (%s/%s)\n", rdai->name,
 		rsnd_io_to_mod_ssi(io_playback) ? "play"    : " -- ",
 		rsnd_io_to_mod_ssi(io_capture) ? "capture" : "  --   ");
diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 9538f76f8e20..4e605648918b 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -1055,9 +1055,10 @@ struct rsnd_mod *rsnd_ssi_mod_get(struct rsnd_priv *priv, int id)
 
 int __rsnd_ssi_is_pin_sharing(struct rsnd_mod *mod)
 {
-	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
+	if (!mod)
+		return 0;
 
-	return !!(rsnd_flags_has(ssi, RSND_SSI_CLK_PIN_SHARE));
+	return !!(rsnd_flags_has(rsnd_mod_to_ssi(mod), RSND_SSI_CLK_PIN_SHARE));
 }
 
 static u32 *rsnd_ssi_get_status(struct rsnd_dai_stream *io,
-- 
cgit v1.2.3


From 203cdf51f28820bee7893b4be392847418e6f4ec Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:52:17 +0000
Subject: ASoC: rsnd: SSI parent cares SWSP bit

SSICR has SWSP bit (= Serial WS Polarity) which decides WS pin 1st
channel polarity (low or hi). This bit shouldn't exchange after running.

Current SSI "parent" doesn't care SSICR, just controls clock only.
Because of this behavior, if platform uses SSI0 as playback,
SSI1 as capture, and if user starts capture -> playback order,
SSI0 SSICR::SWSP bit exchanged 0 -> 1 during captureing, and it makes
capture noise.
This patch cares SSICR on SSI parent, too.
Special thanks to Yokoyama-san

Reported-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx@renesas.com>
Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Tested-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/rcar/ssi.c | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/sound/soc/sh/rcar/ssi.c b/sound/soc/sh/rcar/ssi.c
index 4e605648918b..98dd120d830a 100644
--- a/sound/soc/sh/rcar/ssi.c
+++ b/sound/soc/sh/rcar/ssi.c
@@ -37,6 +37,7 @@
 #define	CHNL_4		(1 << 22)	/* Channels */
 #define	CHNL_6		(2 << 22)	/* Channels */
 #define	CHNL_8		(3 << 22)	/* Channels */
+#define DWL_MASK	(7 << 19)	/* Data Word Length mask */
 #define	DWL_8		(0 << 19)	/* Data Word Length */
 #define	DWL_16		(1 << 19)	/* Data Word Length */
 #define	DWL_18		(2 << 19)	/* Data Word Length */
@@ -353,21 +354,18 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 	struct rsnd_dai *rdai = rsnd_io_to_rdai(io);
 	struct snd_pcm_runtime *runtime = rsnd_io_to_runtime(io);
 	struct rsnd_ssi *ssi = rsnd_mod_to_ssi(mod);
-	u32 cr_own;
-	u32 cr_mode;
-	u32 wsr;
+	u32 cr_own	= ssi->cr_own;
+	u32 cr_mode	= ssi->cr_mode;
+	u32 wsr		= ssi->wsr;
 	int is_tdm;
 
-	if (rsnd_ssi_is_parent(mod, io))
-		return;
-
 	is_tdm = rsnd_runtime_is_ssi_tdm(io);
 
 	/*
 	 * always use 32bit system word.
 	 * see also rsnd_ssi_master_clk_enable()
 	 */
-	cr_own = FORCE | SWL_32;
+	cr_own |= FORCE | SWL_32;
 
 	if (rdai->bit_clk_inv)
 		cr_own |= SCKP;
@@ -377,9 +375,18 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 		cr_own |= SDTA;
 	if (rdai->sys_delay)
 		cr_own |= DEL;
+
+	/*
+	 * We shouldn't exchange SWSP after running.
+	 * This means, parent needs to care it.
+	 */
+	if (rsnd_ssi_is_parent(mod, io))
+		goto init_end;
+
 	if (rsnd_io_is_play(io))
 		cr_own |= TRMD;
 
+	cr_own &= ~DWL_MASK;
 	switch (snd_pcm_format_width(runtime->format)) {
 	case 16:
 		cr_own |= DWL_16;
@@ -406,7 +413,7 @@ static void rsnd_ssi_config_init(struct rsnd_mod *mod,
 		wsr	|= WS_MODE;
 		cr_own	|= CHNL_8;
 	}
-
+init_end:
 	ssi->cr_own	= cr_own;
 	ssi->cr_mode	= cr_mode;
 	ssi->wsr	= wsr;
@@ -470,15 +477,18 @@ static int rsnd_ssi_quit(struct rsnd_mod *mod,
 		return -EIO;
 	}
 
-	if (!rsnd_ssi_is_parent(mod, io))
-		ssi->cr_own	= 0;
-
 	rsnd_ssi_master_clk_stop(mod, io);
 
 	rsnd_mod_power_off(mod);
 
 	ssi->usrcnt--;
 
+	if (!ssi->usrcnt) {
+		ssi->cr_own	= 0;
+		ssi->cr_mode	= 0;
+		ssi->wsr	= 0;
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 6e56e5d04191aa20e08430dcb203c081fa247e93 Mon Sep 17 00:00:00 2001
From: "Agrawal, Akshu" <Akshu.Agrawal@amd.com>
Date: Thu, 7 Jun 2018 14:48:43 +0800
Subject: ASoC: AMD: Add NULL pointer check

Fix crash in those platforms whose machine driver does not expose
platform_info. For those platforms we rely on default value and
select I2SSP channel.

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 77203841c535..1458b5048498 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -773,7 +773,8 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	if (WARN_ON(!rtd))
 		return -EINVAL;
 
-	rtd->i2s_instance = pinfo->i2s_instance;
+	if (pinfo)
+		rtd->i2s_instance = pinfo->i2s_instance;
 	if (adata->asic_type == CHIP_STONEY) {
 		val = acp_reg_read(adata->acp_mmio,
 				   mmACP_I2S_16BIT_RESOLUTION_EN);
-- 
cgit v1.2.3


From 0ede01418854664526541eed7164c2e77df1646c Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 12 Jun 2018 12:19:29 +0300
Subject: drm/i915/vbt: switch to kernel unsigned int types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have fairly mixed uintN_t vs. uN usage throughout the driver, but try
to stick to kernel types at least where it's more prevalent.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/ed5de29c280797b20eb625d52592dcbba8326684.1528794959.git.jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_bios.c     | 4 ++--
 drivers/gpu/drm/i915/intel_vbt_defs.h | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 18b9e0444116..62a53eb89b6b 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -652,7 +652,7 @@ parse_edp(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 	}
 
 	if (bdb->version >= 173) {
-		uint8_t vswing;
+		u8 vswing;
 
 		/* Don't read from VBT if module parameter has valid value*/
 		if (i915_modparams.edp_vswing) {
@@ -964,7 +964,7 @@ static int goto_next_sequence_v3(const u8 *data, int index, int total)
 	 * includes MIPI_SEQ_ELEM_END byte, excludes the final MIPI_SEQ_END
 	 * byte.
 	 */
-	size_of_sequence = *((const uint32_t *)(data + index));
+	size_of_sequence = *((const u32 *)(data + index));
 	index += 4;
 
 	seq_end = index + size_of_sequence;
diff --git a/drivers/gpu/drm/i915/intel_vbt_defs.h b/drivers/gpu/drm/i915/intel_vbt_defs.h
index c614c9f3f28b..bba98cf83cbd 100644
--- a/drivers/gpu/drm/i915/intel_vbt_defs.h
+++ b/drivers/gpu/drm/i915/intel_vbt_defs.h
@@ -456,7 +456,7 @@ struct bdb_general_definitions {
 	 * number = (block_size - sizeof(bdb_general_definitions))/
 	 *	     defs->child_dev_size;
 	 */
-	uint8_t devices[0];
+	u8 devices[0];
 } __packed;
 
 /* Mask for DRRS / Panel Channel / SSC / BLT control bits extraction */
-- 
cgit v1.2.3


From faa087c476a3bc6bbbb8600043eb53733233e7c5 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 12 Jun 2018 12:19:30 +0300
Subject: drm/i915/hdmi: switch to kernel unsigned int types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have fairly mixed uintN_t vs. uN usage throughout the driver, but try
to stick to kernel types at least where it's more prevalent.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/d8b79de3d52e1fcaeabf3abfbb2ed99c4397ff2b.1528794959.git.jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_hdmi.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 3dd3ee259e7f..8398d4b31712 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -51,7 +51,7 @@ assert_hdmi_port_disabled(struct intel_hdmi *intel_hdmi)
 {
 	struct drm_device *dev = intel_hdmi_to_dev(intel_hdmi);
 	struct drm_i915_private *dev_priv = to_i915(dev);
-	uint32_t enabled_bits;
+	u32 enabled_bits;
 
 	enabled_bits = HAS_DDI(dev_priv) ? DDI_BUF_CTL_ENABLE : SDVO_ENABLE;
 
@@ -153,7 +153,7 @@ static void g4x_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	u32 val = I915_READ(VIDEO_DIP_CTL);
@@ -208,7 +208,7 @@ static void ibx_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
@@ -268,7 +268,7 @@ static void cpt_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
@@ -326,7 +326,7 @@ static void vlv_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
@@ -385,7 +385,7 @@ static void hsw_write_infoframe(struct drm_encoder *encoder,
 				unsigned int type,
 				const void *frame, ssize_t len)
 {
-	const uint32_t *data = frame;
+	const u32 *data = frame;
 	struct drm_device *dev = encoder->dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
@@ -448,7 +448,7 @@ static void intel_write_infoframe(struct drm_encoder *encoder,
 				  union hdmi_infoframe *frame)
 {
 	struct intel_digital_port *intel_dig_port = enc_to_dig_port(encoder);
-	uint8_t buffer[VIDEO_DIP_DATA_SIZE];
+	u8 buffer[VIDEO_DIP_DATA_SIZE];
 	ssize_t len;
 
 	/* see comment above for the reason for this offset */
-- 
cgit v1.2.3


From 93383b5705e689451fff99f2a6048750104982a3 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 12 Jun 2018 12:19:31 +0300
Subject: drm/i915/uncore: switch to kernel unsigned int types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have fairly mixed uintN_t vs. uN usage throughout the driver, but try
to stick to kernel types at least where it's more prevalent.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/4af5f30fc9665d1bed1eed09e7f749737749d739.1528794959.git.jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_uncore.h | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_uncore.h b/drivers/gpu/drm/i915/intel_uncore.h
index 47478d609630..2fbe93178fb2 100644
--- a/drivers/gpu/drm/i915/intel_uncore.h
+++ b/drivers/gpu/drm/i915/intel_uncore.h
@@ -67,21 +67,21 @@ struct intel_uncore_funcs {
 	void (*force_wake_put)(struct drm_i915_private *dev_priv,
 			       enum forcewake_domains domains);
 
-	uint8_t  (*mmio_readb)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
-	uint16_t (*mmio_readw)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
-	uint32_t (*mmio_readl)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
-	uint64_t (*mmio_readq)(struct drm_i915_private *dev_priv,
-			       i915_reg_t r, bool trace);
+	u8 (*mmio_readb)(struct drm_i915_private *dev_priv,
+			 i915_reg_t r, bool trace);
+	u16 (*mmio_readw)(struct drm_i915_private *dev_priv,
+			  i915_reg_t r, bool trace);
+	u32 (*mmio_readl)(struct drm_i915_private *dev_priv,
+			  i915_reg_t r, bool trace);
+	u64 (*mmio_readq)(struct drm_i915_private *dev_priv,
+			  i915_reg_t r, bool trace);
 
 	void (*mmio_writeb)(struct drm_i915_private *dev_priv,
-			    i915_reg_t r, uint8_t val, bool trace);
+			    i915_reg_t r, u8 val, bool trace);
 	void (*mmio_writew)(struct drm_i915_private *dev_priv,
-			    i915_reg_t r, uint16_t val, bool trace);
+			    i915_reg_t r, u16 val, bool trace);
 	void (*mmio_writel)(struct drm_i915_private *dev_priv,
-			    i915_reg_t r, uint32_t val, bool trace);
+			    i915_reg_t r, u32 val, bool trace);
 };
 
 struct intel_forcewake_range {
-- 
cgit v1.2.3


From accb1eb57196adcdd47efc7ded32f356ed396b6c Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 12 Jun 2018 12:56:21 +0300
Subject: drm/i915/dvo: switch to kernel unsigned int types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have fairly mixed uintN_t vs. uN usage throughout the driver, but try
to stick to kernel types at least where it's more prevalent.

v2: fix checkpatch warning on indentation

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612095621.21101-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/dvo_ch7017.c | 20 +++++++++---------
 drivers/gpu/drm/i915/dvo_ch7xxx.c | 22 ++++++++++----------
 drivers/gpu/drm/i915/dvo_ivch.c   | 26 +++++++++++------------
 drivers/gpu/drm/i915/dvo_ns2501.c | 44 +++++++++++++++++++--------------------
 drivers/gpu/drm/i915/dvo_sil164.c | 10 ++++-----
 drivers/gpu/drm/i915/dvo_tfp410.c | 16 +++++++-------
 drivers/gpu/drm/i915/intel_dvo.c  |  2 +-
 7 files changed, 70 insertions(+), 70 deletions(-)

diff --git a/drivers/gpu/drm/i915/dvo_ch7017.c b/drivers/gpu/drm/i915/dvo_ch7017.c
index 80b3e16cf48c..caac9942e1e3 100644
--- a/drivers/gpu/drm/i915/dvo_ch7017.c
+++ b/drivers/gpu/drm/i915/dvo_ch7017.c
@@ -159,7 +159,7 @@
 #define CH7017_BANG_LIMIT_CONTROL	0x7f
 
 struct ch7017_priv {
-	uint8_t dummy;
+	u8 dummy;
 };
 
 static void ch7017_dump_regs(struct intel_dvo_device *dvo);
@@ -186,7 +186,7 @@ static bool ch7017_read(struct intel_dvo_device *dvo, u8 addr, u8 *val)
 
 static bool ch7017_write(struct intel_dvo_device *dvo, u8 addr, u8 val)
 {
-	uint8_t buf[2] = { addr, val };
+	u8 buf[2] = { addr, val };
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -258,11 +258,11 @@ static void ch7017_mode_set(struct intel_dvo_device *dvo,
 			    const struct drm_display_mode *mode,
 			    const struct drm_display_mode *adjusted_mode)
 {
-	uint8_t lvds_pll_feedback_div, lvds_pll_vco_control;
-	uint8_t outputs_enable, lvds_control_2, lvds_power_down;
-	uint8_t horizontal_active_pixel_input;
-	uint8_t horizontal_active_pixel_output, vertical_active_line_output;
-	uint8_t active_input_line_output;
+	u8 lvds_pll_feedback_div, lvds_pll_vco_control;
+	u8 outputs_enable, lvds_control_2, lvds_power_down;
+	u8 horizontal_active_pixel_input;
+	u8 horizontal_active_pixel_output, vertical_active_line_output;
+	u8 active_input_line_output;
 
 	DRM_DEBUG_KMS("Registers before mode setting\n");
 	ch7017_dump_regs(dvo);
@@ -333,7 +333,7 @@ static void ch7017_mode_set(struct intel_dvo_device *dvo,
 /* set the CH7017 power state */
 static void ch7017_dpms(struct intel_dvo_device *dvo, bool enable)
 {
-	uint8_t val;
+	u8 val;
 
 	ch7017_read(dvo, CH7017_LVDS_POWER_DOWN, &val);
 
@@ -361,7 +361,7 @@ static void ch7017_dpms(struct intel_dvo_device *dvo, bool enable)
 
 static bool ch7017_get_hw_state(struct intel_dvo_device *dvo)
 {
-	uint8_t val;
+	u8 val;
 
 	ch7017_read(dvo, CH7017_LVDS_POWER_DOWN, &val);
 
@@ -373,7 +373,7 @@ static bool ch7017_get_hw_state(struct intel_dvo_device *dvo)
 
 static void ch7017_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint8_t val;
+	u8 val;
 
 #define DUMP(reg)					\
 do {							\
diff --git a/drivers/gpu/drm/i915/dvo_ch7xxx.c b/drivers/gpu/drm/i915/dvo_ch7xxx.c
index 7aeeffd2428b..397ac5233726 100644
--- a/drivers/gpu/drm/i915/dvo_ch7xxx.c
+++ b/drivers/gpu/drm/i915/dvo_ch7xxx.c
@@ -85,7 +85,7 @@ SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
  */
 
 static struct ch7xxx_id_struct {
-	uint8_t vid;
+	u8 vid;
 	char *name;
 } ch7xxx_ids[] = {
 	{ CH7011_VID, "CH7011" },
@@ -96,7 +96,7 @@ static struct ch7xxx_id_struct {
 };
 
 static struct ch7xxx_did_struct {
-	uint8_t did;
+	u8 did;
 	char *name;
 } ch7xxx_dids[] = {
 	{ CH7xxx_DID, "CH7XXX" },
@@ -107,7 +107,7 @@ struct ch7xxx_priv {
 	bool quiet;
 };
 
-static char *ch7xxx_get_id(uint8_t vid)
+static char *ch7xxx_get_id(u8 vid)
 {
 	int i;
 
@@ -119,7 +119,7 @@ static char *ch7xxx_get_id(uint8_t vid)
 	return NULL;
 }
 
-static char *ch7xxx_get_did(uint8_t did)
+static char *ch7xxx_get_did(u8 did)
 {
 	int i;
 
@@ -132,7 +132,7 @@ static char *ch7xxx_get_did(uint8_t did)
 }
 
 /** Reads an 8 bit register */
-static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
+static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct ch7xxx_priv *ch7xxx = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -170,11 +170,11 @@ static bool ch7xxx_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 }
 
 /** Writes an 8 bit register */
-static bool ch7xxx_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool ch7xxx_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct ch7xxx_priv *ch7xxx = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -201,7 +201,7 @@ static bool ch7xxx_init(struct intel_dvo_device *dvo,
 {
 	/* this will detect the CH7xxx chip on the specified i2c bus */
 	struct ch7xxx_priv *ch7xxx;
-	uint8_t vendor, device;
+	u8 vendor, device;
 	char *name, *devid;
 
 	ch7xxx = kzalloc(sizeof(struct ch7xxx_priv), GFP_KERNEL);
@@ -244,7 +244,7 @@ out:
 
 static enum drm_connector_status ch7xxx_detect(struct intel_dvo_device *dvo)
 {
-	uint8_t cdet, orig_pm, pm;
+	u8 cdet, orig_pm, pm;
 
 	ch7xxx_readb(dvo, CH7xxx_PM, &orig_pm);
 
@@ -276,7 +276,7 @@ static void ch7xxx_mode_set(struct intel_dvo_device *dvo,
 			    const struct drm_display_mode *mode,
 			    const struct drm_display_mode *adjusted_mode)
 {
-	uint8_t tvco, tpcp, tpd, tlpf, idf;
+	u8 tvco, tpcp, tpd, tlpf, idf;
 
 	if (mode->clock <= 65000) {
 		tvco = 0x23;
@@ -336,7 +336,7 @@ static void ch7xxx_dump_regs(struct intel_dvo_device *dvo)
 	int i;
 
 	for (i = 0; i < CH7xxx_NUM_REGS; i++) {
-		uint8_t val;
+		u8 val;
 		if ((i % 8) == 0)
 			DRM_DEBUG_KMS("\n %02X: ", i);
 		ch7xxx_readb(dvo, i, &val);
diff --git a/drivers/gpu/drm/i915/dvo_ivch.c b/drivers/gpu/drm/i915/dvo_ivch.c
index c73aff163908..24278cc49090 100644
--- a/drivers/gpu/drm/i915/dvo_ivch.c
+++ b/drivers/gpu/drm/i915/dvo_ivch.c
@@ -161,7 +161,7 @@
  * instead. The following list contains all registers that
  * require saving.
  */
-static const uint16_t backup_addresses[] = {
+static const u16 backup_addresses[] = {
 	0x11, 0x12,
 	0x18, 0x19, 0x1a, 0x1f,
 	0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27,
@@ -174,11 +174,11 @@ static const uint16_t backup_addresses[] = {
 struct ivch_priv {
 	bool quiet;
 
-	uint16_t width, height;
+	u16 width, height;
 
 	/* Register backup */
 
-	uint16_t reg_backup[ARRAY_SIZE(backup_addresses)];
+	u16 reg_backup[ARRAY_SIZE(backup_addresses)];
 };
 
 
@@ -188,7 +188,7 @@ static void ivch_dump_regs(struct intel_dvo_device *dvo);
  *
  * Each of the 256 registers are 16 bits long.
  */
-static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data)
+static bool ivch_read(struct intel_dvo_device *dvo, int addr, u16 *data)
 {
 	struct ivch_priv *priv = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -231,7 +231,7 @@ static bool ivch_read(struct intel_dvo_device *dvo, int addr, uint16_t *data)
 }
 
 /* Writes a 16-bit register on the ivch */
-static bool ivch_write(struct intel_dvo_device *dvo, int addr, uint16_t data)
+static bool ivch_write(struct intel_dvo_device *dvo, int addr, u16 data)
 {
 	struct ivch_priv *priv = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -263,7 +263,7 @@ static bool ivch_init(struct intel_dvo_device *dvo,
 		      struct i2c_adapter *adapter)
 {
 	struct ivch_priv *priv;
-	uint16_t temp;
+	u16 temp;
 	int i;
 
 	priv = kzalloc(sizeof(struct ivch_priv), GFP_KERNEL);
@@ -342,7 +342,7 @@ static void ivch_reset(struct intel_dvo_device *dvo)
 static void ivch_dpms(struct intel_dvo_device *dvo, bool enable)
 {
 	int i;
-	uint16_t vr01, vr30, backlight;
+	u16 vr01, vr30, backlight;
 
 	ivch_reset(dvo);
 
@@ -379,7 +379,7 @@ static void ivch_dpms(struct intel_dvo_device *dvo, bool enable)
 
 static bool ivch_get_hw_state(struct intel_dvo_device *dvo)
 {
-	uint16_t vr01;
+	u16 vr01;
 
 	ivch_reset(dvo);
 
@@ -398,9 +398,9 @@ static void ivch_mode_set(struct intel_dvo_device *dvo,
 			  const struct drm_display_mode *adjusted_mode)
 {
 	struct ivch_priv *priv = dvo->dev_priv;
-	uint16_t vr40 = 0;
-	uint16_t vr01 = 0;
-	uint16_t vr10;
+	u16 vr40 = 0;
+	u16 vr01 = 0;
+	u16 vr10;
 
 	ivch_reset(dvo);
 
@@ -416,7 +416,7 @@ static void ivch_mode_set(struct intel_dvo_device *dvo,
 
 	if (mode->hdisplay != adjusted_mode->crtc_hdisplay ||
 	    mode->vdisplay != adjusted_mode->crtc_vdisplay) {
-		uint16_t x_ratio, y_ratio;
+		u16 x_ratio, y_ratio;
 
 		vr01 |= VR01_PANEL_FIT_ENABLE;
 		vr40 |= VR40_CLOCK_GATING_ENABLE;
@@ -438,7 +438,7 @@ static void ivch_mode_set(struct intel_dvo_device *dvo,
 
 static void ivch_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint16_t val;
+	u16 val;
 
 	ivch_read(dvo, VR00, &val);
 	DRM_DEBUG_KMS("VR00: 0x%04x\n", val);
diff --git a/drivers/gpu/drm/i915/dvo_ns2501.c b/drivers/gpu/drm/i915/dvo_ns2501.c
index 2379c33cfe51..c584e01dc8dc 100644
--- a/drivers/gpu/drm/i915/dvo_ns2501.c
+++ b/drivers/gpu/drm/i915/dvo_ns2501.c
@@ -191,8 +191,8 @@ enum {
 };
 
 struct ns2501_reg {
-	 uint8_t offset;
-	 uint8_t value;
+	u8 offset;
+	u8 value;
 };
 
 /*
@@ -202,23 +202,23 @@ struct ns2501_reg {
  * read all this with a grain of salt.
  */
 struct ns2501_configuration {
-	uint8_t sync;		/* configuration of the C0 register */
-	uint8_t conf;		/* configuration register 8 */
-	uint8_t syncb;		/* configuration register 41 */
-	uint8_t	dither;		/* configuration of the dithering */
-	uint8_t pll_a;		/* PLL configuration, register A, 1B */
-	uint16_t pll_b;		/* PLL configuration, register B, 1C/1D */
-	uint16_t hstart;	/* horizontal start, registers C1/C2 */
-	uint16_t hstop;		/* horizontal total, registers C3/C4 */
-	uint16_t vstart;	/* vertical start, registers C5/C6 */
-	uint16_t vstop;		/* vertical total, registers C7/C8 */
-	uint16_t vsync;         /* manual vertical sync start, 80/81 */
-	uint16_t vtotal;        /* number of lines generated, 82/83 */
-	uint16_t hpos;		/* horizontal position + 256, 98/99  */
-	uint16_t vpos;		/* vertical position, 8e/8f */
-	uint16_t voffs;		/* vertical output offset, 9c/9d */
-	uint16_t hscale;	/* horizontal scaling factor, b8/b9 */
-	uint16_t vscale;	/* vertical scaling factor, 10/11 */
+	u8 sync;		/* configuration of the C0 register */
+	u8 conf;		/* configuration register 8 */
+	u8 syncb;		/* configuration register 41 */
+	u8 dither;		/* configuration of the dithering */
+	u8 pll_a;		/* PLL configuration, register A, 1B */
+	u16 pll_b;		/* PLL configuration, register B, 1C/1D */
+	u16 hstart;		/* horizontal start, registers C1/C2 */
+	u16 hstop;		/* horizontal total, registers C3/C4 */
+	u16 vstart;		/* vertical start, registers C5/C6 */
+	u16 vstop;		/* vertical total, registers C7/C8 */
+	u16 vsync;		/* manual vertical sync start, 80/81 */
+	u16 vtotal;		/* number of lines generated, 82/83 */
+	u16 hpos;		/* horizontal position + 256, 98/99  */
+	u16 vpos;		/* vertical position, 8e/8f */
+	u16 voffs;		/* vertical output offset, 9c/9d */
+	u16 hscale;		/* horizontal scaling factor, b8/b9 */
+	u16 vscale;		/* vertical scaling factor, 10/11 */
 };
 
 /*
@@ -389,7 +389,7 @@ struct ns2501_priv {
 ** If it returns false, it might be wise to enable the
 ** DVO with the above function.
 */
-static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, uint8_t * ch)
+static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct ns2501_priv *ns = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -434,11 +434,11 @@ static bool ns2501_readb(struct intel_dvo_device *dvo, int addr, uint8_t * ch)
 ** If it returns false, it might be wise to enable the
 ** DVO with the above function.
 */
-static bool ns2501_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool ns2501_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct ns2501_priv *ns = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
diff --git a/drivers/gpu/drm/i915/dvo_sil164.c b/drivers/gpu/drm/i915/dvo_sil164.c
index 1c1a0674dbab..4ae5d8fd9ff0 100644
--- a/drivers/gpu/drm/i915/dvo_sil164.c
+++ b/drivers/gpu/drm/i915/dvo_sil164.c
@@ -65,7 +65,7 @@ struct sil164_priv {
 
 #define SILPTR(d) ((SIL164Ptr)(d->DriverPrivate.ptr))
 
-static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
+static bool sil164_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct sil164_priv *sil = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -102,11 +102,11 @@ static bool sil164_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 	return false;
 }
 
-static bool sil164_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool sil164_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct sil164_priv *sil = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -173,7 +173,7 @@ out:
 
 static enum drm_connector_status sil164_detect(struct intel_dvo_device *dvo)
 {
-	uint8_t reg9;
+	u8 reg9;
 
 	sil164_readb(dvo, SIL164_REG9, &reg9);
 
@@ -243,7 +243,7 @@ static bool sil164_get_hw_state(struct intel_dvo_device *dvo)
 
 static void sil164_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint8_t val;
+	u8 val;
 
 	sil164_readb(dvo, SIL164_FREQ_LO, &val);
 	DRM_DEBUG_KMS("SIL164_FREQ_LO: 0x%02x\n", val);
diff --git a/drivers/gpu/drm/i915/dvo_tfp410.c b/drivers/gpu/drm/i915/dvo_tfp410.c
index 31e181da93db..d603bc2f2506 100644
--- a/drivers/gpu/drm/i915/dvo_tfp410.c
+++ b/drivers/gpu/drm/i915/dvo_tfp410.c
@@ -90,7 +90,7 @@ struct tfp410_priv {
 	bool quiet;
 };
 
-static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
+static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, u8 *ch)
 {
 	struct tfp410_priv *tfp = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
@@ -127,11 +127,11 @@ static bool tfp410_readb(struct intel_dvo_device *dvo, int addr, uint8_t *ch)
 	return false;
 }
 
-static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
+static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, u8 ch)
 {
 	struct tfp410_priv *tfp = dvo->dev_priv;
 	struct i2c_adapter *adapter = dvo->i2c_bus;
-	uint8_t out_buf[2];
+	u8 out_buf[2];
 	struct i2c_msg msg = {
 		.addr = dvo->slave_addr,
 		.flags = 0,
@@ -155,7 +155,7 @@ static bool tfp410_writeb(struct intel_dvo_device *dvo, int addr, uint8_t ch)
 
 static int tfp410_getid(struct intel_dvo_device *dvo, int addr)
 {
-	uint8_t ch1, ch2;
+	u8 ch1, ch2;
 
 	if (tfp410_readb(dvo, addr+0, &ch1) &&
 	    tfp410_readb(dvo, addr+1, &ch2))
@@ -203,7 +203,7 @@ out:
 static enum drm_connector_status tfp410_detect(struct intel_dvo_device *dvo)
 {
 	enum drm_connector_status ret = connector_status_disconnected;
-	uint8_t ctl2;
+	u8 ctl2;
 
 	if (tfp410_readb(dvo, TFP410_CTL_2, &ctl2)) {
 		if (ctl2 & TFP410_CTL_2_RSEN)
@@ -236,7 +236,7 @@ static void tfp410_mode_set(struct intel_dvo_device *dvo,
 /* set the tfp410 power state */
 static void tfp410_dpms(struct intel_dvo_device *dvo, bool enable)
 {
-	uint8_t ctl1;
+	u8 ctl1;
 
 	if (!tfp410_readb(dvo, TFP410_CTL_1, &ctl1))
 		return;
@@ -251,7 +251,7 @@ static void tfp410_dpms(struct intel_dvo_device *dvo, bool enable)
 
 static bool tfp410_get_hw_state(struct intel_dvo_device *dvo)
 {
-	uint8_t ctl1;
+	u8 ctl1;
 
 	if (!tfp410_readb(dvo, TFP410_CTL_1, &ctl1))
 		return false;
@@ -264,7 +264,7 @@ static bool tfp410_get_hw_state(struct intel_dvo_device *dvo)
 
 static void tfp410_dump_regs(struct intel_dvo_device *dvo)
 {
-	uint8_t val, val2;
+	u8 val, val2;
 
 	tfp410_readb(dvo, TFP410_REV, &val);
 	DRM_DEBUG_KMS("TFP410_REV: 0x%02X\n", val);
diff --git a/drivers/gpu/drm/i915/intel_dvo.c b/drivers/gpu/drm/i915/intel_dvo.c
index 27f16db8953a..4e142ff49708 100644
--- a/drivers/gpu/drm/i915/intel_dvo.c
+++ b/drivers/gpu/drm/i915/intel_dvo.c
@@ -438,7 +438,7 @@ void intel_dvo_init(struct drm_i915_private *dev_priv)
 		int gpio;
 		bool dvoinit;
 		enum pipe pipe;
-		uint32_t dpll[I915_MAX_PIPES];
+		u32 dpll[I915_MAX_PIPES];
 		enum port port;
 
 		/*
-- 
cgit v1.2.3


From fd620bf92a609315241fa5440d336ef17ea76550 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 12 Jun 2018 12:19:33 +0300
Subject: drm/i915/backlight: switch to kernel unsigned int types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have fairly mixed uintN_t vs. uN usage throughout the driver, but try
to stick to kernel types at least where it's more prevalent.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/e68c3f16738eb3ab9f276d797f20326ed6d15848.1528794959.git.jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_dp_aux_backlight.c | 12 ++++++------
 drivers/gpu/drm/i915/intel_panel.c            |  8 ++++----
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
index 2bb2ceb9d463..357136f17f85 100644
--- a/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
+++ b/drivers/gpu/drm/i915/intel_dp_aux_backlight.c
@@ -26,7 +26,7 @@
 
 static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
 {
-	uint8_t reg_val = 0;
+	u8 reg_val = 0;
 
 	/* Early return when display use other mechanism to enable backlight. */
 	if (!(intel_dp->edp_dpcd[1] & DP_EDP_BACKLIGHT_AUX_ENABLE_CAP))
@@ -54,11 +54,11 @@ static void set_aux_backlight_enable(struct intel_dp *intel_dp, bool enable)
  * Read the current backlight value from DPCD register(s) based
  * on if 8-bit(MSB) or 16-bit(MSB and LSB) values are supported
  */
-static uint32_t intel_dp_aux_get_backlight(struct intel_connector *connector)
+static u32 intel_dp_aux_get_backlight(struct intel_connector *connector)
 {
 	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
-	uint8_t read_val[2] = { 0x0 };
-	uint16_t level = 0;
+	u8 read_val[2] = { 0x0 };
+	u16 level = 0;
 
 	if (drm_dp_dpcd_read(&intel_dp->aux, DP_EDP_BACKLIGHT_BRIGHTNESS_MSB,
 			     &read_val, sizeof(read_val)) < 0) {
@@ -82,7 +82,7 @@ intel_dp_aux_set_backlight(const struct drm_connector_state *conn_state, u32 lev
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
-	uint8_t vals[2] = { 0x0 };
+	u8 vals[2] = { 0x0 };
 
 	vals[0] = level;
 
@@ -178,7 +178,7 @@ static void intel_dp_aux_enable_backlight(const struct intel_crtc_state *crtc_st
 {
 	struct intel_connector *connector = to_intel_connector(conn_state->connector);
 	struct intel_dp *intel_dp = enc_to_intel_dp(&connector->encoder->base);
-	uint8_t dpcd_buf, new_dpcd_buf, edp_backlight_mode;
+	u8 dpcd_buf, new_dpcd_buf, edp_backlight_mode;
 
 	if (drm_dp_dpcd_readb(&intel_dp->aux,
 			DP_EDP_BACKLIGHT_MODE_SET_REGISTER, &dpcd_buf) != 1) {
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index b443278e569c..14b827ec5427 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -406,11 +406,11 @@ intel_panel_detect(struct drm_i915_private *dev_priv)
  * Return @source_val in range [@source_min..@source_max] scaled to range
  * [@target_min..@target_max].
  */
-static uint32_t scale(uint32_t source_val,
-		      uint32_t source_min, uint32_t source_max,
-		      uint32_t target_min, uint32_t target_max)
+static u32 scale(u32 source_val,
+		 u32 source_min, u32 source_max,
+		 u32 target_min, u32 target_max)
 {
-	uint64_t target_val;
+	u64 target_val;
 
 	WARN_ON(source_min > source_max);
 	WARN_ON(target_min > target_max);
-- 
cgit v1.2.3


From c25004964c5a8a0ee7b749bf969b3621dcaf2597 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 12 Jun 2018 12:19:34 +0300
Subject: drm/i915/audio: switch to kernel unsigned int types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have fairly mixed uintN_t vs. uN usage throughout the driver, but try
to stick to kernel types at least where it's more prevalent.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/808b06e1f0a95a4ee892553abf11fdbc30025571.1528794959.git.jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_audio.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 3ea566f99450..4e4c0ec44f35 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -198,13 +198,13 @@ static int audio_config_hdmi_get_n(const struct intel_crtc_state *crtc_state,
 }
 
 static bool intel_eld_uptodate(struct drm_connector *connector,
-			       i915_reg_t reg_eldv, uint32_t bits_eldv,
-			       i915_reg_t reg_elda, uint32_t bits_elda,
+			       i915_reg_t reg_eldv, u32 bits_eldv,
+			       i915_reg_t reg_elda, u32 bits_elda,
 			       i915_reg_t reg_edid)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	uint8_t *eld = connector->eld;
-	uint32_t tmp;
+	u8 *eld = connector->eld;
+	u32 tmp;
 	int i;
 
 	tmp = I915_READ(reg_eldv);
@@ -218,7 +218,7 @@ static bool intel_eld_uptodate(struct drm_connector *connector,
 	I915_WRITE(reg_elda, tmp);
 
 	for (i = 0; i < drm_eld_size(eld) / 4; i++)
-		if (I915_READ(reg_edid) != *((uint32_t *)eld + i))
+		if (I915_READ(reg_edid) != *((u32 *)eld + i))
 			return false;
 
 	return true;
@@ -229,7 +229,7 @@ static void g4x_audio_codec_disable(struct intel_encoder *encoder,
 				    const struct drm_connector_state *old_conn_state)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	uint32_t eldv, tmp;
+	u32 eldv, tmp;
 
 	DRM_DEBUG_KMS("Disable audio codec\n");
 
@@ -251,9 +251,9 @@ static void g4x_audio_codec_enable(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct drm_connector *connector = conn_state->connector;
-	uint8_t *eld = connector->eld;
-	uint32_t eldv;
-	uint32_t tmp;
+	u8 *eld = connector->eld;
+	u32 eldv;
+	u32 tmp;
 	int len, i;
 
 	DRM_DEBUG_KMS("Enable audio codec, %u bytes ELD\n", eld[2]);
@@ -278,7 +278,7 @@ static void g4x_audio_codec_enable(struct intel_encoder *encoder,
 	len = min(drm_eld_size(eld) / 4, len);
 	DRM_DEBUG_DRIVER("ELD size %d\n", len);
 	for (i = 0; i < len; i++)
-		I915_WRITE(G4X_HDMIW_HDMIEDID, *((uint32_t *)eld + i));
+		I915_WRITE(G4X_HDMIW_HDMIEDID, *((u32 *)eld + i));
 
 	tmp = I915_READ(G4X_AUD_CNTL_ST);
 	tmp |= eldv;
@@ -393,7 +393,7 @@ static void hsw_audio_codec_disable(struct intel_encoder *encoder,
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	enum pipe pipe = crtc->pipe;
-	uint32_t tmp;
+	u32 tmp;
 
 	DRM_DEBUG_KMS("Disable audio codec on pipe %c\n", pipe_name(pipe));
 
@@ -426,8 +426,8 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
 	struct drm_connector *connector = conn_state->connector;
 	enum pipe pipe = crtc->pipe;
-	const uint8_t *eld = connector->eld;
-	uint32_t tmp;
+	const u8 *eld = connector->eld;
+	u32 tmp;
 	int len, i;
 
 	DRM_DEBUG_KMS("Enable audio codec on pipe %c, %u bytes ELD\n",
@@ -456,7 +456,7 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 	/* Up to 84 bytes of hw ELD buffer */
 	len = min(drm_eld_size(eld), 84);
 	for (i = 0; i < len / 4; i++)
-		I915_WRITE(HSW_AUD_EDID_DATA(pipe), *((uint32_t *)eld + i));
+		I915_WRITE(HSW_AUD_EDID_DATA(pipe), *((u32 *)eld + i));
 
 	/* ELD valid */
 	tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
@@ -477,7 +477,7 @@ static void ilk_audio_codec_disable(struct intel_encoder *encoder,
 	struct intel_crtc *crtc = to_intel_crtc(old_crtc_state->base.crtc);
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
-	uint32_t tmp, eldv;
+	u32 tmp, eldv;
 	i915_reg_t aud_config, aud_cntrl_st2;
 
 	DRM_DEBUG_KMS("Disable audio codec on port %c, pipe %c\n",
@@ -524,8 +524,8 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 	struct drm_connector *connector = conn_state->connector;
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
-	uint8_t *eld = connector->eld;
-	uint32_t tmp, eldv;
+	u8 *eld = connector->eld;
+	u32 tmp, eldv;
 	int len, i;
 	i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2;
 
@@ -575,7 +575,7 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 	/* Up to 84 bytes of hw ELD buffer */
 	len = min(drm_eld_size(eld), 84);
 	for (i = 0; i < len / 4; i++)
-		I915_WRITE(hdmiw_hdmiedid, *((uint32_t *)eld + i));
+		I915_WRITE(hdmiw_hdmiedid, *((u32 *)eld + i));
 
 	/* ELD valid */
 	tmp = I915_READ(aud_cntrl_st2);
-- 
cgit v1.2.3


From 02f361f5fdfb7bc24fcd686ae581114038eacbdd Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 12 Jun 2018 12:19:35 +0300
Subject: drm/i915/lspcon: switch to kernel unsigned int types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We have fairly mixed uintN_t vs. uN usage throughout the driver, but try
to stick to kernel types at least where it's more prevalent.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1e132575785d9b615208eb60ee5e388df5991172.1528794959.git.jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_lspcon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_lspcon.c b/drivers/gpu/drm/i915/intel_lspcon.c
index 8ae8f42f430a..5dae16ccd9f1 100644
--- a/drivers/gpu/drm/i915/intel_lspcon.c
+++ b/drivers/gpu/drm/i915/intel_lspcon.c
@@ -116,7 +116,7 @@ static int lspcon_change_mode(struct intel_lspcon *lspcon,
 
 static bool lspcon_wake_native_aux_ch(struct intel_lspcon *lspcon)
 {
-	uint8_t rev;
+	u8 rev;
 
 	if (drm_dp_dpcd_readb(&lspcon_to_intel_dp(lspcon)->aux, DP_DPCD_REV,
 			      &rev) != 1) {
-- 
cgit v1.2.3


From 3e247b0fb540a9a503a71ef6b918a3443e49655f Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Thu, 7 Jun 2018 19:40:32 +0000
Subject: spi: remove unused adi_spi3.h header

include/linux/spi/adi_spi3.h is unused since commit 47838669de9d ("spi: remove blackfin related host drivers")
Finish the cleaning by removing it.

Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/adi_spi3.h | 254 -------------------------------------------
 1 file changed, 254 deletions(-)
 delete mode 100644 include/linux/spi/adi_spi3.h

diff --git a/include/linux/spi/adi_spi3.h b/include/linux/spi/adi_spi3.h
deleted file mode 100644
index c84123aa1d06..000000000000
--- a/include/linux/spi/adi_spi3.h
+++ /dev/null
@@ -1,254 +0,0 @@
-/*
- * Analog Devices SPI3 controller driver
- *
- * Copyright (c) 2014 Analog Devices Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#ifndef _ADI_SPI3_H_
-#define _ADI_SPI3_H_
-
-#include <linux/types.h>
-
-/* SPI_CONTROL */
-#define SPI_CTL_EN                  0x00000001    /* Enable */
-#define SPI_CTL_MSTR                0x00000002    /* Master/Slave */
-#define SPI_CTL_PSSE                0x00000004    /* controls modf error in master mode */
-#define SPI_CTL_ODM                 0x00000008    /* Open Drain Mode */
-#define SPI_CTL_CPHA                0x00000010    /* Clock Phase */
-#define SPI_CTL_CPOL                0x00000020    /* Clock Polarity */
-#define SPI_CTL_ASSEL               0x00000040    /* Slave Select Pin Control */
-#define SPI_CTL_SELST               0x00000080    /* Slave Select Polarity in-between transfers */
-#define SPI_CTL_EMISO               0x00000100    /* Enable MISO */
-#define SPI_CTL_SIZE                0x00000600    /* Word Transfer Size */
-#define SPI_CTL_SIZE08              0x00000000    /* SIZE: 8 bits */
-#define SPI_CTL_SIZE16              0x00000200    /* SIZE: 16 bits */
-#define SPI_CTL_SIZE32              0x00000400    /* SIZE: 32 bits */
-#define SPI_CTL_LSBF                0x00001000    /* LSB First */
-#define SPI_CTL_FCEN                0x00002000    /* Flow-Control Enable */
-#define SPI_CTL_FCCH                0x00004000    /* Flow-Control Channel Selection */
-#define SPI_CTL_FCPL                0x00008000    /* Flow-Control Polarity */
-#define SPI_CTL_FCWM                0x00030000    /* Flow-Control Water-Mark */
-#define SPI_CTL_FIFO0               0x00000000    /* FCWM: TFIFO empty or RFIFO Full */
-#define SPI_CTL_FIFO1               0x00010000    /* FCWM: TFIFO 75% or more empty or RFIFO 75% or more full */
-#define SPI_CTL_FIFO2               0x00020000    /* FCWM: TFIFO 50% or more empty or RFIFO 50% or more full */
-#define SPI_CTL_FMODE               0x00040000    /* Fast-mode Enable */
-#define SPI_CTL_MIOM                0x00300000    /* Multiple I/O Mode */
-#define SPI_CTL_MIO_DIS             0x00000000    /* MIOM: Disable */
-#define SPI_CTL_MIO_DUAL            0x00100000    /* MIOM: Enable DIOM (Dual I/O Mode) */
-#define SPI_CTL_MIO_QUAD            0x00200000    /* MIOM: Enable QUAD (Quad SPI Mode) */
-#define SPI_CTL_SOSI                0x00400000    /* Start on MOSI */
-/* SPI_RX_CONTROL */
-#define SPI_RXCTL_REN               0x00000001    /* Receive Channel Enable */
-#define SPI_RXCTL_RTI               0x00000004    /* Receive Transfer Initiate */
-#define SPI_RXCTL_RWCEN             0x00000008    /* Receive Word Counter Enable */
-#define SPI_RXCTL_RDR               0x00000070    /* Receive Data Request */
-#define SPI_RXCTL_RDR_DIS           0x00000000    /* RDR: Disabled */
-#define SPI_RXCTL_RDR_NE            0x00000010    /* RDR: RFIFO not empty */
-#define SPI_RXCTL_RDR_25            0x00000020    /* RDR: RFIFO 25% full */
-#define SPI_RXCTL_RDR_50            0x00000030    /* RDR: RFIFO 50% full */
-#define SPI_RXCTL_RDR_75            0x00000040    /* RDR: RFIFO 75% full */
-#define SPI_RXCTL_RDR_FULL          0x00000050    /* RDR: RFIFO full */
-#define SPI_RXCTL_RDO               0x00000100    /* Receive Data Over-Run */
-#define SPI_RXCTL_RRWM              0x00003000    /* FIFO Regular Water-Mark */
-#define SPI_RXCTL_RWM_0             0x00000000    /* RRWM: RFIFO Empty */
-#define SPI_RXCTL_RWM_25            0x00001000    /* RRWM: RFIFO 25% full */
-#define SPI_RXCTL_RWM_50            0x00002000    /* RRWM: RFIFO 50% full */
-#define SPI_RXCTL_RWM_75            0x00003000    /* RRWM: RFIFO 75% full */
-#define SPI_RXCTL_RUWM              0x00070000    /* FIFO Urgent Water-Mark */
-#define SPI_RXCTL_UWM_DIS           0x00000000    /* RUWM: Disabled */
-#define SPI_RXCTL_UWM_25            0x00010000    /* RUWM: RFIFO 25% full */
-#define SPI_RXCTL_UWM_50            0x00020000    /* RUWM: RFIFO 50% full */
-#define SPI_RXCTL_UWM_75            0x00030000    /* RUWM: RFIFO 75% full */
-#define SPI_RXCTL_UWM_FULL          0x00040000    /* RUWM: RFIFO full */
-/* SPI_TX_CONTROL */
-#define SPI_TXCTL_TEN               0x00000001    /* Transmit Channel Enable */
-#define SPI_TXCTL_TTI               0x00000004    /* Transmit Transfer Initiate */
-#define SPI_TXCTL_TWCEN             0x00000008    /* Transmit Word Counter Enable */
-#define SPI_TXCTL_TDR               0x00000070    /* Transmit Data Request */
-#define SPI_TXCTL_TDR_DIS           0x00000000    /* TDR: Disabled */
-#define SPI_TXCTL_TDR_NF            0x00000010    /* TDR: TFIFO not full */
-#define SPI_TXCTL_TDR_25            0x00000020    /* TDR: TFIFO 25% empty */
-#define SPI_TXCTL_TDR_50            0x00000030    /* TDR: TFIFO 50% empty */
-#define SPI_TXCTL_TDR_75            0x00000040    /* TDR: TFIFO 75% empty */
-#define SPI_TXCTL_TDR_EMPTY         0x00000050    /* TDR: TFIFO empty */
-#define SPI_TXCTL_TDU               0x00000100    /* Transmit Data Under-Run */
-#define SPI_TXCTL_TRWM              0x00003000    /* FIFO Regular Water-Mark */
-#define SPI_TXCTL_RWM_FULL          0x00000000    /* TRWM: TFIFO full */
-#define SPI_TXCTL_RWM_25            0x00001000    /* TRWM: TFIFO 25% empty */
-#define SPI_TXCTL_RWM_50            0x00002000    /* TRWM: TFIFO 50% empty */
-#define SPI_TXCTL_RWM_75            0x00003000    /* TRWM: TFIFO 75% empty */
-#define SPI_TXCTL_TUWM              0x00070000    /* FIFO Urgent Water-Mark */
-#define SPI_TXCTL_UWM_DIS           0x00000000    /* TUWM: Disabled */
-#define SPI_TXCTL_UWM_25            0x00010000    /* TUWM: TFIFO 25% empty */
-#define SPI_TXCTL_UWM_50            0x00020000    /* TUWM: TFIFO 50% empty */
-#define SPI_TXCTL_UWM_75            0x00030000    /* TUWM: TFIFO 75% empty */
-#define SPI_TXCTL_UWM_EMPTY         0x00040000    /* TUWM: TFIFO empty */
-/* SPI_CLOCK */
-#define SPI_CLK_BAUD                0x0000FFFF    /* Baud Rate */
-/* SPI_DELAY */
-#define SPI_DLY_STOP                0x000000FF    /* Transfer delay time in multiples of SCK period */
-#define SPI_DLY_LEADX               0x00000100    /* Extended (1 SCK) LEAD Control */
-#define SPI_DLY_LAGX                0x00000200    /* Extended (1 SCK) LAG control */
-/* SPI_SSEL */
-#define SPI_SLVSEL_SSE1             0x00000002    /* SPISSEL1 Enable */
-#define SPI_SLVSEL_SSE2             0x00000004    /* SPISSEL2 Enable */
-#define SPI_SLVSEL_SSE3             0x00000008    /* SPISSEL3 Enable */
-#define SPI_SLVSEL_SSE4             0x00000010    /* SPISSEL4 Enable */
-#define SPI_SLVSEL_SSE5             0x00000020    /* SPISSEL5 Enable */
-#define SPI_SLVSEL_SSE6             0x00000040    /* SPISSEL6 Enable */
-#define SPI_SLVSEL_SSE7             0x00000080    /* SPISSEL7 Enable */
-#define SPI_SLVSEL_SSEL1            0x00000200    /* SPISSEL1 Value */
-#define SPI_SLVSEL_SSEL2            0x00000400    /* SPISSEL2 Value */
-#define SPI_SLVSEL_SSEL3            0x00000800    /* SPISSEL3 Value */
-#define SPI_SLVSEL_SSEL4            0x00001000    /* SPISSEL4 Value */
-#define SPI_SLVSEL_SSEL5            0x00002000    /* SPISSEL5 Value */
-#define SPI_SLVSEL_SSEL6            0x00004000    /* SPISSEL6 Value */
-#define SPI_SLVSEL_SSEL7            0x00008000    /* SPISSEL7 Value */
-/* SPI_RWC */
-#define SPI_RWC_VALUE               0x0000FFFF    /* Received Word-Count */
-/* SPI_RWCR */
-#define SPI_RWCR_VALUE              0x0000FFFF    /* Received Word-Count Reload */
-/* SPI_TWC */
-#define SPI_TWC_VALUE               0x0000FFFF    /* Transmitted Word-Count */
-/* SPI_TWCR */
-#define SPI_TWCR_VALUE              0x0000FFFF    /* Transmitted Word-Count Reload */
-/* SPI_IMASK */
-#define SPI_IMSK_RUWM               0x00000002    /* Receive Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_TUWM               0x00000004    /* Transmit Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_ROM                0x00000010    /* Receive Over-Run Error Interrupt Mask */
-#define SPI_IMSK_TUM                0x00000020    /* Transmit Under-Run Error Interrupt Mask */
-#define SPI_IMSK_TCM                0x00000040    /* Transmit Collision Error Interrupt Mask */
-#define SPI_IMSK_MFM                0x00000080    /* Mode Fault Error Interrupt Mask */
-#define SPI_IMSK_RSM                0x00000100    /* Receive Start Interrupt Mask */
-#define SPI_IMSK_TSM                0x00000200    /* Transmit Start Interrupt Mask */
-#define SPI_IMSK_RFM                0x00000400    /* Receive Finish Interrupt Mask */
-#define SPI_IMSK_TFM                0x00000800    /* Transmit Finish Interrupt Mask */
-/* SPI_IMASKCL */
-#define SPI_IMSK_CLR_RUW            0x00000002    /* Receive Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_CLR_TUWM           0x00000004    /* Transmit Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_CLR_ROM            0x00000010    /* Receive Over-Run Error Interrupt Mask */
-#define SPI_IMSK_CLR_TUM            0x00000020    /* Transmit Under-Run Error Interrupt Mask */
-#define SPI_IMSK_CLR_TCM            0x00000040    /* Transmit Collision Error Interrupt Mask */
-#define SPI_IMSK_CLR_MFM            0x00000080    /* Mode Fault Error Interrupt Mask */
-#define SPI_IMSK_CLR_RSM            0x00000100    /* Receive Start Interrupt Mask */
-#define SPI_IMSK_CLR_TSM            0x00000200    /* Transmit Start Interrupt Mask */
-#define SPI_IMSK_CLR_RFM            0x00000400    /* Receive Finish Interrupt Mask */
-#define SPI_IMSK_CLR_TFM            0x00000800    /* Transmit Finish Interrupt Mask */
-/* SPI_IMASKST */
-#define SPI_IMSK_SET_RUWM           0x00000002    /* Receive Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_SET_TUWM           0x00000004    /* Transmit Urgent Water-Mark Interrupt Mask */
-#define SPI_IMSK_SET_ROM            0x00000010    /* Receive Over-Run Error Interrupt Mask */
-#define SPI_IMSK_SET_TUM            0x00000020    /* Transmit Under-Run Error Interrupt Mask */
-#define SPI_IMSK_SET_TCM            0x00000040    /* Transmit Collision Error Interrupt Mask */
-#define SPI_IMSK_SET_MFM            0x00000080    /* Mode Fault Error Interrupt Mask */
-#define SPI_IMSK_SET_RSM            0x00000100    /* Receive Start Interrupt Mask */
-#define SPI_IMSK_SET_TSM            0x00000200    /* Transmit Start Interrupt Mask */
-#define SPI_IMSK_SET_RFM            0x00000400    /* Receive Finish Interrupt Mask */
-#define SPI_IMSK_SET_TFM            0x00000800    /* Transmit Finish Interrupt Mask */
-/* SPI_STATUS */
-#define SPI_STAT_SPIF               0x00000001    /* SPI Finished */
-#define SPI_STAT_RUWM               0x00000002    /* Receive Urgent Water-Mark Breached */
-#define SPI_STAT_TUWM               0x00000004    /* Transmit Urgent Water-Mark Breached */
-#define SPI_STAT_ROE                0x00000010    /* Receive Over-Run Error Indication */
-#define SPI_STAT_TUE                0x00000020    /* Transmit Under-Run Error Indication */
-#define SPI_STAT_TCE                0x00000040    /* Transmit Collision Error Indication */
-#define SPI_STAT_MODF               0x00000080    /* Mode Fault Error Indication */
-#define SPI_STAT_RS                 0x00000100    /* Receive Start Indication */
-#define SPI_STAT_TS                 0x00000200    /* Transmit Start Indication */
-#define SPI_STAT_RF                 0x00000400    /* Receive Finish Indication */
-#define SPI_STAT_TF                 0x00000800    /* Transmit Finish Indication */
-#define SPI_STAT_RFS                0x00007000    /* SPI_RFIFO status */
-#define SPI_STAT_RFIFO_EMPTY        0x00000000    /* RFS: RFIFO Empty */
-#define SPI_STAT_RFIFO_25           0x00001000    /* RFS: RFIFO 25% Full */
-#define SPI_STAT_RFIFO_50           0x00002000    /* RFS: RFIFO 50% Full */
-#define SPI_STAT_RFIFO_75           0x00003000    /* RFS: RFIFO 75% Full */
-#define SPI_STAT_RFIFO_FULL         0x00004000    /* RFS: RFIFO Full */
-#define SPI_STAT_TFS                0x00070000    /* SPI_TFIFO status */
-#define SPI_STAT_TFIFO_FULL         0x00000000    /* TFS: TFIFO full */
-#define SPI_STAT_TFIFO_25           0x00010000    /* TFS: TFIFO 25% empty */
-#define SPI_STAT_TFIFO_50           0x00020000    /* TFS: TFIFO 50% empty */
-#define SPI_STAT_TFIFO_75           0x00030000    /* TFS: TFIFO 75% empty */
-#define SPI_STAT_TFIFO_EMPTY        0x00040000    /* TFS: TFIFO empty */
-#define SPI_STAT_FCS                0x00100000    /* Flow-Control Stall Indication */
-#define SPI_STAT_RFE                0x00400000    /* SPI_RFIFO Empty */
-#define SPI_STAT_TFF                0x00800000    /* SPI_TFIFO Full */
-/* SPI_ILAT */
-#define SPI_ILAT_RUWMI              0x00000002    /* Receive Urgent Water Mark Interrupt */
-#define SPI_ILAT_TUWMI              0x00000004    /* Transmit Urgent Water Mark Interrupt */
-#define SPI_ILAT_ROI                0x00000010    /* Receive Over-Run Error Indication */
-#define SPI_ILAT_TUI                0x00000020    /* Transmit Under-Run Error Indication */
-#define SPI_ILAT_TCI                0x00000040    /* Transmit Collision Error Indication */
-#define SPI_ILAT_MFI                0x00000080    /* Mode Fault Error Indication */
-#define SPI_ILAT_RSI                0x00000100    /* Receive Start Indication */
-#define SPI_ILAT_TSI                0x00000200    /* Transmit Start Indication */
-#define SPI_ILAT_RFI                0x00000400    /* Receive Finish Indication */
-#define SPI_ILAT_TFI                0x00000800    /* Transmit Finish Indication */
-/* SPI_ILATCL */
-#define SPI_ILAT_CLR_RUWMI          0x00000002    /* Receive Urgent Water Mark Interrupt */
-#define SPI_ILAT_CLR_TUWMI          0x00000004    /* Transmit Urgent Water Mark Interrupt */
-#define SPI_ILAT_CLR_ROI            0x00000010    /* Receive Over-Run Error Indication */
-#define SPI_ILAT_CLR_TUI            0x00000020    /* Transmit Under-Run Error Indication */
-#define SPI_ILAT_CLR_TCI            0x00000040    /* Transmit Collision Error Indication */
-#define SPI_ILAT_CLR_MFI            0x00000080    /* Mode Fault Error Indication */
-#define SPI_ILAT_CLR_RSI            0x00000100    /* Receive Start Indication */
-#define SPI_ILAT_CLR_TSI            0x00000200    /* Transmit Start Indication */
-#define SPI_ILAT_CLR_RFI            0x00000400    /* Receive Finish Indication */
-#define SPI_ILAT_CLR_TFI            0x00000800    /* Transmit Finish Indication */
-
-/*
- * adi spi3 registers layout
- */
-struct adi_spi_regs {
-	u32 revid;
-	u32 control;
-	u32 rx_control;
-	u32 tx_control;
-	u32 clock;
-	u32 delay;
-	u32 ssel;
-	u32 rwc;
-	u32 rwcr;
-	u32 twc;
-	u32 twcr;
-	u32 reserved0;
-	u32 emask;
-	u32 emaskcl;
-	u32 emaskst;
-	u32 reserved1;
-	u32 status;
-	u32 elat;
-	u32 elatcl;
-	u32 reserved2;
-	u32 rfifo;
-	u32 reserved3;
-	u32 tfifo;
-};
-
-#define MAX_CTRL_CS          8  /* cs in spi controller */
-
-/* device.platform_data for SSP controller devices */
-struct adi_spi3_master {
-	u16 num_chipselect;
-	u16 pin_req[7];
-};
-
-/* spi_board_info.controller_data for SPI slave devices,
- * copied to spi_device.platform_data ... mostly for dma tuning
- */
-struct adi_spi3_chip {
-	u32 control;
-	u16 cs_chg_udelay; /* Some devices require 16-bit delays */
-	u32 tx_dummy_val; /* tx value for rx only transfer */
-	bool enable_dma;
-};
-
-#endif /* _ADI_SPI3_H_ */
-- 
cgit v1.2.3


From 08ba7ae35b15cd13b965d5fd5a835e0a0cb803e6 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 13 Jun 2018 10:41:15 +0200
Subject: spi: sh-msiof: Make sure all DMA operations have completed

In case of a bi-directional transfer, receive DMA may complete in the
rcar-dmac driver before transmit DMA, due to scheduling latencies.
As the MSIOF driver waits for completion of the receive DMA only, it may
submit the next transmit DMA request before the previous one has
completed.

Make the driver more robust by waiting for the completion of both
receive and transmit DMA, when applicable.

Based on a patch in the BSP by Ryo Kataoka.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-sh-msiof.c | 53 +++++++++++++++++++++++++---------------------
 1 file changed, 29 insertions(+), 24 deletions(-)

diff --git a/drivers/spi/spi-sh-msiof.c b/drivers/spi/spi-sh-msiof.c
index 0e74cbf9929d..539d6d1a277a 100644
--- a/drivers/spi/spi-sh-msiof.c
+++ b/drivers/spi/spi-sh-msiof.c
@@ -49,6 +49,7 @@ struct sh_msiof_spi_priv {
 	struct platform_device *pdev;
 	struct sh_msiof_spi_info *info;
 	struct completion done;
+	struct completion done_txdma;
 	unsigned int tx_fifo_size;
 	unsigned int rx_fifo_size;
 	unsigned int min_div_pow;
@@ -649,19 +650,21 @@ static int sh_msiof_slave_abort(struct spi_master *master)
 
 	p->slave_aborted = true;
 	complete(&p->done);
+	complete(&p->done_txdma);
 	return 0;
 }
 
-static int sh_msiof_wait_for_completion(struct sh_msiof_spi_priv *p)
+static int sh_msiof_wait_for_completion(struct sh_msiof_spi_priv *p,
+					struct completion *x)
 {
 	if (spi_controller_is_slave(p->master)) {
-		if (wait_for_completion_interruptible(&p->done) ||
+		if (wait_for_completion_interruptible(x) ||
 		    p->slave_aborted) {
 			dev_dbg(&p->pdev->dev, "interrupted\n");
 			return -EINTR;
 		}
 	} else {
-		if (!wait_for_completion_timeout(&p->done, HZ)) {
+		if (!wait_for_completion_timeout(x, HZ)) {
 			dev_err(&p->pdev->dev, "timeout\n");
 			return -ETIMEDOUT;
 		}
@@ -711,7 +714,7 @@ static int sh_msiof_spi_txrx_once(struct sh_msiof_spi_priv *p,
 	}
 
 	/* wait for tx fifo to be emptied / rx fifo to be filled */
-	ret = sh_msiof_wait_for_completion(p);
+	ret = sh_msiof_wait_for_completion(p, &p->done);
 	if (ret)
 		goto stop_reset;
 
@@ -740,10 +743,7 @@ stop_ier:
 
 static void sh_msiof_dma_complete(void *arg)
 {
-	struct sh_msiof_spi_priv *p = arg;
-
-	sh_msiof_write(p, IER, 0);
-	complete(&p->done);
+	complete(arg);
 }
 
 static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
@@ -764,7 +764,7 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 			return -EAGAIN;
 
 		desc_rx->callback = sh_msiof_dma_complete;
-		desc_rx->callback_param = p;
+		desc_rx->callback_param = &p->done;
 		cookie = dmaengine_submit(desc_rx);
 		if (dma_submit_error(cookie))
 			return cookie;
@@ -782,13 +782,8 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 			goto no_dma_tx;
 		}
 
-		if (rx) {
-			/* No callback */
-			desc_tx->callback = NULL;
-		} else {
-			desc_tx->callback = sh_msiof_dma_complete;
-			desc_tx->callback_param = p;
-		}
+		desc_tx->callback = sh_msiof_dma_complete;
+		desc_tx->callback_param = &p->done_txdma;
 		cookie = dmaengine_submit(desc_tx);
 		if (dma_submit_error(cookie)) {
 			ret = cookie;
@@ -805,6 +800,8 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 	sh_msiof_write(p, IER, ier_bits);
 
 	reinit_completion(&p->done);
+	if (tx)
+		reinit_completion(&p->done_txdma);
 	p->slave_aborted = false;
 
 	/* Now start DMA */
@@ -819,17 +816,24 @@ static int sh_msiof_dma_once(struct sh_msiof_spi_priv *p, const void *tx,
 		goto stop_dma;
 	}
 
-	/* wait for tx/rx DMA completion */
-	ret = sh_msiof_wait_for_completion(p);
-	if (ret)
-		goto stop_reset;
+	if (tx) {
+		/* wait for tx DMA completion */
+		ret = sh_msiof_wait_for_completion(p, &p->done_txdma);
+		if (ret)
+			goto stop_reset;
+	}
 
-	if (!rx) {
-		reinit_completion(&p->done);
-		sh_msiof_write(p, IER, IER_TEOFE);
+	if (rx) {
+		/* wait for rx DMA completion */
+		ret = sh_msiof_wait_for_completion(p, &p->done);
+		if (ret)
+			goto stop_reset;
 
+		sh_msiof_write(p, IER, 0);
+	} else {
 		/* wait for tx fifo to be emptied */
-		ret = sh_msiof_wait_for_completion(p);
+		sh_msiof_write(p, IER, IER_TEOFE);
+		ret = sh_msiof_wait_for_completion(p, &p->done);
 		if (ret)
 			goto stop_reset;
 	}
@@ -1327,6 +1331,7 @@ static int sh_msiof_spi_probe(struct platform_device *pdev)
 	p->min_div_pow = chipdata->min_div_pow;
 
 	init_completion(&p->done);
+	init_completion(&p->done_txdma);
 
 	p->clk = devm_clk_get(&pdev->dev, NULL);
 	if (IS_ERR(p->clk)) {
-- 
cgit v1.2.3


From 187e01d0d56d1fd682dfaafb0b45d332abec6387 Mon Sep 17 00:00:00 2001
From: olivier moysan <olivier.moysan@st.com>
Date: Mon, 11 Jun 2018 17:13:59 +0200
Subject: ASoC: stm32: sai: add iec958 controls support

Add support of iec958 controls for STM32 SAI.

Signed-off-by: Olivier Moysan <olivier.moysan@st.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/stm/Kconfig         |   1 +
 sound/soc/stm/stm32_sai_sub.c | 139 ++++++++++++++++++++++++++++++++++++++----
 2 files changed, 128 insertions(+), 12 deletions(-)

diff --git a/sound/soc/stm/Kconfig b/sound/soc/stm/Kconfig
index 48f9ddd94016..9b2681397dba 100644
--- a/sound/soc/stm/Kconfig
+++ b/sound/soc/stm/Kconfig
@@ -6,6 +6,7 @@ config SND_SOC_STM32_SAI
 	depends on SND_SOC
 	select SND_SOC_GENERIC_DMAENGINE_PCM
 	select REGMAP_MMIO
+	select SND_PCM_IEC958
 	help
 	  Say Y if you want to enable SAI for STM32
 
diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index cfeb219e1d78..c4f15ea14197 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -96,7 +96,8 @@
  * @slot_mask: rx or tx active slots mask. set at init or at runtime
  * @data_size: PCM data width. corresponds to PCM substream width.
  * @spdif_frm_cnt: S/PDIF playback frame counter
- * @spdif_status_bits: S/PDIF status bits
+ * @snd_aes_iec958: iec958 data
+ * @ctrl_lock: control lock
  */
 struct stm32_sai_sub_data {
 	struct platform_device *pdev;
@@ -125,7 +126,8 @@ struct stm32_sai_sub_data {
 	int slot_mask;
 	int data_size;
 	unsigned int spdif_frm_cnt;
-	unsigned char spdif_status_bits[SAI_IEC60958_STATUS_BYTES];
+	struct snd_aes_iec958 iec958;
+	struct mutex ctrl_lock; /* protect resources accessed by controls */
 };
 
 enum stm32_sai_fifo_th {
@@ -184,10 +186,6 @@ static bool stm32_sai_sub_writeable_reg(struct device *dev, unsigned int reg)
 	}
 }
 
-static const unsigned char default_status_bits[SAI_IEC60958_STATUS_BYTES] = {
-	0, 0, 0, IEC958_AES3_CON_FS_48000,
-};
-
 static const struct regmap_config stm32_sai_sub_regmap_config_f4 = {
 	.reg_bits = 32,
 	.reg_stride = 4,
@@ -210,6 +208,49 @@ static const struct regmap_config stm32_sai_sub_regmap_config_h7 = {
 	.fast_io = true,
 };
 
+static int snd_pcm_iec958_info(struct snd_kcontrol *kcontrol,
+			       struct snd_ctl_elem_info *uinfo)
+{
+	uinfo->type = SNDRV_CTL_ELEM_TYPE_IEC958;
+	uinfo->count = 1;
+
+	return 0;
+}
+
+static int snd_pcm_iec958_get(struct snd_kcontrol *kcontrol,
+			      struct snd_ctl_elem_value *uctl)
+{
+	struct stm32_sai_sub_data *sai = snd_kcontrol_chip(kcontrol);
+
+	mutex_lock(&sai->ctrl_lock);
+	memcpy(uctl->value.iec958.status, sai->iec958.status, 4);
+	mutex_unlock(&sai->ctrl_lock);
+
+	return 0;
+}
+
+static int snd_pcm_iec958_put(struct snd_kcontrol *kcontrol,
+			      struct snd_ctl_elem_value *uctl)
+{
+	struct stm32_sai_sub_data *sai = snd_kcontrol_chip(kcontrol);
+
+	mutex_lock(&sai->ctrl_lock);
+	memcpy(sai->iec958.status, uctl->value.iec958.status, 4);
+	mutex_unlock(&sai->ctrl_lock);
+
+	return 0;
+}
+
+static const struct snd_kcontrol_new iec958_ctls = {
+	.access = (SNDRV_CTL_ELEM_ACCESS_READWRITE |
+			SNDRV_CTL_ELEM_ACCESS_VOLATILE),
+	.iface = SNDRV_CTL_ELEM_IFACE_PCM,
+	.name = SNDRV_CTL_NAME_IEC958("", PLAYBACK, DEFAULT),
+	.info = snd_pcm_iec958_info,
+	.get = snd_pcm_iec958_get,
+	.put = snd_pcm_iec958_put,
+};
+
 static irqreturn_t stm32_sai_isr(int irq, void *devid)
 {
 	struct stm32_sai_sub_data *sai = (struct stm32_sai_sub_data *)devid;
@@ -619,6 +660,59 @@ static void stm32_sai_set_frame(struct snd_soc_dai *cpu_dai)
 	}
 }
 
+static void stm32_sai_init_iec958_status(struct stm32_sai_sub_data *sai)
+{
+	unsigned char *cs = sai->iec958.status;
+
+	cs[0] = IEC958_AES0_CON_NOT_COPYRIGHT | IEC958_AES0_CON_EMPHASIS_NONE;
+	cs[1] = IEC958_AES1_CON_GENERAL;
+	cs[2] = IEC958_AES2_CON_SOURCE_UNSPEC | IEC958_AES2_CON_CHANNEL_UNSPEC;
+	cs[3] = IEC958_AES3_CON_CLOCK_1000PPM | IEC958_AES3_CON_FS_NOTID;
+}
+
+static void stm32_sai_set_iec958_status(struct stm32_sai_sub_data *sai,
+					struct snd_pcm_runtime *runtime)
+{
+	if (!runtime)
+		return;
+
+	/* Force the sample rate according to runtime rate */
+	mutex_lock(&sai->ctrl_lock);
+	switch (runtime->rate) {
+	case 22050:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_22050;
+		break;
+	case 44100:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_44100;
+		break;
+	case 88200:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_88200;
+		break;
+	case 176400:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_176400;
+		break;
+	case 24000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_24000;
+		break;
+	case 48000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_48000;
+		break;
+	case 96000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_96000;
+		break;
+	case 192000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_192000;
+		break;
+	case 32000:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_32000;
+		break;
+	default:
+		sai->iec958.status[3] = IEC958_AES3_CON_FS_NOTID;
+		break;
+	}
+	mutex_unlock(&sai->ctrl_lock);
+}
+
 static int stm32_sai_configure_clock(struct snd_soc_dai *cpu_dai,
 				     struct snd_pcm_hw_params *params)
 {
@@ -709,7 +803,11 @@ static int stm32_sai_hw_params(struct snd_pcm_substream *substream,
 
 	sai->data_size = params_width(params);
 
-	if (!STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+		/* Rate not already set in runtime structure */
+		substream->runtime->rate = params_rate(params);
+		stm32_sai_set_iec958_status(sai, substream->runtime);
+	} else {
 		ret = stm32_sai_set_slots(cpu_dai);
 		if (ret < 0)
 			return ret;
@@ -789,6 +887,20 @@ static void stm32_sai_shutdown(struct snd_pcm_substream *substream,
 	sai->substream = NULL;
 }
 
+static int stm32_sai_pcm_new(struct snd_soc_pcm_runtime *rtd,
+			     struct snd_soc_dai *cpu_dai)
+{
+	struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
+
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai)) {
+		dev_dbg(&sai->pdev->dev, "%s: register iec controls", __func__);
+		return snd_ctl_add(rtd->pcm->card,
+				   snd_ctl_new1(&iec958_ctls, sai));
+	}
+
+	return 0;
+}
+
 static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 {
 	struct stm32_sai_sub_data *sai = dev_get_drvdata(cpu_dai->dev);
@@ -809,6 +921,10 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 	else
 		snd_soc_dai_init_dma_data(cpu_dai, NULL, &sai->dma_params);
 
+	/* Next settings are not relevant for spdif mode */
+	if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
+		return 0;
+
 	cr1_mask = SAI_XCR1_RX_TX;
 	if (STM_SAI_IS_CAPTURE(sai))
 		cr1 |= SAI_XCR1_RX_TX;
@@ -820,10 +936,6 @@ static int stm32_sai_dai_probe(struct snd_soc_dai *cpu_dai)
 				     sai->synco, sai->synci);
 	}
 
-	if (STM_SAI_PROTOCOL_IS_SPDIF(sai))
-		memcpy(sai->spdif_status_bits, default_status_bits,
-		       sizeof(default_status_bits));
-
 	cr1_mask |= SAI_XCR1_SYNCEN_MASK;
 	cr1 |= SAI_XCR1_SYNCEN_SET(sai->sync);
 
@@ -861,7 +973,7 @@ static int stm32_sai_pcm_process_spdif(struct snd_pcm_substream *substream,
 		/* Set channel status bit */
 		byte = frm_cnt >> 3;
 		mask = 1 << (frm_cnt - (byte << 3));
-		if (sai->spdif_status_bits[byte] & mask)
+		if (sai->iec958.status[byte] & mask)
 			*ptr |= 0x04000000;
 		ptr++;
 
@@ -888,6 +1000,7 @@ static const struct snd_pcm_hardware stm32_sai_pcm_hw = {
 static struct snd_soc_dai_driver stm32_sai_playback_dai[] = {
 {
 		.probe = stm32_sai_dai_probe,
+		.pcm_new = stm32_sai_pcm_new,
 		.id = 1, /* avoid call to fmt_single_name() */
 		.playback = {
 			.channels_min = 1,
@@ -998,6 +1111,7 @@ static int stm32_sai_sub_parse_of(struct platform_device *pdev,
 			dev_err(&pdev->dev, "S/PDIF IEC60958 not supported\n");
 			return -EINVAL;
 		}
+		stm32_sai_init_iec958_status(sai);
 		sai->spdif = true;
 		sai->master = true;
 	}
@@ -1114,6 +1228,7 @@ static int stm32_sai_sub_probe(struct platform_device *pdev)
 	sai->id = (uintptr_t)of_id->data;
 
 	sai->pdev = pdev;
+	mutex_init(&sai->ctrl_lock);
 	platform_set_drvdata(pdev, sai);
 
 	sai->pdata = dev_get_drvdata(pdev->dev.parent);
-- 
cgit v1.2.3


From a56df73ba5960848f60f609c68770d2638bf1dd5 Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sun, 10 Jun 2018 01:20:54 +0300
Subject: ASoC: rockchip: put device_node on remove

snd_rk_mc_probe() gets a couple of device nodes with of_parse_phandle(),
but there is no release of them.

The patch adds remove handler and proper error handling in the probe.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/rockchip/rockchip_rt5645.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/sound/soc/rockchip/rockchip_rt5645.c b/sound/soc/rockchip/rockchip_rt5645.c
index 4db4fd56db35..881c32498808 100644
--- a/sound/soc/rockchip/rockchip_rt5645.c
+++ b/sound/soc/rockchip/rockchip_rt5645.c
@@ -181,7 +181,8 @@ static int snd_rk_mc_probe(struct platform_device *pdev)
 	if (!rk_dailink.cpu_of_node) {
 		dev_err(&pdev->dev,
 			"Property 'rockchip,i2s-controller' missing or invalid\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto put_codec_of_node;
 	}
 
 	rk_dailink.platform_of_node = rk_dailink.cpu_of_node;
@@ -190,17 +191,36 @@ static int snd_rk_mc_probe(struct platform_device *pdev)
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Soc parse card name failed %d\n", ret);
-		return ret;
+		goto put_cpu_of_node;
 	}
 
 	ret = devm_snd_soc_register_card(&pdev->dev, card);
 	if (ret) {
 		dev_err(&pdev->dev,
 			"Soc register card failed %d\n", ret);
-		return ret;
+		goto put_cpu_of_node;
 	}
 
 	return ret;
+
+put_cpu_of_node:
+	of_node_put(rk_dailink.cpu_of_node);
+	rk_dailink.cpu_of_node = NULL;
+put_codec_of_node:
+	of_node_put(rk_dailink.codec_of_node);
+	rk_dailink.codec_of_node = NULL;
+
+	return ret;
+}
+
+static int snd_rk_mc_remove(struct platform_device *pdev)
+{
+	of_node_put(rk_dailink.cpu_of_node);
+	rk_dailink.cpu_of_node = NULL;
+	of_node_put(rk_dailink.codec_of_node);
+	rk_dailink.codec_of_node = NULL;
+
+	return 0;
 }
 
 static const struct of_device_id rockchip_rt5645_of_match[] = {
@@ -212,6 +232,7 @@ MODULE_DEVICE_TABLE(of, rockchip_rt5645_of_match);
 
 static struct platform_driver snd_rk_mc_driver = {
 	.probe = snd_rk_mc_probe,
+	.remove = snd_rk_mc_remove,
 	.driver = {
 		.name = DRV_NAME,
 		.pm = &snd_soc_pm_ops,
-- 
cgit v1.2.3


From 75b31192fe6ad20b42276b20ee3bdf1493216d63 Mon Sep 17 00:00:00 2001
From: Jianqun Xu <jay.xu@rock-chips.com>
Date: Fri, 8 Jun 2018 16:31:09 +0800
Subject: ASoC: rockchip: add config for rockchip dmaengine pcm register

This patch makes the rockchip i2s pcm configurable by adding
rockchip pcm config for devm_snd_dmaengine_pcm_register.

Signed-off-by: Jianqun Xu <jay.xu@rock-chips.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/rockchip/Makefile       |  3 ++-
 sound/soc/rockchip/rockchip_i2s.c |  3 ++-
 sound/soc/rockchip/rockchip_pcm.c | 45 +++++++++++++++++++++++++++++++++++++++
 sound/soc/rockchip/rockchip_pcm.h | 14 ++++++++++++
 4 files changed, 63 insertions(+), 2 deletions(-)
 create mode 100644 sound/soc/rockchip/rockchip_pcm.c
 create mode 100644 sound/soc/rockchip/rockchip_pcm.h

diff --git a/sound/soc/rockchip/Makefile b/sound/soc/rockchip/Makefile
index 05b078e7b87f..65e814d46006 100644
--- a/sound/soc/rockchip/Makefile
+++ b/sound/soc/rockchip/Makefile
@@ -1,10 +1,11 @@
 # SPDX-License-Identifier: GPL-2.0
 # ROCKCHIP Platform Support
 snd-soc-rockchip-i2s-objs := rockchip_i2s.o
+snd-soc-rockchip-pcm-objs := rockchip_pcm.o
 snd-soc-rockchip-pdm-objs := rockchip_pdm.o
 snd-soc-rockchip-spdif-objs := rockchip_spdif.o
 
-obj-$(CONFIG_SND_SOC_ROCKCHIP_I2S) += snd-soc-rockchip-i2s.o
+obj-$(CONFIG_SND_SOC_ROCKCHIP_I2S) += snd-soc-rockchip-i2s.o snd-soc-rockchip-pcm.o
 obj-$(CONFIG_SND_SOC_ROCKCHIP_PDM) += snd-soc-rockchip-pdm.o
 obj-$(CONFIG_SND_SOC_ROCKCHIP_SPDIF) += snd-soc-rockchip-spdif.o
 
diff --git a/sound/soc/rockchip/rockchip_i2s.c b/sound/soc/rockchip/rockchip_i2s.c
index 950823d69e9c..60d43d53a8f5 100644
--- a/sound/soc/rockchip/rockchip_i2s.c
+++ b/sound/soc/rockchip/rockchip_i2s.c
@@ -22,6 +22,7 @@
 #include <sound/dmaengine_pcm.h>
 
 #include "rockchip_i2s.h"
+#include "rockchip_pcm.h"
 
 #define DRV_NAME "rockchip-i2s"
 
@@ -674,7 +675,7 @@ static int rockchip_i2s_probe(struct platform_device *pdev)
 		goto err_suspend;
 	}
 
-	ret = devm_snd_dmaengine_pcm_register(&pdev->dev, NULL, 0);
+	ret = rockchip_pcm_platform_register(&pdev->dev);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not register PCM\n");
 		return ret;
diff --git a/sound/soc/rockchip/rockchip_pcm.c b/sound/soc/rockchip/rockchip_pcm.c
new file mode 100644
index 000000000000..f77538319221
--- /dev/null
+++ b/sound/soc/rockchip/rockchip_pcm.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/device.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/dmaengine_pcm.h>
+
+#include "rockchip_pcm.h"
+
+static const struct snd_pcm_hardware snd_rockchip_hardware = {
+	.info			= SNDRV_PCM_INFO_MMAP |
+				  SNDRV_PCM_INFO_MMAP_VALID |
+				  SNDRV_PCM_INFO_PAUSE |
+				  SNDRV_PCM_INFO_RESUME,
+	.period_bytes_min	= 32,
+	.period_bytes_max	= 8192,
+	.periods_min		= 1,
+	.periods_max		= 52,
+	.buffer_bytes_max	= 64 * 1024,
+	.fifo_size		= 32,
+};
+
+static const struct snd_dmaengine_pcm_config rk_dmaengine_pcm_config = {
+	.pcm_hardware = &snd_rockchip_hardware,
+	.prealloc_buffer_size = 32 * 1024,
+};
+
+int rockchip_pcm_platform_register(struct device *dev)
+{
+	return devm_snd_dmaengine_pcm_register(dev, &rk_dmaengine_pcm_config,
+		SND_DMAENGINE_PCM_FLAG_COMPAT);
+}
+EXPORT_SYMBOL_GPL(rockchip_pcm_platform_register);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/rockchip/rockchip_pcm.h b/sound/soc/rockchip/rockchip_pcm.h
new file mode 100644
index 000000000000..d6c36115c60a
--- /dev/null
+++ b/sound/soc/rockchip/rockchip_pcm.h
@@ -0,0 +1,14 @@
+/*
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _ROCKCHIP_PCM_H
+#define _ROCKCHIP_PCM_H
+
+int rockchip_pcm_platform_register(struct device *dev);
+
+#endif
-- 
cgit v1.2.3


From 4f29b663c08d369fe320a148179996c94cf7d01b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 7 Jun 2018 15:50:48 +0200
Subject: ASoC: rt1305: Use ULL suffixes for 64-bit constants
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With gcc 4.1.2:

    sound/soc/codecs/rt1305.c: In function ‘rt1305_calibrate’:
    sound/soc/codecs/rt1305.c:1069: warning: integer constant is too large for ‘long’ type
    sound/soc/codecs/rt1305.c:1086: warning: integer constant is too large for ‘long’ type

Add the missing "ULL" suffixes to fix this.

Fixes: 29bc643ddd7efb74 ("ASoC: rt1305: Add RT1305/RT1306 amplifier driver")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1305.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/rt1305.c b/sound/soc/codecs/rt1305.c
index f4c8c45f4010..421b8fb2fa04 100644
--- a/sound/soc/codecs/rt1305.c
+++ b/sound/soc/codecs/rt1305.c
@@ -1066,7 +1066,7 @@ static void rt1305_calibrate(struct rt1305_priv *rt1305)
 	pr_debug("Left_rhl = 0x%x rh=0x%x rl=0x%x\n", rhl, rh, rl);
 	pr_info("Left channel %d.%dohm\n", (r0ohm/10), (r0ohm%10));
 
-	r0l = 562949953421312;
+	r0l = 562949953421312ULL;
 	if (rhl != 0)
 		do_div(r0l, rhl);
 	pr_debug("Left_r0 = 0x%llx\n", r0l);
@@ -1083,7 +1083,7 @@ static void rt1305_calibrate(struct rt1305_priv *rt1305)
 	pr_debug("Right_rhl = 0x%x rh=0x%x rl=0x%x\n", rhl, rh, rl);
 	pr_info("Right channel %d.%dohm\n", (r0ohm/10), (r0ohm%10));
 
-	r0r = 562949953421312;
+	r0r = 562949953421312ULL;
 	if (rhl != 0)
 		do_div(r0r, rhl);
 	pr_debug("Right_r0 = 0x%llx\n", r0r);
-- 
cgit v1.2.3


From d5a1826c32fa2ec2b161a89df904c6977f7ec44c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 8 Jun 2018 10:19:25 +0200
Subject: ASoC: Intel: bytcr_rt5640: Add quirk for the Chuwi Vi10 tablet

Add a quirk for the Chuwi Vi10 tablet, this tablet uses IN1 for the
internal mic rather then the default IN3 and it uses JD2 rather
then JD1 for its jack-detect switch.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5640.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 33065ba294a9..5c4f9ea40f57 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -463,6 +463,22 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{
+		/* Chuwi Vi10 (CWI505) */
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"),
+			DMI_MATCH(DMI_BOARD_NAME, "BYT-PF02"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ilife"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "S165"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
-- 
cgit v1.2.3


From 62c2c9fcac4341d306dda4cf400b77e7e124480a Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Mon, 11 Jun 2018 17:32:12 +0900
Subject: ASoC: simple-card-utils: move hp and mic detect gpios from
 simple-card

This patch moves headphone and microphone jack detection gpios from
simple-card driver. It is preparing for using this feature from other
drivers.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/simple_card_utils.h     | 15 ++++++++
 sound/soc/generic/simple-card-utils.c | 59 ++++++++++++++++++++++++++++++++
 sound/soc/generic/simple-card.c       | 64 -----------------------------------
 3 files changed, 74 insertions(+), 64 deletions(-)

diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index 7e25afce6566..f82acef3b992 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -12,6 +12,11 @@
 
 #include <sound/soc.h>
 
+#define asoc_simple_card_init_hp(card, sjack, prefix) \
+	asoc_simple_card_init_jack(card, sjack, 1, prefix)
+#define asoc_simple_card_init_mic(card, sjack, prefix) \
+	asoc_simple_card_init_jack(card, sjack, 0, prefix)
+
 struct asoc_simple_dai {
 	const char *name;
 	unsigned int sysclk;
@@ -28,6 +33,12 @@ struct asoc_simple_card_data {
 	u32 convert_channels;
 };
 
+struct asoc_simple_jack {
+	struct snd_soc_jack jack;
+	struct snd_soc_jack_pin pin;
+	struct snd_soc_jack_gpio gpio;
+};
+
 int asoc_simple_card_parse_daifmt(struct device *dev,
 				  struct device_node *node,
 				  struct device_node *codec,
@@ -107,4 +118,8 @@ int asoc_simple_card_of_parse_routing(struct snd_soc_card *card,
 int asoc_simple_card_of_parse_widgets(struct snd_soc_card *card,
 				      char *prefix);
 
+int asoc_simple_card_init_jack(struct snd_soc_card *card,
+			       struct asoc_simple_jack *sjack,
+			       int is_hp, char *prefix);
+
 #endif /* __SIMPLE_CARD_UTILS_H */
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index 3751a07de6aa..4398c9580929 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -8,9 +8,13 @@
  * published by the Free Software Foundation.
  */
 #include <linux/clk.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_gpio.h>
 #include <linux/of_graph.h>
+#include <sound/jack.h>
 #include <sound/simple_card_utils.h>
 
 void asoc_simple_card_convert_fixup(struct asoc_simple_card_data *data,
@@ -419,6 +423,61 @@ int asoc_simple_card_of_parse_widgets(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(asoc_simple_card_of_parse_widgets);
 
+int asoc_simple_card_init_jack(struct snd_soc_card *card,
+			       struct asoc_simple_jack *sjack,
+			       int is_hp, char *prefix)
+{
+	struct device *dev = card->dev;
+	enum of_gpio_flags flags;
+	char prop[128];
+	char *pin_name;
+	char *gpio_name;
+	int mask;
+	int det;
+
+	if (!prefix)
+		prefix = "";
+
+	sjack->gpio.gpio = -ENOENT;
+
+	if (is_hp) {
+		snprintf(prop, sizeof(prop), "%shp-det-gpio", prefix);
+		pin_name	= "Headphones";
+		gpio_name	= "Headphone detection";
+		mask		= SND_JACK_HEADPHONE;
+	} else {
+		snprintf(prop, sizeof(prop), "%smic-det-gpio", prefix);
+		pin_name	= "Mic Jack";
+		gpio_name	= "Mic detection";
+		mask		= SND_JACK_MICROPHONE;
+	}
+
+	det = of_get_named_gpio_flags(dev->of_node, prop, 0, &flags);
+	if (det == -EPROBE_DEFER)
+		return -EPROBE_DEFER;
+
+	if (gpio_is_valid(det)) {
+		sjack->pin.pin		= pin_name;
+		sjack->pin.mask		= mask;
+
+		sjack->gpio.name	= gpio_name;
+		sjack->gpio.report	= mask;
+		sjack->gpio.gpio	= det;
+		sjack->gpio.invert	= !!(flags & OF_GPIO_ACTIVE_LOW);
+		sjack->gpio.debounce_time = 150;
+
+		snd_soc_card_jack_new(card, pin_name, mask,
+				      &sjack->jack,
+				      &sjack->pin, 1);
+
+		snd_soc_jack_add_gpios(&sjack->jack, 1,
+				       &sjack->gpio);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(asoc_simple_card_init_jack);
+
 /* Module information */
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
 MODULE_DESCRIPTION("ALSA SoC Simple Card Utils");
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index 8b374af86a6e..a6477a022156 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -10,23 +10,14 @@
  */
 #include <linux/clk.h>
 #include <linux/device.h>
-#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/platform_device.h>
 #include <linux/string.h>
-#include <sound/jack.h>
 #include <sound/simple_card.h>
 #include <sound/soc-dai.h>
 #include <sound/soc.h>
 
-struct asoc_simple_jack {
-	struct snd_soc_jack jack;
-	struct snd_soc_jack_pin pin;
-	struct snd_soc_jack_gpio gpio;
-};
-
 struct simple_card_data {
 	struct snd_soc_card snd_card;
 	struct simple_dai_props {
@@ -49,61 +40,6 @@ struct simple_card_data {
 #define CELL	"#sound-dai-cells"
 #define PREFIX	"simple-audio-card,"
 
-#define asoc_simple_card_init_hp(card, sjack, prefix)\
-	asoc_simple_card_init_jack(card, sjack, 1, prefix)
-#define asoc_simple_card_init_mic(card, sjack, prefix)\
-	asoc_simple_card_init_jack(card, sjack, 0, prefix)
-static int asoc_simple_card_init_jack(struct snd_soc_card *card,
-				      struct asoc_simple_jack *sjack,
-				      int is_hp, char *prefix)
-{
-	struct device *dev = card->dev;
-	enum of_gpio_flags flags;
-	char prop[128];
-	char *pin_name;
-	char *gpio_name;
-	int mask;
-	int det;
-
-	sjack->gpio.gpio = -ENOENT;
-
-	if (is_hp) {
-		snprintf(prop, sizeof(prop), "%shp-det-gpio", prefix);
-		pin_name	= "Headphones";
-		gpio_name	= "Headphone detection";
-		mask		= SND_JACK_HEADPHONE;
-	} else {
-		snprintf(prop, sizeof(prop), "%smic-det-gpio", prefix);
-		pin_name	= "Mic Jack";
-		gpio_name	= "Mic detection";
-		mask		= SND_JACK_MICROPHONE;
-	}
-
-	det = of_get_named_gpio_flags(dev->of_node, prop, 0, &flags);
-	if (det == -EPROBE_DEFER)
-		return -EPROBE_DEFER;
-
-	if (gpio_is_valid(det)) {
-		sjack->pin.pin		= pin_name;
-		sjack->pin.mask		= mask;
-
-		sjack->gpio.name	= gpio_name;
-		sjack->gpio.report	= mask;
-		sjack->gpio.gpio	= det;
-		sjack->gpio.invert	= !!(flags & OF_GPIO_ACTIVE_LOW);
-		sjack->gpio.debounce_time = 150;
-
-		snd_soc_card_jack_new(card, pin_name, mask,
-				      &sjack->jack,
-				      &sjack->pin, 1);
-
-		snd_soc_jack_add_gpios(&sjack->jack, 1,
-				       &sjack->gpio);
-	}
-
-	return 0;
-}
-
 static int asoc_simple_card_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-- 
cgit v1.2.3


From 8d1bd113a194407f9ad083403ea1cf92108edf5c Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Mon, 11 Jun 2018 17:32:13 +0900
Subject: ASoC: simple-card: move hp and mic detection to soc_card probe

This patch moves headphone and microphone detection to probe() of
snd_soc_card from init() of snd_soc_dai_link. This is because init()
is called (and an input device /dev/input/eventX is created too)
twice or above if simple card has two or more DAI links.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/simple-card.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index a6477a022156..c5b6e04cd926 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -149,14 +149,6 @@ static int asoc_simple_card_dai_init(struct snd_soc_pcm_runtime *rtd)
 	if (ret < 0)
 		return ret;
 
-	ret = asoc_simple_card_init_hp(rtd->card, &priv->hp_jack, PREFIX);
-	if (ret < 0)
-		return ret;
-
-	ret = asoc_simple_card_init_mic(rtd->card, &priv->mic_jack, PREFIX);
-	if (ret < 0)
-		return ret;
-
 	return 0;
 }
 
@@ -350,6 +342,22 @@ card_parse_end:
 	return ret;
 }
 
+static int asoc_simple_soc_card_probe(struct snd_soc_card *card)
+{
+	struct simple_card_data *priv = snd_soc_card_get_drvdata(card);
+	int ret;
+
+	ret = asoc_simple_card_init_hp(card, &priv->hp_jack, PREFIX);
+	if (ret < 0)
+		return ret;
+
+	ret = asoc_simple_card_init_mic(card, &priv->mic_jack, PREFIX);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int asoc_simple_card_probe(struct platform_device *pdev)
 {
 	struct simple_card_data *priv;
@@ -385,6 +393,7 @@ static int asoc_simple_card_probe(struct platform_device *pdev)
 	card->dev		= dev;
 	card->dai_link		= priv->dai_link;
 	card->num_links		= num;
+	card->probe		= asoc_simple_soc_card_probe;
 
 	if (np && of_device_is_available(np)) {
 
-- 
cgit v1.2.3


From f6de35cc145fb55d842db94e74841ecd8382e012 Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Mon, 11 Jun 2018 17:32:14 +0900
Subject: ASoC: audio-graph-card: add hp and mic detect gpios same as
 simple-card

This patch adds headphone and microphone jack detection gpios as same
as simple-card driver.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/audio-graph-card.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c
index d93bacacbd5b..a2a3e630f11c 100644
--- a/sound/soc/generic/audio-graph-card.c
+++ b/sound/soc/generic/audio-graph-card.c
@@ -21,7 +21,6 @@
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
 #include <linux/string.h>
-#include <sound/jack.h>
 #include <sound/simple_card_utils.h>
 
 struct graph_card_data {
@@ -32,6 +31,8 @@ struct graph_card_data {
 		unsigned int mclk_fs;
 	} *dai_props;
 	unsigned int mclk_fs;
+	struct asoc_simple_jack hp_jack;
+	struct asoc_simple_jack mic_jack;
 	struct snd_soc_dai_link *dai_link;
 	struct gpio_desc *pa_gpio;
 };
@@ -278,6 +279,22 @@ static int asoc_graph_get_dais_count(struct device *dev)
 	return count;
 }
 
+static int asoc_graph_soc_card_probe(struct snd_soc_card *card)
+{
+	struct graph_card_data *priv = snd_soc_card_get_drvdata(card);
+	int ret;
+
+	ret = asoc_simple_card_init_hp(card, &priv->hp_jack, NULL);
+	if (ret < 0)
+		return ret;
+
+	ret = asoc_simple_card_init_mic(card, &priv->mic_jack, NULL);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 static int asoc_graph_card_probe(struct platform_device *pdev)
 {
 	struct graph_card_data *priv;
@@ -319,6 +336,7 @@ static int asoc_graph_card_probe(struct platform_device *pdev)
 	card->num_links	= num;
 	card->dapm_widgets = asoc_graph_card_dapm_widgets;
 	card->num_dapm_widgets = ARRAY_SIZE(asoc_graph_card_dapm_widgets);
+	card->probe	= asoc_graph_soc_card_probe;
 
 	ret = asoc_graph_card_parse_of(priv);
 	if (ret < 0) {
-- 
cgit v1.2.3


From a0d847c380ba47886fcca4168698eef51c69f109 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Tue, 12 Jun 2018 05:51:46 +0000
Subject: ASoC: rsnd: add rsnd_daidrv_get()

rsnd priv has many parameters. On __rsnd_dai_probe() it uses
rsnd_rdai_get() to get rdai pointer, but is using priv->daidrv
directly to get daidrvhv, but it is confusable for reader.
This patch adds rsnd_daidrv_get() to get daidrv from priv.
Now reader can understand that rdai and daidrv are related.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Tested-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/rcar/core.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/sound/soc/sh/rcar/core.c b/sound/soc/sh/rcar/core.c
index eac22fef4543..6091e0916085 100644
--- a/sound/soc/sh/rcar/core.c
+++ b/sound/soc/sh/rcar/core.c
@@ -548,6 +548,15 @@ struct rsnd_dai *rsnd_rdai_get(struct rsnd_priv *priv, int id)
 	return priv->rdai + id;
 }
 
+static struct snd_soc_dai_driver
+*rsnd_daidrv_get(struct rsnd_priv *priv, int id)
+{
+	if ((id < 0) || (id >= rsnd_rdai_nr(priv)))
+		return NULL;
+
+	return priv->daidrv + id;
+}
+
 #define rsnd_dai_to_priv(dai) snd_soc_dai_get_drvdata(dai)
 static struct rsnd_dai *rsnd_dai_to_rdai(struct snd_soc_dai *dai)
 {
@@ -1033,7 +1042,7 @@ static void __rsnd_dai_probe(struct rsnd_priv *priv,
 	int io_i;
 
 	rdai		= rsnd_rdai_get(priv, dai_i);
-	drv		= priv->daidrv + dai_i;
+	drv		= rsnd_daidrv_get(priv, dai_i);
 	io_playback	= &rdai->playback;
 	io_capture	= &rdai->capture;
 
-- 
cgit v1.2.3


From d5c4e972d512ae0b59108ca92b9b35bc5cf5c14e Mon Sep 17 00:00:00 2001
From: Rohit Kumar <rohitkr@codeaurora.org>
Date: Wed, 6 Jun 2018 14:25:24 +0530
Subject: ASoC: qcom: apq8096: set card as device drvdata

snd_soc_card is retrieved as device drvdata during unbind().
Set it as drvdata during bind() to avoid memory corruption during
unbind().

Signed-off-by: Rohit kumar <rohitkr@codeaurora.org>
Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/apq8096.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index 561cd429e6f2..239b8cb77bdb 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -140,6 +140,7 @@ static int apq8096_bind(struct device *dev)
 
 	component_bind_all(dev, card);
 	card->dev = dev;
+	dev_set_drvdata(dev, card);
 	ret = apq8096_sbc_parse_of(card);
 	if (ret) {
 		dev_err(dev, "Error parsing OF data\n");
-- 
cgit v1.2.3


From 510e419cb85798915c6426c496a164ec6328d1a7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 6 Jun 2018 10:35:04 +0100
Subject: ASoC: twl6040: make pointer dmic_codec_dev static

The pointer dmic_codec_dev is local to the source and does not need
to be in global scope, so make it static.

Cleans up sparse warning:
warning: symbol 'dmic_codec_dev' was not declared. Should it be static?

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/omap/omap-abe-twl6040.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/omap/omap-abe-twl6040.c b/sound/soc/omap/omap-abe-twl6040.c
index 15ccbf479c96..d5ae9eb8c756 100644
--- a/sound/soc/omap/omap-abe-twl6040.c
+++ b/sound/soc/omap/omap-abe-twl6040.c
@@ -40,7 +40,7 @@ struct abe_twl6040 {
 	int	mclk_freq;	/* MCLK frequency speed for twl6040 */
 };
 
-struct platform_device *dmic_codec_dev;
+static struct platform_device *dmic_codec_dev;
 
 static int omap_abe_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *params)
-- 
cgit v1.2.3


From e380be7c557c4ddb1cb71404c10e0bfb3daf4644 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 6 Jun 2018 10:57:19 +0100
Subject: ASoC: ak5558: make two structures static

The structure ak5558_pm and soc_codec_dev_ak5558 are local to the
source and do not need to be in global scope, so make them static.
Also make soc_codec_dev_ak5558 static.

Cleans up sparse warnings:
warning: symbol 'ak5558_pm' was not declared. Should it be static?
warning: symbol 'soc_codec_dev_ak5558' was not declared. Should it be
static?

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Daniel Baluta <daniel.baluta@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/ak5558.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/ak5558.c b/sound/soc/codecs/ak5558.c
index f4ed5cc40661..448bb90c9c8e 100644
--- a/sound/soc/codecs/ak5558.c
+++ b/sound/soc/codecs/ak5558.c
@@ -322,13 +322,13 @@ static int __maybe_unused ak5558_runtime_resume(struct device *dev)
 	return regcache_sync(ak5558->regmap);
 }
 
-const struct dev_pm_ops ak5558_pm = {
+static const struct dev_pm_ops ak5558_pm = {
 	SET_RUNTIME_PM_OPS(ak5558_runtime_suspend, ak5558_runtime_resume, NULL)
 	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
 				pm_runtime_force_resume)
 };
 
-struct snd_soc_component_driver soc_codec_dev_ak5558 = {
+static const struct snd_soc_component_driver soc_codec_dev_ak5558 = {
 	.probe			= ak5558_probe,
 	.remove			= ak5558_remove,
 	.controls		= ak5558_snd_controls,
-- 
cgit v1.2.3


From 62624f72592b1d8e756e699cd6ade2be379f95a9 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 6 Jun 2018 11:31:23 +0100
Subject: ASoC: ak4458: make structure soc_codec_dev_ak4458 static const

The structure soc_codec_dev_ak4458 is local to the source and do not
need to be in global scope and can be const, make it static const.

Cleans up sparse warnings:
warning: symbol 'soc_codec_dev_ak4458' was not declared. Should it
be static?

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/ak4458.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/ak4458.c b/sound/soc/codecs/ak4458.c
index 31ec0ba2e639..299ada4dfaa0 100644
--- a/sound/soc/codecs/ak4458.c
+++ b/sound/soc/codecs/ak4458.c
@@ -558,7 +558,7 @@ static int __maybe_unused ak4458_runtime_resume(struct device *dev)
 }
 #endif /* CONFIG_PM */
 
-struct snd_soc_component_driver soc_codec_dev_ak4458 = {
+static const struct snd_soc_component_driver soc_codec_dev_ak4458 = {
 	.probe			= ak4458_probe,
 	.remove			= ak4458_remove,
 	.controls		= ak4458_snd_controls,
-- 
cgit v1.2.3


From 58f7d470c85801f55bbae2d3c93fe1a3d34aa143 Mon Sep 17 00:00:00 2001
From: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
Date: Mon, 4 Jun 2018 15:45:40 -0500
Subject: ASoC: TSCS42xx: Add mic bias boost control

Add mic bias boost control

Signed-off-by: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tscs42xx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/codecs/tscs42xx.c b/sound/soc/codecs/tscs42xx.c
index d18ff17719cc..743194052fc4 100644
--- a/sound/soc/codecs/tscs42xx.c
+++ b/sound/soc/codecs/tscs42xx.c
@@ -644,6 +644,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 	/* Input Channel Map */
 	SOC_ENUM("Input Channel Map", ch_map_select_enum),
 
+	/* Mic Bias */
+	SOC_SINGLE("Mic Bias Boost Switch", 0x71, 0x07, 1, 0),
+
 	/* Coefficient Ram */
 	COEFF_RAM_CTL("Cascade1L BiQuad1", BIQUAD_SIZE, 0x00),
 	COEFF_RAM_CTL("Cascade1L BiQuad2", BIQUAD_SIZE, 0x05),
-- 
cgit v1.2.3


From 19d996cc3ad698379bcd8482dabe78abe3dc8d96 Mon Sep 17 00:00:00 2001
From: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
Date: Mon, 4 Jun 2018 15:46:28 -0500
Subject: ASoC: TSCS42xx: Remove Playback/Capture in names

These aren't needed and some userspace apps don't work consistently with
them.

Remove Playback/Capture from control names

Signed-off-by: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tscs42xx.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/sound/soc/codecs/tscs42xx.c b/sound/soc/codecs/tscs42xx.c
index 743194052fc4..5d596e4dab0c 100644
--- a/sound/soc/codecs/tscs42xx.c
+++ b/sound/soc/codecs/tscs42xx.c
@@ -625,19 +625,19 @@ static int bytes_info_ext(struct snd_kcontrol *kcontrol,
 
 static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 	/* Volumes */
-	SOC_DOUBLE_R_TLV("Headphone Playback Volume", R_HPVOLL, R_HPVOLR,
+	SOC_DOUBLE_R_TLV("Headphone Volume", R_HPVOLL, R_HPVOLR,
 			FB_HPVOLL, 0x7F, 0, hpvol_scale),
-	SOC_DOUBLE_R_TLV("Speaker Playback Volume", R_SPKVOLL, R_SPKVOLR,
+	SOC_DOUBLE_R_TLV("Speaker Volume", R_SPKVOLL, R_SPKVOLR,
 			FB_SPKVOLL, 0x7F, 0, spkvol_scale),
-	SOC_DOUBLE_R_TLV("Master Playback Volume", R_DACVOLL, R_DACVOLR,
+	SOC_DOUBLE_R_TLV("Master Volume", R_DACVOLL, R_DACVOLR,
 			FB_DACVOLL, 0xFF, 0, dacvol_scale),
-	SOC_DOUBLE_R_TLV("PCM Capture Volume", R_ADCVOLL, R_ADCVOLR,
+	SOC_DOUBLE_R_TLV("PCM Volume", R_ADCVOLL, R_ADCVOLR,
 			FB_ADCVOLL, 0xFF, 0, adcvol_scale),
-	SOC_DOUBLE_R_TLV("Master Capture Volume", R_INVOLL, R_INVOLR,
+	SOC_DOUBLE_R_TLV("Input Volume", R_INVOLL, R_INVOLR,
 			FB_INVOLL, 0x3F, 0, invol_scale),
 
 	/* INSEL */
-	SOC_DOUBLE_R_TLV("Mic Boost Capture Volume", R_INSELL, R_INSELR,
+	SOC_DOUBLE_R_TLV("Mic Boost Volume", R_INSELL, R_INSELR,
 			FB_INSELL_MICBSTL, FV_INSELL_MICBSTL_30DB,
 			0, mic_boost_scale),
 
@@ -736,9 +736,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 		R_CLECTL, FB_CLECTL_LIMIT_EN, 1, 0),
 	SOC_SINGLE("Comp Switch",
 		R_CLECTL, FB_CLECTL_COMP_EN, 1, 0),
-	SOC_SINGLE_TLV("CLE Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("CLE Make-Up Gain Volume",
 		R_MUGAIN, FB_MUGAIN_CLEMUG, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("Comp Thresh Volume",
 		R_COMPTH, FB_COMPTH, 0xff, 0, compth_scale),
 	SOC_ENUM("Comp Ratio", compressor_ratio_enum),
 	SND_SOC_BYTES("Comp Atk Time", R_CATKTCL, 2),
@@ -769,9 +769,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 
 	SOC_SINGLE("MBC1 Phase Invert Switch",
 		R_DACMBCMUG1, FB_DACMBCMUG1_PHASE, 1, 0),
-	SOC_SINGLE_TLV("DAC MBC1 Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC1 Make-Up Gain Volume",
 		R_DACMBCMUG1, FB_DACMBCMUG1_MUGAIN, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("DAC MBC1 Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC1 Comp Thresh Volume",
 		R_DACMBCTHR1, FB_DACMBCTHR1_THRESH, 0xff, 0, compth_scale),
 	SOC_ENUM("DAC MBC1 Comp Ratio",
 		dac_mbc1_compressor_ratio_enum),
@@ -781,9 +781,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 
 	SOC_SINGLE("MBC2 Phase Invert Switch",
 		R_DACMBCMUG2, FB_DACMBCMUG2_PHASE, 1, 0),
-	SOC_SINGLE_TLV("DAC MBC2 Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC2 Make-Up Gain Volume",
 		R_DACMBCMUG2, FB_DACMBCMUG2_MUGAIN, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("DAC MBC2 Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC2 Comp Thresh Volume",
 		R_DACMBCTHR2, FB_DACMBCTHR2_THRESH, 0xff, 0, compth_scale),
 	SOC_ENUM("DAC MBC2 Comp Ratio",
 		dac_mbc2_compressor_ratio_enum),
@@ -793,9 +793,9 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 
 	SOC_SINGLE("MBC3 Phase Invert Switch",
 		R_DACMBCMUG3, FB_DACMBCMUG3_PHASE, 1, 0),
-	SOC_SINGLE_TLV("DAC MBC3 Make-Up Gain Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC3 Make-Up Gain Volume",
 		R_DACMBCMUG3, FB_DACMBCMUG3_MUGAIN, 0x1f, 0, mugain_scale),
-	SOC_SINGLE_TLV("DAC MBC3 Comp Thresh Playback Volume",
+	SOC_SINGLE_TLV("DAC MBC3 Comp Thresh Volume",
 		R_DACMBCTHR3, FB_DACMBCTHR3_THRESH, 0xff, 0, compth_scale),
 	SOC_ENUM("DAC MBC3 Comp Ratio",
 		dac_mbc3_compressor_ratio_enum),
-- 
cgit v1.2.3


From 53af408cd9f2d1c66bc081c1d82797bfe44af3e5 Mon Sep 17 00:00:00 2001
From: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
Date: Mon, 4 Jun 2018 15:47:02 -0500
Subject: ASoC: TSCS42xx: Add headphone auto switching

Add headphone auto switching controls

Signed-off-by: Steven Eckhoff <steven.eckhoff.opensource@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tscs42xx.c | 6 ++++++
 sound/soc/codecs/tscs42xx.h | 8 ++++++++
 2 files changed, 14 insertions(+)

diff --git a/sound/soc/codecs/tscs42xx.c b/sound/soc/codecs/tscs42xx.c
index 5d596e4dab0c..7396a6e5277e 100644
--- a/sound/soc/codecs/tscs42xx.c
+++ b/sound/soc/codecs/tscs42xx.c
@@ -647,6 +647,12 @@ static const struct snd_kcontrol_new tscs42xx_snd_controls[] = {
 	/* Mic Bias */
 	SOC_SINGLE("Mic Bias Boost Switch", 0x71, 0x07, 1, 0),
 
+	/* Headphone Auto Switching */
+	SOC_SINGLE("Headphone Auto Switching Switch",
+			R_CTL, FB_CTL_HPSWEN, 1, 0),
+	SOC_SINGLE("Headphone Detect Polarity Toggle Switch",
+			R_CTL, FB_CTL_HPSWPOL, 1, 0),
+
 	/* Coefficient Ram */
 	COEFF_RAM_CTL("Cascade1L BiQuad1", BIQUAD_SIZE, 0x00),
 	COEFF_RAM_CTL("Cascade1L BiQuad2", BIQUAD_SIZE, 0x05),
diff --git a/sound/soc/codecs/tscs42xx.h b/sound/soc/codecs/tscs42xx.h
index 814c8f3c4a68..6b3a21081635 100644
--- a/sound/soc/codecs/tscs42xx.h
+++ b/sound/soc/codecs/tscs42xx.h
@@ -34,6 +34,7 @@ enum {
 #define R_DACSR         0x19
 #define R_PWRM1         0x1A
 #define R_PWRM2         0x1B
+#define R_CTL		0x1C
 #define R_CONFIG0       0x1F
 #define R_CONFIG1       0x20
 #define R_DMICCTL       0x24
@@ -1110,6 +1111,13 @@ enum {
 #define RV_PWRM2_VREF_DISABLE \
 	 RV(FV_PWRM2_VREF_DISABLE, FB_PWRM2_VREF)
 
+/******************************
+ *      R_CTL (0x1C)          *
+ ******************************/
+
+/* Fiel Offsets */
+#define FB_CTL_HPSWEN                        7
+#define FB_CTL_HPSWPOL                       6
 
 /******************************
  *      R_CONFIG0 (0x1F)      *
-- 
cgit v1.2.3


From 0ddce71c21f03fd19867c4939d3ca710f37cdf1a Mon Sep 17 00:00:00 2001
From: Bard Liao <bardliao@realtek.com>
Date: Thu, 7 Jun 2018 16:37:38 +0800
Subject: ASoC: rt5682: add rt5682 codec driver

This is the initial codec driver for rt5682.

Signed-off-by: Bard Liao <bardliao@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/rt5682.txt |   50 +
 include/sound/rt5682.h                             |   40 +
 sound/soc/codecs/Kconfig                           |    6 +
 sound/soc/codecs/Makefile                          |    2 +
 sound/soc/codecs/rt5682.c                          | 2682 ++++++++++++++++++++
 sound/soc/codecs/rt5682.h                          | 1324 ++++++++++
 6 files changed, 4104 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/rt5682.txt
 create mode 100644 include/sound/rt5682.h
 create mode 100644 sound/soc/codecs/rt5682.c
 create mode 100644 sound/soc/codecs/rt5682.h

diff --git a/Documentation/devicetree/bindings/sound/rt5682.txt b/Documentation/devicetree/bindings/sound/rt5682.txt
new file mode 100644
index 000000000000..312e9a129530
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/rt5682.txt
@@ -0,0 +1,50 @@
+RT5682 audio CODEC
+
+This device supports I2C only.
+
+Required properties:
+
+- compatible : "realtek,rt5682" or "realtek,rt5682i"
+
+- reg : The I2C address of the device.
+
+Optional properties:
+
+- interrupts : The CODEC's interrupt output.
+
+- realtek,dmic1-data-pin
+  0: dmic1 is not used
+  1: using GPIO2 pin as dmic1 data pin
+  2: using GPIO5 pin as dmic1 data pin
+
+- realtek,dmic1-clk-pin
+  0: using GPIO1 pin as dmic1 clock pin
+  1: using GPIO3 pin as dmic1 clock pin
+
+- realtek,jd-src
+  0: No JD is used
+  1: using JD1 as JD source
+
+- realtek,ldo1-en-gpios : The GPIO that controls the CODEC's LDO1_EN pin.
+
+Pins on the device (for linking into audio routes) for RT5682:
+
+  * DMIC L1
+  * DMIC R1
+  * IN1P
+  * HPOL
+  * HPOR
+
+Example:
+
+rt5682 {
+	compatible = "realtek,rt5682i";
+	reg = <0x1a>;
+	interrupt-parent = <&gpio>;
+	interrupts = <TEGRA_GPIO(U, 6) GPIO_ACTIVE_HIGH>;
+	realtek,ldo1-en-gpios =
+		<&gpio TEGRA_GPIO(R, 2) GPIO_ACTIVE_HIGH>;
+	realtek,dmic1-data-pin = <1>;
+	realtek,dmic1-clk-pin = <1>;
+	realtek,jd-src = <1>;
+};
diff --git a/include/sound/rt5682.h b/include/sound/rt5682.h
new file mode 100644
index 000000000000..0251797ab438
--- /dev/null
+++ b/include/sound/rt5682.h
@@ -0,0 +1,40 @@
+/*
+ * linux/sound/rt5682.h -- Platform data for RT5682
+ *
+ * Copyright 2018 Realtek Microelectronics
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __LINUX_SND_RT5682_H
+#define __LINUX_SND_RT5682_H
+
+enum rt5682_dmic1_data_pin {
+	RT5682_DMIC1_NULL,
+	RT5682_DMIC1_DATA_GPIO2,
+	RT5682_DMIC1_DATA_GPIO5,
+};
+
+enum rt5682_dmic1_clk_pin {
+	RT5682_DMIC1_CLK_GPIO1,
+	RT5682_DMIC1_CLK_GPIO3,
+};
+
+enum rt5682_jd_src {
+	RT5682_JD_NULL,
+	RT5682_JD1,
+};
+
+struct rt5682_platform_data {
+
+	int ldo1_en; /* GPIO for LDO1_EN */
+
+	enum rt5682_dmic1_data_pin dmic1_data_pin;
+	enum rt5682_dmic1_clk_pin dmic1_clk_pin;
+	enum rt5682_jd_src jd_src;
+};
+
+#endif
+
diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 63cf62e9c9aa..f6b8d4bf8796 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -141,6 +141,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_RT5668 if I2C
 	select SND_SOC_RT5670 if I2C
 	select SND_SOC_RT5677 if I2C && SPI_MASTER
+	select SND_SOC_RT5682 if I2C
 	select SND_SOC_SGTL5000 if I2C
 	select SND_SOC_SI476X if MFD_SI476X_CORE
 	select SND_SOC_SIRF_AUDIO_CODEC
@@ -778,6 +779,7 @@ config SND_SOC_RL6231
 	default y if SND_SOC_RT5668=y
 	default y if SND_SOC_RT5670=y
 	default y if SND_SOC_RT5677=y
+	default y if SND_SOC_RT5682=y
 	default y if SND_SOC_RT1305=y
 	default m if SND_SOC_RT5514=m
 	default m if SND_SOC_RT5616=m
@@ -791,6 +793,7 @@ config SND_SOC_RL6231
 	default m if SND_SOC_RT5668=m
 	default m if SND_SOC_RT5670=m
 	default m if SND_SOC_RT5677=m
+	default m if SND_SOC_RT5682=m
 	default m if SND_SOC_RT1305=m
 
 config SND_SOC_RL6347A
@@ -871,6 +874,9 @@ config SND_SOC_RT5677_SPI
 	tristate
 	default SND_SOC_RT5677 && SPI
 
+config SND_SOC_RT5682
+	tristate
+
 #Freescale sgtl5000 codec
 config SND_SOC_SGTL5000
 	tristate "Freescale SGTL5000 CODEC"
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index e023fdf85221..e43d99a039d3 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -146,6 +146,7 @@ snd-soc-rt5668-objs := rt5668.o
 snd-soc-rt5670-objs := rt5670.o
 snd-soc-rt5677-objs := rt5677.o
 snd-soc-rt5677-spi-objs := rt5677-spi.o
+snd-soc-rt5682-objs := rt5682.o
 snd-soc-sgtl5000-objs := sgtl5000.o
 snd-soc-alc5623-objs := alc5623.o
 snd-soc-alc5632-objs := alc5632.o
@@ -405,6 +406,7 @@ obj-$(CONFIG_SND_SOC_RT5668)	+= snd-soc-rt5668.o
 obj-$(CONFIG_SND_SOC_RT5670)	+= snd-soc-rt5670.o
 obj-$(CONFIG_SND_SOC_RT5677)	+= snd-soc-rt5677.o
 obj-$(CONFIG_SND_SOC_RT5677_SPI)	+= snd-soc-rt5677-spi.o
+obj-$(CONFIG_SND_SOC_RT5682)	+= snd-soc-rt5682.o
 obj-$(CONFIG_SND_SOC_SGTL5000)  += snd-soc-sgtl5000.o
 obj-$(CONFIG_SND_SOC_SIGMADSP)	+= snd-soc-sigmadsp.o
 obj-$(CONFIG_SND_SOC_SIGMADSP_I2C)	+= snd-soc-sigmadsp-i2c.o
diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
new file mode 100644
index 000000000000..61a97301bcfa
--- /dev/null
+++ b/sound/soc/codecs/rt5682.c
@@ -0,0 +1,2682 @@
+/*
+ * rt5682.c  --  RT5682 ALSA SoC audio component driver
+ *
+ * Copyright 2018 Realtek Semiconductor Corp.
+ * Author: Bard Liao <bardliao@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/pm.h>
+#include <linux/i2c.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/acpi.h>
+#include <linux/gpio.h>
+#include <linux/of_gpio.h>
+#include <linux/regulator/consumer.h>
+#include <linux/mutex.h>
+#include <sound/core.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/jack.h>
+#include <sound/soc.h>
+#include <sound/soc-dapm.h>
+#include <sound/initval.h>
+#include <sound/tlv.h>
+#include <sound/rt5682.h>
+
+#include "rl6231.h"
+#include "rt5682.h"
+
+#define RT5682_NUM_SUPPLIES 3
+
+static const char *rt5682_supply_names[RT5682_NUM_SUPPLIES] = {
+	"AVDD",
+	"MICVDD",
+	"VBAT",
+};
+
+struct rt5682_priv {
+	struct snd_soc_component *component;
+	struct rt5682_platform_data pdata;
+	struct regmap *regmap;
+	struct snd_soc_jack *hs_jack;
+	struct regulator_bulk_data supplies[RT5682_NUM_SUPPLIES];
+	struct delayed_work jack_detect_work;
+	struct delayed_work jd_check_work;
+	struct mutex calibrate_mutex;
+
+	int sysclk;
+	int sysclk_src;
+	int lrck[RT5682_AIFS];
+	int bclk[RT5682_AIFS];
+	int master[RT5682_AIFS];
+
+	int pll_src;
+	int pll_in;
+	int pll_out;
+
+	int jack_type;
+};
+
+static const struct reg_sequence patch_list[] = {
+	{0x01c1, 0x1000},
+};
+
+static const struct reg_default rt5682_reg[] = {
+	{0x0002, 0x8080},
+	{0x0003, 0x8000},
+	{0x0005, 0x0000},
+	{0x0006, 0x0000},
+	{0x0008, 0x800f},
+	{0x000b, 0x0000},
+	{0x0010, 0x4040},
+	{0x0011, 0x0000},
+	{0x0012, 0x1404},
+	{0x0013, 0x1000},
+	{0x0014, 0xa00a},
+	{0x0015, 0x0404},
+	{0x0016, 0x0404},
+	{0x0019, 0xafaf},
+	{0x001c, 0x2f2f},
+	{0x001f, 0x0000},
+	{0x0022, 0x5757},
+	{0x0023, 0x0039},
+	{0x0024, 0x000b},
+	{0x0026, 0xc0c4},
+	{0x0029, 0x8080},
+	{0x002a, 0xa0a0},
+	{0x002b, 0x0300},
+	{0x0030, 0x0000},
+	{0x003c, 0x0080},
+	{0x0044, 0x0c0c},
+	{0x0049, 0x0000},
+	{0x0061, 0x0000},
+	{0x0062, 0x0000},
+	{0x0063, 0x003f},
+	{0x0064, 0x0000},
+	{0x0065, 0x0000},
+	{0x0066, 0x0030},
+	{0x0067, 0x0000},
+	{0x006b, 0x0000},
+	{0x006c, 0x0000},
+	{0x006d, 0x2200},
+	{0x006e, 0x0a10},
+	{0x0070, 0x8000},
+	{0x0071, 0x8000},
+	{0x0073, 0x0000},
+	{0x0074, 0x0000},
+	{0x0075, 0x0002},
+	{0x0076, 0x0001},
+	{0x0079, 0x0000},
+	{0x007a, 0x0000},
+	{0x007b, 0x0000},
+	{0x007c, 0x0100},
+	{0x007e, 0x0000},
+	{0x0080, 0x0000},
+	{0x0081, 0x0000},
+	{0x0082, 0x0000},
+	{0x0083, 0x0000},
+	{0x0084, 0x0000},
+	{0x0085, 0x0000},
+	{0x0086, 0x0005},
+	{0x0087, 0x0000},
+	{0x0088, 0x0000},
+	{0x008c, 0x0003},
+	{0x008d, 0x0000},
+	{0x008e, 0x0060},
+	{0x008f, 0x1000},
+	{0x0091, 0x0c26},
+	{0x0092, 0x0073},
+	{0x0093, 0x0000},
+	{0x0094, 0x0080},
+	{0x0098, 0x0000},
+	{0x009a, 0x0000},
+	{0x009b, 0x0000},
+	{0x009c, 0x0000},
+	{0x009d, 0x0000},
+	{0x009e, 0x100c},
+	{0x009f, 0x0000},
+	{0x00a0, 0x0000},
+	{0x00a3, 0x0002},
+	{0x00a4, 0x0001},
+	{0x00ae, 0x2040},
+	{0x00af, 0x0000},
+	{0x00b6, 0x0000},
+	{0x00b7, 0x0000},
+	{0x00b8, 0x0000},
+	{0x00b9, 0x0002},
+	{0x00be, 0x0000},
+	{0x00c0, 0x0160},
+	{0x00c1, 0x82a0},
+	{0x00c2, 0x0000},
+	{0x00d0, 0x0000},
+	{0x00d1, 0x2244},
+	{0x00d2, 0x3300},
+	{0x00d3, 0x2200},
+	{0x00d4, 0x0000},
+	{0x00d9, 0x0009},
+	{0x00da, 0x0000},
+	{0x00db, 0x0000},
+	{0x00dc, 0x00c0},
+	{0x00dd, 0x2220},
+	{0x00de, 0x3131},
+	{0x00df, 0x3131},
+	{0x00e0, 0x3131},
+	{0x00e2, 0x0000},
+	{0x00e3, 0x4000},
+	{0x00e4, 0x0aa0},
+	{0x00e5, 0x3131},
+	{0x00e6, 0x3131},
+	{0x00e7, 0x3131},
+	{0x00e8, 0x3131},
+	{0x00ea, 0xb320},
+	{0x00eb, 0x0000},
+	{0x00f0, 0x0000},
+	{0x00f1, 0x00d0},
+	{0x00f2, 0x00d0},
+	{0x00f6, 0x0000},
+	{0x00fa, 0x0000},
+	{0x00fb, 0x0000},
+	{0x00fc, 0x0000},
+	{0x00fd, 0x0000},
+	{0x00fe, 0x10ec},
+	{0x00ff, 0x6530},
+	{0x0100, 0xa0a0},
+	{0x010b, 0x0000},
+	{0x010c, 0xae00},
+	{0x010d, 0xaaa0},
+	{0x010e, 0x8aa2},
+	{0x010f, 0x02a2},
+	{0x0110, 0xc000},
+	{0x0111, 0x04a2},
+	{0x0112, 0x2800},
+	{0x0113, 0x0000},
+	{0x0117, 0x0100},
+	{0x0125, 0x0410},
+	{0x0132, 0x6026},
+	{0x0136, 0x5555},
+	{0x0138, 0x3700},
+	{0x013a, 0x2000},
+	{0x013b, 0x2000},
+	{0x013c, 0x2005},
+	{0x013f, 0x0000},
+	{0x0142, 0x0000},
+	{0x0145, 0x0002},
+	{0x0146, 0x0000},
+	{0x0147, 0x0000},
+	{0x0148, 0x0000},
+	{0x0149, 0x0000},
+	{0x0150, 0x79a1},
+	{0x0151, 0x0000},
+	{0x0160, 0x4ec0},
+	{0x0161, 0x0080},
+	{0x0162, 0x0200},
+	{0x0163, 0x0800},
+	{0x0164, 0x0000},
+	{0x0165, 0x0000},
+	{0x0166, 0x0000},
+	{0x0167, 0x000f},
+	{0x0168, 0x000f},
+	{0x0169, 0x0021},
+	{0x0190, 0x413d},
+	{0x0194, 0x0000},
+	{0x0195, 0x0000},
+	{0x0197, 0x0022},
+	{0x0198, 0x0000},
+	{0x0199, 0x0000},
+	{0x01af, 0x0000},
+	{0x01b0, 0x0400},
+	{0x01b1, 0x0000},
+	{0x01b2, 0x0000},
+	{0x01b3, 0x0000},
+	{0x01b4, 0x0000},
+	{0x01b5, 0x0000},
+	{0x01b6, 0x01c3},
+	{0x01b7, 0x02a0},
+	{0x01b8, 0x03e9},
+	{0x01b9, 0x1389},
+	{0x01ba, 0xc351},
+	{0x01bb, 0x0009},
+	{0x01bc, 0x0018},
+	{0x01bd, 0x002a},
+	{0x01be, 0x004c},
+	{0x01bf, 0x0097},
+	{0x01c0, 0x433d},
+	{0x01c2, 0x0000},
+	{0x01c3, 0x0000},
+	{0x01c4, 0x0000},
+	{0x01c5, 0x0000},
+	{0x01c6, 0x0000},
+	{0x01c7, 0x0000},
+	{0x01c8, 0x40af},
+	{0x01c9, 0x0702},
+	{0x01ca, 0x0000},
+	{0x01cb, 0x0000},
+	{0x01cc, 0x5757},
+	{0x01cd, 0x5757},
+	{0x01ce, 0x5757},
+	{0x01cf, 0x5757},
+	{0x01d0, 0x5757},
+	{0x01d1, 0x5757},
+	{0x01d2, 0x5757},
+	{0x01d3, 0x5757},
+	{0x01d4, 0x5757},
+	{0x01d5, 0x5757},
+	{0x01d6, 0x0000},
+	{0x01d7, 0x0008},
+	{0x01d8, 0x0029},
+	{0x01d9, 0x3333},
+	{0x01da, 0x0000},
+	{0x01db, 0x0004},
+	{0x01dc, 0x0000},
+	{0x01de, 0x7c00},
+	{0x01df, 0x0320},
+	{0x01e0, 0x06a1},
+	{0x01e1, 0x0000},
+	{0x01e2, 0x0000},
+	{0x01e3, 0x0000},
+	{0x01e4, 0x0000},
+	{0x01e6, 0x0001},
+	{0x01e7, 0x0000},
+	{0x01e8, 0x0000},
+	{0x01ea, 0x0000},
+	{0x01eb, 0x0000},
+	{0x01ec, 0x0000},
+	{0x01ed, 0x0000},
+	{0x01ee, 0x0000},
+	{0x01ef, 0x0000},
+	{0x01f0, 0x0000},
+	{0x01f1, 0x0000},
+	{0x01f2, 0x0000},
+	{0x01f3, 0x0000},
+	{0x01f4, 0x0000},
+	{0x0210, 0x6297},
+	{0x0211, 0xa005},
+	{0x0212, 0x824c},
+	{0x0213, 0xf7ff},
+	{0x0214, 0xf24c},
+	{0x0215, 0x0102},
+	{0x0216, 0x00a3},
+	{0x0217, 0x0048},
+	{0x0218, 0xa2c0},
+	{0x0219, 0x0400},
+	{0x021a, 0x00c8},
+	{0x021b, 0x00c0},
+	{0x021c, 0x0000},
+	{0x0250, 0x4500},
+	{0x0251, 0x40b3},
+	{0x0252, 0x0000},
+	{0x0253, 0x0000},
+	{0x0254, 0x0000},
+	{0x0255, 0x0000},
+	{0x0256, 0x0000},
+	{0x0257, 0x0000},
+	{0x0258, 0x0000},
+	{0x0259, 0x0000},
+	{0x025a, 0x0005},
+	{0x0270, 0x0000},
+	{0x02ff, 0x0110},
+	{0x0300, 0x001f},
+	{0x0301, 0x032c},
+	{0x0302, 0x5f21},
+	{0x0303, 0x4000},
+	{0x0304, 0x4000},
+	{0x0305, 0x06d5},
+	{0x0306, 0x8000},
+	{0x0307, 0x0700},
+	{0x0310, 0x4560},
+	{0x0311, 0xa4a8},
+	{0x0312, 0x7418},
+	{0x0313, 0x0000},
+	{0x0314, 0x0006},
+	{0x0315, 0xffff},
+	{0x0316, 0xc400},
+	{0x0317, 0x0000},
+	{0x03c0, 0x7e00},
+	{0x03c1, 0x8000},
+	{0x03c2, 0x8000},
+	{0x03c3, 0x8000},
+	{0x03c4, 0x8000},
+	{0x03c5, 0x8000},
+	{0x03c6, 0x8000},
+	{0x03c7, 0x8000},
+	{0x03c8, 0x8000},
+	{0x03c9, 0x8000},
+	{0x03ca, 0x8000},
+	{0x03cb, 0x8000},
+	{0x03cc, 0x8000},
+	{0x03d0, 0x0000},
+	{0x03d1, 0x0000},
+	{0x03d2, 0x0000},
+	{0x03d3, 0x0000},
+	{0x03d4, 0x2000},
+	{0x03d5, 0x2000},
+	{0x03d6, 0x0000},
+	{0x03d7, 0x0000},
+	{0x03d8, 0x2000},
+	{0x03d9, 0x2000},
+	{0x03da, 0x2000},
+	{0x03db, 0x2000},
+	{0x03dc, 0x0000},
+	{0x03dd, 0x0000},
+	{0x03de, 0x0000},
+	{0x03df, 0x2000},
+	{0x03e0, 0x0000},
+	{0x03e1, 0x0000},
+	{0x03e2, 0x0000},
+	{0x03e3, 0x0000},
+	{0x03e4, 0x0000},
+	{0x03e5, 0x0000},
+	{0x03e6, 0x0000},
+	{0x03e7, 0x0000},
+	{0x03e8, 0x0000},
+	{0x03e9, 0x0000},
+	{0x03ea, 0x0000},
+	{0x03eb, 0x0000},
+	{0x03ec, 0x0000},
+	{0x03ed, 0x0000},
+	{0x03ee, 0x0000},
+	{0x03ef, 0x0000},
+	{0x03f0, 0x0800},
+	{0x03f1, 0x0800},
+	{0x03f2, 0x0800},
+	{0x03f3, 0x0800},
+};
+
+static bool rt5682_volatile_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RT5682_RESET:
+	case RT5682_CBJ_CTRL_2:
+	case RT5682_INT_ST_1:
+	case RT5682_4BTN_IL_CMD_1:
+	case RT5682_AJD1_CTRL:
+	case RT5682_HP_CALIB_CTRL_1:
+	case RT5682_DEVICE_ID:
+	case RT5682_I2C_MODE:
+	case RT5682_HP_CALIB_CTRL_10:
+	case RT5682_EFUSE_CTRL_2:
+	case RT5682_JD_TOP_VC_VTRL:
+	case RT5682_HP_IMP_SENS_CTRL_19:
+	case RT5682_IL_CMD_1:
+	case RT5682_SAR_IL_CMD_2:
+	case RT5682_SAR_IL_CMD_4:
+	case RT5682_SAR_IL_CMD_10:
+	case RT5682_SAR_IL_CMD_11:
+	case RT5682_EFUSE_CTRL_6...RT5682_EFUSE_CTRL_11:
+	case RT5682_HP_CALIB_STA_1...RT5682_HP_CALIB_STA_11:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool rt5682_readable_register(struct device *dev, unsigned int reg)
+{
+	switch (reg) {
+	case RT5682_RESET:
+	case RT5682_VERSION_ID:
+	case RT5682_VENDOR_ID:
+	case RT5682_DEVICE_ID:
+	case RT5682_HP_CTRL_1:
+	case RT5682_HP_CTRL_2:
+	case RT5682_HPL_GAIN:
+	case RT5682_HPR_GAIN:
+	case RT5682_I2C_CTRL:
+	case RT5682_CBJ_BST_CTRL:
+	case RT5682_CBJ_CTRL_1:
+	case RT5682_CBJ_CTRL_2:
+	case RT5682_CBJ_CTRL_3:
+	case RT5682_CBJ_CTRL_4:
+	case RT5682_CBJ_CTRL_5:
+	case RT5682_CBJ_CTRL_6:
+	case RT5682_CBJ_CTRL_7:
+	case RT5682_DAC1_DIG_VOL:
+	case RT5682_STO1_ADC_DIG_VOL:
+	case RT5682_STO1_ADC_BOOST:
+	case RT5682_HP_IMP_GAIN_1:
+	case RT5682_HP_IMP_GAIN_2:
+	case RT5682_SIDETONE_CTRL:
+	case RT5682_STO1_ADC_MIXER:
+	case RT5682_AD_DA_MIXER:
+	case RT5682_STO1_DAC_MIXER:
+	case RT5682_A_DAC1_MUX:
+	case RT5682_DIG_INF2_DATA:
+	case RT5682_REC_MIXER:
+	case RT5682_CAL_REC:
+	case RT5682_ALC_BACK_GAIN:
+	case RT5682_PWR_DIG_1:
+	case RT5682_PWR_DIG_2:
+	case RT5682_PWR_ANLG_1:
+	case RT5682_PWR_ANLG_2:
+	case RT5682_PWR_ANLG_3:
+	case RT5682_PWR_MIXER:
+	case RT5682_PWR_VOL:
+	case RT5682_CLK_DET:
+	case RT5682_RESET_LPF_CTRL:
+	case RT5682_RESET_HPF_CTRL:
+	case RT5682_DMIC_CTRL_1:
+	case RT5682_I2S1_SDP:
+	case RT5682_I2S2_SDP:
+	case RT5682_ADDA_CLK_1:
+	case RT5682_ADDA_CLK_2:
+	case RT5682_I2S1_F_DIV_CTRL_1:
+	case RT5682_I2S1_F_DIV_CTRL_2:
+	case RT5682_TDM_CTRL:
+	case RT5682_TDM_ADDA_CTRL_1:
+	case RT5682_TDM_ADDA_CTRL_2:
+	case RT5682_DATA_SEL_CTRL_1:
+	case RT5682_TDM_TCON_CTRL:
+	case RT5682_GLB_CLK:
+	case RT5682_PLL_CTRL_1:
+	case RT5682_PLL_CTRL_2:
+	case RT5682_PLL_TRACK_1:
+	case RT5682_PLL_TRACK_2:
+	case RT5682_PLL_TRACK_3:
+	case RT5682_PLL_TRACK_4:
+	case RT5682_PLL_TRACK_5:
+	case RT5682_PLL_TRACK_6:
+	case RT5682_PLL_TRACK_11:
+	case RT5682_SDW_REF_CLK:
+	case RT5682_DEPOP_1:
+	case RT5682_DEPOP_2:
+	case RT5682_HP_CHARGE_PUMP_1:
+	case RT5682_HP_CHARGE_PUMP_2:
+	case RT5682_MICBIAS_1:
+	case RT5682_MICBIAS_2:
+	case RT5682_PLL_TRACK_12:
+	case RT5682_PLL_TRACK_14:
+	case RT5682_PLL2_CTRL_1:
+	case RT5682_PLL2_CTRL_2:
+	case RT5682_PLL2_CTRL_3:
+	case RT5682_PLL2_CTRL_4:
+	case RT5682_RC_CLK_CTRL:
+	case RT5682_I2S_M_CLK_CTRL_1:
+	case RT5682_I2S2_F_DIV_CTRL_1:
+	case RT5682_I2S2_F_DIV_CTRL_2:
+	case RT5682_EQ_CTRL_1:
+	case RT5682_EQ_CTRL_2:
+	case RT5682_IRQ_CTRL_1:
+	case RT5682_IRQ_CTRL_2:
+	case RT5682_IRQ_CTRL_3:
+	case RT5682_IRQ_CTRL_4:
+	case RT5682_INT_ST_1:
+	case RT5682_GPIO_CTRL_1:
+	case RT5682_GPIO_CTRL_2:
+	case RT5682_GPIO_CTRL_3:
+	case RT5682_HP_AMP_DET_CTRL_1:
+	case RT5682_HP_AMP_DET_CTRL_2:
+	case RT5682_MID_HP_AMP_DET:
+	case RT5682_LOW_HP_AMP_DET:
+	case RT5682_DELAY_BUF_CTRL:
+	case RT5682_SV_ZCD_1:
+	case RT5682_SV_ZCD_2:
+	case RT5682_IL_CMD_1:
+	case RT5682_IL_CMD_2:
+	case RT5682_IL_CMD_3:
+	case RT5682_IL_CMD_4:
+	case RT5682_IL_CMD_5:
+	case RT5682_IL_CMD_6:
+	case RT5682_4BTN_IL_CMD_1:
+	case RT5682_4BTN_IL_CMD_2:
+	case RT5682_4BTN_IL_CMD_3:
+	case RT5682_4BTN_IL_CMD_4:
+	case RT5682_4BTN_IL_CMD_5:
+	case RT5682_4BTN_IL_CMD_6:
+	case RT5682_4BTN_IL_CMD_7:
+	case RT5682_ADC_STO1_HP_CTRL_1:
+	case RT5682_ADC_STO1_HP_CTRL_2:
+	case RT5682_AJD1_CTRL:
+	case RT5682_JD1_THD:
+	case RT5682_JD2_THD:
+	case RT5682_JD_CTRL_1:
+	case RT5682_DUMMY_1:
+	case RT5682_DUMMY_2:
+	case RT5682_DUMMY_3:
+	case RT5682_DAC_ADC_DIG_VOL1:
+	case RT5682_BIAS_CUR_CTRL_2:
+	case RT5682_BIAS_CUR_CTRL_3:
+	case RT5682_BIAS_CUR_CTRL_4:
+	case RT5682_BIAS_CUR_CTRL_5:
+	case RT5682_BIAS_CUR_CTRL_6:
+	case RT5682_BIAS_CUR_CTRL_7:
+	case RT5682_BIAS_CUR_CTRL_8:
+	case RT5682_BIAS_CUR_CTRL_9:
+	case RT5682_BIAS_CUR_CTRL_10:
+	case RT5682_VREF_REC_OP_FB_CAP_CTRL:
+	case RT5682_CHARGE_PUMP_1:
+	case RT5682_DIG_IN_CTRL_1:
+	case RT5682_PAD_DRIVING_CTRL:
+	case RT5682_SOFT_RAMP_DEPOP:
+	case RT5682_CHOP_DAC:
+	case RT5682_CHOP_ADC:
+	case RT5682_CALIB_ADC_CTRL:
+	case RT5682_VOL_TEST:
+	case RT5682_SPKVDD_DET_STA:
+	case RT5682_TEST_MODE_CTRL_1:
+	case RT5682_TEST_MODE_CTRL_2:
+	case RT5682_TEST_MODE_CTRL_3:
+	case RT5682_TEST_MODE_CTRL_4:
+	case RT5682_TEST_MODE_CTRL_5:
+	case RT5682_PLL1_INTERNAL:
+	case RT5682_PLL2_INTERNAL:
+	case RT5682_STO_NG2_CTRL_1:
+	case RT5682_STO_NG2_CTRL_2:
+	case RT5682_STO_NG2_CTRL_3:
+	case RT5682_STO_NG2_CTRL_4:
+	case RT5682_STO_NG2_CTRL_5:
+	case RT5682_STO_NG2_CTRL_6:
+	case RT5682_STO_NG2_CTRL_7:
+	case RT5682_STO_NG2_CTRL_8:
+	case RT5682_STO_NG2_CTRL_9:
+	case RT5682_STO_NG2_CTRL_10:
+	case RT5682_STO1_DAC_SIL_DET:
+	case RT5682_SIL_PSV_CTRL1:
+	case RT5682_SIL_PSV_CTRL2:
+	case RT5682_SIL_PSV_CTRL3:
+	case RT5682_SIL_PSV_CTRL4:
+	case RT5682_SIL_PSV_CTRL5:
+	case RT5682_HP_IMP_SENS_CTRL_01:
+	case RT5682_HP_IMP_SENS_CTRL_02:
+	case RT5682_HP_IMP_SENS_CTRL_03:
+	case RT5682_HP_IMP_SENS_CTRL_04:
+	case RT5682_HP_IMP_SENS_CTRL_05:
+	case RT5682_HP_IMP_SENS_CTRL_06:
+	case RT5682_HP_IMP_SENS_CTRL_07:
+	case RT5682_HP_IMP_SENS_CTRL_08:
+	case RT5682_HP_IMP_SENS_CTRL_09:
+	case RT5682_HP_IMP_SENS_CTRL_10:
+	case RT5682_HP_IMP_SENS_CTRL_11:
+	case RT5682_HP_IMP_SENS_CTRL_12:
+	case RT5682_HP_IMP_SENS_CTRL_13:
+	case RT5682_HP_IMP_SENS_CTRL_14:
+	case RT5682_HP_IMP_SENS_CTRL_15:
+	case RT5682_HP_IMP_SENS_CTRL_16:
+	case RT5682_HP_IMP_SENS_CTRL_17:
+	case RT5682_HP_IMP_SENS_CTRL_18:
+	case RT5682_HP_IMP_SENS_CTRL_19:
+	case RT5682_HP_IMP_SENS_CTRL_20:
+	case RT5682_HP_IMP_SENS_CTRL_21:
+	case RT5682_HP_IMP_SENS_CTRL_22:
+	case RT5682_HP_IMP_SENS_CTRL_23:
+	case RT5682_HP_IMP_SENS_CTRL_24:
+	case RT5682_HP_IMP_SENS_CTRL_25:
+	case RT5682_HP_IMP_SENS_CTRL_26:
+	case RT5682_HP_IMP_SENS_CTRL_27:
+	case RT5682_HP_IMP_SENS_CTRL_28:
+	case RT5682_HP_IMP_SENS_CTRL_29:
+	case RT5682_HP_IMP_SENS_CTRL_30:
+	case RT5682_HP_IMP_SENS_CTRL_31:
+	case RT5682_HP_IMP_SENS_CTRL_32:
+	case RT5682_HP_IMP_SENS_CTRL_33:
+	case RT5682_HP_IMP_SENS_CTRL_34:
+	case RT5682_HP_IMP_SENS_CTRL_35:
+	case RT5682_HP_IMP_SENS_CTRL_36:
+	case RT5682_HP_IMP_SENS_CTRL_37:
+	case RT5682_HP_IMP_SENS_CTRL_38:
+	case RT5682_HP_IMP_SENS_CTRL_39:
+	case RT5682_HP_IMP_SENS_CTRL_40:
+	case RT5682_HP_IMP_SENS_CTRL_41:
+	case RT5682_HP_IMP_SENS_CTRL_42:
+	case RT5682_HP_IMP_SENS_CTRL_43:
+	case RT5682_HP_LOGIC_CTRL_1:
+	case RT5682_HP_LOGIC_CTRL_2:
+	case RT5682_HP_LOGIC_CTRL_3:
+	case RT5682_HP_CALIB_CTRL_1:
+	case RT5682_HP_CALIB_CTRL_2:
+	case RT5682_HP_CALIB_CTRL_3:
+	case RT5682_HP_CALIB_CTRL_4:
+	case RT5682_HP_CALIB_CTRL_5:
+	case RT5682_HP_CALIB_CTRL_6:
+	case RT5682_HP_CALIB_CTRL_7:
+	case RT5682_HP_CALIB_CTRL_9:
+	case RT5682_HP_CALIB_CTRL_10:
+	case RT5682_HP_CALIB_CTRL_11:
+	case RT5682_HP_CALIB_STA_1:
+	case RT5682_HP_CALIB_STA_2:
+	case RT5682_HP_CALIB_STA_3:
+	case RT5682_HP_CALIB_STA_4:
+	case RT5682_HP_CALIB_STA_5:
+	case RT5682_HP_CALIB_STA_6:
+	case RT5682_HP_CALIB_STA_7:
+	case RT5682_HP_CALIB_STA_8:
+	case RT5682_HP_CALIB_STA_9:
+	case RT5682_HP_CALIB_STA_10:
+	case RT5682_HP_CALIB_STA_11:
+	case RT5682_SAR_IL_CMD_1:
+	case RT5682_SAR_IL_CMD_2:
+	case RT5682_SAR_IL_CMD_3:
+	case RT5682_SAR_IL_CMD_4:
+	case RT5682_SAR_IL_CMD_5:
+	case RT5682_SAR_IL_CMD_6:
+	case RT5682_SAR_IL_CMD_7:
+	case RT5682_SAR_IL_CMD_8:
+	case RT5682_SAR_IL_CMD_9:
+	case RT5682_SAR_IL_CMD_10:
+	case RT5682_SAR_IL_CMD_11:
+	case RT5682_SAR_IL_CMD_12:
+	case RT5682_SAR_IL_CMD_13:
+	case RT5682_EFUSE_CTRL_1:
+	case RT5682_EFUSE_CTRL_2:
+	case RT5682_EFUSE_CTRL_3:
+	case RT5682_EFUSE_CTRL_4:
+	case RT5682_EFUSE_CTRL_5:
+	case RT5682_EFUSE_CTRL_6:
+	case RT5682_EFUSE_CTRL_7:
+	case RT5682_EFUSE_CTRL_8:
+	case RT5682_EFUSE_CTRL_9:
+	case RT5682_EFUSE_CTRL_10:
+	case RT5682_EFUSE_CTRL_11:
+	case RT5682_JD_TOP_VC_VTRL:
+	case RT5682_DRC1_CTRL_0:
+	case RT5682_DRC1_CTRL_1:
+	case RT5682_DRC1_CTRL_2:
+	case RT5682_DRC1_CTRL_3:
+	case RT5682_DRC1_CTRL_4:
+	case RT5682_DRC1_CTRL_5:
+	case RT5682_DRC1_CTRL_6:
+	case RT5682_DRC1_HARD_LMT_CTRL_1:
+	case RT5682_DRC1_HARD_LMT_CTRL_2:
+	case RT5682_DRC1_PRIV_1:
+	case RT5682_DRC1_PRIV_2:
+	case RT5682_DRC1_PRIV_3:
+	case RT5682_DRC1_PRIV_4:
+	case RT5682_DRC1_PRIV_5:
+	case RT5682_DRC1_PRIV_6:
+	case RT5682_DRC1_PRIV_7:
+	case RT5682_DRC1_PRIV_8:
+	case RT5682_EQ_AUTO_RCV_CTRL1:
+	case RT5682_EQ_AUTO_RCV_CTRL2:
+	case RT5682_EQ_AUTO_RCV_CTRL3:
+	case RT5682_EQ_AUTO_RCV_CTRL4:
+	case RT5682_EQ_AUTO_RCV_CTRL5:
+	case RT5682_EQ_AUTO_RCV_CTRL6:
+	case RT5682_EQ_AUTO_RCV_CTRL7:
+	case RT5682_EQ_AUTO_RCV_CTRL8:
+	case RT5682_EQ_AUTO_RCV_CTRL9:
+	case RT5682_EQ_AUTO_RCV_CTRL10:
+	case RT5682_EQ_AUTO_RCV_CTRL11:
+	case RT5682_EQ_AUTO_RCV_CTRL12:
+	case RT5682_EQ_AUTO_RCV_CTRL13:
+	case RT5682_ADC_L_EQ_LPF1_A1:
+	case RT5682_R_EQ_LPF1_A1:
+	case RT5682_L_EQ_LPF1_H0:
+	case RT5682_R_EQ_LPF1_H0:
+	case RT5682_L_EQ_BPF1_A1:
+	case RT5682_R_EQ_BPF1_A1:
+	case RT5682_L_EQ_BPF1_A2:
+	case RT5682_R_EQ_BPF1_A2:
+	case RT5682_L_EQ_BPF1_H0:
+	case RT5682_R_EQ_BPF1_H0:
+	case RT5682_L_EQ_BPF2_A1:
+	case RT5682_R_EQ_BPF2_A1:
+	case RT5682_L_EQ_BPF2_A2:
+	case RT5682_R_EQ_BPF2_A2:
+	case RT5682_L_EQ_BPF2_H0:
+	case RT5682_R_EQ_BPF2_H0:
+	case RT5682_L_EQ_BPF3_A1:
+	case RT5682_R_EQ_BPF3_A1:
+	case RT5682_L_EQ_BPF3_A2:
+	case RT5682_R_EQ_BPF3_A2:
+	case RT5682_L_EQ_BPF3_H0:
+	case RT5682_R_EQ_BPF3_H0:
+	case RT5682_L_EQ_BPF4_A1:
+	case RT5682_R_EQ_BPF4_A1:
+	case RT5682_L_EQ_BPF4_A2:
+	case RT5682_R_EQ_BPF4_A2:
+	case RT5682_L_EQ_BPF4_H0:
+	case RT5682_R_EQ_BPF4_H0:
+	case RT5682_L_EQ_HPF1_A1:
+	case RT5682_R_EQ_HPF1_A1:
+	case RT5682_L_EQ_HPF1_H0:
+	case RT5682_R_EQ_HPF1_H0:
+	case RT5682_L_EQ_PRE_VOL:
+	case RT5682_R_EQ_PRE_VOL:
+	case RT5682_L_EQ_POST_VOL:
+	case RT5682_R_EQ_POST_VOL:
+	case RT5682_I2C_MODE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static const DECLARE_TLV_DB_SCALE(hp_vol_tlv, -2250, 150, 0);
+static const DECLARE_TLV_DB_SCALE(dac_vol_tlv, -65625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(adc_vol_tlv, -17625, 375, 0);
+static const DECLARE_TLV_DB_SCALE(adc_bst_tlv, 0, 1200, 0);
+
+/* {0, +20, +24, +30, +35, +40, +44, +50, +52} dB */
+static const DECLARE_TLV_DB_RANGE(bst_tlv,
+	0, 0, TLV_DB_SCALE_ITEM(0, 0, 0),
+	1, 1, TLV_DB_SCALE_ITEM(2000, 0, 0),
+	2, 2, TLV_DB_SCALE_ITEM(2400, 0, 0),
+	3, 5, TLV_DB_SCALE_ITEM(3000, 500, 0),
+	6, 6, TLV_DB_SCALE_ITEM(4400, 0, 0),
+	7, 7, TLV_DB_SCALE_ITEM(5000, 0, 0),
+	8, 8, TLV_DB_SCALE_ITEM(5200, 0, 0)
+);
+
+/* Interface data select */
+static const char * const rt5682_data_select[] = {
+	"L/R", "R/L", "L/L", "R/R"
+};
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if2_adc_enum,
+	RT5682_DIG_INF2_DATA, RT5682_IF2_ADC_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_01_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC1_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_23_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC2_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_45_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC3_SEL_SFT, rt5682_data_select);
+
+static SOC_ENUM_SINGLE_DECL(rt5682_if1_67_adc_enum,
+	RT5682_TDM_ADDA_CTRL_1, RT5682_IF1_ADC4_SEL_SFT, rt5682_data_select);
+
+static const struct snd_kcontrol_new rt5682_if2_adc_swap_mux =
+	SOC_DAPM_ENUM("IF2 ADC Swap Mux", rt5682_if2_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_01_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 01 ADC Swap Mux", rt5682_if1_01_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_23_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 23 ADC Swap Mux", rt5682_if1_23_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_45_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 45 ADC Swap Mux", rt5682_if1_45_adc_enum);
+
+static const struct snd_kcontrol_new rt5682_if1_67_adc_swap_mux =
+	SOC_DAPM_ENUM("IF1 67 ADC Swap Mux", rt5682_if1_67_adc_enum);
+
+static void rt5682_reset(struct regmap *regmap)
+{
+	regmap_write(regmap, RT5682_RESET, 0);
+	regmap_write(regmap, RT5682_I2C_MODE, 1);
+}
+/**
+ * rt5682_sel_asrc_clk_src - select ASRC clock source for a set of filters
+ * @component: SoC audio component device.
+ * @filter_mask: mask of filters.
+ * @clk_src: clock source
+ *
+ * The ASRC function is for asynchronous MCLK and LRCK. Also, since RT5682 can
+ * only support standard 32fs or 64fs i2s format, ASRC should be enabled to
+ * support special i2s clock format such as Intel's 100fs(100 * sampling rate).
+ * ASRC function will track i2s clock and generate a corresponding system clock
+ * for codec. This function provides an API to select the clock source for a
+ * set of filters specified by the mask. And the component driver will turn on
+ * ASRC for these filters if ASRC is selected as their clock source.
+ */
+int rt5682_sel_asrc_clk_src(struct snd_soc_component *component,
+		unsigned int filter_mask, unsigned int clk_src)
+{
+
+	switch (clk_src) {
+	case RT5682_CLK_SEL_SYS:
+	case RT5682_CLK_SEL_I2S1_ASRC:
+	case RT5682_CLK_SEL_I2S2_ASRC:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (filter_mask & RT5682_DA_STEREO1_FILTER) {
+		snd_soc_component_update_bits(component, RT5682_PLL_TRACK_2,
+			RT5682_FILTER_CLK_SEL_MASK,
+			clk_src << RT5682_FILTER_CLK_SEL_SFT);
+	}
+
+	if (filter_mask & RT5682_AD_STEREO1_FILTER) {
+		snd_soc_component_update_bits(component, RT5682_PLL_TRACK_3,
+			RT5682_FILTER_CLK_SEL_MASK,
+			clk_src << RT5682_FILTER_CLK_SEL_SFT);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rt5682_sel_asrc_clk_src);
+
+static int rt5682_button_detect(struct snd_soc_component *component)
+{
+	int btn_type, val;
+
+	val = snd_soc_component_read32(component, RT5682_4BTN_IL_CMD_1);
+	btn_type = val & 0xfff0;
+	snd_soc_component_write(component, RT5682_4BTN_IL_CMD_1, val);
+	pr_debug("%s btn_type=%x\n", __func__, btn_type);
+
+	return btn_type;
+}
+
+static void rt5682_enable_push_button_irq(struct snd_soc_component *component,
+		bool enable)
+{
+	if (enable) {
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
+			RT5682_SAR_BUTT_DET_MASK, RT5682_SAR_BUTT_DET_EN);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_13,
+			RT5682_SAR_SOUR_MASK, RT5682_SAR_SOUR_BTN);
+		snd_soc_component_write(component, RT5682_IL_CMD_1, 0x0040);
+		snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2,
+			RT5682_4BTN_IL_MASK | RT5682_4BTN_IL_RST_MASK,
+			RT5682_4BTN_IL_EN | RT5682_4BTN_IL_NOR);
+		snd_soc_component_update_bits(component, RT5682_IRQ_CTRL_3,
+			RT5682_IL_IRQ_MASK, RT5682_IL_IRQ_EN);
+	} else {
+		snd_soc_component_update_bits(component, RT5682_IRQ_CTRL_3,
+			RT5682_IL_IRQ_MASK, RT5682_IL_IRQ_DIS);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
+			RT5682_SAR_BUTT_DET_MASK, RT5682_SAR_BUTT_DET_DIS);
+		snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2,
+			RT5682_4BTN_IL_MASK, RT5682_4BTN_IL_DIS);
+		snd_soc_component_update_bits(component, RT5682_4BTN_IL_CMD_2,
+			RT5682_4BTN_IL_RST_MASK, RT5682_4BTN_IL_RST);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_13,
+			RT5682_SAR_SOUR_MASK, RT5682_SAR_SOUR_TYPE);
+	}
+}
+
+/**
+ * rt5682_headset_detect - Detect headset.
+ * @component: SoC audio component device.
+ * @jack_insert: Jack insert or not.
+ *
+ * Detect whether is headset or not when jack inserted.
+ *
+ * Returns detect status.
+ */
+static int rt5682_headset_detect(struct snd_soc_component *component,
+		int jack_insert)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	struct snd_soc_dapm_context *dapm =
+		snd_soc_component_get_dapm(component);
+	unsigned int val, count;
+
+	if (jack_insert) {
+		snd_soc_dapm_force_enable_pin(dapm, "CBJ Power");
+		snd_soc_dapm_sync(dapm);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_HIGH);
+
+		count = 0;
+		val = snd_soc_component_read32(component, RT5682_CBJ_CTRL_2)
+			& RT5682_JACK_TYPE_MASK;
+		while (val == 0 && count < 50) {
+			usleep_range(10000, 15000);
+			val = snd_soc_component_read32(component,
+				RT5682_CBJ_CTRL_2) & RT5682_JACK_TYPE_MASK;
+			count++;
+		}
+
+		switch (val) {
+		case 0x1:
+		case 0x2:
+			rt5682->jack_type = SND_JACK_HEADSET;
+			rt5682_enable_push_button_irq(component, true);
+			break;
+		default:
+			rt5682->jack_type = SND_JACK_HEADPHONE;
+		}
+
+	} else {
+		rt5682_enable_push_button_irq(component, false);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_1,
+			RT5682_TRIG_JD_MASK, RT5682_TRIG_JD_LOW);
+		snd_soc_dapm_disable_pin(dapm, "CBJ Power");
+		snd_soc_dapm_sync(dapm);
+
+		rt5682->jack_type = 0;
+	}
+
+	dev_dbg(component->dev, "jack_type = %d\n", rt5682->jack_type);
+	return rt5682->jack_type;
+}
+
+static irqreturn_t rt5682_irq(int irq, void *data)
+{
+	struct rt5682_priv *rt5682 = data;
+
+	mod_delayed_work(system_power_efficient_wq,
+			&rt5682->jack_detect_work, msecs_to_jiffies(250));
+
+	return IRQ_HANDLED;
+}
+
+static void rt5682_jd_check_handler(struct work_struct *work)
+{
+	struct rt5682_priv *rt5682 = container_of(work, struct rt5682_priv,
+		jd_check_work.work);
+
+	if (snd_soc_component_read32(rt5682->component, RT5682_AJD1_CTRL)
+		& RT5682_JDH_RS_MASK) {
+		/* jack out */
+		rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0);
+
+		snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type,
+				SND_JACK_HEADSET |
+				SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+				SND_JACK_BTN_2 | SND_JACK_BTN_3);
+	} else {
+		schedule_delayed_work(&rt5682->jd_check_work, 500);
+	}
+}
+
+static int rt5682_set_jack_detect(struct snd_soc_component *component,
+	struct snd_soc_jack *hs_jack, void *data)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	switch (rt5682->pdata.jd_src) {
+	case RT5682_JD1:
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_2,
+			RT5682_EXT_JD_SRC, RT5682_EXT_JD_SRC_MANUAL);
+		snd_soc_component_write(component, RT5682_CBJ_CTRL_1, 0xd042);
+		snd_soc_component_update_bits(component, RT5682_CBJ_CTRL_3,
+			RT5682_CBJ_IN_BUF_EN, RT5682_CBJ_IN_BUF_EN);
+		snd_soc_component_update_bits(component, RT5682_SAR_IL_CMD_1,
+			RT5682_SAR_POW_MASK, RT5682_SAR_POW_EN);
+		regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+			RT5682_GP1_PIN_MASK, RT5682_GP1_PIN_IRQ);
+		regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL,
+				RT5682_POW_IRQ | RT5682_POW_JDH |
+				RT5682_POW_ANA, RT5682_POW_IRQ |
+				RT5682_POW_JDH | RT5682_POW_ANA);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_2,
+			RT5682_PWR_JDH | RT5682_PWR_JDL,
+			RT5682_PWR_JDH | RT5682_PWR_JDL);
+		regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2,
+			RT5682_JD1_EN_MASK | RT5682_JD1_POL_MASK,
+			RT5682_JD1_EN | RT5682_JD1_POL_NOR);
+		mod_delayed_work(system_power_efficient_wq,
+			   &rt5682->jack_detect_work, msecs_to_jiffies(250));
+		break;
+
+	case RT5682_JD_NULL:
+		regmap_update_bits(rt5682->regmap, RT5682_IRQ_CTRL_2,
+			RT5682_JD1_EN_MASK, RT5682_JD1_DIS);
+		regmap_update_bits(rt5682->regmap, RT5682_RC_CLK_CTRL,
+				RT5682_POW_JDH | RT5682_POW_JDL, 0);
+		break;
+
+	default:
+		dev_warn(component->dev, "Wrong JD source\n");
+		break;
+	}
+
+	rt5682->hs_jack = hs_jack;
+
+	return 0;
+}
+
+static void rt5682_jack_detect_handler(struct work_struct *work)
+{
+	struct rt5682_priv *rt5682 =
+		container_of(work, struct rt5682_priv, jack_detect_work.work);
+	int val, btn_type;
+
+	while (!rt5682->component)
+		usleep_range(10000, 15000);
+
+	while (!rt5682->component->card->instantiated)
+		usleep_range(10000, 15000);
+
+	mutex_lock(&rt5682->calibrate_mutex);
+
+	val = snd_soc_component_read32(rt5682->component, RT5682_AJD1_CTRL)
+		& RT5682_JDH_RS_MASK;
+	if (!val) {
+		/* jack in */
+		if (rt5682->jack_type == 0) {
+			/* jack was out, report jack type */
+			rt5682->jack_type =
+				rt5682_headset_detect(rt5682->component, 1);
+		} else {
+			/* jack is already in, report button event */
+			rt5682->jack_type = SND_JACK_HEADSET;
+			btn_type = rt5682_button_detect(rt5682->component);
+			/**
+			 * rt5682 can report three kinds of button behavior,
+			 * one click, double click and hold. However,
+			 * currently we will report button pressed/released
+			 * event. So all the three button behaviors are
+			 * treated as button pressed.
+			 */
+			switch (btn_type) {
+			case 0x8000:
+			case 0x4000:
+			case 0x2000:
+				rt5682->jack_type |= SND_JACK_BTN_0;
+				break;
+			case 0x1000:
+			case 0x0800:
+			case 0x0400:
+				rt5682->jack_type |= SND_JACK_BTN_1;
+				break;
+			case 0x0200:
+			case 0x0100:
+			case 0x0080:
+				rt5682->jack_type |= SND_JACK_BTN_2;
+				break;
+			case 0x0040:
+			case 0x0020:
+			case 0x0010:
+				rt5682->jack_type |= SND_JACK_BTN_3;
+				break;
+			case 0x0000: /* unpressed */
+				break;
+			default:
+				btn_type = 0;
+				dev_err(rt5682->component->dev,
+					"Unexpected button code 0x%04x\n",
+					btn_type);
+				break;
+			}
+		}
+	} else {
+		/* jack out */
+		rt5682->jack_type = rt5682_headset_detect(rt5682->component, 0);
+	}
+
+	snd_soc_jack_report(rt5682->hs_jack, rt5682->jack_type,
+			SND_JACK_HEADSET |
+			    SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+			    SND_JACK_BTN_2 | SND_JACK_BTN_3);
+
+	if (rt5682->jack_type & (SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+		SND_JACK_BTN_2 | SND_JACK_BTN_3))
+		schedule_delayed_work(&rt5682->jd_check_work, 0);
+	else
+		cancel_delayed_work_sync(&rt5682->jd_check_work);
+
+	mutex_unlock(&rt5682->calibrate_mutex);
+}
+
+static const struct snd_kcontrol_new rt5682_snd_controls[] = {
+	/* Headphone Output Volume */
+	SOC_DOUBLE_R_TLV("Headphone Playback Volume", RT5682_HPL_GAIN,
+		RT5682_HPR_GAIN, RT5682_G_HP_SFT, 15, 1, hp_vol_tlv),
+
+	/* DAC Digital Volume */
+	SOC_DOUBLE_TLV("DAC1 Playback Volume", RT5682_DAC1_DIG_VOL,
+		RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 175, 0, dac_vol_tlv),
+
+	/* IN Boost Volume */
+	SOC_SINGLE_TLV("CBJ Boost Volume", RT5682_CBJ_BST_CTRL,
+		RT5682_BST_CBJ_SFT, 8, 0, bst_tlv),
+
+	/* ADC Digital Volume Control */
+	SOC_DOUBLE("STO1 ADC Capture Switch", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_L_MUTE_SFT, RT5682_R_MUTE_SFT, 1, 1),
+	SOC_DOUBLE_TLV("STO1 ADC Capture Volume", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_L_VOL_SFT, RT5682_R_VOL_SFT, 127, 0, adc_vol_tlv),
+
+	/* ADC Boost Volume Control */
+	SOC_DOUBLE_TLV("STO1 ADC Boost Gain Volume", RT5682_STO1_ADC_BOOST,
+		RT5682_STO1_ADC_L_BST_SFT, RT5682_STO1_ADC_R_BST_SFT,
+		3, 0, adc_bst_tlv),
+};
+
+
+static int rt5682_div_sel(struct rt5682_priv *rt5682,
+			  int target, const int div[], int size)
+{
+	int i;
+
+	if (rt5682->sysclk < target) {
+		pr_err("sysclk rate %d is too low\n",
+			rt5682->sysclk);
+		return 0;
+	}
+
+	for (i = 0; i < size - 1; i++) {
+		pr_info("div[%d]=%d\n", i, div[i]);
+		if (target * div[i] == rt5682->sysclk)
+			return i;
+		if (target * div[i + 1] > rt5682->sysclk) {
+			pr_err("can't find div for sysclk %d\n",
+				rt5682->sysclk);
+			return i;
+		}
+	}
+
+	if (target * div[i] < rt5682->sysclk)
+		pr_err("sysclk rate %d is too high\n",
+			rt5682->sysclk);
+
+	return size - 1;
+
+}
+
+/**
+ * set_dmic_clk - Set parameter of dmic.
+ *
+ * @w: DAPM widget.
+ * @kcontrol: The kcontrol of this widget.
+ * @event: Event id.
+ *
+ * Choose dmic clock between 1MHz and 3MHz.
+ * It is better for clock to approximate 3MHz.
+ */
+static int set_dmic_clk(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	int idx = -EINVAL;
+	static const int div[] = {2, 4, 6, 8, 12, 16, 24, 32, 48, 64, 96, 128};
+
+	idx = rt5682_div_sel(rt5682, 1500000, div, ARRAY_SIZE(div));
+
+	snd_soc_component_update_bits(component, RT5682_DMIC_CTRL_1,
+		RT5682_DMIC_CLK_MASK, idx << RT5682_DMIC_CLK_SFT);
+
+	return 0;
+}
+
+static int set_filter_clk(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	int ref, val, reg, sft, mask, idx = -EINVAL;
+	static const int div_f[] = {1, 2, 3, 4, 6, 8, 12, 16, 24, 32, 48};
+	static const int div_o[] = {1, 2, 4, 6, 8, 12, 16, 24, 32, 48};
+
+	val = snd_soc_component_read32(component, RT5682_GPIO_CTRL_1) &
+		RT5682_GP4_PIN_MASK;
+	if (w->shift == RT5682_PWR_ADC_S1F_BIT &&
+		val == RT5682_GP4_PIN_ADCDAT2)
+		ref = 256 * rt5682->lrck[RT5682_AIF2];
+	else
+		ref = 256 * rt5682->lrck[RT5682_AIF1];
+
+	idx = rt5682_div_sel(rt5682, ref, div_f, ARRAY_SIZE(div_f));
+
+	if (w->shift == RT5682_PWR_ADC_S1F_BIT) {
+		reg = RT5682_PLL_TRACK_3;
+		sft = RT5682_ADC_OSR_SFT;
+		mask = RT5682_ADC_OSR_MASK;
+	} else {
+		reg = RT5682_PLL_TRACK_2;
+		sft = RT5682_DAC_OSR_SFT;
+		mask = RT5682_DAC_OSR_MASK;
+	}
+
+	snd_soc_component_update_bits(component, reg,
+		RT5682_FILTER_CLK_DIV_MASK, idx << RT5682_FILTER_CLK_DIV_SFT);
+
+	/* select over sample rate */
+	for (idx = 0; idx < ARRAY_SIZE(div_o); idx++) {
+		if (rt5682->sysclk <= 12288000 * div_o[idx])
+			break;
+	}
+
+	snd_soc_component_update_bits(component, RT5682_ADDA_CLK_1,
+		mask, idx << sft);
+
+	return 0;
+}
+
+static int is_sys_clk_from_pll1(struct snd_soc_dapm_widget *w,
+			 struct snd_soc_dapm_widget *sink)
+{
+	unsigned int val;
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	val = snd_soc_component_read32(component, RT5682_GLB_CLK);
+	val &= RT5682_SCLK_SRC_MASK;
+	if (val == RT5682_SCLK_SRC_PLL1)
+		return 1;
+	else
+		return 0;
+}
+
+static int is_using_asrc(struct snd_soc_dapm_widget *w,
+			 struct snd_soc_dapm_widget *sink)
+{
+	unsigned int reg, shift, val;
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (w->shift) {
+	case RT5682_ADC_STO1_ASRC_SFT:
+		reg = RT5682_PLL_TRACK_3;
+		shift = RT5682_FILTER_CLK_SEL_SFT;
+		break;
+	case RT5682_DAC_STO1_ASRC_SFT:
+		reg = RT5682_PLL_TRACK_2;
+		shift = RT5682_FILTER_CLK_SEL_SFT;
+		break;
+	default:
+		return 0;
+	}
+
+	val = (snd_soc_component_read32(component, reg) >> shift) & 0xf;
+	switch (val) {
+	case RT5682_CLK_SEL_I2S1_ASRC:
+	case RT5682_CLK_SEL_I2S2_ASRC:
+		return 1;
+	default:
+		return 0;
+	}
+
+}
+
+/* Digital Mixer */
+static const struct snd_kcontrol_new rt5682_sto1_adc_l_mix[] = {
+	SOC_DAPM_SINGLE("ADC1 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_L1_SFT, 1, 1),
+	SOC_DAPM_SINGLE("ADC2 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_L2_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_sto1_adc_r_mix[] = {
+	SOC_DAPM_SINGLE("ADC1 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_R1_SFT, 1, 1),
+	SOC_DAPM_SINGLE("ADC2 Switch", RT5682_STO1_ADC_MIXER,
+			RT5682_M_STO1_ADC_R2_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_dac_l_mix[] = {
+	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_ADCMIX_L_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC1 Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_DAC1_L_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_dac_r_mix[] = {
+	SOC_DAPM_SINGLE("Stereo ADC Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_ADCMIX_R_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC1 Switch", RT5682_AD_DA_MIXER,
+			RT5682_M_DAC1_R_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_sto1_dac_l_mix[] = {
+	SOC_DAPM_SINGLE("DAC L1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_L1_STO_L_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC R1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_R1_STO_L_SFT, 1, 1),
+};
+
+static const struct snd_kcontrol_new rt5682_sto1_dac_r_mix[] = {
+	SOC_DAPM_SINGLE("DAC L1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_L1_STO_R_SFT, 1, 1),
+	SOC_DAPM_SINGLE("DAC R1 Switch", RT5682_STO1_DAC_MIXER,
+			RT5682_M_DAC_R1_STO_R_SFT, 1, 1),
+};
+
+/* Analog Input Mixer */
+static const struct snd_kcontrol_new rt5682_rec1_l_mix[] = {
+	SOC_DAPM_SINGLE("CBJ Switch", RT5682_REC_MIXER,
+			RT5682_M_CBJ_RM1_L_SFT, 1, 1),
+};
+
+/* STO1 ADC1 Source */
+/* MX-26 [13] [5] */
+static const char * const rt5682_sto1_adc1_src[] = {
+	"DAC MIX", "ADC"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc1l_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC1L_SRC_SFT, rt5682_sto1_adc1_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc1l_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5682_sto1_adc1l_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc1r_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC1R_SRC_SFT, rt5682_sto1_adc1_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc1r_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC1L Source", rt5682_sto1_adc1r_enum);
+
+/* STO1 ADC Source */
+/* MX-26 [11:10] [3:2] */
+static const char * const rt5682_sto1_adc_src[] = {
+	"ADC1 L", "ADC1 R"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adcl_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADCL_SRC_SFT, rt5682_sto1_adc_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adcl_mux =
+	SOC_DAPM_ENUM("Stereo1 ADCL Source", rt5682_sto1_adcl_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adcr_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADCR_SRC_SFT, rt5682_sto1_adc_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adcr_mux =
+	SOC_DAPM_ENUM("Stereo1 ADCR Source", rt5682_sto1_adcr_enum);
+
+/* STO1 ADC2 Source */
+/* MX-26 [12] [4] */
+static const char * const rt5682_sto1_adc2_src[] = {
+	"DAC MIX", "DMIC"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc2l_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC2L_SRC_SFT, rt5682_sto1_adc2_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc2l_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC2L Source", rt5682_sto1_adc2l_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_sto1_adc2r_enum, RT5682_STO1_ADC_MIXER,
+	RT5682_STO1_ADC2R_SRC_SFT, rt5682_sto1_adc2_src);
+
+static const struct snd_kcontrol_new rt5682_sto1_adc2r_mux =
+	SOC_DAPM_ENUM("Stereo1 ADC2R Source", rt5682_sto1_adc2r_enum);
+
+/* MX-79 [6:4] I2S1 ADC data location */
+static const unsigned int rt5682_if1_adc_slot_values[] = {
+	0,
+	2,
+	4,
+	6,
+};
+
+static const char * const rt5682_if1_adc_slot_src[] = {
+	"Slot 0", "Slot 2", "Slot 4", "Slot 6"
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(rt5682_if1_adc_slot_enum,
+	RT5682_TDM_CTRL, RT5682_TDM_ADC_LCA_SFT, RT5682_TDM_ADC_LCA_MASK,
+	rt5682_if1_adc_slot_src, rt5682_if1_adc_slot_values);
+
+static const struct snd_kcontrol_new rt5682_if1_adc_slot_mux =
+	SOC_DAPM_ENUM("IF1 ADC Slot location", rt5682_if1_adc_slot_enum);
+
+/* Analog DAC L1 Source, Analog DAC R1 Source*/
+/* MX-2B [4], MX-2B [0]*/
+static const char * const rt5682_alg_dac1_src[] = {
+	"Stereo1 DAC Mixer", "DAC1"
+};
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_alg_dac_l1_enum, RT5682_A_DAC1_MUX,
+	RT5682_A_DACL1_SFT, rt5682_alg_dac1_src);
+
+static const struct snd_kcontrol_new rt5682_alg_dac_l1_mux =
+	SOC_DAPM_ENUM("Analog DAC L1 Source", rt5682_alg_dac_l1_enum);
+
+static SOC_ENUM_SINGLE_DECL(
+	rt5682_alg_dac_r1_enum, RT5682_A_DAC1_MUX,
+	RT5682_A_DACR1_SFT, rt5682_alg_dac1_src);
+
+static const struct snd_kcontrol_new rt5682_alg_dac_r1_mux =
+	SOC_DAPM_ENUM("Analog DAC R1 Source", rt5682_alg_dac_r1_enum);
+
+/* Out Switch */
+static const struct snd_kcontrol_new hpol_switch =
+	SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5682_HP_CTRL_1,
+					RT5682_L_MUTE_SFT, 1, 1);
+static const struct snd_kcontrol_new hpor_switch =
+	SOC_DAPM_SINGLE_AUTODISABLE("Switch", RT5682_HP_CTRL_1,
+					RT5682_R_MUTE_SFT, 1, 1);
+
+static int rt5682_hp_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		snd_soc_component_write(component,
+			RT5682_HP_LOGIC_CTRL_2, 0x0012);
+		snd_soc_component_write(component,
+			RT5682_HP_CTRL_2, 0x6000);
+		snd_soc_component_update_bits(component, RT5682_STO_NG2_CTRL_1,
+			RT5682_NG2_EN_MASK, RT5682_NG2_EN);
+		snd_soc_component_update_bits(component,
+			RT5682_DEPOP_1, 0x60, 0x60);
+		break;
+
+	case SND_SOC_DAPM_POST_PMD:
+		snd_soc_component_update_bits(component,
+			RT5682_DEPOP_1, 0x60, 0x0);
+		snd_soc_component_write(component,
+			RT5682_HP_CTRL_2, 0x0000);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+
+}
+
+static int set_dmic_power(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		/*Add delay to avoid pop noise*/
+		msleep(150);
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static int rt5655_set_verf(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component =
+		snd_soc_dapm_to_component(w->dapm);
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		switch (w->shift) {
+		case RT5682_PWR_VREF1_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV1, 0);
+			break;
+
+		case RT5682_PWR_VREF2_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV2, 0);
+			break;
+
+		default:
+			break;
+		}
+		break;
+
+	case SND_SOC_DAPM_POST_PMU:
+		usleep_range(15000, 20000);
+		switch (w->shift) {
+		case RT5682_PWR_VREF1_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV1,
+				RT5682_PWR_FV1);
+			break;
+
+		case RT5682_PWR_VREF2_BIT:
+			snd_soc_component_update_bits(component,
+				RT5682_PWR_ANLG_1, RT5682_PWR_FV2,
+				RT5682_PWR_FV2);
+			break;
+
+		default:
+			break;
+		}
+		break;
+
+	default:
+		return 0;
+	}
+
+	return 0;
+}
+
+static const unsigned int rt5682_adcdat_pin_values[] = {
+	1,
+	3,
+};
+
+static const char * const rt5682_adcdat_pin_select[] = {
+	"ADCDAT1",
+	"ADCDAT2",
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(rt5682_adcdat_pin_enum,
+	RT5682_GPIO_CTRL_1, RT5682_GP4_PIN_SFT, RT5682_GP4_PIN_MASK,
+	rt5682_adcdat_pin_select, rt5682_adcdat_pin_values);
+
+static const struct snd_kcontrol_new rt5682_adcdat_pin_ctrl =
+	SOC_DAPM_ENUM("ADCDAT", rt5682_adcdat_pin_enum);
+
+static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = {
+	SND_SOC_DAPM_SUPPLY("LDO2", RT5682_PWR_ANLG_3, RT5682_PWR_LDO2_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL1", RT5682_PWR_ANLG_3, RT5682_PWR_PLL_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL2B", RT5682_PWR_ANLG_3, RT5682_PWR_PLL2B_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("PLL2F", RT5682_PWR_ANLG_3, RT5682_PWR_PLL2F_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("Vref1", RT5682_PWR_ANLG_1, RT5682_PWR_VREF1_BIT, 0,
+		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+	SND_SOC_DAPM_SUPPLY("Vref2", RT5682_PWR_ANLG_1, RT5682_PWR_VREF2_BIT, 0,
+		rt5655_set_verf, SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU),
+
+	/* ASRC */
+	SND_SOC_DAPM_SUPPLY_S("DAC STO1 ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_DAC_STO1_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("ADC STO1 ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_ADC_STO1_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("AD ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_AD_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("DA ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_DA_ASRC_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("DMIC ASRC", 1, RT5682_PLL_TRACK_1,
+		RT5682_DMIC_ASRC_SFT, 0, NULL, 0),
+
+	/* Input Side */
+	SND_SOC_DAPM_SUPPLY("MICBIAS1", RT5682_PWR_ANLG_2, RT5682_PWR_MB1_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("MICBIAS2", RT5682_PWR_ANLG_2, RT5682_PWR_MB2_BIT,
+		0, NULL, 0),
+
+	/* Input Lines */
+	SND_SOC_DAPM_INPUT("DMIC L1"),
+	SND_SOC_DAPM_INPUT("DMIC R1"),
+
+	SND_SOC_DAPM_INPUT("IN1P"),
+
+	SND_SOC_DAPM_SUPPLY("DMIC CLK", SND_SOC_NOPM, 0, 0,
+		set_dmic_clk, SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_SUPPLY("DMIC1 Power", RT5682_DMIC_CTRL_1,
+		RT5682_DMIC_1_EN_SFT, 0, set_dmic_power, SND_SOC_DAPM_POST_PMU),
+
+	/* Boost */
+	SND_SOC_DAPM_PGA("BST1 CBJ", SND_SOC_NOPM,
+		0, 0, NULL, 0),
+
+	SND_SOC_DAPM_SUPPLY("CBJ Power", RT5682_PWR_ANLG_3,
+		RT5682_PWR_CBJ_BIT, 0, NULL, 0),
+
+	/* REC Mixer */
+	SND_SOC_DAPM_MIXER("RECMIX1L", SND_SOC_NOPM, 0, 0, rt5682_rec1_l_mix,
+		ARRAY_SIZE(rt5682_rec1_l_mix)),
+	SND_SOC_DAPM_SUPPLY("RECMIX1L Power", RT5682_PWR_ANLG_2,
+		RT5682_PWR_RM1_L_BIT, 0, NULL, 0),
+
+	/* ADCs */
+	SND_SOC_DAPM_ADC("ADC1 L", NULL, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_ADC("ADC1 R", NULL, SND_SOC_NOPM, 0, 0),
+
+	SND_SOC_DAPM_SUPPLY("ADC1 L Power", RT5682_PWR_DIG_1,
+		RT5682_PWR_ADC_L1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC1 R Power", RT5682_PWR_DIG_1,
+		RT5682_PWR_ADC_R1_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("ADC1 clock", RT5682_CHOP_ADC,
+		RT5682_CKGEN_ADC1_SFT, 0, NULL, 0),
+
+	/* ADC Mux */
+	SND_SOC_DAPM_MUX("Stereo1 ADC L1 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc1l_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R1 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc1r_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC L2 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc2l_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R2 Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adc2r_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC L Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adcl_mux),
+	SND_SOC_DAPM_MUX("Stereo1 ADC R Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_sto1_adcr_mux),
+	SND_SOC_DAPM_MUX("IF1_ADC Mux", SND_SOC_NOPM, 0, 0,
+		&rt5682_if1_adc_slot_mux),
+
+	/* ADC Mixer */
+	SND_SOC_DAPM_SUPPLY("ADC Stereo1 Filter", RT5682_PWR_DIG_2,
+		RT5682_PWR_ADC_S1F_BIT, 0, set_filter_clk,
+		SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_MIXER("Stereo1 ADC MIXL", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_L_MUTE_SFT, 1, rt5682_sto1_adc_l_mix,
+		ARRAY_SIZE(rt5682_sto1_adc_l_mix)),
+	SND_SOC_DAPM_MIXER("Stereo1 ADC MIXR", RT5682_STO1_ADC_DIG_VOL,
+		RT5682_R_MUTE_SFT, 1, rt5682_sto1_adc_r_mix,
+		ARRAY_SIZE(rt5682_sto1_adc_r_mix)),
+
+	/* ADC PGA */
+	SND_SOC_DAPM_PGA("Stereo1 ADC MIX", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	/* Digital Interface */
+	SND_SOC_DAPM_SUPPLY("I2S1", RT5682_PWR_DIG_1, RT5682_PWR_I2S1_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("I2S2", RT5682_PWR_DIG_1, RT5682_PWR_I2S2_BIT,
+		0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1 L", SND_SOC_NOPM, 0, 0, NULL, 0),
+	SND_SOC_DAPM_PGA("IF1 DAC1 R", SND_SOC_NOPM, 0, 0, NULL, 0),
+
+	/* Digital Interface Select */
+	SND_SOC_DAPM_MUX("IF1 01 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_01_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 23 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_23_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 45 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_45_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF1 67 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if1_67_adc_swap_mux),
+	SND_SOC_DAPM_MUX("IF2 ADC Swap Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_if2_adc_swap_mux),
+
+	SND_SOC_DAPM_MUX("ADCDAT Mux", SND_SOC_NOPM, 0, 0,
+			&rt5682_adcdat_pin_ctrl),
+
+	/* Audio Interface */
+	SND_SOC_DAPM_AIF_OUT("AIF1TX", "AIF1 Capture", 0,
+		RT5682_I2S1_SDP, RT5682_SEL_ADCDAT_SFT, 1),
+	SND_SOC_DAPM_AIF_OUT("AIF2TX", "AIF2 Capture", 0,
+		RT5682_I2S2_SDP, RT5682_I2S2_PIN_CFG_SFT, 1),
+	SND_SOC_DAPM_AIF_IN("AIF1RX", "AIF1 Playback", 0, SND_SOC_NOPM, 0, 0),
+
+	/* Output Side */
+	/* DAC mixer before sound effect  */
+	SND_SOC_DAPM_MIXER("DAC1 MIXL", SND_SOC_NOPM, 0, 0,
+		rt5682_dac_l_mix, ARRAY_SIZE(rt5682_dac_l_mix)),
+	SND_SOC_DAPM_MIXER("DAC1 MIXR", SND_SOC_NOPM, 0, 0,
+		rt5682_dac_r_mix, ARRAY_SIZE(rt5682_dac_r_mix)),
+
+	/* DAC channel Mux */
+	SND_SOC_DAPM_MUX("DAC L1 Source", SND_SOC_NOPM, 0, 0,
+		&rt5682_alg_dac_l1_mux),
+	SND_SOC_DAPM_MUX("DAC R1 Source", SND_SOC_NOPM, 0, 0,
+		&rt5682_alg_dac_r1_mux),
+
+	/* DAC Mixer */
+	SND_SOC_DAPM_SUPPLY("DAC Stereo1 Filter", RT5682_PWR_DIG_2,
+		RT5682_PWR_DAC_S1F_BIT, 0, set_filter_clk,
+		SND_SOC_DAPM_PRE_PMU),
+	SND_SOC_DAPM_MIXER("Stereo1 DAC MIXL", SND_SOC_NOPM, 0, 0,
+		rt5682_sto1_dac_l_mix, ARRAY_SIZE(rt5682_sto1_dac_l_mix)),
+	SND_SOC_DAPM_MIXER("Stereo1 DAC MIXR", SND_SOC_NOPM, 0, 0,
+		rt5682_sto1_dac_r_mix, ARRAY_SIZE(rt5682_sto1_dac_r_mix)),
+
+	/* DACs */
+	SND_SOC_DAPM_DAC("DAC L1", NULL, RT5682_PWR_DIG_1,
+		RT5682_PWR_DAC_L1_BIT, 0),
+	SND_SOC_DAPM_DAC("DAC R1", NULL, RT5682_PWR_DIG_1,
+		RT5682_PWR_DAC_R1_BIT, 0),
+	SND_SOC_DAPM_SUPPLY_S("DAC 1 Clock", 3, RT5682_CHOP_DAC,
+		RT5682_CKGEN_DAC1_SFT, 0, NULL, 0),
+
+	/* HPO */
+	SND_SOC_DAPM_PGA_S("HP Amp", 1, SND_SOC_NOPM, 0, 0, rt5682_hp_event,
+		SND_SOC_DAPM_POST_PMD | SND_SOC_DAPM_PRE_PMU),
+
+	SND_SOC_DAPM_SUPPLY("HP Amp L", RT5682_PWR_ANLG_1,
+		RT5682_PWR_HA_L_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("HP Amp R", RT5682_PWR_ANLG_1,
+		RT5682_PWR_HA_R_BIT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("Charge Pump", 1, RT5682_DEPOP_1,
+		RT5682_PUMP_EN_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY_S("Capless", 2, RT5682_DEPOP_1,
+		RT5682_CAPLESS_EN_SFT, 0, NULL, 0),
+
+	SND_SOC_DAPM_SWITCH("HPOL Playback", SND_SOC_NOPM, 0, 0,
+		&hpol_switch),
+	SND_SOC_DAPM_SWITCH("HPOR Playback", SND_SOC_NOPM, 0, 0,
+		&hpor_switch),
+
+	/* CLK DET */
+	SND_SOC_DAPM_SUPPLY("CLKDET SYS", RT5682_CLK_DET,
+		RT5682_SYS_CLK_DET_SFT,	0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET PLL1", RT5682_CLK_DET,
+		RT5682_PLL1_CLK_DET_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET PLL2", RT5682_CLK_DET,
+		RT5682_PLL2_CLK_DET_SFT, 0, NULL, 0),
+	SND_SOC_DAPM_SUPPLY("CLKDET", RT5682_CLK_DET,
+		RT5682_POW_CLK_DET_SFT, 0, NULL, 0),
+
+	/* Output Lines */
+	SND_SOC_DAPM_OUTPUT("HPOL"),
+	SND_SOC_DAPM_OUTPUT("HPOR"),
+
+};
+
+static const struct snd_soc_dapm_route rt5682_dapm_routes[] = {
+	/*PLL*/
+	{"ADC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1},
+	{"DAC Stereo1 Filter", NULL, "PLL1", is_sys_clk_from_pll1},
+
+	/*ASRC*/
+	{"ADC Stereo1 Filter", NULL, "ADC STO1 ASRC", is_using_asrc},
+	{"DAC Stereo1 Filter", NULL, "DAC STO1 ASRC", is_using_asrc},
+	{"ADC STO1 ASRC", NULL, "AD ASRC"},
+	{"ADC STO1 ASRC", NULL, "CLKDET"},
+	{"DAC STO1 ASRC", NULL, "DA ASRC"},
+	{"DAC STO1 ASRC", NULL, "CLKDET"},
+
+	/*Vref*/
+	{"MICBIAS1", NULL, "Vref1"},
+	{"MICBIAS1", NULL, "Vref2"},
+	{"MICBIAS2", NULL, "Vref1"},
+	{"MICBIAS2", NULL, "Vref2"},
+
+	{"CLKDET SYS", NULL, "CLKDET"},
+
+	{"IN1P", NULL, "LDO2"},
+
+	{"BST1 CBJ", NULL, "IN1P"},
+	{"BST1 CBJ", NULL, "CBJ Power"},
+	{"CBJ Power", NULL, "Vref2"},
+
+	{"RECMIX1L", "CBJ Switch", "BST1 CBJ"},
+	{"RECMIX1L", NULL, "RECMIX1L Power"},
+
+	{"ADC1 L", NULL, "RECMIX1L"},
+	{"ADC1 L", NULL, "ADC1 L Power"},
+	{"ADC1 L", NULL, "ADC1 clock"},
+
+	{"DMIC L1", NULL, "DMIC CLK"},
+	{"DMIC L1", NULL, "DMIC1 Power"},
+	{"DMIC R1", NULL, "DMIC CLK"},
+	{"DMIC R1", NULL, "DMIC1 Power"},
+	{"DMIC CLK", NULL, "DMIC ASRC"},
+
+	{"Stereo1 ADC L Mux", "ADC1 L", "ADC1 L"},
+	{"Stereo1 ADC L Mux", "ADC1 R", "ADC1 R"},
+	{"Stereo1 ADC R Mux", "ADC1 L", "ADC1 L"},
+	{"Stereo1 ADC R Mux", "ADC1 R", "ADC1 R"},
+
+	{"Stereo1 ADC L1 Mux", "ADC", "Stereo1 ADC L Mux"},
+	{"Stereo1 ADC L1 Mux", "DAC MIX", "Stereo1 DAC MIXL"},
+	{"Stereo1 ADC L2 Mux", "DMIC", "DMIC L1"},
+	{"Stereo1 ADC L2 Mux", "DAC MIX", "Stereo1 DAC MIXL"},
+
+	{"Stereo1 ADC R1 Mux", "ADC", "Stereo1 ADC R Mux"},
+	{"Stereo1 ADC R1 Mux", "DAC MIX", "Stereo1 DAC MIXR"},
+	{"Stereo1 ADC R2 Mux", "DMIC", "DMIC R1"},
+	{"Stereo1 ADC R2 Mux", "DAC MIX", "Stereo1 DAC MIXR"},
+
+	{"Stereo1 ADC MIXL", "ADC1 Switch", "Stereo1 ADC L1 Mux"},
+	{"Stereo1 ADC MIXL", "ADC2 Switch", "Stereo1 ADC L2 Mux"},
+	{"Stereo1 ADC MIXL", NULL, "ADC Stereo1 Filter"},
+
+	{"Stereo1 ADC MIXR", "ADC1 Switch", "Stereo1 ADC R1 Mux"},
+	{"Stereo1 ADC MIXR", "ADC2 Switch", "Stereo1 ADC R2 Mux"},
+	{"Stereo1 ADC MIXR", NULL, "ADC Stereo1 Filter"},
+
+	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXL"},
+	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXR"},
+
+	{"IF1 01 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 01 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 23 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 45 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF1 67 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+
+	{"IF1_ADC Mux", "Slot 0", "IF1 01 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 2", "IF1 23 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 4", "IF1 45 ADC Swap Mux"},
+	{"IF1_ADC Mux", "Slot 6", "IF1 67 ADC Swap Mux"},
+	{"IF1_ADC Mux", NULL, "I2S1"},
+	{"ADCDAT Mux", "ADCDAT1", "IF1_ADC Mux"},
+	{"AIF1TX", NULL, "ADCDAT Mux"},
+	{"IF2 ADC Swap Mux", "L/R", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "R/L", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "L/L", "Stereo1 ADC MIX"},
+	{"IF2 ADC Swap Mux", "R/R", "Stereo1 ADC MIX"},
+	{"ADCDAT Mux", "ADCDAT2", "IF2 ADC Swap Mux"},
+	{"AIF2TX", NULL, "ADCDAT Mux"},
+
+	{"IF1 DAC1 L", NULL, "AIF1RX"},
+	{"IF1 DAC1 L", NULL, "I2S1"},
+	{"IF1 DAC1 L", NULL, "DAC Stereo1 Filter"},
+	{"IF1 DAC1 R", NULL, "AIF1RX"},
+	{"IF1 DAC1 R", NULL, "I2S1"},
+	{"IF1 DAC1 R", NULL, "DAC Stereo1 Filter"},
+
+	{"DAC1 MIXL", "Stereo ADC Switch", "Stereo1 ADC MIXL"},
+	{"DAC1 MIXL", "DAC1 Switch", "IF1 DAC1 L"},
+	{"DAC1 MIXR", "Stereo ADC Switch", "Stereo1 ADC MIXR"},
+	{"DAC1 MIXR", "DAC1 Switch", "IF1 DAC1 R"},
+
+	{"Stereo1 DAC MIXL", "DAC L1 Switch", "DAC1 MIXL"},
+	{"Stereo1 DAC MIXL", "DAC R1 Switch", "DAC1 MIXR"},
+
+	{"Stereo1 DAC MIXR", "DAC R1 Switch", "DAC1 MIXR"},
+	{"Stereo1 DAC MIXR", "DAC L1 Switch", "DAC1 MIXL"},
+
+	{"DAC L1 Source", "DAC1", "DAC1 MIXL"},
+	{"DAC L1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXL"},
+	{"DAC R1 Source", "DAC1", "DAC1 MIXR"},
+	{"DAC R1 Source", "Stereo1 DAC Mixer", "Stereo1 DAC MIXR"},
+
+	{"DAC L1", NULL, "DAC L1 Source"},
+	{"DAC R1", NULL, "DAC R1 Source"},
+
+	{"DAC L1", NULL, "DAC 1 Clock"},
+	{"DAC R1", NULL, "DAC 1 Clock"},
+
+	{"HP Amp", NULL, "DAC L1"},
+	{"HP Amp", NULL, "DAC R1"},
+	{"HP Amp", NULL, "HP Amp L"},
+	{"HP Amp", NULL, "HP Amp R"},
+	{"HP Amp", NULL, "Capless"},
+	{"HP Amp", NULL, "Charge Pump"},
+	{"HP Amp", NULL, "CLKDET SYS"},
+	{"HP Amp", NULL, "CBJ Power"},
+	{"HP Amp", NULL, "Vref2"},
+	{"HPOL Playback", "Switch", "HP Amp"},
+	{"HPOR Playback", "Switch", "HP Amp"},
+	{"HPOL", NULL, "HPOL Playback"},
+	{"HPOR", NULL, "HPOR Playback"},
+};
+
+static int rt5682_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
+			unsigned int rx_mask, int slots, int slot_width)
+{
+	struct snd_soc_component *component = dai->component;
+	unsigned int cl, val = 0;
+
+	if (tx_mask || rx_mask)
+		snd_soc_component_update_bits(component, RT5682_TDM_ADDA_CTRL_2,
+			RT5682_TDM_EN, RT5682_TDM_EN);
+	else
+		snd_soc_component_update_bits(component, RT5682_TDM_ADDA_CTRL_2,
+			RT5682_TDM_EN, 0);
+
+	switch (slots) {
+	case 4:
+		val |= RT5682_TDM_TX_CH_4;
+		val |= RT5682_TDM_RX_CH_4;
+		break;
+	case 6:
+		val |= RT5682_TDM_TX_CH_6;
+		val |= RT5682_TDM_RX_CH_6;
+		break;
+	case 8:
+		val |= RT5682_TDM_TX_CH_8;
+		val |= RT5682_TDM_RX_CH_8;
+		break;
+	case 2:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(component, RT5682_TDM_CTRL,
+		RT5682_TDM_TX_CH_MASK | RT5682_TDM_RX_CH_MASK, val);
+
+	switch (slot_width) {
+	case 8:
+		if (tx_mask || rx_mask)
+			return -EINVAL;
+		cl = RT5682_I2S1_TX_CHL_8 | RT5682_I2S1_RX_CHL_8;
+		break;
+	case 16:
+		val = RT5682_TDM_CL_16;
+		cl = RT5682_I2S1_TX_CHL_16 | RT5682_I2S1_RX_CHL_16;
+		break;
+	case 20:
+		val = RT5682_TDM_CL_20;
+		cl = RT5682_I2S1_TX_CHL_20 | RT5682_I2S1_RX_CHL_20;
+		break;
+	case 24:
+		val = RT5682_TDM_CL_24;
+		cl = RT5682_I2S1_TX_CHL_24 | RT5682_I2S1_RX_CHL_24;
+		break;
+	case 32:
+		val = RT5682_TDM_CL_32;
+		cl = RT5682_I2S1_TX_CHL_32 | RT5682_I2S1_RX_CHL_32;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	snd_soc_component_update_bits(component, RT5682_TDM_TCON_CTRL,
+		RT5682_TDM_CL_MASK, val);
+	snd_soc_component_update_bits(component, RT5682_I2S1_SDP,
+		RT5682_I2S1_TX_CHL_MASK | RT5682_I2S1_RX_CHL_MASK, cl);
+
+	return 0;
+}
+
+
+static int rt5682_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params, struct snd_soc_dai *dai)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	unsigned int len_1 = 0, len_2 = 0;
+	int pre_div, frame_size;
+
+	rt5682->lrck[dai->id] = params_rate(params);
+	pre_div = rl6231_get_clk_info(rt5682->sysclk, rt5682->lrck[dai->id]);
+
+	frame_size = snd_soc_params_to_frame_size(params);
+	if (frame_size < 0) {
+		dev_err(component->dev, "Unsupported frame size: %d\n",
+			frame_size);
+		return -EINVAL;
+	}
+
+	dev_dbg(dai->dev, "lrck is %dHz and pre_div is %d for iis %d\n",
+				rt5682->lrck[dai->id], pre_div, dai->id);
+
+	switch (params_width(params)) {
+	case 16:
+		break;
+	case 20:
+		len_1 |= RT5682_I2S1_DL_20;
+		len_2 |= RT5682_I2S2_DL_20;
+		break;
+	case 24:
+		len_1 |= RT5682_I2S1_DL_24;
+		len_2 |= RT5682_I2S2_DL_24;
+		break;
+	case 32:
+		len_1 |= RT5682_I2S1_DL_32;
+		len_2 |= RT5682_I2S2_DL_24;
+		break;
+	case 8:
+		len_1 |= RT5682_I2S2_DL_8;
+		len_2 |= RT5682_I2S2_DL_8;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT5682_AIF1:
+		snd_soc_component_update_bits(component, RT5682_I2S1_SDP,
+			RT5682_I2S1_DL_MASK, len_1);
+		if (rt5682->master[RT5682_AIF1]) {
+			snd_soc_component_update_bits(component,
+				RT5682_ADDA_CLK_1, RT5682_I2S_M_DIV_MASK,
+				pre_div << RT5682_I2S_M_DIV_SFT);
+		}
+		if (params_channels(params) == 1) /* mono mode */
+			snd_soc_component_update_bits(component,
+				RT5682_I2S1_SDP, RT5682_I2S1_MONO_MASK,
+				RT5682_I2S1_MONO_EN);
+		else
+			snd_soc_component_update_bits(component,
+				RT5682_I2S1_SDP, RT5682_I2S1_MONO_MASK,
+				RT5682_I2S1_MONO_DIS);
+		break;
+	case RT5682_AIF2:
+		snd_soc_component_update_bits(component, RT5682_I2S2_SDP,
+			RT5682_I2S2_DL_MASK, len_2);
+		if (rt5682->master[RT5682_AIF2]) {
+			snd_soc_component_update_bits(component,
+				RT5682_I2S_M_CLK_CTRL_1, RT5682_I2S2_M_PD_MASK,
+				pre_div << RT5682_I2S2_M_PD_SFT);
+		}
+		if (params_channels(params) == 1) /* mono mode */
+			snd_soc_component_update_bits(component,
+				RT5682_I2S2_SDP, RT5682_I2S2_MONO_MASK,
+				RT5682_I2S2_MONO_EN);
+		else
+			snd_soc_component_update_bits(component,
+				RT5682_I2S2_SDP, RT5682_I2S2_MONO_MASK,
+				RT5682_I2S2_MONO_DIS);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rt5682_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0, tdm_ctrl = 0;
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBM_CFM:
+		rt5682->master[dai->id] = 1;
+		break;
+	case SND_SOC_DAIFMT_CBS_CFS:
+		rt5682->master[dai->id] = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+	case SND_SOC_DAIFMT_NB_NF:
+		break;
+	case SND_SOC_DAIFMT_IB_NF:
+		reg_val |= RT5682_I2S_BP_INV;
+		tdm_ctrl |= RT5682_TDM_S_BP_INV;
+		break;
+	case SND_SOC_DAIFMT_NB_IF:
+		if (dai->id == RT5682_AIF1)
+			tdm_ctrl |= RT5682_TDM_S_LP_INV | RT5682_TDM_M_BP_INV;
+		else
+			return -EINVAL;
+		break;
+	case SND_SOC_DAIFMT_IB_IF:
+		if (dai->id == RT5682_AIF1)
+			tdm_ctrl |= RT5682_TDM_S_BP_INV | RT5682_TDM_S_LP_INV |
+				    RT5682_TDM_M_BP_INV | RT5682_TDM_M_LP_INV;
+		else
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+		break;
+	case SND_SOC_DAIFMT_LEFT_J:
+		reg_val |= RT5682_I2S_DF_LEFT;
+		tdm_ctrl |= RT5682_TDM_DF_LEFT;
+		break;
+	case SND_SOC_DAIFMT_DSP_A:
+		reg_val |= RT5682_I2S_DF_PCM_A;
+		tdm_ctrl |= RT5682_TDM_DF_PCM_A;
+		break;
+	case SND_SOC_DAIFMT_DSP_B:
+		reg_val |= RT5682_I2S_DF_PCM_B;
+		tdm_ctrl |= RT5682_TDM_DF_PCM_B;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (dai->id) {
+	case RT5682_AIF1:
+		snd_soc_component_update_bits(component, RT5682_I2S1_SDP,
+			RT5682_I2S_DF_MASK, reg_val);
+		snd_soc_component_update_bits(component, RT5682_TDM_TCON_CTRL,
+			RT5682_TDM_MS_MASK | RT5682_TDM_S_BP_MASK |
+			RT5682_TDM_DF_MASK | RT5682_TDM_M_BP_MASK |
+			RT5682_TDM_M_LP_MASK | RT5682_TDM_S_LP_MASK,
+			tdm_ctrl | rt5682->master[dai->id]);
+		break;
+	case RT5682_AIF2:
+		if (rt5682->master[dai->id] == 0)
+			reg_val |= RT5682_I2S2_MS_S;
+		snd_soc_component_update_bits(component, RT5682_I2S2_SDP,
+			RT5682_I2S2_MS_MASK | RT5682_I2S_BP_MASK |
+			RT5682_I2S_DF_MASK, reg_val);
+		break;
+	default:
+		dev_err(component->dev, "Invalid dai->id: %d\n", dai->id);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int rt5682_set_component_sysclk(struct snd_soc_component *component,
+		int clk_id, int source, unsigned int freq, int dir)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	unsigned int reg_val = 0, src = 0;
+
+	if (freq == rt5682->sysclk && clk_id == rt5682->sysclk_src)
+		return 0;
+
+	switch (clk_id) {
+	case RT5682_SCLK_S_MCLK:
+		reg_val |= RT5682_SCLK_SRC_MCLK;
+		src = RT5682_CLK_SRC_MCLK;
+		break;
+	case RT5682_SCLK_S_PLL1:
+		reg_val |= RT5682_SCLK_SRC_PLL1;
+		src = RT5682_CLK_SRC_PLL1;
+		break;
+	case RT5682_SCLK_S_PLL2:
+		reg_val |= RT5682_SCLK_SRC_PLL2;
+		src = RT5682_CLK_SRC_PLL2;
+		break;
+	case RT5682_SCLK_S_RCCLK:
+		reg_val |= RT5682_SCLK_SRC_RCCLK;
+		src = RT5682_CLK_SRC_RCCLK;
+		break;
+	default:
+		dev_err(component->dev, "Invalid clock id (%d)\n", clk_id);
+		return -EINVAL;
+	}
+	snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+		RT5682_SCLK_SRC_MASK, reg_val);
+
+	if (rt5682->master[RT5682_AIF2]) {
+		snd_soc_component_update_bits(component,
+			RT5682_I2S_M_CLK_CTRL_1, RT5682_I2S2_SRC_MASK,
+			src << RT5682_I2S2_SRC_SFT);
+	}
+
+	rt5682->sysclk = freq;
+	rt5682->sysclk_src = clk_id;
+
+	dev_dbg(component->dev, "Sysclk is %dHz and clock id is %d\n",
+		freq, clk_id);
+
+	return 0;
+}
+
+static int rt5682_set_component_pll(struct snd_soc_component *component,
+		int pll_id, int source, unsigned int freq_in,
+		unsigned int freq_out)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+	struct rl6231_pll_code pll_code;
+	int ret;
+
+	if (source == rt5682->pll_src && freq_in == rt5682->pll_in &&
+	    freq_out == rt5682->pll_out)
+		return 0;
+
+	if (!freq_in || !freq_out) {
+		dev_dbg(component->dev, "PLL disabled\n");
+
+		rt5682->pll_in = 0;
+		rt5682->pll_out = 0;
+		snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+			RT5682_SCLK_SRC_MASK, RT5682_SCLK_SRC_MCLK);
+		return 0;
+	}
+
+	switch (source) {
+	case RT5682_PLL1_S_MCLK:
+		snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+			RT5682_PLL1_SRC_MASK, RT5682_PLL1_SRC_MCLK);
+		break;
+	case RT5682_PLL1_S_BCLK1:
+		snd_soc_component_update_bits(component, RT5682_GLB_CLK,
+				RT5682_PLL1_SRC_MASK, RT5682_PLL1_SRC_BCLK1);
+		break;
+	default:
+		dev_err(component->dev, "Unknown PLL Source %d\n", source);
+		return -EINVAL;
+	}
+
+	ret = rl6231_pll_calc(freq_in, freq_out, &pll_code);
+	if (ret < 0) {
+		dev_err(component->dev, "Unsupport input clock %d\n", freq_in);
+		return ret;
+	}
+
+	dev_dbg(component->dev, "bypass=%d m=%d n=%d k=%d\n",
+		pll_code.m_bp, (pll_code.m_bp ? 0 : pll_code.m_code),
+		pll_code.n_code, pll_code.k_code);
+
+	snd_soc_component_write(component, RT5682_PLL_CTRL_1,
+		pll_code.n_code << RT5682_PLL_N_SFT | pll_code.k_code);
+	snd_soc_component_write(component, RT5682_PLL_CTRL_2,
+		(pll_code.m_bp ? 0 : pll_code.m_code) << RT5682_PLL_M_SFT |
+		pll_code.m_bp << RT5682_PLL_M_BP_SFT | RT5682_PLL_RST);
+
+	rt5682->pll_in = freq_in;
+	rt5682->pll_out = freq_out;
+	rt5682->pll_src = source;
+
+	return 0;
+}
+
+static int rt5682_set_bclk_ratio(struct snd_soc_dai *dai, unsigned int ratio)
+{
+	struct snd_soc_component *component = dai->component;
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	rt5682->bclk[dai->id] = ratio;
+
+	switch (ratio) {
+	case 64:
+		snd_soc_component_update_bits(component, RT5682_ADDA_CLK_2,
+			RT5682_I2S2_BCLK_MS2_MASK,
+			RT5682_I2S2_BCLK_MS2_64);
+		break;
+	case 32:
+		snd_soc_component_update_bits(component, RT5682_ADDA_CLK_2,
+			RT5682_I2S2_BCLK_MS2_MASK,
+			RT5682_I2S2_BCLK_MS2_32);
+		break;
+	default:
+		dev_err(dai->dev, "Invalid bclk ratio %d\n", ratio);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int rt5682_set_bias_level(struct snd_soc_component *component,
+			enum snd_soc_bias_level level)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_PWR_MB | RT5682_PWR_BG,
+			RT5682_PWR_MB | RT5682_PWR_BG);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
+			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO,
+			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_PWR_MB, RT5682_PWR_MB);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
+			RT5682_DIG_GATE_CTRL, RT5682_DIG_GATE_CTRL);
+		break;
+	case SND_SOC_BIAS_OFF:
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_DIG_1,
+			RT5682_DIG_GATE_CTRL | RT5682_PWR_LDO, 0);
+		regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_PWR_MB | RT5682_PWR_BG, 0);
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int rt5682_probe(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	rt5682->component = component;
+
+	return 0;
+}
+
+static void rt5682_remove(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	rt5682_reset(rt5682->regmap);
+}
+
+#ifdef CONFIG_PM
+static int rt5682_suspend(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt5682->regmap, true);
+	regcache_mark_dirty(rt5682->regmap);
+	return 0;
+}
+
+static int rt5682_resume(struct snd_soc_component *component)
+{
+	struct rt5682_priv *rt5682 = snd_soc_component_get_drvdata(component);
+
+	regcache_cache_only(rt5682->regmap, false);
+	regcache_sync(rt5682->regmap);
+
+	return 0;
+}
+#else
+#define rt5682_suspend NULL
+#define rt5682_resume NULL
+#endif
+
+#define RT5682_STEREO_RATES SNDRV_PCM_RATE_8000_192000
+#define RT5682_FORMATS (SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_S20_3LE | \
+		SNDRV_PCM_FMTBIT_S24_LE | SNDRV_PCM_FMTBIT_S8)
+
+static const struct snd_soc_dai_ops rt5682_aif1_dai_ops = {
+	.hw_params = rt5682_hw_params,
+	.set_fmt = rt5682_set_dai_fmt,
+	.set_tdm_slot = rt5682_set_tdm_slot,
+};
+
+static const struct snd_soc_dai_ops rt5682_aif2_dai_ops = {
+	.hw_params = rt5682_hw_params,
+	.set_fmt = rt5682_set_dai_fmt,
+	.set_bclk_ratio = rt5682_set_bclk_ratio,
+};
+
+static struct snd_soc_dai_driver rt5682_dai[] = {
+	{
+		.name = "rt5682-aif1",
+		.id = RT5682_AIF1,
+		.playback = {
+			.stream_name = "AIF1 Playback",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5682_STEREO_RATES,
+			.formats = RT5682_FORMATS,
+		},
+		.capture = {
+			.stream_name = "AIF1 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5682_STEREO_RATES,
+			.formats = RT5682_FORMATS,
+		},
+		.ops = &rt5682_aif1_dai_ops,
+	},
+	{
+		.name = "rt5682-aif2",
+		.id = RT5682_AIF2,
+		.capture = {
+			.stream_name = "AIF2 Capture",
+			.channels_min = 1,
+			.channels_max = 2,
+			.rates = RT5682_STEREO_RATES,
+			.formats = RT5682_FORMATS,
+		},
+		.ops = &rt5682_aif2_dai_ops,
+	},
+};
+
+static const struct snd_soc_component_driver soc_component_dev_rt5682 = {
+	.probe = rt5682_probe,
+	.remove = rt5682_remove,
+	.suspend = rt5682_suspend,
+	.resume = rt5682_resume,
+	.set_bias_level = rt5682_set_bias_level,
+	.controls = rt5682_snd_controls,
+	.num_controls = ARRAY_SIZE(rt5682_snd_controls),
+	.dapm_widgets = rt5682_dapm_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(rt5682_dapm_widgets),
+	.dapm_routes = rt5682_dapm_routes,
+	.num_dapm_routes = ARRAY_SIZE(rt5682_dapm_routes),
+	.set_sysclk = rt5682_set_component_sysclk,
+	.set_pll = rt5682_set_component_pll,
+	.set_jack = rt5682_set_jack_detect,
+	.use_pmdown_time	= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static const struct regmap_config rt5682_regmap = {
+	.reg_bits = 16,
+	.val_bits = 16,
+	.max_register = RT5682_I2C_MODE,
+	.volatile_reg = rt5682_volatile_register,
+	.readable_reg = rt5682_readable_register,
+	.cache_type = REGCACHE_RBTREE,
+	.reg_defaults = rt5682_reg,
+	.num_reg_defaults = ARRAY_SIZE(rt5682_reg),
+	.use_single_rw = true,
+};
+
+static const struct i2c_device_id rt5682_i2c_id[] = {
+	{"rt5682", 0},
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, rt5682_i2c_id);
+
+static int rt5682_parse_dt(struct rt5682_priv *rt5682, struct device *dev)
+{
+
+	device_property_read_u32(dev, "realtek,dmic1-data-pin",
+		&rt5682->pdata.dmic1_data_pin);
+	device_property_read_u32(dev, "realtek,dmic1-clk-pin",
+		&rt5682->pdata.dmic1_clk_pin);
+	device_property_read_u32(dev, "realtek,jd-src",
+		&rt5682->pdata.jd_src);
+
+	rt5682->pdata.ldo1_en = of_get_named_gpio(dev->of_node,
+		"realtek,ldo1-en-gpios", 0);
+
+	return 0;
+}
+
+static void rt5682_calibrate(struct rt5682_priv *rt5682)
+{
+	int value, count;
+
+	mutex_lock(&rt5682->calibrate_mutex);
+
+	rt5682_reset(rt5682->regmap);
+	regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xa2bf);
+	usleep_range(15000, 20000);
+	regmap_write(rt5682->regmap, RT5682_PWR_ANLG_1, 0xf2bf);
+	regmap_write(rt5682->regmap, RT5682_MICBIAS_2, 0x0380);
+	regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x8001);
+	regmap_write(rt5682->regmap, RT5682_TEST_MODE_CTRL_1, 0x0000);
+	regmap_write(rt5682->regmap, RT5682_STO1_DAC_MIXER, 0x2080);
+	regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0x4040);
+	regmap_write(rt5682->regmap, RT5682_DEPOP_1, 0x0069);
+	regmap_write(rt5682->regmap, RT5682_CHOP_DAC, 0x3000);
+	regmap_write(rt5682->regmap, RT5682_HP_CTRL_2, 0x6000);
+	regmap_write(rt5682->regmap, RT5682_HP_CHARGE_PUMP_1, 0x0f26);
+	regmap_write(rt5682->regmap, RT5682_CALIB_ADC_CTRL, 0x7f05);
+	regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0x686c);
+	regmap_write(rt5682->regmap, RT5682_CAL_REC, 0x0d0d);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_9, 0x000f);
+	regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x8d01);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_2, 0x0321);
+	regmap_write(rt5682->regmap, RT5682_HP_LOGIC_CTRL_2, 0x0004);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_1, 0x7c00);
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_3, 0x06a1);
+	regmap_write(rt5682->regmap, RT5682_A_DAC1_MUX, 0x0311);
+	regmap_write(rt5682->regmap, RT5682_RESET_HPF_CTRL, 0x0000);
+	regmap_write(rt5682->regmap, RT5682_ADC_STO1_HP_CTRL_1, 0x3320);
+
+	regmap_write(rt5682->regmap, RT5682_HP_CALIB_CTRL_1, 0xfc00);
+
+	for (count = 0; count < 60; count++) {
+		regmap_read(rt5682->regmap, RT5682_HP_CALIB_STA_1, &value);
+		if (!(value & 0x8000))
+			break;
+
+		usleep_range(10000, 10005);
+	}
+
+	if (count >= 60)
+		pr_err("HP Calibration Failure\n");
+
+	/* restore settings */
+	regmap_write(rt5682->regmap, RT5682_STO1_ADC_MIXER, 0xc0c4);
+	regmap_write(rt5682->regmap, RT5682_PWR_DIG_1, 0x0000);
+
+	mutex_unlock(&rt5682->calibrate_mutex);
+
+}
+
+static int rt5682_i2c_probe(struct i2c_client *i2c,
+		    const struct i2c_device_id *id)
+{
+	struct rt5682_platform_data *pdata = dev_get_platdata(&i2c->dev);
+	struct rt5682_priv *rt5682;
+	int i, ret;
+	unsigned int val;
+
+	rt5682 = devm_kzalloc(&i2c->dev, sizeof(struct rt5682_priv),
+		GFP_KERNEL);
+
+	if (rt5682 == NULL)
+		return -ENOMEM;
+
+	i2c_set_clientdata(i2c, rt5682);
+
+	if (pdata)
+		rt5682->pdata = *pdata;
+	else
+		rt5682_parse_dt(rt5682, &i2c->dev);
+
+	rt5682->regmap = devm_regmap_init_i2c(i2c, &rt5682_regmap);
+	if (IS_ERR(rt5682->regmap)) {
+		ret = PTR_ERR(rt5682->regmap);
+		dev_err(&i2c->dev, "Failed to allocate register map: %d\n",
+			ret);
+		return ret;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(rt5682->supplies); i++)
+		rt5682->supplies[i].supply = rt5682_supply_names[i];
+
+	ret = devm_regulator_bulk_get(&i2c->dev, ARRAY_SIZE(rt5682->supplies),
+				      rt5682->supplies);
+	if (ret != 0) {
+		dev_err(&i2c->dev, "Failed to request supplies: %d\n", ret);
+		return ret;
+	}
+
+	ret = regulator_bulk_enable(ARRAY_SIZE(rt5682->supplies),
+				    rt5682->supplies);
+	if (ret != 0) {
+		dev_err(&i2c->dev, "Failed to enable supplies: %d\n", ret);
+		return ret;
+	}
+
+	if (gpio_is_valid(rt5682->pdata.ldo1_en)) {
+		if (devm_gpio_request_one(&i2c->dev, rt5682->pdata.ldo1_en,
+					  GPIOF_OUT_INIT_HIGH, "rt5682"))
+			dev_err(&i2c->dev, "Fail gpio_request gpio_ldo\n");
+	}
+
+	/* Sleep for 300 ms miniumum */
+	usleep_range(300000, 350000);
+
+	regmap_write(rt5682->regmap, RT5682_I2C_MODE, 0x1);
+	usleep_range(10000, 15000);
+
+	regmap_read(rt5682->regmap, RT5682_DEVICE_ID, &val);
+	if (val != DEVICE_ID) {
+		pr_err("Device with ID register %x is not rt5682\n", val);
+		return -ENODEV;
+	}
+
+	rt5682_reset(rt5682->regmap);
+
+	rt5682_calibrate(rt5682);
+
+	ret = regmap_register_patch(rt5682->regmap, patch_list,
+				    ARRAY_SIZE(patch_list));
+	if (ret != 0)
+		dev_warn(&i2c->dev, "Failed to apply regmap patch: %d\n", ret);
+
+	regmap_write(rt5682->regmap, RT5682_DEPOP_1, 0x0000);
+
+	/* DMIC pin*/
+	if (rt5682->pdata.dmic1_data_pin != RT5682_DMIC1_NULL) {
+		switch (rt5682->pdata.dmic1_data_pin) {
+		case RT5682_DMIC1_DATA_GPIO2: /* share with LRCK2 */
+			regmap_update_bits(rt5682->regmap, RT5682_DMIC_CTRL_1,
+				RT5682_DMIC_1_DP_MASK, RT5682_DMIC_1_DP_GPIO2);
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP2_PIN_MASK, RT5682_GP2_PIN_DMIC_SDA);
+			break;
+
+		case RT5682_DMIC1_DATA_GPIO5: /* share with DACDAT1 */
+			regmap_update_bits(rt5682->regmap, RT5682_DMIC_CTRL_1,
+				RT5682_DMIC_1_DP_MASK, RT5682_DMIC_1_DP_GPIO5);
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP5_PIN_MASK, RT5682_GP5_PIN_DMIC_SDA);
+			break;
+
+		default:
+			dev_warn(&i2c->dev, "invalid DMIC_DAT pin\n");
+			break;
+		}
+
+		switch (rt5682->pdata.dmic1_clk_pin) {
+		case RT5682_DMIC1_CLK_GPIO1: /* share with IRQ */
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP1_PIN_MASK, RT5682_GP1_PIN_DMIC_CLK);
+			break;
+
+		case RT5682_DMIC1_CLK_GPIO3: /* share with BCLK2 */
+			regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+				RT5682_GP3_PIN_MASK, RT5682_GP3_PIN_DMIC_CLK);
+			break;
+
+		default:
+			dev_warn(&i2c->dev, "invalid DMIC_CLK pin\n");
+			break;
+		}
+	}
+
+	regmap_update_bits(rt5682->regmap, RT5682_PWR_ANLG_1,
+			RT5682_LDO1_DVO_MASK | RT5682_HP_DRIVER_MASK,
+			RT5682_LDO1_DVO_12 | RT5682_HP_DRIVER_5X);
+	regmap_write(rt5682->regmap, RT5682_MICBIAS_2, 0x0380);
+	regmap_update_bits(rt5682->regmap, RT5682_GPIO_CTRL_1,
+			RT5682_GP4_PIN_MASK | RT5682_GP5_PIN_MASK,
+			RT5682_GP4_PIN_ADCDAT1 | RT5682_GP5_PIN_DACDAT1);
+	regmap_write(rt5682->regmap, RT5682_TEST_MODE_CTRL_1, 0x0000);
+
+	INIT_DELAYED_WORK(&rt5682->jack_detect_work,
+				rt5682_jack_detect_handler);
+	INIT_DELAYED_WORK(&rt5682->jd_check_work,
+				rt5682_jd_check_handler);
+
+	mutex_init(&rt5682->calibrate_mutex);
+
+	if (i2c->irq) {
+		ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL,
+			rt5682_irq, IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			| IRQF_ONESHOT, "rt5682", rt5682);
+		if (ret)
+			dev_err(&i2c->dev, "Failed to reguest IRQ: %d\n", ret);
+
+	}
+
+	return snd_soc_register_component(&i2c->dev, &soc_component_dev_rt5682,
+			rt5682_dai, ARRAY_SIZE(rt5682_dai));
+}
+
+static int rt5682_i2c_remove(struct i2c_client *i2c)
+{
+	snd_soc_unregister_component(&i2c->dev);
+
+	return 0;
+}
+
+static void rt5682_i2c_shutdown(struct i2c_client *client)
+{
+	struct rt5682_priv *rt5682 = i2c_get_clientdata(client);
+
+	rt5682_reset(rt5682->regmap);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id rt5682_of_match[] = {
+	{.compatible = "realtek,rt5682i"},
+	{},
+};
+MODULE_DEVICE_TABLE(of, rt5682_of_match);
+#endif
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id rt5682_acpi_match[] = {
+	{"10EC5682", 0,},
+	{},
+};
+MODULE_DEVICE_TABLE(acpi, rt5682_acpi_match);
+#endif
+
+static struct i2c_driver rt5682_i2c_driver = {
+	.driver = {
+		.name = "rt5682",
+		.of_match_table = of_match_ptr(rt5682_of_match),
+		.acpi_match_table = ACPI_PTR(rt5682_acpi_match),
+	},
+	.probe = rt5682_i2c_probe,
+	.remove = rt5682_i2c_remove,
+	.shutdown = rt5682_i2c_shutdown,
+	.id_table = rt5682_i2c_id,
+};
+module_i2c_driver(rt5682_i2c_driver);
+
+MODULE_DESCRIPTION("ASoC RT5682 driver");
+MODULE_AUTHOR("Bard Liao <bardliao@realtek.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/codecs/rt5682.h b/sound/soc/codecs/rt5682.h
new file mode 100644
index 000000000000..8068140ebe3f
--- /dev/null
+++ b/sound/soc/codecs/rt5682.h
@@ -0,0 +1,1324 @@
+/*
+ * rt5682.h  --  RT5682/RT5658 ALSA SoC audio driver
+ *
+ * Copyright 2018 Realtek Microelectronics
+ * Author: Bard Liao <bardliao@realtek.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __RT5682_H__
+#define __RT5682_H__
+
+#include <sound/rt5682.h>
+
+#define DEVICE_ID 0x6530
+
+/* Info */
+#define RT5682_RESET				0x0000
+#define RT5682_VERSION_ID			0x00fd
+#define RT5682_VENDOR_ID			0x00fe
+#define RT5682_DEVICE_ID			0x00ff
+/*  I/O - Output */
+#define RT5682_HP_CTRL_1			0x0002
+#define RT5682_HP_CTRL_2			0x0003
+#define RT5682_HPL_GAIN				0x0005
+#define RT5682_HPR_GAIN				0x0006
+
+#define RT5682_I2C_CTRL				0x0008
+
+/* I/O - Input */
+#define RT5682_CBJ_BST_CTRL			0x000b
+#define RT5682_CBJ_CTRL_1			0x0010
+#define RT5682_CBJ_CTRL_2			0x0011
+#define RT5682_CBJ_CTRL_3			0x0012
+#define RT5682_CBJ_CTRL_4			0x0013
+#define RT5682_CBJ_CTRL_5			0x0014
+#define RT5682_CBJ_CTRL_6			0x0015
+#define RT5682_CBJ_CTRL_7			0x0016
+/* I/O - ADC/DAC/DMIC */
+#define RT5682_DAC1_DIG_VOL			0x0019
+#define RT5682_STO1_ADC_DIG_VOL			0x001c
+#define RT5682_STO1_ADC_BOOST			0x001f
+#define RT5682_HP_IMP_GAIN_1			0x0022
+#define RT5682_HP_IMP_GAIN_2			0x0023
+/* Mixer - D-D */
+#define RT5682_SIDETONE_CTRL			0x0024
+#define RT5682_STO1_ADC_MIXER			0x0026
+#define RT5682_AD_DA_MIXER			0x0029
+#define RT5682_STO1_DAC_MIXER			0x002a
+#define RT5682_A_DAC1_MUX			0x002b
+#define RT5682_DIG_INF2_DATA			0x0030
+/* Mixer - ADC */
+#define RT5682_REC_MIXER			0x003c
+#define RT5682_CAL_REC				0x0044
+#define RT5682_ALC_BACK_GAIN			0x0049
+/* Power */
+#define RT5682_PWR_DIG_1			0x0061
+#define RT5682_PWR_DIG_2			0x0062
+#define RT5682_PWR_ANLG_1			0x0063
+#define RT5682_PWR_ANLG_2			0x0064
+#define RT5682_PWR_ANLG_3			0x0065
+#define RT5682_PWR_MIXER			0x0066
+#define RT5682_PWR_VOL				0x0067
+/* Clock Detect */
+#define RT5682_CLK_DET				0x006b
+/* Filter Auto Reset */
+#define RT5682_RESET_LPF_CTRL			0x006c
+#define RT5682_RESET_HPF_CTRL			0x006d
+/* DMIC */
+#define RT5682_DMIC_CTRL_1			0x006e
+/* Format - ADC/DAC */
+#define RT5682_I2S1_SDP				0x0070
+#define RT5682_I2S2_SDP				0x0071
+#define RT5682_ADDA_CLK_1			0x0073
+#define RT5682_ADDA_CLK_2			0x0074
+#define RT5682_I2S1_F_DIV_CTRL_1		0x0075
+#define RT5682_I2S1_F_DIV_CTRL_2		0x0076
+/* Format - TDM Control */
+#define RT5682_TDM_CTRL				0x0079
+#define RT5682_TDM_ADDA_CTRL_1			0x007a
+#define RT5682_TDM_ADDA_CTRL_2			0x007b
+#define RT5682_DATA_SEL_CTRL_1			0x007c
+#define RT5682_TDM_TCON_CTRL			0x007e
+/* Function - Analog */
+#define RT5682_GLB_CLK				0x0080
+#define RT5682_PLL_CTRL_1			0x0081
+#define RT5682_PLL_CTRL_2			0x0082
+#define RT5682_PLL_TRACK_1			0x0083
+#define RT5682_PLL_TRACK_2			0x0084
+#define RT5682_PLL_TRACK_3			0x0085
+#define RT5682_PLL_TRACK_4			0x0086
+#define RT5682_PLL_TRACK_5			0x0087
+#define RT5682_PLL_TRACK_6			0x0088
+#define RT5682_PLL_TRACK_11			0x008c
+#define RT5682_SDW_REF_CLK			0x008d
+#define RT5682_DEPOP_1				0x008e
+#define RT5682_DEPOP_2				0x008f
+#define RT5682_HP_CHARGE_PUMP_1			0x0091
+#define RT5682_HP_CHARGE_PUMP_2			0x0092
+#define RT5682_MICBIAS_1			0x0093
+#define RT5682_MICBIAS_2			0x0094
+#define RT5682_PLL_TRACK_12			0x0098
+#define RT5682_PLL_TRACK_14			0x009a
+#define RT5682_PLL2_CTRL_1			0x009b
+#define RT5682_PLL2_CTRL_2			0x009c
+#define RT5682_PLL2_CTRL_3			0x009d
+#define RT5682_PLL2_CTRL_4			0x009e
+#define RT5682_RC_CLK_CTRL			0x009f
+#define RT5682_I2S_M_CLK_CTRL_1			0x00a0
+#define RT5682_I2S2_F_DIV_CTRL_1		0x00a3
+#define RT5682_I2S2_F_DIV_CTRL_2		0x00a4
+/* Function - Digital */
+#define RT5682_EQ_CTRL_1			0x00ae
+#define RT5682_EQ_CTRL_2			0x00af
+#define RT5682_IRQ_CTRL_1			0x00b6
+#define RT5682_IRQ_CTRL_2			0x00b7
+#define RT5682_IRQ_CTRL_3			0x00b8
+#define RT5682_IRQ_CTRL_4			0x00b9
+#define RT5682_INT_ST_1				0x00be
+#define RT5682_GPIO_CTRL_1			0x00c0
+#define RT5682_GPIO_CTRL_2			0x00c1
+#define RT5682_GPIO_CTRL_3			0x00c2
+#define RT5682_HP_AMP_DET_CTRL_1		0x00d0
+#define RT5682_HP_AMP_DET_CTRL_2		0x00d1
+#define RT5682_MID_HP_AMP_DET			0x00d2
+#define RT5682_LOW_HP_AMP_DET			0x00d3
+#define RT5682_DELAY_BUF_CTRL			0x00d4
+#define RT5682_SV_ZCD_1				0x00d9
+#define RT5682_SV_ZCD_2				0x00da
+#define RT5682_IL_CMD_1				0x00db
+#define RT5682_IL_CMD_2				0x00dc
+#define RT5682_IL_CMD_3				0x00dd
+#define RT5682_IL_CMD_4				0x00de
+#define RT5682_IL_CMD_5				0x00df
+#define RT5682_IL_CMD_6				0x00e0
+#define RT5682_4BTN_IL_CMD_1			0x00e2
+#define RT5682_4BTN_IL_CMD_2			0x00e3
+#define RT5682_4BTN_IL_CMD_3			0x00e4
+#define RT5682_4BTN_IL_CMD_4			0x00e5
+#define RT5682_4BTN_IL_CMD_5			0x00e6
+#define RT5682_4BTN_IL_CMD_6			0x00e7
+#define RT5682_4BTN_IL_CMD_7			0x00e8
+
+#define RT5682_ADC_STO1_HP_CTRL_1		0x00ea
+#define RT5682_ADC_STO1_HP_CTRL_2		0x00eb
+#define RT5682_AJD1_CTRL			0x00f0
+#define RT5682_JD1_THD				0x00f1
+#define RT5682_JD2_THD				0x00f2
+#define RT5682_JD_CTRL_1			0x00f6
+/* General Control */
+#define RT5682_DUMMY_1				0x00fa
+#define RT5682_DUMMY_2				0x00fb
+#define RT5682_DUMMY_3				0x00fc
+
+#define RT5682_DAC_ADC_DIG_VOL1			0x0100
+#define RT5682_BIAS_CUR_CTRL_2			0x010b
+#define RT5682_BIAS_CUR_CTRL_3			0x010c
+#define RT5682_BIAS_CUR_CTRL_4			0x010d
+#define RT5682_BIAS_CUR_CTRL_5			0x010e
+#define RT5682_BIAS_CUR_CTRL_6			0x010f
+#define RT5682_BIAS_CUR_CTRL_7			0x0110
+#define RT5682_BIAS_CUR_CTRL_8			0x0111
+#define RT5682_BIAS_CUR_CTRL_9			0x0112
+#define RT5682_BIAS_CUR_CTRL_10			0x0113
+#define RT5682_VREF_REC_OP_FB_CAP_CTRL		0x0117
+#define RT5682_CHARGE_PUMP_1			0x0125
+#define RT5682_DIG_IN_CTRL_1			0x0132
+#define RT5682_PAD_DRIVING_CTRL			0x0136
+#define RT5682_SOFT_RAMP_DEPOP			0x0138
+#define RT5682_CHOP_DAC				0x013a
+#define RT5682_CHOP_ADC				0x013b
+#define RT5682_CALIB_ADC_CTRL			0x013c
+#define RT5682_VOL_TEST				0x013f
+#define RT5682_SPKVDD_DET_STA			0x0142
+#define RT5682_TEST_MODE_CTRL_1			0x0145
+#define RT5682_TEST_MODE_CTRL_2			0x0146
+#define RT5682_TEST_MODE_CTRL_3			0x0147
+#define RT5682_TEST_MODE_CTRL_4			0x0148
+#define RT5682_TEST_MODE_CTRL_5			0x0149
+#define RT5682_PLL1_INTERNAL			0x0150
+#define RT5682_PLL2_INTERNAL			0x0151
+#define RT5682_STO_NG2_CTRL_1			0x0160
+#define RT5682_STO_NG2_CTRL_2			0x0161
+#define RT5682_STO_NG2_CTRL_3			0x0162
+#define RT5682_STO_NG2_CTRL_4			0x0163
+#define RT5682_STO_NG2_CTRL_5			0x0164
+#define RT5682_STO_NG2_CTRL_6			0x0165
+#define RT5682_STO_NG2_CTRL_7			0x0166
+#define RT5682_STO_NG2_CTRL_8			0x0167
+#define RT5682_STO_NG2_CTRL_9			0x0168
+#define RT5682_STO_NG2_CTRL_10			0x0169
+#define RT5682_STO1_DAC_SIL_DET			0x0190
+#define RT5682_SIL_PSV_CTRL1			0x0194
+#define RT5682_SIL_PSV_CTRL2			0x0195
+#define RT5682_SIL_PSV_CTRL3			0x0197
+#define RT5682_SIL_PSV_CTRL4			0x0198
+#define RT5682_SIL_PSV_CTRL5			0x0199
+#define RT5682_HP_IMP_SENS_CTRL_01		0x01af
+#define RT5682_HP_IMP_SENS_CTRL_02		0x01b0
+#define RT5682_HP_IMP_SENS_CTRL_03		0x01b1
+#define RT5682_HP_IMP_SENS_CTRL_04		0x01b2
+#define RT5682_HP_IMP_SENS_CTRL_05		0x01b3
+#define RT5682_HP_IMP_SENS_CTRL_06		0x01b4
+#define RT5682_HP_IMP_SENS_CTRL_07		0x01b5
+#define RT5682_HP_IMP_SENS_CTRL_08		0x01b6
+#define RT5682_HP_IMP_SENS_CTRL_09		0x01b7
+#define RT5682_HP_IMP_SENS_CTRL_10		0x01b8
+#define RT5682_HP_IMP_SENS_CTRL_11		0x01b9
+#define RT5682_HP_IMP_SENS_CTRL_12		0x01ba
+#define RT5682_HP_IMP_SENS_CTRL_13		0x01bb
+#define RT5682_HP_IMP_SENS_CTRL_14		0x01bc
+#define RT5682_HP_IMP_SENS_CTRL_15		0x01bd
+#define RT5682_HP_IMP_SENS_CTRL_16		0x01be
+#define RT5682_HP_IMP_SENS_CTRL_17		0x01bf
+#define RT5682_HP_IMP_SENS_CTRL_18		0x01c0
+#define RT5682_HP_IMP_SENS_CTRL_19		0x01c1
+#define RT5682_HP_IMP_SENS_CTRL_20		0x01c2
+#define RT5682_HP_IMP_SENS_CTRL_21		0x01c3
+#define RT5682_HP_IMP_SENS_CTRL_22		0x01c4
+#define RT5682_HP_IMP_SENS_CTRL_23		0x01c5
+#define RT5682_HP_IMP_SENS_CTRL_24		0x01c6
+#define RT5682_HP_IMP_SENS_CTRL_25		0x01c7
+#define RT5682_HP_IMP_SENS_CTRL_26		0x01c8
+#define RT5682_HP_IMP_SENS_CTRL_27		0x01c9
+#define RT5682_HP_IMP_SENS_CTRL_28		0x01ca
+#define RT5682_HP_IMP_SENS_CTRL_29		0x01cb
+#define RT5682_HP_IMP_SENS_CTRL_30		0x01cc
+#define RT5682_HP_IMP_SENS_CTRL_31		0x01cd
+#define RT5682_HP_IMP_SENS_CTRL_32		0x01ce
+#define RT5682_HP_IMP_SENS_CTRL_33		0x01cf
+#define RT5682_HP_IMP_SENS_CTRL_34		0x01d0
+#define RT5682_HP_IMP_SENS_CTRL_35		0x01d1
+#define RT5682_HP_IMP_SENS_CTRL_36		0x01d2
+#define RT5682_HP_IMP_SENS_CTRL_37		0x01d3
+#define RT5682_HP_IMP_SENS_CTRL_38		0x01d4
+#define RT5682_HP_IMP_SENS_CTRL_39		0x01d5
+#define RT5682_HP_IMP_SENS_CTRL_40		0x01d6
+#define RT5682_HP_IMP_SENS_CTRL_41		0x01d7
+#define RT5682_HP_IMP_SENS_CTRL_42		0x01d8
+#define RT5682_HP_IMP_SENS_CTRL_43		0x01d9
+#define RT5682_HP_LOGIC_CTRL_1			0x01da
+#define RT5682_HP_LOGIC_CTRL_2			0x01db
+#define RT5682_HP_LOGIC_CTRL_3			0x01dc
+#define RT5682_HP_CALIB_CTRL_1			0x01de
+#define RT5682_HP_CALIB_CTRL_2			0x01df
+#define RT5682_HP_CALIB_CTRL_3			0x01e0
+#define RT5682_HP_CALIB_CTRL_4			0x01e1
+#define RT5682_HP_CALIB_CTRL_5			0x01e2
+#define RT5682_HP_CALIB_CTRL_6			0x01e3
+#define RT5682_HP_CALIB_CTRL_7			0x01e4
+#define RT5682_HP_CALIB_CTRL_9			0x01e6
+#define RT5682_HP_CALIB_CTRL_10			0x01e7
+#define RT5682_HP_CALIB_CTRL_11			0x01e8
+#define RT5682_HP_CALIB_STA_1			0x01ea
+#define RT5682_HP_CALIB_STA_2			0x01eb
+#define RT5682_HP_CALIB_STA_3			0x01ec
+#define RT5682_HP_CALIB_STA_4			0x01ed
+#define RT5682_HP_CALIB_STA_5			0x01ee
+#define RT5682_HP_CALIB_STA_6			0x01ef
+#define RT5682_HP_CALIB_STA_7			0x01f0
+#define RT5682_HP_CALIB_STA_8			0x01f1
+#define RT5682_HP_CALIB_STA_9			0x01f2
+#define RT5682_HP_CALIB_STA_10			0x01f3
+#define RT5682_HP_CALIB_STA_11			0x01f4
+#define RT5682_SAR_IL_CMD_1			0x0210
+#define RT5682_SAR_IL_CMD_2			0x0211
+#define RT5682_SAR_IL_CMD_3			0x0212
+#define RT5682_SAR_IL_CMD_4			0x0213
+#define RT5682_SAR_IL_CMD_5			0x0214
+#define RT5682_SAR_IL_CMD_6			0x0215
+#define RT5682_SAR_IL_CMD_7			0x0216
+#define RT5682_SAR_IL_CMD_8			0x0217
+#define RT5682_SAR_IL_CMD_9			0x0218
+#define RT5682_SAR_IL_CMD_10			0x0219
+#define RT5682_SAR_IL_CMD_11			0x021a
+#define RT5682_SAR_IL_CMD_12			0x021b
+#define RT5682_SAR_IL_CMD_13			0x021c
+#define RT5682_EFUSE_CTRL_1			0x0250
+#define RT5682_EFUSE_CTRL_2			0x0251
+#define RT5682_EFUSE_CTRL_3			0x0252
+#define RT5682_EFUSE_CTRL_4			0x0253
+#define RT5682_EFUSE_CTRL_5			0x0254
+#define RT5682_EFUSE_CTRL_6			0x0255
+#define RT5682_EFUSE_CTRL_7			0x0256
+#define RT5682_EFUSE_CTRL_8			0x0257
+#define RT5682_EFUSE_CTRL_9			0x0258
+#define RT5682_EFUSE_CTRL_10			0x0259
+#define RT5682_EFUSE_CTRL_11			0x025a
+#define RT5682_JD_TOP_VC_VTRL			0x0270
+#define RT5682_DRC1_CTRL_0			0x02ff
+#define RT5682_DRC1_CTRL_1			0x0300
+#define RT5682_DRC1_CTRL_2			0x0301
+#define RT5682_DRC1_CTRL_3			0x0302
+#define RT5682_DRC1_CTRL_4			0x0303
+#define RT5682_DRC1_CTRL_5			0x0304
+#define RT5682_DRC1_CTRL_6			0x0305
+#define RT5682_DRC1_HARD_LMT_CTRL_1		0x0306
+#define RT5682_DRC1_HARD_LMT_CTRL_2		0x0307
+#define RT5682_DRC1_PRIV_1			0x0310
+#define RT5682_DRC1_PRIV_2			0x0311
+#define RT5682_DRC1_PRIV_3			0x0312
+#define RT5682_DRC1_PRIV_4			0x0313
+#define RT5682_DRC1_PRIV_5			0x0314
+#define RT5682_DRC1_PRIV_6			0x0315
+#define RT5682_DRC1_PRIV_7			0x0316
+#define RT5682_DRC1_PRIV_8			0x0317
+#define RT5682_EQ_AUTO_RCV_CTRL1		0x03c0
+#define RT5682_EQ_AUTO_RCV_CTRL2		0x03c1
+#define RT5682_EQ_AUTO_RCV_CTRL3		0x03c2
+#define RT5682_EQ_AUTO_RCV_CTRL4		0x03c3
+#define RT5682_EQ_AUTO_RCV_CTRL5		0x03c4
+#define RT5682_EQ_AUTO_RCV_CTRL6		0x03c5
+#define RT5682_EQ_AUTO_RCV_CTRL7		0x03c6
+#define RT5682_EQ_AUTO_RCV_CTRL8		0x03c7
+#define RT5682_EQ_AUTO_RCV_CTRL9		0x03c8
+#define RT5682_EQ_AUTO_RCV_CTRL10		0x03c9
+#define RT5682_EQ_AUTO_RCV_CTRL11		0x03ca
+#define RT5682_EQ_AUTO_RCV_CTRL12		0x03cb
+#define RT5682_EQ_AUTO_RCV_CTRL13		0x03cc
+#define RT5682_ADC_L_EQ_LPF1_A1			0x03d0
+#define RT5682_R_EQ_LPF1_A1			0x03d1
+#define RT5682_L_EQ_LPF1_H0			0x03d2
+#define RT5682_R_EQ_LPF1_H0			0x03d3
+#define RT5682_L_EQ_BPF1_A1			0x03d4
+#define RT5682_R_EQ_BPF1_A1			0x03d5
+#define RT5682_L_EQ_BPF1_A2			0x03d6
+#define RT5682_R_EQ_BPF1_A2			0x03d7
+#define RT5682_L_EQ_BPF1_H0			0x03d8
+#define RT5682_R_EQ_BPF1_H0			0x03d9
+#define RT5682_L_EQ_BPF2_A1			0x03da
+#define RT5682_R_EQ_BPF2_A1			0x03db
+#define RT5682_L_EQ_BPF2_A2			0x03dc
+#define RT5682_R_EQ_BPF2_A2			0x03dd
+#define RT5682_L_EQ_BPF2_H0			0x03de
+#define RT5682_R_EQ_BPF2_H0			0x03df
+#define RT5682_L_EQ_BPF3_A1			0x03e0
+#define RT5682_R_EQ_BPF3_A1			0x03e1
+#define RT5682_L_EQ_BPF3_A2			0x03e2
+#define RT5682_R_EQ_BPF3_A2			0x03e3
+#define RT5682_L_EQ_BPF3_H0			0x03e4
+#define RT5682_R_EQ_BPF3_H0			0x03e5
+#define RT5682_L_EQ_BPF4_A1			0x03e6
+#define RT5682_R_EQ_BPF4_A1			0x03e7
+#define RT5682_L_EQ_BPF4_A2			0x03e8
+#define RT5682_R_EQ_BPF4_A2			0x03e9
+#define RT5682_L_EQ_BPF4_H0			0x03ea
+#define RT5682_R_EQ_BPF4_H0			0x03eb
+#define RT5682_L_EQ_HPF1_A1			0x03ec
+#define RT5682_R_EQ_HPF1_A1			0x03ed
+#define RT5682_L_EQ_HPF1_H0			0x03ee
+#define RT5682_R_EQ_HPF1_H0			0x03ef
+#define RT5682_L_EQ_PRE_VOL			0x03f0
+#define RT5682_R_EQ_PRE_VOL			0x03f1
+#define RT5682_L_EQ_POST_VOL			0x03f2
+#define RT5682_R_EQ_POST_VOL			0x03f3
+#define RT5682_I2C_MODE				0xffff
+
+
+/* global definition */
+#define RT5682_L_MUTE				(0x1 << 15)
+#define RT5682_L_MUTE_SFT			15
+#define RT5682_VOL_L_MUTE			(0x1 << 14)
+#define RT5682_VOL_L_SFT			14
+#define RT5682_R_MUTE				(0x1 << 7)
+#define RT5682_R_MUTE_SFT			7
+#define RT5682_VOL_R_MUTE			(0x1 << 6)
+#define RT5682_VOL_R_SFT			6
+#define RT5682_L_VOL_MASK			(0x3f << 8)
+#define RT5682_L_VOL_SFT			8
+#define RT5682_R_VOL_MASK			(0x3f)
+#define RT5682_R_VOL_SFT			0
+
+/*Headphone Amp L/R Analog Gain and Digital NG2 Gain Control (0x0005 0x0006)*/
+#define RT5682_G_HP				(0xf << 8)
+#define RT5682_G_HP_SFT				8
+#define RT5682_G_STO_DA_DMIX			(0xf)
+#define RT5682_G_STO_DA_SFT			0
+
+/* CBJ Control (0x000b) */
+#define RT5682_BST_CBJ_MASK			(0xf << 8)
+#define RT5682_BST_CBJ_SFT			8
+
+/* Embeeded Jack and Type Detection Control 1 (0x0010) */
+#define RT5682_EMB_JD_EN			(0x1 << 15)
+#define RT5682_EMB_JD_EN_SFT			15
+#define RT5682_EMB_JD_RST			(0x1 << 14)
+#define RT5682_JD_MODE				(0x1 << 13)
+#define RT5682_JD_MODE_SFT			13
+#define RT5682_DET_TYPE				(0x1 << 12)
+#define RT5682_DET_TYPE_SFT			12
+#define RT5682_POLA_EXT_JD_MASK			(0x1 << 11)
+#define RT5682_POLA_EXT_JD_LOW			(0x1 << 11)
+#define RT5682_POLA_EXT_JD_HIGH			(0x0 << 11)
+#define RT5682_EXT_JD_DIG			(0x1 << 9)
+#define RT5682_POL_FAST_OFF_MASK		(0x1 << 8)
+#define RT5682_POL_FAST_OFF_HIGH		(0x1 << 8)
+#define RT5682_POL_FAST_OFF_LOW			(0x0 << 8)
+#define RT5682_FAST_OFF_MASK			(0x1 << 7)
+#define RT5682_FAST_OFF_EN			(0x1 << 7)
+#define RT5682_FAST_OFF_DIS			(0x0 << 7)
+#define RT5682_VREF_POW_MASK			(0x1 << 6)
+#define RT5682_VREF_POW_FSM			(0x0 << 6)
+#define RT5682_VREF_POW_REG			(0x1 << 6)
+#define RT5682_MB1_PATH_MASK			(0x1 << 5)
+#define RT5682_CTRL_MB1_REG			(0x1 << 5)
+#define RT5682_CTRL_MB1_FSM			(0x0 << 5)
+#define RT5682_MB2_PATH_MASK			(0x1 << 4)
+#define RT5682_CTRL_MB2_REG			(0x1 << 4)
+#define RT5682_CTRL_MB2_FSM			(0x0 << 4)
+#define RT5682_TRIG_JD_MASK			(0x1 << 3)
+#define RT5682_TRIG_JD_HIGH			(0x1 << 3)
+#define RT5682_TRIG_JD_LOW			(0x0 << 3)
+#define RT5682_MIC_CAP_MASK			(0x1 << 1)
+#define RT5682_MIC_CAP_HS			(0x1 << 1)
+#define RT5682_MIC_CAP_HP			(0x0 << 1)
+#define RT5682_MIC_CAP_SRC_MASK			(0x1)
+#define RT5682_MIC_CAP_SRC_REG			(0x1)
+#define RT5682_MIC_CAP_SRC_ANA			(0x0)
+
+/* Embeeded Jack and Type Detection Control 2 (0x0011) */
+#define RT5682_EXT_JD_SRC			(0x7 << 4)
+#define RT5682_EXT_JD_SRC_SFT			4
+#define RT5682_EXT_JD_SRC_GPIO_JD1		(0x0 << 4)
+#define RT5682_EXT_JD_SRC_GPIO_JD2		(0x1 << 4)
+#define RT5682_EXT_JD_SRC_JDH			(0x2 << 4)
+#define RT5682_EXT_JD_SRC_JDL			(0x3 << 4)
+#define RT5682_EXT_JD_SRC_MANUAL		(0x4 << 4)
+#define RT5682_JACK_TYPE_MASK			(0x3)
+
+/* Combo Jack and Type Detection Control 3 (0x0012) */
+#define RT5682_CBJ_IN_BUF_EN			(0x1 << 7)
+
+/* Combo Jack and Type Detection Control 4 (0x0013) */
+#define RT5682_SEL_SHT_MID_TON_MASK		(0x3 << 12)
+#define RT5682_SEL_SHT_MID_TON_2		(0x0 << 12)
+#define RT5682_SEL_SHT_MID_TON_3		(0x1 << 12)
+#define RT5682_CBJ_JD_TEST_MASK			(0x1 << 6)
+#define RT5682_CBJ_JD_TEST_NORM			(0x0 << 6)
+#define RT5682_CBJ_JD_TEST_MODE			(0x1 << 6)
+
+/* DAC1 Digital Volume (0x0019) */
+#define RT5682_DAC_L1_VOL_MASK			(0xff << 8)
+#define RT5682_DAC_L1_VOL_SFT			8
+#define RT5682_DAC_R1_VOL_MASK			(0xff)
+#define RT5682_DAC_R1_VOL_SFT			0
+
+/* ADC Digital Volume Control (0x001c) */
+#define RT5682_ADC_L_VOL_MASK			(0x7f << 8)
+#define RT5682_ADC_L_VOL_SFT			8
+#define RT5682_ADC_R_VOL_MASK			(0x7f)
+#define RT5682_ADC_R_VOL_SFT			0
+
+/* Stereo1 ADC Boost Gain Control (0x001f) */
+#define RT5682_STO1_ADC_L_BST_MASK		(0x3 << 14)
+#define RT5682_STO1_ADC_L_BST_SFT		14
+#define RT5682_STO1_ADC_R_BST_MASK		(0x3 << 12)
+#define RT5682_STO1_ADC_R_BST_SFT		12
+
+/* Sidetone Control (0x0024) */
+#define RT5682_ST_SRC_SEL			(0x1 << 8)
+#define RT5682_ST_SRC_SFT			8
+#define RT5682_ST_EN_MASK			(0x1 << 6)
+#define RT5682_ST_DIS				(0x0 << 6)
+#define RT5682_ST_EN				(0x1 << 6)
+#define RT5682_ST_EN_SFT			6
+
+/* Stereo1 ADC Mixer Control (0x0026) */
+#define RT5682_M_STO1_ADC_L1			(0x1 << 15)
+#define RT5682_M_STO1_ADC_L1_SFT		15
+#define RT5682_M_STO1_ADC_L2			(0x1 << 14)
+#define RT5682_M_STO1_ADC_L2_SFT		14
+#define RT5682_STO1_ADC1L_SRC_MASK		(0x1 << 13)
+#define RT5682_STO1_ADC1L_SRC_SFT		13
+#define RT5682_STO1_ADC1_SRC_ADC		(0x1 << 13)
+#define RT5682_STO1_ADC1_SRC_DACMIX		(0x0 << 13)
+#define RT5682_STO1_ADC2L_SRC_MASK		(0x1 << 12)
+#define RT5682_STO1_ADC2L_SRC_SFT		12
+#define RT5682_STO1_ADCL_SRC_MASK		(0x3 << 10)
+#define RT5682_STO1_ADCL_SRC_SFT		10
+#define RT5682_STO1_DD_L_SRC_MASK		(0x1 << 9)
+#define RT5682_STO1_DD_L_SRC_SFT		9
+#define RT5682_STO1_DMIC_SRC_MASK		(0x1 << 8)
+#define RT5682_STO1_DMIC_SRC_SFT		8
+#define RT5682_STO1_DMIC_SRC_DMIC2		(0x1 << 8)
+#define RT5682_STO1_DMIC_SRC_DMIC1		(0x0 << 8)
+#define RT5682_M_STO1_ADC_R1			(0x1 << 7)
+#define RT5682_M_STO1_ADC_R1_SFT		7
+#define RT5682_M_STO1_ADC_R2			(0x1 << 6)
+#define RT5682_M_STO1_ADC_R2_SFT		6
+#define RT5682_STO1_ADC1R_SRC_MASK		(0x1 << 5)
+#define RT5682_STO1_ADC1R_SRC_SFT		5
+#define RT5682_STO1_ADC2R_SRC_MASK		(0x1 << 4)
+#define RT5682_STO1_ADC2R_SRC_SFT		4
+#define RT5682_STO1_ADCR_SRC_MASK		(0x3 << 2)
+#define RT5682_STO1_ADCR_SRC_SFT		2
+
+/* ADC Mixer to DAC Mixer Control (0x0029) */
+#define RT5682_M_ADCMIX_L			(0x1 << 15)
+#define RT5682_M_ADCMIX_L_SFT			15
+#define RT5682_M_DAC1_L				(0x1 << 14)
+#define RT5682_M_DAC1_L_SFT			14
+#define RT5682_DAC1_R_SEL_MASK			(0x1 << 10)
+#define RT5682_DAC1_R_SEL_SFT			10
+#define RT5682_DAC1_L_SEL_MASK			(0x1 << 8)
+#define RT5682_DAC1_L_SEL_SFT			8
+#define RT5682_M_ADCMIX_R			(0x1 << 7)
+#define RT5682_M_ADCMIX_R_SFT			7
+#define RT5682_M_DAC1_R				(0x1 << 6)
+#define RT5682_M_DAC1_R_SFT			6
+
+/* Stereo1 DAC Mixer Control (0x002a) */
+#define RT5682_M_DAC_L1_STO_L			(0x1 << 15)
+#define RT5682_M_DAC_L1_STO_L_SFT		15
+#define RT5682_G_DAC_L1_STO_L_MASK		(0x1 << 14)
+#define RT5682_G_DAC_L1_STO_L_SFT		14
+#define RT5682_M_DAC_R1_STO_L			(0x1 << 13)
+#define RT5682_M_DAC_R1_STO_L_SFT		13
+#define RT5682_G_DAC_R1_STO_L_MASK		(0x1 << 12)
+#define RT5682_G_DAC_R1_STO_L_SFT		12
+#define RT5682_M_DAC_L1_STO_R			(0x1 << 7)
+#define RT5682_M_DAC_L1_STO_R_SFT		7
+#define RT5682_G_DAC_L1_STO_R_MASK		(0x1 << 6)
+#define RT5682_G_DAC_L1_STO_R_SFT		6
+#define RT5682_M_DAC_R1_STO_R			(0x1 << 5)
+#define RT5682_M_DAC_R1_STO_R_SFT		5
+#define RT5682_G_DAC_R1_STO_R_MASK		(0x1 << 4)
+#define RT5682_G_DAC_R1_STO_R_SFT		4
+
+/* Analog DAC1 Input Source Control (0x002b) */
+#define RT5682_M_ST_STO_L			(0x1 << 9)
+#define RT5682_M_ST_STO_L_SFT			9
+#define RT5682_M_ST_STO_R			(0x1 << 8)
+#define RT5682_M_ST_STO_R_SFT			8
+#define RT5682_DAC_L1_SRC_MASK			(0x3 << 4)
+#define RT5682_A_DACL1_SFT			4
+#define RT5682_DAC_R1_SRC_MASK			(0x3)
+#define RT5682_A_DACR1_SFT			0
+
+/* Digital Interface Data Control (0x0030) */
+#define RT5682_IF2_ADC_SEL_MASK			(0x3 << 0)
+#define RT5682_IF2_ADC_SEL_SFT			0
+
+/* REC Left Mixer Control 2 (0x003c) */
+#define RT5682_G_CBJ_RM1_L			(0x7 << 10)
+#define RT5682_G_CBJ_RM1_L_SFT			10
+#define RT5682_M_CBJ_RM1_L			(0x1 << 7)
+#define RT5682_M_CBJ_RM1_L_SFT			7
+
+/* Power Management for Digital 1 (0x0061) */
+#define RT5682_PWR_I2S1				(0x1 << 15)
+#define RT5682_PWR_I2S1_BIT			15
+#define RT5682_PWR_I2S2				(0x1 << 14)
+#define RT5682_PWR_I2S2_BIT			14
+#define RT5682_PWR_DAC_L1			(0x1 << 11)
+#define RT5682_PWR_DAC_L1_BIT			11
+#define RT5682_PWR_DAC_R1			(0x1 << 10)
+#define RT5682_PWR_DAC_R1_BIT			10
+#define RT5682_PWR_LDO				(0x1 << 8)
+#define RT5682_PWR_LDO_BIT			8
+#define RT5682_PWR_ADC_L1			(0x1 << 4)
+#define RT5682_PWR_ADC_L1_BIT			4
+#define RT5682_PWR_ADC_R1			(0x1 << 3)
+#define RT5682_PWR_ADC_R1_BIT			3
+#define RT5682_DIG_GATE_CTRL			(0x1 << 0)
+#define RT5682_DIG_GATE_CTRL_SFT		0
+
+
+/* Power Management for Digital 2 (0x0062) */
+#define RT5682_PWR_ADC_S1F			(0x1 << 15)
+#define RT5682_PWR_ADC_S1F_BIT			15
+#define RT5682_PWR_DAC_S1F			(0x1 << 10)
+#define RT5682_PWR_DAC_S1F_BIT			10
+
+/* Power Management for Analog 1 (0x0063) */
+#define RT5682_PWR_VREF1			(0x1 << 15)
+#define RT5682_PWR_VREF1_BIT			15
+#define RT5682_PWR_FV1				(0x1 << 14)
+#define RT5682_PWR_FV1_BIT			14
+#define RT5682_PWR_VREF2			(0x1 << 13)
+#define RT5682_PWR_VREF2_BIT			13
+#define RT5682_PWR_FV2				(0x1 << 12)
+#define RT5682_PWR_FV2_BIT			12
+#define RT5682_LDO1_DBG_MASK			(0x3 << 10)
+#define RT5682_PWR_MB				(0x1 << 9)
+#define RT5682_PWR_MB_BIT			9
+#define RT5682_PWR_BG				(0x1 << 7)
+#define RT5682_PWR_BG_BIT			7
+#define RT5682_LDO1_BYPASS_MASK			(0x1 << 6)
+#define RT5682_LDO1_BYPASS			(0x1 << 6)
+#define RT5682_LDO1_NOT_BYPASS			(0x0 << 6)
+#define RT5682_PWR_MA_BIT			6
+#define RT5682_LDO1_DVO_MASK			(0x3 << 4)
+#define RT5682_LDO1_DVO_09			(0x0 << 4)
+#define RT5682_LDO1_DVO_10			(0x1 << 4)
+#define RT5682_LDO1_DVO_12			(0x2 << 4)
+#define RT5682_LDO1_DVO_14			(0x3 << 4)
+#define RT5682_HP_DRIVER_MASK			(0x3 << 2)
+#define RT5682_HP_DRIVER_1X			(0x0 << 2)
+#define RT5682_HP_DRIVER_3X			(0x1 << 2)
+#define RT5682_HP_DRIVER_5X			(0x3 << 2)
+#define RT5682_PWR_HA_L				(0x1 << 1)
+#define RT5682_PWR_HA_L_BIT			1
+#define RT5682_PWR_HA_R				(0x1 << 0)
+#define RT5682_PWR_HA_R_BIT			0
+
+/* Power Management for Analog 2 (0x0064) */
+#define RT5682_PWR_MB1				(0x1 << 11)
+#define RT5682_PWR_MB1_PWR_DOWN			(0x0 << 11)
+#define RT5682_PWR_MB1_BIT			11
+#define RT5682_PWR_MB2				(0x1 << 10)
+#define RT5682_PWR_MB2_PWR_DOWN			(0x0 << 10)
+#define RT5682_PWR_MB2_BIT			10
+#define RT5682_PWR_JDH				(0x1 << 3)
+#define RT5682_PWR_JDH_BIT			3
+#define RT5682_PWR_JDL				(0x1 << 2)
+#define RT5682_PWR_JDL_BIT			2
+#define RT5682_PWR_RM1_L			(0x1 << 1)
+#define RT5682_PWR_RM1_L_BIT			1
+
+/* Power Management for Analog 3 (0x0065) */
+#define RT5682_PWR_CBJ				(0x1 << 9)
+#define RT5682_PWR_CBJ_BIT			9
+#define RT5682_PWR_PLL				(0x1 << 6)
+#define RT5682_PWR_PLL_BIT			6
+#define RT5682_PWR_PLL2B			(0x1 << 5)
+#define RT5682_PWR_PLL2B_BIT			5
+#define RT5682_PWR_PLL2F			(0x1 << 4)
+#define RT5682_PWR_PLL2F_BIT			4
+#define RT5682_PWR_LDO2				(0x1 << 2)
+#define RT5682_PWR_LDO2_BIT			2
+#define RT5682_PWR_DET_SPKVDD			(0x1 << 1)
+#define RT5682_PWR_DET_SPKVDD_BIT		1
+
+/* Power Management for Mixer (0x0066) */
+#define RT5682_PWR_STO1_DAC_L			(0x1 << 5)
+#define RT5682_PWR_STO1_DAC_L_BIT		5
+#define RT5682_PWR_STO1_DAC_R			(0x1 << 4)
+#define RT5682_PWR_STO1_DAC_R_BIT		4
+
+/* MCLK and System Clock Detection Control (0x006b) */
+#define RT5682_SYS_CLK_DET			(0x1 << 15)
+#define RT5682_SYS_CLK_DET_SFT			15
+#define RT5682_PLL1_CLK_DET			(0x1 << 14)
+#define RT5682_PLL1_CLK_DET_SFT			14
+#define RT5682_PLL2_CLK_DET			(0x1 << 13)
+#define RT5682_PLL2_CLK_DET_SFT			13
+#define RT5682_POW_CLK_DET2_SFT			8
+#define RT5682_POW_CLK_DET_SFT			0
+
+/* Digital Microphone Control 1 (0x006e) */
+#define RT5682_DMIC_1_EN_MASK			(0x1 << 15)
+#define RT5682_DMIC_1_EN_SFT			15
+#define RT5682_DMIC_1_DIS			(0x0 << 15)
+#define RT5682_DMIC_1_EN			(0x1 << 15)
+#define RT5682_DMIC_1_DP_MASK			(0x3 << 4)
+#define RT5682_DMIC_1_DP_SFT			4
+#define RT5682_DMIC_1_DP_GPIO2			(0x0 << 4)
+#define RT5682_DMIC_1_DP_GPIO5			(0x1 << 4)
+#define RT5682_DMIC_CLK_MASK			(0xf << 0)
+#define RT5682_DMIC_CLK_SFT			0
+
+/* I2S1 Audio Serial Data Port Control (0x0070) */
+#define RT5682_SEL_ADCDAT_MASK			(0x1 << 15)
+#define RT5682_SEL_ADCDAT_OUT			(0x0 << 15)
+#define RT5682_SEL_ADCDAT_IN			(0x1 << 15)
+#define RT5682_SEL_ADCDAT_SFT			15
+#define RT5682_I2S1_TX_CHL_MASK			(0x7 << 12)
+#define RT5682_I2S1_TX_CHL_SFT			12
+#define RT5682_I2S1_TX_CHL_16			(0x0 << 12)
+#define RT5682_I2S1_TX_CHL_20			(0x1 << 12)
+#define RT5682_I2S1_TX_CHL_24			(0x2 << 12)
+#define RT5682_I2S1_TX_CHL_32			(0x3 << 12)
+#define RT5682_I2S1_TX_CHL_8			(0x4 << 12)
+#define RT5682_I2S1_RX_CHL_MASK			(0x7 << 8)
+#define RT5682_I2S1_RX_CHL_SFT			8
+#define RT5682_I2S1_RX_CHL_16			(0x0 << 8)
+#define RT5682_I2S1_RX_CHL_20			(0x1 << 8)
+#define RT5682_I2S1_RX_CHL_24			(0x2 << 8)
+#define RT5682_I2S1_RX_CHL_32			(0x3 << 8)
+#define RT5682_I2S1_RX_CHL_8			(0x4 << 8)
+#define RT5682_I2S1_MONO_MASK			(0x1 << 7)
+#define RT5682_I2S1_MONO_EN			(0x1 << 7)
+#define RT5682_I2S1_MONO_DIS			(0x0 << 7)
+#define RT5682_I2S2_MONO_MASK			(0x1 << 6)
+#define RT5682_I2S2_MONO_EN			(0x1 << 6)
+#define RT5682_I2S2_MONO_DIS			(0x0 << 6)
+#define RT5682_I2S1_DL_MASK			(0x7 << 4)
+#define RT5682_I2S1_DL_SFT			4
+#define RT5682_I2S1_DL_16			(0x0 << 4)
+#define RT5682_I2S1_DL_20			(0x1 << 4)
+#define RT5682_I2S1_DL_24			(0x2 << 4)
+#define RT5682_I2S1_DL_32			(0x3 << 4)
+#define RT5682_I2S1_DL_8			(0x4 << 4)
+
+/* I2S1/2 Audio Serial Data Port Control (0x0070)(0x0071) */
+#define RT5682_I2S2_MS_MASK			(0x1 << 15)
+#define RT5682_I2S2_MS_SFT			15
+#define RT5682_I2S2_MS_M			(0x0 << 15)
+#define RT5682_I2S2_MS_S			(0x1 << 15)
+#define RT5682_I2S2_PIN_CFG_MASK		(0x1 << 14)
+#define RT5682_I2S2_PIN_CFG_SFT			14
+#define RT5682_I2S2_CLK_SEL_MASK		(0x1 << 11)
+#define RT5682_I2S2_CLK_SEL_SFT			11
+#define RT5682_I2S2_OUT_MASK			(0x1 << 9)
+#define RT5682_I2S2_OUT_SFT			9
+#define RT5682_I2S2_OUT_UM			(0x0 << 9)
+#define RT5682_I2S2_OUT_M			(0x1 << 9)
+#define RT5682_I2S_BP_MASK			(0x1 << 8)
+#define RT5682_I2S_BP_SFT			8
+#define RT5682_I2S_BP_NOR			(0x0 << 8)
+#define RT5682_I2S_BP_INV			(0x1 << 8)
+#define RT5682_I2S2_MONO_EN			(0x1 << 6)
+#define RT5682_I2S2_MONO_DIS			(0x0 << 6)
+#define RT5682_I2S2_DL_MASK			(0x3 << 4)
+#define RT5682_I2S2_DL_SFT			4
+#define RT5682_I2S2_DL_16			(0x0 << 4)
+#define RT5682_I2S2_DL_20			(0x1 << 4)
+#define RT5682_I2S2_DL_24			(0x2 << 4)
+#define RT5682_I2S2_DL_8			(0x3 << 4)
+#define RT5682_I2S_DF_MASK			(0x7)
+#define RT5682_I2S_DF_SFT			0
+#define RT5682_I2S_DF_I2S			(0x0)
+#define RT5682_I2S_DF_LEFT			(0x1)
+#define RT5682_I2S_DF_PCM_A			(0x2)
+#define RT5682_I2S_DF_PCM_B			(0x3)
+#define RT5682_I2S_DF_PCM_A_N			(0x6)
+#define RT5682_I2S_DF_PCM_B_N			(0x7)
+
+/* ADC/DAC Clock Control 1 (0x0073) */
+#define RT5682_ADC_OSR_MASK			(0xf << 12)
+#define RT5682_ADC_OSR_SFT			12
+#define RT5682_ADC_OSR_D_1			(0x0 << 12)
+#define RT5682_ADC_OSR_D_2			(0x1 << 12)
+#define RT5682_ADC_OSR_D_4			(0x2 << 12)
+#define RT5682_ADC_OSR_D_6			(0x3 << 12)
+#define RT5682_ADC_OSR_D_8			(0x4 << 12)
+#define RT5682_ADC_OSR_D_12			(0x5 << 12)
+#define RT5682_ADC_OSR_D_16			(0x6 << 12)
+#define RT5682_ADC_OSR_D_24			(0x7 << 12)
+#define RT5682_ADC_OSR_D_32			(0x8 << 12)
+#define RT5682_ADC_OSR_D_48			(0x9 << 12)
+#define RT5682_I2S_M_DIV_MASK			(0xf << 12)
+#define RT5682_I2S_M_DIV_SFT			8
+#define RT5682_I2S_M_D_1			(0x0 << 8)
+#define RT5682_I2S_M_D_2			(0x1 << 8)
+#define RT5682_I2S_M_D_3			(0x2 << 8)
+#define RT5682_I2S_M_D_4			(0x3 << 8)
+#define RT5682_I2S_M_D_6			(0x4 << 8)
+#define RT5682_I2S_M_D_8			(0x5 << 8)
+#define RT5682_I2S_M_D_12			(0x6 << 8)
+#define RT5682_I2S_M_D_16			(0x7 << 8)
+#define RT5682_I2S_M_D_24			(0x8 << 8)
+#define RT5682_I2S_M_D_32			(0x9 << 8)
+#define RT5682_I2S_M_D_48			(0x10 << 8)
+#define RT5682_I2S_CLK_SRC_MASK			(0x7 << 4)
+#define RT5682_I2S_CLK_SRC_SFT			4
+#define RT5682_I2S_CLK_SRC_MCLK			(0x0 << 4)
+#define RT5682_I2S_CLK_SRC_PLL1			(0x1 << 4)
+#define RT5682_I2S_CLK_SRC_PLL2			(0x2 << 4)
+#define RT5682_I2S_CLK_SRC_SDW			(0x3 << 4)
+#define RT5682_I2S_CLK_SRC_RCCLK		(0x4 << 4) /* 25M */
+#define RT5682_DAC_OSR_MASK			(0xf << 0)
+#define RT5682_DAC_OSR_SFT			0
+#define RT5682_DAC_OSR_D_1			(0x0 << 0)
+#define RT5682_DAC_OSR_D_2			(0x1 << 0)
+#define RT5682_DAC_OSR_D_4			(0x2 << 0)
+#define RT5682_DAC_OSR_D_6			(0x3 << 0)
+#define RT5682_DAC_OSR_D_8			(0x4 << 0)
+#define RT5682_DAC_OSR_D_12			(0x5 << 0)
+#define RT5682_DAC_OSR_D_16			(0x6 << 0)
+#define RT5682_DAC_OSR_D_24			(0x7 << 0)
+#define RT5682_DAC_OSR_D_32			(0x8 << 0)
+#define RT5682_DAC_OSR_D_48			(0x9 << 0)
+
+/* ADC/DAC Clock Control 2 (0x0074) */
+#define RT5682_I2S2_BCLK_MS2_MASK		(0x1 << 11)
+#define RT5682_I2S2_BCLK_MS2_SFT		11
+#define RT5682_I2S2_BCLK_MS2_32			(0x0 << 11)
+#define RT5682_I2S2_BCLK_MS2_64			(0x1 << 11)
+
+
+/* TDM control 1 (0x0079) */
+#define RT5682_TDM_TX_CH_MASK			(0x3 << 12)
+#define RT5682_TDM_TX_CH_2			(0x0 << 12)
+#define RT5682_TDM_TX_CH_4			(0x1 << 12)
+#define RT5682_TDM_TX_CH_6			(0x2 << 12)
+#define RT5682_TDM_TX_CH_8			(0x3 << 12)
+#define RT5682_TDM_RX_CH_MASK			(0x3 << 8)
+#define RT5682_TDM_RX_CH_2			(0x0 << 8)
+#define RT5682_TDM_RX_CH_4			(0x1 << 8)
+#define RT5682_TDM_RX_CH_6			(0x2 << 8)
+#define RT5682_TDM_RX_CH_8			(0x3 << 8)
+#define RT5682_TDM_ADC_LCA_MASK			(0xf << 4)
+#define RT5682_TDM_ADC_LCA_SFT			4
+#define RT5682_TDM_ADC_DL_SFT			0
+
+/* TDM control 2 (0x007a) */
+#define RT5682_IF1_ADC1_SEL_SFT			14
+#define RT5682_IF1_ADC2_SEL_SFT			12
+#define RT5682_IF1_ADC3_SEL_SFT			10
+#define RT5682_IF1_ADC4_SEL_SFT			8
+#define RT5682_TDM_ADC_SEL_SFT			4
+
+/* TDM control 3 (0x007b) */
+#define RT5682_TDM_EN				(0x1 << 7)
+
+/* TDM/I2S control (0x007e) */
+#define RT5682_TDM_S_BP_MASK			(0x1 << 15)
+#define RT5682_TDM_S_BP_SFT			15
+#define RT5682_TDM_S_BP_NOR			(0x0 << 15)
+#define RT5682_TDM_S_BP_INV			(0x1 << 15)
+#define RT5682_TDM_S_LP_MASK			(0x1 << 14)
+#define RT5682_TDM_S_LP_SFT			14
+#define RT5682_TDM_S_LP_NOR			(0x0 << 14)
+#define RT5682_TDM_S_LP_INV			(0x1 << 14)
+#define RT5682_TDM_DF_MASK			(0x7 << 11)
+#define RT5682_TDM_DF_SFT			11
+#define RT5682_TDM_DF_I2S			(0x0 << 11)
+#define RT5682_TDM_DF_LEFT			(0x1 << 11)
+#define RT5682_TDM_DF_PCM_A			(0x2 << 11)
+#define RT5682_TDM_DF_PCM_B			(0x3 << 11)
+#define RT5682_TDM_DF_PCM_A_N			(0x6 << 11)
+#define RT5682_TDM_DF_PCM_B_N			(0x7 << 11)
+#define RT5682_TDM_CL_MASK			(0x3 << 4)
+#define RT5682_TDM_CL_16			(0x0 << 4)
+#define RT5682_TDM_CL_20			(0x1 << 4)
+#define RT5682_TDM_CL_24			(0x2 << 4)
+#define RT5682_TDM_CL_32			(0x3 << 4)
+#define RT5682_TDM_M_BP_MASK			(0x1 << 2)
+#define RT5682_TDM_M_BP_SFT			2
+#define RT5682_TDM_M_BP_NOR			(0x0 << 2)
+#define RT5682_TDM_M_BP_INV			(0x1 << 2)
+#define RT5682_TDM_M_LP_MASK			(0x1 << 1)
+#define RT5682_TDM_M_LP_SFT			1
+#define RT5682_TDM_M_LP_NOR			(0x0 << 1)
+#define RT5682_TDM_M_LP_INV			(0x1 << 1)
+#define RT5682_TDM_MS_MASK			(0x1 << 0)
+#define RT5682_TDM_MS_SFT			0
+#define RT5682_TDM_MS_M				(0x0 << 0)
+#define RT5682_TDM_MS_S				(0x1 << 0)
+
+/* Global Clock Control (0x0080) */
+#define RT5682_SCLK_SRC_MASK			(0x7 << 13)
+#define RT5682_SCLK_SRC_SFT			13
+#define RT5682_SCLK_SRC_MCLK			(0x0 << 13)
+#define RT5682_SCLK_SRC_PLL1			(0x1 << 13)
+#define RT5682_SCLK_SRC_PLL2			(0x2 << 13)
+#define RT5682_SCLK_SRC_SDW			(0x3 << 13)
+#define RT5682_SCLK_SRC_RCCLK			(0x4 << 13)
+#define RT5682_PLL1_SRC_MASK			(0x3 << 10)
+#define RT5682_PLL1_SRC_SFT			10
+#define RT5682_PLL1_SRC_MCLK			(0x0 << 10)
+#define RT5682_PLL1_SRC_BCLK1			(0x1 << 10)
+#define RT5682_PLL1_SRC_SDW			(0x2 << 10)
+#define RT5682_PLL1_SRC_RC			(0x3 << 10)
+#define RT5682_PLL2_SRC_MASK			(0x3 << 8)
+#define RT5682_PLL2_SRC_SFT			8
+#define RT5682_PLL2_SRC_MCLK			(0x0 << 8)
+#define RT5682_PLL2_SRC_BCLK1			(0x1 << 8)
+#define RT5682_PLL2_SRC_SDW			(0x2 << 8)
+#define RT5682_PLL2_SRC_RC			(0x3 << 8)
+
+
+
+#define RT5682_PLL_INP_MAX			40000000
+#define RT5682_PLL_INP_MIN			256000
+/* PLL M/N/K Code Control 1 (0x0081) */
+#define RT5682_PLL_N_MAX			0x001ff
+#define RT5682_PLL_N_MASK			(RT5682_PLL_N_MAX << 7)
+#define RT5682_PLL_N_SFT			7
+#define RT5682_PLL_K_MAX			0x001f
+#define RT5682_PLL_K_MASK			(RT5682_PLL_K_MAX)
+#define RT5682_PLL_K_SFT			0
+
+/* PLL M/N/K Code Control 2 (0x0082) */
+#define RT5682_PLL_M_MAX			0x00f
+#define RT5682_PLL_M_MASK			(RT5682_PLL_M_MAX << 12)
+#define RT5682_PLL_M_SFT			12
+#define RT5682_PLL_M_BP				(0x1 << 11)
+#define RT5682_PLL_M_BP_SFT			11
+#define RT5682_PLL_K_BP				(0x1 << 10)
+#define RT5682_PLL_K_BP_SFT			10
+#define RT5682_PLL_RST				(0x1 << 1)
+
+/* PLL tracking mode 1 (0x0083) */
+#define RT5682_DA_ASRC_MASK			(0x1 << 13)
+#define RT5682_DA_ASRC_SFT			13
+#define RT5682_DAC_STO1_ASRC_MASK		(0x1 << 12)
+#define RT5682_DAC_STO1_ASRC_SFT		12
+#define RT5682_AD_ASRC_MASK			(0x1 << 8)
+#define RT5682_AD_ASRC_SFT			8
+#define RT5682_AD_ASRC_SEL_MASK			(0x1 << 4)
+#define RT5682_AD_ASRC_SEL_SFT			4
+#define RT5682_DMIC_ASRC_MASK			(0x1 << 3)
+#define RT5682_DMIC_ASRC_SFT			3
+#define RT5682_ADC_STO1_ASRC_MASK		(0x1 << 2)
+#define RT5682_ADC_STO1_ASRC_SFT		2
+#define RT5682_DA_ASRC_SEL_MASK			(0x1 << 0)
+#define RT5682_DA_ASRC_SEL_SFT			0
+
+/* PLL tracking mode 2 3 (0x0084)(0x0085)*/
+#define RT5682_FILTER_CLK_SEL_MASK		(0x7 << 12)
+#define RT5682_FILTER_CLK_SEL_SFT		12
+#define RT5682_FILTER_CLK_DIV_MASK		(0xf << 8)
+#define RT5682_FILTER_CLK_DIV_SFT		8
+
+/* ASRC Control 4 (0x0086) */
+#define RT5682_ASRCIN_FTK_N1_MASK		(0x3 << 14)
+#define RT5682_ASRCIN_FTK_N1_SFT		14
+#define RT5682_ASRCIN_FTK_N2_MASK		(0x3 << 12)
+#define RT5682_ASRCIN_FTK_N2_SFT		12
+#define RT5682_ASRCIN_FTK_M1_MASK		(0x7 << 8)
+#define RT5682_ASRCIN_FTK_M1_SFT		8
+#define RT5682_ASRCIN_FTK_M2_MASK		(0x7 << 4)
+#define RT5682_ASRCIN_FTK_M2_SFT		4
+
+/* SoundWire reference clk (0x008d) */
+#define RT5682_PLL2_OUT_MASK			(0x1 << 8)
+#define RT5682_PLL2_OUT_98M			(0x0 << 8)
+#define RT5682_PLL2_OUT_49M			(0x1 << 8)
+#define RT5682_SDW_REF_2_MASK			(0xf << 4)
+#define RT5682_SDW_REF_2_SFT			4
+#define RT5682_SDW_REF_2_48K			(0x0 << 4)
+#define RT5682_SDW_REF_2_96K			(0x1 << 4)
+#define RT5682_SDW_REF_2_192K			(0x2 << 4)
+#define RT5682_SDW_REF_2_32K			(0x3 << 4)
+#define RT5682_SDW_REF_2_24K			(0x4 << 4)
+#define RT5682_SDW_REF_2_16K			(0x5 << 4)
+#define RT5682_SDW_REF_2_12K			(0x6 << 4)
+#define RT5682_SDW_REF_2_8K			(0x7 << 4)
+#define RT5682_SDW_REF_2_44K			(0x8 << 4)
+#define RT5682_SDW_REF_2_88K			(0x9 << 4)
+#define RT5682_SDW_REF_2_176K			(0xa << 4)
+#define RT5682_SDW_REF_2_353K			(0xb << 4)
+#define RT5682_SDW_REF_2_22K			(0xc << 4)
+#define RT5682_SDW_REF_2_384K			(0xd << 4)
+#define RT5682_SDW_REF_2_11K			(0xe << 4)
+#define RT5682_SDW_REF_1_MASK			(0xf << 0)
+#define RT5682_SDW_REF_1_SFT			0
+#define RT5682_SDW_REF_1_48K			(0x0 << 0)
+#define RT5682_SDW_REF_1_96K			(0x1 << 0)
+#define RT5682_SDW_REF_1_192K			(0x2 << 0)
+#define RT5682_SDW_REF_1_32K			(0x3 << 0)
+#define RT5682_SDW_REF_1_24K			(0x4 << 0)
+#define RT5682_SDW_REF_1_16K			(0x5 << 0)
+#define RT5682_SDW_REF_1_12K			(0x6 << 0)
+#define RT5682_SDW_REF_1_8K			(0x7 << 0)
+#define RT5682_SDW_REF_1_44K			(0x8 << 0)
+#define RT5682_SDW_REF_1_88K			(0x9 << 0)
+#define RT5682_SDW_REF_1_176K			(0xa << 0)
+#define RT5682_SDW_REF_1_353K			(0xb << 0)
+#define RT5682_SDW_REF_1_22K			(0xc << 0)
+#define RT5682_SDW_REF_1_384K			(0xd << 0)
+#define RT5682_SDW_REF_1_11K			(0xe << 0)
+
+/* Depop Mode Control 1 (0x008e) */
+#define RT5682_PUMP_EN				(0x1 << 3)
+#define RT5682_PUMP_EN_SFT				3
+#define RT5682_CAPLESS_EN			(0x1 << 0)
+#define RT5682_CAPLESS_EN_SFT			0
+
+/* Depop Mode Control 2 (0x8f) */
+#define RT5682_RAMP_MASK			(0x1 << 12)
+#define RT5682_RAMP_SFT				12
+#define RT5682_RAMP_DIS				(0x0 << 12)
+#define RT5682_RAMP_EN				(0x1 << 12)
+#define RT5682_BPS_MASK				(0x1 << 11)
+#define RT5682_BPS_SFT				11
+#define RT5682_BPS_DIS				(0x0 << 11)
+#define RT5682_BPS_EN				(0x1 << 11)
+#define RT5682_FAST_UPDN_MASK			(0x1 << 10)
+#define RT5682_FAST_UPDN_SFT			10
+#define RT5682_FAST_UPDN_DIS			(0x0 << 10)
+#define RT5682_FAST_UPDN_EN			(0x1 << 10)
+#define RT5682_VLO_MASK				(0x1 << 7)
+#define RT5682_VLO_SFT				7
+#define RT5682_VLO_3V				(0x0 << 7)
+#define RT5682_VLO_33V				(0x1 << 7)
+
+/* HPOUT charge pump 1 (0x0091) */
+#define RT5682_OSW_L_MASK			(0x1 << 11)
+#define RT5682_OSW_L_SFT			11
+#define RT5682_OSW_L_DIS			(0x0 << 11)
+#define RT5682_OSW_L_EN				(0x1 << 11)
+#define RT5682_OSW_R_MASK			(0x1 << 10)
+#define RT5682_OSW_R_SFT			10
+#define RT5682_OSW_R_DIS			(0x0 << 10)
+#define RT5682_OSW_R_EN				(0x1 << 10)
+#define RT5682_PM_HP_MASK			(0x3 << 8)
+#define RT5682_PM_HP_SFT			8
+#define RT5682_PM_HP_LV				(0x0 << 8)
+#define RT5682_PM_HP_MV				(0x1 << 8)
+#define RT5682_PM_HP_HV				(0x2 << 8)
+#define RT5682_IB_HP_MASK			(0x3 << 6)
+#define RT5682_IB_HP_SFT			6
+#define RT5682_IB_HP_125IL			(0x0 << 6)
+#define RT5682_IB_HP_25IL			(0x1 << 6)
+#define RT5682_IB_HP_5IL			(0x2 << 6)
+#define RT5682_IB_HP_1IL			(0x3 << 6)
+
+/* Micbias Control1 (0x93) */
+#define RT5682_MIC1_OV_MASK			(0x3 << 14)
+#define RT5682_MIC1_OV_SFT			14
+#define RT5682_MIC1_OV_2V7			(0x0 << 14)
+#define RT5682_MIC1_OV_2V4			(0x1 << 14)
+#define RT5682_MIC1_OV_2V25			(0x3 << 14)
+#define RT5682_MIC1_OV_1V8			(0x4 << 14)
+#define RT5682_MIC1_CLK_MASK			(0x1 << 13)
+#define RT5682_MIC1_CLK_SFT			13
+#define RT5682_MIC1_CLK_DIS			(0x0 << 13)
+#define RT5682_MIC1_CLK_EN			(0x1 << 13)
+#define RT5682_MIC1_OVCD_MASK			(0x1 << 12)
+#define RT5682_MIC1_OVCD_SFT			12
+#define RT5682_MIC1_OVCD_DIS			(0x0 << 12)
+#define RT5682_MIC1_OVCD_EN			(0x1 << 12)
+#define RT5682_MIC1_OVTH_MASK			(0x3 << 10)
+#define RT5682_MIC1_OVTH_SFT			10
+#define RT5682_MIC1_OVTH_768UA			(0x0 << 10)
+#define RT5682_MIC1_OVTH_960UA			(0x1 << 10)
+#define RT5682_MIC1_OVTH_1152UA			(0x2 << 10)
+#define RT5682_MIC1_OVTH_1960UA			(0x3 << 10)
+#define RT5682_MIC2_OV_MASK			(0x3 << 8)
+#define RT5682_MIC2_OV_SFT			8
+#define RT5682_MIC2_OV_2V7			(0x0 << 8)
+#define RT5682_MIC2_OV_2V4			(0x1 << 8)
+#define RT5682_MIC2_OV_2V25			(0x3 << 8)
+#define RT5682_MIC2_OV_1V8			(0x4 << 8)
+#define RT5682_MIC2_CLK_MASK			(0x1 << 7)
+#define RT5682_MIC2_CLK_SFT			7
+#define RT5682_MIC2_CLK_DIS			(0x0 << 7)
+#define RT5682_MIC2_CLK_EN			(0x1 << 7)
+#define RT5682_MIC2_OVTH_MASK			(0x3 << 4)
+#define RT5682_MIC2_OVTH_SFT			4
+#define RT5682_MIC2_OVTH_768UA			(0x0 << 4)
+#define RT5682_MIC2_OVTH_960UA			(0x1 << 4)
+#define RT5682_MIC2_OVTH_1152UA			(0x2 << 4)
+#define RT5682_MIC2_OVTH_1960UA			(0x3 << 4)
+#define RT5682_PWR_MB_MASK			(0x1 << 3)
+#define RT5682_PWR_MB_SFT			3
+#define RT5682_PWR_MB_PD			(0x0 << 3)
+#define RT5682_PWR_MB_PU			(0x1 << 3)
+
+/* Micbias Control2 (0x0094) */
+#define RT5682_PWR_CLK25M_MASK			(0x1 << 9)
+#define RT5682_PWR_CLK25M_SFT			9
+#define RT5682_PWR_CLK25M_PD			(0x0 << 9)
+#define RT5682_PWR_CLK25M_PU			(0x1 << 9)
+#define RT5682_PWR_CLK1M_MASK			(0x1 << 8)
+#define RT5682_PWR_CLK1M_SFT			8
+#define RT5682_PWR_CLK1M_PD			(0x0 << 8)
+#define RT5682_PWR_CLK1M_PU			(0x1 << 8)
+
+/* RC Clock Control (0x009f) */
+#define RT5682_POW_IRQ				(0x1 << 15)
+#define RT5682_POW_JDH				(0x1 << 14)
+#define RT5682_POW_JDL				(0x1 << 13)
+#define RT5682_POW_ANA				(0x1 << 12)
+
+/* I2S Master Mode Clock Control 1 (0x00a0) */
+#define RT5682_CLK_SRC_MCLK			(0x0)
+#define RT5682_CLK_SRC_PLL1			(0x1)
+#define RT5682_CLK_SRC_PLL2			(0x2)
+#define RT5682_CLK_SRC_SDW			(0x3)
+#define RT5682_CLK_SRC_RCCLK			(0x4)
+#define RT5682_I2S_PD_1				(0x0)
+#define RT5682_I2S_PD_2				(0x1)
+#define RT5682_I2S_PD_3				(0x2)
+#define RT5682_I2S_PD_4				(0x3)
+#define RT5682_I2S_PD_6				(0x4)
+#define RT5682_I2S_PD_8				(0x5)
+#define RT5682_I2S_PD_12			(0x6)
+#define RT5682_I2S_PD_16			(0x7)
+#define RT5682_I2S_PD_24			(0x8)
+#define RT5682_I2S_PD_32			(0x9)
+#define RT5682_I2S_PD_48			(0xa)
+#define RT5682_I2S2_SRC_MASK			(0x3 << 4)
+#define RT5682_I2S2_SRC_SFT			4
+#define RT5682_I2S2_M_PD_MASK			(0xf << 0)
+#define RT5682_I2S2_M_PD_SFT			0
+
+/* IRQ Control 1 (0x00b6) */
+#define RT5682_JD1_PULSE_EN_MASK		(0x1 << 10)
+#define RT5682_JD1_PULSE_EN_SFT			10
+#define RT5682_JD1_PULSE_DIS			(0x0 << 10)
+#define RT5682_JD1_PULSE_EN			(0x1 << 10)
+
+/* IRQ Control 2 (0x00b7) */
+#define RT5682_JD1_EN_MASK			(0x1 << 15)
+#define RT5682_JD1_EN_SFT			15
+#define RT5682_JD1_DIS				(0x0 << 15)
+#define RT5682_JD1_EN				(0x1 << 15)
+#define RT5682_JD1_POL_MASK			(0x1 << 13)
+#define RT5682_JD1_POL_NOR			(0x0 << 13)
+#define RT5682_JD1_POL_INV			(0x1 << 13)
+
+/* IRQ Control 3 (0x00b8) */
+#define RT5682_IL_IRQ_MASK			(0x1 << 7)
+#define RT5682_IL_IRQ_DIS			(0x0 << 7)
+#define RT5682_IL_IRQ_EN			(0x1 << 7)
+
+/* GPIO Control 1 (0x00c0) */
+#define RT5682_GP1_PIN_MASK			(0x3 << 14)
+#define RT5682_GP1_PIN_SFT			14
+#define RT5682_GP1_PIN_GPIO1			(0x0 << 14)
+#define RT5682_GP1_PIN_IRQ			(0x1 << 14)
+#define RT5682_GP1_PIN_DMIC_CLK			(0x2 << 14)
+#define RT5682_GP2_PIN_MASK			(0x3 << 12)
+#define RT5682_GP2_PIN_SFT			12
+#define RT5682_GP2_PIN_GPIO2			(0x0 << 12)
+#define RT5682_GP2_PIN_LRCK2			(0x1 << 12)
+#define RT5682_GP2_PIN_DMIC_SDA			(0x2 << 12)
+#define RT5682_GP3_PIN_MASK			(0x3 << 10)
+#define RT5682_GP3_PIN_SFT			10
+#define RT5682_GP3_PIN_GPIO3			(0x0 << 10)
+#define RT5682_GP3_PIN_BCLK2			(0x1 << 10)
+#define RT5682_GP3_PIN_DMIC_CLK			(0x2 << 10)
+#define RT5682_GP4_PIN_MASK			(0x3 << 8)
+#define RT5682_GP4_PIN_SFT			8
+#define RT5682_GP4_PIN_GPIO4			(0x0 << 8)
+#define RT5682_GP4_PIN_ADCDAT1			(0x1 << 8)
+#define RT5682_GP4_PIN_DMIC_CLK			(0x2 << 8)
+#define RT5682_GP4_PIN_ADCDAT2			(0x3 << 8)
+#define RT5682_GP5_PIN_MASK			(0x3 << 6)
+#define RT5682_GP5_PIN_SFT			6
+#define RT5682_GP5_PIN_GPIO5			(0x0 << 6)
+#define RT5682_GP5_PIN_DACDAT1			(0x1 << 6)
+#define RT5682_GP5_PIN_DMIC_SDA			(0x2 << 6)
+#define RT5682_GP6_PIN_MASK			(0x1 << 5)
+#define RT5682_GP6_PIN_SFT			5
+#define RT5682_GP6_PIN_GPIO6			(0x0 << 5)
+#define RT5682_GP6_PIN_LRCK1			(0x1 << 5)
+
+/* GPIO Control 2 (0x00c1)*/
+#define RT5682_GP1_PF_MASK			(0x1 << 15)
+#define RT5682_GP1_PF_IN			(0x0 << 15)
+#define RT5682_GP1_PF_OUT			(0x1 << 15)
+#define RT5682_GP1_OUT_MASK			(0x1 << 14)
+#define RT5682_GP1_OUT_L			(0x0 << 14)
+#define RT5682_GP1_OUT_H			(0x1 << 14)
+#define RT5682_GP2_PF_MASK			(0x1 << 13)
+#define RT5682_GP2_PF_IN			(0x0 << 13)
+#define RT5682_GP2_PF_OUT			(0x1 << 13)
+#define RT5682_GP2_OUT_MASK			(0x1 << 12)
+#define RT5682_GP2_OUT_L			(0x0 << 12)
+#define RT5682_GP2_OUT_H			(0x1 << 12)
+#define RT5682_GP3_PF_MASK			(0x1 << 11)
+#define RT5682_GP3_PF_IN			(0x0 << 11)
+#define RT5682_GP3_PF_OUT			(0x1 << 11)
+#define RT5682_GP3_OUT_MASK			(0x1 << 10)
+#define RT5682_GP3_OUT_L			(0x0 << 10)
+#define RT5682_GP3_OUT_H			(0x1 << 10)
+#define RT5682_GP4_PF_MASK			(0x1 << 9)
+#define RT5682_GP4_PF_IN			(0x0 << 9)
+#define RT5682_GP4_PF_OUT			(0x1 << 9)
+#define RT5682_GP4_OUT_MASK			(0x1 << 8)
+#define RT5682_GP4_OUT_L			(0x0 << 8)
+#define RT5682_GP4_OUT_H			(0x1 << 8)
+#define RT5682_GP5_PF_MASK			(0x1 << 7)
+#define RT5682_GP5_PF_IN			(0x0 << 7)
+#define RT5682_GP5_PF_OUT			(0x1 << 7)
+#define RT5682_GP5_OUT_MASK			(0x1 << 6)
+#define RT5682_GP5_OUT_L			(0x0 << 6)
+#define RT5682_GP5_OUT_H			(0x1 << 6)
+#define RT5682_GP6_PF_MASK			(0x1 << 5)
+#define RT5682_GP6_PF_IN			(0x0 << 5)
+#define RT5682_GP6_PF_OUT			(0x1 << 5)
+#define RT5682_GP6_OUT_MASK			(0x1 << 4)
+#define RT5682_GP6_OUT_L			(0x0 << 4)
+#define RT5682_GP6_OUT_H			(0x1 << 4)
+
+
+/* GPIO Status (0x00c2) */
+#define RT5682_GP6_STA				(0x1 << 6)
+#define RT5682_GP5_STA				(0x1 << 5)
+#define RT5682_GP4_STA				(0x1 << 4)
+#define RT5682_GP3_STA				(0x1 << 3)
+#define RT5682_GP2_STA				(0x1 << 2)
+#define RT5682_GP1_STA				(0x1 << 1)
+
+/* Soft volume and zero cross control 1 (0x00d9) */
+#define RT5682_SV_MASK				(0x1 << 15)
+#define RT5682_SV_SFT				15
+#define RT5682_SV_DIS				(0x0 << 15)
+#define RT5682_SV_EN				(0x1 << 15)
+#define RT5682_ZCD_MASK				(0x1 << 10)
+#define RT5682_ZCD_SFT				10
+#define RT5682_ZCD_PD				(0x0 << 10)
+#define RT5682_ZCD_PU				(0x1 << 10)
+#define RT5682_SV_DLY_MASK			(0xf)
+#define RT5682_SV_DLY_SFT			0
+
+/* Soft volume and zero cross control 2 (0x00da) */
+#define RT5682_ZCD_BST1_CBJ_MASK		(0x1 << 7)
+#define RT5682_ZCD_BST1_CBJ_SFT			7
+#define RT5682_ZCD_BST1_CBJ_DIS			(0x0 << 7)
+#define RT5682_ZCD_BST1_CBJ_EN			(0x1 << 7)
+#define RT5682_ZCD_RECMIX_MASK			(0x1)
+#define RT5682_ZCD_RECMIX_SFT			0
+#define RT5682_ZCD_RECMIX_DIS			(0x0)
+#define RT5682_ZCD_RECMIX_EN			(0x1)
+
+/* 4 Button Inline Command Control 2 (0x00e3) */
+#define RT5682_4BTN_IL_MASK			(0x1 << 15)
+#define RT5682_4BTN_IL_EN			(0x1 << 15)
+#define RT5682_4BTN_IL_DIS			(0x0 << 15)
+#define RT5682_4BTN_IL_RST_MASK			(0x1 << 14)
+#define RT5682_4BTN_IL_NOR			(0x1 << 14)
+#define RT5682_4BTN_IL_RST			(0x0 << 14)
+
+/* Analog JD Control (0x00f0) */
+#define RT5682_JDH_RS_MASK			(0x1 << 4)
+#define RT5682_JDH_NO_PLUG			(0x1 << 4)
+#define RT5682_JDH_PLUG				(0x0 << 4)
+
+/* Chopper and Clock control for DAC (0x013a)*/
+#define RT5682_CKXEN_DAC1_MASK			(0x1 << 13)
+#define RT5682_CKXEN_DAC1_SFT			13
+#define RT5682_CKGEN_DAC1_MASK			(0x1 << 12)
+#define RT5682_CKGEN_DAC1_SFT			12
+
+/* Chopper and Clock control for ADC (0x013b)*/
+#define RT5682_CKXEN_ADC1_MASK			(0x1 << 13)
+#define RT5682_CKXEN_ADC1_SFT			13
+#define RT5682_CKGEN_ADC1_MASK			(0x1 << 12)
+#define RT5682_CKGEN_ADC1_SFT			12
+
+/* Volume test (0x013f)*/
+#define RT5682_SEL_CLK_VOL_MASK			(0x1 << 15)
+#define RT5682_SEL_CLK_VOL_EN			(0x1 << 15)
+#define RT5682_SEL_CLK_VOL_DIS			(0x0 << 15)
+
+/* Test Mode Control 1 (0x0145) */
+#define RT5682_AD2DA_LB_MASK			(0x1 << 10)
+#define RT5682_AD2DA_LB_SFT			10
+
+/* Stereo Noise Gate Control 1 (0x0160) */
+#define RT5682_NG2_EN_MASK			(0x1 << 15)
+#define RT5682_NG2_EN				(0x1 << 15)
+#define RT5682_NG2_DIS				(0x0 << 15)
+
+/* Stereo1 DAC Silence Detection Control (0x0190) */
+#define RT5682_DEB_STO_DAC_MASK			(0x7 << 4)
+#define RT5682_DEB_80_MS			(0x0 << 4)
+
+/* SAR ADC Inline Command Control 1 (0x0210) */
+#define RT5682_SAR_BUTT_DET_MASK		(0x1 << 15)
+#define RT5682_SAR_BUTT_DET_EN			(0x1 << 15)
+#define RT5682_SAR_BUTT_DET_DIS			(0x0 << 15)
+#define RT5682_SAR_BUTDET_MODE_MASK		(0x1 << 14)
+#define RT5682_SAR_BUTDET_POW_SAV		(0x1 << 14)
+#define RT5682_SAR_BUTDET_POW_NORM		(0x0 << 14)
+#define RT5682_SAR_BUTDET_RST_MASK		(0x1 << 13)
+#define RT5682_SAR_BUTDET_RST_NORMAL		(0x1 << 13)
+#define RT5682_SAR_BUTDET_RST			(0x0 << 13)
+#define RT5682_SAR_POW_MASK			(0x1 << 12)
+#define RT5682_SAR_POW_EN			(0x1 << 12)
+#define RT5682_SAR_POW_DIS			(0x0 << 12)
+#define RT5682_SAR_RST_MASK			(0x1 << 11)
+#define RT5682_SAR_RST_NORMAL			(0x1 << 11)
+#define RT5682_SAR_RST				(0x0 << 11)
+#define RT5682_SAR_BYPASS_MASK			(0x1 << 10)
+#define RT5682_SAR_BYPASS_EN			(0x1 << 10)
+#define RT5682_SAR_BYPASS_DIS			(0x0 << 10)
+#define RT5682_SAR_SEL_MB1_MASK			(0x1 << 9)
+#define RT5682_SAR_SEL_MB1_SEL			(0x1 << 9)
+#define RT5682_SAR_SEL_MB1_NOSEL		(0x0 << 9)
+#define RT5682_SAR_SEL_MB2_MASK			(0x1 << 8)
+#define RT5682_SAR_SEL_MB2_SEL			(0x1 << 8)
+#define RT5682_SAR_SEL_MB2_NOSEL		(0x0 << 8)
+#define RT5682_SAR_SEL_MODE_MASK		(0x1 << 7)
+#define RT5682_SAR_SEL_MODE_CMP			(0x1 << 7)
+#define RT5682_SAR_SEL_MODE_ADC			(0x0 << 7)
+#define RT5682_SAR_SEL_MB1_MB2_MASK		(0x1 << 5)
+#define RT5682_SAR_SEL_MB1_MB2_AUTO		(0x1 << 5)
+#define RT5682_SAR_SEL_MB1_MB2_MANU		(0x0 << 5)
+#define RT5682_SAR_SEL_SIGNAL_MASK		(0x1 << 4)
+#define RT5682_SAR_SEL_SIGNAL_AUTO		(0x1 << 4)
+#define RT5682_SAR_SEL_SIGNAL_MANU		(0x0 << 4)
+
+/* SAR ADC Inline Command Control 13 (0x021c) */
+#define RT5682_SAR_SOUR_MASK			(0x3f)
+#define RT5682_SAR_SOUR_BTN			(0x3f)
+#define RT5682_SAR_SOUR_TYPE			(0x0)
+
+
+/* System Clock Source */
+enum {
+	RT5682_SCLK_S_MCLK,
+	RT5682_SCLK_S_PLL1,
+	RT5682_SCLK_S_PLL2,
+	RT5682_SCLK_S_RCCLK,
+};
+
+/* PLL Source */
+enum {
+	RT5682_PLL1_S_MCLK,
+	RT5682_PLL1_S_BCLK1,
+	RT5682_PLL1_S_RCCLK,
+};
+
+enum {
+	RT5682_AIF1,
+	RT5682_AIF2,
+	RT5682_AIFS
+};
+
+/* filter mask */
+enum {
+	RT5682_DA_STEREO1_FILTER = 0x1,
+	RT5682_AD_STEREO1_FILTER = (0x1 << 1),
+};
+
+enum {
+	RT5682_CLK_SEL_SYS,
+	RT5682_CLK_SEL_I2S1_ASRC,
+	RT5682_CLK_SEL_I2S2_ASRC,
+};
+
+int rt5682_sel_asrc_clk_src(struct snd_soc_component *component,
+		unsigned int filter_mask, unsigned int clk_src);
+
+#endif /* __RT5682_H__ */
-- 
cgit v1.2.3


From a7dc662c6a7b9209df600c64b16d33d72dbf56b1 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 17 Jun 2018 15:45:29 +0200
Subject: ASoC: codecs: PCM1789: unconditionally flush work

Work is guaranteed to be initialized on exit. Drop the unnecessary
if statement and always call flush_work.

This fixes a warning seen with clang:
sound/soc/codecs/pcm1789.c:265:13: warning: address of 'priv->work' will
      always evaluate to 'true' [-Wpointer-bool-conversion]
        if (&priv->work)
        ~~   ~~~~~~^~~~

Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/pcm1789.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/soc/codecs/pcm1789.c b/sound/soc/codecs/pcm1789.c
index 21f15219b3ad..8df6447c76a6 100644
--- a/sound/soc/codecs/pcm1789.c
+++ b/sound/soc/codecs/pcm1789.c
@@ -262,8 +262,7 @@ int pcm1789_common_exit(struct device *dev)
 {
 	struct pcm1789_private *priv = dev_get_drvdata(dev);
 
-	if (&priv->work)
-		flush_work(&priv->work);
+	flush_work(&priv->work);
 
 	return 0;
 }
-- 
cgit v1.2.3


From e2b35e468c89000cf3b8b5beb63fd73dfa8a5435 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 12:50:00 +0200
Subject: ASoC: pxa: add binding for pxa2xx-ac97 audio complex

This adds a binding for the Marvell PXA audio complex, available in
pxa2xx and pxa3xx variants.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/sound/marvell,pxa2xx-ac97.txt         | 27 ++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/marvell,pxa2xx-ac97.txt

diff --git a/Documentation/devicetree/bindings/sound/marvell,pxa2xx-ac97.txt b/Documentation/devicetree/bindings/sound/marvell,pxa2xx-ac97.txt
new file mode 100644
index 000000000000..2ea85d5be6a4
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/marvell,pxa2xx-ac97.txt
@@ -0,0 +1,27 @@
+Marvell PXA2xx audio complex
+
+This descriptions matches the AC97 controller found in pxa2xx and pxa3xx series.
+
+Required properties:
+  - compatible: should be one of the following:
+    "marvell,pxa250-ac97"
+    "marvell,pxa270-ac97"
+    "marvell,pxa300-ac97"
+  - reg: device MMIO address space
+  - interrupts: single interrupt generated by AC97 IP
+  - clocks: input clock of the AC97 IP, refer to clock-bindings.txt
+
+Optional properties:
+  - pinctrl-names, pinctrl-0: refer to pinctrl-bindings.txt
+  - reset-gpios: gpio used for AC97 reset, refer to gpio.txt
+
+Example:
+	ac97: sound@40500000 {
+		compatible = "marvell,pxa250-ac97";
+		reg = < 0x40500000 0x1000 >;
+		interrupts = <14>;
+		reset-gpios = <&gpio 113 GPIO_ACTIVE_HIGH>;
+		#sound-dai-cells = <1>;
+		pinctrl-names = "default";
+		pinctrl-0 = < &pmux_ac97_default >;
+	};
-- 
cgit v1.2.3


From a4519526ebbd261e36425fa1c269515ee0648ab2 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 12:50:01 +0200
Subject: ASoC: pxa: add devicetree support

Add the devicetree support, so that the driver can be used in a
devictree platform.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/arm/pxa2xx-ac97-lib.c | 12 ++++++++++++
 sound/soc/pxa/pxa2xx-ac97.c | 12 ++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/sound/arm/pxa2xx-ac97-lib.c b/sound/arm/pxa2xx-ac97-lib.c
index 5950a9e218d9..8eafd3d3dff6 100644
--- a/sound/arm/pxa2xx-ac97-lib.c
+++ b/sound/arm/pxa2xx-ac97-lib.c
@@ -19,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/io.h>
 #include <linux/gpio.h>
+#include <linux/of_gpio.h>
 
 #include <sound/pxa2xx-lib.h>
 
@@ -337,6 +338,17 @@ int pxa2xx_ac97_hw_probe(struct platform_device *dev)
 			dev_err(&dev->dev, "Invalid reset GPIO %d\n",
 				pdata->reset_gpio);
 		}
+	} else if (!pdata && dev->dev.of_node) {
+		pdata = devm_kzalloc(&dev->dev, sizeof(*pdata), GFP_KERNEL);
+		if (!pdata)
+			return -ENOMEM;
+		pdata->reset_gpio = of_get_named_gpio(dev->dev.of_node,
+						      "reset-gpios", 0);
+		if (pdata->reset_gpio == -ENOENT)
+			pdata->reset_gpio = -1;
+		else if (pdata->reset_gpio < 0)
+			return pdata->reset_gpio;
+		reset_gpio = pdata->reset_gpio;
 	} else {
 		if (cpu_is_pxa27x())
 			reset_gpio = 113;
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 803818aabee9..5738a0abcd6a 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -238,6 +238,17 @@ static const struct snd_soc_component_driver pxa_ac97_component = {
 	.name		= "pxa-ac97",
 };
 
+#ifdef CONFIG_OF
+static const struct of_device_id pxa2xx_ac97_dt_ids[] = {
+	{ .compatible = "marvell,pxa250-ac97", },
+	{ .compatible = "marvell,pxa270-ac97", },
+	{ .compatible = "marvell,pxa300-ac97", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, pxa2xx_ac97_dt_ids);
+
+#endif
+
 static int pxa2xx_ac97_dev_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -296,6 +307,7 @@ static struct platform_driver pxa2xx_ac97_driver = {
 #ifdef CONFIG_PM_SLEEP
 		.pm	= &pxa2xx_ac97_pm_ops,
 #endif
+		.of_match_table = of_match_ptr(pxa2xx_ac97_dt_ids),
 	},
 };
 
-- 
cgit v1.2.3


From 7c5dfd549617b87db8e891ff4ecaa4a582b6c4cc Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sat, 16 Jun 2018 01:22:58 +0300
Subject: ASoC: tegra: fix device_node refcounting

tegra_rt5677_probe() gets a couple of device nodes with of_parse_phandle(),
but there is no release of them.

The patch adds the release to tegra_rt5677_remove() and
to error handling paths in the probe.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Reviewed-by: Nicholas Mc Guire <der.herr@hofr.at>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/tegra/tegra_rt5677.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/sound/soc/tegra/tegra_rt5677.c b/sound/soc/tegra/tegra_rt5677.c
index 0e4805c7b4ca..7081f15302cc 100644
--- a/sound/soc/tegra/tegra_rt5677.c
+++ b/sound/soc/tegra/tegra_rt5677.c
@@ -264,13 +264,13 @@ static int tegra_rt5677_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Property 'nvidia,i2s-controller' missing or invalid\n");
 		ret = -EINVAL;
-		goto err;
+		goto err_put_codec_of_node;
 	}
 	tegra_rt5677_dai.platform_of_node = tegra_rt5677_dai.cpu_of_node;
 
 	ret = tegra_asoc_utils_init(&machine->util_data, &pdev->dev);
 	if (ret)
-		goto err;
+		goto err_put_cpu_of_node;
 
 	ret = snd_soc_register_card(card);
 	if (ret) {
@@ -283,6 +283,13 @@ static int tegra_rt5677_probe(struct platform_device *pdev)
 
 err_fini_utils:
 	tegra_asoc_utils_fini(&machine->util_data);
+err_put_cpu_of_node:
+	of_node_put(tegra_rt5677_dai.cpu_of_node);
+	tegra_rt5677_dai.cpu_of_node = NULL;
+	tegra_rt5677_dai.platform_of_node = NULL;
+err_put_codec_of_node:
+	of_node_put(tegra_rt5677_dai.codec_of_node);
+	tegra_rt5677_dai.codec_of_node = NULL;
 err:
 	return ret;
 }
@@ -296,6 +303,12 @@ static int tegra_rt5677_remove(struct platform_device *pdev)
 
 	tegra_asoc_utils_fini(&machine->util_data);
 
+	tegra_rt5677_dai.platform_of_node = NULL;
+	of_node_put(tegra_rt5677_dai.codec_of_node);
+	tegra_rt5677_dai.codec_of_node = NULL;
+	of_node_put(tegra_rt5677_dai.cpu_of_node);
+	tegra_rt5677_dai.cpu_of_node = NULL;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 6cea3590820819049df5945136b8a5acd72ed0f8 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 3 Jun 2018 15:42:31 +0200
Subject: ASoC: Intel: bytcr_rt5640: Add quirk for the Nuvison/TMax TM800W560
 tablet

Add a quirk for the Nuvison/TMax TM800W560 tablet, this tablet uses IN1
for the internal mic rather then the default IN3 and it uses JD2 rather
then JD1 for its not-inverted jack-detect switch.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5640.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 5c4f9ea40f57..8571f41767ef 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -565,6 +565,20 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_DIFF_MIC |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Nuvison/TMax TM800W560 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "TMAX"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "TM800W560L"),
+		},
+		.driver_data = (void *)(BYT_RT5640_IN1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_JD_NOT_INV |
+					BYT_RT5640_DIFF_MIC |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* Pipo W4 */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_BOARD_VENDOR, "AMI Corporation"),
-- 
cgit v1.2.3


From f12a0a3c4cc6f594d7c2ea361f2396ae5c518d2c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 3 Jun 2018 15:42:32 +0200
Subject: ASoC: Intel: bytcr_rt5640: Fix Acer Iconia 8 over-current detect
 threshold

Change the over-current detect threshold on the Acer Iconia 8 from
2000ua to 1500uA, this fixes headset button presses not being detected.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 8571f41767ef..7456566c5648 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -404,7 +404,7 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 		},
 		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
 					BYT_RT5640_JD_SRC_JD1_IN4P |
-					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_TH_1500UA |
 					BYT_RT5640_OVCD_SF_0P75 |
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
-- 
cgit v1.2.3


From 931c4e9a72ae91d59c5332ffb6812911a749da8e Mon Sep 17 00:00:00 2001
From: Janek Kotas <jank@cadence.com>
Date: Mon, 4 Jun 2018 11:24:44 +0000
Subject: spi: cadence: Change usleep_range() to udelay(), for atomic context

The path "spi: cadence: Add usleep_range() for
cdns_spi_fill_tx_fifo()" added a usleep_range() function call,
which cannot be used in atomic context.
However the cdns_spi_fill_tx_fifo() function can be called during
an interrupt which may result in a kernel panic:

BUG: scheduling while atomic: grep/561/0x00010002
Modules linked in:
Preemption disabled at:
[<ffffff800858ea28>] wait_for_common+0x48/0x178
CPU: 0 PID: 561 Comm: grep Not tainted 4.17.0 #1
Hardware name: Cadence CSP (DT)
Call trace:
 dump_backtrace+0x0/0x198
 show_stack+0x14/0x20
 dump_stack+0x8c/0xac
 __schedule_bug+0x6c/0xb8
 __schedule+0x570/0x5d8
 schedule+0x34/0x98
 schedule_hrtimeout_range_clock+0x98/0x110
 schedule_hrtimeout_range+0x10/0x18
 usleep_range+0x64/0x98
 cdns_spi_fill_tx_fifo+0x70/0xb0
 cdns_spi_irq+0xd0/0xe0
 __handle_irq_event_percpu+0x9c/0x128
 handle_irq_event_percpu+0x34/0x88
 handle_irq_event+0x48/0x78
 handle_fasteoi_irq+0xbc/0x1b0
 generic_handle_irq+0x24/0x38
 __handle_domain_irq+0x84/0xf8
 gic_handle_irq+0xc4/0x180

This patch replaces the function call with udelay() which can be
used in an atomic context, like an interrupt.

Signed-off-by: Jan Kotas <jank@cadence.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/spi/spi-cadence.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index f3dad6fcdc35..a568f35522f9 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -319,7 +319,7 @@ static void cdns_spi_fill_tx_fifo(struct cdns_spi *xspi)
 		 */
 		if (cdns_spi_read(xspi, CDNS_SPI_ISR) &
 		    CDNS_SPI_IXR_TXFULL)
-			usleep_range(10, 20);
+			udelay(10);
 
 		if (xspi->txbuf)
 			cdns_spi_write(xspi, CDNS_SPI_TXD, *xspi->txbuf++);
-- 
cgit v1.2.3


From e2810a7167df14c762e085fae5aade38425b71bf Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Tue, 12 Jun 2018 15:20:27 +0200
Subject: drm/rockchip: vop: split out core clock enablement into separate
 functions

Judging from the iommu code, both the hclk and aclk are necessary for
register access. Split them off into separate functions from the regular
vop enablement, so that we can use them elsewhere as well.

Fixes: d0b912bd4c23 ("iommu/rockchip: Request irqs in rk_iommu_probe()")
[prerequisite change for the actual fix]
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Tested-by: Ezequiel Garcia <ezequiel@collabora.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612132028.27490-2-heiko@sntech.de
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 44 ++++++++++++++++++++---------
 1 file changed, 31 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index 45847d4a2e14..b55156b8ba3b 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -486,6 +486,31 @@ static void vop_line_flag_irq_disable(struct vop *vop)
 	spin_unlock_irqrestore(&vop->irq_lock, flags);
 }
 
+static int vop_core_clks_enable(struct vop *vop)
+{
+	int ret;
+
+	ret = clk_enable(vop->hclk);
+	if (ret < 0)
+		return ret;
+
+	ret = clk_enable(vop->aclk);
+	if (ret < 0)
+		goto err_disable_hclk;
+
+	return 0;
+
+err_disable_hclk:
+	clk_disable(vop->hclk);
+	return ret;
+}
+
+static void vop_core_clks_disable(struct vop *vop)
+{
+	clk_disable(vop->aclk);
+	clk_disable(vop->hclk);
+}
+
 static int vop_enable(struct drm_crtc *crtc)
 {
 	struct vop *vop = to_vop(crtc);
@@ -497,17 +522,13 @@ static int vop_enable(struct drm_crtc *crtc)
 		return ret;
 	}
 
-	ret = clk_enable(vop->hclk);
+	ret = vop_core_clks_enable(vop);
 	if (WARN_ON(ret < 0))
 		goto err_put_pm_runtime;
 
 	ret = clk_enable(vop->dclk);
 	if (WARN_ON(ret < 0))
-		goto err_disable_hclk;
-
-	ret = clk_enable(vop->aclk);
-	if (WARN_ON(ret < 0))
-		goto err_disable_dclk;
+		goto err_disable_core;
 
 	/*
 	 * Slave iommu shares power, irq and clock with vop.  It was associated
@@ -519,7 +540,7 @@ static int vop_enable(struct drm_crtc *crtc)
 	if (ret) {
 		DRM_DEV_ERROR(vop->dev,
 			      "failed to attach dma mapping, %d\n", ret);
-		goto err_disable_aclk;
+		goto err_disable_dclk;
 	}
 
 	spin_lock(&vop->reg_lock);
@@ -558,12 +579,10 @@ static int vop_enable(struct drm_crtc *crtc)
 
 	return 0;
 
-err_disable_aclk:
-	clk_disable(vop->aclk);
 err_disable_dclk:
 	clk_disable(vop->dclk);
-err_disable_hclk:
-	clk_disable(vop->hclk);
+err_disable_core:
+	vop_core_clks_disable(vop);
 err_put_pm_runtime:
 	pm_runtime_put_sync(vop->dev);
 	return ret;
@@ -609,8 +628,7 @@ static void vop_crtc_atomic_disable(struct drm_crtc *crtc,
 	rockchip_drm_dma_detach_device(vop->drm_dev, vop->dev);
 
 	clk_disable(vop->dclk);
-	clk_disable(vop->aclk);
-	clk_disable(vop->hclk);
+	vop_core_clks_disable(vop);
 	pm_runtime_put(vop->dev);
 	mutex_unlock(&vop->vop_lock);
 
-- 
cgit v1.2.3


From 6456314ff1de246414a43e3132075b70b3e050ac Mon Sep 17 00:00:00 2001
From: Sandy Huang <hjc@rock-chips.com>
Date: Tue, 12 Jun 2018 15:20:28 +0200
Subject: drm/rockchip: vop: fix irq disabled after vop driver probed

The vop irq is shared between vop and iommu and irq probing in the
iommu driver moved to the probe function recently. This can in some
cases lead to a stall if the irq is triggered while the vop driver
still has it disabled, but the vop irq handler gets called.

But there is no real need to disable the irq, as the vop can simply
also track its enabled state and ignore irqs in that case.
For this we can simply check the power-domain state of the vop,
similar to how the iommu driver does it.

So remove the enable/disable handling and add appropriate condition
to the irq handler.

changes in v2:
- move to just check the power-domain state
- add clock handling
changes in v3:
- clarify comment to speak of runtime-pm not power-domain
changes in v4:
- address Marc's comments (clk-enable WARN_ON and style improvement)

Fixes: d0b912bd4c23 ("iommu/rockchip: Request irqs in rk_iommu_probe()")
Cc: stable@vger.kernel.org
Signed-off-by: Sandy Huang <hjc@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Tested-by: Ezequiel Garcia <ezequiel@collabora.com>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Marc Zyngier <marc.zyngier@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612132028.27490-3-heiko@sntech.de
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index b55156b8ba3b..c9222119767d 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -573,8 +573,6 @@ static int vop_enable(struct drm_crtc *crtc)
 
 	spin_unlock(&vop->reg_lock);
 
-	enable_irq(vop->irq);
-
 	drm_crtc_vblank_on(crtc);
 
 	return 0;
@@ -618,8 +616,6 @@ static void vop_crtc_atomic_disable(struct drm_crtc *crtc,
 
 	vop_dsp_hold_valid_irq_disable(vop);
 
-	disable_irq(vop->irq);
-
 	vop->is_enabled = false;
 
 	/*
@@ -1195,6 +1191,18 @@ static irqreturn_t vop_isr(int irq, void *data)
 	uint32_t active_irqs;
 	int ret = IRQ_NONE;
 
+	/*
+	 * The irq is shared with the iommu. If the runtime-pm state of the
+	 * vop-device is disabled the irq has to be targeted at the iommu.
+	 */
+	if (!pm_runtime_get_if_in_use(vop->dev))
+		return IRQ_NONE;
+
+	if (vop_core_clks_enable(vop)) {
+		DRM_DEV_ERROR_RATELIMITED(vop->dev, "couldn't enable clocks\n");
+		goto out;
+	}
+
 	/*
 	 * interrupt register has interrupt status, enable and clear bits, we
 	 * must hold irq_lock to avoid a race with enable/disable_vblank().
@@ -1210,7 +1218,7 @@ static irqreturn_t vop_isr(int irq, void *data)
 
 	/* This is expected for vop iommu irqs, since the irq is shared */
 	if (!active_irqs)
-		return IRQ_NONE;
+		goto out_disable;
 
 	if (active_irqs & DSP_HOLD_VALID_INTR) {
 		complete(&vop->dsp_hold_completion);
@@ -1236,6 +1244,10 @@ static irqreturn_t vop_isr(int irq, void *data)
 		DRM_DEV_ERROR(vop->dev, "Unknown VOP IRQs: %#02x\n",
 			      active_irqs);
 
+out_disable:
+	vop_core_clks_disable(vop);
+out:
+	pm_runtime_put(vop->dev);
 	return ret;
 }
 
@@ -1614,9 +1626,6 @@ static int vop_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		goto err_disable_pm_runtime;
 
-	/* IRQ is initially disabled; it gets enabled in power_on */
-	disable_irq(vop->irq);
-
 	return 0;
 
 err_disable_pm_runtime:
-- 
cgit v1.2.3


From bcc2661e3243fe75b91ec682de01e7cbedfbe7f9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 18 Jun 2018 08:31:35 +0100
Subject: drm/i915: Only show debug for state changes when banning

Since we trigger 10,000s of hangs and resets during selftesting, we emit
many, many thousands of lines of useless debug messages. Reduce the
frequency by only logging a change in state of a guilty context.

Fixes: 14921f3cef85 ("drm/i915: Fix context ban and hang accounting for client")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618073135.10849-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 822abf444378..858d188dd33b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2976,16 +2976,16 @@ static void i915_gem_context_mark_guilty(struct i915_gem_context *ctx)
 	score = atomic_add_return(CONTEXT_SCORE_GUILTY, &ctx->ban_score);
 	banned = score >= CONTEXT_SCORE_BAN_THRESHOLD;
 
-	DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, ban %s\n",
-			 ctx->name, atomic_read(&ctx->guilty_count),
-			 score, yesno(banned && bannable));
-
 	/* Cool contexts don't accumulate client ban score */
 	if (!bannable)
 		return;
 
-	if (banned)
+	if (banned) {
+		DRM_DEBUG_DRIVER("context %s: guilty %d, score %u, banned\n",
+				 ctx->name, atomic_read(&ctx->guilty_count),
+				 score);
 		i915_gem_context_set_banned(ctx);
+	}
 
 	if (!IS_ERR_OR_NULL(ctx->file_priv))
 		i915_gem_client_mark_guilty(ctx->file_priv, ctx);
-- 
cgit v1.2.3


From 5ee4a7a6db8eb46aafdfea1f26cbdbbb4cef76b3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 18 Jun 2018 10:41:50 +0100
Subject: drm/i915/execlists: Pull the w/a LRI emission into a helper

Having the w/a registers as an open-coded table leaves a trap for the
unwary; it would be easy to miss incrementing the LRI counter when
adding a new register to the list. Instead, pull the list of registers
into a table, so that we only need add new registers to that table
rather than try and remember important side-effects of earlier chunks of
GPU instructions.

Suggested-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618094150.30895-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_reg.h  |  3 +-
 drivers/gpu/drm/i915/intel_lrc.c | 59 +++++++++++++++++++++++++++++-----------
 2 files changed, 45 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 54ec7ab57ce8..1f928bac2532 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -156,6 +156,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__)
 #define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c))
 
+#define __MASKED_FIELD(mask, value) ((mask) << 16 | (value))
 #define _MASKED_FIELD(mask, value) ({					   \
 	if (__builtin_constant_p(mask))					   \
 		BUILD_BUG_ON_MSG(((mask) & 0xffff0000), "Incorrect mask"); \
@@ -164,7 +165,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 	if (__builtin_constant_p(mask) && __builtin_constant_p(value))	   \
 		BUILD_BUG_ON_MSG((value) & ~(mask),			   \
 				 "Incorrect value for mask");		   \
-	(mask) << 16 | (value); })
+	__MASKED_FIELD(mask, value); })
 #define _MASKED_BIT_ENABLE(a)	({ typeof(a) _a = (a); _MASKED_FIELD(_a, _a); })
 #define _MASKED_BIT_DISABLE(a)	(_MASKED_FIELD((a), 0))
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index b6c230bd7d6e..10deebe49543 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1566,29 +1566,56 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
 	return batch;
 }
 
-static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
+struct lri {
+	i915_reg_t reg;
+	u32 value;
+};
+
+static u32 *emit_lri(u32 *batch, const struct lri *lri, unsigned int count)
 {
-	*batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
+	GEM_BUG_ON(!count || count > 63);
 
-	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
-	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
+	*batch++ = MI_LOAD_REGISTER_IMM(count);
+	do {
+		*batch++ = i915_mmio_reg_offset(lri->reg);
+		*batch++ = lri->value;
+	} while (lri++, --count);
+	*batch++ = MI_NOOP;
 
-	*batch++ = MI_LOAD_REGISTER_IMM(3);
+	return batch;
+}
 
-	/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
-	*batch++ = i915_mmio_reg_offset(COMMON_SLICE_CHICKEN2);
-	*batch++ = _MASKED_BIT_DISABLE(
-			GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE);
+static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch)
+{
+	static const struct lri lri[] = {
+		/* WaDisableGatherAtSetShaderCommonSlice:skl,bxt,kbl,glk */
+		{
+			COMMON_SLICE_CHICKEN2,
+			__MASKED_FIELD(GEN9_DISABLE_GATHER_AT_SET_SHADER_COMMON_SLICE,
+				       0),
+		},
+
+		/* BSpec: 11391 */
+		{
+			FF_SLICE_CHICKEN,
+			__MASKED_FIELD(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX,
+				       FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX),
+		},
+
+		/* BSpec: 11299 */
+		{
+			_3D_CHICKEN3,
+			__MASKED_FIELD(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX,
+				       _3D_CHICKEN_SF_PROVOKING_VERTEX_FIX),
+		}
+	};
 
-	/* BSpec: 11391 */
-	*batch++ = i915_mmio_reg_offset(FF_SLICE_CHICKEN);
-	*batch++ = _MASKED_BIT_ENABLE(FF_SLICE_CHICKEN_CL_PROVOKING_VERTEX_FIX);
+	*batch++ = MI_ARB_ON_OFF | MI_ARB_DISABLE;
 
-	/* BSpec: 11299 */
-	*batch++ = i915_mmio_reg_offset(_3D_CHICKEN3);
-	*batch++ = _MASKED_BIT_ENABLE(_3D_CHICKEN_SF_PROVOKING_VERTEX_FIX);
+	/* WaFlushCoherentL3CacheLinesAtContextSwitch:skl,bxt,glk */
+	batch = gen8_emit_flush_coherentl3_wa(engine, batch);
 
-	*batch++ = MI_NOOP;
+	batch = emit_lri(batch, lri, ARRAY_SIZE(lri));
 
 	/* WaClearSlmSpaceAtContextSwitch:kbl */
 	/* Actual scratch location is at 128 bytes offset */
-- 
cgit v1.2.3


From cf85ec88701610f0de2e959ac447d9613462fbc7 Mon Sep 17 00:00:00 2001
From: Vasily Averin <vvs@virtuozzo.com>
Date: Sat, 9 Jun 2018 16:18:16 +0300
Subject: removed extra extern file_fdatawait_range

Jeff added this extern twice in commit a823e4589e68

Fixes: a823e4589e68 ("mm: add file_fdatawait_range and file_write_and_wait")
Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5c91108846db..f140c11d35dd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2623,8 +2623,6 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 
 extern bool filemap_range_has_page(struct address_space *, loff_t lstart,
 				  loff_t lend);
-extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
-						loff_t lend);
 extern int filemap_write_and_wait(struct address_space *mapping);
 extern int filemap_write_and_wait_range(struct address_space *mapping,
 				        loff_t lstart, loff_t lend);
-- 
cgit v1.2.3


From 01655193c2da12510af8a8b66b56da5e13ce1f91 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 17 Jun 2018 15:46:29 +0200
Subject: ALSA: ice1724: remove unused array

This fixes a warning seen with clang:

sound/pci/ice1712/prodigy_hifi.c:321:28: warning: variable 'wm_vol' is not
      needed and will not be emitted [-Wunneeded-internal-declaration]
static const unsigned char wm_vol[256] = {
                           ^

Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ice1712/prodigy_hifi.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/sound/pci/ice1712/prodigy_hifi.c b/sound/pci/ice1712/prodigy_hifi.c
index d7366ade5a25..c97b5528e4b8 100644
--- a/sound/pci/ice1712/prodigy_hifi.c
+++ b/sound/pci/ice1712/prodigy_hifi.c
@@ -314,26 +314,7 @@ static struct snd_kcontrol_new prodigy_hd2_controls[] = {
 
 /* --------------- */
 
-/*
- * Logarithmic volume values for WM87*6
- * Computed as 20 * Log10(255 / x)
- */
-static const unsigned char wm_vol[256] = {
-	127, 48, 42, 39, 36, 34, 33, 31, 30, 29, 28, 27, 27, 26, 25, 25, 24, 24, 23,
-	23, 22, 22, 21, 21, 21, 20, 20, 20, 19, 19, 19, 18, 18, 18, 18, 17, 17, 17,
-	17, 16, 16, 16, 16, 15, 15, 15, 15, 15, 15, 14, 14, 14, 14, 14, 13, 13, 13,
-	13, 13, 13, 13, 12, 12, 12, 12, 12, 12, 12, 11, 11, 11, 11, 11, 11, 11, 11,
-	11, 10, 10, 10, 10, 10, 10, 10, 10, 10, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 8, 8,
-	8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 6, 6, 6,
-	6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
-	5, 5, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 4, 3, 3, 3, 3, 3,
-	3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
-	2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,
-	1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0
-};
-
-#define WM_VOL_MAX	(sizeof(wm_vol) - 1)
+#define WM_VOL_MAX	255
 #define WM_VOL_MUTE	0x8000
 
 
-- 
cgit v1.2.3


From a753af301c616cd51dedb3b5a8b3ba6cac3e58b8 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 17 Jun 2018 15:46:49 +0200
Subject: ALSA: ctxfi: use enum type CT_SUM_CTL where appropriate

Currently a variable of type enum CT_AMIXER_CTL is used for enum
CT_SUM_CTL values. This leads to warnings when using clang:
sound/pci/ctxfi/ctmixer.c:945:32: warning: implicit conversion from enumeration type
      'enum CT_SUM_CTL' to different enumeration type 'enum CT_AMIXER_CTL'
      [-Wenum-conversion]
        for (i = AMIXER_MASTER_F, j = SUM_IN_F;
                                    ~ ^~~~~~~~
sound/pci/ctxfi/ctmixer.c:975:29: warning: implicit conversion from enumeration type
      'enum CT_SUM_CTL' to different enumeration type 'enum CT_AMIXER_CTL'
      [-Wenum-conversion]
        for (i = AMIXER_PCM_F, j = SUM_IN_F; i <= AMIXER_PCM_S; i++, j++) {
                                 ~ ^~~~~~~~

Introduce enum CT_SUM_CTL k and it instead.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ctxfi/ctmixer.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/sound/pci/ctxfi/ctmixer.c b/sound/pci/ctxfi/ctmixer.c
index db710d0a609f..4777d50fbbf8 100644
--- a/sound/pci/ctxfi/ctmixer.c
+++ b/sound/pci/ctxfi/ctmixer.c
@@ -938,17 +938,18 @@ static int ct_mixer_topology_build(struct ct_mixer *mixer)
 	struct sum *sum;
 	struct amixer *amix_d, *amix_s;
 	enum CT_AMIXER_CTL i, j;
+	enum CT_SUM_CTL k;
 
 	/* Build topology from destination to source */
 
 	/* Set up Master mixer */
-	for (i = AMIXER_MASTER_F, j = SUM_IN_F;
-					i <= AMIXER_MASTER_S; i++, j++) {
+	for (i = AMIXER_MASTER_F, k = SUM_IN_F;
+					i <= AMIXER_MASTER_S; i++, k++) {
 		amix_d = mixer->amixers[i*CHN_NUM];
-		sum = mixer->sums[j*CHN_NUM];
+		sum = mixer->sums[k*CHN_NUM];
 		amix_d->ops->setup(amix_d, &sum->rsc, INIT_VOL, NULL);
 		amix_d = mixer->amixers[i*CHN_NUM+1];
-		sum = mixer->sums[j*CHN_NUM+1];
+		sum = mixer->sums[k*CHN_NUM+1];
 		amix_d->ops->setup(amix_d, &sum->rsc, INIT_VOL, NULL);
 	}
 
@@ -972,12 +973,12 @@ static int ct_mixer_topology_build(struct ct_mixer *mixer)
 	amix_d->ops->setup(amix_d, &amix_s->rsc, INIT_VOL, NULL);
 
 	/* Set up PCM-in mixer */
-	for (i = AMIXER_PCM_F, j = SUM_IN_F; i <= AMIXER_PCM_S; i++, j++) {
+	for (i = AMIXER_PCM_F, k = SUM_IN_F; i <= AMIXER_PCM_S; i++, k++) {
 		amix_d = mixer->amixers[i*CHN_NUM];
-		sum = mixer->sums[j*CHN_NUM];
+		sum = mixer->sums[k*CHN_NUM];
 		amix_d->ops->setup(amix_d, NULL, INIT_VOL, sum);
 		amix_d = mixer->amixers[i*CHN_NUM+1];
-		sum = mixer->sums[j*CHN_NUM+1];
+		sum = mixer->sums[k*CHN_NUM+1];
 		amix_d->ops->setup(amix_d, NULL, INIT_VOL, sum);
 	}
 
-- 
cgit v1.2.3


From a8eaad7b04eaab3df6b8db722d4418286815b46c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:41:01 +0200
Subject: ALSA: line6: stop using get_seconds()

The get_seconds() function is deprecated because it truncates the
timestamp to 32 bits, so all users should change to ktime_get_seconds()
or ktime_get_real_seconds().

The firmware interface for passing the timestamp is also limited to
32 bits, so this patch only has the cosmetic effect of avoiding the
old interface.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/line6/toneport.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/usb/line6/toneport.c b/sound/usb/line6/toneport.c
index 750467fb95db..f47ba94e6f4a 100644
--- a/sound/usb/line6/toneport.c
+++ b/sound/usb/line6/toneport.c
@@ -367,12 +367,13 @@ static bool toneport_has_source_select(struct usb_line6_toneport *toneport)
 */
 static void toneport_setup(struct usb_line6_toneport *toneport)
 {
-	int ticks;
+	u32 ticks;
 	struct usb_line6 *line6 = &toneport->line6;
 	struct usb_device *usbdev = line6->usbdev;
 
 	/* sync time on device with host: */
-	ticks = (int)get_seconds();
+	/* note: 32-bit timestamps overflow in year 2106 */
+	ticks = (u32)ktime_get_real_seconds();
 	line6_write_data(line6, 0x80c6, &ticks, 4);
 
 	/* enable device: */
-- 
cgit v1.2.3


From b9be78531d2710f4302545aa80e0678ed0a3dd09 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Thu, 14 Jun 2018 16:37:19 -0700
Subject: drm/i915/whl: Introducing Whiskey Lake platform
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Whiskey Lake uses the same gen graphics as Coffe Lake, including some
ids that were previously marked as reserved on Coffe Lake, but that
now are moved to WHL page.

So, let's just move them to WHL macros that will feed into CFL macro
just to keep it better organized to make easier future code review
but it will be handled as a CFL.

v2:
Fixing GT level of some ids

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614233720.30517-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/i915_pci.c |  4 +++-
 include/drm/i915_pciids.h       | 28 ++++++++++++++++++----------
 2 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 97a91e6af7e3..92e98773e53d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -660,9 +660,11 @@ static const struct pci_device_id pciidlist[] = {
 	INTEL_CFL_S_GT1_IDS(&intel_coffeelake_gt1_info),
 	INTEL_CFL_S_GT2_IDS(&intel_coffeelake_gt2_info),
 	INTEL_CFL_H_GT2_IDS(&intel_coffeelake_gt2_info),
-	INTEL_CFL_U_GT1_IDS(&intel_coffeelake_gt1_info),
 	INTEL_CFL_U_GT2_IDS(&intel_coffeelake_gt2_info),
 	INTEL_CFL_U_GT3_IDS(&intel_coffeelake_gt3_info),
+	INTEL_WHL_U_GT1_IDS(&intel_coffeelake_gt1_info),
+	INTEL_WHL_U_GT2_IDS(&intel_coffeelake_gt2_info),
+	INTEL_WHL_U_GT3_IDS(&intel_coffeelake_gt3_info),
 	INTEL_CNL_IDS(&intel_cannonlake_info),
 	INTEL_ICL_11_IDS(&intel_icelake_11_info),
 	{0, 0, 0}
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index bab70ff6e78b..d03350a38025 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -388,32 +388,40 @@
 	INTEL_VGA_DEVICE(0x3E9B, info), /* Halo GT2 */ \
 	INTEL_VGA_DEVICE(0x3E94, info)  /* Halo GT2 */
 
-/* CFL U GT1 */
-#define INTEL_CFL_U_GT1_IDS(info) \
-	INTEL_VGA_DEVICE(0x3EA1, info), \
-	INTEL_VGA_DEVICE(0x3EA4, info)
-
 /* CFL U GT2 */
 #define INTEL_CFL_U_GT2_IDS(info) \
-	INTEL_VGA_DEVICE(0x3EA0, info), \
-	INTEL_VGA_DEVICE(0x3EA3, info), \
 	INTEL_VGA_DEVICE(0x3EA9, info)
 
 /* CFL U GT3 */
 #define INTEL_CFL_U_GT3_IDS(info) \
-	INTEL_VGA_DEVICE(0x3EA2, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x3EA5, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x3EA6, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x3EA7, info), /* ULT GT3 */ \
 	INTEL_VGA_DEVICE(0x3EA8, info)  /* ULT GT3 */
 
+/* WHL/CFL U GT1 */
+#define INTEL_WHL_U_GT1_IDS(info) \
+	INTEL_VGA_DEVICE(0x3EA1, info)
+
+/* WHL/CFL U GT2 */
+#define INTEL_WHL_U_GT2_IDS(info) \
+	INTEL_VGA_DEVICE(0x3EA0, info)
+
+/* WHL/CFL U GT3 */
+#define INTEL_WHL_U_GT3_IDS(info) \
+	INTEL_VGA_DEVICE(0x3EA2, info), \
+	INTEL_VGA_DEVICE(0x3EA3, info), \
+	INTEL_VGA_DEVICE(0x3EA4, info)
+
 #define INTEL_CFL_IDS(info)	   \
 	INTEL_CFL_S_GT1_IDS(info), \
 	INTEL_CFL_S_GT2_IDS(info), \
 	INTEL_CFL_H_GT2_IDS(info), \
-	INTEL_CFL_U_GT1_IDS(info), \
 	INTEL_CFL_U_GT2_IDS(info), \
-	INTEL_CFL_U_GT3_IDS(info)
+	INTEL_CFL_U_GT3_IDS(info), \
+	INTEL_WHL_U_GT1_IDS(info), \
+	INTEL_WHL_U_GT2_IDS(info), \
+	INTEL_WHL_U_GT3_IDS(info)
 
 /* CNL */
 #define INTEL_CNL_IDS(info) \
-- 
cgit v1.2.3


From e364672477a105029346f0888bfa797b1ec3eee4 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Thu, 14 Jun 2018 16:37:20 -0700
Subject: drm/i915/aml: Introducing Amber Lake platform
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Amber Lake uses the same gen graphics as Kaby Lake, including a id
that were previously marked as reserved on Kaby Lake, but that
now is moved to AML page.

So, let's just move it to AML macro that will feed into KBL macro
just to keep it better organized to make easier future code review
but it will be handled as a KBL.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614233720.30517-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/i915_pci.c | 1 +
 include/drm/i915_pciids.h       | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 92e98773e53d..55543f1b0236 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -657,6 +657,7 @@ static const struct pci_device_id pciidlist[] = {
 	INTEL_KBL_GT2_IDS(&intel_kabylake_gt2_info),
 	INTEL_KBL_GT3_IDS(&intel_kabylake_gt3_info),
 	INTEL_KBL_GT4_IDS(&intel_kabylake_gt3_info),
+	INTEL_AML_GT2_IDS(&intel_kabylake_gt2_info),
 	INTEL_CFL_S_GT1_IDS(&intel_coffeelake_gt1_info),
 	INTEL_CFL_S_GT2_IDS(&intel_coffeelake_gt2_info),
 	INTEL_CFL_H_GT2_IDS(&intel_coffeelake_gt2_info),
diff --git a/include/drm/i915_pciids.h b/include/drm/i915_pciids.h
index d03350a38025..fbf5cfc9b352 100644
--- a/include/drm/i915_pciids.h
+++ b/include/drm/i915_pciids.h
@@ -349,7 +349,6 @@
 #define INTEL_KBL_GT2_IDS(info)	\
 	INTEL_VGA_DEVICE(0x5916, info), /* ULT GT2 */ \
 	INTEL_VGA_DEVICE(0x5917, info), /* Mobile GT2 */ \
-	INTEL_VGA_DEVICE(0x591C, info), /* ULX GT2 */ \
 	INTEL_VGA_DEVICE(0x5921, info), /* ULT GT2F */ \
 	INTEL_VGA_DEVICE(0x591E, info), /* ULX GT2 */ \
 	INTEL_VGA_DEVICE(0x5912, info), /* DT  GT2 */ \
@@ -365,11 +364,17 @@
 #define INTEL_KBL_GT4_IDS(info) \
 	INTEL_VGA_DEVICE(0x593B, info) /* Halo GT4 */
 
+/* AML/KBL Y GT2 */
+#define INTEL_AML_GT2_IDS(info) \
+	INTEL_VGA_DEVICE(0x591C, info),  /* ULX GT2 */ \
+	INTEL_VGA_DEVICE(0x87C0, info) /* ULX GT2 */
+
 #define INTEL_KBL_IDS(info) \
 	INTEL_KBL_GT1_IDS(info), \
 	INTEL_KBL_GT2_IDS(info), \
 	INTEL_KBL_GT3_IDS(info), \
-	INTEL_KBL_GT4_IDS(info)
+	INTEL_KBL_GT4_IDS(info), \
+	INTEL_AML_GT2_IDS(info)
 
 /* CFL S */
 #define INTEL_CFL_S_GT1_IDS(info) \
-- 
cgit v1.2.3


From 420c0117db25db38b72b6230223f7a976d3070ea Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:04 +0200
Subject: dmaengine: pxa: use a dma slave map

In order to remove the specific knowledge of the dma mapping from PXA
drivers, add a default slave map for pxa architectures.

This won't impact MMP architecture, but is aimed only at all PXA boards.

This is the first step, and once all drivers are converted,
pxad_filter_fn() will be made static, and the DMA resources removed from
device.c.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/pxa_dma.c                 | 10 +++++++++-
 include/linux/platform_data/mmp_dma.h |  4 ++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index b53fb618bbf6..9505334f9c6e 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -179,6 +179,8 @@ static unsigned int pxad_drcmr(unsigned int line)
 	return 0x1000 + line * 4;
 }
 
+bool pxad_filter_fn(struct dma_chan *chan, void *param);
+
 /*
  * Debug fs
  */
@@ -1396,9 +1398,10 @@ static int pxad_probe(struct platform_device *op)
 {
 	struct pxad_device *pdev;
 	const struct of_device_id *of_id;
+	const struct dma_slave_map *slave_map = NULL;
 	struct mmp_dma_platdata *pdata = dev_get_platdata(&op->dev);
 	struct resource *iores;
-	int ret, dma_channels = 0, nb_requestors = 0;
+	int ret, dma_channels = 0, nb_requestors = 0, slave_map_cnt = 0;
 	const enum dma_slave_buswidth widths =
 		DMA_SLAVE_BUSWIDTH_1_BYTE   | DMA_SLAVE_BUSWIDTH_2_BYTES |
 		DMA_SLAVE_BUSWIDTH_4_BYTES;
@@ -1429,6 +1432,8 @@ static int pxad_probe(struct platform_device *op)
 	} else if (pdata && pdata->dma_channels) {
 		dma_channels = pdata->dma_channels;
 		nb_requestors = pdata->nb_requestors;
+		slave_map = pdata->slave_map;
+		slave_map_cnt = pdata->slave_map_cnt;
 	} else {
 		dma_channels = 32;	/* default 32 channel */
 	}
@@ -1440,6 +1445,9 @@ static int pxad_probe(struct platform_device *op)
 	pdev->slave.device_prep_dma_memcpy = pxad_prep_memcpy;
 	pdev->slave.device_prep_slave_sg = pxad_prep_slave_sg;
 	pdev->slave.device_prep_dma_cyclic = pxad_prep_dma_cyclic;
+	pdev->slave.filter.map = slave_map;
+	pdev->slave.filter.mapcnt = slave_map_cnt;
+	pdev->slave.filter.fn = pxad_filter_fn;
 
 	pdev->slave.copy_align = PDMA_ALIGNMENT;
 	pdev->slave.src_addr_widths = widths;
diff --git a/include/linux/platform_data/mmp_dma.h b/include/linux/platform_data/mmp_dma.h
index d1397c8ed94e..6397b9c8149a 100644
--- a/include/linux/platform_data/mmp_dma.h
+++ b/include/linux/platform_data/mmp_dma.h
@@ -12,9 +12,13 @@
 #ifndef MMP_DMA_H
 #define MMP_DMA_H
 
+struct dma_slave_map;
+
 struct mmp_dma_platdata {
 	int dma_channels;
 	int nb_requestors;
+	int slave_map_cnt;
+	const struct dma_slave_map *slave_map;
 };
 
 #endif /* MMP_DMA_H */
-- 
cgit v1.2.3


From 1da10c17afd1109ae22d529c3b16d9f6de3fdbec Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:05 +0200
Subject: ARM: pxa: add dma slave map

In order to remove the specific knowledge of the dma mapping from PXA
drivers, add a default slave map for pxa architectures.

This is the first step, and once all drivers are converted,
pxad_filter_fn() will be made static, and the DMA resources removed from
device.c.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Reported-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-pxa/devices.c | 12 +++---------
 arch/arm/mach-pxa/devices.h |  6 +++++-
 arch/arm/mach-pxa/pxa25x.c  | 38 +++++++++++++++++++++++++++++++++++++-
 arch/arm/mach-pxa/pxa27x.c  | 39 ++++++++++++++++++++++++++++++++++++++-
 arch/arm/mach-pxa/pxa3xx.c  | 41 ++++++++++++++++++++++++++++++++++++++++-
 5 files changed, 123 insertions(+), 13 deletions(-)

diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index d7c9a8476d57..1e8915fc340d 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -4,6 +4,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
+#include <linux/dmaengine.h>
 #include <linux/spi/pxa2xx_spi.h>
 #include <linux/platform_data/i2c-pxa.h>
 
@@ -1202,11 +1203,6 @@ void __init pxa2xx_set_spi_info(unsigned id, struct pxa2xx_spi_master *info)
 	platform_device_add(pd);
 }
 
-static struct mmp_dma_platdata pxa_dma_pdata = {
-	.dma_channels	= 0,
-	.nb_requestors	= 0,
-};
-
 static struct resource pxa_dma_resource[] = {
 	[0] = {
 		.start	= 0x40000000,
@@ -1233,9 +1229,7 @@ static struct platform_device pxa2xx_pxa_dma = {
 	.resource	= pxa_dma_resource,
 };
 
-void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors)
+void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata)
 {
-	pxa_dma_pdata.dma_channels = nb_channels;
-	pxa_dma_pdata.nb_requestors = nb_requestors;
-	pxa_register_device(&pxa2xx_pxa_dma, &pxa_dma_pdata);
+	pxa_register_device(&pxa2xx_pxa_dma, dma_pdata);
 }
diff --git a/arch/arm/mach-pxa/devices.h b/arch/arm/mach-pxa/devices.h
index 11263f7c455b..498b07bc6a3e 100644
--- a/arch/arm/mach-pxa/devices.h
+++ b/arch/arm/mach-pxa/devices.h
@@ -1,4 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#define PDMA_FILTER_PARAM(_prio, _requestor) (&(struct pxad_param) { \
+	.prio = PXAD_PRIO_##_prio, .drcmr = _requestor })
+struct mmp_dma_platdata;
+
 extern struct platform_device pxa_device_pmu;
 extern struct platform_device pxa_device_mci;
 extern struct platform_device pxa3xx_device_mci2;
@@ -55,7 +59,7 @@ extern struct platform_device pxa3xx_device_gpio;
 extern struct platform_device pxa93x_device_gpio;
 
 void __init pxa_register_device(struct platform_device *dev, void *data);
-void __init pxa2xx_set_dmac_info(int nb_channels, int nb_requestors);
+void __init pxa2xx_set_dmac_info(struct mmp_dma_platdata *dma_pdata);
 
 struct i2c_pxa_platform_data;
 extern void pxa_set_i2c_info(struct i2c_pxa_platform_data *info);
diff --git a/arch/arm/mach-pxa/pxa25x.c b/arch/arm/mach-pxa/pxa25x.c
index ba431fad5c47..ab8808ce7e21 100644
--- a/arch/arm/mach-pxa/pxa25x.c
+++ b/arch/arm/mach-pxa/pxa25x.c
@@ -16,6 +16,8 @@
  * initialization stuff for PXA machines which can be overridden later if
  * need be.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
 #include <linux/module.h>
@@ -26,6 +28,7 @@
 #include <linux/syscore_ops.h>
 #include <linux/irq.h>
 #include <linux/irqchip.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
@@ -201,6 +204,39 @@ static struct platform_device *pxa25x_devices[] __initdata = {
 	&pxa_device_asoc_platform,
 };
 
+static const struct dma_slave_map pxa25x_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+
+	/* PXA25x specific map */
+	{ "pxa25x-ssp.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa25x-ssp.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa25x-nssp.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa25x-nssp.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa25x-nssp.2", "rx", PDMA_FILTER_PARAM(LOWEST, 23) },
+	{ "pxa25x-nssp.2", "tx", PDMA_FILTER_PARAM(LOWEST, 24) },
+};
+
+static struct mmp_dma_platdata pxa25x_dma_pdata = {
+	.dma_channels	= 16,
+	.nb_requestors	= 40,
+	.slave_map	= pxa25x_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa25x_slave_map),
+};
+
 static int __init pxa25x_init(void)
 {
 	int ret = 0;
@@ -215,7 +251,7 @@ static int __init pxa25x_init(void)
 		register_syscore_ops(&pxa2xx_mfp_syscore_ops);
 
 		if (!of_have_populated_dt()) {
-			pxa2xx_set_dmac_info(16, 40);
+			pxa2xx_set_dmac_info(&pxa25x_dma_pdata);
 			pxa_register_device(&pxa25x_device_gpio, &pxa25x_gpio_info);
 			ret = platform_add_devices(pxa25x_devices,
 						   ARRAY_SIZE(pxa25x_devices));
diff --git a/arch/arm/mach-pxa/pxa27x.c b/arch/arm/mach-pxa/pxa27x.c
index 0c06f383ad52..5a8990a9313d 100644
--- a/arch/arm/mach-pxa/pxa27x.c
+++ b/arch/arm/mach-pxa/pxa27x.c
@@ -11,6 +11,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/gpio-pxa.h>
 #include <linux/module.h>
@@ -23,6 +25,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/platform_data/i2c-pxa.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <mach/hardware.h>
@@ -297,6 +300,40 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
+static const struct dma_slave_map pxa27x_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) },
+
+	/* PXA27x specific map */
+	{ "pxa2xx-i2s", "rx", PDMA_FILTER_PARAM(LOWEST, 2) },
+	{ "pxa2xx-i2s", "tx", PDMA_FILTER_PARAM(LOWEST, 3) },
+	{ "pxa27x-camera.0", "CI_Y", PDMA_FILTER_PARAM(HIGHEST, 68) },
+	{ "pxa27x-camera.0", "CI_U", PDMA_FILTER_PARAM(HIGHEST, 69) },
+	{ "pxa27x-camera.0", "CI_V", PDMA_FILTER_PARAM(HIGHEST, 70) },
+};
+
+static struct mmp_dma_platdata pxa27x_dma_pdata = {
+	.dma_channels	= 32,
+	.nb_requestors	= 75,
+	.slave_map	= pxa27x_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa27x_slave_map),
+};
+
 static int __init pxa27x_init(void)
 {
 	int ret = 0;
@@ -313,7 +350,7 @@ static int __init pxa27x_init(void)
 		if (!of_have_populated_dt()) {
 			pxa_register_device(&pxa27x_device_gpio,
 					    &pxa27x_gpio_info);
-			pxa2xx_set_dmac_info(32, 75);
+			pxa2xx_set_dmac_info(&pxa27x_dma_pdata);
 			ret = platform_add_devices(devices,
 						   ARRAY_SIZE(devices));
 		}
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index 8c64f93b669b..df9c8970adcf 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -12,6 +12,8 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
+#include <linux/dmaengine.h>
+#include <linux/dma/pxa-dma.h>
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -24,6 +26,7 @@
 #include <linux/of.h>
 #include <linux/syscore_ops.h>
 #include <linux/platform_data/i2c-pxa.h>
+#include <linux/platform_data/mmp_dma.h>
 
 #include <asm/mach/map.h>
 #include <asm/suspend.h>
@@ -421,6 +424,42 @@ static struct platform_device *devices[] __initdata = {
 	&pxa27x_device_pwm1,
 };
 
+static const struct dma_slave_map pxa3xx_slave_map[] = {
+	/* PXA25x, PXA27x and PXA3xx common entries */
+	{ "pxa2xx-ac97", "pcm_pcm_mic_mono", PDMA_FILTER_PARAM(LOWEST, 8) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_in", PDMA_FILTER_PARAM(LOWEST, 9) },
+	{ "pxa2xx-ac97", "pcm_pcm_aux_mono_out",
+	  PDMA_FILTER_PARAM(LOWEST, 10) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_in", PDMA_FILTER_PARAM(LOWEST, 11) },
+	{ "pxa2xx-ac97", "pcm_pcm_stereo_out", PDMA_FILTER_PARAM(LOWEST, 12) },
+	{ "pxa-ssp-dai.0", "rx", PDMA_FILTER_PARAM(LOWEST, 13) },
+	{ "pxa-ssp-dai.0", "tx", PDMA_FILTER_PARAM(LOWEST, 14) },
+	{ "pxa-ssp-dai.1", "rx", PDMA_FILTER_PARAM(LOWEST, 15) },
+	{ "pxa-ssp-dai.1", "tx", PDMA_FILTER_PARAM(LOWEST, 16) },
+	{ "pxa2xx-ir", "rx", PDMA_FILTER_PARAM(LOWEST, 17) },
+	{ "pxa2xx-ir", "tx", PDMA_FILTER_PARAM(LOWEST, 18) },
+	{ "pxa2xx-mci.0", "rx", PDMA_FILTER_PARAM(LOWEST, 21) },
+	{ "pxa2xx-mci.0", "tx", PDMA_FILTER_PARAM(LOWEST, 22) },
+	{ "pxa-ssp-dai.2", "rx", PDMA_FILTER_PARAM(LOWEST, 66) },
+	{ "pxa-ssp-dai.2", "tx", PDMA_FILTER_PARAM(LOWEST, 67) },
+
+	/* PXA3xx specific map */
+	{ "pxa-ssp-dai.3", "rx", PDMA_FILTER_PARAM(LOWEST, 2) },
+	{ "pxa-ssp-dai.3", "tx", PDMA_FILTER_PARAM(LOWEST, 3) },
+	{ "pxa2xx-mci.1", "rx", PDMA_FILTER_PARAM(LOWEST, 93) },
+	{ "pxa2xx-mci.1", "tx", PDMA_FILTER_PARAM(LOWEST, 94) },
+	{ "pxa3xx-nand", "data", PDMA_FILTER_PARAM(LOWEST, 97) },
+	{ "pxa2xx-mci.2", "rx", PDMA_FILTER_PARAM(LOWEST, 100) },
+	{ "pxa2xx-mci.2", "tx", PDMA_FILTER_PARAM(LOWEST, 101) },
+};
+
+static struct mmp_dma_platdata pxa3xx_dma_pdata = {
+	.dma_channels	= 32,
+	.nb_requestors	= 100,
+	.slave_map	= pxa3xx_slave_map,
+	.slave_map_cnt	= ARRAY_SIZE(pxa3xx_slave_map),
+};
+
 static int __init pxa3xx_init(void)
 {
 	int ret = 0;
@@ -456,7 +495,7 @@ static int __init pxa3xx_init(void)
 		if (of_have_populated_dt())
 			return 0;
 
-		pxa2xx_set_dmac_info(32, 100);
+		pxa2xx_set_dmac_info(&pxa3xx_dma_pdata);
 		ret = platform_add_devices(devices, ARRAY_SIZE(devices));
 		if (ret)
 			return ret;
-- 
cgit v1.2.3


From 88a0513cf6114bbabbd3a158f039dbd03f49e0bf Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:06 +0200
Subject: dmaengine: pxa: add a default requestor policy

As what former drcmr -1 value meant, add a this as a default to each
channel, ie. that by default no requestor line is used.

This is specifically used for network drivers smc91x and smc911x, and
needed for their port to slave maps.

Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Acked-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/pxa_dma.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/dma/pxa_dma.c b/drivers/dma/pxa_dma.c
index 9505334f9c6e..b31c28b67ad3 100644
--- a/drivers/dma/pxa_dma.c
+++ b/drivers/dma/pxa_dma.c
@@ -762,6 +762,8 @@ static void pxad_free_chan_resources(struct dma_chan *dchan)
 	dma_pool_destroy(chan->desc_pool);
 	chan->desc_pool = NULL;
 
+	chan->drcmr = U32_MAX;
+	chan->prio = PXAD_PRIO_LOWEST;
 }
 
 static void pxad_free_desc(struct virt_dma_desc *vd)
@@ -1386,6 +1388,9 @@ static int pxad_init_dmadev(struct platform_device *op,
 		c = devm_kzalloc(&op->dev, sizeof(*c), GFP_KERNEL);
 		if (!c)
 			return -ENOMEM;
+
+		c->drcmr = U32_MAX;
+		c->prio = PXAD_PRIO_LOWEST;
 		c->vc.desc_free = pxad_free_desc;
 		vchan_init(&c->vc, &pdev->slave);
 		init_waitqueue_head(&c->wq_state);
-- 
cgit v1.2.3


From 6b3348f9e6eb35d2c2d49ffa274039ef9a901adc Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:07 +0200
Subject: mmc: pxamci: remove the dmaengine compat need

As the pxa architecture switched towards the dmaengine slave map, the
old compatibility mechanism to acquire the dma requestor line number and
priority are not needed anymore.

This patch simplifies the dma resource acquisition, using the more
generic function dma_request_slave_channel().

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Acked-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/pxamci.c | 29 +++--------------------------
 1 file changed, 3 insertions(+), 26 deletions(-)

diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index c763b404510f..6c94474e36f4 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -24,7 +24,6 @@
 #include <linux/interrupt.h>
 #include <linux/dmaengine.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma/pxa-dma.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/mmc/host.h>
@@ -637,10 +636,8 @@ static int pxamci_probe(struct platform_device *pdev)
 {
 	struct mmc_host *mmc;
 	struct pxamci_host *host = NULL;
-	struct resource *r, *dmarx, *dmatx;
-	struct pxad_param param_rx, param_tx;
+	struct resource *r;
 	int ret, irq, gpio_cd = -1, gpio_ro = -1, gpio_power = -1;
-	dma_cap_mask_t mask;
 
 	ret = pxamci_of_init(pdev);
 	if (ret)
@@ -739,34 +736,14 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, mmc);
 
-	if (!pdev->dev.of_node) {
-		dmarx = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		dmatx = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (!dmarx || !dmatx) {
-			ret = -ENXIO;
-			goto out;
-		}
-		param_rx.prio = PXAD_PRIO_LOWEST;
-		param_rx.drcmr = dmarx->start;
-		param_tx.prio = PXAD_PRIO_LOWEST;
-		param_tx.drcmr = dmatx->start;
-	}
-
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-
-	host->dma_chan_rx =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param_rx, &pdev->dev, "rx");
+	host->dma_chan_rx = dma_request_slave_channel(&pdev->dev, "rx");
 	if (host->dma_chan_rx == NULL) {
 		dev_err(&pdev->dev, "unable to request rx dma channel\n");
 		ret = -ENODEV;
 		goto out;
 	}
 
-	host->dma_chan_tx =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param_tx,  &pdev->dev, "tx");
+	host->dma_chan_tx = dma_request_slave_channel(&pdev->dev, "tx");
 	if (host->dma_chan_tx == NULL) {
 		dev_err(&pdev->dev, "unable to request tx dma channel\n");
 		ret = -ENODEV;
-- 
cgit v1.2.3


From f727b6cda449184188d8a64987f194687bf01782 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:08 +0200
Subject: media: pxa_camera: remove the dmaengine compat need

As the pxa architecture switched towards the dmaengine slave map, the
old compatibility mechanism to acquire the dma requestor line number and
priority are not needed anymore.

This patch simplifies the dma resource acquisition, using the more
generic function dma_request_slave_channel().

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/pxa_camera.c | 22 +++-------------------
 1 file changed, 3 insertions(+), 19 deletions(-)

diff --git a/drivers/media/platform/pxa_camera.c b/drivers/media/platform/pxa_camera.c
index d85ffbfb7c1f..b6e9e93bde7a 100644
--- a/drivers/media/platform/pxa_camera.c
+++ b/drivers/media/platform/pxa_camera.c
@@ -2375,8 +2375,6 @@ static int pxa_camera_probe(struct platform_device *pdev)
 		.src_maxburst = 8,
 		.direction = DMA_DEV_TO_MEM,
 	};
-	dma_cap_mask_t mask;
-	struct pxad_param params;
 	char clk_name[V4L2_CLK_NAME_SIZE];
 	int irq;
 	int err = 0, i;
@@ -2450,34 +2448,20 @@ static int pxa_camera_probe(struct platform_device *pdev)
 	pcdev->base = base;
 
 	/* request dma */
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	dma_cap_set(DMA_PRIVATE, mask);
-
-	params.prio = 0;
-	params.drcmr = 68;
-	pcdev->dma_chans[0] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_Y");
+	pcdev->dma_chans[0] = dma_request_slave_channel(&pdev->dev, "CI_Y");
 	if (!pcdev->dma_chans[0]) {
 		dev_err(&pdev->dev, "Can't request DMA for Y\n");
 		return -ENODEV;
 	}
 
-	params.drcmr = 69;
-	pcdev->dma_chans[1] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_U");
+	pcdev->dma_chans[1] = dma_request_slave_channel(&pdev->dev, "CI_U");
 	if (!pcdev->dma_chans[1]) {
 		dev_err(&pdev->dev, "Can't request DMA for Y\n");
 		err = -ENODEV;
 		goto exit_free_dma_y;
 	}
 
-	params.drcmr = 70;
-	pcdev->dma_chans[2] =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &params, &pdev->dev, "CI_V");
+	pcdev->dma_chans[2] = dma_request_slave_channel(&pdev->dev, "CI_V");
 	if (!pcdev->dma_chans[2]) {
 		dev_err(&pdev->dev, "Can't request DMA for V\n");
 		err = -ENODEV;
-- 
cgit v1.2.3


From ac75a50b6de3b092d084fdd9818707d0d5073ad6 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:09 +0200
Subject: mtd: rawnand: marvell: remove the dmaengine compat need

As the pxa architecture switched towards the dmaengine slave map, the
old compatibility mechanism to acquire the dma requestor line number and
priority are not needed anymore.

This patch simplifies the dma resource acquisition, using the more
generic function dma_request_slave_channel().

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/marvell_nand.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index ebb1d141b900..00d9f29bbdb6 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2612,8 +2612,6 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 						    dev);
 	struct dma_slave_config config = {};
 	struct resource *r;
-	dma_cap_mask_t mask;
-	struct pxad_param param;
 	int ret;
 
 	if (!IS_ENABLED(CONFIG_PXA_DMA)) {
@@ -2626,20 +2624,7 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 	if (ret)
 		return ret;
 
-	r = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-	if (!r) {
-		dev_err(nfc->dev, "No resource defined for data DMA\n");
-		return -ENXIO;
-	}
-
-	param.drcmr = r->start;
-	param.prio = PXAD_PRIO_LOWEST;
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	nfc->dma_chan =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param, nfc->dev,
-						 "data");
+	nfc->dma_chan =	dma_request_slave_channel(nfc->dev, "data");
 	if (!nfc->dma_chan) {
 		dev_err(nfc->dev,
 			"Unable to request data DMA channel\n");
-- 
cgit v1.2.3


From 273340e8bf86de53eef7073993352ea11c563696 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:13 +0200
Subject: ata: pata_pxa: remove the dmaengine compat need

As the pxa architecture switched towards the dmaengine slave map, the
old compatibility mechanism to acquire the dma requestor line number and
priority are not needed anymore.

This patch simplifies the dma resource acquisition, using the more
generic function dma_request_slave_channel().

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
---
 drivers/ata/pata_pxa.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/ata/pata_pxa.c b/drivers/ata/pata_pxa.c
index f6c46e9a4dc0..e8b6a2e464c9 100644
--- a/drivers/ata/pata_pxa.c
+++ b/drivers/ata/pata_pxa.c
@@ -25,7 +25,6 @@
 #include <linux/libata.h>
 #include <linux/platform_device.h>
 #include <linux/dmaengine.h>
-#include <linux/dma/pxa-dma.h>
 #include <linux/gpio.h>
 #include <linux/slab.h>
 #include <linux/completion.h>
@@ -180,8 +179,6 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	struct resource *irq_res;
 	struct pata_pxa_pdata *pdata = dev_get_platdata(&pdev->dev);
 	struct dma_slave_config	config;
-	dma_cap_mask_t mask;
-	struct pxad_param param;
 	int ret = 0;
 
 	/*
@@ -278,10 +275,6 @@ static int pxa_ata_probe(struct platform_device *pdev)
 
 	ap->private_data = data;
 
-	dma_cap_zero(mask);
-	dma_cap_set(DMA_SLAVE, mask);
-	param.prio = PXAD_PRIO_LOWEST;
-	param.drcmr = pdata->dma_dreq;
 	memset(&config, 0, sizeof(config));
 	config.src_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
 	config.dst_addr_width = DMA_SLAVE_BUSWIDTH_2_BYTES;
@@ -294,8 +287,7 @@ static int pxa_ata_probe(struct platform_device *pdev)
 	 * Request the DMA channel
 	 */
 	data->dma_chan =
-		dma_request_slave_channel_compat(mask, pxad_filter_fn,
-						 &param, &pdev->dev, "data");
+		dma_request_slave_channel(&pdev->dev, "data");
 	if (!data->dma_chan)
 		return -EBUSY;
 	ret = dmaengine_slave_config(data->dma_chan, &config);
-- 
cgit v1.2.3


From b6d1a17f4729e4fda5740a855da91d202db2c118 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:14 +0200
Subject: dmaengine: pxa: document pxad_param

Add some documentation for the pxad_param structure, and describe the
contract behind the minimal required priority of a DMA channel.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Acked-by: Vinod Koul <vkoul@kernel.org>
---
 include/linux/dma/pxa-dma.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/linux/dma/pxa-dma.h b/include/linux/dma/pxa-dma.h
index e56ec7af4fd7..9fc594f69eff 100644
--- a/include/linux/dma/pxa-dma.h
+++ b/include/linux/dma/pxa-dma.h
@@ -9,6 +9,15 @@ enum pxad_chan_prio {
 	PXAD_PRIO_LOWEST,
 };
 
+/**
+ * struct pxad_param - dma channel request parameters
+ * @drcmr: requestor line number
+ * @prio: minimal mandatory priority of the channel
+ *
+ * If a requested channel is granted, its priority will be at least @prio,
+ * ie. if PXAD_PRIO_LOW is required, the requested channel will be either
+ * PXAD_PRIO_LOW, PXAD_PRIO_NORMAL or PXAD_PRIO_HIGHEST.
+ */
 struct pxad_param {
 	unsigned int drcmr;
 	enum pxad_chan_prio prio;
-- 
cgit v1.2.3


From b77ed2e6d61d40117272be1b2377c5dfd101e9cd Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:16 +0200
Subject: ARM: pxa: remove the DMA IO resources

As the last driver using the former mechanism to acquire the DMA
requestor line has be converted to the dma_slave_map, remove all these
resources from the PXA devices.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
---
 arch/arm/mach-pxa/devices.c | 136 --------------------------------------------
 1 file changed, 136 deletions(-)

diff --git a/arch/arm/mach-pxa/devices.c b/arch/arm/mach-pxa/devices.c
index 1e8915fc340d..5a16ea74e28a 100644
--- a/arch/arm/mach-pxa/devices.c
+++ b/arch/arm/mach-pxa/devices.c
@@ -60,16 +60,6 @@ static struct resource pxamci_resources[] = {
 		.end	= IRQ_MMC,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 21,
-		.end	= 21,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 22,
-		.end	= 22,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 static u64 pxamci_dmamask = 0xffffffffUL;
@@ -407,16 +397,6 @@ static struct resource pxa_ir_resources[] = {
 		.end	= 0x40700023,
 		.flags  = IORESOURCE_MEM,
 	},
-	[5] = {
-		.start  = 17,
-		.end	= 17,
-		.flags  = IORESOURCE_DMA,
-	},
-	[6] = {
-		.start  = 18,
-		.end	= 18,
-		.flags  = IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa_device_ficp = {
@@ -545,18 +525,6 @@ static struct resource pxa25x_resource_ssp[] = {
 		.end	= IRQ_SSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 13,
-		.end	= 13,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 14,
-		.end	= 14,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_ssp = {
@@ -583,18 +551,6 @@ static struct resource pxa25x_resource_nssp[] = {
 		.end	= IRQ_NSSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 15,
-		.end	= 15,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 16,
-		.end	= 16,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_nssp = {
@@ -621,18 +577,6 @@ static struct resource pxa25x_resource_assp[] = {
 		.end	= IRQ_ASSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 23,
-		.end	= 23,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 24,
-		.end	= 24,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa25x_device_assp = {
@@ -751,18 +695,6 @@ static struct resource pxa27x_resource_ssp1[] = {
 		.end	= IRQ_SSP,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 13,
-		.end	= 13,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 14,
-		.end	= 14,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp1 = {
@@ -789,18 +721,6 @@ static struct resource pxa27x_resource_ssp2[] = {
 		.end	= IRQ_SSP2,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 15,
-		.end	= 15,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 16,
-		.end	= 16,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp2 = {
@@ -827,18 +747,6 @@ static struct resource pxa27x_resource_ssp3[] = {
 		.end	= IRQ_SSP3,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 66,
-		.end	= 66,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 67,
-		.end	= 67,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa27x_device_ssp3 = {
@@ -895,16 +803,6 @@ static struct resource pxa3xx_resources_mci2[] = {
 		.end	= IRQ_MMC2,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 93,
-		.end	= 93,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 94,
-		.end	= 94,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa3xx_device_mci2 = {
@@ -934,16 +832,6 @@ static struct resource pxa3xx_resources_mci3[] = {
 		.end	= IRQ_MMC3,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		.start	= 100,
-		.end	= 100,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		.start	= 101,
-		.end	= 101,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 struct platform_device pxa3xx_device_mci3 = {
@@ -1021,18 +909,6 @@ static struct resource pxa3xx_resources_nand[] = {
 		.end	= IRQ_NAND,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for Data DMA */
-		.start	= 97,
-		.end	= 97,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for Command DMA */
-		.start	= 99,
-		.end	= 99,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 static u64 pxa3xx_nand_dma_mask = DMA_BIT_MASK(32);
@@ -1066,18 +942,6 @@ static struct resource pxa3xx_resource_ssp4[] = {
 		.end	= IRQ_SSP4,
 		.flags	= IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* DRCMR for RX */
-		.start	= 2,
-		.end	= 2,
-		.flags	= IORESOURCE_DMA,
-	},
-	[3] = {
-		/* DRCMR for TX */
-		.start	= 3,
-		.end	= 3,
-		.flags	= IORESOURCE_DMA,
-	},
 };
 
 /*
-- 
cgit v1.2.3


From cd31b80736852d34bc1072f3e579a6fd73a244e7 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Sun, 17 Jun 2018 19:02:17 +0200
Subject: ARM: pxa: change SSP DMA channels allocation

Now the dma_slave_map is available for PXA architecture, switch the SSP
device to it.

This specifically means that :
- for platform data based machines, the DMA requestor channels are
  extracted from the slave map, where pxa-ssp-dai.<N> is a 1-1 match to
  ssp.<N>, and the channels are either "rx" or "tx".

- for device tree platforms, the dma node should be hooked into the
  pxa2xx-ac97 or pxa-ssp-dai node.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Acked-by: Daniel Mack <daniel@zonque.org>
---
 arch/arm/plat-pxa/ssp.c    | 47 ----------------------------------------------
 include/linux/pxa2xx_ssp.h |  2 --
 sound/soc/pxa/pxa-ssp.c    |  5 ++---
 3 files changed, 2 insertions(+), 52 deletions(-)

diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ba13f793fbce..ed36dcab80f1 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -127,53 +127,6 @@ static int pxa_ssp_probe(struct platform_device *pdev)
 	if (IS_ERR(ssp->clk))
 		return PTR_ERR(ssp->clk);
 
-	if (dev->of_node) {
-		struct of_phandle_args dma_spec;
-		struct device_node *np = dev->of_node;
-		int ret;
-
-		/*
-		 * FIXME: we should allocate the DMA channel from this
-		 * context and pass the channel down to the ssp users.
-		 * For now, we lookup the rx and tx indices manually
-		 */
-
-		/* rx */
-		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
-						 0, &dma_spec);
-
-		if (ret) {
-			dev_err(dev, "Can't parse dmas property\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_rx = dma_spec.args[0];
-		of_node_put(dma_spec.np);
-
-		/* tx */
-		ret = of_parse_phandle_with_args(np, "dmas", "#dma-cells",
-						 1, &dma_spec);
-		if (ret) {
-			dev_err(dev, "Can't parse dmas property\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_tx = dma_spec.args[0];
-		of_node_put(dma_spec.np);
-	} else {
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 0);
-		if (res == NULL) {
-			dev_err(dev, "no SSP RX DRCMR defined\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_rx = res->start;
-
-		res = platform_get_resource(pdev, IORESOURCE_DMA, 1);
-		if (res == NULL) {
-			dev_err(dev, "no SSP TX DRCMR defined\n");
-			return -ENODEV;
-		}
-		ssp->drcmr_tx = res->start;
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(dev, "no memory resource defined\n");
diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 8461b18e4608..03a7ca46735b 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -212,8 +212,6 @@ struct ssp_device {
 	int		type;
 	int		use_count;
 	int		irq;
-	int		drcmr_rx;
-	int		drcmr_tx;
 
 	struct device_node	*of_node;
 };
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 6fc986080130..0b441338bdd4 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -105,9 +105,8 @@ static int pxa_ssp_startup(struct snd_pcm_substream *substream,
 	dma = kzalloc(sizeof(struct snd_dmaengine_dai_dma_data), GFP_KERNEL);
 	if (!dma)
 		return -ENOMEM;
-
-	dma->filter_data = substream->stream == SNDRV_PCM_STREAM_PLAYBACK ?
-				&ssp->drcmr_tx : &ssp->drcmr_rx;
+	dma->chan_name = substream->stream == SNDRV_PCM_STREAM_PLAYBACK ?
+		"tx" : "rx";
 
 	snd_soc_dai_set_dma_data(cpu_dai, substream, dma);
 
-- 
cgit v1.2.3


From 58884bbc7c9d8dd2623510ecf8ba3ddf1af9ce96 Mon Sep 17 00:00:00 2001
From: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Date: Thu, 7 Jun 2018 12:20:13 -0700
Subject: drm/i915/audio: Add 810 MHz clock entries to dp_aud_n_m table

Expand the Maud/Naud table according to DP 1.4 spec to include entries for
810 MHz clock. This is required for audio to work with HBR3.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180607192013.25872-1-radhakrishna.sripada@intel.com
---
 drivers/gpu/drm/i915/intel_audio.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 4e4c0ec44f35..a34aa66f28f8 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -59,6 +59,7 @@
  */
 
 /* DP N/M table */
+#define LC_810M	810000
 #define LC_540M	540000
 #define LC_270M	270000
 #define LC_162M	162000
@@ -99,6 +100,15 @@ static const struct dp_aud_n_m dp_aud_n_m[] = {
 	{ 128000, LC_540M, 4096, 33750 },
 	{ 176400, LC_540M, 3136, 18750 },
 	{ 192000, LC_540M, 2048, 11250 },
+	{ 32000, LC_810M, 1024, 50625 },
+	{ 44100, LC_810M, 784, 28125 },
+	{ 48000, LC_810M, 512, 16875 },
+	{ 64000, LC_810M, 2048, 50625 },
+	{ 88200, LC_810M, 1568, 28125 },
+	{ 96000, LC_810M, 1024, 16875 },
+	{ 128000, LC_810M, 4096, 50625 },
+	{ 176400, LC_810M, 3136, 28125 },
+	{ 192000, LC_810M, 2048, 16875 },
 };
 
 static const struct dp_aud_n_m *
-- 
cgit v1.2.3


From cf76e1e5198aad2721c8da84c2cc0933d32223cf Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Mon, 18 Jun 2018 15:43:32 -0400
Subject: MAINTAINERS: update the LSM and SELinux subsystems

The SELinux code, security/selinux/, already has a MAINTAINERS entry
so exclude it from the security subsystem entry in an effort to better
reflect current practices.

Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9d5eeff51b5f..67e4c4f92ba9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12769,6 +12769,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security.git
 W:	http://kernsec.org/
 S:	Supported
 F:	security/
+X:	security/selinux/
 
 SELINUX SECURITY MODULE
 M:	Paul Moore <paul@paul-moore.com>
-- 
cgit v1.2.3


From b8042b3da925f390c1482bf9dc0898dc0b3ea7b5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 18 Jun 2018 22:39:29 +0200
Subject: ieee80211: bump IEEE80211_MAX_AMPDU_BUF to support HE

Bump the IEEE80211_MAX_AMPDU_BUF size to 0x100 for HE support
and - for now - use IEEE80211_MAX_AMPDU_BUF_HT everywhere.

This is derived from my internal patch, parts of which Luca
had sent upstream.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/realtek/rtlwifi/base.c |  2 +-
 drivers/staging/rtl8188eu/include/wifi.h    |  1 -
 drivers/staging/rtl8712/wifi.h              |  1 -
 drivers/staging/rtl8723bs/include/wifi.h    |  1 -
 drivers/staging/rtlwifi/base.c              |  2 +-
 include/linux/ieee80211.h                   | 10 ++++++----
 net/mac80211/agg-rx.c                       |  4 ++--
 net/mac80211/agg-tx.c                       |  2 +-
 net/mac80211/ht.c                           |  2 +-
 net/mac80211/main.c                         |  4 ++--
 10 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/base.c b/drivers/net/wireless/realtek/rtlwifi/base.c
index 39c817eddd78..31bd6f714052 100644
--- a/drivers/net/wireless/realtek/rtlwifi/base.c
+++ b/drivers/net/wireless/realtek/rtlwifi/base.c
@@ -1904,7 +1904,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv)
 		 reject_agg, ctrl_agg_size, agg_size);
 
 	rtlpriv->hw->max_rx_aggregation_subframes =
-		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF);
+		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT);
 }
 EXPORT_SYMBOL(rtl_rx_ampdu_apply);
 
diff --git a/drivers/staging/rtl8188eu/include/wifi.h b/drivers/staging/rtl8188eu/include/wifi.h
index 084a246eec19..6790b7c8cfb1 100644
--- a/drivers/staging/rtl8188eu/include/wifi.h
+++ b/drivers/staging/rtl8188eu/include/wifi.h
@@ -575,7 +575,6 @@ enum ht_cap_ampdu_factor {
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
  */
 #define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
 
 
 #define OP_MODE_PURE                    0
diff --git a/drivers/staging/rtl8712/wifi.h b/drivers/staging/rtl8712/wifi.h
index 0ed2f44ab4e9..00a4302e9983 100644
--- a/drivers/staging/rtl8712/wifi.h
+++ b/drivers/staging/rtl8712/wifi.h
@@ -574,7 +574,6 @@ struct ieee80211_ht_addt_info {
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
  */
 #define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
 
 
 /* Spatial Multiplexing Power Save Modes */
diff --git a/drivers/staging/rtl8723bs/include/wifi.h b/drivers/staging/rtl8723bs/include/wifi.h
index 08bc79840b23..559bf2606fb7 100644
--- a/drivers/staging/rtl8723bs/include/wifi.h
+++ b/drivers/staging/rtl8723bs/include/wifi.h
@@ -799,7 +799,6 @@ enum HT_CAP_AMPDU_FACTOR {
  * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
  */
 #define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
 
 
 /* Spatial Multiplexing Power Save Modes */
diff --git a/drivers/staging/rtlwifi/base.c b/drivers/staging/rtlwifi/base.c
index e46e47d93d7d..094827c1879a 100644
--- a/drivers/staging/rtlwifi/base.c
+++ b/drivers/staging/rtlwifi/base.c
@@ -1838,7 +1838,7 @@ void rtl_rx_ampdu_apply(struct rtl_priv *rtlpriv)
 		 reject_agg, ctrl_agg_size, agg_size);
 
 	rtlpriv->hw->max_rx_aggregation_subframes =
-		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF);
+		(ctrl_agg_size ? agg_size : IEEE80211_MAX_AMPDU_BUF_HT);
 }
 
 /*********************************************************
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index e6a6503bfa33..9c03a7d5e400 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1433,11 +1433,13 @@ struct ieee80211_ht_operation {
 #define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
 
 /*
- * A-PMDU buffer sizes
- * According to IEEE802.11n spec size varies from 8K to 64K (in powers of 2)
+ * A-MPDU buffer sizes
+ * According to HT size varies from 8 to 64 frames
+ * HE adds the ability to have up to 256 frames.
  */
-#define IEEE80211_MIN_AMPDU_BUF 0x8
-#define IEEE80211_MAX_AMPDU_BUF 0x40
+#define IEEE80211_MIN_AMPDU_BUF		0x8
+#define IEEE80211_MAX_AMPDU_BUF_HT	0x40
+#define IEEE80211_MAX_AMPDU_BUF		0x100
 
 
 /* Spatial Multiplexing Power Save Modes (for capability) */
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index e83c19d4c292..3ffd853b483f 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -274,7 +274,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta,
 	/* XXX: check own ht delayed BA capability?? */
 	if (((ba_policy != 1) &&
 	     (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) ||
-	    (buf_size > IEEE80211_MAX_AMPDU_BUF)) {
+	    (buf_size > IEEE80211_MAX_AMPDU_BUF_HT)) {
 		status = WLAN_STATUS_INVALID_QOS_PARAM;
 		ht_dbg_ratelimited(sta->sdata,
 				   "AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n",
@@ -283,7 +283,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta,
 	}
 	/* determine default buffer size */
 	if (buf_size == 0)
-		buf_size = IEEE80211_MAX_AMPDU_BUF;
+		buf_size = IEEE80211_MAX_AMPDU_BUF_HT;
 
 	/* make sure the size doesn't exceed the maximum supported by the hw */
 	if (buf_size > sta->sta.max_rx_aggregation_subframes)
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index ac4295296514..86c6bc0432ba 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -514,7 +514,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 	/* send AddBA request */
 	ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
 				     tid_tx->dialog_token, params.ssn,
-				     IEEE80211_MAX_AMPDU_BUF,
+				     IEEE80211_MAX_AMPDU_BUF_HT,
 				     tid_tx->timeout);
 }
 
diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c
index 26a7ba3b698f..f849ea814993 100644
--- a/net/mac80211/ht.c
+++ b/net/mac80211/ht.c
@@ -352,7 +352,7 @@ void ieee80211_ba_session_work(struct work_struct *work)
 		    test_and_clear_bit(tid,
 				       sta->ampdu_mlme.tid_rx_manage_offl))
 			___ieee80211_start_rx_ba_session(sta, 0, 0, 0, 1, tid,
-							 IEEE80211_MAX_AMPDU_BUF,
+							 IEEE80211_MAX_AMPDU_BUF_HT,
 							 false, true);
 
 		if (test_and_clear_bit(tid + IEEE80211_NUM_TIDS,
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index a6f8e3a646d4..070f77862014 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -597,8 +597,8 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len,
 	local->hw.queues = 1;
 	local->hw.max_rates = 1;
 	local->hw.max_report_rates = 0;
-	local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
-	local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF;
+	local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT;
+	local->hw.max_tx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_HT;
 	local->hw.offchannel_tx_hw_queue = IEEE80211_INVAL_HW_QUEUE;
 	local->hw.conf.long_frame_max_tx_count = wiphy->retry_long;
 	local->hw.conf.short_frame_max_tx_count = wiphy->retry_short;
-- 
cgit v1.2.3


From 41cbb0f5a29592874355e4159489eb08337cd50e Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sat, 9 Jun 2018 09:14:44 +0300
Subject: mac80211: add support for HE

Add support for HE in mac80211 conforming with P802.11ax_D1.4.

Johannes: Fix another bug with the buf_size comparison in agg-rx.c.

Signed-off-by: Liad Kaufman <liad.kaufman@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Ido Yariv <idox.yariv@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h     |  64 ++++++++--
 net/mac80211/Makefile      |   1 +
 net/mac80211/agg-rx.c      |  10 +-
 net/mac80211/agg-tx.c      |  19 ++-
 net/mac80211/cfg.c         |   5 +
 net/mac80211/he.c          |  55 +++++++++
 net/mac80211/ieee80211_i.h |  16 +++
 net/mac80211/main.c        |  19 ++-
 net/mac80211/mlme.c        | 288 ++++++++++++++++++++++++++++++++++++++++++---
 net/mac80211/rx.c          | 127 +++++++++++++++++++-
 net/mac80211/sta_info.c    |  15 ++-
 net/mac80211/sta_info.h    |  20 +++-
 net/mac80211/trace.h       |   2 +-
 net/mac80211/util.c        | 120 ++++++++++++++++++-
 14 files changed, 716 insertions(+), 45 deletions(-)
 create mode 100644 net/mac80211/he.c

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 851a5e19ae32..5790f55c241d 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -23,6 +23,7 @@
 #include <linux/ieee80211.h>
 #include <net/cfg80211.h>
 #include <net/codel.h>
+#include <net/ieee80211_radiotap.h>
 #include <asm/unaligned.h>
 
 /**
@@ -162,6 +163,8 @@ enum ieee80211_ac_numbers {
  * @txop: maximum burst time in units of 32 usecs, 0 meaning disabled
  * @acm: is mandatory admission control required for the access category
  * @uapsd: is U-APSD mode enabled for the queue
+ * @mu_edca: is the MU EDCA configured
+ * @mu_edca_param_rec: MU EDCA Parameter Record for HE
  */
 struct ieee80211_tx_queue_params {
 	u16 txop;
@@ -170,6 +173,8 @@ struct ieee80211_tx_queue_params {
 	u8 aifs;
 	bool acm;
 	bool uapsd;
+	bool mu_edca;
+	struct ieee80211_he_mu_edca_param_ac_rec mu_edca_param_rec;
 };
 
 struct ieee80211_low_level_stats {
@@ -463,6 +468,15 @@ struct ieee80211_mu_group_data {
  * This structure keeps information about a BSS (and an association
  * to that BSS) that can change during the lifetime of the BSS.
  *
+ * @bss_color: 6-bit value to mark inter-BSS frame, if BSS supports HE
+ * @htc_trig_based_pkt_ext: default PE in 4us units, if BSS supports HE
+ * @multi_sta_back_32bit: supports BA bitmap of 32-bits in Multi-STA BACK
+ * @uora_exists: is the UORA element advertised by AP
+ * @ack_enabled: indicates support to receive a multi-TID that solicits either
+ *	ACK, BACK or both
+ * @uora_ocw_range: UORA element's OCW Range field
+ * @frame_time_rts_th: HE duration RTS threshold, in units of 32us
+ * @he_support: does this BSS support HE
  * @assoc: association status
  * @ibss_joined: indicates whether this station is part of an IBSS
  *	or not
@@ -550,6 +564,14 @@ struct ieee80211_mu_group_data {
  */
 struct ieee80211_bss_conf {
 	const u8 *bssid;
+	u8 bss_color;
+	u8 htc_trig_based_pkt_ext;
+	bool multi_sta_back_32bit;
+	bool uora_exists;
+	bool ack_enabled;
+	u8 uora_ocw_range;
+	u16 frame_time_rts_th;
+	bool he_support;
 	/* association related data */
 	bool assoc, ibss_joined;
 	bool ibss_creator;
@@ -1106,6 +1128,18 @@ ieee80211_tx_info_clear_status(struct ieee80211_tx_info *info)
  * @RX_FLAG_AMPDU_EOF_BIT: Value of the EOF bit in the A-MPDU delimiter for this
  *	frame
  * @RX_FLAG_AMPDU_EOF_BIT_KNOWN: The EOF value is known
+ * @RX_FLAG_RADIOTAP_HE: HE radiotap data is present
+ *	(&struct ieee80211_radiotap_he, mac80211 will fill in
+ *	 - DATA3_DATA_MCS
+ *	 - DATA3_DATA_DCM
+ *	 - DATA3_CODING
+ *	 - DATA5_GI
+ *	 - DATA5_DATA_BW_RU_ALLOC
+ *	 - DATA6_NSTS
+ *	 - DATA3_STBC
+ *	from the RX info data, so leave those zeroed when building this data)
+ * @RX_FLAG_RADIOTAP_HE_MU: HE MU radiotap data is present
+ *	(&struct ieee80211_radiotap_he_mu)
  */
 enum mac80211_rx_flags {
 	RX_FLAG_MMIC_ERROR		= BIT(0),
@@ -1134,6 +1168,8 @@ enum mac80211_rx_flags {
 	RX_FLAG_ICV_STRIPPED		= BIT(23),
 	RX_FLAG_AMPDU_EOF_BIT		= BIT(24),
 	RX_FLAG_AMPDU_EOF_BIT_KNOWN	= BIT(25),
+	RX_FLAG_RADIOTAP_HE		= BIT(26),
+	RX_FLAG_RADIOTAP_HE_MU		= BIT(27),
 };
 
 /**
@@ -1164,6 +1200,7 @@ enum mac80211_rx_encoding {
 	RX_ENC_LEGACY = 0,
 	RX_ENC_HT,
 	RX_ENC_VHT,
+	RX_ENC_HE,
 };
 
 /**
@@ -1198,6 +1235,9 @@ enum mac80211_rx_encoding {
  * @encoding: &enum mac80211_rx_encoding
  * @bw: &enum rate_info_bw
  * @enc_flags: uses bits from &enum mac80211_rx_encoding_flags
+ * @he_ru: HE RU, from &enum nl80211_he_ru_alloc
+ * @he_gi: HE GI, from &enum nl80211_he_gi
+ * @he_dcm: HE DCM value
  * @rx_flags: internal RX flags for mac80211
  * @ampdu_reference: A-MPDU reference number, must be a different value for
  *	each A-MPDU but the same for each subframe within one A-MPDU
@@ -1211,7 +1251,8 @@ struct ieee80211_rx_status {
 	u32 flag;
 	u16 freq;
 	u8 enc_flags;
-	u8 encoding:2, bw:3;
+	u8 encoding:2, bw:3, he_ru:3;
+	u8 he_gi:2, he_dcm:1;
 	u8 rate_idx;
 	u8 nss;
 	u8 rx_flags;
@@ -1770,6 +1811,7 @@ struct ieee80211_sta_rates {
  * @supp_rates: Bitmap of supported rates (per band)
  * @ht_cap: HT capabilities of this STA; restricted to our own capabilities
  * @vht_cap: VHT capabilities of this STA; restricted to our own capabilities
+ * @he_cap: HE capabilities of this STA
  * @max_rx_aggregation_subframes: maximal amount of frames in a single AMPDU
  *	that this station is allowed to transmit to us.
  *	Can be modified by driver.
@@ -1805,7 +1847,8 @@ struct ieee80211_sta {
 	u16 aid;
 	struct ieee80211_sta_ht_cap ht_cap;
 	struct ieee80211_sta_vht_cap vht_cap;
-	u8 max_rx_aggregation_subframes;
+	struct ieee80211_sta_he_cap he_cap;
+	u16 max_rx_aggregation_subframes;
 	bool wme;
 	u8 uapsd_queues;
 	u8 max_sp;
@@ -2196,10 +2239,11 @@ enum ieee80211_hw_flags {
  *	it shouldn't be set.
  *
  * @max_tx_aggregation_subframes: maximum number of subframes in an
- *	aggregate an HT driver will transmit. Though ADDBA will advertise
- *	a constant value of 64 as some older APs can crash if the window
- *	size is smaller (an example is LinkSys WRT120N with FW v1.0.07
- *	build 002 Jun 18 2012).
+ *	aggregate an HT/HE device will transmit. In HT AddBA we'll
+ *	advertise a constant value of 64 as some older APs crash if
+ *	the window size is smaller (an example is LinkSys WRT120N
+ *	with FW v1.0.07 build 002 Jun 18 2012).
+ *	For AddBA to HE capable peers this value will be used.
  *
  * @max_tx_fragments: maximum number of tx buffers per (A)-MSDU, sum
  *	of 1 + skb_shinfo(skb)->nr_frags for each skb in the frag_list.
@@ -2216,6 +2260,8 @@ enum ieee80211_hw_flags {
  *	the default is _GI | _BANDWIDTH.
  *	Use the %IEEE80211_RADIOTAP_VHT_KNOWN_\* values.
  *
+ * @radiotap_he: HE radiotap validity flags
+ *
  * @radiotap_timestamp: Information for the radiotap timestamp field; if the
  *	'units_pos' member is set to a non-negative value it must be set to
  *	a combination of a IEEE80211_RADIOTAP_TIMESTAMP_UNIT_* and a
@@ -2263,8 +2309,8 @@ struct ieee80211_hw {
 	u8 max_rates;
 	u8 max_report_rates;
 	u8 max_rate_tries;
-	u8 max_rx_aggregation_subframes;
-	u8 max_tx_aggregation_subframes;
+	u16 max_rx_aggregation_subframes;
+	u16 max_tx_aggregation_subframes;
 	u8 max_tx_fragments;
 	u8 offchannel_tx_hw_queue;
 	u8 radiotap_mcs_details;
@@ -2904,7 +2950,7 @@ struct ieee80211_ampdu_params {
 	struct ieee80211_sta *sta;
 	u16 tid;
 	u16 ssn;
-	u8 buf_size;
+	u16 buf_size;
 	bool amsdu;
 	u16 timeout;
 };
diff --git a/net/mac80211/Makefile b/net/mac80211/Makefile
index e3589ade62e0..bb707789ef2b 100644
--- a/net/mac80211/Makefile
+++ b/net/mac80211/Makefile
@@ -12,6 +12,7 @@ mac80211-y := \
 	scan.o offchannel.o \
 	ht.o agg-tx.o agg-rx.o \
 	vht.o \
+	he.o \
 	ibss.o \
 	iface.o \
 	rate.o \
diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index 3ffd853b483f..6a4f154c99f6 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -245,6 +245,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta,
 	};
 	int i, ret = -EOPNOTSUPP;
 	u16 status = WLAN_STATUS_REQUEST_DECLINED;
+	u16 max_buf_size;
 
 	if (tid >= IEEE80211_FIRST_TSPEC_TSID) {
 		ht_dbg(sta->sdata,
@@ -268,13 +269,18 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta,
 		goto end;
 	}
 
+	if (sta->sta.he_cap.has_he)
+		max_buf_size = IEEE80211_MAX_AMPDU_BUF;
+	else
+		max_buf_size = IEEE80211_MAX_AMPDU_BUF_HT;
+
 	/* sanity check for incoming parameters:
 	 * check if configuration can support the BA policy
 	 * and if buffer size does not exceeds max value */
 	/* XXX: check own ht delayed BA capability?? */
 	if (((ba_policy != 1) &&
 	     (!(sta->sta.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) ||
-	    (buf_size > IEEE80211_MAX_AMPDU_BUF_HT)) {
+	    (buf_size > max_buf_size)) {
 		status = WLAN_STATUS_INVALID_QOS_PARAM;
 		ht_dbg_ratelimited(sta->sdata,
 				   "AddBA Req with bad params from %pM on tid %u. policy %d, buffer size %d\n",
@@ -283,7 +289,7 @@ void ___ieee80211_start_rx_ba_session(struct sta_info *sta,
 	}
 	/* determine default buffer size */
 	if (buf_size == 0)
-		buf_size = IEEE80211_MAX_AMPDU_BUF_HT;
+		buf_size = max_buf_size;
 
 	/* make sure the size doesn't exceed the maximum supported by the hw */
 	if (buf_size > sta->sta.max_rx_aggregation_subframes)
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 86c6bc0432ba..69e831bc317b 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -463,6 +463,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 		.timeout = 0,
 	};
 	int ret;
+	u16 buf_size;
 
 	tid_tx = rcu_dereference_protected_tid_tx(sta, tid);
 
@@ -511,11 +512,22 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid)
 	sta->ampdu_mlme.addba_req_num[tid]++;
 	spin_unlock_bh(&sta->lock);
 
+	if (sta->sta.he_cap.has_he) {
+		buf_size = local->hw.max_tx_aggregation_subframes;
+	} else {
+		/*
+		 * We really should use what the driver told us it will
+		 * transmit as the maximum, but certain APs (e.g. the
+		 * LinkSys WRT120N with FW v1.0.07 build 002 Jun 18 2012)
+		 * will crash when we use a lower number.
+		 */
+		buf_size = IEEE80211_MAX_AMPDU_BUF_HT;
+	}
+
 	/* send AddBA request */
 	ieee80211_send_addba_request(sdata, sta->sta.addr, tid,
 				     tid_tx->dialog_token, params.ssn,
-				     IEEE80211_MAX_AMPDU_BUF_HT,
-				     tid_tx->timeout);
+				     buf_size, tid_tx->timeout);
 }
 
 /*
@@ -905,8 +917,7 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local,
 {
 	struct tid_ampdu_tx *tid_tx;
 	struct ieee80211_txq *txq;
-	u16 capab, tid;
-	u8 buf_size;
+	u16 capab, tid, buf_size;
 	bool amsdu;
 
 	capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab);
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index c4e2f7d2bcb8..02f3672e7b5e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1412,6 +1412,11 @@ static int sta_apply_parameters(struct ieee80211_local *local,
 		ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
 						    params->vht_capa, sta);
 
+	if (params->he_capa)
+		ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband,
+						  (void *)params->he_capa,
+						  params->he_capa_len, sta);
+
 	if (params->opmode_notif_used) {
 		/* returned value is only needed for rc update, but the
 		 * rc isn't initialized here yet, so ignore it
diff --git a/net/mac80211/he.c b/net/mac80211/he.c
new file mode 100644
index 000000000000..769078ed5a12
--- /dev/null
+++ b/net/mac80211/he.c
@@ -0,0 +1,55 @@
+/*
+ * HE handling
+ *
+ * Copyright(c) 2017 Intel Deutschland GmbH
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include "ieee80211_i.h"
+
+void
+ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata,
+				  struct ieee80211_supported_band *sband,
+				  const u8 *he_cap_ie, u8 he_cap_len,
+				  struct sta_info *sta)
+{
+	struct ieee80211_sta_he_cap *he_cap = &sta->sta.he_cap;
+	struct ieee80211_he_cap_elem *he_cap_ie_elem = (void *)he_cap_ie;
+	u8 he_ppe_size;
+	u8 mcs_nss_size;
+	u8 he_total_size;
+
+	memset(he_cap, 0, sizeof(*he_cap));
+
+	if (!he_cap_ie || !ieee80211_get_he_sta_cap(sband))
+		return;
+
+	/* Make sure size is OK */
+	mcs_nss_size = ieee80211_he_mcs_nss_size(he_cap_ie_elem);
+	he_ppe_size =
+		ieee80211_he_ppe_size(he_cap_ie[sizeof(he_cap->he_cap_elem) +
+						mcs_nss_size],
+				      he_cap_ie_elem->phy_cap_info);
+	he_total_size = sizeof(he_cap->he_cap_elem) + mcs_nss_size +
+			he_ppe_size;
+	if (he_cap_len < he_total_size)
+		return;
+
+	memcpy(&he_cap->he_cap_elem, he_cap_ie, sizeof(he_cap->he_cap_elem));
+
+	/* HE Tx/Rx HE MCS NSS Support Field */
+	memcpy(&he_cap->he_mcs_nss_supp,
+	       &he_cap_ie[sizeof(he_cap->he_cap_elem)], mcs_nss_size);
+
+	/* Check if there are (optional) PPE Thresholds */
+	if (he_cap->he_cap_elem.phy_cap_info[6] &
+	    IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT)
+		memcpy(he_cap->ppe_thres,
+		       &he_cap_ie[sizeof(he_cap->he_cap_elem) + mcs_nss_size],
+		       he_ppe_size);
+
+	he_cap->has_he = true;
+}
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index a6c12c104c38..172aeae21ae9 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -365,6 +365,7 @@ enum ieee80211_sta_flags {
 	IEEE80211_STA_DISABLE_160MHZ	= BIT(13),
 	IEEE80211_STA_DISABLE_WMM	= BIT(14),
 	IEEE80211_STA_ENABLE_RRM	= BIT(15),
+	IEEE80211_STA_DISABLE_HE	= BIT(16),
 };
 
 struct ieee80211_mgd_auth_data {
@@ -1454,6 +1455,10 @@ struct ieee802_11_elems {
 	const struct ieee80211_vht_cap *vht_cap_elem;
 	const struct ieee80211_vht_operation *vht_operation;
 	const struct ieee80211_meshconf_ie *mesh_config;
+	const u8 *he_cap;
+	const struct ieee80211_he_operation *he_operation;
+	const struct ieee80211_mu_edca_param_set *mu_edca_param_set;
+	const u8 *uora_element;
 	const u8 *mesh_id;
 	const u8 *peering;
 	const __le16 *awake_window;
@@ -1483,6 +1488,7 @@ struct ieee802_11_elems {
 	u8 ext_supp_rates_len;
 	u8 wmm_info_len;
 	u8 wmm_param_len;
+	u8 he_cap_len;
 	u8 mesh_id_len;
 	u8 peering_len;
 	u8 preq_len;
@@ -1825,6 +1831,13 @@ void ieee80211_get_vht_mask_from_cap(__le16 vht_cap,
 enum nl80211_chan_width
 ieee80211_sta_rx_bw_to_chan_width(struct sta_info *sta);
 
+/* HE */
+void
+ieee80211_he_cap_ie_to_sta_he_cap(struct ieee80211_sub_if_data *sdata,
+				  struct ieee80211_supported_band *sband,
+				  const u8 *he_cap_ie, u8 he_cap_len,
+				  struct sta_info *sta);
+
 /* Spectrum management */
 void ieee80211_process_measurement_req(struct ieee80211_sub_if_data *sdata,
 				       struct ieee80211_mgmt *mgmt,
@@ -2076,6 +2089,9 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 			       u32 cap);
 u8 *ieee80211_ie_build_vht_oper(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 				const struct cfg80211_chan_def *chandef);
+u8 *ieee80211_ie_build_he_cap(u8 *pos,
+			      const struct ieee80211_sta_he_cap *he_cap,
+			      u8 *end);
 int ieee80211_parse_bitrates(struct cfg80211_chan_def *chandef,
 			     const struct ieee80211_supported_band *sband,
 			     const u8 *srates, int srates_len, u32 *rates);
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 070f77862014..b33faba8cbbe 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -3,6 +3,7 @@
  * Copyright 2005-2006, Devicescape Software, Inc.
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
+ * Copyright (C) 2017     Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -825,7 +826,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	int result, i;
 	enum nl80211_band band;
 	int channels, max_bitrates;
-	bool supp_ht, supp_vht;
+	bool supp_ht, supp_vht, supp_he;
 	netdev_features_t feature_whitelist;
 	struct cfg80211_chan_def dflt_chandef = {};
 
@@ -905,6 +906,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 	max_bitrates = 0;
 	supp_ht = false;
 	supp_vht = false;
+	supp_he = false;
 	for (band = 0; band < NUM_NL80211_BANDS; band++) {
 		struct ieee80211_supported_band *sband;
 
@@ -931,6 +933,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		supp_ht = supp_ht || sband->ht_cap.ht_supported;
 		supp_vht = supp_vht || sband->vht_cap.vht_supported;
 
+		if (!supp_he)
+			supp_he = !!ieee80211_get_he_sta_cap(sband);
+
 		if (!sband->ht_cap.ht_supported)
 			continue;
 
@@ -1020,6 +1025,18 @@ int ieee80211_register_hw(struct ieee80211_hw *hw)
 		local->scan_ies_len +=
 			2 + sizeof(struct ieee80211_vht_cap);
 
+	/* HE cap element is variable in size - set len to allow max size */
+	/*
+	 * TODO: 1 is added at the end of the calculation to accommodate for
+	 *	the temporary placing of the HE capabilities IE under EXT.
+	 *	Remove it once it is placed in the final place.
+	 */
+	if (supp_he)
+		local->scan_ies_len +=
+			2 + sizeof(struct ieee80211_he_cap_elem) +
+			sizeof(struct ieee80211_he_mcs_nss_supp) +
+			IEEE80211_HE_PPE_THRES_MAX_LEN + 1;
+
 	if (!local->ops->hw_scan) {
 		/* For hw_scan, driver needs to set these up. */
 		local->hw.wiphy->max_scan_ssids = 4;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a44e5b4aaeda..0322d78007ad 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -149,6 +149,7 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 			     struct ieee80211_channel *channel,
 			     const struct ieee80211_ht_operation *ht_oper,
 			     const struct ieee80211_vht_operation *vht_oper,
+			     const struct ieee80211_he_operation *he_oper,
 			     struct cfg80211_chan_def *chandef, bool tracking)
 {
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -207,7 +208,27 @@ ieee80211_determine_chantype(struct ieee80211_sub_if_data *sdata,
 	}
 
 	vht_chandef = *chandef;
-	if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) {
+	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) && he_oper &&
+	    (le32_to_cpu(he_oper->he_oper_params) &
+	     IEEE80211_HE_OPERATION_VHT_OPER_INFO)) {
+		struct ieee80211_vht_operation he_oper_vht_cap;
+
+		/*
+		 * Set only first 3 bytes (other 2 aren't used in
+		 * ieee80211_chandef_vht_oper() anyway)
+		 */
+		memcpy(&he_oper_vht_cap, he_oper->optional, 3);
+		he_oper_vht_cap.basic_mcs_set = cpu_to_le16(0);
+
+		if (!ieee80211_chandef_vht_oper(&he_oper_vht_cap,
+						&vht_chandef)) {
+			if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE))
+				sdata_info(sdata,
+					   "HE AP VHT information is invalid, disable HE\n");
+			ret = IEEE80211_STA_DISABLE_HE;
+			goto out;
+		}
+	} else if (!ieee80211_chandef_vht_oper(vht_oper, &vht_chandef)) {
 		if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
 			sdata_info(sdata,
 				   "AP VHT information is invalid, disable VHT\n");
@@ -300,12 +321,14 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 			       const struct ieee80211_ht_cap *ht_cap,
 			       const struct ieee80211_ht_operation *ht_oper,
 			       const struct ieee80211_vht_operation *vht_oper,
+			       const struct ieee80211_he_operation *he_oper,
 			       const u8 *bssid, u32 *changed)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
-	struct ieee80211_supported_band *sband;
-	struct ieee80211_channel *chan;
+	struct ieee80211_channel *chan = sdata->vif.bss_conf.chandef.chan;
+	struct ieee80211_supported_band *sband =
+		local->hw.wiphy->bands[chan->band];
 	struct cfg80211_chan_def chandef;
 	u16 ht_opmode;
 	u32 flags;
@@ -320,6 +343,11 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->flags & IEEE80211_STA_DISABLE_VHT)
 		vht_oper = NULL;
 
+	/* don't check HE if we associated as non-HE station */
+	if (ifmgd->flags & IEEE80211_STA_DISABLE_HE ||
+	    !ieee80211_get_he_sta_cap(sband))
+		he_oper = NULL;
+
 	if (WARN_ON_ONCE(!sta))
 		return -EINVAL;
 
@@ -333,12 +361,9 @@ static int ieee80211_config_bw(struct ieee80211_sub_if_data *sdata,
 		sdata->vif.bss_conf.ht_operation_mode = ht_opmode;
 	}
 
-	chan = sdata->vif.bss_conf.chandef.chan;
-	sband = local->hw.wiphy->bands[chan->band];
-
-	/* calculate new channel (type) based on HT/VHT operation IEs */
+	/* calculate new channel (type) based on HT/VHT/HE operation IEs */
 	flags = ieee80211_determine_chantype(sdata, sband, chan,
-					     ht_oper, vht_oper,
+					     ht_oper, vht_oper, he_oper,
 					     &chandef, true);
 
 	/*
@@ -582,6 +607,34 @@ static void ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 	ieee80211_ie_build_vht_cap(pos, &vht_cap, cap);
 }
 
+/* This function determines HE capability flags for the association
+ * and builds the IE.
+ */
+static void ieee80211_add_he_ie(struct ieee80211_sub_if_data *sdata,
+				struct sk_buff *skb,
+				struct ieee80211_supported_band *sband)
+{
+	u8 *pos;
+	const struct ieee80211_sta_he_cap *he_cap = NULL;
+	u8 he_cap_size;
+
+	he_cap = ieee80211_get_he_sta_cap(sband);
+	if (!he_cap)
+		return;
+
+	/*
+	 * TODO: the 1 added is because this temporarily is under the EXTENSION
+	 * IE. Get rid of it when it moves.
+	 */
+	he_cap_size =
+		2 + 1 + sizeof(he_cap->he_cap_elem) +
+		ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem) +
+		ieee80211_he_ppe_size(he_cap->ppe_thres[0],
+				      he_cap->he_cap_elem.phy_cap_info);
+	pos = skb_put(skb, he_cap_size);
+	ieee80211_ie_build_he_cap(pos, he_cap, pos + he_cap_size);
+}
+
 static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 {
 	struct ieee80211_local *local = sdata->local;
@@ -643,6 +696,9 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 			2 + 2 * sband->n_channels + /* supported channels */
 			2 + sizeof(struct ieee80211_ht_cap) + /* HT */
 			2 + sizeof(struct ieee80211_vht_cap) + /* VHT */
+			2 + 1 + sizeof(struct ieee80211_he_cap_elem) + /* HE */
+				sizeof(struct ieee80211_he_mcs_nss_supp) +
+				IEEE80211_HE_PPE_THRES_MAX_LEN +
 			assoc_data->ie_len + /* extra IEs */
 			(assoc_data->fils_kek_len ? 16 /* AES-SIV */ : 0) +
 			9, /* WMM */
@@ -827,11 +883,41 @@ static void ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		offset = noffset;
 	}
 
+	/* if present, add any custom IEs that go before HE */
+	if (assoc_data->ie_len) {
+		static const u8 before_he[] = {
+			/*
+			 * no need to list the ones split off before VHT
+			 * or generated here
+			 */
+			WLAN_EID_OPMODE_NOTIF,
+			WLAN_EID_EXTENSION, WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE,
+			/* 11ai elements */
+			WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_SESSION,
+			WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_PUBLIC_KEY,
+			WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_KEY_CONFIRM,
+			WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_HLP_CONTAINER,
+			WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_IP_ADDR_ASSIGN,
+			/* TODO: add 11ah/11aj/11ak elements */
+		};
+
+		/* RIC already taken above, so no need to handle here anymore */
+		noffset = ieee80211_ie_split(assoc_data->ie, assoc_data->ie_len,
+					     before_he, ARRAY_SIZE(before_he),
+					     offset);
+		pos = skb_put(skb, noffset - offset);
+		memcpy(pos, assoc_data->ie + offset, noffset - offset);
+		offset = noffset;
+	}
+
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_VHT))
 		ieee80211_add_vht_ie(sdata, skb, sband,
 				     &assoc_data->ap_vht_cap);
 
-	/* if present, add any custom non-vendor IEs that go after HT */
+	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE))
+		ieee80211_add_he_ie(sdata, skb, sband);
+
+	/* if present, add any custom non-vendor IEs that go after HE */
 	if (assoc_data->ie_len) {
 		noffset = ieee80211_ie_split_vendor(assoc_data->ie,
 						    assoc_data->ie_len,
@@ -898,6 +984,11 @@ void ieee80211_send_nullfunc(struct ieee80211_local *local,
 	struct ieee80211_hdr_3addr *nullfunc;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 
+	/* Don't send NDPs when STA is connected HE */
+	if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+	    !(ifmgd->flags & IEEE80211_STA_DISABLE_HE))
+		return;
+
 	skb = ieee80211_nullfunc_get(&local->hw, &sdata->vif,
 		!ieee80211_hw_check(&local->hw, DOESNT_SUPPORT_QOS_NDP));
 	if (!skb)
@@ -929,6 +1020,10 @@ static void ieee80211_send_4addr_nullfunc(struct ieee80211_local *local,
 	if (WARN_ON(sdata->vif.type != NL80211_IFTYPE_STATION))
 		return;
 
+	/* Don't send NDPs when connected HE */
+	if (!(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE))
+		return;
+
 	skb = dev_alloc_skb(local->hw.extra_tx_headroom + 30);
 	if (!skb)
 		return;
@@ -1700,9 +1795,11 @@ static void ieee80211_sta_handle_tspec_ac_params_wk(struct work_struct *work)
 }
 
 /* MLME */
-static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
-				     struct ieee80211_sub_if_data *sdata,
-				     const u8 *wmm_param, size_t wmm_param_len)
+static bool
+ieee80211_sta_wmm_params(struct ieee80211_local *local,
+			 struct ieee80211_sub_if_data *sdata,
+			 const u8 *wmm_param, size_t wmm_param_len,
+			 const struct ieee80211_mu_edca_param_set *mu_edca)
 {
 	struct ieee80211_tx_queue_params params[IEEE80211_NUM_ACS];
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
@@ -1749,6 +1846,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 				sdata->wmm_acm |= BIT(1) | BIT(2); /* BK/- */
 			if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK)
 				uapsd = true;
+			params[ac].mu_edca = !!mu_edca;
+			if (mu_edca)
+				params[ac].mu_edca_param_rec = mu_edca->ac_bk;
 			break;
 		case 2: /* AC_VI */
 			ac = IEEE80211_AC_VI;
@@ -1756,6 +1856,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 				sdata->wmm_acm |= BIT(4) | BIT(5); /* CL/VI */
 			if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI)
 				uapsd = true;
+			params[ac].mu_edca = !!mu_edca;
+			if (mu_edca)
+				params[ac].mu_edca_param_rec = mu_edca->ac_vi;
 			break;
 		case 3: /* AC_VO */
 			ac = IEEE80211_AC_VO;
@@ -1763,6 +1866,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 				sdata->wmm_acm |= BIT(6) | BIT(7); /* VO/NC */
 			if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO)
 				uapsd = true;
+			params[ac].mu_edca = !!mu_edca;
+			if (mu_edca)
+				params[ac].mu_edca_param_rec = mu_edca->ac_vo;
 			break;
 		case 0: /* AC_BE */
 		default:
@@ -1771,6 +1877,9 @@ static bool ieee80211_sta_wmm_params(struct ieee80211_local *local,
 				sdata->wmm_acm |= BIT(0) | BIT(3); /* BE/EE */
 			if (uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE)
 				uapsd = true;
+			params[ac].mu_edca = !!mu_edca;
+			if (mu_edca)
+				params[ac].mu_edca_param_rec = mu_edca->ac_be;
 			break;
 		}
 
@@ -3021,6 +3130,25 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		goto out;
 	}
 
+	/*
+	 * If AP doesn't support HT, or it doesn't have HE mandatory IEs, mark
+	 * HE as disabled. If on the 5GHz band, make sure it supports VHT.
+	 */
+	if (ifmgd->flags & IEEE80211_STA_DISABLE_HT ||
+	    (sband->band == NL80211_BAND_5GHZ &&
+	     ifmgd->flags & IEEE80211_STA_DISABLE_VHT) ||
+	    (!elems.he_cap && !elems.he_operation))
+		ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
+
+	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
+	    (!elems.he_cap || !elems.he_operation)) {
+		mutex_unlock(&sdata->local->sta_mtx);
+		sdata_info(sdata,
+			   "HE AP is missing HE capability/operation\n");
+		ret = false;
+		goto out;
+	}
+
 	/* Set up internal HT/VHT capabilities */
 	if (elems.ht_cap_elem && !(ifmgd->flags & IEEE80211_STA_DISABLE_HT))
 		ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,
@@ -3030,6 +3158,48 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 		ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
 						    elems.vht_cap_elem, sta);
 
+	if (elems.he_operation && !(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
+	    elems.he_cap) {
+		ieee80211_he_cap_ie_to_sta_he_cap(sdata, sband,
+						  elems.he_cap,
+						  elems.he_cap_len,
+						  sta);
+
+		bss_conf->he_support = sta->sta.he_cap.has_he;
+	} else {
+		bss_conf->he_support = false;
+	}
+
+	if (bss_conf->he_support) {
+		u32 he_oper_params =
+			le32_to_cpu(elems.he_operation->he_oper_params);
+
+		bss_conf->bss_color = he_oper_params &
+				      IEEE80211_HE_OPERATION_BSS_COLOR_MASK;
+		bss_conf->htc_trig_based_pkt_ext =
+			(he_oper_params &
+			 IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK) <<
+			IEEE80211_HE_OPERATION_DFLT_PE_DURATION_OFFSET;
+		bss_conf->frame_time_rts_th =
+			(he_oper_params &
+			 IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK) <<
+			IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET;
+
+		bss_conf->multi_sta_back_32bit =
+			sta->sta.he_cap.he_cap_elem.mac_cap_info[2] &
+			IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP;
+
+		bss_conf->ack_enabled =
+			sta->sta.he_cap.he_cap_elem.mac_cap_info[2] &
+			IEEE80211_HE_MAC_CAP2_ACK_EN;
+
+		bss_conf->uora_exists = !!elems.uora_element;
+		if (elems.uora_element)
+			bss_conf->uora_ocw_range = elems.uora_element[0];
+
+		/* TODO: OPEN: what happens if BSS color disable is set? */
+	}
+
 	/*
 	 * Some APs, e.g. Netgear WNDR3700, report invalid HT operation data
 	 * in their association response, so ignore that data for our own
@@ -3089,7 +3259,8 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 	if (ifmgd->flags & IEEE80211_STA_DISABLE_WMM) {
 		ieee80211_set_wmm_default(sdata, false, false);
 	} else if (!ieee80211_sta_wmm_params(local, sdata, elems.wmm_param,
-					     elems.wmm_param_len)) {
+					     elems.wmm_param_len,
+					     elems.mu_edca_param_set)) {
 		/* still enable QoS since we might have HT/VHT */
 		ieee80211_set_wmm_default(sdata, false, true);
 		/* set the disable-WMM flag in this case to disable
@@ -3603,7 +3774,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 
 	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_WMM) &&
 	    ieee80211_sta_wmm_params(local, sdata, elems.wmm_param,
-				     elems.wmm_param_len))
+				     elems.wmm_param_len,
+				     elems.mu_edca_param_set))
 		changed |= BSS_CHANGED_QOS;
 
 	/*
@@ -3642,7 +3814,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_sub_if_data *sdata,
 
 	if (ieee80211_config_bw(sdata, sta,
 				elems.ht_cap_elem, elems.ht_operation,
-				elems.vht_operation, bssid, &changed)) {
+				elems.vht_operation, elems.he_operation,
+				bssid, &changed)) {
 		mutex_unlock(&local->sta_mtx);
 		sdata_info(sdata,
 			   "failed to follow AP %pM bandwidth change, disconnect\n",
@@ -4279,6 +4452,66 @@ static u8 ieee80211_ht_vht_rx_chains(struct ieee80211_sub_if_data *sdata,
 	return chains;
 }
 
+static bool
+ieee80211_verify_sta_he_mcs_support(struct ieee80211_supported_band *sband,
+				    const struct ieee80211_he_operation *he_op)
+{
+	const struct ieee80211_sta_he_cap *sta_he_cap =
+		ieee80211_get_he_sta_cap(sband);
+	u16 ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set);
+	int i;
+
+	if (!sta_he_cap || !he_op)
+		return false;
+
+	/* Need to go over for 80MHz, 160MHz and for 80+80 */
+	for (i = 0; i < 3; i++) {
+		const struct ieee80211_he_mcs_nss_supp *sta_mcs_nss_supp =
+			&sta_he_cap->he_mcs_nss_supp;
+		u16 sta_mcs_map_rx =
+			le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i]);
+		u16 sta_mcs_map_tx =
+			le16_to_cpu(((__le16 *)sta_mcs_nss_supp)[2 * i + 1]);
+		u8 nss;
+		bool verified = true;
+
+		/*
+		 * For each band there is a maximum of 8 spatial streams
+		 * possible. Each of the sta_mcs_map_* is a 16-bit struct built
+		 * of 2 bits per NSS (1-8), with the values defined in enum
+		 * ieee80211_he_mcs_support. Need to make sure STA TX and RX
+		 * capabilities aren't less than the AP's minimum requirements
+		 * for this HE BSS per SS.
+		 * It is enough to find one such band that meets the reqs.
+		 */
+		for (nss = 8; nss > 0; nss--) {
+			u8 sta_rx_val = (sta_mcs_map_rx >> (2 * (nss - 1))) & 3;
+			u8 sta_tx_val = (sta_mcs_map_tx >> (2 * (nss - 1))) & 3;
+			u8 ap_val = (ap_min_req_set >> (2 * (nss - 1))) & 3;
+
+			if (ap_val == IEEE80211_HE_MCS_NOT_SUPPORTED)
+				continue;
+
+			/*
+			 * Make sure the HE AP doesn't require MCSs that aren't
+			 * supported by the client
+			 */
+			if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+			    sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+			    (ap_val > sta_rx_val) || (ap_val > sta_tx_val)) {
+				verified = false;
+				break;
+			}
+		}
+
+		if (verified)
+			return true;
+	}
+
+	/* If here, STA doesn't meet AP's HE min requirements */
+	return false;
+}
+
 static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 				  struct cfg80211_bss *cbss)
 {
@@ -4287,6 +4520,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 	const struct ieee80211_ht_cap *ht_cap = NULL;
 	const struct ieee80211_ht_operation *ht_oper = NULL;
 	const struct ieee80211_vht_operation *vht_oper = NULL;
+	const struct ieee80211_he_operation *he_oper = NULL;
 	struct ieee80211_supported_band *sband;
 	struct cfg80211_chan_def chandef;
 	int ret;
@@ -4342,6 +4576,25 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 		}
 	}
 
+	if (!(ifmgd->flags & IEEE80211_STA_DISABLE_HE) &&
+	    ieee80211_get_he_sta_cap(sband)) {
+		const struct cfg80211_bss_ies *ies;
+		const u8 *he_oper_ie;
+
+		ies = rcu_dereference(cbss->ies);
+		he_oper_ie = cfg80211_find_ext_ie(WLAN_EID_EXT_HE_OPERATION,
+						  ies->data, ies->len);
+		if (he_oper_ie &&
+		    he_oper_ie[1] == ieee80211_he_oper_size(&he_oper_ie[3]))
+			he_oper = (void *)(he_oper_ie + 3);
+		else
+			he_oper = NULL;
+
+		if (!he_oper ||
+		    !ieee80211_verify_sta_he_mcs_support(sband, he_oper))
+			ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
+	}
+
 	/* Allow VHT if at least one channel on the sband supports 80 MHz */
 	have_80mhz = false;
 	for (i = 0; i < sband->n_channels; i++) {
@@ -4358,7 +4611,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 
 	ifmgd->flags |= ieee80211_determine_chantype(sdata, sband,
 						     cbss->channel,
-						     ht_oper, vht_oper,
+						     ht_oper, vht_oper, he_oper,
 						     &chandef, false);
 
 	sdata->needed_rx_chains = min(ieee80211_ht_vht_rx_chains(sdata, cbss),
@@ -4764,8 +5017,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 		    req->crypto.ciphers_pairwise[i] == WLAN_CIPHER_SUITE_WEP104) {
 			ifmgd->flags |= IEEE80211_STA_DISABLE_HT;
 			ifmgd->flags |= IEEE80211_STA_DISABLE_VHT;
+			ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
 			netdev_info(sdata->dev,
-				    "disabling HT/VHT due to WEP/TKIP use\n");
+				    "disabling HE/HT/VHT due to WEP/TKIP use\n");
 		}
 	}
 
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 756ba176db1e..a16ba568e2a3 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -175,6 +175,20 @@ ieee80211_rx_radiotap_hdrlen(struct ieee80211_local *local,
 		len += 12;
 	}
 
+	if (status->encoding == RX_ENC_HE &&
+	    status->flag & RX_FLAG_RADIOTAP_HE) {
+		len = ALIGN(len, 2);
+		len += 12;
+		BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he) != 12);
+	}
+
+	if (status->encoding == RX_ENC_HE &&
+	    status->flag & RX_FLAG_RADIOTAP_HE_MU) {
+		len = ALIGN(len, 2);
+		len += 12;
+		BUILD_BUG_ON(sizeof(struct ieee80211_radiotap_he_mu) != 12);
+	}
+
 	if (status->chains) {
 		/* antenna and antenna signal fields */
 		len += 2 * hweight8(status->chains);
@@ -263,6 +277,19 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 	int mpdulen, chain;
 	unsigned long chains = status->chains;
 	struct ieee80211_vendor_radiotap rtap = {};
+	struct ieee80211_radiotap_he he = {};
+	struct ieee80211_radiotap_he_mu he_mu = {};
+
+	if (status->flag & RX_FLAG_RADIOTAP_HE) {
+		he = *(struct ieee80211_radiotap_he *)skb->data;
+		skb_pull(skb, sizeof(he));
+		WARN_ON_ONCE(status->encoding != RX_ENC_HE);
+	}
+
+	if (status->flag & RX_FLAG_RADIOTAP_HE_MU) {
+		he_mu = *(struct ieee80211_radiotap_he_mu *)skb->data;
+		skb_pull(skb, sizeof(he_mu));
+	}
 
 	if (status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA) {
 		rtap = *(struct ieee80211_vendor_radiotap *)skb->data;
@@ -520,6 +547,89 @@ ieee80211_add_rx_radiotap_header(struct ieee80211_local *local,
 		*pos++ = flags;
 	}
 
+	if (status->encoding == RX_ENC_HE &&
+	    status->flag & RX_FLAG_RADIOTAP_HE) {
+#define HE_PREP(f, val)	cpu_to_le16(FIELD_PREP(IEEE80211_RADIOTAP_HE_##f, val))
+
+		if (status->enc_flags & RX_ENC_FLAG_STBC_MASK) {
+			he.data6 |= HE_PREP(DATA6_NSTS,
+					    FIELD_GET(RX_ENC_FLAG_STBC_MASK,
+						      status->enc_flags));
+			he.data3 |= HE_PREP(DATA3_STBC, 1);
+		} else {
+			he.data6 |= HE_PREP(DATA6_NSTS, status->nss);
+		}
+
+#define CHECK_GI(s) \
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_GI_##s != \
+		     (int)NL80211_RATE_INFO_HE_GI_##s)
+
+		CHECK_GI(0_8);
+		CHECK_GI(1_6);
+		CHECK_GI(3_2);
+
+		he.data3 |= HE_PREP(DATA3_DATA_MCS, status->rate_idx);
+		he.data3 |= HE_PREP(DATA3_DATA_DCM, status->he_dcm);
+		he.data3 |= HE_PREP(DATA3_CODING,
+				    !!(status->enc_flags & RX_ENC_FLAG_LDPC));
+
+		he.data5 |= HE_PREP(DATA5_GI, status->he_gi);
+
+		switch (status->bw) {
+		case RATE_INFO_BW_20:
+			he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+					    IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_20MHZ);
+			break;
+		case RATE_INFO_BW_40:
+			he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+					    IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_40MHZ);
+			break;
+		case RATE_INFO_BW_80:
+			he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+					    IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_80MHZ);
+			break;
+		case RATE_INFO_BW_160:
+			he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+					    IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_160MHZ);
+			break;
+		case RATE_INFO_BW_HE_RU:
+#define CHECK_RU_ALLOC(s) \
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA5_DATA_BW_RU_ALLOC_##s##T != \
+		     NL80211_RATE_INFO_HE_RU_ALLOC_##s + 4)
+
+			CHECK_RU_ALLOC(26);
+			CHECK_RU_ALLOC(52);
+			CHECK_RU_ALLOC(106);
+			CHECK_RU_ALLOC(242);
+			CHECK_RU_ALLOC(484);
+			CHECK_RU_ALLOC(996);
+			CHECK_RU_ALLOC(2x996);
+
+			he.data5 |= HE_PREP(DATA5_DATA_BW_RU_ALLOC,
+					    status->he_ru + 4);
+			break;
+		default:
+			WARN_ONCE(1, "Invalid SU BW %d\n", status->bw);
+		}
+
+		/* ensure 2 byte alignment */
+		while ((pos - (u8 *)rthdr) & 1)
+			pos++;
+		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE);
+		memcpy(pos, &he, sizeof(he));
+		pos += sizeof(he);
+	}
+
+	if (status->encoding == RX_ENC_HE &&
+	    status->flag & RX_FLAG_RADIOTAP_HE_MU) {
+		/* ensure 2 byte alignment */
+		while ((pos - (u8 *)rthdr) & 1)
+			pos++;
+		rthdr->it_present |= cpu_to_le32(1 << IEEE80211_RADIOTAP_HE_MU);
+		memcpy(pos, &he_mu, sizeof(he_mu));
+		pos += sizeof(he_mu);
+	}
+
 	for_each_set_bit(chain, &chains, IEEE80211_MAX_CHAINS) {
 		*pos++ = status->chain_signal[chain];
 		*pos++ = chain;
@@ -613,6 +723,12 @@ ieee80211_rx_monitor(struct ieee80211_local *local, struct sk_buff *origskb,
 		rcu_dereference(local->monitor_sdata);
 	bool only_monitor = false;
 
+	if (status->flag & RX_FLAG_RADIOTAP_HE)
+		rtap_space += sizeof(struct ieee80211_radiotap_he);
+
+	if (status->flag & RX_FLAG_RADIOTAP_HE_MU)
+		rtap_space += sizeof(struct ieee80211_radiotap_he_mu);
+
 	if (unlikely(status->flag & RX_FLAG_RADIOTAP_VENDOR_DATA)) {
 		struct ieee80211_vendor_radiotap *rtap = (void *)origskb->data;
 
@@ -3386,8 +3502,7 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx,
 		status = IEEE80211_SKB_RXCB((rx->skb));
 
 		sband = rx->local->hw.wiphy->bands[status->band];
-		if (!(status->encoding == RX_ENC_HT) &&
-		    !(status->encoding == RX_ENC_VHT))
+		if (status->encoding == RX_ENC_LEGACY)
 			rate = &sband->bitrates[status->rate_idx];
 
 		ieee80211_rx_cooked_monitor(rx, rate);
@@ -4386,6 +4501,14 @@ void ieee80211_rx_napi(struct ieee80211_hw *hw, struct ieee80211_sta *pubsta,
 				      status->rate_idx, status->nss))
 				goto drop;
 			break;
+		case RX_ENC_HE:
+			if (WARN_ONCE(status->rate_idx > 11 ||
+				      !status->nss ||
+				      status->nss > 8,
+				      "Rate marked as an HE rate but data is invalid: MCS: %d, NSS: %d\n",
+				      status->rate_idx, status->nss))
+				goto drop;
+			break;
 		default:
 			WARN_ON_ONCE(1);
 			/* fall through */
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index aa96fddfbfc2..aa8fe771a8db 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -1323,6 +1323,11 @@ static void ieee80211_send_null_response(struct sta_info *sta, int tid,
 	struct ieee80211_tx_info *info;
 	struct ieee80211_chanctx_conf *chanctx_conf;
 
+	/* Don't send NDPs when STA is connected HE */
+	if (sdata->vif.type == NL80211_IFTYPE_STATION &&
+	    !(sdata->u.mgd.flags & IEEE80211_STA_DISABLE_HE))
+		return;
+
 	if (qos) {
 		fc = cpu_to_le16(IEEE80211_FTYPE_DATA |
 				 IEEE80211_STYPE_QOS_NULLFUNC |
@@ -1968,7 +1973,7 @@ sta_get_last_rx_stats(struct sta_info *sta)
 	return stats;
 }
 
-static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate,
+static void sta_stats_decode_rate(struct ieee80211_local *local, u32 rate,
 				  struct rate_info *rinfo)
 {
 	rinfo->bw = STA_STATS_GET(BW, rate);
@@ -2005,6 +2010,14 @@ static void sta_stats_decode_rate(struct ieee80211_local *local, u16 rate,
 		rinfo->legacy = DIV_ROUND_UP(brate, 1 << shift);
 		break;
 		}
+	case STA_STATS_RATE_TYPE_HE:
+		rinfo->flags = RATE_INFO_FLAGS_HE_MCS;
+		rinfo->mcs = STA_STATS_GET(HE_MCS, rate);
+		rinfo->nss = STA_STATS_GET(HE_NSS, rate);
+		rinfo->he_gi = STA_STATS_GET(HE_GI, rate);
+		rinfo->he_ru_alloc = STA_STATS_GET(HE_RU, rate);
+		rinfo->he_dcm = STA_STATS_GET(HE_DCM, rate);
+		break;
 	}
 }
 
diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
index 81b35f623792..9a04327d71d1 100644
--- a/net/mac80211/sta_info.h
+++ b/net/mac80211/sta_info.h
@@ -170,7 +170,7 @@ struct tid_ampdu_tx {
 	u8 dialog_token;
 	u8 stop_initiator;
 	bool tx_stop;
-	u8 buf_size;
+	u16 buf_size;
 
 	u16 failed_bar_ssn;
 	bool bar_pending;
@@ -405,7 +405,7 @@ struct ieee80211_sta_rx_stats {
 	int last_signal;
 	u8 chains;
 	s8 chain_signal_last[IEEE80211_MAX_CHAINS];
-	u16 last_rate;
+	u32 last_rate;
 	struct u64_stats_sync syncp;
 	u64 bytes;
 	u64 msdu[IEEE80211_NUM_TIDS + 1];
@@ -764,6 +764,7 @@ enum sta_stats_type {
 	STA_STATS_RATE_TYPE_LEGACY,
 	STA_STATS_RATE_TYPE_HT,
 	STA_STATS_RATE_TYPE_VHT,
+	STA_STATS_RATE_TYPE_HE,
 };
 
 #define STA_STATS_FIELD_HT_MCS		GENMASK( 7,  0)
@@ -771,9 +772,14 @@ enum sta_stats_type {
 #define STA_STATS_FIELD_LEGACY_BAND	GENMASK( 7,  4)
 #define STA_STATS_FIELD_VHT_MCS		GENMASK( 3,  0)
 #define STA_STATS_FIELD_VHT_NSS		GENMASK( 7,  4)
+#define STA_STATS_FIELD_HE_MCS		GENMASK( 3,  0)
+#define STA_STATS_FIELD_HE_NSS		GENMASK( 7,  4)
 #define STA_STATS_FIELD_BW		GENMASK(11,  8)
 #define STA_STATS_FIELD_SGI		GENMASK(12, 12)
 #define STA_STATS_FIELD_TYPE		GENMASK(15, 13)
+#define STA_STATS_FIELD_HE_RU		GENMASK(18, 16)
+#define STA_STATS_FIELD_HE_GI		GENMASK(20, 19)
+#define STA_STATS_FIELD_HE_DCM		GENMASK(21, 21)
 
 #define STA_STATS_FIELD(_n, _v)		FIELD_PREP(STA_STATS_FIELD_ ## _n, _v)
 #define STA_STATS_GET(_n, _v)		FIELD_GET(STA_STATS_FIELD_ ## _n, _v)
@@ -782,7 +788,7 @@ enum sta_stats_type {
 
 static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s)
 {
-	u16 r;
+	u32 r;
 
 	r = STA_STATS_FIELD(BW, s->bw);
 
@@ -804,6 +810,14 @@ static inline u32 sta_stats_encode_rate(struct ieee80211_rx_status *s)
 		r |= STA_STATS_FIELD(LEGACY_BAND, s->band);
 		r |= STA_STATS_FIELD(LEGACY_IDX, s->rate_idx);
 		break;
+	case RX_ENC_HE:
+		r |= STA_STATS_FIELD(TYPE, STA_STATS_RATE_TYPE_HE);
+		r |= STA_STATS_FIELD(HE_NSS, s->nss);
+		r |= STA_STATS_FIELD(HE_MCS, s->rate_idx);
+		r |= STA_STATS_FIELD(HE_GI, s->he_gi);
+		r |= STA_STATS_FIELD(HE_RU, s->he_ru);
+		r |= STA_STATS_FIELD(HE_DCM, s->he_dcm);
+		break;
 	default:
 		WARN_ON(1);
 		return STA_STATS_RATE_INVALID;
diff --git a/net/mac80211/trace.h b/net/mac80211/trace.h
index 80a7edf8d314..0ab69a1964f8 100644
--- a/net/mac80211/trace.h
+++ b/net/mac80211/trace.h
@@ -92,7 +92,7 @@
 				STA_ENTRY						\
 				__field(u16, tid)					\
 				__field(u16, ssn)					\
-				__field(u8, buf_size)					\
+				__field(u16, buf_size)					\
 				__field(bool, amsdu)					\
 				__field(u16, timeout)					\
 				__field(u16, action)
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index b744b10465c3..c77c84325348 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -1095,6 +1095,21 @@ u32 ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action,
 			if (elen >= sizeof(*elems->max_idle_period_ie))
 				elems->max_idle_period_ie = (void *)pos;
 			break;
+		case WLAN_EID_EXTENSION:
+			if (pos[0] == WLAN_EID_EXT_HE_MU_EDCA &&
+			    elen >= (sizeof(*elems->mu_edca_param_set) + 1)) {
+				elems->mu_edca_param_set = (void *)&pos[1];
+			} else if (pos[0] == WLAN_EID_EXT_HE_CAPABILITY) {
+				elems->he_cap = (void *)&pos[1];
+				elems->he_cap_len = elen - 1;
+			} else if (pos[0] == WLAN_EID_EXT_HE_OPERATION &&
+				   elen >= sizeof(*elems->he_operation) &&
+				   elen >= ieee80211_he_oper_size(&pos[1])) {
+				elems->he_operation = (void *)&pos[1];
+			} else if (pos[0] == WLAN_EID_EXT_UORA && elen >= 1) {
+				elems->uora_element = (void *)&pos[1];
+			}
+			break;
 		default:
 			break;
 		}
@@ -1356,6 +1371,7 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 					 size_t *offset, u32 flags)
 {
 	struct ieee80211_supported_band *sband;
+	const struct ieee80211_sta_he_cap *he_cap;
 	u8 *pos = buffer, *end = buffer + buffer_len;
 	size_t noffset;
 	int supp_rates_len, i;
@@ -1463,11 +1479,6 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 						sband->ht_cap.cap);
 	}
 
-	/*
-	 * If adding more here, adjust code in main.c
-	 * that calculates local->scan_ies_len.
-	 */
-
 	/* insert custom IEs that go before VHT */
 	if (ie && ie_len) {
 		static const u8 before_vht[] = {
@@ -1510,6 +1521,39 @@ static int ieee80211_build_preq_ies_band(struct ieee80211_local *local,
 						 sband->vht_cap.cap);
 	}
 
+	/* insert custom IEs that go before HE */
+	if (ie && ie_len) {
+		static const u8 before_he[] = {
+			/*
+			 * no need to list the ones split off before VHT
+			 * or generated here
+			 */
+			WLAN_EID_EXTENSION, WLAN_EID_EXT_FILS_REQ_PARAMS,
+			WLAN_EID_AP_CSN,
+			/* TODO: add 11ah/11aj/11ak elements */
+		};
+		noffset = ieee80211_ie_split(ie, ie_len,
+					     before_he, ARRAY_SIZE(before_he),
+					     *offset);
+		if (end - pos < noffset - *offset)
+			goto out_err;
+		memcpy(pos, ie + *offset, noffset - *offset);
+		pos += noffset - *offset;
+		*offset = noffset;
+	}
+
+	he_cap = ieee80211_get_he_sta_cap(sband);
+	if (he_cap) {
+		pos = ieee80211_ie_build_he_cap(pos, he_cap, end);
+		if (!pos)
+			goto out_err;
+	}
+
+	/*
+	 * If adding more here, adjust code in main.c
+	 * that calculates local->scan_ies_len.
+	 */
+
 	return pos - buffer;
  out_err:
 	WARN_ONCE(1, "not enough space for preq IEs\n");
@@ -2396,6 +2440,72 @@ u8 *ieee80211_ie_build_vht_cap(u8 *pos, struct ieee80211_sta_vht_cap *vht_cap,
 	return pos;
 }
 
+u8 *ieee80211_ie_build_he_cap(u8 *pos,
+			      const struct ieee80211_sta_he_cap *he_cap,
+			      u8 *end)
+{
+	u8 n;
+	u8 ie_len;
+	u8 *orig_pos = pos;
+
+	/* Make sure we have place for the IE */
+	/*
+	 * TODO: the 1 added is because this temporarily is under the EXTENSION
+	 * IE. Get rid of it when it moves.
+	 */
+	if (!he_cap)
+		return orig_pos;
+
+	n = ieee80211_he_mcs_nss_size(&he_cap->he_cap_elem);
+	ie_len = 2 + 1 +
+		 sizeof(he_cap->he_cap_elem) + n +
+		 ieee80211_he_ppe_size(he_cap->ppe_thres[0],
+				       he_cap->he_cap_elem.phy_cap_info);
+
+	if ((end - pos) < ie_len)
+		return orig_pos;
+
+	*pos++ = WLAN_EID_EXTENSION;
+	pos++; /* We'll set the size later below */
+	*pos++ = WLAN_EID_EXT_HE_CAPABILITY;
+
+	/* Fixed data */
+	memcpy(pos, &he_cap->he_cap_elem, sizeof(he_cap->he_cap_elem));
+	pos += sizeof(he_cap->he_cap_elem);
+
+	memcpy(pos, &he_cap->he_mcs_nss_supp, n);
+	pos += n;
+
+	/* Check if PPE Threshold should be present */
+	if ((he_cap->he_cap_elem.phy_cap_info[6] &
+	     IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0)
+		goto end;
+
+	/*
+	 * Calculate how many PPET16/PPET8 pairs are to come. Algorithm:
+	 * (NSS_M1 + 1) x (num of 1 bits in RU_INDEX_BITMASK)
+	 */
+	n = hweight8(he_cap->ppe_thres[0] &
+		     IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK);
+	n *= (1 + ((he_cap->ppe_thres[0] & IEEE80211_PPE_THRES_NSS_MASK) >>
+		   IEEE80211_PPE_THRES_NSS_POS));
+
+	/*
+	 * Each pair is 6 bits, and we need to add the 7 "header" bits to the
+	 * total size.
+	 */
+	n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7;
+	n = DIV_ROUND_UP(n, 8);
+
+	/* Copy PPE Thresholds */
+	memcpy(pos, &he_cap->ppe_thres, n);
+	pos += n;
+
+end:
+	orig_pos[1] = (pos - orig_pos) - 2;
+	return pos;
+}
+
 u8 *ieee80211_ie_build_ht_oper(u8 *pos, struct ieee80211_sta_ht_cap *ht_cap,
 			       const struct cfg80211_chan_def *chandef,
 			       u16 prot_mode, bool rifs_mode)
-- 
cgit v1.2.3


From 8ba6731ad4c7e9f612b2f7dae1b5ed6bfc884b67 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 18 Jun 2018 22:43:58 +0200
Subject: rfkill: add header files to MAINTAINERS

These files weren't covered by the MAINTAINERS file,
add them.

Reported-by: Peter Meerwald-Stadler <pmeerw@pmeerw.net>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 2c7069037a15..1fe2aac28177 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12155,6 +12155,8 @@ S:	Maintained
 F:	Documentation/rfkill.txt
 F:	Documentation/ABI/stable/sysfs-class-rfkill
 F:	net/rfkill/
+F:	include/linux/rfkill.h
+F:	include/uapi/linux/rfkill.h
 
 RHASHTABLE
 M:	Thomas Graf <tgraf@suug.ch>
-- 
cgit v1.2.3


From 5ee8ee86c86f30950a6e53eb5a340e929353e855 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Mon, 18 Jun 2018 11:09:43 -0700
Subject: drm/i915/i915_reg.h: fix the checkpatch SPACING issues

Because OCD.

Now seriously, commit 1aa920ea0e85 ("drm/i915: add register macro
definition style guide") has finally established a coding standard to
be followed by the rest of the file, and I've been trying to request
everybody to adhere to that since then. The problem is that when
someone adds a new line to a register that has the wrong style, these
people generally propagate the wrong style and I have to keep asking
them to drive-by fix the whole register, which is not something I like
to do and also creates extra work for them. Or I can ignore the
propagation of the wrong coding style and feel anxious about it. On
top of that, we now have our CI happily reminding us about these
problems, which makes everything worse.

So IMHO the best way to proceed is to fix the spacing issues in the
file once and for all. Contributors will stop propagating the bad
style when adding new bits to registers that already have bad style,
we will stop asking them to redo their patches and the CI emails will
become more relevant by having less semi-false errors.

Yes, there will be some pain involved for backporters, but at least
spacing issues like that are easy to spot and fix in the patch files.

This patch was generated by:

../../../../scripts/checkpatch.pl -f --strict --types SPACING \
	--fix-inplace i915_reg.h

I manually checked the output and everything seems sane.

v2: Single conflict around the addition of DP_TP_CTL_LINK_TRAIN_PAT4.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618180943.894-1-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 3184 +++++++++++++++++++--------------------
 1 file changed, 1592 insertions(+), 1592 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 1f928bac2532..b0dd26fc1ee3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -141,17 +141,17 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define _PICK(__index, ...) (((const u32 []){ __VA_ARGS__ })[__index])
 
-#define _PIPE(pipe, a, b) ((a) + (pipe)*((b)-(a)))
+#define _PIPE(pipe, a, b) ((a) + (pipe) * ((b) - (a)))
 #define _MMIO_PIPE(pipe, a, b) _MMIO(_PIPE(pipe, a, b))
 #define _PLANE(plane, a, b) _PIPE(plane, a, b)
 #define _MMIO_PLANE(plane, a, b) _MMIO_PIPE(plane, a, b)
-#define _TRANS(tran, a, b) ((a) + (tran)*((b)-(a)))
+#define _TRANS(tran, a, b) ((a) + (tran) * ((b) - (a)))
 #define _MMIO_TRANS(tran, a, b) _MMIO(_TRANS(tran, a, b))
-#define _PORT(port, a, b) ((a) + (port)*((b)-(a)))
+#define _PORT(port, a, b) ((a) + (port) * ((b) - (a)))
 #define _MMIO_PORT(port, a, b) _MMIO(_PORT(port, a, b))
 #define _MMIO_PIPE3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
 #define _MMIO_PORT3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
-#define _PLL(pll, a, b) ((a) + (pll)*((b)-(a)))
+#define _PLL(pll, a, b) ((a) + (pll) * ((b) - (a)))
 #define _MMIO_PLL(pll, a, b) _MMIO(_PLL(pll, a, b))
 #define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__)
 #define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c))
@@ -271,19 +271,19 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 
 #define ILK_GDSR _MMIO(MCHBAR_MIRROR_BASE + 0x2ca4)
-#define  ILK_GRDOM_FULL		(0<<1)
-#define  ILK_GRDOM_RENDER	(1<<1)
-#define  ILK_GRDOM_MEDIA	(3<<1)
-#define  ILK_GRDOM_MASK		(3<<1)
-#define  ILK_GRDOM_RESET_ENABLE (1<<0)
+#define  ILK_GRDOM_FULL		(0 << 1)
+#define  ILK_GRDOM_RENDER	(1 << 1)
+#define  ILK_GRDOM_MEDIA	(3 << 1)
+#define  ILK_GRDOM_MASK		(3 << 1)
+#define  ILK_GRDOM_RESET_ENABLE (1 << 0)
 
 #define GEN6_MBCUNIT_SNPCR	_MMIO(0x900c) /* for LLC config */
 #define   GEN6_MBC_SNPCR_SHIFT	21
-#define   GEN6_MBC_SNPCR_MASK	(3<<21)
-#define   GEN6_MBC_SNPCR_MAX	(0<<21)
-#define   GEN6_MBC_SNPCR_MED	(1<<21)
-#define   GEN6_MBC_SNPCR_LOW	(2<<21)
-#define   GEN6_MBC_SNPCR_MIN	(3<<21) /* only 1/16th of the cache is shared */
+#define   GEN6_MBC_SNPCR_MASK	(3 << 21)
+#define   GEN6_MBC_SNPCR_MAX	(0 << 21)
+#define   GEN6_MBC_SNPCR_MED	(1 << 21)
+#define   GEN6_MBC_SNPCR_LOW	(2 << 21)
+#define   GEN6_MBC_SNPCR_MIN	(3 << 21) /* only 1/16th of the cache is shared */
 
 #define VLV_G3DCTL		_MMIO(0x9024)
 #define VLV_GSCKGCTL		_MMIO(0x9028)
@@ -315,13 +315,13 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN11_GRDOM_VECS		(1 << 13)
 #define  GEN11_GRDOM_VECS2		(1 << 14)
 
-#define RING_PP_DIR_BASE(engine)	_MMIO((engine)->mmio_base+0x228)
-#define RING_PP_DIR_BASE_READ(engine)	_MMIO((engine)->mmio_base+0x518)
-#define RING_PP_DIR_DCLV(engine)	_MMIO((engine)->mmio_base+0x220)
+#define RING_PP_DIR_BASE(engine)	_MMIO((engine)->mmio_base + 0x228)
+#define RING_PP_DIR_BASE_READ(engine)	_MMIO((engine)->mmio_base + 0x518)
+#define RING_PP_DIR_DCLV(engine)	_MMIO((engine)->mmio_base + 0x220)
 #define   PP_DIR_DCLV_2G		0xffffffff
 
-#define GEN8_RING_PDP_UDW(engine, n)	_MMIO((engine)->mmio_base+0x270 + (n) * 8 + 4)
-#define GEN8_RING_PDP_LDW(engine, n)	_MMIO((engine)->mmio_base+0x270 + (n) * 8)
+#define GEN8_RING_PDP_UDW(engine, n)	_MMIO((engine)->mmio_base + 0x270 + (n) * 8 + 4)
+#define GEN8_RING_PDP_LDW(engine, n)	_MMIO((engine)->mmio_base + 0x270 + (n) * 8)
 
 #define GEN8_R_PWR_CLK_STATE		_MMIO(0x20C8)
 #define   GEN8_RPCS_ENABLE		(1 << 31)
@@ -359,25 +359,25 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   GEN8_SELECTIVE_READ_ADDRESSING_ENABLE         (1 << 13)
 
 #define GAM_ECOCHK			_MMIO(0x4090)
-#define   BDW_DISABLE_HDC_INVALIDATION	(1<<25)
-#define   ECOCHK_SNB_BIT		(1<<10)
-#define   ECOCHK_DIS_TLB		(1<<8)
-#define   HSW_ECOCHK_ARB_PRIO_SOL	(1<<6)
-#define   ECOCHK_PPGTT_CACHE64B		(0x3<<3)
-#define   ECOCHK_PPGTT_CACHE4B		(0x0<<3)
-#define   ECOCHK_PPGTT_GFDT_IVB		(0x1<<4)
-#define   ECOCHK_PPGTT_LLC_IVB		(0x1<<3)
-#define   ECOCHK_PPGTT_UC_HSW		(0x1<<3)
-#define   ECOCHK_PPGTT_WT_HSW		(0x2<<3)
-#define   ECOCHK_PPGTT_WB_HSW		(0x3<<3)
+#define   BDW_DISABLE_HDC_INVALIDATION	(1 << 25)
+#define   ECOCHK_SNB_BIT		(1 << 10)
+#define   ECOCHK_DIS_TLB		(1 << 8)
+#define   HSW_ECOCHK_ARB_PRIO_SOL	(1 << 6)
+#define   ECOCHK_PPGTT_CACHE64B		(0x3 << 3)
+#define   ECOCHK_PPGTT_CACHE4B		(0x0 << 3)
+#define   ECOCHK_PPGTT_GFDT_IVB		(0x1 << 4)
+#define   ECOCHK_PPGTT_LLC_IVB		(0x1 << 3)
+#define   ECOCHK_PPGTT_UC_HSW		(0x1 << 3)
+#define   ECOCHK_PPGTT_WT_HSW		(0x2 << 3)
+#define   ECOCHK_PPGTT_WB_HSW		(0x3 << 3)
 
 #define GAC_ECO_BITS			_MMIO(0x14090)
-#define   ECOBITS_SNB_BIT		(1<<13)
-#define   ECOBITS_PPGTT_CACHE64B	(3<<8)
-#define   ECOBITS_PPGTT_CACHE4B		(0<<8)
+#define   ECOBITS_SNB_BIT		(1 << 13)
+#define   ECOBITS_PPGTT_CACHE64B	(3 << 8)
+#define   ECOBITS_PPGTT_CACHE4B		(0 << 8)
 
 #define GAB_CTL				_MMIO(0x24000)
-#define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1<<8)
+#define   GAB_CTL_CONT_AFTER_PAGEFAULT	(1 << 8)
 
 #define GEN6_STOLEN_RESERVED		_MMIO(0x1082C0)
 #define GEN6_STOLEN_RESERVED_ADDR_MASK	(0xFFF << 20)
@@ -405,15 +405,15 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define _VGA_MSR_WRITE _MMIO(0x3c2)
 #define VGA_MSR_WRITE 0x3c2
 #define VGA_MSR_READ 0x3cc
-#define   VGA_MSR_MEM_EN (1<<1)
-#define   VGA_MSR_CGA_MODE (1<<0)
+#define   VGA_MSR_MEM_EN (1 << 1)
+#define   VGA_MSR_CGA_MODE (1 << 0)
 
 #define VGA_SR_INDEX 0x3c4
 #define SR01			1
 #define VGA_SR_DATA 0x3c5
 
 #define VGA_AR_INDEX 0x3c0
-#define   VGA_AR_VID_EN (1<<5)
+#define   VGA_AR_VID_EN (1 << 5)
 #define VGA_AR_DATA_WRITE 0x3c0
 #define VGA_AR_DATA_READ 0x3c1
 
@@ -446,8 +446,8 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define MI_PREDICATE_SRC1_UDW	_MMIO(0x2408 + 4)
 
 #define MI_PREDICATE_RESULT_2	_MMIO(0x2214)
-#define  LOWER_SLICE_ENABLED	(1<<0)
-#define  LOWER_SLICE_DISABLED	(0<<0)
+#define  LOWER_SLICE_ENABLED	(1 << 0)
+#define  LOWER_SLICE_DISABLED	(0 << 0)
 
 /*
  * Registers used only by the command parser
@@ -505,47 +505,47 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define  GEN7_OACONTROL_CTX_MASK	    0xFFFFF000
 #define  GEN7_OACONTROL_TIMER_PERIOD_MASK   0x3F
 #define  GEN7_OACONTROL_TIMER_PERIOD_SHIFT  6
-#define  GEN7_OACONTROL_TIMER_ENABLE	    (1<<5)
-#define  GEN7_OACONTROL_FORMAT_A13	    (0<<2)
-#define  GEN7_OACONTROL_FORMAT_A29	    (1<<2)
-#define  GEN7_OACONTROL_FORMAT_A13_B8_C8    (2<<2)
-#define  GEN7_OACONTROL_FORMAT_A29_B8_C8    (3<<2)
-#define  GEN7_OACONTROL_FORMAT_B4_C8	    (4<<2)
-#define  GEN7_OACONTROL_FORMAT_A45_B8_C8    (5<<2)
-#define  GEN7_OACONTROL_FORMAT_B4_C8_A16    (6<<2)
-#define  GEN7_OACONTROL_FORMAT_C4_B8	    (7<<2)
+#define  GEN7_OACONTROL_TIMER_ENABLE	    (1 << 5)
+#define  GEN7_OACONTROL_FORMAT_A13	    (0 << 2)
+#define  GEN7_OACONTROL_FORMAT_A29	    (1 << 2)
+#define  GEN7_OACONTROL_FORMAT_A13_B8_C8    (2 << 2)
+#define  GEN7_OACONTROL_FORMAT_A29_B8_C8    (3 << 2)
+#define  GEN7_OACONTROL_FORMAT_B4_C8	    (4 << 2)
+#define  GEN7_OACONTROL_FORMAT_A45_B8_C8    (5 << 2)
+#define  GEN7_OACONTROL_FORMAT_B4_C8_A16    (6 << 2)
+#define  GEN7_OACONTROL_FORMAT_C4_B8	    (7 << 2)
 #define  GEN7_OACONTROL_FORMAT_SHIFT	    2
-#define  GEN7_OACONTROL_PER_CTX_ENABLE	    (1<<1)
-#define  GEN7_OACONTROL_ENABLE		    (1<<0)
+#define  GEN7_OACONTROL_PER_CTX_ENABLE	    (1 << 1)
+#define  GEN7_OACONTROL_ENABLE		    (1 << 0)
 
 #define GEN8_OACTXID _MMIO(0x2364)
 
 #define GEN8_OA_DEBUG _MMIO(0x2B04)
-#define  GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS    (1<<5)
-#define  GEN9_OA_DEBUG_INCLUDE_CLK_RATIO	    (1<<6)
-#define  GEN9_OA_DEBUG_DISABLE_GO_1_0_REPORTS	    (1<<2)
-#define  GEN9_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS   (1<<1)
+#define  GEN9_OA_DEBUG_DISABLE_CLK_RATIO_REPORTS    (1 << 5)
+#define  GEN9_OA_DEBUG_INCLUDE_CLK_RATIO	    (1 << 6)
+#define  GEN9_OA_DEBUG_DISABLE_GO_1_0_REPORTS	    (1 << 2)
+#define  GEN9_OA_DEBUG_DISABLE_CTX_SWITCH_REPORTS   (1 << 1)
 
 #define GEN8_OACONTROL _MMIO(0x2B00)
-#define  GEN8_OA_REPORT_FORMAT_A12	    (0<<2)
-#define  GEN8_OA_REPORT_FORMAT_A12_B8_C8    (2<<2)
-#define  GEN8_OA_REPORT_FORMAT_A36_B8_C8    (5<<2)
-#define  GEN8_OA_REPORT_FORMAT_C4_B8	    (7<<2)
+#define  GEN8_OA_REPORT_FORMAT_A12	    (0 << 2)
+#define  GEN8_OA_REPORT_FORMAT_A12_B8_C8    (2 << 2)
+#define  GEN8_OA_REPORT_FORMAT_A36_B8_C8    (5 << 2)
+#define  GEN8_OA_REPORT_FORMAT_C4_B8	    (7 << 2)
 #define  GEN8_OA_REPORT_FORMAT_SHIFT	    2
-#define  GEN8_OA_SPECIFIC_CONTEXT_ENABLE    (1<<1)
-#define  GEN8_OA_COUNTER_ENABLE             (1<<0)
+#define  GEN8_OA_SPECIFIC_CONTEXT_ENABLE    (1 << 1)
+#define  GEN8_OA_COUNTER_ENABLE             (1 << 0)
 
 #define GEN8_OACTXCONTROL _MMIO(0x2360)
 #define  GEN8_OA_TIMER_PERIOD_MASK	    0x3F
 #define  GEN8_OA_TIMER_PERIOD_SHIFT	    2
-#define  GEN8_OA_TIMER_ENABLE		    (1<<1)
-#define  GEN8_OA_COUNTER_RESUME		    (1<<0)
+#define  GEN8_OA_TIMER_ENABLE		    (1 << 1)
+#define  GEN8_OA_COUNTER_RESUME		    (1 << 0)
 
 #define GEN7_OABUFFER _MMIO(0x23B0) /* R/W */
-#define  GEN7_OABUFFER_OVERRUN_DISABLE	    (1<<3)
-#define  GEN7_OABUFFER_EDGE_TRIGGER	    (1<<2)
-#define  GEN7_OABUFFER_STOP_RESUME_ENABLE   (1<<1)
-#define  GEN7_OABUFFER_RESUME		    (1<<0)
+#define  GEN7_OABUFFER_OVERRUN_DISABLE	    (1 << 3)
+#define  GEN7_OABUFFER_EDGE_TRIGGER	    (1 << 2)
+#define  GEN7_OABUFFER_STOP_RESUME_ENABLE   (1 << 1)
+#define  GEN7_OABUFFER_RESUME		    (1 << 0)
 
 #define GEN8_OABUFFER_UDW _MMIO(0x23b4)
 #define GEN8_OABUFFER _MMIO(0x2b14)
@@ -553,33 +553,33 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 
 #define GEN7_OASTATUS1 _MMIO(0x2364)
 #define  GEN7_OASTATUS1_TAIL_MASK	    0xffffffc0
-#define  GEN7_OASTATUS1_COUNTER_OVERFLOW    (1<<2)
-#define  GEN7_OASTATUS1_OABUFFER_OVERFLOW   (1<<1)
-#define  GEN7_OASTATUS1_REPORT_LOST	    (1<<0)
+#define  GEN7_OASTATUS1_COUNTER_OVERFLOW    (1 << 2)
+#define  GEN7_OASTATUS1_OABUFFER_OVERFLOW   (1 << 1)
+#define  GEN7_OASTATUS1_REPORT_LOST	    (1 << 0)
 
 #define GEN7_OASTATUS2 _MMIO(0x2368)
 #define  GEN7_OASTATUS2_HEAD_MASK           0xffffffc0
 #define  GEN7_OASTATUS2_MEM_SELECT_GGTT     (1 << 0) /* 0: PPGTT, 1: GGTT */
 
 #define GEN8_OASTATUS _MMIO(0x2b08)
-#define  GEN8_OASTATUS_OVERRUN_STATUS	    (1<<3)
-#define  GEN8_OASTATUS_COUNTER_OVERFLOW     (1<<2)
-#define  GEN8_OASTATUS_OABUFFER_OVERFLOW    (1<<1)
-#define  GEN8_OASTATUS_REPORT_LOST	    (1<<0)
+#define  GEN8_OASTATUS_OVERRUN_STATUS	    (1 << 3)
+#define  GEN8_OASTATUS_COUNTER_OVERFLOW     (1 << 2)
+#define  GEN8_OASTATUS_OABUFFER_OVERFLOW    (1 << 1)
+#define  GEN8_OASTATUS_REPORT_LOST	    (1 << 0)
 
 #define GEN8_OAHEADPTR _MMIO(0x2B0C)
 #define GEN8_OAHEADPTR_MASK    0xffffffc0
 #define GEN8_OATAILPTR _MMIO(0x2B10)
 #define GEN8_OATAILPTR_MASK    0xffffffc0
 
-#define OABUFFER_SIZE_128K  (0<<3)
-#define OABUFFER_SIZE_256K  (1<<3)
-#define OABUFFER_SIZE_512K  (2<<3)
-#define OABUFFER_SIZE_1M    (3<<3)
-#define OABUFFER_SIZE_2M    (4<<3)
-#define OABUFFER_SIZE_4M    (5<<3)
-#define OABUFFER_SIZE_8M    (6<<3)
-#define OABUFFER_SIZE_16M   (7<<3)
+#define OABUFFER_SIZE_128K  (0 << 3)
+#define OABUFFER_SIZE_256K  (1 << 3)
+#define OABUFFER_SIZE_512K  (2 << 3)
+#define OABUFFER_SIZE_1M    (3 << 3)
+#define OABUFFER_SIZE_2M    (4 << 3)
+#define OABUFFER_SIZE_4M    (5 << 3)
+#define OABUFFER_SIZE_8M    (6 << 3)
+#define OABUFFER_SIZE_16M   (7 << 3)
 
 /*
  * Flexible, Aggregate EU Counter Registers.
@@ -602,35 +602,35 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OASTARTTRIG1_THRESHOLD_MASK	      0xffff
 
 #define OASTARTTRIG2 _MMIO(0x2714)
-#define OASTARTTRIG2_INVERT_A_0 (1<<0)
-#define OASTARTTRIG2_INVERT_A_1 (1<<1)
-#define OASTARTTRIG2_INVERT_A_2 (1<<2)
-#define OASTARTTRIG2_INVERT_A_3 (1<<3)
-#define OASTARTTRIG2_INVERT_A_4 (1<<4)
-#define OASTARTTRIG2_INVERT_A_5 (1<<5)
-#define OASTARTTRIG2_INVERT_A_6 (1<<6)
-#define OASTARTTRIG2_INVERT_A_7 (1<<7)
-#define OASTARTTRIG2_INVERT_A_8 (1<<8)
-#define OASTARTTRIG2_INVERT_A_9 (1<<9)
-#define OASTARTTRIG2_INVERT_A_10 (1<<10)
-#define OASTARTTRIG2_INVERT_A_11 (1<<11)
-#define OASTARTTRIG2_INVERT_A_12 (1<<12)
-#define OASTARTTRIG2_INVERT_A_13 (1<<13)
-#define OASTARTTRIG2_INVERT_A_14 (1<<14)
-#define OASTARTTRIG2_INVERT_A_15 (1<<15)
-#define OASTARTTRIG2_INVERT_B_0 (1<<16)
-#define OASTARTTRIG2_INVERT_B_1 (1<<17)
-#define OASTARTTRIG2_INVERT_B_2 (1<<18)
-#define OASTARTTRIG2_INVERT_B_3 (1<<19)
-#define OASTARTTRIG2_INVERT_C_0 (1<<20)
-#define OASTARTTRIG2_INVERT_C_1 (1<<21)
-#define OASTARTTRIG2_INVERT_D_0 (1<<22)
-#define OASTARTTRIG2_THRESHOLD_ENABLE	    (1<<23)
-#define OASTARTTRIG2_START_TRIG_FLAG_MBZ    (1<<24)
-#define OASTARTTRIG2_EVENT_SELECT_0  (1<<28)
-#define OASTARTTRIG2_EVENT_SELECT_1  (1<<29)
-#define OASTARTTRIG2_EVENT_SELECT_2  (1<<30)
-#define OASTARTTRIG2_EVENT_SELECT_3  (1<<31)
+#define OASTARTTRIG2_INVERT_A_0 (1 << 0)
+#define OASTARTTRIG2_INVERT_A_1 (1 << 1)
+#define OASTARTTRIG2_INVERT_A_2 (1 << 2)
+#define OASTARTTRIG2_INVERT_A_3 (1 << 3)
+#define OASTARTTRIG2_INVERT_A_4 (1 << 4)
+#define OASTARTTRIG2_INVERT_A_5 (1 << 5)
+#define OASTARTTRIG2_INVERT_A_6 (1 << 6)
+#define OASTARTTRIG2_INVERT_A_7 (1 << 7)
+#define OASTARTTRIG2_INVERT_A_8 (1 << 8)
+#define OASTARTTRIG2_INVERT_A_9 (1 << 9)
+#define OASTARTTRIG2_INVERT_A_10 (1 << 10)
+#define OASTARTTRIG2_INVERT_A_11 (1 << 11)
+#define OASTARTTRIG2_INVERT_A_12 (1 << 12)
+#define OASTARTTRIG2_INVERT_A_13 (1 << 13)
+#define OASTARTTRIG2_INVERT_A_14 (1 << 14)
+#define OASTARTTRIG2_INVERT_A_15 (1 << 15)
+#define OASTARTTRIG2_INVERT_B_0 (1 << 16)
+#define OASTARTTRIG2_INVERT_B_1 (1 << 17)
+#define OASTARTTRIG2_INVERT_B_2 (1 << 18)
+#define OASTARTTRIG2_INVERT_B_3 (1 << 19)
+#define OASTARTTRIG2_INVERT_C_0 (1 << 20)
+#define OASTARTTRIG2_INVERT_C_1 (1 << 21)
+#define OASTARTTRIG2_INVERT_D_0 (1 << 22)
+#define OASTARTTRIG2_THRESHOLD_ENABLE	    (1 << 23)
+#define OASTARTTRIG2_START_TRIG_FLAG_MBZ    (1 << 24)
+#define OASTARTTRIG2_EVENT_SELECT_0  (1 << 28)
+#define OASTARTTRIG2_EVENT_SELECT_1  (1 << 29)
+#define OASTARTTRIG2_EVENT_SELECT_2  (1 << 30)
+#define OASTARTTRIG2_EVENT_SELECT_3  (1 << 31)
 
 #define OASTARTTRIG3 _MMIO(0x2718)
 #define OASTARTTRIG3_NOA_SELECT_MASK	   0xf
@@ -659,35 +659,35 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OASTARTTRIG5_THRESHOLD_MASK	      0xffff
 
 #define OASTARTTRIG6 _MMIO(0x2724)
-#define OASTARTTRIG6_INVERT_A_0 (1<<0)
-#define OASTARTTRIG6_INVERT_A_1 (1<<1)
-#define OASTARTTRIG6_INVERT_A_2 (1<<2)
-#define OASTARTTRIG6_INVERT_A_3 (1<<3)
-#define OASTARTTRIG6_INVERT_A_4 (1<<4)
-#define OASTARTTRIG6_INVERT_A_5 (1<<5)
-#define OASTARTTRIG6_INVERT_A_6 (1<<6)
-#define OASTARTTRIG6_INVERT_A_7 (1<<7)
-#define OASTARTTRIG6_INVERT_A_8 (1<<8)
-#define OASTARTTRIG6_INVERT_A_9 (1<<9)
-#define OASTARTTRIG6_INVERT_A_10 (1<<10)
-#define OASTARTTRIG6_INVERT_A_11 (1<<11)
-#define OASTARTTRIG6_INVERT_A_12 (1<<12)
-#define OASTARTTRIG6_INVERT_A_13 (1<<13)
-#define OASTARTTRIG6_INVERT_A_14 (1<<14)
-#define OASTARTTRIG6_INVERT_A_15 (1<<15)
-#define OASTARTTRIG6_INVERT_B_0 (1<<16)
-#define OASTARTTRIG6_INVERT_B_1 (1<<17)
-#define OASTARTTRIG6_INVERT_B_2 (1<<18)
-#define OASTARTTRIG6_INVERT_B_3 (1<<19)
-#define OASTARTTRIG6_INVERT_C_0 (1<<20)
-#define OASTARTTRIG6_INVERT_C_1 (1<<21)
-#define OASTARTTRIG6_INVERT_D_0 (1<<22)
-#define OASTARTTRIG6_THRESHOLD_ENABLE	    (1<<23)
-#define OASTARTTRIG6_START_TRIG_FLAG_MBZ    (1<<24)
-#define OASTARTTRIG6_EVENT_SELECT_4  (1<<28)
-#define OASTARTTRIG6_EVENT_SELECT_5  (1<<29)
-#define OASTARTTRIG6_EVENT_SELECT_6  (1<<30)
-#define OASTARTTRIG6_EVENT_SELECT_7  (1<<31)
+#define OASTARTTRIG6_INVERT_A_0 (1 << 0)
+#define OASTARTTRIG6_INVERT_A_1 (1 << 1)
+#define OASTARTTRIG6_INVERT_A_2 (1 << 2)
+#define OASTARTTRIG6_INVERT_A_3 (1 << 3)
+#define OASTARTTRIG6_INVERT_A_4 (1 << 4)
+#define OASTARTTRIG6_INVERT_A_5 (1 << 5)
+#define OASTARTTRIG6_INVERT_A_6 (1 << 6)
+#define OASTARTTRIG6_INVERT_A_7 (1 << 7)
+#define OASTARTTRIG6_INVERT_A_8 (1 << 8)
+#define OASTARTTRIG6_INVERT_A_9 (1 << 9)
+#define OASTARTTRIG6_INVERT_A_10 (1 << 10)
+#define OASTARTTRIG6_INVERT_A_11 (1 << 11)
+#define OASTARTTRIG6_INVERT_A_12 (1 << 12)
+#define OASTARTTRIG6_INVERT_A_13 (1 << 13)
+#define OASTARTTRIG6_INVERT_A_14 (1 << 14)
+#define OASTARTTRIG6_INVERT_A_15 (1 << 15)
+#define OASTARTTRIG6_INVERT_B_0 (1 << 16)
+#define OASTARTTRIG6_INVERT_B_1 (1 << 17)
+#define OASTARTTRIG6_INVERT_B_2 (1 << 18)
+#define OASTARTTRIG6_INVERT_B_3 (1 << 19)
+#define OASTARTTRIG6_INVERT_C_0 (1 << 20)
+#define OASTARTTRIG6_INVERT_C_1 (1 << 21)
+#define OASTARTTRIG6_INVERT_D_0 (1 << 22)
+#define OASTARTTRIG6_THRESHOLD_ENABLE	    (1 << 23)
+#define OASTARTTRIG6_START_TRIG_FLAG_MBZ    (1 << 24)
+#define OASTARTTRIG6_EVENT_SELECT_4  (1 << 28)
+#define OASTARTTRIG6_EVENT_SELECT_5  (1 << 29)
+#define OASTARTTRIG6_EVENT_SELECT_6  (1 << 30)
+#define OASTARTTRIG6_EVENT_SELECT_7  (1 << 31)
 
 #define OASTARTTRIG7 _MMIO(0x2728)
 #define OASTARTTRIG7_NOA_SELECT_MASK	   0xf
@@ -716,31 +716,31 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OAREPORTTRIG1_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
 
 #define OAREPORTTRIG2 _MMIO(0x2744)
-#define OAREPORTTRIG2_INVERT_A_0  (1<<0)
-#define OAREPORTTRIG2_INVERT_A_1  (1<<1)
-#define OAREPORTTRIG2_INVERT_A_2  (1<<2)
-#define OAREPORTTRIG2_INVERT_A_3  (1<<3)
-#define OAREPORTTRIG2_INVERT_A_4  (1<<4)
-#define OAREPORTTRIG2_INVERT_A_5  (1<<5)
-#define OAREPORTTRIG2_INVERT_A_6  (1<<6)
-#define OAREPORTTRIG2_INVERT_A_7  (1<<7)
-#define OAREPORTTRIG2_INVERT_A_8  (1<<8)
-#define OAREPORTTRIG2_INVERT_A_9  (1<<9)
-#define OAREPORTTRIG2_INVERT_A_10 (1<<10)
-#define OAREPORTTRIG2_INVERT_A_11 (1<<11)
-#define OAREPORTTRIG2_INVERT_A_12 (1<<12)
-#define OAREPORTTRIG2_INVERT_A_13 (1<<13)
-#define OAREPORTTRIG2_INVERT_A_14 (1<<14)
-#define OAREPORTTRIG2_INVERT_A_15 (1<<15)
-#define OAREPORTTRIG2_INVERT_B_0  (1<<16)
-#define OAREPORTTRIG2_INVERT_B_1  (1<<17)
-#define OAREPORTTRIG2_INVERT_B_2  (1<<18)
-#define OAREPORTTRIG2_INVERT_B_3  (1<<19)
-#define OAREPORTTRIG2_INVERT_C_0  (1<<20)
-#define OAREPORTTRIG2_INVERT_C_1  (1<<21)
-#define OAREPORTTRIG2_INVERT_D_0  (1<<22)
-#define OAREPORTTRIG2_THRESHOLD_ENABLE	    (1<<23)
-#define OAREPORTTRIG2_REPORT_TRIGGER_ENABLE (1<<31)
+#define OAREPORTTRIG2_INVERT_A_0  (1 << 0)
+#define OAREPORTTRIG2_INVERT_A_1  (1 << 1)
+#define OAREPORTTRIG2_INVERT_A_2  (1 << 2)
+#define OAREPORTTRIG2_INVERT_A_3  (1 << 3)
+#define OAREPORTTRIG2_INVERT_A_4  (1 << 4)
+#define OAREPORTTRIG2_INVERT_A_5  (1 << 5)
+#define OAREPORTTRIG2_INVERT_A_6  (1 << 6)
+#define OAREPORTTRIG2_INVERT_A_7  (1 << 7)
+#define OAREPORTTRIG2_INVERT_A_8  (1 << 8)
+#define OAREPORTTRIG2_INVERT_A_9  (1 << 9)
+#define OAREPORTTRIG2_INVERT_A_10 (1 << 10)
+#define OAREPORTTRIG2_INVERT_A_11 (1 << 11)
+#define OAREPORTTRIG2_INVERT_A_12 (1 << 12)
+#define OAREPORTTRIG2_INVERT_A_13 (1 << 13)
+#define OAREPORTTRIG2_INVERT_A_14 (1 << 14)
+#define OAREPORTTRIG2_INVERT_A_15 (1 << 15)
+#define OAREPORTTRIG2_INVERT_B_0  (1 << 16)
+#define OAREPORTTRIG2_INVERT_B_1  (1 << 17)
+#define OAREPORTTRIG2_INVERT_B_2  (1 << 18)
+#define OAREPORTTRIG2_INVERT_B_3  (1 << 19)
+#define OAREPORTTRIG2_INVERT_C_0  (1 << 20)
+#define OAREPORTTRIG2_INVERT_C_1  (1 << 21)
+#define OAREPORTTRIG2_INVERT_D_0  (1 << 22)
+#define OAREPORTTRIG2_THRESHOLD_ENABLE	    (1 << 23)
+#define OAREPORTTRIG2_REPORT_TRIGGER_ENABLE (1 << 31)
 
 #define OAREPORTTRIG3 _MMIO(0x2748)
 #define OAREPORTTRIG3_NOA_SELECT_MASK	    0xf
@@ -769,31 +769,31 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OAREPORTTRIG5_EDGE_LEVEL_TRIGER_SELECT_MASK 0xffff0000 /* 0=level */
 
 #define OAREPORTTRIG6 _MMIO(0x2754)
-#define OAREPORTTRIG6_INVERT_A_0  (1<<0)
-#define OAREPORTTRIG6_INVERT_A_1  (1<<1)
-#define OAREPORTTRIG6_INVERT_A_2  (1<<2)
-#define OAREPORTTRIG6_INVERT_A_3  (1<<3)
-#define OAREPORTTRIG6_INVERT_A_4  (1<<4)
-#define OAREPORTTRIG6_INVERT_A_5  (1<<5)
-#define OAREPORTTRIG6_INVERT_A_6  (1<<6)
-#define OAREPORTTRIG6_INVERT_A_7  (1<<7)
-#define OAREPORTTRIG6_INVERT_A_8  (1<<8)
-#define OAREPORTTRIG6_INVERT_A_9  (1<<9)
-#define OAREPORTTRIG6_INVERT_A_10 (1<<10)
-#define OAREPORTTRIG6_INVERT_A_11 (1<<11)
-#define OAREPORTTRIG6_INVERT_A_12 (1<<12)
-#define OAREPORTTRIG6_INVERT_A_13 (1<<13)
-#define OAREPORTTRIG6_INVERT_A_14 (1<<14)
-#define OAREPORTTRIG6_INVERT_A_15 (1<<15)
-#define OAREPORTTRIG6_INVERT_B_0  (1<<16)
-#define OAREPORTTRIG6_INVERT_B_1  (1<<17)
-#define OAREPORTTRIG6_INVERT_B_2  (1<<18)
-#define OAREPORTTRIG6_INVERT_B_3  (1<<19)
-#define OAREPORTTRIG6_INVERT_C_0  (1<<20)
-#define OAREPORTTRIG6_INVERT_C_1  (1<<21)
-#define OAREPORTTRIG6_INVERT_D_0  (1<<22)
-#define OAREPORTTRIG6_THRESHOLD_ENABLE	    (1<<23)
-#define OAREPORTTRIG6_REPORT_TRIGGER_ENABLE (1<<31)
+#define OAREPORTTRIG6_INVERT_A_0  (1 << 0)
+#define OAREPORTTRIG6_INVERT_A_1  (1 << 1)
+#define OAREPORTTRIG6_INVERT_A_2  (1 << 2)
+#define OAREPORTTRIG6_INVERT_A_3  (1 << 3)
+#define OAREPORTTRIG6_INVERT_A_4  (1 << 4)
+#define OAREPORTTRIG6_INVERT_A_5  (1 << 5)
+#define OAREPORTTRIG6_INVERT_A_6  (1 << 6)
+#define OAREPORTTRIG6_INVERT_A_7  (1 << 7)
+#define OAREPORTTRIG6_INVERT_A_8  (1 << 8)
+#define OAREPORTTRIG6_INVERT_A_9  (1 << 9)
+#define OAREPORTTRIG6_INVERT_A_10 (1 << 10)
+#define OAREPORTTRIG6_INVERT_A_11 (1 << 11)
+#define OAREPORTTRIG6_INVERT_A_12 (1 << 12)
+#define OAREPORTTRIG6_INVERT_A_13 (1 << 13)
+#define OAREPORTTRIG6_INVERT_A_14 (1 << 14)
+#define OAREPORTTRIG6_INVERT_A_15 (1 << 15)
+#define OAREPORTTRIG6_INVERT_B_0  (1 << 16)
+#define OAREPORTTRIG6_INVERT_B_1  (1 << 17)
+#define OAREPORTTRIG6_INVERT_B_2  (1 << 18)
+#define OAREPORTTRIG6_INVERT_B_3  (1 << 19)
+#define OAREPORTTRIG6_INVERT_C_0  (1 << 20)
+#define OAREPORTTRIG6_INVERT_C_1  (1 << 21)
+#define OAREPORTTRIG6_INVERT_D_0  (1 << 22)
+#define OAREPORTTRIG6_THRESHOLD_ENABLE	    (1 << 23)
+#define OAREPORTTRIG6_REPORT_TRIGGER_ENABLE (1 << 31)
 
 #define OAREPORTTRIG7 _MMIO(0x2758)
 #define OAREPORTTRIG7_NOA_SELECT_MASK	    0xf
@@ -829,9 +829,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define OACEC_COMPARE_VALUE_MASK    0xffff
 #define OACEC_COMPARE_VALUE_SHIFT   3
 
-#define OACEC_SELECT_NOA	(0<<19)
-#define OACEC_SELECT_PREV	(1<<19)
-#define OACEC_SELECT_BOOLEAN	(2<<19)
+#define OACEC_SELECT_NOA	(0 << 19)
+#define OACEC_SELECT_PREV	(1 << 19)
+#define OACEC_SELECT_BOOLEAN	(2 << 19)
 
 /* CECX_1 */
 #define OACEC_MASK_MASK		    0xffff
@@ -949,9 +949,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
  * Reset registers
  */
 #define DEBUG_RESET_I830		_MMIO(0x6070)
-#define  DEBUG_RESET_FULL		(1<<7)
-#define  DEBUG_RESET_RENDER		(1<<8)
-#define  DEBUG_RESET_DISPLAY		(1<<9)
+#define  DEBUG_RESET_FULL		(1 << 7)
+#define  DEBUG_RESET_RENDER		(1 << 8)
+#define  DEBUG_RESET_DISPLAY		(1 << 9)
 
 /*
  * IOSF sideband
@@ -962,7 +962,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define   IOSF_PORT_SHIFT			8
 #define   IOSF_BYTE_ENABLES_SHIFT		4
 #define   IOSF_BAR_SHIFT			1
-#define   IOSF_SB_BUSY				(1<<0)
+#define   IOSF_SB_BUSY				(1 << 0)
 #define   IOSF_PORT_BUNIT			0x03
 #define   IOSF_PORT_PUNIT			0x04
 #define   IOSF_PORT_NC				0x11
@@ -1099,8 +1099,8 @@ enum i915_power_well_id {
 #define PUNIT_REG_GPU_LFM			0xd3
 #define PUNIT_REG_GPU_FREQ_REQ			0xd4
 #define PUNIT_REG_GPU_FREQ_STS			0xd8
-#define   GPLLENABLE				(1<<4)
-#define   GENFREQSTATUS				(1<<0)
+#define   GPLLENABLE				(1 << 4)
+#define   GENFREQSTATUS				(1 << 0)
 #define PUNIT_REG_MEDIA_TURBO_FREQ_REQ		0xdc
 #define PUNIT_REG_CZ_TIMESTAMP			0xce
 
@@ -1195,10 +1195,10 @@ enum i915_power_well_id {
 #define DPIO_DEVFN			0
 
 #define DPIO_CTL			_MMIO(VLV_DISPLAY_BASE + 0x2110)
-#define  DPIO_MODSEL1			(1<<3) /* if ref clk b == 27 */
-#define  DPIO_MODSEL0			(1<<2) /* if ref clk a == 27 */
-#define  DPIO_SFR_BYPASS		(1<<1)
-#define  DPIO_CMNRST			(1<<0)
+#define  DPIO_MODSEL1			(1 << 3) /* if ref clk b == 27 */
+#define  DPIO_MODSEL0			(1 << 2) /* if ref clk a == 27 */
+#define  DPIO_SFR_BYPASS		(1 << 1)
+#define  DPIO_CMNRST			(1 << 0)
 
 #define DPIO_PHY(pipe)			((pipe) >> 1)
 #define DPIO_PHY_IOSF_PORT(phy)		(dev_priv->dpio_phy_iosf_port[phy])
@@ -1216,7 +1216,7 @@ enum i915_power_well_id {
 #define   DPIO_P1_SHIFT			(21) /* 3 bits */
 #define   DPIO_P2_SHIFT			(16) /* 5 bits */
 #define   DPIO_N_SHIFT			(12) /* 4 bits */
-#define   DPIO_ENABLE_CALIBRATION	(1<<11)
+#define   DPIO_ENABLE_CALIBRATION	(1 << 11)
 #define   DPIO_M1DIV_SHIFT		(8) /* 3 bits */
 #define   DPIO_M2DIV_MASK		0xff
 #define _VLV_PLL_DW3_CH1		0x802c
@@ -1265,10 +1265,10 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW0_CH0		0x8200
 #define _VLV_PCS_DW0_CH1		0x8400
-#define   DPIO_PCS_TX_LANE2_RESET	(1<<16)
-#define   DPIO_PCS_TX_LANE1_RESET	(1<<7)
-#define   DPIO_LEFT_TXFIFO_RST_MASTER2	(1<<4)
-#define   DPIO_RIGHT_TXFIFO_RST_MASTER2	(1<<3)
+#define   DPIO_PCS_TX_LANE2_RESET	(1 << 16)
+#define   DPIO_PCS_TX_LANE1_RESET	(1 << 7)
+#define   DPIO_LEFT_TXFIFO_RST_MASTER2	(1 << 4)
+#define   DPIO_RIGHT_TXFIFO_RST_MASTER2	(1 << 3)
 #define VLV_PCS_DW0(ch) _PORT(ch, _VLV_PCS_DW0_CH0, _VLV_PCS_DW0_CH1)
 
 #define _VLV_PCS01_DW0_CH0		0x200
@@ -1280,11 +1280,11 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW1_CH0		0x8204
 #define _VLV_PCS_DW1_CH1		0x8404
-#define   CHV_PCS_REQ_SOFTRESET_EN	(1<<23)
-#define   DPIO_PCS_CLK_CRI_RXEB_EIOS_EN	(1<<22)
-#define   DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1<<21)
+#define   CHV_PCS_REQ_SOFTRESET_EN	(1 << 23)
+#define   DPIO_PCS_CLK_CRI_RXEB_EIOS_EN	(1 << 22)
+#define   DPIO_PCS_CLK_CRI_RXDIGFILTSG_EN (1 << 21)
 #define   DPIO_PCS_CLK_DATAWIDTH_SHIFT	(6)
-#define   DPIO_PCS_CLK_SOFT_RESET	(1<<5)
+#define   DPIO_PCS_CLK_SOFT_RESET	(1 << 5)
 #define VLV_PCS_DW1(ch) _PORT(ch, _VLV_PCS_DW1_CH0, _VLV_PCS_DW1_CH1)
 
 #define _VLV_PCS01_DW1_CH0		0x204
@@ -1309,12 +1309,12 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW9_CH0		0x8224
 #define _VLV_PCS_DW9_CH1		0x8424
-#define   DPIO_PCS_TX2MARGIN_MASK	(0x7<<13)
-#define   DPIO_PCS_TX2MARGIN_000	(0<<13)
-#define   DPIO_PCS_TX2MARGIN_101	(1<<13)
-#define   DPIO_PCS_TX1MARGIN_MASK	(0x7<<10)
-#define   DPIO_PCS_TX1MARGIN_000	(0<<10)
-#define   DPIO_PCS_TX1MARGIN_101	(1<<10)
+#define   DPIO_PCS_TX2MARGIN_MASK	(0x7 << 13)
+#define   DPIO_PCS_TX2MARGIN_000	(0 << 13)
+#define   DPIO_PCS_TX2MARGIN_101	(1 << 13)
+#define   DPIO_PCS_TX1MARGIN_MASK	(0x7 << 10)
+#define   DPIO_PCS_TX1MARGIN_000	(0 << 10)
+#define   DPIO_PCS_TX1MARGIN_101	(1 << 10)
 #define	VLV_PCS_DW9(ch) _PORT(ch, _VLV_PCS_DW9_CH0, _VLV_PCS_DW9_CH1)
 
 #define _VLV_PCS01_DW9_CH0		0x224
@@ -1326,14 +1326,14 @@ enum i915_power_well_id {
 
 #define _CHV_PCS_DW10_CH0		0x8228
 #define _CHV_PCS_DW10_CH1		0x8428
-#define   DPIO_PCS_SWING_CALC_TX0_TX2	(1<<30)
-#define   DPIO_PCS_SWING_CALC_TX1_TX3	(1<<31)
-#define   DPIO_PCS_TX2DEEMP_MASK	(0xf<<24)
-#define   DPIO_PCS_TX2DEEMP_9P5		(0<<24)
-#define   DPIO_PCS_TX2DEEMP_6P0		(2<<24)
-#define   DPIO_PCS_TX1DEEMP_MASK	(0xf<<16)
-#define   DPIO_PCS_TX1DEEMP_9P5		(0<<16)
-#define   DPIO_PCS_TX1DEEMP_6P0		(2<<16)
+#define   DPIO_PCS_SWING_CALC_TX0_TX2	(1 << 30)
+#define   DPIO_PCS_SWING_CALC_TX1_TX3	(1 << 31)
+#define   DPIO_PCS_TX2DEEMP_MASK	(0xf << 24)
+#define   DPIO_PCS_TX2DEEMP_9P5		(0 << 24)
+#define   DPIO_PCS_TX2DEEMP_6P0		(2 << 24)
+#define   DPIO_PCS_TX1DEEMP_MASK	(0xf << 16)
+#define   DPIO_PCS_TX1DEEMP_9P5		(0 << 16)
+#define   DPIO_PCS_TX1DEEMP_6P0		(2 << 16)
 #define CHV_PCS_DW10(ch) _PORT(ch, _CHV_PCS_DW10_CH0, _CHV_PCS_DW10_CH1)
 
 #define _VLV_PCS01_DW10_CH0		0x0228
@@ -1345,10 +1345,10 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW11_CH0		0x822c
 #define _VLV_PCS_DW11_CH1		0x842c
-#define   DPIO_TX2_STAGGER_MASK(x)	((x)<<24)
-#define   DPIO_LANEDESKEW_STRAP_OVRD	(1<<3)
-#define   DPIO_LEFT_TXFIFO_RST_MASTER	(1<<1)
-#define   DPIO_RIGHT_TXFIFO_RST_MASTER	(1<<0)
+#define   DPIO_TX2_STAGGER_MASK(x)	((x) << 24)
+#define   DPIO_LANEDESKEW_STRAP_OVRD	(1 << 3)
+#define   DPIO_LEFT_TXFIFO_RST_MASTER	(1 << 1)
+#define   DPIO_RIGHT_TXFIFO_RST_MASTER	(1 << 0)
 #define VLV_PCS_DW11(ch) _PORT(ch, _VLV_PCS_DW11_CH0, _VLV_PCS_DW11_CH1)
 
 #define _VLV_PCS01_DW11_CH0		0x022c
@@ -1367,11 +1367,11 @@ enum i915_power_well_id {
 
 #define _VLV_PCS_DW12_CH0		0x8230
 #define _VLV_PCS_DW12_CH1		0x8430
-#define   DPIO_TX2_STAGGER_MULT(x)	((x)<<20)
-#define   DPIO_TX1_STAGGER_MULT(x)	((x)<<16)
-#define   DPIO_TX1_STAGGER_MASK(x)	((x)<<8)
-#define   DPIO_LANESTAGGER_STRAP_OVRD	(1<<6)
-#define   DPIO_LANESTAGGER_STRAP(x)	((x)<<0)
+#define   DPIO_TX2_STAGGER_MULT(x)	((x) << 20)
+#define   DPIO_TX1_STAGGER_MULT(x)	((x) << 16)
+#define   DPIO_TX1_STAGGER_MASK(x)	((x) << 8)
+#define   DPIO_LANESTAGGER_STRAP_OVRD	(1 << 6)
+#define   DPIO_LANESTAGGER_STRAP(x)	((x) << 0)
 #define VLV_PCS_DW12(ch) _PORT(ch, _VLV_PCS_DW12_CH0, _VLV_PCS_DW12_CH1)
 
 #define _VLV_PCS_DW14_CH0		0x8238
@@ -1392,7 +1392,7 @@ enum i915_power_well_id {
 #define _VLV_TX_DW3_CH0			0x828c
 #define _VLV_TX_DW3_CH1			0x848c
 /* The following bit for CHV phy */
-#define   DPIO_TX_UNIQ_TRANS_SCALE_EN	(1<<27)
+#define   DPIO_TX_UNIQ_TRANS_SCALE_EN	(1 << 27)
 #define   DPIO_SWING_MARGIN101_SHIFT	16
 #define   DPIO_SWING_MARGIN101_MASK	(0xff << DPIO_SWING_MARGIN101_SHIFT)
 #define VLV_TX_DW3(ch) _PORT(ch, _VLV_TX_DW3_CH0, _VLV_TX_DW3_CH1)
@@ -1411,7 +1411,7 @@ enum i915_power_well_id {
 
 #define _VLV_TX_DW5_CH0			0x8294
 #define _VLV_TX_DW5_CH1			0x8494
-#define   DPIO_TX_OCALINIT_EN		(1<<31)
+#define   DPIO_TX_OCALINIT_EN		(1 << 31)
 #define VLV_TX_DW5(ch) _PORT(ch, _VLV_TX_DW5_CH0, _VLV_TX_DW5_CH1)
 
 #define _VLV_TX_DW11_CH0		0x82ac
@@ -1641,10 +1641,10 @@ enum i915_power_well_id {
 #define  PORT_PLL_LOCK_THRESHOLD_SHIFT	1
 #define  PORT_PLL_LOCK_THRESHOLD_MASK	(0x7 << PORT_PLL_LOCK_THRESHOLD_SHIFT)
 /* PORT_PLL_10_A */
-#define  PORT_PLL_DCO_AMP_OVR_EN_H	(1<<27)
+#define  PORT_PLL_DCO_AMP_OVR_EN_H	(1 << 27)
 #define  PORT_PLL_DCO_AMP_DEFAULT	15
 #define  PORT_PLL_DCO_AMP_MASK		0x3c00
-#define  PORT_PLL_DCO_AMP(x)		((x)<<10)
+#define  PORT_PLL_DCO_AMP(x)		((x) << 10)
 #define _PORT_PLL_BASE(phy, ch)		_BXT_PHY_CH(phy, ch, \
 						    _PORT_PLL_0_B, \
 						    _PORT_PLL_0_C)
@@ -1746,7 +1746,7 @@ enum i915_power_well_id {
 					       _CNL_PORT_TX_D_GRP_OFFSET, \
 					       _CNL_PORT_TX_AE_GRP_OFFSET, \
 					       _CNL_PORT_TX_F_GRP_OFFSET) + \
-					       4*(dw))
+					       4 * (dw))
 #define _CNL_PORT_TX_DW_LN0(port, dw)	(_PICK((port), \
 					       _CNL_PORT_TX_AE_LN0_OFFSET, \
 					       _CNL_PORT_TX_B_LN0_OFFSET, \
@@ -1754,7 +1754,7 @@ enum i915_power_well_id {
 					       _CNL_PORT_TX_D_LN0_OFFSET, \
 					       _CNL_PORT_TX_AE_LN0_OFFSET, \
 					       _CNL_PORT_TX_F_LN0_OFFSET) + \
-					       4*(dw))
+					       4 * (dw))
 
 #define CNL_PORT_TX_DW2_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 2))
 #define CNL_PORT_TX_DW2_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 2))
@@ -2140,8 +2140,8 @@ enum i915_power_well_id {
 /* SKL balance leg register */
 #define DISPIO_CR_TX_BMU_CR0		_MMIO(0x6C00C)
 /* I_boost values */
-#define BALANCE_LEG_SHIFT(port)		(8+3*(port))
-#define BALANCE_LEG_MASK(port)		(7<<(8+3*(port)))
+#define BALANCE_LEG_SHIFT(port)		(8 + 3 * (port))
+#define BALANCE_LEG_MASK(port)		(7 << (8 + 3 * (port)))
 /* Balance leg disable bits */
 #define BALANCE_LEG_DISABLE_SHIFT	23
 #define BALANCE_LEG_DISABLE(port)	(1 << (23 + (port)))
@@ -2161,10 +2161,10 @@ enum i915_power_well_id {
 #define   I830_FENCE_TILING_Y_SHIFT	12
 #define   I830_FENCE_SIZE_BITS(size)	((ffs((size) >> 19) - 1) << 8)
 #define   I830_FENCE_PITCH_SHIFT	4
-#define   I830_FENCE_REG_VALID		(1<<0)
+#define   I830_FENCE_REG_VALID		(1 << 0)
 #define   I915_FENCE_MAX_PITCH_VAL	4
 #define   I830_FENCE_MAX_PITCH_VAL	6
-#define   I830_FENCE_MAX_SIZE_VAL	(1<<8)
+#define   I830_FENCE_MAX_SIZE_VAL	(1 << 8)
 
 #define   I915_FENCE_START_MASK		0x0ff00000
 #define   I915_FENCE_SIZE_BITS(size)	((ffs((size) >> 20) - 1) << 8)
@@ -2173,7 +2173,7 @@ enum i915_power_well_id {
 #define FENCE_REG_965_HI(i)		_MMIO(0x03000 + (i) * 8 + 4)
 #define   I965_FENCE_PITCH_SHIFT	2
 #define   I965_FENCE_TILING_Y_SHIFT	1
-#define   I965_FENCE_REG_VALID		(1<<0)
+#define   I965_FENCE_REG_VALID		(1 << 0)
 #define   I965_FENCE_MAX_PITCH_VAL	0x0400
 
 #define FENCE_REG_GEN6_LO(i)		_MMIO(0x100000 + (i) * 8)
@@ -2196,13 +2196,13 @@ enum i915_power_well_id {
 #define   PGTBL_ADDRESS_LO_MASK	0xfffff000 /* bits [31:12] */
 #define   PGTBL_ADDRESS_HI_MASK	0x000000f0 /* bits [35:32] (gen4) */
 #define PGTBL_ER	_MMIO(0x02024)
-#define PRB0_BASE	(0x2030-0x30)
-#define PRB1_BASE	(0x2040-0x30) /* 830,gen3 */
-#define PRB2_BASE	(0x2050-0x30) /* gen3 */
-#define SRB0_BASE	(0x2100-0x30) /* gen2 */
-#define SRB1_BASE	(0x2110-0x30) /* gen2 */
-#define SRB2_BASE	(0x2120-0x30) /* 830 */
-#define SRB3_BASE	(0x2130-0x30) /* 830 */
+#define PRB0_BASE	(0x2030 - 0x30)
+#define PRB1_BASE	(0x2040 - 0x30) /* 830,gen3 */
+#define PRB2_BASE	(0x2050 - 0x30) /* gen3 */
+#define SRB0_BASE	(0x2100 - 0x30) /* gen2 */
+#define SRB1_BASE	(0x2110 - 0x30) /* gen2 */
+#define SRB2_BASE	(0x2120 - 0x30) /* 830 */
+#define SRB3_BASE	(0x2130 - 0x30) /* 830 */
 #define RENDER_RING_BASE	0x02000
 #define BSD_RING_BASE		0x04000
 #define GEN6_BSD_RING_BASE	0x12000
@@ -2215,14 +2215,14 @@ enum i915_power_well_id {
 #define GEN11_VEBOX_RING_BASE		0x1c8000
 #define GEN11_VEBOX2_RING_BASE		0x1d8000
 #define BLT_RING_BASE		0x22000
-#define RING_TAIL(base)		_MMIO((base)+0x30)
-#define RING_HEAD(base)		_MMIO((base)+0x34)
-#define RING_START(base)	_MMIO((base)+0x38)
-#define RING_CTL(base)		_MMIO((base)+0x3c)
+#define RING_TAIL(base)		_MMIO((base) + 0x30)
+#define RING_HEAD(base)		_MMIO((base) + 0x34)
+#define RING_START(base)	_MMIO((base) + 0x38)
+#define RING_CTL(base)		_MMIO((base) + 0x3c)
 #define   RING_CTL_SIZE(size)	((size) - PAGE_SIZE) /* in bytes -> pages */
-#define RING_SYNC_0(base)	_MMIO((base)+0x40)
-#define RING_SYNC_1(base)	_MMIO((base)+0x44)
-#define RING_SYNC_2(base)	_MMIO((base)+0x48)
+#define RING_SYNC_0(base)	_MMIO((base) + 0x40)
+#define RING_SYNC_1(base)	_MMIO((base) + 0x44)
+#define RING_SYNC_2(base)	_MMIO((base) + 0x48)
 #define GEN6_RVSYNC	(RING_SYNC_0(RENDER_RING_BASE))
 #define GEN6_RBSYNC	(RING_SYNC_1(RENDER_RING_BASE))
 #define GEN6_RVESYNC	(RING_SYNC_2(RENDER_RING_BASE))
@@ -2236,11 +2236,11 @@ enum i915_power_well_id {
 #define GEN6_VERSYNC	(RING_SYNC_1(VEBOX_RING_BASE))
 #define GEN6_VEVSYNC	(RING_SYNC_2(VEBOX_RING_BASE))
 #define GEN6_NOSYNC	INVALID_MMIO_REG
-#define RING_PSMI_CTL(base)	_MMIO((base)+0x50)
-#define RING_MAX_IDLE(base)	_MMIO((base)+0x54)
-#define RING_HWS_PGA(base)	_MMIO((base)+0x80)
-#define RING_HWS_PGA_GEN6(base)	_MMIO((base)+0x2080)
-#define RING_RESET_CTL(base)	_MMIO((base)+0xd0)
+#define RING_PSMI_CTL(base)	_MMIO((base) + 0x50)
+#define RING_MAX_IDLE(base)	_MMIO((base) + 0x54)
+#define RING_HWS_PGA(base)	_MMIO((base) + 0x80)
+#define RING_HWS_PGA_GEN6(base)	_MMIO((base) + 0x2080)
+#define RING_RESET_CTL(base)	_MMIO((base) + 0xd0)
 #define   RESET_CTL_REQUEST_RESET  (1 << 0)
 #define   RESET_CTL_READY_TO_RESET (1 << 1)
 #define RING_SEMA_WAIT_POLL(base) _MMIO((base) + 0x24c)
@@ -2250,8 +2250,8 @@ enum i915_power_well_id {
 #define GEN7_WR_WATERMARK	_MMIO(0x4028)
 #define GEN7_GFX_PRIO_CTRL	_MMIO(0x402C)
 #define ARB_MODE		_MMIO(0x4030)
-#define   ARB_MODE_SWIZZLE_SNB	(1<<4)
-#define   ARB_MODE_SWIZZLE_IVB	(1<<5)
+#define   ARB_MODE_SWIZZLE_SNB	(1 << 4)
+#define   ARB_MODE_SWIZZLE_IVB	(1 << 5)
 #define GEN7_GFX_PEND_TLB0	_MMIO(0x4034)
 #define GEN7_GFX_PEND_TLB1	_MMIO(0x4038)
 /* L3, CVS, ZTLB, RCC, CASC LRA min, max values */
@@ -2261,30 +2261,30 @@ enum i915_power_well_id {
 #define GEN7_GFX_MAX_REQ_COUNT		_MMIO(0x4074)
 
 #define GAMTARBMODE		_MMIO(0x04a08)
-#define   ARB_MODE_BWGTLB_DISABLE (1<<9)
-#define   ARB_MODE_SWIZZLE_BDW	(1<<1)
+#define   ARB_MODE_BWGTLB_DISABLE (1 << 9)
+#define   ARB_MODE_SWIZZLE_BDW	(1 << 1)
 #define RENDER_HWS_PGA_GEN7	_MMIO(0x04080)
-#define RING_FAULT_REG(engine)	_MMIO(0x4094 + 0x100*(engine)->hw_id)
+#define RING_FAULT_REG(engine)	_MMIO(0x4094 + 0x100 * (engine)->hw_id)
 #define GEN8_RING_FAULT_REG	_MMIO(0x4094)
 #define   GEN8_RING_FAULT_ENGINE_ID(x)	(((x) >> 12) & 0x7)
-#define   RING_FAULT_GTTSEL_MASK (1<<11)
+#define   RING_FAULT_GTTSEL_MASK (1 << 11)
 #define   RING_FAULT_SRCID(x)	(((x) >> 3) & 0xff)
 #define   RING_FAULT_FAULT_TYPE(x) (((x) >> 1) & 0x3)
-#define   RING_FAULT_VALID	(1<<0)
+#define   RING_FAULT_VALID	(1 << 0)
 #define DONE_REG		_MMIO(0x40b0)
 #define GEN8_PRIVATE_PAT_LO	_MMIO(0x40e0)
 #define GEN8_PRIVATE_PAT_HI	_MMIO(0x40e0 + 4)
-#define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index)*4)
+#define GEN10_PAT_INDEX(index)	_MMIO(0x40e0 + (index) * 4)
 #define BSD_HWS_PGA_GEN7	_MMIO(0x04180)
 #define BLT_HWS_PGA_GEN7	_MMIO(0x04280)
 #define VEBOX_HWS_PGA_GEN7	_MMIO(0x04380)
-#define RING_ACTHD(base)	_MMIO((base)+0x74)
-#define RING_ACTHD_UDW(base)	_MMIO((base)+0x5c)
-#define RING_NOPID(base)	_MMIO((base)+0x94)
-#define RING_IMR(base)		_MMIO((base)+0xa8)
-#define RING_HWSTAM(base)	_MMIO((base)+0x98)
-#define RING_TIMESTAMP(base)		_MMIO((base)+0x358)
-#define RING_TIMESTAMP_UDW(base)	_MMIO((base)+0x358 + 4)
+#define RING_ACTHD(base)	_MMIO((base) + 0x74)
+#define RING_ACTHD_UDW(base)	_MMIO((base) + 0x5c)
+#define RING_NOPID(base)	_MMIO((base) + 0x94)
+#define RING_IMR(base)		_MMIO((base) + 0xa8)
+#define RING_HWSTAM(base)	_MMIO((base) + 0x98)
+#define RING_TIMESTAMP(base)		_MMIO((base) + 0x358)
+#define RING_TIMESTAMP_UDW(base)	_MMIO((base) + 0x358 + 4)
 #define   TAIL_ADDR		0x001FFFF8
 #define   HEAD_WRAP_COUNT	0xFFE00000
 #define   HEAD_WRAP_ONE		0x00200000
@@ -2297,17 +2297,17 @@ enum i915_power_well_id {
 #define   RING_VALID_MASK	0x00000001
 #define   RING_VALID		0x00000001
 #define   RING_INVALID		0x00000000
-#define   RING_WAIT_I8XX	(1<<0) /* gen2, PRBx_HEAD */
-#define   RING_WAIT		(1<<11) /* gen3+, PRBx_CTL */
-#define   RING_WAIT_SEMAPHORE	(1<<10) /* gen6+ */
+#define   RING_WAIT_I8XX	(1 << 0) /* gen2, PRBx_HEAD */
+#define   RING_WAIT		(1 << 11) /* gen3+, PRBx_CTL */
+#define   RING_WAIT_SEMAPHORE	(1 << 10) /* gen6+ */
 
-#define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base)+0x4D0) + (i)*4)
+#define RING_FORCE_TO_NONPRIV(base, i) _MMIO(((base) + 0x4D0) + (i) * 4)
 #define   RING_MAX_NONPRIV_SLOTS  12
 
 #define GEN7_TLB_RD_ADDR	_MMIO(0x4700)
 
 #define GEN9_GAMT_ECO_REG_RW_IA _MMIO(0x4ab0)
-#define   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS	(1<<18)
+#define   GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS	(1 << 18)
 
 #define GEN8_GAMW_ECO_DEV_RW_IA _MMIO(0x4080)
 #define   GAMW_ECO_ENABLE_64K_IPS_FIELD 0xF
@@ -2341,19 +2341,19 @@ enum i915_power_well_id {
 #define   GEN11_MCR_SLICE_MASK		GEN11_MCR_SLICE(0xf)
 #define   GEN11_MCR_SUBSLICE(subslice)	(((subslice) & 0x7) << 24)
 #define   GEN11_MCR_SUBSLICE_MASK	GEN11_MCR_SUBSLICE(0x7)
-#define RING_IPEIR(base)	_MMIO((base)+0x64)
-#define RING_IPEHR(base)	_MMIO((base)+0x68)
+#define RING_IPEIR(base)	_MMIO((base) + 0x64)
+#define RING_IPEHR(base)	_MMIO((base) + 0x68)
 /*
  * On GEN4, only the render ring INSTDONE exists and has a different
  * layout than the GEN7+ version.
  * The GEN2 counterpart of this register is GEN2_INSTDONE.
  */
-#define RING_INSTDONE(base)	_MMIO((base)+0x6c)
-#define RING_INSTPS(base)	_MMIO((base)+0x70)
-#define RING_DMA_FADD(base)	_MMIO((base)+0x78)
-#define RING_DMA_FADD_UDW(base)	_MMIO((base)+0x60) /* gen8+ */
-#define RING_INSTPM(base)	_MMIO((base)+0xc0)
-#define RING_MI_MODE(base)	_MMIO((base)+0x9c)
+#define RING_INSTDONE(base)	_MMIO((base) + 0x6c)
+#define RING_INSTPS(base)	_MMIO((base) + 0x70)
+#define RING_DMA_FADD(base)	_MMIO((base) + 0x78)
+#define RING_DMA_FADD_UDW(base)	_MMIO((base) + 0x60) /* gen8+ */
+#define RING_INSTPM(base)	_MMIO((base) + 0xc0)
+#define RING_MI_MODE(base)	_MMIO((base) + 0x9c)
 #define INSTPS		_MMIO(0x2070) /* 965+ only */
 #define GEN4_INSTDONE1	_MMIO(0x207c) /* 965+ only, aka INSTDONE_2 on SNB */
 #define ACTHD_I965	_MMIO(0x2074)
@@ -2361,37 +2361,37 @@ enum i915_power_well_id {
 #define HWS_ADDRESS_MASK	0xfffff000
 #define HWS_START_ADDRESS_SHIFT	4
 #define PWRCTXA		_MMIO(0x2088) /* 965GM+ only */
-#define   PWRCTX_EN	(1<<0)
+#define   PWRCTX_EN	(1 << 0)
 #define IPEIR		_MMIO(0x2088)
 #define IPEHR		_MMIO(0x208c)
 #define GEN2_INSTDONE	_MMIO(0x2090)
 #define NOPID		_MMIO(0x2094)
 #define HWSTAM		_MMIO(0x2098)
 #define DMA_FADD_I8XX	_MMIO(0x20d0)
-#define RING_BBSTATE(base)	_MMIO((base)+0x110)
+#define RING_BBSTATE(base)	_MMIO((base) + 0x110)
 #define   RING_BB_PPGTT		(1 << 5)
-#define RING_SBBADDR(base)	_MMIO((base)+0x114) /* hsw+ */
-#define RING_SBBSTATE(base)	_MMIO((base)+0x118) /* hsw+ */
-#define RING_SBBADDR_UDW(base)	_MMIO((base)+0x11c) /* gen8+ */
-#define RING_BBADDR(base)	_MMIO((base)+0x140)
-#define RING_BBADDR_UDW(base)	_MMIO((base)+0x168) /* gen8+ */
-#define RING_BB_PER_CTX_PTR(base)	_MMIO((base)+0x1c0) /* gen8+ */
-#define RING_INDIRECT_CTX(base)		_MMIO((base)+0x1c4) /* gen8+ */
-#define RING_INDIRECT_CTX_OFFSET(base)	_MMIO((base)+0x1c8) /* gen8+ */
-#define RING_CTX_TIMESTAMP(base)	_MMIO((base)+0x3a8) /* gen8+ */
+#define RING_SBBADDR(base)	_MMIO((base) + 0x114) /* hsw+ */
+#define RING_SBBSTATE(base)	_MMIO((base) + 0x118) /* hsw+ */
+#define RING_SBBADDR_UDW(base)	_MMIO((base) + 0x11c) /* gen8+ */
+#define RING_BBADDR(base)	_MMIO((base) + 0x140)
+#define RING_BBADDR_UDW(base)	_MMIO((base) + 0x168) /* gen8+ */
+#define RING_BB_PER_CTX_PTR(base)	_MMIO((base) + 0x1c0) /* gen8+ */
+#define RING_INDIRECT_CTX(base)		_MMIO((base) + 0x1c4) /* gen8+ */
+#define RING_INDIRECT_CTX_OFFSET(base)	_MMIO((base) + 0x1c8) /* gen8+ */
+#define RING_CTX_TIMESTAMP(base)	_MMIO((base) + 0x3a8) /* gen8+ */
 
 #define ERROR_GEN6	_MMIO(0x40a0)
 #define GEN7_ERR_INT	_MMIO(0x44040)
-#define   ERR_INT_POISON		(1<<31)
-#define   ERR_INT_MMIO_UNCLAIMED	(1<<13)
-#define   ERR_INT_PIPE_CRC_DONE_C	(1<<8)
-#define   ERR_INT_FIFO_UNDERRUN_C	(1<<6)
-#define   ERR_INT_PIPE_CRC_DONE_B	(1<<5)
-#define   ERR_INT_FIFO_UNDERRUN_B	(1<<3)
-#define   ERR_INT_PIPE_CRC_DONE_A	(1<<2)
-#define   ERR_INT_PIPE_CRC_DONE(pipe)	(1<<(2 + (pipe)*3))
-#define   ERR_INT_FIFO_UNDERRUN_A	(1<<0)
-#define   ERR_INT_FIFO_UNDERRUN(pipe)	(1<<((pipe)*3))
+#define   ERR_INT_POISON		(1 << 31)
+#define   ERR_INT_MMIO_UNCLAIMED	(1 << 13)
+#define   ERR_INT_PIPE_CRC_DONE_C	(1 << 8)
+#define   ERR_INT_FIFO_UNDERRUN_C	(1 << 6)
+#define   ERR_INT_PIPE_CRC_DONE_B	(1 << 5)
+#define   ERR_INT_FIFO_UNDERRUN_B	(1 << 3)
+#define   ERR_INT_PIPE_CRC_DONE_A	(1 << 2)
+#define   ERR_INT_PIPE_CRC_DONE(pipe)	(1 << (2 + (pipe) * 3))
+#define   ERR_INT_FIFO_UNDERRUN_A	(1 << 0)
+#define   ERR_INT_FIFO_UNDERRUN(pipe)	(1 << ((pipe) * 3))
 
 #define GEN8_FAULT_TLB_DATA0		_MMIO(0x4b10)
 #define GEN8_FAULT_TLB_DATA1		_MMIO(0x4b14)
@@ -2399,7 +2399,7 @@ enum i915_power_well_id {
 #define   FAULT_GTT_SEL			(1 << 4)
 
 #define FPGA_DBG		_MMIO(0x42300)
-#define   FPGA_DBG_RM_NOCLAIM	(1<<31)
+#define   FPGA_DBG_RM_NOCLAIM	(1 << 31)
 
 #define CLAIM_ER		_MMIO(VLV_DISPLAY_BASE + 0x2028)
 #define   CLAIM_ER_CLR		(1 << 31)
@@ -2408,22 +2408,22 @@ enum i915_power_well_id {
 
 #define DERRMR		_MMIO(0x44050)
 /* Note that HBLANK events are reserved on bdw+ */
-#define   DERRMR_PIPEA_SCANLINE		(1<<0)
-#define   DERRMR_PIPEA_PRI_FLIP_DONE	(1<<1)
-#define   DERRMR_PIPEA_SPR_FLIP_DONE	(1<<2)
-#define   DERRMR_PIPEA_VBLANK		(1<<3)
-#define   DERRMR_PIPEA_HBLANK		(1<<5)
-#define   DERRMR_PIPEB_SCANLINE 	(1<<8)
-#define   DERRMR_PIPEB_PRI_FLIP_DONE	(1<<9)
-#define   DERRMR_PIPEB_SPR_FLIP_DONE	(1<<10)
-#define   DERRMR_PIPEB_VBLANK		(1<<11)
-#define   DERRMR_PIPEB_HBLANK		(1<<13)
+#define   DERRMR_PIPEA_SCANLINE		(1 << 0)
+#define   DERRMR_PIPEA_PRI_FLIP_DONE	(1 << 1)
+#define   DERRMR_PIPEA_SPR_FLIP_DONE	(1 << 2)
+#define   DERRMR_PIPEA_VBLANK		(1 << 3)
+#define   DERRMR_PIPEA_HBLANK		(1 << 5)
+#define   DERRMR_PIPEB_SCANLINE 	(1 << 8)
+#define   DERRMR_PIPEB_PRI_FLIP_DONE	(1 << 9)
+#define   DERRMR_PIPEB_SPR_FLIP_DONE	(1 << 10)
+#define   DERRMR_PIPEB_VBLANK		(1 << 11)
+#define   DERRMR_PIPEB_HBLANK		(1 << 13)
 /* Note that PIPEC is not a simple translation of PIPEA/PIPEB */
-#define   DERRMR_PIPEC_SCANLINE		(1<<14)
-#define   DERRMR_PIPEC_PRI_FLIP_DONE	(1<<15)
-#define   DERRMR_PIPEC_SPR_FLIP_DONE	(1<<20)
-#define   DERRMR_PIPEC_VBLANK		(1<<21)
-#define   DERRMR_PIPEC_HBLANK		(1<<22)
+#define   DERRMR_PIPEC_SCANLINE		(1 << 14)
+#define   DERRMR_PIPEC_PRI_FLIP_DONE	(1 << 15)
+#define   DERRMR_PIPEC_SPR_FLIP_DONE	(1 << 20)
+#define   DERRMR_PIPEC_VBLANK		(1 << 21)
+#define   DERRMR_PIPEC_HBLANK		(1 << 22)
 
 
 /* GM45+ chicken bits -- debug workaround bits that may be required
@@ -2447,7 +2447,7 @@ enum i915_power_well_id {
 #define  _3D_CHICKEN_SF_DISABLE_OBJEND_CULL		(1 << 10)
 #define  _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE	(1 << 5)
 #define  _3D_CHICKEN3_SF_DISABLE_FASTCLIP_CULL		(1 << 5)
-#define  _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x)<<1) /* gen8+ */
+#define  _3D_CHICKEN_SDE_LIMIT_FIFO_POLY_DEPTH(x)	((x) << 1) /* gen8+ */
 #define  _3D_CHICKEN3_SF_DISABLE_PIPELINED_ATTR_FETCH	(1 << 1) /* gen6 */
 
 #define MI_MODE		_MMIO(0x209c)
@@ -2486,22 +2486,22 @@ enum i915_power_well_id {
 
 #define GFX_MODE	_MMIO(0x2520)
 #define GFX_MODE_GEN7	_MMIO(0x229c)
-#define RING_MODE_GEN7(engine)	_MMIO((engine)->mmio_base+0x29c)
-#define   GFX_RUN_LIST_ENABLE		(1<<15)
-#define   GFX_INTERRUPT_STEERING	(1<<14)
-#define   GFX_TLB_INVALIDATE_EXPLICIT	(1<<13)
-#define   GFX_SURFACE_FAULT_ENABLE	(1<<12)
-#define   GFX_REPLAY_MODE		(1<<11)
-#define   GFX_PSMI_GRANULARITY		(1<<10)
-#define   GFX_PPGTT_ENABLE		(1<<9)
-#define   GEN8_GFX_PPGTT_48B		(1<<7)
-
-#define   GFX_FORWARD_VBLANK_MASK	(3<<5)
-#define   GFX_FORWARD_VBLANK_NEVER	(0<<5)
-#define   GFX_FORWARD_VBLANK_ALWAYS	(1<<5)
-#define   GFX_FORWARD_VBLANK_COND	(2<<5)
-
-#define   GEN11_GFX_DISABLE_LEGACY_MODE	(1<<3)
+#define RING_MODE_GEN7(engine)	_MMIO((engine)->mmio_base + 0x29c)
+#define   GFX_RUN_LIST_ENABLE		(1 << 15)
+#define   GFX_INTERRUPT_STEERING	(1 << 14)
+#define   GFX_TLB_INVALIDATE_EXPLICIT	(1 << 13)
+#define   GFX_SURFACE_FAULT_ENABLE	(1 << 12)
+#define   GFX_REPLAY_MODE		(1 << 11)
+#define   GFX_PSMI_GRANULARITY		(1 << 10)
+#define   GFX_PPGTT_ENABLE		(1 << 9)
+#define   GEN8_GFX_PPGTT_48B		(1 << 7)
+
+#define   GFX_FORWARD_VBLANK_MASK	(3 << 5)
+#define   GFX_FORWARD_VBLANK_NEVER	(0 << 5)
+#define   GFX_FORWARD_VBLANK_ALWAYS	(1 << 5)
+#define   GFX_FORWARD_VBLANK_COND	(2 << 5)
+
+#define   GEN11_GFX_DISABLE_LEGACY_MODE	(1 << 3)
 
 #define VLV_DISPLAY_BASE 0x180000
 #define VLV_MIPI_BASE VLV_DISPLAY_BASE
@@ -2515,8 +2515,8 @@ enum i915_power_well_id {
 #define IMR		_MMIO(0x20a8)
 #define ISR		_MMIO(0x20ac)
 #define VLV_GUNIT_CLOCK_GATE	_MMIO(VLV_DISPLAY_BASE + 0x2060)
-#define   GINT_DIS		(1<<22)
-#define   GCFG_DIS		(1<<8)
+#define   GINT_DIS		(1 << 22)
+#define   GCFG_DIS		(1 << 8)
 #define VLV_GUNIT_CLOCK_GATE2	_MMIO(VLV_DISPLAY_BASE + 0x2064)
 #define VLV_IIR_RW	_MMIO(VLV_DISPLAY_BASE + 0x2084)
 #define VLV_IER		_MMIO(VLV_DISPLAY_BASE + 0x20a0)
@@ -2526,35 +2526,35 @@ enum i915_power_well_id {
 #define VLV_PCBR	_MMIO(VLV_DISPLAY_BASE + 0x2120)
 #define VLV_PCBR_ADDR_SHIFT	12
 
-#define   DISPLAY_PLANE_FLIP_PENDING(plane) (1<<(11-(plane))) /* A and B only */
+#define   DISPLAY_PLANE_FLIP_PENDING(plane) (1 << (11 - (plane))) /* A and B only */
 #define EIR		_MMIO(0x20b0)
 #define EMR		_MMIO(0x20b4)
 #define ESR		_MMIO(0x20b8)
-#define   GM45_ERROR_PAGE_TABLE				(1<<5)
-#define   GM45_ERROR_MEM_PRIV				(1<<4)
-#define   I915_ERROR_PAGE_TABLE				(1<<4)
-#define   GM45_ERROR_CP_PRIV				(1<<3)
-#define   I915_ERROR_MEMORY_REFRESH			(1<<1)
-#define   I915_ERROR_INSTRUCTION			(1<<0)
+#define   GM45_ERROR_PAGE_TABLE				(1 << 5)
+#define   GM45_ERROR_MEM_PRIV				(1 << 4)
+#define   I915_ERROR_PAGE_TABLE				(1 << 4)
+#define   GM45_ERROR_CP_PRIV				(1 << 3)
+#define   I915_ERROR_MEMORY_REFRESH			(1 << 1)
+#define   I915_ERROR_INSTRUCTION			(1 << 0)
 #define INSTPM	        _MMIO(0x20c0)
-#define   INSTPM_SELF_EN (1<<12) /* 915GM only */
-#define   INSTPM_AGPBUSY_INT_EN (1<<11) /* gen3: when disabled, pending interrupts
+#define   INSTPM_SELF_EN (1 << 12) /* 915GM only */
+#define   INSTPM_AGPBUSY_INT_EN (1 << 11) /* gen3: when disabled, pending interrupts
 					will not assert AGPBUSY# and will only
 					be delivered when out of C3. */
-#define   INSTPM_FORCE_ORDERING				(1<<7) /* GEN6+ */
-#define   INSTPM_TLB_INVALIDATE	(1<<9)
-#define   INSTPM_SYNC_FLUSH	(1<<5)
+#define   INSTPM_FORCE_ORDERING				(1 << 7) /* GEN6+ */
+#define   INSTPM_TLB_INVALIDATE	(1 << 9)
+#define   INSTPM_SYNC_FLUSH	(1 << 5)
 #define ACTHD	        _MMIO(0x20c8)
 #define MEM_MODE	_MMIO(0x20cc)
-#define   MEM_DISPLAY_B_TRICKLE_FEED_DISABLE (1<<3) /* 830 only */
-#define   MEM_DISPLAY_A_TRICKLE_FEED_DISABLE (1<<2) /* 830/845 only */
-#define   MEM_DISPLAY_TRICKLE_FEED_DISABLE (1<<2) /* 85x only */
+#define   MEM_DISPLAY_B_TRICKLE_FEED_DISABLE (1 << 3) /* 830 only */
+#define   MEM_DISPLAY_A_TRICKLE_FEED_DISABLE (1 << 2) /* 830/845 only */
+#define   MEM_DISPLAY_TRICKLE_FEED_DISABLE (1 << 2) /* 85x only */
 #define FW_BLC		_MMIO(0x20d8)
 #define FW_BLC2		_MMIO(0x20dc)
 #define FW_BLC_SELF	_MMIO(0x20e0) /* 915+ only */
-#define   FW_BLC_SELF_EN_MASK      (1<<31)
-#define   FW_BLC_SELF_FIFO_MASK    (1<<16) /* 945 only */
-#define   FW_BLC_SELF_EN           (1<<15) /* 945 only */
+#define   FW_BLC_SELF_EN_MASK      (1 << 31)
+#define   FW_BLC_SELF_FIFO_MASK    (1 << 16) /* 945 only */
+#define   FW_BLC_SELF_EN           (1 << 15) /* 945 only */
 #define MM_BURST_LENGTH     0x00700000
 #define MM_FIFO_WATERMARK   0x0001F000
 #define LM_BURST_LENGTH     0x00000700
@@ -2653,40 +2653,40 @@ enum i915_power_well_id {
 #define   MI_AGPBUSY_830_MODE			(1 << 0) /* 85x only */
 
 #define CACHE_MODE_0	_MMIO(0x2120) /* 915+ only */
-#define   CM0_PIPELINED_RENDER_FLUSH_DISABLE (1<<8)
-#define   CM0_IZ_OPT_DISABLE      (1<<6)
-#define   CM0_ZR_OPT_DISABLE      (1<<5)
-#define	  CM0_STC_EVICT_DISABLE_LRA_SNB	(1<<5)
-#define   CM0_DEPTH_EVICT_DISABLE (1<<4)
-#define   CM0_COLOR_EVICT_DISABLE (1<<3)
-#define   CM0_DEPTH_WRITE_DISABLE (1<<1)
-#define   CM0_RC_OP_FLUSH_DISABLE (1<<0)
+#define   CM0_PIPELINED_RENDER_FLUSH_DISABLE (1 << 8)
+#define   CM0_IZ_OPT_DISABLE      (1 << 6)
+#define   CM0_ZR_OPT_DISABLE      (1 << 5)
+#define	  CM0_STC_EVICT_DISABLE_LRA_SNB	(1 << 5)
+#define   CM0_DEPTH_EVICT_DISABLE (1 << 4)
+#define   CM0_COLOR_EVICT_DISABLE (1 << 3)
+#define   CM0_DEPTH_WRITE_DISABLE (1 << 1)
+#define   CM0_RC_OP_FLUSH_DISABLE (1 << 0)
 #define GFX_FLSH_CNTL	_MMIO(0x2170) /* 915+ only */
 #define GFX_FLSH_CNTL_GEN6	_MMIO(0x101008)
-#define   GFX_FLSH_CNTL_EN	(1<<0)
+#define   GFX_FLSH_CNTL_EN	(1 << 0)
 #define ECOSKPD		_MMIO(0x21d0)
-#define   ECO_GATING_CX_ONLY	(1<<3)
-#define   ECO_FLIP_DONE		(1<<0)
+#define   ECO_GATING_CX_ONLY	(1 << 3)
+#define   ECO_FLIP_DONE		(1 << 0)
 
 #define CACHE_MODE_0_GEN7	_MMIO(0x7000) /* IVB+ */
-#define RC_OP_FLUSH_ENABLE (1<<0)
-#define   HIZ_RAW_STALL_OPT_DISABLE (1<<2)
+#define RC_OP_FLUSH_ENABLE (1 << 0)
+#define   HIZ_RAW_STALL_OPT_DISABLE (1 << 2)
 #define CACHE_MODE_1		_MMIO(0x7004) /* IVB+ */
-#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1<<6)
-#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1<<6)
-#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1<<1)
+#define   PIXEL_SUBSPAN_COLLECT_OPT_DISABLE	(1 << 6)
+#define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1 << 6)
+#define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1 << 1)
 
 #define GEN10_CACHE_MODE_SS			_MMIO(0xe420)
 #define   FLOAT_BLEND_OPTIMIZATION_ENABLE	(1 << 4)
 
 #define GEN6_BLITTER_ECOSKPD	_MMIO(0x221d0)
 #define   GEN6_BLITTER_LOCK_SHIFT			16
-#define   GEN6_BLITTER_FBC_NOTIFY			(1<<3)
+#define   GEN6_BLITTER_FBC_NOTIFY			(1 << 3)
 
 #define GEN6_RC_SLEEP_PSMI_CONTROL	_MMIO(0x2050)
 #define   GEN6_PSMI_SLEEP_MSG_DISABLE	(1 << 0)
 #define   GEN8_RC_SEMA_IDLE_MSG_DISABLE	(1 << 12)
-#define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1<<10)
+#define   GEN8_FF_DOP_CLOCK_GATE_DISABLE	(1 << 10)
 
 #define GEN6_RCS_PWR_FSM _MMIO(0x22ac)
 #define GEN9_RCS_FE_FSM2 _MMIO(0x22a4)
@@ -2742,7 +2742,7 @@ enum i915_power_well_id {
 #define GEN8_EU_DISABLE2		_MMIO(0x913c)
 #define   GEN8_EU_DIS2_S2_MASK		0xff
 
-#define GEN9_EU_DISABLE(slice)		_MMIO(0x9134 + (slice)*0x4)
+#define GEN9_EU_DISABLE(slice)		_MMIO(0x9134 + (slice) * 0x4)
 
 #define GEN10_EU_DISABLE3		_MMIO(0x9140)
 #define   GEN10_EU_DIS_SS_MASK		0xff
@@ -2799,44 +2799,44 @@ enum i915_power_well_id {
 	 (IS_HASWELL(dev_priv) ? GT_RENDER_L3_PARITY_ERROR_INTERRUPT_S1 : 0))
 
 /* These are all the "old" interrupts */
-#define ILK_BSD_USER_INTERRUPT				(1<<5)
-
-#define I915_PM_INTERRUPT				(1<<31)
-#define I915_ISP_INTERRUPT				(1<<22)
-#define I915_LPE_PIPE_B_INTERRUPT			(1<<21)
-#define I915_LPE_PIPE_A_INTERRUPT			(1<<20)
-#define I915_MIPIC_INTERRUPT				(1<<19)
-#define I915_MIPIA_INTERRUPT				(1<<18)
-#define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1<<18)
-#define I915_DISPLAY_PORT_INTERRUPT			(1<<17)
-#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT		(1<<16)
-#define I915_MASTER_ERROR_INTERRUPT			(1<<15)
-#define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1<<15)
-#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT		(1<<14)
-#define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1<<14) /* p-state */
-#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT		(1<<13)
-#define I915_HWB_OOM_INTERRUPT				(1<<13)
-#define I915_LPE_PIPE_C_INTERRUPT			(1<<12)
-#define I915_SYNC_STATUS_INTERRUPT			(1<<12)
-#define I915_MISC_INTERRUPT				(1<<11)
-#define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT	(1<<11)
-#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT		(1<<10)
-#define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT	(1<<10)
-#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT		(1<<9)
-#define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT	(1<<9)
-#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT		(1<<8)
-#define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT	(1<<8)
-#define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT		(1<<7)
-#define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT		(1<<6)
-#define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT		(1<<5)
-#define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT		(1<<4)
-#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT		(1<<3)
-#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT		(1<<2)
-#define I915_DEBUG_INTERRUPT				(1<<2)
-#define I915_WINVALID_INTERRUPT				(1<<1)
-#define I915_USER_INTERRUPT				(1<<1)
-#define I915_ASLE_INTERRUPT				(1<<0)
-#define I915_BSD_USER_INTERRUPT				(1<<25)
+#define ILK_BSD_USER_INTERRUPT				(1 << 5)
+
+#define I915_PM_INTERRUPT				(1 << 31)
+#define I915_ISP_INTERRUPT				(1 << 22)
+#define I915_LPE_PIPE_B_INTERRUPT			(1 << 21)
+#define I915_LPE_PIPE_A_INTERRUPT			(1 << 20)
+#define I915_MIPIC_INTERRUPT				(1 << 19)
+#define I915_MIPIA_INTERRUPT				(1 << 18)
+#define I915_PIPE_CONTROL_NOTIFY_INTERRUPT		(1 << 18)
+#define I915_DISPLAY_PORT_INTERRUPT			(1 << 17)
+#define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT		(1 << 16)
+#define I915_MASTER_ERROR_INTERRUPT			(1 << 15)
+#define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1 << 15)
+#define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT		(1 << 14)
+#define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1 << 14) /* p-state */
+#define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT		(1 << 13)
+#define I915_HWB_OOM_INTERRUPT				(1 << 13)
+#define I915_LPE_PIPE_C_INTERRUPT			(1 << 12)
+#define I915_SYNC_STATUS_INTERRUPT			(1 << 12)
+#define I915_MISC_INTERRUPT				(1 << 11)
+#define I915_DISPLAY_PLANE_A_FLIP_PENDING_INTERRUPT	(1 << 11)
+#define I915_DISPLAY_PIPE_C_VBLANK_INTERRUPT		(1 << 10)
+#define I915_DISPLAY_PLANE_B_FLIP_PENDING_INTERRUPT	(1 << 10)
+#define I915_DISPLAY_PIPE_C_EVENT_INTERRUPT		(1 << 9)
+#define I915_OVERLAY_PLANE_FLIP_PENDING_INTERRUPT	(1 << 9)
+#define I915_DISPLAY_PIPE_C_DPBM_INTERRUPT		(1 << 8)
+#define I915_DISPLAY_PLANE_C_FLIP_PENDING_INTERRUPT	(1 << 8)
+#define I915_DISPLAY_PIPE_A_VBLANK_INTERRUPT		(1 << 7)
+#define I915_DISPLAY_PIPE_A_EVENT_INTERRUPT		(1 << 6)
+#define I915_DISPLAY_PIPE_B_VBLANK_INTERRUPT		(1 << 5)
+#define I915_DISPLAY_PIPE_B_EVENT_INTERRUPT		(1 << 4)
+#define I915_DISPLAY_PIPE_A_DPBM_INTERRUPT		(1 << 3)
+#define I915_DISPLAY_PIPE_B_DPBM_INTERRUPT		(1 << 2)
+#define I915_DEBUG_INTERRUPT				(1 << 2)
+#define I915_WINVALID_INTERRUPT				(1 << 1)
+#define I915_USER_INTERRUPT				(1 << 1)
+#define I915_ASLE_INTERRUPT				(1 << 0)
+#define I915_BSD_USER_INTERRUPT				(1 << 25)
 
 #define I915_HDMI_LPE_AUDIO_BASE	(VLV_DISPLAY_BASE + 0x65000)
 #define I915_HDMI_LPE_AUDIO_SIZE	0x1000
@@ -2859,19 +2859,19 @@ enum i915_power_well_id {
 #define GEN7_FF_THREAD_MODE		_MMIO(0x20a0)
 #define   GEN7_FF_SCHED_MASK		0x0077070
 #define   GEN8_FF_DS_REF_CNT_FFME	(1 << 19)
-#define   GEN7_FF_TS_SCHED_HS1		(0x5<<16)
-#define   GEN7_FF_TS_SCHED_HS0		(0x3<<16)
-#define   GEN7_FF_TS_SCHED_LOAD_BALANCE	(0x1<<16)
-#define   GEN7_FF_TS_SCHED_HW		(0x0<<16) /* Default */
+#define   GEN7_FF_TS_SCHED_HS1		(0x5 << 16)
+#define   GEN7_FF_TS_SCHED_HS0		(0x3 << 16)
+#define   GEN7_FF_TS_SCHED_LOAD_BALANCE	(0x1 << 16)
+#define   GEN7_FF_TS_SCHED_HW		(0x0 << 16) /* Default */
 #define   GEN7_FF_VS_REF_CNT_FFME	(1 << 15)
-#define   GEN7_FF_VS_SCHED_HS1		(0x5<<12)
-#define   GEN7_FF_VS_SCHED_HS0		(0x3<<12)
-#define   GEN7_FF_VS_SCHED_LOAD_BALANCE	(0x1<<12) /* Default */
-#define   GEN7_FF_VS_SCHED_HW		(0x0<<12)
-#define   GEN7_FF_DS_SCHED_HS1		(0x5<<4)
-#define   GEN7_FF_DS_SCHED_HS0		(0x3<<4)
-#define   GEN7_FF_DS_SCHED_LOAD_BALANCE	(0x1<<4)  /* Default */
-#define   GEN7_FF_DS_SCHED_HW		(0x0<<4)
+#define   GEN7_FF_VS_SCHED_HS1		(0x5 << 12)
+#define   GEN7_FF_VS_SCHED_HS0		(0x3 << 12)
+#define   GEN7_FF_VS_SCHED_LOAD_BALANCE	(0x1 << 12) /* Default */
+#define   GEN7_FF_VS_SCHED_HW		(0x0 << 12)
+#define   GEN7_FF_DS_SCHED_HS1		(0x5 << 4)
+#define   GEN7_FF_DS_SCHED_HS0		(0x3 << 4)
+#define   GEN7_FF_DS_SCHED_LOAD_BALANCE	(0x1 << 4)  /* Default */
+#define   GEN7_FF_DS_SCHED_HW		(0x0 << 4)
 
 /*
  * Framebuffer compression (915+ only)
@@ -2880,51 +2880,51 @@ enum i915_power_well_id {
 #define FBC_CFB_BASE		_MMIO(0x3200) /* 4k page aligned */
 #define FBC_LL_BASE		_MMIO(0x3204) /* 4k page aligned */
 #define FBC_CONTROL		_MMIO(0x3208)
-#define   FBC_CTL_EN		(1<<31)
-#define   FBC_CTL_PERIODIC	(1<<30)
+#define   FBC_CTL_EN		(1 << 31)
+#define   FBC_CTL_PERIODIC	(1 << 30)
 #define   FBC_CTL_INTERVAL_SHIFT (16)
-#define   FBC_CTL_UNCOMPRESSIBLE (1<<14)
-#define   FBC_CTL_C3_IDLE	(1<<13)
+#define   FBC_CTL_UNCOMPRESSIBLE (1 << 14)
+#define   FBC_CTL_C3_IDLE	(1 << 13)
 #define   FBC_CTL_STRIDE_SHIFT	(5)
 #define   FBC_CTL_FENCENO_SHIFT	(0)
 #define FBC_COMMAND		_MMIO(0x320c)
-#define   FBC_CMD_COMPRESS	(1<<0)
+#define   FBC_CMD_COMPRESS	(1 << 0)
 #define FBC_STATUS		_MMIO(0x3210)
-#define   FBC_STAT_COMPRESSING	(1<<31)
-#define   FBC_STAT_COMPRESSED	(1<<30)
-#define   FBC_STAT_MODIFIED	(1<<29)
+#define   FBC_STAT_COMPRESSING	(1 << 31)
+#define   FBC_STAT_COMPRESSED	(1 << 30)
+#define   FBC_STAT_MODIFIED	(1 << 29)
 #define   FBC_STAT_CURRENT_LINE_SHIFT	(0)
 #define FBC_CONTROL2		_MMIO(0x3214)
-#define   FBC_CTL_FENCE_DBL	(0<<4)
-#define   FBC_CTL_IDLE_IMM	(0<<2)
-#define   FBC_CTL_IDLE_FULL	(1<<2)
-#define   FBC_CTL_IDLE_LINE	(2<<2)
-#define   FBC_CTL_IDLE_DEBUG	(3<<2)
-#define   FBC_CTL_CPU_FENCE	(1<<1)
-#define   FBC_CTL_PLANE(plane)	((plane)<<0)
+#define   FBC_CTL_FENCE_DBL	(0 << 4)
+#define   FBC_CTL_IDLE_IMM	(0 << 2)
+#define   FBC_CTL_IDLE_FULL	(1 << 2)
+#define   FBC_CTL_IDLE_LINE	(2 << 2)
+#define   FBC_CTL_IDLE_DEBUG	(3 << 2)
+#define   FBC_CTL_CPU_FENCE	(1 << 1)
+#define   FBC_CTL_PLANE(plane)	((plane) << 0)
 #define FBC_FENCE_OFF		_MMIO(0x3218) /* BSpec typo has 321Bh */
 #define FBC_TAG(i)		_MMIO(0x3300 + (i) * 4)
 
 #define FBC_LL_SIZE		(1536)
 
 #define FBC_LLC_READ_CTRL	_MMIO(0x9044)
-#define   FBC_LLC_FULLY_OPEN	(1<<30)
+#define   FBC_LLC_FULLY_OPEN	(1 << 30)
 
 /* Framebuffer compression for GM45+ */
 #define DPFC_CB_BASE		_MMIO(0x3200)
 #define DPFC_CONTROL		_MMIO(0x3208)
-#define   DPFC_CTL_EN		(1<<31)
-#define   DPFC_CTL_PLANE(plane)	((plane)<<30)
-#define   IVB_DPFC_CTL_PLANE(plane)	((plane)<<29)
-#define   DPFC_CTL_FENCE_EN	(1<<29)
-#define   IVB_DPFC_CTL_FENCE_EN	(1<<28)
-#define   DPFC_CTL_PERSISTENT_MODE	(1<<25)
-#define   DPFC_SR_EN		(1<<10)
-#define   DPFC_CTL_LIMIT_1X	(0<<6)
-#define   DPFC_CTL_LIMIT_2X	(1<<6)
-#define   DPFC_CTL_LIMIT_4X	(2<<6)
+#define   DPFC_CTL_EN		(1 << 31)
+#define   DPFC_CTL_PLANE(plane)	((plane) << 30)
+#define   IVB_DPFC_CTL_PLANE(plane)	((plane) << 29)
+#define   DPFC_CTL_FENCE_EN	(1 << 29)
+#define   IVB_DPFC_CTL_FENCE_EN	(1 << 28)
+#define   DPFC_CTL_PERSISTENT_MODE	(1 << 25)
+#define   DPFC_SR_EN		(1 << 10)
+#define   DPFC_CTL_LIMIT_1X	(0 << 6)
+#define   DPFC_CTL_LIMIT_2X	(1 << 6)
+#define   DPFC_CTL_LIMIT_4X	(2 << 6)
 #define DPFC_RECOMP_CTL		_MMIO(0x320c)
-#define   DPFC_RECOMP_STALL_EN	(1<<27)
+#define   DPFC_RECOMP_STALL_EN	(1 << 27)
 #define   DPFC_RECOMP_STALL_WM_SHIFT (16)
 #define   DPFC_RECOMP_STALL_WM_MASK (0x07ff0000)
 #define   DPFC_RECOMP_TIMER_COUNT_SHIFT (0)
@@ -2937,12 +2937,12 @@ enum i915_power_well_id {
 #define DPFC_STATUS2		_MMIO(0x3214)
 #define DPFC_FENCE_YOFF		_MMIO(0x3218)
 #define DPFC_CHICKEN		_MMIO(0x3224)
-#define   DPFC_HT_MODIFY	(1<<31)
+#define   DPFC_HT_MODIFY	(1 << 31)
 
 /* Framebuffer compression for Ironlake */
 #define ILK_DPFC_CB_BASE	_MMIO(0x43200)
 #define ILK_DPFC_CONTROL	_MMIO(0x43208)
-#define   FBC_CTL_FALSE_COLOR	(1<<10)
+#define   FBC_CTL_FALSE_COLOR	(1 << 10)
 /* The bit 28-8 is reserved */
 #define   DPFC_RESERVED		(0x1FFFFF00)
 #define ILK_DPFC_RECOMP_CTL	_MMIO(0x4320c)
@@ -2953,15 +2953,15 @@ enum i915_power_well_id {
 #define  BDW_FBC_COMP_SEG_MASK	0xfff
 #define ILK_DPFC_FENCE_YOFF	_MMIO(0x43218)
 #define ILK_DPFC_CHICKEN	_MMIO(0x43224)
-#define   ILK_DPFC_DISABLE_DUMMY0 (1<<8)
-#define   ILK_DPFC_NUKE_ON_ANY_MODIFICATION	(1<<23)
+#define   ILK_DPFC_DISABLE_DUMMY0 (1 << 8)
+#define   ILK_DPFC_NUKE_ON_ANY_MODIFICATION	(1 << 23)
 #define ILK_FBC_RT_BASE		_MMIO(0x2128)
-#define   ILK_FBC_RT_VALID	(1<<0)
-#define   SNB_FBC_FRONT_BUFFER	(1<<1)
+#define   ILK_FBC_RT_VALID	(1 << 0)
+#define   SNB_FBC_FRONT_BUFFER	(1 << 1)
 
 #define ILK_DISPLAY_CHICKEN1	_MMIO(0x42000)
-#define   ILK_FBCQ_DIS		(1<<22)
-#define	  ILK_PABSTRETCH_DIS	(1<<21)
+#define   ILK_FBCQ_DIS		(1 << 22)
+#define	  ILK_PABSTRETCH_DIS	(1 << 21)
 
 
 /*
@@ -2970,7 +2970,7 @@ enum i915_power_well_id {
  * The following two registers are of type GTTMMADR
  */
 #define SNB_DPFC_CTL_SA		_MMIO(0x100100)
-#define   SNB_CPU_FENCE_ENABLE	(1<<29)
+#define   SNB_CPU_FENCE_ENABLE	(1 << 29)
 #define DPFC_CPU_FENCE_OFFSET	_MMIO(0x100104)
 
 /* Framebuffer compression for Ivybridge */
@@ -2980,8 +2980,8 @@ enum i915_power_well_id {
 #define   IPS_ENABLE	(1 << 31)
 
 #define MSG_FBC_REND_STATE	_MMIO(0x50380)
-#define   FBC_REND_NUKE		(1<<2)
-#define   FBC_REND_CACHE_CLEAN	(1<<1)
+#define   FBC_REND_NUKE		(1 << 2)
+#define   FBC_REND_CACHE_CLEAN	(1 << 1)
 
 /*
  * GPIO regs
@@ -3014,12 +3014,12 @@ enum i915_power_well_id {
 # define GPIO_DATA_PULLUP_DISABLE	(1 << 13)
 
 #define GMBUS0			_MMIO(dev_priv->gpio_mmio_base + 0x5100) /* clock/port select */
-#define   GMBUS_AKSV_SELECT	(1<<11)
-#define   GMBUS_RATE_100KHZ	(0<<8)
-#define   GMBUS_RATE_50KHZ	(1<<8)
-#define   GMBUS_RATE_400KHZ	(2<<8) /* reserved on Pineview */
-#define   GMBUS_RATE_1MHZ	(3<<8) /* reserved on Pineview */
-#define   GMBUS_HOLD_EXT	(1<<7) /* 300ns hold time, rsvd on Pineview */
+#define   GMBUS_AKSV_SELECT	(1 << 11)
+#define   GMBUS_RATE_100KHZ	(0 << 8)
+#define   GMBUS_RATE_50KHZ	(1 << 8)
+#define   GMBUS_RATE_400KHZ	(2 << 8) /* reserved on Pineview */
+#define   GMBUS_RATE_1MHZ	(3 << 8) /* reserved on Pineview */
+#define   GMBUS_HOLD_EXT	(1 << 7) /* 300ns hold time, rsvd on Pineview */
 #define   GMBUS_PIN_DISABLED	0
 #define   GMBUS_PIN_SSC		1
 #define   GMBUS_PIN_VGADDC	2
@@ -3040,36 +3040,36 @@ enum i915_power_well_id {
 
 #define   GMBUS_NUM_PINS	13 /* including 0 */
 #define GMBUS1			_MMIO(dev_priv->gpio_mmio_base + 0x5104) /* command/status */
-#define   GMBUS_SW_CLR_INT	(1<<31)
-#define   GMBUS_SW_RDY		(1<<30)
-#define   GMBUS_ENT		(1<<29) /* enable timeout */
-#define   GMBUS_CYCLE_NONE	(0<<25)
-#define   GMBUS_CYCLE_WAIT	(1<<25)
-#define   GMBUS_CYCLE_INDEX	(2<<25)
-#define   GMBUS_CYCLE_STOP	(4<<25)
+#define   GMBUS_SW_CLR_INT	(1 << 31)
+#define   GMBUS_SW_RDY		(1 << 30)
+#define   GMBUS_ENT		(1 << 29) /* enable timeout */
+#define   GMBUS_CYCLE_NONE	(0 << 25)
+#define   GMBUS_CYCLE_WAIT	(1 << 25)
+#define   GMBUS_CYCLE_INDEX	(2 << 25)
+#define   GMBUS_CYCLE_STOP	(4 << 25)
 #define   GMBUS_BYTE_COUNT_SHIFT 16
 #define   GMBUS_BYTE_COUNT_MAX   256U
 #define   GMBUS_SLAVE_INDEX_SHIFT 8
 #define   GMBUS_SLAVE_ADDR_SHIFT 1
-#define   GMBUS_SLAVE_READ	(1<<0)
-#define   GMBUS_SLAVE_WRITE	(0<<0)
+#define   GMBUS_SLAVE_READ	(1 << 0)
+#define   GMBUS_SLAVE_WRITE	(0 << 0)
 #define GMBUS2			_MMIO(dev_priv->gpio_mmio_base + 0x5108) /* status */
-#define   GMBUS_INUSE		(1<<15)
-#define   GMBUS_HW_WAIT_PHASE	(1<<14)
-#define   GMBUS_STALL_TIMEOUT	(1<<13)
-#define   GMBUS_INT		(1<<12)
-#define   GMBUS_HW_RDY		(1<<11)
-#define   GMBUS_SATOER		(1<<10)
-#define   GMBUS_ACTIVE		(1<<9)
+#define   GMBUS_INUSE		(1 << 15)
+#define   GMBUS_HW_WAIT_PHASE	(1 << 14)
+#define   GMBUS_STALL_TIMEOUT	(1 << 13)
+#define   GMBUS_INT		(1 << 12)
+#define   GMBUS_HW_RDY		(1 << 11)
+#define   GMBUS_SATOER		(1 << 10)
+#define   GMBUS_ACTIVE		(1 << 9)
 #define GMBUS3			_MMIO(dev_priv->gpio_mmio_base + 0x510c) /* data buffer bytes 3-0 */
 #define GMBUS4			_MMIO(dev_priv->gpio_mmio_base + 0x5110) /* interrupt mask (Pineview+) */
-#define   GMBUS_SLAVE_TIMEOUT_EN (1<<4)
-#define   GMBUS_NAK_EN		(1<<3)
-#define   GMBUS_IDLE_EN		(1<<2)
-#define   GMBUS_HW_WAIT_EN	(1<<1)
-#define   GMBUS_HW_RDY_EN	(1<<0)
+#define   GMBUS_SLAVE_TIMEOUT_EN (1 << 4)
+#define   GMBUS_NAK_EN		(1 << 3)
+#define   GMBUS_IDLE_EN		(1 << 2)
+#define   GMBUS_HW_WAIT_EN	(1 << 1)
+#define   GMBUS_HW_RDY_EN	(1 << 0)
 #define GMBUS5			_MMIO(dev_priv->gpio_mmio_base + 0x5120) /* byte index */
-#define   GMBUS_2BYTE_INDEX_EN	(1<<31)
+#define   GMBUS_2BYTE_INDEX_EN	(1 << 31)
 
 /*
  * Clock control & power management
@@ -3107,10 +3107,10 @@ enum i915_power_well_id {
 #define   DPLL_P2_CLOCK_DIV_MASK	0x03000000 /* i915 */
 #define   DPLL_FPA01_P1_POST_DIV_MASK	0x00ff0000 /* i915 */
 #define   DPLL_FPA01_P1_POST_DIV_MASK_PINEVIEW	0x00ff8000 /* Pineview */
-#define   DPLL_LOCK_VLV			(1<<15)
-#define   DPLL_INTEGRATED_CRI_CLK_VLV	(1<<14)
-#define   DPLL_INTEGRATED_REF_CLK_VLV	(1<<13)
-#define   DPLL_SSC_REF_CLK_CHV		(1<<13)
+#define   DPLL_LOCK_VLV			(1 << 15)
+#define   DPLL_INTEGRATED_CRI_CLK_VLV	(1 << 14)
+#define   DPLL_INTEGRATED_REF_CLK_VLV	(1 << 13)
+#define   DPLL_SSC_REF_CLK_CHV		(1 << 13)
 #define   DPLL_PORTC_READY_MASK		(0xf << 4)
 #define   DPLL_PORTB_READY_MASK		(0xf)
 
@@ -3120,20 +3120,20 @@ enum i915_power_well_id {
 #define DPIO_PHY_STATUS			_MMIO(VLV_DISPLAY_BASE + 0x6240)
 #define   DPLL_PORTD_READY_MASK		(0xf)
 #define DISPLAY_PHY_CONTROL _MMIO(VLV_DISPLAY_BASE + 0x60100)
-#define   PHY_CH_POWER_DOWN_OVRD_EN(phy, ch)	(1 << (2*(phy)+(ch)+27))
+#define   PHY_CH_POWER_DOWN_OVRD_EN(phy, ch)	(1 << (2 * (phy) + (ch) + 27))
 #define   PHY_LDO_DELAY_0NS			0x0
 #define   PHY_LDO_DELAY_200NS			0x1
 #define   PHY_LDO_DELAY_600NS			0x2
-#define   PHY_LDO_SEQ_DELAY(delay, phy)		((delay) << (2*(phy)+23))
-#define   PHY_CH_POWER_DOWN_OVRD(mask, phy, ch)	((mask) << (8*(phy)+4*(ch)+11))
+#define   PHY_LDO_SEQ_DELAY(delay, phy)		((delay) << (2 * (phy) + 23))
+#define   PHY_CH_POWER_DOWN_OVRD(mask, phy, ch)	((mask) << (8 * (phy) + 4 * (ch) + 11))
 #define   PHY_CH_SU_PSR				0x1
 #define   PHY_CH_DEEP_PSR			0x7
-#define   PHY_CH_POWER_MODE(mode, phy, ch)	((mode) << (6*(phy)+3*(ch)+2))
+#define   PHY_CH_POWER_MODE(mode, phy, ch)	((mode) << (6 * (phy) + 3 * (ch) + 2))
 #define   PHY_COM_LANE_RESET_DEASSERT(phy)	(1 << (phy))
 #define DISPLAY_PHY_STATUS _MMIO(VLV_DISPLAY_BASE + 0x60104)
-#define   PHY_POWERGOOD(phy)	(((phy) == DPIO_PHY0) ? (1<<31) : (1<<30))
-#define   PHY_STATUS_CMN_LDO(phy, ch)                   (1 << (6-(6*(phy)+3*(ch))))
-#define   PHY_STATUS_SPLINE_LDO(phy, ch, spline)        (1 << (8-(6*(phy)+3*(ch)+(spline))))
+#define   PHY_POWERGOOD(phy)	(((phy) == DPIO_PHY0) ? (1 << 31) : (1 << 30))
+#define   PHY_STATUS_CMN_LDO(phy, ch)                   (1 << (6 - (6 * (phy) + 3 * (ch))))
+#define   PHY_STATUS_SPLINE_LDO(phy, ch, spline)        (1 << (8 - (6 * (phy) + 3 * (ch) + (spline))))
 
 /*
  * The i830 generation, in LVDS mode, defines P1 as the bit number set within
@@ -3154,7 +3154,7 @@ enum i915_power_well_id {
 /* Ironlake */
 # define PLL_REF_SDVO_HDMI_MULTIPLIER_SHIFT     9
 # define PLL_REF_SDVO_HDMI_MULTIPLIER_MASK      (7 << 9)
-# define PLL_REF_SDVO_HDMI_MULTIPLIER(x)	(((x)-1) << 9)
+# define PLL_REF_SDVO_HDMI_MULTIPLIER(x)	(((x) - 1) << 9)
 # define DPLL_FPA1_P1_POST_DIV_SHIFT            0
 # define DPLL_FPA1_P1_POST_DIV_MASK             0xff
 
@@ -3243,10 +3243,10 @@ enum i915_power_well_id {
 #define   DPLLA_TEST_M_BYPASS		(1 << 2)
 #define   DPLLA_INPUT_BUFFER_ENABLE	(1 << 0)
 #define D_STATE		_MMIO(0x6104)
-#define  DSTATE_GFX_RESET_I830			(1<<6)
-#define  DSTATE_PLL_D3_OFF			(1<<3)
-#define  DSTATE_GFX_CLOCK_GATING		(1<<1)
-#define  DSTATE_DOT_CLOCK_GATING		(1<<0)
+#define  DSTATE_GFX_RESET_I830			(1 << 6)
+#define  DSTATE_PLL_D3_OFF			(1 << 3)
+#define  DSTATE_GFX_CLOCK_GATING		(1 << 1)
+#define  DSTATE_DOT_CLOCK_GATING		(1 << 0)
 #define DSPCLK_GATE_D	_MMIO(dev_priv->info.display_mmio_offset + 0x6200)
 # define DPUNIT_B_CLOCK_GATE_DISABLE		(1 << 30) /* 965 */
 # define VSUNIT_CLOCK_GATE_DISABLE		(1 << 29) /* 965 */
@@ -3363,7 +3363,7 @@ enum i915_power_well_id {
 #define DEUC			_MMIO(0x6214)          /* CRL only */
 
 #define FW_BLC_SELF_VLV		_MMIO(VLV_DISPLAY_BASE + 0x6500)
-#define  FW_CSPWRDWNEN		(1<<15)
+#define  FW_CSPWRDWNEN		(1 << 15)
 
 #define MI_ARB_VLV		_MMIO(VLV_DISPLAY_BASE + 0x6504)
 
@@ -3488,7 +3488,7 @@ enum i915_power_well_id {
 #define HPLLVCO_MOBILE          _MMIO(MCHBAR_MIRROR_BASE + 0xc0f)
 
 #define TSC1			_MMIO(0x11001)
-#define   TSE			(1<<0)
+#define   TSE			(1 << 0)
 #define TR1			_MMIO(0x11006)
 #define TSFS			_MMIO(0x11020)
 #define   TSFS_SLOPE_MASK	0x0000ff00
@@ -3534,23 +3534,23 @@ enum i915_power_well_id {
 #define   MEMCTL_CMD_CHVID	3
 #define   MEMCTL_CMD_VMMOFF	4
 #define   MEMCTL_CMD_VMMON	5
-#define   MEMCTL_CMD_STS	(1<<12) /* write 1 triggers command, clears
+#define   MEMCTL_CMD_STS	(1 << 12) /* write 1 triggers command, clears
 					   when command complete */
 #define   MEMCTL_FREQ_MASK	0x0f00 /* jitter, from 0-15 */
 #define   MEMCTL_FREQ_SHIFT	8
-#define   MEMCTL_SFCAVM		(1<<7)
+#define   MEMCTL_SFCAVM		(1 << 7)
 #define   MEMCTL_TGT_VID_MASK	0x007f
 #define MEMIHYST		_MMIO(0x1117c)
 #define MEMINTREN		_MMIO(0x11180) /* 16 bits */
-#define   MEMINT_RSEXIT_EN	(1<<8)
-#define   MEMINT_CX_SUPR_EN	(1<<7)
-#define   MEMINT_CONT_BUSY_EN	(1<<6)
-#define   MEMINT_AVG_BUSY_EN	(1<<5)
-#define   MEMINT_EVAL_CHG_EN	(1<<4)
-#define   MEMINT_MON_IDLE_EN	(1<<3)
-#define   MEMINT_UP_EVAL_EN	(1<<2)
-#define   MEMINT_DOWN_EVAL_EN	(1<<1)
-#define   MEMINT_SW_CMD_EN	(1<<0)
+#define   MEMINT_RSEXIT_EN	(1 << 8)
+#define   MEMINT_CX_SUPR_EN	(1 << 7)
+#define   MEMINT_CONT_BUSY_EN	(1 << 6)
+#define   MEMINT_AVG_BUSY_EN	(1 << 5)
+#define   MEMINT_EVAL_CHG_EN	(1 << 4)
+#define   MEMINT_MON_IDLE_EN	(1 << 3)
+#define   MEMINT_UP_EVAL_EN	(1 << 2)
+#define   MEMINT_DOWN_EVAL_EN	(1 << 1)
+#define   MEMINT_SW_CMD_EN	(1 << 0)
 #define MEMINTRSTR		_MMIO(0x11182) /* 16 bits */
 #define   MEM_RSEXIT_MASK	0xc000
 #define   MEM_RSEXIT_SHIFT	14
@@ -3572,26 +3572,26 @@ enum i915_power_well_id {
 #define   MEM_INT_STEER_SMI	2
 #define   MEM_INT_STEER_SCI	3
 #define MEMINTRSTS		_MMIO(0x11184)
-#define   MEMINT_RSEXIT		(1<<7)
-#define   MEMINT_CONT_BUSY	(1<<6)
-#define   MEMINT_AVG_BUSY	(1<<5)
-#define   MEMINT_EVAL_CHG	(1<<4)
-#define   MEMINT_MON_IDLE	(1<<3)
-#define   MEMINT_UP_EVAL	(1<<2)
-#define   MEMINT_DOWN_EVAL	(1<<1)
-#define   MEMINT_SW_CMD		(1<<0)
+#define   MEMINT_RSEXIT		(1 << 7)
+#define   MEMINT_CONT_BUSY	(1 << 6)
+#define   MEMINT_AVG_BUSY	(1 << 5)
+#define   MEMINT_EVAL_CHG	(1 << 4)
+#define   MEMINT_MON_IDLE	(1 << 3)
+#define   MEMINT_UP_EVAL	(1 << 2)
+#define   MEMINT_DOWN_EVAL	(1 << 1)
+#define   MEMINT_SW_CMD		(1 << 0)
 #define MEMMODECTL		_MMIO(0x11190)
-#define   MEMMODE_BOOST_EN	(1<<31)
+#define   MEMMODE_BOOST_EN	(1 << 31)
 #define   MEMMODE_BOOST_FREQ_MASK 0x0f000000 /* jitter for boost, 0-15 */
 #define   MEMMODE_BOOST_FREQ_SHIFT 24
 #define   MEMMODE_IDLE_MODE_MASK 0x00030000
 #define   MEMMODE_IDLE_MODE_SHIFT 16
 #define   MEMMODE_IDLE_MODE_EVAL 0
 #define   MEMMODE_IDLE_MODE_CONT 1
-#define   MEMMODE_HWIDLE_EN	(1<<15)
-#define   MEMMODE_SWMODE_EN	(1<<14)
-#define   MEMMODE_RCLK_GATE	(1<<13)
-#define   MEMMODE_HW_UPDATE	(1<<12)
+#define   MEMMODE_HWIDLE_EN	(1 << 15)
+#define   MEMMODE_SWMODE_EN	(1 << 14)
+#define   MEMMODE_RCLK_GATE	(1 << 13)
+#define   MEMMODE_HW_UPDATE	(1 << 12)
 #define   MEMMODE_FSTART_MASK	0x00000f00 /* starting jitter, 0-15 */
 #define   MEMMODE_FSTART_SHIFT	8
 #define   MEMMODE_FMAX_MASK	0x000000f0 /* max jitter, 0-15 */
@@ -3605,8 +3605,8 @@ enum i915_power_well_id {
 #define   SWMEMCMD_TARVID	(3 << 13)
 #define   SWMEMCMD_VRM_OFF	(4 << 13)
 #define   SWMEMCMD_VRM_ON	(5 << 13)
-#define   CMDSTS		(1<<12)
-#define   SFCAVM		(1<<11)
+#define   CMDSTS		(1 << 12)
+#define   SFCAVM		(1 << 11)
 #define   SWFREQ_MASK		0x0380 /* P0-7 */
 #define   SWFREQ_SHIFT		7
 #define   TARVID_MASK		0x001f
@@ -3615,49 +3615,49 @@ enum i915_power_well_id {
 #define RCUPEI			_MMIO(0x111b0)
 #define RCDNEI			_MMIO(0x111b4)
 #define RSTDBYCTL		_MMIO(0x111b8)
-#define   RS1EN			(1<<31)
-#define   RS2EN			(1<<30)
-#define   RS3EN			(1<<29)
-#define   D3RS3EN		(1<<28) /* Display D3 imlies RS3 */
-#define   SWPROMORSX		(1<<27) /* RSx promotion timers ignored */
-#define   RCWAKERW		(1<<26) /* Resetwarn from PCH causes wakeup */
-#define   DPRSLPVREN		(1<<25) /* Fast voltage ramp enable */
-#define   GFXTGHYST		(1<<24) /* Hysteresis to allow trunk gating */
-#define   RCX_SW_EXIT		(1<<23) /* Leave RSx and prevent re-entry */
-#define   RSX_STATUS_MASK	(7<<20)
-#define   RSX_STATUS_ON		(0<<20)
-#define   RSX_STATUS_RC1	(1<<20)
-#define   RSX_STATUS_RC1E	(2<<20)
-#define   RSX_STATUS_RS1	(3<<20)
-#define   RSX_STATUS_RS2	(4<<20) /* aka rc6 */
-#define   RSX_STATUS_RSVD	(5<<20) /* deep rc6 unsupported on ilk */
-#define   RSX_STATUS_RS3	(6<<20) /* rs3 unsupported on ilk */
-#define   RSX_STATUS_RSVD2	(7<<20)
-#define   UWRCRSXE		(1<<19) /* wake counter limit prevents rsx */
-#define   RSCRP			(1<<18) /* rs requests control on rs1/2 reqs */
-#define   JRSC			(1<<17) /* rsx coupled to cpu c-state */
-#define   RS2INC0		(1<<16) /* allow rs2 in cpu c0 */
-#define   RS1CONTSAV_MASK	(3<<14)
-#define   RS1CONTSAV_NO_RS1	(0<<14) /* rs1 doesn't save/restore context */
-#define   RS1CONTSAV_RSVD	(1<<14)
-#define   RS1CONTSAV_SAVE_RS1	(2<<14) /* rs1 saves context */
-#define   RS1CONTSAV_FULL_RS1	(3<<14) /* rs1 saves and restores context */
-#define   NORMSLEXLAT_MASK	(3<<12)
-#define   SLOW_RS123		(0<<12)
-#define   SLOW_RS23		(1<<12)
-#define   SLOW_RS3		(2<<12)
-#define   NORMAL_RS123		(3<<12)
-#define   RCMODE_TIMEOUT	(1<<11) /* 0 is eval interval method */
-#define   IMPROMOEN		(1<<10) /* promo is immediate or delayed until next idle interval (only for timeout method above) */
-#define   RCENTSYNC		(1<<9) /* rs coupled to cpu c-state (3/6/7) */
-#define   STATELOCK		(1<<7) /* locked to rs_cstate if 0 */
-#define   RS_CSTATE_MASK	(3<<4)
-#define   RS_CSTATE_C367_RS1	(0<<4)
-#define   RS_CSTATE_C36_RS1_C7_RS2 (1<<4)
-#define   RS_CSTATE_RSVD	(2<<4)
-#define   RS_CSTATE_C367_RS2	(3<<4)
-#define   REDSAVES		(1<<3) /* no context save if was idle during rs0 */
-#define   REDRESTORES		(1<<2) /* no restore if was idle during rs0 */
+#define   RS1EN			(1 << 31)
+#define   RS2EN			(1 << 30)
+#define   RS3EN			(1 << 29)
+#define   D3RS3EN		(1 << 28) /* Display D3 imlies RS3 */
+#define   SWPROMORSX		(1 << 27) /* RSx promotion timers ignored */
+#define   RCWAKERW		(1 << 26) /* Resetwarn from PCH causes wakeup */
+#define   DPRSLPVREN		(1 << 25) /* Fast voltage ramp enable */
+#define   GFXTGHYST		(1 << 24) /* Hysteresis to allow trunk gating */
+#define   RCX_SW_EXIT		(1 << 23) /* Leave RSx and prevent re-entry */
+#define   RSX_STATUS_MASK	(7 << 20)
+#define   RSX_STATUS_ON		(0 << 20)
+#define   RSX_STATUS_RC1	(1 << 20)
+#define   RSX_STATUS_RC1E	(2 << 20)
+#define   RSX_STATUS_RS1	(3 << 20)
+#define   RSX_STATUS_RS2	(4 << 20) /* aka rc6 */
+#define   RSX_STATUS_RSVD	(5 << 20) /* deep rc6 unsupported on ilk */
+#define   RSX_STATUS_RS3	(6 << 20) /* rs3 unsupported on ilk */
+#define   RSX_STATUS_RSVD2	(7 << 20)
+#define   UWRCRSXE		(1 << 19) /* wake counter limit prevents rsx */
+#define   RSCRP			(1 << 18) /* rs requests control on rs1/2 reqs */
+#define   JRSC			(1 << 17) /* rsx coupled to cpu c-state */
+#define   RS2INC0		(1 << 16) /* allow rs2 in cpu c0 */
+#define   RS1CONTSAV_MASK	(3 << 14)
+#define   RS1CONTSAV_NO_RS1	(0 << 14) /* rs1 doesn't save/restore context */
+#define   RS1CONTSAV_RSVD	(1 << 14)
+#define   RS1CONTSAV_SAVE_RS1	(2 << 14) /* rs1 saves context */
+#define   RS1CONTSAV_FULL_RS1	(3 << 14) /* rs1 saves and restores context */
+#define   NORMSLEXLAT_MASK	(3 << 12)
+#define   SLOW_RS123		(0 << 12)
+#define   SLOW_RS23		(1 << 12)
+#define   SLOW_RS3		(2 << 12)
+#define   NORMAL_RS123		(3 << 12)
+#define   RCMODE_TIMEOUT	(1 << 11) /* 0 is eval interval method */
+#define   IMPROMOEN		(1 << 10) /* promo is immediate or delayed until next idle interval (only for timeout method above) */
+#define   RCENTSYNC		(1 << 9) /* rs coupled to cpu c-state (3/6/7) */
+#define   STATELOCK		(1 << 7) /* locked to rs_cstate if 0 */
+#define   RS_CSTATE_MASK	(3 << 4)
+#define   RS_CSTATE_C367_RS1	(0 << 4)
+#define   RS_CSTATE_C36_RS1_C7_RS2 (1 << 4)
+#define   RS_CSTATE_RSVD	(2 << 4)
+#define   RS_CSTATE_C367_RS2	(3 << 4)
+#define   REDSAVES		(1 << 3) /* no context save if was idle during rs0 */
+#define   REDRESTORES		(1 << 2) /* no restore if was idle during rs0 */
 #define VIDCTL			_MMIO(0x111c0)
 #define VIDSTS			_MMIO(0x111c8)
 #define VIDSTART		_MMIO(0x111cc) /* 8 bits */
@@ -3666,7 +3666,7 @@ enum i915_power_well_id {
 #define   MEMSTAT_VID_SHIFT	8
 #define   MEMSTAT_PSTATE_MASK	0x00f8
 #define   MEMSTAT_PSTATE_SHIFT  3
-#define   MEMSTAT_MON_ACTV	(1<<2)
+#define   MEMSTAT_MON_ACTV	(1 << 2)
 #define   MEMSTAT_SRC_CTL_MASK	0x0003
 #define   MEMSTAT_SRC_CTL_CORE	0
 #define   MEMSTAT_SRC_CTL_TRB	1
@@ -3675,7 +3675,7 @@ enum i915_power_well_id {
 #define RCPREVBSYTUPAVG		_MMIO(0x113b8)
 #define RCPREVBSYTDNAVG		_MMIO(0x113bc)
 #define PMMISC			_MMIO(0x11214)
-#define   MCPPCE_EN		(1<<0) /* enable PM_MSG from PCH->MPC */
+#define   MCPPCE_EN		(1 << 0) /* enable PM_MSG from PCH->MPC */
 #define SDEW			_MMIO(0x1124c)
 #define CSIEW0			_MMIO(0x11250)
 #define CSIEW1			_MMIO(0x11254)
@@ -3692,8 +3692,8 @@ enum i915_power_well_id {
 #define RPPREVBSYTUPAVG		_MMIO(0x113b8)
 #define RPPREVBSYTDNAVG		_MMIO(0x113bc)
 #define ECR			_MMIO(0x11600)
-#define   ECR_GPFE		(1<<31)
-#define   ECR_IMONE		(1<<30)
+#define   ECR_GPFE		(1 << 31)
+#define   ECR_IMONE		(1 << 30)
 #define   ECR_CAP_MASK		0x0000001f /* Event range, 0-31 */
 #define OGW0			_MMIO(0x11608)
 #define OGW1			_MMIO(0x1160c)
@@ -3800,11 +3800,11 @@ enum {
 	FAULT_AND_CONTINUE /* Unsupported */
 };
 
-#define GEN8_CTX_VALID (1<<0)
-#define GEN8_CTX_FORCE_PD_RESTORE (1<<1)
-#define GEN8_CTX_FORCE_RESTORE (1<<2)
-#define GEN8_CTX_L3LLC_COHERENT (1<<5)
-#define GEN8_CTX_PRIVILEGE (1<<8)
+#define GEN8_CTX_VALID (1 << 0)
+#define GEN8_CTX_FORCE_PD_RESTORE (1 << 1)
+#define GEN8_CTX_FORCE_RESTORE (1 << 2)
+#define GEN8_CTX_L3LLC_COHERENT (1 << 5)
+#define GEN8_CTX_PRIVILEGE (1 << 8)
 #define GEN8_CTX_ADDRESSING_MODE_SHIFT 3
 
 #define GEN8_CTX_ID_SHIFT 32
@@ -3826,7 +3826,7 @@ enum {
 
 #define OVADD			_MMIO(0x30000)
 #define DOVSTA			_MMIO(0x30008)
-#define OC_BUF			(0x3<<20)
+#define OC_BUF			(0x3 << 20)
 #define OGAMC5			_MMIO(0x30010)
 #define OGAMC4			_MMIO(0x30014)
 #define OGAMC3			_MMIO(0x30018)
@@ -3994,64 +3994,64 @@ enum {
 /* VLV eDP PSR registers */
 #define _PSRCTLA				(VLV_DISPLAY_BASE + 0x60090)
 #define _PSRCTLB				(VLV_DISPLAY_BASE + 0x61090)
-#define  VLV_EDP_PSR_ENABLE			(1<<0)
-#define  VLV_EDP_PSR_RESET			(1<<1)
-#define  VLV_EDP_PSR_MODE_MASK			(7<<2)
-#define  VLV_EDP_PSR_MODE_HW_TIMER		(1<<3)
-#define  VLV_EDP_PSR_MODE_SW_TIMER		(1<<2)
-#define  VLV_EDP_PSR_SINGLE_FRAME_UPDATE	(1<<7)
-#define  VLV_EDP_PSR_ACTIVE_ENTRY		(1<<8)
-#define  VLV_EDP_PSR_SRC_TRANSMITTER_STATE	(1<<9)
-#define  VLV_EDP_PSR_DBL_FRAME			(1<<10)
-#define  VLV_EDP_PSR_FRAME_COUNT_MASK		(0xff<<16)
+#define  VLV_EDP_PSR_ENABLE			(1 << 0)
+#define  VLV_EDP_PSR_RESET			(1 << 1)
+#define  VLV_EDP_PSR_MODE_MASK			(7 << 2)
+#define  VLV_EDP_PSR_MODE_HW_TIMER		(1 << 3)
+#define  VLV_EDP_PSR_MODE_SW_TIMER		(1 << 2)
+#define  VLV_EDP_PSR_SINGLE_FRAME_UPDATE	(1 << 7)
+#define  VLV_EDP_PSR_ACTIVE_ENTRY		(1 << 8)
+#define  VLV_EDP_PSR_SRC_TRANSMITTER_STATE	(1 << 9)
+#define  VLV_EDP_PSR_DBL_FRAME			(1 << 10)
+#define  VLV_EDP_PSR_FRAME_COUNT_MASK		(0xff << 16)
 #define  VLV_EDP_PSR_IDLE_FRAME_SHIFT		16
 #define VLV_PSRCTL(pipe)	_MMIO_PIPE(pipe, _PSRCTLA, _PSRCTLB)
 
 #define _VSCSDPA			(VLV_DISPLAY_BASE + 0x600a0)
 #define _VSCSDPB			(VLV_DISPLAY_BASE + 0x610a0)
-#define  VLV_EDP_PSR_SDP_FREQ_MASK	(3<<30)
-#define  VLV_EDP_PSR_SDP_FREQ_ONCE	(1<<31)
-#define  VLV_EDP_PSR_SDP_FREQ_EVFRAME	(1<<30)
+#define  VLV_EDP_PSR_SDP_FREQ_MASK	(3 << 30)
+#define  VLV_EDP_PSR_SDP_FREQ_ONCE	(1 << 31)
+#define  VLV_EDP_PSR_SDP_FREQ_EVFRAME	(1 << 30)
 #define VLV_VSCSDP(pipe)	_MMIO_PIPE(pipe, _VSCSDPA, _VSCSDPB)
 
 #define _PSRSTATA			(VLV_DISPLAY_BASE + 0x60094)
 #define _PSRSTATB			(VLV_DISPLAY_BASE + 0x61094)
-#define  VLV_EDP_PSR_LAST_STATE_MASK	(7<<3)
+#define  VLV_EDP_PSR_LAST_STATE_MASK	(7 << 3)
 #define  VLV_EDP_PSR_CURR_STATE_MASK	7
-#define  VLV_EDP_PSR_DISABLED		(0<<0)
-#define  VLV_EDP_PSR_INACTIVE		(1<<0)
-#define  VLV_EDP_PSR_IN_TRANS_TO_ACTIVE	(2<<0)
-#define  VLV_EDP_PSR_ACTIVE_NORFB_UP	(3<<0)
-#define  VLV_EDP_PSR_ACTIVE_SF_UPDATE	(4<<0)
-#define  VLV_EDP_PSR_EXIT		(5<<0)
-#define  VLV_EDP_PSR_IN_TRANS		(1<<7)
+#define  VLV_EDP_PSR_DISABLED		(0 << 0)
+#define  VLV_EDP_PSR_INACTIVE		(1 << 0)
+#define  VLV_EDP_PSR_IN_TRANS_TO_ACTIVE	(2 << 0)
+#define  VLV_EDP_PSR_ACTIVE_NORFB_UP	(3 << 0)
+#define  VLV_EDP_PSR_ACTIVE_SF_UPDATE	(4 << 0)
+#define  VLV_EDP_PSR_EXIT		(5 << 0)
+#define  VLV_EDP_PSR_IN_TRANS		(1 << 7)
 #define VLV_PSRSTAT(pipe)	_MMIO_PIPE(pipe, _PSRSTATA, _PSRSTATB)
 
 /* HSW+ eDP PSR registers */
 #define HSW_EDP_PSR_BASE	0x64800
 #define BDW_EDP_PSR_BASE	0x6f800
 #define EDP_PSR_CTL				_MMIO(dev_priv->psr_mmio_base + 0)
-#define   EDP_PSR_ENABLE			(1<<31)
-#define   BDW_PSR_SINGLE_FRAME			(1<<30)
-#define   EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK	(1<<29) /* SW can't modify */
-#define   EDP_PSR_LINK_STANDBY			(1<<27)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_MASK	(3<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES	(0<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_4_LINES	(1<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_2_LINES	(2<<25)
-#define   EDP_PSR_MIN_LINK_ENTRY_TIME_0_LINES	(3<<25)
+#define   EDP_PSR_ENABLE			(1 << 31)
+#define   BDW_PSR_SINGLE_FRAME			(1 << 30)
+#define   EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK	(1 << 29) /* SW can't modify */
+#define   EDP_PSR_LINK_STANDBY			(1 << 27)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_MASK	(3 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_8_LINES	(0 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_4_LINES	(1 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_2_LINES	(2 << 25)
+#define   EDP_PSR_MIN_LINK_ENTRY_TIME_0_LINES	(3 << 25)
 #define   EDP_PSR_MAX_SLEEP_TIME_SHIFT		20
-#define   EDP_PSR_SKIP_AUX_EXIT			(1<<12)
-#define   EDP_PSR_TP1_TP2_SEL			(0<<11)
-#define   EDP_PSR_TP1_TP3_SEL			(1<<11)
-#define   EDP_PSR_TP2_TP3_TIME_500us		(0<<8)
-#define   EDP_PSR_TP2_TP3_TIME_100us		(1<<8)
-#define   EDP_PSR_TP2_TP3_TIME_2500us		(2<<8)
-#define   EDP_PSR_TP2_TP3_TIME_0us		(3<<8)
-#define   EDP_PSR_TP1_TIME_500us		(0<<4)
-#define   EDP_PSR_TP1_TIME_100us		(1<<4)
-#define   EDP_PSR_TP1_TIME_2500us		(2<<4)
-#define   EDP_PSR_TP1_TIME_0us			(3<<4)
+#define   EDP_PSR_SKIP_AUX_EXIT			(1 << 12)
+#define   EDP_PSR_TP1_TP2_SEL			(0 << 11)
+#define   EDP_PSR_TP1_TP3_SEL			(1 << 11)
+#define   EDP_PSR_TP2_TP3_TIME_500us		(0 << 8)
+#define   EDP_PSR_TP2_TP3_TIME_100us		(1 << 8)
+#define   EDP_PSR_TP2_TP3_TIME_2500us		(2 << 8)
+#define   EDP_PSR_TP2_TP3_TIME_0us		(3 << 8)
+#define   EDP_PSR_TP1_TIME_500us		(0 << 4)
+#define   EDP_PSR_TP1_TIME_100us		(1 << 4)
+#define   EDP_PSR_TP1_TIME_2500us		(2 << 4)
+#define   EDP_PSR_TP1_TIME_0us			(3 << 4)
 #define   EDP_PSR_IDLE_FRAME_SHIFT		0
 
 /* Bspec claims those aren't shifted but stay at 0x64800 */
@@ -4071,55 +4071,55 @@ enum {
 #define EDP_PSR_AUX_DATA(i)			_MMIO(dev_priv->psr_mmio_base + 0x14 + (i) * 4) /* 5 registers */
 
 #define EDP_PSR_STATUS				_MMIO(dev_priv->psr_mmio_base + 0x40)
-#define   EDP_PSR_STATUS_STATE_MASK		(7<<29)
-#define   EDP_PSR_STATUS_STATE_IDLE		(0<<29)
-#define   EDP_PSR_STATUS_STATE_SRDONACK		(1<<29)
-#define   EDP_PSR_STATUS_STATE_SRDENT		(2<<29)
-#define   EDP_PSR_STATUS_STATE_BUFOFF		(3<<29)
-#define   EDP_PSR_STATUS_STATE_BUFON		(4<<29)
-#define   EDP_PSR_STATUS_STATE_AUXACK		(5<<29)
-#define   EDP_PSR_STATUS_STATE_SRDOFFACK	(6<<29)
-#define   EDP_PSR_STATUS_LINK_MASK		(3<<26)
-#define   EDP_PSR_STATUS_LINK_FULL_OFF		(0<<26)
-#define   EDP_PSR_STATUS_LINK_FULL_ON		(1<<26)
-#define   EDP_PSR_STATUS_LINK_STANDBY		(2<<26)
+#define   EDP_PSR_STATUS_STATE_MASK		(7 << 29)
+#define   EDP_PSR_STATUS_STATE_IDLE		(0 << 29)
+#define   EDP_PSR_STATUS_STATE_SRDONACK		(1 << 29)
+#define   EDP_PSR_STATUS_STATE_SRDENT		(2 << 29)
+#define   EDP_PSR_STATUS_STATE_BUFOFF		(3 << 29)
+#define   EDP_PSR_STATUS_STATE_BUFON		(4 << 29)
+#define   EDP_PSR_STATUS_STATE_AUXACK		(5 << 29)
+#define   EDP_PSR_STATUS_STATE_SRDOFFACK	(6 << 29)
+#define   EDP_PSR_STATUS_LINK_MASK		(3 << 26)
+#define   EDP_PSR_STATUS_LINK_FULL_OFF		(0 << 26)
+#define   EDP_PSR_STATUS_LINK_FULL_ON		(1 << 26)
+#define   EDP_PSR_STATUS_LINK_STANDBY		(2 << 26)
 #define   EDP_PSR_STATUS_MAX_SLEEP_TIMER_SHIFT	20
 #define   EDP_PSR_STATUS_MAX_SLEEP_TIMER_MASK	0x1f
 #define   EDP_PSR_STATUS_COUNT_SHIFT		16
 #define   EDP_PSR_STATUS_COUNT_MASK		0xf
-#define   EDP_PSR_STATUS_AUX_ERROR		(1<<15)
-#define   EDP_PSR_STATUS_AUX_SENDING		(1<<12)
-#define   EDP_PSR_STATUS_SENDING_IDLE		(1<<9)
-#define   EDP_PSR_STATUS_SENDING_TP2_TP3	(1<<8)
-#define   EDP_PSR_STATUS_SENDING_TP1		(1<<4)
+#define   EDP_PSR_STATUS_AUX_ERROR		(1 << 15)
+#define   EDP_PSR_STATUS_AUX_SENDING		(1 << 12)
+#define   EDP_PSR_STATUS_SENDING_IDLE		(1 << 9)
+#define   EDP_PSR_STATUS_SENDING_TP2_TP3	(1 << 8)
+#define   EDP_PSR_STATUS_SENDING_TP1		(1 << 4)
 #define   EDP_PSR_STATUS_IDLE_MASK		0xf
 
 #define EDP_PSR_PERF_CNT		_MMIO(dev_priv->psr_mmio_base + 0x44)
 #define   EDP_PSR_PERF_CNT_MASK		0xffffff
 
 #define EDP_PSR_DEBUG				_MMIO(dev_priv->psr_mmio_base + 0x60) /* PSR_MASK on SKL+ */
-#define   EDP_PSR_DEBUG_MASK_MAX_SLEEP         (1<<28)
-#define   EDP_PSR_DEBUG_MASK_LPSP              (1<<27)
-#define   EDP_PSR_DEBUG_MASK_MEMUP             (1<<26)
-#define   EDP_PSR_DEBUG_MASK_HPD               (1<<25)
-#define   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE    (1<<16)
-#define   EDP_PSR_DEBUG_EXIT_ON_PIXEL_UNDERRUN (1<<15) /* SKL+ */
+#define   EDP_PSR_DEBUG_MASK_MAX_SLEEP         (1 << 28)
+#define   EDP_PSR_DEBUG_MASK_LPSP              (1 << 27)
+#define   EDP_PSR_DEBUG_MASK_MEMUP             (1 << 26)
+#define   EDP_PSR_DEBUG_MASK_HPD               (1 << 25)
+#define   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE    (1 << 16)
+#define   EDP_PSR_DEBUG_EXIT_ON_PIXEL_UNDERRUN (1 << 15) /* SKL+ */
 
 #define EDP_PSR2_CTL			_MMIO(0x6f900)
-#define   EDP_PSR2_ENABLE		(1<<31)
-#define   EDP_SU_TRACK_ENABLE		(1<<30)
-#define   EDP_Y_COORDINATE_VALID	(1<<26) /* GLK and CNL+ */
-#define   EDP_Y_COORDINATE_ENABLE	(1<<25) /* GLK and CNL+ */
-#define   EDP_MAX_SU_DISABLE_TIME(t)	((t)<<20)
-#define   EDP_MAX_SU_DISABLE_TIME_MASK	(0x1f<<20)
-#define   EDP_PSR2_TP2_TIME_500us	(0<<8)
-#define   EDP_PSR2_TP2_TIME_100us	(1<<8)
-#define   EDP_PSR2_TP2_TIME_2500us	(2<<8)
-#define   EDP_PSR2_TP2_TIME_50us	(3<<8)
-#define   EDP_PSR2_TP2_TIME_MASK	(3<<8)
+#define   EDP_PSR2_ENABLE		(1 << 31)
+#define   EDP_SU_TRACK_ENABLE		(1 << 30)
+#define   EDP_Y_COORDINATE_VALID	(1 << 26) /* GLK and CNL+ */
+#define   EDP_Y_COORDINATE_ENABLE	(1 << 25) /* GLK and CNL+ */
+#define   EDP_MAX_SU_DISABLE_TIME(t)	((t) << 20)
+#define   EDP_MAX_SU_DISABLE_TIME_MASK	(0x1f << 20)
+#define   EDP_PSR2_TP2_TIME_500us	(0 << 8)
+#define   EDP_PSR2_TP2_TIME_100us	(1 << 8)
+#define   EDP_PSR2_TP2_TIME_2500us	(2 << 8)
+#define   EDP_PSR2_TP2_TIME_50us	(3 << 8)
+#define   EDP_PSR2_TP2_TIME_MASK	(3 << 8)
 #define   EDP_PSR2_FRAME_BEFORE_SU_SHIFT 4
-#define   EDP_PSR2_FRAME_BEFORE_SU_MASK	(0xf<<4)
-#define   EDP_PSR2_FRAME_BEFORE_SU(a)	((a)<<4)
+#define   EDP_PSR2_FRAME_BEFORE_SU_MASK	(0xf << 4)
+#define   EDP_PSR2_FRAME_BEFORE_SU(a)	((a) << 4)
 #define   EDP_PSR2_IDLE_FRAME_MASK	0xf
 #define   EDP_PSR2_IDLE_FRAME_SHIFT	0
 
@@ -4147,7 +4147,7 @@ enum {
 #define  PSR_EVENT_PSR_DISABLE			(1 << 0)
 
 #define EDP_PSR2_STATUS			_MMIO(0x6f940)
-#define EDP_PSR2_STATUS_STATE_MASK     (0xf<<28)
+#define EDP_PSR2_STATUS_STATE_MASK     (0xf << 28)
 #define EDP_PSR2_STATUS_STATE_SHIFT    28
 
 /* VGA port control */
@@ -4155,48 +4155,48 @@ enum {
 #define PCH_ADPA                _MMIO(0xe1100)
 #define VLV_ADPA		_MMIO(VLV_DISPLAY_BASE + 0x61100)
 
-#define   ADPA_DAC_ENABLE	(1<<31)
+#define   ADPA_DAC_ENABLE	(1 << 31)
 #define   ADPA_DAC_DISABLE	0
 #define   ADPA_PIPE_SEL_SHIFT		30
-#define   ADPA_PIPE_SEL_MASK		(1<<30)
+#define   ADPA_PIPE_SEL_MASK		(1 << 30)
 #define   ADPA_PIPE_SEL(pipe)		((pipe) << 30)
 #define   ADPA_PIPE_SEL_SHIFT_CPT	29
-#define   ADPA_PIPE_SEL_MASK_CPT	(3<<29)
+#define   ADPA_PIPE_SEL_MASK_CPT	(3 << 29)
 #define   ADPA_PIPE_SEL_CPT(pipe)	((pipe) << 29)
 #define   ADPA_CRT_HOTPLUG_MASK  0x03ff0000 /* bit 25-16 */
-#define   ADPA_CRT_HOTPLUG_MONITOR_NONE  (0<<24)
-#define   ADPA_CRT_HOTPLUG_MONITOR_MASK  (3<<24)
-#define   ADPA_CRT_HOTPLUG_MONITOR_COLOR (3<<24)
-#define   ADPA_CRT_HOTPLUG_MONITOR_MONO  (2<<24)
-#define   ADPA_CRT_HOTPLUG_ENABLE        (1<<23)
-#define   ADPA_CRT_HOTPLUG_PERIOD_64     (0<<22)
-#define   ADPA_CRT_HOTPLUG_PERIOD_128    (1<<22)
-#define   ADPA_CRT_HOTPLUG_WARMUP_5MS    (0<<21)
-#define   ADPA_CRT_HOTPLUG_WARMUP_10MS   (1<<21)
-#define   ADPA_CRT_HOTPLUG_SAMPLE_2S     (0<<20)
-#define   ADPA_CRT_HOTPLUG_SAMPLE_4S     (1<<20)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_40    (0<<18)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_50    (1<<18)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_60    (2<<18)
-#define   ADPA_CRT_HOTPLUG_VOLTAGE_70    (3<<18)
-#define   ADPA_CRT_HOTPLUG_VOLREF_325MV  (0<<17)
-#define   ADPA_CRT_HOTPLUG_VOLREF_475MV  (1<<17)
-#define   ADPA_CRT_HOTPLUG_FORCE_TRIGGER (1<<16)
-#define   ADPA_USE_VGA_HVPOLARITY (1<<15)
+#define   ADPA_CRT_HOTPLUG_MONITOR_NONE  (0 << 24)
+#define   ADPA_CRT_HOTPLUG_MONITOR_MASK  (3 << 24)
+#define   ADPA_CRT_HOTPLUG_MONITOR_COLOR (3 << 24)
+#define   ADPA_CRT_HOTPLUG_MONITOR_MONO  (2 << 24)
+#define   ADPA_CRT_HOTPLUG_ENABLE        (1 << 23)
+#define   ADPA_CRT_HOTPLUG_PERIOD_64     (0 << 22)
+#define   ADPA_CRT_HOTPLUG_PERIOD_128    (1 << 22)
+#define   ADPA_CRT_HOTPLUG_WARMUP_5MS    (0 << 21)
+#define   ADPA_CRT_HOTPLUG_WARMUP_10MS   (1 << 21)
+#define   ADPA_CRT_HOTPLUG_SAMPLE_2S     (0 << 20)
+#define   ADPA_CRT_HOTPLUG_SAMPLE_4S     (1 << 20)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_40    (0 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_50    (1 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_60    (2 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLTAGE_70    (3 << 18)
+#define   ADPA_CRT_HOTPLUG_VOLREF_325MV  (0 << 17)
+#define   ADPA_CRT_HOTPLUG_VOLREF_475MV  (1 << 17)
+#define   ADPA_CRT_HOTPLUG_FORCE_TRIGGER (1 << 16)
+#define   ADPA_USE_VGA_HVPOLARITY (1 << 15)
 #define   ADPA_SETS_HVPOLARITY	0
-#define   ADPA_VSYNC_CNTL_DISABLE (1<<10)
+#define   ADPA_VSYNC_CNTL_DISABLE (1 << 10)
 #define   ADPA_VSYNC_CNTL_ENABLE 0
-#define   ADPA_HSYNC_CNTL_DISABLE (1<<11)
+#define   ADPA_HSYNC_CNTL_DISABLE (1 << 11)
 #define   ADPA_HSYNC_CNTL_ENABLE 0
-#define   ADPA_VSYNC_ACTIVE_HIGH (1<<4)
+#define   ADPA_VSYNC_ACTIVE_HIGH (1 << 4)
 #define   ADPA_VSYNC_ACTIVE_LOW	0
-#define   ADPA_HSYNC_ACTIVE_HIGH (1<<3)
+#define   ADPA_HSYNC_ACTIVE_HIGH (1 << 3)
 #define   ADPA_HSYNC_ACTIVE_LOW	0
-#define   ADPA_DPMS_MASK	(~(3<<10))
-#define   ADPA_DPMS_ON		(0<<10)
-#define   ADPA_DPMS_SUSPEND	(1<<10)
-#define   ADPA_DPMS_STANDBY	(2<<10)
-#define   ADPA_DPMS_OFF		(3<<10)
+#define   ADPA_DPMS_MASK	(~(3 << 10))
+#define   ADPA_DPMS_ON		(0 << 10)
+#define   ADPA_DPMS_SUSPEND	(1 << 10)
+#define   ADPA_DPMS_STANDBY	(2 << 10)
+#define   ADPA_DPMS_OFF		(3 << 10)
 
 
 /* Hotplug control (945+ only) */
@@ -4405,7 +4405,7 @@ enum {
 #define   DVO_BLANK_ACTIVE_HIGH		(1 << 2)
 #define   DVO_OUTPUT_CSTATE_PIXELS	(1 << 1)	/* SDG only */
 #define   DVO_OUTPUT_SOURCE_SIZE_PIXELS	(1 << 0)	/* SDG only */
-#define   DVO_PRESERVE_MASK		(0x7<<24)
+#define   DVO_PRESERVE_MASK		(0x7 << 24)
 #define DVOA_SRCDIM		_MMIO(0x61124)
 #define DVOB_SRCDIM		_MMIO(0x61144)
 #define DVOC_SRCDIM		_MMIO(0x61164)
@@ -5383,7 +5383,7 @@ enum {
 #define _PIPEB_DATA_M_G4X	0x71050
 
 /* Transfer unit size for display port - 1, default is 0x3f (for TU size 64) */
-#define  TU_SIZE(x)             (((x)-1) << 25) /* default size 64 */
+#define  TU_SIZE(x)             (((x) - 1) << 25) /* default size 64 */
 #define  TU_SIZE_SHIFT		25
 #define  TU_SIZE_MASK           (0x3f << 25)
 
@@ -5425,18 +5425,18 @@ enum {
 #define   DSL_LINEMASK_GEN2	0x00000fff
 #define   DSL_LINEMASK_GEN3	0x00001fff
 #define _PIPEACONF		0x70008
-#define   PIPECONF_ENABLE	(1<<31)
+#define   PIPECONF_ENABLE	(1 << 31)
 #define   PIPECONF_DISABLE	0
-#define   PIPECONF_DOUBLE_WIDE	(1<<30)
-#define   I965_PIPECONF_ACTIVE	(1<<30)
-#define   PIPECONF_DSI_PLL_LOCKED	(1<<29) /* vlv & pipe A only */
-#define   PIPECONF_FRAME_START_DELAY_MASK (3<<27)
+#define   PIPECONF_DOUBLE_WIDE	(1 << 30)
+#define   I965_PIPECONF_ACTIVE	(1 << 30)
+#define   PIPECONF_DSI_PLL_LOCKED	(1 << 29) /* vlv & pipe A only */
+#define   PIPECONF_FRAME_START_DELAY_MASK (3 << 27)
 #define   PIPECONF_SINGLE_WIDE	0
 #define   PIPECONF_PIPE_UNLOCKED 0
-#define   PIPECONF_PIPE_LOCKED	(1<<25)
+#define   PIPECONF_PIPE_LOCKED	(1 << 25)
 #define   PIPECONF_PALETTE	0
-#define   PIPECONF_GAMMA		(1<<24)
-#define   PIPECONF_FORCE_BORDER	(1<<25)
+#define   PIPECONF_GAMMA		(1 << 24)
+#define   PIPECONF_FORCE_BORDER	(1 << 25)
 #define   PIPECONF_INTERLACE_MASK	(7 << 21)
 #define   PIPECONF_INTERLACE_MASK_HSW	(3 << 21)
 /* Note that pre-gen3 does not support interlaced display directly. Panel
@@ -5455,67 +5455,67 @@ enum {
 #define   PIPECONF_PFIT_PF_INTERLACED_DBL_ILK	(5 << 21) /* ilk/snb only */
 #define   PIPECONF_INTERLACE_MODE_MASK		(7 << 21)
 #define   PIPECONF_EDP_RR_MODE_SWITCH		(1 << 20)
-#define   PIPECONF_CXSR_DOWNCLOCK	(1<<16)
+#define   PIPECONF_CXSR_DOWNCLOCK	(1 << 16)
 #define   PIPECONF_EDP_RR_MODE_SWITCH_VLV	(1 << 14)
 #define   PIPECONF_COLOR_RANGE_SELECT	(1 << 13)
 #define   PIPECONF_BPC_MASK	(0x7 << 5)
-#define   PIPECONF_8BPC		(0<<5)
-#define   PIPECONF_10BPC	(1<<5)
-#define   PIPECONF_6BPC		(2<<5)
-#define   PIPECONF_12BPC	(3<<5)
-#define   PIPECONF_DITHER_EN	(1<<4)
+#define   PIPECONF_8BPC		(0 << 5)
+#define   PIPECONF_10BPC	(1 << 5)
+#define   PIPECONF_6BPC		(2 << 5)
+#define   PIPECONF_12BPC	(3 << 5)
+#define   PIPECONF_DITHER_EN	(1 << 4)
 #define   PIPECONF_DITHER_TYPE_MASK (0x0000000c)
-#define   PIPECONF_DITHER_TYPE_SP (0<<2)
-#define   PIPECONF_DITHER_TYPE_ST1 (1<<2)
-#define   PIPECONF_DITHER_TYPE_ST2 (2<<2)
-#define   PIPECONF_DITHER_TYPE_TEMP (3<<2)
+#define   PIPECONF_DITHER_TYPE_SP (0 << 2)
+#define   PIPECONF_DITHER_TYPE_ST1 (1 << 2)
+#define   PIPECONF_DITHER_TYPE_ST2 (2 << 2)
+#define   PIPECONF_DITHER_TYPE_TEMP (3 << 2)
 #define _PIPEASTAT		0x70024
-#define   PIPE_FIFO_UNDERRUN_STATUS		(1UL<<31)
-#define   SPRITE1_FLIP_DONE_INT_EN_VLV		(1UL<<30)
-#define   PIPE_CRC_ERROR_ENABLE			(1UL<<29)
-#define   PIPE_CRC_DONE_ENABLE			(1UL<<28)
-#define   PERF_COUNTER2_INTERRUPT_EN		(1UL<<27)
-#define   PIPE_GMBUS_EVENT_ENABLE		(1UL<<27)
-#define   PLANE_FLIP_DONE_INT_EN_VLV		(1UL<<26)
-#define   PIPE_HOTPLUG_INTERRUPT_ENABLE		(1UL<<26)
-#define   PIPE_VSYNC_INTERRUPT_ENABLE		(1UL<<25)
-#define   PIPE_DISPLAY_LINE_COMPARE_ENABLE	(1UL<<24)
-#define   PIPE_DPST_EVENT_ENABLE		(1UL<<23)
-#define   SPRITE0_FLIP_DONE_INT_EN_VLV		(1UL<<22)
-#define   PIPE_LEGACY_BLC_EVENT_ENABLE		(1UL<<22)
-#define   PIPE_ODD_FIELD_INTERRUPT_ENABLE	(1UL<<21)
-#define   PIPE_EVEN_FIELD_INTERRUPT_ENABLE	(1UL<<20)
-#define   PIPE_B_PSR_INTERRUPT_ENABLE_VLV	(1UL<<19)
-#define   PERF_COUNTER_INTERRUPT_EN		(1UL<<19)
-#define   PIPE_HOTPLUG_TV_INTERRUPT_ENABLE	(1UL<<18) /* pre-965 */
-#define   PIPE_START_VBLANK_INTERRUPT_ENABLE	(1UL<<18) /* 965 or later */
-#define   PIPE_FRAMESTART_INTERRUPT_ENABLE	(1UL<<17)
-#define   PIPE_VBLANK_INTERRUPT_ENABLE		(1UL<<17)
-#define   PIPEA_HBLANK_INT_EN_VLV		(1UL<<16)
-#define   PIPE_OVERLAY_UPDATED_ENABLE		(1UL<<16)
-#define   SPRITE1_FLIP_DONE_INT_STATUS_VLV	(1UL<<15)
-#define   SPRITE0_FLIP_DONE_INT_STATUS_VLV	(1UL<<14)
-#define   PIPE_CRC_ERROR_INTERRUPT_STATUS	(1UL<<13)
-#define   PIPE_CRC_DONE_INTERRUPT_STATUS	(1UL<<12)
-#define   PERF_COUNTER2_INTERRUPT_STATUS	(1UL<<11)
-#define   PIPE_GMBUS_INTERRUPT_STATUS		(1UL<<11)
-#define   PLANE_FLIP_DONE_INT_STATUS_VLV	(1UL<<10)
-#define   PIPE_HOTPLUG_INTERRUPT_STATUS		(1UL<<10)
-#define   PIPE_VSYNC_INTERRUPT_STATUS		(1UL<<9)
-#define   PIPE_DISPLAY_LINE_COMPARE_STATUS	(1UL<<8)
-#define   PIPE_DPST_EVENT_STATUS		(1UL<<7)
-#define   PIPE_A_PSR_STATUS_VLV			(1UL<<6)
-#define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL<<6)
-#define   PIPE_ODD_FIELD_INTERRUPT_STATUS	(1UL<<5)
-#define   PIPE_EVEN_FIELD_INTERRUPT_STATUS	(1UL<<4)
-#define   PIPE_B_PSR_STATUS_VLV			(1UL<<3)
-#define   PERF_COUNTER_INTERRUPT_STATUS		(1UL<<3)
-#define   PIPE_HOTPLUG_TV_INTERRUPT_STATUS	(1UL<<2) /* pre-965 */
-#define   PIPE_START_VBLANK_INTERRUPT_STATUS	(1UL<<2) /* 965 or later */
-#define   PIPE_FRAMESTART_INTERRUPT_STATUS	(1UL<<1)
-#define   PIPE_VBLANK_INTERRUPT_STATUS		(1UL<<1)
-#define   PIPE_HBLANK_INT_STATUS		(1UL<<0)
-#define   PIPE_OVERLAY_UPDATED_STATUS		(1UL<<0)
+#define   PIPE_FIFO_UNDERRUN_STATUS		(1UL << 31)
+#define   SPRITE1_FLIP_DONE_INT_EN_VLV		(1UL << 30)
+#define   PIPE_CRC_ERROR_ENABLE			(1UL << 29)
+#define   PIPE_CRC_DONE_ENABLE			(1UL << 28)
+#define   PERF_COUNTER2_INTERRUPT_EN		(1UL << 27)
+#define   PIPE_GMBUS_EVENT_ENABLE		(1UL << 27)
+#define   PLANE_FLIP_DONE_INT_EN_VLV		(1UL << 26)
+#define   PIPE_HOTPLUG_INTERRUPT_ENABLE		(1UL << 26)
+#define   PIPE_VSYNC_INTERRUPT_ENABLE		(1UL << 25)
+#define   PIPE_DISPLAY_LINE_COMPARE_ENABLE	(1UL << 24)
+#define   PIPE_DPST_EVENT_ENABLE		(1UL << 23)
+#define   SPRITE0_FLIP_DONE_INT_EN_VLV		(1UL << 22)
+#define   PIPE_LEGACY_BLC_EVENT_ENABLE		(1UL << 22)
+#define   PIPE_ODD_FIELD_INTERRUPT_ENABLE	(1UL << 21)
+#define   PIPE_EVEN_FIELD_INTERRUPT_ENABLE	(1UL << 20)
+#define   PIPE_B_PSR_INTERRUPT_ENABLE_VLV	(1UL << 19)
+#define   PERF_COUNTER_INTERRUPT_EN		(1UL << 19)
+#define   PIPE_HOTPLUG_TV_INTERRUPT_ENABLE	(1UL << 18) /* pre-965 */
+#define   PIPE_START_VBLANK_INTERRUPT_ENABLE	(1UL << 18) /* 965 or later */
+#define   PIPE_FRAMESTART_INTERRUPT_ENABLE	(1UL << 17)
+#define   PIPE_VBLANK_INTERRUPT_ENABLE		(1UL << 17)
+#define   PIPEA_HBLANK_INT_EN_VLV		(1UL << 16)
+#define   PIPE_OVERLAY_UPDATED_ENABLE		(1UL << 16)
+#define   SPRITE1_FLIP_DONE_INT_STATUS_VLV	(1UL << 15)
+#define   SPRITE0_FLIP_DONE_INT_STATUS_VLV	(1UL << 14)
+#define   PIPE_CRC_ERROR_INTERRUPT_STATUS	(1UL << 13)
+#define   PIPE_CRC_DONE_INTERRUPT_STATUS	(1UL << 12)
+#define   PERF_COUNTER2_INTERRUPT_STATUS	(1UL << 11)
+#define   PIPE_GMBUS_INTERRUPT_STATUS		(1UL << 11)
+#define   PLANE_FLIP_DONE_INT_STATUS_VLV	(1UL << 10)
+#define   PIPE_HOTPLUG_INTERRUPT_STATUS		(1UL << 10)
+#define   PIPE_VSYNC_INTERRUPT_STATUS		(1UL << 9)
+#define   PIPE_DISPLAY_LINE_COMPARE_STATUS	(1UL << 8)
+#define   PIPE_DPST_EVENT_STATUS		(1UL << 7)
+#define   PIPE_A_PSR_STATUS_VLV			(1UL << 6)
+#define   PIPE_LEGACY_BLC_EVENT_STATUS		(1UL << 6)
+#define   PIPE_ODD_FIELD_INTERRUPT_STATUS	(1UL << 5)
+#define   PIPE_EVEN_FIELD_INTERRUPT_STATUS	(1UL << 4)
+#define   PIPE_B_PSR_STATUS_VLV			(1UL << 3)
+#define   PERF_COUNTER_INTERRUPT_STATUS		(1UL << 3)
+#define   PIPE_HOTPLUG_TV_INTERRUPT_STATUS	(1UL << 2) /* pre-965 */
+#define   PIPE_START_VBLANK_INTERRUPT_STATUS	(1UL << 2) /* 965 or later */
+#define   PIPE_FRAMESTART_INTERRUPT_STATUS	(1UL << 1)
+#define   PIPE_VBLANK_INTERRUPT_STATUS		(1UL << 1)
+#define   PIPE_HBLANK_INT_STATUS		(1UL << 0)
+#define   PIPE_OVERLAY_UPDATED_STATUS		(1UL << 0)
 
 #define PIPESTAT_INT_ENABLE_MASK		0x7fff0000
 #define PIPESTAT_INT_STATUS_MASK		0x0000ffff
@@ -5544,67 +5544,67 @@ enum {
 
 #define _PIPE_MISC_A			0x70030
 #define _PIPE_MISC_B			0x71030
-#define   PIPEMISC_YUV420_ENABLE	(1<<27)
-#define   PIPEMISC_YUV420_MODE_FULL_BLEND (1<<26)
-#define   PIPEMISC_OUTPUT_COLORSPACE_YUV  (1<<11)
-#define   PIPEMISC_DITHER_BPC_MASK	(7<<5)
-#define   PIPEMISC_DITHER_8_BPC		(0<<5)
-#define   PIPEMISC_DITHER_10_BPC	(1<<5)
-#define   PIPEMISC_DITHER_6_BPC		(2<<5)
-#define   PIPEMISC_DITHER_12_BPC	(3<<5)
-#define   PIPEMISC_DITHER_ENABLE	(1<<4)
-#define   PIPEMISC_DITHER_TYPE_MASK	(3<<2)
-#define   PIPEMISC_DITHER_TYPE_SP	(0<<2)
+#define   PIPEMISC_YUV420_ENABLE	(1 << 27)
+#define   PIPEMISC_YUV420_MODE_FULL_BLEND (1 << 26)
+#define   PIPEMISC_OUTPUT_COLORSPACE_YUV  (1 << 11)
+#define   PIPEMISC_DITHER_BPC_MASK	(7 << 5)
+#define   PIPEMISC_DITHER_8_BPC		(0 << 5)
+#define   PIPEMISC_DITHER_10_BPC	(1 << 5)
+#define   PIPEMISC_DITHER_6_BPC		(2 << 5)
+#define   PIPEMISC_DITHER_12_BPC	(3 << 5)
+#define   PIPEMISC_DITHER_ENABLE	(1 << 4)
+#define   PIPEMISC_DITHER_TYPE_MASK	(3 << 2)
+#define   PIPEMISC_DITHER_TYPE_SP	(0 << 2)
 #define PIPEMISC(pipe)			_MMIO_PIPE2(pipe, _PIPE_MISC_A)
 
 #define VLV_DPFLIPSTAT				_MMIO(VLV_DISPLAY_BASE + 0x70028)
-#define   PIPEB_LINE_COMPARE_INT_EN		(1<<29)
-#define   PIPEB_HLINE_INT_EN			(1<<28)
-#define   PIPEB_VBLANK_INT_EN			(1<<27)
-#define   SPRITED_FLIP_DONE_INT_EN		(1<<26)
-#define   SPRITEC_FLIP_DONE_INT_EN		(1<<25)
-#define   PLANEB_FLIP_DONE_INT_EN		(1<<24)
-#define   PIPE_PSR_INT_EN			(1<<22)
-#define   PIPEA_LINE_COMPARE_INT_EN		(1<<21)
-#define   PIPEA_HLINE_INT_EN			(1<<20)
-#define   PIPEA_VBLANK_INT_EN			(1<<19)
-#define   SPRITEB_FLIP_DONE_INT_EN		(1<<18)
-#define   SPRITEA_FLIP_DONE_INT_EN		(1<<17)
-#define   PLANEA_FLIPDONE_INT_EN		(1<<16)
-#define   PIPEC_LINE_COMPARE_INT_EN		(1<<13)
-#define   PIPEC_HLINE_INT_EN			(1<<12)
-#define   PIPEC_VBLANK_INT_EN			(1<<11)
-#define   SPRITEF_FLIPDONE_INT_EN		(1<<10)
-#define   SPRITEE_FLIPDONE_INT_EN		(1<<9)
-#define   PLANEC_FLIPDONE_INT_EN		(1<<8)
+#define   PIPEB_LINE_COMPARE_INT_EN		(1 << 29)
+#define   PIPEB_HLINE_INT_EN			(1 << 28)
+#define   PIPEB_VBLANK_INT_EN			(1 << 27)
+#define   SPRITED_FLIP_DONE_INT_EN		(1 << 26)
+#define   SPRITEC_FLIP_DONE_INT_EN		(1 << 25)
+#define   PLANEB_FLIP_DONE_INT_EN		(1 << 24)
+#define   PIPE_PSR_INT_EN			(1 << 22)
+#define   PIPEA_LINE_COMPARE_INT_EN		(1 << 21)
+#define   PIPEA_HLINE_INT_EN			(1 << 20)
+#define   PIPEA_VBLANK_INT_EN			(1 << 19)
+#define   SPRITEB_FLIP_DONE_INT_EN		(1 << 18)
+#define   SPRITEA_FLIP_DONE_INT_EN		(1 << 17)
+#define   PLANEA_FLIPDONE_INT_EN		(1 << 16)
+#define   PIPEC_LINE_COMPARE_INT_EN		(1 << 13)
+#define   PIPEC_HLINE_INT_EN			(1 << 12)
+#define   PIPEC_VBLANK_INT_EN			(1 << 11)
+#define   SPRITEF_FLIPDONE_INT_EN		(1 << 10)
+#define   SPRITEE_FLIPDONE_INT_EN		(1 << 9)
+#define   PLANEC_FLIPDONE_INT_EN		(1 << 8)
 
 #define DPINVGTT				_MMIO(VLV_DISPLAY_BASE + 0x7002c) /* VLV/CHV only */
-#define   SPRITEF_INVALID_GTT_INT_EN		(1<<27)
-#define   SPRITEE_INVALID_GTT_INT_EN		(1<<26)
-#define   PLANEC_INVALID_GTT_INT_EN		(1<<25)
-#define   CURSORC_INVALID_GTT_INT_EN		(1<<24)
-#define   CURSORB_INVALID_GTT_INT_EN		(1<<23)
-#define   CURSORA_INVALID_GTT_INT_EN		(1<<22)
-#define   SPRITED_INVALID_GTT_INT_EN		(1<<21)
-#define   SPRITEC_INVALID_GTT_INT_EN		(1<<20)
-#define   PLANEB_INVALID_GTT_INT_EN		(1<<19)
-#define   SPRITEB_INVALID_GTT_INT_EN		(1<<18)
-#define   SPRITEA_INVALID_GTT_INT_EN		(1<<17)
-#define   PLANEA_INVALID_GTT_INT_EN		(1<<16)
+#define   SPRITEF_INVALID_GTT_INT_EN		(1 << 27)
+#define   SPRITEE_INVALID_GTT_INT_EN		(1 << 26)
+#define   PLANEC_INVALID_GTT_INT_EN		(1 << 25)
+#define   CURSORC_INVALID_GTT_INT_EN		(1 << 24)
+#define   CURSORB_INVALID_GTT_INT_EN		(1 << 23)
+#define   CURSORA_INVALID_GTT_INT_EN		(1 << 22)
+#define   SPRITED_INVALID_GTT_INT_EN		(1 << 21)
+#define   SPRITEC_INVALID_GTT_INT_EN		(1 << 20)
+#define   PLANEB_INVALID_GTT_INT_EN		(1 << 19)
+#define   SPRITEB_INVALID_GTT_INT_EN		(1 << 18)
+#define   SPRITEA_INVALID_GTT_INT_EN		(1 << 17)
+#define   PLANEA_INVALID_GTT_INT_EN		(1 << 16)
 #define   DPINVGTT_EN_MASK			0xff0000
 #define   DPINVGTT_EN_MASK_CHV			0xfff0000
-#define   SPRITEF_INVALID_GTT_STATUS		(1<<11)
-#define   SPRITEE_INVALID_GTT_STATUS		(1<<10)
-#define   PLANEC_INVALID_GTT_STATUS		(1<<9)
-#define   CURSORC_INVALID_GTT_STATUS		(1<<8)
-#define   CURSORB_INVALID_GTT_STATUS		(1<<7)
-#define   CURSORA_INVALID_GTT_STATUS		(1<<6)
-#define   SPRITED_INVALID_GTT_STATUS		(1<<5)
-#define   SPRITEC_INVALID_GTT_STATUS		(1<<4)
-#define   PLANEB_INVALID_GTT_STATUS		(1<<3)
-#define   SPRITEB_INVALID_GTT_STATUS		(1<<2)
-#define   SPRITEA_INVALID_GTT_STATUS		(1<<1)
-#define   PLANEA_INVALID_GTT_STATUS		(1<<0)
+#define   SPRITEF_INVALID_GTT_STATUS		(1 << 11)
+#define   SPRITEE_INVALID_GTT_STATUS		(1 << 10)
+#define   PLANEC_INVALID_GTT_STATUS		(1 << 9)
+#define   CURSORC_INVALID_GTT_STATUS		(1 << 8)
+#define   CURSORB_INVALID_GTT_STATUS		(1 << 7)
+#define   CURSORA_INVALID_GTT_STATUS		(1 << 6)
+#define   SPRITED_INVALID_GTT_STATUS		(1 << 5)
+#define   SPRITEC_INVALID_GTT_STATUS		(1 << 4)
+#define   PLANEB_INVALID_GTT_STATUS		(1 << 3)
+#define   SPRITEB_INVALID_GTT_STATUS		(1 << 2)
+#define   SPRITEA_INVALID_GTT_STATUS		(1 << 1)
+#define   PLANEA_INVALID_GTT_STATUS		(1 << 0)
 #define   DPINVGTT_STATUS_MASK			0xff
 #define   DPINVGTT_STATUS_MASK_CHV		0xfff
 
@@ -5645,149 +5645,149 @@ enum {
 /* pnv/gen4/g4x/vlv/chv */
 #define DSPFW1		_MMIO(dev_priv->info.display_mmio_offset + 0x70034)
 #define   DSPFW_SR_SHIFT		23
-#define   DSPFW_SR_MASK			(0x1ff<<23)
+#define   DSPFW_SR_MASK			(0x1ff << 23)
 #define   DSPFW_CURSORB_SHIFT		16
-#define   DSPFW_CURSORB_MASK		(0x3f<<16)
+#define   DSPFW_CURSORB_MASK		(0x3f << 16)
 #define   DSPFW_PLANEB_SHIFT		8
-#define   DSPFW_PLANEB_MASK		(0x7f<<8)
-#define   DSPFW_PLANEB_MASK_VLV		(0xff<<8) /* vlv/chv */
+#define   DSPFW_PLANEB_MASK		(0x7f << 8)
+#define   DSPFW_PLANEB_MASK_VLV		(0xff << 8) /* vlv/chv */
 #define   DSPFW_PLANEA_SHIFT		0
-#define   DSPFW_PLANEA_MASK		(0x7f<<0)
-#define   DSPFW_PLANEA_MASK_VLV		(0xff<<0) /* vlv/chv */
+#define   DSPFW_PLANEA_MASK		(0x7f << 0)
+#define   DSPFW_PLANEA_MASK_VLV		(0xff << 0) /* vlv/chv */
 #define DSPFW2		_MMIO(dev_priv->info.display_mmio_offset + 0x70038)
-#define   DSPFW_FBC_SR_EN		(1<<31)	  /* g4x */
+#define   DSPFW_FBC_SR_EN		(1 << 31)	  /* g4x */
 #define   DSPFW_FBC_SR_SHIFT		28
-#define   DSPFW_FBC_SR_MASK		(0x7<<28) /* g4x */
+#define   DSPFW_FBC_SR_MASK		(0x7 << 28) /* g4x */
 #define   DSPFW_FBC_HPLL_SR_SHIFT	24
-#define   DSPFW_FBC_HPLL_SR_MASK	(0xf<<24) /* g4x */
+#define   DSPFW_FBC_HPLL_SR_MASK	(0xf << 24) /* g4x */
 #define   DSPFW_SPRITEB_SHIFT		(16)
-#define   DSPFW_SPRITEB_MASK		(0x7f<<16) /* g4x */
-#define   DSPFW_SPRITEB_MASK_VLV	(0xff<<16) /* vlv/chv */
+#define   DSPFW_SPRITEB_MASK		(0x7f << 16) /* g4x */
+#define   DSPFW_SPRITEB_MASK_VLV	(0xff << 16) /* vlv/chv */
 #define   DSPFW_CURSORA_SHIFT		8
-#define   DSPFW_CURSORA_MASK		(0x3f<<8)
+#define   DSPFW_CURSORA_MASK		(0x3f << 8)
 #define   DSPFW_PLANEC_OLD_SHIFT	0
-#define   DSPFW_PLANEC_OLD_MASK		(0x7f<<0) /* pre-gen4 sprite C */
+#define   DSPFW_PLANEC_OLD_MASK		(0x7f << 0) /* pre-gen4 sprite C */
 #define   DSPFW_SPRITEA_SHIFT		0
-#define   DSPFW_SPRITEA_MASK		(0x7f<<0) /* g4x */
-#define   DSPFW_SPRITEA_MASK_VLV	(0xff<<0) /* vlv/chv */
+#define   DSPFW_SPRITEA_MASK		(0x7f << 0) /* g4x */
+#define   DSPFW_SPRITEA_MASK_VLV	(0xff << 0) /* vlv/chv */
 #define DSPFW3		_MMIO(dev_priv->info.display_mmio_offset + 0x7003c)
-#define   DSPFW_HPLL_SR_EN		(1<<31)
-#define   PINEVIEW_SELF_REFRESH_EN	(1<<30)
+#define   DSPFW_HPLL_SR_EN		(1 << 31)
+#define   PINEVIEW_SELF_REFRESH_EN	(1 << 30)
 #define   DSPFW_CURSOR_SR_SHIFT		24
-#define   DSPFW_CURSOR_SR_MASK		(0x3f<<24)
+#define   DSPFW_CURSOR_SR_MASK		(0x3f << 24)
 #define   DSPFW_HPLL_CURSOR_SHIFT	16
-#define   DSPFW_HPLL_CURSOR_MASK	(0x3f<<16)
+#define   DSPFW_HPLL_CURSOR_MASK	(0x3f << 16)
 #define   DSPFW_HPLL_SR_SHIFT		0
-#define   DSPFW_HPLL_SR_MASK		(0x1ff<<0)
+#define   DSPFW_HPLL_SR_MASK		(0x1ff << 0)
 
 /* vlv/chv */
 #define DSPFW4		_MMIO(VLV_DISPLAY_BASE + 0x70070)
 #define   DSPFW_SPRITEB_WM1_SHIFT	16
-#define   DSPFW_SPRITEB_WM1_MASK	(0xff<<16)
+#define   DSPFW_SPRITEB_WM1_MASK	(0xff << 16)
 #define   DSPFW_CURSORA_WM1_SHIFT	8
-#define   DSPFW_CURSORA_WM1_MASK	(0x3f<<8)
+#define   DSPFW_CURSORA_WM1_MASK	(0x3f << 8)
 #define   DSPFW_SPRITEA_WM1_SHIFT	0
-#define   DSPFW_SPRITEA_WM1_MASK	(0xff<<0)
+#define   DSPFW_SPRITEA_WM1_MASK	(0xff << 0)
 #define DSPFW5		_MMIO(VLV_DISPLAY_BASE + 0x70074)
 #define   DSPFW_PLANEB_WM1_SHIFT	24
-#define   DSPFW_PLANEB_WM1_MASK		(0xff<<24)
+#define   DSPFW_PLANEB_WM1_MASK		(0xff << 24)
 #define   DSPFW_PLANEA_WM1_SHIFT	16
-#define   DSPFW_PLANEA_WM1_MASK		(0xff<<16)
+#define   DSPFW_PLANEA_WM1_MASK		(0xff << 16)
 #define   DSPFW_CURSORB_WM1_SHIFT	8
-#define   DSPFW_CURSORB_WM1_MASK	(0x3f<<8)
+#define   DSPFW_CURSORB_WM1_MASK	(0x3f << 8)
 #define   DSPFW_CURSOR_SR_WM1_SHIFT	0
-#define   DSPFW_CURSOR_SR_WM1_MASK	(0x3f<<0)
+#define   DSPFW_CURSOR_SR_WM1_MASK	(0x3f << 0)
 #define DSPFW6		_MMIO(VLV_DISPLAY_BASE + 0x70078)
 #define   DSPFW_SR_WM1_SHIFT		0
-#define   DSPFW_SR_WM1_MASK		(0x1ff<<0)
+#define   DSPFW_SR_WM1_MASK		(0x1ff << 0)
 #define DSPFW7		_MMIO(VLV_DISPLAY_BASE + 0x7007c)
 #define DSPFW7_CHV	_MMIO(VLV_DISPLAY_BASE + 0x700b4) /* wtf #1? */
 #define   DSPFW_SPRITED_WM1_SHIFT	24
-#define   DSPFW_SPRITED_WM1_MASK	(0xff<<24)
+#define   DSPFW_SPRITED_WM1_MASK	(0xff << 24)
 #define   DSPFW_SPRITED_SHIFT		16
-#define   DSPFW_SPRITED_MASK_VLV	(0xff<<16)
+#define   DSPFW_SPRITED_MASK_VLV	(0xff << 16)
 #define   DSPFW_SPRITEC_WM1_SHIFT	8
-#define   DSPFW_SPRITEC_WM1_MASK	(0xff<<8)
+#define   DSPFW_SPRITEC_WM1_MASK	(0xff << 8)
 #define   DSPFW_SPRITEC_SHIFT		0
-#define   DSPFW_SPRITEC_MASK_VLV	(0xff<<0)
+#define   DSPFW_SPRITEC_MASK_VLV	(0xff << 0)
 #define DSPFW8_CHV	_MMIO(VLV_DISPLAY_BASE + 0x700b8)
 #define   DSPFW_SPRITEF_WM1_SHIFT	24
-#define   DSPFW_SPRITEF_WM1_MASK	(0xff<<24)
+#define   DSPFW_SPRITEF_WM1_MASK	(0xff << 24)
 #define   DSPFW_SPRITEF_SHIFT		16
-#define   DSPFW_SPRITEF_MASK_VLV	(0xff<<16)
+#define   DSPFW_SPRITEF_MASK_VLV	(0xff << 16)
 #define   DSPFW_SPRITEE_WM1_SHIFT	8
-#define   DSPFW_SPRITEE_WM1_MASK	(0xff<<8)
+#define   DSPFW_SPRITEE_WM1_MASK	(0xff << 8)
 #define   DSPFW_SPRITEE_SHIFT		0
-#define   DSPFW_SPRITEE_MASK_VLV	(0xff<<0)
+#define   DSPFW_SPRITEE_MASK_VLV	(0xff << 0)
 #define DSPFW9_CHV	_MMIO(VLV_DISPLAY_BASE + 0x7007c) /* wtf #2? */
 #define   DSPFW_PLANEC_WM1_SHIFT	24
-#define   DSPFW_PLANEC_WM1_MASK		(0xff<<24)
+#define   DSPFW_PLANEC_WM1_MASK		(0xff << 24)
 #define   DSPFW_PLANEC_SHIFT		16
-#define   DSPFW_PLANEC_MASK_VLV		(0xff<<16)
+#define   DSPFW_PLANEC_MASK_VLV		(0xff << 16)
 #define   DSPFW_CURSORC_WM1_SHIFT	8
-#define   DSPFW_CURSORC_WM1_MASK	(0x3f<<16)
+#define   DSPFW_CURSORC_WM1_MASK	(0x3f << 16)
 #define   DSPFW_CURSORC_SHIFT		0
-#define   DSPFW_CURSORC_MASK		(0x3f<<0)
+#define   DSPFW_CURSORC_MASK		(0x3f << 0)
 
 /* vlv/chv high order bits */
 #define DSPHOWM		_MMIO(VLV_DISPLAY_BASE + 0x70064)
 #define   DSPFW_SR_HI_SHIFT		24
-#define   DSPFW_SR_HI_MASK		(3<<24) /* 2 bits for chv, 1 for vlv */
+#define   DSPFW_SR_HI_MASK		(3 << 24) /* 2 bits for chv, 1 for vlv */
 #define   DSPFW_SPRITEF_HI_SHIFT	23
-#define   DSPFW_SPRITEF_HI_MASK		(1<<23)
+#define   DSPFW_SPRITEF_HI_MASK		(1 << 23)
 #define   DSPFW_SPRITEE_HI_SHIFT	22
-#define   DSPFW_SPRITEE_HI_MASK		(1<<22)
+#define   DSPFW_SPRITEE_HI_MASK		(1 << 22)
 #define   DSPFW_PLANEC_HI_SHIFT		21
-#define   DSPFW_PLANEC_HI_MASK		(1<<21)
+#define   DSPFW_PLANEC_HI_MASK		(1 << 21)
 #define   DSPFW_SPRITED_HI_SHIFT	20
-#define   DSPFW_SPRITED_HI_MASK		(1<<20)
+#define   DSPFW_SPRITED_HI_MASK		(1 << 20)
 #define   DSPFW_SPRITEC_HI_SHIFT	16
-#define   DSPFW_SPRITEC_HI_MASK		(1<<16)
+#define   DSPFW_SPRITEC_HI_MASK		(1 << 16)
 #define   DSPFW_PLANEB_HI_SHIFT		12
-#define   DSPFW_PLANEB_HI_MASK		(1<<12)
+#define   DSPFW_PLANEB_HI_MASK		(1 << 12)
 #define   DSPFW_SPRITEB_HI_SHIFT	8
-#define   DSPFW_SPRITEB_HI_MASK		(1<<8)
+#define   DSPFW_SPRITEB_HI_MASK		(1 << 8)
 #define   DSPFW_SPRITEA_HI_SHIFT	4
-#define   DSPFW_SPRITEA_HI_MASK		(1<<4)
+#define   DSPFW_SPRITEA_HI_MASK		(1 << 4)
 #define   DSPFW_PLANEA_HI_SHIFT		0
-#define   DSPFW_PLANEA_HI_MASK		(1<<0)
+#define   DSPFW_PLANEA_HI_MASK		(1 << 0)
 #define DSPHOWM1	_MMIO(VLV_DISPLAY_BASE + 0x70068)
 #define   DSPFW_SR_WM1_HI_SHIFT		24
-#define   DSPFW_SR_WM1_HI_MASK		(3<<24) /* 2 bits for chv, 1 for vlv */
+#define   DSPFW_SR_WM1_HI_MASK		(3 << 24) /* 2 bits for chv, 1 for vlv */
 #define   DSPFW_SPRITEF_WM1_HI_SHIFT	23
-#define   DSPFW_SPRITEF_WM1_HI_MASK	(1<<23)
+#define   DSPFW_SPRITEF_WM1_HI_MASK	(1 << 23)
 #define   DSPFW_SPRITEE_WM1_HI_SHIFT	22
-#define   DSPFW_SPRITEE_WM1_HI_MASK	(1<<22)
+#define   DSPFW_SPRITEE_WM1_HI_MASK	(1 << 22)
 #define   DSPFW_PLANEC_WM1_HI_SHIFT	21
-#define   DSPFW_PLANEC_WM1_HI_MASK	(1<<21)
+#define   DSPFW_PLANEC_WM1_HI_MASK	(1 << 21)
 #define   DSPFW_SPRITED_WM1_HI_SHIFT	20
-#define   DSPFW_SPRITED_WM1_HI_MASK	(1<<20)
+#define   DSPFW_SPRITED_WM1_HI_MASK	(1 << 20)
 #define   DSPFW_SPRITEC_WM1_HI_SHIFT	16
-#define   DSPFW_SPRITEC_WM1_HI_MASK	(1<<16)
+#define   DSPFW_SPRITEC_WM1_HI_MASK	(1 << 16)
 #define   DSPFW_PLANEB_WM1_HI_SHIFT	12
-#define   DSPFW_PLANEB_WM1_HI_MASK	(1<<12)
+#define   DSPFW_PLANEB_WM1_HI_MASK	(1 << 12)
 #define   DSPFW_SPRITEB_WM1_HI_SHIFT	8
-#define   DSPFW_SPRITEB_WM1_HI_MASK	(1<<8)
+#define   DSPFW_SPRITEB_WM1_HI_MASK	(1 << 8)
 #define   DSPFW_SPRITEA_WM1_HI_SHIFT	4
-#define   DSPFW_SPRITEA_WM1_HI_MASK	(1<<4)
+#define   DSPFW_SPRITEA_WM1_HI_MASK	(1 << 4)
 #define   DSPFW_PLANEA_WM1_HI_SHIFT	0
-#define   DSPFW_PLANEA_WM1_HI_MASK	(1<<0)
+#define   DSPFW_PLANEA_WM1_HI_MASK	(1 << 0)
 
 /* drain latency register values*/
 #define VLV_DDL(pipe)			_MMIO(VLV_DISPLAY_BASE + 0x70050 + 4 * (pipe))
 #define DDL_CURSOR_SHIFT		24
-#define DDL_SPRITE_SHIFT(sprite)	(8+8*(sprite))
+#define DDL_SPRITE_SHIFT(sprite)	(8 + 8 * (sprite))
 #define DDL_PLANE_SHIFT			0
-#define DDL_PRECISION_HIGH		(1<<7)
-#define DDL_PRECISION_LOW		(0<<7)
+#define DDL_PRECISION_HIGH		(1 << 7)
+#define DDL_PRECISION_LOW		(0 << 7)
 #define DRAIN_LATENCY_MASK		0x7f
 
 #define CBR1_VLV			_MMIO(VLV_DISPLAY_BASE + 0x70400)
-#define  CBR_PND_DEADLINE_DISABLE	(1<<31)
-#define  CBR_PWM_CLOCK_MUX_SELECT	(1<<30)
+#define  CBR_PND_DEADLINE_DISABLE	(1 << 31)
+#define  CBR_PWM_CLOCK_MUX_SELECT	(1 << 30)
 
 #define CBR4_VLV			_MMIO(VLV_DISPLAY_BASE + 0x70450)
-#define  CBR_DPLLBMD_PIPE(pipe)		(1<<(7+(pipe)*11)) /* pipes B and C */
+#define  CBR_DPLLBMD_PIPE(pipe)		(1 << (7 + (pipe) * 11)) /* pipes B and C */
 
 /* FIFO watermark sizes etc */
 #define G4X_FIFO_LINE_SIZE	64
@@ -5859,32 +5859,32 @@ enum {
 
 /* define the Watermark register on Ironlake */
 #define WM0_PIPEA_ILK		_MMIO(0x45100)
-#define  WM0_PIPE_PLANE_MASK	(0xffff<<16)
+#define  WM0_PIPE_PLANE_MASK	(0xffff << 16)
 #define  WM0_PIPE_PLANE_SHIFT	16
-#define  WM0_PIPE_SPRITE_MASK	(0xff<<8)
+#define  WM0_PIPE_SPRITE_MASK	(0xff << 8)
 #define  WM0_PIPE_SPRITE_SHIFT	8
 #define  WM0_PIPE_CURSOR_MASK	(0xff)
 
 #define WM0_PIPEB_ILK		_MMIO(0x45104)
 #define WM0_PIPEC_IVB		_MMIO(0x45200)
 #define WM1_LP_ILK		_MMIO(0x45108)
-#define  WM1_LP_SR_EN		(1<<31)
+#define  WM1_LP_SR_EN		(1 << 31)
 #define  WM1_LP_LATENCY_SHIFT	24
-#define  WM1_LP_LATENCY_MASK	(0x7f<<24)
-#define  WM1_LP_FBC_MASK	(0xf<<20)
+#define  WM1_LP_LATENCY_MASK	(0x7f << 24)
+#define  WM1_LP_FBC_MASK	(0xf << 20)
 #define  WM1_LP_FBC_SHIFT	20
 #define  WM1_LP_FBC_SHIFT_BDW	19
-#define  WM1_LP_SR_MASK		(0x7ff<<8)
+#define  WM1_LP_SR_MASK		(0x7ff << 8)
 #define  WM1_LP_SR_SHIFT	8
 #define  WM1_LP_CURSOR_MASK	(0xff)
 #define WM2_LP_ILK		_MMIO(0x4510c)
-#define  WM2_LP_EN		(1<<31)
+#define  WM2_LP_EN		(1 << 31)
 #define WM3_LP_ILK		_MMIO(0x45110)
-#define  WM3_LP_EN		(1<<31)
+#define  WM3_LP_EN		(1 << 31)
 #define WM1S_LP_ILK		_MMIO(0x45120)
 #define WM2S_LP_IVB		_MMIO(0x45124)
 #define WM3S_LP_IVB		_MMIO(0x45128)
-#define  WM1S_LP_EN		(1<<31)
+#define  WM1S_LP_EN		(1 << 31)
 
 #define HSW_WM_LP_VAL(lat, fbc, pri, cur) \
 	(WM3_LP_EN | ((lat) << WM1_LP_LATENCY_SHIFT) | \
@@ -5941,7 +5941,7 @@ enum {
 #define   CURSOR_ENABLE		0x80000000
 #define   CURSOR_GAMMA_ENABLE	0x40000000
 #define   CURSOR_STRIDE_SHIFT	28
-#define   CURSOR_STRIDE(x)	((ffs(x)-9) << CURSOR_STRIDE_SHIFT) /* 256,512,1k,2k */
+#define   CURSOR_STRIDE(x)	((ffs(x) - 9) << CURSOR_STRIDE_SHIFT) /* 256,512,1k,2k */
 #define   CURSOR_FORMAT_SHIFT	24
 #define   CURSOR_FORMAT_MASK	(0x07 << CURSOR_FORMAT_SHIFT)
 #define   CURSOR_FORMAT_2C	(0x00 << CURSOR_FORMAT_SHIFT)
@@ -5962,8 +5962,8 @@ enum {
 #define   MCURSOR_PIPE_SELECT_SHIFT	28
 #define   MCURSOR_PIPE_SELECT(pipe)	((pipe) << 28)
 #define   MCURSOR_GAMMA_ENABLE  (1 << 26)
-#define   MCURSOR_PIPE_CSC_ENABLE (1<<24)
-#define   MCURSOR_ROTATE_180	(1<<15)
+#define   MCURSOR_PIPE_CSC_ENABLE (1 << 24)
+#define   MCURSOR_ROTATE_180	(1 << 15)
 #define   MCURSOR_TRICKLE_FEED_DISABLE	(1 << 14)
 #define _CURABASE		0x70084
 #define _CURAPOS		0x70088
@@ -6001,41 +6001,41 @@ enum {
 
 /* Display A control */
 #define _DSPACNTR				0x70180
-#define   DISPLAY_PLANE_ENABLE			(1<<31)
+#define   DISPLAY_PLANE_ENABLE			(1 << 31)
 #define   DISPLAY_PLANE_DISABLE			0
-#define   DISPPLANE_GAMMA_ENABLE		(1<<30)
+#define   DISPPLANE_GAMMA_ENABLE		(1 << 30)
 #define   DISPPLANE_GAMMA_DISABLE		0
-#define   DISPPLANE_PIXFORMAT_MASK		(0xf<<26)
-#define   DISPPLANE_YUV422			(0x0<<26)
-#define   DISPPLANE_8BPP			(0x2<<26)
-#define   DISPPLANE_BGRA555			(0x3<<26)
-#define   DISPPLANE_BGRX555			(0x4<<26)
-#define   DISPPLANE_BGRX565			(0x5<<26)
-#define   DISPPLANE_BGRX888			(0x6<<26)
-#define   DISPPLANE_BGRA888			(0x7<<26)
-#define   DISPPLANE_RGBX101010			(0x8<<26)
-#define   DISPPLANE_RGBA101010			(0x9<<26)
-#define   DISPPLANE_BGRX101010			(0xa<<26)
-#define   DISPPLANE_RGBX161616			(0xc<<26)
-#define   DISPPLANE_RGBX888			(0xe<<26)
-#define   DISPPLANE_RGBA888			(0xf<<26)
-#define   DISPPLANE_STEREO_ENABLE		(1<<25)
+#define   DISPPLANE_PIXFORMAT_MASK		(0xf << 26)
+#define   DISPPLANE_YUV422			(0x0 << 26)
+#define   DISPPLANE_8BPP			(0x2 << 26)
+#define   DISPPLANE_BGRA555			(0x3 << 26)
+#define   DISPPLANE_BGRX555			(0x4 << 26)
+#define   DISPPLANE_BGRX565			(0x5 << 26)
+#define   DISPPLANE_BGRX888			(0x6 << 26)
+#define   DISPPLANE_BGRA888			(0x7 << 26)
+#define   DISPPLANE_RGBX101010			(0x8 << 26)
+#define   DISPPLANE_RGBA101010			(0x9 << 26)
+#define   DISPPLANE_BGRX101010			(0xa << 26)
+#define   DISPPLANE_RGBX161616			(0xc << 26)
+#define   DISPPLANE_RGBX888			(0xe << 26)
+#define   DISPPLANE_RGBA888			(0xf << 26)
+#define   DISPPLANE_STEREO_ENABLE		(1 << 25)
 #define   DISPPLANE_STEREO_DISABLE		0
-#define   DISPPLANE_PIPE_CSC_ENABLE		(1<<24)
+#define   DISPPLANE_PIPE_CSC_ENABLE		(1 << 24)
 #define   DISPPLANE_SEL_PIPE_SHIFT		24
-#define   DISPPLANE_SEL_PIPE_MASK		(3<<DISPPLANE_SEL_PIPE_SHIFT)
-#define   DISPPLANE_SEL_PIPE(pipe)		((pipe)<<DISPPLANE_SEL_PIPE_SHIFT)
-#define   DISPPLANE_SRC_KEY_ENABLE		(1<<22)
+#define   DISPPLANE_SEL_PIPE_MASK		(3 << DISPPLANE_SEL_PIPE_SHIFT)
+#define   DISPPLANE_SEL_PIPE(pipe)		((pipe) << DISPPLANE_SEL_PIPE_SHIFT)
+#define   DISPPLANE_SRC_KEY_ENABLE		(1 << 22)
 #define   DISPPLANE_SRC_KEY_DISABLE		0
-#define   DISPPLANE_LINE_DOUBLE			(1<<20)
+#define   DISPPLANE_LINE_DOUBLE			(1 << 20)
 #define   DISPPLANE_NO_LINE_DOUBLE		0
 #define   DISPPLANE_STEREO_POLARITY_FIRST	0
-#define   DISPPLANE_STEREO_POLARITY_SECOND	(1<<18)
-#define   DISPPLANE_ALPHA_PREMULTIPLY		(1<<16) /* CHV pipe B */
-#define   DISPPLANE_ROTATE_180			(1<<15)
-#define   DISPPLANE_TRICKLE_FEED_DISABLE	(1<<14) /* Ironlake */
-#define   DISPPLANE_TILED			(1<<10)
-#define   DISPPLANE_MIRROR			(1<<8) /* CHV pipe B */
+#define   DISPPLANE_STEREO_POLARITY_SECOND	(1 << 18)
+#define   DISPPLANE_ALPHA_PREMULTIPLY		(1 << 16) /* CHV pipe B */
+#define   DISPPLANE_ROTATE_180			(1 << 15)
+#define   DISPPLANE_TRICKLE_FEED_DISABLE	(1 << 14) /* Ironlake */
+#define   DISPPLANE_TILED			(1 << 10)
+#define   DISPPLANE_MIRROR			(1 << 8) /* CHV pipe B */
 #define _DSPAADDR				0x70184
 #define _DSPASTRIDE				0x70188
 #define _DSPAPOS				0x7018C /* reserved */
@@ -6058,15 +6058,15 @@ enum {
 
 /* CHV pipe B blender and primary plane */
 #define _CHV_BLEND_A		0x60a00
-#define   CHV_BLEND_LEGACY		(0<<30)
-#define   CHV_BLEND_ANDROID		(1<<30)
-#define   CHV_BLEND_MPO			(2<<30)
-#define   CHV_BLEND_MASK		(3<<30)
+#define   CHV_BLEND_LEGACY		(0 << 30)
+#define   CHV_BLEND_ANDROID		(1 << 30)
+#define   CHV_BLEND_MPO			(2 << 30)
+#define   CHV_BLEND_MASK		(3 << 30)
 #define _CHV_CANVAS_A		0x60a04
 #define _PRIMPOS_A		0x60a08
 #define _PRIMSIZE_A		0x60a0c
 #define _PRIMCNSTALPHA_A	0x60a10
-#define   PRIM_CONST_ALPHA_ENABLE	(1<<31)
+#define   PRIM_CONST_ALPHA_ENABLE	(1 << 31)
 
 #define CHV_BLEND(pipe)		_MMIO_TRANS2(pipe, _CHV_BLEND_A)
 #define CHV_CANVAS(pipe)	_MMIO_TRANS2(pipe, _CHV_CANVAS_A)
@@ -6107,7 +6107,7 @@ enum {
 
 /* Display B control */
 #define _DSPBCNTR		(dev_priv->info.display_mmio_offset + 0x71180)
-#define   DISPPLANE_ALPHA_TRANS_ENABLE		(1<<15)
+#define   DISPPLANE_ALPHA_TRANS_ENABLE		(1 << 15)
 #define   DISPPLANE_ALPHA_TRANS_DISABLE		0
 #define   DISPPLANE_SPRITE_ABOVE_DISPLAY	0
 #define   DISPPLANE_SPRITE_ABOVE_OVERLAY	(1)
@@ -6122,27 +6122,27 @@ enum {
 
 /* Sprite A control */
 #define _DVSACNTR		0x72180
-#define   DVS_ENABLE		(1<<31)
-#define   DVS_GAMMA_ENABLE	(1<<30)
-#define   DVS_YUV_RANGE_CORRECTION_DISABLE	(1<<27)
-#define   DVS_PIXFORMAT_MASK	(3<<25)
-#define   DVS_FORMAT_YUV422	(0<<25)
-#define   DVS_FORMAT_RGBX101010	(1<<25)
-#define   DVS_FORMAT_RGBX888	(2<<25)
-#define   DVS_FORMAT_RGBX161616	(3<<25)
-#define   DVS_PIPE_CSC_ENABLE   (1<<24)
-#define   DVS_SOURCE_KEY	(1<<22)
-#define   DVS_RGB_ORDER_XBGR	(1<<20)
-#define   DVS_YUV_FORMAT_BT709	(1<<18)
-#define   DVS_YUV_BYTE_ORDER_MASK (3<<16)
-#define   DVS_YUV_ORDER_YUYV	(0<<16)
-#define   DVS_YUV_ORDER_UYVY	(1<<16)
-#define   DVS_YUV_ORDER_YVYU	(2<<16)
-#define   DVS_YUV_ORDER_VYUY	(3<<16)
-#define   DVS_ROTATE_180	(1<<15)
-#define   DVS_DEST_KEY		(1<<2)
-#define   DVS_TRICKLE_FEED_DISABLE (1<<14)
-#define   DVS_TILED		(1<<10)
+#define   DVS_ENABLE		(1 << 31)
+#define   DVS_GAMMA_ENABLE	(1 << 30)
+#define   DVS_YUV_RANGE_CORRECTION_DISABLE	(1 << 27)
+#define   DVS_PIXFORMAT_MASK	(3 << 25)
+#define   DVS_FORMAT_YUV422	(0 << 25)
+#define   DVS_FORMAT_RGBX101010	(1 << 25)
+#define   DVS_FORMAT_RGBX888	(2 << 25)
+#define   DVS_FORMAT_RGBX161616	(3 << 25)
+#define   DVS_PIPE_CSC_ENABLE   (1 << 24)
+#define   DVS_SOURCE_KEY	(1 << 22)
+#define   DVS_RGB_ORDER_XBGR	(1 << 20)
+#define   DVS_YUV_FORMAT_BT709	(1 << 18)
+#define   DVS_YUV_BYTE_ORDER_MASK (3 << 16)
+#define   DVS_YUV_ORDER_YUYV	(0 << 16)
+#define   DVS_YUV_ORDER_UYVY	(1 << 16)
+#define   DVS_YUV_ORDER_YVYU	(2 << 16)
+#define   DVS_YUV_ORDER_VYUY	(3 << 16)
+#define   DVS_ROTATE_180	(1 << 15)
+#define   DVS_DEST_KEY		(1 << 2)
+#define   DVS_TRICKLE_FEED_DISABLE (1 << 14)
+#define   DVS_TILED		(1 << 10)
 #define _DVSALINOFF		0x72184
 #define _DVSASTRIDE		0x72188
 #define _DVSAPOS		0x7218c
@@ -6154,13 +6154,13 @@ enum {
 #define _DVSATILEOFF		0x721a4
 #define _DVSASURFLIVE		0x721ac
 #define _DVSASCALE		0x72204
-#define   DVS_SCALE_ENABLE	(1<<31)
-#define   DVS_FILTER_MASK	(3<<29)
-#define   DVS_FILTER_MEDIUM	(0<<29)
-#define   DVS_FILTER_ENHANCING	(1<<29)
-#define   DVS_FILTER_SOFTENING	(2<<29)
-#define   DVS_VERTICAL_OFFSET_HALF (1<<28) /* must be enabled below */
-#define   DVS_VERTICAL_OFFSET_ENABLE (1<<27)
+#define   DVS_SCALE_ENABLE	(1 << 31)
+#define   DVS_FILTER_MASK	(3 << 29)
+#define   DVS_FILTER_MEDIUM	(0 << 29)
+#define   DVS_FILTER_ENHANCING	(1 << 29)
+#define   DVS_FILTER_SOFTENING	(2 << 29)
+#define   DVS_VERTICAL_OFFSET_HALF (1 << 28) /* must be enabled below */
+#define   DVS_VERTICAL_OFFSET_ENABLE (1 << 27)
 #define _DVSAGAMC		0x72300
 
 #define _DVSBCNTR		0x73180
@@ -6191,31 +6191,31 @@ enum {
 #define DVSSURFLIVE(pipe) _MMIO_PIPE(pipe, _DVSASURFLIVE, _DVSBSURFLIVE)
 
 #define _SPRA_CTL		0x70280
-#define   SPRITE_ENABLE			(1<<31)
-#define   SPRITE_GAMMA_ENABLE		(1<<30)
-#define   SPRITE_YUV_RANGE_CORRECTION_DISABLE	(1<<28)
-#define   SPRITE_PIXFORMAT_MASK		(7<<25)
-#define   SPRITE_FORMAT_YUV422		(0<<25)
-#define   SPRITE_FORMAT_RGBX101010	(1<<25)
-#define   SPRITE_FORMAT_RGBX888		(2<<25)
-#define   SPRITE_FORMAT_RGBX161616	(3<<25)
-#define   SPRITE_FORMAT_YUV444		(4<<25)
-#define   SPRITE_FORMAT_XR_BGR101010	(5<<25) /* Extended range */
-#define   SPRITE_PIPE_CSC_ENABLE	(1<<24)
-#define   SPRITE_SOURCE_KEY		(1<<22)
-#define   SPRITE_RGB_ORDER_RGBX		(1<<20) /* only for 888 and 161616 */
-#define   SPRITE_YUV_TO_RGB_CSC_DISABLE	(1<<19)
-#define   SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709	(1<<18) /* 0 is BT601 */
-#define   SPRITE_YUV_BYTE_ORDER_MASK	(3<<16)
-#define   SPRITE_YUV_ORDER_YUYV		(0<<16)
-#define   SPRITE_YUV_ORDER_UYVY		(1<<16)
-#define   SPRITE_YUV_ORDER_YVYU		(2<<16)
-#define   SPRITE_YUV_ORDER_VYUY		(3<<16)
-#define   SPRITE_ROTATE_180		(1<<15)
-#define   SPRITE_TRICKLE_FEED_DISABLE	(1<<14)
-#define   SPRITE_INT_GAMMA_ENABLE	(1<<13)
-#define   SPRITE_TILED			(1<<10)
-#define   SPRITE_DEST_KEY		(1<<2)
+#define   SPRITE_ENABLE			(1 << 31)
+#define   SPRITE_GAMMA_ENABLE		(1 << 30)
+#define   SPRITE_YUV_RANGE_CORRECTION_DISABLE	(1 << 28)
+#define   SPRITE_PIXFORMAT_MASK		(7 << 25)
+#define   SPRITE_FORMAT_YUV422		(0 << 25)
+#define   SPRITE_FORMAT_RGBX101010	(1 << 25)
+#define   SPRITE_FORMAT_RGBX888		(2 << 25)
+#define   SPRITE_FORMAT_RGBX161616	(3 << 25)
+#define   SPRITE_FORMAT_YUV444		(4 << 25)
+#define   SPRITE_FORMAT_XR_BGR101010	(5 << 25) /* Extended range */
+#define   SPRITE_PIPE_CSC_ENABLE	(1 << 24)
+#define   SPRITE_SOURCE_KEY		(1 << 22)
+#define   SPRITE_RGB_ORDER_RGBX		(1 << 20) /* only for 888 and 161616 */
+#define   SPRITE_YUV_TO_RGB_CSC_DISABLE	(1 << 19)
+#define   SPRITE_YUV_TO_RGB_CSC_FORMAT_BT709	(1 << 18) /* 0 is BT601 */
+#define   SPRITE_YUV_BYTE_ORDER_MASK	(3 << 16)
+#define   SPRITE_YUV_ORDER_YUYV		(0 << 16)
+#define   SPRITE_YUV_ORDER_UYVY		(1 << 16)
+#define   SPRITE_YUV_ORDER_YVYU		(2 << 16)
+#define   SPRITE_YUV_ORDER_VYUY		(3 << 16)
+#define   SPRITE_ROTATE_180		(1 << 15)
+#define   SPRITE_TRICKLE_FEED_DISABLE	(1 << 14)
+#define   SPRITE_INT_GAMMA_ENABLE	(1 << 13)
+#define   SPRITE_TILED			(1 << 10)
+#define   SPRITE_DEST_KEY		(1 << 2)
 #define _SPRA_LINOFF		0x70284
 #define _SPRA_STRIDE		0x70288
 #define _SPRA_POS		0x7028c
@@ -6228,13 +6228,13 @@ enum {
 #define _SPRA_OFFSET		0x702a4
 #define _SPRA_SURFLIVE		0x702ac
 #define _SPRA_SCALE		0x70304
-#define   SPRITE_SCALE_ENABLE	(1<<31)
-#define   SPRITE_FILTER_MASK	(3<<29)
-#define   SPRITE_FILTER_MEDIUM	(0<<29)
-#define   SPRITE_FILTER_ENHANCING	(1<<29)
-#define   SPRITE_FILTER_SOFTENING	(2<<29)
-#define   SPRITE_VERTICAL_OFFSET_HALF	(1<<28) /* must be enabled below */
-#define   SPRITE_VERTICAL_OFFSET_ENABLE	(1<<27)
+#define   SPRITE_SCALE_ENABLE	(1 << 31)
+#define   SPRITE_FILTER_MASK	(3 << 29)
+#define   SPRITE_FILTER_MEDIUM	(0 << 29)
+#define   SPRITE_FILTER_ENHANCING	(1 << 29)
+#define   SPRITE_FILTER_SOFTENING	(2 << 29)
+#define   SPRITE_VERTICAL_OFFSET_HALF	(1 << 28) /* must be enabled below */
+#define   SPRITE_VERTICAL_OFFSET_ENABLE	(1 << 27)
 #define _SPRA_GAMC		0x70400
 
 #define _SPRB_CTL		0x71280
@@ -6268,28 +6268,28 @@ enum {
 #define SPRSURFLIVE(pipe) _MMIO_PIPE(pipe, _SPRA_SURFLIVE, _SPRB_SURFLIVE)
 
 #define _SPACNTR		(VLV_DISPLAY_BASE + 0x72180)
-#define   SP_ENABLE			(1<<31)
-#define   SP_GAMMA_ENABLE		(1<<30)
-#define   SP_PIXFORMAT_MASK		(0xf<<26)
-#define   SP_FORMAT_YUV422		(0<<26)
-#define   SP_FORMAT_BGR565		(5<<26)
-#define   SP_FORMAT_BGRX8888		(6<<26)
-#define   SP_FORMAT_BGRA8888		(7<<26)
-#define   SP_FORMAT_RGBX1010102		(8<<26)
-#define   SP_FORMAT_RGBA1010102		(9<<26)
-#define   SP_FORMAT_RGBX8888		(0xe<<26)
-#define   SP_FORMAT_RGBA8888		(0xf<<26)
-#define   SP_ALPHA_PREMULTIPLY		(1<<23) /* CHV pipe B */
-#define   SP_SOURCE_KEY			(1<<22)
-#define   SP_YUV_FORMAT_BT709		(1<<18)
-#define   SP_YUV_BYTE_ORDER_MASK	(3<<16)
-#define   SP_YUV_ORDER_YUYV		(0<<16)
-#define   SP_YUV_ORDER_UYVY		(1<<16)
-#define   SP_YUV_ORDER_YVYU		(2<<16)
-#define   SP_YUV_ORDER_VYUY		(3<<16)
-#define   SP_ROTATE_180			(1<<15)
-#define   SP_TILED			(1<<10)
-#define   SP_MIRROR			(1<<8) /* CHV pipe B */
+#define   SP_ENABLE			(1 << 31)
+#define   SP_GAMMA_ENABLE		(1 << 30)
+#define   SP_PIXFORMAT_MASK		(0xf << 26)
+#define   SP_FORMAT_YUV422		(0 << 26)
+#define   SP_FORMAT_BGR565		(5 << 26)
+#define   SP_FORMAT_BGRX8888		(6 << 26)
+#define   SP_FORMAT_BGRA8888		(7 << 26)
+#define   SP_FORMAT_RGBX1010102		(8 << 26)
+#define   SP_FORMAT_RGBA1010102		(9 << 26)
+#define   SP_FORMAT_RGBX8888		(0xe << 26)
+#define   SP_FORMAT_RGBA8888		(0xf << 26)
+#define   SP_ALPHA_PREMULTIPLY		(1 << 23) /* CHV pipe B */
+#define   SP_SOURCE_KEY			(1 << 22)
+#define   SP_YUV_FORMAT_BT709		(1 << 18)
+#define   SP_YUV_BYTE_ORDER_MASK	(3 << 16)
+#define   SP_YUV_ORDER_YUYV		(0 << 16)
+#define   SP_YUV_ORDER_UYVY		(1 << 16)
+#define   SP_YUV_ORDER_YVYU		(2 << 16)
+#define   SP_YUV_ORDER_VYUY		(3 << 16)
+#define   SP_ROTATE_180			(1 << 15)
+#define   SP_TILED			(1 << 10)
+#define   SP_MIRROR			(1 << 8) /* CHV pipe B */
 #define _SPALINOFF		(VLV_DISPLAY_BASE + 0x72184)
 #define _SPASTRIDE		(VLV_DISPLAY_BASE + 0x72188)
 #define _SPAPOS			(VLV_DISPLAY_BASE + 0x7218c)
@@ -6300,7 +6300,7 @@ enum {
 #define _SPAKEYMAXVAL		(VLV_DISPLAY_BASE + 0x721a0)
 #define _SPATILEOFF		(VLV_DISPLAY_BASE + 0x721a4)
 #define _SPACONSTALPHA		(VLV_DISPLAY_BASE + 0x721a8)
-#define   SP_CONST_ALPHA_ENABLE		(1<<31)
+#define   SP_CONST_ALPHA_ENABLE		(1 << 31)
 #define _SPACLRC0		(VLV_DISPLAY_BASE + 0x721d0)
 #define   SP_CONTRAST(x)		((x) << 18) /* u3.6 */
 #define   SP_BRIGHTNESS(x)		((x) & 0xff) /* s8 */
@@ -6392,40 +6392,40 @@ enum {
  * correctly map to the same formats in ICL, as long as bit 23 is set to 0
  */
 #define   PLANE_CTL_FORMAT_MASK			(0xf << 24)
-#define   PLANE_CTL_FORMAT_YUV422		(  0 << 24)
-#define   PLANE_CTL_FORMAT_NV12			(  1 << 24)
-#define   PLANE_CTL_FORMAT_XRGB_2101010		(  2 << 24)
-#define   PLANE_CTL_FORMAT_XRGB_8888		(  4 << 24)
-#define   PLANE_CTL_FORMAT_XRGB_16161616F	(  6 << 24)
-#define   PLANE_CTL_FORMAT_AYUV			(  8 << 24)
-#define   PLANE_CTL_FORMAT_INDEXED		( 12 << 24)
-#define   PLANE_CTL_FORMAT_RGB_565		( 14 << 24)
+#define   PLANE_CTL_FORMAT_YUV422		(0 << 24)
+#define   PLANE_CTL_FORMAT_NV12			(1 << 24)
+#define   PLANE_CTL_FORMAT_XRGB_2101010		(2 << 24)
+#define   PLANE_CTL_FORMAT_XRGB_8888		(4 << 24)
+#define   PLANE_CTL_FORMAT_XRGB_16161616F	(6 << 24)
+#define   PLANE_CTL_FORMAT_AYUV			(8 << 24)
+#define   PLANE_CTL_FORMAT_INDEXED		(12 << 24)
+#define   PLANE_CTL_FORMAT_RGB_565		(14 << 24)
 #define   ICL_PLANE_CTL_FORMAT_MASK		(0x1f << 23)
 #define   PLANE_CTL_PIPE_CSC_ENABLE		(1 << 23) /* Pre-GLK */
 #define   PLANE_CTL_KEY_ENABLE_MASK		(0x3 << 21)
-#define   PLANE_CTL_KEY_ENABLE_SOURCE		(  1 << 21)
-#define   PLANE_CTL_KEY_ENABLE_DESTINATION	(  2 << 21)
+#define   PLANE_CTL_KEY_ENABLE_SOURCE		(1 << 21)
+#define   PLANE_CTL_KEY_ENABLE_DESTINATION	(2 << 21)
 #define   PLANE_CTL_ORDER_BGRX			(0 << 20)
 #define   PLANE_CTL_ORDER_RGBX			(1 << 20)
 #define   PLANE_CTL_YUV_TO_RGB_CSC_FORMAT_BT709	(1 << 18)
 #define   PLANE_CTL_YUV422_ORDER_MASK		(0x3 << 16)
-#define   PLANE_CTL_YUV422_YUYV			(  0 << 16)
-#define   PLANE_CTL_YUV422_UYVY			(  1 << 16)
-#define   PLANE_CTL_YUV422_YVYU			(  2 << 16)
-#define   PLANE_CTL_YUV422_VYUY			(  3 << 16)
+#define   PLANE_CTL_YUV422_YUYV			(0 << 16)
+#define   PLANE_CTL_YUV422_UYVY			(1 << 16)
+#define   PLANE_CTL_YUV422_YVYU			(2 << 16)
+#define   PLANE_CTL_YUV422_VYUY			(3 << 16)
 #define   PLANE_CTL_DECOMPRESSION_ENABLE	(1 << 15)
 #define   PLANE_CTL_TRICKLE_FEED_DISABLE	(1 << 14)
 #define   PLANE_CTL_PLANE_GAMMA_DISABLE		(1 << 13) /* Pre-GLK */
 #define   PLANE_CTL_TILED_MASK			(0x7 << 10)
-#define   PLANE_CTL_TILED_LINEAR		(  0 << 10)
-#define   PLANE_CTL_TILED_X			(  1 << 10)
-#define   PLANE_CTL_TILED_Y			(  4 << 10)
-#define   PLANE_CTL_TILED_YF			(  5 << 10)
-#define   PLANE_CTL_FLIP_HORIZONTAL		(  1 << 8)
+#define   PLANE_CTL_TILED_LINEAR		(0 << 10)
+#define   PLANE_CTL_TILED_X			(1 << 10)
+#define   PLANE_CTL_TILED_Y			(4 << 10)
+#define   PLANE_CTL_TILED_YF			(5 << 10)
+#define   PLANE_CTL_FLIP_HORIZONTAL		(1 << 8)
 #define   PLANE_CTL_ALPHA_MASK			(0x3 << 4) /* Pre-GLK */
-#define   PLANE_CTL_ALPHA_DISABLE		(  0 << 4)
-#define   PLANE_CTL_ALPHA_SW_PREMULTIPLY	(  2 << 4)
-#define   PLANE_CTL_ALPHA_HW_PREMULTIPLY	(  3 << 4)
+#define   PLANE_CTL_ALPHA_DISABLE		(0 << 4)
+#define   PLANE_CTL_ALPHA_SW_PREMULTIPLY	(2 << 4)
+#define   PLANE_CTL_ALPHA_HW_PREMULTIPLY	(3 << 4)
 #define   PLANE_CTL_ROTATE_MASK			0x3
 #define   PLANE_CTL_ROTATE_0			0x0
 #define   PLANE_CTL_ROTATE_90			0x1
@@ -6653,7 +6653,7 @@ enum {
 # define VFMUNIT_CLOCK_GATE_DISABLE		(1 << 11)
 
 #define FDI_PLL_FREQ_CTL        _MMIO(0x46030)
-#define  FDI_PLL_FREQ_CHANGE_REQUEST    (1<<24)
+#define  FDI_PLL_FREQ_CHANGE_REQUEST    (1 << 24)
 #define  FDI_PLL_FREQ_LOCK_LIMIT_MASK   0xfff00
 #define  FDI_PLL_FREQ_DISABLE_COUNT_LIMIT_MASK  0xff
 
@@ -6702,14 +6702,14 @@ enum {
 /* IVB+ has 3 fitters, 0 is 7x5 capable, the other two only 3x3 */
 #define _PFA_CTL_1               0x68080
 #define _PFB_CTL_1               0x68880
-#define  PF_ENABLE              (1<<31)
-#define  PF_PIPE_SEL_MASK_IVB	(3<<29)
-#define  PF_PIPE_SEL_IVB(pipe)	((pipe)<<29)
-#define  PF_FILTER_MASK		(3<<23)
-#define  PF_FILTER_PROGRAMMED	(0<<23)
-#define  PF_FILTER_MED_3x3	(1<<23)
-#define  PF_FILTER_EDGE_ENHANCE	(2<<23)
-#define  PF_FILTER_EDGE_SOFTEN	(3<<23)
+#define  PF_ENABLE              (1 << 31)
+#define  PF_PIPE_SEL_MASK_IVB	(3 << 29)
+#define  PF_PIPE_SEL_IVB(pipe)	((pipe) << 29)
+#define  PF_FILTER_MASK		(3 << 23)
+#define  PF_FILTER_PROGRAMMED	(0 << 23)
+#define  PF_FILTER_MED_3x3	(1 << 23)
+#define  PF_FILTER_EDGE_ENHANCE	(2 << 23)
+#define  PF_FILTER_EDGE_SOFTEN	(3 << 23)
 #define _PFA_WIN_SZ		0x68074
 #define _PFB_WIN_SZ		0x68874
 #define _PFA_WIN_POS		0x68070
@@ -6727,7 +6727,7 @@ enum {
 
 #define _PSA_CTL		0x68180
 #define _PSB_CTL		0x68980
-#define PS_ENABLE		(1<<31)
+#define PS_ENABLE		(1 << 31)
 #define _PSA_WIN_SZ		0x68174
 #define _PSB_WIN_SZ		0x68974
 #define _PSA_WIN_POS		0x68170
@@ -6829,7 +6829,7 @@ enum {
 #define _PS_ECC_STAT_2B     0x68AD0
 #define _PS_ECC_STAT_1C     0x691D0
 
-#define _ID(id, a, b) ((a) + (id)*((b)-(a)))
+#define _ID(id, a, b) ((a) + (id) * ((b) - (a)))
 #define SKL_PS_CTRL(pipe, id) _MMIO_PIPE(pipe,        \
 			_ID(id, _PS_1A_CTRL, _PS_2A_CTRL),       \
 			_ID(id, _PS_1B_CTRL, _PS_2B_CTRL))
@@ -6910,37 +6910,37 @@ enum {
 #define DE_PIPEB_CRC_DONE	(1 << 10)
 #define DE_PIPEB_FIFO_UNDERRUN  (1 << 8)
 #define DE_PIPEA_VBLANK         (1 << 7)
-#define DE_PIPE_VBLANK(pipe)    (1 << (7 + 8*(pipe)))
+#define DE_PIPE_VBLANK(pipe)    (1 << (7 + 8 * (pipe)))
 #define DE_PIPEA_EVEN_FIELD     (1 << 6)
 #define DE_PIPEA_ODD_FIELD      (1 << 5)
 #define DE_PIPEA_LINE_COMPARE   (1 << 4)
 #define DE_PIPEA_VSYNC          (1 << 3)
 #define DE_PIPEA_CRC_DONE	(1 << 2)
-#define DE_PIPE_CRC_DONE(pipe)	(1 << (2 + 8*(pipe)))
+#define DE_PIPE_CRC_DONE(pipe)	(1 << (2 + 8 * (pipe)))
 #define DE_PIPEA_FIFO_UNDERRUN  (1 << 0)
-#define DE_PIPE_FIFO_UNDERRUN(pipe)  (1 << (8*(pipe)))
+#define DE_PIPE_FIFO_UNDERRUN(pipe)  (1 << (8 * (pipe)))
 
 /* More Ivybridge lolz */
-#define DE_ERR_INT_IVB			(1<<30)
-#define DE_GSE_IVB			(1<<29)
-#define DE_PCH_EVENT_IVB		(1<<28)
-#define DE_DP_A_HOTPLUG_IVB		(1<<27)
-#define DE_AUX_CHANNEL_A_IVB		(1<<26)
-#define DE_EDP_PSR_INT_HSW		(1<<19)
-#define DE_SPRITEC_FLIP_DONE_IVB	(1<<14)
-#define DE_PLANEC_FLIP_DONE_IVB		(1<<13)
-#define DE_PIPEC_VBLANK_IVB		(1<<10)
-#define DE_SPRITEB_FLIP_DONE_IVB	(1<<9)
-#define DE_PLANEB_FLIP_DONE_IVB		(1<<8)
-#define DE_PIPEB_VBLANK_IVB		(1<<5)
-#define DE_SPRITEA_FLIP_DONE_IVB	(1<<4)
-#define DE_PLANEA_FLIP_DONE_IVB		(1<<3)
-#define DE_PLANE_FLIP_DONE_IVB(plane)	(1<< (3 + 5*(plane)))
-#define DE_PIPEA_VBLANK_IVB		(1<<0)
+#define DE_ERR_INT_IVB			(1 << 30)
+#define DE_GSE_IVB			(1 << 29)
+#define DE_PCH_EVENT_IVB		(1 << 28)
+#define DE_DP_A_HOTPLUG_IVB		(1 << 27)
+#define DE_AUX_CHANNEL_A_IVB		(1 << 26)
+#define DE_EDP_PSR_INT_HSW		(1 << 19)
+#define DE_SPRITEC_FLIP_DONE_IVB	(1 << 14)
+#define DE_PLANEC_FLIP_DONE_IVB		(1 << 13)
+#define DE_PIPEC_VBLANK_IVB		(1 << 10)
+#define DE_SPRITEB_FLIP_DONE_IVB	(1 << 9)
+#define DE_PLANEB_FLIP_DONE_IVB		(1 << 8)
+#define DE_PIPEB_VBLANK_IVB		(1 << 5)
+#define DE_SPRITEA_FLIP_DONE_IVB	(1 << 4)
+#define DE_PLANEA_FLIP_DONE_IVB		(1 << 3)
+#define DE_PLANE_FLIP_DONE_IVB(plane)	(1 << (3 + 5 * (plane)))
+#define DE_PIPEA_VBLANK_IVB		(1 << 0)
 #define DE_PIPE_VBLANK_IVB(pipe)	(1 << ((pipe) * 5))
 
 #define VLV_MASTER_IER			_MMIO(0x4400c) /* Gunit master IER */
-#define   MASTER_INTERRUPT_ENABLE	(1<<31)
+#define   MASTER_INTERRUPT_ENABLE	(1 << 31)
 
 #define DEISR   _MMIO(0x44000)
 #define DEIMR   _MMIO(0x44004)
@@ -6953,37 +6953,37 @@ enum {
 #define GTIER   _MMIO(0x4401c)
 
 #define GEN8_MASTER_IRQ			_MMIO(0x44200)
-#define  GEN8_MASTER_IRQ_CONTROL	(1<<31)
-#define  GEN8_PCU_IRQ			(1<<30)
-#define  GEN8_DE_PCH_IRQ		(1<<23)
-#define  GEN8_DE_MISC_IRQ		(1<<22)
-#define  GEN8_DE_PORT_IRQ		(1<<20)
-#define  GEN8_DE_PIPE_C_IRQ		(1<<18)
-#define  GEN8_DE_PIPE_B_IRQ		(1<<17)
-#define  GEN8_DE_PIPE_A_IRQ		(1<<16)
-#define  GEN8_DE_PIPE_IRQ(pipe)		(1<<(16+(pipe)))
-#define  GEN8_GT_VECS_IRQ		(1<<6)
-#define  GEN8_GT_GUC_IRQ		(1<<5)
-#define  GEN8_GT_PM_IRQ			(1<<4)
-#define  GEN8_GT_VCS2_IRQ		(1<<3)
-#define  GEN8_GT_VCS1_IRQ		(1<<2)
-#define  GEN8_GT_BCS_IRQ		(1<<1)
-#define  GEN8_GT_RCS_IRQ		(1<<0)
+#define  GEN8_MASTER_IRQ_CONTROL	(1 << 31)
+#define  GEN8_PCU_IRQ			(1 << 30)
+#define  GEN8_DE_PCH_IRQ		(1 << 23)
+#define  GEN8_DE_MISC_IRQ		(1 << 22)
+#define  GEN8_DE_PORT_IRQ		(1 << 20)
+#define  GEN8_DE_PIPE_C_IRQ		(1 << 18)
+#define  GEN8_DE_PIPE_B_IRQ		(1 << 17)
+#define  GEN8_DE_PIPE_A_IRQ		(1 << 16)
+#define  GEN8_DE_PIPE_IRQ(pipe)		(1 << (16 + (pipe)))
+#define  GEN8_GT_VECS_IRQ		(1 << 6)
+#define  GEN8_GT_GUC_IRQ		(1 << 5)
+#define  GEN8_GT_PM_IRQ			(1 << 4)
+#define  GEN8_GT_VCS2_IRQ		(1 << 3)
+#define  GEN8_GT_VCS1_IRQ		(1 << 2)
+#define  GEN8_GT_BCS_IRQ		(1 << 1)
+#define  GEN8_GT_RCS_IRQ		(1 << 0)
 
 #define GEN8_GT_ISR(which) _MMIO(0x44300 + (0x10 * (which)))
 #define GEN8_GT_IMR(which) _MMIO(0x44304 + (0x10 * (which)))
 #define GEN8_GT_IIR(which) _MMIO(0x44308 + (0x10 * (which)))
 #define GEN8_GT_IER(which) _MMIO(0x4430c + (0x10 * (which)))
 
-#define GEN9_GUC_TO_HOST_INT_EVENT	(1<<31)
-#define GEN9_GUC_EXEC_ERROR_EVENT	(1<<30)
-#define GEN9_GUC_DISPLAY_EVENT		(1<<29)
-#define GEN9_GUC_SEMA_SIGNAL_EVENT	(1<<28)
-#define GEN9_GUC_IOMMU_MSG_EVENT	(1<<27)
-#define GEN9_GUC_DB_RING_EVENT		(1<<26)
-#define GEN9_GUC_DMA_DONE_EVENT		(1<<25)
-#define GEN9_GUC_FATAL_ERROR_EVENT	(1<<24)
-#define GEN9_GUC_NOTIFICATION_EVENT	(1<<23)
+#define GEN9_GUC_TO_HOST_INT_EVENT	(1 << 31)
+#define GEN9_GUC_EXEC_ERROR_EVENT	(1 << 30)
+#define GEN9_GUC_DISPLAY_EVENT		(1 << 29)
+#define GEN9_GUC_SEMA_SIGNAL_EVENT	(1 << 28)
+#define GEN9_GUC_IOMMU_MSG_EVENT	(1 << 27)
+#define GEN9_GUC_DB_RING_EVENT		(1 << 26)
+#define GEN9_GUC_DMA_DONE_EVENT		(1 << 25)
+#define GEN9_GUC_FATAL_ERROR_EVENT	(1 << 24)
+#define GEN9_GUC_NOTIFICATION_EVENT	(1 << 23)
 
 #define GEN8_RCS_IRQ_SHIFT 0
 #define GEN8_BCS_IRQ_SHIFT 16
@@ -7127,8 +7127,8 @@ enum {
 #define ILK_DISPLAY_CHICKEN2	_MMIO(0x42004)
 /* Required on all Ironlake and Sandybridge according to the B-Spec. */
 #define  ILK_ELPIN_409_SELECT	(1 << 25)
-#define  ILK_DPARB_GATE	(1<<22)
-#define  ILK_VSDPFD_FULL	(1<<21)
+#define  ILK_DPARB_GATE	(1 << 22)
+#define  ILK_VSDPFD_FULL	(1 << 21)
 #define FUSE_STRAP			_MMIO(0x42014)
 #define  ILK_INTERNAL_GRAPHICS_DISABLE	(1 << 31)
 #define  ILK_INTERNAL_DISPLAY_DISABLE	(1 << 30)
@@ -7178,31 +7178,31 @@ enum {
 #define CHICKEN_TRANS_A         0x420c0
 #define CHICKEN_TRANS_B         0x420c4
 #define CHICKEN_TRANS(trans) _MMIO_TRANS(trans, CHICKEN_TRANS_A, CHICKEN_TRANS_B)
-#define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1<<25) /* GLK and CNL+ */
-#define  DDI_TRAINING_OVERRIDE_ENABLE	(1<<19)
-#define  DDI_TRAINING_OVERRIDE_VALUE	(1<<18)
-#define  DDIE_TRAINING_OVERRIDE_ENABLE	(1<<17) /* CHICKEN_TRANS_A only */
-#define  DDIE_TRAINING_OVERRIDE_VALUE	(1<<16) /* CHICKEN_TRANS_A only */
-#define  PSR2_ADD_VERTICAL_LINE_COUNT   (1<<15)
-#define  PSR2_VSC_ENABLE_PROG_HEADER    (1<<12)
+#define  VSC_DATA_SEL_SOFTWARE_CONTROL	(1 << 25) /* GLK and CNL+ */
+#define  DDI_TRAINING_OVERRIDE_ENABLE	(1 << 19)
+#define  DDI_TRAINING_OVERRIDE_VALUE	(1 << 18)
+#define  DDIE_TRAINING_OVERRIDE_ENABLE	(1 << 17) /* CHICKEN_TRANS_A only */
+#define  DDIE_TRAINING_OVERRIDE_VALUE	(1 << 16) /* CHICKEN_TRANS_A only */
+#define  PSR2_ADD_VERTICAL_LINE_COUNT   (1 << 15)
+#define  PSR2_VSC_ENABLE_PROG_HEADER    (1 << 12)
 
 #define DISP_ARB_CTL	_MMIO(0x45000)
-#define  DISP_FBC_MEMORY_WAKE		(1<<31)
-#define  DISP_TILE_SURFACE_SWIZZLING	(1<<13)
-#define  DISP_FBC_WM_DIS		(1<<15)
+#define  DISP_FBC_MEMORY_WAKE		(1 << 31)
+#define  DISP_TILE_SURFACE_SWIZZLING	(1 << 13)
+#define  DISP_FBC_WM_DIS		(1 << 15)
 #define DISP_ARB_CTL2	_MMIO(0x45004)
-#define  DISP_DATA_PARTITION_5_6	(1<<6)
-#define  DISP_IPC_ENABLE		(1<<3)
+#define  DISP_DATA_PARTITION_5_6	(1 << 6)
+#define  DISP_IPC_ENABLE		(1 << 3)
 #define DBUF_CTL	_MMIO(0x45008)
 #define DBUF_CTL_S1	_MMIO(0x45008)
 #define DBUF_CTL_S2	_MMIO(0x44FE8)
-#define  DBUF_POWER_REQUEST		(1<<31)
-#define  DBUF_POWER_STATE		(1<<30)
+#define  DBUF_POWER_REQUEST		(1 << 31)
+#define  DBUF_POWER_STATE		(1 << 30)
 #define GEN7_MSG_CTL	_MMIO(0x45010)
-#define  WAIT_FOR_PCH_RESET_ACK		(1<<1)
-#define  WAIT_FOR_PCH_FLR_ACK		(1<<0)
+#define  WAIT_FOR_PCH_RESET_ACK		(1 << 1)
+#define  WAIT_FOR_PCH_FLR_ACK		(1 << 0)
 #define HSW_NDE_RSTWRN_OPT	_MMIO(0x46408)
-#define  RESET_PCH_HANDSHAKE_ENABLE	(1<<4)
+#define  RESET_PCH_HANDSHAKE_ENABLE	(1 << 4)
 
 #define GEN8_CHICKEN_DCPR_1		_MMIO(0x46430)
 #define   SKL_SELECT_ALTERNATE_DC_EXIT	(1 << 30)
@@ -7227,16 +7227,16 @@ enum {
 #define ICL_DSSM_CDCLK_PLL_REFCLK_38_4MHz	(2 << 29)
 
 #define GEN7_FF_SLICE_CS_CHICKEN1	_MMIO(0x20e0)
-#define   GEN9_FFSC_PERCTX_PREEMPT_CTRL	(1<<14)
+#define   GEN9_FFSC_PERCTX_PREEMPT_CTRL	(1 << 14)
 
 #define FF_SLICE_CS_CHICKEN2			_MMIO(0x20e4)
-#define  GEN9_TSG_BARRIER_ACK_DISABLE		(1<<8)
-#define  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE  (1<<10)
+#define  GEN9_TSG_BARRIER_ACK_DISABLE		(1 << 8)
+#define  GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE  (1 << 10)
 
 #define GEN9_CS_DEBUG_MODE1		_MMIO(0x20ec)
 #define GEN9_CTX_PREEMPT_REG		_MMIO(0x2248)
 #define GEN8_CS_CHICKEN1		_MMIO(0x2580)
-#define GEN9_PREEMPT_3D_OBJECT_LEVEL		(1<<0)
+#define GEN9_PREEMPT_3D_OBJECT_LEVEL		(1 << 0)
 #define GEN9_PREEMPT_GPGPU_LEVEL(hi, lo)	(((hi) << 2) | ((lo) << 1))
 #define GEN9_PREEMPT_GPGPU_MID_THREAD_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 0)
 #define GEN9_PREEMPT_GPGPU_THREAD_GROUP_LEVEL	GEN9_PREEMPT_GPGPU_LEVEL(0, 1)
@@ -7258,11 +7258,11 @@ enum {
   #define GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC	(1 << 11)
 
 #define HIZ_CHICKEN					_MMIO(0x7018)
-# define CHV_HZ_8X8_MODE_IN_1X				(1<<15)
-# define BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	(1<<3)
+# define CHV_HZ_8X8_MODE_IN_1X				(1 << 15)
+# define BDW_HIZ_POWER_COMPILER_CLOCK_GATING_DISABLE	(1 << 3)
 
 #define GEN9_SLICE_COMMON_ECO_CHICKEN0		_MMIO(0x7308)
-#define  DISABLE_PIXEL_MASK_CAMMING		(1<<14)
+#define  DISABLE_PIXEL_MASK_CAMMING		(1 << 14)
 
 #define GEN9_SLICE_COMMON_ECO_CHICKEN1		_MMIO(0x731c)
 #define   GEN11_STATE_CACHE_REDIRECT_TO_CS	(1 << 11)
@@ -7283,7 +7283,7 @@ enum {
 
 #define GEN7_L3CNTLREG1				_MMIO(0xB01C)
 #define  GEN7_WA_FOR_GEN7_L3_CONTROL			0x3C47FF8C
-#define  GEN7_L3AGDIS				(1<<19)
+#define  GEN7_L3AGDIS				(1 << 19)
 #define GEN7_L3CNTLREG2				_MMIO(0xB020)
 #define GEN7_L3CNTLREG3				_MMIO(0xB024)
 
@@ -7293,7 +7293,7 @@ enum {
 #define   GEN11_I2M_WRITE_DISABLE		(1 << 28)
 
 #define GEN7_L3SQCREG4				_MMIO(0xb034)
-#define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1<<27)
+#define  L3SQ_URB_READ_CAM_MATCH_DISABLE	(1 << 27)
 
 #define GEN8_L3SQCREG4				_MMIO(0xb118)
 #define  GEN11_LQSC_CLEAN_EVICT_DISABLE		(1 << 6)
@@ -7304,12 +7304,12 @@ enum {
 #define HDC_CHICKEN0				_MMIO(0x7300)
 #define CNL_HDC_CHICKEN0			_MMIO(0xE5F0)
 #define ICL_HDC_MODE				_MMIO(0xE5F4)
-#define  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1<<15)
-#define  HDC_FENCE_DEST_SLM_DISABLE		(1<<14)
-#define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1<<11)
-#define  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT	(1<<5)
-#define  HDC_FORCE_NON_COHERENT			(1<<4)
-#define  HDC_BARRIER_PERFORMANCE_DISABLE	(1<<10)
+#define  HDC_FORCE_CSR_NON_COHERENT_OVR_DISABLE	(1 << 15)
+#define  HDC_FENCE_DEST_SLM_DISABLE		(1 << 14)
+#define  HDC_DONOT_FETCH_MEM_WHEN_MASKED	(1 << 11)
+#define  HDC_FORCE_CONTEXT_SAVE_RESTORE_NON_COHERENT	(1 << 5)
+#define  HDC_FORCE_NON_COHERENT			(1 << 4)
+#define  HDC_BARRIER_PERFORMANCE_DISABLE	(1 << 10)
 
 #define GEN8_HDC_CHICKEN1			_MMIO(0x7304)
 
@@ -7322,13 +7322,13 @@ enum {
 
 /* WaCatErrorRejectionIssue */
 #define GEN7_SQ_CHICKEN_MBCUNIT_CONFIG		_MMIO(0x9030)
-#define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1<<11)
+#define  GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB	(1 << 11)
 
 #define HSW_SCRATCH1				_MMIO(0xb038)
-#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1<<27)
+#define  HSW_SCRATCH1_L3_DATA_ATOMICS_DISABLE	(1 << 27)
 
 #define BDW_SCRATCH1					_MMIO(0xb11c)
-#define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1<<2)
+#define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1 << 2)
 
 /* PCH */
 
@@ -7427,8 +7427,8 @@ enum {
 #define SDEIER  _MMIO(0xc400c)
 
 #define SERR_INT			_MMIO(0xc4040)
-#define  SERR_INT_POISON		(1<<31)
-#define  SERR_INT_TRANS_FIFO_UNDERRUN(pipe)	(1<<((pipe)*3))
+#define  SERR_INT_POISON		(1 << 31)
+#define  SERR_INT_TRANS_FIFO_UNDERRUN(pipe)	(1 << ((pipe) * 3))
 
 /* digital port hotplug */
 #define PCH_PORT_HOTPLUG		_MMIO(0xc4030)	/* SHOTPLUG_CTL */
@@ -7500,7 +7500,7 @@ enum {
 #define PCH_DPLL(pll) _MMIO(pll == 0 ? _PCH_DPLL_A : _PCH_DPLL_B)
 
 #define _PCH_FPA0                0xc6040
-#define  FP_CB_TUNE		(0x3<<22)
+#define  FP_CB_TUNE		(0x3 << 22)
 #define _PCH_FPA1                0xc6044
 #define _PCH_FPB0                0xc6048
 #define _PCH_FPB1                0xc604c
@@ -7511,32 +7511,32 @@ enum {
 
 #define PCH_DREF_CONTROL        _MMIO(0xC6200)
 #define  DREF_CONTROL_MASK      0x7fc3
-#define  DREF_CPU_SOURCE_OUTPUT_DISABLE         (0<<13)
-#define  DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD      (2<<13)
-#define  DREF_CPU_SOURCE_OUTPUT_NONSPREAD       (3<<13)
-#define  DREF_CPU_SOURCE_OUTPUT_MASK		(3<<13)
-#define  DREF_SSC_SOURCE_DISABLE                (0<<11)
-#define  DREF_SSC_SOURCE_ENABLE                 (2<<11)
-#define  DREF_SSC_SOURCE_MASK			(3<<11)
-#define  DREF_NONSPREAD_SOURCE_DISABLE          (0<<9)
-#define  DREF_NONSPREAD_CK505_ENABLE		(1<<9)
-#define  DREF_NONSPREAD_SOURCE_ENABLE           (2<<9)
-#define  DREF_NONSPREAD_SOURCE_MASK		(3<<9)
-#define  DREF_SUPERSPREAD_SOURCE_DISABLE        (0<<7)
-#define  DREF_SUPERSPREAD_SOURCE_ENABLE         (2<<7)
-#define  DREF_SUPERSPREAD_SOURCE_MASK		(3<<7)
-#define  DREF_SSC4_DOWNSPREAD                   (0<<6)
-#define  DREF_SSC4_CENTERSPREAD                 (1<<6)
-#define  DREF_SSC1_DISABLE                      (0<<1)
-#define  DREF_SSC1_ENABLE                       (1<<1)
+#define  DREF_CPU_SOURCE_OUTPUT_DISABLE         (0 << 13)
+#define  DREF_CPU_SOURCE_OUTPUT_DOWNSPREAD      (2 << 13)
+#define  DREF_CPU_SOURCE_OUTPUT_NONSPREAD       (3 << 13)
+#define  DREF_CPU_SOURCE_OUTPUT_MASK		(3 << 13)
+#define  DREF_SSC_SOURCE_DISABLE                (0 << 11)
+#define  DREF_SSC_SOURCE_ENABLE                 (2 << 11)
+#define  DREF_SSC_SOURCE_MASK			(3 << 11)
+#define  DREF_NONSPREAD_SOURCE_DISABLE          (0 << 9)
+#define  DREF_NONSPREAD_CK505_ENABLE		(1 << 9)
+#define  DREF_NONSPREAD_SOURCE_ENABLE           (2 << 9)
+#define  DREF_NONSPREAD_SOURCE_MASK		(3 << 9)
+#define  DREF_SUPERSPREAD_SOURCE_DISABLE        (0 << 7)
+#define  DREF_SUPERSPREAD_SOURCE_ENABLE         (2 << 7)
+#define  DREF_SUPERSPREAD_SOURCE_MASK		(3 << 7)
+#define  DREF_SSC4_DOWNSPREAD                   (0 << 6)
+#define  DREF_SSC4_CENTERSPREAD                 (1 << 6)
+#define  DREF_SSC1_DISABLE                      (0 << 1)
+#define  DREF_SSC1_ENABLE                       (1 << 1)
 #define  DREF_SSC4_DISABLE                      (0)
 #define  DREF_SSC4_ENABLE                       (1)
 
 #define PCH_RAWCLK_FREQ         _MMIO(0xc6204)
 #define  FDL_TP1_TIMER_SHIFT    12
-#define  FDL_TP1_TIMER_MASK     (3<<12)
+#define  FDL_TP1_TIMER_MASK     (3 << 12)
 #define  FDL_TP2_TIMER_SHIFT    10
-#define  FDL_TP2_TIMER_MASK     (3<<10)
+#define  FDL_TP2_TIMER_MASK     (3 << 10)
 #define  RAWCLK_FREQ_MASK       0x3ff
 #define  CNP_RAWCLK_DIV_MASK	(0x3ff << 16)
 #define  CNP_RAWCLK_DIV(div)	((div) << 16)
@@ -7661,7 +7661,7 @@ enum {
 #define HSW_TVIDEO_DIP_VSC_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VSC_DATA_A + (i) * 4)
 
 #define _HSW_STEREO_3D_CTL_A		0x70020
-#define   S3D_ENABLE			(1<<31)
+#define   S3D_ENABLE			(1 << 31)
 #define _HSW_STEREO_3D_CTL_B		0x71020
 
 #define HSW_STEREO_3D_CTL(trans)	_MMIO_PIPE2(trans, _HSW_STEREO_3D_CTL_A)
@@ -7704,156 +7704,156 @@ enum {
 #define _PCH_TRANSBCONF              0xf1008
 #define PCH_TRANSCONF(pipe)	_MMIO_PIPE(pipe, _PCH_TRANSACONF, _PCH_TRANSBCONF)
 #define LPT_TRANSCONF		PCH_TRANSCONF(PIPE_A) /* lpt has only one transcoder */
-#define  TRANS_DISABLE          (0<<31)
-#define  TRANS_ENABLE           (1<<31)
-#define  TRANS_STATE_MASK       (1<<30)
-#define  TRANS_STATE_DISABLE    (0<<30)
-#define  TRANS_STATE_ENABLE     (1<<30)
-#define  TRANS_FSYNC_DELAY_HB1  (0<<27)
-#define  TRANS_FSYNC_DELAY_HB2  (1<<27)
-#define  TRANS_FSYNC_DELAY_HB3  (2<<27)
-#define  TRANS_FSYNC_DELAY_HB4  (3<<27)
-#define  TRANS_INTERLACE_MASK   (7<<21)
-#define  TRANS_PROGRESSIVE      (0<<21)
-#define  TRANS_INTERLACED       (3<<21)
-#define  TRANS_LEGACY_INTERLACED_ILK (2<<21)
-#define  TRANS_8BPC             (0<<5)
-#define  TRANS_10BPC            (1<<5)
-#define  TRANS_6BPC             (2<<5)
-#define  TRANS_12BPC            (3<<5)
+#define  TRANS_DISABLE          (0 << 31)
+#define  TRANS_ENABLE           (1 << 31)
+#define  TRANS_STATE_MASK       (1 << 30)
+#define  TRANS_STATE_DISABLE    (0 << 30)
+#define  TRANS_STATE_ENABLE     (1 << 30)
+#define  TRANS_FSYNC_DELAY_HB1  (0 << 27)
+#define  TRANS_FSYNC_DELAY_HB2  (1 << 27)
+#define  TRANS_FSYNC_DELAY_HB3  (2 << 27)
+#define  TRANS_FSYNC_DELAY_HB4  (3 << 27)
+#define  TRANS_INTERLACE_MASK   (7 << 21)
+#define  TRANS_PROGRESSIVE      (0 << 21)
+#define  TRANS_INTERLACED       (3 << 21)
+#define  TRANS_LEGACY_INTERLACED_ILK (2 << 21)
+#define  TRANS_8BPC             (0 << 5)
+#define  TRANS_10BPC            (1 << 5)
+#define  TRANS_6BPC             (2 << 5)
+#define  TRANS_12BPC            (3 << 5)
 
 #define _TRANSA_CHICKEN1	 0xf0060
 #define _TRANSB_CHICKEN1	 0xf1060
 #define TRANS_CHICKEN1(pipe)	_MMIO_PIPE(pipe, _TRANSA_CHICKEN1, _TRANSB_CHICKEN1)
-#define  TRANS_CHICKEN1_HDMIUNIT_GC_DISABLE	(1<<10)
-#define  TRANS_CHICKEN1_DP0UNIT_GC_DISABLE	(1<<4)
+#define  TRANS_CHICKEN1_HDMIUNIT_GC_DISABLE	(1 << 10)
+#define  TRANS_CHICKEN1_DP0UNIT_GC_DISABLE	(1 << 4)
 #define _TRANSA_CHICKEN2	 0xf0064
 #define _TRANSB_CHICKEN2	 0xf1064
 #define TRANS_CHICKEN2(pipe)	_MMIO_PIPE(pipe, _TRANSA_CHICKEN2, _TRANSB_CHICKEN2)
-#define  TRANS_CHICKEN2_TIMING_OVERRIDE			(1<<31)
-#define  TRANS_CHICKEN2_FDI_POLARITY_REVERSED		(1<<29)
-#define  TRANS_CHICKEN2_FRAME_START_DELAY_MASK		(3<<27)
-#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER	(1<<26)
-#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH	(1<<25)
+#define  TRANS_CHICKEN2_TIMING_OVERRIDE			(1 << 31)
+#define  TRANS_CHICKEN2_FDI_POLARITY_REVERSED		(1 << 29)
+#define  TRANS_CHICKEN2_FRAME_START_DELAY_MASK		(3 << 27)
+#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_COUNTER	(1 << 26)
+#define  TRANS_CHICKEN2_DISABLE_DEEP_COLOR_MODESWITCH	(1 << 25)
 
 #define SOUTH_CHICKEN1		_MMIO(0xc2000)
 #define  FDIA_PHASE_SYNC_SHIFT_OVR	19
 #define  FDIA_PHASE_SYNC_SHIFT_EN	18
-#define  FDI_PHASE_SYNC_OVR(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_OVR - ((pipe) * 2)))
-#define  FDI_PHASE_SYNC_EN(pipe) (1<<(FDIA_PHASE_SYNC_SHIFT_EN - ((pipe) * 2)))
+#define  FDI_PHASE_SYNC_OVR(pipe) (1 << (FDIA_PHASE_SYNC_SHIFT_OVR - ((pipe) * 2)))
+#define  FDI_PHASE_SYNC_EN(pipe) (1 << (FDIA_PHASE_SYNC_SHIFT_EN - ((pipe) * 2)))
 #define  FDI_BC_BIFURCATION_SELECT	(1 << 12)
 #define  CHASSIS_CLK_REQ_DURATION_MASK	(0xf << 8)
 #define  CHASSIS_CLK_REQ_DURATION(x)	((x) << 8)
-#define  SPT_PWM_GRANULARITY		(1<<0)
+#define  SPT_PWM_GRANULARITY		(1 << 0)
 #define SOUTH_CHICKEN2		_MMIO(0xc2004)
-#define  FDI_MPHY_IOSFSB_RESET_STATUS	(1<<13)
-#define  FDI_MPHY_IOSFSB_RESET_CTL	(1<<12)
-#define  LPT_PWM_GRANULARITY		(1<<5)
-#define  DPLS_EDP_PPS_FIX_DIS		(1<<0)
+#define  FDI_MPHY_IOSFSB_RESET_STATUS	(1 << 13)
+#define  FDI_MPHY_IOSFSB_RESET_CTL	(1 << 12)
+#define  LPT_PWM_GRANULARITY		(1 << 5)
+#define  DPLS_EDP_PPS_FIX_DIS		(1 << 0)
 
 #define _FDI_RXA_CHICKEN        0xc200c
 #define _FDI_RXB_CHICKEN        0xc2010
-#define  FDI_RX_PHASE_SYNC_POINTER_OVR	(1<<1)
-#define  FDI_RX_PHASE_SYNC_POINTER_EN	(1<<0)
+#define  FDI_RX_PHASE_SYNC_POINTER_OVR	(1 << 1)
+#define  FDI_RX_PHASE_SYNC_POINTER_EN	(1 << 0)
 #define FDI_RX_CHICKEN(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_CHICKEN, _FDI_RXB_CHICKEN)
 
 #define SOUTH_DSPCLK_GATE_D	_MMIO(0xc2020)
-#define  PCH_GMBUSUNIT_CLOCK_GATE_DISABLE (1<<31)
-#define  PCH_DPLUNIT_CLOCK_GATE_DISABLE (1<<30)
-#define  PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1<<29)
-#define  PCH_CPUNIT_CLOCK_GATE_DISABLE (1<<14)
-#define  CNP_PWM_CGE_GATING_DISABLE (1<<13)
-#define  PCH_LP_PARTITION_LEVEL_DISABLE  (1<<12)
+#define  PCH_GMBUSUNIT_CLOCK_GATE_DISABLE (1 << 31)
+#define  PCH_DPLUNIT_CLOCK_GATE_DISABLE (1 << 30)
+#define  PCH_DPLSUNIT_CLOCK_GATE_DISABLE (1 << 29)
+#define  PCH_CPUNIT_CLOCK_GATE_DISABLE (1 << 14)
+#define  CNP_PWM_CGE_GATING_DISABLE (1 << 13)
+#define  PCH_LP_PARTITION_LEVEL_DISABLE  (1 << 12)
 
 /* CPU: FDI_TX */
 #define _FDI_TXA_CTL            0x60100
 #define _FDI_TXB_CTL            0x61100
 #define FDI_TX_CTL(pipe)	_MMIO_PIPE(pipe, _FDI_TXA_CTL, _FDI_TXB_CTL)
-#define  FDI_TX_DISABLE         (0<<31)
-#define  FDI_TX_ENABLE          (1<<31)
-#define  FDI_LINK_TRAIN_PATTERN_1       (0<<28)
-#define  FDI_LINK_TRAIN_PATTERN_2       (1<<28)
-#define  FDI_LINK_TRAIN_PATTERN_IDLE    (2<<28)
-#define  FDI_LINK_TRAIN_NONE            (3<<28)
-#define  FDI_LINK_TRAIN_VOLTAGE_0_4V    (0<<25)
-#define  FDI_LINK_TRAIN_VOLTAGE_0_6V    (1<<25)
-#define  FDI_LINK_TRAIN_VOLTAGE_0_8V    (2<<25)
-#define  FDI_LINK_TRAIN_VOLTAGE_1_2V    (3<<25)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_NONE (0<<22)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_1_5X (1<<22)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_2X   (2<<22)
-#define  FDI_LINK_TRAIN_PRE_EMPHASIS_3X   (3<<22)
+#define  FDI_TX_DISABLE         (0 << 31)
+#define  FDI_TX_ENABLE          (1 << 31)
+#define  FDI_LINK_TRAIN_PATTERN_1       (0 << 28)
+#define  FDI_LINK_TRAIN_PATTERN_2       (1 << 28)
+#define  FDI_LINK_TRAIN_PATTERN_IDLE    (2 << 28)
+#define  FDI_LINK_TRAIN_NONE            (3 << 28)
+#define  FDI_LINK_TRAIN_VOLTAGE_0_4V    (0 << 25)
+#define  FDI_LINK_TRAIN_VOLTAGE_0_6V    (1 << 25)
+#define  FDI_LINK_TRAIN_VOLTAGE_0_8V    (2 << 25)
+#define  FDI_LINK_TRAIN_VOLTAGE_1_2V    (3 << 25)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_NONE (0 << 22)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_1_5X (1 << 22)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_2X   (2 << 22)
+#define  FDI_LINK_TRAIN_PRE_EMPHASIS_3X   (3 << 22)
 /* ILK always use 400mV 0dB for voltage swing and pre-emphasis level.
    SNB has different settings. */
 /* SNB A-stepping */
-#define  FDI_LINK_TRAIN_400MV_0DB_SNB_A		(0x38<<22)
-#define  FDI_LINK_TRAIN_400MV_6DB_SNB_A		(0x02<<22)
-#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01<<22)
-#define  FDI_LINK_TRAIN_800MV_0DB_SNB_A		(0x0<<22)
+#define  FDI_LINK_TRAIN_400MV_0DB_SNB_A		(0x38 << 22)
+#define  FDI_LINK_TRAIN_400MV_6DB_SNB_A		(0x02 << 22)
+#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01 << 22)
+#define  FDI_LINK_TRAIN_800MV_0DB_SNB_A		(0x0 << 22)
 /* SNB B-stepping */
-#define  FDI_LINK_TRAIN_400MV_0DB_SNB_B		(0x0<<22)
-#define  FDI_LINK_TRAIN_400MV_6DB_SNB_B		(0x3a<<22)
-#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_B	(0x39<<22)
-#define  FDI_LINK_TRAIN_800MV_0DB_SNB_B		(0x38<<22)
-#define  FDI_LINK_TRAIN_VOL_EMP_MASK		(0x3f<<22)
+#define  FDI_LINK_TRAIN_400MV_0DB_SNB_B		(0x0 << 22)
+#define  FDI_LINK_TRAIN_400MV_6DB_SNB_B		(0x3a << 22)
+#define  FDI_LINK_TRAIN_600MV_3_5DB_SNB_B	(0x39 << 22)
+#define  FDI_LINK_TRAIN_800MV_0DB_SNB_B		(0x38 << 22)
+#define  FDI_LINK_TRAIN_VOL_EMP_MASK		(0x3f << 22)
 #define  FDI_DP_PORT_WIDTH_SHIFT		19
 #define  FDI_DP_PORT_WIDTH_MASK			(7 << FDI_DP_PORT_WIDTH_SHIFT)
 #define  FDI_DP_PORT_WIDTH(width)           (((width) - 1) << FDI_DP_PORT_WIDTH_SHIFT)
-#define  FDI_TX_ENHANCE_FRAME_ENABLE    (1<<18)
+#define  FDI_TX_ENHANCE_FRAME_ENABLE    (1 << 18)
 /* Ironlake: hardwired to 1 */
-#define  FDI_TX_PLL_ENABLE              (1<<14)
+#define  FDI_TX_PLL_ENABLE              (1 << 14)
 
 /* Ivybridge has different bits for lolz */
-#define  FDI_LINK_TRAIN_PATTERN_1_IVB       (0<<8)
-#define  FDI_LINK_TRAIN_PATTERN_2_IVB       (1<<8)
-#define  FDI_LINK_TRAIN_PATTERN_IDLE_IVB    (2<<8)
-#define  FDI_LINK_TRAIN_NONE_IVB            (3<<8)
+#define  FDI_LINK_TRAIN_PATTERN_1_IVB       (0 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_2_IVB       (1 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_IDLE_IVB    (2 << 8)
+#define  FDI_LINK_TRAIN_NONE_IVB            (3 << 8)
 
 /* both Tx and Rx */
-#define  FDI_COMPOSITE_SYNC		(1<<11)
-#define  FDI_LINK_TRAIN_AUTO		(1<<10)
-#define  FDI_SCRAMBLING_ENABLE          (0<<7)
-#define  FDI_SCRAMBLING_DISABLE         (1<<7)
+#define  FDI_COMPOSITE_SYNC		(1 << 11)
+#define  FDI_LINK_TRAIN_AUTO		(1 << 10)
+#define  FDI_SCRAMBLING_ENABLE          (0 << 7)
+#define  FDI_SCRAMBLING_DISABLE         (1 << 7)
 
 /* FDI_RX, FDI_X is hard-wired to Transcoder_X */
 #define _FDI_RXA_CTL             0xf000c
 #define _FDI_RXB_CTL             0xf100c
 #define FDI_RX_CTL(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_CTL, _FDI_RXB_CTL)
-#define  FDI_RX_ENABLE          (1<<31)
+#define  FDI_RX_ENABLE          (1 << 31)
 /* train, dp width same as FDI_TX */
-#define  FDI_FS_ERRC_ENABLE		(1<<27)
-#define  FDI_FE_ERRC_ENABLE		(1<<26)
-#define  FDI_RX_POLARITY_REVERSED_LPT	(1<<16)
-#define  FDI_8BPC                       (0<<16)
-#define  FDI_10BPC                      (1<<16)
-#define  FDI_6BPC                       (2<<16)
-#define  FDI_12BPC                      (3<<16)
-#define  FDI_RX_LINK_REVERSAL_OVERRIDE  (1<<15)
-#define  FDI_DMI_LINK_REVERSE_MASK      (1<<14)
-#define  FDI_RX_PLL_ENABLE              (1<<13)
-#define  FDI_FS_ERR_CORRECT_ENABLE      (1<<11)
-#define  FDI_FE_ERR_CORRECT_ENABLE      (1<<10)
-#define  FDI_FS_ERR_REPORT_ENABLE       (1<<9)
-#define  FDI_FE_ERR_REPORT_ENABLE       (1<<8)
-#define  FDI_RX_ENHANCE_FRAME_ENABLE    (1<<6)
-#define  FDI_PCDCLK	                (1<<4)
+#define  FDI_FS_ERRC_ENABLE		(1 << 27)
+#define  FDI_FE_ERRC_ENABLE		(1 << 26)
+#define  FDI_RX_POLARITY_REVERSED_LPT	(1 << 16)
+#define  FDI_8BPC                       (0 << 16)
+#define  FDI_10BPC                      (1 << 16)
+#define  FDI_6BPC                       (2 << 16)
+#define  FDI_12BPC                      (3 << 16)
+#define  FDI_RX_LINK_REVERSAL_OVERRIDE  (1 << 15)
+#define  FDI_DMI_LINK_REVERSE_MASK      (1 << 14)
+#define  FDI_RX_PLL_ENABLE              (1 << 13)
+#define  FDI_FS_ERR_CORRECT_ENABLE      (1 << 11)
+#define  FDI_FE_ERR_CORRECT_ENABLE      (1 << 10)
+#define  FDI_FS_ERR_REPORT_ENABLE       (1 << 9)
+#define  FDI_FE_ERR_REPORT_ENABLE       (1 << 8)
+#define  FDI_RX_ENHANCE_FRAME_ENABLE    (1 << 6)
+#define  FDI_PCDCLK	                (1 << 4)
 /* CPT */
-#define  FDI_AUTO_TRAINING			(1<<10)
-#define  FDI_LINK_TRAIN_PATTERN_1_CPT		(0<<8)
-#define  FDI_LINK_TRAIN_PATTERN_2_CPT		(1<<8)
-#define  FDI_LINK_TRAIN_PATTERN_IDLE_CPT	(2<<8)
-#define  FDI_LINK_TRAIN_NORMAL_CPT		(3<<8)
-#define  FDI_LINK_TRAIN_PATTERN_MASK_CPT	(3<<8)
+#define  FDI_AUTO_TRAINING			(1 << 10)
+#define  FDI_LINK_TRAIN_PATTERN_1_CPT		(0 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_2_CPT		(1 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_IDLE_CPT	(2 << 8)
+#define  FDI_LINK_TRAIN_NORMAL_CPT		(3 << 8)
+#define  FDI_LINK_TRAIN_PATTERN_MASK_CPT	(3 << 8)
 
 #define _FDI_RXA_MISC			0xf0010
 #define _FDI_RXB_MISC			0xf1010
-#define  FDI_RX_PWRDN_LANE1_MASK	(3<<26)
-#define  FDI_RX_PWRDN_LANE1_VAL(x)	((x)<<26)
-#define  FDI_RX_PWRDN_LANE0_MASK	(3<<24)
-#define  FDI_RX_PWRDN_LANE0_VAL(x)	((x)<<24)
-#define  FDI_RX_TP1_TO_TP2_48		(2<<20)
-#define  FDI_RX_TP1_TO_TP2_64		(3<<20)
-#define  FDI_RX_FDI_DELAY_90		(0x90<<0)
+#define  FDI_RX_PWRDN_LANE1_MASK	(3 << 26)
+#define  FDI_RX_PWRDN_LANE1_VAL(x)	((x) << 26)
+#define  FDI_RX_PWRDN_LANE0_MASK	(3 << 24)
+#define  FDI_RX_PWRDN_LANE0_VAL(x)	((x) << 24)
+#define  FDI_RX_TP1_TO_TP2_48		(2 << 20)
+#define  FDI_RX_TP1_TO_TP2_64		(3 << 20)
+#define  FDI_RX_FDI_DELAY_90		(0x90 << 0)
 #define FDI_RX_MISC(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_MISC, _FDI_RXB_MISC)
 
 #define _FDI_RXA_TUSIZE1        0xf0030
@@ -7864,17 +7864,17 @@ enum {
 #define FDI_RX_TUSIZE2(pipe)	_MMIO_PIPE(pipe, _FDI_RXA_TUSIZE2, _FDI_RXB_TUSIZE2)
 
 /* FDI_RX interrupt register format */
-#define FDI_RX_INTER_LANE_ALIGN         (1<<10)
-#define FDI_RX_SYMBOL_LOCK              (1<<9) /* train 2 */
-#define FDI_RX_BIT_LOCK                 (1<<8) /* train 1 */
-#define FDI_RX_TRAIN_PATTERN_2_FAIL     (1<<7)
-#define FDI_RX_FS_CODE_ERR              (1<<6)
-#define FDI_RX_FE_CODE_ERR              (1<<5)
-#define FDI_RX_SYMBOL_ERR_RATE_ABOVE    (1<<4)
-#define FDI_RX_HDCP_LINK_FAIL           (1<<3)
-#define FDI_RX_PIXEL_FIFO_OVERFLOW      (1<<2)
-#define FDI_RX_CROSS_CLOCK_OVERFLOW     (1<<1)
-#define FDI_RX_SYMBOL_QUEUE_OVERFLOW    (1<<0)
+#define FDI_RX_INTER_LANE_ALIGN         (1 << 10)
+#define FDI_RX_SYMBOL_LOCK              (1 << 9) /* train 2 */
+#define FDI_RX_BIT_LOCK                 (1 << 8) /* train 1 */
+#define FDI_RX_TRAIN_PATTERN_2_FAIL     (1 << 7)
+#define FDI_RX_FS_CODE_ERR              (1 << 6)
+#define FDI_RX_FE_CODE_ERR              (1 << 5)
+#define FDI_RX_SYMBOL_ERR_RATE_ABOVE    (1 << 4)
+#define FDI_RX_HDCP_LINK_FAIL           (1 << 3)
+#define FDI_RX_PIXEL_FIFO_OVERFLOW      (1 << 2)
+#define FDI_RX_CROSS_CLOCK_OVERFLOW     (1 << 1)
+#define FDI_RX_SYMBOL_QUEUE_OVERFLOW    (1 << 0)
 
 #define _FDI_RXA_IIR            0xf0014
 #define _FDI_RXA_IMR            0xf0018
@@ -7924,54 +7924,54 @@ enum {
 #define _TRANS_DP_CTL_B		0xe1300
 #define _TRANS_DP_CTL_C		0xe2300
 #define TRANS_DP_CTL(pipe)	_MMIO_PIPE(pipe, _TRANS_DP_CTL_A, _TRANS_DP_CTL_B)
-#define  TRANS_DP_OUTPUT_ENABLE	(1<<31)
+#define  TRANS_DP_OUTPUT_ENABLE	(1 << 31)
 #define  TRANS_DP_PORT_SEL_MASK		(3 << 29)
 #define  TRANS_DP_PORT_SEL_NONE		(3 << 29)
 #define  TRANS_DP_PORT_SEL(port)	(((port) - PORT_B) << 29)
-#define  TRANS_DP_AUDIO_ONLY	(1<<26)
-#define  TRANS_DP_ENH_FRAMING	(1<<18)
-#define  TRANS_DP_8BPC		(0<<9)
-#define  TRANS_DP_10BPC		(1<<9)
-#define  TRANS_DP_6BPC		(2<<9)
-#define  TRANS_DP_12BPC		(3<<9)
-#define  TRANS_DP_BPC_MASK	(3<<9)
-#define  TRANS_DP_VSYNC_ACTIVE_HIGH	(1<<4)
+#define  TRANS_DP_AUDIO_ONLY	(1 << 26)
+#define  TRANS_DP_ENH_FRAMING	(1 << 18)
+#define  TRANS_DP_8BPC		(0 << 9)
+#define  TRANS_DP_10BPC		(1 << 9)
+#define  TRANS_DP_6BPC		(2 << 9)
+#define  TRANS_DP_12BPC		(3 << 9)
+#define  TRANS_DP_BPC_MASK	(3 << 9)
+#define  TRANS_DP_VSYNC_ACTIVE_HIGH	(1 << 4)
 #define  TRANS_DP_VSYNC_ACTIVE_LOW	0
-#define  TRANS_DP_HSYNC_ACTIVE_HIGH	(1<<3)
+#define  TRANS_DP_HSYNC_ACTIVE_HIGH	(1 << 3)
 #define  TRANS_DP_HSYNC_ACTIVE_LOW	0
-#define  TRANS_DP_SYNC_MASK	(3<<3)
+#define  TRANS_DP_SYNC_MASK	(3 << 3)
 
 /* SNB eDP training params */
 /* SNB A-stepping */
-#define  EDP_LINK_TRAIN_400MV_0DB_SNB_A		(0x38<<22)
-#define  EDP_LINK_TRAIN_400MV_6DB_SNB_A		(0x02<<22)
-#define  EDP_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01<<22)
-#define  EDP_LINK_TRAIN_800MV_0DB_SNB_A		(0x0<<22)
+#define  EDP_LINK_TRAIN_400MV_0DB_SNB_A		(0x38 << 22)
+#define  EDP_LINK_TRAIN_400MV_6DB_SNB_A		(0x02 << 22)
+#define  EDP_LINK_TRAIN_600MV_3_5DB_SNB_A	(0x01 << 22)
+#define  EDP_LINK_TRAIN_800MV_0DB_SNB_A		(0x0 << 22)
 /* SNB B-stepping */
-#define  EDP_LINK_TRAIN_400_600MV_0DB_SNB_B	(0x0<<22)
-#define  EDP_LINK_TRAIN_400MV_3_5DB_SNB_B	(0x1<<22)
-#define  EDP_LINK_TRAIN_400_600MV_6DB_SNB_B	(0x3a<<22)
-#define  EDP_LINK_TRAIN_600_800MV_3_5DB_SNB_B	(0x39<<22)
-#define  EDP_LINK_TRAIN_800_1200MV_0DB_SNB_B	(0x38<<22)
-#define  EDP_LINK_TRAIN_VOL_EMP_MASK_SNB	(0x3f<<22)
+#define  EDP_LINK_TRAIN_400_600MV_0DB_SNB_B	(0x0 << 22)
+#define  EDP_LINK_TRAIN_400MV_3_5DB_SNB_B	(0x1 << 22)
+#define  EDP_LINK_TRAIN_400_600MV_6DB_SNB_B	(0x3a << 22)
+#define  EDP_LINK_TRAIN_600_800MV_3_5DB_SNB_B	(0x39 << 22)
+#define  EDP_LINK_TRAIN_800_1200MV_0DB_SNB_B	(0x38 << 22)
+#define  EDP_LINK_TRAIN_VOL_EMP_MASK_SNB	(0x3f << 22)
 
 /* IVB */
-#define EDP_LINK_TRAIN_400MV_0DB_IVB		(0x24 <<22)
-#define EDP_LINK_TRAIN_400MV_3_5DB_IVB		(0x2a <<22)
-#define EDP_LINK_TRAIN_400MV_6DB_IVB		(0x2f <<22)
-#define EDP_LINK_TRAIN_600MV_0DB_IVB		(0x30 <<22)
-#define EDP_LINK_TRAIN_600MV_3_5DB_IVB		(0x36 <<22)
-#define EDP_LINK_TRAIN_800MV_0DB_IVB		(0x38 <<22)
-#define EDP_LINK_TRAIN_800MV_3_5DB_IVB		(0x3e <<22)
+#define EDP_LINK_TRAIN_400MV_0DB_IVB		(0x24 << 22)
+#define EDP_LINK_TRAIN_400MV_3_5DB_IVB		(0x2a << 22)
+#define EDP_LINK_TRAIN_400MV_6DB_IVB		(0x2f << 22)
+#define EDP_LINK_TRAIN_600MV_0DB_IVB		(0x30 << 22)
+#define EDP_LINK_TRAIN_600MV_3_5DB_IVB		(0x36 << 22)
+#define EDP_LINK_TRAIN_800MV_0DB_IVB		(0x38 << 22)
+#define EDP_LINK_TRAIN_800MV_3_5DB_IVB		(0x3e << 22)
 
 /* legacy values */
-#define EDP_LINK_TRAIN_500MV_0DB_IVB		(0x00 <<22)
-#define EDP_LINK_TRAIN_1000MV_0DB_IVB		(0x20 <<22)
-#define EDP_LINK_TRAIN_500MV_3_5DB_IVB		(0x02 <<22)
-#define EDP_LINK_TRAIN_1000MV_3_5DB_IVB		(0x22 <<22)
-#define EDP_LINK_TRAIN_1000MV_6DB_IVB		(0x23 <<22)
+#define EDP_LINK_TRAIN_500MV_0DB_IVB		(0x00 << 22)
+#define EDP_LINK_TRAIN_1000MV_0DB_IVB		(0x20 << 22)
+#define EDP_LINK_TRAIN_500MV_3_5DB_IVB		(0x02 << 22)
+#define EDP_LINK_TRAIN_1000MV_3_5DB_IVB		(0x22 << 22)
+#define EDP_LINK_TRAIN_1000MV_6DB_IVB		(0x23 << 22)
 
-#define  EDP_LINK_TRAIN_VOL_EMP_MASK_IVB	(0x3f<<22)
+#define  EDP_LINK_TRAIN_VOL_EMP_MASK_IVB	(0x3f << 22)
 
 #define  VLV_PMWGICZ				_MMIO(0x1300a4)
 
@@ -8018,7 +8018,7 @@ enum {
 #define   FORCEWAKE_KERNEL_FALLBACK		BIT(15)
 #define  FORCEWAKE_MT_ACK			_MMIO(0x130040)
 #define  ECOBUS					_MMIO(0xa180)
-#define    FORCEWAKE_MT_ENABLE			(1<<5)
+#define    FORCEWAKE_MT_ENABLE			(1 << 5)
 #define  VLV_SPAREG2H				_MMIO(0xA194)
 #define  GEN9_PWRGT_DOMAIN_STATUS		_MMIO(0xA2A0)
 #define   GEN9_PWRGT_MEDIA_STATUS_MASK		(1 << 0)
@@ -8027,13 +8027,13 @@ enum {
 #define  GTFIFODBG				_MMIO(0x120000)
 #define    GT_FIFO_SBDEDICATE_FREE_ENTRY_CHV	(0x1f << 20)
 #define    GT_FIFO_FREE_ENTRIES_CHV		(0x7f << 13)
-#define    GT_FIFO_SBDROPERR			(1<<6)
-#define    GT_FIFO_BLOBDROPERR			(1<<5)
-#define    GT_FIFO_SB_READ_ABORTERR		(1<<4)
-#define    GT_FIFO_DROPERR			(1<<3)
-#define    GT_FIFO_OVFERR			(1<<2)
-#define    GT_FIFO_IAWRERR			(1<<1)
-#define    GT_FIFO_IARDERR			(1<<0)
+#define    GT_FIFO_SBDROPERR			(1 << 6)
+#define    GT_FIFO_BLOBDROPERR			(1 << 5)
+#define    GT_FIFO_SB_READ_ABORTERR		(1 << 4)
+#define    GT_FIFO_DROPERR			(1 << 3)
+#define    GT_FIFO_OVFERR			(1 << 2)
+#define    GT_FIFO_IAWRERR			(1 << 1)
+#define    GT_FIFO_IARDERR			(1 << 0)
 
 #define  GTFIFOCTL				_MMIO(0x120008)
 #define    GT_FIFO_FREE_ENTRIES_MASK		0x7f
@@ -8067,37 +8067,37 @@ enum {
 # define GEN6_OACSUNIT_CLOCK_GATE_DISABLE		(1 << 20)
 
 #define GEN7_UCGCTL4				_MMIO(0x940c)
-#define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1<<25)
-#define  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1<<14)
+#define  GEN7_L3BANK2X_CLOCK_GATE_DISABLE	(1 << 25)
+#define  GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE	(1 << 14)
 
 #define GEN6_RCGCTL1				_MMIO(0x9410)
 #define GEN6_RCGCTL2				_MMIO(0x9414)
 #define GEN6_RSTCTL				_MMIO(0x9420)
 
 #define GEN8_UCGCTL6				_MMIO(0x9430)
-#define   GEN8_GAPSUNIT_CLOCK_GATE_DISABLE	(1<<24)
-#define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1<<14)
-#define   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ (1<<28)
+#define   GEN8_GAPSUNIT_CLOCK_GATE_DISABLE	(1 << 24)
+#define   GEN8_SDEUNIT_CLOCK_GATE_DISABLE	(1 << 14)
+#define   GEN8_HDCUNIT_CLOCK_GATE_DISABLE_HDCREQ (1 << 28)
 
 #define GEN6_GFXPAUSE				_MMIO(0xA000)
 #define GEN6_RPNSWREQ				_MMIO(0xA008)
-#define   GEN6_TURBO_DISABLE			(1<<31)
-#define   GEN6_FREQUENCY(x)			((x)<<25)
-#define   HSW_FREQUENCY(x)			((x)<<24)
-#define   GEN9_FREQUENCY(x)			((x)<<23)
-#define   GEN6_OFFSET(x)			((x)<<19)
-#define   GEN6_AGGRESSIVE_TURBO			(0<<15)
+#define   GEN6_TURBO_DISABLE			(1 << 31)
+#define   GEN6_FREQUENCY(x)			((x) << 25)
+#define   HSW_FREQUENCY(x)			((x) << 24)
+#define   GEN9_FREQUENCY(x)			((x) << 23)
+#define   GEN6_OFFSET(x)			((x) << 19)
+#define   GEN6_AGGRESSIVE_TURBO			(0 << 15)
 #define GEN6_RC_VIDEO_FREQ			_MMIO(0xA00C)
 #define GEN6_RC_CONTROL				_MMIO(0xA090)
-#define   GEN6_RC_CTL_RC6pp_ENABLE		(1<<16)
-#define   GEN6_RC_CTL_RC6p_ENABLE		(1<<17)
-#define   GEN6_RC_CTL_RC6_ENABLE		(1<<18)
-#define   GEN6_RC_CTL_RC1e_ENABLE		(1<<20)
-#define   GEN6_RC_CTL_RC7_ENABLE		(1<<22)
-#define   VLV_RC_CTL_CTX_RST_PARALLEL		(1<<24)
-#define   GEN7_RC_CTL_TO_MODE			(1<<28)
-#define   GEN6_RC_CTL_EI_MODE(x)		((x)<<27)
-#define   GEN6_RC_CTL_HW_ENABLE			(1<<31)
+#define   GEN6_RC_CTL_RC6pp_ENABLE		(1 << 16)
+#define   GEN6_RC_CTL_RC6p_ENABLE		(1 << 17)
+#define   GEN6_RC_CTL_RC6_ENABLE		(1 << 18)
+#define   GEN6_RC_CTL_RC1e_ENABLE		(1 << 20)
+#define   GEN6_RC_CTL_RC7_ENABLE		(1 << 22)
+#define   VLV_RC_CTL_CTX_RST_PARALLEL		(1 << 24)
+#define   GEN7_RC_CTL_TO_MODE			(1 << 28)
+#define   GEN6_RC_CTL_EI_MODE(x)		((x) << 27)
+#define   GEN6_RC_CTL_HW_ENABLE			(1 << 31)
 #define GEN6_RP_DOWN_TIMEOUT			_MMIO(0xA010)
 #define GEN6_RP_INTERRUPT_LIMITS		_MMIO(0xA014)
 #define GEN6_RPSTAT1				_MMIO(0xA01C)
@@ -8108,19 +8108,19 @@ enum {
 #define   HSW_CAGF_MASK				(0x7f << HSW_CAGF_SHIFT)
 #define   GEN9_CAGF_MASK			(0x1ff << GEN9_CAGF_SHIFT)
 #define GEN6_RP_CONTROL				_MMIO(0xA024)
-#define   GEN6_RP_MEDIA_TURBO			(1<<11)
-#define   GEN6_RP_MEDIA_MODE_MASK		(3<<9)
-#define   GEN6_RP_MEDIA_HW_TURBO_MODE		(3<<9)
-#define   GEN6_RP_MEDIA_HW_NORMAL_MODE		(2<<9)
-#define   GEN6_RP_MEDIA_HW_MODE			(1<<9)
-#define   GEN6_RP_MEDIA_SW_MODE			(0<<9)
-#define   GEN6_RP_MEDIA_IS_GFX			(1<<8)
-#define   GEN6_RP_ENABLE			(1<<7)
-#define   GEN6_RP_UP_IDLE_MIN			(0x1<<3)
-#define   GEN6_RP_UP_BUSY_AVG			(0x2<<3)
-#define   GEN6_RP_UP_BUSY_CONT			(0x4<<3)
-#define   GEN6_RP_DOWN_IDLE_AVG			(0x2<<0)
-#define   GEN6_RP_DOWN_IDLE_CONT		(0x1<<0)
+#define   GEN6_RP_MEDIA_TURBO			(1 << 11)
+#define   GEN6_RP_MEDIA_MODE_MASK		(3 << 9)
+#define   GEN6_RP_MEDIA_HW_TURBO_MODE		(3 << 9)
+#define   GEN6_RP_MEDIA_HW_NORMAL_MODE		(2 << 9)
+#define   GEN6_RP_MEDIA_HW_MODE			(1 << 9)
+#define   GEN6_RP_MEDIA_SW_MODE			(0 << 9)
+#define   GEN6_RP_MEDIA_IS_GFX			(1 << 8)
+#define   GEN6_RP_ENABLE			(1 << 7)
+#define   GEN6_RP_UP_IDLE_MIN			(0x1 << 3)
+#define   GEN6_RP_UP_BUSY_AVG			(0x2 << 3)
+#define   GEN6_RP_UP_BUSY_CONT			(0x4 << 3)
+#define   GEN6_RP_DOWN_IDLE_AVG			(0x2 << 0)
+#define   GEN6_RP_DOWN_IDLE_CONT		(0x1 << 0)
 #define GEN6_RP_UP_THRESHOLD			_MMIO(0xA02C)
 #define GEN6_RP_DOWN_THRESHOLD			_MMIO(0xA030)
 #define GEN6_RP_CUR_UP_EI			_MMIO(0xA050)
@@ -8156,15 +8156,15 @@ enum {
 #define VLV_RCEDATA				_MMIO(0xA0BC)
 #define GEN6_RC6pp_THRESHOLD			_MMIO(0xA0C0)
 #define GEN6_PMINTRMSK				_MMIO(0xA168)
-#define   GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC	(1<<31)
-#define   ARAT_EXPIRED_INTRMSK			(1<<9)
+#define   GEN8_PMINTR_DISABLE_REDIRECT_TO_GUC	(1 << 31)
+#define   ARAT_EXPIRED_INTRMSK			(1 << 9)
 #define GEN8_MISC_CTRL0				_MMIO(0xA180)
 #define VLV_PWRDWNUPCTL				_MMIO(0xA294)
 #define GEN9_MEDIA_PG_IDLE_HYSTERESIS		_MMIO(0xA0C4)
 #define GEN9_RENDER_PG_IDLE_HYSTERESIS		_MMIO(0xA0C8)
 #define GEN9_PG_ENABLE				_MMIO(0xA210)
-#define GEN9_RENDER_PG_ENABLE			(1<<0)
-#define GEN9_MEDIA_PG_ENABLE			(1<<1)
+#define GEN9_RENDER_PG_ENABLE			(1 << 0)
+#define GEN9_MEDIA_PG_ENABLE			(1 << 1)
 #define GEN8_PUSHBUS_CONTROL			_MMIO(0xA248)
 #define GEN8_PUSHBUS_ENABLE			_MMIO(0xA250)
 #define GEN8_PUSHBUS_SHIFT			_MMIO(0xA25C)
@@ -8177,13 +8177,13 @@ enum {
 #define GEN6_PMIMR				_MMIO(0x44024) /* rps_lock */
 #define GEN6_PMIIR				_MMIO(0x44028)
 #define GEN6_PMIER				_MMIO(0x4402C)
-#define  GEN6_PM_MBOX_EVENT			(1<<25)
-#define  GEN6_PM_THERMAL_EVENT			(1<<24)
-#define  GEN6_PM_RP_DOWN_TIMEOUT		(1<<6)
-#define  GEN6_PM_RP_UP_THRESHOLD		(1<<5)
-#define  GEN6_PM_RP_DOWN_THRESHOLD		(1<<4)
-#define  GEN6_PM_RP_UP_EI_EXPIRED		(1<<2)
-#define  GEN6_PM_RP_DOWN_EI_EXPIRED		(1<<1)
+#define  GEN6_PM_MBOX_EVENT			(1 << 25)
+#define  GEN6_PM_THERMAL_EVENT			(1 << 24)
+#define  GEN6_PM_RP_DOWN_TIMEOUT		(1 << 6)
+#define  GEN6_PM_RP_UP_THRESHOLD		(1 << 5)
+#define  GEN6_PM_RP_DOWN_THRESHOLD		(1 << 4)
+#define  GEN6_PM_RP_UP_EI_EXPIRED		(1 << 2)
+#define  GEN6_PM_RP_DOWN_EI_EXPIRED		(1 << 1)
 #define  GEN6_PM_RPS_EVENTS			(GEN6_PM_RP_UP_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_THRESHOLD | \
 						 GEN6_PM_RP_DOWN_TIMEOUT)
@@ -8192,16 +8192,16 @@ enum {
 #define GEN7_GT_SCRATCH_REG_NUM			8
 
 #define VLV_GTLC_SURVIVABILITY_REG              _MMIO(0x130098)
-#define VLV_GFX_CLK_STATUS_BIT			(1<<3)
-#define VLV_GFX_CLK_FORCE_ON_BIT		(1<<2)
+#define VLV_GFX_CLK_STATUS_BIT			(1 << 3)
+#define VLV_GFX_CLK_FORCE_ON_BIT		(1 << 2)
 
 #define GEN6_GT_GFX_RC6_LOCKED			_MMIO(0x138104)
 #define VLV_COUNTER_CONTROL			_MMIO(0x138104)
-#define   VLV_COUNT_RANGE_HIGH			(1<<15)
-#define   VLV_MEDIA_RC0_COUNT_EN		(1<<5)
-#define   VLV_RENDER_RC0_COUNT_EN		(1<<4)
-#define   VLV_MEDIA_RC6_COUNT_EN		(1<<1)
-#define   VLV_RENDER_RC6_COUNT_EN		(1<<0)
+#define   VLV_COUNT_RANGE_HIGH			(1 << 15)
+#define   VLV_MEDIA_RC0_COUNT_EN		(1 << 5)
+#define   VLV_RENDER_RC0_COUNT_EN		(1 << 4)
+#define   VLV_MEDIA_RC6_COUNT_EN		(1 << 1)
+#define   VLV_RENDER_RC6_COUNT_EN		(1 << 0)
 #define GEN6_GT_GFX_RC6				_MMIO(0x138108)
 #define VLV_GT_RENDER_RC6			_MMIO(0x138108)
 #define VLV_GT_MEDIA_RC6			_MMIO(0x13810C)
@@ -8212,7 +8212,7 @@ enum {
 #define VLV_MEDIA_C0_COUNT			_MMIO(0x13811C)
 
 #define GEN6_PCODE_MAILBOX			_MMIO(0x138124)
-#define   GEN6_PCODE_READY			(1<<31)
+#define   GEN6_PCODE_READY			(1 << 31)
 #define   GEN6_PCODE_ERROR_MASK			0xFF
 #define     GEN6_PCODE_SUCCESS			0x0
 #define     GEN6_PCODE_ILLEGAL_CMD		0x1
@@ -8256,7 +8256,7 @@ enum {
 #define GEN6_PCODE_DATA1			_MMIO(0x13812C)
 
 #define GEN6_GT_CORE_STATUS		_MMIO(0x138060)
-#define   GEN6_CORE_CPD_STATE_MASK	(7<<4)
+#define   GEN6_CORE_CPD_STATE_MASK	(7 << 4)
 #define   GEN6_RCn_MASK			7
 #define   GEN6_RC0			0
 #define   GEN6_RC3			2
@@ -8268,26 +8268,26 @@ enum {
 
 #define CHV_POWER_SS0_SIG1		_MMIO(0xa720)
 #define CHV_POWER_SS1_SIG1		_MMIO(0xa728)
-#define   CHV_SS_PG_ENABLE		(1<<1)
-#define   CHV_EU08_PG_ENABLE		(1<<9)
-#define   CHV_EU19_PG_ENABLE		(1<<17)
-#define   CHV_EU210_PG_ENABLE		(1<<25)
+#define   CHV_SS_PG_ENABLE		(1 << 1)
+#define   CHV_EU08_PG_ENABLE		(1 << 9)
+#define   CHV_EU19_PG_ENABLE		(1 << 17)
+#define   CHV_EU210_PG_ENABLE		(1 << 25)
 
 #define CHV_POWER_SS0_SIG2		_MMIO(0xa724)
 #define CHV_POWER_SS1_SIG2		_MMIO(0xa72c)
-#define   CHV_EU311_PG_ENABLE		(1<<1)
+#define   CHV_EU311_PG_ENABLE		(1 << 1)
 
-#define GEN9_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + (slice)*0x4)
+#define GEN9_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + (slice) * 0x4)
 #define GEN10_SLICE_PGCTL_ACK(slice)	_MMIO(0x804c + ((slice) / 3) * 0x34 + \
 					      ((slice) % 3) * 0x4)
 #define   GEN9_PGCTL_SLICE_ACK		(1 << 0)
-#define   GEN9_PGCTL_SS_ACK(subslice)	(1 << (2 + (subslice)*2))
+#define   GEN9_PGCTL_SS_ACK(subslice)	(1 << (2 + (subslice) * 2))
 #define   GEN10_PGCTL_VALID_SS_MASK(slice) ((slice) == 0 ? 0x7F : 0x1F)
 
-#define GEN9_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + (slice)*0x8)
+#define GEN9_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + (slice) * 0x8)
 #define GEN10_SS01_EU_PGCTL_ACK(slice)	_MMIO(0x805c + ((slice) / 3) * 0x30 + \
 					      ((slice) % 3) * 0x8)
-#define GEN9_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + (slice)*0x8)
+#define GEN9_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + (slice) * 0x8)
 #define GEN10_SS23_EU_PGCTL_ACK(slice)	_MMIO(0x8060 + ((slice) / 3) * 0x30 + \
 					      ((slice) % 3) * 0x8)
 #define   GEN9_PGCTL_SSA_EU08_ACK	(1 << 0)
@@ -8300,10 +8300,10 @@ enum {
 #define   GEN9_PGCTL_SSB_EU311_ACK	(1 << 14)
 
 #define GEN7_MISCCPCTL				_MMIO(0x9424)
-#define   GEN7_DOP_CLOCK_GATE_ENABLE		(1<<0)
-#define   GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE	(1<<2)
-#define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1<<4)
-#define   GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE     (1<<6)
+#define   GEN7_DOP_CLOCK_GATE_ENABLE		(1 << 0)
+#define   GEN8_DOP_CLOCK_GATE_CFCLK_ENABLE	(1 << 2)
+#define   GEN8_DOP_CLOCK_GATE_GUC_ENABLE	(1 << 4)
+#define   GEN8_DOP_CLOCK_GATE_MEDIA_ENABLE     (1 << 6)
 
 #define GEN8_GARBCNTL				_MMIO(0xB004)
 #define   GEN9_GAPS_TSV_CREDIT_DISABLE		(1 << 7)
@@ -8332,38 +8332,38 @@ enum {
 
 /* IVYBRIDGE DPF */
 #define GEN7_L3CDERRST1(slice)		_MMIO(0xB008 + (slice) * 0x200) /* L3CD Error Status 1 */
-#define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff<<14)
-#define   GEN7_PARITY_ERROR_VALID	(1<<13)
-#define   GEN7_L3CDERRST1_BANK_MASK	(3<<11)
-#define   GEN7_L3CDERRST1_SUBBANK_MASK	(7<<8)
+#define   GEN7_L3CDERRST1_ROW_MASK	(0x7ff << 14)
+#define   GEN7_PARITY_ERROR_VALID	(1 << 13)
+#define   GEN7_L3CDERRST1_BANK_MASK	(3 << 11)
+#define   GEN7_L3CDERRST1_SUBBANK_MASK	(7 << 8)
 #define GEN7_PARITY_ERROR_ROW(reg) \
 		((reg & GEN7_L3CDERRST1_ROW_MASK) >> 14)
 #define GEN7_PARITY_ERROR_BANK(reg) \
 		((reg & GEN7_L3CDERRST1_BANK_MASK) >> 11)
 #define GEN7_PARITY_ERROR_SUBBANK(reg) \
 		((reg & GEN7_L3CDERRST1_SUBBANK_MASK) >> 8)
-#define   GEN7_L3CDERRST1_ENABLE	(1<<7)
+#define   GEN7_L3CDERRST1_ENABLE	(1 << 7)
 
 #define GEN7_L3LOG(slice, i)		_MMIO(0xB070 + (slice) * 0x200 + (i) * 4)
 #define GEN7_L3LOG_SIZE			0x80
 
 #define GEN7_HALF_SLICE_CHICKEN1	_MMIO(0xe100) /* IVB GT1 + VLV */
 #define GEN7_HALF_SLICE_CHICKEN1_GT2	_MMIO(0xf100)
-#define   GEN7_MAX_PS_THREAD_DEP		(8<<12)
-#define   GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE	(1<<10)
-#define   GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE	(1<<4)
-#define   GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE	(1<<3)
+#define   GEN7_MAX_PS_THREAD_DEP		(8 << 12)
+#define   GEN7_SINGLE_SUBSCAN_DISPATCH_ENABLE	(1 << 10)
+#define   GEN7_SBE_SS_CACHE_DISPATCH_PORT_SHARING_DISABLE	(1 << 4)
+#define   GEN7_PSD_SINGLE_PORT_DISPATCH_ENABLE	(1 << 3)
 
 #define GEN9_HALF_SLICE_CHICKEN5	_MMIO(0xe188)
-#define   GEN9_DG_MIRROR_FIX_ENABLE	(1<<5)
-#define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1<<3)
+#define   GEN9_DG_MIRROR_FIX_ENABLE	(1 << 5)
+#define   GEN9_CCS_TLB_PREFETCH_ENABLE	(1 << 3)
 
 #define GEN8_ROW_CHICKEN		_MMIO(0xe4f0)
-#define   FLOW_CONTROL_ENABLE		(1<<15)
-#define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1<<8)
-#define   STALL_DOP_GATING_DISABLE		(1<<5)
-#define   THROTTLE_12_5				(7<<2)
-#define   DISABLE_EARLY_EOT			(1<<1)
+#define   FLOW_CONTROL_ENABLE		(1 << 15)
+#define   PARTIAL_INSTRUCTION_SHOOTDOWN_DISABLE	(1 << 8)
+#define   STALL_DOP_GATING_DISABLE		(1 << 5)
+#define   THROTTLE_12_5				(7 << 2)
+#define   DISABLE_EARLY_EOT			(1 << 1)
 
 #define GEN7_ROW_CHICKEN2		_MMIO(0xe4f4)
 #define GEN7_ROW_CHICKEN2_GT2		_MMIO(0xf4f4)
@@ -8375,19 +8375,19 @@ enum {
 #define  HSW_ROW_CHICKEN3_L3_GLOBAL_ATOMICS_DISABLE    (1 << 6)
 
 #define HALF_SLICE_CHICKEN2		_MMIO(0xe180)
-#define   GEN8_ST_PO_DISABLE		(1<<13)
+#define   GEN8_ST_PO_DISABLE		(1 << 13)
 
 #define HALF_SLICE_CHICKEN3		_MMIO(0xe184)
-#define   HSW_SAMPLE_C_PERFORMANCE	(1<<9)
-#define   GEN8_CENTROID_PIXEL_OPT_DIS	(1<<8)
-#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1<<5)
-#define   CNL_FAST_ANISO_L1_BANKING_FIX	(1<<4)
-#define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1<<1)
+#define   HSW_SAMPLE_C_PERFORMANCE	(1 << 9)
+#define   GEN8_CENTROID_PIXEL_OPT_DIS	(1 << 8)
+#define   GEN9_DISABLE_OCL_OOB_SUPPRESS_LOGIC	(1 << 5)
+#define   CNL_FAST_ANISO_L1_BANKING_FIX	(1 << 4)
+#define   GEN8_SAMPLER_POWER_BYPASS_DIS	(1 << 1)
 
 #define GEN9_HALF_SLICE_CHICKEN7	_MMIO(0xe194)
-#define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	(1<<8)
-#define   GEN9_ENABLE_YV12_BUGFIX	(1<<4)
-#define   GEN9_ENABLE_GPGPU_PREEMPTION	(1<<2)
+#define   GEN9_SAMPLER_HASH_COMPRESSED_READ_ADDR	(1 << 8)
+#define   GEN9_ENABLE_YV12_BUGFIX	(1 << 4)
+#define   GEN9_ENABLE_GPGPU_PREEMPTION	(1 << 2)
 
 /* Audio */
 #define G4X_AUD_VID_DID			_MMIO(dev_priv->info.display_mmio_offset + 0x62020)
@@ -8540,9 +8540,9 @@ enum {
 #define   HSW_PWR_WELL_CTL_REQ(pw)		(1 << (_HSW_PW_SHIFT(pw) + 1))
 #define   HSW_PWR_WELL_CTL_STATE(pw)		(1 << _HSW_PW_SHIFT(pw))
 #define HSW_PWR_WELL_CTL5			_MMIO(0x45410)
-#define   HSW_PWR_WELL_ENABLE_SINGLE_STEP	(1<<31)
-#define   HSW_PWR_WELL_PWR_GATE_OVERRIDE	(1<<20)
-#define   HSW_PWR_WELL_FORCE_ON			(1<<19)
+#define   HSW_PWR_WELL_ENABLE_SINGLE_STEP	(1 << 31)
+#define   HSW_PWR_WELL_PWR_GATE_OVERRIDE	(1 << 20)
+#define   HSW_PWR_WELL_FORCE_ON			(1 << 19)
 #define HSW_PWR_WELL_CTL6			_MMIO(0x45414)
 
 /* SKL Fuse Status */
@@ -8553,7 +8553,7 @@ enum skl_power_gate {
 };
 
 #define SKL_FUSE_STATUS				_MMIO(0x42000)
-#define  SKL_FUSE_DOWNLOAD_STATUS		(1<<31)
+#define  SKL_FUSE_DOWNLOAD_STATUS		(1 << 31)
 /* PG0 (HW control->no power well ID), PG1..PG2 (SKL_DISP_PW1..SKL_DISP_PW2) */
 #define  SKL_PW_TO_PG(pw)			((pw) - SKL_DISP_PW_1 + SKL_PG1)
 #define  SKL_FUSE_PG_DIST_STATUS(pg)		(1 << (27 - (pg)))
@@ -8568,8 +8568,8 @@ enum skl_power_gate {
 						    _CNL_AUX_ANAOVRD1_C, \
 						    _CNL_AUX_ANAOVRD1_D, \
 						    _CNL_AUX_ANAOVRD1_F))
-#define   CNL_AUX_ANAOVRD1_ENABLE	(1<<16)
-#define   CNL_AUX_ANAOVRD1_LDO_BYPASS	(1<<23)
+#define   CNL_AUX_ANAOVRD1_ENABLE	(1 << 16)
+#define   CNL_AUX_ANAOVRD1_LDO_BYPASS	(1 << 23)
 
 /* HDCP Key Registers */
 #define HDCP_KEY_CONF			_MMIO(0x66c00)
@@ -8660,37 +8660,37 @@ enum skl_power_gate {
 #define _TRANS_DDI_FUNC_CTL_EDP		0x6F400
 #define TRANS_DDI_FUNC_CTL(tran) _MMIO_TRANS2(tran, _TRANS_DDI_FUNC_CTL_A)
 
-#define  TRANS_DDI_FUNC_ENABLE		(1<<31)
+#define  TRANS_DDI_FUNC_ENABLE		(1 << 31)
 /* Those bits are ignored by pipe EDP since it can only connect to DDI A */
-#define  TRANS_DDI_PORT_MASK		(7<<28)
+#define  TRANS_DDI_PORT_MASK		(7 << 28)
 #define  TRANS_DDI_PORT_SHIFT		28
-#define  TRANS_DDI_SELECT_PORT(x)	((x)<<28)
-#define  TRANS_DDI_PORT_NONE		(0<<28)
-#define  TRANS_DDI_MODE_SELECT_MASK	(7<<24)
-#define  TRANS_DDI_MODE_SELECT_HDMI	(0<<24)
-#define  TRANS_DDI_MODE_SELECT_DVI	(1<<24)
-#define  TRANS_DDI_MODE_SELECT_DP_SST	(2<<24)
-#define  TRANS_DDI_MODE_SELECT_DP_MST	(3<<24)
-#define  TRANS_DDI_MODE_SELECT_FDI	(4<<24)
-#define  TRANS_DDI_BPC_MASK		(7<<20)
-#define  TRANS_DDI_BPC_8		(0<<20)
-#define  TRANS_DDI_BPC_10		(1<<20)
-#define  TRANS_DDI_BPC_6		(2<<20)
-#define  TRANS_DDI_BPC_12		(3<<20)
-#define  TRANS_DDI_PVSYNC		(1<<17)
-#define  TRANS_DDI_PHSYNC		(1<<16)
-#define  TRANS_DDI_EDP_INPUT_MASK	(7<<12)
-#define  TRANS_DDI_EDP_INPUT_A_ON	(0<<12)
-#define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4<<12)
-#define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5<<12)
-#define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6<<12)
-#define  TRANS_DDI_HDCP_SIGNALLING	(1<<9)
-#define  TRANS_DDI_DP_VC_PAYLOAD_ALLOC	(1<<8)
-#define  TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE (1<<7)
-#define  TRANS_DDI_HDMI_SCRAMBLER_RESET_FREQ (1<<6)
-#define  TRANS_DDI_BFI_ENABLE		(1<<4)
-#define  TRANS_DDI_HIGH_TMDS_CHAR_RATE	(1<<4)
-#define  TRANS_DDI_HDMI_SCRAMBLING	(1<<0)
+#define  TRANS_DDI_SELECT_PORT(x)	((x) << 28)
+#define  TRANS_DDI_PORT_NONE		(0 << 28)
+#define  TRANS_DDI_MODE_SELECT_MASK	(7 << 24)
+#define  TRANS_DDI_MODE_SELECT_HDMI	(0 << 24)
+#define  TRANS_DDI_MODE_SELECT_DVI	(1 << 24)
+#define  TRANS_DDI_MODE_SELECT_DP_SST	(2 << 24)
+#define  TRANS_DDI_MODE_SELECT_DP_MST	(3 << 24)
+#define  TRANS_DDI_MODE_SELECT_FDI	(4 << 24)
+#define  TRANS_DDI_BPC_MASK		(7 << 20)
+#define  TRANS_DDI_BPC_8		(0 << 20)
+#define  TRANS_DDI_BPC_10		(1 << 20)
+#define  TRANS_DDI_BPC_6		(2 << 20)
+#define  TRANS_DDI_BPC_12		(3 << 20)
+#define  TRANS_DDI_PVSYNC		(1 << 17)
+#define  TRANS_DDI_PHSYNC		(1 << 16)
+#define  TRANS_DDI_EDP_INPUT_MASK	(7 << 12)
+#define  TRANS_DDI_EDP_INPUT_A_ON	(0 << 12)
+#define  TRANS_DDI_EDP_INPUT_A_ONOFF	(4 << 12)
+#define  TRANS_DDI_EDP_INPUT_B_ONOFF	(5 << 12)
+#define  TRANS_DDI_EDP_INPUT_C_ONOFF	(6 << 12)
+#define  TRANS_DDI_HDCP_SIGNALLING	(1 << 9)
+#define  TRANS_DDI_DP_VC_PAYLOAD_ALLOC	(1 << 8)
+#define  TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE (1 << 7)
+#define  TRANS_DDI_HDMI_SCRAMBLER_RESET_FREQ (1 << 6)
+#define  TRANS_DDI_BFI_ENABLE		(1 << 4)
+#define  TRANS_DDI_HIGH_TMDS_CHAR_RATE	(1 << 4)
+#define  TRANS_DDI_HDMI_SCRAMBLING	(1 << 0)
 #define  TRANS_DDI_HDMI_SCRAMBLING_MASK (TRANS_DDI_HDMI_SCRAMBLER_CTS_ENABLE \
 					| TRANS_DDI_HDMI_SCRAMBLER_RESET_FREQ \
 					| TRANS_DDI_HDMI_SCRAMBLING)
@@ -8699,29 +8699,29 @@ enum skl_power_gate {
 #define _DP_TP_CTL_A			0x64040
 #define _DP_TP_CTL_B			0x64140
 #define DP_TP_CTL(port) _MMIO_PORT(port, _DP_TP_CTL_A, _DP_TP_CTL_B)
-#define  DP_TP_CTL_ENABLE			(1<<31)
-#define  DP_TP_CTL_MODE_SST			(0<<27)
-#define  DP_TP_CTL_MODE_MST			(1<<27)
-#define  DP_TP_CTL_FORCE_ACT			(1<<25)
-#define  DP_TP_CTL_ENHANCED_FRAME_ENABLE	(1<<18)
-#define  DP_TP_CTL_FDI_AUTOTRAIN		(1<<15)
-#define  DP_TP_CTL_LINK_TRAIN_MASK		(7<<8)
-#define  DP_TP_CTL_LINK_TRAIN_PAT1		(0<<8)
-#define  DP_TP_CTL_LINK_TRAIN_PAT2		(1<<8)
-#define  DP_TP_CTL_LINK_TRAIN_PAT3		(4<<8)
-#define  DP_TP_CTL_LINK_TRAIN_PAT4		(5<<8)
-#define  DP_TP_CTL_LINK_TRAIN_IDLE		(2<<8)
-#define  DP_TP_CTL_LINK_TRAIN_NORMAL		(3<<8)
-#define  DP_TP_CTL_SCRAMBLE_DISABLE		(1<<7)
+#define  DP_TP_CTL_ENABLE			(1 << 31)
+#define  DP_TP_CTL_MODE_SST			(0 << 27)
+#define  DP_TP_CTL_MODE_MST			(1 << 27)
+#define  DP_TP_CTL_FORCE_ACT			(1 << 25)
+#define  DP_TP_CTL_ENHANCED_FRAME_ENABLE	(1 << 18)
+#define  DP_TP_CTL_FDI_AUTOTRAIN		(1 << 15)
+#define  DP_TP_CTL_LINK_TRAIN_MASK		(7 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT1		(0 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT2		(1 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT3		(4 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_PAT4		(5 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_IDLE		(2 << 8)
+#define  DP_TP_CTL_LINK_TRAIN_NORMAL		(3 << 8)
+#define  DP_TP_CTL_SCRAMBLE_DISABLE		(1 << 7)
 
 /* DisplayPort Transport Status */
 #define _DP_TP_STATUS_A			0x64044
 #define _DP_TP_STATUS_B			0x64144
 #define DP_TP_STATUS(port) _MMIO_PORT(port, _DP_TP_STATUS_A, _DP_TP_STATUS_B)
-#define  DP_TP_STATUS_IDLE_DONE			(1<<25)
-#define  DP_TP_STATUS_ACT_SENT			(1<<24)
-#define  DP_TP_STATUS_MODE_STATUS_MST		(1<<23)
-#define  DP_TP_STATUS_AUTOTRAIN_DONE		(1<<12)
+#define  DP_TP_STATUS_IDLE_DONE			(1 << 25)
+#define  DP_TP_STATUS_ACT_SENT			(1 << 24)
+#define  DP_TP_STATUS_MODE_STATUS_MST		(1 << 23)
+#define  DP_TP_STATUS_AUTOTRAIN_DONE		(1 << 12)
 #define  DP_TP_STATUS_PAYLOAD_MAPPING_VC2	(3 << 8)
 #define  DP_TP_STATUS_PAYLOAD_MAPPING_VC1	(3 << 4)
 #define  DP_TP_STATUS_PAYLOAD_MAPPING_VC0	(3 << 0)
@@ -8730,16 +8730,16 @@ enum skl_power_gate {
 #define _DDI_BUF_CTL_A				0x64000
 #define _DDI_BUF_CTL_B				0x64100
 #define DDI_BUF_CTL(port) _MMIO_PORT(port, _DDI_BUF_CTL_A, _DDI_BUF_CTL_B)
-#define  DDI_BUF_CTL_ENABLE			(1<<31)
+#define  DDI_BUF_CTL_ENABLE			(1 << 31)
 #define  DDI_BUF_TRANS_SELECT(n)	((n) << 24)
-#define  DDI_BUF_EMP_MASK			(0xf<<24)
-#define  DDI_BUF_PORT_REVERSAL			(1<<16)
-#define  DDI_BUF_IS_IDLE			(1<<7)
-#define  DDI_A_4_LANES				(1<<4)
+#define  DDI_BUF_EMP_MASK			(0xf << 24)
+#define  DDI_BUF_PORT_REVERSAL			(1 << 16)
+#define  DDI_BUF_IS_IDLE			(1 << 7)
+#define  DDI_A_4_LANES				(1 << 4)
 #define  DDI_PORT_WIDTH(width)			(((width) - 1) << 1)
 #define  DDI_PORT_WIDTH_MASK			(7 << 1)
 #define  DDI_PORT_WIDTH_SHIFT			1
-#define  DDI_INIT_DISPLAY_DETECTED		(1<<0)
+#define  DDI_INIT_DISPLAY_DETECTED		(1 << 0)
 
 /* DDI Buffer Translations */
 #define _DDI_BUF_TRANS_A		0x64E00
@@ -8754,90 +8754,90 @@ enum skl_power_gate {
 #define SBI_ADDR			_MMIO(0xC6000)
 #define SBI_DATA			_MMIO(0xC6004)
 #define SBI_CTL_STAT			_MMIO(0xC6008)
-#define  SBI_CTL_DEST_ICLK		(0x0<<16)
-#define  SBI_CTL_DEST_MPHY		(0x1<<16)
-#define  SBI_CTL_OP_IORD		(0x2<<8)
-#define  SBI_CTL_OP_IOWR		(0x3<<8)
-#define  SBI_CTL_OP_CRRD		(0x6<<8)
-#define  SBI_CTL_OP_CRWR		(0x7<<8)
-#define  SBI_RESPONSE_FAIL		(0x1<<1)
-#define  SBI_RESPONSE_SUCCESS		(0x0<<1)
-#define  SBI_BUSY			(0x1<<0)
-#define  SBI_READY			(0x0<<0)
+#define  SBI_CTL_DEST_ICLK		(0x0 << 16)
+#define  SBI_CTL_DEST_MPHY		(0x1 << 16)
+#define  SBI_CTL_OP_IORD		(0x2 << 8)
+#define  SBI_CTL_OP_IOWR		(0x3 << 8)
+#define  SBI_CTL_OP_CRRD		(0x6 << 8)
+#define  SBI_CTL_OP_CRWR		(0x7 << 8)
+#define  SBI_RESPONSE_FAIL		(0x1 << 1)
+#define  SBI_RESPONSE_SUCCESS		(0x0 << 1)
+#define  SBI_BUSY			(0x1 << 0)
+#define  SBI_READY			(0x0 << 0)
 
 /* SBI offsets */
 #define  SBI_SSCDIVINTPHASE			0x0200
 #define  SBI_SSCDIVINTPHASE6			0x0600
 #define   SBI_SSCDIVINTPHASE_DIVSEL_SHIFT	1
-#define   SBI_SSCDIVINTPHASE_DIVSEL_MASK	(0x7f<<1)
-#define   SBI_SSCDIVINTPHASE_DIVSEL(x)		((x)<<1)
+#define   SBI_SSCDIVINTPHASE_DIVSEL_MASK	(0x7f << 1)
+#define   SBI_SSCDIVINTPHASE_DIVSEL(x)		((x) << 1)
 #define   SBI_SSCDIVINTPHASE_INCVAL_SHIFT	8
-#define   SBI_SSCDIVINTPHASE_INCVAL_MASK	(0x7f<<8)
-#define   SBI_SSCDIVINTPHASE_INCVAL(x)		((x)<<8)
-#define   SBI_SSCDIVINTPHASE_DIR(x)		((x)<<15)
-#define   SBI_SSCDIVINTPHASE_PROPAGATE		(1<<0)
+#define   SBI_SSCDIVINTPHASE_INCVAL_MASK	(0x7f << 8)
+#define   SBI_SSCDIVINTPHASE_INCVAL(x)		((x) << 8)
+#define   SBI_SSCDIVINTPHASE_DIR(x)		((x) << 15)
+#define   SBI_SSCDIVINTPHASE_PROPAGATE		(1 << 0)
 #define  SBI_SSCDITHPHASE			0x0204
 #define  SBI_SSCCTL				0x020c
 #define  SBI_SSCCTL6				0x060C
-#define   SBI_SSCCTL_PATHALT			(1<<3)
-#define   SBI_SSCCTL_DISABLE			(1<<0)
+#define   SBI_SSCCTL_PATHALT			(1 << 3)
+#define   SBI_SSCCTL_DISABLE			(1 << 0)
 #define  SBI_SSCAUXDIV6				0x0610
 #define   SBI_SSCAUXDIV_FINALDIV2SEL_SHIFT	4
-#define   SBI_SSCAUXDIV_FINALDIV2SEL_MASK	(1<<4)
-#define   SBI_SSCAUXDIV_FINALDIV2SEL(x)		((x)<<4)
+#define   SBI_SSCAUXDIV_FINALDIV2SEL_MASK	(1 << 4)
+#define   SBI_SSCAUXDIV_FINALDIV2SEL(x)		((x) << 4)
 #define  SBI_DBUFF0				0x2a00
 #define  SBI_GEN0				0x1f00
-#define   SBI_GEN0_CFG_BUFFENABLE_DISABLE	(1<<0)
+#define   SBI_GEN0_CFG_BUFFENABLE_DISABLE	(1 << 0)
 
 /* LPT PIXCLK_GATE */
 #define PIXCLK_GATE			_MMIO(0xC6020)
-#define  PIXCLK_GATE_UNGATE		(1<<0)
-#define  PIXCLK_GATE_GATE		(0<<0)
+#define  PIXCLK_GATE_UNGATE		(1 << 0)
+#define  PIXCLK_GATE_GATE		(0 << 0)
 
 /* SPLL */
 #define SPLL_CTL			_MMIO(0x46020)
-#define  SPLL_PLL_ENABLE		(1<<31)
-#define  SPLL_PLL_SSC			(1<<28)
-#define  SPLL_PLL_NON_SSC		(2<<28)
-#define  SPLL_PLL_LCPLL			(3<<28)
-#define  SPLL_PLL_REF_MASK		(3<<28)
-#define  SPLL_PLL_FREQ_810MHz		(0<<26)
-#define  SPLL_PLL_FREQ_1350MHz		(1<<26)
-#define  SPLL_PLL_FREQ_2700MHz		(2<<26)
-#define  SPLL_PLL_FREQ_MASK		(3<<26)
+#define  SPLL_PLL_ENABLE		(1 << 31)
+#define  SPLL_PLL_SSC			(1 << 28)
+#define  SPLL_PLL_NON_SSC		(2 << 28)
+#define  SPLL_PLL_LCPLL			(3 << 28)
+#define  SPLL_PLL_REF_MASK		(3 << 28)
+#define  SPLL_PLL_FREQ_810MHz		(0 << 26)
+#define  SPLL_PLL_FREQ_1350MHz		(1 << 26)
+#define  SPLL_PLL_FREQ_2700MHz		(2 << 26)
+#define  SPLL_PLL_FREQ_MASK		(3 << 26)
 
 /* WRPLL */
 #define _WRPLL_CTL1			0x46040
 #define _WRPLL_CTL2			0x46060
 #define WRPLL_CTL(pll)			_MMIO_PIPE(pll, _WRPLL_CTL1, _WRPLL_CTL2)
-#define  WRPLL_PLL_ENABLE		(1<<31)
-#define  WRPLL_PLL_SSC			(1<<28)
-#define  WRPLL_PLL_NON_SSC		(2<<28)
-#define  WRPLL_PLL_LCPLL		(3<<28)
-#define  WRPLL_PLL_REF_MASK		(3<<28)
+#define  WRPLL_PLL_ENABLE		(1 << 31)
+#define  WRPLL_PLL_SSC			(1 << 28)
+#define  WRPLL_PLL_NON_SSC		(2 << 28)
+#define  WRPLL_PLL_LCPLL		(3 << 28)
+#define  WRPLL_PLL_REF_MASK		(3 << 28)
 /* WRPLL divider programming */
-#define  WRPLL_DIVIDER_REFERENCE(x)	((x)<<0)
+#define  WRPLL_DIVIDER_REFERENCE(x)	((x) << 0)
 #define  WRPLL_DIVIDER_REF_MASK		(0xff)
-#define  WRPLL_DIVIDER_POST(x)		((x)<<8)
-#define  WRPLL_DIVIDER_POST_MASK	(0x3f<<8)
+#define  WRPLL_DIVIDER_POST(x)		((x) << 8)
+#define  WRPLL_DIVIDER_POST_MASK	(0x3f << 8)
 #define  WRPLL_DIVIDER_POST_SHIFT	8
-#define  WRPLL_DIVIDER_FEEDBACK(x)	((x)<<16)
+#define  WRPLL_DIVIDER_FEEDBACK(x)	((x) << 16)
 #define  WRPLL_DIVIDER_FB_SHIFT		16
-#define  WRPLL_DIVIDER_FB_MASK		(0xff<<16)
+#define  WRPLL_DIVIDER_FB_MASK		(0xff << 16)
 
 /* Port clock selection */
 #define _PORT_CLK_SEL_A			0x46100
 #define _PORT_CLK_SEL_B			0x46104
 #define PORT_CLK_SEL(port) _MMIO_PORT(port, _PORT_CLK_SEL_A, _PORT_CLK_SEL_B)
-#define  PORT_CLK_SEL_LCPLL_2700	(0<<29)
-#define  PORT_CLK_SEL_LCPLL_1350	(1<<29)
-#define  PORT_CLK_SEL_LCPLL_810		(2<<29)
-#define  PORT_CLK_SEL_SPLL		(3<<29)
-#define  PORT_CLK_SEL_WRPLL(pll)	(((pll)+4)<<29)
-#define  PORT_CLK_SEL_WRPLL1		(4<<29)
-#define  PORT_CLK_SEL_WRPLL2		(5<<29)
-#define  PORT_CLK_SEL_NONE		(7<<29)
-#define  PORT_CLK_SEL_MASK		(7<<29)
+#define  PORT_CLK_SEL_LCPLL_2700	(0 << 29)
+#define  PORT_CLK_SEL_LCPLL_1350	(1 << 29)
+#define  PORT_CLK_SEL_LCPLL_810		(2 << 29)
+#define  PORT_CLK_SEL_SPLL		(3 << 29)
+#define  PORT_CLK_SEL_WRPLL(pll)	(((pll) + 4) << 29)
+#define  PORT_CLK_SEL_WRPLL1		(4 << 29)
+#define  PORT_CLK_SEL_WRPLL2		(5 << 29)
+#define  PORT_CLK_SEL_NONE		(7 << 29)
+#define  PORT_CLK_SEL_MASK		(7 << 29)
 
 /* On ICL+ this is the same as PORT_CLK_SEL, but all bits change. */
 #define DDI_CLK_SEL(port)		PORT_CLK_SEL(port)
@@ -8854,8 +8854,8 @@ enum skl_power_gate {
 #define _TRANS_CLK_SEL_B		0x46144
 #define TRANS_CLK_SEL(tran) _MMIO_TRANS(tran, _TRANS_CLK_SEL_A, _TRANS_CLK_SEL_B)
 /* For each transcoder, we need to select the corresponding port clock */
-#define  TRANS_CLK_SEL_DISABLED		(0x0<<29)
-#define  TRANS_CLK_SEL_PORT(x)		(((x)+1)<<29)
+#define  TRANS_CLK_SEL_DISABLED		(0x0 << 29)
+#define  TRANS_CLK_SEL_PORT(x)		(((x) + 1) << 29)
 
 #define CDCLK_FREQ			_MMIO(0x46200)
 
@@ -8865,28 +8865,28 @@ enum skl_power_gate {
 #define _TRANS_EDP_MSA_MISC		0x6f410
 #define TRANS_MSA_MISC(tran) _MMIO_TRANS2(tran, _TRANSA_MSA_MISC)
 
-#define  TRANS_MSA_SYNC_CLK		(1<<0)
-#define  TRANS_MSA_6_BPC		(0<<5)
-#define  TRANS_MSA_8_BPC		(1<<5)
-#define  TRANS_MSA_10_BPC		(2<<5)
-#define  TRANS_MSA_12_BPC		(3<<5)
-#define  TRANS_MSA_16_BPC		(4<<5)
+#define  TRANS_MSA_SYNC_CLK		(1 << 0)
+#define  TRANS_MSA_6_BPC		(0 << 5)
+#define  TRANS_MSA_8_BPC		(1 << 5)
+#define  TRANS_MSA_10_BPC		(2 << 5)
+#define  TRANS_MSA_12_BPC		(3 << 5)
+#define  TRANS_MSA_16_BPC		(4 << 5)
 
 /* LCPLL Control */
 #define LCPLL_CTL			_MMIO(0x130040)
-#define  LCPLL_PLL_DISABLE		(1<<31)
-#define  LCPLL_PLL_LOCK			(1<<30)
-#define  LCPLL_CLK_FREQ_MASK		(3<<26)
-#define  LCPLL_CLK_FREQ_450		(0<<26)
-#define  LCPLL_CLK_FREQ_54O_BDW		(1<<26)
-#define  LCPLL_CLK_FREQ_337_5_BDW	(2<<26)
-#define  LCPLL_CLK_FREQ_675_BDW		(3<<26)
-#define  LCPLL_CD_CLOCK_DISABLE		(1<<25)
-#define  LCPLL_ROOT_CD_CLOCK_DISABLE	(1<<24)
-#define  LCPLL_CD2X_CLOCK_DISABLE	(1<<23)
-#define  LCPLL_POWER_DOWN_ALLOW		(1<<22)
-#define  LCPLL_CD_SOURCE_FCLK		(1<<21)
-#define  LCPLL_CD_SOURCE_FCLK_DONE	(1<<19)
+#define  LCPLL_PLL_DISABLE		(1 << 31)
+#define  LCPLL_PLL_LOCK			(1 << 30)
+#define  LCPLL_CLK_FREQ_MASK		(3 << 26)
+#define  LCPLL_CLK_FREQ_450		(0 << 26)
+#define  LCPLL_CLK_FREQ_54O_BDW		(1 << 26)
+#define  LCPLL_CLK_FREQ_337_5_BDW	(2 << 26)
+#define  LCPLL_CLK_FREQ_675_BDW		(3 << 26)
+#define  LCPLL_CD_CLOCK_DISABLE		(1 << 25)
+#define  LCPLL_ROOT_CD_CLOCK_DISABLE	(1 << 24)
+#define  LCPLL_CD2X_CLOCK_DISABLE	(1 << 23)
+#define  LCPLL_POWER_DOWN_ALLOW		(1 << 22)
+#define  LCPLL_CD_SOURCE_FCLK		(1 << 21)
+#define  LCPLL_CD_SOURCE_FCLK_DONE	(1 << 19)
 
 /*
  * SKL Clocks
@@ -8914,16 +8914,16 @@ enum skl_power_gate {
 /* LCPLL_CTL */
 #define LCPLL1_CTL		_MMIO(0x46010)
 #define LCPLL2_CTL		_MMIO(0x46014)
-#define  LCPLL_PLL_ENABLE	(1<<31)
+#define  LCPLL_PLL_ENABLE	(1 << 31)
 
 /* DPLL control1 */
 #define DPLL_CTRL1		_MMIO(0x6C058)
-#define  DPLL_CTRL1_HDMI_MODE(id)		(1<<((id)*6+5))
-#define  DPLL_CTRL1_SSC(id)			(1<<((id)*6+4))
-#define  DPLL_CTRL1_LINK_RATE_MASK(id)		(7<<((id)*6+1))
-#define  DPLL_CTRL1_LINK_RATE_SHIFT(id)		((id)*6+1)
-#define  DPLL_CTRL1_LINK_RATE(linkrate, id)	((linkrate)<<((id)*6+1))
-#define  DPLL_CTRL1_OVERRIDE(id)		(1<<((id)*6))
+#define  DPLL_CTRL1_HDMI_MODE(id)		(1 << ((id) * 6 + 5))
+#define  DPLL_CTRL1_SSC(id)			(1 << ((id) * 6 + 4))
+#define  DPLL_CTRL1_LINK_RATE_MASK(id)		(7 << ((id) * 6 + 1))
+#define  DPLL_CTRL1_LINK_RATE_SHIFT(id)		((id) * 6 + 1)
+#define  DPLL_CTRL1_LINK_RATE(linkrate, id)	((linkrate) << ((id) * 6 + 1))
+#define  DPLL_CTRL1_OVERRIDE(id)		(1 << ((id) * 6))
 #define  DPLL_CTRL1_LINK_RATE_2700		0
 #define  DPLL_CTRL1_LINK_RATE_1350		1
 #define  DPLL_CTRL1_LINK_RATE_810		2
@@ -8933,43 +8933,43 @@ enum skl_power_gate {
 
 /* DPLL control2 */
 #define DPLL_CTRL2				_MMIO(0x6C05C)
-#define  DPLL_CTRL2_DDI_CLK_OFF(port)		(1<<((port)+15))
-#define  DPLL_CTRL2_DDI_CLK_SEL_MASK(port)	(3<<((port)*3+1))
-#define  DPLL_CTRL2_DDI_CLK_SEL_SHIFT(port)    ((port)*3+1)
-#define  DPLL_CTRL2_DDI_CLK_SEL(clk, port)	((clk)<<((port)*3+1))
-#define  DPLL_CTRL2_DDI_SEL_OVERRIDE(port)     (1<<((port)*3))
+#define  DPLL_CTRL2_DDI_CLK_OFF(port)		(1 << ((port) + 15))
+#define  DPLL_CTRL2_DDI_CLK_SEL_MASK(port)	(3 << ((port) * 3 + 1))
+#define  DPLL_CTRL2_DDI_CLK_SEL_SHIFT(port)    ((port) * 3 + 1)
+#define  DPLL_CTRL2_DDI_CLK_SEL(clk, port)	((clk) << ((port) * 3 + 1))
+#define  DPLL_CTRL2_DDI_SEL_OVERRIDE(port)     (1 << ((port) * 3))
 
 /* DPLL Status */
 #define DPLL_STATUS	_MMIO(0x6C060)
-#define  DPLL_LOCK(id) (1<<((id)*8))
+#define  DPLL_LOCK(id) (1 << ((id) * 8))
 
 /* DPLL cfg */
 #define _DPLL1_CFGCR1	0x6C040
 #define _DPLL2_CFGCR1	0x6C048
 #define _DPLL3_CFGCR1	0x6C050
-#define  DPLL_CFGCR1_FREQ_ENABLE	(1<<31)
-#define  DPLL_CFGCR1_DCO_FRACTION_MASK	(0x7fff<<9)
-#define  DPLL_CFGCR1_DCO_FRACTION(x)	((x)<<9)
+#define  DPLL_CFGCR1_FREQ_ENABLE	(1 << 31)
+#define  DPLL_CFGCR1_DCO_FRACTION_MASK	(0x7fff << 9)
+#define  DPLL_CFGCR1_DCO_FRACTION(x)	((x) << 9)
 #define  DPLL_CFGCR1_DCO_INTEGER_MASK	(0x1ff)
 
 #define _DPLL1_CFGCR2	0x6C044
 #define _DPLL2_CFGCR2	0x6C04C
 #define _DPLL3_CFGCR2	0x6C054
-#define  DPLL_CFGCR2_QDIV_RATIO_MASK	(0xff<<8)
-#define  DPLL_CFGCR2_QDIV_RATIO(x)	((x)<<8)
-#define  DPLL_CFGCR2_QDIV_MODE(x)	((x)<<7)
-#define  DPLL_CFGCR2_KDIV_MASK		(3<<5)
-#define  DPLL_CFGCR2_KDIV(x)		((x)<<5)
-#define  DPLL_CFGCR2_KDIV_5 (0<<5)
-#define  DPLL_CFGCR2_KDIV_2 (1<<5)
-#define  DPLL_CFGCR2_KDIV_3 (2<<5)
-#define  DPLL_CFGCR2_KDIV_1 (3<<5)
-#define  DPLL_CFGCR2_PDIV_MASK		(7<<2)
-#define  DPLL_CFGCR2_PDIV(x)		((x)<<2)
-#define  DPLL_CFGCR2_PDIV_1 (0<<2)
-#define  DPLL_CFGCR2_PDIV_2 (1<<2)
-#define  DPLL_CFGCR2_PDIV_3 (2<<2)
-#define  DPLL_CFGCR2_PDIV_7 (4<<2)
+#define  DPLL_CFGCR2_QDIV_RATIO_MASK	(0xff << 8)
+#define  DPLL_CFGCR2_QDIV_RATIO(x)	((x) << 8)
+#define  DPLL_CFGCR2_QDIV_MODE(x)	((x) << 7)
+#define  DPLL_CFGCR2_KDIV_MASK		(3 << 5)
+#define  DPLL_CFGCR2_KDIV(x)		((x) << 5)
+#define  DPLL_CFGCR2_KDIV_5 (0 << 5)
+#define  DPLL_CFGCR2_KDIV_2 (1 << 5)
+#define  DPLL_CFGCR2_KDIV_3 (2 << 5)
+#define  DPLL_CFGCR2_KDIV_1 (3 << 5)
+#define  DPLL_CFGCR2_PDIV_MASK		(7 << 2)
+#define  DPLL_CFGCR2_PDIV(x)		((x) << 2)
+#define  DPLL_CFGCR2_PDIV_1 (0 << 2)
+#define  DPLL_CFGCR2_PDIV_2 (1 << 2)
+#define  DPLL_CFGCR2_PDIV_3 (2 << 2)
+#define  DPLL_CFGCR2_PDIV_7 (4 << 2)
 #define  DPLL_CFGCR2_CENTRAL_FREQ_MASK	(3)
 
 #define DPLL_CFGCR1(id)	_MMIO_PIPE((id) - SKL_DPLL1, _DPLL1_CFGCR1, _DPLL2_CFGCR1)
@@ -8981,9 +8981,9 @@ enum skl_power_gate {
 #define DPCLKA_CFGCR0				_MMIO(0x6C200)
 #define DPCLKA_CFGCR0_ICL			_MMIO(0x164280)
 #define  DPCLKA_CFGCR0_DDI_CLK_OFF(port)	(1 << ((port) ==  PORT_F ? 23 : \
-						      (port)+10))
+						      (port) + 10))
 #define  DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port)	((port) == PORT_F ? 21 : \
-						(port)*2)
+						(port) * 2)
 #define  DPCLKA_CFGCR0_DDI_CLK_SEL_MASK(port)	(3 << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
 #define  DPCLKA_CFGCR0_DDI_CLK_SEL(pll, port)	((pll) << DPCLKA_CFGCR0_DDI_CLK_SEL_SHIFT(port))
 
@@ -9196,22 +9196,22 @@ enum skl_power_gate {
 /* GEN9 DC */
 #define DC_STATE_EN			_MMIO(0x45504)
 #define  DC_STATE_DISABLE		0
-#define  DC_STATE_EN_UPTO_DC5		(1<<0)
-#define  DC_STATE_EN_DC9		(1<<3)
-#define  DC_STATE_EN_UPTO_DC6		(2<<0)
+#define  DC_STATE_EN_UPTO_DC5		(1 << 0)
+#define  DC_STATE_EN_DC9		(1 << 3)
+#define  DC_STATE_EN_UPTO_DC6		(2 << 0)
 #define  DC_STATE_EN_UPTO_DC5_DC6_MASK   0x3
 
 #define  DC_STATE_DEBUG                  _MMIO(0x45520)
-#define  DC_STATE_DEBUG_MASK_CORES	(1<<0)
-#define  DC_STATE_DEBUG_MASK_MEMORY_UP	(1<<1)
+#define  DC_STATE_DEBUG_MASK_CORES	(1 << 0)
+#define  DC_STATE_DEBUG_MASK_MEMORY_UP	(1 << 1)
 
 /* Please see hsw_read_dcomp() and hsw_write_dcomp() before using this register,
  * since on HSW we can't write to it using I915_WRITE. */
 #define D_COMP_HSW			_MMIO(MCHBAR_MIRROR_BASE_SNB + 0x5F0C)
 #define D_COMP_BDW			_MMIO(0x138144)
-#define  D_COMP_RCOMP_IN_PROGRESS	(1<<9)
-#define  D_COMP_COMP_FORCE		(1<<8)
-#define  D_COMP_COMP_DISABLE		(1<<0)
+#define  D_COMP_RCOMP_IN_PROGRESS	(1 << 9)
+#define  D_COMP_COMP_FORCE		(1 << 8)
+#define  D_COMP_COMP_DISABLE		(1 << 0)
 
 /* Pipe WM_LINETIME - watermark line time */
 #define _PIPE_WM_LINETIME_A		0x45270
@@ -9219,27 +9219,27 @@ enum skl_power_gate {
 #define PIPE_WM_LINETIME(pipe) _MMIO_PIPE(pipe, _PIPE_WM_LINETIME_A, _PIPE_WM_LINETIME_B)
 #define   PIPE_WM_LINETIME_MASK			(0x1ff)
 #define   PIPE_WM_LINETIME_TIME(x)		((x))
-#define   PIPE_WM_LINETIME_IPS_LINETIME_MASK	(0x1ff<<16)
-#define   PIPE_WM_LINETIME_IPS_LINETIME(x)	((x)<<16)
+#define   PIPE_WM_LINETIME_IPS_LINETIME_MASK	(0x1ff << 16)
+#define   PIPE_WM_LINETIME_IPS_LINETIME(x)	((x) << 16)
 
 /* SFUSE_STRAP */
 #define SFUSE_STRAP			_MMIO(0xc2014)
-#define  SFUSE_STRAP_FUSE_LOCK		(1<<13)
-#define  SFUSE_STRAP_RAW_FREQUENCY	(1<<8)
-#define  SFUSE_STRAP_DISPLAY_DISABLED	(1<<7)
-#define  SFUSE_STRAP_CRT_DISABLED	(1<<6)
-#define  SFUSE_STRAP_DDIF_DETECTED	(1<<3)
-#define  SFUSE_STRAP_DDIB_DETECTED	(1<<2)
-#define  SFUSE_STRAP_DDIC_DETECTED	(1<<1)
-#define  SFUSE_STRAP_DDID_DETECTED	(1<<0)
+#define  SFUSE_STRAP_FUSE_LOCK		(1 << 13)
+#define  SFUSE_STRAP_RAW_FREQUENCY	(1 << 8)
+#define  SFUSE_STRAP_DISPLAY_DISABLED	(1 << 7)
+#define  SFUSE_STRAP_CRT_DISABLED	(1 << 6)
+#define  SFUSE_STRAP_DDIF_DETECTED	(1 << 3)
+#define  SFUSE_STRAP_DDIB_DETECTED	(1 << 2)
+#define  SFUSE_STRAP_DDIC_DETECTED	(1 << 1)
+#define  SFUSE_STRAP_DDID_DETECTED	(1 << 0)
 
 #define WM_MISC				_MMIO(0x45260)
 #define  WM_MISC_DATA_PARTITION_5_6	(1 << 0)
 
 #define WM_DBG				_MMIO(0x45280)
-#define  WM_DBG_DISALLOW_MULTIPLE_LP	(1<<0)
-#define  WM_DBG_DISALLOW_MAXFIFO	(1<<1)
-#define  WM_DBG_DISALLOW_SPRITE		(1<<2)
+#define  WM_DBG_DISALLOW_MULTIPLE_LP	(1 << 0)
+#define  WM_DBG_DISALLOW_MAXFIFO	(1 << 1)
+#define  WM_DBG_DISALLOW_SPRITE		(1 << 2)
 
 /* pipe CSC */
 #define _PIPE_A_CSC_COEFF_RY_GY	0x49010
-- 
cgit v1.2.3


From af7187b784432d62cb2059d65ef91b7e0aa77a4f Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Tue, 12 Jun 2018 16:56:53 -0700
Subject: drm/i915/i915_reg.h: fix the checkpatch SPACE_BEFORE_TAB issues

Since I'm touching the file I might as well fix this class of errors
since they are just a few. Also drive-by fix the styling of the
VLV_TURBO_SOC_OVERRIDE definitions instead of just the spaces before
the tabs.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612235654.7914-3-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b0dd26fc1ee3..1bf3bdc61e45 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1142,11 +1142,11 @@ enum i915_power_well_id {
 #define   FB_FMAX_VMIN_FREQ_LO_SHIFT		27
 #define   FB_FMAX_VMIN_FREQ_LO_MASK		0xf8000000
 
-#define VLV_TURBO_SOC_OVERRIDE	0x04
-#define 	VLV_OVERRIDE_EN	1
-#define 	VLV_SOC_TDP_EN	(1 << 1)
-#define 	VLV_BIAS_CPU_125_SOC_875 (6 << 2)
-#define 	CHV_BIAS_CPU_50_SOC_50 (3 << 2)
+#define VLV_TURBO_SOC_OVERRIDE		0x04
+#define   VLV_OVERRIDE_EN		1
+#define   VLV_SOC_TDP_EN		(1 << 1)
+#define   VLV_BIAS_CPU_125_SOC_875	(6 << 2)
+#define   CHV_BIAS_CPU_50_SOC_50	(3 << 2)
 
 /* vlv2 north clock has */
 #define CCK_FUSE_REG				0x8
@@ -2413,7 +2413,7 @@ enum i915_power_well_id {
 #define   DERRMR_PIPEA_SPR_FLIP_DONE	(1 << 2)
 #define   DERRMR_PIPEA_VBLANK		(1 << 3)
 #define   DERRMR_PIPEA_HBLANK		(1 << 5)
-#define   DERRMR_PIPEB_SCANLINE 	(1 << 8)
+#define   DERRMR_PIPEB_SCANLINE		(1 << 8)
 #define   DERRMR_PIPEB_PRI_FLIP_DONE	(1 << 9)
 #define   DERRMR_PIPEB_SPR_FLIP_DONE	(1 << 10)
 #define   DERRMR_PIPEB_VBLANK		(1 << 11)
@@ -7573,7 +7573,7 @@ enum {
 #define  TRANS_VBLANK_END_SHIFT		16
 #define  TRANS_VBLANK_START_SHIFT	0
 #define _PCH_TRANS_VSYNC_A		0xe0014
-#define  TRANS_VSYNC_END_SHIFT	 	16
+#define  TRANS_VSYNC_END_SHIFT		16
 #define  TRANS_VSYNC_START_SHIFT	0
 #define _PCH_TRANS_VSYNCSHIFT_A		0xe0028
 
-- 
cgit v1.2.3


From 9e8789ec967a2d524bcfc79c47a85d08dfbe626a Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Tue, 12 Jun 2018 16:56:54 -0700
Subject: drm/i915/i915_reg.h: fix the checkpatch MACRO_ARG_PRECEDENCE issues

While I don't see any issue with the way these macros are being called
today, let's protect them against operator precedence issues before
they happen.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180612235654.7914-4-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 42 ++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 1bf3bdc61e45..50fe3b27ec94 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1780,7 +1780,7 @@ enum i915_power_well_id {
 #define CNL_PORT_TX_DW4_GRP(port)	_MMIO(_CNL_PORT_TX_DW_GRP((port), 4))
 #define CNL_PORT_TX_DW4_LN0(port)	_MMIO(_CNL_PORT_TX_DW_LN0((port), 4))
 #define CNL_PORT_TX_DW4_LN(port, ln)   _MMIO(_CNL_PORT_TX_DW_LN0((port), 4) + \
-					     (ln * (_CNL_PORT_TX_DW4_LN1_AE - \
+					   ((ln) * (_CNL_PORT_TX_DW4_LN1_AE - \
 						    _CNL_PORT_TX_DW4_LN0_AE)))
 #define _ICL_PORT_TX_DW4_GRP_A		0x162690
 #define _ICL_PORT_TX_DW4_GRP_B		0x6C690
@@ -1793,8 +1793,8 @@ enum i915_power_well_id {
 #define ICL_PORT_TX_DW4_LN(port, ln)	_MMIO(_PORT(port, \
 						   _ICL_PORT_TX_DW4_LN0_A, \
 						   _ICL_PORT_TX_DW4_LN0_B) + \
-					      (ln * (_ICL_PORT_TX_DW4_LN1_A - \
-						     _ICL_PORT_TX_DW4_LN0_A)))
+					     ((ln) * (_ICL_PORT_TX_DW4_LN1_A - \
+						      _ICL_PORT_TX_DW4_LN0_A)))
 #define   LOADGEN_SELECT		(1 << 31)
 #define   POST_CURSOR_1(x)		((x) << 12)
 #define   POST_CURSOR_1_MASK		(0x3F << 12)
@@ -6076,8 +6076,8 @@ enum {
 
 /* Display/Sprite base address macros */
 #define DISP_BASEADDR_MASK	(0xfffff000)
-#define I915_LO_DISPBASE(val)	(val & ~DISP_BASEADDR_MASK)
-#define I915_HI_DISPBASE(val)	(val & DISP_BASEADDR_MASK)
+#define I915_LO_DISPBASE(val)	((val) & ~DISP_BASEADDR_MASK)
+#define I915_HI_DISPBASE(val)	((val) & DISP_BASEADDR_MASK)
 
 /*
  * VBIOS flags
@@ -7091,7 +7091,7 @@ enum {
 #define  GEN11_VECS(x)			(31 - (x))
 #define  GEN11_VCS(x)			(x)
 
-#define GEN11_GT_INTR_DW(x)		_MMIO(0x190018 + (x * 4))
+#define GEN11_GT_INTR_DW(x)		_MMIO(0x190018 + ((x) * 4))
 
 #define GEN11_INTR_IDENTITY_REG0	_MMIO(0x190060)
 #define GEN11_INTR_IDENTITY_REG1	_MMIO(0x190064)
@@ -7100,12 +7100,12 @@ enum {
 #define  GEN11_INTR_ENGINE_INSTANCE(x)	(((x) & GENMASK(25, 20)) >> 20)
 #define  GEN11_INTR_ENGINE_INTR(x)	((x) & 0xffff)
 
-#define GEN11_INTR_IDENTITY_REG(x)	_MMIO(0x190060 + (x * 4))
+#define GEN11_INTR_IDENTITY_REG(x)	_MMIO(0x190060 + ((x) * 4))
 
 #define GEN11_IIR_REG0_SELECTOR		_MMIO(0x190070)
 #define GEN11_IIR_REG1_SELECTOR		_MMIO(0x190074)
 
-#define GEN11_IIR_REG_SELECTOR(x)	_MMIO(0x190070 + (x * 4))
+#define GEN11_IIR_REG_SELECTOR(x)	_MMIO(0x190070 + ((x) * 4))
 
 #define GEN11_RENDER_COPY_INTR_ENABLE	_MMIO(0x190030)
 #define GEN11_VCS_VECS_INTR_ENABLE	_MMIO(0x190034)
@@ -7497,15 +7497,15 @@ enum {
 
 #define _PCH_DPLL_A              0xc6014
 #define _PCH_DPLL_B              0xc6018
-#define PCH_DPLL(pll) _MMIO(pll == 0 ? _PCH_DPLL_A : _PCH_DPLL_B)
+#define PCH_DPLL(pll) _MMIO((pll) == 0 ? _PCH_DPLL_A : _PCH_DPLL_B)
 
 #define _PCH_FPA0                0xc6040
 #define  FP_CB_TUNE		(0x3 << 22)
 #define _PCH_FPA1                0xc6044
 #define _PCH_FPB0                0xc6048
 #define _PCH_FPB1                0xc604c
-#define PCH_FP0(pll) _MMIO(pll == 0 ? _PCH_FPA0 : _PCH_FPB0)
-#define PCH_FP1(pll) _MMIO(pll == 0 ? _PCH_FPA1 : _PCH_FPB1)
+#define PCH_FP0(pll) _MMIO((pll) == 0 ? _PCH_FPA0 : _PCH_FPB0)
+#define PCH_FP1(pll) _MMIO((pll) == 0 ? _PCH_FPA1 : _PCH_FPB1)
 
 #define PCH_DPLL_TEST           _MMIO(0xc606c)
 
@@ -8337,11 +8337,11 @@ enum {
 #define   GEN7_L3CDERRST1_BANK_MASK	(3 << 11)
 #define   GEN7_L3CDERRST1_SUBBANK_MASK	(7 << 8)
 #define GEN7_PARITY_ERROR_ROW(reg) \
-		((reg & GEN7_L3CDERRST1_ROW_MASK) >> 14)
+		(((reg) & GEN7_L3CDERRST1_ROW_MASK) >> 14)
 #define GEN7_PARITY_ERROR_BANK(reg) \
-		((reg & GEN7_L3CDERRST1_BANK_MASK) >> 11)
+		(((reg) & GEN7_L3CDERRST1_BANK_MASK) >> 11)
 #define GEN7_PARITY_ERROR_SUBBANK(reg) \
-		((reg & GEN7_L3CDERRST1_SUBBANK_MASK) >> 8)
+		(((reg) & GEN7_L3CDERRST1_SUBBANK_MASK) >> 8)
 #define   GEN7_L3CDERRST1_ENABLE	(1 << 7)
 
 #define GEN7_L3LOG(slice, i)		_MMIO(0xB070 + (slice) * 0x200 + (i) * 4)
@@ -8614,7 +8614,7 @@ enum skl_power_gate {
 #define HDCP_SHA_V_PRIME_H2		_MMIO(0x66d0C)
 #define HDCP_SHA_V_PRIME_H3		_MMIO(0x66d10)
 #define HDCP_SHA_V_PRIME_H4		_MMIO(0x66d14)
-#define HDCP_SHA_V_PRIME(h)		_MMIO((0x66d04 + h * 4))
+#define HDCP_SHA_V_PRIME(h)		_MMIO((0x66d04 + (h) * 4))
 #define HDCP_SHA_TEXT			_MMIO(0x66d18)
 
 /* HDCP Auth Registers */
@@ -8630,7 +8630,7 @@ enum skl_power_gate {
 					  _PORTC_HDCP_AUTHENC, \
 					  _PORTD_HDCP_AUTHENC, \
 					  _PORTE_HDCP_AUTHENC, \
-					  _PORTF_HDCP_AUTHENC) + x)
+					  _PORTF_HDCP_AUTHENC) + (x))
 #define PORT_HDCP_CONF(port)		_PORT_HDCP_AUTHENC(port, 0x0)
 #define  HDCP_CONF_CAPTURE_AN		BIT(0)
 #define  HDCP_CONF_AUTH_AND_ENC		(BIT(1) | BIT(0))
@@ -8651,7 +8651,7 @@ enum skl_power_gate {
 #define  HDCP_STATUS_R0_READY		BIT(18)
 #define  HDCP_STATUS_AN_READY		BIT(17)
 #define  HDCP_STATUS_CIPHER		BIT(16)
-#define  HDCP_STATUS_FRAME_CNT(x)	((x >> 8) & 0xff)
+#define  HDCP_STATUS_FRAME_CNT(x)	(((x) >> 8) & 0xff)
 
 /* Per-pipe DDI Function Control */
 #define _TRANS_DDI_FUNC_CTL_A		0x60400
@@ -9402,7 +9402,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_TX_ESCLK_FIXDIV_MASK, \
 					BXT_MIPI2_TX_ESCLK_FIXDIV_MASK)
 #define  BXT_MIPI_TX_ESCLK_DIVIDER(port, val)	\
-		((val & 0x3F) << BXT_MIPI_TX_ESCLK_SHIFT(port))
+		(((val) & 0x3F) << BXT_MIPI_TX_ESCLK_SHIFT(port))
 /* RX upper control divider to select actual RX clock output from 8x */
 #define  BXT_MIPI1_RX_ESCLK_UPPER_SHIFT		21
 #define  BXT_MIPI2_RX_ESCLK_UPPER_SHIFT		5
@@ -9415,7 +9415,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_RX_ESCLK_UPPER_FIXDIV_MASK, \
 					BXT_MIPI2_RX_ESCLK_UPPER_FIXDIV_MASK)
 #define  BXT_MIPI_RX_ESCLK_UPPER_DIVIDER(port, val)	\
-		((val & 3) << BXT_MIPI_RX_ESCLK_UPPER_SHIFT(port))
+		(((val) & 3) << BXT_MIPI_RX_ESCLK_UPPER_SHIFT(port))
 /* 8/3X divider to select the actual 8/3X clock output from 8x */
 #define  BXT_MIPI1_8X_BY3_SHIFT                19
 #define  BXT_MIPI2_8X_BY3_SHIFT                3
@@ -9428,7 +9428,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_8X_BY3_DIVIDER_MASK, \
 						BXT_MIPI2_8X_BY3_DIVIDER_MASK)
 #define  BXT_MIPI_8X_BY3_DIVIDER(port, val)    \
-			((val & 3) << BXT_MIPI_8X_BY3_SHIFT(port))
+			(((val) & 3) << BXT_MIPI_8X_BY3_SHIFT(port))
 /* RX lower control divider to select actual RX clock output from 8x */
 #define  BXT_MIPI1_RX_ESCLK_LOWER_SHIFT		16
 #define  BXT_MIPI2_RX_ESCLK_LOWER_SHIFT		0
@@ -9441,7 +9441,7 @@ enum skl_power_gate {
 			_MIPI_PORT(port, BXT_MIPI1_RX_ESCLK_LOWER_FIXDIV_MASK, \
 					BXT_MIPI2_RX_ESCLK_LOWER_FIXDIV_MASK)
 #define  BXT_MIPI_RX_ESCLK_LOWER_DIVIDER(port, val)	\
-		((val & 3) << BXT_MIPI_RX_ESCLK_LOWER_SHIFT(port))
+		(((val) & 3) << BXT_MIPI_RX_ESCLK_LOWER_SHIFT(port))
 
 #define RX_DIVIDER_BIT_1_2                     0x3
 #define RX_DIVIDER_BIT_3_4                     0xC
-- 
cgit v1.2.3


From df0d28c185ad29d539826a8eb8b651ea9c46051d Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 15 Jun 2018 17:05:28 -0700
Subject: drm/i915/icl: GSE interrupt moves from DE_MISC to GU_MISC

The Graphics System Event(GSE) interrupt bit has a new location in the
GU_MISC_INTERRUPT_{IIR, ISR, IMR, IER} registers. Since GSE was the only
DE_MISC interrupt that was enabled, with this change we don't enable/handle
any of DE_MISC interrupts for gen11. Credits to Paulo for pointing out
the register change.

v2: from DK
raw_reg_[read/write], branch prediction hint and drop platform check (Mika)

v3: From DK
Early re-enable of master interrupt (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
[Paulo: bikesheds and rebases]
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180616000530.5357-1-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_irq.c | 46 ++++++++++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h |  7 +++++++
 2 files changed, 52 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index d5aee0b74f4b..64d5e10a4de8 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2954,11 +2954,44 @@ gen11_gt_irq_handler(struct drm_i915_private * const i915,
 	spin_unlock(&i915->irq_lock);
 }
 
+static void
+gen11_gu_misc_irq_ack(struct drm_i915_private *dev_priv, const u32 master_ctl,
+		      u32 *iir)
+{
+	void __iomem * const regs = dev_priv->regs;
+
+	if (!(master_ctl & GEN11_GU_MISC_IRQ))
+		return;
+
+	*iir = raw_reg_read(regs, GEN11_GU_MISC_IIR);
+	if (likely(*iir))
+		raw_reg_write(regs, GEN11_GU_MISC_IIR, *iir);
+}
+
+static void
+gen11_gu_misc_irq_handler(struct drm_i915_private *dev_priv,
+			  const u32 master_ctl, const u32 iir)
+{
+	if (!(master_ctl & GEN11_GU_MISC_IRQ))
+		return;
+
+	if (unlikely(!iir)) {
+		DRM_ERROR("GU_MISC iir blank!\n");
+		return;
+	}
+
+	if (iir & GEN11_GU_MISC_GSE)
+		intel_opregion_asle_intr(dev_priv);
+	else
+		DRM_ERROR("Unexpected GU_MISC interrupt 0x%x\n", iir);
+}
+
 static irqreturn_t gen11_irq_handler(int irq, void *arg)
 {
 	struct drm_i915_private * const i915 = to_i915(arg);
 	void __iomem * const regs = i915->regs;
 	u32 master_ctl;
+	u32 gu_misc_iir;
 
 	if (!intel_irqs_enabled(i915))
 		return IRQ_NONE;
@@ -2987,9 +3020,13 @@ static irqreturn_t gen11_irq_handler(int irq, void *arg)
 		enable_rpm_wakeref_asserts(i915);
 	}
 
+	gen11_gu_misc_irq_ack(i915, master_ctl, &gu_misc_iir);
+
 	/* Acknowledge and enable interrupts. */
 	raw_reg_write(regs, GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ | master_ctl);
 
+	gen11_gu_misc_irq_handler(i915, master_ctl, gu_misc_iir);
+
 	return IRQ_HANDLED;
 }
 
@@ -3476,6 +3513,7 @@ static void gen11_irq_reset(struct drm_device *dev)
 
 	GEN3_IRQ_RESET(GEN8_DE_PORT_);
 	GEN3_IRQ_RESET(GEN8_DE_MISC_);
+	GEN3_IRQ_RESET(GEN11_GU_MISC_);
 	GEN3_IRQ_RESET(GEN8_PCU_);
 }
 
@@ -3919,9 +3957,12 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	uint32_t de_pipe_enables;
 	u32 de_port_masked = GEN8_AUX_CHANNEL_A;
 	u32 de_port_enables;
-	u32 de_misc_masked = GEN8_DE_MISC_GSE | GEN8_DE_EDP_PSR;
+	u32 de_misc_masked = GEN8_DE_EDP_PSR;
 	enum pipe pipe;
 
+	if (INTEL_GEN(dev_priv) <= 10)
+		de_misc_masked |= GEN8_DE_MISC_GSE;
+
 	if (INTEL_GEN(dev_priv) >= 9) {
 		de_pipe_masked |= GEN9_DE_PIPE_IRQ_FAULT_ERRORS;
 		de_port_masked |= GEN9_AUX_CHANNEL_B | GEN9_AUX_CHANNEL_C |
@@ -4018,10 +4059,13 @@ static void gen11_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 static int gen11_irq_postinstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
+	u32 gu_misc_masked = GEN11_GU_MISC_GSE;
 
 	gen11_gt_irq_postinstall(dev_priv);
 	gen8_de_irq_postinstall(dev_priv);
 
+	GEN3_IRQ_INIT(GEN11_GU_MISC_, ~gu_misc_masked, gu_misc_masked);
+
 	I915_WRITE(GEN11_DISPLAY_INT_CTL, GEN11_DISPLAY_IRQ_ENABLE);
 
 	I915_WRITE(GEN11_GFX_MSTR_IRQ, GEN11_MASTER_IRQ);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 50fe3b27ec94..aed5ef9a95cb 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7059,9 +7059,16 @@ enum {
 #define GEN8_PCU_IIR _MMIO(0x444e8)
 #define GEN8_PCU_IER _MMIO(0x444ec)
 
+#define GEN11_GU_MISC_ISR	_MMIO(0x444f0)
+#define GEN11_GU_MISC_IMR	_MMIO(0x444f4)
+#define GEN11_GU_MISC_IIR	_MMIO(0x444f8)
+#define GEN11_GU_MISC_IER	_MMIO(0x444fc)
+#define  GEN11_GU_MISC_GSE	(1 << 27)
+
 #define GEN11_GFX_MSTR_IRQ		_MMIO(0x190010)
 #define  GEN11_MASTER_IRQ		(1 << 31)
 #define  GEN11_PCU_IRQ			(1 << 30)
+#define  GEN11_GU_MISC_IRQ		(1 << 29)
 #define  GEN11_DISPLAY_IRQ		(1 << 16)
 #define  GEN11_GT_DW_IRQ(x)		(1 << (x))
 #define  GEN11_GT_DW1_IRQ		(1 << 1)
-- 
cgit v1.2.3


From 121e758ee5782b31fa5ecf23a3828f86167d36cc Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 15 Jun 2018 17:05:29 -0700
Subject: drm/i915/icl: Support for TC North Display interrupts

The hotplug interrupts for the ports can be routed to either North
Display or South Display depending on the output mode. DP Alternate or
DP over TBT outputs will have hotplug interrupts routed to the North
Display while interrupts for legacy modes will be routed to the South
Display in PCH. This patch adds hotplug interrupt handling support for
DP Alternate mode.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
[Paulo: coding style changes]
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180616000530.5357-2-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_irq.c | 95 +++++++++++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_reg.h | 20 +++++++++
 2 files changed, 112 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 64d5e10a4de8..40e563eb3a1f 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -115,6 +115,13 @@ static const u32 hpd_bxt[HPD_NUM_PINS] = {
 	[HPD_PORT_C] = BXT_DE_PORT_HP_DDIC
 };
 
+static const u32 hpd_tc_gen11[HPD_NUM_PINS] = {
+	[HPD_PORT_C] = GEN11_TC1_HOTPLUG,
+	[HPD_PORT_D] = GEN11_TC2_HOTPLUG,
+	[HPD_PORT_E] = GEN11_TC3_HOTPLUG,
+	[HPD_PORT_F] = GEN11_TC4_HOTPLUG
+};
+
 /* IIR can theoretically queue up two events. Be paranoid. */
 #define GEN8_IRQ_RESET_NDX(type, which) do { \
 	I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \
@@ -1549,6 +1556,22 @@ static void gen8_gt_irq_handler(struct drm_i915_private *i915,
 	}
 }
 
+static bool gen11_port_hotplug_long_detect(enum port port, u32 val)
+{
+	switch (port) {
+	case PORT_C:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC1);
+	case PORT_D:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC2);
+	case PORT_E:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC3);
+	case PORT_F:
+		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC4);
+	default:
+		return false;
+	}
+}
+
 static bool bxt_port_hotplug_long_detect(enum port port, u32 val)
 {
 	switch (port) {
@@ -2598,6 +2621,25 @@ static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv,
 	intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
 }
 
+static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
+{
+	u32 pin_mask = 0, long_mask = 0;
+	u32 trigger_tc, dig_hotplug_reg;
+
+	trigger_tc = iir & GEN11_DE_TC_HOTPLUG_MASK;
+	if (trigger_tc) {
+		dig_hotplug_reg = I915_READ(GEN11_TC_HOTPLUG_CTL);
+		I915_WRITE(GEN11_TC_HOTPLUG_CTL, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tc,
+				   dig_hotplug_reg, hpd_tc_gen11,
+				   gen11_port_hotplug_long_detect);
+		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
+	} else {
+		DRM_ERROR("Unexpected DE HPD interrupt 0x%08x\n", iir);
+	}
+}
+
 static irqreturn_t
 gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 {
@@ -2633,6 +2675,17 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			DRM_ERROR("The master control interrupt lied (DE MISC)!\n");
 	}
 
+	if (INTEL_GEN(dev_priv) >= 11 && (master_ctl & GEN11_DE_HPD_IRQ)) {
+		iir = I915_READ(GEN11_DE_HPD_IIR);
+		if (iir) {
+			I915_WRITE(GEN11_DE_HPD_IIR, iir);
+			ret = IRQ_HANDLED;
+			gen11_hpd_irq_handler(dev_priv, iir);
+		} else {
+			DRM_ERROR("The master control interrupt lied, (DE HPD)!\n");
+		}
+	}
+
 	if (master_ctl & GEN8_DE_PORT_IRQ) {
 		iir = I915_READ(GEN8_DE_PORT_IIR);
 		if (iir) {
@@ -3513,6 +3566,7 @@ static void gen11_irq_reset(struct drm_device *dev)
 
 	GEN3_IRQ_RESET(GEN8_DE_PORT_);
 	GEN3_IRQ_RESET(GEN8_DE_MISC_);
+	GEN3_IRQ_RESET(GEN11_DE_HPD_);
 	GEN3_IRQ_RESET(GEN11_GU_MISC_);
 	GEN3_IRQ_RESET(GEN8_PCU_);
 }
@@ -3631,6 +3685,34 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	ibx_hpd_detection_setup(dev_priv);
 }
 
+static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug;
+
+	hotplug = I915_READ(GEN11_TC_HOTPLUG_CTL);
+	hotplug |= GEN11_HOTPLUG_CTL_ENABLE(PORT_TC1) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC2) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC3) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4);
+	I915_WRITE(GEN11_TC_HOTPLUG_CTL, hotplug);
+}
+
+static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug_irqs, enabled_irqs;
+	u32 val;
+
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_tc_gen11);
+	hotplug_irqs = GEN11_DE_TC_HOTPLUG_MASK;
+
+	val = I915_READ(GEN11_DE_HPD_IMR);
+	val &= ~hotplug_irqs;
+	I915_WRITE(GEN11_DE_HPD_IMR, val);
+	POSTING_READ(GEN11_DE_HPD_IMR);
+
+	gen11_hpd_detection_setup(dev_priv);
+}
+
 static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
 	u32 val, hotplug;
@@ -4004,10 +4086,17 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 	GEN3_IRQ_INIT(GEN8_DE_PORT_, ~de_port_masked, de_port_enables);
 	GEN3_IRQ_INIT(GEN8_DE_MISC_, ~de_misc_masked, de_misc_masked);
 
-	if (IS_GEN9_LP(dev_priv))
+	if (INTEL_GEN(dev_priv) >= 11) {
+		u32 de_hpd_masked = 0;
+		u32 de_hpd_enables = GEN11_DE_TC_HOTPLUG_MASK;
+
+		GEN3_IRQ_INIT(GEN11_DE_HPD_, ~de_hpd_masked, de_hpd_enables);
+		gen11_hpd_detection_setup(dev_priv);
+	} else if (IS_GEN9_LP(dev_priv)) {
 		bxt_hpd_detection_setup(dev_priv);
-	else if (IS_BROADWELL(dev_priv))
+	} else if (IS_BROADWELL(dev_priv)) {
 		ilk_hpd_detection_setup(dev_priv);
+	}
 }
 
 static int gen8_irq_postinstall(struct drm_device *dev)
@@ -4529,7 +4618,7 @@ void intel_irq_init(struct drm_i915_private *dev_priv)
 		dev->driver->irq_uninstall = gen11_irq_reset;
 		dev->driver->enable_vblank = gen8_enable_vblank;
 		dev->driver->disable_vblank = gen8_disable_vblank;
-		dev_priv->display.hpd_irq_setup = spt_hpd_irq_setup;
+		dev_priv->display.hpd_irq_setup = gen11_hpd_irq_setup;
 	} else if (INTEL_GEN(dev_priv) >= 8) {
 		dev->driver->irq_handler = gen8_irq_handler;
 		dev->driver->irq_preinstall = gen8_irq_reset;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index aed5ef9a95cb..21692228cb81 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7079,11 +7079,31 @@ enum {
 #define  GEN11_AUDIO_CODEC_IRQ		(1 << 24)
 #define  GEN11_DE_PCH_IRQ		(1 << 23)
 #define  GEN11_DE_MISC_IRQ		(1 << 22)
+#define  GEN11_DE_HPD_IRQ		(1 << 21)
 #define  GEN11_DE_PORT_IRQ		(1 << 20)
 #define  GEN11_DE_PIPE_C		(1 << 18)
 #define  GEN11_DE_PIPE_B		(1 << 17)
 #define  GEN11_DE_PIPE_A		(1 << 16)
 
+#define GEN11_DE_HPD_ISR		_MMIO(0x44470)
+#define GEN11_DE_HPD_IMR		_MMIO(0x44474)
+#define GEN11_DE_HPD_IIR		_MMIO(0x44478)
+#define GEN11_DE_HPD_IER		_MMIO(0x4447c)
+#define  GEN11_TC4_HOTPLUG			(1 << 19)
+#define  GEN11_TC3_HOTPLUG			(1 << 18)
+#define  GEN11_TC2_HOTPLUG			(1 << 17)
+#define  GEN11_TC1_HOTPLUG			(1 << 16)
+#define  GEN11_DE_TC_HOTPLUG_MASK		(GEN11_TC4_HOTPLUG | \
+						 GEN11_TC3_HOTPLUG | \
+						 GEN11_TC2_HOTPLUG | \
+						 GEN11_TC1_HOTPLUG)
+
+#define GEN11_TC_HOTPLUG_CTL				_MMIO(0x44038)
+#define  GEN11_HOTPLUG_CTL_ENABLE(tc_port)		(8 << (tc_port) * 4)
+#define  GEN11_HOTPLUG_CTL_LONG_DETECT(tc_port)		(2 << (tc_port) * 4)
+#define  GEN11_HOTPLUG_CTL_SHORT_DETECT(tc_port)	(1 << (tc_port) * 4)
+#define  GEN11_HOTPLUG_CTL_NO_DETECT(tc_port)		(0 << (tc_port) * 4)
+
 #define GEN11_GT_INTR_DW0		_MMIO(0x190018)
 #define  GEN11_CSME			(31)
 #define  GEN11_GUNIT			(28)
-- 
cgit v1.2.3


From b796b9710fd52d7f406f606697322fb5c7f562f3 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Fri, 15 Jun 2018 17:05:30 -0700
Subject: drm/i915/icl: Handle hotplug interrupts for DP over TBT

This patch enables hotplug interrupts for DP over TBT output on TC
ports. The TBT interrupts are enabled and handled irrespective of the
actual output type which could be DP Alternate, DP over TBT, native DP
or native HDMI.

Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Anusha Srivatsa <anusha.srivatsa@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180616000530.5357-3-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_irq.c | 49 ++++++++++++++++++++++++++++++-----------
 drivers/gpu/drm/i915/i915_reg.h | 11 ++++++++-
 2 files changed, 46 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 40e563eb3a1f..46aaef5c1851 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -115,11 +115,11 @@ static const u32 hpd_bxt[HPD_NUM_PINS] = {
 	[HPD_PORT_C] = BXT_DE_PORT_HP_DDIC
 };
 
-static const u32 hpd_tc_gen11[HPD_NUM_PINS] = {
-	[HPD_PORT_C] = GEN11_TC1_HOTPLUG,
-	[HPD_PORT_D] = GEN11_TC2_HOTPLUG,
-	[HPD_PORT_E] = GEN11_TC3_HOTPLUG,
-	[HPD_PORT_F] = GEN11_TC4_HOTPLUG
+static const u32 hpd_gen11[HPD_NUM_PINS] = {
+	[HPD_PORT_C] = GEN11_TC1_HOTPLUG | GEN11_TBT1_HOTPLUG,
+	[HPD_PORT_D] = GEN11_TC2_HOTPLUG | GEN11_TBT2_HOTPLUG,
+	[HPD_PORT_E] = GEN11_TC3_HOTPLUG | GEN11_TBT3_HOTPLUG,
+	[HPD_PORT_F] = GEN11_TC4_HOTPLUG | GEN11_TBT4_HOTPLUG
 };
 
 /* IIR can theoretically queue up two events. Be paranoid. */
@@ -2624,20 +2624,35 @@ static void bxt_hpd_irq_handler(struct drm_i915_private *dev_priv,
 static void gen11_hpd_irq_handler(struct drm_i915_private *dev_priv, u32 iir)
 {
 	u32 pin_mask = 0, long_mask = 0;
-	u32 trigger_tc, dig_hotplug_reg;
+	u32 trigger_tc = iir & GEN11_DE_TC_HOTPLUG_MASK;
+	u32 trigger_tbt = iir & GEN11_DE_TBT_HOTPLUG_MASK;
 
-	trigger_tc = iir & GEN11_DE_TC_HOTPLUG_MASK;
 	if (trigger_tc) {
+		u32 dig_hotplug_reg;
+
 		dig_hotplug_reg = I915_READ(GEN11_TC_HOTPLUG_CTL);
 		I915_WRITE(GEN11_TC_HOTPLUG_CTL, dig_hotplug_reg);
 
 		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tc,
-				   dig_hotplug_reg, hpd_tc_gen11,
+				   dig_hotplug_reg, hpd_gen11,
+				   gen11_port_hotplug_long_detect);
+	}
+
+	if (trigger_tbt) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(GEN11_TBT_HOTPLUG_CTL);
+		I915_WRITE(GEN11_TBT_HOTPLUG_CTL, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask, trigger_tbt,
+				   dig_hotplug_reg, hpd_gen11,
 				   gen11_port_hotplug_long_detect);
+	}
+
+	if (pin_mask)
 		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
-	} else {
+	else
 		DRM_ERROR("Unexpected DE HPD interrupt 0x%08x\n", iir);
-	}
 }
 
 static irqreturn_t
@@ -3695,6 +3710,13 @@ static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
 		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC3) |
 		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4);
 	I915_WRITE(GEN11_TC_HOTPLUG_CTL, hotplug);
+
+	hotplug = I915_READ(GEN11_TBT_HOTPLUG_CTL);
+	hotplug |= GEN11_HOTPLUG_CTL_ENABLE(PORT_TC1) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC2) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC3) |
+		   GEN11_HOTPLUG_CTL_ENABLE(PORT_TC4);
+	I915_WRITE(GEN11_TBT_HOTPLUG_CTL, hotplug);
 }
 
 static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
@@ -3702,8 +3724,8 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	u32 hotplug_irqs, enabled_irqs;
 	u32 val;
 
-	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_tc_gen11);
-	hotplug_irqs = GEN11_DE_TC_HOTPLUG_MASK;
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_gen11);
+	hotplug_irqs = GEN11_DE_TC_HOTPLUG_MASK | GEN11_DE_TBT_HOTPLUG_MASK;
 
 	val = I915_READ(GEN11_DE_HPD_IMR);
 	val &= ~hotplug_irqs;
@@ -4088,7 +4110,8 @@ static void gen8_de_irq_postinstall(struct drm_i915_private *dev_priv)
 
 	if (INTEL_GEN(dev_priv) >= 11) {
 		u32 de_hpd_masked = 0;
-		u32 de_hpd_enables = GEN11_DE_TC_HOTPLUG_MASK;
+		u32 de_hpd_enables = GEN11_DE_TC_HOTPLUG_MASK |
+				     GEN11_DE_TBT_HOTPLUG_MASK;
 
 		GEN3_IRQ_INIT(GEN11_DE_HPD_, ~de_hpd_masked, de_hpd_enables);
 		gen11_hpd_detection_setup(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 21692228cb81..4bfd7a9bd75f 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7097,7 +7097,16 @@ enum {
 						 GEN11_TC3_HOTPLUG | \
 						 GEN11_TC2_HOTPLUG | \
 						 GEN11_TC1_HOTPLUG)
-
+#define  GEN11_TBT4_HOTPLUG			(1 << 3)
+#define  GEN11_TBT3_HOTPLUG			(1 << 2)
+#define  GEN11_TBT2_HOTPLUG			(1 << 1)
+#define  GEN11_TBT1_HOTPLUG			(1 << 0)
+#define  GEN11_DE_TBT_HOTPLUG_MASK		(GEN11_TBT4_HOTPLUG | \
+						 GEN11_TBT3_HOTPLUG | \
+						 GEN11_TBT2_HOTPLUG | \
+						 GEN11_TBT1_HOTPLUG)
+
+#define GEN11_TBT_HOTPLUG_CTL				_MMIO(0x44030)
 #define GEN11_TC_HOTPLUG_CTL				_MMIO(0x44038)
 #define  GEN11_HOTPLUG_CTL_ENABLE(tc_port)		(8 << (tc_port) * 4)
 #define  GEN11_HOTPLUG_CTL_LONG_DETECT(tc_port)		(2 << (tc_port) * 4)
-- 
cgit v1.2.3


From 9554c1be48b437f192234eebb89f124ba3ef0e25 Mon Sep 17 00:00:00 2001
From: Xiubo Li <xiubli@redhat.com>
Date: Thu, 7 Jun 2018 02:31:36 -0400
Subject: scsi: tcmu: remove useless code and clean up the code style.

Since the TCMU_RING_SIZE macro is not using here will discard it and at the
same time clean up the code style.

Signed-off-by: Xiubo Li <xiubli@redhat.com>
Acked-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 7f96dfa32b9c..e4a76f9771ce 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -83,14 +83,10 @@
 #define DATA_BLOCK_SIZE PAGE_SIZE
 #define DATA_BLOCK_SHIFT PAGE_SHIFT
 #define DATA_BLOCK_BITS_DEF (256 * 1024)
-#define DATA_SIZE (DATA_BLOCK_BITS * DATA_BLOCK_SIZE)
 
 #define TCMU_MBS_TO_BLOCKS(_mbs) (_mbs << (20 - DATA_BLOCK_SHIFT))
 #define TCMU_BLOCKS_TO_MBS(_blocks) (_blocks >> (20 - DATA_BLOCK_SHIFT))
 
-/* The total size of the ring is 8M + 256K * PAGE_SIZE */
-#define TCMU_RING_SIZE (CMDR_SIZE + DATA_SIZE)
-
 /*
  * Default number of global data blocks(512K * PAGE_SIZE)
  * when the unmap thread will be started.
@@ -283,7 +279,7 @@ static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
 	if (!info->attrs[TCMU_ATTR_CMD_STATUS] ||
 	    !info->attrs[TCMU_ATTR_DEVICE_ID]) {
 		printk(KERN_ERR "TCMU_ATTR_CMD_STATUS or TCMU_ATTR_DEVICE_ID not set, doing nothing\n");
-                return -EINVAL;
+		return -EINVAL;
         }
 
 	dev_id = nla_get_u32(info->attrs[TCMU_ATTR_DEVICE_ID]);
@@ -313,7 +309,7 @@ static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
 
 	spin_unlock(&udev->nl_cmd_lock);
 	if (!is_removed)
-		 target_undepend_item(&dev->dev_group.cg_item);
+		target_undepend_item(&dev->dev_group.cg_item);
 	if (!ret)
 		complete(&nl_cmd->complete);
 	return ret;
-- 
cgit v1.2.3


From 999c85134db71599698917775f35fd56ced2dc0a Mon Sep 17 00:00:00 2001
From: Chaitra P B <chaitra.basappa@broadcom.com>
Date: Thu, 31 May 2018 06:34:47 -0400
Subject: scsi: mpt3sas: Don't abort I/Os issued to NVMe drives while
 processing Async Broadcast primitive event.

Linux driver when receives Broadcast Asynchronous Event Notification (BAEN)
from the controller firmware, checks all pending I/Os at the driver level
and issues query task, abort task TMs. This is done in the driver to handle
drives which are connected with multiple initiators and undergoing target
resets. In the BAEN handling code, the I/Os issued to NVMe drives are also
handled and query task and abort task TMs are issued, which are not
necessary as there is no multi-initiator and no BAEN concept with NVMe
drives. Hence when the driver checks for pending I/Os it skips NVMe drives
at this moment.

Signed-off-by: Chaitra P B <chaitra.basappa@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b8d131a455d0..d31f0ccdf688 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -7483,6 +7483,10 @@ _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
 		if (sas_device_priv_data->sas_target->flags &
 		    MPT_TARGET_FLAGS_VOLUME)
 			continue;
+		 /* skip PCIe devices */
+		if (sas_device_priv_data->sas_target->flags &
+		    MPT_TARGET_FLAGS_PCIE_DEVICE)
+			continue;
 
 		handle = sas_device_priv_data->sas_target->handle;
 		lun = sas_device_priv_data->lun;
-- 
cgit v1.2.3


From e3586147b8b123fcaf739f4dcda741e13c5eaf9e Mon Sep 17 00:00:00 2001
From: Chaitra P B <chaitra.basappa@broadcom.com>
Date: Thu, 31 May 2018 06:34:48 -0400
Subject: scsi: mpt3sas: Incorrect command status was set/marked as not used.

In _scsih_scan_finished driver should mark port_enable_cmd.status as
'command not used', instead base_cmds.status was marked as 'command not
used'. Update code to mark port_enable_cmd.status as 'command not used'.

Signed-off-by: Chaitra P B <chaitra.basappa@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index d31f0ccdf688..884878b2113d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -10394,7 +10394,7 @@ scsih_scan_finished(struct Scsi_Host *shost, unsigned long time)
 	}
 
 	if (time >= (300 * HZ)) {
-		ioc->base_cmds.status = MPT3_CMD_NOT_USED;
+		ioc->port_enable_cmds.status = MPT3_CMD_NOT_USED;
 		pr_info(MPT3SAS_FMT
 			"port enable: FAILED with timeout (timeout=300s)\n",
 			ioc->name);
@@ -10416,7 +10416,7 @@ scsih_scan_finished(struct Scsi_Host *shost, unsigned long time)
 	}
 
 	pr_info(MPT3SAS_FMT "port enable: SUCCESS\n", ioc->name);
-	ioc->base_cmds.status = MPT3_CMD_NOT_USED;
+	ioc->port_enable_cmds.status = MPT3_CMD_NOT_USED;
 
 	if (ioc->wait_for_discovery_to_complete) {
 		ioc->wait_for_discovery_to_complete = 0;
-- 
cgit v1.2.3


From 20a044332dc47e91045670311f9f9dcb1e32483f Mon Sep 17 00:00:00 2001
From: Chaitra P B <chaitra.basappa@broadcom.com>
Date: Thu, 31 May 2018 06:34:49 -0400
Subject: scsi: mpt3sas: Don't access the structure after decrementing it's
 instance reference count.

While configuring of NVMe device handling, _pcie_device structure member
was accessed after its reference count is decremented/put. Hence modified
code to access member of _pcie_device structure before its reference count
is decremented/put.

Signed-off-by: Chaitra P B <chaitra.basappa@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 884878b2113d..bf578271a844 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2365,13 +2365,14 @@ scsih_slave_configure(struct scsi_device *sdev)
 				"connector name( %s)\n", ds,
 				pcie_device->enclosure_level,
 				pcie_device->connector_name);
-		pcie_device_put(pcie_device);
-		spin_unlock_irqrestore(&ioc->pcie_device_lock, flags);
-		scsih_change_queue_depth(sdev, qdepth);
 
 		if (pcie_device->nvme_mdts)
 			blk_queue_max_hw_sectors(sdev->request_queue,
 					pcie_device->nvme_mdts/512);
+
+		pcie_device_put(pcie_device);
+		spin_unlock_irqrestore(&ioc->pcie_device_lock, flags);
+		scsih_change_queue_depth(sdev, qdepth);
 		/* Enable QUEUE_FLAG_NOMERGES flag, so that IOs won't be
 		 ** merged and can eliminate holes created during merging
 		 ** operation.
-- 
cgit v1.2.3


From d37306ca0eacdc040e1df91910123117a9df6d40 Mon Sep 17 00:00:00 2001
From: Chaitra P B <chaitra.basappa@broadcom.com>
Date: Thu, 31 May 2018 06:34:50 -0400
Subject: scsi: mpt3sas: Fix, False timeout prints for ioctl and other internal
 commands during controller reset.

When an ioctl is sent to FW, and if there is a controller reset issued
before ioctl gets completed, then in controller reset path all the pending
ioctl commands are terminated from "mpt3sas_ctl_reset_handler" function.
This will wake up the waiting ioctl commands in ioctl path and print
timeouts which are actually not timeouts.

Introduced "mpt3sas_base_check_cmd_timeout" function to check and print
whether command got timed out (or) terminated due to Host reset.

Signed-off-by: Chaitra P B <chaitra.basappa@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c   | 52 +++++++++++++++++++++++++----------
 drivers/scsi/mpt3sas/mpt3sas_base.h   |  2 ++
 drivers/scsi/mpt3sas/mpt3sas_config.c |  7 ++---
 drivers/scsi/mpt3sas/mpt3sas_ctl.c    | 38 ++++++++++---------------
 drivers/scsi/mpt3sas/mpt3sas_scsih.c  | 16 +++++------
 5 files changed, 65 insertions(+), 50 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 569392d0d4c9..b397cc2d18f5 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -101,6 +101,34 @@ MODULE_PARM_DESC(mpt3sas_fwfault_debug,
 static int
 _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc);
 
+/**
+ * mpt3sas_base_check_cmd_timeout - Function
+ *		to check timeout and command termination due
+ *		to Host reset.
+ *
+ * @ioc:	per adapter object.
+ * @status:	Status of issued command.
+ * @mpi_request:mf request pointer.
+ * @sz:		size of buffer.
+ *
+ * @Returns - 1/0 Reset to be done or Not
+ */
+u8
+mpt3sas_base_check_cmd_timeout(struct MPT3SAS_ADAPTER *ioc,
+		u8 status, void *mpi_request, int sz)
+{
+	u8 issue_reset = 0;
+
+	if (!(status & MPT3_CMD_RESET))
+		issue_reset = 1;
+
+	pr_err(MPT3SAS_FMT "Command %s\n", ioc->name,
+	    ((issue_reset == 0) ? "terminated due to Host Reset" : "Timeout"));
+	_debug_dump_mf(mpi_request, sz);
+
+	return issue_reset;
+}
+
 /**
  * _scsih_set_fwfault_debug - global setting of ioc->fwfault_debug.
  *
@@ -5355,7 +5383,7 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
 {
 	u16 smid;
 	u32 ioc_state;
-	bool issue_reset = false;
+	u8 issue_reset = 0;
 	int rc;
 	void *request;
 	u16 wait_state_count;
@@ -5414,12 +5442,10 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
 	    ioc->ioc_link_reset_in_progress)
 		ioc->ioc_link_reset_in_progress = 0;
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2SasIoUnitControlRequest_t)/4);
-		if (!(ioc->base_cmds.status & MPT3_CMD_RESET))
-			issue_reset = true;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->base_cmds.status, mpi_request,
+				sizeof(Mpi2SasIoUnitControlRequest_t)/4);
 		goto issue_host_reset;
 	}
 	if (ioc->base_cmds.status & MPT3_CMD_REPLY_VALID)
@@ -5457,7 +5483,7 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 {
 	u16 smid;
 	u32 ioc_state;
-	bool issue_reset = false;
+	u8 issue_reset = 0;
 	int rc;
 	void *request;
 	u16 wait_state_count;
@@ -5510,12 +5536,10 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 	wait_for_completion_timeout(&ioc->base_cmds.done,
 	    msecs_to_jiffies(10000));
 	if (!(ioc->base_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2SepRequest_t)/4);
-		if (!(ioc->base_cmds.status & MPT3_CMD_RESET))
-			issue_reset = false;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->base_cmds.status, mpi_request,
+				sizeof(Mpi2SepRequest_t)/4);
 		goto issue_host_reset;
 	}
 	if (ioc->base_cmds.status & MPT3_CMD_REPLY_VALID)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index f02974c0be4a..ec222add0bb5 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1482,6 +1482,8 @@ int mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc);
 void
 mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc);
 
+u8 mpt3sas_base_check_cmd_timeout(struct MPT3SAS_ADAPTER *ioc,
+	u8 status, void *mpi_request, int sz);
 
 /* scsih shared API */
 struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c
index e87c76a832f6..0d87e7bef215 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_config.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_config.c
@@ -406,10 +406,9 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
 	mpt3sas_base_put_smid_default(ioc, smid);
 	wait_for_completion_timeout(&ioc->config_cmds.done, timeout*HZ);
 	if (!(ioc->config_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2ConfigRequest_t)/4);
+		mpt3sas_base_check_cmd_timeout(ioc,
+			ioc->config_cmds.status, mpi_request,
+			sizeof(Mpi2ConfigRequest_t)/4);
 		retry_count++;
 		if (ioc->config_cmds.smid == smid)
 			mpt3sas_base_free_smid(ioc, smid);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 3269ef43f07e..1005249a0f25 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -995,11 +995,10 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		ioc->ignore_loginfos = 0;
 	}
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request, karg.data_sge_offset);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				karg.data_sge_offset);
 		goto issue_host_reset;
 	}
 
@@ -1621,12 +1620,10 @@ _ctl_diag_register_2(struct MPT3SAS_ADAPTER *ioc,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2DiagBufferPostRequest_t)/4);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				sizeof(Mpi2DiagBufferPostRequest_t)/4);
 		goto issue_host_reset;
 	}
 
@@ -1968,12 +1965,9 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2DiagReleaseRequest_t)/4);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			*issue_reset = 1;
+		*issue_reset = mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				sizeof(Mpi2DiagReleaseRequest_t)/4);
 		rc = -EFAULT;
 		goto out;
 	}
@@ -2235,12 +2229,10 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 	    MPT3_IOCTL_DEFAULT_TIMEOUT*HZ);
 
 	if (!(ioc->ctl_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n", ioc->name,
-		    __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2DiagBufferPostRequest_t)/4);
-		if (!(ioc->ctl_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->ctl_cmds.status, mpi_request,
+				sizeof(Mpi2DiagBufferPostRequest_t)/4);
 		goto issue_host_reset;
 	}
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index bf578271a844..23902ad3cae5 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2709,11 +2709,9 @@ mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 	mpt3sas_base_put_smid_hi_priority(ioc, smid, msix_task);
 	wait_for_completion_timeout(&ioc->tm_cmds.done, timeout*HZ);
 	if (!(ioc->tm_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		_debug_dump_mf(mpi_request,
-		    sizeof(Mpi2SCSITaskManagementRequest_t)/4);
-		if (!(ioc->tm_cmds.status & MPT3_CMD_RESET)) {
+		if (mpt3sas_base_check_cmd_timeout(ioc,
+			ioc->tm_cmds.status, mpi_request,
+			sizeof(Mpi2SCSITaskManagementRequest_t)/4)) {
 			rc = mpt3sas_base_hard_reset_handler(ioc,
 					FORCE_BIG_HAMMER);
 			rc = (!rc) ? SUCCESS : FAILED;
@@ -7741,10 +7739,10 @@ _scsih_ir_fastpath(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phys_disk_num)
 	wait_for_completion_timeout(&ioc->scsih_cmds.done, 10*HZ);
 
 	if (!(ioc->scsih_cmds.status & MPT3_CMD_COMPLETE)) {
-		pr_err(MPT3SAS_FMT "%s: timeout\n",
-		    ioc->name, __func__);
-		if (!(ioc->scsih_cmds.status & MPT3_CMD_RESET))
-			issue_reset = 1;
+		issue_reset =
+			mpt3sas_base_check_cmd_timeout(ioc,
+				ioc->scsih_cmds.status, mpi_request,
+				sizeof(Mpi2RaidActionRequest_t)/4);
 		rc = -EFAULT;
 		goto out;
 	}
-- 
cgit v1.2.3


From 2b48be65685a23f4ffc7a06858992bc31e98e198 Mon Sep 17 00:00:00 2001
From: Chaitra P B <chaitra.basappa@broadcom.com>
Date: Thu, 31 May 2018 06:34:51 -0400
Subject: scsi: mpt3sas: As per MPI-spec, use combined reply queue for SAS3.5
 controllers when HBA supports more than 16 MSI-x vectors.

Presently driver is using combined reply queue feature when MSI-x vectors >
8 for both SAS3 and SAS3.5 controllers.  But as per MPI-spec,

1. For SAS3 controllers, driver should use combined reply queue when HBA
supports more than 8 MSI-x vectors.

2. For SAS3.5 controllers, driver should use combined reply queue when HBA
supports more than 16 MSI-x vectors.

Modified driver code to use combined reply queue for SAS3 controllers when
HBA supports > 8 MSI-x vectors and for SAS3.5 controllers when HBA supports
> 16 MSI-x vectors.

Signed-off-by: Chaitra P B <chaitra.basappa@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 15 ++++++++-------
 drivers/scsi/mpt3sas/mpt3sas_base.h |  1 +
 2 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index b397cc2d18f5..8273ed7e7896 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2952,10 +2952,9 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
 	_base_free_irq(ioc);
 	_base_disable_msix(ioc);
 
-	if (ioc->combined_reply_queue) {
-		kfree(ioc->replyPostRegisterIndex);
-		ioc->replyPostRegisterIndex = NULL;
-	}
+	kfree(ioc->replyPostRegisterIndex);
+	ioc->replyPostRegisterIndex = NULL;
+
 
 	if (ioc->chip_phys) {
 		iounmap(ioc->chip);
@@ -3062,7 +3061,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 	/* Use the Combined reply queue feature only for SAS3 C0 & higher
 	 * revision HBAs and also only when reply queue count is greater than 8
 	 */
-	if (ioc->combined_reply_queue && ioc->reply_queue_count > 8) {
+	if (ioc->combined_reply_queue) {
 		/* Determine the Supplemental Reply Post Host Index Registers
 		 * Addresse. Supplemental Reply Post Host Index Registers
 		 * starts at offset MPI25_SUP_REPLY_POST_HOST_INDEX_OFFSET and
@@ -3086,8 +3085,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
 			     MPI25_SUP_REPLY_POST_HOST_INDEX_OFFSET +
 			     (i * MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET));
 		}
-	} else
-		ioc->combined_reply_queue = 0;
+	}
 
 	if (ioc->is_warpdrive) {
 		ioc->reply_post_host_index[0] = (resource_size_t __iomem *)
@@ -5705,6 +5703,9 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc)
 	facts->WhoInit = mpi_reply.WhoInit;
 	facts->NumberOfPorts = mpi_reply.NumberOfPorts;
 	facts->MaxMSIxVectors = mpi_reply.MaxMSIxVectors;
+	if (ioc->msix_enable && (facts->MaxMSIxVectors <=
+	    MAX_COMBINED_MSIX_VECTORS(ioc->is_gen35_ioc)))
+		ioc->combined_reply_queue = 0;
 	facts->RequestCredit = le16_to_cpu(mpi_reply.RequestCredit);
 	facts->MaxReplyDescriptorPostQueueDepth =
 	    le16_to_cpu(mpi_reply.MaxReplyDescriptorPostQueueDepth);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index ec222add0bb5..3d49eadeb789 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -323,6 +323,7 @@
  * There are twelve Supplemental Reply Post Host Index Registers
  * and each register is at offset 0x10 bytes from the previous one.
  */
+#define MAX_COMBINED_MSIX_VECTORS(gen35) ((gen35 == 1) ? 16 : 8)
 #define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G3	12
 #define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_COUNT_G35	16
 #define MPT3_SUP_REPLY_POST_HOST_INDEX_REG_OFFSET	(0x10)
-- 
cgit v1.2.3


From 2cd4bf89f76311944fd7415a2402bd88f1eaf79d Mon Sep 17 00:00:00 2001
From: Chaitra P B <chaitra.basappa@broadcom.com>
Date: Thu, 31 May 2018 06:34:52 -0400
Subject: scsi: mpt3sas: Update driver version "26.100.00.00"

Updated driver version to "26.100.00.00"

Signed-off-by: Chaitra P B <chaitra.basappa@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 3d49eadeb789..b00670a54106 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -74,8 +74,8 @@
 #define MPT3SAS_DRIVER_NAME		"mpt3sas"
 #define MPT3SAS_AUTHOR "Avago Technologies <MPT-FusionLinux.pdl@avagotech.com>"
 #define MPT3SAS_DESCRIPTION	"LSI MPT Fusion SAS 3.0 Device Driver"
-#define MPT3SAS_DRIVER_VERSION		"25.100.00.00"
-#define MPT3SAS_MAJOR_VERSION		25
+#define MPT3SAS_DRIVER_VERSION		"26.100.00.00"
+#define MPT3SAS_MAJOR_VERSION		26
 #define MPT3SAS_MINOR_VERSION		100
 #define MPT3SAS_BUILD_VERSION		0
 #define MPT3SAS_RELEASE_VERSION	00
-- 
cgit v1.2.3


From 2747e6be4ca71b1c44ed25c89cc100f89a4e913b Mon Sep 17 00:00:00 2001
From: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Date: Mon, 4 Jun 2018 03:45:09 -0700
Subject: scsi: megaraid_sas: Do not do Kill adapter if GET_CTRL_INFO times out

If MR_DCMD_CTRL_GET_INFO DCMD timed out, return failure rather than doing
kill adapter.

Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/megaraid/megaraid_sas_base.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 71d97573a667..6554ce81c0dd 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -4755,14 +4755,15 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 				__func__, __LINE__);
 			break;
 		}
+		break;
 	case DCMD_FAILED:
 		megaraid_sas_kill_hba(instance);
 		break;
 
 	}
 
-	megasas_return_cmd(instance, cmd);
-
+	if (ret != DCMD_TIMEOUT)
+		megasas_return_cmd(instance, cmd);
 
 	return ret;
 }
-- 
cgit v1.2.3


From c3b10a55abc943a526aaecd7e860b15671beb906 Mon Sep 17 00:00:00 2001
From: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Date: Mon, 4 Jun 2018 03:45:10 -0700
Subject: scsi: megaraid_sas: Update controller info during resume

There is a possibility that firmware on the controller was upgraded before
system was suspended. During resume, driver needs to read updated
controller properties.

Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/megaraid/megaraid_sas_base.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index 6554ce81c0dd..c787fed48ec7 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -6790,6 +6790,9 @@ megasas_resume(struct pci_dev *pdev)
 			goto fail_init_mfi;
 	}
 
+	if (megasas_get_ctrl_info(instance) != DCMD_SUCCESS)
+		goto fail_init_mfi;
+
 	tasklet_init(&instance->isr_tasklet, instance->instancet->tasklet,
 		     (unsigned long)instance);
 
-- 
cgit v1.2.3


From 9c9db8b792a27d38cbb2a4f51a56e35b4506c897 Mon Sep 17 00:00:00 2001
From: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Date: Mon, 4 Jun 2018 03:45:11 -0700
Subject: scsi: megaraid_sas: Return immediately from
 wait_for_adapter_operational after kill adapter

While driver is waiting for adapter to become operational, if a kill
adapter is issued, driver can bail out from the wait loop immediately
rather than waiting for the entire 180 seconds.

Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/megaraid/megaraid_sas_base.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index c787fed48ec7..fd2ce75b4d73 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -6846,12 +6846,12 @@ megasas_wait_for_adapter_operational(struct megasas_instance *instance)
 {
 	int wait_time = MEGASAS_RESET_WAIT_TIME * 2;
 	int i;
-
-	if (atomic_read(&instance->adprecovery) == MEGASAS_HW_CRITICAL_ERROR)
-		return 1;
+	u8 adp_state;
 
 	for (i = 0; i < wait_time; i++) {
-		if (atomic_read(&instance->adprecovery)	== MEGASAS_HBA_OPERATIONAL)
+		adp_state = atomic_read(&instance->adprecovery);
+		if ((adp_state == MEGASAS_HBA_OPERATIONAL) ||
+		    (adp_state == MEGASAS_HW_CRITICAL_ERROR))
 			break;
 
 		if (!(i % MEGASAS_RESET_NOTICE_INTERVAL))
@@ -6860,9 +6860,10 @@ megasas_wait_for_adapter_operational(struct megasas_instance *instance)
 		msleep(1000);
 	}
 
-	if (atomic_read(&instance->adprecovery) != MEGASAS_HBA_OPERATIONAL) {
-		dev_info(&instance->pdev->dev, "%s timed out while waiting for HBA to recover.\n",
-			__func__);
+	if (adp_state != MEGASAS_HBA_OPERATIONAL) {
+		dev_info(&instance->pdev->dev,
+			 "%s HBA failed to become operational, adp_state %d\n",
+			 __func__, adp_state);
 		return 1;
 	}
 
-- 
cgit v1.2.3


From e9495e2de7769a9cfec03281d611313347f337ca Mon Sep 17 00:00:00 2001
From: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Date: Mon, 4 Jun 2018 03:45:12 -0700
Subject: scsi: megaraid_sas: Support FW provided TM timeout values

Firmware provides drive specific target reset and task abort timeout
values. Driver needs to use these timeout values during task management
calls. If FW does not provide these values, fall back to using earlier
default timeout of 50 seconds for TM.

[mkp: clarified comment]

Signed-off-by: Sumit Saxena <sumit.saxena@broadcom.com>
Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/megaraid/megaraid_sas.h        | 29 ++++++++++++++++++++---
 drivers/scsi/megaraid/megaraid_sas_base.c   | 36 +++++++++++++++++++++++------
 drivers/scsi/megaraid/megaraid_sas_fusion.c | 36 +++++++++++++++++++++++------
 3 files changed, 84 insertions(+), 17 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index 75dc25f78336..c199070f04b4 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -709,7 +709,8 @@ struct MR_TARGET_PROPERTIES {
 	u32    max_io_size_kb;
 	u32    device_qdepth;
 	u32    sector_size;
-	u8     reserved[500];
+	u8     reset_tmo;
+	u8     reserved[499];
 } __packed;
 
  /*
@@ -1400,6 +1401,19 @@ struct megasas_ctrl_info {
 	#endif
 		} adapter_operations4;
 	u8 pad[0x800 - 0x7FE]; /* 0x7FE pad to 2K for expansion */
+
+	u32 size;
+	u32 pad1;
+
+	u8 reserved6[64];
+
+	u32 rsvdForAdptOp[64];
+
+	u8 reserved7[3];
+
+	u8 TaskAbortTO;	/* Timeout value in seconds used by Abort Task TM */
+	u8 MaxResetTO;	/* Max Supported Reset timeout in seconds. */
+	u8 reserved8[3];
 } __packed;
 
 /*
@@ -1472,6 +1486,7 @@ enum FW_BOOT_CONTEXT {
 #define MEGASAS_DEFAULT_CMD_TIMEOUT		90
 #define MEGASAS_THROTTLE_QUEUE_DEPTH		16
 #define MEGASAS_BLOCKED_CMD_TIMEOUT		60
+#define MEGASAS_DEFAULT_TM_TIMEOUT		50
 /*
  * FW reports the maximum of number of commands that it can accept (maximum
  * commands that can be outstanding) at any time. The driver must report a
@@ -1915,7 +1930,9 @@ struct MR_PRIV_DEVICE {
 	bool is_tm_capable;
 	bool tm_busy;
 	atomic_t r1_ldio_hint;
-	u8   interface_type;
+	u8 interface_type;
+	u8 task_abort_tmo;
+	u8 target_reset_tmo;
 };
 struct megasas_cmd;
 
@@ -2291,6 +2308,8 @@ struct megasas_instance {
 	u8 adapter_type;
 	bool consistent_mask_64bit;
 	bool support_nvme_passthru;
+	u8 task_abort_tmo;
+	u8 max_reset_tmo;
 };
 struct MR_LD_VF_MAP {
 	u32 size;
@@ -2512,7 +2531,11 @@ int megasas_get_ctrl_info(struct megasas_instance *instance);
 /* PD sequence */
 int
 megasas_sync_pd_seq_num(struct megasas_instance *instance, bool pend);
-void megasas_set_dynamic_target_properties(struct scsi_device *sdev);
+void megasas_set_dynamic_target_properties(struct scsi_device *sdev,
+					   bool is_target_prop);
+int megasas_get_target_prop(struct megasas_instance *instance,
+			    struct scsi_device *sdev);
+
 int megasas_set_crash_dump_params(struct megasas_instance *instance,
 	u8 crash_buf_state);
 void megasas_free_host_crash_buffer(struct megasas_instance *instance);
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index fd2ce75b4d73..e6ba02793610 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -120,8 +120,7 @@ static int megasas_register_aen(struct megasas_instance *instance,
 				u32 seq_num, u32 class_locale_word);
 static void megasas_get_pd_info(struct megasas_instance *instance,
 				struct scsi_device *sdev);
-static int megasas_get_target_prop(struct megasas_instance *instance,
-				   struct scsi_device *sdev);
+
 /*
  * PCI ID table for all supported controllers
  */
@@ -1794,7 +1793,8 @@ static struct megasas_instance *megasas_lookup_instance(u16 host_no)
 *
 * Returns void
 */
-void megasas_set_dynamic_target_properties(struct scsi_device *sdev)
+void megasas_set_dynamic_target_properties(struct scsi_device *sdev,
+					   bool is_target_prop)
 {
 	u16 pd_index = 0, ld;
 	u32 device_id;
@@ -1834,6 +1834,22 @@ void megasas_set_dynamic_target_properties(struct scsi_device *sdev)
 		mr_device_priv_data->is_tm_capable =
 			pd_sync->seq[pd_index].capability.tmCapable;
 	}
+
+	if (is_target_prop && instance->tgt_prop->reset_tmo) {
+		/*
+		 * If FW provides a target reset timeout value, driver will use
+		 * it. If not set, fallback to default values.
+		 */
+		mr_device_priv_data->target_reset_tmo =
+			min_t(u8, instance->max_reset_tmo,
+			      instance->tgt_prop->reset_tmo);
+		mr_device_priv_data->task_abort_tmo = instance->task_abort_tmo;
+	} else {
+		mr_device_priv_data->target_reset_tmo =
+						MEGASAS_DEFAULT_TM_TIMEOUT;
+		mr_device_priv_data->task_abort_tmo =
+						MEGASAS_DEFAULT_TM_TIMEOUT;
+	}
 }
 
 /*
@@ -1967,10 +1983,10 @@ static int megasas_slave_configure(struct scsi_device *sdev)
 	is_target_prop = (ret_target_prop == DCMD_SUCCESS) ? true : false;
 	megasas_set_static_target_properties(sdev, is_target_prop);
 
-	mutex_unlock(&instance->reset_mutex);
-
 	/* This sdev property may change post OCR */
-	megasas_set_dynamic_target_properties(sdev);
+	megasas_set_dynamic_target_properties(sdev, is_target_prop);
+
+	mutex_unlock(&instance->reset_mutex);
 
 	return 0;
 }
@@ -4720,6 +4736,8 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 			ci->adapter_operations4.support_pd_map_target_id;
 		instance->support_nvme_passthru =
 			ci->adapter_operations4.support_nvme_passthru;
+		instance->task_abort_tmo = ci->TaskAbortTO;
+		instance->max_reset_tmo = ci->MaxResetTO;
 
 		/*Check whether controller is iMR or MR */
 		instance->is_imr = (ci->memory_size ? 0 : 1);
@@ -4738,6 +4756,10 @@ megasas_get_ctrl_info(struct megasas_instance *instance)
 			instance->secure_jbod_support ? "Yes" : "No");
 		dev_info(&instance->pdev->dev, "NVMe passthru support\t: %s\n",
 			 instance->support_nvme_passthru ? "Yes" : "No");
+		dev_info(&instance->pdev->dev,
+			 "FW provided TM TaskAbort/Reset timeout\t: %d secs/%d secs\n",
+			 instance->task_abort_tmo, instance->max_reset_tmo);
+
 		break;
 
 	case DCMD_TIMEOUT:
@@ -5832,7 +5854,7 @@ megasas_register_aen(struct megasas_instance *instance, u32 seq_num,
  *
  * Returns 0 on success non-zero on failure.
  */
-static int
+int
 megasas_get_target_prop(struct megasas_instance *instance,
 			struct scsi_device *sdev)
 {
diff --git a/drivers/scsi/megaraid/megaraid_sas_fusion.c b/drivers/scsi/megaraid/megaraid_sas_fusion.c
index 94c23ad51179..c7f95bace353 100644
--- a/drivers/scsi/megaraid/megaraid_sas_fusion.c
+++ b/drivers/scsi/megaraid/megaraid_sas_fusion.c
@@ -4108,7 +4108,8 @@ megasas_tm_response_code(struct megasas_instance *instance,
  */
 static int
 megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
-	uint channel, uint id, u16 smid_task, u8 type)
+	uint channel, uint id, u16 smid_task, u8 type,
+	struct MR_PRIV_DEVICE *mr_device_priv_data)
 {
 	struct MR_TASK_MANAGE_REQUEST *mr_request;
 	struct MPI2_SCSI_TASK_MANAGE_REQUEST *mpi_request;
@@ -4119,6 +4120,7 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 	struct fusion_context *fusion = NULL;
 	struct megasas_cmd_fusion *scsi_lookup;
 	int rc;
+	int timeout = MEGASAS_DEFAULT_TM_TIMEOUT;
 	struct MPI2_SCSI_TASK_MANAGE_REPLY *mpi_reply;
 
 	fusion = instance->ctrl_context;
@@ -4170,7 +4172,16 @@ megasas_issue_tm(struct megasas_instance *instance, u16 device_handle,
 	init_completion(&cmd_fusion->done);
 	megasas_fire_cmd_fusion(instance, req_desc);
 
-	timeleft = wait_for_completion_timeout(&cmd_fusion->done, 50 * HZ);
+	switch (type) {
+	case MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK:
+		timeout = mr_device_priv_data->task_abort_tmo;
+		break;
+	case MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET:
+		timeout = mr_device_priv_data->target_reset_tmo;
+		break;
+	}
+
+	timeleft = wait_for_completion_timeout(&cmd_fusion->done, timeout * HZ);
 
 	if (!timeleft) {
 		dev_err(&instance->pdev->dev,
@@ -4363,7 +4374,8 @@ int megasas_task_abort_fusion(struct scsi_cmnd *scmd)
 	mr_device_priv_data->tm_busy = 1;
 	ret = megasas_issue_tm(instance, devhandle,
 			scmd->device->channel, scmd->device->id, smid,
-			MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK);
+			MPI2_SCSITASKMGMT_TASKTYPE_ABORT_TASK,
+			mr_device_priv_data);
 	mr_device_priv_data->tm_busy = 0;
 
 	mutex_unlock(&instance->reset_mutex);
@@ -4435,7 +4447,8 @@ int megasas_reset_target_fusion(struct scsi_cmnd *scmd)
 	mr_device_priv_data->tm_busy = 1;
 	ret = megasas_issue_tm(instance, devhandle,
 			scmd->device->channel, scmd->device->id, 0,
-			MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET);
+			MPI2_SCSITASKMGMT_TASKTYPE_TARGET_RESET,
+			mr_device_priv_data);
 	mr_device_priv_data->tm_busy = 0;
 	mutex_unlock(&instance->reset_mutex);
 out:
@@ -4490,6 +4503,8 @@ int megasas_reset_fusion(struct Scsi_Host *shost, int reason)
 	u32 io_timeout_in_crash_mode = 0;
 	struct scsi_cmnd *scmd_local = NULL;
 	struct scsi_device *sdev;
+	int ret_target_prop = DCMD_FAILED;
+	bool is_target_prop = false;
 
 	instance = (struct megasas_instance *)shost->hostdata;
 	fusion = instance->ctrl_context;
@@ -4661,9 +4676,6 @@ transition_to_ready:
 
 			megasas_setup_jbod_map(instance);
 
-			shost_for_each_device(sdev, shost)
-				megasas_set_dynamic_target_properties(sdev);
-
 			/* reset stream detection array */
 			if (instance->adapter_type == VENTURA_SERIES) {
 				for (j = 0; j < MAX_LOGICAL_DRIVES_EXT; ++j) {
@@ -4677,6 +4689,16 @@ transition_to_ready:
 			clear_bit(MEGASAS_FUSION_IN_RESET,
 				  &instance->reset_flags);
 			instance->instancet->enable_intr(instance);
+
+			shost_for_each_device(sdev, shost) {
+				if ((instance->tgt_prop) &&
+				    (instance->nvme_page_size))
+					ret_target_prop = megasas_get_target_prop(instance, sdev);
+
+				is_target_prop = (ret_target_prop == DCMD_SUCCESS) ? true : false;
+				megasas_set_dynamic_target_properties(sdev, is_target_prop);
+			}
+
 			atomic_set(&instance->adprecovery, MEGASAS_HBA_OPERATIONAL);
 
 			dev_info(&instance->pdev->dev, "Interrupts are enabled and"
-- 
cgit v1.2.3


From cda6d30e60c4abceee3ad4f80559b8e37385549c Mon Sep 17 00:00:00 2001
From: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Date: Mon, 4 Jun 2018 03:45:13 -0700
Subject: scsi: megaraid_sas: driver version upgrade

Signed-off-by: Shivasharan S <shivasharan.srikanteshwara@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/megaraid/megaraid_sas.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/megaraid/megaraid_sas.h b/drivers/scsi/megaraid/megaraid_sas.h
index c199070f04b4..67d356d84717 100644
--- a/drivers/scsi/megaraid/megaraid_sas.h
+++ b/drivers/scsi/megaraid/megaraid_sas.h
@@ -35,8 +35,8 @@
 /*
  * MegaRAID SAS Driver meta data
  */
-#define MEGASAS_VERSION				"07.705.02.00-rc1"
-#define MEGASAS_RELDATE				"April 4, 2018"
+#define MEGASAS_VERSION				"07.706.03.00-rc1"
+#define MEGASAS_RELDATE				"May 21, 2018"
 
 /*
  * Device IDs
-- 
cgit v1.2.3


From 707c62352909a9be2453ae073e160de59d2d4a1f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 15:20:42 -0700
Subject: configfs: use kvasprintf() instead of open-coding it

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/configfs/item.c | 24 ++++--------------------
 1 file changed, 4 insertions(+), 20 deletions(-)

diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index 88f266efc09b..99d491cd01f9 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -64,7 +64,6 @@ static void config_item_init(struct config_item *item)
  */
 int config_item_set_name(struct config_item *item, const char *fmt, ...)
 {
-	int error = 0;
 	int limit = CONFIGFS_ITEM_NAME_LEN;
 	int need;
 	va_list args;
@@ -79,25 +78,11 @@ int config_item_set_name(struct config_item *item, const char *fmt, ...)
 	if (need < limit)
 		name = item->ci_namebuf;
 	else {
-		/*
-		 * Need more space? Allocate it and try again
-		 */
-		limit = need + 1;
-		name = kmalloc(limit, GFP_KERNEL);
-		if (!name) {
-			error = -ENOMEM;
-			goto Done;
-		}
 		va_start(args, fmt);
-		need = vsnprintf(name, limit, fmt, args);
+		name = kvasprintf(GFP_KERNEL, fmt, args);
 		va_end(args);
-
-		/* Still? Give up. */
-		if (need >= limit) {
-			kfree(name);
-			error = -EFAULT;
-			goto Done;
-		}
+		if (!name)
+			return -EFAULT;
 	}
 
 	/* Free the old name, if necessary. */
@@ -106,8 +91,7 @@ int config_item_set_name(struct config_item *item, const char *fmt, ...)
 
 	/* Now, set the new name */
 	item->ci_name = name;
- Done:
-	return error;
+	return 0;
 }
 EXPORT_SYMBOL(config_item_set_name);
 
-- 
cgit v1.2.3


From d5b65efd2b2e674668d773a82d858ce161956b0a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:38:43 +0200
Subject: i915: remove timespec_to_jiffies_timeout

This function has been unused since commit 5ed0bdf21a85 ("drm: i915:
Use nsec based interfaces"). Let's remove the definition as well now
to help get rid of all uses of 'timespec'.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618153855.2126048-1-arnd@arndb.de
---
 drivers/gpu/drm/i915/i915_drv.h | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index d00761a06f05..ebece44a807f 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3700,14 +3700,6 @@ static inline unsigned long nsecs_to_jiffies_timeout(const u64 n)
         return min_t(u64, MAX_JIFFY_OFFSET, nsecs_to_jiffies64(n) + 1);
 }
 
-static inline unsigned long
-timespec_to_jiffies_timeout(const struct timespec *value)
-{
-	unsigned long j = timespec_to_jiffies(value);
-
-	return min_t(unsigned long, MAX_JIFFY_OFFSET, j + 1);
-}
-
 /*
  * If you need to wait X milliseconds between events A and B, but event B
  * doesn't happen exactly after event A, you record the timestamp (jiffies) of
-- 
cgit v1.2.3


From 4a5f4d2f891bcff7285b5f7490ed5a7a5d516049 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 18 Jun 2018 05:56:12 -0700
Subject: genirq: Use rcu in kstat_irqs_usr()

Jeremy Dorfman identified mutex contention when multiple threads
parse /proc/stat concurrently.

Since commit 425a5072dcd1 ("genirq: Free irq_desc with rcu"),
kstat_irqs_usr() can be switched to rcu locking, which removes this mutex
contention.

show_interrupts() case will be handled in a separate patch.

Reported-by: Jeremy Dorfman <jdorfman@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Willem de Bruijn <willemb@google.com>
Link: https://lkml.kernel.org/r/20180618125612.155057-1-edumazet@google.com
---
 kernel/irq/irqdesc.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index afc7f902d74a..578d0e5f1b5b 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -443,6 +443,7 @@ static void free_desc(unsigned int irq)
 	 * We free the descriptor, masks and stat fields via RCU. That
 	 * allows demultiplex interrupts to do rcu based management of
 	 * the child interrupts.
+	 * This also allows us to use rcu in kstat_irqs_usr().
 	 */
 	call_rcu(&desc->rcu, delayed_free_desc);
 }
@@ -928,17 +929,17 @@ unsigned int kstat_irqs(unsigned int irq)
  * kstat_irqs_usr - Get the statistics for an interrupt
  * @irq:	The interrupt number
  *
- * Returns the sum of interrupt counts on all cpus since boot for
- * @irq. Contrary to kstat_irqs() this can be called from any
- * preemptible context. It's protected against concurrent removal of
- * an interrupt descriptor when sparse irqs are enabled.
+ * Returns the sum of interrupt counts on all cpus since boot for @irq.
+ * Contrary to kstat_irqs() this can be called from any context.
+ * It uses rcu since a concurrent removal of an interrupt descriptor is
+ * observing an rcu grace period before delayed_free_desc()/irq_kobj_release().
  */
 unsigned int kstat_irqs_usr(unsigned int irq)
 {
 	unsigned int sum;
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	sum = kstat_irqs(irq);
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return sum;
 }
-- 
cgit v1.2.3


From 0a13ec0bbc42bddf90ab6a444df8aaa67c148b16 Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Sun, 17 Jun 2018 14:40:18 +0200
Subject: genirq: Fix editing error in a comment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the comment was reflowed to a wider format, the "*" snuck in.

Fixes: ae88a23b32fa ("irq: refactor and clean up the free_irq() code flow")
Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180617124018.25539-1-j.neuschaefer@gmx.net
---
 kernel/irq/manage.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index daeabd791d58..591cfe901162 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1638,7 +1638,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	 * is so by doing an extra call to the handler ....
 	 *
 	 * ( We do this after actually deregistering it, to make sure that a
-	 *   'real' IRQ doesn't run in * parallel with our fake. )
+	 *   'real' IRQ doesn't run in parallel with our fake. )
 	 */
 	if (action->flags & IRQF_SHARED) {
 		local_irq_save(flags);
-- 
cgit v1.2.3


From f5a89295e2f566d8e9f1d4f3d524d8d3c966958c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 16:08:00 +0200
Subject: time: Use ktime_get_real_seconds() in time syscall

Both get_seconds() and do_gettimeofday() are deprecated. Change the time()
implementation to use the replacement function instead.

Obviously the system call will still overflow in 2038, but this gets us
closer to removing the old helper functions.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Cc: y2038@lists.linaro.org
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Deepa Dinamani <deepa.kernel@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lkml.kernel.org/r/20180618140811.2998503-2-arnd@arndb.de
---
 kernel/time/time.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/time/time.c b/kernel/time/time.c
index 6fa99213fc72..b1225db61eb2 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -63,7 +63,7 @@ EXPORT_SYMBOL(sys_tz);
  */
 SYSCALL_DEFINE1(time, time_t __user *, tloc)
 {
-	time_t i = get_seconds();
+	time_t i = (time_t)ktime_get_real_seconds();
 
 	if (tloc) {
 		if (put_user(i,tloc))
@@ -106,11 +106,9 @@ SYSCALL_DEFINE1(stime, time_t __user *, tptr)
 /* compat_time_t is a 32 bit "long" and needs to get converted. */
 COMPAT_SYSCALL_DEFINE1(time, compat_time_t __user *, tloc)
 {
-	struct timeval tv;
 	compat_time_t i;
 
-	do_gettimeofday(&tv);
-	i = tv.tv_sec;
+	i = (compat_time_t)ktime_get_real_seconds();
 
 	if (tloc) {
 		if (put_user(i,tloc))
-- 
cgit v1.2.3


From d30faff900e666f9a6395a159fdd353c02f5bed0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 16:08:01 +0200
Subject: timekeeping: Use ktime_get_real_ts64() instead of getnstimeofday64()

The two do the same, this moves all users to the newer name for consistency.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Cc: y2038@lists.linaro.org
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Link: https://lkml.kernel.org/r/20180618140811.2998503-3-arnd@arndb.de
---
 kernel/time/ntp.c         | 6 +++---
 kernel/time/timekeeping.c | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index a09ded765f6c..10a79053e82f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -502,7 +502,7 @@ static void sched_sync_hw_clock(struct timespec64 now,
 {
 	struct timespec64 next;
 
-	getnstimeofday64(&next);
+	ktime_get_real_ts64(&next);
 	if (!fail)
 		next.tv_sec = 659;
 	else {
@@ -537,7 +537,7 @@ static void sync_rtc_clock(void)
 	if (!IS_ENABLED(CONFIG_RTC_SYSTOHC))
 		return;
 
-	getnstimeofday64(&now);
+	ktime_get_real_ts64(&now);
 
 	adjust = now;
 	if (persistent_clock_is_local)
@@ -591,7 +591,7 @@ static bool sync_cmos_clock(void)
 	 * Architectures are strongly encouraged to use rtclib and not
 	 * implement this legacy API.
 	 */
-	getnstimeofday64(&now);
+	ktime_get_real_ts64(&now);
 	if (rtc_tv_nsec_ok(-1 * target_nsec, &adjust, &now)) {
 		if (persistent_clock_is_local)
 			adjust.tv_sec -= (sys_tz.tz_minuteswest * 60);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..77c436a0070b 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2310,7 +2310,7 @@ int do_adjtimex(struct timex *txc)
 			return ret;
 	}
 
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
-- 
cgit v1.2.3


From 58a10456d7175fa674b951f1fd7ead3d9a550db4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 16:32:24 +0200
Subject: posix-timers: Use new ktime_get_*_ts64() helpers

Some of the oddly named time accessor functions now have a more consistent
naming, which should be used from now on so the aliases can be removed.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: y2038@lists.linaro.org
Cc: Deepa Dinamani <deepa.kernel@gmail.com>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Link: https://lkml.kernel.org/r/20180618143246.3865099-1-arnd@arndb.de
---
 kernel/time/posix-stubs.c  |  2 +-
 kernel/time/posix-timers.c | 10 +++++-----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/time/posix-stubs.c b/kernel/time/posix-stubs.c
index 26aa9569e24a..2c6847d5d69b 100644
--- a/kernel/time/posix-stubs.c
+++ b/kernel/time/posix-stubs.c
@@ -81,7 +81,7 @@ int do_clock_gettime(clockid_t which_clock, struct timespec64 *tp)
 		ktime_get_ts64(tp);
 		break;
 	case CLOCK_BOOTTIME:
-		get_monotonic_boottime64(tp);
+		ktime_get_boottime_ts64(tp);
 		break;
 	default:
 		return -EINVAL;
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index e08ce3f27447..fcf90a10c43a 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -228,21 +228,21 @@ static int posix_ktime_get_ts(clockid_t which_clock, struct timespec64 *tp)
  */
 static int posix_get_monotonic_raw(clockid_t which_clock, struct timespec64 *tp)
 {
-	getrawmonotonic64(tp);
+	ktime_get_raw_ts64(tp);
 	return 0;
 }
 
 
 static int posix_get_realtime_coarse(clockid_t which_clock, struct timespec64 *tp)
 {
-	*tp = current_kernel_time64();
+	ktime_get_coarse_real_ts64(tp);
 	return 0;
 }
 
 static int posix_get_monotonic_coarse(clockid_t which_clock,
 						struct timespec64 *tp)
 {
-	*tp = get_monotonic_coarse64();
+	ktime_get_coarse_ts64(tp);
 	return 0;
 }
 
@@ -254,13 +254,13 @@ static int posix_get_coarse_res(const clockid_t which_clock, struct timespec64 *
 
 static int posix_get_boottime(const clockid_t which_clock, struct timespec64 *tp)
 {
-	get_monotonic_boottime64(tp);
+	ktime_get_boottime_ts64(tp);
 	return 0;
 }
 
 static int posix_get_tai(clockid_t which_clock, struct timespec64 *tp)
 {
-	timekeeping_clocktai64(tp);
+	ktime_get_clocktai_ts64(tp);
 	return 0;
 }
 
-- 
cgit v1.2.3


From dc1b7b6ca9d5fa905c164a667086d8a3d8605875 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:00:38 +0200
Subject: sysinfo: Remove get_monotonic_boottime()

get_monotonic_boottime() is deprecated because it uses the old 'timespec'
structure. This replaces one of the last callers with a call to
ktime_get_boottime.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: y2038@lists.linaro.org
Cc: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
Link: https://lkml.kernel.org/r/20180618150114.849216-1-arnd@arndb.de
---
 kernel/sys.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sys.c b/kernel/sys.c
index 38509dc1f77b..e27b51d3facd 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2512,11 +2512,11 @@ static int do_sysinfo(struct sysinfo *info)
 {
 	unsigned long mem_total, sav_total;
 	unsigned int mem_unit, bitcount;
-	struct timespec tp;
+	struct timespec64 tp;
 
 	memset(info, 0, sizeof(struct sysinfo));
 
-	get_monotonic_boottime(&tp);
+	ktime_get_boottime_ts64(&tp);
 	info->uptime = tp.tv_sec + (tp.tv_nsec ? 1 : 0);
 
 	get_avenrun(info->loads, 0, SI_LOAD_SHIFT - FSHIFT);
-- 
cgit v1.2.3


From 3d5155eaadaf512808cb57ec0c7db7bd4cc1ef67 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 17 May 2018 11:04:15 +0200
Subject: clk: renesas: r8a7795: Add CR clock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the CR core clock, which is used by the Secure Engine (SCEG).

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Tested-by: Gilad Ben-Yossef <gilad@benyossef.com>
---
 drivers/clk/renesas/r8a7795-cpg-mssr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/renesas/r8a7795-cpg-mssr.c b/drivers/clk/renesas/r8a7795-cpg-mssr.c
index 775b0ceaa337..e5b186566c09 100644
--- a/drivers/clk/renesas/r8a7795-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a7795-cpg-mssr.c
@@ -103,6 +103,7 @@ static struct cpg_core_clk r8a7795_core_clks[] __initdata = {
 	DEF_GEN3_SD("sd3",      R8A7795_CLK_SD3,   CLK_SDSRC,     0x26c),
 
 	DEF_FIXED("cl",         R8A7795_CLK_CL,    CLK_PLL1_DIV2, 48, 1),
+	DEF_FIXED("cr",         R8A7795_CLK_CR,    CLK_PLL1_DIV4,  2, 1),
 	DEF_FIXED("cp",         R8A7795_CLK_CP,    CLK_EXTAL,      2, 1),
 
 	DEF_DIV6P1("canfd",     R8A7795_CLK_CANFD, CLK_PLL1_DIV4, 0x244),
-- 
cgit v1.2.3


From 46f3bb5fb944089aaa8130a80f5b7df877c58554 Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Thu, 24 May 2018 15:19:09 +0100
Subject: clk: renesas: r8a7795: Add CCREE clock

This patch adds the clock used by the CryptoCell 630p instance in the
SoC.

Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/clk/renesas/r8a7795-cpg-mssr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/renesas/r8a7795-cpg-mssr.c b/drivers/clk/renesas/r8a7795-cpg-mssr.c
index e5b186566c09..a85dd50e8911 100644
--- a/drivers/clk/renesas/r8a7795-cpg-mssr.c
+++ b/drivers/clk/renesas/r8a7795-cpg-mssr.c
@@ -133,6 +133,7 @@ static struct mssr_mod_clk r8a7795_mod_clks[] __initdata = {
 	DEF_MOD("sys-dmac2",		 217,	R8A7795_CLK_S0D3),
 	DEF_MOD("sys-dmac1",		 218,	R8A7795_CLK_S0D3),
 	DEF_MOD("sys-dmac0",		 219,	R8A7795_CLK_S0D3),
+	DEF_MOD("sceg-pub",		 229,	R8A7795_CLK_CR),
 	DEF_MOD("cmt3",			 300,	R8A7795_CLK_R),
 	DEF_MOD("cmt2",			 301,	R8A7795_CLK_R),
 	DEF_MOD("cmt1",			 302,	R8A7795_CLK_R),
-- 
cgit v1.2.3


From 0fdb3f75a358256188b88391d698349af8cb7340 Mon Sep 17 00:00:00 2001
From: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Date: Mon, 18 Jun 2018 11:42:06 +0530
Subject: drm/i915/psr: Adds psrwake options for all platforms

Adds new psrwake options defined in the below table.
Platform	PSR wake options vbt version
KBL/CFL/WHL	All(205+)
BXT		Uses old interpretation.
CNL/ICL+	All(205+)
GLK		All(205+)
SKL		All PV releases (Check for 205+ might help but cannot be foolproof)

We will continue with newer interpretation for SKL from 205.

v2: Jani
    Keep the bdb version check.
v3:
    Apply newer version for skl from 205+(DK).
    Add (version check && platform list) (Jani).
    Add bdb version for each platform in commit message(DK).

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Puthikorn Voravootivat <puthik@chromium.org>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Ashutosh D Shukla <ashutosh.d.shukla@intel.com>
Cc: Maulik V Vaghela <maulik.v.vaghela@intel.com>
Signed-off-by: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1529302326-3567-1-git-send-email-vathsala.nagaraju@intel.com
---
 drivers/gpu/drm/i915/intel_bios.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 62a53eb89b6b..03f04b472394 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -710,7 +710,9 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 	 * New psr options 0=500us, 1=100us, 2=2500us, 3=0us
 	 * Old decimal value is wake up time in multiples of 100 us.
 	 */
-	if (bdb->version >= 209 && IS_GEN9_BC(dev_priv)) {
+	if (bdb->version >= 205 &&
+	    (IS_GEN9_BC(dev_priv) || IS_GEMINILAKE(dev_priv) ||
+	     INTEL_GEN(dev_priv) >= 10)) {
 		switch (psr_table->tp1_wakeup_time) {
 		case 0:
 			dev_priv->vbt.psr.tp1_wakeup_time_us = 500;
-- 
cgit v1.2.3


From fb9acf5f1f21f1de193523ff780bda375b4c2e21 Mon Sep 17 00:00:00 2001
From: Jan Kundrát <jan.kundrat@cesnet.cz>
Date: Mon, 4 Jun 2018 16:34:25 +0200
Subject: spi: orion: fix CS GPIO handling again
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The code did not de-assert any CS GPIOs before probing slaves. This
means that several CS signals could be active at once, garbling the
communication. Whether this was actually a problem depended on the type
of the SPI device attached (so my "spidev" for userspace access worked
correctly because its probe was effectively a no-op), and on the state
of the GPIO pins at SoC's boot.

The code was already iterating through all DT children of the SPI
controller, so this change re-uses that loop for CS GPIO setup as well.
This means that this might change the number of the HW CS signal which
is picked for all GPIO CS devices. Previously, the lowest one was used,
but we now use the first one from the DT.

With this move of the code, we can also finally initialize each GPIO CS
lane before registering the SPI controller (which in turn probes for
slaves).

I tried to fix this in 544248623b95 already, but that only did it half
way by registering the GPIOs properly. That patch failed to set their
logic signals early enough, though.

Signed-off-by: Jan Kundrát <jan.kundrat@cesnet.cz>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-orion.c | 77 +++++++++++++++++++++++++------------------------
 1 file changed, 40 insertions(+), 37 deletions(-)

diff --git a/drivers/spi/spi-orion.c b/drivers/spi/spi-orion.c
index d01a6adc726e..47ef6b1a2e76 100644
--- a/drivers/spi/spi-orion.c
+++ b/drivers/spi/spi-orion.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
+#include <linux/of_gpio.h>
 #include <linux/clk.h>
 #include <linux/sizes.h>
 #include <linux/gpio.h>
@@ -681,9 +682,9 @@ static int orion_spi_probe(struct platform_device *pdev)
 		goto out_rel_axi_clk;
 	}
 
-	/* Scan all SPI devices of this controller for direct mapped devices */
 	for_each_available_child_of_node(pdev->dev.of_node, np) {
 		u32 cs;
+		int cs_gpio;
 
 		/* Get chip-select number from the "reg" property */
 		status = of_property_read_u32(np, "reg", &cs);
@@ -694,6 +695,44 @@ static int orion_spi_probe(struct platform_device *pdev)
 			continue;
 		}
 
+		/*
+		 * Initialize the CS GPIO:
+		 * - properly request the actual GPIO signal
+		 * - de-assert the logical signal so that all GPIO CS lines
+		 *   are inactive when probing for slaves
+		 * - find an unused physical CS which will be driven for any
+		 *   slave which uses a CS GPIO
+		 */
+		cs_gpio = of_get_named_gpio(pdev->dev.of_node, "cs-gpios", cs);
+		if (cs_gpio > 0) {
+			char *gpio_name;
+			int cs_flags;
+
+			if (spi->unused_hw_gpio == -1) {
+				dev_info(&pdev->dev,
+					"Selected unused HW CS#%d for any GPIO CSes\n",
+					cs);
+				spi->unused_hw_gpio = cs;
+			}
+
+			gpio_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					"%s-CS%d", dev_name(&pdev->dev), cs);
+			if (!gpio_name) {
+				status = -ENOMEM;
+				goto out_rel_axi_clk;
+			}
+
+			cs_flags = of_property_read_bool(np, "spi-cs-high") ?
+				GPIOF_OUT_INIT_LOW : GPIOF_OUT_INIT_HIGH;
+			status = devm_gpio_request_one(&pdev->dev, cs_gpio,
+					cs_flags, gpio_name);
+			if (status) {
+				dev_err(&pdev->dev,
+					"Can't request GPIO for CS %d\n", cs);
+				goto out_rel_axi_clk;
+			}
+		}
+
 		/*
 		 * Check if an address is configured for this SPI device. If
 		 * not, the MBus mapping via the 'ranges' property in the 'soc'
@@ -740,44 +779,8 @@ static int orion_spi_probe(struct platform_device *pdev)
 	if (status < 0)
 		goto out_rel_pm;
 
-	if (master->cs_gpios) {
-		int i;
-		for (i = 0; i < master->num_chipselect; ++i) {
-			char *gpio_name;
-
-			if (!gpio_is_valid(master->cs_gpios[i])) {
-				continue;
-			}
-
-			gpio_name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					"%s-CS%d", dev_name(&pdev->dev), i);
-			if (!gpio_name) {
-				status = -ENOMEM;
-				goto out_rel_master;
-			}
-
-			status = devm_gpio_request(&pdev->dev,
-					master->cs_gpios[i], gpio_name);
-			if (status) {
-				dev_err(&pdev->dev,
-					"Can't request GPIO for CS %d\n",
-					master->cs_gpios[i]);
-				goto out_rel_master;
-			}
-			if (spi->unused_hw_gpio == -1) {
-				dev_info(&pdev->dev,
-					"Selected unused HW CS#%d for any GPIO CSes\n",
-					i);
-				spi->unused_hw_gpio = i;
-			}
-		}
-	}
-
-
 	return status;
 
-out_rel_master:
-	spi_unregister_master(master);
 out_rel_pm:
 	pm_runtime_disable(&pdev->dev);
 out_rel_axi_clk:
-- 
cgit v1.2.3


From 29c1372d6a9b872acf479ba2744e4e7f043981c0 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnáček <omosnace@redhat.com>
Date: Wed, 30 May 2018 10:45:24 +0200
Subject: audit: allow other filter list types for AUDIT_EXE

This patch removes the restriction of the AUDIT_EXE field to only
SYSCALL filter and teaches audit_filter to recognize this field.

This makes it possible to write rule lists such as:

    auditctl -a exit,always [some general rule]
    # Filter out events with executable name /bin/exe1 or /bin/exe2:
    auditctl -a exclude,always -F exe=/bin/exe1
    auditctl -a exclude,always -F exe=/bin/exe2

See: https://github.com/linux-audit/audit-kernel/issues/54

Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Reviewed-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/auditfilter.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index eaa320148d97..6db9847ca031 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -428,8 +428,6 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
 	case AUDIT_EXE:
 		if (f->op != Audit_not_equal && f->op != Audit_equal)
 			return -EINVAL;
-		if (entry->rule.listnr != AUDIT_FILTER_EXIT)
-			return -EINVAL;
 		break;
 	}
 	return 0;
@@ -1360,6 +1358,11 @@ int audit_filter(int msgtype, unsigned int listtype)
 							f->type, f->op, f->lsm_rule, NULL);
 				}
 				break;
+			case AUDIT_EXE:
+				result = audit_exe_compare(current, e->rule.exe);
+				if (f->op == Audit_not_equal)
+					result = !result;
+				break;
 			default:
 				goto unlock_and_return;
 			}
-- 
cgit v1.2.3


From 1a4b8901c5ecd321904f7eb5bd73be59c1ca062c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 11 Jun 2018 22:34:03 +0300
Subject: drm/i915: Print prop name/id when rejecting it
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the '[PROP:id:name]' format I introduced for the core in the driver
debug messages as well.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611193403.16118-3-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_atomic.c       | 6 ++++--
 drivers/gpu/drm/i915/intel_atomic_plane.c | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_atomic.c b/drivers/gpu/drm/i915/intel_atomic.c
index 40285d1b91b7..fee026ca449b 100644
--- a/drivers/gpu/drm/i915/intel_atomic.c
+++ b/drivers/gpu/drm/i915/intel_atomic.c
@@ -59,7 +59,8 @@ int intel_digital_connector_atomic_get_property(struct drm_connector *connector,
 	else if (property == dev_priv->broadcast_rgb_property)
 		*val = intel_conn_state->broadcast_rgb;
 	else {
-		DRM_DEBUG_ATOMIC("Unknown property %s\n", property->name);
+		DRM_DEBUG_ATOMIC("Unknown property [PROP:%d:%s]\n",
+				 property->base.id, property->name);
 		return -EINVAL;
 	}
 
@@ -95,7 +96,8 @@ int intel_digital_connector_atomic_set_property(struct drm_connector *connector,
 		return 0;
 	}
 
-	DRM_DEBUG_ATOMIC("Unknown property %s\n", property->name);
+	DRM_DEBUG_ATOMIC("Unknown property [PROP:%d:%s]\n",
+			 property->base.id, property->name);
 	return -EINVAL;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_atomic_plane.c b/drivers/gpu/drm/i915/intel_atomic_plane.c
index 6d068786eb41..69a18d4ff59d 100644
--- a/drivers/gpu/drm/i915/intel_atomic_plane.c
+++ b/drivers/gpu/drm/i915/intel_atomic_plane.c
@@ -277,7 +277,8 @@ intel_plane_atomic_get_property(struct drm_plane *plane,
 				struct drm_property *property,
 				uint64_t *val)
 {
-	DRM_DEBUG_KMS("Unknown plane property '%s'\n", property->name);
+	DRM_DEBUG_KMS("Unknown property [PROP:%d:%s]\n",
+		      property->base.id, property->name);
 	return -EINVAL;
 }
 
@@ -299,6 +300,7 @@ intel_plane_atomic_set_property(struct drm_plane *plane,
 				struct drm_property *property,
 				uint64_t val)
 {
-	DRM_DEBUG_KMS("Unknown plane property '%s'\n", property->name);
+	DRM_DEBUG_KMS("Unknown property [PROP:%d:%s]\n",
+		      property->base.id, property->name);
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From 98fac1d5c5825e61721c7b73875f8b46159e6dcb Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 15 Jun 2018 20:44:04 +0300
Subject: drm/i915: Nuke the cursor size defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

No point in having this extra indireciton for the cursor max size.
So drop the defines and just write out the raw numbers. Makes it
easier to see what's going on.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615174406.12258-1-ville.syrjala@linux.intel.com
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 8 ++++----
 drivers/gpu/drm/i915/intel_drv.h     | 6 ------
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 9939e092d9aa..aa7fed31ccda 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15052,11 +15052,11 @@ int intel_modeset_init(struct drm_device *dev)
 		dev->mode_config.cursor_width = IS_I845G(dev_priv) ? 64 : 512;
 		dev->mode_config.cursor_height = 1023;
 	} else if (IS_GEN2(dev_priv)) {
-		dev->mode_config.cursor_width = GEN2_CURSOR_WIDTH;
-		dev->mode_config.cursor_height = GEN2_CURSOR_HEIGHT;
+		dev->mode_config.cursor_width = 64;
+		dev->mode_config.cursor_height = 64;
 	} else {
-		dev->mode_config.cursor_width = MAX_CURSOR_WIDTH;
-		dev->mode_config.cursor_height = MAX_CURSOR_HEIGHT;
+		dev->mode_config.cursor_width = 256;
+		dev->mode_config.cursor_height = 256;
 	}
 
 	dev->mode_config.fb_base = ggtt->gmadr.start;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index fd2e4de77697..22831acc7c30 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -158,12 +158,6 @@
 #define MAX_OUTPUTS 6
 /* maximum connectors per crtcs in the mode set */
 
-/* Maximum cursor sizes */
-#define GEN2_CURSOR_WIDTH 64
-#define GEN2_CURSOR_HEIGHT 64
-#define MAX_CURSOR_WIDTH 256
-#define MAX_CURSOR_HEIGHT 256
-
 #define INTEL_I2C_BUS_DVO 1
 #define INTEL_I2C_BUS_SDVO 2
 
-- 
cgit v1.2.3


From ad77c537eab1c28732e02c03f3da82917722bef6 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 15 Jun 2018 20:44:05 +0300
Subject: drm/i915: Check timings against hardware maximums
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Validate that all display timings fit within the number of bits
we have in the transcoder timing registers.

The limits are:
hsw+:
 4k: vdisplay, vblank_start
 8k: everything else
gen3+:
 4k: h/vdisplay, h/vblank_start
 8k: everything else
gen2:
 2k: h/vdisplay, h/vblank_start
 4k: everything else

Also document the fact that the mode_config.max_width/height limits
refer to just the max framebuffer dimensions we support. Which may
be larger than the max hdisplay/vdisplay.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615174406.12258-2-ville.syrjala@linux.intel.com
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c | 35 +++++++++++++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index aa7fed31ccda..b2a5a9ed9404 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -14570,6 +14570,10 @@ static enum drm_mode_status
 intel_mode_valid(struct drm_device *dev,
 		 const struct drm_display_mode *mode)
 {
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	int hdisplay_max, htotal_max;
+	int vdisplay_max, vtotal_max;
+
 	/*
 	 * Can't reject DBLSCAN here because Xorg ddxen can add piles
 	 * of DBLSCAN modes to the output's mode list when they detect
@@ -14599,6 +14603,36 @@ intel_mode_valid(struct drm_device *dev,
 			   DRM_MODE_FLAG_CLKDIV2))
 		return MODE_BAD;
 
+	if (INTEL_GEN(dev_priv) >= 9 ||
+	    IS_BROADWELL(dev_priv) || IS_HASWELL(dev_priv)) {
+		hdisplay_max = 8192; /* FDI max 4096 handled elsewhere */
+		vdisplay_max = 4096;
+		htotal_max = 8192;
+		vtotal_max = 8192;
+	} else if (INTEL_GEN(dev_priv) >= 3) {
+		hdisplay_max = 4096;
+		vdisplay_max = 4096;
+		htotal_max = 8192;
+		vtotal_max = 8192;
+	} else {
+		hdisplay_max = 2048;
+		vdisplay_max = 2048;
+		htotal_max = 4096;
+		vtotal_max = 4096;
+	}
+
+	if (mode->hdisplay > hdisplay_max ||
+	    mode->hsync_start > htotal_max ||
+	    mode->hsync_end > htotal_max ||
+	    mode->htotal > htotal_max)
+		return MODE_H_ILLEGAL;
+
+	if (mode->vdisplay > vdisplay_max ||
+	    mode->vsync_start > vtotal_max ||
+	    mode->vsync_end > vtotal_max ||
+	    mode->vtotal > vtotal_max)
+		return MODE_V_ILLEGAL;
+
 	return MODE_OK;
 }
 
@@ -15037,6 +15071,7 @@ int intel_modeset_init(struct drm_device *dev)
 		}
 	}
 
+	/* maximum framebuffer dimensions */
 	if (IS_GEN2(dev_priv)) {
 		dev->mode_config.max_width = 2048;
 		dev->mode_config.max_height = 2048;
-- 
cgit v1.2.3


From ad193bc6206d3ee2fc39fe29a2525333faf1afd9 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 15 Jun 2018 20:44:06 +0300
Subject: drm/i915: Enforce max hdisplay/hblank_start limits on HSW/BDW FDI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PCH transcoder registers are only 12 bits wide for the hdisplay
and hblank_start values. On HSW/BDW the CPU side registers are 13
bits wide. intel_mode_valid() only checks against the higher limit
(since we don't know where the mode is to be used), so an extra
check is required against the FDI limits.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615174406.12258-3-ville.syrjala@linux.intel.com
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
---
 drivers/gpu/drm/i915/intel_crt.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index a1ddd9f62bb8..0c6bf82bb059 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -337,6 +337,10 @@ intel_crt_mode_valid(struct drm_connector *connector,
 	    (ironlake_get_lanes_required(mode->clock, 270000, 24) > 2))
 		return MODE_CLOCK_HIGH;
 
+	/* HSW/BDW FDI limited to 4k */
+	if (mode->hdisplay > 4096)
+		return MODE_H_ILLEGAL;
+
 	return MODE_OK;
 }
 
@@ -379,6 +383,11 @@ static bool hsw_crt_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return false;
 
+	/* HSW/BDW FDI limited to 4k */
+	if (adjusted_mode->crtc_hdisplay > 4096 ||
+	    adjusted_mode->crtc_hblank_start > 4096)
+		return false;
+
 	pipe_config->has_pch_encoder = true;
 
 	/* LPT FDI RX only supports 8bpc. */
-- 
cgit v1.2.3


From 9b8753fffe7b3642688135f28aa8a0a0f45fd9ab Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Thu, 31 May 2018 16:27:24 -0400
Subject: audit: tie SECCOMP records to syscall

Since seccomp events are triggered by user activity, tie the SECCOMP
record to the syscall record to collect all records from the same event.

See: https://github.com/linux-audit/audit-kernel/issues/87

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/auditsc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ceb1c4596c51..fefb9e215cd0 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2485,7 +2485,7 @@ void audit_seccomp(unsigned long syscall, long signr, int code)
 {
 	struct audit_buffer *ab;
 
-	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_SECCOMP);
+	ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_SECCOMP);
 	if (unlikely(!ab))
 		return;
 	audit_log_task(ab);
-- 
cgit v1.2.3


From d87de4a878e110d0061fb22726d37a54a281285d Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Thu, 31 May 2018 16:28:12 -0400
Subject: audit: tie ANOM_ABEND records to syscall

Since core dump events are triggered by user activity, tie the
ANOM_ABEND record to the syscall record to collect all records from the
same event.

See: https://github.com/linux-audit/audit-kernel/issues/88

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/auditsc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index fefb9e215cd0..5f0bd5ece578 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2461,7 +2461,7 @@ void audit_core_dumps(long signr)
 	if (signr == SIGQUIT)	/* don't care for those */
 		return;
 
-	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND);
+	ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_ANOM_ABEND);
 	if (unlikely(!ab))
 		return;
 	audit_log_task(ab);
-- 
cgit v1.2.3


From af85d1772e31fed34165a1b3decef340cf4080c0 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnáček <omosnace@redhat.com>
Date: Tue, 5 Jun 2018 11:00:10 +0200
Subject: audit: Fix extended comparison of GID/EGID

The audit_filter_rules() function in auditsc.c used the in_[e]group_p()
functions to check GID/EGID match, but these functions use the current
task's credentials, while the comparison should use the credentials of
the task given to audit_filter_rules() as a parameter (tsk).

Note that we can use group_search(cred->group_info, ...) as a
replacement for both in_group_p and in_egroup_p as these functions only
compare the parameter to cred->fsgid/egid and then call group_search.

In fact, the usage of in_group_p was even more incorrect: it compares to
cred->fsgid (which is usually equal to cred->egid) and not cred->gid.

GitHub issue:
https://github.com/linux-audit/audit-kernel/issues/82

Fixes: 37eebe39c973 ("audit: improve GID/EGID comparation logic")
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/auditsc.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 5f0bd5ece578..d762e0b8160e 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -494,20 +494,20 @@ static int audit_filter_rules(struct task_struct *tsk,
 			result = audit_gid_comparator(cred->gid, f->op, f->gid);
 			if (f->op == Audit_equal) {
 				if (!result)
-					result = in_group_p(f->gid);
+					result = groups_search(cred->group_info, f->gid);
 			} else if (f->op == Audit_not_equal) {
 				if (result)
-					result = !in_group_p(f->gid);
+					result = !groups_search(cred->group_info, f->gid);
 			}
 			break;
 		case AUDIT_EGID:
 			result = audit_gid_comparator(cred->egid, f->op, f->gid);
 			if (f->op == Audit_equal) {
 				if (!result)
-					result = in_egroup_p(f->gid);
+					result = groups_search(cred->group_info, f->gid);
 			} else if (f->op == Audit_not_equal) {
 				if (result)
-					result = !in_egroup_p(f->gid);
+					result = !groups_search(cred->group_info, f->gid);
 			}
 			break;
 		case AUDIT_SGID:
-- 
cgit v1.2.3


From d904ac0320d3c4ff4e9d80e4294ca5dde803696f Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 5 Jun 2018 11:45:07 -0400
Subject: audit: rename FILTER_TYPE to FILTER_EXCLUDE

The AUDIT_FILTER_TYPE name is vague and misleading due to not describing
where or when the filter is applied and obsolete due to its available
filter fields having been expanded.

Userspace has already renamed it from AUDIT_FILTER_TYPE to
AUDIT_FILTER_EXCLUDE without checking if it already exists.  The
userspace maintainer assures that as long as it is set to the same value
it will not be a problem since the userspace code does not treat
compiler warnings as errors.  If this policy changes then checks if it
already exists can be added at the same time.

See: https://github.com/linux-audit/audit-kernel/issues/89

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/uapi/linux/audit.h |  3 ++-
 kernel/audit.c             |  2 +-
 kernel/auditfilter.c       | 10 +++++-----
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index c35aee9ad4a6..4e3eaba84175 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -157,7 +157,8 @@
 #define AUDIT_FILTER_ENTRY	0x02	/* Apply rule at syscall entry */
 #define AUDIT_FILTER_WATCH	0x03	/* Apply rule to file system watches */
 #define AUDIT_FILTER_EXIT	0x04	/* Apply rule at syscall exit */
-#define AUDIT_FILTER_TYPE	0x05	/* Apply rule at audit_log_start */
+#define AUDIT_FILTER_EXCLUDE	0x05	/* Apply rule before record creation */
+#define AUDIT_FILTER_TYPE	AUDIT_FILTER_EXCLUDE /* obsolete misleading naming */
 #define AUDIT_FILTER_FS		0x06	/* Apply rule at __audit_inode_child */
 
 #define AUDIT_NR_FILTERS	7
diff --git a/kernel/audit.c b/kernel/audit.c
index e7478cb58079..5c0a1d7b0c7b 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1754,7 +1754,7 @@ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask,
 	if (audit_initialized != AUDIT_INITIALIZED)
 		return NULL;
 
-	if (unlikely(!audit_filter(type, AUDIT_FILTER_TYPE)))
+	if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE)))
 		return NULL;
 
 	/* NOTE: don't ever fail/sleep on these two conditions:
diff --git a/kernel/auditfilter.c b/kernel/auditfilter.c
index 6db9847ca031..bf309f2592c4 100644
--- a/kernel/auditfilter.c
+++ b/kernel/auditfilter.c
@@ -264,7 +264,7 @@ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *
 	case AUDIT_FILTER_TASK:
 #endif
 	case AUDIT_FILTER_USER:
-	case AUDIT_FILTER_TYPE:
+	case AUDIT_FILTER_EXCLUDE:
 	case AUDIT_FILTER_FS:
 		;
 	}
@@ -337,7 +337,7 @@ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f)
 {
 	switch(f->type) {
 	case AUDIT_MSGTYPE:
-		if (entry->rule.listnr != AUDIT_FILTER_TYPE &&
+		if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE &&
 		    entry->rule.listnr != AUDIT_FILTER_USER)
 			return -EINVAL;
 		break;
@@ -929,7 +929,7 @@ static inline int audit_add_rule(struct audit_entry *entry)
 	/* If any of these, don't count towards total */
 	switch(entry->rule.listnr) {
 	case AUDIT_FILTER_USER:
-	case AUDIT_FILTER_TYPE:
+	case AUDIT_FILTER_EXCLUDE:
 	case AUDIT_FILTER_FS:
 		dont_count = 1;
 	}
@@ -1011,7 +1011,7 @@ int audit_del_rule(struct audit_entry *entry)
 	/* If any of these, don't count towards total */
 	switch(entry->rule.listnr) {
 	case AUDIT_FILTER_USER:
-	case AUDIT_FILTER_TYPE:
+	case AUDIT_FILTER_EXCLUDE:
 	case AUDIT_FILTER_FS:
 		dont_count = 1;
 	}
@@ -1372,7 +1372,7 @@ int audit_filter(int msgtype, unsigned int listtype)
 				break;
 		}
 		if (result > 0) {
-			if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_TYPE)
+			if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE)
 				ret = 0;
 			break;
 		}
-- 
cgit v1.2.3


From 1c3eced3d4ad7fd0a62c782205c36b96c0091813 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Tue, 19 Jun 2018 15:44:37 +0300
Subject: drm/i915/audio: constify ELD pointers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The hooks aren't supposed to modify the ELD, so use const pointer. As a
drive-by fix, use drm_eld_size() to log ELD size.

Suggested-by: Ville Syrjala <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180619124437.10982-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_audio.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index a34aa66f28f8..bb94172ffc07 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -213,7 +213,7 @@ static bool intel_eld_uptodate(struct drm_connector *connector,
 			       i915_reg_t reg_edid)
 {
 	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	u8 *eld = connector->eld;
+	const u8 *eld = connector->eld;
 	u32 tmp;
 	int i;
 
@@ -228,7 +228,7 @@ static bool intel_eld_uptodate(struct drm_connector *connector,
 	I915_WRITE(reg_elda, tmp);
 
 	for (i = 0; i < drm_eld_size(eld) / 4; i++)
-		if (I915_READ(reg_edid) != *((u32 *)eld + i))
+		if (I915_READ(reg_edid) != *((const u32 *)eld + i))
 			return false;
 
 	return true;
@@ -261,12 +261,12 @@ static void g4x_audio_codec_enable(struct intel_encoder *encoder,
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct drm_connector *connector = conn_state->connector;
-	u8 *eld = connector->eld;
+	const u8 *eld = connector->eld;
 	u32 eldv;
 	u32 tmp;
 	int len, i;
 
-	DRM_DEBUG_KMS("Enable audio codec, %u bytes ELD\n", eld[2]);
+	DRM_DEBUG_KMS("Enable audio codec, %u bytes ELD\n", drm_eld_size(eld));
 
 	tmp = I915_READ(G4X_AUD_VID_DID);
 	if (tmp == INTEL_AUDIO_DEVBLC || tmp == INTEL_AUDIO_DEVCL)
@@ -288,7 +288,7 @@ static void g4x_audio_codec_enable(struct intel_encoder *encoder,
 	len = min(drm_eld_size(eld) / 4, len);
 	DRM_DEBUG_DRIVER("ELD size %d\n", len);
 	for (i = 0; i < len; i++)
-		I915_WRITE(G4X_HDMIW_HDMIEDID, *((u32 *)eld + i));
+		I915_WRITE(G4X_HDMIW_HDMIEDID, *((const u32 *)eld + i));
 
 	tmp = I915_READ(G4X_AUD_CNTL_ST);
 	tmp |= eldv;
@@ -466,7 +466,7 @@ static void hsw_audio_codec_enable(struct intel_encoder *encoder,
 	/* Up to 84 bytes of hw ELD buffer */
 	len = min(drm_eld_size(eld), 84);
 	for (i = 0; i < len / 4; i++)
-		I915_WRITE(HSW_AUD_EDID_DATA(pipe), *((u32 *)eld + i));
+		I915_WRITE(HSW_AUD_EDID_DATA(pipe), *((const u32 *)eld + i));
 
 	/* ELD valid */
 	tmp = I915_READ(HSW_AUD_PIN_ELD_CP_VLD);
@@ -534,7 +534,7 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 	struct drm_connector *connector = conn_state->connector;
 	enum pipe pipe = crtc->pipe;
 	enum port port = encoder->port;
-	u8 *eld = connector->eld;
+	const u8 *eld = connector->eld;
 	u32 tmp, eldv;
 	int len, i;
 	i915_reg_t hdmiw_hdmiedid, aud_config, aud_cntl_st, aud_cntrl_st2;
@@ -585,7 +585,7 @@ static void ilk_audio_codec_enable(struct intel_encoder *encoder,
 	/* Up to 84 bytes of hw ELD buffer */
 	len = min(drm_eld_size(eld), 84);
 	for (i = 0; i < len / 4; i++)
-		I915_WRITE(hdmiw_hdmiedid, *((u32 *)eld + i));
+		I915_WRITE(hdmiw_hdmiedid, *((const u32 *)eld + i));
 
 	/* ELD valid */
 	tmp = I915_READ(aud_cntrl_st2);
-- 
cgit v1.2.3


From f7859590d97614815b35a755c8213dfb8f2766bd Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Tue, 5 Jun 2018 19:20:39 -0400
Subject: audit: eliminate audit_enabled magic number comparison

Remove comparison of audit_enabled to magic numbers outside of audit.

Related: https://github.com/linux-audit/audit-kernel/issues/86

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 drivers/tty/tty_audit.c      | 2 +-
 include/linux/audit.h        | 5 ++++-
 include/net/xfrm.h           | 2 +-
 kernel/audit.c               | 3 ---
 net/netfilter/xt_AUDIT.c     | 2 +-
 net/netlabel/netlabel_user.c | 2 +-
 6 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/tty/tty_audit.c b/drivers/tty/tty_audit.c
index e30aa6bf9ff9..50f567b6a66e 100644
--- a/drivers/tty/tty_audit.c
+++ b/drivers/tty/tty_audit.c
@@ -92,7 +92,7 @@ static void tty_audit_buf_push(struct tty_audit_buf *buf)
 {
 	if (buf->valid == 0)
 		return;
-	if (audit_enabled == 0) {
+	if (audit_enabled == AUDIT_OFF) {
 		buf->valid = 0;
 		return;
 	}
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 69c78477590b..9334fbef7bae 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -117,6 +117,9 @@ struct filename;
 
 extern void audit_log_session_info(struct audit_buffer *ab);
 
+#define AUDIT_OFF	0
+#define AUDIT_ON	1
+#define AUDIT_LOCKED	2
 #ifdef CONFIG_AUDIT
 /* These are defined in audit.c */
 				/* Public API */
@@ -202,7 +205,7 @@ static inline int audit_log_task_context(struct audit_buffer *ab)
 static inline void audit_log_task_info(struct audit_buffer *ab,
 				       struct task_struct *tsk)
 { }
-#define audit_enabled 0
+#define audit_enabled AUDIT_OFF
 #endif /* CONFIG_AUDIT */
 
 #ifdef CONFIG_AUDIT_COMPAT_GENERIC
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 557122846e0e..f7f297727ed8 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -735,7 +735,7 @@ static inline struct audit_buffer *xfrm_audit_start(const char *op)
 {
 	struct audit_buffer *audit_buf = NULL;
 
-	if (audit_enabled == 0)
+	if (audit_enabled == AUDIT_OFF)
 		return NULL;
 	audit_buf = audit_log_start(audit_context(), GFP_ATOMIC,
 				    AUDIT_MAC_IPSEC_EVENT);
diff --git a/kernel/audit.c b/kernel/audit.c
index 5c0a1d7b0c7b..0f3222e4edde 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -83,9 +83,6 @@
 #define AUDIT_INITIALIZED	1
 static int	audit_initialized;
 
-#define AUDIT_OFF	0
-#define AUDIT_ON	1
-#define AUDIT_LOCKED	2
 u32		audit_enabled = AUDIT_OFF;
 bool		audit_ever_enabled = !!AUDIT_OFF;
 
diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c
index f368ee6741db..af883f1b64f9 100644
--- a/net/netfilter/xt_AUDIT.c
+++ b/net/netfilter/xt_AUDIT.c
@@ -72,7 +72,7 @@ audit_tg(struct sk_buff *skb, const struct xt_action_param *par)
 	struct audit_buffer *ab;
 	int fam = -1;
 
-	if (audit_enabled == 0)
+	if (audit_enabled == AUDIT_OFF)
 		goto errout;
 	ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT);
 	if (ab == NULL)
diff --git a/net/netlabel/netlabel_user.c b/net/netlabel/netlabel_user.c
index 2f328af91a52..4676f5bb16ae 100644
--- a/net/netlabel/netlabel_user.c
+++ b/net/netlabel/netlabel_user.c
@@ -101,7 +101,7 @@ struct audit_buffer *netlbl_audit_start_common(int type,
 	char *secctx;
 	u32 secctx_len;
 
-	if (audit_enabled == 0)
+	if (audit_enabled == AUDIT_OFF)
 		return NULL;
 
 	audit_buf = audit_log_start(audit_context(), GFP_ATOMIC, type);
-- 
cgit v1.2.3


From 5fd46e649ee63259f2197625662477ac67a69e79 Mon Sep 17 00:00:00 2001
From: Mac Chiang <mac.chiang@intel.com>
Date: Tue, 19 Jun 2018 14:16:06 +0800
Subject: ASoC: Intel: kbl_da7219_max98357a: add fe_ops for kbl Audio Capture
 Port

platform support fixed constraint hw_prams as Stereo, 48KHz, 16 bits.
This fixed the headset mic recorded noise due to mono capturing
request from some apps. e.g. online Voice Recorder

Signed-off-by: Louis Collard <louiscollard@google.com>
Signed-off-by: Mac Chiang <mac.chiang@intel.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/kbl_da7219_max98357a.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/intel/boards/kbl_da7219_max98357a.c b/sound/soc/intel/boards/kbl_da7219_max98357a.c
index 94294c27d1db..7961f1fd18bd 100644
--- a/sound/soc/intel/boards/kbl_da7219_max98357a.c
+++ b/sound/soc/intel/boards/kbl_da7219_max98357a.c
@@ -380,6 +380,7 @@ static struct snd_soc_dai_link kabylake_dais[] = {
 		.trigger = {
 			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
 		.dpcm_capture = 1,
+		.ops = &kabylake_da7219_fe_ops,
 	},
 	[KBL_DPCM_AUDIO_DMIC_CP] = {
 		.name = "Kbl Audio DMIC cap",
-- 
cgit v1.2.3


From 95555f580dca21fac5ea35c10fa92fa034bd403f Mon Sep 17 00:00:00 2001
From: Naveen Manohar <naveen.m@intel.com>
Date: Mon, 18 Jun 2018 13:29:35 -0500
Subject: ASoC: Intel: broxton: reduce machine name for bxt_da7219_max98357a

Use truncated names in bxt id table and bxt_da7219_max98357a machine
as platform device id table expects names to be less then 20chars.

Signed-off-by: Naveen Manohar <naveen.m@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bxt_da7219_max98357a.c | 4 ++--
 sound/soc/intel/skylake/skl.c                 | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 40eb979d5ac1..3aba5bcf806a 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -586,7 +586,7 @@ static int broxton_audio_probe(struct platform_device *pdev)
 static struct platform_driver broxton_audio = {
 	.probe = broxton_audio_probe,
 	.driver = {
-		.name = "bxt_da7219_max98357a_i2s",
+		.name = "bxt_da7219_max98357a",
 		.pm = &snd_soc_pm_ops,
 	},
 };
@@ -599,4 +599,4 @@ MODULE_AUTHOR("Rohit Ainapure <rohit.m.ainapure@intel.com>");
 MODULE_AUTHOR("Harsha Priya <harshapriya.n@intel.com>");
 MODULE_AUTHOR("Conrad Cooke <conrad.cooke@intel.com>");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("platform:bxt_da7219_max98357a_i2s");
+MODULE_ALIAS("platform:bxt_da7219_max98357a");
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index f0d9793f872a..0a8f0768e987 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -1093,7 +1093,7 @@ static struct snd_soc_acpi_mach sst_bxtp_devdata[] = {
 	},
 	{
 		.id = "DLGS7219",
-		.drv_name = "bxt_da7219_max98357a_i2s",
+		.drv_name = "bxt_da7219_max98357a",
 		.fw_filename = "intel/dsp_fw_bxtn.bin",
 		.machine_quirk = snd_soc_acpi_codec_list,
 		.quirk_data = &bxt_codecs,
-- 
cgit v1.2.3


From 5f15f267daf81a4c7c2a1cd2a0d6743ec7fc8b59 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 18 Jun 2018 13:29:36 -0500
Subject: ASoC: Intel: Skylake: cleanup before moving ACPI tables

There is no need to deal with DMICs if the DSP is not present and
there is no ACPI machine ID found.

Simplify before moving these ACPI tables to sound/soc/intel/common

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/skylake/skl.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 0a8f0768e987..6dec748e8949 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -500,10 +500,12 @@ static int skl_find_machine(struct skl *skl, void *driver_data)
 
 	skl->mach = mach;
 	skl->fw_name = mach->fw_filename;
-	pdata = skl->mach->pdata;
+	pdata = mach->pdata;
 
-	if (mach->pdata)
+	if (pdata) {
 		skl->use_tplg_pcm = pdata->use_tplg_pcm;
+		pdata->dmic_num = skl_get_dmic_geo(skl);
+	}
 
 	return 0;
 }
@@ -930,8 +932,6 @@ static int skl_probe(struct pci_dev *pci,
 
 	pci_set_drvdata(skl->pci, ebus);
 
-	skl_dmic_data.dmic_num = skl_get_dmic_geo(skl);
-
 	/* check if dsp is there */
 	if (bus->ppcap) {
 		/* create device for dsp clk */
-- 
cgit v1.2.3


From cbaa7f0bdbee1969bb311c641abbd0d2af6ba861 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 18 Jun 2018 13:29:37 -0500
Subject: ASoC: Intel: move SKL+ codec ACPI tables to common directory

No functionality change, just move to common tables to make it easier
to deal with SOF and share the same machine drivers - as done
previously for BYT/CHT/HSW/BDW.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-acpi-intel-match.h              |   5 +
 sound/soc/intel/common/Makefile                   |   6 +-
 sound/soc/intel/common/soc-acpi-intel-bxt-match.c |  35 +++++
 sound/soc/intel/common/soc-acpi-intel-cnl-match.c |  29 ++++
 sound/soc/intel/common/soc-acpi-intel-glk-match.c |  23 +++
 sound/soc/intel/common/soc-acpi-intel-kbl-match.c |  91 ++++++++++++
 sound/soc/intel/common/soc-acpi-intel-skl-match.c |  47 +++++++
 sound/soc/intel/skylake/skl.c                     | 162 +---------------------
 8 files changed, 241 insertions(+), 157 deletions(-)
 create mode 100644 sound/soc/intel/common/soc-acpi-intel-bxt-match.c
 create mode 100644 sound/soc/intel/common/soc-acpi-intel-cnl-match.c
 create mode 100644 sound/soc/intel/common/soc-acpi-intel-glk-match.c
 create mode 100644 sound/soc/intel/common/soc-acpi-intel-kbl-match.c
 create mode 100644 sound/soc/intel/common/soc-acpi-intel-skl-match.c

diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h
index 9da6388c20a1..917ddd0f2762 100644
--- a/include/sound/soc-acpi-intel-match.h
+++ b/include/sound/soc-acpi-intel-match.h
@@ -29,5 +29,10 @@ extern struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_legacy_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_baytrail_machines[];
 extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cherrytrail_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[];
+extern struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[];
 
 #endif
diff --git a/sound/soc/intel/common/Makefile b/sound/soc/intel/common/Makefile
index 7379d8830c39..915a34cdc8ac 100644
--- a/sound/soc/intel/common/Makefile
+++ b/sound/soc/intel/common/Makefile
@@ -3,7 +3,11 @@ snd-soc-sst-dsp-objs := sst-dsp.o
 snd-soc-sst-acpi-objs := sst-acpi.o
 snd-soc-sst-ipc-objs := sst-ipc.o
 snd-soc-sst-firmware-objs := sst-firmware.o
-snd-soc-acpi-intel-match-objs := soc-acpi-intel-byt-match.o soc-acpi-intel-cht-match.o soc-acpi-intel-hsw-bdw-match.o
+snd-soc-acpi-intel-match-objs := soc-acpi-intel-byt-match.o soc-acpi-intel-cht-match.o \
+	soc-acpi-intel-hsw-bdw-match.o \
+	soc-acpi-intel-skl-match.o soc-acpi-intel-kbl-match.o \
+	soc-acpi-intel-bxt-match.o soc-acpi-intel-glk-match.o \
+	soc-acpi-intel-cnl-match.o
 
 obj-$(CONFIG_SND_SOC_INTEL_SST) += snd-soc-sst-dsp.o snd-soc-sst-ipc.o
 obj-$(CONFIG_SND_SOC_INTEL_SST_ACPI) += snd-soc-sst-acpi.o
diff --git a/sound/soc/intel/common/soc-acpi-intel-bxt-match.c b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
new file mode 100644
index 000000000000..569f1de97e82
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-bxt-match.c - tables and support for BXT ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+
+static struct snd_soc_acpi_codecs bxt_codecs = {
+	.num_codecs = 1,
+	.codecs = {"MX98357A"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "bxt_alc298s_i2s",
+		.fw_filename = "intel/dsp_fw_bxtn.bin",
+	},
+	{
+		.id = "DLGS7219",
+		.drv_name = "bxt_da7219_max98357a",
+		.fw_filename = "intel/dsp_fw_bxtn.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &bxt_codecs,
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_bxt_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
new file mode 100644
index 000000000000..b83ee053d417
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-cnl-match.c - tables and support for CNL ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+#include "../skylake/skl.h"
+
+static struct skl_machine_pdata cnl_pdata = {
+	.use_tplg_pcm = true,
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[] = {
+	{
+		.id = "INT34C2",
+		.drv_name = "cnl_rt274",
+		.fw_filename = "intel/dsp_fw_cnl.bin",
+		.pdata = &cnl_pdata,
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_cnl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-glk-match.c b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
new file mode 100644
index 000000000000..dee09439e7cb
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
@@ -0,0 +1,23 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-glk-match.c - tables and support for GLK ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "glk_alc298s_i2s",
+		.fw_filename = "intel/dsp_fw_glk.bin",
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_glk_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-kbl-match.c b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c
new file mode 100644
index 000000000000..0ee173ca437d
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-kbl-match.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-kbl-match.c - tables and support for KBL ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+#include "../skylake/skl.h"
+
+static struct skl_machine_pdata skl_dmic_data;
+
+static struct snd_soc_acpi_codecs kbl_codecs = {
+	.num_codecs = 1,
+	.codecs = {"10508825"}
+};
+
+static struct snd_soc_acpi_codecs kbl_poppy_codecs = {
+	.num_codecs = 1,
+	.codecs = {"10EC5663"}
+};
+
+static struct snd_soc_acpi_codecs kbl_5663_5514_codecs = {
+	.num_codecs = 2,
+	.codecs = {"10EC5663", "10EC5514"}
+};
+
+static struct snd_soc_acpi_codecs kbl_7219_98357_codecs = {
+	.num_codecs = 1,
+	.codecs = {"MX98357A"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_kbl_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "kbl_alc286s_i2s",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+	},
+	{
+		.id = "INT343B",
+		.drv_name = "kbl_n88l25_s4567",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98357A",
+		.drv_name = "kbl_n88l25_m98357a",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98927",
+		.drv_name = "kbl_r5514_5663_max",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_5663_5514_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98927",
+		.drv_name = "kbl_rt5663_m98927",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_poppy_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "10EC5663",
+		.drv_name = "kbl_rt5663",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+	},
+	{
+		.id = "DLGS7219",
+		.drv_name = "kbl_da7219_max98357a",
+		.fw_filename = "intel/dsp_fw_kbl.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &kbl_7219_98357_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_kbl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/common/soc-acpi-intel-skl-match.c b/sound/soc/intel/common/soc-acpi-intel-skl-match.c
new file mode 100644
index 000000000000..0c9c0edd35b3
--- /dev/null
+++ b/sound/soc/intel/common/soc-acpi-intel-skl-match.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * soc-apci-intel-skl-match.c - tables and support for SKL ACPI enumeration.
+ *
+ * Copyright (c) 2018, Intel Corporation.
+ *
+ */
+
+#include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
+#include "../skylake/skl.h"
+
+static struct skl_machine_pdata skl_dmic_data;
+
+static struct snd_soc_acpi_codecs skl_codecs = {
+	.num_codecs = 1,
+	.codecs = {"10508825"}
+};
+
+struct snd_soc_acpi_mach snd_soc_acpi_intel_skl_machines[] = {
+	{
+		.id = "INT343A",
+		.drv_name = "skl_alc286s_i2s",
+		.fw_filename = "intel/dsp_fw_release.bin",
+	},
+	{
+		.id = "INT343B",
+		.drv_name = "skl_n88l25_s4567",
+		.fw_filename = "intel/dsp_fw_release.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &skl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{
+		.id = "MX98357A",
+		.drv_name = "skl_n88l25_m98357a",
+		.fw_filename = "intel/dsp_fw_release.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &skl_codecs,
+		.pdata = &skl_dmic_data,
+	},
+	{},
+};
+EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_skl_machines);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel Common ACPI Match module");
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 6dec748e8949..670ff9aaca55 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -29,6 +29,7 @@
 #include <linux/delay.h>
 #include <sound/pcm.h>
 #include <sound/soc-acpi.h>
+#include <sound/soc-acpi-intel-match.h>
 #include <sound/hda_register.h>
 #include <sound/hdaudio.h>
 #include <sound/hda_i915.h>
@@ -36,8 +37,6 @@
 #include "skl-sst-dsp.h"
 #include "skl-sst-ipc.h"
 
-static struct skl_machine_pdata skl_dmic_data;
-
 /*
  * initialize the PCI registers
  */
@@ -1026,172 +1025,23 @@ static void skl_remove(struct pci_dev *pci)
 	dev_set_drvdata(&pci->dev, NULL);
 }
 
-static struct snd_soc_acpi_codecs skl_codecs = {
-	.num_codecs = 1,
-	.codecs = {"10508825"}
-};
-
-static struct snd_soc_acpi_codecs kbl_codecs = {
-	.num_codecs = 1,
-	.codecs = {"10508825"}
-};
-
-static struct snd_soc_acpi_codecs bxt_codecs = {
-	.num_codecs = 1,
-	.codecs = {"MX98357A"}
-};
-
-static struct snd_soc_acpi_codecs kbl_poppy_codecs = {
-	.num_codecs = 1,
-	.codecs = {"10EC5663"}
-};
-
-static struct snd_soc_acpi_codecs kbl_5663_5514_codecs = {
-	.num_codecs = 2,
-	.codecs = {"10EC5663", "10EC5514"}
-};
-
-static struct snd_soc_acpi_codecs kbl_7219_98357_codecs = {
-	.num_codecs = 1,
-	.codecs = {"MX98357A"}
-};
-
-static struct skl_machine_pdata cnl_pdata = {
-	.use_tplg_pcm = true,
-};
-
-static struct snd_soc_acpi_mach sst_skl_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "skl_alc286s_i2s",
-		.fw_filename = "intel/dsp_fw_release.bin",
-	},
-	{
-		.id = "INT343B",
-		.drv_name = "skl_n88l25_s4567",
-		.fw_filename = "intel/dsp_fw_release.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &skl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98357A",
-		.drv_name = "skl_n88l25_m98357a",
-		.fw_filename = "intel/dsp_fw_release.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &skl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{}
-};
-
-static struct snd_soc_acpi_mach sst_bxtp_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "bxt_alc298s_i2s",
-		.fw_filename = "intel/dsp_fw_bxtn.bin",
-	},
-	{
-		.id = "DLGS7219",
-		.drv_name = "bxt_da7219_max98357a",
-		.fw_filename = "intel/dsp_fw_bxtn.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &bxt_codecs,
-	},
-	{}
-};
-
-static struct snd_soc_acpi_mach sst_kbl_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "kbl_alc286s_i2s",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-	},
-	{
-		.id = "INT343B",
-		.drv_name = "kbl_n88l25_s4567",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98357A",
-		.drv_name = "kbl_n88l25_m98357a",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98927",
-		.drv_name = "kbl_r5514_5663_max",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_5663_5514_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "MX98927",
-		.drv_name = "kbl_rt5663_m98927",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_poppy_codecs,
-		.pdata = &skl_dmic_data
-	},
-	{
-		.id = "10EC5663",
-		.drv_name = "kbl_rt5663",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-	},
-	{
-		.id = "DLGS7219",
-		.drv_name = "kbl_da7219_max98357a",
-		.fw_filename = "intel/dsp_fw_kbl.bin",
-		.machine_quirk = snd_soc_acpi_codec_list,
-		.quirk_data = &kbl_7219_98357_codecs,
-		.pdata = &skl_dmic_data
-	},
-
-	{}
-};
-
-static struct snd_soc_acpi_mach sst_glk_devdata[] = {
-	{
-		.id = "INT343A",
-		.drv_name = "glk_alc298s_i2s",
-		.fw_filename = "intel/dsp_fw_glk.bin",
-	},
-	{}
-};
-
-static const struct snd_soc_acpi_mach sst_cnl_devdata[] = {
-	{
-		.id = "INT34C2",
-		.drv_name = "cnl_rt274",
-		.fw_filename = "intel/dsp_fw_cnl.bin",
-		.pdata = &cnl_pdata,
-	},
-	{}
-};
-
 /* PCI IDs */
 static const struct pci_device_id skl_ids[] = {
 	/* Sunrise Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9d70),
-		.driver_data = (unsigned long)&sst_skl_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_skl_machines},
 	/* BXT-P */
 	{ PCI_DEVICE(0x8086, 0x5a98),
-		.driver_data = (unsigned long)&sst_bxtp_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_bxt_machines},
 	/* KBL */
 	{ PCI_DEVICE(0x8086, 0x9D71),
-		.driver_data = (unsigned long)&sst_kbl_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_kbl_machines},
 	/* GLK */
 	{ PCI_DEVICE(0x8086, 0x3198),
-		.driver_data = (unsigned long)&sst_glk_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_glk_machines},
 	/* CNL */
 	{ PCI_DEVICE(0x8086, 0x9dc8),
-		.driver_data = (unsigned long)&sst_cnl_devdata},
+		.driver_data = (unsigned long)&snd_soc_acpi_intel_cnl_machines},
 	{ 0, }
 };
 MODULE_DEVICE_TABLE(pci, skl_ids);
-- 
cgit v1.2.3


From 65a33883c778befcb85ef45285763fd8ac1b2ba3 Mon Sep 17 00:00:00 2001
From: Naveen Manohar <naveen.m@intel.com>
Date: Mon, 18 Jun 2018 13:29:38 -0500
Subject: ASoC: Intel: common: Add Geminilake Dialog+Maxim machine driver entry

This patch adds da7219_max98357a machine driver entry into
machine table

Signed-off-by: Naveen Manohar <naveen.m@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/soc-acpi-intel-glk-match.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/sound/soc/intel/common/soc-acpi-intel-glk-match.c b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
index dee09439e7cb..5902aa1d0ee3 100644
--- a/sound/soc/intel/common/soc-acpi-intel-glk-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
@@ -9,12 +9,24 @@
 #include <sound/soc-acpi.h>
 #include <sound/soc-acpi-intel-match.h>
 
+static struct snd_soc_acpi_codecs glk_codecs = {
+	.num_codecs = 1,
+	.codecs = {"MX98357A"}
+};
+
 struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = {
 	{
 		.id = "INT343A",
 		.drv_name = "glk_alc298s_i2s",
 		.fw_filename = "intel/dsp_fw_glk.bin",
 	},
+	{
+		.id = "DLGS7219",
+		.drv_name = "glk_da7219_max98357a",
+		.fw_filename = "intel/dsp_fw_glk.bin",
+		.machine_quirk = snd_soc_acpi_codec_list,
+		.quirk_data = &glk_codecs,
+	},
 	{},
 };
 EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_glk_machines);
-- 
cgit v1.2.3


From e6d298fd4a4454dd121343323e3f00a27f8819a4 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 18 Jun 2018 13:29:39 -0500
Subject: ASoC: Intel: common: add firmware/topology information for SOF

No functionality change for Skylake driver, add relevant names needed
by SOF for BXT/APL, GLK and CNL.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/soc-acpi-intel-bxt-match.c | 3 +++
 sound/soc/intel/common/soc-acpi-intel-cnl-match.c | 3 +++
 sound/soc/intel/common/soc-acpi-intel-glk-match.c | 6 ++++++
 3 files changed, 12 insertions(+)

diff --git a/sound/soc/intel/common/soc-acpi-intel-bxt-match.c b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
index 569f1de97e82..50869eddbb3b 100644
--- a/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
@@ -26,6 +26,9 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[] = {
 		.fw_filename = "intel/dsp_fw_bxtn.bin",
 		.machine_quirk = snd_soc_acpi_codec_list,
 		.quirk_data = &bxt_codecs,
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-da7219.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
 	},
 	{},
 };
diff --git a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
index b83ee053d417..ec8e28e7b937 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cnl-match.c
@@ -20,6 +20,9 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_cnl_machines[] = {
 		.drv_name = "cnl_rt274",
 		.fw_filename = "intel/dsp_fw_cnl.bin",
 		.pdata = &cnl_pdata,
+		.sof_fw_filename = "intel/sof-cnl.ri",
+		.sof_tplg_filename = "intel/sof-cnl-rt274.tplg",
+		.asoc_plat_name = "0000:00:1f.3",
 	},
 	{},
 };
diff --git a/sound/soc/intel/common/soc-acpi-intel-glk-match.c b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
index 5902aa1d0ee3..305875af71ca 100644
--- a/sound/soc/intel/common/soc-acpi-intel-glk-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-glk-match.c
@@ -19,6 +19,9 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = {
 		.id = "INT343A",
 		.drv_name = "glk_alc298s_i2s",
 		.fw_filename = "intel/dsp_fw_glk.bin",
+		.sof_fw_filename = "intel/sof-glk.ri",
+		.sof_tplg_filename = "intel/sof-glk-alc298.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
 	},
 	{
 		.id = "DLGS7219",
@@ -26,6 +29,9 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_glk_machines[] = {
 		.fw_filename = "intel/dsp_fw_glk.bin",
 		.machine_quirk = snd_soc_acpi_codec_list,
 		.quirk_data = &glk_codecs,
+		.sof_fw_filename = "intel/sof-glk.ri",
+		.sof_tplg_filename = "intel/sof-glk-da7219.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
 	},
 	{},
 };
-- 
cgit v1.2.3


From b45350135b9241b64cc91ccc8dddca2ee4dc25d7 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 18 Jun 2018 13:29:41 -0500
Subject: ASoC: Intel: common: add entries for SOF-based machine drivers

While we are at it, add entries for machine drivers that are used on
SOF-based platforms. The drivers will be submitted upstream after the
core SOF patches, but there's no harm in adding these references now.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/soc-acpi-intel-bxt-match.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/sound/soc/intel/common/soc-acpi-intel-bxt-match.c b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
index 50869eddbb3b..f39386e540d3 100644
--- a/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-bxt-match.c
@@ -30,6 +30,27 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_bxt_machines[] = {
 		.sof_tplg_filename = "intel/sof-apl-da7219.tplg",
 		.asoc_plat_name = "0000:00:0e.0",
 	},
+	{
+		.id = "104C5122",
+		.drv_name = "bxt-pcm512x",
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-pcm512x.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{
+		.id = "1AEC8804",
+		.drv_name = "bxt-wm8804",
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-wm8804.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
+	{
+		.id = "INT34C3",
+		.drv_name = "bxt_tdf8532",
+		.sof_fw_filename = "intel/sof-apl.ri",
+		.sof_tplg_filename = "intel/sof-apl-tdf8532.tplg",
+		.asoc_plat_name = "0000:00:0e.0",
+	},
 	{},
 };
 EXPORT_SYMBOL_GPL(snd_soc_acpi_intel_bxt_machines);
-- 
cgit v1.2.3


From f0d9034b290d8bad590e843c2a1081eb47d813ad Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Mon, 18 Jun 2018 13:29:42 -0500
Subject: ASoC: Intel: common: fix copy/paste issue with SOF/broadwell topology
 file

There are two commercially-available Broadwell platforms based on I2S
(Dell XPS13 and 'Samus' Pixel 2015 Chromebook).

Fix a copy/paste issue to allow each platform to enable different
features if needed when SOF is enabled

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c b/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
index e0e8c8c27528..53e7acdfbb81 100644
--- a/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
@@ -45,7 +45,7 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[] = {
 		.drv_name = "bdw-rt5677",
 		.fw_filename =  "intel/IntcSST2.bin",
 		.sof_fw_filename = "intel/reef-bdw.ri",
-		.sof_tplg_filename = "intel/reef-bdw-rt286.tplg",
+		.sof_tplg_filename = "intel/reef-bdw-rt5677.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{
-- 
cgit v1.2.3


From a9191579ba1086d91842199263e6fe6bb5eec1ba Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 19 Jun 2018 16:10:00 +0100
Subject: regulator: arizona-ldo1: Use correct device to get enable GPIO

Currently the enable GPIO is being looked up on the regulator
device itself but that does not have its own DT node, this causes
the lookup to fail and the regulator not to get its GPIO. The DT
node is shared across the whole MFD and as such the lookup needs
to happen on that parent device. Moving the lookup to the parent
device also means devres can no longer be used as the life time
would attach to the wrong device.

Additionally, the enable GPIO is active high so we should be passing
GPIOD_OUT_LOW to ensure the regulator starts in its off state allowing
the driver to enable it when it is ready.

Fixes: e1739e86f0cb ("regulator: arizona-ldo1: Look up a descriptor and pass to the core")
Reported-by: Matthias Reichl <hias@horus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/arizona-ldo1.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/drivers/regulator/arizona-ldo1.c b/drivers/regulator/arizona-ldo1.c
index f6d6a4ad9e8a..e976d073f28d 100644
--- a/drivers/regulator/arizona-ldo1.c
+++ b/drivers/regulator/arizona-ldo1.c
@@ -36,6 +36,8 @@ struct arizona_ldo1 {
 
 	struct regulator_consumer_supply supply;
 	struct regulator_init_data init_data;
+
+	struct gpio_desc *ena_gpiod;
 };
 
 static int arizona_ldo1_hc_list_voltage(struct regulator_dev *rdev,
@@ -253,12 +255,17 @@ static int arizona_ldo1_common_init(struct platform_device *pdev,
 		}
 	}
 
-	/* We assume that high output = regulator off */
-	config.ena_gpiod = devm_gpiod_get_optional(&pdev->dev, "wlf,ldoena",
-						   GPIOD_OUT_HIGH);
+	/* We assume that high output = regulator off
+	 * Don't use devm, since we need to get against the parent device
+	 * so clean up would happen at the wrong time
+	 */
+	config.ena_gpiod = gpiod_get_optional(parent_dev, "wlf,ldoena",
+					      GPIOD_OUT_LOW);
 	if (IS_ERR(config.ena_gpiod))
 		return PTR_ERR(config.ena_gpiod);
 
+	ldo1->ena_gpiod = config.ena_gpiod;
+
 	if (pdata->init_data)
 		config.init_data = pdata->init_data;
 	else
@@ -276,6 +283,9 @@ static int arizona_ldo1_common_init(struct platform_device *pdev,
 	of_node_put(config.of_node);
 
 	if (IS_ERR(ldo1->regulator)) {
+		if (config.ena_gpiod)
+			gpiod_put(config.ena_gpiod);
+
 		ret = PTR_ERR(ldo1->regulator);
 		dev_err(&pdev->dev, "Failed to register LDO1 supply: %d\n",
 			ret);
@@ -334,8 +344,19 @@ static int arizona_ldo1_probe(struct platform_device *pdev)
 	return ret;
 }
 
+static int arizona_ldo1_remove(struct platform_device *pdev)
+{
+	struct arizona_ldo1 *ldo1 = platform_get_drvdata(pdev);
+
+	if (ldo1->ena_gpiod)
+		gpiod_put(ldo1->ena_gpiod);
+
+	return 0;
+}
+
 static struct platform_driver arizona_ldo1_driver = {
 	.probe = arizona_ldo1_probe,
+	.remove = arizona_ldo1_remove,
 	.driver		= {
 		.name	= "arizona-ldo1",
 	},
-- 
cgit v1.2.3


From 244e293690a6e07cbdfa11af1977488d91931eed Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Tue, 19 Jun 2018 16:22:09 +0100
Subject: ASoC: pcm: Tidy up open/hw_params handling

Currently, the core will continue processing open/hw_params
component callbacks after one has failed even though it will abort
immediately afterwards. This is unnecessary and also has the issue
that close/hw_free will be called on the component which failed
open/hw_params which could result in issues if the driver doesn't
expect this behaviour.

Update the core to abort processing open/hw_params when an error
is hit and only call close/hw_free for those components that were
successfully opened.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-pcm.c | 116 ++++++++++++++++++++++++++++------------------------
 1 file changed, 62 insertions(+), 54 deletions(-)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 5e7ae47a9658..45b52f7b9690 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -448,6 +448,29 @@ static void soc_pcm_init_runtime_hw(struct snd_pcm_substream *substream)
 	hw->rate_max = min_not_zero(hw->rate_max, rate_max);
 }
 
+static int soc_pcm_components_close(struct snd_pcm_substream *substream,
+				    struct snd_soc_component *last)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
+
+	for_each_rtdcom(rtd, rtdcom) {
+		component = rtdcom->component;
+
+		if (component == last)
+			break;
+
+		if (!component->driver->ops ||
+		    !component->driver->ops->close)
+			continue;
+
+		component->driver->ops->close(substream);
+	}
+
+	return 0;
+}
+
 /*
  * Called by ALSA when a PCM substream is opened, the runtime->hw record is
  * then initialized and any private data can be allocated. This also calls
@@ -462,7 +485,7 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai *codec_dai;
 	const char *codec_dai_name = "multicodec";
-	int i, ret = 0, __ret;
+	int i, ret = 0;
 
 	pinctrl_pm_select_default_state(cpu_dai->dev);
 	for (i = 0; i < rtd->num_codecs; i++)
@@ -486,7 +509,6 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 		}
 	}
 
-	ret = 0;
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
@@ -494,16 +516,15 @@ static int soc_pcm_open(struct snd_pcm_substream *substream)
 		    !component->driver->ops->open)
 			continue;
 
-		__ret = component->driver->ops->open(substream);
-		if (__ret < 0) {
+		ret = component->driver->ops->open(substream);
+		if (ret < 0) {
 			dev_err(component->dev,
 				"ASoC: can't open component %s: %d\n",
-				component->name, __ret);
-			ret = __ret;
+				component->name, ret);
+			goto component_err;
 		}
 	}
-	if (ret < 0)
-		goto component_err;
+	component = NULL;
 
 	for (i = 0; i < rtd->num_codecs; i++) {
 		codec_dai = rtd->codec_dais[i];
@@ -612,15 +633,7 @@ codec_dai_err:
 	}
 
 component_err:
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->close)
-			continue;
-
-		component->driver->ops->close(substream);
-	}
+	soc_pcm_components_close(substream, component);
 
 	if (cpu_dai->driver->ops->shutdown)
 		cpu_dai->driver->ops->shutdown(substream, cpu_dai);
@@ -714,15 +727,7 @@ static int soc_pcm_close(struct snd_pcm_substream *substream)
 	if (rtd->dai_link->ops->shutdown)
 		rtd->dai_link->ops->shutdown(substream);
 
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->close)
-			continue;
-
-		component->driver->ops->close(substream);
-	}
+	soc_pcm_components_close(substream, NULL);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 		if (snd_soc_runtime_ignore_pmdown_time(rtd)) {
@@ -874,6 +879,29 @@ int soc_dai_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+static int soc_pcm_components_hw_free(struct snd_pcm_substream *substream,
+				      struct snd_soc_component *last)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
+
+	for_each_rtdcom(rtd, rtdcom) {
+		component = rtdcom->component;
+
+		if (component == last)
+			break;
+
+		if (!component->driver->ops ||
+		    !component->driver->ops->hw_free)
+			continue;
+
+		component->driver->ops->hw_free(substream);
+	}
+
+	return 0;
+}
+
 /*
  * Called by ALSA when the hardware params are set by application. This
  * function can also be called multiple times and can allocate buffers
@@ -886,7 +914,7 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component;
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	int i, ret = 0, __ret;
+	int i, ret = 0;
 
 	mutex_lock_nested(&rtd->pcm_mutex, rtd->pcm_subclass);
 	if (rtd->dai_link->ops->hw_params) {
@@ -944,7 +972,6 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (ret < 0)
 		goto interface_err;
 
-	ret = 0;
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
@@ -952,16 +979,15 @@ static int soc_pcm_hw_params(struct snd_pcm_substream *substream,
 		    !component->driver->ops->hw_params)
 			continue;
 
-		__ret = component->driver->ops->hw_params(substream, params);
-		if (__ret < 0) {
+		ret = component->driver->ops->hw_params(substream, params);
+		if (ret < 0) {
 			dev_err(component->dev,
 				"ASoC: %s hw params failed: %d\n",
-				component->name, __ret);
-			ret = __ret;
+				component->name, ret);
+			goto component_err;
 		}
 	}
-	if (ret < 0)
-		goto component_err;
+	component = NULL;
 
 	/* store the parameters for each DAIs */
 	cpu_dai->rate = params_rate(params);
@@ -977,15 +1003,7 @@ out:
 	return ret;
 
 component_err:
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->hw_free)
-			continue;
-
-		component->driver->ops->hw_free(substream);
-	}
+	soc_pcm_components_hw_free(substream, component);
 
 	if (cpu_dai->driver->ops->hw_free)
 		cpu_dai->driver->ops->hw_free(substream, cpu_dai);
@@ -1014,8 +1032,6 @@ codec_err:
 static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_soc_component *component;
-	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai *codec_dai;
 	bool playback = substream->stream == SNDRV_PCM_STREAM_PLAYBACK;
@@ -1052,15 +1068,7 @@ static int soc_pcm_hw_free(struct snd_pcm_substream *substream)
 		rtd->dai_link->ops->hw_free(substream);
 
 	/* free any component resources */
-	for_each_rtdcom(rtd, rtdcom) {
-		component = rtdcom->component;
-
-		if (!component->driver->ops ||
-		    !component->driver->ops->hw_free)
-			continue;
-
-		component->driver->ops->hw_free(substream);
-	}
+	soc_pcm_components_hw_free(substream, NULL);
 
 	/* now free hw params for the DAIs  */
 	for (i = 0; i < rtd->num_codecs; i++) {
-- 
cgit v1.2.3


From ab48576c4298f7d8cd93e78f085841a05967e125 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:00 +0200
Subject: selinux: Cleanup printk logging in conditional

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/conditional.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/security/selinux/ss/conditional.c b/security/selinux/ss/conditional.c
index c91543a617ac..f49e522e932d 100644
--- a/security/selinux/ss/conditional.c
+++ b/security/selinux/ss/conditional.c
@@ -96,7 +96,7 @@ int evaluate_cond_node(struct policydb *p, struct cond_node *node)
 	if (new_state != node->cur_state) {
 		node->cur_state = new_state;
 		if (new_state == -1)
-			printk(KERN_ERR "SELinux: expression result was undefined - disabling all rules.\n");
+			pr_err("SELinux: expression result was undefined - disabling all rules.\n");
 		/* turn the rules on or off */
 		for (cur = node->true_list; cur; cur = cur->next) {
 			if (new_state <= 0)
@@ -287,7 +287,7 @@ static int cond_insertf(struct avtab *a, struct avtab_key *k, struct avtab_datum
 	 */
 	if (k->specified & AVTAB_TYPE) {
 		if (avtab_search(&p->te_avtab, k)) {
-			printk(KERN_ERR "SELinux: type rule already exists outside of a conditional.\n");
+			pr_err("SELinux: type rule already exists outside of a conditional.\n");
 			goto err;
 		}
 		/*
@@ -302,7 +302,7 @@ static int cond_insertf(struct avtab *a, struct avtab_key *k, struct avtab_datum
 			node_ptr = avtab_search_node(&p->te_cond_avtab, k);
 			if (node_ptr) {
 				if (avtab_search_node_next(node_ptr, k->specified)) {
-					printk(KERN_ERR "SELinux: too many conflicting type rules.\n");
+					pr_err("SELinux: too many conflicting type rules.\n");
 					goto err;
 				}
 				found = 0;
@@ -313,13 +313,13 @@ static int cond_insertf(struct avtab *a, struct avtab_key *k, struct avtab_datum
 					}
 				}
 				if (!found) {
-					printk(KERN_ERR "SELinux: conflicting type rules.\n");
+					pr_err("SELinux: conflicting type rules.\n");
 					goto err;
 				}
 			}
 		} else {
 			if (avtab_search(&p->te_cond_avtab, k)) {
-				printk(KERN_ERR "SELinux: conflicting type rules when adding type rule for true.\n");
+				pr_err("SELinux: conflicting type rules when adding type rule for true.\n");
 				goto err;
 			}
 		}
@@ -327,7 +327,7 @@ static int cond_insertf(struct avtab *a, struct avtab_key *k, struct avtab_datum
 
 	node_ptr = avtab_insert_nonunique(&p->te_cond_avtab, k, d);
 	if (!node_ptr) {
-		printk(KERN_ERR "SELinux: could not insert rule.\n");
+		pr_err("SELinux: could not insert rule.\n");
 		rc = -ENOMEM;
 		goto err;
 	}
@@ -387,12 +387,12 @@ static int cond_read_av_list(struct policydb *p, void *fp, struct cond_av_list *
 static int expr_isvalid(struct policydb *p, struct cond_expr *expr)
 {
 	if (expr->expr_type <= 0 || expr->expr_type > COND_LAST) {
-		printk(KERN_ERR "SELinux: conditional expressions uses unknown operator.\n");
+		pr_err("SELinux: conditional expressions uses unknown operator.\n");
 		return 0;
 	}
 
 	if (expr->bool > p->p_bools.nprim) {
-		printk(KERN_ERR "SELinux: conditional expressions uses unknown bool.\n");
+		pr_err("SELinux: conditional expressions uses unknown bool.\n");
 		return 0;
 	}
 	return 1;
-- 
cgit v1.2.3


From 180cfc58cd9a8bf836dccde0c9e8af0d3073e4bd Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:01 +0200
Subject: selinux: Cleanup printk logging in ebitmap

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/ebitmap.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/security/selinux/ss/ebitmap.c b/security/selinux/ss/ebitmap.c
index 5ae8c61b75bf..8f624f80055b 100644
--- a/security/selinux/ss/ebitmap.c
+++ b/security/selinux/ss/ebitmap.c
@@ -362,7 +362,7 @@ int ebitmap_read(struct ebitmap *e, void *fp)
 	count = le32_to_cpu(buf[2]);
 
 	if (mapunit != BITS_PER_U64) {
-		printk(KERN_ERR "SELinux: ebitmap: map size %u does not "
+		pr_err("SELinux: ebitmap: map size %u does not "
 		       "match my size %zd (high bit was %d)\n",
 		       mapunit, BITS_PER_U64, e->highbit);
 		goto bad;
@@ -383,19 +383,19 @@ int ebitmap_read(struct ebitmap *e, void *fp)
 	for (i = 0; i < count; i++) {
 		rc = next_entry(&startbit, fp, sizeof(u32));
 		if (rc < 0) {
-			printk(KERN_ERR "SELinux: ebitmap: truncated map\n");
+			pr_err("SELinux: ebitmap: truncated map\n");
 			goto bad;
 		}
 		startbit = le32_to_cpu(startbit);
 
 		if (startbit & (mapunit - 1)) {
-			printk(KERN_ERR "SELinux: ebitmap start bit (%d) is "
+			pr_err("SELinux: ebitmap start bit (%d) is "
 			       "not a multiple of the map unit size (%u)\n",
 			       startbit, mapunit);
 			goto bad;
 		}
 		if (startbit > e->highbit - mapunit) {
-			printk(KERN_ERR "SELinux: ebitmap start bit (%d) is "
+			pr_err("SELinux: ebitmap start bit (%d) is "
 			       "beyond the end of the bitmap (%u)\n",
 			       startbit, (e->highbit - mapunit));
 			goto bad;
@@ -405,8 +405,7 @@ int ebitmap_read(struct ebitmap *e, void *fp)
 			struct ebitmap_node *tmp;
 			tmp = kmem_cache_zalloc(ebitmap_node_cachep, GFP_KERNEL);
 			if (!tmp) {
-				printk(KERN_ERR
-				       "SELinux: ebitmap: out of memory\n");
+				pr_err("SELinux: ebitmap: out of memory\n");
 				rc = -ENOMEM;
 				goto bad;
 			}
@@ -418,7 +417,7 @@ int ebitmap_read(struct ebitmap *e, void *fp)
 				e->node = tmp;
 			n = tmp;
 		} else if (startbit <= n->startbit) {
-			printk(KERN_ERR "SELinux: ebitmap: start bit %d"
+			pr_err("SELinux: ebitmap: start bit %d"
 			       " comes after start bit %d\n",
 			       startbit, n->startbit);
 			goto bad;
@@ -426,7 +425,7 @@ int ebitmap_read(struct ebitmap *e, void *fp)
 
 		rc = next_entry(&map, fp, sizeof(u64));
 		if (rc < 0) {
-			printk(KERN_ERR "SELinux: ebitmap: truncated map\n");
+			pr_err("SELinux: ebitmap: truncated map\n");
 			goto bad;
 		}
 		map = le64_to_cpu(map);
-- 
cgit v1.2.3


From 9ffdd49e3d735a5d12b5b31151893049e7075332 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:02 +0200
Subject: selinux: Cleanup printk logging in policydb

Replace printk with pr_* to avoid checkpatch warnings and
replace KERN_CONT with 2 longer prints.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
[PM: fixed some missing newlines identified by Joe Perches]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/policydb.c | 91 +++++++++++++++++++++---------------------
 1 file changed, 46 insertions(+), 45 deletions(-)

diff --git a/security/selinux/ss/policydb.c b/security/selinux/ss/policydb.c
index 6e8c8056d7ad..e9394e7adc84 100644
--- a/security/selinux/ss/policydb.c
+++ b/security/selinux/ss/policydb.c
@@ -504,7 +504,7 @@ static void hash_eval(struct hashtab *h, const char *hash_name)
 	struct hashtab_info info;
 
 	hashtab_stat(h, &info);
-	printk(KERN_DEBUG "SELinux: %s:  %d entries and %d/%d buckets used, "
+	pr_debug("SELinux: %s:  %d entries and %d/%d buckets used, "
 	       "longest chain length %d\n", hash_name, h->nel,
 	       info.slots_used, h->size, info.max_chain_len);
 }
@@ -533,15 +533,17 @@ static int policydb_index(struct policydb *p)
 {
 	int i, rc;
 
-	printk(KERN_DEBUG "SELinux:  %d users, %d roles, %d types, %d bools",
-	       p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim, p->p_bools.nprim);
 	if (p->mls_enabled)
-		printk(KERN_CONT ", %d sens, %d cats", p->p_levels.nprim,
-		       p->p_cats.nprim);
-	printk(KERN_CONT "\n");
+		pr_debug("SELinux:  %d users, %d roles, %d types, %d bools, %d sens, %d cats\n",
+			 p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim,
+			 p->p_bools.nprim, p->p_levels.nprim, p->p_cats.nprim);
+	else
+		pr_debug("SELinux:  %d users, %d roles, %d types, %d bools\n",
+			 p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim,
+			 p->p_bools.nprim);
 
-	printk(KERN_DEBUG "SELinux:  %d classes, %d rules\n",
-	       p->p_classes.nprim, p->te_avtab.nel);
+	pr_debug("SELinux:  %d classes, %d rules\n",
+		 p->p_classes.nprim, p->te_avtab.nel);
 
 #ifdef DEBUG_HASHES
 	avtab_hash_eval(&p->te_avtab, "rules");
@@ -897,7 +899,7 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s)
 
 	rc = sidtab_init(s);
 	if (rc) {
-		printk(KERN_ERR "SELinux:  out of memory on SID table init\n");
+		pr_err("SELinux:  out of memory on SID table init\n");
 		goto out;
 	}
 
@@ -905,14 +907,14 @@ int policydb_load_isids(struct policydb *p, struct sidtab *s)
 	for (c = head; c; c = c->next) {
 		rc = -EINVAL;
 		if (!c->context[0].user) {
-			printk(KERN_ERR "SELinux:  SID %s was never defined.\n",
+			pr_err("SELinux:  SID %s was never defined.\n",
 				c->u.name);
 			goto out;
 		}
 
 		rc = sidtab_insert(s, c->sid[0], &c->context[0]);
 		if (rc) {
-			printk(KERN_ERR "SELinux:  unable to load initial SID %s.\n",
+			pr_err("SELinux:  unable to load initial SID %s.\n",
 				c->u.name);
 			goto out;
 		}
@@ -1005,13 +1007,13 @@ static int mls_read_range_helper(struct mls_range *r, void *fp)
 	rc = -EINVAL;
 	items = le32_to_cpu(buf[0]);
 	if (items > ARRAY_SIZE(buf)) {
-		printk(KERN_ERR "SELinux: mls:  range overflow\n");
+		pr_err("SELinux: mls:  range overflow\n");
 		goto out;
 	}
 
 	rc = next_entry(buf, fp, sizeof(u32) * items);
 	if (rc) {
-		printk(KERN_ERR "SELinux: mls:  truncated range\n");
+		pr_err("SELinux: mls:  truncated range\n");
 		goto out;
 	}
 
@@ -1023,19 +1025,19 @@ static int mls_read_range_helper(struct mls_range *r, void *fp)
 
 	rc = ebitmap_read(&r->level[0].cat, fp);
 	if (rc) {
-		printk(KERN_ERR "SELinux: mls:  error reading low categories\n");
+		pr_err("SELinux: mls:  error reading low categories\n");
 		goto out;
 	}
 	if (items > 1) {
 		rc = ebitmap_read(&r->level[1].cat, fp);
 		if (rc) {
-			printk(KERN_ERR "SELinux: mls:  error reading high categories\n");
+			pr_err("SELinux: mls:  error reading high categories\n");
 			goto bad_high;
 		}
 	} else {
 		rc = ebitmap_cpy(&r->level[1].cat, &r->level[0].cat);
 		if (rc) {
-			printk(KERN_ERR "SELinux: mls:  out of memory\n");
+			pr_err("SELinux: mls:  out of memory\n");
 			goto bad_high;
 		}
 	}
@@ -1060,7 +1062,7 @@ static int context_read_and_validate(struct context *c,
 
 	rc = next_entry(buf, fp, sizeof buf);
 	if (rc) {
-		printk(KERN_ERR "SELinux: context truncated\n");
+		pr_err("SELinux: context truncated\n");
 		goto out;
 	}
 	c->user = le32_to_cpu(buf[0]);
@@ -1069,14 +1071,14 @@ static int context_read_and_validate(struct context *c,
 	if (p->policyvers >= POLICYDB_VERSION_MLS) {
 		rc = mls_read_range_helper(&c->range, fp);
 		if (rc) {
-			printk(KERN_ERR "SELinux: error reading MLS range of context\n");
+			pr_err("SELinux: error reading MLS range of context\n");
 			goto out;
 		}
 	}
 
 	rc = -EINVAL;
 	if (!policydb_context_isvalid(p, c)) {
-		printk(KERN_ERR "SELinux:  invalid security context\n");
+		pr_err("SELinux:  invalid security context\n");
 		context_destroy(c);
 		goto out;
 	}
@@ -1352,7 +1354,8 @@ static int class_read(struct policydb *p, struct hashtab *h, void *fp)
 		rc = -EINVAL;
 		cladatum->comdatum = hashtab_search(p->p_commons.table, cladatum->comkey);
 		if (!cladatum->comdatum) {
-			printk(KERN_ERR "SELinux:  unknown common %s\n", cladatum->comkey);
+			pr_err("SELinux:  unknown common %s\n",
+			       cladatum->comkey);
 			goto bad;
 		}
 	}
@@ -1444,7 +1447,7 @@ static int role_read(struct policydb *p, struct hashtab *h, void *fp)
 	if (strcmp(key, OBJECT_R) == 0) {
 		rc = -EINVAL;
 		if (role->value != OBJECT_R_VAL) {
-			printk(KERN_ERR "SELinux: Role %s has wrong value %d\n",
+			pr_err("SELinux: Role %s has wrong value %d\n",
 			       OBJECT_R, role->value);
 			goto bad;
 		}
@@ -1522,14 +1525,14 @@ static int mls_read_level(struct mls_level *lp, void *fp)
 
 	rc = next_entry(buf, fp, sizeof buf);
 	if (rc) {
-		printk(KERN_ERR "SELinux: mls: truncated level\n");
+		pr_err("SELinux: mls: truncated level\n");
 		return rc;
 	}
 	lp->sens = le32_to_cpu(buf[0]);
 
 	rc = ebitmap_read(&lp->cat, fp);
 	if (rc) {
-		printk(KERN_ERR "SELinux: mls:  error reading level categories\n");
+		pr_err("SELinux: mls:  error reading level categories\n");
 		return rc;
 	}
 	return 0;
@@ -1683,7 +1686,7 @@ static int user_bounds_sanity_check(void *key, void *datum, void *datap)
 		unsigned long bit;
 
 		if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
-			printk(KERN_ERR "SELinux: user %s: "
+			pr_err("SELinux: user %s: "
 			       "too deep or looped boundary",
 			       (char *) key);
 			return -EINVAL;
@@ -1694,8 +1697,7 @@ static int user_bounds_sanity_check(void *key, void *datum, void *datap)
 			if (ebitmap_get_bit(&upper->roles, bit))
 				continue;
 
-			printk(KERN_ERR
-			       "SELinux: boundary violated policy: "
+			pr_err("SELinux: boundary violated policy: "
 			       "user=%s role=%s bounds=%s\n",
 			       sym_name(p, SYM_USERS, user->value - 1),
 			       sym_name(p, SYM_ROLES, bit),
@@ -1720,7 +1722,7 @@ static int role_bounds_sanity_check(void *key, void *datum, void *datap)
 		unsigned long bit;
 
 		if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
-			printk(KERN_ERR "SELinux: role %s: "
+			pr_err("SELinux: role %s: "
 			       "too deep or looped bounds\n",
 			       (char *) key);
 			return -EINVAL;
@@ -1731,8 +1733,7 @@ static int role_bounds_sanity_check(void *key, void *datum, void *datap)
 			if (ebitmap_get_bit(&upper->types, bit))
 				continue;
 
-			printk(KERN_ERR
-			       "SELinux: boundary violated policy: "
+			pr_err("SELinux: boundary violated policy: "
 			       "role=%s type=%s bounds=%s\n",
 			       sym_name(p, SYM_ROLES, role->value - 1),
 			       sym_name(p, SYM_TYPES, bit),
@@ -1754,7 +1755,7 @@ static int type_bounds_sanity_check(void *key, void *datum, void *datap)
 	upper = datum;
 	while (upper->bounds) {
 		if (++depth == POLICYDB_BOUNDS_MAXDEPTH) {
-			printk(KERN_ERR "SELinux: type %s: "
+			pr_err("SELinux: type %s: "
 			       "too deep or looped boundary\n",
 			       (char *) key);
 			return -EINVAL;
@@ -1765,7 +1766,7 @@ static int type_bounds_sanity_check(void *key, void *datum, void *datap)
 		BUG_ON(!upper);
 
 		if (upper->attribute) {
-			printk(KERN_ERR "SELinux: type %s: "
+			pr_err("SELinux: type %s: "
 			       "bounded by attribute %s",
 			       (char *) key,
 			       sym_name(p, SYM_TYPES, upper->value - 1));
@@ -1888,7 +1889,7 @@ static int range_read(struct policydb *p, void *fp)
 
 		rc = -EINVAL;
 		if (!mls_range_isvalid(p, r)) {
-			printk(KERN_WARNING "SELinux:  rangetrans:  invalid range\n");
+			pr_warn("SELinux:  rangetrans:  invalid range\n");
 			goto out;
 		}
 
@@ -2023,7 +2024,7 @@ static int genfs_read(struct policydb *p, void *fp)
 		     genfs_p = genfs, genfs = genfs->next) {
 			rc = -EINVAL;
 			if (strcmp(newgenfs->fstype, genfs->fstype) == 0) {
-				printk(KERN_ERR "SELinux:  dup genfs fstype %s\n",
+				pr_err("SELinux:  dup genfs fstype %s\n",
 				       newgenfs->fstype);
 				goto out;
 			}
@@ -2073,7 +2074,7 @@ static int genfs_read(struct policydb *p, void *fp)
 				if (!strcmp(newc->u.name, c->u.name) &&
 				    (!c->v.sclass || !newc->v.sclass ||
 				     newc->v.sclass == c->v.sclass)) {
-					printk(KERN_ERR "SELinux:  dup genfs entry (%s,%s)\n",
+					pr_err("SELinux:  dup genfs entry (%s,%s)\n",
 					       genfs->fstype, c->u.name);
 					goto out;
 				}
@@ -2295,7 +2296,7 @@ int policydb_read(struct policydb *p, void *fp)
 
 	rc = -EINVAL;
 	if (le32_to_cpu(buf[0]) != POLICYDB_MAGIC) {
-		printk(KERN_ERR "SELinux:  policydb magic number 0x%x does "
+		pr_err("SELinux:  policydb magic number 0x%x does "
 		       "not match expected magic number 0x%x\n",
 		       le32_to_cpu(buf[0]), POLICYDB_MAGIC);
 		goto bad;
@@ -2304,7 +2305,7 @@ int policydb_read(struct policydb *p, void *fp)
 	rc = -EINVAL;
 	len = le32_to_cpu(buf[1]);
 	if (len != strlen(POLICYDB_STRING)) {
-		printk(KERN_ERR "SELinux:  policydb string length %d does not "
+		pr_err("SELinux:  policydb string length %d does not "
 		       "match expected length %zu\n",
 		       len, strlen(POLICYDB_STRING));
 		goto bad;
@@ -2313,14 +2314,14 @@ int policydb_read(struct policydb *p, void *fp)
 	rc = -ENOMEM;
 	policydb_str = kmalloc(len + 1, GFP_KERNEL);
 	if (!policydb_str) {
-		printk(KERN_ERR "SELinux:  unable to allocate memory for policydb "
+		pr_err("SELinux:  unable to allocate memory for policydb "
 		       "string of length %d\n", len);
 		goto bad;
 	}
 
 	rc = next_entry(policydb_str, fp, len);
 	if (rc) {
-		printk(KERN_ERR "SELinux:  truncated policydb string identifier\n");
+		pr_err("SELinux:  truncated policydb string identifier\n");
 		kfree(policydb_str);
 		goto bad;
 	}
@@ -2328,7 +2329,7 @@ int policydb_read(struct policydb *p, void *fp)
 	rc = -EINVAL;
 	policydb_str[len] = '\0';
 	if (strcmp(policydb_str, POLICYDB_STRING)) {
-		printk(KERN_ERR "SELinux:  policydb string %s does not match "
+		pr_err("SELinux:  policydb string %s does not match "
 		       "my string %s\n", policydb_str, POLICYDB_STRING);
 		kfree(policydb_str);
 		goto bad;
@@ -2346,7 +2347,7 @@ int policydb_read(struct policydb *p, void *fp)
 	p->policyvers = le32_to_cpu(buf[0]);
 	if (p->policyvers < POLICYDB_VERSION_MIN ||
 	    p->policyvers > POLICYDB_VERSION_MAX) {
-		printk(KERN_ERR "SELinux:  policydb version %d does not match "
+		pr_err("SELinux:  policydb version %d does not match "
 		       "my version range %d-%d\n",
 		       le32_to_cpu(buf[0]), POLICYDB_VERSION_MIN, POLICYDB_VERSION_MAX);
 		goto bad;
@@ -2357,7 +2358,7 @@ int policydb_read(struct policydb *p, void *fp)
 
 		rc = -EINVAL;
 		if (p->policyvers < POLICYDB_VERSION_MLS) {
-			printk(KERN_ERR "SELinux: security policydb version %d "
+			pr_err("SELinux: security policydb version %d "
 				"(MLS) not backwards compatible\n",
 				p->policyvers);
 			goto bad;
@@ -2381,7 +2382,7 @@ int policydb_read(struct policydb *p, void *fp)
 	rc = -EINVAL;
 	info = policydb_lookup_compat(p->policyvers);
 	if (!info) {
-		printk(KERN_ERR "SELinux:  unable to find policy compat info "
+		pr_err("SELinux:  unable to find policy compat info "
 		       "for version %d\n", p->policyvers);
 		goto bad;
 	}
@@ -2389,7 +2390,7 @@ int policydb_read(struct policydb *p, void *fp)
 	rc = -EINVAL;
 	if (le32_to_cpu(buf[2]) != info->sym_num ||
 		le32_to_cpu(buf[3]) != info->ocon_num) {
-		printk(KERN_ERR "SELinux:  policydb table sizes (%d,%d) do "
+		pr_err("SELinux:  policydb table sizes (%d,%d) do "
 		       "not match mine (%d,%d)\n", le32_to_cpu(buf[2]),
 			le32_to_cpu(buf[3]),
 		       info->sym_num, info->ocon_num);
@@ -3417,7 +3418,7 @@ int policydb_write(struct policydb *p, void *fp)
 	 * careful if you ever try to remove this restriction
 	 */
 	if (p->policyvers < POLICYDB_VERSION_AVTAB) {
-		printk(KERN_ERR "SELinux: refusing to write policy version %d."
+		pr_err("SELinux: refusing to write policy version %d."
 		       "  Because it is less than version %d\n", p->policyvers,
 		       POLICYDB_VERSION_AVTAB);
 		return -EINVAL;
@@ -3446,7 +3447,7 @@ int policydb_write(struct policydb *p, void *fp)
 	/* Write the version, config, and table sizes. */
 	info = policydb_lookup_compat(p->policyvers);
 	if (!info) {
-		printk(KERN_ERR "SELinux: compatibility lookup failed for policy "
+		pr_err("SELinux: compatibility lookup failed for policy "
 		    "version %d", p->policyvers);
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From c103a91e8916540c774805af11ed4bc3ba75f874 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:03 +0200
Subject: selinux: Cleanup printk logging in hooks

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/hooks.c | 68 +++++++++++++++++++++++-------------------------
 1 file changed, 33 insertions(+), 35 deletions(-)

diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2b5ee5fbd652..f78318af8254 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -530,7 +530,7 @@ static int sb_finish_set_opts(struct super_block *sb)
 		   the first boot of the SELinux kernel before we have
 		   assigned xattr values to the filesystem. */
 		if (!(root_inode->i_opflags & IOP_XATTR)) {
-			printk(KERN_WARNING "SELinux: (dev %s, type %s) has no "
+			pr_warn("SELinux: (dev %s, type %s) has no "
 			       "xattr support\n", sb->s_id, sb->s_type->name);
 			rc = -EOPNOTSUPP;
 			goto out;
@@ -539,11 +539,11 @@ static int sb_finish_set_opts(struct super_block *sb)
 		rc = __vfs_getxattr(root, root_inode, XATTR_NAME_SELINUX, NULL, 0);
 		if (rc < 0 && rc != -ENODATA) {
 			if (rc == -EOPNOTSUPP)
-				printk(KERN_WARNING "SELinux: (dev %s, type "
+				pr_warn("SELinux: (dev %s, type "
 				       "%s) has no security xattr handler\n",
 				       sb->s_id, sb->s_type->name);
 			else
-				printk(KERN_WARNING "SELinux: (dev %s, type "
+				pr_warn("SELinux: (dev %s, type "
 				       "%s) getxattr errno %d\n", sb->s_id,
 				       sb->s_type->name, -rc);
 			goto out;
@@ -742,7 +742,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 			goto out;
 		}
 		rc = -EINVAL;
-		printk(KERN_WARNING "SELinux: Unable to set superblock options "
+		pr_warn("SELinux: Unable to set superblock options "
 			"before the security server is initialized\n");
 		goto out;
 	}
@@ -784,7 +784,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 						 mount_options[i], &sid,
 						 GFP_KERNEL);
 		if (rc) {
-			printk(KERN_WARNING "SELinux: security_context_str_to_sid"
+			pr_warn("SELinux: security_context_str_to_sid"
 			       "(%s) failed for (dev %s, type %s) errno=%d\n",
 			       mount_options[i], sb->s_id, name, rc);
 			goto out;
@@ -860,8 +860,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 		 */
 		rc = security_fs_use(&selinux_state, sb);
 		if (rc) {
-			printk(KERN_WARNING
-				"%s: security_fs_use(%s) returned %d\n",
+			pr_warn("%s: security_fs_use(%s) returned %d\n",
 					__func__, sb->s_type->name, rc);
 			goto out;
 		}
@@ -947,7 +946,7 @@ static int selinux_set_mnt_opts(struct super_block *sb,
 		if (sbsec->behavior != SECURITY_FS_USE_XATTR &&
 			sbsec->behavior != SECURITY_FS_USE_NATIVE) {
 			rc = -EINVAL;
-			printk(KERN_WARNING "SELinux: defcontext option is "
+			pr_warn("SELinux: defcontext option is "
 			       "invalid for this filesystem type\n");
 			goto out;
 		}
@@ -969,7 +968,7 @@ out:
 	return rc;
 out_double_mount:
 	rc = -EINVAL;
-	printk(KERN_WARNING "SELinux: mount invalid.  Same superblock, different "
+	pr_warn("SELinux: mount invalid.  Same superblock, different "
 	       "security settings for (dev %s, type %s)\n", sb->s_id, name);
 	goto out;
 }
@@ -998,7 +997,7 @@ static int selinux_cmp_sb_context(const struct super_block *oldsb,
 	}
 	return 0;
 mismatch:
-	printk(KERN_WARNING "SELinux: mount invalid.  Same superblock, "
+	pr_warn("SELinux: mount invalid.  Same superblock, "
 			    "different security settings for (dev %s, "
 			    "type %s)\n", newsb->s_id, newsb->s_type->name);
 	return -EBUSY;
@@ -1106,7 +1105,7 @@ static int selinux_parse_opts_str(char *options,
 		case Opt_context:
 			if (context || defcontext) {
 				rc = -EINVAL;
-				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
+				pr_warn(SEL_MOUNT_FAIL_MSG);
 				goto out_err;
 			}
 			context = match_strdup(&args[0]);
@@ -1119,7 +1118,7 @@ static int selinux_parse_opts_str(char *options,
 		case Opt_fscontext:
 			if (fscontext) {
 				rc = -EINVAL;
-				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
+				pr_warn(SEL_MOUNT_FAIL_MSG);
 				goto out_err;
 			}
 			fscontext = match_strdup(&args[0]);
@@ -1132,7 +1131,7 @@ static int selinux_parse_opts_str(char *options,
 		case Opt_rootcontext:
 			if (rootcontext) {
 				rc = -EINVAL;
-				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
+				pr_warn(SEL_MOUNT_FAIL_MSG);
 				goto out_err;
 			}
 			rootcontext = match_strdup(&args[0]);
@@ -1145,7 +1144,7 @@ static int selinux_parse_opts_str(char *options,
 		case Opt_defcontext:
 			if (context || defcontext) {
 				rc = -EINVAL;
-				printk(KERN_WARNING SEL_MOUNT_FAIL_MSG);
+				pr_warn(SEL_MOUNT_FAIL_MSG);
 				goto out_err;
 			}
 			defcontext = match_strdup(&args[0]);
@@ -1158,7 +1157,7 @@ static int selinux_parse_opts_str(char *options,
 			break;
 		default:
 			rc = -EINVAL;
-			printk(KERN_WARNING "SELinux:  unknown mount option\n");
+			pr_warn("SELinux:  unknown mount option\n");
 			goto out_err;
 
 		}
@@ -1623,7 +1622,7 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 		dput(dentry);
 		if (rc < 0) {
 			if (rc != -ENODATA) {
-				printk(KERN_WARNING "SELinux: %s:  getxattr returned "
+				pr_warn("SELinux: %s:  getxattr returned "
 				       "%d for dev=%s ino=%ld\n", __func__,
 				       -rc, inode->i_sb->s_id, inode->i_ino);
 				kfree(context);
@@ -1643,11 +1642,11 @@ static int inode_doinit_with_dentry(struct inode *inode, struct dentry *opt_dent
 
 				if (rc == -EINVAL) {
 					if (printk_ratelimit())
-						printk(KERN_NOTICE "SELinux: inode=%lu on dev=%s was found to have an invalid "
+						pr_notice("SELinux: inode=%lu on dev=%s was found to have an invalid "
 							"context=%s.  This indicates you may need to relabel the inode or the "
 							"filesystem in question.\n", ino, dev, context);
 				} else {
-					printk(KERN_WARNING "SELinux: %s:  context_to_sid(%s) "
+					pr_warn("SELinux: %s:  context_to_sid(%s) "
 					       "returned %d for dev=%s ino=%ld\n",
 					       __func__, context, -rc, dev, ino);
 				}
@@ -1785,8 +1784,7 @@ static int cred_has_capability(const struct cred *cred,
 		sclass = initns ? SECCLASS_CAPABILITY2 : SECCLASS_CAP2_USERNS;
 		break;
 	default:
-		printk(KERN_ERR
-		       "SELinux:  out of range capability %d\n", cap);
+		pr_err("SELinux:  out of range capability %d\n", cap);
 		BUG();
 		return -EINVAL;
 	}
@@ -2029,7 +2027,7 @@ static int may_link(struct inode *dir,
 		av = DIR__RMDIR;
 		break;
 	default:
-		printk(KERN_WARNING "SELinux: %s:  unrecognized kind %d\n",
+		pr_warn("SELinux: %s:  unrecognized kind %d\n",
 			__func__, kind);
 		return 0;
 	}
@@ -2875,7 +2873,7 @@ static int selinux_sb_remount(struct super_block *sb, void *data)
 						 mount_options[i], &sid,
 						 GFP_KERNEL);
 		if (rc) {
-			printk(KERN_WARNING "SELinux: security_context_str_to_sid"
+			pr_warn("SELinux: security_context_str_to_sid"
 			       "(%s) failed for (dev %s, type %s) errno=%d\n",
 			       mount_options[i], sb->s_id, sb->s_type->name, rc);
 			goto out_free_opts;
@@ -2914,7 +2912,7 @@ out_free_secdata:
 	free_secdata(secdata);
 	return rc;
 out_bad_option:
-	printk(KERN_WARNING "SELinux: unable to change security options "
+	pr_warn("SELinux: unable to change security options "
 	       "during remount (dev %s, type=%s)\n", sb->s_id,
 	       sb->s_type->name);
 	goto out_free_opts;
@@ -3357,7 +3355,7 @@ static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name,
 	rc = security_context_to_sid_force(&selinux_state, value, size,
 					   &newsid);
 	if (rc) {
-		printk(KERN_ERR "SELinux:  unable to map context to SID"
+		pr_err("SELinux:  unable to map context to SID"
 		       "for (%s, %lu), rc=%d\n",
 		       inode->i_sb->s_id, inode->i_ino, -rc);
 		return;
@@ -4420,7 +4418,7 @@ static int selinux_parse_skb(struct sk_buff *skb, struct common_audit_data *ad,
 	}
 
 parse_error:
-	printk(KERN_WARNING
+	pr_warn(
 	       "SELinux: failure in selinux_parse_skb(),"
 	       " unable to parse packet\n");
 	return ret;
@@ -4463,7 +4461,7 @@ static int selinux_skb_peerlbl_sid(struct sk_buff *skb, u16 family, u32 *sid)
 	err = security_net_peersid_resolve(&selinux_state, nlbl_sid,
 					   nlbl_type, xfrm_sid, sid);
 	if (unlikely(err)) {
-		printk(KERN_WARNING
+		pr_warn(
 		       "SELinux: failure in selinux_skb_peerlbl_sid(),"
 		       " unable to determine packet's peer label\n");
 		return -EACCES;
@@ -7126,11 +7124,11 @@ static __init int selinux_init(void)
 	}
 
 	if (!selinux_enabled) {
-		printk(KERN_INFO "SELinux:  Disabled at boot.\n");
+		pr_info("SELinux:  Disabled at boot.\n");
 		return 0;
 	}
 
-	printk(KERN_INFO "SELinux:  Initializing.\n");
+	pr_info("SELinux:  Initializing.\n");
 
 	memset(&selinux_state, 0, sizeof(selinux_state));
 	enforcing_set(&selinux_state, selinux_enforcing_boot);
@@ -7166,9 +7164,9 @@ static __init int selinux_init(void)
 		panic("SELinux: Unable to register AVC LSM notifier callback\n");
 
 	if (selinux_enforcing_boot)
-		printk(KERN_DEBUG "SELinux:  Starting in enforcing mode\n");
+		pr_debug("SELinux:  Starting in enforcing mode\n");
 	else
-		printk(KERN_DEBUG "SELinux:  Starting in permissive mode\n");
+		pr_debug("SELinux:  Starting in permissive mode\n");
 
 	return 0;
 }
@@ -7180,10 +7178,10 @@ static void delayed_superblock_init(struct super_block *sb, void *unused)
 
 void selinux_complete_init(void)
 {
-	printk(KERN_DEBUG "SELinux:  Completing initialization.\n");
+	pr_debug("SELinux:  Completing initialization.\n");
 
 	/* Set up any superblocks initialized prior to the policy load. */
-	printk(KERN_DEBUG "SELinux:  Setting up existing superblocks.\n");
+	pr_debug("SELinux:  Setting up existing superblocks.\n");
 	iterate_supers(delayed_superblock_init, NULL);
 }
 
@@ -7258,7 +7256,7 @@ static int __init selinux_nf_ip_init(void)
 	if (!selinux_enabled)
 		return 0;
 
-	printk(KERN_DEBUG "SELinux:  Registering netfilter hooks\n");
+	pr_debug("SELinux:  Registering netfilter hooks\n");
 
 	err = register_pernet_subsys(&selinux_net_ops);
 	if (err)
@@ -7271,7 +7269,7 @@ __initcall(selinux_nf_ip_init);
 #ifdef CONFIG_SECURITY_SELINUX_DISABLE
 static void selinux_nf_ip_exit(void)
 {
-	printk(KERN_DEBUG "SELinux:  Unregistering netfilter hooks\n");
+	pr_debug("SELinux:  Unregistering netfilter hooks\n");
 
 	unregister_pernet_subsys(&selinux_net_ops);
 }
@@ -7300,7 +7298,7 @@ int selinux_disable(struct selinux_state *state)
 
 	state->disabled = 1;
 
-	printk(KERN_INFO "SELinux:  Disabled at runtime.\n");
+	pr_info("SELinux:  Disabled at runtime.\n");
 
 	selinux_enabled = 0;
 
-- 
cgit v1.2.3


From c87a7e75a3e2180a15df1c76343ee1a2d477b224 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:04 +0200
Subject: selinux: Cleanup printk logging in avtab

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/avtab.c | 51 +++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 25 deletions(-)

diff --git a/security/selinux/ss/avtab.c b/security/selinux/ss/avtab.c
index a2c9148b0662..c0417cf17fee 100644
--- a/security/selinux/ss/avtab.c
+++ b/security/selinux/ss/avtab.c
@@ -338,7 +338,7 @@ int avtab_alloc(struct avtab *h, u32 nrules)
 	h->nel = 0;
 	h->nslot = nslot;
 	h->mask = mask;
-	printk(KERN_DEBUG "SELinux: %d avtab hash slots, %d rules.\n",
+	pr_debug("SELinux: %d avtab hash slots, %d rules.\n",
 	       h->nslot, nrules);
 	return 0;
 }
@@ -368,7 +368,7 @@ void avtab_hash_eval(struct avtab *h, char *tag)
 		}
 	}
 
-	printk(KERN_DEBUG "SELinux: %s:  %d entries and %d/%d buckets used, "
+	pr_debug("SELinux: %s:  %d entries and %d/%d buckets used, "
 	       "longest chain length %d sum of chain length^2 %llu\n",
 	       tag, h->nel, slots_used, h->nslot, max_chain_len,
 	       chain2_len_sum);
@@ -407,18 +407,18 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 	if (vers < POLICYDB_VERSION_AVTAB) {
 		rc = next_entry(buf32, fp, sizeof(u32));
 		if (rc) {
-			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			pr_err("SELinux: avtab: truncated entry\n");
 			return rc;
 		}
 		items2 = le32_to_cpu(buf32[0]);
 		if (items2 > ARRAY_SIZE(buf32)) {
-			printk(KERN_ERR "SELinux: avtab: entry overflow\n");
+			pr_err("SELinux: avtab: entry overflow\n");
 			return -EINVAL;
 
 		}
 		rc = next_entry(buf32, fp, sizeof(u32)*items2);
 		if (rc) {
-			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			pr_err("SELinux: avtab: truncated entry\n");
 			return rc;
 		}
 		items = 0;
@@ -426,19 +426,19 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		val = le32_to_cpu(buf32[items++]);
 		key.source_type = (u16)val;
 		if (key.source_type != val) {
-			printk(KERN_ERR "SELinux: avtab: truncated source type\n");
+			pr_err("SELinux: avtab: truncated source type\n");
 			return -EINVAL;
 		}
 		val = le32_to_cpu(buf32[items++]);
 		key.target_type = (u16)val;
 		if (key.target_type != val) {
-			printk(KERN_ERR "SELinux: avtab: truncated target type\n");
+			pr_err("SELinux: avtab: truncated target type\n");
 			return -EINVAL;
 		}
 		val = le32_to_cpu(buf32[items++]);
 		key.target_class = (u16)val;
 		if (key.target_class != val) {
-			printk(KERN_ERR "SELinux: avtab: truncated target class\n");
+			pr_err("SELinux: avtab: truncated target class\n");
 			return -EINVAL;
 		}
 
@@ -446,16 +446,16 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0;
 
 		if (!(val & (AVTAB_AV | AVTAB_TYPE))) {
-			printk(KERN_ERR "SELinux: avtab: null entry\n");
+			pr_err("SELinux: avtab: null entry\n");
 			return -EINVAL;
 		}
 		if ((val & AVTAB_AV) &&
 		    (val & AVTAB_TYPE)) {
-			printk(KERN_ERR "SELinux: avtab: entry has both access vectors and types\n");
+			pr_err("SELinux: avtab: entry has both access vectors and types\n");
 			return -EINVAL;
 		}
 		if (val & AVTAB_XPERMS) {
-			printk(KERN_ERR "SELinux: avtab: entry has extended permissions\n");
+			pr_err("SELinux: avtab: entry has extended permissions\n");
 			return -EINVAL;
 		}
 
@@ -470,7 +470,8 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		}
 
 		if (items != items2) {
-			printk(KERN_ERR "SELinux: avtab: entry only had %d items, expected %d\n", items2, items);
+			pr_err("SELinux: avtab: entry only had %d items, expected %d\n",
+			       items2, items);
 			return -EINVAL;
 		}
 		return 0;
@@ -478,7 +479,7 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 
 	rc = next_entry(buf16, fp, sizeof(u16)*4);
 	if (rc) {
-		printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+		pr_err("SELinux: avtab: truncated entry\n");
 		return rc;
 	}
 
@@ -491,7 +492,7 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 	if (!policydb_type_isvalid(pol, key.source_type) ||
 	    !policydb_type_isvalid(pol, key.target_type) ||
 	    !policydb_class_isvalid(pol, key.target_class)) {
-		printk(KERN_ERR "SELinux: avtab: invalid type or class\n");
+		pr_err("SELinux: avtab: invalid type or class\n");
 		return -EINVAL;
 	}
 
@@ -501,13 +502,13 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 			set++;
 	}
 	if (!set || set > 1) {
-		printk(KERN_ERR "SELinux:  avtab:  more than one specifier\n");
+		pr_err("SELinux:  avtab:  more than one specifier\n");
 		return -EINVAL;
 	}
 
 	if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) &&
 			(key.specified & AVTAB_XPERMS)) {
-		printk(KERN_ERR "SELinux:  avtab:  policy version %u does not "
+		pr_err("SELinux:  avtab:  policy version %u does not "
 				"support extended permissions rules and one "
 				"was specified\n", vers);
 		return -EINVAL;
@@ -515,17 +516,17 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 		memset(&xperms, 0, sizeof(struct avtab_extended_perms));
 		rc = next_entry(&xperms.specified, fp, sizeof(u8));
 		if (rc) {
-			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			pr_err("SELinux: avtab: truncated entry\n");
 			return rc;
 		}
 		rc = next_entry(&xperms.driver, fp, sizeof(u8));
 		if (rc) {
-			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			pr_err("SELinux: avtab: truncated entry\n");
 			return rc;
 		}
 		rc = next_entry(buf32, fp, sizeof(u32)*ARRAY_SIZE(xperms.perms.p));
 		if (rc) {
-			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			pr_err("SELinux: avtab: truncated entry\n");
 			return rc;
 		}
 		for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++)
@@ -534,14 +535,14 @@ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol,
 	} else {
 		rc = next_entry(buf32, fp, sizeof(u32));
 		if (rc) {
-			printk(KERN_ERR "SELinux: avtab: truncated entry\n");
+			pr_err("SELinux: avtab: truncated entry\n");
 			return rc;
 		}
 		datum.u.data = le32_to_cpu(*buf32);
 	}
 	if ((key.specified & AVTAB_TYPE) &&
 	    !policydb_type_isvalid(pol, datum.u.data)) {
-		printk(KERN_ERR "SELinux: avtab: invalid type\n");
+		pr_err("SELinux: avtab: invalid type\n");
 		return -EINVAL;
 	}
 	return insertf(a, &key, &datum, p);
@@ -562,12 +563,12 @@ int avtab_read(struct avtab *a, void *fp, struct policydb *pol)
 
 	rc = next_entry(buf, fp, sizeof(u32));
 	if (rc < 0) {
-		printk(KERN_ERR "SELinux: avtab: truncated table\n");
+		pr_err("SELinux: avtab: truncated table\n");
 		goto bad;
 	}
 	nel = le32_to_cpu(buf[0]);
 	if (!nel) {
-		printk(KERN_ERR "SELinux: avtab: table is empty\n");
+		pr_err("SELinux: avtab: table is empty\n");
 		rc = -EINVAL;
 		goto bad;
 	}
@@ -580,9 +581,9 @@ int avtab_read(struct avtab *a, void *fp, struct policydb *pol)
 		rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL);
 		if (rc) {
 			if (rc == -ENOMEM)
-				printk(KERN_ERR "SELinux: avtab: out of memory\n");
+				pr_err("SELinux: avtab: out of memory\n");
 			else if (rc == -EEXIST)
-				printk(KERN_ERR "SELinux: avtab: duplicate entry\n");
+				pr_err("SELinux: avtab: duplicate entry\n");
 
 			goto bad;
 		}
-- 
cgit v1.2.3


From 04cdd5af51c610ddc7ff4881790a830a6a97d3fd Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 19 Jun 2018 15:40:50 +0200
Subject: clk: qcom: drop CLK_SET_RATE_GATE from sdc clocks

the mmci driver (drivers/mmc/host/mmci.c) does the following sequence:
* clk_prepare_enable()
* clk_set_rate()

on SDCx_clk which is a children of SDCx_src. SDCx_src has
CLK_SET_RATE_GATE so this sequence should not be allowed but this was not
enforced. IOW, the flag is ignored. Dropping the flag won't change
anything to the current behaviour of the platform.

CLK_SET_RATE_GATE is being fixed and enforced now. If the flag was kept,
the mmci driver would receive -EBUSY when calling clk_set_rate()

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Michael Turquette <mturquette@baylibre.com>
Link: lkml.kernel.org/r/20180619134051.16726-2-jbrunet@baylibre.com
---
 drivers/clk/qcom/gcc-ipq806x.c | 3 ---
 drivers/clk/qcom/gcc-mdm9615.c | 2 --
 drivers/clk/qcom/gcc-msm8660.c | 5 -----
 drivers/clk/qcom/gcc-msm8960.c | 5 -----
 4 files changed, 15 deletions(-)

diff --git a/drivers/clk/qcom/gcc-ipq806x.c b/drivers/clk/qcom/gcc-ipq806x.c
index 28eb200d0f1e..5f61225657ab 100644
--- a/drivers/clk/qcom/gcc-ipq806x.c
+++ b/drivers/clk/qcom/gcc-ipq806x.c
@@ -1220,7 +1220,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1269,7 +1268,6 @@ static struct clk_rcg sdc3_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1353,7 +1351,6 @@ static struct clk_rcg tsif_ref_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
diff --git a/drivers/clk/qcom/gcc-mdm9615.c b/drivers/clk/qcom/gcc-mdm9615.c
index b99dd406e907..849046fbed6d 100644
--- a/drivers/clk/qcom/gcc-mdm9615.c
+++ b/drivers/clk/qcom/gcc-mdm9615.c
@@ -947,7 +947,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_cxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -996,7 +995,6 @@ static struct clk_rcg sdc2_src = {
 			.parent_names = gcc_cxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
diff --git a/drivers/clk/qcom/gcc-msm8660.c b/drivers/clk/qcom/gcc-msm8660.c
index c347a0d44bc8..7e930e25c79f 100644
--- a/drivers/clk/qcom/gcc-msm8660.c
+++ b/drivers/clk/qcom/gcc-msm8660.c
@@ -1558,7 +1558,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1607,7 +1606,6 @@ static struct clk_rcg sdc2_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1656,7 +1654,6 @@ static struct clk_rcg sdc3_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1705,7 +1702,6 @@ static struct clk_rcg sdc4_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1754,7 +1750,6 @@ static struct clk_rcg sdc5_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
diff --git a/drivers/clk/qcom/gcc-msm8960.c b/drivers/clk/qcom/gcc-msm8960.c
index eb551c75fba6..fd495e0471bb 100644
--- a/drivers/clk/qcom/gcc-msm8960.c
+++ b/drivers/clk/qcom/gcc-msm8960.c
@@ -1628,7 +1628,6 @@ static struct clk_rcg sdc1_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1677,7 +1676,6 @@ static struct clk_rcg sdc2_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1726,7 +1724,6 @@ static struct clk_rcg sdc3_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1775,7 +1772,6 @@ static struct clk_rcg sdc4_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
@@ -1824,7 +1820,6 @@ static struct clk_rcg sdc5_src = {
 			.parent_names = gcc_pxo_pll8,
 			.num_parents = 2,
 			.ops = &clk_rcg_ops,
-			.flags = CLK_SET_RATE_GATE,
 		},
 	}
 };
-- 
cgit v1.2.3


From 9461f7b33d11cbbf5ce79c3c03d0da9d42dfce92 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 19 Jun 2018 15:40:51 +0200
Subject: clk: fix CLK_SET_RATE_GATE with clock rate protection

CLK_SET_RATE_GATE should prevent any operation which may result in a rate
change or glitch while the clock is prepared/enabled.

IOW, the following sequence is not allowed anymore with CLK_SET_RATE_GATE:
* clk_get()
* clk_prepare_enable()
* clk_get_rate()
* clk_set_rate()

At the moment this is enforced on the leaf clock of the operation, not
along the tree. This problematic because, if a PLL has the CLK_RATE_GATE,
it won't be enforced if the clk_set_rate() is called on its child clocks.

Using clock rate protection, we can now enforce CLK_SET_RATE_GATE along the
clock tree

Acked-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: Quentin Schulz <quentin.schulz@free-electrons.com>
Tested-by: Maxime Ripard <maxime.ripard@free-electrons.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Michael Turquette <mturquette@baylibre.com>
Link: lkml.kernel.org/r/20180619134051.16726-3-jbrunet@baylibre.com
---
 drivers/clk/clk.c | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 9760b526ca31..97c09243fb21 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -691,6 +691,9 @@ static void clk_core_unprepare(struct clk_core *core)
 	    "Unpreparing critical %s\n", core->name))
 		return;
 
+	if (core->flags & CLK_SET_RATE_GATE)
+		clk_core_rate_unprotect(core);
+
 	if (--core->prepare_count > 0)
 		return;
 
@@ -765,6 +768,16 @@ static int clk_core_prepare(struct clk_core *core)
 
 	core->prepare_count++;
 
+	/*
+	 * CLK_SET_RATE_GATE is a special case of clock protection
+	 * Instead of a consumer claiming exclusive rate control, it is
+	 * actually the provider which prevents any consumer from making any
+	 * operation which could result in a rate change or rate glitch while
+	 * the clock is prepared.
+	 */
+	if (core->flags & CLK_SET_RATE_GATE)
+		clk_core_rate_protect(core);
+
 	return 0;
 unprepare:
 	clk_core_unprepare(core->parent);
@@ -1888,9 +1901,6 @@ static int clk_core_set_rate_nolock(struct clk_core *core,
 	if (clk_core_rate_is_protected(core))
 		return -EBUSY;
 
-	if ((core->flags & CLK_SET_RATE_GATE) && core->prepare_count)
-		return -EBUSY;
-
 	/* calculate new rates and get the topmost changed clock */
 	top = clk_calc_new_rates(core, req_rate);
 	if (!top)
-- 
cgit v1.2.3


From 9fba738a53dda20e748d6ee240b6c017c8146b4b Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 19 Jun 2018 16:41:41 +0200
Subject: clk: add duty cycle support

Add the possibility to apply and query the clock signal duty cycle ratio.

This is useful when the duty cycle of the clock signal depends on some
other parameters controlled by the clock framework.

For example, the duty cycle of a divider may depends on the raw divider
setting (ratio = N / div) , which is controlled by the CCF. In such case,
going through the pwm framework to control the duty cycle ratio of this
clock would be a burden.

A clock provider is not required to implement the operation to set and get
the duty cycle. If it does not implement .get_duty_cycle(), the ratio is
assumed to be 50%.

This change also adds a new flag, CLK_DUTY_CYCLE_PARENT. This flag should
be used to indicate that a clock, such as gates and muxes, may inherit
the duty cycle ratio of its parent clock. If a clock does not provide a
get_duty_cycle() callback and has CLK_DUTY_CYCLE_PARENT, then the call
will be directly forwarded to its parent clock, if any. For
set_duty_cycle(), the clock should also have CLK_SET_RATE_PARENT for the
call to be forwarded

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Michael Turquette <mturquette@baylibre.com>
Link: lkml.kernel.org/r/20180619144141.8506-1-jbrunet@baylibre.com
---
 drivers/clk/clk.c            | 199 +++++++++++++++++++++++++++++++++++++++++--
 include/linux/clk-provider.h |  26 ++++++
 include/linux/clk.h          |  33 +++++++
 include/trace/events/clk.h   |  36 ++++++++
 4 files changed, 289 insertions(+), 5 deletions(-)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 9760b526ca31..b0a2719d86f3 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -68,6 +68,7 @@ struct clk_core {
 	unsigned long		max_rate;
 	unsigned long		accuracy;
 	int			phase;
+	struct clk_duty		duty;
 	struct hlist_head	children;
 	struct hlist_node	child_node;
 	struct hlist_head	clks;
@@ -2402,6 +2403,172 @@ int clk_get_phase(struct clk *clk)
 }
 EXPORT_SYMBOL_GPL(clk_get_phase);
 
+static void clk_core_reset_duty_cycle_nolock(struct clk_core *core)
+{
+	/* Assume a default value of 50% */
+	core->duty.num = 1;
+	core->duty.den = 2;
+}
+
+static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core);
+
+static int clk_core_update_duty_cycle_nolock(struct clk_core *core)
+{
+	struct clk_duty *duty = &core->duty;
+	int ret = 0;
+
+	if (!core->ops->get_duty_cycle)
+		return clk_core_update_duty_cycle_parent_nolock(core);
+
+	ret = core->ops->get_duty_cycle(core->hw, duty);
+	if (ret)
+		goto reset;
+
+	/* Don't trust the clock provider too much */
+	if (duty->den == 0 || duty->num > duty->den) {
+		ret = -EINVAL;
+		goto reset;
+	}
+
+	return 0;
+
+reset:
+	clk_core_reset_duty_cycle_nolock(core);
+	return ret;
+}
+
+static int clk_core_update_duty_cycle_parent_nolock(struct clk_core *core)
+{
+	int ret = 0;
+
+	if (core->parent &&
+	    core->flags & CLK_DUTY_CYCLE_PARENT) {
+		ret = clk_core_update_duty_cycle_nolock(core->parent);
+		memcpy(&core->duty, &core->parent->duty, sizeof(core->duty));
+	} else {
+		clk_core_reset_duty_cycle_nolock(core);
+	}
+
+	return ret;
+}
+
+static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core,
+						 struct clk_duty *duty);
+
+static int clk_core_set_duty_cycle_nolock(struct clk_core *core,
+					  struct clk_duty *duty)
+{
+	int ret;
+
+	lockdep_assert_held(&prepare_lock);
+
+	if (clk_core_rate_is_protected(core))
+		return -EBUSY;
+
+	trace_clk_set_duty_cycle(core, duty);
+
+	if (!core->ops->set_duty_cycle)
+		return clk_core_set_duty_cycle_parent_nolock(core, duty);
+
+	ret = core->ops->set_duty_cycle(core->hw, duty);
+	if (!ret)
+		memcpy(&core->duty, duty, sizeof(*duty));
+
+	trace_clk_set_duty_cycle_complete(core, duty);
+
+	return ret;
+}
+
+static int clk_core_set_duty_cycle_parent_nolock(struct clk_core *core,
+						 struct clk_duty *duty)
+{
+	int ret = 0;
+
+	if (core->parent &&
+	    core->flags & (CLK_DUTY_CYCLE_PARENT | CLK_SET_RATE_PARENT)) {
+		ret = clk_core_set_duty_cycle_nolock(core->parent, duty);
+		memcpy(&core->duty, &core->parent->duty, sizeof(core->duty));
+	}
+
+	return ret;
+}
+
+/**
+ * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @num: numerator of the duty cycle ratio to be applied
+ * @den: denominator of the duty cycle ratio to be applied
+ *
+ * Apply the duty cycle ratio if the ratio is valid and the clock can
+ * perform this operation
+ *
+ * Returns (0) on success, a negative errno otherwise.
+ */
+int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den)
+{
+	int ret;
+	struct clk_duty duty;
+
+	if (!clk)
+		return 0;
+
+	/* sanity check the ratio */
+	if (den == 0 || num > den)
+		return -EINVAL;
+
+	duty.num = num;
+	duty.den = den;
+
+	clk_prepare_lock();
+
+	if (clk->exclusive_count)
+		clk_core_rate_unprotect(clk->core);
+
+	ret = clk_core_set_duty_cycle_nolock(clk->core, &duty);
+
+	if (clk->exclusive_count)
+		clk_core_rate_protect(clk->core);
+
+	clk_prepare_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(clk_set_duty_cycle);
+
+static int clk_core_get_scaled_duty_cycle(struct clk_core *core,
+					  unsigned int scale)
+{
+	struct clk_duty *duty = &core->duty;
+	int ret;
+
+	clk_prepare_lock();
+
+	ret = clk_core_update_duty_cycle_nolock(core);
+	if (!ret)
+		ret = mult_frac(scale, duty->num, duty->den);
+
+	clk_prepare_unlock();
+
+	return ret;
+}
+
+/**
+ * clk_get_scaled_duty_cycle - return the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @scale: scaling factor to be applied to represent the ratio as an integer
+ *
+ * Returns the duty cycle ratio of a clock node multiplied by the provided
+ * scaling factor, or negative errno on error.
+ */
+int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale)
+{
+	if (!clk)
+		return 0;
+
+	return clk_core_get_scaled_duty_cycle(clk->core, scale);
+}
+EXPORT_SYMBOL_GPL(clk_get_scaled_duty_cycle);
+
 /**
  * clk_is_match - check if two clk's point to the same hardware clock
  * @p: clk compared against q
@@ -2455,12 +2622,13 @@ static void clk_summary_show_one(struct seq_file *s, struct clk_core *c,
 	if (!c)
 		return;
 
-	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %-3d\n",
+	seq_printf(s, "%*s%-*s %7d %8d %8d %11lu %10lu %5d %6d\n",
 		   level * 3 + 1, "",
 		   30 - level * 3, c->name,
 		   c->enable_count, c->prepare_count, c->protect_count,
 		   clk_core_get_rate(c), clk_core_get_accuracy(c),
-		   clk_core_get_phase(c));
+		   clk_core_get_phase(c),
+		   clk_core_get_scaled_duty_cycle(c, 100000));
 }
 
 static void clk_summary_show_subtree(struct seq_file *s, struct clk_core *c,
@@ -2482,9 +2650,9 @@ static int clk_summary_show(struct seq_file *s, void *data)
 	struct clk_core *c;
 	struct hlist_head **lists = (struct hlist_head **)s->private;
 
-	seq_puts(s, "                                 enable  prepare  protect                               \n");
-	seq_puts(s, "   clock                          count    count    count        rate   accuracy   phase\n");
-	seq_puts(s, "----------------------------------------------------------------------------------------\n");
+	seq_puts(s, "                                 enable  prepare  protect                                duty\n");
+	seq_puts(s, "   clock                          count    count    count        rate   accuracy phase  cycle\n");
+	seq_puts(s, "---------------------------------------------------------------------------------------------\n");
 
 	clk_prepare_lock();
 
@@ -2511,6 +2679,8 @@ static void clk_dump_one(struct seq_file *s, struct clk_core *c, int level)
 	seq_printf(s, "\"rate\": %lu,", clk_core_get_rate(c));
 	seq_printf(s, "\"accuracy\": %lu,", clk_core_get_accuracy(c));
 	seq_printf(s, "\"phase\": %d", clk_core_get_phase(c));
+	seq_printf(s, "\"duty_cycle\": %u",
+		   clk_core_get_scaled_duty_cycle(c, 100000));
 }
 
 static void clk_dump_subtree(struct seq_file *s, struct clk_core *c, int level)
@@ -2572,6 +2742,7 @@ static const struct {
 	ENTRY(CLK_SET_RATE_UNGATE),
 	ENTRY(CLK_IS_CRITICAL),
 	ENTRY(CLK_OPS_PARENT_ENABLE),
+	ENTRY(CLK_DUTY_CYCLE_PARENT),
 #undef ENTRY
 };
 
@@ -2610,6 +2781,17 @@ static int possible_parents_show(struct seq_file *s, void *data)
 }
 DEFINE_SHOW_ATTRIBUTE(possible_parents);
 
+static int clk_duty_cycle_show(struct seq_file *s, void *data)
+{
+	struct clk_core *core = s->private;
+	struct clk_duty *duty = &core->duty;
+
+	seq_printf(s, "%u/%u\n", duty->num, duty->den);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(clk_duty_cycle);
+
 static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 {
 	struct dentry *root;
@@ -2628,6 +2810,8 @@ static void clk_debug_create_one(struct clk_core *core, struct dentry *pdentry)
 	debugfs_create_u32("clk_enable_count", 0444, root, &core->enable_count);
 	debugfs_create_u32("clk_protect_count", 0444, root, &core->protect_count);
 	debugfs_create_u32("clk_notifier_count", 0444, root, &core->notifier_count);
+	debugfs_create_file("clk_duty_cycle", 0444, root, core,
+			    &clk_duty_cycle_fops);
 
 	if (core->num_parents > 1)
 		debugfs_create_file("clk_possible_parents", 0444, root, core,
@@ -2845,6 +3029,11 @@ static int __clk_core_init(struct clk_core *core)
 	else
 		core->phase = 0;
 
+	/*
+	 * Set clk's duty cycle.
+	 */
+	clk_core_update_duty_cycle_nolock(core);
+
 	/*
 	 * Set clk's rate.  The preferred method is to use .recalc_rate.  For
 	 * simple clocks and lazy developers the default fallback is to use the
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index b7cfa037e593..08b1aa70a38d 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -38,6 +38,8 @@
 #define CLK_IS_CRITICAL		BIT(11) /* do not gate, ever */
 /* parents need enable during gate/ungate, set rate and re-parent */
 #define CLK_OPS_PARENT_ENABLE	BIT(12)
+/* duty cycle call may be forwarded to the parent clock */
+#define CLK_DUTY_CYCLE_PARENT	BIT(13)
 
 struct clk;
 struct clk_hw;
@@ -66,6 +68,17 @@ struct clk_rate_request {
 	struct clk_hw *best_parent_hw;
 };
 
+/**
+ * struct clk_duty - Struture encoding the duty cycle ratio of a clock
+ *
+ * @num:	Numerator of the duty cycle ratio
+ * @den:	Denominator of the duty cycle ratio
+ */
+struct clk_duty {
+	unsigned int num;
+	unsigned int den;
+};
+
 /**
  * struct clk_ops -  Callback operations for hardware clocks; these are to
  * be provided by the clock implementation, and will be called by drivers
@@ -169,6 +182,15 @@ struct clk_rate_request {
  *		by the second argument. Valid values for degrees are
  *		0-359. Return 0 on success, otherwise -EERROR.
  *
+ * @get_duty_cycle: Queries the hardware to get the current duty cycle ratio
+ *              of a clock. Returned values denominator cannot be 0 and must be
+ *              superior or equal to the numerator.
+ *
+ * @set_duty_cycle: Apply the duty cycle ratio to this clock signal specified by
+ *              the numerator (2nd argurment) and denominator (3rd  argument).
+ *              Argument must be a valid ratio (denominator > 0
+ *              and >= numerator) Return 0 on success, otherwise -EERROR.
+ *
  * @init:	Perform platform-specific initialization magic.
  *		This is not not used by any of the basic clock types.
  *		Please consider other ways of solving initialization problems
@@ -218,6 +240,10 @@ struct clk_ops {
 					   unsigned long parent_accuracy);
 	int		(*get_phase)(struct clk_hw *hw);
 	int		(*set_phase)(struct clk_hw *hw, int degrees);
+	int		(*get_duty_cycle)(struct clk_hw *hw,
+					  struct clk_duty *duty);
+	int		(*set_duty_cycle)(struct clk_hw *hw,
+					  struct clk_duty *duty);
 	void		(*init)(struct clk_hw *hw);
 	void		(*debug_init)(struct clk_hw *hw, struct dentry *dentry);
 };
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 0dbd0885b2c2..4f750c481b82 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -141,6 +141,27 @@ int clk_set_phase(struct clk *clk, int degrees);
  */
 int clk_get_phase(struct clk *clk);
 
+/**
+ * clk_set_duty_cycle - adjust the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @num: numerator of the duty cycle ratio to be applied
+ * @den: denominator of the duty cycle ratio to be applied
+ *
+ * Adjust the duty cycle of a clock signal by the specified ratio. Returns 0 on
+ * success, -EERROR otherwise.
+ */
+int clk_set_duty_cycle(struct clk *clk, unsigned int num, unsigned int den);
+
+/**
+ * clk_get_duty_cycle - return the duty cycle ratio of a clock signal
+ * @clk: clock signal source
+ * @scale: scaling factor to be applied to represent the ratio as an integer
+ *
+ * Returns the duty cycle ratio multiplied by the scale provided, otherwise
+ * returns -EERROR.
+ */
+int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale);
+
 /**
  * clk_is_match - check if two clk's point to the same hardware clock
  * @p: clk compared against q
@@ -183,6 +204,18 @@ static inline long clk_get_phase(struct clk *clk)
 	return -ENOTSUPP;
 }
 
+static inline int clk_set_duty_cycle(struct clk *clk, unsigned int num,
+				     unsigned int den)
+{
+	return -ENOTSUPP;
+}
+
+static inline unsigned int clk_get_scaled_duty_cycle(struct clk *clk,
+						     unsigned int scale)
+{
+	return 0;
+}
+
 static inline bool clk_is_match(const struct clk *p, const struct clk *q)
 {
 	return p == q;
diff --git a/include/trace/events/clk.h b/include/trace/events/clk.h
index 2cd449328aee..9004ffff7f32 100644
--- a/include/trace/events/clk.h
+++ b/include/trace/events/clk.h
@@ -192,6 +192,42 @@ DEFINE_EVENT(clk_phase, clk_set_phase_complete,
 	TP_ARGS(core, phase)
 );
 
+DECLARE_EVENT_CLASS(clk_duty_cycle,
+
+	TP_PROTO(struct clk_core *core, struct clk_duty *duty),
+
+	TP_ARGS(core, duty),
+
+	TP_STRUCT__entry(
+		__string(        name,           core->name              )
+		__field( unsigned int,           num                     )
+		__field( unsigned int,           den                     )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, core->name);
+		__entry->num = duty->num;
+		__entry->den = duty->den;
+	),
+
+	TP_printk("%s %u/%u", __get_str(name), (unsigned int)__entry->num,
+		  (unsigned int)__entry->den)
+);
+
+DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle,
+
+	TP_PROTO(struct clk_core *core, struct clk_duty *duty),
+
+	TP_ARGS(core, duty)
+);
+
+DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle_complete,
+
+	TP_PROTO(struct clk_core *core, struct clk_duty *duty),
+
+	TP_ARGS(core, duty)
+);
+
 #endif /* _TRACE_CLK_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From b54c85c15a7bf1a34b14f23eb186e4a737ac3447 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:05 +0200
Subject: selinux: Cleanup printk logging in services

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/services.c | 71 +++++++++++++++++++++---------------------
 1 file changed, 35 insertions(+), 36 deletions(-)

diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c
index dd2ceec06fef..f3def298a90e 100644
--- a/security/selinux/ss/services.c
+++ b/security/selinux/ss/services.c
@@ -136,8 +136,7 @@ static int selinux_set_mapping(struct policydb *pol,
 
 		p_out->value = string_to_security_class(pol, p_in->name);
 		if (!p_out->value) {
-			printk(KERN_INFO
-			       "SELinux:  Class %s not defined in policy.\n",
+			pr_info("SELinux:  Class %s not defined in policy.\n",
 			       p_in->name);
 			if (pol->reject_unknown)
 				goto err;
@@ -156,8 +155,7 @@ static int selinux_set_mapping(struct policydb *pol,
 			p_out->perms[k] = string_to_av_perm(pol, p_out->value,
 							    p_in->perms[k]);
 			if (!p_out->perms[k]) {
-				printk(KERN_INFO
-				       "SELinux:  Permission %s in class %s not defined in policy.\n",
+				pr_info("SELinux:  Permission %s in class %s not defined in policy.\n",
 				       p_in->perms[k], p_in->name);
 				if (pol->reject_unknown)
 					goto err;
@@ -170,7 +168,7 @@ static int selinux_set_mapping(struct policydb *pol,
 	}
 
 	if (print_unknown_handle)
-		printk(KERN_INFO "SELinux: the above unknown classes and permissions will be %s\n",
+		pr_info("SELinux: the above unknown classes and permissions will be %s\n",
 		       pol->allow_unknown ? "allowed" : "denied");
 
 	out_map->size = i;
@@ -644,7 +642,7 @@ static void context_struct_compute_av(struct policydb *policydb,
 
 	if (unlikely(!tclass || tclass > policydb->p_classes.nprim)) {
 		if (printk_ratelimit())
-			printk(KERN_WARNING "SELinux:  Invalid class %hu\n", tclass);
+			pr_warn("SELinux:  Invalid class %hu\n", tclass);
 		return;
 	}
 
@@ -793,7 +791,7 @@ static int security_compute_validatetrans(struct selinux_state *state,
 
 	ocontext = sidtab_search(sidtab, oldsid);
 	if (!ocontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 			__func__, oldsid);
 		rc = -EINVAL;
 		goto out;
@@ -801,7 +799,7 @@ static int security_compute_validatetrans(struct selinux_state *state,
 
 	ncontext = sidtab_search(sidtab, newsid);
 	if (!ncontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 			__func__, newsid);
 		rc = -EINVAL;
 		goto out;
@@ -809,7 +807,7 @@ static int security_compute_validatetrans(struct selinux_state *state,
 
 	tcontext = sidtab_search(sidtab, tasksid);
 	if (!tcontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 			__func__, tasksid);
 		rc = -EINVAL;
 		goto out;
@@ -883,7 +881,7 @@ int security_bounded_transition(struct selinux_state *state,
 	rc = -EINVAL;
 	old_context = sidtab_search(sidtab, old_sid);
 	if (!old_context) {
-		printk(KERN_ERR "SELinux: %s: unrecognized SID %u\n",
+		pr_err("SELinux: %s: unrecognized SID %u\n",
 		       __func__, old_sid);
 		goto out;
 	}
@@ -891,7 +889,7 @@ int security_bounded_transition(struct selinux_state *state,
 	rc = -EINVAL;
 	new_context = sidtab_search(sidtab, new_sid);
 	if (!new_context) {
-		printk(KERN_ERR "SELinux: %s: unrecognized SID %u\n",
+		pr_err("SELinux: %s: unrecognized SID %u\n",
 		       __func__, new_sid);
 		goto out;
 	}
@@ -1040,14 +1038,14 @@ void security_compute_xperms_decision(struct selinux_state *state,
 
 	scontext = sidtab_search(sidtab, ssid);
 	if (!scontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, ssid);
 		goto out;
 	}
 
 	tcontext = sidtab_search(sidtab, tsid);
 	if (!tcontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, tsid);
 		goto out;
 	}
@@ -1129,7 +1127,7 @@ void security_compute_av(struct selinux_state *state,
 
 	scontext = sidtab_search(sidtab, ssid);
 	if (!scontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, ssid);
 		goto out;
 	}
@@ -1140,7 +1138,7 @@ void security_compute_av(struct selinux_state *state,
 
 	tcontext = sidtab_search(sidtab, tsid);
 	if (!tcontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, tsid);
 		goto out;
 	}
@@ -1183,7 +1181,7 @@ void security_compute_av_user(struct selinux_state *state,
 
 	scontext = sidtab_search(sidtab, ssid);
 	if (!scontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, ssid);
 		goto out;
 	}
@@ -1194,7 +1192,7 @@ void security_compute_av_user(struct selinux_state *state,
 
 	tcontext = sidtab_search(sidtab, tsid);
 	if (!tcontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, tsid);
 		goto out;
 	}
@@ -1310,7 +1308,7 @@ static int security_sid_to_context_core(struct selinux_state *state,
 			*scontext = scontextp;
 			goto out;
 		}
-		printk(KERN_ERR "SELinux: %s:  called before initial "
+		pr_err("SELinux: %s:  called before initial "
 		       "load_policy on unknown SID %d\n", __func__, sid);
 		rc = -EINVAL;
 		goto out;
@@ -1323,7 +1321,7 @@ static int security_sid_to_context_core(struct selinux_state *state,
 	else
 		context = sidtab_search(sidtab, sid);
 	if (!context) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 			__func__, sid);
 		rc = -EINVAL;
 		goto out_unlock;
@@ -1678,14 +1676,14 @@ static int security_compute_sid(struct selinux_state *state,
 
 	scontext = sidtab_search(sidtab, ssid);
 	if (!scontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, ssid);
 		rc = -EINVAL;
 		goto out_unlock;
 	}
 	tcontext = sidtab_search(sidtab, tsid);
 	if (!tcontext) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, tsid);
 		rc = -EINVAL;
 		goto out_unlock;
@@ -1911,7 +1909,8 @@ static inline int convert_context_handle_invalid_context(
 		return -EINVAL;
 
 	if (!context_struct_to_string(policydb, context, &s, &len)) {
-		printk(KERN_WARNING "SELinux:  Context %s would be invalid if enforcing\n", s);
+		pr_warn("SELinux:  Context %s would be invalid if enforcing\n",
+			s);
 		kfree(s);
 	}
 	return 0;
@@ -1962,7 +1961,7 @@ static int convert_context(u32 key,
 					      c->len, &ctx, SECSID_NULL);
 		kfree(s);
 		if (!rc) {
-			printk(KERN_INFO "SELinux:  Context %s became valid (mapped).\n",
+			pr_info("SELinux:  Context %s became valid (mapped).\n",
 			       c->str);
 			/* Replace string with mapped representation. */
 			kfree(c->str);
@@ -1974,7 +1973,7 @@ static int convert_context(u32 key,
 			goto out;
 		} else {
 			/* Other error condition, e.g. ENOMEM. */
-			printk(KERN_ERR "SELinux:   Unable to map context %s, rc = %d.\n",
+			pr_err("SELinux:   Unable to map context %s, rc = %d.\n",
 			       c->str, -rc);
 			goto out;
 		}
@@ -2033,7 +2032,7 @@ static int convert_context(u32 key,
 			oc = oc->next;
 		rc = -EINVAL;
 		if (!oc) {
-			printk(KERN_ERR "SELinux:  unable to look up"
+			pr_err("SELinux:  unable to look up"
 				" the initial SIDs list\n");
 			goto bad;
 		}
@@ -2065,7 +2064,7 @@ bad:
 	context_destroy(c);
 	c->str = s;
 	c->len = len;
-	printk(KERN_INFO "SELinux:  Context %s became invalid (unmapped).\n",
+	pr_info("SELinux:  Context %s became invalid (unmapped).\n",
 	       c->str);
 	rc = 0;
 	goto out;
@@ -2170,13 +2169,13 @@ int security_load_policy(struct selinux_state *state, void *data, size_t len)
 	newpolicydb->len = len;
 	/* If switching between different policy types, log MLS status */
 	if (policydb->mls_enabled && !newpolicydb->mls_enabled)
-		printk(KERN_INFO "SELinux: Disabling MLS support...\n");
+		pr_info("SELinux: Disabling MLS support...\n");
 	else if (!policydb->mls_enabled && newpolicydb->mls_enabled)
-		printk(KERN_INFO "SELinux: Enabling MLS support...\n");
+		pr_info("SELinux: Enabling MLS support...\n");
 
 	rc = policydb_load_isids(newpolicydb, &newsidtab);
 	if (rc) {
-		printk(KERN_ERR "SELinux:  unable to load the initial SIDs\n");
+		pr_err("SELinux:  unable to load the initial SIDs\n");
 		policydb_destroy(newpolicydb);
 		goto out;
 	}
@@ -2187,7 +2186,7 @@ int security_load_policy(struct selinux_state *state, void *data, size_t len)
 
 	rc = security_preserve_bools(state, newpolicydb);
 	if (rc) {
-		printk(KERN_ERR "SELinux:  unable to preserve booleans\n");
+		pr_err("SELinux:  unable to preserve booleans\n");
 		goto err;
 	}
 
@@ -2207,7 +2206,7 @@ int security_load_policy(struct selinux_state *state, void *data, size_t len)
 	args.newp = newpolicydb;
 	rc = sidtab_map(&newsidtab, convert_context, &args);
 	if (rc) {
-		printk(KERN_ERR "SELinux:  unable to convert the internal"
+		pr_err("SELinux:  unable to convert the internal"
 			" representation of contexts in the new SID"
 			" table\n");
 		goto err;
@@ -2999,7 +2998,7 @@ int security_sid_mls_copy(struct selinux_state *state,
 	rc = -EINVAL;
 	context1 = sidtab_search(sidtab, sid);
 	if (!context1) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 			__func__, sid);
 		goto out_unlock;
 	}
@@ -3007,7 +3006,7 @@ int security_sid_mls_copy(struct selinux_state *state,
 	rc = -EINVAL;
 	context2 = sidtab_search(sidtab, mls_sid);
 	if (!context2) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 			__func__, mls_sid);
 		goto out_unlock;
 	}
@@ -3104,14 +3103,14 @@ int security_net_peersid_resolve(struct selinux_state *state,
 	rc = -EINVAL;
 	nlbl_ctx = sidtab_search(sidtab, nlbl_sid);
 	if (!nlbl_ctx) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, nlbl_sid);
 		goto out;
 	}
 	rc = -EINVAL;
 	xfrm_ctx = sidtab_search(sidtab, xfrm_sid);
 	if (!xfrm_ctx) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized SID %d\n",
+		pr_err("SELinux: %s:  unrecognized SID %d\n",
 		       __func__, xfrm_sid);
 		goto out;
 	}
@@ -3202,7 +3201,7 @@ int security_get_permissions(struct selinux_state *state,
 	rc = -EINVAL;
 	match = hashtab_search(policydb->p_classes.table, class);
 	if (!match) {
-		printk(KERN_ERR "SELinux: %s:  unrecognized class %s\n",
+		pr_err("SELinux: %s:  unrecognized class %s\n",
 			__func__, class);
 		goto out;
 	}
-- 
cgit v1.2.3


From f8b69a5f00ee0a8e71555fdbd77f79db9c0769f0 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:06 +0200
Subject: selinux: Cleanup printk logging in selinuxfs

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/selinuxfs.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index f3d374d2ca04..d64a06e84eec 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -620,7 +620,7 @@ static ssize_t sel_write_context(struct file *file, char *buf, size_t size)
 
 	length = -ERANGE;
 	if (len > SIMPLE_TRANSACTION_LIMIT) {
-		printk(KERN_ERR "SELinux: %s:  context size (%u) exceeds "
+		pr_err("SELinux: %s:  context size (%u) exceeds "
 			"payload max\n", __func__, len);
 		goto out;
 	}
@@ -956,7 +956,7 @@ static ssize_t sel_write_create(struct file *file, char *buf, size_t size)
 
 	length = -ERANGE;
 	if (len > SIMPLE_TRANSACTION_LIMIT) {
-		printk(KERN_ERR "SELinux: %s:  context size (%u) exceeds "
+		pr_err("SELinux: %s:  context size (%u) exceeds "
 			"payload max\n", __func__, len);
 		goto out;
 	}
@@ -1147,7 +1147,7 @@ static ssize_t sel_write_member(struct file *file, char *buf, size_t size)
 
 	length = -ERANGE;
 	if (len > SIMPLE_TRANSACTION_LIMIT) {
-		printk(KERN_ERR "SELinux: %s:  context size (%u) exceeds "
+		pr_err("SELinux: %s:  context size (%u) exceeds "
 			"payload max\n", __func__, len);
 		goto out;
 	}
@@ -1996,7 +1996,7 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent)
 		goto err;
 	return 0;
 err:
-	printk(KERN_ERR "SELinux: %s:  failed while creating inodes\n",
+	pr_err("SELinux: %s:  failed while creating inodes\n",
 		__func__);
 
 	selinux_fs_info_free(sb);
@@ -2046,7 +2046,7 @@ static int __init init_sel_fs(void)
 
 	selinux_null.mnt = selinuxfs_mount = kern_mount(&sel_fs_type);
 	if (IS_ERR(selinuxfs_mount)) {
-		printk(KERN_ERR "selinuxfs:  could not mount!\n");
+		pr_err("selinuxfs:  could not mount!\n");
 		err = PTR_ERR(selinuxfs_mount);
 		selinuxfs_mount = NULL;
 	}
-- 
cgit v1.2.3


From d85a78334e7b67292834cd222962e010142905ca Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:07 +0200
Subject: selinux: Cleanup printk logging in netlink

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/selinux/netlink.c b/security/selinux/netlink.c
index 828fb6a4e941..8a8a72507437 100644
--- a/security/selinux/netlink.c
+++ b/security/selinux/netlink.c
@@ -94,7 +94,7 @@ out:
 out_kfree_skb:
 	kfree_skb(skb);
 oom:
-	printk(KERN_ERR "SELinux:  OOM in %s\n", __func__);
+	pr_err("SELinux:  OOM in %s\n", __func__);
 	goto out;
 }
 
-- 
cgit v1.2.3


From b21a695d9cba3a144cc833961457bdc6c987226e Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:08 +0200
Subject: selinux: Cleanup printk logging in sidtab

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/ss/sidtab.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/security/selinux/ss/sidtab.c b/security/selinux/ss/sidtab.c
index 5be31b7af225..fd75a12fa8fc 100644
--- a/security/selinux/ss/sidtab.c
+++ b/security/selinux/ss/sidtab.c
@@ -214,8 +214,7 @@ int sidtab_context_to_sid(struct sidtab *s,
 		}
 		sid = s->next_sid++;
 		if (context->len)
-			printk(KERN_INFO
-		       "SELinux:  Context %s is not valid (left unmapped).\n",
+			pr_info("SELinux:  Context %s is not valid (left unmapped).\n",
 			       context->str);
 		ret = sidtab_insert(s, sid, context);
 		if (ret)
@@ -253,7 +252,7 @@ void sidtab_hash_eval(struct sidtab *h, char *tag)
 		}
 	}
 
-	printk(KERN_DEBUG "%s:  %d entries and %d/%d buckets used, longest "
+	pr_debug("%s:  %d entries and %d/%d buckets used, longest "
 	       "chain length %d\n", tag, h->nel, slots_used, SIDTAB_SIZE,
 	       max_chain_len);
 }
-- 
cgit v1.2.3


From d006469d3fac547743612170756ed1571edcf97e Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:09 +0200
Subject: selinux: Cleanup printk logging in netport

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/netport.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/security/selinux/netport.c b/security/selinux/netport.c
index 9ed4c5064a5e..7a141cadbffc 100644
--- a/security/selinux/netport.c
+++ b/security/selinux/netport.c
@@ -173,9 +173,8 @@ static int sel_netport_sid_slow(u8 protocol, u16 pnum, u32 *sid)
 out:
 	spin_unlock_bh(&sel_netport_lock);
 	if (unlikely(ret)) {
-		printk(KERN_WARNING
-		       "SELinux: failure in sel_netport_sid_slow(),"
-		       " unable to determine network port label\n");
+		pr_warn("SELinux: failure in %s(), unable to determine network port label\n",
+			__func__);
 		kfree(new);
 	}
 	return ret;
-- 
cgit v1.2.3


From 0d3a115429e98997b6d12cbd0670059501f4ce71 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:10 +0200
Subject: selinux: Cleanup printk logging in netif

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/netif.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/security/selinux/netif.c b/security/selinux/netif.c
index ac65f7417413..8c738c189942 100644
--- a/security/selinux/netif.c
+++ b/security/selinux/netif.c
@@ -145,9 +145,8 @@ static int sel_netif_sid_slow(struct net *ns, int ifindex, u32 *sid)
 
 	dev = dev_get_by_index(ns, ifindex);
 	if (unlikely(dev == NULL)) {
-		printk(KERN_WARNING
-		       "SELinux: failure in sel_netif_sid_slow(),"
-		       " invalid network interface (%d)\n", ifindex);
+		pr_warn("SELinux: failure in %s(), invalid network interface (%d)\n",
+			__func__, ifindex);
 		return -ENOENT;
 	}
 
@@ -177,10 +176,8 @@ out:
 	spin_unlock_bh(&sel_netif_lock);
 	dev_put(dev);
 	if (unlikely(ret)) {
-		printk(KERN_WARNING
-		       "SELinux: failure in sel_netif_sid_slow(),"
-		       " unable to determine network interface label (%d)\n",
-		       ifindex);
+		pr_warn("SELinux: failure in %s(), unable to determine network interface label (%d)\n",
+			__func__, ifindex);
 		kfree(new);
 	}
 	return ret;
-- 
cgit v1.2.3


From 07c81ac2adccbdfe8cc48fe4ad347cd37520c504 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:11 +0200
Subject: selinux: Cleanup printk logging in avc

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/avc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/selinux/avc.c b/security/selinux/avc.c
index f3aedf077509..635e5c1e3e48 100644
--- a/security/selinux/avc.c
+++ b/security/selinux/avc.c
@@ -650,7 +650,7 @@ static int avc_latest_notif_update(struct selinux_avc *avc,
 	spin_lock_irqsave(&notif_lock, flag);
 	if (is_insert) {
 		if (seqno < avc->avc_cache.latest_notif) {
-			printk(KERN_WARNING "SELinux: avc:  seqno %d < latest_notif %d\n",
+			pr_warn("SELinux: avc:  seqno %d < latest_notif %d\n",
 			       seqno, avc->avc_cache.latest_notif);
 			ret = -EAGAIN;
 		}
-- 
cgit v1.2.3


From 67b0b4e4988f296ecc69fc8d09a2ce2741653ee0 Mon Sep 17 00:00:00 2001
From: peter enderborg <peter.enderborg@sony.com>
Date: Tue, 12 Jun 2018 10:09:12 +0200
Subject: selinux: Cleanup printk logging in netnode

Replace printk with pr_* to avoid checkpatch warnings.

Signed-off-by: Peter Enderborg <peter.enderborg@sony.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/netnode.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/security/selinux/netnode.c b/security/selinux/netnode.c
index 6dd89b89bc1f..afa0d432436b 100644
--- a/security/selinux/netnode.c
+++ b/security/selinux/netnode.c
@@ -238,9 +238,8 @@ static int sel_netnode_sid_slow(void *addr, u16 family, u32 *sid)
 out:
 	spin_unlock_bh(&sel_netnode_lock);
 	if (unlikely(ret)) {
-		printk(KERN_WARNING
-		       "SELinux: failure in sel_netnode_sid_slow(),"
-		       " unable to determine network node label\n");
+		pr_warn("SELinux: failure in %s(), unable to determine network node label\n",
+			__func__);
 		kfree(new);
 	}
 	return ret;
-- 
cgit v1.2.3


From 2bfb0b678e48dee76543bfa2079b7e42609332fb Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Mon, 16 Apr 2018 19:13:51 +0530
Subject: gpu: drm: radeon: Adding new typedef vm_fault_t
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use new return type vm_fault_t for fault handler
in vm_operations_struct.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_ttm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_ttm.c b/drivers/gpu/drm/radeon/radeon_ttm.c
index 8689fcca051c..cbb67e9ffb3a 100644
--- a/drivers/gpu/drm/radeon/radeon_ttm.c
+++ b/drivers/gpu/drm/radeon/radeon_ttm.c
@@ -947,11 +947,11 @@ void radeon_ttm_set_active_vram_size(struct radeon_device *rdev, u64 size)
 static struct vm_operations_struct radeon_ttm_vm_ops;
 static const struct vm_operations_struct *ttm_vm_ops = NULL;
 
-static int radeon_ttm_fault(struct vm_fault *vmf)
+static vm_fault_t radeon_ttm_fault(struct vm_fault *vmf)
 {
 	struct ttm_buffer_object *bo;
 	struct radeon_device *rdev;
-	int r;
+	vm_fault_t ret;
 
 	bo = (struct ttm_buffer_object *)vmf->vma->vm_private_data;
 	if (bo == NULL) {
@@ -959,9 +959,9 @@ static int radeon_ttm_fault(struct vm_fault *vmf)
 	}
 	rdev = radeon_get_rdev(bo->bdev);
 	down_read(&rdev->pm.mclk_lock);
-	r = ttm_vm_ops->fault(vmf);
+	ret = ttm_vm_ops->fault(vmf);
 	up_read(&rdev->pm.mclk_lock);
-	return r;
+	return ret;
 }
 
 int radeon_mmap(struct file *filp, struct vm_area_struct *vma)
-- 
cgit v1.2.3


From 4daa4fba3a3899a3eefff26e38cf680661a931e4 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Sat, 2 Jun 2018 00:57:24 +0530
Subject: gpu: drm: ttm: Adding new return type vm_fault_t
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use new return type vm_fault_t for fault handler. For
now, this is just documenting that the function returns
a VM_FAULT value rather than an errno. Once all instances
are converted, vm_fault_t will become a distinct type.

Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Previously vm_insert_{mixed,pfn} returns err which driver
mapped into VM_FAULT_* type. The new function
vmf_insert_{mixed,pfn} will replace this inefficiency by
returning VM_FAULT_* type.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo_vm.c | 45 ++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index c7ece7613a6a..0ca0ec47334e 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -44,10 +44,11 @@
 
 #define TTM_BO_VM_NUM_PREFAULT 16
 
-static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
+static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 				struct vm_fault *vmf)
 {
-	int ret = 0;
+	vm_fault_t ret = 0;
+	int err = 0;
 
 	if (likely(!bo->moving))
 		goto out_unlock;
@@ -78,9 +79,9 @@ static int ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 	/*
 	 * Ordinary wait.
 	 */
-	ret = dma_fence_wait(bo->moving, true);
-	if (unlikely(ret != 0)) {
-		ret = (ret != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
+	err = dma_fence_wait(bo->moving, true);
+	if (unlikely(err != 0)) {
+		ret = (err != -ERESTARTSYS) ? VM_FAULT_SIGBUS :
 			VM_FAULT_NOPAGE;
 		goto out_unlock;
 	}
@@ -105,7 +106,7 @@ static unsigned long ttm_bo_io_mem_pfn(struct ttm_buffer_object *bo,
 		+ page_offset;
 }
 
-static int ttm_bo_vm_fault(struct vm_fault *vmf)
+static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)
@@ -116,8 +117,9 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 	unsigned long pfn;
 	struct ttm_tt *ttm = NULL;
 	struct page *page;
-	int ret;
+	int err;
 	int i;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
 	unsigned long address = vmf->address;
 	struct ttm_mem_type_manager *man =
 		&bdev->man[bo->mem.mem_type];
@@ -129,9 +131,9 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 	 * for reserve, and if it fails, retry the fault after waiting
 	 * for the buffer to become unreserved.
 	 */
-	ret = ttm_bo_reserve(bo, true, true, NULL);
-	if (unlikely(ret != 0)) {
-		if (ret != -EBUSY)
+	err = ttm_bo_reserve(bo, true, true, NULL);
+	if (unlikely(err != 0)) {
+		if (err != -EBUSY)
 			return VM_FAULT_NOPAGE;
 
 		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
@@ -163,8 +165,8 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 	}
 
 	if (bdev->driver->fault_reserve_notify) {
-		ret = bdev->driver->fault_reserve_notify(bo);
-		switch (ret) {
+		err = bdev->driver->fault_reserve_notify(bo);
+		switch (err) {
 		case 0:
 			break;
 		case -EBUSY:
@@ -192,13 +194,13 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 		goto out_unlock;
 	}
 
-	ret = ttm_mem_io_lock(man, true);
-	if (unlikely(ret != 0)) {
+	err = ttm_mem_io_lock(man, true);
+	if (unlikely(err != 0)) {
 		ret = VM_FAULT_NOPAGE;
 		goto out_unlock;
 	}
-	ret = ttm_mem_io_reserve_vm(bo);
-	if (unlikely(ret != 0)) {
+	err = ttm_mem_io_reserve_vm(bo);
+	if (unlikely(err != 0)) {
 		ret = VM_FAULT_SIGBUS;
 		goto out_io_unlock;
 	}
@@ -266,23 +268,20 @@ static int ttm_bo_vm_fault(struct vm_fault *vmf)
 		}
 
 		if (vma->vm_flags & VM_MIXEDMAP)
-			ret = vm_insert_mixed(&cvma, address,
+			ret = vmf_insert_mixed(&cvma, address,
 					__pfn_to_pfn_t(pfn, PFN_DEV));
 		else
-			ret = vm_insert_pfn(&cvma, address, pfn);
+			ret = vmf_insert_pfn(&cvma, address, pfn);
 
 		/*
 		 * Somebody beat us to this PTE or prefaulting to
 		 * an already populated PTE, or prefaulting error.
 		 */
 
-		if (unlikely((ret == -EBUSY) || (ret != 0 && i > 0)))
+		if (unlikely((ret == VM_FAULT_NOPAGE && i > 0)))
 			break;
-		else if (unlikely(ret != 0)) {
-			ret =
-			    (ret == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+		else if (unlikely(ret & VM_FAULT_ERROR))
 			goto out_io_unlock;
-		}
 
 		address += PAGE_SIZE;
 		if (unlikely(++page_offset >= page_last))
-- 
cgit v1.2.3


From eeb2c3c2a614f003cd42cc3d96d23f5c29ff6727 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:35:10 +0200
Subject: amdgpu: display: use modern ktime accessors

getrawmonotonic64() is deprecated because of the nonstandard naming.

The replacement functions ktime_get_raw_ns() also simplifies the callers.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 8 --------
 drivers/gpu/drm/amd/display/dc/dm_services.h               | 5 ++++-
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 5a3346124a01..e861929dd981 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -35,14 +35,6 @@
 #include "amdgpu_dm_irq.h"
 #include "amdgpu_pm.h"
 
-unsigned long long dm_get_timestamp(struct dc_context *ctx)
-{
-	struct timespec64 time;
-
-	getrawmonotonic64(&time);
-	return timespec64_to_ns(&time);
-}
-
 unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
 		unsigned long long current_time_stamp,
 		unsigned long long last_time_stamp)
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services.h b/drivers/gpu/drm/amd/display/dc/dm_services.h
index 4ff9b2bba178..eb5ab3978e84 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services.h
@@ -339,7 +339,10 @@ bool dm_dmcu_set_pipe(struct dc_context *ctx, unsigned int controller_id);
 #define dm_log_to_buffer(buffer, size, fmt, args)\
 	vsnprintf(buffer, size, fmt, args)
 
-unsigned long long dm_get_timestamp(struct dc_context *ctx);
+static inline unsigned long long dm_get_timestamp(struct dc_context *ctx)
+{
+	return ktime_get_raw_ns();
+}
 
 unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
 		unsigned long long current_time_stamp,
-- 
cgit v1.2.3


From 8e2c7ad99dce3f4242fa0d0d5950ca3ba0f212c3 Mon Sep 17 00:00:00 2001
From: Chunming Zhou <david1.zhou@amd.com>
Date: Fri, 15 Jun 2018 14:39:57 +0800
Subject: drm/amdgpu: update ib_start/size_alignment same as windows used
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PAGE_SIZE for start_alignment is far much than hw requirement,
And now, update to expereince value from window side.

Signed-off-by: Chunming Zhou <david1.zhou@amd.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index ec1060a5eab3..2060f208e60b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -329,35 +329,35 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_gfx_rings; i++)
 				ring_mask |= ((adev->gfx.gfx_ring[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 8;
+			ib_start_alignment = 32;
+			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_COMPUTE:
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_compute_rings; i++)
 				ring_mask |= ((adev->gfx.compute_ring[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 8;
+			ib_start_alignment = 32;
+			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_DMA:
 			type = AMD_IP_BLOCK_TYPE_SDMA;
 			for (i = 0; i < adev->sdma.num_instances; i++)
 				ring_mask |= ((adev->sdma.instance[i].ring.ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 1;
+			ib_start_alignment = 256;
+			ib_size_alignment = 4;
 			break;
 		case AMDGPU_HW_IP_UVD:
 			type = AMD_IP_BLOCK_TYPE_UVD;
 			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
 				ring_mask |= ((adev->uvd.inst[i].ring.ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 16;
+			ib_start_alignment = 64;
+			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCE:
 			type = AMD_IP_BLOCK_TYPE_VCE;
 			for (i = 0; i < adev->vce.num_rings; i++)
 				ring_mask |= ((adev->vce.ring[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+			ib_start_alignment = 4;
 			ib_size_alignment = 1;
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
@@ -367,26 +367,26 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 					ring_mask |=
 					((adev->uvd.inst[i].ring_enc[j].ready ? 1 : 0) <<
 					(j + i * adev->uvd.num_enc_rings));
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
-			ib_size_alignment = 1;
+			ib_start_alignment = 64;
+			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			ring_mask = adev->vcn.ring_dec.ready ? 1 : 0;
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+			ib_start_alignment = 16;
 			ib_size_alignment = 16;
 			break;
 		case AMDGPU_HW_IP_VCN_ENC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			for (i = 0; i < adev->vcn.num_enc_rings; i++)
 				ring_mask |= ((adev->vcn.ring_enc[i].ready ? 1 : 0) << i);
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+			ib_start_alignment = 64;
 			ib_size_alignment = 1;
 			break;
 		case AMDGPU_HW_IP_VCN_JPEG:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			ring_mask = adev->vcn.ring_jpeg.ready ? 1 : 0;
-			ib_start_alignment = AMDGPU_GPU_PAGE_SIZE;
+			ib_start_alignment = 16;
 			ib_size_alignment = 16;
 			break;
 		default:
-- 
cgit v1.2.3


From 761f58e0e91334983cce60637adfbf7492aa97b3 Mon Sep 17 00:00:00 2001
From: Junwei Zhang <Jerry.Zhang@amd.com>
Date: Tue, 19 Jun 2018 11:22:18 +0800
Subject: drm/amdgpu: correct GART location info
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoid confusing the GART with the GTT domain.

Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fe76ec1f9737..f81e8d53d708 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -676,17 +676,15 @@ void amdgpu_device_vram_location(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_device_gart_location - try to find GTT location
+ * amdgpu_device_gart_location - try to find GART location
  *
  * @adev: amdgpu device structure holding all necessary informations
  * @mc: memory controller structure holding memory informations
  *
- * Function will place try to place GTT before or after VRAM.
+ * Function will place try to place GART before or after VRAM.
  *
- * If GTT size is bigger than space left then we ajust GTT size.
+ * If GART size is bigger than space left then we ajust GART size.
  * Thus function will never fails.
- *
- * FIXME: when reducing GTT size align new size on power of 2.
  */
 void amdgpu_device_gart_location(struct amdgpu_device *adev,
 				 struct amdgpu_gmc *mc)
@@ -699,13 +697,13 @@ void amdgpu_device_gart_location(struct amdgpu_device *adev,
 	size_bf = mc->vram_start;
 	if (size_bf > size_af) {
 		if (mc->gart_size > size_bf) {
-			dev_warn(adev->dev, "limiting GTT\n");
+			dev_warn(adev->dev, "limiting GART\n");
 			mc->gart_size = size_bf;
 		}
 		mc->gart_start = 0;
 	} else {
 		if (mc->gart_size > size_af) {
-			dev_warn(adev->dev, "limiting GTT\n");
+			dev_warn(adev->dev, "limiting GART\n");
 			mc->gart_size = size_af;
 		}
 		/* VCE doesn't like it when BOs cross a 4GB segment, so align
@@ -714,7 +712,7 @@ void amdgpu_device_gart_location(struct amdgpu_device *adev,
 		mc->gart_start = ALIGN(mc->vram_end + 1, 0x100000000ULL);
 	}
 	mc->gart_end = mc->gart_start + mc->gart_size - 1;
-	dev_info(adev->dev, "GTT: %lluM 0x%016llX - 0x%016llX\n",
+	dev_info(adev->dev, "GART: %lluM 0x%016llX - 0x%016llX\n",
 			mc->gart_size >> 20, mc->gart_start, mc->gart_end);
 }
 
-- 
cgit v1.2.3


From a21daa88d4f08c959a36ad9760df045407a080e5 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Tue, 19 Jun 2018 11:16:56 +0200
Subject: drm/amdgpu: Use correct enum to set powergating state

Use enum amd_powergating_state instead of enum amd_clockgating_state.
The underlying value stays the same, so there is no functional change
in practise. This fixes a warning seen with clang:
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c:1930:14: warning: implicit
      conversion from enumeration type 'enum amd_clockgating_state' to
      different enumeration type 'enum amd_powergating_state'
      [-Wenum-conversion]
                                                       AMD_CG_STATE_UNGATE);
                                                       ^~~~~~~~~~~~~~~~~~~

Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index f81e8d53d708..cd8177967e67 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1925,7 +1925,7 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
 		amdgpu_device_ip_set_powergating_state(adev,
 						       AMD_IP_BLOCK_TYPE_SMC,
-						       AMD_CG_STATE_UNGATE);
+						       AMD_PG_STATE_UNGATE);
 
 	/* ungate SMC block first */
 	r = amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_SMC,
-- 
cgit v1.2.3


From 6c1549c4cc3c1b0d8623cde00e28f094b2db0d41 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Mon, 18 Jun 2018 21:07:51 +0900
Subject: ALSA: firewire-motu: suppless consumption for unused element of array
 in stack

In MOTU firewire protocol, data block consists of 24 bit data chunks except
for one quadlet for source packet header (SPH). The number of data chunk in
a data block is different between three clock modes; low, middle and high.
When unit supports ADAT on optical interface, the data block includes some
chunks for ADAT channels. These ADAT chunks are unavailable at high mode.

This driver has local functions to calculate the number of ADAT chunks. But
They uses stack for three clock modes. This is useless for higher mode.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/motu/motu-protocol-v2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c
index 525b746330be..a51fd196d884 100644
--- a/sound/firewire/motu/motu-protocol-v2.c
+++ b/sound/firewire/motu/motu-protocol-v2.c
@@ -176,7 +176,7 @@ static void calculate_differed_part(struct snd_motu_packet_format *formats,
 				    enum snd_motu_spec_flags flags,
 				    u32 data, u32 mask, u32 shift)
 {
-	unsigned char pcm_chunks[3] = {0, 0};
+	unsigned char pcm_chunks[2] = {0, 0};
 
 	/*
 	 * When optical interfaces are configured for S/PDIF (TOSLINK),
-- 
cgit v1.2.3


From 81720c6d49b7932d642e7dca736bef9a40c9b5f7 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Mon, 18 Jun 2018 21:07:52 +0900
Subject: ALSA: firewire-motu: add a flag for chunks for main 1/2 out

This driver explicitly assumes that all of supported models have main data
chunk separated from chunk for analog ports. However, MOTU Traveler doesn't
support the separated main data chunk.

This commit adds a flag for the separated main data chunk.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/motu/motu-protocol-v2.c | 14 +++++++++-----
 sound/firewire/motu/motu-protocol-v3.c | 14 +++++++++-----
 sound/firewire/motu/motu.c             |  3 +++
 sound/firewire/motu/motu.h             |  1 +
 4 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c
index a51fd196d884..614f9b11e010 100644
--- a/sound/firewire/motu/motu-protocol-v2.c
+++ b/sound/firewire/motu/motu-protocol-v2.c
@@ -149,11 +149,15 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 			pcm_chunks[1] += 2;
 		}
 	} else {
-		/*
-		 * Packets to v2 units transfer main-out-1/2 and phone-out-1/2.
-		 */
-		pcm_chunks[0] += 4;
-		pcm_chunks[1] += 4;
+		if (flags & SND_MOTU_SPEC_RX_SEPARETED_MAIN) {
+			pcm_chunks[0] += 2;
+			pcm_chunks[1] += 2;
+		}
+
+		// Packets to v2 units include 2 chunks for phone 1/2, except
+		// for 176.4/192.0 kHz.
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
 	}
 
 	/*
diff --git a/sound/firewire/motu/motu-protocol-v3.c b/sound/firewire/motu/motu-protocol-v3.c
index c7cd9864dc4d..293353991591 100644
--- a/sound/firewire/motu/motu-protocol-v3.c
+++ b/sound/firewire/motu/motu-protocol-v3.c
@@ -188,11 +188,15 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 			pcm_chunks[1] += 2;
 		}
 	} else {
-		/*
-		 * Packets to v2 units transfer main-out-1/2 and phone-out-1/2.
-		 */
-		pcm_chunks[0] += 4;
-		pcm_chunks[1] += 4;
+		if (flags & SND_MOTU_SPEC_RX_SEPARETED_MAIN) {
+			pcm_chunks[0] += 2;
+			pcm_chunks[1] += 2;
+		}
+
+		// Packets to v3 units include 2 chunks for phone 1/2, except
+		// for 176.4/192.0 kHz.
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
 	}
 
 	/*
diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c
index 0d6b526105ab..445aa589582d 100644
--- a/sound/firewire/motu/motu.c
+++ b/sound/firewire/motu/motu.c
@@ -200,6 +200,7 @@ static const struct snd_motu_spec motu_828mk2 = {
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
+		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
 		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
 		 SND_MOTU_SPEC_TX_MIDI_2ND_Q,
@@ -216,6 +217,7 @@ static const struct snd_motu_spec motu_828mk3 = {
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
 		 SND_MOTU_SPEC_TX_REVERB_CHUNK |
+		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
 		 SND_MOTU_SPEC_HAS_OPT_IFACE_B |
 		 SND_MOTU_SPEC_RX_MIDI_3RD_Q |
@@ -231,6 +233,7 @@ static const struct snd_motu_spec motu_audio_express = {
 	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
 		 SND_MOTU_SPEC_TX_MICINST_CHUNK |
 		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
+		 SND_MOTU_SPEC_RX_SEPARETED_MAIN |
 		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
 		 SND_MOTU_SPEC_TX_MIDI_3RD_Q,
 	.analog_in_ports = 2,
diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h
index 4b23cf337c4b..bced0407179e 100644
--- a/sound/firewire/motu/motu.h
+++ b/sound/firewire/motu/motu.h
@@ -86,6 +86,7 @@ enum snd_motu_spec_flags {
 	SND_MOTU_SPEC_RX_MIDI_3RD_Q	= 0x0200,
 	SND_MOTU_SPEC_TX_MIDI_2ND_Q	= 0x0400,
 	SND_MOTU_SPEC_TX_MIDI_3RD_Q	= 0x0800,
+	SND_MOTU_SPEC_RX_SEPARETED_MAIN	= 0x1000,
 };
 
 #define SND_MOTU_CLOCK_RATE_COUNT	6
-- 
cgit v1.2.3


From 06ac0b6f8f74e98d32f9dea5209bd26f3e7b50ba Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Mon, 18 Jun 2018 21:07:53 +0900
Subject: ALSA: firewire-motu: add a flag for AES/EBU on XLR interface

MOTU Traveler supports AES/EBU on XLR interface and data block of rx/tx
packet includes two chunk for the interface. This commit adds a flag
for this purpose.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/motu/motu-protocol-v2.c | 5 +++++
 sound/firewire/motu/motu-protocol-v3.c | 5 +++++
 sound/firewire/motu/motu.h             | 2 +-
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c
index 614f9b11e010..f25b1ba118a2 100644
--- a/sound/firewire/motu/motu-protocol-v2.c
+++ b/sound/firewire/motu/motu-protocol-v2.c
@@ -160,6 +160,11 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 		pcm_chunks[1] += 2;
 	}
 
+	if (flags & SND_MOTU_SPEC_HAS_AESEBU_IFACE) {
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
+	}
+
 	/*
 	 * All of v2 models have a pair of coaxial interfaces for digital in/out
 	 * port. At 44.1/48.0/88.2/96.0 kHz, packets includes PCM from these
diff --git a/sound/firewire/motu/motu-protocol-v3.c b/sound/firewire/motu/motu-protocol-v3.c
index 293353991591..7cc80a05e91f 100644
--- a/sound/firewire/motu/motu-protocol-v3.c
+++ b/sound/firewire/motu/motu-protocol-v3.c
@@ -199,6 +199,11 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 		pcm_chunks[1] += 2;
 	}
 
+	if (flags & SND_MOTU_SPEC_HAS_AESEBU_IFACE) {
+		pcm_chunks[0] += 2;
+		pcm_chunks[1] += 2;
+	}
+
 	/*
 	 * At least, packets have two data chunks for S/PDIF on coaxial
 	 * interface.
diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h
index bced0407179e..2764bcaab327 100644
--- a/sound/firewire/motu/motu.h
+++ b/sound/firewire/motu/motu.h
@@ -79,7 +79,7 @@ enum snd_motu_spec_flags {
 	SND_MOTU_SPEC_TX_MICINST_CHUNK	= 0x0004,
 	SND_MOTU_SPEC_TX_RETURN_CHUNK	= 0x0008,
 	SND_MOTU_SPEC_TX_REVERB_CHUNK	= 0x0010,
-	SND_MOTU_SPEC_TX_AESEBU_CHUNK	= 0x0020,
+	SND_MOTU_SPEC_HAS_AESEBU_IFACE	= 0x0020,
 	SND_MOTU_SPEC_HAS_OPT_IFACE_A	= 0x0040,
 	SND_MOTU_SPEC_HAS_OPT_IFACE_B	= 0x0080,
 	SND_MOTU_SPEC_RX_MIDI_2ND_Q	= 0x0100,
-- 
cgit v1.2.3


From 191ef57683aab1939d9b7afdc43f9213c21c5e1e Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Mon, 18 Jun 2018 21:07:54 +0900
Subject: ALSA: firewire-motu: cancel chunk alignment for protocol version 2

For MOTU protocol version 2, this driver arranges the number of data
chunks to align chunks to quadlet data channel. However, MOTU Traveler
has padding bytes in the end of data block at high clock mode.

This commit removes the arrangement. Fortunately, at low and middle clock
mode, supported model for v2 protocol (828mkII) gets no influence from this
change because all of combination for data chunks are just aligned to
quadlet data channel.

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/motu/motu-protocol-v2.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c
index f25b1ba118a2..e5bd3ac02300 100644
--- a/sound/firewire/motu/motu-protocol-v2.c
+++ b/sound/firewire/motu/motu-protocol-v2.c
@@ -173,12 +173,9 @@ static void calculate_fixed_part(struct snd_motu_packet_format *formats,
 	pcm_chunks[0] += 2;
 	pcm_chunks[1] += 2;
 
-	/* This part should be multiples of 4. */
-	formats->fixed_part_pcm_chunks[0] = round_up(2 + pcm_chunks[0], 4) - 2;
-	formats->fixed_part_pcm_chunks[1] = round_up(2 + pcm_chunks[1], 4) - 2;
-	if (flags & SND_MOTU_SPEC_SUPPORT_CLOCK_X4)
-		formats->fixed_part_pcm_chunks[2] =
-					round_up(2 + pcm_chunks[2], 4) - 2;
+	formats->fixed_part_pcm_chunks[0] = pcm_chunks[0];
+	formats->fixed_part_pcm_chunks[1] = pcm_chunks[1];
+	formats->fixed_part_pcm_chunks[2] = pcm_chunks[2];
 }
 
 static void calculate_differed_part(struct snd_motu_packet_format *formats,
-- 
cgit v1.2.3


From 6c5e1ac0e144a8560cfa11bed8cdadab9491952f Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Mon, 18 Jun 2018 21:07:55 +0900
Subject: ALSA: firewire-motu: add support for Motu Traveler

This commit adds support for MOTU Traveler, launched in 2005, discontinued
quite before. As a result, transmission of PCM frame and MIDI messages is
available via ALSA PCM and RawMIDI/Sequencer interfaces.

This model supports sampling transmission frequency up to 192.0 kHz, and
AES/EBU on XLR interface and ADAT on optical interface. Unlike
Motu 828MkII, Windows driver can switch fetching mode for DSP, like
mute/unmute feature.

Although this commit enables high sampling transmission frequency, actual
sound from this model is not good. As long as I tested, it's silence at
176.4 kHz, and it includes hissing noise at 192.0 kHz. In my opinion, as I
reported at 3526ce7f9ba7 ('ALSA: firewire-motu: add MOTU specific protocol
layer'), timestamping on source packet header (SPH) may not still be good
for this model as well.

$ python2 crpp < /sys/bus/firewire/devices/fw1/config_rom
               ROM header and bus information block
               -----------------------------------------------------------------
400  04106505  bus_info_length 4, crc_length 16, crc 25861
404  31333934  bus_name "1394"
408  20001000  irmc 0, cmc 0, isc 1, bmc 0, cyc_clk_acc 0, max_rec 1 (4)
40c  0001f200  company_id 0001f2     |
410  0001f32f  device_id 000001f32f  | EUI-64 0001f2000001f32f

               root directory
               -----------------------------------------------------------------
414  0004c65c  directory_length 4, crc 50780
418  030001f2  vendor
41c  0c0083c0  node capabilities per IEEE 1394
420  8d000006  --> eui-64 leaf at 438
424  d1000001  --> unit directory at 428

               unit directory at 428
               -----------------------------------------------------------------
428  00035955  directory_length 3, crc 22869
42c  120001f2  specifier id
430  13000009  version
434  17107800  model

               eui-64 leaf at 438
               -----------------------------------------------------------------
438  000206b2  leaf_length 2, crc 1714
43c  0001f200  company_id 0001f2     |
440  0001f32f  device_id 000001f32f  | EUI-64 0001f2000001f32f

Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/motu/motu-protocol-v2.c | 34 ++++++++++++++++++++++++++++++++--
 sound/firewire/motu/motu.c             | 16 ++++++++++++++++
 sound/firewire/motu/motu.h             |  2 ++
 3 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/sound/firewire/motu/motu-protocol-v2.c b/sound/firewire/motu/motu-protocol-v2.c
index e5bd3ac02300..453fc29fade7 100644
--- a/sound/firewire/motu/motu-protocol-v2.c
+++ b/sound/firewire/motu/motu-protocol-v2.c
@@ -13,6 +13,8 @@
 #define  V2_CLOCK_RATE_SHIFT			3
 #define  V2_CLOCK_SRC_MASK			0x00000007
 #define  V2_CLOCK_SRC_SHIFT			0
+#define  V2_CLOCK_TRAVELER_FETCH_DISABLE	0x04000000
+#define  V2_CLOCK_TRAVELER_FETCH_ENABLE		0x03000000
 
 #define V2_IN_OUT_CONF_OFFSET			0x0c04
 #define  V2_OPT_OUT_IFACE_MASK			0x00000c00
@@ -66,6 +68,11 @@ static int v2_set_clock_rate(struct snd_motu *motu, unsigned int rate)
 	data &= ~V2_CLOCK_RATE_MASK;
 	data |= i << V2_CLOCK_RATE_SHIFT;
 
+	if (motu->spec == &snd_motu_spec_traveler) {
+		data &= ~V2_CLOCK_TRAVELER_FETCH_ENABLE;
+		data |= V2_CLOCK_TRAVELER_FETCH_DISABLE;
+	}
+
 	reg = cpu_to_be32(data);
 	return snd_motu_transaction_write(motu, V2_CLOCK_STATUS_OFFSET, &reg,
 					  sizeof(reg));
@@ -121,8 +128,31 @@ static int v2_get_clock_source(struct snd_motu *motu,
 
 static int v2_switch_fetching_mode(struct snd_motu *motu, bool enable)
 {
-	/* V2 protocol doesn't have this feature. */
-	return 0;
+	__be32 reg;
+	u32 data;
+	int err = 0;
+
+	if (motu->spec == &snd_motu_spec_traveler) {
+		err = snd_motu_transaction_read(motu, V2_CLOCK_STATUS_OFFSET,
+						&reg, sizeof(reg));
+		if (err < 0)
+			return err;
+		data = be32_to_cpu(reg);
+
+		data &= ~(V2_CLOCK_TRAVELER_FETCH_DISABLE |
+			  V2_CLOCK_TRAVELER_FETCH_ENABLE);
+
+		if (enable)
+			data |= V2_CLOCK_TRAVELER_FETCH_ENABLE;
+		else
+			data |= V2_CLOCK_TRAVELER_FETCH_DISABLE;
+
+		reg = cpu_to_be32(data);
+		err = snd_motu_transaction_write(motu, V2_CLOCK_STATUS_OFFSET,
+						 &reg, sizeof(reg));
+	}
+
+	return err;
 }
 
 static void calculate_fixed_part(struct snd_motu_packet_format *formats,
diff --git a/sound/firewire/motu/motu.c b/sound/firewire/motu/motu.c
index 445aa589582d..300d31b6f191 100644
--- a/sound/firewire/motu/motu.c
+++ b/sound/firewire/motu/motu.c
@@ -209,6 +209,21 @@ static const struct snd_motu_spec motu_828mk2 = {
 	.analog_out_ports = 8,
 };
 
+const struct snd_motu_spec snd_motu_spec_traveler = {
+	.name = "Traveler",
+	.protocol = &snd_motu_protocol_v2,
+	.flags = SND_MOTU_SPEC_SUPPORT_CLOCK_X2 |
+		 SND_MOTU_SPEC_SUPPORT_CLOCK_X4 |
+		 SND_MOTU_SPEC_TX_RETURN_CHUNK |
+		 SND_MOTU_SPEC_HAS_AESEBU_IFACE |
+		 SND_MOTU_SPEC_HAS_OPT_IFACE_A |
+		 SND_MOTU_SPEC_RX_MIDI_2ND_Q |
+		 SND_MOTU_SPEC_TX_MIDI_2ND_Q,
+
+	.analog_in_ports = 8,
+	.analog_out_ports = 8,
+};
+
 static const struct snd_motu_spec motu_828mk3 = {
 	.name = "828mk3",
 	.protocol = &snd_motu_protocol_v3,
@@ -253,6 +268,7 @@ static const struct snd_motu_spec motu_audio_express = {
 
 static const struct ieee1394_device_id motu_id_table[] = {
 	SND_MOTU_DEV_ENTRY(0x101800, &motu_828mk2),
+	SND_MOTU_DEV_ENTRY(0x107800, &snd_motu_spec_traveler),
 	SND_MOTU_DEV_ENTRY(0x106800, &motu_828mk3),	/* FireWire only. */
 	SND_MOTU_DEV_ENTRY(0x100800, &motu_828mk3),	/* Hybrid. */
 	SND_MOTU_DEV_ENTRY(0x104800, &motu_audio_express),
diff --git a/sound/firewire/motu/motu.h b/sound/firewire/motu/motu.h
index 2764bcaab327..fd5327d30ab1 100644
--- a/sound/firewire/motu/motu.h
+++ b/sound/firewire/motu/motu.h
@@ -129,6 +129,8 @@ struct snd_motu_spec {
 extern const struct snd_motu_protocol snd_motu_protocol_v2;
 extern const struct snd_motu_protocol snd_motu_protocol_v3;
 
+extern const struct snd_motu_spec snd_motu_spec_traveler;
+
 int amdtp_motu_init(struct amdtp_stream *s, struct fw_unit *unit,
 		    enum amdtp_stream_direction dir,
 		    const struct snd_motu_protocol *const protocol);
-- 
cgit v1.2.3


From bd646104ac5a6bf8bdddaeaf4e441f5d439ded96 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 19 Jun 2018 17:51:02 +0200
Subject: jfs: use time64_t for otime

The file creation time in the inode uses time_t which is defined
differently on 32-bit and 64-bit architectures and deprecated. The
representation in the inode uses an unsigned 32-bit number, but this
gets wrapped around after year 2038 when assigned to a time_t.

This changes the type to time64_t, so we can support the full range of
timestamps between 1970 and 2106 on 32-bit systems like we do on 64-bit
systems already, and matching what we do for the atime/ctime/mtime stamps
since the introduction of 64-bit timestamps in VFS.

Note: the otime stamp is not actually used anywhere at the moment in
the kernel, it is just set when writing a file, so none of this really
makes a difference unless we implement setting the btime field in the
getattr() callback.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
---
 fs/jfs/jfs_incore.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/jfs/jfs_incore.h b/fs/jfs/jfs_incore.h
index 1f26d1910409..d5c46f86b2ef 100644
--- a/fs/jfs/jfs_incore.h
+++ b/fs/jfs/jfs_incore.h
@@ -43,7 +43,7 @@ struct jfs_inode_info {
 	pxd_t	ixpxd;		/* inode extent descriptor	*/
 	dxd_t	acl;		/* dxd describing acl	*/
 	dxd_t	ea;		/* dxd describing ea	*/
-	time_t	otime;		/* time created	*/
+	time64_t otime;		/* time created	*/
 	uint	next_index;	/* next available directory entry index */
 	int	acltype;	/* Type of ACL	*/
 	short	btorder;	/* access order	*/
-- 
cgit v1.2.3


From d30c8d2031259d6dc360f8c96d362bb36665c99c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 19 Jun 2018 10:18:56 +0200
Subject: leds: ledtrig-activity: use ktime_get_boot_ns()

get_monotonic_boottime() is deprecated, so let's convert this to
the simpler ktime_get_boot_ns().

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-activity.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c
index 5081894082bd..6c6f8a9b8d9a 100644
--- a/drivers/leds/trigger/ledtrig-activity.c
+++ b/drivers/leds/trigger/ledtrig-activity.c
@@ -37,7 +37,6 @@ static void led_activity_function(struct timer_list *t)
 	struct activity_data *activity_data = from_timer(activity_data, t,
 							 timer);
 	struct led_classdev *led_cdev = activity_data->led_cdev;
-	struct timespec boot_time;
 	unsigned int target;
 	unsigned int usage;
 	int delay;
@@ -57,8 +56,6 @@ static void led_activity_function(struct timer_list *t)
 		return;
 	}
 
-	get_monotonic_boottime(&boot_time);
-
 	cpus = 0;
 	curr_used = 0;
 
@@ -76,7 +73,7 @@ static void led_activity_function(struct timer_list *t)
 	 * down to 16us, ensuring we won't overflow 32-bit computations below
 	 * even up to 3k CPUs, while keeping divides cheap on smaller systems.
 	 */
-	curr_boot = timespec_to_ns(&boot_time) * cpus;
+	curr_boot = ktime_get_boot_ns() * cpus;
 	diff_boot = (curr_boot - activity_data->last_boot) >> 16;
 	diff_used = (curr_used - activity_data->last_used) >> 16;
 	activity_data->last_boot = curr_boot;
-- 
cgit v1.2.3


From 93c9a7f8793175fdad5c472af5af07f994116a04 Mon Sep 17 00:00:00 2001
From: Jan Kiszka <jan.kiszka@siemens.com>
Date: Tue, 19 Jun 2018 16:52:42 -0500
Subject: PCI: Clean up resource allocation in
 devm_of_pci_get_host_bridge_resources()

Instead of first allocating and then freeing memory for struct resource in
case we cannot parse a PCI resource from the device tree, work against a
local struct and kmemdup() it when we decide to go with it.

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Vladimir Zapolskiy <vladimir_zapolskiy@mentor.com>
---
 drivers/pci/of.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/of.c b/drivers/pci/of.c
index d088c9147f10..f8686c48e255 100644
--- a/drivers/pci/of.c
+++ b/drivers/pci/of.c
@@ -266,7 +266,7 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev,
 			struct list_head *resources, resource_size_t *io_base)
 {
 	struct device_node *dev_node = dev->of_node;
-	struct resource *res;
+	struct resource *res, tmp_res;
 	struct resource *bus_range;
 	struct of_pci_range range;
 	struct of_pci_range_parser parser;
@@ -320,18 +320,16 @@ int devm_of_pci_get_host_bridge_resources(struct device *dev,
 		if (range.cpu_addr == OF_BAD_ADDR || range.size == 0)
 			continue;
 
-		res = devm_kzalloc(dev, sizeof(struct resource), GFP_KERNEL);
+		err = of_pci_range_to_resource(&range, dev_node, &tmp_res);
+		if (err)
+			continue;
+
+		res = devm_kmemdup(dev, &tmp_res, sizeof(tmp_res), GFP_KERNEL);
 		if (!res) {
 			err = -ENOMEM;
 			goto failed;
 		}
 
-		err = of_pci_range_to_resource(&range, dev_node, res);
-		if (err) {
-			devm_kfree(dev, res);
-			continue;
-		}
-
 		if (resource_type(res) == IORESOURCE_IO) {
 			if (!io_base) {
 				dev_err(dev, "I/O range found for %pOF. Please provide an io_base pointer to save CPU base address\n",
-- 
cgit v1.2.3


From a6d639da63aeb838d5c0b7dc50598f2eac4014a0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jun 2018 15:10:55 -0700
Subject: fs: factor out a __generic_write_end helper

Bits of the buffer.c based write_end implementations that don't know
about buffer_heads and can be reused by other implementations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/buffer.c   | 67 +++++++++++++++++++++++++++++++----------------------------
 fs/internal.h |  2 ++
 2 files changed, 37 insertions(+), 32 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index cabc045f483d..aba2a948b235 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2076,6 +2076,40 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 }
 EXPORT_SYMBOL(block_write_begin);
 
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+		struct page *page)
+{
+	loff_t old_size = inode->i_size;
+	bool i_size_changed = false;
+
+	/*
+	 * No need to use i_size_read() here, the i_size cannot change under us
+	 * because we hold i_rwsem.
+	 *
+	 * But it's important to update i_size while still holding page lock:
+	 * page writeout could otherwise come in and zero beyond i_size.
+	 */
+	if (pos + copied > inode->i_size) {
+		i_size_write(inode, pos + copied);
+		i_size_changed = true;
+	}
+
+	unlock_page(page);
+	put_page(page);
+
+	if (old_size < pos)
+		pagecache_isize_extended(inode, old_size, pos);
+	/*
+	 * Don't mark the inode dirty under page lock. First, it unnecessarily
+	 * makes the holding time of page lock longer. Second, it forces lock
+	 * ordering of page lock and transaction start for journaling
+	 * filesystems.
+	 */
+	if (i_size_changed)
+		mark_inode_dirty(inode);
+	return copied;
+}
+
 int block_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
@@ -2116,39 +2150,8 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct page *page, void *fsdata)
 {
-	struct inode *inode = mapping->host;
-	loff_t old_size = inode->i_size;
-	int i_size_changed = 0;
-
 	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-	/*
-	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold i_mutex.
-	 *
-	 * But it's important to update i_size while still holding page lock:
-	 * page writeout could otherwise come in and zero beyond i_size.
-	 */
-	if (pos+copied > inode->i_size) {
-		i_size_write(inode, pos+copied);
-		i_size_changed = 1;
-	}
-
-	unlock_page(page);
-	put_page(page);
-
-	if (old_size < pos)
-		pagecache_isize_extended(inode, old_size, pos);
-	/*
-	 * Don't mark the inode dirty under page lock. First, it unnecessarily
-	 * makes the holding time of page lock longer. Second, it forces lock
-	 * ordering of page lock and transaction start for journaling
-	 * filesystems.
-	 */
-	if (i_size_changed)
-		mark_inode_dirty(inode);
-
-	return copied;
+	return __generic_write_end(mapping->host, pos, copied, page);
 }
 EXPORT_SYMBOL(generic_write_end);
 
diff --git a/fs/internal.h b/fs/internal.h
index 980d005b21b4..4a18bdbd2214 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -43,6 +43,8 @@ static inline int __sync_blockdev(struct block_device *bdev, int wait)
 extern void guard_bio_eod(int rw, struct bio *bio);
 extern int __block_write_begin_int(struct page *page, loff_t pos, unsigned len,
 		get_block_t *get_block, struct iomap *iomap);
+int __generic_write_end(struct inode *inode, loff_t pos, unsigned copied,
+		struct page *page);
 
 /*
  * char_dev.c
-- 
cgit v1.2.3


From 3d7b6b21f6c590c4d70b311bbdd78a214637c9c7 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 19 Jun 2018 15:10:55 -0700
Subject: iomap: mark newly allocated buffer heads as new

In iomap_to_bh, not only mark buffer heads in IOMAP_UNWRITTEN maps as
new, but also buffer heads in IOMAP_MAPPED maps with the IOMAP_F_NEW
flag set.  This will be used by filesystems like gfs2, which allocate
blocks in iomap->begin.

Minor corrections to the comment for IOMAP_UNWRITTEN maps.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/buffer.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/buffer.c b/fs/buffer.c
index aba2a948b235..c8c2b7d8b8d6 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -1900,15 +1900,16 @@ iomap_to_bh(struct inode *inode, sector_t block, struct buffer_head *bh,
 		break;
 	case IOMAP_UNWRITTEN:
 		/*
-		 * For unwritten regions, we always need to ensure that
-		 * sub-block writes cause the regions in the block we are not
-		 * writing to are zeroed. Set the buffer as new to ensure this.
+		 * For unwritten regions, we always need to ensure that regions
+		 * in the block we are not writing to are zeroed. Mark the
+		 * buffer as new to ensure this.
 		 */
 		set_buffer_new(bh);
 		set_buffer_unwritten(bh);
 		/* FALLTHRU */
 	case IOMAP_MAPPED:
-		if (offset >= i_size_read(inode))
+		if ((iomap->flags & IOMAP_F_NEW) ||
+		    offset >= i_size_read(inode))
 			set_buffer_new(bh);
 		bh->b_blocknr = (iomap->addr + offset - iomap->offset) >>
 				inode->i_blkbits;
-- 
cgit v1.2.3


From ebf00be37de35788cad72f4f20b4a39e30c0be4a Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 19 Jun 2018 15:10:55 -0700
Subject: iomap: complete partial direct I/O writes synchronously

According to xfstest generic/240, applications seem to expect direct I/O
writes to either complete as a whole or to fail; short direct I/O writes
are apparently not appreciated.  This means that when only part of an
asynchronous direct I/O write succeeds, we can either fail the entire
write, or we can wait for the partial write to complete and retry the
remaining write as buffered I/O.  The old __blockdev_direct_IO helper
has code for waiting for partial writes to complete; the new
iomap_dio_rw iomap helper does not.

The above mentioned fallback mode is needed for gfs2, which doesn't
allow block allocations under direct I/O to avoid taking cluster-wide
exclusive locks.  As a consequence, an asynchronous direct I/O write to
a file range that contains a hole will result in a short write.  In that
case, wait for the short write to complete to allow gfs2 to recover.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 77397b5a96ef..9c454459a1e9 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -811,6 +811,7 @@ struct iomap_dio {
 	atomic_t		ref;
 	unsigned		flags;
 	int			error;
+	bool			wait_for_completion;
 
 	union {
 		/* used during submission and for synchronous completion: */
@@ -914,9 +915,8 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 		iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
 
 	if (atomic_dec_and_test(&dio->ref)) {
-		if (is_sync_kiocb(dio->iocb)) {
+		if (dio->wait_for_completion) {
 			struct task_struct *waiter = dio->submit.waiter;
-
 			WRITE_ONCE(dio->submit.waiter, NULL);
 			wake_up_process(waiter);
 		} else if (dio->flags & IOMAP_DIO_WRITE) {
@@ -1131,13 +1131,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	dio->end_io = end_io;
 	dio->error = 0;
 	dio->flags = 0;
+	dio->wait_for_completion = is_sync_kiocb(iocb);
 
 	dio->submit.iter = iter;
-	if (is_sync_kiocb(iocb)) {
-		dio->submit.waiter = current;
-		dio->submit.cookie = BLK_QC_T_NONE;
-		dio->submit.last_queue = NULL;
-	}
+	dio->submit.waiter = current;
+	dio->submit.cookie = BLK_QC_T_NONE;
+	dio->submit.last_queue = NULL;
 
 	if (iov_iter_rw(iter) == READ) {
 		if (pos >= dio->i_size)
@@ -1187,7 +1186,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio_warn_stale_pagecache(iocb->ki_filp);
 	ret = 0;
 
-	if (iov_iter_rw(iter) == WRITE && !is_sync_kiocb(iocb) &&
+	if (iov_iter_rw(iter) == WRITE && !dio->wait_for_completion &&
 	    !inode->i_sb->s_dio_done_wq) {
 		ret = sb_init_dio_done_wq(inode->i_sb);
 		if (ret < 0)
@@ -1202,8 +1201,10 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 				iomap_dio_actor);
 		if (ret <= 0) {
 			/* magic error code to fall back to buffered I/O */
-			if (ret == -ENOTBLK)
+			if (ret == -ENOTBLK) {
+				dio->wait_for_completion = true;
 				ret = 0;
+			}
 			break;
 		}
 		pos += ret;
@@ -1224,7 +1225,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		dio->flags &= ~IOMAP_DIO_NEED_SYNC;
 
 	if (!atomic_dec_and_test(&dio->ref)) {
-		if (!is_sync_kiocb(iocb))
+		if (!dio->wait_for_completion)
 			return -EIOCBQUEUED;
 
 		for (;;) {
-- 
cgit v1.2.3


From 19e0c58f6552638c86395f0717210326fdf14fd2 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 19 Jun 2018 15:10:56 -0700
Subject: iomap: generic inline data handling

Add generic inline data handling by adding a pointer to the inline data
region to struct iomap.  When handling a buffered IOMAP_INLINE write,
iomap_write_begin will copy the current inline data from the inline data
region into the page cache, and iomap_write_end will copy the changes in
the page cache back to the inline data region.

This doesn't cover inline data reads and direct I/O yet because so far,
we have no users.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
[hch: small cleanups to better fit in with other iomap work]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c            | 62 +++++++++++++++++++++++++++++++++++++++++++++------
 include/linux/iomap.h |  1 +
 2 files changed, 56 insertions(+), 7 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 9c454459a1e9..4aecd7c5dbd8 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -103,6 +103,26 @@ iomap_sector(struct iomap *iomap, loff_t pos)
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
+static void
+iomap_read_inline_data(struct inode *inode, struct page *page,
+		struct iomap *iomap)
+{
+	size_t size = i_size_read(inode);
+	void *addr;
+
+	if (PageUptodate(page))
+		return;
+
+	BUG_ON(page->index);
+	BUG_ON(size > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	addr = kmap_atomic(page);
+	memcpy(addr, iomap->inline_data, size);
+	memset(addr + size, 0, PAGE_SIZE - size);
+	kunmap_atomic(addr);
+	SetPageUptodate(page);
+}
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
@@ -133,7 +153,11 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	if (!page)
 		return -ENOMEM;
 
-	status = __block_write_begin_int(page, pos, len, NULL, iomap);
+	if (iomap->type == IOMAP_INLINE)
+		iomap_read_inline_data(inode, page, iomap);
+	else
+		status = __block_write_begin_int(page, pos, len, NULL, iomap);
+
 	if (unlikely(status)) {
 		unlock_page(page);
 		put_page(page);
@@ -146,14 +170,37 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	return status;
 }
 
+static int
+iomap_write_end_inline(struct inode *inode, struct page *page,
+		struct iomap *iomap, loff_t pos, unsigned copied)
+{
+	void *addr;
+
+	WARN_ON_ONCE(!PageUptodate(page));
+	BUG_ON(pos + copied > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	addr = kmap_atomic(page);
+	memcpy(iomap->inline_data + pos, addr + pos, copied);
+	kunmap_atomic(addr);
+
+	mark_inode_dirty(inode);
+	__generic_write_end(inode, pos, copied, page);
+	return copied;
+}
+
 static int
 iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
-		unsigned copied, struct page *page)
+		unsigned copied, struct page *page, struct iomap *iomap)
 {
 	int ret;
 
-	ret = generic_write_end(NULL, inode->i_mapping, pos, len,
-			copied, page, NULL);
+	if (iomap->type == IOMAP_INLINE) {
+		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
+	} else {
+		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
+				copied, page, NULL);
+	}
+
 	if (ret < len)
 		iomap_write_failed(inode, pos, len);
 	return ret;
@@ -208,7 +255,8 @@ again:
 
 		flush_dcache_page(page);
 
-		status = iomap_write_end(inode, pos, bytes, copied, page);
+		status = iomap_write_end(inode, pos, bytes, copied, page,
+				iomap);
 		if (unlikely(status < 0))
 			break;
 		copied = status;
@@ -302,7 +350,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 		WARN_ON_ONCE(!PageUptodate(page));
 
-		status = iomap_write_end(inode, pos, bytes, bytes, page);
+		status = iomap_write_end(inode, pos, bytes, bytes, page, iomap);
 		if (unlikely(status <= 0)) {
 			if (WARN_ON_ONCE(status == 0))
 				return -EIO;
@@ -354,7 +402,7 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	zero_user(page, offset, bytes);
 	mark_page_accessed(page);
 
-	return iomap_write_end(inode, pos, bytes, bytes, page);
+	return iomap_write_end(inode, pos, bytes, bytes, page, iomap);
 }
 
 static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index a044a824da85..10d6cff7f69a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -55,6 +55,7 @@ struct iomap {
 	u16			flags;	/* flags for mapping */
 	struct block_device	*bdev;	/* block device for I/O */
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
+	void			*inline_data;
 };
 
 /*
-- 
cgit v1.2.3


From 63899c6f8851c32214b19390254fa1ae90b582df Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jun 2018 15:10:56 -0700
Subject: iomap: add a page_done callback

This will be used by gfs2 to attach data to transactions for the journaled
data mode.  But the concept is generic enough that we might be able to
use it for other purposes like encryption/integrity post-processing in the
future.

Based on a patch from Andreas Gruenbacher.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c            | 3 +++
 include/linux/iomap.h | 9 +++++++++
 2 files changed, 12 insertions(+)

diff --git a/fs/iomap.c b/fs/iomap.c
index 4aecd7c5dbd8..a1f71e64ea49 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -201,6 +201,9 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 				copied, page, NULL);
 	}
 
+	if (iomap->page_done)
+		iomap->page_done(inode, pos, copied, page, iomap);
+
 	if (ret < len)
 		iomap_write_failed(inode, pos, len);
 	return ret;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 10d6cff7f69a..45f43865b0f0 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -9,6 +9,7 @@ struct fiemap_extent_info;
 struct inode;
 struct iov_iter;
 struct kiocb;
+struct page;
 struct vm_area_struct;
 struct vm_fault;
 
@@ -56,6 +57,14 @@ struct iomap {
 	struct block_device	*bdev;	/* block device for I/O */
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
 	void			*inline_data;
+
+	/*
+	 * Called when finished processing a page in the mapping returned in
+	 * this iomap.  At least for now this is only supported in the buffered
+	 * write path.
+	 */
+	void (*page_done)(struct inode *inode, loff_t pos, unsigned copied,
+			struct page *page, struct iomap *iomap);
 };
 
 /*
-- 
cgit v1.2.3


From 72b4daa241295440f98e80ae21294a67b27ca091 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jun 2018 15:10:57 -0700
Subject: iomap: add an iomap-based readpage and readpages implementation

Simply use iomap_apply to iterate over the file and a submit a bio for
each non-uptodate but mapped region and zero everything else.  Note that
as-is this can not be used for file systems with a blocksize smaller than
the page size, but that support will be added later.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c            | 214 +++++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/iomap.h |   3 +
 2 files changed, 216 insertions(+), 1 deletion(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index a1f71e64ea49..4f10c6b1cf6d 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (c) 2016 Christoph Hellwig.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -18,6 +18,7 @@
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
+#include <linux/mm_inline.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
@@ -123,6 +124,217 @@ iomap_read_inline_data(struct inode *inode, struct page *page,
 	SetPageUptodate(page);
 }
 
+static void
+iomap_read_end_io(struct bio *bio)
+{
+	int error = blk_status_to_errno(bio->bi_status);
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i)
+		page_endio(bvec->bv_page, false, error);
+	bio_put(bio);
+}
+
+struct iomap_readpage_ctx {
+	struct page		*cur_page;
+	bool			cur_page_in_bio;
+	bool			is_readahead;
+	struct bio		*bio;
+	struct list_head	*pages;
+};
+
+static loff_t
+iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
+		struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	struct page *page = ctx->cur_page;
+	unsigned poff = pos & (PAGE_SIZE - 1);
+	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
+	bool is_contig = false;
+	sector_t sector;
+
+	/* we don't support blocksize < PAGE_SIZE quite yet. */
+	WARN_ON_ONCE(pos != page_offset(page));
+	WARN_ON_ONCE(plen != PAGE_SIZE);
+
+	if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) {
+		zero_user(page, poff, plen);
+		SetPageUptodate(page);
+		goto done;
+	}
+
+	ctx->cur_page_in_bio = true;
+
+	/*
+	 * Try to merge into a previous segment if we can.
+	 */
+	sector = iomap_sector(iomap, pos);
+	if (ctx->bio && bio_end_sector(ctx->bio) == sector) {
+		if (__bio_try_merge_page(ctx->bio, page, plen, poff))
+			goto done;
+		is_contig = true;
+	}
+
+	if (!ctx->bio || !is_contig || bio_full(ctx->bio)) {
+		gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
+		int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
+
+		if (ctx->bio)
+			submit_bio(ctx->bio);
+
+		if (ctx->is_readahead) /* same as readahead_gfp_mask */
+			gfp |= __GFP_NORETRY | __GFP_NOWARN;
+		ctx->bio = bio_alloc(gfp, min(BIO_MAX_PAGES, nr_vecs));
+		ctx->bio->bi_opf = REQ_OP_READ;
+		if (ctx->is_readahead)
+			ctx->bio->bi_opf |= REQ_RAHEAD;
+		ctx->bio->bi_iter.bi_sector = sector;
+		bio_set_dev(ctx->bio, iomap->bdev);
+		ctx->bio->bi_end_io = iomap_read_end_io;
+	}
+
+	__bio_add_page(ctx->bio, page, plen, poff);
+done:
+	return plen;
+}
+
+int
+iomap_readpage(struct page *page, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = { .cur_page = page };
+	struct inode *inode = page->mapping->host;
+	unsigned poff;
+	loff_t ret;
+
+	WARN_ON_ONCE(page_has_buffers(page));
+
+	for (poff = 0; poff < PAGE_SIZE; poff += ret) {
+		ret = iomap_apply(inode, page_offset(page) + poff,
+				PAGE_SIZE - poff, 0, ops, &ctx,
+				iomap_readpage_actor);
+		if (ret <= 0) {
+			WARN_ON_ONCE(ret == 0);
+			SetPageError(page);
+			break;
+		}
+	}
+
+	if (ctx.bio) {
+		submit_bio(ctx.bio);
+		WARN_ON_ONCE(!ctx.cur_page_in_bio);
+	} else {
+		WARN_ON_ONCE(ctx.cur_page_in_bio);
+		unlock_page(page);
+	}
+
+	/*
+	 * Just like mpage_readpages and block_read_full_page we always
+	 * return 0 and just mark the page as PageError on errors.  This
+	 * should be cleaned up all through the stack eventually.
+	 */
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_readpage);
+
+static struct page *
+iomap_next_page(struct inode *inode, struct list_head *pages, loff_t pos,
+		loff_t length, loff_t *done)
+{
+	while (!list_empty(pages)) {
+		struct page *page = lru_to_page(pages);
+
+		if (page_offset(page) >= (u64)pos + length)
+			break;
+
+		list_del(&page->lru);
+		if (!add_to_page_cache_lru(page, inode->i_mapping, page->index,
+				GFP_NOFS))
+			return page;
+
+		/*
+		 * If we already have a page in the page cache at index we are
+		 * done.  Upper layers don't care if it is uptodate after the
+		 * readpages call itself as every page gets checked again once
+		 * actually needed.
+		 */
+		*done += PAGE_SIZE;
+		put_page(page);
+	}
+
+	return NULL;
+}
+
+static loff_t
+iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct iomap_readpage_ctx *ctx = data;
+	loff_t done, ret;
+
+	for (done = 0; done < length; done += ret) {
+		if (ctx->cur_page && ((pos + done) & (PAGE_SIZE - 1)) == 0) {
+			if (!ctx->cur_page_in_bio)
+				unlock_page(ctx->cur_page);
+			put_page(ctx->cur_page);
+			ctx->cur_page = NULL;
+		}
+		if (!ctx->cur_page) {
+			ctx->cur_page = iomap_next_page(inode, ctx->pages,
+					pos, length, &done);
+			if (!ctx->cur_page)
+				break;
+			ctx->cur_page_in_bio = false;
+		}
+		ret = iomap_readpage_actor(inode, pos + done, length - done,
+				ctx, iomap);
+	}
+
+	return done;
+}
+
+int
+iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops)
+{
+	struct iomap_readpage_ctx ctx = {
+		.pages		= pages,
+		.is_readahead	= true,
+	};
+	loff_t pos = page_offset(list_entry(pages->prev, struct page, lru));
+	loff_t last = page_offset(list_entry(pages->next, struct page, lru));
+	loff_t length = last - pos + PAGE_SIZE, ret = 0;
+
+	while (length > 0) {
+		ret = iomap_apply(mapping->host, pos, length, 0, ops,
+				&ctx, iomap_readpages_actor);
+		if (ret <= 0) {
+			WARN_ON_ONCE(ret == 0);
+			goto done;
+		}
+		pos += ret;
+		length -= ret;
+	}
+	ret = 0;
+done:
+	if (ctx.bio)
+		submit_bio(ctx.bio);
+	if (ctx.cur_page) {
+		if (!ctx.cur_page_in_bio)
+			unlock_page(ctx.cur_page);
+		put_page(ctx.cur_page);
+	}
+
+	/*
+	 * Check that we didn't lose a page due to the arcance calling
+	 * conventions..
+	 */
+	WARN_ON_ONCE(!ret && !list_empty(ctx.pages));
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iomap_readpages);
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 1f36523d448a..30d314407f66 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -99,6 +99,9 @@ struct iomap_ops {
 
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
+int iomap_readpage(struct page *page, const struct iomap_ops *ops);
+int iomap_readpages(struct address_space *mapping, struct list_head *pages,
+		unsigned nr_pages, const struct iomap_ops *ops);
 int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-- 
cgit v1.2.3


From e184fde6f3f5353040dd4b5637f823fc87436e55 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 19 Jun 2018 15:10:57 -0700
Subject: iomap: add private pointer to struct iomap

Add a private pointer to struct iomap to allow filesystems to pass data
from iomap_begin to iomap_end.  Will be used by gfs2 for passing on the
on-disk inode buffer head.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 include/linux/iomap.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 45f43865b0f0..1f36523d448a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -57,6 +57,7 @@ struct iomap {
 	struct block_device	*bdev;	/* block device for I/O */
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
 	void			*inline_data;
+	void			*private; /* filesystem private */
 
 	/*
 	 * Called when finished processing a page in the mapping returned in
-- 
cgit v1.2.3


From a81dde7e0216d2520f04027d0dfbb94d9713e8b4 Mon Sep 17 00:00:00 2001
From: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Date: Thu, 7 Jun 2018 13:54:41 +0530
Subject: scsi: be2iscsi: Include null char in SET_HOST_DATA

FW needs NULL terminated driver version string.

Signed-off-by: Ketan Mukadam <ketan.mukadam@broadcom.com>
Reviewed-by: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Signed-off-by: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/be2iscsi/be_cmds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/be2iscsi/be_cmds.c b/drivers/scsi/be2iscsi/be_cmds.c
index 2eb66df3e3d6..c10aac4dbc5e 100644
--- a/drivers/scsi/be2iscsi/be_cmds.c
+++ b/drivers/scsi/be2iscsi/be_cmds.c
@@ -1545,7 +1545,7 @@ int beiscsi_set_host_data(struct beiscsi_hba *phba)
 		snprintf((char *)ioctl->param.req.param_data,
 			 sizeof(ioctl->param.req.param_data),
 			 "Linux iSCSI v%s", BUILD_STR);
-	ioctl->param.req.param_len = ALIGN(ioctl->param.req.param_len, 4);
+	ioctl->param.req.param_len = ALIGN(ioctl->param.req.param_len + 1, 4);
 	if (ioctl->param.req.param_len > BE_CMD_MAX_DRV_VERSION)
 		ioctl->param.req.param_len = BE_CMD_MAX_DRV_VERSION;
 	ret = be_mbox_notify(ctrl);
-- 
cgit v1.2.3


From 9458321750cbfdaf9fd3cb95194f37c52e0cb356 Mon Sep 17 00:00:00 2001
From: Ketan Mukadam <ketan.mukadam@broadcom.com>
Date: Thu, 7 Jun 2018 13:54:43 +0530
Subject: scsi: be2iscsi: Update copyright

Update Broadcom copyright markings in all modified files.

Signed-off-by: Ketan Mukadam <ketan.mukadam@broadcom.com>
Reviewed-by: Jitendra Bhivare <jitendra.bhivare@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/be2iscsi/be_iscsi.c | 15 +++++++++------
 drivers/scsi/be2iscsi/be_main.c  | 23 +++++++++++++++++------
 drivers/scsi/be2iscsi/be_mgmt.c  | 23 +++++++++++++++++------
 3 files changed, 43 insertions(+), 18 deletions(-)

diff --git a/drivers/scsi/be2iscsi/be_iscsi.c b/drivers/scsi/be2iscsi/be_iscsi.c
index a398c54139aa..c8f0a2144b44 100644
--- a/drivers/scsi/be2iscsi/be_iscsi.c
+++ b/drivers/scsi/be2iscsi/be_iscsi.c
@@ -1,11 +1,14 @@
 /*
- * Copyright 2017 Broadcom. All Rights Reserved.
- * The term "Broadcom" refers to Broadcom Limited and/or its subsidiaries.
+ * This file is part of the Emulex Linux Device Driver for Enterprise iSCSI
+ * Host Bus Adapters. Refer to the README file included with this package
+ * for driver version and adapter compatibility.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
+ * Copyright (c) 2018 Broadcom. All Rights Reserved.
+ * The term "Broadcom" refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as published
+ * by the Free Software Foundation.
  *
  * Contact Information:
  * linux-drivers@broadcom.com
diff --git a/drivers/scsi/be2iscsi/be_main.c b/drivers/scsi/be2iscsi/be_main.c
index 818d185d63f0..3660059784f7 100644
--- a/drivers/scsi/be2iscsi/be_main.c
+++ b/drivers/scsi/be2iscsi/be_main.c
@@ -1,11 +1,22 @@
 /*
- * Copyright 2017 Broadcom. All Rights Reserved.
- * The term "Broadcom" refers to Broadcom Limited and/or its subsidiaries.
+ * This file is part of the Emulex Linux Device Driver for Enterprise iSCSI
+ * Host Bus Adapters. Refer to the README file included with this package
+ * for driver version and adapter compatibility.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
+ * Copyright (c) 2018 Broadcom. All Rights Reserved.
+ * The term “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful. ALL EXPRESS
+ * OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING ANY
+ * IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE,
+ * OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH
+ * DISCLAIMERS ARE HELD TO BE LEGALLY INVALID.
+ * See the GNU General Public License for more details, a copy of which
+ * can be found in the file COPYING included with this package.
  *
  * Contact Information:
  * linux-drivers@broadcom.com
diff --git a/drivers/scsi/be2iscsi/be_mgmt.c b/drivers/scsi/be2iscsi/be_mgmt.c
index 66ca967f2850..8fdc07b6c686 100644
--- a/drivers/scsi/be2iscsi/be_mgmt.c
+++ b/drivers/scsi/be2iscsi/be_mgmt.c
@@ -1,11 +1,22 @@
 /*
- * Copyright 2017 Broadcom. All Rights Reserved.
- * The term "Broadcom" refers to Broadcom Limited and/or its subsidiaries.
+ * This file is part of the Emulex Linux Device Driver for Enterprise iSCSI
+ * Host Bus Adapters. Refer to the README file included with this package
+ * for driver version and adapter compatibility.
  *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version 2
- * as published by the Free Software Foundation. The full GNU General
- * Public License is included in this distribution in the file called COPYING.
+ * Copyright (c) 2018 Broadcom. All Rights Reserved.
+ * The term “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of version 2 of the GNU General Public License as published
+ * by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful. ALL EXPRESS
+ * OR IMPLIED CONDITIONS, REPRESENTATIONS AND WARRANTIES, INCLUDING ANY
+ * IMPLIED WARRANTY OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE,
+ * OR NON-INFRINGEMENT, ARE DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH
+ * DISCLAIMERS ARE HELD TO BE LEGALLY INVALID.
+ * See the GNU General Public License for more details, a copy of which
+ * can be found in the file COPYING included with this package.
  *
  * Contact Information:
  * linux-drivers@broadcom.com
-- 
cgit v1.2.3


From 4e63ac82b9f020f348ab6c9f062d2fbd2dcd0b7e Mon Sep 17 00:00:00 2001
From: Xiang Chen <chenxiang66@hisilicon.com>
Date: Thu, 31 May 2018 20:50:42 +0800
Subject: scsi: hisi_sas: Use dmam_alloc_coherent()

This patch replaces the usage of dma_alloc_coherent() with the managed
version, dmam_alloc_coherent(), hereby reducing replicated code.

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by; John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 80 +++++++++--------------------------
 1 file changed, 20 insertions(+), 60 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 6f562974f8f6..1c424bb363fd 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -2045,15 +2045,17 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 
 		/* Delivery queue */
 		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->cmd_hdr[i] = dma_alloc_coherent(dev, s,
-					&hisi_hba->cmd_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->cmd_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->cmd_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->cmd_hdr[i])
 			goto err_out;
 
 		/* Completion queue */
 		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		hisi_hba->complete_hdr[i] = dma_alloc_coherent(dev, s,
-				&hisi_hba->complete_hdr_dma[i], GFP_KERNEL);
+		hisi_hba->complete_hdr[i] = dmam_alloc_coherent(dev, s,
+						&hisi_hba->complete_hdr_dma[i],
+						GFP_KERNEL);
 		if (!hisi_hba->complete_hdr[i])
 			goto err_out;
 	}
@@ -2064,10 +2066,11 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	hisi_hba->itct = dma_zalloc_coherent(dev, s, &hisi_hba->itct_dma,
-					    GFP_KERNEL);
+	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->itct)
 		goto err_out;
+	memset(hisi_hba->itct, 0, s);
 
 	hisi_hba->slot_info = devm_kcalloc(dev, max_command_entries,
 					   sizeof(struct hisi_sas_slot),
@@ -2076,14 +2079,15 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	hisi_hba->iost = dma_alloc_coherent(dev, s, &hisi_hba->iost_dma,
-					    GFP_KERNEL);
+	hisi_hba->iost = dmam_alloc_coherent(dev, s, &hisi_hba->iost_dma,
+					     GFP_KERNEL);
 	if (!hisi_hba->iost)
 		goto err_out;
 
 	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	hisi_hba->breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->breakpoint_dma, GFP_KERNEL);
+	hisi_hba->breakpoint = dmam_alloc_coherent(dev, s,
+						   &hisi_hba->breakpoint_dma,
+						   GFP_KERNEL);
 	if (!hisi_hba->breakpoint)
 		goto err_out;
 
@@ -2094,14 +2098,16 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 		goto err_out;
 
 	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	hisi_hba->initial_fis = dma_alloc_coherent(dev, s,
-				&hisi_hba->initial_fis_dma, GFP_KERNEL);
+	hisi_hba->initial_fis = dmam_alloc_coherent(dev, s,
+						    &hisi_hba->initial_fis_dma,
+						    GFP_KERNEL);
 	if (!hisi_hba->initial_fis)
 		goto err_out;
 
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	hisi_hba->sata_breakpoint = dma_alloc_coherent(dev, s,
-				&hisi_hba->sata_breakpoint_dma, GFP_KERNEL);
+	hisi_hba->sata_breakpoint = dmam_alloc_coherent(dev, s,
+					&hisi_hba->sata_breakpoint_dma,
+					GFP_KERNEL);
 	if (!hisi_hba->sata_breakpoint)
 		goto err_out;
 	hisi_sas_init_mem(hisi_hba);
@@ -2122,54 +2128,8 @@ EXPORT_SYMBOL_GPL(hisi_sas_alloc);
 
 void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
-
-	for (i = 0; i < hisi_hba->queue_count; i++) {
-		s = sizeof(struct hisi_sas_cmd_hdr) * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->cmd_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->cmd_hdr[i],
-					  hisi_hba->cmd_hdr_dma[i]);
-
-		s = hisi_hba->hw->complete_hdr_size * HISI_SAS_QUEUE_SLOTS;
-		if (hisi_hba->complete_hdr[i])
-			dma_free_coherent(dev, s,
-					  hisi_hba->complete_hdr[i],
-					  hisi_hba->complete_hdr_dma[i]);
-	}
-
 	dma_pool_destroy(hisi_hba->buffer_pool);
 
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
-	if (hisi_hba->itct)
-		dma_free_coherent(dev, s,
-				  hisi_hba->itct, hisi_hba->itct_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_iost);
-	if (hisi_hba->iost)
-		dma_free_coherent(dev, s,
-				  hisi_hba->iost, hisi_hba->iost_dma);
-
-	s = max_command_entries * sizeof(struct hisi_sas_breakpoint);
-	if (hisi_hba->breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->breakpoint,
-				  hisi_hba->breakpoint_dma);
-
-
-	s = sizeof(struct hisi_sas_initial_fis) * HISI_SAS_MAX_PHYS;
-	if (hisi_hba->initial_fis)
-		dma_free_coherent(dev, s,
-				  hisi_hba->initial_fis,
-				  hisi_hba->initial_fis_dma);
-
-	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_sata_breakpoint);
-	if (hisi_hba->sata_breakpoint)
-		dma_free_coherent(dev, s,
-				  hisi_hba->sata_breakpoint,
-				  hisi_hba->sata_breakpoint_dma);
-
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
-- 
cgit v1.2.3


From 1324ae1ce55927622b531cc3123387c0fe05244d Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Thu, 31 May 2018 20:50:43 +0800
Subject: scsi: hisi_sas: Only process broadcast change in phy_bcast_v3_hw()

There are many BROADCAST primitives generated by the host. We are only
interested in BROADCAST (CHANGE) primitives currently, so only process
this.

We have applied this processing for v2 hw before, and it is also needed for
v3 hw.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 9f1e2d03f914..0a126a8285c6 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -131,6 +131,9 @@
 #define SL_CONTROL_NOTIFY_EN_MSK	(0x1 << SL_CONTROL_NOTIFY_EN_OFF)
 #define SL_CTA_OFF		17
 #define SL_CTA_MSK		(0x1 << SL_CTA_OFF)
+#define RX_PRIMS_STATUS			(PORT_BASE + 0x98)
+#define RX_BCAST_CHG_OFF		1
+#define RX_BCAST_CHG_MSK		(0x1 << RX_BCAST_CHG_OFF)
 #define TX_ID_DWORD0			(PORT_BASE + 0x9c)
 #define TX_ID_DWORD1			(PORT_BASE + 0xa0)
 #define TX_ID_DWORD2			(PORT_BASE + 0xa4)
@@ -1256,9 +1259,12 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct asd_sas_phy *sas_phy = &phy->sas_phy;
 	struct sas_ha_struct *sas_ha = &hisi_hba->sha;
+	u32 bcast_status;
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
-	sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
+	if (bcast_status & RX_BCAST_CHG_MSK)
+		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 0);
-- 
cgit v1.2.3


From d2fc401e47529d9ffd2673a5395d56002e31ad98 Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Thu, 31 May 2018 20:50:44 +0800
Subject: scsi: hisi_sas: Fix the conflict between dev gone and host reset

There is a possible conflict when a device is removed and host reset occurs
concurrently.

The reason is that then the device is notified as gone, we try to clear the
ITCT, which is notified via an interrupt. The dev gone function pends on
this event with a completion, which is completed when the ITCT interrupt
occurs.

But host reset will disable all interrupts, the wait_for_completion() may
wait indefinitely.

This patch adds an semaphore to synchronise this two processes. The
semaphore is taken by the host reset as the basis of synchronising.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h      | 1 +
 drivers/scsi/hisi_sas/hisi_sas_main.c | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 7052a5d45f7f..78e5a9254143 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -277,6 +277,7 @@ struct hisi_hba {
 
 	int n_phy;
 	spinlock_t lock;
+	struct semaphore sem;
 
 	struct timer_list timer;
 	struct workqueue_struct *wq;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 1c424bb363fd..823386ff940c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -914,7 +914,9 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 
 		hisi_sas_dereg_device(hisi_hba, device);
 
+		down(&hisi_hba->sem);
 		hisi_hba->hw->clear_itct(hisi_hba, sas_dev);
+		up(&hisi_hba->sem);
 		device->lldd_dev = NULL;
 	}
 
@@ -1364,6 +1366,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		return -1;
 
+	down(&hisi_hba->sem);
 	dev_info(dev, "controller resetting...\n");
 	old_state = hisi_hba->hw->get_phys_state(hisi_hba);
 
@@ -1378,6 +1381,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	if (rc) {
 		dev_warn(dev, "controller reset failed (%d)\n", rc);
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+		up(&hisi_hba->sem);
 		scsi_unblock_requests(shost);
 		goto out;
 	}
@@ -1388,6 +1392,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	hisi_hba->hw->phys_init(hisi_hba);
 	msleep(1000);
 	hisi_sas_refresh_port_id(hisi_hba);
+	up(&hisi_hba->sem);
 
 	if (hisi_hba->reject_stp_links_msk)
 		hisi_sas_terminate_stp_reject(hisi_hba);
@@ -2016,6 +2021,7 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	struct device *dev = hisi_hba->dev;
 	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
+	sema_init(&hisi_hba->sem, 1);
 	spin_lock_init(&hisi_hba->lock);
 	for (i = 0; i < hisi_hba->n_phy; i++) {
 		hisi_sas_phy_init(hisi_hba, i);
-- 
cgit v1.2.3


From 214e702d4b70b6ca7c8a57ff89e1990a76d12f82 Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Thu, 31 May 2018 20:50:45 +0800
Subject: scsi: hisi_sas: Adjust task reject period during host reset

After soft_reset() for host reset, we should not be allowed to send
commands to the HW before the PHYs have come up and the port ids have been
refreshed.

Prior to this point, any commands cannot be successfully completed.

This exclusion is achieved by grabbing the host reset semaphore.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 21 ++++++++++++---------
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c |  4 +++-
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 823386ff940c..090d3e0b1a00 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -536,8 +536,13 @@ static int hisi_sas_task_exec(struct sas_task *task, gfp_t gfp_flags,
 	struct device *dev = hisi_hba->dev;
 	struct hisi_sas_dq *dq = NULL;
 
-	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags)))
-		return -EINVAL;
+	if (unlikely(test_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags))) {
+		if (in_softirq())
+			return -EINVAL;
+
+		down(&hisi_hba->sem);
+		up(&hisi_hba->sem);
+	}
 
 	/* protect task_prep and start_delivery sequence */
 	rc = hisi_sas_task_prep(task, &dq, is_tmf, tmf, &pass);
@@ -1383,30 +1388,28 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 		up(&hisi_hba->sem);
 		scsi_unblock_requests(shost);
-		goto out;
+		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+		return rc;
 	}
 
-	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
-
 	/* Init and wait for PHYs to come up and all libsas event finished. */
 	hisi_hba->hw->phys_init(hisi_hba);
 	msleep(1000);
 	hisi_sas_refresh_port_id(hisi_hba);
+	clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	up(&hisi_hba->sem);
 
 	if (hisi_hba->reject_stp_links_msk)
 		hisi_sas_terminate_stp_reject(hisi_hba);
 	hisi_sas_reset_init_all_devices(hisi_hba);
 	scsi_unblock_requests(shost);
+	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
 
 	state = hisi_hba->hw->get_phys_state(hisi_hba);
 	hisi_sas_rescan_topology(hisi_hba, old_state, state);
 	dev_info(dev, "controller reset complete\n");
 
-out:
-	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
-
-	return rc;
+	return 0;
 }
 
 static int hisi_sas_abort_task(struct sas_task *task)
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 0a126a8285c6..c40fdb8d5c2c 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2459,7 +2459,9 @@ static int hisi_sas_v3_suspend(struct pci_dev *pdev, pm_message_t state)
 		return -ENODEV;
 	}
 
-	set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		return -1;
+
 	scsi_block_requests(shost);
 	set_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	flush_workqueue(hisi_hba->wq);
-- 
cgit v1.2.3


From ed99e1d94936bb33fc32d1f0151ae42c051e0d42 Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Thu, 31 May 2018 20:50:46 +0800
Subject: scsi: hisi_sas: Add a flag to filter PHY events during reset

During reset, we don't want PHY events reported to libsas for PHYs which
were previously attached prior to reset.

So check hisi_hba->flags for HISI_SAS_RESET_BIT to filter PHY events during
reset.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 3 ++-
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 ++-
 4 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 090d3e0b1a00..006e776ac115 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1927,7 +1927,8 @@ void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy)
 	} else {
 		struct hisi_sas_port *port  = phy->port;
 
-		if (phy->in_reset) {
+		if (test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags) ||
+		    phy->in_reset) {
 			dev_info(dev, "ignore flutter phy%d down\n", phy_no);
 			return;
 		}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 89ab18c1959c..32774427bbad 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1469,7 +1469,8 @@ static irqreturn_t int_bcast_v1_hw(int irq, void *p)
 		goto end;
 	}
 
-	sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
+	if (!test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		sha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 
 end:
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2,
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 213c530e63f2..159576e560d7 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -2840,7 +2840,8 @@ static void phy_bcast_v2_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
 	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
-	if (bcast_status & RX_BCAST_CHG_MSK)
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index c40fdb8d5c2c..e43881d0d7d2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1263,7 +1263,8 @@ static irqreturn_t phy_bcast_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 
 	hisi_sas_phy_write32(hisi_hba, phy_no, SL_RX_BCAST_CHK_MSK, 1);
 	bcast_status = hisi_sas_phy_read32(hisi_hba, phy_no, RX_PRIMS_STATUS);
-	if (bcast_status & RX_BCAST_CHG_MSK)
+	if ((bcast_status & RX_BCAST_CHG_MSK) &&
+	    !test_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
 		sas_ha->notify_port_event(sas_phy, PORTE_BROADCAST_RCVD);
 	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT0,
 			     CHL_INT0_SL_RX_BCST_ACK_MSK);
-- 
cgit v1.2.3


From f2ae8d04327f14ff93a263af265bc91c689c208e Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Thu, 31 May 2018 20:50:47 +0800
Subject: scsi: hisi_sas: Release all remaining resources in clear nexus ha

In host reset, we use TMF or soft-reset to re-init device, and if success,
we will release all LLDD resources of this device. If the init fails -
maybe because the device was removed or link has not come up - then do not
release the LLDD resources, but rather rely on SCSI EH to handle the
timeout for these resources later on.

But if clear nexus ha calls host reset, which is the last effort of SCSI
EH, we should release all LLDD remain resources. Because SCSI EH will
release all tasks after clear nexus ha.

Before release, we do I_T nexus reset to try to clear target remain IOs.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 006e776ac115..da1d5fe6d2c9 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1652,14 +1652,32 @@ out:
 static int hisi_sas_clear_nexus_ha(struct sas_ha_struct *sas_ha)
 {
 	struct hisi_hba *hisi_hba = sas_ha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
 	HISI_SAS_DECLARE_RST_WORK_ON_STACK(r);
+	int rc, i;
 
 	queue_work(hisi_hba->wq, &r.work);
 	wait_for_completion(r.completion);
-	if (r.done)
-		return TMF_RESP_FUNC_COMPLETE;
+	if (!r.done)
+		return TMF_RESP_FUNC_FAILED;
+
+	for (i = 0; i < HISI_SAS_MAX_DEVICES; i++) {
+		struct hisi_sas_device *sas_dev = &hisi_hba->devices[i];
+		struct domain_device *device = sas_dev->sas_device;
+
+		if ((sas_dev->dev_type == SAS_PHY_UNUSED) || !device ||
+		    DEV_IS_EXPANDER(device->dev_type))
+			continue;
+
+		rc = hisi_sas_debug_I_T_nexus_reset(device);
+		if (rc != TMF_RESP_FUNC_COMPLETE)
+			dev_info(dev, "clear nexus ha: for device[%d] rc=%d\n",
+				 sas_dev->device_id, rc);
+	}
+
+	hisi_sas_release_tasks(hisi_hba);
 
-	return TMF_RESP_FUNC_FAILED;
+	return TMF_RESP_FUNC_COMPLETE;
 }
 
 static int hisi_sas_query_task(struct sas_task *task)
-- 
cgit v1.2.3


From 2ba5afb6834b876c1547fa7d714ddca8a8039b36 Mon Sep 17 00:00:00 2001
From: Xiang Chen <chenxiang66@hisilicon.com>
Date: Thu, 31 May 2018 20:50:48 +0800
Subject: scsi: hisi_sas: Pre-allocate slot DMA buffers

Currently the driver spends much time allocating and freeing the slot DMA
buffer for command delivery/completion. To boost the performance,
pre-allocate the buffers for all IPTT. The downside of this approach is
that we are reallocating all buffer memory upfront, so hog memory which we
may not need.

However, the current method - DMA buffer pool - also caches all buffers and
does not free them until the pool is destroyed, so is not exactly efficient
either.

On top of this, since the slot DMA buffer is slightly bigger than a 4K
page, we need to allocate 2x4K pages per buffer (for 4K page kernel), which
is quite wasteful. For 64K page size this is not such an issue.

So, for the 4K page case, in order to make memory usage more efficient,
pre-allocating larger blocks of DMA memory for the buffers can be more
efficient.

To make DMA memory usage most efficient, we would choose a single
contiguous DMA memory block, but this could use up all the DMA memory in
the system (when CMA enabled and no IOMMU), or we may just not be able to
allocate a DMA buffer large enough when no CMA or IOMMU.

To decide the block size we use the LCM (least common multiple) of the
buffer size and the page size. We roundup(64) to ensure the LCM is not too
large, even though a little memory may be wasted per block.

So, with this, the total memory requirement is about is about 17MB for 4096
max IPTT.

Previously (for 4K pages case), it would be 32MB (for all slots
allocated).

With this change, the relative increase of IOPS for bs=4K read when
PAGE_SIZE=4K and PAGE_SIZE=64K is as follows:
    IODEPTH     4K PAGE_SIZE      64K PAGE_SIZE
    32          56%               47%
    64          53%               44%
    128         64%               43%
    256         67%               45%

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h      |  9 ++--
 drivers/scsi/hisi_sas/hisi_sas_main.c | 78 +++++++++++++++++------------------
 2 files changed, 42 insertions(+), 45 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 78e5a9254143..beda41238285 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -16,6 +16,7 @@
 #include <linux/clk.h>
 #include <linux/dmapool.h>
 #include <linux/iopoll.h>
+#include <linux/lcm.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
@@ -199,17 +200,18 @@ struct hisi_sas_slot {
 	int	dlvry_queue_slot;
 	int	cmplt_queue;
 	int	cmplt_queue_slot;
-	int	idx;
 	int	abort;
 	int	ready;
-	void	*buf;
-	dma_addr_t buf_dma;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
 	struct work_struct abort_slot;
 	struct timer_list internal_abort_timer;
 	bool is_internal;
 	struct hisi_sas_tmf_task *tmf;
+	/* Do not reorder/change members after here */
+	void	*buf;
+	dma_addr_t buf_dma;
+	int	idx;
 };
 
 struct hisi_sas_hw {
@@ -299,7 +301,6 @@ struct hisi_hba {
 
 	int	queue_count;
 
-	struct dma_pool *buffer_pool;
 	struct hisi_sas_device	devices[HISI_SAS_MAX_DEVICES];
 	struct hisi_sas_cmd_hdr	*cmd_hdr[HISI_SAS_MAX_QUEUES];
 	dma_addr_t cmd_hdr_dma[HISI_SAS_MAX_QUEUES];
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index da1d5fe6d2c9..20aab1079e4e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -242,20 +242,16 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task,
 					     task->data_dir);
 	}
 
-	if (slot->buf)
-		dma_pool_free(hisi_hba->buffer_pool, slot->buf, slot->buf_dma);
 
 	spin_lock_irqsave(&dq->lock, flags);
 	list_del_init(&slot->entry);
 	spin_unlock_irqrestore(&dq->lock, flags);
-	slot->buf = NULL;
-	slot->task = NULL;
-	slot->port = NULL;
+
+	memset(slot, 0, offsetof(struct hisi_sas_slot, buf));
+
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot->idx);
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
-
-	/* slot memory is fully zeroed when it is reused */
 }
 EXPORT_SYMBOL_GPL(hisi_sas_slot_task_free);
 
@@ -430,21 +426,13 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		goto err_out_dma_unmap;
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-				   GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
 	spin_lock_irqsave(&dq->lock, flags_dq);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
 		spin_unlock_irqrestore(&dq->lock, flags_dq);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 
 	list_add_tail(&slot->delivery, &dq->list);
@@ -453,7 +441,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -500,9 +487,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -1749,21 +1733,13 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	spin_unlock_irqrestore(&hisi_hba->lock, flags);
 
 	slot = &hisi_hba->slot_info[slot_idx];
-	memset(slot, 0, sizeof(struct hisi_sas_slot));
-
-	slot->buf = dma_pool_alloc(hisi_hba->buffer_pool,
-			GFP_ATOMIC, &slot->buf_dma);
-	if (!slot->buf) {
-		rc = -ENOMEM;
-		goto err_out_tag;
-	}
 
 	spin_lock_irqsave(&dq->lock, flags_dq);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
 		spin_unlock_irqrestore(&dq->lock, flags_dq);
 		rc = -EAGAIN;
-		goto err_out_buf;
+		goto err_out_tag;
 	}
 	list_add_tail(&slot->delivery, &dq->list);
 	spin_unlock_irqrestore(&dq->lock, flags_dq);
@@ -1771,7 +1747,6 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
 
-	slot->idx = slot_idx;
 	slot->n_elem = n_elem;
 	slot->dlvry_queue = dlvry_queue;
 	slot->dlvry_queue_slot = dlvry_queue_slot;
@@ -1802,9 +1777,6 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 
 	return 0;
 
-err_out_buf:
-	dma_pool_free(hisi_hba->buffer_pool, slot->buf,
-		      slot->buf_dma);
 err_out_tag:
 	spin_lock_irqsave(&hisi_hba->lock, flags);
 	hisi_sas_slot_index_free(hisi_hba, slot_idx);
@@ -2041,7 +2013,9 @@ EXPORT_SYMBOL_GPL(hisi_sas_init_mem);
 int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 {
 	struct device *dev = hisi_hba->dev;
-	int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int i, j, s, max_command_entries = hisi_hba->hw->max_command_entries;
+	int max_command_entries_ru, sz_slot_buf_ru;
+	int blk_cnt, slots_per_blk;
 
 	sema_init(&hisi_hba->sem, 1);
 	spin_lock_init(&hisi_hba->lock);
@@ -2088,11 +2062,6 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 			goto err_out;
 	}
 
-	s = sizeof(struct hisi_sas_slot_buf_table);
-	hisi_hba->buffer_pool = dma_pool_create("dma_buffer", dev, s, 16, 0);
-	if (!hisi_hba->buffer_pool)
-		goto err_out;
-
 	s = HISI_SAS_MAX_ITCT_ENTRIES * sizeof(struct hisi_sas_itct);
 	hisi_hba->itct = dmam_alloc_coherent(dev, s, &hisi_hba->itct_dma,
 					     GFP_KERNEL);
@@ -2106,6 +2075,35 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
 	if (!hisi_hba->slot_info)
 		goto err_out;
 
+	/* roundup to avoid overly large block size */
+	max_command_entries_ru = roundup(max_command_entries, 64);
+	sz_slot_buf_ru = roundup(sizeof(struct hisi_sas_slot_buf_table), 64);
+	s = lcm(max_command_entries_ru, sz_slot_buf_ru);
+	blk_cnt = (max_command_entries_ru * sz_slot_buf_ru) / s;
+	slots_per_blk = s / sz_slot_buf_ru;
+	for (i = 0; i < blk_cnt; i++) {
+		struct hisi_sas_slot_buf_table *buf;
+		dma_addr_t buf_dma;
+		int slot_index = i * slots_per_blk;
+
+		buf = dmam_alloc_coherent(dev, s, &buf_dma, GFP_KERNEL);
+		if (!buf)
+			goto err_out;
+		memset(buf, 0, s);
+
+		for (j = 0; j < slots_per_blk; j++, slot_index++) {
+			struct hisi_sas_slot *slot;
+
+			slot = &hisi_hba->slot_info[slot_index];
+			slot->buf = buf;
+			slot->buf_dma = buf_dma;
+			slot->idx = slot_index;
+
+			buf++;
+			buf_dma += sizeof(*buf);
+		}
+	}
+
 	s = max_command_entries * sizeof(struct hisi_sas_iost);
 	hisi_hba->iost = dmam_alloc_coherent(dev, s, &hisi_hba->iost_dma,
 					     GFP_KERNEL);
@@ -2156,8 +2154,6 @@ EXPORT_SYMBOL_GPL(hisi_sas_alloc);
 
 void hisi_sas_free(struct hisi_hba *hisi_hba)
 {
-	dma_pool_destroy(hisi_hba->buffer_pool);
-
 	if (hisi_hba->wq)
 		destroy_workqueue(hisi_hba->wq);
 }
-- 
cgit v1.2.3


From ce70c2e6af8e9bb823b5e2183f3b777e9a5e7259 Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Thu, 31 May 2018 20:50:49 +0800
Subject: scsi: hisi_sas: Add missing PHY spinlock init

The init is missed for hisi_sas_phy spinlock, so add it.

Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 20aab1079e4e..781b2af483a2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -808,6 +808,8 @@ static void hisi_sas_phy_init(struct hisi_hba *hisi_hba, int phy_no)
 
 	for (i = 0; i < HISI_PHYES_NUM; i++)
 		INIT_WORK(&phy->works[i], hisi_sas_phye_fns[i]);
+
+	spin_lock_init(&phy->lock);
 }
 
 static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy)
-- 
cgit v1.2.3


From 7931cd918f35e1e7c9183f004f4b90b43f22adfd Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Thu, 31 May 2018 20:50:50 +0800
Subject: scsi: hisi_sas: Update a couple of register settings for v3 hw

Update CFG_1US_TIMER_TRSH and CON_CFG_DRIVER settings.

Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index e43881d0d7d2..4b7688a856af 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -51,7 +51,6 @@
 #define CFG_ABT_SET_IPTT_DONE	0xd8
 #define CFG_ABT_SET_IPTT_DONE_OFF	0
 #define HGC_IOMB_PROC1_STATUS	0x104
-#define CFG_1US_TIMER_TRSH		0xcc
 #define CHNL_INT_STATUS			0x148
 #define HGC_AXI_FIFO_ERR_INFO  0x154
 #define AXI_ERR_INFO_OFF               0
@@ -428,7 +427,6 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 			 (u32)((1ULL << hisi_hba->queue_count) - 1));
 	hisi_sas_write32(hisi_hba, CFG_MAX_TAG, 0xfff0400);
 	hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108);
-	hisi_sas_write32(hisi_hba, CFG_1US_TIMER_TRSH, 0xd);
 	hisi_sas_write32(hisi_hba, INT_COAL_EN, 0x1);
 	hisi_sas_write32(hisi_hba, OQ_INT_COAL_TIME, 0x1);
 	hisi_sas_write32(hisi_hba, OQ_INT_COAL_CNT, 0x1);
@@ -489,6 +487,7 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba)
 		hisi_sas_phy_write32(hisi_hba, i, SL_RX_BCAST_CHK_MSK, 0x0);
 		hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x1);
 		hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7f7a120);
+		hisi_sas_phy_write32(hisi_hba, i, CON_CFG_DRIVER, 0x2a0a01);
 
 		/* used for 12G negotiate */
 		hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e);
-- 
cgit v1.2.3


From 15c5a5e0761f9ace2e58097c405ab362b2e02c83 Mon Sep 17 00:00:00 2001
From: Wen Xiong <wenxiong@linux.vnet.ibm.com>
Date: Wed, 6 Jun 2018 10:01:36 -0500
Subject: scsi: ipr: Format HCAM overlay ID 0x41

This patch adds formatting error overlay 0x41 to improve debug
capabilities.

Signed-off-by: Wen Xiong <wenxiong@linux.vnet.ibm.com>
Acked-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ipr.c | 25 +++++++++++++++++++++++++
 drivers/scsi/ipr.h |  7 +++++++
 2 files changed, 32 insertions(+)

diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 0a9b8b387bd2..f796f0ec5ca9 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -2412,6 +2412,28 @@ static void ipr_log_sis64_fabric_error(struct ipr_ioa_cfg *ioa_cfg,
 	ipr_log_hex_data(ioa_cfg, (__be32 *)fabric, add_len);
 }
 
+/**
+ * ipr_log_sis64_service_required_error - Log a sis64 service required error.
+ * @ioa_cfg:    ioa config struct
+ * @hostrcb:    hostrcb struct
+ *
+ * Return value:
+ *      none
+ **/
+static void ipr_log_sis64_service_required_error(struct ipr_ioa_cfg *ioa_cfg,
+				       struct ipr_hostrcb *hostrcb)
+{
+	struct ipr_hostrcb_type_41_error *error;
+
+	error = &hostrcb->hcam.u.error64.u.type_41_error;
+
+	error->failure_reason[sizeof(error->failure_reason) - 1] = '\0';
+	ipr_err("Primary Failure Reason: %s\n", error->failure_reason);
+	ipr_log_hex_data(ioa_cfg, error->data,
+			 be32_to_cpu(hostrcb->hcam.length) -
+			 (offsetof(struct ipr_hostrcb_error, u) +
+			  offsetof(struct ipr_hostrcb_type_41_error, data)));
+}
 /**
  * ipr_log_generic_error - Log an adapter error.
  * @ioa_cfg:	ioa config struct
@@ -2587,6 +2609,9 @@ static void ipr_handle_log_data(struct ipr_ioa_cfg *ioa_cfg,
 	case IPR_HOST_RCB_OVERLAY_ID_30:
 		ipr_log_sis64_fabric_error(ioa_cfg, hostrcb);
 		break;
+	case IPR_HOST_RCB_OVERLAY_ID_41:
+		ipr_log_sis64_service_required_error(ioa_cfg, hostrcb);
+		break;
 	case IPR_HOST_RCB_OVERLAY_ID_1:
 	case IPR_HOST_RCB_OVERLAY_ID_DEFAULT:
 	default:
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 93570734cbfb..68afbbde54d3 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1135,6 +1135,11 @@ struct ipr_hostrcb_type_30_error {
 	struct ipr_hostrcb64_fabric_desc desc[1];
 }__attribute__((packed, aligned (4)));
 
+struct ipr_hostrcb_type_41_error {
+	u8 failure_reason[64];
+	 __be32 data[200];
+}__attribute__((packed, aligned (4)));
+
 struct ipr_hostrcb_error {
 	__be32 fd_ioasc;
 	struct ipr_res_addr fd_res_addr;
@@ -1173,6 +1178,7 @@ struct ipr_hostrcb64_error {
 		struct ipr_hostrcb_type_23_error type_23_error;
 		struct ipr_hostrcb_type_24_error type_24_error;
 		struct ipr_hostrcb_type_30_error type_30_error;
+		struct ipr_hostrcb_type_41_error type_41_error;
 	} u;
 }__attribute__((packed, aligned (8)));
 
@@ -1218,6 +1224,7 @@ struct ipr_hcam {
 #define IPR_HOST_RCB_OVERLAY_ID_24				0x24
 #define IPR_HOST_RCB_OVERLAY_ID_26				0x26
 #define IPR_HOST_RCB_OVERLAY_ID_30				0x30
+#define IPR_HOST_RCB_OVERLAY_ID_41				0x41
 #define IPR_HOST_RCB_OVERLAY_ID_DEFAULT				0xFF
 
 	u8 reserved1[3];
-- 
cgit v1.2.3


From 2da11d4262639dc0e2fabc6a70886db57af25c43 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 14 Jun 2018 18:18:09 +0200
Subject: scsi: libsas: remove irq save in sas_ata_qc_issue()

Since commit 312d3e56119a ("[SCSI] libsas: remove ata_port.lock management
duties from lldds") the sas_ata_qc_issue() function unlocks the
ata_port.lock and disables interrupts before doing so.  That lock is always
taken with disabled interrupts so at this point, the interrupts are already
disabled. There is no need to disable the interrupts before the unlock
operation because they are already disabled.  Restoring the interrupt state
later does not change anything because they were disabled and remain
disabled. Therefore remove the operations which do not change the
behaviour.

Fixes: 312d3e56119a ("[SCSI] libsas: remove ata_port.lock management duties from lldds")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libsas/sas_ata.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index ff1d612f6fb9..2ac7395112b4 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -176,7 +176,6 @@ qc_already_gone:
 
 static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 {
-	unsigned long flags;
 	struct sas_task *task;
 	struct scatterlist *sg;
 	int ret = AC_ERR_SYSTEM;
@@ -187,10 +186,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 	struct Scsi_Host *host = sas_ha->core.shost;
 	struct sas_internal *i = to_sas_internal(host->transportt);
 
-	/* TODO: audit callers to ensure they are ready for qc_issue to
-	 * unconditionally re-enable interrupts
-	 */
-	local_irq_save(flags);
+	/* TODO: we should try to remove that unlock */
 	spin_unlock(ap->lock);
 
 	/* If the device fell off, no sense in issuing commands */
@@ -252,7 +248,6 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
 
  out:
 	spin_lock(ap->lock);
-	local_irq_restore(flags);
 	return ret;
 }
 
-- 
cgit v1.2.3


From aa154ea885eb0c2407457ce9c1538d78c95456fa Mon Sep 17 00:00:00 2001
From: Zhouyang Jia <jiazhouyang09@gmail.com>
Date: Tue, 12 Jun 2018 11:13:00 +0800
Subject: scsi: bnx2i: add error handling for ioremap_nocache

When ioremap_nocache fails, the lack of error-handling code may cause
unexpected results.

This patch adds error-handling code after calling ioremap_nocache.

Signed-off-by: Zhouyang Jia <jiazhouyang09@gmail.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Acked-by: Manish Rangankar <Manish.Rangankar@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bnx2i/bnx2i_hwi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/bnx2i/bnx2i_hwi.c b/drivers/scsi/bnx2i/bnx2i_hwi.c
index 8f03a869ac98..e9e669a6c2bc 100644
--- a/drivers/scsi/bnx2i/bnx2i_hwi.c
+++ b/drivers/scsi/bnx2i/bnx2i_hwi.c
@@ -2727,6 +2727,8 @@ int bnx2i_map_ep_dbell_regs(struct bnx2i_endpoint *ep)
 					      BNX2X_DOORBELL_PCI_BAR);
 		reg_off = (1 << BNX2X_DB_SHIFT) * (cid_num & 0x1FFFF);
 		ep->qp.ctx_base = ioremap_nocache(reg_base + reg_off, 4);
+		if (!ep->qp.ctx_base)
+			return -ENOMEM;
 		goto arm_cq;
 	}
 
-- 
cgit v1.2.3


From 91ebc1facd7797d799a4c9208cb7fdc8d86e0bb4 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Wed, 13 Jun 2018 09:53:47 +0200
Subject: scsi: core: remove Scsi_Cmnd typedef

This will make subsequent refactoring easier to handle.

Note: this patch is nowhere checkpatch clean.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/3w-xxxx.c           |  2 +-
 drivers/scsi/advansys.c          |  2 +-
 drivers/scsi/aha152x.c           | 71 +++++++++++++++++++++-------------------
 drivers/scsi/aha1740.c           |  9 ++---
 drivers/scsi/aha1740.h           |  4 +--
 drivers/scsi/gdth.c              | 67 +++++++++++++++++++------------------
 drivers/scsi/gdth.h              | 10 +++---
 drivers/scsi/gdth_proc.c         |  2 +-
 drivers/scsi/ibmvscsi/ibmvfc.c   |  2 +-
 drivers/scsi/ibmvscsi/ibmvscsi.c |  2 +-
 drivers/scsi/libiscsi_tcp.c      |  2 +-
 drivers/scsi/megaraid.c          | 29 ++++++++--------
 drivers/scsi/megaraid.h          | 14 ++++----
 drivers/scsi/nsp32_debug.c       |  2 +-
 drivers/scsi/scsi.h              |  3 --
 drivers/scsi/scsi_typedefs.h     |  2 --
 16 files changed, 114 insertions(+), 109 deletions(-)
 delete mode 100644 drivers/scsi/scsi_typedefs.h

diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index f6179e3d6953..a40d353bd8b3 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -1925,7 +1925,7 @@ static int tw_scsi_queue_lck(struct scsi_cmnd *SCpnt, void (*done)(struct scsi_c
 	if (test_bit(TW_IN_RESET, &tw_dev->flags))
 		return SCSI_MLQUEUE_HOST_BUSY;
 
-	/* Save done function into Scsi_Cmnd struct */
+	/* Save done function into struct scsi_cmnd */
 	SCpnt->scsi_done = done;
 		 
 	/* Queue the command and get a request id */
diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index 24e57e770432..c9a52905070e 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -8466,7 +8466,7 @@ static int AdvExeScsiQueue(ADV_DVC_VAR *asc_dvc, adv_req_t *reqp)
 }
 
 /*
- * Execute a single 'Scsi_Cmnd'.
+ * Execute a single 'struct scsi_cmnd'.
  */
 static int asc_execute_scsi_cmnd(struct scsi_cmnd *scp)
 {
diff --git a/drivers/scsi/aha152x.c b/drivers/scsi/aha152x.c
index bc0058df31c6..4d7b0e0adbf7 100644
--- a/drivers/scsi/aha152x.c
+++ b/drivers/scsi/aha152x.c
@@ -422,16 +422,16 @@ enum aha152x_state {
  *
  */
 struct aha152x_hostdata {
-	Scsi_Cmnd *issue_SC;
+	struct scsi_cmnd *issue_SC;
 		/* pending commands to issue */
 
-	Scsi_Cmnd *current_SC;
+	struct scsi_cmnd *current_SC;
 		/* current command on the bus */
 
-	Scsi_Cmnd *disconnected_SC;
+	struct scsi_cmnd *disconnected_SC;
 		/* commands that disconnected */
 
-	Scsi_Cmnd *done_SC;
+	struct scsi_cmnd *done_SC;
 		/* command that was completed */
 
 	spinlock_t lock;
@@ -510,7 +510,7 @@ struct aha152x_hostdata {
  *
  */
 struct aha152x_scdata {
-	Scsi_Cmnd *next;	/* next sc in queue */
+	struct scsi_cmnd *next;	/* next sc in queue */
 	struct completion *done;/* semaphore to block on */
 	struct scsi_eh_save ses;
 };
@@ -633,7 +633,7 @@ static void aha152x_error(struct Scsi_Host *shpnt, char *msg);
 static void done(struct Scsi_Host *shpnt, int error);
 
 /* diagnostics */
-static void show_command(Scsi_Cmnd * ptr);
+static void show_command(struct scsi_cmnd * ptr);
 static void show_queues(struct Scsi_Host *shpnt);
 static void disp_enintr(struct Scsi_Host *shpnt);
 
@@ -642,9 +642,9 @@ static void disp_enintr(struct Scsi_Host *shpnt);
  *  queue services:
  *
  */
-static inline void append_SC(Scsi_Cmnd **SC, Scsi_Cmnd *new_SC)
+static inline void append_SC(struct scsi_cmnd **SC, struct scsi_cmnd *new_SC)
 {
-	Scsi_Cmnd *end;
+	struct scsi_cmnd *end;
 
 	SCNEXT(new_SC) = NULL;
 	if (!*SC)
@@ -656,9 +656,9 @@ static inline void append_SC(Scsi_Cmnd **SC, Scsi_Cmnd *new_SC)
 	}
 }
 
-static inline Scsi_Cmnd *remove_first_SC(Scsi_Cmnd ** SC)
+static inline struct scsi_cmnd *remove_first_SC(struct scsi_cmnd ** SC)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 
 	ptr = *SC;
 	if (ptr) {
@@ -668,9 +668,10 @@ static inline Scsi_Cmnd *remove_first_SC(Scsi_Cmnd ** SC)
 	return ptr;
 }
 
-static inline Scsi_Cmnd *remove_lun_SC(Scsi_Cmnd ** SC, int target, int lun)
+static inline struct scsi_cmnd *remove_lun_SC(struct scsi_cmnd ** SC,
+					      int target, int lun)
 {
-	Scsi_Cmnd *ptr, *prev;
+	struct scsi_cmnd *ptr, *prev;
 
 	for (ptr = *SC, prev = NULL;
 	     ptr && ((ptr->device->id != target) || (ptr->device->lun != lun));
@@ -689,9 +690,10 @@ static inline Scsi_Cmnd *remove_lun_SC(Scsi_Cmnd ** SC, int target, int lun)
 	return ptr;
 }
 
-static inline Scsi_Cmnd *remove_SC(Scsi_Cmnd **SC, Scsi_Cmnd *SCp)
+static inline struct scsi_cmnd *remove_SC(struct scsi_cmnd **SC,
+					  struct scsi_cmnd *SCp)
 {
-	Scsi_Cmnd *ptr, *prev;
+	struct scsi_cmnd *ptr, *prev;
 
 	for (ptr = *SC, prev = NULL;
 	     ptr && SCp!=ptr;
@@ -912,8 +914,9 @@ static int setup_expected_interrupts(struct Scsi_Host *shpnt)
 /*
  *  Queue a command and setup interrupts for a free bus.
  */
-static int aha152x_internal_queue(Scsi_Cmnd *SCpnt, struct completion *complete,
-		int phase, void (*done)(Scsi_Cmnd *))
+static int aha152x_internal_queue(struct scsi_cmnd *SCpnt,
+				  struct completion *complete,
+				  int phase, void (*done)(struct scsi_cmnd *))
 {
 	struct Scsi_Host *shpnt = SCpnt->device->host;
 	unsigned long flags;
@@ -987,7 +990,8 @@ static int aha152x_internal_queue(Scsi_Cmnd *SCpnt, struct completion *complete,
  *  queue a command
  *
  */
-static int aha152x_queue_lck(Scsi_Cmnd *SCpnt, void (*done)(Scsi_Cmnd *))
+static int aha152x_queue_lck(struct scsi_cmnd *SCpnt,
+			     void (*done)(struct scsi_cmnd *))
 {
 	return aha152x_internal_queue(SCpnt, NULL, 0, done);
 }
@@ -998,7 +1002,7 @@ static DEF_SCSI_QCMD(aha152x_queue)
 /*
  *
  */
-static void reset_done(Scsi_Cmnd *SCpnt)
+static void reset_done(struct scsi_cmnd *SCpnt)
 {
 	if(SCSEM(SCpnt)) {
 		complete(SCSEM(SCpnt));
@@ -1011,10 +1015,10 @@ static void reset_done(Scsi_Cmnd *SCpnt)
  *  Abort a command
  *
  */
-static int aha152x_abort(Scsi_Cmnd *SCpnt)
+static int aha152x_abort(struct scsi_cmnd *SCpnt)
 {
 	struct Scsi_Host *shpnt = SCpnt->device->host;
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 	unsigned long flags;
 
 	DO_LOCK(flags);
@@ -1052,7 +1056,7 @@ static int aha152x_abort(Scsi_Cmnd *SCpnt)
  * Reset a device
  *
  */
-static int aha152x_device_reset(Scsi_Cmnd * SCpnt)
+static int aha152x_device_reset(struct scsi_cmnd * SCpnt)
 {
 	struct Scsi_Host *shpnt = SCpnt->device->host;
 	DECLARE_COMPLETION(done);
@@ -1110,13 +1114,14 @@ static int aha152x_device_reset(Scsi_Cmnd * SCpnt)
 	return ret;
 }
 
-static void free_hard_reset_SCs(struct Scsi_Host *shpnt, Scsi_Cmnd **SCs)
+static void free_hard_reset_SCs(struct Scsi_Host *shpnt,
+				struct scsi_cmnd **SCs)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 
 	ptr=*SCs;
 	while(ptr) {
-		Scsi_Cmnd *next;
+		struct scsi_cmnd *next;
 
 		if(SCDATA(ptr)) {
 			next = SCNEXT(ptr);
@@ -1171,7 +1176,7 @@ static int aha152x_bus_reset_host(struct Scsi_Host *shpnt)
  * Reset the bus
  *
  */
-static int aha152x_bus_reset(Scsi_Cmnd *SCpnt)
+static int aha152x_bus_reset(struct scsi_cmnd *SCpnt)
 {
 	return aha152x_bus_reset_host(SCpnt->device->host);
 }
@@ -1436,7 +1441,7 @@ static void busfree_run(struct Scsi_Host *shpnt)
 
 			if(!(DONE_SC->SCp.phase & not_issued)) {
 				struct aha152x_scdata *sc;
-				Scsi_Cmnd *ptr = DONE_SC;
+				struct scsi_cmnd *ptr = DONE_SC;
 				DONE_SC=NULL;
 
 				sc = SCDATA(ptr);
@@ -1451,7 +1456,7 @@ static void busfree_run(struct Scsi_Host *shpnt)
 		}
 
 		if(DONE_SC && DONE_SC->scsi_done) {
-			Scsi_Cmnd *ptr = DONE_SC;
+			struct scsi_cmnd *ptr = DONE_SC;
 			DONE_SC=NULL;
 
 			/* turn led off, when no commands are in the driver */
@@ -2247,13 +2252,13 @@ static void parerr_run(struct Scsi_Host *shpnt)
  */
 static void rsti_run(struct Scsi_Host *shpnt)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 
 	shost_printk(KERN_NOTICE, shpnt, "scsi reset in\n");
 
 	ptr=DISCONNECTED_SC;
 	while(ptr) {
-		Scsi_Cmnd *next = SCNEXT(ptr);
+		struct scsi_cmnd *next = SCNEXT(ptr);
 
 		if (!ptr->device->soft_reset) {
 			remove_SC(&DISCONNECTED_SC, ptr);
@@ -2438,7 +2443,7 @@ static void disp_enintr(struct Scsi_Host *shpnt)
 /*
  * Show the command data of a command
  */
-static void show_command(Scsi_Cmnd *ptr)
+static void show_command(struct scsi_cmnd *ptr)
 {
 	scsi_print_command(ptr);
 	scmd_printk(KERN_DEBUG, ptr,
@@ -2462,7 +2467,7 @@ static void show_command(Scsi_Cmnd *ptr)
  */
 static void show_queues(struct Scsi_Host *shpnt)
 {
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 	unsigned long flags;
 
 	DO_LOCK(flags);
@@ -2484,7 +2489,7 @@ static void show_queues(struct Scsi_Host *shpnt)
 	disp_enintr(shpnt);
 }
 
-static void get_command(struct seq_file *m, Scsi_Cmnd * ptr)
+static void get_command(struct seq_file *m, struct scsi_cmnd * ptr)
 {
 	int i;
 
@@ -2813,7 +2818,7 @@ static int aha152x_set_info(struct Scsi_Host *shpnt, char *buffer, int length)
 static int aha152x_show_info(struct seq_file *m, struct Scsi_Host *shpnt)
 {
 	int i;
-	Scsi_Cmnd *ptr;
+	struct scsi_cmnd *ptr;
 	unsigned long flags;
 
 	seq_puts(m, AHA152X_REVID "\n");
diff --git a/drivers/scsi/aha1740.c b/drivers/scsi/aha1740.c
index b48d5436f094..786bf7f32c64 100644
--- a/drivers/scsi/aha1740.c
+++ b/drivers/scsi/aha1740.c
@@ -207,11 +207,11 @@ static int aha1740_test_port(unsigned int base)
 static irqreturn_t aha1740_intr_handle(int irq, void *dev_id)
 {
 	struct Scsi_Host *host = (struct Scsi_Host *) dev_id;
-        void (*my_done)(Scsi_Cmnd *);
+        void (*my_done)(struct scsi_cmnd *);
 	int errstatus, adapstat;
 	int number_serviced;
 	struct ecb *ecbptr;
-	Scsi_Cmnd *SCtmp;
+	struct scsi_cmnd *SCtmp;
 	unsigned int base;
 	unsigned long flags;
 	int handled = 0;
@@ -311,7 +311,8 @@ static irqreturn_t aha1740_intr_handle(int irq, void *dev_id)
 	return IRQ_RETVAL(handled);
 }
 
-static int aha1740_queuecommand_lck(Scsi_Cmnd * SCpnt, void (*done)(Scsi_Cmnd *))
+static int aha1740_queuecommand_lck(struct scsi_cmnd * SCpnt,
+				    void (*done)(struct scsi_cmnd *))
 {
 	unchar direction;
 	unchar *cmd = (unchar *) SCpnt->cmnd;
@@ -520,7 +521,7 @@ static int aha1740_biosparam(struct scsi_device *sdev,
 	return 0;
 }
 
-static int aha1740_eh_abort_handler (Scsi_Cmnd *dummy)
+static int aha1740_eh_abort_handler (struct scsi_cmnd *dummy)
 {
 /*
  * From Alan Cox :
diff --git a/drivers/scsi/aha1740.h b/drivers/scsi/aha1740.h
index dfdaa4d3ea4e..6eeed6da0b54 100644
--- a/drivers/scsi/aha1740.h
+++ b/drivers/scsi/aha1740.h
@@ -135,8 +135,8 @@ struct ecb {			/* Enhanced Control Block 6.1 */
 /* Hardware defined portion ends here, rest is driver defined */
 	u8 sense[MAX_SENSE];	/* Sense area */
 	u8 status[MAX_STATUS];	/* Status area */
-	Scsi_Cmnd *SCpnt;	/* Link to the SCSI Command Block */
-	void (*done) (Scsi_Cmnd *);	/* Completion Function */
+	struct scsi_cmnd *SCpnt;	/* Link to the SCSI Command Block */
+	void (*done) (struct scsi_cmnd *);	/* Completion Function */
 };
 
 #define	AHA1740CMD_NOP	 0x00	/* No OP */
diff --git a/drivers/scsi/gdth.c b/drivers/scsi/gdth.c
index 85604795d8ee..16709735b546 100644
--- a/drivers/scsi/gdth.c
+++ b/drivers/scsi/gdth.c
@@ -146,14 +146,14 @@ static irqreturn_t gdth_interrupt(int irq, void *dev_id);
 static irqreturn_t __gdth_interrupt(gdth_ha_str *ha,
                                     int gdth_from_wait, int* pIndex);
 static int gdth_sync_event(gdth_ha_str *ha, int service, u8 index,
-                                                               Scsi_Cmnd *scp);
+                                                               struct scsi_cmnd *scp);
 static int gdth_async_event(gdth_ha_str *ha);
 static void gdth_log_event(gdth_evt_data *dvr, char *buffer);
 
-static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority);
+static void gdth_putq(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 priority);
 static void gdth_next(gdth_ha_str *ha);
-static int gdth_fill_raw_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 b);
-static int gdth_special_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp);
+static int gdth_fill_raw_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 b);
+static int gdth_special_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp);
 static gdth_evt_str *gdth_store_event(gdth_ha_str *ha, u16 source,
                                       u16 idx, gdth_evt_data *evt);
 static int gdth_read_event(gdth_ha_str *ha, int handle, gdth_evt_str *estr);
@@ -161,10 +161,11 @@ static void gdth_readapp_event(gdth_ha_str *ha, u8 application,
                                gdth_evt_str *estr);
 static void gdth_clear_events(void);
 
-static void gdth_copy_internal_data(gdth_ha_str *ha, Scsi_Cmnd *scp,
+static void gdth_copy_internal_data(gdth_ha_str *ha, struct scsi_cmnd *scp,
                                     char *buffer, u16 count);
-static int gdth_internal_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp);
-static int gdth_fill_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u16 hdrive);
+static int gdth_internal_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp);
+static int gdth_fill_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp,
+			       u16 hdrive);
 
 static void gdth_enable_int(gdth_ha_str *ha);
 static int gdth_test_busy(gdth_ha_str *ha);
@@ -446,7 +447,7 @@ int __gdth_execute(struct scsi_device *sdev, gdth_cmd_str *gdtcmd, char *cmnd,
                    int timeout, u32 *info)
 {
     gdth_ha_str *ha = shost_priv(sdev->host);
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     struct gdth_cmndinfo cmndinfo;
     DECLARE_COMPLETION_ONSTACK(wait);
     int rval;
@@ -1982,11 +1983,11 @@ static int gdth_analyse_hdrive(gdth_ha_str *ha, u16 hdrive)
 
 /* command queueing/sending functions */
 
-static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
+static void gdth_putq(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 priority)
 {
     struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
-    register Scsi_Cmnd *pscp;
-    register Scsi_Cmnd *nscp;
+    register struct scsi_cmnd *pscp;
+    register struct scsi_cmnd *nscp;
     unsigned long flags;
 
     TRACE(("gdth_putq() priority %d\n",priority));
@@ -2000,11 +2001,11 @@ static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
         scp->SCp.ptr = NULL;
     } else {                                    /* queue not empty */
         pscp = ha->req_first;
-        nscp = (Scsi_Cmnd *)pscp->SCp.ptr;
+        nscp = (struct scsi_cmnd *)pscp->SCp.ptr;
         /* priority: 0-highest,..,0xff-lowest */
         while (nscp && gdth_cmnd_priv(nscp)->priority <= priority) {
             pscp = nscp;
-            nscp = (Scsi_Cmnd *)pscp->SCp.ptr;
+            nscp = (struct scsi_cmnd *)pscp->SCp.ptr;
         }
         pscp->SCp.ptr = (char *)scp;
         scp->SCp.ptr  = (char *)nscp;
@@ -2013,7 +2014,7 @@ static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
 
 #ifdef GDTH_STATISTICS
     flags = 0;
-    for (nscp=ha->req_first; nscp; nscp=(Scsi_Cmnd*)nscp->SCp.ptr)
+    for (nscp=ha->req_first; nscp; nscp=(struct scsi_cmnd*)nscp->SCp.ptr)
         ++flags;
     if (max_rq < flags) {
         max_rq = flags;
@@ -2024,8 +2025,8 @@ static void gdth_putq(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 priority)
 
 static void gdth_next(gdth_ha_str *ha)
 {
-    register Scsi_Cmnd *pscp;
-    register Scsi_Cmnd *nscp;
+    register struct scsi_cmnd *pscp;
+    register struct scsi_cmnd *nscp;
     u8 b, t, l, firsttime;
     u8 this_cmd, next_cmd;
     unsigned long flags = 0;
@@ -2040,10 +2041,10 @@ static void gdth_next(gdth_ha_str *ha)
     next_cmd = gdth_polling ? FALSE:TRUE;
     cmd_index = 0;
 
-    for (nscp = pscp = ha->req_first; nscp; nscp = (Scsi_Cmnd *)nscp->SCp.ptr) {
+    for (nscp = pscp = ha->req_first; nscp; nscp = (struct scsi_cmnd *)nscp->SCp.ptr) {
         struct gdth_cmndinfo *nscp_cmndinfo = gdth_cmnd_priv(nscp);
-        if (nscp != pscp && nscp != (Scsi_Cmnd *)pscp->SCp.ptr)
-            pscp = (Scsi_Cmnd *)pscp->SCp.ptr;
+        if (nscp != pscp && nscp != (struct scsi_cmnd *)pscp->SCp.ptr)
+            pscp = (struct scsi_cmnd *)pscp->SCp.ptr;
         if (!nscp_cmndinfo->internal_command) {
             b = nscp->device->channel;
             t = nscp->device->id;
@@ -2250,7 +2251,7 @@ static void gdth_next(gdth_ha_str *ha)
         if (!this_cmd)
             break;
         if (nscp == ha->req_first)
-            ha->req_first = pscp = (Scsi_Cmnd *)nscp->SCp.ptr;
+            ha->req_first = pscp = (struct scsi_cmnd *)nscp->SCp.ptr;
         else
             pscp->SCp.ptr = nscp->SCp.ptr;
         if (!next_cmd)
@@ -2275,7 +2276,7 @@ static void gdth_next(gdth_ha_str *ha)
  * gdth_copy_internal_data() - copy to/from a buffer onto a scsi_cmnd's
  * buffers, kmap_atomic() as needed.
  */
-static void gdth_copy_internal_data(gdth_ha_str *ha, Scsi_Cmnd *scp,
+static void gdth_copy_internal_data(gdth_ha_str *ha, struct scsi_cmnd *scp,
                                     char *buffer, u16 count)
 {
     u16 cpcount,i, max_sg = scsi_sg_count(scp);
@@ -2317,7 +2318,7 @@ static void gdth_copy_internal_data(gdth_ha_str *ha, Scsi_Cmnd *scp,
     }
 }
 
-static int gdth_internal_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp)
+static int gdth_internal_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp)
 {
     u8 t;
     gdth_inq_data inq;
@@ -2419,7 +2420,8 @@ static int gdth_internal_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp)
     return 0;
 }
 
-static int gdth_fill_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u16 hdrive)
+static int gdth_fill_cache_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp,
+                               u16 hdrive)
 {
     register gdth_cmd_str *cmdp;
     struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
@@ -2594,7 +2596,7 @@ static int gdth_fill_cache_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u16 hdrive)
     return cmd_index;
 }
 
-static int gdth_fill_raw_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 b)
+static int gdth_fill_raw_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp, u8 b)
 {
     register gdth_cmd_str *cmdp;
     u16 i;
@@ -2767,7 +2769,7 @@ static int gdth_fill_raw_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp, u8 b)
     return cmd_index;
 }
 
-static int gdth_special_cmd(gdth_ha_str *ha, Scsi_Cmnd *scp)
+static int gdth_special_cmd(gdth_ha_str *ha, struct scsi_cmnd *scp)
 {
     register gdth_cmd_str *cmdp;
     struct gdth_cmndinfo *cmndinfo = gdth_cmnd_priv(scp);
@@ -2958,7 +2960,7 @@ static irqreturn_t __gdth_interrupt(gdth_ha_str *ha,
     gdt6m_dpram_str __iomem *dp6m_ptr = NULL;
     gdt6_dpram_str __iomem *dp6_ptr;
     gdt2_dpram_str __iomem *dp2_ptr;
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     int rval, i;
     u8 IStatus;
     u16 Service;
@@ -3217,7 +3219,7 @@ static irqreturn_t gdth_interrupt(int irq, void *dev_id)
 }
 
 static int gdth_sync_event(gdth_ha_str *ha, int service, u8 index,
-                                                              Scsi_Cmnd *scp)
+                                                              struct scsi_cmnd *scp)
 {
     gdth_msg_str *msg;
     gdth_cmd_str *cmdp;
@@ -3708,7 +3710,7 @@ static u8	gdth_timer_running;
 static void gdth_timeout(struct timer_list *unused)
 {
     u32 i;
-    Scsi_Cmnd *nscp;
+    struct scsi_cmnd *nscp;
     gdth_ha_str *ha;
     unsigned long flags;
 
@@ -3724,7 +3726,8 @@ static void gdth_timeout(struct timer_list *unused)
         if (ha->cmd_tab[i].cmnd != UNUSED_CMND)
             ++act_stats;
 
-    for (act_rq=0,nscp=ha->req_first; nscp; nscp=(Scsi_Cmnd*)nscp->SCp.ptr)
+    for (act_rq=0,
+         nscp=ha->req_first; nscp; nscp=(struct scsi_cmnd*)nscp->SCp.ptr)
         ++act_rq;
 
     TRACE2(("gdth_to(): ints %d, ios %d, act_stats %d, act_rq %d\n",
@@ -3909,12 +3912,12 @@ static enum blk_eh_timer_return gdth_timed_out(struct scsi_cmnd *scp)
 }
 
 
-static int gdth_eh_bus_reset(Scsi_Cmnd *scp)
+static int gdth_eh_bus_reset(struct scsi_cmnd *scp)
 {
     gdth_ha_str *ha = shost_priv(scp->device->host);
     int i;
     unsigned long flags;
-    Scsi_Cmnd *cmnd;
+    struct scsi_cmnd *cmnd;
     u8 b;
 
     TRACE2(("gdth_eh_bus_reset()\n"));
@@ -4465,7 +4468,7 @@ free_fail:
 static int gdth_ioctl(struct file *filep, unsigned int cmd, unsigned long arg)
 {
     gdth_ha_str *ha; 
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     unsigned long flags;
     char cmnd[MAX_COMMAND_SIZE];   
     void __user *argp = (void __user *)arg;
diff --git a/drivers/scsi/gdth.h b/drivers/scsi/gdth.h
index e6e5ccb1e0f3..ee6ffcf388e8 100644
--- a/drivers/scsi/gdth.h
+++ b/drivers/scsi/gdth.h
@@ -162,9 +162,9 @@
 #define BIGSECS         63                      /* mapping 255*63 */
 
 /* special command ptr. */
-#define UNUSED_CMND     ((Scsi_Cmnd *)-1)
-#define INTERNAL_CMND   ((Scsi_Cmnd *)-2)
-#define SCREEN_CMND     ((Scsi_Cmnd *)-3)
+#define UNUSED_CMND     ((struct scsi_cmnd *)-1)
+#define INTERNAL_CMND   ((struct scsi_cmnd *)-2)
+#define SCREEN_CMND     ((struct scsi_cmnd *)-3)
 #define SPECIAL_SCP(p)  (p==UNUSED_CMND || p==INTERNAL_CMND || p==SCREEN_CMND)
 
 /* controller services */
@@ -867,7 +867,7 @@ typedef struct {
     u16              service;                /* service/firmware ver./.. */
     u32             info;
     u32             info2;                  /* additional info */
-    Scsi_Cmnd           *req_first;             /* top of request queue */
+    struct scsi_cmnd           *req_first;             /* top of request queue */
     struct {
         u8          present;                /* Flag: host drive present? */
         u8          is_logdrv;              /* Flag: log. drive (master)? */
@@ -896,7 +896,7 @@ typedef struct {
         u32         id_list[MAXID];         /* IDs of the phys. devices */
     } raw[MAXBUS];                              /* SCSI channels */
     struct {
-        Scsi_Cmnd       *cmnd;                  /* pending request */
+        struct scsi_cmnd       *cmnd;                  /* pending request */
         u16          service;                /* service */
     } cmd_tab[GDTH_MAXCMDS];                    /* table of pend. requests */
     struct gdth_cmndinfo {                      /* per-command private info */
diff --git a/drivers/scsi/gdth_proc.c b/drivers/scsi/gdth_proc.c
index 20add49cdd32..3a9751a80225 100644
--- a/drivers/scsi/gdth_proc.c
+++ b/drivers/scsi/gdth_proc.c
@@ -626,7 +626,7 @@ static void gdth_wait_completion(gdth_ha_str *ha, int busnum, int id)
 {
     unsigned long flags;
     int i;
-    Scsi_Cmnd *scp;
+    struct scsi_cmnd *scp;
     struct gdth_cmndinfo *cmndinfo;
     u8 b, t;
 
diff --git a/drivers/scsi/ibmvscsi/ibmvfc.c b/drivers/scsi/ibmvscsi/ibmvfc.c
index daefe8172b04..b64ca977825d 100644
--- a/drivers/scsi/ibmvscsi/ibmvfc.c
+++ b/drivers/scsi/ibmvscsi/ibmvfc.c
@@ -1322,7 +1322,7 @@ static void ibmvfc_map_sg_list(struct scsi_cmnd *scmd, int nseg,
 
 /**
  * ibmvfc_map_sg_data - Maps dma for a scatterlist and initializes decriptor fields
- * @scmd:		Scsi_Cmnd with the scatterlist
+ * @scmd:		struct scsi_cmnd with the scatterlist
  * @evt:		ibmvfc event struct
  * @vfc_cmd:	vfc_cmd that contains the memory descriptor
  * @dev:		device for which to map dma memory
diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 17df76f0be3c..44916282ebd4 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -681,7 +681,7 @@ static int map_sg_list(struct scsi_cmnd *cmd, int nseg,
 
 /**
  * map_sg_data: - Maps dma for a scatterlist and initializes decriptor fields
- * @cmd:	Scsi_Cmnd with the scatterlist
+ * @cmd:	struct scsi_cmnd with the scatterlist
  * @srp_cmd:	srp_cmd that contains the memory descriptor
  * @dev:	device for which to map dma memory
  *
diff --git a/drivers/scsi/libiscsi_tcp.c b/drivers/scsi/libiscsi_tcp.c
index 369ef8f23b24..4fcb9e65be57 100644
--- a/drivers/scsi/libiscsi_tcp.c
+++ b/drivers/scsi/libiscsi_tcp.c
@@ -695,7 +695,7 @@ iscsi_tcp_hdr_dissect(struct iscsi_conn *conn, struct iscsi_hdr *hdr)
 			struct scsi_data_buffer *sdb = scsi_in(task->sc);
 
 			/*
-			 * Setup copy of Data-In into the Scsi_Cmnd
+			 * Setup copy of Data-In into the struct scsi_cmnd
 			 * Scatterlist case:
 			 * We set up the iscsi_segment to point to the next
 			 * scatterlist entry to copy to. As we go along,
diff --git a/drivers/scsi/megaraid.c b/drivers/scsi/megaraid.c
index 8e8cf1145d7f..8c7154143a4e 100644
--- a/drivers/scsi/megaraid.c
+++ b/drivers/scsi/megaraid.c
@@ -371,7 +371,7 @@ mega_runpendq(adapter_t *adapter)
  * The command queuing entry point for the mid-layer.
  */
 static int
-megaraid_queue_lck(Scsi_Cmnd *scmd, void (*done)(Scsi_Cmnd *))
+megaraid_queue_lck(struct scsi_cmnd *scmd, void (*done)(struct scsi_cmnd *))
 {
 	adapter_t	*adapter;
 	scb_t	*scb;
@@ -425,7 +425,7 @@ static DEF_SCSI_QCMD(megaraid_queue)
  * commands.
  */
 static inline scb_t *
-mega_allocate_scb(adapter_t *adapter, Scsi_Cmnd *cmd)
+mega_allocate_scb(adapter_t *adapter, struct scsi_cmnd *cmd)
 {
 	struct list_head *head = &adapter->free_list;
 	scb_t	*scb;
@@ -457,7 +457,7 @@ mega_allocate_scb(adapter_t *adapter, Scsi_Cmnd *cmd)
  * and the channel number.
  */
 static inline int
-mega_get_ldrv_num(adapter_t *adapter, Scsi_Cmnd *cmd, int channel)
+mega_get_ldrv_num(adapter_t *adapter, struct scsi_cmnd *cmd, int channel)
 {
 	int		tgt;
 	int		ldrv_num;
@@ -520,7 +520,7 @@ mega_get_ldrv_num(adapter_t *adapter, Scsi_Cmnd *cmd, int channel)
  * boot settings.
  */
 static scb_t *
-mega_build_cmd(adapter_t *adapter, Scsi_Cmnd *cmd, int *busy)
+mega_build_cmd(adapter_t *adapter, struct scsi_cmnd *cmd, int *busy)
 {
 	mega_ext_passthru	*epthru;
 	mega_passthru	*pthru;
@@ -951,8 +951,8 @@ mega_build_cmd(adapter_t *adapter, Scsi_Cmnd *cmd, int *busy)
  * prepare a command for the scsi physical devices.
  */
 static mega_passthru *
-mega_prepare_passthru(adapter_t *adapter, scb_t *scb, Scsi_Cmnd *cmd,
-		int channel, int target)
+mega_prepare_passthru(adapter_t *adapter, scb_t *scb, struct scsi_cmnd *cmd,
+		      int channel, int target)
 {
 	mega_passthru *pthru;
 
@@ -1015,8 +1015,9 @@ mega_prepare_passthru(adapter_t *adapter, scb_t *scb, Scsi_Cmnd *cmd,
  * commands for devices which can take extended CDBs (>10 bytes)
  */
 static mega_ext_passthru *
-mega_prepare_extpassthru(adapter_t *adapter, scb_t *scb, Scsi_Cmnd *cmd,
-		int channel, int target)
+mega_prepare_extpassthru(adapter_t *adapter, scb_t *scb,
+			 struct scsi_cmnd *cmd,
+			 int channel, int target)
 {
 	mega_ext_passthru	*epthru;
 
@@ -1417,7 +1418,7 @@ mega_cmd_done(adapter_t *adapter, u8 completed[], int nstatus, int status)
 {
 	mega_ext_passthru	*epthru = NULL;
 	struct scatterlist	*sgl;
-	Scsi_Cmnd	*cmd = NULL;
+	struct scsi_cmnd	*cmd = NULL;
 	mega_passthru	*pthru = NULL;
 	mbox_t	*mbox = NULL;
 	u8	c;
@@ -1652,14 +1653,14 @@ mega_cmd_done(adapter_t *adapter, u8 completed[], int nstatus, int status)
 static void
 mega_rundoneq (adapter_t *adapter)
 {
-	Scsi_Cmnd *cmd;
+	struct scsi_cmnd *cmd;
 	struct list_head *pos;
 
 	list_for_each(pos, &adapter->completed_list) {
 
 		struct scsi_pointer* spos = (struct scsi_pointer *)pos;
 
-		cmd = list_entry(spos, Scsi_Cmnd, SCp);
+		cmd = list_entry(spos, struct scsi_cmnd, SCp);
 		cmd->scsi_done(cmd);
 	}
 
@@ -1722,7 +1723,7 @@ static int
 mega_build_sglist(adapter_t *adapter, scb_t *scb, u32 *buf, u32 *len)
 {
 	struct scatterlist *sg;
-	Scsi_Cmnd	*cmd;
+	struct scsi_cmnd	*cmd;
 	int	sgcnt;
 	int	idx;
 
@@ -1869,7 +1870,7 @@ megaraid_info(struct Scsi_Host *host)
  * aborted. All the commands issued to the F/W must complete.
  */
 static int
-megaraid_abort(Scsi_Cmnd *cmd)
+megaraid_abort(struct scsi_cmnd *cmd)
 {
 	adapter_t	*adapter;
 	int		rval;
@@ -1933,7 +1934,7 @@ megaraid_reset(struct scsi_cmnd *cmd)
  * issued to the controller, abort/reset it. Otherwise return failure
  */
 static int
-megaraid_abort_and_reset(adapter_t *adapter, Scsi_Cmnd *cmd, int aor)
+megaraid_abort_and_reset(adapter_t *adapter, struct scsi_cmnd *cmd, int aor)
 {
 	struct list_head	*pos, *next;
 	scb_t			*scb;
diff --git a/drivers/scsi/megaraid.h b/drivers/scsi/megaraid.h
index 18e85d9267ff..cce23a086fbe 100644
--- a/drivers/scsi/megaraid.h
+++ b/drivers/scsi/megaraid.h
@@ -191,7 +191,7 @@ typedef struct {
 	u32	dma_type;
 	u32	dma_direction;
 
-	Scsi_Cmnd	*cmd;
+	struct scsi_cmnd	*cmd;
 	dma_addr_t	dma_h_bulkdata;
 	dma_addr_t	dma_h_sgdata;
 
@@ -942,7 +942,7 @@ static int issue_scb(adapter_t *, scb_t *);
 static int mega_setup_mailbox(adapter_t *);
 
 static int megaraid_queue (struct Scsi_Host *, struct scsi_cmnd *);
-static scb_t * mega_build_cmd(adapter_t *, Scsi_Cmnd *, int *);
+static scb_t * mega_build_cmd(adapter_t *, struct scsi_cmnd *, int *);
 static void __mega_runpendq(adapter_t *);
 static int issue_scb_block(adapter_t *, u_char *);
 
@@ -951,9 +951,9 @@ static irqreturn_t megaraid_isr_iomapped(int, void *);
 
 static void mega_free_scb(adapter_t *, scb_t *);
 
-static int megaraid_abort(Scsi_Cmnd *);
-static int megaraid_reset(Scsi_Cmnd *);
-static int megaraid_abort_and_reset(adapter_t *, Scsi_Cmnd *, int);
+static int megaraid_abort(struct scsi_cmnd *);
+static int megaraid_reset(struct scsi_cmnd *);
+static int megaraid_abort_and_reset(adapter_t *, struct scsi_cmnd *, int);
 static int megaraid_biosparam(struct scsi_device *, struct block_device *,
 		sector_t, int []);
 
@@ -983,9 +983,9 @@ static int mega_internal_dev_inquiry(adapter_t *, u8, u8, dma_addr_t);
 
 static int mega_support_ext_cdb(adapter_t *);
 static mega_passthru* mega_prepare_passthru(adapter_t *, scb_t *,
-		Scsi_Cmnd *, int, int);
+		struct scsi_cmnd *, int, int);
 static mega_ext_passthru* mega_prepare_extpassthru(adapter_t *,
-		scb_t *, Scsi_Cmnd *, int, int);
+		scb_t *, struct scsi_cmnd *, int, int);
 static void mega_enum_raid_scsi(adapter_t *);
 static void mega_get_boot_drv(adapter_t *);
 static int mega_support_random_del(adapter_t *);
diff --git a/drivers/scsi/nsp32_debug.c b/drivers/scsi/nsp32_debug.c
index 58806f432a16..4f1d4bf9c775 100644
--- a/drivers/scsi/nsp32_debug.c
+++ b/drivers/scsi/nsp32_debug.c
@@ -137,7 +137,7 @@ static void print_commandk (unsigned char *command)
 	printk("\n");
 }
 
-static void show_command(Scsi_Cmnd *SCpnt)
+static void show_command(struct scsi_cmnd *SCpnt)
 {
 	print_commandk(SCpnt->cmnd);
 }
diff --git a/drivers/scsi/scsi.h b/drivers/scsi/scsi.h
index 6dcc4c685d1d..4fd75a3aff66 100644
--- a/drivers/scsi/scsi.h
+++ b/drivers/scsi/scsi.h
@@ -43,7 +43,4 @@ struct scsi_device;
 struct scsi_target;
 struct scatterlist;
 
-/* obsolete typedef junk. */
-#include "scsi_typedefs.h"
-
 #endif /* _SCSI_H */
diff --git a/drivers/scsi/scsi_typedefs.h b/drivers/scsi/scsi_typedefs.h
deleted file mode 100644
index 2ed4c5cb7088..000000000000
--- a/drivers/scsi/scsi_typedefs.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-typedef struct scsi_cmnd Scsi_Cmnd;
-- 
cgit v1.2.3


From b3a8aa90c46095cbad454eb068bfb5a8eb56d4e3 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 11 Jun 2018 16:40:53 +0200
Subject: scsi: qla2xxx: remove irq save in qla2x00_poll()

In commit d2ba5675d899 ("[SCSI] qla2xxx: Disable local-interrupts while
polling for RISC status.") added a local_irq_disable() before invoking the
->intr_handler callback. The function, which was used in this callback, did
not disable interrupts while acquiring the spin_lock so a deadlock was
possible and this change was one possible solution.

The function in question was qla2300_intr_handler() and is using
spin_lock_irqsave() since commit 43fac4d97a1a ("[SCSI] qla2xxx: Resolve a
performance issue in interrupt").  I checked all other ->intr_handler
callbacks and all of them use the irqsave variant so it is safe to remove
the local_irq_save() block now.

Cc: qla2xxx-upstream@qlogic.com
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_inline.h | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 37ae0f6d8ae5..bcbdf28bd7b9 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -58,14 +58,12 @@ qla2x00_debounce_register(volatile uint16_t __iomem *addr)
 static inline void
 qla2x00_poll(struct rsp_que *rsp)
 {
-	unsigned long flags;
 	struct qla_hw_data *ha = rsp->hw;
-	local_irq_save(flags);
+
 	if (IS_P3P_TYPE(ha))
 		qla82xx_poll(0, rsp);
 	else
 		ha->isp_ops->intr_handler(0, rsp);
-	local_irq_restore(flags);
 }
 
 static inline uint8_t *
-- 
cgit v1.2.3


From 5b9d397447f8c03843198b573d7cecf8893523fb Mon Sep 17 00:00:00 2001
From: Jeff Moyer <jmoyer@redhat.com>
Date: Mon, 18 Jun 2018 09:57:12 -0400
Subject: scsi: sg: clean up gfp_mask in sg_build_indirect

commit a45b599ad808c ("scsi: sg: allocate with __GFP_ZERO in
sg_build_indirect()") changed the call to alloc_pages to always use
__GFP_ZERO.  Just above that, though, there was this:

       if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
               gfp_mask |= __GFP_ZERO;

And there's only one user of the gfp_mask.  Just or in the __GFP_ZERO
flag at the top of the function and be done with it.

Signed-off-by: Jeff Moyer <jmoyer@redhat.com>
Acked-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sg.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index 53ae52dbff84..c926e07aabda 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1850,7 +1850,7 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
 	int ret_sz = 0, i, k, rem_sz, num, mx_sc_elems;
 	int sg_tablesize = sfp->parentdp->sg_tablesize;
 	int blk_size = buff_size, order;
-	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN;
+	gfp_t gfp_mask = GFP_ATOMIC | __GFP_COMP | __GFP_NOWARN | __GFP_ZERO;
 	struct sg_device *sdp = sfp->parentdp;
 
 	if (blk_size < 0)
@@ -1880,9 +1880,6 @@ sg_build_indirect(Sg_scatter_hold * schp, Sg_fd * sfp, int buff_size)
 	if (sdp->device->host->unchecked_isa_dma)
 		gfp_mask |= GFP_DMA;
 
-	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SYS_RAWIO))
-		gfp_mask |= __GFP_ZERO;
-
 	order = get_order(num);
 retry:
 	ret_sz = 1 << (PAGE_SHIFT + order);
@@ -1893,7 +1890,7 @@ retry:
 		num = (rem_sz > scatter_elem_sz_prev) ?
 			scatter_elem_sz_prev : rem_sz;
 
-		schp->pages[k] = alloc_pages(gfp_mask | __GFP_ZERO, order);
+		schp->pages[k] = alloc_pages(gfp_mask, order);
 		if (!schp->pages[k])
 			goto out;
 
-- 
cgit v1.2.3


From ba80917d9932da022d2e74eae66e44139dd65136 Mon Sep 17 00:00:00 2001
From: Tomas Winkler <tomas.winkler@intel.com>
Date: Thu, 14 Jun 2018 11:14:09 +0300
Subject: scsi: ufs: ufshcd_dump_regs to use memcpy_fromio

ufshcd_dump_regs should use memcpy_fromio to read host registers
instead of directly accessing using memcpy.  The same function is
utilized in ufs-qcom.

Elminite compilation warning
drivers/scsi/ufs/ufshcd.c:356:9: warning: incorrect type in argument 6 (different address spaces)
drivers/scsi/ufs/ufshcd.c:356:9:    expected void const *buf
drivers/scsi/ufs/ufshcd.c:356:9:    got void [noderef] <asn:2>*mmio_base

Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufs-qcom.c | 21 ++++++---------------
 drivers/scsi/ufs/ufshcd.c   | 35 ++++++++++++++++++++++++-----------
 drivers/scsi/ufs/ufshcd.h   |  3 +++
 3 files changed, 33 insertions(+), 26 deletions(-)

diff --git a/drivers/scsi/ufs/ufs-qcom.c b/drivers/scsi/ufs/ufs-qcom.c
index 221820a7c78b..75ee5906b966 100644
--- a/drivers/scsi/ufs/ufs-qcom.c
+++ b/drivers/scsi/ufs/ufs-qcom.c
@@ -50,19 +50,10 @@ static void ufs_qcom_get_default_testbus_cfg(struct ufs_qcom_host *host);
 static int ufs_qcom_set_dme_vs_core_clk_ctrl_clear_div(struct ufs_hba *hba,
 						       u32 clk_cycles);
 
-static void ufs_qcom_dump_regs(struct ufs_hba *hba, int offset, int len,
-		char *prefix)
-{
-	print_hex_dump(KERN_ERR, prefix,
-			len > 4 ? DUMP_PREFIX_OFFSET : DUMP_PREFIX_NONE,
-			16, 4, (void __force *)hba->mmio_base + offset,
-			len * 4, false);
-}
-
 static void ufs_qcom_dump_regs_wrapper(struct ufs_hba *hba, int offset, int len,
-		char *prefix, void *priv)
+				       const char *prefix, void *priv)
 {
-	ufs_qcom_dump_regs(hba, offset, len, prefix);
+	ufshcd_dump_regs(hba, offset, len * 4, prefix);
 }
 
 static int ufs_qcom_get_connected_tx_lanes(struct ufs_hba *hba, u32 *tx_lanes)
@@ -1431,7 +1422,7 @@ out:
 
 static void ufs_qcom_print_hw_debug_reg_all(struct ufs_hba *hba,
 		void *priv, void (*print_fn)(struct ufs_hba *hba,
-		int offset, int num_regs, char *str, void *priv))
+		int offset, int num_regs, const char *str, void *priv))
 {
 	u32 reg;
 	struct ufs_qcom_host *host;
@@ -1613,7 +1604,7 @@ int ufs_qcom_testbus_config(struct ufs_qcom_host *host)
 
 static void ufs_qcom_testbus_read(struct ufs_hba *hba)
 {
-	ufs_qcom_dump_regs(hba, UFS_TEST_BUS, 1, "UFS_TEST_BUS ");
+	ufshcd_dump_regs(hba, UFS_TEST_BUS, 4, "UFS_TEST_BUS ");
 }
 
 static void ufs_qcom_print_unipro_testbus(struct ufs_hba *hba)
@@ -1639,8 +1630,8 @@ static void ufs_qcom_print_unipro_testbus(struct ufs_hba *hba)
 
 static void ufs_qcom_dump_dbg_regs(struct ufs_hba *hba)
 {
-	ufs_qcom_dump_regs(hba, REG_UFS_SYS1CLK_1US, 16,
-			"HCI Vendor Specific Registers ");
+	ufshcd_dump_regs(hba, REG_UFS_SYS1CLK_1US, 16 * 4,
+			 "HCI Vendor Specific Registers ");
 
 	/* sleep a bit intermittently as we are dumping too much data */
 	ufs_qcom_print_hw_debug_reg_all(hba, NULL, ufs_qcom_dump_regs_wrapper);
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 397081d320b1..350f859625f6 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -99,8 +99,29 @@
 		_ret;                                                   \
 	})
 
-#define ufshcd_hex_dump(prefix_str, buf, len) \
-print_hex_dump(KERN_ERR, prefix_str, DUMP_PREFIX_OFFSET, 16, 4, buf, len, false)
+#define ufshcd_hex_dump(prefix_str, buf, len) do {                       \
+	size_t __len = (len);                                            \
+	print_hex_dump(KERN_ERR, prefix_str,                             \
+		       __len > 4 ? DUMP_PREFIX_OFFSET : DUMP_PREFIX_NONE,\
+		       16, 4, buf, __len, false);                        \
+} while (0)
+
+int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len,
+		     const char *prefix)
+{
+	u8 *regs;
+
+	regs = kzalloc(len, GFP_KERNEL);
+	if (!regs)
+		return -ENOMEM;
+
+	memcpy_fromio(regs, hba->mmio_base + offset, len);
+	ufshcd_hex_dump(prefix, regs, len);
+	kfree(regs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(ufshcd_dump_regs);
 
 enum {
 	UFSHCD_MAX_CHANNEL	= 0,
@@ -386,15 +407,7 @@ static void ufshcd_print_uic_err_hist(struct ufs_hba *hba,
 
 static void ufshcd_print_host_regs(struct ufs_hba *hba)
 {
-	/*
-	 * hex_dump reads its data without the readl macro. This might
-	 * cause inconsistency issues on some platform, as the printed
-	 * values may be from cache and not the most recent value.
-	 * To know whether you are looking at an un-cached version verify
-	 * that IORESOURCE_MEM flag is on when xxx_get_resource() is invoked
-	 * during platform/pci probe function.
-	 */
-	ufshcd_hex_dump("host regs: ", hba->mmio_base, UFSHCI_REG_SPACE_SIZE);
+	ufshcd_dump_regs(hba, 0, UFSHCI_REG_SPACE_SIZE, "host_regs: ");
 	dev_err(hba->dev, "hba->ufs_version = 0x%x, hba->capabilities = 0x%x\n",
 		hba->ufs_version, hba->capabilities);
 	dev_err(hba->dev,
diff --git a/drivers/scsi/ufs/ufshcd.h b/drivers/scsi/ufs/ufshcd.h
index f51758f1e5cc..33fdd3f281ae 100644
--- a/drivers/scsi/ufs/ufshcd.h
+++ b/drivers/scsi/ufs/ufshcd.h
@@ -1043,4 +1043,7 @@ static inline u8 ufshcd_scsi_to_upiu_lun(unsigned int scsi_lun)
 		return scsi_lun & UFS_UPIU_MAX_UNIT_NUM_ID;
 }
 
+int ufshcd_dump_regs(struct ufs_hba *hba, size_t offset, size_t len,
+		     const char *prefix);
+
 #endif /* End of Header */
-- 
cgit v1.2.3


From 83c2b54b9295a5fc0d9c8f1751aaf8099d1760f6 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 12 Jun 2018 12:05:43 -0700
Subject: scsi: target: Abstract tag freeing

Introduce target_free_tag() and convert all drivers to use it.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_target.c        | 4 ++--
 drivers/target/iscsi/iscsi_target_util.c | 2 +-
 drivers/target/sbp/sbp_target.c          | 2 +-
 drivers/target/tcm_fc/tfc_cmd.c          | 4 ++--
 drivers/usb/gadget/function/f_tcm.c      | 2 +-
 drivers/vhost/scsi.c                     | 2 +-
 drivers/xen/xen-scsiback.c               | 4 +---
 include/target/target_core_base.h        | 5 +++++
 8 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 0fea2e2326be..11274317118a 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -3783,7 +3783,7 @@ void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 		return;
 	}
 	cmd->jiffies_at_free = get_jiffies_64();
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	target_free_tag(sess->se_sess, &cmd->se_cmd);
 }
 EXPORT_SYMBOL(qlt_free_cmd);
 
@@ -4146,7 +4146,7 @@ out_term:
 	qlt_send_term_exchange(qpair, NULL, &cmd->atio, 1, 0);
 
 	qlt_decr_num_pend_cmds(vha);
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	target_free_tag(sess->se_sess, &cmd->se_cmd);
 	spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
 
 	spin_lock_irqsave(&ha->tgt.sess_lock, flags);
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 4435bf374d2d..7e98697cfb8e 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -711,7 +711,7 @@ void iscsit_release_cmd(struct iscsi_cmd *cmd)
 	kfree(cmd->iov_data);
 	kfree(cmd->text_in_ptr);
 
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(sess->se_sess, se_cmd);
 }
 EXPORT_SYMBOL(iscsit_release_cmd);
 
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index fb1003921d85..679ae29d25ab 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -1460,7 +1460,7 @@ static void sbp_free_request(struct sbp_target_request *req)
 	kfree(req->pg_tbl);
 	kfree(req->cmd_buf);
 
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_sess, se_cmd);
 }
 
 static void sbp_mgt_agent_process(struct work_struct *work)
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index ec372860106f..13e4efbe1ce7 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -92,7 +92,7 @@ static void ft_free_cmd(struct ft_cmd *cmd)
 	if (fr_seq(fp))
 		fc_seq_release(fr_seq(fp));
 	fc_frame_free(fp);
-	percpu_ida_free(&sess->se_sess->sess_tag_pool, cmd->se_cmd.map_tag);
+	target_free_tag(sess->se_sess, &cmd->se_cmd);
 	ft_sess_put(sess);	/* undo get from lookup at recv */
 }
 
@@ -461,7 +461,7 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	cmd->sess = sess;
 	cmd->seq = fc_seq_assign(lport, fp);
 	if (!cmd->seq) {
-		percpu_ida_free(&se_sess->sess_tag_pool, tag);
+		target_free_tag(se_sess, &cmd->se_cmd);
 		goto busy;
 	}
 	cmd->req_frame = fp;		/* hold frame during cmd */
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index d78dbb73bde8..9f670d9224b9 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1288,7 +1288,7 @@ static void usbg_release_cmd(struct se_cmd *se_cmd)
 	struct se_session *se_sess = se_cmd->se_sess;
 
 	kfree(cmd->data_buf);
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_sess, se_cmd);
 }
 
 static u32 usbg_sess_get_index(struct se_session *se_sess)
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 17fcd3b2e686..7aaf0e5512ed 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -324,7 +324,7 @@ static void vhost_scsi_release_cmd(struct se_cmd *se_cmd)
 	}
 
 	vhost_scsi_put_inflight(tv_cmd->inflight);
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_sess, se_cmd);
 }
 
 static u32 vhost_scsi_sess_get_index(struct se_session *se_sess)
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 7bc88fd43cfc..ec6635258ed8 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1377,9 +1377,7 @@ static int scsiback_check_stop_free(struct se_cmd *se_cmd)
 
 static void scsiback_release_cmd(struct se_cmd *se_cmd)
 {
-	struct se_session *se_sess = se_cmd->se_sess;
-
-	percpu_ida_free(&se_sess->sess_tag_pool, se_cmd->map_tag);
+	target_free_tag(se_cmd->se_sess, se_cmd);
 }
 
 static u32 scsiback_sess_get_index(struct se_session *se_sess)
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 922a39f45abc..260c2f3e9460 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -934,4 +934,9 @@ static inline void atomic_dec_mb(atomic_t *v)
 	smp_mb__after_atomic();
 }
 
+static inline void target_free_tag(struct se_session *sess, struct se_cmd *cmd)
+{
+	percpu_ida_free(&sess->sess_tag_pool, cmd->map_tag);
+}
+
 #endif /* TARGET_CORE_BASE_H */
-- 
cgit v1.2.3


From 10e9cbb6b531117be0c4a79f2c7fa9a45a0dd532 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 12 Jun 2018 12:05:44 -0700
Subject: scsi: target: Convert target drivers to use sbitmap

The sbitmap and the percpu_ida perform essentially the same task,
allocating tags for commands.  The sbitmap outperforms the percpu_ida as
documented here: https://lkml.org/lkml/2014/4/22/553

The sbitmap interface is a little harder to use, but being able to remove
the percpu_ida code and getting better performance justifies the additional
complexity.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Acked-by: Felipe Balbi <felipe.balbi@linux.intel.com>	# f_tcm
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_target.c        | 10 ++++++----
 drivers/target/iscsi/iscsi_target_util.c | 33 +++++++++++++++++++++++++++++---
 drivers/target/sbp/sbp_target.c          |  5 +++--
 drivers/target/target_core_transport.c   |  5 +++--
 drivers/target/tcm_fc/tfc_cmd.c          |  6 +++---
 drivers/usb/gadget/function/f_tcm.c      |  5 +++--
 drivers/vhost/scsi.c                     |  6 +++---
 drivers/xen/xen-scsiback.c               |  5 +++--
 include/target/iscsi/iscsi_target_core.h |  1 +
 include/target/target_core_base.h        |  7 ++++---
 10 files changed, 59 insertions(+), 24 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 11274317118a..3de11153d1d3 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -4277,9 +4277,9 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
 {
 	struct se_session *se_sess = sess->se_sess;
 	struct qla_tgt_cmd *cmd;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return NULL;
 
@@ -4292,6 +4292,7 @@ static struct qla_tgt_cmd *qlt_get_tag(scsi_qla_host_t *vha,
 	qlt_incr_num_pend_cmds(vha);
 	cmd->vha = vha;
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->sess = sess;
 	cmd->loop_id = sess->loop_id;
 	cmd->conf_compl_supported = sess->conf_compl_supported;
@@ -5294,7 +5295,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 	struct fc_port *sess;
 	struct se_session *se_sess;
 	struct qla_tgt_cmd *cmd;
-	int tag;
+	int tag, cpu;
 	unsigned long flags;
 
 	if (unlikely(tgt->tgt_stop)) {
@@ -5326,7 +5327,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 
 	se_sess = sess->se_sess;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return;
 
@@ -5357,6 +5358,7 @@ qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 	cmd->reset_count = ha->base_qpair->chip_reset;
 	cmd->q_full = 1;
 	cmd->qpair = ha->base_qpair;
+	cmd->se_cmd.map_cpu = cpu;
 
 	if (qfull) {
 		cmd->q_full = 1;
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 7e98697cfb8e..8cfcf9033507 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -17,7 +17,7 @@
  ******************************************************************************/
 
 #include <linux/list.h>
-#include <linux/percpu_ida.h>
+#include <linux/sched/signal.h>
 #include <net/ipv6.h>         /* ipv6_addr_equal() */
 #include <scsi/scsi_tcq.h>
 #include <scsi/iscsi_proto.h>
@@ -147,6 +147,30 @@ void iscsit_free_r2ts_from_list(struct iscsi_cmd *cmd)
 	spin_unlock_bh(&cmd->r2t_lock);
 }
 
+static int iscsit_wait_for_tag(struct se_session *se_sess, int state, int *cpup)
+{
+	int tag = -1;
+	DEFINE_WAIT(wait);
+	struct sbq_wait_state *ws;
+
+	if (state == TASK_RUNNING)
+		return tag;
+
+	ws = &se_sess->sess_tag_pool.ws[0];
+	for (;;) {
+		prepare_to_wait_exclusive(&ws->wait, &wait, state);
+		if (signal_pending_state(state, current))
+			break;
+		tag = sbitmap_queue_get(&se_sess->sess_tag_pool, cpup);
+		if (tag >= 0)
+			break;
+		schedule();
+	}
+
+	finish_wait(&ws->wait, &wait);
+	return tag;
+}
+
 /*
  * May be called from software interrupt (timer) context for allocating
  * iSCSI NopINs.
@@ -155,9 +179,11 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state)
 {
 	struct iscsi_cmd *cmd;
 	struct se_session *se_sess = conn->sess->se_sess;
-	int size, tag;
+	int size, tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, state);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
+	if (tag < 0)
+		tag = iscsit_wait_for_tag(se_sess, state, &cpu);
 	if (tag < 0)
 		return NULL;
 
@@ -166,6 +192,7 @@ struct iscsi_cmd *iscsit_allocate_cmd(struct iscsi_conn *conn, int state)
 	memset(cmd, 0, size);
 
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->conn = conn;
 	cmd->data_direction = DMA_NONE;
 	INIT_LIST_HEAD(&cmd->i_conn_node);
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index 679ae29d25ab..42b21f2ac8b0 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -926,15 +926,16 @@ static struct sbp_target_request *sbp_mgt_get_req(struct sbp_session *sess,
 {
 	struct se_session *se_sess = sess->se_sess;
 	struct sbp_target_request *req;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return ERR_PTR(-ENOMEM);
 
 	req = &((struct sbp_target_request *)se_sess->sess_cmd_map)[tag];
 	memset(req, 0, sizeof(*req));
 	req->se_cmd.map_tag = tag;
+	req->se_cmd.map_cpu = cpu;
 	req->se_cmd.tag = next_orb;
 
 	return req;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index ee5081ba5313..89dd475d0a8f 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -260,7 +260,8 @@ int transport_alloc_session_tags(struct se_session *se_sess,
 		}
 	}
 
-	rc = percpu_ida_init(&se_sess->sess_tag_pool, tag_num);
+	rc = sbitmap_queue_init_node(&se_sess->sess_tag_pool, tag_num, -1,
+			false, GFP_KERNEL, NUMA_NO_NODE);
 	if (rc < 0) {
 		pr_err("Unable to init se_sess->sess_tag_pool,"
 			" tag_num: %u\n", tag_num);
@@ -547,7 +548,7 @@ void transport_free_session(struct se_session *se_sess)
 		target_put_nacl(se_nacl);
 	}
 	if (se_sess->sess_cmd_map) {
-		percpu_ida_destroy(&se_sess->sess_tag_pool);
+		sbitmap_queue_free(&se_sess->sess_tag_pool);
 		kvfree(se_sess->sess_cmd_map);
 	}
 	kmem_cache_free(se_sess_cache, se_sess);
diff --git a/drivers/target/tcm_fc/tfc_cmd.c b/drivers/target/tcm_fc/tfc_cmd.c
index 13e4efbe1ce7..a183d4da7db2 100644
--- a/drivers/target/tcm_fc/tfc_cmd.c
+++ b/drivers/target/tcm_fc/tfc_cmd.c
@@ -28,7 +28,6 @@
 #include <linux/configfs.h>
 #include <linux/ctype.h>
 #include <linux/hash.h>
-#include <linux/percpu_ida.h>
 #include <asm/unaligned.h>
 #include <scsi/scsi_tcq.h>
 #include <scsi/libfc.h>
@@ -448,9 +447,9 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	struct ft_cmd *cmd;
 	struct fc_lport *lport = sess->tport->lport;
 	struct se_session *se_sess = sess->se_sess;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		goto busy;
 
@@ -458,6 +457,7 @@ static void ft_recv_cmd(struct ft_sess *sess, struct fc_frame *fp)
 	memset(cmd, 0, sizeof(struct ft_cmd));
 
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->sess = sess;
 	cmd->seq = fc_seq_assign(lport, fp);
 	if (!cmd->seq) {
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 9f670d9224b9..5003e857dce7 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1071,15 +1071,16 @@ static struct usbg_cmd *usbg_get_cmd(struct f_uas *fu,
 {
 	struct se_session *se_sess = tv_nexus->tvn_se_sess;
 	struct usbg_cmd *cmd;
-	int tag;
+	int tag, cpu;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0)
 		return ERR_PTR(-ENOMEM);
 
 	cmd = &((struct usbg_cmd *)se_sess->sess_cmd_map)[tag];
 	memset(cmd, 0, sizeof(*cmd));
 	cmd->se_cmd.map_tag = tag;
+	cmd->se_cmd.map_cpu = cpu;
 	cmd->se_cmd.tag = cmd->tag = scsi_tag;
 	cmd->fu = fu;
 
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index 7aaf0e5512ed..ebaf831285ea 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -46,7 +46,6 @@
 #include <linux/virtio_scsi.h>
 #include <linux/llist.h>
 #include <linux/bitmap.h>
-#include <linux/percpu_ida.h>
 
 #include "vhost.h"
 
@@ -567,7 +566,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 	struct se_session *se_sess;
 	struct scatterlist *sg, *prot_sg;
 	struct page **pages;
-	int tag;
+	int tag, cpu;
 
 	tv_nexus = tpg->tpg_nexus;
 	if (!tv_nexus) {
@@ -576,7 +575,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 	}
 	se_sess = tv_nexus->tvn_se_sess;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for vhost_scsi_cmd\n");
 		return ERR_PTR(-ENOMEM);
@@ -591,6 +590,7 @@ vhost_scsi_get_tag(struct vhost_virtqueue *vq, struct vhost_scsi_tpg *tpg,
 	cmd->tvc_prot_sgl = prot_sg;
 	cmd->tvc_upages = pages;
 	cmd->tvc_se_cmd.map_tag = tag;
+	cmd->tvc_se_cmd.map_cpu = cpu;
 	cmd->tvc_tag = scsi_tag;
 	cmd->tvc_lun = lun;
 	cmd->tvc_task_attr = task_attr;
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index ec6635258ed8..764dd9aa0131 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -654,9 +654,9 @@ static struct vscsibk_pend *scsiback_get_pend_req(struct vscsiif_back_ring *ring
 	struct scsiback_nexus *nexus = tpg->tpg_nexus;
 	struct se_session *se_sess = nexus->tvn_se_sess;
 	struct vscsibk_pend *req;
-	int tag, i;
+	int tag, cpu, i;
 
-	tag = percpu_ida_alloc(&se_sess->sess_tag_pool, TASK_RUNNING);
+	tag = sbitmap_queue_get(&se_sess->sess_tag_pool, &cpu);
 	if (tag < 0) {
 		pr_err("Unable to obtain tag for vscsiif_request\n");
 		return ERR_PTR(-ENOMEM);
@@ -665,6 +665,7 @@ static struct vscsibk_pend *scsiback_get_pend_req(struct vscsiif_back_ring *ring
 	req = &((struct vscsibk_pend *)se_sess->sess_cmd_map)[tag];
 	memset(req, 0, sizeof(*req));
 	req->se_cmd.map_tag = tag;
+	req->se_cmd.map_cpu = cpu;
 
 	for (i = 0; i < VSCSI_MAX_GRANTS; i++)
 		req->grant_handles[i] = SCSIBACK_INVALID_HANDLE;
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index cf5f3fff1f1a..f2e6abea8490 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -4,6 +4,7 @@
 
 #include <linux/dma-direction.h>     /* enum dma_data_direction */
 #include <linux/list.h>              /* struct list_head */
+#include <linux/sched.h>
 #include <linux/socket.h>            /* struct sockaddr_storage */
 #include <linux/types.h>             /* u8 */
 #include <scsi/iscsi_proto.h>        /* itt_t */
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 260c2f3e9460..448f291125c2 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -4,7 +4,7 @@
 
 #include <linux/configfs.h>      /* struct config_group */
 #include <linux/dma-direction.h> /* enum dma_data_direction */
-#include <linux/percpu_ida.h>    /* struct percpu_ida */
+#include <linux/sbitmap.h>
 #include <linux/percpu-refcount.h>
 #include <linux/semaphore.h>     /* struct semaphore */
 #include <linux/completion.h>
@@ -455,6 +455,7 @@ struct se_cmd {
 	int			sam_task_attr;
 	/* Used for se_sess->sess_tag_pool */
 	unsigned int		map_tag;
+	int			map_cpu;
 	/* Transport protocol dependent state, see transport_state_table */
 	enum transport_state_table t_state;
 	/* See se_cmd_flags_table */
@@ -608,7 +609,7 @@ struct se_session {
 	struct list_head	sess_wait_list;
 	spinlock_t		sess_cmd_lock;
 	void			*sess_cmd_map;
-	struct percpu_ida	sess_tag_pool;
+	struct sbitmap_queue	sess_tag_pool;
 };
 
 struct se_device;
@@ -936,7 +937,7 @@ static inline void atomic_dec_mb(atomic_t *v)
 
 static inline void target_free_tag(struct se_session *sess, struct se_cmd *cmd)
 {
-	percpu_ida_free(&sess->sess_tag_pool, cmd->map_tag);
+	sbitmap_queue_clear(&sess->sess_tag_pool, cmd->map_tag, cmd->map_cpu);
 }
 
 #endif /* TARGET_CORE_BASE_H */
-- 
cgit v1.2.3


From 693ba15c9202fe0283404abe4066e1b986e284eb Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 12 Jun 2018 12:05:45 -0700
Subject: scsi: Remove percpu_ida

With its one user gone, remove the library code.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/linux/percpu_ida.h |  83 ----------
 lib/Makefile               |   2 +-
 lib/percpu_ida.c           | 370 ---------------------------------------------
 3 files changed, 1 insertion(+), 454 deletions(-)
 delete mode 100644 include/linux/percpu_ida.h
 delete mode 100644 lib/percpu_ida.c

diff --git a/include/linux/percpu_ida.h b/include/linux/percpu_ida.h
deleted file mode 100644
index 07d78e4653bc..000000000000
--- a/include/linux/percpu_ida.h
+++ /dev/null
@@ -1,83 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __PERCPU_IDA_H__
-#define __PERCPU_IDA_H__
-
-#include <linux/types.h>
-#include <linux/bitops.h>
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/spinlock_types.h>
-#include <linux/wait.h>
-#include <linux/cpumask.h>
-
-struct percpu_ida_cpu;
-
-struct percpu_ida {
-	/*
-	 * number of tags available to be allocated, as passed to
-	 * percpu_ida_init()
-	 */
-	unsigned			nr_tags;
-	unsigned			percpu_max_size;
-	unsigned			percpu_batch_size;
-
-	struct percpu_ida_cpu __percpu	*tag_cpu;
-
-	/*
-	 * Bitmap of cpus that (may) have tags on their percpu freelists:
-	 * steal_tags() uses this to decide when to steal tags, and which cpus
-	 * to try stealing from.
-	 *
-	 * It's ok for a freelist to be empty when its bit is set - steal_tags()
-	 * will just keep looking - but the bitmap _must_ be set whenever a
-	 * percpu freelist does have tags.
-	 */
-	cpumask_t			cpus_have_tags;
-
-	struct {
-		spinlock_t		lock;
-		/*
-		 * When we go to steal tags from another cpu (see steal_tags()),
-		 * we want to pick a cpu at random. Cycling through them every
-		 * time we steal is a bit easier and more or less equivalent:
-		 */
-		unsigned		cpu_last_stolen;
-
-		/* For sleeping on allocation failure */
-		wait_queue_head_t	wait;
-
-		/*
-		 * Global freelist - it's a stack where nr_free points to the
-		 * top
-		 */
-		unsigned		nr_free;
-		unsigned		*freelist;
-	} ____cacheline_aligned_in_smp;
-};
-
-/*
- * Number of tags we move between the percpu freelist and the global freelist at
- * a time
- */
-#define IDA_DEFAULT_PCPU_BATCH_MOVE	32U
-/* Max size of percpu freelist, */
-#define IDA_DEFAULT_PCPU_SIZE	((IDA_DEFAULT_PCPU_BATCH_MOVE * 3) / 2)
-
-int percpu_ida_alloc(struct percpu_ida *pool, int state);
-void percpu_ida_free(struct percpu_ida *pool, unsigned tag);
-
-void percpu_ida_destroy(struct percpu_ida *pool);
-int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
-	unsigned long max_size, unsigned long batch_size);
-static inline int percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags)
-{
-	return __percpu_ida_init(pool, nr_tags, IDA_DEFAULT_PCPU_SIZE,
-		IDA_DEFAULT_PCPU_BATCH_MOVE);
-}
-
-typedef int (*percpu_ida_cb)(unsigned, void *);
-int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
-	void *data);
-
-unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu);
-#endif /* __PERCPU_IDA_H__ */
diff --git a/lib/Makefile b/lib/Makefile
index 956b320292fe..055420101965 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -40,7 +40,7 @@ obj-y += bcd.o div64.o sort.o parser.o debug_locks.o random32.o \
 	 bust_spinlocks.o kasprintf.o bitmap.o scatterlist.o \
 	 gcd.o lcm.o list_sort.o uuid.o flex_array.o iov_iter.o clz_ctz.o \
 	 bsearch.o find_bit.o llist.o memweight.o kfifo.o \
-	 percpu-refcount.o percpu_ida.o rhashtable.o reciprocal_div.o \
+	 percpu-refcount.o rhashtable.o reciprocal_div.o \
 	 once.o refcount.o usercopy.o errseq.o bucket_locks.o
 obj-$(CONFIG_STRING_SELFTEST) += test_string.o
 obj-y += string_helpers.o
diff --git a/lib/percpu_ida.c b/lib/percpu_ida.c
deleted file mode 100644
index 9bbd9c5d375a..000000000000
--- a/lib/percpu_ida.c
+++ /dev/null
@@ -1,370 +0,0 @@
-/*
- * Percpu IDA library
- *
- * Copyright (C) 2013 Datera, Inc. Kent Overstreet
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation; either version 2, or (at
- * your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- */
-
-#include <linux/mm.h>
-#include <linux/bitmap.h>
-#include <linux/bitops.h>
-#include <linux/bug.h>
-#include <linux/err.h>
-#include <linux/export.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/percpu.h>
-#include <linux/sched/signal.h>
-#include <linux/string.h>
-#include <linux/spinlock.h>
-#include <linux/percpu_ida.h>
-
-struct percpu_ida_cpu {
-	/*
-	 * Even though this is percpu, we need a lock for tag stealing by remote
-	 * CPUs:
-	 */
-	spinlock_t			lock;
-
-	/* nr_free/freelist form a stack of free IDs */
-	unsigned			nr_free;
-	unsigned			freelist[];
-};
-
-static inline void move_tags(unsigned *dst, unsigned *dst_nr,
-			     unsigned *src, unsigned *src_nr,
-			     unsigned nr)
-{
-	*src_nr -= nr;
-	memcpy(dst + *dst_nr, src + *src_nr, sizeof(unsigned) * nr);
-	*dst_nr += nr;
-}
-
-/*
- * Try to steal tags from a remote cpu's percpu freelist.
- *
- * We first check how many percpu freelists have tags
- *
- * Then we iterate through the cpus until we find some tags - we don't attempt
- * to find the "best" cpu to steal from, to keep cacheline bouncing to a
- * minimum.
- */
-static inline void steal_tags(struct percpu_ida *pool,
-			      struct percpu_ida_cpu *tags)
-{
-	unsigned cpus_have_tags, cpu = pool->cpu_last_stolen;
-	struct percpu_ida_cpu *remote;
-
-	for (cpus_have_tags = cpumask_weight(&pool->cpus_have_tags);
-	     cpus_have_tags; cpus_have_tags--) {
-		cpu = cpumask_next(cpu, &pool->cpus_have_tags);
-
-		if (cpu >= nr_cpu_ids) {
-			cpu = cpumask_first(&pool->cpus_have_tags);
-			if (cpu >= nr_cpu_ids)
-				BUG();
-		}
-
-		pool->cpu_last_stolen = cpu;
-		remote = per_cpu_ptr(pool->tag_cpu, cpu);
-
-		cpumask_clear_cpu(cpu, &pool->cpus_have_tags);
-
-		if (remote == tags)
-			continue;
-
-		spin_lock(&remote->lock);
-
-		if (remote->nr_free) {
-			memcpy(tags->freelist,
-			       remote->freelist,
-			       sizeof(unsigned) * remote->nr_free);
-
-			tags->nr_free = remote->nr_free;
-			remote->nr_free = 0;
-		}
-
-		spin_unlock(&remote->lock);
-
-		if (tags->nr_free)
-			break;
-	}
-}
-
-/*
- * Pop up to IDA_PCPU_BATCH_MOVE IDs off the global freelist, and push them onto
- * our percpu freelist:
- */
-static inline void alloc_global_tags(struct percpu_ida *pool,
-				     struct percpu_ida_cpu *tags)
-{
-	move_tags(tags->freelist, &tags->nr_free,
-		  pool->freelist, &pool->nr_free,
-		  min(pool->nr_free, pool->percpu_batch_size));
-}
-
-/**
- * percpu_ida_alloc - allocate a tag
- * @pool: pool to allocate from
- * @state: task state for prepare_to_wait
- *
- * Returns a tag - an integer in the range [0..nr_tags) (passed to
- * tag_pool_init()), or otherwise -ENOSPC on allocation failure.
- *
- * Safe to be called from interrupt context (assuming it isn't passed
- * TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE, of course).
- *
- * @gfp indicates whether or not to wait until a free id is available (it's not
- * used for internal memory allocations); thus if passed __GFP_RECLAIM we may sleep
- * however long it takes until another thread frees an id (same semantics as a
- * mempool).
- *
- * Will not fail if passed TASK_UNINTERRUPTIBLE | TASK_INTERRUPTIBLE.
- */
-int percpu_ida_alloc(struct percpu_ida *pool, int state)
-{
-	DEFINE_WAIT(wait);
-	struct percpu_ida_cpu *tags;
-	unsigned long flags;
-	int tag = -ENOSPC;
-
-	tags = raw_cpu_ptr(pool->tag_cpu);
-	spin_lock_irqsave(&tags->lock, flags);
-
-	/* Fastpath */
-	if (likely(tags->nr_free >= 0)) {
-		tag = tags->freelist[--tags->nr_free];
-		spin_unlock_irqrestore(&tags->lock, flags);
-		return tag;
-	}
-	spin_unlock_irqrestore(&tags->lock, flags);
-
-	while (1) {
-		spin_lock_irqsave(&pool->lock, flags);
-		tags = this_cpu_ptr(pool->tag_cpu);
-
-		/*
-		 * prepare_to_wait() must come before steal_tags(), in case
-		 * percpu_ida_free() on another cpu flips a bit in
-		 * cpus_have_tags
-		 *
-		 * global lock held and irqs disabled, don't need percpu lock
-		 */
-		if (state != TASK_RUNNING)
-			prepare_to_wait(&pool->wait, &wait, state);
-
-		if (!tags->nr_free)
-			alloc_global_tags(pool, tags);
-		if (!tags->nr_free)
-			steal_tags(pool, tags);
-
-		if (tags->nr_free) {
-			tag = tags->freelist[--tags->nr_free];
-			if (tags->nr_free)
-				cpumask_set_cpu(smp_processor_id(),
-						&pool->cpus_have_tags);
-		}
-
-		spin_unlock_irqrestore(&pool->lock, flags);
-
-		if (tag >= 0 || state == TASK_RUNNING)
-			break;
-
-		if (signal_pending_state(state, current)) {
-			tag = -ERESTARTSYS;
-			break;
-		}
-
-		schedule();
-	}
-	if (state != TASK_RUNNING)
-		finish_wait(&pool->wait, &wait);
-
-	return tag;
-}
-EXPORT_SYMBOL_GPL(percpu_ida_alloc);
-
-/**
- * percpu_ida_free - free a tag
- * @pool: pool @tag was allocated from
- * @tag: a tag previously allocated with percpu_ida_alloc()
- *
- * Safe to be called from interrupt context.
- */
-void percpu_ida_free(struct percpu_ida *pool, unsigned tag)
-{
-	struct percpu_ida_cpu *tags;
-	unsigned long flags;
-	unsigned nr_free;
-
-	BUG_ON(tag >= pool->nr_tags);
-
-	tags = raw_cpu_ptr(pool->tag_cpu);
-
-	spin_lock_irqsave(&tags->lock, flags);
-	tags->freelist[tags->nr_free++] = tag;
-
-	nr_free = tags->nr_free;
-
-	if (nr_free == 1) {
-		cpumask_set_cpu(smp_processor_id(),
-				&pool->cpus_have_tags);
-		wake_up(&pool->wait);
-	}
-	spin_unlock_irqrestore(&tags->lock, flags);
-
-	if (nr_free == pool->percpu_max_size) {
-		spin_lock_irqsave(&pool->lock, flags);
-		spin_lock(&tags->lock);
-
-		if (tags->nr_free == pool->percpu_max_size) {
-			move_tags(pool->freelist, &pool->nr_free,
-				  tags->freelist, &tags->nr_free,
-				  pool->percpu_batch_size);
-
-			wake_up(&pool->wait);
-		}
-		spin_unlock(&tags->lock);
-		spin_unlock_irqrestore(&pool->lock, flags);
-	}
-}
-EXPORT_SYMBOL_GPL(percpu_ida_free);
-
-/**
- * percpu_ida_destroy - release a tag pool's resources
- * @pool: pool to free
- *
- * Frees the resources allocated by percpu_ida_init().
- */
-void percpu_ida_destroy(struct percpu_ida *pool)
-{
-	free_percpu(pool->tag_cpu);
-	free_pages((unsigned long) pool->freelist,
-		   get_order(pool->nr_tags * sizeof(unsigned)));
-}
-EXPORT_SYMBOL_GPL(percpu_ida_destroy);
-
-/**
- * percpu_ida_init - initialize a percpu tag pool
- * @pool: pool to initialize
- * @nr_tags: number of tags that will be available for allocation
- *
- * Initializes @pool so that it can be used to allocate tags - integers in the
- * range [0, nr_tags). Typically, they'll be used by driver code to refer to a
- * preallocated array of tag structures.
- *
- * Allocation is percpu, but sharding is limited by nr_tags - for best
- * performance, the workload should not span more cpus than nr_tags / 128.
- */
-int __percpu_ida_init(struct percpu_ida *pool, unsigned long nr_tags,
-	unsigned long max_size, unsigned long batch_size)
-{
-	unsigned i, cpu, order;
-
-	memset(pool, 0, sizeof(*pool));
-
-	init_waitqueue_head(&pool->wait);
-	spin_lock_init(&pool->lock);
-	pool->nr_tags = nr_tags;
-	pool->percpu_max_size = max_size;
-	pool->percpu_batch_size = batch_size;
-
-	/* Guard against overflow */
-	if (nr_tags > (unsigned) INT_MAX + 1) {
-		pr_err("percpu_ida_init(): nr_tags too large\n");
-		return -EINVAL;
-	}
-
-	order = get_order(nr_tags * sizeof(unsigned));
-	pool->freelist = (void *) __get_free_pages(GFP_KERNEL, order);
-	if (!pool->freelist)
-		return -ENOMEM;
-
-	for (i = 0; i < nr_tags; i++)
-		pool->freelist[i] = i;
-
-	pool->nr_free = nr_tags;
-
-	pool->tag_cpu = __alloc_percpu(sizeof(struct percpu_ida_cpu) +
-				       pool->percpu_max_size * sizeof(unsigned),
-				       sizeof(unsigned));
-	if (!pool->tag_cpu)
-		goto err;
-
-	for_each_possible_cpu(cpu)
-		spin_lock_init(&per_cpu_ptr(pool->tag_cpu, cpu)->lock);
-
-	return 0;
-err:
-	percpu_ida_destroy(pool);
-	return -ENOMEM;
-}
-EXPORT_SYMBOL_GPL(__percpu_ida_init);
-
-/**
- * percpu_ida_for_each_free - iterate free ids of a pool
- * @pool: pool to iterate
- * @fn: interate callback function
- * @data: parameter for @fn
- *
- * Note, this doesn't guarantee to iterate all free ids restrictly. Some free
- * ids might be missed, some might be iterated duplicated, and some might
- * be iterated and not free soon.
- */
-int percpu_ida_for_each_free(struct percpu_ida *pool, percpu_ida_cb fn,
-	void *data)
-{
-	unsigned long flags;
-	struct percpu_ida_cpu *remote;
-	unsigned cpu, i, err = 0;
-
-	for_each_possible_cpu(cpu) {
-		remote = per_cpu_ptr(pool->tag_cpu, cpu);
-		spin_lock_irqsave(&remote->lock, flags);
-		for (i = 0; i < remote->nr_free; i++) {
-			err = fn(remote->freelist[i], data);
-			if (err)
-				break;
-		}
-		spin_unlock_irqrestore(&remote->lock, flags);
-		if (err)
-			goto out;
-	}
-
-	spin_lock_irqsave(&pool->lock, flags);
-	for (i = 0; i < pool->nr_free; i++) {
-		err = fn(pool->freelist[i], data);
-		if (err)
-			break;
-	}
-	spin_unlock_irqrestore(&pool->lock, flags);
-out:
-	return err;
-}
-EXPORT_SYMBOL_GPL(percpu_ida_for_each_free);
-
-/**
- * percpu_ida_free_tags - return free tags number of a specific cpu or global pool
- * @pool: pool related
- * @cpu: specific cpu or global pool if @cpu == nr_cpu_ids
- *
- * Note: this just returns a snapshot of free tags number.
- */
-unsigned percpu_ida_free_tags(struct percpu_ida *pool, int cpu)
-{
-	struct percpu_ida_cpu *remote;
-	if (cpu == nr_cpu_ids)
-		return pool->nr_free;
-	remote = per_cpu_ptr(pool->tag_cpu, cpu);
-	return remote->nr_free;
-}
-EXPORT_SYMBOL_GPL(percpu_ida_free_tags);
-- 
cgit v1.2.3


From 2fa4a32613c9182b00e46872755b0662374424a7 Mon Sep 17 00:00:00 2001
From: Jason Yan <yanaijie@huawei.com>
Date: Thu, 10 May 2018 11:05:16 +0800
Subject: scsi: libsas: dynamically allocate and free ata host

Commit 2623c7a5f2 ("libata: add refcounting to ata_host") v4.17+ introduced
refcounting to ata_host and will increase or decrease the refcount when
adding or deleting transport ATA port.

Now the ata host for libsas is embedded in domain_device, and the ->kref
member is not initialized. Afer we add ata transport class, ata_host_get()
will be called when adding transport ATA port and a warning will be
triggered as below:

refcount_t: increment on 0; use-after-free.
WARNING: CPU: 2 PID: 103 at
lib/refcount.c:153 refcount_inc+0x40/0x48 ......  Call trace:
 refcount_inc+0x40/0x48
 ata_host_get+0x10/0x18
 ata_tport_add+0x40/0x120
 ata_sas_tport_add+0xc/0x14
 sas_ata_init+0x7c/0xc8
 sas_discover_domain+0x380/0x53c
 process_one_work+0x12c/0x288
 worker_thread+0x58/0x3f0
 kthread+0xfc/0x128
 ret_from_fork+0x10/0x18

And also when removing transport ATA port ata_host_put() will be called and
another similar warning will be triggered. If the refcount decreased to
zero, the ata host will be freed. But this ata host is only part of
domain_device, it cannot be freed directly.

So we have to change this embedded static ata host to a dynamically
allocated ata host and initialize the ->kref member. To use ata_host_get()
and ata_host_put() in libsas, we need to move the declaration of these
functions to the public libata.h and export them.

Fixes: b6240a4df018 ("scsi: libsas: add transport class for ATA devices")
Signed-off-by: Jason Yan <yanaijie@huawei.com>
CC: John Garry <john.garry@huawei.com>
CC: Taras Kondratiuk <takondra@cisco.com>
CC: Tejun Heo <tj@kernel.org>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/libata-core.c          |  3 +++
 drivers/ata/libata.h               |  2 --
 drivers/scsi/libsas/sas_ata.c      | 40 +++++++++++++++++++++++++-------------
 drivers/scsi/libsas/sas_discover.c |  2 ++
 include/linux/libata.h             |  2 ++
 include/scsi/libsas.h              |  2 +-
 6 files changed, 34 insertions(+), 17 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 27d15ed7fa3d..89cb4872a09c 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -6421,6 +6421,7 @@ void ata_host_init(struct ata_host *host, struct device *dev,
 	host->n_tags = ATA_MAX_QUEUE;
 	host->dev = dev;
 	host->ops = ops;
+	kref_init(&host->kref);
 }
 
 void __ata_port_probe(struct ata_port *ap)
@@ -7388,3 +7389,5 @@ EXPORT_SYMBOL_GPL(ata_cable_80wire);
 EXPORT_SYMBOL_GPL(ata_cable_unknown);
 EXPORT_SYMBOL_GPL(ata_cable_ignore);
 EXPORT_SYMBOL_GPL(ata_cable_sata);
+EXPORT_SYMBOL_GPL(ata_host_get);
+EXPORT_SYMBOL_GPL(ata_host_put);
\ No newline at end of file
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index 9e21c49cf6be..f953cb4bb1ba 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -100,8 +100,6 @@ extern int ata_port_probe(struct ata_port *ap);
 extern void __ata_port_probe(struct ata_port *ap);
 extern unsigned int ata_read_log_page(struct ata_device *dev, u8 log,
 				      u8 page, void *buf, unsigned int sectors);
-extern void ata_host_get(struct ata_host *host);
-extern void ata_host_put(struct ata_host *host);
 
 #define to_ata_port(d) container_of(d, struct ata_port, tdev)
 
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 2ac7395112b4..64a958a99f6a 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -552,34 +552,46 @@ int sas_ata_init(struct domain_device *found_dev)
 {
 	struct sas_ha_struct *ha = found_dev->port->ha;
 	struct Scsi_Host *shost = ha->core.shost;
+	struct ata_host *ata_host;
 	struct ata_port *ap;
 	int rc;
 
-	ata_host_init(&found_dev->sata_dev.ata_host, ha->dev, &sas_sata_ops);
-	ap = ata_sas_port_alloc(&found_dev->sata_dev.ata_host,
-				&sata_port_info,
-				shost);
+	ata_host = kzalloc(sizeof(*ata_host), GFP_KERNEL);
+	if (!ata_host)	{
+		SAS_DPRINTK("ata host alloc failed.\n");
+		return -ENOMEM;
+	}
+
+	ata_host_init(ata_host, ha->dev, &sas_sata_ops);
+
+	ap = ata_sas_port_alloc(ata_host, &sata_port_info, shost);
 	if (!ap) {
 		SAS_DPRINTK("ata_sas_port_alloc failed.\n");
-		return -ENODEV;
+		rc = -ENODEV;
+		goto free_host;
 	}
 
 	ap->private_data = found_dev;
 	ap->cbl = ATA_CBL_SATA;
 	ap->scsi_host = shost;
 	rc = ata_sas_port_init(ap);
-	if (rc) {
-		ata_sas_port_destroy(ap);
-		return rc;
-	}
-	rc = ata_sas_tport_add(found_dev->sata_dev.ata_host.dev, ap);
-	if (rc) {
-		ata_sas_port_destroy(ap);
-		return rc;
-	}
+	if (rc)
+		goto destroy_port;
+
+	rc = ata_sas_tport_add(ata_host->dev, ap);
+	if (rc)
+		goto destroy_port;
+
+	found_dev->sata_dev.ata_host = ata_host;
 	found_dev->sata_dev.ap = ap;
 
 	return 0;
+
+destroy_port:
+	ata_sas_port_destroy(ap);
+free_host:
+	ata_host_put(ata_host);
+	return rc;
 }
 
 void sas_ata_task_abort(struct sas_task *task)
diff --git a/drivers/scsi/libsas/sas_discover.c b/drivers/scsi/libsas/sas_discover.c
index 1ffca28fe6a8..0148ae62a52a 100644
--- a/drivers/scsi/libsas/sas_discover.c
+++ b/drivers/scsi/libsas/sas_discover.c
@@ -316,6 +316,8 @@ void sas_free_device(struct kref *kref)
 	if (dev_is_sata(dev) && dev->sata_dev.ap) {
 		ata_sas_tport_delete(dev->sata_dev.ap);
 		ata_sas_port_destroy(dev->sata_dev.ap);
+		ata_host_put(dev->sata_dev.ata_host);
+		dev->sata_dev.ata_host = NULL;
 		dev->sata_dev.ap = NULL;
 	}
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 8b8946dd63b9..33e9718397e2 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1110,6 +1110,8 @@ extern struct ata_host *ata_host_alloc(struct device *dev, int max_ports);
 extern struct ata_host *ata_host_alloc_pinfo(struct device *dev,
 			const struct ata_port_info * const * ppi, int n_ports);
 extern int ata_slave_link_init(struct ata_port *ap);
+extern void ata_host_get(struct ata_host *host);
+extern void ata_host_put(struct ata_host *host);
 extern int ata_host_start(struct ata_host *host);
 extern int ata_host_register(struct ata_host *host,
 			     struct scsi_host_template *sht);
diff --git a/include/scsi/libsas.h b/include/scsi/libsas.h
index 225ab7783dfd..3de3b10da19a 100644
--- a/include/scsi/libsas.h
+++ b/include/scsi/libsas.h
@@ -161,7 +161,7 @@ struct sata_device {
 	u8     port_no;        /* port number, if this is a PM (Port) */
 
 	struct ata_port *ap;
-	struct ata_host ata_host;
+	struct ata_host *ata_host;
 	struct smp_resp rps_resp ____cacheline_aligned; /* report_phy_sata_resp */
 	u8     fis[ATA_RESP_FIS_SIZE];
 };
-- 
cgit v1.2.3


From 199fd79a11f29f222da41421846b37a68e66ce0d Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:41:54 -0700
Subject: scsi: mpt3sas: Fix indentation

Modify the indentation such that smatch no longer complains about
inconsistent indenting.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c      |  2 +-
 drivers/scsi/mpt3sas/mpt3sas_scsih.c     | 40 ++++++++++++++++----------------
 drivers/scsi/mpt3sas/mpt3sas_transport.c |  2 +-
 3 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 8273ed7e7896..5e632bbd8410 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -661,7 +661,7 @@ mpt3sas_base_start_watchdog(struct MPT3SAS_ADAPTER *ioc)
 	if (!ioc->fault_reset_work_q) {
 		pr_err(MPT3SAS_FMT "%s: failed (line=%d)\n",
 		    ioc->name, __func__, __LINE__);
-			return;
+		return;
 	}
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
 	if (ioc->fault_reset_work_q)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 23902ad3cae5..f3fcdd465479 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -2256,7 +2256,7 @@ scsih_slave_configure(struct scsi_device *sdev)
 			ds = "SSP";
 		} else {
 			qdepth = MPT3SAS_SATA_QUEUE_DEPTH;
-			 if (raid_device->device_info &
+			if (raid_device->device_info &
 			    MPI2_SAS_DEVICE_INFO_SATA_DEVICE)
 				ds = "SATA";
 			else
@@ -4003,19 +4003,19 @@ _scsih_issue_delayed_event_ack(struct MPT3SAS_ADAPTER *ioc, u16 smid, U16 event,
 static void
 _scsih_issue_delayed_sas_io_unit_ctrl(struct MPT3SAS_ADAPTER *ioc,
 					u16 smid, u16 handle)
-	{
-		Mpi2SasIoUnitControlRequest_t *mpi_request;
-		u32 ioc_state;
-		int i = smid - ioc->internal_smid;
-		unsigned long flags;
+{
+	Mpi2SasIoUnitControlRequest_t *mpi_request;
+	u32 ioc_state;
+	int i = smid - ioc->internal_smid;
+	unsigned long flags;
 
-		if (ioc->remove_host) {
-			dewtprintk(ioc, pr_info(MPT3SAS_FMT
+	if (ioc->remove_host) {
+		dewtprintk(ioc, pr_info(MPT3SAS_FMT
 			    "%s: host has been removed\n",
 			     __func__, ioc->name));
-			return;
-		} else if (ioc->pci_error_recovery) {
-			dewtprintk(ioc, pr_info(MPT3SAS_FMT
+		return;
+	} else if (ioc->pci_error_recovery) {
+		dewtprintk(ioc, pr_info(MPT3SAS_FMT
 			    "%s: host in pci error recovery\n",
 			    __func__, ioc->name));
 		return;
@@ -4673,19 +4673,19 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
 	}
 
 
-	/* host recovery or link resets sent via IOCTLs */
-	if (ioc->shost_recovery || ioc->ioc_link_reset_in_progress)
+	if (ioc->shost_recovery || ioc->ioc_link_reset_in_progress) {
+		/* host recovery or link resets sent via IOCTLs */
 		return SCSI_MLQUEUE_HOST_BUSY;
-
-	/* device has been deleted */
-	else if (sas_target_priv_data->deleted) {
+	} else if (sas_target_priv_data->deleted) {
+		/* device has been deleted */
 		scmd->result = DID_NO_CONNECT << 16;
 		scmd->scsi_done(scmd);
 		return 0;
-	/* device busy with task management */
 	} else if (sas_target_priv_data->tm_busy ||
-	    sas_device_priv_data->block)
+		   sas_device_priv_data->block) {
+		/* device busy with task management */
 		return SCSI_MLQUEUE_DEVICE_BUSY;
+	}
 
 	/*
 	 * Bug work around for firmware SATL handling.  The loop
@@ -5811,7 +5811,7 @@ _scsih_expander_add(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	}
 
 	_scsih_expander_node_add(ioc, sas_expander);
-	 return 0;
+	return 0;
 
  out_fail:
 
@@ -9522,7 +9522,7 @@ _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
 		break;
 	case MPT3SAS_PORT_ENABLE_COMPLETE:
 		ioc->start_scan = 0;
-	if (missing_delay[0] != -1 && missing_delay[1] != -1)
+		if (missing_delay[0] != -1 && missing_delay[1] != -1)
 			mpt3sas_base_update_missing_delay(ioc, missing_delay[0],
 			    missing_delay[1]);
 		dewtprintk(ioc, pr_info(MPT3SAS_FMT
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index 3a143bb5ca72..05d506d78c66 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -563,7 +563,7 @@ _transport_add_phy_to_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
 				return;
 		}
 		_transport_add_phy(ioc, mpt3sas_port, mpt3sas_phy);
-			return;
+		return;
 	}
 
 }
-- 
cgit v1.2.3


From 7d1207288fdff3f645f3f7a5c8cf658b3e389c5d Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:41:55 -0700
Subject: scsi: mpt3sas: Remove set-but-not-used variables

This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c  | 10 ----------
 drivers/scsi/mpt3sas/mpt3sas_scsih.c |  5 -----
 2 files changed, 15 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 5e632bbd8410..3bf9ee7d9603 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -2155,11 +2155,9 @@ base_is_prp_possible(struct MPT3SAS_ADAPTER *ioc,
 	struct _pcie_device *pcie_device, struct scsi_cmnd *scmd, int sge_count)
 {
 	u32 data_length = 0;
-	struct scatterlist *sg_scmd;
 	bool build_prp = true;
 
 	data_length = scsi_bufflen(scmd);
-	sg_scmd = scsi_sglist(scmd);
 
 	/* If Datalenth is <= 16K and number of SGE’s entries are <= 2
 	 * we built IEEE SGL
@@ -2190,11 +2188,9 @@ _base_check_pcie_native_sgl(struct MPT3SAS_ADAPTER *ioc,
 	Mpi25SCSIIORequest_t *mpi_request, u16 smid, struct scsi_cmnd *scmd,
 	struct _pcie_device *pcie_device)
 {
-	struct scatterlist *sg_scmd;
 	int sges_left;
 
 	/* Get the SG list pointer and info. */
-	sg_scmd = scsi_sglist(scmd);
 	sges_left = scsi_dma_map(scmd);
 	if (sges_left < 0) {
 		sdev_printk(KERN_ERR, scmd->device,
@@ -3498,11 +3494,8 @@ mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u64 *request;
 
 	if (ioc->is_mcpu_endpoint) {
-		MPI2RequestHeader_t *request_hdr;
-
 		__le32 *mfp = (__le32 *)mpt3sas_base_get_msg_frame(ioc, smid);
 
-		request_hdr = (MPI2RequestHeader_t *)mfp;
 		/* TBD 256 is offset within sys register. */
 		mpi_req_iomem = (void __force *)ioc->chip
 					+ MPI_FRAME_START_OFFSET
@@ -3565,13 +3558,10 @@ mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 	Mpi2RequestDescriptorUnion_t descriptor;
 	void *mpi_req_iomem;
 	u64 *request;
-	MPI2RequestHeader_t *request_hdr;
 
 	if (ioc->is_mcpu_endpoint) {
 		__le32 *mfp = (__le32 *)mpt3sas_base_get_msg_frame(ioc, smid);
 
-		request_hdr = (MPI2RequestHeader_t *)mfp;
-
 		_clone_sg_entries(ioc, (void *) mfp, smid);
 		/* TBD 256 is offset within sys register */
 		mpi_req_iomem = (void __force *)ioc->chip +
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index f3fcdd465479..4f7a91f63f01 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1653,7 +1653,6 @@ scsih_target_destroy(struct scsi_target *starget)
 	struct _raid_device *raid_device;
 	struct _pcie_device *pcie_device;
 	unsigned long flags;
-	struct sas_rphy *rphy;
 
 	sas_target_priv_data = starget->hostdata;
 	if (!sas_target_priv_data)
@@ -1693,7 +1692,6 @@ scsih_target_destroy(struct scsi_target *starget)
 	}
 
 	spin_lock_irqsave(&ioc->sas_device_lock, flags);
-	rphy = dev_to_rphy(starget->dev.parent);
 	sas_device = __mpt3sas_get_sdev_from_target(ioc, sas_target_priv_data);
 	if (sas_device && (sas_device->starget == starget) &&
 	    (sas_device->id == starget->id) &&
@@ -6872,7 +6870,6 @@ _scsih_pcie_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	Mpi2ConfigReply_t mpi_reply;
 	struct _pcie_device *pcie_device;
 	struct _enclosure_node *enclosure_dev;
-	u32 pcie_device_type;
 	u32 ioc_status;
 	u64 wwid;
 
@@ -6934,8 +6931,6 @@ _scsih_pcie_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 	pcie_device->port_num = pcie_device_pg0.PortNum;
 	pcie_device->fast_path = (le32_to_cpu(pcie_device_pg0.Flags) &
 	    MPI26_PCIEDEV0_FLAGS_FAST_PATH_CAPABLE) ? 1 : 0;
-	pcie_device_type = pcie_device->device_info &
-	    MPI26_PCIE_DEVINFO_MASK_DEVICE_TYPE;
 
 	pcie_device->enclosure_handle =
 	    le16_to_cpu(pcie_device_pg0.EnclosureHandle);
-- 
cgit v1.2.3


From eb0c7af26beb1cf13b30fc51ea05dd1977df2061 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:41:56 -0700
Subject: scsi: mpt3sas: Annotate switch/case fall-through

This patch avoids that gcc complains about switch/case fall-through
when building with W=1.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_ctl.c   | 1 +
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 1005249a0f25..6126d4ebfa24 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -970,6 +970,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 		}
 		/* drop to default case for posting the request */
 	}
+		/* fall through */
 	default:
 		ioc->build_sg_mpi(ioc, psge, data_out_dma, data_out_sz,
 		    data_in_dma, data_in_sz);
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 4f7a91f63f01..fbed210d3f1b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -5413,6 +5413,7 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
 
 	case MPI2_IOCSTATUS_SCSI_DATA_OVERRUN:
 		scsi_set_resid(scmd, 0);
+		/* fall through */
 	case MPI2_IOCSTATUS_SCSI_RECOVERED_ERROR:
 	case MPI2_IOCSTATUS_SUCCESS:
 		scmd->result = (DID_OK << 16) | scsi_status;
@@ -6443,6 +6444,7 @@ _scsih_sas_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 			if (!test_bit(handle, ioc->pend_os_device_add))
 				break;
 
+			/* fall through */
 
 		case MPI2_EVENT_SAS_TOPO_RC_TARG_ADDED:
 
@@ -7159,6 +7161,7 @@ _scsih_pcie_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 			event_data->PortEntry[i].PortStatus &= 0xF0;
 			event_data->PortEntry[i].PortStatus |=
 				MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED;
+			/* fall through */
 		case MPI26_EVENT_PCIE_TOPO_PS_DEV_ADDED:
 			if (ioc->shost_recovery)
 				break;
-- 
cgit v1.2.3


From 84203b3561726be0e4c4fbb2db90c9d7e6f59314 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:41:57 -0700
Subject: scsi: mpt3sas: Introduce struct mpt3sas_nvme_cmd

Make _base_build_nvme_prp() easier to read by introducing a structure
to access NVMe command fields.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 13 ++++---------
 drivers/scsi/mpt3sas/mpt3sas_base.h |  7 +++++--
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 3bf9ee7d9603..340db9ee090d 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -1864,6 +1864,8 @@ _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	u32		offset, entry_len;
 	u32		page_mask_result, page_mask;
 	size_t		length;
+	struct mpt3sas_nvme_cmd *nvme_cmd =
+		(void *)nvme_encap_request->NVMe_Command;
 
 	/*
 	 * Not all commands require a data transfer. If no data, just return
@@ -1871,15 +1873,8 @@ _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
 	 */
 	if (!data_in_sz && !data_out_sz)
 		return;
-	/*
-	 * Set pointers to PRP1 and PRP2, which are in the NVMe command.
-	 * PRP1 is located at a 24 byte offset from the start of the NVMe
-	 * command.  Then set the current PRP entry pointer to PRP1.
-	 */
-	prp1_entry = (__le64 *)(nvme_encap_request->NVMe_Command +
-	    NVME_CMD_PRP1_OFFSET);
-	prp2_entry = (__le64 *)(nvme_encap_request->NVMe_Command +
-	    NVME_CMD_PRP2_OFFSET);
+	prp1_entry = &nvme_cmd->prp1;
+	prp2_entry = &nvme_cmd->prp2;
 	prp_entry = prp1_entry;
 	/*
 	 * For the PRP entries, use the specially allocated buffer of
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index b00670a54106..247a9e6c485c 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -143,14 +143,17 @@
  * NVMe defines
  */
 #define	NVME_PRP_SIZE			8	/* PRP size */
-#define	NVME_CMD_PRP1_OFFSET		24	/* PRP1 offset in NVMe cmd */
-#define	NVME_CMD_PRP2_OFFSET		32	/* PRP2 offset in NVMe cmd */
 #define	NVME_ERROR_RESPONSE_SIZE	16	/* Max NVME Error Response */
 #define NVME_TASK_ABORT_MIN_TIMEOUT	6
 #define NVME_TASK_ABORT_MAX_TIMEOUT	60
 #define NVME_TASK_MNGT_CUSTOM_MASK	(0x0010)
 #define	NVME_PRP_PAGE_SIZE		4096	/* Page size */
 
+struct mpt3sas_nvme_cmd {
+	u8	rsvd[24];
+	__le64	prp1;
+	__le64	prp2;
+};
 
 /*
  * reset phases
-- 
cgit v1.2.3


From 91b7bdb2c0089cbbb817df6888ab1458c645184e Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:41:58 -0700
Subject: scsi: mpt3sas: Fix _transport_smp_handler() error path

This patch avoids that smatch complains about a double unlock on
ioc->transport_cmds.mutex.

Fixes: 651a01364994 ("scsi: scsi_transport_sas: switch to bsg-lib for SMP passthrough")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Cc: stable@vger.kernel.org
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_transport.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index 05d506d78c66..f4b02dd7f6cf 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -1936,12 +1936,12 @@ _transport_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
 		pr_info(MPT3SAS_FMT "%s: host reset in progress!\n",
 		    __func__, ioc->name);
 		rc = -EFAULT;
-		goto out;
+		goto job_done;
 	}
 
 	rc = mutex_lock_interruptible(&ioc->transport_cmds.mutex);
 	if (rc)
-		goto out;
+		goto job_done;
 
 	if (ioc->transport_cmds.status != MPT3_CMD_NOT_USED) {
 		pr_err(MPT3SAS_FMT "%s: transport_cmds in use\n", ioc->name,
@@ -2066,6 +2066,7 @@ _transport_smp_handler(struct bsg_job *job, struct Scsi_Host *shost,
  out:
 	ioc->transport_cmds.status = MPT3_CMD_NOT_USED;
 	mutex_unlock(&ioc->transport_cmds.mutex);
+job_done:
 	bsg_job_done(job, rc, reslen);
 }
 
-- 
cgit v1.2.3


From 982ea6f9ff2b2f92c03eda06df420b2f3699b7ad Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:41:59 -0700
Subject: scsi: mpt3sas: Fix a race condition in
 mpt3sas_base_hard_reset_handler()

Since ioc->shost_recovery is set after ioc->reset_in_progress_mutex is
obtained, if concurrent resets are issued there is a short time during
which ioc->reset_in_progress_mutex is locked and ioc->shost_recovery ==
0. Avoid that this can cause trouble by unconditionally locking
ioc->shost_recovery.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 10 +---------
 drivers/scsi/mpt3sas/mpt3sas_base.h |  1 -
 2 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 340db9ee090d..107c9b4d197b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -6959,14 +6959,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 		mpt3sas_halt_firmware(ioc);
 
 	/* wait for an active reset in progress to complete */
-	if (!mutex_trylock(&ioc->reset_in_progress_mutex)) {
-		do {
-			ssleep(1);
-		} while (ioc->shost_recovery == 1);
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT "%s: exit\n", ioc->name,
-		    __func__));
-		return ioc->ioc_reset_in_progress_status;
-	}
+	mutex_lock(&ioc->reset_in_progress_mutex);
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
 	ioc->shost_recovery = 1;
@@ -7015,7 +7008,6 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 	    ioc->name, __func__, ((r == 0) ? "SUCCESS" : "FAILED")));
 
 	spin_lock_irqsave(&ioc->ioc_reset_in_progress_lock, flags);
-	ioc->ioc_reset_in_progress_status = r;
 	ioc->shost_recovery = 0;
 	spin_unlock_irqrestore(&ioc->ioc_reset_in_progress_lock, flags);
 	ioc->ioc_reset_count++;
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index 247a9e6c485c..f137c51b4623 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -1166,7 +1166,6 @@ struct MPT3SAS_ADAPTER {
 	struct mutex	reset_in_progress_mutex;
 	spinlock_t	ioc_reset_in_progress_lock;
 	u8		ioc_link_reset_in_progress;
-	u8		ioc_reset_in_progress_status;
 
 	u8		ignore_loginfos;
 	u8		remove_host;
-- 
cgit v1.2.3


From c7a357058882637548dd0908b743c674a23ce0e2 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:42:00 -0700
Subject: scsi: mpt3sas: Split _base_reset_handler(),
 mpt3sas_scsih_reset_handler() and mpt3sas_ctl_reset_handler()

Split each of these functions in three functions - one function per reset
phase. This patch does not change any functionality but makes the code
easier to read.

Note: it is much easier to review the git diff -w output after having
applied this patch than by reviewing the patch itself.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c  | 118 ++++++++++++++++++-----------------
 drivers/scsi/mpt3sas/mpt3sas_base.h  |  15 ++---
 drivers/scsi/mpt3sas/mpt3sas_ctl.c   |  89 ++++++++++++++------------
 drivers/scsi/mpt3sas/mpt3sas_scsih.c |  92 ++++++++++++++-------------
 4 files changed, 166 insertions(+), 148 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 107c9b4d197b..37365bfb1772 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -6840,65 +6840,69 @@ mpt3sas_base_detach(struct MPT3SAS_ADAPTER *ioc)
 }
 
 /**
- * _base_reset_handler - reset callback handler (for base)
+ * _base_pre_reset_handler - pre reset handler
  * @ioc: per adapter object
- * @reset_phase: phase
- *
- * The handler for doing any required cleanup or initialization.
- *
- * The reset phase can be MPT3_IOC_PRE_RESET, MPT3_IOC_AFTER_RESET,
- * MPT3_IOC_DONE_RESET
- *
- * Return nothing.
  */
-static void
-_base_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
+static void _base_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 {
-	mpt3sas_scsih_reset_handler(ioc, reset_phase);
-	mpt3sas_ctl_reset_handler(ioc, reset_phase);
-	switch (reset_phase) {
-	case MPT3_IOC_PRE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-		"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
-		break;
-	case MPT3_IOC_AFTER_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-		"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
-		if (ioc->transport_cmds.status & MPT3_CMD_PENDING) {
-			ioc->transport_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->transport_cmds.smid);
-			complete(&ioc->transport_cmds.done);
-		}
-		if (ioc->base_cmds.status & MPT3_CMD_PENDING) {
-			ioc->base_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->base_cmds.smid);
-			complete(&ioc->base_cmds.done);
-		}
-		if (ioc->port_enable_cmds.status & MPT3_CMD_PENDING) {
-			ioc->port_enable_failed = 1;
-			ioc->port_enable_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->port_enable_cmds.smid);
-			if (ioc->is_driver_loading) {
-				ioc->start_scan_failed =
-				    MPI2_IOCSTATUS_INTERNAL_ERROR;
-				ioc->start_scan = 0;
-				ioc->port_enable_cmds.status =
-				    MPT3_CMD_NOT_USED;
-			} else
-				complete(&ioc->port_enable_cmds.done);
-		}
-		if (ioc->config_cmds.status & MPT3_CMD_PENDING) {
-			ioc->config_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->config_cmds.smid);
-			ioc->config_cmds.smid = USHRT_MAX;
-			complete(&ioc->config_cmds.done);
+	mpt3sas_scsih_pre_reset_handler(ioc);
+	mpt3sas_ctl_pre_reset_handler(ioc);
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
+}
+
+/**
+ * _base_after_reset_handler - after reset handler
+ * @ioc: per adapter object
+ */
+static void _base_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	mpt3sas_scsih_after_reset_handler(ioc);
+	mpt3sas_ctl_after_reset_handler(ioc);
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
+	if (ioc->transport_cmds.status & MPT3_CMD_PENDING) {
+		ioc->transport_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->transport_cmds.smid);
+		complete(&ioc->transport_cmds.done);
+	}
+	if (ioc->base_cmds.status & MPT3_CMD_PENDING) {
+		ioc->base_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->base_cmds.smid);
+		complete(&ioc->base_cmds.done);
+	}
+	if (ioc->port_enable_cmds.status & MPT3_CMD_PENDING) {
+		ioc->port_enable_failed = 1;
+		ioc->port_enable_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->port_enable_cmds.smid);
+		if (ioc->is_driver_loading) {
+			ioc->start_scan_failed =
+				MPI2_IOCSTATUS_INTERNAL_ERROR;
+			ioc->start_scan = 0;
+			ioc->port_enable_cmds.status =
+				MPT3_CMD_NOT_USED;
+		} else {
+			complete(&ioc->port_enable_cmds.done);
 		}
-		break;
-	case MPT3_IOC_DONE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
-		break;
 	}
+	if (ioc->config_cmds.status & MPT3_CMD_PENDING) {
+		ioc->config_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->config_cmds.smid);
+		ioc->config_cmds.smid = USHRT_MAX;
+		complete(&ioc->config_cmds.done);
+	}
+}
+
+/**
+ * _base_reset_done_handler - reset done handler
+ * @ioc: per adapter object
+ */
+static void _base_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	mpt3sas_scsih_reset_done_handler(ioc);
+	mpt3sas_ctl_reset_done_handler(ioc);
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
 }
 
 /**
@@ -6974,13 +6978,13 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 		if ((ioc_state & MPI2_IOC_STATE_MASK) == MPI2_IOC_STATE_FAULT)
 			is_fault = 1;
 	}
-	_base_reset_handler(ioc, MPT3_IOC_PRE_RESET);
+	_base_pre_reset_handler(ioc);
 	mpt3sas_wait_for_commands_to_complete(ioc);
 	_base_mask_interrupts(ioc);
 	r = _base_make_ioc_ready(ioc, type);
 	if (r)
 		goto out;
-	_base_reset_handler(ioc, MPT3_IOC_AFTER_RESET);
+	_base_after_reset_handler(ioc);
 
 	/* If this hard reset is called while port enable is active, then
 	 * there is no reason to call make_ioc_operational
@@ -7001,7 +7005,7 @@ mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
 
 	r = _base_make_ioc_operational(ioc);
 	if (!r)
-		_base_reset_handler(ioc, MPT3_IOC_DONE_RESET);
+		_base_reset_done_handler(ioc);
 
  out:
 	dtmprintk(ioc, pr_info(MPT3SAS_FMT "%s: %s\n",
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.h b/drivers/scsi/mpt3sas/mpt3sas_base.h
index f137c51b4623..96dc15e90bd8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.h
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.h
@@ -155,13 +155,6 @@ struct mpt3sas_nvme_cmd {
 	__le64	prp2;
 };
 
-/*
- * reset phases
- */
-#define MPT3_IOC_PRE_RESET		1 /* prior to host reset */
-#define MPT3_IOC_AFTER_RESET		2 /* just after host reset */
-#define MPT3_IOC_DONE_RESET		3 /* links re-initialized */
-
 /*
  * logging format
  */
@@ -1493,7 +1486,9 @@ struct scsi_cmnd *mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc,
 	u16 smid);
 u8 mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 	u32 reply);
-void mpt3sas_scsih_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase);
+void mpt3sas_scsih_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_scsih_after_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_scsih_reset_done_handler(struct MPT3SAS_ADAPTER *ioc);
 
 int mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
 	u8 type, u16 smid_task, u16 msix_task, u8 timeout, u8 tr_method);
@@ -1620,7 +1615,9 @@ void mpt3sas_ctl_init(ushort hbas_to_enumerate);
 void mpt3sas_ctl_exit(ushort hbas_to_enumerate);
 u8 mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
 	u32 reply);
-void mpt3sas_ctl_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase);
+void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_ctl_after_reset_handler(struct MPT3SAS_ADAPTER *ioc);
+void mpt3sas_ctl_reset_done_handler(struct MPT3SAS_ADAPTER *ioc);
 u8 mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc,
 	u8 msix_index, u32 reply);
 void mpt3sas_ctl_add_to_event_log(struct MPT3SAS_ADAPTER *ioc,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 6126d4ebfa24..0b8fd13593bf 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -460,57 +460,66 @@ out:
 /**
  * mpt3sas_ctl_reset_handler - reset callback handler (for ctl)
  * @ioc: per adapter object
- * @reset_phase: phase
  *
  * The handler for doing any required cleanup or initialization.
- *
- * The reset phase can be MPT3_IOC_PRE_RESET, MPT3_IOC_AFTER_RESET,
- * MPT3_IOC_DONE_RESET
  */
-void
-mpt3sas_ctl_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
+void mpt3sas_ctl_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 {
 	int i;
 	u8 issue_reset;
 
-	switch (reset_phase) {
-	case MPT3_IOC_PRE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
-		for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
-			if (!(ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_REGISTERED))
-				continue;
-			if ((ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_RELEASED))
-				continue;
-			mpt3sas_send_diag_release(ioc, i, &issue_reset);
-		}
-		break;
-	case MPT3_IOC_AFTER_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
+		if (!(ioc->diag_buffer_status[i] &
+		      MPT3_DIAG_BUFFER_IS_REGISTERED))
+			continue;
+		if ((ioc->diag_buffer_status[i] &
+		     MPT3_DIAG_BUFFER_IS_RELEASED))
+			continue;
+		mpt3sas_send_diag_release(ioc, i, &issue_reset);
+	}
+}
+
+/**
+ * mpt3sas_ctl_reset_handler - reset callback handler (for ctl)
+ * @ioc: per adapter object
+ *
+ * The handler for doing any required cleanup or initialization.
+ */
+void mpt3sas_ctl_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
-		if (ioc->ctl_cmds.status & MPT3_CMD_PENDING) {
-			ioc->ctl_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->ctl_cmds.smid);
-			complete(&ioc->ctl_cmds.done);
-		}
-		break;
-	case MPT3_IOC_DONE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	if (ioc->ctl_cmds.status & MPT3_CMD_PENDING) {
+		ioc->ctl_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->ctl_cmds.smid);
+		complete(&ioc->ctl_cmds.done);
+	}
+}
+
+/**
+ * mpt3sas_ctl_reset_handler - reset callback handler (for ctl)
+ * @ioc: per adapter object
+ *
+ * The handler for doing any required cleanup or initialization.
+ */
+void mpt3sas_ctl_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	int i;
+
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
 
-		for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
-			if (!(ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_REGISTERED))
-				continue;
-			if ((ioc->diag_buffer_status[i] &
-			    MPT3_DIAG_BUFFER_IS_RELEASED))
-				continue;
-			ioc->diag_buffer_status[i] |=
-			    MPT3_DIAG_BUFFER_IS_DIAG_RESET;
-		}
-		break;
+	for (i = 0; i < MPI2_DIAG_BUF_TYPE_COUNT; i++) {
+		if (!(ioc->diag_buffer_status[i] &
+		      MPT3_DIAG_BUFFER_IS_REGISTERED))
+			continue;
+		if ((ioc->diag_buffer_status[i] &
+		     MPT3_DIAG_BUFFER_IS_RELEASED))
+			continue;
+		ioc->diag_buffer_status[i] |=
+			MPT3_DIAG_BUFFER_IS_DIAG_RESET;
 	}
 }
 
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index fbed210d3f1b..74dfbaf21814 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -9422,60 +9422,68 @@ _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
 		ioc->name);
 	pr_info(MPT3SAS_FMT "scan devices: complete\n", ioc->name);
 }
+
 /**
  * mpt3sas_scsih_reset_handler - reset callback handler (for scsih)
  * @ioc: per adapter object
- * @reset_phase: phase
  *
  * The handler for doing any required cleanup or initialization.
+ */
+void mpt3sas_scsih_pre_reset_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
+			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
+}
+
+/**
+ * mpt3sas_scsih_after_reset_handler - reset callback handler (for scsih)
+ * @ioc: per adapter object
  *
- * The reset phase can be MPT3_IOC_PRE_RESET, MPT3_IOC_AFTER_RESET,
- * MPT3_IOC_DONE_RESET
- *
- * Return nothing.
+ * The handler for doing any required cleanup or initialization.
  */
 void
-mpt3sas_scsih_reset_handler(struct MPT3SAS_ADAPTER *ioc, int reset_phase)
+mpt3sas_scsih_after_reset_handler(struct MPT3SAS_ADAPTER *ioc)
 {
-	switch (reset_phase) {
-	case MPT3_IOC_PRE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
-			"%s: MPT3_IOC_PRE_RESET\n", ioc->name, __func__));
-		break;
-	case MPT3_IOC_AFTER_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_AFTER_RESET\n", ioc->name, __func__));
-		if (ioc->scsih_cmds.status & MPT3_CMD_PENDING) {
-			ioc->scsih_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->scsih_cmds.smid);
-			complete(&ioc->scsih_cmds.done);
-		}
-		if (ioc->tm_cmds.status & MPT3_CMD_PENDING) {
-			ioc->tm_cmds.status |= MPT3_CMD_RESET;
-			mpt3sas_base_free_smid(ioc, ioc->tm_cmds.smid);
-			complete(&ioc->tm_cmds.done);
-		}
+	if (ioc->scsih_cmds.status & MPT3_CMD_PENDING) {
+		ioc->scsih_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->scsih_cmds.smid);
+		complete(&ioc->scsih_cmds.done);
+	}
+	if (ioc->tm_cmds.status & MPT3_CMD_PENDING) {
+		ioc->tm_cmds.status |= MPT3_CMD_RESET;
+		mpt3sas_base_free_smid(ioc, ioc->tm_cmds.smid);
+		complete(&ioc->tm_cmds.done);
+	}
 
-		memset(ioc->pend_os_device_add, 0, ioc->pend_os_device_add_sz);
-		memset(ioc->device_remove_in_progress, 0,
-		       ioc->device_remove_in_progress_sz);
-		_scsih_fw_event_cleanup_queue(ioc);
-		_scsih_flush_running_cmds(ioc);
-		break;
-	case MPT3_IOC_DONE_RESET:
-		dtmprintk(ioc, pr_info(MPT3SAS_FMT
+	memset(ioc->pend_os_device_add, 0, ioc->pend_os_device_add_sz);
+	memset(ioc->device_remove_in_progress, 0,
+	       ioc->device_remove_in_progress_sz);
+	_scsih_fw_event_cleanup_queue(ioc);
+	_scsih_flush_running_cmds(ioc);
+}
+
+/**
+ * mpt3sas_scsih_reset_handler - reset callback handler (for scsih)
+ * @ioc: per adapter object
+ *
+ * The handler for doing any required cleanup or initialization.
+ */
+void
+mpt3sas_scsih_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
+{
+	dtmprintk(ioc, pr_info(MPT3SAS_FMT
 			"%s: MPT3_IOC_DONE_RESET\n", ioc->name, __func__));
-		if ((!ioc->is_driver_loading) && !(disable_discovery > 0 &&
-		    !ioc->sas_hba.num_phys)) {
-			_scsih_prep_device_scan(ioc);
-			_scsih_create_enclosure_list_after_reset(ioc);
-			_scsih_search_responding_sas_devices(ioc);
-			_scsih_search_responding_pcie_devices(ioc);
-			_scsih_search_responding_raid_devices(ioc);
-			_scsih_search_responding_expanders(ioc);
-			_scsih_error_recovery_delete_devices(ioc);
-		}
-		break;
+	if ((!ioc->is_driver_loading) && !(disable_discovery > 0 &&
+					   !ioc->sas_hba.num_phys)) {
+		_scsih_prep_device_scan(ioc);
+		_scsih_create_enclosure_list_after_reset(ioc);
+		_scsih_search_responding_sas_devices(ioc);
+		_scsih_search_responding_pcie_devices(ioc);
+		_scsih_search_responding_raid_devices(ioc);
+		_scsih_search_responding_expanders(ioc);
+		_scsih_error_recovery_delete_devices(ioc);
 	}
 }
 
-- 
cgit v1.2.3


From 4beb4867f049aea801a93a8fc97801250e32d700 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:42:01 -0700
Subject: scsi: mpt3sas: Improve kernel-doc headers

Avoids that warnings about the kernel headers appear when building with
W=1. Remove useless "@Returns - Nothing" clauses. Change "@Return - " into
"Return: ".

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Sathya Prakash <sathya.prakash@broadcom.com>
Cc: Chaitra P B <chaitra.basappa@broadcom.com>
Cc: Suganath Prabu Subramani <suganath-prabu.subramani@broadcom.com>
Cc: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c         | 213 +++++++-------------
 drivers/scsi/mpt3sas/mpt3sas_config.c       |  74 +++----
 drivers/scsi/mpt3sas/mpt3sas_ctl.c          | 267 +++++++++++++++-----------
 drivers/scsi/mpt3sas/mpt3sas_scsih.c        | 288 +++++++---------------------
 drivers/scsi/mpt3sas/mpt3sas_transport.c    |  55 +++---
 drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c |  18 +-
 drivers/scsi/mpt3sas/mpt3sas_warpdrive.c    |   3 -
 7 files changed, 363 insertions(+), 555 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 37365bfb1772..2053970fc9f8 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -131,7 +131,10 @@ mpt3sas_base_check_cmd_timeout(struct MPT3SAS_ADAPTER *ioc,
 
 /**
  * _scsih_set_fwfault_debug - global setting of ioc->fwfault_debug.
+ * @val: ?
+ * @kp: ?
  *
+ * Return: ?
  */
 static int
 _scsih_set_fwfault_debug(const char *val, const struct kernel_param *kp)
@@ -160,8 +163,6 @@ module_param_call(mpt3sas_fwfault_debug, _scsih_set_fwfault_debug,
  * @ioc: per adapter object
  * @reply: reply message frame(lower 32bit addr)
  * @index: System request message index.
- *
- * @Returns - Nothing
  */
 static void
 _base_clone_reply_to_sys_mem(struct MPT3SAS_ADAPTER *ioc, u32 reply,
@@ -184,7 +185,7 @@ _base_clone_reply_to_sys_mem(struct MPT3SAS_ADAPTER *ioc, u32 reply,
  * _base_clone_mpi_to_sys_mem - Writes/copies MPI frames
  *				to system/BAR0 region.
  *
- * @dst_iomem: Pointer to the destinaltion location in BAR0 space.
+ * @dst_iomem: Pointer to the destination location in BAR0 space.
  * @src: Pointer to the Source data.
  * @size: Size of data to be copied.
  */
@@ -225,7 +226,7 @@ _base_clone_to_sys_mem(void __iomem *dst_iomem, void *src, u32 size)
  * @smid: system request message index
  * @sge_chain_count: Scatter gather chain count.
  *
- * @Return: chain address.
+ * Return: the chain address.
  */
 static inline void __iomem*
 _base_get_chain(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -251,7 +252,7 @@ _base_get_chain(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @smid: system request message index
  * @sge_chain_count: Scatter gather chain count.
  *
- * @Return - Physical chain address.
+ * Return: Physical chain address.
  */
 static inline phys_addr_t
 _base_get_chain_phys(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -276,7 +277,7 @@ _base_get_chain_phys(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * @Returns - Pointer to buffer location in BAR0.
+ * Return: Pointer to buffer location in BAR0.
  */
 
 static void __iomem *
@@ -298,7 +299,7 @@ _base_get_buffer_bar0(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * @Returns - Pointer to buffer location in BAR0.
+ * Return: Pointer to buffer location in BAR0.
  */
 static phys_addr_t
 _base_get_buffer_phys_bar0(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -319,7 +320,7 @@ _base_get_buffer_phys_bar0(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @chain_buffer_dma: Chain buffer dma address.
  *
- * @Returns - Pointer to chain buffer. Or Null on Failure.
+ * Return: Pointer to chain buffer. Or Null on Failure.
  */
 static void *
 _base_get_chain_buffer_dma_to_chain_buffer(struct MPT3SAS_ADAPTER *ioc,
@@ -350,8 +351,6 @@ _base_get_chain_buffer_dma_to_chain_buffer(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object.
  * @mpi_request: mf request pointer.
  * @smid: system request message index.
- *
- * @Returns: Nothing.
  */
 static void _clone_sg_entries(struct MPT3SAS_ADAPTER *ioc,
 		void *mpi_request, u16 smid)
@@ -524,8 +523,9 @@ eob_clone_chain:
  *  mpt3sas_remove_dead_ioc_func - kthread context to remove dead ioc
  * @arg: input argument, used to derive ioc
  *
- * Return 0 if controller is removed from pci subsystem.
- * Return -1 for other case.
+ * Return:
+ * 0 if controller is removed from pci subsystem.
+ * -1 for other case.
  */
 static int mpt3sas_remove_dead_ioc_func(void *arg)
 {
@@ -545,9 +545,8 @@ static int mpt3sas_remove_dead_ioc_func(void *arg)
 /**
  * _base_fault_reset_work - workq handling ioc fault conditions
  * @work: input argument, used to derive ioc
- * Context: sleep.
  *
- * Return nothing.
+ * Context: sleep.
  */
 static void
 _base_fault_reset_work(struct work_struct *work)
@@ -638,9 +637,8 @@ _base_fault_reset_work(struct work_struct *work)
 /**
  * mpt3sas_base_start_watchdog - start the fault_reset_work_q
  * @ioc: per adapter object
- * Context: sleep.
  *
- * Return nothing.
+ * Context: sleep.
  */
 void
 mpt3sas_base_start_watchdog(struct MPT3SAS_ADAPTER *ioc)
@@ -674,9 +672,8 @@ mpt3sas_base_start_watchdog(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_stop_watchdog - stop the fault_reset_work_q
  * @ioc: per adapter object
- * Context: sleep.
  *
- * Return nothing.
+ * Context: sleep.
  */
 void
 mpt3sas_base_stop_watchdog(struct MPT3SAS_ADAPTER *ioc)
@@ -699,8 +696,6 @@ mpt3sas_base_stop_watchdog(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_base_fault_info - verbose translation of firmware FAULT code
  * @ioc: per adapter object
  * @fault_code: fault code
- *
- * Return nothing.
  */
 void
 mpt3sas_base_fault_info(struct MPT3SAS_ADAPTER *ioc , u16 fault_code)
@@ -749,8 +744,6 @@ mpt3sas_halt_firmware(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @mpi_reply: reply mf payload returned from firmware
  * @request_hdr: request mf
- *
- * Return nothing.
  */
 static void
 _base_sas_ioc_info(struct MPT3SAS_ADAPTER *ioc, MPI2DefaultReply_t *mpi_reply,
@@ -973,8 +966,6 @@ _base_sas_ioc_info(struct MPT3SAS_ADAPTER *ioc, MPI2DefaultReply_t *mpi_reply,
  * _base_display_event_data - verbose translation of firmware asyn events
  * @ioc: per adapter object
  * @mpi_reply: reply mf payload returned from firmware
- *
- * Return nothing.
  */
 static void
 _base_display_event_data(struct MPT3SAS_ADAPTER *ioc,
@@ -1093,8 +1084,6 @@ _base_display_event_data(struct MPT3SAS_ADAPTER *ioc,
  * _base_sas_log_info - verbose translation of firmware log info
  * @ioc: per adapter object
  * @log_info: log info
- *
- * Return nothing.
  */
 static void
 _base_sas_log_info(struct MPT3SAS_ADAPTER *ioc , u32 log_info)
@@ -1152,8 +1141,6 @@ _base_sas_log_info(struct MPT3SAS_ADAPTER *ioc , u32 log_info)
  * @smid: system request message index
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
- *
- * Return nothing.
  */
 static void
 _base_display_reply_info(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -1195,8 +1182,9 @@ _base_display_reply_info(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return:
+ * 1 meaning mf should be freed from _base_interrupt
+ * 0 means the mf is freed from this function.
  */
 u8
 mpt3sas_base_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -1228,8 +1216,9 @@ mpt3sas_base_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return:
+ * 1 meaning mf should be freed from _base_interrupt
+ * 0 means the mf is freed from this function.
  */
 static u8
 _base_async_event(struct MPT3SAS_ADAPTER *ioc, u8 msix_index, u32 reply)
@@ -1307,7 +1296,7 @@ _get_st_from_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Return callback index.
+ * Return: callback index.
  */
 static u8
 _base_get_cb_idx(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -1340,8 +1329,6 @@ _base_get_cb_idx(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  *
  * Disabling ResetIRQ, Reply and Doorbell Interrupts
- *
- * Return nothing.
  */
 static void
 _base_mask_interrupts(struct MPT3SAS_ADAPTER *ioc)
@@ -1360,8 +1347,6 @@ _base_mask_interrupts(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Enabling only Reply Interrupts
- *
- * Return nothing.
  */
 static void
 _base_unmask_interrupts(struct MPT3SAS_ADAPTER *ioc)
@@ -1386,9 +1371,8 @@ union reply_descriptor {
  * _base_interrupt - MPT adapter (IOC) specific interrupt handler.
  * @irq: irq number (not used)
  * @bus_id: bus identifier cookie == pointer to MPT_ADAPTER structure
- * @r: pt_regs pointer (not used)
  *
- * Return IRQ_HANDLE if processed, else IRQ_NONE.
+ * Return: IRQ_HANDLED if processed, else IRQ_NONE.
  */
 static irqreturn_t
 _base_interrupt(int irq, void *bus_id)
@@ -1563,6 +1547,7 @@ _base_interrupt(int irq, void *bus_id)
  * _base_is_controller_msix_enabled - is controller support muli-reply queues
  * @ioc: per adapter object
  *
+ * Return: Whether or not MSI/X is enabled.
  */
 static inline int
 _base_is_controller_msix_enabled(struct MPT3SAS_ADAPTER *ioc)
@@ -1577,8 +1562,6 @@ _base_is_controller_msix_enabled(struct MPT3SAS_ADAPTER *ioc)
  * Context: non ISR conext
  *
  * Called when a Task Management request has completed.
- *
- * Return nothing.
  */
 void
 mpt3sas_base_sync_reply_irqs(struct MPT3SAS_ADAPTER *ioc)
@@ -1605,8 +1588,6 @@ mpt3sas_base_sync_reply_irqs(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_release_callback_handler - clear interrupt callback handler
  * @cb_idx: callback index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_release_callback_handler(u8 cb_idx)
@@ -1618,7 +1599,7 @@ mpt3sas_base_release_callback_handler(u8 cb_idx)
  * mpt3sas_base_register_callback_handler - obtain index for the interrupt callback handler
  * @cb_func: callback function
  *
- * Returns cb_func.
+ * Return: Index of @cb_func.
  */
 u8
 mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func)
@@ -1635,8 +1616,6 @@ mpt3sas_base_register_callback_handler(MPT_CALLBACK cb_func)
 
 /**
  * mpt3sas_base_initialize_callback_handler - initialize the interrupt callback handler
- *
- * Return nothing.
  */
 void
 mpt3sas_base_initialize_callback_handler(void)
@@ -1656,8 +1635,6 @@ mpt3sas_base_initialize_callback_handler(void)
  * Create a zero length scatter gather entry to insure the IOCs hardware has
  * something to use if the target device goes brain dead and tries
  * to send data even when none is asked for.
- *
- * Return nothing.
  */
 static void
 _base_build_zero_len_sge(struct MPT3SAS_ADAPTER *ioc, void *paddr)
@@ -1674,8 +1651,6 @@ _base_build_zero_len_sge(struct MPT3SAS_ADAPTER *ioc, void *paddr)
  * @paddr: virtual address for SGE
  * @flags_length: SGE flags and data transfer length
  * @dma_addr: Physical address
- *
- * Return nothing.
  */
 static void
 _base_add_sg_single_32(void *paddr, u32 flags_length, dma_addr_t dma_addr)
@@ -1694,8 +1669,6 @@ _base_add_sg_single_32(void *paddr, u32 flags_length, dma_addr_t dma_addr)
  * @paddr: virtual address for SGE
  * @flags_length: SGE flags and data transfer length
  * @dma_addr: Physical address
- *
- * Return nothing.
  */
 static void
 _base_add_sg_single_64(void *paddr, u32 flags_length, dma_addr_t dma_addr)
@@ -1713,7 +1686,7 @@ _base_add_sg_single_64(void *paddr, u32 flags_length, dma_addr_t dma_addr)
  * @ioc: per adapter object
  * @scmd: SCSI commands of the IO request
  *
- * Returns chain tracker from chain_lookup table using key as
+ * Return: chain tracker from chain_lookup table using key as
  * smid and smid's chain_offset.
  */
 static struct chain_tracker *
@@ -1743,8 +1716,6 @@ _base_get_chain_buffer_tracker(struct MPT3SAS_ADAPTER *ioc,
  * @data_out_sz: data xfer size for WRITES
  * @data_in_dma: physical address for READS
  * @data_in_sz: data xfer size for READS
- *
- * Return nothing.
  */
 static void
 _base_build_sg(struct MPT3SAS_ADAPTER *ioc, void *psge,
@@ -1805,7 +1776,7 @@ _base_build_sg(struct MPT3SAS_ADAPTER *ioc, void *psge,
  * describes the first data memory segment, and PRP2 contains a pointer to a PRP
  * list located elsewhere in memory to describe the remaining data memory
  * segments.  The PRP list will be contiguous.
-
+ *
  * The native SGL for NVMe devices is a Physical Region Page (PRP).  A PRP
  * consists of a list of PRP entries to describe a number of noncontigous
  * physical memory segments as a single memory buffer, just as a SGL does.  Note
@@ -1848,8 +1819,6 @@ _base_build_sg(struct MPT3SAS_ADAPTER *ioc, void *psge,
  * @data_out_sz: data xfer size for WRITES
  * @data_in_dma: physical address for READS
  * @data_in_sz: data xfer size for READS
- *
- * Returns nothing.
  */
 static void
 _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -2015,7 +1984,7 @@ _base_build_nvme_prp(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @smid:		msg Index
  * @sge_count:		scatter gather element count.
  *
- * Returns:		true: PRPs are built
+ * Return:		true: PRPs are built
  *			false: IEEE SGLs needs to be built
  */
 static void
@@ -2176,7 +2145,7 @@ base_is_prp_possible(struct MPT3SAS_ADAPTER *ioc,
  * @scmd: scsi command
  * @pcie_device: points to the PCIe device's info
  *
- * Returns 0 if native SGL was built, 1 if no SGL was built
+ * Return: 0 if native SGL was built, 1 if no SGL was built
  */
 static int
 _base_check_pcie_native_sgl(struct MPT3SAS_ADAPTER *ioc,
@@ -2220,8 +2189,6 @@ out:
  * @chain_offset: number of 128 byte elements from start of segment
  * @length: data transfer length
  * @dma_addr: Physical address
- *
- * Return nothing.
  */
 static void
 _base_add_sg_single_ieee(void *paddr, u8 flags, u8 chain_offset, u32 length,
@@ -2243,8 +2210,6 @@ _base_add_sg_single_ieee(void *paddr, u8 flags, u8 chain_offset, u32 length,
  * Create a zero length scatter gather entry to insure the IOCs hardware has
  * something to use if the target device goes brain dead and tries
  * to send data even when none is asked for.
- *
- * Return nothing.
  */
 static void
 _base_build_zero_len_sge_ieee(struct MPT3SAS_ADAPTER *ioc, void *paddr)
@@ -2268,7 +2233,7 @@ _base_build_zero_len_sge_ieee(struct MPT3SAS_ADAPTER *ioc, void *paddr)
  * The main routine that builds scatter gather table from a given
  * scsi request sent via the .queuecommand main handler.
  *
- * Returns 0 success, anything else error
+ * Return: 0 success, anything else error
  */
 static int
 _base_build_sg_scmd(struct MPT3SAS_ADAPTER *ioc,
@@ -2413,7 +2378,7 @@ _base_build_sg_scmd(struct MPT3SAS_ADAPTER *ioc,
  * The main routine that builds scatter gather table from a given
  * scsi request sent via the .queuecommand main handler.
  *
- * Returns 0 success, anything else error
+ * Return: 0 success, anything else error
  */
 static int
 _base_build_sg_scmd_ieee(struct MPT3SAS_ADAPTER *ioc,
@@ -2544,8 +2509,6 @@ _base_build_sg_scmd_ieee(struct MPT3SAS_ADAPTER *ioc,
  * @data_out_sz: data xfer size for WRITES
  * @data_in_dma: physical address for READS
  * @data_in_sz: data xfer size for READS
- *
- * Return nothing.
  */
 static void
 _base_build_sg_ieee(struct MPT3SAS_ADAPTER *ioc, void *psge,
@@ -2595,7 +2558,7 @@ _base_build_sg_ieee(struct MPT3SAS_ADAPTER *ioc, void *psge,
  * @ioc: per adapter object
  * @pdev: PCI device struct
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_config_dma_addressing(struct MPT3SAS_ADAPTER *ioc, struct pci_dev *pdev)
@@ -2963,7 +2926,7 @@ mpt3sas_base_unmap_resources(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_base_map_resources - map in controller resources (io/irq/memap)
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
@@ -3114,7 +3077,7 @@ mpt3sas_base_map_resources(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @smid: system request message index(smid zero is invalid)
  *
- * Returns virt pointer to message frame.
+ * Return: virt pointer to message frame.
  */
 void *
 mpt3sas_base_get_msg_frame(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3127,7 +3090,7 @@ mpt3sas_base_get_msg_frame(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns virt pointer to sense buffer.
+ * Return: virt pointer to sense buffer.
  */
 void *
 mpt3sas_base_get_sense_buffer(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3140,7 +3103,7 @@ mpt3sas_base_get_sense_buffer(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns phys pointer to the low 32bit address of the sense buffer.
+ * Return: phys pointer to the low 32bit address of the sense buffer.
  */
 __le32
 mpt3sas_base_get_sense_buffer_dma(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3154,7 +3117,7 @@ mpt3sas_base_get_sense_buffer_dma(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns virt pointer to a PCIe SGL.
+ * Return: virt pointer to a PCIe SGL.
  */
 void *
 mpt3sas_base_get_pcie_sgl(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3167,7 +3130,7 @@ mpt3sas_base_get_pcie_sgl(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns phys pointer to the address of the PCIe buffer.
+ * Return: phys pointer to the address of the PCIe buffer.
  */
 dma_addr_t
 mpt3sas_base_get_pcie_sgl_dma(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3201,7 +3164,7 @@ _base_get_msix_index(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @cb_idx: callback index
  *
- * Returns smid (zero is invalid)
+ * Return: smid (zero is invalid)
  */
 u16
 mpt3sas_base_get_smid(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx)
@@ -3233,7 +3196,7 @@ mpt3sas_base_get_smid(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx)
  * @cb_idx: callback index
  * @scmd: pointer to scsi command object
  *
- * Returns smid (zero is invalid)
+ * Return: smid (zero is invalid)
  */
 u16
 mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
@@ -3256,7 +3219,7 @@ mpt3sas_base_get_smid_scsiio(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx,
  * @ioc: per adapter object
  * @cb_idx: callback index
  *
- * Returns smid (zero is invalid)
+ * Return: smid (zero is invalid)
  */
 u16
 mpt3sas_base_get_smid_hpr(struct MPT3SAS_ADAPTER *ioc, u8 cb_idx)
@@ -3307,8 +3270,6 @@ void mpt3sas_base_clear_st(struct MPT3SAS_ADAPTER *ioc,
  * mpt3sas_base_free_smid - put smid back on free_list
  * @ioc: per adapter object
  * @smid: system request message index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_free_smid(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3371,7 +3332,6 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 
 /**
  * _base_writeq - 64 bit write to MMIO
- * @ioc: per adapter object
  * @b: data payload
  * @addr: address in MMIO space
  * @writeq_lock: spin lock
@@ -3399,8 +3359,6 @@ _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _base_put_smid_mpi_ep_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
@@ -3429,8 +3387,6 @@ _base_put_smid_mpi_ep_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
@@ -3453,8 +3409,6 @@ _base_put_smid_scsi_io(struct MPT3SAS_ADAPTER *ioc, u16 smid, u16 handle)
  * @ioc: per adapter object
  * @smid: system request message index
  * @handle: device handle
- *
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -3478,7 +3432,6 @@ mpt3sas_base_put_smid_fast_path(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  * @ioc: per adapter object
  * @smid: system request message index
  * @msix_task: msix_task will be same as msix of IO incase of task abort else 0.
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -3521,8 +3474,6 @@ mpt3sas_base_put_smid_hi_priority(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  *  firmware
  * @ioc: per adapter object
  * @smid: system request message index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_nvme_encap(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3544,8 +3495,6 @@ mpt3sas_base_put_smid_nvme_encap(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * mpt3sas_base_put_smid_default - Default, primarily used for config pages
  * @ioc: per adapter object
  * @smid: system request message index
- *
- * Return nothing.
  */
 void
 mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -3582,8 +3531,6 @@ mpt3sas_base_put_smid_default(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 /**
  * _base_display_OEMs_branding - Display branding string
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _base_display_OEMs_branding(struct MPT3SAS_ADAPTER *ioc)
@@ -3844,7 +3791,7 @@ _base_display_OEMs_branding(struct MPT3SAS_ADAPTER *ioc)
  *				version from FW Image Header.
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 	static int
 _base_display_fwpkg_version(struct MPT3SAS_ADAPTER *ioc)
@@ -3941,8 +3888,6 @@ out:
 /**
  * _base_display_ioc_capabilities - Disply IOC's capabilities.
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _base_display_ioc_capabilities(struct MPT3SAS_ADAPTER *ioc)
@@ -4058,8 +4003,6 @@ _base_display_ioc_capabilities(struct MPT3SAS_ADAPTER *ioc)
  * @device_missing_delay: amount of time till device is reported missing
  * @io_missing_delay: interval IO is returned when there is a missing device
  *
- * Return nothing.
- *
  * Passed on the command line, this function will modify the device missing
  * delay, as well as the io missing delay. This should be called at driver
  * load time.
@@ -4142,11 +4085,10 @@ mpt3sas_base_update_missing_delay(struct MPT3SAS_ADAPTER *ioc,
 out:
 	kfree(sas_iounit_pg1);
 }
+
 /**
  * _base_static_config_pages - static start of day config pages
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
@@ -4218,8 +4160,6 @@ _base_static_config_pages(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Free memory allocated during encloure add.
- *
- * Return nothing.
  */
 void
 mpt3sas_free_enclosure_list(struct MPT3SAS_ADAPTER *ioc)
@@ -4239,8 +4179,6 @@ mpt3sas_free_enclosure_list(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Free memory allocated from _base_allocate_memory_pools.
- *
- * Return nothing.
  */
 static void
 _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc)
@@ -4361,9 +4299,8 @@ _base_release_memory_pools(struct MPT3SAS_ADAPTER *ioc)
  * @reply_pool_start_address: Base address of a reply queue set
  * @pool_sz: Size of single Reply Descriptor Post Queues pool size
  *
- * Returns 1 if reply queues in a set have a same upper 32bits
- * in their base memory address,
- * else 0
+ * Return: 1 if reply queues in a set have a same upper 32bits in their base
+ * memory address, else 0.
  */
 
 static int
@@ -4384,7 +4321,7 @@ is_MSB_are_same(long reply_pool_start_address, u32 pool_sz)
  * _base_allocate_memory_pools - allocate start of day memory pools
  * @ioc: per adapter object
  *
- * Returns 0 success, anything else error
+ * Return: 0 success, anything else error.
  */
 static int
 _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
@@ -4986,7 +4923,7 @@ _base_allocate_memory_pools(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: Pointer to MPT_ADAPTER structure
  * @cooked: Request raw or cooked IOC state
  *
- * Returns all IOC Doorbell register bits if cooked==0, else just the
+ * Return: all IOC Doorbell register bits if cooked==0, else just the
  * Doorbell bits in MPI_IOC_STATE_MASK.
  */
 u32
@@ -5001,10 +4938,11 @@ mpt3sas_base_get_iocstate(struct MPT3SAS_ADAPTER *ioc, int cooked)
 
 /**
  * _base_wait_on_iocstate - waiting on a particular ioc state
+ * @ioc: ?
  * @ioc_state: controller state { READY, OPERATIONAL, or RESET }
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_wait_on_iocstate(struct MPT3SAS_ADAPTER *ioc, u32 ioc_state, int timeout)
@@ -5032,9 +4970,8 @@ _base_wait_on_iocstate(struct MPT3SAS_ADAPTER *ioc, u32 ioc_state, int timeout)
  * _base_wait_for_doorbell_int - waiting for controller interrupt(generated by
  * a write to the doorbell)
  * @ioc: per adapter object
- * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  * Notes: MPI2_HIS_IOC2SYS_DB_STATUS - set to one when IOC writes to doorbell.
  */
@@ -5101,7 +5038,7 @@ _base_spin_on_doorbell_int(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * @ioc: per adapter object
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  * Notes: MPI2_HIS_SYS2IOC_DB_STATUS - set to one when host writes to
  * doorbell.
@@ -5148,8 +5085,7 @@ _base_wait_for_doorbell_ack(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * @ioc: per adapter object
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
- *
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_wait_for_doorbell_not_used(struct MPT3SAS_ADAPTER *ioc, int timeout)
@@ -5184,7 +5120,7 @@ _base_wait_for_doorbell_not_used(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * @reset_type: currently only supports: MPI2_FUNCTION_IOC_MESSAGE_UNIT_RESET
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_send_ioc_reset(struct MPT3SAS_ADAPTER *ioc, u8 reset_type, int timeout)
@@ -5233,7 +5169,7 @@ _base_send_ioc_reset(struct MPT3SAS_ADAPTER *ioc, u8 reset_type, int timeout)
  * @reply: pointer to reply payload
  * @timeout: timeout in second
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
@@ -5357,7 +5293,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
  * identifying information about the device, in addition allows the host to
  * remove IOC resources associated with the device.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
@@ -5458,7 +5394,7 @@ mpt3sas_base_sas_iounit_control(struct MPT3SAS_ADAPTER *ioc,
  * The SCSI Enclosure Processor request message causes the IOC to
  * communicate with SES devices to control LED status signals.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
@@ -5546,8 +5482,9 @@ mpt3sas_base_scsi_enclosure_processor(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _base_get_port_facts - obtain port facts reply and save in ioc
  * @ioc: per adapter object
+ * @port: ?
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_get_port_facts(struct MPT3SAS_ADAPTER *ioc, int port)
@@ -5590,7 +5527,7 @@ _base_get_port_facts(struct MPT3SAS_ADAPTER *ioc, int port)
  * @ioc: per adapter object
  * @timeout:
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout)
@@ -5644,7 +5581,7 @@ _base_wait_for_iocstate(struct MPT3SAS_ADAPTER *ioc, int timeout)
  * _base_get_ioc_facts - obtain ioc facts reply and save in ioc
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc)
@@ -5746,7 +5683,7 @@ _base_get_ioc_facts(struct MPT3SAS_ADAPTER *ioc)
  * _base_send_ioc_init - send ioc_init to firmware
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc)
@@ -5847,8 +5784,8 @@ _base_send_ioc_init(struct MPT3SAS_ADAPTER *ioc)
  * @msix_index: MSIX table index supplied by the OS
  * @reply: reply message frame(lower 32bit addr)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *          0 means the mf is freed from this function.
  */
 u8
 mpt3sas_port_enable_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -5893,7 +5830,7 @@ mpt3sas_port_enable_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * _base_send_port_enable - send port_enable(discovery stuff) to firmware
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_send_port_enable(struct MPT3SAS_ADAPTER *ioc)
@@ -5960,7 +5897,7 @@ _base_send_port_enable(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_port_enable - initiate firmware discovery (don't wait for reply)
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc)
@@ -6000,7 +5937,7 @@ mpt3sas_port_enable(struct MPT3SAS_ADAPTER *ioc)
  * Decide whether to wait on discovery to complete. Used to either
  * locate boot device, or report volumes ahead of physical devices.
  *
- * Returns 1 for wait, 0 for don't wait
+ * Return: 1 for wait, 0 for don't wait.
  */
 static int
 _base_determine_wait_on_discovery(struct MPT3SAS_ADAPTER *ioc)
@@ -6072,7 +6009,7 @@ _base_unmask_events(struct MPT3SAS_ADAPTER *ioc, u16 event)
  * _base_event_notification - send event notification
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_event_notification(struct MPT3SAS_ADAPTER *ioc)
@@ -6129,7 +6066,7 @@ _base_event_notification(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_validate_event_type - validating event types
  * @ioc: per adapter object
- * @event: firmware event
+ * @event_type: firmware event
  *
  * This will turn on firmware event notification when application
  * ask for that event. We don't mask events that are already enabled.
@@ -6167,7 +6104,7 @@ mpt3sas_base_validate_event_type(struct MPT3SAS_ADAPTER *ioc, u32 *event_type)
  * _base_diag_reset - the "big hammer" start of day reset
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
@@ -6281,7 +6218,7 @@ _base_diag_reset(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @type: FORCE_BIG_HAMMER or SOFT_RESET
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
@@ -6350,7 +6287,7 @@ _base_make_ioc_ready(struct MPT3SAS_ADAPTER *ioc, enum reset_type type)
  * _base_make_ioc_operational - put controller in OPERATIONAL state
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc)
@@ -6523,8 +6460,6 @@ _base_make_ioc_operational(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_free_resources - free resources controller resources
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 void
 mpt3sas_base_free_resources(struct MPT3SAS_ADAPTER *ioc)
@@ -6550,7 +6485,7 @@ mpt3sas_base_free_resources(struct MPT3SAS_ADAPTER *ioc)
  * mpt3sas_base_attach - attach controller instance
  * @ioc: per adapter object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
@@ -6807,8 +6742,6 @@ mpt3sas_base_attach(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_base_detach - remove controller instance
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 void
 mpt3sas_base_detach(struct MPT3SAS_ADAPTER *ioc)
@@ -6938,7 +6871,7 @@ mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: Pointer to MPT_ADAPTER structure
  * @type: FORCE_BIG_HAMMER or SOFT_RESET
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_base_hard_reset_handler(struct MPT3SAS_ADAPTER *ioc,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_config.c b/drivers/scsi/mpt3sas/mpt3sas_config.c
index 0d87e7bef215..d29a2dcc7d0e 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_config.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_config.c
@@ -198,7 +198,7 @@ _config_display_some_debug(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  *
  * A wrapper for obtaining dma-able memory for config page request.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _config_alloc_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
@@ -230,7 +230,7 @@ _config_alloc_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
  *
  * A wrapper to free dma-able memory when using _config_alloc_config_dma_memory.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static void
 _config_free_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
@@ -251,8 +251,8 @@ _config_free_config_dma_memory(struct MPT3SAS_ADAPTER *ioc,
  *
  * The callback handler when using _config_request.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_config_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -295,7 +295,7 @@ mpt3sas_config_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  *
  * The callback index is set inside `ioc->config_cb_idx.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
@@ -518,7 +518,7 @@ _config_request(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigRequest_t
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -555,7 +555,7 @@ mpt3sas_config_get_manufacturing_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @sz: size of buffer passed in config_page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg7(struct MPT3SAS_ADAPTER *ioc,
@@ -592,7 +592,7 @@ mpt3sas_config_get_manufacturing_pg7(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg10(struct MPT3SAS_ADAPTER *ioc,
@@ -629,7 +629,7 @@ mpt3sas_config_get_manufacturing_pg10(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
@@ -666,7 +666,7 @@ mpt3sas_config_get_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_set_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
@@ -707,7 +707,7 @@ mpt3sas_config_set_manufacturing_pg11(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_bios_pg2(struct MPT3SAS_ADAPTER *ioc,
@@ -743,7 +743,7 @@ mpt3sas_config_get_bios_pg2(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_bios_pg3(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -779,7 +779,7 @@ mpt3sas_config_get_bios_pg3(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -815,7 +815,7 @@ mpt3sas_config_get_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -851,7 +851,7 @@ mpt3sas_config_get_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_set_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -888,7 +888,7 @@ mpt3sas_config_set_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @sz: size of buffer passed in config_page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg3(struct MPT3SAS_ADAPTER *ioc,
@@ -923,7 +923,7 @@ mpt3sas_config_get_iounit_pg3(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_iounit_pg8(struct MPT3SAS_ADAPTER *ioc,
@@ -959,7 +959,7 @@ mpt3sas_config_get_iounit_pg8(struct MPT3SAS_ADAPTER *ioc,
  * @config_page: contents of the config page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_ioc_pg8(struct MPT3SAS_ADAPTER *ioc,
@@ -997,7 +997,7 @@ mpt3sas_config_get_ioc_pg8(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_device_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1038,7 +1038,7 @@ mpt3sas_config_get_sas_device_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_device_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1079,7 +1079,7 @@ mpt3sas_config_get_sas_device_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_pcie_device_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1120,7 +1120,7 @@ out:
  * @handle: device handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_pcie_device_pg2(struct MPT3SAS_ADAPTER *ioc,
@@ -1158,7 +1158,7 @@ out:
  * @num_phys: pointer returned with the number of phys
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_number_hba_phys(struct MPT3SAS_ADAPTER *ioc, u8 *num_phys)
@@ -1208,7 +1208,7 @@ mpt3sas_config_get_number_hba_phys(struct MPT3SAS_ADAPTER *ioc, u8 *num_phys)
  * Calling function should call config_get_number_hba_phys prior to
  * this function, so enough memory is allocated for config_page.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1249,7 +1249,7 @@ mpt3sas_config_get_sas_iounit_pg0(struct MPT3SAS_ADAPTER *ioc,
  * Calling function should call config_get_number_hba_phys prior to
  * this function, so enough memory is allocated for config_page.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1290,7 +1290,7 @@ mpt3sas_config_get_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * Calling function should call config_get_number_hba_phys prior to
  * this function, so enough memory is allocated for config_page.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_set_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1332,7 +1332,7 @@ mpt3sas_config_set_sas_iounit_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @handle: expander handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_expander_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1372,7 +1372,7 @@ mpt3sas_config_get_expander_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @handle: expander handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_expander_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1415,7 +1415,7 @@ mpt3sas_config_get_expander_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @handle: expander handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_enclosure_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1454,7 +1454,7 @@ mpt3sas_config_get_enclosure_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @phy_number: phy number
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_phy_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1494,7 +1494,7 @@ mpt3sas_config_get_phy_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @phy_number: phy number
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_phy_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1535,7 +1535,7 @@ mpt3sas_config_get_phy_pg1(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @handle: volume handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_raid_volume_pg1(struct MPT3SAS_ADAPTER *ioc,
@@ -1573,7 +1573,7 @@ mpt3sas_config_get_raid_volume_pg1(struct MPT3SAS_ADAPTER *ioc,
  * @num_pds: returns pds count
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_number_pds(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -1625,7 +1625,7 @@ mpt3sas_config_get_number_pds(struct MPT3SAS_ADAPTER *ioc, u16 handle,
  * @sz: size of buffer passed in config_page
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_raid_volume_pg0(struct MPT3SAS_ADAPTER *ioc,
@@ -1664,7 +1664,7 @@ mpt3sas_config_get_raid_volume_pg0(struct MPT3SAS_ADAPTER *ioc,
  * @form_specific: specific to the form
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_phys_disk_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
@@ -1703,7 +1703,7 @@ mpt3sas_config_get_phys_disk_pg0(struct MPT3SAS_ADAPTER *ioc, Mpi2ConfigReply_t
  * @volume_handle: volume handle
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_volume_handle(struct MPT3SAS_ADAPTER *ioc, u16 pd_handle,
@@ -1793,7 +1793,7 @@ mpt3sas_config_get_volume_handle(struct MPT3SAS_ADAPTER *ioc, u16 pd_handle,
  * @wwid: volume wwid
  * Context: sleep.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_config_get_volume_wwid(struct MPT3SAS_ADAPTER *ioc, u16 volume_handle,
diff --git a/drivers/scsi/mpt3sas/mpt3sas_ctl.c b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
index 0b8fd13593bf..5e8c059ce2c9 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_ctl.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_ctl.c
@@ -253,8 +253,8 @@ _ctl_display_some_debug(struct MPT3SAS_ADAPTER *ioc, u16 smid,
  *
  * The callback handler when using ioc->ctl_cb_idx.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -317,7 +317,7 @@ mpt3sas_ctl_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * The bitmask in ioc->event_type[] indicates which events should be
  * be saved in the driver event_log.  This bitmask is set by application.
  *
- * Returns 1 when event should be captured, or zero means no match.
+ * Return: 1 when event should be captured, or zero means no match.
  */
 static int
 _ctl_check_event_type(struct MPT3SAS_ADAPTER *ioc, u16 event)
@@ -339,8 +339,6 @@ _ctl_check_event_type(struct MPT3SAS_ADAPTER *ioc, u16 event)
  * mpt3sas_ctl_add_to_event_log - add event
  * @ioc: per adapter object
  * @mpi_reply: reply message frame
- *
- * Return nothing.
  */
 void
 mpt3sas_ctl_add_to_event_log(struct MPT3SAS_ADAPTER *ioc,
@@ -395,8 +393,8 @@ mpt3sas_ctl_add_to_event_log(struct MPT3SAS_ADAPTER *ioc,
  * This function merely adds a new work task into ioc->firmware_event_thread.
  * The tasks are worked from _firmware_event_work in user context.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
@@ -412,12 +410,12 @@ mpt3sas_ctl_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
 
 /**
  * _ctl_verify_adapter - validates ioc_number passed from application
- * @ioc: per adapter object
+ * @ioc_number: ?
  * @iocpp: The ioc pointer is returned in this.
  * @mpi_version: will be MPI2_VERSION for mpt2ctl ioctl device &
  * MPI25_VERSION | MPI26_VERSION for mpt3ctl ioctl device.
  *
- * Return (-1) means error, else ioc_number.
+ * Return: (-1) means error, else ioc_number.
  */
 static int
 _ctl_verify_adapter(int ioc_number, struct MPT3SAS_ADAPTER **iocpp,
@@ -525,9 +523,9 @@ void mpt3sas_ctl_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
 
 /**
  * _ctl_fasync -
- * @fd -
- * @filep -
- * @mode -
+ * @fd: ?
+ * @filep: ?
+ * @mode: ?
  *
  * Called when application request fasyn callback handler.
  */
@@ -539,8 +537,8 @@ _ctl_fasync(int fd, struct file *filep, int mode)
 
 /**
  * _ctl_poll -
- * @file -
- * @wait -
+ * @filep: ?
+ * @wait: ?
  *
  */
 static __poll_t
@@ -565,10 +563,10 @@ _ctl_poll(struct file *filep, poll_table *wait)
 /**
  * _ctl_set_task_mid - assign an active smid to tm request
  * @ioc: per adapter object
- * @karg - (struct mpt3_ioctl_command)
- * @tm_request - pointer to mf from user space
+ * @karg: (struct mpt3_ioctl_command)
+ * @tm_request: pointer to mf from user space
  *
- * Returns 0 when an smid if found, else fail.
+ * Return: 0 when an smid if found, else fail.
  * during failure, the reply frame is filled.
  */
 static int
@@ -643,8 +641,8 @@ _ctl_set_task_mid(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command *karg,
 /**
  * _ctl_do_mpt_command - main handler for MPT3COMMAND opcode
  * @ioc: per adapter object
- * @karg - (struct mpt3_ioctl_command)
- * @mf - pointer to mf in user space
+ * @karg: (struct mpt3_ioctl_command)
+ * @mf: pointer to mf in user space
  */
 static long
 _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
@@ -1123,7 +1121,7 @@ _ctl_do_mpt_command(struct MPT3SAS_ADAPTER *ioc, struct mpt3_ioctl_command karg,
 /**
  * _ctl_getiocinfo - main handler for MPT3IOCINFO opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_getiocinfo(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1177,7 +1175,7 @@ _ctl_getiocinfo(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_eventquery - main handler for MPT3EVENTQUERY opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_eventquery(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1208,7 +1206,7 @@ _ctl_eventquery(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_eventenable - main handler for MPT3EVENTENABLE opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_eventenable(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1246,7 +1244,7 @@ _ctl_eventenable(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_eventreport - main handler for MPT3EVENTREPORT opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_eventreport(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1290,7 +1288,7 @@ _ctl_eventreport(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_do_reset - main handler for MPT3HARDRESET opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_do_reset(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1428,7 +1426,7 @@ _ctl_btdh_search_raid_device(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _ctl_btdh_mapping - main handler for MPT3BTDHMAPPING opcode
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_btdh_mapping(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -1726,7 +1724,7 @@ mpt3sas_enable_diag_buffer(struct MPT3SAS_ADAPTER *ioc, u8 bits_to_register)
 /**
  * _ctl_diag_register - application register with driver
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  *
  * This will allow the driver to setup any required buffers that will be
  * needed by firmware to communicate with the driver.
@@ -1750,7 +1748,7 @@ _ctl_diag_register(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_diag_unregister - application unregister with driver
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  *
  * This will allow the driver to cleanup any memory allocated for diag
  * messages and to free up any resources.
@@ -1823,7 +1821,7 @@ _ctl_diag_unregister(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_diag_query - query relevant info associated with diag buffers
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  *
  * The application will send only buffer_type and unique_id.  Driver will
  * inspect unique_id first, if valid, fill in all the info.  If unique_id is
@@ -1910,8 +1908,8 @@ _ctl_diag_query(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * mpt3sas_send_diag_release - Diag Release Message
  * @ioc: per adapter object
- * @buffer_type - specifies either TRACE, SNAPSHOT, or EXTENDED
- * @issue_reset - specifies whether host reset is required.
+ * @buffer_type: specifies either TRACE, SNAPSHOT, or EXTENDED
+ * @issue_reset: specifies whether host reset is required.
  *
  */
 int
@@ -2013,7 +2011,8 @@ mpt3sas_send_diag_release(struct MPT3SAS_ADAPTER *ioc, u8 buffer_type,
 
 /**
  * _ctl_diag_release - request to send Diag Release Message to firmware
- * @arg - user space buffer containing ioctl content
+ * @ioc: ?
+ * @arg: user space buffer containing ioctl content
  *
  * This allows ownership of the specified buffer to returned to the driver,
  * allowing an application to read the buffer without fear that firmware is
@@ -2102,7 +2101,7 @@ _ctl_diag_release(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_diag_read_buffer - request for copy of the diag buffer
  * @ioc: per adapter object
- * @arg - user space buffer containing ioctl content
+ * @arg: user space buffer containing ioctl content
  */
 static long
 _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
@@ -2286,8 +2285,8 @@ _ctl_diag_read_buffer(struct MPT3SAS_ADAPTER *ioc, void __user *arg)
 /**
  * _ctl_compat_mpt_command - convert 32bit pointers to 64bit.
  * @ioc: per adapter object
- * @cmd - ioctl opcode
- * @arg - (struct mpt3_ioctl_command32)
+ * @cmd: ioctl opcode
+ * @arg: (struct mpt3_ioctl_command32)
  *
  * MPT3COMMAND32 - Handle 32bit applications running on 64bit os.
  */
@@ -2330,10 +2329,10 @@ _ctl_compat_mpt_command(struct MPT3SAS_ADAPTER *ioc, unsigned cmd,
 
 /**
  * _ctl_ioctl_main - main ioctl entry point
- * @file - (struct file)
- * @cmd - ioctl opcode
- * @arg - user space data buffer
- * @compat - handles 32 bit applications in 64bit os
+ * @file:  (struct file)
+ * @cmd:  ioctl opcode
+ * @arg:  user space data buffer
+ * @compat:  handles 32 bit applications in 64bit os
  * @mpi_version: will be MPI2_VERSION for mpt2ctl ioctl device &
  * MPI25_VERSION | MPI26_VERSION for mpt3ctl ioctl device.
  */
@@ -2464,9 +2463,9 @@ out_unlock_pciaccess:
 
 /**
  * _ctl_ioctl - mpt3ctl main ioctl entry point (unlocked)
- * @file - (struct file)
- * @cmd - ioctl opcode
- * @arg -
+ * @file: (struct file)
+ * @cmd: ioctl opcode
+ * @arg: ?
  */
 static long
 _ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -2484,9 +2483,9 @@ _ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 
 /**
  * _ctl_mpt2_ioctl - mpt2ctl main ioctl entry point (unlocked)
- * @file - (struct file)
- * @cmd - ioctl opcode
- * @arg -
+ * @file: (struct file)
+ * @cmd: ioctl opcode
+ * @arg: ?
  */
 static long
 _ctl_mpt2_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
@@ -2502,9 +2501,9 @@ _ctl_mpt2_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 #ifdef CONFIG_COMPAT
 /**
  *_ ctl_ioctl_compat - main ioctl entry point (compat)
- * @file -
- * @cmd -
- * @arg -
+ * @file: ?
+ * @cmd: ?
+ * @arg: ?
  *
  * This routine handles 32 bit applications in 64bit os.
  */
@@ -2520,9 +2519,9 @@ _ctl_ioctl_compat(struct file *file, unsigned cmd, unsigned long arg)
 
 /**
  *_ ctl_mpt2_ioctl_compat - main ioctl entry point (compat)
- * @file -
- * @cmd -
- * @arg -
+ * @file: ?
+ * @cmd: ?
+ * @arg: ?
  *
  * This routine handles 32 bit applications in 64bit os.
  */
@@ -2539,8 +2538,9 @@ _ctl_mpt2_ioctl_compat(struct file *file, unsigned cmd, unsigned long arg)
 /* scsi host attributes */
 /**
  * _ctl_version_fw_show - firmware version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2561,8 +2561,9 @@ static DEVICE_ATTR(version_fw, S_IRUGO, _ctl_version_fw_show, NULL);
 
 /**
  * _ctl_version_bios_show - bios version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2585,8 +2586,9 @@ static DEVICE_ATTR(version_bios, S_IRUGO, _ctl_version_bios_show, NULL);
 
 /**
  * _ctl_version_mpi_show - MPI (message passing interface) version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2604,8 +2606,9 @@ static DEVICE_ATTR(version_mpi, S_IRUGO, _ctl_version_mpi_show, NULL);
 
 /**
  * _ctl_version_product_show - product name
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2622,8 +2625,9 @@ static DEVICE_ATTR(version_product, S_IRUGO, _ctl_version_product_show, NULL);
 
 /**
  * _ctl_version_nvdata_persistent_show - ndvata persistent version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2642,8 +2646,9 @@ static DEVICE_ATTR(version_nvdata_persistent, S_IRUGO,
 
 /**
  * _ctl_version_nvdata_default_show - nvdata default version
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2662,8 +2667,9 @@ static DEVICE_ATTR(version_nvdata_default, S_IRUGO,
 
 /**
  * _ctl_board_name_show - board name
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2680,8 +2686,9 @@ static DEVICE_ATTR(board_name, S_IRUGO, _ctl_board_name_show, NULL);
 
 /**
  * _ctl_board_assembly_show - board assembly name
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2698,8 +2705,9 @@ static DEVICE_ATTR(board_assembly, S_IRUGO, _ctl_board_assembly_show, NULL);
 
 /**
  * _ctl_board_tracer_show - board tracer number
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -2716,8 +2724,9 @@ static DEVICE_ATTR(board_tracer, S_IRUGO, _ctl_board_tracer_show, NULL);
 
 /**
  * _ctl_io_delay_show - io missing delay
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is for firmware implemention for deboucing device
  * removal events.
@@ -2737,8 +2746,9 @@ static DEVICE_ATTR(io_delay, S_IRUGO, _ctl_io_delay_show, NULL);
 
 /**
  * _ctl_device_delay_show - device missing delay
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is for firmware implemention for deboucing device
  * removal events.
@@ -2758,8 +2768,9 @@ static DEVICE_ATTR(device_delay, S_IRUGO, _ctl_device_delay_show, NULL);
 
 /**
  * _ctl_fw_queue_depth_show - global credits
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is firmware queue depth limit
  *
@@ -2778,8 +2789,9 @@ static DEVICE_ATTR(fw_queue_depth, S_IRUGO, _ctl_fw_queue_depth_show, NULL);
 
 /**
  * _ctl_sas_address_show - sas address
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is the controller sas address
  *
@@ -2801,8 +2813,9 @@ static DEVICE_ATTR(host_sas_address, S_IRUGO,
 
 /**
  * _ctl_logging_level_show - logging level
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -2836,8 +2849,9 @@ static DEVICE_ATTR(logging_level, S_IRUGO | S_IWUSR, _ctl_logging_level_show,
 
 /**
  * _ctl_fwfault_debug_show - show/store fwfault_debug
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * mpt3sas_fwfault_debug is command line option
  * A sysfs 'read/write' shost attribute.
@@ -2872,8 +2886,9 @@ static DEVICE_ATTR(fwfault_debug, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_ioc_reset_count_show - ioc reset count
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is firmware queue depth limit
  *
@@ -2892,8 +2907,9 @@ static DEVICE_ATTR(ioc_reset_count, S_IRUGO, _ctl_ioc_reset_count_show, NULL);
 
 /**
  * _ctl_ioc_reply_queue_count_show - number of reply queues
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is number of reply queues
  *
@@ -2920,8 +2936,9 @@ static DEVICE_ATTR(reply_queue_count, S_IRUGO, _ctl_ioc_reply_queue_count_show,
 
 /**
  * _ctl_BRM_status_show - Backup Rail Monitor Status
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is number of reply queues
  *
@@ -3006,8 +3023,9 @@ struct DIAG_BUFFER_START {
 
 /**
  * _ctl_host_trace_buffer_size_show - host buffer size (trace only)
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read-only' shost attribute.
  */
@@ -3051,8 +3069,9 @@ static DEVICE_ATTR(host_trace_buffer_size, S_IRUGO,
 
 /**
  * _ctl_host_trace_buffer_show - firmware ring buffer (trace only)
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  *
@@ -3116,8 +3135,9 @@ static DEVICE_ATTR(host_trace_buffer, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_host_trace_buffer_enable_show - firmware ring buffer (trace only)
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  *
@@ -3202,8 +3222,9 @@ static DEVICE_ATTR(host_trace_buffer_enable, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_master_show - show the diag_trigger_master attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3226,8 +3247,10 @@ _ctl_diag_trigger_master_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_master_store - store the diag_trigger_master attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3257,8 +3280,9 @@ static DEVICE_ATTR(diag_trigger_master, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_event_show - show the diag_trigger_event attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3280,8 +3304,10 @@ _ctl_diag_trigger_event_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_event_store - store the diag_trigger_event attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3311,8 +3337,9 @@ static DEVICE_ATTR(diag_trigger_event, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_scsi_show - show the diag_trigger_scsi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3334,8 +3361,10 @@ _ctl_diag_trigger_scsi_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_scsi_store - store the diag_trigger_scsi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3364,8 +3393,9 @@ static DEVICE_ATTR(diag_trigger_scsi, S_IRUGO | S_IWUSR,
 
 /**
  * _ctl_diag_trigger_scsi_show - show the diag_trigger_mpi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3387,8 +3417,10 @@ _ctl_diag_trigger_mpi_show(struct device *cdev,
 
 /**
  * _ctl_diag_trigger_mpi_store - store the diag_trigger_mpi attribute
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @cdev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
+ * @count: ?
  *
  * A sysfs 'read/write' shost attribute.
  */
@@ -3452,8 +3484,9 @@ struct device_attribute *mpt3sas_host_attrs[] = {
 
 /**
  * _ctl_device_sas_address_show - sas address
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @dev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is the sas address for the target
  *
@@ -3473,8 +3506,9 @@ static DEVICE_ATTR(sas_address, S_IRUGO, _ctl_device_sas_address_show, NULL);
 
 /**
  * _ctl_device_handle_show - device handle
- * @cdev - pointer to embedded class device
- * @buf - the buffer returned
+ * @dev: pointer to embedded class device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * This is the firmware assigned device handle
  *
@@ -3494,8 +3528,9 @@ static DEVICE_ATTR(sas_device_handle, S_IRUGO, _ctl_device_handle_show, NULL);
 
 /**
  * _ctl_device_ncq_io_prio_show - send prioritized io commands to device
- * @dev - pointer to embedded device
- * @buf - the buffer returned
+ * @dev: pointer to embedded device
+ * @attr: ?
+ * @buf: the buffer returned
  *
  * A sysfs 'read/write' sdev attribute, only works with SATA
  */
@@ -3575,7 +3610,7 @@ static struct miscdevice gen2_ctl_dev = {
 
 /**
  * mpt3sas_ctl_init - main entry point for ctl.
- *
+ * @hbas_to_enumerate: ?
  */
 void
 mpt3sas_ctl_init(ushort hbas_to_enumerate)
@@ -3603,7 +3638,7 @@ mpt3sas_ctl_init(ushort hbas_to_enumerate)
 
 /**
  * mpt3sas_ctl_exit - exit point for ctl
- *
+ * @hbas_to_enumerate: ?
  */
 void
 mpt3sas_ctl_exit(ushort hbas_to_enumerate)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 74dfbaf21814..061736f8025b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -284,6 +284,8 @@ struct _scsi_io_transfer {
 
 /**
  * _scsih_set_debug_level - global setting of ioc->logging_level.
+ * @val: ?
+ * @kp: ?
  *
  * Note: The logging levels are defined in mpt3sas_debug.h.
  */
@@ -311,7 +313,7 @@ module_param_call(logging_level, _scsih_set_debug_level, param_get_int,
  * @sas_address: sas address
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static inline int
 _scsih_srch_boot_sas_address(u64 sas_address,
@@ -325,7 +327,7 @@ _scsih_srch_boot_sas_address(u64 sas_address,
  * @device_name: device name specified in INDENTIFY fram
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static inline int
 _scsih_srch_boot_device_name(u64 device_name,
@@ -340,7 +342,7 @@ _scsih_srch_boot_device_name(u64 device_name,
  * @slot_number: slot number
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static inline int
 _scsih_srch_boot_encl_slot(u64 enclosure_logical_id, u16 slot_number,
@@ -356,11 +358,11 @@ _scsih_srch_boot_encl_slot(u64 enclosure_logical_id, u16 slot_number,
  * @sas_address: sas address
  * @device_name: device name specified in INDENTIFY fram
  * @enclosure_logical_id: enclosure logical id
- * @slot_number: slot number
+ * @slot: slot number
  * @form: specifies boot device form
  * @boot_device: boot device object from bios page 2
  *
- * Returns 1 when there's a match, 0 means no match.
+ * Return: 1 when there's a match, 0 means no match.
  */
 static int
 _scsih_is_boot_device(u64 sas_address, u64 device_name,
@@ -398,10 +400,11 @@ _scsih_is_boot_device(u64 sas_address, u64 device_name,
 
 /**
  * _scsih_get_sas_address - set the sas_address for given device handle
+ * @ioc: ?
  * @handle: device handle
  * @sas_address: sas address
  *
- * Returns 0 success, non-zero when failure
+ * Return: 0 success, non-zero when failure
  */
 static int
 _scsih_get_sas_address(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -710,8 +713,6 @@ mpt3sas_get_sdev_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @sas_device: per sas device object
  * @sdev: scsi device struct
  * @starget: scsi target struct
- *
- * Returns nothing.
  */
 static void
 _scsih_display_enclosure_chassis_info(struct MPT3SAS_ADAPTER *ioc,
@@ -806,8 +807,6 @@ _scsih_sas_device_remove(struct MPT3SAS_ADAPTER *ioc,
  * _scsih_device_remove_by_handle - removing device object by handle
  * @ioc: per adapter object
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _scsih_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -835,8 +834,6 @@ _scsih_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * mpt3sas_device_remove_by_sas_address - removing device object by sas address
  * @ioc: per adapter object
  * @sas_address: device sas_address
- *
- * Return nothing.
  */
 void
 mpt3sas_device_remove_by_sas_address(struct MPT3SAS_ADAPTER *ioc,
@@ -1109,8 +1106,6 @@ _scsih_pcie_device_remove(struct MPT3SAS_ADAPTER *ioc,
  * _scsih_pcie_device_remove_by_handle - removing pcie device object by handle
  * @ioc: per adapter object
  * @handle: device handle
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_remove_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -1273,7 +1268,7 @@ mpt3sas_raid_device_find_by_handle(struct MPT3SAS_ADAPTER *ioc, u16 handle)
 /**
  * _scsih_raid_device_find_by_wwid - raid device search
  * @ioc: per adapter object
- * @handle: sas device handle (assigned by firmware)
+ * @wwid: ?
  * Context: Calling function should acquire ioc->raid_device_lock
  *
  * This searches for raid_device based on wwid, then return raid_device
@@ -1418,8 +1413,6 @@ mpt3sas_scsih_expander_find_by_sas_address(struct MPT3SAS_ADAPTER *ioc,
  * Context: This function will acquire ioc->sas_node_lock.
  *
  * Adding new object to the ioc->sas_expander_list.
- *
- * Return nothing.
  */
 static void
 _scsih_expander_node_add(struct MPT3SAS_ADAPTER *ioc,
@@ -1437,7 +1430,7 @@ _scsih_expander_node_add(struct MPT3SAS_ADAPTER *ioc,
  * @device_info: bitfield providing information about the device.
  * Context: none
  *
- * Returns 1 if end device.
+ * Return: 1 if end device.
  */
 static int
 _scsih_is_end_device(u32 device_info)
@@ -1456,7 +1449,7 @@ _scsih_is_end_device(u32 device_info)
  * @device_info: bitfield providing information about the device.
  * Context: none
  *
- * Returns 1 if nvme device.
+ * Return: 1 if nvme device.
  */
 static int
 _scsih_is_nvme_device(u32 device_info)
@@ -1473,7 +1466,7 @@ _scsih_is_nvme_device(u32 device_info)
  * @ioc: per adapter object
  * @smid: system request message index
  *
- * Returns the smid stored scmd pointer.
+ * Return: the smid stored scmd pointer.
  * Then will dereference the stored scmd pointer.
  */
 struct scsi_cmnd *
@@ -1501,7 +1494,7 @@ mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * @sdev: scsi device struct
  * @qdepth: requested queue depth
  *
- * Returns queue depth.
+ * Return: queue depth.
  */
 static int
 scsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
@@ -1549,7 +1542,7 @@ scsih_change_queue_depth(struct scsi_device *sdev, int qdepth)
  * scsih_target_alloc - target add routine
  * @starget: scsi target struct
  *
- * Returns 0 if ok. Any other return is assumed to be an error and
+ * Return: 0 if ok. Any other return is assumed to be an error and
  * the device is ignored.
  */
 static int
@@ -1640,8 +1633,6 @@ scsih_target_alloc(struct scsi_target *starget)
 /**
  * scsih_target_destroy - target destroy routine
  * @starget: scsi target struct
- *
- * Returns nothing.
  */
 static void
 scsih_target_destroy(struct scsi_target *starget)
@@ -1718,7 +1709,7 @@ scsih_target_destroy(struct scsi_target *starget)
  * scsih_slave_alloc - device add routine
  * @sdev: scsi device struct
  *
- * Returns 0 if ok. Any other return is assumed to be an error and
+ * Return: 0 if ok. Any other return is assumed to be an error and
  * the device is ignored.
  */
 static int
@@ -1798,8 +1789,6 @@ scsih_slave_alloc(struct scsi_device *sdev)
 /**
  * scsih_slave_destroy - device destroy routine
  * @sdev: scsi device struct
- *
- * Returns nothing.
  */
 static void
 scsih_slave_destroy(struct scsi_device *sdev)
@@ -1905,7 +1894,7 @@ _scsih_display_sata_capabilities(struct MPT3SAS_ADAPTER *ioc,
 
 /**
  * scsih_is_raid - return boolean indicating device is raid volume
- * @dev the device struct object
+ * @dev: the device struct object
  */
 static int
 scsih_is_raid(struct device *dev)
@@ -1928,7 +1917,7 @@ scsih_is_nvme(struct device *dev)
 
 /**
  * scsih_get_resync - get raid volume resync percent complete
- * @dev the device struct object
+ * @dev: the device struct object
  */
 static void
 scsih_get_resync(struct device *dev)
@@ -1989,7 +1978,7 @@ scsih_get_resync(struct device *dev)
 
 /**
  * scsih_get_state - get raid volume level
- * @dev the device struct object
+ * @dev: the device struct object
  */
 static void
 scsih_get_state(struct device *dev)
@@ -2055,6 +2044,7 @@ scsih_get_state(struct device *dev)
 
 /**
  * _scsih_set_level - set raid level
+ * @ioc: ?
  * @sdev: scsi device struct
  * @volume_type: volume type
  */
@@ -2096,9 +2086,9 @@ _scsih_set_level(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _scsih_get_volume_capabilities - volume capabilities
  * @ioc: per adapter object
- * @sas_device: the raid_device object
+ * @raid_device: the raid_device object
  *
- * Returns 0 for success, else 1
+ * Return: 0 for success, else 1
  */
 static int
 _scsih_get_volume_capabilities(struct MPT3SAS_ADAPTER *ioc,
@@ -2190,7 +2180,7 @@ _scsih_enable_tlr(struct MPT3SAS_ADAPTER *ioc, struct scsi_device *sdev)
  * scsih_slave_configure - device configure routine.
  * @sdev: scsi device struct
  *
- * Returns 0 if ok. Any other return is assumed to be an error and
+ * Return: 0 if ok. Any other return is assumed to be an error and
  * the device is ignored.
  */
 static int
@@ -2449,8 +2439,6 @@ scsih_slave_configure(struct scsi_device *sdev)
  *              params[0] number of heads (max 255)
  *              params[1] number of sectors (max 63)
  *              params[2] number of cylinders
- *
- * Return nothing.
  */
 static int
 scsih_bios_param(struct scsi_device *sdev, struct block_device *bdev,
@@ -2492,8 +2480,6 @@ scsih_bios_param(struct scsi_device *sdev, struct block_device *bdev,
  * _scsih_response_code - translation of device response code
  * @ioc: per adapter object
  * @response_code: response code returned by the device
- *
- * Return nothing.
  */
 static void
 _scsih_response_code(struct MPT3SAS_ADAPTER *ioc, u8 response_code)
@@ -2543,8 +2529,8 @@ _scsih_response_code(struct MPT3SAS_ADAPTER *ioc, u8 response_code)
  *
  * The callback handler when using scsih_issue_tm.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_tm_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
@@ -2639,7 +2625,7 @@ mpt3sas_scsih_clear_tm_flag(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * The callback index is set inside `ioc->tm_cb_idx`.
  * The caller is responsible to check for outstanding commands.
  *
- * Return SUCCESS or FAILED.
+ * Return: SUCCESS or FAILED.
  */
 int
 mpt3sas_scsih_issue_tm(struct MPT3SAS_ADAPTER *ioc, u16 handle, u64 lun,
@@ -2843,7 +2829,7 @@ _scsih_tm_display_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd)
  * scsih_abort - eh threads main abort routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_abort(struct scsi_cmnd *scmd)
@@ -2911,7 +2897,7 @@ scsih_abort(struct scsi_cmnd *scmd)
  * scsih_dev_reset - eh threads main device reset routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_dev_reset(struct scsi_cmnd *scmd)
@@ -2989,7 +2975,7 @@ scsih_dev_reset(struct scsi_cmnd *scmd)
  * scsih_target_reset - eh threads main target reset routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_target_reset(struct scsi_cmnd *scmd)
@@ -3066,7 +3052,7 @@ scsih_target_reset(struct scsi_cmnd *scmd)
  * scsih_host_reset - eh threads main host reset routine
  * @scmd: pointer to scsi command object
  *
- * Returns SUCCESS if command aborted else FAILED
+ * Return: SUCCESS if command aborted else FAILED
  */
 static int
 scsih_host_reset(struct scsi_cmnd *scmd)
@@ -3102,8 +3088,6 @@ out:
  *
  * This adds the firmware event object into link list, then queues it up to
  * be processed from user context.
- *
- * Return nothing.
  */
 static void
 _scsih_fw_event_add(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
@@ -3130,8 +3114,6 @@ _scsih_fw_event_add(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
  * Context: This function will acquire ioc->fw_event_lock.
  *
  * If the fw_event is on the fw_event_list, remove it and do a put.
- *
- * Return nothing.
  */
 static void
 _scsih_fw_event_del_from_list(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work
@@ -3152,8 +3134,6 @@ _scsih_fw_event_del_from_list(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work
  * mpt3sas_send_trigger_data_event - send event for processing trigger data
  * @ioc: per adapter object
  * @event_data: trigger event data
- *
- * Return nothing.
  */
 void
 mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc,
@@ -3178,8 +3158,6 @@ mpt3sas_send_trigger_data_event(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _scsih_error_recovery_delete_devices - remove devices not responding
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_error_recovery_delete_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -3200,8 +3178,6 @@ _scsih_error_recovery_delete_devices(struct MPT3SAS_ADAPTER *ioc)
 /**
  * mpt3sas_port_enable_complete - port enable completed (fake event)
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 void
 mpt3sas_port_enable_complete(struct MPT3SAS_ADAPTER *ioc)
@@ -3239,8 +3215,6 @@ static struct fw_event_work *dequeue_next_fw_event(struct MPT3SAS_ADAPTER *ioc)
  *
  * Walk the firmware event queue, either killing timers, or waiting
  * for outstanding events to complete
- *
- * Return nothing.
  */
 static void
 _scsih_fw_event_cleanup_queue(struct MPT3SAS_ADAPTER *ioc)
@@ -3366,7 +3340,7 @@ _scsih_ublock_io_all_device(struct MPT3SAS_ADAPTER *ioc)
 /**
  * _scsih_ublock_io_device - prepare device to be deleted
  * @ioc: per adapter object
- * @sas_addr: sas address
+ * @sas_address: sas address
  *
  * unblock then put device in offline state
  */
@@ -3392,7 +3366,6 @@ _scsih_ublock_io_device(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
 /**
  * _scsih_block_io_all_device - set the device state to SDEV_BLOCK
  * @ioc: per adapter object
- * @handle: device handle
  *
  * During device pull we need to appropriately set the sdev state.
  */
@@ -3727,8 +3700,8 @@ out:
  * handshake protocol with controller firmware.
  * It will send a sas iounit control request (MPI2_SAS_OP_REMOVE_DEVICE)
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -3819,8 +3792,8 @@ _scsih_tm_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
  * This code is part of the code to initiate the device removal
  * handshake protocol with controller firmware.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_sas_control_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -3906,8 +3879,8 @@ _scsih_tm_tr_volume_send(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @reply: reply message frame(lower 32bit addr)
  * Context: interrupt time.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_tm_volume_tr_complete(struct MPT3SAS_ADAPTER *ioc, u16 smid,
@@ -4056,8 +4029,8 @@ _scsih_issue_delayed_sas_io_unit_ctrl(struct MPT3SAS_ADAPTER *ioc,
  * This will check delayed internal messages list, and process the
  * next request.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_check_for_pending_internal_cmds(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -4095,8 +4068,8 @@ mpt3sas_check_for_pending_internal_cmds(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * This will check delayed target reset list, and feed the
  * next reqeust.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_check_for_pending_tm(struct MPT3SAS_ADAPTER *ioc, u16 smid)
@@ -4136,8 +4109,6 @@ _scsih_check_for_pending_tm(struct MPT3SAS_ADAPTER *ioc, u16 smid)
  * This handles the case where driver receives multiple expander
  * add and delete events in a single shot.  When there is a delete event
  * the routine will void any pending add events waiting in the event queue.
- *
- * Return nothing.
  */
 static void
 _scsih_check_topo_delete_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4219,8 +4190,6 @@ _scsih_check_topo_delete_events(struct MPT3SAS_ADAPTER *ioc,
  * or device add and delete events in a single shot.  When there
  * is a delete event the routine will void any pending add
  * events waiting in the event queue.
- *
- * Return nothing.
  */
 static void
 _scsih_check_pcie_topo_remove_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4345,8 +4314,6 @@ _scsih_set_volume_handle_for_tr(u16 handle, u16 *a, u16 *b)
  * volume has been deleted or removed. When the target reset is sent
  * to volume, the PD target resets need to be queued to start upon
  * completion of the volume target reset.
- *
- * Return nothing.
  */
 static void
 _scsih_check_ir_config_unhide_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4430,8 +4397,6 @@ _scsih_check_ir_config_unhide_events(struct MPT3SAS_ADAPTER *ioc,
  * This will handle the case when the cable connected to entire volume is
  * pulled. We will take care of setting the deleted flag so normal IO will
  * not be sent.
- *
- * Return nothing.
  */
 static void
 _scsih_check_volume_delete_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4453,8 +4418,6 @@ _scsih_check_volume_delete_events(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @event_data: the temp threshold event data
  * Context: interrupt time.
- *
- * Return nothing.
  */
 static void
 _scsih_temp_threshold_events(struct MPT3SAS_ADAPTER *ioc,
@@ -4493,8 +4456,6 @@ static int _scsih_set_satl_pending(struct scsi_cmnd *scmd, bool pending)
  *
  * The flushing out of all pending scmd commands following host reset,
  * where all IO is dropped to the floor.
- *
- * Return nothing.
  */
 static void
 _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
@@ -4530,8 +4491,6 @@ _scsih_flush_running_cmds(struct MPT3SAS_ADAPTER *ioc)
  * @mpi_request: pointer to the SCSI_IO request message frame
  *
  * Supporting protection 1 and 3.
- *
- * Returns nothing
  */
 static void
 _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
@@ -4590,8 +4549,6 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
  * _scsih_eedp_error_handling - return sense code for EEDP errors
  * @scmd: pointer to scsi command object
  * @ioc_status: ioc status
- *
- * Returns nothing
  */
 static void
 _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
@@ -4620,12 +4577,12 @@ _scsih_eedp_error_handling(struct scsi_cmnd *scmd, u16 ioc_status)
 
 /**
  * scsih_qcmd - main scsi request entry point
+ * @shost: SCSI host pointer
  * @scmd: pointer to scsi command object
- * @done: function pointer to be invoked on completion
  *
  * The callback index is set inside `ioc->scsi_io_cb_idx`.
  *
- * Returns 0 on success.  If there's a failure, return either:
+ * Return: 0 on success.  If there's a failure, return either:
  * SCSI_MLQUEUE_DEVICE_BUSY if the device queue is full, or
  * SCSI_MLQUEUE_HOST_BUSY if the entire host queue is full
  */
@@ -4788,8 +4745,6 @@ scsih_qcmd(struct Scsi_Host *shost, struct scsi_cmnd *scmd)
  * _scsih_normalize_sense - normalize descriptor and fixed format sense data
  * @sense_buffer: sense data returned by target
  * @data: normalized skey/asc/ascq
- *
- * Return nothing.
  */
 static void
 _scsih_normalize_sense(char *sense_buffer, struct sense_info *data)
@@ -4812,12 +4767,11 @@ _scsih_normalize_sense(char *sense_buffer, struct sense_info *data)
  * @ioc: per adapter object
  * @scmd: pointer to scsi command object
  * @mpi_reply: reply mf payload returned from firmware
+ * @smid: ?
  *
  * scsi_status - SCSI Status code returned from target device
  * scsi_state - state info associated with SCSI_IO determined by ioc
  * ioc_status - ioc supplied status info
- *
- * Return nothing.
  */
 static void
 _scsih_scsi_ioc_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
@@ -5041,8 +4995,6 @@ _scsih_scsi_ioc_info(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
  * @ioc: per adapter object
  * @handle: device handle
  * Context: process
- *
- * Return nothing.
  */
 static void
 _scsih_turn_on_pfa_led(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5086,8 +5038,6 @@ out:
  * @ioc: per adapter object
  * @sas_device: sas device whose PFA LED has to turned off
  * Context: process
- *
- * Return nothing.
  */
 static void
 _scsih_turn_off_pfa_led(struct MPT3SAS_ADAPTER *ioc,
@@ -5125,8 +5075,6 @@ _scsih_turn_off_pfa_led(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @handle: device handle
  * Context: interrupt.
- *
- * Return nothing.
  */
 static void
 _scsih_send_event_to_turn_on_pfa_led(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5148,8 +5096,6 @@ _scsih_send_event_to_turn_on_pfa_led(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @ioc: per adapter object
  * @handle: device handle
  * Context: interrupt.
- *
- * Return nothing.
  */
 static void
 _scsih_smart_predicted_fault(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5225,8 +5171,8 @@ out_unlock:
  *
  * Callback handler when using _scsih_qcmd.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
@@ -5466,8 +5412,6 @@ _scsih_io_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
  * During port enable, fw will send topology events for every device. Its
  * possible that the handles may change from the previous setting, so this
  * code keeping handles updating if changed.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc)
@@ -5521,8 +5465,6 @@ _scsih_sas_host_refresh(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  *
  * Creating host side data object, stored in ioc->sas_hba
- *
- * Return nothing.
  */
 static void
 _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc)
@@ -5670,7 +5612,7 @@ _scsih_sas_host_add(struct MPT3SAS_ADAPTER *ioc)
  *
  * Creating expander object, stored in ioc->sas_expander_list.
  *
- * Return 0 for success, else error.
+ * Return: 0 for success, else error.
  */
 static int
 _scsih_expander_add(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -5825,8 +5767,6 @@ _scsih_expander_add(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * mpt3sas_expander_remove - removing expander object
  * @ioc: per adapter object
  * @sas_address: expander sas_address
- *
- * Return nothing.
  */
 void
 mpt3sas_expander_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
@@ -5855,8 +5795,8 @@ mpt3sas_expander_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address)
  * Callback handler when sending internal generated SCSI_IO.
  * The callback index passed is `ioc->scsih_cb_idx`
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 static u8
 _scsih_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
@@ -5890,9 +5830,9 @@ _scsih_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index, u32 reply)
  * @ioc: per adapter object
  * @sas_address: sas address
  * @handle: sas device handle
- * @access_flags: errors returned during discovery of the device
+ * @access_status: errors returned during discovery of the device
  *
- * Return 0 for success, else failure
+ * Return: 0 for success, else failure
  */
 static u8
 _scsih_check_access_status(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
@@ -5954,10 +5894,8 @@ _scsih_check_access_status(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
  * @ioc: per adapter object
  * @parent_sas_address: sas address of parent expander or sas host
  * @handle: attached device handle
- * @phy_numberv: phy number
+ * @phy_number: phy number
  * @link_rate: new link rate
- *
- * Returns nothing.
  */
 static void
 _scsih_check_device(struct MPT3SAS_ADAPTER *ioc,
@@ -6074,7 +6012,7 @@ out_unlock:
  *
  * Creating end device object, stored in ioc->sas_device_list.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _scsih_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phy_num,
@@ -6206,9 +6144,7 @@ _scsih_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phy_num,
 /**
  * _scsih_remove_device -  removing sas device object
  * @ioc: per adapter object
- * @sas_device_delete: the sas_device object
- *
- * Return nothing.
+ * @sas_device: the sas_device object
  */
 static void
 _scsih_remove_device(struct MPT3SAS_ADAPTER *ioc,
@@ -6474,10 +6410,9 @@ _scsih_sas_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 
 /**
  * _scsih_sas_device_status_change_event_debug - debug for device event
+ * @ioc: ?
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -6545,8 +6480,6 @@ _scsih_sas_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_device_status_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -6607,9 +6540,9 @@ out:
  * @ioc: per adapter object
  * @wwid: wwid
  * @handle: sas device handle
- * @access_flags: errors returned during discovery of the device
+ * @access_status: errors returned during discovery of the device
  *
- * Return 0 for success, else failure
+ * Return: 0 for success, else failure
  */
 static u8
 _scsih_check_pcie_access_status(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
@@ -6694,8 +6627,6 @@ _scsih_check_pcie_access_status(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
  * from SML and free up associated memory
  * @ioc: per adapter object
  * @pcie_device: the pcie_device object
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_remove_from_sml(struct MPT3SAS_ADAPTER *ioc,
@@ -6769,8 +6700,6 @@ _scsih_pcie_device_remove_from_sml(struct MPT3SAS_ADAPTER *ioc,
  * _scsih_pcie_check_device - checking device responsiveness
  * @ioc: per adapter object
  * @handle: attached device handle
- *
- * Returns nothing.
  */
 static void
 _scsih_pcie_check_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -6862,7 +6791,7 @@ _scsih_pcie_check_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  *
  * Creating end device object, stored in ioc->pcie_device_list.
  *
- * Return 1 means queue the event later, 0 means complete the event
+ * Return: 1 means queue the event later, 0 means complete the event
  */
 static int
 _scsih_pcie_add_device(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -7187,12 +7116,10 @@ _scsih_pcie_topology_change_event(struct MPT3SAS_ADAPTER *ioc,
 }
 
 /**
- * _scsih_pcie_device_status_change_event_debug - debug for
- * device event
+ * _scsih_pcie_device_status_change_event_debug - debug for device event
+ * @ioc: ?
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -7259,8 +7186,6 @@ _scsih_pcie_device_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_device_status_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7311,8 +7236,6 @@ out:
  * @ioc: per adapter object
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_enclosure_dev_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -7345,8 +7268,6 @@ _scsih_sas_enclosure_dev_status_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_enclosure_dev_status_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7413,8 +7334,6 @@ _scsih_sas_enclosure_dev_status_change_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7581,8 +7500,6 @@ _scsih_sas_broadcast_primitive_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_discovery_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7618,8 +7535,6 @@ _scsih_sas_discovery_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_device_discovery_error_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7655,8 +7570,6 @@ _scsih_sas_device_discovery_error_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_pcie_enumeration_event(struct MPT3SAS_ADAPTER *ioc,
@@ -7685,7 +7598,7 @@ _scsih_pcie_enumeration_event(struct MPT3SAS_ADAPTER *ioc,
  * @handle: device handle for physical disk
  * @phys_disk_num: physical disk number
  *
- * Return 0 for success, else failure.
+ * Return: 0 for success, else failure.
  */
 static int
 _scsih_ir_fastpath(struct MPT3SAS_ADAPTER *ioc, u16 handle, u8 phys_disk_num)
@@ -7795,8 +7708,6 @@ _scsih_reprobe_lun(struct scsi_device *sdev, void *no_uld_attach)
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_volume_add(struct MPT3SAS_ADAPTER *ioc,
@@ -7853,8 +7764,6 @@ _scsih_sas_volume_add(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @handle: volume device handle
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_volume_delete(struct MPT3SAS_ADAPTER *ioc, u16 handle)
@@ -7888,8 +7797,6 @@ _scsih_sas_volume_delete(struct MPT3SAS_ADAPTER *ioc, u16 handle)
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_expose(struct MPT3SAS_ADAPTER *ioc,
@@ -7930,8 +7837,6 @@ _scsih_sas_pd_expose(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_hide(struct MPT3SAS_ADAPTER *ioc,
@@ -7981,8 +7886,6 @@ _scsih_sas_pd_hide(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_delete(struct MPT3SAS_ADAPTER *ioc,
@@ -7998,8 +7901,6 @@ _scsih_sas_pd_delete(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @element: IR config element data
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_pd_add(struct MPT3SAS_ADAPTER *ioc,
@@ -8051,8 +7952,6 @@ _scsih_sas_pd_add(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_config_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -8131,8 +8030,6 @@ _scsih_sas_ir_config_change_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_config_change_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8203,8 +8100,6 @@ _scsih_sas_ir_config_change_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_volume_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8287,8 +8182,6 @@ _scsih_sas_ir_volume_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_physical_disk_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8373,8 +8266,6 @@ _scsih_sas_ir_physical_disk_event(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @event_data: event data payload
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_operation_status_event_debug(struct MPT3SAS_ADAPTER *ioc,
@@ -8415,8 +8306,6 @@ _scsih_sas_ir_operation_status_event_debug(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _scsih_sas_ir_operation_status_event(struct MPT3SAS_ADAPTER *ioc,
@@ -8474,8 +8363,6 @@ _scsih_prep_device_scan(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponsive_sas_devices.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_sas_device(struct MPT3SAS_ADAPTER *ioc,
@@ -8570,8 +8457,6 @@ Mpi2SasDevicePage0_t *sas_device_pg0)
  * _scsih_create_enclosure_list_after_reset - Free Existing list,
  *	And create enclosure list by scanning all Enclosure Page(0)s
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_create_enclosure_list_after_reset(struct MPT3SAS_ADAPTER *ioc)
@@ -8618,8 +8503,6 @@ _scsih_create_enclosure_list_after_reset(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_sas_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -8662,8 +8545,6 @@ _scsih_search_responding_sas_devices(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponding_devices.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_pcie_device(struct MPT3SAS_ADAPTER *ioc,
@@ -8737,8 +8618,6 @@ _scsih_mark_responding_pcie_device(struct MPT3SAS_ADAPTER *ioc,
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_pcie_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -8786,8 +8665,6 @@ out:
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponsive_raid_devices.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_raid_device(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
@@ -8843,8 +8720,6 @@ _scsih_mark_responding_raid_device(struct MPT3SAS_ADAPTER *ioc, u64 wwid,
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_raid_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -8915,8 +8790,6 @@ _scsih_search_responding_raid_devices(struct MPT3SAS_ADAPTER *ioc)
  *
  * After host reset, find out whether devices are still responding.
  * Used in _scsih_remove_unresponsive_expanders.
- *
- * Return nothing.
  */
 static void
 _scsih_mark_responding_expander(struct MPT3SAS_ADAPTER *ioc,
@@ -8969,8 +8842,6 @@ _scsih_mark_responding_expander(struct MPT3SAS_ADAPTER *ioc,
  *
  * After host reset, find out whether devices are still responding.
  * If not remove.
- *
- * Return nothing.
  */
 static void
 _scsih_search_responding_expanders(struct MPT3SAS_ADAPTER *ioc)
@@ -9010,8 +8881,6 @@ _scsih_search_responding_expanders(struct MPT3SAS_ADAPTER *ioc)
 /**
  * _scsih_remove_unresponding_devices - removing unresponding devices
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_remove_unresponding_devices(struct MPT3SAS_ADAPTER *ioc)
@@ -9137,8 +9006,6 @@ _scsih_refresh_expander_links(struct MPT3SAS_ADAPTER *ioc,
 /**
  * _scsih_scan_for_devices_after_reset - scan for devices after host reset
  * @ioc: per adapter object
- *
- * Return nothing.
  */
 static void
 _scsih_scan_for_devices_after_reset(struct MPT3SAS_ADAPTER *ioc)
@@ -9492,8 +9359,6 @@ mpt3sas_scsih_reset_done_handler(struct MPT3SAS_ADAPTER *ioc)
  * @ioc: per adapter object
  * @fw_event: The fw_event_work object
  * Context: user.
- *
- * Return nothing.
  */
 static void
 _mpt3sas_fw_work(struct MPT3SAS_ADAPTER *ioc, struct fw_event_work *fw_event)
@@ -9586,13 +9451,10 @@ out:
 
 /**
  * _firmware_event_work
- * @ioc: per adapter object
  * @work: The fw_event_work object
  * Context: user.
  *
  * wrappers for the work thread handling firmware events
- *
- * Return nothing.
  */
 
 static void
@@ -9614,8 +9476,8 @@ _firmware_event_work(struct work_struct *work)
  * This function merely adds a new work task into ioc->firmware_event_thread.
  * The tasks are worked from _firmware_event_work in user context.
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
@@ -9800,8 +9662,6 @@ mpt3sas_scsih_event_callback(struct MPT3SAS_ADAPTER *ioc, u8 msix_index,
  *
  * Removing object and freeing associated memory from the
  * ioc->sas_expander_list.
- *
- * Return nothing.
  */
 static void
 _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
@@ -9850,8 +9710,6 @@ _scsih_expander_node_remove(struct MPT3SAS_ADAPTER *ioc,
  *
  * Sending RAID Action to alert the Integrated RAID subsystem of the IOC that
  * the host system is shutting down.
- *
- * Return nothing.
  */
 static void
 _scsih_ir_shutdown(struct MPT3SAS_ADAPTER *ioc)
@@ -9923,7 +9781,6 @@ _scsih_ir_shutdown(struct MPT3SAS_ADAPTER *ioc)
  * @pdev: PCI device struct
  *
  * Routine called when unloading the driver.
- * Return nothing.
  */
 static void scsih_remove(struct pci_dev *pdev)
 {
@@ -10005,8 +9862,6 @@ static void scsih_remove(struct pci_dev *pdev)
 /**
  * scsih_shutdown - routine call during system shutdown
  * @pdev: PCI device struct
- *
- * Return nothing.
  */
 static void
 scsih_shutdown(struct pci_dev *pdev)
@@ -10229,7 +10084,7 @@ _scsih_probe_sas(struct MPT3SAS_ADAPTER *ioc)
  *
  * Get the next pcie device from pcie_device_init_list list.
  *
- * Returns pcie device structure if pcie_device_init_list list is not empty
+ * Return: pcie device structure if pcie_device_init_list list is not empty
  * otherwise returns NULL
  */
 static struct _pcie_device *get_next_pcie_device(struct MPT3SAS_ADAPTER *ioc)
@@ -10577,7 +10432,7 @@ _scsih_determine_hba_mpi_version(struct pci_dev *pdev)
  * @pdev: PCI device struct
  * @id: pci device id
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 _scsih_probe(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -10827,7 +10682,7 @@ out_add_shost_fail:
  * @pdev: PCI device struct
  * @state: PM state change to (usually PCI_D3)
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 scsih_suspend(struct pci_dev *pdev, pm_message_t state)
@@ -10854,7 +10709,7 @@ scsih_suspend(struct pci_dev *pdev, pm_message_t state)
  * scsih_resume - power management resume main entry point
  * @pdev: PCI device struct
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 scsih_resume(struct pci_dev *pdev)
@@ -10890,8 +10745,7 @@ scsih_resume(struct pci_dev *pdev)
  *
  * Description: Called when a PCI error is detected.
  *
- * Return value:
- *      PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT
+ * Return: PCI_ERS_RESULT_NEED_RESET or PCI_ERS_RESULT_DISCONNECT.
  */
 static pci_ers_result_t
 scsih_pci_error_detected(struct pci_dev *pdev, pci_channel_state_t state)
@@ -11152,7 +11006,7 @@ static struct pci_driver mpt3sas_driver = {
 /**
  * scsih_init - main entry point for this driver.
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int
 scsih_init(void)
@@ -11202,7 +11056,7 @@ scsih_init(void)
 /**
  * scsih_exit - exit point for this driver (when it is a module).
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static void
 scsih_exit(void)
@@ -11232,7 +11086,7 @@ scsih_exit(void)
 /**
  * _mpt3sas_init - main entry point for this driver.
  *
- * Returns 0 success, anything else error.
+ * Return: 0 success, anything else error.
  */
 static int __init
 _mpt3sas_init(void)
diff --git a/drivers/scsi/mpt3sas/mpt3sas_transport.c b/drivers/scsi/mpt3sas/mpt3sas_transport.c
index f4b02dd7f6cf..f8cc2677c1cd 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_transport.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_transport.c
@@ -134,7 +134,7 @@ _transport_convert_phy_link_rate(u8 link_rate)
  *
  * Populates sas identify info.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_set_identify(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -226,8 +226,8 @@ _transport_set_identify(struct MPT3SAS_ADAPTER *ioc, u16 handle,
  * Callback handler when sending internal generated transport cmds.
  * The callback index passed is `ioc->transport_cb_idx`
  *
- * Return 1 meaning mf should be freed from _base_interrupt
- *        0 means the mf is freed from this function.
+ * Return: 1 meaning mf should be freed from _base_interrupt
+ *         0 means the mf is freed from this function.
  */
 u8
 mpt3sas_transport_done(struct MPT3SAS_ADAPTER *ioc, u16 smid, u8 msix_index,
@@ -287,7 +287,7 @@ struct rep_manu_reply {
  *
  * Fills in the sas_expander_device object when SMP port is created.
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_expander_report_manufacture(struct MPT3SAS_ADAPTER *ioc,
@@ -460,8 +460,6 @@ _transport_expander_report_manufacture(struct MPT3SAS_ADAPTER *ioc,
  * _transport_delete_port - helper function to removing a port
  * @ioc: per adapter object
  * @mpt3sas_port: mpt3sas per port object
- *
- * Returns nothing.
  */
 static void
 _transport_delete_port(struct MPT3SAS_ADAPTER *ioc,
@@ -489,8 +487,6 @@ _transport_delete_port(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @mpt3sas_port: mpt3sas per port object
  * @mpt3sas_phy: mpt3sas per phy object
- *
- * Returns nothing.
  */
 static void
 _transport_delete_phy(struct MPT3SAS_ADAPTER *ioc,
@@ -513,8 +509,6 @@ _transport_delete_phy(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @mpt3sas_port: mpt3sas per port object
  * @mpt3sas_phy: mpt3sas per phy object
- *
- * Returns nothing.
  */
 static void
 _transport_add_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_port *mpt3sas_port,
@@ -538,8 +532,6 @@ _transport_add_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_port *mpt3sas_port,
  * @sas_node: sas node object (either expander or sas host)
  * @mpt3sas_phy: mpt3sas per phy object
  * @sas_address: sas address of device/expander were phy needs to be added to
- *
- * Returns nothing.
  */
 static void
 _transport_add_phy_to_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
@@ -573,8 +565,6 @@ _transport_add_phy_to_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
  * @ioc: per adapter object
  * @sas_node: sas node object (either expander or sas host)
  * @mpt3sas_phy: mpt3sas per phy object
- *
- * Returns nothing.
  */
 static void
 _transport_del_phy_from_an_existing_port(struct MPT3SAS_ADAPTER *ioc,
@@ -635,7 +625,7 @@ _transport_sanity_check(struct MPT3SAS_ADAPTER *ioc, struct _sas_node *sas_node,
  *
  * Adding new port object to the sas_node->sas_port_list.
  *
- * Returns mpt3sas_port.
+ * Return: mpt3sas_port.
  */
 struct _sas_port *
 mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle,
@@ -794,8 +784,6 @@ mpt3sas_transport_port_add(struct MPT3SAS_ADAPTER *ioc, u16 handle,
  *
  * Removing object and freeing associated memory from the
  * ioc->sas_port_list.
- *
- * Return nothing.
  */
 void
 mpt3sas_transport_port_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
@@ -860,7 +848,7 @@ mpt3sas_transport_port_remove(struct MPT3SAS_ADAPTER *ioc, u64 sas_address,
  * @phy_pg0: sas phy page 0
  * @parent_dev: parent device class object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_transport_add_host_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
@@ -928,7 +916,7 @@ mpt3sas_transport_add_host_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
  * @expander_pg1: expander page 1
  * @parent_dev: parent device class object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 int
 mpt3sas_transport_add_expander_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
@@ -995,10 +983,8 @@ mpt3sas_transport_add_expander_phy(struct MPT3SAS_ADAPTER *ioc, struct _sas_phy
  * @ioc: per adapter object
  * @sas_address: sas address of parent expander or sas host
  * @handle: attached device handle
- * @phy_numberv: phy number
+ * @phy_number: phy number
  * @link_rate: new link rate
- *
- * Returns nothing.
  */
 void
 mpt3sas_transport_update_links(struct MPT3SAS_ADAPTER *ioc,
@@ -1090,7 +1076,7 @@ struct phy_error_log_reply {
  * @ioc: per adapter object
  * @phy: The sas phy object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  */
 static int
@@ -1262,7 +1248,7 @@ _transport_get_expander_phy_error_log(struct MPT3SAS_ADAPTER *ioc,
  * _transport_get_linkerrors - return phy counters for both hba and expanders
  * @phy: The sas phy object
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  */
 static int
@@ -1311,10 +1297,11 @@ _transport_get_linkerrors(struct sas_phy *phy)
 
 /**
  * _transport_get_enclosure_identifier -
- * @phy: The sas phy object
+ * @rphy: The sas phy object
+ * @identifier: ?
  *
  * Obtain the enclosure logical id for an expander.
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier)
@@ -1342,9 +1329,9 @@ _transport_get_enclosure_identifier(struct sas_rphy *rphy, u64 *identifier)
 
 /**
  * _transport_get_bay_identifier -
- * @phy: The sas phy object
+ * @rphy: The sas phy object
  *
- * Returns the slot id for a device that resides inside an enclosure.
+ * Return: the slot id for a device that resides inside an enclosure.
  */
 static int
 _transport_get_bay_identifier(struct sas_rphy *rphy)
@@ -1400,8 +1387,9 @@ struct phy_control_reply {
  * _transport_expander_phy_control - expander phy control
  * @ioc: per adapter object
  * @phy: The sas phy object
+ * @phy_operation: ?
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  *
  */
 static int
@@ -1571,7 +1559,7 @@ _transport_expander_phy_control(struct MPT3SAS_ADAPTER *ioc,
  * @phy: The sas phy object
  * @hard_reset:
  *
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_phy_reset(struct sas_phy *phy, int hard_reset)
@@ -1623,7 +1611,7 @@ _transport_phy_reset(struct sas_phy *phy, int hard_reset)
  * @enable: enable phy when true
  *
  * Only support sas_host direct attached phys.
- * Returns 0 for success, non-zero for failure.
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_phy_enable(struct sas_phy *phy, int enable)
@@ -1761,7 +1749,8 @@ _transport_phy_enable(struct sas_phy *phy, int enable)
  * @rates: rates defined in sas_phy_linkrates
  *
  * Only support sas_host direct attached phys.
- * Returns 0 for success, non-zero for failure.
+ *
+ * Return: 0 for success, non-zero for failure.
  */
 static int
 _transport_phy_speed(struct sas_phy *phy, struct sas_phy_linkrates *rates)
@@ -1904,9 +1893,9 @@ _transport_unmap_smp_buffer(struct device *dev, struct bsg_buffer *buf,
 
 /**
  * _transport_smp_handler - transport portal for smp passthru
+ * @job: ?
  * @shost: shost object
  * @rphy: sas transport rphy object
- * @req:
  *
  * This used primarily for smp_utils.
  * Example:
diff --git a/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c b/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
index b60fd7a3b571..cae7c1eaef34 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_trigger_diag.c
@@ -62,7 +62,7 @@
 /**
  * _mpt3sas_raise_sigio - notifiy app
  * @ioc: per adapter object
- * @event_data:
+ * @event_data: ?
  */
 static void
 _mpt3sas_raise_sigio(struct MPT3SAS_ADAPTER *ioc,
@@ -107,7 +107,7 @@ _mpt3sas_raise_sigio(struct MPT3SAS_ADAPTER *ioc,
 /**
  * mpt3sas_process_trigger_data - process the event data for the trigger
  * @ioc: per adapter object
- * @event_data:
+ * @event_data: ?
  */
 void
 mpt3sas_process_trigger_data(struct MPT3SAS_ADAPTER *ioc,
@@ -209,8 +209,8 @@ mpt3sas_trigger_master(struct MPT3SAS_ADAPTER *ioc, u32 trigger_bitmask)
 /**
  * mpt3sas_trigger_event - Event trigger handler
  * @ioc: per adapter object
- * @event:
- * @log_entry_qualifier:
+ * @event: ?
+ * @log_entry_qualifier: ?
  *
  */
 void
@@ -288,9 +288,9 @@ mpt3sas_trigger_event(struct MPT3SAS_ADAPTER *ioc, u16 event,
 /**
  * mpt3sas_trigger_scsi - SCSI trigger handler
  * @ioc: per adapter object
- * @sense_key:
- * @asc:
- * @ascq:
+ * @sense_key: ?
+ * @asc: ?
+ * @ascq: ?
  *
  */
 void
@@ -364,8 +364,8 @@ mpt3sas_trigger_scsi(struct MPT3SAS_ADAPTER *ioc, u8 sense_key, u8 asc,
 /**
  * mpt3sas_trigger_mpi - MPI trigger handler
  * @ioc: per adapter object
- * @ioc_status:
- * @loginfo:
+ * @ioc_status: ?
+ * @loginfo: ?
  *
  */
 void
diff --git a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
index 45aa94915cbf..b4927f2b7677 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_warpdrive.c
@@ -267,9 +267,6 @@ out_error:
  * @scmd: pointer to scsi command object
  * @raid_device: pointer to raid device data structure
  * @mpi_request: pointer to the SCSI_IO reqest message frame
- * @smid: system request message index
- *
- * Returns nothing
  */
 void
 mpt3sas_setup_direct_io(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
-- 
cgit v1.2.3


From 957c5ab108c7d98369b7524daea532c0ebbcf845 Mon Sep 17 00:00:00 2001
From: Kevin Barnett <kevin.barnett@microsemi.com>
Date: Mon, 18 Jun 2018 13:22:42 -0500
Subject: scsi: smartpqi: improve handling for sync requests

Decrement the active thread count after the synchronous request was
submitted to the controller but before the driver blocks to wait for the
request to complete.

Reviewed-by: Scott Benesh <scott.benesh@microsemi.com>
Reviewed-by: Scott Teel <scott.teel@microsemi.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microsemi.com>
Signed-off-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 55 +++++++++++++++--------------------
 1 file changed, 23 insertions(+), 32 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index b78d20b74ed8..4036f65cbb72 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -3621,43 +3621,16 @@ static void pqi_raid_synchronous_complete(struct pqi_io_request *io_request,
 	complete(waiting);
 }
 
-static int pqi_submit_raid_request_synchronous_with_io_request(
-	struct pqi_ctrl_info *ctrl_info, struct pqi_io_request *io_request,
-	unsigned long timeout_msecs)
-{
-	int rc = 0;
-	DECLARE_COMPLETION_ONSTACK(wait);
-
-	io_request->io_complete_callback = pqi_raid_synchronous_complete;
-	io_request->context = &wait;
-
-	pqi_start_io(ctrl_info,
-		&ctrl_info->queue_groups[PQI_DEFAULT_QUEUE_GROUP], RAID_PATH,
-		io_request);
-
-	if (timeout_msecs == NO_TIMEOUT) {
-		pqi_wait_for_completion_io(ctrl_info, &wait);
-	} else {
-		if (!wait_for_completion_io_timeout(&wait,
-			msecs_to_jiffies(timeout_msecs))) {
-			dev_warn(&ctrl_info->pci_dev->dev,
-				"command timed out\n");
-			rc = -ETIMEDOUT;
-		}
-	}
-
-	return rc;
-}
-
 static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_iu_header *request, unsigned int flags,
 	struct pqi_raid_error_info *error_info, unsigned long timeout_msecs)
 {
-	int rc;
+	int rc = 0;
 	struct pqi_io_request *io_request;
 	unsigned long start_jiffies;
 	unsigned long msecs_blocked;
 	size_t iu_length;
+	DECLARE_COMPLETION_ONSTACK(wait);
 
 	/*
 	 * Note that specifying PQI_SYNC_FLAGS_INTERRUPTABLE and a timeout value
@@ -3686,11 +3659,13 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 	pqi_ctrl_busy(ctrl_info);
 	timeout_msecs = pqi_wait_if_ctrl_blocked(ctrl_info, timeout_msecs);
 	if (timeout_msecs == 0) {
+		pqi_ctrl_unbusy(ctrl_info);
 		rc = -ETIMEDOUT;
 		goto out;
 	}
 
 	if (pqi_ctrl_offline(ctrl_info)) {
+		pqi_ctrl_unbusy(ctrl_info);
 		rc = -ENXIO;
 		goto out;
 	}
@@ -3708,8 +3683,25 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 		PQI_REQUEST_HEADER_LENGTH;
 	memcpy(io_request->iu, request, iu_length);
 
-	rc = pqi_submit_raid_request_synchronous_with_io_request(ctrl_info,
-		io_request, timeout_msecs);
+	io_request->io_complete_callback = pqi_raid_synchronous_complete;
+	io_request->context = &wait;
+
+	pqi_start_io(ctrl_info,
+		&ctrl_info->queue_groups[PQI_DEFAULT_QUEUE_GROUP], RAID_PATH,
+		io_request);
+
+	pqi_ctrl_unbusy(ctrl_info);
+
+	if (timeout_msecs == NO_TIMEOUT) {
+		pqi_wait_for_completion_io(ctrl_info, &wait);
+	} else {
+		if (!wait_for_completion_io_timeout(&wait,
+			msecs_to_jiffies(timeout_msecs))) {
+			dev_warn(&ctrl_info->pci_dev->dev,
+				"command timed out\n");
+			rc = -ETIMEDOUT;
+		}
+	}
 
 	if (error_info) {
 		if (io_request->error_info)
@@ -3736,7 +3728,6 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 	pqi_free_io_request(io_request);
 
 out:
-	pqi_ctrl_unbusy(ctrl_info);
 	up(&ctrl_info->sync_request_sem);
 
 	return rc;
-- 
cgit v1.2.3


From 26b390aba2a8f7b9dd5ce4e3ada9431de327da6d Mon Sep 17 00:00:00 2001
From: Kevin Barnett <kevin.barnett@microsemi.com>
Date: Mon, 18 Jun 2018 13:22:48 -0500
Subject: scsi: smartpqi: improve error checking for sync requests

Detect rare error cases for synchronous requests down the RAID path.

Also retry INQUIRY of VPD page 0 sent to an HBA drive if the command failed
due to an abort.

Reviewed-by: Scott Benesh <scott.benesh@microsemi.com>
Reviewed-by: Scott Teel <scott.teel@microsemi.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microsemi.com>
Signed-off-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi.h      |  2 ++
 drivers/scsi/smartpqi/smartpqi_init.c | 54 ++++++++++++++++++++++++-----------
 2 files changed, 40 insertions(+), 16 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index dc3a0542a2e8..a8e7c4d48061 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -483,6 +483,8 @@ struct pqi_raid_error_info {
 #define CISS_CMD_STATUS_TMF			0xd
 #define CISS_CMD_STATUS_AIO_DISABLED		0xe
 
+#define PQI_CMD_STATUS_ABORTED	CISS_CMD_STATUS_ABORTED
+
 #define PQI_NUM_EVENT_QUEUE_ELEMENTS	32
 #define PQI_EVENT_OQ_ELEMENT_LENGTH	sizeof(struct pqi_event_response)
 
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 4036f65cbb72..1593ee343a2b 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -1197,20 +1197,30 @@ no_buffer:
 	device->volume_offline = volume_offline;
 }
 
+#define PQI_INQUIRY_PAGE0_RETRIES	3
+
 static int pqi_get_device_info(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_scsi_dev *device)
 {
 	int rc;
 	u8 *buffer;
+	unsigned int retries;
 
 	buffer = kmalloc(64, GFP_KERNEL);
 	if (!buffer)
 		return -ENOMEM;
 
 	/* Send an inquiry to the device to see what it is. */
-	rc = pqi_scsi_inquiry(ctrl_info, device->scsi3addr, 0, buffer, 64);
-	if (rc)
-		goto out;
+	for (retries = 0;;) {
+		rc = pqi_scsi_inquiry(ctrl_info, device->scsi3addr, 0,
+			buffer, 64);
+		if (rc == 0)
+			break;
+		if (pqi_is_logical_device(device) ||
+			rc != PQI_CMD_STATUS_ABORTED ||
+			++retries > PQI_INQUIRY_PAGE0_RETRIES)
+			goto out;
+	}
 
 	scsi_sanitize_inquiry_string(&buffer[8], 8);
 	scsi_sanitize_inquiry_string(&buffer[16], 16);
@@ -3621,6 +3631,29 @@ static void pqi_raid_synchronous_complete(struct pqi_io_request *io_request,
 	complete(waiting);
 }
 
+static int pqi_process_raid_io_error_synchronous(struct pqi_raid_error_info
+						*error_info)
+{
+	int rc = -EIO;
+
+	switch (error_info->data_out_result) {
+	case PQI_DATA_IN_OUT_GOOD:
+		if (error_info->status == SAM_STAT_GOOD)
+			rc = 0;
+		break;
+	case PQI_DATA_IN_OUT_UNDERFLOW:
+		if (error_info->status == SAM_STAT_GOOD ||
+			error_info->status == SAM_STAT_CHECK_CONDITION)
+			rc = 0;
+		break;
+	case PQI_DATA_IN_OUT_ABORTED:
+		rc = PQI_CMD_STATUS_ABORTED;
+		break;
+	}
+
+	return rc;
+}
+
 static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 	struct pqi_iu_header *request, unsigned int flags,
 	struct pqi_raid_error_info *error_info, unsigned long timeout_msecs)
@@ -3710,19 +3743,8 @@ static int pqi_submit_raid_request_synchronous(struct pqi_ctrl_info *ctrl_info,
 		else
 			memset(error_info, 0, sizeof(*error_info));
 	} else if (rc == 0 && io_request->error_info) {
-		u8 scsi_status;
-		struct pqi_raid_error_info *raid_error_info;
-
-		raid_error_info = io_request->error_info;
-		scsi_status = raid_error_info->status;
-
-		if (scsi_status == SAM_STAT_CHECK_CONDITION &&
-			raid_error_info->data_out_result ==
-			PQI_DATA_IN_OUT_UNDERFLOW)
-			scsi_status = SAM_STAT_GOOD;
-
-		if (scsi_status != SAM_STAT_GOOD)
-			rc = -EIO;
+		rc = pqi_process_raid_io_error_synchronous(
+			io_request->error_info);
 	}
 
 	pqi_free_io_request(io_request);
-- 
cgit v1.2.3


From 9f8d05fa98442de78d1ab30235b0cc656ed7aff0 Mon Sep 17 00:00:00 2001
From: Kevin Barnett <kevin.barnett@microsemi.com>
Date: Mon, 18 Jun 2018 13:22:54 -0500
Subject: scsi: smartpqi: add inspur advantech ids

Add support for these new device IDs:

  Advantech MIC-8312BridgeB
  INSPUR PM8204-2GB
  INSPUR PM8204-4GB
  INSPUR PM8222-SHBA

Reviewed-by: Scott Benesh <scott.benesh@microsemi.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microsemi.com>
Signed-off-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 1593ee343a2b..8b70b879735e 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -6837,6 +6837,18 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       0x1bd4, 0x0048)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x004a)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x004b)
+	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       0x1bd4, 0x004c)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADAPTEC2, 0x0110)
@@ -6961,6 +6973,10 @@ static const struct pci_device_id pqi_pci_id_table[] = {
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_ADAPTEC2, 0x1380)
 	},
+	{
+		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
+			       PCI_VENDOR_ID_ADVANTECH, 0x8312)
+	},
 	{
 		PCI_DEVICE_SUB(PCI_VENDOR_ID_ADAPTEC2, 0x028f,
 			       PCI_VENDOR_ID_DELL, 0x1fe0)
-- 
cgit v1.2.3


From dac12fbc7b0a433a160b89212a56e155c94f3a80 Mon Sep 17 00:00:00 2001
From: Kevin Barnett <kevin.barnett@microsemi.com>
Date: Mon, 18 Jun 2018 13:23:00 -0500
Subject: scsi: smartpqi: fix critical ARM issue reading PQI index registers

Use the readl() kernel function to read all index registers. For ARM
systems, this function includes a read memory barrier that eliminates ci/pi
corruption.

Reviewed-by: Scott Benesh <scott.benesh@microsemi.com>
Reviewed-by: Scott Teel <scott.teel@microsemi.com>
Tested-by: Shunyong Yang <shunyong.yang@hxt-semitech.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microsemi.com>
Signed-off-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi.h      | 10 ++++----
 drivers/scsi/smartpqi/smartpqi_init.c | 45 +++++++++++++++++++----------------
 2 files changed, 30 insertions(+), 25 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi.h b/drivers/scsi/smartpqi/smartpqi.h
index a8e7c4d48061..e97bf2670315 100644
--- a/drivers/scsi/smartpqi/smartpqi.h
+++ b/drivers/scsi/smartpqi/smartpqi.h
@@ -583,8 +583,8 @@ struct pqi_admin_queues_aligned {
 struct pqi_admin_queues {
 	void		*iq_element_array;
 	void		*oq_element_array;
-	volatile pqi_index_t *iq_ci;
-	volatile pqi_index_t *oq_pi;
+	pqi_index_t	*iq_ci;
+	pqi_index_t __iomem *oq_pi;
 	dma_addr_t	iq_element_array_bus_addr;
 	dma_addr_t	oq_element_array_bus_addr;
 	dma_addr_t	iq_ci_bus_addr;
@@ -608,8 +608,8 @@ struct pqi_queue_group {
 	dma_addr_t	oq_element_array_bus_addr;
 	__le32 __iomem	*iq_pi[2];
 	pqi_index_t	iq_pi_copy[2];
-	volatile pqi_index_t *iq_ci[2];
-	volatile pqi_index_t *oq_pi;
+	pqi_index_t __iomem	*iq_ci[2];
+	pqi_index_t __iomem	*oq_pi;
 	dma_addr_t	iq_ci_bus_addr[2];
 	dma_addr_t	oq_pi_bus_addr;
 	__le32 __iomem	*oq_ci;
@@ -622,7 +622,7 @@ struct pqi_event_queue {
 	u16		oq_id;
 	u16		int_msg_num;
 	void		*oq_element_array;
-	volatile pqi_index_t *oq_pi;
+	pqi_index_t __iomem	*oq_pi;
 	dma_addr_t	oq_element_array_bus_addr;
 	dma_addr_t	oq_pi_bus_addr;
 	__le32 __iomem	*oq_ci;
diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index 8b70b879735e..b4a685ed9ed1 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -2703,7 +2703,7 @@ static unsigned int pqi_process_io_intr(struct pqi_ctrl_info *ctrl_info,
 	oq_ci = queue_group->oq_ci_copy;
 
 	while (1) {
-		oq_pi = *queue_group->oq_pi;
+		oq_pi = readl(queue_group->oq_pi);
 		if (oq_pi == oq_ci)
 			break;
 
@@ -2794,7 +2794,7 @@ static void pqi_send_event_ack(struct pqi_ctrl_info *ctrl_info,
 		spin_lock_irqsave(&queue_group->submit_lock[RAID_PATH], flags);
 
 		iq_pi = queue_group->iq_pi_copy[RAID_PATH];
-		iq_ci = *queue_group->iq_ci[RAID_PATH];
+		iq_ci = readl(queue_group->iq_ci[RAID_PATH]);
 
 		if (pqi_num_elements_free(iq_pi, iq_ci,
 			ctrl_info->num_elements_per_iq))
@@ -2953,7 +2953,7 @@ static unsigned int pqi_process_event_intr(struct pqi_ctrl_info *ctrl_info)
 	oq_ci = event_queue->oq_ci_copy;
 
 	while (1) {
-		oq_pi = *event_queue->oq_pi;
+		oq_pi = readl(event_queue->oq_pi);
 		if (oq_pi == oq_ci)
 			break;
 
@@ -3177,7 +3177,7 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 	size_t element_array_length_per_iq;
 	size_t element_array_length_per_oq;
 	void *element_array;
-	void *next_queue_index;
+	void __iomem *next_queue_index;
 	void *aligned_pointer;
 	unsigned int num_inbound_queues;
 	unsigned int num_outbound_queues;
@@ -3273,7 +3273,7 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 	element_array += PQI_NUM_EVENT_QUEUE_ELEMENTS *
 		PQI_EVENT_OQ_ELEMENT_LENGTH;
 
-	next_queue_index = PTR_ALIGN(element_array,
+	next_queue_index = (void __iomem *)PTR_ALIGN(element_array,
 		PQI_OPERATIONAL_INDEX_ALIGNMENT);
 
 	for (i = 0; i < ctrl_info->num_queue_groups; i++) {
@@ -3281,21 +3281,24 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 		queue_group->iq_ci[RAID_PATH] = next_queue_index;
 		queue_group->iq_ci_bus_addr[RAID_PATH] =
 			ctrl_info->queue_memory_base_dma_handle +
-			(next_queue_index - ctrl_info->queue_memory_base);
+			(next_queue_index -
+			(void __iomem *)ctrl_info->queue_memory_base);
 		next_queue_index += sizeof(pqi_index_t);
 		next_queue_index = PTR_ALIGN(next_queue_index,
 			PQI_OPERATIONAL_INDEX_ALIGNMENT);
 		queue_group->iq_ci[AIO_PATH] = next_queue_index;
 		queue_group->iq_ci_bus_addr[AIO_PATH] =
 			ctrl_info->queue_memory_base_dma_handle +
-			(next_queue_index - ctrl_info->queue_memory_base);
+			(next_queue_index -
+			(void __iomem *)ctrl_info->queue_memory_base);
 		next_queue_index += sizeof(pqi_index_t);
 		next_queue_index = PTR_ALIGN(next_queue_index,
 			PQI_OPERATIONAL_INDEX_ALIGNMENT);
 		queue_group->oq_pi = next_queue_index;
 		queue_group->oq_pi_bus_addr =
 			ctrl_info->queue_memory_base_dma_handle +
-			(next_queue_index - ctrl_info->queue_memory_base);
+			(next_queue_index -
+			(void __iomem *)ctrl_info->queue_memory_base);
 		next_queue_index += sizeof(pqi_index_t);
 		next_queue_index = PTR_ALIGN(next_queue_index,
 			PQI_OPERATIONAL_INDEX_ALIGNMENT);
@@ -3304,7 +3307,8 @@ static int pqi_alloc_operational_queues(struct pqi_ctrl_info *ctrl_info)
 	ctrl_info->event_queue.oq_pi = next_queue_index;
 	ctrl_info->event_queue.oq_pi_bus_addr =
 		ctrl_info->queue_memory_base_dma_handle +
-		(next_queue_index - ctrl_info->queue_memory_base);
+		(next_queue_index -
+		(void __iomem *)ctrl_info->queue_memory_base);
 
 	return 0;
 }
@@ -3378,7 +3382,8 @@ static int pqi_alloc_admin_queues(struct pqi_ctrl_info *ctrl_info)
 	admin_queues->oq_element_array =
 		&admin_queues_aligned->oq_element_array;
 	admin_queues->iq_ci = &admin_queues_aligned->iq_ci;
-	admin_queues->oq_pi = &admin_queues_aligned->oq_pi;
+	admin_queues->oq_pi =
+		(pqi_index_t __iomem *)&admin_queues_aligned->oq_pi;
 
 	admin_queues->iq_element_array_bus_addr =
 		ctrl_info->admin_queue_memory_base_dma_handle +
@@ -3394,8 +3399,8 @@ static int pqi_alloc_admin_queues(struct pqi_ctrl_info *ctrl_info)
 		ctrl_info->admin_queue_memory_base);
 	admin_queues->oq_pi_bus_addr =
 		ctrl_info->admin_queue_memory_base_dma_handle +
-		((void *)admin_queues->oq_pi -
-		ctrl_info->admin_queue_memory_base);
+		((void __iomem *)admin_queues->oq_pi -
+		(void __iomem *)ctrl_info->admin_queue_memory_base);
 
 	return 0;
 }
@@ -3496,7 +3501,7 @@ static int pqi_poll_for_admin_response(struct pqi_ctrl_info *ctrl_info,
 	timeout = (PQI_ADMIN_REQUEST_TIMEOUT_SECS * HZ) + jiffies;
 
 	while (1) {
-		oq_pi = *admin_queues->oq_pi;
+		oq_pi = readl(admin_queues->oq_pi);
 		if (oq_pi != oq_ci)
 			break;
 		if (time_after(jiffies, timeout)) {
@@ -3555,7 +3560,7 @@ static void pqi_start_io(struct pqi_ctrl_info *ctrl_info,
 			DIV_ROUND_UP(iu_length,
 				PQI_OPERATIONAL_IQ_ELEMENT_LENGTH);
 
-		iq_ci = *queue_group->iq_ci[path];
+		iq_ci = readl(queue_group->iq_ci[path]);
 
 		if (num_elements_needed > pqi_num_elements_free(iq_pi, iq_ci,
 			ctrl_info->num_elements_per_iq))
@@ -5054,7 +5059,7 @@ static int pqi_wait_until_inbound_queues_empty(struct pqi_ctrl_info *ctrl_info)
 			iq_pi = queue_group->iq_pi_copy[path];
 
 			while (1) {
-				iq_ci = *queue_group->iq_ci[path];
+				iq_ci = readl(queue_group->iq_ci[path]);
 				if (iq_ci == iq_pi)
 					break;
 				pqi_check_ctrl_health(ctrl_info);
@@ -6243,20 +6248,20 @@ static void pqi_reinit_queues(struct pqi_ctrl_info *ctrl_info)
 	admin_queues = &ctrl_info->admin_queues;
 	admin_queues->iq_pi_copy = 0;
 	admin_queues->oq_ci_copy = 0;
-	*admin_queues->oq_pi = 0;
+	writel(0, admin_queues->oq_pi);
 
 	for (i = 0; i < ctrl_info->num_queue_groups; i++) {
 		ctrl_info->queue_groups[i].iq_pi_copy[RAID_PATH] = 0;
 		ctrl_info->queue_groups[i].iq_pi_copy[AIO_PATH] = 0;
 		ctrl_info->queue_groups[i].oq_ci_copy = 0;
 
-		*ctrl_info->queue_groups[i].iq_ci[RAID_PATH] = 0;
-		*ctrl_info->queue_groups[i].iq_ci[AIO_PATH] = 0;
-		*ctrl_info->queue_groups[i].oq_pi = 0;
+		writel(0, ctrl_info->queue_groups[i].iq_ci[RAID_PATH]);
+		writel(0, ctrl_info->queue_groups[i].iq_ci[AIO_PATH]);
+		writel(0, ctrl_info->queue_groups[i].oq_pi);
 	}
 
 	event_queue = &ctrl_info->event_queue;
-	*event_queue->oq_pi = 0;
+	writel(0, event_queue->oq_pi);
 	event_queue->oq_ci_copy = 0;
 }
 
-- 
cgit v1.2.3


From 4ae5e9d159f83392c98c4ed88dfc63f19745be38 Mon Sep 17 00:00:00 2001
From: Don Brace <don.brace@microsemi.com>
Date: Mon, 18 Jun 2018 13:23:06 -0500
Subject: scsi: smartpqi: bump driver version to 1.1.4-130

Reviewed-by: Scott Benesh <scott.benesh@microsemi.com>
Signed-off-by: Kevin Barnett <kevin.barnett@microsemi.com>
Signed-off-by: Don Brace <don.brace@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/smartpqi/smartpqi_init.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
index b4a685ed9ed1..2112ea6723c6 100644
--- a/drivers/scsi/smartpqi/smartpqi_init.c
+++ b/drivers/scsi/smartpqi/smartpqi_init.c
@@ -40,11 +40,11 @@
 #define BUILD_TIMESTAMP
 #endif
 
-#define DRIVER_VERSION		"1.1.4-115"
+#define DRIVER_VERSION		"1.1.4-130"
 #define DRIVER_MAJOR		1
 #define DRIVER_MINOR		1
 #define DRIVER_RELEASE		4
-#define DRIVER_REVISION		115
+#define DRIVER_REVISION		130
 
 #define DRIVER_NAME		"Microsemi PQI Driver (v" \
 				DRIVER_VERSION BUILD_TIMESTAMP ")"
-- 
cgit v1.2.3


From 6519750210d9d3330e85d12e0128652edde448d2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 12 Jun 2018 10:34:50 +0200
Subject: sched/swait: Remove __prepare_to_swait

There is no public user of this API, remove it.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: bigeasy@linutronix.de
Cc: oleg@redhat.com
Cc: paulmck@linux.vnet.ibm.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180612083909.157076812@infradead.org
---
 include/linux/swait.h | 1 -
 kernel/sched/swait.c  | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/include/linux/swait.h b/include/linux/swait.h
index bf8cb0dee23c..d6a5e949e4ca 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -161,7 +161,6 @@ extern void swake_up(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
 
-extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
 extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
 
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index b6fb2c3b3ff7..e68bb1398b05 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -69,7 +69,7 @@ void swake_up_all(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_all);
 
-void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
 {
 	wait->task = current;
 	if (list_empty(&wait->task_list))
-- 
cgit v1.2.3


From 0abf17bc7790dd0467ed0e38522242f23c5da1c4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 12 Jun 2018 10:34:51 +0200
Subject: sched/swait: Switch to full exclusive mode

Linus noted that swait basically implements exclusive mode -- because
swake_up() only wakes a single waiter. And because of that it should
take care to properly deal with the interruptible case.

In short, the problem is that swake_up() can race with a signal. In
this this case it is possible the swake_up() 'wakes' the waiter that
is already on the way out because it just got a signal and the wakeup
gets lost.

The normal wait code is very careful and avoids this situation, make
sure we do too.

Copy the exact exclusive semantics from wait.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: bigeasy@linutronix.de
Cc: oleg@redhat.com
Cc: paulmck@linux.vnet.ibm.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180612083909.209762413@infradead.org
---
 include/linux/swait.h | 11 ++++++-----
 kernel/sched/swait.c  | 22 +++++++++++++++++-----
 2 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/include/linux/swait.h b/include/linux/swait.h
index d6a5e949e4ca..dd032061112d 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -38,8 +38,8 @@
  *    all wakeups are TASK_NORMAL in order to avoid O(n) lookups for the right
  *    sleeper state.
  *
- *  - the exclusive mode; because this requires preserving the list order
- *    and this is hard.
+ *  - the !exclusive mode; because that leads to O(n) wakeups, everything is
+ *    exclusive.
  *
  *  - custom wake callback functions; because you cannot give any guarantees
  *    about random code. This also allows swait to be used in RT, such that
@@ -167,9 +167,10 @@ extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queu
 extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 
-/* as per ___wait_event() but for swait, therefore "exclusive == 0" */
+/* as per ___wait_event() but for swait, therefore "exclusive == 1" */
 #define ___swait_event(wq, condition, state, ret, cmd)			\
 ({									\
+	__label__ __out;						\
 	struct swait_queue __wait;					\
 	long __ret = ret;						\
 									\
@@ -182,13 +183,13 @@ extern void finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
 									\
 		if (___wait_is_interruptible(state) && __int) {		\
 			__ret = __int;					\
-			break;						\
+			goto __out;					\
 		}							\
 									\
 		cmd;							\
 	}								\
 	finish_swait(&wq, &__wait);					\
-	__ret;								\
+__out:	__ret;								\
 })
 
 #define __swait_event(wq, condition)					\
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index e68bb1398b05..66890de93ee5 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -73,7 +73,7 @@ static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *w
 {
 	wait->task = current;
 	if (list_empty(&wait->task_list))
-		list_add(&wait->task_list, &q->task_list);
+		list_add_tail(&wait->task_list, &q->task_list);
 }
 
 void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
@@ -89,12 +89,24 @@ EXPORT_SYMBOL(prepare_to_swait);
 
 long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
-	if (signal_pending_state(state, current))
-		return -ERESTARTSYS;
+	unsigned long flags;
+	long ret = 0;
 
-	prepare_to_swait(q, wait, state);
+	raw_spin_lock_irqsave(&q->lock, flags);
+	if (unlikely(signal_pending_state(state, current))) {
+		/*
+		 * See prepare_to_wait_event(). TL;DR, subsequent swake_up()
+		 * must not see us.
+		 */
+		list_del_init(&wait->task_list);
+		ret = -ERESTARTSYS;
+	} else {
+		__prepare_to_swait(q, wait);
+		set_current_state(state);
+	}
+	raw_spin_unlock_irqrestore(&q->lock, flags);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(prepare_to_swait_event);
 
-- 
cgit v1.2.3


From b3dae109fa89d67334bf3349babab3ad9b6f233f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 12 Jun 2018 10:34:52 +0200
Subject: sched/swait: Rename to exclusive

Since swait basically implemented exclusive waits only, make sure
the API reflects that.

  $ git grep -l -e "\<swake_up\>"
		-e "\<swait_event[^ (]*"
		-e "\<prepare_to_swait\>" | while read file;
    do
	sed -i -e 's/\<swake_up\>/&_one/g'
	       -e 's/\<swait_event[^ (]*/&_exclusive/g'
	       -e 's/\<prepare_to_swait\>/&_exclusive/g' $file;
    done

With a few manual touch-ups.

Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: bigeasy@linutronix.de
Cc: oleg@redhat.com
Cc: paulmck@linux.vnet.ibm.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180612083909.261946548@infradead.org
---
 arch/mips/kvm/mips.c         |  4 ++--
 arch/powerpc/kvm/book3s_hv.c |  6 +++---
 arch/s390/kvm/interrupt.c    |  2 +-
 arch/x86/kernel/kvm.c        |  4 ++--
 arch/x86/kvm/lapic.c         |  2 +-
 include/linux/swait.h        | 24 ++++++++++++------------
 kernel/power/suspend.c       |  4 ++--
 kernel/rcu/srcutiny.c        |  4 ++--
 kernel/rcu/tree.c            |  8 ++++----
 kernel/rcu/tree_exp.h        |  4 ++--
 kernel/rcu/tree_plugin.h     | 12 ++++++------
 kernel/sched/swait.c         | 10 +++++-----
 virt/kvm/arm/arm.c           |  4 ++--
 virt/kvm/arm/psci.c          |  2 +-
 virt/kvm/async_pf.c          |  2 +-
 virt/kvm/kvm_main.c          |  4 ++--
 16 files changed, 48 insertions(+), 48 deletions(-)

diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index 7cd76f93a438..f7ea8e21656b 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -515,7 +515,7 @@ int kvm_vcpu_ioctl_interrupt(struct kvm_vcpu *vcpu,
 	dvcpu->arch.wait = 0;
 
 	if (swq_has_sleeper(&dvcpu->wq))
-		swake_up(&dvcpu->wq);
+		swake_up_one(&dvcpu->wq);
 
 	return 0;
 }
@@ -1204,7 +1204,7 @@ static void kvm_mips_comparecount_func(unsigned long data)
 
 	vcpu->arch.wait = 0;
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 }
 
 /* low level hrtimer wake routine */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index de686b340f4a..ee4a8854985e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -216,7 +216,7 @@ static void kvmppc_fast_vcpu_kick_hv(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 	}
 
@@ -3188,7 +3188,7 @@ static void kvmppc_vcore_blocked(struct kvmppc_vcore *vc)
 		}
 	}
 
-	prepare_to_swait(&vc->wq, &wait, TASK_INTERRUPTIBLE);
+	prepare_to_swait_exclusive(&vc->wq, &wait, TASK_INTERRUPTIBLE);
 
 	if (kvmppc_vcore_check_block(vc)) {
 		finish_swait(&vc->wq, &wait);
@@ -3311,7 +3311,7 @@ static int kvmppc_run_vcpu(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 			kvmppc_start_thread(vcpu, vc);
 			trace_kvm_guest_enter(vcpu);
 		} else if (vc->vcore_state == VCORE_SLEEPING) {
-			swake_up(&vc->wq);
+			swake_up_one(&vc->wq);
 		}
 
 	}
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index daa09f89ca2d..fcb55b02990e 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -1145,7 +1145,7 @@ void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
 		 * yield-candidate.
 		 */
 		vcpu->preempted = true;
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 		vcpu->stat.halt_wakeup++;
 	}
 	/*
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5b2300b818af..a37bda38d205 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -154,7 +154,7 @@ void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
 
 	for (;;) {
 		if (!n.halted)
-			prepare_to_swait(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
+			prepare_to_swait_exclusive(&n.wq, &wait, TASK_UNINTERRUPTIBLE);
 		if (hlist_unhashed(&n.link))
 			break;
 
@@ -188,7 +188,7 @@ static void apf_task_wake_one(struct kvm_task_sleep_node *n)
 	if (n->halted)
 		smp_send_reschedule(n->cpu);
 	else if (swq_has_sleeper(&n->wq))
-		swake_up(&n->wq);
+		swake_up_one(&n->wq);
 }
 
 static void apf_task_wake_all(void)
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index b5cd8465d44f..d536d457517b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1379,7 +1379,7 @@ static void apic_timer_expired(struct kvm_lapic *apic)
 	 * using swait_active() is safe.
 	 */
 	if (swait_active(q))
-		swake_up(q);
+		swake_up_one(q);
 
 	if (apic_lvtt_tscdeadline(apic))
 		ktimer->expired_tscdeadline = ktimer->tscdeadline;
diff --git a/include/linux/swait.h b/include/linux/swait.h
index dd032061112d..73e06e9986d4 100644
--- a/include/linux/swait.h
+++ b/include/linux/swait.h
@@ -16,7 +16,7 @@
  * wait-queues, but the semantics are actually completely different, and
  * every single user we have ever had has been buggy (or pointless).
  *
- * A "swake_up()" only wakes up _one_ waiter, which is not at all what
+ * A "swake_up_one()" only wakes up _one_ waiter, which is not at all what
  * "wake_up()" does, and has led to problems. In other cases, it has
  * been fine, because there's only ever one waiter (kvm), but in that
  * case gthe whole "simple" wait-queue is just pointless to begin with,
@@ -115,7 +115,7 @@ extern void __init_swait_queue_head(struct swait_queue_head *q, const char *name
  *      CPU0 - waker                    CPU1 - waiter
  *
  *                                      for (;;) {
- *      @cond = true;                     prepare_to_swait(&wq_head, &wait, state);
+ *      @cond = true;                     prepare_to_swait_exclusive(&wq_head, &wait, state);
  *      smp_mb();                         // smp_mb() from set_current_state()
  *      if (swait_active(wq_head))        if (@cond)
  *        wake_up(wq_head);                      break;
@@ -157,11 +157,11 @@ static inline bool swq_has_sleeper(struct swait_queue_head *wq)
 	return swait_active(wq);
 }
 
-extern void swake_up(struct swait_queue_head *q);
+extern void swake_up_one(struct swait_queue_head *q);
 extern void swake_up_all(struct swait_queue_head *q);
 extern void swake_up_locked(struct swait_queue_head *q);
 
-extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state);
+extern void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state);
 extern long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state);
 
 extern void __finish_swait(struct swait_queue_head *q, struct swait_queue *wait);
@@ -196,7 +196,7 @@ __out:	__ret;								\
 	(void)___swait_event(wq, condition, TASK_UNINTERRUPTIBLE, 0,	\
 			    schedule())
 
-#define swait_event(wq, condition)					\
+#define swait_event_exclusive(wq, condition)				\
 do {									\
 	if (condition)							\
 		break;							\
@@ -208,7 +208,7 @@ do {									\
 		      TASK_UNINTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_timeout(wq, condition, timeout)			\
+#define swait_event_timeout_exclusive(wq, condition, timeout)		\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -220,7 +220,7 @@ do {									\
 	___swait_event(wq, condition, TASK_INTERRUPTIBLE, 0,		\
 		      schedule())
 
-#define swait_event_interruptible(wq, condition)			\
+#define swait_event_interruptible_exclusive(wq, condition)		\
 ({									\
 	int __ret = 0;							\
 	if (!(condition))						\
@@ -233,7 +233,7 @@ do {									\
 		      TASK_INTERRUPTIBLE, timeout,			\
 		      __ret = schedule_timeout(__ret))
 
-#define swait_event_interruptible_timeout(wq, condition, timeout)	\
+#define swait_event_interruptible_timeout_exclusive(wq, condition, timeout)\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
@@ -246,7 +246,7 @@ do {									\
 	(void)___swait_event(wq, condition, TASK_IDLE, 0, schedule())
 
 /**
- * swait_event_idle - wait without system load contribution
+ * swait_event_idle_exclusive - wait without system load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  *
@@ -257,7 +257,7 @@ do {									\
  * condition and doesn't want to contribute to system load. Signals are
  * ignored.
  */
-#define swait_event_idle(wq, condition)					\
+#define swait_event_idle_exclusive(wq, condition)			\
 do {									\
 	if (condition)							\
 		break;							\
@@ -270,7 +270,7 @@ do {									\
 		       __ret = schedule_timeout(__ret))
 
 /**
- * swait_event_idle_timeout - wait up to timeout without load contribution
+ * swait_event_idle_timeout_exclusive - wait up to timeout without load contribution
  * @wq: the waitqueue to wait on
  * @condition: a C expression for the event to wait for
  * @timeout: timeout at which we'll give up in jiffies
@@ -288,7 +288,7 @@ do {									\
  * or the remaining jiffies (at least 1) if the @condition evaluated
  * to %true before the @timeout elapsed.
  */
-#define swait_event_idle_timeout(wq, condition, timeout)		\
+#define swait_event_idle_timeout_exclusive(wq, condition, timeout)	\
 ({									\
 	long __ret = timeout;						\
 	if (!___wait_cond_timeout(condition))				\
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 87331565e505..70178f6ffdc4 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -92,7 +92,7 @@ static void s2idle_enter(void)
 	/* Push all the CPUs into the idle loop. */
 	wake_up_all_idle_cpus();
 	/* Make the current CPU wait so it can enter the idle loop too. */
-	swait_event(s2idle_wait_head,
+	swait_event_exclusive(s2idle_wait_head,
 		    s2idle_state == S2IDLE_STATE_WAKE);
 
 	cpuidle_pause();
@@ -160,7 +160,7 @@ void s2idle_wake(void)
 	raw_spin_lock_irqsave(&s2idle_lock, flags);
 	if (s2idle_state > S2IDLE_STATE_NONE) {
 		s2idle_state = S2IDLE_STATE_WAKE;
-		swake_up(&s2idle_wait_head);
+		swake_up_one(&s2idle_wait_head);
 	}
 	raw_spin_unlock_irqrestore(&s2idle_lock, flags);
 }
diff --git a/kernel/rcu/srcutiny.c b/kernel/rcu/srcutiny.c
index 622792abe41a..04fc2ed71af8 100644
--- a/kernel/rcu/srcutiny.c
+++ b/kernel/rcu/srcutiny.c
@@ -110,7 +110,7 @@ void __srcu_read_unlock(struct srcu_struct *sp, int idx)
 
 	WRITE_ONCE(sp->srcu_lock_nesting[idx], newval);
 	if (!newval && READ_ONCE(sp->srcu_gp_waiting))
-		swake_up(&sp->srcu_wq);
+		swake_up_one(&sp->srcu_wq);
 }
 EXPORT_SYMBOL_GPL(__srcu_read_unlock);
 
@@ -140,7 +140,7 @@ void srcu_drive_gp(struct work_struct *wp)
 	idx = sp->srcu_idx;
 	WRITE_ONCE(sp->srcu_idx, !sp->srcu_idx);
 	WRITE_ONCE(sp->srcu_gp_waiting, true);  /* srcu_read_unlock() wakes! */
-	swait_event(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
+	swait_event_exclusive(sp->srcu_wq, !READ_ONCE(sp->srcu_lock_nesting[idx]));
 	WRITE_ONCE(sp->srcu_gp_waiting, false); /* srcu_read_unlock() cheap. */
 
 	/* Invoke the callbacks we removed above. */
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index aa7cade1b9f3..91f888d3b23a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1727,7 +1727,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 	    !READ_ONCE(rsp->gp_flags) ||
 	    !rsp->gp_kthread)
 		return;
-	swake_up(&rsp->gp_wq);
+	swake_up_one(&rsp->gp_wq);
 }
 
 /*
@@ -2002,7 +2002,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 }
 
 /*
- * Helper function for swait_event_idle() wakeup at force-quiescent-state
+ * Helper function for swait_event_idle_exclusive() wakeup at force-quiescent-state
  * time.
  */
 static bool rcu_gp_fqs_check_wake(struct rcu_state *rsp, int *gfp)
@@ -2144,7 +2144,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
-			swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
+			swait_event_idle_exclusive(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
 						     RCU_GP_FLAG_INIT);
 			rsp->gp_state = RCU_GP_DONE_GPS;
 			/* Locking provides needed memory barrier. */
@@ -2176,7 +2176,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					       READ_ONCE(rsp->gpnum),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
-			ret = swait_event_idle_timeout(rsp->gp_wq,
+			ret = swait_event_idle_timeout_exclusive(rsp->gp_wq,
 					rcu_gp_fqs_check_wake(rsp, &gf), j);
 			rsp->gp_state = RCU_GP_DOING_FQS;
 			/* Locking provides needed memory barriers. */
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d40708e8c5d6..d428cc1064c8 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -212,7 +212,7 @@ static void __rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			if (wake) {
 				smp_mb(); /* EGP done before wake_up(). */
-				swake_up(&rsp->expedited_wq);
+				swake_up_one(&rsp->expedited_wq);
 			}
 			break;
 		}
@@ -518,7 +518,7 @@ static void synchronize_sched_expedited_wait(struct rcu_state *rsp)
 	jiffies_start = jiffies;
 
 	for (;;) {
-		ret = swait_event_timeout(
+		ret = swait_event_timeout_exclusive(
 				rsp->expedited_wq,
 				sync_rcu_preempt_exp_done_unlocked(rnp_root),
 				jiffies_stall);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7fd12039e512..ad53d133f709 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1854,8 +1854,8 @@ static void __wake_nocb_leader(struct rcu_data *rdp, bool force,
 		WRITE_ONCE(rdp_leader->nocb_leader_sleep, false);
 		del_timer(&rdp->nocb_timer);
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
-		smp_mb(); /* ->nocb_leader_sleep before swake_up(). */
-		swake_up(&rdp_leader->nocb_wq);
+		smp_mb(); /* ->nocb_leader_sleep before swake_up_one(). */
+		swake_up_one(&rdp_leader->nocb_wq);
 	} else {
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 	}
@@ -2082,7 +2082,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	 */
 	trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
 	for (;;) {
-		swait_event_interruptible(
+		swait_event_interruptible_exclusive(
 			rnp->nocb_gp_wq[c & 0x1],
 			(d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
 		if (likely(d))
@@ -2111,7 +2111,7 @@ wait_again:
 	/* Wait for callbacks to appear. */
 	if (!rcu_nocb_poll) {
 		trace_rcu_nocb_wake(my_rdp->rsp->name, my_rdp->cpu, TPS("Sleep"));
-		swait_event_interruptible(my_rdp->nocb_wq,
+		swait_event_interruptible_exclusive(my_rdp->nocb_wq,
 				!READ_ONCE(my_rdp->nocb_leader_sleep));
 		raw_spin_lock_irqsave(&my_rdp->nocb_lock, flags);
 		my_rdp->nocb_leader_sleep = true;
@@ -2176,7 +2176,7 @@ wait_again:
 		raw_spin_unlock_irqrestore(&rdp->nocb_lock, flags);
 		if (rdp != my_rdp && tail == &rdp->nocb_follower_head) {
 			/* List was empty, so wake up the follower.  */
-			swake_up(&rdp->nocb_wq);
+			swake_up_one(&rdp->nocb_wq);
 		}
 	}
 
@@ -2193,7 +2193,7 @@ static void nocb_follower_wait(struct rcu_data *rdp)
 {
 	for (;;) {
 		trace_rcu_nocb_wake(rdp->rsp->name, rdp->cpu, TPS("FollowerSleep"));
-		swait_event_interruptible(rdp->nocb_wq,
+		swait_event_interruptible_exclusive(rdp->nocb_wq,
 					 READ_ONCE(rdp->nocb_follower_head));
 		if (smp_load_acquire(&rdp->nocb_follower_head)) {
 			/* ^^^ Ensure CB invocation follows _head test. */
diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c
index 66890de93ee5..66b59ac77c22 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,7 +32,7 @@ void swake_up_locked(struct swait_queue_head *q)
 }
 EXPORT_SYMBOL(swake_up_locked);
 
-void swake_up(struct swait_queue_head *q)
+void swake_up_one(struct swait_queue_head *q)
 {
 	unsigned long flags;
 
@@ -40,7 +40,7 @@ void swake_up(struct swait_queue_head *q)
 	swake_up_locked(q);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(swake_up);
+EXPORT_SYMBOL(swake_up_one);
 
 /*
  * Does not allow usage from IRQ disabled, since we must be able to
@@ -76,7 +76,7 @@ static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *w
 		list_add_tail(&wait->task_list, &q->task_list);
 }
 
-void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state)
+void prepare_to_swait_exclusive(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
 	unsigned long flags;
 
@@ -85,7 +85,7 @@ void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int
 	set_current_state(state);
 	raw_spin_unlock_irqrestore(&q->lock, flags);
 }
-EXPORT_SYMBOL(prepare_to_swait);
+EXPORT_SYMBOL(prepare_to_swait_exclusive);
 
 long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait, int state)
 {
@@ -95,7 +95,7 @@ long prepare_to_swait_event(struct swait_queue_head *q, struct swait_queue *wait
 	raw_spin_lock_irqsave(&q->lock, flags);
 	if (unlikely(signal_pending_state(state, current))) {
 		/*
-		 * See prepare_to_wait_event(). TL;DR, subsequent swake_up()
+		 * See prepare_to_wait_event(). TL;DR, subsequent swake_up_one()
 		 * must not see us.
 		 */
 		list_del_init(&wait->task_list);
diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 04e554cae3a2..108250e4d376 100644
--- a/virt/kvm/arm/arm.c
+++ b/virt/kvm/arm/arm.c
@@ -604,7 +604,7 @@ void kvm_arm_resume_guest(struct kvm *kvm)
 
 	kvm_for_each_vcpu(i, vcpu, kvm) {
 		vcpu->arch.pause = false;
-		swake_up(kvm_arch_vcpu_wq(vcpu));
+		swake_up_one(kvm_arch_vcpu_wq(vcpu));
 	}
 }
 
@@ -612,7 +612,7 @@ static void vcpu_req_sleep(struct kvm_vcpu *vcpu)
 {
 	struct swait_queue_head *wq = kvm_arch_vcpu_wq(vcpu);
 
-	swait_event_interruptible(*wq, ((!vcpu->arch.power_off) &&
+	swait_event_interruptible_exclusive(*wq, ((!vcpu->arch.power_off) &&
 				       (!vcpu->arch.pause)));
 
 	if (vcpu->arch.power_off || vcpu->arch.pause) {
diff --git a/virt/kvm/arm/psci.c b/virt/kvm/arm/psci.c
index c95ab4c5a475..9b73d3ad918a 100644
--- a/virt/kvm/arm/psci.c
+++ b/virt/kvm/arm/psci.c
@@ -155,7 +155,7 @@ static unsigned long kvm_psci_vcpu_on(struct kvm_vcpu *source_vcpu)
 	smp_mb();		/* Make sure the above is visible */
 
 	wq = kvm_arch_vcpu_wq(vcpu);
-	swake_up(wq);
+	swake_up_one(wq);
 
 	return PSCI_RET_SUCCESS;
 }
diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
index 57bcb27dcf30..23c2519c5b32 100644
--- a/virt/kvm/async_pf.c
+++ b/virt/kvm/async_pf.c
@@ -107,7 +107,7 @@ static void async_pf_execute(struct work_struct *work)
 	trace_kvm_async_pf_completed(addr, gva);
 
 	if (swq_has_sleeper(&vcpu->wq))
-		swake_up(&vcpu->wq);
+		swake_up_one(&vcpu->wq);
 
 	mmput(mm);
 	kvm_put_kvm(vcpu->kvm);
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index ada21f47f22b..940a4aed5b2d 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -2167,7 +2167,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu)
 	kvm_arch_vcpu_blocking(vcpu);
 
 	for (;;) {
-		prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+		prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
 
 		if (kvm_vcpu_check_block(vcpu) < 0)
 			break;
@@ -2209,7 +2209,7 @@ bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
 
 	wqp = kvm_arch_vcpu_wq(vcpu);
 	if (swq_has_sleeper(wqp)) {
-		swake_up(wqp);
+		swake_up_one(wqp);
 		++vcpu->stat.halt_wakeup;
 		return true;
 	}
-- 
cgit v1.2.3


From 7f7cca08abf4c6c58ff1037cff5beec5a10a7da3 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Wed, 20 Jun 2018 11:56:21 +0100
Subject: ASoC: wm_adsp: Simplify handling of alg offset and length

The current code that reads the algorithm list from the DSP is
somewhat unclear, it converts directly from bytes to registers using
a hard coded divide by 2. Most offsets are usually handled in DSP
words within the driver and there is a function specifically for
converting from words to register addresses. So update the handling
to use these. This also removes the assumption that the registers
are 16-bit word addressed, which will no longer be true on some of
our newer parts.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 2fcdd84021a5..07c17acc8a4f 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1871,9 +1871,11 @@ static void wm_adsp_ctl_fixup_base(struct wm_adsp *dsp,
 }
 
 static void *wm_adsp_read_algs(struct wm_adsp *dsp, size_t n_algs,
+			       const struct wm_adsp_region *mem,
 			       unsigned int pos, unsigned int len)
 {
 	void *alg;
+	unsigned int reg;
 	int ret;
 	__be32 val;
 
@@ -1888,7 +1890,9 @@ static void *wm_adsp_read_algs(struct wm_adsp *dsp, size_t n_algs,
 	}
 
 	/* Read the terminator first to validate the length */
-	ret = regmap_raw_read(dsp->regmap, pos + len, &val, sizeof(val));
+	reg = wm_adsp_region_to_reg(mem, pos + len);
+
+	ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val));
 	if (ret != 0) {
 		adsp_err(dsp, "Failed to read algorithm list end: %d\n",
 			ret);
@@ -1897,13 +1901,18 @@ static void *wm_adsp_read_algs(struct wm_adsp *dsp, size_t n_algs,
 
 	if (be32_to_cpu(val) != 0xbedead)
 		adsp_warn(dsp, "Algorithm list end %x 0x%x != 0xbedead\n",
-			  pos + len, be32_to_cpu(val));
+			  reg, be32_to_cpu(val));
+
+	/* Convert length from DSP words to bytes */
+	len *= sizeof(u32);
 
 	alg = kcalloc(len, 2, GFP_KERNEL | GFP_DMA);
 	if (!alg)
 		return ERR_PTR(-ENOMEM);
 
-	ret = regmap_raw_read(dsp->regmap, pos, alg, len * 2);
+	reg = wm_adsp_region_to_reg(mem, pos);
+
+	ret = regmap_raw_read(dsp->regmap, reg, alg, len);
 	if (ret != 0) {
 		adsp_err(dsp, "Failed to read algorithm list: %d\n", ret);
 		kfree(alg);
@@ -2002,10 +2011,11 @@ static int wm_adsp1_setup_algs(struct wm_adsp *dsp)
 	if (IS_ERR(alg_region))
 		return PTR_ERR(alg_region);
 
-	pos = sizeof(adsp1_id) / 2;
-	len = (sizeof(*adsp1_alg) * n_algs) / 2;
+	/* Calculate offset and length in DSP words */
+	pos = sizeof(adsp1_id) / sizeof(u32);
+	len = (sizeof(*adsp1_alg) * n_algs) / sizeof(u32);
 
-	adsp1_alg = wm_adsp_read_algs(dsp, n_algs, mem->base + pos, len);
+	adsp1_alg = wm_adsp_read_algs(dsp, n_algs, mem, pos, len);
 	if (IS_ERR(adsp1_alg))
 		return PTR_ERR(adsp1_alg);
 
@@ -2113,10 +2123,11 @@ static int wm_adsp2_setup_algs(struct wm_adsp *dsp)
 	if (IS_ERR(alg_region))
 		return PTR_ERR(alg_region);
 
-	pos = sizeof(adsp2_id) / 2;
-	len = (sizeof(*adsp2_alg) * n_algs) / 2;
+	/* Calculate offset and length in DSP words */
+	pos = sizeof(adsp2_id) / sizeof(u32);
+	len = (sizeof(*adsp2_alg) * n_algs) / sizeof(u32);
 
-	adsp2_alg = wm_adsp_read_algs(dsp, n_algs, mem->base + pos, len);
+	adsp2_alg = wm_adsp_read_algs(dsp, n_algs, mem, pos, len);
 	if (IS_ERR(adsp2_alg))
 		return PTR_ERR(adsp2_alg);
 
-- 
cgit v1.2.3


From 1b31de922e28de2bf2078b7a1e341ad4aee6aa03 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Wed, 20 Jun 2018 11:56:20 +0100
Subject: ASoC: arizona: Set compressed IRQ to a wake source

The current code is not setting the compressed IRQ as a wake
source.  Normally this doesn't cause any issues as the CODEC
IRQ is set as a wake source by the jack detection code and the
CODEC only produces a single IRQ line. However if the system
is not using jack detection the compressed audio IRQ should
still function as a wake source, as such directly set the
compressed audio IRQ as a wake source.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs47l24.c | 8 ++++++++
 sound/soc/codecs/wm5102.c  | 8 ++++++++
 sound/soc/codecs/wm5110.c  | 8 ++++++++
 3 files changed, 24 insertions(+)

diff --git a/sound/soc/codecs/cs47l24.c b/sound/soc/codecs/cs47l24.c
index 196e9c343aeb..0da52ead91e0 100644
--- a/sound/soc/codecs/cs47l24.c
+++ b/sound/soc/codecs/cs47l24.c
@@ -1283,6 +1283,12 @@ static int cs47l24_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 1);
+	if (ret != 0)
+		dev_warn(&pdev->dev,
+			 "Failed to set compressed IRQ as a wake source: %d\n",
+			 ret);
+
 	arizona_init_common(arizona);
 
 	ret = arizona_init_vol_limit(arizona);
@@ -1306,6 +1312,7 @@ static int cs47l24_probe(struct platform_device *pdev)
 err_spk_irqs:
 	arizona_free_spk_irqs(arizona);
 err_dsp_irq:
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, cs47l24);
 
 	return ret;
@@ -1323,6 +1330,7 @@ static int cs47l24_remove(struct platform_device *pdev)
 
 	arizona_free_spk_irqs(arizona);
 
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, cs47l24);
 
 	return 0;
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index 1ac83388d1b8..a01a0c0e01eb 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -2094,6 +2094,12 @@ static int wm5102_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 1);
+	if (ret != 0)
+		dev_warn(&pdev->dev,
+			 "Failed to set compressed IRQ as a wake source: %d\n",
+			 ret);
+
 	arizona_init_common(arizona);
 
 	ret = arizona_init_vol_limit(arizona);
@@ -2117,6 +2123,7 @@ static int wm5102_probe(struct platform_device *pdev)
 err_spk_irqs:
 	arizona_free_spk_irqs(arizona);
 err_dsp_irq:
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5102);
 
 	return ret;
@@ -2133,6 +2140,7 @@ static int wm5102_remove(struct platform_device *pdev)
 
 	arizona_free_spk_irqs(arizona);
 
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5102);
 
 	return 0;
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index fb9835dcd836..00c735c585d9 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -2455,6 +2455,12 @@ static int wm5110_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 1);
+	if (ret != 0)
+		dev_warn(&pdev->dev,
+			 "Failed to set compressed IRQ as a wake source: %d\n",
+			 ret);
+
 	arizona_init_common(arizona);
 
 	ret = arizona_init_vol_limit(arizona);
@@ -2478,6 +2484,7 @@ static int wm5110_probe(struct platform_device *pdev)
 err_spk_irqs:
 	arizona_free_spk_irqs(arizona);
 err_dsp_irq:
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5110);
 
 	return ret;
@@ -2496,6 +2503,7 @@ static int wm5110_remove(struct platform_device *pdev)
 
 	arizona_free_spk_irqs(arizona);
 
+	arizona_set_irq_wake(arizona, ARIZONA_IRQ_DSP_IRQ1, 0);
 	arizona_free_irq(arizona, ARIZONA_IRQ_DSP_IRQ1, wm5110);
 
 	return 0;
-- 
cgit v1.2.3


From f648661bc7de497634c474a38608a715a0af4bbd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 20 Jun 2018 12:24:41 +0100
Subject: drm/i915/selftests: Avoid ERR_PTR dereference

Along the early error path for igt_switch_to_kernel_context we may try
to dereference an invalid error pointer. Instead, return early rather
than dump the GEM trace since we haven't yet emitted anything of
interest.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: 09a4c02e58c1 ("drm/i915: Look for an active kernel context before switching")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180620112441.13085-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_context.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 836f1af8b833..90c3c36173ba 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -519,8 +519,8 @@ static int igt_switch_to_kernel_context(void *arg)
 	mutex_lock(&i915->drm.struct_mutex);
 	ctx = kernel_context(i915);
 	if (IS_ERR(ctx)) {
-		err = PTR_ERR(ctx);
-		goto out_unlock;
+		mutex_unlock(&i915->drm.struct_mutex);
+		return PTR_ERR(ctx);
 	}
 
 	/* First check idling each individual engine */
-- 
cgit v1.2.3


From 9d54fcd5416d84a3ab6a0b58846cff88ce62a4d4 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 5 Apr 2018 17:44:47 +0200
Subject: drm/gem-fb-helper: Always do implicit sync
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I've done a lot of history digging. The first signs of this
optimization was introduced in i915:

commit 25067bfc060d1a481584dcb51ef4b5680176ecb6
Author: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Date:   Wed Sep 10 12:03:17 2014 -0300

    drm/i915: pin sprite fb only if it changed

without much justification. Pinning already pinned stuff is real cheap
(it's just obj->pin_count++ really), and the missing implicit sync was
entirely forgotten about it seems. It's at least not mentioned
anywhere it the commit message.

It was also promptly removed shortly afterwards in

commit ea2c67bb4affa84080c616920f3899f123786e56
Author: Matt Roper <matthew.d.roper@intel.com>
Date:   Tue Dec 23 10:41:52 2014 -0800

    drm/i915: Move to atomic plane helpers (v9)

again without really mentioning the side-effect that plane updates
with the same fb now again obey implicit syncing.

Note that this only ever applied to the plane_update hook, all other
legacy entry points (set_base, page_flip) always obeyed implicit sync
in the drm/i915 driver.

The real source of this code here seems to be msm, copied to vc4, then
copied to tinydrm. I've also tried to dig around in all available msm
sources, but the corresponding check for fb != old_fb is present ever
since the initial merge in

commit cf3a7e4ce08e6876cdcb80390876647f28a7cf8f
Author: Rob Clark <robdclark@gmail.com>
Date:   Sat Nov 8 13:21:06 2014 -0500

    drm/msm: atomic core bits

The only older version I've found of msm atomic code predates the
atomic helpers, and so didn't even use any of this. It also does not
have a corresponding check (because it simply did no implicit sync at
all).

I've chatted with Rob on irc, and he didn't remember the reason for
this either.

Note we had epic amounts of fun with too much syncing against
_vblank_, especially around cursor updates. But I don't ever
discussing a need for less syncing against implicit fences.

Also note that explicit fencing allows you to sidetrack all of this,
at least for all the drivers correctly implemented using
drm_atomic_set_fence_for_plane().

Given that it seems to be an accident of history, and that big drivers
like i915 (and also nouveau it seems, I didn't follow the
amdgpu/radeon sync code to figure this out properly there) never have
done it, let's remove this.

Cc: Rob Clark <robdclark@gmail.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: Gustavo Padovan <gustavo.padovan@collabora.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: David Airlie <airlied@linux.ie>
Cc: "Noralf Trønnes" <noralf@tronnes.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405154449.23038-8-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/drm_gem_framebuffer_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_gem_framebuffer_helper.c b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
index acfbc0641a06..2810d4131411 100644
--- a/drivers/gpu/drm/drm_gem_framebuffer_helper.c
+++ b/drivers/gpu/drm/drm_gem_framebuffer_helper.c
@@ -253,7 +253,7 @@ int drm_gem_fb_prepare_fb(struct drm_plane *plane,
 	struct dma_buf *dma_buf;
 	struct dma_fence *fence;
 
-	if (plane->state->fb == state->fb || !state->fb)
+	if (!state->fb)
 		return 0;
 
 	dma_buf = drm_gem_fb_get_obj(state->fb, 0)->dma_buf;
-- 
cgit v1.2.3


From 2227a7a219fdd2b925b1e861f36255efd149ff6d Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 5 Apr 2018 17:44:48 +0200
Subject: drm/vc4: Always obey implicit sync

Same justification as for drm_gem_fb_prepare_fb.

Cc: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180405154449.23038-9-daniel.vetter@ffwll.ch
Link: https://patchwork.freedesktop.org/patch/msgid/20180409085134.27321-1-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/vc4/vc4_plane.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 2575bd81a010..3922f5f5807d 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -861,18 +861,21 @@ static int vc4_prepare_fb(struct drm_plane *plane,
 	struct dma_fence *fence;
 	int ret;
 
-	if ((plane->state->fb == state->fb) || !state->fb)
+	if (!state->fb)
 		return 0;
 
 	bo = to_vc4_bo(&drm_fb_cma_get_gem_obj(state->fb, 0)->base);
 
+	fence = reservation_object_get_excl_rcu(bo->resv);
+	drm_atomic_set_fence_for_plane(state, fence);
+
+	if (plane->state->fb == state->fb)
+		return 0;
+
 	ret = vc4_bo_inc_usecnt(bo);
 	if (ret)
 		return ret;
 
-	fence = reservation_object_get_excl_rcu(bo->resv);
-	drm_atomic_set_fence_for_plane(state, fence);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From c87bdcc89d867df13fbb92d05323337bfd15d579 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:31 +0200
Subject: spi: spi-fsl-dspi: Drop unreachable else if statement
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The if statement just above this if/else statement triggers on the same
condition, and then invalidates it.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 0630962ce442..3ca9b9608801 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -593,8 +593,7 @@ static int dspi_eoq_write(struct fsl_dspi *dspi)
 			dspi_pushr |= SPI_PUSHR_EOQ;
 			if ((dspi->cs_change) && (!dspi->len))
 				dspi_pushr &= ~SPI_PUSHR_CONT;
-		} else if (tx_word && (dspi->len == 1))
-			dspi_pushr |= SPI_PUSHR_EOQ;
+		}
 
 		regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
 
-- 
cgit v1.2.3


From 4779f23d1ac8694f7acc537fcadb750bff664ea5 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:32 +0200
Subject: spi: spi-fsl-dspi: Drop unneeded use of dataflags bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Checking directly against pointer value should be at least as fast as doing
bitmasking and compare, so let's keep it simple.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 23 ++++++++---------------
 1 file changed, 8 insertions(+), 15 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 3ca9b9608801..3bf135bf8b93 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -38,8 +38,6 @@
 
 #define DRIVER_NAME "fsl-dspi"
 
-#define TRAN_STATE_RX_VOID		0x01
-#define TRAN_STATE_TX_VOID		0x02
 #define TRAN_STATE_WORD_ODD_NUM	0x04
 
 #define DSPI_FIFO_SIZE			4
@@ -232,7 +230,7 @@ static void dspi_rx_dma_callback(void *arg)
 
 	rx_word = is_double_byte_mode(dspi);
 
-	if (!(dspi->dataflags & TRAN_STATE_RX_VOID)) {
+	if (dspi->rx) {
 		for (i = 0; i < dma->curr_xfer_len; i++) {
 			d = dspi->dma->rx_dma_buf[i];
 			rx_word ? (*(u16 *)dspi->rx = d) :
@@ -538,12 +536,13 @@ static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word)
 {
 	u16 d16;
 
-	if (!(dspi->dataflags & TRAN_STATE_TX_VOID))
+	if (dspi->tx) {
 		d16 = tx_word ? *(u16 *)dspi->tx : *(u8 *)dspi->tx;
-	else
+		dspi->tx += tx_word + 1;
+	} else {
 		d16 = dspi->void_write_data;
+	}
 
-	dspi->tx += tx_word + 1;
 	dspi->len -= tx_word + 1;
 
 	return	SPI_PUSHR_TXDATA(d16) |
@@ -560,10 +559,10 @@ static void dspi_data_from_popr(struct fsl_dspi *dspi, int rx_word)
 	regmap_read(dspi->regmap, SPI_POPR, &val);
 	d = SPI_POPR_RXDATA(val);
 
-	if (!(dspi->dataflags & TRAN_STATE_RX_VOID))
+	if (dspi->rx) {
 		rx_word ? (*(u16 *)dspi->rx = d) : (*(u8 *)dspi->rx = d);
-
-	dspi->rx += rx_word + 1;
+		dspi->rx += rx_word + 1;
+	}
 }
 
 static int dspi_eoq_write(struct fsl_dspi *dspi)
@@ -687,12 +686,6 @@ static int dspi_transfer_one_message(struct spi_master *master,
 		dspi->rx_end = dspi->rx + transfer->len;
 		dspi->len = transfer->len;
 
-		if (!dspi->rx)
-			dspi->dataflags |= TRAN_STATE_RX_VOID;
-
-		if (!dspi->tx)
-			dspi->dataflags |= TRAN_STATE_TX_VOID;
-
 		regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val);
 		regmap_update_bits(dspi->regmap, SPI_MCR,
 				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
-- 
cgit v1.2.3


From 9e1dc9bd099363760afdd2316fc057f9ca38b559 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:33 +0200
Subject: spi: spi-fsl-dspi: Fix per transfer cs_change handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As of 92dc20d83adec565378254c0630e839ff5674e14, transfer->cs_change has
been supported for non-last transfers, but not for last transfer.

This change brings handling of cs_change in line with the specification in
spi.h, implementing handling of transfer->cs_change for all transfers.

The value for CMD FIFO is precalculated with transfer->cs_change field
taken into account, allowing for CS de-activate between transfers and
keeping CS activated after last transfer.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 68 +++++++++++++++++++++++++++-------------------
 1 file changed, 40 insertions(+), 28 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 3bf135bf8b93..c0c3b8bf2781 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -84,11 +84,16 @@
 #define SPI_RSER_TCFQE		0x80000000
 
 #define SPI_PUSHR		0x34
-#define SPI_PUSHR_CONT		(1 << 31)
-#define SPI_PUSHR_CTAS(x)	(((x) & 0x00000003) << 28)
-#define SPI_PUSHR_EOQ		(1 << 27)
-#define SPI_PUSHR_CTCNT	(1 << 26)
-#define SPI_PUSHR_PCS(x)	(((1 << x) & 0x0000003f) << 16)
+#define SPI_PUSHR_CMD_CONT	(1 << 15)
+#define SPI_PUSHR_CONT		(SPI_PUSHR_CMD_CONT << 16)
+#define SPI_PUSHR_CMD_CTAS(x)	(((x) & 0x0003) << 12)
+#define SPI_PUSHR_CTAS(x)	(SPI_PUSHR_CMD_CTAS(x) << 16)
+#define SPI_PUSHR_CMD_EOQ	(1 << 11)
+#define SPI_PUSHR_EOQ		(SPI_PUSHR_CMD_EOQ << 16)
+#define SPI_PUSHR_CMD_CTCNT	(1 << 10)
+#define SPI_PUSHR_CTCNT		(SPI_PUSHR_CMD_CTCNT << 16)
+#define SPI_PUSHR_CMD_PCS(x)	((1 << x) & 0x003f)
+#define SPI_PUSHR_PCS(x)	(SPI_PUSHR_CMD_PCS(x) << 16)
 #define SPI_PUSHR_TXDATA(x)	((x) & 0x0000ffff)
 
 #define SPI_PUSHR_SLAVE	0x34
@@ -189,9 +194,8 @@ struct fsl_dspi {
 	void			*rx;
 	void			*rx_end;
 	char			dataflags;
-	u8			cs;
 	u16			void_write_data;
-	u32			cs_change;
+	u16			tx_cmd;
 	const struct fsl_dspi_devtype_data *devtype_data;
 
 	wait_queue_head_t	waitq;
@@ -254,8 +258,6 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 
 	for (i = 0; i < dma->curr_xfer_len; i++) {
 		dspi->dma->tx_dma_buf[i] = dspi_data_to_pushr(dspi, tx_word);
-		if ((dspi->cs_change) && (!dspi->len))
-			dspi->dma->tx_dma_buf[i] &= ~SPI_PUSHR_CONT;
 	}
 
 	dma->tx_desc = dmaengine_prep_slave_single(dma->chan_tx,
@@ -534,21 +536,22 @@ static void ns_delay_scale(char *psc, char *sc, int delay_ns,
 
 static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word)
 {
-	u16 d16;
+	u16 data, cmd;
 
 	if (dspi->tx) {
-		d16 = tx_word ? *(u16 *)dspi->tx : *(u8 *)dspi->tx;
+		data = tx_word ? *(u16 *)dspi->tx : *(u8 *)dspi->tx;
 		dspi->tx += tx_word + 1;
 	} else {
-		d16 = dspi->void_write_data;
+		data = dspi->void_write_data;
 	}
 
 	dspi->len -= tx_word + 1;
 
-	return	SPI_PUSHR_TXDATA(d16) |
-		SPI_PUSHR_PCS(dspi->cs) |
-		SPI_PUSHR_CTAS(0) |
-		SPI_PUSHR_CONT;
+	cmd = dspi->tx_cmd;
+	if (dspi->len > 0)
+		cmd |= SPI_PUSHR_CMD_CONT;
+
+	return (cmd << 16) | SPI_PUSHR_TXDATA(data);
 }
 
 static void dspi_data_from_popr(struct fsl_dspi *dspi, int rx_word)
@@ -587,12 +590,9 @@ static int dspi_eoq_write(struct fsl_dspi *dspi)
 
 		dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
 
-		if (dspi->len == 0 || tx_count == DSPI_FIFO_SIZE - 1) {
-			/* last transfer in the transfer */
+		if (dspi->len == 0 || tx_count == DSPI_FIFO_SIZE - 1)
+			/* request EOQ flag for last transfer in queue */
 			dspi_pushr |= SPI_PUSHR_EOQ;
-			if ((dspi->cs_change) && (!dspi->len))
-				dspi_pushr &= ~SPI_PUSHR_CONT;
-		}
 
 		regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
 
@@ -635,9 +635,6 @@ static int dspi_tcfq_write(struct fsl_dspi *dspi)
 
 	dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
 
-	if ((dspi->cs_change) && (!dspi->len))
-		dspi_pushr &= ~SPI_PUSHR_CONT;
-
 	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
 
 	return tx_word + 1;
@@ -672,11 +669,26 @@ static int dspi_transfer_one_message(struct spi_master *master,
 		dspi->cur_transfer = transfer;
 		dspi->cur_msg = message;
 		dspi->cur_chip = spi_get_ctldata(spi);
-		dspi->cs = spi->chip_select;
-		dspi->cs_change = 0;
+		/* Prepare command word for CMD FIFO */
+		dspi->tx_cmd = SPI_PUSHR_CMD_CTAS(0) |
+			SPI_PUSHR_CMD_PCS(spi->chip_select);
 		if (list_is_last(&dspi->cur_transfer->transfer_list,
-				 &dspi->cur_msg->transfers) || transfer->cs_change)
-			dspi->cs_change = 1;
+				 &dspi->cur_msg->transfers)) {
+			/* Leave PCS activated after last transfer when
+			 * cs_change is set.
+			 */
+			if (transfer->cs_change)
+				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
+		} else {
+			/* Keep PCS active between transfers in same message
+			 * when cs_change is not set, and de-activate PCS
+			 * between transfers in the same message when
+			 * cs_change is set.
+			 */
+			if (!transfer->cs_change)
+				dspi->tx_cmd |= SPI_PUSHR_CMD_CONT;
+		}
+
 		dspi->void_write_data = dspi->cur_chip->void_write_data;
 
 		dspi->dataflags = 0;
-- 
cgit v1.2.3


From 0a4ec2c158634afa208ceda970b2c83764a1d99c Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:34 +0200
Subject: spi: spi-fsl-dspi: Simplify transfer counter handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Simplify driver by avoiding counter wrapping by clearing transfer counter
on first SPI transfer per interrupt instead of tracking what it was before.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 39 ++++++++++++++-------------------------
 1 file changed, 14 insertions(+), 25 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index c0c3b8bf2781..2371b9978e65 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -119,8 +119,6 @@
 #define SPI_CS_ASSERT		0x02
 #define SPI_CS_DROP		0x04
 
-#define SPI_TCR_TCNT_MAX	0x10000
-
 #define DMA_COMPLETION_TIMEOUT	msecs_to_jiffies(3000)
 
 struct chip_data {
@@ -201,7 +199,6 @@ struct fsl_dspi {
 	wait_queue_head_t	waitq;
 	u32			waitflags;
 
-	u32			spi_tcnt;
 	struct fsl_dspi_dma	*dma;
 };
 
@@ -594,6 +591,10 @@ static int dspi_eoq_write(struct fsl_dspi *dspi)
 			/* request EOQ flag for last transfer in queue */
 			dspi_pushr |= SPI_PUSHR_EOQ;
 
+		/* Clear transfer counter on first transfer (in FIFO) */
+		if (tx_count == 0)
+			dspi_pushr |= SPI_PUSHR_CTCNT;
+
 		regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
 
 		tx_count++;
@@ -635,6 +636,9 @@ static int dspi_tcfq_write(struct fsl_dspi *dspi)
 
 	dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
 
+	/* Clear transfer counter on each transfer */
+	dspi_pushr |= SPI_PUSHR_CTCNT;
+
 	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
 
 	return tx_word + 1;
@@ -658,10 +662,6 @@ static int dspi_transfer_one_message(struct spi_master *master,
 	struct spi_transfer *transfer;
 	int status = 0;
 	enum dspi_trans_mode trans_mode;
-	u32 spi_tcr;
-
-	regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
-	dspi->spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
 
 	message->actual_length = 0;
 
@@ -831,7 +831,7 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 	struct spi_message *msg = dspi->cur_msg;
 	enum dspi_trans_mode trans_mode;
 	u32 spi_sr, spi_tcr;
-	u32 spi_tcnt, tcnt_diff;
+	u16 spi_tcnt;
 	int tx_word;
 
 	regmap_read(dspi->regmap, SPI_SR, &spi_sr);
@@ -841,26 +841,15 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 	if (spi_sr & (SPI_SR_EOQF | SPI_SR_TCFQF)) {
 		tx_word = is_double_byte_mode(dspi);
 
+		/* Get transfer counter (in number of SPI transfers). It was
+		 * reset to 0 when transfer(s) were started.
+		 */
 		regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
 		spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
-		/*
-		 * The width of SPI Transfer Counter in SPI_TCR is 16bits,
-		 * so the max couner is 65535. When the counter reach 65535,
-		 * it will wrap around, counter reset to zero.
-		 * spi_tcnt my be less than dspi->spi_tcnt, it means the
-		 * counter already wrapped around.
-		 * SPI Transfer Counter is a counter of transmitted frames.
-		 * The size of frame maybe two bytes.
-		 */
-		tcnt_diff = ((spi_tcnt + SPI_TCR_TCNT_MAX) - dspi->spi_tcnt)
-			% SPI_TCR_TCNT_MAX;
-		tcnt_diff *= (tx_word + 1);
-		if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM)
-			tcnt_diff--;
-
-		msg->actual_length += tcnt_diff;
 
-		dspi->spi_tcnt = spi_tcnt;
+		/* Update total number of bytes that were transferred */
+		msg->actual_length += spi_tcnt * (tx_word + 1) -
+			(dspi->dataflags & TRAN_STATE_WORD_ODD_NUM ? 1 : 0);
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
-- 
cgit v1.2.3


From dadcf4abd60ba6401b592c329a19719a6e1dd444 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:35 +0200
Subject: spi: spi-fsl-dspi: Support 4 to 16 bits per word transfers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This extends the driver with support for all SPI framesizes from 4 to 16
bits, and adds support for per transfer specific bits_per_word, while at
the same time reducing code size and complexity.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 251 ++++++++++++++++-----------------------------
 1 file changed, 88 insertions(+), 163 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 2371b9978e65..df07dd4722fb 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -38,8 +38,6 @@
 
 #define DRIVER_NAME "fsl-dspi"
 
-#define TRAN_STATE_WORD_ODD_NUM	0x04
-
 #define DSPI_FIFO_SIZE			4
 #define DSPI_DMA_BUFSIZE		(DSPI_FIFO_SIZE * 1024)
 
@@ -187,13 +185,13 @@ struct fsl_dspi {
 	struct spi_message	*cur_msg;
 	struct chip_data	*cur_chip;
 	size_t			len;
-	void			*tx;
-	void			*tx_end;
+	const void		*tx;
 	void			*rx;
 	void			*rx_end;
-	char			dataflags;
 	u16			void_write_data;
 	u16			tx_cmd;
+	u8			bits_per_word;
+	u8			bytes_per_word;
 	const struct fsl_dspi_devtype_data *devtype_data;
 
 	wait_queue_head_t	waitq;
@@ -202,15 +200,43 @@ struct fsl_dspi {
 	struct fsl_dspi_dma	*dma;
 };
 
-static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word);
+static u16 dspi_pop_tx(struct fsl_dspi *dspi)
+{
+	u16 txdata = 0;
+
+	if (dspi->tx) {
+		if (dspi->bytes_per_word == 1)
+			txdata = *(u8 *)dspi->tx;
+		else /* dspi->bytes_per_word == 2 */
+			txdata = *(u16 *)dspi->tx;
+		dspi->tx += dspi->bytes_per_word;
+	}
+	dspi->len -= dspi->bytes_per_word;
+	return txdata;
+}
 
-static inline int is_double_byte_mode(struct fsl_dspi *dspi)
+static u32 dspi_pop_tx_pushr(struct fsl_dspi *dspi)
 {
-	unsigned int val;
+	u16 cmd = dspi->tx_cmd, data = dspi_pop_tx(dspi);
 
-	regmap_read(dspi->regmap, SPI_CTAR(0), &val);
+	if (dspi->len > 0)
+		cmd |= SPI_PUSHR_CMD_CONT;
+	return cmd << 16 | data;
+}
+
+static void dspi_push_rx(struct fsl_dspi *dspi, u32 rxdata)
+{
+	if (!dspi->rx)
+		return;
+
+	/* Mask of undefined bits */
+	rxdata &= (1 << dspi->bits_per_word) - 1;
 
-	return ((val & SPI_FRAME_BITS_MASK) == SPI_FRAME_BITS(8)) ? 0 : 1;
+	if (dspi->bytes_per_word == 1)
+		*(u8 *)dspi->rx = rxdata;
+	else /* dspi->bytes_per_word == 2 */
+		*(u16 *)dspi->rx = rxdata;
+	dspi->rx += dspi->bytes_per_word;
 }
 
 static void dspi_tx_dma_callback(void *arg)
@@ -225,19 +251,11 @@ static void dspi_rx_dma_callback(void *arg)
 {
 	struct fsl_dspi *dspi = arg;
 	struct fsl_dspi_dma *dma = dspi->dma;
-	int rx_word;
 	int i;
-	u16 d;
-
-	rx_word = is_double_byte_mode(dspi);
 
 	if (dspi->rx) {
-		for (i = 0; i < dma->curr_xfer_len; i++) {
-			d = dspi->dma->rx_dma_buf[i];
-			rx_word ? (*(u16 *)dspi->rx = d) :
-						(*(u8 *)dspi->rx = d);
-			dspi->rx += rx_word + 1;
-		}
+		for (i = 0; i < dma->curr_xfer_len; i++)
+			dspi_push_rx(dspi, dspi->dma->rx_dma_buf[i]);
 	}
 
 	complete(&dma->cmd_rx_complete);
@@ -248,14 +266,10 @@ static int dspi_next_xfer_dma_submit(struct fsl_dspi *dspi)
 	struct fsl_dspi_dma *dma = dspi->dma;
 	struct device *dev = &dspi->pdev->dev;
 	int time_left;
-	int tx_word;
 	int i;
 
-	tx_word = is_double_byte_mode(dspi);
-
-	for (i = 0; i < dma->curr_xfer_len; i++) {
-		dspi->dma->tx_dma_buf[i] = dspi_data_to_pushr(dspi, tx_word);
-	}
+	for (i = 0; i < dma->curr_xfer_len; i++)
+		dspi->dma->tx_dma_buf[i] = dspi_pop_tx_pushr(dspi);
 
 	dma->tx_desc = dmaengine_prep_slave_single(dma->chan_tx,
 					dma->tx_dma_phys,
@@ -326,16 +340,14 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 	struct device *dev = &dspi->pdev->dev;
 	int curr_remaining_bytes;
 	int bytes_per_buffer;
-	int word = 1;
 	int ret = 0;
 
-	if (is_double_byte_mode(dspi))
-		word = 2;
 	curr_remaining_bytes = dspi->len;
 	bytes_per_buffer = DSPI_DMA_BUFSIZE / DSPI_FIFO_SIZE;
 	while (curr_remaining_bytes) {
 		/* Check if current transfer fits the DMA buffer */
-		dma->curr_xfer_len = curr_remaining_bytes / word;
+		dma->curr_xfer_len = curr_remaining_bytes
+			/ dspi->bytes_per_word;
 		if (dma->curr_xfer_len > bytes_per_buffer)
 			dma->curr_xfer_len = bytes_per_buffer;
 
@@ -345,7 +357,8 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 			goto exit;
 
 		} else {
-			curr_remaining_bytes -= dma->curr_xfer_len * word;
+			curr_remaining_bytes -= dma->curr_xfer_len
+				* dspi->bytes_per_word;
 			if (curr_remaining_bytes < 0)
 				curr_remaining_bytes = 0;
 		}
@@ -531,127 +544,56 @@ static void ns_delay_scale(char *psc, char *sc, int delay_ns,
 	}
 }
 
-static u32 dspi_data_to_pushr(struct fsl_dspi *dspi, int tx_word)
+static void fifo_write(struct fsl_dspi *dspi)
 {
-	u16 data, cmd;
-
-	if (dspi->tx) {
-		data = tx_word ? *(u16 *)dspi->tx : *(u8 *)dspi->tx;
-		dspi->tx += tx_word + 1;
-	} else {
-		data = dspi->void_write_data;
-	}
-
-	dspi->len -= tx_word + 1;
-
-	cmd = dspi->tx_cmd;
-	if (dspi->len > 0)
-		cmd |= SPI_PUSHR_CMD_CONT;
-
-	return (cmd << 16) | SPI_PUSHR_TXDATA(data);
+	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pop_tx_pushr(dspi));
 }
 
-static void dspi_data_from_popr(struct fsl_dspi *dspi, int rx_word)
+static void dspi_tcfq_write(struct fsl_dspi *dspi)
 {
-	u16 d;
-	unsigned int val;
-
-	regmap_read(dspi->regmap, SPI_POPR, &val);
-	d = SPI_POPR_RXDATA(val);
-
-	if (dspi->rx) {
-		rx_word ? (*(u16 *)dspi->rx = d) : (*(u8 *)dspi->rx = d);
-		dspi->rx += rx_word + 1;
-	}
+	/* Clear transfer count */
+	dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
+	/* Write one entry to both TX FIFO and CMD FIFO simultaneously */
+	fifo_write(dspi);
 }
 
-static int dspi_eoq_write(struct fsl_dspi *dspi)
+static u32 fifo_read(struct fsl_dspi *dspi)
 {
-	int tx_count = 0;
-	int tx_word;
-	u32 dspi_pushr = 0;
-
-	tx_word = is_double_byte_mode(dspi);
+	u32 rxdata = 0;
 
-	while (dspi->len && (tx_count < DSPI_FIFO_SIZE)) {
-		/* If we are in word mode, only have a single byte to transfer
-		 * switch to byte mode temporarily.  Will switch back at the
-		 * end of the transfer.
-		 */
-		if (tx_word && (dspi->len == 1)) {
-			dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM;
-			regmap_update_bits(dspi->regmap, SPI_CTAR(0),
-					SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8));
-			tx_word = 0;
-		}
-
-		dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
-
-		if (dspi->len == 0 || tx_count == DSPI_FIFO_SIZE - 1)
-			/* request EOQ flag for last transfer in queue */
-			dspi_pushr |= SPI_PUSHR_EOQ;
-
-		/* Clear transfer counter on first transfer (in FIFO) */
-		if (tx_count == 0)
-			dspi_pushr |= SPI_PUSHR_CTCNT;
-
-		regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
-
-		tx_count++;
-	}
-
-	return tx_count * (tx_word + 1);
+	regmap_read(dspi->regmap, SPI_POPR, &rxdata);
+	return rxdata;
 }
 
-static int dspi_eoq_read(struct fsl_dspi *dspi)
+static void dspi_tcfq_read(struct fsl_dspi *dspi)
 {
-	int rx_count = 0;
-	int rx_word = is_double_byte_mode(dspi);
-
-	while ((dspi->rx < dspi->rx_end)
-			&& (rx_count < DSPI_FIFO_SIZE)) {
-		if (rx_word && (dspi->rx_end - dspi->rx) == 1)
-			rx_word = 0;
-
-		dspi_data_from_popr(dspi, rx_word);
-		rx_count++;
-	}
-
-	return rx_count;
+	dspi_push_rx(dspi, fifo_read(dspi));
 }
 
-static int dspi_tcfq_write(struct fsl_dspi *dspi)
+static void dspi_eoq_write(struct fsl_dspi *dspi)
 {
-	int tx_word;
-	u32 dspi_pushr = 0;
-
-	tx_word = is_double_byte_mode(dspi);
-
-	if (tx_word && (dspi->len == 1)) {
-		dspi->dataflags |= TRAN_STATE_WORD_ODD_NUM;
-		regmap_update_bits(dspi->regmap, SPI_CTAR(0),
-				SPI_FRAME_BITS_MASK, SPI_FRAME_BITS(8));
-		tx_word = 0;
+	int fifo_size = DSPI_FIFO_SIZE;
+
+	/* Fill TX FIFO with as many transfers as possible */
+	while (dspi->len && fifo_size--) {
+		/* Request EOQF for last transfer in FIFO */
+		if (dspi->len == dspi->bytes_per_word || fifo_size == 0)
+			dspi->tx_cmd |= SPI_PUSHR_CMD_EOQ;
+		/* Clear transfer count for first transfer in FIFO */
+		if (fifo_size == (DSPI_FIFO_SIZE - 1))
+			dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
+		/* Write combined TX FIFO and CMD FIFO entry */
+		fifo_write(dspi);
 	}
-
-	dspi_pushr = dspi_data_to_pushr(dspi, tx_word);
-
-	/* Clear transfer counter on each transfer */
-	dspi_pushr |= SPI_PUSHR_CTCNT;
-
-	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pushr);
-
-	return tx_word + 1;
 }
 
-static void dspi_tcfq_read(struct fsl_dspi *dspi)
+static void dspi_eoq_read(struct fsl_dspi *dspi)
 {
-	int rx_word = is_double_byte_mode(dspi);
-
-	if (rx_word && (dspi->rx_end - dspi->rx) == 1)
-		rx_word = 0;
+	int fifo_size = DSPI_FIFO_SIZE;
 
-	dspi_data_from_popr(dspi, rx_word);
+	/* Read one FIFO entry at and push to rx buffer */
+	while ((dspi->rx < dspi->rx_end) && fifo_size--)
+		dspi_push_rx(dspi, fifo_read(dspi));
 }
 
 static int dspi_transfer_one_message(struct spi_master *master,
@@ -691,19 +633,24 @@ static int dspi_transfer_one_message(struct spi_master *master,
 
 		dspi->void_write_data = dspi->cur_chip->void_write_data;
 
-		dspi->dataflags = 0;
-		dspi->tx = (void *)transfer->tx_buf;
-		dspi->tx_end = dspi->tx + transfer->len;
+		dspi->tx = transfer->tx_buf;
 		dspi->rx = transfer->rx_buf;
 		dspi->rx_end = dspi->rx + transfer->len;
 		dspi->len = transfer->len;
+		/* Validated transfer specific frame size (defaults applied) */
+		dspi->bits_per_word = transfer->bits_per_word;
+		if (transfer->bits_per_word <= 8)
+			dspi->bytes_per_word = 1;
+		else
+			dspi->bytes_per_word = 2;
 
 		regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val);
 		regmap_update_bits(dspi->regmap, SPI_MCR,
 				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
 				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
 		regmap_write(dspi->regmap, SPI_CTAR(0),
-				dspi->cur_chip->ctar_val);
+			     dspi->cur_chip->ctar_val |
+			     SPI_FRAME_BITS(transfer->bits_per_word));
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
@@ -754,16 +701,9 @@ static int dspi_setup(struct spi_device *spi)
 	struct fsl_dspi_platform_data *pdata;
 	u32 cs_sck_delay = 0, sck_cs_delay = 0;
 	unsigned char br = 0, pbr = 0, pcssck = 0, cssck = 0;
-	unsigned char pasc = 0, asc = 0, fmsz = 0;
+	unsigned char pasc = 0, asc = 0;
 	unsigned long clkrate;
 
-	if ((spi->bits_per_word >= 4) && (spi->bits_per_word <= 16)) {
-		fmsz = spi->bits_per_word - 1;
-	} else {
-		pr_err("Invalid wordsize\n");
-		return -ENODEV;
-	}
-
 	/* Only alloc on first setup */
 	chip = spi_get_ctldata(spi);
 	if (chip == NULL) {
@@ -799,8 +739,7 @@ static int dspi_setup(struct spi_device *spi)
 	/* Set After SCK delay scale values */
 	ns_delay_scale(&pasc, &asc, sck_cs_delay, clkrate);
 
-	chip->ctar_val =  SPI_CTAR_FMSZ(fmsz)
-		| SPI_CTAR_CPOL(spi->mode & SPI_CPOL ? 1 : 0)
+	chip->ctar_val = SPI_CTAR_CPOL(spi->mode & SPI_CPOL ? 1 : 0)
 		| SPI_CTAR_CPHA(spi->mode & SPI_CPHA ? 1 : 0)
 		| SPI_CTAR_LSBFE(spi->mode & SPI_LSB_FIRST ? 1 : 0)
 		| SPI_CTAR_PCSSCK(pcssck)
@@ -832,24 +771,19 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 	enum dspi_trans_mode trans_mode;
 	u32 spi_sr, spi_tcr;
 	u16 spi_tcnt;
-	int tx_word;
 
 	regmap_read(dspi->regmap, SPI_SR, &spi_sr);
 	regmap_write(dspi->regmap, SPI_SR, spi_sr);
 
 
 	if (spi_sr & (SPI_SR_EOQF | SPI_SR_TCFQF)) {
-		tx_word = is_double_byte_mode(dspi);
-
 		/* Get transfer counter (in number of SPI transfers). It was
 		 * reset to 0 when transfer(s) were started.
 		 */
 		regmap_read(dspi->regmap, SPI_TCR, &spi_tcr);
 		spi_tcnt = SPI_TCR_GET_TCNT(spi_tcr);
-
 		/* Update total number of bytes that were transferred */
-		msg->actual_length += spi_tcnt * (tx_word + 1) -
-			(dspi->dataflags & TRAN_STATE_WORD_ODD_NUM ? 1 : 0);
+		msg->actual_length += spi_tcnt * dspi->bytes_per_word;
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
@@ -866,14 +800,6 @@ static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 		}
 
 		if (!dspi->len) {
-			if (dspi->dataflags & TRAN_STATE_WORD_ODD_NUM) {
-				regmap_update_bits(dspi->regmap,
-						   SPI_CTAR(0),
-						   SPI_FRAME_BITS_MASK,
-						   SPI_FRAME_BITS(16));
-				dspi->dataflags &= ~TRAN_STATE_WORD_ODD_NUM;
-			}
-
 			dspi->waitflags = 1;
 			wake_up_interruptible(&dspi->waitq);
 		} else {
@@ -973,8 +899,7 @@ static int dspi_probe(struct platform_device *pdev)
 
 	master->cleanup = dspi_cleanup;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
-	master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) |
-					SPI_BPW_MASK(16);
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
 
 	pdata = dev_get_platdata(&pdev->dev);
 	if (pdata) {
-- 
cgit v1.2.3


From d87e08f1421373f010308b1d065a1f0c3b251a52 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:37 +0200
Subject: spi: spi-fsl-dspi: Fix MCR register handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The MCR register is not changed, so initialize it in dspi_init().

The exception is the CLR_TXF and CLR_RXF bits, which should be written to
before each transfer to make sure we start with empty FIFOs.  With MCR
register now configured as volatile, the regmap_update_bits will do a real
read-modify-write cycle.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index df07dd4722fb..39b3c6f4f5c3 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -120,7 +120,6 @@
 #define DMA_COMPLETION_TIMEOUT	msecs_to_jiffies(3000)
 
 struct chip_data {
-	u32 mcr_val;
 	u32 ctar_val;
 	u16 void_write_data;
 };
@@ -644,10 +643,9 @@ static int dspi_transfer_one_message(struct spi_master *master,
 		else
 			dspi->bytes_per_word = 2;
 
-		regmap_write(dspi->regmap, SPI_MCR, dspi->cur_chip->mcr_val);
 		regmap_update_bits(dspi->regmap, SPI_MCR,
-				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
-				SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
+				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
+				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF);
 		regmap_write(dspi->regmap, SPI_CTAR(0),
 			     dspi->cur_chip->ctar_val |
 			     SPI_FRAME_BITS(transfer->bits_per_word));
@@ -725,9 +723,6 @@ static int dspi_setup(struct spi_device *spi)
 		sck_cs_delay = pdata->sck_cs_delay;
 	}
 
-	chip->mcr_val = SPI_MCR_MASTER | SPI_MCR_PCSIS |
-		SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF;
-
 	chip->void_write_data = 0;
 
 	clkrate = clk_get_rate(dspi->clk);
@@ -871,6 +866,7 @@ static const struct regmap_config dspi_regmap_config = {
 
 static void dspi_init(struct fsl_dspi *dspi)
 {
+	regmap_write(dspi->regmap, SPI_MCR, SPI_MCR_MASTER | SPI_MCR_PCSIS);
 	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
 }
 
-- 
cgit v1.2.3


From 8570043e2cc659f375336fb8141917ca1b050234 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:36 +0200
Subject: spi: spi-fsl-dspi: Fixup regmap configuration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Mark volatile registers to avoid caching bugs.

Note: SPI_MCR is marked volatile because of CLR_TXF and CLR_RXF bits.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 0630962ce442..1c1070114246 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -943,11 +943,23 @@ static int dspi_resume(struct device *dev)
 
 static SIMPLE_DEV_PM_OPS(dspi_pm, dspi_suspend, dspi_resume);
 
+static const struct regmap_range dspi_volatile_ranges[] = {
+	regmap_reg_range(SPI_MCR, SPI_TCR),
+	regmap_reg_range(SPI_SR, SPI_SR),
+	regmap_reg_range(SPI_PUSHR, SPI_RXFR3),
+};
+
+static const struct regmap_access_table dspi_volatile_table = {
+	.yes_ranges     = dspi_volatile_ranges,
+	.n_yes_ranges   = ARRAY_SIZE(dspi_volatile_ranges),
+};
+
 static const struct regmap_config dspi_regmap_config = {
 	.reg_bits = 32,
 	.val_bits = 32,
 	.reg_stride = 4,
 	.max_register = 0x88,
+	.volatile_table = &dspi_volatile_table,
 };
 
 static void dspi_init(struct fsl_dspi *dspi)
-- 
cgit v1.2.3


From 58ba07ec79e62054dd2b2f1cea082a542aa01c44 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:38 +0200
Subject: spi: spi-fsl-dspi: Add support for XSPI mode registers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This prepares for adding support for extended SPI mode (XSPI), by extending
the regmap with the extra SREX and CTAREx registers.

An additional register map is made for allowing 16 bit access to CMD and TX
FIFO of the PUSHR register separately, which is also needed for XSPI mode
support.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 63 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 61 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index d83d3496d538..3e9dd645ee54 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -108,11 +108,21 @@
 #define SPI_RXFR2		0x84
 #define SPI_RXFR3		0x88
 
+#define SPI_CTARE(x)		(0x11c + (((x) & 0x3) * 4))
+#define SPI_CTARE_FMSZE(x)	(((x) & 0x1) << 16)
+#define SPI_CTARE_DTCP(x)	((x) & 0x7ff)
+
+#define SPI_SREX		0x13c
+
 #define SPI_FRAME_BITS(bits)	SPI_CTAR_FMSZ((bits) - 1)
 #define SPI_FRAME_BITS_MASK	SPI_CTAR_FMSZ(0xf)
 #define SPI_FRAME_BITS_16	SPI_CTAR_FMSZ(0xf)
 #define SPI_FRAME_BITS_8	SPI_CTAR_FMSZ(0x7)
 
+/* Register offsets for regmap_pushr */
+#define PUSHR_CMD		0x0
+#define PUSHR_TX		0x2
+
 #define SPI_CS_INIT		0x01
 #define SPI_CS_ASSERT		0x02
 #define SPI_CS_DROP		0x04
@@ -133,6 +143,7 @@ enum dspi_trans_mode {
 struct fsl_dspi_devtype_data {
 	enum dspi_trans_mode trans_mode;
 	u8 max_clock_factor;
+	bool xspi_mode;
 };
 
 static const struct fsl_dspi_devtype_data vf610_data = {
@@ -143,6 +154,7 @@ static const struct fsl_dspi_devtype_data vf610_data = {
 static const struct fsl_dspi_devtype_data ls1021a_v1_data = {
 	.trans_mode = DSPI_TCFQ_MODE,
 	.max_clock_factor = 8,
+	.xspi_mode = true,
 };
 
 static const struct fsl_dspi_devtype_data ls2085a_data = {
@@ -177,6 +189,7 @@ struct fsl_dspi {
 	struct platform_device	*pdev;
 
 	struct regmap		*regmap;
+	struct regmap		*regmap_pushr;
 	int			irq;
 	struct clk		*clk;
 
@@ -876,6 +889,35 @@ static const struct regmap_config dspi_regmap_config = {
 	.volatile_table = &dspi_volatile_table,
 };
 
+static const struct regmap_range dspi_xspi_volatile_ranges[] = {
+	regmap_reg_range(SPI_MCR, SPI_TCR),
+	regmap_reg_range(SPI_SR, SPI_SR),
+	regmap_reg_range(SPI_PUSHR, SPI_RXFR3),
+	regmap_reg_range(SPI_SREX, SPI_SREX),
+};
+
+static const struct regmap_access_table dspi_xspi_volatile_table = {
+	.yes_ranges     = dspi_xspi_volatile_ranges,
+	.n_yes_ranges   = ARRAY_SIZE(dspi_xspi_volatile_ranges),
+};
+
+static const struct regmap_config dspi_xspi_regmap_config[] = {
+	{
+		.reg_bits = 32,
+		.val_bits = 32,
+		.reg_stride = 4,
+		.max_register = 0x13c,
+		.volatile_table = &dspi_xspi_volatile_table,
+	},
+	{
+		.name = "pushr",
+		.reg_bits = 16,
+		.val_bits = 16,
+		.reg_stride = 2,
+		.max_register = 0x2,
+	},
+};
+
 static void dspi_init(struct fsl_dspi *dspi)
 {
 	regmap_write(dspi->regmap, SPI_MCR, SPI_MCR_MASTER | SPI_MCR_PCSIS);
@@ -888,6 +930,7 @@ static int dspi_probe(struct platform_device *pdev)
 	struct spi_master *master;
 	struct fsl_dspi *dspi;
 	struct resource *res;
+	const struct regmap_config *regmap_config;
 	void __iomem *base;
 	struct fsl_dspi_platform_data *pdata;
 	int ret = 0, cs_num, bus_num;
@@ -946,8 +989,11 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_master_put;
 	}
 
-	dspi->regmap = devm_regmap_init_mmio_clk(&pdev->dev, NULL, base,
-						&dspi_regmap_config);
+	if (dspi->devtype_data->xspi_mode)
+		regmap_config = &dspi_xspi_regmap_config[0];
+	else
+		regmap_config = &dspi_regmap_config;
+	dspi->regmap = devm_regmap_init_mmio(&pdev->dev, base, regmap_config);
 	if (IS_ERR(dspi->regmap)) {
 		dev_err(&pdev->dev, "failed to init regmap: %ld\n",
 				PTR_ERR(dspi->regmap));
@@ -955,6 +1001,19 @@ static int dspi_probe(struct platform_device *pdev)
 		goto out_master_put;
 	}
 
+	if (dspi->devtype_data->xspi_mode) {
+		dspi->regmap_pushr = devm_regmap_init_mmio(
+			&pdev->dev, base + SPI_PUSHR,
+			&dspi_xspi_regmap_config[1]);
+		if (IS_ERR(dspi->regmap_pushr)) {
+			dev_err(&pdev->dev,
+				"failed to init pushr regmap: %ld\n",
+				PTR_ERR(dspi->regmap_pushr));
+			ret = PTR_ERR(dspi->regmap);
+			goto out_master_put;
+		}
+	}
+
 	dspi_init(dspi);
 	dspi->irq = platform_get_irq(pdev, 0);
 	if (dspi->irq < 0) {
-- 
cgit v1.2.3


From 51d583ae7792cb11e952124cedc0e06e7b55d031 Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:39 +0200
Subject: spi: spi-fsl-dspi: Framesize control for XSPI mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 3e9dd645ee54..ba83ff4512c9 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -119,6 +119,9 @@
 #define SPI_FRAME_BITS_16	SPI_CTAR_FMSZ(0xf)
 #define SPI_FRAME_BITS_8	SPI_CTAR_FMSZ(0x7)
 
+#define SPI_FRAME_EBITS(bits)	SPI_CTARE_FMSZE(((bits) - 1) >> 4)
+#define SPI_FRAME_EBITS_MASK	SPI_CTARE_FMSZE(1)
+
 /* Register offsets for regmap_pushr */
 #define PUSHR_CMD		0x0
 #define PUSHR_TX		0x2
@@ -662,6 +665,10 @@ static int dspi_transfer_one_message(struct spi_master *master,
 		regmap_write(dspi->regmap, SPI_CTAR(0),
 			     dspi->cur_chip->ctar_val |
 			     SPI_FRAME_BITS(transfer->bits_per_word));
+		if (dspi->devtype_data->xspi_mode)
+			regmap_write(dspi->regmap, SPI_CTARE(0),
+				     SPI_FRAME_EBITS(transfer->bits_per_word)
+				     | SPI_CTARE_DTCP(1));
 
 		trans_mode = dspi->devtype_data->trans_mode;
 		switch (trans_mode) {
@@ -922,6 +929,9 @@ static void dspi_init(struct fsl_dspi *dspi)
 {
 	regmap_write(dspi->regmap, SPI_MCR, SPI_MCR_MASTER | SPI_MCR_PCSIS);
 	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
+	if (dspi->devtype_data->xspi_mode)
+		regmap_write(dspi->regmap, SPI_CTARE(0),
+			     SPI_CTARE_FMSZE(0) | SPI_CTARE_DTCP(1));
 }
 
 static int dspi_probe(struct platform_device *pdev)
-- 
cgit v1.2.3


From 8fcd151d2619c46e3435e891379a22985538633c Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:40 +0200
Subject: spi: spi-fsl-dspi: XSPI FIFO handling (in TCFQ mode)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This implements handling of split CMD and TX FIFO queues for XSPI when
running in TCFQ mode.

It should be simple to add it to EOQ mode also.  Currently, EOQ mode is
only used with coldfire.  So if coldfire DSPI supports XSPI, XSPI FIFO
handling should be added to EOQ mode also.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 55 ++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 48 insertions(+), 7 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index ba83ff4512c9..67cd2e901255 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -215,15 +215,17 @@ struct fsl_dspi {
 	struct fsl_dspi_dma	*dma;
 };
 
-static u16 dspi_pop_tx(struct fsl_dspi *dspi)
+static u32 dspi_pop_tx(struct fsl_dspi *dspi)
 {
-	u16 txdata = 0;
+	u32 txdata = 0;
 
 	if (dspi->tx) {
 		if (dspi->bytes_per_word == 1)
 			txdata = *(u8 *)dspi->tx;
-		else /* dspi->bytes_per_word == 2 */
+		else if (dspi->bytes_per_word == 2)
 			txdata = *(u16 *)dspi->tx;
+		else  /* dspi->bytes_per_word == 4 */
+			txdata = *(u32 *)dspi->tx;
 		dspi->tx += dspi->bytes_per_word;
 	}
 	dspi->len -= dspi->bytes_per_word;
@@ -249,8 +251,10 @@ static void dspi_push_rx(struct fsl_dspi *dspi, u32 rxdata)
 
 	if (dspi->bytes_per_word == 1)
 		*(u8 *)dspi->rx = rxdata;
-	else /* dspi->bytes_per_word == 2 */
+	else if (dspi->bytes_per_word == 2)
 		*(u16 *)dspi->rx = rxdata;
+	else /* dspi->bytes_per_word == 4 */
+		*(u32 *)dspi->rx = rxdata;
 	dspi->rx += dspi->bytes_per_word;
 }
 
@@ -564,12 +568,47 @@ static void fifo_write(struct fsl_dspi *dspi)
 	regmap_write(dspi->regmap, SPI_PUSHR, dspi_pop_tx_pushr(dspi));
 }
 
+static void cmd_fifo_write(struct fsl_dspi *dspi)
+{
+	u16 cmd = dspi->tx_cmd;
+
+	if (dspi->len > 0)
+		cmd |= SPI_PUSHR_CMD_CONT;
+	regmap_write(dspi->regmap_pushr, PUSHR_CMD, cmd);
+}
+
+static void tx_fifo_write(struct fsl_dspi *dspi, u16 txdata)
+{
+	regmap_write(dspi->regmap_pushr, PUSHR_TX, txdata);
+}
+
 static void dspi_tcfq_write(struct fsl_dspi *dspi)
 {
 	/* Clear transfer count */
 	dspi->tx_cmd |= SPI_PUSHR_CMD_CTCNT;
-	/* Write one entry to both TX FIFO and CMD FIFO simultaneously */
-	fifo_write(dspi);
+
+	if (dspi->devtype_data->xspi_mode && dspi->bits_per_word > 16) {
+		/* Write two TX FIFO entries first, and then the corresponding
+		 * CMD FIFO entry.
+		 */
+		u32 data = dspi_pop_tx(dspi);
+
+		if (dspi->cur_chip->ctar_val & SPI_CTAR_LSBFE(1)) {
+			/* LSB */
+			tx_fifo_write(dspi, data & 0xFFFF);
+			tx_fifo_write(dspi, data >> 16);
+		} else {
+			/* MSB */
+			tx_fifo_write(dspi, data >> 16);
+			tx_fifo_write(dspi, data & 0xFFFF);
+		}
+		cmd_fifo_write(dspi);
+	} else {
+		/* Write one entry to both TX FIFO and CMD FIFO
+		 * simultaneously.
+		 */
+		fifo_write(dspi);
+	}
 }
 
 static u32 fifo_read(struct fsl_dspi *dspi)
@@ -656,8 +695,10 @@ static int dspi_transfer_one_message(struct spi_master *master,
 		dspi->bits_per_word = transfer->bits_per_word;
 		if (transfer->bits_per_word <= 8)
 			dspi->bytes_per_word = 1;
-		else
+		else if (transfer->bits_per_word <= 16)
 			dspi->bytes_per_word = 2;
+		else
+			dspi->bytes_per_word = 4;
 
 		regmap_update_bits(dspi->regmap, SPI_MCR,
 				   SPI_MCR_CLR_TXF | SPI_MCR_CLR_RXF,
-- 
cgit v1.2.3


From 35c9d461a436101a31d4ece7e5de5f4df6b59a5e Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:41 +0200
Subject: spi: spi-fsl-dspi: Advertise 32 bit for XSPI mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 67cd2e901255..eed55491b2c9 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1001,7 +1001,6 @@ static int dspi_probe(struct platform_device *pdev)
 
 	master->cleanup = dspi_cleanup;
 	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_LSB_FIRST;
-	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
 
 	pdata = dev_get_platdata(&pdev->dev);
 	if (pdata) {
@@ -1033,6 +1032,11 @@ static int dspi_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (dspi->devtype_data->xspi_mode)
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 32);
+	else
+		master->bits_per_word_mask = SPI_BPW_RANGE_MASK(4, 16);
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base)) {
-- 
cgit v1.2.3


From 3e7cc6252dc81100bd2803b3148a1e59b3dfae6a Mon Sep 17 00:00:00 2001
From: Esben Haabendal <eha@deif.com>
Date: Wed, 20 Jun 2018 09:34:42 +0200
Subject: spi: spi-fsl-dspi: Enable extended SPI mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the XSPI bit for devices configured for XSPI mode (currently LS1021A),
and thereby switch to extended SPI mode, allowing for SPI transfers using
from 4 to 32 bits per word instead of 4 to 16 bits per word.

Signed-off-by: Esben Haabendal <eha@deif.com>
Acked-by: Martin Hundebøll <martin@geanix.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index eed55491b2c9..1f85dcdb2203 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -46,6 +46,7 @@
 #define SPI_MCR_PCSIS		(0x3F << 16)
 #define SPI_MCR_CLR_TXF	(1 << 11)
 #define SPI_MCR_CLR_RXF	(1 << 10)
+#define SPI_MCR_XSPI		(1 << 3)
 
 #define SPI_TCR			0x08
 #define SPI_TCR_GET_TCNT(x)	(((x) & 0xffff0000) >> 16)
@@ -968,7 +969,8 @@ static const struct regmap_config dspi_xspi_regmap_config[] = {
 
 static void dspi_init(struct fsl_dspi *dspi)
 {
-	regmap_write(dspi->regmap, SPI_MCR, SPI_MCR_MASTER | SPI_MCR_PCSIS);
+	regmap_write(dspi->regmap, SPI_MCR, SPI_MCR_MASTER | SPI_MCR_PCSIS |
+		     (dspi->devtype_data->xspi_mode ? SPI_MCR_XSPI : 0));
 	regmap_write(dspi->regmap, SPI_SR, SPI_SR_CLEAR);
 	if (dspi->devtype_data->xspi_mode)
 		regmap_write(dspi->regmap, SPI_CTARE(0),
-- 
cgit v1.2.3


From a19741e5e5a9f1f02f8e3c037bde7d73d4bfae9c Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 28 May 2018 11:47:52 +0200
Subject: dma_buf: remove device parameter from attach callback v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The device parameter is completely unused because it is available in the
attachment structure as well.

v2: fix kerneldoc as well

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/226643/
---
 drivers/dma-buf/dma-buf.c                             |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c             |  3 +--
 drivers/gpu/drm/drm_prime.c                           |  3 +--
 drivers/gpu/drm/udl/udl_dmabuf.c                      |  1 -
 drivers/gpu/drm/vmwgfx/vmwgfx_prime.c                 |  1 -
 drivers/media/common/videobuf2/videobuf2-dma-contig.c |  2 +-
 drivers/media/common/videobuf2/videobuf2-dma-sg.c     |  2 +-
 drivers/media/common/videobuf2/videobuf2-vmalloc.c    |  2 +-
 include/drm/drm_prime.h                               |  2 +-
 include/linux/dma-buf.h                               | 13 ++++++-------
 10 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 4c45e31258f0..50771063c617 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -568,7 +568,7 @@ struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 	mutex_lock(&dmabuf->lock);
 
 	if (dmabuf->ops->attach) {
-		ret = dmabuf->ops->attach(dmabuf, dev, attach);
+		ret = dmabuf->ops->attach(dmabuf, attach);
 		if (ret)
 			goto err_attach;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 4b584cb75bf4..bbbb4f9578db 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -127,7 +127,6 @@ error:
 }
 
 static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
-				 struct device *target_dev,
 				 struct dma_buf_attachment *attach)
 {
 	struct drm_gem_object *obj = dma_buf->priv;
@@ -135,7 +134,7 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	long r;
 
-	r = drm_gem_map_attach(dma_buf, target_dev, attach);
+	r = drm_gem_map_attach(dma_buf, attach);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 397b46b33739..0055d919070c 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -186,7 +186,6 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
 /**
  * drm_gem_map_attach - dma_buf attach implementation for GEM
  * @dma_buf: buffer to attach device to
- * @target_dev: not used
  * @attach: buffer attachment data
  *
  * Allocates &drm_prime_attachment and calls &drm_driver.gem_prime_pin for
@@ -195,7 +194,7 @@ static int drm_prime_lookup_buf_handle(struct drm_prime_file_private *prime_fpri
  *
  * Returns 0 on success, negative error code on failure.
  */
-int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev,
+int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach)
 {
 	struct drm_prime_attachment *prime_attach;
diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c
index 0a20695eb120..91ae60309d3e 100644
--- a/drivers/gpu/drm/udl/udl_dmabuf.c
+++ b/drivers/gpu/drm/udl/udl_dmabuf.c
@@ -29,7 +29,6 @@ struct udl_drm_dmabuf_attachment {
 };
 
 static int udl_attach_dma_buf(struct dma_buf *dmabuf,
-			      struct device *dev,
 			      struct dma_buf_attachment *attach)
 {
 	struct udl_drm_dmabuf_attachment *udl_attach;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index 0d42a46521fc..fbffb37ccf42 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -40,7 +40,6 @@
  */
 
 static int vmw_prime_map_attach(struct dma_buf *dma_buf,
-				struct device *target_dev,
 				struct dma_buf_attachment *attach)
 {
 	return -ENOSYS;
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
index f1178f6f434d..12d0072c52c2 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
@@ -222,7 +222,7 @@ struct vb2_dc_attachment {
 	enum dma_data_direction dma_dir;
 };
 
-static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
+static int vb2_dc_dmabuf_ops_attach(struct dma_buf *dbuf,
 	struct dma_buf_attachment *dbuf_attach)
 {
 	struct vb2_dc_attachment *attach;
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index 753ed3138dcc..cf94765e593f 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -371,7 +371,7 @@ struct vb2_dma_sg_attachment {
 	enum dma_data_direction dma_dir;
 };
 
-static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
+static int vb2_dma_sg_dmabuf_ops_attach(struct dma_buf *dbuf,
 	struct dma_buf_attachment *dbuf_attach)
 {
 	struct vb2_dma_sg_attachment *attach;
diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
index 359fb9804d16..cdec023a918d 100644
--- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c
+++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
@@ -209,7 +209,7 @@ struct vb2_vmalloc_attachment {
 	enum dma_data_direction dma_dir;
 };
 
-static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf, struct device *dev,
+static int vb2_vmalloc_dmabuf_ops_attach(struct dma_buf *dbuf,
 	struct dma_buf_attachment *dbuf_attach)
 {
 	struct vb2_vmalloc_attachment *attach;
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index 4d5f5d6cf6a6..ef338151cea8 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -82,7 +82,7 @@ int drm_gem_prime_fd_to_handle(struct drm_device *dev,
 struct dma_buf *drm_gem_dmabuf_export(struct drm_device *dev,
 				      struct dma_buf_export_info *exp_info);
 void drm_gem_dmabuf_release(struct dma_buf *dma_buf);
-int drm_gem_map_attach(struct dma_buf *dma_buf, struct device *target_dev,
+int drm_gem_map_attach(struct dma_buf *dma_buf,
 		       struct dma_buf_attachment *attach);
 void drm_gem_map_detach(struct dma_buf *dma_buf,
 			struct dma_buf_attachment *attach);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 88917fa796e4..c0ad5bf61188 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -55,11 +55,11 @@ struct dma_buf_ops {
 	 * @attach:
 	 *
 	 * This is called from dma_buf_attach() to make sure that a given
-	 * &device can access the provided &dma_buf. Exporters which support
-	 * buffer objects in special locations like VRAM or device-specific
-	 * carveout areas should check whether the buffer could be move to
-	 * system memory (or directly accessed by the provided device), and
-	 * otherwise need to fail the attach operation.
+	 * &dma_buf_attachment.dev can access the provided &dma_buf. Exporters
+	 * which support buffer objects in special locations like VRAM or
+	 * device-specific carveout areas should check whether the buffer could
+	 * be move to system memory (or directly accessed by the provided
+	 * device), and otherwise need to fail the attach operation.
 	 *
 	 * The exporter should also in general check whether the current
 	 * allocation fullfills the DMA constraints of the new device. If this
@@ -77,8 +77,7 @@ struct dma_buf_ops {
 	 * to signal that backing storage is already allocated and incompatible
 	 * with the requirements of requesting device.
 	 */
-	int (*attach)(struct dma_buf *, struct device *,
-		      struct dma_buf_attachment *);
+	int (*attach)(struct dma_buf *, struct dma_buf_attachment *);
 
 	/**
 	 * @detach:
-- 
cgit v1.2.3


From f664a52695429b68afb4e130a0f69cd5fd1fec86 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 28 May 2018 13:34:01 +0200
Subject: dma-buf: remove kmap_atomic interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Neither used nor correctly implemented anywhere. Just completely remove
the interface.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Acked-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/226645/
---
 drivers/dma-buf/dma-buf.c                          | 54 +---------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c          |  2 -
 drivers/gpu/drm/armada/armada_gem.c                |  2 -
 drivers/gpu/drm/drm_prime.c                        | 31 -------------
 drivers/gpu/drm/i915/i915_gem_dmabuf.c             | 11 -----
 drivers/gpu/drm/i915/selftests/mock_dmabuf.c       |  2 -
 drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c          |  2 -
 drivers/gpu/drm/tegra/gem.c                        | 14 ------
 drivers/gpu/drm/udl/udl_dmabuf.c                   | 17 -------
 drivers/gpu/drm/vmwgfx/vmwgfx_prime.c              | 13 ------
 .../media/common/videobuf2/videobuf2-dma-contig.c  |  1 -
 drivers/media/common/videobuf2/videobuf2-dma-sg.c  |  1 -
 drivers/media/common/videobuf2/videobuf2-vmalloc.c |  1 -
 drivers/staging/android/ion/ion.c                  |  2 -
 drivers/tee/tee_shm.c                              |  6 ---
 include/drm/drm_prime.h                            |  4 --
 include/linux/dma-buf.h                            |  4 --
 17 files changed, 2 insertions(+), 165 deletions(-)

diff --git a/drivers/dma-buf/dma-buf.c b/drivers/dma-buf/dma-buf.c
index 50771063c617..13884474d158 100644
--- a/drivers/dma-buf/dma-buf.c
+++ b/drivers/dma-buf/dma-buf.c
@@ -405,7 +405,6 @@ struct dma_buf *dma_buf_export(const struct dma_buf_export_info *exp_info)
 			  || !exp_info->ops->map_dma_buf
 			  || !exp_info->ops->unmap_dma_buf
 			  || !exp_info->ops->release
-			  || !exp_info->ops->map_atomic
 			  || !exp_info->ops->map
 			  || !exp_info->ops->mmap)) {
 		return ERR_PTR(-EINVAL);
@@ -687,26 +686,14 @@ EXPORT_SYMBOL_GPL(dma_buf_unmap_attachment);
  *      void \*dma_buf_kmap(struct dma_buf \*, unsigned long);
  *      void dma_buf_kunmap(struct dma_buf \*, unsigned long, void \*);
  *
- *   There are also atomic variants of these interfaces. Like for kmap they
- *   facilitate non-blocking fast-paths. Neither the importer nor the exporter
- *   (in the callback) is allowed to block when using these.
- *
- *   Interfaces::
- *      void \*dma_buf_kmap_atomic(struct dma_buf \*, unsigned long);
- *      void dma_buf_kunmap_atomic(struct dma_buf \*, unsigned long, void \*);
- *
- *   For importers all the restrictions of using kmap apply, like the limited
- *   supply of kmap_atomic slots. Hence an importer shall only hold onto at
- *   max 2 atomic dma_buf kmaps at the same time (in any given process context).
+ *   Implementing the functions is optional for exporters and for importers all
+ *   the restrictions of using kmap apply.
  *
  *   dma_buf kmap calls outside of the range specified in begin_cpu_access are
  *   undefined. If the range is not PAGE_SIZE aligned, kmap needs to succeed on
  *   the partial chunks at the beginning and end but may return stale or bogus
  *   data outside of the range (in these partial chunks).
  *
- *   Note that these calls need to always succeed. The exporter needs to
- *   complete any preparations that might fail in begin_cpu_access.
- *
  *   For some cases the overhead of kmap can be too high, a vmap interface
  *   is introduced. This interface should be used very carefully, as vmalloc
  *   space is a limited resources on many architectures.
@@ -859,43 +846,6 @@ int dma_buf_end_cpu_access(struct dma_buf *dmabuf,
 }
 EXPORT_SYMBOL_GPL(dma_buf_end_cpu_access);
 
-/**
- * dma_buf_kmap_atomic - Map a page of the buffer object into kernel address
- * space. The same restrictions as for kmap_atomic and friends apply.
- * @dmabuf:	[in]	buffer to map page from.
- * @page_num:	[in]	page in PAGE_SIZE units to map.
- *
- * This call must always succeed, any necessary preparations that might fail
- * need to be done in begin_cpu_access.
- */
-void *dma_buf_kmap_atomic(struct dma_buf *dmabuf, unsigned long page_num)
-{
-	WARN_ON(!dmabuf);
-
-	if (!dmabuf->ops->map_atomic)
-		return NULL;
-	return dmabuf->ops->map_atomic(dmabuf, page_num);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kmap_atomic);
-
-/**
- * dma_buf_kunmap_atomic - Unmap a page obtained by dma_buf_kmap_atomic.
- * @dmabuf:	[in]	buffer to unmap page from.
- * @page_num:	[in]	page in PAGE_SIZE units to unmap.
- * @vaddr:	[in]	kernel space pointer obtained from dma_buf_kmap_atomic.
- *
- * This call must always succeed.
- */
-void dma_buf_kunmap_atomic(struct dma_buf *dmabuf, unsigned long page_num,
-			   void *vaddr)
-{
-	WARN_ON(!dmabuf);
-
-	if (dmabuf->ops->unmap_atomic)
-		dmabuf->ops->unmap_atomic(dmabuf, page_num, vaddr);
-}
-EXPORT_SYMBOL_GPL(dma_buf_kunmap_atomic);
-
 /**
  * dma_buf_kmap - Map a page of the buffer object into kernel address space. The
  * same restrictions as for kmap and friends apply.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index bbbb4f9578db..0558da049827 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -238,9 +238,7 @@ static const struct dma_buf_ops amdgpu_dmabuf_ops = {
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = amdgpu_gem_begin_cpu_access,
 	.map = drm_gem_dmabuf_kmap,
-	.map_atomic = drm_gem_dmabuf_kmap_atomic,
 	.unmap = drm_gem_dmabuf_kunmap,
-	.unmap_atomic = drm_gem_dmabuf_kunmap_atomic,
 	.mmap = drm_gem_dmabuf_mmap,
 	.vmap = drm_gem_dmabuf_vmap,
 	.vunmap = drm_gem_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index a97f509743a5..3fb37c75c065 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -490,8 +490,6 @@ static const struct dma_buf_ops armada_gem_prime_dmabuf_ops = {
 	.map_dma_buf	= armada_gem_prime_map_dma_buf,
 	.unmap_dma_buf	= armada_gem_prime_unmap_dma_buf,
 	.release	= drm_gem_dmabuf_release,
-	.map_atomic	= armada_gem_dmabuf_no_kmap,
-	.unmap_atomic	= armada_gem_dmabuf_no_kunmap,
 	.map		= armada_gem_dmabuf_no_kmap,
 	.unmap		= armada_gem_dmabuf_no_kunmap,
 	.mmap		= armada_gem_dmabuf_mmap,
diff --git a/drivers/gpu/drm/drm_prime.c b/drivers/gpu/drm/drm_prime.c
index 0055d919070c..186db2e4c57a 100644
--- a/drivers/gpu/drm/drm_prime.c
+++ b/drivers/gpu/drm/drm_prime.c
@@ -433,35 +433,6 @@ void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 }
 EXPORT_SYMBOL(drm_gem_dmabuf_vunmap);
 
-/**
- * drm_gem_dmabuf_kmap_atomic - map_atomic implementation for GEM
- * @dma_buf: buffer to be mapped
- * @page_num: page number within the buffer
- *
- * Not implemented. This can be used as the &dma_buf_ops.map_atomic callback.
- */
-void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-				 unsigned long page_num)
-{
-	return NULL;
-}
-EXPORT_SYMBOL(drm_gem_dmabuf_kmap_atomic);
-
-/**
- * drm_gem_dmabuf_kunmap_atomic - unmap_atomic implementation for GEM
- * @dma_buf: buffer to be unmapped
- * @page_num: page number within the buffer
- * @addr: virtual address of the buffer
- *
- * Not implemented. This can be used as the &dma_buf_ops.unmap_atomic callback.
- */
-void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-				  unsigned long page_num, void *addr)
-{
-
-}
-EXPORT_SYMBOL(drm_gem_dmabuf_kunmap_atomic);
-
 /**
  * drm_gem_dmabuf_kmap - map implementation for GEM
  * @dma_buf: buffer to be mapped
@@ -519,9 +490,7 @@ static const struct dma_buf_ops drm_gem_prime_dmabuf_ops =  {
 	.unmap_dma_buf = drm_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
 	.map = drm_gem_dmabuf_kmap,
-	.map_atomic = drm_gem_dmabuf_kmap_atomic,
 	.unmap = drm_gem_dmabuf_kunmap,
-	.unmap_atomic = drm_gem_dmabuf_kunmap_atomic,
 	.mmap = drm_gem_dmabuf_mmap,
 	.vmap = drm_gem_dmabuf_vmap,
 	.vunmap = drm_gem_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
index 69a7aec49e84..82e2ca17a441 100644
--- a/drivers/gpu/drm/i915/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/i915_gem_dmabuf.c
@@ -111,15 +111,6 @@ static void i915_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	i915_gem_object_unpin_map(obj);
 }
 
-static void *i915_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	return NULL;
-}
-
-static void i915_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-
-}
 static void *i915_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
 {
 	struct drm_i915_gem_object *obj = dma_buf_to_obj(dma_buf);
@@ -225,9 +216,7 @@ static const struct dma_buf_ops i915_dmabuf_ops =  {
 	.unmap_dma_buf = i915_gem_unmap_dma_buf,
 	.release = drm_gem_dmabuf_release,
 	.map = i915_gem_dmabuf_kmap,
-	.map_atomic = i915_gem_dmabuf_kmap_atomic,
 	.unmap = i915_gem_dmabuf_kunmap,
-	.unmap_atomic = i915_gem_dmabuf_kunmap_atomic,
 	.mmap = i915_gem_dmabuf_mmap,
 	.vmap = i915_gem_dmabuf_vmap,
 	.vunmap = i915_gem_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
index 302f7d103635..f81fda8ea45e 100644
--- a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
+++ b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
@@ -130,9 +130,7 @@ static const struct dma_buf_ops mock_dmabuf_ops =  {
 	.unmap_dma_buf = mock_unmap_dma_buf,
 	.release = mock_dmabuf_release,
 	.map = mock_dmabuf_kmap,
-	.map_atomic = mock_dmabuf_kmap_atomic,
 	.unmap = mock_dmabuf_kunmap,
-	.unmap_atomic = mock_dmabuf_kunmap_atomic,
 	.mmap = mock_dmabuf_mmap,
 	.vmap = mock_dmabuf_vmap,
 	.vunmap = mock_dmabuf_vunmap,
diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index 8e41d649e248..1a073f9b2834 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -148,8 +148,6 @@ static const struct dma_buf_ops omap_dmabuf_ops = {
 	.release = drm_gem_dmabuf_release,
 	.begin_cpu_access = omap_gem_dmabuf_begin_cpu_access,
 	.end_cpu_access = omap_gem_dmabuf_end_cpu_access,
-	.map_atomic = omap_gem_dmabuf_kmap_atomic,
-	.unmap_atomic = omap_gem_dmabuf_kunmap_atomic,
 	.map = omap_gem_dmabuf_kmap,
 	.unmap = omap_gem_dmabuf_kunmap,
 	.mmap = omap_gem_dmabuf_mmap,
diff --git a/drivers/gpu/drm/tegra/gem.c b/drivers/gpu/drm/tegra/gem.c
index 8b0b4ff64bb4..d7661702c11c 100644
--- a/drivers/gpu/drm/tegra/gem.c
+++ b/drivers/gpu/drm/tegra/gem.c
@@ -596,18 +596,6 @@ static int tegra_gem_prime_end_cpu_access(struct dma_buf *buf,
 	return 0;
 }
 
-static void *tegra_gem_prime_kmap_atomic(struct dma_buf *buf,
-					 unsigned long page)
-{
-	return NULL;
-}
-
-static void tegra_gem_prime_kunmap_atomic(struct dma_buf *buf,
-					  unsigned long page,
-					  void *addr)
-{
-}
-
 static void *tegra_gem_prime_kmap(struct dma_buf *buf, unsigned long page)
 {
 	return NULL;
@@ -648,8 +636,6 @@ static const struct dma_buf_ops tegra_gem_prime_dmabuf_ops = {
 	.release = tegra_gem_prime_release,
 	.begin_cpu_access = tegra_gem_prime_begin_cpu_access,
 	.end_cpu_access = tegra_gem_prime_end_cpu_access,
-	.map_atomic = tegra_gem_prime_kmap_atomic,
-	.unmap_atomic = tegra_gem_prime_kunmap_atomic,
 	.map = tegra_gem_prime_kmap,
 	.unmap = tegra_gem_prime_kunmap,
 	.mmap = tegra_gem_prime_mmap,
diff --git a/drivers/gpu/drm/udl/udl_dmabuf.c b/drivers/gpu/drm/udl/udl_dmabuf.c
index 91ae60309d3e..556f62662aa9 100644
--- a/drivers/gpu/drm/udl/udl_dmabuf.c
+++ b/drivers/gpu/drm/udl/udl_dmabuf.c
@@ -157,27 +157,12 @@ static void *udl_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
 	return NULL;
 }
 
-static void *udl_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-				    unsigned long page_num)
-{
-	/* TODO */
-
-	return NULL;
-}
-
 static void udl_dmabuf_kunmap(struct dma_buf *dma_buf,
 			      unsigned long page_num, void *addr)
 {
 	/* TODO */
 }
 
-static void udl_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-				     unsigned long page_num,
-				     void *addr)
-{
-	/* TODO */
-}
-
 static int udl_dmabuf_mmap(struct dma_buf *dma_buf,
 			   struct vm_area_struct *vma)
 {
@@ -192,9 +177,7 @@ static const struct dma_buf_ops udl_dmabuf_ops = {
 	.map_dma_buf		= udl_map_dma_buf,
 	.unmap_dma_buf		= udl_unmap_dma_buf,
 	.map			= udl_dmabuf_kmap,
-	.map_atomic		= udl_dmabuf_kmap_atomic,
 	.unmap			= udl_dmabuf_kunmap,
-	.unmap_atomic		= udl_dmabuf_kunmap_atomic,
 	.mmap			= udl_dmabuf_mmap,
 	.release		= drm_gem_dmabuf_release,
 };
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index fbffb37ccf42..373bc6da2f84 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -71,17 +71,6 @@ static void vmw_prime_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 {
 }
 
-static void *vmw_prime_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-		unsigned long page_num)
-{
-	return NULL;
-}
-
-static void vmw_prime_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-		unsigned long page_num, void *addr)
-{
-
-}
 static void *vmw_prime_dmabuf_kmap(struct dma_buf *dma_buf,
 		unsigned long page_num)
 {
@@ -108,9 +97,7 @@ const struct dma_buf_ops vmw_prime_dmabuf_ops =  {
 	.unmap_dma_buf = vmw_prime_unmap_dma_buf,
 	.release = NULL,
 	.map = vmw_prime_dmabuf_kmap,
-	.map_atomic = vmw_prime_dmabuf_kmap_atomic,
 	.unmap = vmw_prime_dmabuf_kunmap,
-	.unmap_atomic = vmw_prime_dmabuf_kunmap_atomic,
 	.mmap = vmw_prime_dmabuf_mmap,
 	.vmap = vmw_prime_dmabuf_vmap,
 	.vunmap = vmw_prime_dmabuf_vunmap,
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-contig.c b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
index 12d0072c52c2..aff0ab7bf83d 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-contig.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-contig.c
@@ -358,7 +358,6 @@ static const struct dma_buf_ops vb2_dc_dmabuf_ops = {
 	.map_dma_buf = vb2_dc_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_dc_dmabuf_ops_unmap,
 	.map = vb2_dc_dmabuf_ops_kmap,
-	.map_atomic = vb2_dc_dmabuf_ops_kmap,
 	.vmap = vb2_dc_dmabuf_ops_vmap,
 	.mmap = vb2_dc_dmabuf_ops_mmap,
 	.release = vb2_dc_dmabuf_ops_release,
diff --git a/drivers/media/common/videobuf2/videobuf2-dma-sg.c b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
index cf94765e593f..015e737095cd 100644
--- a/drivers/media/common/videobuf2/videobuf2-dma-sg.c
+++ b/drivers/media/common/videobuf2/videobuf2-dma-sg.c
@@ -507,7 +507,6 @@ static const struct dma_buf_ops vb2_dma_sg_dmabuf_ops = {
 	.map_dma_buf = vb2_dma_sg_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_dma_sg_dmabuf_ops_unmap,
 	.map = vb2_dma_sg_dmabuf_ops_kmap,
-	.map_atomic = vb2_dma_sg_dmabuf_ops_kmap,
 	.vmap = vb2_dma_sg_dmabuf_ops_vmap,
 	.mmap = vb2_dma_sg_dmabuf_ops_mmap,
 	.release = vb2_dma_sg_dmabuf_ops_release,
diff --git a/drivers/media/common/videobuf2/videobuf2-vmalloc.c b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
index cdec023a918d..6dfbd5b05907 100644
--- a/drivers/media/common/videobuf2/videobuf2-vmalloc.c
+++ b/drivers/media/common/videobuf2/videobuf2-vmalloc.c
@@ -346,7 +346,6 @@ static const struct dma_buf_ops vb2_vmalloc_dmabuf_ops = {
 	.map_dma_buf = vb2_vmalloc_dmabuf_ops_map,
 	.unmap_dma_buf = vb2_vmalloc_dmabuf_ops_unmap,
 	.map = vb2_vmalloc_dmabuf_ops_kmap,
-	.map_atomic = vb2_vmalloc_dmabuf_ops_kmap,
 	.vmap = vb2_vmalloc_dmabuf_ops_vmap,
 	.mmap = vb2_vmalloc_dmabuf_ops_mmap,
 	.release = vb2_vmalloc_dmabuf_ops_release,
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index e74db7902549..a5220445b5e8 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -369,8 +369,6 @@ static const struct dma_buf_ops dma_buf_ops = {
 	.detach = ion_dma_buf_detatch,
 	.begin_cpu_access = ion_dma_buf_begin_cpu_access,
 	.end_cpu_access = ion_dma_buf_end_cpu_access,
-	.map_atomic = ion_dma_buf_kmap,
-	.unmap_atomic = ion_dma_buf_kunmap,
 	.map = ion_dma_buf_kmap,
 	.unmap = ion_dma_buf_kunmap,
 };
diff --git a/drivers/tee/tee_shm.c b/drivers/tee/tee_shm.c
index 556960a1bab3..df4a1553b78b 100644
--- a/drivers/tee/tee_shm.c
+++ b/drivers/tee/tee_shm.c
@@ -80,11 +80,6 @@ static void tee_shm_op_release(struct dma_buf *dmabuf)
 	tee_shm_release(shm);
 }
 
-static void *tee_shm_op_map_atomic(struct dma_buf *dmabuf, unsigned long pgnum)
-{
-	return NULL;
-}
-
 static void *tee_shm_op_map(struct dma_buf *dmabuf, unsigned long pgnum)
 {
 	return NULL;
@@ -107,7 +102,6 @@ static const struct dma_buf_ops tee_shm_dma_buf_ops = {
 	.map_dma_buf = tee_shm_op_map_dma_buf,
 	.unmap_dma_buf = tee_shm_op_unmap_dma_buf,
 	.release = tee_shm_op_release,
-	.map_atomic = tee_shm_op_map_atomic,
 	.map = tee_shm_op_map,
 	.mmap = tee_shm_op_mmap,
 };
diff --git a/include/drm/drm_prime.h b/include/drm/drm_prime.h
index ef338151cea8..d716d653b096 100644
--- a/include/drm/drm_prime.h
+++ b/include/drm/drm_prime.h
@@ -93,10 +93,6 @@ void drm_gem_unmap_dma_buf(struct dma_buf_attachment *attach,
 			   enum dma_data_direction dir);
 void *drm_gem_dmabuf_vmap(struct dma_buf *dma_buf);
 void drm_gem_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr);
-void *drm_gem_dmabuf_kmap_atomic(struct dma_buf *dma_buf,
-				 unsigned long page_num);
-void drm_gem_dmabuf_kunmap_atomic(struct dma_buf *dma_buf,
-				  unsigned long page_num, void *addr);
 void *drm_gem_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num);
 void drm_gem_dmabuf_kunmap(struct dma_buf *dma_buf, unsigned long page_num,
 			   void *addr);
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index c0ad5bf61188..58725f890b5b 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -205,8 +205,6 @@ struct dma_buf_ops {
 	 * to be restarted.
 	 */
 	int (*end_cpu_access)(struct dma_buf *, enum dma_data_direction);
-	void *(*map_atomic)(struct dma_buf *, unsigned long);
-	void (*unmap_atomic)(struct dma_buf *, unsigned long, void *);
 	void *(*map)(struct dma_buf *, unsigned long);
 	void (*unmap)(struct dma_buf *, unsigned long, void *);
 
@@ -394,8 +392,6 @@ int dma_buf_begin_cpu_access(struct dma_buf *dma_buf,
 			     enum dma_data_direction dir);
 int dma_buf_end_cpu_access(struct dma_buf *dma_buf,
 			   enum dma_data_direction dir);
-void *dma_buf_kmap_atomic(struct dma_buf *, unsigned long);
-void dma_buf_kunmap_atomic(struct dma_buf *, unsigned long, void *);
 void *dma_buf_kmap(struct dma_buf *, unsigned long);
 void dma_buf_kunmap(struct dma_buf *, unsigned long, void *);
 
-- 
cgit v1.2.3


From 935774cd71fe604cc8ed24adcb507d7784255672 Mon Sep 17 00:00:00 2001
From: Brian Starkey <brian.starkey@arm.com>
Date: Wed, 29 Mar 2017 17:42:32 +0100
Subject: drm: Add writeback connector type

Writeback connectors represent writeback engines which can write the
CRTC output to a memory framebuffer. Add a writeback connector type and
related support functions.

Drivers should initialize a writeback connector with
drm_writeback_connector_init() which takes care of setting up all the
writeback-specific details on top of the normal functionality of
drm_connector_init().

Writeback connectors have a WRITEBACK_FB_ID property, used to set the
output framebuffer, and a WRITEBACK_PIXEL_FORMATS blob used to expose the
supported writeback formats to userspace.

When a framebuffer is attached to a writeback connector with the
WRITEBACK_FB_ID property, it is used only once (for the commit in which
it was included), and userspace can never read back the value of
WRITEBACK_FB_ID. WRITEBACK_FB_ID can only be set if the connector is
attached to a CRTC.

Changes since v1:
 - Added drm_writeback.c + documentation
 - Added helper to initialize writeback connector in one go
 - Added core checks
 - Squashed into a single commit
 - Dropped the client cap
 - Writeback framebuffers are no longer persistent

Changes since v2:
 Daniel Vetter:
 - Subclass drm_connector to drm_writeback_connector
 - Relax check to allow CRTC to be set without an FB
 - Add some writeback_ prefixes
 - Drop PIXEL_FORMATS_SIZE property, as it was unnecessary
 Gustavo Padovan:
 - Add drm_writeback_job to handle writeback signalling centrally

Changes since v3:
 - Rebased
 - Rename PIXEL_FORMATS -> WRITEBACK_PIXEL_FORMATS

Chances since v4:
 - Embed a drm_encoder inside the drm_writeback_connector to
   reduce the amount of boilerplate code required from the drivers
   that are using it.

Changes since v5:
 - Added Rob Clark's atomic_commit() vfunc to connector helper
   funcs, so that writeback jobs are committed from atomic helpers
 - Updated create_writeback_properties() signature to return an
   error code rather than a boolean false for failure.
 - Free writeback job with the connector state rather than when
   doing the cleanup_work()

Changes since v7:
 - fix extraneous use of out_fence that is only introduced in a
   subsequent patch.

Changes since v8:
 - whitespace changes pull from subsequent patch

Changes since v9:
 - Revert the v6 changes that free the writeback job in the connector
   state cleanup and return to doing it in the cleanup_work() function

Signed-off-by: Brian Starkey <brian.starkey@arm.com>
[rebased and fixed conflicts]
Signed-off-by: Mihail Atanassov <mihail.atanassov@arm.com>
[rebased and added atomic_commit() vfunc for writeback jobs]
Signed-off-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/229037/
---
 Documentation/gpu/drm-kms.rst            |   9 ++
 drivers/gpu/drm/Makefile                 |   2 +-
 drivers/gpu/drm/drm_atomic.c             | 124 ++++++++++++++++
 drivers/gpu/drm/drm_atomic_helper.c      |  25 ++++
 drivers/gpu/drm/drm_connector.c          |   4 +-
 drivers/gpu/drm/drm_writeback.c          | 245 +++++++++++++++++++++++++++++++
 include/drm/drm_atomic.h                 |   3 +
 include/drm/drm_connector.h              |  13 ++
 include/drm/drm_mode_config.h            |  15 ++
 include/drm/drm_modeset_helper_vtables.h |  11 ++
 include/drm/drm_writeback.h              |  91 ++++++++++++
 include/uapi/drm/drm_mode.h              |   1 +
 12 files changed, 541 insertions(+), 2 deletions(-)
 create mode 100644 drivers/gpu/drm/drm_writeback.c
 create mode 100644 include/drm/drm_writeback.h

diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index e233c2626bd0..4f6f113a7f5d 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -373,6 +373,15 @@ Connector Functions Reference
 .. kernel-doc:: drivers/gpu/drm/drm_connector.c
    :export:
 
+Writeback Connectors
+--------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_writeback.c
+  :doc: overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_writeback.c
+  :export:
+
 Encoder Abstraction
 ===================
 
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index ef9f3dab287f..69c13517ea3a 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -18,7 +18,7 @@ drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
 		drm_encoder.o drm_mode_object.o drm_property.o \
 		drm_plane.o drm_color_mgmt.o drm_print.o \
 		drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \
-		drm_syncobj.o drm_lease.o
+		drm_syncobj.o drm_lease.o drm_writeback.o
 
 drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
 drm-$(CONFIG_DRM_VM) += drm_vm.o
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 9ec5c865a043..3e53d6e5c340 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -30,6 +30,7 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_mode.h>
 #include <drm/drm_print.h>
+#include <drm/drm_writeback.h>
 #include <linux/sync_file.h>
 
 #include "drm_crtc_internal.h"
@@ -690,6 +691,45 @@ static void drm_atomic_crtc_print_state(struct drm_printer *p,
 		crtc->funcs->atomic_print_state(p, state);
 }
 
+/**
+ * drm_atomic_connector_check - check connector state
+ * @connector: connector to check
+ * @state: connector state to check
+ *
+ * Provides core sanity checks for connector state.
+ *
+ * RETURNS:
+ * Zero on success, error code on failure
+ */
+static int drm_atomic_connector_check(struct drm_connector *connector,
+		struct drm_connector_state *state)
+{
+	struct drm_crtc_state *crtc_state;
+	struct drm_writeback_job *writeback_job = state->writeback_job;
+
+	if ((connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK) || !writeback_job)
+		return 0;
+
+	if (writeback_job->fb && !state->crtc) {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] framebuffer without CRTC\n",
+				 connector->base.id, connector->name);
+		return -EINVAL;
+	}
+
+	if (state->crtc)
+		crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+								state->crtc);
+
+	if (writeback_job->fb && !crtc_state->active) {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] has framebuffer, but [CRTC:%d] is off\n",
+				 connector->base.id, connector->name,
+				 state->crtc->base.id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /**
  * drm_atomic_get_plane_state - get plane state
  * @state: global atomic state object
@@ -1321,6 +1361,12 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 			return -EINVAL;
 		}
 		state->content_protection = val;
+	} else if (property == config->writeback_fb_id_property) {
+		struct drm_framebuffer *fb = drm_framebuffer_lookup(dev, NULL, val);
+		int ret = drm_atomic_set_writeback_fb_for_connector(state, fb);
+		if (fb)
+			drm_framebuffer_put(fb);
+		return ret;
 	} else if (connector->funcs->atomic_set_property) {
 		return connector->funcs->atomic_set_property(connector,
 				state, property, val);
@@ -1407,6 +1453,9 @@ drm_atomic_connector_get_property(struct drm_connector *connector,
 		*val = state->scaling_mode;
 	} else if (property == connector->content_protection_property) {
 		*val = state->content_protection;
+	} else if (property == config->writeback_fb_id_property) {
+		/* Writeback framebuffer is one-shot, write and forget */
+		*val = 0;
 	} else if (connector->funcs->atomic_get_property) {
 		return connector->funcs->atomic_get_property(connector,
 				state, property, val);
@@ -1631,6 +1680,70 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 }
 EXPORT_SYMBOL(drm_atomic_set_crtc_for_connector);
 
+/*
+ * drm_atomic_get_writeback_job - return or allocate a writeback job
+ * @conn_state: Connector state to get the job for
+ *
+ * Writeback jobs have a different lifetime to the atomic state they are
+ * associated with. This convenience function takes care of allocating a job
+ * if there isn't yet one associated with the connector state, otherwise
+ * it just returns the existing job.
+ *
+ * Returns: The writeback job for the given connector state
+ */
+static struct drm_writeback_job *
+drm_atomic_get_writeback_job(struct drm_connector_state *conn_state)
+{
+	WARN_ON(conn_state->connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
+
+	if (!conn_state->writeback_job)
+		conn_state->writeback_job =
+			kzalloc(sizeof(*conn_state->writeback_job), GFP_KERNEL);
+
+	return conn_state->writeback_job;
+}
+
+/**
+ * drm_atomic_set_writeback_fb_for_connector - set writeback framebuffer
+ * @conn_state: atomic state object for the connector
+ * @fb: fb to use for the connector
+ *
+ * This is used to set the framebuffer for a writeback connector, which outputs
+ * to a buffer instead of an actual physical connector.
+ * Changing the assigned framebuffer requires us to grab a reference to the new
+ * fb and drop the reference to the old fb, if there is one. This function
+ * takes care of all these details besides updating the pointer in the
+ * state object itself.
+ *
+ * Note: The only way conn_state can already have an fb set is if the commit
+ * sets the property more than once.
+ *
+ * See also: drm_writeback_connector_init()
+ *
+ * Returns: 0 on success
+ */
+int drm_atomic_set_writeback_fb_for_connector(
+		struct drm_connector_state *conn_state,
+		struct drm_framebuffer *fb)
+{
+	struct drm_writeback_job *job =
+		drm_atomic_get_writeback_job(conn_state);
+	if (!job)
+		return -ENOMEM;
+
+	drm_framebuffer_assign(&job->fb, fb);
+
+	if (fb)
+		DRM_DEBUG_ATOMIC("Set [FB:%d] for connector state %p\n",
+				 fb->base.id, conn_state);
+	else
+		DRM_DEBUG_ATOMIC("Set [NOFB] for connector state %p\n",
+				 conn_state);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_atomic_set_writeback_fb_for_connector);
+
 /**
  * drm_atomic_add_affected_connectors - add connectors for crtc
  * @state: atomic state
@@ -1752,6 +1865,8 @@ int drm_atomic_check_only(struct drm_atomic_state *state)
 	struct drm_plane_state *plane_state;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
+	struct drm_connector *conn;
+	struct drm_connector_state *conn_state;
 	int i, ret = 0;
 
 	DRM_DEBUG_ATOMIC("checking %p\n", state);
@@ -1774,6 +1889,15 @@ int drm_atomic_check_only(struct drm_atomic_state *state)
 		}
 	}
 
+	for_each_new_connector_in_state(state, conn, conn_state, i) {
+		ret = drm_atomic_connector_check(conn, conn_state);
+		if (ret) {
+			DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] atomic core check failed\n",
+					 conn->base.id, conn->name);
+			return ret;
+		}
+	}
+
 	if (config->funcs->atomic_check)
 		ret = config->funcs->atomic_check(state->dev, state);
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 232fa11a5e31..17baf5057132 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -30,6 +30,7 @@
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_writeback.h>
 #include <linux/dma-fence.h>
 
 #include "drm_crtc_helper_internal.h"
@@ -1172,6 +1173,25 @@ void drm_atomic_helper_commit_modeset_disables(struct drm_device *dev,
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_disables);
 
+static void drm_atomic_helper_commit_writebacks(struct drm_device *dev,
+						struct drm_atomic_state *old_state)
+{
+	struct drm_connector *connector;
+	struct drm_connector_state *new_conn_state;
+	int i;
+
+	for_each_new_connector_in_state(old_state, connector, new_conn_state, i) {
+		const struct drm_connector_helper_funcs *funcs;
+
+		funcs = connector->helper_private;
+
+		if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) {
+			WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
+			funcs->atomic_commit(connector, new_conn_state->writeback_job);
+		}
+	}
+}
+
 /**
  * drm_atomic_helper_commit_modeset_enables - modeset commit to enable outputs
  * @dev: DRM device
@@ -1251,6 +1271,8 @@ void drm_atomic_helper_commit_modeset_enables(struct drm_device *dev,
 
 		drm_bridge_enable(encoder->bridge);
 	}
+
+	drm_atomic_helper_commit_writebacks(dev, old_state);
 }
 EXPORT_SYMBOL(drm_atomic_helper_commit_modeset_enables);
 
@@ -3647,6 +3669,9 @@ __drm_atomic_helper_connector_duplicate_state(struct drm_connector *connector,
 	if (state->crtc)
 		drm_connector_get(connector);
 	state->commit = NULL;
+
+	/* Don't copy over a writeback job, they are used only once */
+	state->writeback_job = NULL;
 }
 EXPORT_SYMBOL(__drm_atomic_helper_connector_duplicate_state);
 
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 549b89501e01..2f9ebddd178e 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -87,6 +87,7 @@ static struct drm_conn_prop_enum_list drm_connector_enum_list[] = {
 	{ DRM_MODE_CONNECTOR_VIRTUAL, "Virtual" },
 	{ DRM_MODE_CONNECTOR_DSI, "DSI" },
 	{ DRM_MODE_CONNECTOR_DPI, "DPI" },
+	{ DRM_MODE_CONNECTOR_WRITEBACK, "Writeback" },
 };
 
 void drm_connector_ida_init(void)
@@ -253,7 +254,8 @@ int drm_connector_init(struct drm_device *dev,
 	config->num_connector++;
 	spin_unlock_irq(&config->connector_list_lock);
 
-	if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL)
+	if (connector_type != DRM_MODE_CONNECTOR_VIRTUAL &&
+	    connector_type != DRM_MODE_CONNECTOR_WRITEBACK)
 		drm_object_attach_property(&connector->base,
 					      config->edid_property,
 					      0);
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
new file mode 100644
index 000000000000..e5b8a4b79724
--- /dev/null
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -0,0 +1,245 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Brian Starkey <brian.starkey@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ */
+
+#include <drm/drm_crtc.h>
+#include <drm/drm_modeset_helper_vtables.h>
+#include <drm/drm_property.h>
+#include <drm/drm_writeback.h>
+#include <drm/drmP.h>
+
+/**
+ * DOC: overview
+ *
+ * Writeback connectors are used to expose hardware which can write the output
+ * from a CRTC to a memory buffer. They are used and act similarly to other
+ * types of connectors, with some important differences:
+ *  - Writeback connectors don't provide a way to output visually to the user.
+ *  - Writeback connectors should always report as "disconnected" (so that
+ *    clients which don't understand them will ignore them).
+ *  - Writeback connectors don't have EDID.
+ *
+ * A framebuffer may only be attached to a writeback connector when the
+ * connector is attached to a CRTC. The WRITEBACK_FB_ID property which sets the
+ * framebuffer applies only to a single commit (see below). A framebuffer may
+ * not be attached while the CRTC is off.
+ *
+ * Writeback connectors have some additional properties, which userspace
+ * can use to query and control them:
+ *
+ *  "WRITEBACK_FB_ID":
+ *	Write-only object property storing a DRM_MODE_OBJECT_FB: it stores the
+ *	framebuffer to be written by the writeback connector. This property is
+ *	similar to the FB_ID property on planes, but will always read as zero
+ *	and is not preserved across commits.
+ *	Userspace must set this property to an output buffer every time it
+ *	wishes the buffer to get filled.
+ *
+ *  "WRITEBACK_PIXEL_FORMATS":
+ *	Immutable blob property to store the supported pixel formats table. The
+ *	data is an array of u32 DRM_FORMAT_* fourcc values.
+ *	Userspace can use this blob to find out what pixel formats are supported
+ *	by the connector's writeback engine.
+ */
+
+static int create_writeback_properties(struct drm_device *dev)
+{
+	struct drm_property *prop;
+
+	if (!dev->mode_config.writeback_fb_id_property) {
+		prop = drm_property_create_object(dev, DRM_MODE_PROP_ATOMIC,
+						  "WRITEBACK_FB_ID",
+						  DRM_MODE_OBJECT_FB);
+		if (!prop)
+			return -ENOMEM;
+		dev->mode_config.writeback_fb_id_property = prop;
+	}
+
+	if (!dev->mode_config.writeback_pixel_formats_property) {
+		prop = drm_property_create(dev, DRM_MODE_PROP_BLOB |
+					   DRM_MODE_PROP_ATOMIC |
+					   DRM_MODE_PROP_IMMUTABLE,
+					   "WRITEBACK_PIXEL_FORMATS", 0);
+		if (!prop)
+			return -ENOMEM;
+		dev->mode_config.writeback_pixel_formats_property = prop;
+	}
+
+	return 0;
+}
+
+static const struct drm_encoder_funcs drm_writeback_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+/**
+ * drm_writeback_connector_init - Initialize a writeback connector and its properties
+ * @dev: DRM device
+ * @wb_connector: Writeback connector to initialize
+ * @con_funcs: Connector funcs vtable
+ * @enc_helper_funcs: Encoder helper funcs vtable to be used by the internal encoder
+ * @formats: Array of supported pixel formats for the writeback engine
+ * @n_formats: Length of the formats array
+ *
+ * This function creates the writeback-connector-specific properties if they
+ * have not been already created, initializes the connector as
+ * type DRM_MODE_CONNECTOR_WRITEBACK, and correctly initializes the property
+ * values. It will also create an internal encoder associated with the
+ * drm_writeback_connector and set it to use the @enc_helper_funcs vtable for
+ * the encoder helper.
+ *
+ * Drivers should always use this function instead of drm_connector_init() to
+ * set up writeback connectors.
+ *
+ * Returns: 0 on success, or a negative error code
+ */
+int drm_writeback_connector_init(struct drm_device *dev,
+				 struct drm_writeback_connector *wb_connector,
+				 const struct drm_connector_funcs *con_funcs,
+				 const struct drm_encoder_helper_funcs *enc_helper_funcs,
+				 const u32 *formats, int n_formats)
+{
+	struct drm_property_blob *blob;
+	struct drm_connector *connector = &wb_connector->base;
+	struct drm_mode_config *config = &dev->mode_config;
+	int ret = create_writeback_properties(dev);
+
+	if (ret != 0)
+		return ret;
+
+	blob = drm_property_create_blob(dev, n_formats * sizeof(*formats),
+					formats);
+	if (IS_ERR(blob))
+		return PTR_ERR(blob);
+
+	drm_encoder_helper_add(&wb_connector->encoder, enc_helper_funcs);
+	ret = drm_encoder_init(dev, &wb_connector->encoder,
+			       &drm_writeback_encoder_funcs,
+			       DRM_MODE_ENCODER_VIRTUAL, NULL);
+	if (ret)
+		goto fail;
+
+	connector->interlace_allowed = 0;
+
+	ret = drm_connector_init(dev, connector, con_funcs,
+				 DRM_MODE_CONNECTOR_WRITEBACK);
+	if (ret)
+		goto connector_fail;
+
+	ret = drm_mode_connector_attach_encoder(connector,
+						&wb_connector->encoder);
+	if (ret)
+		goto attach_fail;
+
+	INIT_LIST_HEAD(&wb_connector->job_queue);
+	spin_lock_init(&wb_connector->job_lock);
+
+	drm_object_attach_property(&connector->base,
+				   config->writeback_fb_id_property, 0);
+
+	drm_object_attach_property(&connector->base,
+				   config->writeback_pixel_formats_property,
+				   blob->base.id);
+	wb_connector->pixel_formats_blob_ptr = blob;
+
+	return 0;
+
+attach_fail:
+	drm_connector_cleanup(connector);
+connector_fail:
+	drm_encoder_cleanup(&wb_connector->encoder);
+fail:
+	drm_property_blob_put(blob);
+	return ret;
+}
+EXPORT_SYMBOL(drm_writeback_connector_init);
+
+/**
+ * drm_writeback_queue_job - Queue a writeback job for later signalling
+ * @wb_connector: The writeback connector to queue a job on
+ * @job: The job to queue
+ *
+ * This function adds a job to the job_queue for a writeback connector. It
+ * should be considered to take ownership of the writeback job, and so any other
+ * references to the job must be cleared after calling this function.
+ *
+ * Drivers must ensure that for a given writeback connector, jobs are queued in
+ * exactly the same order as they will be completed by the hardware (and
+ * signaled via drm_writeback_signal_completion).
+ *
+ * For every call to drm_writeback_queue_job() there must be exactly one call to
+ * drm_writeback_signal_completion()
+ *
+ * See also: drm_writeback_signal_completion()
+ */
+void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector,
+			     struct drm_writeback_job *job)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&wb_connector->job_lock, flags);
+	list_add_tail(&job->list_entry, &wb_connector->job_queue);
+	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
+}
+EXPORT_SYMBOL(drm_writeback_queue_job);
+
+/*
+ * @cleanup_work: deferred cleanup of a writeback job
+ *
+ * The job cannot be cleaned up directly in drm_writeback_signal_completion,
+ * because it may be called in interrupt context. Dropping the framebuffer
+ * reference can sleep, and so the cleanup is deferred to a workqueue.
+ */
+static void cleanup_work(struct work_struct *work)
+{
+	struct drm_writeback_job *job = container_of(work,
+						     struct drm_writeback_job,
+						     cleanup_work);
+	drm_framebuffer_put(job->fb);
+	kfree(job);
+}
+
+
+/**
+ * drm_writeback_signal_completion - Signal the completion of a writeback job
+ * @wb_connector: The writeback connector whose job is complete
+ *
+ * Drivers should call this to signal the completion of a previously queued
+ * writeback job. It should be called as soon as possible after the hardware
+ * has finished writing, and may be called from interrupt context.
+ * It is the driver's responsibility to ensure that for a given connector, the
+ * hardware completes writeback jobs in the same order as they are queued.
+ *
+ * Unless the driver is holding its own reference to the framebuffer, it must
+ * not be accessed after calling this function.
+ *
+ * See also: drm_writeback_queue_job()
+ */
+void
+drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector)
+{
+	unsigned long flags;
+	struct drm_writeback_job *job;
+
+	spin_lock_irqsave(&wb_connector->job_lock, flags);
+	job = list_first_entry_or_null(&wb_connector->job_queue,
+				       struct drm_writeback_job,
+				       list_entry);
+	if (job)
+		list_del(&job->list_entry);
+	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
+
+	if (WARN_ON(!job))
+		return;
+
+	INIT_WORK(&job->cleanup_work, cleanup_work);
+	queue_work(system_long_wq, &job->cleanup_work);
+}
+EXPORT_SYMBOL(drm_writeback_signal_completion);
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index ca461b6cf71f..8254521b4583 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -594,6 +594,9 @@ void drm_atomic_set_fence_for_plane(struct drm_plane_state *plane_state,
 int __must_check
 drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 				  struct drm_crtc *crtc);
+int drm_atomic_set_writeback_fb_for_connector(
+		struct drm_connector_state *conn_state,
+		struct drm_framebuffer *fb);
 int __must_check
 drm_atomic_add_affected_connectors(struct drm_atomic_state *state,
 				   struct drm_crtc *crtc);
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index c5797c24edd3..716c3a0e0e1d 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -437,6 +437,19 @@ struct drm_connector_state {
 	 * protection. This is most commonly used for HDCP.
 	 */
 	unsigned int content_protection;
+
+	/**
+	 * @writeback_job: Writeback job for writeback connectors
+	 *
+	 * Holds the framebuffer for a writeback connector. As the writeback
+	 * completion may be asynchronous to the normal commit cycle, the
+	 * writeback job lifetime is managed separately from the normal atomic
+	 * state by this object.
+	 *
+	 * See also: drm_writeback_queue_job() and
+	 * drm_writeback_signal_completion()
+	 */
+	struct drm_writeback_job *writeback_job;
 };
 
 /**
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index fb45839179dd..5f24329e6927 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -784,6 +784,21 @@ struct drm_mode_config {
 	 */
 	struct drm_property *panel_orientation_property;
 
+	/**
+	 * @writeback_fb_id_property: Property for writeback connectors, storing
+	 * the ID of the output framebuffer.
+	 * See also: drm_writeback_connector_init()
+	 */
+	struct drm_property *writeback_fb_id_property;
+
+	/**
+	 * @writeback_pixel_formats_property: Property for writeback connectors,
+	 * storing an array of the supported pixel formats for the writeback
+	 * engine (read-only).
+	 * See also: drm_writeback_connector_init()
+	 */
+	struct drm_property *writeback_pixel_formats_property;
+
 	/* dumb ioctl parameters */
 	uint32_t preferred_depth, prefer_shadow;
 
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index 35e2a3a79fc5..3b289773297c 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -974,6 +974,17 @@ struct drm_connector_helper_funcs {
 	 */
 	int (*atomic_check)(struct drm_connector *connector,
 			    struct drm_connector_state *state);
+
+	/**
+	 * @atomic_commit:
+	 *
+	 * This hook is to be used by drivers implementing writeback connectors
+	 * that need a point when to commit the writeback job to the hardware.
+	 *
+	 * This callback is used by the atomic modeset helpers.
+	 */
+	void (*atomic_commit)(struct drm_connector *connector,
+			      struct drm_writeback_job *writeback_job);
 };
 
 /**
diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h
new file mode 100644
index 000000000000..17cd1feecd7e
--- /dev/null
+++ b/include/drm/drm_writeback.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Brian Starkey <brian.starkey@arm.com>
+ *
+ * This program is free software and is provided to you under the terms of the
+ * GNU General Public License version 2 as published by the Free Software
+ * Foundation, and any use by you of this program is subject to the terms
+ * of such GNU licence.
+ */
+
+#ifndef __DRM_WRITEBACK_H__
+#define __DRM_WRITEBACK_H__
+#include <drm/drm_connector.h>
+#include <drm/drm_encoder.h>
+#include <linux/workqueue.h>
+
+struct drm_writeback_connector {
+	struct drm_connector base;
+
+	/**
+	 * @encoder: Internal encoder used by the connector to fulfill
+	 * the DRM framework requirements. The users of the
+	 * @drm_writeback_connector control the behaviour of the @encoder
+	 * by passing the @enc_funcs parameter to drm_writeback_connector_init()
+	 * function.
+	 */
+	struct drm_encoder encoder;
+
+	/**
+	 * @pixel_formats_blob_ptr:
+	 *
+	 * DRM blob property data for the pixel formats list on writeback
+	 * connectors
+	 * See also drm_writeback_connector_init()
+	 */
+	struct drm_property_blob *pixel_formats_blob_ptr;
+
+	/** @job_lock: Protects job_queue */
+	spinlock_t job_lock;
+
+	/**
+	 * @job_queue:
+	 *
+	 * Holds a list of a connector's writeback jobs; the last item is the
+	 * most recent. The first item may be either waiting for the hardware
+	 * to begin writing, or currently being written.
+	 *
+	 * See also: drm_writeback_queue_job() and
+	 * drm_writeback_signal_completion()
+	 */
+	struct list_head job_queue;
+};
+
+struct drm_writeback_job {
+	/**
+	 * @cleanup_work:
+	 *
+	 * Used to allow drm_writeback_signal_completion to defer dropping the
+	 * framebuffer reference to a workqueue
+	 */
+	struct work_struct cleanup_work;
+
+	/**
+	 * @list_entry:
+	 *
+	 * List item for the writeback connector's @job_queue
+	 */
+	struct list_head list_entry;
+
+	/**
+	 * @fb:
+	 *
+	 * Framebuffer to be written to by the writeback connector. Do not set
+	 * directly, use drm_atomic_set_writeback_fb_for_connector()
+	 */
+	struct drm_framebuffer *fb;
+};
+
+int drm_writeback_connector_init(struct drm_device *dev,
+				 struct drm_writeback_connector *wb_connector,
+				 const struct drm_connector_funcs *con_funcs,
+				 const struct drm_encoder_helper_funcs *enc_helper_funcs,
+				 const u32 *formats, int n_formats);
+
+void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector,
+			     struct drm_writeback_job *job);
+
+void drm_writeback_cleanup_job(struct drm_writeback_job *job);
+void drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector);
+#endif
diff --git a/include/uapi/drm/drm_mode.h b/include/uapi/drm/drm_mode.h
index 971c016b368c..8d67243952f4 100644
--- a/include/uapi/drm/drm_mode.h
+++ b/include/uapi/drm/drm_mode.h
@@ -351,6 +351,7 @@ enum drm_mode_subconnector {
 #define DRM_MODE_CONNECTOR_VIRTUAL      15
 #define DRM_MODE_CONNECTOR_DSI		16
 #define DRM_MODE_CONNECTOR_DPI		17
+#define DRM_MODE_CONNECTOR_WRITEBACK	18
 
 struct drm_mode_get_connector {
 
-- 
cgit v1.2.3


From b13cc8dd588434e2aec781e6d12224e4c408ac18 Mon Sep 17 00:00:00 2001
From: Brian Starkey <brian.starkey@arm.com>
Date: Wed, 29 Mar 2017 17:42:33 +0100
Subject: drm: writeback: Add out-fences for writeback connectors

Add the WRITEBACK_OUT_FENCE_PTR property to writeback connectors, to
enable userspace to get a fence which will signal once the writeback is
complete. It is not allowed to request an out-fence without a
framebuffer attached to the connector.

A timeline is added to drm_writeback_connector for use by the writeback
out-fences.

In the case of a commit failure or DRM_MODE_ATOMIC_TEST_ONLY, the fence
is set to -1.

Changes from v2:
 - Rebase onto Gustavo Padovan's v9 explicit sync series
 - Change out_fence_ptr type to s32 __user *
 - Set *out_fence_ptr to -1 in drm_atomic_connector_set_property
 - Store fence in drm_writeback_job
 Gustavo Padovan:
 - Move out_fence_ptr out of connector_state
 - Signal fence from drm_writeback_signal_completion instead of
   in driver directly

Changes from v3:
 - Rebase onto commit 7e9081c5aac7 ("drm/fence: fix memory overwrite
   when setting out_fence fd") (change out_fence_ptr to s32 __user *,
   for real this time.)
 - Update documentation around WRITEBACK_OUT_FENCE_PTR

Signed-off-by: Brian Starkey <brian.starkey@arm.com>
[rebased and fixed conflicts]
Signed-off-by: Mihail Atanassov <mihail.atanassov@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Link: https://patchwork.freedesktop.org/patch/229036/
---
 drivers/gpu/drm/drm_atomic.c    |  99 ++++++++++++++++++++++++++++++++----
 drivers/gpu/drm/drm_writeback.c | 109 +++++++++++++++++++++++++++++++++++++++-
 include/drm/drm_atomic.h        |   8 +++
 include/drm/drm_connector.h     |   8 +--
 include/drm/drm_mode_config.h   |   8 +++
 include/drm/drm_writeback.h     |  41 ++++++++++++++-
 6 files changed, 257 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 3e53d6e5c340..115719059434 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -318,6 +318,35 @@ static s32 __user *get_out_fence_for_crtc(struct drm_atomic_state *state,
 	return fence_ptr;
 }
 
+static int set_out_fence_for_connector(struct drm_atomic_state *state,
+					struct drm_connector *connector,
+					s32 __user *fence_ptr)
+{
+	unsigned int index = drm_connector_index(connector);
+
+	if (!fence_ptr)
+		return 0;
+
+	if (put_user(-1, fence_ptr))
+		return -EFAULT;
+
+	state->connectors[index].out_fence_ptr = fence_ptr;
+
+	return 0;
+}
+
+static s32 __user *get_out_fence_for_connector(struct drm_atomic_state *state,
+					       struct drm_connector *connector)
+{
+	unsigned int index = drm_connector_index(connector);
+	s32 __user *fence_ptr;
+
+	fence_ptr = state->connectors[index].out_fence_ptr;
+	state->connectors[index].out_fence_ptr = NULL;
+
+	return fence_ptr;
+}
+
 /**
  * drm_atomic_set_mode_for_crtc - set mode for CRTC
  * @state: the CRTC whose incoming state to update
@@ -727,6 +756,12 @@ static int drm_atomic_connector_check(struct drm_connector *connector,
 		return -EINVAL;
 	}
 
+	if (writeback_job->out_fence && !writeback_job->fb) {
+		DRM_DEBUG_ATOMIC("[CONNECTOR:%d:%s] requesting out-fence without framebuffer\n",
+				 connector->base.id, connector->name);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -1367,6 +1402,11 @@ static int drm_atomic_connector_set_property(struct drm_connector *connector,
 		if (fb)
 			drm_framebuffer_put(fb);
 		return ret;
+	} else if (property == config->writeback_out_fence_ptr_property) {
+		s32 __user *fence_ptr = u64_to_user_ptr(val);
+
+		return set_out_fence_for_connector(state->state, connector,
+						   fence_ptr);
 	} else if (connector->funcs->atomic_set_property) {
 		return connector->funcs->atomic_set_property(connector,
 				state, property, val);
@@ -1456,6 +1496,8 @@ drm_atomic_connector_get_property(struct drm_connector *connector,
 	} else if (property == config->writeback_fb_id_property) {
 		/* Writeback framebuffer is one-shot, write and forget */
 		*val = 0;
+	} else if (property == config->writeback_out_fence_ptr_property) {
+		*val = 0;
 	} else if (connector->funcs->atomic_get_property) {
 		return connector->funcs->atomic_get_property(connector,
 				state, property, val);
@@ -2292,7 +2334,7 @@ static int setup_out_fence(struct drm_out_fence_state *fence_state,
 	return 0;
 }
 
-static int prepare_crtc_signaling(struct drm_device *dev,
+static int prepare_signaling(struct drm_device *dev,
 				  struct drm_atomic_state *state,
 				  struct drm_mode_atomic *arg,
 				  struct drm_file *file_priv,
@@ -2301,6 +2343,8 @@ static int prepare_crtc_signaling(struct drm_device *dev,
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
+	struct drm_connector *conn;
+	struct drm_connector_state *conn_state;
 	int i, c = 0, ret;
 
 	if (arg->flags & DRM_MODE_ATOMIC_TEST_ONLY)
@@ -2366,6 +2410,43 @@ static int prepare_crtc_signaling(struct drm_device *dev,
 		c++;
 	}
 
+	for_each_new_connector_in_state(state, conn, conn_state, i) {
+		struct drm_writeback_job *job;
+		struct drm_out_fence_state *f;
+		struct dma_fence *fence;
+		s32 __user *fence_ptr;
+
+		fence_ptr = get_out_fence_for_connector(state, conn);
+		if (!fence_ptr)
+			continue;
+
+		job = drm_atomic_get_writeback_job(conn_state);
+		if (!job)
+			return -ENOMEM;
+
+		f = krealloc(*fence_state, sizeof(**fence_state) *
+			     (*num_fences + 1), GFP_KERNEL);
+		if (!f)
+			return -ENOMEM;
+
+		memset(&f[*num_fences], 0, sizeof(*f));
+
+		f[*num_fences].out_fence_ptr = fence_ptr;
+		*fence_state = f;
+
+		fence = drm_writeback_get_out_fence((struct drm_writeback_connector *)conn);
+		if (!fence)
+			return -ENOMEM;
+
+		ret = setup_out_fence(&f[(*num_fences)++], fence);
+		if (ret) {
+			dma_fence_put(fence);
+			return ret;
+		}
+
+		job->out_fence = fence;
+	}
+
 	/*
 	 * Having this flag means user mode pends on event which will never
 	 * reach due to lack of at least one CRTC for signaling
@@ -2376,11 +2457,11 @@ static int prepare_crtc_signaling(struct drm_device *dev,
 	return 0;
 }
 
-static void complete_crtc_signaling(struct drm_device *dev,
-				    struct drm_atomic_state *state,
-				    struct drm_out_fence_state *fence_state,
-				    unsigned int num_fences,
-				    bool install_fds)
+static void complete_signaling(struct drm_device *dev,
+			       struct drm_atomic_state *state,
+			       struct drm_out_fence_state *fence_state,
+			       unsigned int num_fences,
+			       bool install_fds)
 {
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
@@ -2550,8 +2631,8 @@ retry:
 		drm_mode_object_put(obj);
 	}
 
-	ret = prepare_crtc_signaling(dev, state, arg, file_priv, &fence_state,
-				     &num_fences);
+	ret = prepare_signaling(dev, state, arg, file_priv, &fence_state,
+				&num_fences);
 	if (ret)
 		goto out;
 
@@ -2567,7 +2648,7 @@ retry:
 	}
 
 out:
-	complete_crtc_signaling(dev, state, fence_state, num_fences, !ret);
+	complete_signaling(dev, state, fence_state, num_fences, !ret);
 
 	if (ret == -EDEADLK) {
 		drm_atomic_state_clear(state);
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index e5b8a4b79724..827395071f0b 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -14,6 +14,7 @@
 #include <drm/drm_property.h>
 #include <drm/drm_writeback.h>
 #include <drm/drmP.h>
+#include <linux/dma-fence.h>
 
 /**
  * DOC: overview
@@ -31,6 +32,16 @@
  * framebuffer applies only to a single commit (see below). A framebuffer may
  * not be attached while the CRTC is off.
  *
+ * Unlike with planes, when a writeback framebuffer is removed by userspace DRM
+ * makes no attempt to remove it from active use by the connector. This is
+ * because no method is provided to abort a writeback operation, and in any
+ * case making a new commit whilst a writeback is ongoing is undefined (see
+ * WRITEBACK_OUT_FENCE_PTR below). As soon as the current writeback is finished,
+ * the framebuffer will automatically no longer be in active use. As it will
+ * also have already been removed from the framebuffer list, there will be no
+ * way for any userspace application to retrieve a reference to it in the
+ * intervening period.
+ *
  * Writeback connectors have some additional properties, which userspace
  * can use to query and control them:
  *
@@ -47,8 +58,54 @@
  *	data is an array of u32 DRM_FORMAT_* fourcc values.
  *	Userspace can use this blob to find out what pixel formats are supported
  *	by the connector's writeback engine.
+ *
+ *  "WRITEBACK_OUT_FENCE_PTR":
+ *	Userspace can use this property to provide a pointer for the kernel to
+ *	fill with a sync_file file descriptor, which will signal once the
+ *	writeback is finished. The value should be the address of a 32-bit
+ *	signed integer, cast to a u64.
+ *	Userspace should wait for this fence to signal before making another
+ *	commit affecting any of the same CRTCs, Planes or Connectors.
+ *	**Failure to do so will result in undefined behaviour.**
+ *	For this reason it is strongly recommended that all userspace
+ *	applications making use of writeback connectors *always* retrieve an
+ *	out-fence for the commit and use it appropriately.
+ *	From userspace, this property will always read as zero.
  */
 
+#define fence_to_wb_connector(x) container_of(x->lock, \
+					      struct drm_writeback_connector, \
+					      fence_lock)
+
+static const char *drm_writeback_fence_get_driver_name(struct dma_fence *fence)
+{
+	struct drm_writeback_connector *wb_connector =
+		fence_to_wb_connector(fence);
+
+	return wb_connector->base.dev->driver->name;
+}
+
+static const char *
+drm_writeback_fence_get_timeline_name(struct dma_fence *fence)
+{
+	struct drm_writeback_connector *wb_connector =
+		fence_to_wb_connector(fence);
+
+	return wb_connector->timeline_name;
+}
+
+static bool drm_writeback_fence_enable_signaling(struct dma_fence *fence)
+{
+	return true;
+}
+
+static const struct dma_fence_ops drm_writeback_fence_ops = {
+	.get_driver_name = drm_writeback_fence_get_driver_name,
+	.get_timeline_name = drm_writeback_fence_get_timeline_name,
+	.enable_signaling = drm_writeback_fence_enable_signaling,
+	.wait = dma_fence_default_wait,
+};
+
 static int create_writeback_properties(struct drm_device *dev)
 {
 	struct drm_property *prop;
@@ -72,6 +129,15 @@ static int create_writeback_properties(struct drm_device *dev)
 		dev->mode_config.writeback_pixel_formats_property = prop;
 	}
 
+	if (!dev->mode_config.writeback_out_fence_ptr_property) {
+		prop = drm_property_create_range(dev, DRM_MODE_PROP_ATOMIC,
+						 "WRITEBACK_OUT_FENCE_PTR", 0,
+						 U64_MAX);
+		if (!prop)
+			return -ENOMEM;
+		dev->mode_config.writeback_out_fence_ptr_property = prop;
+	}
+
 	return 0;
 }
 
@@ -141,6 +207,15 @@ int drm_writeback_connector_init(struct drm_device *dev,
 	INIT_LIST_HEAD(&wb_connector->job_queue);
 	spin_lock_init(&wb_connector->job_lock);
 
+	wb_connector->fence_context = dma_fence_context_alloc(1);
+	spin_lock_init(&wb_connector->fence_lock);
+	snprintf(wb_connector->timeline_name,
+		 sizeof(wb_connector->timeline_name),
+		 "CONNECTOR:%d-%s", connector->base.id, connector->name);
+
+	drm_object_attach_property(&connector->base,
+				   config->writeback_out_fence_ptr_property, 0);
+
 	drm_object_attach_property(&connector->base,
 				   config->writeback_fb_id_property, 0);
 
@@ -210,6 +285,7 @@ static void cleanup_work(struct work_struct *work)
 /**
  * drm_writeback_signal_completion - Signal the completion of a writeback job
  * @wb_connector: The writeback connector whose job is complete
+ * @status: Status code to set in the writeback out_fence (0 for success)
  *
  * Drivers should call this to signal the completion of a previously queued
  * writeback job. It should be called as soon as possible after the hardware
@@ -223,7 +299,8 @@ static void cleanup_work(struct work_struct *work)
  * See also: drm_writeback_queue_job()
  */
 void
-drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector)
+drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector,
+				int status)
 {
 	unsigned long flags;
 	struct drm_writeback_job *job;
@@ -232,8 +309,15 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector)
 	job = list_first_entry_or_null(&wb_connector->job_queue,
 				       struct drm_writeback_job,
 				       list_entry);
-	if (job)
+	if (job) {
 		list_del(&job->list_entry);
+		if (job->out_fence) {
+			if (status)
+				dma_fence_set_error(job->out_fence, status);
+			dma_fence_signal(job->out_fence);
+			dma_fence_put(job->out_fence);
+		}
+	}
 	spin_unlock_irqrestore(&wb_connector->job_lock, flags);
 
 	if (WARN_ON(!job))
@@ -243,3 +327,24 @@ drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector)
 	queue_work(system_long_wq, &job->cleanup_work);
 }
 EXPORT_SYMBOL(drm_writeback_signal_completion);
+
+struct dma_fence *
+drm_writeback_get_out_fence(struct drm_writeback_connector *wb_connector)
+{
+	struct dma_fence *fence;
+
+	if (WARN_ON(wb_connector->base.connector_type !=
+		    DRM_MODE_CONNECTOR_WRITEBACK))
+		return NULL;
+
+	fence = kzalloc(sizeof(*fence), GFP_KERNEL);
+	if (!fence)
+		return NULL;
+
+	dma_fence_init(fence, &drm_writeback_fence_ops,
+		       &wb_connector->fence_lock, wb_connector->fence_context,
+		       ++wb_connector->fence_seqno);
+
+	return fence;
+}
+EXPORT_SYMBOL(drm_writeback_get_out_fence);
diff --git a/include/drm/drm_atomic.h b/include/drm/drm_atomic.h
index 8254521b4583..da9d95a19580 100644
--- a/include/drm/drm_atomic.h
+++ b/include/drm/drm_atomic.h
@@ -160,6 +160,14 @@ struct __drm_crtcs_state {
 struct __drm_connnectors_state {
 	struct drm_connector *ptr;
 	struct drm_connector_state *state, *old_state, *new_state;
+	/**
+	 * @out_fence_ptr:
+	 *
+	 * User-provided pointer which the kernel uses to return a sync_file
+	 * file descriptor. Used by writeback connectors to signal completion of
+	 * the writeback.
+	 */
+	s32 __user *out_fence_ptr;
 };
 
 struct drm_private_obj;
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index 716c3a0e0e1d..14ab58ade87f 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -441,10 +441,10 @@ struct drm_connector_state {
 	/**
 	 * @writeback_job: Writeback job for writeback connectors
 	 *
-	 * Holds the framebuffer for a writeback connector. As the writeback
-	 * completion may be asynchronous to the normal commit cycle, the
-	 * writeback job lifetime is managed separately from the normal atomic
-	 * state by this object.
+	 * Holds the framebuffer and out-fence for a writeback connector. As
+	 * the writeback completion may be asynchronous to the normal commit
+	 * cycle, the writeback job lifetime is managed separately from the
+	 * normal atomic state by this object.
 	 *
 	 * See also: drm_writeback_queue_job() and
 	 * drm_writeback_signal_completion()
diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index 5f24329e6927..f4a173c8d79c 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -798,6 +798,14 @@ struct drm_mode_config {
 	 * See also: drm_writeback_connector_init()
 	 */
 	struct drm_property *writeback_pixel_formats_property;
+	/**
+	 * @writeback_out_fence_ptr_property: Property for writeback connectors,
+	 * fd pointer representing the outgoing fences for a writeback
+	 * connector. Userspace should provide a pointer to a value of type s32,
+	 * and then cast that pointer to u64.
+	 * See also: drm_writeback_connector_init()
+	 */
+	struct drm_property *writeback_out_fence_ptr_property;
 
 	/* dumb ioctl parameters */
 	uint32_t preferred_depth, prefer_shadow;
diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h
index 17cd1feecd7e..a10fe556dfd4 100644
--- a/include/drm/drm_writeback.h
+++ b/include/drm/drm_writeback.h
@@ -50,6 +50,32 @@ struct drm_writeback_connector {
 	 * drm_writeback_signal_completion()
 	 */
 	struct list_head job_queue;
+
+	/**
+	 * @fence_context:
+	 *
+	 * timeline context used for fence operations.
+	 */
+	unsigned int fence_context;
+	/**
+	 * @fence_lock:
+	 *
+	 * spinlock to protect the fences in the fence_context.
+	 */
+	spinlock_t fence_lock;
+	/**
+	 * @fence_seqno:
+	 *
+	 * Seqno variable used as monotonic counter for the fences
+	 * created on the connector's timeline.
+	 */
+	unsigned long fence_seqno;
+	/**
+	 * @timeline_name:
+	 *
+	 * The name of the connector's fence timeline.
+	 */
+	char timeline_name[32];
 };
 
 struct drm_writeback_job {
@@ -75,6 +101,13 @@ struct drm_writeback_job {
 	 * directly, use drm_atomic_set_writeback_fb_for_connector()
 	 */
 	struct drm_framebuffer *fb;
+
+	/**
+	 * @out_fence:
+	 *
+	 * Fence which will signal once the writeback has completed
+	 */
+	struct dma_fence *out_fence;
 };
 
 int drm_writeback_connector_init(struct drm_device *dev,
@@ -87,5 +120,11 @@ void drm_writeback_queue_job(struct drm_writeback_connector *wb_connector,
 			     struct drm_writeback_job *job);
 
 void drm_writeback_cleanup_job(struct drm_writeback_job *job);
-void drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector);
+
+void
+drm_writeback_signal_completion(struct drm_writeback_connector *wb_connector,
+				int status);
+
+struct dma_fence *
+drm_writeback_get_out_fence(struct drm_writeback_connector *wb_connector);
 #endif
-- 
cgit v1.2.3


From d67b6a2065076d763c7df626b8c54f16038ad862 Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Wed, 28 Feb 2018 14:11:23 +0000
Subject: drm: writeback: Add client capability for exposing writeback
 connectors

Due to the fact that writeback connectors behave in a special way
in DRM (they always report being disconnected) we might confuse some
userspace. Add a client capability for writeback connectors that will
filter them out for clients that don't understand the capability.

Changelog:
 - only accept the capability if the client has already set the
DRM_CLIENT_CAP_ATOMIC one.

Cc: Sean Paul <seanpaul@chromium.org>
Cc: Brian Starkey <brian.starkey@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Brian Starkey <brian.starkey@arm.com>
Link: https://patchwork.freedesktop.org/patch/229038/
---
 drivers/gpu/drm/drm_ioctl.c       | 7 +++++++
 drivers/gpu/drm/drm_mode_config.c | 5 +++++
 include/drm/drm_file.h            | 7 +++++++
 include/uapi/drm/drm.h            | 9 +++++++++
 4 files changed, 28 insertions(+)

diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 0d4cfb232576..fe49fb0356b5 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -334,6 +334,13 @@ drm_setclientcap(struct drm_device *dev, void *data, struct drm_file *file_priv)
 			return -EINVAL;
 		file_priv->aspect_ratio_allowed = req->value;
 		break;
+	case DRM_CLIENT_CAP_WRITEBACK_CONNECTORS:
+		if (!file_priv->atomic)
+			return -EINVAL;
+		if (req->value > 1)
+			return -EINVAL;
+		file_priv->writeback_connectors = req->value;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/gpu/drm/drm_mode_config.c b/drivers/gpu/drm/drm_mode_config.c
index e5c653357024..21e353bd3948 100644
--- a/drivers/gpu/drm/drm_mode_config.c
+++ b/drivers/gpu/drm/drm_mode_config.c
@@ -145,6 +145,11 @@ int drm_mode_getresources(struct drm_device *dev, void *data,
 	count = 0;
 	connector_id = u64_to_user_ptr(card_res->connector_id_ptr);
 	drm_for_each_connector_iter(connector, &conn_iter) {
+		/* only expose writeback connectors if userspace understands them */
+		if (!file_priv->writeback_connectors &&
+		    (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK))
+			continue;
+
 		if (drm_lease_held(file_priv, connector->base.id)) {
 			if (count < card_res->count_connectors &&
 			    put_user(connector->base.id, connector_id + count)) {
diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
index 027ac16da3d1..26485acc51d7 100644
--- a/include/drm/drm_file.h
+++ b/include/drm/drm_file.h
@@ -192,6 +192,13 @@ struct drm_file {
 	 */
 	unsigned aspect_ratio_allowed:1;
 
+	/**
+	 * @writeback_connectors:
+	 *
+	 * True if client understands writeback connectors
+	 */
+	unsigned writeback_connectors:1;
+
 	/**
 	 * @is_master:
 	 *
diff --git a/include/uapi/drm/drm.h b/include/uapi/drm/drm.h
index 9c660e1688ab..300f336633f2 100644
--- a/include/uapi/drm/drm.h
+++ b/include/uapi/drm/drm.h
@@ -687,6 +687,15 @@ struct drm_get_cap {
  */
 #define DRM_CLIENT_CAP_ASPECT_RATIO    4
 
+/**
+ * DRM_CLIENT_CAP_WRITEBACK_CONNECTORS
+ *
+ * If set to 1, the DRM core will expose special connectors to be used for
+ * writing back to memory the scene setup in the commit. Depends on client
+ * also supporting DRM_CLIENT_CAP_ATOMIC
+ */
+#define DRM_CLIENT_CAP_WRITEBACK_CONNECTORS	5
+
 /** DRM_IOCTL_SET_CLIENT_CAP ioctl argument type */
 struct drm_set_client_cap {
 	__u64 capability;
-- 
cgit v1.2.3


From c03cea42149de56fbae2301d7123daaa2cfe80e2 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jun 2018 15:10:58 -0700
Subject: iomap: add initial support for writes without buffer heads

For now just limited to blocksize == PAGE_SIZE, where we can simply read
in the full page in write begin, and just set the whole page dirty after
copying data into it.  This code is enabled by default and XFS will now
be feed pages without buffer heads in ->writepage and ->writepages.

If a file system sets the IOMAP_F_BUFFER_HEAD flag on the iomap the old
path will still be used, this both helps the transition in XFS and
prepares for the gfs2 migration to the iomap infrastructure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c            | 115 +++++++++++++++++++++++++++++++++++++++++++++++---
 fs/xfs/xfs_iomap.c    |   6 ++-
 include/linux/iomap.h |   2 +
 3 files changed, 114 insertions(+), 9 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 4f10c6b1cf6d..2ebff76039b5 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -348,6 +348,48 @@ iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 		truncate_pagecache_range(inode, max(pos, i_size), pos + len);
 }
 
+static int
+iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
+		unsigned poff, unsigned plen, unsigned from, unsigned to,
+		struct iomap *iomap)
+{
+	struct bio_vec bvec;
+	struct bio bio;
+
+	if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) {
+		zero_user_segments(page, poff, from, to, poff + plen);
+		return 0;
+	}
+
+	bio_init(&bio, &bvec, 1);
+	bio.bi_opf = REQ_OP_READ;
+	bio.bi_iter.bi_sector = iomap_sector(iomap, block_start);
+	bio_set_dev(&bio, iomap->bdev);
+	__bio_add_page(&bio, page, plen, poff);
+	return submit_bio_wait(&bio);
+}
+
+static int
+__iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
+		struct page *page, struct iomap *iomap)
+{
+	loff_t block_size = i_blocksize(inode);
+	loff_t block_start = pos & ~(block_size - 1);
+	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
+	unsigned poff = block_start & (PAGE_SIZE - 1);
+	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, block_end - block_start);
+	unsigned from = pos & (PAGE_SIZE - 1), to = from + len;
+
+	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE);
+
+	if (PageUptodate(page))
+		return 0;
+	if (from <= poff && to >= poff + plen)
+		return 0;
+	return iomap_read_page_sync(inode, block_start, page,
+			poff, plen, from, to, iomap);
+}
+
 static int
 iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 		struct page **pagep, struct iomap *iomap)
@@ -367,9 +409,10 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 
 	if (iomap->type == IOMAP_INLINE)
 		iomap_read_inline_data(inode, page, iomap);
-	else
+	else if (iomap->flags & IOMAP_F_BUFFER_HEAD)
 		status = __block_write_begin_int(page, pos, len, NULL, iomap);
-
+	else
+		status = __iomap_write_begin(inode, pos, len, page, iomap);
 	if (unlikely(status)) {
 		unlock_page(page);
 		put_page(page);
@@ -382,6 +425,57 @@ iomap_write_begin(struct inode *inode, loff_t pos, unsigned len, unsigned flags,
 	return status;
 }
 
+int
+iomap_set_page_dirty(struct page *page)
+{
+	struct address_space *mapping = page_mapping(page);
+	int newly_dirty;
+
+	if (unlikely(!mapping))
+		return !TestSetPageDirty(page);
+
+	/*
+	 * Lock out page->mem_cgroup migration to keep PageDirty
+	 * synchronized with per-memcg dirty page counters.
+	 */
+	lock_page_memcg(page);
+	newly_dirty = !TestSetPageDirty(page);
+	if (newly_dirty)
+		__set_page_dirty(page, mapping, 0);
+	unlock_page_memcg(page);
+
+	if (newly_dirty)
+		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
+	return newly_dirty;
+}
+EXPORT_SYMBOL_GPL(iomap_set_page_dirty);
+
+static int
+__iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
+		unsigned copied, struct page *page, struct iomap *iomap)
+{
+	flush_dcache_page(page);
+
+	/*
+	 * The blocks that were entirely written will now be uptodate, so we
+	 * don't have to worry about a readpage reading them and overwriting a
+	 * partial write.  However if we have encountered a short write and only
+	 * partially written into a block, it will not be marked uptodate, so a
+	 * readpage might come in and destroy our partial write.
+	 *
+	 * Do the simplest thing, and just treat any short write to a non
+	 * uptodate page as a zero-length write, and force the caller to redo
+	 * the whole thing.
+	 */
+	if (unlikely(copied < len && !PageUptodate(page))) {
+		copied = 0;
+	} else {
+		SetPageUptodate(page);
+		iomap_set_page_dirty(page);
+	}
+	return __generic_write_end(inode, pos, copied, page);
+}
+
 static int
 iomap_write_end_inline(struct inode *inode, struct page *page,
 		struct iomap *iomap, loff_t pos, unsigned copied)
@@ -408,9 +502,11 @@ iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 
 	if (iomap->type == IOMAP_INLINE) {
 		ret = iomap_write_end_inline(inode, page, iomap, pos, copied);
-	} else {
+	} else if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
 		ret = generic_write_end(NULL, inode->i_mapping, pos, len,
 				copied, page, NULL);
+	} else {
+		ret = __iomap_write_end(inode, pos, len, copied, page, iomap);
 	}
 
 	if (iomap->page_done)
@@ -703,11 +799,16 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct page *page = data;
 	int ret;
 
-	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
-	if (ret)
-		return ret;
+	if (iomap->flags & IOMAP_F_BUFFER_HEAD) {
+		ret = __block_write_begin_int(page, pos, length, NULL, iomap);
+		if (ret)
+			return ret;
+		block_commit_write(page, 0, length);
+	} else {
+		WARN_ON_ONCE(!PageUptodate(page));
+		WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE);
+	}
 
-	block_commit_write(page, 0, length);
 	return length;
 }
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 49f5492eed3b..8a3613d576af 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -626,7 +626,7 @@ retry:
 	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
 	 * them out if the write happens to fail.
 	 */
-	iomap->flags = IOMAP_F_NEW;
+	iomap->flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -1019,6 +1019,8 @@ xfs_file_iomap_begin(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
+	iomap->flags |= IOMAP_F_BUFFER_HEAD;
+
 	if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
 			!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
 		/* Reserve delalloc blocks for regular writeback. */
@@ -1119,7 +1121,7 @@ xfs_file_iomap_begin(
 	if (error)
 		return error;
 
-	iomap->flags = IOMAP_F_NEW;
+	iomap->flags |= IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
 
 out_finish:
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 30d314407f66..5eb9ca8d7ce5 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -30,6 +30,7 @@ struct vm_fault;
  */
 #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
 #define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
+#define IOMAP_F_BUFFER_HEAD	0x04	/* file system requires buffer heads */
 
 /*
  * Flags that only need to be reported for IOMAP_REPORT requests:
@@ -102,6 +103,7 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 int iomap_readpage(struct page *page, const struct iomap_ops *ops);
 int iomap_readpages(struct address_space *mapping, struct list_head *pages,
 		unsigned nr_pages, const struct iomap_ops *ops);
+int iomap_set_page_dirty(struct page *page);
 int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-- 
cgit v1.2.3


From f55786faa156370374c358d186eabf2f6e32e93f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 20 Jun 2018 17:21:52 +0100
Subject: drm/i915/selftests: Remove unused dmabuf->kmap routines, fix the
 build
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix i915's CI build after the removal of the dmabuf->kmap interface that
left the mock routines intact.

In file included from drivers/gpu/drm/i915/i915_gem_dmabuf.c:335:0:
drivers/gpu/drm/i915/selftests/mock_dmabuf.c:104:13: error: ‘mock_dmabuf_kunmap_atomic’ defined but not used [-Werror=unused-function]
 static void mock_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
drivers/gpu/drm/i915/selftests/mock_dmabuf.c:97:14: error: ‘mock_dmabuf_kmap_atomic’ defined but not used [-Werror=unused-function]
 static void *mock_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num)

Fixes: f664a5269542 ("dma-buf: remove kmap_atomic interface")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Christian König <christian.koenig@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180620162152.1158-1-chris@chris-wilson.co.uk
Reviewed-by: Christian König <christian.koenig@amd.com>
---
 drivers/gpu/drm/i915/selftests/mock_dmabuf.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
index f81fda8ea45e..ca682caf1062 100644
--- a/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
+++ b/drivers/gpu/drm/i915/selftests/mock_dmabuf.c
@@ -94,18 +94,6 @@ static void mock_dmabuf_vunmap(struct dma_buf *dma_buf, void *vaddr)
 	vm_unmap_ram(vaddr, mock->npages);
 }
 
-static void *mock_dmabuf_kmap_atomic(struct dma_buf *dma_buf, unsigned long page_num)
-{
-	struct mock_dmabuf *mock = to_mock(dma_buf);
-
-	return kmap_atomic(mock->pages[page_num]);
-}
-
-static void mock_dmabuf_kunmap_atomic(struct dma_buf *dma_buf, unsigned long page_num, void *addr)
-{
-	kunmap_atomic(addr);
-}
-
 static void *mock_dmabuf_kmap(struct dma_buf *dma_buf, unsigned long page_num)
 {
 	struct mock_dmabuf *mock = to_mock(dma_buf);
-- 
cgit v1.2.3


From 50896e180c6aa3a9c61a26ced99e15d602666a4c Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 13 Jun 2018 15:48:21 -0700
Subject: x86/speculation/l1tf: Increase 32bit PAE __PHYSICAL_PAGE_SHIFT

L1 Terminal Fault (L1TF) is a speculation related vulnerability. The CPU
speculates on PTE entries which do not have the PRESENT bit set, if the
content of the resulting physical address is available in the L1D cache.

The OS side mitigation makes sure that a !PRESENT PTE entry points to a
physical address outside the actually existing and cachable memory
space. This is achieved by inverting the upper bits of the PTE. Due to the
address space limitations this only works for 64bit and 32bit PAE kernels,
but not for 32bit non PAE.

This mitigation applies to both host and guest kernels, but in case of a
64bit host (hypervisor) and a 32bit PAE guest, inverting the upper bits of
the PAE address space (44bit) is not enough if the host has more than 43
bits of populated memory address space, because the speculation treats the
PTE content as a physical host address bypassing EPT.

The host (hypervisor) protects itself against the guest by flushing L1D as
needed, but pages inside the guest are not protected against attacks from
other processes inside the same guest.

For the guest the inverted PTE mask has to match the host to provide the
full protection for all pages the host could possibly map into the
guest. The hosts populated address space is not known to the guest, so the
mask must cover the possible maximal host address space, i.e. 52 bit.

On 32bit PAE the maximum PTE mask is currently set to 44 bit because that
is the limit imposed by 32bit unsigned long PFNs in the VMs. This limits
the mask to be below what the host could possible use for physical pages.

The L1TF PROT_NONE protection code uses the PTE masks to determine which
bits to invert to make sure the higher bits are set for unmapped entries to
prevent L1TF speculation attacks against EPT inside guests.

In order to invert all bits that could be used by the host, increase
__PHYSICAL_PAGE_SHIFT to 52 to match 64bit.

The real limit for a 32bit PAE kernel is still 44 bits because all Linux
PTEs are created from unsigned long PFNs, so they cannot be higher than 44
bits on a 32bit kernel. So these extra PFN bits should be never set. The
only users of this macro are using it to look at PTEs, so it's safe.

[ tglx: Massaged changelog ]

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/include/asm/page_32_types.h | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index aa30c3241ea7..0d5c739eebd7 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -29,8 +29,13 @@
 #define N_EXCEPTION_STACKS 1
 
 #ifdef CONFIG_X86_PAE
-/* 44=32+12, the limit we can fit into an unsigned long pfn */
-#define __PHYSICAL_MASK_SHIFT	44
+/*
+ * This is beyond the 44 bit limit imposed by the 32bit long pfns,
+ * but we need the full mask to make sure inverted PROT_NONE
+ * entries have all the host bits set in a guest.
+ * The real limit is still 44 bits.
+ */
+#define __PHYSICAL_MASK_SHIFT	52
 #define __VIRTUAL_MASK_SHIFT	32
 
 #else  /* !CONFIG_X86_PAE */
-- 
cgit v1.2.3


From bcd11afa7adad8d720e7ba5ef58bdcd9775cf45f Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 13 Jun 2018 15:48:22 -0700
Subject: x86/speculation/l1tf: Change order of offset/type in swap entry

If pages are swapped out, the swap entry is stored in the corresponding
PTE, which has the Present bit cleared. CPUs vulnerable to L1TF speculate
on PTE entries which have the present bit set and would treat the swap
entry as phsyical address (PFN). To mitigate that the upper bits of the PTE
must be set so the PTE points to non existent memory.

The swap entry stores the type and the offset of a swapped out page in the
PTE. type is stored in bit 9-13 and offset in bit 14-63. The hardware
ignores the bits beyond the phsyical address space limit, so to make the
mitigation effective its required to start 'offset' at the lowest possible
bit so that even large swap offsets do not reach into the physical address
space limit bits.

Move offset to bit 9-58 and type to bit 59-63 which are the bits that
hardware generally doesn't care about.

That, in turn, means that if you on desktop chip with only 40 bits of
physical addressing, now that the offset starts at bit 9, there needs to be
30 bits of offset actually *in use* until bit 39 ends up being set, which
means when inverted it will again point into existing memory.

So that's 4 terabyte of swap space (because the offset is counted in pages,
so 30 bits of offset is 42 bits of actual coverage). With bigger physical
addressing, that obviously grows further, until the limit of the offset is
hit (at 50 bits of offset - 62 bits of actual swap file coverage).

This is a preparatory change for the actual swap entry inversion to protect
against L1TF.

[ AK: Updated description and minor tweaks. Split into two parts ]
[ tglx: Massaged changelog ]

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/include/asm/pgtable_64.h | 31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 0fdcd21dadbd..cc26ea9fa288 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -273,7 +273,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | OFFSET (14->63) | TYPE (9-13)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) |  OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -287,19 +287,28 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
  */
-#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
-#define SWP_TYPE_BITS 5
-/* Place the offset above the type: */
-#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS)
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
-#define __swp_type(x)			(((x).val >> (SWP_TYPE_FIRST_BIT)) \
-					 & ((1U << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x)			((x).val >> SWP_OFFSET_FIRST_BIT)
-#define __swp_entry(type, offset)	((swp_entry_t) { \
-					 ((type) << (SWP_TYPE_FIRST_BIT)) \
-					 | ((offset) << SWP_OFFSET_FIRST_BIT) })
+/* Extract the high bits for type */
+#define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
+
+/* Shift up (to get rid of type), then down to get value */
+#define __swp_offset(x) ((x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+
+/*
+ * Shift the offset up "too far" by TYPE bits, then down again
+ */
+#define __swp_entry(type, offset) ((swp_entry_t) { \
+	((unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
+
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __pmd_to_swp_entry(pmd)		((swp_entry_t) { pmd_val((pmd)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
-- 
cgit v1.2.3


From 2f22b4cd45b67b3496f4aa4c7180a1271c6452f6 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 13 Jun 2018 15:48:23 -0700
Subject: x86/speculation/l1tf: Protect swap entries against L1TF

With L1 terminal fault the CPU speculates into unmapped PTEs, and resulting
side effects allow to read the memory the PTE is pointing too, if its
values are still in the L1 cache.

For swapped out pages Linux uses unmapped PTEs and stores a swap entry into
them.

To protect against L1TF it must be ensured that the swap entry is not
pointing to valid memory, which requires setting higher bits (between bit
36 and bit 45) that are inside the CPUs physical address space, but outside
any real memory.

To do this invert the offset to make sure the higher bits are always set,
as long as the swap file is not too big.

Note there is no workaround for 32bit !PAE, or on systems which have more
than MAX_PA/2 worth of memory. The later case is very unlikely to happen on
real systems.

[AK: updated description and minor tweaks by. Split out from the original
     patch ]

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/include/asm/pgtable_64.h | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index cc26ea9fa288..009d3be3cc19 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -273,7 +273,7 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2| 1|0| <- bit number
  * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names
- * | TYPE (59-63) |  OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
+ * | TYPE (59-63) | ~OFFSET (9-58)  |0|0|X|X| X| X|X|SD|0| <- swp entry
  *
  * G (8) is aliased and used as a PROT_NONE indicator for
  * !present ptes.  We need to start storing swap entries above
@@ -286,6 +286,9 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
  *
  * Bit 7 in swp entry should be 0 because pmd_present checks not only P,
  * but also L and G.
+ *
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
  */
 #define SWP_TYPE_BITS		5
 
@@ -300,13 +303,15 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS))
 
 /* Shift up (to get rid of type), then down to get value */
-#define __swp_offset(x) ((x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
+#define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT)
 
 /*
  * Shift the offset up "too far" by TYPE bits, then down again
+ * The offset is inverted by a binary not operation to make the high
+ * physical bits set.
  */
 #define __swp_entry(type, offset) ((swp_entry_t) { \
-	((unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	(~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
 	| ((unsigned long)(type) << (64-SWP_TYPE_BITS)) })
 
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
-- 
cgit v1.2.3


From 6b28baca9b1f0d4a42b865da7a05b1c81424bd5c Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 13 Jun 2018 15:48:24 -0700
Subject: x86/speculation/l1tf: Protect PROT_NONE PTEs against speculation

When PTEs are set to PROT_NONE the kernel just clears the Present bit and
preserves the PFN, which creates attack surface for L1TF speculation
speculation attacks.

This is important inside guests, because L1TF speculation bypasses physical
page remapping. While the host has its own migitations preventing leaking
data from other VMs into the guest, this would still risk leaking the wrong
page inside the current guest.

This uses the same technique as Linus' swap entry patch: while an entry is
is in PROTNONE state invert the complete PFN part part of it. This ensures
that the the highest bit will point to non existing memory.

The invert is done by pte/pmd_modify and pfn/pmd/pud_pte for PROTNONE and
pte/pmd/pud_pfn undo it.

This assume that no code path touches the PFN part of a PTE directly
without using these primitives.

This doesn't handle the case that MMIO is on the top of the CPU physical
memory. If such an MMIO region was exposed by an unpriviledged driver for
mmap it would be possible to attack some real memory.  However this
situation is all rather unlikely.

For 32bit non PAE the inversion is not done because there are really not
enough bits to protect anything.

Q: Why does the guest need to be protected when the HyperVisor already has
   L1TF mitigations?

A: Here's an example:

   Physical pages 1 2 get mapped into a guest as
   GPA 1 -> PA 2
   GPA 2 -> PA 1
   through EPT.

   The L1TF speculation ignores the EPT remapping.

   Now the guest kernel maps GPA 1 to process A and GPA 2 to process B, and
   they belong to different users and should be isolated.

   A sets the GPA 1 PA 2 PTE to PROT_NONE to bypass the EPT remapping and
   gets read access to the underlying physical page. Which in this case
   points to PA 2, so it can read process B's data, if it happened to be in
   L1, so isolation inside the guest is broken.

   There's nothing the hypervisor can do about this. This mitigation has to
   be done in the guest itself.

[ tglx: Massaged changelog ]

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/include/asm/pgtable-2level.h | 17 ++++++++++++++
 arch/x86/include/asm/pgtable-3level.h |  2 ++
 arch/x86/include/asm/pgtable-invert.h | 32 +++++++++++++++++++++++++
 arch/x86/include/asm/pgtable.h        | 44 ++++++++++++++++++++++++-----------
 arch/x86/include/asm/pgtable_64.h     |  2 ++
 5 files changed, 84 insertions(+), 13 deletions(-)
 create mode 100644 arch/x86/include/asm/pgtable-invert.h

diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 685ffe8a0eaf..60d0f9015317 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -95,4 +95,21 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 
+/* No inverted PFNs on 2 level page tables */
+
+static inline u64 protnone_mask(u64 val)
+{
+	return 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	return val;
+}
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return false;
+}
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index f24df59c40b2..76ab26a99e6e 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -295,4 +295,6 @@ static inline pte_t gup_get_pte(pte_t *ptep)
 	return pte;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* _ASM_X86_PGTABLE_3LEVEL_H */
diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h
new file mode 100644
index 000000000000..177564187fc0
--- /dev/null
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_PGTABLE_INVERT_H
+#define _ASM_PGTABLE_INVERT_H 1
+
+#ifndef __ASSEMBLY__
+
+static inline bool __pte_needs_invert(u64 val)
+{
+	return (val & (_PAGE_PRESENT|_PAGE_PROTNONE)) == _PAGE_PROTNONE;
+}
+
+/* Get a mask to xor with the page table entry to get the correct pfn. */
+static inline u64 protnone_mask(u64 val)
+{
+	return __pte_needs_invert(val) ?  ~0ull : 0;
+}
+
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask)
+{
+	/*
+	 * When a PTE transitions from NONE to !NONE or vice-versa
+	 * invert the PFN part to stop speculation.
+	 * pte_pfn undoes this when needed.
+	 */
+	if (__pte_needs_invert(oldval) != __pte_needs_invert(val))
+		val = (val & ~mask) | (~val & mask);
+	return val;
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 99ecde23c3ec..a9c89cb1a9c5 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -185,19 +185,29 @@ static inline int pte_special(pte_t pte)
 	return pte_flags(pte) & _PAGE_SPECIAL;
 }
 
+/* Entries that were set to PROT_NONE are inverted */
+
+static inline u64 protnone_mask(u64 val);
+
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	return (pte_val(pte) & PTE_PFN_MASK) >> PAGE_SHIFT;
+	unsigned long pfn = pte_val(pte);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	return (pmd_val(pmd) & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
+	unsigned long pfn = pmd_val(pmd);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	return (pud_val(pud) & pud_pfn_mask(pud)) >> PAGE_SHIFT;
+	unsigned long pfn = pud_val(pud);
+	pfn ^= protnone_mask(pfn);
+	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long p4d_pfn(p4d_t p4d)
@@ -545,25 +555,33 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot)
 
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pte(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PTE_PFN_MASK;
+	return __pte(pfn | check_pgprot(pgprot));
 }
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pmd(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PMD_PAGE_MASK;
+	return __pmd(pfn | check_pgprot(pgprot));
 }
 
 static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 {
-	return __pud(((phys_addr_t)page_nr << PAGE_SHIFT) |
-		     check_pgprot(pgprot));
+	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	pfn ^= protnone_mask(pgprot_val(pgprot));
+	pfn &= PHYSICAL_PUD_PAGE_MASK;
+	return __pud(pfn | check_pgprot(pgprot));
 }
 
+static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
+
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
-	pteval_t val = pte_val(pte);
+	pteval_t val = pte_val(pte), oldval = val;
 
 	/*
 	 * Chop off the NX bit (if present), and add the NX portion of
@@ -571,17 +589,17 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 	 */
 	val &= _PAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_PAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PTE_PFN_MASK);
 	return __pte(val);
 }
 
 static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot)
 {
-	pmdval_t val = pmd_val(pmd);
+	pmdval_t val = pmd_val(pmd), oldval = val;
 
 	val &= _HPAGE_CHG_MASK;
 	val |= check_pgprot(newprot) & ~_HPAGE_CHG_MASK;
-
+	val = flip_protnone_guard(oldval, val, PHYSICAL_PMD_PAGE_MASK);
 	return __pmd(val);
 }
 
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 009d3be3cc19..3c687e9a95a4 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -357,5 +357,7 @@ static inline bool gup_fast_permitted(unsigned long start, int nr_pages,
 	return true;
 }
 
+#include <asm/pgtable-invert.h>
+
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_X86_PGTABLE_64_H */
-- 
cgit v1.2.3


From 10a70416e1f067f6c4efda6ffd8ea96002ac4223 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 13 Jun 2018 15:48:25 -0700
Subject: x86/speculation/l1tf: Make sure the first page is always reserved

The L1TF workaround doesn't make any attempt to mitigate speculate accesses
to the first physical page for zeroed PTEs. Normally it only contains some
data from the early real mode BIOS.

It's not entirely clear that the first page is reserved in all
configurations, so add an extra reservation call to make sure it is really
reserved. In most configurations (e.g.  with the standard reservations)
it's likely a nop.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/kernel/setup.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2f86d883dd95..74b4472ba0a6 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -823,6 +823,12 @@ void __init setup_arch(char **cmdline_p)
 	memblock_reserve(__pa_symbol(_text),
 			 (unsigned long)__bss_stop - (unsigned long)_text);
 
+	/*
+	 * Make sure page 0 is always reserved because on systems with
+	 * L1TF its contents can be leaked to user processes.
+	 */
+	memblock_reserve(0, PAGE_SIZE);
+
 	early_reserve_initrd();
 
 	/*
-- 
cgit v1.2.3


From 17dbca119312b4e8173d4e25ff64262119fcef38 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 13 Jun 2018 15:48:26 -0700
Subject: x86/speculation/l1tf: Add sysfs reporting for l1tf

L1TF core kernel workarounds are cheap and normally always enabled, However
they still should be reported in sysfs if the system is vulnerable or
mitigated. Add the necessary CPU feature/bug bits.

- Extend the existing checks for Meltdowns to determine if the system is
  vulnerable. All CPUs which are not vulnerable to Meltdown are also not
  vulnerable to L1TF

- Check for 32bit non PAE and emit a warning as there is no practical way
  for mitigation due to the limited physical address bits

- If the system has more than MAX_PA/2 physical memory the invert page
  workarounds don't protect the system against the L1TF attack anymore,
  because an inverted physical address will also point to valid
  memory. Print a warning in this case and report that the system is
  vulnerable.

Add a function which returns the PFN limit for the L1TF mitigation, which
will be used in follow up patches for sanity and range checks.

[ tglx: Renamed the CPU feature bit to L1TF_PTEINV ]

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/include/asm/cpufeatures.h |  2 ++
 arch/x86/include/asm/processor.h   |  5 +++++
 arch/x86/kernel/cpu/bugs.c         | 40 ++++++++++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/common.c       | 20 +++++++++++++++++++
 drivers/base/cpu.c                 |  8 ++++++++
 include/linux/cpu.h                |  2 ++
 6 files changed, 77 insertions(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..f41cf9df4a83 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,7 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -373,5 +374,6 @@
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cfd29ee8c3da..7e3ac5eedcd6 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -181,6 +181,11 @@ extern const struct seq_operations cpuinfo_op;
 
 extern void cpu_detect(struct cpuinfo_x86 *c);
 
+static inline unsigned long l1tf_pfn_limit(void)
+{
+	return BIT(boot_cpu_data.x86_phys_bits - 1 - PAGE_SHIFT) - 1;
+}
+
 extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index cd0fda1fff6d..3ce9674e4887 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -27,9 +27,11 @@
 #include <asm/pgtable.h>
 #include <asm/set_memory.h>
 #include <asm/intel-family.h>
+#include <asm/e820/api.h>
 
 static void __init spectre_v2_select_mitigation(void);
 static void __init ssb_select_mitigation(void);
+static void __init l1tf_select_mitigation(void);
 
 /*
  * Our boot-time value of the SPEC_CTRL MSR. We read it once so that any
@@ -81,6 +83,8 @@ void __init check_bugs(void)
 	 */
 	ssb_select_mitigation();
 
+	l1tf_select_mitigation();
+
 #ifdef CONFIG_X86_32
 	/*
 	 * Check whether we are able to run this kernel safely on SMP.
@@ -205,6 +209,32 @@ static void x86_amd_ssb_disable(void)
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
+static void __init l1tf_select_mitigation(void)
+{
+	u64 half_pa;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+#if CONFIG_PGTABLE_LEVELS == 2
+	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+	return;
+#endif
+
+	/*
+	 * This is extremely unlikely to happen because almost all
+	 * systems have far more MAX_PA/2 than RAM can be fit into
+	 * DIMM slots.
+	 */
+	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
+		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
+		return;
+	}
+
+	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
+}
+
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 
@@ -678,6 +708,11 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_SPEC_STORE_BYPASS:
 		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
 
+	case X86_BUG_L1TF:
+		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
+			return sprintf(buf, "Mitigation: Page Table Inversion\n");
+		break;
+
 	default:
 		break;
 	}
@@ -704,4 +739,9 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute *
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_SPEC_STORE_BYPASS);
 }
+
+ssize_t cpu_show_l1tf(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_L1TF);
+}
 #endif
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0df7151cfef4..9baf684e2b55 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -984,6 +984,21 @@ static const __initconst struct x86_cpu_id cpu_no_spec_store_bypass[] = {
 	{}
 };
 
+static const __initconst struct x86_cpu_id cpu_no_l1tf[] = {
+	/* in addition to cpu_no_speculation */
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT1	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_SILVERMONT2	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_AIRMONT		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MERRIFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_MOOREFIELD	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GOLDMONT	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_DENVERTON	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_ATOM_GEMINI_LAKE	},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNL		},
+	{ X86_VENDOR_INTEL,	6,	INTEL_FAM6_XEON_PHI_KNM		},
+	{}
+};
+
 static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 {
 	u64 ia32_cap = 0;
@@ -1010,6 +1025,11 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 		return;
 
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
+
+	if (x86_match_cpu(cpu_no_l1tf))
+		return;
+
+	setup_force_cpu_bug(X86_BUG_L1TF);
 }
 
 /*
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 30cc9c877ebb..eb9443d5bae1 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -540,16 +540,24 @@ ssize_t __weak cpu_show_spec_store_bypass(struct device *dev,
 	return sprintf(buf, "Not affected\n");
 }
 
+ssize_t __weak cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sprintf(buf, "Not affected\n");
+}
+
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
 static DEVICE_ATTR(spectre_v2, 0444, cpu_show_spectre_v2, NULL);
 static DEVICE_ATTR(spec_store_bypass, 0444, cpu_show_spec_store_bypass, NULL);
+static DEVICE_ATTR(l1tf, 0444, cpu_show_l1tf, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
 	&dev_attr_spectre_v1.attr,
 	&dev_attr_spectre_v2.attr,
 	&dev_attr_spec_store_bypass.attr,
+	&dev_attr_l1tf.attr,
 	NULL
 };
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index a97a63eef59f..d3da5184aa1c 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -55,6 +55,8 @@ extern ssize_t cpu_show_spectre_v2(struct device *dev,
 				   struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_spec_store_bypass(struct device *dev,
 					  struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_l1tf(struct device *dev,
+			     struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
-- 
cgit v1.2.3


From 42e4089c7890725fcd329999252dc489b72f2921 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 13 Jun 2018 15:48:27 -0700
Subject: x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE
 mappings

For L1TF PROT_NONE mappings are protected by inverting the PFN in the page
table entry. This sets the high bits in the CPU's address space, thus
making sure to point to not point an unmapped entry to valid cached memory.

Some server system BIOSes put the MMIO mappings high up in the physical
address space. If such an high mapping was mapped to unprivileged users
they could attack low memory by setting such a mapping to PROT_NONE. This
could happen through a special device driver which is not access
protected. Normal /dev/mem is of course access protected.

To avoid this forbid PROT_NONE mappings or mprotect for high MMIO mappings.

Valid page mappings are allowed because the system is then unsafe anyways.

It's not expected that users commonly use PROT_NONE on MMIO. But to
minimize any impact this is only enforced if the mapping actually refers to
a high MMIO address (defined as the MAX_PA-1 bit being set), and also skip
the check for root.

For mmaps this is straight forward and can be handled in vm_insert_pfn and
in remap_pfn_range().

For mprotect it's a bit trickier. At the point where the actual PTEs are
accessed a lot of state has been changed and it would be difficult to undo
on an error. Since this is a uncommon case use a separate early page talk
walk pass for MMIO PROT_NONE mappings that checks for this condition
early. For non MMIO and non PROT_NONE there are no changes.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/include/asm/pgtable.h |  8 +++++++
 arch/x86/mm/mmap.c             | 21 ++++++++++++++++++
 include/asm-generic/pgtable.h  | 12 +++++++++++
 mm/memory.c                    | 37 ++++++++++++++++++++++---------
 mm/mprotect.c                  | 49 ++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 117 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index a9c89cb1a9c5..6a090a76fdca 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1338,6 +1338,14 @@ static inline bool pud_access_permitted(pud_t pud, bool write)
 	return __pte_access_permitted(pud_val(pud), write);
 }
 
+#define __HAVE_ARCH_PFN_MODIFY_ALLOWED 1
+extern bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot);
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return boot_cpu_has_bug(X86_BUG_L1TF);
+}
+
 #include <asm-generic/pgtable.h>
 #endif	/* __ASSEMBLY__ */
 
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 48c591251600..f40ab8185d94 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -240,3 +240,24 @@ int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
 
 	return phys_addr_valid(addr + count - 1);
 }
+
+/*
+ * Only allow root to set high MMIO mappings to PROT_NONE.
+ * This prevents an unpriv. user to set them to PROT_NONE and invert
+ * them, then pointing to valid memory for L1TF speculation.
+ *
+ * Note: for locked down kernels may want to disable the root override.
+ */
+bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return true;
+	if (!__pte_needs_invert(pgprot_val(prot)))
+		return true;
+	/* If it's real memory always allow */
+	if (pfn_valid(pfn))
+		return true;
+	if (pfn > l1tf_pfn_limit() && !capable(CAP_SYS_ADMIN))
+		return false;
+	return true;
+}
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f59639afaa39..0ecc1197084b 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1097,4 +1097,16 @@ static inline void init_espfix_bsp(void) { }
 #endif
 #endif
 
+#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
+static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	return true;
+}
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return false;
+}
+#endif
+
 #endif /* _ASM_GENERIC_PGTABLE_H */
diff --git a/mm/memory.c b/mm/memory.c
index 7206a634270b..3ba81b44a542 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1886,6 +1886,9 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
 
+	if (!pfn_modify_allowed(pfn, pgprot))
+		return -EACCES;
+
 	track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV));
 
 	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot,
@@ -1921,6 +1924,9 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 
 	track_pfn_insert(vma, &pgprot, pfn);
 
+	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
+		return -EACCES;
+
 	/*
 	 * If we don't have pte special, then we have to use the pfn_valid()
 	 * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
@@ -1982,6 +1988,7 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 {
 	pte_t *pte;
 	spinlock_t *ptl;
+	int err = 0;
 
 	pte = pte_alloc_map_lock(mm, pmd, addr, &ptl);
 	if (!pte)
@@ -1989,12 +1996,16 @@ static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	arch_enter_lazy_mmu_mode();
 	do {
 		BUG_ON(!pte_none(*pte));
+		if (!pfn_modify_allowed(pfn, prot)) {
+			err = -EACCES;
+			break;
+		}
 		set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot)));
 		pfn++;
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 	arch_leave_lazy_mmu_mode();
 	pte_unmap_unlock(pte - 1, ptl);
-	return 0;
+	return err;
 }
 
 static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
@@ -2003,6 +2014,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 {
 	pmd_t *pmd;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pmd = pmd_alloc(mm, pud, addr);
@@ -2011,9 +2023,10 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	VM_BUG_ON(pmd_trans_huge(*pmd));
 	do {
 		next = pmd_addr_end(addr, end);
-		if (remap_pte_range(mm, pmd, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pte_range(mm, pmd, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pmd++, addr = next, addr != end);
 	return 0;
 }
@@ -2024,6 +2037,7 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 {
 	pud_t *pud;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	pud = pud_alloc(mm, p4d, addr);
@@ -2031,9 +2045,10 @@ static inline int remap_pud_range(struct mm_struct *mm, p4d_t *p4d,
 		return -ENOMEM;
 	do {
 		next = pud_addr_end(addr, end);
-		if (remap_pmd_range(mm, pud, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pmd_range(mm, pud, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (pud++, addr = next, addr != end);
 	return 0;
 }
@@ -2044,6 +2059,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 {
 	p4d_t *p4d;
 	unsigned long next;
+	int err;
 
 	pfn -= addr >> PAGE_SHIFT;
 	p4d = p4d_alloc(mm, pgd, addr);
@@ -2051,9 +2067,10 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
 		return -ENOMEM;
 	do {
 		next = p4d_addr_end(addr, end);
-		if (remap_pud_range(mm, p4d, addr, next,
-				pfn + (addr >> PAGE_SHIFT), prot))
-			return -ENOMEM;
+		err = remap_pud_range(mm, p4d, addr, next,
+				pfn + (addr >> PAGE_SHIFT), prot);
+		if (err)
+			return err;
 	} while (p4d++, addr = next, addr != end);
 	return 0;
 }
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 625608bc8962..6d331620b9e5 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -306,6 +306,42 @@ unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
 	return pages;
 }
 
+static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
+			       unsigned long next, struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
+				   unsigned long addr, unsigned long next,
+				   struct mm_walk *walk)
+{
+	return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
+		0 : -EACCES;
+}
+
+static int prot_none_test(unsigned long addr, unsigned long next,
+			  struct mm_walk *walk)
+{
+	return 0;
+}
+
+static int prot_none_walk(struct vm_area_struct *vma, unsigned long start,
+			   unsigned long end, unsigned long newflags)
+{
+	pgprot_t new_pgprot = vm_get_page_prot(newflags);
+	struct mm_walk prot_none_walk = {
+		.pte_entry = prot_none_pte_entry,
+		.hugetlb_entry = prot_none_hugetlb_entry,
+		.test_walk = prot_none_test,
+		.mm = current->mm,
+		.private = &new_pgprot,
+	};
+
+	return walk_page_range(start, end, &prot_none_walk);
+}
+
 int
 mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 	unsigned long start, unsigned long end, unsigned long newflags)
@@ -323,6 +359,19 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
 		return 0;
 	}
 
+	/*
+	 * Do PROT_NONE PFN permission checks here when we can still
+	 * bail out without undoing a lot of state. This is a rather
+	 * uncommon case, so doesn't need to be very optimized.
+	 */
+	if (arch_has_pfn_modify_check() &&
+	    (vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
+	    (newflags & (VM_READ|VM_WRITE|VM_EXEC)) == 0) {
+		error = prot_none_walk(vma, start, end, newflags);
+		if (error)
+			return error;
+	}
+
 	/*
 	 * If we make a private mapping writable we increase our commit;
 	 * but (without finer accounting) cannot reduce our commit if we
-- 
cgit v1.2.3


From 377eeaa8e11fe815b1d07c81c4a0e2843a8c15eb Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Wed, 13 Jun 2018 15:48:28 -0700
Subject: x86/speculation/l1tf: Limit swap file size to MAX_PA/2

For the L1TF workaround its necessary to limit the swap file size to below
MAX_PA/2, so that the higher bits of the swap offset inverted never point
to valid memory.

Add a mechanism for the architecture to override the swap file size check
in swapfile.c and add a x86 specific max swapfile check function that
enforces that limit.

The check is only enabled if the CPU is vulnerable to L1TF.

In VMs with 42bit MAX_PA the typical limit is 2TB now, on a native system
with 46bit PA it is 32TB. The limit is only per individual swap file, so
it's always possible to exceed these limits with multiple swap files or
partitions.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
---
 arch/x86/mm/init.c       | 15 +++++++++++++++
 include/linux/swapfile.h |  2 ++
 mm/swapfile.c            | 46 ++++++++++++++++++++++++++++++----------------
 3 files changed, 47 insertions(+), 16 deletions(-)

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cee58a972cb2..1b530197d114 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -4,6 +4,8 @@
 #include <linux/swap.h>
 #include <linux/memblock.h>
 #include <linux/bootmem.h>	/* for max_low_pfn */
+#include <linux/swapfile.h>
+#include <linux/swapops.h>
 
 #include <asm/set_memory.h>
 #include <asm/e820/api.h>
@@ -880,3 +882,16 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
 	__cachemode2pte_tbl[cache] = __cm_idx2pte(entry);
 	__pte2cachemode_tbl[entry] = cache;
 }
+
+unsigned long max_swapfile_size(void)
+{
+	unsigned long pages;
+
+	pages = generic_max_swapfile_size();
+
+	if (boot_cpu_has_bug(X86_BUG_L1TF)) {
+		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
+		pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages);
+	}
+	return pages;
+}
diff --git a/include/linux/swapfile.h b/include/linux/swapfile.h
index 06bd7b096167..e06febf62978 100644
--- a/include/linux/swapfile.h
+++ b/include/linux/swapfile.h
@@ -10,5 +10,7 @@ extern spinlock_t swap_lock;
 extern struct plist_head swap_active_head;
 extern struct swap_info_struct *swap_info[];
 extern int try_to_unuse(unsigned int, bool, unsigned long);
+extern unsigned long generic_max_swapfile_size(void);
+extern unsigned long max_swapfile_size(void);
 
 #endif /* _LINUX_SWAPFILE_H */
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2cc2972eedaf..18185ae4f223 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2909,6 +2909,35 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode)
 	return 0;
 }
 
+
+/*
+ * Find out how many pages are allowed for a single swap device. There
+ * are two limiting factors:
+ * 1) the number of bits for the swap offset in the swp_entry_t type, and
+ * 2) the number of bits in the swap pte, as defined by the different
+ * architectures.
+ *
+ * In order to find the largest possible bit mask, a swap entry with
+ * swap type 0 and swap offset ~0UL is created, encoded to a swap pte,
+ * decoded to a swp_entry_t again, and finally the swap offset is
+ * extracted.
+ *
+ * This will mask all the bits from the initial ~0UL mask that can't
+ * be encoded in either the swp_entry_t or the architecture definition
+ * of a swap pte.
+ */
+unsigned long generic_max_swapfile_size(void)
+{
+	return swp_offset(pte_to_swp_entry(
+			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+}
+
+/* Can be overridden by an architecture for additional checks. */
+__weak unsigned long max_swapfile_size(void)
+{
+	return generic_max_swapfile_size();
+}
+
 static unsigned long read_swap_header(struct swap_info_struct *p,
 					union swap_header *swap_header,
 					struct inode *inode)
@@ -2944,22 +2973,7 @@ static unsigned long read_swap_header(struct swap_info_struct *p,
 	p->cluster_next = 1;
 	p->cluster_nr = 0;
 
-	/*
-	 * Find out how many pages are allowed for a single swap
-	 * device. There are two limiting factors: 1) the number
-	 * of bits for the swap offset in the swp_entry_t type, and
-	 * 2) the number of bits in the swap pte as defined by the
-	 * different architectures. In order to find the
-	 * largest possible bit mask, a swap entry with swap type 0
-	 * and swap offset ~0UL is created, encoded to a swap pte,
-	 * decoded to a swp_entry_t again, and finally the swap
-	 * offset is extracted. This will mask all the bits from
-	 * the initial ~0UL mask that can't be encoded in either
-	 * the swp_entry_t or the architecture definition of a
-	 * swap pte.
-	 */
-	maxpages = swp_offset(pte_to_swp_entry(
-			swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1;
+	maxpages = max_swapfile_size();
 	last_page = swap_header->info.last_page;
 	if (!last_page) {
 		pr_warn("Empty swap-file\n");
-- 
cgit v1.2.3


From 98fa2aecb5096bbeb18f6509ffd181aafe4d267d Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Mon, 18 Jun 2018 15:02:07 -0700
Subject: drm/i915/psr: Fix warning in intel_psr_activate()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

commit 5422b37c907e ("drm/i915/psr: Kill delays when activating psr
back.") removed the call to cancel a scheduled psr_work from
psr_disable() and instead added an early return in the work function. But,
if the scheduled work item is executed after psr_enable(), we end up
printing warnings as PSR is already enabled and active. So, put the
cancel_work call back in psr_disable().

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Fixes: 5422b37c907e ("drm/i915/psr: Kill delays when activating psr back.")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106948
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618220207.2778-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index ef0f4741a95d..d4cd19fea148 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -754,6 +754,7 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 
 	dev_priv->psr.enabled = NULL;
 	mutex_unlock(&dev_priv->psr.lock);
+	cancel_work_sync(&dev_priv->psr.work);
 }
 
 static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From c238ad62588981b3e83e1ba41bf5ec57b8875dd4 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 20 Jun 2018 14:25:43 +0100
Subject: drm/i915/psr: fix copy-paste error with setting of tp2_wakeup_time_us

Currently for the psr_table->tp2_tp3_wakeup_time case 3 there appears
to be a copy-paste error from the previous switch statement where
dev_priv->vbt.psr.tp1_wakeup_time_us is being assigned and I believe
it should be dev_priv->vbt.psr.tp2_tp3_wakeup_time_us that should be
assigned instead.

Detected by CoverityScan, CID#1470105 ("Copy-paste error")

Fixes: 77312ae8f071 ("drm/i915/psr: vbt change for psr")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180620132543.28092-1-colin.king@canonical.com
---
 drivers/gpu/drm/i915/intel_bios.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 03f04b472394..1faa494e2bc9 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -740,7 +740,7 @@ parse_psr(struct drm_i915_private *dev_priv, const struct bdb_header *bdb)
 			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 100;
 			break;
 		case 3:
-			dev_priv->vbt.psr.tp1_wakeup_time_us = 0;
+			dev_priv->vbt.psr.tp2_tp3_wakeup_time_us = 0;
 			break;
 		default:
 			DRM_DEBUG_KMS("VBT tp2_tp3 wakeup time value %d is outside range[0-3], defaulting to max value 2500us\n",
-- 
cgit v1.2.3


From cd9e11a8bf259550577e2df7163d43a8a5655739 Mon Sep 17 00:00:00 2001
From: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Date: Mon, 21 May 2018 17:25:51 -0700
Subject: drm/i915/icl: Add 10-bit support for hdmi
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Starting Icelake silicon supports 10-bpc hdmi to support certain
media workloads. Currently hdmi supports 8 and 12 bpc. Plumbed
in support for 10 bit hdmi.

Cc: James Ausmus <james.ausmus@intel.com>
Cc: Jani Nikula <jani.nikula@linux.intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180522002558.29262-18-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/intel_hdmi.c | 64 +++++++++++++++++++++++++++++----------
 1 file changed, 48 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index 8398d4b31712..98ad4313d9f2 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -1566,14 +1566,23 @@ intel_hdmi_mode_valid(struct drm_connector *connector,
 	/* check if we can do 8bpc */
 	status = hdmi_port_clock_valid(hdmi, clock, true, force_dvi);
 
-	/* if we can't do 8bpc we may still be able to do 12bpc */
-	if (!HAS_GMCH_DISPLAY(dev_priv) && status != MODE_OK && hdmi->has_hdmi_sink && !force_dvi)
-		status = hdmi_port_clock_valid(hdmi, clock * 3 / 2, true, force_dvi);
+	if (hdmi->has_hdmi_sink && !force_dvi) {
+		/* if we can't do 8bpc we may still be able to do 12bpc */
+		if (status != MODE_OK && !HAS_GMCH_DISPLAY(dev_priv))
+			status = hdmi_port_clock_valid(hdmi, clock * 3 / 2,
+						       true, force_dvi);
+
+		/* if we can't do 8,12bpc we may still be able to do 10bpc */
+		if (status != MODE_OK && INTEL_GEN(dev_priv) >= 11)
+			status = hdmi_port_clock_valid(hdmi, clock * 5 / 4,
+						       true, force_dvi);
+	}
 
 	return status;
 }
 
-static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
+static bool hdmi_deep_color_possible(const struct intel_crtc_state *crtc_state,
+				     int bpc)
 {
 	struct drm_i915_private *dev_priv =
 		to_i915(crtc_state->base.crtc->dev);
@@ -1585,6 +1594,9 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 	if (HAS_GMCH_DISPLAY(dev_priv))
 		return false;
 
+	if (bpc == 10 && INTEL_GEN(dev_priv) < 11)
+		return false;
+
 	if (crtc_state->pipe_bpp <= 8*3)
 		return false;
 
@@ -1592,7 +1604,7 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 		return false;
 
 	/*
-	 * HDMI 12bpc affects the clocks, so it's only possible
+	 * HDMI deep color affects the clocks, so it's only possible
 	 * when not cloning with other encoder types.
 	 */
 	if (crtc_state->output_types != 1 << INTEL_OUTPUT_HDMI)
@@ -1607,16 +1619,24 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 		if (crtc_state->ycbcr420) {
 			const struct drm_hdmi_info *hdmi = &info->hdmi;
 
-			if (!(hdmi->y420_dc_modes & DRM_EDID_YCBCR420_DC_36))
+			if (bpc == 12 && !(hdmi->y420_dc_modes &
+					   DRM_EDID_YCBCR420_DC_36))
+				return false;
+			else if (bpc == 10 && !(hdmi->y420_dc_modes &
+						DRM_EDID_YCBCR420_DC_30))
 				return false;
 		} else {
-			if (!(info->edid_hdmi_dc_modes & DRM_EDID_HDMI_DC_36))
+			if (bpc == 12 && !(info->edid_hdmi_dc_modes &
+					   DRM_EDID_HDMI_DC_36))
+				return false;
+			else if (bpc == 10 && !(info->edid_hdmi_dc_modes &
+						DRM_EDID_HDMI_DC_30))
 				return false;
 		}
 	}
 
 	/* Display WA #1139: glk */
-	if (IS_GLK_REVID(dev_priv, 0, GLK_REVID_A1) &&
+	if (bpc == 12 && IS_GLK_REVID(dev_priv, 0, GLK_REVID_A1) &&
 	    crtc_state->base.adjusted_mode.htotal > 5460)
 		return false;
 
@@ -1626,7 +1646,8 @@ static bool hdmi_12bpc_possible(const struct intel_crtc_state *crtc_state)
 static bool
 intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 			   struct intel_crtc_state *config,
-			   int *clock_12bpc, int *clock_8bpc)
+			   int *clock_12bpc, int *clock_10bpc,
+			   int *clock_8bpc)
 {
 	struct intel_crtc *intel_crtc = to_intel_crtc(config->base.crtc);
 
@@ -1638,6 +1659,7 @@ intel_hdmi_ycbcr420_config(struct drm_connector *connector,
 	/* YCBCR420 TMDS rate requirement is half the pixel clock */
 	config->port_clock /= 2;
 	*clock_12bpc /= 2;
+	*clock_10bpc /= 2;
 	*clock_8bpc /= 2;
 	config->ycbcr420 = true;
 
@@ -1665,6 +1687,7 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	struct intel_digital_connector_state *intel_conn_state =
 		to_intel_digital_connector_state(conn_state);
 	int clock_8bpc = pipe_config->base.adjusted_mode.crtc_clock;
+	int clock_10bpc = clock_8bpc * 5 / 4;
 	int clock_12bpc = clock_8bpc * 3 / 2;
 	int desired_bpp;
 	bool force_dvi = intel_conn_state->force_audio == HDMI_AUDIO_OFF_DVI;
@@ -1691,12 +1714,14 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLCLK) {
 		pipe_config->pixel_multiplier = 2;
 		clock_8bpc *= 2;
+		clock_10bpc *= 2;
 		clock_12bpc *= 2;
 	}
 
 	if (drm_mode_is_420_only(&connector->display_info, adjusted_mode)) {
 		if (!intel_hdmi_ycbcr420_config(connector, pipe_config,
-						&clock_12bpc, &clock_8bpc)) {
+						&clock_12bpc, &clock_10bpc,
+						&clock_8bpc)) {
 			DRM_ERROR("Can't support YCBCR420 output\n");
 			return false;
 		}
@@ -1714,18 +1739,25 @@ bool intel_hdmi_compute_config(struct intel_encoder *encoder,
 	}
 
 	/*
-	 * HDMI is either 12 or 8, so if the display lets 10bpc sneak
-	 * through, clamp it down. Note that g4x/vlv don't support 12bpc hdmi
-	 * outputs. We also need to check that the higher clock still fits
-	 * within limits.
+	 * Note that g4x/vlv don't support 12bpc hdmi outputs. We also need
+	 * to check that the higher clock still fits within limits.
 	 */
-	if (hdmi_12bpc_possible(pipe_config) &&
-	    hdmi_port_clock_valid(intel_hdmi, clock_12bpc, true, force_dvi) == MODE_OK) {
+	if (hdmi_deep_color_possible(pipe_config, 12) &&
+	    hdmi_port_clock_valid(intel_hdmi, clock_12bpc,
+				  true, force_dvi) == MODE_OK) {
 		DRM_DEBUG_KMS("picking bpc to 12 for HDMI output\n");
 		desired_bpp = 12*3;
 
 		/* Need to adjust the port link by 1.5x for 12bpc. */
 		pipe_config->port_clock = clock_12bpc;
+	} else if (hdmi_deep_color_possible(pipe_config, 10) &&
+		   hdmi_port_clock_valid(intel_hdmi, clock_10bpc,
+					 true, force_dvi) == MODE_OK) {
+		DRM_DEBUG_KMS("picking bpc to 10 for HDMI output\n");
+		desired_bpp = 10 * 3;
+
+		/* Need to adjust the port link by 1.25x for 10bpc. */
+		pipe_config->port_clock = clock_10bpc;
 	} else {
 		DRM_DEBUG_KMS("picking bpc to 8 for HDMI output\n");
 		desired_bpp = 8*3;
-- 
cgit v1.2.3


From e1cacec9d50d7299893eeab2d895189f3db625da Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Wed, 20 Jun 2018 14:10:48 -0700
Subject: drm/i915: Update DRIVER_DATE to 20180620

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ebece44a807f..735f695cb889 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -86,8 +86,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180606"
-#define DRIVER_TIMESTAMP	1528323047
+#define DRIVER_DATE		"20180620"
+#define DRIVER_TIMESTAMP	1529529048
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
-- 
cgit v1.2.3


From 26eb4cd6c7c7793ee76c73b66621f63daff51953 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 20 Jun 2018 14:59:29 +0100
Subject: drm/i915: Disable bh around call to tasklet
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The guc submission backends expects to only be run from (at least)
softirq context, but during our intel_engine_is_idle() check we would
call into the tasklet to make sure it was flushed. As this could occur
from process context, occasionally we would be caught out using a
wait_for_atomic() not from an atomic context:

[   59.939091] WARN_ON_ONCE((1) && !(preempt_count() != 0))
[   59.939142] WARNING: CPU: 1 PID: 2901 at drivers/gpu/drm/i915/intel_guc_submission.c:615 guc_submission_tasklet+0x784/0xa90 [i915]
[   59.939143] Modules linked in: vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic i915 x86_pkg_temp_thermal intel_powerclamp coretemp crct10dif_pclmul snd_hda_intel crc32_pclmul snd_hda_codec ghash_clmulni_intel snd_hwdep snd_hda_core e1000e snd_pcm mei_me mei prime_numbers
[   59.939164] CPU: 1 PID: 2901 Comm: gem_exec_schedu Tainted: G     U  W         4.18.0-rc1-g93475d62c730-drmtip_67+ #1
[   59.939165] Hardware name: System manufacturer System Product Name/Z170M-PLUS, BIOS 3610 03/29/2018
[   59.939188] RIP: 0010:guc_submission_tasklet+0x784/0xa90 [i915]
[   59.939189] Code: fc ff ff 80 3d 2f 87 11 00 00 0f 85 80 fb ff ff 48 c7 c6 f8 49 40 c0 48 c7 c7 80 41 3e c0 c6 05 14 87 11 00 01 e8 2c ea d6 d3 <0f> 0b e9 5f fb ff ff 8b 46 38 89 cf 31 c7 83 e7 c0 75 08 39 c1 0f
[   59.939253] RSP: 0018:ffffaafe08a03c10 EFLAGS: 00010286
[   59.939255] RAX: 0000000000000000 RBX: ffff8f9112c246f0 RCX: 0000000000000001
[   59.939256] RDX: 0000000080000001 RSI: ffffffff95086d8e RDI: 00000000ffffffff
[   59.939257] RBP: ffff8f9112c24680 R08: 000000009517be77 R09: 0000000000000000
[   59.939258] R10: 0000000000000000 R11: 0000000000000000 R12: ffff8f9112c24700
[   59.939259] R13: ffff8f9112c24700 R14: 0000000000000000 R15: ffff8f9112c242a8
[   59.939260] FS:  00007fc2cc7e5980(0000) GS:ffff8f9136c40000(0000) knlGS:0000000000000000
[   59.939261] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   59.939262] CR2: 00007fc2cc815040 CR3: 000000021f10e003 CR4: 00000000003606e0
[   59.939263] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[   59.939264] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[   59.939265] Call Trace:
[   59.939288]  ? intel_engine_is_idle+0x64/0x160 [i915]
[   59.939323]  ? intel_engine_dump+0x638/0x890 [i915]
[   59.939327]  ? seq_printf+0x49/0x70
[   59.939353]  ? i915_engine_info+0xc8/0x100 [i915]
[   59.939356]  ? drm_get_color_range_name+0x20/0x20
[   59.939361]  ? seq_read+0xf1/0x470
[   59.939365]  ? trace_hardirqs_on_caller+0xe0/0x1b0
[   59.939370]  ? full_proxy_read+0x51/0x80
[   59.939389]  ? __vfs_read+0x31/0x170
[   59.939395]  ? do_sys_open+0x13b/0x240
[   59.939398]  ? rcu_read_lock_sched_held+0x6f/0x80
[   59.939401]  ? vfs_read+0x9e/0x140
[   59.939404]  ? ksys_read+0x50/0xc0
[   59.939409]  ? do_syscall_64+0x55/0x190
[   59.939412]  ? entry_SYSCALL_64_after_hwframe+0x49/0xbe
[   59.939420] irq event stamp: 552834
[   59.939422] hardirqs last  enabled at (552833): [<ffffffff940fc74c>] console_unlock+0x3fc/0x600
[   59.939425] hardirqs last disabled at (552834): [<ffffffff94a0111c>] error_entry+0x7c/0x100
[   59.939451] softirqs last  enabled at (552614): [<ffffffffc02e0f53>] i915_request_add+0x2e3/0x7b0 [i915]
[   59.939470] softirqs last disabled at (552604): [<ffffffffc02e0ecb>] i915_request_add+0x25b/0x7b0 [i915]

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106977
Fixes: dd0cf235d81f ("drm/i915: Speed up idle detection by kicking the tasklets")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180620135929.23956-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 32bf3a408d46..d3264bd6e9dc 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1000,10 +1000,12 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	if (READ_ONCE(engine->execlists.active)) {
 		struct intel_engine_execlists *execlists = &engine->execlists;
 
+		local_bh_disable();
 		if (tasklet_trylock(&execlists->tasklet)) {
 			execlists->tasklet.func(execlists->tasklet.data);
 			tasklet_unlock(&execlists->tasklet);
 		}
+		local_bh_enable();
 
 		if (READ_ONCE(execlists->active))
 			return false;
-- 
cgit v1.2.3


From 56563f53d3066afa9e63d6c997bf67e76a8b05c0 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 20 Jun 2018 16:42:57 -0400
Subject: x86/bugs: Move the l1tf function and define pr_fmt properly

The pr_warn in l1tf_select_mitigation would have used the prior pr_fmt
which was defined as "Spectre V2 : ".

Move the function to be past SSBD and also define the pr_fmt.

Fixes: 17dbca119312 ("x86/speculation/l1tf: Add sysfs reporting for l1tf")
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/bugs.c | 55 ++++++++++++++++++++++++----------------------
 1 file changed, 29 insertions(+), 26 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 3ce9674e4887..50500cea6eba 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -209,32 +209,6 @@ static void x86_amd_ssb_disable(void)
 		wrmsrl(MSR_AMD64_LS_CFG, msrval);
 }
 
-static void __init l1tf_select_mitigation(void)
-{
-	u64 half_pa;
-
-	if (!boot_cpu_has_bug(X86_BUG_L1TF))
-		return;
-
-#if CONFIG_PGTABLE_LEVELS == 2
-	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
-	return;
-#endif
-
-	/*
-	 * This is extremely unlikely to happen because almost all
-	 * systems have far more MAX_PA/2 than RAM can be fit into
-	 * DIMM slots.
-	 */
-	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
-	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
-		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
-		return;
-	}
-
-	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
-}
-
 #ifdef RETPOLINE
 static bool spectre_v2_bad_module;
 
@@ -681,6 +655,35 @@ void x86_spec_ctrl_setup_ap(void)
 		x86_amd_ssb_disable();
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"L1TF: " fmt
+static void __init l1tf_select_mitigation(void)
+{
+	u64 half_pa;
+
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+#if CONFIG_PGTABLE_LEVELS == 2
+	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
+	return;
+#endif
+
+	/*
+	 * This is extremely unlikely to happen because almost all
+	 * systems have far more MAX_PA/2 than RAM can be fit into
+	 * DIMM slots.
+	 */
+	half_pa = (u64)l1tf_pfn_limit() << PAGE_SHIFT;
+	if (e820__mapped_any(half_pa, ULLONG_MAX - half_pa, E820_TYPE_RAM)) {
+		pr_warn("System has more than MAX_PA/2 memory. L1TF mitigation not effective.\n");
+		return;
+	}
+
+	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
+}
+#undef pr_fmt
+
 #ifdef CONFIG_SYSFS
 
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
-- 
cgit v1.2.3


From 827db9d8bb4a01314f214065e3f18c8345c5fc9f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 21 Jun 2018 08:32:05 +0100
Subject: drm/i915: Ignore applying the self-relocation BIAS if no relocations

We only need to apply the BIAS for self-relocations into the batchbuffer
iff the execobject has any relocations.

This suppresses some warnings we may get with a full gtt (so the batch
object has wound up at 0 from a previous invocation), but doesn't fix
the underlying problem of how we tried to move a pinned batch vma (how
we have a pinned user vma outside of execbuf, I do not know, though this
being on an aliasing ppgtt means it could be a spurious pinning via the
global gtt). One step at a time...

References: https://bugs.freedesktop.org/show_bug.cgi?id=106744#c1
Testcase: igt/gem_exec_gttfill # byt (sporadic)
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180621073205.26701-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 60dc2a865f5f..437441f4af41 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -534,7 +534,8 @@ eb_add_vma(struct i915_execbuffer *eb,
 	 * paranoia do it everywhere.
 	 */
 	if (i == batch_idx) {
-		if (!(eb->flags[i] & EXEC_OBJECT_PINNED))
+		if (entry->relocation_count &&
+		    !(eb->flags[i] & EXEC_OBJECT_PINNED))
 			eb->flags[i] |= __EXEC_OBJECT_NEEDS_BIAS;
 		if (eb->reloc_cache.has_fence)
 			eb->flags[i] |= EXEC_OBJECT_NEEDS_FENCE;
-- 
cgit v1.2.3


From d20ac620f0010f9cdcbbe8408e5f22aae3c49faa Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 21 Jun 2018 09:01:50 +0100
Subject: drm/i915: Redefine EINVAL for debugging

To aide debugging spurious EINVALs, include a debug message every time
we emit one from execbuf.

References: https://bugs.freedesktop.org/show_bug.cgi?id=106744
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180621080150.8110-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 437441f4af41..c2dd9b4cdace 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -66,6 +66,15 @@ enum {
 #define __I915_EXEC_ILLEGAL_FLAGS \
 	(__I915_EXEC_UNKNOWN_FLAGS | I915_EXEC_CONSTANTS_MASK)
 
+/* Catch emission of unexpected errors for CI! */
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM)
+#undef EINVAL
+#define EINVAL ({ \
+	DRM_DEBUG_DRIVER("EINVAL at %s:%d\n", __func__, __LINE__); \
+	22; \
+})
+#endif
+
 /**
  * DOC: User command execution
  *
-- 
cgit v1.2.3


From c612ae0503af753c062594dcd14aecea121fa414 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 20 Jun 2018 20:48:59 +0200
Subject: staging: android: ion: fix ion_dma_buf_attach signatur
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixup for "dma_buf: remove device parameter from attach callback v2".

I missed this driver, sorry for the noise. Patch is not even compile
tested.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/230641/
---
 drivers/staging/android/ion/ion.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index a5220445b5e8..3d4d35558937 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -201,7 +201,7 @@ struct ion_dma_buf_attachment {
 	struct list_head list;
 };
 
-static int ion_dma_buf_attach(struct dma_buf *dmabuf, struct device *dev,
+static int ion_dma_buf_attach(struct dma_buf *dmabuf,
 			      struct dma_buf_attachment *attachment)
 {
 	struct ion_dma_buf_attachment *a;
@@ -219,7 +219,7 @@ static int ion_dma_buf_attach(struct dma_buf *dmabuf, struct device *dev,
 	}
 
 	a->table = table;
-	a->dev = dev;
+	a->dev = attachment->dev;
 	INIT_LIST_HEAD(&a->list);
 
 	attachment->priv = a;
-- 
cgit v1.2.3


From bc8c9da5a24bb5087197820a2ccabd9c37627035 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:04:38 +0900
Subject: Documentation/kprobes: Remove jprobes related leftover

Remove 'jps' from the document, since jprobe got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942427814.15209.6650206464370123166.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/kprobes.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index cb3b0de83fc6..33dd6a81fb64 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -474,7 +474,7 @@ error occurs during registration, all probes in the array, up to
 the bad probe, are safely unregistered before the register_*probes
 function returns.
 
-- kps/rps/jps: an array of pointers to ``*probe`` data structures
+- kps/rps: an array of pointers to ``*probe`` data structures
 - num: the number of the array entries.
 
 .. note::
-- 
cgit v1.2.3


From 5a6cf77f5e35e7af35d36a1e7dc21a42f6412e4f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:05:07 +0900
Subject: kprobes: Remove jprobe API implementation

Remove functionally empty jprobe API implementations and test cases.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942430705.15209.2307050500995264322.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kprobes.h |  3 --
 kernel/kprobes.c        | 78 +---------------------------------------
 kernel/test_kprobes.c   | 94 -------------------------------------------------
 lib/Kconfig.debug       |  2 +-
 4 files changed, 2 insertions(+), 175 deletions(-)

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 9440a2fc8893..b520baa65682 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -389,9 +389,6 @@ int register_kprobe(struct kprobe *p);
 void unregister_kprobe(struct kprobe *p);
 int register_kprobes(struct kprobe **kps, int num);
 void unregister_kprobes(struct kprobe **kps, int num);
-int setjmp_pre_handler(struct kprobe *, struct pt_regs *);
-int longjmp_break_handler(struct kprobe *, struct pt_regs *);
-void jprobe_return(void);
 unsigned long arch_deref_entry_point(void *);
 
 int register_kretprobe(struct kretprobe *rp);
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ea619021d901..69de130595f7 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1272,7 +1272,7 @@ NOKPROBE_SYMBOL(cleanup_rp_inst);
 
 /*
 * Add the new probe to ap->list. Fail if this is the
-* second jprobe at the address - two jprobes can't coexist
+* second break_handler at the address
 */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
@@ -1812,77 +1812,6 @@ unsigned long __weak arch_deref_entry_point(void *entry)
 	return (unsigned long)entry;
 }
 
-#if 0
-int register_jprobes(struct jprobe **jps, int num)
-{
-	int ret = 0, i;
-
-	if (num <= 0)
-		return -EINVAL;
-
-	for (i = 0; i < num; i++) {
-		ret = register_jprobe(jps[i]);
-
-		if (ret < 0) {
-			if (i > 0)
-				unregister_jprobes(jps, i);
-			break;
-		}
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(register_jprobes);
-
-int register_jprobe(struct jprobe *jp)
-{
-	unsigned long addr, offset;
-	struct kprobe *kp = &jp->kp;
-
-	/*
-	 * Verify probepoint as well as the jprobe handler are
-	 * valid function entry points.
-	 */
-	addr = arch_deref_entry_point(jp->entry);
-
-	if (kallsyms_lookup_size_offset(addr, NULL, &offset) && offset == 0 &&
-	    kprobe_on_func_entry(kp->addr, kp->symbol_name, kp->offset)) {
-		kp->pre_handler = setjmp_pre_handler;
-		kp->break_handler = longjmp_break_handler;
-		return register_kprobe(kp);
-	}
-
-	return -EINVAL;
-}
-EXPORT_SYMBOL_GPL(register_jprobe);
-
-void unregister_jprobe(struct jprobe *jp)
-{
-	unregister_jprobes(&jp, 1);
-}
-EXPORT_SYMBOL_GPL(unregister_jprobe);
-
-void unregister_jprobes(struct jprobe **jps, int num)
-{
-	int i;
-
-	if (num <= 0)
-		return;
-	mutex_lock(&kprobe_mutex);
-	for (i = 0; i < num; i++)
-		if (__unregister_kprobe_top(&jps[i]->kp) < 0)
-			jps[i]->kp.addr = NULL;
-	mutex_unlock(&kprobe_mutex);
-
-	synchronize_sched();
-	for (i = 0; i < num; i++) {
-		if (jps[i]->kp.addr)
-			__unregister_kprobe_bottom(&jps[i]->kp);
-	}
-}
-EXPORT_SYMBOL_GPL(unregister_jprobes);
-#endif
-
 #ifdef CONFIG_KRETPROBES
 /*
  * This kprobe pre_handler is registered with every kretprobe. When probe
@@ -2329,8 +2258,6 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 
 	if (p->pre_handler == pre_handler_kretprobe)
 		kprobe_type = "r";
-	else if (p->pre_handler == setjmp_pre_handler)
-		kprobe_type = "j";
 	else
 		kprobe_type = "k";
 
@@ -2637,6 +2564,3 @@ late_initcall(debugfs_kprobe_init);
 #endif /* CONFIG_DEBUG_FS */
 
 module_init(init_kprobes);
-
-/* defined in arch/.../kernel/kprobes.c */
-EXPORT_SYMBOL_GPL(jprobe_return);
diff --git a/kernel/test_kprobes.c b/kernel/test_kprobes.c
index dd53e354f630..7bca480151b0 100644
--- a/kernel/test_kprobes.c
+++ b/kernel/test_kprobes.c
@@ -162,90 +162,6 @@ static int test_kprobes(void)
 
 }
 
-#if 0
-static u32 jph_val;
-
-static u32 j_kprobe_target(u32 value)
-{
-	if (preemptible()) {
-		handler_errors++;
-		pr_err("jprobe-handler is preemptible\n");
-	}
-	if (value != rand1) {
-		handler_errors++;
-		pr_err("incorrect value in jprobe handler\n");
-	}
-
-	jph_val = rand1;
-	jprobe_return();
-	return 0;
-}
-
-static struct jprobe jp = {
-	.entry		= j_kprobe_target,
-	.kp.symbol_name = "kprobe_target"
-};
-
-static int test_jprobe(void)
-{
-	int ret;
-
-	ret = register_jprobe(&jp);
-	if (ret < 0) {
-		pr_err("register_jprobe returned %d\n", ret);
-		return ret;
-	}
-
-	ret = target(rand1);
-	unregister_jprobe(&jp);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	return 0;
-}
-
-static struct jprobe jp2 = {
-	.entry          = j_kprobe_target,
-	.kp.symbol_name = "kprobe_target2"
-};
-
-static int test_jprobes(void)
-{
-	int ret;
-	struct jprobe *jps[2] = {&jp, &jp2};
-
-	/* addr and flags should be cleard for reusing kprobe. */
-	jp.kp.addr = NULL;
-	jp.kp.flags = 0;
-	ret = register_jprobes(jps, 2);
-	if (ret < 0) {
-		pr_err("register_jprobes returned %d\n", ret);
-		return ret;
-	}
-
-	jph_val = 0;
-	ret = target(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler not called\n");
-		handler_errors++;
-	}
-
-	jph_val = 0;
-	ret = target2(rand1);
-	if (jph_val == 0) {
-		pr_err("jprobe handler2 not called\n");
-		handler_errors++;
-	}
-	unregister_jprobes(jps, 2);
-
-	return 0;
-}
-#else
-#define test_jprobe() (0)
-#define test_jprobes() (0)
-#endif
 #ifdef CONFIG_KRETPROBES
 static u32 krph_val;
 
@@ -383,16 +299,6 @@ int init_test_probes(void)
 	if (ret < 0)
 		errors++;
 
-	num_tests++;
-	ret = test_jprobe();
-	if (ret < 0)
-		errors++;
-
-	num_tests++;
-	ret = test_jprobes();
-	if (ret < 0)
-		errors++;
-
 #ifdef CONFIG_KRETPROBES
 	num_tests++;
 	ret = test_kretprobe();
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8838d1158d19..0b066b3c9284 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1718,7 +1718,7 @@ config KPROBES_SANITY_TEST
 	default n
 	help
 	  This option provides for testing basic kprobes functionality on
-	  boot. A sample kprobe, jprobe and kretprobe are inserted and
+	  boot. Samples of kprobe and kretprobe are inserted and
 	  verified for functionality.
 
 	  Say N if you are unsure.
-- 
cgit v1.2.3


From 80006dbee674f9fa7c20a799d208657a18b5dabf Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:05:35 +0900
Subject: kprobes/x86: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/x86.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942433578.15209.14034551799624757792.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/kprobes.h |  3 --
 arch/x86/kernel/kprobes/core.c | 96 ++----------------------------------------
 2 files changed, 3 insertions(+), 96 deletions(-)

diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 367d99cff426..06782c2efa04 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -111,9 +111,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_old_flags;
 	unsigned long kprobe_saved_flags;
-	unsigned long *jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6f4d42377fe5..1b2d1acba810 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -66,8 +66,6 @@
 
 #include "common.h"
 
-void jprobe_return_end(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -690,10 +688,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 			/*
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
+			 * pre-handler and it returned non-zero, that means
+			 * user handler setup registers to exit to another
+			 * instruction, we must skip the single stepping.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
 				setup_singlestep(p, regs, kcb, 0);
@@ -1083,93 +1080,6 @@ int kprobe_exceptions_notify(struct notifier_block *self, unsigned long val,
 }
 NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = stack_addr(regs);
-	addr = (unsigned long)(kcb->jprobe_saved_sp);
-
-	/*
-	 * As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
-	 * Use __memcpy() to avoid KASAN stack out-of-bounds reports as we copy
-	 * raw stack chunk with redzones:
-	 */
-	__memcpy(kcb->jprobes_stack, (kprobe_opcode_t *)addr, MIN_STACK_SIZE(addr));
-	regs->ip = (unsigned long)(jp->entry);
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer to get messed up.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/* Unpoison stack redzones in the frames we are going to jump over. */
-	kasan_unpoison_stack_above_sp_to(kcb->jprobe_saved_sp);
-
-	asm volatile (
-#ifdef CONFIG_X86_64
-			"       xchg   %%rbx,%%rsp	\n"
-#else
-			"       xchgl   %%ebx,%%esp	\n"
-#endif
-			"       int3			\n"
-			"       .globl jprobe_return_end\n"
-			"       jprobe_return_end:	\n"
-			"       nop			\n"::"b"
-			(kcb->jprobe_saved_sp):"memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-NOKPROBE_SYMBOL(jprobe_return_end);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	u8 *addr = (u8 *) (regs->ip - 1);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	void *saved_sp = kcb->jprobe_saved_sp;
-
-	if ((addr > (u8 *) jprobe_return) &&
-	    (addr < (u8 *) jprobe_return_end)) {
-		if (stack_addr(regs) != saved_sp) {
-			struct pt_regs *saved_regs = &kcb->jprobe_saved_regs;
-			printk(KERN_ERR
-			       "current sp %p does not match saved sp %p\n",
-			       stack_addr(regs), saved_sp);
-			printk(KERN_ERR "Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk(KERN_ERR "Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		/* It's OK to start function graph tracing again */
-		unpause_graph_tracing();
-		*regs = kcb->jprobe_saved_regs;
-		__memcpy(saved_sp, kcb->jprobes_stack, MIN_STACK_SIZE(saved_sp));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	bool is_in_entry_trampoline_section = false;
-- 
cgit v1.2.3


From e00f1993e98b464bf530ba6ac5763b2ceccd2a1e Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:06:04 +0900
Subject: ARC/kprobes: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/arc.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-snps-arc@lists.infradead.org
Link: https://lore.kernel.org/lkml/152942436460.15209.3038881268172249579.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/include/asm/kprobes.h |  2 --
 arch/arc/kernel/kprobes.c      | 38 ++------------------------------------
 2 files changed, 2 insertions(+), 38 deletions(-)

diff --git a/arch/arc/include/asm/kprobes.h b/arch/arc/include/asm/kprobes.h
index 2e52d18e6bc7..2c1b479d5aea 100644
--- a/arch/arc/include/asm/kprobes.h
+++ b/arch/arc/include/asm/kprobes.h
@@ -45,8 +45,6 @@ struct prev_kprobe {
 
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 42b05046fad9..7811a6bbe8f0 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -225,10 +225,8 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
 
 		/* If we have no pre-handler or it returned 0, we continue with
 		 * normal processing. If we have a pre-handler and it returned
-		 * non-zero - which is expected from setjmp_pre_handler for
-		 * jprobe, we return without single stepping and leave that to
-		 * the break-handler which is invoked by a kprobe from
-		 * jprobe_return
+		 * non-zero - which means user handler setup registers to exit
+		 * to another instruction, we must skip the single stepping.
 		 */
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			setup_singlestep(p, regs);
@@ -386,38 +384,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long sp_addr = regs->sp;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ret = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	__asm__ __volatile__("unimp_s");
-	return;
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long sp_addr;
-
-	*regs = kcb->jprobe_saved_regs;
-	sp_addr = regs->sp;
-	memcpy((void *)sp_addr, kcb->jprobes_stack, MIN_STACK_SIZE(sp_addr));
-	preempt_enable_no_resched();
-
-	return 1;
-}
-
 static void __used kretprobe_trampoline_holder(void)
 {
 	__asm__ __volatile__(".global kretprobe_trampoline\n"
-- 
cgit v1.2.3


From 454f3e132d0520472558518df61ee14db1dbef88 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:06:34 +0900
Subject: ARM/kprobes: Remove jprobe arm implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/arm.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/lkml/152942439350.15209.11127640848082283736.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/kprobes.h |   2 -
 arch/arm/include/asm/probes.h  |   1 -
 arch/arm/probes/kprobes/core.c | 114 -----------------------------------------
 3 files changed, 117 deletions(-)

diff --git a/arch/arm/include/asm/kprobes.h b/arch/arm/include/asm/kprobes.h
index 59655459da59..82290f212d8e 100644
--- a/arch/arm/include/asm/kprobes.h
+++ b/arch/arm/include/asm/kprobes.h
@@ -44,8 +44,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned int kprobe_status;
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	char jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm/include/asm/probes.h b/arch/arm/include/asm/probes.h
index 1e5b9bb92270..991c9127c650 100644
--- a/arch/arm/include/asm/probes.h
+++ b/arch/arm/include/asm/probes.h
@@ -51,7 +51,6 @@ struct arch_probes_insn {
  * We assume one instruction can consume at most 64 bytes stack, which is
  * 'push {r0-r15}'. Instructions consume more or unknown stack space like
  * 'str r0, [sp, #-80]' and 'str r0, [sp, r1]' should be prohibit to probe.
- * Both kprobe and jprobe use this macro.
  */
 #define MAX_STACK_SIZE			64
 
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index e90cc8a08186..23562111c511 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -47,9 +47,6 @@
 			   (unsigned long)(addr) +	\
 			   (size))
 
-/* Used as a marker in ARM_pc to note when we're in a jprobe. */
-#define JPROBE_MAGIC_ADDR		0xffffffff
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -521,117 +518,6 @@ void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri,
 	regs->ARM_lr = (unsigned long)&kretprobe_trampoline;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long sp_addr = regs->ARM_sp;
-	long cpsr;
-
-	kcb->jprobe_saved_regs = *regs;
-	memcpy(kcb->jprobes_stack, (void *)sp_addr, MIN_STACK_SIZE(sp_addr));
-	regs->ARM_pc = (long)jp->entry;
-
-	cpsr = regs->ARM_cpsr | PSR_I_BIT;
-#ifdef CONFIG_THUMB2_KERNEL
-	/* Set correct Thumb state in cpsr */
-	if (regs->ARM_pc & 1)
-		cpsr |= PSR_T_BIT;
-	else
-		cpsr &= ~PSR_T_BIT;
-#endif
-	regs->ARM_cpsr = cpsr;
-
-	preempt_disable();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	__asm__ __volatile__ (
-		/*
-		 * Setup an empty pt_regs. Fill SP and PC fields as
-		 * they're needed by longjmp_break_handler.
-		 *
-		 * We allocate some slack between the original SP and start of
-		 * our fabricated regs. To be precise we want to have worst case
-		 * covered which is STMFD with all 16 regs so we allocate 2 *
-		 * sizeof(struct_pt_regs)).
-		 *
-		 * This is to prevent any simulated instruction from writing
-		 * over the regs when they are accessing the stack.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"sub    r0, %0, %1		\n\t"
-		"mov    sp, r0			\n\t"
-#else
-		"sub    sp, %0, %1		\n\t"
-#endif
-		"ldr    r0, ="__stringify(JPROBE_MAGIC_ADDR)"\n\t"
-		"str    %0, [sp, %2]		\n\t"
-		"str    r0, [sp, %3]		\n\t"
-		"mov    r0, sp			\n\t"
-		"bl     kprobe_handler		\n\t"
-
-		/*
-		 * Return to the context saved by setjmp_pre_handler
-		 * and restored by longjmp_break_handler.
-		 */
-#ifdef CONFIG_THUMB2_KERNEL
-		"ldr	lr, [sp, %2]		\n\t" /* lr = saved sp */
-		"ldrd	r0, r1, [sp, %5]	\n\t" /* r0,r1 = saved lr,pc */
-		"ldr	r2, [sp, %4]		\n\t" /* r2 = saved psr */
-		"stmdb	lr!, {r0, r1, r2}	\n\t" /* push saved lr and */
-						      /* rfe context */
-		"ldmia	sp, {r0 - r12}		\n\t"
-		"mov	sp, lr			\n\t"
-		"ldr	lr, [sp], #4		\n\t"
-		"rfeia	sp!			\n\t"
-#else
-		"ldr	r0, [sp, %4]		\n\t"
-		"msr	cpsr_cxsf, r0		\n\t"
-		"ldmia	sp, {r0 - pc}		\n\t"
-#endif
-		:
-		: "r" (kcb->jprobe_saved_regs.ARM_sp),
-		  "I" (sizeof(struct pt_regs) * 2),
-		  "J" (offsetof(struct pt_regs, ARM_sp)),
-		  "J" (offsetof(struct pt_regs, ARM_pc)),
-		  "J" (offsetof(struct pt_regs, ARM_cpsr)),
-		  "J" (offsetof(struct pt_regs, ARM_lr))
-		: "memory", "cc");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_addr = kcb->jprobe_saved_regs.ARM_sp;
-	long orig_sp = regs->ARM_sp;
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-
-	if (regs->ARM_pc == JPROBE_MAGIC_ADDR) {
-		if (orig_sp != stack_addr) {
-			struct pt_regs *saved_regs =
-				(struct pt_regs *)kcb->jprobe_saved_regs.ARM_sp;
-			printk("current sp %lx does not match saved sp %lx\n",
-			       orig_sp, stack_addr);
-			printk("Saved registers for jprobe %p\n", jp);
-			show_regs(saved_regs);
-			printk("Current registers\n");
-			show_regs(regs);
-			BUG();
-		}
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 int __kprobes arch_trampoline_kprobe(struct kprobe *p)
 {
 	return 0;
-- 
cgit v1.2.3


From 2efb75cd712d8311a2d0c1ba041ded191398bca7 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:07:03 +0900
Subject: arm64/kprobes: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/arm64.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/lkml/152942442318.15209.17767976282305601884.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/include/asm/kprobes.h   |  1 -
 arch/arm64/kernel/probes/kprobes.c | 68 --------------------------------------
 2 files changed, 69 deletions(-)

diff --git a/arch/arm64/include/asm/kprobes.h b/arch/arm64/include/asm/kprobes.h
index 6deb8d726041..d5a44cf859e9 100644
--- a/arch/arm64/include/asm/kprobes.h
+++ b/arch/arm64/include/asm/kprobes.h
@@ -48,7 +48,6 @@ struct kprobe_ctlblk {
 	unsigned long saved_irqflag;
 	struct prev_kprobe prev_kprobe;
 	struct kprobe_step_ctx ss_ctx;
-	struct pt_regs jprobe_saved_regs;
 };
 
 void arch_remove_kprobe(struct kprobe *);
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index d849d9804011..3ca2351109a6 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -465,74 +465,6 @@ kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr)
 	return DBG_HOOK_HANDLED;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	/*
-	 * Since we can't be sure where in the stack frame "stacked"
-	 * pass-by-value arguments are stored we just don't try to
-	 * duplicate any of the stack. Do not use jprobes on functions that
-	 * use more than 64 bytes (after padding each to an 8 byte boundary)
-	 * of arguments, or pass individual arguments larger than 16 bytes.
-	 */
-
-	instruction_pointer_set(regs, (unsigned long) jp->entry);
-	preempt_disable();
-	pause_graph_tracing();
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	/*
-	 * Jprobe handler return by entering break exception,
-	 * encoded same as kprobe, but with following conditions
-	 * -a special PC to identify it from the other kprobes.
-	 * -restore stack addr to original saved pt_regs
-	 */
-	asm volatile("				mov sp, %0	\n"
-		     "jprobe_return_break:	brk %1		\n"
-		     :
-		     : "r" (kcb->jprobe_saved_regs.sp),
-		       "I" (BRK64_ESR_KPROBES)
-		     : "memory");
-
-	unreachable();
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	long stack_addr = kcb->jprobe_saved_regs.sp;
-	long orig_sp = kernel_stack_pointer(regs);
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	extern const char jprobe_return_break[];
-
-	if (instruction_pointer(regs) != (u64) jprobe_return_break)
-		return 0;
-
-	if (orig_sp != stack_addr) {
-		struct pt_regs *saved_regs =
-		    (struct pt_regs *)kcb->jprobe_saved_regs.sp;
-		pr_err("current sp %lx does not match saved sp %lx\n",
-		       orig_sp, stack_addr);
-		pr_err("Saved registers for jprobe %p\n", jp);
-		__show_regs(saved_regs);
-		pr_err("Current registers\n");
-		__show_regs(regs);
-		BUG();
-	}
-	unpause_graph_tracing();
-	*regs = kcb->jprobe_saved_regs;
-	preempt_enable_no_resched();
-	return 1;
-}
-
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	if ((addr >= (unsigned long)__kprobes_text_start &&
-- 
cgit v1.2.3


From c530e2f02ef8700ec59fed175e800a2a97695350 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:07:32 +0900
Subject: powerpc/kprobes: Remove jprobe powerpc implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/powerpc. This also reverts commits
related __is_active_jprobe() function.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/lkml/152942445234.15209.12868722778364739753.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/include/asm/kprobes.h             |  2 -
 arch/powerpc/kernel/kprobes-ftrace.c           | 15 -------
 arch/powerpc/kernel/kprobes.c                  | 54 --------------------------
 arch/powerpc/kernel/trace/ftrace_64_mprofile.S | 39 +++----------------
 4 files changed, 5 insertions(+), 105 deletions(-)

diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 9f3be5c8a4a3..674036db558b 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -88,7 +88,6 @@ struct prev_kprobe {
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_saved_msr;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
@@ -104,7 +103,6 @@ extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
 #ifdef CONFIG_KPROBES_ON_FTRACE
-extern int __is_active_jprobe(unsigned long addr);
 extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 			   struct kprobe_ctlblk *kcb);
 #else
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 7a1f99f1b47f..1b316331c2d9 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -25,21 +25,6 @@
 #include <linux/preempt.h>
 #include <linux/ftrace.h>
 
-/*
- * This is called from ftrace code after invoking registered handlers to
- * disambiguate regs->nip changes done by jprobes and livepatch. We check if
- * there is an active jprobe at the provided address (mcount location).
- */
-int __is_active_jprobe(unsigned long addr)
-{
-	if (!preemptible()) {
-		struct kprobe *p = raw_cpu_read(current_kprobe);
-		return (p && (unsigned long)p->addr == addr) ? 1 : 0;
-	}
-
-	return 0;
-}
-
 static nokprobe_inline
 int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 		      struct kprobe_ctlblk *kcb, unsigned long orig_nip)
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index e4c5bf33970b..600678fce0a8 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -611,60 +611,6 @@ unsigned long arch_deref_entry_point(void *entry)
 }
 NOKPROBE_SYMBOL(arch_deref_entry_point);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->nip = arch_deref_entry_point(jp->entry);
-#ifdef PPC64_ELF_ABI_v2
-	regs->gpr[12] = (unsigned long)jp->entry;
-#elif defined(PPC64_ELF_ABI_v1)
-	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
-#endif
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void __used jprobe_return(void)
-{
-	asm volatile("jprobe_return_trap:\n"
-		     "trap\n"
-		     ::: "memory");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->nip != ppc_kallsyms_lookup_name("jprobe_return_trap")) {
-		pr_debug("longjmp_break_handler NIP (0x%lx) does not match jprobe_return_trap (0x%lx)\n",
-				regs->nip, ppc_kallsyms_lookup_name("jprobe_return_trap"));
-		return 0;
-	}
-
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 9a5b5a513604..32476a6e4e9c 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -104,39 +104,13 @@ ftrace_regs_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load the possibly modified NIP */
-	ld	r15, _NIP(r1)
-
+	/* Load ctr with the possibly modified NIP */
+	ld	r3, _NIP(r1)
+	mtctr	r3
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14, r15	/* has NIP been altered? */
+	cmpd	r14, r3		/* has NIP been altered? */
 #endif
 
-#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
-	/* NIP has not been altered, skip over further checks */
-	beq	1f
-
-	/* Check if there is an active jprobe on us */
-	subi	r3, r14, 4
-	bl	__is_active_jprobe
-	nop
-
-	/*
-	 * If r3 == 1, then this is a kprobe/jprobe.
-	 * else, this is livepatched function.
-	 *
-	 * The conditional branch for livepatch_handler below will use the
-	 * result of this comparison. For kprobe/jprobe, we just need to branch to
-	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
-	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
-	 * CR0[EQ] = (r3 == 1).
-	 */
-	cmpdi	r3, 1
-1:
-#endif
-
-	/* Load CTR with the possibly modified NIP */
-	mtctr	r15
-
 	/* Restore gprs */
 	REST_GPR(0,r1)
 	REST_10GPRS(2,r1)
@@ -154,10 +128,7 @@ ftrace_regs_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /*
-	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
-	 * not on a kprobe/jprobe, then handle livepatch.
-	 */
+        /* Based on the cmpd above, if the NIP was altered handle livepatch */
 	bne-	livepatch_handler
 #endif
 
-- 
cgit v1.2.3


From 0aeaf6b3a34588050a32d88177e18a1909bbb994 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:08:01 +0900
Subject: ia64/kprobes: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/ia64.

Note that since ia64 jprobes code is a bit different
from other architectures, this keeps __IA64_BREAK_JPROBE
for checking the ->break_handler(). It will be removed
with the break_handler() calls afterwards.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942448152.15209.2026051332977587306.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/ia64/include/asm/kprobes.h |  2 -
 arch/ia64/kernel/Makefile       |  2 +-
 arch/ia64/kernel/jprobes.S      | 90 -----------------------------------------
 arch/ia64/kernel/kprobes.c      | 70 --------------------------------
 4 files changed, 1 insertion(+), 163 deletions(-)
 delete mode 100644 arch/ia64/kernel/jprobes.S

diff --git a/arch/ia64/include/asm/kprobes.h b/arch/ia64/include/asm/kprobes.h
index 0302b3664789..580356a2eea6 100644
--- a/arch/ia64/include/asm/kprobes.h
+++ b/arch/ia64/include/asm/kprobes.h
@@ -82,8 +82,6 @@ struct prev_kprobe {
 #define ARCH_PREV_KPROBE_SZ 2
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	struct pt_regs jprobe_saved_regs;
-	unsigned long jprobes_saved_stacked_regs[MAX_PARAM_RSE_SIZE];
 	unsigned long *bsp;
 	unsigned long cfm;
 	atomic_t prev_kprobe_index;
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index 498f3da3f225..d0c0ccdd656a 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_NUMA)		+= numa.o
 obj-$(CONFIG_PERFMON)		+= perfmon_default_smpl.o
 obj-$(CONFIG_IA64_CYCLONE)	+= cyclone.o
 obj-$(CONFIG_IA64_MCA_RECOVERY)	+= mca_recovery.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o jprobes.o
+obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o crash.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
diff --git a/arch/ia64/kernel/jprobes.S b/arch/ia64/kernel/jprobes.S
deleted file mode 100644
index f69389c7be1d..000000000000
--- a/arch/ia64/kernel/jprobes.S
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Jprobe specific operations
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
- *
- * Copyright (C) Intel Corporation, 2005
- *
- * 2005-May     Rusty Lynch <rusty.lynch@intel.com> and Anil S Keshavamurthy
- *              <anil.s.keshavamurthy@intel.com> initial implementation
- *
- * Jprobes (a.k.a. "jump probes" which is built on-top of kprobes) allow a
- * probe to be inserted into the beginning of a function call.  The fundamental
- * difference between a jprobe and a kprobe is the jprobe handler is executed
- * in the same context as the target function, while the kprobe handlers
- * are executed in interrupt context.
- *
- * For jprobes we initially gain control by placing a break point in the
- * first instruction of the targeted function.  When we catch that specific
- * break, we:
- *        * set the return address to our jprobe_inst_return() function
- *        * jump to the jprobe handler function
- *
- * Since we fixed up the return address, the jprobe handler will return to our
- * jprobe_inst_return() function, giving us control again.  At this point we
- * are back in the parents frame marker, so we do yet another call to our
- * jprobe_break() function to fix up the frame marker as it would normally
- * exist in the target function.
- *
- * Our jprobe_return function then transfers control back to kprobes.c by
- * executing a break instruction using one of our reserved numbers.  When we
- * catch that break in kprobes.c, we continue like we do for a normal kprobe
- * by single stepping the emulated instruction, and then returning execution
- * to the correct location.
- */
-#include <asm/asmmacro.h>
-#include <asm/break.h>
-
-	/*
-	 * void jprobe_break(void)
-	 */
-	.section .kprobes.text, "ax"
-ENTRY(jprobe_break)
-	break.m __IA64_BREAK_JPROBE
-END(jprobe_break)
-
-	/*
-	 * void jprobe_inst_return(void)
-	 */
-GLOBAL_ENTRY(jprobe_inst_return)
-	br.call.sptk.many b0=jprobe_break
-END(jprobe_inst_return)
-
-GLOBAL_ENTRY(invalidate_stacked_regs)
-	movl r16=invalidate_restore_cfm
-	;;
-	mov b6=r16
-	;;
-	br.ret.sptk.many b6
-	;;
-invalidate_restore_cfm:
-	mov r16=ar.rsc
-	;;
-	mov ar.rsc=r0
-	;;
-	loadrs
-	;;
-	mov ar.rsc=r16
-	;;
-	br.cond.sptk.many rp
-END(invalidate_stacked_regs)
-
-GLOBAL_ENTRY(flush_register_stack)
-	// flush dirty regs to backing store (must be first in insn group)
-	flushrs
-	;;
-	br.ret.sptk.many rp
-END(flush_register_stack)
-
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index f5f3a5e6fcd1..823e4bd03a18 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -35,8 +35,6 @@
 #include <asm/sections.h>
 #include <asm/exception.h>
 
-extern void jprobe_inst_return(void);
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -1040,74 +1038,6 @@ unsigned long arch_deref_entry_point(void *entry)
 	return ((struct fnptr *)entry)->ip;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr = arch_deref_entry_point(jp->entry);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	struct param_bsp_cfm pa;
-	int bytes;
-
-	/*
-	 * Callee owns the argument space and could overwrite it, eg
-	 * tail call optimization. So to be absolutely safe
-	 * we save the argument space before transferring the control
-	 * to instrumented jprobe function which runs in
-	 * the process context
-	 */
-	pa.ip = regs->cr_iip;
-	unw_init_running(ia64_get_bsp_cfm, &pa);
-	bytes = (char *)ia64_rse_skip_regs(pa.bsp, pa.cfm & 0x3f)
-				- (char *)pa.bsp;
-	memcpy( kcb->jprobes_saved_stacked_regs,
-		pa.bsp,
-		bytes );
-	kcb->bsp = pa.bsp;
-	kcb->cfm = pa.cfm;
-
-	/* save architectural state */
-	kcb->jprobe_saved_regs = *regs;
-
-	/* after rfi, execute the jprobe instrumented function */
-	regs->cr_iip = addr & ~0xFULL;
-	ia64_psr(regs)->ri = addr & 0xf;
-	regs->r1 = ((struct fnptr *)(jp->entry))->gp;
-
-	/*
-	 * fix the return address to our jprobe_inst_return() function
-	 * in the jprobes.S file
-	 */
-	regs->b0 = ((struct fnptr *)(jprobe_inst_return))->ip;
-
-	return 1;
-}
-
-/* ia64 does not need this */
-void __kprobes jprobe_return(void)
-{
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	int bytes;
-
-	/* restoring architectural state */
-	*regs = kcb->jprobe_saved_regs;
-
-	/* restoring the original argument space */
-	flush_register_stack();
-	bytes = (char *)ia64_rse_skip_regs(kcb->bsp, kcb->cfm & 0x3f)
-				- (char *)kcb->bsp;
-	memcpy( kcb->bsp,
-		kcb->jprobes_saved_stacked_regs,
-		bytes );
-	invalidate_stacked_regs();
-
-	preempt_enable_no_resched();
-	return 1;
-}
-
 static struct kprobe trampoline_p = {
 	.pre_handler = trampoline_probe_handler
 };
-- 
cgit v1.2.3


From 8c2c3f2d40b6c4f40eddc099916dffac6171bf2e Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:08:30 +0900
Subject: MIPS/kprobes: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/mips.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-mips@linux-mips.org
Link: https://lore.kernel.org/lkml/152942451058.15209.3459785416221980965.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/include/asm/kprobes.h | 13 ------------
 arch/mips/kernel/kprobes.c      | 45 -----------------------------------------
 2 files changed, 58 deletions(-)

diff --git a/arch/mips/include/asm/kprobes.h b/arch/mips/include/asm/kprobes.h
index ad1a99948f27..a72dfbf1babb 100644
--- a/arch/mips/include/asm/kprobes.h
+++ b/arch/mips/include/asm/kprobes.h
@@ -68,16 +68,6 @@ struct prev_kprobe {
 	unsigned long saved_epc;
 };
 
-#define MAX_JPROBES_STACK_SIZE 128
-#define MAX_JPROBES_STACK_ADDR \
-	(((unsigned long)current_thread_info()) + THREAD_SIZE - 32 - sizeof(struct pt_regs))
-
-#define MIN_JPROBES_STACK_SIZE(ADDR)					\
-	((((ADDR) + MAX_JPROBES_STACK_SIZE) > MAX_JPROBES_STACK_ADDR)	\
-		? MAX_JPROBES_STACK_ADDR - (ADDR)			\
-		: MAX_JPROBES_STACK_SIZE)
-
-
 #define SKIP_DELAYSLOT 0x0001
 
 /* per-cpu kprobe control block */
@@ -86,12 +76,9 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_old_SR;
 	unsigned long kprobe_saved_SR;
 	unsigned long kprobe_saved_epc;
-	unsigned long jprobe_saved_sp;
-	struct pt_regs jprobe_saved_regs;
 	/* Per-thread fields, used while emulating branches */
 	unsigned long flags;
 	unsigned long target_epc;
-	u8 jprobes_stack[MAX_JPROBES_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index f5c8bce70db2..efdcd0b1ce12 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -468,51 +468,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_sp = regs->regs[29];
-
-	memcpy(kcb->jprobes_stack, (void *)kcb->jprobe_saved_sp,
-	       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-
-	regs->cp0_epc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-/* Defined in the inline asm below. */
-void jprobe_return_end(void);
-
-void __kprobes jprobe_return(void)
-{
-	/* Assembler quirk necessitates this '0,code' business.	 */
-	asm volatile(
-		"break 0,%0\n\t"
-		".globl jprobe_return_end\n"
-		"jprobe_return_end:\n"
-		: : "n" (BRK_KPROBE_BP) : "memory");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (regs->cp0_epc >= (unsigned long)jprobe_return &&
-	    regs->cp0_epc <= (unsigned long)jprobe_return_end) {
-		*regs = kcb->jprobe_saved_regs;
-		memcpy((void *)kcb->jprobe_saved_sp, kcb->jprobes_stack,
-		       MIN_JPROBES_STACK_SIZE(kcb->jprobe_saved_sp));
-		preempt_enable_no_resched();
-
-		return 1;
-	}
-	return 0;
-}
-
 /*
  * Function return probe trampoline:
  *	- init_kprobes() establishes a probepoint here
-- 
cgit v1.2.3


From fc682f7ba30e89aa49386fd7e427e3d083b7ae58 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:08:59 +0900
Subject: s390/kprobes: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/s390.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942453967.15209.8535227381029256754.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/s390/include/asm/kprobes.h |  2 --
 arch/s390/kernel/kprobes.c      | 59 ++---------------------------------------
 2 files changed, 2 insertions(+), 59 deletions(-)

diff --git a/arch/s390/include/asm/kprobes.h b/arch/s390/include/asm/kprobes.h
index 13de80cf741c..b106aa29bf55 100644
--- a/arch/s390/include/asm/kprobes.h
+++ b/arch/s390/include/asm/kprobes.h
@@ -68,8 +68,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_saved_imask;
 	unsigned long kprobe_saved_ctl[3];
 	struct prev_kprobe prev_kprobe;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 };
 
 void arch_remove_kprobe(struct kprobe *p);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 60f60afa645c..0967de19f53d 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -321,9 +321,8 @@ static int kprobe_handler(struct pt_regs *regs)
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with single stepping. If we have a
 			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry
-			 * for jprobe processing, so get out doing nothing
-			 * more here.
+			 * for changing execution path, so get out doing
+			 * nothing more here.
 			 */
 			push_kprobe(kcb, p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
@@ -661,60 +660,6 @@ int kprobe_exceptions_notify(struct notifier_block *self,
 }
 NOKPROBE_SYMBOL(kprobe_exceptions_notify);
 
-int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	memcpy(&kcb->jprobe_saved_regs, regs, sizeof(struct pt_regs));
-
-	/* setup return addr to the jprobe handler routine */
-	regs->psw.addr = (unsigned long) jp->entry;
-	regs->psw.mask &= ~(PSW_MASK_IO | PSW_MASK_EXT);
-
-	/* r15 is the stack pointer */
-	stack = (unsigned long) regs->gprs[15];
-
-	memcpy(kcb->jprobes_stack, (void *) stack, MIN_STACK_SIZE(stack));
-
-	/*
-	 * jprobes use jprobe_return() which skips the normal return
-	 * path of the function, and this messes up the accounting of the
-	 * function graph tracer to get messed up.
-	 *
-	 * Pause function graph tracing while performing the jprobe function.
-	 */
-	pause_graph_tracing();
-	return 1;
-}
-NOKPROBE_SYMBOL(setjmp_pre_handler);
-
-void jprobe_return(void)
-{
-	asm volatile(".word 0x0002");
-}
-NOKPROBE_SYMBOL(jprobe_return);
-
-int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack;
-
-	/* It's OK to start function graph tracing again */
-	unpause_graph_tracing();
-
-	stack = (unsigned long) kcb->jprobe_saved_regs.gprs[15];
-
-	/* Put the regs back */
-	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
-	/* put the stack back */
-	memcpy((void *) stack, kcb->jprobes_stack, MIN_STACK_SIZE(stack));
-	preempt_enable_no_resched();
-	return 1;
-}
-NOKPROBE_SYMBOL(longjmp_break_handler);
-
 static struct kprobe trampoline = {
 	.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
-- 
cgit v1.2.3


From 8a4b11a21eaf2b7bae91e6de7ac0543e0342e955 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:09:28 +0900
Subject: sh/kprobes: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/sh.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: linux-arch@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942456877.15209.5482537226935729621.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sh/include/asm/kprobes.h |  4 ----
 arch/sh/kernel/kprobes.c      | 51 -------------------------------------------
 2 files changed, 55 deletions(-)

diff --git a/arch/sh/include/asm/kprobes.h b/arch/sh/include/asm/kprobes.h
index 85d8bcaa8493..6171682f7798 100644
--- a/arch/sh/include/asm/kprobes.h
+++ b/arch/sh/include/asm/kprobes.h
@@ -27,7 +27,6 @@ struct kprobe;
 
 void arch_remove_kprobe(struct kprobe *);
 void kretprobe_trampoline(void);
-void jprobe_return_end(void);
 
 /* Architecture specific copy of original instruction*/
 struct arch_specific_insn {
@@ -43,9 +42,6 @@ struct prev_kprobe {
 /* per-cpu kprobe control block */
 struct kprobe_ctlblk {
 	unsigned long kprobe_status;
-	unsigned long jprobe_saved_r15;
-	struct pt_regs jprobe_saved_regs;
-	kprobe_opcode_t jprobes_stack[MAX_STACK_SIZE];
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 52a5e11247d1..2b5e58873b96 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -523,57 +523,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	return ret;
 }
 
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	unsigned long addr;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	kcb->jprobe_saved_regs = *regs;
-	kcb->jprobe_saved_r15 = regs->regs[15];
-	addr = kcb->jprobe_saved_r15;
-
-	/*
-	 * TBD: As Linus pointed out, gcc assumes that the callee
-	 * owns the argument space and could overwrite it, e.g.
-	 * tailcall optimization. So, to be absolutely safe
-	 * we also save and restore enough stack bytes to cover
-	 * the argument area.
-	 */
-	memcpy(kcb->jprobes_stack, (kprobe_opcode_t *) addr,
-	       MIN_STACK_SIZE(addr));
-
-	regs->pc = (unsigned long)(jp->entry);
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	asm volatile ("trapa #0x3a\n\t" "jprobe_return_end:\n\t" "nop\n\t");
-}
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	unsigned long stack_addr = kcb->jprobe_saved_r15;
-	u8 *addr = (u8 *)regs->pc;
-
-	if ((addr >= (u8 *)jprobe_return) &&
-	    (addr <= (u8 *)jprobe_return_end)) {
-		*regs = kcb->jprobe_saved_regs;
-
-		memcpy((kprobe_opcode_t *)stack_addr, kcb->jprobes_stack,
-		       MIN_STACK_SIZE(stack_addr));
-
-		kcb->kprobe_status = KPROBE_HIT_SS;
-		preempt_enable_no_resched();
-		return 1;
-	}
-
-	return 0;
-}
-
 static struct kprobe trampoline_p = {
 	.addr = (kprobe_opcode_t *)&kretprobe_trampoline,
 	.pre_handler = trampoline_probe_handler
-- 
cgit v1.2.3


From e9bf11a5a68b39e41f2113b7d3cf5125d6816e23 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:09:58 +0900
Subject: sparc64/kprobes: Remove jprobe implementation

Remove arch dependent setjump/longjump functions
and unused fields in kprobe_ctlblk for jprobes
from arch/sparc.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942459795.15209.9736720668494241853.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sparc/include/asm/kprobes.h |  1 -
 arch/sparc/kernel/kprobes.c      | 47 ----------------------------------------
 2 files changed, 48 deletions(-)

diff --git a/arch/sparc/include/asm/kprobes.h b/arch/sparc/include/asm/kprobes.h
index 3704490b4488..bfcaa6326c20 100644
--- a/arch/sparc/include/asm/kprobes.h
+++ b/arch/sparc/include/asm/kprobes.h
@@ -44,7 +44,6 @@ struct kprobe_ctlblk {
 	unsigned long kprobe_status;
 	unsigned long kprobe_orig_tnpc;
 	unsigned long kprobe_orig_tstate_pil;
-	struct pt_regs jprobe_saved_regs;
 	struct prev_kprobe prev_kprobe;
 };
 
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index ab4ba4347941..f555711da8f1 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -441,53 +441,6 @@ out:
 	exception_exit(prev_state);
 }
 
-/* Jprobes support.  */
-int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct jprobe *jp = container_of(p, struct jprobe, kp);
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	memcpy(&(kcb->jprobe_saved_regs), regs, sizeof(*regs));
-
-	regs->tpc  = (unsigned long) jp->entry;
-	regs->tnpc = ((unsigned long) jp->entry) + 0x4UL;
-	regs->tstate |= TSTATE_PIL;
-
-	return 1;
-}
-
-void __kprobes jprobe_return(void)
-{
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-	register unsigned long orig_fp asm("g1");
-
-	orig_fp = kcb->jprobe_saved_regs.u_regs[UREG_FP];
-	__asm__ __volatile__("\n"
-"1:	cmp		%%sp, %0\n\t"
-	"blu,a,pt	%%xcc, 1b\n\t"
-	" restore\n\t"
-	".globl		jprobe_return_trap_instruction\n"
-"jprobe_return_trap_instruction:\n\t"
-	"ta		0x70"
-	: /* no outputs */
-	: "r" (orig_fp));
-}
-
-extern void jprobe_return_trap_instruction(void);
-
-int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	u32 *addr = (u32 *) regs->tpc;
-	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
-
-	if (addr == (u32 *) jprobe_return_trap_instruction) {
-		memcpy(regs, &(kcb->jprobe_saved_regs), sizeof(*regs));
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-
 /* The value stored in the return address register is actually 2
  * instructions before where the callee will return to.
  * Sequences usually look something like this
-- 
cgit v1.2.3


From 059053a275b56eff1db11605c68988a6e9818561 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:10:27 +0900
Subject: kprobes: Don't check the ->break_handler() in generic kprobes code

Don't check the ->break_handler() from the core kprobes code,
because it was only used by jprobes which got removed.

( In followup patches we'll remove the remaining calls in low level
  arch handlers as well and remove the callback altogether. )

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942462686.15209.6324404940493598980.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/kprobes.txt |  2 +-
 kernel/kprobes.c          | 39 +++++----------------------------------
 2 files changed, 6 insertions(+), 35 deletions(-)

diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 33dd6a81fb64..ab2c7307f123 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -262,7 +262,7 @@ is optimized, that modification is ignored.  Thus, if you want to
 tweak the kernel's execution path, you need to suppress optimization,
 using one of the following techniques:
 
-- Specify an empty function for the kprobe's post_handler or break_handler.
+- Specify an empty function for the kprobe's post_handler.
 
 or
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 69de130595f7..536ab451e96d 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -627,8 +627,8 @@ static void optimize_kprobe(struct kprobe *p)
 	    (kprobe_disabled(p) || kprobes_all_disarmed))
 		return;
 
-	/* Both of break_handler and post_handler are not supported. */
-	if (p->break_handler || p->post_handler)
+	/* kprobes with post_handler can not be optimized */
+	if (p->post_handler)
 		return;
 
 	op = container_of(p, struct optimized_kprobe, kp);
@@ -1116,20 +1116,6 @@ static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
 }
 NOKPROBE_SYMBOL(aggr_fault_handler);
 
-static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
-{
-	struct kprobe *cur = __this_cpu_read(kprobe_instance);
-	int ret = 0;
-
-	if (cur && cur->break_handler) {
-		if (cur->break_handler(cur, regs))
-			ret = 1;
-	}
-	reset_kprobe_instance();
-	return ret;
-}
-NOKPROBE_SYMBOL(aggr_break_handler);
-
 /* Walks the list and increments nmissed count for multiprobe case */
 void kprobes_inc_nmissed_count(struct kprobe *p)
 {
@@ -1270,24 +1256,15 @@ static void cleanup_rp_inst(struct kretprobe *rp)
 }
 NOKPROBE_SYMBOL(cleanup_rp_inst);
 
-/*
-* Add the new probe to ap->list. Fail if this is the
-* second break_handler at the address
-*/
+/* Add the new probe to ap->list */
 static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
 {
 	BUG_ON(kprobe_gone(ap) || kprobe_gone(p));
 
-	if (p->break_handler || p->post_handler)
+	if (p->post_handler)
 		unoptimize_kprobe(ap, true);	/* Fall back to normal kprobe */
 
-	if (p->break_handler) {
-		if (ap->break_handler)
-			return -EEXIST;
-		list_add_tail_rcu(&p->list, &ap->list);
-		ap->break_handler = aggr_break_handler;
-	} else
-		list_add_rcu(&p->list, &ap->list);
+	list_add_rcu(&p->list, &ap->list);
 	if (p->post_handler && !ap->post_handler)
 		ap->post_handler = aggr_post_handler;
 
@@ -1310,8 +1287,6 @@ static void init_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 	/* We don't care the kprobe which has gone. */
 	if (p->post_handler && !kprobe_gone(p))
 		ap->post_handler = aggr_post_handler;
-	if (p->break_handler && !kprobe_gone(p))
-		ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
 	INIT_HLIST_NODE(&ap->hlist);
@@ -1706,8 +1681,6 @@ static int __unregister_kprobe_top(struct kprobe *p)
 		goto disarmed;
 	else {
 		/* If disabling probe has special handlers, update aggrprobe */
-		if (p->break_handler && !kprobe_gone(p))
-			ap->break_handler = NULL;
 		if (p->post_handler && !kprobe_gone(p)) {
 			list_for_each_entry_rcu(list_p, &ap->list, list) {
 				if ((list_p != p) && (list_p->post_handler))
@@ -1911,7 +1884,6 @@ int register_kretprobe(struct kretprobe *rp)
 	rp->kp.pre_handler = pre_handler_kretprobe;
 	rp->kp.post_handler = NULL;
 	rp->kp.fault_handler = NULL;
-	rp->kp.break_handler = NULL;
 
 	/* Pre-allocate memory for max kretprobe instances */
 	if (rp->maxactive <= 0) {
@@ -2034,7 +2006,6 @@ static void kill_kprobe(struct kprobe *p)
 		list_for_each_entry_rcu(kp, &p->list, list)
 			kp->flags |= KPROBE_FLAG_GONE;
 		p->post_handler = NULL;
-		p->break_handler = NULL;
 		kill_optimized_kprobe(p);
 	}
 	/*
-- 
cgit v1.2.3


From e704e34cd0bbd1c69eb4ca724935a23f6440502e Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:10:55 +0900
Subject: kprobes/x86: Don't call the ->break_handler() in x86 kprobes

Don't call the ->break_handler() and remove break_handler
related code from x86 since that was only used by jprobe
which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942465549.15209.15889693025972771135.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/kprobes.h   |  2 +-
 arch/x86/kernel/kprobes/common.h | 10 ----------
 arch/x86/kernel/kprobes/core.c   |  7 -------
 arch/x86/kernel/kprobes/ftrace.c | 42 +++++++++++-----------------------------
 4 files changed, 12 insertions(+), 49 deletions(-)

diff --git a/arch/x86/include/asm/kprobes.h b/arch/x86/include/asm/kprobes.h
index 06782c2efa04..c8cec1b39b88 100644
--- a/arch/x86/include/asm/kprobes.h
+++ b/arch/x86/include/asm/kprobes.h
@@ -78,7 +78,7 @@ struct arch_specific_insn {
 	 * boostable = true: This instruction has been boosted: we have
 	 * added a relative jump after the instruction copy in insn,
 	 * so no single-step and fixup are needed (unless there's
-	 * a post_handler or break_handler).
+	 * a post_handler).
 	 */
 	bool boostable;
 	bool if_modifier;
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index ae38dccf0c8f..2b949f4fd4d8 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -105,14 +105,4 @@ static inline unsigned long __recover_optprobed_insn(kprobe_opcode_t *buf, unsig
 }
 #endif
 
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
 #endif
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 1b2d1acba810..0ac16a0d93e5 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -709,13 +709,6 @@ int kprobe_int3_handler(struct pt_regs *regs)
 		regs->ip = (unsigned long)addr;
 		preempt_enable_no_resched();
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			if (!skip_singlestep(p, regs, kcb))
-				setup_singlestep(p, regs, kcb, 0);
-			return 1;
-		}
 	} /* else: not a kprobe fault; let the kernel handle it */
 
 	preempt_enable_no_resched();
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 8dc0161cec8f..02a6dd1b6bd0 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -25,36 +25,6 @@
 
 #include "common.h"
 
-static nokprobe_inline
-void __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_ip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->ip)
-	 * as if there is a 5byte nop
-	 */
-	regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	if (orig_ip)
-		regs->ip = orig_ip;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p)) {
-		__skip_singlestep(p, regs, kcb, 0);
-		preempt_enable_no_resched();
-		return 1;
-	}
-	return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes -- called under preepmt disabed */
 void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -80,7 +50,17 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
-			__skip_singlestep(p, regs, kcb, orig_ip);
+			/*
+			 * Emulate singlestep (and also recover regs->ip)
+			 * as if there is a 5byte nop
+			 */
+			regs->ip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			regs->ip = orig_ip;
+			__this_cpu_write(current_kprobe, NULL);
 			preempt_enable_no_resched();
 		}
 		/*
-- 
cgit v1.2.3


From 5ed4b0c5d17671160c0ab74a260ae57e9352b585 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:11:24 +0900
Subject: ARC/kprobes: Don't call the ->break_handler() in ARC kprobes code

Don't call the ->break_handler() from the ARC kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-snps-arc@lists.infradead.org
Link: https://lore.kernel.org/lkml/152942468446.15209.13773902741600803798.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/kernel/kprobes.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 7811a6bbe8f0..465365696c91 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -234,13 +234,6 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
 		}
 
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			setup_singlestep(p, regs);
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			return 1;
-		}
 	}
 
 	/* no_kprobe: */
-- 
cgit v1.2.3


From 75feff53a2011e8954fab02bdcef49f36a01b256 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:11:53 +0900
Subject: ARM/kprobes: Don't call the ->break_handler() in arm kprobes code

Don't call the ->break_handler() from the arm kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/lkml/152942471328.15209.10625693210204476080.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/probes/kprobes/core.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 23562111c511..3192350f389d 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -315,17 +315,6 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				reset_current_kprobe();
 			}
 		}
-	} else if (cur) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur->break_handler && cur->break_handler(cur, regs)) {
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			singlestep(cur, regs, kcb);
-			if (cur->post_handler) {
-				kcb->kprobe_status = KPROBE_HIT_SSDONE;
-				cur->post_handler(cur, regs, 0);
-			}
-		}
-		reset_current_kprobe();
 	} else {
 		/*
 		 * The probe was removed and a race is in progress.
-- 
cgit v1.2.3


From c9abd554aa1231df2ad1dd5b30114c1552c2d956 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:12:22 +0900
Subject: arm64/kprobes: Don't call the ->break_handler() in arm64 kprobes code

Don't call the ->break_handler() from the arm64 kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/lkml/152942474231.15209.17684808374429473004.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/kernel/probes/kprobes.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 3ca2351109a6..076c3c0775a6 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -408,14 +408,6 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 				return;
 			}
 		}
-	} else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) ==
-	    BRK64_OPCODE_KPROBES) && cur_kprobe) {
-		/* We probably hit a jprobe.  Call its break handler. */
-		if (cur_kprobe->break_handler  &&
-		     cur_kprobe->break_handler(cur_kprobe, regs)) {
-			setup_singlestep(cur_kprobe, regs, kcb, 0);
-			return;
-		}
 	}
 	/*
 	 * The breakpoint instruction was removed right
-- 
cgit v1.2.3


From 6e5fd3a298e9ff74e5bf60f161e31cdb72f2e6bd Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:12:51 +0900
Subject: powerpc/kprobes: Don't call the ->break_handler() in powerpc kprobes
 code

Don't call the ->break_handler() from the powerpc kprobes code,
because it was only used by jprobes which got removed.

This also removes skip_singlestep() and embeds it in the
caller, kprobe_ftrace_handler(), which simplifies regs->nip
operation around there.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Link: https://lore.kernel.org/lkml/152942477127.15209.8982613703787878618.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/include/asm/kprobes.h   | 10 --------
 arch/powerpc/kernel/kprobes-ftrace.c | 46 ++++++++++--------------------------
 arch/powerpc/kernel/kprobes.c        | 31 +++++++++---------------
 3 files changed, 23 insertions(+), 64 deletions(-)

diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index 674036db558b..785c464b6588 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -102,16 +102,6 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
-#ifdef CONFIG_KPROBES_ON_FTRACE
-extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-			   struct kprobe_ctlblk *kcb);
-#else
-static inline int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-				  struct kprobe_ctlblk *kcb)
-{
-	return 0;
-}
-#endif
 #else
 static inline int kprobe_handler(struct pt_regs *regs) { return 0; }
 static inline int kprobe_post_handler(struct pt_regs *regs) { return 0; }
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 1b316331c2d9..070d1d862444 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -25,35 +25,6 @@
 #include <linux/preempt.h>
 #include <linux/ftrace.h>
 
-static nokprobe_inline
-int __skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		      struct kprobe_ctlblk *kcb, unsigned long orig_nip)
-{
-	/*
-	 * Emulate singlestep (and also recover regs->nip)
-	 * as if there is a nop
-	 */
-	regs->nip = (unsigned long)p->addr + MCOUNT_INSN_SIZE;
-	if (unlikely(p->post_handler)) {
-		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-		p->post_handler(p, regs, 0);
-	}
-	__this_cpu_write(current_kprobe, NULL);
-	if (orig_nip)
-		regs->nip = orig_nip;
-	return 1;
-}
-
-int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
-		    struct kprobe_ctlblk *kcb)
-{
-	if (kprobe_ftrace(p))
-		return __skip_singlestep(p, regs, kcb, 0);
-	else
-		return 0;
-}
-NOKPROBE_SYMBOL(skip_singlestep);
-
 /* Ftrace callback handler for kprobes */
 void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 			   struct ftrace_ops *ops, struct pt_regs *regs)
@@ -71,8 +42,6 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	if (kprobe_running()) {
 		kprobes_inc_nmissed_count(p);
 	} else {
-		unsigned long orig_nip = regs->nip;
-
 		/*
 		 * On powerpc, NIP is *before* this instruction for the
 		 * pre handler
@@ -81,9 +50,18 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-		if (!p->pre_handler || !p->pre_handler(p, regs))
-			__skip_singlestep(p, regs, kcb, orig_nip);
-		else {
+		if (!p->pre_handler || !p->pre_handler(p, regs)) {
+			/*
+			 * Emulate singlestep (and also recover regs->nip)
+			 * as if there is a nop
+			 */
+			regs->nip += MCOUNT_INSN_SIZE;
+			if (unlikely(p->post_handler)) {
+				kcb->kprobe_status = KPROBE_HIT_SSDONE;
+				p->post_handler(p, regs, 0);
+			}
+			__this_cpu_write(current_kprobe, NULL);
+		} else {
 			/*
 			 * If pre_handler returns !0, it sets regs->nip and
 			 * resets current kprobe. In this case, we should not
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 600678fce0a8..f06747e2e70d 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -317,25 +317,17 @@ int kprobe_handler(struct pt_regs *regs)
 			}
 			prepare_singlestep(p, regs);
 			return 1;
-		} else {
-			if (*addr != BREAKPOINT_INSTRUCTION) {
-				/* If trap variant, then it belongs not to us */
-				kprobe_opcode_t cur_insn = *addr;
-				if (is_trap(cur_insn))
-		       			goto no_kprobe;
-				/* The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
+		} else if (*addr != BREAKPOINT_INSTRUCTION) {
+			/* If trap variant, then it belongs not to us */
+			kprobe_opcode_t cur_insn = *addr;
+
+			if (is_trap(cur_insn))
 				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				if (!skip_singlestep(p, regs, kcb))
-					goto ss_probe;
-				ret = 1;
-			}
+			/* The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -350,7 +342,7 @@ int kprobe_handler(struct pt_regs *regs)
 			 */
 			kprobe_opcode_t cur_insn = *addr;
 			if (is_trap(cur_insn))
-		       		goto no_kprobe;
+				goto no_kprobe;
 			/*
 			 * The breakpoint instruction was removed right
 			 * after we hit it.  Another cpu has removed
@@ -370,7 +362,6 @@ int kprobe_handler(struct pt_regs *regs)
 		/* handler has already set things up, so skip ss setup */
 		return 1;
 
-ss_probe:
 	if (p->ainsn.boostable >= 0) {
 		ret = try_to_emulate(p, regs);
 
-- 
cgit v1.2.3


From cf3bb032fd753424e48d1bc580634768fc54aabe Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:13:20 +0900
Subject: ia64/kprobes: Don't call the ->break_handler() in ia64 kprobes code

Don't call the ->break_handler() from the ia64 kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-arch@vger.kernel.org
Cc: linux-ia64@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942480045.15209.10715901482832337704.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/ia64/include/uapi/asm/break.h |  1 -
 arch/ia64/kernel/kprobes.c         | 10 ----------
 2 files changed, 11 deletions(-)

diff --git a/arch/ia64/include/uapi/asm/break.h b/arch/ia64/include/uapi/asm/break.h
index 5d742bcb0018..4ca110f0a94b 100644
--- a/arch/ia64/include/uapi/asm/break.h
+++ b/arch/ia64/include/uapi/asm/break.h
@@ -14,7 +14,6 @@
  */
 #define __IA64_BREAK_KDB		0x80100
 #define __IA64_BREAK_KPROBE		0x81000 /* .. 0x81fff */
-#define __IA64_BREAK_JPROBE		0x82000
 
 /*
  * OS-specific break numbers:
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 823e4bd03a18..74c8524e6309 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -817,14 +817,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 			prepare_ss(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else if (args->err == __IA64_BREAK_JPROBE) {
-			/*
-			 * jprobe instrumented function just completed
-			 */
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		} else if (!is_ia64_break_inst(regs)) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
@@ -867,7 +859,6 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 		 */
 		return 1;
 
-ss_probe:
 #if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
 		/* Boost up -- we can execute copied instructions directly */
@@ -990,7 +981,6 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 	case DIE_BREAK:
 		/* err is break number from ia64_bad_break() */
 		if ((args->err >> 12) == (__IA64_BREAK_KPROBE >> 12)
-			|| args->err == __IA64_BREAK_JPROBE
 			|| args->err == 0)
 			if (pre_kprobes_handler(args))
 				ret = NOTIFY_STOP;
-- 
cgit v1.2.3


From 9b85753da73c5c10a9bee4d573be9503ad726b45 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:13:49 +0900
Subject: MIPS/kprobes: Don't call the ->break_handler() in MIPS kprobes code

Don't call the ->break_handler() from the MIPS kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-mips@linux-mips.org
Link: https://lore.kernel.org/lkml/152942482953.15209.843924518200700137.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/mips/kernel/kprobes.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index efdcd0b1ce12..7fd277bc59b9 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -326,19 +326,13 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 				preempt_enable_no_resched();
 			}
 			return 1;
-		} else {
-			if (addr->word != breakpoint_insn.word) {
-				/*
-				 * The breakpoint instruction was removed by
-				 * another cpu right after we hit, no further
-				 * handling of this interrupt is appropriate
-				 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+		} else if (addr->word != breakpoint_insn.word) {
+			/*
+			 * The breakpoint instruction was removed by
+			 * another cpu right after we hit, no further
+			 * handling of this interrupt is appropriate
+			 */
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -367,7 +361,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		return 1;
 	}
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	if (kcb->flags & SKIP_DELAYSLOT) {
 		kcb->kprobe_status = KPROBE_HIT_SSDONE;
-- 
cgit v1.2.3


From cba5ec980ca14b204bdb128be397ed1ddc1c7249 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:14:18 +0900
Subject: s390/kprobes: Don't call the ->break_handler() in s390 kprobes code

Don't call the ->break_handler() from the s390 kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-s390@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942485849.15209.16608277783809018031.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/s390/kernel/kprobes.c | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 0967de19f53d..3e34018960b5 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -332,26 +332,6 @@ static int kprobe_handler(struct pt_regs *regs)
 		}
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
 		return 1;
-	} else if (kprobe_running()) {
-		p = __this_cpu_read(current_kprobe);
-		if (p->break_handler && p->break_handler(p, regs)) {
-			/*
-			 * Continuation after the jprobe completed and
-			 * caused the jprobe_return trap. The jprobe
-			 * break_handler "returns" to the original
-			 * function that still has the kprobe breakpoint
-			 * installed. We continue with single stepping.
-			 */
-			kcb->kprobe_status = KPROBE_HIT_SS;
-			enable_singlestep(kcb, regs,
-					  (unsigned long) p->ainsn.insn);
-			return 1;
-		} /* else:
-		   * No kprobe at this address and the current kprobe
-		   * has no break handler (no jprobe!). The kernel just
-		   * exploded, let the standard trap handler pick up the
-		   * pieces.
-		   */
 	} /* else:
 	   * No kprobe at this address and no active kprobe. The trap has
 	   * not been caused by a kprobe breakpoint. The race of breakpoint
-- 
cgit v1.2.3


From fa5a24b16f94415d0a5da40bd479c26cfc6c15e3 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:14:47 +0900
Subject: sh/kprobes: Don't call the ->break_handler() in SH kprobes code

Don't call the ->break_handler() from the SH kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: linux-arch@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942488763.15209.7791710414058030809.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sh/kernel/kprobes.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 2b5e58873b96..4fafe0cd12c6 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -248,11 +248,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			prepare_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_REENTER;
 			return 1;
-		} else {
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs)) {
-				goto ss_probe;
-			}
 		}
 		goto no_kprobe;
 	}
@@ -281,7 +276,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 		/* handler has already set things up, so skip ss setup */
 		return 1;
 
-ss_probe:
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
@@ -508,14 +502,8 @@ int __kprobes kprobe_exceptions_notify(struct notifier_block *self,
 				if (post_kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
 			} else {
-				if (kprobe_handler(args->regs)) {
+				if (kprobe_handler(args->regs))
 					ret = NOTIFY_STOP;
-				} else {
-					p = __this_cpu_read(current_kprobe);
-					if (p->break_handler &&
-					    p->break_handler(p, args->regs))
-						ret = NOTIFY_STOP;
-				}
 			}
 		}
 	}
-- 
cgit v1.2.3


From d5ad85b6d9ac286ae7fa8718a8a1c28561349c07 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:15:17 +0900
Subject: sparc64/kprobes: Don't call the ->break_handler() in sparc64 kprobes
 code

Don't call the ->break_handler() from the sparc64 kprobes code,
because it was only used by jprobes which got removed.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: sparclinux@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942491684.15209.8114703769135529984.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sparc/kernel/kprobes.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index f555711da8f1..c684c96ef2e9 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -147,18 +147,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 			kcb->kprobe_status = KPROBE_REENTER;
 			prepare_singlestep(p, regs, kcb);
 			return 1;
-		} else {
-			if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
+		} else if (*(u32 *)addr != BREAKPOINT_INSTRUCTION) {
 			/* The breakpoint instruction was removed by
 			 * another cpu right after we hit, no further
 			 * handling of this interrupt is appropriate
 			 */
-				ret = 1;
-				goto no_kprobe;
-			}
-			p = __this_cpu_read(current_kprobe);
-			if (p->break_handler && p->break_handler(p, regs))
-				goto ss_probe;
+			ret = 1;
 		}
 		goto no_kprobe;
 	}
@@ -184,7 +178,6 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	if (p->pre_handler && p->pre_handler(p, regs))
 		return 1;
 
-ss_probe:
 	prepare_singlestep(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_SS;
 	return 1;
-- 
cgit v1.2.3


From cce188bd58cfbd603b904dbce75f34de2eff959a Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:15:45 +0900
Subject: bpf/error-inject/kprobes: Clear current_kprobe and enable preempt in
 kprobe

Clear current_kprobe and enable preemption in kprobe
even if pre_handler returns !0.

This simplifies function override using kprobes.

Jprobe used to require to keep the preemption disabled and
keep current_kprobe until it returned to original function
entry. For this reason kprobe_int3_handler() and similar
arch dependent kprobe handers checks pre_handler result
and exit without enabling preemption if the result is !0.

After removing the jprobe, Kprobes does not need to
keep preempt disabled even if user handler returns !0
anymore.

But since the function override handler in error-inject
and bpf is also returns !0 if it overrides a function,
to balancing the preempt count, it enables preemption
and reset current kprobe by itself.

That is a bad design that is very buggy. This fixes
such unbalanced preempt-count and current_kprobes setting
in kprobes, bpf and error-inject.

Note: for powerpc and x86, this removes all preempt_disable
from kprobe_ftrace_handler because ftrace callbacks are
called under preempt disabled.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Vineet Gupta <vgupta@synopsys.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: linux-arch@vger.kernel.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux-ia64@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-s390@vger.kernel.org
Cc: linux-sh@vger.kernel.org
Cc: linux-snps-arc@lists.infradead.org
Cc: linuxppc-dev@lists.ozlabs.org
Cc: sparclinux@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942494574.15209.12323837825873032258.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/kernel/kprobes.c            |  5 +++--
 arch/arm/probes/kprobes/core.c       | 10 +++++-----
 arch/arm64/kernel/probes/kprobes.c   | 10 +++++-----
 arch/ia64/kernel/kprobes.c           | 13 ++++---------
 arch/mips/kernel/kprobes.c           |  4 ++--
 arch/powerpc/kernel/kprobes-ftrace.c | 19 ++++++-------------
 arch/powerpc/kernel/kprobes.c        |  7 +++++--
 arch/s390/kernel/kprobes.c           |  7 ++++---
 arch/sh/kernel/kprobes.c             |  7 ++++---
 arch/sparc/kernel/kprobes.c          |  7 ++++---
 arch/x86/kernel/kprobes/core.c       |  4 ++++
 arch/x86/kernel/kprobes/ftrace.c     |  9 +++------
 kernel/fail_function.c               |  3 ---
 kernel/trace/trace_kprobe.c          | 11 +++--------
 14 files changed, 52 insertions(+), 64 deletions(-)

diff --git a/arch/arc/kernel/kprobes.c b/arch/arc/kernel/kprobes.c
index 465365696c91..df35d4c0b0b8 100644
--- a/arch/arc/kernel/kprobes.c
+++ b/arch/arc/kernel/kprobes.c
@@ -231,6 +231,9 @@ int __kprobes arc_kprobe_handler(unsigned long addr, struct pt_regs *regs)
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
 			setup_singlestep(p, regs);
 			kcb->kprobe_status = KPROBE_HIT_SS;
+		} else {
+			reset_current_kprobe();
+			preempt_enable_no_resched();
 		}
 
 		return 1;
@@ -442,9 +445,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	regs->ret = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 3192350f389d..8d37601fdb20 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -300,10 +300,10 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 
 			/*
 			 * If we have no pre-handler or it returned 0, we
-			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry,
-			 * so get out doing nothing more here.
+			 * continue with normal processing. If we have a
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				kcb->kprobe_status = KPROBE_HIT_SS;
@@ -312,8 +312,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 					kcb->kprobe_status = KPROBE_HIT_SSDONE;
 					p->post_handler(p, regs, 0);
 				}
-				reset_current_kprobe();
 			}
+			reset_current_kprobe();
 		}
 	} else {
 		/*
diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 076c3c0775a6..5daf3d721cb7 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -395,9 +395,9 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			/*
 			 * If we have no pre-handler or it returned 0, we
 			 * continue with normal processing.  If we have a
-			 * pre-handler and it returned non-zero, it prepped
-			 * for calling the break_handler below on re-entry,
-			 * so get out doing nothing more here.
+			 * pre-handler and it returned non-zero, it will
+			 * modify the execution path and no need to single
+			 * stepping. Let's just reset current kprobe and exit.
 			 *
 			 * pre_handler can hit a breakpoint and can step thru
 			 * before return, keep PSTATE D-flag enabled until
@@ -405,8 +405,8 @@ static void __kprobes kprobe_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs)) {
 				setup_singlestep(p, regs, kcb, 0);
-				return;
-			}
+			} else
+				reset_current_kprobe();
 		}
 	}
 	/*
diff --git a/arch/ia64/kernel/kprobes.c b/arch/ia64/kernel/kprobes.c
index 74c8524e6309..aa41bd5cf9b7 100644
--- a/arch/ia64/kernel/kprobes.c
+++ b/arch/ia64/kernel/kprobes.c
@@ -478,12 +478,9 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 			 */
 			break;
 	}
-
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
@@ -851,13 +848,11 @@ static int __kprobes pre_kprobes_handler(struct die_args *args)
 	set_current_kprobe(p, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/*
-		 * Our pre-handler is specifically requesting that we just
-		 * do a return.  This is used for both the jprobe pre-handler
-		 * and the kretprobe trampoline
-		 */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 #if !defined(CONFIG_PREEMPT)
 	if (p->ainsn.inst_flag == INST_FLAG_BOOSTABLE && !p->post_handler) {
diff --git a/arch/mips/kernel/kprobes.c b/arch/mips/kernel/kprobes.c
index 7fd277bc59b9..54cd675c5d1d 100644
--- a/arch/mips/kernel/kprobes.c
+++ b/arch/mips/kernel/kprobes.c
@@ -358,6 +358,8 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
 	}
 
@@ -543,9 +545,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	kretprobe_assert(ri, orig_ret_address, trampoline_address);
 	instruction_pointer(regs) = orig_ret_address;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
index 070d1d862444..e4a49c051325 100644
--- a/arch/powerpc/kernel/kprobes-ftrace.c
+++ b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -32,11 +32,9 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
-	preempt_disable();
-
 	p = get_kprobe((kprobe_opcode_t *)nip);
 	if (unlikely(!p) || kprobe_disabled(p))
-		goto end;
+		return;
 
 	kcb = get_kprobe_ctlblk();
 	if (kprobe_running()) {
@@ -60,18 +58,13 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 				kcb->kprobe_status = KPROBE_HIT_SSDONE;
 				p->post_handler(p, regs, 0);
 			}
-			__this_cpu_write(current_kprobe, NULL);
-		} else {
-			/*
-			 * If pre_handler returns !0, it sets regs->nip and
-			 * resets current kprobe. In this case, we should not
-			 * re-enable preemption.
-			 */
-			return;
 		}
+		/*
+		 * If pre_handler returns !0, it changes regs->nip. We have to
+		 * skip emulating post_handler.
+		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
-end:
-	preempt_enable_no_resched();
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index f06747e2e70d..5c60bb0f927f 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -358,9 +358,12 @@ int kprobe_handler(struct pt_regs *regs)
 
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 	set_current_kprobe(p, regs, kcb);
-	if (p->pre_handler && p->pre_handler(p, regs))
-		/* handler has already set things up, so skip ss setup */
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		/* handler changed execution path, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 	if (p->ainsn.boostable >= 0) {
 		ret = try_to_emulate(p, regs);
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3e34018960b5..7c0a095e9c5f 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -326,8 +326,11 @@ static int kprobe_handler(struct pt_regs *regs)
 			 */
 			push_kprobe(kcb, p);
 			kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-			if (p->pre_handler && p->pre_handler(p, regs))
+			if (p->pre_handler && p->pre_handler(p, regs)) {
+				pop_kprobe(kcb);
+				preempt_enable_no_resched();
 				return 1;
+			}
 			kcb->kprobe_status = KPROBE_HIT_SS;
 		}
 		enable_singlestep(kcb, regs, (unsigned long) p->ainsn.insn);
@@ -431,9 +434,7 @@ static int trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 
 	regs->psw.addr = orig_ret_address;
 
-	pop_kprobe(get_kprobe_ctlblk());
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/sh/kernel/kprobes.c b/arch/sh/kernel/kprobes.c
index 4fafe0cd12c6..241e903dd3ee 100644
--- a/arch/sh/kernel/kprobes.c
+++ b/arch/sh/kernel/kprobes.c
@@ -272,9 +272,12 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
 		/* handler has already set things up, so skip ss setup */
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 	prepare_singlestep(p, regs);
 	kcb->kprobe_status = KPROBE_HIT_SS;
@@ -352,8 +355,6 @@ int __kprobes trampoline_probe_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->pc = orig_ret_address;
 	kretprobe_hash_unlock(current, &flags);
 
-	preempt_enable_no_resched();
-
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
 		kfree(ri);
diff --git a/arch/sparc/kernel/kprobes.c b/arch/sparc/kernel/kprobes.c
index c684c96ef2e9..dfbca2470536 100644
--- a/arch/sparc/kernel/kprobes.c
+++ b/arch/sparc/kernel/kprobes.c
@@ -175,8 +175,11 @@ static int __kprobes kprobe_handler(struct pt_regs *regs)
 
 	set_current_kprobe(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-	if (p->pre_handler && p->pre_handler(p, regs))
+	if (p->pre_handler && p->pre_handler(p, regs)) {
+		reset_current_kprobe();
+		preempt_enable_no_resched();
 		return 1;
+	}
 
 	prepare_singlestep(p, regs, kcb);
 	kcb->kprobe_status = KPROBE_HIT_SS;
@@ -508,9 +511,7 @@ static int __kprobes trampoline_probe_handler(struct kprobe *p,
 	regs->tpc = orig_ret_address;
 	regs->tnpc = orig_ret_address + 4;
 
-	reset_current_kprobe();
 	kretprobe_hash_unlock(current, &flags);
-	preempt_enable_no_resched();
 
 	hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) {
 		hlist_del(&ri->hlist);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 0ac16a0d93e5..814e26b7c8a2 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -694,6 +694,10 @@ int kprobe_int3_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
 				setup_singlestep(p, regs, kcb, 0);
+			else {
+				reset_current_kprobe();
+				preempt_enable_no_resched();
+			}
 			return 1;
 		}
 	} else if (*addr != BREAKPOINT_INSTRUCTION) {
diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
index 02a6dd1b6bd0..ef819e19650b 100644
--- a/arch/x86/kernel/kprobes/ftrace.c
+++ b/arch/x86/kernel/kprobes/ftrace.c
@@ -45,8 +45,6 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 		/* Kprobe handler expects regs->ip = ip + 1 as breakpoint hit */
 		regs->ip = ip + sizeof(kprobe_opcode_t);
 
-		/* To emulate trap based kprobes, preempt_disable here */
-		preempt_disable();
 		__this_cpu_write(current_kprobe, p);
 		kcb->kprobe_status = KPROBE_HIT_ACTIVE;
 		if (!p->pre_handler || !p->pre_handler(p, regs)) {
@@ -60,13 +58,12 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 				p->post_handler(p, regs, 0);
 			}
 			regs->ip = orig_ip;
-			__this_cpu_write(current_kprobe, NULL);
-			preempt_enable_no_resched();
 		}
 		/*
-		 * If pre_handler returns !0, it sets regs->ip and
-		 * resets current kprobe, and keep preempt count +1.
+		 * If pre_handler returns !0, it changes regs->ip. We have to
+		 * skip emulating post_handler.
 		 */
+		__this_cpu_write(current_kprobe, NULL);
 	}
 }
 NOKPROBE_SYMBOL(kprobe_ftrace_handler);
diff --git a/kernel/fail_function.c b/kernel/fail_function.c
index 5349c91c2298..bc80a4e268c0 100644
--- a/kernel/fail_function.c
+++ b/kernel/fail_function.c
@@ -184,9 +184,6 @@ static int fei_kprobe_handler(struct kprobe *kp, struct pt_regs *regs)
 	if (should_fail(&fei_fault_attr, 1)) {
 		regs_set_return_value(regs, attr->retval);
 		override_function_with_return(regs);
-		/* Kprobe specific fixup */
-		reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index daa81571b22a..7e3b944b6ac1 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1217,16 +1217,11 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 		/*
 		 * We need to check and see if we modified the pc of the
-		 * pt_regs, and if so clear the kprobe and return 1 so that we
-		 * don't do the single stepping.
-		 * The ftrace kprobe handler leaves it up to us to re-enable
-		 * preemption here before returning if we've modified the ip.
+		 * pt_regs, and if so return 1 so that we don't do the
+		 * single stepping.
 		 */
-		if (orig_ip != instruction_pointer(regs)) {
-			reset_current_kprobe();
-			preempt_enable_no_resched();
+		if (orig_ip != instruction_pointer(regs))
 			return 1;
-		}
 		if (!ret)
 			return 0;
 	}
-- 
cgit v1.2.3


From 2bbda764d720aacabaad38374d26fcccb7843f17 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:16:17 +0900
Subject: kprobes/x86: Do not disable preempt on int3 path

Since int3 and debug exception(for singlestep) are run with
IRQ disabled and while running single stepping we drop IF
from regs->flags, that path must not be preemptible. So we
can remove the preempt disable/enable calls from that path.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942497779.15209.2879580696589868291.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/kprobes.txt      | 11 +++++------
 arch/x86/kernel/kprobes/core.c | 18 ++++--------------
 arch/x86/kernel/kprobes/opt.c  |  1 -
 3 files changed, 9 insertions(+), 21 deletions(-)

diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index ab2c7307f123..cbb545910634 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -566,12 +566,11 @@ the same handler) may run concurrently on different CPUs.
 Kprobes does not use mutexes or allocate memory except during
 registration and unregistration.
 
-Probe handlers are run with preemption disabled.  Depending on the
-architecture and optimization state, handlers may also run with
-interrupts disabled (e.g., kretprobe handlers and optimized kprobe
-handlers run without interrupt disabled on x86/x86-64).  In any case,
-your handler should not yield the CPU (e.g., by attempting to acquire
-a semaphore).
+Probe handlers are run with preemption disabled or interrupt disabled,
+which depends on the architecture and optimization state.  (e.g.,
+kretprobe handlers and optimized kprobe handlers run without interrupt
+disabled on x86/x86-64).  In any case, your handler should not yield
+the CPU (e.g., by attempting to acquire a semaphore, or waiting I/O).
 
 Since a return probe is implemented by replacing the return
 address with the trampoline's address, stack backtraces and calls
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 814e26b7c8a2..f7104b256de7 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -594,7 +594,6 @@ static void setup_singlestep(struct kprobe *p, struct pt_regs *regs,
 		 * stepping.
 		 */
 		regs->ip = (unsigned long)p->ainsn.insn;
-		preempt_enable_no_resched();
 		return;
 	}
 #endif
@@ -667,12 +666,10 @@ int kprobe_int3_handler(struct pt_regs *regs)
 
 	addr = (kprobe_opcode_t *)(regs->ip - sizeof(kprobe_opcode_t));
 	/*
-	 * We don't want to be preempted for the entire
-	 * duration of kprobe processing. We conditionally
-	 * re-enable preemption at the end of this function,
-	 * and also in reenter_kprobe() and setup_singlestep().
+	 * We don't want to be preempted for the entire duration of kprobe
+	 * processing. Since int3 and debug trap disables irqs and we clear
+	 * IF while singlestepping, it must be no preemptible.
 	 */
-	preempt_disable();
 
 	kcb = get_kprobe_ctlblk();
 	p = get_kprobe(addr);
@@ -694,10 +691,8 @@ int kprobe_int3_handler(struct pt_regs *regs)
 			 */
 			if (!p->pre_handler || !p->pre_handler(p, regs))
 				setup_singlestep(p, regs, kcb, 0);
-			else {
+			else
 				reset_current_kprobe();
-				preempt_enable_no_resched();
-			}
 			return 1;
 		}
 	} else if (*addr != BREAKPOINT_INSTRUCTION) {
@@ -711,11 +706,9 @@ int kprobe_int3_handler(struct pt_regs *regs)
 		 * the original instruction.
 		 */
 		regs->ip = (unsigned long)addr;
-		preempt_enable_no_resched();
 		return 1;
 	} /* else: not a kprobe fault; let the kernel handle it */
 
-	preempt_enable_no_resched();
 	return 0;
 }
 NOKPROBE_SYMBOL(kprobe_int3_handler);
@@ -966,8 +959,6 @@ int kprobe_debug_handler(struct pt_regs *regs)
 	}
 	reset_current_kprobe();
 out:
-	preempt_enable_no_resched();
-
 	/*
 	 * if somebody else is singlestepping across a probe point, flags
 	 * will have TF set, in which case, continue the remaining processing
@@ -1014,7 +1005,6 @@ int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
 			restore_previous_kprobe(kcb);
 		else
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 	} else if (kcb->kprobe_status == KPROBE_HIT_ACTIVE ||
 		   kcb->kprobe_status == KPROBE_HIT_SSDONE) {
 		/*
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 203d398802a3..eaf02f2e7300 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -491,7 +491,6 @@ int setup_detour_execution(struct kprobe *p, struct pt_regs *regs, int reenter)
 		regs->ip = (unsigned long)op->optinsn.insn + TMPL_END_IDX;
 		if (!reenter)
 			reset_current_kprobe();
-		preempt_enable_no_resched();
 		return 1;
 	}
 	return 0;
-- 
cgit v1.2.3


From dcce32d952eddcd427f648ebd04339cfbf305e23 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:16:46 +0900
Subject: Documentation/kprobes: Add how to change the execution path

Add a section that explaining how to change the execution
path with kprobes and warnings for some arch.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942500680.15209.12374262914863044775.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/kprobes.txt | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index cbb545910634..13d8efdb9718 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -80,6 +80,26 @@ After the instruction is single-stepped, Kprobes executes the
 "post_handler," if any, that is associated with the kprobe.
 Execution then continues with the instruction following the probepoint.
 
+Changing Execution Path
+-----------------------
+
+Since the kprobes can probe into a running kernel code, it can change
+the register set, including instruction pointer. This operation
+requires maximum attention, such as keeping the stack frame, recovering
+execution path etc. Since it is operated on running kernel and need deep
+knowladge of the archtecture and concurrent computing, you can easily
+shot your foot.
+
+If you change the instruction pointer (and set up other related
+registers) in pre_handler, you must return !0 so that the kprobes
+stops single stepping and just returns to given address.
+This also means post_handler should not be called anymore.
+
+Note that this operation may be harder on some architectures which
+use TOC (Table of Contents) for function call, since you have to
+setup new TOC for your function in your module, and recover old
+one after back from it.
+
 Return Probes
 -------------
 
-- 
cgit v1.2.3


From 4de58696de076d9bd2745d1cbe0930635c3f5ac9 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Wed, 20 Jun 2018 01:17:15 +0900
Subject: kprobes: Remove jprobe stub API

Remove jprobe stub APIs from linux/kprobes.h since
the jprobe implementation was completely gone.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-arch@vger.kernel.org
Link: https://lore.kernel.org/lkml/152942503572.15209.1652552217914694917.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/kprobes.h | 50 -------------------------------------------------
 1 file changed, 50 deletions(-)

diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index b520baa65682..e909413e4e38 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -63,7 +63,6 @@ struct pt_regs;
 struct kretprobe;
 struct kretprobe_instance;
 typedef int (*kprobe_pre_handler_t) (struct kprobe *, struct pt_regs *);
-typedef int (*kprobe_break_handler_t) (struct kprobe *, struct pt_regs *);
 typedef void (*kprobe_post_handler_t) (struct kprobe *, struct pt_regs *,
 				       unsigned long flags);
 typedef int (*kprobe_fault_handler_t) (struct kprobe *, struct pt_regs *,
@@ -101,12 +100,6 @@ struct kprobe {
 	 */
 	kprobe_fault_handler_t fault_handler;
 
-	/*
-	 * ... called if breakpoint trap occurs in probe handler.
-	 * Return 1 if it handled break, otherwise kernel will see it.
-	 */
-	kprobe_break_handler_t break_handler;
-
 	/* Saved opcode (which has been replaced with breakpoint) */
 	kprobe_opcode_t opcode;
 
@@ -154,24 +147,6 @@ static inline int kprobe_ftrace(struct kprobe *p)
 	return p->flags & KPROBE_FLAG_FTRACE;
 }
 
-/*
- * Special probe type that uses setjmp-longjmp type tricks to resume
- * execution at a specified entry with a matching prototype corresponding
- * to the probed function - a trick to enable arguments to become
- * accessible seamlessly by probe handling logic.
- * Note:
- * Because of the way compilers allocate stack space for local variables
- * etc upfront, regardless of sub-scopes within a function, this mirroring
- * principle currently works only for probes placed on function entry points.
- */
-struct jprobe {
-	struct kprobe kp;
-	void *entry;	/* probe handling code to jump to */
-};
-
-/* For backward compatibility with old code using JPROBE_ENTRY() */
-#define JPROBE_ENTRY(handler)	(handler)
-
 /*
  * Function-return probe -
  * Note:
@@ -436,9 +411,6 @@ static inline void unregister_kprobe(struct kprobe *p)
 static inline void unregister_kprobes(struct kprobe **kps, int num)
 {
 }
-static inline void jprobe_return(void)
-{
-}
 static inline int register_kretprobe(struct kretprobe *rp)
 {
 	return -ENOSYS;
@@ -465,20 +437,6 @@ static inline int enable_kprobe(struct kprobe *kp)
 	return -ENOSYS;
 }
 #endif /* CONFIG_KPROBES */
-static inline int register_jprobe(struct jprobe *p)
-{
-	return -ENOSYS;
-}
-static inline int register_jprobes(struct jprobe **jps, int num)
-{
-	return -ENOSYS;
-}
-static inline void unregister_jprobe(struct jprobe *p)
-{
-}
-static inline void unregister_jprobes(struct jprobe **jps, int num)
-{
-}
 static inline int disable_kretprobe(struct kretprobe *rp)
 {
 	return disable_kprobe(&rp->kp);
@@ -487,14 +445,6 @@ static inline int enable_kretprobe(struct kretprobe *rp)
 {
 	return enable_kprobe(&rp->kp);
 }
-static inline int disable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
-static inline int enable_jprobe(struct jprobe *jp)
-{
-	return -ENOSYS;
-}
 
 #ifndef CONFIG_KPROBES
 static inline bool is_kprobe_insn_slot(unsigned long addr)
-- 
cgit v1.2.3


From a70cee9737802654bbbddec027d1d57b7ff24a2c Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:06 +0100
Subject: locking/atomics/h8300: Don't include <linux/kernel.h> in
 <asm/atomic.h>

<linux/kernel.h> isn't needed by <asm/atomic.h> and will result in circular
dependencies when the asm-generic atomic bitops are built around the
atomic_long_t interface.

Remove the broad include and replace it with <linux/compiler.h> for
READ_ONCE() etc and <asm/irqflags.h> for arch_local_irq_save() etc.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-2-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/h8300/include/asm/atomic.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 941e7554e886..b174dec099bf 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -2,8 +2,10 @@
 #ifndef __ARCH_H8300_ATOMIC__
 #define __ARCH_H8300_ATOMIC__
 
+#include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/irqflags.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for
@@ -15,8 +17,6 @@
 #define atomic_read(v)		READ_ONCE((v)->counter)
 #define atomic_set(v, i)	WRITE_ONCE(((v)->counter), (i))
 
-#include <linux/kernel.h>
-
 #define ATOMIC_OP_RETURN(op, c_op)				\
 static inline int atomic_##op##_return(int i, atomic_t *v)	\
 {								\
-- 
cgit v1.2.3


From 84038fd98e8e03ec418e3244b98eb248c5349d7e Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:07 +0100
Subject: locking/atomics/m68k: Don't use <asm-generic/bitops/lock.h>

<asm-generic/bitops/lock.h> is shortly going to be built on top of the
atomic_long_*() API, which introduces a nasty circular dependency for
m68k where <linux/atomic.h> pulls in <linux/bitops.h> via:

	linux/atomic.h
	asm/atomic.h
	linux/irqflags.h
	asm/irqflags.h
	linux/preempt.h
	asm/preempt.h
	asm-generic/preempt.h
	linux/thread_info.h
	asm/thread_info.h
	asm/page.h
	asm-generic/getorder.h
	linux/log2.h
	linux/bitops.h

Since m68k isn't SMP and doesn't support ACQUIRE/RELEASE barriers, we
can just define the lock bitops in terms of the atomic bitops in the
<asm/bitops.h> header.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-3-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/m68k/include/asm/bitops.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 93b47b1f6fb4..18193419f97d 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -515,12 +515,16 @@ static inline int __fls(int x)
 
 #endif
 
+/* Simple test-and-set bit locks */
+#define test_and_set_bit_lock	test_and_set_bit
+#define clear_bit_unlock	clear_bit
+#define __clear_bit_unlock	clear_bit_unlock
+
 #include <asm-generic/bitops/ext2-atomic.h>
 #include <asm-generic/bitops/le.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 #endif /* __KERNEL__ */
 
 #endif /* _M68K_BITOPS_H */
-- 
cgit v1.2.3


From 8bd9cb51daac89337295b6f037b0486911e1b408 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:08 +0100
Subject: locking/atomics, asm-generic: Move some macros from <linux/bitops.h>
 to a new <linux/bits.h> file

In preparation for implementing the asm-generic atomic bitops in terms
of atomic_long_*(), we need to prevent <asm/atomic.h> implementations from
pulling in <linux/bitops.h>. A common reason for this include is for the
BITS_PER_BYTE definition, so move this and some other BIT() and masking
macros into a new header file, <linux/bits.h>.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-4-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/bitops.h | 22 +---------------------
 include/linux/bits.h   | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+), 21 deletions(-)
 create mode 100644 include/linux/bits.h

diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 4cac4e1a72ff..af419012d77d 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -2,29 +2,9 @@
 #ifndef _LINUX_BITOPS_H
 #define _LINUX_BITOPS_H
 #include <asm/types.h>
+#include <linux/bits.h>
 
-#ifdef	__KERNEL__
-#define BIT(nr)			(1UL << (nr))
-#define BIT_ULL(nr)		(1ULL << (nr))
-#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
-#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
-#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
-#define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
-#endif
-
-/*
- * Create a contiguous bitmask starting at bit position @l and ending at
- * position @h. For example
- * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
- */
-#define GENMASK(h, l) \
-	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
-
-#define GENMASK_ULL(h, l) \
-	(((~0ULL) - (1ULL << (l)) + 1) & \
-	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
 
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
diff --git a/include/linux/bits.h b/include/linux/bits.h
new file mode 100644
index 000000000000..2b7b532c1d51
--- /dev/null
+++ b/include/linux/bits.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITS_H
+#define __LINUX_BITS_H
+#include <asm/bitsperlong.h>
+
+#define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
+#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
+#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
+#define BITS_PER_BYTE		8
+
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l) \
+	(((~0UL) - (1UL << (l)) + 1) & (~0UL >> (BITS_PER_LONG - 1 - (h))))
+
+#define GENMASK_ULL(h, l) \
+	(((~0ULL) - (1ULL << (l)) + 1) & \
+	 (~0ULL >> (BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif	/* __LINUX_BITS_H */
-- 
cgit v1.2.3


From b22d73c2bd76a6d05256dcd3262d00b5f5af09f4 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:09 +0100
Subject: locking/atomics/openrisc: Don't pull in all of <linux/bitops.h> in
 <asm/cmpxchg.h>

The openrisc implementation of <asm/cmpxchg.h> pulls in <linux/bitops.h>,
so that it can refer to BITS_PER_BYTE. It also transitively relies on
this pulling in <linux/compiler.h> for READ_ONCE().

Replace the #include with <linux/bits.h> and <linux/compiler.h>.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-5-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/openrisc/include/asm/cmpxchg.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/openrisc/include/asm/cmpxchg.h b/arch/openrisc/include/asm/cmpxchg.h
index d29f7db53906..f9cd43a39d72 100644
--- a/arch/openrisc/include/asm/cmpxchg.h
+++ b/arch/openrisc/include/asm/cmpxchg.h
@@ -16,8 +16,9 @@
 #ifndef __ASM_OPENRISC_CMPXCHG_H
 #define __ASM_OPENRISC_CMPXCHG_H
 
+#include  <linux/bits.h>
+#include  <linux/compiler.h>
 #include  <linux/types.h>
-#include  <linux/bitops.h>
 
 #define __HAVE_ARCH_CMPXCHG 1
 
-- 
cgit v1.2.3


From 1c2672b49aa49d4fdc69d4ebbaf959264051e34a Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:10 +0100
Subject: locking/atomics/sh: Don't pull in all of <linux/bitops.h> in
 <asm/cmpxchg-xchg.h>

The sh implementation of <asm/cmpxchg-xchg.h> pulls in <linux/bitops.h>
so that it can refer to BITS_PER_BYTE. It also transitively relies on
this pulling in <linux/compiler.h> for READ_ONCE().

Replace the #include with <linux/bits.h> and <linux/compiler.h>.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-6-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sh/include/asm/cmpxchg-xchg.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/sh/include/asm/cmpxchg-xchg.h b/arch/sh/include/asm/cmpxchg-xchg.h
index 1e881f5db659..593a9704782b 100644
--- a/arch/sh/include/asm/cmpxchg-xchg.h
+++ b/arch/sh/include/asm/cmpxchg-xchg.h
@@ -8,7 +8,8 @@
  * This work is licensed under the terms of the GNU GPL, version 2.  See the
  * file "COPYING" in the main directory of this archive for more details.
  */
-#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/compiler.h>
 #include <asm/byteorder.h>
 
 /*
-- 
cgit v1.2.3


From e986a0d6cb36b54838b2f5f8ac2bb5f9baadd977 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:11 +0100
Subject: locking/atomics, asm-generic/bitops/atomic.h: Rewrite using
 atomic_*() APIs

The atomic bitops can actually be implemented pretty efficiently using
the atomic_*() ops, rather than explicit use of spinlocks.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-7-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/bitops/atomic.h | 188 +++++++-----------------------------
 1 file changed, 33 insertions(+), 155 deletions(-)

diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h
index 04deffaf5f7d..dd90c9792909 100644
--- a/include/asm-generic/bitops/atomic.h
+++ b/include/asm-generic/bitops/atomic.h
@@ -2,189 +2,67 @@
 #ifndef _ASM_GENERIC_BITOPS_ATOMIC_H_
 #define _ASM_GENERIC_BITOPS_ATOMIC_H_
 
-#include <asm/types.h>
-#include <linux/irqflags.h>
-
-#ifdef CONFIG_SMP
-#include <asm/spinlock.h>
-#include <asm/cache.h>		/* we use L1_CACHE_BYTES */
-
-/* Use an array of spinlocks for our atomic_ts.
- * Hash function to index into a different SPINLOCK.
- * Since "a" is usually an address, use one spinlock per cacheline.
- */
-#  define ATOMIC_HASH_SIZE 4
-#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
-
-extern arch_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
-
-/* Can't use raw_spin_lock_irq because of #include problems, so
- * this is the substitute */
-#define _atomic_spin_lock_irqsave(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);	\
-	local_irq_save(f);			\
-	arch_spin_lock(s);			\
-} while(0)
-
-#define _atomic_spin_unlock_irqrestore(l,f) do {	\
-	arch_spinlock_t *s = ATOMIC_HASH(l);		\
-	arch_spin_unlock(s);				\
-	local_irq_restore(f);				\
-} while(0)
-
-
-#else
-#  define _atomic_spin_lock_irqsave(l,f) do { local_irq_save(f); } while (0)
-#  define _atomic_spin_unlock_irqrestore(l,f) do { local_irq_restore(f); } while (0)
-#endif
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
 
 /*
- * NMI events can occur at any time, including when interrupts have been
- * disabled by *_irqsave().  So you can get NMI events occurring while a
- * *_bit function is holding a spin lock.  If the NMI handler also wants
- * to do bit manipulation (and they do) then you can get a deadlock
- * between the original caller of *_bit() and the NMI handler.
- *
- * by Keith Owens
+ * Implementation of atomic bitops using atomic-fetch ops.
+ * See Documentation/atomic_bitops.txt for details.
  */
 
-/**
- * set_bit - Atomically set a bit in memory
- * @nr: the bit to set
- * @addr: the address to start counting from
- *
- * This function is atomic and may not be reordered.  See __set_bit()
- * if you do not require the atomic guarantees.
- *
- * Note: there are no guarantees that this function will not be reordered
- * on non x86 architectures, so if you are writing portable code,
- * make sure not to rely on its reordering guarantees.
- *
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void set_bit(int nr, volatile unsigned long *addr)
+static inline void set_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p  |= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_or(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * clear_bit - Clears a bit in memory
- * @nr: Bit to clear
- * @addr: Address to start counting from
- *
- * clear_bit() is atomic and may not be reordered.  However, it does
- * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
- * in order to ensure changes are visible on other processors.
- */
-static inline void clear_bit(int nr, volatile unsigned long *addr)
+static inline void clear_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p &= ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_andnot(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * change_bit - Toggle a bit in memory
- * @nr: Bit to change
- * @addr: Address to start counting from
- *
- * change_bit() is atomic and may not be reordered. It may be
- * reordered on other architectures than x86.
- * Note that @nr may be almost arbitrarily large; this function is not
- * restricted to acting on a single-word quantity.
- */
-static inline void change_bit(int nr, volatile unsigned long *addr)
+static inline void change_bit(unsigned int nr, volatile unsigned long *p)
 {
-	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	*p ^= mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	atomic_long_xor(BIT_MASK(nr), (atomic_long_t *)p);
 }
 
-/**
- * test_and_set_bit - Set a bit and return its old value
- * @nr: Bit to set
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It may be reordered on other architectures than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_set_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old | mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_or(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_clear_bit - Clear a bit and return its old value
- * @nr: Bit to clear
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It can be reorderdered on other architectures other than x86.
- * It also implies a memory barrier.
- */
-static inline int test_and_clear_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_clear_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
 
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old & ~mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
+	p += BIT_WORD(nr);
+	if (!(READ_ONCE(*p) & mask))
+		return 0;
 
-	return (old & mask) != 0;
+	old = atomic_long_fetch_andnot(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
-/**
- * test_and_change_bit - Change a bit and return its old value
- * @nr: Bit to change
- * @addr: Address to count from
- *
- * This operation is atomic and cannot be reordered.
- * It also implies a memory barrier.
- */
-static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
+static inline int test_and_change_bit(unsigned int nr, volatile unsigned long *p)
 {
+	long old;
 	unsigned long mask = BIT_MASK(nr);
-	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
-	unsigned long old;
-	unsigned long flags;
-
-	_atomic_spin_lock_irqsave(p, flags);
-	old = *p;
-	*p = old ^ mask;
-	_atomic_spin_unlock_irqrestore(p, flags);
 
-	return (old & mask) != 0;
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_xor(mask, (atomic_long_t *)p);
+	return !!(old & mask);
 }
 
 #endif /* _ASM_GENERIC_BITOPS_ATOMIC_H */
-- 
cgit v1.2.3


From 84c6591103dbeaf393a092a3fc7b09510825f6b9 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:12 +0100
Subject: locking/atomics, asm-generic/bitops/lock.h: Rewrite using
 atomic_fetch_*()

The lock bitops can be implemented more efficiently using the atomic_fetch_*()
ops, which provide finer-grained control over the memory ordering semantics
than the bitops.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-8-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/bitops/lock.h | 68 ++++++++++++++++++++++++++++++++-------
 1 file changed, 56 insertions(+), 12 deletions(-)

diff --git a/include/asm-generic/bitops/lock.h b/include/asm-generic/bitops/lock.h
index 67ab280ad134..3ae021368f48 100644
--- a/include/asm-generic/bitops/lock.h
+++ b/include/asm-generic/bitops/lock.h
@@ -2,6 +2,10 @@
 #ifndef _ASM_GENERIC_BITOPS_LOCK_H_
 #define _ASM_GENERIC_BITOPS_LOCK_H_
 
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
 /**
  * test_and_set_bit_lock - Set a bit and return its old value, for lock
  * @nr: Bit to set
@@ -11,7 +15,20 @@
  * the returned value is 0.
  * It can be used to implement bit locks.
  */
-#define test_and_set_bit_lock(nr, addr)	test_and_set_bit(nr, addr)
+static inline int test_and_set_bit_lock(unsigned int nr,
+					volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	if (READ_ONCE(*p) & mask)
+		return 1;
+
+	old = atomic_long_fetch_or_acquire(mask, (atomic_long_t *)p);
+	return !!(old & mask);
+}
+
 
 /**
  * clear_bit_unlock - Clear a bit in memory, for unlock
@@ -20,11 +37,11 @@
  *
  * This operation is atomic and provides release barrier semantics.
  */
-#define clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void clear_bit_unlock(unsigned int nr, volatile unsigned long *p)
+{
+	p += BIT_WORD(nr);
+	atomic_long_fetch_andnot_release(BIT_MASK(nr), (atomic_long_t *)p);
+}
 
 /**
  * __clear_bit_unlock - Clear a bit in memory, for unlock
@@ -37,11 +54,38 @@ do {					\
  *
  * See for example x86's implementation.
  */
-#define __clear_bit_unlock(nr, addr)	\
-do {					\
-	smp_mb__before_atomic();	\
-	clear_bit(nr, addr);		\
-} while (0)
+static inline void __clear_bit_unlock(unsigned int nr,
+				      volatile unsigned long *p)
+{
+	unsigned long old;
 
-#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
+	p += BIT_WORD(nr);
+	old = READ_ONCE(*p);
+	old &= ~BIT_MASK(nr);
+	atomic_long_set_release((atomic_long_t *)p, old);
+}
+
+/**
+ * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
+ *                                     byte is negative, for unlock.
+ * @nr: the bit to clear
+ * @addr: the address to start counting from
+ *
+ * This is a bit of a one-trick-pony for the filemap code, which clears
+ * PG_locked and tests PG_waiters,
+ */
+#ifndef clear_bit_unlock_is_negative_byte
+static inline bool clear_bit_unlock_is_negative_byte(unsigned int nr,
+						     volatile unsigned long *p)
+{
+	long old;
+	unsigned long mask = BIT_MASK(nr);
+
+	p += BIT_WORD(nr);
+	old = atomic_long_fetch_andnot_release(mask, (atomic_long_t *)p);
+	return !!(old & BIT(7));
+}
+#define clear_bit_unlock_is_negative_byte clear_bit_unlock_is_negative_byte
+#endif
 
+#endif /* _ASM_GENERIC_BITOPS_LOCK_H_ */
-- 
cgit v1.2.3


From 7c8fc35dfc32dfa97d8a1dc25dbd064cf83936db Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:13 +0100
Subject: locking/atomics/arm64: Replace our atomic/lock bitop implementations
 with asm-generic

The <asm-generic/bitops/{atomic,lock}.h> implementations are built around
the atomic-fetch ops, which we implement efficiently for both LSE and
LL/SC systems. Use that instead of our hand-rolled, out-of-line bitops.S.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-9-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/include/asm/bitops.h | 14 ++------
 arch/arm64/lib/Makefile         |  2 +-
 arch/arm64/lib/bitops.S         | 76 -----------------------------------------
 3 files changed, 3 insertions(+), 89 deletions(-)
 delete mode 100644 arch/arm64/lib/bitops.S

diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h
index 9c19594ce7cb..13501460be6b 100644
--- a/arch/arm64/include/asm/bitops.h
+++ b/arch/arm64/include/asm/bitops.h
@@ -17,22 +17,11 @@
 #define __ASM_BITOPS_H
 
 #include <linux/compiler.h>
-#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
 #endif
 
-/*
- * Little endian assembly atomic bitops.
- */
-extern void set_bit(int nr, volatile unsigned long *p);
-extern void clear_bit(int nr, volatile unsigned long *p);
-extern void change_bit(int nr, volatile unsigned long *p);
-extern int test_and_set_bit(int nr, volatile unsigned long *p);
-extern int test_and_clear_bit(int nr, volatile unsigned long *p);
-extern int test_and_change_bit(int nr, volatile unsigned long *p);
-
 #include <asm-generic/bitops/builtin-__ffs.h>
 #include <asm-generic/bitops/builtin-ffs.h>
 #include <asm-generic/bitops/builtin-__fls.h>
@@ -44,8 +33,9 @@ extern int test_and_change_bit(int nr, volatile unsigned long *p);
 
 #include <asm-generic/bitops/sched.h>
 #include <asm-generic/bitops/hweight.h>
-#include <asm-generic/bitops/lock.h>
 
+#include <asm-generic/bitops/atomic.h>
+#include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/le.h>
 
diff --git a/arch/arm64/lib/Makefile b/arch/arm64/lib/Makefile
index 137710f4dac3..68755fd70dcf 100644
--- a/arch/arm64/lib/Makefile
+++ b/arch/arm64/lib/Makefile
@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
-lib-y		:= bitops.o clear_user.o delay.o copy_from_user.o	\
+lib-y		:= clear_user.o delay.o copy_from_user.o		\
 		   copy_to_user.o copy_in_user.o copy_page.o		\
 		   clear_page.o memchr.o memcpy.o memmove.o memset.o	\
 		   memcmp.o strcmp.o strncmp.o strlen.o strnlen.o	\
diff --git a/arch/arm64/lib/bitops.S b/arch/arm64/lib/bitops.S
deleted file mode 100644
index 43ac736baa5b..000000000000
--- a/arch/arm64/lib/bitops.S
+++ /dev/null
@@ -1,76 +0,0 @@
-/*
- * Based on arch/arm/lib/bitops.h
- *
- * Copyright (C) 2013 ARM Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <asm/assembler.h>
-#include <asm/lse.h>
-
-/*
- * x0: bits 5:0  bit offset
- *     bits 31:6 word offset
- * x1: address
- */
-	.macro	bitop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x3, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x3, [x1]"
-alt_lse	"	\llsc	x2, x2, x3",		"nop"
-alt_lse	"	stxr	w0, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w0, 1b",		"nop"
-
-	ret
-ENDPROC(\name	)
-	.endm
-
-	.macro	testop, name, llsc, lse
-ENTRY(	\name	)
-	and	w3, w0, #63		// Get bit offset
-	eor	w0, w0, w3		// Clear low bits
-	mov	x2, #1
-	add	x1, x1, x0, lsr #3	// Get word offset
-alt_lse "	prfm	pstl1strm, [x1]",	"nop"
-	lsl	x4, x2, x3		// Create mask
-
-alt_lse	"1:	ldxr	x2, [x1]",		"\lse	x4, x2, [x1]"
-	lsr	x0, x2, x3
-alt_lse	"	\llsc	x2, x2, x4",		"nop"
-alt_lse	"	stlxr	w5, x2, [x1]",		"nop"
-alt_lse	"	cbnz	w5, 1b",		"nop"
-alt_lse	"	dmb	ish",			"nop"
-
-	and	x0, x0, #1
-	ret
-ENDPROC(\name	)
-	.endm
-
-/*
- * Atomic bit operations.
- */
-	bitop	change_bit, eor, steor
-	bitop	clear_bit, bic, stclr
-	bitop	set_bit, orr, stset
-
-	testop	test_and_change_bit, eor, ldeoral
-	testop	test_and_clear_bit, bic, ldclral
-	testop	test_and_set_bit, orr, ldsetal
-- 
cgit v1.2.3


From 356c6fe7d80c678cf77aede0f95291dfd5ed2ef2 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 13:53:14 +0100
Subject: locking/atomics/arm64, arm64/bitops: Include
 <asm-generic/bitops/ext2-atomic-setbit.h>

<asm-generic/bitops/ext2-atomic-setbit.h> provides the ext2 atomic bitop
definitions, so we don't need to define our own.

Signed-off-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Cc: yamada.masahiro@socionext.com
Link: https://lore.kernel.org/lkml/1529412794-17720-10-git-send-email-will.deacon@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/include/asm/bitops.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/bitops.h b/arch/arm64/include/asm/bitops.h
index 13501460be6b..10d536b1af74 100644
--- a/arch/arm64/include/asm/bitops.h
+++ b/arch/arm64/include/asm/bitops.h
@@ -38,11 +38,6 @@
 #include <asm-generic/bitops/lock.h>
 #include <asm-generic/bitops/non-atomic.h>
 #include <asm-generic/bitops/le.h>
-
-/*
- * Ext2 is defined to use little-endian byte ordering.
- */
-#define ext2_set_bit_atomic(lock, nr, p)	test_and_set_bit_le(nr, p)
-#define ext2_clear_bit_atomic(lock, nr, p)	test_and_clear_bit_le(nr, p)
+#include <asm-generic/bitops/ext2-atomic-setbit.h>
 
 #endif /* __ASM_BITOPS_H */
-- 
cgit v1.2.3


From 4f722a6a736765310bc95dd3879f1545e5f64303 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 19 Jun 2018 14:00:37 -0500
Subject: ASoC: Intel: common: rename 'reef' to 'sof' in ACPI matching table

Align with firmware tools, no functionality change

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/soc-acpi-intel-byt-match.c  | 40 ++++++++---------
 sound/soc/intel/common/soc-acpi-intel-cht-match.c  | 52 +++++++++++-----------
 .../intel/common/soc-acpi-intel-hsw-bdw-match.c    | 16 +++----
 3 files changed, 54 insertions(+), 54 deletions(-)

diff --git a/sound/soc/intel/common/soc-acpi-intel-byt-match.c b/sound/soc/intel/common/soc-acpi-intel-byt-match.c
index bfe1ca68a542..4daa8a4f0c0c 100644
--- a/sound/soc/intel/common/soc-acpi-intel-byt-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-byt-match.c
@@ -59,8 +59,8 @@ static struct snd_soc_acpi_mach byt_thinkpad_10 = {
 	.drv_name = "cht-bsw-rt5672",
 	.fw_filename = "intel/fw_sst_0f28.bin",
 	.board = "cht-bsw",
-	.sof_fw_filename = "intel/reef-byt.ri",
-	.sof_tplg_filename = "intel/reef-byt-rt5670.tplg",
+	.sof_fw_filename = "intel/sof-byt.ri",
+	.sof_tplg_filename = "intel/sof-byt-rt5670.tplg",
 	.asoc_plat_name = "sst-mfld-platform",
 };
 
@@ -98,8 +98,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5640",
 		.machine_quirk = byt_quirk,
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -107,8 +107,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcr_rt5640",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5640",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -116,8 +116,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcr_rt5640",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5640",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -125,8 +125,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcr_rt5651",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcr_rt5651",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5651.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5651.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -134,8 +134,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-da7213.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -143,8 +143,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-da7213.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* some Baytrail platforms rely on RT5645, use CHT machine driver */
@@ -153,8 +153,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -162,8 +162,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* use CHT driver to Baytrail Chromebooks */
@@ -172,8 +172,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_baytrail_machines[] = {
 		.drv_name = "cht-bsw-max98090",
 		.fw_filename = "intel/fw_sst_0f28.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-byt.ri",
-		.sof_tplg_filename = "intel/reef-byt-max98090.tplg",
+		.sof_fw_filename = "intel/sof-byt.ri",
+		.sof_tplg_filename = "intel/sof-byt-max98090.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 #if IS_ENABLED(CONFIG_SND_SOC_INTEL_BYT_CHT_NOCODEC_MACH)
diff --git a/sound/soc/intel/common/soc-acpi-intel-cht-match.c b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
index ad1eb2d644be..3c3f2f8585d7 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cht-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
@@ -44,8 +44,8 @@ static struct snd_soc_acpi_mach cht_surface_mach = {
 	.drv_name = "cht-bsw-rt5645",
 	.fw_filename = "intel/fw_sst_22a8.bin",
 	.board = "cht-bsw",
-	.sof_fw_filename = "intel/reef-cht.ri",
-	.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+	.sof_fw_filename = "intel/sof-cht.ri",
+	.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 	.asoc_plat_name = "sst-mfld-platform",
 };
 
@@ -68,8 +68,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5672",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5670.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5670.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -77,8 +77,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5672",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5670.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5670.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -86,8 +86,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -95,8 +95,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -104,8 +104,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-rt5645",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5645.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5645.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -113,8 +113,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-max98090",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-max98090.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-max98090.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -131,8 +131,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-da7213.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -140,8 +140,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcht_da7213",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcht_da7213",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-da7213.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-da7213.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -149,8 +149,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcht_es8316",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcht_es8316",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-es8316.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-es8316.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* some CHT-T platforms rely on RT5640, use Baytrail machine driver */
@@ -160,8 +160,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcr_rt5640",
 		.machine_quirk = cht_quirk,
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
@@ -169,8 +169,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcr_rt5640",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcr_rt5640",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5640.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	/* some CHT-T platforms rely on RT5651, use Baytrail machine driver */
@@ -179,8 +179,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "bytcr_rt5651",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "bytcr_rt5651",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-rt5651.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-rt5651.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 #if IS_ENABLED(CONFIG_SND_SOC_INTEL_BYT_CHT_NOCODEC_MACH)
diff --git a/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c b/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
index 53e7acdfbb81..494a0ea9b029 100644
--- a/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-hsw-bdw-match.c
@@ -23,8 +23,8 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_haswell_machines[] = {
 		.id = "INT33CA",
 		.drv_name = "haswell-audio",
 		.fw_filename = "intel/IntcSST1.bin",
-		.sof_fw_filename = "intel/reef-hsw.ri",
-		.sof_tplg_filename = "intel/reef-hsw.tplg",
+		.sof_fw_filename = "intel/sof-hsw.ri",
+		.sof_tplg_filename = "intel/sof-hsw.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{}
@@ -36,24 +36,24 @@ struct snd_soc_acpi_mach snd_soc_acpi_intel_broadwell_machines[] = {
 		.id = "INT343A",
 		.drv_name = "broadwell-audio",
 		.fw_filename =  "intel/IntcSST2.bin",
-		.sof_fw_filename = "intel/reef-bdw.ri",
-		.sof_tplg_filename = "intel/reef-bdw-rt286.tplg",
+		.sof_fw_filename = "intel/sof-bdw.ri",
+		.sof_tplg_filename = "intel/sof-bdw-rt286.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{
 		.id = "RT5677CE",
 		.drv_name = "bdw-rt5677",
 		.fw_filename =  "intel/IntcSST2.bin",
-		.sof_fw_filename = "intel/reef-bdw.ri",
-		.sof_tplg_filename = "intel/reef-bdw-rt5677.tplg",
+		.sof_fw_filename = "intel/sof-bdw.ri",
+		.sof_tplg_filename = "intel/sof-bdw-rt5677.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{
 		.id = "INT33CA",
 		.drv_name = "haswell-audio",
 		.fw_filename = "intel/IntcSST2.bin",
-		.sof_fw_filename = "intel/reef-bdw.ri",
-		.sof_tplg_filename = "intel/reef-bdw-rt5640.tplg",
+		.sof_fw_filename = "intel/sof-bdw.ri",
+		.sof_tplg_filename = "intel/sof-bdw-rt5640.tplg",
 		.asoc_plat_name = "haswell-pcm-audio",
 	},
 	{}
-- 
cgit v1.2.3


From f567b78851d49a4887b9bb1a8b3cfad37da515c8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 18 Jun 2018 17:26:12 +0200
Subject: ALSA: hda - Move mic mute LED helper to the generic parser
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move the code for setting up and controlling the mic mute LED hook
from dell-wmi helper to the generic parser, so that it can be referred
from the multiple driver codes.

No functional change.

Tested-by: Pali Rohár <pali.rohar@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/dell_wmi_helper.c | 116 ++-------------------------------
 sound/pci/hda/hda_generic.c     | 140 ++++++++++++++++++++++++++++++++++++++++
 sound/pci/hda/hda_generic.h     |  16 +++++
 3 files changed, 162 insertions(+), 110 deletions(-)

diff --git a/sound/pci/hda/dell_wmi_helper.c b/sound/pci/hda/dell_wmi_helper.c
index 1b48a8c19d28..8a7dbd1a7fbf 100644
--- a/sound/pci/hda/dell_wmi_helper.c
+++ b/sound/pci/hda/dell_wmi_helper.c
@@ -6,111 +6,18 @@
 #if IS_ENABLED(CONFIG_DELL_LAPTOP)
 #include <linux/dell-led.h>
 
-enum {
-	MICMUTE_LED_ON,
-	MICMUTE_LED_OFF,
-	MICMUTE_LED_FOLLOW_CAPTURE,
-	MICMUTE_LED_FOLLOW_MUTE,
-};
-
-static int dell_led_mode = MICMUTE_LED_FOLLOW_MUTE;
-static int dell_capture;
-static int dell_led_value;
 static int (*dell_micmute_led_set_func)(int);
-static void (*dell_old_cap_hook)(struct hda_codec *,
-			         struct snd_kcontrol *,
-				 struct snd_ctl_elem_value *);
-
-static void call_micmute_led_update(void)
-{
-	int val;
-
-	switch (dell_led_mode) {
-	case MICMUTE_LED_ON:
-		val = 1;
-		break;
-	case MICMUTE_LED_OFF:
-		val = 0;
-		break;
-	case MICMUTE_LED_FOLLOW_CAPTURE:
-		val = dell_capture;
-		break;
-	case MICMUTE_LED_FOLLOW_MUTE:
-	default:
-		val = !dell_capture;
-		break;
-	}
-
-	if (val == dell_led_value)
-		return;
-	dell_led_value = val;
-	dell_micmute_led_set_func(dell_led_value);
-}
-
-static void update_dell_wmi_micmute_led(struct hda_codec *codec,
-				        struct snd_kcontrol *kcontrol,
-					struct snd_ctl_elem_value *ucontrol)
-{
-	if (dell_old_cap_hook)
-		dell_old_cap_hook(codec, kcontrol, ucontrol);
-
-	if (!ucontrol || !dell_micmute_led_set_func)
-		return;
-	if (strcmp("Capture Switch", ucontrol->id.name) == 0 && ucontrol->id.index == 0) {
-		/* TODO: How do I verify if it's a mono or stereo here? */
-		dell_capture = (ucontrol->value.integer.value[0] ||
-				ucontrol->value.integer.value[1]);
-		call_micmute_led_update();
-	}
-}
 
-static int dell_mic_mute_led_mode_info(struct snd_kcontrol *kcontrol,
-				       struct snd_ctl_elem_info *uinfo)
+static void dell_micmute_update(struct hda_codec *codec)
 {
-	static const char * const texts[] = {
-		"On", "Off", "Follow Capture", "Follow Mute",
-	};
-
-	return snd_ctl_enum_info(uinfo, 1, ARRAY_SIZE(texts), texts);
-}
+	struct hda_gen_spec *spec = codec->spec;
 
-static int dell_mic_mute_led_mode_get(struct snd_kcontrol *kcontrol,
-				      struct snd_ctl_elem_value *ucontrol)
-{
-	ucontrol->value.enumerated.item[0] = dell_led_mode;
-	return 0;
+	dell_micmute_led_set_func(spec->micmute_led.led_value);
 }
 
-static int dell_mic_mute_led_mode_put(struct snd_kcontrol *kcontrol,
-				      struct snd_ctl_elem_value *ucontrol)
-{
-	unsigned int mode;
-
-	mode = ucontrol->value.enumerated.item[0];
-	if (mode > MICMUTE_LED_FOLLOW_MUTE)
-		mode = MICMUTE_LED_FOLLOW_MUTE;
-	if (mode == dell_led_mode)
-		return 0;
-	dell_led_mode = mode;
-	call_micmute_led_update();
-	return 1;
-}
-
-static const struct snd_kcontrol_new dell_mic_mute_mode_ctls[] = {
-	{
-		.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
-		.name = "Mic Mute-LED Mode",
-		.info = dell_mic_mute_led_mode_info,
-		.get = dell_mic_mute_led_mode_get,
-		.put = dell_mic_mute_led_mode_put,
-	},
-	{}
-};
-
 static void alc_fixup_dell_wmi(struct hda_codec *codec,
 			       const struct hda_fixup *fix, int action)
 {
-	struct alc_spec *spec = codec->spec;
 	bool removefunc = false;
 
 	if (action == HDA_FIXUP_ACT_PROBE) {
@@ -121,25 +28,14 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec,
 			return;
 		}
 
-		removefunc = true;
-		if (dell_micmute_led_set_func(false) >= 0) {
-			dell_led_value = 0;
-			if (spec->gen.num_adc_nids > 1 && !spec->gen.dyn_adc_switch)
-				codec_dbg(codec, "Skipping micmute LED control due to several ADCs");
-			else {
-				dell_old_cap_hook = spec->gen.cap_sync_hook;
-				spec->gen.cap_sync_hook = update_dell_wmi_micmute_led;
-				removefunc = false;
-				add_mixer(spec, dell_mic_mute_mode_ctls);
-			}
-		}
-
+		removefunc = (dell_micmute_led_set_func(false) < 0) ||
+			(snd_hda_gen_add_micmute_led(codec,
+						     dell_micmute_update) <= 0);
 	}
 
 	if (dell_micmute_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
 		symbol_put(dell_micmute_led_set);
 		dell_micmute_led_set_func = NULL;
-		dell_old_cap_hook = NULL;
 	}
 }
 
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index db773e219aaa..cdce9ce6b901 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -3899,6 +3899,146 @@ static int parse_mic_boost(struct hda_codec *codec)
 	return 0;
 }
 
+/*
+ * mic mute LED hook helpers
+ */
+enum {
+	MICMUTE_LED_ON,
+	MICMUTE_LED_OFF,
+	MICMUTE_LED_FOLLOW_CAPTURE,
+	MICMUTE_LED_FOLLOW_MUTE,
+};
+
+static void call_micmute_led_update(struct hda_codec *codec)
+{
+	struct hda_gen_spec *spec = codec->spec;
+	unsigned int val;
+
+	switch (spec->micmute_led.led_mode) {
+	case MICMUTE_LED_ON:
+		val = 1;
+		break;
+	case MICMUTE_LED_OFF:
+		val = 0;
+		break;
+	case MICMUTE_LED_FOLLOW_CAPTURE:
+		val = spec->micmute_led.capture;
+		break;
+	case MICMUTE_LED_FOLLOW_MUTE:
+	default:
+		val = !spec->micmute_led.capture;
+		break;
+	}
+
+	if (val == spec->micmute_led.led_value)
+		return;
+	spec->micmute_led.led_value = val;
+	if (spec->micmute_led.update)
+		spec->micmute_led.update(codec);
+}
+
+static void update_micmute_led(struct hda_codec *codec,
+			       struct snd_kcontrol *kcontrol,
+			       struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_gen_spec *spec = codec->spec;
+
+	if (spec->micmute_led.old_hook)
+		spec->micmute_led.old_hook(codec, kcontrol, ucontrol);
+
+	if (!ucontrol)
+		return;
+	if (!strcmp("Capture Switch", ucontrol->id.name) &&
+	    !ucontrol->id.index) {
+		/* TODO: How do I verify if it's a mono or stereo here? */
+		spec->micmute_led.capture = (ucontrol->value.integer.value[0] ||
+					     ucontrol->value.integer.value[1]);
+		call_micmute_led_update(codec);
+	}
+}
+
+static int micmute_led_mode_info(struct snd_kcontrol *kcontrol,
+				 struct snd_ctl_elem_info *uinfo)
+{
+	static const char * const texts[] = {
+		"On", "Off", "Follow Capture", "Follow Mute",
+	};
+
+	return snd_ctl_enum_info(uinfo, 1, ARRAY_SIZE(texts), texts);
+}
+
+static int micmute_led_mode_get(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct hda_gen_spec *spec = codec->spec;
+
+	ucontrol->value.enumerated.item[0] = spec->micmute_led.led_mode;
+	return 0;
+}
+
+static int micmute_led_mode_put(struct snd_kcontrol *kcontrol,
+				struct snd_ctl_elem_value *ucontrol)
+{
+	struct hda_codec *codec = snd_kcontrol_chip(kcontrol);
+	struct hda_gen_spec *spec = codec->spec;
+	unsigned int mode;
+
+	mode = ucontrol->value.enumerated.item[0];
+	if (mode > MICMUTE_LED_FOLLOW_MUTE)
+		mode = MICMUTE_LED_FOLLOW_MUTE;
+	if (mode == spec->micmute_led.led_mode)
+		return 0;
+	spec->micmute_led.led_mode = mode;
+	call_micmute_led_update(codec);
+	return 1;
+}
+
+static const struct snd_kcontrol_new micmute_led_mode_ctl = {
+	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
+	.name = "Mic Mute-LED Mode",
+	.info = micmute_led_mode_info,
+	.get = micmute_led_mode_get,
+	.put = micmute_led_mode_put,
+};
+
+/**
+ * snd_hda_gen_add_micmute_led - helper for setting up mic mute LED hook
+ * @codec: the HDA codec
+ * @hook: the callback for updating LED
+ *
+ * Called from the codec drivers for offering the mic mute LED controls.
+ * Only valid for a single ADC (or a single input).  When established, it
+ * sets up cap_sync_hook and triggers the callback at each time when the
+ * capture mixer switch changes.  The callback is supposed to update the LED
+ * accordingly.
+ *
+ * Returns 1 if the hook is established, 0 if skipped (no valid config), or
+ * a negative error code.
+ */
+int snd_hda_gen_add_micmute_led(struct hda_codec *codec,
+				void (*hook)(struct hda_codec *))
+{
+	struct hda_gen_spec *spec = codec->spec;
+
+	if (spec->num_adc_nids > 1 && !spec->dyn_adc_switch) {
+		codec_dbg(codec,
+			  "Skipping micmute LED control due to several ADCs");
+		return 0;
+	}
+
+	spec->micmute_led.led_mode = MICMUTE_LED_FOLLOW_MUTE;
+	spec->micmute_led.capture = 0;
+	spec->micmute_led.led_value = 0;
+	spec->micmute_led.old_hook = spec->cap_sync_hook;
+	spec->micmute_led.update = hook;
+	spec->cap_sync_hook = update_micmute_led;
+	if (!snd_hda_gen_add_kctl(spec, NULL, &micmute_led_mode_ctl))
+		return -ENOMEM;
+	return 1;
+}
+EXPORT_SYMBOL_GPL(snd_hda_gen_add_micmute_led);
+
 /*
  * parse digital I/Os and set up NIDs in BIOS auto-parse mode
  */
diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
index 61772317de46..10123664fa61 100644
--- a/sound/pci/hda/hda_generic.h
+++ b/sound/pci/hda/hda_generic.h
@@ -86,6 +86,16 @@ struct badness_table {
 extern const struct badness_table hda_main_out_badness;
 extern const struct badness_table hda_extra_out_badness;
 
+struct hda_micmute_hook {
+	unsigned int led_mode;
+	unsigned int capture;
+	unsigned int led_value;
+	void (*update)(struct hda_codec *codec);
+	void (*old_hook)(struct hda_codec *codec,
+			 struct snd_kcontrol *kcontrol,
+			 struct snd_ctl_elem_value *ucontrol);
+};
+
 struct hda_gen_spec {
 	char stream_name_analog[32];	/* analog PCM stream */
 	const struct hda_pcm_stream *stream_analog_playback;
@@ -276,6 +286,9 @@ struct hda_gen_spec {
 			      struct snd_kcontrol *kcontrol,
 			      struct snd_ctl_elem_value *ucontrol);
 
+	/* mic mute LED hook; called via cap_sync_hook */
+	struct hda_micmute_hook micmute_led;
+
 	/* PCM hooks */
 	void (*pcm_playback_hook)(struct hda_pcm_stream *hinfo,
 				  struct hda_codec *codec,
@@ -342,4 +355,7 @@ unsigned int snd_hda_gen_path_power_filter(struct hda_codec *codec,
 void snd_hda_gen_stream_pm(struct hda_codec *codec, hda_nid_t nid, bool on);
 int snd_hda_gen_fix_pin_power(struct hda_codec *codec, hda_nid_t pin);
 
+int snd_hda_gen_add_micmute_led(struct hda_codec *codec,
+				void (*hook)(struct hda_codec *));
+
 #endif /* __SOUND_HDA_GENERIC_H */
-- 
cgit v1.2.3


From 69b2c6d7c0204e68185b694f9cfcb8f2636fed5d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 18 Jun 2018 17:28:45 +0200
Subject: ALSA: hda - Use the common helper for thinkpad_acpi mic mute LED
 handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the new common helper for setting up and controlling the mic mute
LED over thinkpad_acpi.  This also provides a new mixer enum "Mic
Mute-LED Mode" (that was present only for Dell models), which allows
user to choose the mic mute LED behavior.  For example, if you want
the mic mute LED turned on only while mic is on, choose "Follow
Capture" there.

Tested-by: Pali Rohár <pali.rohar@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/thinkpad_helper.c | 27 ++++++++-------------------
 1 file changed, 8 insertions(+), 19 deletions(-)

diff --git a/sound/pci/hda/thinkpad_helper.c b/sound/pci/hda/thinkpad_helper.c
index 65bb3ac6af4c..97f49b751e6e 100644
--- a/sound/pci/hda/thinkpad_helper.c
+++ b/sound/pci/hda/thinkpad_helper.c
@@ -27,17 +27,11 @@ static void update_tpacpi_mute_led(void *private_data, int enabled)
 		led_set_func(TPACPI_LED_MUTE, !enabled);
 }
 
-static void update_tpacpi_micmute_led(struct hda_codec *codec,
-				      struct snd_kcontrol *kcontrol,
-				      struct snd_ctl_elem_value *ucontrol)
+static void update_tpacpi_micmute(struct hda_codec *codec)
 {
-	if (!ucontrol || !led_set_func)
-		return;
-	if (strcmp("Capture Switch", ucontrol->id.name) == 0 && ucontrol->id.index == 0) {
-		/* TODO: How do I verify if it's a mono or stereo here? */
-		bool val = ucontrol->value.integer.value[0] || ucontrol->value.integer.value[1];
-		led_set_func(TPACPI_LED_MICMUTE, !val);
-	}
+	struct hda_gen_spec *spec = codec->spec;
+
+	led_set_func(TPACPI_LED_MICMUTE, spec->micmute_led.led_value);
 }
 
 static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
@@ -63,15 +57,10 @@ static void hda_fixup_thinkpad_acpi(struct hda_codec *codec,
 			spec->vmaster_mute.hook = update_tpacpi_mute_led;
 			removefunc = false;
 		}
-		if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0) {
-			if (spec->num_adc_nids > 1 && !spec->dyn_adc_switch)
-				codec_dbg(codec,
-					  "Skipping micmute LED control due to several ADCs");
-			else {
-				spec->cap_sync_hook = update_tpacpi_micmute_led;
-				removefunc = false;
-			}
-		}
+		if (led_set_func(TPACPI_LED_MICMUTE, false) >= 0 &&
+		    snd_hda_gen_add_micmute_led(codec,
+						update_tpacpi_micmute) > 0)
+			removefunc = false;
 	}
 
 	if (led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
-- 
cgit v1.2.3


From d03abecab5b4f4fa533f5971a4b205d05e9a4bc3 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 12:29:13 +0200
Subject: ALSA: hda/realtek - Use the mic-mute LED helper for HP and others

Similar as the previous commit, convert to use the common helper for
controlling the mic mute LED for HP and other machines in the Realtek
codec driver, too.  This will give the mic mute LED enum as gratis.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 49 ++++++++++++++++---------------------------
 1 file changed, 18 insertions(+), 31 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 487ceb9fd038..32a7a72033ae 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3718,16 +3718,12 @@ static void alc_fixup_gpio_mute_hook(void *private_data, int enabled)
 }
 
 /* turn on/off mic-mute LED via GPIO per capture hook */
-static void alc_fixup_gpio_mic_mute_hook(struct hda_codec *codec,
-					 struct snd_kcontrol *kcontrol,
-					 struct snd_ctl_elem_value *ucontrol)
+static void alc_gpio_micmute_update(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
 
-	if (ucontrol)
-		alc_update_gpio_led(codec, spec->gpio_mic_led_mask,
-				    ucontrol->value.integer.value[0] ||
-				    ucontrol->value.integer.value[1]);
+	alc_update_gpio_led(codec, spec->gpio_mic_led_mask,
+			    spec->gen.micmute_led.led_value);
 }
 
 static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
@@ -3742,12 +3738,12 @@ static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->gpio_mic_led_mask = 0x10;
 		snd_hda_add_verbs(codec, gpio_init);
+		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 	}
 }
 
@@ -3763,39 +3759,30 @@ static void alc286_fixup_hp_gpio_led(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x02;
 		spec->gpio_mic_led_mask = 0x20;
 		snd_hda_add_verbs(codec, gpio_init);
+		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 	}
 }
 
 /* turn on/off mic-mute LED per capture hook */
-static void alc269_fixup_hp_cap_mic_mute_hook(struct hda_codec *codec,
-					       struct snd_kcontrol *kcontrol,
-					       struct snd_ctl_elem_value *ucontrol)
+static void alc_cap_micmute_update(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
-	unsigned int pinval, enable, disable;
+	unsigned int pinval;
 
+	if (!spec->cap_mute_led_nid)
+		return;
 	pinval = snd_hda_codec_get_pin_target(codec, spec->cap_mute_led_nid);
 	pinval &= ~AC_PINCTL_VREFEN;
-	enable  = pinval | AC_PINCTL_VREF_80;
-	disable = pinval | AC_PINCTL_VREF_HIZ;
-
-	if (!ucontrol)
-		return;
-
-	if (ucontrol->value.integer.value[0] ||
-	    ucontrol->value.integer.value[1])
-		pinval = disable;
+	if (spec->gen.micmute_led.led_value)
+		pinval |= AC_PINCTL_VREF_80;
 	else
-		pinval = enable;
-
-	if (spec->cap_mute_led_nid)
-		snd_hda_set_pin_ctl_cache(codec, spec->cap_mute_led_nid, pinval);
+		pinval |= AC_PINCTL_VREF_HIZ;
+	snd_hda_set_pin_ctl_cache(codec, spec->cap_mute_led_nid, pinval);
 }
 
 static void alc269_fixup_hp_gpio_mic1_led(struct hda_codec *codec,
@@ -3810,12 +3797,12 @@ static void alc269_fixup_hp_gpio_mic1_led(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc269_fixup_hp_cap_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->cap_mute_led_nid = 0x18;
 		snd_hda_add_verbs(codec, gpio_init);
+		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 		codec->power_filter = led_power_filter;
 	}
 }
@@ -3833,12 +3820,12 @@ static void alc280_fixup_hp_gpio4(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc269_fixup_hp_cap_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->cap_mute_led_nid = 0x18;
 		snd_hda_add_verbs(codec, gpio_init);
+		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 		codec->power_filter = led_power_filter;
 	}
 }
@@ -3915,11 +3902,11 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 						    gpio2_mic_hotkey_event);
 
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->gpio_mic_led_mask = 0x10;
+		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 		return;
 	}
 
@@ -3957,10 +3944,10 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 		snd_hda_jack_detect_enable_callback(codec, 0x1b,
 						    gpio2_mic_hotkey_event);
 
-		spec->gen.cap_sync_hook = alc_fixup_gpio_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mic_led_mask = 0x04;
+		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 		return;
 	}
 
@@ -3988,10 +3975,10 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
-		spec->gen.cap_sync_hook = alc269_fixup_hp_cap_mic_mute_hook;
 		spec->mute_led_polarity = 0;
 		spec->mute_led_nid = 0x1a;
 		spec->cap_mute_led_nid = 0x18;
+		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 		spec->gen.vmaster_mute_enum = 1;
 		codec->power_filter = led_power_filter;
 	}
-- 
cgit v1.2.3


From 184e302b46c94bfb1d53fe3d4c925a45a6990430 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 12:36:36 +0200
Subject: ALSA: hda/conexant - Use the mic-mute LED helper

Convert to use the common helper for controlling the mic mute LED for
HP laptops, just as we've done for Realtek codecs.  This will give the
mic mute LED enum as gratis.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_conexant.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index e7fcfc3b8885..a9fd0572d526 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -695,16 +695,12 @@ static void cxt_fixup_gpio_mute_hook(void *private_data, int enabled)
 }
 
 /* turn on/off mic-mute LED via GPIO per capture hook */
-static void cxt_fixup_gpio_mic_mute_hook(struct hda_codec *codec,
-					 struct snd_kcontrol *kcontrol,
-					 struct snd_ctl_elem_value *ucontrol)
+static void cxt_gpio_micmute_update(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
 
-	if (ucontrol)
-		cxt_update_gpio_led(codec, spec->gpio_mic_led_mask,
-				    ucontrol->value.integer.value[0] ||
-				    ucontrol->value.integer.value[1]);
+	cxt_update_gpio_led(codec, spec->gpio_mic_led_mask,
+			    spec->gen.micmute_led.led_value);
 }
 
 
@@ -721,11 +717,11 @@ static void cxt_fixup_mute_led_gpio(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = cxt_fixup_gpio_mute_hook;
-		spec->gen.cap_sync_hook = cxt_fixup_gpio_mic_mute_hook;
 		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x01;
 		spec->gpio_mic_led_mask = 0x02;
+		snd_hda_gen_add_micmute_led(codec, cxt_gpio_micmute_update);
 	}
 	snd_hda_add_verbs(codec, gpio_init);
 	if (spec->gpio_led)
-- 
cgit v1.2.3


From c647f806b8c227de05f7f91b0ba8450b58cb3dfe Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 12:42:03 +0200
Subject: ALSA: hda - Allow multiple ADCs for mic mute LED controls

Instead of refusing, allow the configuration with the multiple ADCs
(thus multiple capture switches) for enabling the mic mute LED.
This has been done for Sigmatel/IDT codecs, and we treat the OR-ed
values from all capture switches as the boolean condition.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_generic.c | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index cdce9ce6b901..942f96e184b6 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -3922,7 +3922,7 @@ static void call_micmute_led_update(struct hda_codec *codec)
 		val = 0;
 		break;
 	case MICMUTE_LED_FOLLOW_CAPTURE:
-		val = spec->micmute_led.capture;
+		val = !!spec->micmute_led.capture;
 		break;
 	case MICMUTE_LED_FOLLOW_MUTE:
 	default:
@@ -3942,17 +3942,21 @@ static void update_micmute_led(struct hda_codec *codec,
 			       struct snd_ctl_elem_value *ucontrol)
 {
 	struct hda_gen_spec *spec = codec->spec;
+	unsigned int mask;
 
 	if (spec->micmute_led.old_hook)
 		spec->micmute_led.old_hook(codec, kcontrol, ucontrol);
 
 	if (!ucontrol)
 		return;
-	if (!strcmp("Capture Switch", ucontrol->id.name) &&
-	    !ucontrol->id.index) {
+	mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id);
+	if (!strcmp("Capture Switch", ucontrol->id.name)) {
 		/* TODO: How do I verify if it's a mono or stereo here? */
-		spec->micmute_led.capture = (ucontrol->value.integer.value[0] ||
-					     ucontrol->value.integer.value[1]);
+		if (ucontrol->value.integer.value[0] ||
+		    ucontrol->value.integer.value[1])
+			spec->micmute_led.capture |= mask;
+		else
+			spec->micmute_led.capture &= ~mask;
 		call_micmute_led_update(codec);
 	}
 }
@@ -4008,25 +4012,17 @@ static const struct snd_kcontrol_new micmute_led_mode_ctl = {
  * @hook: the callback for updating LED
  *
  * Called from the codec drivers for offering the mic mute LED controls.
- * Only valid for a single ADC (or a single input).  When established, it
- * sets up cap_sync_hook and triggers the callback at each time when the
- * capture mixer switch changes.  The callback is supposed to update the LED
- * accordingly.
+ * When established, it sets up cap_sync_hook and triggers the callback at
+ * each time when the capture mixer switch changes.  The callback is supposed
+ * to update the LED accordingly.
  *
- * Returns 1 if the hook is established, 0 if skipped (no valid config), or
- * a negative error code.
+ * Returns 0 if the hook is established or a negative error code.
  */
 int snd_hda_gen_add_micmute_led(struct hda_codec *codec,
 				void (*hook)(struct hda_codec *))
 {
 	struct hda_gen_spec *spec = codec->spec;
 
-	if (spec->num_adc_nids > 1 && !spec->dyn_adc_switch) {
-		codec_dbg(codec,
-			  "Skipping micmute LED control due to several ADCs");
-		return 0;
-	}
-
 	spec->micmute_led.led_mode = MICMUTE_LED_FOLLOW_MUTE;
 	spec->micmute_led.capture = 0;
 	spec->micmute_led.led_value = 0;
@@ -4035,7 +4031,7 @@ int snd_hda_gen_add_micmute_led(struct hda_codec *codec,
 	spec->cap_sync_hook = update_micmute_led;
 	if (!snd_hda_gen_add_kctl(spec, NULL, &micmute_led_mode_ctl))
 		return -ENOMEM;
-	return 1;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_hda_gen_add_micmute_led);
 
-- 
cgit v1.2.3


From 3bf29db731ce22480de748464031b4447b248c0f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 12:44:35 +0200
Subject: ALSA: hda/sigmatel - Use common helper for mic mute LED

To simplify the code and to get the mic-mute LED behavior control, use
the new helper function for controlling the mic mute LED instead of
open-codes.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_sigmatel.c | 31 ++++++-------------------------
 1 file changed, 6 insertions(+), 25 deletions(-)

diff --git a/sound/pci/hda/patch_sigmatel.c b/sound/pci/hda/patch_sigmatel.c
index 63d15b545b33..046705b4691a 100644
--- a/sound/pci/hda/patch_sigmatel.c
+++ b/sound/pci/hda/patch_sigmatel.c
@@ -332,33 +332,15 @@ static void stac_gpio_set(struct hda_codec *codec, unsigned int mask,
 }
 
 /* hook for controlling mic-mute LED GPIO */
-static void stac_capture_led_hook(struct hda_codec *codec,
-				  struct snd_kcontrol *kcontrol,
-				  struct snd_ctl_elem_value *ucontrol)
+static void stac_capture_led_update(struct hda_codec *codec)
 {
 	struct sigmatel_spec *spec = codec->spec;
-	unsigned int mask;
-	bool cur_mute, prev_mute;
 
-	if (!kcontrol || !ucontrol)
-		return;
-
-	mask = 1U << snd_ctl_get_ioffidx(kcontrol, &ucontrol->id);
-	prev_mute = !spec->mic_enabled;
-	if (ucontrol->value.integer.value[0] ||
-	    ucontrol->value.integer.value[1])
-		spec->mic_enabled |= mask;
+	if (spec->gen.micmute_led.led_value)
+		spec->gpio_data |= spec->mic_mute_led_gpio;
 	else
-		spec->mic_enabled &= ~mask;
-	cur_mute = !spec->mic_enabled;
-	if (cur_mute != prev_mute) {
-		if (cur_mute)
-			spec->gpio_data |= spec->mic_mute_led_gpio;
-		else
-			spec->gpio_data &= ~spec->mic_mute_led_gpio;
-		stac_gpio_set(codec, spec->gpio_mask,
-			      spec->gpio_dir, spec->gpio_data);
-	}
+		spec->gpio_data &= ~spec->mic_mute_led_gpio;
+	stac_gpio_set(codec, spec->gpio_mask, spec->gpio_dir, spec->gpio_data);
 }
 
 static int stac_vrefout_set(struct hda_codec *codec,
@@ -4656,8 +4638,7 @@ static void stac_setup_gpio(struct hda_codec *codec)
 		spec->gpio_dir |= spec->mic_mute_led_gpio;
 		spec->mic_enabled = 0;
 		spec->gpio_data |= spec->mic_mute_led_gpio;
-
-		spec->gen.cap_sync_hook = stac_capture_led_hook;
+		snd_hda_gen_add_micmute_led(codec, stac_capture_led_update);
 	}
 }
 
-- 
cgit v1.2.3


From 0bed2aa3ac5cbbd0b89bf5e94f165e2ef18180ad Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 12:45:53 +0200
Subject: ALSA: hda - Sanity check of unexpected cap_sync_hook override

There are a couple of places setting cap_sync_hook in the codec
drivers, and they just overwrite the value.  Add a sanity check via
WARN_ON() in case if an old non-NULL value is overridden and
forgotten.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_conexant.c | 1 +
 sound/pci/hda/patch_realtek.c  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index a9fd0572d526..b7339cb5c45b 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -343,6 +343,7 @@ static void cxt_fixup_headphone_mic(struct hda_codec *codec,
 		snd_hdac_regmap_add_vendor_verb(&codec->core, 0x410);
 		break;
 	case HDA_FIXUP_ACT_PROBE:
+		WARN_ON(spec->gen.cap_sync_hook);
 		spec->gen.cap_sync_hook = cxt_update_headset_mode_hook;
 		spec->gen.automute_hook = cxt_update_headset_mode;
 		break;
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 32a7a72033ae..d9461eebcfdf 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4828,6 +4828,7 @@ static void alc_probe_headset_mode(struct hda_codec *codec)
 			spec->headphone_mic_pin = cfg->inputs[i].pin;
 	}
 
+	WARN_ON(spec->gen.cap_sync_hook);
 	spec->gen.cap_sync_hook = alc_update_headset_mode_hook;
 	spec->gen.automute_hook = alc_update_headset_mode;
 	spec->gen.hp_automute_hook = alc_update_headset_jack_cb;
-- 
cgit v1.2.3


From ba2591a5993eabcc8e874e30f361d8ffbb10d6d4 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 29 May 2018 16:43:46 +0200
Subject: sched/smt: Update sched_smt_present at runtime

The static key sched_smt_present is only updated at boot time when SMT
siblings have been detected. Booting with maxcpus=1 and bringing the
siblings online after boot rebuilds the scheduling domains correctly but
does not update the static key, so the SMT code is not enabled.

Let the key be updated in the scheduler CPU hotplug code to fix this.

Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 30 ++++++++++++------------------
 kernel/sched/fair.c |  1 +
 2 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78d8facba456..0f79bb5ffb5a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5777,6 +5777,18 @@ int sched_cpu_activate(unsigned int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	struct rq_flags rf;
 
+#ifdef CONFIG_SCHED_SMT
+	/*
+	 * The sched_smt_present static key needs to be evaluated on every
+	 * hotplug event because at boot time SMT might be disabled when
+	 * the number of booted CPUs is limited.
+	 *
+	 * If then later a sibling gets hotplugged, then the key would stay
+	 * off and SMT scheduling would never be functional.
+	 */
+	if (cpumask_weight(cpu_smt_mask(cpu)) > 1)
+		static_branch_enable_cpuslocked(&sched_smt_present);
+#endif
 	set_cpu_active(cpu, true);
 
 	if (sched_smp_initialized) {
@@ -5874,22 +5886,6 @@ int sched_cpu_dying(unsigned int cpu)
 }
 #endif
 
-#ifdef CONFIG_SCHED_SMT
-DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-
-static void sched_init_smt(void)
-{
-	/*
-	 * We've enumerated all CPUs and will assume that if any CPU
-	 * has SMT siblings, CPU0 will too.
-	 */
-	if (cpumask_weight(cpu_smt_mask(0)) > 1)
-		static_branch_enable(&sched_smt_present);
-}
-#else
-static inline void sched_init_smt(void) { }
-#endif
-
 void __init sched_init_smp(void)
 {
 	sched_init_numa();
@@ -5911,8 +5907,6 @@ void __init sched_init_smp(void)
 	init_sched_rt_class();
 	init_sched_dl_class();
 
-	sched_init_smt();
-
 	sched_smp_initialized = true;
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1866e64792a7..cacdbef99b95 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6238,6 +6238,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
 }
 
 #ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 
 static inline void set_idle_cores(int cpu, int val)
 {
-- 
cgit v1.2.3


From 6a4d2657e048f096c7ffcad254010bd94891c8c0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 29 May 2018 17:50:22 +0200
Subject: x86/smp: Provide topology_is_primary_thread()

If the CPU is supporting SMT then the primary thread can be found by
checking the lower APIC ID bits for zero. smp_num_siblings is used to build
the mask for the APIC ID bits which need to be taken into account.

This uses the MPTABLE or ACPI/MADT supplied APIC ID, which can be different
than the initial APIC ID in CPUID. But according to AMD the lower bits have
to be consistent. Intel gave a tentative confirmation as well.

Preparatory patch to support disabling SMT at boot/runtime.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/apic.h     |  6 ++++++
 arch/x86/include/asm/topology.h |  4 +++-
 arch/x86/kernel/apic/apic.c     | 15 +++++++++++++++
 arch/x86/kernel/smpboot.c       |  9 +++++++++
 4 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 74a9e06b6cfd..9362a3aae927 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -502,6 +502,12 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #endif /* CONFIG_X86_LOCAL_APIC */
 
+#ifdef CONFIG_SMP
+bool apic_id_is_primary_thread(unsigned int id);
+#else
+static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
+#endif
+
 extern void irq_enter(void);
 extern void irq_exit(void);
 
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index c1d2a9892352..661e361a12a6 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -123,13 +123,15 @@ static inline int topology_max_smt_threads(void)
 }
 
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
-extern int topology_phys_to_logical_pkg(unsigned int pkg);
+int topology_phys_to_logical_pkg(unsigned int pkg);
+bool topology_is_primary_thread(unsigned int cpu);
 #else
 #define topology_max_packages()			(1)
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
+static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2aabd4cb0e3f..8703caa9d6db 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2189,6 +2189,21 @@ static int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
+/**
+ * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
+ * @id:	APIC ID to check
+ */
+bool apic_id_is_primary_thread(unsigned int apicid)
+{
+	u32 mask;
+
+	if (smp_num_siblings == 1)
+		return true;
+	/* Isolate the SMT bit(s) in the APICID and check for 0 */
+	mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
+	return !(apicid & mask);
+}
+
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
  * and cpuid_to_apicid[] synchronized.
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index c2f7d1d2a5c3..f9c731240142 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -265,6 +265,15 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
+/**
+ * topology_is_primary_thread - Check whether CPU is the primary SMT thread
+ * @cpu:	CPU to check
+ */
+bool topology_is_primary_thread(unsigned int cpu)
+{
+	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
+}
+
 /**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
-- 
cgit v1.2.3


From f048c399e0f7490ab7296bc2c255d37eb14a9675 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 21 Jun 2018 10:37:20 +0200
Subject: x86/topology: Provide topology_smt_supported()

Provide information whether SMT is supoorted by the CPUs. Preparatory patch
for SMT control mechanism.

Suggested-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/topology.h | 2 ++
 arch/x86/kernel/smpboot.c       | 8 ++++++++
 2 files changed, 10 insertions(+)

diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 661e361a12a6..453cf38a1c33 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -125,6 +125,7 @@ static inline int topology_max_smt_threads(void)
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
 int topology_phys_to_logical_pkg(unsigned int pkg);
 bool topology_is_primary_thread(unsigned int cpu);
+bool topology_smt_supported(void);
 #else
 #define topology_max_packages()			(1)
 static inline int
@@ -132,6 +133,7 @@ topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
 static inline int topology_max_smt_threads(void) { return 1; }
 static inline bool topology_is_primary_thread(unsigned int cpu) { return true; }
+static inline bool topology_smt_supported(void) { return false; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f9c731240142..7f7def989fb0 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -274,6 +274,14 @@ bool topology_is_primary_thread(unsigned int cpu)
 	return apic_id_is_primary_thread(per_cpu(x86_cpu_to_apicid, cpu));
 }
 
+/**
+ * topology_smt_supported - Check whether SMT is supported by the CPUs
+ */
+bool topology_smt_supported(void)
+{
+	return smp_num_siblings > 1;
+}
+
 /**
  * topology_phys_to_logical_pkg - Map a physical package id to a logical
  *
-- 
cgit v1.2.3


From c4de65696d865c225fda3b9913b31284ea65ea96 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 29 May 2018 19:05:25 +0200
Subject: cpu/hotplug: Make bringup/teardown of smp threads symmetric

The asymmetry caused a warning to trigger if the bootup was stopped in state
CPUHP_AP_ONLINE_IDLE. The warning no longer triggers as kthread_park() can
now be invoked on already or still parked threads. But there is still no
reason to have this be asymmetric.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/cpu.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..61396b3e9058 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -754,7 +754,6 @@ static int takedown_cpu(unsigned int cpu)
 
 	/* Park the smpboot threads */
 	kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread);
-	smpboot_park_threads(cpu);
 
 	/*
 	 * Prevent irq alloc/free while the dying cpu reorganizes the
@@ -1332,7 +1331,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	[CPUHP_AP_SMPBOOT_THREADS] = {
 		.name			= "smpboot/threads:online",
 		.startup.single		= smpboot_unpark_threads,
-		.teardown.single	= NULL,
+		.teardown.single	= smpboot_park_threads,
 	},
 	[CPUHP_AP_IRQ_AFFINITY_ONLINE] = {
 		.name			= "irq/affinity:online",
-- 
cgit v1.2.3


From cc1fe215e1efa406b03aa4389e6269b61342dec5 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 29 May 2018 17:49:05 +0200
Subject: cpu/hotplug: Split do_cpu_down()

Split out the inner workings of do_cpu_down() to allow reuse of that
function for the upcoming SMT disabling mechanism.

No functional change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/cpu.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 61396b3e9058..e266cb529c1a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -906,20 +906,19 @@ out:
 	return ret;
 }
 
+static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target)
+{
+	if (cpu_hotplug_disabled)
+		return -EBUSY;
+	return _cpu_down(cpu, 0, target);
+}
+
 static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
 {
 	int err;
 
 	cpu_maps_update_begin();
-
-	if (cpu_hotplug_disabled) {
-		err = -EBUSY;
-		goto out;
-	}
-
-	err = _cpu_down(cpu, 0, target);
-
-out:
+	err = cpu_down_maps_locked(cpu, target);
 	cpu_maps_update_done();
 	return err;
 }
-- 
cgit v1.2.3


From 05736e4ac13c08a4a9b1ef2de26dd31a32cbee57 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 29 May 2018 17:48:27 +0200
Subject: cpu/hotplug: Provide knobs to control SMT

Provide a command line and a sysfs knob to control SMT.

The command line options are:

 'nosmt':	Enumerate secondary threads, but do not online them

 'nosmt=force': Ignore secondary threads completely during enumeration
 		via MP table and ACPI/MADT.

The sysfs control file has the following states (read/write):

 'on':		 SMT is enabled. Secondary threads can be freely onlined
 'off':		 SMT is disabled. Secondary threads, even if enumerated
 		 cannot be onlined
 'forceoff':	 SMT is permanentely disabled. Writes to the control
 		 file are rejected.
 'notsupported': SMT is not supported by the CPU

The command line option 'nosmt' sets the sysfs control to 'off'. This
can be changed to 'on' to reenable SMT during runtime.

The command line option 'nosmt=force' sets the sysfs control to
'forceoff'. This cannot be changed during runtime.

When SMT is 'on' and the control file is changed to 'off' then all online
secondary threads are offlined and attempts to online a secondary thread
later on are rejected.

When SMT is 'off' and the control file is changed to 'on' then secondary
threads can be onlined again. The 'off' -> 'on' transition does not
automatically online the secondary threads.

When the control file is set to 'forceoff', the behaviour is the same as
setting it to 'off', but the operation is irreversible and later writes to
the control file are rejected.

When the control status is 'notsupported' then writes to the control file
are rejected.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/ABI/testing/sysfs-devices-system-cpu |  20 +++
 Documentation/admin-guide/kernel-parameters.txt    |   8 +
 arch/Kconfig                                       |   3 +
 arch/x86/Kconfig                                   |   1 +
 include/linux/cpu.h                                |  13 ++
 kernel/cpu.c                                       | 170 +++++++++++++++++++++
 6 files changed, 215 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 9c5e7732d249..65d9b844ecfd 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -487,3 +487,23 @@ Description:	Information about CPU vulnerabilities
 		"Not affected"	  CPU is not affected by the vulnerability
 		"Vulnerable"	  CPU is affected and no mitigation in effect
 		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
+
+What:		/sys/devices/system/cpu/smt
+		/sys/devices/system/cpu/smt/active
+		/sys/devices/system/cpu/smt/control
+Date:		June 2018
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:	Control Symetric Multi Threading (SMT)
+
+		active:  Tells whether SMT is active (enabled and siblings online)
+
+		control: Read/write interface to control SMT. Possible
+			 values:
+
+			 "on"		SMT is enabled
+			 "off"		SMT is disabled
+			 "forceoff"	SMT is force disabled. Cannot be changed.
+			 "notsupported" SMT is not supported by the CPU
+
+			 If control status is "forceoff" or "notsupported" writes
+			 are rejected.
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..8e29c4b6756f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2687,6 +2687,14 @@
 	nosmt		[KNL,S390] Disable symmetric multithreading (SMT).
 			Equivalent to smt=1.
 
+			[KNL,x86] Disable symmetric multithreading (SMT).
+			nosmt=force: Force disable SMT, similar to disabling
+				     it in the BIOS except that some of the
+				     resource partitioning effects which are
+				     caused by having SMT enabled in the BIOS
+				     cannot be undone. Depending on the CPU
+				     type this might have a performance impact.
+
 	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
 			(indirect branch prediction) vulnerability. System may
 			allow data leaks with this option, which is equivalent
diff --git a/arch/Kconfig b/arch/Kconfig
index 1aa59063f1fd..d1f2ed462ac8 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -13,6 +13,9 @@ config KEXEC_CORE
 config HAVE_IMA_KEXEC
 	bool
 
+config HOTPLUG_SMT
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f1dbb4ee19d7..7a34fdf8daf0 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -187,6 +187,7 @@ config X86
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK
 	select HAVE_USER_RETURN_NOTIFIER
+	select HOTPLUG_SMT			if SMP
 	select IRQ_FORCED_THREADING
 	select NEED_SG_DMA_LENGTH
 	select PCI_LOCKLESS_CONFIG
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index d3da5184aa1c..7532cbf27b1d 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -168,4 +168,17 @@ void cpuhp_report_idle_dead(void);
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
+enum cpuhp_smt_control {
+	CPU_SMT_ENABLED,
+	CPU_SMT_DISABLED,
+	CPU_SMT_FORCE_DISABLED,
+	CPU_SMT_NOT_SUPPORTED,
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
+extern enum cpuhp_smt_control cpu_smt_control;
+#else
+# define cpu_smt_control		(CPU_SMT_ENABLED)
+#endif
+
 #endif /* _LINUX_CPU_H_ */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index e266cb529c1a..d29fdd7e57bb 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -933,6 +933,29 @@ EXPORT_SYMBOL(cpu_down);
 #define takedown_cpu		NULL
 #endif /*CONFIG_HOTPLUG_CPU*/
 
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_control = CPU_SMT_DISABLED;
+	if (str && !strcmp(str, "force")) {
+		pr_info("SMT: Force disabled\n");
+		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	}
+	return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+	return cpu_smt_control == CPU_SMT_ENABLED ||
+		topology_is_primary_thread(cpu);
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
 /**
  * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
  * @cpu: cpu that just started
@@ -1056,6 +1079,10 @@ static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
 		err = -EBUSY;
 		goto out;
 	}
+	if (!cpu_smt_allowed(cpu)) {
+		err = -EPERM;
+		goto out;
+	}
 
 	err = _cpu_up(cpu, 0, target);
 out:
@@ -1904,10 +1931,153 @@ static const struct attribute_group cpuhp_cpu_root_attr_group = {
 	NULL
 };
 
+#ifdef CONFIG_HOTPLUG_SMT
+
+static const char *smt_states[] = {
+	[CPU_SMT_ENABLED]		= "on",
+	[CPU_SMT_DISABLED]		= "off",
+	[CPU_SMT_FORCE_DISABLED]	= "forceoff",
+	[CPU_SMT_NOT_SUPPORTED]		= "notsupported",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
+}
+
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = true;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+	int cpu, ret = 0;
+
+	cpu_maps_update_begin();
+	for_each_online_cpu(cpu) {
+		if (topology_is_primary_thread(cpu))
+			continue;
+		ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+		if (ret)
+			break;
+		/*
+		 * As this needs to hold the cpu maps lock it's impossible
+		 * to call device_offline() because that ends up calling
+		 * cpu_down() which takes cpu maps lock. cpu maps lock
+		 * needs to be held as this might race against in kernel
+		 * abusers of the hotplug machinery (thermal management).
+		 *
+		 * So nothing would update device:offline state. That would
+		 * leave the sysfs entry stale and prevent onlining after
+		 * smt control has been changed to 'off' again. This is
+		 * called under the sysfs hotplug lock, so it is properly
+		 * serialized against the regular offline usage.
+		 */
+		cpuhp_offline_cpu_device(cpu);
+	}
+	if (!ret)
+		cpu_smt_control = ctrlval;
+	cpu_maps_update_done();
+	return ret;
+}
+
+static void cpuhp_smt_enable(void)
+{
+	cpu_maps_update_begin();
+	cpu_smt_control = CPU_SMT_ENABLED;
+	cpu_maps_update_done();
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+		  const char *buf, size_t count)
+{
+	int ctrlval, ret;
+
+	if (sysfs_streq(buf, "on"))
+		ctrlval = CPU_SMT_ENABLED;
+	else if (sysfs_streq(buf, "off"))
+		ctrlval = CPU_SMT_DISABLED;
+	else if (sysfs_streq(buf, "forceoff"))
+		ctrlval = CPU_SMT_FORCE_DISABLED;
+	else
+		return -EINVAL;
+
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED)
+		return -EPERM;
+
+	if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return -ENODEV;
+
+	ret = lock_device_hotplug_sysfs();
+	if (ret)
+		return ret;
+
+	if (ctrlval != cpu_smt_control) {
+		switch (ctrlval) {
+		case CPU_SMT_ENABLED:
+			cpuhp_smt_enable();
+			break;
+		case CPU_SMT_DISABLED:
+		case CPU_SMT_FORCE_DISABLED:
+			ret = cpuhp_smt_disable(ctrlval);
+			break;
+		}
+	}
+
+	unlock_device_hotplug();
+	return ret ? ret : count;
+}
+static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
+
+static ssize_t
+show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	bool active = topology_max_smt_threads() > 1;
+
+	return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+}
+static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
+
+static struct attribute *cpuhp_smt_attrs[] = {
+	&dev_attr_control.attr,
+	&dev_attr_active.attr,
+	NULL
+};
+
+static const struct attribute_group cpuhp_smt_attr_group = {
+	.attrs = cpuhp_smt_attrs,
+	.name = "smt",
+	NULL
+};
+
+static int __init cpu_smt_state_init(void)
+{
+	if (!topology_smt_supported())
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+
+	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
+				  &cpuhp_smt_attr_group);
+}
+
+#else
+static inline int cpu_smt_state_init(void) { return 0; }
+#endif
+
 static int __init cpuhp_sysfs_init(void)
 {
 	int cpu, ret;
 
+	ret = cpu_smt_state_init();
+	if (ret)
+		return ret;
+
 	ret = sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				 &cpuhp_cpu_root_attr_group);
 	if (ret)
-- 
cgit v1.2.3


From 55e6d279abd92cfd7576bba031e7589be8475edb Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Jun 2018 00:36:15 +0200
Subject: x86/cpu: Remove the pointless CPU printout

The value of this printout is dubious at best and there is no point in
having it in two different places along with convoluted ways to reach it.

Remove it completely.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/common.c   | 20 +++++---------------
 arch/x86/kernel/cpu/topology.c | 10 ----------
 2 files changed, 5 insertions(+), 25 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 9baf684e2b55..81fbb267489e 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -663,13 +663,12 @@ void detect_ht(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
 	int index_msb, core_bits;
-	static bool printed;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
 		return;
 
 	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		goto out;
+		return;
 
 	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
 		return;
@@ -678,14 +677,14 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
 
+	if (!smp_num_siblings)
+		smp_num_siblings = 1;
+
 	if (smp_num_siblings == 1) {
 		pr_info_once("CPU0: Hyper-Threading is disabled\n");
-		goto out;
+		return;
 	}
 
-	if (smp_num_siblings <= 1)
-		goto out;
-
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
 
@@ -697,15 +696,6 @@ void detect_ht(struct cpuinfo_x86 *c)
 
 	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, index_msb) &
 				       ((1 << core_bits) - 1);
-
-out:
-	if (!printed && (c->x86_max_cores * smp_num_siblings) > 1) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-			c->phys_proc_id);
-		pr_info("CPU: Processor Core ID: %d\n",
-			c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 }
 
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 81c0afb39d0a..1072b5eda607 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -33,7 +33,6 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	unsigned int eax, ebx, ecx, edx, sub_index;
 	unsigned int ht_mask_width, core_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
-	static bool printed;
 
 	if (c->cpuid_level < 0xb)
 		return -1;
@@ -86,15 +85,6 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
-
-	if (!printed) {
-		pr_info("CPU: Physical Processor ID: %d\n",
-		       c->phys_proc_id);
-		if (c->x86_max_cores > 1)
-			pr_info("CPU: Processor Core ID: %d\n",
-			       c->cpu_core_id);
-		printed = 1;
-	}
 #endif
 	return 0;
 }
-- 
cgit v1.2.3


From 44ca36de56d1bf196dca2eb67cd753a46961ffe6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Jun 2018 00:47:10 +0200
Subject: x86/cpu/AMD: Remove the pointless detect_ht() call

Real 32bit AMD CPUs do not have SMT and the only value of the call was to
reach the magic printout which got removed.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/amd.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 082d7875cef8..9fb1c681b63a 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -855,10 +855,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 		srat_detect_node(c);
 	}
 
-#ifdef CONFIG_X86_32
-	detect_ht(c);
-#endif
-
 	init_amd_cacheinfo(c);
 
 	if (c->x86 >= 0xf)
-- 
cgit v1.2.3


From 545401f4448a807b963ff17b575e0a393e68b523 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Jun 2018 00:53:57 +0200
Subject: x86/cpu/common: Provide detect_ht_early()

To support force disabling of SMT it's required to know the number of
thread siblings early. detect_ht() cannot be called before the APIC driver
is selected, so split out the part which initializes smp_num_siblings.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/common.c | 24 ++++++++++++++----------
 arch/x86/kernel/cpu/cpu.h    |  1 +
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 81fbb267489e..0768492f4687 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -658,32 +658,36 @@ static void cpu_detect_tlb(struct cpuinfo_x86 *c)
 		tlb_lld_4m[ENTRIES], tlb_lld_1g[ENTRIES]);
 }
 
-void detect_ht(struct cpuinfo_x86 *c)
+int detect_ht_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	u32 eax, ebx, ecx, edx;
-	int index_msb, core_bits;
 
 	if (!cpu_has(c, X86_FEATURE_HT))
-		return;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_CMP_LEGACY))
-		return;
+		return -1;
 
 	if (cpu_has(c, X86_FEATURE_XTOPOLOGY))
-		return;
+		return -1;
 
 	cpuid(1, &eax, &ebx, &ecx, &edx);
 
 	smp_num_siblings = (ebx & 0xff0000) >> 16;
+	if (smp_num_siblings == 1)
+		pr_info_once("CPU0: Hyper-Threading is disabled\n");
+#endif
+	return 0;
+}
 
-	if (!smp_num_siblings)
-		smp_num_siblings = 1;
+void detect_ht(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	int index_msb, core_bits;
 
-	if (smp_num_siblings == 1) {
-		pr_info_once("CPU0: Hyper-Threading is disabled\n");
+	if (detect_ht_early(c) < 0)
 		return;
-	}
 
 	index_msb = get_count_order(smp_num_siblings);
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, index_msb);
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 38216f678fc3..898da0b974e2 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -56,6 +56,7 @@ extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
 extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
 extern int detect_extended_topology(struct cpuinfo_x86 *c);
+extern int detect_ht_early(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);
 
 unsigned int aperfmperf_get_khz(int cpu);
-- 
cgit v1.2.3


From 95f3d39ccf7aaea79d1ffdac1c887c2e100ec1b6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Jun 2018 00:55:39 +0200
Subject: x86/cpu/topology: Provide detect_extended_topology_early()

To support force disabling of SMT it's required to know the number of
thread siblings early. detect_extended_topology() cannot be called before
the APIC driver is selected, so split out the part which initializes
smp_num_siblings.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/cpu.h      |  1 +
 arch/x86/kernel/cpu/topology.c | 31 ++++++++++++++++++++++---------
 2 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 898da0b974e2..e59c0ea82a33 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -55,6 +55,7 @@ extern void init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern void init_amd_cacheinfo(struct cpuinfo_x86 *c);
 
 extern void detect_num_cpu_cores(struct cpuinfo_x86 *c);
+extern int detect_extended_topology_early(struct cpuinfo_x86 *c);
 extern int detect_extended_topology(struct cpuinfo_x86 *c);
 extern int detect_ht_early(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 1072b5eda607..71ca064e3794 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -22,17 +22,10 @@
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-/*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
- * exists, use it for populating initial_apicid and cpu topology
- * detection.
- */
-int detect_extended_topology(struct cpuinfo_x86 *c)
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
-	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width;
-	unsigned int core_select_mask, core_level_siblings;
+	unsigned int eax, ebx, ecx, edx;
 
 	if (c->cpuid_level < 0xb)
 		return -1;
@@ -51,10 +44,30 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
 	c->initial_apicid = edx;
+	smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
+#endif
+	return 0;
+}
+
+/*
+ * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * exists, use it for populating initial_apicid and cpu topology
+ * detection.
+ */
+int detect_extended_topology(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx, sub_index;
+	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int core_select_mask, core_level_siblings;
+
+	if (detect_extended_topology_early(c) < 0)
+		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
+	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
-- 
cgit v1.2.3


From 1910ad5624968f93be48e8e265513c54d66b897c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Jun 2018 01:00:55 +0200
Subject: x86/cpu/intel: Evaluate smp_num_siblings early

Make use of the new early detection function to initialize smp_num_siblings
on the boot cpu before the MP-Table or ACPI/MADT scan happens. That's
required for force disabling SMT.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/intel.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index eb75564f2d25..6602941cfebf 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -301,6 +301,13 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	}
 
 	check_mpx_erratum(c);
+
+	/*
+	 * Get the number of SMT siblings early from the extended topology
+	 * leaf, if available. Otherwise try the legacy SMT detection.
+	 */
+	if (detect_extended_topology_early(c) < 0)
+		detect_ht_early(c);
 }
 
 #ifdef CONFIG_X86_32
-- 
cgit v1.2.3


From 119bff8a9c9bb00116a844ec68be7bc4b1c768f5 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Fri, 15 Jun 2018 20:48:39 +0200
Subject: x86/CPU/AMD: Do not check CPUID max ext level before parsing SMP info

Old code used to check whether CPUID ext max level is >= 0x80000008 because
that last leaf contains the number of cores of the physical CPU.  The three
functions called there now do not depend on that leaf anymore so the check
can go.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/amd.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 9fb1c681b63a..d120e5cefca9 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -848,12 +848,9 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	cpu_detect_cache_sizes(c);
 
-	/* Multi core CPU? */
-	if (c->extended_cpuid_level >= 0x80000008) {
-		amd_detect_cmp(c);
-		amd_get_topology(c);
-		srat_detect_node(c);
-	}
+	amd_detect_cmp(c);
+	amd_get_topology(c);
+	srat_detect_node(c);
 
 	init_amd_cacheinfo(c);
 
-- 
cgit v1.2.3


From 1e1d7e25fd759eddf96d8ab39d0a90a1979b2d8c Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 6 Jun 2018 00:57:38 +0200
Subject: x86/cpu/AMD: Evaluate smp_num_siblings early

To support force disabling of SMT it's required to know the number of
thread siblings early. amd_get_topology() cannot be called before the APIC
driver is selected, so split out the part which initializes
smp_num_siblings and invoke it from amd_early_init().

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/cpu/amd.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d120e5cefca9..b20dee982a53 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -315,6 +315,17 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
 	c->cpu_core_id %= cus_per_node;
 }
 
+
+static void amd_get_topology_early(struct cpuinfo_x86 *c)
+{
+	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+		u32 eax, ebx, ecx, edx;
+
+		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
+		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
+	}
+}
+
 /*
  * Fixup core topology information for
  * (1) AMD multi-node processors
@@ -681,6 +692,8 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 		set_cpu_bug(c, X86_BUG_AMD_E400);
 
 	early_detect_mem_encrypt(c);
+
+	amd_get_topology_early(c);
 }
 
 static void init_amd_k8(struct cpuinfo_x86 *c)
-- 
cgit v1.2.3


From 2207def700f902f169fc237b717252c326f9e464 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 5 Jun 2018 14:00:11 +0200
Subject: x86/apic: Ignore secondary threads if nosmt=force
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

nosmt on the kernel command line merely prevents the onlining of the
secondary SMT siblings.

nosmt=force makes the APIC detection code ignore the secondary SMT siblings
completely, so they even do not show up as possible CPUs. That reduces the
amount of memory allocations for per cpu variables and saves other
resources from being allocated too large.

This is not fully equivalent to disabling SMT in the BIOS because the low
level SMT enabling in the BIOS can result in partitioning of resources
between the siblings, which is not undone by just ignoring them. Some CPUs
can use the full resources when their sibling is not onlined, but this is
depending on the CPU family and model and it's not well documented whether
this applies to all partitioned resources. That means depending on the
workload disabling SMT in the BIOS might result in better performance.

Linus analysis of the Intel manual:

  The intel optimization manual is not very clear on what the partitioning
  rules are.

  I find:

    "In general, the buffers for staging instructions between major pipe
     stages  are partitioned. These buffers include µop queues after the
     execution trace cache, the queues after the register rename stage, the
     reorder buffer which stages instructions for retirement, and the load
     and store buffers.

     In the case of load and store buffers, partitioning also provided an
     easier implementation to maintain memory ordering for each logical
     processor and detect memory ordering violations"

  but some of that partitioning may be relaxed if the HT thread is "not
  active":

    "In Intel microarchitecture code name Sandy Bridge, the micro-op queue
     is statically partitioned to provide 28 entries for each logical
     processor,  irrespective of software executing in single thread or
     multiple threads. If one logical processor is not active in Intel
     microarchitecture code name Ivy Bridge, then a single thread executing
     on that processor  core can use the 56 entries in the micro-op queue"

  but I do not know what "not active" means, and how dynamic it is. Some of
  that partitioning may be entirely static and depend on the early BIOS
  disabling of HT, and even if we park the cores, the resources will just be
  wasted.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/apic.h |  2 ++
 arch/x86/kernel/acpi/boot.c |  3 ++-
 arch/x86/kernel/apic/apic.c | 19 +++++++++++++++++++
 3 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 9362a3aae927..ef40e4acd7c2 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -504,8 +504,10 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #ifdef CONFIG_SMP
 bool apic_id_is_primary_thread(unsigned int id);
+bool apic_id_disabled(unsigned int id);
 #else
 static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
+static inline bool apic_id_disabled(unsigned int id) { return false; }
 #endif
 
 extern void irq_enter(void);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 3b20607d581b..db4c118a7e4d 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -181,7 +181,8 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 	}
 
 	if (!enabled) {
-		++disabled_cpus;
+		if (!apic_id_disabled(id))
+			++disabled_cpus;
 		return -EINVAL;
 	}
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 8703caa9d6db..b86091add294 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2204,6 +2204,16 @@ bool apic_id_is_primary_thread(unsigned int apicid)
 	return !(apicid & mask);
 }
 
+/**
+ * apic_id_disabled - Check whether APIC ID is disabled via SMT control
+ * @id:	APIC ID to check
+ */
+bool apic_id_disabled(unsigned int id)
+{
+	return (cpu_smt_control == CPU_SMT_FORCE_DISABLED &&
+		!apic_id_is_primary_thread(id));
+}
+
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
  * and cpuid_to_apicid[] synchronized.
@@ -2299,6 +2309,15 @@ int generic_processor_info(int apicid, int version)
 		return -EINVAL;
 	}
 
+	/*
+	 * If SMT is force disabled and the APIC ID belongs to
+	 * a secondary thread, ignore it.
+	 */
+	if (apic_id_disabled(apicid)) {
+		pr_info_once("Ignoring secondary SMT threads\n");
+		return -EINVAL;
+	}
+
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
 		 * x86_bios_cpu_apicid is required to have processors listed
-- 
cgit v1.2.3


From bfc18e389c7a09fbbbed6bf4032396685b14246e Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:04 +0100
Subject: atomics/treewide: Rename __atomic_add_unless() =>
 atomic_fetch_add_unless()

While __atomic_add_unless() was originally intended as a building-block
for atomic_add_unless(), it's now used in a number of places around the
kernel. It's the only common atomic operation named __atomic*(), rather
than atomic_*(), and for consistency it would be better named
atomic_fetch_add_unless().

This lack of consistency is slightly confusing, and gets in the way of
scripting atomics. Given that, let's clean things up and promote it to
an official part of the atomics API, in the form of
atomic_fetch_add_unless().

This patch converts definitions and invocations over to the new name,
including the instrumented version, using the following script:

  ----
  git grep -w __atomic_add_unless | while read line; do
  sed -i '{s/\<__atomic_add_unless\>/atomic_fetch_add_unless/}' "${line%%:*}";
  done
  git grep -w __arch_atomic_add_unless | while read line; do
  sed -i '{s/\<__arch_atomic_add_unless\>/arch_atomic_fetch_add_unless/}' "${line%%:*}";
  done
  ----

Note that we do not have atomic{64,_long}_fetch_add_unless(), which will
be introduced by later patches.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Palmer Dabbelt <palmer@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-2-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h           | 4 ++--
 arch/arc/include/asm/atomic.h             | 4 ++--
 arch/arm/include/asm/atomic.h             | 4 ++--
 arch/arm64/include/asm/atomic.h           | 2 +-
 arch/h8300/include/asm/atomic.h           | 2 +-
 arch/hexagon/include/asm/atomic.h         | 4 ++--
 arch/ia64/include/asm/atomic.h            | 2 +-
 arch/m68k/include/asm/atomic.h            | 2 +-
 arch/mips/include/asm/atomic.h            | 4 ++--
 arch/openrisc/include/asm/atomic.h        | 4 ++--
 arch/parisc/include/asm/atomic.h          | 4 ++--
 arch/powerpc/include/asm/atomic.h         | 8 ++++----
 arch/riscv/include/asm/atomic.h           | 4 ++--
 arch/s390/include/asm/atomic.h            | 2 +-
 arch/sh/include/asm/atomic.h              | 4 ++--
 arch/sparc/include/asm/atomic_32.h        | 2 +-
 arch/sparc/include/asm/atomic_64.h        | 2 +-
 arch/sparc/lib/atomic32.c                 | 4 ++--
 arch/x86/include/asm/atomic.h             | 4 ++--
 arch/xtensa/include/asm/atomic.h          | 4 ++--
 drivers/block/rbd.c                       | 2 +-
 drivers/infiniband/core/rdma_core.c       | 2 +-
 fs/afs/rxrpc.c                            | 2 +-
 include/asm-generic/atomic-instrumented.h | 4 ++--
 include/asm-generic/atomic.h              | 4 ++--
 include/linux/atomic.h                    | 2 +-
 kernel/bpf/syscall.c                      | 4 ++--
 net/rxrpc/call_object.c                   | 2 +-
 net/rxrpc/conn_object.c                   | 4 ++--
 net/rxrpc/local_object.c                  | 2 +-
 net/rxrpc/peer_object.c                   | 2 +-
 31 files changed, 50 insertions(+), 50 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 767bfdd42992..392b15a4dd4f 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -206,7 +206,7 @@ ATOMIC_OPS(xor, xor)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -214,7 +214,7 @@ ATOMIC_OPS(xor, xor)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, new, old;
 	smp_mb();
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 11859287c52a..67121b5ff3a3 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -309,7 +309,7 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 #undef ATOMIC_OP
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -317,7 +317,7 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v
  */
-#define __atomic_add_unless(v, a, u)					\
+#define atomic_fetch_add_unless(v, a, u)					\
 ({									\
 	int c, old;							\
 									\
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 66d0e215a773..9d56d0727c9b 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -130,7 +130,7 @@ static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 }
 #define atomic_cmpxchg_relaxed		atomic_cmpxchg_relaxed
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int oldval, newval;
 	unsigned long tmp;
@@ -215,7 +215,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index c0235e0ff849..264d20339f74 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -125,7 +125,7 @@
 #define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
 #define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
 #define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
-#define __atomic_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
+#define atomic_fetch_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
 #define atomic_andnot			atomic_andnot
 
 /*
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index b174dec099bf..5c856887fdf2 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -94,7 +94,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	h8300flags flags;
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index fb3dfb2a667e..287aa9f394f3 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -164,7 +164,7 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer to value
  * @a: amount to add
  * @u: unless value is equal to u
@@ -173,7 +173,7 @@ ATOMIC_OPS(xor)
  *
  */
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int __oldval;
 	register int tmp;
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 2524fb60fbc2..9d2ddde5f9d5 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -215,7 +215,7 @@ ATOMIC64_FETCH_OP(xor, ^)
 	(cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index e993e2860ee1..8022d9ea1213 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -211,7 +211,7 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 	return c != 0;
 }
 
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 0ab176bdb8e8..02fc1553cf9b 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -275,7 +275,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -283,7 +283,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/arch/openrisc/include/asm/atomic.h b/arch/openrisc/include/asm/atomic.h
index 146e1660f00e..b589fac39b92 100644
--- a/arch/openrisc/include/asm/atomic.h
+++ b/arch/openrisc/include/asm/atomic.h
@@ -100,7 +100,7 @@ ATOMIC_OP(xor)
  *
  * This is often used through atomic_inc_not_zero()
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int old, tmp;
 
@@ -119,7 +119,7 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 	return old;
 }
-#define __atomic_add_unless	__atomic_add_unless
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
 
 #include <asm-generic/atomic.h>
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 88bae6676c9b..7748abced766 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -78,7 +78,7 @@ static __inline__ int atomic_read(const atomic_t *v)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -86,7 +86,7 @@ static __inline__ int atomic_read(const atomic_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 682b3e6a1e21..1483261080a1 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -218,7 +218,7 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 #define atomic_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -226,13 +226,13 @@ static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	lwarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	lwarx	%0,0,%1		# atomic_fetch_add_unless\n\
 	cmpw	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -538,7 +538,7 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%1		# __atomic_add_unless\n\
+"1:	ldarx	%0,0,%1		# atomic_fetch_add_unless\n\
 	cmpd	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 855115ace98c..739e810c857e 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -332,7 +332,7 @@ ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
 #undef ATOMIC_OP
 
 /* This is required to provide a full barrier on success. */
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
        int prev, rc;
 
@@ -381,7 +381,7 @@ static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
  */
 static __always_inline int atomic_inc_not_zero(atomic_t *v)
 {
-        return __atomic_add_unless(v, 1, 0);
+        return atomic_fetch_add_unless(v, 1, 0);
 }
 
 #ifndef CONFIG_GENERIC_ATOMIC64
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 4b55532f15c4..c2858cdd8c29 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -90,7 +90,7 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return __atomic_cmpxchg(&v->counter, old, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index 0fd0099f43cc..ef45931ebac5 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -46,7 +46,7 @@
 #define atomic_cmpxchg(v, o, n)		(cmpxchg(&((v)->counter), (o), (n)))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -54,7 +54,7 @@
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index d13ce517f4b9..a58f4b43bcc7 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -27,7 +27,7 @@ int atomic_fetch_or(int, atomic_t *);
 int atomic_fetch_xor(int, atomic_t *);
 int atomic_cmpxchg(atomic_t *, int, int);
 int atomic_xchg(atomic_t *, int);
-int __atomic_add_unless(atomic_t *, int, int);
+int atomic_fetch_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
 #define atomic_set_release(v, i)	atomic_set((v), (i))
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 28db058d471b..f416fd3d2708 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -89,7 +89,7 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c
index 465a901a0ada..281fa634bb1a 100644
--- a/arch/sparc/lib/atomic32.c
+++ b/arch/sparc/lib/atomic32.c
@@ -95,7 +95,7 @@ int atomic_cmpxchg(atomic_t *v, int old, int new)
 }
 EXPORT_SYMBOL(atomic_cmpxchg);
 
-int __atomic_add_unless(atomic_t *v, int a, int u)
+int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int ret;
 	unsigned long flags;
@@ -107,7 +107,7 @@ int __atomic_add_unless(atomic_t *v, int a, int u)
 	spin_unlock_irqrestore(ATOMIC_HASH(v), flags);
 	return ret;
 }
-EXPORT_SYMBOL(__atomic_add_unless);
+EXPORT_SYMBOL(atomic_fetch_add_unless);
 
 /* Atomic operations are already serializing */
 void atomic_set(atomic_t *v, int i)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 0db6bec95489..84ed0bd76aef 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -254,7 +254,7 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 }
 
 /**
- * __arch_atomic_add_unless - add unless the number is already a given value
+ * arch_atomic_fetch_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -262,7 +262,7 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
  * Atomically adds @a to @v, so long as @v was not already @u.
  * Returns the old value of @v.
  */
-static __always_inline int __arch_atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c = arch_atomic_read(v);
 
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index e7a23f2a519a..4188e56c06c9 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -275,7 +275,7 @@ ATOMIC_OPS(xor)
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 /**
- * __atomic_add_unless - add unless the number is a given value
+ * atomic_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -283,7 +283,7 @@ ATOMIC_OPS(xor)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
+static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index fa0729c1e776..d81c653b9bf6 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -61,7 +61,7 @@ static int atomic_inc_return_safe(atomic_t *v)
 {
 	unsigned int counter;
 
-	counter = (unsigned int)__atomic_add_unless(v, 1, 0);
+	counter = (unsigned int)atomic_fetch_add_unless(v, 1, 0);
 	if (counter <= (unsigned int)INT_MAX)
 		return (int)counter;
 
diff --git a/drivers/infiniband/core/rdma_core.c b/drivers/infiniband/core/rdma_core.c
index a6e904973ba8..475910ffbcb6 100644
--- a/drivers/infiniband/core/rdma_core.c
+++ b/drivers/infiniband/core/rdma_core.c
@@ -121,7 +121,7 @@ static int uverbs_try_lock_object(struct ib_uobject *uobj, bool exclusive)
 	 * this lock.
 	 */
 	if (!exclusive)
-		return __atomic_add_unless(&uobj->usecnt, 1, -1) == -1 ?
+		return atomic_fetch_add_unless(&uobj->usecnt, 1, -1) == -1 ?
 			-EBUSY : 0;
 
 	/* lock is either WRITE or DESTROY - should be exclusive */
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index a1b18082991b..183cc5418722 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -648,7 +648,7 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
 	trace_afs_notify_call(rxcall, call);
 	call->need_attention = true;
 
-	u = __atomic_add_unless(&call->usage, 1, 0);
+	u = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (u != 0) {
 		trace_afs_call(call, afs_call_trace_wake, u,
 			       atomic_read(&call->net->nr_outstanding_calls),
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index ec07f23678ea..b8b14cc2df6c 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -84,10 +84,10 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne
 }
 #endif
 
-static __always_inline int __atomic_add_unless(atomic_t *v, int a, int u)
+static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	kasan_check_write(v, sizeof(*v));
-	return __arch_atomic_add_unless(v, a, u);
+	return arch_atomic_fetch_add_unless(v, a, u);
 }
 
 
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index abe6dd9ca2a8..10051ed6d088 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -221,8 +221,8 @@ static inline void atomic_dec(atomic_t *v)
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-#ifndef __atomic_add_unless
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#ifndef atomic_fetch_add_unless
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
 	c = atomic_read(v);
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 01ce3997cb42..9cc982936675 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -530,7 +530,7 @@
  */
 static inline int atomic_add_unless(atomic_t *v, int a, int u)
 {
-	return __atomic_add_unless(v, a, u) != u;
+	return atomic_fetch_add_unless(v, a, u) != u;
 }
 
 /**
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 35dc466641f2..f12db70d3bf3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -575,7 +575,7 @@ static struct bpf_map *bpf_map_inc_not_zero(struct bpf_map *map,
 {
 	int refold;
 
-	refold = __atomic_add_unless(&map->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&map->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_map_put(map, false);
@@ -1142,7 +1142,7 @@ struct bpf_prog *bpf_prog_inc_not_zero(struct bpf_prog *prog)
 {
 	int refold;
 
-	refold = __atomic_add_unless(&prog->aux->refcnt, 1, 0);
+	refold = atomic_fetch_add_unless(&prog->aux->refcnt, 1, 0);
 
 	if (refold >= BPF_MAX_REFCNT) {
 		__bpf_prog_put(prog, false);
diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c
index f6734d8cb01a..9486293fef5c 100644
--- a/net/rxrpc/call_object.c
+++ b/net/rxrpc/call_object.c
@@ -415,7 +415,7 @@ void rxrpc_incoming_call(struct rxrpc_sock *rx,
 bool rxrpc_queue_call(struct rxrpc_call *call)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&call->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&call->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&call->processor))
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 4c77a78a252a..77440a356b14 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -266,7 +266,7 @@ void rxrpc_kill_connection(struct rxrpc_connection *conn)
 bool rxrpc_queue_conn(struct rxrpc_connection *conn)
 {
 	const void *here = __builtin_return_address(0);
-	int n = __atomic_add_unless(&conn->usage, 1, 0);
+	int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 	if (n == 0)
 		return false;
 	if (rxrpc_queue_work(&conn->processor))
@@ -309,7 +309,7 @@ rxrpc_get_connection_maybe(struct rxrpc_connection *conn)
 	const void *here = __builtin_return_address(0);
 
 	if (conn) {
-		int n = __atomic_add_unless(&conn->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&conn->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_conn(conn, rxrpc_conn_got, n + 1, here);
 		else
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index b493e6b62740..777c3ed4cfc0 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -305,7 +305,7 @@ struct rxrpc_local *rxrpc_get_local_maybe(struct rxrpc_local *local)
 	const void *here = __builtin_return_address(0);
 
 	if (local) {
-		int n = __atomic_add_unless(&local->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&local->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_local(local, rxrpc_local_got, n + 1, here);
 		else
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 1b7e8107b3ae..1cf3b408017a 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -406,7 +406,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer)
 	const void *here = __builtin_return_address(0);
 
 	if (peer) {
-		int n = __atomic_add_unless(&peer->usage, 1, 0);
+		int n = atomic_fetch_add_unless(&peer->usage, 1, 0);
 		if (n > 0)
 			trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here);
 		else
-- 
cgit v1.2.3


From 8b47038e6d349cca950e75076566a0de990c4645 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:05 +0100
Subject: atomics/treewide: Remove redundant atomic_inc_not_zero() definitions

When atomic_inc_not_zero(v) isn't defined, <linux/atomic.h> will define
it as falling back to atomic_add_unless((v), 1, 0), so there's no need
for arch code to do so.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Palmer Dabbelt <palmer@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-3-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/include/asm/atomic.h     | 2 --
 arch/hexagon/include/asm/atomic.h | 2 --
 arch/riscv/include/asm/atomic.h   | 9 ---------
 3 files changed, 13 deletions(-)

diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 67121b5ff3a3..cecdf3403caf 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -336,8 +336,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 	c;								\
 })
 
-#define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
-
 #define atomic_inc(v)			atomic_add(1, v)
 #define atomic_dec(v)			atomic_sub(1, v)
 
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 287aa9f394f3..d2feeba93c44 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -197,8 +197,6 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 	return __oldval;
 }
 
-#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
-
 #define atomic_inc(v) atomic_add(1, (v))
 #define atomic_dec(v) atomic_sub(1, (v))
 
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 739e810c857e..0e27e050ba14 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -375,15 +375,6 @@ static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
 }
 #endif
 
-/*
- * The extra atomic operations that are constructed from one of the core
- * LR/SC-based operations above.
- */
-static __always_inline int atomic_inc_not_zero(atomic_t *v)
-{
-        return atomic_fetch_add_unless(v, 1, 0);
-}
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
 {
-- 
cgit v1.2.3


From f74445b6dd6b8f33ed34e005d19ecbb49171dabf Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:06 +0100
Subject: atomics/treewide: Remove atomic_inc_not_zero_hint()

While documentation suggests atomic_inc_not_zero_hint() will perform better
than atomic_inc_not_zero(), this is unlikely to be the case. No architectures
implement atomic_inc_not_zero_hint() directly, and thus it either falls back to
atomic_inc_not_zero(), or a loop using atomic_cmpxchg().

Whenever the hint does not match the value in memory, the repeated use of
atomic_cmpxchg() will be more expensive than the read that
atomic_inc_not_zero_hint() attempts to avoid. For architectures with LL/SC
atomics, a read cannot be avoided, and it would always be better to use
atomic_inc_not_zero() directly. For other architectures, their own
atomic_inc_not_zero() is likely to be more optimal than an atomic_cmpxchg()
loop regardless.

Generally, atomic_inc_not_zero_hint() is liable to perform worse than
atomic_inc_not_zero(). Further, atomic_inc_not_zero_hint() only exists
for atomic_t, and not atomic64_t or atomic_long_t, and there is only one
user in the kernel tree.

Given all this, let's remove atomic_inc_not_zero_hint(), and migrate the
existing user over to atomic_inc_not_zero().

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-4-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/atomic.h | 32 --------------------------------
 net/atm/pppoatm.c      |  2 +-
 2 files changed, 1 insertion(+), 33 deletions(-)

diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 9cc982936675..5c5620ae5a35 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -571,38 +571,6 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
 }
 #endif
 
-/**
- * atomic_inc_not_zero_hint - increment if not null
- * @v: pointer of type atomic_t
- * @hint: probable value of the atomic before the increment
- *
- * This version of atomic_inc_not_zero() gives a hint of probable
- * value of the atomic. This helps processor to not read the memory
- * before doing the atomic read/modify/write cycle, lowering
- * number of bus transactions on some arches.
- *
- * Returns: 0 if increment was not done, 1 otherwise.
- */
-#ifndef atomic_inc_not_zero_hint
-static inline int atomic_inc_not_zero_hint(atomic_t *v, int hint)
-{
-	int val, c = hint;
-
-	/* sanity test, should be removed by compiler if hint is a constant */
-	if (!hint)
-		return atomic_inc_not_zero(v);
-
-	do {
-		val = atomic_cmpxchg(v, c, c + 1);
-		if (val == c)
-			return 1;
-		c = val;
-	} while (c);
-
-	return 0;
-}
-#endif
-
 #ifndef atomic_inc_unless_negative
 static inline int atomic_inc_unless_negative(atomic_t *p)
 {
diff --git a/net/atm/pppoatm.c b/net/atm/pppoatm.c
index af8c4b38b746..d84227d75717 100644
--- a/net/atm/pppoatm.c
+++ b/net/atm/pppoatm.c
@@ -244,7 +244,7 @@ static int pppoatm_may_send(struct pppoatm_vcc *pvcc, int size)
 	 * the packet count limit, so...
 	 */
 	if (atm_may_send(pvcc->atmvcc, size) &&
-	    atomic_inc_not_zero_hint(&pvcc->inflight, NONE_INFLIGHT))
+	    atomic_inc_not_zero(&pvcc->inflight))
 		return 1;
 
 	/*
-- 
cgit v1.2.3


From ade5ef9280c33993099199c51e2e27c2c4013afd Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:07 +0100
Subject: atomics: Make conditional ops return 'bool'

Some of the atomics return a status value, which is a boolean value
describing whether the operation was performed. To make it clear that
this is a boolean value, let's update the common fallbacks to return
bool, fixing up the return values and comments likewise.

At the same time, let's simplify the description of the operations in
their respective comments.

The instrumented atomics and generic atomic64 implementation are updated
accordingly.

Note that atomic64_dec_if_positive() doesn't follow the usual test op
pattern, and returns the would-be decremented value. This is not
changed.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-5-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/atomic-instrumented.h |  2 +-
 include/asm-generic/atomic64.h            |  3 ++-
 include/linux/atomic.h                    | 24 +++++++++++++-----------
 lib/atomic64.c                            |  6 +++---
 4 files changed, 19 insertions(+), 16 deletions(-)

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index b8b14cc2df6c..497faa4a05e3 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -205,7 +205,7 @@ static __always_inline s64 atomic64_dec_return(atomic64_t *v)
 	return arch_atomic64_dec_return(v);
 }
 
-static __always_inline s64 atomic64_inc_not_zero(atomic64_t *v)
+static __always_inline bool atomic64_inc_not_zero(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 8d28eb010d0d..a951a721e1bb 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -11,6 +11,7 @@
  */
 #ifndef _ASM_GENERIC_ATOMIC64_H
 #define _ASM_GENERIC_ATOMIC64_H
+#include <linux/types.h>
 
 typedef struct {
 	long long counter;
@@ -52,7 +53,7 @@ ATOMIC64_OPS(xor)
 extern long long atomic64_dec_if_positive(atomic64_t *v);
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern int	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
+extern bool	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 5c5620ae5a35..307a7f6d619a 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -2,6 +2,8 @@
 /* Atomic operations usable in machine independent code */
 #ifndef _LINUX_ATOMIC_H
 #define _LINUX_ATOMIC_H
+#include <linux/types.h>
+
 #include <asm/atomic.h>
 #include <asm/barrier.h>
 
@@ -525,10 +527,10 @@
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns non-zero if @v was not @u, and zero otherwise.
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
  */
-static inline int atomic_add_unless(atomic_t *v, int a, int u)
+static inline bool atomic_add_unless(atomic_t *v, int a, int u)
 {
 	return atomic_fetch_add_unless(v, a, u) != u;
 }
@@ -537,8 +539,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
  * atomic_inc_not_zero - increment unless the number is zero
  * @v: pointer of type atomic_t
  *
- * Atomically increments @v by 1, so long as @v is non-zero.
- * Returns non-zero if @v was non-zero, and zero otherwise.
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
  */
 #ifndef atomic_inc_not_zero
 #define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
@@ -572,28 +574,28 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
 #endif
 
 #ifndef atomic_inc_unless_negative
-static inline int atomic_inc_unless_negative(atomic_t *p)
+static inline bool atomic_inc_unless_negative(atomic_t *p)
 {
 	int v, v1;
 	for (v = 0; v >= 0; v = v1) {
 		v1 = atomic_cmpxchg(p, v, v + 1);
 		if (likely(v1 == v))
-			return 1;
+			return true;
 	}
-	return 0;
+	return false;
 }
 #endif
 
 #ifndef atomic_dec_unless_positive
-static inline int atomic_dec_unless_positive(atomic_t *p)
+static inline bool atomic_dec_unless_positive(atomic_t *p)
 {
 	int v, v1;
 	for (v = 0; v <= 0; v = v1) {
 		v1 = atomic_cmpxchg(p, v, v - 1);
 		if (likely(v1 == v))
-			return 1;
+			return true;
 	}
-	return 0;
+	return false;
 }
 #endif
 
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 53c2d5edc826..4230f4b8906c 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -178,16 +178,16 @@ long long atomic64_xchg(atomic64_t *v, long long new)
 }
 EXPORT_SYMBOL(atomic64_xchg);
 
-int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	int ret = 0;
+	bool ret = false;
 
 	raw_spin_lock_irqsave(lock, flags);
 	if (v->counter != u) {
 		v->counter += a;
-		ret = 1;
+		ret = true;
 	}
 	raw_spin_unlock_irqrestore(lock, flags);
 	return ret;
-- 
cgit v1.2.3


From bef828204a1bc7a0fd3a24551c4265e9c2ab95ed Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:08 +0100
Subject: atomics/treewide: Make atomic64_inc_not_zero() optional

We define a trivial fallback for atomic_inc_not_zero(), but don't do
the same for atomic64_inc_not_zero(), leading most architectures to
define the same boilerplate.

Let's add a fallback in <linux/atomic.h>, and remove the redundant
implementations. Note that atomic64_add_unless() is always defined in
<linux/atomic.h>, and promotes its arguments to the requisite types, so
we need not do this explicitly.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Palmer Dabbelt <palmer@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-6-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h           |  2 --
 arch/arc/include/asm/atomic.h             |  1 -
 arch/arm/include/asm/atomic.h             |  1 -
 arch/arm64/include/asm/atomic.h           |  2 --
 arch/ia64/include/asm/atomic.h            |  2 --
 arch/mips/include/asm/atomic.h            |  2 --
 arch/parisc/include/asm/atomic.h          |  2 --
 arch/powerpc/include/asm/atomic.h         |  1 +
 arch/riscv/include/asm/atomic.h           |  7 -------
 arch/s390/include/asm/atomic.h            |  1 -
 arch/sparc/include/asm/atomic_64.h        |  2 --
 arch/x86/include/asm/atomic64_32.h        |  2 +-
 arch/x86/include/asm/atomic64_64.h        |  2 --
 include/asm-generic/atomic-instrumented.h |  3 +++
 include/asm-generic/atomic64.h            |  1 -
 include/linux/atomic.h                    | 11 +++++++++++
 16 files changed, 16 insertions(+), 26 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 392b15a4dd4f..eb0f25e4c5dd 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -296,8 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return old - 1;
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 #define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
 #define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index cecdf3403caf..1406825b5e7d 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -603,7 +603,6 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
 #endif	/* !CONFIG_GENERIC_ATOMIC64 */
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 9d56d0727c9b..02f3894faa48 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -534,7 +534,6 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
 #define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
 #endif /* !CONFIG_GENERIC_ATOMIC64 */
 #endif
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 264d20339f74..ad50412889c5 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -204,7 +204,5 @@
 #define atomic64_add_unless(v, a, u)	(___atomic_add_unless(v, a, u, 64) != u)
 #define atomic64_andnot			atomic64_andnot
 
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
-
 #endif
 #endif
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 9d2ddde5f9d5..93d48b823220 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -246,8 +246,6 @@ static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
 	return c != (u);
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 {
 	long c, old, dec;
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 02fc1553cf9b..502e691c6393 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -644,8 +644,6 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	return c != (u);
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 #define atomic64_dec_return(v) atomic64_sub_return(1, (v))
 #define atomic64_inc_return(v) atomic64_add_return(1, (v))
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 7748abced766..3fd0243bf405 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -305,8 +305,6 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	return c != (u);
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 1483261080a1..e59620ee4f6b 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -582,6 +582,7 @@ static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 
 	return t1 != 0;
 }
+#define atomic64_inc_not_zero(v) atomic64_inc_not_zero((v))
 
 #endif /* __powerpc64__ */
 
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 0e27e050ba14..18259e90f57e 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -375,13 +375,6 @@ static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
 }
 #endif
 
-#ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_inc_not_zero(atomic64_t *v)
-{
-        return atomic64_add_unless(v, 1, 0);
-}
-#endif
-
 /*
  * atomic_{cmp,}xchg is required to have exactly the same ordering semantics as
  * {cmp,}xchg and the operations that return, so they need a full barrier.
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index c2858cdd8c29..66dac30a4fe1 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -212,6 +212,5 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_dec(_v)		atomic64_sub(1, _v)
 #define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
 #define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)
-#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index f416fd3d2708..07830a316464 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -123,8 +123,6 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 	return c != (u);
 }
 
-#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)
-
 long atomic64_dec_if_positive(atomic64_t *v);
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 92212bf0484f..2a33cc17801b 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -295,7 +295,7 @@ static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
 	return (int)a;
 }
 
-
+#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 6106b59d3260..6f95023894b7 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -207,8 +207,6 @@ static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
 	return true;
 }
 
-#define arch_atomic64_inc_not_zero(v) arch_atomic64_add_unless((v), 1, 0)
-
 /*
  * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 497faa4a05e3..83bb88d791c4 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -205,11 +205,14 @@ static __always_inline s64 atomic64_dec_return(atomic64_t *v)
 	return arch_atomic64_dec_return(v);
 }
 
+#ifdef arch_atomic64_inc_not_zero
+#define atomic64_inc_not_zero atomic64_inc_not_zero
 static __always_inline bool atomic64_inc_not_zero(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_not_zero(v);
 }
+#endif
 
 static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index a951a721e1bb..5105275ac825 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -63,6 +63,5 @@ extern bool	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-#define atomic64_inc_not_zero(v) 	atomic64_add_unless((v), 1LL, 0LL)
 
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 307a7f6d619a..ae3f30923d05 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -1019,6 +1019,17 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
 #endif /* atomic64_try_cmpxchg */
 
+/**
+ * atomic64_inc_not_zero - increment unless the number is zero
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1, if @v is non-zero.
+ * Returns true if the increment was done.
+ */
+#ifndef atomic64_inc_not_zero
+#define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
+#endif
+
 #ifndef atomic64_andnot
 static inline void atomic64_andnot(long long i, atomic64_t *v)
 {
-- 
cgit v1.2.3


From eccc2da8c03f316bba202e15af2be4615f461900 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:09 +0100
Subject: atomics/treewide: Make atomic_fetch_add_unless() optional

Several architectures these have a near-identical implementation based
on atomic_read() and atomic_cmpxchg() which we can instead define in
<linux/atomic.h>, so let's do so, using something close to the existing
x86 implementation with try_cmpxchg().

Where an architecture provides its own atomic_fetch_add_unless(), it
must define a preprocessor symbol for it. The instrumented atomics are
updated accordingly.

Note that arch/arc's existing atomic_fetch_add_unless() had redundant
barriers, as these are already present in its atomic_cmpxchg()
implementation.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Palmer Dabbelt <palmer@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vineet Gupta <vgupta@synopsys.com>
Link: https://lore.kernel.org/lkml/20180621121321.4761-7-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h           |  2 +-
 arch/arc/include/asm/atomic.h             | 28 ----------------------------
 arch/arm/include/asm/atomic.h             | 11 +----------
 arch/arm64/include/asm/atomic.h           |  1 -
 arch/h8300/include/asm/atomic.h           |  1 +
 arch/hexagon/include/asm/atomic.h         |  1 +
 arch/ia64/include/asm/atomic.h            | 16 ----------------
 arch/m68k/include/asm/atomic.h            | 15 ---------------
 arch/mips/include/asm/atomic.h            | 24 ------------------------
 arch/parisc/include/asm/atomic.h          | 24 ------------------------
 arch/powerpc/include/asm/atomic.h         |  1 +
 arch/riscv/include/asm/atomic.h           |  1 +
 arch/s390/include/asm/atomic.h            | 15 ---------------
 arch/sh/include/asm/atomic.h              | 25 -------------------------
 arch/sparc/include/asm/atomic_32.h        |  2 ++
 arch/sparc/include/asm/atomic_64.h        | 15 ---------------
 arch/x86/include/asm/atomic.h             | 21 ---------------------
 arch/xtensa/include/asm/atomic.h          | 24 ------------------------
 include/asm-generic/atomic-instrumented.h |  4 +++-
 include/asm-generic/atomic.h              | 11 -----------
 include/linux/atomic.h                    | 23 +++++++++++++++++++++++
 21 files changed, 34 insertions(+), 231 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index eb0f25e4c5dd..4a800a3424a3 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -235,7 +235,7 @@ static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 	smp_mb();
 	return old;
 }
-
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
  * atomic64_add_unless - add unless the number is a given value
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 1406825b5e7d..60da80481c5d 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -308,34 +308,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * atomic_fetch_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v
- */
-#define atomic_fetch_add_unless(v, a, u)					\
-({									\
-	int c, old;							\
-									\
-	/*								\
-	 * Explicit full memory barrier needed before/after as		\
-	 * LLOCK/SCOND thmeselves don't provide any such semantics	\
-	 */								\
-	smp_mb();							\
-									\
-	c = atomic_read(v);						\
-	while (c != (u) && (old = atomic_cmpxchg((v), c, c + (a))) != c)\
-		c = old;						\
-									\
-	smp_mb();							\
-									\
-	c;								\
-})
-
 #define atomic_inc(v)			atomic_add(1, v)
 #define atomic_dec(v)			atomic_sub(1, v)
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 02f3894faa48..74460aa00fa0 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -156,6 +156,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 
 	return oldval;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #else /* ARM_ARCH_6 */
 
@@ -215,16 +216,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
-		c = old;
-	return c;
-}
-
 #endif /* __LINUX_ARM_ARCH__ */
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index ad50412889c5..22c8c43d6689 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -125,7 +125,6 @@
 #define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
 #define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
 #define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
-#define atomic_fetch_add_unless(v, a, u)	___atomic_add_unless(v, a, u,)
 #define atomic_andnot			atomic_andnot
 
 /*
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 5c856887fdf2..710364946308 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -106,5 +106,6 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 	arch_local_irq_restore(flags);
 	return ret;
 }
+#define atomic_fetch_add_unless		atomic_fetch_add_unless
 
 #endif /* __ARCH_H8300_ATOMIC __ */
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index d2feeba93c44..86c67e9adbfa 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -196,6 +196,7 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 	);
 	return __oldval;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #define atomic_inc(v) atomic_add(1, (v))
 #define atomic_dec(v) atomic_sub(1, (v))
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 93d48b823220..cfe44086338e 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -215,22 +215,6 @@ ATOMIC64_FETCH_OP(xor, ^)
 	(cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
-
 static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
 {
 	long c, old;
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 8022d9ea1213..596882cda224 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -211,19 +211,4 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 	return c != 0;
 }
 
-static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #endif /* __ARCH_M68K_ATOMIC __ */
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 502e691c6393..794734e730d9 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -274,30 +274,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * atomic_fetch_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define atomic_dec_return(v) atomic_sub_return(1, (v))
 #define atomic_inc_return(v) atomic_add_return(1, (v))
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 3fd0243bf405..b2b6261d05e7 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -77,30 +77,6 @@ static __inline__ int atomic_read(const atomic_t *v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * atomic_fetch_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC_OP(op, c_op)						\
 static __inline__ void atomic_##op(int i, atomic_t *v)			\
 {									\
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index e59620ee4f6b..b5646c079c16 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -248,6 +248,7 @@ static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 
 	return t;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
  * atomic_inc_not_zero - increment unless the number is zero
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 18259e90f57e..5f161daefcd2 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -349,6 +349,7 @@ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 		: "memory");
 	return prev;
 }
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #ifndef CONFIG_GENERIC_ATOMIC64
 static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 66dac30a4fe1..26c6b713a7a3 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -90,21 +90,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return __atomic_cmpxchg(&v->counter, old, new);
 }
 
-static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic_cmpxchg(v, c, c + a);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define ATOMIC64_INIT(i)  { (i) }
 
 static inline long atomic64_read(const atomic64_t *v)
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index ef45931ebac5..422fac764ca1 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -45,31 +45,6 @@
 #define atomic_xchg(v, new)		(xchg(&((v)->counter), new))
 #define atomic_cmpxchg(v, o, n)		(cmpxchg(&((v)->counter), (o), (n)))
 
-/**
- * atomic_fetch_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-
-	return c;
-}
-
 #endif /* CONFIG_CPU_J2 */
 
 #endif /* __ASM_SH_ATOMIC_H */
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index a58f4b43bcc7..9d7a15acc0c5 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -30,6 +30,8 @@ int atomic_xchg(atomic_t *, int);
 int atomic_fetch_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
+#define atomic_fetch_add_unless	atomic_fetch_add_unless
+
 #define atomic_set_release(v, i)	atomic_set((v), (i))
 
 #define atomic_read(v)          READ_ONCE((v)->counter)
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 07830a316464..e4f1c93db31f 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -89,21 +89,6 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	return xchg(&v->counter, new);
 }
 
-static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 84ed0bd76aef..616327ac9d39 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -253,27 +253,6 @@ static inline int arch_atomic_fetch_xor(int i, atomic_t *v)
 	return val;
 }
 
-/**
- * arch_atomic_fetch_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns the old value of @v.
- */
-static __always_inline int arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c = arch_atomic_read(v);
-
-	do {
-		if (unlikely(c == u))
-			break;
-	} while (!arch_atomic_try_cmpxchg(v, &c, c + a));
-
-	return c;
-}
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 4188e56c06c9..f4c9f82c40c6 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -274,30 +274,6 @@ ATOMIC_OPS(xor)
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * atomic_fetch_add_unless - add unless the number is a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c;
-}
-
 #endif /* __KERNEL__ */
 
 #endif /* _XTENSA_ATOMIC_H */
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 83bb88d791c4..1f9b2a767d3c 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -84,12 +84,14 @@ static __always_inline bool atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 ne
 }
 #endif
 
+#ifdef arch_atomic_fetch_add_unless
+#define atomic_fetch_add_unless atomic_fetch_add_unless
 static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_fetch_add_unless(v, a, u);
 }
-
+#endif
 
 static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 10051ed6d088..757e45821220 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -221,15 +221,4 @@ static inline void atomic_dec(atomic_t *v)
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
-#ifndef atomic_fetch_add_unless
-static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
-{
-	int c, old;
-	c = atomic_read(v);
-	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
-		c = old;
-	return c;
-}
-#endif
-
 #endif /* __ASM_GENERIC_ATOMIC_H */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index ae3f30923d05..b89ba36cab94 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -521,6 +521,29 @@
 #endif
 #endif /* xchg_relaxed */
 
+/**
+ * atomic_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic_fetch_add_unless
+static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
+{
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic_try_cmpxchg(v, &c, c + a));
+
+	return c;
+}
+#endif
+
 /**
  * atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
-- 
cgit v1.2.3


From 0ae1d994020d75ac065fd42ac4cbf5ac6ce9b255 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:10 +0100
Subject: atomics: Prepare for atomic64_fetch_add_unless()

Currently all architectures must implement atomic_fetch_add_unless(),
with common code providing atomic_add_unless(). Architectures must also
implement atomic64_add_unless() directly, with no corresponding
atomic64_fetch_add_unless().

This divergence is unfortunate, and means that the APIs for atomic_t,
atomic64_t, and atomic_long_t differ.

In preparation for unifying things, with architectures providing
atomic64_fetch_add_unless, this patch adds a generic
atomic64_add_unless() which will use atomic64_fetch_add_unless(). The
instrumented atomics are updated to take this case into account.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Albert Ou <albert@sifive.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vineet Gupta <vgupta@synopsys.com>
Link: https://lore.kernel.org/lkml/20180621121321.4761-8-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/atomic-instrumented.h |  9 +++++++++
 include/linux/atomic.h                    | 16 ++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 1f9b2a767d3c..444bf2f9d54d 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -93,11 +93,20 @@ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 }
 #endif
 
+#ifdef arch_atomic64_fetch_add_unless
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
+static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
+{
+	kasan_check_write(v, sizeof(*v));
+	return arch_atomic64_fetch_add_unless(v, a, u);
+}
+#else
 static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_unless(v, a, u);
 }
+#endif
 
 static __always_inline void atomic_inc(atomic_t *v)
 {
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index b89ba36cab94..3c03de648007 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -1042,6 +1042,22 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
 #endif /* atomic64_try_cmpxchg */
 
+/**
+ * atomic64_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns true if the addition was done.
+ */
+#ifdef atomic64_fetch_add_unless
+static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+	return atomic64_fetch_add_unless(v, a, u) != u;
+}
+#endif
+
 /**
  * atomic64_inc_not_zero - increment unless the number is zero
  * @v: pointer of type atomic64_t
-- 
cgit v1.2.3


From 00b808ab79ead372daf1a0682d1ef271599c0b55 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:11 +0100
Subject: atomics/generic: Define atomic64_fetch_add_unless()

As a step towards unifying the atomic/atomic64/atomic_long APIs, this
patch converts the generic implementation of atomic64_add_unless() into
a generic implementation of atomic64_fetch_add_unless().

A wrapper in <linux/atomic.h> will build atomic_add_unless() atop of
this, provided it is given a preprocessor definition.

No functional change is intended as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-9-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/atomic64.h |  3 ++-
 lib/atomic64.c                 | 14 +++++++-------
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 5105275ac825..49460107b29a 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -53,7 +53,8 @@ ATOMIC64_OPS(xor)
 extern long long atomic64_dec_if_positive(atomic64_t *v);
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern bool	 atomic64_add_unless(atomic64_t *v, long long a, long long u);
+extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 4230f4b8906c..1d91e31eceec 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -178,18 +178,18 @@ long long atomic64_xchg(atomic64_t *v, long long new)
 }
 EXPORT_SYMBOL(atomic64_xchg);
 
-bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
+long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	bool ret = false;
+	long long val;
 
 	raw_spin_lock_irqsave(lock, flags);
-	if (v->counter != u) {
+	val = v->counter;
+	if (val != u)
 		v->counter += a;
-		ret = true;
-	}
 	raw_spin_unlock_irqrestore(lock, flags);
-	return ret;
+
+	return val;
 }
-EXPORT_SYMBOL(atomic64_add_unless);
+EXPORT_SYMBOL(atomic64_fetch_add_unless);
-- 
cgit v1.2.3


From 434b6acc31302b37031674af104f45eb4e7a1fc1 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:12 +0100
Subject: atomics/alpha: Define atomic64_fetch_add_unless()

As a step towards unifying the atomic/atomic64/atomic_long APIs, this
patch converts the arch/alpha implementation of atomic64_add_unless() into
an implementation of atomic64_fetch_add_unless().

A wrapper in <linux/atomic.h> will build atomic_add_unless() atop of
this, provided it is given a preprocessor definition.

No functional change is intended as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-10-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 4a800a3424a3..cc486dbb3837 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -238,35 +238,36 @@ static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 #define atomic_fetch_add_unless atomic_fetch_add_unless
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
+ * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
-	long c, tmp;
+	long c, new, old;
 	smp_mb();
 	__asm__ __volatile__(
-	"1:	ldq_l	%[tmp],%[mem]\n"
-	"	cmpeq	%[tmp],%[u],%[c]\n"
-	"	addq	%[tmp],%[a],%[tmp]\n"
+	"1:	ldq_l	%[old],%[mem]\n"
+	"	cmpeq	%[old],%[u],%[c]\n"
+	"	addq	%[old],%[a],%[new]\n"
 	"	bne	%[c],2f\n"
-	"	stq_c	%[tmp],%[mem]\n"
-	"	beq	%[tmp],3f\n"
+	"	stq_c	%[new],%[mem]\n"
+	"	beq	%[new],3f\n"
 	"2:\n"
 	".subsection 2\n"
 	"3:	br	1b\n"
 	".previous"
-	: [tmp] "=&r"(tmp), [c] "=&r"(c)
+	: [old] "=&r"(old), [new] "=&r"(new), [c] "=&r"(c)
 	: [mem] "m"(*v), [a] "rI"(a), [u] "rI"(u)
 	: "memory");
 	smp_mb();
-	return !c;
+	return old;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
-- 
cgit v1.2.3


From ab0b910490fef91cd02691d3311f6ebaaed4c196 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:13 +0100
Subject: atomics/arc: Define atomic64_fetch_add_unless()

As a step towards unifying the atomic/atomic64/atomic_long APIs, this
patch converts the arch/arc implementation of atomic64_add_unless() into
an implementation of atomic64_fetch_add_unless().

A wrapper in <linux/atomic.h> will build atomic_add_unless() atop of
this, provided it is given a preprocessor definition.

No functional change is intended as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vineet Gupta <vgupta@synopsys.com>
Link: https://lore.kernel.org/lkml/20180621121321.4761-11-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/include/asm/atomic.h | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 60da80481c5d..4917ffa61579 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -531,41 +531,40 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 }
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
  *
- * if (v != u) { v += a; ret = 1} else {ret = 0}
- * Returns 1 iff @v was not @u (i.e. if add actually happened)
+ * Atomically adds @a to @v, if it was not @u.
+ * Returns the old value of @v
  */
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
-	int op_done;
+	long long old, temp;
 
 	smp_mb();
 
 	__asm__ __volatile__(
 	"1:	llockd  %0, [%2]	\n"
-	"	mov	%1, 1		\n"
 	"	brne	%L0, %L4, 2f	# continue to add since v != u \n"
 	"	breq.d	%H0, %H4, 3f	# return since v == u \n"
-	"	mov	%1, 0		\n"
 	"2:				\n"
-	"	add.f   %L0, %L0, %L3	\n"
-	"	adc     %H0, %H0, %H3	\n"
-	"	scondd  %0, [%2]	\n"
+	"	add.f   %L1, %L0, %L3	\n"
+	"	adc     %H1, %H0, %H3	\n"
+	"	scondd  %1, [%2]	\n"
 	"	bnz     1b		\n"
 	"3:				\n"
-	: "=&r"(val), "=&r" (op_done)
+	: "=&r"(old), "=&r" (temp)
 	: "r"(&v->counter), "r"(a), "r"(u)
 	: "cc");	/* memory clobber comes from smp_mb() */
 
 	smp_mb();
 
-	return op_done;
+	return old;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
-- 
cgit v1.2.3


From fee8ca9fa5659d8d79432d38c52fa18da67f1e71 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:14 +0100
Subject: atomics/arm: Define atomic64_fetch_add_unless()

As a step towards unifying the atomic/atomic64/atomic_long APIs, this
patch converts the arch/arm implementation of atomic64_add_unless() into
an implementation of atomic64_fetch_add_unless().

A wrapper in <linux/atomic.h> will build atomic_add_unless() atop of
this, provided it is given a preprocessor definition.

No functional change is intended as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Russell King <linux@armlinux.org.uk>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-12-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/atomic.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 74460aa00fa0..852e1fee72b0 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -486,11 +486,11 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 	return result;
 }
 
-static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
 {
-	long long val;
+	long long oldval, newval;
 	unsigned long tmp;
-	int ret = 1;
 
 	smp_mb();
 	prefetchw(&v->counter);
@@ -499,23 +499,23 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 "1:	ldrexd	%0, %H0, [%4]\n"
 "	teq	%0, %5\n"
 "	teqeq	%H0, %H5\n"
-"	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%Q0, %Q0, %Q6\n"
-"	adc	%R0, %R0, %R6\n"
-"	strexd	%2, %0, %H0, [%4]\n"
+"	adds	%Q1, %Q0, %Q6\n"
+"	adc	%R1, %R0, %R6\n"
+"	strexd	%2, %1, %H1, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
 "2:"
-	: "=&r" (val), "+r" (ret), "=&r" (tmp), "+Qo" (v->counter)
+	: "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
 	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");
 
-	if (ret)
+	if (oldval != u)
 		smp_mb();
 
-	return ret;
+	return oldval;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
-- 
cgit v1.2.3


From 4f44b4b2b337e100ae655d03c42d140816c8caf9 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:15 +0100
Subject: atomics/powerpc: Define atomic64_fetch_add_unless()

As a step towards unifying the atomic/atomic64/atomic_long APIs, this
patch converts the arch/powerpc implementation of atomic64_add_unless()
into an implementation of atomic64_fetch_add_unless().

A wrapper in <linux/atomic.h> will build atomic_add_unless() atop of
this, provided it is given a preprocessor definition.

No functional change is intended as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-13-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/include/asm/atomic.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index b5646c079c16..233dbf31911c 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -525,7 +525,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_xchg_relaxed(v, new) xchg_relaxed(&((v)->counter), (new))
 
 /**
- * atomic64_add_unless - add unless the number is a given value
+ * atomic64_fetch_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
  * @a: the amount to add to v...
  * @u: ...unless v is equal to u.
@@ -533,13 +533,13 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
+static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
 	long t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
-"1:	ldarx	%0,0,%1		# atomic_fetch_add_unless\n\
+"1:	ldarx	%0,0,%1		# atomic64_fetch_add_unless\n\
 	cmpd	0,%0,%3 \n\
 	beq	2f \n\
 	add	%0,%2,%0 \n"
@@ -552,8 +552,9 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 	: "r" (&v->counter), "r" (a), "r" (u)
 	: "cc", "memory");
 
-	return t != u;
+	return t;
 }
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 /**
  * atomic_inc64_not_zero - increment unless the number is zero
-- 
cgit v1.2.3


From 2b523f170e399b0e1c8eec2c4b5889735b0d2b9b Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:16 +0100
Subject: atomics/riscv: Define atomic64_fetch_add_unless()

As a step towards unifying the atomic/atomic64/atomic_long APIs, this
patch converts the arch/riscv implementation of atomic64_add_unless()
into an implementation of atomic64_fetch_add_unless().

A wrapper in <linux/atomic.h> will build atomic_add_unless() atop of
this, provided it is given a preprocessor definition.

No functional change is intended as a result of this patch.

Acked-by Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Albert Ou <albert@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Palmer Dabbelt <palmer@sifive.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-14-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/riscv/include/asm/atomic.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 5f161daefcd2..d959bbaaad41 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -352,7 +352,7 @@ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 #define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
+static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
 {
        long prev, rc;
 
@@ -369,11 +369,7 @@ static __always_inline long __atomic64_add_unless(atomic64_t *v, long a, long u)
 		: "memory");
 	return prev;
 }
-
-static __always_inline int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	return __atomic64_add_unless(v, a, u) != u;
-}
+#define atomic64_fetch_add_unless atomic64_fetch_add_unless
 #endif
 
 /*
-- 
cgit v1.2.3


From 356701329fb391184618eda7b7fb68cb35271506 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:17 +0100
Subject: atomics/treewide: Make atomic64_fetch_add_unless() optional

Architectures with atomic64_fetch_add_unless() provide a preprocessor
symbol if they do so, and all other architectures have trivial C
implementations of atomic64_add_unless() which are near-identical.

Let's unify the trivial definitions of atomic64_fetch_add_unless() in
<linux/atomic.h>, so that we always have both
atomic64_fetch_add_unless() and atomic64_add_unless() with less
boilerplate code.

This means that atomic64_add_unless() is always implemented in core
code, and the instrumented atomics are updated accordingly.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-15-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/include/asm/atomic.h           | 12 ------------
 arch/ia64/include/asm/atomic.h            | 15 ---------------
 arch/mips/include/asm/atomic.h            | 24 ------------------------
 arch/parisc/include/asm/atomic.h          | 24 ------------------------
 arch/s390/include/asm/atomic.h            | 16 ----------------
 arch/sparc/include/asm/atomic_64.h        | 15 ---------------
 arch/x86/include/asm/atomic64_64.h        | 19 -------------------
 include/asm-generic/atomic-instrumented.h |  6 ------
 include/linux/atomic.h                    | 26 ++++++++++++++++++++++++--
 9 files changed, 24 insertions(+), 133 deletions(-)

diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 22c8c43d6689..82db0e4febd4 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -40,17 +40,6 @@
 
 #include <asm/cmpxchg.h>
 
-#define ___atomic_add_unless(v, a, u, sfx)				\
-({									\
-	typeof((v)->counter) c, old;					\
-									\
-	c = atomic##sfx##_read(v);					\
-	while (c != (u) &&						\
-	      (old = atomic##sfx##_cmpxchg((v), c, c + (a))) != c)	\
-		c = old;						\
-	c;								\
- })
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #define atomic_read(v)			READ_ONCE((v)->counter)
@@ -200,7 +189,6 @@
 #define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
 #define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
 #define atomic64_add_negative(i, v)	(atomic64_add_return((i), (v)) < 0)
-#define atomic64_add_unless(v, a, u)	(___atomic_add_unless(v, a, u, 64) != u)
 #define atomic64_andnot			atomic64_andnot
 
 #endif
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index cfe44086338e..0f80a3eafaba 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -215,21 +215,6 @@ ATOMIC64_FETCH_OP(xor, ^)
 	(cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static __inline__ long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
 static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 {
 	long c, old, dec;
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 794734e730d9..d42b27df1548 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -596,30 +596,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns true iff @v was not @u.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
 #define atomic64_dec_return(v) atomic64_sub_return(1, (v))
 #define atomic64_inc_return(v) atomic64_add_return(1, (v))
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index b2b6261d05e7..f53ba2d6ff67 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -257,30 +257,6 @@ atomic64_read(const atomic64_t *v)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-/**
- * atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 26c6b713a7a3..eb9329741bad 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -153,22 +153,6 @@ ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
 
-static inline int atomic64_add_unless(atomic64_t *v, long i, long u)
-{
-	long c, old;
-
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == u))
-			break;
-		old = atomic64_cmpxchg(v, c, c + i);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != u;
-}
-
 static inline long atomic64_dec_if_positive(atomic64_t *v)
 {
 	long c, old, dec;
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index e4f1c93db31f..458783e99997 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -93,21 +93,6 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	long c, old;
-	c = atomic64_read(v);
-	for (;;) {
-		if (unlikely(c == (u)))
-			break;
-		old = atomic64_cmpxchg((v), c, c + (a));
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return c != (u);
-}
-
 long atomic64_dec_if_positive(atomic64_t *v);
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 6f95023894b7..7e04b294e6eb 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -188,25 +188,6 @@ static inline long arch_atomic64_xchg(atomic64_t *v, long new)
 	return xchg(&v->counter, new);
 }
 
-/**
- * arch_atomic64_add_unless - add unless the number is a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
- *
- * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
- */
-static inline bool arch_atomic64_add_unless(atomic64_t *v, long a, long u)
-{
-	s64 c = arch_atomic64_read(v);
-	do {
-		if (unlikely(c == u))
-			return false;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
-	return true;
-}
-
 /*
  * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 444bf2f9d54d..2b487f28ef35 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -100,12 +100,6 @@ static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_fetch_add_unless(v, a, u);
 }
-#else
-static __always_inline bool atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
-{
-	kasan_check_write(v, sizeof(*v));
-	return arch_atomic64_add_unless(v, a, u);
-}
 #endif
 
 static __always_inline void atomic_inc(atomic_t *v)
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 3c03de648007..530562ac7909 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -1042,6 +1042,30 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #define atomic64_try_cmpxchg_release	atomic64_try_cmpxchg
 #endif /* atomic64_try_cmpxchg */
 
+/**
+ * atomic64_fetch_add_unless - add unless the number is already a given value
+ * @v: pointer of type atomic64_t
+ * @a: the amount to add to v...
+ * @u: ...unless v is equal to u.
+ *
+ * Atomically adds @a to @v, if @v was not already @u.
+ * Returns the original value of @v.
+ */
+#ifndef atomic64_fetch_add_unless
+static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
+						  long long u)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c == u))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, c + a));
+
+	return c;
+}
+#endif
+
 /**
  * atomic64_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t
@@ -1051,12 +1075,10 @@ static inline int atomic_dec_if_positive(atomic_t *v)
  * Atomically adds @a to @v, if @v was not already @u.
  * Returns true if the addition was done.
  */
-#ifdef atomic64_fetch_add_unless
 static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
 	return atomic64_fetch_add_unless(v, a, u) != u;
 }
-#endif
 
 /**
  * atomic64_inc_not_zero - increment unless the number is zero
-- 
cgit v1.2.3


From 18cc1814d4e7560412c9c8c6d28f9d6782c8b402 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:18 +0100
Subject: atomics/treewide: Make test ops optional

Some of the atomics return the result of a test applied after the atomic
operation, and almost all architectures implement these as trivial
wrappers around the underlying atomic. Specifically:

 * <atomic>_inc_and_test(v)    is (<atomic>_inc_return(v)    == 0)
 * <atomic>_dec_and_test(v)    is (<atomic>_dec_return(v)    == 0)
 * <atomic>_sub_and_test(i, v) is (<atomic>_sub_return(i, v) == 0)
 * <atomic>_add_negative(i, v) is (<atomic>_add_return(i, v)  < 0)

Rather than have these definitions duplicated in all architectures, with
minor inconsistencies in formatting and documentation, let's make these
operations optional, with default fallbacks as above. Implementations
must now provide a preprocessor symbol.

The instrumented atomics are updated accordingly.

Both x86 and m68k have custom implementations, which are left as-is,
given preprocessor symbols to avoid being overridden.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Palmer Dabbelt <palmer@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-16-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h           |  12 ---
 arch/arc/include/asm/atomic.h             |  10 ---
 arch/arm/include/asm/atomic.h             |   9 ---
 arch/arm64/include/asm/atomic.h           |   8 --
 arch/h8300/include/asm/atomic.h           |   5 --
 arch/hexagon/include/asm/atomic.h         |   5 --
 arch/ia64/include/asm/atomic.h            |  23 ------
 arch/m68k/include/asm/atomic.h            |   4 +
 arch/mips/include/asm/atomic.h            |  84 --------------------
 arch/parisc/include/asm/atomic.h          |  22 ------
 arch/powerpc/include/asm/atomic.h         |  30 --------
 arch/riscv/include/asm/atomic.h           |  46 -----------
 arch/s390/include/asm/atomic.h            |   8 --
 arch/sh/include/asm/atomic.h              |   4 -
 arch/sparc/include/asm/atomic_32.h        |  15 ----
 arch/sparc/include/asm/atomic_64.h        |  20 -----
 arch/x86/include/asm/atomic.h             |   4 +
 arch/x86/include/asm/atomic64_32.h        |  54 -------------
 arch/x86/include/asm/atomic64_64.h        |   4 +
 arch/xtensa/include/asm/atomic.h          |  42 ----------
 include/asm-generic/atomic-instrumented.h |  24 ++++++
 include/asm-generic/atomic.h              |   9 ---
 include/asm-generic/atomic64.h            |   4 -
 include/linux/atomic.h                    | 124 ++++++++++++++++++++++++++++++
 24 files changed, 160 insertions(+), 410 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index cc486dbb3837..25f8693c5a42 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -297,24 +297,12 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return old - 1;
 }
 
-#define atomic_add_negative(a, v) (atomic_add_return((a), (v)) < 0)
-#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
-
 #define atomic_dec_return(v) atomic_sub_return(1,(v))
 #define atomic64_dec_return(v) atomic64_sub_return(1,(v))
 
 #define atomic_inc_return(v) atomic_add_return(1,(v))
 #define atomic64_inc_return(v) atomic64_add_return(1,(v))
 
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i), (v)) == 0)
-#define atomic64_sub_and_test(i,v) (atomic64_sub_return((i), (v)) == 0)
-
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v) (atomic64_add_return(1, (v)) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
 #define atomic_inc(v) atomic_add(1,(v))
 #define atomic64_inc(v) atomic64_add(1,(v))
 
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 4917ffa61579..4222e726f84c 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -311,14 +311,8 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 #define atomic_inc(v)			atomic_add(1, v)
 #define atomic_dec(v)			atomic_sub(1, v)
 
-#define atomic_inc_and_test(v)		(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, v) == 0)
 #define atomic_inc_return(v)		atomic_add_return(1, (v))
 #define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i, v)	(atomic_add_return(i, v) < 0)
-
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 
@@ -566,14 +560,10 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
 }
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 
 #endif	/* !CONFIG_GENERIC_ATOMIC64 */
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 852e1fee72b0..35fb7f504daa 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -248,13 +248,8 @@ ATOMIC_OPS(xor, ^=, eor)
 #define atomic_inc(v)		atomic_add(1, v)
 #define atomic_dec(v)		atomic_sub(1, v)
 
-#define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
-#define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
 #define atomic_inc_return_relaxed(v)    (atomic_add_return_relaxed(1, v))
 #define atomic_dec_return_relaxed(v)    (atomic_sub_return_relaxed(1, v))
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
-#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
@@ -517,14 +512,10 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
 }
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
 #define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1LL, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
 #define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 
 #endif /* !CONFIG_GENERIC_ATOMIC64 */
 #endif
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 82db0e4febd4..edbe53fa3106 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -110,10 +110,6 @@
 
 #define atomic_inc(v)			atomic_add(1, (v))
 #define atomic_dec(v)			atomic_sub(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_add_negative(i, v)	(atomic_add_return((i), (v)) < 0)
 #define atomic_andnot			atomic_andnot
 
 /*
@@ -185,10 +181,6 @@
 
 #define atomic64_inc(v)			atomic64_add(1, (v))
 #define atomic64_dec(v)			atomic64_sub(1, (v))
-#define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i, v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_add_negative(i, v)	(atomic64_add_return((i), (v)) < 0)
 #define atomic64_andnot			atomic64_andnot
 
 #endif
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 710364946308..8977b5157c8f 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -69,17 +69,12 @@ ATOMIC_OPS(sub, -=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-#define atomic_sub_and_test(i, v)	(atomic_sub_return(i, v) == 0)
-
 #define atomic_inc_return(v)		atomic_add_return(1, v)
 #define atomic_dec_return(v)		atomic_sub_return(1, v)
 
 #define atomic_inc(v)			(void)atomic_inc_return(v)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
 
 #define atomic_dec(v)			(void)atomic_dec_return(v)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 86c67e9adbfa..31638f511674 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -201,11 +201,6 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 #define atomic_inc(v) atomic_add(1, (v))
 #define atomic_dec(v) atomic_sub(1, (v))
 
-#define atomic_inc_and_test(v) (atomic_add_return(1, (v)) == 0)
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
 #define atomic_inc_return(v) (atomic_add_return(1, v))
 #define atomic_dec_return(v) (atomic_sub_return(1, v))
 
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 0f80a3eafaba..e4143c462e65 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -231,34 +231,11 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
-/*
- * Atomically add I to V and return TRUE if the resulting value is
- * negative.
- */
-static __inline__ int
-atomic_add_negative (int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
-static __inline__ long
-atomic64_add_negative (__s64 i, atomic64_t *v)
-{
-	return atomic64_add_return(i, v) < 0;
-}
-
 #define atomic_dec_return(v)		atomic_sub_return(1, (v))
 #define atomic_inc_return(v)		atomic_add_return(1, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1, (v))
 
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
-#define atomic_inc_and_test(v)		(atomic_add_return(1, (v)) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_sub_return(1, (v)) == 0)
-#define atomic64_inc_and_test(v)	(atomic64_add_return(1, (v)) == 0)
-
 #define atomic_add(i,v)			(void)atomic_add_return((i), (v))
 #define atomic_sub(i,v)			(void)atomic_sub_return((i), (v))
 #define atomic_inc(v)			atomic_add(1, (v))
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 596882cda224..9df09c876fa2 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -138,6 +138,7 @@ static inline int atomic_dec_and_test(atomic_t *v)
 	__asm__ __volatile__("subql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_dec_and_test atomic_dec_and_test
 
 static inline int atomic_dec_and_test_lt(atomic_t *v)
 {
@@ -155,6 +156,7 @@ static inline int atomic_inc_and_test(atomic_t *v)
 	__asm__ __volatile__("addql #1,%1; seq %0" : "=d" (c), "+m" (*v));
 	return c != 0;
 }
+#define atomic_inc_and_test atomic_inc_and_test
 
 #ifdef CONFIG_RMW_INSNS
 
@@ -201,6 +203,7 @@ static inline int atomic_sub_and_test(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
+#define atomic_sub_and_test atomic_sub_and_test
 
 static inline int atomic_add_negative(int i, atomic_t *v)
 {
@@ -210,5 +213,6 @@ static inline int atomic_add_negative(int i, atomic_t *v)
 			     : ASM_DI (i));
 	return c != 0;
 }
+#define atomic_add_negative atomic_add_negative
 
 #endif /* __ARCH_M68K_ATOMIC __ */
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index d42b27df1548..fd3008ae164c 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -277,37 +277,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic_dec_return(v) atomic_sub_return(1, (v))
 #define atomic_inc_return(v) atomic_add_return(1, (v))
 
-/*
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i, v) (atomic_sub_return((i), (v)) == 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-/*
- * atomic_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1, (v)) == 0)
-
 /*
  * atomic_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
@@ -330,17 +299,6 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
  */
 #define atomic_dec(v) atomic_sub(1, (v))
 
-/*
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i)    { (i) }
@@ -599,37 +557,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 #define atomic64_dec_return(v) atomic64_sub_return(1, (v))
 #define atomic64_inc_return(v) atomic64_add_return(1, (v))
 
-/*
- * atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return((i), (v)) == 0)
-
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-/*
- * atomic64_dec_and_test - decrement by 1 and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, (v)) == 0)
-
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic64_t
@@ -652,17 +579,6 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
  */
 #define atomic64_dec(v) atomic64_sub(1, (v))
 
-/*
- * atomic64_add_negative - add and test if negative
- * @v: pointer of type atomic64_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, (v)) < 0)
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index f53ba2d6ff67..f85844ff6336 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -142,22 +142,6 @@ ATOMIC_OPS(xor, ^=)
 #define atomic_inc_return(v)	(atomic_add_return(   1,(v)))
 #define atomic_dec_return(v)	(atomic_add_return(  -1,(v)))
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v)	(atomic_dec_return(v) == 0)
-
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i),(v)) == 0)
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_64BIT
@@ -246,12 +230,6 @@ atomic64_read(const atomic64_t *v)
 #define atomic64_inc_return(v)		(atomic64_add_return(   1,(v)))
 #define atomic64_dec_return(v)		(atomic64_add_return(  -1,(v)))
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return(v) == 0)
-#define atomic64_sub_and_test(i,v)	(atomic64_sub_return((i),(v)) == 0)
-
 /* exported interface */
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 233dbf31911c..5d76f05d2be3 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -129,8 +129,6 @@ ATOMIC_OPS(xor, xor)
 #undef ATOMIC_OP_RETURN_RELAXED
 #undef ATOMIC_OP
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
 static __inline__ void atomic_inc(atomic_t *v)
 {
 	int t;
@@ -163,16 +161,6 @@ static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 	return t;
 }
 
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
 static __inline__ void atomic_dec(atomic_t *v)
 {
 	int t;
@@ -281,9 +269,6 @@ static __inline__ int atomic_inc_not_zero(atomic_t *v)
 }
 #define atomic_inc_not_zero(v) atomic_inc_not_zero((v))
 
-#define atomic_sub_and_test(a, v)	(atomic_sub_return((a), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1, even if
@@ -413,8 +398,6 @@ ATOMIC64_OPS(xor, xor)
 #undef ATOMIC64_OP_RETURN_RELAXED
 #undef ATOMIC64_OP
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
-
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
 	long t;
@@ -445,16 +428,6 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 	return t;
 }
 
-/*
- * atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
 static __inline__ void atomic64_dec(atomic64_t *v)
 {
 	long t;
@@ -488,9 +461,6 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 #define atomic64_inc_return_relaxed atomic64_inc_return_relaxed
 #define atomic64_dec_return_relaxed atomic64_dec_return_relaxed
 
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
-
 /*
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1.
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index d959bbaaad41..68eef0a805ca 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -209,36 +209,6 @@ ATOMIC_OPS(xor, xor, i)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
-/*
- * The extra atomic operations that are constructed from one of the core
- * AMO-based operations above (aside from sub, which is easier to fit above).
- * These are required to perform a full barrier, but they're OK this way
- * because atomic_*_return is also required to perform a full barrier.
- *
- */
-#define ATOMIC_OP(op, func_op, comp_op, I, c_type, prefix)		\
-static __always_inline							\
-bool atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_##func_op##_return(i, v) comp_op I;	\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, func_op, comp_op, I)				\
-        ATOMIC_OP(op, func_op, comp_op, I,  int,   )			\
-        ATOMIC_OP(op, func_op, comp_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(add_and_test, add, ==, 0)
-ATOMIC_OPS(sub_and_test, sub, ==, 0)
-ATOMIC_OPS(add_negative, add,  <, 0)
-
-#undef ATOMIC_OP
-#undef ATOMIC_OPS
-
 #define ATOMIC_OP(op, func_op, I, c_type, prefix)			\
 static __always_inline							\
 void atomic##prefix##_##op(atomic##prefix##_t *v)			\
@@ -315,22 +285,6 @@ ATOMIC_OPS(dec, add, +, -1)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
-#define ATOMIC_OP(op, func_op, comp_op, I, prefix)			\
-static __always_inline							\
-bool atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	return atomic##prefix##_##func_op##_return(v) comp_op I;	\
-}
-
-ATOMIC_OP(inc_and_test, inc, ==, 0,   )
-ATOMIC_OP(dec_and_test, dec, ==, 0,   )
-#ifndef CONFIG_GENERIC_ATOMIC64
-ATOMIC_OP(inc_and_test, inc, ==, 0, 64)
-ATOMIC_OP(dec_and_test, dec, ==, 0, 64)
-#endif
-
-#undef ATOMIC_OP
-
 /* This is required to provide a full barrier on success. */
 static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index eb9329741bad..7f5fbd595f01 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -55,17 +55,13 @@ static inline void atomic_add(int i, atomic_t *v)
 	__atomic_add(i, &v->counter);
 }
 
-#define atomic_add_negative(_i, _v)	(atomic_add_return(_i, _v) < 0)
 #define atomic_inc(_v)			atomic_add(1, _v)
 #define atomic_inc_return(_v)		atomic_add_return(1, _v)
-#define atomic_inc_and_test(_v)		(atomic_add_return(1, _v) == 0)
 #define atomic_sub(_i, _v)		atomic_add(-(int)(_i), _v)
 #define atomic_sub_return(_i, _v)	atomic_add_return(-(int)(_i), _v)
 #define atomic_fetch_sub(_i, _v)	atomic_fetch_add(-(int)(_i), _v)
-#define atomic_sub_and_test(_i, _v)	(atomic_sub_return(_i, _v) == 0)
 #define atomic_dec(_v)			atomic_sub(1, _v)
 #define atomic_dec_return(_v)		atomic_sub_return(1, _v)
-#define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)
 
 #define ATOMIC_OPS(op)							\
 static inline void atomic_##op(int i, atomic_t *v)			\
@@ -170,16 +166,12 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
-#define atomic64_add_negative(_i, _v)	(atomic64_add_return(_i, _v) < 0)
 #define atomic64_inc(_v)		atomic64_add(1, _v)
 #define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
-#define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
 #define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
-#define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
 #define atomic64_dec(_v)		atomic64_sub(1, _v)
 #define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
-#define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)
 
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index 422fac764ca1..d438494fa112 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -32,12 +32,8 @@
 #include <asm/atomic-irq.h>
 #endif
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
 #define atomic_dec_return(v)		atomic_sub_return(1, (v))
 #define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-#define atomic_sub_and_test(i,v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_sub_return(1, (v)) == 0)
 
 #define atomic_inc(v)			atomic_add(1, (v))
 #define atomic_dec(v)			atomic_sub(1, (v))
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 9d7a15acc0c5..3a26573790c6 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -51,19 +51,4 @@ void atomic_set(atomic_t *, int);
 #define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
 #define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
 
-#define atomic_add_negative(a, v)	(atomic_add_return((a), (v)) < 0)
-
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-
 #endif /* !(__ARCH_SPARC_ATOMIC__) */
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 458783e99997..634508282aea 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -56,32 +56,12 @@ ATOMIC_OPS(xor)
 #define atomic_inc_return(v)   atomic_add_return(1, v)
 #define atomic64_inc_return(v) atomic64_add_return(1, v)
 
-/*
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_inc_return(v) == 0)
-#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
-
-#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
-#define atomic64_sub_and_test(i, v) (atomic64_sub_return(i, v) == 0)
-
-#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
-#define atomic64_dec_and_test(v) (atomic64_sub_return(1, v) == 0)
-
 #define atomic_inc(v) atomic_add(1, v)
 #define atomic64_inc(v) atomic64_add(1, v)
 
 #define atomic_dec(v) atomic_sub(1, v)
 #define atomic64_dec(v) atomic64_sub(1, v)
 
-#define atomic_add_negative(i, v) (atomic_add_return(i, v) < 0)
-#define atomic64_add_negative(i, v) (atomic64_add_return(i, v) < 0)
-
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 
 static inline int atomic_xchg(atomic_t *v, int new)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 616327ac9d39..73bda4abe180 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -80,6 +80,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_sub_and_test arch_atomic_sub_and_test
 static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
@@ -117,6 +118,7 @@ static __always_inline void arch_atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic_dec_and_test arch_atomic_dec_and_test
 static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
@@ -130,6 +132,7 @@ static __always_inline bool arch_atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic_inc_and_test arch_atomic_inc_and_test
 static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
@@ -144,6 +147,7 @@ static __always_inline bool arch_atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic_add_negative arch_atomic_add_negative
 static __always_inline bool arch_atomic_add_negative(int i, atomic_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 2a33cc17801b..a26810d005e0 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -197,20 +197,6 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
 	return i;
 }
 
-/**
- * arch_atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer to type atomic64_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_sub_and_test(long long i, atomic64_t *v)
-{
-	return arch_atomic64_sub_return(i, v) == 0;
-}
-
 /**
  * arch_atomic64_inc - increment atomic64 variable
  * @v: pointer to type atomic64_t
@@ -235,46 +221,6 @@ static inline void arch_atomic64_dec(atomic64_t *v)
 			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
 
-/**
- * arch_atomic64_dec_and_test - decrement and test
- * @v: pointer to type atomic64_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-static inline int arch_atomic64_dec_and_test(atomic64_t *v)
-{
-	return arch_atomic64_dec_return(v) == 0;
-}
-
-/**
- * atomic64_inc_and_test - increment and test
- * @v: pointer to type atomic64_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-static inline int arch_atomic64_inc_and_test(atomic64_t *v)
-{
-	return arch_atomic64_inc_return(v) == 0;
-}
-
-/**
- * arch_atomic64_add_negative - add and test if negative
- * @i: integer value to add
- * @v: pointer to type atomic64_t
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-static inline int arch_atomic64_add_negative(long long i, atomic64_t *v)
-{
-	return arch_atomic64_add_return(i, v) < 0;
-}
-
 /**
  * arch_atomic64_add_unless - add unless the number is a given value
  * @v: pointer of type atomic64_t
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 7e04b294e6eb..6a65228a3db6 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -71,6 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
 static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
@@ -110,6 +111,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
+#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
 static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
@@ -123,6 +125,7 @@ static inline bool arch_atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
+#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
 static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
 {
 	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
@@ -137,6 +140,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
+#define arch_atomic64_add_negative arch_atomic64_add_negative
 static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
 {
 	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index f4c9f82c40c6..332ae4eca737 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -197,17 +197,6 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
- *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_sub_and_test(i,v) (atomic_sub_return((i),(v)) == 0)
-
 /**
  * atomic_inc - increment atomic variable
  * @v: pointer of type atomic_t
@@ -240,37 +229,6 @@ ATOMIC_OPS(xor)
  */
 #define atomic_dec_return(v) atomic_sub_return(1,(v))
 
-/**
- * atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
- */
-#define atomic_dec_and_test(v) (atomic_sub_return(1,(v)) == 0)
-
-/**
- * atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
- */
-#define atomic_inc_and_test(v) (atomic_add_return(1,(v)) == 0)
-
-/**
- * atomic_add_negative - add and test if negative
- * @v: pointer of type atomic_t
- * @i: integer value to add
- *
- * Atomically adds @i to @v and returns true
- * if the result is negative, or false when
- * result is greater than or equal to zero.
- */
-#define atomic_add_negative(i,v) (atomic_add_return((i),(v)) < 0)
-
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 2b487f28ef35..6b64c200de73 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -225,29 +225,41 @@ static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
 	return arch_atomic64_dec_if_positive(v);
 }
 
+#ifdef arch_atomic_dec_and_test
+#define atomic_dec_and_test atomic_dec_and_test
 static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_and_test
+#define atomic64_dec_and_test atomic64_dec_and_test
 static __always_inline bool atomic64_dec_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic_inc_and_test
+#define atomic_inc_and_test atomic_inc_and_test
 static __always_inline bool atomic_inc_and_test(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_and_test(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc_and_test
+#define atomic64_inc_and_test atomic64_inc_and_test
 static __always_inline bool atomic64_inc_and_test(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_and_test(v);
 }
+#endif
 
 static __always_inline int atomic_add_return(int i, atomic_t *v)
 {
@@ -333,29 +345,41 @@ static __always_inline s64 atomic64_fetch_xor(s64 i, atomic64_t *v)
 	return arch_atomic64_fetch_xor(i, v);
 }
 
+#ifdef arch_atomic_sub_and_test
+#define atomic_sub_and_test atomic_sub_and_test
 static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_sub_and_test
+#define atomic64_sub_and_test atomic64_sub_and_test
 static __always_inline bool atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_sub_and_test(i, v);
 }
+#endif
 
+#ifdef arch_atomic_add_negative
+#define atomic_add_negative atomic_add_negative
 static __always_inline bool atomic_add_negative(int i, atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_add_negative(i, v);
 }
+#endif
 
+#ifdef arch_atomic64_add_negative
+#define atomic64_add_negative atomic64_add_negative
 static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_add_negative(i, v);
 }
+#endif
 
 static __always_inline unsigned long
 cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size)
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 757e45821220..40cab858aaaa 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -186,11 +186,6 @@ ATOMIC_OP(xor, ^)
 
 #include <linux/irqflags.h>
 
-static inline int atomic_add_negative(int i, atomic_t *v)
-{
-	return atomic_add_return(i, v) < 0;
-}
-
 static inline void atomic_add(int i, atomic_t *v)
 {
 	atomic_add_return(i, v);
@@ -214,10 +209,6 @@ static inline void atomic_dec(atomic_t *v)
 #define atomic_dec_return(v)		atomic_sub_return(1, (v))
 #define atomic_inc_return(v)		atomic_add_return(1, (v))
 
-#define atomic_sub_and_test(i, v)	(atomic_sub_return((i), (v)) == 0)
-#define atomic_dec_and_test(v)		(atomic_dec_return(v) == 0)
-#define atomic_inc_and_test(v)		(atomic_inc_return(v) == 0)
-
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 49460107b29a..d3827ab97aa4 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -56,13 +56,9 @@ extern long long atomic64_xchg(atomic64_t *v, long long new);
 extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
-#define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_inc_and_test(v) 	(atomic64_inc_return(v) == 0)
-#define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-#define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 530562ac7909..3ee8da9023cd 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -569,6 +569,68 @@ static inline bool atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic_inc_not_zero(v)		atomic_add_unless((v), 1, 0)
 #endif
 
+/**
+ * atomic_inc_and_test - increment and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_inc_and_test
+static inline bool atomic_inc_and_test(atomic_t *v)
+{
+	return atomic_inc_return(v) == 0;
+}
+#endif
+
+/**
+ * atomic_dec_and_test - decrement and test
+ * @v: pointer of type atomic_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic_dec_and_test
+static inline bool atomic_dec_and_test(atomic_t *v)
+{
+	return atomic_dec_return(v) == 0;
+}
+#endif
+
+/**
+ * atomic_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic_sub_and_test
+static inline bool atomic_sub_and_test(int i, atomic_t *v)
+{
+	return atomic_sub_return(i, v) == 0;
+}
+#endif
+
+/**
+ * atomic_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#ifndef atomic_add_negative
+static inline bool atomic_add_negative(int i, atomic_t *v)
+{
+	return atomic_add_return(i, v) < 0;
+}
+#endif
+
 #ifndef atomic_andnot
 static inline void atomic_andnot(int i, atomic_t *v)
 {
@@ -1091,6 +1153,68 @@ static inline bool atomic64_add_unless(atomic64_t *v, long long a, long long u)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 #endif
 
+/**
+ * atomic64_inc_and_test - increment and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically increments @v by 1
+ * and returns true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_inc_and_test
+static inline bool atomic64_inc_and_test(atomic64_t *v)
+{
+	return atomic64_inc_return(v) == 0;
+}
+#endif
+
+/**
+ * atomic64_dec_and_test - decrement and test
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically decrements @v by 1 and
+ * returns true if the result is 0, or false for all other
+ * cases.
+ */
+#ifndef atomic64_dec_and_test
+static inline bool atomic64_dec_and_test(atomic64_t *v)
+{
+	return atomic64_dec_return(v) == 0;
+}
+#endif
+
+/**
+ * atomic64_sub_and_test - subtract value from variable and test result
+ * @i: integer value to subtract
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically subtracts @i from @v and returns
+ * true if the result is zero, or false for all
+ * other cases.
+ */
+#ifndef atomic64_sub_and_test
+static inline bool atomic64_sub_and_test(long long i, atomic64_t *v)
+{
+	return atomic64_sub_return(i, v) == 0;
+}
+#endif
+
+/**
+ * atomic64_add_negative - add and test if negative
+ * @i: integer value to add
+ * @v: pointer of type atomic64_t
+ *
+ * Atomically adds @i to @v and returns true
+ * if the result is negative, or false when
+ * result is greater than or equal to zero.
+ */
+#ifndef atomic64_add_negative
+static inline bool atomic64_add_negative(long long i, atomic64_t *v)
+{
+	return atomic64_add_return(i, v) < 0;
+}
+#endif
+
 #ifndef atomic64_andnot
 static inline void atomic64_andnot(long long i, atomic64_t *v)
 {
-- 
cgit v1.2.3


From 9837559d8eb01ce834e56fc9a567c1d94ebd3698 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:19 +0100
Subject: atomics/treewide: Make unconditional inc/dec ops optional

Many of the inc/dec ops are mandatory, but for most architectures inc/dec are
simply trivial wrappers around their corresponding add/sub ops.

Let's make all the inc/dec ops optional, so that we can get rid of these
boilerplate wrappers.

The instrumented atomics are updated accordingly.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Palmer Dabbelt <palmer@sifive.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-17-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h           | 12 -----
 arch/arc/include/asm/atomic.h             | 11 -----
 arch/arm/include/asm/atomic.h             | 11 -----
 arch/arm64/include/asm/atomic.h           | 24 ----------
 arch/h8300/include/asm/atomic.h           |  7 ---
 arch/hexagon/include/asm/atomic.h         |  6 ---
 arch/ia64/include/asm/atomic.h            |  9 ----
 arch/m68k/include/asm/atomic.h            |  5 +-
 arch/mips/include/asm/atomic.h            | 38 ----------------
 arch/parisc/include/asm/atomic.h          | 12 -----
 arch/powerpc/include/asm/atomic.h         |  4 ++
 arch/riscv/include/asm/atomic.h           | 76 -------------------------------
 arch/s390/include/asm/atomic.h            |  8 ----
 arch/sh/include/asm/atomic.h              |  6 ---
 arch/sparc/include/asm/atomic_32.h        |  5 --
 arch/sparc/include/asm/atomic_64.h        | 12 -----
 arch/x86/include/asm/atomic.h             |  5 +-
 arch/x86/include/asm/atomic64_32.h        |  4 ++
 arch/x86/include/asm/atomic64_64.h        |  5 +-
 arch/xtensa/include/asm/atomic.h          | 32 -------------
 include/asm-generic/atomic-instrumented.h | 24 ++++++++++
 include/asm-generic/atomic.h              | 13 ------
 include/asm-generic/atomic64.h            |  5 --
 include/linux/atomic.h                    | 48 +++++++++++++++++++
 24 files changed, 86 insertions(+), 296 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 25f8693c5a42..f6410cb68058 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -297,16 +297,4 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return old - 1;
 }
 
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-#define atomic64_dec_return(v) atomic64_sub_return(1,(v))
-
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-#define atomic64_inc_return(v) atomic64_add_return(1,(v))
-
-#define atomic_inc(v) atomic_add(1,(v))
-#define atomic64_inc(v) atomic64_add(1,(v))
-
-#define atomic_dec(v) atomic_sub(1,(v))
-#define atomic64_dec(v) atomic64_sub(1,(v))
-
 #endif /* _ALPHA_ATOMIC_H */
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 4222e726f84c..27b95a928c1e 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -308,12 +308,6 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_inc(v)			atomic_add(1, v)
-#define atomic_dec(v)			atomic_sub(1, v)
-
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-
 #ifdef CONFIG_GENERIC_ATOMIC64
 
 #include <asm-generic/atomic64.h>
@@ -560,11 +554,6 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
 }
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-
 #endif	/* !CONFIG_GENERIC_ATOMIC64 */
 
 #endif	/* !__ASSEMBLY__ */
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 35fb7f504daa..5a58d061d3d2 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -245,12 +245,6 @@ ATOMIC_OPS(xor, ^=, eor)
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
-#define atomic_inc(v)		atomic_add(1, v)
-#define atomic_dec(v)		atomic_sub(1, v)
-
-#define atomic_inc_return_relaxed(v)    (atomic_add_return_relaxed(1, v))
-#define atomic_dec_return_relaxed(v)    (atomic_sub_return_relaxed(1, v))
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
 	long long counter;
@@ -512,11 +506,6 @@ static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
 }
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1LL, (v))
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1LL, (v))
-
 #endif /* !CONFIG_GENERIC_ATOMIC64 */
 #endif
 #endif
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index edbe53fa3106..078f785cd97f 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -50,21 +50,11 @@
 #define atomic_add_return_release	atomic_add_return_release
 #define atomic_add_return		atomic_add_return
 
-#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
-#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
-#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
 #define atomic_sub_return_relaxed	atomic_sub_return_relaxed
 #define atomic_sub_return_acquire	atomic_sub_return_acquire
 #define atomic_sub_return_release	atomic_sub_return_release
 #define atomic_sub_return		atomic_sub_return
 
-#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
-#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
-#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-
 #define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
 #define atomic_fetch_add_acquire	atomic_fetch_add_acquire
 #define atomic_fetch_add_release	atomic_fetch_add_release
@@ -108,8 +98,6 @@
 	cmpxchg_release(&((v)->counter), (old), (new))
 #define atomic_cmpxchg(v, old, new)	cmpxchg(&((v)->counter), (old), (new))
 
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
 #define atomic_andnot			atomic_andnot
 
 /*
@@ -124,21 +112,11 @@
 #define atomic64_add_return_release	atomic64_add_return_release
 #define atomic64_add_return		atomic64_add_return
 
-#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
-#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
-#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
 #define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
 #define atomic64_sub_return_acquire	atomic64_sub_return_acquire
 #define atomic64_sub_return_release	atomic64_sub_return_release
 #define atomic64_sub_return		atomic64_sub_return
 
-#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
-#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
-#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-
 #define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
 #define atomic64_fetch_add_acquire	atomic64_fetch_add_acquire
 #define atomic64_fetch_add_release	atomic64_fetch_add_release
@@ -179,8 +157,6 @@
 #define atomic64_cmpxchg_release	atomic_cmpxchg_release
 #define atomic64_cmpxchg		atomic_cmpxchg
 
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
 #define atomic64_andnot			atomic64_andnot
 
 #endif
diff --git a/arch/h8300/include/asm/atomic.h b/arch/h8300/include/asm/atomic.h
index 8977b5157c8f..c6b6a06231b2 100644
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@@ -69,13 +69,6 @@ ATOMIC_OPS(sub, -=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_inc_return(v)		atomic_add_return(1, v)
-#define atomic_dec_return(v)		atomic_sub_return(1, v)
-
-#define atomic_inc(v)			(void)atomic_inc_return(v)
-
-#define atomic_dec(v)			(void)atomic_dec_return(v)
-
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 31638f511674..311b9894ccc8 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -198,10 +198,4 @@ static inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 }
 #define atomic_fetch_add_unless atomic_fetch_add_unless
 
-#define atomic_inc(v) atomic_add(1, (v))
-#define atomic_dec(v) atomic_sub(1, (v))
-
-#define atomic_inc_return(v) (atomic_add_return(1, v))
-#define atomic_dec_return(v) (atomic_sub_return(1, v))
-
 #endif
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index e4143c462e65..46a15a974bed 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -231,19 +231,10 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
-
 #define atomic_add(i,v)			(void)atomic_add_return((i), (v))
 #define atomic_sub(i,v)			(void)atomic_sub_return((i), (v))
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
 
 #define atomic64_add(i,v)		(void)atomic64_add_return((i), (v))
 #define atomic64_sub(i,v)		(void)atomic64_sub_return((i), (v))
-#define atomic64_inc(v)			atomic64_add(1, (v))
-#define atomic64_dec(v)			atomic64_sub(1, (v))
 
 #endif /* _ASM_IA64_ATOMIC_H */
diff --git a/arch/m68k/include/asm/atomic.h b/arch/m68k/include/asm/atomic.h
index 9df09c876fa2..47228b0d4163 100644
--- a/arch/m68k/include/asm/atomic.h
+++ b/arch/m68k/include/asm/atomic.h
@@ -126,11 +126,13 @@ static inline void atomic_inc(atomic_t *v)
 {
 	__asm__ __volatile__("addql #1,%0" : "+m" (*v));
 }
+#define atomic_inc atomic_inc
 
 static inline void atomic_dec(atomic_t *v)
 {
 	__asm__ __volatile__("subql #1,%0" : "+m" (*v));
 }
+#define atomic_dec atomic_dec
 
 static inline int atomic_dec_and_test(atomic_t *v)
 {
@@ -192,9 +194,6 @@ static inline int atomic_xchg(atomic_t *v, int new)
 
 #endif /* !CONFIG_RMW_INSNS */
 
-#define atomic_dec_return(v)	atomic_sub_return(1, (v))
-#define atomic_inc_return(v)	atomic_add_return(1, (v))
-
 static inline int atomic_sub_and_test(int i, atomic_t *v)
 {
 	char c;
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index fd3008ae164c..79be687de4ab 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -274,31 +274,12 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-#define atomic_dec_return(v) atomic_sub_return(1, (v))
-#define atomic_inc_return(v) atomic_add_return(1, (v))
-
 /*
  * atomic_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic_t
  */
 #define atomic_dec_if_positive(v)	atomic_sub_if_positive(1, v)
 
-/*
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1, (v))
-
-/*
- * atomic_dec - decrement and test
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1, (v))
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i)    { (i) }
@@ -554,31 +535,12 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), (new)))
 
-#define atomic64_dec_return(v) atomic64_sub_return(1, (v))
-#define atomic64_inc_return(v) atomic64_add_return(1, (v))
-
 /*
  * atomic64_dec_if_positive - decrement by 1 if old value positive
  * @v: pointer of type atomic64_t
  */
 #define atomic64_dec_if_positive(v)	atomic64_sub_if_positive(1, v)
 
-/*
- * atomic64_inc - increment atomic variable
- * @v: pointer of type atomic64_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic64_inc(v) atomic64_add(1, (v))
-
-/*
- * atomic64_dec - decrement and test
- * @v: pointer of type atomic64_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic64_dec(v) atomic64_sub(1, (v))
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_ATOMIC_H */
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index f85844ff6336..10bc490327c1 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -136,12 +136,6 @@ ATOMIC_OPS(xor, ^=)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_inc(v)	(atomic_add(   1,(v)))
-#define atomic_dec(v)	(atomic_add(  -1,(v)))
-
-#define atomic_inc_return(v)	(atomic_add_return(   1,(v)))
-#define atomic_dec_return(v)	(atomic_add_return(  -1,(v)))
-
 #define ATOMIC_INIT(i)	{ (i) }
 
 #ifdef CONFIG_64BIT
@@ -224,12 +218,6 @@ atomic64_read(const atomic64_t *v)
 	return READ_ONCE((v)->counter);
 }
 
-#define atomic64_inc(v)		(atomic64_add(   1,(v)))
-#define atomic64_dec(v)		(atomic64_add(  -1,(v)))
-
-#define atomic64_inc_return(v)		(atomic64_add_return(   1,(v)))
-#define atomic64_dec_return(v)		(atomic64_add_return(  -1,(v)))
-
 /* exported interface */
 #define atomic64_cmpxchg(v, o, n) \
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 5d76f05d2be3..ebaefdee4a57 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -143,6 +143,7 @@ static __inline__ void atomic_inc(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_inc atomic_inc
 
 static __inline__ int atomic_inc_return_relaxed(atomic_t *v)
 {
@@ -175,6 +176,7 @@ static __inline__ void atomic_dec(atomic_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic_dec atomic_dec
 
 static __inline__ int atomic_dec_return_relaxed(atomic_t *v)
 {
@@ -411,6 +413,7 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_inc atomic64_inc
 
 static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 {
@@ -441,6 +444,7 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 	: "r" (&v->counter)
 	: "cc", "xer");
 }
+#define atomic64_dec atomic64_dec
 
 static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
 {
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 68eef0a805ca..512b89485790 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -209,82 +209,6 @@ ATOMIC_OPS(xor, xor, i)
 #undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 
-#define ATOMIC_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-void atomic##prefix##_##op(atomic##prefix##_t *v)			\
-{									\
-	atomic##prefix##_##func_op(I, v);				\
-}
-
-#define ATOMIC_FETCH_OP(op, func_op, I, c_type, prefix)			\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op##_relaxed(atomic##prefix##_t *v)	\
-{									\
-	return atomic##prefix##_fetch_##func_op##_relaxed(I, v);	\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_fetch_##op(atomic##prefix##_t *v)		\
-{									\
-	return atomic##prefix##_fetch_##func_op(I, v);			\
-}
-
-#define ATOMIC_OP_RETURN(op, asm_op, c_op, I, c_type, prefix)		\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return_relaxed(atomic##prefix##_t *v)	\
-{									\
-        return atomic##prefix##_fetch_##op##_relaxed(v) c_op I;		\
-}									\
-static __always_inline							\
-c_type atomic##prefix##_##op##_return(atomic##prefix##_t *v)		\
-{									\
-        return atomic##prefix##_fetch_##op(v) c_op I;			\
-}
-
-#ifdef CONFIG_GENERIC_ATOMIC64
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )
-#else
-#define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_OP(       op, asm_op,       I,  int,   )			\
-        ATOMIC_FETCH_OP( op, asm_op,       I,  int,   )			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I,  int,   )			\
-        ATOMIC_OP(       op, asm_op,       I, long, 64)			\
-        ATOMIC_FETCH_OP( op, asm_op,       I, long, 64)			\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, long, 64)
-#endif
-
-ATOMIC_OPS(inc, add, +,  1)
-ATOMIC_OPS(dec, add, +, -1)
-
-#define atomic_inc_return_relaxed	atomic_inc_return_relaxed
-#define atomic_dec_return_relaxed	atomic_dec_return_relaxed
-#define atomic_inc_return		atomic_inc_return
-#define atomic_dec_return		atomic_dec_return
-
-#define atomic_fetch_inc_relaxed	atomic_fetch_inc_relaxed
-#define atomic_fetch_dec_relaxed	atomic_fetch_dec_relaxed
-#define atomic_fetch_inc		atomic_fetch_inc
-#define atomic_fetch_dec		atomic_fetch_dec
-
-#ifndef CONFIG_GENERIC_ATOMIC64
-#define atomic64_inc_return_relaxed	atomic64_inc_return_relaxed
-#define atomic64_dec_return_relaxed	atomic64_dec_return_relaxed
-#define atomic64_inc_return		atomic64_inc_return
-#define atomic64_dec_return		atomic64_dec_return
-
-#define atomic64_fetch_inc_relaxed	atomic64_fetch_inc_relaxed
-#define atomic64_fetch_dec_relaxed	atomic64_fetch_dec_relaxed
-#define atomic64_fetch_inc		atomic64_fetch_inc
-#define atomic64_fetch_dec		atomic64_fetch_dec
-#endif
-
-#undef ATOMIC_OPS
-#undef ATOMIC_OP
-#undef ATOMIC_FETCH_OP
-#undef ATOMIC_OP_RETURN
-
 /* This is required to provide a full barrier on success. */
 static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 7f5fbd595f01..376e64af951f 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -55,13 +55,9 @@ static inline void atomic_add(int i, atomic_t *v)
 	__atomic_add(i, &v->counter);
 }
 
-#define atomic_inc(_v)			atomic_add(1, _v)
-#define atomic_inc_return(_v)		atomic_add_return(1, _v)
 #define atomic_sub(_i, _v)		atomic_add(-(int)(_i), _v)
 #define atomic_sub_return(_i, _v)	atomic_add_return(-(int)(_i), _v)
 #define atomic_fetch_sub(_i, _v)	atomic_fetch_add(-(int)(_i), _v)
-#define atomic_dec(_v)			atomic_sub(1, _v)
-#define atomic_dec_return(_v)		atomic_sub_return(1, _v)
 
 #define ATOMIC_OPS(op)							\
 static inline void atomic_##op(int i, atomic_t *v)			\
@@ -166,12 +162,8 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	return dec;
 }
 
-#define atomic64_inc(_v)		atomic64_add(1, _v)
-#define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
 #define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
-#define atomic64_dec(_v)		atomic64_sub(1, _v)
-#define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
 
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/sh/include/asm/atomic.h b/arch/sh/include/asm/atomic.h
index d438494fa112..f37b95a80232 100644
--- a/arch/sh/include/asm/atomic.h
+++ b/arch/sh/include/asm/atomic.h
@@ -32,12 +32,6 @@
 #include <asm/atomic-irq.h>
 #endif
 
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
-#define atomic_inc(v)			atomic_add(1, (v))
-#define atomic_dec(v)			atomic_sub(1, (v))
-
 #define atomic_xchg(v, new)		(xchg(&((v)->counter), new))
 #define atomic_cmpxchg(v, o, n)		(cmpxchg(&((v)->counter), (o), (n)))
 
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index 3a26573790c6..94c930f0bc62 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -38,8 +38,6 @@ void atomic_set(atomic_t *, int);
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
 #define atomic_sub(i, v)	((void)atomic_add_return(-(int)(i), (v)))
-#define atomic_inc(v)		((void)atomic_add_return(        1, (v)))
-#define atomic_dec(v)		((void)atomic_add_return(       -1, (v)))
 
 #define atomic_and(i, v)	((void)atomic_fetch_and((i), (v)))
 #define atomic_or(i, v)		((void)atomic_fetch_or((i), (v)))
@@ -48,7 +46,4 @@ void atomic_set(atomic_t *, int);
 #define atomic_sub_return(i, v)	(atomic_add_return(-(int)(i), (v)))
 #define atomic_fetch_sub(i, v)  (atomic_fetch_add (-(int)(i), (v)))
 
-#define atomic_inc_return(v)	(atomic_add_return(        1, (v)))
-#define atomic_dec_return(v)	(atomic_add_return(       -1, (v)))
-
 #endif /* !(__ARCH_SPARC_ATOMIC__) */
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 634508282aea..304865c7cdbb 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -50,18 +50,6 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-#define atomic_dec_return(v)   atomic_sub_return(1, v)
-#define atomic64_dec_return(v) atomic64_sub_return(1, v)
-
-#define atomic_inc_return(v)   atomic_add_return(1, v)
-#define atomic64_inc_return(v) atomic64_add_return(1, v)
-
-#define atomic_inc(v) atomic_add(1, v)
-#define atomic64_inc(v) atomic64_add(1, v)
-
-#define atomic_dec(v) atomic_sub(1, v)
-#define atomic64_dec(v) atomic64_sub(1, v)
-
 #define atomic_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 
 static inline int atomic_xchg(atomic_t *v, int new)
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 73bda4abe180..823fd2f320cf 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -92,6 +92,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic_inc arch_atomic_inc
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
@@ -104,6 +105,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic_dec arch_atomic_dec
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
@@ -177,9 +179,6 @@ static __always_inline int arch_atomic_sub_return(int i, atomic_t *v)
 	return arch_atomic_add_return(-i, v);
 }
 
-#define arch_atomic_inc_return(v)  (arch_atomic_add_return(1, v))
-#define arch_atomic_dec_return(v)  (arch_atomic_sub_return(1, v))
-
 static __always_inline int arch_atomic_fetch_add(int i, atomic_t *v)
 {
 	return xadd(&v->counter, i);
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a26810d005e0..472c7af0ed48 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -158,6 +158,7 @@ static inline long long arch_atomic64_inc_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_inc_return arch_atomic64_inc_return
 
 static inline long long arch_atomic64_dec_return(atomic64_t *v)
 {
@@ -166,6 +167,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v)
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
+#define arch_atomic64_dec_return arch_atomic64_dec_return
 
 /**
  * arch_atomic64_add - add integer to atomic64 variable
@@ -203,6 +205,7 @@ static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static inline void arch_atomic64_inc(atomic64_t *v)
 {
 	__alternative_atomic64(inc, inc_return, /* no output */,
@@ -215,6 +218,7 @@ static inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static inline void arch_atomic64_dec(atomic64_t *v)
 {
 	__alternative_atomic64(dec, dec_return, /* no output */,
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 6a65228a3db6..1b282272a801 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -83,6 +83,7 @@ static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
  *
  * Atomically increments @v by 1.
  */
+#define arch_atomic64_inc arch_atomic64_inc
 static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
@@ -96,6 +97,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
  *
  * Atomically decrements @v by 1.
  */
+#define arch_atomic64_dec arch_atomic64_dec
 static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
@@ -173,9 +175,6 @@ static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v)
 	return xadd(&v->counter, -i);
 }
 
-#define arch_atomic64_inc_return(v)  (arch_atomic64_add_return(1, (v)))
-#define arch_atomic64_dec_return(v)  (arch_atomic64_sub_return(1, (v)))
-
 static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
diff --git a/arch/xtensa/include/asm/atomic.h b/arch/xtensa/include/asm/atomic.h
index 332ae4eca737..7de0149e1cf7 100644
--- a/arch/xtensa/include/asm/atomic.h
+++ b/arch/xtensa/include/asm/atomic.h
@@ -197,38 +197,6 @@ ATOMIC_OPS(xor)
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc(v) atomic_add(1,(v))
-
-/**
- * atomic_inc - increment atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically increments @v by 1.
- */
-#define atomic_inc_return(v) atomic_add_return(1,(v))
-
-/**
- * atomic_dec - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec(v) atomic_sub(1,(v))
-
-/**
- * atomic_dec_return - decrement atomic variable
- * @v: pointer of type atomic_t
- *
- * Atomically decrements @v by 1.
- */
-#define atomic_dec_return(v) atomic_sub_return(1,(v))
-
 #define atomic_cmpxchg(v, o, n) ((int)cmpxchg(&((v)->counter), (o), (n)))
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 6b64c200de73..12f9634750d7 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -102,29 +102,41 @@ static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u
 }
 #endif
 
+#ifdef arch_atomic_inc
+#define atomic_inc atomic_inc
 static __always_inline void atomic_inc(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_inc(v);
 }
+#endif
 
+#ifdef arch_atomic64_inc
+#define atomic64_inc atomic64_inc
 static __always_inline void atomic64_inc(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_inc(v);
 }
+#endif
 
+#ifdef arch_atomic_dec
+#define atomic_dec atomic_dec
 static __always_inline void atomic_dec(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic_dec(v);
 }
+#endif
 
+#ifdef atch_atomic64_dec
+#define atomic64_dec
 static __always_inline void atomic64_dec(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	arch_atomic64_dec(v);
 }
+#endif
 
 static __always_inline void atomic_add(int i, atomic_t *v)
 {
@@ -186,29 +198,41 @@ static __always_inline void atomic64_xor(s64 i, atomic64_t *v)
 	arch_atomic64_xor(i, v);
 }
 
+#ifdef arch_atomic_inc_return
+#define atomic_inc_return atomic_inc_return
 static __always_inline int atomic_inc_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_in_return
+#define atomic64_inc_return atomic64_inc_return
 static __always_inline s64 atomic64_inc_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_inc_return(v);
 }
+#endif
 
+#ifdef arch_atomic_dec_return
+#define atomic_dec_return atomic_dec_return
 static __always_inline int atomic_dec_return(atomic_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic_dec_return(v);
 }
+#endif
 
+#ifdef arch_atomic64_dec_return
+#define atomic64_dec_return atomic64_dec_return
 static __always_inline s64 atomic64_dec_return(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_return(v);
 }
+#endif
 
 #ifdef arch_atomic64_inc_not_zero
 #define atomic64_inc_not_zero atomic64_inc_not_zero
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 40cab858aaaa..13324aa828eb 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -196,19 +196,6 @@ static inline void atomic_sub(int i, atomic_t *v)
 	atomic_sub_return(i, v);
 }
 
-static inline void atomic_inc(atomic_t *v)
-{
-	atomic_add_return(1, v);
-}
-
-static inline void atomic_dec(atomic_t *v)
-{
-	atomic_sub_return(1, v);
-}
-
-#define atomic_dec_return(v)		atomic_sub_return(1, (v))
-#define atomic_inc_return(v)		atomic_add_return(1, (v))
-
 #define atomic_xchg(ptr, v)		(xchg(&(ptr)->counter, (v)))
 #define atomic_cmpxchg(v, old, new)	(cmpxchg(&((v)->counter), (old), (new)))
 
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index d3827ab97aa4..242b79ae0b57 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -56,9 +56,4 @@ extern long long atomic64_xchg(atomic64_t *v, long long new);
 extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
-#define atomic64_inc(v)			atomic64_add(1LL, (v))
-#define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
-#define atomic64_dec(v)			atomic64_sub(1LL, (v))
-#define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
-
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 3ee8da9023cd..24f345df7ba6 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -97,11 +97,23 @@
 #endif
 #endif /* atomic_add_return_relaxed */
 
+#ifndef atomic_inc
+#define atomic_inc(v)			atomic_add(1, (v))
+#endif
+
 /* atomic_inc_return_relaxed */
 #ifndef atomic_inc_return_relaxed
+
+#ifndef atomic_inc_return
+#define atomic_inc_return(v)		atomic_add_return(1, (v))
+#define atomic_inc_return_relaxed(v)	atomic_add_return_relaxed(1, (v))
+#define atomic_inc_return_acquire(v)	atomic_add_return_acquire(1, (v))
+#define atomic_inc_return_release(v)	atomic_add_return_release(1, (v))
+#else /* atomic_inc_return */
 #define  atomic_inc_return_relaxed	atomic_inc_return
 #define  atomic_inc_return_acquire	atomic_inc_return
 #define  atomic_inc_return_release	atomic_inc_return
+#endif /* atomic_inc_return */
 
 #else /* atomic_inc_return_relaxed */
 
@@ -145,11 +157,23 @@
 #endif
 #endif /* atomic_sub_return_relaxed */
 
+#ifndef atomic_dec
+#define atomic_dec(v)			atomic_sub(1, (v))
+#endif
+
 /* atomic_dec_return_relaxed */
 #ifndef atomic_dec_return_relaxed
+
+#ifndef atomic_dec_return
+#define atomic_dec_return(v)		atomic_sub_return(1, (v))
+#define atomic_dec_return_relaxed(v)	atomic_sub_return_relaxed(1, (v))
+#define atomic_dec_return_acquire(v)	atomic_sub_return_acquire(1, (v))
+#define atomic_dec_return_release(v)	atomic_sub_return_release(1, (v))
+#else /* atomic_dec_return */
 #define  atomic_dec_return_relaxed	atomic_dec_return
 #define  atomic_dec_return_acquire	atomic_dec_return
 #define  atomic_dec_return_release	atomic_dec_return
+#endif /* atomic_dec_return */
 
 #else /* atomic_dec_return_relaxed */
 
@@ -748,11 +772,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_add_return_relaxed */
 
+#ifndef atomic64_inc
+#define atomic64_inc(v)			atomic64_add(1, (v))
+#endif
+
 /* atomic64_inc_return_relaxed */
 #ifndef atomic64_inc_return_relaxed
+
+#ifndef atomic64_inc_return
+#define atomic64_inc_return(v)		atomic64_add_return(1, (v))
+#define atomic64_inc_return_relaxed(v)	atomic64_add_return_relaxed(1, (v))
+#define atomic64_inc_return_acquire(v)	atomic64_add_return_acquire(1, (v))
+#define atomic64_inc_return_release(v)	atomic64_add_return_release(1, (v))
+#else /* atomic64_inc_return */
 #define  atomic64_inc_return_relaxed	atomic64_inc_return
 #define  atomic64_inc_return_acquire	atomic64_inc_return
 #define  atomic64_inc_return_release	atomic64_inc_return
+#endif /* atomic64_inc_return */
 
 #else /* atomic64_inc_return_relaxed */
 
@@ -797,11 +833,23 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_sub_return_relaxed */
 
+#ifndef atomic64_dec
+#define atomic64_dec(v)			atomic64_sub(1, (v))
+#endif
+
 /* atomic64_dec_return_relaxed */
 #ifndef atomic64_dec_return_relaxed
+
+#ifndef atomic64_dec_return
+#define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
+#define atomic64_dec_return_relaxed(v)	atomic64_sub_return_relaxed(1, (v))
+#define atomic64_dec_return_acquire(v)	atomic64_sub_return_acquire(1, (v))
+#define atomic64_dec_return_release(v)	atomic64_sub_return_release(1, (v))
+#else /* atomic64_dec_return */
 #define  atomic64_dec_return_relaxed	atomic64_dec_return
 #define  atomic64_dec_return_acquire	atomic64_dec_return
 #define  atomic64_dec_return_release	atomic64_dec_return
+#endif /* atomic64_dec_return */
 
 #else /* atomic64_dec_return_relaxed */
 
-- 
cgit v1.2.3


From b3a2a05f9111de0b79312e577608a27b0318c0a1 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:20 +0100
Subject: atomics/treewide: Make conditional inc/dec ops optional

The conditional inc/dec ops differ for atomic_t and atomic64_t:

- atomic_inc_unless_positive() is optional for atomic_t, and doesn't exist for atomic64_t.
- atomic_dec_unless_negative() is optional for atomic_t, and doesn't exist for atomic64_t.
- atomic_dec_if_positive is optional for atomic_t, and is mandatory for atomic64_t.

Let's make these consistently optional for both. At the same time, let's
clean up the existing fallbacks to use atomic_try_cmpxchg().

The instrumented atomics are updated accordingly.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-18-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h           |  1 +
 arch/arc/include/asm/atomic.h             |  1 +
 arch/arm/include/asm/atomic.h             |  1 +
 arch/arm64/include/asm/atomic.h           |  2 +
 arch/ia64/include/asm/atomic.h            | 16 -----
 arch/parisc/include/asm/atomic.h          | 23 --------
 arch/powerpc/include/asm/atomic.h         |  1 +
 arch/s390/include/asm/atomic.h            | 17 ------
 arch/sparc/include/asm/atomic_64.h        |  1 +
 arch/x86/include/asm/atomic64_32.h        |  1 +
 arch/x86/include/asm/atomic64_64.h        | 18 ------
 include/asm-generic/atomic-instrumented.h |  3 +
 include/asm-generic/atomic64.h            |  1 +
 include/linux/atomic.h                    | 97 +++++++++++++++++++++++--------
 14 files changed, 85 insertions(+), 98 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index f6410cb68058..4a6a8f58c9c9 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -296,5 +296,6 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 	smp_mb();
 	return old - 1;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* _ALPHA_ATOMIC_H */
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 27b95a928c1e..8f64f3b79b8a 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -517,6 +517,7 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return val;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 /**
  * atomic64_fetch_add_unless - add unless the number is a given value
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 5a58d061d3d2..884c241424fe 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -474,6 +474,7 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 
 	return result;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
 						  long long u)
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 078f785cd97f..9bca54dda75c 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -159,5 +159,7 @@
 
 #define atomic64_andnot			atomic64_andnot
 
+#define atomic64_dec_if_positive	atomic64_dec_if_positive
+
 #endif
 #endif
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 46a15a974bed..206530d0751b 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -215,22 +215,6 @@ ATOMIC64_FETCH_OP(xor, ^)
 	(cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
 #define atomic_add(i,v)			(void)atomic_add_return((i), (v))
 #define atomic_sub(i,v)			(void)atomic_sub_return((i), (v))
 
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 10bc490327c1..118953d41763 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -223,29 +223,6 @@ atomic64_read(const atomic64_t *v)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-/*
- * atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
 #endif /* !CONFIG_64BIT */
 
 
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index ebaefdee4a57..a0156cb43d1f 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -488,6 +488,7 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
 
 	return t;
 }
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #define atomic64_cmpxchg(v, o, n) (cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_cmpxchg_relaxed(v, o, n) \
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index 376e64af951f..fd20ab5d4cf7 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -145,23 +145,6 @@ ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
 
-static inline long atomic64_dec_if_positive(atomic64_t *v)
-{
-	long c, old, dec;
-
-	c = atomic64_read(v);
-	for (;;) {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-		old = atomic64_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
-	return dec;
-}
-
 #define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
 #define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
 #define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 304865c7cdbb..6963482c81d8 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -62,5 +62,6 @@ static inline int atomic_xchg(atomic_t *v, int new)
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
 long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 472c7af0ed48..ef959f02d070 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -254,6 +254,7 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 	return r;
 }
 
+#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 1b282272a801..849f1c566a11 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -191,24 +191,6 @@ static inline long arch_atomic64_xchg(atomic64_t *v, long new)
 	return xchg(&v->counter, new);
 }
 
-/*
- * arch_atomic64_dec_if_positive - decrement by 1 if old value positive
- * @v: pointer of type atomic_t
- *
- * The function returns the old value of *v minus 1, even if
- * the atomic variable, v, was not decremented.
- */
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
-{
-	s64 dec, c = arch_atomic64_read(v);
-	do {
-		dec = c - 1;
-		if (unlikely(dec < 0))
-			break;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, dec));
-	return dec;
-}
-
 static inline void arch_atomic64_and(long i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "andq %1,%0"
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 12f9634750d7..3c64e95d5ed0 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -243,11 +243,14 @@ static __always_inline bool atomic64_inc_not_zero(atomic64_t *v)
 }
 #endif
 
+#ifdef arch_atomic64_dec_if_positive
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 static __always_inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
 	kasan_check_write(v, sizeof(*v));
 	return arch_atomic64_dec_if_positive(v);
 }
+#endif
 
 #ifdef arch_atomic_dec_and_test
 #define atomic_dec_and_test atomic_dec_and_test
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index 242b79ae0b57..97b28b7f1f29 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -51,6 +51,7 @@ ATOMIC64_OPS(xor)
 #undef ATOMIC64_OP
 
 extern long long atomic64_dec_if_positive(atomic64_t *v);
+#define atomic64_dec_if_positive atomic64_dec_if_positive
 extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
 extern long long atomic64_xchg(atomic64_t *v, long long new);
 extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 24f345df7ba6..93fe5b4041e1 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -683,28 +683,30 @@ static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
 #endif
 
 #ifndef atomic_inc_unless_negative
-static inline bool atomic_inc_unless_negative(atomic_t *p)
+static inline bool atomic_inc_unless_negative(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v >= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v + 1);
-		if (likely(v1 == v))
-			return true;
-	}
-	return false;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c + 1));
+
+	return true;
 }
 #endif
 
 #ifndef atomic_dec_unless_positive
-static inline bool atomic_dec_unless_positive(atomic_t *p)
+static inline bool atomic_dec_unless_positive(atomic_t *v)
 {
-	int v, v1;
-	for (v = 0; v <= 0; v = v1) {
-		v1 = atomic_cmpxchg(p, v, v - 1);
-		if (likely(v1 == v))
-			return true;
-	}
-	return false;
+	int c = atomic_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic_try_cmpxchg(v, &c, c - 1));
+
+	return true;
 }
 #endif
 
@@ -718,17 +720,14 @@ static inline bool atomic_dec_unless_positive(atomic_t *p)
 #ifndef atomic_dec_if_positive
 static inline int atomic_dec_if_positive(atomic_t *v)
 {
-	int c, old, dec;
-	c = atomic_read(v);
-	for (;;) {
+	int dec, c = atomic_read(v);
+
+	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-		old = atomic_cmpxchg((v), c, dec);
-		if (likely(old == c))
-			break;
-		c = old;
-	}
+	} while (!atomic_try_cmpxchg(v, &c, dec));
+
 	return dec;
 }
 #endif
@@ -1290,6 +1289,56 @@ static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v
 }
 #endif
 
+#ifndef atomic64_inc_unless_negative
+static inline bool atomic64_inc_unless_negative(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c < 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c + 1));
+
+	return true;
+}
+#endif
+
+#ifndef atomic64_dec_unless_positive
+static inline bool atomic64_dec_unless_positive(atomic64_t *v)
+{
+	long long c = atomic64_read(v);
+
+	do {
+		if (unlikely(c > 0))
+			return false;
+	} while (!atomic64_try_cmpxchg(v, &c, c - 1));
+
+	return true;
+}
+#endif
+
+/*
+ * atomic64_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic64_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic64 variable, v, was not decremented.
+ */
+#ifndef atomic64_dec_if_positive
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
+{
+	long long dec, c = atomic64_read(v);
+
+	do {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+	} while (!atomic64_try_cmpxchg(v, &c, dec));
+
+	return dec;
+}
+#endif
+
 #define atomic64_cond_read_relaxed(v, c)	smp_cond_load_relaxed(&(v)->counter, (c))
 #define atomic64_cond_read_acquire(v, c)	smp_cond_load_acquire(&(v)->counter, (c))
 
-- 
cgit v1.2.3


From 7cc7eaad49c30ac165ecf84d95b26f7e0d53bd97 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 21 Jun 2018 13:13:21 +0100
Subject: atomics/treewide: Clean up '*_andnot()' ifdeffery

The ifdeffery for atomic*_{fetch_,}andnot() is unlike that for all the
other atomics. If atomic*_andnot() is not defined, the corresponding
atomic*_fetch_andnot() is assumed to not be defined.

Additionally, the fallbacks for the various ordering cases are written
much later in atomic.h as static inlines.

This isn't problematic today, but gets in the way of scripting the
generation of atomics. To prepare for scripting, this patch:

* Switches to separate ifdefs for atomic*_andnot() and
  atomic*_fetch_andnot(), updating implementations as appropriate.

* Moves the fallbacks into the standards ifdefs, as macro expansions
  rather than static inlines.

* Removes trivial andnot implementations from architectures, where these
  are superseded by core code.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180621121321.4761-19-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arc/include/asm/atomic.h |  8 ++--
 arch/arm/include/asm/atomic.h |  2 +
 include/linux/atomic.h        | 96 ++++++++++++++-----------------------------
 3 files changed, 36 insertions(+), 70 deletions(-)

diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 8f64f3b79b8a..4e0072730241 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -187,7 +187,8 @@ static inline int atomic_fetch_##op(int i, atomic_t *v)			\
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
-#define atomic_andnot atomic_andnot
+#define atomic_andnot		atomic_andnot
+#define atomic_fetch_andnot	atomic_fetch_andnot
 
 #undef ATOMIC_OPS
 #define ATOMIC_OPS(op, c_op, asm_op)					\
@@ -296,8 +297,6 @@ ATOMIC_OPS(add, +=, CTOP_INST_AADD_DI_R2_R2_R3)
 	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(and, &=, CTOP_INST_AAND_DI_R2_R2_R3)
-#define atomic_andnot(mask, v) atomic_and(~(mask), (v))
-#define atomic_fetch_andnot(mask, v) atomic_fetch_and(~(mask), (v))
 ATOMIC_OPS(or, |=, CTOP_INST_AOR_DI_R2_R2_R3)
 ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
 
@@ -430,7 +429,8 @@ static inline long long atomic64_fetch_##op(long long a, atomic64_t *v)	\
 	ATOMIC64_OP_RETURN(op, op1, op2)				\
 	ATOMIC64_FETCH_OP(op, op1, op2)
 
-#define atomic64_andnot atomic64_andnot
+#define atomic64_andnot		atomic64_andnot
+#define atomic64_fetch_andnot	atomic64_fetch_andnot
 
 ATOMIC64_OPS(add, add.f, adc)
 ATOMIC64_OPS(sub, sub.f, sbc)
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 884c241424fe..f74756641410 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -216,6 +216,8 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
+#define atomic_fetch_andnot		atomic_fetch_andnot
+
 #endif /* __LINUX_ARM_ARCH__ */
 
 #define ATOMIC_OPS(op, c_op, asm_op)					\
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 93fe5b4041e1..8e04f1f69bd9 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -354,12 +354,22 @@
 #endif
 #endif /* atomic_fetch_and_relaxed */
 
-#ifdef atomic_andnot
-/* atomic_fetch_andnot_relaxed */
+#ifndef atomic_andnot
+#define atomic_andnot(i, v)		atomic_and(~(int)(i), (v))
+#endif
+
 #ifndef atomic_fetch_andnot_relaxed
-#define atomic_fetch_andnot_relaxed	atomic_fetch_andnot
-#define atomic_fetch_andnot_acquire	atomic_fetch_andnot
-#define atomic_fetch_andnot_release	atomic_fetch_andnot
+
+#ifndef atomic_fetch_andnot
+#define atomic_fetch_andnot(i, v)		atomic_fetch_and(~(int)(i), (v))
+#define atomic_fetch_andnot_relaxed(i, v)	atomic_fetch_and_relaxed(~(int)(i), (v))
+#define atomic_fetch_andnot_acquire(i, v)	atomic_fetch_and_acquire(~(int)(i), (v))
+#define atomic_fetch_andnot_release(i, v)	atomic_fetch_and_release(~(int)(i), (v))
+#else /* atomic_fetch_andnot */
+#define atomic_fetch_andnot_relaxed		atomic_fetch_andnot
+#define atomic_fetch_andnot_acquire		atomic_fetch_andnot
+#define atomic_fetch_andnot_release		atomic_fetch_andnot
+#endif /* atomic_fetch_andnot */
 
 #else /* atomic_fetch_andnot_relaxed */
 
@@ -378,7 +388,6 @@
 	__atomic_op_fence(atomic_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic_fetch_andnot_relaxed */
-#endif /* atomic_andnot */
 
 /* atomic_fetch_xor_relaxed */
 #ifndef atomic_fetch_xor_relaxed
@@ -655,33 +664,6 @@ static inline bool atomic_add_negative(int i, atomic_t *v)
 }
 #endif
 
-#ifndef atomic_andnot
-static inline void atomic_andnot(int i, atomic_t *v)
-{
-	atomic_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot(int i, atomic_t *v)
-{
-	return atomic_fetch_and(~i, v);
-}
-
-static inline int atomic_fetch_andnot_relaxed(int i, atomic_t *v)
-{
-	return atomic_fetch_and_relaxed(~i, v);
-}
-
-static inline int atomic_fetch_andnot_acquire(int i, atomic_t *v)
-{
-	return atomic_fetch_and_acquire(~i, v);
-}
-
-static inline int atomic_fetch_andnot_release(int i, atomic_t *v)
-{
-	return atomic_fetch_and_release(~i, v);
-}
-#endif
-
 #ifndef atomic_inc_unless_negative
 static inline bool atomic_inc_unless_negative(atomic_t *v)
 {
@@ -1029,12 +1011,22 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 #endif
 #endif /* atomic64_fetch_and_relaxed */
 
-#ifdef atomic64_andnot
-/* atomic64_fetch_andnot_relaxed */
+#ifndef atomic64_andnot
+#define atomic64_andnot(i, v)		atomic64_and(~(long long)(i), (v))
+#endif
+
 #ifndef atomic64_fetch_andnot_relaxed
-#define atomic64_fetch_andnot_relaxed	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_acquire	atomic64_fetch_andnot
-#define atomic64_fetch_andnot_release	atomic64_fetch_andnot
+
+#ifndef atomic64_fetch_andnot
+#define atomic64_fetch_andnot(i, v)		atomic64_fetch_and(~(long long)(i), (v))
+#define atomic64_fetch_andnot_relaxed(i, v)	atomic64_fetch_and_relaxed(~(long long)(i), (v))
+#define atomic64_fetch_andnot_acquire(i, v)	atomic64_fetch_and_acquire(~(long long)(i), (v))
+#define atomic64_fetch_andnot_release(i, v)	atomic64_fetch_and_release(~(long long)(i), (v))
+#else /* atomic64_fetch_andnot */
+#define atomic64_fetch_andnot_relaxed		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_acquire		atomic64_fetch_andnot
+#define atomic64_fetch_andnot_release		atomic64_fetch_andnot
+#endif /* atomic64_fetch_andnot */
 
 #else /* atomic64_fetch_andnot_relaxed */
 
@@ -1053,7 +1045,6 @@ static inline int atomic_dec_if_positive(atomic_t *v)
 	__atomic_op_fence(atomic64_fetch_andnot, __VA_ARGS__)
 #endif
 #endif /* atomic64_fetch_andnot_relaxed */
-#endif /* atomic64_andnot */
 
 /* atomic64_fetch_xor_relaxed */
 #ifndef atomic64_fetch_xor_relaxed
@@ -1262,33 +1253,6 @@ static inline bool atomic64_add_negative(long long i, atomic64_t *v)
 }
 #endif
 
-#ifndef atomic64_andnot
-static inline void atomic64_andnot(long long i, atomic64_t *v)
-{
-	atomic64_and(~i, v);
-}
-
-static inline long long atomic64_fetch_andnot(long long i, atomic64_t *v)
-{
-	return atomic64_fetch_and(~i, v);
-}
-
-static inline long long atomic64_fetch_andnot_relaxed(long long i, atomic64_t *v)
-{
-	return atomic64_fetch_and_relaxed(~i, v);
-}
-
-static inline long long atomic64_fetch_andnot_acquire(long long i, atomic64_t *v)
-{
-	return atomic64_fetch_and_acquire(~i, v);
-}
-
-static inline long long atomic64_fetch_andnot_release(long long i, atomic64_t *v)
-{
-	return atomic64_fetch_and_release(~i, v);
-}
-#endif
-
 #ifndef atomic64_inc_unless_negative
 static inline bool atomic64_inc_unless_negative(atomic64_t *v)
 {
-- 
cgit v1.2.3


From f85c10e24ab9fd8ccb6de3d6061a3110ff3581df Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 13 Jun 2018 08:52:47 -0500
Subject: gfs2: eliminate rs_inum and reduce the size of gfs2 inodes

Before this patch, block reservations kept track of the inode
number. At one point, that was a valid thing to do. However, since
we made the reservation a part of the inode (rather than a pointer
to a separate allocated object) the reservation can determine the
inode number by using container_of. This saves us a little memory
in our inode.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Acked-by: Steven Whitehouse <swhiteho@redhat.com>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/incore.h     | 1 -
 fs/gfs2/rgrp.c       | 5 +++--
 fs/gfs2/trace_gfs2.h | 3 ++-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index d2ad817e089f..e9cd2cc292d3 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -295,7 +295,6 @@ struct gfs2_blkreserv {
 	struct rb_node rs_node;       /* link to other block reservations */
 	struct gfs2_rbm rs_rbm;       /* Start of reservation */
 	u32 rs_free;                  /* how many blocks are still free */
-	u64 rs_inum;                  /* Inode number for reservation */
 };
 
 /*
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 6bc5cfe710d1..7a001f6e8aee 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -607,8 +607,10 @@ int gfs2_rsqa_alloc(struct gfs2_inode *ip)
 
 static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
 {
+	struct gfs2_inode *ip = container_of(rs, struct gfs2_inode, i_res);
+
 	gfs2_print_dbg(seq, "  B: n:%llu s:%llu b:%u f:%u\n",
-		       (unsigned long long)rs->rs_inum,
+		       (unsigned long long)ip->i_no_addr,
 		       (unsigned long long)gfs2_rbm_to_block(&rs->rs_rbm),
 		       rs->rs_rbm.offset, rs->rs_free);
 }
@@ -1528,7 +1530,6 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 	if (ret == 0) {
 		rs->rs_rbm = rbm;
 		rs->rs_free = extlen;
-		rs->rs_inum = ip->i_no_addr;
 		rs_insert(ip);
 	} else {
 		if (goal == rgd->rd_last_alloc + rgd->rd_data0)
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index cb10b95efe0f..e0025258107a 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -606,7 +606,8 @@ TRACE_EVENT(gfs2_rs,
 		__entry->rd_addr	= rs->rs_rbm.rgd->rd_addr;
 		__entry->rd_free_clone	= rs->rs_rbm.rgd->rd_free_clone;
 		__entry->rd_reserved	= rs->rs_rbm.rgd->rd_reserved;
-		__entry->inum		= rs->rs_inum;
+		__entry->inum		= container_of(rs, struct gfs2_inode,
+						       i_res)->i_no_addr;
 		__entry->start		= gfs2_rbm_to_block(&rs->rs_rbm);
 		__entry->free		= rs->rs_free;
 		__entry->func		= func;
-- 
cgit v1.2.3


From 9e1a9ecd13b9bb421c88135b178577caf4d54f6a Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 7 Jun 2018 11:56:46 +0100
Subject: gfs2: Don't withdraw under a spin lock

In two places, the gfs2_io_error_bh macro is called while holding the
sd_ail_lock spin lock.  This isn't allowed because gfs2_io_error_bh
withdraws the filesystem, which can sleep because it issues a uevent.
To fix that, add a gfs2_io_error_bh_wd macro that does withdraw the
filesystem and change gfs2_io_error_bh to not withdraw the filesystem.
In those places where the new gfs2_io_error_bh is used, withdraw the
filesystem after releasing sd_ail_lock.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Reviewed-by: Andrew Price <anprice@redhat.com>
---
 fs/gfs2/log.c     | 26 +++++++++++++++++++-------
 fs/gfs2/lops.c    |  2 +-
 fs/gfs2/meta_io.c |  4 ++--
 fs/gfs2/util.c    | 38 ++++++++++++++++++++------------------
 fs/gfs2/util.h    | 10 +++++++---
 5 files changed, 49 insertions(+), 31 deletions(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 0248835625f1..a767fad02386 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -92,7 +92,8 @@ static void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
 
 static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
 			       struct writeback_control *wbc,
-			       struct gfs2_trans *tr)
+			       struct gfs2_trans *tr,
+			       bool *withdraw)
 __releases(&sdp->sd_ail_lock)
 __acquires(&sdp->sd_ail_lock)
 {
@@ -107,8 +108,10 @@ __acquires(&sdp->sd_ail_lock)
 		gfs2_assert(sdp, bd->bd_tr == tr);
 
 		if (!buffer_busy(bh)) {
-			if (!buffer_uptodate(bh))
+			if (!buffer_uptodate(bh)) {
 				gfs2_io_error_bh(sdp, bh);
+				*withdraw = true;
+			}
 			list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 			continue;
 		}
@@ -148,6 +151,7 @@ void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
 	struct list_head *head = &sdp->sd_ail1_list;
 	struct gfs2_trans *tr;
 	struct blk_plug plug;
+	bool withdraw = false;
 
 	trace_gfs2_ail_flush(sdp, wbc, 1);
 	blk_start_plug(&plug);
@@ -156,11 +160,13 @@ restart:
 	list_for_each_entry_reverse(tr, head, tr_list) {
 		if (wbc->nr_to_write <= 0)
 			break;
-		if (gfs2_ail1_start_one(sdp, wbc, tr))
+		if (gfs2_ail1_start_one(sdp, wbc, tr, &withdraw))
 			goto restart;
 	}
 	spin_unlock(&sdp->sd_ail_lock);
 	blk_finish_plug(&plug);
+	if (withdraw)
+		gfs2_lm_withdraw(sdp, NULL);
 	trace_gfs2_ail_flush(sdp, wbc, 0);
 }
 
@@ -188,7 +194,8 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp)
  *
  */
 
-static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr,
+				bool *withdraw)
 {
 	struct gfs2_bufdata *bd, *s;
 	struct buffer_head *bh;
@@ -199,11 +206,12 @@ static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 		gfs2_assert(sdp, bd->bd_tr == tr);
 		if (buffer_busy(bh))
 			continue;
-		if (!buffer_uptodate(bh))
+		if (!buffer_uptodate(bh)) {
 			gfs2_io_error_bh(sdp, bh);
+			*withdraw = true;
+		}
 		list_move(&bd->bd_ail_st_list, &tr->tr_ail2_list);
 	}
-
 }
 
 /**
@@ -218,10 +226,11 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 	struct gfs2_trans *tr, *s;
 	int oldest_tr = 1;
 	int ret;
+	bool withdraw = false;
 
 	spin_lock(&sdp->sd_ail_lock);
 	list_for_each_entry_safe_reverse(tr, s, &sdp->sd_ail1_list, tr_list) {
-		gfs2_ail1_empty_one(sdp, tr);
+		gfs2_ail1_empty_one(sdp, tr, &withdraw);
 		if (list_empty(&tr->tr_ail1_list) && oldest_tr)
 			list_move(&tr->tr_list, &sdp->sd_ail2_list);
 		else
@@ -230,6 +239,9 @@ static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
 	ret = list_empty(&sdp->sd_ail1_list);
 	spin_unlock(&sdp->sd_ail_lock);
 
+	if (withdraw)
+		gfs2_lm_withdraw(sdp, "fatal: I/O error(s)\n");
+
 	return ret;
 }
 
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index 4d6567990baf..f2567f958d00 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -49,7 +49,7 @@ void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
 	if (test_set_buffer_pinned(bh))
 		gfs2_assert_withdraw(sdp, 0);
 	if (!buffer_uptodate(bh))
-		gfs2_io_error_bh(sdp, bh);
+		gfs2_io_error_bh_wd(sdp, bh);
 	bd = bh->b_private;
 	/* If this buffer is in the AIL and it has already been written
 	 * to in-place disk block, remove it from the AIL.
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 52de1036d9f9..be9c0bf697fe 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -293,7 +293,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
 		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
-			gfs2_io_error_bh(sdp, bh);
+			gfs2_io_error_bh_wd(sdp, bh);
 		brelse(bh);
 		*bhp = NULL;
 		return -EIO;
@@ -320,7 +320,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 	if (!buffer_uptodate(bh)) {
 		struct gfs2_trans *tr = current->journal_info;
 		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
-			gfs2_io_error_bh(sdp, bh);
+			gfs2_io_error_bh_wd(sdp, bh);
 		return -EIO;
 	}
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
index 763d659db91b..59c811de0dc7 100644
--- a/fs/gfs2/util.c
+++ b/fs/gfs2/util.c
@@ -46,14 +46,16 @@ int gfs2_lm_withdraw(struct gfs2_sbd *sdp, const char *fmt, ...)
 	    test_and_set_bit(SDF_SHUTDOWN, &sdp->sd_flags))
 		return 0;
 
-	va_start(args, fmt);
+	if (fmt) {
+		va_start(args, fmt);
 
-	vaf.fmt = fmt;
-	vaf.va = &args;
+		vaf.fmt = fmt;
+		vaf.va = &args;
 
-	fs_err(sdp, "%pV", &vaf);
+		fs_err(sdp, "%pV", &vaf);
 
-	va_end(args);
+		va_end(args);
+	}
 
 	if (sdp->sd_args.ar_errors == GFS2_ERRORS_WITHDRAW) {
 		fs_err(sdp, "about to withdraw this file system\n");
@@ -246,21 +248,21 @@ int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function, char *file,
 }
 
 /**
- * gfs2_io_error_bh_i - Flag a buffer I/O error and withdraw
- * Returns: -1 if this call withdrew the machine,
- *          0 if it was already withdrawn
+ * gfs2_io_error_bh_i - Flag a buffer I/O error
+ * @withdraw: withdraw the filesystem
  */
 
-int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
-		       const char *function, char *file, unsigned int line)
+void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			const char *function, char *file, unsigned int line,
+			bool withdraw)
 {
-	int rv;
-	rv = gfs2_lm_withdraw(sdp,
-			      "fatal: I/O error\n"
-			      "  block = %llu\n"
-			      "  function = %s, file = %s, line = %u\n",
-			      (unsigned long long)bh->b_blocknr,
-			      function, file, line);
-	return rv;
+	fs_err(sdp,
+	       "fatal: I/O error\n"
+	       "  block = %llu\n"
+	       "  function = %s, file = %s, line = %u\n",
+	       (unsigned long long)bh->b_blocknr,
+	       function, file, line);
+	if (withdraw)
+		gfs2_lm_withdraw(sdp, NULL);
 }
 
diff --git a/fs/gfs2/util.h b/fs/gfs2/util.h
index 3926f95a6eb7..96ac4aba4738 100644
--- a/fs/gfs2/util.h
+++ b/fs/gfs2/util.h
@@ -136,11 +136,15 @@ int gfs2_io_error_i(struct gfs2_sbd *sdp, const char *function,
 gfs2_io_error_i((sdp), __func__, __FILE__, __LINE__);
 
 
-int gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
-		       const char *function, char *file, unsigned int line);
+void gfs2_io_error_bh_i(struct gfs2_sbd *sdp, struct buffer_head *bh,
+			const char *function, char *file, unsigned int line,
+			bool withdraw);
+
+#define gfs2_io_error_bh_wd(sdp, bh) \
+gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, true);
 
 #define gfs2_io_error_bh(sdp, bh) \
-gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__);
+gfs2_io_error_bh_i((sdp), (bh), __func__, __FILE__, __LINE__, false);
 
 
 extern struct kmem_cache *gfs2_glock_cachep;
-- 
cgit v1.2.3


From 00251a16d7f9eb380437b402def05cd7c1b16c09 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 18 Jun 2018 16:34:59 +0100
Subject: gfs2: Minor clarification to __gfs2_punch_hole

Rename end_off to end_len to make the code less confusing.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/bmap.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index ed6699705c13..c7287afeeef5 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -2154,11 +2154,11 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length)
 		if (error)
 			goto out;
 	} else {
-		unsigned int start_off, end_off, blocksize;
+		unsigned int start_off, end_len, blocksize;
 
 		blocksize = i_blocksize(inode);
 		start_off = offset & (blocksize - 1);
-		end_off = (offset + length) & (blocksize - 1);
+		end_len = (offset + length) & (blocksize - 1);
 		if (start_off) {
 			unsigned int len = length;
 			if (length > blocksize - start_off)
@@ -2167,11 +2167,11 @@ int __gfs2_punch_hole(struct file *file, loff_t offset, loff_t length)
 			if (error)
 				goto out;
 			if (start_off + length < blocksize)
-				end_off = 0;
+				end_len = 0;
 		}
-		if (end_off) {
+		if (end_len) {
 			error = gfs2_block_zero_range(inode,
-				offset + length - end_off, end_off);
+				offset + length - end_len, end_len);
 			if (error)
 				goto out;
 		}
-- 
cgit v1.2.3


From ee9c7f9ae3d4fb9fb5c9cacbe3880d5dd66feb16 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 20 Jun 2018 15:15:24 -0500
Subject: gfs2: call ktime_get_coarse_real_ts64() directly

current_kernel_time64() is now just a deprecated wrapper around
ktime_get_coarse_real_ts64(), so let's just call that directly.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/log.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index a767fad02386..ee20ea42e7b5 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -701,7 +701,7 @@ void gfs2_write_log_header(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
 	hash = ~crc32(~0, lh, LH_V1_SIZE);
 	lh->lh_hash = cpu_to_be32(hash);
 
-	tv = current_kernel_time64();
+	ktime_get_coarse_real_ts64(&tv);
 	lh->lh_nsec = cpu_to_be32(tv.tv_nsec);
 	lh->lh_sec = cpu_to_be64(tv.tv_sec);
 	addr = gfs2_log_bmap(sdp);
-- 
cgit v1.2.3


From 1966c5e5bd9802cf62d3744ef4d2d6d32e22604d Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Tue, 5 Jun 2018 18:39:09 +0200
Subject: x86/asm: Use CC_SET/CC_OUT in percpu_cmpxchg8b_double() to
 micro-optimize code generation

Use CC_SET(z)/CC_OUT(z) instead of explicit SETZ instruction.

Using these two defines, the compiler that supports generation of
condition code outputs from inline assembly flags generates e.g.:

  cmpxchg8b %fs:(%esi)
  jne    172255 <__kmalloc+0x65>

instead of:

  cmpxchg8b %fs:(%esi)
  sete   %al
  test   %al,%al
  je     172255 <__kmalloc+0x65>

Note that older compilers now generate:

  cmpxchg8b %fs:(%esi)
  sete   %cl
  test   %cl,%cl
  je     173a85 <__kmalloc+0x65>

since we have to mark that cmpxchg8b instruction outputs to %eax
register and this way clobbers the value in the register.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/20180605163910.13015-1-ubizjak@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/percpu.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index a06b07399d17..e9202a0de8f0 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -450,9 +450,10 @@ do {									\
 	bool __ret;							\
 	typeof(pcp1) __o1 = (o1), __n1 = (n1);				\
 	typeof(pcp2) __o2 = (o2), __n2 = (n2);				\
-	asm volatile("cmpxchg8b "__percpu_arg(1)"\n\tsetz %0\n\t"	\
-		    : "=a" (__ret), "+m" (pcp1), "+m" (pcp2), "+d" (__o2) \
-		    :  "b" (__n1), "c" (__n2), "a" (__o1));		\
+	asm volatile("cmpxchg8b "__percpu_arg(1)			\
+		     CC_SET(z)						\
+		     : CC_OUT(z) (__ret), "+m" (pcp1), "+m" (pcp2), "+a" (__o1), "+d" (__o2) \
+		     : "b" (__n1), "c" (__n2));				\
 	__ret;								\
 })
 
-- 
cgit v1.2.3


From 0592e57b24e7e05ec1f4c50b9666c013abff7017 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 5 Jun 2018 08:38:45 -0700
Subject: perf/x86/intel/lbr: Fix incomplete LBR call stack

LBR has a limited stack size. If a task has a deeper call stack than
LBR's stack size, only the overflowed part is reported. A complete call
stack may not be reconstructed by perf tool.

Current code doesn't access all LBR registers. It only read the ones
below the TOS. The LBR registers above the TOS will be discarded
unconditionally.

When a CALL is captured, the TOS is incremented by 1 , modulo max LBR
stack size. The LBR HW only records the call stack information to the
register which the TOS points to. It will not touch other LBR
registers. So the registers above the TOS probably still store the valid
call stack information for an overflowed call stack, which need to be
reported.

To retrieve complete call stack information, we need to start from TOS,
read all LBR registers until an invalid entry is detected.
0s can be used to detect the invalid entry, because:

 - When a RET is captured, the HW zeros the LBR register which TOS points
   to, then decreases the TOS.
 - The LBR registers are reset to 0 when adding a new LBR event or
   scheduling an existing LBR event.
 - A taken branch at IP 0 is not expected

The context switch code is also modified to save/restore all valid LBR
registers. Furthermore, the LBR registers, which don't have valid call
stack information, need to be reset in restore, because they may be
polluted while swapped out.

Here is a small test program, tchain_deep.
Its call stack is deeper than 32.

 noinline void f33(void)
 {
        int i;

        for (i = 0; i < 10000000;) {
                if (i%2)
                        i++;
                else
                        i++;
        }
 }

 noinline void f32(void)
 {
        f33();
 }

 noinline void f31(void)
 {
        f32();
 }

 ... ...

 noinline void f1(void)
 {
        f2();
 }

 int main()
 {
        f1();
 }

Here is the test result on SKX. The max stack size of SKX is 32.

Without the patch:

 $ perf record -e cycles --call-graph lbr -- ./tchain_deep
 $ perf report --stdio
 #
 # Children      Self  Command      Shared Object     Symbol
 # ........  ........  ...........  ................  .................
 #
   100.00%    99.99%  tchain_deep    tchain_deep       [.] f33
            |
             --99.99%--f30
                       f31
                       f32
                       f33

With the patch:

 $ perf record -e cycles --call-graph lbr -- ./tchain_deep
 $ perf report --stdio
 # Children      Self  Command      Shared Object     Symbol
 # ........  ........  ...........  ................  ..................
 #
    99.99%     0.00%  tchain_deep    tchain_deep       [.] f1
            |
            ---f1
               f2
               f3
               f4
               f5
               f6
               f7
               f8
               f9
               f10
               f11
               f12
               f13
               f14
               f15
               f16
               f17
               f18
               f19
               f20
               f21
               f22
               f23
               f24
               f25
               f26
               f27
               f28
               f29
               f30
               f31
               f32
               f33

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: eranian@google.com
Link: https://lore.kernel.org/lkml/1528213126-4312-1-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/lbr.c  | 32 ++++++++++++++++++++++++++------
 arch/x86/events/perf_event.h |  1 +
 2 files changed, 27 insertions(+), 6 deletions(-)

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index cf372b90557e..a4170048a30b 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -346,7 +346,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = task_ctx->tos;
-	for (i = 0; i < tos; i++) {
+	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
 		wrlbr_to  (lbr_idx, task_ctx->lbr_to[i]);
@@ -354,6 +354,15 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+
+	for (; i < x86_pmu.lbr_nr; i++) {
+		lbr_idx = (tos - i) & mask;
+		wrlbr_from(lbr_idx, 0);
+		wrlbr_to(lbr_idx, 0);
+		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
+			wrmsrl(MSR_LBR_INFO_0 + lbr_idx, 0);
+	}
+
 	wrmsrl(x86_pmu.lbr_tos, tos);
 	task_ctx->lbr_stack_state = LBR_NONE;
 }
@@ -361,7 +370,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
 	unsigned lbr_idx, mask;
-	u64 tos;
+	u64 tos, from;
 	int i;
 
 	if (task_ctx->lbr_callstack_users == 0) {
@@ -371,13 +380,17 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 
 	mask = x86_pmu.lbr_nr - 1;
 	tos = intel_pmu_lbr_tos();
-	for (i = 0; i < tos; i++) {
+	for (i = 0; i < x86_pmu.lbr_nr; i++) {
 		lbr_idx = (tos - i) & mask;
-		task_ctx->lbr_from[i] = rdlbr_from(lbr_idx);
+		from = rdlbr_from(lbr_idx);
+		if (!from)
+			break;
+		task_ctx->lbr_from[i] = from;
 		task_ctx->lbr_to[i]   = rdlbr_to(lbr_idx);
 		if (x86_pmu.intel_cap.lbr_format == LBR_FORMAT_INFO)
 			rdmsrl(MSR_LBR_INFO_0 + lbr_idx, task_ctx->lbr_info[i]);
 	}
+	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
 }
@@ -531,7 +544,7 @@ static void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
  */
 static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 {
-	bool need_info = false;
+	bool need_info = false, call_stack = false;
 	unsigned long mask = x86_pmu.lbr_nr - 1;
 	int lbr_format = x86_pmu.intel_cap.lbr_format;
 	u64 tos = intel_pmu_lbr_tos();
@@ -542,7 +555,7 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 	if (cpuc->lbr_sel) {
 		need_info = !(cpuc->lbr_sel->config & LBR_NO_INFO);
 		if (cpuc->lbr_sel->config & LBR_CALL_STACK)
-			num = tos;
+			call_stack = true;
 	}
 
 	for (i = 0; i < num; i++) {
@@ -555,6 +568,13 @@ static void intel_pmu_lbr_read_64(struct cpu_hw_events *cpuc)
 		from = rdlbr_from(lbr_idx);
 		to   = rdlbr_to(lbr_idx);
 
+		/*
+		 * Read LBR call stack entries
+		 * until invalid entry (0s) is detected.
+		 */
+		if (call_stack && !from)
+			break;
+
 		if (lbr_format == LBR_FORMAT_INFO && need_info) {
 			u64 info;
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 9f3711470ec1..6b72a92069fd 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -648,6 +648,7 @@ struct x86_perf_task_context {
 	u64 lbr_to[MAX_LBR_ENTRIES];
 	u64 lbr_info[MAX_LBR_ENTRIES];
 	int tos;
+	int valid_lbrs;
 	int lbr_callstack_users;
 	int lbr_stack_state;
 };
-- 
cgit v1.2.3


From 8b077e4a69bef5c4121426e99497975860191e53 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Tue, 5 Jun 2018 08:38:46 -0700
Subject: perf/x86/intel/lbr: Optimize context switches for the LBR call stack

Context switches with perf LBR call stack context are fairly expensive
because they do a lot of MSR writes. Currently we unconditionally do the
expensive operation when LBR call stack is enabled. It's not necessary
for some common cases, e.g task -> other kernel thread -> same task.
The LBR registers are not changed, hence they don't need to be
rewritten/restored.

Introduce per-CPU variables to track the last LBR call stack context.
If the same context is scheduled in, the rewrite/restore is not
required, with the following two exceptions:

 - The LBR registers may be modified by a normal LBR event, i.e., adding
   a new LBR event or scheduling an existing LBR event. In both cases,
   the LBR registers are reset first. The last LBR call stack information
   is cleared in intel_pmu_lbr_reset(). Restoring the LBR registers is
   required.

 - The LBR registers are initialized to zero in C6.
   If the LBR registers which TOS points is cleared, C6 must be entered
   while swapped out. Restoring the LBR registers is required as well.

These exceptions are not common.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: acme@kernel.org
Cc: eranian@google.com
Link: https://lore.kernel.org/lkml/1528213126-4312-2-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/lbr.c  | 24 +++++++++++++++++++++++-
 arch/x86/events/perf_event.h |  4 ++++
 2 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index a4170048a30b..f3e006bed9a7 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -216,6 +216,8 @@ static void intel_pmu_lbr_reset_64(void)
 
 void intel_pmu_lbr_reset(void)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
 	if (!x86_pmu.lbr_nr)
 		return;
 
@@ -223,6 +225,9 @@ void intel_pmu_lbr_reset(void)
 		intel_pmu_lbr_reset_32();
 	else
 		intel_pmu_lbr_reset_64();
+
+	cpuc->last_task_ctx = NULL;
+	cpuc->last_log_id = 0;
 }
 
 /*
@@ -334,6 +339,7 @@ static inline u64 rdlbr_to(unsigned int idx)
 
 static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int i;
 	unsigned lbr_idx, mask;
 	u64 tos;
@@ -344,8 +350,20 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 		return;
 	}
 
-	mask = x86_pmu.lbr_nr - 1;
 	tos = task_ctx->tos;
+	/*
+	 * Does not restore the LBR registers, if
+	 * - No one else touched them, and
+	 * - Did not enter C6
+	 */
+	if ((task_ctx == cpuc->last_task_ctx) &&
+	    (task_ctx->log_id == cpuc->last_log_id) &&
+	    rdlbr_from(tos)) {
+		task_ctx->lbr_stack_state = LBR_NONE;
+		return;
+	}
+
+	mask = x86_pmu.lbr_nr - 1;
 	for (i = 0; i < task_ctx->valid_lbrs; i++) {
 		lbr_idx = (tos - i) & mask;
 		wrlbr_from(lbr_idx, task_ctx->lbr_from[i]);
@@ -369,6 +387,7 @@ static void __intel_pmu_lbr_restore(struct x86_perf_task_context *task_ctx)
 
 static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 {
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	unsigned lbr_idx, mask;
 	u64 tos, from;
 	int i;
@@ -393,6 +412,9 @@ static void __intel_pmu_lbr_save(struct x86_perf_task_context *task_ctx)
 	task_ctx->valid_lbrs = i;
 	task_ctx->tos = tos;
 	task_ctx->lbr_stack_state = LBR_VALID;
+
+	cpuc->last_task_ctx = task_ctx;
+	cpuc->last_log_id = ++task_ctx->log_id;
 }
 
 void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in)
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 6b72a92069fd..2430398befd8 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -163,6 +163,7 @@ struct intel_excl_cntrs {
 	unsigned	core_id;	/* per-core: core id */
 };
 
+struct x86_perf_task_context;
 #define MAX_LBR_ENTRIES		32
 
 enum {
@@ -214,6 +215,8 @@ struct cpu_hw_events {
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
 	struct er_account		*lbr_sel;
 	u64				br_sel;
+	struct x86_perf_task_context	*last_task_ctx;
+	int				last_log_id;
 
 	/*
 	 * Intel host/guest exclude bits
@@ -651,6 +654,7 @@ struct x86_perf_task_context {
 	int valid_lbrs;
 	int lbr_callstack_users;
 	int lbr_stack_state;
+	int log_id;
 };
 
 #define x86_add_quirk(func_)						\
-- 
cgit v1.2.3


From 8f894bf47dc9e8b77166125a084a7217693a28cd Mon Sep 17 00:00:00 2001
From: Yisheng Xie <xieyisheng1@huawei.com>
Date: Thu, 31 May 2018 19:11:19 +0800
Subject: sched/debug: Use match_string() helper instead of open-coded logic

match_string() returns the index of an array for a matching string,
which can be used instead of the open coded variant.

Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/lkml/1527765086-19873-15-git-send-email-xieyisheng1@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/debug.c | 31 +++++++++++++++----------------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e593b4118578..c96e89cc4bc7 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -111,20 +111,19 @@ static int sched_feat_set(char *cmp)
 		cmp += 3;
 	}
 
-	for (i = 0; i < __SCHED_FEAT_NR; i++) {
-		if (strcmp(cmp, sched_feat_names[i]) == 0) {
-			if (neg) {
-				sysctl_sched_features &= ~(1UL << i);
-				sched_feat_disable(i);
-			} else {
-				sysctl_sched_features |= (1UL << i);
-				sched_feat_enable(i);
-			}
-			break;
-		}
+	i = match_string(sched_feat_names, __SCHED_FEAT_NR, cmp);
+	if (i < 0)
+		return i;
+
+	if (neg) {
+		sysctl_sched_features &= ~(1UL << i);
+		sched_feat_disable(i);
+	} else {
+		sysctl_sched_features |= (1UL << i);
+		sched_feat_enable(i);
 	}
 
-	return i;
+	return 0;
 }
 
 static ssize_t
@@ -133,7 +132,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 {
 	char buf[64];
 	char *cmp;
-	int i;
+	int ret;
 	struct inode *inode;
 
 	if (cnt > 63)
@@ -148,10 +147,10 @@ sched_feat_write(struct file *filp, const char __user *ubuf,
 	/* Ensure the static_key remains in a consistent state */
 	inode = file_inode(filp);
 	inode_lock(inode);
-	i = sched_feat_set(cmp);
+	ret = sched_feat_set(cmp);
 	inode_unlock(inode);
-	if (i == __SCHED_FEAT_NR)
-		return -EINVAL;
+	if (ret < 0)
+		return ret;
 
 	*ppos += cnt;
 
-- 
cgit v1.2.3


From 1a7ed1ba4bba6c075d5ad61bb75e3fbc870840d6 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Thu, 21 Jun 2018 12:36:29 +0200
Subject: x86/speculation/l1tf: Extend 64bit swap file size limit

The previous patch has limited swap file size so that large offsets cannot
clear bits above MAX_PA/2 in the pte and interfere with L1TF mitigation.

It assumed that offsets are encoded starting with bit 12, same as pfn. But
on x86_64, offsets are encoded starting with bit 9.

Thus the limit can be raised by 3 bits. That means 16TB with 42bit MAX_PA
and 256TB with 46bit MAX_PA.

Fixes: 377eeaa8e11f ("x86/speculation/l1tf: Limit swap file size to MAX_PA/2")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/init.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 1b530197d114..c0870df32b2d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -891,7 +891,15 @@ unsigned long max_swapfile_size(void)
 
 	if (boot_cpu_has_bug(X86_BUG_L1TF)) {
 		/* Limit the swap file size to MAX_PA/2 for L1TF workaround */
-		pages = min_t(unsigned long, l1tf_pfn_limit() + 1, pages);
+		unsigned long l1tf_limit = l1tf_pfn_limit() + 1;
+		/*
+		 * We encode swap offsets also with 3 bits below those for pfn
+		 * which makes the usable limit higher.
+		 */
+#ifdef CONFIG_X86_64
+		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
+#endif
+		pages = min_t(unsigned long, l1tf_limit, pages);
 	}
 	return pages;
 }
-- 
cgit v1.2.3


From 9e3ed2d7597ccbce2a30e036342fb0613d0759e5 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Mon, 21 May 2018 23:55:20 +0530
Subject: perf/core: Change perf_mmap_fault() return type to 'vm_fault_t'

Use new return type 'vm_fault_t' for fault handlers.

For now, this is just documenting that the function returns
a VM_FAULT value rather than an errno. Once all instances
are converted, vm_fault_t will become a distinct type.

See the following commit:

  1c8f422059ae ("mm: change return type to vm_fault_t")

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: alexander.shishkin@linux.intel.com
Cc: jolsa@redhat.com
Cc: namhyung@kernel.org
Link: https://lkml.kernel.org/lkml/20180521182520.GA19677@jordon-HP-15-Notebook-PC
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/events/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80cca2b30c4f..a4d5ac6d74af 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5273,11 +5273,11 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(perf_event_update_userpage);
 
-static int perf_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t perf_mmap_fault(struct vm_fault *vmf)
 {
 	struct perf_event *event = vmf->vma->vm_file->private_data;
 	struct ring_buffer *rb;
-	int ret = VM_FAULT_SIGBUS;
+	vm_fault_t ret = VM_FAULT_SIGBUS;
 
 	if (vmf->flags & FAULT_FLAG_MKWRITE) {
 		if (vmf->pgoff == 0)
-- 
cgit v1.2.3


From 0797a8d0d79769574550caa5ca5d89c237723250 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 18 May 2018 08:47:08 +0200
Subject: x86/stacktrace: Do not unwind after user regs

Josh pointed out, that there is no way a frame can be after user regs.
So remove the last unwind and the check.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/lkml/20180518064713.26440-1-jslaby@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/stacktrace.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 093f2ea5dd56..8948b7d9c064 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -113,15 +113,6 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 			if (!user_mode(regs))
 				return -EINVAL;
 
-			/*
-			 * The last frame contains the user mode syscall
-			 * pt_regs.  Skip it and finish the unwind.
-			 */
-			unwind_next_frame(&state);
-			if (!unwind_done(&state)) {
-				STACKTRACE_DUMP_ONCE(task);
-				return -EINVAL;
-			}
 			break;
 		}
 
-- 
cgit v1.2.3


From 17426923b03f098da83b8c1e044934a34959f69b Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 18 May 2018 08:47:09 +0200
Subject: x86/stacktrace: Remove STACKTRACE_DUMP_ONCE

The stack unwinding can sometimes fail yet. Especially with the
generated debug info. So do not yell at users -- live patching (the only
user of this interface) will inform the user about the failure
gracefully.

And given this was the only user of the macro, remove the macro proper
too.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/lkml/20180518064713.26440-2-jslaby@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/stacktrace.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 8948b7d9c064..f9dacf6d4667 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -81,16 +81,6 @@ EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
 
 #ifdef CONFIG_HAVE_RELIABLE_STACKTRACE
 
-#define STACKTRACE_DUMP_ONCE(task) ({				\
-	static bool __section(.data.unlikely) __dumped;		\
-								\
-	if (!__dumped) {					\
-		__dumped = true;				\
-		WARN_ON(1);					\
-		show_stack(task, NULL);				\
-	}							\
-})
-
 static int __always_inline
 __save_stack_trace_reliable(struct stack_trace *trace,
 			    struct task_struct *task)
@@ -123,20 +113,16 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 		 * generated code which __kernel_text_address() doesn't know
 		 * about.
 		 */
-		if (!addr) {
-			STACKTRACE_DUMP_ONCE(task);
+		if (!addr)
 			return -EINVAL;
-		}
 
 		if (save_stack_address(trace, addr, false))
 			return -EINVAL;
 	}
 
 	/* Check for stack corruption */
-	if (unwind_error(&state)) {
-		STACKTRACE_DUMP_ONCE(task);
+	if (unwind_error(&state))
 		return -EINVAL;
-	}
 
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
-- 
cgit v1.2.3


From 441ccc3580f45340715fd8f5c4db795b06326404 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 18 May 2018 08:47:10 +0200
Subject: x86/stacktrace: Clarify the reliable success paths

Make clear which path is for user tasks and for kthreads and idle
tasks. This will allow easier plug-in of the ORC unwinder in the next
patches.

Note that we added a check for unwind error to the top of the loop, so
that an error is returned also for user tasks (the 'goto success' would
skip the check after the loop otherwise).

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/lkml/20180518064713.26440-3-jslaby@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/stacktrace.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index f9dacf6d4667..6acf1d5ca832 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -89,21 +89,24 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	struct pt_regs *regs;
 	unsigned long addr;
 
-	for (unwind_start(&state, task, NULL, NULL); !unwind_done(&state);
+	for (unwind_start(&state, task, NULL, NULL);
+	     !unwind_done(&state) && !unwind_error(&state);
 	     unwind_next_frame(&state)) {
 
 		regs = unwind_get_entry_regs(&state, NULL);
 		if (regs) {
+			/* Success path for user tasks */
+			if (user_mode(regs))
+				goto success;
+
 			/*
 			 * Kernel mode registers on the stack indicate an
 			 * in-kernel interrupt or exception (e.g., preemption
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-			if (!user_mode(regs))
-				return -EINVAL;
 
-			break;
+			return -EINVAL;
 		}
 
 		addr = unwind_get_return_address(&state);
@@ -124,6 +127,11 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 	if (unwind_error(&state))
 		return -EINVAL;
 
+	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
+	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
+		return -EINVAL;
+
+success:
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
 
-- 
cgit v1.2.3


From 0c414367c04eeb00c3ebfee0b74c9e7f3b95fd62 Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 18 May 2018 08:47:11 +0200
Subject: x86/stacktrace: Do not fail for ORC with regs on stack

save_stack_trace_reliable now returns "non reliable" when there are
kernel pt_regs on stack. This means an interrupt or exception happened
somewhere down the route. It is a problem for the frame pointer
unwinder, because the frame might not have been set up yet when the irq
happened, so the unwinder might fail to unwind from the interrupted
function.

With ORC, this is not a problem, as ORC has out-of-band data. We can
find ORC data even for the IP in the interrupted function and always
unwind one level up reliably.

So lift the check to apply only when CONFIG_FRAME_POINTER=y is enabled.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/lkml/20180518064713.26440-4-jslaby@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/stacktrace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 6acf1d5ca832..7627455047c2 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -106,7 +106,8 @@ __save_stack_trace_reliable(struct stack_trace *trace,
 			 * unreliable.
 			 */
 
-			return -EINVAL;
+			if (IS_ENABLED(CONFIG_FRAME_POINTER))
+				return -EINVAL;
 		}
 
 		addr = unwind_get_return_address(&state);
-- 
cgit v1.2.3


From d31a580266eeb1f355df90fde8a71f480e30ad70 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Fri, 18 May 2018 08:47:12 +0200
Subject: x86/unwind/orc: Detect the end of the stack

The existing UNWIND_HINT_EMPTY annotations happen to be good indicators
of where entry code calls into C code for the first time.  So also use
them to mark the end of the stack for the ORC unwinder.

Use that information to set unwind->error if the ORC unwinder doesn't
unwind all the way to the end.  This will be needed for enabling
HAVE_RELIABLE_STACKTRACE for the ORC unwinder so we can use it with the
livepatch consistency model.

Thanks to Jiri Slaby for teaching the ORCs about the unwind hints.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/lkml/20180518064713.26440-5-jslaby@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/entry/entry_64.S                      |  1 +
 arch/x86/include/asm/orc_types.h               |  2 +
 arch/x86/include/asm/unwind_hints.h            | 16 +++++---
 arch/x86/kernel/unwind_orc.c                   | 52 +++++++++++++++-----------
 tools/objtool/arch/x86/include/asm/orc_types.h |  2 +
 tools/objtool/check.c                          |  1 +
 tools/objtool/check.h                          |  2 +-
 tools/objtool/orc_dump.c                       |  3 +-
 tools/objtool/orc_gen.c                        |  2 +
 9 files changed, 52 insertions(+), 29 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 73a522d53b53..c6f3677e6105 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -408,6 +408,7 @@ ENTRY(ret_from_fork)
 
 1:
 	/* kernel thread */
+	UNWIND_HINT_EMPTY
 	movq	%r12, %rdi
 	CALL_NOSPEC %rbx
 	/*
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..46f516dd80ce 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -88,6 +88,7 @@ struct orc_entry {
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
+	unsigned	end:1;
 } __packed;
 
 /*
@@ -101,6 +102,7 @@ struct unwind_hint {
 	s16		sp_offset;
 	u8		sp_reg;
 	u8		type;
+	u8		end;
 };
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/unwind_hints.h b/arch/x86/include/asm/unwind_hints.h
index bae46fc6b9de..0bcdb1279361 100644
--- a/arch/x86/include/asm/unwind_hints.h
+++ b/arch/x86/include/asm/unwind_hints.h
@@ -26,7 +26,7 @@
  * the debuginfo as necessary.  It will also warn if it sees any
  * inconsistencies.
  */
-.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL
+.macro UNWIND_HINT sp_reg=ORC_REG_SP sp_offset=0 type=ORC_TYPE_CALL end=0
 #ifdef CONFIG_STACK_VALIDATION
 .Lunwind_hint_ip_\@:
 	.pushsection .discard.unwind_hints
@@ -35,12 +35,14 @@
 		.short \sp_offset
 		.byte \sp_reg
 		.byte \type
+		.byte \end
+		.balign 4
 	.popsection
 #endif
 .endm
 
 .macro UNWIND_HINT_EMPTY
-	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED
+	UNWIND_HINT sp_reg=ORC_REG_UNDEFINED end=1
 .endm
 
 .macro UNWIND_HINT_REGS base=%rsp offset=0 indirect=0 extra=1 iret=0
@@ -86,19 +88,21 @@
 
 #else /* !__ASSEMBLY__ */
 
-#define UNWIND_HINT(sp_reg, sp_offset, type)			\
+#define UNWIND_HINT(sp_reg, sp_offset, type, end)		\
 	"987: \n\t"						\
 	".pushsection .discard.unwind_hints\n\t"		\
 	/* struct unwind_hint */				\
 	".long 987b - .\n\t"					\
-	".short " __stringify(sp_offset) "\n\t"		\
+	".short " __stringify(sp_offset) "\n\t"			\
 	".byte " __stringify(sp_reg) "\n\t"			\
 	".byte " __stringify(type) "\n\t"			\
+	".byte " __stringify(end) "\n\t"			\
+	".balign 4 \n\t"					\
 	".popsection\n\t"
 
-#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE)
+#define UNWIND_HINT_SAVE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_SAVE, 0)
 
-#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE)
+#define UNWIND_HINT_RESTORE UNWIND_HINT(0, 0, UNWIND_HINT_TYPE_RESTORE, 0)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index feb28fee6cea..26038eacf74a 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -198,7 +198,7 @@ static int orc_sort_cmp(const void *_a, const void *_b)
 	 * whitelisted .o files which didn't get objtool generation.
 	 */
 	orc_a = cur_orc_table + (a - cur_orc_ip_table);
-	return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1;
+	return orc_a->sp_reg == ORC_REG_UNDEFINED && !orc_a->end ? -1 : 1;
 }
 
 #ifdef CONFIG_MODULES
@@ -352,7 +352,7 @@ static bool deref_stack_iret_regs(struct unwind_state *state, unsigned long addr
 
 bool unwind_next_frame(struct unwind_state *state)
 {
-	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
+	unsigned long ip_p, sp, orig_ip = state->ip, prev_sp = state->sp;
 	enum stack_type prev_type = state->stack_info.type;
 	struct orc_entry *orc;
 	bool indirect = false;
@@ -363,9 +363,9 @@ bool unwind_next_frame(struct unwind_state *state)
 	/* Don't let modules unload while we're reading their ORC data. */
 	preempt_disable();
 
-	/* Have we reached the end? */
+	/* End-of-stack check for user tasks: */
 	if (state->regs && user_mode(state->regs))
-		goto done;
+		goto the_end;
 
 	/*
 	 * Find the orc_entry associated with the text address.
@@ -374,9 +374,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	 * calls and calls to noreturn functions.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
-	if (!orc || orc->sp_reg == ORC_REG_UNDEFINED)
-		goto done;
-	orig_ip = state->ip;
+	if (!orc)
+		goto err;
+
+	/* End-of-stack check for kernel threads: */
+	if (orc->sp_reg == ORC_REG_UNDEFINED) {
+		if (!orc->end)
+			goto err;
+
+		goto the_end;
+	}
 
 	/* Find the previous frame's stack: */
 	switch (orc->sp_reg) {
@@ -402,7 +409,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R10 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r10;
 		break;
@@ -411,7 +418,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg R13 at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->r13;
 		break;
@@ -420,7 +427,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DI at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->di;
 		break;
@@ -429,7 +436,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!state->regs || !state->full_regs) {
 			orc_warn("missing regs for base reg DX at ip %pB\n",
 				 (void *)state->ip);
-			goto done;
+			goto err;
 		}
 		sp = state->regs->dx;
 		break;
@@ -437,12 +444,12 @@ bool unwind_next_frame(struct unwind_state *state)
 	default:
 		orc_warn("unknown SP base reg %d for ip %pB\n",
 			 orc->sp_reg, (void *)state->ip);
-		goto done;
+		goto err;
 	}
 
 	if (indirect) {
 		if (!deref_stack_reg(state, sp, &sp))
-			goto done;
+			goto err;
 	}
 
 	/* Find IP, SP and possibly regs: */
@@ -451,7 +458,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		ip_p = sp - sizeof(long);
 
 		if (!deref_stack_reg(state, ip_p, &state->ip))
-			goto done;
+			goto err;
 
 		state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
 						  state->ip, (void *)ip_p);
@@ -465,7 +472,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!deref_stack_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
-			goto done;
+			goto err;
 		}
 
 		state->regs = (struct pt_regs *)sp;
@@ -477,7 +484,7 @@ bool unwind_next_frame(struct unwind_state *state)
 		if (!deref_stack_iret_regs(state, sp, &state->ip, &state->sp)) {
 			orc_warn("can't dereference iret registers at %p for ip %pB\n",
 				 (void *)sp, (void *)orig_ip);
-			goto done;
+			goto err;
 		}
 
 		state->regs = (void *)sp - IRET_FRAME_OFFSET;
@@ -500,18 +507,18 @@ bool unwind_next_frame(struct unwind_state *state)
 
 	case ORC_REG_PREV_SP:
 		if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	case ORC_REG_BP:
 		if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp))
-			goto done;
+			goto err;
 		break;
 
 	default:
 		orc_warn("unknown BP base reg %d for ip %pB\n",
 			 orc->bp_reg, (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	/* Prevent a recursive loop due to bad ORC data: */
@@ -520,13 +527,16 @@ bool unwind_next_frame(struct unwind_state *state)
 	    state->sp <= prev_sp) {
 		orc_warn("stack going in the wrong direction? ip=%pB\n",
 			 (void *)orig_ip);
-		goto done;
+		goto err;
 	}
 
 	preempt_enable();
 	return true;
 
-done:
+err:
+	state->error = true;
+
+the_end:
 	preempt_enable();
 	state->stack_info.type = STACK_TYPE_UNKNOWN;
 	return false;
diff --git a/tools/objtool/arch/x86/include/asm/orc_types.h b/tools/objtool/arch/x86/include/asm/orc_types.h
index 9c9dc579bd7d..46f516dd80ce 100644
--- a/tools/objtool/arch/x86/include/asm/orc_types.h
+++ b/tools/objtool/arch/x86/include/asm/orc_types.h
@@ -88,6 +88,7 @@ struct orc_entry {
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
+	unsigned	end:1;
 } __packed;
 
 /*
@@ -101,6 +102,7 @@ struct unwind_hint {
 	s16		sp_offset;
 	u8		sp_reg;
 	u8		type;
+	u8		end;
 };
 #endif /* __ASSEMBLY__ */
 
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 38047c6aa575..8491beb1a636 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1156,6 +1156,7 @@ static int read_unwind_hints(struct objtool_file *file)
 
 		cfa->offset = hint->sp_offset;
 		insn->state.type = hint->type;
+		insn->state.end = hint->end;
 	}
 
 	return 0;
diff --git a/tools/objtool/check.h b/tools/objtool/check.h
index c6b68fcb926f..95700a2bcb7c 100644
--- a/tools/objtool/check.h
+++ b/tools/objtool/check.h
@@ -31,7 +31,7 @@ struct insn_state {
 	int stack_size;
 	unsigned char type;
 	bool bp_scratch;
-	bool drap;
+	bool drap, end;
 	int drap_reg, drap_offset;
 	struct cfi_reg vals[CFI_NUM_REGS];
 };
diff --git a/tools/objtool/orc_dump.c b/tools/objtool/orc_dump.c
index c3343820916a..faa444270ee3 100644
--- a/tools/objtool/orc_dump.c
+++ b/tools/objtool/orc_dump.c
@@ -203,7 +203,8 @@ int orc_dump(const char *_objname)
 
 		print_reg(orc[i].bp_reg, orc[i].bp_offset);
 
-		printf(" type:%s\n", orc_type_name(orc[i].type));
+		printf(" type:%s end:%d\n",
+		       orc_type_name(orc[i].type), orc[i].end);
 	}
 
 	elf_end(elf);
diff --git a/tools/objtool/orc_gen.c b/tools/objtool/orc_gen.c
index 18384d9be4e1..3f98dcfbc177 100644
--- a/tools/objtool/orc_gen.c
+++ b/tools/objtool/orc_gen.c
@@ -31,6 +31,8 @@ int create_orc(struct objtool_file *file)
 		struct cfi_reg *cfa = &insn->state.cfa;
 		struct cfi_reg *bp = &insn->state.regs[CFI_BP];
 
+		orc->end = insn->state.end;
+
 		if (cfa->base == CFI_UNDEFINED) {
 			orc->sp_reg = ORC_REG_UNDEFINED;
 			continue;
-- 
cgit v1.2.3


From 6415b38bae2641ab6e173ffa4ff6a453b60ba99b Mon Sep 17 00:00:00 2001
From: Jiri Slaby <jslaby@suse.cz>
Date: Fri, 18 May 2018 08:47:13 +0200
Subject: x86/stacktrace: Enable HAVE_RELIABLE_STACKTRACE for the ORC unwinder

In SUSE, we need a reliable stack unwinder for kernel live patching, but
we do not want to enable frame pointers for performance reasons. So
after the previous patches to make the ORC reliable, mark ORC as a
reliable stack unwinder on x86.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/lkml/20180518064713.26440-6-jslaby@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f1dbb4ee19d7..c4d64b19acff 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -180,7 +180,7 @@ config X86
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_RCU_TABLE_FREE
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_RELIABLE_STACKTRACE		if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
+	select HAVE_RELIABLE_STACKTRACE		if X86_64 && (UNWINDER_FRAME_POINTER || UNWINDER_ORC) && STACK_VALIDATION
 	select HAVE_STACKPROTECTOR		if CC_HAS_SANE_STACKPROTECTOR
 	select HAVE_STACK_VALIDATION		if X86_64
 	select HAVE_RSEQ
-- 
cgit v1.2.3


From 11e34e64e4103955fc4568750914c75d65ea87ee Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 20 Jun 2018 16:42:58 -0400
Subject: x86/cpufeatures: Add detection of L1D cache flush support.

336996-Speculative-Execution-Side-Channel-Mitigations.pdf defines a new MSR
(IA32_FLUSH_CMD) which is detected by CPUID.7.EDX[28]=1 bit being set.

This new MSR "gives software a way to invalidate structures with finer
granularity than other architectual methods like WBINVD."

A copy of this document is available at
  https://bugzilla.kernel.org/show_bug.cgi?id=199511

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/cpufeatures.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index f41cf9df4a83..64aaa3f5f36c 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -342,6 +342,7 @@
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
-- 
cgit v1.2.3


From 80dc12cdfb9e8966da4f02d6d7accf2cb691caf2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 21 Jun 2018 08:22:09 -0500
Subject: spi: spi-fsl-dspi: Fix copy-paste error in dspi_probe

It seems that the proper structure field to use in this particular
case is *regmap_pushr* instead of regmap.

Addresses-Coverity-ID: 1470126 ("Copy-paste error")
Fixes: 58ba07ec79e6 ("spi: spi-fsl-dspi: Add support for XSPI mode registers")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Esben Haabendal <eha@deif.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 1f85dcdb2203..ff7456be9d6d 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1066,7 +1066,7 @@ static int dspi_probe(struct platform_device *pdev)
 			dev_err(&pdev->dev,
 				"failed to init pushr regmap: %ld\n",
 				PTR_ERR(dspi->regmap_pushr));
-			ret = PTR_ERR(dspi->regmap);
+			ret = PTR_ERR(dspi->regmap_pushr);
 			goto out_master_put;
 		}
 	}
-- 
cgit v1.2.3


From f2a3ab36077222437b4826fc76111caa14562b7c Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 28 Apr 2018 21:35:01 +0900
Subject: kprobes: Make list and blacklist root user read only

Since the blacklist and list files on debugfs indicates
a sensitive address information to reader, it should be
restricted to the root user.

Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jon Medhurst <tixy@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tobin C . Harding <me@tobin.cc>
Cc: Will Deacon <will.deacon@arm.com>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: brueckner@linux.vnet.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: rostedt@goodmis.org
Cc: schwidefsky@de.ibm.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/lkml/152491890171.9916.5183693615601334087.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/kprobes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 536ab451e96d..898ee56d4f48 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2509,7 +2509,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!dir)
 		return -ENOMEM;
 
-	file = debugfs_create_file("list", 0444, dir, NULL,
+	file = debugfs_create_file("list", 0400, dir, NULL,
 				&debugfs_kprobes_operations);
 	if (!file)
 		goto error;
@@ -2519,7 +2519,7 @@ static int __init debugfs_kprobe_init(void)
 	if (!file)
 		goto error;
 
-	file = debugfs_create_file("blacklist", 0444, dir, NULL,
+	file = debugfs_create_file("blacklist", 0400, dir, NULL,
 				&debugfs_kprobe_blacklist_ops);
 	if (!file)
 		goto error;
-- 
cgit v1.2.3


From ffb9bd68ebdb3b8d00ef5a79bbe8167a3281cace Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 28 Apr 2018 21:35:32 +0900
Subject: kprobes: Show blacklist addresses as same as kallsyms does

Show kprobes blacklist addresses under same condition of
showing kallsyms addresses.

Since there are several name conflict for local symbols,
kprobe blacklist needs to show each addresses so that
user can identify where is on blacklist by comparing
with kallsyms.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jon Medhurst <tixy@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tobin C . Harding <me@tobin.cc>
Cc: Will Deacon <will.deacon@arm.com>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: brueckner@linux.vnet.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: rostedt@goodmis.org
Cc: schwidefsky@de.ibm.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/lkml/152491893217.9916.14760965896164273464.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/kprobes.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 898ee56d4f48..ab1bfa3d1d9c 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2326,8 +2326,16 @@ static int kprobe_blacklist_seq_show(struct seq_file *m, void *v)
 	struct kprobe_blacklist_entry *ent =
 		list_entry(v, struct kprobe_blacklist_entry, list);
 
-	seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
-		   (void *)ent->end_addr, (void *)ent->start_addr);
+	/*
+	 * If /proc/kallsyms is not showing kernel address, we won't
+	 * show them here either.
+	 */
+	if (!kallsyms_show_value())
+		seq_printf(m, "0x%px-0x%px\t%ps\n", NULL, NULL,
+			   (void *)ent->start_addr);
+	else
+		seq_printf(m, "0x%px-0x%px\t%ps\n", (void *)ent->start_addr,
+			   (void *)ent->end_addr, (void *)ent->start_addr);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 81365a947de453bcaba2558f8de5dadcffe05bc1 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 28 Apr 2018 21:36:02 +0900
Subject: kprobes: Show address of kprobes if kallsyms does

Show probed address in debugfs kprobe list file as same
as kallsyms does. This information is used for checking
kprobes are placed in the expected address. So it should
be able to compared with address in kallsyms.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jon Medhurst <tixy@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tobin C . Harding <me@tobin.cc>
Cc: Will Deacon <will.deacon@arm.com>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: brueckner@linux.vnet.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: rostedt@goodmis.org
Cc: schwidefsky@de.ibm.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/lkml/152491896256.9916.1583733714492565296.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/kprobes.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index ab1bfa3d1d9c..1d6130d2937a 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -2226,19 +2226,23 @@ static void report_probe(struct seq_file *pi, struct kprobe *p,
 		const char *sym, int offset, char *modname, struct kprobe *pp)
 {
 	char *kprobe_type;
+	void *addr = p->addr;
 
 	if (p->pre_handler == pre_handler_kretprobe)
 		kprobe_type = "r";
 	else
 		kprobe_type = "k";
 
+	if (!kallsyms_show_value())
+		addr = NULL;
+
 	if (sym)
-		seq_printf(pi, "%p  %s  %s+0x%x  %s ",
-			p->addr, kprobe_type, sym, offset,
+		seq_printf(pi, "%px  %s  %s+0x%x  %s ",
+			addr, kprobe_type, sym, offset,
 			(modname ? modname : " "));
-	else
-		seq_printf(pi, "%p  %s  %p ",
-			p->addr, kprobe_type, p->addr);
+	else	/* try to use %pS */
+		seq_printf(pi, "%px  %s  %pS ",
+			addr, kprobe_type, p->addr);
 
 	if (!pp)
 		pp = p;
-- 
cgit v1.2.3


From 4458515b2c52831ee622411d2fe3e774d1f5c49a Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 28 Apr 2018 21:36:33 +0900
Subject: kprobes: Replace %p with other pointer types

Replace %p with %pS or just remove it if unneeded.
And use WARN_ONCE() if it is a single bug.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jon Medhurst <tixy@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tobin C . Harding <me@tobin.cc>
Cc: Will Deacon <will.deacon@arm.com>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: brueckner@linux.vnet.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: rostedt@goodmis.org
Cc: schwidefsky@de.ibm.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/lkml/152491899284.9916.5350534544808158621.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/kprobes.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 1d6130d2937a..ab257be4d924 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -710,9 +710,7 @@ static void reuse_unused_kprobe(struct kprobe *ap)
 	 * there is still a relative jump) and disabled.
 	 */
 	op = container_of(ap, struct optimized_kprobe, kp);
-	if (unlikely(list_empty(&op->list)))
-		printk(KERN_WARNING "Warning: found a stray unused "
-			"aggrprobe@%p\n", ap->addr);
+	WARN_ON_ONCE(list_empty(&op->list));
 	/* Enable the probe again */
 	ap->flags &= ~KPROBE_FLAG_DISABLED;
 	/* Optimize it again (remove from op->list) */
@@ -985,7 +983,8 @@ static int arm_kprobe_ftrace(struct kprobe *p)
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 				   (unsigned long)p->addr, 0, 0);
 	if (ret) {
-		pr_debug("Failed to arm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+		pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n",
+			 p->addr, ret);
 		return ret;
 	}
 
@@ -1025,7 +1024,8 @@ static int disarm_kprobe_ftrace(struct kprobe *p)
 
 	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
 			   (unsigned long)p->addr, 1, 0);
-	WARN(ret < 0, "Failed to disarm kprobe-ftrace at %p (%d)\n", p->addr, ret);
+	WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n",
+		  p->addr, ret);
 	return ret;
 }
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
@@ -2069,11 +2069,12 @@ out:
 }
 EXPORT_SYMBOL_GPL(enable_kprobe);
 
+/* Caller must NOT call this in usual path. This is only for critical case */
 void dump_kprobe(struct kprobe *kp)
 {
-	printk(KERN_WARNING "Dumping kprobe:\n");
-	printk(KERN_WARNING "Name: %s\nAddress: %p\nOffset: %x\n",
-	       kp->symbol_name, kp->addr, kp->offset);
+	pr_err("Dumping kprobe:\n");
+	pr_err("Name: %s\nOffset: %x\nAddress: %pS\n",
+	       kp->symbol_name, kp->offset, kp->addr);
 }
 NOKPROBE_SYMBOL(dump_kprobe);
 
@@ -2096,11 +2097,8 @@ static int __init populate_kprobe_blacklist(unsigned long *start,
 		entry = arch_deref_entry_point((void *)*iter);
 
 		if (!kernel_text_address(entry) ||
-		    !kallsyms_lookup_size_offset(entry, &size, &offset)) {
-			pr_err("Failed to find blacklist at %p\n",
-				(void *)entry);
+		    !kallsyms_lookup_size_offset(entry, &size, &offset))
 			continue;
-		}
 
 		ent = kmalloc(sizeof(*ent), GFP_KERNEL);
 		if (!ent)
-- 
cgit v1.2.3


From 0ea063306eecf300fcf06d2f5917474b580f666f Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 28 Apr 2018 21:37:03 +0900
Subject: kprobes/x86: Fix %p uses in error messages

Remove all %p uses in error messages in kprobes/x86.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jon Medhurst <tixy@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tobin C . Harding <me@tobin.cc>
Cc: Will Deacon <will.deacon@arm.com>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: brueckner@linux.vnet.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: rostedt@goodmis.org
Cc: schwidefsky@de.ibm.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/lkml/152491902310.9916.13355297638917767319.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/kprobes/core.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index f7104b256de7..b0d1e81c96bb 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -393,8 +393,6 @@ int __copy_instruction(u8 *dest, u8 *src, u8 *real, struct insn *insn)
 			  - (u8 *) real;
 		if ((s64) (s32) newdisp != newdisp) {
 			pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp);
-			pr_err("\tSrc: %p, Dest: %p, old disp: %x\n",
-				src, real, insn->displacement.value);
 			return 0;
 		}
 		disp = (u8 *) dest + insn_offset_displacement(insn);
@@ -637,8 +635,7 @@ static int reenter_kprobe(struct kprobe *p, struct pt_regs *regs,
 		 * Raise a BUG or we'll continue in an endless reentering loop
 		 * and eventually a stack overflow.
 		 */
-		printk(KERN_WARNING "Unrecoverable kprobe detected at %p.\n",
-		       p->addr);
+		pr_err("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 	default:
-- 
cgit v1.2.3


From 75b2f5f5911fe7a2fc82969b2b24dde34e8f820d Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 28 Apr 2018 21:37:33 +0900
Subject: kprobes/arm: Fix %p uses in error messages

Fix %p uses in error messages by removing it and
using general dumper.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jon Medhurst <tixy@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tobin C . Harding <me@tobin.cc>
Cc: Will Deacon <will.deacon@arm.com>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: brueckner@linux.vnet.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: rostedt@goodmis.org
Cc: schwidefsky@de.ibm.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/lkml/152491905361.9916.15300852365956231645.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/probes/kprobes/core.c      | 4 ++--
 arch/arm/probes/kprobes/test-core.c | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index 8d37601fdb20..f8bd523d64d1 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -286,8 +286,8 @@ void __kprobes kprobe_handler(struct pt_regs *regs)
 				break;
 			case KPROBE_REENTER:
 				/* A nested probe was hit in FIQ, it is a BUG */
-				pr_warn("Unrecoverable kprobe detected at %p.\n",
-					p->addr);
+				pr_warn("Unrecoverable kprobe detected.\n");
+				dump_kprobe(p);
 				/* fall through */
 			default:
 				/* impossible cases */
diff --git a/arch/arm/probes/kprobes/test-core.c b/arch/arm/probes/kprobes/test-core.c
index 14db14152909..cc237fa9b90f 100644
--- a/arch/arm/probes/kprobes/test-core.c
+++ b/arch/arm/probes/kprobes/test-core.c
@@ -1461,7 +1461,6 @@ fail:
 	print_registers(&result_regs);
 
 	if (mem) {
-		pr_err("current_stack=%p\n", current_stack);
 		pr_err("expected_memory:\n");
 		print_memory(expected_memory, mem_size);
 		pr_err("result_memory:\n");
-- 
cgit v1.2.3


From 0722867dcbc28cc9b269b57acd847c7c1aa638d6 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Sat, 28 Apr 2018 21:38:04 +0900
Subject: kprobes/arm64: Fix %p uses in error messages

Fix %p uses in error messages by removing it because
those are redundant or meaningless.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: David Howells <dhowells@redhat.com>
Cc: David S . Miller <davem@davemloft.net>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Jon Medhurst <tixy@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Tobin C . Harding <me@tobin.cc>
Cc: acme@kernel.org
Cc: akpm@linux-foundation.org
Cc: brueckner@linux.vnet.ibm.com
Cc: linux-arch@vger.kernel.org
Cc: rostedt@goodmis.org
Cc: schwidefsky@de.ibm.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/lkml/152491908405.9916.12425053035317241111.stgit@devbox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/kernel/probes/kprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c
index 5daf3d721cb7..e78c3ef04d95 100644
--- a/arch/arm64/kernel/probes/kprobes.c
+++ b/arch/arm64/kernel/probes/kprobes.c
@@ -275,7 +275,7 @@ static int __kprobes reenter_kprobe(struct kprobe *p,
 		break;
 	case KPROBE_HIT_SS:
 	case KPROBE_REENTER:
-		pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr);
+		pr_warn("Unrecoverable kprobe detected.\n");
 		dump_kprobe(p);
 		BUG();
 		break;
-- 
cgit v1.2.3


From 1bce62a6e0dd85c15cbab36a0f7b9d4766cef18e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 23:15:59 +0200
Subject: ALSA: hda/realtek - Simplify alc269_fixup_hp_line1_mic1_led()

alc269_fixup_hp_line1_mic1_led() can be simplified more with the
existing helper code.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d9461eebcfdf..7934c5df4d80 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3973,14 +3973,10 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 {
 	struct alc_spec *spec = codec->spec;
 
+	alc269_fixup_hp_mute_led_micx(codec, fix, action, 0x1a);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc269_fixup_mic_mute_hook;
-		spec->mute_led_polarity = 0;
-		spec->mute_led_nid = 0x1a;
 		spec->cap_mute_led_nid = 0x18;
 		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
-		spec->gen.vmaster_mute_enum = 1;
-		codec->power_filter = led_power_filter;
 	}
 }
 
-- 
cgit v1.2.3


From 8a29c778fa1a50a25a3e66cf9589888758858d24 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Wed, 23 May 2018 11:04:35 -0700
Subject: drm/i915: remove check for aux irq
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This became dead code with commit 309bd8ed464f ("drm/i915: Reinstate
GMBUS and AUX interrupts on gen4/g4x").

v2: Move comment about HW behavior to where decision is made to enable
MSI (Ville).

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180523180435.18042-1-lucas.demarchi@intel.com
---
 drivers/gpu/drm/i915/i915_drv.c  |  6 ++++++
 drivers/gpu/drm/i915/i915_drv.h  | 10 ----------
 drivers/gpu/drm/i915/intel_dp.c  | 22 +++++++---------------
 drivers/gpu/drm/i915/intel_drv.h |  1 -
 drivers/gpu/drm/i915/intel_psr.c |  2 +-
 5 files changed, 14 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 33453d56c386..2959c88a37a5 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1165,6 +1165,12 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 	 * get lost on g4x as well, and interrupt delivery seems to stay
 	 * properly dead afterwards. So we'll just disable them for all
 	 * pre-gen5 chipsets.
+	 *
+	 * dp aux and gmbus irq on gen4 seems to be able to generate legacy
+	 * interrupts even when in MSI mode. This results in spurious
+	 * interrupt warnings if the legacy irq no. is shared with another
+	 * device. The kernel then disables that interrupt source and so
+	 * prevents the other device from working properly.
 	 */
 	if (INTEL_GEN(dev_priv) >= 5) {
 		if (pci_enable_msi(pdev) < 0)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 735f695cb889..6f08ab310118 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2581,16 +2581,6 @@ intel_info(const struct drm_i915_private *dev_priv)
 	(IS_CANNONLAKE(dev_priv) || \
 	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
 
-/*
- * dp aux and gmbus irq on gen4 seems to be able to generate legacy interrupts
- * even when in MSI mode. This results in spurious interrupt warnings if the
- * legacy irq no. is shared with another device. The kernel then disables that
- * interrupt source and so prevents the other device from working properly.
- *
- * Since we don't enable MSI anymore on gen4, we can always use GMBUS/AUX
- * interrupts.
- */
-#define HAS_AUX_IRQ(dev_priv)   true
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
 
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 6ac6c8787dcf..c1b2f00f324b 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -953,7 +953,7 @@ intel_dp_check_edp(struct intel_dp *intel_dp)
 }
 
 static uint32_t
-intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
+intel_dp_aux_wait_done(struct intel_dp *intel_dp)
 {
 	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
 	i915_reg_t ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
@@ -961,14 +961,10 @@ intel_dp_aux_wait_done(struct intel_dp *intel_dp, bool has_aux_irq)
 	bool done;
 
 #define C (((status = I915_READ_NOTRACE(ch_ctl)) & DP_AUX_CH_CTL_SEND_BUSY) == 0)
-	if (has_aux_irq)
-		done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
-					  msecs_to_jiffies_timeout(10));
-	else
-		done = wait_for(C, 10) == 0;
+	done = wait_event_timeout(dev_priv->gmbus_wait_queue, C,
+				  msecs_to_jiffies_timeout(10));
 	if (!done)
-		DRM_ERROR("dp aux hw did not signal timeout (has irq: %i)!\n",
-			  has_aux_irq);
+		DRM_ERROR("dp aux hw did not signal timeout!\n");
 #undef C
 
 	return status;
@@ -1033,7 +1029,6 @@ static uint32_t skl_get_aux_clock_divider(struct intel_dp *intel_dp, int index)
 }
 
 static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
-				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider)
 {
@@ -1054,7 +1049,7 @@ static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
 
 	return DP_AUX_CH_CTL_SEND_BUSY |
 	       DP_AUX_CH_CTL_DONE |
-	       (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
+	       DP_AUX_CH_CTL_INTERRUPT |
 	       DP_AUX_CH_CTL_TIME_OUT_ERROR |
 	       timeout |
 	       DP_AUX_CH_CTL_RECEIVE_ERROR |
@@ -1064,13 +1059,12 @@ static uint32_t g4x_get_aux_send_ctl(struct intel_dp *intel_dp,
 }
 
 static uint32_t skl_get_aux_send_ctl(struct intel_dp *intel_dp,
-				      bool has_aux_irq,
 				      int send_bytes,
 				      uint32_t unused)
 {
 	return DP_AUX_CH_CTL_SEND_BUSY |
 	       DP_AUX_CH_CTL_DONE |
-	       (has_aux_irq ? DP_AUX_CH_CTL_INTERRUPT : 0) |
+	       DP_AUX_CH_CTL_INTERRUPT |
 	       DP_AUX_CH_CTL_TIME_OUT_ERROR |
 	       DP_AUX_CH_CTL_TIME_OUT_MAX |
 	       DP_AUX_CH_CTL_RECEIVE_ERROR |
@@ -1093,7 +1087,6 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 	int i, ret, recv_bytes;
 	uint32_t status;
 	int try, clock = 0;
-	bool has_aux_irq = HAS_AUX_IRQ(dev_priv);
 	bool vdd;
 
 	ch_ctl = intel_dp->aux_ch_ctl_reg(intel_dp);
@@ -1148,7 +1141,6 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 
 	while ((aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, clock++))) {
 		u32 send_ctl = intel_dp->get_aux_send_ctl(intel_dp,
-							  has_aux_irq,
 							  send_bytes,
 							  aux_clock_divider);
 
@@ -1165,7 +1157,7 @@ intel_dp_aux_xfer(struct intel_dp *intel_dp,
 			/* Send the command and wait for it to complete */
 			I915_WRITE(ch_ctl, send_ctl);
 
-			status = intel_dp_aux_wait_done(intel_dp, has_aux_irq);
+			status = intel_dp_aux_wait_done(intel_dp);
 
 			/* Clear done status and any errors */
 			I915_WRITE(ch_ctl,
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 22831acc7c30..9e0a8cc48521 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1132,7 +1132,6 @@ struct intel_dp {
 	 * register with to kick off an AUX transaction.
 	 */
 	uint32_t (*get_aux_send_ctl)(struct intel_dp *dp,
-				     bool has_aux_irq,
 				     int send_bytes,
 				     uint32_t aux_clock_divider);
 
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index d4cd19fea148..aea81ace854b 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -336,7 +336,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 	aux_clock_divider = intel_dp->get_aux_clock_divider(intel_dp, 0);
 
 	/* Start with bits set for DDI_AUX_CTL register */
-	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, 0, sizeof(aux_msg),
+	aux_ctl = intel_dp->get_aux_send_ctl(intel_dp, sizeof(aux_msg),
 					     aux_clock_divider);
 
 	/* Select only valid bits for SRD_AUX_CTL */
-- 
cgit v1.2.3


From 03585a95cd830e7a92697d2a8fe9a34df87563db Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 11 Apr 2018 13:16:56 +0800
Subject: sched/fair: Remove stale tg_unthrottle_up() comments

After commit:

  82958366cfea ("sched: Replace update_shares weight distribution with per-entity computation")

tg_unthrottle_up() did not update the weight.

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/lkml/1523423816-18322-1-git-send-email-lirongqing@baidu.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1866e64792a7..4cc1441b0746 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4732,7 +4732,6 @@ static inline int throttled_lb_pair(struct task_group *tg,
 	       throttled_hierarchy(dest_cfs_rq);
 }
 
-/* updated child weight may affect parent so we have to do this bottom up */
 static int tg_unthrottle_up(struct task_group *tg, void *data)
 {
 	struct rq *rq = data;
-- 
cgit v1.2.3


From 9fc59bae0f4a8ec3676a9245abed7721b4d3d8c9 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 15 Jun 2018 17:39:10 +0300
Subject: drm/i915/icl: Fix MG PLL setup when refclk is 38.4MHz

Atm we're zeroing out fields in MG_PLL_BIAS and MG_PLL_TDC_COLDST_BIAS
if refclk is 38.4MHz, whereas the spec tells us to preserve them.
Although the calculated values mostly match the register defaults even
for the 38.4MHz case, there are some differences wrt. what BIOS
programs (I noticed at least differences in the MG_PLL_BIAS/IREFTRIM and
MG_PLL_BIAS/BIASCAL_EN fields). In the lack of further info on how to
program these fields, just do what the spec says and preserve the BIOS
state.

v2:
- Preserve the BIOS programmed reg fields instead of programming them.

Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: James Ausmus <james.ausmus@intel.com> (v1)
Reviewed-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615143911.31082-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_dpll_mgr.c | 67 ++++++++++++++++++++++++-----------
 drivers/gpu/drm/i915/intel_dpll_mgr.h |  2 ++
 2 files changed, 49 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 132fe63e042a..d4c7bacbe83e 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -2812,25 +2812,31 @@ static bool icl_calc_mg_pll_state(struct intel_crtc_state *crtc_state,
 				MG_PLL_SSC_FLLEN |
 				MG_PLL_SSC_STEPSIZE(ssc_stepsize);
 
-	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART;
-
-	if (refclk_khz != 38400) {
-		pll_state->mg_pll_tdc_coldst_bias |=
-			MG_PLL_TDC_COLDST_IREFINT_EN |
-			MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
-			MG_PLL_TDC_COLDST_COLDSTART |
-			MG_PLL_TDC_TDCOVCCORR_EN |
-			MG_PLL_TDC_TDCSEL(3);
-
-		pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
-					 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
-					 MG_PLL_BIAS_BIAS_BONUS(10) |
-					 MG_PLL_BIAS_BIASCAL_EN |
-					 MG_PLL_BIAS_CTRIM(12) |
-					 MG_PLL_BIAS_VREF_RDAC(4) |
-					 MG_PLL_BIAS_IREFTRIM(iref_trim);
+	pll_state->mg_pll_tdc_coldst_bias = MG_PLL_TDC_COLDST_COLDSTART |
+					    MG_PLL_TDC_COLDST_IREFINT_EN |
+					    MG_PLL_TDC_COLDST_REFBIAS_START_PULSE_W(iref_pulse_w) |
+					    MG_PLL_TDC_TDCOVCCORR_EN |
+					    MG_PLL_TDC_TDCSEL(3);
+
+	pll_state->mg_pll_bias = MG_PLL_BIAS_BIAS_GB_SEL(3) |
+				 MG_PLL_BIAS_INIT_DCOAMP(0x3F) |
+				 MG_PLL_BIAS_BIAS_BONUS(10) |
+				 MG_PLL_BIAS_BIASCAL_EN |
+				 MG_PLL_BIAS_CTRIM(12) |
+				 MG_PLL_BIAS_VREF_RDAC(4) |
+				 MG_PLL_BIAS_IREFTRIM(iref_trim);
+
+	if (refclk_khz == 38400) {
+		pll_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART;
+		pll_state->mg_pll_bias_mask = 0;
+	} else {
+		pll_state->mg_pll_tdc_coldst_bias_mask = -1U;
+		pll_state->mg_pll_bias_mask = -1U;
 	}
 
+	pll_state->mg_pll_tdc_coldst_bias &= pll_state->mg_pll_tdc_coldst_bias_mask;
+	pll_state->mg_pll_bias &= pll_state->mg_pll_bias_mask;
+
 	return true;
 }
 
@@ -2948,9 +2954,21 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 		hw_state->mg_pll_lf = I915_READ(MG_PLL_LF(port));
 		hw_state->mg_pll_frac_lock = I915_READ(MG_PLL_FRAC_LOCK(port));
 		hw_state->mg_pll_ssc = I915_READ(MG_PLL_SSC(port));
+
 		hw_state->mg_pll_bias = I915_READ(MG_PLL_BIAS(port));
 		hw_state->mg_pll_tdc_coldst_bias =
 			I915_READ(MG_PLL_TDC_COLDST_BIAS(port));
+
+		if (dev_priv->cdclk.hw.ref == 38400) {
+			hw_state->mg_pll_tdc_coldst_bias_mask = MG_PLL_TDC_COLDST_COLDSTART;
+			hw_state->mg_pll_bias_mask = 0;
+		} else {
+			hw_state->mg_pll_tdc_coldst_bias_mask = -1U;
+			hw_state->mg_pll_bias_mask = -1U;
+		}
+
+		hw_state->mg_pll_tdc_coldst_bias &= hw_state->mg_pll_tdc_coldst_bias_mask;
+		hw_state->mg_pll_bias &= hw_state->mg_pll_bias_mask;
 		break;
 	default:
 		MISSING_CASE(id);
@@ -2978,6 +2996,7 @@ static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
 {
 	struct intel_dpll_hw_state *hw_state = &pll->state.hw_state;
 	enum port port = icl_mg_pll_id_to_port(pll->info->id);
+	u32 val;
 
 	I915_WRITE(MG_REFCLKIN_CTL(port), hw_state->mg_refclkin_ctl);
 	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port),
@@ -2988,9 +3007,17 @@ static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
 	I915_WRITE(MG_PLL_LF(port), hw_state->mg_pll_lf);
 	I915_WRITE(MG_PLL_FRAC_LOCK(port), hw_state->mg_pll_frac_lock);
 	I915_WRITE(MG_PLL_SSC(port), hw_state->mg_pll_ssc);
-	I915_WRITE(MG_PLL_BIAS(port), hw_state->mg_pll_bias);
-	I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port),
-		   hw_state->mg_pll_tdc_coldst_bias);
+
+	val = I915_READ(MG_PLL_BIAS(port));
+	val &= ~hw_state->mg_pll_bias_mask;
+	val |= hw_state->mg_pll_bias;
+	I915_WRITE(MG_PLL_BIAS(port), val);
+
+	val = I915_READ(MG_PLL_TDC_COLDST_BIAS(port));
+	val &= ~hw_state->mg_pll_tdc_coldst_bias_mask;
+	val |= hw_state->mg_pll_tdc_coldst_bias;
+	I915_WRITE(MG_PLL_TDC_COLDST_BIAS(port), val);
+
 	POSTING_READ(MG_PLL_TDC_COLDST_BIAS(port));
 }
 
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.h b/drivers/gpu/drm/i915/intel_dpll_mgr.h
index ba925c7ee482..7e522cf4f13f 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.h
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.h
@@ -180,6 +180,8 @@ struct intel_dpll_hw_state {
 	uint32_t mg_pll_ssc;
 	uint32_t mg_pll_bias;
 	uint32_t mg_pll_tdc_coldst_bias;
+	uint32_t mg_pll_bias_mask;
+	uint32_t mg_pll_tdc_coldst_bias_mask;
 };
 
 /**
-- 
cgit v1.2.3


From bd99ce085f165a07fe8b33ad04157b91c91b8668 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 19 Jun 2018 19:41:15 +0300
Subject: drm/i915/icl: Do read-modify-write as needed during MG PLL
 programming

Some MG PLL registers have fields that need to be preserved at their HW
default or BIOS programmed values. So make sure we preserve them.

v2:
- Add comment to icl_mg_pll_write() explaining the need for register
  masks. (Vandita)
- Fix patchwork checkpatch warning.

v3:
- Rebase on drm-tip.

Cc: Vandita Kulkarni <vandita.kulkarni@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: James Ausmus <james.ausmus@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: James Ausmus <james.ausmus@intel.com> (v1)
Reviewed-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180619164115.7835-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h       | 13 ++++++++++++
 drivers/gpu/drm/i915/intel_dpll_mgr.c | 39 +++++++++++++++++++++++++++++++----
 2 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 4bfd7a9bd75f..65b222287ee4 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9047,6 +9047,7 @@ enum skl_power_gate {
 #define _MG_REFCLKIN_CTL_PORT3				0x16A92C
 #define _MG_REFCLKIN_CTL_PORT4				0x16B92C
 #define   MG_REFCLKIN_CTL_OD_2_MUX(x)			((x) << 8)
+#define   MG_REFCLKIN_CTL_OD_2_MUX_MASK			(0x7 << 8)
 #define MG_REFCLKIN_CTL(port) _MMIO_PORT((port) - PORT_C, \
 					 _MG_REFCLKIN_CTL_PORT1, \
 					 _MG_REFCLKIN_CTL_PORT2)
@@ -9056,7 +9057,9 @@ enum skl_power_gate {
 #define _MG_CLKTOP2_CORECLKCTL1_PORT3			0x16A8D8
 #define _MG_CLKTOP2_CORECLKCTL1_PORT4			0x16B8D8
 #define   MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO(x)		((x) << 16)
+#define   MG_CLKTOP2_CORECLKCTL1_B_DIVRATIO_MASK	(0xff << 16)
 #define   MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO(x)		((x) << 8)
+#define   MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK	(0xff << 8)
 #define MG_CLKTOP2_CORECLKCTL1(port) _MMIO_PORT((port) - PORT_C, \
 						_MG_CLKTOP2_CORECLKCTL1_PORT1, \
 						_MG_CLKTOP2_CORECLKCTL1_PORT2)
@@ -9066,9 +9069,13 @@ enum skl_power_gate {
 #define _MG_CLKTOP2_HSCLKCTL_PORT3			0x16A8D4
 #define _MG_CLKTOP2_HSCLKCTL_PORT4			0x16B8D4
 #define   MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL(x)		((x) << 16)
+#define   MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK	(0x1 << 16)
 #define   MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL(x)	((x) << 14)
+#define   MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK	(0x3 << 14)
 #define   MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO(x)		((x) << 12)
+#define   MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK		(0x3 << 12)
 #define   MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO(x)		((x) << 8)
+#define   MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK		(0xf << 8)
 #define MG_CLKTOP2_HSCLKCTL(port) _MMIO_PORT((port) - PORT_C, \
 					     _MG_CLKTOP2_HSCLKCTL_PORT1, \
 					     _MG_CLKTOP2_HSCLKCTL_PORT2)
@@ -9142,12 +9149,18 @@ enum skl_power_gate {
 #define _MG_PLL_BIAS_PORT3				0x16AA14
 #define _MG_PLL_BIAS_PORT4				0x16BA14
 #define   MG_PLL_BIAS_BIAS_GB_SEL(x)			((x) << 30)
+#define   MG_PLL_BIAS_BIAS_GB_SEL_MASK			(0x3 << 30)
 #define   MG_PLL_BIAS_INIT_DCOAMP(x)			((x) << 24)
+#define   MG_PLL_BIAS_INIT_DCOAMP_MASK			(0x3f << 24)
 #define   MG_PLL_BIAS_BIAS_BONUS(x)			((x) << 16)
+#define   MG_PLL_BIAS_BIAS_BONUS_MASK			(0xff << 16)
 #define   MG_PLL_BIAS_BIASCAL_EN			(1 << 15)
 #define   MG_PLL_BIAS_CTRIM(x)				((x) << 8)
+#define   MG_PLL_BIAS_CTRIM_MASK			(0x1f << 8)
 #define   MG_PLL_BIAS_VREF_RDAC(x)			((x) << 5)
+#define   MG_PLL_BIAS_VREF_RDAC_MASK			(0x7 << 5)
 #define   MG_PLL_BIAS_IREFTRIM(x)			((x) << 0)
+#define   MG_PLL_BIAS_IREFTRIM_MASK			(0x1f << 0)
 #define MG_PLL_BIAS(port) _MMIO_PORT((port) - PORT_C, _MG_PLL_BIAS_PORT1, \
 				     _MG_PLL_BIAS_PORT2)
 
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index d4c7bacbe83e..57342364fd30 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -2945,10 +2945,21 @@ static bool icl_pll_get_hw_state(struct drm_i915_private *dev_priv,
 	case DPLL_ID_ICL_MGPLL4:
 		port = icl_mg_pll_id_to_port(id);
 		hw_state->mg_refclkin_ctl = I915_READ(MG_REFCLKIN_CTL(port));
+		hw_state->mg_refclkin_ctl &= MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+
 		hw_state->mg_clktop2_coreclkctl1 =
 			I915_READ(MG_CLKTOP2_CORECLKCTL1(port));
+		hw_state->mg_clktop2_coreclkctl1 &=
+			MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+
 		hw_state->mg_clktop2_hsclkctl =
 			I915_READ(MG_CLKTOP2_HSCLKCTL(port));
+		hw_state->mg_clktop2_hsclkctl &=
+			MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+			MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+			MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+			MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK;
+
 		hw_state->mg_pll_div0 = I915_READ(MG_PLL_DIV0(port));
 		hw_state->mg_pll_div1 = I915_READ(MG_PLL_DIV1(port));
 		hw_state->mg_pll_lf = I915_READ(MG_PLL_LF(port));
@@ -2998,10 +3009,30 @@ static void icl_mg_pll_write(struct drm_i915_private *dev_priv,
 	enum port port = icl_mg_pll_id_to_port(pll->info->id);
 	u32 val;
 
-	I915_WRITE(MG_REFCLKIN_CTL(port), hw_state->mg_refclkin_ctl);
-	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port),
-		   hw_state->mg_clktop2_coreclkctl1);
-	I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), hw_state->mg_clktop2_hsclkctl);
+	/*
+	 * Some of the following registers have reserved fields, so program
+	 * these with RMW based on a mask. The mask can be fixed or generated
+	 * during the calc/readout phase if the mask depends on some other HW
+	 * state like refclk, see icl_calc_mg_pll_state().
+	 */
+	val = I915_READ(MG_REFCLKIN_CTL(port));
+	val &= ~MG_REFCLKIN_CTL_OD_2_MUX_MASK;
+	val |= hw_state->mg_refclkin_ctl;
+	I915_WRITE(MG_REFCLKIN_CTL(port), val);
+
+	val = I915_READ(MG_CLKTOP2_CORECLKCTL1(port));
+	val &= ~MG_CLKTOP2_CORECLKCTL1_A_DIVRATIO_MASK;
+	val |= hw_state->mg_clktop2_coreclkctl1;
+	I915_WRITE(MG_CLKTOP2_CORECLKCTL1(port), val);
+
+	val = I915_READ(MG_CLKTOP2_HSCLKCTL(port));
+	val &= ~(MG_CLKTOP2_HSCLKCTL_TLINEDRV_CLKSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_CORE_INPUTSEL_MASK |
+		 MG_CLKTOP2_HSCLKCTL_HSDIV_RATIO_MASK |
+		 MG_CLKTOP2_HSCLKCTL_DSDIV_RATIO_MASK);
+	val |= hw_state->mg_clktop2_hsclkctl;
+	I915_WRITE(MG_CLKTOP2_HSCLKCTL(port), val);
+
 	I915_WRITE(MG_PLL_DIV0(port), hw_state->mg_pll_div0);
 	I915_WRITE(MG_PLL_DIV1(port), hw_state->mg_pll_div1);
 	I915_WRITE(MG_PLL_LF(port), hw_state->mg_pll_lf);
-- 
cgit v1.2.3


From 8d4f4b82155cc6774d0fd8aaafb882566f7fd5fb Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 15 Jun 2018 20:39:39 +0300
Subject: drm: Document mode_config.max_width/height as the max fb dimensions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The meaning of the mode_config max_width/height fields has not been
entirely clear. They are used both as the max framebuffer dimensions,
and they are also used by drm_mode_getconnector() to filter out
any mode whose hdisplay/vdisplay exceed those limits.

Let's put it in writing that max_width/height only refrer to the max
framebuffer dimensions, and should those be higher than the hardware
limits for display timings the driver must validate the latter using
some other means.

We'll keep the max_width/height usage in drm_mode_getconnector()
because setcrtc treats hdisplay/vdisplay also as the primary plane
width, and having a plane bigger than the max fb size doesn't make
much sense (if we ignore scaling that is). It all works out fine
as long as the max fb dimensions are at least equal to the max
timing limits. If the opposite were true we may want to rethink
what drm_mode_getconnector() does. Maybe do the mode filtering
only for non-atomic userspace?

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615173939.11353-1-ville.syrjala@linux.intel.com
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
---
 include/drm/drm_mode_config.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/drm/drm_mode_config.h b/include/drm/drm_mode_config.h
index f4a173c8d79c..a0b202e1d69a 100644
--- a/include/drm/drm_mode_config.h
+++ b/include/drm/drm_mode_config.h
@@ -329,10 +329,10 @@ struct drm_mode_config_funcs {
 
 /**
  * struct drm_mode_config - Mode configuration control structure
- * @min_width: minimum pixel width on this device
- * @min_height: minimum pixel height on this device
- * @max_width: maximum pixel width on this device
- * @max_height: maximum pixel height on this device
+ * @min_width: minimum fb pixel width on this device
+ * @min_height: minimum fb pixel height on this device
+ * @max_width: maximum fb pixel width on this device
+ * @max_height: maximum fb pixel height on this device
  * @funcs: core driver provided mode setting functions
  * @fb_base: base address of the framebuffer
  * @poll_enabled: track polling support for this device
-- 
cgit v1.2.3


From 75a040ff14d9a99fc041f5e1d8f09541cab13ba4 Mon Sep 17 00:00:00 2001
From: Alexey Dobriyan <adobriyan@gmail.com>
Date: Sun, 1 Apr 2018 01:00:36 +0300
Subject: locking/refcounts: Include fewer headers in <linux/refcount.h>

Debloat <linux/refcount.h>'s dependencies:

- <linux/kernel.h> is not needed, but <linux/compiler.h> is.
- <linux/mutex.h> is not needed, only a forward declaration of "struct mutex".
- <linux/spinlock.h> is not needed, <linux/spinlock_types.h> is enough.

Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Link: https://lkml.kernel.org/lkml/20180331220036.GA7676@avx2
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/refcount.h | 1 +
 include/linux/refcount.h        | 7 ++++---
 lib/refcount.c                  | 2 ++
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/refcount.h b/arch/x86/include/asm/refcount.h
index 4cf11d88d3b3..19b90521954c 100644
--- a/arch/x86/include/asm/refcount.h
+++ b/arch/x86/include/asm/refcount.h
@@ -5,6 +5,7 @@
  * PaX/grsecurity.
  */
 #include <linux/refcount.h>
+#include <asm/bug.h>
 
 /*
  * This is the first portion of the refcount error handling, which lives in
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 4193c41e383a..c36addd27dd5 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -3,9 +3,10 @@
 #define _LINUX_REFCOUNT_H
 
 #include <linux/atomic.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
+#include <linux/compiler.h>
+#include <linux/spinlock_types.h>
+
+struct mutex;
 
 /**
  * struct refcount_t - variant of atomic_t specialized for reference counts
diff --git a/lib/refcount.c b/lib/refcount.c
index 0eb48353abe3..4bd842f20749 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -35,7 +35,9 @@
  *
  */
 
+#include <linux/mutex.h>
 #include <linux/refcount.h>
+#include <linux/spinlock.h>
 #include <linux/bug.h>
 
 #ifdef CONFIG_REFCOUNT_FULL
-- 
cgit v1.2.3


From e16a375086337af3fcf21dbd512e1573049ba6cb Mon Sep 17 00:00:00 2001
From: Vandita Kulkarni <vandita.kulkarni@intel.com>
Date: Thu, 21 Jun 2018 20:43:56 +0530
Subject: drm/i915: Enable hw workaround to bypass alpha

Alpha blending with alpha 0 and 0xff passes through
alpha math and rounding logic causing differences
compared to fully transparent or opaque plane,resulting
in CRC mismatch.
This WA on icl and above enables hardware to bypass alpha
math and rounding for per pixel alpha values of 00 and 0xff

v2: Fix patchwork checkpatch warnings.

Signed-off-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1529594036-25036-1-git-send-email-vandita.kulkarni@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h      |  8 ++++++++
 drivers/gpu/drm/i915/intel_display.c | 12 ++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 65b222287ee4..caad19f5f557 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7366,6 +7366,14 @@ enum {
 #define BDW_SCRATCH1					_MMIO(0xb11c)
 #define  GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE	(1 << 2)
 
+/*GEN11 chicken */
+#define _PIPEA_CHICKEN			0x70038
+#define _PIPEB_CHICKEN			0x71038
+#define _PIPEC_CHICKEN			0x72038
+#define  PER_PIXEL_ALPHA_BYPASS_EN	(1 << 7)
+#define PIPE_CHICKEN(pipe)		_MMIO_PIPE(pipe, _PIPEA_CHICKEN,\
+						   _PIPEB_CHICKEN)
+
 /* PCH */
 
 /* south display engine interrupt: IBX */
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index b2a5a9ed9404..4db576c3e364 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5633,6 +5633,7 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	struct intel_atomic_state *old_intel_state =
 		to_intel_atomic_state(old_state);
 	bool psl_clkgate_wa;
+	u32 pipe_chicken;
 
 	if (WARN_ON(intel_crtc->active))
 		return;
@@ -5692,6 +5693,17 @@ static void haswell_crtc_enable(struct intel_crtc_state *pipe_config,
 	 */
 	intel_color_load_luts(&pipe_config->base);
 
+	/*
+	 * Display WA #1153: enable hardware to bypass the alpha math
+	 * and rounding for per-pixel values 00 and 0xff
+	 */
+	if (INTEL_GEN(dev_priv) >= 11) {
+		pipe_chicken = I915_READ(PIPE_CHICKEN(pipe));
+		if (!(pipe_chicken & PER_PIXEL_ALPHA_BYPASS_EN))
+			I915_WRITE_FW(PIPE_CHICKEN(pipe),
+				      pipe_chicken | PER_PIXEL_ALPHA_BYPASS_EN);
+	}
+
 	intel_ddi_set_pipe_settings(pipe_config);
 	if (!transcoder_is_dsi(cpu_transcoder))
 		intel_ddi_enable_transcoder_func(pipe_config);
-- 
cgit v1.2.3


From abd7dbe921bb2c12933551423de23dda2980c890 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Sat, 14 Apr 2018 21:53:21 +0530
Subject: gpu: drm: vc4: Adding new typedef vm_fault_t

Use new return type vm_fault_t for fault handler.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
---
 drivers/gpu/drm/vc4/vc4_bo.c  | 2 +-
 drivers/gpu/drm/vc4/vc4_drv.h | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_bo.c b/drivers/gpu/drm/vc4/vc4_bo.c
index add9cc97a3b6..8dcce7182bb7 100644
--- a/drivers/gpu/drm/vc4/vc4_bo.c
+++ b/drivers/gpu/drm/vc4/vc4_bo.c
@@ -721,7 +721,7 @@ vc4_prime_export(struct drm_device *dev, struct drm_gem_object *obj, int flags)
 	return dmabuf;
 }
 
-int vc4_fault(struct vm_fault *vmf)
+vm_fault_t vc4_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index 554a4e810d5b..eace76c621a1 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/mm_types.h>
 #include <linux/reservation.h>
 #include <drm/drmP.h>
 #include <drm/drm_encoder.h>
@@ -674,7 +675,7 @@ int vc4_get_hang_state_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
 int vc4_label_bo_ioctl(struct drm_device *dev, void *data,
 		       struct drm_file *file_priv);
-int vc4_fault(struct vm_fault *vmf);
+vm_fault_t vc4_fault(struct vm_fault *vmf);
 int vc4_mmap(struct file *filp, struct vm_area_struct *vma);
 struct reservation_object *vc4_prime_res_obj(struct drm_gem_object *obj);
 int vc4_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
-- 
cgit v1.2.3


From 6aa13402c11035a428d8c621b334734971d5d39d Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Wed, 6 Jun 2018 12:04:29 -0700
Subject: drm/bridge: Move the struct drm_bridge member kerneldoc inline.

This makes it more likely that the docs stay updated with the code.

Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180606190431.1833-1-eric@anholt.net
Reviewed-by: Andrzej Hajda <a.hajda@samsung.com>
---
 include/drm/drm_bridge.h | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/include/drm/drm_bridge.h b/include/drm/drm_bridge.h
index 70131ab57e8f..bd850747ce54 100644
--- a/include/drm/drm_bridge.h
+++ b/include/drm/drm_bridge.h
@@ -270,27 +270,29 @@ struct drm_bridge_timings {
 
 /**
  * struct drm_bridge - central DRM bridge control structure
- * @dev: DRM device this bridge belongs to
- * @encoder: encoder to which this bridge is connected
- * @next: the next bridge in the encoder chain
- * @of_node: device node pointer to the bridge
- * @list: to keep track of all added bridges
- * @timings: the timing specification for the bridge, if any (may
- * be NULL)
- * @funcs: control functions
- * @driver_private: pointer to the bridge driver's internal context
  */
 struct drm_bridge {
+	/** @dev: DRM device this bridge belongs to */
 	struct drm_device *dev;
+	/** @encoder: encoder to which this bridge is connected */
 	struct drm_encoder *encoder;
+	/** @next: the next bridge in the encoder chain */
 	struct drm_bridge *next;
 #ifdef CONFIG_OF
+	/** @of_node: device node pointer to the bridge */
 	struct device_node *of_node;
 #endif
+	/** @list: to keep track of all added bridges */
 	struct list_head list;
+	/**
+	 * @timings:
+	 *
+	 * the timing specification for the bridge, if any (may be NULL)
+	 */
 	const struct drm_bridge_timings *timings;
-
+	/** @funcs: control functions */
 	const struct drm_bridge_funcs *funcs;
+	/** @driver_private: pointer to the bridge driver's internal context */
 	void *driver_private;
 };
 
-- 
cgit v1.2.3


From 7122b68b8a9692dcc3acf89595f04c492872115f Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Wed, 6 Jun 2018 10:48:51 -0700
Subject: drm/v3d: Take a lock across GPU scheduler job creation and queuing.

Between creation and queueing of a job, you need to prevent any other
job from being created and queued.  Otherwise the scheduler's fences
may be signaled out of seqno order.

v2: move mutex unlock to the error label.

Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: 57692c94dcbe ("drm/v3d: Introduce a new DRM driver for Broadcom V3D V3.x+")
Link: https://patchwork.freedesktop.org/patch/msgid/20180606174851.12433-1-eric@anholt.net
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
---
 drivers/gpu/drm/v3d/v3d_drv.h | 5 +++++
 drivers/gpu/drm/v3d/v3d_gem.c | 4 ++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index a043ac3aae98..26005abd9c5d 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -85,6 +85,11 @@ struct v3d_dev {
 	 */
 	struct mutex reset_lock;
 
+	/* Lock taken when creating and pushing the GPU scheduler
+	 * jobs, to keep the sched-fence seqnos in order.
+	 */
+	struct mutex sched_lock;
+
 	struct {
 		u32 num_allocated;
 		u32 pages_allocated;
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index b513f9189caf..269fe16379c0 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -550,6 +550,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	if (ret)
 		goto fail;
 
+	mutex_lock(&v3d->sched_lock);
 	if (exec->bin.start != exec->bin.end) {
 		ret = drm_sched_job_init(&exec->bin.base,
 					 &v3d->queue[V3D_BIN].sched,
@@ -576,6 +577,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	kref_get(&exec->refcount); /* put by scheduler job completion */
 	drm_sched_entity_push_job(&exec->render.base,
 				  &v3d_priv->sched_entity[V3D_RENDER]);
+	mutex_unlock(&v3d->sched_lock);
 
 	v3d_attach_object_fences(exec);
 
@@ -594,6 +596,7 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	return 0;
 
 fail_unreserve:
+	mutex_unlock(&v3d->sched_lock);
 	v3d_unlock_bo_reservations(dev, exec, &acquire_ctx);
 fail:
 	v3d_exec_put(exec);
@@ -615,6 +618,7 @@ v3d_gem_init(struct drm_device *dev)
 	spin_lock_init(&v3d->job_lock);
 	mutex_init(&v3d->bo_lock);
 	mutex_init(&v3d->reset_lock);
+	mutex_init(&v3d->sched_lock);
 
 	/* Note: We don't allocate address 0.  Various bits of HW
 	 * treat 0 as special, such as the occlusion query counters
-- 
cgit v1.2.3


From 14d1d190869685d3a1e8a3f63924e20594557cb2 Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Tue, 5 Jun 2018 12:03:01 -0700
Subject: drm/v3d: Remove the bad signaled() implementation.

Since our seqno value comes from a counter associated with the GPU
ring, not the entity (aka client), they'll be completed out of order.
There's actually no need for this code at all, since we don't have
enable_signaling() and thus DMA_FENCE_SIGNALED_BIT will be set before
we could be called.

Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605190302.18279-2-eric@anholt.net
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
---
 drivers/gpu/drm/v3d/v3d_drv.h   |  1 -
 drivers/gpu/drm/v3d/v3d_fence.c | 13 ++++---------
 drivers/gpu/drm/v3d/v3d_gem.c   |  7 ++-----
 drivers/gpu/drm/v3d/v3d_irq.c   |  3 ---
 4 files changed, 6 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 26005abd9c5d..f32ac8c98f37 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -25,7 +25,6 @@ struct v3d_queue_state {
 
 	u64 fence_context;
 	u64 emit_seqno;
-	u64 finished_seqno;
 };
 
 struct v3d_dev {
diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index 087d49c8cb12..bfe31a89668b 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -40,19 +40,14 @@ static bool v3d_fence_enable_signaling(struct dma_fence *fence)
 	return true;
 }
 
-static bool v3d_fence_signaled(struct dma_fence *fence)
-{
-	struct v3d_fence *f = to_v3d_fence(fence);
-	struct v3d_dev *v3d = to_v3d_dev(f->dev);
-
-	return v3d->queue[f->queue].finished_seqno >= f->seqno;
-}
-
 const struct dma_fence_ops v3d_fence_ops = {
 	.get_driver_name = v3d_fence_get_driver_name,
 	.get_timeline_name = v3d_fence_get_timeline_name,
 	.enable_signaling = v3d_fence_enable_signaling,
-	.signaled = v3d_fence_signaled,
+	/* Each of our fences gets signaled as complete by the IRQ
+	 * handler, so we rely on the core's tracking of signaling.
+	 */
+	.signaled = NULL,
 	.wait = dma_fence_default_wait,
 	.release = dma_fence_free,
 };
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index 269fe16379c0..e1fcbb4cd0ae 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -654,17 +654,14 @@ void
 v3d_gem_destroy(struct drm_device *dev)
 {
 	struct v3d_dev *v3d = to_v3d_dev(dev);
-	enum v3d_queue q;
 
 	v3d_sched_fini(v3d);
 
 	/* Waiting for exec to finish would need to be done before
 	 * unregistering V3D.
 	 */
-	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		WARN_ON(v3d->queue[q].emit_seqno !=
-			v3d->queue[q].finished_seqno);
-	}
+	WARN_ON(v3d->bin_job);
+	WARN_ON(v3d->render_job);
 
 	drm_mm_takedown(&v3d->mm);
 
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index 77e1fa046c10..e07514eb11b5 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -87,15 +87,12 @@ v3d_irq(int irq, void *arg)
 	}
 
 	if (intsts & V3D_INT_FLDONE) {
-		v3d->queue[V3D_BIN].finished_seqno++;
 		dma_fence_signal(v3d->bin_job->bin.done_fence);
 		status = IRQ_HANDLED;
 	}
 
 	if (intsts & V3D_INT_FRDONE) {
-		v3d->queue[V3D_RENDER].finished_seqno++;
 		dma_fence_signal(v3d->render_job->render.done_fence);
-
 		status = IRQ_HANDLED;
 	}
 
-- 
cgit v1.2.3


From 38ebbe2b7282e985a7acc862892564e8fbbde866 Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Wed, 9 May 2018 18:11:20 +0300
Subject: mtd: spi-nor: nxp-spifi: release flash_np in nxp_spifi_probe()

nxp_spifi_probe() increments refcnt of SPI flash device node by
of_get_next_available_child() and leaves it undecremented on both
successful and error paths.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/spi-nor/nxp-spifi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mtd/spi-nor/nxp-spifi.c b/drivers/mtd/spi-nor/nxp-spifi.c
index 15374216d4d9..0c9094ec5966 100644
--- a/drivers/mtd/spi-nor/nxp-spifi.c
+++ b/drivers/mtd/spi-nor/nxp-spifi.c
@@ -436,6 +436,7 @@ static int nxp_spifi_probe(struct platform_device *pdev)
 	}
 
 	ret = nxp_spifi_setup_flash(spifi, flash_np);
+	of_node_put(flash_np);
 	if (ret) {
 		dev_err(&pdev->dev, "unable to setup flash chip\n");
 		goto dis_clks;
-- 
cgit v1.2.3


From 02361bc7788852f33dd0a05235a52b9ccf097916 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 31 May 2018 11:45:25 -0700
Subject: lib/bch: Remove VLA usage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the quest to remove all stack VLA usage from the kernel[1], this
allocates a fixed size stack array to cover the range needed for
bch. This was done instead of a preallocation on the SLAB due to
performance reasons, shown by Ivan Djelic:

 little-endian, type sizes: int=4 long=8 longlong=8
 cpu: Intel(R) Core(TM) i5 CPU         650  @ 3.20GHz
 calibration: iter=4.9143µs niter=2034 nsamples=200 m=13 t=4

   Buffer allocation |  Encoding throughput (Mbit/s)
 ---------------------------------------------------
  on-stack, VLA      |   3988
  on-stack, fixed    |   4494
  kmalloc            |   1967

So this change actually improves performance too, it seems.

The resulting stack allocation can get rather large; without
CONFIG_BCH_CONST_PARAMS, it will allocate 4096 bytes, which
trips the stack size checking:

lib/bch.c: In function ‘encode_bch’:
lib/bch.c:261:1: warning: the frame size of 4432 bytes is larger than 2048 bytes [-Wframe-larger-than=]

Even the default case for "allmodconfig" (with CONFIG_BCH_CONST_M=14 and
CONFIG_BCH_CONST_T=4) would have started throwing a warning:

lib/bch.c: In function ‘encode_bch’:
lib/bch.c:261:1: warning: the frame size of 2288 bytes is larger than 2048 bytes [-Wframe-larger-than=]

But this is how large it's always been; it was just hidden from
the checker because it was a VLA. So the Makefile has been adjusted to
silence this warning for anything smaller than 4500 bytes, which should
provide room for normal cases, but still low enough to catch any future
pathological situations.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Ivan Djelic <ivan.djelic@parrot.com>
Tested-by: Ivan Djelic <ivan.djelic@parrot.com>
Acked-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 lib/Makefile |  1 +
 lib/bch.c    | 23 +++++++++++++++--------
 2 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/lib/Makefile b/lib/Makefile
index 956b320292fe..e1ee1046abf0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -123,6 +123,7 @@ obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
 obj-$(CONFIG_BCH) += bch.o
+CFLAGS_bch.o := $(call cc-option,-Wframe-larger-than=4500)
 obj-$(CONFIG_LZO_COMPRESS) += lzo/
 obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
 obj-$(CONFIG_LZ4_COMPRESS) += lz4/
diff --git a/lib/bch.c b/lib/bch.c
index bc89dfe4d1b3..7b0f2006698b 100644
--- a/lib/bch.c
+++ b/lib/bch.c
@@ -78,15 +78,22 @@
 #define GF_M(_p)               (CONFIG_BCH_CONST_M)
 #define GF_T(_p)               (CONFIG_BCH_CONST_T)
 #define GF_N(_p)               ((1 << (CONFIG_BCH_CONST_M))-1)
+#define BCH_MAX_M              (CONFIG_BCH_CONST_M)
 #else
 #define GF_M(_p)               ((_p)->m)
 #define GF_T(_p)               ((_p)->t)
 #define GF_N(_p)               ((_p)->n)
+#define BCH_MAX_M              15
 #endif
 
+#define BCH_MAX_T              (((1 << BCH_MAX_M) - 1) / BCH_MAX_M)
+
 #define BCH_ECC_WORDS(_p)      DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 32)
 #define BCH_ECC_BYTES(_p)      DIV_ROUND_UP(GF_M(_p)*GF_T(_p), 8)
 
+#define BCH_ECC_MAX_WORDS      DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 32)
+#define BCH_ECC_MAX_BYTES      DIV_ROUND_UP(BCH_MAX_M * BCH_MAX_T, 8)
+
 #ifndef dbg
 #define dbg(_fmt, args...)     do {} while (0)
 #endif
@@ -187,7 +194,8 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	const unsigned int l = BCH_ECC_WORDS(bch)-1;
 	unsigned int i, mlen;
 	unsigned long m;
-	uint32_t w, r[l+1];
+	uint32_t w, r[BCH_ECC_MAX_WORDS];
+	const size_t r_bytes = BCH_ECC_WORDS(bch) * sizeof(*r);
 	const uint32_t * const tab0 = bch->mod8_tab;
 	const uint32_t * const tab1 = tab0 + 256*(l+1);
 	const uint32_t * const tab2 = tab1 + 256*(l+1);
@@ -198,7 +206,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 		/* load ecc parity bytes into internal 32-bit buffer */
 		load_ecc8(bch, bch->ecc_buf, ecc);
 	} else {
-		memset(bch->ecc_buf, 0, sizeof(r));
+		memset(bch->ecc_buf, 0, r_bytes);
 	}
 
 	/* process first unaligned data bytes */
@@ -215,7 +223,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 	mlen  = len/4;
 	data += 4*mlen;
 	len  -= 4*mlen;
-	memcpy(r, bch->ecc_buf, sizeof(r));
+	memcpy(r, bch->ecc_buf, r_bytes);
 
 	/*
 	 * split each 32-bit word into 4 polynomials of weight 8 as follows:
@@ -241,7 +249,7 @@ void encode_bch(struct bch_control *bch, const uint8_t *data,
 
 		r[l] = p0[l]^p1[l]^p2[l]^p3[l];
 	}
-	memcpy(bch->ecc_buf, r, sizeof(r));
+	memcpy(bch->ecc_buf, r, r_bytes);
 
 	/* process last unaligned bytes */
 	if (len)
@@ -434,7 +442,7 @@ static int solve_linear_system(struct bch_control *bch, unsigned int *rows,
 {
 	const int m = GF_M(bch);
 	unsigned int tmp, mask;
-	int rem, c, r, p, k, param[m];
+	int rem, c, r, p, k, param[BCH_MAX_M];
 
 	k = 0;
 	mask = 1 << m;
@@ -1114,7 +1122,7 @@ static int build_deg2_base(struct bch_control *bch)
 {
 	const int m = GF_M(bch);
 	int i, j, r;
-	unsigned int sum, x, y, remaining, ak = 0, xi[m];
+	unsigned int sum, x, y, remaining, ak = 0, xi[BCH_MAX_M];
 
 	/* find k s.t. Tr(a^k) = 1 and 0 <= k < m */
 	for (i = 0; i < m; i++) {
@@ -1254,7 +1262,6 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 	struct bch_control *bch = NULL;
 
 	const int min_m = 5;
-	const int max_m = 15;
 
 	/* default primitive polynomials */
 	static const unsigned int prim_poly_tab[] = {
@@ -1270,7 +1277,7 @@ struct bch_control *init_bch(int m, int t, unsigned int prim_poly)
 		goto fail;
 	}
 #endif
-	if ((m < min_m) || (m > max_m))
+	if ((m < min_m) || (m > BCH_MAX_M))
 		/*
 		 * values of m greater than 15 are not currently supported;
 		 * supporting m > 15 would require changing table base type
-- 
cgit v1.2.3


From a38b80c5f49c30c3cbd4523bdbde0cc725bb0e63 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Wed, 20 Jun 2018 23:55:07 +0530
Subject: scsi: cxlflash: Change return type for fault handler

Use new return type vm_fault_t for fault handler. For now, this is just
documenting that the function returns a VM_FAULT value rather than an
errno. Once all instances are converted, vm_fault_t will become a distinct
type.

Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Previously, VM_FAULT_NOPAGE was returned without verifying return value of
vm_insert_pfn. The new inline vmf_insert_pfn() will address this issue by
returning correct VM_FAULT_* type from fault handler.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Acked-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/cxlflash/ocxl_hw.c   | 5 ++---
 drivers/scsi/cxlflash/superpipe.c | 6 +++---
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 0a95b5f25380..91178ff4d13b 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -1158,7 +1158,7 @@ static int afu_release(struct inode *inode, struct file *file)
  *
  * Return: 0 on success, -errno on failure
  */
-static int ocxlflash_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t ocxlflash_mmap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct ocxlflash_context *ctx = vma->vm_file->private_data;
@@ -1181,8 +1181,7 @@ static int ocxlflash_mmap_fault(struct vm_fault *vmf)
 	mmio_area = ctx->psn_phys;
 	mmio_area += offset;
 
-	vm_insert_pfn(vma, vmf->address, mmio_area >> PAGE_SHIFT);
-	return VM_FAULT_NOPAGE;
+	return vmf_insert_pfn(vma, vmf->address, mmio_area >> PAGE_SHIFT);
 }
 
 static const struct vm_operations_struct ocxlflash_vmops = {
diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index e489d89cbb45..eee193e2db91 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -1108,7 +1108,7 @@ out:
  *
  * Return: 0 on success, VM_FAULT_SIGBUS on failure
  */
-static int cxlflash_mmap_fault(struct vm_fault *vmf)
+static vm_fault_t cxlflash_mmap_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct file *file = vma->vm_file;
@@ -1119,7 +1119,7 @@ static int cxlflash_mmap_fault(struct vm_fault *vmf)
 	struct ctx_info *ctxi = NULL;
 	struct page *err_page = NULL;
 	enum ctx_ctrl ctrl = CTX_CTRL_ERR_FALLBACK | CTX_CTRL_FILE;
-	int rc = 0;
+	vm_fault_t rc = 0;
 	int ctxid;
 
 	ctxid = cfg->ops->process_element(ctx);
@@ -1159,7 +1159,7 @@ static int cxlflash_mmap_fault(struct vm_fault *vmf)
 out:
 	if (likely(ctxi))
 		put_context(ctxi);
-	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
+	dev_dbg(dev, "%s: returning rc=%x\n", __func__, rc);
 	return rc;
 
 err:
-- 
cgit v1.2.3


From cbab901296232b1247b46e6e127103d2f738d783 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 12:52:50 +1000
Subject: rhashtable: silence RCU warning in rhashtable_test.

print_ht in rhashtable_test calls rht_dereference() with neither
RCU protection or the mutex.  This triggers an RCU warning.
So take the mutex to silence the warning.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/test_rhashtable.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index fb6968109113..6ca59ffcacbe 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -501,6 +501,8 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
 	unsigned int i, cnt = 0;
 
 	ht = &rhlt->ht;
+	/* Take the mutex to avoid RCU warning */
+	mutex_lock(&ht->mutex);
 	tbl = rht_dereference(ht->tbl, ht);
 	for (i = 0; i < tbl->size; i++) {
 		struct rhash_head *pos, *next;
@@ -534,6 +536,7 @@ static unsigned int __init print_ht(struct rhltable *rhlt)
 		}
 	}
 	printk(KERN_ERR "\n---- ht: ----%s\n-------------\n", buff);
+	mutex_unlock(&ht->mutex);
 
 	return cnt;
 }
-- 
cgit v1.2.3


From 0eb71a9da5796851fa87ddc1a534066c0fe54055 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 12:52:50 +1000
Subject: rhashtable: split rhashtable.h

Due to the use of rhashtables in net namespaces,
rhashtable.h is included in lots of the kernel,
so a small changes can required a large recompilation.
This makes development painful.

This patch splits out rhashtable-types.h which just includes
the major type declarations, and does not include (non-trivial)
inline code.  rhashtable.h is no longer included by anything
in the include/ directory.
Common include files only include rhashtable-types.h so a large
recompilation is only triggered when that changes.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                                |   2 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h |   1 +
 include/linux/ipc.h                        |   2 +-
 include/linux/ipc_namespace.h              |   2 +-
 include/linux/mroute_base.h                |   2 +-
 include/linux/rhashtable-types.h           | 139 +++++++++++++++++++++++++++++
 include/linux/rhashtable.h                 | 127 +-------------------------
 include/net/inet_frag.h                    |   2 +-
 include/net/netfilter/nf_flow_table.h      |   2 +-
 include/net/sctp/structs.h                 |   2 +-
 include/net/seg6.h                         |   2 +-
 include/net/seg6_hmac.h                    |   2 +-
 ipc/msg.c                                  |   1 +
 ipc/sem.c                                  |   1 +
 ipc/shm.c                                  |   1 +
 ipc/util.c                                 |   1 +
 lib/rhashtable.c                           |   1 +
 net/ipv4/inet_fragment.c                   |   1 +
 net/ipv4/ipmr.c                            |   1 +
 net/ipv4/ipmr_base.c                       |   1 +
 net/ipv6/ip6mr.c                           |   1 +
 net/ipv6/seg6.c                            |   1 +
 net/ipv6/seg6_hmac.c                       |   1 +
 net/netfilter/nf_tables_api.c              |   1 +
 net/sctp/input.c                           |   1 +
 net/sctp/socket.c                          |   1 +
 26 files changed, 166 insertions(+), 133 deletions(-)
 create mode 100644 include/linux/rhashtable-types.h

diff --git a/MAINTAINERS b/MAINTAINERS
index edf3cf5ea691..99e5cef8172e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12162,7 +12162,9 @@ M:	Herbert Xu <herbert@gondor.apana.org.au>
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	lib/rhashtable.c
+F:	lib/test_rhashtable.c
 F:	include/linux/rhashtable.h
+F:	include/linux/rhashtable-types.h
 
 RICOH R5C592 MEMORYSTICK DRIVER
 M:	Maxim Levitsky <maximlevitsky@gmail.com>
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 0dbe2d9e22d6..1adb968b8354 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -46,6 +46,7 @@
 #include <linux/spinlock.h>
 #include <linux/timer.h>
 #include <linux/vmalloc.h>
+#include <linux/rhashtable.h>
 #include <linux/etherdevice.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_clock_kernel.h>
diff --git a/include/linux/ipc.h b/include/linux/ipc.h
index 6cc2df7f7ac9..e1c9eea6015b 100644
--- a/include/linux/ipc.h
+++ b/include/linux/ipc.h
@@ -4,7 +4,7 @@
 
 #include <linux/spinlock.h>
 #include <linux/uidgid.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 #include <uapi/linux/ipc.h>
 #include <linux/refcount.h>
 
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index b5630c8eb2f3..6cea726612b7 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -9,7 +9,7 @@
 #include <linux/nsproxy.h>
 #include <linux/ns_common.h>
 #include <linux/refcount.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 
 struct user_namespace;
 
diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index d633f737b3c6..fd436cdd4725 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -2,7 +2,7 @@
 #define __LINUX_MROUTE_BASE_H
 
 #include <linux/netdevice.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 #include <linux/spinlock.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h
new file mode 100644
index 000000000000..9740063ff13b
--- /dev/null
+++ b/include/linux/rhashtable-types.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Resizable, Scalable, Concurrent Hash Table
+ *
+ * Simple structures that might be needed in include
+ * files.
+ */
+
+#ifndef _LINUX_RHASHTABLE_TYPES_H
+#define _LINUX_RHASHTABLE_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/compiler.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+
+struct rhash_head {
+	struct rhash_head __rcu		*next;
+};
+
+struct rhlist_head {
+	struct rhash_head		rhead;
+	struct rhlist_head __rcu	*next;
+};
+
+struct bucket_table;
+
+/**
+ * struct rhashtable_compare_arg - Key for the function rhashtable_compare
+ * @ht: Hash table
+ * @key: Key to compare against
+ */
+struct rhashtable_compare_arg {
+	struct rhashtable *ht;
+	const void *key;
+};
+
+typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
+typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed);
+typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
+			       const void *obj);
+
+/**
+ * struct rhashtable_params - Hash table construction parameters
+ * @nelem_hint: Hint on number of elements, should be 75% of desired size
+ * @key_len: Length of key
+ * @key_offset: Offset of key in struct to be hashed
+ * @head_offset: Offset of rhash_head in struct to be hashed
+ * @max_size: Maximum size while expanding
+ * @min_size: Minimum size while shrinking
+ * @locks_mul: Number of bucket locks to allocate per cpu (default: 32)
+ * @automatic_shrinking: Enable automatic shrinking of tables
+ * @nulls_base: Base value to generate nulls marker
+ * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
+ * @obj_hashfn: Function to hash object
+ * @obj_cmpfn: Function to compare key with object
+ */
+struct rhashtable_params {
+	u16			nelem_hint;
+	u16			key_len;
+	u16			key_offset;
+	u16			head_offset;
+	unsigned int		max_size;
+	u16			min_size;
+	bool			automatic_shrinking;
+	u8			locks_mul;
+	u32			nulls_base;
+	rht_hashfn_t		hashfn;
+	rht_obj_hashfn_t	obj_hashfn;
+	rht_obj_cmpfn_t		obj_cmpfn;
+};
+
+/**
+ * struct rhashtable - Hash table handle
+ * @tbl: Bucket table
+ * @key_len: Key length for hashfn
+ * @max_elems: Maximum number of elements in table
+ * @p: Configuration parameters
+ * @rhlist: True if this is an rhltable
+ * @run_work: Deferred worker to expand/shrink asynchronously
+ * @mutex: Mutex to protect current/future table swapping
+ * @lock: Spin lock to protect walker list
+ * @nelems: Number of elements in table
+ */
+struct rhashtable {
+	struct bucket_table __rcu	*tbl;
+	unsigned int			key_len;
+	unsigned int			max_elems;
+	struct rhashtable_params	p;
+	bool				rhlist;
+	struct work_struct		run_work;
+	struct mutex                    mutex;
+	spinlock_t			lock;
+	atomic_t			nelems;
+};
+
+/**
+ * struct rhltable - Hash table with duplicate objects in a list
+ * @ht: Underlying rhtable
+ */
+struct rhltable {
+	struct rhashtable ht;
+};
+
+/**
+ * struct rhashtable_walker - Hash table walker
+ * @list: List entry on list of walkers
+ * @tbl: The table that we were walking over
+ */
+struct rhashtable_walker {
+	struct list_head list;
+	struct bucket_table *tbl;
+};
+
+/**
+ * struct rhashtable_iter - Hash table iterator
+ * @ht: Table to iterate through
+ * @p: Current pointer
+ * @list: Current hash list pointer
+ * @walker: Associated rhashtable walker
+ * @slot: Current slot
+ * @skip: Number of entries to skip in slot
+ */
+struct rhashtable_iter {
+	struct rhashtable *ht;
+	struct rhash_head *p;
+	struct rhlist_head *list;
+	struct rhashtable_walker walker;
+	unsigned int slot;
+	unsigned int skip;
+	bool end_of_table;
+};
+
+int rhashtable_init(struct rhashtable *ht,
+		    const struct rhashtable_params *params);
+int rhltable_init(struct rhltable *hlt,
+		  const struct rhashtable_params *params);
+
+#endif /* _LINUX_RHASHTABLE_TYPES_H */
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 4e1f535c2034..48754ab07cdf 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Resizable, Scalable, Concurrent Hash Table
  *
@@ -17,16 +18,14 @@
 #ifndef _LINUX_RHASHTABLE_H
 #define _LINUX_RHASHTABLE_H
 
-#include <linux/atomic.h>
-#include <linux/compiler.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/jhash.h>
 #include <linux/list_nulls.h>
 #include <linux/workqueue.h>
-#include <linux/mutex.h>
 #include <linux/rculist.h>
 
+#include <linux/rhashtable-types.h>
 /*
  * The end of the chain is marked with a special nulls marks which has
  * the following format:
@@ -64,15 +63,6 @@
  */
 #define RHT_ELASTICITY	16u
 
-struct rhash_head {
-	struct rhash_head __rcu		*next;
-};
-
-struct rhlist_head {
-	struct rhash_head		rhead;
-	struct rhlist_head __rcu	*next;
-};
-
 /**
  * struct bucket_table - Table of hash buckets
  * @size: Number of hash buckets
@@ -102,114 +92,6 @@ struct bucket_table {
 	struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
-/**
- * struct rhashtable_compare_arg - Key for the function rhashtable_compare
- * @ht: Hash table
- * @key: Key to compare against
- */
-struct rhashtable_compare_arg {
-	struct rhashtable *ht;
-	const void *key;
-};
-
-typedef u32 (*rht_hashfn_t)(const void *data, u32 len, u32 seed);
-typedef u32 (*rht_obj_hashfn_t)(const void *data, u32 len, u32 seed);
-typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
-			       const void *obj);
-
-struct rhashtable;
-
-/**
- * struct rhashtable_params - Hash table construction parameters
- * @nelem_hint: Hint on number of elements, should be 75% of desired size
- * @key_len: Length of key
- * @key_offset: Offset of key in struct to be hashed
- * @head_offset: Offset of rhash_head in struct to be hashed
- * @max_size: Maximum size while expanding
- * @min_size: Minimum size while shrinking
- * @locks_mul: Number of bucket locks to allocate per cpu (default: 32)
- * @automatic_shrinking: Enable automatic shrinking of tables
- * @nulls_base: Base value to generate nulls marker
- * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
- * @obj_hashfn: Function to hash object
- * @obj_cmpfn: Function to compare key with object
- */
-struct rhashtable_params {
-	u16			nelem_hint;
-	u16			key_len;
-	u16			key_offset;
-	u16			head_offset;
-	unsigned int		max_size;
-	u16			min_size;
-	bool			automatic_shrinking;
-	u8			locks_mul;
-	u32			nulls_base;
-	rht_hashfn_t		hashfn;
-	rht_obj_hashfn_t	obj_hashfn;
-	rht_obj_cmpfn_t		obj_cmpfn;
-};
-
-/**
- * struct rhashtable - Hash table handle
- * @tbl: Bucket table
- * @key_len: Key length for hashfn
- * @max_elems: Maximum number of elements in table
- * @p: Configuration parameters
- * @rhlist: True if this is an rhltable
- * @run_work: Deferred worker to expand/shrink asynchronously
- * @mutex: Mutex to protect current/future table swapping
- * @lock: Spin lock to protect walker list
- * @nelems: Number of elements in table
- */
-struct rhashtable {
-	struct bucket_table __rcu	*tbl;
-	unsigned int			key_len;
-	unsigned int			max_elems;
-	struct rhashtable_params	p;
-	bool				rhlist;
-	struct work_struct		run_work;
-	struct mutex                    mutex;
-	spinlock_t			lock;
-	atomic_t			nelems;
-};
-
-/**
- * struct rhltable - Hash table with duplicate objects in a list
- * @ht: Underlying rhtable
- */
-struct rhltable {
-	struct rhashtable ht;
-};
-
-/**
- * struct rhashtable_walker - Hash table walker
- * @list: List entry on list of walkers
- * @tbl: The table that we were walking over
- */
-struct rhashtable_walker {
-	struct list_head list;
-	struct bucket_table *tbl;
-};
-
-/**
- * struct rhashtable_iter - Hash table iterator
- * @ht: Table to iterate through
- * @p: Current pointer
- * @list: Current hash list pointer
- * @walker: Associated rhashtable walker
- * @slot: Current slot
- * @skip: Number of entries to skip in slot
- */
-struct rhashtable_iter {
-	struct rhashtable *ht;
-	struct rhash_head *p;
-	struct rhlist_head *list;
-	struct rhashtable_walker walker;
-	unsigned int slot;
-	unsigned int skip;
-	bool end_of_table;
-};
-
 static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash)
 {
 	return NULLS_MARKER(ht->p.nulls_base + hash);
@@ -376,11 +258,6 @@ static inline int lockdep_rht_bucket_is_held(const struct bucket_table *tbl,
 }
 #endif /* CONFIG_PROVE_LOCKING */
 
-int rhashtable_init(struct rhashtable *ht,
-		    const struct rhashtable_params *params);
-int rhltable_init(struct rhltable *hlt,
-		  const struct rhashtable_params *params);
-
 void *rhashtable_insert_slow(struct rhashtable *ht, const void *key,
 			     struct rhash_head *obj);
 
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index ed07e3786d98..f4272a29dc44 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -2,7 +2,7 @@
 #ifndef __NET_FRAG_H__
 #define __NET_FRAG_H__
 
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 
 struct netns_frags {
 	/* sysctls */
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index ba9fa4592f2b..0e355f4a3d76 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -4,7 +4,7 @@
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/netdevice.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 #include <linux/rcupdate.h>
 #include <linux/netfilter/nf_conntrack_tuple_common.h>
 #include <net/dst.h>
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index dbe1b911a24d..e0f962d27386 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -48,7 +48,7 @@
 #define __sctp_structs_h__
 
 #include <linux/ktime.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 #include <linux/socket.h>	/* linux/in.h needs this!!    */
 #include <linux/in.h>		/* We get struct sockaddr_in. */
 #include <linux/in6.h>		/* We get struct in6_addr     */
diff --git a/include/net/seg6.h b/include/net/seg6.h
index e029e301faa5..2567941a2f32 100644
--- a/include/net/seg6.h
+++ b/include/net/seg6.h
@@ -18,7 +18,7 @@
 #include <linux/ipv6.h>
 #include <net/lwtunnel.h>
 #include <linux/seg6.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 
 static inline void update_csum_diff4(struct sk_buff *skb, __be32 from,
 				     __be32 to)
diff --git a/include/net/seg6_hmac.h b/include/net/seg6_hmac.h
index 69c3a106056b..7fda469e2758 100644
--- a/include/net/seg6_hmac.h
+++ b/include/net/seg6_hmac.h
@@ -22,7 +22,7 @@
 #include <linux/route.h>
 #include <net/seg6.h>
 #include <linux/seg6_hmac.h>
-#include <linux/rhashtable.h>
+#include <linux/rhashtable-types.h>
 
 #define SEG6_HMAC_MAX_DIGESTSIZE	160
 #define SEG6_HMAC_RING_SIZE		256
diff --git a/ipc/msg.c b/ipc/msg.c
index 3b6545302598..203281198079 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -38,6 +38,7 @@
 #include <linux/rwsem.h>
 #include <linux/nsproxy.h>
 #include <linux/ipc_namespace.h>
+#include <linux/rhashtable.h>
 
 #include <asm/current.h>
 #include <linux/uaccess.h>
diff --git a/ipc/sem.c b/ipc/sem.c
index 5af1943ad782..29c0347ef11d 100644
--- a/ipc/sem.c
+++ b/ipc/sem.c
@@ -86,6 +86,7 @@
 #include <linux/ipc_namespace.h>
 #include <linux/sched/wake_q.h>
 #include <linux/nospec.h>
+#include <linux/rhashtable.h>
 
 #include <linux/uaccess.h>
 #include "util.h"
diff --git a/ipc/shm.c b/ipc/shm.c
index 051a3e1fb8df..d4daf78df6da 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -43,6 +43,7 @@
 #include <linux/nsproxy.h>
 #include <linux/mount.h>
 #include <linux/ipc_namespace.h>
+#include <linux/rhashtable.h>
 
 #include <linux/uaccess.h>
 
diff --git a/ipc/util.c b/ipc/util.c
index 4e81182fa0ac..fdffff41f65b 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -63,6 +63,7 @@
 #include <linux/rwsem.h>
 #include <linux/memory.h>
 #include <linux/ipc_namespace.h>
+#include <linux/rhashtable.h>
 
 #include <asm/unistd.h>
 
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 9427b5766134..c9fafea7dc6e 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -28,6 +28,7 @@
 #include <linux/rhashtable.h>
 #include <linux/err.h>
 #include <linux/export.h>
+#include <linux/rhashtable.h>
 
 #define HASH_DEFAULT_SIZE	64UL
 #define HASH_MIN_SIZE		4U
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index c9e35b81d093..316518f87294 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -20,6 +20,7 @@
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
 #include <linux/slab.h>
+#include <linux/rhashtable.h>
 
 #include <net/sock.h>
 #include <net/inet_frag.h>
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9f79b9803a16..82f914122f1b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -60,6 +60,7 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/compat.h>
 #include <linux/export.h>
+#include <linux/rhashtable.h>
 #include <net/ip_tunnels.h>
 #include <net/checksum.h>
 #include <net/netlink.h>
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index cafb0506c8c9..1ad9aa62a97b 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -2,6 +2,7 @@
  * Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation
  */
 
+#include <linux/rhashtable.h>
 #include <linux/mroute_base.h>
 
 /* Sets everything common except 'dev', since that is done under locking */
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 0d0f0053bb11..d0b7e0249c13 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -32,6 +32,7 @@
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/compat.h>
+#include <linux/rhashtable.h>
 #include <net/protocol.h>
 #include <linux/skbuff.h>
 #include <net/raw.h>
diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c
index 0fdf2a55e746..8d0ba757a46c 100644
--- a/net/ipv6/seg6.c
+++ b/net/ipv6/seg6.c
@@ -17,6 +17,7 @@
 #include <linux/net.h>
 #include <linux/in6.h>
 #include <linux/slab.h>
+#include <linux/rhashtable.h>
 
 #include <net/ipv6.h>
 #include <net/protocol.h>
diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c
index 33fb35cbfac1..b1791129a875 100644
--- a/net/ipv6/seg6_hmac.c
+++ b/net/ipv6/seg6_hmac.c
@@ -22,6 +22,7 @@
 #include <linux/icmpv6.h>
 #include <linux/mroute6.h>
 #include <linux/slab.h>
+#include <linux/rhashtable.h>
 
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv6.h>
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 896d4a36081d..3f211e1025c1 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -14,6 +14,7 @@
 #include <linux/skbuff.h>
 #include <linux/netlink.h>
 #include <linux/vmalloc.h>
+#include <linux/rhashtable.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nf_tables.h>
diff --git a/net/sctp/input.c b/net/sctp/input.c
index ba8a6e6c36fa..9bbc5f92c941 100644
--- a/net/sctp/input.c
+++ b/net/sctp/input.c
@@ -56,6 +56,7 @@
 #include <net/sctp/sm.h>
 #include <net/sctp/checksum.h>
 #include <net/net_namespace.h>
+#include <linux/rhashtable.h>
 
 /* Forward declarations for internal helpers. */
 static int sctp_rcv_ootb(struct sk_buff *);
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index d20f7addee19..0e91e83eea5a 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -66,6 +66,7 @@
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/compat.h>
+#include <linux/rhashtable.h>
 
 #include <net/ip.h>
 #include <net/icmp.h>
-- 
cgit v1.2.3


From 9f9a707738aa7a8b9f78a641b83927ada256a626 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 12:52:50 +1000
Subject: rhashtable: remove nulls_base and related code.

This "feature" is unused, undocumented, and untested and so doesn't
really belong.  A patch is under development to properly implement
support for detecting when a search gets diverted down a different
chain, which the common purpose of nulls markers.

This patch actually fixes a bug too.  The table resizing allows a
table to grow to 2^31 buckets, but the hash is truncated to 27 bits -
any growth beyond 2^27 is wasteful an ineffective.

This patch results in NULLS_MARKER(0) being used for all chains,
and leaves the use of rht_is_a_null() to test for it.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable-types.h |  2 --
 include/linux/rhashtable.h       | 33 +++------------------------------
 lib/rhashtable.c                 |  8 --------
 lib/test_rhashtable.c            |  5 +----
 net/core/xdp.c                   |  4 ++--
 5 files changed, 6 insertions(+), 46 deletions(-)

diff --git a/include/linux/rhashtable-types.h b/include/linux/rhashtable-types.h
index 9740063ff13b..763d613ce2c2 100644
--- a/include/linux/rhashtable-types.h
+++ b/include/linux/rhashtable-types.h
@@ -50,7 +50,6 @@ typedef int (*rht_obj_cmpfn_t)(struct rhashtable_compare_arg *arg,
  * @min_size: Minimum size while shrinking
  * @locks_mul: Number of bucket locks to allocate per cpu (default: 32)
  * @automatic_shrinking: Enable automatic shrinking of tables
- * @nulls_base: Base value to generate nulls marker
  * @hashfn: Hash function (default: jhash2 if !(key_len % 4), or jhash)
  * @obj_hashfn: Function to hash object
  * @obj_cmpfn: Function to compare key with object
@@ -64,7 +63,6 @@ struct rhashtable_params {
 	u16			min_size;
 	bool			automatic_shrinking;
 	u8			locks_mul;
-	u32			nulls_base;
 	rht_hashfn_t		hashfn;
 	rht_obj_hashfn_t	obj_hashfn;
 	rht_obj_cmpfn_t		obj_cmpfn;
diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 48754ab07cdf..d9f719af7936 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -28,25 +28,8 @@
 #include <linux/rhashtable-types.h>
 /*
  * The end of the chain is marked with a special nulls marks which has
- * the following format:
- *
- * +-------+-----------------------------------------------------+-+
- * | Base  |                      Hash                           |1|
- * +-------+-----------------------------------------------------+-+
- *
- * Base (4 bits) : Reserved to distinguish between multiple tables.
- *                 Specified via &struct rhashtable_params.nulls_base.
- * Hash (27 bits): Full hash (unmasked) of first element added to bucket
- * 1 (1 bit)     : Nulls marker (always set)
- *
- * The remaining bits of the next pointer remain unused for now.
+ * the least significant bit set.
  */
-#define RHT_BASE_BITS		4
-#define RHT_HASH_BITS		27
-#define RHT_BASE_SHIFT		RHT_HASH_BITS
-
-/* Base bits plus 1 bit for nulls marker */
-#define RHT_HASH_RESERVED_SPACE	(RHT_BASE_BITS + 1)
 
 /* Maximum chain length before rehash
  *
@@ -92,24 +75,14 @@ struct bucket_table {
 	struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
-static inline unsigned long rht_marker(const struct rhashtable *ht, u32 hash)
-{
-	return NULLS_MARKER(ht->p.nulls_base + hash);
-}
-
 #define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \
-	((ptr) = (typeof(ptr)) rht_marker(ht, hash))
+	((ptr) = (typeof(ptr)) NULLS_MARKER(0))
 
 static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
 {
 	return ((unsigned long) ptr & 1);
 }
 
-static inline unsigned long rht_get_nulls_value(const struct rhash_head *ptr)
-{
-	return ((unsigned long) ptr) >> 1;
-}
-
 static inline void *rht_obj(const struct rhashtable *ht,
 			    const struct rhash_head *he)
 {
@@ -119,7 +92,7 @@ static inline void *rht_obj(const struct rhashtable *ht,
 static inline unsigned int rht_bucket_index(const struct bucket_table *tbl,
 					    unsigned int hash)
 {
-	return (hash >> RHT_HASH_RESERVED_SPACE) & (tbl->size - 1);
+	return hash & (tbl->size - 1);
 }
 
 static inline unsigned int rht_key_get_hash(struct rhashtable *ht,
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index c9fafea7dc6e..688693c919be 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -995,7 +995,6 @@ static u32 rhashtable_jhash2(const void *key, u32 length, u32 seed)
  *	.key_offset = offsetof(struct test_obj, key),
  *	.key_len = sizeof(int),
  *	.hashfn = jhash,
- *	.nulls_base = (1U << RHT_BASE_SHIFT),
  * };
  *
  * Configuration Example 2: Variable length keys
@@ -1029,9 +1028,6 @@ int rhashtable_init(struct rhashtable *ht,
 	    (params->obj_hashfn && !params->obj_cmpfn))
 		return -EINVAL;
 
-	if (params->nulls_base && params->nulls_base < (1U << RHT_BASE_SHIFT))
-		return -EINVAL;
-
 	memset(ht, 0, sizeof(*ht));
 	mutex_init(&ht->mutex);
 	spin_lock_init(&ht->lock);
@@ -1096,10 +1092,6 @@ int rhltable_init(struct rhltable *hlt, const struct rhashtable_params *params)
 {
 	int err;
 
-	/* No rhlist NULLs marking for now. */
-	if (params->nulls_base)
-		return -EINVAL;
-
 	err = rhashtable_init(&hlt->ht, params);
 	hlt->ht.rhlist = true;
 	return err;
diff --git a/lib/test_rhashtable.c b/lib/test_rhashtable.c
index 6ca59ffcacbe..82ac39ce5310 100644
--- a/lib/test_rhashtable.c
+++ b/lib/test_rhashtable.c
@@ -83,7 +83,7 @@ static u32 my_hashfn(const void *data, u32 len, u32 seed)
 {
 	const struct test_obj_rhl *obj = data;
 
-	return (obj->value.id % 10) << RHT_HASH_RESERVED_SPACE;
+	return (obj->value.id % 10);
 }
 
 static int my_cmpfn(struct rhashtable_compare_arg *arg, const void *obj)
@@ -99,7 +99,6 @@ static struct rhashtable_params test_rht_params = {
 	.key_offset = offsetof(struct test_obj, value),
 	.key_len = sizeof(struct test_obj_val),
 	.hashfn = jhash,
-	.nulls_base = (3U << RHT_BASE_SHIFT),
 };
 
 static struct rhashtable_params test_rht_params_dup = {
@@ -296,8 +295,6 @@ static int __init test_rhltable(unsigned int entries)
 	if (!obj_in_table)
 		goto out_free;
 
-	/* nulls_base not supported in rhlist interface */
-	test_rht_params.nulls_base = 0;
 	err = rhltable_init(&rhlt, &test_rht_params);
 	if (WARN_ON(err))
 		goto out_free;
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 9d1f22072d5d..31c58719b5a9 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -45,8 +45,8 @@ static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed)
 	BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id)
 		     != sizeof(u32));
 
-	/* Use cyclic increasing ID as direct hash key, see rht_bucket_index */
-	return key << RHT_HASH_RESERVED_SPACE;
+	/* Use cyclic increasing ID as direct hash key */
+	return key;
 }
 
 static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg,
-- 
cgit v1.2.3


From 9b4f64a227b6f462482a8cc68c7134dc6e26f1c1 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 12:52:50 +1000
Subject: rhashtable: simplify INIT_RHT_NULLS_HEAD()

The 'ht' and 'hash' arguments to INIT_RHT_NULLS_HEAD() are
no longer used - so drop them.  This allows us to also
remove the nhash argument from nested_table_alloc().

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h |  2 +-
 lib/rhashtable.c           | 15 ++++++---------
 2 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index d9f719af7936..3f3a182bd0b4 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -75,7 +75,7 @@ struct bucket_table {
 	struct rhash_head __rcu *buckets[] ____cacheline_aligned_in_smp;
 };
 
-#define INIT_RHT_NULLS_HEAD(ptr, ht, hash) \
+#define INIT_RHT_NULLS_HEAD(ptr)	\
 	((ptr) = (typeof(ptr)) NULLS_MARKER(0))
 
 static inline bool rht_is_a_nulls(const struct rhash_head *ptr)
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 688693c919be..a81cd27d518c 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -116,8 +116,7 @@ static void bucket_table_free_rcu(struct rcu_head *head)
 
 static union nested_table *nested_table_alloc(struct rhashtable *ht,
 					      union nested_table __rcu **prev,
-					      unsigned int shifted,
-					      unsigned int nhash)
+					      unsigned int shifted)
 {
 	union nested_table *ntbl;
 	int i;
@@ -130,8 +129,7 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht,
 
 	if (ntbl && shifted) {
 		for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0].bucket); i++)
-			INIT_RHT_NULLS_HEAD(ntbl[i].bucket, ht,
-					    (i << shifted) | nhash);
+			INIT_RHT_NULLS_HEAD(ntbl[i].bucket);
 	}
 
 	rcu_assign_pointer(*prev, ntbl);
@@ -157,7 +155,7 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht,
 		return NULL;
 
 	if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets,
-				0, 0)) {
+				0)) {
 		kfree(tbl);
 		return NULL;
 	}
@@ -207,7 +205,7 @@ static struct bucket_table *bucket_table_alloc(struct rhashtable *ht,
 	tbl->hash_rnd = get_random_u32();
 
 	for (i = 0; i < nbuckets; i++)
-		INIT_RHT_NULLS_HEAD(tbl->buckets[i], ht, i);
+		INIT_RHT_NULLS_HEAD(tbl->buckets[i]);
 
 	return tbl;
 }
@@ -1217,7 +1215,7 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
 	nhash = index;
 	shifted = tbl->nest;
 	ntbl = nested_table_alloc(ht, &ntbl[index].table,
-				  size <= (1 << shift) ? shifted : 0, nhash);
+				  size <= (1 << shift) ? shifted : 0);
 
 	while (ntbl && size > (1 << shift)) {
 		index = hash & ((1 << shift) - 1);
@@ -1226,8 +1224,7 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
 		nhash |= index << shifted;
 		shifted += shift;
 		ntbl = nested_table_alloc(ht, &ntbl[index].table,
-					  size <= (1 << shift) ? shifted : 0,
-					  nhash);
+					  size <= (1 << shift) ? shifted : 0);
 	}
 
 	if (!ntbl)
-- 
cgit v1.2.3


From 5af68ef7333c8606bfe6e400cb962081518c3acb Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 12:52:50 +1000
Subject: rhashtable: simplify nested_table_alloc() and
 rht_bucket_nested_insert()

Now that we don't use the hash value or shift in nested_table_alloc()
there is room for simplification.
We only need to pass a "is this a leaf" flag to nested_table_alloc(),
and don't need to track as much information in
rht_bucket_nested_insert().

Note there is another minor cleanup in nested_table_alloc() here.
The number of elements in a page of "union nested_tables" is most naturally

  PAGE_SIZE / sizeof(ntbl[0])

The previous code had

  PAGE_SIZE / sizeof(ntbl[0].bucket)

which happens to be the correct value only because the bucket uses all
the space in the union.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index a81cd27d518c..2aa41c15df17 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -116,7 +116,7 @@ static void bucket_table_free_rcu(struct rcu_head *head)
 
 static union nested_table *nested_table_alloc(struct rhashtable *ht,
 					      union nested_table __rcu **prev,
-					      unsigned int shifted)
+					      bool leaf)
 {
 	union nested_table *ntbl;
 	int i;
@@ -127,8 +127,8 @@ static union nested_table *nested_table_alloc(struct rhashtable *ht,
 
 	ntbl = kzalloc(PAGE_SIZE, GFP_ATOMIC);
 
-	if (ntbl && shifted) {
-		for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0].bucket); i++)
+	if (ntbl && leaf) {
+		for (i = 0; i < PAGE_SIZE / sizeof(ntbl[0]); i++)
 			INIT_RHT_NULLS_HEAD(ntbl[i].bucket);
 	}
 
@@ -155,7 +155,7 @@ static struct bucket_table *nested_bucket_table_alloc(struct rhashtable *ht,
 		return NULL;
 
 	if (!nested_table_alloc(ht, (union nested_table __rcu **)tbl->buckets,
-				0)) {
+				false)) {
 		kfree(tbl);
 		return NULL;
 	}
@@ -1207,24 +1207,18 @@ struct rhash_head __rcu **rht_bucket_nested_insert(struct rhashtable *ht,
 	unsigned int index = hash & ((1 << tbl->nest) - 1);
 	unsigned int size = tbl->size >> tbl->nest;
 	union nested_table *ntbl;
-	unsigned int shifted;
-	unsigned int nhash;
 
 	ntbl = (union nested_table *)rcu_dereference_raw(tbl->buckets[0]);
 	hash >>= tbl->nest;
-	nhash = index;
-	shifted = tbl->nest;
 	ntbl = nested_table_alloc(ht, &ntbl[index].table,
-				  size <= (1 << shift) ? shifted : 0);
+				  size <= (1 << shift));
 
 	while (ntbl && size > (1 << shift)) {
 		index = hash & ((1 << shift) - 1);
 		size >>= shift;
 		hash >>= shift;
-		nhash |= index << shifted;
-		shifted += shift;
 		ntbl = nested_table_alloc(ht, &ntbl[index].table,
-					  size <= (1 << shift) ? shifted : 0);
+					  size <= (1 << shift));
 	}
 
 	if (!ntbl)
-- 
cgit v1.2.3


From 0ad66449aa3cbaedbdeaf55bffce74084bb7e9f9 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 12:52:50 +1000
Subject: rhashtable: use cmpxchg() to protect ->future_tbl.

Rather than borrowing one of the bucket locks to
protect ->future_tbl updates, use cmpxchg().
This gives more freedom to change how bucket locking
is implemented.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/rhashtable.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 2aa41c15df17..52ec83212856 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -297,21 +297,14 @@ static int rhashtable_rehash_attach(struct rhashtable *ht,
 				    struct bucket_table *old_tbl,
 				    struct bucket_table *new_tbl)
 {
-	/* Protect future_tbl using the first bucket lock. */
-	spin_lock_bh(old_tbl->locks);
-
-	/* Did somebody beat us to it? */
-	if (rcu_access_pointer(old_tbl->future_tbl)) {
-		spin_unlock_bh(old_tbl->locks);
-		return -EEXIST;
-	}
-
 	/* Make insertions go into the new, empty table right away. Deletions
 	 * and lookups will be attempted in both tables until we synchronize.
+	 * As cmpxchg() provides strong barriers, we do not need
+	 * rcu_assign_pointer().
 	 */
-	rcu_assign_pointer(old_tbl->future_tbl, new_tbl);
 
-	spin_unlock_bh(old_tbl->locks);
+	if (cmpxchg(&old_tbl->future_tbl, NULL, new_tbl) != NULL)
+		return -EEXIST;
 
 	return 0;
 }
-- 
cgit v1.2.3


From c0690016a73fe6bd456887bbbe6e10c7f0096554 Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 12:52:50 +1000
Subject: rhashtable: clean up dereference of ->future_tbl.

Using rht_dereference_bucket() to dereference
->future_tbl looks like a type error, and could be confusing.
Using rht_dereference_rcu() to test a pointer for NULL
adds an unnecessary barrier - rcu_access_pointer() is preferred
for NULL tests when no lock is held.

This uses 3 different ways to access ->future_tbl.
- if we know the mutex is held, use rht_dereference()
- if we don't hold the mutex, and are only testing for NULL,
  use rcu_access_pointer()
- otherwise (using RCU protection for true dereference),
  use rht_dereference_rcu().

Note that this includes a simplification of the call to
rhashtable_last_table() - we don't do an extra dereference
before the call any more.

Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/rhashtable.h | 2 +-
 lib/rhashtable.c           | 9 ++++-----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h
index 3f3a182bd0b4..eb7111039247 100644
--- a/include/linux/rhashtable.h
+++ b/include/linux/rhashtable.h
@@ -595,7 +595,7 @@ static inline void *__rhashtable_insert_fast(
 	lock = rht_bucket_lock(tbl, hash);
 	spin_lock_bh(lock);
 
-	if (unlikely(rht_dereference_bucket(tbl->future_tbl, tbl, hash))) {
+	if (unlikely(rcu_access_pointer(tbl->future_tbl))) {
 slow_path:
 		spin_unlock_bh(lock);
 		rcu_read_unlock();
diff --git a/lib/rhashtable.c b/lib/rhashtable.c
index 52ec83212856..0e04947b7e0c 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -226,8 +226,7 @@ static struct bucket_table *rhashtable_last_table(struct rhashtable *ht,
 static int rhashtable_rehash_one(struct rhashtable *ht, unsigned int old_hash)
 {
 	struct bucket_table *old_tbl = rht_dereference(ht->tbl, ht);
-	struct bucket_table *new_tbl = rhashtable_last_table(ht,
-		rht_dereference_rcu(old_tbl->future_tbl, ht));
+	struct bucket_table *new_tbl = rhashtable_last_table(ht, old_tbl);
 	struct rhash_head __rcu **pprev = rht_bucket_var(old_tbl, old_hash);
 	int err = -EAGAIN;
 	struct rhash_head *head, *next, *entry;
@@ -467,7 +466,7 @@ static int rhashtable_insert_rehash(struct rhashtable *ht,
 
 fail:
 	/* Do not fail the insert if someone else did a rehash. */
-	if (likely(rcu_dereference_raw(tbl->future_tbl)))
+	if (likely(rcu_access_pointer(tbl->future_tbl)))
 		return 0;
 
 	/* Schedule async rehash to retry allocation in process context. */
@@ -540,7 +539,7 @@ static struct bucket_table *rhashtable_insert_one(struct rhashtable *ht,
 	if (PTR_ERR(data) != -EAGAIN && PTR_ERR(data) != -ENOENT)
 		return ERR_CAST(data);
 
-	new_tbl = rcu_dereference(tbl->future_tbl);
+	new_tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 	if (new_tbl)
 		return new_tbl;
 
@@ -599,7 +598,7 @@ static void *rhashtable_try_insert(struct rhashtable *ht, const void *key,
 			break;
 
 		spin_unlock_bh(lock);
-		tbl = rcu_dereference(tbl->future_tbl);
+		tbl = rht_dereference_rcu(tbl->future_tbl, ht);
 	}
 
 	data = rhashtable_lookup_one(ht, tbl, hash, key, obj);
-- 
cgit v1.2.3


From 3f6c65d6255a872846c44182c82c78d3dc6239f5 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 19 Jun 2018 21:42:50 -0700
Subject: tcp: ignore rcv_rtt sample with old ts ecr value

When receiving multiple packets with the same ts ecr value, only try
to compute rcv_rtt sample with the earliest received packet.
This is because the rcv_rtt calculated by later received packets
could possibly include long idle time or other types of delay.
For example:
(1) server sends last packet of reply with TS val V1
(2) client ACKs last packet of reply with TS ecr V1
(3) long idle time passes
(4) client sends next request data packet with TS ecr V1 (again!)
At this time, the rcv_rtt computed on server with TS ecr V1 will be
inflated with the idle time and should get ignored.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h  |  1 +
 net/ipv4/tcp.c       |  1 +
 net/ipv4/tcp_input.c | 14 +++++++++++---
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 72705eaf4b84..3dbea6610304 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -350,6 +350,7 @@ struct tcp_sock {
 #endif
 
 /* Receiver side RTT estimation */
+	u32 rcv_rtt_last_tsecr;
 	struct {
 		u32	rtt_us;
 		u32	seq;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 141acd92e58a..47c45d5be9f9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2563,6 +2563,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_shutdown = 0;
 	sock_reset_flag(sk, SOCK_DONE);
 	tp->srtt_us = 0;
+	tp->rcv_rtt_last_tsecr = 0;
 	tp->write_seq += tp->max_window + 2;
 	if (tp->write_seq == 0)
 		tp->write_seq = 1;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 355d3dffd021..76ca88f63b70 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -582,9 +582,12 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tp->rx_opt.rcv_tsecr &&
-	    (TCP_SKB_CB(skb)->end_seq -
-	     TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss)) {
+	if (tp->rx_opt.rcv_tsecr == tp->rcv_rtt_last_tsecr)
+		return;
+	tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
+
+	if (TCP_SKB_CB(skb)->end_seq -
+	    TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss) {
 		u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr;
 		u32 delta_us;
 
@@ -5475,6 +5478,11 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 				tcp_ack(sk, skb, 0);
 				__kfree_skb(skb);
 				tcp_data_snd_check(sk);
+				/* When receiving pure ack in fast path, update
+				 * last ts ecr directly instead of calling
+				 * tcp_rcv_rtt_measure_ts()
+				 */
+				tp->rcv_rtt_last_tsecr = tp->rx_opt.rcv_tsecr;
 				return;
 			} else { /* Header too small */
 				TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
-- 
cgit v1.2.3


From 1599b218d511afad570be6048108d0746f78bfe9 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Tue, 19 Jun 2018 22:42:42 -0700
Subject: selftests: rtnetlink: hide complaint from terminated monitor

Set up the "ip xfrm monitor" subprogram so as to not see
a "Terminated" message when the subprogram is killed.

Fixes: 5e596ee171ba ("selftests: add xfrm state-policy-monitor to rtnetlink.sh")
Reported-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 0d7a44fa30af..4cd252f4e077 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -535,8 +535,7 @@ kci_test_ipsec()
 
 	# start the monitor in the background
 	tmpfile=`mktemp ipsectestXXX`
-	ip x m > $tmpfile &
-	mpid=$!
+	mpid=`(ip x m > $tmpfile & echo $!) 2>/dev/null`
 	sleep 0.2
 
 	ipsecid="proto esp src $srcip dst $dstip spi 0x07"
-- 
cgit v1.2.3


From 7000d53b865ab46e0c557e2bf7ccf05d33d0624c Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Tue, 19 Jun 2018 22:42:43 -0700
Subject: selftests: rtnetlink: use a local IP address for IPsec tests

Find an IP address on this machine to use as a source IP, and
make up a destination IP address based on the source IP.  No
actual messages will be sent, just a couple of IPsec rules are
created and deleted.

Fixes: 5e596ee171ba ("selftests: add xfrm state-policy-monitor to rtnetlink.sh")
Reported-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index 4cd252f4e077..a90eb31abd59 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -525,8 +525,12 @@ kci_test_macsec()
 #-------------------------------------------------------------------
 kci_test_ipsec()
 {
-	srcip="14.0.0.52"
-	dstip="14.0.0.70"
+	# find an ip address on this machine and make up a destination
+	srcip=`ip -o addr | awk '/inet / { print $4; }' | grep -v "^127" | head -1 | cut -f1 -d/`
+	net=`echo $srcip | cut -f1-3 -d.`
+	base=`echo $srcip | cut -f4 -d.`
+	dstip="$net."`expr $base + 1`
+
 	algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
 
 	# flush to be sure there's nothing configured
-- 
cgit v1.2.3


From 78c696c19578ff2bb14622304e63d7beb54206e5 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 12:40:25 +0200
Subject: isdn: gigaset: use usb_fill_int_urb()

Using usb_fill_int_urb() helps to find code which initializes an
URB. A grep for members of the struct (like ->complete) reveal lots
of other things, too.

Cc: Paul Bolle <pebolle@tiscali.nl>
Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: gigaset307x-common@lists.sourceforge.net
Cc: netdev@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/bas-gigaset.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index 20d0a080a2b0..40c141163f0f 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -972,16 +972,14 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
+		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
+				 usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel),
+				 ubc->isoinbuf + k * BAS_INBUFSIZE,
+				 BAS_INBUFSIZE, read_iso_callback, bcs,
+				 BAS_FRAMETIME);
 
-		urb->dev = bcs->cs->hw.bas->udev;
-		urb->pipe = usb_rcvisocpipe(urb->dev, 3 + 2 * bcs->channel);
 		urb->transfer_flags = URB_ISO_ASAP;
-		urb->transfer_buffer = ubc->isoinbuf + k * BAS_INBUFSIZE;
-		urb->transfer_buffer_length = BAS_INBUFSIZE;
 		urb->number_of_packets = BAS_NUMFRAMES;
-		urb->interval = BAS_FRAMETIME;
-		urb->complete = read_iso_callback;
-		urb->context = bcs;
 		for (j = 0; j < BAS_NUMFRAMES; j++) {
 			urb->iso_frame_desc[j].offset = j * BAS_MAXFRAME;
 			urb->iso_frame_desc[j].length = BAS_MAXFRAME;
@@ -1005,15 +1003,15 @@ static int starturbs(struct bc_state *bcs)
 			rc = -EFAULT;
 			goto error;
 		}
-		urb->dev = bcs->cs->hw.bas->udev;
-		urb->pipe = usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel);
+		usb_fill_int_urb(urb, bcs->cs->hw.bas->udev,
+				 usb_sndisocpipe(urb->dev, 4 + 2 * bcs->channel),
+				 ubc->isooutbuf->data,
+				 sizeof(ubc->isooutbuf->data),
+				 write_iso_callback, &ubc->isoouturbs[k],
+				 BAS_FRAMETIME);
+
 		urb->transfer_flags = URB_ISO_ASAP;
-		urb->transfer_buffer = ubc->isooutbuf->data;
-		urb->transfer_buffer_length = sizeof(ubc->isooutbuf->data);
 		urb->number_of_packets = BAS_NUMFRAMES;
-		urb->interval = BAS_FRAMETIME;
-		urb->complete = write_iso_callback;
-		urb->context = &ubc->isoouturbs[k];
 		for (j = 0; j < BAS_NUMFRAMES; ++j) {
 			urb->iso_frame_desc[j].offset = BAS_OUTBUFSIZE;
 			urb->iso_frame_desc[j].length = BAS_NORMFRAME;
-- 
cgit v1.2.3


From dd3adc4e604a3d1ad71da489310221e136937efe Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 12:40:26 +0200
Subject: isdn: hisax: hfc_usb: use usb_fill_int_urb()

Using usb_fill_int_urb() helps to find code which initializes an
URB. A grep for members of the struct (like ->complete) reveal lots
of other things, too.

The `interval' parameter is now set differently on HS and SS. The
argument is fed from bInterval so it should be the right thing to do.

Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: netdev@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hisax/hfc_usb.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/isdn/hisax/hfc_usb.c b/drivers/isdn/hisax/hfc_usb.c
index 97ecb3073045..1d4cd01d4685 100644
--- a/drivers/isdn/hisax/hfc_usb.c
+++ b/drivers/isdn/hisax/hfc_usb.c
@@ -432,16 +432,12 @@ fill_isoc_urb(struct urb *urb, struct usb_device *dev, unsigned int pipe,
 {
 	int k;
 
-	urb->dev = dev;
-	urb->pipe = pipe;
-	urb->complete = complete;
+	usb_fill_int_urb(urb, dev, pipe, buf, packet_size * num_packets,
+			 complete, context, interval);
+
 	urb->number_of_packets = num_packets;
-	urb->transfer_buffer_length = packet_size * num_packets;
-	urb->context = context;
-	urb->transfer_buffer = buf;
 	urb->transfer_flags = URB_ISO_ASAP;
 	urb->actual_length = 0;
-	urb->interval = interval;
 	for (k = 0; k < num_packets; k++) {
 		urb->iso_frame_desc[k].offset = packet_size * k;
 		urb->iso_frame_desc[k].length = packet_size;
-- 
cgit v1.2.3


From e112ce43565492fae9a0481f26909899c0b60293 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 12:40:27 +0200
Subject: isdn: hisax: st5481_usb: use usb_fill_int_urb()

Using usb_fill_int_urb() helps to find code which initializes an
URB. A grep for members of the struct (like ->complete) reveal lots
of other things, too.

Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: netdev@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hisax/st5481_usb.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/isdn/hisax/st5481_usb.c b/drivers/isdn/hisax/st5481_usb.c
index 1cb9930d5e24..f207fda691c7 100644
--- a/drivers/isdn/hisax/st5481_usb.c
+++ b/drivers/isdn/hisax/st5481_usb.c
@@ -408,15 +408,10 @@ fill_isoc_urb(struct urb *urb, struct usb_device *dev,
 {
 	int k;
 
-	urb->dev = dev;
-	urb->pipe = pipe;
-	urb->interval = 1;
-	urb->transfer_buffer = buf;
+	usb_fill_int_urb(urb, dev, pipe, buf, num_packets * packet_size,
+			 complete, context, 1);
+
 	urb->number_of_packets = num_packets;
-	urb->transfer_buffer_length = num_packets * packet_size;
-	urb->actual_length = 0;
-	urb->complete = complete;
-	urb->context = context;
 	urb->transfer_flags = URB_ISO_ASAP;
 	for (k = 0; k < num_packets; k++) {
 		urb->iso_frame_desc[k].offset = packet_size * k;
-- 
cgit v1.2.3


From 16630f54fe28fb50f95f2911dc7a3b4bf137305f Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 12:40:28 +0200
Subject: isdn: mISDN: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the ->lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: netdev@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/mISDN/hfcsusb.c | 36 +++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/isdn/hardware/mISDN/hfcsusb.c b/drivers/isdn/hardware/mISDN/hfcsusb.c
index 17cc879ad2bb..6d05946b445e 100644
--- a/drivers/isdn/hardware/mISDN/hfcsusb.c
+++ b/drivers/isdn/hardware/mISDN/hfcsusb.c
@@ -819,6 +819,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 	int		fifon = fifo->fifonum;
 	int		i;
 	int		hdlc = 0;
+	unsigned long	flags;
 
 	if (debug & DBG_HFC_CALL_TRACE)
 		printk(KERN_DEBUG "%s: %s: fifo(%i) len(%i) "
@@ -835,7 +836,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 		return;
 	}
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->dch) {
 		rx_skb = fifo->dch->rx_skb;
 		maxlen = fifo->dch->maxlen;
@@ -844,7 +845,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 	if (fifo->bch) {
 		if (test_bit(FLG_RX_OFF, &fifo->bch->Flags)) {
 			fifo->bch->dropcnt += len;
-			spin_unlock(&hw->lock);
+			spin_unlock_irqrestore(&hw->lock, flags);
 			return;
 		}
 		maxlen = bchannel_get_rxbuf(fifo->bch, len);
@@ -854,7 +855,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 				skb_trim(rx_skb, 0);
 			pr_warning("%s.B%d: No bufferspace for %d bytes\n",
 				   hw->name, fifo->bch->nr, len);
-			spin_unlock(&hw->lock);
+			spin_unlock_irqrestore(&hw->lock, flags);
 			return;
 		}
 		maxlen = fifo->bch->maxlen;
@@ -878,7 +879,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 			} else {
 				printk(KERN_DEBUG "%s: %s: No mem for rx_skb\n",
 				       hw->name, __func__);
-				spin_unlock(&hw->lock);
+				spin_unlock_irqrestore(&hw->lock, flags);
 				return;
 			}
 		}
@@ -888,7 +889,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 			       "for fifo(%d) HFCUSB_D_RX\n",
 			       hw->name, __func__, fifon);
 			skb_trim(rx_skb, 0);
-			spin_unlock(&hw->lock);
+			spin_unlock_irqrestore(&hw->lock, flags);
 			return;
 		}
 	}
@@ -942,7 +943,7 @@ hfcsusb_rx_frame(struct usb_fifo *fifo, __u8 *data, unsigned int len,
 		/* deliver transparent data to layer2 */
 		recv_Bchannel(fifo->bch, MISDN_ID_ANY, false);
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 }
 
 static void
@@ -979,18 +980,19 @@ rx_iso_complete(struct urb *urb)
 	__u8 *buf;
 	static __u8 eof[8];
 	__u8 s0_state;
+	unsigned long flags;
 
 	fifon = fifo->fifonum;
 	status = urb->status;
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->stop_gracefull) {
 		fifo->stop_gracefull = 0;
 		fifo->active = 0;
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 
 	/*
 	 * ISO transfer only partially completed,
@@ -1096,15 +1098,16 @@ rx_int_complete(struct urb *urb)
 	struct usb_fifo *fifo = (struct usb_fifo *) urb->context;
 	struct hfcsusb *hw = fifo->hw;
 	static __u8 eof[8];
+	unsigned long flags;
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->stop_gracefull) {
 		fifo->stop_gracefull = 0;
 		fifo->active = 0;
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 
 	fifon = fifo->fifonum;
 	if ((!fifo->active) || (urb->status)) {
@@ -1172,12 +1175,13 @@ tx_iso_complete(struct urb *urb)
 	int *tx_idx;
 	int frame_complete, fifon, status, fillempty = 0;
 	__u8 threshbit, *p;
+	unsigned long flags;
 
-	spin_lock(&hw->lock);
+	spin_lock_irqsave(&hw->lock, flags);
 	if (fifo->stop_gracefull) {
 		fifo->stop_gracefull = 0;
 		fifo->active = 0;
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
 
@@ -1195,7 +1199,7 @@ tx_iso_complete(struct urb *urb)
 	} else {
 		printk(KERN_DEBUG "%s: %s: neither BCH nor DCH\n",
 		       hw->name, __func__);
-		spin_unlock(&hw->lock);
+		spin_unlock_irqrestore(&hw->lock, flags);
 		return;
 	}
 
@@ -1375,7 +1379,7 @@ tx_iso_complete(struct urb *urb)
 			       hw->name, __func__,
 			       symbolic(urb_errlist, status), status, fifon);
 	}
-	spin_unlock(&hw->lock);
+	spin_unlock_irqrestore(&hw->lock, flags);
 }
 
 /*
-- 
cgit v1.2.3


From f79e7115bd76666860603b8fab8ccaa48a7d1735 Mon Sep 17 00:00:00 2001
From: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Date: Wed, 20 Jun 2018 18:29:18 +0200
Subject: ucc_geth: Add BQL support

Signed-off-by: Joakim Tjernlund <joakim.tjernlund@infinera.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/ucc_geth.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 42fca3208c0b..22a817da861e 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3096,6 +3096,7 @@ static int ucc_geth_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	ugeth_vdbg("%s: IN", __func__);
 
+	netdev_sent_queue(dev, skb->len);
 	spin_lock_irqsave(&ugeth->lock, flags);
 
 	dev->stats.tx_bytes += skb->len;
@@ -3240,6 +3241,8 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ)
 {
 	/* Start from the next BD that should be filled */
 	struct ucc_geth_private *ugeth = netdev_priv(dev);
+	unsigned int bytes_sent = 0;
+	int howmany = 0;
 	u8 __iomem *bd;		/* BD pointer */
 	u32 bd_status;
 
@@ -3257,7 +3260,8 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ)
 		skb = ugeth->tx_skbuff[txQ][ugeth->skb_dirtytx[txQ]];
 		if (!skb)
 			break;
-
+		howmany++;
+		bytes_sent += skb->len;
 		dev->stats.tx_packets++;
 
 		dev_consume_skb_any(skb);
@@ -3279,6 +3283,7 @@ static int ucc_geth_tx(struct net_device *dev, u8 txQ)
 		bd_status = in_be32((u32 __iomem *)bd);
 	}
 	ugeth->confBd[txQ] = bd;
+	netdev_completed_queue(dev, howmany, bytes_sent);
 	return 0;
 }
 
@@ -3479,6 +3484,7 @@ static int ucc_geth_open(struct net_device *dev)
 
 	phy_start(ugeth->phydev);
 	napi_enable(&ugeth->napi);
+	netdev_reset_queue(dev);
 	netif_start_queue(dev);
 
 	device_set_wakeup_capable(&dev->dev,
@@ -3509,6 +3515,7 @@ static int ucc_geth_close(struct net_device *dev)
 	free_irq(ugeth->ug_info->uf_info.irq, ugeth->ndev);
 
 	netif_stop_queue(dev);
+	netdev_reset_queue(dev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From fafa6b10485e4534fcce00a75226caec7f5e2c11 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:31:17 +0200
Subject: net: usb: cdc-phonet: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/cdc-phonet.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index 288ecd999171..3c40312fa453 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -99,6 +99,7 @@ static void tx_complete(struct urb *req)
 	struct net_device *dev = skb->dev;
 	struct usbpn_dev *pnd = netdev_priv(dev);
 	int status = req->status;
+	unsigned long flags;
 
 	switch (status) {
 	case 0:
@@ -115,10 +116,10 @@ static void tx_complete(struct urb *req)
 	}
 	dev->stats.tx_packets++;
 
-	spin_lock(&pnd->tx_lock);
+	spin_lock_irqsave(&pnd->tx_lock, flags);
 	pnd->tx_queue--;
 	netif_wake_queue(dev);
-	spin_unlock(&pnd->tx_lock);
+	spin_unlock_irqrestore(&pnd->tx_lock, flags);
 
 	dev_kfree_skb_any(skb);
 	usb_free_urb(req);
-- 
cgit v1.2.3


From 12c4de4bcc23ecf3ae3400e12d0686ccdc1c0238 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:31:18 +0200
Subject: net: usb: hso: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 35 +++++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 14 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index e53883ad6107..de305ead32e6 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -999,6 +999,7 @@ static void read_bulk_callback(struct urb *urb)
 	struct hso_net *odev = urb->context;
 	struct net_device *net;
 	int result;
+	unsigned long flags;
 	int status = urb->status;
 
 	/* is al ok?  (Filip: Who's Al ?) */
@@ -1028,11 +1029,11 @@ static void read_bulk_callback(struct urb *urb)
 	if (urb->actual_length) {
 		/* Handle the IP stream, add header and push it onto network
 		 * stack if the packet is complete. */
-		spin_lock(&odev->net_lock);
+		spin_lock_irqsave(&odev->net_lock, flags);
 		packetizeRx(odev, urb->transfer_buffer, urb->actual_length,
 			    (urb->transfer_buffer_length >
 			     urb->actual_length) ? 1 : 0);
-		spin_unlock(&odev->net_lock);
+		spin_unlock_irqrestore(&odev->net_lock, flags);
 	}
 
 	/* We are done with this URB, resubmit it. Prep the USB to wait for
@@ -1193,6 +1194,7 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb)
 {
 	struct hso_serial *serial = urb->context;
 	int status = urb->status;
+	unsigned long flags;
 
 	hso_dbg(0x8, "--- Got serial_read_bulk callback %02x ---\n", status);
 
@@ -1216,10 +1218,10 @@ static void hso_std_serial_read_bulk_callback(struct urb *urb)
 	if (serial->parent->port_spec & HSO_INFO_CRC_BUG)
 		fix_crc_bug(urb, serial->in_endp->wMaxPacketSize);
 	/* Valid data, handle RX data */
-	spin_lock(&serial->serial_lock);
+	spin_lock_irqsave(&serial->serial_lock, flags);
 	serial->rx_urb_filled[hso_urb_to_index(serial, urb)] = 1;
 	put_rxbuf_data_and_resubmit_bulk_urb(serial);
-	spin_unlock(&serial->serial_lock);
+	spin_unlock_irqrestore(&serial->serial_lock, flags);
 }
 
 /*
@@ -1502,12 +1504,13 @@ static void tiocmget_intr_callback(struct urb *urb)
 		DUMP(serial_state_notification,
 		     sizeof(struct hso_serial_state_notification));
 	} else {
+		unsigned long flags;
 
 		UART_state_bitmap = le16_to_cpu(serial_state_notification->
 						UART_state_bitmap);
 		prev_UART_state_bitmap = tiocmget->prev_UART_state_bitmap;
 		icount = &tiocmget->icount;
-		spin_lock(&serial->serial_lock);
+		spin_lock_irqsave(&serial->serial_lock, flags);
 		if ((UART_state_bitmap & B_OVERRUN) !=
 		   (prev_UART_state_bitmap & B_OVERRUN))
 			icount->parity++;
@@ -1530,7 +1533,7 @@ static void tiocmget_intr_callback(struct urb *urb)
 		   (prev_UART_state_bitmap & B_RX_CARRIER))
 			icount->dcd++;
 		tiocmget->prev_UART_state_bitmap = UART_state_bitmap;
-		spin_unlock(&serial->serial_lock);
+		spin_unlock_irqrestore(&serial->serial_lock, flags);
 		tiocmget->intr_completed = 1;
 		wake_up_interruptible(&tiocmget->waitq);
 	}
@@ -1852,6 +1855,7 @@ static void intr_callback(struct urb *urb)
 	struct hso_serial *serial;
 	unsigned char *port_req;
 	int status = urb->status;
+	unsigned long flags;
 	int i;
 
 	usb_mark_last_busy(urb->dev);
@@ -1879,7 +1883,7 @@ static void intr_callback(struct urb *urb)
 			if (serial != NULL) {
 				hso_dbg(0x1, "Pending read interrupt on port %d\n",
 					i);
-				spin_lock(&serial->serial_lock);
+				spin_lock_irqsave(&serial->serial_lock, flags);
 				if (serial->rx_state == RX_IDLE &&
 					serial->port.count > 0) {
 					/* Setup and send a ctrl req read on
@@ -1893,7 +1897,8 @@ static void intr_callback(struct urb *urb)
 					hso_dbg(0x1, "Already a read pending on port %d or port not open\n",
 						i);
 				}
-				spin_unlock(&serial->serial_lock);
+				spin_unlock_irqrestore(&serial->serial_lock,
+						       flags);
 			}
 		}
 	}
@@ -1920,6 +1925,7 @@ static void hso_std_serial_write_bulk_callback(struct urb *urb)
 {
 	struct hso_serial *serial = urb->context;
 	int status = urb->status;
+	unsigned long flags;
 
 	/* sanity check */
 	if (!serial) {
@@ -1927,9 +1933,9 @@ static void hso_std_serial_write_bulk_callback(struct urb *urb)
 		return;
 	}
 
-	spin_lock(&serial->serial_lock);
+	spin_lock_irqsave(&serial->serial_lock, flags);
 	serial->tx_urb_used = 0;
-	spin_unlock(&serial->serial_lock);
+	spin_unlock_irqrestore(&serial->serial_lock, flags);
 	if (status) {
 		handle_usb_error(status, __func__, serial->parent);
 		return;
@@ -1971,14 +1977,15 @@ static void ctrl_callback(struct urb *urb)
 	struct hso_serial *serial = urb->context;
 	struct usb_ctrlrequest *req;
 	int status = urb->status;
+	unsigned long flags;
 
 	/* sanity check */
 	if (!serial)
 		return;
 
-	spin_lock(&serial->serial_lock);
+	spin_lock_irqsave(&serial->serial_lock, flags);
 	serial->tx_urb_used = 0;
-	spin_unlock(&serial->serial_lock);
+	spin_unlock_irqrestore(&serial->serial_lock, flags);
 	if (status) {
 		handle_usb_error(status, __func__, serial->parent);
 		return;
@@ -1994,9 +2001,9 @@ static void ctrl_callback(struct urb *urb)
 	    (USB_DIR_IN | USB_TYPE_OPTION_VENDOR | USB_RECIP_INTERFACE)) {
 		/* response to a read command */
 		serial->rx_urb_filled[0] = 1;
-		spin_lock(&serial->serial_lock);
+		spin_lock_irqsave(&serial->serial_lock, flags);
 		put_rxbuf_data_and_resubmit_ctrl_urb(serial);
-		spin_unlock(&serial->serial_lock);
+		spin_unlock_irqrestore(&serial->serial_lock, flags);
 	} else {
 		hso_put_activity(serial->parent);
 		tty_port_tty_wakeup(&serial->port);
-- 
cgit v1.2.3


From ba49fed8bbaebe6cc1fba0ac57789894be7121ed Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:31:19 +0200
Subject: net: usb: kaweth: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/kaweth.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index f1605833c5cf..913e50bab0a2 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -587,7 +587,7 @@ static void kaweth_usb_receive(struct urb *urb)
 	struct kaweth_device *kaweth = urb->context;
 	struct net_device *net = kaweth->net;
 	int status = urb->status;
-
+	unsigned long flags;
 	int count = urb->actual_length;
 	int count2 = urb->transfer_buffer_length;
 
@@ -619,12 +619,12 @@ static void kaweth_usb_receive(struct urb *urb)
 		net->stats.rx_errors++;
 		dev_dbg(dev, "Status was -EOVERFLOW.\n");
 	}
-	spin_lock(&kaweth->device_lock);
+	spin_lock_irqsave(&kaweth->device_lock, flags);
 	if (IS_BLOCKED(kaweth->status)) {
-		spin_unlock(&kaweth->device_lock);
+		spin_unlock_irqrestore(&kaweth->device_lock, flags);
 		return;
 	}
-	spin_unlock(&kaweth->device_lock);
+	spin_unlock_irqrestore(&kaweth->device_lock, flags);
 
 	if(status && status != -EREMOTEIO && count != 1) {
 		dev_err(&kaweth->intf->dev,
-- 
cgit v1.2.3


From ed7aa30e861510043f602b39f460c90aba792776 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:31:20 +0200
Subject: net: usb: r8152: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 86f7196f9d91..c08c0d633407 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1252,6 +1252,7 @@ static void read_bulk_callback(struct urb *urb)
 	int status = urb->status;
 	struct rx_agg *agg;
 	struct r8152 *tp;
+	unsigned long flags;
 
 	agg = urb->context;
 	if (!agg)
@@ -1281,9 +1282,9 @@ static void read_bulk_callback(struct urb *urb)
 		if (urb->actual_length < ETH_ZLEN)
 			break;
 
-		spin_lock(&tp->rx_lock);
+		spin_lock_irqsave(&tp->rx_lock, flags);
 		list_add_tail(&agg->list, &tp->rx_done);
-		spin_unlock(&tp->rx_lock);
+		spin_unlock_irqrestore(&tp->rx_lock, flags);
 		napi_schedule(&tp->napi);
 		return;
 	case -ESHUTDOWN:
@@ -1311,6 +1312,7 @@ static void write_bulk_callback(struct urb *urb)
 	struct net_device *netdev;
 	struct tx_agg *agg;
 	struct r8152 *tp;
+	unsigned long flags;
 	int status = urb->status;
 
 	agg = urb->context;
@@ -1332,9 +1334,9 @@ static void write_bulk_callback(struct urb *urb)
 		stats->tx_bytes += agg->skb_len;
 	}
 
-	spin_lock(&tp->tx_lock);
+	spin_lock_irqsave(&tp->tx_lock, flags);
 	list_add_tail(&agg->list, &tp->tx_free);
-	spin_unlock(&tp->tx_lock);
+	spin_unlock_irqrestore(&tp->tx_lock, flags);
 
 	usb_autopm_put_interface_async(tp->intf);
 
-- 
cgit v1.2.3


From feae641d2914e1559a29b9bf2e349578c3634b00 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:31:21 +0200
Subject: net: usb: rtl8150: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: Petko Manolov <petkan@nucleusys.com>
Cc: "David S. Miller" <davem@davemloft.net>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/rtl8150.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/rtl8150.c b/drivers/net/usb/rtl8150.c
index 5f565bd574da..0e81d4c441d9 100644
--- a/drivers/net/usb/rtl8150.c
+++ b/drivers/net/usb/rtl8150.c
@@ -391,6 +391,7 @@ static void read_bulk_callback(struct urb *urb)
 	u16 rx_stat;
 	int status = urb->status;
 	int result;
+	unsigned long flags;
 
 	dev = urb->context;
 	if (!dev)
@@ -432,9 +433,9 @@ static void read_bulk_callback(struct urb *urb)
 	netdev->stats.rx_packets++;
 	netdev->stats.rx_bytes += pkt_len;
 
-	spin_lock(&dev->rx_pool_lock);
+	spin_lock_irqsave(&dev->rx_pool_lock, flags);
 	skb = pull_skb(dev);
-	spin_unlock(&dev->rx_pool_lock);
+	spin_unlock_irqrestore(&dev->rx_pool_lock, flags);
 	if (!skb)
 		goto resched;
 
-- 
cgit v1.2.3


From cadefe5f584abaac40dce72009e4de738cbff467 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 20 Jun 2018 16:07:35 -0400
Subject: tcp_bbr: fix bbr pacing rate for internal pacing

This commit makes BBR use only the MSS (without any headers) to
calculate pacing rates when internal TCP-layer pacing is used.

This is necessary to achieve the correct pacing behavior in this case,
since tcp_internal_pacing() uses only the payload length to calculate
pacing delays.

Signed-off-by: Kevin Yang <yyd@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 11 +++++++++++
 net/ipv4/tcp_bbr.c    |  6 +++++-
 net/ipv4/tcp_output.c | 14 --------------
 3 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 0448e7c5d2b4..822ee49ed0f9 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1184,6 +1184,17 @@ static inline bool tcp_is_cwnd_limited(const struct sock *sk)
 	return tp->is_cwnd_limited;
 }
 
+/* BBR congestion control needs pacing.
+ * Same remark for SO_MAX_PACING_RATE.
+ * sch_fq packet scheduler is efficiently handling pacing,
+ * but is not always installed/used.
+ * Return true if TCP stack should pace packets itself.
+ */
+static inline bool tcp_needs_internal_pacing(const struct sock *sk)
+{
+	return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
+}
+
 /* Something is really bad, we could not queue an additional packet,
  * because qdisc is full or receiver sent a 0 window.
  * We do not want to add fuel to the fire, or abort too early,
diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c
index 58e2f479ffb4..3b5f45b9e81e 100644
--- a/net/ipv4/tcp_bbr.c
+++ b/net/ipv4/tcp_bbr.c
@@ -205,7 +205,11 @@ static u32 bbr_bw(const struct sock *sk)
  */
 static u64 bbr_rate_bytes_per_sec(struct sock *sk, u64 rate, int gain)
 {
-	rate *= tcp_mss_to_mtu(sk, tcp_sk(sk)->mss_cache);
+	unsigned int mss = tcp_sk(sk)->mss_cache;
+
+	if (!tcp_needs_internal_pacing(sk))
+		mss = tcp_mss_to_mtu(sk, mss);
+	rate *= mss;
 	rate *= gain;
 	rate >>= BBR_SCALE;
 	rate *= USEC_PER_SEC;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e08b409c71e..f8f6129160dd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -973,17 +973,6 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-/* BBR congestion control needs pacing.
- * Same remark for SO_MAX_PACING_RATE.
- * sch_fq packet scheduler is efficiently handling pacing,
- * but is not always installed/used.
- * Return true if TCP stack should pace packets itself.
- */
-static bool tcp_needs_internal_pacing(const struct sock *sk)
-{
-	return smp_load_acquire(&sk->sk_pacing_status) == SK_PACING_NEEDED;
-}
-
 static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 {
 	u64 len_ns;
@@ -995,9 +984,6 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 	if (!rate || rate == ~0U)
 		return;
 
-	/* Should account for header sizes as sch_fq does,
-	 * but lets make things simple.
-	 */
 	len_ns = (u64)skb->len * NSEC_PER_SEC;
 	do_div(len_ns, rate);
 	hrtimer_start(&tcp_sk(sk)->pacing_timer,
-- 
cgit v1.2.3


From 671646c151d492c3846e6e6797e72ff757b5d65e Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 21 Jun 2018 16:30:38 +0800
Subject: r8169: Don't disable ASPM in the driver

Enable or disable ASPM should be done in PCI core instead of in the
device driver.

Commit ba04c7c93bbc ("r8169: disable ASPM") uses
pci_disable_link_state() to disable ASPM, but it's not the best way to
do it. If the device really wants to disable ASPM, we can use a quirk in
PCI core to prevent the PCI core from setting ASPM before probe.

Let's remove pci_disable_link_state() for now. Use PCI core quirks if
any regression happens.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f4cae2be0fda..49467c2b7a0a 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -25,7 +25,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/pm_runtime.h>
 #include <linux/firmware.h>
-#include <linux/pci-aspm.h>
 #include <linux/prefetch.h>
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
@@ -7647,11 +7646,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	mii->reg_num_mask = 0x1f;
 	mii->supports_gmii = cfg->has_gmii;
 
-	/* disable ASPM completely as that cause random device stop working
-	 * problems as well as full system hangs for some PCIe devices users */
-	pci_disable_link_state(pdev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1 |
-				     PCIE_LINK_STATE_CLKPM);
-
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
 	if (rc < 0) {
-- 
cgit v1.2.3


From a99790bf5c7f3d68d8b01e015d3212a98ee7bd57 Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 21 Jun 2018 16:30:39 +0800
Subject: r8169: Reinstate ASPM Support

On Intel platforms (Skylake and newer), ASPM support in r8169 is the
last missing puzzle to let CPU's Package C-State reaches PC8.  Without
ASPM support, the CPU cannot reach beyond PC3. PC8 can save additional
~3W in comparison with PC3 on a Coffee Lake platform, Dell G3 3779.

This is based on the work from Chunhao Lin <hau@realtek.com>.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 39 +++++++++++++++++++++++++-----------
 1 file changed, 27 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 49467c2b7a0a..06e14da1b4af 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5289,6 +5289,17 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable)
 	RTL_W8(tp, Config3, data);
 }
 
+static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable)
+{
+	if (enable) {
+		RTL_W8(tp, Config2, RTL_R8(tp, Config2) | ClkReqEn);
+		RTL_W8(tp, Config5, RTL_R8(tp, Config5) | ASPM_en);
+	} else {
+		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
+		RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	}
+}
+
 static void rtl_hw_start_8168bb(struct rtl8169_private *tp)
 {
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
@@ -5645,9 +5656,9 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp)
 	rtl_hw_start_8168g(tp);
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168g_1, ARRAY_SIZE(e_info_8168g_1));
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168g_2(struct rtl8169_private *tp)
@@ -5680,9 +5691,9 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp)
 	rtl_hw_start_8168g(tp);
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8411_2, ARRAY_SIZE(e_info_8411_2));
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
@@ -5699,8 +5710,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168h_1, ARRAY_SIZE(e_info_8168h_1));
 
 	RTL_W32(tp, TxConfig, RTL_R32(tp, TxConfig) | TXCFG_AUTO_FIFO);
@@ -5779,6 +5789,8 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	r8168_mac_ocp_write(tp, 0xe63e, 0x0000);
 	r8168_mac_ocp_write(tp, 0xc094, 0x0000);
 	r8168_mac_ocp_write(tp, 0xc09e, 0x0000);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
@@ -5830,11 +5842,12 @@ static void rtl_hw_start_8168ep_1(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168ep_1, ARRAY_SIZE(e_info_8168ep_1));
 
 	rtl_hw_start_8168ep(tp);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp)
@@ -5846,14 +5859,15 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168ep_2, ARRAY_SIZE(e_info_8168ep_2));
 
 	rtl_hw_start_8168ep(tp);
 
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN);
 	RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
@@ -5867,8 +5881,7 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 	};
 
 	/* disable aspm and clock request before access ephy */
-	RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~ClkReqEn);
-	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~ASPM_en);
+	rtl_hw_aspm_clkreq_enable(tp, false);
 	rtl_ephy_init(tp, e_info_8168ep_3, ARRAY_SIZE(e_info_8168ep_3));
 
 	rtl_hw_start_8168ep(tp);
@@ -5888,6 +5901,8 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp)
 	data = r8168_mac_ocp_read(tp, 0xe860);
 	data |= 0x0080;
 	r8168_mac_ocp_write(tp, 0xe860, data);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From 01bdee64f9cf8e15f998bf52789ed9d0ebdfa621 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Fri, 22 Jun 2018 15:07:40 +0900
Subject: kprobes/Documentation: Fix various typos

Fix typos and clean up the wording, with the help of Randy Dunlap.

Suggested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arch@vger.kernel.org
Cc: linux-doc@vger.kernel.org
Link: http://lkml.kernel.org/r/20180622150740.bd26241032c972d86e23bf73@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/kprobes.txt | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/Documentation/kprobes.txt b/Documentation/kprobes.txt
index 13d8efdb9718..10f4499e677c 100644
--- a/Documentation/kprobes.txt
+++ b/Documentation/kprobes.txt
@@ -83,22 +83,22 @@ Execution then continues with the instruction following the probepoint.
 Changing Execution Path
 -----------------------
 
-Since the kprobes can probe into a running kernel code, it can change
-the register set, including instruction pointer. This operation
-requires maximum attention, such as keeping the stack frame, recovering
-execution path etc. Since it is operated on running kernel and need deep
-knowladge of the archtecture and concurrent computing, you can easily
-shot your foot.
+Since kprobes can probe into a running kernel code, it can change the
+register set, including instruction pointer. This operation requires
+maximum care, such as keeping the stack frame, recovering the execution
+path etc. Since it operates on a running kernel and needs deep knowledge
+of computer architecture and concurrent computing, you can easily shoot
+your foot.
 
 If you change the instruction pointer (and set up other related
-registers) in pre_handler, you must return !0 so that the kprobes
-stops single stepping and just returns to given address.
+registers) in pre_handler, you must return !0 so that kprobes stops
+single stepping and just returns to the given address.
 This also means post_handler should not be called anymore.
 
-Note that this operation may be harder on some architectures which
-use TOC (Table of Contents) for function call, since you have to
-setup new TOC for your function in your module, and recover old
-one after back from it.
+Note that this operation may be harder on some architectures which use
+TOC (Table of Contents) for function call, since you have to setup a new
+TOC for your function in your module, and recover the old one after
+returning from it.
 
 Return Probes
 -------------
-- 
cgit v1.2.3


From 372401efd9eeee24701848874ecb9845524013ee Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 22 May 2018 18:34:56 +0200
Subject: dt-bindings: clock: add meson axg audio clock controller bindings

Export the clock ids dt-bindings usable by the consumers of the clock
controller and add the documentation for the device tree bindings of
the audio clock controller of the A113 based SoCs.

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 .../bindings/clock/amlogic,axg-audio-clkc.txt      | 56 +++++++++++++
 include/dt-bindings/clock/axg-audio-clkc.h         | 94 ++++++++++++++++++++++
 2 files changed, 150 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt
 create mode 100644 include/dt-bindings/clock/axg-audio-clkc.h

diff --git a/Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt b/Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt
new file mode 100644
index 000000000000..61777ad24f61
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/amlogic,axg-audio-clkc.txt
@@ -0,0 +1,56 @@
+* Amlogic AXG Audio Clock Controllers
+
+The Amlogic AXG audio clock controller generates and supplies clock to the
+other elements of the audio subsystem, such as fifos, i2s, spdif and pdm
+devices.
+
+Required Properties:
+
+- compatible	: should be "amlogic,axg-audio-clkc" for the A113X and A113D
+- reg		: physical base address of the clock controller and length of
+		  memory mapped region.
+- clocks	: a list of phandle + clock-specifier pairs for the clocks listed
+		  in clock-names.
+- clock-names	: must contain the following:
+		  * "pclk" - Main peripheral bus clock
+		  may contain the following:
+		  * "mst_in[0-7]" - 8 input plls to generate clock signals
+		  * "slv_sclk[0-9]" - 10 slave bit clocks provided by external
+				      components.
+		  * "slv_lrclk[0-9]" - 10 slave sample clocks provided by external
+				       components.
+- resets	: phandle of the internal reset line
+- #clock-cells	: should be 1.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/axg-audio-clkc.h header and can be
+used in device tree sources.
+
+Example:
+
+clkc_audio: clock-controller@0 {
+	compatible = "amlogic,axg-audio-clkc";
+	reg = <0x0 0x0 0x0 0xb4>;
+	#clock-cells = <1>;
+
+	clocks = <&clkc CLKID_AUDIO>,
+		 <&clkc CLKID_MPLL0>,
+		 <&clkc CLKID_MPLL1>,
+		 <&clkc CLKID_MPLL2>,
+		 <&clkc CLKID_MPLL3>,
+		 <&clkc CLKID_HIFI_PLL>,
+		 <&clkc CLKID_FCLK_DIV3>,
+		 <&clkc CLKID_FCLK_DIV4>,
+		 <&clkc CLKID_GP0_PLL>;
+	clock-names = "pclk",
+		      "mst_in0",
+		      "mst_in1",
+		      "mst_in2",
+		      "mst_in3",
+		      "mst_in4",
+		      "mst_in5",
+		      "mst_in6",
+		      "mst_in7";
+	resets = <&reset RESET_AUDIO>;
+};
diff --git a/include/dt-bindings/clock/axg-audio-clkc.h b/include/dt-bindings/clock/axg-audio-clkc.h
new file mode 100644
index 000000000000..fd9c362099d9
--- /dev/null
+++ b/include/dt-bindings/clock/axg-audio-clkc.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Copyright (c) 2018 Baylibre SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef __AXG_AUDIO_CLKC_BINDINGS_H
+#define __AXG_AUDIO_CLKC_BINDINGS_H
+
+#define AUD_CLKID_SLV_SCLK0		9
+#define AUD_CLKID_SLV_SCLK1		10
+#define AUD_CLKID_SLV_SCLK2		11
+#define AUD_CLKID_SLV_SCLK3		12
+#define AUD_CLKID_SLV_SCLK4		13
+#define AUD_CLKID_SLV_SCLK5		14
+#define AUD_CLKID_SLV_SCLK6		15
+#define AUD_CLKID_SLV_SCLK7		16
+#define AUD_CLKID_SLV_SCLK8		17
+#define AUD_CLKID_SLV_SCLK9		18
+#define AUD_CLKID_SLV_LRCLK0		19
+#define AUD_CLKID_SLV_LRCLK1		20
+#define AUD_CLKID_SLV_LRCLK2		21
+#define AUD_CLKID_SLV_LRCLK3		22
+#define AUD_CLKID_SLV_LRCLK4		23
+#define AUD_CLKID_SLV_LRCLK5		24
+#define AUD_CLKID_SLV_LRCLK6		25
+#define AUD_CLKID_SLV_LRCLK7		26
+#define AUD_CLKID_SLV_LRCLK8		27
+#define AUD_CLKID_SLV_LRCLK9		28
+#define AUD_CLKID_DDR_ARB		29
+#define AUD_CLKID_PDM			30
+#define AUD_CLKID_TDMIN_A		31
+#define AUD_CLKID_TDMIN_B		32
+#define AUD_CLKID_TDMIN_C		33
+#define AUD_CLKID_TDMIN_LB		34
+#define AUD_CLKID_TDMOUT_A		35
+#define AUD_CLKID_TDMOUT_B		36
+#define AUD_CLKID_TDMOUT_C		37
+#define AUD_CLKID_FRDDR_A		38
+#define AUD_CLKID_FRDDR_B		39
+#define AUD_CLKID_FRDDR_C		40
+#define AUD_CLKID_TODDR_A		41
+#define AUD_CLKID_TODDR_B		42
+#define AUD_CLKID_TODDR_C		43
+#define AUD_CLKID_LOOPBACK		44
+#define AUD_CLKID_SPDIFIN		45
+#define AUD_CLKID_SPDIFOUT		46
+#define AUD_CLKID_RESAMPLE		47
+#define AUD_CLKID_POWER_DETECT		48
+#define AUD_CLKID_MST_A_MCLK		49
+#define AUD_CLKID_MST_B_MCLK		50
+#define AUD_CLKID_MST_C_MCLK		51
+#define AUD_CLKID_MST_D_MCLK		52
+#define AUD_CLKID_MST_E_MCLK		53
+#define AUD_CLKID_MST_F_MCLK		54
+#define AUD_CLKID_SPDIFOUT_CLK		55
+#define AUD_CLKID_SPDIFIN_CLK		56
+#define AUD_CLKID_PDM_DCLK		57
+#define AUD_CLKID_PDM_SYSCLK		58
+#define AUD_CLKID_MST_A_SCLK		79
+#define AUD_CLKID_MST_B_SCLK		80
+#define AUD_CLKID_MST_C_SCLK		81
+#define AUD_CLKID_MST_D_SCLK		82
+#define AUD_CLKID_MST_E_SCLK		83
+#define AUD_CLKID_MST_F_SCLK		84
+#define AUD_CLKID_MST_A_LRCLK		86
+#define AUD_CLKID_MST_B_LRCLK		87
+#define AUD_CLKID_MST_C_LRCLK		88
+#define AUD_CLKID_MST_D_LRCLK		89
+#define AUD_CLKID_MST_E_LRCLK		90
+#define AUD_CLKID_MST_F_LRCLK		91
+#define AUD_CLKID_TDMIN_A_SCLK_SEL	116
+#define AUD_CLKID_TDMIN_B_SCLK_SEL	117
+#define AUD_CLKID_TDMIN_C_SCLK_SEL	118
+#define AUD_CLKID_TDMIN_LB_SCLK_SEL	119
+#define AUD_CLKID_TDMOUT_A_SCLK_SEL	120
+#define AUD_CLKID_TDMOUT_B_SCLK_SEL	121
+#define AUD_CLKID_TDMOUT_C_SCLK_SEL	122
+#define AUD_CLKID_TDMIN_A_SCLK		123
+#define AUD_CLKID_TDMIN_B_SCLK		124
+#define AUD_CLKID_TDMIN_C_SCLK		125
+#define AUD_CLKID_TDMIN_LB_SCLK		126
+#define AUD_CLKID_TDMOUT_A_SCLK		127
+#define AUD_CLKID_TDMOUT_B_SCLK		128
+#define AUD_CLKID_TDMOUT_C_SCLK		129
+#define AUD_CLKID_TDMIN_A_LRCLK		130
+#define AUD_CLKID_TDMIN_B_LRCLK		131
+#define AUD_CLKID_TDMIN_C_LRCLK		132
+#define AUD_CLKID_TDMIN_LB_LRCLK	133
+#define AUD_CLKID_TDMOUT_A_LRCLK	134
+#define AUD_CLKID_TDMOUT_B_LRCLK	135
+#define AUD_CLKID_TDMOUT_C_LRCLK	136
+
+#endif /* __AXG_AUDIO_CLKC_BINDINGS_H */
-- 
cgit v1.2.3


From 74bdf7815dfb3805a37b0bba615814063a227bf5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 20 Jun 2018 08:03:32 -0700
Subject: genirq: Speedup show_interrupts()

Since commit 425a5072dcd1 ("genirq: Free irq_desc with rcu"),
show_interrupts() can be switched to rcu locking, which removes possible
contention on sparse_irq_lock.

The per_cpu count scan and print can be done without holding desc spinlock.

And there is no need to call kstat_irqs_cpu() and abuse irq_to_desc() while
holding rcu read lock, since desc and desc->kstat_irqs wont disappear or
change.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Link: https://lkml.kernel.org/r/20180620150332.163320-1-edumazet@google.com
---
 kernel/irq/proc.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 37eda10f5c36..da9addb8d655 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -475,22 +475,24 @@ int show_interrupts(struct seq_file *p, void *v)
 		seq_putc(p, '\n');
 	}
 
-	irq_lock_sparse();
+	rcu_read_lock();
 	desc = irq_to_desc(i);
 	if (!desc)
 		goto outsparse;
 
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if ((!action || irq_desc_is_chained(desc)) && !any_count)
-		goto out;
+	if (desc->kstat_irqs)
+		for_each_online_cpu(j)
+			any_count |= *per_cpu_ptr(desc->kstat_irqs, j);
+
+	if ((!desc->action || irq_desc_is_chained(desc)) && !any_count)
+		goto outsparse;
 
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
+		seq_printf(p, "%10u ", desc->kstat_irqs ?
+					*per_cpu_ptr(desc->kstat_irqs, j) : 0);
 
+	raw_spin_lock_irqsave(&desc->lock, flags);
 	if (desc->irq_data.chip) {
 		if (desc->irq_data.chip->irq_print_chip)
 			desc->irq_data.chip->irq_print_chip(&desc->irq_data, p);
@@ -511,6 +513,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	if (desc->name)
 		seq_printf(p, "-%-8s", desc->name);
 
+	action = desc->action;
 	if (action) {
 		seq_printf(p, "  %s", action->name);
 		while ((action = action->next) != NULL)
@@ -518,10 +521,9 @@ int show_interrupts(struct seq_file *p, void *v)
 	}
 
 	seq_putc(p, '\n');
-out:
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 outsparse:
-	irq_unlock_sparse();
+	rcu_read_unlock();
 	return 0;
 }
 #endif
-- 
cgit v1.2.3


From bc39f010200d09dc6d4d5e613e86dfd0b22c63b3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 22 Jun 2018 11:54:22 +0200
Subject: x86/mce: Always use 64-bit timestamps

The machine check timestamp uses get_seconds(), which returns an
'unsigned long' number that might overflow on 32-bit architectures (in
the distant future) and is therefore deprecated.

The normal replacement would be ktime_get_real_seconds(), but that needs
to use a sequence lock that might cause a deadlock if the MCE happens at
just the wrong moment. The __ktime_get_real_seconds() skips that lock
and is safer here, but has a miniscule risk of returning the wrong time
when we read it on a 32-bit architecture at the same time as updating
the epoch, i.e. from before y2106 overflow time to after, or vice versa.

This seems to be an acceptable risk in this particular case, and is the
same thing we do in kdb.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Cc: y2038@lists.linaro.org
Link: http://lkml.kernel.org/r/20180618100759.1921750-1-arnd@arndb.de
---
 arch/x86/kernel/cpu/mcheck/mce.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e93670d736a6..d62201e40027 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -123,8 +123,8 @@ void mce_setup(struct mce *m)
 {
 	memset(m, 0, sizeof(struct mce));
 	m->cpu = m->extcpu = smp_processor_id();
-	/* We hope get_seconds stays lockless */
-	m->time = get_seconds();
+	/* need the internal __ version to avoid deadlocks */
+	m->time = __ktime_get_real_seconds();
 	m->cpuvendor = boot_cpu_data.x86_vendor;
 	m->cpuid = cpuid_eax(1);
 	m->socketid = cpu_data(m->extcpu).phys_proc_id;
-- 
cgit v1.2.3


From d3d6923cd1ae61a493a405f2f001293ab62eb092 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Fri, 22 Jun 2018 11:54:24 +0200
Subject: x86/mce: Carve out the crashing_cpu check

Carve out the rendezvous handler timeout avoidance check into a separate
function in order to simplify the #MC handler.

No functional changes.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180622095428.626-4-bp@alien8.de
---
 arch/x86/kernel/cpu/mcheck/mce.c | 64 +++++++++++++++++++++++-----------------
 1 file changed, 37 insertions(+), 27 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d62201e40027..18804834dbc0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1104,6 +1104,34 @@ static void mce_unmap_kpfn(unsigned long pfn)
 }
 #endif
 
+
+/*
+ * Cases where we avoid rendezvous handler timeout:
+ * 1) If this CPU is offline.
+ *
+ * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
+ *  skip those CPUs which remain looping in the 1st kernel - see
+ *  crash_nmi_callback().
+ *
+ * Note: there still is a small window between kexec-ing and the new,
+ * kdump kernel establishing a new #MC handler where a broadcasted MCE
+ * might not get handled properly.
+ */
+static bool __mc_check_crashing_cpu(int cpu)
+{
+	if (cpu_is_offline(cpu) ||
+	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
+		u64 mcgstatus;
+
+		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+		if (mcgstatus & MCG_STATUS_RIPV) {
+			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+			return true;
+		}
+	}
+	return false;
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1118,60 +1146,42 @@ static void mce_unmap_kpfn(unsigned long pfn)
  */
 void do_machine_check(struct pt_regs *regs, long error_code)
 {
+	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
+	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
 	struct mca_config *cfg = &mca_cfg;
+	int cpu = smp_processor_id();
+	char *msg = "Unknown";
 	struct mce m, *final;
-	int i;
 	int worst = 0;
 	int severity;
+	int i;
 
 	/*
 	 * Establish sequential order between the CPUs entering the machine
 	 * check handler.
 	 */
 	int order = -1;
+
 	/*
 	 * If no_way_out gets set, there is no safe way to recover from this
 	 * MCE.  If mca_cfg.tolerant is cranked up, we'll try anyway.
 	 */
 	int no_way_out = 0;
+
 	/*
 	 * If kill_it gets set, there might be a way to recover from this
 	 * error.
 	 */
 	int kill_it = 0;
-	DECLARE_BITMAP(toclear, MAX_NR_BANKS);
-	DECLARE_BITMAP(valid_banks, MAX_NR_BANKS);
-	char *msg = "Unknown";
 
 	/*
 	 * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES
 	 * on Intel.
 	 */
 	int lmce = 1;
-	int cpu = smp_processor_id();
-
-	/*
-	 * Cases where we avoid rendezvous handler timeout:
-	 * 1) If this CPU is offline.
-	 *
-	 * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to
-	 *  skip those CPUs which remain looping in the 1st kernel - see
-	 *  crash_nmi_callback().
-	 *
-	 * Note: there still is a small window between kexec-ing and the new,
-	 * kdump kernel establishing a new #MC handler where a broadcasted MCE
-	 * might not get handled properly.
-	 */
-	if (cpu_is_offline(cpu) ||
-	    (crashing_cpu != -1 && crashing_cpu != cpu)) {
-		u64 mcgstatus;
 
-		mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
-		if (mcgstatus & MCG_STATUS_RIPV) {
-			mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-			return;
-		}
-	}
+	if (__mc_check_crashing_cpu(cpu))
+		return;
 
 	ist_enter(regs);
 
-- 
cgit v1.2.3


From 45deca7d96e0e33061b7d12932b381114db18f60 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Fri, 22 Jun 2018 11:54:25 +0200
Subject: x86/mce: Remove !banks check

If we don't have MCA banks, we won't see machine checks anyway. Drop the
check.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180622095428.626-5-bp@alien8.de
---
 arch/x86/kernel/cpu/mcheck/mce.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 18804834dbc0..8ac2ea2a874a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1187,9 +1187,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 
 	this_cpu_inc(mce_exception_count);
 
-	if (!cfg->banks)
-		goto out;
-
 	mce_gather_info(&m, regs);
 	m.tsc = rdtsc();
 
@@ -1329,7 +1326,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	if (worst > 0)
 		mce_report_event(regs);
 	mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
-out:
+
 	sync_core();
 
 	if (worst != MCE_AR_SEVERITY && !kill_it)
-- 
cgit v1.2.3


From f35565e3986dcc5dde52649d461543cde1b745cd Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Fri, 22 Jun 2018 11:54:26 +0200
Subject: x86/mce: Carve out bank scanning code

Carve out the scan loop into a separate function.

No functional changes.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180622095428.626-6-bp@alien8.de
---
 arch/x86/kernel/cpu/mcheck/mce.c | 134 +++++++++++++++++++++------------------
 1 file changed, 71 insertions(+), 63 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 8ac2ea2a874a..d23fcd8d11c9 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1132,6 +1132,76 @@ static bool __mc_check_crashing_cpu(int cpu)
 	return false;
 }
 
+static void __mc_scan_banks(struct mce *m, struct mce *final,
+			    unsigned long *toclear, unsigned long *valid_banks,
+			    int no_way_out, int *worst)
+{
+	struct mca_config *cfg = &mca_cfg;
+	int severity, i;
+
+	for (i = 0; i < cfg->banks; i++) {
+		__clear_bit(i, toclear);
+		if (!test_bit(i, valid_banks))
+			continue;
+		if (!mce_banks[i].ctl)
+			continue;
+
+		m->misc = 0;
+		m->addr = 0;
+		m->bank = i;
+
+		m->status = mce_rdmsrl(msr_ops.status(i));
+		if ((m->status & MCI_STATUS_VAL) == 0)
+			continue;
+
+		/*
+		 * Non uncorrected or non signaled errors are handled by
+		 * machine_check_poll. Leave them alone, unless this panics.
+		 */
+		if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
+			!no_way_out)
+			continue;
+
+		/*
+		 * Set taint even when machine check was not enabled.
+		 */
+		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
+
+		severity = mce_severity(m, cfg->tolerant, NULL, true);
+
+		/*
+		 * When machine check was for corrected/deferred handler don't
+		 * touch, unless we're panicing.
+		 */
+		if ((severity == MCE_KEEP_SEVERITY ||
+		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
+			continue;
+		__set_bit(i, toclear);
+		if (severity == MCE_NO_SEVERITY) {
+			/*
+			 * Machine check event was not enabled. Clear, but
+			 * ignore.
+			 */
+			continue;
+		}
+
+		mce_read_aux(m, i);
+
+		/* assuming valid severity level != 0 */
+		m->severity = severity;
+
+		mce_log(m);
+
+		if (severity > *worst) {
+			*final = *m;
+			*worst = severity;
+		}
+	}
+
+	/* mce_clear_state will clear *final, save locally for use later */
+	*m = *final;
+}
+
 /*
  * The actual machine check handler. This only handles real
  * exceptions when something got corrupted coming in through int 18.
@@ -1153,8 +1223,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 	char *msg = "Unknown";
 	struct mce m, *final;
 	int worst = 0;
-	int severity;
-	int i;
 
 	/*
 	 * Establish sequential order between the CPUs entering the machine
@@ -1227,67 +1295,7 @@ void do_machine_check(struct pt_regs *regs, long error_code)
 		order = mce_start(&no_way_out);
 	}
 
-	for (i = 0; i < cfg->banks; i++) {
-		__clear_bit(i, toclear);
-		if (!test_bit(i, valid_banks))
-			continue;
-		if (!mce_banks[i].ctl)
-			continue;
-
-		m.misc = 0;
-		m.addr = 0;
-		m.bank = i;
-
-		m.status = mce_rdmsrl(msr_ops.status(i));
-		if ((m.status & MCI_STATUS_VAL) == 0)
-			continue;
-
-		/*
-		 * Non uncorrected or non signaled errors are handled by
-		 * machine_check_poll. Leave them alone, unless this panics.
-		 */
-		if (!(m.status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
-			!no_way_out)
-			continue;
-
-		/*
-		 * Set taint even when machine check was not enabled.
-		 */
-		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
-
-		severity = mce_severity(&m, cfg->tolerant, NULL, true);
-
-		/*
-		 * When machine check was for corrected/deferred handler don't
-		 * touch, unless we're panicing.
-		 */
-		if ((severity == MCE_KEEP_SEVERITY ||
-		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
-			continue;
-		__set_bit(i, toclear);
-		if (severity == MCE_NO_SEVERITY) {
-			/*
-			 * Machine check event was not enabled. Clear, but
-			 * ignore.
-			 */
-			continue;
-		}
-
-		mce_read_aux(&m, i);
-
-		/* assuming valid severity level != 0 */
-		m.severity = severity;
-
-		mce_log(&m);
-
-		if (severity > worst) {
-			*final = m;
-			worst = severity;
-		}
-	}
-
-	/* mce_clear_state will clear *final, save locally for use later */
-	m = *final;
+	__mc_scan_banks(&m, final, toclear, valid_banks, no_way_out, &worst);
 
 	if (!no_way_out)
 		mce_clear_state(toclear);
-- 
cgit v1.2.3


From d5c84ef202d7db9c838448229f62d66560b951e5 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Fri, 22 Jun 2018 11:54:27 +0200
Subject: x86/mce: Cleanup __mc_scan_banks()

Correct comments, improve readability, simplify.

No functional changes.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180622095428.626-7-bp@alien8.de
---
 arch/x86/kernel/cpu/mcheck/mce.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index d23fcd8d11c9..888b51bef13d 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1143,6 +1143,7 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 		__clear_bit(i, toclear);
 		if (!test_bit(i, valid_banks))
 			continue;
+
 		if (!mce_banks[i].ctl)
 			continue;
 
@@ -1151,39 +1152,35 @@ static void __mc_scan_banks(struct mce *m, struct mce *final,
 		m->bank = i;
 
 		m->status = mce_rdmsrl(msr_ops.status(i));
-		if ((m->status & MCI_STATUS_VAL) == 0)
+		if (!(m->status & MCI_STATUS_VAL))
 			continue;
 
 		/*
-		 * Non uncorrected or non signaled errors are handled by
-		 * machine_check_poll. Leave them alone, unless this panics.
+		 * Corrected or non-signaled errors are handled by
+		 * machine_check_poll(). Leave them alone, unless this panics.
 		 */
 		if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) &&
 			!no_way_out)
 			continue;
 
-		/*
-		 * Set taint even when machine check was not enabled.
-		 */
+		/* Set taint even when machine check was not enabled. */
 		add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE);
 
 		severity = mce_severity(m, cfg->tolerant, NULL, true);
 
 		/*
 		 * When machine check was for corrected/deferred handler don't
-		 * touch, unless we're panicing.
+		 * touch, unless we're panicking.
 		 */
 		if ((severity == MCE_KEEP_SEVERITY ||
 		     severity == MCE_UCNA_SEVERITY) && !no_way_out)
 			continue;
+
 		__set_bit(i, toclear);
-		if (severity == MCE_NO_SEVERITY) {
-			/*
-			 * Machine check event was not enabled. Clear, but
-			 * ignore.
-			 */
+
+		/* Machine check event was not enabled. Clear, but ignore. */
+		if (severity == MCE_NO_SEVERITY)
 			continue;
-		}
 
 		mce_read_aux(m, i);
 
-- 
cgit v1.2.3


From 7ce2f0393ea2396142b7faf6ee9b1f3676d08a5f Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@suse.de>
Date: Fri, 22 Jun 2018 11:34:11 +0200
Subject: x86/CPU/AMD: Move TOPOEXT reenablement before reading
 smp_num_siblings

The TOPOEXT reenablement is a workaround for broken BIOSen which didn't
enable the CPUID bit. amd_get_topology_early(), however, relies on
that bit being set so that it can read out the CPUID leaf and set
smp_num_siblings properly.

Move the reenablement up to early_init_amd(). While at it, simplify
amd_get_topology_early().

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/amd.c | 37 +++++++++++++++++--------------------
 1 file changed, 17 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index b20dee982a53..74061e421e62 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -318,12 +318,8 @@ static void legacy_fixup_core_id(struct cpuinfo_x86 *c)
 
 static void amd_get_topology_early(struct cpuinfo_x86 *c)
 {
-	if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
-		u32 eax, ebx, ecx, edx;
-
-		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
-	}
+	if (cpu_has(c, X86_FEATURE_TOPOEXT))
+		smp_num_siblings = ((cpuid_ebx(0x8000001e) >> 8) & 0xff) + 1;
 }
 
 /*
@@ -345,7 +341,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c)
 		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
 
 		node_id  = ecx & 0xff;
-		smp_num_siblings = ((ebx >> 8) & 0xff) + 1;
 
 		if (c->x86 == 0x15)
 			c->cu_id = ebx & 0xff;
@@ -622,6 +617,7 @@ clear_sev:
 
 static void early_init_amd(struct cpuinfo_x86 *c)
 {
+	u64 value;
 	u32 dummy;
 
 	early_init_amd_mc(c);
@@ -693,6 +689,20 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
 	early_detect_mem_encrypt(c);
 
+	/* Re-enable TopologyExtensions if switched off by BIOS */
+	if (c->x86 == 0x15 &&
+	    (c->x86_model >= 0x10 && c->x86_model <= 0x6f) &&
+	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+
+		if (msr_set_bit(0xc0011005, 54) > 0) {
+			rdmsrl(0xc0011005, value);
+			if (value & BIT_64(54)) {
+				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
+			}
+		}
+	}
+
 	amd_get_topology_early(c);
 }
 
@@ -785,19 +795,6 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
 {
 	u64 value;
 
-	/* re-enable TopologyExtensions if switched off by BIOS */
-	if ((c->x86_model >= 0x10) && (c->x86_model <= 0x6f) &&
-	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
-
-		if (msr_set_bit(0xc0011005, 54) > 0) {
-			rdmsrl(0xc0011005, value);
-			if (value & BIT_64(54)) {
-				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
-				pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
-			}
-		}
-	}
-
 	/*
 	 * The way access filter has a performance penalty on some workloads.
 	 * Disable it on the affected CPUs.
-- 
cgit v1.2.3


From d467239f37c4e49158e0569a26c6a9c365ec5b61 Mon Sep 17 00:00:00 2001
From: Michel Pollet <michel.pollet@bp.renesas.com>
Date: Thu, 14 Jun 2018 11:56:30 +0100
Subject: dt-bindings: clock: Add the r9a06g032-sysctrl.h file

This adds the constants necessary to use the renesas,r9a06g032-sysctrl node.

Signed-off-by: Michel Pollet <michel.pollet@bp.renesas.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 include/dt-bindings/clock/r9a06g032-sysctrl.h | 148 ++++++++++++++++++++++++++
 1 file changed, 148 insertions(+)
 create mode 100644 include/dt-bindings/clock/r9a06g032-sysctrl.h

diff --git a/include/dt-bindings/clock/r9a06g032-sysctrl.h b/include/dt-bindings/clock/r9a06g032-sysctrl.h
new file mode 100644
index 000000000000..90c0f3dc1ba1
--- /dev/null
+++ b/include/dt-bindings/clock/r9a06g032-sysctrl.h
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * R9A06G032 sysctrl IDs
+ *
+ * Copyright (C) 2018 Renesas Electronics Europe Limited
+ *
+ * Michel Pollet <michel.pollet@bp.renesas.com>, <buserror@gmail.com>
+ */
+
+#ifndef __DT_BINDINGS_R9A06G032_SYSCTRL_H__
+#define __DT_BINDINGS_R9A06G032_SYSCTRL_H__
+
+#define R9A06G032_CLK_PLL_USB		1
+#define R9A06G032_CLK_48		1	/* AKA CLK_PLL_USB */
+#define R9A06G032_MSEBIS_CLK		3	/* AKA CLKOUT_D16 */
+#define R9A06G032_MSEBIM_CLK		3	/* AKA CLKOUT_D16 */
+#define R9A06G032_CLK_DDRPHY_PLLCLK	5	/* AKA CLKOUT_D1OR2 */
+#define R9A06G032_CLK50			6	/* AKA CLKOUT_D20 */
+#define R9A06G032_CLK25			7	/* AKA CLKOUT_D40 */
+#define R9A06G032_CLK125		9	/* AKA CLKOUT_D8 */
+#define R9A06G032_CLK_P5_PG1		17	/* AKA DIV_P5_PG */
+#define R9A06G032_CLK_REF_SYNC		21	/* AKA DIV_REF_SYNC */
+#define R9A06G032_CLK_25_PG4		26
+#define R9A06G032_CLK_25_PG5		27
+#define R9A06G032_CLK_25_PG6		28
+#define R9A06G032_CLK_25_PG7		29
+#define R9A06G032_CLK_25_PG8		30
+#define R9A06G032_CLK_ADC		31
+#define R9A06G032_CLK_ECAT100		32
+#define R9A06G032_CLK_HSR100		33
+#define R9A06G032_CLK_I2C0		34
+#define R9A06G032_CLK_I2C1		35
+#define R9A06G032_CLK_MII_REF		36
+#define R9A06G032_CLK_NAND		37
+#define R9A06G032_CLK_NOUSBP2_PG6	38
+#define R9A06G032_CLK_P1_PG2		39
+#define R9A06G032_CLK_P1_PG3		40
+#define R9A06G032_CLK_P1_PG4		41
+#define R9A06G032_CLK_P4_PG3		42
+#define R9A06G032_CLK_P4_PG4		43
+#define R9A06G032_CLK_P6_PG1		44
+#define R9A06G032_CLK_P6_PG2		45
+#define R9A06G032_CLK_P6_PG3		46
+#define R9A06G032_CLK_P6_PG4		47
+#define R9A06G032_CLK_PCI_USB		48
+#define R9A06G032_CLK_QSPI0		49
+#define R9A06G032_CLK_QSPI1		50
+#define R9A06G032_CLK_RGMII_REF		51
+#define R9A06G032_CLK_RMII_REF		52
+#define R9A06G032_CLK_SDIO0		53
+#define R9A06G032_CLK_SDIO1		54
+#define R9A06G032_CLK_SERCOS100		55
+#define R9A06G032_CLK_SLCD		56
+#define R9A06G032_CLK_SPI0		57
+#define R9A06G032_CLK_SPI1		58
+#define R9A06G032_CLK_SPI2		59
+#define R9A06G032_CLK_SPI3		60
+#define R9A06G032_CLK_SPI4		61
+#define R9A06G032_CLK_SPI5		62
+#define R9A06G032_CLK_SWITCH		63
+#define R9A06G032_HCLK_ECAT125		65
+#define R9A06G032_HCLK_PINCONFIG	66
+#define R9A06G032_HCLK_SERCOS		67
+#define R9A06G032_HCLK_SGPIO2		68
+#define R9A06G032_HCLK_SGPIO3		69
+#define R9A06G032_HCLK_SGPIO4		70
+#define R9A06G032_HCLK_TIMER0		71
+#define R9A06G032_HCLK_TIMER1		72
+#define R9A06G032_HCLK_USBF		73
+#define R9A06G032_HCLK_USBH		74
+#define R9A06G032_HCLK_USBPM		75
+#define R9A06G032_CLK_48_PG_F		76
+#define R9A06G032_CLK_48_PG4		77
+#define R9A06G032_CLK_DDRPHY_PCLK	81	/* AKA CLK_REF_SYNC_D4 */
+#define R9A06G032_CLK_FW		81	/* AKA CLK_REF_SYNC_D4 */
+#define R9A06G032_CLK_CRYPTO		81	/* AKA CLK_REF_SYNC_D4 */
+#define R9A06G032_CLK_A7MP		84	/* AKA DIV_CA7 */
+#define R9A06G032_HCLK_CAN0		85
+#define R9A06G032_HCLK_CAN1		86
+#define R9A06G032_HCLK_DELTASIGMA	87
+#define R9A06G032_HCLK_PWMPTO		88
+#define R9A06G032_HCLK_RSV		89
+#define R9A06G032_HCLK_SGPIO0		90
+#define R9A06G032_HCLK_SGPIO1		91
+#define R9A06G032_RTOS_MDC		92
+#define R9A06G032_CLK_CM3		93
+#define R9A06G032_CLK_DDRC		94
+#define R9A06G032_CLK_ECAT25		95
+#define R9A06G032_CLK_HSR50		96
+#define R9A06G032_CLK_HW_RTOS		97
+#define R9A06G032_CLK_SERCOS50		98
+#define R9A06G032_HCLK_ADC		99
+#define R9A06G032_HCLK_CM3		100
+#define R9A06G032_HCLK_CRYPTO_EIP150	101
+#define R9A06G032_HCLK_CRYPTO_EIP93	102
+#define R9A06G032_HCLK_DDRC		103
+#define R9A06G032_HCLK_DMA0		104
+#define R9A06G032_HCLK_DMA1		105
+#define R9A06G032_HCLK_GMAC0		106
+#define R9A06G032_HCLK_GMAC1		107
+#define R9A06G032_HCLK_GPIO0		108
+#define R9A06G032_HCLK_GPIO1		109
+#define R9A06G032_HCLK_GPIO2		110
+#define R9A06G032_HCLK_HSR		111
+#define R9A06G032_HCLK_I2C0		112
+#define R9A06G032_HCLK_I2C1		113
+#define R9A06G032_HCLK_LCD		114
+#define R9A06G032_HCLK_MSEBI_M		115
+#define R9A06G032_HCLK_MSEBI_S		116
+#define R9A06G032_HCLK_NAND		117
+#define R9A06G032_HCLK_PG_I		118
+#define R9A06G032_HCLK_PG19		119
+#define R9A06G032_HCLK_PG20		120
+#define R9A06G032_HCLK_PG3		121
+#define R9A06G032_HCLK_PG4		122
+#define R9A06G032_HCLK_QSPI0		123
+#define R9A06G032_HCLK_QSPI1		124
+#define R9A06G032_HCLK_ROM		125
+#define R9A06G032_HCLK_RTC		126
+#define R9A06G032_HCLK_SDIO0		127
+#define R9A06G032_HCLK_SDIO1		128
+#define R9A06G032_HCLK_SEMAP		129
+#define R9A06G032_HCLK_SPI0		130
+#define R9A06G032_HCLK_SPI1		131
+#define R9A06G032_HCLK_SPI2		132
+#define R9A06G032_HCLK_SPI3		133
+#define R9A06G032_HCLK_SPI4		134
+#define R9A06G032_HCLK_SPI5		135
+#define R9A06G032_HCLK_SWITCH		136
+#define R9A06G032_HCLK_SWITCH_RG	137
+#define R9A06G032_HCLK_UART0		138
+#define R9A06G032_HCLK_UART1		139
+#define R9A06G032_HCLK_UART2		140
+#define R9A06G032_HCLK_UART3		141
+#define R9A06G032_HCLK_UART4		142
+#define R9A06G032_HCLK_UART5		143
+#define R9A06G032_HCLK_UART6		144
+#define R9A06G032_HCLK_UART7		145
+#define R9A06G032_CLK_UART0		146
+#define R9A06G032_CLK_UART1		147
+#define R9A06G032_CLK_UART2		148
+#define R9A06G032_CLK_UART3		149
+#define R9A06G032_CLK_UART4		150
+#define R9A06G032_CLK_UART5		151
+#define R9A06G032_CLK_UART6		152
+#define R9A06G032_CLK_UART7		153
+
+#endif /* __DT_BINDINGS_R9A06G032_SYSCTRL_H__ */
-- 
cgit v1.2.3


From bb450fa59c0772310ebcc704722dd8a0313bf8ed Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Thu, 21 Jun 2018 15:47:35 -0500
Subject: ASoC: Intel: common: fix missing rename from 'reef' to 'sof'

Somehow I missed the Nau8824 support which was added in 4.17. Oops

Fixes: 4f722a6a736 ("ASoC: Intel: common: rename 'reef' to 'sof' in ACPI matching table")
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/soc-acpi-intel-cht-match.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/intel/common/soc-acpi-intel-cht-match.c b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
index 3c3f2f8585d7..91bb99b69601 100644
--- a/sound/soc/intel/common/soc-acpi-intel-cht-match.c
+++ b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
@@ -122,8 +122,8 @@ struct snd_soc_acpi_mach  snd_soc_acpi_intel_cherrytrail_machines[] = {
 		.drv_name = "cht-bsw-nau8824",
 		.fw_filename = "intel/fw_sst_22a8.bin",
 		.board = "cht-bsw",
-		.sof_fw_filename = "intel/reef-cht.ri",
-		.sof_tplg_filename = "intel/reef-cht-nau8824.tplg",
+		.sof_fw_filename = "intel/sof-cht.ri",
+		.sof_tplg_filename = "intel/sof-cht-nau8824.tplg",
 		.asoc_plat_name = "sst-mfld-platform",
 	},
 	{
-- 
cgit v1.2.3


From a98ec93d7e378db21a6cdbc6d55feaba9fb4b999 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 22 Jun 2018 02:23:24 +0000
Subject: ASoC: rt5682: use devm_snd_soc_register_component()

Using devm_snd_soc_register_component() and drop all of the code
related to .remove hook.

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5682.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index 61a97301bcfa..baad177908ab 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -2630,17 +2630,11 @@ static int rt5682_i2c_probe(struct i2c_client *i2c,
 
 	}
 
-	return snd_soc_register_component(&i2c->dev, &soc_component_dev_rt5682,
+	return devm_snd_soc_register_component(&i2c->dev,
+			&soc_component_dev_rt5682,
 			rt5682_dai, ARRAY_SIZE(rt5682_dai));
 }
 
-static int rt5682_i2c_remove(struct i2c_client *i2c)
-{
-	snd_soc_unregister_component(&i2c->dev);
-
-	return 0;
-}
-
 static void rt5682_i2c_shutdown(struct i2c_client *client)
 {
 	struct rt5682_priv *rt5682 = i2c_get_clientdata(client);
@@ -2671,7 +2665,6 @@ static struct i2c_driver rt5682_i2c_driver = {
 		.acpi_match_table = ACPI_PTR(rt5682_acpi_match),
 	},
 	.probe = rt5682_i2c_probe,
-	.remove = rt5682_i2c_remove,
 	.shutdown = rt5682_i2c_shutdown,
 	.id_table = rt5682_i2c_id,
 };
-- 
cgit v1.2.3


From 2854a214f398f2c3315204a05efff11739fec062 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Fri, 22 Jun 2018 02:23:34 +0000
Subject: ASoC: rt1305: use devm_snd_soc_register_component()

Using devm_snd_soc_register_component() and drop all of the code
related to .remove hook.

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1305.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/sound/soc/codecs/rt1305.c b/sound/soc/codecs/rt1305.c
index 421b8fb2fa04..c4452efc7970 100644
--- a/sound/soc/codecs/rt1305.c
+++ b/sound/soc/codecs/rt1305.c
@@ -1150,17 +1150,11 @@ static int rt1305_i2c_probe(struct i2c_client *i2c,
 	rt1305_reset(rt1305->regmap);
 	rt1305_calibrate(rt1305);
 
-	return snd_soc_register_component(&i2c->dev, &soc_component_dev_rt1305,
+	return devm_snd_soc_register_component(&i2c->dev,
+			&soc_component_dev_rt1305,
 			rt1305_dai, ARRAY_SIZE(rt1305_dai));
 }
 
-static int rt1305_i2c_remove(struct i2c_client *i2c)
-{
-	snd_soc_unregister_component(&i2c->dev);
-
-	return 0;
-}
-
 static void rt1305_i2c_shutdown(struct i2c_client *client)
 {
 	struct rt1305_priv *rt1305 = i2c_get_clientdata(client);
@@ -1180,7 +1174,6 @@ static struct i2c_driver rt1305_i2c_driver = {
 #endif
 	},
 	.probe = rt1305_i2c_probe,
-	.remove   = rt1305_i2c_remove,
 	.shutdown = rt1305_i2c_shutdown,
 	.id_table = rt1305_i2c_id,
 };
-- 
cgit v1.2.3


From 366f074d047b2538cc5d7e4a820bb6c117a3ccec Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Thu, 21 Jun 2018 11:56:28 +0900
Subject: ASoC: uniphier: remove redundant check of PLL ID

This patch removes redudant check of PLL ID. struct uniphier_aio_pll
enable member has already been checked at is_valid_pll().

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/uniphier/aio-cpu.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/sound/soc/uniphier/aio-cpu.c b/sound/soc/uniphier/aio-cpu.c
index 2d9b7dde2ffa..ee90e6c3937c 100644
--- a/sound/soc/uniphier/aio-cpu.c
+++ b/sound/soc/uniphier/aio-cpu.c
@@ -219,15 +219,10 @@ static int uniphier_aio_set_pll(struct snd_soc_dai *dai, int pll_id,
 				unsigned int freq_out)
 {
 	struct uniphier_aio *aio = uniphier_priv(dai);
-	struct device *dev = &aio->chip->pdev->dev;
 	int ret;
 
 	if (!is_valid_pll(aio->chip, pll_id))
 		return -EINVAL;
-	if (!aio->chip->plls[pll_id].enable) {
-		dev_err(dev, "PLL(%d) is not implemented\n", pll_id);
-		return -ENOTSUPP;
-	}
 
 	ret = aio_chip_set_pll(aio->chip, pll_id, freq_out);
 	if (ret < 0)
-- 
cgit v1.2.3


From 3bec6fa3cdd338860d4b7d4110a49292646d801e Mon Sep 17 00:00:00 2001
From: "Agrawal, Akshu" <Akshu.Agrawal@amd.com>
Date: Thu, 21 Jun 2018 12:58:16 +0800
Subject: ASoC: AMD: Change codec to channel link as per hardware redesign

This is a correction to match acutal hardware configuration.
The hardware configuration looks like:
I2S_BT -> SPK(Max) + DMIC(Adau)
I2S_SP -> DA7219 Headset

No actual products have been shipped with previous configuration.

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-da7219-max98357a.c | 27 +++++++++++++++++++--------
 1 file changed, 19 insertions(+), 8 deletions(-)

diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index ccddc6650b9c..566bd268be3a 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -148,7 +148,7 @@ static int cz_da7219_startup(struct snd_pcm_substream *substream)
 	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_RATE,
 				   &constraints_rates);
 
-	machine->i2s_instance = I2S_BT_INSTANCE;
+	machine->i2s_instance = I2S_SP_INSTANCE;
 	return da7219_clk_enable(substream);
 }
 
@@ -163,7 +163,7 @@ static int cz_max_startup(struct snd_pcm_substream *substream)
 	struct snd_soc_card *card = rtd->card;
 	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
 
-	machine->i2s_instance = I2S_SP_INSTANCE;
+	machine->i2s_instance = I2S_BT_INSTANCE;
 	return da7219_clk_enable(substream);
 }
 
@@ -178,7 +178,7 @@ static int cz_dmic_startup(struct snd_pcm_substream *substream)
 	struct snd_soc_card *card = rtd->card;
 	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
 
-	machine->i2s_instance = I2S_SP_INSTANCE;
+	machine->i2s_instance = I2S_BT_INSTANCE;
 	return da7219_clk_enable(substream);
 }
 
@@ -204,16 +204,27 @@ static const struct snd_soc_ops cz_dmic_cap_ops = {
 
 static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 	{
-		.name = "amd-da7219-play-cap",
-		.stream_name = "Playback and Capture",
+		.name = "amd-da7219-play",
+		.stream_name = "Playback",
 		.platform_name = "acp_audio_dma.0.auto",
-		.cpu_dai_name = "designware-i2s.3.auto",
+		.cpu_dai_name = "designware-i2s.1.auto",
 		.codec_dai_name = "da7219-hifi",
 		.codec_name = "i2c-DLGS7219:00",
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
 				| SND_SOC_DAIFMT_CBM_CFM,
 		.init = cz_da7219_init,
 		.dpcm_playback = 1,
+		.ops = &cz_da7219_cap_ops,
+	},
+	{
+		.name = "amd-da7219-cap",
+		.stream_name = "Capture",
+		.platform_name = "acp_audio_dma.0.auto",
+		.cpu_dai_name = "designware-i2s.2.auto",
+		.codec_dai_name = "da7219-hifi",
+		.codec_name = "i2c-DLGS7219:00",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
+				| SND_SOC_DAIFMT_CBM_CFM,
 		.dpcm_capture = 1,
 		.ops = &cz_da7219_cap_ops,
 	},
@@ -221,7 +232,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 		.name = "amd-max98357-play",
 		.stream_name = "HiFi Playback",
 		.platform_name = "acp_audio_dma.0.auto",
-		.cpu_dai_name = "designware-i2s.1.auto",
+		.cpu_dai_name = "designware-i2s.3.auto",
 		.codec_dai_name = "HiFi",
 		.codec_name = "MX98357A:00",
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
@@ -233,7 +244,7 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 		.name = "dmic",
 		.stream_name = "DMIC Capture",
 		.platform_name = "acp_audio_dma.0.auto",
-		.cpu_dai_name = "designware-i2s.2.auto",
+		.cpu_dai_name = "designware-i2s.3.auto",
 		.codec_dai_name = "adau7002-hifi",
 		.codec_name = "ADAU7002:00",
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
-- 
cgit v1.2.3


From 2718c89a233bf8549fdba0925947b2c3cb887a95 Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Thu, 21 Jun 2018 12:58:17 +0800
Subject: ASoC: AMD: Configure channel 1 or channel 0 for capture

ST/CZ SoC have 2 channels for capture in the I2SSP path.
The DMA though these channels is done using the same dma
descriptors.
We configure the channel and enable it on the basis of
channel selected by machine driver. Machine driver knows
which codec sits on which channel and thus sends the information
to dma driver.

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-da7219-max98357a.c | 43 +++++++++++++++++++---
 sound/soc/amd/acp-pcm-dma.c          | 71 +++++++++++++++++++++++++++++++++++-
 sound/soc/amd/acp.h                  |  4 ++
 3 files changed, 111 insertions(+), 7 deletions(-)

diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index 566bd268be3a..f42606e5879e 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -149,6 +149,7 @@ static int cz_da7219_startup(struct snd_pcm_substream *substream)
 				   &constraints_rates);
 
 	machine->i2s_instance = I2S_SP_INSTANCE;
+	machine->capture_channel = CAP_CHANNEL1;
 	return da7219_clk_enable(substream);
 }
 
@@ -172,7 +173,7 @@ static void cz_max_shutdown(struct snd_pcm_substream *substream)
 	da7219_clk_disable();
 }
 
-static int cz_dmic_startup(struct snd_pcm_substream *substream)
+static int cz_dmic0_startup(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_card *card = rtd->card;
@@ -182,6 +183,17 @@ static int cz_dmic_startup(struct snd_pcm_substream *substream)
 	return da7219_clk_enable(substream);
 }
 
+static int cz_dmic1_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct acp_platform_info *machine = snd_soc_card_get_drvdata(card);
+
+	machine->i2s_instance = I2S_SP_INSTANCE;
+	machine->capture_channel = CAP_CHANNEL0;
+	return da7219_clk_enable(substream);
+}
+
 static void cz_dmic_shutdown(struct snd_pcm_substream *substream)
 {
 	da7219_clk_disable();
@@ -197,8 +209,13 @@ static const struct snd_soc_ops cz_max_play_ops = {
 	.shutdown = cz_max_shutdown,
 };
 
-static const struct snd_soc_ops cz_dmic_cap_ops = {
-	.startup = cz_dmic_startup,
+static const struct snd_soc_ops cz_dmic0_cap_ops = {
+	.startup = cz_dmic0_startup,
+	.shutdown = cz_dmic_shutdown,
+};
+
+static const struct snd_soc_ops cz_dmic1_cap_ops = {
+	.startup = cz_dmic1_startup,
 	.shutdown = cz_dmic_shutdown,
 };
 
@@ -241,8 +258,9 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 		.ops = &cz_max_play_ops,
 	},
 	{
-		.name = "dmic",
-		.stream_name = "DMIC Capture",
+		/* C panel DMIC */
+		.name = "dmic0",
+		.stream_name = "DMIC0 Capture",
 		.platform_name = "acp_audio_dma.0.auto",
 		.cpu_dai_name = "designware-i2s.3.auto",
 		.codec_dai_name = "adau7002-hifi",
@@ -250,7 +268,20 @@ static struct snd_soc_dai_link cz_dai_7219_98357[] = {
 		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
 				| SND_SOC_DAIFMT_CBM_CFM,
 		.dpcm_capture = 1,
-		.ops = &cz_dmic_cap_ops,
+		.ops = &cz_dmic0_cap_ops,
+	},
+	{
+		/* A/B panel DMIC */
+		.name = "dmic1",
+		.stream_name = "DMIC1 Capture",
+		.platform_name = "acp_audio_dma.0.auto",
+		.cpu_dai_name = "designware-i2s.2.auto",
+		.codec_dai_name = "adau7002-hifi",
+		.codec_name = "ADAU7002:00",
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF
+				| SND_SOC_DAIFMT_CBM_CFM,
+		.dpcm_capture = 1,
+		.ops = &cz_dmic1_cap_ops,
 	},
 };
 
diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 1458b5048498..3c3d398d0d0b 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -336,6 +336,61 @@ static void config_acp_dma(void __iomem *acp_mmio,
 				       rtd->dma_dscr_idx_2, asic_type);
 }
 
+static void acp_dma_cap_channel_enable(void __iomem *acp_mmio,
+				       u16 cap_channel)
+{
+	u32 val, ch_reg, imr_reg, res_reg;
+
+	switch (cap_channel) {
+	case CAP_CHANNEL1:
+		ch_reg = mmACP_I2SMICSP_RER1;
+		res_reg = mmACP_I2SMICSP_RCR1;
+		imr_reg = mmACP_I2SMICSP_IMR1;
+		break;
+	case CAP_CHANNEL0:
+	default:
+		ch_reg = mmACP_I2SMICSP_RER0;
+		res_reg = mmACP_I2SMICSP_RCR0;
+		imr_reg = mmACP_I2SMICSP_IMR0;
+		break;
+	}
+	val = acp_reg_read(acp_mmio,
+			   mmACP_I2S_16BIT_RESOLUTION_EN);
+	if (val & ACP_I2S_MIC_16BIT_RESOLUTION_EN) {
+		acp_reg_write(0x0, acp_mmio, ch_reg);
+		/* Set 16bit resolution on capture */
+		acp_reg_write(0x2, acp_mmio, res_reg);
+	}
+	val = acp_reg_read(acp_mmio, imr_reg);
+	val &= ~ACP_I2SMICSP_IMR1__I2SMICSP_RXDAM_MASK;
+	val &= ~ACP_I2SMICSP_IMR1__I2SMICSP_RXFOM_MASK;
+	acp_reg_write(val, acp_mmio, imr_reg);
+	acp_reg_write(0x1, acp_mmio, ch_reg);
+}
+
+static void acp_dma_cap_channel_disable(void __iomem *acp_mmio,
+					u16 cap_channel)
+{
+	u32 val, ch_reg, imr_reg;
+
+	switch (cap_channel) {
+	case CAP_CHANNEL1:
+		imr_reg = mmACP_I2SMICSP_IMR1;
+		ch_reg = mmACP_I2SMICSP_RER1;
+		break;
+	case CAP_CHANNEL0:
+	default:
+		imr_reg = mmACP_I2SMICSP_IMR0;
+		ch_reg = mmACP_I2SMICSP_RER0;
+		break;
+	}
+	val = acp_reg_read(acp_mmio, imr_reg);
+	val |= ACP_I2SMICSP_IMR1__I2SMICSP_RXDAM_MASK;
+	val |= ACP_I2SMICSP_IMR1__I2SMICSP_RXFOM_MASK;
+	acp_reg_write(val, acp_mmio, imr_reg);
+	acp_reg_write(0x0, acp_mmio, ch_reg);
+}
+
 /* Start a given DMA channel transfer */
 static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
 {
@@ -773,8 +828,10 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 	if (WARN_ON(!rtd))
 		return -EINVAL;
 
-	if (pinfo)
+	if (pinfo) {
 		rtd->i2s_instance = pinfo->i2s_instance;
+		rtd->capture_channel = pinfo->capture_channel;
+	}
 	if (adata->asic_type == CHIP_STONEY) {
 		val = acp_reg_read(adata->acp_mmio,
 				   mmACP_I2S_16BIT_RESOLUTION_EN);
@@ -990,6 +1047,18 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 			acp_dma_start(rtd->acp_mmio, rtd->ch1);
 			acp_dma_start(rtd->acp_mmio, rtd->ch2);
 		} else {
+			if (rtd->capture_channel == CAP_CHANNEL0) {
+				acp_dma_cap_channel_disable(rtd->acp_mmio,
+							    CAP_CHANNEL1);
+				acp_dma_cap_channel_enable(rtd->acp_mmio,
+							   CAP_CHANNEL0);
+			}
+			if (rtd->capture_channel == CAP_CHANNEL1) {
+				acp_dma_cap_channel_disable(rtd->acp_mmio,
+							    CAP_CHANNEL0);
+				acp_dma_cap_channel_enable(rtd->acp_mmio,
+							   CAP_CHANNEL1);
+			}
 			acp_dma_start(rtd->acp_mmio, rtd->ch2);
 			acp_dma_start(rtd->acp_mmio, rtd->ch1);
 		}
diff --git a/sound/soc/amd/acp.h b/sound/soc/amd/acp.h
index 9cd3e96c84d4..3190fdce6307 100644
--- a/sound/soc/amd/acp.h
+++ b/sound/soc/amd/acp.h
@@ -55,6 +55,8 @@
 
 #define I2S_SP_INSTANCE                 0x01
 #define I2S_BT_INSTANCE                 0x02
+#define CAP_CHANNEL0			0x00
+#define CAP_CHANNEL1			0x01
 
 #define ACP_TILE_ON_MASK                0x03
 #define ACP_TILE_OFF_MASK               0x02
@@ -125,6 +127,7 @@ struct audio_substream_data {
 	unsigned int order;
 	u16 num_of_pages;
 	u16 i2s_instance;
+	u16 capture_channel;
 	u16 direction;
 	u16 ch1;
 	u16 ch2;
@@ -155,6 +158,7 @@ struct audio_drv_data {
  */
 struct acp_platform_info {
 	u16 i2s_instance;
+	u16 capture_channel;
 };
 
 union acp_dma_count {
-- 
cgit v1.2.3


From a12f671b4241f53e7cd9dec8770d51549682453b Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Wed, 20 Jun 2018 10:59:59 +0900
Subject: ASoC: add hp-det-gpio and mic-det-gpio to audio graph card binding

Add headphone and microphone detection GPIO support to audio graph
card same as supported in simple card.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/audio-graph-card.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/audio-graph-card.txt b/Documentation/devicetree/bindings/sound/audio-graph-card.txt
index d04ea3b1a1dd..7e63e53a901c 100644
--- a/Documentation/devicetree/bindings/sound/audio-graph-card.txt
+++ b/Documentation/devicetree/bindings/sound/audio-graph-card.txt
@@ -18,6 +18,8 @@ Below are same as Simple-Card.
 - bitclock-inversion
 - frame-inversion
 - mclk-fs
+- hp-det-gpio
+- mic-det-gpio
 - dai-tdm-slot-num
 - dai-tdm-slot-width
 - clocks / system-clock-frequency
-- 
cgit v1.2.3


From f4c277b817cc9489fffabffb4e15d2f3b686056c Mon Sep 17 00:00:00 2001
From: Jiada Wang <jiada_wang@mentor.com>
Date: Wed, 20 Jun 2018 18:25:20 +0900
Subject: ASoC: soc-pcm: DPCM cares BE channel constraint

Current DPCM is caring only FE channel configuration. Sometimes
it will be trouble if user selects channel which isn't supported
by BE.

This patch adds new .dpcm_merged_chan on struct snd_soc_dai_link.
DPCM will use FE / BE merged channel if struct snd_soc_dai_link
has it.

Signed-off-by: Jiada Wang <jiada_wang@mentor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h |  2 ++
 sound/soc/soc-pcm.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 48 insertions(+)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 1378dcd2128a..f7579f82cc00 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -957,6 +957,8 @@ struct snd_soc_dai_link {
 
 	/* DPCM used FE & BE merged format */
 	unsigned int dpcm_merged_format:1;
+	/* DPCM used FE & BE merged channel */
+	unsigned int dpcm_merged_chan:1;
 
 	/* pmdown_time is ignored at stop */
 	unsigned int ignore_pmdown_time:1;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 45b52f7b9690..19ebfc958b9d 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1715,6 +1715,46 @@ static u64 dpcm_runtime_base_format(struct snd_pcm_substream *substream)
 	return formats;
 }
 
+static void dpcm_runtime_base_chan(struct snd_pcm_substream *substream,
+				   unsigned int *channels_min,
+				   unsigned int *channels_max)
+{
+	struct snd_soc_pcm_runtime *fe = substream->private_data;
+	struct snd_soc_dpcm *dpcm;
+	int stream = substream->stream;
+
+	if (!fe->dai_link->dpcm_merged_chan)
+		return;
+
+	*channels_min = 0;
+	*channels_max = UINT_MAX;
+
+	/*
+	 * It returns merged BE codec channel;
+	 * if FE want to use it (= dpcm_merged_chan)
+	 */
+
+	list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be) {
+		struct snd_soc_pcm_runtime *be = dpcm->be;
+		struct snd_soc_dai_driver *codec_dai_drv;
+		struct snd_soc_pcm_stream *codec_stream;
+		int i;
+
+		for (i = 0; i < be->num_codecs; i++) {
+			codec_dai_drv = be->codec_dais[i]->driver;
+			if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+				codec_stream = &codec_dai_drv->playback;
+			else
+				codec_stream = &codec_dai_drv->capture;
+
+			*channels_min = max(*channels_min,
+					    codec_stream->channels_min);
+			*channels_max = min(*channels_max,
+					    codec_stream->channels_max);
+		}
+	}
+}
+
 static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -1722,11 +1762,17 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai_driver *cpu_dai_drv = cpu_dai->driver;
 	u64 format = dpcm_runtime_base_format(substream);
+	unsigned int channels_min = 0, channels_max = UINT_MAX;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->playback, format);
 	else
 		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture, format);
+
+	dpcm_runtime_base_chan(substream, &channels_min, &channels_max);
+
+	runtime->hw.channels_min = max(channels_min, runtime->hw.channels_min);
+	runtime->hw.channels_max = min(channels_max, runtime->hw.channels_max);
 }
 
 static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd);
-- 
cgit v1.2.3


From ce43b2e351c860bc50151b3ddc190b92a7536c8e Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Mon, 28 May 2018 11:03:27 +0200
Subject: crypto: inside-secure - increase minimum transfer size

The token size was increased for AEAD support. Occasional authentication
fails arise since the result descriptor overflows. This is because the
token size and the engine minimal thresholds must be in sync.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 4e86f864a952..8691f6369a13 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -296,8 +296,8 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 
 	/* DMA transfer size to use */
 	val = EIP197_HIA_DFE_CFG_DIS_DEBUG;
-	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(5) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(9);
-	val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(5) | EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
+	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(6) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(9);
+	val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(6) | EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
 	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
 	val |= EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(RD_CACHE_3BITS);
 	writel(val, EIP197_HIA_DFE(priv) + EIP197_HIA_DFE_CFG);
@@ -306,9 +306,9 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	writel(0, EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
 
 	/* Configure the procesing engine thresholds */
-	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(9),
+	writel(EIP197_PE_IN_xBUF_THRES_MIN(6) | EIP197_PE_IN_xBUF_THRES_MAX(9),
 	       EIP197_PE(priv) + EIP197_PE_IN_DBUF_THRES);
-	writel(EIP197_PE_IN_xBUF_THRES_MIN(5) | EIP197_PE_IN_xBUF_THRES_MAX(7),
+	writel(EIP197_PE_IN_xBUF_THRES_MIN(6) | EIP197_PE_IN_xBUF_THRES_MAX(7),
 	       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES);
 
 	if (priv->version == EIP197) {
-- 
cgit v1.2.3


From cda3e73a54971e38a7388db0132c3681eab87847 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:43 +0200
Subject: crypto: inside-secure - use the error handler for invalidation
 requests

This patch reworks the way invalidation request handlers handle the
result descriptor errors, to use the common error handling function.
This improves the drivers in terms of readability and maintainability.

Suggested-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel_cipher.c | 7 ++-----
 drivers/crypto/inside-secure/safexcel_hash.c   | 7 ++-----
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 6bb60fda2043..5bc0afc8e63a 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -491,11 +491,8 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 			break;
 		}
 
-		if (rdesc->result_data.error_code) {
-			dev_err(priv->dev, "cipher: invalidate: result descriptor error (%d)\n",
-				rdesc->result_data.error_code);
-			*ret = -EIO;
-		}
+		if (likely(!*ret))
+			*ret = safexcel_rdesc_check_errors(priv, rdesc);
 
 		ndesc++;
 	} while (!rdesc->last_seg);
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index c77b0e1655a8..9c1ba7f4f11e 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -369,11 +369,8 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 		dev_err(priv->dev,
 			"hash: invalidate: could not retrieve the result descriptor\n");
 		*ret = PTR_ERR(rdesc);
-	} else if (rdesc->result_data.error_code) {
-		dev_err(priv->dev,
-			"hash: invalidate: result descriptor error (%d)\n",
-			rdesc->result_data.error_code);
-		*ret = -EINVAL;
+	} else {
+		*ret = safexcel_rdesc_check_errors(priv, rdesc);
 	}
 
 	safexcel_complete(priv, ring);
-- 
cgit v1.2.3


From 25bc95510317dc7259299adb786f050617199b42 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:44 +0200
Subject: crypto: inside-secure - improve the counter computation

A counter is given to the engine when finishing hash computation. It
currently uses the blocksize while it counts the number of 64 bytes
blocks given to the engine. This works well for all algorithms so far,
as SHA1, SHA224 and SHA256 all have a blocksize of 64 bytes, but others
algorithms such as SHA512 wouldn't work.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.h      |  5 +++++
 drivers/crypto/inside-secure/safexcel_hash.c | 12 +++++-------
 2 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 8b3ee9b59f53..d2adedc23e9a 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -327,6 +327,11 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_COUNTER_MODE		BIT(10)
 #define CONTEXT_CONTROL_HASH_STORE		BIT(19)
 
+/* The hash counter given to the engine in the context has a granularity of
+ * 64 bits.
+ */
+#define EIP197_COUNTER_BLOCK_SIZE		64
+
 /* EIP197_CS_RAM_CTRL */
 #define EIP197_TRC_ENABLE_0			BIT(4)
 #define EIP197_TRC_ENABLE_1			BIT(5)
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 9c1ba7f4f11e..c284c84cdddb 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -72,8 +72,7 @@ static void safexcel_hash_token(struct safexcel_command_desc *cdesc,
 static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 				     struct safexcel_ahash_req *req,
 				     struct safexcel_command_desc *cdesc,
-				     unsigned int digestsize,
-				     unsigned int blocksize)
+				     unsigned int digestsize)
 {
 	int i;
 
@@ -107,7 +106,8 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 				ctx->base.ctxr->data[i] = cpu_to_le32(req->state[i]);
 
 			if (req->finish)
-				ctx->base.ctxr->data[i] = cpu_to_le32(req->processed / blocksize);
+				ctx->base.ctxr->data[i] =
+					cpu_to_le32(req->processed / EIP197_COUNTER_BLOCK_SIZE);
 		}
 	} else if (req->digest == CONTEXT_CONTROL_DIGEST_HMAC) {
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(2 * req->state_sz / sizeof(u32));
@@ -282,8 +282,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 
 send_command:
 	/* Setup the context options */
-	safexcel_context_control(ctx, req, first_cdesc, req->state_sz,
-				 crypto_ahash_blocksize(ahash));
+	safexcel_context_control(ctx, req, first_cdesc, req->state_sz);
 
 	/* Add the token */
 	safexcel_hash_token(first_cdesc, len, req->state_sz);
@@ -335,7 +334,6 @@ static inline bool safexcel_ahash_needs_inv_get(struct ahash_request *areq)
 {
 	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
-	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
 	unsigned int state_w_sz = req->state_sz / sizeof(u32);
 	int i;
 
@@ -344,7 +342,7 @@ static inline bool safexcel_ahash_needs_inv_get(struct ahash_request *areq)
 			return true;
 
 	if (ctx->base.ctxr->data[state_w_sz] !=
-	    cpu_to_le32(req->processed / crypto_ahash_blocksize(ahash)))
+	    cpu_to_le32(req->processed / EIP197_COUNTER_BLOCK_SIZE))
 		return true;
 
 	return false;
-- 
cgit v1.2.3


From 30c217ef6411d24b8c8b0478b89335dc2dabe6e8 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:45 +0200
Subject: crypto: sha512_generic - add a sha512 0-length pre-computed hash

This patch adds the sha512 pre-computed 0-length hash so that device
drivers can use it when an hardware engine does not support computing a
hash from a 0 length input.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/sha512_generic.c | 12 ++++++++++++
 include/crypto/sha.h    |  2 ++
 2 files changed, 14 insertions(+)

diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index eba965d18bfc..439723d9273e 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -23,6 +23,18 @@
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
+const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE] = {
+	0xcf, 0x83, 0xe1, 0x35, 0x7e, 0xef, 0xb8, 0xbd,
+	0xf1, 0x54, 0x28, 0x50, 0xd6, 0x6d, 0x80, 0x07,
+	0xd6, 0x20, 0xe4, 0x05, 0x0b, 0x57, 0x15, 0xdc,
+	0x83, 0xf4, 0xa9, 0x21, 0xd3, 0x6c, 0xe9, 0xce,
+	0x47, 0xd0, 0xd1, 0x3c, 0x5d, 0x85, 0xf2, 0xb0,
+	0xff, 0x83, 0x18, 0xd2, 0x87, 0x7e, 0xec, 0x2f,
+	0x63, 0xb9, 0x31, 0xbd, 0x47, 0x41, 0x7a, 0x81,
+	0xa5, 0x38, 0x32, 0x7a, 0xf9, 0x27, 0xda, 0x3e
+};
+EXPORT_SYMBOL_GPL(sha512_zero_message_hash);
+
 static inline u64 Ch(u64 x, u64 y, u64 z)
 {
         return z ^ (x & (y ^ z));
diff --git a/include/crypto/sha.h b/include/crypto/sha.h
index 0555b571dd34..799f071b93df 100644
--- a/include/crypto/sha.h
+++ b/include/crypto/sha.h
@@ -71,6 +71,8 @@ extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE];
 
 extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE];
 
+extern const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE];
+
 struct sha1_state {
 	u32 state[SHA1_DIGEST_SIZE / 4];
 	u64 count;
-- 
cgit v1.2.3


From b460edb6230ac2877b0d176b9122736fed6f3c6e Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:46 +0200
Subject: crypto: inside-secure - sha512 support

This patch adds the sha512 algorithm support to the Inside Secure
SafeXcel driver.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c      |   1 +
 drivers/crypto/inside-secure/safexcel.h      |  11 +-
 drivers/crypto/inside-secure/safexcel_hash.c | 178 ++++++++++++++++++++++-----
 3 files changed, 153 insertions(+), 37 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 8691f6369a13..126def0b4450 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -790,6 +790,7 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_sha1,
 	&safexcel_alg_sha224,
 	&safexcel_alg_sha256,
+	&safexcel_alg_sha512,
 	&safexcel_alg_hmac_sha1,
 	&safexcel_alg_hmac_sha224,
 	&safexcel_alg_hmac_sha256,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index d2adedc23e9a..0438e058844c 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -313,6 +313,8 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA1		(0x2 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA224	(0x4 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA256	(0x3 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA384	(0x6 << 23)
+#define CONTEXT_CONTROL_CRYPTO_ALG_SHA512	(0x5 << 23)
 #define CONTEXT_CONTROL_INV_FR			(0x5 << 24)
 #define CONTEXT_CONTROL_INV_TR			(0x6 << 24)
 
@@ -605,13 +607,13 @@ struct safexcel_context {
 };
 
 struct safexcel_ahash_export_state {
-	u64 len;
-	u64 processed;
+	u64 len[2];
+	u64 processed[2];
 
 	u32 digest;
 
-	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)];
-	u8 cache[SHA256_BLOCK_SIZE];
+	u32 state[SHA512_DIGEST_SIZE / sizeof(u32)];
+	u8 cache[SHA512_BLOCK_SIZE];
 };
 
 /*
@@ -670,6 +672,7 @@ extern struct safexcel_alg_template safexcel_alg_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_sha1;
 extern struct safexcel_alg_template safexcel_alg_sha224;
 extern struct safexcel_alg_template safexcel_alg_sha256;
+extern struct safexcel_alg_template safexcel_alg_sha512;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha256;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index c284c84cdddb..5d8e15e70cff 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -38,18 +38,26 @@ struct safexcel_ahash_req {
 	u32 digest;
 
 	u8 state_sz;    /* expected sate size, only set once */
-	u32 state[SHA256_DIGEST_SIZE / sizeof(u32)] __aligned(sizeof(u32));
+	u32 state[SHA512_DIGEST_SIZE / sizeof(u32)] __aligned(sizeof(u32));
 
-	u64 len;
-	u64 processed;
+	u64 len[2];
+	u64 processed[2];
 
-	u8 cache[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
+	u8 cache[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
 	dma_addr_t cache_dma;
 	unsigned int cache_sz;
 
-	u8 cache_next[SHA256_BLOCK_SIZE] __aligned(sizeof(u32));
+	u8 cache_next[SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
 };
 
+static inline u64 safexcel_queued_len(struct safexcel_ahash_req *req)
+{
+	if (req->len[1] > req->processed[1])
+		return 0xffffffff - (req->len[0] - req->processed[0]);
+
+	return req->len[0] - req->processed[0];
+}
+
 static void safexcel_hash_token(struct safexcel_command_desc *cdesc,
 				u32 input_length, u32 result_length)
 {
@@ -74,6 +82,7 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 				     struct safexcel_command_desc *cdesc,
 				     unsigned int digestsize)
 {
+	struct safexcel_crypto_priv *priv = ctx->priv;
 	int i;
 
 	cdesc->control_data.control0 |= CONTEXT_CONTROL_TYPE_HASH_OUT;
@@ -81,12 +90,14 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 	cdesc->control_data.control0 |= req->digest;
 
 	if (req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED) {
-		if (req->processed) {
+		if (req->processed[0] || req->processed[1]) {
 			if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(6);
 			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224 ||
 				 ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(9);
+			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
+				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(17);
 
 			cdesc->control_data.control1 |= CONTEXT_CONTROL_DIGEST_CNT;
 		} else {
@@ -101,13 +112,28 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 		 * fields. Do this now as we need it to setup the first command
 		 * descriptor.
 		 */
-		if (req->processed) {
+		if (req->processed[0] || req->processed[1]) {
 			for (i = 0; i < digestsize / sizeof(u32); i++)
 				ctx->base.ctxr->data[i] = cpu_to_le32(req->state[i]);
 
-			if (req->finish)
-				ctx->base.ctxr->data[i] =
-					cpu_to_le32(req->processed / EIP197_COUNTER_BLOCK_SIZE);
+			if (req->finish) {
+				u64 count = req->processed[0] / EIP197_COUNTER_BLOCK_SIZE;
+				count += ((0xffffffff / EIP197_COUNTER_BLOCK_SIZE) *
+					  req->processed[1]);
+
+				/* This is a haredware limitation, as the
+				 * counter must fit into an u32. This represents
+				 * a farily big amount of input data, so we
+				 * shouldn't see this.
+				 */
+				if (unlikely(count & 0xffff0000)) {
+					dev_warn(priv->dev,
+						 "Input data is too big\n");
+					return;
+				}
+
+				ctx->base.ctxr->data[i] = cpu_to_le32(count);
+			}
 		}
 	} else if (req->digest == CONTEXT_CONTROL_DIGEST_HMAC) {
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(2 * req->state_sz / sizeof(u32));
@@ -126,7 +152,7 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
 	struct safexcel_ahash_req *sreq = ahash_request_ctx(areq);
-	int cache_len;
+	u64 cache_len;
 
 	*ret = 0;
 
@@ -164,7 +190,7 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 		memcpy(areq->result, sreq->state,
 		       crypto_ahash_digestsize(ahash));
 
-	cache_len = sreq->len - sreq->processed;
+	cache_len = safexcel_queued_len(sreq);
 	if (cache_len)
 		memcpy(sreq->cache, sreq->cache_next, cache_len);
 
@@ -185,9 +211,10 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 	struct safexcel_command_desc *cdesc, *first_cdesc = NULL;
 	struct safexcel_result_desc *rdesc;
 	struct scatterlist *sg;
-	int i, queued, len, cache_len, extra, n_cdesc = 0, ret = 0;
+	int i, extra, n_cdesc = 0, ret = 0;
+	u64 queued, len, cache_len;
 
-	queued = len = req->len - req->processed;
+	queued = len = safexcel_queued_len(req);
 	if (queued <= crypto_ahash_blocksize(ahash))
 		cache_len = queued;
 	else
@@ -260,7 +287,7 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 		int sglen = sg_dma_len(sg);
 
 		/* Do not overflow the request */
-		if (queued - sglen < 0)
+		if (queued < sglen)
 			sglen = queued;
 
 		cdesc = safexcel_add_cdesc(priv, ring, !n_cdesc,
@@ -304,7 +331,10 @@ send_command:
 
 	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
-	req->processed += len;
+	req->processed[0] += len;
+	if (req->processed[0] < len)
+		req->processed[1]++;
+
 	request->req = &areq->base;
 
 	*commands = n_cdesc;
@@ -335,14 +365,17 @@ static inline bool safexcel_ahash_needs_inv_get(struct ahash_request *areq)
 	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	unsigned int state_w_sz = req->state_sz / sizeof(u32);
+	u64 processed;
 	int i;
 
+	processed = req->processed[0] / EIP197_COUNTER_BLOCK_SIZE;
+	processed += (0xffffffff / EIP197_COUNTER_BLOCK_SIZE) * req->processed[1];
+
 	for (i = 0; i < state_w_sz; i++)
 		if (ctx->base.ctxr->data[i] != cpu_to_le32(req->state[i]))
 			return true;
 
-	if (ctx->base.ctxr->data[state_w_sz] !=
-	    cpu_to_le32(req->processed / EIP197_COUNTER_BLOCK_SIZE))
+	if (ctx->base.ctxr->data[state_w_sz] != cpu_to_le32(processed))
 		return true;
 
 	return false;
@@ -504,17 +537,17 @@ static int safexcel_ahash_cache(struct ahash_request *areq)
 {
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	struct crypto_ahash *ahash = crypto_ahash_reqtfm(areq);
-	int queued, cache_len;
+	u64 queued, cache_len;
 
-	/* cache_len: everyting accepted by the driver but not sent yet,
-	 * tot sz handled by update() - last req sz - tot sz handled by send()
-	 */
-	cache_len = req->len - areq->nbytes - req->processed;
 	/* queued: everything accepted by the driver which will be handled by
 	 * the next send() calls.
 	 * tot sz handled by update() - tot sz handled by send()
 	 */
-	queued = req->len - req->processed;
+	queued = safexcel_queued_len(req);
+	/* cache_len: everything accepted by the driver but not sent yet,
+	 * tot sz handled by update() - last req sz - tot sz handled by send()
+	 */
+	cache_len = queued - areq->nbytes;
 
 	/*
 	 * In case there isn't enough bytes to proceed (less than a
@@ -541,8 +574,8 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 	req->needs_inv = false;
 
 	if (ctx->base.ctxr) {
-		if (priv->version == EIP197 &&
-		    !ctx->base.needs_inv && req->processed &&
+		if (priv->version == EIP197 && !ctx->base.needs_inv &&
+		    (req->processed[0] || req->processed[1]) &&
 		    req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
 			/* We're still setting needs_inv here, even though it is
 			 * cleared right away, because the needs_inv flag can be
@@ -585,7 +618,9 @@ static int safexcel_ahash_update(struct ahash_request *areq)
 	if (!areq->nbytes)
 		return 0;
 
-	req->len += areq->nbytes;
+	req->len[0] += areq->nbytes;
+	if (req->len[0] < areq->nbytes)
+		req->len[1]++;
 
 	safexcel_ahash_cache(areq);
 
@@ -600,7 +635,7 @@ static int safexcel_ahash_update(struct ahash_request *areq)
 		return safexcel_ahash_enqueue(areq);
 
 	if (!req->last_req &&
-	    req->len - req->processed > crypto_ahash_blocksize(ahash))
+	    safexcel_queued_len(req) > crypto_ahash_blocksize(ahash))
 		return safexcel_ahash_enqueue(areq);
 
 	return 0;
@@ -615,7 +650,7 @@ static int safexcel_ahash_final(struct ahash_request *areq)
 	req->finish = true;
 
 	/* If we have an overall 0 length request */
-	if (!(req->len + areq->nbytes)) {
+	if (!req->len[0] && !req->len[1] && !areq->nbytes) {
 		if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
 			memcpy(areq->result, sha1_zero_message_hash,
 			       SHA1_DIGEST_SIZE);
@@ -625,6 +660,9 @@ static int safexcel_ahash_final(struct ahash_request *areq)
 		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
 			memcpy(areq->result, sha256_zero_message_hash,
 			       SHA256_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
+			memcpy(areq->result, sha512_zero_message_hash,
+			       SHA512_DIGEST_SIZE);
 
 		return 0;
 	}
@@ -649,8 +687,10 @@ static int safexcel_ahash_export(struct ahash_request *areq, void *out)
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	struct safexcel_ahash_export_state *export = out;
 
-	export->len = req->len;
-	export->processed = req->processed;
+	export->len[0] = req->len[0];
+	export->len[1] = req->len[1];
+	export->processed[0] = req->processed[0];
+	export->processed[1] = req->processed[1];
 
 	export->digest = req->digest;
 
@@ -671,8 +711,10 @@ static int safexcel_ahash_import(struct ahash_request *areq, const void *in)
 	if (ret)
 		return ret;
 
-	req->len = export->len;
-	req->processed = export->processed;
+	req->len[0] = export->len[0];
+	req->len[1] = export->len[1];
+	req->processed[0] = export->processed[0];
+	req->processed[1] = export->processed[1];
 
 	req->digest = export->digest;
 
@@ -1246,3 +1288,73 @@ struct safexcel_alg_template safexcel_alg_hmac_sha256 = {
 		},
 	},
 };
+
+static int safexcel_sha512_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = lower_32_bits(SHA512_H0);
+	req->state[1] = upper_32_bits(SHA512_H0);
+	req->state[2] = lower_32_bits(SHA512_H1);
+	req->state[3] = upper_32_bits(SHA512_H1);
+	req->state[4] = lower_32_bits(SHA512_H2);
+	req->state[5] = upper_32_bits(SHA512_H2);
+	req->state[6] = lower_32_bits(SHA512_H3);
+	req->state[7] = upper_32_bits(SHA512_H3);
+	req->state[8] = lower_32_bits(SHA512_H4);
+	req->state[9] = upper_32_bits(SHA512_H4);
+	req->state[10] = lower_32_bits(SHA512_H5);
+	req->state[11] = upper_32_bits(SHA512_H5);
+	req->state[12] = lower_32_bits(SHA512_H6);
+	req->state[13] = upper_32_bits(SHA512_H6);
+	req->state[14] = lower_32_bits(SHA512_H7);
+	req->state[15] = upper_32_bits(SHA512_H7);
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SHA512_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sha512_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sha512_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_sha512 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_sha512_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sha512_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA512_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha512",
+				.cra_driver_name = "safexcel-sha512",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA512_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
-- 
cgit v1.2.3


From 0de54fb100e9b8adc9df2d896b911dda2dee0a49 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:47 +0200
Subject: crypto: inside-secure - hmac(sha512) support

This patch adds the hmac(sha512) algorithm support to the Inside Secure
SafeXcel driver.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c      |  1 +
 drivers/crypto/inside-secure/safexcel.h      |  3 +-
 drivers/crypto/inside-secure/safexcel_hash.c | 60 +++++++++++++++++++++++++++-
 3 files changed, 61 insertions(+), 3 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 126def0b4450..b3c5f3c8e208 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -794,6 +794,7 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_hmac_sha1,
 	&safexcel_alg_hmac_sha224,
 	&safexcel_alg_hmac_sha256,
+	&safexcel_alg_hmac_sha512,
 	&safexcel_alg_authenc_hmac_sha1_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha224_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha256_cbc_aes,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 0438e058844c..5885844a9994 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -287,7 +287,7 @@ struct safexcel_context_record {
 	u32 control0;
 	u32 control1;
 
-	__le32 data[24];
+	__le32 data[40];
 } __packed;
 
 /* control0 */
@@ -676,6 +676,7 @@ extern struct safexcel_alg_template safexcel_alg_sha512;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha256;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha512;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 5d8e15e70cff..0c452a4bc6dd 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -22,8 +22,8 @@ struct safexcel_ahash_ctx {
 
 	u32 alg;
 
-	u32 ipad[SHA256_DIGEST_SIZE / sizeof(u32)];
-	u32 opad[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
+	u32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
 };
 
 struct safexcel_ahash_req {
@@ -1358,3 +1358,59 @@ struct safexcel_alg_template safexcel_alg_sha512 = {
 		},
 	},
 };
+
+static int safexcel_hmac_sha512_setkey(struct crypto_ahash *tfm, const u8 *key,
+				       unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sha512",
+					SHA512_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_sha512_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_sha512_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_sha512_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sha512_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha512 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha512_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sha512_digest,
+		.setkey = safexcel_hmac_sha512_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA512_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha512)",
+				.cra_driver_name = "safexcel-hmac-sha512",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA512_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
-- 
cgit v1.2.3


From 87eee125e7490cf17e2de845a8b81b5bf63929c7 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:48 +0200
Subject: crypto: inside-secure - authenc(hmac(sha512), cbc(aes)) support

This patch adds the authenc(hmac(sha512),cbc(aes)) algorithm support to
the Inside Secure SafeXcel driver.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        |  1 +
 drivers/crypto/inside-secure/safexcel.h        |  1 +
 drivers/crypto/inside-secure/safexcel_cipher.c | 43 ++++++++++++++++++++++++--
 3 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index b3c5f3c8e208..dcb39d0d82bb 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -798,6 +798,7 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_authenc_hmac_sha1_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha224_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha256_cbc_aes,
+	&safexcel_alg_authenc_hmac_sha512_cbc_aes,
 };
 
 static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 5885844a9994..9e24cab279d2 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -680,5 +680,6 @@ extern struct safexcel_alg_template safexcel_alg_hmac_sha512;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes;
 
 #endif
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 5bc0afc8e63a..560c1e54ce9d 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -40,8 +40,8 @@ struct safexcel_cipher_ctx {
 	/* All the below is AEAD specific */
 	u32 alg;
 	u32 state_sz;
-	u32 ipad[SHA256_DIGEST_SIZE / sizeof(u32)];
-	u32 opad[SHA256_DIGEST_SIZE / sizeof(u32)];
+	u32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
+	u32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
 };
 
 struct safexcel_cipher_req {
@@ -200,6 +200,11 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 					 keys.authkeylen, &istate, &ostate))
 			goto badkey;
 		break;
+	case CONTEXT_CONTROL_CRYPTO_ALG_SHA512:
+		if (safexcel_hmac_setkey("safexcel-sha512", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
 	default:
 		dev_err(priv->dev, "aead: unsupported hash algorithm\n");
 		goto badkey;
@@ -1019,3 +1024,37 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
 		},
 	},
 };
+
+static int safexcel_aead_sha512_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
+	ctx->state_sz = SHA512_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.alg.aead = {
+		.setkey = safexcel_aead_aes_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = AES_BLOCK_SIZE,
+		.maxauthsize = SHA512_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha512),cbc(aes))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha512-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha512_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
-- 
cgit v1.2.3


From 26f7120b86a964a886ececb9eb8e6dd50276dbb2 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:49 +0200
Subject: crypto: sha512_generic - add a sha384 0-length pre-computed hash

This patch adds the sha384 pre-computed 0-length hash so that device
drivers can use it when an hardware engine does not support computing a
hash from a 0 length input.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/sha512_generic.c | 10 ++++++++++
 include/crypto/sha.h    |  2 ++
 2 files changed, 12 insertions(+)

diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 439723d9273e..0b805d03b5e5 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -23,6 +23,16 @@
 #include <asm/byteorder.h>
 #include <asm/unaligned.h>
 
+const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE] = {
+	0x38, 0xb0, 0x60, 0xa7, 0x51, 0xac, 0x96, 0x38,
+	0x4c, 0xd9, 0x32, 0x7e, 0xb1, 0xb1, 0xe3, 0x6a,
+	0x21, 0xfd, 0xb7, 0x11, 0x14, 0xbe, 0x07, 0x43,
+	0x4c, 0x0c, 0xc7, 0xbf, 0x63, 0xf6, 0xe1, 0xda,
+	0x27, 0x4e, 0xde, 0xbf, 0xe7, 0x6f, 0x65, 0xfb,
+	0xd5, 0x1a, 0xd2, 0xf1, 0x48, 0x98, 0xb9, 0x5b
+};
+EXPORT_SYMBOL_GPL(sha384_zero_message_hash);
+
 const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE] = {
 	0xcf, 0x83, 0xe1, 0x35, 0x7e, 0xef, 0xb8, 0xbd,
 	0xf1, 0x54, 0x28, 0x50, 0xd6, 0x6d, 0x80, 0x07,
diff --git a/include/crypto/sha.h b/include/crypto/sha.h
index 799f071b93df..8a46202b1857 100644
--- a/include/crypto/sha.h
+++ b/include/crypto/sha.h
@@ -71,6 +71,8 @@ extern const u8 sha224_zero_message_hash[SHA224_DIGEST_SIZE];
 
 extern const u8 sha256_zero_message_hash[SHA256_DIGEST_SIZE];
 
+extern const u8 sha384_zero_message_hash[SHA384_DIGEST_SIZE];
+
 extern const u8 sha512_zero_message_hash[SHA512_DIGEST_SIZE];
 
 struct sha1_state {
-- 
cgit v1.2.3


From 9e46eafdf82a67dd069eef27c48898b79379c9f2 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:50 +0200
Subject: crypto: inside-secure - sha384 support

This patch adds the sha384 algorithm support to the Inside Secure
SafeXcel driver.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c      |  1 +
 drivers/crypto/inside-secure/safexcel.h      |  1 +
 drivers/crypto/inside-secure/safexcel_hash.c | 76 +++++++++++++++++++++++++++-
 3 files changed, 77 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index dcb39d0d82bb..b02451e0bbb6 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -790,6 +790,7 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_sha1,
 	&safexcel_alg_sha224,
 	&safexcel_alg_sha256,
+	&safexcel_alg_sha384,
 	&safexcel_alg_sha512,
 	&safexcel_alg_hmac_sha1,
 	&safexcel_alg_hmac_sha224,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 9e24cab279d2..57abf75e8b66 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -672,6 +672,7 @@ extern struct safexcel_alg_template safexcel_alg_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_sha1;
 extern struct safexcel_alg_template safexcel_alg_sha224;
 extern struct safexcel_alg_template safexcel_alg_sha256;
+extern struct safexcel_alg_template safexcel_alg_sha384;
 extern struct safexcel_alg_template safexcel_alg_sha512;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 0c452a4bc6dd..585667a1c259 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -96,7 +96,8 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224 ||
 				 ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(9);
-			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
+			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA384 ||
+				 ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(17);
 
 			cdesc->control_data.control1 |= CONTEXT_CONTROL_DIGEST_CNT;
@@ -660,6 +661,9 @@ static int safexcel_ahash_final(struct ahash_request *areq)
 		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
 			memcpy(areq->result, sha256_zero_message_hash,
 			       SHA256_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA384)
+			memcpy(areq->result, sha384_zero_message_hash,
+			       SHA384_DIGEST_SIZE);
 		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA512)
 			memcpy(areq->result, sha512_zero_message_hash,
 			       SHA512_DIGEST_SIZE);
@@ -1359,6 +1363,76 @@ struct safexcel_alg_template safexcel_alg_sha512 = {
 	},
 };
 
+static int safexcel_sha384_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = lower_32_bits(SHA384_H0);
+	req->state[1] = upper_32_bits(SHA384_H0);
+	req->state[2] = lower_32_bits(SHA384_H1);
+	req->state[3] = upper_32_bits(SHA384_H1);
+	req->state[4] = lower_32_bits(SHA384_H2);
+	req->state[5] = upper_32_bits(SHA384_H2);
+	req->state[6] = lower_32_bits(SHA384_H3);
+	req->state[7] = upper_32_bits(SHA384_H3);
+	req->state[8] = lower_32_bits(SHA384_H4);
+	req->state[9] = upper_32_bits(SHA384_H4);
+	req->state[10] = lower_32_bits(SHA384_H5);
+	req->state[11] = upper_32_bits(SHA384_H5);
+	req->state[12] = lower_32_bits(SHA384_H6);
+	req->state[13] = upper_32_bits(SHA384_H6);
+	req->state[14] = lower_32_bits(SHA384_H7);
+	req->state[15] = upper_32_bits(SHA384_H7);
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = SHA512_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_sha384_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_sha384_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_sha384 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_sha384_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_sha384_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA384_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "sha384",
+				.cra_driver_name = "safexcel-sha384",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA384_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
+
 static int safexcel_hmac_sha512_setkey(struct crypto_ahash *tfm, const u8 *key,
 				       unsigned int keylen)
 {
-- 
cgit v1.2.3


From 1f5d5d981879466c4af8be5415fb8be6eb451470 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:51 +0200
Subject: crypto: inside-secure - hmac(sha384) support

This patch adds the hmac(sha384) algorithm support to the Inside Secure
SafeXcel driver.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c      |  1 +
 drivers/crypto/inside-secure/safexcel.h      |  1 +
 drivers/crypto/inside-secure/safexcel_hash.c | 56 ++++++++++++++++++++++++++++
 3 files changed, 58 insertions(+)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index b02451e0bbb6..5ef8ba7ae29c 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -795,6 +795,7 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_hmac_sha1,
 	&safexcel_alg_hmac_sha224,
 	&safexcel_alg_hmac_sha256,
+	&safexcel_alg_hmac_sha384,
 	&safexcel_alg_hmac_sha512,
 	&safexcel_alg_authenc_hmac_sha1_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha224_cbc_aes,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 57abf75e8b66..e002f963ff5a 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -677,6 +677,7 @@ extern struct safexcel_alg_template safexcel_alg_sha512;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha256;
+extern struct safexcel_alg_template safexcel_alg_hmac_sha384;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha512;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 585667a1c259..188ba0734337 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -1488,3 +1488,59 @@ struct safexcel_alg_template safexcel_alg_hmac_sha512 = {
 		},
 	},
 };
+
+static int safexcel_hmac_sha384_setkey(struct crypto_ahash *tfm, const u8 *key,
+				       unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-sha384",
+					SHA512_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_sha384_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_sha384_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_sha384_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_sha384_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_sha384 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.alg.ahash = {
+		.init = safexcel_hmac_sha384_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_sha384_digest,
+		.setkey = safexcel_hmac_sha384_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = SHA384_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(sha384)",
+				.cra_driver_name = "safexcel-hmac-sha384",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = SHA384_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
-- 
cgit v1.2.3


From ea23cb533ce419204af129380cfe1d287481aa14 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 29 May 2018 14:13:52 +0200
Subject: crypto: inside-secure - authenc(hmac(sha384), cbc(aes)) support

This patch adds the authenc(hmac(sha384),cbc(aes)) algorithm support to
the Inside Secure SafeXcel driver.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        |  1 +
 drivers/crypto/inside-secure/safexcel.h        |  1 +
 drivers/crypto/inside-secure/safexcel_cipher.c | 39 ++++++++++++++++++++++++++
 3 files changed, 41 insertions(+)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 5ef8ba7ae29c..c39d2d7c9917 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -800,6 +800,7 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_authenc_hmac_sha1_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha224_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha256_cbc_aes,
+	&safexcel_alg_authenc_hmac_sha384_cbc_aes,
 	&safexcel_alg_authenc_hmac_sha512_cbc_aes,
 };
 
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index e002f963ff5a..5d6b3b705d0c 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -682,6 +682,7 @@ extern struct safexcel_alg_template safexcel_alg_hmac_sha512;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes;
 
 #endif
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 560c1e54ce9d..ca4bc2d28d2a 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -200,6 +200,11 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 					 keys.authkeylen, &istate, &ostate))
 			goto badkey;
 		break;
+	case CONTEXT_CONTROL_CRYPTO_ALG_SHA384:
+		if (safexcel_hmac_setkey("safexcel-sha384", keys.authkey,
+					 keys.authkeylen, &istate, &ostate))
+			goto badkey;
+		break;
 	case CONTEXT_CONTROL_CRYPTO_ALG_SHA512:
 		if (safexcel_hmac_setkey("safexcel-sha512", keys.authkey,
 					 keys.authkeylen, &istate, &ostate))
@@ -1058,3 +1063,37 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes = {
 		},
 	},
 };
+
+static int safexcel_aead_sha384_cra_init(struct crypto_tfm *tfm)
+{
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	safexcel_aead_cra_init(tfm);
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
+	ctx->state_sz = SHA512_DIGEST_SIZE;
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_aes = {
+	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.alg.aead = {
+		.setkey = safexcel_aead_aes_setkey,
+		.encrypt = safexcel_aead_encrypt,
+		.decrypt = safexcel_aead_decrypt,
+		.ivsize = AES_BLOCK_SIZE,
+		.maxauthsize = SHA384_DIGEST_SIZE,
+		.base = {
+			.cra_name = "authenc(hmac(sha384),cbc(aes))",
+			.cra_driver_name = "safexcel-authenc-hmac-sha384-cbc-aes",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_aead_sha384_cra_init,
+			.cra_exit = safexcel_aead_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
-- 
cgit v1.2.3


From b25c1199acaea4fbc69944c0c14eb2300de9dec4 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 30 May 2018 11:50:05 +0100
Subject: crypto: aegis - fix indentation of a statement

Trival fix to correct the indentation of a single statement

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/aegis128l.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crypto/aegis128l.c b/crypto/aegis128l.c
index 0cc1a7525c85..64dc2654b863 100644
--- a/crypto/aegis128l.c
+++ b/crypto/aegis128l.c
@@ -121,7 +121,7 @@ static void crypto_aegis128l_ad(struct aegis_state *state,
 				(const union aegis_chunk *)src;
 
 		while (size >= AEGIS128L_CHUNK_SIZE) {
-                    crypto_aegis128l_update_a(state, src_chunk);
+			crypto_aegis128l_update_a(state, src_chunk);
 
 			size -= AEGIS128L_CHUNK_SIZE;
 			src_chunk += 1;
-- 
cgit v1.2.3


From 2a2b9461f8aceab65bb46f33d7be65bfa3f015e1 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 1 Jun 2018 14:12:27 +0100
Subject: crypto: cavium - make structure algs static

The structure algs is local to the source and does not need to be in
global scope, so make it static.

Cleans up sparse warning:
drivers/crypto/cavium/cpt/cptvf_algs.c:354:19: warning: symbol 'algs'
was not declared. Should it be static?

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/cavium/cpt/cptvf_algs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/cavium/cpt/cptvf_algs.c b/drivers/crypto/cavium/cpt/cptvf_algs.c
index df21d996db7e..600336d169a9 100644
--- a/drivers/crypto/cavium/cpt/cptvf_algs.c
+++ b/drivers/crypto/cavium/cpt/cptvf_algs.c
@@ -351,7 +351,7 @@ static int cvm_enc_dec_init(struct crypto_tfm *tfm)
 	return 0;
 }
 
-struct crypto_alg algs[] = { {
+static struct crypto_alg algs[] = { {
 	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
 	.cra_blocksize = AES_BLOCK_SIZE,
 	.cra_ctxsize = sizeof(struct cvm_enc_ctx),
-- 
cgit v1.2.3


From e9440ff37254c85cbc1143991a39b656957394ba Mon Sep 17 00:00:00 2001
From: Tudor-Dan Ambarus <tudor.ambarus@microchip.com>
Date: Wed, 13 Jun 2018 16:29:58 +0300
Subject: crypto: atmel-ecc - fix to allow multi segment scatterlists

Remove the limitation of single element scatterlists. ECDH with
multi-element scatterlists is needed by TPM.

Similar to 'commit 95ec01ba1ef0 ("crypto: ecdh - fix to allow multi
segment scatterlists")'.

Signed-off-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/atmel-ecc.c | 31 ++++++++++++++++++++++---------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index e66f18a0ddd0..a25772ed26e1 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -186,7 +186,10 @@ static int atmel_ecc_init_ecdh_cmd(struct atmel_ecc_cmd *cmd,
 	 * always be the same. Use a macro for the key size to avoid unnecessary
 	 * computations.
 	 */
-	copied = sg_copy_to_buffer(pubkey, 1, cmd->data, ATMEL_ECC_PUBKEY_SIZE);
+	copied = sg_copy_to_buffer(pubkey,
+				   sg_nents_for_len(pubkey,
+						    ATMEL_ECC_PUBKEY_SIZE),
+				   cmd->data, ATMEL_ECC_PUBKEY_SIZE);
 	if (copied != ATMEL_ECC_PUBKEY_SIZE)
 		return -EINVAL;
 
@@ -268,15 +271,17 @@ static void atmel_ecdh_done(struct atmel_ecc_work_data *work_data, void *areq,
 	struct kpp_request *req = areq;
 	struct atmel_ecdh_ctx *ctx = work_data->ctx;
 	struct atmel_ecc_cmd *cmd = &work_data->cmd;
-	size_t copied;
-	size_t n_sz = ctx->n_sz;
+	size_t copied, n_sz;
 
 	if (status)
 		goto free_work_data;
 
+	/* might want less than we've got */
+	n_sz = min_t(size_t, ctx->n_sz, req->dst_len);
+
 	/* copy the shared secret */
-	copied = sg_copy_from_buffer(req->dst, 1, &cmd->data[RSP_DATA_IDX],
-				     n_sz);
+	copied = sg_copy_from_buffer(req->dst, sg_nents_for_len(req->dst, n_sz),
+				     &cmd->data[RSP_DATA_IDX], n_sz);
 	if (copied != n_sz)
 		status = -EINVAL;
 
@@ -440,7 +445,7 @@ static int atmel_ecdh_generate_public_key(struct kpp_request *req)
 {
 	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
 	struct atmel_ecdh_ctx *ctx = kpp_tfm_ctx(tfm);
-	size_t copied;
+	size_t copied, nbytes;
 	int ret = 0;
 
 	if (ctx->do_fallback) {
@@ -448,10 +453,14 @@ static int atmel_ecdh_generate_public_key(struct kpp_request *req)
 		return crypto_kpp_generate_public_key(req);
 	}
 
+	/* might want less than we've got */
+	nbytes = min_t(size_t, ATMEL_ECC_PUBKEY_SIZE, req->dst_len);
+
 	/* public key was saved at private key generation */
-	copied = sg_copy_from_buffer(req->dst, 1, ctx->public_key,
-				     ATMEL_ECC_PUBKEY_SIZE);
-	if (copied != ATMEL_ECC_PUBKEY_SIZE)
+	copied = sg_copy_from_buffer(req->dst,
+				     sg_nents_for_len(req->dst, nbytes),
+				     ctx->public_key, nbytes);
+	if (copied != nbytes)
 		ret = -EINVAL;
 
 	return ret;
@@ -470,6 +479,10 @@ static int atmel_ecdh_compute_shared_secret(struct kpp_request *req)
 		return crypto_kpp_compute_shared_secret(req);
 	}
 
+	/* must have exactly two points to be on the curve */
+	if (req->src_len != ATMEL_ECC_PUBKEY_SIZE)
+		return -EINVAL;
+
 	gfp = (req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP) ? GFP_KERNEL :
 							     GFP_ATOMIC;
 
-- 
cgit v1.2.3


From 38641b83ebc54635151810eeef00b61da3097952 Mon Sep 17 00:00:00 2001
From: Tudor-Dan Ambarus <tudor.ambarus@microchip.com>
Date: Wed, 13 Jun 2018 16:29:59 +0300
Subject: crypto: atmel-ecc - remove overly verbose dev_info

Remove it because when using a slow console, it can affect
the speed of crypto operations.

Similar to 'commit 730f23b66095 ("crypto: vmx - Remove overly
verbose printk from AES XTS init")'.

Signed-off-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/atmel-ecc.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/crypto/atmel-ecc.c b/drivers/crypto/atmel-ecc.c
index a25772ed26e1..74f083f45e97 100644
--- a/drivers/crypto/atmel-ecc.c
+++ b/drivers/crypto/atmel-ecc.c
@@ -567,10 +567,6 @@ static int atmel_ecdh_init_tfm(struct crypto_kpp *tfm)
 	}
 
 	crypto_kpp_set_flags(fallback, crypto_kpp_get_flags(tfm));
-
-	dev_info(&ctx->client->dev, "Using '%s' as fallback implementation.\n",
-		 crypto_tfm_alg_driver_name(crypto_kpp_tfm(fallback)));
-
 	ctx->fallback = fallback;
 
 	return 0;
-- 
cgit v1.2.3


From 4adc18371f14cf9dfd169d9b8ebdfdaee13c2639 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 22 Jun 2018 11:23:26 +0200
Subject: drm/omap: remove now unused functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some functions are unused after removal of the kmap_atomic
DMA-buf interface.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Fixes: f664a5269542 ("dma-buf: remove kmap_atomic interface")
Link: https://patchwork.freedesktop.org/series/45245/
---
 drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c | 17 -----------------
 1 file changed, 17 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index 1a073f9b2834..ec04a69ade46 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -93,23 +93,6 @@ static int omap_gem_dmabuf_end_cpu_access(struct dma_buf *buffer,
 	return 0;
 }
 
-
-static void *omap_gem_dmabuf_kmap_atomic(struct dma_buf *buffer,
-		unsigned long page_num)
-{
-	struct drm_gem_object *obj = buffer->priv;
-	struct page **pages;
-	omap_gem_get_pages(obj, &pages, false);
-	omap_gem_cpu_sync_page(obj, page_num);
-	return kmap_atomic(pages[page_num]);
-}
-
-static void omap_gem_dmabuf_kunmap_atomic(struct dma_buf *buffer,
-		unsigned long page_num, void *addr)
-{
-	kunmap_atomic(addr);
-}
-
 static void *omap_gem_dmabuf_kmap(struct dma_buf *buffer,
 		unsigned long page_num)
 {
-- 
cgit v1.2.3


From aa58f58d9c6471a1087ede57e4ab6cc0817c949f Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Fri, 22 Jun 2018 11:19:03 -0700
Subject: drm/i915/guc: Remove USES_GUC_SUBMISSION for ads programming

In the guc_ctl_debug_flags, the ads struct is programmed only
when USES_GUC_SUBMISSION is satisfied. But, this has to be
programmed for all suspend/resume cases.
Remove the condition and program the ads struct for
both huc loading and guc submission.

This issue was noticed when CI threw errors for enable_guc=2
(load huc; disable submission)

v2:
- Change commit title.
- Correct the shifts. (Daniele)

Credits to: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: John Spotswood <john.a.spotswood@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: John Spotswood <john.a.spotswood@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/1529691543-28606-1-git-send-email-anusha.srivatsa@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 1aff30b0870c..f651e57b4c61 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -206,7 +206,11 @@ void intel_guc_fini(struct intel_guc *guc)
 static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 {
 	u32 level = intel_guc_log_get_level(&guc->log);
-	u32 flags = 0;
+	u32 flags;
+	u32 ads;
+
+	ads = intel_guc_ggtt_offset(guc, guc->ads_vma) >> PAGE_SHIFT;
+	flags = ads << GUC_ADS_ADDR_SHIFT | GUC_ADS_ENABLED;
 
 	if (!GUC_LOG_LEVEL_IS_ENABLED(level))
 		flags |= GUC_LOG_DEFAULT_DISABLED;
@@ -217,13 +221,6 @@ static u32 guc_ctl_debug_flags(struct intel_guc *guc)
 		flags |= GUC_LOG_LEVEL_TO_VERBOSITY(level) <<
 			 GUC_LOG_VERBOSITY_SHIFT;
 
-	if (USES_GUC_SUBMISSION(guc_to_i915(guc))) {
-		u32 ads = intel_guc_ggtt_offset(guc, guc->ads_vma)
-			>> PAGE_SHIFT;
-
-		flags |= ads << GUC_ADS_ADDR_SHIFT | GUC_ADS_ENABLED;
-	}
-
 	return flags;
 }
 
-- 
cgit v1.2.3


From 46d8f405e16cdc47962edbe7771246c8d5b8c795 Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Thu, 21 Jun 2018 12:54:28 -0700
Subject: drm: Consider drivers setting DRIVER_ATOMIC as atomic.

Drivers such as vc4 don't initialize mode_config.funcs until later in
initialization, but we know they're atomic since they've got the flag
set.  This avoids oopsing on dereferencing funcs in the new atomic
methods sanity checks.

I moved the atomic check function down below the core flag check, to
avoid needing a prototype.

Signed-off-by: Eric Anholt <eric@anholt.net>
Fixes: ba1f665f161c ("drm: Add checks for atomic_[duplicate/destroy]_state with atomic drivers")
Link: https://patchwork.freedesktop.org/patch/msgid/20180621195428.17447-1-eric@anholt.net
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/drm/drmP.h | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index f5099c12c6a6..c5dfbdb7271d 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -97,6 +97,16 @@ struct pci_controller;
 
 #define DRM_IF_VERSION(maj, min) (maj << 16 | min)
 
+#define DRM_SWITCH_POWER_ON 0
+#define DRM_SWITCH_POWER_OFF 1
+#define DRM_SWITCH_POWER_CHANGING 2
+#define DRM_SWITCH_POWER_DYNAMIC_OFF 3
+
+static inline bool drm_core_check_feature(struct drm_device *dev, int feature)
+{
+	return dev->driver->driver_features & feature;
+}
+
 /**
  * drm_drv_uses_atomic_modeset - check if the driver implements
  * atomic_commit()
@@ -107,17 +117,8 @@ struct pci_controller;
  */
 static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev)
 {
-	return dev->mode_config.funcs->atomic_commit != NULL;
-}
-
-#define DRM_SWITCH_POWER_ON 0
-#define DRM_SWITCH_POWER_OFF 1
-#define DRM_SWITCH_POWER_CHANGING 2
-#define DRM_SWITCH_POWER_DYNAMIC_OFF 3
-
-static inline bool drm_core_check_feature(struct drm_device *dev, int feature)
-{
-	return dev->driver->driver_features & feature;
+	return drm_core_check_feature(dev, DRIVER_ATOMIC) ||
+		dev->mode_config.funcs->atomic_commit != NULL;
 }
 
 /* returns true if currently okay to sleep */
-- 
cgit v1.2.3


From d55207e37a35f811e1d93ae83d4dcaaaecde053d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 21 Jun 2018 20:58:00 +0200
Subject: net: phy: Allow compile test of GPIO consumers if !GPIOLIB

The GPIO subsystem provides dummy GPIO consumer functions if GPIOLIB is
not enabled. Hence drivers that depend on GPIOLIB, but use GPIO consumer
functionality only, can still be compiled if GPIOLIB is not enabled.

Relax the dependency on GPIOLIB if COMPILE_TEST is enabled, where
appropriate.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 343989f9f9d9..ceede09a2845 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -92,7 +92,8 @@ config MDIO_CAVIUM
 
 config MDIO_GPIO
 	tristate "GPIO lib-based bitbanged MDIO buses"
-	depends on MDIO_BITBANG && GPIOLIB
+	depends on MDIO_BITBANG
+	depends on GPIOLIB || COMPILE_TEST
 	---help---
 	  Supports GPIO lib-based MDIO busses.
 
-- 
cgit v1.2.3


From 6c1f0a1ffb7c2b0501521b9fc1f53b4109f1791b Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 22 Jun 2018 10:51:00 -0700
Subject: net: drivers/net: Convert random_ether_addr to eth_random_addr

random_ether_addr is a #define for eth_random_addr which is
generally preferred in kernel code by ~3:1

Convert the uses of random_ether_addr to enable removing the #define

Miscellanea:

o Convert &vfmac[0] to equivalent vfmac and avoid unnecessary line wrap

Signed-off-by: Joe Perches <joe@perches.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/lio_main.c          | 5 ++---
 drivers/net/ethernet/cortina/gemini.c                    | 2 +-
 drivers/net/ethernet/hisilicon/hip04_eth.c               | 2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c              | 2 +-
 drivers/net/ethernet/microchip/lan743x_main.c            | 2 +-
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c | 2 +-
 drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c          | 2 +-
 drivers/net/ethernet/sfc/ef10_sriov.c                    | 2 +-
 drivers/net/ethernet/ti/cpsw.c                           | 2 +-
 drivers/net/ethernet/ti/netcp_core.c                     | 4 ++--
 drivers/net/ntb_netdev.c                                 | 2 +-
 drivers/net/usb/lan78xx.c                                | 2 +-
 drivers/net/wireless/ath/ath9k/hw.c                      | 2 +-
 net/batman-adv/bridge_loop_avoidance.c                   | 2 +-
 14 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8a815bb57177..7cb4e753829b 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -3569,9 +3569,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 		for (j = 0; j < octeon_dev->sriov_info.max_vfs; j++) {
 			u8 vfmac[ETH_ALEN];
 
-			random_ether_addr(&vfmac[0]);
-			if (__liquidio_set_vf_mac(netdev, j,
-						  &vfmac[0], false)) {
+			eth_random_addr(vfmac);
+			if (__liquidio_set_vf_mac(netdev, j, vfmac, false)) {
 				dev_err(&octeon_dev->pci_dev->dev,
 					"Error setting VF%d MAC address\n",
 					j);
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 6d7404f66f84..ce1f04fdbf70 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2435,7 +2435,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 			port->mac_addr[0], port->mac_addr[1],
 			port->mac_addr[2]);
 		dev_info(dev, "using a random ethernet address\n");
-		random_ether_addr(netdev->dev_addr);
+		eth_random_addr(netdev->dev_addr);
 	}
 	gmac_write_mac_address(netdev);
 
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index 340e28211135..14374a856d30 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -904,7 +904,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 		hip04_config_port(ndev, SPEED_100, DUPLEX_FULL);
 
 	hip04_config_fifo(priv);
-	random_ether_addr(ndev->dev_addr);
+	eth_random_addr(ndev->dev_addr);
 	hip04_update_mac_address(ndev);
 
 	ret = hip04_alloc_ring(ndev, d);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index c944bd10b03d..95e9dfbe9839 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11978,7 +11978,7 @@ static int i40e_config_netdev(struct i40e_vsi *vsi)
 		snprintf(netdev->name, IFNAMSIZ, "%.*sv%%d",
 			 IFNAMSIZ - 4,
 			 pf->vsi[pf->lan_vsi]->netdev->name);
-		random_ether_addr(mac_addr);
+		eth_random_addr(mac_addr);
 
 		spin_lock_bh(&vsi->mac_filter_hash_lock);
 		i40e_add_mac_filter(vsi, mac_addr);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index dd947e4dd3ce..e1747a490066 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -828,7 +828,7 @@ static int lan743x_mac_init(struct lan743x_adapter *adapter)
 	}
 
 	if (!mac_address_valid)
-		random_ether_addr(adapter->mac_address);
+		eth_random_addr(adapter->mac_address);
 	lan743x_mac_set_address(adapter, adapter->mac_address);
 	ether_addr_copy(netdev->dev_addr, adapter->mac_address);
 	return 0;
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index 0c744b9c6e0a..77e386ebff09 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -212,7 +212,7 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs)
 			vp->max_tx_bw = MAX_BW;
 			vp->min_tx_bw = MIN_BW;
 			vp->spoofchk = false;
-			random_ether_addr(vp->mac);
+			eth_random_addr(vp->mac);
 			dev_info(&adapter->pdev->dev,
 				 "MAC Address %pM is configured for VF %d\n",
 				 vp->mac, i);
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
index b9a7548ec6a0..0afc3d335d56 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_vnd.c
@@ -210,7 +210,7 @@ void rmnet_vnd_setup(struct net_device *rmnet_dev)
 	rmnet_dev->netdev_ops = &rmnet_vnd_ops;
 	rmnet_dev->mtu = RMNET_DFLT_PACKET_SIZE;
 	rmnet_dev->needed_headroom = RMNET_NEEDED_HEADROOM;
-	random_ether_addr(rmnet_dev->dev_addr);
+	eth_random_addr(rmnet_dev->dev_addr);
 	rmnet_dev->tx_queue_len = RMNET_TX_QUEUE_LEN;
 
 	/* Raw IP mode */
diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 019cef1d3cf7..8820be83ce85 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -199,7 +199,7 @@ static int efx_ef10_sriov_alloc_vf_vswitching(struct efx_nic *efx)
 		return -ENOMEM;
 
 	for (i = 0; i < efx->vf_count; i++) {
-		random_ether_addr(nic_data->vf[i].mac);
+		eth_random_addr(nic_data->vf[i].mac);
 		nic_data->vf[i].efx = NULL;
 		nic_data->vf[i].vlan = EFX_EF10_NO_VLAN;
 
diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 358edab9e72e..093998124149 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -2927,7 +2927,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 		dev_info(cpsw->dev, "cpsw: Detected MACID = %pM\n",
 			 priv_sl2->mac_addr);
 	} else {
-		random_ether_addr(priv_sl2->mac_addr);
+		eth_random_addr(priv_sl2->mac_addr);
 		dev_info(cpsw->dev, "cpsw: Random MACID = %pM\n",
 			 priv_sl2->mac_addr);
 	}
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index e40aa3e31af2..6ebf110cd594 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -2052,7 +2052,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device,
 		if (is_valid_ether_addr(efuse_mac_addr))
 			ether_addr_copy(ndev->dev_addr, efuse_mac_addr);
 		else
-			random_ether_addr(ndev->dev_addr);
+			eth_random_addr(ndev->dev_addr);
 
 		devm_iounmap(dev, efuse);
 		devm_release_mem_region(dev, res.start, size);
@@ -2061,7 +2061,7 @@ static int netcp_create_interface(struct netcp_device *netcp_device,
 		if (mac_addr)
 			ether_addr_copy(ndev->dev_addr, mac_addr);
 		else
-			random_ether_addr(ndev->dev_addr);
+			eth_random_addr(ndev->dev_addr);
 	}
 
 	ret = of_property_read_string(node_interface, "rx-channel",
diff --git a/drivers/net/ntb_netdev.c b/drivers/net/ntb_netdev.c
index 9f6f7ccd44f7..b12023bc2cab 100644
--- a/drivers/net/ntb_netdev.c
+++ b/drivers/net/ntb_netdev.c
@@ -430,7 +430,7 @@ static int ntb_netdev_probe(struct device *client_dev)
 	ndev->hw_features = ndev->features;
 	ndev->watchdog_timeo = msecs_to_jiffies(NTB_TX_TIMEOUT_MS);
 
-	random_ether_addr(ndev->perm_addr);
+	eth_random_addr(ndev->perm_addr);
 	memcpy(ndev->dev_addr, ndev->perm_addr, ndev->addr_len);
 
 	ndev->netdev_ops = &ntb_netdev_ops;
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 8dff87ec6d99..a89570f34937 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1720,7 +1720,7 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev)
 				  "MAC address read from EEPROM");
 		} else {
 			/* generate random MAC */
-			random_ether_addr(addr);
+			eth_random_addr(addr);
 			netif_dbg(dev, ifup, dev->net,
 				  "MAC address set to random addr");
 		}
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index e60bea4604e4..1665066f4e24 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -496,7 +496,7 @@ static void ath9k_hw_init_macaddr(struct ath_hw *ah)
 	ath_err(common, "eeprom contains invalid mac address: %pM\n",
 		common->macaddr);
 
-	random_ether_addr(common->macaddr);
+	eth_random_addr(common->macaddr);
 	ath_err(common, "random mac address will be used: %pM\n",
 		common->macaddr);
 
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index a2de5a44bd41..ff9659af6b91 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -1449,7 +1449,7 @@ static void batadv_bla_periodic_work(struct work_struct *work)
 		 * detection frames. Set the locally administered bit to avoid
 		 * collisions with users mac addresses.
 		 */
-		random_ether_addr(bat_priv->bla.loopdetect_addr);
+		eth_random_addr(bat_priv->bla.loopdetect_addr);
 		bat_priv->bla.loopdetect_addr[0] = 0xba;
 		bat_priv->bla.loopdetect_addr[1] = 0xbe;
 		bat_priv->bla.loopdetect_lasttime = jiffies;
-- 
cgit v1.2.3


From 5424ea27390f1f8903e5de0eaa0c5b561e8e877a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 22 Jun 2018 16:27:47 -0700
Subject: netns: get more entropy from net_hash_mix()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

struct net are effectively allocated from order-1 pages on x86,
with one object per slab, meaning that the 13 low order bits
of their addresses are zero.

Once shifted by L1_CACHE_SHIFT, this leaves 7 zero-bits,
meaning that net_hash_mix() does not help spreading
objects on various hash tables.

For example, TCP listen table has 32 buckets, meaning that
all netns use the same bucket for port 80 or port 443.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Maciej Żenczykowski <maze@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netns/hash.h | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/include/net/netns/hash.h b/include/net/netns/hash.h
index 24c78183a4c2..16a842456189 100644
--- a/include/net/netns/hash.h
+++ b/include/net/netns/hash.h
@@ -9,12 +9,7 @@ struct net;
 static inline u32 net_hash_mix(const struct net *net)
 {
 #ifdef CONFIG_NET_NS
-	/*
-	 * shift this right to eliminate bits, that are
-	 * always zeroed
-	 */
-
-	return (u32)(((unsigned long)net) >> L1_CACHE_SHIFT);
+	return (u32)(((unsigned long)net) >> ilog2(sizeof(*net)));
 #else
 	return 0;
 #endif
-- 
cgit v1.2.3


From 951a06e78d5af9ffda9f00139fef1186c202f8ae Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sat, 26 May 2018 11:40:32 +0200
Subject: batman-adv: Drop "experimental" from BATMAN_V Kconfig

The Kconfig option BATMAN_ADV_BATMAN_V is now enabled by default when the
BATMAN_ADV is enabled. A feature which is enabled by default for a module
should not be considered experimental.

Reported-by: Joe Perches <joe@perches.com>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index de8034d80623..98c7f3820d53 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -33,7 +33,7 @@ config BATMAN_ADV
           tools.
 
 config BATMAN_ADV_BATMAN_V
-	bool "B.A.T.M.A.N. V protocol (experimental)"
+	bool "B.A.T.M.A.N. V protocol"
 	depends on BATMAN_ADV && !(CFG80211=m && BATMAN_ADV=y)
 	default y
 	help
-- 
cgit v1.2.3


From ab4e58534dee7f273badfe21fa29cbe24553682f Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <a@unstable.cc>
Date: Sun, 3 Jun 2018 18:52:03 +0800
Subject: batman-adv: enable DAT by default at compile time

DAT (Distributed ARP Table) has been enabled by default
in the out-of-tree batman-adv kernel module for several
years already.
It can now be enabled in the kernel too.

Signed-off-by: Antonio Quartulli <a@unstable.cc>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index 98c7f3820d53..ff38df8bab91 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -60,7 +60,7 @@ config BATMAN_ADV_BLA
 config BATMAN_ADV_DAT
 	bool "Distributed ARP Table"
 	depends on BATMAN_ADV && INET
-	default n
+	default y
 	help
 	  This option enables DAT (Distributed ARP Table), a DHT based
 	  mechanism that increases ARP reliability on sparse wireless
-- 
cgit v1.2.3


From 55f949c4fa6cefb199fd6208c275a3457e39e4bc Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sat, 26 May 2018 11:40:31 +0200
Subject: batman-adv: Remove "default n" in Kconfig

The "default n" is the default value for any bool or tristate Kconfig
setting. It is therefore not necessary to add it to a config entry.

Reported-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/Kconfig | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig
index ff38df8bab91..361116f77cb9 100644
--- a/net/batman-adv/Kconfig
+++ b/net/batman-adv/Kconfig
@@ -24,7 +24,6 @@ config BATMAN_ADV
 	depends on NET
 	select CRC16
 	select LIBCRC32C
-        default n
 	help
           B.A.T.M.A.N. (better approach to mobile ad-hoc networking) is
           a routing protocol for multi-hop ad-hoc mesh networks. The
@@ -70,7 +69,6 @@ config BATMAN_ADV_DAT
 config BATMAN_ADV_NC
 	bool "Network Coding"
 	depends on BATMAN_ADV
-	default n
 	help
 	  This option enables network coding, a mechanism that aims to
 	  increase the overall network throughput by fusing multiple
@@ -84,7 +82,6 @@ config BATMAN_ADV_NC
 config BATMAN_ADV_MCAST
 	bool "Multicast optimisation"
 	depends on BATMAN_ADV && INET && !(BRIDGE=m && BATMAN_ADV=y)
-	default n
 	help
 	  This option enables the multicast optimisation which aims to
 	  reduce the air overhead while improving the reliability of
@@ -94,7 +91,6 @@ config BATMAN_ADV_DEBUGFS
 	bool "batman-adv debugfs entries"
 	depends on BATMAN_ADV
 	depends on DEBUG_FS
-	default n
 	help
 	  Enable this to export routing related debug tables via debugfs.
 	  The information for each soft-interface and used hard-interface can be
-- 
cgit v1.2.3


From 32206ab36553be8714d9253ce33f4085681d369c Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:52 -0700
Subject: x86/intel_rdt: Provide pseudo-locking hooks within rdt_mount

Stephen Rothwell reported that the Cache Pseudo-Locking enabling and the
kernfs support for mounting with fs_context are conflicting.

In preparation for a conflict-free merge between the two repos some no-op
hooks are created within the RDT mount function being changed by the two
features. The goal is for this commit to be placed on a minimal no-rebase
branch to be consumed by both features.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Suggested-by: Al Viro <viro@ZenIV.linux.org.uk>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Cc: David Howells <dhowells@redhat.com>
Link: https://lkml.kernel.org/r/410697ead08978bd12111c0afc4ce9e7bd71a5fe.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          |  9 +++++++++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 10 +++++++++-
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 39752825e376..be152b3b2543 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -468,4 +468,13 @@ void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 
+/*
+ * Define the hooks for Cache Pseudo-Locking to use within rdt_mount().
+ * These are no-ops provided for the new kernfs changes to use as a
+ * baseline in preparation for a conflict-free merge between it
+ * (kernfs changes) and the Cache Pseudo-Locking enabling.
+ */
+static inline int rdt_pseudo_lock_init(void) { return 0; }
+static inline void rdt_pseudo_lock_release(void) { }
+
 #endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 749856a2e736..fa668f967062 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1289,10 +1289,16 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 		rdtgroup_default.mon.mon_data_kn = kn_mondata;
 	}
 
+	ret = rdt_pseudo_lock_init();
+	if (ret) {
+		dentry = ERR_PTR(ret);
+		goto out_mondata;
+	}
+
 	dentry = kernfs_mount(fs_type, flags, rdt_root,
 			      RDTGROUP_SUPER_MAGIC, NULL);
 	if (IS_ERR(dentry))
-		goto out_mondata;
+		goto out_psl;
 
 	if (rdt_alloc_capable)
 		static_branch_enable_cpuslocked(&rdt_alloc_enable_key);
@@ -1310,6 +1316,8 @@ static struct dentry *rdt_mount(struct file_system_type *fs_type,
 
 	goto out;
 
+out_psl:
+	rdt_pseudo_lock_release();
 out_mondata:
 	if (rdt_mon_capable)
 		kernfs_remove(kn_mondata);
-- 
cgit v1.2.3


From cba1aab84fb815675038f9f932c1dd0a5519c63d Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:53 -0700
Subject: x86/intel_rdt: Document new mode, size, and bit_usage

By default resource groups allow sharing of their cache allocations.  There
is nothing that prevents a resource group from configuring a cache
allocation that overlaps with that of an existing resource group.

To enable resource groups to specify that their cache allocations cannot be
shared a resource group "mode" is introduced to support two possible modes:
"shareable" and "exclusive". A "shareable" resource group allows sharing of
its cache allocations, an "exclusive" resource group does not. A new
resctrl file "mode" associated with each resource group is used to
communicate its (the associated resource group's) mode setting and allow
the mode to be changed.  The new "mode" file as well as two other resctrl
files, "bit_usage" and "size", are introduced in this series.

Add documentation for the three new resctrl files as well as one example
demonstrating their use.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/f03a3059ec40ae719be6f3fba9f446bb055e0064.1529706536.git.reinette.chatre@intel.com
---
 Documentation/x86/intel_rdt_ui.txt | 99 +++++++++++++++++++++++++++++++++++++-
 1 file changed, 97 insertions(+), 2 deletions(-)

diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index a16aa2113840..de913e00e922 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -65,6 +65,27 @@ related to allocation:
 			some platforms support devices that have their
 			own settings for cache use which can over-ride
 			these bits.
+"bit_usage":		Annotated capacity bitmasks showing how all
+			instances of the resource are used. The legend is:
+			"0" - Corresponding region is unused. When the system's
+			      resources have been allocated and a "0" is found
+			      in "bit_usage" it is a sign that resources are
+			      wasted.
+			"H" - Corresponding region is used by hardware only
+			      but available for software use. If a resource
+			      has bits set in "shareable_bits" but not all
+			      of these bits appear in the resource groups'
+			      schematas then the bits appearing in
+			      "shareable_bits" but no resource group will
+			      be marked as "H".
+			"X" - Corresponding region is available for sharing and
+			      used by hardware and software. These are the
+			      bits that appear in "shareable_bits" as
+			      well as a resource group's allocation.
+			"S" - Corresponding region is used by software
+			      and available for sharing.
+			"E" - Corresponding region is used exclusively by
+			      one resource group. No sharing allowed.
 
 Memory bandwitdh(MB) subdirectory contains the following files
 with respect to allocation:
@@ -163,6 +184,16 @@ When control is enabled all CTRL_MON groups will also contain:
 	A list of all the resources available to this group.
 	Each resource has its own line and format - see below for details.
 
+"size":
+	Mirrors the display of the "schemata" file to display the size in
+	bytes of each allocation instead of the bits representing the
+	allocation.
+
+"mode":
+	The "mode" of the resource group dictates the sharing of its
+	allocations. A "shareable" resource group allows sharing of its
+	allocations while an "exclusive" resource group does not.
+
 When monitoring is enabled all MON groups will also contain:
 
 "mon_data":
@@ -502,7 +533,71 @@ siblings and only the real time threads are scheduled on the cores 4-7.
 
 # echo F0 > p0/cpus
 
-4) Locking between applications
+Example 4
+---------
+
+The resource groups in previous examples were all in the default "shareable"
+mode allowing sharing of their cache allocations. If one resource group
+configures a cache allocation then nothing prevents another resource group
+to overlap with that allocation.
+
+In this example a new exclusive resource group will be created on a L2 CAT
+system with two L2 cache instances that can be configured with an 8-bit
+capacity bitmask. The new exclusive resource group will be configured to use
+25% of each cache instance.
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+First, we observe that the default group is configured to allocate to all L2
+cache:
+
+# cat schemata
+L2:0=ff;1=ff
+
+We could attempt to create the new resource group at this point, but it will
+fail because of the overlap with the schemata of the default group:
+# mkdir p0
+# echo 'L2:0=0x3;1=0x3' > p0/schemata
+# cat p0/mode
+shareable
+# echo exclusive > p0/mode
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+schemata overlaps
+
+To ensure that there is no overlap with another resource group the default
+resource group's schemata has to change, making it possible for the new
+resource group to become exclusive.
+# echo 'L2:0=0xfc;1=0xfc' > schemata
+# echo exclusive > p0/mode
+# grep . p0/*
+p0/cpus:0
+p0/mode:exclusive
+p0/schemata:L2:0=03;1=03
+p0/size:L2:0=262144;1=262144
+
+A new resource group will on creation not overlap with an exclusive resource
+group:
+# mkdir p1
+# grep . p1/*
+p1/cpus:0
+p1/mode:shareable
+p1/schemata:L2:0=fc;1=fc
+p1/size:L2:0=786432;1=786432
+
+The bit_usage will reflect how the cache is used:
+# cat info/L2/bit_usage
+0=SSSSSSEE;1=SSSSSSEE
+
+A resource group cannot be forced to overlap with an exclusive resource group:
+# echo 'L2:0=0x1;1=0x1' > p1/schemata
+-sh: echo: write error: Invalid argument
+# cat info/last_cmd_status
+overlaps with exclusive group
+
+Locking between applications
+----------------------------
 
 Certain operations on the resctrl filesystem, composed of read/writes
 to/from multiple files, must be atomic.
@@ -510,7 +605,7 @@ to/from multiple files, must be atomic.
 As an example, the allocation of an exclusive reservation of L3 cache
 involves:
 
-  1. Read the cbmmasks from each directory
+  1. Read the cbmmasks from each directory or the per-resource "bit_usage"
   2. Find a contiguous set of bits in the global CBM bitmask that is clear
      in any of the directory cbmmasks
   3. Create a new directory
-- 
cgit v1.2.3


From eb956a636f90bd0297309a7eae6db388ae5bfc43 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:54 -0700
Subject: x86/intel_rdt: Introduce RDT resource group mode

At this time there are no constraints on how bitmasks represented by
schemata can be associated with closids represented by resource groups.  A
bitmask of one class of service can without any objections overlap with the
bitmask of another class of service.

The concept of "mode" is introduced in preparation for support of control
over whether cache regions can be shared between classes of service. At
this time the only mode reflects the current cache allocations where all
can potentially be shared.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/87e88275597fbfa03ea9d41c1186bf012c831c01.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index be152b3b2543..fef254e85da4 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -80,6 +80,22 @@ enum rdt_group_type {
 	RDT_NUM_GROUP,
 };
 
+/**
+ * enum rdtgrp_mode - Mode of a RDT resource group
+ * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
+ *
+ * The mode of a resource group enables control over the allowed overlap
+ * between allocations associated with different resource groups (classes
+ * of service). User is able to modify the mode of a resource group by
+ * writing to the "mode" resctrl file associated with the resource group.
+ */
+enum rdtgrp_mode {
+	RDT_MODE_SHAREABLE = 0,
+
+	/* Must be last */
+	RDT_NUM_MODES,
+};
+
 /**
  * struct mongroup - store mon group's data in resctrl fs.
  * @mon_data_kn		kernlfs node for the mon_data directory
-- 
cgit v1.2.3


From 472ef09b40c5802a2e014ae2503ad8619486f9e6 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:55 -0700
Subject: x86/intel_rdt: Associate mode with each RDT resource group

Each RDT resource group is associated with a mode that will reflect
the level of sharing of its allocations. The default, shareable, will be
associated with each resource group on creation since it is zero and
resource groups are created with kzalloc. The managing of the mode of a
resource group will follow. The default resource group always remain
though so ensure that it is reset to the default mode when the resctrl
filesystem is unmounted.

Also introduce a utility that can be used to determine the mode of a
resource group when it is searched for based on its class of service.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/797e4e1de4e4fcdf5b5e0039354d6a28079e2015.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          |  3 +++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 22 ++++++++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index fef254e85da4..482dd6d3b8c5 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -122,6 +122,7 @@ struct mongroup {
  * @type:			indicates type of this rdtgroup - either
  *				monitor only or ctrl_mon group
  * @mon:			mongroup related data
+ * @mode:			mode of resource group
  */
 struct rdtgroup {
 	struct kernfs_node	*kn;
@@ -132,6 +133,7 @@ struct rdtgroup {
 	atomic_t		waitcount;
 	enum rdt_group_type	type;
 	struct mongroup		mon;
+	enum rdtgrp_mode	mode;
 };
 
 /* rdtgroup.flags */
@@ -461,6 +463,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int alloc_rmid(void);
 void free_rmid(u32 rmid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index fa668f967062..4a72061df7cd 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -126,6 +126,27 @@ static void closid_free(int closid)
 	closid_free_map |= 1 << closid;
 }
 
+/**
+ * rdtgroup_mode_by_closid - Return mode of resource group with closid
+ * @closid: closid if the resource group
+ *
+ * Each resource group is associated with a @closid. Here the mode
+ * of a resource group can be queried by searching for it using its closid.
+ *
+ * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
+ */
+enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
+{
+	struct rdtgroup *rdtgrp;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->closid == closid)
+			return rdtgrp->mode;
+	}
+
+	return RDT_NUM_MODES;
+}
+
 /* set uid and gid of rdtgroup dirs and files to that of the creator */
 static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
 {
@@ -1491,6 +1512,7 @@ static void rdt_kill_sb(struct super_block *sb)
 		reset_all_ctrls(r);
 	cdp_disable_all();
 	rmdir_all_sub();
+	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
 	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
 	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
 	static_branch_disable_cpuslocked(&rdt_enable_key);
-- 
cgit v1.2.3


From d48d7a57f7181b36be748ad8fb806e8de3104e89 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:56 -0700
Subject: x86/intel_rdt: Introduce resource group's mode resctrl file

A new resctrl file "mode" associated with each resource group is
introduced. This file will display the resource group's current mode and an
administrator can also use it to modify the resource group's mode.

Only shareable mode is currently supported.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/20ab78fda26a8c8d98e18ec555f6a1f728948972.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 83 ++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 4a72061df7cd..d00cce3186ad 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -147,6 +147,24 @@ enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
 	return RDT_NUM_MODES;
 }
 
+static const char * const rdt_mode_str[] = {
+	[RDT_MODE_SHAREABLE]	= "shareable",
+};
+
+/**
+ * rdtgroup_mode_str - Return the string representation of mode
+ * @mode: the resource group mode as &enum rdtgroup_mode
+ *
+ * Return: string representation of valid mode, "unknown" otherwise
+ */
+static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
+{
+	if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
+		return "unknown";
+
+	return rdt_mode_str[mode];
+}
+
 /* set uid and gid of rdtgroup dirs and files to that of the creator */
 static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
 {
@@ -761,6 +779,63 @@ static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
 	return nbytes;
 }
 
+/*
+ * rdtgroup_mode_show - Display mode of this resource group
+ */
+static int rdtgroup_mode_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
+
+	rdtgroup_kn_unlock(of->kn);
+	return 0;
+}
+
+static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
+				   char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	enum rdtgrp_mode mode;
+	int ret = 0;
+
+	/* Valid input requires a trailing newline */
+	if (nbytes == 0 || buf[nbytes - 1] != '\n')
+		return -EINVAL;
+	buf[nbytes - 1] = '\0';
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	rdt_last_cmd_clear();
+
+	mode = rdtgrp->mode;
+
+	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE))
+		goto out;
+
+	if (!strcmp(buf, "shareable")) {
+		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	} else {
+		rdt_last_cmd_printf("unknown/unsupported mode\n");
+		ret = -EINVAL;
+	}
+
+out:
+	rdtgroup_kn_unlock(of->kn);
+	return ret ?: nbytes;
+}
+
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
 	{
@@ -874,6 +949,14 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdtgroup_schemata_show,
 		.fflags		= RF_CTRL_BASE,
 	},
+	{
+		.name		= "mode",
+		.mode		= 0644,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.write		= rdtgroup_mode_write,
+		.seq_show	= rdtgroup_mode_show,
+		.fflags		= RF_CTRL_BASE,
+	},
 };
 
 static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
-- 
cgit v1.2.3


From 0b9aa6562650f42da23c29814adc2318c135cef4 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:57 -0700
Subject: x86/intel_rdt: Introduce test to determine if closid is in use

During CAT feature discovery the capacity bitmasks (CBMs) associated
with all the classes of service are initialized to all ones, even if the
class of service is not in use. Introduce a test that can be used to
determine if a class of service is in use. This test enables code
interested in parsing the CBMs to know if its values are meaningful or
can be ignored.

Temporarily mark the function as unused to silence compile warnings
until it is used.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/798f8d89cd9b12df492d48c14bdc8ee3b39b1c6f.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index d00cce3186ad..659b643fcf94 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -126,6 +126,18 @@ static void closid_free(int closid)
 	closid_free_map |= 1 << closid;
 }
 
+/**
+ * closid_allocated - test if provided closid is in use
+ * @closid: closid to be tested
+ *
+ * Return: true if @closid is currently associated with a resource group,
+ * false if @closid is free
+ */
+static bool __attribute__ ((unused)) closid_allocated(unsigned int closid)
+{
+	return (closid_free_map & (1 << closid)) == 0;
+}
+
 /**
  * rdtgroup_mode_by_closid - Return mode of resource group with closid
  * @closid: closid if the resource group
-- 
cgit v1.2.3


From 024d15be3855044faa8bddf829e3613961fd27ba Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:58 -0700
Subject: x86/intel_rdt: Make useful functions available internally

In support of the work done to enable resource groups to have different
modes some static functions need to be available for sharing amongst
all RDT components.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/2af8fd6e937ae4fbdaa52dee1123823cb4993176.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             | 2 ++
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 2 +-
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 2 +-
 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 482dd6d3b8c5..f2fbf4059b3f 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -465,6 +465,8 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
+int update_domains(struct rdt_resource *r, int closid);
+void closid_free(int closid);
 int alloc_rmid(void);
 void free_rmid(u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 116d57b248d3..2c23bb136ccc 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -175,7 +175,7 @@ next:
 	return -EINVAL;
 }
 
-static int update_domains(struct rdt_resource *r, int closid)
+int update_domains(struct rdt_resource *r, int closid)
 {
 	struct msr_param msr_param;
 	cpumask_var_t cpu_mask;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 659b643fcf94..04ef140ebc84 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -121,7 +121,7 @@ static int closid_alloc(void)
 	return closid;
 }
 
-static void closid_free(int closid)
+void closid_free(int closid)
 {
 	closid_free_map |= 1 << closid;
 }
-- 
cgit v1.2.3


From 95f0b77efa5749f19e7acfedcb8521da4b13ed0e Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:41:59 -0700
Subject: x86/intel_rdt: Initialize new resource group with sane defaults

Currently when a new resource group is created its allocations would be
those that belonged to the resource group to which its closid belonged
previously.

That is, we can encounter a case like:
mkdir newgroup
cat newgroup/schemata
L2:0=ff;1=ff
echo 'L2:0=0xf0;1=0xf0' > newgroup/schemata
cat newgroup/schemata
L2:0=0xf0;1=0xf0
rmdir newgroup
mkdir newnewgroup
cat newnewgroup/schemata
L2:0=0xf0;1=0xf0

When the new group is created it would be reasonable to expect its
allocations to be initialized with all regions that it can possibly use.
At this time these regions would be all that are shareable by other
resource groups as well as regions that are not currently used.
If the available cache region is found to be non-contiguous the
available region is adjusted to enforce validity.

When a new resource group is created the hardware is initialized with
these new default allocations.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/c468ed79340b63024111978e01430bb9589d85c0.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 115 ++++++++++++++++++++++++++++++-
 1 file changed, 112 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 04ef140ebc84..80ac09cf978b 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -133,7 +133,7 @@ void closid_free(int closid)
  * Return: true if @closid is currently associated with a resource group,
  * false if @closid is free
  */
-static bool __attribute__ ((unused)) closid_allocated(unsigned int closid)
+static bool closid_allocated(unsigned int closid)
 {
 	return (closid_free_map & (1 << closid)) == 0;
 }
@@ -1807,6 +1807,110 @@ out_destroy:
 	return ret;
 }
 
+/**
+ * cbm_ensure_valid - Enforce validity on provided CBM
+ * @_val:	Candidate CBM
+ * @r:		RDT resource to which the CBM belongs
+ *
+ * The provided CBM represents all cache portions available for use. This
+ * may be represented by a bitmap that does not consist of contiguous ones
+ * and thus be an invalid CBM.
+ * Here the provided CBM is forced to be a valid CBM by only considering
+ * the first set of contiguous bits as valid and clearing all bits.
+ * The intention here is to provide a valid default CBM with which a new
+ * resource group is initialized. The user can follow this with a
+ * modification to the CBM if the default does not satisfy the
+ * requirements.
+ */
+static void cbm_ensure_valid(u32 *_val, struct rdt_resource *r)
+{
+	/*
+	 * Convert the u32 _val to an unsigned long required by all the bit
+	 * operations within this function. No more than 32 bits of this
+	 * converted value can be accessed because all bit operations are
+	 * additionally provided with cbm_len that is initialized during
+	 * hardware enumeration using five bits from the EAX register and
+	 * thus never can exceed 32 bits.
+	 */
+	unsigned long *val = (unsigned long *)_val;
+	unsigned int cbm_len = r->cache.cbm_len;
+	unsigned long first_bit, zero_bit;
+
+	if (*val == 0)
+		return;
+
+	first_bit = find_first_bit(val, cbm_len);
+	zero_bit = find_next_zero_bit(val, cbm_len, first_bit);
+
+	/* Clear any remaining bits to ensure contiguous region */
+	bitmap_clear(val, zero_bit, cbm_len - zero_bit);
+}
+
+/**
+ * rdtgroup_init_alloc - Initialize the new RDT group's allocations
+ *
+ * A new RDT group is being created on an allocation capable (CAT)
+ * supporting system. Set this group up to start off with all usable
+ * allocations. That is, all shareable and unused bits.
+ *
+ * All-zero CBM is invalid. If there are no more shareable bits available
+ * on any domain then the entire allocation will fail.
+ */
+static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
+{
+	u32 used_b = 0, unused_b = 0;
+	u32 closid = rdtgrp->closid;
+	struct rdt_resource *r;
+	enum rdtgrp_mode mode;
+	struct rdt_domain *d;
+	int i, ret;
+	u32 *ctrl;
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d, &r->domains, list) {
+			d->have_new_ctrl = false;
+			d->new_ctrl = r->cache.shareable_bits;
+			used_b = r->cache.shareable_bits;
+			ctrl = d->ctrl_val;
+			for (i = 0; i < r->num_closid; i++, ctrl++) {
+				if (closid_allocated(i) && i != closid) {
+					mode = rdtgroup_mode_by_closid(i);
+					used_b |= *ctrl;
+					if (mode == RDT_MODE_SHAREABLE)
+						d->new_ctrl |= *ctrl;
+				}
+			}
+			unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
+			unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
+			d->new_ctrl |= unused_b;
+			/*
+			 * Force the initial CBM to be valid, user can
+			 * modify the CBM based on system availability.
+			 */
+			cbm_ensure_valid(&d->new_ctrl, r);
+			if (bitmap_weight((unsigned long *) &d->new_ctrl,
+					  r->cache.cbm_len) <
+					r->cache.min_cbm_bits) {
+				rdt_last_cmd_printf("no space on %s:%d\n",
+						    r->name, d->id);
+				return -ENOSPC;
+			}
+			d->have_new_ctrl = true;
+		}
+	}
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		ret = update_domains(r, rdtgrp->closid);
+		if (ret < 0) {
+			rdt_last_cmd_puts("failed to initialize allocations\n");
+			return ret;
+		}
+		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	}
+
+	return 0;
+}
+
 static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 			     struct kernfs_node *prgrp_kn,
 			     const char *name, umode_t mode,
@@ -1965,6 +2069,10 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 	ret = 0;
 
 	rdtgrp->closid = closid;
+	ret = rdtgroup_init_alloc(rdtgrp);
+	if (ret < 0)
+		goto out_id_free;
+
 	list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
 
 	if (rdt_mon_capable) {
@@ -1975,15 +2083,16 @@ static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
 		ret = mongroup_create_dir(kn, NULL, "mon_groups", NULL);
 		if (ret) {
 			rdt_last_cmd_puts("kernfs subdir error\n");
-			goto out_id_free;
+			goto out_del_list;
 		}
 	}
 
 	goto out_unlock;
 
+out_del_list:
+	list_del(&rdtgrp->rdtgroup_list);
 out_id_free:
 	closid_free(closid);
-	list_del(&rdtgrp->rdtgroup_list);
 out_common_fail:
 	mkdir_rdt_prepare_clean(rdtgrp);
 out_unlock:
-- 
cgit v1.2.3


From 414dd2b4732949ddc972c2592a13c799434249c6 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:00 -0700
Subject: x86/intel_rdt: Introduce new "exclusive" mode

At the moment all allocations are shareable. There is no way for a user to
designate that an allocation associated with a resource group cannot be
shared by another.

Introduce the new mode "exclusive". When a resource group is marked as such
it implies that no overlap is allowed between its allocation and that of
another resource group.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/f6d24672a4280fe3b24cd2da9b5f50214439c1af.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          | 2 ++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 1 +
 2 files changed, 3 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index f2fbf4059b3f..c9033fd774d5 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -83,6 +83,7 @@ enum rdt_group_type {
 /**
  * enum rdtgrp_mode - Mode of a RDT resource group
  * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
+ * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
  *
  * The mode of a resource group enables control over the allowed overlap
  * between allocations associated with different resource groups (classes
@@ -91,6 +92,7 @@ enum rdt_group_type {
  */
 enum rdtgrp_mode {
 	RDT_MODE_SHAREABLE = 0,
+	RDT_MODE_EXCLUSIVE,
 
 	/* Must be last */
 	RDT_NUM_MODES,
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 80ac09cf978b..910febef55e8 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -161,6 +161,7 @@ enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
 
 static const char * const rdt_mode_str[] = {
 	[RDT_MODE_SHAREABLE]	= "shareable",
+	[RDT_MODE_EXCLUSIVE]	= "exclusive",
 };
 
 /**
-- 
cgit v1.2.3


From 49f7b4efa1101bbc143a960eff3a9c8f9d6f7358 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:01 -0700
Subject: x86/intel_rdt: Enable setting of exclusive mode

The new "mode" file now accepts "exclusive" that means that the
allocations of this resource group cannot be shared.

Enable users to modify a resource group's mode to "exclusive". To
succeed it is required that there is no overlap between resource group's
current schemata and that of all the other active resource groups as
well as cache regions potentially used by other hardware entities.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/83642cbba3c8c21db7fa6bb36fe7d385d3b275f2.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 97 +++++++++++++++++++++++++++++++-
 1 file changed, 96 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 910febef55e8..ba1410ced420 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -812,6 +812,93 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+/**
+ * rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
+ * @r: Resource to which domain instance @d belongs.
+ * @d: The domain instance for which @closid is being tested.
+ * @cbm: Capacity bitmask being tested.
+ * @closid: Intended closid for @cbm.
+ * @exclusive: Only check if overlaps with exclusive resource groups
+ *
+ * Checks if provided @cbm intended to be used for @closid on domain
+ * @d overlaps with any other closids or other hardware usage associated
+ * with this domain. If @exclusive is true then only overlaps with
+ * resource groups in exclusive mode will be considered. If @exclusive
+ * is false then overlaps with any resource group or hardware entities
+ * will be considered.
+ *
+ * Return: false if CBM does not overlap, true if it does.
+ */
+static bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+				  u32 _cbm, int closid, bool exclusive)
+{
+	unsigned long *cbm = (unsigned long *)&_cbm;
+	unsigned long *ctrl_b;
+	enum rdtgrp_mode mode;
+	u32 *ctrl;
+	int i;
+
+	/* Check for any overlap with regions used by hardware directly */
+	if (!exclusive) {
+		if (bitmap_intersects(cbm,
+				      (unsigned long *)&r->cache.shareable_bits,
+				      r->cache.cbm_len))
+			return true;
+	}
+
+	/* Check for overlap with other resource groups */
+	ctrl = d->ctrl_val;
+	for (i = 0; i < r->num_closid; i++, ctrl++) {
+		ctrl_b = (unsigned long *)ctrl;
+		if (closid_allocated(i) && i != closid) {
+			if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
+				mode = rdtgroup_mode_by_closid(i);
+				if (exclusive) {
+					if (mode == RDT_MODE_EXCLUSIVE)
+						return true;
+					continue;
+				}
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
+/**
+ * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
+ *
+ * An exclusive resource group implies that there should be no sharing of
+ * its allocated resources. At the time this group is considered to be
+ * exclusive this test can determine if its current schemata supports this
+ * setting by testing for overlap with all other resource groups.
+ *
+ * Return: true if resource group can be exclusive, false if there is overlap
+ * with allocations of other resource groups and thus this resource group
+ * cannot be exclusive.
+ */
+static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
+{
+	int closid = rdtgrp->closid;
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d, &r->domains, list) {
+			if (rdtgroup_cbm_overlaps(r, d, d->ctrl_val[closid],
+						  rdtgrp->closid, false))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+/**
+ * rdtgroup_mode_write - Modify the resource group's mode
+ *
+ */
 static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 				   char *buf, size_t nbytes, loff_t off)
 {
@@ -834,11 +921,19 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 
 	mode = rdtgrp->mode;
 
-	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE))
+	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
+	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE))
 		goto out;
 
 	if (!strcmp(buf, "shareable")) {
 		rdtgrp->mode = RDT_MODE_SHAREABLE;
+	} else if (!strcmp(buf, "exclusive")) {
+		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
+			rdt_last_cmd_printf("schemata overlaps\n");
+			ret = -EINVAL;
+			goto out;
+		}
+		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
 	} else {
 		rdt_last_cmd_printf("unknown/unsupported mode\n");
 		ret = -EINVAL;
-- 
cgit v1.2.3


From 9af4c0a6dc1a1abf5336f2c3f951444db6b71da9 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:02 -0700
Subject: x86/intel_rdt: Making CBM name and type more explicit

cbm_validate() receives a pointer to the variable that will be initialized
with a validated capacity bitmask. The pointer points to a variable of type
unsigned long that is immediately assigned to a variable of type u32 by the
caller on return from cbm_validate().

Let cbm_validate() initialize a variable of type u32 directly.

At this time also change tha variable name "data" within parse_cbm() to a
name more reflective of the content: "cbm_val". This frees up the generic
"data" to be used later when it is indeed used for a collection of input.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/5e29cf0209ea2deac9beacd35cbe5239a50959fb.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 2c23bb136ccc..b3da5b981dd8 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -87,7 +87,7 @@ int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
  *	are allowed (e.g. FFFFH, 0FF0H, 003CH, etc.).
  * Additionally Haswell requires at least two bits set.
  */
-static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
+static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 {
 	unsigned long first_bit, zero_bit, val;
 	unsigned int cbm_len = r->cache.cbm_len;
@@ -128,16 +128,17 @@ static bool cbm_validate(char *buf, unsigned long *data, struct rdt_resource *r)
  */
 int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
 {
-	unsigned long data;
+	u32 cbm_val;
 
 	if (d->have_new_ctrl) {
 		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
 		return -EINVAL;
 	}
 
-	if(!cbm_validate(buf, &data, r))
+	if (!cbm_validate(buf, &cbm_val, r))
 		return -EINVAL;
-	d->new_ctrl = data;
+
+	d->new_ctrl = cbm_val;
 	d->have_new_ctrl = true;
 
 	return 0;
-- 
cgit v1.2.3


From 7604df6e16ae0b4dba6553ae74abcf7280a512fb Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:03 -0700
Subject: x86/intel_rdt: Support flexible data to parsing callbacks

Each resource is associated with a configurable callback that should be
used to parse the information provided for the particular resource from
user space. In addition to the resource and domain pointers this callback
is provided with just the character buffer being parsed.

In support of flexible parsing the callback is modified to support a void
pointer as argument. This enables resources that need more data than just
the user provided data to pass its required data to the callback without
affecting the signatures for the callbacks of all the other resources.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/34baacfced4d787d994ec7015e249e6c7e619053.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             | 6 +++---
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 6 ++++--
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index c9033fd774d5..b2b2864150aa 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -371,7 +371,7 @@ struct rdt_resource {
 	struct rdt_cache	cache;
 	struct rdt_membw	membw;
 	const char		*format_str;
-	int (*parse_ctrlval)	(char *buf, struct rdt_resource *r,
+	int (*parse_ctrlval)	(void *data, struct rdt_resource *r,
 				 struct rdt_domain *d);
 	struct list_head	evt_list;
 	int			num_rmid;
@@ -379,8 +379,8 @@ struct rdt_resource {
 	unsigned long		fflags;
 };
 
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d);
-int parse_bw(char *buf, struct rdt_resource *r,  struct rdt_domain *d);
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d);
+int parse_bw(void *_buf, struct rdt_resource *r,  struct rdt_domain *d);
 
 extern struct mutex rdtgroup_mutex;
 
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index b3da5b981dd8..ab4bb8731825 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -64,9 +64,10 @@ static bool bw_validate(char *buf, unsigned long *data, struct rdt_resource *r)
 	return true;
 }
 
-int parse_bw(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_bw(void *_buf, struct rdt_resource *r, struct rdt_domain *d)
 {
 	unsigned long data;
+	char *buf = _buf;
 
 	if (d->have_new_ctrl) {
 		rdt_last_cmd_printf("duplicate domain %d\n", d->id);
@@ -126,8 +127,9 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
-int parse_cbm(char *buf, struct rdt_resource *r, struct rdt_domain *d)
+int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 {
+	char *buf = _data;
 	u32 cbm_val;
 
 	if (d->have_new_ctrl) {
-- 
cgit v1.2.3


From 9ab9aa15c3096000678891b61f7309c8729928e0 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:04 -0700
Subject: x86/intel_rdt: Ensure requested schemata respects mode

When the administrator requests a change in a resource group's schemata
we have to ensure that the new schemata respects the current resource
group as well as the other active resource groups' schemata.

The new schemata is not allowed to overlap with the schemata of any
exclusive resource groups. Similarly, if the resource group being
changed is exclusive then its new schemata is not allowed to overlap
with any schemata of any other active resource group.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/b0c05b21110d3040fff45f4c1d2cfda8dba3f207.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             |  2 ++
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 49 ++++++++++++++++++++++-------
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    |  4 +--
 3 files changed, 41 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index b2b2864150aa..362c8fe695f3 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -465,6 +465,8 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 _cbm, int closid, bool exclusive);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int update_domains(struct rdt_resource *r, int closid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index ab4bb8731825..0e6210a043f0 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -123,13 +123,19 @@ static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
 	return true;
 }
 
+struct rdt_cbm_parse_data {
+	struct rdtgroup		*rdtgrp;
+	char			*buf;
+};
+
 /*
  * Read one cache bit mask (hex). Check that it is valid for the current
  * resource type.
  */
 int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 {
-	char *buf = _data;
+	struct rdt_cbm_parse_data *data = _data;
+	struct rdtgroup *rdtgrp = data->rdtgrp;
 	u32 cbm_val;
 
 	if (d->have_new_ctrl) {
@@ -137,8 +143,24 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 		return -EINVAL;
 	}
 
-	if (!cbm_validate(buf, &cbm_val, r))
+	if (!cbm_validate(data->buf, &cbm_val, r))
+		return -EINVAL;
+
+	/*
+	 * The CBM may not overlap with the CBM of another closid if
+	 * either is exclusive.
+	 */
+	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, true)) {
+		rdt_last_cmd_printf("overlaps with exclusive group\n");
 		return -EINVAL;
+	}
+
+	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
+		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE) {
+			rdt_last_cmd_printf("overlaps with other group\n");
+			return -EINVAL;
+		}
+	}
 
 	d->new_ctrl = cbm_val;
 	d->have_new_ctrl = true;
@@ -152,8 +174,10 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
  * separated by ";". The "id" is in decimal, and must match one of
  * the "id"s for this resource.
  */
-static int parse_line(char *line, struct rdt_resource *r)
+static int parse_line(char *line, struct rdt_resource *r,
+		      struct rdtgroup *rdtgrp)
 {
+	struct rdt_cbm_parse_data data;
 	char *dom = NULL, *id;
 	struct rdt_domain *d;
 	unsigned long dom_id;
@@ -170,7 +194,9 @@ next:
 	dom = strim(dom);
 	list_for_each_entry(d, &r->domains, list) {
 		if (d->id == dom_id) {
-			if (r->parse_ctrlval(dom, r, d))
+			data.buf = dom;
+			data.rdtgrp = rdtgrp;
+			if (r->parse_ctrlval(&data, r, d))
 				return -EINVAL;
 			goto next;
 		}
@@ -223,13 +249,14 @@ done:
 	return 0;
 }
 
-static int rdtgroup_parse_resource(char *resname, char *tok, int closid)
+static int rdtgroup_parse_resource(char *resname, char *tok,
+				   struct rdtgroup *rdtgrp)
 {
 	struct rdt_resource *r;
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		if (!strcmp(resname, r->name) && closid < r->num_closid)
-			return parse_line(tok, r);
+		if (!strcmp(resname, r->name) && rdtgrp->closid < r->num_closid)
+			return parse_line(tok, r, rdtgrp);
 	}
 	rdt_last_cmd_printf("unknown/unsupported resource name '%s'\n", resname);
 	return -EINVAL;
@@ -242,7 +269,7 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	struct rdt_domain *dom;
 	struct rdt_resource *r;
 	char *tok, *resname;
-	int closid, ret = 0;
+	int ret = 0;
 
 	/* Valid input requires a trailing newline */
 	if (nbytes == 0 || buf[nbytes - 1] != '\n')
@@ -256,8 +283,6 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 	rdt_last_cmd_clear();
 
-	closid = rdtgrp->closid;
-
 	for_each_alloc_enabled_rdt_resource(r) {
 		list_for_each_entry(dom, &r->domains, list)
 			dom->have_new_ctrl = false;
@@ -275,13 +300,13 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 			ret = -EINVAL;
 			goto out;
 		}
-		ret = rdtgroup_parse_resource(resname, tok, closid);
+		ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
 		if (ret)
 			goto out;
 	}
 
 	for_each_alloc_enabled_rdt_resource(r) {
-		ret = update_domains(r, closid);
+		ret = update_domains(r, rdtgrp->closid);
 		if (ret)
 			goto out;
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index ba1410ced420..75a43f8b400e 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -829,8 +829,8 @@ static int rdtgroup_mode_show(struct kernfs_open_file *of,
  *
  * Return: false if CBM does not overlap, true if it does.
  */
-static bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
-				  u32 _cbm, int closid, bool exclusive)
+bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
+			   u32 _cbm, int closid, bool exclusive)
 {
 	unsigned long *cbm = (unsigned long *)&_cbm;
 	unsigned long *ctrl_b;
-- 
cgit v1.2.3


From e651901187ab8bc8a0a969144da6ae0e2e59a148 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:05 -0700
Subject: x86/intel_rdt: Introduce "bit_usage" to display cache allocations
 details

With cache regions now explicitly marked as "shareable" or "exclusive"
we would like to communicate to the user how portions of the cache
are used.

Introduce "bit_usage" that indicates for each resource
how portions of the cache are configured to be used.

To assist the user to distinguish whether the sharing is from software or
hardware we add the following annotation:

0 - currently unused
X - currently available for sharing and used by software and hardware
H - currently used by hardware only but available for software use
S - currently used and shareable by software only
E - currently used exclusively by one resource group

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/105d44c40e582c2b7e2dccf0ae247e5e61137d4b.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 79 ++++++++++++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 75a43f8b400e..e0ec41a6540e 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -714,6 +714,78 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
 	return 0;
 }
 
+/**
+ * rdt_bit_usage_show - Display current usage of resources
+ *
+ * A domain is a shared resource that can now be allocated differently. Here
+ * we display the current regions of the domain as an annotated bitmask.
+ * For each domain of this resource its allocation bitmask
+ * is annotated as below to indicate the current usage of the corresponding bit:
+ *   0 - currently unused
+ *   X - currently available for sharing and used by software and hardware
+ *   H - currently used by hardware only but available for software use
+ *   S - currently used and shareable by software only
+ *   E - currently used exclusively by one resource group
+ */
+static int rdt_bit_usage_show(struct kernfs_open_file *of,
+			      struct seq_file *seq, void *v)
+{
+	struct rdt_resource *r = of->kn->parent->priv;
+	u32 sw_shareable, hw_shareable, exclusive;
+	struct rdt_domain *dom;
+	int i, hwb, swb, excl;
+	enum rdtgrp_mode mode;
+	bool sep = false;
+	u32 *ctrl;
+
+	mutex_lock(&rdtgroup_mutex);
+	hw_shareable = r->cache.shareable_bits;
+	list_for_each_entry(dom, &r->domains, list) {
+		if (sep)
+			seq_putc(seq, ';');
+		ctrl = dom->ctrl_val;
+		sw_shareable = 0;
+		exclusive = 0;
+		seq_printf(seq, "%d=", dom->id);
+		for (i = 0; i < r->num_closid; i++, ctrl++) {
+			if (!closid_allocated(i))
+				continue;
+			mode = rdtgroup_mode_by_closid(i);
+			switch (mode) {
+			case RDT_MODE_SHAREABLE:
+				sw_shareable |= *ctrl;
+				break;
+			case RDT_MODE_EXCLUSIVE:
+				exclusive |= *ctrl;
+				break;
+			case RDT_NUM_MODES:
+				WARN(1,
+				     "invalid mode for closid %d\n", i);
+				break;
+			}
+		}
+		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
+			hwb = test_bit(i, (unsigned long *)&hw_shareable);
+			swb = test_bit(i, (unsigned long *)&sw_shareable);
+			excl = test_bit(i, (unsigned long *)&exclusive);
+			if (hwb && swb)
+				seq_putc(seq, 'X');
+			else if (hwb && !swb)
+				seq_putc(seq, 'H');
+			else if (!hwb && swb)
+				seq_putc(seq, 'S');
+			else if (excl)
+				seq_putc(seq, 'E');
+			else /* Unused bits remain */
+				seq_putc(seq, '0');
+		}
+		sep = true;
+	}
+	seq_putc(seq, '\n');
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
 static int rdt_min_bw_show(struct kernfs_open_file *of,
 			     struct seq_file *seq, void *v)
 {
@@ -995,6 +1067,13 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdt_shareable_bits_show,
 		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
 	},
+	{
+		.name		= "bit_usage",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdt_bit_usage_show,
+		.fflags		= RF_CTRL_INFO | RFTYPE_RES_CACHE,
+	},
 	{
 		.name		= "min_bandwidth",
 		.mode		= 0444,
-- 
cgit v1.2.3


From d9b48c86eb380bb272d0ad8f5338d8dc941f3b32 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:06 -0700
Subject: x86/intel_rdt: Display resource groups' allocations' size in bytes

The schemata file displays the allocations associated with each domain of
each resource. The syntax of this file reflects the capacity bitmask (CBM)
of the actual allocation. In order to determine the actual size of an
allocation the user needs to dig through three different files to query the
variables needed to compute it (the cache size, the CBM length, and the
schemata).

Introduce a new file "size" associated with each resource group that will
mirror the schemata file syntax and display the size in bytes of each
allocation.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/cc0058014c30adb88ca7d1a5abfadacbfb5edd0d.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          |  2 +
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 81 ++++++++++++++++++++++++++++++++
 2 files changed, 83 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 362c8fe695f3..ed20e91c28ed 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -467,6 +467,8 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
 bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
 			   u32 _cbm, int closid, bool exclusive);
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
+				  u32 cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int update_domains(struct rdt_resource *r, int closid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index e0ec41a6540e..cde0f4114d4e 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -20,6 +20,7 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
@@ -1016,6 +1017,78 @@ out:
 	return ret ?: nbytes;
 }
 
+/**
+ * rdtgroup_cbm_to_size - Translate CBM to size in bytes
+ * @r: RDT resource to which @d belongs.
+ * @d: RDT domain instance.
+ * @cbm: bitmask for which the size should be computed.
+ *
+ * The bitmask provided associated with the RDT domain instance @d will be
+ * translated into how many bytes it represents. The size in bytes is
+ * computed by first dividing the total cache size by the CBM length to
+ * determine how many bytes each bit in the bitmask represents. The result
+ * is multiplied with the number of bits set in the bitmask.
+ */
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
+				  struct rdt_domain *d, u32 cbm)
+{
+	struct cpu_cacheinfo *ci;
+	unsigned int size = 0;
+	int num_b, i;
+
+	num_b = bitmap_weight((unsigned long *)&cbm, r->cache.cbm_len);
+	ci = get_cpu_cacheinfo(cpumask_any(&d->cpu_mask));
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == r->cache_level) {
+			size = ci->info_list[i].size / r->cache.cbm_len * num_b;
+			break;
+		}
+	}
+
+	return size;
+}
+
+/**
+ * rdtgroup_size_show - Display size in bytes of allocated regions
+ *
+ * The "size" file mirrors the layout of the "schemata" file, printing the
+ * size in bytes of each region instead of the capacity bitmask.
+ *
+ */
+static int rdtgroup_size_show(struct kernfs_open_file *of,
+			      struct seq_file *s, void *v)
+{
+	struct rdtgroup *rdtgrp;
+	struct rdt_resource *r;
+	struct rdt_domain *d;
+	unsigned int size;
+	bool sep = false;
+	u32 cbm;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
+
+	for_each_alloc_enabled_rdt_resource(r) {
+		seq_printf(s, "%*s:", max_name_width, r->name);
+		list_for_each_entry(d, &r->domains, list) {
+			if (sep)
+				seq_putc(s, ';');
+			cbm = d->ctrl_val[rdtgrp->closid];
+			size = rdtgroup_cbm_to_size(r, d, cbm);
+			seq_printf(s, "%d=%u", d->id, size);
+			sep = true;
+		}
+		seq_putc(s, '\n');
+	}
+
+	rdtgroup_kn_unlock(of->kn);
+
+	return 0;
+}
+
 /* rdtgroup information files for one cache resource. */
 static struct rftype res_common_files[] = {
 	{
@@ -1144,6 +1217,14 @@ static struct rftype res_common_files[] = {
 		.seq_show	= rdtgroup_mode_show,
 		.fflags		= RF_CTRL_BASE,
 	},
+	{
+		.name		= "size",
+		.mode		= 0444,
+		.kf_ops		= &rdtgroup_kf_single_ops,
+		.seq_show	= rdtgroup_size_show,
+		.fflags		= RF_CTRL_BASE,
+	},
+
 };
 
 static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
-- 
cgit v1.2.3


From e17e733070d4ab312a35848ab248e85b78dcb3f4 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:07 -0700
Subject: x86/intel_rdt: Documentation for Cache Pseudo-Locking

Add description of Cache Pseudo-Locking feature, its interface, as well as
an example of its usage.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/6e118c15d2c254a27b8891783505cd1bb94a2b10.1529706536.git.reinette.chatre@intel.com
---
 Documentation/x86/intel_rdt_ui.txt | 280 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 278 insertions(+), 2 deletions(-)

diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index de913e00e922..bcd0a6d2fcf8 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -29,7 +29,11 @@ mount options are:
 L2 and L3 CDP are controlled seperately.
 
 RDT features are orthogonal. A particular system may support only
-monitoring, only control, or both monitoring and control.
+monitoring, only control, or both monitoring and control.  Cache
+pseudo-locking is a unique way of using cache control to "pin" or
+"lock" data in the cache. Details can be found in
+"Cache Pseudo-Locking".
+
 
 The mount succeeds if either of allocation or monitoring is present, but
 only those files and directories supported by the system will be created.
@@ -86,6 +90,8 @@ related to allocation:
 			      and available for sharing.
 			"E" - Corresponding region is used exclusively by
 			      one resource group. No sharing allowed.
+			"P" - Corresponding region is pseudo-locked. No
+			      sharing allowed.
 
 Memory bandwitdh(MB) subdirectory contains the following files
 with respect to allocation:
@@ -192,7 +198,12 @@ When control is enabled all CTRL_MON groups will also contain:
 "mode":
 	The "mode" of the resource group dictates the sharing of its
 	allocations. A "shareable" resource group allows sharing of its
-	allocations while an "exclusive" resource group does not.
+	allocations while an "exclusive" resource group does not. A
+	cache pseudo-locked region is created by first writing
+	"pseudo-locksetup" to the "mode" file before writing the cache
+	pseudo-locked region's schemata to the resource group's "schemata"
+	file. On successful pseudo-locked region creation the mode will
+	automatically change to "pseudo-locked".
 
 When monitoring is enabled all MON groups will also contain:
 
@@ -410,6 +421,170 @@ L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
 L3DATA:0=fffff;1=fffff;2=3c0;3=fffff
 L3CODE:0=fffff;1=fffff;2=fffff;3=fffff
 
+Cache Pseudo-Locking
+--------------------
+CAT enables a user to specify the amount of cache space that an
+application can fill. Cache pseudo-locking builds on the fact that a
+CPU can still read and write data pre-allocated outside its current
+allocated area on a cache hit. With cache pseudo-locking, data can be
+preloaded into a reserved portion of cache that no application can
+fill, and from that point on will only serve cache hits. The cache
+pseudo-locked memory is made accessible to user space where an
+application can map it into its virtual address space and thus have
+a region of memory with reduced average read latency.
+
+The creation of a cache pseudo-locked region is triggered by a request
+from the user to do so that is accompanied by a schemata of the region
+to be pseudo-locked. The cache pseudo-locked region is created as follows:
+- Create a CAT allocation CLOSNEW with a CBM matching the schemata
+  from the user of the cache region that will contain the pseudo-locked
+  memory. This region must not overlap with any current CAT allocation/CLOS
+  on the system and no future overlap with this cache region is allowed
+  while the pseudo-locked region exists.
+- Create a contiguous region of memory of the same size as the cache
+  region.
+- Flush the cache, disable hardware prefetchers, disable preemption.
+- Make CLOSNEW the active CLOS and touch the allocated memory to load
+  it into the cache.
+- Set the previous CLOS as active.
+- At this point the closid CLOSNEW can be released - the cache
+  pseudo-locked region is protected as long as its CBM does not appear in
+  any CAT allocation. Even though the cache pseudo-locked region will from
+  this point on not appear in any CBM of any CLOS an application running with
+  any CLOS will be able to access the memory in the pseudo-locked region since
+  the region continues to serve cache hits.
+- The contiguous region of memory loaded into the cache is exposed to
+  user-space as a character device.
+
+Cache pseudo-locking increases the probability that data will remain
+in the cache via carefully configuring the CAT feature and controlling
+application behavior. There is no guarantee that data is placed in
+cache. Instructions like INVD, WBINVD, CLFLUSH, etc. can still evict
+“locked” data from cache. Power management C-states may shrink or
+power off cache. It is thus recommended to limit the processor maximum
+C-state, for example, by setting the processor.max_cstate kernel parameter.
+
+It is required that an application using a pseudo-locked region runs
+with affinity to the cores (or a subset of the cores) associated
+with the cache on which the pseudo-locked region resides. A sanity check
+within the code will not allow an application to map pseudo-locked memory
+unless it runs with affinity to cores associated with the cache on which the
+pseudo-locked region resides. The sanity check is only done during the
+initial mmap() handling, there is no enforcement afterwards and the
+application self needs to ensure it remains affine to the correct cores.
+
+Pseudo-locking is accomplished in two stages:
+1) During the first stage the system administrator allocates a portion
+   of cache that should be dedicated to pseudo-locking. At this time an
+   equivalent portion of memory is allocated, loaded into allocated
+   cache portion, and exposed as a character device.
+2) During the second stage a user-space application maps (mmap()) the
+   pseudo-locked memory into its address space.
+
+Cache Pseudo-Locking Interface
+------------------------------
+A pseudo-locked region is created using the resctrl interface as follows:
+
+1) Create a new resource group by creating a new directory in /sys/fs/resctrl.
+2) Change the new resource group's mode to "pseudo-locksetup" by writing
+   "pseudo-locksetup" to the "mode" file.
+3) Write the schemata of the pseudo-locked region to the "schemata" file. All
+   bits within the schemata should be "unused" according to the "bit_usage"
+   file.
+
+On successful pseudo-locked region creation the "mode" file will contain
+"pseudo-locked" and a new character device with the same name as the resource
+group will exist in /dev/pseudo_lock. This character device can be mmap()'ed
+by user space in order to obtain access to the pseudo-locked memory region.
+
+An example of cache pseudo-locked region creation and usage can be found below.
+
+Cache Pseudo-Locking Debugging Interface
+---------------------------------------
+The pseudo-locking debugging interface is enabled by default (if
+CONFIG_DEBUG_FS is enabled) and can be found in /sys/kernel/debug/resctrl.
+
+There is no explicit way for the kernel to test if a provided memory
+location is present in the cache. The pseudo-locking debugging interface uses
+the tracing infrastructure to provide two ways to measure cache residency of
+the pseudo-locked region:
+1) Memory access latency using the pseudo_lock_mem_latency tracepoint. Data
+   from these measurements are best visualized using a hist trigger (see
+   example below). In this test the pseudo-locked region is traversed at
+   a stride of 32 bytes while hardware prefetchers and preemption
+   are disabled. This also provides a substitute visualization of cache
+   hits and misses.
+2) Cache hit and miss measurements using model specific precision counters if
+   available. Depending on the levels of cache on the system the pseudo_lock_l2
+   and pseudo_lock_l3 tracepoints are available.
+   WARNING: triggering this  measurement uses from two (for just L2
+   measurements) to four (for L2 and L3 measurements) precision counters on
+   the system, if any other measurements are in progress the counters and
+   their corresponding event registers will be clobbered.
+
+When a pseudo-locked region is created a new debugfs directory is created for
+it in debugfs as /sys/kernel/debug/resctrl/<newdir>. A single
+write-only file, pseudo_lock_measure, is present in this directory. The
+measurement on the pseudo-locked region depends on the number, 1 or 2,
+written to this debugfs file. Since the measurements are recorded with the
+tracing infrastructure the relevant tracepoints need to be enabled before the
+measurement is triggered.
+
+Example of latency debugging interface:
+In this example a pseudo-locked region named "newlock" was created. Here is
+how we can measure the latency in cycles of reading from this region and
+visualize this data with a histogram that is available if CONFIG_HIST_TRIGGERS
+is set:
+# :> /sys/kernel/debug/tracing/trace
+# echo 'hist:keys=latency' > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/trigger
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# echo 1 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
+# cat /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/hist
+
+# event histogram
+#
+# trigger info: hist:keys=latency:vals=hitcount:sort=hitcount:size=2048 [active]
+#
+
+{ latency:        456 } hitcount:          1
+{ latency:         50 } hitcount:         83
+{ latency:         36 } hitcount:         96
+{ latency:         44 } hitcount:        174
+{ latency:         48 } hitcount:        195
+{ latency:         46 } hitcount:        262
+{ latency:         42 } hitcount:        693
+{ latency:         40 } hitcount:       3204
+{ latency:         38 } hitcount:       3484
+
+Totals:
+    Hits: 8192
+    Entries: 9
+   Dropped: 0
+
+Example of cache hits/misses debugging:
+In this example a pseudo-locked region named "newlock" was created on the L2
+cache of a platform. Here is how we can obtain details of the cache hits
+and misses using the platform's precision counters.
+
+# :> /sys/kernel/debug/tracing/trace
+# echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# echo 2 > /sys/kernel/debug/resctrl/newlock/pseudo_lock_measure
+# echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_l2/enable
+# cat /sys/kernel/debug/tracing/trace
+
+# tracer: nop
+#
+#                              _-----=> irqs-off
+#                             / _----=> need-resched
+#                            | / _---=> hardirq/softirq
+#                            || / _--=> preempt-depth
+#                            ||| /     delay
+#           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+#              | |       |   ||||       |         |
+ pseudo_lock_mea-1672  [002] ....  3132.860500: pseudo_lock_l2: hits=4097 miss=0
+
+
 Examples for RDT allocation usage:
 
 Example 1
@@ -596,6 +771,107 @@ A resource group cannot be forced to overlap with an exclusive resource group:
 # cat info/last_cmd_status
 overlaps with exclusive group
 
+Example of Cache Pseudo-Locking
+-------------------------------
+Lock portion of L2 cache from cache id 1 using CBM 0x3. Pseudo-locked
+region is exposed at /dev/pseudo_lock/newlock that can be provided to
+application for argument to mmap().
+
+# mount -t resctrl resctrl /sys/fs/resctrl/
+# cd /sys/fs/resctrl
+
+Ensure that there are bits available that can be pseudo-locked, since only
+unused bits can be pseudo-locked the bits to be pseudo-locked needs to be
+removed from the default resource group's schemata:
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSSS
+# echo 'L2:1=0xfc' > schemata
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSS00
+
+Create a new resource group that will be associated with the pseudo-locked
+region, indicate that it will be used for a pseudo-locked region, and
+configure the requested pseudo-locked region capacity bitmask:
+
+# mkdir newlock
+# echo pseudo-locksetup > newlock/mode
+# echo 'L2:1=0x3' > newlock/schemata
+
+On success the resource group's mode will change to pseudo-locked, the
+bit_usage will reflect the pseudo-locked region, and the character device
+exposing the pseudo-locked region will exist:
+
+# cat newlock/mode
+pseudo-locked
+# cat info/L2/bit_usage
+0=SSSSSSSS;1=SSSSSSPP
+# ls -l /dev/pseudo_lock/newlock
+crw------- 1 root root 243, 0 Apr  3 05:01 /dev/pseudo_lock/newlock
+
+/*
+ * Example code to access one page of pseudo-locked cache region
+ * from user space.
+ */
+#define _GNU_SOURCE
+#include <fcntl.h>
+#include <sched.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+#include <sys/mman.h>
+
+/*
+ * It is required that the application runs with affinity to only
+ * cores associated with the pseudo-locked region. Here the cpu
+ * is hardcoded for convenience of example.
+ */
+static int cpuid = 2;
+
+int main(int argc, char *argv[])
+{
+	cpu_set_t cpuset;
+	long page_size;
+	void *mapping;
+	int dev_fd;
+	int ret;
+
+	page_size = sysconf(_SC_PAGESIZE);
+
+	CPU_ZERO(&cpuset);
+	CPU_SET(cpuid, &cpuset);
+	ret = sched_setaffinity(0, sizeof(cpuset), &cpuset);
+	if (ret < 0) {
+		perror("sched_setaffinity");
+		exit(EXIT_FAILURE);
+	}
+
+	dev_fd = open("/dev/pseudo_lock/newlock", O_RDWR);
+	if (dev_fd < 0) {
+		perror("open");
+		exit(EXIT_FAILURE);
+	}
+
+	mapping = mmap(0, page_size, PROT_READ | PROT_WRITE, MAP_SHARED,
+		       dev_fd, 0);
+	if (mapping == MAP_FAILED) {
+		perror("mmap");
+		close(dev_fd);
+		exit(EXIT_FAILURE);
+	}
+
+	/* Application interacts with pseudo-locked memory @mapping */
+
+	ret = munmap(mapping, page_size);
+	if (ret < 0) {
+		perror("munmap");
+		close(dev_fd);
+		exit(EXIT_FAILURE);
+	}
+
+	close(dev_fd);
+	exit(EXIT_SUCCESS);
+}
+
 Locking between applications
 ----------------------------
 
-- 
cgit v1.2.3


From bb9fec69cb41380428d6b8dab3a303189a9b480a Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:08 -0700
Subject: x86/intel_rdt: Introduce the Cache Pseudo-Locking modes

The two modes used to manage Cache Pseudo-Locked regions are introduced.  A
resource group is assigned "pseudo-locksetup" mode when the user indicates
that this resource group will be used for a Cache Pseudo-Locked
region. When the Cache Pseudo-Locked region has been set up successfully
after the user wrote the requested schemata to the "schemata" file, then
the mode will automatically changed to "pseudo-locked".  The user is not
able to modify the mode to "pseudo-locked" by writing "pseudo-locked" to
the "mode" file directly.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/98d6ca129bbe7dd0932d1fcfeb3cbb65f29a8d9d.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          | 10 ++++++++++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 13 +++++++++++--
 2 files changed, 21 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index ed20e91c28ed..7b872f2cc294 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -84,15 +84,25 @@ enum rdt_group_type {
  * enum rdtgrp_mode - Mode of a RDT resource group
  * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
  * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
+ * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
+ * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
+ *                          allowed AND the allocations are Cache Pseudo-Locked
  *
  * The mode of a resource group enables control over the allowed overlap
  * between allocations associated with different resource groups (classes
  * of service). User is able to modify the mode of a resource group by
  * writing to the "mode" resctrl file associated with the resource group.
+ *
+ * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
+ * writing the appropriate text to the "mode" file. A resource group enters
+ * "pseudo-locked" mode after the schemata is written while the resource
+ * group is in "pseudo-locksetup" mode.
  */
 enum rdtgrp_mode {
 	RDT_MODE_SHAREABLE = 0,
 	RDT_MODE_EXCLUSIVE,
+	RDT_MODE_PSEUDO_LOCKSETUP,
+	RDT_MODE_PSEUDO_LOCKED,
 
 	/* Must be last */
 	RDT_NUM_MODES,
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index cde0f4114d4e..fef92b939f0f 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -161,8 +161,10 @@ enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
 }
 
 static const char * const rdt_mode_str[] = {
-	[RDT_MODE_SHAREABLE]	= "shareable",
-	[RDT_MODE_EXCLUSIVE]	= "exclusive",
+	[RDT_MODE_SHAREABLE]		= "shareable",
+	[RDT_MODE_EXCLUSIVE]		= "exclusive",
+	[RDT_MODE_PSEUDO_LOCKSETUP]	= "pseudo-locksetup",
+	[RDT_MODE_PSEUDO_LOCKED]	= "pseudo-locked",
 };
 
 /**
@@ -759,6 +761,13 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			case RDT_MODE_EXCLUSIVE:
 				exclusive |= *ctrl;
 				break;
+			/*
+			 * Temporarily handle pseudo-locking enums
+			 * to silence compile warnings until handling
+			 * added in later patches.
+			 */
+			case RDT_MODE_PSEUDO_LOCKSETUP:
+			case RDT_MODE_PSEUDO_LOCKED:
 			case RDT_NUM_MODES:
 				WARN(1,
 				     "invalid mode for closid %d\n", i);
-- 
cgit v1.2.3


From 21220bb199f7d65c8f0a63ac7d3209e40fbdd706 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:09 -0700
Subject: x86/intel_rdt: Respect read and write access

By default, if the opener has CAP_DAC_OVERRIDE, a kernfs file can be opened
regardless of RW permissions. Writing to a kernfs file will thus succeed
even if permissions are 0000.

It's required to restrict the actions that can be performed on a resource
group from userspace based on the mode of the resource group.  This
restriction will be done through a modification of the file
permissions. That is, for example, if a resource group is locked then the
user cannot add tasks to the resource group.

For this restriction through file permissions to work it has to be ensured
that the permissions are always respected. To do so the resctrl filesystem
is created with the KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK flag that will result
in open(2) failing with -EACCESS regardless of CAP_DAC_OVERRIDE if the
permission does not have the respective read or write access.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/26f4fc25f110bfc07c2d2c8b2c4ee904922fedf7.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index fef92b939f0f..6eb716765a3f 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -2545,7 +2545,8 @@ static int __init rdtgroup_setup_root(void)
 	int ret;
 
 	rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
-				      KERNFS_ROOT_CREATE_DEACTIVATED,
+				      KERNFS_ROOT_CREATE_DEACTIVATED |
+				      KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
 				      &rdtgroup_default);
 	if (IS_ERR(rdt_root))
 		return PTR_ERR(rdt_root);
-- 
cgit v1.2.3


From f7a6e3f6f5ffa4926818ea2b3e8994ecef00b84f Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:10 -0700
Subject: x86/intel_rdt: Add utility to test if tasks assigned to resource
 group

In considering changes to a resource group it becomes necessary to know
whether tasks have been assigned to the resource group in question.

Introduce a new utility that can be used to check if any tasks have been
assigned to a particular resource group.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/be9ea3969ffd731dfd90c0ebcd5a0e0a2d135bb2.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          |  1 +
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 26 ++++++++++++++++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 7b872f2cc294..11c76c4b9a5e 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -480,6 +480,7 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
 unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
 				  u32 cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
+int rdtgroup_tasks_assigned(struct rdtgroup *r);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int update_domains(struct rdt_resource *r, int closid);
 void closid_free(int closid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 6eb716765a3f..59e1de9fe2d5 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -564,6 +564,32 @@ static int __rdtgroup_move_task(struct task_struct *tsk,
 	return ret;
 }
 
+/**
+ * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
+ * @r: Resource group
+ *
+ * Return: 1 if tasks have been assigned to @r, 0 otherwise
+ */
+int rdtgroup_tasks_assigned(struct rdtgroup *r)
+{
+	struct task_struct *p, *t;
+	int ret = 0;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	rcu_read_lock();
+	for_each_process_thread(p, t) {
+		if ((r->type == RDTCTRL_GROUP && t->closid == r->closid) ||
+		    (r->type == RDTMON_GROUP && t->rmid == r->mon.rmid)) {
+			ret = 1;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
 static int rdtgroup_task_write_permission(struct task_struct *task,
 					  struct kernfs_open_file *of)
 {
-- 
cgit v1.2.3


From 125db711e3629977b5e1f06fa066abe6366db294 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:11 -0700
Subject: x86/intel_rdt: Add utility to restrict/restore access to resctrl
 files

When a resource group is used for Cache Pseudo-Locking then the region of
cache ends up being orphaned with no class of service referring to it. The
resctrl files intended to manage how the classes of services are utilized
thus become irrelevant.

The fact that a resctrl file is not relevant can be communicated to the
user by setting all of its permissions to zero. That is, its read, write,
and execute permissions are unset for all users.

Introduce two utilities, rdtgroup_kn_mode_restrict() and
rdtgroup_kn_mode_restore(), that can be used to restrict and restore the
permissions of a file or directory belonging to a resource group.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/7afdbf5551b2f93cd45d61fbf5e01d87331f529a.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          |  2 +
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 95 ++++++++++++++++++++++++++++++++
 2 files changed, 97 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 11c76c4b9a5e..8d56776a3bd2 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -469,6 +469,8 @@ void rdt_last_cmd_printf(const char *fmt, ...);
 void rdt_ctrl_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name);
 struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 				   struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 59e1de9fe2d5..08a412e0b47a 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1290,6 +1290,101 @@ error:
 	return ret;
 }
 
+/**
+ * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ *
+ * The permissions of named resctrl file, directory, or link are modified
+ * to not allow read, write, or execute by any user.
+ *
+ * WARNING: This function is intended to communicate to the user that the
+ * resctrl file has been locked down - that it is not relevant to the
+ * particular state the system finds itself in. It should not be relied
+ * on to protect from user access because after the file's permissions
+ * are restricted the user can still change the permissions using chmod
+ * from the command line.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		iattr.ia_mode = S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode = S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode = S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
+/**
+ * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
+ * @r: The resource group with which the file is associated.
+ * @name: Name of the file
+ *
+ * Restore the permissions of the named file. If @name is a directory the
+ * permissions of its parent will be used.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name)
+{
+	struct iattr iattr = {.ia_valid = ATTR_MODE,};
+	struct kernfs_node *kn, *parent;
+	struct rftype *rfts, *rft;
+	int ret, len;
+
+	rfts = res_common_files;
+	len = ARRAY_SIZE(res_common_files);
+
+	for (rft = rfts; rft < rfts + len; rft++) {
+		if (!strcmp(rft->name, name))
+			iattr.ia_mode = rft->mode;
+	}
+
+	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
+	if (!kn)
+		return -ENOENT;
+
+	switch (kernfs_type(kn)) {
+	case KERNFS_DIR:
+		parent = kernfs_get_parent(kn);
+		if (parent) {
+			iattr.ia_mode |= parent->mode;
+			kernfs_put(parent);
+		}
+		iattr.ia_mode |= S_IFDIR;
+		break;
+	case KERNFS_FILE:
+		iattr.ia_mode |= S_IFREG;
+		break;
+	case KERNFS_LINK:
+		iattr.ia_mode |= S_IFLNK;
+		break;
+	}
+
+	ret = kernfs_setattr(kn, &iattr);
+	kernfs_put(kn);
+	return ret;
+}
+
 static int rdtgroup_mkdir_info_resdir(struct rdt_resource *r, char *name,
 				      unsigned long fflags)
 {
-- 
cgit v1.2.3


From c966dac8a5ede5d5f9b730512d8bdbcec307fe38 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:12 -0700
Subject: x86/intel_rdt: Protect against resource group changes during locking

We intend to modify file permissions to make the "tasks", "cpus", and
"cpus_list" not accessible to the user when cache pseudo-locking in
progress. Even so, it is still possible for the user to force the file
permissions (using chmod) to make them writeable. Similarly, directory
permissions will be modified to prevent future monitor group creation but
the user can override these restrictions also.

Add additional checks to the files we intend to restrict to ensure that no
modifications from user space are attempted while setting up a
pseudo-locking or after a pseudo-locked region is set up.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/0c5cb006e81ead0b8bfff2df530c5d3017fd31d1.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 10 +++++++++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 32 +++++++++++++++++++++++++----
 2 files changed, 38 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 0e6210a043f0..bc79396c5dad 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -283,6 +283,16 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 	}
 	rdt_last_cmd_clear();
 
+	/*
+	 * No changes to pseudo-locked region allowed. It has to be removed
+	 * and re-created instead.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("resource group is pseudo-locked\n");
+		goto out;
+	}
+
 	for_each_alloc_enabled_rdt_resource(r) {
 		list_for_each_entry(dom, &r->domains, list)
 			dom->have_new_ctrl = false;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 08a412e0b47a..013cbfedc753 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -449,6 +449,13 @@ static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 		goto unlock;
 	}
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto unlock;
+	}
+
 	if (is_cpu_list(of))
 		ret = cpulist_parse(buf, newmask);
 	else
@@ -651,13 +658,22 @@ static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
 	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
 		return -EINVAL;
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp) {
+		rdtgroup_kn_unlock(of->kn);
+		return -ENOENT;
+	}
 	rdt_last_cmd_clear();
 
-	if (rdtgrp)
-		ret = rdtgroup_move_task(pid, rdtgrp, of);
-	else
-		ret = -ENOENT;
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
+	    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto unlock;
+	}
+
+	ret = rdtgroup_move_task(pid, rdtgrp, of);
 
+unlock:
 	rdtgroup_kn_unlock(of->kn);
 
 	return ret ?: nbytes;
@@ -2315,6 +2331,14 @@ static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
 		goto out_unlock;
 	}
 
+	if (rtype == RDTMON_GROUP &&
+	    (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+	     prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
+		ret = -EINVAL;
+		rdt_last_cmd_puts("pseudo-locking in progress\n");
+		goto out_unlock;
+	}
+
 	/* allocate the rdtgroup. */
 	rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
 	if (!rdtgrp) {
-- 
cgit v1.2.3


From 2a5d76a4fc6469ea9dd6f02fcd4dad3a129bc1c0 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:13 -0700
Subject: x86/intel_rdt: Utilities to restrict/restore access to specific files

In support of Cache Pseudo-Locking we need to restrict access to specific
resctrl files to protect the state of a resource group used for
pseudo-locking from being changed in unsupported ways.

Introduce two utilities that can be used to either restrict or restore the
access to all files irrelevant to cache pseudo-locking when pseudo-locking
in progress for the resource group.

At this time introduce a new source file, intel_rdt_pseudo_lock.c, that
will contain most of the code related to cache pseudo-locking.

Temporarily mark these new functions as unused to silence compile warnings
until they are used.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/ab6319d1244366be3f9b7f9fba1c3da4810a274b.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/Makefile                |   3 +-
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 113 ++++++++++++++++++++++++++++
 2 files changed, 115 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 7a40196967cb..c4e02555563a 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -35,7 +35,8 @@ obj-$(CONFIG_CPU_SUP_CENTAUR)		+= centaur.o
 obj-$(CONFIG_CPU_SUP_TRANSMETA_32)	+= transmeta.o
 obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
-obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o intel_rdt_ctrlmondata.o
+obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o
+obj-$(CONFIG_INTEL_RDT)	+= intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
new file mode 100644
index 000000000000..dc79b3090ac5
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -0,0 +1,113 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Resource Director Technology (RDT)
+ *
+ * Pseudo-locking support built on top of Cache Allocation Technology (CAT)
+ *
+ * Copyright (C) 2018 Intel Corporation
+ *
+ * Author: Reinette Chatre <reinette.chatre@intel.com>
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include "intel_rdt.h"
+
+/**
+ * rdtgroup_locksetup_user_restrict - Restrict user access to group
+ * @rdtgrp: resource group needing access restricted
+ *
+ * A resource group used for cache pseudo-locking cannot have cpus or tasks
+ * assigned to it. This is communicated to the user by restricting access
+ * to all the files that can be used to make such changes.
+ *
+ * Permissions restored with rdtgroup_locksetup_user_restore()
+ *
+ * Return: 0 on success, <0 on failure. If a failure occurs during the
+ * restriction of access an attempt will be made to restore permissions but
+ * the state of the mode of these files will be uncertain when a failure
+ * occurs.
+ */
+static int __attribute__ ((unused))
+rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+	if (ret)
+		goto err_cpus;
+
+	if (rdt_mon_capable) {
+		ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list");
+err_cpus:
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus");
+err_tasks:
+	rdtgroup_kn_mode_restore(rdtgrp, "tasks");
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_user_restore - Restore user access to group
+ * @rdtgrp: resource group needing access restored
+ *
+ * Restore all file access previously removed using
+ * rdtgroup_locksetup_user_restrict()
+ *
+ * Return: 0 on success, <0 on failure.  If a failure occurs during the
+ * restoration of access an attempt will be made to restrict permissions
+ * again but the state of the mode of these files will be uncertain when
+ * a failure occurs.
+ */
+static int __attribute__ ((unused))
+rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks");
+	if (ret)
+		return ret;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus");
+	if (ret)
+		goto err_tasks;
+
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list");
+	if (ret)
+		goto err_cpus;
+
+	if (rdt_mon_capable) {
+		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups");
+		if (ret)
+			goto err_cpus_list;
+	}
+
+	ret = 0;
+	goto out;
+
+err_cpus_list:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
+err_cpus:
+	rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
+err_tasks:
+	rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
+out:
+	return ret;
+}
-- 
cgit v1.2.3


From bbcee99b67c5a8cc4e8037d561be9ed293961fd3 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:14 -0700
Subject: x86/intel_rdt: Add check to determine if monitoring in progress

When a resource group is pseudo-locked it is orphaned without a class of
service associated with it. We thus do not want any monitoring in progress
on a resource group that will be used for pseudo-locking.

Introduce a test that can be used to determine if pseudo-locking in
progress on a resource group. Temporarily mark it as unused to avoid
compile warnings until it is used.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/14fd9494f87ca72a213b3a197d1172d4e66ae196.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index dc79b3090ac5..8693dbe602a2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -13,6 +13,19 @@
 
 #include "intel_rdt.h"
 
+/**
+ * rdtgroup_monitor_in_progress - Test if monitoring in progress
+ * @r: resource group being queried
+ *
+ * Return: 1 if monitor groups have been created for this resource
+ * group, 0 otherwise.
+ */
+static int __attribute__ ((unused))
+rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
+{
+	return !list_empty(&rdtgrp->mon.crdtgrp_list);
+}
+
 /**
  * rdtgroup_locksetup_user_restrict - Restrict user access to group
  * @rdtgrp: resource group needing access restricted
-- 
cgit v1.2.3


From e8140a2d13d429364f18ca41b1e4960708c3a40e Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:15 -0700
Subject: x86/intel_rdt: Introduce pseudo-locked region

A pseudo-locked region is introduced representing an instance of a
pseudo-locked cache region. Each cache instance (domain) can support one
pseudo-locked region. Similarly a resource group can be used for one
pseudo-locked region.

Include a pointer to a pseudo-locked region from the domain and resource
group structures.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/9f69eb159051067703bcbc714de62e69874d5dee.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h | 64 ++++++++++++++++++++++++++---------------
 1 file changed, 41 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 8d56776a3bd2..f3dcbcd03dfa 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -122,6 +122,20 @@ struct mongroup {
 	u32			rmid;
 };
 
+/**
+ * struct pseudo_lock_region - pseudo-lock region information
+ * @r:			RDT resource to which this pseudo-locked region
+ *			belongs
+ * @d:			RDT domain to which this pseudo-locked region
+ *			belongs
+ * @cbm:		bitmask of the pseudo-locked region
+ */
+struct pseudo_lock_region {
+	struct rdt_resource	*r;
+	struct rdt_domain	*d;
+	u32			cbm;
+};
+
 /**
  * struct rdtgroup - store rdtgroup's data in resctrl file system.
  * @kn:				kernfs node
@@ -135,17 +149,19 @@ struct mongroup {
  *				monitor only or ctrl_mon group
  * @mon:			mongroup related data
  * @mode:			mode of resource group
+ * @plr:			pseudo-locked region
  */
 struct rdtgroup {
-	struct kernfs_node	*kn;
-	struct list_head	rdtgroup_list;
-	u32			closid;
-	struct cpumask		cpu_mask;
-	int			flags;
-	atomic_t		waitcount;
-	enum rdt_group_type	type;
-	struct mongroup		mon;
-	enum rdtgrp_mode	mode;
+	struct kernfs_node		*kn;
+	struct list_head		rdtgroup_list;
+	u32				closid;
+	struct cpumask			cpu_mask;
+	int				flags;
+	atomic_t			waitcount;
+	enum rdt_group_type		type;
+	struct mongroup			mon;
+	enum rdtgrp_mode		mode;
+	struct pseudo_lock_region	*plr;
 };
 
 /* rdtgroup.flags */
@@ -246,22 +262,24 @@ struct mbm_state {
  * @mbps_val:	When mba_sc is enabled, this holds the bandwidth in MBps
  * @new_ctrl:	new ctrl value to be loaded
  * @have_new_ctrl: did user provide new_ctrl for this domain
+ * @plr:	pseudo-locked region (if any) associated with domain
  */
 struct rdt_domain {
-	struct list_head	list;
-	int			id;
-	struct cpumask		cpu_mask;
-	unsigned long		*rmid_busy_llc;
-	struct mbm_state	*mbm_total;
-	struct mbm_state	*mbm_local;
-	struct delayed_work	mbm_over;
-	struct delayed_work	cqm_limbo;
-	int			mbm_work_cpu;
-	int			cqm_work_cpu;
-	u32			*ctrl_val;
-	u32			*mbps_val;
-	u32			new_ctrl;
-	bool			have_new_ctrl;
+	struct list_head		list;
+	int				id;
+	struct cpumask			cpu_mask;
+	unsigned long			*rmid_busy_llc;
+	struct mbm_state		*mbm_total;
+	struct mbm_state		*mbm_local;
+	struct delayed_work		mbm_over;
+	struct delayed_work		cqm_limbo;
+	int				mbm_work_cpu;
+	int				cqm_work_cpu;
+	u32				*ctrl_val;
+	u32				*mbps_val;
+	u32				new_ctrl;
+	bool				have_new_ctrl;
+	struct pseudo_lock_region	*plr;
 };
 
 /**
-- 
cgit v1.2.3


From 63657c1cdf89a37d3b69471ad4e5b55c77e86d3f Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:16 -0700
Subject: x86/intel_rdt: Support enter/exit of locksetup mode

The locksetup mode is the way in which the user communicates that the
resource group will be used for a pseudo-locked region. Locksetup mode
should thus ensure that all restrictions on a resource group are met before
locksetup mode can be entered. The resource group should also be configured
to ensure that it cannot be modified in unsupported ways when a
pseudo-locked region.

Introduce the support where the request for entering locksetup mode can be
validated. This includes: CDP is not active, no cpus or tasks are assigned
to the resource group, monitoring is not in progress on the resource
group. Once the resource group is determined ready for a pseudo-locked
region it is configured to not allow future changes to these properties.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/b120f71ced30116bcc6c6f651e8a7906ae6b903d.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             |   2 +
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 187 +++++++++++++++++++++++++++-
 2 files changed, 183 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index f3dcbcd03dfa..338fe47396a5 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -501,6 +501,8 @@ unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
 				  u32 cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 int rdtgroup_tasks_assigned(struct rdtgroup *r);
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int update_domains(struct rdt_resource *r, int closid);
 void closid_free(int closid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 8693dbe602a2..ce8243c87877 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -11,8 +11,48 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/slab.h>
 #include "intel_rdt.h"
 
+/**
+ * pseudo_lock_init - Initialize a pseudo-lock region
+ * @rdtgrp: resource group to which new pseudo-locked region will belong
+ *
+ * A pseudo-locked region is associated with a resource group. When this
+ * association is created the pseudo-locked region is initialized. The
+ * details of the pseudo-locked region are not known at this time so only
+ * allocation is done and association established.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_init(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr;
+
+	plr = kzalloc(sizeof(*plr), GFP_KERNEL);
+	if (!plr)
+		return -ENOMEM;
+
+	rdtgrp->plr = plr;
+	return 0;
+}
+
+/**
+ * pseudo_lock_free - Free a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-locked region belonged
+ *
+ * The pseudo-locked region's resources have already been released, or not
+ * yet created at this point. Now it can be freed and disassociated from the
+ * resource group.
+ *
+ * Return: void
+ */
+static void pseudo_lock_free(struct rdtgroup *rdtgrp)
+{
+	kfree(rdtgrp->plr);
+	rdtgrp->plr = NULL;
+}
+
 /**
  * rdtgroup_monitor_in_progress - Test if monitoring in progress
  * @r: resource group being queried
@@ -20,8 +60,7 @@
  * Return: 1 if monitor groups have been created for this resource
  * group, 0 otherwise.
  */
-static int __attribute__ ((unused))
-rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
+static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
 {
 	return !list_empty(&rdtgrp->mon.crdtgrp_list);
 }
@@ -41,8 +80,7 @@ rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
  * the state of the mode of these files will be uncertain when a failure
  * occurs.
  */
-static int __attribute__ ((unused))
-rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
+static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
 {
 	int ret;
 
@@ -89,8 +127,7 @@ out:
  * again but the state of the mode of these files will be uncertain when
  * a failure occurs.
  */
-static int __attribute__ ((unused))
-rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
+static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
 {
 	int ret;
 
@@ -124,3 +161,141 @@ err_tasks:
 out:
 	return ret;
 }
+
+/**
+ * rdtgroup_locksetup_enter - Resource group enters locksetup mode
+ * @rdtgrp: resource group requested to enter locksetup mode
+ *
+ * A resource group enters locksetup mode to reflect that it would be used
+ * to represent a pseudo-locked region and is in the process of being set
+ * up to do so. A resource group used for a pseudo-locked region would
+ * lose the closid associated with it so we cannot allow it to have any
+ * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
+ * future. Monitoring of a pseudo-locked region is not allowed either.
+ *
+ * The above and more restrictions on a pseudo-locked region are checked
+ * for and enforced before the resource group enters the locksetup mode.
+ *
+ * Returns: 0 if the resource group successfully entered locksetup mode, <0
+ * on failure. On failure the last_cmd_status buffer is updated with text to
+ * communicate details of failure to the user.
+ */
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	/*
+	 * The default resource group can neither be removed nor lose the
+	 * default closid associated with it.
+	 */
+	if (rdtgrp == &rdtgroup_default) {
+		rdt_last_cmd_puts("cannot pseudo-lock default group\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Cache Pseudo-locking not supported when CDP is enabled.
+	 *
+	 * Some things to consider if you would like to enable this
+	 * support (using L3 CDP as example):
+	 * - When CDP is enabled two separate resources are exposed,
+	 *   L3DATA and L3CODE, but they are actually on the same cache.
+	 *   The implication for pseudo-locking is that if a
+	 *   pseudo-locked region is created on a domain of one
+	 *   resource (eg. L3CODE), then a pseudo-locked region cannot
+	 *   be created on that same domain of the other resource
+	 *   (eg. L3DATA). This is because the creation of a
+	 *   pseudo-locked region involves a call to wbinvd that will
+	 *   affect all cache allocations on particular domain.
+	 * - Considering the previous, it may be possible to only
+	 *   expose one of the CDP resources to pseudo-locking and
+	 *   hide the other. For example, we could consider to only
+	 *   expose L3DATA and since the L3 cache is unified it is
+	 *   still possible to place instructions there are execute it.
+	 * - If only one region is exposed to pseudo-locking we should
+	 *   still keep in mind that availability of a portion of cache
+	 *   for pseudo-locking should take into account both resources.
+	 *   Similarly, if a pseudo-locked region is created in one
+	 *   resource, the portion of cache used by it should be made
+	 *   unavailable to all future allocations from both resources.
+	 */
+	if (rdt_resources_all[RDT_RESOURCE_L3DATA].alloc_enabled ||
+	    rdt_resources_all[RDT_RESOURCE_L2DATA].alloc_enabled) {
+		rdt_last_cmd_puts("CDP enabled\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_monitor_in_progress(rdtgrp)) {
+		rdt_last_cmd_puts("monitoring in progress\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_tasks_assigned(rdtgrp)) {
+		rdt_last_cmd_puts("tasks assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (!cpumask_empty(&rdtgrp->cpu_mask)) {
+		rdt_last_cmd_puts("CPUs assigned to resource group\n");
+		return -EINVAL;
+	}
+
+	if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
+		rdt_last_cmd_puts("unable to modify resctrl permissions\n");
+		return -EIO;
+	}
+
+	ret = pseudo_lock_init(rdtgrp);
+	if (ret) {
+		rdt_last_cmd_puts("unable to init pseudo-lock region\n");
+		goto out_release;
+	}
+
+	/*
+	 * If this system is capable of monitoring a rmid would have been
+	 * allocated when the control group was created. This is not needed
+	 * anymore when this group would be used for pseudo-locking. This
+	 * is safe to call on platforms not capable of monitoring.
+	 */
+	free_rmid(rdtgrp->mon.rmid);
+
+	ret = 0;
+	goto out;
+
+out_release:
+	rdtgroup_locksetup_user_restore(rdtgrp);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_locksetup_exit - resource group exist locksetup mode
+ * @rdtgrp: resource group
+ *
+ * When a resource group exits locksetup mode the earlier restrictions are
+ * lifted.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+	int ret;
+
+	if (rdt_mon_capable) {
+		ret = alloc_rmid();
+		if (ret < 0) {
+			rdt_last_cmd_puts("out of RMIDs\n");
+			return ret;
+		}
+		rdtgrp->mon.rmid = ret;
+	}
+
+	ret = rdtgroup_locksetup_user_restore(rdtgrp);
+	if (ret) {
+		free_rmid(rdtgrp->mon.rmid);
+		return ret;
+	}
+
+	pseudo_lock_free(rdtgrp);
+	return 0;
+}
-- 
cgit v1.2.3


From dfe9674b04ff6b819f9105650a008d164d81725e Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:17 -0700
Subject: x86/intel_rdt: Enable entering of pseudo-locksetup mode

The user can request entering pseudo-locksetup mode by writing
"pseudo-locksetup" to the mode file. Act on this request as well as
support switching from a pseudo-locksetup mode (before pseudo-locked
mode was entered). It is not supported to modify the mode once
pseudo-locked mode has been entered.

The schemata reflects the new mode by adding "uninitialized" to all
resources. The size resctrl file reports zero for all cache domains in
support of the uninitialized nature. Since there are no users of this
class of service its allocations can be ignored when searching for
appropriate default allocations for new resource groups. For the same
reason resource groups in pseudo-locksetup mode are not considered when
testing if new resource groups may overlap.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/56f553334708022903c296284e62db3bbc1ff150.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 16 +++++++----
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 41 +++++++++++++++++++++++++----
 2 files changed, 47 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index bc79396c5dad..1ed273220ffa 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -156,7 +156,8 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 	}
 
 	if (rdtgroup_cbm_overlaps(r, d, cbm_val, rdtgrp->closid, false)) {
-		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE) {
+		if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 			rdt_last_cmd_printf("overlaps with other group\n");
 			return -EINVAL;
 		}
@@ -356,10 +357,15 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (rdtgrp) {
-		closid = rdtgrp->closid;
-		for_each_alloc_enabled_rdt_resource(r) {
-			if (closid < r->num_closid)
-				show_doms(s, r, closid);
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			for_each_alloc_enabled_rdt_resource(r)
+				seq_printf(s, "%s:uninitialized\n", r->name);
+		} else {
+			closid = rdtgrp->closid;
+			for_each_alloc_enabled_rdt_resource(r) {
+				if (closid < r->num_closid)
+					show_doms(s, r, closid);
+			}
 		}
 	} else {
 		ret = -ENOENT;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 013cbfedc753..bd4e2de303dc 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -974,9 +974,10 @@ bool rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_domain *d,
 	ctrl = d->ctrl_val;
 	for (i = 0; i < r->num_closid; i++, ctrl++) {
 		ctrl_b = (unsigned long *)ctrl;
-		if (closid_allocated(i) && i != closid) {
+		mode = rdtgroup_mode_by_closid(i);
+		if (closid_allocated(i) && i != closid &&
+		    mode != RDT_MODE_PSEUDO_LOCKSETUP) {
 			if (bitmap_intersects(cbm, ctrl_b, r->cache.cbm_len)) {
-				mode = rdtgroup_mode_by_closid(i);
 				if (exclusive) {
 					if (mode == RDT_MODE_EXCLUSIVE)
 						return true;
@@ -1046,10 +1047,24 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 	mode = rdtgrp->mode;
 
 	if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
-	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE))
+	    (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
+	    (!strcmp(buf, "pseudo-locksetup") &&
+	     mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
+	    (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
 		goto out;
 
+	if (mode == RDT_MODE_PSEUDO_LOCKED) {
+		rdt_last_cmd_printf("cannot change pseudo-locked group\n");
+		ret = -EINVAL;
+		goto out;
+	}
+
 	if (!strcmp(buf, "shareable")) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
 		rdtgrp->mode = RDT_MODE_SHAREABLE;
 	} else if (!strcmp(buf, "exclusive")) {
 		if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
@@ -1057,7 +1072,17 @@ static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
 			ret = -EINVAL;
 			goto out;
 		}
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+			ret = rdtgroup_locksetup_exit(rdtgrp);
+			if (ret)
+				goto out;
+		}
 		rdtgrp->mode = RDT_MODE_EXCLUSIVE;
+	} else if (!strcmp(buf, "pseudo-locksetup")) {
+		ret = rdtgroup_locksetup_enter(rdtgrp);
+		if (ret)
+			goto out;
+		rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
 	} else {
 		rdt_last_cmd_printf("unknown/unsupported mode\n");
 		ret = -EINVAL;
@@ -1127,8 +1152,12 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 		list_for_each_entry(d, &r->domains, list) {
 			if (sep)
 				seq_putc(s, ';');
-			cbm = d->ctrl_val[rdtgrp->closid];
-			size = rdtgroup_cbm_to_size(r, d, cbm);
+			if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+				size = 0;
+			} else {
+				cbm = d->ctrl_val[rdtgrp->closid];
+				size = rdtgroup_cbm_to_size(r, d, cbm);
+			}
 			seq_printf(s, "%d=%u", d->id, size);
 			sep = true;
 		}
@@ -2277,6 +2306,8 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 			for (i = 0; i < r->num_closid; i++, ctrl++) {
 				if (closid_allocated(i) && i != closid) {
 					mode = rdtgroup_mode_by_closid(i);
+					if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
+						break;
 					used_b |= *ctrl;
 					if (mode == RDT_MODE_SHAREABLE)
 						d->new_ctrl |= *ctrl;
-- 
cgit v1.2.3


From 17eafd076291ed23eeb17b28132fa33b0688bc57 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:18 -0700
Subject: x86/intel_rdt: Split resource group removal in two

Resource groups used for pseudo-locking do not require the same work on
removal as the other resource groups.

The resource group removal is split in two in preparation for support of
pseudo-locking resource groups. A single re-ordering occurs - the
setting of the rdtgrp flag is moved to later. This flag is not used by
any of the code between its original and new location.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/c8cbf7a7c72480b39bb946a929dbae96c0f9aca1.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index bd4e2de303dc..526cd4a97054 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -2620,6 +2620,21 @@ static int rdtgroup_rmdir_mon(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	return 0;
 }
 
+static int rdtgroup_ctrl_remove(struct kernfs_node *kn,
+				struct rdtgroup *rdtgrp)
+{
+	rdtgrp->flags = RDT_DELETED;
+	list_del(&rdtgrp->rdtgroup_list);
+
+	/*
+	 * one extra hold on this, will drop when we kfree(rdtgrp)
+	 * in rdtgroup_kn_unlock()
+	 */
+	kernfs_get(kn);
+	kernfs_remove(rdtgrp->kn);
+	return 0;
+}
+
 static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 			       cpumask_var_t tmpmask)
 {
@@ -2645,7 +2660,6 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
 	update_closid_rmid(tmpmask, NULL);
 
-	rdtgrp->flags = RDT_DELETED;
 	closid_free(rdtgrp->closid);
 	free_rmid(rdtgrp->mon.rmid);
 
@@ -2654,14 +2668,7 @@ static int rdtgroup_rmdir_ctrl(struct kernfs_node *kn, struct rdtgroup *rdtgrp,
 	 */
 	free_all_child_rdtgrp(rdtgrp);
 
-	list_del(&rdtgrp->rdtgroup_list);
-
-	/*
-	 * one extra hold on this, will drop when we kfree(rdtgrp)
-	 * in rdtgroup_kn_unlock()
-	 */
-	kernfs_get(kn);
-	kernfs_remove(rdtgrp->kn);
+	rdtgroup_ctrl_remove(kn, rdtgrp);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 72d505056604a305a4fcd8b268d2f6e979e17023 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:19 -0700
Subject: x86/intel_rdt: Add utilities to test pseudo-locked region possibility

A pseudo-locked region does not have a class of service associated with
it and thus not tracked in the array of control values maintained as
part of the domain. Even so, when the user provides a new bitmask for
another resource group it needs to be checked for interference with
existing pseudo-locked regions.

Additionally only one pseudo-locked region can be created in any cache
hierarchy.

Introduce two utilities in support of above scenarios: (1) a utility
that can be used to test if a given capacity bitmask overlaps with any
pseudo-locked regions associated with a particular cache instance, (2) a
utility that can be used to test if a pseudo-locked region exists within
a particular cache hierarchy.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/b8e31dbdcf22ddf71df46072647b47e7558abb32.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             |  2 +
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 74 +++++++++++++++++++++++++++++
 2 files changed, 76 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 338fe47396a5..b5d3ddfa94e6 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -503,6 +503,8 @@ enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 int rdtgroup_tasks_assigned(struct rdtgroup *r);
 int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
 int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int update_domains(struct rdt_resource *r, int closid);
 void closid_free(int closid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index ce8243c87877..b145a7386b10 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -299,3 +299,77 @@ int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
 	pseudo_lock_free(rdtgrp);
 	return 0;
 }
+
+/**
+ * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
+ * @d: RDT domain
+ * @_cbm: CBM to test
+ *
+ * @d represents a cache instance and @_cbm a capacity bitmask that is
+ * considered for it. Determine if @_cbm overlaps with any existing
+ * pseudo-locked region on @d.
+ *
+ * Return: true if @_cbm overlaps with pseudo-locked region on @d, false
+ * otherwise.
+ */
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
+{
+	unsigned long *cbm = (unsigned long *)&_cbm;
+	unsigned long *cbm_b;
+	unsigned int cbm_len;
+
+	if (d->plr) {
+		cbm_len = d->plr->r->cache.cbm_len;
+		cbm_b = (unsigned long *)&d->plr->cbm;
+		if (bitmap_intersects(cbm, cbm_b, cbm_len))
+			return true;
+	}
+
+	return false;
+}
+
+/**
+ * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
+ * @d: RDT domain under test
+ *
+ * The setup of a pseudo-locked region affects all cache instances within
+ * the hierarchy of the region. It is thus essential to know if any
+ * pseudo-locked regions exist within a cache hierarchy to prevent any
+ * attempts to create new pseudo-locked regions in the same hierarchy.
+ *
+ * Return: true if a pseudo-locked region exists in the hierarchy of @d or
+ *         if it is not possible to test due to memory allocation issue,
+ *         false otherwise.
+ */
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
+{
+	cpumask_var_t cpu_with_psl;
+	struct rdt_resource *r;
+	struct rdt_domain *d_i;
+	bool ret = false;
+
+	if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
+		return true;
+
+	/*
+	 * First determine which cpus have pseudo-locked regions
+	 * associated with them.
+	 */
+	for_each_alloc_enabled_rdt_resource(r) {
+		list_for_each_entry(d_i, &r->domains, list) {
+			if (d_i->plr)
+				cpumask_or(cpu_with_psl, cpu_with_psl,
+					   &d_i->cpu_mask);
+		}
+	}
+
+	/*
+	 * Next test if new pseudo-locked region would intersect with
+	 * existing region.
+	 */
+	if (cpumask_intersects(&d->cpu_mask, cpu_with_psl))
+		ret = true;
+
+	free_cpumask_var(cpu_with_psl);
+	return ret;
+}
-- 
cgit v1.2.3


From f2a177292bd052ce12ac453d2ceeb083fe07718a Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:20 -0700
Subject: x86/intel_rdt: Discover supported platforms via prefetch disable bits

Knowing the model specific prefetch disable bits is required to support
cache pseudo-locking because the hardware prefetchers need to be disabled
when the kernel memory is pseudo-locked to cache. We add these bits only
for platforms known to support cache pseudo-locking.

When the user requests locksetup mode to be entered it will fail if the
prefetch disabling bits are not known for the platform.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/3eef559aa9fd693a104ff99ff909cfee450c1695.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 75 +++++++++++++++++++++++++++++
 1 file changed, 75 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index b145a7386b10..cbba4bc17522 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -12,8 +12,73 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/slab.h>
+#include <asm/intel-family.h>
 #include "intel_rdt.h"
 
+/*
+ * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
+ * prefetcher state. Details about this register can be found in the MSR
+ * tables for specific platforms found in Intel's SDM.
+ */
+#define MSR_MISC_FEATURE_CONTROL	0x000001a4
+
+/*
+ * The bits needed to disable hardware prefetching varies based on the
+ * platform. During initialization we will discover which bits to use.
+ */
+static u64 prefetch_disable_bits;
+
+/**
+ * get_prefetch_disable_bits - prefetch disable bits of supported platforms
+ *
+ * Capture the list of platforms that have been validated to support
+ * pseudo-locking. This includes testing to ensure pseudo-locked regions
+ * with low cache miss rates can be created under variety of load conditions
+ * as well as that these pseudo-locked regions can maintain their low cache
+ * miss rates under variety of load conditions for significant lengths of time.
+ *
+ * After a platform has been validated to support pseudo-locking its
+ * hardware prefetch disable bits are included here as they are documented
+ * in the SDM.
+ *
+ * Return:
+ * If platform is supported, the bits to disable hardware prefetchers, 0
+ * if platform is not supported.
+ */
+static u64 get_prefetch_disable_bits(void)
+{
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
+	    boot_cpu_data.x86 != 6)
+		return 0;
+
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_BROADWELL_X:
+		/*
+		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+		 * as:
+		 * 0    L2 Hardware Prefetcher Disable (R/W)
+		 * 1    L2 Adjacent Cache Line Prefetcher Disable (R/W)
+		 * 2    DCU Hardware Prefetcher Disable (R/W)
+		 * 3    DCU IP Prefetcher Disable (R/W)
+		 * 63:4 Reserved
+		 */
+		return 0xF;
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		/*
+		 * SDM defines bits of MSR_MISC_FEATURE_CONTROL register
+		 * as:
+		 * 0     L2 Hardware Prefetcher Disable (R/W)
+		 * 1     Reserved
+		 * 2     DCU Hardware Prefetcher Disable (R/W)
+		 * 63:3  Reserved
+		 */
+		return 0x5;
+	}
+
+	return 0;
+}
+
 /**
  * pseudo_lock_init - Initialize a pseudo-lock region
  * @rdtgrp: resource group to which new pseudo-locked region will belong
@@ -225,6 +290,16 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
 		return -EINVAL;
 	}
 
+	/*
+	 * Not knowing the bits to disable prefetching implies that this
+	 * platform does not support Cache Pseudo-Locking.
+	 */
+	prefetch_disable_bits = get_prefetch_disable_bits();
+	if (prefetch_disable_bits == 0) {
+		rdt_last_cmd_puts("pseudo-locking not supported\n");
+		return -EINVAL;
+	}
+
 	if (rdtgroup_monitor_in_progress(rdtgrp)) {
 		rdt_last_cmd_puts("monitoring in progress\n");
 		return -EINVAL;
-- 
cgit v1.2.3


From 018961ae5579016d46ee03587c0ecf673821eedb Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:21 -0700
Subject: x86/intel_rdt: Pseudo-lock region creation/removal core

The user requests a pseudo-locked region by providing a schemata to a
resource group that is in the pseudo-locksetup mode. This is the
functionality that consumes the parsed user data and creates the
pseudo-locked region.

First, required information is deduced from user provided data.
This includes, how much memory does the requested bitmask represent,
which CPU the requested region is associated with, and what is the
cache line size of that cache (to learn the stride needed for locking).
Second, a contiguous block of memory matching the requested bitmask is
allocated.

Finally, pseudo-locking is performed. The resource group already has the
allocation that reflects the requested bitmask. With this class of service
active and interference minimized, the allocated memory is loaded into the
cache.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/67391160bbf06143bc62d856d3d234eb152008b7.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             |  17 ++
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 337 +++++++++++++++++++++++++++-
 2 files changed, 353 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index b5d3ddfa94e6..f245aaae514e 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -129,11 +129,26 @@ struct mongroup {
  * @d:			RDT domain to which this pseudo-locked region
  *			belongs
  * @cbm:		bitmask of the pseudo-locked region
+ * @lock_thread_wq:	waitqueue used to wait on the pseudo-locking thread
+ *			completion
+ * @thread_done:	variable used by waitqueue to test if pseudo-locking
+ *			thread completed
+ * @cpu:		core associated with the cache on which the setup code
+ *			will be run
+ * @line_size:		size of the cache lines
+ * @size:		size of pseudo-locked region in bytes
+ * @kmem:		the kernel memory associated with pseudo-locked region
  */
 struct pseudo_lock_region {
 	struct rdt_resource	*r;
 	struct rdt_domain	*d;
 	u32			cbm;
+	wait_queue_head_t	lock_thread_wq;
+	int			thread_done;
+	int			cpu;
+	unsigned int		line_size;
+	unsigned int		size;
+	void			*kmem;
 };
 
 /**
@@ -505,6 +520,8 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
 int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
 bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
 bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int update_domains(struct rdt_resource *r, int closid);
 void closid_free(int closid);
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index cbba4bc17522..22387af30a9e 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -11,8 +11,14 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
+#include <linux/cacheinfo.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/kthread.h>
 #include <linux/slab.h>
+#include <asm/cacheflush.h>
 #include <asm/intel-family.h>
+#include <asm/intel_rdt_sched.h>
 #include "intel_rdt.h"
 
 /*
@@ -79,6 +85,53 @@ static u64 get_prefetch_disable_bits(void)
 	return 0;
 }
 
+/**
+ * pseudo_lock_region_init - Initialize pseudo-lock region information
+ * @plr: pseudo-lock region
+ *
+ * Called after user provided a schemata to be pseudo-locked. From the
+ * schemata the &struct pseudo_lock_region is on entry already initialized
+ * with the resource, domain, and capacity bitmask. Here the information
+ * required for pseudo-locking is deduced from this data and &struct
+ * pseudo_lock_region initialized further. This information includes:
+ * - size in bytes of the region to be pseudo-locked
+ * - cache line size to know the stride with which data needs to be accessed
+ *   to be pseudo-locked
+ * - a cpu associated with the cache instance on which the pseudo-locking
+ *   flow can be executed
+ *
+ * Return: 0 on success, <0 on failure. Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
+{
+	struct cpu_cacheinfo *ci;
+	int i;
+
+	/* Pick the first cpu we find that is associated with the cache. */
+	plr->cpu = cpumask_first(&plr->d->cpu_mask);
+
+	if (!cpu_online(plr->cpu)) {
+		rdt_last_cmd_printf("cpu %u associated with cache not online\n",
+				    plr->cpu);
+		return -ENODEV;
+	}
+
+	ci = get_cpu_cacheinfo(plr->cpu);
+
+	plr->size = rdtgroup_cbm_to_size(plr->r, plr->d, plr->cbm);
+
+	for (i = 0; i < ci->num_leaves; i++) {
+		if (ci->info_list[i].level == plr->r->cache_level) {
+			plr->line_size = ci->info_list[i].coherency_line_size;
+			return 0;
+		}
+	}
+
+	rdt_last_cmd_puts("unable to determine cache line size\n");
+	return -1;
+}
+
 /**
  * pseudo_lock_init - Initialize a pseudo-lock region
  * @rdtgrp: resource group to which new pseudo-locked region will belong
@@ -98,10 +151,69 @@ static int pseudo_lock_init(struct rdtgroup *rdtgrp)
 	if (!plr)
 		return -ENOMEM;
 
+	init_waitqueue_head(&plr->lock_thread_wq);
 	rdtgrp->plr = plr;
 	return 0;
 }
 
+/**
+ * pseudo_lock_region_clear - Reset pseudo-lock region data
+ * @plr: pseudo-lock region
+ *
+ * All content of the pseudo-locked region is reset - any memory allocated
+ * freed.
+ *
+ * Return: void
+ */
+static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
+{
+	plr->size = 0;
+	plr->line_size = 0;
+	kfree(plr->kmem);
+	plr->kmem = NULL;
+	plr->r = NULL;
+	if (plr->d)
+		plr->d->plr = NULL;
+	plr->d = NULL;
+	plr->cbm = 0;
+}
+
+/**
+ * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
+ * @plr: pseudo-lock region
+ *
+ * Initialize the details required to set up the pseudo-locked region and
+ * allocate the contiguous memory that will be pseudo-locked to the cache.
+ *
+ * Return: 0 on success, <0 on failure.  Descriptive error will be written
+ * to last_cmd_status buffer.
+ */
+static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
+{
+	int ret;
+
+	ret = pseudo_lock_region_init(plr);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * We do not yet support contiguous regions larger than
+	 * KMALLOC_MAX_SIZE.
+	 */
+	if (plr->size > KMALLOC_MAX_SIZE) {
+		rdt_last_cmd_puts("requested region exceeds maximum size\n");
+		return -E2BIG;
+	}
+
+	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
+	if (!plr->kmem) {
+		rdt_last_cmd_puts("unable to allocate memory\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
 /**
  * pseudo_lock_free - Free a pseudo-locked region
  * @rdtgrp: resource group to which pseudo-locked region belonged
@@ -114,10 +226,142 @@ static int pseudo_lock_init(struct rdtgroup *rdtgrp)
  */
 static void pseudo_lock_free(struct rdtgroup *rdtgrp)
 {
+	pseudo_lock_region_clear(rdtgrp->plr);
 	kfree(rdtgrp->plr);
 	rdtgrp->plr = NULL;
 }
 
+/**
+ * pseudo_lock_fn - Load kernel memory into cache
+ * @_rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * This is the core pseudo-locking flow.
+ *
+ * First we ensure that the kernel memory cannot be found in the cache.
+ * Then, while taking care that there will be as little interference as
+ * possible, the memory to be loaded is accessed while core is running
+ * with class of service set to the bitmask of the pseudo-locked region.
+ * After this is complete no future CAT allocations will be allowed to
+ * overlap with this bitmask.
+ *
+ * Local register variables are utilized to ensure that the memory region
+ * to be locked is the only memory access made during the critical locking
+ * loop.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int pseudo_lock_fn(void *_rdtgrp)
+{
+	struct rdtgroup *rdtgrp = _rdtgrp;
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	u32 rmid_p, closid_p;
+	unsigned long i;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use a regular
+	 * variable to ensure we always use a valid pointer, but the cost
+	 * is that this variable will enter the cache through evicting the
+	 * memory we are trying to lock into the cache. Thus expect lower
+	 * pseudo-locking success rate when KASAN is active.
+	 */
+	unsigned int line_size;
+	unsigned int size;
+	void *mem_r;
+#else
+	register unsigned int line_size asm("esi");
+	register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	/*
+	 * Make sure none of the allocated memory is cached. If it is we
+	 * will get a cache hit in below loop from outside of pseudo-locked
+	 * region.
+	 * wbinvd (as opposed to clflush/clflushopt) is required to
+	 * increase likelihood that allocated cache portion will be filled
+	 * with associated memory.
+	 */
+	native_wbinvd();
+
+	/*
+	 * Always called with interrupts enabled. By disabling interrupts
+	 * ensure that we will not be preempted during this critical section.
+	 */
+	local_irq_disable();
+
+	/*
+	 * Call wrmsr and rdmsr as directly as possible to avoid tracing
+	 * clobbering local register variables or affecting cache accesses.
+	 *
+	 * Disable the hardware prefetcher so that when the end of the memory
+	 * being pseudo-locked is reached the hardware will not read beyond
+	 * the buffer and evict pseudo-locked memory read earlier from the
+	 * cache.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	closid_p = this_cpu_read(pqr_state.cur_closid);
+	rmid_p = this_cpu_read(pqr_state.cur_rmid);
+	mem_r = plr->kmem;
+	size = plr->size;
+	line_size = plr->line_size;
+	/*
+	 * Critical section begin: start by writing the closid associated
+	 * with the capacity bitmask of the cache region being
+	 * pseudo-locked followed by reading of kernel memory to load it
+	 * into the cache.
+	 */
+	__wrmsr(IA32_PQR_ASSOC, rmid_p, rdtgrp->closid);
+	/*
+	 * Cache was flushed earlier. Now access kernel memory to read it
+	 * into cache region associated with just activated plr->closid.
+	 * Loop over data twice:
+	 * - In first loop the cache region is shared with the page walker
+	 *   as it populates the paging structure caches (including TLB).
+	 * - In the second loop the paging structure caches are used and
+	 *   cache region is populated with the memory being referenced.
+	 */
+	for (i = 0; i < size; i += PAGE_SIZE) {
+		/*
+		 * Add a barrier to prevent speculative execution of this
+		 * loop reading beyond the end of the buffer.
+		 */
+		rmb();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			:
+			: "r" (mem_r), "r" (i)
+			: "%eax", "memory");
+	}
+	for (i = 0; i < size; i += line_size) {
+		/*
+		 * Add a barrier to prevent speculative execution of this
+		 * loop reading beyond the end of the buffer.
+		 */
+		rmb();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			:
+			: "r" (mem_r), "r" (i)
+			: "%eax", "memory");
+	}
+	/*
+	 * Critical section end: restore closid with capacity bitmask that
+	 * does not overlap with pseudo-locked region.
+	 */
+	__wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);
+
+	/* Re-enable the hardware prefetcher(s) */
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
 /**
  * rdtgroup_monitor_in_progress - Test if monitoring in progress
  * @r: resource group being queried
@@ -399,7 +643,6 @@ bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm)
 		if (bitmap_intersects(cbm, cbm_b, cbm_len))
 			return true;
 	}
-
 	return false;
 }
 
@@ -448,3 +691,95 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	free_cpumask_var(cpu_with_psl);
 	return ret;
 }
+
+/**
+ * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
+ * @rdtgrp: resource group to which pseudo-lock region belongs
+ *
+ * Called when a resource group in the pseudo-locksetup mode receives a
+ * valid schemata that should be pseudo-locked. Since the resource group is
+ * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
+ * allocated and initialized with the essential information. If a failure
+ * occurs the resource group remains in the pseudo-locksetup mode with the
+ * &struct pseudo_lock_region associated with it, but cleared from all
+ * information and ready for the user to re-attempt pseudo-locking by
+ * writing the schemata again.
+ *
+ * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
+ * on failure. Descriptive error will be written to last_cmd_status buffer.
+ */
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	int ret;
+
+	ret = pseudo_lock_region_alloc(plr);
+	if (ret < 0)
+		return ret;
+
+	plr->thread_done = 0;
+
+	thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
+					cpu_to_node(plr->cpu),
+					"pseudo_lock/%u", plr->cpu);
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		rdt_last_cmd_printf("locking thread returned error %d\n", ret);
+		goto out_region;
+	}
+
+	kthread_bind(thread, plr->cpu);
+	wake_up_process(thread);
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0) {
+		/*
+		 * If the thread does not get on the CPU for whatever
+		 * reason and the process which sets up the region is
+		 * interrupted then this will leave the thread in runnable
+		 * state and once it gets on the CPU it will derefence
+		 * the cleared, but not freed, plr struct resulting in an
+		 * empty pseudo-locking loop.
+		 */
+		rdt_last_cmd_puts("locking thread interrupted\n");
+		goto out_region;
+	}
+
+	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
+	closid_free(rdtgrp->closid);
+	ret = 0;
+	goto out;
+
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
+}
+
+/**
+ * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
+ * @rdtgrp: resource group to which the pseudo-locked region belongs
+ *
+ * The removal of a pseudo-locked region can be initiated when the resource
+ * group is removed from user space via a "rmdir" from userspace or the
+ * unmount of the resctrl filesystem. On removal the resource group does
+ * not go back to pseudo-locksetup mode before it is removed, instead it is
+ * removed directly. There is thus assymmetry with the creation where the
+ * &struct pseudo_lock_region is removed here while it was not created in
+ * rdtgroup_pseudo_lock_create().
+ *
+ * Return: void
+ */
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
+{
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP)
+		/*
+		 * Default group cannot be a pseudo-locked region so we can
+		 * free closid here.
+		 */
+		closid_free(rdtgrp->closid);
+
+	pseudo_lock_free(rdtgrp);
+}
-- 
cgit v1.2.3


From e0bdfe8e36f3fbbdc91e70bf927f743ca23917b0 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:22 -0700
Subject: x86/intel_rdt: Support creation/removal of pseudo-locked region

The user triggers the creation of a pseudo-locked region when writing a
valid schemata to the schemata file of a resource group in the
pseudo-locksetup mode.

A valid schemata is one that: (1) does not overlap with any other resource
group, (2) does not involve a cache that already contains a pseudo-locked
region within its hierarchy.

After a valid schemata is parsed the system is programmed to associate the
to be pseudo-lock bitmask with the closid associated with the resource
group. With the system set up the pseudo-locked region can be created.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/8929c3a9e2ba600e79649abe584aa28b8d0ff639.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c | 42 +++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 25 +++++++++++++----
 2 files changed, 62 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 1ed273220ffa..6f4c0002b2c1 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -143,9 +143,26 @@ int parse_cbm(void *_data, struct rdt_resource *r, struct rdt_domain *d)
 		return -EINVAL;
 	}
 
+	/*
+	 * Cannot set up more than one pseudo-locked region in a cache
+	 * hierarchy.
+	 */
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
+	    rdtgroup_pseudo_locked_in_hierarchy(d)) {
+		rdt_last_cmd_printf("pseudo-locked region in hierarchy\n");
+		return -EINVAL;
+	}
+
 	if (!cbm_validate(data->buf, &cbm_val, r))
 		return -EINVAL;
 
+	if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
+	     rdtgrp->mode == RDT_MODE_SHAREABLE) &&
+	    rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
+		rdt_last_cmd_printf("CBM overlaps with pseudo-locked region\n");
+		return -EINVAL;
+	}
+
 	/*
 	 * The CBM may not overlap with the CBM of another closid if
 	 * either is exclusive.
@@ -199,6 +216,21 @@ next:
 			data.rdtgrp = rdtgrp;
 			if (r->parse_ctrlval(&data, r, d))
 				return -EINVAL;
+			if (rdtgrp->mode ==  RDT_MODE_PSEUDO_LOCKSETUP) {
+				/*
+				 * In pseudo-locking setup mode and just
+				 * parsed a valid CBM that should be
+				 * pseudo-locked. Only one locked region per
+				 * resource group and domain so just do
+				 * the required initialization for single
+				 * region and return.
+				 */
+				rdtgrp->plr->r = r;
+				rdtgrp->plr->d = d;
+				rdtgrp->plr->cbm = d->new_ctrl;
+				d->plr = rdtgrp->plr;
+				return 0;
+			}
 			goto next;
 		}
 	}
@@ -322,6 +354,16 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 			goto out;
 	}
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
+		/*
+		 * If pseudo-locking fails we keep the resource group in
+		 * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
+		 * active and updated for just the domain the pseudo-locked
+		 * region was requested for.
+		 */
+		ret = rdtgroup_pseudo_lock_create(rdtgrp);
+	}
+
 out:
 	rdtgroup_kn_unlock(of->kn);
 	return ret ?: nbytes;
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 526cd4a97054..d3fb7bd8cbba 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1771,6 +1771,9 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn)
 
 	if (atomic_dec_and_test(&rdtgrp->waitcount) &&
 	    (rdtgrp->flags & RDT_DELETED)) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
 		kernfs_unbreak_active_protection(kn);
 		kernfs_put(rdtgrp->kn);
 		kfree(rdtgrp);
@@ -2002,6 +2005,10 @@ static void rmdir_all_sub(void)
 		if (rdtgrp == &rdtgroup_default)
 			continue;
 
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			rdtgroup_pseudo_lock_remove(rdtgrp);
+
 		/*
 		 * Give any CPUs back to the default group. We cannot copy
 		 * cpu_online_mask because a CPU might have executed the
@@ -2313,6 +2320,8 @@ static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
 						d->new_ctrl |= *ctrl;
 				}
 			}
+			if (d->plr && d->plr->cbm > 0)
+				used_b |= d->plr->cbm;
 			unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
 			unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
 			d->new_ctrl |= unused_b;
@@ -2696,13 +2705,19 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	 * If the rdtgroup is a mon group and parent directory
 	 * is a valid "mon_groups" directory, remove the mon group.
 	 */
-	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn)
-		ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
-	else if (rdtgrp->type == RDTMON_GROUP &&
-		 is_mon_groups(parent_kn, kn->name))
+	if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn) {
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
+		    rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			ret = rdtgroup_ctrl_remove(kn, rdtgrp);
+		} else {
+			ret = rdtgroup_rmdir_ctrl(kn, rdtgrp, tmpmask);
+		}
+	} else if (rdtgrp->type == RDTMON_GROUP &&
+		 is_mon_groups(parent_kn, kn->name)) {
 		ret = rdtgroup_rmdir_mon(kn, rdtgrp, tmpmask);
-	else
+	} else {
 		ret = -EPERM;
+	}
 
 out:
 	rdtgroup_kn_unlock(kn);
-- 
cgit v1.2.3


From f4e80d67a527469245f391976d8665f934a16205 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:23 -0700
Subject: x86/intel_rdt: Resctrl files reflect pseudo-locked information

Information about resources as well as resource groups are contained in a
variety of resctrl files. Now that pseudo-locked regions can be created the
files can be updated to present appropriate information to the user.

Update the resource group's schemata file to show only the information of
the pseudo-locked region.

Update the resource group's size file to show the size in bytes of only the
pseudo-locked region.

Update the bit_usage file to use the letter 'P' for all pseudo-locked
regions.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/5ece82869b651c2178b278e00bca959f7626b6e9.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c |  3 +++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 31 +++++++++++++++++++++++------
 2 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
index 6f4c0002b2c1..af358ca05160 100644
--- a/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
+++ b/arch/x86/kernel/cpu/intel_rdt_ctrlmondata.c
@@ -402,6 +402,9 @@ int rdtgroup_schemata_show(struct kernfs_open_file *of,
 		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 			for_each_alloc_enabled_rdt_resource(r)
 				seq_printf(s, "%s:uninitialized\n", r->name);
+		} else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+			seq_printf(s, "%s:%d=%x\n", rdtgrp->plr->r->name,
+				   rdtgrp->plr->d->id, rdtgrp->plr->cbm);
 		} else {
 			closid = rdtgrp->closid;
 			for_each_alloc_enabled_rdt_resource(r) {
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index d3fb7bd8cbba..f301919ae9b2 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -771,14 +771,16 @@ static int rdt_shareable_bits_show(struct kernfs_open_file *of,
  *   H - currently used by hardware only but available for software use
  *   S - currently used and shareable by software only
  *   E - currently used exclusively by one resource group
+ *   P - currently pseudo-locked by one resource group
  */
 static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			      struct seq_file *seq, void *v)
 {
 	struct rdt_resource *r = of->kn->parent->priv;
-	u32 sw_shareable, hw_shareable, exclusive;
+	u32 sw_shareable = 0, hw_shareable = 0;
+	u32 exclusive = 0, pseudo_locked = 0;
 	struct rdt_domain *dom;
-	int i, hwb, swb, excl;
+	int i, hwb, swb, excl, psl;
 	enum rdtgrp_mode mode;
 	bool sep = false;
 	u32 *ctrl;
@@ -803,12 +805,15 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			case RDT_MODE_EXCLUSIVE:
 				exclusive |= *ctrl;
 				break;
+			case RDT_MODE_PSEUDO_LOCKSETUP:
 			/*
-			 * Temporarily handle pseudo-locking enums
-			 * to silence compile warnings until handling
-			 * added in later patches.
+			 * RDT_MODE_PSEUDO_LOCKSETUP is possible
+			 * here but not included since the CBM
+			 * associated with this CLOSID in this mode
+			 * is not initialized and no task or cpu can be
+			 * assigned this CLOSID.
 			 */
-			case RDT_MODE_PSEUDO_LOCKSETUP:
+				break;
 			case RDT_MODE_PSEUDO_LOCKED:
 			case RDT_NUM_MODES:
 				WARN(1,
@@ -817,9 +822,11 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 			}
 		}
 		for (i = r->cache.cbm_len - 1; i >= 0; i--) {
+			pseudo_locked = dom->plr ? dom->plr->cbm : 0;
 			hwb = test_bit(i, (unsigned long *)&hw_shareable);
 			swb = test_bit(i, (unsigned long *)&sw_shareable);
 			excl = test_bit(i, (unsigned long *)&exclusive);
+			psl = test_bit(i, (unsigned long *)&pseudo_locked);
 			if (hwb && swb)
 				seq_putc(seq, 'X');
 			else if (hwb && !swb)
@@ -828,6 +835,8 @@ static int rdt_bit_usage_show(struct kernfs_open_file *of,
 				seq_putc(seq, 'S');
 			else if (excl)
 				seq_putc(seq, 'E');
+			else if (psl)
+				seq_putc(seq, 'P');
 			else /* Unused bits remain */
 				seq_putc(seq, '0');
 		}
@@ -1147,6 +1156,15 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 		return -ENOENT;
 	}
 
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
+		seq_printf(s, "%*s:", max_name_width, rdtgrp->plr->r->name);
+		size = rdtgroup_cbm_to_size(rdtgrp->plr->r,
+					    rdtgrp->plr->d,
+					    rdtgrp->plr->cbm);
+		seq_printf(s, "%d=%u\n", rdtgrp->plr->d->id, size);
+		goto out;
+	}
+
 	for_each_alloc_enabled_rdt_resource(r) {
 		seq_printf(s, "%*s:", max_name_width, r->name);
 		list_for_each_entry(d, &r->domains, list) {
@@ -1164,6 +1182,7 @@ static int rdtgroup_size_show(struct kernfs_open_file *of,
 		seq_putc(s, '\n');
 	}
 
+out:
 	rdtgroup_kn_unlock(of->kn);
 
 	return 0;
-- 
cgit v1.2.3


From 0af6a48da481109affc4ea8295034f69993a91ef Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:24 -0700
Subject: x86/intel_rdt: Ensure RDT cleanup on exit

The RDT system's initialization does not have the corresponding exit
handling to ensure everything initialized on load is cleaned up also.

Introduce the cleanup routines that complement all initialization. This
includes the removal of a duplicate rdtgroup_init() declaration.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/a9e3a2bbd731d13915d2d7bf05d4f675b4fa109b.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.c          | 11 +++++++++++
 arch/x86/kernel/cpu/intel_rdt.h          |  3 +--
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c |  7 +++++++
 3 files changed, 19 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index ec4754f81cbd..abb71ac70443 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -859,6 +859,8 @@ static __init bool get_rdt_resources(void)
 	return (rdt_mon_capable || rdt_alloc_capable);
 }
 
+static enum cpuhp_state rdt_online;
+
 static int __init intel_rdt_late_init(void)
 {
 	struct rdt_resource *r;
@@ -880,6 +882,7 @@ static int __init intel_rdt_late_init(void)
 		cpuhp_remove_state(state);
 		return ret;
 	}
+	rdt_online = state;
 
 	for_each_alloc_capable_rdt_resource(r)
 		pr_info("Intel RDT %s allocation detected\n", r->name);
@@ -891,3 +894,11 @@ static int __init intel_rdt_late_init(void)
 }
 
 late_initcall(intel_rdt_late_init);
+
+static void __exit intel_rdt_exit(void)
+{
+	cpuhp_remove_state(rdt_online);
+	rdtgroup_exit();
+}
+
+__exitcall(intel_rdt_exit);
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index f245aaae514e..2b3f7619be48 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -209,6 +209,7 @@ extern struct list_head rdt_all_groups;
 extern int max_name_width, max_data_width;
 
 int __init rdtgroup_init(void);
+void __exit rdtgroup_exit(void);
 
 /**
  * struct rftype - describe each file in the resctrl file system
@@ -431,8 +432,6 @@ extern struct rdt_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
-int __init rdtgroup_init(void);
-
 enum {
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L3DATA,
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index f301919ae9b2..960066249374 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -2828,3 +2828,10 @@ cleanup_root:
 
 	return ret;
 }
+
+void __exit rdtgroup_exit(void)
+{
+	unregister_filesystem(&rdt_fs_type);
+	sysfs_remove_mount_point(fs_kobj, "resctrl");
+	kernfs_destroy_root(rdt_root);
+}
-- 
cgit v1.2.3


From 37707ec6cba6668f22a47016fdee612b0ff62fe9 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:25 -0700
Subject: x86/intel_rdt: Create resctrl debug area

In preparation for support of debugging of RDT sub features the user can
now enable a RDT debugfs region.

The debug area is always enabled when CONFIG_DEBUG_FS is set as advised in
http://lkml.kernel.org/r/20180523080501.GA6822@kroah.com

Also from same discussion in above linked email, no error checking on the
debugfs creation return value since code should not behave differently when
debugging passes or fails. Even on failure the returned value can be passed
safely to other debugfs calls.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/9f553faf30866a6317f1aaaa2fe9f92de66a10d2.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h          |  2 ++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 27 +++++++++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 2b3f7619be48..a97be4094fa5 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -432,6 +432,8 @@ extern struct rdt_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 DECLARE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
 
+extern struct dentry *debugfs_resctrl;
+
 enum {
 	RDT_RESOURCE_L3,
 	RDT_RESOURCE_L3DATA,
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 960066249374..bc52c593a87c 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -22,6 +22,7 @@
 
 #include <linux/cacheinfo.h>
 #include <linux/cpu.h>
+#include <linux/debugfs.h>
 #include <linux/fs.h>
 #include <linux/sysfs.h>
 #include <linux/kernfs.h>
@@ -56,6 +57,8 @@ static struct kernfs_node *kn_mondata;
 static struct seq_buf last_cmd_status;
 static char last_cmd_status_buf[512];
 
+struct dentry *debugfs_resctrl;
+
 void rdt_last_cmd_clear(void)
 {
 	lockdep_assert_held(&rdtgroup_mutex);
@@ -2819,6 +2822,29 @@ int __init rdtgroup_init(void)
 	if (ret)
 		goto cleanup_mountpoint;
 
+	/*
+	 * Adding the resctrl debugfs directory here may not be ideal since
+	 * it would let the resctrl debugfs directory appear on the debugfs
+	 * filesystem before the resctrl filesystem is mounted.
+	 * It may also be ok since that would enable debugging of RDT before
+	 * resctrl is mounted.
+	 * The reason why the debugfs directory is created here and not in
+	 * rdt_mount() is because rdt_mount() takes rdtgroup_mutex and
+	 * during the debugfs directory creation also &sb->s_type->i_mutex_key
+	 * (the lockdep class of inode->i_rwsem). Other filesystem
+	 * interactions (eg. SyS_getdents) have the lock ordering:
+	 * &sb->s_type->i_mutex_key --> &mm->mmap_sem
+	 * During mmap(), called with &mm->mmap_sem, the rdtgroup_mutex
+	 * is taken, thus creating dependency:
+	 * &mm->mmap_sem --> rdtgroup_mutex for the latter that can cause
+	 * issues considering the other two lock dependencies.
+	 * By creating the debugfs directory here we avoid a dependency
+	 * that may cause deadlock (even though file operations cannot
+	 * occur until the filesystem is mounted, but I do not know how to
+	 * tell lockdep that).
+	 */
+	debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
+
 	return 0;
 
 cleanup_mountpoint:
@@ -2831,6 +2857,7 @@ cleanup_root:
 
 void __exit rdtgroup_exit(void)
 {
+	debugfs_remove_recursive(debugfs_resctrl);
 	unregister_filesystem(&rdt_fs_type);
 	sysfs_remove_mount_point(fs_kobj, "resctrl");
 	kernfs_destroy_root(rdt_root);
-- 
cgit v1.2.3


From 443810fe6160542c78e24c66047edd7a3cc830c6 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:26 -0700
Subject: x86/intel_rdt: Create debugfs files for pseudo-locking testing

There is no simple yes/no test to determine if pseudo-locking was
successful. In order to test pseudo-locking we expose a debugfs file for
each pseudo-locked region that will record the latency of reading the
pseudo-locked memory at a stride of 32 bytes (hardcoded). These numbers
will give us an idea of locking was successful or not since they will
reflect cache hits and cache misses (hardware prefetching is disabled
during the test).

The new debugfs file "pseudo_lock_measure" will, when the
pseudo_lock_mem_latency tracepoint is enabled, record the latency of
accessing each cache line twice.

Kernel tracepoints offer us histograms (when CONFIG_HIST_TRIGGERS is
enabled) that is a simple way to visualize the memory access latency
and immediately see any cache misses. For example, the hist trigger
below before trigger of the measurement will display the memory access
latency and instances at each latency:
echo 'hist:keys=latency' > /sys/kernel/debug/tracing/events/resctrl/\
                           pseudo_lock_mem_latency/trigger
echo 1 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
echo 1 > /sys/kernel/debug/resctrl/<newlock>/pseudo_lock_measure
echo 0 > /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/enable
cat /sys/kernel/debug/tracing/events/resctrl/pseudo_lock_mem_latency/hist

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/6b2ea76181099d1b79ccfa7d3be24497ab2d1a45.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/Makefile                      |   1 +
 arch/x86/kernel/cpu/intel_rdt.h                   |   3 +
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c       | 176 +++++++++++++++++++++-
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h |  23 +++
 4 files changed, 202 insertions(+), 1 deletion(-)
 create mode 100644 arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h

diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index c4e02555563a..347137e80bf5 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32)		+= umc.o
 
 obj-$(CONFIG_INTEL_RDT)	+= intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_monitor.o
 obj-$(CONFIG_INTEL_RDT)	+= intel_rdt_ctrlmondata.o intel_rdt_pseudo_lock.o
+CFLAGS_intel_rdt_pseudo_lock.o = -I$(src)
 
 obj-$(CONFIG_X86_MCE)			+= mcheck/
 obj-$(CONFIG_MTRR)			+= mtrr/
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index a97be4094fa5..8a7102cfbec7 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -138,6 +138,8 @@ struct mongroup {
  * @line_size:		size of the cache lines
  * @size:		size of pseudo-locked region in bytes
  * @kmem:		the kernel memory associated with pseudo-locked region
+ * @debugfs_dir:	pointer to this region's directory in the debugfs
+ *			filesystem
  */
 struct pseudo_lock_region {
 	struct rdt_resource	*r;
@@ -149,6 +151,7 @@ struct pseudo_lock_region {
 	unsigned int		line_size;
 	unsigned int		size;
 	void			*kmem;
+	struct dentry		*debugfs_dir;
 };
 
 /**
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 22387af30a9e..5851f3e20742 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -14,6 +14,7 @@
 #include <linux/cacheinfo.h>
 #include <linux/cpu.h>
 #include <linux/cpumask.h>
+#include <linux/debugfs.h>
 #include <linux/kthread.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -21,6 +22,9 @@
 #include <asm/intel_rdt_sched.h>
 #include "intel_rdt.h"
 
+#define CREATE_TRACE_POINTS
+#include "intel_rdt_pseudo_lock_event.h"
+
 /*
  * MSR_MISC_FEATURE_CONTROL register enables the modification of hardware
  * prefetcher state. Details about this register can be found in the MSR
@@ -176,6 +180,7 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
 		plr->d->plr = NULL;
 	plr->d = NULL;
 	plr->cbm = 0;
+	plr->debugfs_dir = NULL;
 }
 
 /**
@@ -692,6 +697,161 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 	return ret;
 }
 
+/**
+ * measure_cycles_lat_fn - Measure cycle latency to read pseudo-locked memory
+ * @_plr: pseudo-lock region to measure
+ *
+ * There is no deterministic way to test if a memory region is cached. One
+ * way is to measure how long it takes to read the memory, the speed of
+ * access is a good way to learn how close to the cpu the data was. Even
+ * more, if the prefetcher is disabled and the memory is read at a stride
+ * of half the cache line, then a cache miss will be easy to spot since the
+ * read of the first half would be significantly slower than the read of
+ * the second half.
+ *
+ * Return: 0. Waiter on waitqueue will be woken on completion.
+ */
+static int measure_cycles_lat_fn(void *_plr)
+{
+	struct pseudo_lock_region *plr = _plr;
+	unsigned long i;
+	u64 start, end;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use a regular
+	 * variable to ensure we always use a valid pointer to access memory.
+	 * The cost is that accessing this pointer, which could be in
+	 * cache, will be included in the measurement of memory read latency.
+	 */
+	void *mem_r;
+#else
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	local_irq_disable();
+	/*
+	 * The wrmsr call may be reordered with the assignment below it.
+	 * Call wrmsr as directly as possible to avoid tracing clobbering
+	 * local register variable used for memory pointer.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	mem_r = plr->kmem;
+	/*
+	 * Dummy execute of the time measurement to load the needed
+	 * instructions into the L1 instruction cache.
+	 */
+	start = rdtsc_ordered();
+	for (i = 0; i < plr->size; i += 32) {
+		start = rdtsc_ordered();
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			     :
+			     : "r" (mem_r), "r" (i)
+			     : "%eax", "memory");
+		end = rdtsc_ordered();
+		trace_pseudo_lock_mem_latency((u32)(end - start));
+	}
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
+/**
+ * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
+ *
+ * The measurement of latency to access a pseudo-locked region should be
+ * done from a cpu that is associated with that pseudo-locked region.
+ * Determine which cpu is associated with this region and start a thread on
+ * that cpu to perform the measurement, wait for that thread to complete.
+ *
+ * Return: 0 on success, <0 on failure
+ */
+static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp)
+{
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+	struct task_struct *thread;
+	unsigned int cpu;
+	int ret;
+
+	cpus_read_lock();
+	mutex_lock(&rdtgroup_mutex);
+
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	plr->thread_done = 0;
+	cpu = cpumask_first(&plr->d->cpu_mask);
+	if (!cpu_online(cpu)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
+					cpu_to_node(cpu),
+					"pseudo_lock_measure/%u", cpu);
+	if (IS_ERR(thread)) {
+		ret = PTR_ERR(thread);
+		goto out;
+	}
+	kthread_bind(thread, cpu);
+	wake_up_process(thread);
+
+	ret = wait_event_interruptible(plr->lock_thread_wq,
+				       plr->thread_done == 1);
+	if (ret < 0)
+		goto out;
+
+	ret = 0;
+
+out:
+	mutex_unlock(&rdtgroup_mutex);
+	cpus_read_unlock();
+	return ret;
+}
+
+static ssize_t pseudo_lock_measure_trigger(struct file *file,
+					   const char __user *user_buf,
+					   size_t count, loff_t *ppos)
+{
+	struct rdtgroup *rdtgrp = file->private_data;
+	size_t buf_size;
+	char buf[32];
+	int ret;
+	bool bv;
+
+	buf_size = min(count, (sizeof(buf) - 1));
+	if (copy_from_user(buf, user_buf, buf_size))
+		return -EFAULT;
+
+	buf[buf_size] = '\0';
+	ret = strtobool(buf, &bv);
+	if (ret == 0 && bv) {
+		ret = debugfs_file_get(file->f_path.dentry);
+		if (ret)
+			return ret;
+		ret = pseudo_lock_measure_cycles(rdtgrp);
+		if (ret == 0)
+			ret = count;
+		debugfs_file_put(file->f_path.dentry);
+	}
+
+	return ret;
+}
+
+static const struct file_operations pseudo_measure_fops = {
+	.write = pseudo_lock_measure_trigger,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
 /**
  * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
  * @rdtgrp: resource group to which pseudo-lock region belongs
@@ -747,6 +907,15 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		goto out_region;
 	}
 
+	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
+		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
+						      debugfs_resctrl);
+		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
+			debugfs_create_file("pseudo_lock_measure", 0200,
+					    plr->debugfs_dir, rdtgrp,
+					    &pseudo_measure_fops);
+	}
+
 	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
 	closid_free(rdtgrp->closid);
 	ret = 0;
@@ -774,12 +943,17 @@ out:
  */
 void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
 {
-	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP)
+	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 		/*
 		 * Default group cannot be a pseudo-locked region so we can
 		 * free closid here.
 		 */
 		closid_free(rdtgrp->closid);
+		goto free;
+	}
+
+	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
 
+free:
 	pseudo_lock_free(rdtgrp);
 }
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
new file mode 100644
index 000000000000..3cd0fa27d5fe
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM resctrl
+
+#if !defined(_TRACE_PSEUDO_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_PSEUDO_LOCK_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(pseudo_lock_mem_latency,
+	    TP_PROTO(u32 latency),
+	    TP_ARGS(latency),
+	    TP_STRUCT__entry(__field(u32, latency)),
+	    TP_fast_assign(__entry->latency = latency),
+	    TP_printk("latency=%u", __entry->latency)
+	   );
+
+#endif /* _TRACE_PSEUDO_LOCK_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#define TRACE_INCLUDE_FILE intel_rdt_pseudo_lock_event
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From 33bfdeaa768a2b53abc7b8c0f3cae272770d31d4 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:40 -0700
Subject: net: pch_gbe: Remove unused copybreak parameter

The pch_gbe driver includes a 'copybreak' parameter which appears to
have been copied from the e1000e driver but is entirely unused. Remove
the dead code.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 34a1581eda95..044a7561752c 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -34,7 +34,6 @@ const char pch_driver_version[] = DRV_VERSION;
 #define PCH_GBE_DMA_ALIGN		0
 #define PCH_GBE_DMA_PADDING		2
 #define PCH_GBE_WATCHDOG_PERIOD		(5 * HZ)	/* watchdog time */
-#define PCH_GBE_COPYBREAK_DEFAULT	256
 #define PCH_GBE_PCI_BAR			1
 #define PCH_GBE_RESERVE_MEMORY		0x200000	/* 2MB */
 
@@ -113,8 +112,6 @@ const char pch_driver_version[] = DRV_VERSION;
 
 #define MINNOW_PHY_RESET_GPIO		13
 
-static unsigned int copybreak __read_mostly = PCH_GBE_COPYBREAK_DEFAULT;
-
 static int pch_gbe_mdio_read(struct net_device *netdev, int addr, int reg);
 static void pch_gbe_mdio_write(struct net_device *netdev, int addr, int reg,
 			       int data);
@@ -2784,14 +2781,6 @@ static int __init pch_gbe_init_module(void)
 
 	pr_info("EG20T PCH Gigabit Ethernet Driver - version %s\n",DRV_VERSION);
 	ret = pci_register_driver(&pch_gbe_driver);
-	if (copybreak != PCH_GBE_COPYBREAK_DEFAULT) {
-		if (copybreak == 0) {
-			pr_info("copybreak disabled\n");
-		} else {
-			pr_info("copybreak enabled for packets <= %u bytes\n",
-				copybreak);
-		}
-	}
 	return ret;
 }
 
@@ -2809,8 +2798,4 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
 MODULE_DEVICE_TABLE(pci, pch_gbe_pcidev_id);
 
-module_param(copybreak, uint, 0644);
-MODULE_PARM_DESC(copybreak,
-	"Maximum size of packet that is copied to a new buffer on receive");
-
 /* pch_gbe_main.c */
-- 
cgit v1.2.3


From ac6c0e0aa49ff8cb26573fe31403800de98218a1 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:41 -0700
Subject: net: pch_gbe: Remove power_{up,down}_phy HAL abstraction

For some reason the pch_gbe driver contains a struct pch_gbe_functions
with pointers used by a HAL abstraction layer, even though there is only
one implementation of each function.

This patch removes the power_up_phy & power_down_phy abstractions in
favor of calling pch_phy_power_up & pch_phy_power_down directly.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h    |  4 ----
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c    | 22 ----------------------
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h    |  2 --
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c   | 12 ++++++------
 4 files changed, 6 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 697e29dd4bd3..8dc40faef720 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -336,8 +336,6 @@ struct pch_gbe_hw;
  * @write_phy_reg:	for pch_gbe_hal_write_phy_reg
  * @reset_phy:		for pch_gbe_hal_phy_hw_reset
  * @sw_reset_phy:	for pch_gbe_hal_phy_sw_reset
- * @power_up_phy:	for pch_gbe_hal_power_up_phy
- * @power_down_phy:	for pch_gbe_hal_power_down_phy
  * @read_mac_addr:	for pch_gbe_hal_read_mac_addr
  */
 struct pch_gbe_functions {
@@ -347,8 +345,6 @@ struct pch_gbe_functions {
 	s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16);
 	void (*reset_phy) (struct pch_gbe_hw *);
 	void (*sw_reset_phy) (struct pch_gbe_hw *);
-	void (*power_up_phy) (struct pch_gbe_hw *hw);
-	void (*power_down_phy) (struct pch_gbe_hw *hw);
 	s32 (*read_mac_addr) (struct pch_gbe_hw *);
 };
 
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
index 51250363566b..d66933b68934 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
@@ -90,8 +90,6 @@ static const struct pch_gbe_functions pch_gbe_ops = {
 	.write_phy_reg     = pch_gbe_phy_write_reg_miic,
 	.reset_phy         = pch_gbe_phy_hw_reset,
 	.sw_reset_phy      = pch_gbe_phy_sw_reset,
-	.power_up_phy      = pch_gbe_phy_power_up,
-	.power_down_phy    = pch_gbe_phy_power_down,
 	.read_mac_addr     = pch_gbe_mac_read_mac_addr
 };
 
@@ -240,23 +238,3 @@ s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw)
 	}
 	return hw->func->read_mac_addr(hw);
 }
-
-/**
- * pch_gbe_hal_power_up_phy - Power up PHY
- * @hw:	Pointer to the HW structure
- */
-void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw)
-{
-	if (hw->func->power_up_phy)
-		hw->func->power_up_phy(hw);
-}
-
-/**
- * pch_gbe_hal_power_down_phy - Power down PHY
- * @hw:	Pointer to the HW structure
- */
-void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw)
-{
-	if (hw->func->power_down_phy)
-		hw->func->power_down_phy(hw);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
index 91ce07c8306c..be2f202c26c4 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
@@ -29,7 +29,5 @@ s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data);
 void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw);
 void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw);
 s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw);
-void pch_gbe_hal_power_up_phy(struct pch_gbe_hw *hw);
-void pch_gbe_hal_power_down_phy(struct pch_gbe_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 044a7561752c..13fc828c7fd3 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2072,7 +2072,7 @@ static int pch_gbe_open(struct net_device *netdev)
 	err = pch_gbe_setup_rx_resources(adapter, adapter->rx_ring);
 	if (err)
 		goto err_setup_rx;
-	pch_gbe_hal_power_up_phy(hw);
+	pch_gbe_phy_power_up(hw);
 	err = pch_gbe_up(adapter);
 	if (err)
 		goto err_up;
@@ -2081,7 +2081,7 @@ static int pch_gbe_open(struct net_device *netdev)
 
 err_up:
 	if (!adapter->wake_up_evt)
-		pch_gbe_hal_power_down_phy(hw);
+		pch_gbe_phy_power_down(hw);
 	pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
 err_setup_rx:
 	pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
@@ -2104,7 +2104,7 @@ static int pch_gbe_stop(struct net_device *netdev)
 
 	pch_gbe_down(adapter);
 	if (!adapter->wake_up_evt)
-		pch_gbe_hal_power_down_phy(hw);
+		pch_gbe_phy_power_down(hw);
 	pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
 	pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
 	return 0;
@@ -2434,7 +2434,7 @@ static pci_ers_result_t pch_gbe_io_slot_reset(struct pci_dev *pdev)
 	}
 	pci_set_master(pdev);
 	pci_enable_wake(pdev, PCI_D0, 0);
-	pch_gbe_hal_power_up_phy(hw);
+	pch_gbe_phy_power_up(hw);
 	pch_gbe_reset(adapter);
 	/* Clear wake up status */
 	pch_gbe_mac_set_wol_event(hw, 0);
@@ -2479,7 +2479,7 @@ static int __pch_gbe_suspend(struct pci_dev *pdev)
 		pch_gbe_mac_set_wol_event(hw, wufc);
 		pci_disable_device(pdev);
 	} else {
-		pch_gbe_hal_power_down_phy(hw);
+		pch_gbe_phy_power_down(hw);
 		pch_gbe_mac_set_wol_event(hw, wufc);
 		pci_disable_device(pdev);
 	}
@@ -2508,7 +2508,7 @@ static int pch_gbe_resume(struct device *device)
 		return err;
 	}
 	pci_set_master(pdev);
-	pch_gbe_hal_power_up_phy(hw);
+	pch_gbe_phy_power_up(hw);
 	pch_gbe_reset(adapter);
 	/* Clear wake on lan control and status */
 	pch_gbe_mac_set_wol_event(hw, 0);
-- 
cgit v1.2.3


From 9c020d7b0525d3b913a85d055a34aca64d852be5 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:42 -0700
Subject: net: pch_gbe: Remove read_mac_addr HAL abstraction

For some reason the pch_gbe driver contains a struct pch_gbe_functions
with pointers used by a HAL abstraction layer, even though there is only
one implementation of each function.

This patch removes the read_mac_addr abstraction in favor of calling
pch_gbe_mac_read_mac_addr directly. Since this is defined in the same
translation unit as all of its callers, we can make it static & remove
it from the pch_gbe.h header.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h      |  3 ---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c  | 19 -------------------
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h  |  1 -
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c |  4 ++--
 4 files changed, 2 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 8dc40faef720..5dbfcd55efa8 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -336,7 +336,6 @@ struct pch_gbe_hw;
  * @write_phy_reg:	for pch_gbe_hal_write_phy_reg
  * @reset_phy:		for pch_gbe_hal_phy_hw_reset
  * @sw_reset_phy:	for pch_gbe_hal_phy_sw_reset
- * @read_mac_addr:	for pch_gbe_hal_read_mac_addr
  */
 struct pch_gbe_functions {
 	void (*get_bus_info) (struct pch_gbe_hw *);
@@ -345,7 +344,6 @@ struct pch_gbe_functions {
 	s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16);
 	void (*reset_phy) (struct pch_gbe_hw *);
 	void (*sw_reset_phy) (struct pch_gbe_hw *);
-	s32 (*read_mac_addr) (struct pch_gbe_hw *);
 };
 
 /**
@@ -676,7 +674,6 @@ void pch_gbe_set_ethtool_ops(struct net_device *netdev);
 
 /* pch_gbe_mac.c */
 s32 pch_gbe_mac_force_mac_fc(struct pch_gbe_hw *hw);
-s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw);
 u16 pch_gbe_mac_ctrl_miim(struct pch_gbe_hw *hw, u32 addr, u32 dir, u32 reg,
 			  u16 data);
 #endif /* _PCH_GBE_H_ */
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
index d66933b68934..3c6e009955ab 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
@@ -90,7 +90,6 @@ static const struct pch_gbe_functions pch_gbe_ops = {
 	.write_phy_reg     = pch_gbe_phy_write_reg_miic,
 	.reset_phy         = pch_gbe_phy_hw_reset,
 	.sw_reset_phy      = pch_gbe_phy_sw_reset,
-	.read_mac_addr     = pch_gbe_mac_read_mac_addr
 };
 
 /**
@@ -220,21 +219,3 @@ void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw)
 	}
 	hw->func->sw_reset_phy(hw);
 }
-
-/**
- * pch_gbe_hal_read_mac_addr - Reads MAC address
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:	Successfully
- *	ENOSYS:	Function is not registered
- */
-s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->read_mac_addr) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return -ENOSYS;
-	}
-	return hw->func->read_mac_addr(hw);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
index be2f202c26c4..13fcdfb4a94d 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
@@ -28,6 +28,5 @@ s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 *data);
 s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data);
 void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw);
 void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_read_mac_addr(struct pch_gbe_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 13fc828c7fd3..fc5079fa01e8 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -287,7 +287,7 @@ static inline void pch_gbe_mac_load_mac_addr(struct pch_gbe_hw *hw)
  * Returns:
  *	0:			Successful.
  */
-s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
+static s32 pch_gbe_mac_read_mac_addr(struct pch_gbe_hw *hw)
 {
 	struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
 	u32  adr1a, adr1b;
@@ -2627,7 +2627,7 @@ static int pch_gbe_probe(struct pci_dev *pdev,
 	pch_gbe_hal_get_bus_info(&adapter->hw);
 
 	/* Read the MAC address. and store to the private data */
-	ret = pch_gbe_hal_read_mac_addr(&adapter->hw);
+	ret = pch_gbe_mac_read_mac_addr(&adapter->hw);
 	if (ret) {
 		dev_err(&pdev->dev, "MAC address Read Error\n");
 		goto err_free_adapter;
-- 
cgit v1.2.3


From 66dde2b0aa7013dbaf9d0e18ff24360877312a79 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:43 -0700
Subject: net: pch_gbe: Remove sw_reset_phy HAL abstraction

For some reason the pch_gbe driver contains a struct pch_gbe_functions
with pointers used by a HAL abstraction layer, even though there is only
one implementation of each function.

This patch removes the sw_reset_phy abstraction, which it turns out is
never even used. Its one implementation, which is already called
directly within the same translation unit, can therefore be made static
and removed from the pch_gbe_phy.h header.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h     |  2 --
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c | 16 ----------------
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h |  1 -
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c |  2 +-
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h |  1 -
 5 files changed, 1 insertion(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 5dbfcd55efa8..47ee7428c3d3 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -335,7 +335,6 @@ struct pch_gbe_hw;
  * @read_phy_reg:	for pch_gbe_hal_read_phy_reg
  * @write_phy_reg:	for pch_gbe_hal_write_phy_reg
  * @reset_phy:		for pch_gbe_hal_phy_hw_reset
- * @sw_reset_phy:	for pch_gbe_hal_phy_sw_reset
  */
 struct pch_gbe_functions {
 	void (*get_bus_info) (struct pch_gbe_hw *);
@@ -343,7 +342,6 @@ struct pch_gbe_functions {
 	s32 (*read_phy_reg) (struct pch_gbe_hw *, u32, u16 *);
 	s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16);
 	void (*reset_phy) (struct pch_gbe_hw *);
-	void (*sw_reset_phy) (struct pch_gbe_hw *);
 };
 
 /**
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
index 3c6e009955ab..e1ecfb076029 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
@@ -89,7 +89,6 @@ static const struct pch_gbe_functions pch_gbe_ops = {
 	.read_phy_reg      = pch_gbe_phy_read_reg_miic,
 	.write_phy_reg     = pch_gbe_phy_write_reg_miic,
 	.reset_phy         = pch_gbe_phy_hw_reset,
-	.sw_reset_phy      = pch_gbe_phy_sw_reset,
 };
 
 /**
@@ -204,18 +203,3 @@ void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw)
 	}
 	hw->func->reset_phy(hw);
 }
-
-/**
- * pch_gbe_hal_phy_sw_reset - Soft PHY reset
- * @hw:	    Pointer to the HW structure
- */
-void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->sw_reset_phy) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return;
-	}
-	hw->func->sw_reset_phy(hw);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
index 13fcdfb4a94d..aa802f670055 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
@@ -27,6 +27,5 @@ s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw);
 s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 *data);
 s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data);
 void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw);
-void pch_gbe_hal_phy_sw_reset(struct pch_gbe_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
index a5cad5ea9436..6b35b573beef 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.c
@@ -184,7 +184,7 @@ s32 pch_gbe_phy_write_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 data)
  * pch_gbe_phy_sw_reset - PHY software reset
  * @hw:	            Pointer to the HW structure
  */
-void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw)
+static void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw)
 {
 	u16 phy_ctrl;
 
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
index 95ad0151ad02..efb955be8cac 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
@@ -26,7 +26,6 @@
 s32 pch_gbe_phy_get_id(struct pch_gbe_hw *hw);
 s32 pch_gbe_phy_read_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 *data);
 s32 pch_gbe_phy_write_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 data);
-void pch_gbe_phy_sw_reset(struct pch_gbe_hw *hw);
 void pch_gbe_phy_hw_reset(struct pch_gbe_hw *hw);
 void pch_gbe_phy_power_up(struct pch_gbe_hw *hw);
 void pch_gbe_phy_power_down(struct pch_gbe_hw *hw);
-- 
cgit v1.2.3


From 7dbe38aed0ba01e9557621d7e6d59c5b92decead Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:44 -0700
Subject: net: pch_gbe: Remove reset_phy HAL abstraction

For some reason the pch_gbe driver contains a struct pch_gbe_functions
with pointers used by a HAL abstraction layer, even though there is only
one implementation of each function.

This patch removes the reset_phy abstraction in favor of calling
pch_gbe_phy_hw_reset directly.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h      |  2 --
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c  | 16 ----------------
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h  |  1 -
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c |  4 ++--
 4 files changed, 2 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 47ee7428c3d3..02e8da2b6ad2 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -334,14 +334,12 @@ struct pch_gbe_hw;
  * @init_hw:		for pch_gbe_hal_init_hw
  * @read_phy_reg:	for pch_gbe_hal_read_phy_reg
  * @write_phy_reg:	for pch_gbe_hal_write_phy_reg
- * @reset_phy:		for pch_gbe_hal_phy_hw_reset
  */
 struct pch_gbe_functions {
 	void (*get_bus_info) (struct pch_gbe_hw *);
 	s32 (*init_hw) (struct pch_gbe_hw *);
 	s32 (*read_phy_reg) (struct pch_gbe_hw *, u32, u16 *);
 	s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16);
-	void (*reset_phy) (struct pch_gbe_hw *);
 };
 
 /**
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
index e1ecfb076029..6fe09af545e8 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
@@ -88,7 +88,6 @@ static const struct pch_gbe_functions pch_gbe_ops = {
 	.init_hw           = pch_gbe_plat_init_hw,
 	.read_phy_reg      = pch_gbe_phy_read_reg_miic,
 	.write_phy_reg     = pch_gbe_phy_write_reg_miic,
-	.reset_phy         = pch_gbe_phy_hw_reset,
 };
 
 /**
@@ -188,18 +187,3 @@ s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset,
 		return 0;
 	return hw->func->write_phy_reg(hw, offset, data);
 }
-
-/**
- * pch_gbe_hal_phy_hw_reset - Hard PHY reset
- * @hw:	    Pointer to the HW structure
- */
-void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->reset_phy) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return;
-	}
-	hw->func->reset_phy(hw);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
index aa802f670055..96540f6648b5 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
@@ -26,6 +26,5 @@ void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw);
 s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw);
 s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 *data);
 s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data);
-void pch_gbe_hal_phy_hw_reset(struct pch_gbe_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index fc5079fa01e8..175d6608bdb9 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2538,7 +2538,7 @@ static void pch_gbe_remove(struct pci_dev *pdev)
 	cancel_work_sync(&adapter->reset_task);
 	unregister_netdev(netdev);
 
-	pch_gbe_hal_phy_hw_reset(&adapter->hw);
+	pch_gbe_phy_hw_reset(&adapter->hw);
 
 	free_netdev(netdev);
 }
@@ -2674,7 +2674,7 @@ static int pch_gbe_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_adapter:
-	pch_gbe_hal_phy_hw_reset(&adapter->hw);
+	pch_gbe_phy_hw_reset(&adapter->hw);
 err_free_netdev:
 	free_netdev(netdev);
 	return ret;
-- 
cgit v1.2.3


From c96a0f74312ba7a640b50257d58085f372fff352 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:45 -0700
Subject: net: pch_gbe: Remove {read,write}_phy_reg HAL abstraction

For some reason the pch_gbe driver contains a struct pch_gbe_functions
with pointers used by a HAL abstraction layer, even though there is only
one implementation of each function.

This patch removes the read_phy_reg & write_phy_reg abstractions in
favor of calling pch_gbe_phy_read_reg_miic & pch_gbe_phy_write_reg_miic
directly.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h    |  4 ---
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c    | 36 ----------------------
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h    |  2 --
 .../ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c    |  4 +--
 4 files changed, 2 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 02e8da2b6ad2..728e876bffc6 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -332,14 +332,10 @@ struct pch_gbe_hw;
  * struct  pch_gbe_functions - HAL APi function pointer
  * @get_bus_info:	for pch_gbe_hal_get_bus_info
  * @init_hw:		for pch_gbe_hal_init_hw
- * @read_phy_reg:	for pch_gbe_hal_read_phy_reg
- * @write_phy_reg:	for pch_gbe_hal_write_phy_reg
  */
 struct pch_gbe_functions {
 	void (*get_bus_info) (struct pch_gbe_hw *);
 	s32 (*init_hw) (struct pch_gbe_hw *);
-	s32 (*read_phy_reg) (struct pch_gbe_hw *, u32, u16 *);
-	s32 (*write_phy_reg) (struct pch_gbe_hw *, u32, u16);
 };
 
 /**
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
index 6fe09af545e8..484be4225352 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
@@ -86,8 +86,6 @@ static s32 pch_gbe_plat_init_hw(struct pch_gbe_hw *hw)
 static const struct pch_gbe_functions pch_gbe_ops = {
 	.get_bus_info      = pch_gbe_plat_get_bus_info,
 	.init_hw           = pch_gbe_plat_init_hw,
-	.read_phy_reg      = pch_gbe_phy_read_reg_miic,
-	.write_phy_reg     = pch_gbe_phy_write_reg_miic,
 };
 
 /**
@@ -153,37 +151,3 @@ s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw)
 	}
 	return hw->func->init_hw(hw);
 }
-
-/**
- * pch_gbe_hal_read_phy_reg - Reads PHY register
- * @hw:	    Pointer to the HW structure
- * @offset: The register to read
- * @data:   The buffer to store the 16-bit read.
- * Returns:
- *	0:	Successfully
- *	Negative value:	Failed
- */
-s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset,
-					u16 *data)
-{
-	if (!hw->func->read_phy_reg)
-		return 0;
-	return hw->func->read_phy_reg(hw, offset, data);
-}
-
-/**
- * pch_gbe_hal_write_phy_reg - Writes PHY register
- * @hw:	    Pointer to the HW structure
- * @offset: The register to read
- * @data:   The value to write.
- * Returns:
- *	0:	Successfully
- *	Negative value:	Failed
- */
-s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset,
-					u16 data)
-{
-	if (!hw->func->write_phy_reg)
-		return 0;
-	return hw->func->write_phy_reg(hw, offset, data);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
index 96540f6648b5..9cd19605f4ff 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
@@ -24,7 +24,5 @@
 s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw);
 void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw);
 s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_read_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 *data);
-s32 pch_gbe_hal_write_phy_reg(struct pch_gbe_hw *hw, u32 offset, u16 data);
 
 #endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index 731ce1e419e4..da39d771ad87 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -125,7 +125,7 @@ static int pch_gbe_set_link_ksettings(struct net_device *netdev,
 	u32 advertising;
 	int ret;
 
-	pch_gbe_hal_write_phy_reg(hw, MII_BMCR, BMCR_RESET);
+	pch_gbe_phy_write_reg_miic(hw, MII_BMCR, BMCR_RESET);
 
 	memcpy(&copy_ecmd, ecmd, sizeof(*ecmd));
 
@@ -204,7 +204,7 @@ static void pch_gbe_get_regs(struct net_device *netdev,
 		*regs_buff++ = ioread32(&hw->reg->INT_ST + i);
 	/* PHY register */
 	for (i = 0; i < PCH_GBE_PHY_REGS_LEN; i++) {
-		pch_gbe_hal_read_phy_reg(&adapter->hw, i, &tmp);
+		pch_gbe_phy_read_reg_miic(&adapter->hw, i, &tmp);
 		*regs_buff++ = tmp;
 	}
 }
-- 
cgit v1.2.3


From 3ef594b0e465c4dd7b1ea7736dfc4bb80c53e33d Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:46 -0700
Subject: net: pch_gbe: Remove init_hw HAL abstraction

For some reason the pch_gbe driver contains a struct pch_gbe_functions
with pointers used by a HAL abstraction layer, even though there is only
one implementation of each function.

This patch removes the init_hw abstraction in favor of inlining its
single implementation (pch_gbe_plat_init_hw) into its single caller
(pch_gbe_reset).

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h    |  2 -
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c    | 45 ----------------------
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h    |  1 -
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c   | 19 +++++++--
 4 files changed, 15 insertions(+), 52 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 728e876bffc6..2e824baff9d7 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -331,11 +331,9 @@ struct pch_gbe_hw;
 /**
  * struct  pch_gbe_functions - HAL APi function pointer
  * @get_bus_info:	for pch_gbe_hal_get_bus_info
- * @init_hw:		for pch_gbe_hal_init_hw
  */
 struct pch_gbe_functions {
 	void (*get_bus_info) (struct pch_gbe_hw *);
-	s32 (*init_hw) (struct pch_gbe_hw *);
 };
 
 /**
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
index 484be4225352..03fbd4752d4f 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
@@ -57,35 +57,8 @@ static void pch_gbe_plat_get_bus_info(struct pch_gbe_hw *hw)
 	hw->bus.width = pch_gbe_bus_width_pcie_x1;
 }
 
-/**
- * pch_gbe_plat_init_hw - Initialize hardware
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:		Successfully
- *	Negative value:	Failed-EBUSY
- */
-static s32 pch_gbe_plat_init_hw(struct pch_gbe_hw *hw)
-{
-	s32 ret_val;
-
-	ret_val = pch_gbe_phy_get_id(hw);
-	if (ret_val) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n");
-		return ret_val;
-	}
-	pch_gbe_phy_init_setting(hw);
-	/* Setup Mac interface option RGMII */
-#ifdef PCH_GBE_MAC_IFOP_RGMII
-	pch_gbe_phy_set_rgmii(hw);
-#endif
-	return ret_val;
-}
-
 static const struct pch_gbe_functions pch_gbe_ops = {
 	.get_bus_info      = pch_gbe_plat_get_bus_info,
-	.init_hw           = pch_gbe_plat_init_hw,
 };
 
 /**
@@ -133,21 +106,3 @@ void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw)
 	}
 	hw->func->get_bus_info(hw);
 }
-
-/**
- * pch_gbe_hal_init_hw - Initialize hardware
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:	Successfully
- *	ENOSYS:	Function is not registered
- */
-s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->init_hw) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return -ENOSYS;
-	}
-	return hw->func->init_hw(hw);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
index 9cd19605f4ff..56cae9cfb5c5 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
@@ -23,6 +23,5 @@
 
 s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw);
 void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw);
-s32 pch_gbe_hal_init_hw(struct pch_gbe_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 175d6608bdb9..9297a94df999 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -760,14 +760,25 @@ void pch_gbe_reinit_locked(struct pch_gbe_adapter *adapter)
 void pch_gbe_reset(struct pch_gbe_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
+	struct pch_gbe_hw *hw = &adapter->hw;
+	s32 ret_val;
 
-	pch_gbe_mac_reset_hw(&adapter->hw);
+	pch_gbe_mac_reset_hw(hw);
 	/* reprogram multicast address register after reset */
 	pch_gbe_set_multi(netdev);
 	/* Setup the receive address. */
-	pch_gbe_mac_init_rx_addrs(&adapter->hw, PCH_GBE_MAR_ENTRIES);
-	if (pch_gbe_hal_init_hw(&adapter->hw))
-		netdev_err(netdev, "Hardware Error\n");
+	pch_gbe_mac_init_rx_addrs(hw, PCH_GBE_MAR_ENTRIES);
+
+	ret_val = pch_gbe_phy_get_id(hw);
+	if (ret_val) {
+		netdev_err(adapter->netdev, "pch_gbe_phy_get_id error\n");
+		return;
+	}
+	pch_gbe_phy_init_setting(hw);
+	/* Setup Mac interface option RGMII */
+#ifdef PCH_GBE_MAC_IFOP_RGMII
+	pch_gbe_phy_set_rgmii(hw);
+#endif
 }
 
 /**
-- 
cgit v1.2.3


From b02c38a23a5a308466d6cf87895ef16b6fa3306c Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:47 -0700
Subject: net: pch_gbe: Remove get_bus_info HAL abstraction

For some reason the pch_gbe driver contains a struct pch_gbe_functions
with pointers used by a HAL abstraction layer, even though there is only
one implementation of each function.

This patch removes the get_bus_info abstraction. Its single
implementation (pch_gbe_plat_get_bus_info) only sets values within a
struct pch_gbe_bus_info which is never used, so we simply remove the
call to it in pch_gbe_probe & remove struct pch_gbe_bus_info entirely.

Now that struct pch_gbe_functions is empty we remove it entirely too.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h    | 23 ---------
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c    | 58 ----------------------
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h    |  1 -
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c   |  1 -
 4 files changed, 83 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
index 2e824baff9d7..44c2f291e766 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe.h
@@ -326,16 +326,6 @@ struct pch_gbe_regs {
 #define PCH_GBE_FC_FULL			3
 #define PCH_GBE_FC_DEFAULT		PCH_GBE_FC_FULL
 
-
-struct pch_gbe_hw;
-/**
- * struct  pch_gbe_functions - HAL APi function pointer
- * @get_bus_info:	for pch_gbe_hal_get_bus_info
- */
-struct pch_gbe_functions {
-	void (*get_bus_info) (struct pch_gbe_hw *);
-};
-
 /**
  * struct pch_gbe_mac_info - MAC information
  * @addr[6]:		Store the MAC address
@@ -376,17 +366,6 @@ struct pch_gbe_phy_info {
 	u16 autoneg_advertised;
 };
 
-/*!
- * @ingroup Gigabit Ether driver Layer
- * @struct  pch_gbe_bus_info
- * @brief   Bus information
- */
-struct pch_gbe_bus_info {
-	u8 type;
-	u8 speed;
-	u8 width;
-};
-
 /*!
  * @ingroup Gigabit Ether driver Layer
  * @struct  pch_gbe_hw
@@ -398,10 +377,8 @@ struct pch_gbe_hw {
 	struct pch_gbe_regs  __iomem *reg;
 	spinlock_t miim_lock;
 
-	const struct pch_gbe_functions *func;
 	struct pch_gbe_mac_info mac;
 	struct pch_gbe_phy_info phy;
-	struct pch_gbe_bus_info bus;
 };
 
 /**
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
index 03fbd4752d4f..89c0db27b797 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
@@ -20,47 +20,6 @@
 #include "pch_gbe_phy.h"
 #include "pch_gbe_api.h"
 
-/* bus type values */
-#define pch_gbe_bus_type_unknown	0
-#define pch_gbe_bus_type_pci		1
-#define pch_gbe_bus_type_pcix		2
-#define pch_gbe_bus_type_pci_express	3
-#define pch_gbe_bus_type_reserved	4
-
-/* bus speed values */
-#define pch_gbe_bus_speed_unknown	0
-#define pch_gbe_bus_speed_33		1
-#define pch_gbe_bus_speed_66		2
-#define pch_gbe_bus_speed_100		3
-#define pch_gbe_bus_speed_120		4
-#define pch_gbe_bus_speed_133		5
-#define pch_gbe_bus_speed_2500		6
-#define pch_gbe_bus_speed_reserved	7
-
-/* bus width values */
-#define pch_gbe_bus_width_unknown	0
-#define pch_gbe_bus_width_pcie_x1	1
-#define pch_gbe_bus_width_pcie_x2	2
-#define pch_gbe_bus_width_pcie_x4	4
-#define pch_gbe_bus_width_32		5
-#define pch_gbe_bus_width_64		6
-#define pch_gbe_bus_width_reserved	7
-
-/**
- * pch_gbe_plat_get_bus_info - Obtain bus information for adapter
- * @hw:	Pointer to the HW structure
- */
-static void pch_gbe_plat_get_bus_info(struct pch_gbe_hw *hw)
-{
-	hw->bus.type  = pch_gbe_bus_type_pci_express;
-	hw->bus.speed = pch_gbe_bus_speed_2500;
-	hw->bus.width = pch_gbe_bus_width_pcie_x1;
-}
-
-static const struct pch_gbe_functions pch_gbe_ops = {
-	.get_bus_info      = pch_gbe_plat_get_bus_info,
-};
-
 /**
  * pch_gbe_plat_init_function_pointers - Init func ptrs
  * @hw:	Pointer to the HW structure
@@ -69,8 +28,6 @@ static void pch_gbe_plat_init_function_pointers(struct pch_gbe_hw *hw)
 {
 	/* Set PHY parameter */
 	hw->phy.reset_delay_us     = PCH_GBE_PHY_RESET_DELAY_US;
-	/* Set function pointers */
-	hw->func = &pch_gbe_ops;
 }
 
 /**
@@ -91,18 +48,3 @@ s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw)
 	pch_gbe_plat_init_function_pointers(hw);
 	return 0;
 }
-
-/**
- * pch_gbe_hal_get_bus_info - Obtain bus information for adapter
- * @hw:	Pointer to the HW structure
- */
-void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw)
-{
-	if (!hw->func->get_bus_info) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: configuration\n");
-		return;
-	}
-	hw->func->get_bus_info(hw);
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
index 56cae9cfb5c5..b3b713a32f38 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
@@ -22,6 +22,5 @@
 #include "pch_gbe_phy.h"
 
 s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw);
-void pch_gbe_hal_get_bus_info(struct pch_gbe_hw *hw);
 
 #endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 9297a94df999..246167dbeacd 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2635,7 +2635,6 @@ static int pch_gbe_probe(struct pci_dev *pdev,
 		dev_err(&pdev->dev, "PHY initialize error\n");
 		goto err_free_adapter;
 	}
-	pch_gbe_hal_get_bus_info(&adapter->hw);
 
 	/* Read the MAC address. and store to the private data */
 	ret = pch_gbe_mac_read_mac_addr(&adapter->hw);
-- 
cgit v1.2.3


From c63ebdf01ad96d8c11ab3ff245a3acd30e7fc8ba Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:48 -0700
Subject: net: pch_gbe: Remove pch_gbe_hal_setup_init_funcs

The pch_gbe driver calls a pch_gbe_hal_setup_init_funcs function which
ultimately sets the value of one field in struct pch_gbe_phy_info in a
convoluted way.

This patch removes pch_gbe_hal_setup_init_funcs in favor of inlining it,
and in turn its callee pch_gbe_plat_init_function_pointers, into the
single caller pch_gbe_sw_init.

With this pch_gbe_api.c & pch_gbe_api.h are essentially empty, so they
are removed & inclusions of the latter replaced with pch_gbe_phy.h which
was previously being included via pch_gbe_api.h.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/Makefile     |  2 +-
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c    | 50 ----------------------
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h    | 26 -----------
 .../ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c    |  2 +-
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c   |  8 +---
 5 files changed, 4 insertions(+), 84 deletions(-)
 delete mode 100644 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
 delete mode 100644 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
index 31288d4ad248..862de0f3bc41 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_PCH_GBE) += pch_gbe.o
 
 pch_gbe-y := pch_gbe_phy.o pch_gbe_ethtool.o pch_gbe_param.o
-pch_gbe-y += pch_gbe_api.o pch_gbe_main.o
+pch_gbe-y += pch_gbe_main.o
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
deleted file mode 100644
index 89c0db27b797..000000000000
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.c
+++ /dev/null
@@ -1,50 +0,0 @@
-/*
- * Copyright (C) 1999 - 2010 Intel Corporation.
- * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
- *
- * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-#include "pch_gbe.h"
-#include "pch_gbe_phy.h"
-#include "pch_gbe_api.h"
-
-/**
- * pch_gbe_plat_init_function_pointers - Init func ptrs
- * @hw:	Pointer to the HW structure
- */
-static void pch_gbe_plat_init_function_pointers(struct pch_gbe_hw *hw)
-{
-	/* Set PHY parameter */
-	hw->phy.reset_delay_us     = PCH_GBE_PHY_RESET_DELAY_US;
-}
-
-/**
- * pch_gbe_hal_setup_init_funcs - Initializes function pointers
- * @hw:	Pointer to the HW structure
- * Returns:
- *	0:	Successfully
- *	ENOSYS:	Function is not registered
- */
-s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw)
-{
-	if (!hw->reg) {
-		struct pch_gbe_adapter *adapter = pch_gbe_hw_to_adapter(hw);
-
-		netdev_err(adapter->netdev, "ERROR: Registers not mapped\n");
-		return -ENOSYS;
-	}
-	pch_gbe_plat_init_function_pointers(hw);
-	return 0;
-}
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
deleted file mode 100644
index b3b713a32f38..000000000000
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_api.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Copyright (C) 1999 - 2010 Intel Corporation.
- * Copyright (C) 2010 OKI SEMICONDUCTOR Co., LTD.
- *
- * This code was derived from the Intel e1000e Linux driver.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; version 2 of the License.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- */
-#ifndef _PCH_GBE_API_H_
-#define _PCH_GBE_API_H_
-
-#include "pch_gbe_phy.h"
-
-s32 pch_gbe_hal_setup_init_funcs(struct pch_gbe_hw *hw);
-
-#endif
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index da39d771ad87..a7bdb53790ff 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -17,7 +17,7 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 #include "pch_gbe.h"
-#include "pch_gbe_api.h"
+#include "pch_gbe_phy.h"
 
 /**
  * pch_gbe_stats - Stats item information
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 246167dbeacd..5846e8cf1750 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -18,7 +18,7 @@
  */
 
 #include "pch_gbe.h"
-#include "pch_gbe_api.h"
+#include "pch_gbe_phy.h"
 #include <linux/module.h>
 #include <linux/net_tstamp.h>
 #include <linux/ptp_classify.h>
@@ -2037,12 +2037,8 @@ static int pch_gbe_sw_init(struct pch_gbe_adapter *adapter)
 	adapter->rx_buffer_len = PCH_GBE_FRAME_SIZE_2048;
 	hw->mac.max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN;
 	hw->mac.min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
+	hw->phy.reset_delay_us = PCH_GBE_PHY_RESET_DELAY_US;
 
-	/* Initialize the hardware-specific values */
-	if (pch_gbe_hal_setup_init_funcs(hw)) {
-		netdev_err(netdev, "Hardware Initialization Failure\n");
-		return -EIO;
-	}
 	if (pch_gbe_alloc_queues(adapter)) {
 		netdev_err(netdev, "Unable to allocate memory for queues\n");
 		return -ENOMEM;
-- 
cgit v1.2.3


From 41fd60fa74d6aac84c214afc71aa4b9d3edba263 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:49 -0700
Subject: net: pch_gbe: Remove PCH_GBE_MAC_IFOP_RGMII define

The pch_gbe driver currently presumes that the PHY is connected using
RGMII, and would need further work to support other buses. It includes a
define which is always set that conditionalises some of the
RGMII-specific code regardless. Remove it. If we do ever support
different MII buses then preprocessor defines won't be the best way to
select between them anyway.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 9 ---------
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h  | 1 -
 2 files changed, 10 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 5846e8cf1750..11c42aa42b8a 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -366,9 +366,7 @@ static void pch_gbe_mac_reset_hw(struct pch_gbe_hw *hw)
 	/* Read the MAC address. and store to the private data */
 	pch_gbe_mac_read_mac_addr(hw);
 	iowrite32(PCH_GBE_ALL_RST, &hw->reg->RESET);
-#ifdef PCH_GBE_MAC_IFOP_RGMII
 	iowrite32(PCH_GBE_MODE_GMII_ETHER, &hw->reg->MODE);
-#endif
 	pch_gbe_wait_clr_bit(&hw->reg->RESET, PCH_GBE_ALL_RST);
 	/* Setup the receive addresses */
 	pch_gbe_mac_mar_set(hw, hw->mac.addr, 0);
@@ -776,9 +774,7 @@ void pch_gbe_reset(struct pch_gbe_adapter *adapter)
 	}
 	pch_gbe_phy_init_setting(hw);
 	/* Setup Mac interface option RGMII */
-#ifdef PCH_GBE_MAC_IFOP_RGMII
 	pch_gbe_phy_set_rgmii(hw);
-#endif
 }
 
 /**
@@ -1044,7 +1040,6 @@ static void pch_gbe_set_rgmii_ctrl(struct pch_gbe_adapter *adapter, u16 speed,
 	unsigned long rgmii = 0;
 
 	/* Set the RGMII control. */
-#ifdef PCH_GBE_MAC_IFOP_RGMII
 	switch (speed) {
 	case SPEED_10:
 		rgmii = (PCH_GBE_RGMII_RATE_2_5M |
@@ -1060,10 +1055,6 @@ static void pch_gbe_set_rgmii_ctrl(struct pch_gbe_adapter *adapter, u16 speed,
 		break;
 	}
 	iowrite32(rgmii, &hw->reg->RGMII_CTRL);
-#else	/* GMII */
-	rgmii = 0;
-	iowrite32(rgmii, &hw->reg->RGMII_CTRL);
-#endif
 }
 static void pch_gbe_set_mode(struct pch_gbe_adapter *adapter, u16 speed,
 			      u16 duplex)
diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
index efb955be8cac..23ac38711619 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_phy.h
@@ -21,7 +21,6 @@
 
 #define PCH_GBE_PHY_REGS_LEN		32
 #define	PCH_GBE_PHY_RESET_DELAY_US	10
-#define PCH_GBE_MAC_IFOP_RGMII
 
 s32 pch_gbe_phy_get_id(struct pch_gbe_hw *hw);
 s32 pch_gbe_phy_read_reg_miic(struct pch_gbe_hw *hw, u32 offset, u16 *data);
-- 
cgit v1.2.3


From 90e3f637eb4d2e1fdb6a799e758a21c2a4e20a1d Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:50 -0700
Subject: net: pch_gbe: Remove dead RINGFREE code

The pch_gbe driver includes some code which appears to be an attempt to
work around a problem with the pch_gbe_free_rx_resources &
pch_gbe_free_tx_resources functions that no longer exists. Remove the
code guarded by the never-defined RINGFREE preprocessor macro.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
index a7bdb53790ff..adaa0024adfe 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_ethtool.c
@@ -349,25 +349,12 @@ static int pch_gbe_set_ringparam(struct net_device *netdev,
 		err = pch_gbe_setup_tx_resources(adapter, adapter->tx_ring);
 		if (err)
 			goto err_setup_tx;
-		/* save the new, restore the old in order to free it,
-		 * then restore the new back again */
-#ifdef RINGFREE
-		adapter->rx_ring = rx_old;
-		adapter->tx_ring = tx_old;
-		pch_gbe_free_rx_resources(adapter, adapter->rx_ring);
-		pch_gbe_free_tx_resources(adapter, adapter->tx_ring);
-		kfree(tx_old);
-		kfree(rx_old);
-		adapter->rx_ring = rxdr;
-		adapter->tx_ring = txdr;
-#else
 		pch_gbe_free_rx_resources(adapter, rx_old);
 		pch_gbe_free_tx_resources(adapter, tx_old);
 		kfree(tx_old);
 		kfree(rx_old);
 		adapter->rx_ring = rxdr;
 		adapter->tx_ring = txdr;
-#endif
 		err = pch_gbe_up(adapter);
 	}
 	return err;
-- 
cgit v1.2.3


From 99a9c28863ccccf25f6e95c5b38cb6884d922a7f Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:51 -0700
Subject: net: pch_gbe: Use module_pci_driver()

Make use of the module_pci_driver() macro to remove some needless
boilerplate code from the pch_gbe driver. This does have the side effect
of removing the print of the driver's version during probe, but this is
pretty useless information anyway - the version has changed only once
whilst the driver has been in mainline, despite many changes being made
to it before and since.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c | 19 +------------------
 1 file changed, 1 insertion(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 11c42aa42b8a..3f2dd36d45ad 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2770,24 +2770,7 @@ static struct pci_driver pch_gbe_driver = {
 	.shutdown = pch_gbe_shutdown,
 	.err_handler = &pch_gbe_err_handler
 };
-
-
-static int __init pch_gbe_init_module(void)
-{
-	int ret;
-
-	pr_info("EG20T PCH Gigabit Ethernet Driver - version %s\n",DRV_VERSION);
-	ret = pci_register_driver(&pch_gbe_driver);
-	return ret;
-}
-
-static void __exit pch_gbe_exit_module(void)
-{
-	pci_unregister_driver(&pch_gbe_driver);
-}
-
-module_init(pch_gbe_init_module);
-module_exit(pch_gbe_exit_module);
+module_pci_driver(pch_gbe_driver);
 
 MODULE_DESCRIPTION("EG20T PCH Gigabit ethernet Driver");
 MODULE_AUTHOR("LAPIS SEMICONDUCTOR, <tshimizu818@gmail.com>");
-- 
cgit v1.2.3


From 6ab91e47694e03775bbe874fa8f15f84db404c00 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:52 -0700
Subject: net: pch_gbe: Inline pch_gbe_mac_mc_addr_list_update

The pch_gbe driver sets up multicast address filters using a convoluted
mechanism by which pch_gbe_set_multi allocates an array to hold
multicast addresses, copies desired addresses into that array, calls a
pch_gbe_mac_mc_addr_list_update function which copies addresses out of
that array into MAC registers, then frees the array.

This patch simplifies this somewhat by inlining
pch_gbe_mac_mc_addr_list_update into pch_gbe_set_multi, and removing the
requirement for the MAC addresses to stored consecutively in a single
array.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c   | 73 ++++++----------------
 1 file changed, 19 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index 3f2dd36d45ad..dc8c4050fad3 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -411,44 +411,6 @@ static void pch_gbe_mac_init_rx_addrs(struct pch_gbe_hw *hw, u16 mar_count)
 	pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
 }
 
-
-/**
- * pch_gbe_mac_mc_addr_list_update - Update Multicast addresses
- * @hw:	            Pointer to the HW structure
- * @mc_addr_list:   Array of multicast addresses to program
- * @mc_addr_count:  Number of multicast addresses to program
- * @mar_used_count: The first MAC Address register free to program
- * @mar_total_num:  Total number of supported MAC Address Registers
- */
-static void pch_gbe_mac_mc_addr_list_update(struct pch_gbe_hw *hw,
-					    u8 *mc_addr_list, u32 mc_addr_count,
-					    u32 mar_used_count, u32 mar_total_num)
-{
-	u32 i, adrmask;
-
-	/* Load the first set of multicast addresses into the exact
-	 * filters (RAR).  If there are not enough to fill the RAR
-	 * array, clear the filters.
-	 */
-	for (i = mar_used_count; i < mar_total_num; i++) {
-		if (mc_addr_count) {
-			pch_gbe_mac_mar_set(hw, mc_addr_list, i);
-			mc_addr_count--;
-			mc_addr_list += ETH_ALEN;
-		} else {
-			/* Clear MAC address mask */
-			adrmask = ioread32(&hw->reg->ADDR_MASK);
-			iowrite32((adrmask | (0x0001 << i)),
-					&hw->reg->ADDR_MASK);
-			/* wait busy */
-			pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
-			/* Clear MAC address */
-			iowrite32(0, &hw->reg->mac_adr[i].high);
-			iowrite32(0, &hw->reg->mac_adr[i].low);
-		}
-	}
-}
-
 /**
  * pch_gbe_mac_force_mac_fc - Force the MAC's flow control settings
  * @hw:	            Pointer to the HW structure
@@ -2143,10 +2105,8 @@ static void pch_gbe_set_multi(struct net_device *netdev)
 	struct pch_gbe_adapter *adapter = netdev_priv(netdev);
 	struct pch_gbe_hw *hw = &adapter->hw;
 	struct netdev_hw_addr *ha;
-	u8 *mta_list;
-	u32 rctl;
-	int i;
-	int mc_count;
+	u32 rctl, adrmask;
+	int mc_count, i;
 
 	netdev_dbg(netdev, "netdev->flags : 0x%08x\n", netdev->flags);
 
@@ -2173,20 +2133,25 @@ static void pch_gbe_set_multi(struct net_device *netdev)
 
 	if (mc_count >= PCH_GBE_MAR_ENTRIES)
 		return;
-	mta_list = kmalloc_array(ETH_ALEN, mc_count, GFP_ATOMIC);
-	if (!mta_list)
-		return;
 
-	/* The shared function expects a packed array of only addresses. */
-	i = 0;
-	netdev_for_each_mc_addr(ha, netdev) {
-		if (i == mc_count)
-			break;
-		memcpy(mta_list + (i++ * ETH_ALEN), &ha->addr, ETH_ALEN);
+	/* Load the first set of multicast addresses into MAC address registers
+	 * for use by hardware filtering.
+	 */
+	i = 1;
+	netdev_for_each_mc_addr(ha, netdev)
+		pch_gbe_mac_mar_set(hw, ha->addr, i++);
+
+	/* If there are spare MAC registers, mask & clear them */
+	for (; i < PCH_GBE_MAR_ENTRIES; i++) {
+		/* Clear MAC address mask */
+		adrmask = ioread32(&hw->reg->ADDR_MASK);
+		iowrite32(adrmask | BIT(i), &hw->reg->ADDR_MASK);
+		/* wait busy */
+		pch_gbe_wait_clr_bit(&hw->reg->ADDR_MASK, PCH_GBE_BUSY);
+		/* Clear MAC address */
+		iowrite32(0, &hw->reg->mac_adr[i].high);
+		iowrite32(0, &hw->reg->mac_adr[i].low);
 	}
-	pch_gbe_mac_mc_addr_list_update(hw, mta_list, i, 1,
-					PCH_GBE_MAR_ENTRIES);
-	kfree(mta_list);
 
 	netdev_dbg(netdev,
 		 "RX_MODE reg(check bit31,30 ADD,MLT) : 0x%08x  netdev->mc_count : 0x%08x\n",
-- 
cgit v1.2.3


From 418e7dab0f83fcef4f3cb1ae5b1c02ee83b8e26c Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 20:17:53 -0700
Subject: net: pch_gbe: Clean up pch_gbe_set_multi

Refactor pch_gbe_set_multi in order to avoid unnecessary indentation &
make it clearer what the code is doing.

The one behavioral change from this patch is that we'll no longer
configure the MAC address registers for multicast addresses when the
IFF_PROMISC or IFF_ALLMULTI flags are set. In these cases, just as when
we want to monitor more multicast addresses than we have MAC address
registers, we disable multicast filtering so the MAC address registers
are unused.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c   | 33 +++++++++++-----------
 1 file changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
index dc8c4050fad3..43c0c10dfeb7 100644
--- a/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
+++ b/drivers/net/ethernet/oki-semi/pch_gbe/pch_gbe_main.c
@@ -2110,28 +2110,27 @@ static void pch_gbe_set_multi(struct net_device *netdev)
 
 	netdev_dbg(netdev, "netdev->flags : 0x%08x\n", netdev->flags);
 
-	/* Check for Promiscuous and All Multicast modes */
+	/* By default enable address & multicast filtering */
 	rctl = ioread32(&hw->reg->RX_MODE);
+	rctl |= PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN;
+
+	/* Promiscuous mode disables all hardware address filtering */
+	if (netdev->flags & IFF_PROMISC)
+		rctl &= ~(PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN);
+
+	/* If we want to monitor more multicast addresses than the hardware can
+	 * support then disable hardware multicast filtering.
+	 */
 	mc_count = netdev_mc_count(netdev);
-	if ((netdev->flags & IFF_PROMISC)) {
-		rctl &= ~PCH_GBE_ADD_FIL_EN;
+	if ((netdev->flags & IFF_ALLMULTI) || mc_count >= PCH_GBE_MAR_ENTRIES)
 		rctl &= ~PCH_GBE_MLT_FIL_EN;
-	} else if ((netdev->flags & IFF_ALLMULTI)) {
-		/* all the multicasting receive permissions */
-		rctl |= PCH_GBE_ADD_FIL_EN;
-		rctl &= ~PCH_GBE_MLT_FIL_EN;
-	} else {
-		if (mc_count >= PCH_GBE_MAR_ENTRIES) {
-			/* all the multicasting receive permissions */
-			rctl |= PCH_GBE_ADD_FIL_EN;
-			rctl &= ~PCH_GBE_MLT_FIL_EN;
-		} else {
-			rctl |= (PCH_GBE_ADD_FIL_EN | PCH_GBE_MLT_FIL_EN);
-		}
-	}
+
 	iowrite32(rctl, &hw->reg->RX_MODE);
 
-	if (mc_count >= PCH_GBE_MAR_ENTRIES)
+	/* If we're not using multicast filtering then there's no point
+	 * configuring the unused MAC address registers.
+	 */
+	if (!(rctl & PCH_GBE_MLT_FIL_EN))
 		return;
 
 	/* Load the first set of multicast addresses into MAC address registers
-- 
cgit v1.2.3


From f37658da21aae3b4801860858caf4616286a0dc8 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 23 Jun 2018 09:51:28 +0200
Subject: r8169: align ASPM entry latency setting with vendor driver

The r8168 vendor driver always uses value 0x27. In r8169 we have few
chips where 0x17 is used. So far this didn't matter because ASPM was
disabled anyway. Now that ASPM was re-enabled let's also use 0x27 only.

One of the chips affected by this change is RTL8168E-VL, on my system
with this chip value 0x27 works fine.

In addition rename rtl_csi_access_enable_2() to
rtl_set_def_aspm_entry_latency() to make clear that we set the default
ASPM entry latency.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 43 ++++++++++++++++--------------------
 1 file changed, 19 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 06e14da1b4af..d5e380d909dd 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5235,12 +5235,7 @@ static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val)
 	rtl_csi_write(tp, 0x070c, csi | val << 24);
 }
 
-static void rtl_csi_access_enable_1(struct rtl8169_private *tp)
-{
-	rtl_csi_access_enable(tp, 0x17);
-}
-
-static void rtl_csi_access_enable_2(struct rtl8169_private *tp)
+static void rtl_set_def_aspm_entry_latency(struct rtl8169_private *tp)
 {
 	rtl_csi_access_enable(tp, 0x27);
 }
@@ -5347,7 +5342,7 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
 		{ 0x07, 0,	0x2000 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168cp, ARRAY_SIZE(e_info_8168cp));
 
@@ -5356,7 +5351,7 @@ static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
 
@@ -5369,7 +5364,7 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en);
 
@@ -5393,7 +5388,7 @@ static void rtl_hw_start_8168c_1(struct rtl8169_private *tp)
 		{ 0x06, 0x0080,	0x0000 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, DBG_REG, 0x06 | FIX_NAK_1 | FIX_NAK_2);
 
@@ -5409,7 +5404,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp)
 		{ 0x03, 0x0400,	0x0220 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168c_2, ARRAY_SIZE(e_info_8168c_2));
 
@@ -5423,14 +5418,14 @@ static void rtl_hw_start_8168c_3(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168c_4(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	__rtl_hw_start_8168cp(tp);
 }
 
 static void rtl_hw_start_8168d(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_disable_clock_request(tp);
 
@@ -5445,7 +5440,7 @@ static void rtl_hw_start_8168d(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168dp(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	if (tp->dev->mtu <= ETH_DATA_LEN)
 		rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
@@ -5463,7 +5458,7 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp)
 		{ 0x0c, 0x0100,	0x0020 }
 	};
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5492,7 +5487,7 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp)
 		{ 0x0a, 0x0000,	0x0040 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168e_1, ARRAY_SIZE(e_info_8168e_1));
 
@@ -5517,7 +5512,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 		{ 0x19, 0x0000,	0x0224 }
 	};
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_ephy_init(tp, e_info_8168e_2, ARRAY_SIZE(e_info_8168e_2));
 
@@ -5550,7 +5545,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8168f(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5621,7 +5616,7 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5720,7 +5715,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x48, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -5804,7 +5799,7 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp)
 	rtl_eri_write(tp, 0xd0, ERIAR_MASK_0001, 0x5f, ERIAR_EXGMAC);
 	rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00100006, ERIAR_EXGMAC);
 
-	rtl_csi_access_enable_1(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -6040,7 +6035,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
 	};
 	u8 cfg1;
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	RTL_W8(tp, DBG_REG, FIX_NAK_1);
 
@@ -6059,7 +6054,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8102e_2(struct rtl8169_private *tp)
 {
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B);
 
@@ -6114,7 +6109,7 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp)
 		{ 0x1e,	0, 0x4000 }
 	};
 
-	rtl_csi_access_enable_2(tp);
+	rtl_set_def_aspm_entry_latency(tp);
 
 	/* Force LAN exit from ASPM if Rx/Tx are not idle */
 	RTL_W32(tp, FuncEvent, RTL_R32(tp, FuncEvent) | 0x002800);
-- 
cgit v1.2.3


From aa1e7d2c31efd561fbbecc77eb785c8af685c1af Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 23 Jun 2018 09:53:00 +0200
Subject: r8169: enable ASPM on RTL8168E-VL

Let's enable ASPM also on the RTL8168E-VL (chip version 34).
Works fine on my Zotac Mini PC with this chip. Temperature when
being idle is significantly lower than before due to reaching
deeper PC states.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index d5e380d909dd..44715958b246 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -5541,6 +5541,8 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp)
 	RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) | PFM_EN);
 	RTL_W32(tp, MISC, RTL_R32(tp, MISC) | PWM_EN);
 	RTL_W8(tp, Config5, RTL_R8(tp, Config5) & ~Spi_en);
+
+	rtl_hw_aspm_clkreq_enable(tp, true);
 }
 
 static void rtl_hw_start_8168f(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From 9b42c1f179a614e11893ae4619f0304a38f481ae Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 12 Jun 2018 12:44:26 +0200
Subject: xfrm: Extend the output_mark to support input direction and masking.

We already support setting an output mark at the xfrm_state,
unfortunately this does not support the input direction and
masking the marks that will be applied to the skb. This change
adds support applying a masked value in both directions.

The existing XFRMA_OUTPUT_MARK number is reused for this purpose
and as it is now bi-directional, it is renamed to XFRMA_SET_MARK.

An additional XFRMA_SET_MARK_MASK attribute is added for setting the
mask. If the attribute mask not provided, it is set to 0xffffffff,
keeping the XFRMA_OUTPUT_MARK existing 'full mask' semantics.

Co-developed-by: Tobias Brunner <tobias@strongswan.org>
Co-developed-by: Eyal Birger <eyal.birger@gmail.com>
Co-developed-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Signed-off-by: Tobias Brunner <tobias@strongswan.org>
Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
---
 include/net/xfrm.h        |  9 ++++++++-
 include/uapi/linux/xfrm.h |  4 +++-
 net/xfrm/xfrm_device.c    |  3 ++-
 net/xfrm/xfrm_input.c     |  2 ++
 net/xfrm/xfrm_output.c    |  3 +--
 net/xfrm/xfrm_policy.c    |  5 +++--
 net/xfrm/xfrm_user.c      | 48 +++++++++++++++++++++++++++++++++++++----------
 7 files changed, 57 insertions(+), 17 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 557122846e0e..3dc83ba26f62 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -166,7 +166,7 @@ struct xfrm_state {
 		int		header_len;
 		int		trailer_len;
 		u32		extra_flags;
-		u32		output_mark;
+		struct xfrm_mark	smark;
 	} props;
 
 	struct xfrm_lifetime_cfg lft;
@@ -2012,6 +2012,13 @@ static inline int xfrm_mark_put(struct sk_buff *skb, const struct xfrm_mark *m)
 	return ret;
 }
 
+static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x)
+{
+	struct xfrm_mark *m = &x->props.smark;
+
+	return (m->v & m->m) | (mark & ~m->m);
+}
+
 static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 				    unsigned int family)
 {
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index e3af2859188b..5a6ed7ce5a29 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -305,9 +305,11 @@ enum xfrm_attr_type_t {
 	XFRMA_ADDRESS_FILTER,	/* struct xfrm_address_filter */
 	XFRMA_PAD,
 	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
-	XFRMA_OUTPUT_MARK,	/* __u32 */
+	XFRMA_SET_MARK,		/* __u32 */
+	XFRMA_SET_MARK_MASK,	/* __u32 */
 	__XFRMA_MAX
 
+#define XFRMA_OUTPUT_MARK XFRMA_SET_MARK	/* Compatibility */
 #define XFRMA_MAX (__XFRMA_MAX - 1)
 };
 
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 175941e15a6e..16c1230d20fa 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -162,7 +162,8 @@ int xfrm_dev_state_add(struct net *net, struct xfrm_state *x,
 		}
 
 		dst = __xfrm_dst_lookup(net, 0, 0, saddr, daddr,
-					x->props.family, x->props.output_mark);
+					x->props.family,
+					xfrm_smark_get(0, x));
 		if (IS_ERR(dst))
 			return 0;
 
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 352abca2605f..074810436242 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -339,6 +339,8 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 			goto drop;
 		}
 
+		skb->mark = xfrm_smark_get(skb->mark, x);
+
 		skb->sp->xvec[skb->sp->len++] = x;
 
 lock:
diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index 89b178a78dc7..45ba07ab3e4f 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -66,8 +66,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err)
 			goto error_nolock;
 		}
 
-		if (x->props.output_mark)
-			skb->mark = x->props.output_mark;
+		skb->mark = xfrm_smark_get(skb->mark, x);
 
 		err = x->outer_mode->output(x, skb);
 		if (err) {
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5f48251c1319..7637637717ec 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1607,10 +1607,11 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy,
 		dst_copy_metrics(dst1, dst);
 
 		if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) {
+			__u32 mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]);
+
 			family = xfrm[i]->props.family;
 			dst = xfrm_dst_lookup(xfrm[i], tos, fl->flowi_oif,
-					      &saddr, &daddr, family,
-					      xfrm[i]->props.output_mark);
+					      &saddr, &daddr, family, mark);
 			err = PTR_ERR(dst);
 			if (IS_ERR(dst))
 				goto put_states;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 080035f056d9..9602cc9e05ab 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -527,6 +527,19 @@ static void xfrm_update_ae_params(struct xfrm_state *x, struct nlattr **attrs,
 		x->replay_maxdiff = nla_get_u32(rt);
 }
 
+static void xfrm_smark_init(struct nlattr **attrs, struct xfrm_mark *m)
+{
+	if (attrs[XFRMA_SET_MARK]) {
+		m->v = nla_get_u32(attrs[XFRMA_SET_MARK]);
+		if (attrs[XFRMA_SET_MARK_MASK])
+			m->m = nla_get_u32(attrs[XFRMA_SET_MARK_MASK]);
+		else
+			m->m = 0xffffffff;
+	} else {
+		m->v = m->m = 0;
+	}
+}
+
 static struct xfrm_state *xfrm_state_construct(struct net *net,
 					       struct xfrm_usersa_info *p,
 					       struct nlattr **attrs,
@@ -579,8 +592,7 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 
 	xfrm_mark_get(attrs, &x->mark);
 
-	if (attrs[XFRMA_OUTPUT_MARK])
-		x->props.output_mark = nla_get_u32(attrs[XFRMA_OUTPUT_MARK]);
+	xfrm_smark_init(attrs, &x->props.smark);
 
 	err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]);
 	if (err)
@@ -824,6 +836,18 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 	return 0;
 }
 
+static int xfrm_smark_put(struct sk_buff *skb, struct xfrm_mark *m)
+{
+	int ret = 0;
+
+	if (m->v | m->m) {
+		ret = nla_put_u32(skb, XFRMA_SET_MARK, m->v);
+		if (!ret)
+			ret = nla_put_u32(skb, XFRMA_SET_MARK_MASK, m->m);
+	}
+	return ret;
+}
+
 /* Don't change this without updating xfrm_sa_len! */
 static int copy_to_user_state_extra(struct xfrm_state *x,
 				    struct xfrm_usersa_info *p,
@@ -887,6 +911,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 	ret = xfrm_mark_put(skb, &x->mark);
 	if (ret)
 		goto out;
+
+	ret = xfrm_smark_put(skb, &x->props.smark);
+	if (ret)
+		goto out;
+
 	if (x->replay_esn)
 		ret = nla_put(skb, XFRMA_REPLAY_ESN_VAL,
 			      xfrm_replay_state_esn_len(x->replay_esn),
@@ -900,11 +929,7 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 		ret = copy_user_offload(&x->xso, skb);
 	if (ret)
 		goto out;
-	if (x->props.output_mark) {
-		ret = nla_put_u32(skb, XFRMA_OUTPUT_MARK, x->props.output_mark);
-		if (ret)
-			goto out;
-	}
+
 	if (x->security)
 		ret = copy_sec_ctx(x->security, skb);
 out:
@@ -2493,7 +2518,8 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_PROTO]		= { .type = NLA_U8 },
 	[XFRMA_ADDRESS_FILTER]	= { .len = sizeof(struct xfrm_address_filter) },
 	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
-	[XFRMA_OUTPUT_MARK]	= { .type = NLA_U32 },
+	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
+	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
 };
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
@@ -2719,8 +2745,10 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
 		l += nla_total_size(sizeof(x->props.extra_flags));
 	if (x->xso.dev)
 		 l += nla_total_size(sizeof(x->xso));
-	if (x->props.output_mark)
-		l += nla_total_size(sizeof(x->props.output_mark));
+	if (x->props.smark.v | x->props.smark.m) {
+		l += nla_total_size(sizeof(x->props.smark.v));
+		l += nla_total_size(sizeof(x->props.smark.m));
+	}
 
 	/* Must count x->lastused as it may become non-zero behind our back. */
 	l += nla_total_size_64bit(sizeof(u64));
-- 
cgit v1.2.3


From d159ce7957eec306eacda672e5909e26675ca8ef Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 12 Jun 2018 14:06:57 +0200
Subject: flow: Extend flow informations with xfrm interface id.

Add a new flowi_xfrm structure with informations needed to do
a xfrm lookup. At the moment it keeps the informations about
the new xfrm interface id needed to lookup xfrm interfaces
that are introduced with a followup patch. We need this new
lookup key as other possible keys, like the ifindex is
already part of the xfrm selector and used as a key to
enforce the output device after the transformation in the
policy/state lookup.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Acked-by: Benedict Wong <benedictwong@google.com>
Tested-by: Benedict Wong <benedictwong@google.com>
Tested-by: Antony Antony <antony@phenome.org>
Reviewed-by: Eyal Birger <eyal.birger@gmail.com>
---
 include/net/flow.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/include/net/flow.h b/include/net/flow.h
index 8ce21793094e..187c9bef672f 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -26,6 +26,10 @@ struct flowi_tunnel {
 	__be64			tun_id;
 };
 
+struct flowi_xfrm {
+	__u32			if_id;
+};
+
 struct flowi_common {
 	int	flowic_oif;
 	int	flowic_iif;
@@ -39,6 +43,7 @@ struct flowi_common {
 #define FLOWI_FLAG_SKIP_NH_OIF		0x04
 	__u32	flowic_secid;
 	struct flowi_tunnel flowic_tun_key;
+	struct flowi_xfrm xfrm;
 	kuid_t  flowic_uid;
 };
 
@@ -78,6 +83,7 @@ struct flowi4 {
 #define flowi4_secid		__fl_common.flowic_secid
 #define flowi4_tun_key		__fl_common.flowic_tun_key
 #define flowi4_uid		__fl_common.flowic_uid
+#define flowi4_xfrm		__fl_common.xfrm
 
 	/* (saddr,daddr) must be grouped, same order as in IP header */
 	__be32			saddr;
@@ -109,6 +115,7 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->flowi4_flags = flags;
 	fl4->flowi4_secid = 0;
 	fl4->flowi4_tun_key.tun_id = 0;
+	fl4->flowi4_xfrm.if_id = 0;
 	fl4->flowi4_uid = uid;
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
@@ -138,6 +145,7 @@ struct flowi6 {
 #define flowi6_secid		__fl_common.flowic_secid
 #define flowi6_tun_key		__fl_common.flowic_tun_key
 #define flowi6_uid		__fl_common.flowic_uid
+#define flowi6_xfrm		__fl_common.xfrm
 	struct in6_addr		daddr;
 	struct in6_addr		saddr;
 	/* Note: flowi6_tos is encoded in flowlabel, too. */
@@ -185,6 +193,7 @@ struct flowi {
 #define flowi_secid	u.__fl_common.flowic_secid
 #define flowi_tun_key	u.__fl_common.flowic_tun_key
 #define flowi_uid	u.__fl_common.flowic_uid
+#define flowi_xfrm	u.__fl_common.xfrm
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
-- 
cgit v1.2.3


From 7e6526404adedf079279aa7aa11722deaca8fe2e Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 12 Jun 2018 14:07:07 +0200
Subject: xfrm: Add a new lookup key to match xfrm interfaces.

This patch adds the xfrm interface id as a lookup key
for xfrm states and policies. With this we can assign
states and policies to virtual xfrm interfaces.

Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Acked-by: Benedict Wong <benedictwong@google.com>
Tested-by: Benedict Wong <benedictwong@google.com>
Tested-by: Antony Antony <antony@phenome.org>
Reviewed-by: Eyal Birger <eyal.birger@gmail.com>
---
 include/net/xfrm.h        | 21 +++++++++++++-----
 include/uapi/linux/xfrm.h |  1 +
 net/core/pktgen.c         |  2 +-
 net/key/af_key.c          |  6 +++---
 net/xfrm/xfrm_policy.c    | 18 +++++++++++-----
 net/xfrm/xfrm_state.c     | 19 ++++++++++++-----
 net/xfrm/xfrm_user.c      | 54 +++++++++++++++++++++++++++++++++++++++++------
 7 files changed, 96 insertions(+), 25 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 3dc83ba26f62..e8bada4d2a45 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -147,6 +147,7 @@ struct xfrm_state {
 	struct xfrm_id		id;
 	struct xfrm_selector	sel;
 	struct xfrm_mark	mark;
+	u32			if_id;
 	u32			tfcpad;
 
 	u32			genid;
@@ -574,6 +575,7 @@ struct xfrm_policy {
 	atomic_t		genid;
 	u32			priority;
 	u32			index;
+	u32			if_id;
 	struct xfrm_mark	mark;
 	struct xfrm_selector	selector;
 	struct xfrm_lifetime_cfg lft;
@@ -1533,7 +1535,7 @@ struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
 				   struct xfrm_tmpl *tmpl,
 				   struct xfrm_policy *pol, int *err,
 				   unsigned short family);
-struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark,
+struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
 				       xfrm_address_t *daddr,
 				       xfrm_address_t *saddr,
 				       unsigned short family,
@@ -1690,20 +1692,20 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk,
 		     void *);
 void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net);
 int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl);
-struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark,
+struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
 					  u8 type, int dir,
 					  struct xfrm_selector *sel,
 					  struct xfrm_sec_ctx *ctx, int delete,
 					  int *err);
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8, int dir,
-				     u32 id, int delete, int *err);
+struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8,
+				     int dir, u32 id, int delete, int *err);
 int xfrm_policy_flush(struct net *net, u8 type, bool task_valid);
 void xfrm_policy_hash_rebuild(struct net *net);
 u32 xfrm_get_acqseq(void);
 int verify_spi_info(u8 proto, u32 min, u32 max);
 int xfrm_alloc_spi(struct xfrm_state *x, u32 minspi, u32 maxspi);
 struct xfrm_state *xfrm_find_acq(struct net *net, const struct xfrm_mark *mark,
-				 u8 mode, u32 reqid, u8 proto,
+				 u8 mode, u32 reqid, u32 if_id, u8 proto,
 				 const xfrm_address_t *daddr,
 				 const xfrm_address_t *saddr, int create,
 				 unsigned short family);
@@ -2019,6 +2021,15 @@ static inline __u32 xfrm_smark_get(__u32 mark, struct xfrm_state *x)
 	return (m->v & m->m) | (mark & ~m->m);
 }
 
+static inline int xfrm_if_id_put(struct sk_buff *skb, __u32 if_id)
+{
+	int ret = 0;
+
+	if (if_id)
+		ret = nla_put_u32(skb, XFRMA_IF_ID, if_id);
+	return ret;
+}
+
 static inline int xfrm_tunnel_check(struct sk_buff *skb, struct xfrm_state *x,
 				    unsigned int family)
 {
diff --git a/include/uapi/linux/xfrm.h b/include/uapi/linux/xfrm.h
index 5a6ed7ce5a29..5f3b9fec7b5f 100644
--- a/include/uapi/linux/xfrm.h
+++ b/include/uapi/linux/xfrm.h
@@ -307,6 +307,7 @@ enum xfrm_attr_type_t {
 	XFRMA_OFFLOAD_DEV,	/* struct xfrm_state_offload */
 	XFRMA_SET_MARK,		/* __u32 */
 	XFRMA_SET_MARK_MASK,	/* __u32 */
+	XFRMA_IF_ID,		/* __u32 */
 	__XFRMA_MAX
 
 #define XFRMA_OUTPUT_MARK XFRMA_SET_MARK	/* Compatibility */
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 49368e21d228..6d37dbf0aa64 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -2255,7 +2255,7 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
 			x = xfrm_state_lookup_byspi(pn->net, htonl(pkt_dev->spi), AF_INET);
 		} else {
 			/* slow path: we dont already have xfrm_state */
-			x = xfrm_stateonly_find(pn->net, DUMMY_MARK,
+			x = xfrm_stateonly_find(pn->net, DUMMY_MARK, 0,
 						(xfrm_address_t *)&pkt_dev->cur_daddr,
 						(xfrm_address_t *)&pkt_dev->cur_saddr,
 						AF_INET,
diff --git a/net/key/af_key.c b/net/key/af_key.c
index 8bdc1cbe490a..398ebcd614a0 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -1383,7 +1383,7 @@ static int pfkey_getspi(struct sock *sk, struct sk_buff *skb, const struct sadb_
 	}
 
 	if (!x)
-		x = xfrm_find_acq(net, &dummy_mark, mode, reqid, proto, xdaddr, xsaddr, 1, family);
+		x = xfrm_find_acq(net, &dummy_mark, mode, reqid, 0, proto, xdaddr, xsaddr, 1, family);
 
 	if (x == NULL)
 		return -ENOENT;
@@ -2414,7 +2414,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa
 			return err;
 	}
 
-	xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN,
+	xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN,
 				   pol->sadb_x_policy_dir - 1, &sel, pol_ctx,
 				   1, &err);
 	security_xfrm_policy_free(pol_ctx);
@@ -2663,7 +2663,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_
 		return -EINVAL;
 
 	delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2);
-	xp = xfrm_policy_byid(net, DUMMY_MARK, XFRM_POLICY_TYPE_MAIN,
+	xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN,
 			      dir, pol->sadb_x_policy_id, delete, &err);
 	if (xp == NULL)
 		return -ENOENT;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 7637637717ec..fc0c69312b2c 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -747,6 +747,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	newpos = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == policy->type &&
+		    pol->if_id == policy->if_id &&
 		    !selector_cmp(&pol->selector, &policy->selector) &&
 		    xfrm_policy_mark_match(policy, pol) &&
 		    xfrm_sec_ctx_match(pol->security, policy->security) &&
@@ -798,8 +799,9 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 }
 EXPORT_SYMBOL(xfrm_policy_insert);
 
-struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
-					  int dir, struct xfrm_selector *sel,
+struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id,
+					  u8 type, int dir,
+					  struct xfrm_selector *sel,
 					  struct xfrm_sec_ctx *ctx, int delete,
 					  int *err)
 {
@@ -812,6 +814,7 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, bydst) {
 		if (pol->type == type &&
+		    pol->if_id == if_id &&
 		    (mark & pol->mark.m) == pol->mark.v &&
 		    !selector_cmp(sel, &pol->selector) &&
 		    xfrm_sec_ctx_match(ctx, pol->security)) {
@@ -837,8 +840,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u8 type,
 }
 EXPORT_SYMBOL(xfrm_policy_bysel_ctx);
 
-struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
-				     int dir, u32 id, int delete, int *err)
+struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id,
+				     u8 type, int dir, u32 id, int delete,
+				     int *err)
 {
 	struct xfrm_policy *pol, *ret;
 	struct hlist_head *chain;
@@ -853,6 +857,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u8 type,
 	ret = NULL;
 	hlist_for_each_entry(pol, chain, byidx) {
 		if (pol->type == type && pol->index == id &&
+		    pol->if_id == if_id &&
 		    (mark & pol->mark.m) == pol->mark.v) {
 			xfrm_pol_hold(pol);
 			if (delete) {
@@ -1063,6 +1068,7 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 	bool match;
 
 	if (pol->family != family ||
+	    pol->if_id != fl->flowi_xfrm.if_id ||
 	    (fl->flowi_mark & pol->mark.m) != pol->mark.v ||
 	    pol->type != type)
 		return ret;
@@ -1177,7 +1183,8 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
 
 		match = xfrm_selector_match(&pol->selector, fl, family);
 		if (match) {
-			if ((sk->sk_mark & pol->mark.m) != pol->mark.v) {
+			if ((sk->sk_mark & pol->mark.m) != pol->mark.v ||
+			    pol->if_id != fl->flowi_xfrm.if_id) {
 				pol = NULL;
 				goto out;
 			}
@@ -1305,6 +1312,7 @@ static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir)
 		newp->lft = old->lft;
 		newp->curlft = old->curlft;
 		newp->mark = old->mark;
+		newp->if_id = old->if_id;
 		newp->action = old->action;
 		newp->flags = old->flags;
 		newp->xfrm_nr = old->xfrm_nr;
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 8308281f3253..3803b6813fc5 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -941,6 +941,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	int error = 0;
 	struct xfrm_state *best = NULL;
 	u32 mark = pol->mark.v & pol->mark.m;
+	u32 if_id = fl->flowi_xfrm.if_id;
 	unsigned short encap_family = tmpl->encap_family;
 	unsigned int sequence;
 	struct km_event c;
@@ -955,6 +956,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
+		    x->if_id == if_id &&
 		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
 		    xfrm_state_addr_check(x, daddr, saddr, encap_family) &&
 		    tmpl->mode == x->props.mode &&
@@ -971,6 +973,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		if (x->props.family == encap_family &&
 		    x->props.reqid == tmpl->reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
+		    x->if_id == if_id &&
 		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
 		    xfrm_addr_equal(&x->id.daddr, daddr, encap_family) &&
 		    tmpl->mode == x->props.mode &&
@@ -1010,6 +1013,7 @@ found:
 		 * to current session. */
 		xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family);
 		memcpy(&x->mark, &pol->mark, sizeof(x->mark));
+		x->if_id = if_id;
 
 		error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid);
 		if (error) {
@@ -1067,7 +1071,7 @@ out:
 }
 
 struct xfrm_state *
-xfrm_stateonly_find(struct net *net, u32 mark,
+xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
 		    xfrm_address_t *daddr, xfrm_address_t *saddr,
 		    unsigned short family, u8 mode, u8 proto, u32 reqid)
 {
@@ -1080,6 +1084,7 @@ xfrm_stateonly_find(struct net *net, u32 mark,
 		if (x->props.family == family &&
 		    x->props.reqid == reqid &&
 		    (mark & x->mark.m) == x->mark.v &&
+		    x->if_id == if_id &&
 		    !(x->props.flags & XFRM_STATE_WILDRECV) &&
 		    xfrm_state_addr_check(x, daddr, saddr, family) &&
 		    mode == x->props.mode &&
@@ -1160,11 +1165,13 @@ static void __xfrm_state_bump_genids(struct xfrm_state *xnew)
 	struct xfrm_state *x;
 	unsigned int h;
 	u32 mark = xnew->mark.v & xnew->mark.m;
+	u32 if_id = xnew->if_id;
 
 	h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family);
 	hlist_for_each_entry(x, net->xfrm.state_bydst+h, bydst) {
 		if (x->props.family	== family &&
 		    x->props.reqid	== reqid &&
+		    x->if_id		== if_id &&
 		    (mark & x->mark.m) == x->mark.v &&
 		    xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) &&
 		    xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family))
@@ -1187,7 +1194,7 @@ EXPORT_SYMBOL(xfrm_state_insert);
 static struct xfrm_state *__find_acq_core(struct net *net,
 					  const struct xfrm_mark *m,
 					  unsigned short family, u8 mode,
-					  u32 reqid, u8 proto,
+					  u32 reqid, u32 if_id, u8 proto,
 					  const xfrm_address_t *daddr,
 					  const xfrm_address_t *saddr,
 					  int create)
@@ -1242,6 +1249,7 @@ static struct xfrm_state *__find_acq_core(struct net *net,
 		x->props.family = family;
 		x->props.mode = mode;
 		x->props.reqid = reqid;
+		x->if_id = if_id;
 		x->mark.v = m->v;
 		x->mark.m = m->m;
 		x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires;
@@ -1296,7 +1304,7 @@ int xfrm_state_add(struct xfrm_state *x)
 
 	if (use_spi && !x1)
 		x1 = __find_acq_core(net, &x->mark, family, x->props.mode,
-				     x->props.reqid, x->id.proto,
+				     x->props.reqid, x->if_id, x->id.proto,
 				     &x->id.daddr, &x->props.saddr, 0);
 
 	__xfrm_state_bump_genids(x);
@@ -1395,6 +1403,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig,
 	x->props.flags = orig->props.flags;
 	x->props.extra_flags = orig->props.extra_flags;
 
+	x->if_id = orig->if_id;
 	x->tfcpad = orig->tfcpad;
 	x->replay_maxdiff = orig->replay_maxdiff;
 	x->replay_maxage = orig->replay_maxage;
@@ -1619,13 +1628,13 @@ EXPORT_SYMBOL(xfrm_state_lookup_byaddr);
 
 struct xfrm_state *
 xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid,
-	      u8 proto, const xfrm_address_t *daddr,
+	      u32 if_id, u8 proto, const xfrm_address_t *daddr,
 	      const xfrm_address_t *saddr, int create, unsigned short family)
 {
 	struct xfrm_state *x;
 
 	spin_lock_bh(&net->xfrm.xfrm_state_lock);
-	x = __find_acq_core(net, mark, family, mode, reqid, proto, daddr, saddr, create);
+	x = __find_acq_core(net, mark, family, mode, reqid, if_id, proto, daddr, saddr, create);
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
 
 	return x;
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 9602cc9e05ab..79245e1c3487 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -594,6 +594,9 @@ static struct xfrm_state *xfrm_state_construct(struct net *net,
 
 	xfrm_smark_init(attrs, &x->props.smark);
 
+	if (attrs[XFRMA_IF_ID])
+		x->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
 	err = __xfrm_init_state(x, false, attrs[XFRMA_OFFLOAD_DEV]);
 	if (err)
 		goto error;
@@ -929,7 +932,11 @@ static int copy_to_user_state_extra(struct xfrm_state *x,
 		ret = copy_user_offload(&x->xso, skb);
 	if (ret)
 		goto out;
-
+	if (x->if_id) {
+		ret = nla_put_u32(skb, XFRMA_IF_ID, x->if_id);
+		if (ret)
+			goto out;
+	}
 	if (x->security)
 		ret = copy_sec_ctx(x->security, skb);
 out:
@@ -1278,6 +1285,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err;
 	u32 mark;
 	struct xfrm_mark m;
+	u32 if_id = 0;
 
 	p = nlmsg_data(nlh);
 	err = verify_spi_info(p->info.id.proto, p->min, p->max);
@@ -1290,6 +1298,10 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 	x = NULL;
 
 	mark = xfrm_mark_get(attrs, &m);
+
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
 	if (p->info.seq) {
 		x = xfrm_find_acq_byseq(net, mark, p->info.seq);
 		if (x && !xfrm_addr_equal(&x->id.daddr, daddr, family)) {
@@ -1300,7 +1312,7 @@ static int xfrm_alloc_userspi(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	if (!x)
 		x = xfrm_find_acq(net, &m, p->info.mode, p->info.reqid,
-				  p->info.id.proto, daddr,
+				  if_id, p->info.id.proto, daddr,
 				  &p->info.saddr, 1,
 				  family);
 	err = -ENOENT;
@@ -1588,6 +1600,9 @@ static struct xfrm_policy *xfrm_policy_construct(struct net *net, struct xfrm_us
 
 	xfrm_mark_get(attrs, &xp->mark);
 
+	if (attrs[XFRMA_IF_ID])
+		xp->if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
 	return xp;
  error:
 	*errp = err;
@@ -1733,6 +1748,8 @@ static int dump_one_policy(struct xfrm_policy *xp, int dir, int count, void *ptr
 		err = copy_to_user_policy_type(xp->type, skb);
 	if (!err)
 		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
 	if (err) {
 		nlmsg_cancel(skb, nlh);
 		return err;
@@ -1814,6 +1831,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int delete;
 	struct xfrm_mark m;
 	u32 mark = xfrm_mark_get(attrs, &m);
+	u32 if_id = 0;
 
 	p = nlmsg_data(nlh);
 	delete = nlh->nlmsg_type == XFRM_MSG_DELPOLICY;
@@ -1826,8 +1844,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		return err;
 
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
 	if (p->index)
-		xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, delete, &err);
+		xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err);
 	else {
 		struct nlattr *rt = attrs[XFRMA_SEC_CTX];
 		struct xfrm_sec_ctx *ctx;
@@ -1844,7 +1865,7 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
 			if (err)
 				return err;
 		}
-		xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir, &p->sel,
+		xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel,
 					   ctx, delete, &err);
 		security_xfrm_policy_free(ctx);
 	}
@@ -1967,6 +1988,10 @@ static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct
 	if (err)
 		goto out_cancel;
 
+	err = xfrm_if_id_put(skb, x->if_id);
+	if (err)
+		goto out_cancel;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -2109,6 +2134,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int err = -ENOENT;
 	struct xfrm_mark m;
 	u32 mark = xfrm_mark_get(attrs, &m);
+	u32 if_id = 0;
 
 	err = copy_from_user_policy_type(&type, attrs);
 	if (err)
@@ -2118,8 +2144,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		return err;
 
+	if (attrs[XFRMA_IF_ID])
+		if_id = nla_get_u32(attrs[XFRMA_IF_ID]);
+
 	if (p->index)
-		xp = xfrm_policy_byid(net, mark, type, p->dir, p->index, 0, &err);
+		xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err);
 	else {
 		struct nlattr *rt = attrs[XFRMA_SEC_CTX];
 		struct xfrm_sec_ctx *ctx;
@@ -2136,7 +2165,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh,
 			if (err)
 				return err;
 		}
-		xp = xfrm_policy_bysel_ctx(net, mark, type, p->dir,
+		xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir,
 					   &p->sel, ctx, 0, &err);
 		security_xfrm_policy_free(ctx);
 	}
@@ -2520,6 +2549,7 @@ static const struct nla_policy xfrma_policy[XFRMA_MAX+1] = {
 	[XFRMA_OFFLOAD_DEV]	= { .len = sizeof(struct xfrm_user_offload) },
 	[XFRMA_SET_MARK]	= { .type = NLA_U32 },
 	[XFRMA_SET_MARK_MASK]	= { .type = NLA_U32 },
+	[XFRMA_IF_ID]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy xfrma_spd_policy[XFRMA_SPD_MAX+1] = {
@@ -2651,6 +2681,10 @@ static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct
 	if (err)
 		return err;
 
+	err = xfrm_if_id_put(skb, x->if_id);
+	if (err)
+		return err;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 }
@@ -2749,6 +2783,8 @@ static inline unsigned int xfrm_sa_len(struct xfrm_state *x)
 		l += nla_total_size(sizeof(x->props.smark.v));
 		l += nla_total_size(sizeof(x->props.smark.m));
 	}
+	if (x->if_id)
+		l += nla_total_size(sizeof(x->if_id));
 
 	/* Must count x->lastused as it may become non-zero behind our back. */
 	l += nla_total_size_64bit(sizeof(u64));
@@ -2878,6 +2914,8 @@ static int build_acquire(struct sk_buff *skb, struct xfrm_state *x,
 		err = copy_to_user_policy_type(xp->type, skb);
 	if (!err)
 		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
 	if (err) {
 		nlmsg_cancel(skb, nlh);
 		return err;
@@ -2994,6 +3032,8 @@ static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp,
 		err = copy_to_user_policy_type(xp->type, skb);
 	if (!err)
 		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
 	if (err) {
 		nlmsg_cancel(skb, nlh);
 		return err;
@@ -3075,6 +3115,8 @@ static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_e
 		err = copy_to_user_policy_type(xp->type, skb);
 	if (!err)
 		err = xfrm_mark_put(skb, &xp->mark);
+	if (!err)
+		err = xfrm_if_id_put(skb, xp->if_id);
 	if (err)
 		goto out_free_skb;
 
-- 
cgit v1.2.3


From f203b76d78092faf248db3f851840fbecf80b40e Mon Sep 17 00:00:00 2001
From: Steffen Klassert <steffen.klassert@secunet.com>
Date: Tue, 12 Jun 2018 14:07:12 +0200
Subject: xfrm: Add virtual xfrm interfaces

This patch adds support for virtual xfrm interfaces.
Packets that are routed through such an interface
are guaranteed to be IPsec transformed or dropped.
It is a generic virtual interface that ensures IPsec
transformation, no need to know what happens behind
the interface. This means that we can tunnel IPv4 and
IPv6 through the same interface and support all xfrm
modes (tunnel, transport and beet) on it.

Co-developed-by: Lorenzo Colitti <lorenzo@google.com>
Co-developed-by: Benedict Wong <benedictwong@google.com>
Signed-off-by: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Benedict Wong <benedictwong@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Benedict Wong <benedictwong@google.com>
Tested-by: Antony Antony <antony@phenome.org>
Reviewed-by: Eyal Birger <eyal.birger@gmail.com>
---
 include/net/xfrm.h           |  24 ++
 include/uapi/linux/if_link.h |  10 +
 net/xfrm/Kconfig             |   8 +
 net/xfrm/Makefile            |   1 +
 net/xfrm/xfrm_input.c        |   3 +
 net/xfrm/xfrm_interface.c    | 972 +++++++++++++++++++++++++++++++++++++++++++
 net/xfrm/xfrm_policy.c       |  43 ++
 7 files changed, 1061 insertions(+)
 create mode 100644 net/xfrm/xfrm_interface.c

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index e8bada4d2a45..3fa578a6a819 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -23,6 +23,7 @@
 #include <net/ipv6.h>
 #include <net/ip6_fib.h>
 #include <net/flow.h>
+#include <net/gro_cells.h>
 
 #include <linux/interrupt.h>
 
@@ -293,6 +294,13 @@ struct xfrm_replay {
 	int	(*overflow)(struct xfrm_state *x, struct sk_buff *skb);
 };
 
+struct xfrm_if_cb {
+	struct xfrm_if	*(*decode_session)(struct sk_buff *skb);
+};
+
+void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb);
+void xfrm_if_unregister_cb(void);
+
 struct net_device;
 struct xfrm_type;
 struct xfrm_dst;
@@ -1039,6 +1047,22 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst)
 
 void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev);
 
+struct xfrm_if_parms {
+	char name[IFNAMSIZ];	/* name of XFRM device */
+	int link;		/* ifindex of underlying L2 interface */
+	u32 if_id;		/* interface identifyer */
+};
+
+struct xfrm_if {
+	struct xfrm_if __rcu *next;	/* next interface in list */
+	struct net_device *dev;		/* virtual device associated with interface */
+	struct net_device *phydev;	/* physical device */
+	struct net *net;		/* netns for packet i/o */
+	struct xfrm_if_parms p;		/* interface parms */
+
+	struct gro_cells gro_cells;
+};
+
 struct xfrm_offload {
 	/* Output sequence number for replay protection on offloading. */
 	struct {
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cf01b6824244..bff0af507b32 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -459,6 +459,16 @@ enum {
 
 #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
 
+/* XFRM section */
+enum {
+	IFLA_XFRM_UNSPEC,
+	IFLA_XFRM_LINK,
+	IFLA_XFRM_IF_ID,
+	__IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
 enum macsec_validation_type {
 	MACSEC_VALIDATE_DISABLED = 0,
 	MACSEC_VALIDATE_CHECK = 1,
diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 286ed25c1a69..53381888a7b3 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -25,6 +25,14 @@ config XFRM_USER
 
 	  If unsure, say Y.
 
+config XFRM_INTERFACE
+	tristate "Transformation virtual interface"
+	depends on XFRM && IPV6
+	---help---
+	  This provides a virtual interface to route IPsec traffic.
+
+	  If unsure, say N.
+
 config XFRM_SUB_POLICY
 	bool "Transformation sub policy support"
 	depends on XFRM
diff --git a/net/xfrm/Makefile b/net/xfrm/Makefile
index 0bd2465a8c5a..fbc4552d17b8 100644
--- a/net/xfrm/Makefile
+++ b/net/xfrm/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_XFRM_STATISTICS) += xfrm_proc.o
 obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o
 obj-$(CONFIG_XFRM_USER) += xfrm_user.o
 obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o
+obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o
diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
index 074810436242..b89c9c7f8c5c 100644
--- a/net/xfrm/xfrm_input.c
+++ b/net/xfrm/xfrm_input.c
@@ -320,6 +320,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 
 	seq = 0;
 	if (!spi && (err = xfrm_parse_spi(skb, nexthdr, &spi, &seq)) != 0) {
+		secpath_reset(skb);
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR);
 		goto drop;
 	}
@@ -328,12 +329,14 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 				   XFRM_SPI_SKB_CB(skb)->daddroff);
 	do {
 		if (skb->sp->len == XFRM_MAX_DEPTH) {
+			secpath_reset(skb);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR);
 			goto drop;
 		}
 
 		x = xfrm_state_lookup(net, mark, daddr, spi, nexthdr, family);
 		if (x == NULL) {
+			secpath_reset(skb);
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOSTATES);
 			xfrm_audit_state_notfound(skb, family, spi, seq);
 			goto drop;
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
new file mode 100644
index 000000000000..31cb1c7e3881
--- /dev/null
+++ b/net/xfrm/xfrm_interface.c
@@ -0,0 +1,972 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *	XFRM virtual interface
+ *
+ *	Copyright (C) 2018 secunet Security Networks AG
+ *
+ *	Author:
+ *	Steffen Klassert <steffen.klassert@secunet.com>
+ */
+
+#include <linux/module.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/sockios.h>
+#include <linux/icmp.h>
+#include <linux/if.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <linux/netdevice.h>
+#include <linux/if_link.h>
+#include <linux/if_arp.h>
+#include <linux/icmpv6.h>
+#include <linux/init.h>
+#include <linux/route.h>
+#include <linux/rtnetlink.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/slab.h>
+#include <linux/hash.h>
+
+#include <linux/uaccess.h>
+#include <linux/atomic.h>
+
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/ip6_route.h>
+#include <net/addrconf.h>
+#include <net/xfrm.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <linux/etherdevice.h>
+
+static int xfrmi_dev_init(struct net_device *dev);
+static void xfrmi_dev_setup(struct net_device *dev);
+static struct rtnl_link_ops xfrmi_link_ops __read_mostly;
+static unsigned int xfrmi_net_id __read_mostly;
+
+struct xfrmi_net {
+	/* lists for storing interfaces in use */
+	struct xfrm_if __rcu *xfrmi[1];
+};
+
+#define for_each_xfrmi_rcu(start, xi) \
+	for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next))
+
+static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x)
+{
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	struct xfrm_if *xi;
+
+	for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
+		if (x->if_id == xi->p.if_id &&
+		    (xi->dev->flags & IFF_UP))
+			return xi;
+	}
+
+	return NULL;
+}
+
+static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb)
+{
+	struct xfrmi_net *xfrmn;
+	int ifindex;
+	struct xfrm_if *xi;
+
+	if (!skb->dev)
+		return NULL;
+
+	xfrmn = net_generic(dev_net(skb->dev), xfrmi_net_id);
+	ifindex = skb->dev->ifindex;
+
+	for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) {
+		if (ifindex == xi->dev->ifindex &&
+			(xi->dev->flags & IFF_UP))
+				return xi;
+	}
+
+	return NULL;
+}
+
+static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
+{
+	struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0];
+
+	rcu_assign_pointer(xi->next , rtnl_dereference(*xip));
+	rcu_assign_pointer(*xip, xi);
+}
+
+static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi)
+{
+	struct xfrm_if __rcu **xip;
+	struct xfrm_if *iter;
+
+	for (xip = &xfrmn->xfrmi[0];
+	     (iter = rtnl_dereference(*xip)) != NULL;
+	     xip = &iter->next) {
+		if (xi == iter) {
+			rcu_assign_pointer(*xip, xi->next);
+			break;
+		}
+	}
+}
+
+static void xfrmi_dev_free(struct net_device *dev)
+{
+	free_percpu(dev->tstats);
+}
+
+static int xfrmi_create2(struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net *net = dev_net(dev);
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	int err;
+
+	dev->rtnl_link_ops = &xfrmi_link_ops;
+	err = register_netdevice(dev);
+	if (err < 0)
+		goto out;
+
+	strcpy(xi->p.name, dev->name);
+
+	dev_hold(dev);
+	xfrmi_link(xfrmn, xi);
+
+	return 0;
+
+out:
+	return err;
+}
+
+static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p)
+{
+	struct net_device *dev;
+	struct xfrm_if *xi;
+	char name[IFNAMSIZ];
+	int err;
+
+	if (p->name[0])
+		strlcpy(name, p->name, IFNAMSIZ);
+	else
+		goto failed;
+
+	dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup);
+	if (!dev)
+		goto failed;
+
+	dev_net_set(dev, net);
+
+	xi = netdev_priv(dev);
+	xi->p = *p;
+	xi->net = net;
+	xi->dev = dev;
+	xi->phydev = dev_get_by_index(net, p->link);
+	if (!xi->phydev)
+		goto failed_free;
+
+	err = xfrmi_create2(dev);
+	if (err < 0)
+		goto failed_dev_put;
+
+	return xi;
+
+failed_dev_put:
+	dev_put(xi->phydev);
+failed_free:
+	free_netdev(dev);
+failed:
+	return NULL;
+}
+
+static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p,
+				   int create)
+{
+	struct xfrm_if __rcu **xip;
+	struct xfrm_if *xi;
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+
+	for (xip = &xfrmn->xfrmi[0];
+	     (xi = rtnl_dereference(*xip)) != NULL;
+	     xip = &xi->next) {
+		if (xi->p.if_id == p->if_id) {
+			if (create)
+				return NULL;
+
+			return xi;
+		}
+	}
+	if (!create)
+		return NULL;
+	return xfrmi_create(net, p);
+}
+
+static void xfrmi_dev_uninit(struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id);
+
+	xfrmi_unlink(xfrmn, xi);
+	dev_put(xi->phydev);
+	dev_put(dev);
+}
+
+static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet)
+{
+	skb->tstamp = 0;
+	skb->pkt_type = PACKET_HOST;
+	skb->skb_iif = 0;
+	skb->ignore_df = 0;
+	skb_dst_drop(skb);
+	nf_reset(skb);
+	nf_reset_trace(skb);
+
+	if (!xnet)
+		return;
+
+	ipvs_reset(skb);
+	secpath_reset(skb);
+	skb_orphan(skb);
+	skb->mark = 0;
+}
+
+static int xfrmi_rcv_cb(struct sk_buff *skb, int err)
+{
+	struct pcpu_sw_netstats *tstats;
+	struct xfrm_mode *inner_mode;
+	struct net_device *dev;
+	struct xfrm_state *x;
+	struct xfrm_if *xi;
+	bool xnet;
+
+	if (err && !skb->sp)
+		return 0;
+
+	x = xfrm_input_state(skb);
+
+	xi = xfrmi_lookup(xs_net(x), x);
+	if (!xi)
+		return 1;
+
+	dev = xi->dev;
+	skb->dev = dev;
+
+	if (err) {
+		dev->stats.rx_errors++;
+		dev->stats.rx_dropped++;
+
+		return 0;
+	}
+
+	xnet = !net_eq(xi->net, dev_net(skb->dev));
+
+	if (xnet) {
+		inner_mode = x->inner_mode;
+
+		if (x->sel.family == AF_UNSPEC) {
+			inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol);
+			if (inner_mode == NULL) {
+				XFRM_INC_STATS(dev_net(skb->dev),
+					       LINUX_MIB_XFRMINSTATEMODEERROR);
+				return -EINVAL;
+			}
+		}
+
+		if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb,
+				       inner_mode->afinfo->family))
+			return -EPERM;
+	}
+
+	xfrmi_scrub_packet(skb, xnet);
+
+	tstats = this_cpu_ptr(dev->tstats);
+
+	u64_stats_update_begin(&tstats->syncp);
+	tstats->rx_packets++;
+	tstats->rx_bytes += skb->len;
+	u64_stats_update_end(&tstats->syncp);
+
+	return 0;
+}
+
+static int
+xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net_device_stats *stats = &xi->dev->stats;
+	struct dst_entry *dst = skb_dst(skb);
+	unsigned int length = skb->len;
+	struct net_device *tdev;
+	struct xfrm_state *x;
+	int err = -1;
+	int mtu;
+
+	if (!dst)
+		goto tx_err_link_failure;
+
+	fl->flowi_xfrm.if_id = xi->p.if_id;
+
+	dst_hold(dst);
+	dst = xfrm_lookup(xi->net, dst, fl, NULL, 0);
+	if (IS_ERR(dst)) {
+		err = PTR_ERR(dst);
+		dst = NULL;
+		goto tx_err_link_failure;
+	}
+
+	x = dst->xfrm;
+	if (!x)
+		goto tx_err_link_failure;
+
+	if (x->if_id != xi->p.if_id)
+		goto tx_err_link_failure;
+
+	tdev = dst->dev;
+
+	if (tdev == dev) {
+		stats->collisions++;
+		net_warn_ratelimited("%s: Local routing loop detected!\n",
+				     xi->p.name);
+		goto tx_err_dst_release;
+	}
+
+	mtu = dst_mtu(dst);
+	if (!skb->ignore_df && skb->len > mtu) {
+		skb_dst_update_pmtu(skb, mtu);
+
+		if (skb->protocol == htons(ETH_P_IPV6)) {
+			if (mtu < IPV6_MIN_MTU)
+				mtu = IPV6_MIN_MTU;
+
+			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
+		} else {
+			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
+				  htonl(mtu));
+		}
+
+		dst_release(dst);
+		return -EMSGSIZE;
+	}
+
+	xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev)));
+	skb_dst_set(skb, dst);
+	skb->dev = tdev;
+
+	err = dst_output(xi->net, skb->sk, skb);
+	if (net_xmit_eval(err) == 0) {
+		struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats);
+
+		u64_stats_update_begin(&tstats->syncp);
+		tstats->tx_bytes += length;
+		tstats->tx_packets++;
+		u64_stats_update_end(&tstats->syncp);
+	} else {
+		stats->tx_errors++;
+		stats->tx_aborted_errors++;
+	}
+
+	return 0;
+tx_err_link_failure:
+	stats->tx_carrier_errors++;
+	dst_link_failure(skb);
+tx_err_dst_release:
+	dst_release(dst);
+	return err;
+}
+
+static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net_device_stats *stats = &xi->dev->stats;
+	struct flowi fl;
+	int ret;
+
+	memset(&fl, 0, sizeof(fl));
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IPV6):
+		xfrm_decode_session(skb, &fl, AF_INET6);
+		memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
+		break;
+	case htons(ETH_P_IP):
+		xfrm_decode_session(skb, &fl, AF_INET);
+		memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
+		break;
+	default:
+		goto tx_err;
+	}
+
+	fl.flowi_oif = xi->phydev->ifindex;
+
+	ret = xfrmi_xmit2(skb, dev, &fl);
+	if (ret < 0)
+		goto tx_err;
+
+	return NETDEV_TX_OK;
+
+tx_err:
+	stats->tx_errors++;
+	stats->tx_dropped++;
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static int xfrmi4_err(struct sk_buff *skb, u32 info)
+{
+	const struct iphdr *iph = (const struct iphdr *)skb->data;
+	struct net *net = dev_net(skb->dev);
+	int protocol = iph->protocol;
+	struct ip_comp_hdr *ipch;
+	struct ip_esp_hdr *esph;
+	struct ip_auth_hdr *ah ;
+	struct xfrm_state *x;
+	struct xfrm_if *xi;
+	__be32 spi;
+
+	switch (protocol) {
+	case IPPROTO_ESP:
+		esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
+		spi = esph->spi;
+		break;
+	case IPPROTO_AH:
+		ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2));
+		spi = ah->spi;
+		break;
+	case IPPROTO_COMP:
+		ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2));
+		spi = htonl(ntohs(ipch->cpi));
+		break;
+	default:
+		return 0;
+	}
+
+	switch (icmp_hdr(skb)->type) {
+	case ICMP_DEST_UNREACH:
+		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
+			return 0;
+	case ICMP_REDIRECT:
+		break;
+	default:
+		return 0;
+	}
+
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, protocol, AF_INET);
+	if (!x)
+		return 0;
+
+	xi = xfrmi_lookup(net, x);
+	if (!xi) {
+		xfrm_state_put(x);
+		return -1;
+	}
+
+	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
+		ipv4_update_pmtu(skb, net, info, 0, 0, protocol, 0);
+	else
+		ipv4_redirect(skb, net, 0, 0, protocol, 0);
+	xfrm_state_put(x);
+
+	return 0;
+}
+
+static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+		    u8 type, u8 code, int offset, __be32 info)
+{
+	const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data;
+	struct net *net = dev_net(skb->dev);
+	int protocol = iph->nexthdr;
+	struct ip_comp_hdr *ipch;
+	struct ip_esp_hdr *esph;
+	struct ip_auth_hdr *ah;
+	struct xfrm_state *x;
+	struct xfrm_if *xi;
+	__be32 spi;
+
+	switch (protocol) {
+	case IPPROTO_ESP:
+		esph = (struct ip_esp_hdr *)(skb->data + offset);
+		spi = esph->spi;
+		break;
+	case IPPROTO_AH:
+		ah = (struct ip_auth_hdr *)(skb->data + offset);
+		spi = ah->spi;
+		break;
+	case IPPROTO_COMP:
+		ipch = (struct ip_comp_hdr *)(skb->data + offset);
+		spi = htonl(ntohs(ipch->cpi));
+		break;
+	default:
+		return 0;
+	}
+
+	if (type != ICMPV6_PKT_TOOBIG &&
+	    type != NDISC_REDIRECT)
+		return 0;
+
+	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
+			      spi, protocol, AF_INET6);
+	if (!x)
+		return 0;
+
+	xi = xfrmi_lookup(net, x);
+	if (!xi) {
+		xfrm_state_put(x);
+		return -1;
+	}
+
+	if (type == NDISC_REDIRECT)
+		ip6_redirect(skb, net, skb->dev->ifindex, 0,
+			     sock_net_uid(net, NULL));
+	else
+		ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
+	xfrm_state_put(x);
+
+	return 0;
+}
+
+static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p)
+{
+	if (xi->p.link != p->link)
+		return -EINVAL;
+
+	xi->p.if_id = p->if_id;
+
+	return 0;
+}
+
+static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p)
+{
+	struct net *net = dev_net(xi->dev);
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+	int err;
+
+	xfrmi_unlink(xfrmn, xi);
+	synchronize_net();
+	err = xfrmi_change(xi, p);
+	xfrmi_link(xfrmn, xi);
+	netdev_state_change(xi->dev);
+	return err;
+}
+
+static void xfrmi_get_stats64(struct net_device *dev,
+			       struct rtnl_link_stats64 *s)
+{
+	int cpu;
+
+	if (!dev->tstats)
+		return;
+
+	for_each_possible_cpu(cpu) {
+		struct pcpu_sw_netstats *stats;
+		struct pcpu_sw_netstats tmp;
+		int start;
+
+		stats = per_cpu_ptr(dev->tstats, cpu);
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			tmp.rx_packets = stats->rx_packets;
+			tmp.rx_bytes   = stats->rx_bytes;
+			tmp.tx_packets = stats->tx_packets;
+			tmp.tx_bytes   = stats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		s->rx_packets += tmp.rx_packets;
+		s->rx_bytes   += tmp.rx_bytes;
+		s->tx_packets += tmp.tx_packets;
+		s->tx_bytes   += tmp.tx_bytes;
+	}
+
+	s->rx_dropped = dev->stats.rx_dropped;
+	s->tx_dropped = dev->stats.tx_dropped;
+}
+
+static int xfrmi_get_iflink(const struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+
+	return xi->phydev->ifindex;
+}
+
+
+static const struct net_device_ops xfrmi_netdev_ops = {
+	.ndo_init	= xfrmi_dev_init,
+	.ndo_uninit	= xfrmi_dev_uninit,
+	.ndo_start_xmit = xfrmi_xmit,
+	.ndo_get_stats64 = xfrmi_get_stats64,
+	.ndo_get_iflink = xfrmi_get_iflink,
+};
+
+static void xfrmi_dev_setup(struct net_device *dev)
+{
+	dev->netdev_ops 	= &xfrmi_netdev_ops;
+	dev->type		= ARPHRD_NONE;
+	dev->hard_header_len 	= ETH_HLEN;
+	dev->min_header_len	= ETH_HLEN;
+	dev->mtu		= ETH_DATA_LEN;
+	dev->min_mtu		= ETH_MIN_MTU;
+	dev->max_mtu		= ETH_DATA_LEN;
+	dev->addr_len		= ETH_ALEN;
+	dev->flags 		= IFF_NOARP;
+	dev->needs_free_netdev	= true;
+	dev->priv_destructor	= xfrmi_dev_free;
+	netif_keep_dst(dev);
+}
+
+static int xfrmi_dev_init(struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net_device *phydev = xi->phydev;
+	int err;
+
+	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
+	if (!dev->tstats)
+		return -ENOMEM;
+
+	err = gro_cells_init(&xi->gro_cells, dev);
+	if (err) {
+		free_percpu(dev->tstats);
+		return err;
+	}
+
+	dev->features |= NETIF_F_LLTX;
+
+	dev->needed_headroom = phydev->needed_headroom;
+	dev->needed_tailroom = phydev->needed_tailroom;
+
+	if (is_zero_ether_addr(dev->dev_addr))
+		eth_hw_addr_inherit(dev, phydev);
+	if (is_zero_ether_addr(dev->broadcast))
+		memcpy(dev->broadcast, phydev->broadcast, dev->addr_len);
+
+	return 0;
+}
+
+static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[],
+			 struct netlink_ext_ack *extack)
+{
+	return 0;
+}
+
+static void xfrmi_netlink_parms(struct nlattr *data[],
+			       struct xfrm_if_parms *parms)
+{
+	memset(parms, 0, sizeof(*parms));
+
+	if (!data)
+		return;
+
+	if (data[IFLA_XFRM_LINK])
+		parms->link = nla_get_u32(data[IFLA_XFRM_LINK]);
+
+	if (data[IFLA_XFRM_IF_ID])
+		parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]);
+}
+
+static int xfrmi_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
+{
+	struct net *net = dev_net(dev);
+	struct xfrm_if_parms *p;
+	struct xfrm_if *xi;
+
+	xi = netdev_priv(dev);
+	p = &xi->p;
+
+	xfrmi_netlink_parms(data, p);
+
+	if (!tb[IFLA_IFNAME])
+		return -EINVAL;
+
+	nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ);
+
+	if (!xfrmi_locate(net, p, 1))
+		return -EEXIST;
+
+	return 0;
+}
+
+static void xfrmi_dellink(struct net_device *dev, struct list_head *head)
+{
+	unregister_netdevice_queue(dev, head);
+}
+
+static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
+			   struct nlattr *data[],
+			   struct netlink_ext_ack *extack)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct net *net = dev_net(dev);
+
+	xfrmi_netlink_parms(data, &xi->p);
+
+	xi = xfrmi_locate(net, &xi->p, 0);
+
+	if (xi) {
+		if (xi->dev != dev)
+			return -EEXIST;
+	} else
+		xi = netdev_priv(dev);
+
+	return xfrmi_update(xi, &xi->p);
+}
+
+static size_t xfrmi_get_size(const struct net_device *dev)
+{
+	return
+		/* IFLA_XFRM_LINK */
+		nla_total_size(4) +
+		/* IFLA_XFRM_IF_ID */
+		nla_total_size(4) +
+		0;
+}
+
+static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+	struct xfrm_if_parms *parm = &xi->p;
+
+	if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) ||
+	    nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+struct net *xfrmi_get_link_net(const struct net_device *dev)
+{
+	struct xfrm_if *xi = netdev_priv(dev);
+
+	return dev_net(xi->phydev);
+}
+
+static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = {
+	[IFLA_XFRM_LINK]	= { .type = NLA_U32 },
+	[IFLA_XFRM_IF_ID]	= { .type = NLA_U32 },
+};
+
+static struct rtnl_link_ops xfrmi_link_ops __read_mostly = {
+	.kind		= "xfrm",
+	.maxtype	= IFLA_XFRM_MAX,
+	.policy		= xfrmi_policy,
+	.priv_size	= sizeof(struct xfrm_if),
+	.setup		= xfrmi_dev_setup,
+	.validate	= xfrmi_validate,
+	.newlink	= xfrmi_newlink,
+	.dellink	= xfrmi_dellink,
+	.changelink	= xfrmi_changelink,
+	.get_size	= xfrmi_get_size,
+	.fill_info	= xfrmi_fill_info,
+	.get_link_net	= xfrmi_get_link_net,
+};
+
+static void __net_exit xfrmi_destroy_interfaces(struct xfrmi_net *xfrmn)
+{
+	struct xfrm_if *xi;
+	LIST_HEAD(list);
+
+	xi = rtnl_dereference(xfrmn->xfrmi[0]);
+	if (!xi)
+		return;
+
+	unregister_netdevice_queue(xi->dev, &list);
+	unregister_netdevice_many(&list);
+}
+
+static int __net_init xfrmi_init_net(struct net *net)
+{
+	return 0;
+}
+
+static void __net_exit xfrmi_exit_net(struct net *net)
+{
+	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
+
+	rtnl_lock();
+	xfrmi_destroy_interfaces(xfrmn);
+	rtnl_unlock();
+}
+
+static struct pernet_operations xfrmi_net_ops = {
+	.init = xfrmi_init_net,
+	.exit = xfrmi_exit_net,
+	.id   = &xfrmi_net_id,
+	.size = sizeof(struct xfrmi_net),
+};
+
+static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = {
+	.handler	=	xfrm6_rcv,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	10,
+};
+
+static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = {
+	.handler	=	xfrm6_rcv,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	10,
+};
+
+static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = {
+	.handler	=	xfrm6_rcv,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi6_err,
+	.priority	=	10,
+};
+
+static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = {
+	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	10,
+};
+
+static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = {
+	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	10,
+};
+
+static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = {
+	.handler	=	xfrm4_rcv,
+	.input_handler	=	xfrm_input,
+	.cb_handler	=	xfrmi_rcv_cb,
+	.err_handler	=	xfrmi4_err,
+	.priority	=	10,
+};
+
+static int __init xfrmi4_init(void)
+{
+	int err;
+
+	err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP);
+	if (err < 0)
+		goto xfrm_proto_esp_failed;
+	err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH);
+	if (err < 0)
+		goto xfrm_proto_ah_failed;
+	err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+	if (err < 0)
+		goto xfrm_proto_comp_failed;
+
+	return 0;
+
+xfrm_proto_comp_failed:
+	xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
+xfrm_proto_ah_failed:
+	xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP);
+xfrm_proto_esp_failed:
+	return err;
+}
+
+static void xfrmi4_fini(void)
+{
+	xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP);
+	xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH);
+	xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP);
+}
+
+static int __init xfrmi6_init(void)
+{
+	int err;
+
+	err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP);
+	if (err < 0)
+		goto xfrm_proto_esp_failed;
+	err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH);
+	if (err < 0)
+		goto xfrm_proto_ah_failed;
+	err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+	if (err < 0)
+		goto xfrm_proto_comp_failed;
+
+	return 0;
+
+xfrm_proto_comp_failed:
+	xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
+xfrm_proto_ah_failed:
+	xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP);
+xfrm_proto_esp_failed:
+	return err;
+}
+
+static void xfrmi6_fini(void)
+{
+	xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP);
+	xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH);
+	xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP);
+}
+
+static const struct xfrm_if_cb xfrm_if_cb = {
+	.decode_session =	xfrmi_decode_session,
+};
+
+static int __init xfrmi_init(void)
+{
+	const char *msg;
+	int err;
+
+	pr_info("IPsec XFRM device driver\n");
+
+	msg = "tunnel device";
+	err = register_pernet_device(&xfrmi_net_ops);
+	if (err < 0)
+		goto pernet_dev_failed;
+
+	msg = "xfrm4 protocols";
+	err = xfrmi4_init();
+	if (err < 0)
+		goto xfrmi4_failed;
+
+	msg = "xfrm6 protocols";
+	err = xfrmi6_init();
+	if (err < 0)
+		goto xfrmi6_failed;
+
+
+	msg = "netlink interface";
+	err = rtnl_link_register(&xfrmi_link_ops);
+	if (err < 0)
+		goto rtnl_link_failed;
+
+	xfrm_if_register_cb(&xfrm_if_cb);
+
+	return err;
+
+rtnl_link_failed:
+	xfrmi6_fini();
+xfrmi6_failed:
+	xfrmi4_fini();
+xfrmi4_failed:
+	unregister_pernet_device(&xfrmi_net_ops);
+pernet_dev_failed:
+	pr_err("xfrmi init: failed to register %s\n", msg);
+	return err;
+}
+
+static void __exit xfrmi_fini(void)
+{
+	xfrm_if_unregister_cb();
+	rtnl_link_unregister(&xfrmi_link_ops);
+	xfrmi4_fini();
+	xfrmi6_fini();
+	unregister_pernet_device(&xfrmi_net_ops);
+}
+
+module_init(xfrmi_init);
+module_exit(xfrmi_fini);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_RTNL_LINK("xfrm");
+MODULE_ALIAS_NETDEV("xfrm0");
+MODULE_AUTHOR("Steffen Klassert");
+MODULE_DESCRIPTION("XFRM virtual interface");
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index fc0c69312b2c..d960ea6657b5 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -47,6 +47,9 @@ struct xfrm_flo {
 
 static DEFINE_PER_CPU(struct xfrm_dst *, xfrm_last_dst);
 static struct work_struct *xfrm_pcpu_work __read_mostly;
+static DEFINE_SPINLOCK(xfrm_if_cb_lock);
+static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
+
 static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock);
 static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1]
 						__read_mostly;
@@ -119,6 +122,12 @@ static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short fa
 	return afinfo;
 }
 
+/* Called with rcu_read_lock(). */
+static const struct xfrm_if_cb *xfrm_if_get_cb(void)
+{
+	return rcu_dereference(xfrm_if_cb);
+}
+
 struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, int oif,
 				    const xfrm_address_t *saddr,
 				    const xfrm_address_t *daddr,
@@ -2083,6 +2092,11 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 
 	if (IS_ERR(xdst)) {
 		err = PTR_ERR(xdst);
+		if (err == -EREMOTE) {
+			xfrm_pols_put(pols, num_pols);
+			return NULL;
+		}
+
 		if (err != -EAGAIN)
 			goto error;
 		goto make_dummy_bundle;
@@ -2176,6 +2190,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 			if (IS_ERR(xdst)) {
 				xfrm_pols_put(pols, num_pols);
 				err = PTR_ERR(xdst);
+				if (err == -EREMOTE)
+					goto nopol;
+
 				goto dropdst;
 			} else if (xdst == NULL) {
 				num_xfrms = 0;
@@ -2368,12 +2385,20 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 			  unsigned int family, int reverse)
 {
 	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
+	const struct xfrm_if_cb *ifcb = xfrm_if_get_cb();
+	struct xfrm_if *xi;
 	int err;
 
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
 
 	afinfo->decode_session(skb, fl, reverse);
+	if (ifcb) {
+		xi = ifcb->decode_session(skb);
+		if (xi)
+			fl->flowi_xfrm.if_id = xi->p.if_id;
+	}
+
 	err = security_xfrm_decode_session(skb, &fl->flowi_secid);
 	rcu_read_unlock();
 	return err;
@@ -2828,6 +2853,21 @@ void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo)
 }
 EXPORT_SYMBOL(xfrm_policy_unregister_afinfo);
 
+void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb)
+{
+	spin_lock(&xfrm_if_cb_lock);
+	rcu_assign_pointer(xfrm_if_cb, ifcb);
+	spin_unlock(&xfrm_if_cb_lock);
+}
+EXPORT_SYMBOL(xfrm_if_register_cb);
+
+void xfrm_if_unregister_cb(void)
+{
+	RCU_INIT_POINTER(xfrm_if_cb, NULL);
+	synchronize_rcu();
+}
+EXPORT_SYMBOL(xfrm_if_unregister_cb);
+
 #ifdef CONFIG_XFRM_STATISTICS
 static int __net_init xfrm_statistics_init(struct net *net)
 {
@@ -3008,6 +3048,9 @@ void __init xfrm_init(void)
 	xfrm_dev_init();
 	seqcount_init(&xfrm_policy_hash_generation);
 	xfrm_input_init();
+
+	RCU_INIT_POINTER(xfrm_if_cb, NULL);
+	synchronize_rcu();
 }
 
 #ifdef CONFIG_AUDITSYSCALL
-- 
cgit v1.2.3


From 63a67a926e214dac94e29147c0f3d11499f655a1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 23 Jun 2018 17:16:44 -0400
Subject: kill dentry_update_name_case()

the last user is gone

Spotted-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 27 ---------------------------
 include/linux/dcache.h |  2 --
 2 files changed, 29 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 0e8e5de3c48a..d9323af88ed0 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2676,33 +2676,6 @@ struct dentry *d_exact_alias(struct dentry *entry, struct inode *inode)
 }
 EXPORT_SYMBOL(d_exact_alias);
 
-/**
- * dentry_update_name_case - update case insensitive dentry with a new name
- * @dentry: dentry to be updated
- * @name: new name
- *
- * Update a case insensitive dentry with new case of name.
- *
- * dentry must have been returned by d_lookup with name @name. Old and new
- * name lengths must match (ie. no d_compare which allows mismatched name
- * lengths).
- *
- * Parent inode i_mutex must be held over d_lookup and into this call (to
- * keep renames and concurrent inserts, and readdir(2) away).
- */
-void dentry_update_name_case(struct dentry *dentry, const struct qstr *name)
-{
-	BUG_ON(!inode_is_locked(dentry->d_parent->d_inode));
-	BUG_ON(dentry->d_name.len != name->len); /* d_lookup gives this */
-
-	spin_lock(&dentry->d_lock);
-	write_seqcount_begin(&dentry->d_seq);
-	memcpy((unsigned char *)dentry->d_name.name, name->name, name->len);
-	write_seqcount_end(&dentry->d_seq);
-	spin_unlock(&dentry->d_lock);
-}
-EXPORT_SYMBOL(dentry_update_name_case);
-
 static void swap_names(struct dentry *dentry, struct dentry *target)
 {
 	if (unlikely(dname_external(target))) {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 66c6e17e61e5..cee70bf207fc 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -271,8 +271,6 @@ extern void d_rehash(struct dentry *);
  
 extern void d_add(struct dentry *, struct inode *);
 
-extern void dentry_update_name_case(struct dentry *, const struct qstr *);
-
 /* used for rename() and baskets */
 extern void d_move(struct dentry *, struct dentry *);
 extern void d_exchange(struct dentry *, struct dentry *);
-- 
cgit v1.2.3


From 50f307401113350a8d46ca45cace07a92c9bedc8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 23 Jun 2018 20:27:29 -0400
Subject: hostfs_lookup: switch to d_splice_alias()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/hostfs/hostfs_kern.c | 28 ++++++++--------------------
 1 file changed, 8 insertions(+), 20 deletions(-)

diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 2597b290c2a5..444c7b170359 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -610,33 +610,21 @@ static struct dentry *hostfs_lookup(struct inode *ino, struct dentry *dentry,
 	int err;
 
 	inode = hostfs_iget(ino->i_sb);
-	if (IS_ERR(inode)) {
-		err = PTR_ERR(inode);
+	if (IS_ERR(inode))
 		goto out;
-	}
 
 	err = -ENOMEM;
 	name = dentry_name(dentry);
-	if (name == NULL)
-		goto out_put;
-
-	err = read_name(inode, name);
-
-	__putname(name);
-	if (err == -ENOENT) {
+	if (name) {
+		err = read_name(inode, name);
+		__putname(name);
+	}
+	if (err) {
 		iput(inode);
-		inode = NULL;
+		inode = (err == -ENOENT) ? NULL : ERR_PTR(err);
 	}
-	else if (err)
-		goto out_put;
-
-	d_add(dentry, inode);
-	return NULL;
-
- out_put:
-	iput(inode);
  out:
-	return ERR_PTR(err);
+	return d_splice_alias(inode, dentry);
 }
 
 static int hostfs_link(struct dentry *to, struct inode *ino,
-- 
cgit v1.2.3


From 9dd64e8f7b62e04cb34e984f637ba331d7e71829 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:03 +0800
Subject: drm/mediatek: update dt-bindings for mt2712

Update device tree binding documentation for the display subsystem for
Mediatek MT2712 SoCs.

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
index 383183a89164..8469de510001 100644
--- a/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
+++ b/Documentation/devicetree/bindings/display/mediatek/mediatek,disp.txt
@@ -40,7 +40,7 @@ Required properties (all function blocks):
 	"mediatek,<chip>-dpi"        - DPI controller, see mediatek,dpi.txt
 	"mediatek,<chip>-disp-mutex" - display mutex
 	"mediatek,<chip>-disp-od"    - overdrive
-  the supported chips are mt2701 and mt8173.
+  the supported chips are mt2701, mt2712 and mt8173.
 - reg: Physical base address and length of the function block register space
 - interrupts: The interrupt signal from the function block (required, except for
   merge and split function blocks).
-- 
cgit v1.2.3


From 8617ec2474fda604d60eefe1bd058a167f265308 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:04 +0800
Subject: drm/mediatek: support maximum 64 mutex mod

This patch support that if modules more than 32,
add index more than 31 when using DISP_REG_MUTEX_MOD2 bit

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 75 +++++++++++++++++++++-------------
 1 file changed, 47 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 8130f3dab661..47ffa240bd25 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -41,31 +41,32 @@
 #define DISP_REG_MUTEX_RST(n)	(0x28 + 0x20 * (n))
 #define DISP_REG_MUTEX_MOD(n)	(0x2c + 0x20 * (n))
 #define DISP_REG_MUTEX_SOF(n)	(0x30 + 0x20 * (n))
+#define DISP_REG_MUTEX_MOD2(n)	(0x34 + 0x20 * (n))
 
 #define INT_MUTEX				BIT(1)
 
-#define MT8173_MUTEX_MOD_DISP_OVL0		BIT(11)
-#define MT8173_MUTEX_MOD_DISP_OVL1		BIT(12)
-#define MT8173_MUTEX_MOD_DISP_RDMA0		BIT(13)
-#define MT8173_MUTEX_MOD_DISP_RDMA1		BIT(14)
-#define MT8173_MUTEX_MOD_DISP_RDMA2		BIT(15)
-#define MT8173_MUTEX_MOD_DISP_WDMA0		BIT(16)
-#define MT8173_MUTEX_MOD_DISP_WDMA1		BIT(17)
-#define MT8173_MUTEX_MOD_DISP_COLOR0		BIT(18)
-#define MT8173_MUTEX_MOD_DISP_COLOR1		BIT(19)
-#define MT8173_MUTEX_MOD_DISP_AAL		BIT(20)
-#define MT8173_MUTEX_MOD_DISP_GAMMA		BIT(21)
-#define MT8173_MUTEX_MOD_DISP_UFOE		BIT(22)
-#define MT8173_MUTEX_MOD_DISP_PWM0		BIT(23)
-#define MT8173_MUTEX_MOD_DISP_PWM1		BIT(24)
-#define MT8173_MUTEX_MOD_DISP_OD		BIT(25)
-
-#define MT2701_MUTEX_MOD_DISP_OVL		BIT(3)
-#define MT2701_MUTEX_MOD_DISP_WDMA		BIT(6)
-#define MT2701_MUTEX_MOD_DISP_COLOR		BIT(7)
-#define MT2701_MUTEX_MOD_DISP_BLS		BIT(9)
-#define MT2701_MUTEX_MOD_DISP_RDMA0		BIT(10)
-#define MT2701_MUTEX_MOD_DISP_RDMA1		BIT(12)
+#define MT8173_MUTEX_MOD_DISP_OVL0		11
+#define MT8173_MUTEX_MOD_DISP_OVL1		12
+#define MT8173_MUTEX_MOD_DISP_RDMA0		13
+#define MT8173_MUTEX_MOD_DISP_RDMA1		14
+#define MT8173_MUTEX_MOD_DISP_RDMA2		15
+#define MT8173_MUTEX_MOD_DISP_WDMA0		16
+#define MT8173_MUTEX_MOD_DISP_WDMA1		17
+#define MT8173_MUTEX_MOD_DISP_COLOR0		18
+#define MT8173_MUTEX_MOD_DISP_COLOR1		19
+#define MT8173_MUTEX_MOD_DISP_AAL		20
+#define MT8173_MUTEX_MOD_DISP_GAMMA		21
+#define MT8173_MUTEX_MOD_DISP_UFOE		22
+#define MT8173_MUTEX_MOD_DISP_PWM0		23
+#define MT8173_MUTEX_MOD_DISP_PWM1		24
+#define MT8173_MUTEX_MOD_DISP_OD		25
+
+#define MT2701_MUTEX_MOD_DISP_OVL		3
+#define MT2701_MUTEX_MOD_DISP_WDMA		6
+#define MT2701_MUTEX_MOD_DISP_COLOR		7
+#define MT2701_MUTEX_MOD_DISP_BLS		9
+#define MT2701_MUTEX_MOD_DISP_RDMA0		10
+#define MT2701_MUTEX_MOD_DISP_RDMA1		12
 
 #define MUTEX_SOF_SINGLE_MODE		0
 #define MUTEX_SOF_DSI0			1
@@ -278,6 +279,7 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	struct mtk_ddp *ddp = container_of(mutex, struct mtk_ddp,
 					   mutex[mutex->id]);
 	unsigned int reg;
+	unsigned int offset;
 
 	WARN_ON(&ddp->mutex[mutex->id] != mutex);
 
@@ -292,9 +294,17 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 		reg = MUTEX_SOF_DPI0;
 		break;
 	default:
-		reg = readl_relaxed(ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
-		reg |= ddp->mutex_mod[id];
-		writel_relaxed(reg, ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
+		if (ddp->mutex_mod[id] < 32) {
+			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg |= 1 << ddp->mutex_mod[id];
+			writel_relaxed(reg, ddp->regs + offset);
+		} else {
+			offset = DISP_REG_MUTEX_MOD2(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg |= 1 << (ddp->mutex_mod[id] - 32);
+			writel_relaxed(reg, ddp->regs + offset);
+		}
 		return;
 	}
 
@@ -307,6 +317,7 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	struct mtk_ddp *ddp = container_of(mutex, struct mtk_ddp,
 					   mutex[mutex->id]);
 	unsigned int reg;
+	unsigned int offset;
 
 	WARN_ON(&ddp->mutex[mutex->id] != mutex);
 
@@ -318,9 +329,17 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 			       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
 		break;
 	default:
-		reg = readl_relaxed(ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
-		reg &= ~(ddp->mutex_mod[id]);
-		writel_relaxed(reg, ddp->regs + DISP_REG_MUTEX_MOD(mutex->id));
+		if (ddp->mutex_mod[id] < 32) {
+			offset = DISP_REG_MUTEX_MOD(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg &= ~(1 << ddp->mutex_mod[id]);
+			writel_relaxed(reg, ddp->regs + offset);
+		} else {
+			offset = DISP_REG_MUTEX_MOD2(mutex->id);
+			reg = readl_relaxed(ddp->regs + offset);
+			reg &= ~(1 << (ddp->mutex_mod[id] - 32));
+			writel_relaxed(reg, ddp->regs + offset);
+		}
 		break;
 	}
 }
-- 
cgit v1.2.3


From d480bbc47425d82d7f6cee0f370e43a1f6aff1a1 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:05 +0800
Subject: drm/mediatek: add ddp component AAL1

This patch add component AAL1 and
rename AAL to AAL0

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c      | 2 +-
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 3 ++-
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 3 ++-
 drivers/gpu/drm/mediatek/mtk_drm_drv.c      | 2 +-
 4 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 47ffa240bd25..7217665f4b5d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -110,7 +110,7 @@ static const unsigned int mt2701_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 };
 
 static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
-	[DDP_COMPONENT_AAL] = MT8173_MUTEX_MOD_DISP_AAL,
+	[DDP_COMPONENT_AAL0] = MT8173_MUTEX_MOD_DISP_AAL,
 	[DDP_COMPONENT_COLOR0] = MT8173_MUTEX_MOD_DISP_COLOR0,
 	[DDP_COMPONENT_COLOR1] = MT8173_MUTEX_MOD_DISP_COLOR1,
 	[DDP_COMPONENT_GAMMA] = MT8173_MUTEX_MOD_DISP_GAMMA,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 4672317e3ad1..0919039805aa 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -218,7 +218,8 @@ struct mtk_ddp_comp_match {
 };
 
 static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
-	[DDP_COMPONENT_AAL]	= { MTK_DISP_AAL,	0, &ddp_aal },
+	[DDP_COMPONENT_AAL0]	= { MTK_DISP_AAL,	0, &ddp_aal },
+	[DDP_COMPONENT_AAL1]	= { MTK_DISP_AAL,	1, &ddp_aal },
 	[DDP_COMPONENT_BLS]	= { MTK_DISP_BLS,	0, NULL },
 	[DDP_COMPONENT_COLOR0]	= { MTK_DISP_COLOR,	0, NULL },
 	[DDP_COMPONENT_COLOR1]	= { MTK_DISP_COLOR,	1, NULL },
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 0828cf8bf85c..eee3c0cc2632 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -41,7 +41,8 @@ enum mtk_ddp_comp_type {
 };
 
 enum mtk_ddp_comp_id {
-	DDP_COMPONENT_AAL,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_AAL1,
 	DDP_COMPONENT_BLS,
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index a2ca90fc403c..a415260f3d5f 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -149,7 +149,7 @@ static const enum mtk_ddp_comp_id mt2701_mtk_ddp_ext[] = {
 static const enum mtk_ddp_comp_id mt8173_mtk_ddp_main[] = {
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_COLOR0,
-	DDP_COMPONENT_AAL,
+	DDP_COMPONENT_AAL0,
 	DDP_COMPONENT_OD,
 	DDP_COMPONENT_RDMA0,
 	DDP_COMPONENT_UFOE,
-- 
cgit v1.2.3


From df2dce4e11a33fa7e3e72d3b4e4570e8f653d387 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:06 +0800
Subject: drm/mediatek: add ddp component OD1

This patch add the component OD1 and
rename the OD to OD0

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c      | 4 ++--
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 3 ++-
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 3 ++-
 drivers/gpu/drm/mediatek/mtk_drm_drv.c      | 2 +-
 4 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 7217665f4b5d..58e44349e315 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -114,7 +114,7 @@ static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_COLOR0] = MT8173_MUTEX_MOD_DISP_COLOR0,
 	[DDP_COMPONENT_COLOR1] = MT8173_MUTEX_MOD_DISP_COLOR1,
 	[DDP_COMPONENT_GAMMA] = MT8173_MUTEX_MOD_DISP_GAMMA,
-	[DDP_COMPONENT_OD] = MT8173_MUTEX_MOD_DISP_OD,
+	[DDP_COMPONENT_OD0] = MT8173_MUTEX_MOD_DISP_OD,
 	[DDP_COMPONENT_OVL0] = MT8173_MUTEX_MOD_DISP_OVL0,
 	[DDP_COMPONENT_OVL1] = MT8173_MUTEX_MOD_DISP_OVL1,
 	[DDP_COMPONENT_PWM0] = MT8173_MUTEX_MOD_DISP_PWM0,
@@ -139,7 +139,7 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_OVL0 && next == DDP_COMPONENT_RDMA0) {
 		*addr = DISP_REG_CONFIG_DISP_OVL_MOUT_EN;
 		value = OVL_MOUT_EN_RDMA;
-	} else if (cur == DDP_COMPONENT_OD && next == DDP_COMPONENT_RDMA0) {
+	} else if (cur == DDP_COMPONENT_OD0 && next == DDP_COMPONENT_RDMA0) {
 		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
 		value = OD_MOUT_EN_RDMA0;
 	} else if (cur == DDP_COMPONENT_UFOE && next == DDP_COMPONENT_DSI0) {
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 0919039805aa..87acf6be87f6 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -227,7 +227,8 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_DSI0]	= { MTK_DSI,		0, NULL },
 	[DDP_COMPONENT_DSI1]	= { MTK_DSI,		1, NULL },
 	[DDP_COMPONENT_GAMMA]	= { MTK_DISP_GAMMA,	0, &ddp_gamma },
-	[DDP_COMPONENT_OD]	= { MTK_DISP_OD,	0, &ddp_od },
+	[DDP_COMPONENT_OD0]	= { MTK_DISP_OD,	0, &ddp_od },
+	[DDP_COMPONENT_OD1]	= { MTK_DISP_OD,	1, &ddp_od },
 	[DDP_COMPONENT_OVL0]	= { MTK_DISP_OVL,	0, NULL },
 	[DDP_COMPONENT_OVL1]	= { MTK_DISP_OVL,	1, NULL },
 	[DDP_COMPONENT_PWM0]	= { MTK_DISP_PWM,	0, NULL },
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index eee3c0cc2632..9b19fc4423f1 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -50,7 +50,8 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_DSI0,
 	DDP_COMPONENT_DSI1,
 	DDP_COMPONENT_GAMMA,
-	DDP_COMPONENT_OD,
+	DDP_COMPONENT_OD0,
+	DDP_COMPONENT_OD1,
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_OVL1,
 	DDP_COMPONENT_PWM0,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index a415260f3d5f..08d5d0b47bfe 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -150,7 +150,7 @@ static const enum mtk_ddp_comp_id mt8173_mtk_ddp_main[] = {
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_AAL0,
-	DDP_COMPONENT_OD,
+	DDP_COMPONENT_OD0,
 	DDP_COMPONENT_RDMA0,
 	DDP_COMPONENT_UFOE,
 	DDP_COMPONENT_DSI0,
-- 
cgit v1.2.3


From 9ec3818eb37104561774c96349ec7a2b0633fbac Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:07 +0800
Subject: drm/mediatek: add ddp component PWM1

This patch add component PWM1 in mtk_ddp_matches

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 87acf6be87f6..a5c7ac2d162d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -232,6 +232,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_OVL0]	= { MTK_DISP_OVL,	0, NULL },
 	[DDP_COMPONENT_OVL1]	= { MTK_DISP_OVL,	1, NULL },
 	[DDP_COMPONENT_PWM0]	= { MTK_DISP_PWM,	0, NULL },
+	[DDP_COMPONENT_PWM1]	= { MTK_DISP_PWM,	1, NULL },
 	[DDP_COMPONENT_RDMA0]	= { MTK_DISP_RDMA,	0, NULL },
 	[DDP_COMPONENT_RDMA1]	= { MTK_DISP_RDMA,	1, NULL },
 	[DDP_COMPONENT_RDMA2]	= { MTK_DISP_RDMA,	2, NULL },
-- 
cgit v1.2.3


From 2e2447784e568bd3469df085d51cd651e6a00993 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:08 +0800
Subject: drm/mediatek: add ddp component PWM2

This patch add component PWM2

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 1 +
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index a5c7ac2d162d..86e8c9e5df41 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -233,6 +233,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_OVL1]	= { MTK_DISP_OVL,	1, NULL },
 	[DDP_COMPONENT_PWM0]	= { MTK_DISP_PWM,	0, NULL },
 	[DDP_COMPONENT_PWM1]	= { MTK_DISP_PWM,	1, NULL },
+	[DDP_COMPONENT_PWM2]	= { MTK_DISP_PWM,	2, NULL },
 	[DDP_COMPONENT_RDMA0]	= { MTK_DISP_RDMA,	0, NULL },
 	[DDP_COMPONENT_RDMA1]	= { MTK_DISP_RDMA,	1, NULL },
 	[DDP_COMPONENT_RDMA2]	= { MTK_DISP_RDMA,	2, NULL },
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 9b19fc4423f1..e00c2e798abd 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -56,6 +56,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_OVL1,
 	DDP_COMPONENT_PWM0,
 	DDP_COMPONENT_PWM1,
+	DDP_COMPONENT_PWM2,
 	DDP_COMPONENT_RDMA0,
 	DDP_COMPONENT_RDMA1,
 	DDP_COMPONENT_RDMA2,
-- 
cgit v1.2.3


From 879a91807f5af1bb02ad3b6019f9729c2b0ea4bf Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:09 +0800
Subject: drm/mediatek: add component DPI1

This patch add the component DPI1

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 2 ++
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 86e8c9e5df41..cc74b1a7278c 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -224,6 +224,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_COLOR0]	= { MTK_DISP_COLOR,	0, NULL },
 	[DDP_COMPONENT_COLOR1]	= { MTK_DISP_COLOR,	1, NULL },
 	[DDP_COMPONENT_DPI0]	= { MTK_DPI,		0, NULL },
+	[DDP_COMPONENT_DPI1]	= { MTK_DPI,		1, NULL },
 	[DDP_COMPONENT_DSI0]	= { MTK_DSI,		0, NULL },
 	[DDP_COMPONENT_DSI1]	= { MTK_DSI,		1, NULL },
 	[DDP_COMPONENT_GAMMA]	= { MTK_DISP_GAMMA,	0, &ddp_gamma },
@@ -275,6 +276,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 
 	if (comp_id == DDP_COMPONENT_BLS ||
 	    comp_id == DDP_COMPONENT_DPI0 ||
+	    comp_id == DDP_COMPONENT_DPI1 ||
 	    comp_id == DDP_COMPONENT_DSI0 ||
 	    comp_id == DDP_COMPONENT_PWM0) {
 		comp->regs = NULL;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index e00c2e798abd..54c99c169093 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -47,6 +47,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_COLOR0,
 	DDP_COMPONENT_COLOR1,
 	DDP_COMPONENT_DPI0,
+	DDP_COMPONENT_DPI1,
 	DDP_COMPONENT_DSI0,
 	DDP_COMPONENT_DSI1,
 	DDP_COMPONENT_GAMMA,
-- 
cgit v1.2.3


From afbff52882325db7cfb65fab014dae5930dce31a Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:10 +0800
Subject: drm/mediatek: add component DSI2

This patch add the component DSI2

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 2 ++
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index cc74b1a7278c..071f9f5aefea 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -227,6 +227,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_DPI1]	= { MTK_DPI,		1, NULL },
 	[DDP_COMPONENT_DSI0]	= { MTK_DSI,		0, NULL },
 	[DDP_COMPONENT_DSI1]	= { MTK_DSI,		1, NULL },
+	[DDP_COMPONENT_DSI2]	= { MTK_DSI,		2, NULL },
 	[DDP_COMPONENT_GAMMA]	= { MTK_DISP_GAMMA,	0, &ddp_gamma },
 	[DDP_COMPONENT_OD0]	= { MTK_DISP_OD,	0, &ddp_od },
 	[DDP_COMPONENT_OD1]	= { MTK_DISP_OD,	1, &ddp_od },
@@ -278,6 +279,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 	    comp_id == DDP_COMPONENT_DPI0 ||
 	    comp_id == DDP_COMPONENT_DPI1 ||
 	    comp_id == DDP_COMPONENT_DSI0 ||
+	    comp_id == DDP_COMPONENT_DSI2 ||
 	    comp_id == DDP_COMPONENT_PWM0) {
 		comp->regs = NULL;
 		comp->clk = NULL;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 54c99c169093..8d152b337f15 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -50,6 +50,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_DPI1,
 	DDP_COMPONENT_DSI0,
 	DDP_COMPONENT_DSI1,
+	DDP_COMPONENT_DSI2,
 	DDP_COMPONENT_GAMMA,
 	DDP_COMPONENT_OD0,
 	DDP_COMPONENT_OD1,
-- 
cgit v1.2.3


From b1df55d308a0489dc7f1531c83607101c3535b8e Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:11 +0800
Subject: drm/mediatek: add component DSI3

This patch add the component DSI3

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 2 ++
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 071f9f5aefea..17b681686471 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -228,6 +228,7 @@ static const struct mtk_ddp_comp_match mtk_ddp_matches[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_DSI0]	= { MTK_DSI,		0, NULL },
 	[DDP_COMPONENT_DSI1]	= { MTK_DSI,		1, NULL },
 	[DDP_COMPONENT_DSI2]	= { MTK_DSI,		2, NULL },
+	[DDP_COMPONENT_DSI3]	= { MTK_DSI,		3, NULL },
 	[DDP_COMPONENT_GAMMA]	= { MTK_DISP_GAMMA,	0, &ddp_gamma },
 	[DDP_COMPONENT_OD0]	= { MTK_DISP_OD,	0, &ddp_od },
 	[DDP_COMPONENT_OD1]	= { MTK_DISP_OD,	1, &ddp_od },
@@ -280,6 +281,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 	    comp_id == DDP_COMPONENT_DPI1 ||
 	    comp_id == DDP_COMPONENT_DSI0 ||
 	    comp_id == DDP_COMPONENT_DSI2 ||
+	    comp_id == DDP_COMPONENT_DSI3 ||
 	    comp_id == DDP_COMPONENT_PWM0) {
 		comp->regs = NULL;
 		comp->clk = NULL;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
index 8d152b337f15..7413ffeb3c9d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.h
@@ -51,6 +51,7 @@ enum mtk_ddp_comp_id {
 	DDP_COMPONENT_DSI0,
 	DDP_COMPONENT_DSI1,
 	DDP_COMPONENT_DSI2,
+	DDP_COMPONENT_DSI3,
 	DDP_COMPONENT_GAMMA,
 	DDP_COMPONENT_OD0,
 	DDP_COMPONENT_OD1,
-- 
cgit v1.2.3


From 6de614026234f900ee55afb8dc8ea5f07b7509cd Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:12 +0800
Subject: drm/mediatek: add the DSI1 for component init condition

This patch add the DSI1 for component init condition

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
index 17b681686471..ff974d82a4a6 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp_comp.c
@@ -280,6 +280,7 @@ int mtk_ddp_comp_init(struct device *dev, struct device_node *node,
 	    comp_id == DDP_COMPONENT_DPI0 ||
 	    comp_id == DDP_COMPONENT_DPI1 ||
 	    comp_id == DDP_COMPONENT_DSI0 ||
+	    comp_id == DDP_COMPONENT_DSI1 ||
 	    comp_id == DDP_COMPONENT_DSI2 ||
 	    comp_id == DDP_COMPONENT_DSI3 ||
 	    comp_id == DDP_COMPONENT_PWM0) {
-- 
cgit v1.2.3


From 9b7b38de386c529d2529bb9670582cec680e239e Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:13 +0800
Subject: drm/mediatek: add connection from OD1 to RDMA1

This patch add the connection from OD1 to RDMA1 for ext path.

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 58e44349e315..8bfc0debd2c2 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -75,6 +75,7 @@
 
 #define OVL0_MOUT_EN_COLOR0		0x1
 #define OD_MOUT_EN_RDMA0		0x1
+#define OD1_MOUT_EN_RDMA1		BIT(16)
 #define UFOE_MOUT_EN_DSI0		0x1
 #define COLOR0_SEL_IN_OVL0		0x1
 #define OVL1_MOUT_EN_COLOR1		0x1
@@ -151,6 +152,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_GAMMA && next == DDP_COMPONENT_RDMA1) {
 		*addr = DISP_REG_CONFIG_DISP_GAMMA_MOUT_EN;
 		value = GAMMA_MOUT_EN_RDMA1;
+	} else if (cur == DDP_COMPONENT_OD1 && next == DDP_COMPONENT_RDMA1) {
+		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
+		value = OD1_MOUT_EN_RDMA1;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_MOUT_EN;
 		value = RDMA1_MOUT_DPI0;
-- 
cgit v1.2.3


From 09013b1619934cb5c5b17d9a5a183c3b20ca8d6e Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:14 +0800
Subject: drm/mediatek: Update the definition of connection from RDMA1 to DPI0

This patch update the definition of connection from RDMA1 to DPI0.
Change the term MOUT to SOUT.

Because our HW datasheet use the term SOUT to match its function for RDMA.
For consistency, changing the name from MOUT to SOUT is better.

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 8bfc0debd2c2..977df8facb79 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -29,7 +29,7 @@
 #define DISP_REG_CONFIG_DISP_COLOR0_SEL_IN	0x084
 #define DISP_REG_CONFIG_DISP_COLOR1_SEL_IN	0x088
 #define DISP_REG_CONFIG_DPI_SEL_IN		0x0ac
-#define DISP_REG_CONFIG_DISP_RDMA1_MOUT_EN	0x0c8
+#define DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN	0x0c8
 #define DISP_REG_CONFIG_MMSYS_CG_CON0		0x100
 
 #define DISP_REG_CONFIG_DISP_OVL_MOUT_EN	0x030
@@ -80,7 +80,7 @@
 #define COLOR0_SEL_IN_OVL0		0x1
 #define OVL1_MOUT_EN_COLOR1		0x1
 #define GAMMA_MOUT_EN_RDMA1		0x1
-#define RDMA1_MOUT_DPI0			0x2
+#define RDMA1_SOUT_DPI0			0x2
 #define DPI0_SEL_IN_RDMA1		0x1
 #define COLOR1_SEL_IN_OVL1		0x1
 
@@ -156,8 +156,8 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
 		value = OD1_MOUT_EN_RDMA1;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
-		*addr = DISP_REG_CONFIG_DISP_RDMA1_MOUT_EN;
-		value = RDMA1_MOUT_DPI0;
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DPI0;
 	} else {
 		value = 0;
 	}
-- 
cgit v1.2.3


From 7b86302401dfdee2b26d99be0d61759a5ab47f11 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:15 +0800
Subject: drm/mediatek: add connection from RDMA0 to DPI0

This patch add the connection from RDMA0 to DPI0

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 977df8facb79..3a3f37f523f2 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -29,6 +29,7 @@
 #define DISP_REG_CONFIG_DISP_COLOR0_SEL_IN	0x084
 #define DISP_REG_CONFIG_DISP_COLOR1_SEL_IN	0x088
 #define DISP_REG_CONFIG_DPI_SEL_IN		0x0ac
+#define DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN	0x0c4
 #define DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN	0x0c8
 #define DISP_REG_CONFIG_MMSYS_CG_CON0		0x100
 
@@ -80,6 +81,7 @@
 #define COLOR0_SEL_IN_OVL0		0x1
 #define OVL1_MOUT_EN_COLOR1		0x1
 #define GAMMA_MOUT_EN_RDMA1		0x1
+#define RDMA0_SOUT_DPI0			0x2
 #define RDMA1_SOUT_DPI0			0x2
 #define DPI0_SEL_IN_RDMA1		0x1
 #define COLOR1_SEL_IN_OVL1		0x1
@@ -155,6 +157,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_OD1 && next == DDP_COMPONENT_RDMA1) {
 		*addr = DISP_REG_CONFIG_DISP_OD_MOUT_EN;
 		value = OD1_MOUT_EN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DPI0;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI0;
-- 
cgit v1.2.3


From 49793b767456863ccd260b61a661e74b8cd6d103 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:16 +0800
Subject: drm/mediatek: add connection from RDMA0 to DSI2

This patch add the connection from RDMA0 to DSI2

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 3a3f37f523f2..f985bad61d83 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -82,6 +82,7 @@
 #define OVL1_MOUT_EN_COLOR1		0x1
 #define GAMMA_MOUT_EN_RDMA1		0x1
 #define RDMA0_SOUT_DPI0			0x2
+#define RDMA0_SOUT_DSI2			0x4
 #define RDMA1_SOUT_DPI0			0x2
 #define DPI0_SEL_IN_RDMA1		0x1
 #define COLOR1_SEL_IN_OVL1		0x1
@@ -160,6 +161,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
 		value = RDMA0_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DSI2;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI0;
-- 
cgit v1.2.3


From 89c04d65022496628dc6f9b01e51533ab26a8d18 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:17 +0800
Subject: drm/mediatek: add connection from RDMA0 to DSI3

This patch add the connection from RDMA0 to DSI3

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index f985bad61d83..463ed7830d17 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -83,6 +83,7 @@
 #define GAMMA_MOUT_EN_RDMA1		0x1
 #define RDMA0_SOUT_DPI0			0x2
 #define RDMA0_SOUT_DSI2			0x4
+#define RDMA0_SOUT_DSI3			0x5
 #define RDMA1_SOUT_DPI0			0x2
 #define DPI0_SEL_IN_RDMA1		0x1
 #define COLOR1_SEL_IN_OVL1		0x1
@@ -164,6 +165,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI2) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
 		value = RDMA0_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
+		value = RDMA0_SOUT_DSI3;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI0;
-- 
cgit v1.2.3


From 73fabd5cebc11eccbf99dacda397c1dcb1198d73 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:18 +0800
Subject: drm/mediatek: add connection from RDMA1 to DPI1

This patch add the connection from RDMA1 to DPI1

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 463ed7830d17..13e91903f493 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -85,7 +85,9 @@
 #define RDMA0_SOUT_DSI2			0x4
 #define RDMA0_SOUT_DSI3			0x5
 #define RDMA1_SOUT_DPI0			0x2
+#define RDMA1_SOUT_DPI1			0x3
 #define DPI0_SEL_IN_RDMA1		0x1
+#define DPI1_SEL_IN_RDMA1		(0x1 << 8)
 #define COLOR1_SEL_IN_OVL1		0x1
 
 #define OVL_MOUT_EN_RDMA		0x1
@@ -171,6 +173,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DPI1;
 	} else {
 		value = 0;
 	}
@@ -190,6 +195,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
 		value = DPI0_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI1_SEL_IN_RDMA1;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From d46a8f851e880695410745a72a69abd6f05c376b Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:19 +0800
Subject: drm/mediatek: add connection from RDMA1 to DSI1

This patch add the connection from RDMA1 to DSI1

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 13e91903f493..90228cad051a 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -28,6 +28,7 @@
 #define DISP_REG_CONFIG_DISP_UFOE_MOUT_EN	0x050
 #define DISP_REG_CONFIG_DISP_COLOR0_SEL_IN	0x084
 #define DISP_REG_CONFIG_DISP_COLOR1_SEL_IN	0x088
+#define DISP_REG_CONFIG_DSIO_SEL_IN		0x0a8
 #define DISP_REG_CONFIG_DPI_SEL_IN		0x0ac
 #define DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN	0x0c4
 #define DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN	0x0c8
@@ -86,8 +87,10 @@
 #define RDMA0_SOUT_DSI3			0x5
 #define RDMA1_SOUT_DPI0			0x2
 #define RDMA1_SOUT_DPI1			0x3
+#define RDMA1_SOUT_DSI1			0x1
 #define DPI0_SEL_IN_RDMA1		0x1
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
+#define DSI1_SEL_IN_RDMA1		0x1
 #define COLOR1_SEL_IN_OVL1		0x1
 
 #define OVL_MOUT_EN_RDMA		0x1
@@ -170,6 +173,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA0 && next == DDP_COMPONENT_DSI3) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN;
 		value = RDMA0_SOUT_DSI3;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI1;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI0;
@@ -198,6 +204,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
 		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
 		value = DPI1_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
+		value = DSI1_SEL_IN_RDMA1;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From 5346010f72226c38de987c366fdf81cb313679ef Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:20 +0800
Subject: drm/mediatek: add connection from RDMA1 to DSI2

This patch add the connection from RDMA1 to DSI2

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 90228cad051a..9cf2fcb4932a 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -28,6 +28,7 @@
 #define DISP_REG_CONFIG_DISP_UFOE_MOUT_EN	0x050
 #define DISP_REG_CONFIG_DISP_COLOR0_SEL_IN	0x084
 #define DISP_REG_CONFIG_DISP_COLOR1_SEL_IN	0x088
+#define DISP_REG_CONFIG_DSIE_SEL_IN		0x0a4
 #define DISP_REG_CONFIG_DSIO_SEL_IN		0x0a8
 #define DISP_REG_CONFIG_DPI_SEL_IN		0x0ac
 #define DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN	0x0c4
@@ -88,9 +89,11 @@
 #define RDMA1_SOUT_DPI0			0x2
 #define RDMA1_SOUT_DPI1			0x3
 #define RDMA1_SOUT_DSI1			0x1
+#define RDMA1_SOUT_DSI2			0x4
 #define DPI0_SEL_IN_RDMA1		0x1
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
 #define DSI1_SEL_IN_RDMA1		0x1
+#define DSI2_SEL_IN_RDMA1		(0x1 << 16)
 #define COLOR1_SEL_IN_OVL1		0x1
 
 #define OVL_MOUT_EN_RDMA		0x1
@@ -176,6 +179,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DSI1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI2;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI0;
@@ -207,6 +213,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI1) {
 		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
 		value = DSI1_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI2_SEL_IN_RDMA1;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From 15484ae0afa9286f166bdb64a97700f215ada956 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:21 +0800
Subject: drm/mediatek: add connection from RDMA1 to DSI3

This patch add the connection from RDMA1 to DSI3

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 9cf2fcb4932a..d0d5f337ce14 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -90,10 +90,12 @@
 #define RDMA1_SOUT_DPI1			0x3
 #define RDMA1_SOUT_DSI1			0x1
 #define RDMA1_SOUT_DSI2			0x4
+#define RDMA1_SOUT_DSI3			0x5
 #define DPI0_SEL_IN_RDMA1		0x1
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
 #define DSI1_SEL_IN_RDMA1		0x1
 #define DSI2_SEL_IN_RDMA1		(0x1 << 16)
+#define DSI3_SEL_IN_RDMA1		(0x1 << 16)
 #define COLOR1_SEL_IN_OVL1		0x1
 
 #define OVL_MOUT_EN_RDMA		0x1
@@ -182,6 +184,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
+		value = RDMA1_SOUT_DSI3;
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI0;
@@ -216,6 +221,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI2) {
 		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
 		value = DSI2_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
+		value = DSI3_SEL_IN_RDMA1;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From 01915b8588142af11a9416dcbb4e58bc0518c3ee Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:22 +0800
Subject: drm/mediatek: add connection from RDMA2 to DPI0

This patch add the connection from RDMA2 to DPI0

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index d0d5f337ce14..c88742a6c2b9 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -31,6 +31,7 @@
 #define DISP_REG_CONFIG_DSIE_SEL_IN		0x0a4
 #define DISP_REG_CONFIG_DSIO_SEL_IN		0x0a8
 #define DISP_REG_CONFIG_DPI_SEL_IN		0x0ac
+#define DISP_REG_CONFIG_DISP_RDMA2_SOUT		0x0b8
 #define DISP_REG_CONFIG_DISP_RDMA0_SOUT_EN	0x0c4
 #define DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN	0x0c8
 #define DISP_REG_CONFIG_MMSYS_CG_CON0		0x100
@@ -91,7 +92,9 @@
 #define RDMA1_SOUT_DSI1			0x1
 #define RDMA1_SOUT_DSI2			0x4
 #define RDMA1_SOUT_DSI3			0x5
+#define RDMA2_SOUT_DPI0			0x2
 #define DPI0_SEL_IN_RDMA1		0x1
+#define DPI0_SEL_IN_RDMA2		0x3
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
 #define DSI1_SEL_IN_RDMA1		0x1
 #define DSI2_SEL_IN_RDMA1		(0x1 << 16)
@@ -193,6 +196,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DPI1) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA1_SOUT_EN;
 		value = RDMA1_SOUT_DPI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DPI0;
 	} else {
 		value = 0;
 	}
@@ -224,6 +230,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA1 && next == DDP_COMPONENT_DSI3) {
 		*addr = DISP_REG_CONFIG_DSIO_SEL_IN;
 		value = DSI3_SEL_IN_RDMA1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI0_SEL_IN_RDMA2;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From 7ddac091673c576f010aca262bb56f5e25fc5577 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:23 +0800
Subject: drm/mediatek: add connection from RDMA2 to DPI1

This patch add the connection from RDMA2 to DPI1

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index c88742a6c2b9..a4b418302f32 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -93,9 +93,11 @@
 #define RDMA1_SOUT_DSI2			0x4
 #define RDMA1_SOUT_DSI3			0x5
 #define RDMA2_SOUT_DPI0			0x2
+#define RDMA2_SOUT_DPI1			0x3
 #define DPI0_SEL_IN_RDMA1		0x1
 #define DPI0_SEL_IN_RDMA2		0x3
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
+#define DPI1_SEL_IN_RDMA2		(0x3 << 8)
 #define DSI1_SEL_IN_RDMA1		0x1
 #define DSI2_SEL_IN_RDMA1		(0x1 << 16)
 #define DSI3_SEL_IN_RDMA1		(0x1 << 16)
@@ -199,6 +201,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
 		value = RDMA2_SOUT_DPI0;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DPI1;
 	} else {
 		value = 0;
 	}
@@ -233,6 +238,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI0) {
 		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
 		value = DPI0_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
+		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
+		value = DPI1_SEL_IN_RDMA2;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From 0064be8c71fd38d9d65c18d3561d9ea48d759387 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:24 +0800
Subject: drm/mediatek: add connection from RDMA2 to DSI1

This patch add the connection from RDMA2 to DSI1

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index a4b418302f32..db78fad785e3 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -94,11 +94,13 @@
 #define RDMA1_SOUT_DSI3			0x5
 #define RDMA2_SOUT_DPI0			0x2
 #define RDMA2_SOUT_DPI1			0x3
+#define RDMA2_SOUT_DSI1			0x1
 #define DPI0_SEL_IN_RDMA1		0x1
 #define DPI0_SEL_IN_RDMA2		0x3
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
 #define DPI1_SEL_IN_RDMA2		(0x3 << 8)
 #define DSI1_SEL_IN_RDMA1		0x1
+#define DSI1_SEL_IN_RDMA2		0x4
 #define DSI2_SEL_IN_RDMA1		(0x1 << 16)
 #define DSI3_SEL_IN_RDMA1		(0x1 << 16)
 #define COLOR1_SEL_IN_OVL1		0x1
@@ -204,6 +206,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
 		value = RDMA2_SOUT_DPI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI1;
 	} else {
 		value = 0;
 	}
@@ -241,6 +246,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DPI1) {
 		*addr = DISP_REG_CONFIG_DPI_SEL_IN;
 		value = DPI1_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI1_SEL_IN_RDMA2;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From 46ce9b2dc78ca7f8e224fb74c71f3d4caf2f7dab Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:25 +0800
Subject: drm/mediatek: add connection from RDMA2 to DSI2

This patch add the connection from RDMA2 to DSI2

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index db78fad785e3..e5db1ab51c9b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -95,6 +95,7 @@
 #define RDMA2_SOUT_DPI0			0x2
 #define RDMA2_SOUT_DPI1			0x3
 #define RDMA2_SOUT_DSI1			0x1
+#define RDMA2_SOUT_DSI2			0x4
 #define DPI0_SEL_IN_RDMA1		0x1
 #define DPI0_SEL_IN_RDMA2		0x3
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
@@ -102,6 +103,7 @@
 #define DSI1_SEL_IN_RDMA1		0x1
 #define DSI1_SEL_IN_RDMA2		0x4
 #define DSI2_SEL_IN_RDMA1		(0x1 << 16)
+#define DSI2_SEL_IN_RDMA2		(0x4 << 16)
 #define DSI3_SEL_IN_RDMA1		(0x1 << 16)
 #define COLOR1_SEL_IN_OVL1		0x1
 
@@ -209,6 +211,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
 		value = RDMA2_SOUT_DSI1;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI2;
 	} else {
 		value = 0;
 	}
@@ -249,6 +254,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI1) {
 		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
 		value = DSI1_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI2_SEL_IN_RDMA2;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From d335369e7543fdf8f9111d8b03a8cae3e1526434 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:26 +0800
Subject: drm/mediatek: add connection from RDMA2 to DSI3

This patch add the connection from RDMA2 to DSI3

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index e5db1ab51c9b..0a1b967cab1b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -96,6 +96,7 @@
 #define RDMA2_SOUT_DPI1			0x3
 #define RDMA2_SOUT_DSI1			0x1
 #define RDMA2_SOUT_DSI2			0x4
+#define RDMA2_SOUT_DSI3			0x5
 #define DPI0_SEL_IN_RDMA1		0x1
 #define DPI0_SEL_IN_RDMA2		0x3
 #define DPI1_SEL_IN_RDMA1		(0x1 << 8)
@@ -105,6 +106,7 @@
 #define DSI2_SEL_IN_RDMA1		(0x1 << 16)
 #define DSI2_SEL_IN_RDMA2		(0x4 << 16)
 #define DSI3_SEL_IN_RDMA1		(0x1 << 16)
+#define DSI3_SEL_IN_RDMA2		(0x4 << 16)
 #define COLOR1_SEL_IN_OVL1		0x1
 
 #define OVL_MOUT_EN_RDMA		0x1
@@ -214,6 +216,9 @@ static unsigned int mtk_ddp_mout_en(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
 		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
 		value = RDMA2_SOUT_DSI2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DISP_RDMA2_SOUT;
+		value = RDMA2_SOUT_DSI3;
 	} else {
 		value = 0;
 	}
@@ -257,6 +262,9 @@ static unsigned int mtk_ddp_sel_in(enum mtk_ddp_comp_id cur,
 	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI2) {
 		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
 		value = DSI2_SEL_IN_RDMA2;
+	} else if (cur == DDP_COMPONENT_RDMA2 && next == DDP_COMPONENT_DSI3) {
+		*addr = DISP_REG_CONFIG_DSIE_SEL_IN;
+		value = DSI3_SEL_IN_RDMA2;
 	} else if (cur == DDP_COMPONENT_OVL1 && next == DDP_COMPONENT_COLOR1) {
 		*addr = DISP_REG_CONFIG_DISP_COLOR1_SEL_IN;
 		value = COLOR1_SEL_IN_OVL1;
-- 
cgit v1.2.3


From f4f3ec480e82fa0c8c93a02b01e46719e4985752 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:27 +0800
Subject: drm/mediatek: add DPI1 support for mutex

This patch add the DPI1 support for mutex

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 0a1b967cab1b..4c203d013d7c 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -76,6 +76,7 @@
 #define MUTEX_SOF_DSI0			1
 #define MUTEX_SOF_DSI1			2
 #define MUTEX_SOF_DPI0			3
+#define MUTEX_SOF_DPI1			4
 
 #define OVL0_MOUT_EN_COLOR0		0x1
 #define OD_MOUT_EN_RDMA0		0x1
@@ -385,6 +386,9 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DPI0:
 		reg = MUTEX_SOF_DPI0;
 		break;
+	case DDP_COMPONENT_DPI1:
+		reg = MUTEX_SOF_DPI1;
+		break;
 	default:
 		if (ddp->mutex_mod[id] < 32) {
 			offset = DISP_REG_MUTEX_MOD(mutex->id);
@@ -417,6 +421,7 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DSI0:
 	case DDP_COMPONENT_DSI1:
 	case DDP_COMPONENT_DPI0:
+	case DDP_COMPONENT_DPI1:
 		writel_relaxed(MUTEX_SOF_SINGLE_MODE,
 			       ddp->regs + DISP_REG_MUTEX_SOF(mutex->id));
 		break;
-- 
cgit v1.2.3


From dee8eb4e668d059d2cc3a92717006da50bb2d491 Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:28 +0800
Subject: drm/mediatek: add DSI2 support for mutex

This patch add the DSI2 support for mutex

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 4c203d013d7c..a0b526b16da1 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -77,6 +77,7 @@
 #define MUTEX_SOF_DSI1			2
 #define MUTEX_SOF_DPI0			3
 #define MUTEX_SOF_DPI1			4
+#define MUTEX_SOF_DSI2			5
 
 #define OVL0_MOUT_EN_COLOR0		0x1
 #define OD_MOUT_EN_RDMA0		0x1
@@ -383,6 +384,9 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DSI1:
 		reg = MUTEX_SOF_DSI0;
 		break;
+	case DDP_COMPONENT_DSI2:
+		reg = MUTEX_SOF_DSI2;
+		break;
 	case DDP_COMPONENT_DPI0:
 		reg = MUTEX_SOF_DPI0;
 		break;
@@ -420,6 +424,7 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	switch (id) {
 	case DDP_COMPONENT_DSI0:
 	case DDP_COMPONENT_DSI1:
+	case DDP_COMPONENT_DSI2:
 	case DDP_COMPONENT_DPI0:
 	case DDP_COMPONENT_DPI1:
 		writel_relaxed(MUTEX_SOF_SINGLE_MODE,
-- 
cgit v1.2.3


From 16dd757ead7a05e9cb88db9972916eef4e0a842a Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:29 +0800
Subject: drm/mediatek: add DSI3 support for mutex

This patch add the DSI3 support for mutex

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index a0b526b16da1..15e436d4e8a0 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -78,6 +78,7 @@
 #define MUTEX_SOF_DPI0			3
 #define MUTEX_SOF_DPI1			4
 #define MUTEX_SOF_DSI2			5
+#define MUTEX_SOF_DSI3			6
 
 #define OVL0_MOUT_EN_COLOR0		0x1
 #define OD_MOUT_EN_RDMA0		0x1
@@ -387,6 +388,9 @@ void mtk_disp_mutex_add_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DSI2:
 		reg = MUTEX_SOF_DSI2;
 		break;
+	case DDP_COMPONENT_DSI3:
+		reg = MUTEX_SOF_DSI3;
+		break;
 	case DDP_COMPONENT_DPI0:
 		reg = MUTEX_SOF_DPI0;
 		break;
@@ -425,6 +429,7 @@ void mtk_disp_mutex_remove_comp(struct mtk_disp_mutex *mutex,
 	case DDP_COMPONENT_DSI0:
 	case DDP_COMPONENT_DSI1:
 	case DDP_COMPONENT_DSI2:
+	case DDP_COMPONENT_DSI3:
 	case DDP_COMPONENT_DPI0:
 	case DDP_COMPONENT_DPI1:
 		writel_relaxed(MUTEX_SOF_SINGLE_MODE,
-- 
cgit v1.2.3


From 561fad31e697b73c22e0373e01a33311912b58eb Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:30 +0800
Subject: drm/mediatek: add third ddp path

This patch create third crtc by third ddp path

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_crtc.c | 3 +++
 drivers/gpu/drm/mediatek/mtk_drm_drv.c  | 5 +++++
 drivers/gpu/drm/mediatek/mtk_drm_drv.h  | 5 ++++-
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
index 658b8dd45b83..2d6aa150a9ff 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_crtc.c
@@ -539,6 +539,9 @@ int mtk_drm_crtc_create(struct drm_device *drm_dev,
 	int ret;
 	int i;
 
+	if (!path)
+		return 0;
+
 	for (i = 0; i < path_len; i++) {
 		enum mtk_ddp_comp_id comp_id = path[i];
 		struct device_node *node;
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 08d5d0b47bfe..3d279a299383 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -232,6 +232,11 @@ static int mtk_drm_kms_init(struct drm_device *drm)
 	if (ret < 0)
 		goto err_component_unbind;
 
+	ret = mtk_drm_crtc_create(drm, private->data->third_path,
+				  private->data->third_len);
+	if (ret < 0)
+		goto err_component_unbind;
+
 	/* Use OVL device for all DMA memory allocations */
 	np = private->comp_node[private->data->main_path[0]] ?:
 	     private->comp_node[private->data->ext_path[0]];
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
index c3378c452c0a..ecc00ca3221d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
@@ -17,7 +17,7 @@
 #include <linux/io.h>
 #include "mtk_drm_ddp_comp.h"
 
-#define MAX_CRTC	2
+#define MAX_CRTC	3
 #define MAX_CONNECTOR	2
 
 struct device;
@@ -33,6 +33,9 @@ struct mtk_mmsys_driver_data {
 	unsigned int main_len;
 	const enum mtk_ddp_comp_id *ext_path;
 	unsigned int ext_len;
+	const enum mtk_ddp_comp_id *third_path;
+	unsigned int third_len;
+
 	bool shadow_register;
 };
 
-- 
cgit v1.2.3


From b0c1638f26a5f8d593e79b226e8dec0bcd5adc3e Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Sat, 23 Jun 2018 21:28:22 -0300
Subject: net: phy: fixed-phy: Make the error path simpler

When platform_device_register_simple() fails we can return
the error immediately instead of jumping to the 'err_pdev'
label.

This makes the error path a bit simpler.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/fixed_phy.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index 001fe1df7557..67b260877f30 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -259,10 +259,8 @@ static int __init fixed_mdio_bus_init(void)
 	int ret;
 
 	pdev = platform_device_register_simple("Fixed MDIO bus", 0, NULL, 0);
-	if (IS_ERR(pdev)) {
-		ret = PTR_ERR(pdev);
-		goto err_pdev;
-	}
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
 
 	fmb->mii_bus = mdiobus_alloc();
 	if (fmb->mii_bus == NULL) {
@@ -287,7 +285,6 @@ err_mdiobus_alloc:
 	mdiobus_free(fmb->mii_bus);
 err_mdiobus_reg:
 	platform_device_unregister(pdev);
-err_pdev:
 	return ret;
 }
 module_init(fixed_mdio_bus_init);
-- 
cgit v1.2.3


From fe0b082fedd1d09c73c48883f04a9fe2967b5899 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Sat, 23 Jun 2018 13:46:39 -0700
Subject: net_sched: remove unused htb drop_list

After commit a09ceb0e0814 ("sched: remove qdisc->drop"),
it is no longer used.

Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_htb.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 2a4ab7caf553..43c4bfe625a9 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -126,7 +126,6 @@ struct htb_class {
 
 	union {
 		struct htb_class_leaf {
-			struct list_head drop_list;
 			int		deficit[TC_HTB_MAXDEPTH];
 			struct Qdisc	*q;
 		} leaf;
@@ -171,7 +170,6 @@ struct htb_sched {
 	struct qdisc_watchdog	watchdog;
 
 	s64			now;	/* cached dequeue time */
-	struct list_head	drops[TC_HTB_NUMPRIO];/* active leaves (for drops) */
 
 	/* time of nearest event per level (row) */
 	s64			near_ev_cache[TC_HTB_MAXDEPTH];
@@ -562,8 +560,6 @@ static inline void htb_activate(struct htb_sched *q, struct htb_class *cl)
 	if (!cl->prio_activity) {
 		cl->prio_activity = 1 << cl->prio;
 		htb_activate_prios(q, cl);
-		list_add_tail(&cl->un.leaf.drop_list,
-			      q->drops + cl->prio);
 	}
 }
 
@@ -579,7 +575,6 @@ static inline void htb_deactivate(struct htb_sched *q, struct htb_class *cl)
 
 	htb_deactivate_prios(q, cl);
 	cl->prio_activity = 0;
-	list_del_init(&cl->un.leaf.drop_list);
 }
 
 static void htb_enqueue_tail(struct sk_buff *skb, struct Qdisc *sch,
@@ -981,7 +976,6 @@ static void htb_reset(struct Qdisc *sch)
 			else {
 				if (cl->un.leaf.q)
 					qdisc_reset(cl->un.leaf.q);
-				INIT_LIST_HEAD(&cl->un.leaf.drop_list);
 			}
 			cl->prio_activity = 0;
 			cl->cmode = HTB_CAN_SEND;
@@ -993,8 +987,6 @@ static void htb_reset(struct Qdisc *sch)
 	sch->qstats.backlog = 0;
 	memset(q->hlevel, 0, sizeof(q->hlevel));
 	memset(q->row_mask, 0, sizeof(q->row_mask));
-	for (i = 0; i < TC_HTB_NUMPRIO; i++)
-		INIT_LIST_HEAD(q->drops + i);
 }
 
 static const struct nla_policy htb_policy[TCA_HTB_MAX + 1] = {
@@ -1024,7 +1016,6 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 	struct nlattr *tb[TCA_HTB_MAX + 1];
 	struct tc_htb_glob *gopt;
 	int err;
-	int i;
 
 	qdisc_watchdog_init(&q->watchdog, sch);
 	INIT_WORK(&q->work, htb_work_func);
@@ -1050,8 +1041,6 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt,
 	err = qdisc_class_hash_init(&q->clhash);
 	if (err < 0)
 		return err;
-	for (i = 0; i < TC_HTB_NUMPRIO; i++)
-		INIT_LIST_HEAD(q->drops + i);
 
 	qdisc_skb_head_init(&q->direct_queue);
 
@@ -1224,7 +1213,6 @@ static void htb_parent_to_leaf(struct htb_sched *q, struct htb_class *cl,
 
 	parent->level = 0;
 	memset(&parent->un.inner, 0, sizeof(parent->un.inner));
-	INIT_LIST_HEAD(&parent->un.leaf.drop_list);
 	parent->un.leaf.q = new_q ? new_q : &noop_qdisc;
 	parent->tokens = parent->buffer;
 	parent->ctokens = parent->cbuffer;
@@ -1418,7 +1406,6 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 		}
 
 		cl->children = 0;
-		INIT_LIST_HEAD(&cl->un.leaf.drop_list);
 		RB_CLEAR_NODE(&cl->pq_node);
 
 		for (prio = 0; prio < TC_HTB_NUMPRIO; prio++)
-- 
cgit v1.2.3


From 836557bd58e5e65c05c73af9f6ebed885dbfccfc Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 24 Jun 2018 10:35:18 +0200
Subject: genirq: Update code comments wrt recycled thread_mask

Previously a race existed between __free_irq() and __setup_irq() wherein
the thread_mask of a just removed action could be handed out to a newly
added action and the freed irq thread would then tread on the oneshot
mask bit of the newly added irq thread in irq_finalize_oneshot():

time
 |  __free_irq()
 |    raw_spin_lock_irqsave(&desc->lock, flags);
 |    <remove action from linked list>
 |    raw_spin_unlock_irqrestore(&desc->lock, flags);
 |
 |  __setup_irq()
 |    raw_spin_lock_irqsave(&desc->lock, flags);
 |    <traverse linked list to determine oneshot mask bit>
 |    raw_spin_unlock_irqrestore(&desc->lock, flags);
 |
 |  irq_thread() of freed irq (__free_irq() waits in synchronize_irq())
 |    irq_thread_fn()
 |      irq_finalize_oneshot()
 |        raw_spin_lock_irq(&desc->lock);
 |        desc->threads_oneshot &= ~action->thread_mask;
 |        raw_spin_unlock_irq(&desc->lock);
 v

The race was known at least since 2012 when it was documented in a code
comment by commit e04268b0effc ("genirq: Remove paranoid warnons and bogus
fixups"). The race itself is harmless as nothing touches any of the
potentially freed data after synchronize_irq().

In 2017 the race was close by commit 9114014cf4e6 ("genirq: Add mutex to
irq desc to serialize request/free_irq()"), apparently inadvertantly so
because the race is neither mentioned in the commit message nor was the
code comment updated.  Make up for that.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: linux-pci@vger.kernel.org
Link: https://lkml.kernel.org/r/32fc25aa35ecef4b2692f57687bb7fc2a57230e2.1529828292.git.lukas@wunner.de
---
 kernel/irq/manage.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 591cfe901162..123a227d3357 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1025,10 +1025,7 @@ static int irq_thread(void *data)
 	 * This is the regular exit path. __free_irq() is stopping the
 	 * thread via kthread_stop() after calling
 	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
-	 * oneshot mask bit can be set. We cannot verify that as we
-	 * cannot touch the oneshot mask at this point anymore as
-	 * __setup_irq() might have given out currents thread_mask
-	 * again.
+	 * oneshot mask bit can be set.
 	 */
 	task_work_cancel(current, irq_thread_dtor);
 	return 0;
@@ -1245,7 +1242,9 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	/*
 	 * Protects against a concurrent __free_irq() call which might wait
 	 * for synchronize_irq() to complete without holding the optional
-	 * chip bus lock and desc->lock.
+	 * chip bus lock and desc->lock. Also protects against handing out
+	 * a recycled oneshot thread_mask bit while it's still in use by
+	 * its previous owner.
 	 */
 	mutex_lock(&desc->request_mutex);
 
-- 
cgit v1.2.3


From 519cc8652b3a1d3d0a02257afbe9573ad644da26 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 24 Jun 2018 10:35:30 +0200
Subject: genirq: Synchronize only with single thread on free_irq()

When pciehp is converted to threaded IRQ handling, removal of unplugged
devices below a PCIe hotplug port happens synchronously in the IRQ thread.
Removal of devices typically entails a call to free_irq() by their drivers.

If those devices share their IRQ with the hotplug port, __free_irq()
deadlocks because it calls synchronize_irq() to wait for all hard IRQ
handlers as well as all threads sharing the IRQ to finish.

Actually it's sufficient to wait only for the IRQ thread of the removed
device, so call synchronize_hardirq() to wait for all hard IRQ handlers to
finish, but no longer for any threads.  Compensate by rearranging the
control flow in irq_wait_for_interrupt() such that the device's thread is
allowed to run one last time after kthread_stop() has been called.

kthread_stop() blocks until the IRQ thread has completed.  On completion
the IRQ thread clears its oneshot thread_mask bit.  This is safe because
__free_irq() holds the request_mutex, thereby preventing __setup_irq() from
handing out the same oneshot thread_mask bit to a newly requested action.

Stack trace for posterity:
    INFO: task irq/17-pciehp:94 blocked for more than 120 seconds.
    schedule+0x28/0x80
    synchronize_irq+0x6e/0xa0
    __free_irq+0x15a/0x2b0
    free_irq+0x33/0x70
    pciehp_release_ctrl+0x98/0xb0
    pcie_port_remove_service+0x2f/0x40
    device_release_driver_internal+0x157/0x220
    bus_remove_device+0xe2/0x150
    device_del+0x124/0x340
    device_unregister+0x16/0x60
    remove_iter+0x1a/0x20
    device_for_each_child+0x4b/0x90
    pcie_port_device_remove+0x1e/0x30
    pci_device_remove+0x36/0xb0
    device_release_driver_internal+0x157/0x220
    pci_stop_bus_device+0x7d/0xa0
    pci_stop_bus_device+0x3d/0xa0
    pci_stop_and_remove_bus_device+0xe/0x20
    pciehp_unconfigure_device+0xb8/0x160
    pciehp_disable_slot+0x84/0x130
    pciehp_ist+0x158/0x190
    irq_thread_fn+0x1b/0x50
    irq_thread+0x143/0x1a0
    kthread+0x111/0x130

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: linux-pci@vger.kernel.org
Link: https://lkml.kernel.org/r/d72b41309f077c8d3bee6cc08ad3662d50b5d22a.1529828292.git.lukas@wunner.de
---
 kernel/irq/manage.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 123a227d3357..1f8be33572a7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -790,9 +790,19 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
 
 static int irq_wait_for_interrupt(struct irqaction *action)
 {
-	set_current_state(TASK_INTERRUPTIBLE);
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE);
 
-	while (!kthread_should_stop()) {
+		if (kthread_should_stop()) {
+			/* may need to run one last time */
+			if (test_and_clear_bit(IRQTF_RUNTHREAD,
+					       &action->thread_flags)) {
+				__set_current_state(TASK_RUNNING);
+				return 0;
+			}
+			__set_current_state(TASK_RUNNING);
+			return -1;
+		}
 
 		if (test_and_clear_bit(IRQTF_RUNTHREAD,
 				       &action->thread_flags)) {
@@ -800,10 +810,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 			return 0;
 		}
 		schedule();
-		set_current_state(TASK_INTERRUPTIBLE);
 	}
-	__set_current_state(TASK_RUNNING);
-	return -1;
 }
 
 /*
@@ -1024,7 +1031,7 @@ static int irq_thread(void *data)
 	/*
 	 * This is the regular exit path. __free_irq() is stopping the
 	 * thread via kthread_stop() after calling
-	 * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
+	 * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
 	 * oneshot mask bit can be set.
 	 */
 	task_work_cancel(current, irq_thread_dtor);
@@ -1241,7 +1248,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 
 	/*
 	 * Protects against a concurrent __free_irq() call which might wait
-	 * for synchronize_irq() to complete without holding the optional
+	 * for synchronize_hardirq() to complete without holding the optional
 	 * chip bus lock and desc->lock. Also protects against handing out
 	 * a recycled oneshot thread_mask bit while it's still in use by
 	 * its previous owner.
@@ -1612,11 +1619,11 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	/*
 	 * Drop bus_lock here so the changes which were done in the chip
 	 * callbacks above are synced out to the irq chips which hang
-	 * behind a slow bus (I2C, SPI) before calling synchronize_irq().
+	 * behind a slow bus (I2C, SPI) before calling synchronize_hardirq().
 	 *
 	 * Aside of that the bus_lock can also be taken from the threaded
 	 * handler in irq_finalize_oneshot() which results in a deadlock
-	 * because synchronize_irq() would wait forever for the thread to
+	 * because kthread_stop() would wait forever for the thread to
 	 * complete, which is blocked on the bus lock.
 	 *
 	 * The still held desc->request_mutex() protects against a
@@ -1628,7 +1635,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	unregister_handler_proc(irq, action);
 
 	/* Make sure it's not being used on another CPU: */
-	synchronize_irq(irq);
+	synchronize_hardirq(irq);
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
@@ -1646,6 +1653,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	}
 #endif
 
+	/*
+	 * The action has already been removed above, but the thread writes
+	 * its oneshot mask bit when it completes. Though request_mutex is
+	 * held across this which prevents __setup_irq() from handing out
+	 * the same bit to a newly requested action.
+	 */
 	if (action->thread) {
 		kthread_stop(action->thread);
 		put_task_struct(action->thread);
-- 
cgit v1.2.3


From d0dd63a8aee1ef89f2e48e554b796b9f9e4fcadb Mon Sep 17 00:00:00 2001
From: Deepa Dinamani <deepa.kernel@gmail.com>
Date: Sat, 16 Jun 2018 22:11:42 -0700
Subject: time: Introduce struct __kernel_itimerspec

struct itimerspec is not y2038-safe.

Introduce a new struct __kernel_itimerspec based on the kernel internal
y2038-safe struct itimerspec64.

The definition of struct __kernel_itimerspec includes two struct
__kernel_timespec.

Since struct __kernel_timespec has the same representation in native and
compat modes, so does struct __kernel_itimerspec. This helps have a common
entry point for syscalls using struct __kernel_itimerspec.

New y2038-safe syscalls will use this new type. Since most of the new
syscalls are just an update to the native syscalls with the type update,
place the new definition under CONFIG_64BIT_TIME. This helps architectures
that do not support the above config to keep using the old definition of
struct itimerspec.

Also change the get/put_itimerspec64 to use struct__kernel_itimerspec.
This will help 32 bit architectures to use the new syscalls when
architectures select CONFIG_64BIT_TIME.

Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: arnd@arndb.de
Cc: viro@zeniv.linux.org.uk
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Cc: y2038@lists.linaro.org
Link: https://lkml.kernel.org/r/20180617051144.29756-2-deepa.kernel@gmail.com
---
 include/linux/time.h      | 4 ++--
 include/linux/time64.h    | 1 +
 include/uapi/linux/time.h | 7 +++++++
 kernel/time/time.c        | 4 ++--
 4 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/linux/time.h b/include/linux/time.h
index aed74463592d..27d83fd2ae61 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -14,9 +14,9 @@ int get_timespec64(struct timespec64 *ts,
 int put_timespec64(const struct timespec64 *ts,
 		struct __kernel_timespec __user *uts);
 int get_itimerspec64(struct itimerspec64 *it,
-			const struct itimerspec __user *uit);
+			const struct __kernel_itimerspec __user *uit);
 int put_itimerspec64(const struct itimerspec64 *it,
-			struct itimerspec __user *uit);
+			struct __kernel_itimerspec __user *uit);
 
 extern time64_t mktime64(const unsigned int year, const unsigned int mon,
 			const unsigned int day, const unsigned int hour,
diff --git a/include/linux/time64.h b/include/linux/time64.h
index 0a7b2f79cec7..05634afba0db 100644
--- a/include/linux/time64.h
+++ b/include/linux/time64.h
@@ -12,6 +12,7 @@ typedef __u64 timeu64_t;
  */
 #ifndef CONFIG_64BIT_TIME
 #define __kernel_timespec timespec
+#define __kernel_itimerspec itimerspec
 #endif
 
 #include <uapi/linux/time.h>
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index fcf936656493..6b56a2208be7 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -49,6 +49,13 @@ struct __kernel_timespec {
 };
 #endif
 
+#ifndef __kernel_itimerspec
+struct __kernel_itimerspec {
+	struct __kernel_timespec it_interval;    /* timer period */
+	struct __kernel_timespec it_value;       /* timer expiration */
+};
+#endif
+
 /*
  * legacy timeval structure, only embedded in structures that
  * traditionally used 'timeval' to pass time intervals (not absolute
diff --git a/kernel/time/time.c b/kernel/time/time.c
index b1225db61eb2..c0195225fdce 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -927,7 +927,7 @@ int compat_put_timespec64(const struct timespec64 *ts, void __user *uts)
 EXPORT_SYMBOL_GPL(compat_put_timespec64);
 
 int get_itimerspec64(struct itimerspec64 *it,
-			const struct itimerspec __user *uit)
+			const struct __kernel_itimerspec __user *uit)
 {
 	int ret;
 
@@ -942,7 +942,7 @@ int get_itimerspec64(struct itimerspec64 *it,
 EXPORT_SYMBOL_GPL(get_itimerspec64);
 
 int put_itimerspec64(const struct itimerspec64 *it,
-			struct itimerspec __user *uit)
+			struct __kernel_itimerspec __user *uit)
 {
 	int ret;
 
-- 
cgit v1.2.3


From afef05cf238cfcecdc5ea9b06f31027b13ce6214 Mon Sep 17 00:00:00 2001
From: Deepa Dinamani <deepa.kernel@gmail.com>
Date: Sat, 16 Jun 2018 22:11:43 -0700
Subject: time: Enable get/put_compat_itimerspec64 always

This will aid in enabling the compat syscalls on 32-bit architectures later
on.

Also move compat_itimerspec and related defines to compat_time.h.  The
compat_time.h file will eventually be deleted.

Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: arnd@arndb.de
Cc: viro@zeniv.linux.org.uk
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Cc: y2038@lists.linaro.org
Link: https://lkml.kernel.org/r/20180617051144.29756-3-deepa.kernel@gmail.com
---
 include/linux/compat.h      |  9 ---------
 include/linux/compat_time.h |  9 +++++++++
 kernel/compat.c             | 29 -----------------------------
 kernel/time/time.c          | 21 +++++++++++++++++++++
 4 files changed, 30 insertions(+), 38 deletions(-)

diff --git a/include/linux/compat.h b/include/linux/compat.h
index b1a5562b3215..18a13f2df14b 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -109,11 +109,6 @@ typedef	compat_ulong_t		compat_aio_context_t;
 struct compat_sel_arg_struct;
 struct rusage;
 
-struct compat_itimerspec {
-	struct compat_timespec it_interval;
-	struct compat_timespec it_value;
-};
-
 struct compat_utimbuf {
 	compat_time_t		actime;
 	compat_time_t		modtime;
@@ -294,10 +289,6 @@ extern int compat_get_timespec(struct timespec *, const void __user *);
 extern int compat_put_timespec(const struct timespec *, void __user *);
 extern int compat_get_timeval(struct timeval *, const void __user *);
 extern int compat_put_timeval(const struct timeval *, void __user *);
-extern int get_compat_itimerspec64(struct itimerspec64 *its,
-			const struct compat_itimerspec __user *uits);
-extern int put_compat_itimerspec64(const struct itimerspec64 *its,
-			struct compat_itimerspec __user *uits);
 
 struct compat_iovec {
 	compat_uptr_t	iov_base;
diff --git a/include/linux/compat_time.h b/include/linux/compat_time.h
index 31f2774f1994..e70bfd1d2c3f 100644
--- a/include/linux/compat_time.h
+++ b/include/linux/compat_time.h
@@ -17,7 +17,16 @@ struct compat_timeval {
 	s32		tv_usec;
 };
 
+struct compat_itimerspec {
+	struct compat_timespec it_interval;
+	struct compat_timespec it_value;
+};
+
 extern int compat_get_timespec64(struct timespec64 *, const void __user *);
 extern int compat_put_timespec64(const struct timespec64 *, void __user *);
+extern int get_compat_itimerspec64(struct itimerspec64 *its,
+			const struct compat_itimerspec __user *uits);
+extern int put_compat_itimerspec64(const struct itimerspec64 *its,
+			struct compat_itimerspec __user *uits);
 
 #endif /* _LINUX_COMPAT_TIME_H */
diff --git a/kernel/compat.c b/kernel/compat.c
index 702aa846ddac..8e40efc2928a 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -324,35 +324,6 @@ COMPAT_SYSCALL_DEFINE3(sched_getaffinity, compat_pid_t,  pid, unsigned int, len,
 	return ret;
 }
 
-/* Todo: Delete these extern declarations when get/put_compat_itimerspec64()
- * are moved to kernel/time/time.c .
- */
-extern int __compat_get_timespec64(struct timespec64 *ts64,
-				   const struct compat_timespec __user *cts);
-extern int __compat_put_timespec64(const struct timespec64 *ts64,
-				   struct compat_timespec __user *cts);
-
-int get_compat_itimerspec64(struct itimerspec64 *its,
-			const struct compat_itimerspec __user *uits)
-{
-
-	if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
-	    __compat_get_timespec64(&its->it_value, &uits->it_value))
-		return -EFAULT;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
-
-int put_compat_itimerspec64(const struct itimerspec64 *its,
-			struct compat_itimerspec __user *uits)
-{
-	if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
-	    __compat_put_timespec64(&its->it_value, &uits->it_value))
-		return -EFAULT;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
-
 /*
  * We currently only need the following fields from the sigevent
  * structure: sigev_value, sigev_signo, sig_notify and (sometimes
diff --git a/kernel/time/time.c b/kernel/time/time.c
index c0195225fdce..72caf051901c 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -955,3 +955,24 @@ int put_itimerspec64(const struct itimerspec64 *it,
 	return ret;
 }
 EXPORT_SYMBOL_GPL(put_itimerspec64);
+
+int get_compat_itimerspec64(struct itimerspec64 *its,
+			const struct compat_itimerspec __user *uits)
+{
+
+	if (__compat_get_timespec64(&its->it_interval, &uits->it_interval) ||
+	    __compat_get_timespec64(&its->it_value, &uits->it_value))
+		return -EFAULT;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(get_compat_itimerspec64);
+
+int put_compat_itimerspec64(const struct itimerspec64 *its,
+			struct compat_itimerspec __user *uits)
+{
+	if (__compat_put_timespec64(&its->it_interval, &uits->it_interval) ||
+	    __compat_put_timespec64(&its->it_value, &uits->it_value))
+		return -EFAULT;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(put_compat_itimerspec64);
-- 
cgit v1.2.3


From 6ff84735070276d72af716e21c3214ee20d60e70 Mon Sep 17 00:00:00 2001
From: Deepa Dinamani <deepa.kernel@gmail.com>
Date: Sat, 16 Jun 2018 22:11:44 -0700
Subject: time: Change types to new y2038 safe __kernel_itimerspec

timer_set/gettime and timerfd_set/get apis use struct itimerspec at the
user interface layer.  struct itimerspec is not y2038-safe.  Change these
interfaces to use y2038-safe struct __kernel_itimerspec instead.  This will
help define new syscalls when 32bit architectures select CONFIG_64BIT_TIME.

Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: arnd@arndb.de
Cc: viro@zeniv.linux.org.uk
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-api@vger.kernel.org
Cc: y2038@lists.linaro.org
Link: https://lkml.kernel.org/r/20180617051144.29756-4-deepa.kernel@gmail.com
---
 fs/timerfd.c               |  8 ++++----
 include/linux/syscalls.h   | 10 +++++-----
 kernel/time/posix-timers.c | 12 +++++++-----
 3 files changed, 16 insertions(+), 14 deletions(-)

diff --git a/fs/timerfd.c b/fs/timerfd.c
index d84a2bee4f82..8bb926253f88 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -533,8 +533,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec64 *t)
 }
 
 SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
-		const struct itimerspec __user *, utmr,
-		struct itimerspec __user *, otmr)
+		const struct __kernel_itimerspec __user *, utmr,
+		struct __kernel_itimerspec __user *, otmr)
 {
 	struct itimerspec64 new, old;
 	int ret;
@@ -550,7 +550,7 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 	return ret;
 }
 
-SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
+SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct __kernel_itimerspec __user *, otmr)
 {
 	struct itimerspec64 kotmr;
 	int ret = do_timerfd_gettime(ufd, &kotmr);
@@ -559,7 +559,7 @@ SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
 	return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 		const struct compat_itimerspec __user *, utmr,
 		struct compat_itimerspec __user *, otmr)
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 73810808cdf2..38b9ec152024 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -501,9 +501,9 @@ asmlinkage long sys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
 /* fs/timerfd.c */
 asmlinkage long sys_timerfd_create(int clockid, int flags);
 asmlinkage long sys_timerfd_settime(int ufd, int flags,
-				    const struct itimerspec __user *utmr,
-				    struct itimerspec __user *otmr);
-asmlinkage long sys_timerfd_gettime(int ufd, struct itimerspec __user *otmr);
+				    const struct __kernel_itimerspec __user *utmr,
+				    struct __kernel_itimerspec __user *otmr);
+asmlinkage long sys_timerfd_gettime(int ufd, struct __kernel_itimerspec __user *otmr);
 
 /* fs/utimes.c */
 asmlinkage long sys_utimensat(int dfd, const char __user *filename,
@@ -568,10 +568,10 @@ asmlinkage long sys_timer_create(clockid_t which_clock,
 				 struct sigevent __user *timer_event_spec,
 				 timer_t __user * created_timer_id);
 asmlinkage long sys_timer_gettime(timer_t timer_id,
-				struct itimerspec __user *setting);
+				struct __kernel_itimerspec __user *setting);
 asmlinkage long sys_timer_getoverrun(timer_t timer_id);
 asmlinkage long sys_timer_settime(timer_t timer_id, int flags,
-				const struct itimerspec __user *new_setting,
+				const struct __kernel_itimerspec __user *new_setting,
 				struct itimerspec __user *old_setting);
 asmlinkage long sys_timer_delete(timer_t timer_id);
 asmlinkage long sys_clock_settime(clockid_t which_clock,
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index fcf90a10c43a..80d59333c76e 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -743,7 +743,7 @@ static int do_timer_gettime(timer_t timer_id,  struct itimerspec64 *setting)
 
 /* Get the time remaining on a POSIX.1b interval timer. */
 SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
-		struct itimerspec __user *, setting)
+		struct __kernel_itimerspec __user *, setting)
 {
 	struct itimerspec64 cur_setting;
 
@@ -755,7 +755,8 @@ SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	return ret;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
+
 COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 		       struct compat_itimerspec __user *, setting)
 {
@@ -768,6 +769,7 @@ COMPAT_SYSCALL_DEFINE2(timer_gettime, timer_t, timer_id,
 	}
 	return ret;
 }
+
 #endif
 
 /*
@@ -906,8 +908,8 @@ retry:
 
 /* Set a POSIX.1b interval timer */
 SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
-		const struct itimerspec __user *, new_setting,
-		struct itimerspec __user *, old_setting)
+		const struct __kernel_itimerspec __user *, new_setting,
+		struct __kernel_itimerspec __user *, old_setting)
 {
 	struct itimerspec64 new_spec, old_spec;
 	struct itimerspec64 *rtn = old_setting ? &old_spec : NULL;
@@ -927,7 +929,7 @@ SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 	return error;
 }
 
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
 COMPAT_SYSCALL_DEFINE4(timer_settime, timer_t, timer_id, int, flags,
 		       struct compat_itimerspec __user *, new,
 		       struct compat_itimerspec __user *, old)
-- 
cgit v1.2.3


From 0e4c88f37693d4857fc0be66e548e2eb8b3d8a15 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Thu, 21 Jun 2018 15:32:38 +0200
Subject: x86/hyper-v: Use cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}
 hypercalls when possible

While working on Hyper-V style PV TLB flush support in KVM I noticed that
real Windows guests use TLB flush hypercall in a somewhat smarter way:

  When the flush needs to be performed on a subset of first 64 vCPUs or on
  all present vCPUs Windows avoids more expensive hypercalls which support
  sparse CPU sets and uses their 'cheap' counterparts.

This means that HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED name is actually a
misnomer: EX hypercalls (which support sparse CPU sets) are "available",
not "recommended". This makes sense as they are actually harder to parse.

Nothing stops us from being equally 'smart' in Linux too. Switch to doing
cheaper hypercalls whenever possible.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Cc: Tianyu Lan <Tianyu.Lan@microsoft.com>
Cc: devel@linuxdriverproject.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lkml.kernel.org/r/20180621133238.30757-1-vkuznets@redhat.com
---
 arch/x86/hyperv/mmu.c | 73 ++++++++++++++++++++++-----------------------------
 1 file changed, 32 insertions(+), 41 deletions(-)

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index de27615c51ea..0d90e515ec98 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -16,6 +16,8 @@
 /* Each gva in gva_list encodes up to 4096 pages to flush */
 #define HV_TLB_FLUSH_UNIT (4096 * PAGE_SIZE)
 
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				      const struct flush_tlb_info *info);
 
 /*
  * Fills in gva_list starting from offset. Returns the number of items added.
@@ -93,10 +95,24 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (cpumask_equal(cpus, cpu_present_mask)) {
 		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
 	} else {
+		/*
+		 * From the supplied CPU set we need to figure out if we can get
+		 * away with cheaper HVCALL_FLUSH_VIRTUAL_ADDRESS_{LIST,SPACE}
+		 * hypercalls. This is possible when the highest VP number in
+		 * the set is < 64. As VP numbers are usually in ascending order
+		 * and match Linux CPU ids, here is an optimization: we check
+		 * the VP number for the highest bit in the supplied set first
+		 * so we can quickly find out if using *_EX hypercalls is a
+		 * must. We will also check all VP numbers when walking the
+		 * supplied CPU set to remain correct in all cases.
+		 */
+		if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64)
+			goto do_ex_hypercall;
+
 		for_each_cpu(cpu, cpus) {
 			vcpu = hv_cpu_number_to_vp_number(cpu);
 			if (vcpu >= 64)
-				goto do_native;
+				goto do_ex_hypercall;
 
 			__set_bit(vcpu, (unsigned long *)
 				  &flush->processor_mask);
@@ -123,7 +139,12 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 		status = hv_do_rep_hypercall(HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST,
 					     gva_n, 0, flush, NULL);
 	}
+	goto check_status;
+
+do_ex_hypercall:
+	status = hyperv_flush_tlb_others_ex(cpus, info);
 
+check_status:
 	local_irq_restore(flags);
 
 	if (!(status & HV_HYPERCALL_RESULT_MASK))
@@ -132,35 +153,22 @@ do_native:
 	native_flush_tlb_others(cpus, info);
 }
 
-static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
-				       const struct flush_tlb_info *info)
+static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
+				      const struct flush_tlb_info *info)
 {
 	int nr_bank = 0, max_gvas, gva_n;
 	struct hv_tlb_flush_ex **flush_pcpu;
 	struct hv_tlb_flush_ex *flush;
-	u64 status = U64_MAX;
-	unsigned long flags;
-
-	trace_hyperv_mmu_flush_tlb_others(cpus, info);
+	u64 status;
 
-	if (!hv_hypercall_pg)
-		goto do_native;
-
-	if (cpumask_empty(cpus))
-		return;
-
-	local_irq_save(flags);
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+		return U64_MAX;
 
 	flush_pcpu = (struct hv_tlb_flush_ex **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	flush = *flush_pcpu;
 
-	if (unlikely(!flush)) {
-		local_irq_restore(flags);
-		goto do_native;
-	}
-
 	if (info->mm) {
 		/*
 		 * AddressSpace argument must match the CR3 with PCID bits
@@ -176,15 +184,8 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	flush->hv_vp_set.valid_bank_mask = 0;
 
-	if (!cpumask_equal(cpus, cpu_present_mask)) {
-		flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
-		nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
-	}
-
-	if (!nr_bank) {
-		flush->hv_vp_set.format = HV_GENERIC_SET_ALL;
-		flush->flags |= HV_FLUSH_ALL_PROCESSORS;
-	}
+	flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+	nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
 
 	/*
 	 * We can flush not more than max_gvas with one hypercall. Flush the
@@ -213,12 +214,7 @@ static void hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 			gva_n, nr_bank, flush, NULL);
 	}
 
-	local_irq_restore(flags);
-
-	if (!(status & HV_HYPERCALL_RESULT_MASK))
-		return;
-do_native:
-	native_flush_tlb_others(cpus, info);
+	return status;
 }
 
 void hyperv_setup_mmu_ops(void)
@@ -226,11 +222,6 @@ void hyperv_setup_mmu_ops(void)
 	if (!(ms_hyperv.hints & HV_X64_REMOTE_TLB_FLUSH_RECOMMENDED))
 		return;
 
-	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED)) {
-		pr_info("Using hypercall for remote TLB flush\n");
-		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
-	} else {
-		pr_info("Using ext hypercall for remote TLB flush\n");
-		pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others_ex;
-	}
+	pr_info("Using hypercall for remote TLB flush\n");
+	pv_mmu_ops.flush_tlb_others = hyperv_flush_tlb_others;
 }
-- 
cgit v1.2.3


From 746e08590b864cf730d7bd23394e2d3fbb0f22b6 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:27 -0700
Subject: x86/intel_rdt: Create character device exposing pseudo-locked region

After a pseudo-locked region is created it needs to be made
available to user space for usage.

A character device supporting mmap() is created for each pseudo-locked
region. A user space application can now use mmap() system call to map
pseudo-locked region into its virtual address space.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/fccbb9b20f07655ab0a4df9fa1c1babc0288aea0.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             |  14 +-
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 285 ++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    |   1 +
 3 files changed, 291 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 8a7102cfbec7..b8e490a43290 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -138,6 +138,8 @@ struct mongroup {
  * @line_size:		size of the cache lines
  * @size:		size of pseudo-locked region in bytes
  * @kmem:		the kernel memory associated with pseudo-locked region
+ * @minor:		minor number of character device associated with this
+ *			region
  * @debugfs_dir:	pointer to this region's directory in the debugfs
  *			filesystem
  */
@@ -151,6 +153,7 @@ struct pseudo_lock_region {
 	unsigned int		line_size;
 	unsigned int		size;
 	void			*kmem;
+	unsigned int		minor;
 	struct dentry		*debugfs_dir;
 };
 
@@ -524,6 +527,8 @@ int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
 int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
 bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, u32 _cbm);
 bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
+int rdt_pseudo_lock_init(void);
+void rdt_pseudo_lock_release(void);
 int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
 void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
 struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
@@ -551,13 +556,4 @@ void cqm_handle_limbo(struct work_struct *work);
 bool has_busy_rmid(struct rdt_resource *r, struct rdt_domain *d);
 void __check_limbo(struct rdt_domain *d, bool force_free);
 
-/*
- * Define the hooks for Cache Pseudo-Locking to use within rdt_mount().
- * These are no-ops provided for the new kernfs changes to use as a
- * baseline in preparation for a conflict-free merge between it
- * (kernfs changes) and the Cache Pseudo-Locking enabling.
- */
-static inline int rdt_pseudo_lock_init(void) { return 0; }
-static inline void rdt_pseudo_lock_release(void) { }
-
 #endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 5851f3e20742..1c5e7f28da5b 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -16,10 +16,14 @@
 #include <linux/cpumask.h>
 #include <linux/debugfs.h>
 #include <linux/kthread.h>
+#include <linux/mman.h>
 #include <linux/slab.h>
+#include <linux/uaccess.h>
+
 #include <asm/cacheflush.h>
 #include <asm/intel-family.h>
 #include <asm/intel_rdt_sched.h>
+
 #include "intel_rdt.h"
 
 #define CREATE_TRACE_POINTS
@@ -38,6 +42,14 @@
  */
 static u64 prefetch_disable_bits;
 
+/*
+ * Major number assigned to and shared by all devices exposing
+ * pseudo-locked regions.
+ */
+static unsigned int pseudo_lock_major;
+static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
+static struct class *pseudo_lock_class;
+
 /**
  * get_prefetch_disable_bits - prefetch disable bits of supported platforms
  *
@@ -89,6 +101,66 @@ static u64 get_prefetch_disable_bits(void)
 	return 0;
 }
 
+/**
+ * pseudo_lock_minor_get - Obtain available minor number
+ * @minor: Pointer to where new minor number will be stored
+ *
+ * A bitmask is used to track available minor numbers. Here the next free
+ * minor number is marked as unavailable and returned.
+ *
+ * Return: 0 on success, <0 on failure.
+ */
+static int pseudo_lock_minor_get(unsigned int *minor)
+{
+	unsigned long first_bit;
+
+	first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
+
+	if (first_bit == MINORBITS)
+		return -ENOSPC;
+
+	__clear_bit(first_bit, &pseudo_lock_minor_avail);
+	*minor = first_bit;
+
+	return 0;
+}
+
+/**
+ * pseudo_lock_minor_release - Return minor number to available
+ * @minor: The minor number made available
+ */
+static void pseudo_lock_minor_release(unsigned int minor)
+{
+	__set_bit(minor, &pseudo_lock_minor_avail);
+}
+
+/**
+ * region_find_by_minor - Locate a pseudo-lock region by inode minor number
+ * @minor: The minor number of the device representing pseudo-locked region
+ *
+ * When the character device is accessed we need to determine which
+ * pseudo-locked region it belongs to. This is done by matching the minor
+ * number of the device to the pseudo-locked region it belongs.
+ *
+ * Minor numbers are assigned at the time a pseudo-locked region is associated
+ * with a cache instance.
+ *
+ * Return: On success return pointer to resource group owning the pseudo-locked
+ *         region, NULL on failure.
+ */
+static struct rdtgroup *region_find_by_minor(unsigned int minor)
+{
+	struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
+			rdtgrp_match = rdtgrp;
+			break;
+		}
+	}
+	return rdtgrp_match;
+}
+
 /**
  * pseudo_lock_region_init - Initialize pseudo-lock region information
  * @plr: pseudo-lock region
@@ -872,6 +944,8 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 {
 	struct pseudo_lock_region *plr = rdtgrp->plr;
 	struct task_struct *thread;
+	unsigned int new_minor;
+	struct device *dev;
 	int ret;
 
 	ret = pseudo_lock_region_alloc(plr);
@@ -916,11 +990,55 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 					    &pseudo_measure_fops);
 	}
 
+	ret = pseudo_lock_minor_get(&new_minor);
+	if (ret < 0) {
+		rdt_last_cmd_puts("unable to obtain a new minor number\n");
+		goto out_debugfs;
+	}
+
+	/*
+	 * Unlock access but do not release the reference. The
+	 * pseudo-locked region will still be here on return.
+	 *
+	 * The mutex has to be released temporarily to avoid a potential
+	 * deadlock with the mm->mmap_sem semaphore which is obtained in
+	 * the device_create() callpath below as well as before the mmap()
+	 * callback is called.
+	 */
+	mutex_unlock(&rdtgroup_mutex);
+
+	dev = device_create(pseudo_lock_class, NULL,
+			    MKDEV(pseudo_lock_major, new_minor),
+			    rdtgrp, "%s", rdtgrp->kn->name);
+
+	mutex_lock(&rdtgroup_mutex);
+
+	if (IS_ERR(dev)) {
+		ret = PTR_ERR(dev);
+		rdt_last_cmd_printf("failed to create character device: %d\n",
+				    ret);
+		goto out_minor;
+	}
+
+	/* We released the mutex - check if group was removed while we did so */
+	if (rdtgrp->flags & RDT_DELETED) {
+		ret = -ENODEV;
+		goto out_device;
+	}
+
+	plr->minor = new_minor;
+
 	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
 	closid_free(rdtgrp->closid);
 	ret = 0;
 	goto out;
 
+out_device:
+	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
+out_minor:
+	pseudo_lock_minor_release(new_minor);
+out_debugfs:
+	debugfs_remove_recursive(plr->debugfs_dir);
 out_region:
 	pseudo_lock_region_clear(plr);
 out:
@@ -943,6 +1061,8 @@ out:
  */
 void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
 {
+	struct pseudo_lock_region *plr = rdtgrp->plr;
+
 	if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
 		/*
 		 * Default group cannot be a pseudo-locked region so we can
@@ -953,7 +1073,172 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
 	}
 
 	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
+	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
+	pseudo_lock_minor_release(plr->minor);
 
 free:
 	pseudo_lock_free(rdtgrp);
 }
+
+static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = region_find_by_minor(iminor(inode));
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	filp->private_data = rdtgrp;
+	atomic_inc(&rdtgrp->waitcount);
+	/* Perform a non-seekable open - llseek is not supported */
+	filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+	mutex_unlock(&rdtgroup_mutex);
+
+	return 0;
+}
+
+static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
+{
+	struct rdtgroup *rdtgrp;
+
+	mutex_lock(&rdtgroup_mutex);
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+	filp->private_data = NULL;
+	atomic_dec(&rdtgrp->waitcount);
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
+{
+	/* Not supported */
+	return -EINVAL;
+}
+
+static const struct vm_operations_struct pseudo_mmap_ops = {
+	.mremap = pseudo_lock_dev_mremap,
+};
+
+static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	unsigned long vsize = vma->vm_end - vma->vm_start;
+	unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
+	struct pseudo_lock_region *plr;
+	struct rdtgroup *rdtgrp;
+	unsigned long physical;
+	unsigned long psize;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	rdtgrp = filp->private_data;
+	WARN_ON(!rdtgrp);
+	if (!rdtgrp) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENODEV;
+	}
+
+	plr = rdtgrp->plr;
+
+	/*
+	 * Task is required to run with affinity to the cpus associated
+	 * with the pseudo-locked region. If this is not the case the task
+	 * may be scheduled elsewhere and invalidate entries in the
+	 * pseudo-locked region.
+	 */
+	if (!cpumask_subset(&current->cpus_allowed, &plr->d->cpu_mask)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	physical = __pa(plr->kmem) >> PAGE_SHIFT;
+	psize = plr->size - off;
+
+	if (off > plr->size) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	/*
+	 * Ensure changes are carried directly to the memory being mapped,
+	 * do not allow copy-on-write mapping.
+	 */
+	if (!(vma->vm_flags & VM_SHARED)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EINVAL;
+	}
+
+	if (vsize > psize) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -ENOSPC;
+	}
+
+	memset(plr->kmem + off, 0, vsize);
+
+	if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
+			    vsize, vma->vm_page_prot)) {
+		mutex_unlock(&rdtgroup_mutex);
+		return -EAGAIN;
+	}
+	vma->vm_ops = &pseudo_mmap_ops;
+	mutex_unlock(&rdtgroup_mutex);
+	return 0;
+}
+
+static const struct file_operations pseudo_lock_dev_fops = {
+	.owner =	THIS_MODULE,
+	.llseek =	no_llseek,
+	.read =		NULL,
+	.write =	NULL,
+	.open =		pseudo_lock_dev_open,
+	.release =	pseudo_lock_dev_release,
+	.mmap =		pseudo_lock_dev_mmap,
+};
+
+static char *pseudo_lock_devnode(struct device *dev, umode_t *mode)
+{
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = dev_get_drvdata(dev);
+	if (mode)
+		*mode = 0600;
+	return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdtgrp->kn->name);
+}
+
+int rdt_pseudo_lock_init(void)
+{
+	int ret;
+
+	ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
+	if (ret < 0)
+		return ret;
+
+	pseudo_lock_major = ret;
+
+	pseudo_lock_class = class_create(THIS_MODULE, "pseudo_lock");
+	if (IS_ERR(pseudo_lock_class)) {
+		ret = PTR_ERR(pseudo_lock_class);
+		unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+		return ret;
+	}
+
+	pseudo_lock_class->devnode = pseudo_lock_devnode;
+	return 0;
+}
+
+void rdt_pseudo_lock_release(void)
+{
+	class_destroy(pseudo_lock_class);
+	pseudo_lock_class = NULL;
+	unregister_chrdev(pseudo_lock_major, "pseudo_lock");
+	pseudo_lock_major = 0;
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index bc52c593a87c..7b4a09d81a30 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -2067,6 +2067,7 @@ static void rdt_kill_sb(struct super_block *sb)
 		reset_all_ctrls(r);
 	cdp_disable_all();
 	rmdir_all_sub();
+	rdt_pseudo_lock_release();
 	rdtgroup_default.mode = RDT_MODE_SHAREABLE;
 	static_branch_disable_cpuslocked(&rdt_alloc_enable_key);
 	static_branch_disable_cpuslocked(&rdt_mon_enable_key);
-- 
cgit v1.2.3


From 8a2fc0e1bc0cd856101927188884d7c370b62188 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:28 -0700
Subject: x86/intel_rdt: More precise L2 hit/miss measurements

Intel Goldmont processors supports non-architectural precise events that
can be used to give us more insight into the success of L2 cache
pseudo-locking on these platforms.

Introduce a new measurement trigger that will enable two precise events,
MEM_LOAD_UOPS_RETIRED.L2_HIT and MEM_LOAD_UOPS_RETIRED.L2_MISS, while
accessing pseudo-locked data. A new tracepoint, pseudo_lock_l2, is
created to make these results visible to the user.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/06b1456da65b543479dac8d9493e41f92f175d6c.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c       | 145 ++++++++++++++++++++--
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h |  10 ++
 2 files changed, 146 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 1c5e7f28da5b..9e808c07a7f0 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -23,6 +23,7 @@
 #include <asm/cacheflush.h>
 #include <asm/intel-family.h>
 #include <asm/intel_rdt_sched.h>
+#include <asm/perf_event.h>
 
 #include "intel_rdt.h"
 
@@ -63,6 +64,9 @@ static struct class *pseudo_lock_class;
  * hardware prefetch disable bits are included here as they are documented
  * in the SDM.
  *
+ * When adding a platform here also add support for its cache events to
+ * measure_cycles_perf_fn()
+ *
  * Return:
  * If platform is supported, the bits to disable hardware prefetchers, 0
  * if platform is not supported.
@@ -101,6 +105,16 @@ static u64 get_prefetch_disable_bits(void)
 	return 0;
 }
 
+/*
+ * Helper to write 64bit value to MSR without tracing. Used when
+ * use of the cache should be restricted and use of registers used
+ * for local variables avoided.
+ */
+static inline void pseudo_wrmsrl_notrace(unsigned int msr, u64 val)
+{
+	__wrmsr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
+}
+
 /**
  * pseudo_lock_minor_get - Obtain available minor number
  * @minor: Pointer to where new minor number will be stored
@@ -834,6 +848,107 @@ static int measure_cycles_lat_fn(void *_plr)
 	return 0;
 }
 
+static int measure_cycles_perf_fn(void *_plr)
+{
+	struct pseudo_lock_region *plr = _plr;
+	unsigned long long l2_hits, l2_miss;
+	u64 l2_hit_bits, l2_miss_bits;
+	unsigned long i;
+#ifdef CONFIG_KASAN
+	/*
+	 * The registers used for local register variables are also used
+	 * when KASAN is active. When KASAN is active we use regular variables
+	 * at the cost of including cache access latency to these variables
+	 * in the measurements.
+	 */
+	unsigned int line_size;
+	unsigned int size;
+	void *mem_r;
+#else
+	register unsigned int line_size asm("esi");
+	register unsigned int size asm("edi");
+#ifdef CONFIG_X86_64
+	register void *mem_r asm("rbx");
+#else
+	register void *mem_r asm("ebx");
+#endif /* CONFIG_X86_64 */
+#endif /* CONFIG_KASAN */
+
+	/*
+	 * Non-architectural event for the Goldmont Microarchitecture
+	 * from Intel x86 Architecture Software Developer Manual (SDM):
+	 * MEM_LOAD_UOPS_RETIRED D1H (event number)
+	 * Umask values:
+	 *     L1_HIT   01H
+	 *     L2_HIT   02H
+	 *     L1_MISS  08H
+	 *     L2_MISS  10H
+	 */
+
+	/*
+	 * Start by setting flags for IA32_PERFEVTSELx:
+	 *     OS  (Operating system mode)  0x2
+	 *     INT (APIC interrupt enable)  0x10
+	 *     EN  (Enable counter)         0x40
+	 *
+	 * Then add the Umask value and event number to select performance
+	 * event.
+	 */
+
+	switch (boot_cpu_data.x86_model) {
+	case INTEL_FAM6_ATOM_GOLDMONT:
+	case INTEL_FAM6_ATOM_GEMINI_LAKE:
+		l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
+		l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
+		break;
+	default:
+		goto out;
+	}
+
+	local_irq_disable();
+	/*
+	 * Call wrmsr direcly to avoid the local register variables from
+	 * being overwritten due to reordering of their assignment with
+	 * the wrmsr calls.
+	 */
+	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+	/* Disable events and reset counters */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
+	/* Set and enable the L2 counters */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
+	mem_r = plr->kmem;
+	size = plr->size;
+	line_size = plr->line_size;
+	for (i = 0; i < size; i += line_size) {
+		asm volatile("mov (%0,%1,1), %%eax\n\t"
+			     :
+			     : "r" (mem_r), "r" (i)
+			     : "%eax", "memory");
+	}
+	/*
+	 * Call wrmsr directly (no tracing) to not influence
+	 * the cache access counters as they are disabled.
+	 */
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0,
+			      l2_hit_bits & ~(0x40ULL << 16));
+	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
+			      l2_miss_bits & ~(0x40ULL << 16));
+	l2_hits = native_read_pmc(0);
+	l2_miss = native_read_pmc(1);
+	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	local_irq_enable();
+	trace_pseudo_lock_l2(l2_hits, l2_miss);
+
+out:
+	plr->thread_done = 1;
+	wake_up_interruptible(&plr->lock_thread_wq);
+	return 0;
+}
+
 /**
  * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
  *
@@ -844,12 +959,12 @@ static int measure_cycles_lat_fn(void *_plr)
  *
  * Return: 0 on success, <0 on failure
  */
-static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp)
+static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
 {
 	struct pseudo_lock_region *plr = rdtgrp->plr;
 	struct task_struct *thread;
 	unsigned int cpu;
-	int ret;
+	int ret = -1;
 
 	cpus_read_lock();
 	mutex_lock(&rdtgroup_mutex);
@@ -866,9 +981,19 @@ static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp)
 		goto out;
 	}
 
-	thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
-					cpu_to_node(cpu),
-					"pseudo_lock_measure/%u", cpu);
+	if (sel == 1)
+		thread = kthread_create_on_node(measure_cycles_lat_fn, plr,
+						cpu_to_node(cpu),
+						"pseudo_lock_measure/%u",
+						cpu);
+	else if (sel == 2)
+		thread = kthread_create_on_node(measure_cycles_perf_fn, plr,
+						cpu_to_node(cpu),
+						"pseudo_lock_measure/%u",
+						cpu);
+	else
+		goto out;
+
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);
 		goto out;
@@ -897,19 +1022,21 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file,
 	size_t buf_size;
 	char buf[32];
 	int ret;
-	bool bv;
+	int sel;
 
 	buf_size = min(count, (sizeof(buf) - 1));
 	if (copy_from_user(buf, user_buf, buf_size))
 		return -EFAULT;
 
 	buf[buf_size] = '\0';
-	ret = strtobool(buf, &bv);
-	if (ret == 0 && bv) {
+	ret = kstrtoint(buf, 10, &sel);
+	if (ret == 0) {
+		if (sel != 1 && sel != 2)
+			return -EINVAL;
 		ret = debugfs_file_get(file->f_path.dentry);
 		if (ret)
 			return ret;
-		ret = pseudo_lock_measure_cycles(rdtgrp);
+		ret = pseudo_lock_measure_cycles(rdtgrp, sel);
 		if (ret == 0)
 			ret = count;
 		debugfs_file_put(file->f_path.dentry);
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
index 3cd0fa27d5fe..efad50d2ee2f 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
@@ -15,6 +15,16 @@ TRACE_EVENT(pseudo_lock_mem_latency,
 	    TP_printk("latency=%u", __entry->latency)
 	   );
 
+TRACE_EVENT(pseudo_lock_l2,
+	    TP_PROTO(u64 l2_hits, u64 l2_miss),
+	    TP_ARGS(l2_hits, l2_miss),
+	    TP_STRUCT__entry(__field(u64, l2_hits)
+			     __field(u64, l2_miss)),
+	    TP_fast_assign(__entry->l2_hits = l2_hits;
+			   __entry->l2_miss = l2_miss;),
+	    TP_printk("hits=%llu miss=%llu",
+		      __entry->l2_hits, __entry->l2_miss));
+
 #endif /* _TRACE_PSEUDO_LOCK_H */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From f3be1e7b2cf8bc096386a3588fc640b0db6b28d7 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:29 -0700
Subject: x86/intel_rdt: Support L3 cache performance event of Broadwell

Broadwell microarchitecture supports pseudo-locking. Add support for
the L3 cache related performance events of these systems so that
the success of pseudo-locking can be measured more accurately on these
platforms.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/36c1414e9bd17c3faf440f32b644b9c879bcbae2.1529706536.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c       | 56 +++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h | 10 ++++
 2 files changed, 66 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 9e808c07a7f0..dd1341557c9d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -850,6 +850,8 @@ static int measure_cycles_lat_fn(void *_plr)
 
 static int measure_cycles_perf_fn(void *_plr)
 {
+	unsigned long long l3_hits = 0, l3_miss = 0;
+	u64 l3_hit_bits = 0, l3_miss_bits = 0;
 	struct pseudo_lock_region *plr = _plr;
 	unsigned long long l2_hits, l2_miss;
 	u64 l2_hit_bits, l2_miss_bits;
@@ -883,6 +885,16 @@ static int measure_cycles_perf_fn(void *_plr)
 	 *     L2_HIT   02H
 	 *     L1_MISS  08H
 	 *     L2_MISS  10H
+	 *
+	 * On Broadwell Microarchitecture the MEM_LOAD_UOPS_RETIRED event
+	 * has two "no fix" errata associated with it: BDM35 and BDM100. On
+	 * this platform we use the following events instead:
+	 *  L2_RQSTS 24H (Documented in https://download.01.org/perfmon/BDW/)
+	 *       REFERENCES FFH
+	 *       MISS       3FH
+	 *  LONGEST_LAT_CACHE 2EH (Documented in SDM)
+	 *       REFERENCE 4FH
+	 *       MISS      41H
 	 */
 
 	/*
@@ -901,6 +913,14 @@ static int measure_cycles_perf_fn(void *_plr)
 		l2_hit_bits = (0x52ULL << 16) | (0x2 << 8) | 0xd1;
 		l2_miss_bits = (0x52ULL << 16) | (0x10 << 8) | 0xd1;
 		break;
+	case INTEL_FAM6_BROADWELL_X:
+		/* On BDW the l2_hit_bits count references, not hits */
+		l2_hit_bits = (0x52ULL << 16) | (0xff << 8) | 0x24;
+		l2_miss_bits = (0x52ULL << 16) | (0x3f << 8) | 0x24;
+		/* On BDW the l3_hit_bits count references, not hits */
+		l3_hit_bits = (0x52ULL << 16) | (0x4f << 8) | 0x2e;
+		l3_miss_bits = (0x52ULL << 16) | (0x41 << 8) | 0x2e;
+		break;
 	default:
 		goto out;
 	}
@@ -917,9 +937,21 @@ static int measure_cycles_perf_fn(void *_plr)
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, 0x0);
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0, 0x0);
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 1, 0x0);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 2, 0x0);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_PERFCTR0 + 3, 0x0);
+	}
 	/* Set and enable the L2 counters */
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0, l2_hit_bits);
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1, l2_miss_bits);
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits);
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits);
+	}
 	mem_r = plr->kmem;
 	size = plr->size;
 	line_size = plr->line_size;
@@ -937,11 +969,35 @@ static int measure_cycles_perf_fn(void *_plr)
 			      l2_hit_bits & ~(0x40ULL << 16));
 	pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 1,
 			      l2_miss_bits & ~(0x40ULL << 16));
+	if (l3_hit_bits > 0) {
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 2,
+				      l3_hit_bits & ~(0x40ULL << 16));
+		pseudo_wrmsrl_notrace(MSR_ARCH_PERFMON_EVENTSEL0 + 3,
+				      l3_miss_bits & ~(0x40ULL << 16));
+	}
 	l2_hits = native_read_pmc(0);
 	l2_miss = native_read_pmc(1);
+	if (l3_hit_bits > 0) {
+		l3_hits = native_read_pmc(2);
+		l3_miss = native_read_pmc(3);
+	}
 	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
 	local_irq_enable();
+	/*
+	 * On BDW we count references and misses, need to adjust. Sometimes
+	 * the "hits" counter is a bit more than the references, for
+	 * example, x references but x + 1 hits. To not report invalid
+	 * hit values in this case we treat that as misses eaqual to
+	 * references.
+	 */
+	if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+		l2_hits -= (l2_miss > l2_hits ? l2_hits : l2_miss);
 	trace_pseudo_lock_l2(l2_hits, l2_miss);
+	if (l3_hit_bits > 0) {
+		if (boot_cpu_data.x86_model == INTEL_FAM6_BROADWELL_X)
+			l3_hits -= (l3_miss > l3_hits ? l3_hits : l3_miss);
+		trace_pseudo_lock_l3(l3_hits, l3_miss);
+	}
 
 out:
 	plr->thread_done = 1;
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
index efad50d2ee2f..2c041e6d9f05 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock_event.h
@@ -25,6 +25,16 @@ TRACE_EVENT(pseudo_lock_l2,
 	    TP_printk("hits=%llu miss=%llu",
 		      __entry->l2_hits, __entry->l2_miss));
 
+TRACE_EVENT(pseudo_lock_l3,
+	    TP_PROTO(u64 l3_hits, u64 l3_miss),
+	    TP_ARGS(l3_hits, l3_miss),
+	    TP_STRUCT__entry(__field(u64, l3_hits)
+			     __field(u64, l3_miss)),
+	    TP_fast_assign(__entry->l3_hits = l3_hits;
+			   __entry->l3_miss = l3_miss;),
+	    TP_printk("hits=%llu miss=%llu",
+		      __entry->l3_hits, __entry->l3_miss));
+
 #endif /* _TRACE_PSEUDO_LOCK_H */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From 6fc0de37f663278af160e8e1f0c38b27e6c06206 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Fri, 22 Jun 2018 15:42:30 -0700
Subject: x86/intel_rdt: Limit C-states dynamically when pseudo-locking active

Deeper C-states impact cache content through shrinking of the cache or
flushing entire cache to memory before reducing power to the cache.
Deeper C-states will thus negatively impact the pseudo-locked regions.

To avoid impacting pseudo-locked regions C-states are limited on
pseudo-locked region creation so that cores associated with the
pseudo-locked region are prevented from entering deeper C-states.
This is accomplished by requesting a CPU latency target which will
prevent the core from entering C6 across all supported platforms.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/1ef4f99dd6ba12fa6fb44c5a1141e75f952b9cd9.1529706536.git.reinette.chatre@intel.com
---
 Documentation/x86/intel_rdt_ui.txt          |  4 +-
 arch/x86/kernel/cpu/intel_rdt.h             |  2 +
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 85 ++++++++++++++++++++++++++++-
 3 files changed, 87 insertions(+), 4 deletions(-)

diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index bcd0a6d2fcf8..acac30b67c62 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -461,8 +461,8 @@ in the cache via carefully configuring the CAT feature and controlling
 application behavior. There is no guarantee that data is placed in
 cache. Instructions like INVD, WBINVD, CLFLUSH, etc. can still evict
 “locked” data from cache. Power management C-states may shrink or
-power off cache. It is thus recommended to limit the processor maximum
-C-state, for example, by setting the processor.max_cstate kernel parameter.
+power off cache. Deeper C-states will automatically be restricted on
+pseudo-locked region creation.
 
 It is required that an application using a pseudo-locked region runs
 with affinity to the cores (or a subset of the cores) associated
diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index b8e490a43290..2d9cbb9d7a58 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -142,6 +142,7 @@ struct mongroup {
  *			region
  * @debugfs_dir:	pointer to this region's directory in the debugfs
  *			filesystem
+ * @pm_reqs:		Power management QoS requests related to this region
  */
 struct pseudo_lock_region {
 	struct rdt_resource	*r;
@@ -155,6 +156,7 @@ struct pseudo_lock_region {
 	void			*kmem;
 	unsigned int		minor;
 	struct dentry		*debugfs_dir;
+	struct list_head	pm_reqs;
 };
 
 /**
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index dd1341557c9d..6e83f61552a5 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -17,6 +17,7 @@
 #include <linux/debugfs.h>
 #include <linux/kthread.h>
 #include <linux/mman.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
 
@@ -175,6 +176,76 @@ static struct rdtgroup *region_find_by_minor(unsigned int minor)
 	return rdtgrp_match;
 }
 
+/**
+ * pseudo_lock_pm_req - A power management QoS request list entry
+ * @list:	Entry within the @pm_reqs list for a pseudo-locked region
+ * @req:	PM QoS request
+ */
+struct pseudo_lock_pm_req {
+	struct list_head list;
+	struct dev_pm_qos_request req;
+};
+
+static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req, *next;
+
+	list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
+		dev_pm_qos_remove_request(&pm_req->req);
+		list_del(&pm_req->list);
+		kfree(pm_req);
+	}
+}
+
+/**
+ * pseudo_lock_cstates_constrain - Restrict cores from entering C6
+ *
+ * To prevent the cache from being affected by power management entering
+ * C6 has to be avoided. This is accomplished by requesting a latency
+ * requirement lower than lowest C6 exit latency of all supported
+ * platforms as found in the cpuidle state tables in the intel_idle driver.
+ * At this time it is possible to do so with a single latency requirement
+ * for all supported platforms.
+ *
+ * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
+ * the ACPI latencies need to be considered while keeping in mind that C2
+ * may be set to map to deeper sleep states. In this case the latency
+ * requirement needs to prevent entering C2 also.
+ */
+static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
+{
+	struct pseudo_lock_pm_req *pm_req;
+	int cpu;
+	int ret;
+
+	for_each_cpu(cpu, &plr->d->cpu_mask) {
+		pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
+		if (!pm_req) {
+			rdt_last_cmd_puts("fail allocating mem for PM QoS\n");
+			ret = -ENOMEM;
+			goto out_err;
+		}
+		ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+					     &pm_req->req,
+					     DEV_PM_QOS_RESUME_LATENCY,
+					     30);
+		if (ret < 0) {
+			rdt_last_cmd_printf("fail to add latency req cpu%d\n",
+					    cpu);
+			kfree(pm_req);
+			ret = -1;
+			goto out_err;
+		}
+		list_add(&pm_req->list, &plr->pm_reqs);
+	}
+
+	return 0;
+
+out_err:
+	pseudo_lock_cstates_relax(plr);
+	return ret;
+}
+
 /**
  * pseudo_lock_region_init - Initialize pseudo-lock region information
  * @plr: pseudo-lock region
@@ -242,6 +313,7 @@ static int pseudo_lock_init(struct rdtgroup *rdtgrp)
 		return -ENOMEM;
 
 	init_waitqueue_head(&plr->lock_thread_wq);
+	INIT_LIST_HEAD(&plr->pm_reqs);
 	rdtgrp->plr = plr;
 	return 0;
 }
@@ -1135,6 +1207,12 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	if (ret < 0)
 		return ret;
 
+	ret = pseudo_lock_cstates_constrain(plr);
+	if (ret < 0) {
+		ret = -EINVAL;
+		goto out_region;
+	}
+
 	plr->thread_done = 0;
 
 	thread = kthread_create_on_node(pseudo_lock_fn, rdtgrp,
@@ -1143,7 +1221,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	if (IS_ERR(thread)) {
 		ret = PTR_ERR(thread);
 		rdt_last_cmd_printf("locking thread returned error %d\n", ret);
-		goto out_region;
+		goto out_cstates;
 	}
 
 	kthread_bind(thread, plr->cpu);
@@ -1161,7 +1239,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		 * empty pseudo-locking loop.
 		 */
 		rdt_last_cmd_puts("locking thread interrupted\n");
-		goto out_region;
+		goto out_cstates;
 	}
 
 	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
@@ -1222,6 +1300,8 @@ out_minor:
 	pseudo_lock_minor_release(new_minor);
 out_debugfs:
 	debugfs_remove_recursive(plr->debugfs_dir);
+out_cstates:
+	pseudo_lock_cstates_relax(plr);
 out_region:
 	pseudo_lock_region_clear(plr);
 out:
@@ -1255,6 +1335,7 @@ void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
 		goto free;
 	}
 
+	pseudo_lock_cstates_relax(plr);
 	debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
 	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
 	pseudo_lock_minor_release(plr->minor);
-- 
cgit v1.2.3


From 0ef8b4567d08a557b5226a4926ffd689ef0298ad Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Mon, 25 Jun 2018 01:37:50 +0530
Subject: tls: Removed unused variable

Removed unused variable 'rxm' from tls_queue().

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f127fac88acf..727433b37bb5 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -990,9 +990,6 @@ static void tls_queue(struct strparser *strp, struct sk_buff *skb)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
-	struct strp_msg *rxm;
-
-	rxm = strp_msg(skb);
 
 	ctx->decrypted = false;
 
-- 
cgit v1.2.3


From 0c3bf18491c094d9fdc1d0a0a9f0f9f8f520869d Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Tue, 5 Jun 2018 12:00:20 +0200
Subject: MIPS: Make elf2ecoff work on 64bit host machines

Use fixed width integer types for ecoff structs to make elf2ecoff work
on 64bit host machines.

Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Reviewed-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19483/
Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/boot/ecoff.h     | 61 ++++++++++++++++++++++++----------------------
 arch/mips/boot/elf2ecoff.c | 31 +++++++++++------------
 2 files changed, 48 insertions(+), 44 deletions(-)

diff --git a/arch/mips/boot/ecoff.h b/arch/mips/boot/ecoff.h
index b3e73c22c345..5be79ebfc3f8 100644
--- a/arch/mips/boot/ecoff.h
+++ b/arch/mips/boot/ecoff.h
@@ -2,14 +2,17 @@
 /*
  * Some ECOFF definitions.
  */
+
+#include <stdint.h>
+
 typedef struct filehdr {
-	unsigned short	f_magic;	/* magic number */
-	unsigned short	f_nscns;	/* number of sections */
-	long		f_timdat;	/* time & date stamp */
-	long		f_symptr;	/* file pointer to symbolic header */
-	long		f_nsyms;	/* sizeof(symbolic hdr) */
-	unsigned short	f_opthdr;	/* sizeof(optional hdr) */
-	unsigned short	f_flags;	/* flags */
+	uint16_t	f_magic;	/* magic number */
+	uint16_t	f_nscns;	/* number of sections */
+	int32_t		f_timdat;	/* time & date stamp */
+	int32_t		f_symptr;	/* file pointer to symbolic header */
+	int32_t		f_nsyms;	/* sizeof(symbolic hdr) */
+	uint16_t	f_opthdr;	/* sizeof(optional hdr) */
+	uint16_t	f_flags;	/* flags */
 } FILHDR;
 #define FILHSZ	sizeof(FILHDR)
 
@@ -18,32 +21,32 @@ typedef struct filehdr {
 
 typedef struct scnhdr {
 	char		s_name[8];	/* section name */
-	long		s_paddr;	/* physical address, aliased s_nlib */
-	long		s_vaddr;	/* virtual address */
-	long		s_size;		/* section size */
-	long		s_scnptr;	/* file ptr to raw data for section */
-	long		s_relptr;	/* file ptr to relocation */
-	long		s_lnnoptr;	/* file ptr to gp histogram */
-	unsigned short	s_nreloc;	/* number of relocation entries */
-	unsigned short	s_nlnno;	/* number of gp histogram entries */
-	long		s_flags;	/* flags */
+	int32_t		s_paddr;	/* physical address, aliased s_nlib */
+	int32_t		s_vaddr;	/* virtual address */
+	int32_t		s_size;		/* section size */
+	int32_t		s_scnptr;	/* file ptr to raw data for section */
+	int32_t		s_relptr;	/* file ptr to relocation */
+	int32_t		s_lnnoptr;	/* file ptr to gp histogram */
+	uint16_t	s_nreloc;	/* number of relocation entries */
+	uint16_t	s_nlnno;	/* number of gp histogram entries */
+	int32_t		s_flags;	/* flags */
 } SCNHDR;
 #define SCNHSZ		sizeof(SCNHDR)
-#define SCNROUND	((long)16)
+#define SCNROUND	((int32_t)16)
 
 typedef struct aouthdr {
-	short	magic;		/* see above				*/
-	short	vstamp;		/* version stamp			*/
-	long	tsize;		/* text size in bytes, padded to DW bdry*/
-	long	dsize;		/* initialized data "  "		*/
-	long	bsize;		/* uninitialized data "	  "		*/
-	long	entry;		/* entry pt.				*/
-	long	text_start;	/* base of text used for this file	*/
-	long	data_start;	/* base of data used for this file	*/
-	long	bss_start;	/* base of bss used for this file	*/
-	long	gprmask;	/* general purpose register mask	*/
-	long	cprmask[4];	/* co-processor register masks		*/
-	long	gp_value;	/* the gp value used for this object	*/
+	int16_t	magic;		/* see above				*/
+	int16_t	vstamp;		/* version stamp			*/
+	int32_t	tsize;		/* text size in bytes, padded to DW bdry*/
+	int32_t	dsize;		/* initialized data "  "		*/
+	int32_t	bsize;		/* uninitialized data "	  "		*/
+	int32_t	entry;		/* entry pt.				*/
+	int32_t	text_start;	/* base of text used for this file	*/
+	int32_t	data_start;	/* base of data used for this file	*/
+	int32_t	bss_start;	/* base of bss used for this file	*/
+	int32_t	gprmask;	/* general purpose register mask	*/
+	int32_t	cprmask[4];	/* co-processor register masks		*/
+	int32_t	gp_value;	/* the gp value used for this object	*/
 } AOUTHDR;
 #define AOUTHSZ sizeof(AOUTHDR)
 
diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c
index 266c8137e859..6972b97235da 100644
--- a/arch/mips/boot/elf2ecoff.c
+++ b/arch/mips/boot/elf2ecoff.c
@@ -43,6 +43,8 @@
 #include <limits.h>
 #include <netinet/in.h>
 #include <stdlib.h>
+#include <stdint.h>
+#include <inttypes.h>
 
 #include "ecoff.h"
 
@@ -55,8 +57,8 @@
 /* -------------------------------------------------------------------- */
 
 struct sect {
-	unsigned long vaddr;
-	unsigned long len;
+	uint32_t vaddr;
+	uint32_t len;
 };
 
 int *symTypeTable;
@@ -153,16 +155,16 @@ static char *saveRead(int file, off_t offset, off_t len, char *name)
 }
 
 #define swab16(x) \
-	((unsigned short)( \
-		(((unsigned short)(x) & (unsigned short)0x00ffU) << 8) | \
-		(((unsigned short)(x) & (unsigned short)0xff00U) >> 8) ))
+	((uint16_t)( \
+		(((uint16_t)(x) & (uint16_t)0x00ffU) << 8) | \
+		(((uint16_t)(x) & (uint16_t)0xff00U) >> 8) ))
 
 #define swab32(x) \
 	((unsigned int)( \
-		(((unsigned int)(x) & (unsigned int)0x000000ffUL) << 24) | \
-		(((unsigned int)(x) & (unsigned int)0x0000ff00UL) <<  8) | \
-		(((unsigned int)(x) & (unsigned int)0x00ff0000UL) >>  8) | \
-		(((unsigned int)(x) & (unsigned int)0xff000000UL) >> 24) ))
+		(((uint32_t)(x) & (uint32_t)0x000000ffUL) << 24) | \
+		(((uint32_t)(x) & (uint32_t)0x0000ff00UL) <<  8) | \
+		(((uint32_t)(x) & (uint32_t)0x00ff0000UL) >>  8) | \
+		(((uint32_t)(x) & (uint32_t)0xff000000UL) >> 24) ))
 
 static void convert_elf_hdr(Elf32_Ehdr * e)
 {
@@ -274,7 +276,7 @@ int main(int argc, char *argv[])
 	struct aouthdr eah;
 	struct scnhdr esecs[6];
 	int infile, outfile;
-	unsigned long cur_vma = ULONG_MAX;
+	uint32_t cur_vma = UINT32_MAX;
 	int addflag = 0;
 	int nosecs;
 
@@ -518,7 +520,7 @@ int main(int argc, char *argv[])
 
 		for (i = 0; i < nosecs; i++) {
 			printf
-			    ("Section %d: %s phys %lx  size %lx	 file offset %lx\n",
+			    ("Section %d: %s phys %"PRIx32"  size %"PRIx32"\t file offset %"PRIx32"\n",
 			     i, esecs[i].s_name, esecs[i].s_paddr,
 			     esecs[i].s_size, esecs[i].s_scnptr);
 		}
@@ -564,17 +566,16 @@ int main(int argc, char *argv[])
 		   the section can be loaded before copying. */
 		if (ph[i].p_type == PT_LOAD && ph[i].p_filesz) {
 			if (cur_vma != ph[i].p_vaddr) {
-				unsigned long gap =
-				    ph[i].p_vaddr - cur_vma;
+				uint32_t gap = ph[i].p_vaddr - cur_vma;
 				char obuf[1024];
 				if (gap > 65536) {
 					fprintf(stderr,
-						"Intersegment gap (%ld bytes) too large.\n",
+						"Intersegment gap (%"PRId32" bytes) too large.\n",
 						gap);
 					exit(1);
 				}
 				fprintf(stderr,
-					"Warning: %ld byte intersegment gap.\n",
+					"Warning: %d byte intersegment gap.\n",
 					gap);
 				memset(obuf, 0, sizeof obuf);
 				while (gap) {
-- 
cgit v1.2.3


From 28a87b459baf7a2b583ba2cdc553e58419b2e40b Mon Sep 17 00:00:00 2001
From: Yegor Yefremov <yegorslists@googlemail.com>
Date: Wed, 25 Apr 2018 09:39:06 +0200
Subject: MIPS: kexec: fix typos

Correct a couple of typos within comments in
arch/mips/kernel/relocate_kernel.S.

[paul.burton@mips.com: Add a commit message.]

Signed-off-by: Yegor Yefremov <yegorslists@googlemail.com>
Patchwork: https://patchwork.linux-mips.org/patch/19218/
Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/kernel/relocate_kernel.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/mips/kernel/relocate_kernel.S b/arch/mips/kernel/relocate_kernel.S
index c6bbf2165051..419c92197b2f 100644
--- a/arch/mips/kernel/relocate_kernel.S
+++ b/arch/mips/kernel/relocate_kernel.S
@@ -85,7 +85,7 @@ done:
 
 #ifdef CONFIG_CPU_CAVIUM_OCTEON
 	/* We need to flush I-cache before jumping to new kernel.
-	 * Unfortunatelly, this code is cpu-specific.
+	 * Unfortunately, this code is cpu-specific.
 	 */
 	.set push
 	.set noreorder
@@ -145,7 +145,7 @@ LEAF(kexec_smp_wait)
 #endif
 
 /* All parameters to new kernel are passed in registers a0-a3.
- * kexec_args[0..3] are uses to prepare register values.
+ * kexec_args[0..3] are used to prepare register values.
  */
 
 kexec_args:
-- 
cgit v1.2.3


From 9c78ecaf7ba88818b45303365d05b5a3461e0f3b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:30 +0200
Subject: MIPS: remove a dead ifdef from mach-ath25/dma-coherence.h

ath25 is alwas non-coherent, so keeping these ifdefs doesn't make any sense.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19528/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/mach-ath25/dma-coherence.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/mips/include/asm/mach-ath25/dma-coherence.h b/arch/mips/include/asm/mach-ath25/dma-coherence.h
index d5defdde32db..124755d4f079 100644
--- a/arch/mips/include/asm/mach-ath25/dma-coherence.h
+++ b/arch/mips/include/asm/mach-ath25/dma-coherence.h
@@ -61,12 +61,7 @@ static inline int plat_dma_supported(struct device *dev, u64 mask)
 
 static inline int plat_device_is_coherent(struct device *dev)
 {
-#ifdef CONFIG_DMA_COHERENT
-	return 1;
-#endif
-#ifdef CONFIG_DMA_NONCOHERENT
 	return 0;
-#endif
 }
 
 static inline void plat_post_dma_flush(struct device *dev)
-- 
cgit v1.2.3


From 972dc3b79f421b5ae553b1073708cbd0d4da4a91 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:31 +0200
Subject: MIPS: simplify CONFIG_DMA_NONCOHERENT ifdefs

CONFIG_DMA_MAYBE_COHERENT already selects CONFIG_DMA_NONCOHERENT, so we
can remove the extra conditions.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19529/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/io.h | 4 ++--
 arch/mips/mm/c-r4k.c       | 4 ++--
 arch/mips/mm/cache.c       | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index cea8ad864b3f..a363d5fa281f 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -590,7 +590,7 @@ static inline void memcpy_toio(volatile void __iomem *dst, const void *src, int
  *
  * This API used to be exported; it now is for arch code internal use only.
  */
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 extern void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
 extern void (*_dma_cache_wback)(unsigned long start, unsigned long size);
@@ -609,7 +609,7 @@ extern void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 #define dma_cache_inv(start,size)	\
 	do { (void) (start); (void) (size); } while (0)
 
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 /*
  * Read a 32-bit register that requires a 64-bit read cycle on the bus.
diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index e12dfa48b478..b83ecfb2fbfc 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -830,7 +830,7 @@ static void r4k_flush_icache_user_range(unsigned long start, unsigned long end)
 	return __r4k_flush_icache_range(start, end, true);
 }
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 {
@@ -904,7 +904,7 @@ static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 	bc_inv(addr, size);
 	__sync();
 }
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 struct flush_cache_sigtramp_args {
 	struct mm_struct *mm;
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index 0d3c656feba0..70a523151ff3 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -56,7 +56,7 @@ EXPORT_SYMBOL_GPL(local_flush_data_cache_page);
 EXPORT_SYMBOL(flush_data_cache_page);
 EXPORT_SYMBOL(flush_icache_all);
 
-#if defined(CONFIG_DMA_NONCOHERENT) || defined(CONFIG_DMA_MAYBE_COHERENT)
+#ifdef CONFIG_DMA_NONCOHERENT
 
 /* DMA cache operations. */
 void (*_dma_cache_wback_inv)(unsigned long start, unsigned long size);
@@ -65,7 +65,7 @@ void (*_dma_cache_inv)(unsigned long start, unsigned long size);
 
 EXPORT_SYMBOL(_dma_cache_wback_inv);
 
-#endif /* CONFIG_DMA_NONCOHERENT || CONFIG_DMA_MAYBE_COHERENT */
+#endif /* CONFIG_DMA_NONCOHERENT */
 
 /*
  * We could optimize the case where the cache argument is not BCACHE but
-- 
cgit v1.2.3


From 7e4dbdc11261bd7aaa18051247d01429e0b7cd03 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:32 +0200
Subject: MIPS: remove CONFIG_DMA_COHERENT

We can just check for !CONFIG_DMA_NONCOHERENT instead and simplify things
a lot.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19530/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                            | 16 ----------------
 arch/mips/include/asm/dma-coherence.h        |  6 +++---
 arch/mips/include/asm/mach-generic/kmalloc.h |  3 +--
 arch/mips/mti-malta/malta-setup.c            |  4 ++--
 arch/mips/sibyte/Kconfig                     |  1 -
 5 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 08c10c518f83..a7ecd785f8b9 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -666,7 +666,6 @@ config SGI_IP27
 	select FW_ARC64
 	select BOOT_ELF64
 	select DEFAULT_SGI_PARTITION
-	select DMA_COHERENT
 	select SYS_HAS_EARLY_PRINTK
 	select HW_HAS_PCI
 	select NR_CPUS_DEFAULT_64
@@ -743,7 +742,6 @@ config SGI_IP32
 config SIBYTE_CRHINE
 	bool "Sibyte BCM91120C-CRhine"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -753,7 +751,6 @@ config SIBYTE_CRHINE
 config SIBYTE_CARMEL
 	bool "Sibyte BCM91120x-Carmel"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -763,7 +760,6 @@ config SIBYTE_CARMEL
 config SIBYTE_CRHONE
 	bool "Sibyte BCM91125C-CRhone"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1125
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -774,7 +770,6 @@ config SIBYTE_CRHONE
 config SIBYTE_RHONE
 	bool "Sibyte BCM91125E-Rhone"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_BCM1125H
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -784,7 +779,6 @@ config SIBYTE_RHONE
 config SIBYTE_SWARM
 	bool "Sibyte BCM91250A-SWARM"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -797,7 +791,6 @@ config SIBYTE_SWARM
 config SIBYTE_LITTLESUR
 	bool "Sibyte BCM91250C2-LittleSur"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select HAVE_PATA_PLATFORM
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
@@ -809,7 +802,6 @@ config SIBYTE_LITTLESUR
 config SIBYTE_SENTOSA
 	bool "Sibyte BCM91250E-Sentosa"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -819,7 +811,6 @@ config SIBYTE_SENTOSA
 config SIBYTE_BIGSUR
 	bool "Sibyte BCM91480B-BigSur"
 	select BOOT_ELF32
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_4
 	select SIBYTE_BCM1x80
 	select SWAP_IO_SPACE
@@ -896,7 +887,6 @@ config CAVIUM_OCTEON_SOC
 	select CEVT_R4K
 	select ARCH_HAS_PHYS_TO_DMA
 	select PHYS_ADDR_T_64BIT
-	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select EDAC_SUPPORT
@@ -945,7 +935,6 @@ config NLM_XLR_BOARD
 	select PHYS_ADDR_T_64BIT
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_32
 	select CEVT_R4K
 	select CSRC_R4K
@@ -973,7 +962,6 @@ config NLM_XLP_BOARD
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	select SYS_SUPPORTS_HIGHMEM
-	select DMA_COHERENT
 	select NR_CPUS_DEFAULT_32
 	select CEVT_R4K
 	select CSRC_R4K
@@ -992,7 +980,6 @@ config MIPS_PARAVIRT
 	bool "Para-Virtualized guest system"
 	select CEVT_R4K
 	select CSRC_R4K
-	select DMA_COHERENT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
@@ -1118,9 +1105,6 @@ config DMA_PERDEV_COHERENT
 	bool
 	select DMA_MAYBE_COHERENT
 
-config DMA_COHERENT
-	bool
-
 config DMA_NONCOHERENT
 	bool
 	select NEED_DMA_MAP_STATE
diff --git a/arch/mips/include/asm/dma-coherence.h b/arch/mips/include/asm/dma-coherence.h
index 72d0eab02afc..8eda48748ed5 100644
--- a/arch/mips/include/asm/dma-coherence.h
+++ b/arch/mips/include/asm/dma-coherence.h
@@ -21,10 +21,10 @@ enum coherent_io_user_state {
 extern enum coherent_io_user_state coherentio;
 extern int hw_coherentio;
 #else
-#ifdef CONFIG_DMA_COHERENT
-#define coherentio	IO_COHERENCE_ENABLED
-#else
+#ifdef CONFIG_DMA_NONCOHERENT
 #define coherentio	IO_COHERENCE_DISABLED
+#else
+#define coherentio	IO_COHERENCE_ENABLED
 #endif
 #define hw_coherentio	0
 #endif /* CONFIG_DMA_MAYBE_COHERENT */
diff --git a/arch/mips/include/asm/mach-generic/kmalloc.h b/arch/mips/include/asm/mach-generic/kmalloc.h
index 74207c7bd00d..649a98338886 100644
--- a/arch/mips/include/asm/mach-generic/kmalloc.h
+++ b/arch/mips/include/asm/mach-generic/kmalloc.h
@@ -2,8 +2,7 @@
 #ifndef __ASM_MACH_GENERIC_KMALLOC_H
 #define __ASM_MACH_GENERIC_KMALLOC_H
 
-
-#ifndef CONFIG_DMA_COHERENT
+#ifdef CONFIG_DMA_NONCOHERENT
 /*
  * Total overkill for most systems but need as a safe default.
  * Set this one if any device in the system might do non-coherent DMA.
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index 7b63914d2e58..4d5cdfeee3db 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -227,7 +227,7 @@ static void __init bonito_quirks_setup(void)
 	} else
 		BONITO_BONGENCFG &= ~BONITO_BONGENCFG_DEBUGMODE;
 
-#ifdef CONFIG_DMA_COHERENT
+#ifndef CONFIG_DMA_NONCOHERENT
 	if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
 		BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
 		pr_info("Enabled Bonito CPU coherency\n");
@@ -279,7 +279,7 @@ void __init plat_mem_setup(void)
 	 */
 	enable_dma(4);
 
-#ifdef CONFIG_DMA_COHERENT
+#ifndef CONFIG_DMA_NONCOHERENT
 	if (mips_revision_sconid != MIPS_REVISION_SCON_BONITO)
 		panic("Hardware DMA cache coherency not supported");
 #endif
diff --git a/arch/mips/sibyte/Kconfig b/arch/mips/sibyte/Kconfig
index f4dbce25bc6a..7ec278d72096 100644
--- a/arch/mips/sibyte/Kconfig
+++ b/arch/mips/sibyte/Kconfig
@@ -70,7 +70,6 @@ config SIBYTE_BCM1x55
 
 config SIBYTE_SB1xxx_SOC
 	bool
-	select DMA_COHERENT
 	select IRQ_MIPS_CPU
 	select SWAP_IO_SPACE
 	select SYS_SUPPORTS_32BIT_KERNEL
-- 
cgit v1.2.3


From e20c5074f829c091d1173622213c98c963bebb91 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:33 +0200
Subject: MIPS: Octeon: unexport __phys_to_dma and __dma_to_phys

These functions are just low-level helpers for the swiotlb and dma-direct
implementations, and should never be used by drivers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19531/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/cavium-octeon/dma-octeon.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 7b335ab21697..e5d00c79bd26 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -13,7 +13,6 @@
 #include <linux/dma-direct.h>
 #include <linux/scatterlist.h>
 #include <linux/bootmem.h>
-#include <linux/export.h>
 #include <linux/swiotlb.h>
 #include <linux/types.h>
 #include <linux/init.h>
@@ -190,7 +189,6 @@ dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 
 	return ops->phys_to_dma(dev, paddr);
 }
-EXPORT_SYMBOL(__phys_to_dma);
 
 phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
@@ -200,7 +198,6 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 
 	return ops->dma_to_phys(dev, daddr);
 }
-EXPORT_SYMBOL(__dma_to_phys);
 
 static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
 	.dma_map_ops = {
-- 
cgit v1.2.3


From 97f9f9763a7a431e04f0ffd4e62d0d288a59f908 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:34 +0200
Subject: MIPS: Octeon: refactor swiotlb code

Share a common set of swiotlb operations, and to instead branch out in
__phys_to_dma/__dma_to_phys for the PCI vs non-PCI case.  Also use const
structures for the PCI methods so that attackers can't use them as
exploit vectors.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19532/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/cavium-octeon/dma-octeon.c               | 161 +++++++++------------
 .../include/asm/mach-cavium-octeon/dma-coherence.h |   2 -
 arch/mips/pci/pci-octeon.c                         |   2 -
 3 files changed, 71 insertions(+), 94 deletions(-)

diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index e5d00c79bd26..7f0c9f926b6e 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -23,10 +23,16 @@
 #include <asm/octeon/octeon.h>
 
 #ifdef CONFIG_PCI
+#include <linux/pci.h>
 #include <asm/octeon/pci-octeon.h>
 #include <asm/octeon/cvmx-npi-defs.h>
 #include <asm/octeon/cvmx-pci-defs.h>
 
+struct octeon_dma_map_ops {
+	dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
+	phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
+};
+
 static dma_addr_t octeon_hole_phys_to_dma(phys_addr_t paddr)
 {
 	if (paddr >= CVMX_PCIE_BAR1_PHYS_BASE && paddr < (CVMX_PCIE_BAR1_PHYS_BASE + CVMX_PCIE_BAR1_PHYS_SIZE))
@@ -60,6 +66,11 @@ static phys_addr_t octeon_gen1_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
+static const struct octeon_dma_map_ops octeon_gen1_ops = {
+	.phys_to_dma	= octeon_gen1_phys_to_dma,
+	.dma_to_phys	= octeon_gen1_dma_to_phys,
+};
+
 static dma_addr_t octeon_gen2_phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	return octeon_hole_phys_to_dma(paddr);
@@ -70,6 +81,11 @@ static phys_addr_t octeon_gen2_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return octeon_hole_dma_to_phys(daddr);
 }
 
+static const struct octeon_dma_map_ops octeon_gen2_ops = {
+	.phys_to_dma	= octeon_gen2_phys_to_dma,
+	.dma_to_phys	= octeon_gen2_dma_to_phys,
+};
+
 static dma_addr_t octeon_big_phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	if (paddr >= 0x410000000ull && paddr < 0x420000000ull)
@@ -92,6 +108,11 @@ static phys_addr_t octeon_big_dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
+static const struct octeon_dma_map_ops octeon_big_ops = {
+	.phys_to_dma	= octeon_big_phys_to_dma,
+	.dma_to_phys	= octeon_big_dma_to_phys,
+};
+
 static dma_addr_t octeon_small_phys_to_dma(struct device *dev,
 					   phys_addr_t paddr)
 {
@@ -120,6 +141,32 @@ static phys_addr_t octeon_small_dma_to_phys(struct device *dev,
 	return daddr;
 }
 
+static const struct octeon_dma_map_ops octeon_small_ops = {
+	.phys_to_dma	= octeon_small_phys_to_dma,
+	.dma_to_phys	= octeon_small_dma_to_phys,
+};
+
+static const struct octeon_dma_map_ops *octeon_pci_dma_ops;
+
+void __init octeon_pci_dma_init(void)
+{
+	switch (octeon_dma_bar_type) {
+	case OCTEON_DMA_BAR_TYPE_PCIE:
+		octeon_pci_dma_ops = &octeon_gen1_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_PCIE2:
+		octeon_pci_dma_ops = &octeon_gen2_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_BIG:
+		octeon_pci_dma_ops = &octeon_big_ops;
+		break;
+	case OCTEON_DMA_BAR_TYPE_SMALL:
+		octeon_pci_dma_ops = &octeon_small_ops;
+		break;
+	default:
+		BUG();
+	}
+}
 #endif /* CONFIG_PCI */
 
 static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page,
@@ -165,57 +212,37 @@ static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
 	return ret;
 }
 
-static dma_addr_t octeon_unity_phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	return paddr;
-}
-
-static phys_addr_t octeon_unity_dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	return daddr;
-}
-
-struct octeon_dma_map_ops {
-	const struct dma_map_ops dma_map_ops;
-	dma_addr_t (*phys_to_dma)(struct device *dev, phys_addr_t paddr);
-	phys_addr_t (*dma_to_phys)(struct device *dev, dma_addr_t daddr);
-};
-
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
-						      struct octeon_dma_map_ops,
-						      dma_map_ops);
-
-	return ops->phys_to_dma(dev, paddr);
+#ifdef CONFIG_PCI
+	if (dev && dev_is_pci(dev))
+		return octeon_pci_dma_ops->phys_to_dma(dev, paddr);
+#endif
+	return paddr;
 }
 
 phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 {
-	struct octeon_dma_map_ops *ops = container_of(get_dma_ops(dev),
-						      struct octeon_dma_map_ops,
-						      dma_map_ops);
-
-	return ops->dma_to_phys(dev, daddr);
+#ifdef CONFIG_PCI
+	if (dev && dev_is_pci(dev))
+		return octeon_pci_dma_ops->dma_to_phys(dev, daddr);
+#endif
+	return daddr;
 }
 
-static struct octeon_dma_map_ops octeon_linear_dma_map_ops = {
-	.dma_map_ops = {
-		.alloc = octeon_dma_alloc_coherent,
-		.free = swiotlb_free,
-		.map_page = octeon_dma_map_page,
-		.unmap_page = swiotlb_unmap_page,
-		.map_sg = octeon_dma_map_sg,
-		.unmap_sg = swiotlb_unmap_sg_attrs,
-		.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-		.sync_single_for_device = octeon_dma_sync_single_for_device,
-		.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-		.sync_sg_for_device = octeon_dma_sync_sg_for_device,
-		.mapping_error = swiotlb_dma_mapping_error,
-		.dma_supported = swiotlb_dma_supported
-	},
-	.phys_to_dma = octeon_unity_phys_to_dma,
-	.dma_to_phys = octeon_unity_dma_to_phys
+static const struct dma_map_ops octeon_swiotlb_ops = {
+	.alloc			= octeon_dma_alloc_coherent,
+	.free			= swiotlb_free,
+	.map_page		= octeon_dma_map_page,
+	.unmap_page		= swiotlb_unmap_page,
+	.map_sg			= octeon_dma_map_sg,
+	.unmap_sg		= swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu	= swiotlb_sync_single_for_cpu,
+	.sync_single_for_device	= octeon_dma_sync_single_for_device,
+	.sync_sg_for_cpu	= swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device	= octeon_dma_sync_sg_for_device,
+	.mapping_error		= swiotlb_dma_mapping_error,
+	.dma_supported		= swiotlb_dma_supported
 };
 
 char *octeon_swiotlb;
@@ -281,51 +308,5 @@ void __init plat_swiotlb_setup(void)
 	if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
 		panic("Cannot allocate SWIOTLB buffer");
 
-	mips_dma_map_ops = &octeon_linear_dma_map_ops.dma_map_ops;
+	mips_dma_map_ops = &octeon_swiotlb_ops;
 }
-
-#ifdef CONFIG_PCI
-static struct octeon_dma_map_ops _octeon_pci_dma_map_ops = {
-	.dma_map_ops = {
-		.alloc = octeon_dma_alloc_coherent,
-		.free = swiotlb_free,
-		.map_page = octeon_dma_map_page,
-		.unmap_page = swiotlb_unmap_page,
-		.map_sg = octeon_dma_map_sg,
-		.unmap_sg = swiotlb_unmap_sg_attrs,
-		.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-		.sync_single_for_device = octeon_dma_sync_single_for_device,
-		.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-		.sync_sg_for_device = octeon_dma_sync_sg_for_device,
-		.mapping_error = swiotlb_dma_mapping_error,
-		.dma_supported = swiotlb_dma_supported
-	},
-};
-
-const struct dma_map_ops *octeon_pci_dma_map_ops;
-
-void __init octeon_pci_dma_init(void)
-{
-	switch (octeon_dma_bar_type) {
-	case OCTEON_DMA_BAR_TYPE_PCIE2:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_gen2_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_gen2_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_PCIE:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_gen1_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_gen1_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_BIG:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_big_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_big_dma_to_phys;
-		break;
-	case OCTEON_DMA_BAR_TYPE_SMALL:
-		_octeon_pci_dma_map_ops.phys_to_dma = octeon_small_phys_to_dma;
-		_octeon_pci_dma_map_ops.dma_to_phys = octeon_small_dma_to_phys;
-		break;
-	default:
-		BUG();
-	}
-	octeon_pci_dma_map_ops = &_octeon_pci_dma_map_ops.dma_map_ops;
-}
-#endif /* CONFIG_PCI */
diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
index 6eb1ee548b11..c5cdeea495f8 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
@@ -72,8 +72,6 @@ static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
 phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
 
-struct dma_map_ops;
-extern const struct dma_map_ops *octeon_pci_dma_map_ops;
 extern char *octeon_swiotlb;
 
 #endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index 3e92a06fa772..a20697df3539 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -166,8 +166,6 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 		pci_write_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, dconfig);
 	}
 
-	dev->dev.dma_ops = octeon_pci_dma_map_ops;
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From e799de3efb9d6e0df5740eed901b89a6e533eaef Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:35 +0200
Subject: MIPS: loongson: remove loongson_dma_supported

swiotlb_dma_supported will always return true for a mask large enough to
cover the DMA addresses for all physical memory, which is the right
thing to do for swiotlb based dma ops.  This function returned false
if the mask was bigger than a firmware set dma_mask_bits that apparently
can be either 32 or 64, and which seems completely buggys if it actually
is not 64, as the false return negates the whole point of swiotlb.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19533/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/loongson64/common/dma-swiotlb.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
index 6a739f8ae110..a5e50f2ec301 100644
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ b/arch/mips/loongson64/common/dma-swiotlb.c
@@ -56,13 +56,6 @@ static void loongson_dma_sync_sg_for_device(struct device *dev,
 	mb();
 }
 
-static int loongson_dma_supported(struct device *dev, u64 mask)
-{
-	if (mask > DMA_BIT_MASK(loongson_sysconf.dma_mask_bits))
-		return 0;
-	return swiotlb_dma_supported(dev, mask);
-}
-
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	long nid;
@@ -99,7 +92,7 @@ static const struct dma_map_ops loongson_dma_map_ops = {
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
 	.sync_sg_for_device = loongson_dma_sync_sg_for_device,
 	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = loongson_dma_supported,
+	.dma_supported = swiotlb_dma_supported,
 };
 
 void __init plat_swiotlb_setup(void)
-- 
cgit v1.2.3


From f6d302e33d68ddbaf99c774ed994599243462b24 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:36 +0200
Subject: MIPS: consolidate the swiotlb implementations

Octeon and Loongson share exactly the same code, move it into a common
implementation, and use that implementation directly from get_arch_dma_ops.

Also provide the expected dma-direct.h helpers directly instead of
delegating to platform dma-coherence.h headers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19534/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/cavium-octeon/dma-octeon.c               | 61 -------------------
 arch/mips/include/asm/dma-direct.h                 | 17 +++++-
 arch/mips/include/asm/dma-mapping.h                |  5 ++
 .../include/asm/mach-cavium-octeon/dma-coherence.h | 11 ----
 .../include/asm/mach-loongson64/dma-coherence.h    | 10 ---
 arch/mips/loongson64/common/dma-swiotlb.c          | 71 +---------------------
 arch/mips/mm/Makefile                              |  1 +
 arch/mips/mm/dma-swiotlb.c                         | 61 +++++++++++++++++++
 8 files changed, 84 insertions(+), 153 deletions(-)
 create mode 100644 arch/mips/mm/dma-swiotlb.c

diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c
index 7f0c9f926b6e..236833be6fbe 100644
--- a/arch/mips/cavium-octeon/dma-octeon.c
+++ b/arch/mips/cavium-octeon/dma-octeon.c
@@ -11,7 +11,6 @@
  * Copyright (C) 2010 Cavium Networks, Inc.
  */
 #include <linux/dma-direct.h>
-#include <linux/scatterlist.h>
 #include <linux/bootmem.h>
 #include <linux/swiotlb.h>
 #include <linux/types.h>
@@ -169,49 +168,6 @@ void __init octeon_pci_dma_init(void)
 }
 #endif /* CONFIG_PCI */
 
-static dma_addr_t octeon_dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
-					    direction, attrs);
-	mb();
-
-	return daddr;
-}
-
-static int octeon_dma_map_sg(struct device *dev, struct scatterlist *sg,
-	int nents, enum dma_data_direction direction, unsigned long attrs)
-{
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, direction, attrs);
-	mb();
-	return r;
-}
-
-static void octeon_dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	swiotlb_sync_single_for_device(dev, dma_handle, size, direction);
-	mb();
-}
-
-static void octeon_dma_sync_sg_for_device(struct device *dev,
-	struct scatterlist *sg, int nelems, enum dma_data_direction direction)
-{
-	swiotlb_sync_sg_for_device(dev, sg, nelems, direction);
-	mb();
-}
-
-static void *octeon_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
-	mb();
-
-	return ret;
-}
-
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 #ifdef CONFIG_PCI
@@ -230,21 +186,6 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
-static const struct dma_map_ops octeon_swiotlb_ops = {
-	.alloc			= octeon_dma_alloc_coherent,
-	.free			= swiotlb_free,
-	.map_page		= octeon_dma_map_page,
-	.unmap_page		= swiotlb_unmap_page,
-	.map_sg			= octeon_dma_map_sg,
-	.unmap_sg		= swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu	= swiotlb_sync_single_for_cpu,
-	.sync_single_for_device	= octeon_dma_sync_single_for_device,
-	.sync_sg_for_cpu	= swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device	= octeon_dma_sync_sg_for_device,
-	.mapping_error		= swiotlb_dma_mapping_error,
-	.dma_supported		= swiotlb_dma_supported
-};
-
 char *octeon_swiotlb;
 
 void __init plat_swiotlb_setup(void)
@@ -307,6 +248,4 @@ void __init plat_swiotlb_setup(void)
 
 	if (swiotlb_init_with_tbl(octeon_swiotlb, swiotlb_nslabs, 1) == -ENOMEM)
 		panic("Cannot allocate SWIOTLB buffer");
-
-	mips_dma_map_ops = &octeon_swiotlb_ops;
 }
diff --git a/arch/mips/include/asm/dma-direct.h b/arch/mips/include/asm/dma-direct.h
index f32f15530aba..b5c240806e1b 100644
--- a/arch/mips/include/asm/dma-direct.h
+++ b/arch/mips/include/asm/dma-direct.h
@@ -1 +1,16 @@
-#include <asm/dma-coherence.h>
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _MIPS_DMA_DIRECT_H
+#define _MIPS_DMA_DIRECT_H 1
+
+static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
+{
+	if (!dev->dma_mask)
+		return false;
+
+	return addr + size - 1 <= *dev->dma_mask;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
+
+#endif /* _MIPS_DMA_DIRECT_H */
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 886e75a383f2..ebcce3e22297 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -11,10 +11,15 @@
 #endif
 
 extern const struct dma_map_ops *mips_dma_map_ops;
+extern const struct dma_map_ops mips_swiotlb_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
+#ifdef CONFIG_SWIOTLB
+	return &mips_swiotlb_ops;
+#else
 	return mips_dma_map_ops;
+#endif
 }
 
 #define arch_setup_dma_ops arch_setup_dma_ops
diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
index c5cdeea495f8..c0254c72d97b 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
@@ -61,17 +61,6 @@ static inline void plat_post_dma_flush(struct device *dev)
 {
 }
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
-
 extern char *octeon_swiotlb;
 
 #endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
index 64fc44dec0a8..b8825a7d1279 100644
--- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h
+++ b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
@@ -17,16 +17,6 @@
 
 struct device;
 
-static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
-{
-	if (!dev->dma_mask)
-		return false;
-
-	return addr + size - 1 <= *dev->dma_mask;
-}
-
-extern dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr);
-extern phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr);
 static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
 					  size_t size)
 {
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
index a5e50f2ec301..a4f554bf1232 100644
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ b/arch/mips/loongson64/common/dma-swiotlb.c
@@ -1,60 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <linux/mm.h>
+#include <linux/dma-direct.h>
 #include <linux/init.h>
-#include <linux/dma-mapping.h>
-#include <linux/scatterlist.h>
 #include <linux/swiotlb.h>
-#include <linux/bootmem.h>
-
-#include <asm/bootinfo.h>
-#include <boot_param.h>
-#include <dma-coherence.h>
-
-static void *loongson_dma_alloc_coherent(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
-	mb();
-	return ret;
-}
-
-static dma_addr_t loongson_dma_map_page(struct device *dev, struct page *page,
-				unsigned long offset, size_t size,
-				enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
-					dir, attrs);
-	mb();
-	return daddr;
-}
-
-static int loongson_dma_map_sg(struct device *dev, struct scatterlist *sg,
-				int nents, enum dma_data_direction dir,
-				unsigned long attrs)
-{
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs);
-	mb();
-
-	return r;
-}
-
-static void loongson_dma_sync_single_for_device(struct device *dev,
-				dma_addr_t dma_handle, size_t size,
-				enum dma_data_direction dir)
-{
-	swiotlb_sync_single_for_device(dev, dma_handle, size, dir);
-	mb();
-}
-
-static void loongson_dma_sync_sg_for_device(struct device *dev,
-				struct scatterlist *sg, int nents,
-				enum dma_data_direction dir)
-{
-	swiotlb_sync_sg_for_device(dev, sg, nents, dir);
-	mb();
-}
 
 dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
@@ -80,23 +27,7 @@ phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
 	return daddr;
 }
 
-static const struct dma_map_ops loongson_dma_map_ops = {
-	.alloc = loongson_dma_alloc_coherent,
-	.free = swiotlb_free,
-	.map_page = loongson_dma_map_page,
-	.unmap_page = swiotlb_unmap_page,
-	.map_sg = loongson_dma_map_sg,
-	.unmap_sg = swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
-	.sync_single_for_device = loongson_dma_sync_single_for_device,
-	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device = loongson_dma_sync_sg_for_device,
-	.mapping_error = swiotlb_dma_mapping_error,
-	.dma_supported = swiotlb_dma_supported,
-};
-
 void __init plat_swiotlb_setup(void)
 {
 	swiotlb_init(1);
-	mips_dma_map_ops = &loongson_dma_map_ops;
 }
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index c463bdad45c7..b87e4258fd78 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
 obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o
diff --git a/arch/mips/mm/dma-swiotlb.c b/arch/mips/mm/dma-swiotlb.c
new file mode 100644
index 000000000000..6014ed3479fd
--- /dev/null
+++ b/arch/mips/mm/dma-swiotlb.c
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-mapping.h>
+#include <linux/swiotlb.h>
+
+static void *mips_swiotlb_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
+
+	mb();
+	return ret;
+}
+
+static dma_addr_t mips_swiotlb_map_page(struct device *dev,
+		struct page *page, unsigned long offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
+					dir, attrs);
+	mb();
+	return daddr;
+}
+
+static int mips_swiotlb_map_sg(struct device *dev, struct scatterlist *sg,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs);
+	mb();
+
+	return r;
+}
+
+static void mips_swiotlb_sync_single_for_device(struct device *dev,
+		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
+{
+	swiotlb_sync_single_for_device(dev, dma_handle, size, dir);
+	mb();
+}
+
+static void mips_swiotlb_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sg, int nents, enum dma_data_direction dir)
+{
+	swiotlb_sync_sg_for_device(dev, sg, nents, dir);
+	mb();
+}
+
+const struct dma_map_ops mips_swiotlb_ops = {
+	.alloc			= mips_swiotlb_alloc,
+	.free			= swiotlb_free,
+	.map_page		= mips_swiotlb_map_page,
+	.unmap_page		= swiotlb_unmap_page,
+	.map_sg			= mips_swiotlb_map_sg,
+	.unmap_sg		= swiotlb_unmap_sg_attrs,
+	.sync_single_for_cpu	= swiotlb_sync_single_for_cpu,
+	.sync_single_for_device	= mips_swiotlb_sync_single_for_device,
+	.sync_sg_for_cpu	= swiotlb_sync_sg_for_cpu,
+	.sync_sg_for_device	= mips_swiotlb_sync_sg_for_device,
+	.mapping_error		= swiotlb_dma_mapping_error,
+	.dma_supported		= swiotlb_dma_supported,
+};
+EXPORT_SYMBOL(mips_swiotlb_ops);
-- 
cgit v1.2.3


From d3b83dcc7fcba94b7ec6bc0899828e1d814d20a9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:37 +0200
Subject: MIPS: remove the mips_dma_map_ops indirection

And use mips_default_dma_map_ops directly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19535/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/dma-mapping.h | 4 ++--
 arch/mips/mm/dma-default.c          | 6 ++----
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index ebcce3e22297..f24b052ec740 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -10,7 +10,7 @@
 #include <dma-coherence.h>
 #endif
 
-extern const struct dma_map_ops *mips_dma_map_ops;
+extern const struct dma_map_ops mips_default_dma_map_ops;
 extern const struct dma_map_ops mips_swiotlb_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
@@ -18,7 +18,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 #ifdef CONFIG_SWIOTLB
 	return &mips_swiotlb_ops;
 #else
-	return mips_dma_map_ops;
+	return &mips_default_dma_map_ops;
 #endif
 }
 
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index f9fef0028ca2..2db6c2a6f964 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -384,7 +384,7 @@ static void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		__dma_sync_virtual(vaddr, size, direction);
 }
 
-static const struct dma_map_ops mips_default_dma_map_ops = {
+const struct dma_map_ops mips_default_dma_map_ops = {
 	.alloc = mips_dma_alloc_coherent,
 	.free = mips_dma_free_coherent,
 	.mmap = mips_dma_mmap,
@@ -399,6 +399,4 @@ static const struct dma_map_ops mips_default_dma_map_ops = {
 	.dma_supported = mips_dma_supported,
 	.cache_sync = mips_dma_cache_sync,
 };
-
-const struct dma_map_ops *mips_dma_map_ops = &mips_default_dma_map_ops;
-EXPORT_SYMBOL(mips_dma_map_ops);
+EXPORT_SYMBOL(mips_default_dma_map_ops);
-- 
cgit v1.2.3


From 3369ddb62a42e8392562c86d63811ba8b0167a58 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:38 +0200
Subject: MIPS: make the default mips dma implementation optional

Octeon and loonson64 already don't use it at all, and we're going to
migrate more plaforms away from it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19536/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                   | 40 +++++++++++++++++++++++++++++++++++++
 arch/mips/include/asm/dma-mapping.h |  4 +++-
 arch/mips/jazz/Kconfig              |  3 +++
 arch/mips/loongson32/Kconfig        |  2 ++
 arch/mips/loongson64/Kconfig        |  2 ++
 arch/mips/mm/Makefile               |  3 ++-
 arch/mips/pic32/Kconfig             |  1 +
 arch/mips/txx9/Kconfig              |  1 +
 arch/mips/vr41xx/Kconfig            |  5 +++++
 9 files changed, 59 insertions(+), 2 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a7ecd785f8b9..7c539a39c43e 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -77,6 +77,9 @@ config MIPS
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
 
+config MIPS_DMA_DEFAULT
+	bool
+
 menu "Machine selection"
 
 choice
@@ -98,6 +101,7 @@ config MIPS_GENERIC
 	select IRQ_MIPS_CPU
 	select LIBFDT
 	select MIPS_CPU_SCACHE
+	select MIPS_DMA_DEFAULT
 	select MIPS_GIC
 	select MIPS_L1_CACHE_SHIFT_7
 	select NO_EXCEPT_FILL
@@ -141,6 +145,7 @@ config MIPS_ALCHEMY
 	select CEVT_R4K
 	select CSRC_R4K
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select DMA_MAYBE_COHERENT	# Au1000,1500,1100 aren't, rest is
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -156,6 +161,7 @@ config AR7
 	select CEVT_R4K
 	select CSRC_R4K
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select NO_EXCEPT_FILL
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_MIPS32_R1
@@ -178,6 +184,7 @@ config ATH25
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
 	select IRQ_DOMAIN
+	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -197,6 +204,7 @@ config ATH79
 	select COMMON_CLK
 	select CLKDEV_LOOKUP
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select MIPS_MACHINE
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_HAS_EARLY_PRINTK
@@ -223,6 +231,7 @@ config BMIPS_GENERIC
 	select BCM7120_L2_IRQ
 	select BRCMSTB_L2_IRQ
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select DMA_NONCOHERENT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -253,6 +262,7 @@ config BCM47XX
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
 	select SYS_HAS_CPU_MIPS32_R1
+	select MIPS_DMA_DEFAULT
 	select NO_EXCEPT_FILL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -276,6 +286,7 @@ config BCM63XX
 	select SYNC_R4K
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_HAS_EARLY_PRINTK
@@ -298,6 +309,7 @@ config MIPS_COBALT
 	select I8259
 	select IRQ_MIPS_CPU
 	select IRQ_GT641XX
+	select MIPS_DMA_DEFAULT
 	select PCI_GT64XXX_PCI0
 	select PCI
 	select SYS_HAS_CPU_NEVADA
@@ -318,6 +330,7 @@ config MACH_DECSTATION
 	select CPU_R4000_WORKAROUNDS if 64BIT
 	select CPU_R4400_WORKAROUNDS if 64BIT
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select NO_IOPORT_MAP
 	select IRQ_MIPS_CPU
 	select SYS_HAS_CPU_R3000
@@ -377,6 +390,7 @@ config MACH_INGENIC
 	select SYS_SUPPORTS_ZBOOT_UART16550
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select PINCTRL
 	select GPIOLIB
 	select COMMON_CLK
@@ -391,6 +405,7 @@ config LANTIQ
 	select IRQ_MIPS_CPU
 	select CEVT_R4K
 	select CSRC_R4K
+	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_SUPPORTS_BIG_ENDIAN
@@ -418,6 +433,7 @@ config LASAT
 	select SYS_HAS_EARLY_PRINTK
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select PCI_GT64XXX_PCI0
 	select MIPS_NILE4
 	select R5000_CPU_SCACHE
@@ -464,6 +480,7 @@ config MACH_PISTACHIO
 	select LIBFDT
 	select MFD_SYSCON
 	select MIPS_CPU_SCACHE
+	select MIPS_DMA_DEFAULT
 	select MIPS_GIC
 	select PINCTRL
 	select REGULATOR
@@ -496,6 +513,7 @@ config MIPS_MALTA
 	select GENERIC_ISA_DMA
 	select HAVE_PCSPKR_PLATFORM
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select MIPS_GIC
 	select HW_HAS_PCI
 	select I8253
@@ -552,6 +570,7 @@ config NEC_MARKEINS
 	bool "NEC EMMA2RH Mark-eins board"
 	select SOC_EMMA2RH
 	select HW_HAS_PCI
+	select MIPS_DMA_DEFAULT
 	help
 	  This enables support for the NEC Electronics Mark-eins boards.
 
@@ -565,12 +584,14 @@ config MACH_VR41XX
 
 config NXP_STB220
 	bool "NXP STB220 board"
+	select MIPS_DMA_DEFAULT
 	select SOC_PNX833X
 	help
 	 Support for NXP Semiconductors STB220 Development Board.
 
 config NXP_STB225
 	bool "NXP 225 board"
+	select MIPS_DMA_DEFAULT
 	select SOC_PNX833X
 	select SOC_PNX8335
 	help
@@ -590,6 +611,7 @@ config PMC_MSP
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_MIPS16
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select SERIAL_8250
 	select SERIAL_8250_CONSOLE
 	select USB_EHCI_BIG_ENDIAN_MMIO
@@ -607,6 +629,7 @@ config RALINK
 	select BOOT_RAW
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select USE_OF
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_HAS_CPU_MIPS32_R2
@@ -633,6 +656,7 @@ config SGI_IP22
 	select I8259
 	select IP22_CPU_SCACHE
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select SGI_HAS_I8042
 	select SGI_HAS_INDYDOG
@@ -666,6 +690,7 @@ config SGI_IP27
 	select FW_ARC64
 	select BOOT_ELF64
 	select DEFAULT_SGI_PARTITION
+	select MIPS_DMA_DEFAULT
 	select SYS_HAS_EARLY_PRINTK
 	select HW_HAS_PCI
 	select NR_CPUS_DEFAULT_64
@@ -692,6 +717,7 @@ config SGI_IP28
 	select DMA_NONCOHERENT
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select HW_HAS_EISA
 	select I8253
 	select I8259
@@ -728,6 +754,7 @@ config SGI_IP32
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select R5000_CPU_SCACHE
 	select RM7000_CPU_SCACHE
 	select SYS_HAS_CPU_R5000
@@ -742,6 +769,7 @@ config SGI_IP32
 config SIBYTE_CRHINE
 	bool "Sibyte BCM91120C-CRhine"
 	select BOOT_ELF32
+	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -751,6 +779,7 @@ config SIBYTE_CRHINE
 config SIBYTE_CARMEL
 	bool "Sibyte BCM91120x-Carmel"
 	select BOOT_ELF32
+	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -760,6 +789,7 @@ config SIBYTE_CARMEL
 config SIBYTE_CRHONE
 	bool "Sibyte BCM91125C-CRhone"
 	select BOOT_ELF32
+	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1125
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -770,6 +800,7 @@ config SIBYTE_CRHONE
 config SIBYTE_RHONE
 	bool "Sibyte BCM91125E-Rhone"
 	select BOOT_ELF32
+	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1125H
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -780,6 +811,7 @@ config SIBYTE_SWARM
 	bool "Sibyte BCM91250A-SWARM"
 	select BOOT_ELF32
 	select HAVE_PATA_PLATFORM
+	select MIPS_DMA_DEFAULT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -792,6 +824,7 @@ config SIBYTE_LITTLESUR
 	bool "Sibyte BCM91250C2-LittleSur"
 	select BOOT_ELF32
 	select HAVE_PATA_PLATFORM
+	select MIPS_DMA_DEFAULT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -802,6 +835,7 @@ config SIBYTE_LITTLESUR
 config SIBYTE_SENTOSA
 	bool "Sibyte BCM91250E-Sentosa"
 	select BOOT_ELF32
+	select MIPS_DMA_DEFAULT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -811,6 +845,7 @@ config SIBYTE_SENTOSA
 config SIBYTE_BIGSUR
 	bool "Sibyte BCM91480B-BigSur"
 	select BOOT_ELF32
+	select MIPS_DMA_DEFAULT
 	select NR_CPUS_DEFAULT_4
 	select SIBYTE_BCM1x80
 	select SWAP_IO_SPACE
@@ -841,6 +876,7 @@ config SNI_RM
 	select I8253
 	select I8259
 	select ISA
+	select MIPS_DMA_DEFAULT
 	select SWAP_IO_SPACE if CPU_BIG_ENDIAN
 	select SYS_HAS_CPU_R4X00
 	select SYS_HAS_CPU_R5000
@@ -871,6 +907,7 @@ config MIKROTIK_RB532
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
+	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -929,6 +966,7 @@ config NLM_XLR_BOARD
 	select SYS_HAS_CPU_XLR
 	select SYS_SUPPORTS_SMP
 	select HW_HAS_PCI
+	select MIPS_DMA_DEFAULT
 	select SWAP_IO_SPACE
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
@@ -955,6 +993,7 @@ config NLM_XLP_BOARD
 	select SYS_HAS_CPU_XLP
 	select SYS_SUPPORTS_SMP
 	select HW_HAS_PCI
+	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select PHYS_ADDR_T_64BIT
@@ -980,6 +1019,7 @@ config MIPS_PARAVIRT
 	bool "Para-Virtualized guest system"
 	select CEVT_R4K
 	select CSRC_R4K
+	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index f24b052ec740..eaf3d9054104 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -17,8 +17,10 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 #ifdef CONFIG_SWIOTLB
 	return &mips_swiotlb_ops;
-#else
+#elif defined(CONFIG_MIPS_DMA_DEFAULT)
 	return &mips_default_dma_map_ops;
+#else
+	return NULL;
 #endif
 }
 
diff --git a/arch/mips/jazz/Kconfig b/arch/mips/jazz/Kconfig
index 06838f80a5d7..d3ae3e0356f6 100644
--- a/arch/mips/jazz/Kconfig
+++ b/arch/mips/jazz/Kconfig
@@ -3,6 +3,7 @@ config ACER_PICA_61
 	bool "Support for Acer PICA 1 chipset"
 	depends on MACH_JAZZ
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	help
 	  This is a machine with a R4400 133/150 MHz CPU. To compile a Linux
@@ -14,6 +15,7 @@ config MIPS_MAGNUM_4000
 	bool "Support for MIPS Magnum 4000"
 	depends on MACH_JAZZ
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	help
@@ -26,6 +28,7 @@ config OLIVETTI_M700
 	bool "Support for Olivetti M700-10"
 	depends on MACH_JAZZ
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	help
 	  This is a machine with a R4000 100 MHz CPU. To compile a Linux
diff --git a/arch/mips/loongson32/Kconfig b/arch/mips/loongson32/Kconfig
index 462b126f45aa..7a69a6c0ce22 100644
--- a/arch/mips/loongson32/Kconfig
+++ b/arch/mips/loongson32/Kconfig
@@ -10,6 +10,7 @@ config LOONGSON1_LS1B
 	select CSRC_R4K if !MIPS_EXTERNAL_TIMER
 	select SYS_HAS_CPU_LOONGSON1B
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select BOOT_ELF32
 	select IRQ_MIPS_CPU
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -26,6 +27,7 @@ config LOONGSON1_LS1C
 	select CSRC_R4K if !MIPS_EXTERNAL_TIMER
 	select SYS_HAS_CPU_LOONGSON1C
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select BOOT_ELF32
 	select IRQ_MIPS_CPU
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index c79e6a565572..dbd2a9f9f9a9 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -13,6 +13,7 @@ config LEMOTE_FULOONG2E
 	select CSRC_R4K
 	select SYS_HAS_CPU_LOONGSON2E
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select BOOT_ELF32
 	select BOARD_SCACHE
 	select HW_HAS_PCI
@@ -44,6 +45,7 @@ config LEMOTE_MACH2F
 	select CS5536
 	select CSRC_R4K if ! MIPS_EXTERNAL_TIMER
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select HAVE_CLK
 	select HW_HAS_PCI
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index b87e4258fd78..038bfed34946 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -3,7 +3,7 @@
 # Makefile for the Linux/MIPS-specific parts of the memory manager.
 #
 
-obj-y				+= cache.o dma-default.o extable.o fault.o \
+obj-y				+= cache.o extable.o fault.o \
 				   gup.o init.o mmap.o page.o page-funcs.o \
 				   pgtable.o tlbex.o tlbex-fault.o tlb-funcs.o
 
@@ -17,6 +17,7 @@ obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
+obj-$(CONFIG_MIPS_DMA_DEFAULT)	+= dma-default.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
 obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
diff --git a/arch/mips/pic32/Kconfig b/arch/mips/pic32/Kconfig
index e284e89183cc..7feb7359b05b 100644
--- a/arch/mips/pic32/Kconfig
+++ b/arch/mips/pic32/Kconfig
@@ -11,6 +11,7 @@ config PIC32MZDA
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/txx9/Kconfig b/arch/mips/txx9/Kconfig
index d2509c93f0ee..9dfda3e90348 100644
--- a/arch/mips/txx9/Kconfig
+++ b/arch/mips/txx9/Kconfig
@@ -16,6 +16,7 @@ config MACH_TX49XX
 config MACH_TXX9
 	bool
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select SWAP_IO_SPACE
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/vr41xx/Kconfig b/arch/mips/vr41xx/Kconfig
index 992c988b83b0..cc69b2f663fa 100644
--- a/arch/mips/vr41xx/Kconfig
+++ b/arch/mips/vr41xx/Kconfig
@@ -9,6 +9,7 @@ config CASIO_E55
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select ISA
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -19,6 +20,7 @@ config IBM_WORKPAD
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select ISA
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -29,6 +31,7 @@ config TANBAC_TB022X
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select HW_HAS_PCI
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -45,6 +48,7 @@ config VICTOR_MPC30X
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select HW_HAS_PCI
 	select PCI_VR41XX
@@ -56,6 +60,7 @@ config ZAO_CAPCELLA
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
+	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select HW_HAS_PCI
 	select PCI_VR41XX
-- 
cgit v1.2.3


From 1f99e4b13b312737f0c4059d668782534ea1dc76 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:39 +0200
Subject: MIPS: Octeon: remove mips dma-default stubs

Octeon doesn't use the dma-default code, and now doesn't built it either,
so these stubs can be removed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19537/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 .../include/asm/mach-cavium-octeon/dma-coherence.h | 48 ----------------------
 1 file changed, 48 deletions(-)

diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
index c0254c72d97b..66eee98b8b8d 100644
--- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
+++ b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
@@ -4,11 +4,6 @@
  * for more details.
  *
  * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- *
- * Similar to mach-generic/dma-coherence.h except
- * plat_device_is_coherent hard coded to return 1.
- *
  */
 #ifndef __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
 #define __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
@@ -18,49 +13,6 @@
 struct device;
 
 extern void octeon_pci_dma_init(void);
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	BUG();
-	return 0;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	BUG();
-	return 0;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	BUG();
-	return 0;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-	BUG();
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	BUG();
-	return 0;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
 extern char *octeon_swiotlb;
 
 #endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */
-- 
cgit v1.2.3


From a330a9c59b45e53dee7985237340f6480a1ea08f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:40 +0200
Subject: MIPS: Octeon: move swiotlb declarations out of dma-coherence.h

No need to pull them into a global header.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19538/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 .../include/asm/mach-cavium-octeon/dma-coherence.h     | 18 ------------------
 arch/mips/include/asm/octeon/pci-octeon.h              |  3 +++
 arch/mips/pci/pci-octeon.c                             |  2 --
 arch/mips/pci/pcie-octeon.c                            |  2 --
 4 files changed, 3 insertions(+), 22 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h

diff --git a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h b/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
deleted file mode 100644
index 66eee98b8b8d..000000000000
--- a/arch/mips/include/asm/mach-cavium-octeon/dma-coherence.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- */
-#ifndef __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-#define __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H
-
-#include <linux/bug.h>
-
-struct device;
-
-extern void octeon_pci_dma_init(void);
-extern char *octeon_swiotlb;
-
-#endif /* __ASM_MACH_CAVIUM_OCTEON_DMA_COHERENCE_H */
diff --git a/arch/mips/include/asm/octeon/pci-octeon.h b/arch/mips/include/asm/octeon/pci-octeon.h
index 1884609741a8..b12d9a3fbfb6 100644
--- a/arch/mips/include/asm/octeon/pci-octeon.h
+++ b/arch/mips/include/asm/octeon/pci-octeon.h
@@ -63,4 +63,7 @@ enum octeon_dma_bar_type {
  */
 extern enum octeon_dma_bar_type octeon_dma_bar_type;
 
+void octeon_pci_dma_init(void);
+extern char *octeon_swiotlb;
+
 #endif
diff --git a/arch/mips/pci/pci-octeon.c b/arch/mips/pci/pci-octeon.c
index a20697df3539..5017d5843c5a 100644
--- a/arch/mips/pci/pci-octeon.c
+++ b/arch/mips/pci/pci-octeon.c
@@ -21,8 +21,6 @@
 #include <asm/octeon/cvmx-pci-defs.h>
 #include <asm/octeon/pci-octeon.h>
 
-#include <dma-coherence.h>
-
 #define USE_OCTEON_INTERNAL_ARBITER
 
 /*
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index 87ba86bd8696..9cc5905860ef 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -94,8 +94,6 @@ union cvmx_pcie_address {
 
 static int cvmx_pcie_rc_initialize(int pcie_port);
 
-#include <dma-coherence.h>
-
 /**
  * Return the Core virtual base address for PCIe IO access. IOs are
  * read/written as an offset from this address.
-- 
cgit v1.2.3


From d3bc81befcf2634c64f1b2a95311d54ccfa1e06c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:41 +0200
Subject: MIPS: loongson: untangle dma implementations

Only loongson-3 is DMA coherent and uses swiotlb.  So move the dma
address translations stubs directly to the loongson-3 code, and remove
a few Kconfig indirections.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19539/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                         |  2 +-
 arch/mips/loongson64/Kconfig              |  5 -----
 arch/mips/loongson64/common/Makefile      |  5 -----
 arch/mips/loongson64/common/dma-swiotlb.c | 33 -------------------------------
 arch/mips/loongson64/loongson-3/Makefile  |  2 +-
 arch/mips/loongson64/loongson-3/dma.c     | 25 +++++++++++++++++++++++
 6 files changed, 27 insertions(+), 45 deletions(-)
 delete mode 100644 arch/mips/loongson64/common/dma-swiotlb.c
 create mode 100644 arch/mips/loongson64/loongson-3/dma.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 7c539a39c43e..6248befb3efc 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -454,7 +454,6 @@ config MACH_LOONGSON32
 
 config MACH_LOONGSON64
 	bool "Loongson-2/3 family of machines"
-	select ARCH_HAS_PHYS_TO_DMA
 	select SYS_SUPPORTS_ZBOOT
 	help
 	  This enables the support of Loongson-2/3 family of machines.
@@ -1389,6 +1388,7 @@ choice
 config CPU_LOONGSON3
 	bool "Loongson 3 CPU"
 	depends on SYS_HAS_CPU_LOONGSON3
+	select ARCH_HAS_PHYS_TO_DMA
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index dbd2a9f9f9a9..a785bf8da3f3 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -93,7 +93,6 @@ config LOONGSON_MACH3X
 	select LOONGSON_MC146818
 	select ZONE_DMA32
 	select LEFI_FIRMWARE_INTERFACE
-	select PHYS48_TO_HT40
 	help
 		Generic Loongson 3 family machines utilize the 3A/3B revision
 		of Loongson processor and RS780/SBX00 chipset.
@@ -132,10 +131,6 @@ config LOONGSON_UART_BASE
 	default y
 	depends on EARLY_PRINTK || SERIAL_8250
 
-config PHYS48_TO_HT40
-	bool
-	default y if CPU_LOONGSON3
-
 config LOONGSON_MC146818
 	bool
 	default n
diff --git a/arch/mips/loongson64/common/Makefile b/arch/mips/loongson64/common/Makefile
index 8235ac7eac95..684624f61f5a 100644
--- a/arch/mips/loongson64/common/Makefile
+++ b/arch/mips/loongson64/common/Makefile
@@ -25,8 +25,3 @@ obj-$(CONFIG_CS5536) += cs5536/
 #
 
 obj-$(CONFIG_SUSPEND) += pm.o
-
-#
-# Big Memory (SWIOTLB) Support
-#
-obj-$(CONFIG_SWIOTLB) += dma-swiotlb.o
diff --git a/arch/mips/loongson64/common/dma-swiotlb.c b/arch/mips/loongson64/common/dma-swiotlb.c
deleted file mode 100644
index a4f554bf1232..000000000000
--- a/arch/mips/loongson64/common/dma-swiotlb.c
+++ /dev/null
@@ -1,33 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-direct.h>
-#include <linux/init.h>
-#include <linux/swiotlb.h>
-
-dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
-{
-	long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
-	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
-	 * Loongson-3's 48bit address space and embed it into 40bit */
-	nid = (paddr >> 44) & 0x3;
-	paddr = ((nid << 44) ^ paddr) | (nid << 37);
-#endif
-	return paddr;
-}
-
-phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
-{
-	long nid;
-#ifdef CONFIG_PHYS48_TO_HT40
-	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
-	 * Loongson-3's 48bit address space and embed it into 40bit */
-	nid = (daddr >> 37) & 0x3;
-	daddr = ((nid << 37) ^ daddr) | (nid << 44);
-#endif
-	return daddr;
-}
-
-void __init plat_swiotlb_setup(void)
-{
-	swiotlb_init(1);
-}
diff --git a/arch/mips/loongson64/loongson-3/Makefile b/arch/mips/loongson64/loongson-3/Makefile
index 44bc1482158b..b5a0c2fa5446 100644
--- a/arch/mips/loongson64/loongson-3/Makefile
+++ b/arch/mips/loongson64/loongson-3/Makefile
@@ -1,7 +1,7 @@
 #
 # Makefile for Loongson-3 family machines
 #
-obj-y			+= irq.o cop2-ex.o platform.o acpi_init.o
+obj-y			+= irq.o cop2-ex.o platform.o acpi_init.o dma.o
 
 obj-$(CONFIG_SMP)	+= smp.o
 
diff --git a/arch/mips/loongson64/loongson-3/dma.c b/arch/mips/loongson64/loongson-3/dma.c
new file mode 100644
index 000000000000..5e86635f71db
--- /dev/null
+++ b/arch/mips/loongson64/loongson-3/dma.c
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+#include <linux/init.h>
+#include <linux/swiotlb.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+	 * Loongson-3's 48bit address space and embed it into 40bit */
+	long nid = (paddr >> 44) & 0x3;
+	return ((nid << 44) ^ paddr) | (nid << 37);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t daddr)
+{
+	/* We extract 2bit node id (bit 44~47, only bit 44~45 used now) from
+	 * Loongson-3's 48bit address space and embed it into 40bit */
+	long nid = (daddr >> 37) & 0x3;
+	return ((nid << 37) ^ daddr) | (nid << 44);
+}
+
+void __init plat_swiotlb_setup(void)
+{
+	swiotlb_init(1);
+}
-- 
cgit v1.2.3


From d7e64bf9499b1c260f274d00199c4556196ec5e5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:42 +0200
Subject: MIPS: loongson: remove loongson-3 handling from dma-coherence.h

Loongson3 is dma coherent and uses swiotlb, so it will never used any
of these helpers.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19541/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/mach-loongson64/dma-coherence.h | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
index b8825a7d1279..651dd2eb3ee5 100644
--- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h
+++ b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
@@ -20,29 +20,19 @@ struct device;
 static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
 					  size_t size)
 {
-#ifdef CONFIG_CPU_LOONGSON3
-	return __phys_to_dma(dev, virt_to_phys(addr));
-#else
 	return virt_to_phys(addr) | 0x80000000;
-#endif
 }
 
 static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
 					       struct page *page)
 {
-#ifdef CONFIG_CPU_LOONGSON3
-	return __phys_to_dma(dev, page_to_phys(page));
-#else
 	return page_to_phys(page) | 0x80000000;
-#endif
 }
 
 static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
 	dma_addr_t dma_addr)
 {
-#if defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_64BIT)
-	return __dma_to_phys(dev, dma_addr);
-#elif defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
+#if defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
 	return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff);
 #else
 	return dma_addr & 0x7fffffff;
@@ -69,11 +59,7 @@ static inline int plat_dma_supported(struct device *dev, u64 mask)
 
 static inline int plat_device_is_coherent(struct device *dev)
 {
-#ifdef CONFIG_DMA_NONCOHERENT
 	return 0;
-#else
-	return 1;
-#endif /* CONFIG_DMA_NONCOHERENT */
 }
 
 static inline void plat_post_dma_flush(struct device *dev)
-- 
cgit v1.2.3


From dffbfde7582b03f57aed15055dbf8af433c5b1ae Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:43 +0200
Subject: MIPS: use dma_direct_ops for coherent I/O

Switch the simple cache coherent architectures that don't require any
DMA address translation to dma_direct_ops.

We'll soon use at least parts of the direct DMA ops implementation for
all platforms, so select the symbol globally.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19540/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                   | 15 +--------------
 arch/mips/include/asm/dma-mapping.h |  2 +-
 2 files changed, 2 insertions(+), 15 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 6248befb3efc..c1307b83de3a 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -16,6 +16,7 @@ config MIPS
 	select BUILDTIME_EXTABLE_SORT
 	select CLONE_BACKWARDS
 	select CPU_PM if CPU_IDLE
+	select DMA_DIRECT_OPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_CMOS_UPDATE
@@ -569,7 +570,6 @@ config NEC_MARKEINS
 	bool "NEC EMMA2RH Mark-eins board"
 	select SOC_EMMA2RH
 	select HW_HAS_PCI
-	select MIPS_DMA_DEFAULT
 	help
 	  This enables support for the NEC Electronics Mark-eins boards.
 
@@ -583,14 +583,12 @@ config MACH_VR41XX
 
 config NXP_STB220
 	bool "NXP STB220 board"
-	select MIPS_DMA_DEFAULT
 	select SOC_PNX833X
 	help
 	 Support for NXP Semiconductors STB220 Development Board.
 
 config NXP_STB225
 	bool "NXP 225 board"
-	select MIPS_DMA_DEFAULT
 	select SOC_PNX833X
 	select SOC_PNX8335
 	help
@@ -768,7 +766,6 @@ config SGI_IP32
 config SIBYTE_CRHINE
 	bool "Sibyte BCM91120C-CRhine"
 	select BOOT_ELF32
-	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -778,7 +775,6 @@ config SIBYTE_CRHINE
 config SIBYTE_CARMEL
 	bool "Sibyte BCM91120x-Carmel"
 	select BOOT_ELF32
-	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1120
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -788,7 +784,6 @@ config SIBYTE_CARMEL
 config SIBYTE_CRHONE
 	bool "Sibyte BCM91125C-CRhone"
 	select BOOT_ELF32
-	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1125
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -799,7 +794,6 @@ config SIBYTE_CRHONE
 config SIBYTE_RHONE
 	bool "Sibyte BCM91125E-Rhone"
 	select BOOT_ELF32
-	select MIPS_DMA_DEFAULT
 	select SIBYTE_BCM1125H
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -810,7 +804,6 @@ config SIBYTE_SWARM
 	bool "Sibyte BCM91250A-SWARM"
 	select BOOT_ELF32
 	select HAVE_PATA_PLATFORM
-	select MIPS_DMA_DEFAULT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -823,7 +816,6 @@ config SIBYTE_LITTLESUR
 	bool "Sibyte BCM91250C2-LittleSur"
 	select BOOT_ELF32
 	select HAVE_PATA_PLATFORM
-	select MIPS_DMA_DEFAULT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -834,7 +826,6 @@ config SIBYTE_LITTLESUR
 config SIBYTE_SENTOSA
 	bool "Sibyte BCM91250E-Sentosa"
 	select BOOT_ELF32
-	select MIPS_DMA_DEFAULT
 	select SIBYTE_SB1250
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_SB1
@@ -844,7 +835,6 @@ config SIBYTE_SENTOSA
 config SIBYTE_BIGSUR
 	bool "Sibyte BCM91480B-BigSur"
 	select BOOT_ELF32
-	select MIPS_DMA_DEFAULT
 	select NR_CPUS_DEFAULT_4
 	select SIBYTE_BCM1x80
 	select SWAP_IO_SPACE
@@ -965,7 +955,6 @@ config NLM_XLR_BOARD
 	select SYS_HAS_CPU_XLR
 	select SYS_SUPPORTS_SMP
 	select HW_HAS_PCI
-	select MIPS_DMA_DEFAULT
 	select SWAP_IO_SPACE
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
@@ -992,7 +981,6 @@ config NLM_XLP_BOARD
 	select SYS_HAS_CPU_XLP
 	select SYS_SUPPORTS_SMP
 	select HW_HAS_PCI
-	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select PHYS_ADDR_T_64BIT
@@ -1018,7 +1006,6 @@ config MIPS_PARAVIRT
 	bool "Para-Virtualized guest system"
 	select CEVT_R4K
 	select CSRC_R4K
-	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index eaf3d9054104..7c0d4f0ccaa0 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -20,7 +20,7 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 #elif defined(CONFIG_MIPS_DMA_DEFAULT)
 	return &mips_default_dma_map_ops;
 #else
-	return NULL;
+	return &dma_direct_ops;
 #endif
 }
 
-- 
cgit v1.2.3


From 54aed4dd35269ef15eb1569517f34fb3961d4d34 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:44 +0200
Subject: MIPS: IP27: use dma_direct_ops

IP27 is coherent and has a reasonably direct mapping, just with a little
per-bus offset added into the dma address.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19542/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                               |  2 +-
 arch/mips/include/asm/mach-ip27/dma-coherence.h | 70 -------------------------
 arch/mips/pci/pci-ip27.c                        | 14 +++++
 3 files changed, 15 insertions(+), 71 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-ip27/dma-coherence.h

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c1307b83de3a..b5b68cfaec2b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -683,11 +683,11 @@ config SGI_IP22
 
 config SGI_IP27
 	bool "SGI IP27 (Origin200/2000)"
+	select ARCH_HAS_PHYS_TO_DMA
 	select FW_ARC
 	select FW_ARC64
 	select BOOT_ELF64
 	select DEFAULT_SGI_PARTITION
-	select MIPS_DMA_DEFAULT
 	select SYS_HAS_EARLY_PRINTK
 	select HW_HAS_PCI
 	select NR_CPUS_DEFAULT_64
diff --git a/arch/mips/include/asm/mach-ip27/dma-coherence.h b/arch/mips/include/asm/mach-ip27/dma-coherence.h
deleted file mode 100644
index 04d862020ac9..000000000000
--- a/arch/mips/include/asm/mach-ip27/dma-coherence.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP27_DMA_COHERENCE_H
-#define __ASM_MACH_IP27_DMA_COHERENCE_H
-
-#include <asm/pci/bridge.h>
-
-#define pdev_to_baddr(pdev, addr) \
-	(BRIDGE_CONTROLLER(pdev->bus)->baddr + (addr))
-#define dev_to_baddr(dev, addr) \
-	pdev_to_baddr(to_pci_dev(dev), (addr))
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	dma_addr_t pa = dev_to_baddr(dev, virt_to_phys(addr));
-
-	return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	dma_addr_t pa = dev_to_baddr(dev, page_to_phys(page));
-
-	return pa;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return dma_addr & ~(0xffUL << 56);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 1;		/* IP27 non-coherent mode is unsupported */
-}
-
-#endif /* __ASM_MACH_IP27_DMA_COHERENCE_H */
diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index 0f09eafa5e3a..65b48d41a229 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -11,6 +11,7 @@
 #include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/smp.h>
+#include <linux/dma-direct.h>
 #include <asm/sn/arch.h>
 #include <asm/pci/bridge.h>
 #include <asm/paccess.h>
@@ -182,6 +183,19 @@ int pcibios_plat_dev_init(struct pci_dev *dev)
 	return 0;
 }
 
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct bridge_controller *bc = BRIDGE_CONTROLLER(pdev->bus);
+
+	return bc->baddr + paddr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr & ~(0xffUL << 56);
+}
+
 /*
  * Device might live on a subordinate PCI bus.	XXX Walk up the chain of buses
  * to find the slot number in sense of the bridge device register.
-- 
cgit v1.2.3


From aa4db775959a65ddbb4a5b2c886cc520614abb81 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:45 +0200
Subject: MIPS: move coherentio setup to setup.c

We want to be able to use it even when not building dma-default.c
in the near future.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19543/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/kernel/setup.c   | 24 ++++++++++++++++++++++++
 arch/mips/mm/dma-default.c | 23 -----------------------
 2 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 2c96c0c68116..3d4524309b5c 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -36,6 +36,7 @@
 #include <asm/cdmm.h>
 #include <asm/cpu.h>
 #include <asm/debug.h>
+#include <asm/dma-coherence.h>
 #include <asm/sections.h>
 #include <asm/setup.h>
 #include <asm/smp-ops.h>
@@ -1055,3 +1056,26 @@ static int __init debugfs_mips(void)
 }
 arch_initcall(debugfs_mips);
 #endif
+
+#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
+/* User defined DMA coherency from command line. */
+enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
+EXPORT_SYMBOL_GPL(coherentio);
+int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */
+
+static int __init setcoherentio(char *str)
+{
+	coherentio = IO_COHERENCE_ENABLED;
+	pr_info("Hardware DMA cache coherency (command line)\n");
+	return 0;
+}
+early_param("coherentio", setcoherentio);
+
+static int __init setnocoherentio(char *str)
+{
+	coherentio = IO_COHERENCE_DISABLED;
+	pr_info("Software DMA cache coherency (command line)\n");
+	return 0;
+}
+early_param("nocoherentio", setnocoherentio);
+#endif
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 2db6c2a6f964..10b56e8a2076 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -24,29 +24,6 @@
 
 #include <dma-coherence.h>
 
-#if defined(CONFIG_DMA_MAYBE_COHERENT) && !defined(CONFIG_DMA_PERDEV_COHERENT)
-/* User defined DMA coherency from command line. */
-enum coherent_io_user_state coherentio = IO_COHERENCE_DEFAULT;
-EXPORT_SYMBOL_GPL(coherentio);
-int hw_coherentio = 0;	/* Actual hardware supported DMA coherency setting. */
-
-static int __init setcoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_ENABLED;
-	pr_info("Hardware DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("coherentio", setcoherentio);
-
-static int __init setnocoherentio(char *str)
-{
-	coherentio = IO_COHERENCE_DISABLED;
-	pr_info("Software DMA cache coherency (command line)\n");
-	return 0;
-}
-early_param("nocoherentio", setnocoherentio);
-#endif
-
 static inline struct page *dma_addr_to_page(struct device *dev,
 	dma_addr_t dma_addr)
 {
-- 
cgit v1.2.3


From f8c55dc6e828324fc58c0bb32d72a5a4041d1c3b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:46 +0200
Subject: MIPS: use generic dma noncoherent ops for simple noncoherent
 platforms

Convert everything not overriding dma-coherence.h to the generic
noncoherent ops.  The new dma-noncoherent.c file duplicates a lot of
the code in dma-default.c, but that file will be gone by the end of
this series.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19544/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                   |  24 +----
 arch/mips/include/asm/dma-mapping.h |   2 +
 arch/mips/loongson32/Kconfig        |   2 -
 arch/mips/mm/Makefile               |   1 +
 arch/mips/mm/dma-noncoherent.c      | 208 ++++++++++++++++++++++++++++++++++++
 arch/mips/pic32/Kconfig             |   1 -
 arch/mips/txx9/Kconfig              |   1 -
 arch/mips/vr41xx/Kconfig            |   5 -
 8 files changed, 216 insertions(+), 28 deletions(-)
 create mode 100644 arch/mips/mm/dma-noncoherent.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index b5b68cfaec2b..47592cc7fa54 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -102,7 +102,6 @@ config MIPS_GENERIC
 	select IRQ_MIPS_CPU
 	select LIBFDT
 	select MIPS_CPU_SCACHE
-	select MIPS_DMA_DEFAULT
 	select MIPS_GIC
 	select MIPS_L1_CACHE_SHIFT_7
 	select NO_EXCEPT_FILL
@@ -146,7 +145,6 @@ config MIPS_ALCHEMY
 	select CEVT_R4K
 	select CSRC_R4K
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select DMA_MAYBE_COHERENT	# Au1000,1500,1100 aren't, rest is
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -162,7 +160,6 @@ config AR7
 	select CEVT_R4K
 	select CSRC_R4K
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select NO_EXCEPT_FILL
 	select SWAP_IO_SPACE
 	select SYS_HAS_CPU_MIPS32_R1
@@ -205,7 +202,6 @@ config ATH79
 	select COMMON_CLK
 	select CLKDEV_LOOKUP
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select MIPS_MACHINE
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_HAS_EARLY_PRINTK
@@ -263,7 +259,6 @@ config BCM47XX
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
 	select SYS_HAS_CPU_MIPS32_R1
-	select MIPS_DMA_DEFAULT
 	select NO_EXCEPT_FILL
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -287,7 +282,6 @@ config BCM63XX
 	select SYNC_R4K
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_HAS_EARLY_PRINTK
@@ -310,7 +304,6 @@ config MIPS_COBALT
 	select I8259
 	select IRQ_MIPS_CPU
 	select IRQ_GT641XX
-	select MIPS_DMA_DEFAULT
 	select PCI_GT64XXX_PCI0
 	select PCI
 	select SYS_HAS_CPU_NEVADA
@@ -331,7 +324,6 @@ config MACH_DECSTATION
 	select CPU_R4000_WORKAROUNDS if 64BIT
 	select CPU_R4400_WORKAROUNDS if 64BIT
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select NO_IOPORT_MAP
 	select IRQ_MIPS_CPU
 	select SYS_HAS_CPU_R3000
@@ -391,7 +383,6 @@ config MACH_INGENIC
 	select SYS_SUPPORTS_ZBOOT_UART16550
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select PINCTRL
 	select GPIOLIB
 	select COMMON_CLK
@@ -406,7 +397,6 @@ config LANTIQ
 	select IRQ_MIPS_CPU
 	select CEVT_R4K
 	select CSRC_R4K
-	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_SUPPORTS_BIG_ENDIAN
@@ -434,7 +424,6 @@ config LASAT
 	select SYS_HAS_EARLY_PRINTK
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select PCI_GT64XXX_PCI0
 	select MIPS_NILE4
 	select R5000_CPU_SCACHE
@@ -480,7 +469,6 @@ config MACH_PISTACHIO
 	select LIBFDT
 	select MFD_SYSCON
 	select MIPS_CPU_SCACHE
-	select MIPS_DMA_DEFAULT
 	select MIPS_GIC
 	select PINCTRL
 	select REGULATOR
@@ -513,7 +501,6 @@ config MIPS_MALTA
 	select GENERIC_ISA_DMA
 	select HAVE_PCSPKR_PLATFORM
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select MIPS_GIC
 	select HW_HAS_PCI
 	select I8253
@@ -608,7 +595,6 @@ config PMC_MSP
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_MIPS16
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select SERIAL_8250
 	select SERIAL_8250_CONSOLE
 	select USB_EHCI_BIG_ENDIAN_MMIO
@@ -626,7 +612,6 @@ config RALINK
 	select BOOT_RAW
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select USE_OF
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_HAS_CPU_MIPS32_R2
@@ -653,7 +638,6 @@ config SGI_IP22
 	select I8259
 	select IP22_CPU_SCACHE
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select SGI_HAS_I8042
 	select SGI_HAS_INDYDOG
@@ -714,7 +698,6 @@ config SGI_IP28
 	select DMA_NONCOHERENT
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select HW_HAS_EISA
 	select I8253
 	select I8259
@@ -865,7 +848,6 @@ config SNI_RM
 	select I8253
 	select I8259
 	select ISA
-	select MIPS_DMA_DEFAULT
 	select SWAP_IO_SPACE if CPU_BIG_ENDIAN
 	select SYS_HAS_CPU_R4X00
 	select SYS_HAS_CPU_R5000
@@ -896,7 +878,6 @@ config MIKROTIK_RB532
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -1133,7 +1114,12 @@ config DMA_PERDEV_COHERENT
 
 config DMA_NONCOHERENT
 	bool
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
 	select NEED_DMA_MAP_STATE
+	select DMA_NONCOHERENT_MMAP
+	select DMA_NONCOHERENT_CACHE_SYNC
+	select DMA_NONCOHERENT_OPS if !MIPS_DMA_DEFAULT
 
 config SYS_HAS_EARLY_PRINTK
 	bool
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 7c0d4f0ccaa0..e32a7b439816 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -19,6 +19,8 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return &mips_swiotlb_ops;
 #elif defined(CONFIG_MIPS_DMA_DEFAULT)
 	return &mips_default_dma_map_ops;
+#elif defined(CONFIG_DMA_NONCOHERENT_OPS)
+	return &dma_noncoherent_ops;
 #else
 	return &dma_direct_ops;
 #endif
diff --git a/arch/mips/loongson32/Kconfig b/arch/mips/loongson32/Kconfig
index 7a69a6c0ce22..462b126f45aa 100644
--- a/arch/mips/loongson32/Kconfig
+++ b/arch/mips/loongson32/Kconfig
@@ -10,7 +10,6 @@ config LOONGSON1_LS1B
 	select CSRC_R4K if !MIPS_EXTERNAL_TIMER
 	select SYS_HAS_CPU_LOONGSON1B
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select BOOT_ELF32
 	select IRQ_MIPS_CPU
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -27,7 +26,6 @@ config LOONGSON1_LS1C
 	select CSRC_R4K if !MIPS_EXTERNAL_TIMER
 	select SYS_HAS_CPU_LOONGSON1C
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select BOOT_ELF32
 	select IRQ_MIPS_CPU
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index 038bfed34946..c6146c3805dc 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -18,6 +18,7 @@ obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_MIPS_DMA_DEFAULT)	+= dma-default.o
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-noncoherent.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
 obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
new file mode 100644
index 000000000000..25edf6d6b686
--- /dev/null
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
+ * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
+ * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
+ */
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/dma-contiguous.h>
+#include <linux/highmem.h>
+
+#include <asm/cache.h>
+#include <asm/cpu-type.h>
+#include <asm/dma-coherence.h>
+#include <asm/io.h>
+
+#ifdef CONFIG_DMA_PERDEV_COHERENT
+static inline int dev_is_coherent(struct device *dev)
+{
+	return dev->archdata.dma_coherent;
+}
+#else
+static inline int dev_is_coherent(struct device *dev)
+{
+	switch (coherentio) {
+	default:
+	case IO_COHERENCE_DEFAULT:
+		return hw_coherentio;
+	case IO_COHERENCE_ENABLED:
+		return 1;
+	case IO_COHERENCE_DISABLED:
+		return 0;
+	}
+}
+#endif /* CONFIG_DMA_PERDEV_COHERENT */
+
+/*
+ * The affected CPUs below in 'cpu_needs_post_dma_flush()' can speculatively
+ * fill random cachelines with stale data at any time, requiring an extra
+ * flush post-DMA.
+ *
+ * Warning on the terminology - Linux calls an uncached area coherent;  MIPS
+ * terminology calls memory areas with hardware maintained coherency coherent.
+ *
+ * Note that the R14000 and R16000 should also be checked for in this condition.
+ * However this function is only called on non-I/O-coherent systems and only the
+ * R10000 and R12000 are used in such systems, the SGI IP28 Indigo² rsp.
+ * SGI IP32 aka O2.
+ */
+static inline bool cpu_needs_post_dma_flush(struct device *dev)
+{
+	if (dev_is_coherent(dev))
+		return false;
+
+	switch (boot_cpu_type()) {
+	case CPU_R10000:
+	case CPU_R12000:
+	case CPU_BMIPS5000:
+		return true;
+	default:
+		/*
+		 * Presence of MAARs suggests that the CPU supports
+		 * speculatively prefetching data, and therefore requires
+		 * the post-DMA flush/invalidate.
+		 */
+		return cpu_has_maar;
+	}
+}
+
+void *arch_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+	if (!ret)
+		return NULL;
+
+	if (!dev_is_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
+		dma_cache_wback_inv((unsigned long) ret, size);
+		ret = UNCAC_ADDR(ret);
+	}
+
+	return ret;
+}
+
+void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t dma_addr, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !dev_is_coherent(dev))
+		cpu_addr = (void *)CAC_ADDR((unsigned long)cpu_addr);
+	dma_direct_free(dev, size, cpu_addr, dma_addr, attrs);
+}
+
+int arch_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs)
+{
+	unsigned long user_count = vma_pages(vma);
+	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long addr = (unsigned long)cpu_addr;
+	unsigned long off = vma->vm_pgoff;
+	unsigned long pfn;
+	int ret = -ENXIO;
+
+	if (!dev_is_coherent(dev))
+		addr = CAC_ADDR(addr);
+
+	pfn = page_to_pfn(virt_to_page((void *)addr));
+
+	if (attrs & DMA_ATTR_WRITE_COMBINE)
+		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	else
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+		return ret;
+
+	if (off < count && user_count <= (count - off)) {
+		ret = remap_pfn_range(vma, vma->vm_start,
+				      pfn + off,
+				      user_count << PAGE_SHIFT,
+				      vma->vm_page_prot);
+	}
+
+	return ret;
+}
+
+static inline void dma_sync_virt(void *addr, size_t size,
+		enum dma_data_direction dir)
+{
+	switch (dir) {
+	case DMA_TO_DEVICE:
+		dma_cache_wback((unsigned long)addr, size);
+		break;
+
+	case DMA_FROM_DEVICE:
+		dma_cache_inv((unsigned long)addr, size);
+		break;
+
+	case DMA_BIDIRECTIONAL:
+		dma_cache_wback_inv((unsigned long)addr, size);
+		break;
+
+	default:
+		BUG();
+	}
+}
+
+/*
+ * A single sg entry may refer to multiple physically contiguous pages.  But
+ * we still need to process highmem pages individually.  If highmem is not
+ * configured then the bulk of this loop gets optimized out.
+ */
+static inline void dma_sync_phys(phys_addr_t paddr, size_t size,
+		enum dma_data_direction dir)
+{
+	struct page *page = pfn_to_page(paddr >> PAGE_SHIFT);
+	unsigned long offset = paddr & ~PAGE_MASK;
+	size_t left = size;
+
+	do {
+		size_t len = left;
+
+		if (PageHighMem(page)) {
+			void *addr;
+
+			if (offset + len > PAGE_SIZE) {
+				if (offset >= PAGE_SIZE) {
+					page += offset >> PAGE_SHIFT;
+					offset &= ~PAGE_MASK;
+				}
+				len = PAGE_SIZE - offset;
+			}
+
+			addr = kmap_atomic(page);
+			dma_sync_virt(addr + offset, len, dir);
+			kunmap_atomic(addr);
+		} else
+			dma_sync_virt(page_address(page) + offset, size, dir);
+		offset = 0;
+		page++;
+		left -= len;
+	} while (left);
+}
+
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (!dev_is_coherent(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (cpu_needs_post_dma_flush(dev))
+		dma_sync_phys(paddr, size, dir);
+}
+
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+		enum dma_data_direction direction)
+{
+	BUG_ON(direction == DMA_NONE);
+
+	if (!dev_is_coherent(dev))
+		dma_sync_virt(vaddr, size, direction);
+}
diff --git a/arch/mips/pic32/Kconfig b/arch/mips/pic32/Kconfig
index 7feb7359b05b..e284e89183cc 100644
--- a/arch/mips/pic32/Kconfig
+++ b/arch/mips/pic32/Kconfig
@@ -11,7 +11,6 @@ config PIC32MZDA
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R2
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/txx9/Kconfig b/arch/mips/txx9/Kconfig
index 9dfda3e90348..d2509c93f0ee 100644
--- a/arch/mips/txx9/Kconfig
+++ b/arch/mips/txx9/Kconfig
@@ -16,7 +16,6 @@ config MACH_TX49XX
 config MACH_TXX9
 	bool
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select SWAP_IO_SPACE
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/vr41xx/Kconfig b/arch/mips/vr41xx/Kconfig
index cc69b2f663fa..992c988b83b0 100644
--- a/arch/mips/vr41xx/Kconfig
+++ b/arch/mips/vr41xx/Kconfig
@@ -9,7 +9,6 @@ config CASIO_E55
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select ISA
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -20,7 +19,6 @@ config IBM_WORKPAD
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select ISA
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -31,7 +29,6 @@ config TANBAC_TB022X
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select HW_HAS_PCI
 	select SYS_SUPPORTS_32BIT_KERNEL
@@ -48,7 +45,6 @@ config VICTOR_MPC30X
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select HW_HAS_PCI
 	select PCI_VR41XX
@@ -60,7 +56,6 @@ config ZAO_CAPCELLA
 	select CEVT_R4K
 	select CSRC_R4K
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select IRQ_MIPS_CPU
 	select HW_HAS_PCI
 	select PCI_VR41XX
-- 
cgit v1.2.3


From e905086e6b2fc9d7e2764cf04622743ca86558f1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Jun 2018 09:11:15 +0200
Subject: MIPS: loongson64: use generic dma noncoherent ops

Provide phys_to_dma/dma_to_phys helpers, everything else is generic.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19545/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                                  |  1 +
 .../include/asm/mach-loongson64/dma-coherence.h    | 69 ----------------------
 arch/mips/loongson64/Kconfig                       |  2 -
 arch/mips/loongson64/common/Makefile               |  1 +
 arch/mips/loongson64/common/dma.c                  | 18 ++++++
 5 files changed, 20 insertions(+), 71 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-loongson64/dma-coherence.h
 create mode 100644 arch/mips/loongson64/common/dma.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 47592cc7fa54..aa438f0a0273 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1828,6 +1828,7 @@ config CPU_LOONGSON2
 	select CPU_SUPPORTS_64BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
 	select CPU_SUPPORTS_HUGEPAGES
+	select ARCH_HAS_PHYS_TO_DMA
 
 config CPU_LOONGSON1
 	bool
diff --git a/arch/mips/include/asm/mach-loongson64/dma-coherence.h b/arch/mips/include/asm/mach-loongson64/dma-coherence.h
deleted file mode 100644
index 651dd2eb3ee5..000000000000
--- a/arch/mips/include/asm/mach-loongson64/dma-coherence.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006, 07  Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007 Lemote, Inc. & Institute of Computing Technology
- * Author: Fuxin Zhang, zhangfx@lemote.com
- *
- */
-#ifndef __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-#define __ASM_MACH_LOONGSON64_DMA_COHERENCE_H
-
-#ifdef CONFIG_SWIOTLB
-#include <linux/swiotlb.h>
-#endif
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-					  size_t size)
-{
-	return virt_to_phys(addr) | 0x80000000;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-					       struct page *page)
-{
-	return page_to_phys(page) | 0x80000000;
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-#if defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
-	return (dma_addr > 0x8fffffff) ? dma_addr : (dma_addr & 0x0fffffff);
-#else
-	return dma_addr & 0x7fffffff;
-#endif
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_LOONGSON64_DMA_COHERENCE_H */
diff --git a/arch/mips/loongson64/Kconfig b/arch/mips/loongson64/Kconfig
index a785bf8da3f3..c865b4b9b775 100644
--- a/arch/mips/loongson64/Kconfig
+++ b/arch/mips/loongson64/Kconfig
@@ -13,7 +13,6 @@ config LEMOTE_FULOONG2E
 	select CSRC_R4K
 	select SYS_HAS_CPU_LOONGSON2E
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select BOOT_ELF32
 	select BOARD_SCACHE
 	select HW_HAS_PCI
@@ -45,7 +44,6 @@ config LEMOTE_MACH2F
 	select CS5536
 	select CSRC_R4K if ! MIPS_EXTERNAL_TIMER
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select HAVE_CLK
 	select HW_HAS_PCI
diff --git a/arch/mips/loongson64/common/Makefile b/arch/mips/loongson64/common/Makefile
index 684624f61f5a..57ee03022941 100644
--- a/arch/mips/loongson64/common/Makefile
+++ b/arch/mips/loongson64/common/Makefile
@@ -6,6 +6,7 @@
 obj-y += setup.o init.o cmdline.o env.o time.o reset.o irq.o \
     bonito-irq.o mem.o machtype.o platform.o serial.o
 obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_CPU_LOONGSON2) += dma.o
 
 #
 # Serial port support
diff --git a/arch/mips/loongson64/common/dma.c b/arch/mips/loongson64/common/dma.c
new file mode 100644
index 000000000000..48f04126bde2
--- /dev/null
+++ b/arch/mips/loongson64/common/dma.c
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/dma-direct.h>
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr | 0x80000000;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+#if defined(CONFIG_CPU_LOONGSON2F) && defined(CONFIG_64BIT)
+	if (dma_addr > 0x8fffffff)
+		return dma_addr;
+	return dma_addr & 0x0fffffff;
+#else
+	return dma_addr & 0x7fffffff;
+#endif
+}
-- 
cgit v1.2.3


From 03df8229a822ab2c262bf78b05a3ada686b885b9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:48 +0200
Subject: MIPS: IP32: use generic dma noncoherent ops

Provide phys_to_dma/dma_to_phys helpers, everything else is generic.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19546/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                               |  2 +-
 arch/mips/include/asm/mach-ip32/dma-coherence.h | 92 -------------------------
 arch/mips/sgi-ip32/Makefile                     |  2 +-
 arch/mips/sgi-ip32/ip32-dma.c                   | 37 ++++++++++
 4 files changed, 39 insertions(+), 94 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-ip32/dma-coherence.h
 create mode 100644 arch/mips/sgi-ip32/ip32-dma.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index aa438f0a0273..a30572400c7e 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -726,6 +726,7 @@ config SGI_IP28
 
 config SGI_IP32
 	bool "SGI IP32 (O2)"
+	select ARCH_HAS_PHYS_TO_DMA
 	select FW_ARC
 	select FW_ARC32
 	select BOOT_ELF32
@@ -734,7 +735,6 @@ config SGI_IP32
 	select DMA_NONCOHERENT
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select R5000_CPU_SCACHE
 	select RM7000_CPU_SCACHE
 	select SYS_HAS_CPU_R5000
diff --git a/arch/mips/include/asm/mach-ip32/dma-coherence.h b/arch/mips/include/asm/mach-ip32/dma-coherence.h
deleted file mode 100644
index 7bdf212587a0..000000000000
--- a/arch/mips/include/asm/mach-ip32/dma-coherence.h
+++ /dev/null
@@ -1,92 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_IP32_DMA_COHERENCE_H
-#define __ASM_MACH_IP32_DMA_COHERENCE_H
-
-#include <asm/ip32/crime.h>
-
-struct device;
-
-/*
- * Few notes.
- * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
- * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
- *    native-endian)
- * 3. All other devices see memory as one big chunk at 0x40000000
- * 4. Non-PCI devices will pass NULL as struct device*
- *
- * Thus we translate differently, depending on device.
- */
-
-#define RAM_OFFSET_MASK 0x3fffffffUL
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	dma_addr_t pa = virt_to_phys(addr) & RAM_OFFSET_MASK;
-
-	if (dev == NULL)
-		pa += CRIME_HI_MEM_BASE;
-
-	return pa;
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	dma_addr_t pa;
-
-	pa = page_to_phys(page) & RAM_OFFSET_MASK;
-
-	if (dev == NULL)
-		pa += CRIME_HI_MEM_BASE;
-
-	return pa;
-}
-
-/* This is almost certainly wrong but it's what dma-ip32.c used to use	*/
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	unsigned long addr = dma_addr & RAM_OFFSET_MASK;
-
-	if (dma_addr >= 256*1024*1024)
-		addr += CRIME_HI_MEM_BASE;
-
-	return addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;		/* IP32 is non-coherent */
-}
-
-#endif /* __ASM_MACH_IP32_DMA_COHERENCE_H */
diff --git a/arch/mips/sgi-ip32/Makefile b/arch/mips/sgi-ip32/Makefile
index 60f0227425e7..4745cd94df11 100644
--- a/arch/mips/sgi-ip32/Makefile
+++ b/arch/mips/sgi-ip32/Makefile
@@ -4,4 +4,4 @@
 #
 
 obj-y	+= ip32-berr.o ip32-irq.o ip32-platform.o ip32-setup.o ip32-reset.o \
-	   crime.o ip32-memory.o
+	   crime.o ip32-memory.o ip32-dma.o
diff --git a/arch/mips/sgi-ip32/ip32-dma.c b/arch/mips/sgi-ip32/ip32-dma.c
new file mode 100644
index 000000000000..fa7b17cb5385
--- /dev/null
+++ b/arch/mips/sgi-ip32/ip32-dma.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <linux/dma-direct.h>
+#include <asm/ip32/crime.h>
+
+/*
+ * Few notes.
+ * 1. CPU sees memory as two chunks: 0-256M@0x0, and the rest @0x40000000+256M
+ * 2. PCI sees memory as one big chunk @0x0 (or we could use 0x40000000 for
+ *    native-endian)
+ * 3. All other devices see memory as one big chunk at 0x40000000
+ * 4. Non-PCI devices will pass NULL as struct device*
+ *
+ * Thus we translate differently, depending on device.
+ */
+
+#define RAM_OFFSET_MASK 0x3fffffffUL
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	dma_addr_t dma_addr = paddr & RAM_OFFSET_MASK;
+
+	if (!dev)
+		dma_addr += CRIME_HI_MEM_BASE;
+	return dma_addr;
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	phys_addr_t paddr = dma_addr & RAM_OFFSET_MASK;
+
+	if (dma_addr >= 256*1024*1024)
+		paddr += CRIME_HI_MEM_BASE;
+	return paddr;
+}
-- 
cgit v1.2.3


From d1f2564a5639bb54493eaa313aef612aee47ba7c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:49 +0200
Subject: MIPS: ath25: use generic dma noncoherent ops

Provide phys_to_dma/dma_to_phys helpers only if PCI support is
enabled, everything else is generic.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19547/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                                |  1 -
 arch/mips/ath25/Kconfig                          |  1 +
 arch/mips/include/asm/mach-ath25/dma-coherence.h | 71 ------------------------
 arch/mips/pci/pci-ar2315.c                       | 24 ++++++++
 4 files changed, 25 insertions(+), 72 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-ath25/dma-coherence.h

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a30572400c7e..a9b4ff75836d 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -182,7 +182,6 @@ config ATH25
 	select DMA_NONCOHERENT
 	select IRQ_MIPS_CPU
 	select IRQ_DOMAIN
-	select MIPS_DMA_DEFAULT
 	select SYS_HAS_CPU_MIPS32_R1
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_32BIT_KERNEL
diff --git a/arch/mips/ath25/Kconfig b/arch/mips/ath25/Kconfig
index 7070b4bcd01d..2c1dfd06c366 100644
--- a/arch/mips/ath25/Kconfig
+++ b/arch/mips/ath25/Kconfig
@@ -12,6 +12,7 @@ config SOC_AR2315
 config PCI_AR2315
 	bool "Atheros AR2315 PCI controller support"
 	depends on SOC_AR2315
+	select ARCH_HAS_PHYS_TO_DMA
 	select HW_HAS_PCI
 	select PCI
 	default y
diff --git a/arch/mips/include/asm/mach-ath25/dma-coherence.h b/arch/mips/include/asm/mach-ath25/dma-coherence.h
deleted file mode 100644
index 124755d4f079..000000000000
--- a/arch/mips/include/asm/mach-ath25/dma-coherence.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2007  Felix Fietkau <nbd@openwrt.org>
- *
- */
-#ifndef __ASM_MACH_ATH25_DMA_COHERENCE_H
-#define __ASM_MACH_ATH25_DMA_COHERENCE_H
-
-#include <linux/device.h>
-
-/*
- * We need some arbitrary non-zero value to be programmed to the BAR1 register
- * of PCI host controller to enable DMA. The same value should be used as the
- * offset to calculate the physical address of DMA buffer for PCI devices.
- */
-#define AR2315_PCI_HOST_SDRAM_BASEADDR	0x20000000
-
-static inline dma_addr_t ath25_dev_offset(struct device *dev)
-{
-#ifdef CONFIG_PCI
-	extern struct bus_type pci_bus_type;
-
-	if (dev && dev->bus == &pci_bus_type)
-		return AR2315_PCI_HOST_SDRAM_BASEADDR;
-#endif
-	return 0;
-}
-
-static inline dma_addr_t
-plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return virt_to_phys(addr) + ath25_dev_offset(dev);
-}
-
-static inline dma_addr_t
-plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
-	return page_to_phys(page) + ath25_dev_offset(dev);
-}
-
-static inline unsigned long
-plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
-{
-	return dma_addr - ath25_dev_offset(dev);
-}
-
-static inline void
-plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr, size_t size,
-		   enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-#endif /* __ASM_MACH_ATH25_DMA_COHERENCE_H */
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index b4fa6413c4e5..c539d0d2b0cf 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -149,6 +149,13 @@
 #define AR2315_PCI_HOST_SLOT	3
 #define AR2315_PCI_HOST_DEVID	((0xff18 << 16) | PCI_VENDOR_ID_ATHEROS)
 
+/*
+ * We need some arbitrary non-zero value to be programmed to the BAR1 register
+ * of PCI host controller to enable DMA. The same value should be used as the
+ * offset to calculate the physical address of DMA buffer for PCI devices.
+ */
+#define AR2315_PCI_HOST_SDRAM_BASEADDR	0x20000000
+
 /* ??? access BAR */
 #define AR2315_PCI_HOST_MBAR0		0x10000000
 /* RAM access BAR */
@@ -167,6 +174,23 @@ struct ar2315_pci_ctrl {
 	struct resource io_res;
 };
 
+static inline dma_addr_t ar2315_dev_offset(struct device *dev)
+{
+	if (dev && dev_is_pci(dev))
+		return AR2315_PCI_HOST_SDRAM_BASEADDR;
+	return 0;
+}
+
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
+{
+	return paddr + ar2315_dev_offset(dev);
+}
+
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr - ar2315_dev_offset(dev);
+}
+
 static inline struct ar2315_pci_ctrl *ar2315_pci_bus_to_apc(struct pci_bus *bus)
 {
 	struct pci_controller *hose = bus->sysdata;
-- 
cgit v1.2.3


From c5e2bbb45d28d53d278f25068142a283a0a74f7a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:50 +0200
Subject: MIPS: jazz: split dma mapping operations from dma-default

Jazz actually has a very basic IOMMU, so split the ops into a separate
implementation from the generic default support (which is about to go
away anyway).

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19548/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/dma-mapping.h             |   5 +-
 arch/mips/include/asm/mach-jazz/dma-coherence.h |  60 ----------
 arch/mips/jazz/Kconfig                          |   3 -
 arch/mips/jazz/jazzdma.c                        | 141 +++++++++++++++++++++++-
 4 files changed, 144 insertions(+), 65 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-jazz/dma-coherence.h

diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index e32a7b439816..caf97f739897 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -10,12 +10,15 @@
 #include <dma-coherence.h>
 #endif
 
+extern const struct dma_map_ops jazz_dma_ops;
 extern const struct dma_map_ops mips_default_dma_map_ops;
 extern const struct dma_map_ops mips_swiotlb_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-#ifdef CONFIG_SWIOTLB
+#if defined(CONFIG_MACH_JAZZ)
+	return &jazz_dma_ops;
+#elif defined(CONFIG_SWIOTLB)
 	return &mips_swiotlb_ops;
 #elif defined(CONFIG_MIPS_DMA_DEFAULT)
 	return &mips_default_dma_map_ops;
diff --git a/arch/mips/include/asm/mach-jazz/dma-coherence.h b/arch/mips/include/asm/mach-jazz/dma-coherence.h
deleted file mode 100644
index dc347c25c343..000000000000
--- a/arch/mips/include/asm/mach-jazz/dma-coherence.h
+++ /dev/null
@@ -1,60 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- */
-#ifndef __ASM_MACH_JAZZ_DMA_COHERENCE_H
-#define __ASM_MACH_JAZZ_DMA_COHERENCE_H
-
-#include <asm/jazzdma.h>
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return vdma_alloc(virt_to_phys(addr), size);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	return vdma_alloc(page_to_phys(page), PAGE_SIZE);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return vdma_log2phys(dma_addr);
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-	vdma_free(dma_addr);
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-#endif /* __ASM_MACH_JAZZ_DMA_COHERENCE_H */
diff --git a/arch/mips/jazz/Kconfig b/arch/mips/jazz/Kconfig
index d3ae3e0356f6..06838f80a5d7 100644
--- a/arch/mips/jazz/Kconfig
+++ b/arch/mips/jazz/Kconfig
@@ -3,7 +3,6 @@ config ACER_PICA_61
 	bool "Support for Acer PICA 1 chipset"
 	depends on MACH_JAZZ
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	help
 	  This is a machine with a R4400 133/150 MHz CPU. To compile a Linux
@@ -15,7 +14,6 @@ config MIPS_MAGNUM_4000
 	bool "Support for MIPS Magnum 4000"
 	depends on MACH_JAZZ
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_BIG_ENDIAN
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	help
@@ -28,7 +26,6 @@ config OLIVETTI_M700
 	bool "Support for Olivetti M700-10"
 	depends on MACH_JAZZ
 	select DMA_NONCOHERENT
-	select MIPS_DMA_DEFAULT
 	select SYS_SUPPORTS_LITTLE_ENDIAN
 	help
 	  This is a machine with a R4000 100 MHz CPU. To compile a Linux
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index d626a9a391cc..446fc8c92e1e 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -16,6 +16,8 @@
 #include <linux/bootmem.h>
 #include <linux/spinlock.h>
 #include <linux/gfp.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 #include <asm/mipsregs.h>
 #include <asm/jazz.h>
 #include <asm/io.h>
@@ -86,6 +88,7 @@ static int __init vdma_init(void)
 	printk(KERN_INFO "VDMA: R4030 DMA pagetables initialized.\n");
 	return 0;
 }
+arch_initcall(vdma_init);
 
 /*
  * Allocate DMA pagetables using a simple first-fit algorithm
@@ -556,4 +559,140 @@ int vdma_get_enable(int channel)
 	return enable;
 }
 
-arch_initcall(vdma_init);
+static void *jazz_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+	void *ret;
+
+	ret = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+	if (!ret)
+		return NULL;
+
+	*dma_handle = vdma_alloc(virt_to_phys(ret), size);
+	if (*dma_handle == VDMA_ERROR) {
+		dma_direct_free(dev, size, ret, *dma_handle, attrs);
+		return NULL;
+	}
+
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT)) {
+		dma_cache_wback_inv((unsigned long)ret, size);
+		ret = UNCAC_ADDR(ret);
+	}
+	return ret;
+}
+
+static void jazz_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
+{
+	vdma_free(dma_handle);
+	if (!(attrs & DMA_ATTR_NON_CONSISTENT))
+		vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
+	return dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+}
+
+static dma_addr_t jazz_dma_map_page(struct device *dev, struct page *page,
+		unsigned long offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs)
+{
+	phys_addr_t phys = page_to_phys(page) + offset;
+
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_device(dev, phys, size, dir);
+	return vdma_alloc(phys, size);
+}
+
+static void jazz_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+		arch_sync_dma_for_cpu(dev, vdma_log2phys(dma_addr), size, dir);
+	vdma_free(dma_addr);
+}
+
+static int jazz_dma_map_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nents, i) {
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			arch_sync_dma_for_device(dev, sg_phys(sg), sg->length,
+				dir);
+		sg->dma_address = vdma_alloc(sg_phys(sg), sg->length);
+		if (sg->dma_address == VDMA_ERROR)
+			return 0;
+		sg_dma_len(sg) = sg->length;
+	}
+
+	return nents;
+}
+
+static void jazz_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+		int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+	int i;
+	struct scatterlist *sg;
+
+	for_each_sg(sglist, sg, nents, i) {
+		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+			arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length,
+				dir);
+		vdma_free(sg->dma_address);
+	}
+}
+
+static void jazz_dma_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_device(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_single_for_cpu(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	arch_sync_dma_for_cpu(dev, vdma_log2phys(addr), size, dir);
+}
+
+static void jazz_dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void jazz_dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+	struct scatterlist *sg;
+	int i;
+
+	for_each_sg(sgl, sg, nents, i)
+		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static int jazz_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_addr == VDMA_ERROR;
+}
+
+const struct dma_map_ops jazz_dma_ops = {
+	.alloc			= jazz_dma_alloc,
+	.free			= jazz_dma_free,
+	.mmap			= arch_dma_mmap,
+	.map_page		= jazz_dma_map_page,
+	.unmap_page		= jazz_dma_unmap_page,
+	.map_sg			= jazz_dma_map_sg,
+	.unmap_sg		= jazz_dma_unmap_sg,
+	.sync_single_for_cpu	= jazz_dma_sync_single_for_cpu,
+	.sync_single_for_device	= jazz_dma_sync_single_for_device,
+	.sync_sg_for_cpu	= jazz_dma_sync_sg_for_cpu,
+	.sync_sg_for_device	= jazz_dma_sync_sg_for_device,
+	.dma_supported		= dma_direct_supported,
+	.cache_sync		= arch_dma_cache_sync,
+	.mapping_error		= jazz_dma_mapping_error,
+};
+EXPORT_SYMBOL(jazz_dma_ops);
-- 
cgit v1.2.3


From faef87723ace12e5f685437c1e68cbecb69a7a89 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:51 +0200
Subject: dma-noncoherent: add a arch_sync_dma_for_cpu_all hook

The MIPS bmips platform needs a global flush when transferring ownership
back to the CPU.  Add a hook for that to the dma-noncoherent
implementation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19549/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 include/linux/dma-noncoherent.h | 8 ++++++++
 kernel/dma/noncoherent.c        | 8 ++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/linux/dma-noncoherent.h b/include/linux/dma-noncoherent.h
index 10b2654d549b..a0aa00cc909d 100644
--- a/include/linux/dma-noncoherent.h
+++ b/include/linux/dma-noncoherent.h
@@ -44,4 +44,12 @@ static inline void arch_sync_dma_for_cpu(struct device *dev,
 }
 #endif /* ARCH_HAS_SYNC_DMA_FOR_CPU */
 
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+void arch_sync_dma_for_cpu_all(struct device *dev);
+#else
+static inline void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+}
+#endif /* CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL */
+
 #endif /* _LINUX_DMA_NONCOHERENT_H */
diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c
index 79e9a757387f..031fe235d958 100644
--- a/kernel/dma/noncoherent.c
+++ b/kernel/dma/noncoherent.c
@@ -49,11 +49,13 @@ static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
 	return nents;
 }
 
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
 		dma_addr_t addr, size_t size, enum dma_data_direction dir)
 {
 	arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+	arch_sync_dma_for_cpu_all(dev);
 }
 
 static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
@@ -64,6 +66,7 @@ static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
 
 	for_each_sg(sgl, sg, nents, i)
 		arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+	arch_sync_dma_for_cpu_all(dev);
 }
 
 static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
@@ -89,7 +92,8 @@ const struct dma_map_ops dma_noncoherent_ops = {
 	.sync_sg_for_device	= dma_noncoherent_sync_sg_for_device,
 	.map_page		= dma_noncoherent_map_page,
 	.map_sg			= dma_noncoherent_map_sg,
-#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+#if defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU) || \
+    defined(CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU_ALL)
 	.sync_single_for_cpu	= dma_noncoherent_sync_single_for_cpu,
 	.sync_sg_for_cpu	= dma_noncoherent_sync_sg_for_cpu,
 	.unmap_page		= dma_noncoherent_unmap_page,
-- 
cgit v1.2.3


From d59098a0e9cb3c7767090e935c909b37a30629ab Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:52 +0200
Subject: MIPS: bmips: use generic dma noncoherent ops

Provide phys_to_dma/dma_to_phys helpers, and the special
arch_sync_dma_for_cpu_all hook, everything else is generic

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19550/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                                |  3 +-
 arch/mips/bmips/dma.c                            | 32 ++++++++------
 arch/mips/include/asm/bmips.h                    | 16 -------
 arch/mips/include/asm/mach-bmips/dma-coherence.h | 54 ------------------------
 4 files changed, 21 insertions(+), 84 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-bmips/dma-coherence.h

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a9b4ff75836d..16542e0d18c7 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -215,6 +215,8 @@ config ATH79
 
 config BMIPS_GENERIC
 	bool "Broadcom Generic BMIPS kernel"
+	select ARCH_HAS_SYNC_DMA_FOR_CPU_ALL
+	select ARCH_HAS_PHYS_TO_DMA
 	select BOOT_RAW
 	select NO_EXCEPT_FILL
 	select USE_OF
@@ -227,7 +229,6 @@ config BMIPS_GENERIC
 	select BCM7120_L2_IRQ
 	select BRCMSTB_L2_IRQ
 	select IRQ_MIPS_CPU
-	select MIPS_DMA_DEFAULT
 	select DMA_NONCOHERENT
 	select SYS_SUPPORTS_32BIT_KERNEL
 	select SYS_SUPPORTS_LITTLE_ENDIAN
diff --git a/arch/mips/bmips/dma.c b/arch/mips/bmips/dma.c
index 6dec30842b2f..3d13c77c125f 100644
--- a/arch/mips/bmips/dma.c
+++ b/arch/mips/bmips/dma.c
@@ -17,7 +17,7 @@
 #include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/types.h>
-#include <dma-coherence.h>
+#include <asm/bmips.h>
 
 /*
  * BCM338x has configurable address translation windows which allow the
@@ -40,7 +40,7 @@ static struct bmips_dma_range *bmips_dma_ranges;
 
 #define FLUSH_RAC		0x100
 
-static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa)
+dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t pa)
 {
 	struct bmips_dma_range *r;
 
@@ -52,17 +52,7 @@ static dma_addr_t bmips_phys_to_dma(struct device *dev, phys_addr_t pa)
 	return pa;
 }
 
-dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size)
-{
-	return bmips_phys_to_dma(dev, virt_to_phys(addr));
-}
-
-dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page)
-{
-	return bmips_phys_to_dma(dev, page_to_phys(page));
-}
-
-unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
+phys_addr_t __dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	struct bmips_dma_range *r;
 
@@ -74,6 +64,22 @@ unsigned long plat_dma_addr_to_phys(struct device *dev, dma_addr_t dma_addr)
 	return dma_addr;
 }
 
+void arch_sync_dma_for_cpu_all(struct device *dev)
+{
+	void __iomem *cbr = BMIPS_GET_CBR();
+	u32 cfg;
+
+	if (boot_cpu_type() != CPU_BMIPS3300 &&
+	    boot_cpu_type() != CPU_BMIPS4350 &&
+	    boot_cpu_type() != CPU_BMIPS4380)
+		return;
+
+	/* Flush stale data out of the readahead cache */
+	cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
+	__raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
+	__raw_readl(cbr + BMIPS_RAC_CONFIG);
+}
+
 static int __init bmips_init_dma_ranges(void)
 {
 	struct device_node *np =
diff --git a/arch/mips/include/asm/bmips.h b/arch/mips/include/asm/bmips.h
index b3e2975f83d3..bf6a8afd7ad2 100644
--- a/arch/mips/include/asm/bmips.h
+++ b/arch/mips/include/asm/bmips.h
@@ -123,22 +123,6 @@ static inline void bmips_write_zscm_reg(unsigned int offset, unsigned long data)
 	barrier();
 }
 
-static inline void bmips_post_dma_flush(struct device *dev)
-{
-	void __iomem *cbr = BMIPS_GET_CBR();
-	u32 cfg;
-
-	if (boot_cpu_type() != CPU_BMIPS3300 &&
-	    boot_cpu_type() != CPU_BMIPS4350 &&
-	    boot_cpu_type() != CPU_BMIPS4380)
-		return;
-
-	/* Flush stale data out of the readahead cache */
-	cfg = __raw_readl(cbr + BMIPS_RAC_CONFIG);
-	__raw_writel(cfg | 0x100, cbr + BMIPS_RAC_CONFIG);
-	__raw_readl(cbr + BMIPS_RAC_CONFIG);
-}
-
 #endif /* !defined(__ASSEMBLY__) */
 
 #endif /* _ASM_BMIPS_H */
diff --git a/arch/mips/include/asm/mach-bmips/dma-coherence.h b/arch/mips/include/asm/mach-bmips/dma-coherence.h
deleted file mode 100644
index d29781f02285..000000000000
--- a/arch/mips/include/asm/mach-bmips/dma-coherence.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/*
- * Copyright (C) 2006 Ralf Baechle <ralf@linux-mips.org>
- * Copyright (C) 2009 Broadcom Corporation
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU General Public License for more details.
- */
-
-#ifndef __ASM_MACH_BMIPS_DMA_COHERENCE_H
-#define __ASM_MACH_BMIPS_DMA_COHERENCE_H
-
-#include <asm/bmips.h>
-#include <asm/cpu-type.h>
-#include <asm/cpu.h>
-
-struct device;
-
-extern dma_addr_t plat_map_dma_mem(struct device *dev, void *addr, size_t size);
-extern dma_addr_t plat_map_dma_mem_page(struct device *dev, struct page *page);
-extern unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr);
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-	return 0;
-}
-
-#define plat_post_dma_flush	bmips_post_dma_flush
-
-#endif /* __ASM_MACH_BMIPS_DMA_COHERENCE_H */
-- 
cgit v1.2.3


From 28f512d9cb48ec09288e4cc4475d022d1745b7bf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:53 +0200
Subject: MIPS: remove the old dma-default implementation

Now unused.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19551/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                                  |   5 +-
 arch/mips/include/asm/dma-mapping.h                |   3 -
 arch/mips/include/asm/mach-generic/dma-coherence.h |  73 ----
 arch/mips/mm/Makefile                              |   1 -
 arch/mips/mm/dma-default.c                         | 379 ---------------------
 5 files changed, 1 insertion(+), 460 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-generic/dma-coherence.h
 delete mode 100644 arch/mips/mm/dma-default.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 16542e0d18c7..33375dd234eb 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -78,9 +78,6 @@ config MIPS
 	select SYSCTL_EXCEPTION_TRACE
 	select VIRT_TO_BUS
 
-config MIPS_DMA_DEFAULT
-	bool
-
 menu "Machine selection"
 
 choice
@@ -1119,7 +1116,7 @@ config DMA_NONCOHERENT
 	select NEED_DMA_MAP_STATE
 	select DMA_NONCOHERENT_MMAP
 	select DMA_NONCOHERENT_CACHE_SYNC
-	select DMA_NONCOHERENT_OPS if !MIPS_DMA_DEFAULT
+	select DMA_NONCOHERENT_OPS
 
 config SYS_HAS_EARLY_PRINTK
 	bool
diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index caf97f739897..143250986e17 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -11,7 +11,6 @@
 #endif
 
 extern const struct dma_map_ops jazz_dma_ops;
-extern const struct dma_map_ops mips_default_dma_map_ops;
 extern const struct dma_map_ops mips_swiotlb_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
@@ -20,8 +19,6 @@ static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 	return &jazz_dma_ops;
 #elif defined(CONFIG_SWIOTLB)
 	return &mips_swiotlb_ops;
-#elif defined(CONFIG_MIPS_DMA_DEFAULT)
-	return &mips_default_dma_map_ops;
 #elif defined(CONFIG_DMA_NONCOHERENT_OPS)
 	return &dma_noncoherent_ops;
 #else
diff --git a/arch/mips/include/asm/mach-generic/dma-coherence.h b/arch/mips/include/asm/mach-generic/dma-coherence.h
deleted file mode 100644
index 8ad7a40ca786..000000000000
--- a/arch/mips/include/asm/mach-generic/dma-coherence.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2006  Ralf Baechle <ralf@linux-mips.org>
- *
- */
-#ifndef __ASM_MACH_GENERIC_DMA_COHERENCE_H
-#define __ASM_MACH_GENERIC_DMA_COHERENCE_H
-
-struct device;
-
-static inline dma_addr_t plat_map_dma_mem(struct device *dev, void *addr,
-	size_t size)
-{
-	return virt_to_phys(addr);
-}
-
-static inline dma_addr_t plat_map_dma_mem_page(struct device *dev,
-	struct page *page)
-{
-	return page_to_phys(page);
-}
-
-static inline unsigned long plat_dma_addr_to_phys(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return dma_addr;
-}
-
-static inline void plat_unmap_dma_mem(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction)
-{
-}
-
-static inline int plat_dma_supported(struct device *dev, u64 mask)
-{
-	/*
-	 * we fall back to GFP_DMA when the mask isn't all 1s,
-	 * so we can't guarantee allocations that must be
-	 * within a tighter range than GFP_DMA..
-	 */
-	if (mask < DMA_BIT_MASK(24))
-		return 0;
-
-	return 1;
-}
-
-static inline int plat_device_is_coherent(struct device *dev)
-{
-#ifdef CONFIG_DMA_PERDEV_COHERENT
-	return dev->archdata.dma_coherent;
-#else
-	switch (coherentio) {
-	default:
-	case IO_COHERENCE_DEFAULT:
-		return hw_coherentio;
-	case IO_COHERENCE_ENABLED:
-		return 1;
-	case IO_COHERENCE_DISABLED:
-		return 0;
-	}
-#endif
-}
-
-#ifndef plat_post_dma_flush
-static inline void plat_post_dma_flush(struct device *dev)
-{
-}
-#endif
-
-#endif /* __ASM_MACH_GENERIC_DMA_COHERENCE_H */
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index c6146c3805dc..6922f393af19 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -17,7 +17,6 @@ obj-$(CONFIG_32BIT)		+= ioremap.o pgtable-32.o
 obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_MIPS_DMA_DEFAULT)	+= dma-default.o
 obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-noncoherent.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
deleted file mode 100644
index 10b56e8a2076..000000000000
--- a/arch/mips/mm/dma-default.c
+++ /dev/null
@@ -1,379 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2000  Ani Joshi <ajoshi@unixbox.com>
- * Copyright (C) 2000, 2001, 06	 Ralf Baechle <ralf@linux-mips.org>
- * swiped from i386, and cloned for MIPS by Geert, polished by Ralf.
- */
-
-#include <linux/types.h>
-#include <linux/dma-mapping.h>
-#include <linux/mm.h>
-#include <linux/export.h>
-#include <linux/scatterlist.h>
-#include <linux/string.h>
-#include <linux/gfp.h>
-#include <linux/highmem.h>
-#include <linux/dma-contiguous.h>
-
-#include <asm/cache.h>
-#include <asm/cpu-type.h>
-#include <asm/io.h>
-
-#include <dma-coherence.h>
-
-static inline struct page *dma_addr_to_page(struct device *dev,
-	dma_addr_t dma_addr)
-{
-	return pfn_to_page(
-		plat_dma_addr_to_phys(dev, dma_addr) >> PAGE_SHIFT);
-}
-
-/*
- * The affected CPUs below in 'cpu_needs_post_dma_flush()' can
- * speculatively fill random cachelines with stale data at any time,
- * requiring an extra flush post-DMA.
- *
- * Warning on the terminology - Linux calls an uncached area coherent;
- * MIPS terminology calls memory areas with hardware maintained coherency
- * coherent.
- *
- * Note that the R14000 and R16000 should also be checked for in this
- * condition.  However this function is only called on non-I/O-coherent
- * systems and only the R10000 and R12000 are used in such systems, the
- * SGI IP28 Indigo² rsp. SGI IP32 aka O2.
- */
-static inline bool cpu_needs_post_dma_flush(struct device *dev)
-{
-	if (plat_device_is_coherent(dev))
-		return false;
-
-	switch (boot_cpu_type()) {
-	case CPU_R10000:
-	case CPU_R12000:
-	case CPU_BMIPS5000:
-		return true;
-
-	default:
-		/*
-		 * Presence of MAARs suggests that the CPU supports
-		 * speculatively prefetching data, and therefore requires
-		 * the post-DMA flush/invalidate.
-		 */
-		return cpu_has_maar;
-	}
-}
-
-static gfp_t massage_gfp_flags(const struct device *dev, gfp_t gfp)
-{
-	gfp_t dma_flag;
-
-#ifdef CONFIG_ISA
-	if (dev == NULL)
-		dma_flag = __GFP_DMA;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(32))
-			dma_flag = __GFP_DMA;
-	else if (dev->coherent_dma_mask < DMA_BIT_MASK(64))
-			dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA32) && !defined(CONFIG_ZONE_DMA)
-	     if (dev == NULL || dev->coherent_dma_mask < DMA_BIT_MASK(64))
-		dma_flag = __GFP_DMA32;
-	else
-#endif
-#if defined(CONFIG_ZONE_DMA) && !defined(CONFIG_ZONE_DMA32)
-	     if (dev == NULL ||
-		 dev->coherent_dma_mask < DMA_BIT_MASK(sizeof(phys_addr_t) * 8))
-		dma_flag = __GFP_DMA;
-	else
-#endif
-		dma_flag = 0;
-
-	/* Don't invoke OOM killer */
-	gfp |= __GFP_NORETRY;
-
-	return gfp | dma_flag;
-}
-
-static void *mips_dma_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret;
-	struct page *page = NULL;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-
-	gfp = massage_gfp_flags(dev, gfp);
-
-	if (IS_ENABLED(CONFIG_DMA_CMA) && gfpflags_allow_blocking(gfp))
-		page = dma_alloc_from_contiguous(dev, count, get_order(size),
-						 gfp);
-	if (!page)
-		page = alloc_pages(gfp, get_order(size));
-
-	if (!page)
-		return NULL;
-
-	ret = page_address(page);
-	memset(ret, 0, size);
-	*dma_handle = plat_map_dma_mem(dev, ret, size);
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) &&
-	    !plat_device_is_coherent(dev)) {
-		dma_cache_wback_inv((unsigned long) ret, size);
-		ret = UNCAC_ADDR(ret);
-	}
-
-	return ret;
-}
-
-static void mips_dma_free_coherent(struct device *dev, size_t size, void *vaddr,
-	dma_addr_t dma_handle, unsigned long attrs)
-{
-	unsigned long addr = (unsigned long) vaddr;
-	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	struct page *page = NULL;
-
-	plat_unmap_dma_mem(dev, dma_handle, size, DMA_BIDIRECTIONAL);
-
-	if (!(attrs & DMA_ATTR_NON_CONSISTENT) && !plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	page = virt_to_page((void *) addr);
-
-	if (!dma_release_from_contiguous(dev, page, count))
-		__free_pages(page, get_order(size));
-}
-
-static int mips_dma_mmap(struct device *dev, struct vm_area_struct *vma,
-	void *cpu_addr, dma_addr_t dma_addr, size_t size,
-	unsigned long attrs)
-{
-	unsigned long user_count = vma_pages(vma);
-	unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	unsigned long addr = (unsigned long)cpu_addr;
-	unsigned long off = vma->vm_pgoff;
-	unsigned long pfn;
-	int ret = -ENXIO;
-
-	if (!plat_device_is_coherent(dev))
-		addr = CAC_ADDR(addr);
-
-	pfn = page_to_pfn(virt_to_page((void *)addr));
-
-	if (attrs & DMA_ATTR_WRITE_COMBINE)
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-	else
-		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-
-	if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
-		return ret;
-
-	if (off < count && user_count <= (count - off)) {
-		ret = remap_pfn_range(vma, vma->vm_start,
-				      pfn + off,
-				      user_count << PAGE_SHIFT,
-				      vma->vm_page_prot);
-	}
-
-	return ret;
-}
-
-static inline void __dma_sync_virtual(void *addr, size_t size,
-	enum dma_data_direction direction)
-{
-	switch (direction) {
-	case DMA_TO_DEVICE:
-		dma_cache_wback((unsigned long)addr, size);
-		break;
-
-	case DMA_FROM_DEVICE:
-		dma_cache_inv((unsigned long)addr, size);
-		break;
-
-	case DMA_BIDIRECTIONAL:
-		dma_cache_wback_inv((unsigned long)addr, size);
-		break;
-
-	default:
-		BUG();
-	}
-}
-
-/*
- * A single sg entry may refer to multiple physically contiguous
- * pages. But we still need to process highmem pages individually.
- * If highmem is not configured then the bulk of this loop gets
- * optimized out.
- */
-static inline void __dma_sync(struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction)
-{
-	size_t left = size;
-
-	do {
-		size_t len = left;
-
-		if (PageHighMem(page)) {
-			void *addr;
-
-			if (offset + len > PAGE_SIZE) {
-				if (offset >= PAGE_SIZE) {
-					page += offset >> PAGE_SHIFT;
-					offset &= ~PAGE_MASK;
-				}
-				len = PAGE_SIZE - offset;
-			}
-
-			addr = kmap_atomic(page);
-			__dma_sync_virtual(addr + offset, len, direction);
-			kunmap_atomic(addr);
-		} else
-			__dma_sync_virtual(page_address(page) + offset,
-					   size, direction);
-		offset = 0;
-		page++;
-		left -= len;
-	} while (left);
-}
-
-static void mips_dma_unmap_page(struct device *dev, dma_addr_t dma_addr,
-	size_t size, enum dma_data_direction direction, unsigned long attrs)
-{
-	if (cpu_needs_post_dma_flush(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(dma_addr_to_page(dev, dma_addr),
-			   dma_addr & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-	plat_unmap_dma_mem(dev, dma_addr, size, direction);
-}
-
-static int mips_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-	int nents, enum dma_data_direction direction, unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-#ifdef CONFIG_NEED_SG_DMA_LENGTH
-		sg->dma_length = sg->length;
-#endif
-		sg->dma_address = plat_map_dma_mem_page(dev, sg_page(sg)) +
-				  sg->offset;
-	}
-
-	return nents;
-}
-
-static dma_addr_t mips_dma_map_page(struct device *dev, struct page *page,
-	unsigned long offset, size_t size, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	if (!plat_device_is_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync(page, offset, size, direction);
-
-	return plat_map_dma_mem_page(dev, page) + offset;
-}
-
-static void mips_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-	int nhwentries, enum dma_data_direction direction,
-	unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nhwentries, i) {
-		if (!plat_device_is_coherent(dev) &&
-		    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
-		    direction != DMA_TO_DEVICE)
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		plat_unmap_dma_mem(dev, sg->dma_address, sg->length, direction);
-	}
-}
-
-static void mips_dma_sync_single_for_cpu(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (cpu_needs_post_dma_flush(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_single_for_device(struct device *dev,
-	dma_addr_t dma_handle, size_t size, enum dma_data_direction direction)
-{
-	if (!plat_device_is_coherent(dev))
-		__dma_sync(dma_addr_to_page(dev, dma_handle),
-			   dma_handle & ~PAGE_MASK, size, direction);
-}
-
-static void mips_dma_sync_sg_for_cpu(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (cpu_needs_post_dma_flush(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-	plat_post_dma_flush(dev);
-}
-
-static void mips_dma_sync_sg_for_device(struct device *dev,
-	struct scatterlist *sglist, int nelems,
-	enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	if (!plat_device_is_coherent(dev)) {
-		for_each_sg(sglist, sg, nelems, i) {
-			__dma_sync(sg_page(sg), sg->offset, sg->length,
-				   direction);
-		}
-	}
-}
-
-static int mips_dma_supported(struct device *dev, u64 mask)
-{
-	return plat_dma_supported(dev, mask);
-}
-
-static void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-			 enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	if (!plat_device_is_coherent(dev))
-		__dma_sync_virtual(vaddr, size, direction);
-}
-
-const struct dma_map_ops mips_default_dma_map_ops = {
-	.alloc = mips_dma_alloc_coherent,
-	.free = mips_dma_free_coherent,
-	.mmap = mips_dma_mmap,
-	.map_page = mips_dma_map_page,
-	.unmap_page = mips_dma_unmap_page,
-	.map_sg = mips_dma_map_sg,
-	.unmap_sg = mips_dma_unmap_sg,
-	.sync_single_for_cpu = mips_dma_sync_single_for_cpu,
-	.sync_single_for_device = mips_dma_sync_single_for_device,
-	.sync_sg_for_cpu = mips_dma_sync_sg_for_cpu,
-	.sync_sg_for_device = mips_dma_sync_sg_for_device,
-	.dma_supported = mips_dma_supported,
-	.cache_sync = mips_dma_cache_sync,
-};
-EXPORT_SYMBOL(mips_default_dma_map_ops);
-- 
cgit v1.2.3


From 803ad26eed4a5db07cc52e8dec387689cd007df4 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 15 Jun 2018 13:08:54 +0200
Subject: MIPS: remove unneeded includes from dma-mapping.h

Keep this file as light as possible as it gets pulled into every
driver using dma mapping APIs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Patchwork: https://patchwork.linux-mips.org/patch/19552/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: David Daney <david.daney@cavium.com>
Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Jiaxun Yang <jiaxun.yang@flygoat.com>
Cc: Tom Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: iommu@lists.linux-foundation.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/dma-mapping.h | 8 --------
 arch/mips/mti-malta/malta-setup.c   | 1 +
 2 files changed, 1 insertion(+), 8 deletions(-)

diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 143250986e17..1c6e0c8ef483 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -2,14 +2,6 @@
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
 
-#include <linux/scatterlist.h>
-#include <asm/dma-coherence.h>
-#include <asm/cache.h>
-
-#ifndef CONFIG_SGI_IP27 /* Kludge to fix 2.6.39 build for IP27 */
-#include <dma-coherence.h>
-#endif
-
 extern const struct dma_map_ops jazz_dma_ops;
 extern const struct dma_map_ops mips_swiotlb_ops;
 
diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index 4d5cdfeee3db..7cb7d5a42087 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -26,6 +26,7 @@
 #include <linux/screen_info.h>
 #include <linux/time.h>
 
+#include <asm/dma-coherence.h>
 #include <asm/fw/fw.h>
 #include <asm/mach-malta/malta-dtshim.h>
 #include <asm/mips-cps.h>
-- 
cgit v1.2.3


From 7896de7bd727c9269b7571cfa8dcbc9b99dfb13c Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Sat, 16 Jun 2018 09:26:32 +0200
Subject: MIPS: Octeon: assign bool true/false not 1/0

Booleans should be assigned true/false not 1/0 as comparison is not needed

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Patchwork: https://patchwork.linux-mips.org/patch/19559/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: David Daney <david.daney@cavium.com>
Cc: "Steven J. Hill" <Steven.Hill@cavium.com>
Cc: Joe Perches <joe@perches.com>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/cavium-octeon/octeon-irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index b3aec101a65d..8272d8c648ca 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -814,7 +814,7 @@ static int octeon_irq_ciu_set_affinity(struct irq_data *data,
 			pen = &per_cpu(octeon_irq_ciu1_en_mirror, cpu);
 
 		if (cpumask_test_cpu(cpu, dest) && enable_one) {
-			enable_one = 0;
+			enable_one = false;
 			__set_bit(cd->bit, pen);
 		} else {
 			__clear_bit(cd->bit, pen);
-- 
cgit v1.2.3


From 902b923da619b79e311fd456f78c24619d03131b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Mon, 16 Apr 2018 23:47:41 +0900
Subject: Revert "MIPS: boot: Define __ASSEMBLY__ for its.S build"

This reverts commit 0f9da844d87796ac31b04e81ee95e155e9043132.

It is true that commit 0f9da844d877 ("MIPS: boot: Define __ASSEMBLY__
for its.S build") fixed the build error, but it should not have
defined __ASSEMBLY__ just for textual substitution in arbitrary data.
The file is image tree source in this case, but the purpose of using
CPP is to replace some macros.

I merged a better solution, commit a95b37e20db9 ("kbuild: get
<linux/compiler_types.h> out of <linux/kconfig.h>").  The original
fix-up is no longer needed.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Patchwork: https://patchwork.linux-mips.org/patch/19096/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/Makefile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index c22da16d67b8..1bd5c4f00d19 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -126,7 +126,6 @@ $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS
 
 quiet_cmd_cpp_its_S = ITS     $@
       cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \
-			-D__ASSEMBLY__ \
 		        -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
 			-DVMLINUX_BINARY="\"$(3)\"" \
 			-DVMLINUX_COMPRESSION="\"$(2)\"" \
-- 
cgit v1.2.3


From 321f95b643573d689ac1fb5b68b90044ba47d1a4 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Mon, 16 Apr 2018 23:47:42 +0900
Subject: MIPS: boot: do not include $(cpp_flags) for preprocessing ITS

$(CPP) is used here to perform macro replacement in ITS.  Do not
pass $(cpp_flags) because it pulls in more options for dependency
file generation etc. but none of which is necessary here.  ITS files
do not include any header file, so $(call if_change,...) is enough.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Patchwork: https://patchwork.linux-mips.org/patch/19093/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/Makefile | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 1bd5c4f00d19..981bcf81c648 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -125,7 +125,7 @@ $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS
 	$(call if_changed,its_cat)
 
 quiet_cmd_cpp_its_S = ITS     $@
-      cmd_cpp_its_S = $(CPP) $(cpp_flags) -P -C -o $@ $< \
+      cmd_cpp_its_S = $(CPP) -P -C -o $@ $< \
 		        -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
 			-DVMLINUX_BINARY="\"$(3)\"" \
 			-DVMLINUX_COMPRESSION="\"$(2)\"" \
@@ -135,19 +135,19 @@ quiet_cmd_cpp_its_S = ITS     $@
 			-DADDR_CELLS=$(itb_addr_cells)
 
 $(obj)/vmlinux.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,none,vmlinux.bin)
+	$(call if_changed,cpp_its_S,none,vmlinux.bin)
 
 $(obj)/vmlinux.gz.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,gzip,vmlinux.bin.gz)
+	$(call if_changed,cpp_its_S,gzip,vmlinux.bin.gz)
 
 $(obj)/vmlinux.bz2.its: $(obj)/vmlinux.its.S $(VMLINUX)  FORCE
-	$(call if_changed_dep,cpp_its_S,bzip2,vmlinux.bin.bz2)
+	$(call if_changed,cpp_its_S,bzip2,vmlinux.bin.bz2)
 
 $(obj)/vmlinux.lzma.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,lzma,vmlinux.bin.lzma)
+	$(call if_changed,cpp_its_S,lzma,vmlinux.bin.lzma)
 
 $(obj)/vmlinux.lzo.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
-	$(call if_changed_dep,cpp_its_S,lzo,vmlinux.bin.lzo)
+	$(call if_changed,cpp_its_S,lzo,vmlinux.bin.lzo)
 
 quiet_cmd_itb-image = ITB     $@
       cmd_itb-image = \
-- 
cgit v1.2.3


From 67e09db507db3e1642ddce512a4313d20addd6e5 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Mon, 16 Apr 2018 23:47:43 +0900
Subject: MIPS: boot: fix build rule of vmlinux.its.S

As Documentation/kbuild/makefile.txt says, it is a typical mistake
to forget the FORCE prerequisite for the rule invoked by if_changed.

Add the FORCE to the prerequisite, but it must be filtered-out from
the files passed to the 'cat' command.  Because this rule generates
.vmlinux.its.S.cmd, vmlinux.its.S must be specified as targets so
that the .cmd file is included.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Patchwork: https://patchwork.linux-mips.org/patch/19097/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/Makefile | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 981bcf81c648..6c7054efd839 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -118,10 +118,12 @@ ifeq ($(ADDR_BITS),64)
 	itb_addr_cells = 2
 endif
 
+targets += vmlinux.its.S
+
 quiet_cmd_its_cat = CAT     $@
-      cmd_its_cat = cat $^ >$@
+      cmd_its_cat = cat $(filter-out $(PHONY), $^) >$@
 
-$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS))
+$(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS)) FORCE
 	$(call if_changed,its_cat)
 
 quiet_cmd_cpp_its_S = ITS     $@
-- 
cgit v1.2.3


From 92b34a9763480b12745a2fc93ff14972426fe8df Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Mon, 16 Apr 2018 23:47:45 +0900
Subject: MIPS: boot: add missing targets for vmlinux.*.its

The build rule of vmlinux.*.its is invoked by $(call if_changed,...)
but it always rebuilds the target needlessly due to missing targets.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Patchwork: https://patchwork.linux-mips.org/patch/19092/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/Makefile | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index 6c7054efd839..f09897f6e65c 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -126,6 +126,12 @@ quiet_cmd_its_cat = CAT     $@
 $(obj)/vmlinux.its.S: $(addprefix $(srctree)/arch/mips/$(PLATFORM)/,$(ITS_INPUTS)) FORCE
 	$(call if_changed,its_cat)
 
+targets += vmlinux.its
+targets += vmlinux.gz.its
+targets += vmlinux.bz2.its
+targets += vmlinux.lzmo.its
+targets += vmlinux.lzo.its
+
 quiet_cmd_cpp_its_S = ITS     $@
       cmd_cpp_its_S = $(CPP) -P -C -o $@ $< \
 		        -DKERNEL_NAME="\"Linux $(KERNELRELEASE)\"" \
-- 
cgit v1.2.3


From be462bd9700aec12029d43d48e6ff2207cb68fb7 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Mon, 16 Apr 2018 23:47:46 +0900
Subject: MIPS: boot: merge build rules of vmlinux.*.itb by using pattern rule

Merge the build rule of vmlinux.{gz,bz2,lzma,lzo}.itb, and also move
'targets' close to the related code.

[paul.burton@mips.com:
  - Remove leading tabs from assignments to itb_addr_cells, since after
    this patch moves the additions to the 'targets' variable the
    assignments to itb_addr_cells wound up being treated as part of the
    uImage rule above them, causing the .its to incorrectly be generated
    with empty ADDR_CELLS.]

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Patchwork: https://patchwork.linux-mips.org/patch/19095/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Kees Cook <keescook@chromium.org>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/Makefile | 27 +++++++++------------------
 1 file changed, 9 insertions(+), 18 deletions(-)

diff --git a/arch/mips/boot/Makefile b/arch/mips/boot/Makefile
index f09897f6e65c..35704c28a28b 100644
--- a/arch/mips/boot/Makefile
+++ b/arch/mips/boot/Makefile
@@ -105,17 +105,11 @@ $(obj)/uImage: $(obj)/uImage.$(suffix-y)
 # Flattened Image Tree (.itb) images
 #
 
-targets += vmlinux.itb
-targets += vmlinux.gz.itb
-targets += vmlinux.bz2.itb
-targets += vmlinux.lzma.itb
-targets += vmlinux.lzo.itb
-
 ifeq ($(ADDR_BITS),32)
-	itb_addr_cells = 1
+itb_addr_cells = 1
 endif
 ifeq ($(ADDR_BITS),64)
-	itb_addr_cells = 2
+itb_addr_cells = 2
 endif
 
 targets += vmlinux.its.S
@@ -157,6 +151,12 @@ $(obj)/vmlinux.lzma.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
 $(obj)/vmlinux.lzo.its: $(obj)/vmlinux.its.S $(VMLINUX) FORCE
 	$(call if_changed,cpp_its_S,lzo,vmlinux.bin.lzo)
 
+targets += vmlinux.itb
+targets += vmlinux.gz.itb
+targets += vmlinux.bz2.itb
+targets += vmlinux.lzma.itb
+targets += vmlinux.lzo.itb
+
 quiet_cmd_itb-image = ITB     $@
       cmd_itb-image = \
 		env PATH="$(objtree)/scripts/dtc:$(PATH)" \
@@ -169,14 +169,5 @@ quiet_cmd_itb-image = ITB     $@
 $(obj)/vmlinux.itb: $(obj)/vmlinux.its $(obj)/vmlinux.bin FORCE
 	$(call if_changed,itb-image,$<)
 
-$(obj)/vmlinux.gz.itb: $(obj)/vmlinux.gz.its $(obj)/vmlinux.bin.gz FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.bz2.itb: $(obj)/vmlinux.bz2.its $(obj)/vmlinux.bin.bz2 FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzma.itb: $(obj)/vmlinux.lzma.its $(obj)/vmlinux.bin.lzma FORCE
-	$(call if_changed,itb-image,$<)
-
-$(obj)/vmlinux.lzo.itb: $(obj)/vmlinux.lzo.its $(obj)/vmlinux.bin.lzo FORCE
+$(obj)/vmlinux.%.itb: $(obj)/vmlinux.%.its $(obj)/vmlinux.bin.% FORCE
 	$(call if_changed,itb-image,$<)
-- 
cgit v1.2.3


From c8bf38055efaf764fd8c313695759c64dc735842 Mon Sep 17 00:00:00 2001
From: Heiher <r@hev.cc>
Date: Mon, 11 Jun 2018 17:01:10 +0800
Subject: MIPS: Fix ejtag handler on SMP

On SMP systems, the shared ejtag debug buffer may be overwritten by
other cores, because every cores can generate ejtag exception at
same time.

Unfortunately, in that context, it's difficult to relax more registers
to access per cpu buffers. so use ll/sc to serialize the access.

[paul.burton@mips.com:
  This could in theory be backported at least as far back as the
  beginning of the git era, however in general it's exceedingly rare
  that anyone would hit this without further changes, so it doesn't seem
  worthwhile marking for backport.]

Signed-off-by: Heiher <r@hev.cc>
Patchwork: https://patchwork.linux-mips.org/patch/19507/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: jhogan@kernel.org
Cc: ralf@linux-mips.org
---
 arch/mips/kernel/genex.S | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/arch/mips/kernel/genex.S b/arch/mips/kernel/genex.S
index 37b9383eacd3..6c257b52f57f 100644
--- a/arch/mips/kernel/genex.S
+++ b/arch/mips/kernel/genex.S
@@ -354,16 +354,56 @@ NESTED(ejtag_debug_handler, PT_SIZE, sp)
 	sll	k0, k0, 30	# Check for SDBBP.
 	bgez	k0, ejtag_return
 
+#ifdef CONFIG_SMP
+1:	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	ll	k0, 0(k0)
+	bnez	k0, 1b
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sc	k0, 0(k0)
+	beqz	k0, 1b
+# ifdef CONFIG_WEAK_REORDERING_BEYOND_LLSC
+	sync
+# endif
+
+	PTR_LA	k0, ejtag_debug_buffer
+	LONG_S	k1, 0(k0)
+
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+
+	PTR_LA	k1, ejtag_debug_buffer
+	LONG_L	k1, 0(k1)
+	LONG_S	k1, 0(k0)
+
+	PTR_LA	k0, ejtag_debug_buffer_spinlock
+	sw	zero, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_S	k1, 0(k0)
+#endif
+
 	SAVE_ALL
 	move	a0, sp
 	jal	ejtag_exception_handler
 	RESTORE_ALL
+
+#ifdef CONFIG_SMP
+	ASM_CPUID_MFC0 k1, ASM_SMP_CPUID_REG
+	PTR_SRL	k1, SMP_CPUID_PTRSHIFT
+	PTR_SLL	k1, LONGLOG
+	PTR_LA	k0, ejtag_debug_buffer_per_cpu
+	PTR_ADDU k0, k1
+	LONG_L	k1, 0(k0)
+#else
 	PTR_LA	k0, ejtag_debug_buffer
 	LONG_L	k1, 0(k0)
+#endif
 
 ejtag_return:
+	back_to_back_c0_hazard
 	MFC0	k0, CP0_DESAVE
 	.set	mips32
 	deret
@@ -377,6 +417,12 @@ ejtag_return:
 	.data
 EXPORT(ejtag_debug_buffer)
 	.fill	LONGSIZE
+#ifdef CONFIG_SMP
+EXPORT(ejtag_debug_buffer_spinlock)
+	.fill	LONGSIZE
+EXPORT(ejtag_debug_buffer_per_cpu)
+	.fill	LONGSIZE * NR_CPUS
+#endif
 	.previous
 
 	__INIT
-- 
cgit v1.2.3


From f072f9ce9bd3602bd3b14e15513ee80d437cf4cf Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 19 Jun 2018 15:47:06 -0600
Subject: MIPS: octeon: use of_platform_populate to probe devices

of_platform_bus_probe is deprecated in favor of of_platform_populate.
of_platform_populate is stricter requiring compatible properties for
matching rather than name or type. Octeon uses compatible strings for
matching, so convert it to of_platform_populate.

Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Signed-off-by: Rob Herring <robh@kernel.org>
Patchwork: https://patchwork.linux-mips.org/patch/19588/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/cavium-octeon/octeon-platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index 8505db478904..2940e9cc3a04 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -1067,6 +1067,6 @@ end_led:
 
 static int __init octeon_publish_devices(void)
 {
-	return of_platform_bus_probe(NULL, octeon_ids, NULL);
+	return of_platform_populate(NULL, octeon_ids, NULL, NULL);
 }
 arch_initcall(octeon_publish_devices);
-- 
cgit v1.2.3


From 40c911ed8432130385ecd049922d7c994a83883d Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 19 Jun 2018 15:47:07 -0600
Subject: MIPS: netlogic: remove unnecessary of_platform_bus_probe call

The DT core code will probe "simple-bus" by default, so remove
the Netlogic specific call. The probing of simple-bus happens at
arch_initcall_sync, so the call being removed here is already a nop.

Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Signed-off-by: Rob Herring <robh@kernel.org>
Patchwork: https://patchwork.linux-mips.org/patch/19589/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/netlogic/xlp/dt.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c
index 856a6e6d296e..b5ba83f4c646 100644
--- a/arch/mips/netlogic/xlp/dt.c
+++ b/arch/mips/netlogic/xlp/dt.c
@@ -93,17 +93,3 @@ void __init device_tree_init(void)
 {
 	unflatten_and_copy_device_tree();
 }
-
-static struct of_device_id __initdata xlp_ids[] = {
-	{ .compatible = "simple-bus", },
-	{},
-};
-
-int __init xlp8xx_ds_publish_devices(void)
-{
-	if (!of_have_populated_dt())
-		return 0;
-	return of_platform_bus_probe(NULL, xlp_ids, NULL);
-}
-
-device_initcall(xlp8xx_ds_publish_devices);
-- 
cgit v1.2.3


From 0279455f166dd79eb6bb1b45982401480db778db Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 19 Jun 2018 15:47:08 -0600
Subject: MIPS: bmips: remove unnecessary call to register "simple-bus"

The DT core will register "simple-bus" by default, so it is not necessary
for arch specific code to do so unless there are custom match entries,
auxdata or parent device. Neither of those apply here, so remove the call.

Cc: Kevin Cernekee <cernekee@gmail.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Signed-off-by: Rob Herring <robh@kernel.org>
Patchwork: https://patchwork.linux-mips.org/patch/19590/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/bmips/setup.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c
index 3b6f687f177c..231fc5ce375e 100644
--- a/arch/mips/bmips/setup.c
+++ b/arch/mips/bmips/setup.c
@@ -202,13 +202,6 @@ void __init device_tree_init(void)
 	of_node_put(np);
 }
 
-int __init plat_of_setup(void)
-{
-	return __dt_register_buses("simple-bus", NULL);
-}
-
-arch_initcall(plat_of_setup);
-
 static int __init plat_dev_init(void)
 {
 	of_clk_init(NULL);
-- 
cgit v1.2.3


From 6a7ec6c5ca0c8264bd505be122ca2d4ede60de92 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 19 Jun 2018 15:47:09 -0600
Subject: MIPS: generic: remove unnecessary of_platform_populate call

The DT core will call of_platform_populate, so it is not necessary for
arch specific code to call it unless there are custom match entries,
auxdata or parent device. Neither of those apply here, so remove the call.

Cc: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Signed-off-by: Rob Herring <robh@kernel.org>
Patchwork: https://patchwork.linux-mips.org/patch/19591/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/generic/init.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
index 5ba6fcc26fa7..07ec08462d70 100644
--- a/arch/mips/generic/init.c
+++ b/arch/mips/generic/init.c
@@ -14,7 +14,6 @@
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/of_fdt.h>
-#include <linux/of_platform.h>
 
 #include <asm/bootinfo.h>
 #include <asm/fw/fw.h>
@@ -208,18 +207,6 @@ void __init arch_init_irq(void)
 	irqchip_init();
 }
 
-static int __init publish_devices(void)
-{
-	if (!of_have_populated_dt())
-		panic("Device-tree not present");
-
-	if (of_platform_populate(NULL, of_default_bus_match_table, NULL, NULL))
-		panic("Failed to populate DT");
-
-	return 0;
-}
-arch_initcall(publish_devices);
-
 void __init prom_free_prom_memory(void)
 {
 }
-- 
cgit v1.2.3


From 9667bb039bf6b5168d502c888fa3ea64b49d2641 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Tue, 19 Jun 2018 15:47:10 -0600
Subject: MIPS: lantiq: remove unnecessary of_platform_default_populate call

The DT core will call of_platform_default_populate, so it is not necessary
for arch specific code to call it unless there are custom match entries,
auxdata or parent device. Neither of those apply here, so remove the call.

Cc: John Crispin <john@phrozen.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Signed-off-by: Rob Herring <robh@kernel.org>
Patchwork: https://patchwork.linux-mips.org/patch/19592/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/lantiq/prom.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c
index 9ff7ccde9de0..d984bd5c2ec5 100644
--- a/arch/mips/lantiq/prom.c
+++ b/arch/mips/lantiq/prom.c
@@ -9,7 +9,6 @@
 #include <linux/export.h>
 #include <linux/clk.h>
 #include <linux/bootmem.h>
-#include <linux/of_platform.h>
 #include <linux/of_fdt.h>
 
 #include <asm/bootinfo.h>
@@ -114,10 +113,3 @@ void __init prom_init(void)
 		panic("failed to register_vsmp_smp_ops()");
 #endif
 }
-
-int __init plat_of_setup(void)
-{
-	return of_platform_default_populate(NULL, NULL, NULL);
-}
-
-arch_initcall(plat_of_setup);
-- 
cgit v1.2.3


From 8c8d953c28000045e5e823f3398319f04d49a7f1 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Tue, 19 Dec 2017 15:11:08 -0800
Subject: MIPS: Schedule on CPUs we need to lose FPU for a mode switch

Commit 6b8322576e9d ("MIPS: Force CPUs to lose FP context during mode
switches") ensures that we react to PR_SET_FP_MODE prctl syscalls
quickly by broadcasting an IPI in order to cause CPUs to lose FPU access
when necessary. Whilst it achieves that, unfortunately it causes all
sorts of strange race conditions because:

 1) The IPI may arrive at a point where the FPU is in the process of
    being enabled, but that process is not yet complete leading to a
    state we aren't prepared to handle. For example:

    [  370.215903] do_cpu invoked from kernel context![#1]:
    [  370.221064] CPU: 0 PID: 963 Comm: fp-prctl Not tainted 4.9.0-rc5-00323-g210db32-dirty #226
    [  370.229420] task: a8000000fd672e00 task.stack: a8000000fd630000
    [  370.235399] $ 0   : 0000000000000000 0000000000000001 0000000000000001 a8000000fd630000
    [  370.243882] $ 4   : a8000000fd672e00 0000000000000000 0000000000000453 0000000000000000
    [  370.252317] $ 8   : 0000000000000000 a8000000fd637c28 1000000000000000 0000000000000010
    [  370.260753] $12   : 00000000140084e0 ffffffff80109c00 0000000000000000 0000000000000002
    [  370.269179] $16   : ffffffff8092f080 a8000000fd672e00 ffffffff80107fe8 a8000000fd485000
    [  370.277612] $20   : ffffffff8084d328 ffffffff80940000 0000000000000009 ffffffff80930000
    [  370.286038] $24   : 0000000000000000 900000001612048c
    [  370.294476] $28   : a8000000fd630000 a8000000fd637ac0 ffffffff80937300 ffffffff8010807c
    [  370.302909] Hi    : 0000000000000000
    [  370.306595] Lo    : 0000000000000200
    [  370.310376] epc   : ffffffff80115d38 _save_fp+0x10/0xa0
    [  370.315784] ra    : ffffffff8010807c prepare_for_fp_mode_switch+0x94/0x1b0
    [  370.322707] Status: 140084e2 KX SX UX KERNEL EXL
    [  370.327980] Cause : 1080002c (ExcCode 0b)
    [  370.332091] PrId  : 0001a428 (MIPS P6600)
    [  370.336179] Modules linked in:
    [  370.339486] Process fp-prctl (pid: 963, threadinfo=a8000000fd630000, task=a8000000fd672e00, tls=00000000756e67d0)
    [  370.349724] Stack : 0000000000000000 a8000000fd557dc0 0000000000000000 ffffffff801ca8e0
    [  370.358161]         0000000000000000 a8000000fd637b9c 0000000000000009 ffffffff80923780
    [  370.366575]         ffffffff80850000 ffffffff8011610c 00000000000000b8 ffffffff801a5084
    [  370.374989]         ffffffff8084a370 ffffffff8084a388 ffffffff80923780 ffffffff80923828
    [  370.383395]         0000000000010000 ffffffff809237a8 0000000000020000 ffffffff80a40000
    [  370.391817]         000000000000007c 00000000004a0000 00000000756dedd0 ffffffff801a5188
    [  370.400230]         a800000002014900 0000000000000001 ffffffff80923780 0000000080923828
    [  370.408644]         ffffffff80923780 ffffffff80923780 ffffffff80923828 ffffffff801a521c
    [  370.417066]         ffffffff80923780 ffffffff80923828 0000000000010000 ffffffff801a8f84
    [  370.425472]         ffffffff80a40000 a8000000fd637c20 ffffffff80a39240 0000000000000001
    [  370.433885]         ...
    [  370.436562] Call Trace:
    [  370.439222] [<ffffffff80115d38>] _save_fp+0x10/0xa0
    [  370.444305] [<ffffffff8010807c>] prepare_for_fp_mode_switch+0x94/0x1b0
    [  370.451035] [<ffffffff801ca8e0>] flush_smp_call_function_queue+0xf8/0x230
    [  370.457991] [<ffffffff8011610c>] ipi_call_interrupt+0xc/0x20
    [  370.463814] [<ffffffff801a5084>] __handle_irq_event_percpu+0xc4/0x1a8
    [  370.470404] [<ffffffff801a5188>] handle_irq_event_percpu+0x20/0x68
    [  370.476734] [<ffffffff801a521c>] handle_irq_event+0x4c/0x88
    [  370.482486] [<ffffffff801a8f84>] handle_edge_irq+0x12c/0x210
    [  370.488316] [<ffffffff801a47a0>] generic_handle_irq+0x38/0x48
    [  370.494280] [<ffffffff804a2dbc>] gic_handle_shared_int+0x194/0x268
    [  370.500616] [<ffffffff801a47a0>] generic_handle_irq+0x38/0x48
    [  370.506529] [<ffffffff80107e60>] do_IRQ+0x18/0x28
    [  370.511445] [<ffffffff804a1524>] plat_irq_dispatch+0xc4/0x140
    [  370.517339] [<ffffffff80106230>] ret_from_irq+0x0/0x4
    [  370.522583] [<ffffffff8010fad4>] do_ri+0x4fc/0x7e8
    [  370.527546] [<ffffffff80106220>] ret_from_exception+0x0/0x10

 2) The IPI may arrive during kernel use of the FPU, since we generally
    only disable preemption around use of the FPU & leave interrupts
    enabled. This can lead to us unexpectedly losing access to the FPU
    in places where it previously had not been possible. For example:

    do_cpu invoked from kernel context![#2]:
    CPU: 2 PID: 7338 Comm: fp-prctl Tainted: G      D         4.7.0-00424-g49b0c82
    #2
    task: 838e4000 ti: 88d38000 task.ti: 88d38000
    $ 0   : 00000000 00000001 ffffffff 88d3fef8
    $ 4   : 838e4000 88d38004 00000000 00000001
    $ 8   : 3400fc01 801f8020 808e9100 24000000
    $12   : dbffffff 807b69d8 807b0000 00000000
    $16   : 00000000 80786150 00400fc4 809c0398
    $20   : 809c0338 0040273c 88d3ff28 808e9d30
    $24   : 808e9d30 00400fb4
    $28   : 88d38000 88d3fe88 00000000 8011a2ac
    Hi    : 0040273c
    Lo    : 88d3ff28
    epc   : 80114178 _restore_fp+0x10/0xa0
    ra    : 8011a2ac mipsr2_decoder+0xd5c/0x1660
    Status: 1400fc03    KERNEL EXL IE
    Cause : 1080002c (ExcCode 0b)
    PrId  : 0001a920 (MIPS I6400)
    Modules linked in:
    Process fp-prctl (pid: 7338, threadinfo=88d38000, task=838e4000, tls=766527d0)
    Stack : 00000000 00000000 00000000 88d3fe98 00000000 00000000 809c0398 809c0338
          808e9100 00000000 88d3ff28 00400fc4 00400fc4 0040273c 7fb69e18 004a0000
          004a0000 004a0000 7664add0 8010de18 00000000 00000000 88d3fef8 88d3ff28
          808e9100 00000000 766527d0 8010e534 000c0000 85755000 8181d580 00000000
          00000000 00000000 004a0000 00000000 766527d0 7fb69e18 004a0000 80105c20
          ...
    Call Trace:
    [<80114178>] _restore_fp+0x10/0xa0
    [<8011a2ac>] mipsr2_decoder+0xd5c/0x1660
    [<8010de18>] do_ri+0x90/0x6b8
    [<80105c20>] ret_from_exception+0x0/0x10

At first glance a simple fix may seem to be to disable interrupts around
kernel use of the FPU rather than merely preemption, however this would
introduce further overhead outside of the mode switch path & doesn't
solve the third problem:

 3) The IPI may arrive whilst the kernel is running code that will lead
    to a preempt_disable() call & FPU usage soon. If this happens then
    the IPI will be serviced & we'll proceed to enable an FPU whilst the
    mode switch is in progress, leading to strange & inconsistent
    behaviour.

Further to all of this is a separate but related problem:

 4) There are various paths through which we may enable the FPU without
    the user having triggered a coprocessor 1 disabled exception. These
    paths are those in which we emulate instructions & then enable the
    FPU with the expectation that the user might execute an FP
    instruction shortly afterwards. However these paths have not
    previously checked whether an FP mode switch is underway for the
    task, and therefore could enable the FPU whilst such a mode switch
    is in progress leading to strange & inconsistent behaviour for user
    code.

This patch fixes all of the above by taking a step back & re-examining
our approach to FP mode switches. Up until now we have taken these basic
steps:

 a) Prevent any threads that are part of the affected process from being
    able to obtain ownership of the FPU.

 b) Cause any threads that are part of the affected process and already
    have ownership of an FPU to lose it.

 c) Set the thread flags for each thread that is part of the affected
    process to reflect the new FP mode.

 d) Allow threads to obtain ownership of the FPU again.

This approach is however more complex than necessary. All that we really
require is that the mode switch has occurred for all threads that are
part of the affected process before mips_set_process_fp_mode(), and thus
the PR_SET_FP_MODE prctl() syscall, returns. This doesn't require that
we stop threads from owning or using an FPU whilst a mode switch occurs,
only that we force them to relinquish it after the mode switch has
occurred such that they next own an FPU with the correct mode
configured. Our basic steps therefore simplify to:

 A) Set the thread flags for each thread that is part of the affected
    process to reflect the new FP mode.

 B) Cause any threads that are part of the affected process and already
    have ownership of an FPU to lose it.

We implement B) by forcing each CPU which might be running a thread
which is part of the affected process to schedule a no-op function,
which causes the affected thread to lose its FPU ownership when it is
descheduled.

The end result is simpler FP mode switching with less overhead in the
FPU enable path (ie. enable_restore_fp_context()) and fewer moving
parts.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 9791554b45a2 ("MIPS,prctl: add PR_[GS]ET_FP_MODE prctl options for MIPS")
Fixes: 6b8322576e9d ("MIPS: Force CPUs to lose FP context during mode switches")
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: stable <stable@vger.kernel.org> # v4.0+
---
 arch/mips/include/asm/mmu_context.h |  2 -
 arch/mips/kernel/process.c          | 80 +++++++++++++++++++------------------
 arch/mips/kernel/traps.c            |  7 ----
 3 files changed, 42 insertions(+), 47 deletions(-)

diff --git a/arch/mips/include/asm/mmu_context.h b/arch/mips/include/asm/mmu_context.h
index da2004cef2d5..b509371a6b0c 100644
--- a/arch/mips/include/asm/mmu_context.h
+++ b/arch/mips/include/asm/mmu_context.h
@@ -126,8 +126,6 @@ init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	for_each_possible_cpu(i)
 		cpu_context(i, mm) = 0;
 
-	atomic_set(&mm->context.fp_mode_switching, 0);
-
 	mm->context.bd_emupage_allocmap = NULL;
 	spin_lock_init(&mm->context.bd_emupage_lock);
 	init_waitqueue_head(&mm->context.bd_emupage_queue);
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 8d85046adcc8..fe6001d748cf 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -29,6 +29,7 @@
 #include <linux/kallsyms.h>
 #include <linux/random.h>
 #include <linux/prctl.h>
+#include <linux/cpu.h>
 
 #include <asm/asm.h>
 #include <asm/bootinfo.h>
@@ -691,19 +692,25 @@ int mips_get_process_fp_mode(struct task_struct *task)
 	return value;
 }
 
-static void prepare_for_fp_mode_switch(void *info)
+static long prepare_for_fp_mode_switch(void *unused)
 {
-	struct mm_struct *mm = info;
-
-	if (current->mm == mm)
-		lose_fpu(1);
+	/*
+	 * This is icky, but we use this to simply ensure that all CPUs have
+	 * context switched, regardless of whether they were previously running
+	 * kernel or user code. This ensures that no CPU currently has its FPU
+	 * enabled, or is about to attempt to enable it through any path other
+	 * than enable_restore_fp_context() which will wait appropriately for
+	 * fp_mode_switching to be zero.
+	 */
+	return 0;
 }
 
 int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 {
 	const unsigned int known_bits = PR_FP_MODE_FR | PR_FP_MODE_FRE;
 	struct task_struct *t;
-	int max_users;
+	struct cpumask process_cpus;
+	int cpu;
 
 	/* If nothing to change, return right away, successfully.  */
 	if (value == mips_get_process_fp_mode(task))
@@ -736,35 +743,7 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 	if (!(value & PR_FP_MODE_FR) && raw_cpu_has_fpu && cpu_has_mips_r6)
 		return -EOPNOTSUPP;
 
-	/* Proceed with the mode switch */
-	preempt_disable();
-
-	/* Save FP & vector context, then disable FPU & MSA */
-	if (task->signal == current->signal)
-		lose_fpu(1);
-
-	/* Prevent any threads from obtaining live FP context */
-	atomic_set(&task->mm->context.fp_mode_switching, 1);
-	smp_mb__after_atomic();
-
-	/*
-	 * If there are multiple online CPUs then force any which are running
-	 * threads in this process to lose their FPU context, which they can't
-	 * regain until fp_mode_switching is cleared later.
-	 */
-	if (num_online_cpus() > 1) {
-		/* No need to send an IPI for the local CPU */
-		max_users = (task->mm == current->mm) ? 1 : 0;
-
-		if (atomic_read(&current->mm->mm_users) > max_users)
-			smp_call_function(prepare_for_fp_mode_switch,
-					  (void *)current->mm, 1);
-	}
-
-	/*
-	 * There are now no threads of the process with live FP context, so it
-	 * is safe to proceed with the FP mode switch.
-	 */
+	/* Indicate the new FP mode in each thread */
 	for_each_thread(task, t) {
 		/* Update desired FP register width */
 		if (value & PR_FP_MODE_FR) {
@@ -781,9 +760,34 @@ int mips_set_process_fp_mode(struct task_struct *task, unsigned int value)
 			clear_tsk_thread_flag(t, TIF_HYBRID_FPREGS);
 	}
 
-	/* Allow threads to use FP again */
-	atomic_set(&task->mm->context.fp_mode_switching, 0);
-	preempt_enable();
+	/*
+	 * We need to ensure that all threads in the process have switched mode
+	 * before returning, in order to allow userland to not worry about
+	 * races. We can do this by forcing all CPUs that any thread in the
+	 * process may be running on to schedule something else - in this case
+	 * prepare_for_fp_mode_switch().
+	 *
+	 * We begin by generating a mask of all CPUs that any thread in the
+	 * process may be running on.
+	 */
+	cpumask_clear(&process_cpus);
+	for_each_thread(task, t)
+		cpumask_set_cpu(task_cpu(t), &process_cpus);
+
+	/*
+	 * Now we schedule prepare_for_fp_mode_switch() on each of those CPUs.
+	 *
+	 * The CPUs may have rescheduled already since we switched mode or
+	 * generated the cpumask, but that doesn't matter. If the task in this
+	 * process is scheduled out then our scheduling
+	 * prepare_for_fp_mode_switch() will simply be redundant. If it's
+	 * scheduled in then it will already have picked up the new FP mode
+	 * whilst doing so.
+	 */
+	get_online_cpus();
+	for_each_cpu_and(cpu, &process_cpus, cpu_online_mask)
+		work_on_cpu(cpu, prepare_for_fp_mode_switch, NULL);
+	put_online_cpus();
 
 	wake_up_var(&task->mm->context.fp_mode_switching);
 
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index d67fa74622ee..4d9ca9b465ae 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1220,13 +1220,6 @@ static int enable_restore_fp_context(int msa)
 {
 	int err, was_fpu_owner, prior_msa;
 
-	/*
-	 * If an FP mode switch is currently underway, wait for it to
-	 * complete before proceeding.
-	 */
-	wait_var_event(&current->mm->context.fp_mode_switching,
-		       !atomic_read(&current->mm->context.fp_mode_switching));
-
 	if (!used_math()) {
 		/* First time FP context user. */
 		preempt_disable();
-- 
cgit v1.2.3


From 8fd2d6ea66272f849943269c7ea771ce85fd8fb1 Mon Sep 17 00:00:00 2001
From: Joshua Kinard <kumba@gentoo.org>
Date: Tue, 17 Oct 2017 14:26:12 -0400
Subject: MIPS: Use !pci_is_root_bus(bus) in ops-bridge.c

This is a manual cherrypick of commit c7ddc3d137b7 from Alastair
Bridgewater's IP35 tree that replaces two cases of
"if (bus->number > 0)" with a more correct "if (!pci_is_root_bus(bus))"
in arch/mips/pci/ops-bridge.c.

Cc: linux-mips@linux-mips.org
Cc: Alastair Bridgewater <alastair.bridgewater@gmail.com>
Suggested-by: Alastair Bridgewater <alastair.bridgewater@gmail.com>
Signed-off-by: Joshua Kinard <kumba@gentoo.org>
Patchwork: https://patchwork.linux-mips.org/patch/17501/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Linux/MIPS <linux-mips@linux-mips.org>
---
 arch/mips/pci/ops-bridge.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/mips/pci/ops-bridge.c b/arch/mips/pci/ops-bridge.c
index 57e1463fcd02..a1d2c4ae0d1b 100644
--- a/arch/mips/pci/ops-bridge.c
+++ b/arch/mips/pci/ops-bridge.c
@@ -167,7 +167,7 @@ oh_my_gawd:
 static int pci_read_config(struct pci_bus *bus, unsigned int devfn,
 			   int where, int size, u32 * value)
 {
-	if (bus->number > 0)
+	if (!pci_is_root_bus(bus))
 		return pci_conf1_read_config(bus, devfn, where, size, value);
 
 	return pci_conf0_read_config(bus, devfn, where, size, value);
@@ -310,7 +310,7 @@ oh_my_gawd:
 static int pci_write_config(struct pci_bus *bus, unsigned int devfn,
 	int where, int size, u32 value)
 {
-	if (bus->number > 0)
+	if (!pci_is_root_bus(bus))
 		return pci_conf1_write_config(bus, devfn, where, size, value);
 
 	return pci_conf0_write_config(bus, devfn, where, size, value);
-- 
cgit v1.2.3


From d1c5872ce1042d10d44e54b6e8e8f5b7c2e76541 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 2 Jun 2017 15:17:25 -0700
Subject: MIPS: Set MIPS_IC_SNOOPS_REMOTE for systems with CM

In systems that include a MIPS Coherency Manager, the icache always
fills from a cache which is coherent across all CPUs. In I6400 & I6500
systems the icache fills from the dcache which is coherent across all
CPUs. In all other CM-based systems the icache fills from the L2 cache
which is shared between all cores.

This means that an icache will always see stores from remote CPUs
without needing to write them back any further than that L2, which is
what the cpu_icache_snoops_remote_store feature is used to test. In
order for it to return 1 without needing a per-platform override (which
is what Malta has relied upon so far) set the MIPS_IC_SNOOPS_REMOTE flag
when a CM is present.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/16200/
---
 arch/mips/mm/c-r4k.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index b83ecfb2fbfc..1b4b583fab08 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -1505,6 +1505,14 @@ static void probe_pcache(void)
 	if (c->dcache.flags & MIPS_CACHE_PINDEX)
 		c->dcache.flags &= ~MIPS_CACHE_ALIASES;
 
+	/*
+	 * In systems with CM the icache fills from L2 or closer caches, and
+	 * thus sees remote stores without needing to write them back any
+	 * further than that.
+	 */
+	if (mips_cm_present())
+		c->icache.flags |= MIPS_IC_SNOOPS_REMOTE;
+
 	switch (current_cpu_type()) {
 	case CPU_20KC:
 		/*
-- 
cgit v1.2.3


From a07539c00046dfa890e6aac1db4f0de01acb0132 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 2 Sep 2016 16:10:06 +0100
Subject: MIPS: Malta: Cleanup DMA coherence #ifdefs

DMA coherence is not user-selectable in Kconfig, and Malta selects
CONFIG_DMA_MAYBE_COHERENT which in turn selects CONFIG_DMA_NONCOHERENT.
Remove #ifdefs whose conditions can therefore never be true for Malta.

This removes a significant amount of code from bonito_quirks_setup(),
but the code is duplicated in plat_enable_iocoherency() anyway so we
lose nothing but duplication.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/14188/
---
 arch/mips/mti-malta/malta-setup.c | 38 --------------------------------------
 1 file changed, 38 deletions(-)

diff --git a/arch/mips/mti-malta/malta-setup.c b/arch/mips/mti-malta/malta-setup.c
index 7cb7d5a42087..5d4c5e5fbd69 100644
--- a/arch/mips/mti-malta/malta-setup.c
+++ b/arch/mips/mti-malta/malta-setup.c
@@ -145,12 +145,6 @@ static int __init plat_enable_iocoherency(void)
 
 static void __init plat_setup_iocoherency(void)
 {
-#ifdef CONFIG_DMA_NONCOHERENT
-	/*
-	 * Kernel has been configured with software coherency
-	 * but we might choose to turn it off and use hardware
-	 * coherency instead.
-	 */
 	if (plat_enable_iocoherency()) {
 		if (coherentio == IO_COHERENCE_DISABLED)
 			pr_info("Hardware DMA cache coherency disabled\n");
@@ -162,10 +156,6 @@ static void __init plat_setup_iocoherency(void)
 		else
 			pr_info("Software DMA cache coherency enabled\n");
 	}
-#else
-	if (!plat_enable_iocoherency())
-		panic("Hardware DMA cache coherency not supported!");
-#endif
 }
 
 static void __init pci_clock_check(void)
@@ -227,29 +217,6 @@ static void __init bonito_quirks_setup(void)
 		pr_info("Enabled Bonito debug mode\n");
 	} else
 		BONITO_BONGENCFG &= ~BONITO_BONGENCFG_DEBUGMODE;
-
-#ifndef CONFIG_DMA_NONCOHERENT
-	if (BONITO_PCICACHECTRL & BONITO_PCICACHECTRL_CPUCOH_PRES) {
-		BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_CPUCOH_EN;
-		pr_info("Enabled Bonito CPU coherency\n");
-
-		argptr = fw_getcmdline();
-		if (strstr(argptr, "iobcuncached")) {
-			BONITO_PCICACHECTRL &= ~BONITO_PCICACHECTRL_IOBCCOH_EN;
-			BONITO_PCIMEMBASECFG = BONITO_PCIMEMBASECFG &
-				~(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
-					BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
-			pr_info("Disabled Bonito IOBC coherency\n");
-		} else {
-			BONITO_PCICACHECTRL |= BONITO_PCICACHECTRL_IOBCCOH_EN;
-			BONITO_PCIMEMBASECFG |=
-				(BONITO_PCIMEMBASECFG_MEMBASE0_CACHED |
-					BONITO_PCIMEMBASECFG_MEMBASE1_CACHED);
-			pr_info("Enabled Bonito IOBC coherency\n");
-		}
-	} else
-		panic("Hardware DMA cache coherency not supported");
-#endif
 }
 
 void __init *plat_get_fdt(void)
@@ -280,11 +247,6 @@ void __init plat_mem_setup(void)
 	 */
 	enable_dma(4);
 
-#ifndef CONFIG_DMA_NONCOHERENT
-	if (mips_revision_sconid != MIPS_REVISION_SCON_BONITO)
-		panic("Hardware DMA cache coherency not supported");
-#endif
-
 	if (mips_revision_sconid == MIPS_REVISION_SCON_BONITO)
 		bonito_quirks_setup();
 
-- 
cgit v1.2.3


From dd129c6374e90e665ec022019bcc2f392f25cf2c Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 19 Sep 2016 22:21:31 +0100
Subject: MIPS: Malta: Use PIIX4 poweroff driver to power down

Remove the platform code used to power down the system, instead relying
upon the new PIIX4 poweroff driver. This reduces the amount of platform
code required for the Malta board in preparation for allowing it to be
part of a more generic kernel.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/14282/
---
 arch/mips/Kconfig                           |  6 --
 arch/mips/configs/malta_defconfig           |  1 +
 arch/mips/configs/malta_kvm_defconfig       |  1 +
 arch/mips/configs/malta_kvm_guest_defconfig |  1 +
 arch/mips/configs/malta_qemu_32r6_defconfig |  1 +
 arch/mips/configs/maltaaprp_defconfig       |  1 +
 arch/mips/configs/maltasmvp_defconfig       |  1 +
 arch/mips/configs/maltasmvp_eva_defconfig   |  1 +
 arch/mips/configs/maltaup_defconfig         |  1 +
 arch/mips/configs/maltaup_xpa_defconfig     |  1 +
 arch/mips/mti-malta/Makefile                |  2 -
 arch/mips/mti-malta/malta-pm.c              | 96 -----------------------------
 arch/mips/mti-malta/malta-reset.c           | 30 ---------
 13 files changed, 9 insertions(+), 134 deletions(-)
 delete mode 100644 arch/mips/mti-malta/malta-pm.c
 delete mode 100644 arch/mips/mti-malta/malta-reset.c

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 33375dd234eb..a6ce5087b729 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1974,12 +1974,6 @@ config SYS_HAS_CPU_XLR
 config SYS_HAS_CPU_XLP
 	bool
 
-config MIPS_MALTA_PM
-	depends on MIPS_MALTA
-	depends on PCI
-	bool
-	default y
-
 #
 # CPU may reorder R->R, R->W, W->R, W->W
 # Reordering beyond LL and SC is handled in WEAK_REORDERING_BEYOND_LLSC
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index df8a9a15ca83..81058295d35f 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -317,6 +317,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 14df9ef15d40..5c10cddc39d3 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -328,6 +328,7 @@ CONFIG_INPUT_MOUSEDEV=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_kvm_guest_defconfig b/arch/mips/configs/malta_kvm_guest_defconfig
index 25092e344574..bb694f5065f1 100644
--- a/arch/mips/configs/malta_kvm_guest_defconfig
+++ b/arch/mips/configs/malta_kvm_guest_defconfig
@@ -330,6 +330,7 @@ CONFIG_INPUT_MOUSEDEV=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/malta_qemu_32r6_defconfig b/arch/mips/configs/malta_qemu_32r6_defconfig
index 210bf609f785..5b5306b80576 100644
--- a/arch/mips/configs/malta_qemu_32r6_defconfig
+++ b/arch/mips/configs/malta_qemu_32r6_defconfig
@@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaaprp_defconfig b/arch/mips/configs/maltaaprp_defconfig
index e5934aa98397..85543599448f 100644
--- a/arch/mips/configs/maltaaprp_defconfig
+++ b/arch/mips/configs/maltaaprp_defconfig
@@ -133,6 +133,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltasmvp_defconfig b/arch/mips/configs/maltasmvp_defconfig
index cb2ca11c1789..067bb84ac916 100644
--- a/arch/mips/configs/maltasmvp_defconfig
+++ b/arch/mips/configs/maltasmvp_defconfig
@@ -134,6 +134,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltasmvp_eva_defconfig b/arch/mips/configs/maltasmvp_eva_defconfig
index be29fcec69fc..dfc78c3172a3 100644
--- a/arch/mips/configs/maltasmvp_eva_defconfig
+++ b/arch/mips/configs/maltasmvp_eva_defconfig
@@ -137,6 +137,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_defconfig b/arch/mips/configs/maltaup_defconfig
index 40462d4c90a0..50a2288c69f8 100644
--- a/arch/mips/configs/maltaup_defconfig
+++ b/arch/mips/configs/maltaup_defconfig
@@ -132,6 +132,7 @@ CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_HW_RANDOM=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 4e50176cb3df..99a19cf5f9ba 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -326,6 +326,7 @@ CONFIG_MOUSE_PS2_ELANTECH=y
 CONFIG_SERIAL_8250=y
 CONFIG_SERIAL_8250_CONSOLE=y
 CONFIG_POWER_RESET=y
+CONFIG_POWER_RESET_PIIX4_POWEROFF=y
 CONFIG_POWER_RESET_SYSCON=y
 # CONFIG_HWMON is not set
 CONFIG_FB=y
diff --git a/arch/mips/mti-malta/Makefile b/arch/mips/mti-malta/Makefile
index 63940bdce698..17c7fd471a27 100644
--- a/arch/mips/mti-malta/Makefile
+++ b/arch/mips/mti-malta/Makefile
@@ -13,11 +13,9 @@ obj-y				+= malta-init.o
 obj-y				+= malta-int.o
 obj-y				+= malta-memory.o
 obj-y				+= malta-platform.o
-obj-y				+= malta-reset.o
 obj-y				+= malta-setup.o
 obj-y				+= malta-time.o
 
 obj-$(CONFIG_MIPS_CMP)		+= malta-amon.o
-obj-$(CONFIG_MIPS_MALTA_PM)	+= malta-pm.o
 
 CFLAGS_malta-dtshim.o = -I$(src)/../../../scripts/dtc/libfdt
diff --git a/arch/mips/mti-malta/malta-pm.c b/arch/mips/mti-malta/malta-pm.c
deleted file mode 100644
index efbd659fb602..000000000000
--- a/arch/mips/mti-malta/malta-pm.c
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * Copyright (C) 2014 Imagination Technologies
- * Author: Paul Burton <paul.burton@mips.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <linux/delay.h>
-#include <linux/init.h>
-#include <linux/io.h>
-#include <linux/pci.h>
-
-#include <asm/mach-malta/malta-pm.h>
-
-static struct pci_bus *pm_pci_bus;
-static resource_size_t pm_io_offset;
-
-int mips_pm_suspend(unsigned state)
-{
-	int spec_devid;
-	u16 sts;
-
-	if (!pm_pci_bus || !pm_io_offset)
-		return -ENODEV;
-
-	/* Ensure the power button status is clear */
-	while (1) {
-		sts = inw(pm_io_offset + PIIX4_FUNC3IO_PMSTS);
-		if (!(sts & PIIX4_FUNC3IO_PMSTS_PWRBTN_STS))
-			break;
-		outw(sts, pm_io_offset + PIIX4_FUNC3IO_PMSTS);
-	}
-
-	/* Enable entry to suspend */
-	outw(state | PIIX4_FUNC3IO_PMCNTRL_SUS_EN,
-	     pm_io_offset + PIIX4_FUNC3IO_PMCNTRL);
-
-	/* If the special cycle occurs too soon this doesn't work... */
-	mdelay(10);
-
-	/*
-	 * The PIIX4 will enter the suspend state only after seeing a special
-	 * cycle with the correct magic data on the PCI bus. Generate that
-	 * cycle now.
-	 */
-	spec_devid = PCI_DEVID(0, PCI_DEVFN(0x1f, 0x7));
-	pci_bus_write_config_dword(pm_pci_bus, spec_devid, 0,
-				   PIIX4_SUSPEND_MAGIC);
-
-	/* Give the system some time to power down */
-	mdelay(1000);
-
-	return 0;
-}
-
-static int __init malta_pm_setup(void)
-{
-	struct pci_dev *dev;
-	int res, io_region = PCI_BRIDGE_RESOURCES;
-
-	/* Find a reference to the PCI bus */
-	pm_pci_bus = pci_find_next_bus(NULL);
-	if (!pm_pci_bus) {
-		pr_warn("malta-pm: failed to find reference to PCI bus\n");
-		return -ENODEV;
-	}
-
-	/* Find the PIIX4 PM device */
-	dev = pci_get_subsys(PCI_VENDOR_ID_INTEL,
-			     PCI_DEVICE_ID_INTEL_82371AB_3, PCI_ANY_ID,
-			     PCI_ANY_ID, NULL);
-	if (!dev) {
-		pr_warn("malta-pm: failed to find PIIX4 PM\n");
-		return -ENODEV;
-	}
-
-	/* Request access to the PIIX4 PM IO registers */
-	res = pci_request_region(dev, io_region, "PIIX4 PM IO registers");
-	if (res) {
-		pr_warn("malta-pm: failed to request PM IO registers (%d)\n",
-			res);
-		pci_dev_put(dev);
-		return -ENODEV;
-	}
-
-	/* Find the offset to the PIIX4 PM IO registers */
-	pm_io_offset = pci_resource_start(dev, io_region);
-
-	pci_dev_put(dev);
-	return 0;
-}
-
-late_initcall(malta_pm_setup);
diff --git a/arch/mips/mti-malta/malta-reset.c b/arch/mips/mti-malta/malta-reset.c
deleted file mode 100644
index dd6f62ad4417..000000000000
--- a/arch/mips/mti-malta/malta-reset.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Carsten Langgaard, carstenl@mips.com
- * Copyright (C) 1999,2000 MIPS Technologies, Inc.  All rights reserved.
- */
-#include <linux/io.h>
-#include <linux/pm.h>
-#include <linux/reboot.h>
-
-#include <asm/reboot.h>
-#include <asm/mach-malta/malta-pm.h>
-
-static void mips_machine_power_off(void)
-{
-	mips_pm_suspend(PIIX4_FUNC3IO_PMCNTRL_SUS_TYP_SOFF);
-
-	pr_info("Failed to power down, resetting\n");
-	machine_restart(NULL);
-}
-
-static int __init mips_reboot_setup(void)
-{
-	pm_power_off = mips_machine_power_off;
-
-	return 0;
-}
-arch_initcall(mips_reboot_setup);
-- 
cgit v1.2.3


From ff404a936a958a45e3969730e065ea2886acc5e8 Mon Sep 17 00:00:00 2001
From: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Date: Thu, 1 Jan 2015 16:32:06 +0100
Subject: arch: mips: pci: pci-ip27.c: Remove unused function

Remove the function pci_enable_swapping() that is not used anywhere.

This was partially found by using a static code analysis program called cppcheck.

Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Patchwork: https://patchwork.linux-mips.org/patch/8867/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: John Crispin <blogic@openwrt.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/pci/pci-ip27.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/arch/mips/pci/pci-ip27.c b/arch/mips/pci/pci-ip27.c
index 65b48d41a229..c94a66070a60 100644
--- a/arch/mips/pci/pci-ip27.c
+++ b/arch/mips/pci/pci-ip27.c
@@ -214,17 +214,6 @@ static inline void pci_disable_swapping(struct pci_dev *dev)
 	bridge->b_widget.w_tflush;	/* Flush */
 }
 
-static inline void pci_enable_swapping(struct pci_dev *dev)
-{
-	struct bridge_controller *bc = BRIDGE_CONTROLLER(dev->bus);
-	bridge_t *bridge = bc->base;
-	int slot = PCI_SLOT(dev->devfn);
-
-	/* Turn on byte swapping */
-	bridge->b_device[slot].reg |= BRIDGE_DEV_SWAP_DIR;
-	bridge->b_widget.w_tflush;	/* Flush */
-}
-
 static void pci_fixup_ioc3(struct pci_dev *d)
 {
 	pci_disable_swapping(d);
-- 
cgit v1.2.3


From 829caee7e38273ef27d64207578d4653979c525e Mon Sep 17 00:00:00 2001
From: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Date: Thu, 1 Jan 2015 20:18:22 +0100
Subject: arch: mips: mm: page: Remove unused function

Remove the function sb1_dma_init() that is not used anywhere.

This was partially found by using a static code analysis program called cppcheck.

Signed-off-by: Rickard Strandqvist <rickard_strandqvist@spectrumdigital.se>
Patchwork: https://patchwork.linux-mips.org/patch/8873/
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: John Crispin <blogic@openwrt.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/mm/page.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/arch/mips/mm/page.c b/arch/mips/mm/page.c
index d5d02993aa21..56e4f8bffd4c 100644
--- a/arch/mips/mm/page.c
+++ b/arch/mips/mm/page.c
@@ -623,21 +623,6 @@ struct dmadscr {
 	u64 pad_b;
 } ____cacheline_aligned_in_smp page_descr[DM_NUM_CHANNELS];
 
-void sb1_dma_init(void)
-{
-	int i;
-
-	for (i = 0; i < DM_NUM_CHANNELS; i++) {
-		const u64 base_val = CPHYSADDR((unsigned long)&page_descr[i]) |
-				     V_DM_DSCR_BASE_RINGSZ(1);
-		void *base_reg = IOADDR(A_DM_REGISTER(i, R_DM_DSCR_BASE));
-
-		__raw_writeq(base_val, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_RESET, base_reg);
-		__raw_writeq(base_val | M_DM_DSCR_BASE_ENABL, base_reg);
-	}
-}
-
 void clear_page(void *page)
 {
 	u64 to_phys = CPHYSADDR((unsigned long)page);
-- 
cgit v1.2.3


From 7a1f1b594a3d102f3766b9866aa081f5480c0be0 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sun, 24 Jun 2018 00:35:42 +0900
Subject: mtd: replace VMLINUX_SYMBOL_STR() with string literal

With the special case handling for Blackfin and Metag was removed by
commit 94e58e0ac312 ("export.h: remove code for prefixing symbols with
underscore"), VMLINUX_SYMBOL_STR() can be replaced with string literal.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/chips/gen_probe.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/chips/gen_probe.c b/drivers/mtd/chips/gen_probe.c
index b57ceea21513..879bebf9d8b1 100644
--- a/drivers/mtd/chips/gen_probe.c
+++ b/drivers/mtd/chips/gen_probe.c
@@ -202,10 +202,10 @@ static inline struct mtd_info *cfi_cmdset_unknown(struct map_info *map,
 	struct cfi_private *cfi = map->fldrv_priv;
 	__u16 type = primary?cfi->cfiq->P_ID:cfi->cfiq->A_ID;
 #ifdef CONFIG_MODULES
-	char probename[sizeof(VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X))];
+	char probename[sizeof("cfi_cmdset_%4.4X")];
 	cfi_cmdset_fn_t *probe_function;
 
-	sprintf(probename, VMLINUX_SYMBOL_STR(cfi_cmdset_%4.4X), type);
+	sprintf(probename, "cfi_cmdset_%4.4X", type);
 
 	probe_function = __symbol_get(probename);
 	if (!probe_function) {
-- 
cgit v1.2.3


From 3c8daa7db46dd50c95778b4fbca5c7da6edaac9b Mon Sep 17 00:00:00 2001
From: Christian König <ckoenig.leichtzumerken@gmail.com>
Date: Fri, 22 Jun 2018 12:37:37 +0200
Subject: drm/omap: remove now unused functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some functions are unused after removal of the kmap_atomic
DMA-buf interface.

Signed-off-by: Christian König <christian.koenig@amd.com>
Fixes: f664a5269542 ("dma-buf: remove kmap_atomic interface")
Link: https://patchwork.freedesktop.org/series/45245/
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c | 17 -----------------
 1 file changed, 17 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
index 1a073f9b2834..ec04a69ade46 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem_dmabuf.c
@@ -93,23 +93,6 @@ static int omap_gem_dmabuf_end_cpu_access(struct dma_buf *buffer,
 	return 0;
 }
 
-
-static void *omap_gem_dmabuf_kmap_atomic(struct dma_buf *buffer,
-		unsigned long page_num)
-{
-	struct drm_gem_object *obj = buffer->priv;
-	struct page **pages;
-	omap_gem_get_pages(obj, &pages, false);
-	omap_gem_cpu_sync_page(obj, page_num);
-	return kmap_atomic(pages[page_num]);
-}
-
-static void omap_gem_dmabuf_kunmap_atomic(struct dma_buf *buffer,
-		unsigned long page_num, void *addr)
-{
-	kunmap_atomic(addr);
-}
-
 static void *omap_gem_dmabuf_kmap(struct dma_buf *buffer,
 		unsigned long page_num)
 {
-- 
cgit v1.2.3


From 83741bb0430465ea9f0654d4772c03d694b33ad7 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 24 Jun 2018 10:38:37 +0200
Subject: bnxt: simplify cls_flower command switch and handle default case

Currently the default case is not handled, which with future command
introductions would introduce a warning. So handle it and make the
switch a bit simplier removing unneeded "rc" variable.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 795f45024c20..d0699f39ba34 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -1544,22 +1544,16 @@ void bnxt_tc_flow_stats_work(struct bnxt *bp)
 int bnxt_tc_setup_flower(struct bnxt *bp, u16 src_fid,
 			 struct tc_cls_flower_offload *cls_flower)
 {
-	int rc = 0;
-
 	switch (cls_flower->command) {
 	case TC_CLSFLOWER_REPLACE:
-		rc = bnxt_tc_add_flow(bp, src_fid, cls_flower);
-		break;
-
+		return bnxt_tc_add_flow(bp, src_fid, cls_flower);
 	case TC_CLSFLOWER_DESTROY:
-		rc = bnxt_tc_del_flow(bp, cls_flower);
-		break;
-
+		return bnxt_tc_del_flow(bp, cls_flower);
 	case TC_CLSFLOWER_STATS:
-		rc = bnxt_tc_get_flow_stats(bp, cls_flower);
-		break;
+		return bnxt_tc_get_flow_stats(bp, cls_flower);
+	default:
+		return -EOPNOTSUPP;
 	}
-	return rc;
 }
 
 static const struct rhashtable_params bnxt_tc_flow_ht_params = {
-- 
cgit v1.2.3


From eba7927b55938b8db7ba5d76086f0ab0a2e2274d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 24 Jun 2018 10:38:38 +0200
Subject: nfp: handle cls_flower command default case

Currently the default case is not handled, which with future command
introductions would introduce a warning. So handle it.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index c42e64f32333..c0e74aa4cb5e 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -576,9 +576,9 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev,
 		return nfp_flower_del_offload(app, netdev, flower, egress);
 	case TC_CLSFLOWER_STATS:
 		return nfp_flower_get_stats(app, netdev, flower, egress);
+	default:
+		return -EOPNOTSUPP;
 	}
-
-	return -EOPNOTSUPP;
 }
 
 int nfp_flower_setup_tc_egress_cb(enum tc_setup_type type, void *type_data,
-- 
cgit v1.2.3


From 246ab6f01efb808610535be34aab2de9325da6fa Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 24 Jun 2018 10:38:39 +0200
Subject: cls_flower: fix error values for commands not supported by drivers

-EOPNOTSUPP is the error value that should be reported if a flower
command is not supported by a driver. Fix it in couple of Intel drivers.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c     | 2 +-
 drivers/net/ethernet/intel/i40evf/i40evf_main.c | 2 +-
 drivers/net/ethernet/intel/igb/igb_main.c       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 95e9dfbe9839..7ad2b1b0b125 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7522,7 +7522,7 @@ static int i40e_setup_tc_cls_flower(struct i40e_netdev_priv *np,
 	case TC_CLSFLOWER_STATS:
 		return -EOPNOTSUPP;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index a7b87f935411..dc56a8667495 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2884,7 +2884,7 @@ static int i40evf_setup_tc_cls_flower(struct i40evf_adapter *adapter,
 	case TC_CLSFLOWER_STATS:
 		return -EOPNOTSUPP;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 }
 
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f707709969ac..6a78d8272eb2 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2698,7 +2698,7 @@ static int igb_setup_tc_cls_flower(struct igb_adapter *adapter,
 	case TC_CLSFLOWER_STATS:
 		return -EOPNOTSUPP;
 	default:
-		return -EINVAL;
+		return -EOPNOTSUPP;
 	}
 }
 
-- 
cgit v1.2.3


From 92bad8509159b2377b40fe91a6b37f1b4cb63569 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 24 Jun 2018 18:37:36 +0200
Subject: r8169: improve phy initialization when resuming

Let's move calling rtl8169_init_phy() to __rtl8169_resume().
It simplifies the code and avoids rtl8169_init_phy() being called
when resuming whilst interface is down. rtl_open() will initialize
the PHY when the interface is brought up.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 44715958b246..480fb141fe62 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7334,6 +7334,7 @@ static void __rtl8169_resume(struct net_device *dev)
 	netif_device_attach(dev);
 
 	rtl_pll_power_up(tp);
+	rtl8169_init_phy(dev, tp);
 
 	rtl_lock_work(tp);
 	napi_enable(&tp->napi);
@@ -7347,9 +7348,6 @@ static int rtl8169_resume(struct device *device)
 {
 	struct pci_dev *pdev = to_pci_dev(device);
 	struct net_device *dev = pci_get_drvdata(pdev);
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	rtl8169_init_phy(dev, tp);
 
 	if (netif_running(dev))
 		__rtl8169_resume(dev);
@@ -7397,8 +7395,6 @@ static int rtl8169_runtime_resume(struct device *device)
 	tp->saved_wolopts = 0;
 	rtl_unlock_work(tp);
 
-	rtl8169_init_phy(dev, tp);
-
 	__rtl8169_resume(dev);
 
 	return 0;
-- 
cgit v1.2.3


From 433f9d0ddcc6020ac5ecc91626f12e3e23b52be0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 24 Jun 2018 18:39:06 +0200
Subject: r8169: improve saved_wolopts handling

Let's make saved_wolopts a shadow copy of the WoL options. This allows
to simplify the code and get rid of calls to now unneeded function
__rtl8169_get_wol(). However don't remove __rtl8169_get_wol()
completely to be prepared for the case that we can respect BIOS WOL
settings again.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 34 ++++++++++++++--------------------
 1 file changed, 14 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 480fb141fe62..f8a1309a6494 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1587,6 +1587,12 @@ static void rtl8169_check_link_status(struct net_device *dev,
 
 #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
 
+/* Currently we only enable WoL if explicitly told by userspace to circumvent
+ * issues on certain platforms, see commit bde135a672bf ("r8169: only enable
+ * PCI wakeups when WOL is active"). Let's keep __rtl8169_get_wol() for the
+ * case that we want to respect BIOS settings again.
+ */
+#if 0
 static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
 {
 	u8 options;
@@ -1621,25 +1627,16 @@ static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
 
 	return wolopts;
 }
+#endif
 
 static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	struct device *d = tp_to_dev(tp);
-
-	pm_runtime_get_noresume(d);
 
 	rtl_lock_work(tp);
-
 	wol->supported = WAKE_ANY;
-	if (pm_runtime_active(d))
-		wol->wolopts = __rtl8169_get_wol(tp);
-	else
-		wol->wolopts = tp->saved_wolopts;
-
+	wol->wolopts = tp->saved_wolopts;
 	rtl_unlock_work(tp);
-
-	pm_runtime_put_noidle(d);
 }
 
 static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts)
@@ -1719,14 +1716,14 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 
 	rtl_lock_work(tp);
 
+	tp->saved_wolopts = wol->wolopts & WAKE_ANY;
+
 	if (pm_runtime_active(d))
-		__rtl8169_set_wol(tp, wol->wolopts);
-	else
-		tp->saved_wolopts = wol->wolopts;
+		__rtl8169_set_wol(tp, tp->saved_wolopts);
 
 	rtl_unlock_work(tp);
 
-	device_set_wakeup_enable(d, wol->wolopts);
+	device_set_wakeup_enable(d, tp->saved_wolopts);
 
 	pm_runtime_put_noidle(d);
 
@@ -4638,7 +4635,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 
 static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 {
-	if (!(__rtl8169_get_wol(tp) & WAKE_ANY))
+	if (!tp->saved_wolopts)
 		return false;
 
 	rtl_speed_down(tp);
@@ -7219,7 +7216,6 @@ static int rtl_open(struct net_device *dev)
 
 	rtl_unlock_work(tp);
 
-	tp->saved_wolopts = 0;
 	pm_runtime_put_sync(&pdev->dev);
 
 	rtl8169_check_link_status(dev, tp);
@@ -7367,7 +7363,6 @@ static int rtl8169_runtime_suspend(struct device *device)
 	}
 
 	rtl_lock_work(tp);
-	tp->saved_wolopts = __rtl8169_get_wol(tp);
 	__rtl8169_set_wol(tp, WAKE_ANY);
 	rtl_unlock_work(tp);
 
@@ -7392,7 +7387,6 @@ static int rtl8169_runtime_resume(struct device *device)
 
 	rtl_lock_work(tp);
 	__rtl8169_set_wol(tp, tp->saved_wolopts);
-	tp->saved_wolopts = 0;
 	rtl_unlock_work(tp);
 
 	__rtl8169_resume(dev);
@@ -7462,7 +7456,7 @@ static void rtl_shutdown(struct pci_dev *pdev)
 	rtl8169_hw_reset(tp);
 
 	if (system_state == SYSTEM_POWER_OFF) {
-		if (__rtl8169_get_wol(tp) & WAKE_ANY) {
+		if (tp->saved_wolopts) {
 			rtl_wol_suspend_quirk(tp);
 			rtl_wol_shutdown_quirk(tp);
 		}
-- 
cgit v1.2.3


From fe87bef01f9be5d968badb35648a527fa37888c1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 24 Jun 2018 18:40:23 +0200
Subject: r8169: don't check WoL when powering down PHY and interface is down

We can power down the PHY irregardless of WOL settings if interface
is down. So far we would have left the PHY enabled if WOL options
are set and the interface is brought down.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f8a1309a6494..1d33672c650d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4635,7 +4635,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 
 static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 {
-	if (!tp->saved_wolopts)
+	if (!netif_running(tp->dev) || !tp->saved_wolopts)
 		return false;
 
 	rtl_speed_down(tp);
-- 
cgit v1.2.3


From 818489e511a3a38d4c9c120675e0700608925800 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <Sudeep.Holla@arm.com>
Date: Mon, 18 Jun 2018 15:34:22 +0100
Subject: ARM: cpuidle: silence error on driver registration failure

It's perfectly fine to have multiple cpuidle driver compiled in the
build configuration. However, it's not good to throw error on driver
registration failure if some other driver is already initialised and
assigned. In such cases, __cpuidle_register_driver returns -EBUSY and
we can check for such error before throwing the error.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpuidle/cpuidle-arm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c
index e07bc7ace774..073557f433eb 100644
--- a/drivers/cpuidle/cpuidle-arm.c
+++ b/drivers/cpuidle/cpuidle-arm.c
@@ -105,7 +105,8 @@ static int __init arm_idle_init_cpu(int cpu)
 
 	ret = cpuidle_register_driver(drv);
 	if (ret) {
-		pr_err("Failed to register cpuidle driver\n");
+		if (ret != -EBUSY)
+			pr_err("Failed to register cpuidle driver\n");
 		goto out_kfree_drv;
 	}
 
-- 
cgit v1.2.3


From cc51574ad2632dde790241129617bb97f46f7c85 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Fri, 22 Jun 2018 21:28:33 +0200
Subject: ALSA: ac97: add bus binding for codecs

Add the generic ac97 bus binding, especially for ac97 codecs discovered
by ac97 hardware probing.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 .../devicetree/bindings/sound/ac97-bus.txt         | 32 ++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/ac97-bus.txt

diff --git a/Documentation/devicetree/bindings/sound/ac97-bus.txt b/Documentation/devicetree/bindings/sound/ac97-bus.txt
new file mode 100644
index 000000000000..103c428f2595
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/ac97-bus.txt
@@ -0,0 +1,32 @@
+Generic AC97 Device Properties
+
+This documents describes the devicetree bindings for an ac97 controller child
+node describing ac97 codecs.
+
+Required properties:
+-compatible : Must be "ac97,vendor_id1,vendor_id2
+	      The ids shall be the 4 characters hexadecimal encoding, such as
+	      given by "%04x" formatting of printf
+-reg	    : Must be the ac97 codec number, between 0 and 3
+
+Example:
+ac97: sound@40500000 {
+	compatible = "marvell,pxa270-ac97";
+	reg = < 0x40500000 0x1000 >;
+	interrupts = <14>;
+	reset-gpios = <&gpio 95 GPIO_ACTIVE_HIGH>;
+	#sound-dai-cells = <1>;
+	pinctrl-names = "default";
+	pinctrl-0 = < &pinctrl_ac97_default >;
+	clocks = <&clks CLK_AC97>, <&clks CLK_AC97CONF>;
+	clock-names = "AC97CLK", "AC97CONFCLK";
+
+	#address-cells = <1>;
+	#size-cells = <0>;
+	audio-codec@0 {
+		reg = <0>;
+		compatible = "ac97,574d,4c13";
+		clocks = <&fixed_wm9713_clock>;
+		clock-names = "ac97_clk";
+	}
+};
-- 
cgit v1.2.3


From 2225a3e6af78e605119e0f178ae957d860882b1d Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Fri, 22 Jun 2018 21:28:34 +0200
Subject: ALSA: ac97: add codecs devicetree binding

Add a devicetree binding for codecs. This is especially useful if the
AC97 bitclk clock is provided by the codec, as it has to be described in
the devicetree description for the ac97 bus code to aquire it.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/ac97/bus.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/sound/ac97/bus.c b/sound/ac97/bus.c
index 31f858eceffc..7a0dfca03a57 100644
--- a/sound/ac97/bus.c
+++ b/sound/ac97/bus.c
@@ -13,6 +13,7 @@
 #include <linux/idr.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
+#include <linux/of.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
@@ -68,6 +69,27 @@ ac97_codec_find(struct ac97_controller *ac97_ctrl, unsigned int codec_num)
 	return ac97_ctrl->codecs[codec_num];
 }
 
+static struct device_node *
+ac97_of_get_child_device(struct ac97_controller *ac97_ctrl, int idx,
+			 unsigned int vendor_id)
+{
+	struct device_node *node;
+	u32 reg;
+	char compat[] = "ac97,0000,0000";
+
+	snprintf(compat, sizeof(compat), "ac97,%04x,%04x",
+		 vendor_id >> 16, vendor_id & 0xffff);
+
+	for_each_child_of_node(ac97_ctrl->parent->of_node, node) {
+		if ((idx != of_property_read_u32(node, "reg", &reg)) ||
+		    !of_device_is_compatible(node, compat))
+			continue;
+		return of_node_get(node);
+	}
+
+	return NULL;
+}
+
 static void ac97_codec_release(struct device *dev)
 {
 	struct ac97_codec_device *adev;
@@ -76,6 +98,7 @@ static void ac97_codec_release(struct device *dev)
 	adev = to_ac97_device(dev);
 	ac97_ctrl = adev->ac97_ctrl;
 	ac97_ctrl->codecs[adev->num] = NULL;
+	of_node_put(dev->of_node);
 	kfree(adev);
 }
 
@@ -98,6 +121,8 @@ static int ac97_codec_add(struct ac97_controller *ac97_ctrl, int idx,
 
 	device_initialize(&codec->dev);
 	dev_set_name(&codec->dev, "%s:%u", dev_name(ac97_ctrl->parent), idx);
+	codec->dev.of_node = ac97_of_get_child_device(ac97_ctrl, idx,
+						      vendor_id);
 
 	ret = device_add(&codec->dev);
 	if (ret)
@@ -105,6 +130,7 @@ static int ac97_codec_add(struct ac97_controller *ac97_ctrl, int idx,
 
 	return 0;
 err_free_codec:
+	of_node_put(codec->dev.of_node);
 	put_device(&codec->dev);
 	kfree(codec);
 	ac97_ctrl->codecs[idx] = NULL;
-- 
cgit v1.2.3


From 1c76aa5fb48d8357f38fb2f1d2cef742a617d695 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 21 Jun 2018 16:37:54 +0200
Subject: ALSA: hda/realtek - Allow skipping spec->init_amp detection

Some devices have the overrides of spec->init_amp at
HDA_FIXUP_ACT_PROBE just because alc_ssid_check() gives the
false-positive values from the SSID.

For more consistent behavior, define the logic in the following way:

- Define ALC_INIT_UNDEFINED as the default value before calling
  alc_ssid_check()
- Each fixup may set up spec->init_amp with another value at
  HDA_FIXUP_ACT_PRE_PROBE
- At detection, check whether spec->init_amp is ALC_INIT_UNDEFINED or
  not; if it's different, we skip the detection

Also, it turned out that ASUS TX300 requires the spec->init_amp
override, too; currently it ignores the GPIO bits implicitly by its
static init verb, but this will be changed in the later patchset.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 44 +++++++++++++++++++++----------------------
 1 file changed, 21 insertions(+), 23 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 7934c5df4d80..1f054e5ae2b3 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -43,6 +43,7 @@
 
 /* extra amp-initialization sequence types */
 enum {
+	ALC_INIT_UNDEFINED,
 	ALC_INIT_NONE,
 	ALC_INIT_DEFAULT,
 	ALC_INIT_GPIO1,
@@ -656,20 +657,22 @@ do_sku:
 	 * 7~6 : Reserved
 	*/
 	tmp = (ass & 0x38) >> 3;	/* external Amp control */
-	switch (tmp) {
-	case 1:
-		spec->init_amp = ALC_INIT_GPIO1;
-		break;
-	case 3:
-		spec->init_amp = ALC_INIT_GPIO2;
-		break;
-	case 7:
-		spec->init_amp = ALC_INIT_GPIO3;
-		break;
-	case 5:
-	default:
-		spec->init_amp = ALC_INIT_DEFAULT;
-		break;
+	if (spec->init_amp == ALC_INIT_UNDEFINED) {
+		switch (tmp) {
+		case 1:
+			spec->init_amp = ALC_INIT_GPIO1;
+			break;
+		case 3:
+			spec->init_amp = ALC_INIT_GPIO2;
+			break;
+		case 7:
+			spec->init_amp = ALC_INIT_GPIO3;
+			break;
+		case 5:
+		default:
+			spec->init_amp = ALC_INIT_DEFAULT;
+			break;
+		}
 	}
 
 	/* is laptop or Desktop and enable the function "Mute internal speaker
@@ -1589,8 +1592,6 @@ static void alc260_fixup_kn1(struct hda_codec *codec,
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
 		snd_hda_apply_pincfgs(codec, pincfgs);
-		break;
-	case HDA_FIXUP_ACT_PROBE:
 		spec->init_amp = ALC_INIT_NONE;
 		break;
 	}
@@ -1600,7 +1601,7 @@ static void alc260_fixup_fsc_s7020(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	if (action == HDA_FIXUP_ACT_PROBE)
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
 		spec->init_amp = ALC_INIT_NONE;
 }
 
@@ -3892,6 +3893,7 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 	struct alc_spec *spec = codec->spec;
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->init_amp = ALC_INIT_DEFAULT;
 		if (alc_register_micmute_input_device(codec) != 0)
 			return;
 
@@ -3914,9 +3916,6 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 		return;
 
 	switch (action) {
-	case HDA_FIXUP_ACT_PROBE:
-		spec->init_amp = ALC_INIT_DEFAULT;
-		break;
 	case HDA_FIXUP_ACT_FREE:
 		input_unregister_device(spec->kb_dev);
 		spec->kb_dev = NULL;
@@ -3937,6 +3936,7 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 	struct alc_spec *spec = codec->spec;
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->init_amp = ALC_INIT_DEFAULT;
 		if (alc_register_micmute_input_device(codec) != 0)
 			return;
 
@@ -3955,9 +3955,6 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 		return;
 
 	switch (action) {
-	case HDA_FIXUP_ACT_PROBE:
-		spec->init_amp = ALC_INIT_DEFAULT;
-		break;
 	case HDA_FIXUP_ACT_FREE:
 		input_unregister_device(spec->kb_dev);
 		spec->kb_dev = NULL;
@@ -5227,6 +5224,7 @@ static void alc282_fixup_asus_tx300(struct hda_codec *codec,
 
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
+		spec->init_amp = ALC_INIT_DEFAULT;
 		snd_hda_add_verbs(codec, gpio2_verbs);
 		snd_hda_apply_pincfgs(codec, dock_pins);
 		spec->gen.auto_mute_via_amp = 1;
-- 
cgit v1.2.3


From 5579cd6f6629bc1e09b3b2d13ab7a1ed371c5ac2 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 22:22:41 +0200
Subject: ALSA: hda/realtek - Manage GPIO bits commonly

Currently the GPIO bits are managed by individual verbs in some cases
while toggled dynamically in other cases.  For simplifying the GPIO
management, define the GPIO mask, dir and data bits in alc_spec
fields, and refer to / set them consistently from all places.

As a first step, along with the definition of the new gpio_* fields,
this patch replaces the static verbs that are used at initialization
and fixups with the common helper functions.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 129 ++++++++++++++++++++++++++----------------
 1 file changed, 81 insertions(+), 48 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1f054e5ae2b3..489075b23652 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -46,9 +46,6 @@ enum {
 	ALC_INIT_UNDEFINED,
 	ALC_INIT_NONE,
 	ALC_INIT_DEFAULT,
-	ALC_INIT_GPIO1,
-	ALC_INIT_GPIO2,
-	ALC_INIT_GPIO3,
 };
 
 enum {
@@ -93,6 +90,11 @@ struct alc_spec {
 	struct alc_customize_define cdefine;
 	unsigned int parse_flags; /* flag for snd_hda_parse_pin_defcfg() */
 
+	/* GPIO bits */
+	unsigned int gpio_mask;
+	unsigned int gpio_dir;
+	unsigned int gpio_data;
+
 	/* mute LED for HP laptops, see alc269_fixup_mic_mute_hook() */
 	int mute_led_polarity;
 	hda_nid_t mute_led_nid;
@@ -220,27 +222,63 @@ static void add_mixer(struct alc_spec *spec, const struct snd_kcontrol_new *mix)
 /*
  * GPIO setup tables, used in initialization
  */
+
 /* Enable GPIO mask and set output */
-static const struct hda_verb alc_gpio1_init_verbs[] = {
-	{0x01, AC_VERB_SET_GPIO_MASK, 0x01},
-	{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01},
-	{0x01, AC_VERB_SET_GPIO_DATA, 0x01},
-	{ }
-};
+static void alc_setup_gpio(struct hda_codec *codec, unsigned int mask)
+{
+	struct alc_spec *spec = codec->spec;
 
-static const struct hda_verb alc_gpio2_init_verbs[] = {
-	{0x01, AC_VERB_SET_GPIO_MASK, 0x02},
-	{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x02},
-	{0x01, AC_VERB_SET_GPIO_DATA, 0x02},
-	{ }
-};
+	spec->gpio_mask |= mask;
+	spec->gpio_dir |= mask;
+	spec->gpio_data |= mask;
+}
 
-static const struct hda_verb alc_gpio3_init_verbs[] = {
-	{0x01, AC_VERB_SET_GPIO_MASK, 0x03},
-	{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x03},
-	{0x01, AC_VERB_SET_GPIO_DATA, 0x03},
-	{ }
-};
+static void alc_write_gpio_data(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
+			    spec->gpio_data);
+}
+
+static void alc_write_gpio(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (!spec->gpio_mask)
+		return;
+
+	snd_hda_codec_write(codec, codec->core.afg, 0,
+			    AC_VERB_SET_GPIO_MASK, spec->gpio_mask);
+	snd_hda_codec_write(codec, codec->core.afg, 0,
+			    AC_VERB_SET_GPIO_DIRECTION, spec->gpio_dir);
+	alc_write_gpio_data(codec);
+}
+
+static void alc_fixup_gpio(struct hda_codec *codec, int action,
+			   unsigned int mask)
+{
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		alc_setup_gpio(codec, mask);
+}
+
+static void alc_fixup_gpio1(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x01);
+}
+
+static void alc_fixup_gpio2(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x02);
+}
+
+static void alc_fixup_gpio3(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x03);
+}
 
 /*
  * Fix hardware PLL issue
@@ -448,16 +486,8 @@ static void alc_auto_init_amp(struct hda_codec *codec, int type)
 {
 	alc_fill_eapd_coef(codec);
 	alc_auto_setup_eapd(codec, true);
+	alc_write_gpio(codec);
 	switch (type) {
-	case ALC_INIT_GPIO1:
-		snd_hda_sequence_write(codec, alc_gpio1_init_verbs);
-		break;
-	case ALC_INIT_GPIO2:
-		snd_hda_sequence_write(codec, alc_gpio2_init_verbs);
-		break;
-	case ALC_INIT_GPIO3:
-		snd_hda_sequence_write(codec, alc_gpio3_init_verbs);
-		break;
 	case ALC_INIT_DEFAULT:
 		switch (codec->core.vendor_id) {
 		case 0x10ec0260:
@@ -660,13 +690,13 @@ do_sku:
 	if (spec->init_amp == ALC_INIT_UNDEFINED) {
 		switch (tmp) {
 		case 1:
-			spec->init_amp = ALC_INIT_GPIO1;
+			alc_setup_gpio(codec, 0x01);
 			break;
 		case 3:
-			spec->init_amp = ALC_INIT_GPIO2;
+			alc_setup_gpio(codec, 0x02);
 			break;
 		case 7:
-			spec->init_amp = ALC_INIT_GPIO3;
+			alc_setup_gpio(codec, 0x03);
 			break;
 		case 5:
 		default:
@@ -1107,12 +1137,12 @@ static void alc880_fixup_vol_knob(struct hda_codec *codec,
 
 static const struct hda_fixup alc880_fixups[] = {
 	[ALC880_FIXUP_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 	},
 	[ALC880_FIXUP_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio2_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio2,
 	},
 	[ALC880_FIXUP_MEDION_RIM] = {
 		.type = HDA_FIXUP_VERBS,
@@ -1565,7 +1595,7 @@ static void alc260_fixup_gpio1_toggle(struct hda_codec *codec,
 		spec->gen.autocfg.hp_pins[0] = 0x0f; /* copy it for automute */
 		snd_hda_jack_detect_enable_callback(codec, 0x0f,
 						    snd_hda_gen_hp_automute);
-		snd_hda_add_verbs(codec, alc_gpio1_init_verbs);
+		alc_setup_gpio(codec, 0x01);
 	}
 }
 
@@ -1639,8 +1669,8 @@ static const struct hda_fixup alc260_fixups[] = {
 		},
 	},
 	[ALC260_FIXUP_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 	},
 	[ALC260_FIXUP_GPIO1_TOGGLE] = {
 		.type = HDA_FIXUP_FUNC,
@@ -2144,20 +2174,20 @@ static const struct hda_fixup alc882_fixups[] = {
 		}
 	},
 	[ALC882_FIXUP_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 	},
 	[ALC882_FIXUP_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio2_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio2,
 	},
 	[ALC882_FIXUP_GPIO3] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio3_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio3,
 	},
 	[ALC882_FIXUP_ASUS_W2JC] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = alc_gpio1_init_verbs,
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc_fixup_gpio1,
 		.chained = true,
 		.chain_id = ALC882_FIXUP_EAPD,
 	},
@@ -5232,6 +5262,9 @@ static void alc282_fixup_asus_tx300(struct hda_codec *codec,
 		snd_hda_jack_detect_enable_callback(codec, 0x1b,
 						    snd_hda_gen_hp_automute);
 		break;
+	case HDA_FIXUP_ACT_PROBE:
+		spec->init_amp = ALC_INIT_DEFAULT;
+		break;
 	case HDA_FIXUP_ACT_BUILD:
 		/* this is a bit tricky; give more sane names for the main
 		 * (tablet) speaker and the dock speaker, respectively
-- 
cgit v1.2.3


From aaf312de4eb915e5b45c65c2da7304bf34b5ab47 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 22:28:22 +0200
Subject: ALSA: hda/realtek - Add GPIO data update helper

For updating GPIO bits dynamically, provide a new helper, and use it
from the alc260 automute hook.  This helper will be used by other
places in future, too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 489075b23652..bd54d9e25440 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -241,6 +241,20 @@ static void alc_write_gpio_data(struct hda_codec *codec)
 			    spec->gpio_data);
 }
 
+static void alc_update_gpio_data(struct hda_codec *codec, unsigned int mask,
+				 bool on)
+{
+	struct alc_spec *spec = codec->spec;
+	unsigned int oldval = spec->gpio_data;
+
+	if (on)
+		spec->gpio_data |= mask;
+	else
+		spec->gpio_data &= ~mask;
+	if (oldval != spec->gpio_data)
+		alc_write_gpio_data(codec);
+}
+
 static void alc_write_gpio(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -1577,8 +1591,8 @@ enum {
 static void alc260_gpio1_automute(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
-	snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
-			    spec->gen.hp_jack_present);
+
+	alc_update_gpio_data(codec, 0x01, spec->gen.hp_jack_present);
 }
 
 static void alc260_fixup_gpio1_toggle(struct hda_codec *codec,
-- 
cgit v1.2.3


From d261eec80ca987a2415dd26f982ca25844e4497c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 22:32:29 +0200
Subject: ALSA: hda/realtek - Consolidate gpio_data and gpio_led

Until now, two fields, gpio_data and gpio_led, coexist in alc_spec
although basically both of them serve for the same purpose -- the GPIO
data bits.

This patch consolidates both usages and eliminates the superfluous
gpio_led field.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 28 ++++------------------------
 1 file changed, 4 insertions(+), 24 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index bd54d9e25440..0db8329aa114 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -100,7 +100,6 @@ struct alc_spec {
 	hda_nid_t mute_led_nid;
 	hda_nid_t cap_mute_led_nid;
 
-	unsigned int gpio_led; /* used for alc269_fixup_hp_gpio_led() */
 	unsigned int gpio_mute_led_mask;
 	unsigned int gpio_mic_led_mask;
 
@@ -3497,9 +3496,8 @@ static int alc269_resume(struct hda_codec *codec)
 	 * suspend, and won't restore the data after resume, so we restore it
 	 * in the driver.
 	 */
-	if (spec->gpio_led)
-		snd_hda_codec_write(codec, codec->core.afg, 0, AC_VERB_SET_GPIO_DATA,
-			    spec->gpio_led);
+	if (spec->gpio_data)
+		alc_write_gpio_data(codec);
 
 	if (spec->has_alc5505_dsp)
 		alc5505_dsp_resume(codec);
@@ -3739,18 +3737,10 @@ static void alc_update_gpio_led(struct hda_codec *codec, unsigned int mask,
 				bool enabled)
 {
 	struct alc_spec *spec = codec->spec;
-	unsigned int oldval = spec->gpio_led;
 
 	if (spec->mute_led_polarity)
 		enabled = !enabled;
-
-	if (enabled)
-		spec->gpio_led &= ~mask;
-	else
-		spec->gpio_led |= mask;
-	if (spec->gpio_led != oldval)
-		snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
-				    spec->gpio_led);
+	alc_update_gpio_data(codec, mask, !enabled); /* muted -> LED on */
 }
 
 /* turn on/off mute LED via GPIO per vmaster hook */
@@ -3783,7 +3773,6 @@ static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->gpio_mic_led_mask = 0x10;
@@ -3804,7 +3793,6 @@ static void alc286_fixup_hp_gpio_led(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x02;
 		spec->gpio_mic_led_mask = 0x20;
@@ -3842,7 +3830,6 @@ static void alc269_fixup_hp_gpio_mic1_led(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->cap_mute_led_nid = 0x18;
@@ -3865,7 +3852,6 @@ static void alc280_fixup_hp_gpio4(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->cap_mute_led_nid = 0x18;
@@ -3948,7 +3934,6 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 						    gpio2_mic_hotkey_event);
 
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mute_led_mask = 0x08;
 		spec->gpio_mic_led_mask = 0x10;
@@ -3988,7 +3973,6 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 		snd_hda_jack_detect_enable_callback(codec, 0x1b,
 						    gpio2_mic_hotkey_event);
 
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 0;
 		spec->gpio_mic_led_mask = 0x04;
 		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
@@ -5365,9 +5349,6 @@ static void alc280_fixup_hp_9480m(struct hda_codec *codec,
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
 		spec->gen.hp_automute_hook = alc280_hp_gpio4_automute_hook;
 
-		/* The GPIOs are currently off */
-		spec->gpio_led = 0;
-
 		/* GPIO3 is connected to the output mute LED,
 		 * high is on, low is off
 		 */
@@ -7592,7 +7573,7 @@ static unsigned int gpio_led_power_filter(struct hda_codec *codec,
 					  unsigned int power_state)
 {
 	struct alc_spec *spec = codec->spec;
-	if (nid == codec->core.afg && power_state == AC_PWRST_D3 && spec->gpio_led)
+	if (nid == codec->core.afg && power_state == AC_PWRST_D3 && spec->gpio_data)
 		return AC_PWRST_D0;
 	return power_state;
 }
@@ -7609,7 +7590,6 @@ static void alc662_fixup_led_gpio1(struct hda_codec *codec,
 
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->gpio_led = 0;
 		spec->mute_led_polarity = 1;
 		spec->gpio_mute_led_mask = 0x01;
 		snd_hda_add_verbs(codec, gpio_init);
-- 
cgit v1.2.3


From 215c850cf205fa502aa45c2540b8d8bc70bd0f1e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 22:34:26 +0200
Subject: ALSA: hda/realtek - Simplify alc885_fixup_macpro_gpio()

The fixup for Macbook Pro is nothing but setting the GPIO bits as
usual but with one exception: it adds some delay at writing the GPIO
bits.

Add a flag to put the conditional delay in the common helper, and
clean up alc885_fixup_macpro_gpio() with the new flag.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 44 +++++++------------------------------------
 1 file changed, 7 insertions(+), 37 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 0db8329aa114..786b29eb2ba9 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -94,6 +94,7 @@ struct alc_spec {
 	unsigned int gpio_mask;
 	unsigned int gpio_dir;
 	unsigned int gpio_data;
+	bool gpio_write_delay;	/* add a delay before writing gpio_data */
 
 	/* mute LED for HP laptops, see alc269_fixup_mic_mute_hook() */
 	int mute_led_polarity;
@@ -265,6 +266,8 @@ static void alc_write_gpio(struct hda_codec *codec)
 			    AC_VERB_SET_GPIO_MASK, spec->gpio_mask);
 	snd_hda_codec_write(codec, codec->core.afg, 0,
 			    AC_VERB_SET_GPIO_DIRECTION, spec->gpio_dir);
+	if (spec->gpio_write_delay)
+		msleep(1);
 	alc_write_gpio_data(codec);
 }
 
@@ -1868,47 +1871,14 @@ static void alc889_fixup_coef(struct hda_codec *codec,
 	alc_update_coef_idx(codec, 7, 0, 0x2030);
 }
 
-/* toggle speaker-output according to the hp-jack state */
-static void alc882_gpio_mute(struct hda_codec *codec, int pin, int muted)
-{
-	unsigned int gpiostate, gpiomask, gpiodir;
-
-	gpiostate = snd_hda_codec_read(codec, codec->core.afg, 0,
-				       AC_VERB_GET_GPIO_DATA, 0);
-
-	if (!muted)
-		gpiostate |= (1 << pin);
-	else
-		gpiostate &= ~(1 << pin);
-
-	gpiomask = snd_hda_codec_read(codec, codec->core.afg, 0,
-				      AC_VERB_GET_GPIO_MASK, 0);
-	gpiomask |= (1 << pin);
-
-	gpiodir = snd_hda_codec_read(codec, codec->core.afg, 0,
-				     AC_VERB_GET_GPIO_DIRECTION, 0);
-	gpiodir |= (1 << pin);
-
-
-	snd_hda_codec_write(codec, codec->core.afg, 0,
-			    AC_VERB_SET_GPIO_MASK, gpiomask);
-	snd_hda_codec_write(codec, codec->core.afg, 0,
-			    AC_VERB_SET_GPIO_DIRECTION, gpiodir);
-
-	msleep(1);
-
-	snd_hda_codec_write(codec, codec->core.afg, 0,
-			    AC_VERB_SET_GPIO_DATA, gpiostate);
-}
-
 /* set up GPIO at initialization */
 static void alc885_fixup_macpro_gpio(struct hda_codec *codec,
 				     const struct hda_fixup *fix, int action)
 {
-	if (action != HDA_FIXUP_ACT_INIT)
-		return;
-	alc882_gpio_mute(codec, 0, 0);
-	alc882_gpio_mute(codec, 1, 0);
+	struct alc_spec *spec = codec->spec;
+
+	spec->gpio_write_delay = true;
+	alc_fixup_gpio3(codec, fix, action);
 }
 
 /* Fix the connection of some pins for ALC889:
-- 
cgit v1.2.3


From 01e4a275e93bc955d0b79520156da6367505658f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 22:47:30 +0200
Subject: ALSA: hda/realtek - Simplify mute LED GPIO handling

Now we can simplify the mute LED GPIO handling as well.  Each fixup
dealing with GPIO for the mute LED controls defined the static init
verbs, and they are converted to the common GPIO bit fields with the
new helper, alc_fixup_hp_gpio_led().

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 149 +++++++++++++-----------------------------
 1 file changed, 46 insertions(+), 103 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 786b29eb2ba9..a0881ffcd9d7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3731,44 +3731,38 @@ static void alc_gpio_micmute_update(struct hda_codec *codec)
 			    spec->gen.micmute_led.led_value);
 }
 
-static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
-				const struct hda_fixup *fix, int action)
+/* setup mute and mic-mute GPIO bits, add hooks appropriately */
+static void alc_fixup_hp_gpio_led(struct hda_codec *codec,
+				  int action,
+				  unsigned int mute_mask,
+				  unsigned int micmute_mask)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x18 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x18 },
-		{}
-	};
 
-	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+	alc_fixup_gpio(codec, action, mute_mask | micmute_mask);
+
+	if (action != HDA_FIXUP_ACT_PRE_PROBE)
+		return;
+	if (mute_mask) {
+		spec->gpio_mute_led_mask = mute_mask;
 		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
-		spec->gpio_mic_led_mask = 0x10;
-		snd_hda_add_verbs(codec, gpio_init);
+	}
+	if (micmute_mask) {
+		spec->gpio_mic_led_mask = micmute_mask;
 		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 	}
 }
 
-static void alc286_fixup_hp_gpio_led(struct hda_codec *codec,
+static void alc269_fixup_hp_gpio_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
-	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x22 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x22 },
-		{}
-	};
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0x10);
+}
 
-	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x02;
-		spec->gpio_mic_led_mask = 0x20;
-		snd_hda_add_verbs(codec, gpio_init);
-		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
-	}
+static void alc286_fixup_hp_gpio_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	alc_fixup_hp_gpio_led(codec, action, 0x02, 0x20);
 }
 
 /* turn on/off mic-mute LED per capture hook */
@@ -3792,18 +3786,15 @@ static void alc269_fixup_hp_gpio_mic1_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x08 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x08 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
+		/* Like hp_gpio_mic1_led, but also needs GPIO4 low to
+		 * enable headphone amp
+		 */
+		spec->gpio_mask |= 0x10;
+		spec->gpio_dir |= 0x10;
 		spec->cap_mute_led_nid = 0x18;
-		snd_hda_add_verbs(codec, gpio_init);
 		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 		codec->power_filter = led_power_filter;
 	}
@@ -3812,20 +3803,11 @@ static void alc269_fixup_hp_gpio_mic1_led(struct hda_codec *codec,
 static void alc280_fixup_hp_gpio4(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
-	/* Like hp_gpio_mic1_led, but also needs GPIO4 low to enable headphone amp */
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x18 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x18 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
 		spec->cap_mute_led_nid = 0x18;
-		snd_hda_add_verbs(codec, gpio_init);
 		snd_hda_gen_add_micmute_led(codec, alc_cap_micmute_update);
 		codec->power_filter = led_power_filter;
 	}
@@ -3876,38 +3858,29 @@ static int alc_register_micmute_input_device(struct hda_codec *codec)
 	return 0;
 }
 
+/* GPIO1 = set according to SKU external amp
+ * GPIO2 = mic mute hotkey
+ * GPIO3 = mute LED
+ * GPIO4 = mic mute LED
+ */
 static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 					     const struct hda_fixup *fix, int action)
 {
-	/* GPIO1 = set according to SKU external amp
-	   GPIO2 = mic mute hotkey
-	   GPIO3 = mute LED
-	   GPIO4 = mic mute LED */
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x1e },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x1a },
-		{ 0x01, AC_VERB_SET_GPIO_DATA, 0x02 },
-		{}
-	};
-
 	struct alc_spec *spec = codec->spec;
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0x10);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->init_amp = ALC_INIT_DEFAULT;
 		if (alc_register_micmute_input_device(codec) != 0)
 			return;
 
-		snd_hda_add_verbs(codec, gpio_init);
+		spec->gpio_mask |= 0x06;
+		spec->gpio_dir |= 0x02;
+		spec->gpio_data |= 0x02;
 		snd_hda_codec_write_cache(codec, codec->core.afg, 0,
 					  AC_VERB_SET_GPIO_UNSOLICITED_RSP_MASK, 0x04);
 		snd_hda_jack_detect_enable_callback(codec, codec->core.afg,
 						    gpio2_mic_hotkey_event);
-
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
-		spec->gpio_mic_led_mask = 0x10;
-		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 		return;
 	}
 
@@ -3921,31 +3894,22 @@ static void alc280_fixup_hp_gpio2_mic_hotkey(struct hda_codec *codec,
 	}
 }
 
+/* Line2 = mic mute hotkey
+ * GPIO2 = mic mute LED
+ */
 static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 					     const struct hda_fixup *fix, int action)
 {
-	/* Line2 = mic mute hotkey
-	   GPIO2 = mic mute LED */
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
-		{}
-	};
-
 	struct alc_spec *spec = codec->spec;
 
+	alc_fixup_hp_gpio_led(codec, action, 0, 0x04);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		spec->init_amp = ALC_INIT_DEFAULT;
 		if (alc_register_micmute_input_device(codec) != 0)
 			return;
 
-		snd_hda_add_verbs(codec, gpio_init);
 		snd_hda_jack_detect_enable_callback(codec, 0x1b,
 						    gpio2_mic_hotkey_event);
-
-		spec->mute_led_polarity = 0;
-		spec->gpio_mic_led_mask = 0x04;
-		snd_hda_gen_add_micmute_led(codec, alc_gpio_micmute_update);
 		return;
 	}
 
@@ -5306,27 +5270,13 @@ static void alc280_fixup_hp_9480m(struct hda_codec *codec,
 				  int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x18 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x18 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x08, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		/* Set the hooks to turn the headphone amp on/off
-		 * as needed
-		 */
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
+		/* amp at GPIO4; toggled via alc280_hp_gpio4_automute_hook() */
+		spec->gpio_mask |= 0x10;
+		spec->gpio_dir |= 0x10;
 		spec->gen.hp_automute_hook = alc280_hp_gpio4_automute_hook;
-
-		/* GPIO3 is connected to the output mute LED,
-		 * high is on, low is off
-		 */
-		spec->mute_led_polarity = 0;
-		spec->gpio_mute_led_mask = 0x08;
-
-		/* Initialize GPIO configuration */
-		snd_hda_add_verbs(codec, gpio_init);
 	}
 }
 
@@ -7552,17 +7502,10 @@ static void alc662_fixup_led_gpio1(struct hda_codec *codec,
 				   const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	static const struct hda_verb gpio_init[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x01 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01 },
-		{}
-	};
 
+	alc_fixup_hp_gpio_led(codec, action, 0x01, 0);
 	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
-		spec->gen.vmaster_mute.hook = alc_fixup_gpio_mute_hook;
 		spec->mute_led_polarity = 1;
-		spec->gpio_mute_led_mask = 0x01;
-		snd_hda_add_verbs(codec, gpio_init);
 		codec->power_filter = gpio_led_power_filter;
 	}
 }
-- 
cgit v1.2.3


From ae065f1ce07c09600af0e1dbb6b071991f7cb6e5 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 23:00:03 +0200
Subject: ALSA: hda/realtek - Convert some manual GPIO setups

This patch converts the remaining static init verbs for GPIO bits with
the common gpio_* fields management.  Only the verbs setting the GPIO
data bits are targeted in this patch.  The rest will be changed in
later patches.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 49 +++++++++++++++++++++++--------------------
 1 file changed, 26 insertions(+), 23 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a0881ffcd9d7..f5cc506504c0 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -296,6 +296,12 @@ static void alc_fixup_gpio3(struct hda_codec *codec,
 	alc_fixup_gpio(codec, action, 0x03);
 }
 
+static void alc_fixup_gpio4(struct hda_codec *codec,
+			    const struct hda_fixup *fix, int action)
+{
+	alc_fixup_gpio(codec, action, 0x04);
+}
+
 /*
  * Fix hardware PLL issue
  * On some codecs, the analog PLL gating control must be off while
@@ -5172,13 +5178,6 @@ static void alc282_fixup_asus_tx300(struct hda_codec *codec,
 				    const struct hda_fixup *fix, int action)
 {
 	struct alc_spec *spec = codec->spec;
-	/* TX300 needs to set up GPIO2 for the speaker amp */
-	static const struct hda_verb gpio2_verbs[] = {
-		{ 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
-		{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
-		{ 0x01, AC_VERB_SET_GPIO_DATA, 0x04 },
-		{}
-	};
 	static const struct hda_pintbl dock_pins[] = {
 		{ 0x1b, 0x21114000 }, /* dock speaker pin */
 		{}
@@ -5187,7 +5186,8 @@ static void alc282_fixup_asus_tx300(struct hda_codec *codec,
 	switch (action) {
 	case HDA_FIXUP_ACT_PRE_PROBE:
 		spec->init_amp = ALC_INIT_DEFAULT;
-		snd_hda_add_verbs(codec, gpio2_verbs);
+		/* TX300 needs to set up GPIO2 for the speaker amp */
+		alc_setup_gpio(codec, 0x04);
 		snd_hda_apply_pincfgs(codec, dock_pins);
 		spec->gen.auto_mute_via_amp = 1;
 		spec->gen.automute_hook = asus_tx300_automute;
@@ -5280,6 +5280,19 @@ static void alc280_fixup_hp_9480m(struct hda_codec *codec,
 	}
 }
 
+static void alc275_fixup_gpio4_off(struct hda_codec *codec,
+				   const struct hda_fixup *fix,
+				   int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->gpio_mask |= 0x04;
+		spec->gpio_dir |= 0x04;
+		/* set data bit low */
+	}
+}
+
 static void alc233_alc662_fixup_lenovo_dual_codecs(struct hda_codec *codec,
 					 const struct hda_fixup *fix,
 					 int action)
@@ -5468,13 +5481,8 @@ static const struct hda_fixup alc269_fixups[] = {
 		}
 	},
 	[ALC275_FIXUP_SONY_VAIO_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			{0x01, AC_VERB_SET_GPIO_MASK, 0x04},
-			{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04},
-			{0x01, AC_VERB_SET_GPIO_DATA, 0x00},
-			{ }
-		},
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc275_fixup_gpio4_off,
 		.chained = true,
 		.chain_id = ALC269_FIXUP_SONY_VAIO
 	},
@@ -6219,14 +6227,9 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chain_id = ALC256_FIXUP_ASUS_HEADSET_MODE
 	},
 	[ALC256_FIXUP_ASUS_AIO_GPIO2] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			/* Set up GPIO2 for the speaker amp */
-			{ 0x01, AC_VERB_SET_GPIO_MASK, 0x04 },
-			{ 0x01, AC_VERB_SET_GPIO_DIRECTION, 0x04 },
-			{ 0x01, AC_VERB_SET_GPIO_DATA, 0x04 },
-			{}
-		},
+		.type = HDA_FIXUP_FUNC,
+		/* Set up GPIO2 for the speaker amp */
+		.v.func = alc_fixup_gpio4,
 	},
 	[ALC233_FIXUP_ASUS_MIC_NO_PRESENCE] = {
 		.type = HDA_FIXUP_PINS,
-- 
cgit v1.2.3


From d44a68640668544891fc4b468284d1eaeb49c1d8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 23:04:03 +0200
Subject: ALSA: hda/realtek - Simplify Dell XPS13 GPIO handling

Dell XPS13 has multi-step fixups, and one of them
(ALC288_FIXUP_DELL_XPS_13_GPIO6) corresponds to the management of GPIO
bit6 (0x40).  It used to be a static init verbs (to turn *off* the
bit6).

In this patch, we convert it as the gpio_mask and gpio_dir
initializations folded in the existing fixup function.  With this
change, ALC288_FIXUP_DELL_XPS_13_GPIO6 becomes superfluous, thus it's
removed.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 24 ++++++------------------
 1 file changed, 6 insertions(+), 18 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f5cc506504c0..2cda4a614435 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4881,13 +4881,10 @@ static void alc288_update_headset_jack_cb(struct hda_codec *codec,
 				       struct hda_jack_callback *jack)
 {
 	struct alc_spec *spec = codec->spec;
-	int present;
 
 	alc_update_headset_jack_cb(codec, jack);
 	/* Headset Mic enable or disable, only for Dell Dino */
-	present = spec->gen.hp_jack_present ? 0x40 : 0;
-	snd_hda_codec_write(codec, 0x01, 0, AC_VERB_SET_GPIO_DATA,
-				present);
+	alc_update_gpio_data(codec, 0x40, spec->gen.hp_jack_present);
 }
 
 static void alc_fixup_headset_mode_dell_alc288(struct hda_codec *codec,
@@ -4896,6 +4893,9 @@ static void alc_fixup_headset_mode_dell_alc288(struct hda_codec *codec,
 	alc_fixup_headset_mode(codec, fix, action);
 	if (action == HDA_FIXUP_ACT_PROBE) {
 		struct alc_spec *spec = codec->spec;
+		/* toggled via hp_automute_hook */
+		spec->gpio_mask |= 0x40;
+		spec->gpio_dir |= 0x40;
 		spec->gen.hp_automute_hook = alc288_update_headset_jack_cb;
 	}
 }
@@ -5433,7 +5433,6 @@ enum {
 	ALC280_FIXUP_HP_9480M,
 	ALC288_FIXUP_DELL_HEADSET_MODE,
 	ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
-	ALC288_FIXUP_DELL_XPS_13_GPIO6,
 	ALC288_FIXUP_DELL_XPS_13,
 	ALC288_FIXUP_DISABLE_AAMIX,
 	ALC292_FIXUP_DELL_E7X,
@@ -6049,22 +6048,11 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC288_FIXUP_DELL_HEADSET_MODE
 	},
-	[ALC288_FIXUP_DELL_XPS_13_GPIO6] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			{0x01, AC_VERB_SET_GPIO_MASK, 0x40},
-			{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x40},
-			{0x01, AC_VERB_SET_GPIO_DATA, 0x00},
-			{ }
-		},
-		.chained = true,
-		.chain_id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE
-	},
 	[ALC288_FIXUP_DISABLE_AAMIX] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_disable_aamix,
 		.chained = true,
-		.chain_id = ALC288_FIXUP_DELL_XPS_13_GPIO6
+		.chain_id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE
 	},
 	[ALC288_FIXUP_DELL_XPS_13] = {
 		.type = HDA_FIXUP_FUNC,
@@ -6902,7 +6890,7 @@ static const struct snd_hda_pin_quirk alc269_pin_fixup_tbl[] = {
 		{0x12, 0x90a60130},
 		{0x19, 0x03a11020},
 		{0x21, 0x0321101f}),
-	SND_HDA_PIN_QUIRK(0x10ec0288, 0x1028, "Dell", ALC288_FIXUP_DELL_XPS_13_GPIO6,
+	SND_HDA_PIN_QUIRK(0x10ec0288, 0x1028, "Dell", ALC288_FIXUP_DELL1_MIC_NO_PRESENCE,
 		{0x12, 0x90a60120},
 		{0x14, 0x90170110},
 		{0x21, 0x0321101f}),
-- 
cgit v1.2.3


From df73d83fad97237b68949058e632b48d55533c09 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 19 Jun 2018 23:05:47 +0200
Subject: ALSA: hda/realtek - Use common GPIO mask for ALC660VD ASUS fixup

The ALC660VD_FIX_ASUS_GPIO1 quirk requires to set up GPIO bit0 ON
while bit 1 OFF.  Implement the fixup function and convert from the
static init verbs.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2cda4a614435..1ee086bcefcf 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7354,16 +7354,21 @@ static void alc861vd_fixup_dallas(struct hda_codec *codec,
 	}
 }
 
+/* reset GPIO1 */
+static void alc660vd_fixup_asus_gpio1(struct hda_codec *codec,
+				      const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->gpio_mask |= 0x02;
+	alc_fixup_gpio(codec, action, 0x01);
+}
+
 static const struct hda_fixup alc861vd_fixups[] = {
 	[ALC660VD_FIX_ASUS_GPIO1] = {
-		.type = HDA_FIXUP_VERBS,
-		.v.verbs = (const struct hda_verb[]) {
-			/* reset GPIO1 */
-			{0x01, AC_VERB_SET_GPIO_MASK, 0x03},
-			{0x01, AC_VERB_SET_GPIO_DIRECTION, 0x01},
-			{0x01, AC_VERB_SET_GPIO_DATA, 0x01},
-			{ }
-		}
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc660vd_fixup_asus_gpio1,
 	},
 	[ALC861VD_FIX_DALLAS] = {
 		.type = HDA_FIXUP_FUNC,
-- 
cgit v1.2.3


From a5cb463a81737dde1ef3f1b1cf3e17bf69f20669 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Jun 2018 12:50:11 +0200
Subject: ALSA: hda/realtek - Use common helper for creating ALC268 beep
 controls

The beep mixer controls are the only remaining stuff that uses
spec->mixers[] array, and they can be well converted to the standard
helper in the generic parser, snd_hda_gen_add_kctl().

This simplifies the code, especially the superfluous mixers and
num_mixers fields can be now removed from alc_spec.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 33 +++++++++------------------------
 1 file changed, 9 insertions(+), 24 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 1ee086bcefcf..42d3b0f77577 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -83,8 +83,6 @@ struct alc_spec {
 	struct hda_gen_spec gen; /* must be at head */
 
 	/* codec parameterization */
-	const struct snd_kcontrol_new *mixers[5];	/* mixer arrays */
-	unsigned int num_mixers;
 	unsigned int beep_amp;	/* beep amp value, set via set_beep_amp() */
 
 	struct alc_customize_define cdefine;
@@ -207,18 +205,6 @@ static void alc_process_coef_fw(struct hda_codec *codec,
 	}
 }
 
-/*
- * Append the given mixer and verb elements for the later use
- * The mixer array is referred in build_controls(), and init_verbs are
- * called in init().
- */
-static void add_mixer(struct alc_spec *spec, const struct snd_kcontrol_new *mix)
-{
-	if (snd_BUG_ON(spec->num_mixers >= ARRAY_SIZE(spec->mixers)))
-		return;
-	spec->mixers[spec->num_mixers++] = mix;
-}
-
 /*
  * GPIO setup tables, used in initialization
  */
@@ -789,18 +775,12 @@ static const struct snd_kcontrol_new alc_beep_mixer[] = {
 static int alc_build_controls(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
-	int i, err;
+	int err;
 
 	err = snd_hda_gen_build_controls(codec);
 	if (err < 0)
 		return err;
 
-	for (i = 0; i < spec->num_mixers; i++) {
-		err = snd_hda_add_new_ctls(codec, spec->mixers[i]);
-		if (err < 0)
-			return err;
-	}
-
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
 	/* create beep controls if needed */
 	if (spec->beep_amp) {
@@ -2663,7 +2643,6 @@ static const struct snd_kcontrol_new alc268_beep_mixer[] = {
 		.put = alc268_beep_switch_put,
 		.private_value = HDA_COMPOSE_AMP_VAL(0x0f, 3, 1, HDA_INPUT)
 	},
-	{ }
 };
 
 /* set PCBEEP vol = 0, mute connections */
@@ -2731,7 +2710,7 @@ static int alc268_parse_auto_config(struct hda_codec *codec)
 static int patch_alc268(struct hda_codec *codec)
 {
 	struct alc_spec *spec;
-	int err;
+	int i, err;
 
 	/* ALC268 has no aa-loopback mixer */
 	err = alc_alloc_spec(codec, 0);
@@ -2753,7 +2732,13 @@ static int patch_alc268(struct hda_codec *codec)
 
 	if (err > 0 && !spec->gen.no_analog &&
 	    spec->gen.autocfg.speaker_pins[0] != 0x1d) {
-		add_mixer(spec, alc268_beep_mixer);
+		for (i = 0; i < ARRAY_SIZE(alc268_beep_mixer); i++) {
+			if (!snd_hda_gen_add_kctl(&spec->gen, NULL,
+						  &alc268_beep_mixer[i])) {
+				err = -ENOMEM;
+				goto error;
+			}
+		}
 		snd_hda_add_verbs(codec, alc268_beep_init_verbs);
 		if (!query_amp_caps(codec, 0x1d, HDA_INPUT))
 			/* override the amp caps for beep generator */
-- 
cgit v1.2.3


From fea80fae552c428b67591cb0aacca56c11c3eeaf Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Jun 2018 12:52:46 +0200
Subject: ALSA: hda/realtek - Use common helper for creating beep controls

In the Realtek codec driver, we used to build kctl elements for beep
mixer in the own build_controls callback.  This is an open-code and
can be covered by the standard feature of the generic parser with
snd_hda_gen_add_kctl() instead.

Also, after the conversion, spec->beep_amp becomes superfluous; hence
it's removed along with the conversion.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 114 ++++++++++++++++++++++++------------------
 1 file changed, 65 insertions(+), 49 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 42d3b0f77577..0e84d9cdd42d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -83,8 +83,6 @@ struct alc_spec {
 	struct hda_gen_spec gen; /* must be at head */
 
 	/* codec parameterization */
-	unsigned int beep_amp;	/* beep amp value, set via set_beep_amp() */
-
 	struct alc_customize_define cdefine;
 	unsigned int parse_flags; /* flag for snd_hda_parse_pin_defcfg() */
 
@@ -763,41 +761,14 @@ static void alc_fixup_inv_dmic(struct hda_codec *codec,
 }
 
 
-#ifdef CONFIG_SND_HDA_INPUT_BEEP
-/* additional beep mixers; the actual parameters are overwritten at build */
-static const struct snd_kcontrol_new alc_beep_mixer[] = {
-	HDA_CODEC_VOLUME("Beep Playback Volume", 0, 0, HDA_INPUT),
-	HDA_CODEC_MUTE_BEEP("Beep Playback Switch", 0, 0, HDA_INPUT),
-	{ } /* end */
-};
-#endif
-
 static int alc_build_controls(struct hda_codec *codec)
 {
-	struct alc_spec *spec = codec->spec;
 	int err;
 
 	err = snd_hda_gen_build_controls(codec);
 	if (err < 0)
 		return err;
 
-#ifdef CONFIG_SND_HDA_INPUT_BEEP
-	/* create beep controls if needed */
-	if (spec->beep_amp) {
-		const struct snd_kcontrol_new *knew;
-		for (knew = alc_beep_mixer; knew->name; knew++) {
-			struct snd_kcontrol *kctl;
-			kctl = snd_ctl_new1(knew, codec);
-			if (!kctl)
-				return -ENOMEM;
-			kctl->private_value = spec->beep_amp;
-			err = snd_hda_ctl_add(codec, 0, kctl);
-			if (err < 0)
-				return err;
-		}
-	}
-#endif
-
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_BUILD);
 	return 0;
 }
@@ -1008,8 +979,30 @@ static int alc_codec_rename_from_preset(struct hda_codec *codec)
  * Digital-beep handlers
  */
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
-#define set_beep_amp(spec, nid, idx, dir) \
-	((spec)->beep_amp = HDA_COMPOSE_AMP_VAL(nid, 3, idx, dir))
+
+/* additional beep mixers; private_value will be overwritten */
+static const struct snd_kcontrol_new alc_beep_mixer[] = {
+	HDA_CODEC_VOLUME("Beep Playback Volume", 0, 0, HDA_INPUT),
+	HDA_CODEC_MUTE_BEEP("Beep Playback Switch", 0, 0, HDA_INPUT),
+};
+
+/* set up and create beep controls */
+static int set_beep_amp(struct alc_spec *spec, hda_nid_t nid,
+			int idx, int dir)
+{
+	struct snd_kcontrol_new *knew;
+	unsigned int beep_amp = HDA_COMPOSE_AMP_VAL(nid, 3, idx, dir);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(alc_beep_mixer); i++) {
+		knew = snd_hda_gen_add_kctl(&spec->gen, NULL,
+					    &alc_beep_mixer[i]);
+		if (!knew)
+			return -ENOMEM;
+		knew->private_value = beep_amp;
+	}
+	return 0;
+}
 
 static const struct snd_pci_quirk beep_white_list[] = {
 	SND_PCI_QUIRK(0x1043, 0x103c, "ASUS", 1),
@@ -1034,7 +1027,7 @@ static inline int has_cdefine_beep(struct hda_codec *codec)
 	return spec->cdefine.enable_pcbeep;
 }
 #else
-#define set_beep_amp(spec, nid, idx, dir) /* NOP */
+#define set_beep_amp(spec, nid, idx, dir)	0
 #define has_cdefine_beep(codec)		0
 #endif
 
@@ -1536,8 +1529,11 @@ static int patch_alc880(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -1784,8 +1780,11 @@ static int patch_alc260(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x07, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x07, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -2434,8 +2433,11 @@ static int patch_alc882(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog && spec->gen.beep_nid)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog && spec->gen.beep_nid) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -2596,8 +2598,11 @@ static int patch_alc262(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog && spec->gen.beep_nid)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog && spec->gen.beep_nid) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -7168,8 +7173,11 @@ static int patch_alc269(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog && spec->gen.beep_nid && spec->gen.mixer_nid)
-		set_beep_amp(spec, spec->gen.mixer_nid, 0x04, HDA_INPUT);
+	if (!spec->gen.no_analog && spec->gen.beep_nid && spec->gen.mixer_nid) {
+		err = set_beep_amp(spec, spec->gen.mixer_nid, 0x04, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -7298,8 +7306,11 @@ static int patch_alc861(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x23, 0, HDA_OUTPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x23, 0, HDA_OUTPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -7392,8 +7403,11 @@ static int patch_alc861vd(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
-	if (!spec->gen.no_analog)
-		set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+	if (!spec->gen.no_analog) {
+		err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+		if (err < 0)
+			goto error;
+	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
 
@@ -8103,18 +8117,20 @@ static int patch_alc662(struct hda_codec *codec)
 	if (!spec->gen.no_analog && spec->gen.beep_nid) {
 		switch (codec->core.vendor_id) {
 		case 0x10ec0662:
-			set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
+			err = set_beep_amp(spec, 0x0b, 0x05, HDA_INPUT);
 			break;
 		case 0x10ec0272:
 		case 0x10ec0663:
 		case 0x10ec0665:
 		case 0x10ec0668:
-			set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT);
+			err = set_beep_amp(spec, 0x0b, 0x04, HDA_INPUT);
 			break;
 		case 0x10ec0273:
-			set_beep_amp(spec, 0x0b, 0x03, HDA_INPUT);
+			err = set_beep_amp(spec, 0x0b, 0x03, HDA_INPUT);
 			break;
 		}
+		if (err < 0)
+			goto error;
 	}
 
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PROBE);
-- 
cgit v1.2.3


From 51e19ca5f7555802687324d3bee3bc6b7df240d4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Jun 2018 17:06:58 +0200
Subject: ALSA: hda/conexant - Clean up beep code

Like the previous commit for Realtek codec, the similar cleanup work
can be applied to Conexant codec, too.  A slight difference is that
the call of cx_auto_parse_beep() is moved after
snd_hda_gen_parse_auto_config().  It's not strictly needed, but it'd
be good to make the creation of such beep mixers at the end, which
matches with the former situation.

Along with this conversion, cx_auto_build_controls() becomes just
calling snd_hda_gen_build_controls(), so it's simply replaced with
snd_hda_gen_build_controls.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_conexant.c | 85 ++++++++++++++----------------------------
 1 file changed, 27 insertions(+), 58 deletions(-)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index b7339cb5c45b..75ba66eb4ccd 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -37,8 +37,6 @@
 struct conexant_spec {
 	struct hda_gen_spec gen;
 
-	unsigned int beep_amp;
-
 	/* extra EAPD pins */
 	unsigned int num_eapds;
 	hda_nid_t eapds[4];
@@ -62,65 +60,48 @@ struct conexant_spec {
 
 
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
-static inline void set_beep_amp(struct conexant_spec *spec, hda_nid_t nid,
-				int idx, int dir)
-{
-	spec->gen.beep_nid = nid;
-	spec->beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
-}
-/* additional beep mixers; the actual parameters are overwritten at build */
+/* additional beep mixers; private_value will be overwritten */
 static const struct snd_kcontrol_new cxt_beep_mixer[] = {
 	HDA_CODEC_VOLUME_MONO("Beep Playback Volume", 0, 1, 0, HDA_OUTPUT),
 	HDA_CODEC_MUTE_BEEP_MONO("Beep Playback Switch", 0, 1, 0, HDA_OUTPUT),
-	{ } /* end */
 };
 
-/* create beep controls if needed */
-static int add_beep_ctls(struct hda_codec *codec)
+static int set_beep_amp(struct conexant_spec *spec, hda_nid_t nid,
+			int idx, int dir)
 {
-	struct conexant_spec *spec = codec->spec;
-	int err;
+	struct snd_kcontrol_new *knew;
+	unsigned int beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
+	int i;
 
-	if (spec->beep_amp) {
-		const struct snd_kcontrol_new *knew;
-		for (knew = cxt_beep_mixer; knew->name; knew++) {
-			struct snd_kcontrol *kctl;
-			kctl = snd_ctl_new1(knew, codec);
-			if (!kctl)
-				return -ENOMEM;
-			kctl->private_value = spec->beep_amp;
-			err = snd_hda_ctl_add(codec, 0, kctl);
-			if (err < 0)
-				return err;
-		}
+	spec->gen.beep_nid = nid;
+	for (i = 0; i < ARRAY_SIZE(cxt_beep_mixer); i++) {
+		knew = snd_hda_gen_add_kctl(&spec->gen, NULL,
+					    &cxt_beep_mixer[i]);
+		if (!knew)
+			return -ENOMEM;
+		knew->private_value = beep_amp;
 	}
 	return 0;
 }
-#else
-#define set_beep_amp(spec, nid, idx, dir) /* NOP */
-#define add_beep_ctls(codec)	0
-#endif
 
-/*
- * Automatic parser for CX20641 & co
- */
-
-#ifdef CONFIG_SND_HDA_INPUT_BEEP
-static void cx_auto_parse_beep(struct hda_codec *codec)
+static int cx_auto_parse_beep(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
 	hda_nid_t nid;
 
 	for_each_hda_codec_node(nid, codec)
-		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP) {
-			set_beep_amp(spec, nid, 0, HDA_OUTPUT);
-			break;
-		}
+		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP)
+			return set_beep_amp(spec, nid, 0, HDA_OUTPUT);
+	return 0;
 }
 #else
-#define cx_auto_parse_beep(codec)
+#define cx_auto_parse_beep(codec)	0
 #endif
 
+/*
+ * Automatic parser for CX20641 & co
+ */
+
 /* parse EAPDs */
 static void cx_auto_parse_eapd(struct hda_codec *codec)
 {
@@ -179,21 +160,6 @@ static void cx_auto_vmaster_hook_mute_led(void *private_data, int enabled)
 			    enabled ? 0x00 : 0x02);
 }
 
-static int cx_auto_build_controls(struct hda_codec *codec)
-{
-	int err;
-
-	err = snd_hda_gen_build_controls(codec);
-	if (err < 0)
-		return err;
-
-	err = add_beep_ctls(codec);
-	if (err < 0)
-		return err;
-
-	return 0;
-}
-
 static int cx_auto_init(struct hda_codec *codec)
 {
 	struct conexant_spec *spec = codec->spec;
@@ -234,7 +200,7 @@ static void cx_auto_free(struct hda_codec *codec)
 }
 
 static const struct hda_codec_ops cx_auto_patch_ops = {
-	.build_controls = cx_auto_build_controls,
+	.build_controls = snd_hda_gen_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = cx_auto_init,
 	.reboot_notify = cx_auto_reboot_notify,
@@ -1033,7 +999,6 @@ static int patch_conexant_auto(struct hda_codec *codec)
 	codec->spec = spec;
 	codec->patch_ops = cx_auto_patch_ops;
 
-	cx_auto_parse_beep(codec);
 	cx_auto_parse_eapd(codec);
 	spec->gen.own_eapd_ctl = 1;
 	if (spec->dynamic_eapd)
@@ -1093,6 +1058,10 @@ static int patch_conexant_auto(struct hda_codec *codec)
 	if (err < 0)
 		goto error;
 
+	err = cx_auto_parse_beep(codec);
+	if (err < 0)
+		goto error;
+
 	/* Some laptops with Conexant chips show stalls in S3 resume,
 	 * which falls into the single-cmd mode.
 	 * Better to make reset, then.
-- 
cgit v1.2.3


From 0785b0ecb8fa960b4f49010d0679d174efad423c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Jun 2018 17:10:51 +0200
Subject: ALSA: hda/cirrus - Simplify creation of new controls

This patch moves the mixer creation code in Cirrus codec driver from
its own build_controls callback to snd_hda_gen_add_kctl() for
simplification.

As a bonus, this allows us to remove the cs421x_build_controls as it
becomes identical with snd_hda_gen_build_controls().

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_cirrus.c | 29 +++++++++--------------------
 1 file changed, 9 insertions(+), 20 deletions(-)

diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c
index d6e079f4ec09..a7f91be45194 100644
--- a/sound/pci/hda/patch_cirrus.c
+++ b/sound/pci/hda/patch_cirrus.c
@@ -1096,25 +1096,6 @@ static int cs421x_init(struct hda_codec *codec)
 	return 0;
 }
 
-static int cs421x_build_controls(struct hda_codec *codec)
-{
-	struct cs_spec *spec = codec->spec;
-	int err;
-
-	err = snd_hda_gen_build_controls(codec);
-	if (err < 0)
-		return err;
-
-	if (spec->gen.autocfg.speaker_outs &&
-	    spec->vendor_nid == CS4210_VENDOR_NID) {
-		err = snd_hda_ctl_add(codec, 0,
-			snd_ctl_new1(&cs421x_speaker_boost_ctl, codec));
-		if (err < 0)
-			return err;
-	}
-	return 0;
-}
-
 static void fix_volume_caps(struct hda_codec *codec, hda_nid_t dac)
 {
 	unsigned int caps;
@@ -1144,6 +1125,14 @@ static int cs421x_parse_auto_config(struct hda_codec *codec)
 		return err;
 
 	parse_cs421x_digital(codec);
+
+	if (spec->gen.autocfg.speaker_outs &&
+	    spec->vendor_nid == CS4210_VENDOR_NID) {
+		if (!snd_hda_gen_add_kctl(&spec->gen, NULL,
+					  &cs421x_speaker_boost_ctl))
+			return -ENOMEM;
+	}
+
 	return 0;
 }
 
@@ -1175,7 +1164,7 @@ static int cs421x_suspend(struct hda_codec *codec)
 #endif
 
 static const struct hda_codec_ops cs421x_patch_ops = {
-	.build_controls = cs421x_build_controls,
+	.build_controls = snd_hda_gen_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = cs421x_init,
 	.free = cs_free,
-- 
cgit v1.2.3


From fcbdcc1a93dd49ccd0e0f34224ce1ba4203b75de Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Jun 2018 22:36:17 +0200
Subject: ALSA: hda/via - Rewrite with error goto

Currently VIA codec driver invokes via_free() at each place of the
error path.  Move the error handling to the end of each function
commonly and do goto-error as a standard idiom.

This is a preliminary patch for the further cleanups, and no
functional changes.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_via.c | 100 +++++++++++++++++++++++++++-------------------
 1 file changed, 60 insertions(+), 40 deletions(-)

diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index fc30d1e8aa76..76e47d088a41 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -686,10 +686,8 @@ static int patch_vt1708(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	/* add jack detect on/off control */
 	spec->mixers[spec->num_mixers++] = vt1708_jack_detect_ctl;
@@ -700,6 +698,10 @@ static int patch_vt1708(struct hda_codec *codec)
 	codec->jackpoll_interval = 0;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 static int patch_vt1709(struct hda_codec *codec)
@@ -715,12 +717,14 @@ static int patch_vt1709(struct hda_codec *codec)
 	spec->gen.mixer_nid = 0x18;
 
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 static int patch_vt1708S(struct hda_codec *codec);
@@ -741,12 +745,14 @@ static int patch_vt1708B(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1708S */
@@ -793,14 +799,16 @@ static int patch_vt1708S(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	spec->init_verbs[spec->num_iverbs++] = vt1708S_init_verbs;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1702 */
@@ -834,14 +842,16 @@ static int patch_vt1702(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	spec->init_verbs[spec->num_iverbs++] = vt1702_init_verbs;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1718S */
@@ -906,14 +916,16 @@ static int patch_vt1718S(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	spec->init_verbs[spec->num_iverbs++] = vt1718S_init_verbs;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* Patch for VT1716S */
@@ -1002,10 +1014,8 @@ static int patch_vt1716S(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	spec->init_verbs[spec->num_iverbs++]  = vt1716S_init_verbs;
 
@@ -1013,6 +1023,10 @@ static int patch_vt1716S(struct hda_codec *codec)
 	spec->mixers[spec->num_mixers++] = vt1716S_mono_out_mixer;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* for vt2002P */
@@ -1109,10 +1123,8 @@ static int patch_vt2002P(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	if (spec->codec_type == VT1802)
 		spec->init_verbs[spec->num_iverbs++] = vt1802_init_verbs;
@@ -1120,6 +1132,10 @@ static int patch_vt2002P(struct hda_codec *codec)
 		spec->init_verbs[spec->num_iverbs++] = vt2002P_init_verbs;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* for vt1812 */
@@ -1150,14 +1166,16 @@ static int patch_vt1812(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	spec->init_verbs[spec->num_iverbs++]  = vt1812_init_verbs;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /* patch for vt3476 */
@@ -1187,14 +1205,16 @@ static int patch_vt3476(struct hda_codec *codec)
 
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
-	if (err < 0) {
-		via_free(codec);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 
 	spec->init_verbs[spec->num_iverbs++] = vt3476_init_verbs;
 
 	return 0;
+
+ error:
+	via_free(codec);
+	return err;
 }
 
 /*
-- 
cgit v1.2.3


From 0e8f9862493a55d85d3351cb4517f2e4d95c9600 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Jun 2018 17:20:42 +0200
Subject: ALSA: hda/via - Simplify control management

This patch replaces the control element creations in VIA codec driver
with the standard snd_hda_gen_add_kctl() calls as a cleanup.  There
are two major fields targeted by this patch: the beep controls and
static init controls.

The former is converted just like other codec drivers do.  The
spec->beep_amp field can be eliminated by this change as well.

The latter, static init controls, are replaced simply with explicit
snd_hda_gen_add_kctl() calls.

After these conversions, via_build_controls() becomes superfluous and
replaced with snd_hda_gen_build_controls(), too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_via.c | 130 ++++++++++++++++------------------------------
 1 file changed, 44 insertions(+), 86 deletions(-)

diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index 76e47d088a41..dc4961f0dfd1 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -91,9 +91,6 @@ struct via_spec {
 	struct hda_gen_spec gen;
 
 	/* codec parameterization */
-	const struct snd_kcontrol_new *mixers[6];
-	unsigned int num_mixers;
-
 	const struct hda_verb *init_verbs[5];
 	unsigned int num_iverbs;
 
@@ -107,8 +104,6 @@ struct via_spec {
 	/* work to check hp jack state */
 	int hp_work_active;
 	int vt1708_jack_detect;
-
-	unsigned int beep_amp;
 };
 
 static enum VIA_HDA_CODEC get_codec_type(struct hda_codec *codec);
@@ -262,69 +257,51 @@ static int via_pin_power_ctl_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const struct snd_kcontrol_new via_pin_power_ctl_enum[] = {
-	{
+static const struct snd_kcontrol_new via_pin_power_ctl_enum = {
 	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
 	.name = "Dynamic Power-Control",
 	.info = via_pin_power_ctl_info,
 	.get = via_pin_power_ctl_get,
 	.put = via_pin_power_ctl_put,
-	},
-	{} /* terminator */
 };
 
 #ifdef CONFIG_SND_HDA_INPUT_BEEP
-static inline void set_beep_amp(struct via_spec *spec, hda_nid_t nid,
-				int idx, int dir)
-{
-	spec->gen.beep_nid = nid;
-	spec->beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
-}
-
 /* additional beep mixers; the actual parameters are overwritten at build */
-static const struct snd_kcontrol_new cxt_beep_mixer[] = {
+static const struct snd_kcontrol_new via_beep_mixer[] = {
 	HDA_CODEC_VOLUME_MONO("Beep Playback Volume", 0, 1, 0, HDA_OUTPUT),
 	HDA_CODEC_MUTE_BEEP_MONO("Beep Playback Switch", 0, 1, 0, HDA_OUTPUT),
-	{ } /* end */
 };
 
-/* create beep controls if needed */
-static int add_beep_ctls(struct hda_codec *codec)
+static int set_beep_amp(struct via_spec *spec, hda_nid_t nid,
+			int idx, int dir)
 {
-	struct via_spec *spec = codec->spec;
-	int err;
+	struct snd_kcontrol_new *knew;
+	unsigned int beep_amp = HDA_COMPOSE_AMP_VAL(nid, 1, idx, dir);
+	int i;
 
-	if (spec->beep_amp) {
-		const struct snd_kcontrol_new *knew;
-		for (knew = cxt_beep_mixer; knew->name; knew++) {
-			struct snd_kcontrol *kctl;
-			kctl = snd_ctl_new1(knew, codec);
-			if (!kctl)
-				return -ENOMEM;
-			kctl->private_value = spec->beep_amp;
-			err = snd_hda_ctl_add(codec, 0, kctl);
-			if (err < 0)
-				return err;
-		}
+	spec->gen.beep_nid = nid;
+	for (i = 0; i < ARRAY_SIZE(via_beep_mixer); i++) {
+		knew = snd_hda_gen_add_kctl(&spec->gen, NULL,
+					    &via_beep_mixer[i]);
+		if (!knew)
+			return -ENOMEM;
+		knew->private_value = beep_amp;
 	}
 	return 0;
 }
 
-static void auto_parse_beep(struct hda_codec *codec)
+static int auto_parse_beep(struct hda_codec *codec)
 {
 	struct via_spec *spec = codec->spec;
 	hda_nid_t nid;
 
 	for_each_hda_codec_node(nid, codec)
-		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP) {
-			set_beep_amp(spec, nid, 0, HDA_OUTPUT);
-			break;
-		}
+		if (get_wcaps_type(get_wcaps(codec, nid)) == AC_WID_BEEP)
+			return set_beep_amp(spec, nid, 0, HDA_OUTPUT);
+	return 0;
 }
 #else
-#define set_beep_amp(spec, nid, idx, dir) /* NOP */
-#define add_beep_ctls(codec)	0
-#define auto_parse_beep(codec)
+#define auto_parse_beep(codec)	0
 #endif
 
 /* check AA path's mute status */
@@ -403,30 +380,6 @@ static void analog_low_current_mode(struct hda_codec *codec)
 	return __analog_low_current_mode(codec, false);
 }
 
-static int via_build_controls(struct hda_codec *codec)
-{
-	struct via_spec *spec = codec->spec;
-	int err, i;
-
-	err = snd_hda_gen_build_controls(codec);
-	if (err < 0)
-		return err;
-
-	err = add_beep_ctls(codec);
-	if (err < 0)
-		return err;
-
-	spec->mixers[spec->num_mixers++] = via_pin_power_ctl_enum;
-
-	for (i = 0; i < spec->num_mixers; i++) {
-		err = snd_hda_add_new_ctls(codec, spec->mixers[i]);
-		if (err < 0)
-			return err;
-	}
-
-	return 0;
-}
-
 static void via_playback_pcm_hook(struct hda_pcm_stream *hinfo,
 				  struct hda_codec *codec,
 				  struct snd_pcm_substream *substream,
@@ -481,7 +434,7 @@ static int via_check_power_status(struct hda_codec *codec, hda_nid_t nid)
 static int via_init(struct hda_codec *codec);
 
 static const struct hda_codec_ops via_patch_ops = {
-	.build_controls = via_build_controls,
+	.build_controls = snd_hda_gen_build_controls,
 	.build_pcms = snd_hda_gen_build_pcms,
 	.init = via_init,
 	.free = via_free,
@@ -545,16 +498,13 @@ static int vt1708_jack_detect_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const struct snd_kcontrol_new vt1708_jack_detect_ctl[] = {
-	{
+static const struct snd_kcontrol_new vt1708_jack_detect_ctl = {
 	.iface = SNDRV_CTL_ELEM_IFACE_MIXER,
 	.name = "Jack Detect",
 	.count = 1,
 	.info = snd_ctl_boolean_mono_info,
 	.get = vt1708_jack_detect_get,
 	.put = vt1708_jack_detect_put,
-	},
-	{} /* terminator */
 };
 
 static const struct badness_table via_main_out_badness = {
@@ -586,12 +536,17 @@ static int via_parse_auto_config(struct hda_codec *codec)
 	if (err < 0)
 		return err;
 
-	auto_parse_beep(codec);
-
 	err = snd_hda_gen_parse_auto_config(codec, &spec->gen.autocfg);
 	if (err < 0)
 		return err;
 
+	err = auto_parse_beep(codec);
+	if (err < 0)
+		return err;
+
+	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &via_pin_power_ctl_enum))
+		return -ENOMEM;
+
 	/* disable widget PM at start for compatibility */
 	codec->power_save_node = 0;
 	spec->gen.power_down_unused = 0;
@@ -623,7 +578,7 @@ static int vt1708_build_controls(struct hda_codec *codec)
 	int err;
 	int old_interval = codec->jackpoll_interval;
 	codec->jackpoll_interval = msecs_to_jiffies(100);
-	err = via_build_controls(codec);
+	err = snd_hda_gen_build_controls(codec);
 	codec->jackpoll_interval = old_interval;
 	return err;
 }
@@ -690,7 +645,10 @@ static int patch_vt1708(struct hda_codec *codec)
 		goto error;
 
 	/* add jack detect on/off control */
-	spec->mixers[spec->num_mixers++] = vt1708_jack_detect_ctl;
+	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1708_jack_detect_ctl)) {
+		err = -ENOMEM;
+		goto error;
+	}
 
 	spec->init_verbs[spec->num_iverbs++] = vt1708_init_verbs;
 
@@ -967,9 +925,9 @@ static int vt1716s_dmic_put(struct snd_kcontrol *kcontrol,
 	return 1;
 }
 
-static const struct snd_kcontrol_new vt1716s_dmic_mixer[] = {
-	HDA_CODEC_VOLUME("Digital Mic Capture Volume", 0x22, 0x0, HDA_INPUT),
-	{
+static const struct snd_kcontrol_new vt1716s_dmic_mixer_vol =
+	HDA_CODEC_VOLUME("Digital Mic Capture Volume", 0x22, 0x0, HDA_INPUT);
+static const struct snd_kcontrol_new vt1716s_dmic_mixer_sw = {
 	 .iface = SNDRV_CTL_ELEM_IFACE_MIXER,
 	 .name = "Digital Mic Capture Switch",
 	 .subdevice = HDA_SUBDEV_NID_FLAG | 0x26,
@@ -977,16 +935,12 @@ static const struct snd_kcontrol_new vt1716s_dmic_mixer[] = {
 	 .info = vt1716s_dmic_info,
 	 .get = vt1716s_dmic_get,
 	 .put = vt1716s_dmic_put,
-	 },
-	{}			/* end */
 };
 
 
 /* mono-out mixer elements */
-static const struct snd_kcontrol_new vt1716S_mono_out_mixer[] = {
-	HDA_CODEC_MUTE("Mono Playback Switch", 0x2a, 0x0, HDA_OUTPUT),
-	{ } /* end */
-};
+static const struct snd_kcontrol_new vt1716S_mono_out_mixer =
+	HDA_CODEC_MUTE("Mono Playback Switch", 0x2a, 0x0, HDA_OUTPUT);
 
 static const struct hda_verb vt1716S_init_verbs[] = {
 	/* Enable Boost Volume backdoor */
@@ -1019,8 +973,12 @@ static int patch_vt1716S(struct hda_codec *codec)
 
 	spec->init_verbs[spec->num_iverbs++]  = vt1716S_init_verbs;
 
-	spec->mixers[spec->num_mixers++] = vt1716s_dmic_mixer;
-	spec->mixers[spec->num_mixers++] = vt1716S_mono_out_mixer;
+	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716s_dmic_mixer_vol) ||
+	    !snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716s_dmic_mixer_sw) ||
+	    !snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716S_mono_out_mixer)) {
+		err = -ENOMEM;
+		goto error;
+	}
 
 	return 0;
 
-- 
cgit v1.2.3


From f8bfc628f73c95c242dd49efa16d59005d8558fc Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 20 Jun 2018 17:27:50 +0200
Subject: ALSA: hda/via - Use standard verb containers

In this patch, the remaining static init verbs in VIA codec driver are
converted to the standard snd_hda_add_verbs() calls.  The conversion
is straightforward, but one change to be noted is the place of calls:
since these verbs are supposed to be executed at the beginning of the
init / resume procedure, we need to add snd_hda_add_verbs() calls
before calling the other parsers.

This is merely a cleanup, no functional changes.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_via.c | 64 ++++++++++++++++++++++++++---------------------
 1 file changed, 35 insertions(+), 29 deletions(-)

diff --git a/sound/pci/hda/patch_via.c b/sound/pci/hda/patch_via.c
index dc4961f0dfd1..6b9617aee0e6 100644
--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c
@@ -90,10 +90,6 @@ enum VIA_HDA_CODEC {
 struct via_spec {
 	struct hda_gen_spec gen;
 
-	/* codec parameterization */
-	const struct hda_verb *init_verbs[5];
-	unsigned int num_iverbs;
-
 	/* HP mode source */
 	unsigned int dmic_enabled;
 	enum VIA_HDA_CODEC codec_type;
@@ -555,12 +551,6 @@ static int via_parse_auto_config(struct hda_codec *codec)
 
 static int via_init(struct hda_codec *codec)
 {
-	struct via_spec *spec = codec->spec;
-	int i;
-
-	for (i = 0; i < spec->num_iverbs; i++)
-		snd_hda_sequence_write(codec, spec->init_verbs[i]);
-
 	/* init power states */
 	__analog_low_current_mode(codec, true);
 
@@ -639,6 +629,10 @@ static int patch_vt1708(struct hda_codec *codec)
 	vt1708_set_pinconfig_connect(codec, VT1708_HP_PIN_NID);
 	vt1708_set_pinconfig_connect(codec, VT1708_CD_PIN_NID);
 
+	err = snd_hda_add_verbs(codec, vt1708_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
@@ -650,8 +644,6 @@ static int patch_vt1708(struct hda_codec *codec)
 		goto error;
 	}
 
-	spec->init_verbs[spec->num_iverbs++] = vt1708_init_verbs;
-
 	/* clear jackpoll_interval again; it's set dynamically */
 	codec->jackpoll_interval = 0;
 
@@ -755,13 +747,15 @@ static int patch_vt1708S(struct hda_codec *codec)
 	if (codec->core.vendor_id == 0x11064397)
 		snd_hda_codec_set_name(codec, "VT1705");
 
+	err = snd_hda_add_verbs(codec, vt1708S_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	spec->init_verbs[spec->num_iverbs++] = vt1708S_init_verbs;
-
 	return 0;
 
  error:
@@ -798,13 +792,15 @@ static int patch_vt1702(struct hda_codec *codec)
 				  (0x5 << AC_AMPCAP_STEP_SIZE_SHIFT) |
 				  (1 << AC_AMPCAP_MUTE_SHIFT));
 
+	err = snd_hda_add_verbs(codec, vt1702_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	spec->init_verbs[spec->num_iverbs++] = vt1702_init_verbs;
-
 	return 0;
 
  error:
@@ -872,13 +868,15 @@ static int patch_vt1718S(struct hda_codec *codec)
 	override_mic_boost(codec, 0x29, 0, 3, 40);
 	add_secret_dac_path(codec);
 
+	err = snd_hda_add_verbs(codec, vt1718S_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	spec->init_verbs[spec->num_iverbs++] = vt1718S_init_verbs;
-
 	return 0;
 
  error:
@@ -966,13 +964,15 @@ static int patch_vt1716S(struct hda_codec *codec)
 	override_mic_boost(codec, 0x1a, 0, 3, 40);
 	override_mic_boost(codec, 0x1e, 0, 3, 40);
 
+	err = snd_hda_add_verbs(codec, vt1716S_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	spec->init_verbs[spec->num_iverbs++]  = vt1716S_init_verbs;
-
 	if (!snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716s_dmic_mixer_vol) ||
 	    !snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716s_dmic_mixer_sw) ||
 	    !snd_hda_gen_add_kctl(&spec->gen, NULL, &vt1716S_mono_out_mixer)) {
@@ -1079,16 +1079,18 @@ static int patch_vt2002P(struct hda_codec *codec)
 	snd_hda_pick_fixup(codec, NULL, vt2002p_fixups, via_fixups);
 	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
 
+	if (spec->codec_type == VT1802)
+		err = snd_hda_add_verbs(codec, vt1802_init_verbs);
+	else
+		err = snd_hda_add_verbs(codec, vt2002P_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	if (spec->codec_type == VT1802)
-		spec->init_verbs[spec->num_iverbs++] = vt1802_init_verbs;
-	else
-		spec->init_verbs[spec->num_iverbs++] = vt2002P_init_verbs;
-
 	return 0;
 
  error:
@@ -1122,13 +1124,15 @@ static int patch_vt1812(struct hda_codec *codec)
 	override_mic_boost(codec, 0x29, 0, 3, 40);
 	add_secret_dac_path(codec);
 
+	err = snd_hda_add_verbs(codec, vt1812_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	spec->init_verbs[spec->num_iverbs++]  = vt1812_init_verbs;
-
 	return 0;
 
  error:
@@ -1161,13 +1165,15 @@ static int patch_vt3476(struct hda_codec *codec)
 	spec->gen.mixer_nid = 0x3f;
 	add_secret_dac_path(codec);
 
+	err = snd_hda_add_verbs(codec, vt3476_init_verbs);
+	if (err < 0)
+		goto error;
+
 	/* automatic parse from the BIOS config */
 	err = via_parse_auto_config(codec);
 	if (err < 0)
 		goto error;
 
-	spec->init_verbs[spec->num_iverbs++] = vt3476_init_verbs;
-
 	return 0;
 
  error:
-- 
cgit v1.2.3


From efe557320ab6cea12205794fd4062e6e850b7e1c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 15 Jun 2018 11:55:02 +0200
Subject: ALSA: hda/realtek - Apply PRE_PROBE fixup after ALC269 codec variant
 setups

Currently patch_alc269() calls the fixup with HDA_FIXUP_ACT_PRE_PROBE
before setting up the codec model-specific setups (e.g. setting
codec_variant or mixer_nid setup).  This is rather confusing as others
do call the *_PRE_PROBE fixup after such a setup.  Due to this
disorder, we have to override spec->shutup not at the usual
HDA_FIXUP_ACT_PRE_PROBE but the unusual HDA_FIXUP_ACT_PROBE time.

This patch corrects the fixup call orders in patch_alc269(), and also
corrects the action to set up spec->shutup accordingly.

No functional changes but just refactoring.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 0e84d9cdd42d..c93e09f9c109 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4906,7 +4906,7 @@ static void alc_no_shutup(struct hda_codec *codec)
 static void alc_fixup_no_shutup(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
-	if (action == HDA_FIXUP_ACT_PROBE) {
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
 		struct alc_spec *spec = codec->spec;
 		spec->shutup = alc_no_shutup;
 	}
@@ -4988,10 +4988,9 @@ static void alc_fixup_dell_xps13(struct hda_codec *codec,
 		 * it causes a click noise at start up
 		 */
 		snd_hda_codec_set_pin_target(codec, 0x19, PIN_VREFHIZ);
+		spec->shutup = alc_shutup_dell_xps13;
 		break;
 	case HDA_FIXUP_ACT_PROBE:
-		spec->shutup = alc_shutup_dell_xps13;
-
 		/* Make the internal mic the default input source. */
 		for (i = 0; i < imux->num_items; i++) {
 			if (spec->gen.imux_pins[i] == 0x12) {
@@ -7037,18 +7036,6 @@ static int patch_alc269(struct hda_codec *codec)
 	spec->shutup = alc_default_shutup;
 	spec->init_hook = alc_default_init;
 
-	snd_hda_pick_fixup(codec, alc269_fixup_models,
-		       alc269_fixup_tbl, alc269_fixups);
-	snd_hda_pick_pin_fixup(codec, alc269_pin_fixup_tbl, alc269_fixups);
-	snd_hda_pick_fixup(codec, NULL,	alc269_fixup_vendor_tbl,
-			   alc269_fixups);
-	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
-
-	alc_auto_parse_customize_define(codec);
-
-	if (has_cdefine_beep(codec))
-		spec->gen.beep_nid = 0x01;
-
 	switch (codec->core.vendor_id) {
 	case 0x10ec0269:
 		spec->codec_variant = ALC269_TYPE_ALC269VA;
@@ -7168,6 +7155,18 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->init_hook = alc5505_dsp_init;
 	}
 
+	snd_hda_pick_fixup(codec, alc269_fixup_models,
+		       alc269_fixup_tbl, alc269_fixups);
+	snd_hda_pick_pin_fixup(codec, alc269_pin_fixup_tbl, alc269_fixups);
+	snd_hda_pick_fixup(codec, NULL,	alc269_fixup_vendor_tbl,
+			   alc269_fixups);
+	snd_hda_apply_fixup(codec, HDA_FIXUP_ACT_PRE_PROBE);
+
+	alc_auto_parse_customize_define(codec);
+
+	if (has_cdefine_beep(codec))
+		spec->gen.beep_nid = 0x01;
+
 	/* automatic parse from the BIOS config */
 	err = alc269_parse_auto_config(codec);
 	if (err < 0)
-- 
cgit v1.2.3


From 64e03ff72623b8c2ea89ca3cb660094e019ed4ae Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 16 May 2018 09:37:25 +0200
Subject: s390/qdio: reset old sbal_state flags

When allocating a new AOB fails, handle_outbound() is still capable of
transmitting the selected buffer (just without async completion).

But if a previous transfer on this queue slot used async completion, its
sbal_state flags field is still set to QDIO_OUTBUF_STATE_FLAG_PENDING.
So when the upper layer driver sees this stale flag, it expects an async
completion that never happens.

Fix this by unconditionally clearing the flags field.

Fixes: 104ea556ee7f ("qdio: support asynchronous delivery of storage blocks")
Cc: <stable@vger.kernel.org> #v3.2+
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/qdio.h | 1 -
 drivers/s390/cio/qdio_main.c | 5 ++---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index de11ecc99c7c..9c9970a5dfb1 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -262,7 +262,6 @@ struct qdio_outbuf_state {
 	void *user;
 };
 
-#define QDIO_OUTBUF_STATE_FLAG_NONE	0x00
 #define QDIO_OUTBUF_STATE_FLAG_PENDING	0x01
 
 #define CHSC_AC1_INITIATE_INPUTQ	0x80
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index f4ca72dd862f..9c7d9da42ba0 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -631,21 +631,20 @@ static inline unsigned long qdio_aob_for_buffer(struct qdio_output_q *q,
 	unsigned long phys_aob = 0;
 
 	if (!q->use_cq)
-		goto out;
+		return 0;
 
 	if (!q->aobs[bufnr]) {
 		struct qaob *aob = qdio_allocate_aob();
 		q->aobs[bufnr] = aob;
 	}
 	if (q->aobs[bufnr]) {
-		q->sbal_state[bufnr].flags = QDIO_OUTBUF_STATE_FLAG_NONE;
 		q->sbal_state[bufnr].aob = q->aobs[bufnr];
 		q->aobs[bufnr]->user1 = (u64) q->sbal_state[bufnr].user;
 		phys_aob = virt_to_phys(q->aobs[bufnr]);
 		WARN_ON_ONCE(phys_aob & 0xFF);
 	}
 
-out:
+	q->sbal_state[bufnr].flags = 0;
 	return phys_aob;
 }
 
-- 
cgit v1.2.3


From 157484abb9b05e3f49cd3903202ffad35cea4350 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 15 Jun 2018 10:22:18 +0200
Subject: s390: disable asm code expolines if cc does not support it

To avoid a mixture of asm code with expolines and c code without them,
propagate CC_USING_EXPOLINE to KBUILD_AFLAGS and use it to detect
whether asm code should have expolines or not.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile                  | 1 +
 arch/s390/include/asm/nospec-insn.h | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 68a690442be0..8a41110d3a9a 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -82,6 +82,7 @@ ifdef CONFIG_EXPOLINE
     CC_FLAGS_EXPOLINE += -mindirect-branch-table
     export CC_FLAGS_EXPOLINE
     cflags-y += $(CC_FLAGS_EXPOLINE) -DCC_USING_EXPOLINE
+    aflags-y += -DCC_USING_EXPOLINE
   endif
 endif
 
diff --git a/arch/s390/include/asm/nospec-insn.h b/arch/s390/include/asm/nospec-insn.h
index a01f81186e86..123dac3717b3 100644
--- a/arch/s390/include/asm/nospec-insn.h
+++ b/arch/s390/include/asm/nospec-insn.h
@@ -8,7 +8,7 @@
 
 #ifdef __ASSEMBLY__
 
-#ifdef CONFIG_EXPOLINE
+#ifdef CC_USING_EXPOLINE
 
 _LC_BR_R1 = __LC_BR_R1
 
@@ -189,7 +189,7 @@ _LC_BR_R1 = __LC_BR_R1
 	.macro BASR_EX rsave,rtarget,ruse=%r1
 	basr	\rsave,\rtarget
 	.endm
-#endif
+#endif /* CC_USING_EXPOLINE */
 
 #endif /* __ASSEMBLY__ */
 
-- 
cgit v1.2.3


From 19f73e16199ee21b95e15bb5c380ad69f12e8c5b Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 15 Jun 2018 10:48:54 +0200
Subject: s390/build: remove obsolete -mkernel-backchain flag

-mkernel-backchain cc flag is obsolete since quite a while, and not
present in minimal (supported by s390) gcc version 4.3. Removing it.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index 8a41110d3a9a..cdf3557864e1 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -52,13 +52,6 @@ cflags-y += -Wa,-I$(srctree)/arch/$(ARCH)/include
 #
 cflags-$(CONFIG_FRAME_POINTER) += -fno-optimize-sibling-calls
 
-# old style option for packed stacks
-ifeq ($(call cc-option-yn,-mkernel-backchain),y)
-cflags-$(CONFIG_PACK_STACK)  += -mkernel-backchain -D__PACK_STACK
-aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
-endif
-
-# new style option for packed stacks
 ifeq ($(call cc-option-yn,-mpacked-stack),y)
 cflags-$(CONFIG_PACK_STACK)  += -mpacked-stack -D__PACK_STACK
 aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
-- 
cgit v1.2.3


From 76bf9d6cef5788c769af987ff6f8ece40c6ab152 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 15 Jun 2018 12:28:05 +0200
Subject: s390/decompressor: correct build flags

The decompressor requires its own set of cc and asm flags, to avoid
building with features which do not make sense at such an early boot stage
(e.g. expoline, ftrace).

Currently cc flags are already set for the decompressor, but "cflags-y"
is not exported and hence empty. To fix that and to add asm flags, define
and export KBUILD_AFLAGS_DECOMPRESSOR and KBUILD_CFLAGS_DECOMPRESSOR
and rely on them in the decompressor's Makefile.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile                 | 20 +++++++++++++++++---
 arch/s390/boot/compressed/Makefile | 13 ++++---------
 2 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index cdf3557864e1..d7ec2baa2f75 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -14,8 +14,14 @@ LD_BFD		:= elf64-s390
 LDFLAGS		:= -m elf64_s390
 KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
-KBUILD_CFLAGS	+= -m64
 KBUILD_AFLAGS	+= -m64
+KBUILD_CFLAGS	+= -m64
+KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
+KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
+KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
+KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
 UTS_MACHINE	:= s390x
 STACK_SIZE	:= 16384
 CHECKFLAGS	+= -D__s390__ -D__s390x__
@@ -57,6 +63,9 @@ cflags-$(CONFIG_PACK_STACK)  += -mpacked-stack -D__PACK_STACK
 aflags-$(CONFIG_PACK_STACK)  += -D__PACK_STACK
 endif
 
+KBUILD_AFLAGS_DECOMPRESSOR += $(aflags-y)
+KBUILD_CFLAGS_DECOMPRESSOR += $(cflags-y)
+
 ifeq ($(call cc-option-yn,-mstack-size=8192 -mstack-guard=128),y)
 cflags-$(CONFIG_CHECK_STACK) += -mstack-size=$(STACK_SIZE)
 ifneq ($(call cc-option-yn,-mstack-size=8192),y)
@@ -64,8 +73,11 @@ cflags-$(CONFIG_CHECK_STACK) += -mstack-guard=$(CONFIG_STACK_GUARD)
 endif
 endif
 
-ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
-cflags-$(CONFIG_WARN_DYNAMIC_STACK) += -mwarn-dynamicstack
+ifdef CONFIG_WARN_DYNAMIC_STACK
+  ifeq ($(call cc-option-yn,-mwarn-dynamicstack),y)
+    KBUILD_CFLAGS += -mwarn-dynamicstack
+    KBUILD_CFLAGS_DECOMPRESSOR += -mwarn-dynamicstack
+  endif
 endif
 
 ifdef CONFIG_EXPOLINE
@@ -96,6 +108,8 @@ KBUILD_CFLAGS	+= -mbackchain -msoft-float $(cflags-y)
 KBUILD_CFLAGS	+= -pipe -fno-strength-reduce -Wno-sign-compare
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables $(cfi)
 KBUILD_AFLAGS	+= $(aflags-y) $(cfi)
+export KBUILD_AFLAGS_DECOMPRESSOR
+export KBUILD_CFLAGS_DECOMPRESSOR
 
 OBJCOPYFLAGS	:= -O binary
 
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 5766f7b9b271..4f81d14c9f35 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -6,20 +6,15 @@
 #
 
 KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
 
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
 targets += misc.o piggy.o sizes.h head.o
 
-KBUILD_CFLAGS := -m64 -D__KERNEL__ -O2
-KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
-KBUILD_CFLAGS += $(cflags-y) -fno-delete-null-pointer-checks -msoft-float
-KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
-KBUILD_CFLAGS += $(call cc-option,-mpacked-stack)
-KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
-
-GCOV_PROFILE := n
-UBSAN_SANITIZE := n
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
 OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o ebcdic.o als.o)
 OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o
-- 
cgit v1.2.3


From 00f2fb573fdc3c21f3b7266a4a8758a85943edfb Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 11 Jun 2018 14:35:01 +0200
Subject: s390: remove uncompressed kernel image build

Dropping support for uncompressed kernel "image" build. Having
both image and bzImage makes it complicated to add new code to an
early boot phase (which is part of vmlinux for uncompressed kernel and
a separate arch/s390/boot/compressed/vmlinux for bzImage).

e.g. sclp_early_core.o is used for both, the decompressor phase and the
main kernel. The fact of having uncompressed kernel "image" forces us
to have a single object file and sacrifice instrumentation flags on such
files (so that we could use them early). The story gets much more
complicated with the need to utilize some of the string functions.

With bzImage only support, we have 2 separate boot stages each built
and linked separately, which allows to reuse some shared code, but
recompile with appropriate flags.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile      | 7 +++----
 arch/s390/boot/Makefile | 6 +-----
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index d7ec2baa2f75..ea3e610ead75 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -129,7 +129,7 @@ boot		:= arch/s390/boot
 syscalls	:= arch/s390/kernel/syscalls
 tools		:= arch/s390/tools
 
-all: image bzImage
+all: bzImage
 
 #KBUILD_IMAGE is necessary for packaging targets like rpm-pkg, deb-pkg...
 KBUILD_IMAGE	:= $(boot)/bzImage
@@ -137,7 +137,7 @@ KBUILD_IMAGE	:= $(boot)/bzImage
 install: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $@
 
-image bzImage: vmlinux
+bzImage: vmlinux
 	$(Q)$(MAKE) $(build)=$(boot) $(boot)/$@
 
 zfcpdump:
@@ -160,8 +160,7 @@ archprepare:
 
 # Don't use tabs in echo arguments
 define archhelp
-  echo  '* image           - Kernel image for IPL ($(boot)/image)'
-  echo	'* bzImage         - Compressed kernel image for IPL ($(boot)/bzImage)'
+  echo	'* bzImage         - Kernel image for IPL ($(boot)/bzImage)'
   echo	'  install         - Install kernel using'
   echo	'                    (your) ~/bin/$(INSTALLKERNEL) or'
   echo	'                    (distribution) /sbin/$(INSTALLKERNEL) or'
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index d1fa37fcce83..da5f299dcd18 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -3,13 +3,9 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-targets := image
-targets += bzImage
+targets := bzImage
 subdir- := compressed
 
-$(obj)/image: vmlinux FORCE
-	$(call if_changed,objcopy)
-
 $(obj)/bzImage: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 
-- 
cgit v1.2.3


From bd79d66329580d6c3fd9556423d2e5124906cfdd Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 15:11:40 +0200
Subject: s390/decompressor: trim the kernel image up to 1M

Move head64.S main kernel entry point "startup_continue" to 0x100000 and
trim everything which is below 1M during build. So, that the decompressor
would unpack the main kernel image, move it to 0x100000 and jump to
startup_continue.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/Makefile | 2 +-
 arch/s390/boot/compressed/head.S   | 6 +++---
 arch/s390/kernel/head64.S          | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 4f81d14c9f35..9b48e7b86fc8 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -24,7 +24,7 @@ LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS)
 	$(call if_changed,ld)
 
-TRIM_HEAD_SIZE := 0x11000
+TRIM_HEAD_SIZE := 0x100000
 
 sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - $(TRIM_HEAD_SIZE))/p'
 
diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S
index 9f94eca0f467..1c69907dba28 100644
--- a/arch/s390/boot/compressed/head.S
+++ b/arch/s390/boot/compressed/head.S
@@ -23,7 +23,7 @@ ENTRY(startup_continue)
 	aghi	%r15,-160
 	brasl	%r14,decompress_kernel
 	# Set up registers for memory mover. We move the decompressed image to
-	# 0x11000, where startup_continue of the decompressed image is supposed
+	# 0x100000, where startup_continue of the decompressed image is supposed
 	# to be.
 	lgr	%r4,%r2
 	lg	%r2,.Loffset-.LPG1(%r13)
@@ -33,7 +33,7 @@ ENTRY(startup_continue)
 	la	%r1,0x200
 	mvc	0(mover_end-mover,%r1),mover-.LPG1(%r13)
 	# When the memory mover is done we pass control to
-	# arch/s390/kernel/head64.S:startup_continue which lives at 0x11000 in
+	# arch/s390/kernel/head64.S:startup_continue which lives at 0x100000 in
 	# the decompressed image.
 	lgr	%r6,%r2
 	br	%r1
@@ -47,6 +47,6 @@ mover_end:
 .Lstack:
 	.quad	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
 .Loffset:
-	.quad	0x11000
+	.quad	0x100000
 .Lmvsize:
 	.quad	SZ__bss_start
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 791cb9000e86..53e5cb0d6f7f 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -16,6 +16,7 @@
 #include <asm/page.h>
 
 __HEAD
+	.org	0x100000 - 0x11000		# head.o ends at 0x11000
 ENTRY(startup_continue)
 	tm	__LC_STFLE_FAC_LIST+5,0x80	# LPP available ?
 	jz	0f
@@ -88,7 +89,6 @@ ENTRY(startup_continue)
 
 ENTRY(_ehead)
 
-	.org	0x100000 - 0x11000	# head.o ends at 0x11000
 #
 # startup-code, running in absolute addressing mode
 #
-- 
cgit v1.2.3


From 8282cd64d0f9a5292e9f8408a96733523e7f1fec Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 15:11:40 +0200
Subject: s390/boot: make head.S and als.c be part of the decompressor only

Since uncompressed kernel image does not have to be bootable anymore,
move head.S, head_kdump.S and als.c to boot/ folder and compile them
in just in the decompressor.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile                 |   3 +-
 arch/s390/boot/Makefile            |  33 +++-
 arch/s390/boot/als.c               | 127 ++++++++++++++
 arch/s390/boot/compressed/Makefile |   4 +-
 arch/s390/boot/head.S              | 339 +++++++++++++++++++++++++++++++++++++
 arch/s390/boot/head_kdump.S        | 101 +++++++++++
 arch/s390/kernel/Makefile          |  24 +--
 arch/s390/kernel/als.c             | 128 --------------
 arch/s390/kernel/entry.h           |   1 -
 arch/s390/kernel/head.S            | 339 -------------------------------------
 arch/s390/kernel/head64.S          |   2 +-
 arch/s390/kernel/head_kdump.S      | 101 -----------
 arch/s390/kernel/vmlinux.lds.S     |   2 +-
 13 files changed, 605 insertions(+), 599 deletions(-)
 create mode 100644 arch/s390/boot/als.c
 create mode 100644 arch/s390/boot/head.S
 create mode 100644 arch/s390/boot/head_kdump.S
 delete mode 100644 arch/s390/kernel/als.c
 delete mode 100644 arch/s390/kernel/head.S
 delete mode 100644 arch/s390/kernel/head_kdump.S

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index ea3e610ead75..d25fbc170164 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -113,8 +113,7 @@ export KBUILD_CFLAGS_DECOMPRESSOR
 
 OBJCOPYFLAGS	:= -O binary
 
-head-y		:= arch/s390/kernel/head.o
-head-y		+= arch/s390/kernel/head64.o
+head-y		:= arch/s390/kernel/head64.o
 
 # See arch/s390/Kbuild for content of core part of the kernel
 core-y		+= arch/s390/
diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index da5f299dcd18..05e92d43d383 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -3,15 +3,42 @@
 # Makefile for the linux s390-specific parts of the memory manager.
 #
 
-targets := bzImage
-subdir- := compressed
+KCOV_INSTRUMENT := n
+GCOV_PROFILE := n
+UBSAN_SANITIZE := n
+
+KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
+KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
+
+#
+# Use -march=z900 for als.c to be able to print an error
+# message if the kernel is started on a machine which is too old
+#
+ifneq ($(CC_FLAGS_MARCH),-march=z900)
+AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
+AFLAGS_head.o		+= -march=z900
+CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
+CFLAGS_als.o		+= -march=z900
+endif
+
+obj-y	:= head.o als.o
+targets	:= bzImage startup.a $(obj-y)
+subdir-	:= compressed
+
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 $(obj)/bzImage: $(obj)/compressed/vmlinux FORCE
 	$(call if_changed,objcopy)
 
-$(obj)/compressed/vmlinux: FORCE
+$(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
 
+quiet_cmd_ar = AR      $@
+      cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter-out FORCE, $^)
+
+$(obj)/startup.a: $(OBJECTS) FORCE
+	$(call if_changed,ar)
+
 install: $(CONFIGURE) $(obj)/bzImage
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
 	      System.map "$(INSTALL_PATH)"
diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c
new file mode 100644
index 000000000000..b6287a99a7b8
--- /dev/null
+++ b/arch/s390/boot/als.c
@@ -0,0 +1,127 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *    Copyright IBM Corp. 2016
+ */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <asm/processor.h>
+#include <asm/facility.h>
+#include <asm/lowcore.h>
+#include <asm/sclp.h>
+
+/*
+ * The code within this file will be called very early. It may _not_
+ * access anything within the bss section, since that is not cleared
+ * yet and may contain data (e.g. initrd) that must be saved by other
+ * code.
+ * For temporary objects the stack (16k) should be used.
+ */
+
+static unsigned long als[] __initdata = { FACILITIES_ALS };
+
+static void __init u16_to_hex(char *str, u16 val)
+{
+	int i, num;
+
+	for (i = 1; i <= 4; i++) {
+		num = (val >> (16 - 4 * i)) & 0xf;
+		if (num >= 10)
+			num += 7;
+		*str++ = '0' + num;
+	}
+	*str = '\0';
+}
+
+static void __init print_machine_type(void)
+{
+	static char mach_str[80] __initdata = "Detected machine-type number: ";
+	char type_str[5];
+	struct cpuid id;
+
+	get_cpu_id(&id);
+	u16_to_hex(type_str, id.machine);
+	strcat(mach_str, type_str);
+	strcat(mach_str, "\n");
+	sclp_early_printk(mach_str);
+}
+
+static void __init u16_to_decimal(char *str, u16 val)
+{
+	int div = 1;
+
+	while (div * 10 <= val)
+		div *= 10;
+	while (div) {
+		*str++ = '0' + val / div;
+		val %= div;
+		div /= 10;
+	}
+	*str = '\0';
+}
+
+static void __init print_missing_facilities(void)
+{
+	static char als_str[80] __initdata = "Missing facilities: ";
+	unsigned long val;
+	char val_str[6];
+	int i, j, first;
+
+	first = 1;
+	for (i = 0; i < ARRAY_SIZE(als); i++) {
+		val = ~S390_lowcore.stfle_fac_list[i] & als[i];
+		for (j = 0; j < BITS_PER_LONG; j++) {
+			if (!(val & (1UL << (BITS_PER_LONG - 1 - j))))
+				continue;
+			if (!first)
+				strcat(als_str, ",");
+			/*
+			 * Make sure we stay within one line. Consider that
+			 * each facility bit adds up to five characters and
+			 * z/VM adds a four character prefix.
+			 */
+			if (strlen(als_str) > 70) {
+				strcat(als_str, "\n");
+				sclp_early_printk(als_str);
+				*als_str = '\0';
+			}
+			u16_to_decimal(val_str, i * BITS_PER_LONG + j);
+			strcat(als_str, val_str);
+			first = 0;
+		}
+	}
+	strcat(als_str, "\n");
+	sclp_early_printk(als_str);
+	sclp_early_printk("See Principles of Operations for facility bits\n");
+}
+
+static void __init facility_mismatch(void)
+{
+	sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
+	print_machine_type();
+	print_missing_facilities();
+	disabled_wait(0x8badcccc);
+}
+
+void __init verify_facilities(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(S390_lowcore.stfle_fac_list); i++)
+		S390_lowcore.stfle_fac_list[i] = 0;
+	asm volatile(
+		"	stfl	0(0)\n"
+		: "=m" (S390_lowcore.stfl_fac_list));
+	S390_lowcore.stfle_fac_list[0] = (u64)S390_lowcore.stfl_fac_list << 32;
+	if (S390_lowcore.stfl_fac_list & 0x01000000) {
+		register unsigned long reg0 asm("0") = ARRAY_SIZE(als) - 1;
+
+		asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
+			     : "+d" (reg0)
+			     : "a" (&S390_lowcore.stfle_fac_list)
+			     : "memory", "cc");
+	}
+	for (i = 0; i < ARRAY_SIZE(als); i++) {
+		if ((S390_lowcore.stfle_fac_list[i] & als[i]) != als[i])
+			facility_mismatch();
+	}
+}
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 9b48e7b86fc8..855f7fdb1f61 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -16,12 +16,12 @@ targets += misc.o piggy.o sizes.h head.o
 KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
-OBJECTS := $(addprefix $(objtree)/arch/s390/kernel/, head.o ebcdic.o als.o)
+OBJECTS := $(objtree)/arch/s390/kernel/ebcdic.o
 OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o
 OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
-$(obj)/vmlinux: $(obj)/vmlinux.lds $(OBJECTS)
+$(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
 	$(call if_changed,ld)
 
 TRIM_HEAD_SIZE := 0x100000
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
new file mode 100644
index 000000000000..5c42f16a54c4
--- /dev/null
+++ b/arch/s390/boot/head.S
@@ -0,0 +1,339 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright IBM Corp. 1999, 2010
+ *
+ *    Author(s): Hartmut Penner <hp@de.ibm.com>
+ *		 Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		 Rob van der Heij <rvdhei@iae.nl>
+ *		 Heiko Carstens <heiko.carstens@de.ibm.com>
+ *
+ * There are 5 different IPL methods
+ *  1) load the image directly into ram at address 0 and do an PSW restart
+ *  2) linload will load the image from address 0x10000 to memory 0x10000
+ *     and start the code thru LPSW 0x0008000080010000 (VM only, deprecated)
+ *  3) generate the tape ipl header, store the generated image on a tape
+ *     and ipl from it
+ *     In case of SL tape you need to IPL 5 times to get past VOL1 etc
+ *  4) generate the vm reader ipl header, move the generated image to the
+ *     VM reader (use option NOH!) and do a ipl from reader (VM only)
+ *  5) direct call of start by the SALIPL loader
+ *  We use the cpuid to distinguish between VM and native ipl
+ *  params for kernel are pushed to 0x10400 (see setup.h)
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+#include <asm/page.h>
+#include <asm/ptrace.h>
+
+#define ARCH_OFFSET	4
+
+__HEAD
+
+#define IPL_BS	0x730
+	.org	0
+	.long	0x00080000,0x80000000+iplstart	# The first 24 bytes are loaded
+	.long	0x02000018,0x60000050		# by ipl to addresses 0-23.
+	.long	0x02000068,0x60000050		# (a PSW and two CCWs).
+	.fill	80-24,1,0x40			# bytes 24-79 are discarded !!
+	.long	0x020000f0,0x60000050		# The next 160 byte are loaded
+	.long	0x02000140,0x60000050		# to addresses 0x18-0xb7
+	.long	0x02000190,0x60000050		# They form the continuation
+	.long	0x020001e0,0x60000050		# of the CCW program started
+	.long	0x02000230,0x60000050		# by ipl and load the range
+	.long	0x02000280,0x60000050		# 0x0f0-0x730 from the image
+	.long	0x020002d0,0x60000050		# to the range 0x0f0-0x730
+	.long	0x02000320,0x60000050		# in memory. At the end of
+	.long	0x02000370,0x60000050		# the channel program the PSW
+	.long	0x020003c0,0x60000050		# at location 0 is loaded.
+	.long	0x02000410,0x60000050		# Initial processing starts
+	.long	0x02000460,0x60000050		# at 0x200 = iplstart.
+	.long	0x020004b0,0x60000050
+	.long	0x02000500,0x60000050
+	.long	0x02000550,0x60000050
+	.long	0x020005a0,0x60000050
+	.long	0x020005f0,0x60000050
+	.long	0x02000640,0x60000050
+	.long	0x02000690,0x60000050
+	.long	0x020006e0,0x20000050
+
+	.org	0x200
+
+#
+# subroutine to wait for end I/O
+#
+.Lirqwait:
+	mvc	__LC_IO_NEW_PSW(16),.Lnewpsw	# set up IO interrupt psw
+	lpsw	.Lwaitpsw
+.Lioint:
+	br	%r14
+	.align	8
+.Lnewpsw:
+	.quad	0x0000000080000000,.Lioint
+.Lwaitpsw:
+	.long	0x020a0000,0x80000000+.Lioint
+
+#
+# subroutine for loading cards from the reader
+#
+.Lloader:
+	la	%r4,0(%r14)
+	la	%r3,.Lorb		# r2 = address of orb into r2
+	la	%r5,.Lirb		# r4 = address of irb
+	la	%r6,.Lccws
+	la	%r7,20
+.Linit:
+	st	%r2,4(%r6)		# initialize CCW data addresses
+	la	%r2,0x50(%r2)
+	la	%r6,8(%r6)
+	bct	7,.Linit
+
+	lctl	%c6,%c6,.Lcr6		# set IO subclass mask
+	slr	%r2,%r2
+.Lldlp:
+	ssch	0(%r3)			# load chunk of 1600 bytes
+	bnz	.Llderr
+.Lwait4irq:
+	bas	%r14,.Lirqwait
+	c	%r1,__LC_SUBCHANNEL_ID	# compare subchannel number
+	bne	.Lwait4irq
+	tsch	0(%r5)
+
+	slr	%r0,%r0
+	ic	%r0,8(%r5)		# get device status
+	chi	%r0,8			# channel end ?
+	be	.Lcont
+	chi	%r0,12			# channel end + device end ?
+	be	.Lcont
+
+	l	%r0,4(%r5)
+	s	%r0,8(%r3)		# r0/8 = number of ccws executed
+	mhi	%r0,10			# *10 = number of bytes in ccws
+	lh	%r3,10(%r5)		# get residual count
+	sr	%r0,%r3 		# #ccws*80-residual=#bytes read
+	ar	%r2,%r0
+
+	br	%r4			# r2 contains the total size
+
+.Lcont:
+	ahi	%r2,0x640		# add 0x640 to total size
+	la	%r6,.Lccws
+	la	%r7,20
+.Lincr:
+	l	%r0,4(%r6)		# update CCW data addresses
+	ahi	%r0,0x640
+	st	%r0,4(%r6)
+	ahi	%r6,8
+	bct	7,.Lincr
+
+	b	.Lldlp
+.Llderr:
+	lpsw	.Lcrash
+
+	.align	8
+.Lorb:	.long	0x00000000,0x0080ff00,.Lccws
+.Lirb:	.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
+.Lcr6:	.long	0xff000000
+.Lloadp:.long	0,0
+	.align	8
+.Lcrash:.long	0x000a0000,0x00000000
+
+	.align	8
+.Lccws: .rept	19
+	.long	0x02600050,0x00000000
+	.endr
+	.long	0x02200050,0x00000000
+
+iplstart:
+	mvi	__LC_AR_MODE_ID,1	# set esame flag
+	slr	%r0,%r0			# set cpuid to zero
+	lhi	%r1,2			# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12		# switch to esame mode
+	bras	%r13,0f
+	.fill	16,4,0x0
+0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
+	sam31				# switch to 31 bit addressing mode
+	lh	%r1,__LC_SUBCHANNEL_ID	# test if subchannel number
+	bct	%r1,.Lnoload		#  is valid
+	l	%r1,__LC_SUBCHANNEL_ID	# load ipl subchannel number
+	la	%r2,IPL_BS		# load start address
+	bas	%r14,.Lloader		# load rest of ipl image
+	l	%r12,.Lparm		# pointer to parameter area
+	st	%r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number
+
+#
+# load parameter file from ipl device
+#
+.Lagain1:
+	l	%r2,.Linitrd		# ramdisk loc. is temp
+	bas	%r14,.Lloader		# load parameter file
+	ltr	%r2,%r2 		# got anything ?
+	bz	.Lnopf
+	chi	%r2,895
+	bnh	.Lnotrunc
+	la	%r2,895
+.Lnotrunc:
+	l	%r4,.Linitrd
+	clc	0(3,%r4),.L_hdr		# if it is HDRx
+	bz	.Lagain1		# skip dataset header
+	clc	0(3,%r4),.L_eof		# if it is EOFx
+	bz	.Lagain1		# skip dateset trailer
+	la	%r5,0(%r4,%r2)
+	lr	%r3,%r2
+	la	%r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
+	mvc	0(256,%r3),0(%r4)
+	mvc	256(256,%r3),256(%r4)
+	mvc	512(256,%r3),512(%r4)
+	mvc	768(122,%r3),768(%r4)
+	slr	%r0,%r0
+	b	.Lcntlp
+.Ldelspc:
+	ic	%r0,0(%r2,%r3)
+	chi	%r0,0x20		# is it a space ?
+	be	.Lcntlp
+	ahi	%r2,1
+	b	.Leolp
+.Lcntlp:
+	brct	%r2,.Ldelspc
+.Leolp:
+	slr	%r0,%r0
+	stc	%r0,0(%r2,%r3)		# terminate buffer
+.Lnopf:
+
+#
+# load ramdisk from ipl device
+#
+.Lagain2:
+	l	%r2,.Linitrd		# addr of ramdisk
+	st	%r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
+	bas	%r14,.Lloader		# load ramdisk
+	st	%r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd
+	ltr	%r2,%r2
+	bnz	.Lrdcont
+	st	%r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found
+.Lrdcont:
+	l	%r2,.Linitrd
+
+	clc	0(3,%r2),.L_hdr		# skip HDRx and EOFx
+	bz	.Lagain2
+	clc	0(3,%r2),.L_eof
+	bz	.Lagain2
+
+#
+# reset files in VM reader
+#
+	stidp	.Lcpuid			# store cpuid
+	tm	.Lcpuid,0xff		# running VM ?
+	bno	.Lnoreset
+	la	%r2,.Lreset
+	lhi	%r3,26
+	diag	%r2,%r3,8
+	la	%r5,.Lirb
+	stsch	0(%r5)			# check if irq is pending
+	tm	30(%r5),0x0f		# by verifying if any of the
+	bnz	.Lwaitforirq		# activity or status control
+	tm	31(%r5),0xff		# bits is set in the schib
+	bz	.Lnoreset
+.Lwaitforirq:
+	bas	%r14,.Lirqwait		# wait for IO interrupt
+	c	%r1,__LC_SUBCHANNEL_ID	# compare subchannel number
+	bne	.Lwaitforirq
+	la	%r5,.Lirb
+	tsch	0(%r5)
+.Lnoreset:
+	b	.Lnoload
+
+#
+# everything loaded, go for it
+#
+.Lnoload:
+	l	%r1,.Lstartup
+	br	%r1
+
+.Linitrd:.long _end			# default address of initrd
+.Lparm:	.long  PARMAREA
+.Lstartup: .long startup
+.Lreset:.byte	0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40
+	.byte	0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6
+	.byte	0xc8,0xd6,0xd3,0xc4	# "change rdr all keep nohold"
+.L_eof: .long	0xc5d6c600	 /* C'EOF' */
+.L_hdr: .long	0xc8c4d900	 /* C'HDR' */
+	.align	8
+.Lcpuid:.fill	8,1,0
+
+#
+# startup-code at 0x10000, running in absolute addressing mode
+# this is called either by the ipl loader or directly by PSW restart
+# or linload or SALIPL
+#
+	.org	0x10000
+ENTRY(startup)
+	j	.Lep_startup_normal
+	.org	0x10008
+#
+# This is a list of s390 kernel entry points. At address 0x1000f the number of
+# valid entry points is stored.
+#
+# IMPORTANT: Do not change this table, it is s390 kernel ABI!
+#
+	.ascii	"S390EP"
+	.byte	0x00,0x01
+#
+# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
+#
+	.org	0x10010
+ENTRY(startup_kdump)
+	j	.Lep_startup_kdump
+.Lep_startup_normal:
+	mvi	__LC_AR_MODE_ID,1	# set esame flag
+	slr	%r0,%r0 		# set cpuid to zero
+	lhi	%r1,2			# mode 2 = esame (dump)
+	sigp	%r1,%r0,0x12		# switch to esame mode
+	bras	%r13,0f
+	.fill	16,4,0x0
+0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
+	sam64				# switch to 64 bit addressing mode
+	basr	%r13,0			# get base
+.LPG0:
+	xc	0x200(256),0x200	# partially clear lowcore
+	xc	0x300(256),0x300
+	xc	0xe00(256),0xe00
+	xc	0xf00(256),0xf00
+	lctlg	%c0,%c15,0x200(%r0)	# initialize control registers
+	stcke	__LC_BOOT_CLOCK
+	mvc	__LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
+	spt	6f-.LPG0(%r13)
+	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
+	l	%r15,.Lstack-.LPG0(%r13)
+	ahi	%r15,-STACK_FRAME_OVERHEAD
+	brasl	%r14,verify_facilities
+# For uncompressed images, continue in
+# arch/s390/kernel/head64.S. For compressed images, continue in
+# arch/s390/boot/compressed/head.S.
+	jg	startup_continue
+
+.Lstack:
+	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
+	.align	8
+6:	.long	0x7fffffff,0xffffffff
+
+#include "head_kdump.S"
+
+#
+# params at 10400 (setup.h)
+#
+	.org	PARMAREA
+	.long	0,0			# IPL_DEVICE
+	.long	0,0			# INITRD_START
+	.long	0,0			# INITRD_SIZE
+	.long	0,0			# OLDMEM_BASE
+	.long	0,0			# OLDMEM_SIZE
+
+	.org	COMMAND_LINE
+	.byte	"root=/dev/ram0 ro"
+	.byte	0
+
+	.org	0x11000
diff --git a/arch/s390/boot/head_kdump.S b/arch/s390/boot/head_kdump.S
new file mode 100644
index 000000000000..174d6959bf5b
--- /dev/null
+++ b/arch/s390/boot/head_kdump.S
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * S390 kdump lowlevel functions (new kernel)
+ *
+ * Copyright IBM Corp. 2011
+ * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
+ */
+
+#include <asm/sigp.h>
+
+#define DATAMOVER_ADDR	0x4000
+#define COPY_PAGE_ADDR	0x6000
+
+#ifdef CONFIG_CRASH_DUMP
+
+#
+# kdump entry (new kernel - not yet relocated)
+#
+# Note: This code has to be position independent
+#
+
+.align 2
+.Lep_startup_kdump:
+	lhi	%r1,2				# mode 2 = esame (dump)
+	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to esame mode
+	sam64					# Switch to 64 bit addressing
+	basr	%r13,0
+.Lbase:
+	larl	%r2,.Lbase_addr			# Check, if we have been
+	lg	%r2,0(%r2)			# already relocated:
+	clgr	%r2,%r13			#
+	jne	.Lrelocate			# No : Start data mover
+	lghi	%r2,0				# Yes: Start kdump kernel
+	brasl	%r14,startup_kdump_relocated
+
+.Lrelocate:
+	larl	%r4,startup
+	lg	%r2,0x418(%r4)			# Get kdump base
+	lg	%r3,0x420(%r4)			# Get kdump size
+
+	larl	%r10,.Lcopy_start		# Source of data mover
+	lghi	%r8,DATAMOVER_ADDR		# Target of data mover
+	mvc	0(256,%r8),0(%r10)		# Copy data mover code
+
+	agr	%r8,%r2				# Copy data mover to
+	mvc	0(256,%r8),0(%r10)		# reserved mem
+
+	lghi	%r14,DATAMOVER_ADDR		# Jump to copied data mover
+	basr	%r14,%r14
+.Lbase_addr:
+	.quad	.Lbase
+
+#
+# kdump data mover code (runs at address DATAMOVER_ADDR)
+#
+# r2: kdump base address
+# r3: kdump size
+#
+.Lcopy_start:
+	basr	%r13,0				# Base
+0:
+	lgr	%r11,%r2			# Save kdump base address
+	lgr	%r12,%r2
+	agr	%r12,%r3			# Compute kdump end address
+
+	lghi	%r5,0
+	lghi	%r10,COPY_PAGE_ADDR		# Load copy page address
+1:
+	mvc	0(256,%r10),0(%r5)		# Copy old kernel to tmp
+	mvc	0(256,%r5),0(%r11)		# Copy new kernel to old
+	mvc	0(256,%r11),0(%r10)		# Copy tmp to new
+	aghi	%r11,256
+	aghi	%r5,256
+	clgr	%r11,%r12
+	jl	1b
+
+	lg	%r14,.Lstartup_kdump-0b(%r13)
+	basr	%r14,%r14			# Start relocated kernel
+.Lstartup_kdump:
+	.long	0x00000000,0x00000000 + startup_kdump_relocated
+.Lcopy_end:
+
+#
+# Startup of kdump (relocated new kernel)
+#
+.align 2
+startup_kdump_relocated:
+	basr	%r13,0
+0:	lpswe	.Lrestart_psw-0b(%r13)		# Start new kernel...
+.align	8
+.Lrestart_psw:
+	.quad	0x0000000080000000,0x0000000000000000 + startup
+#else
+.align 2
+.Lep_startup_kdump:
+	larl	%r13,startup_kdump_crash
+	lpswe	0(%r13)
+.align 8
+startup_kdump_crash:
+	.quad	0x0002000080000000,0x0000000000000000 + startup_kdump_crash
+#endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/s390/kernel/Makefile b/arch/s390/kernel/Makefile
index 2fed39b26b42..dbfd1730e631 100644
--- a/arch/s390/kernel/Makefile
+++ b/arch/s390/kernel/Makefile
@@ -9,38 +9,20 @@ ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_ftrace.o		= $(CC_FLAGS_FTRACE)
 
 # Do not trace early setup code
-CFLAGS_REMOVE_als.o		= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_early.o		= $(CC_FLAGS_FTRACE)
 CFLAGS_REMOVE_early_nobss.o	= $(CC_FLAGS_FTRACE)
 
 endif
 
-GCOV_PROFILE_als.o		:= n
 GCOV_PROFILE_early.o		:= n
 GCOV_PROFILE_early_nobss.o	:= n
 
-KCOV_INSTRUMENT_als.o		:= n
 KCOV_INSTRUMENT_early.o		:= n
 KCOV_INSTRUMENT_early_nobss.o	:= n
 
-UBSAN_SANITIZE_als.o		:= n
 UBSAN_SANITIZE_early.o		:= n
 UBSAN_SANITIZE_early_nobss.o	:= n
 
-#
-# Use -march=z900 for als.c to be able to print an error
-# message if the kernel is started on a machine which is too old
-#
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_EXPOLINE)
-CFLAGS_als.o		+= -march=z900
-AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o		+= -march=z900
-endif
-
-CFLAGS_als.o		+= -D__NO_FORTIFY
-
 #
 # Passing null pointers is ok for smp code, since we access the lowcore here.
 #
@@ -61,13 +43,13 @@ CFLAGS_ptrace.o		+= -DUTS_MACHINE='"$(UTS_MACHINE)"'
 
 obj-y	:= traps.o time.o process.o base.o early.o setup.o idle.o vtime.o
 obj-y	+= processor.o sys_s390.o ptrace.o signal.o cpcmd.o ebcdic.o nmi.o
-obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o als.o early_nobss.o
+obj-y	+= debug.o irq.o ipl.o dis.o diag.o vdso.o early_nobss.o
 obj-y	+= sysinfo.o jump_label.o lgr.o os_info.o machine_kexec.o pgm_check.o
 obj-y	+= runtime_instr.o cache.o fpu.o dumpstack.o guarded_storage.o sthyi.o
 obj-y	+= entry.o reipl.o relocate_kernel.o kdebugfs.o alternative.o
 obj-y	+= nospec-branch.o
 
-extra-y				+= head.o head64.o vmlinux.lds
+extra-y				+= head64.o vmlinux.lds
 
 obj-$(CONFIG_SYSFS)		+= nospec-sysfs.o
 CFLAGS_REMOVE_nospec-branch.o	+= $(CC_FLAGS_EXPOLINE)
@@ -99,5 +81,5 @@ obj-$(CONFIG_TRACEPOINTS)	+= trace.o
 obj-y				+= vdso64/
 obj-$(CONFIG_COMPAT)		+= vdso32/
 
-chkbss := head.o head64.o als.o early_nobss.o
+chkbss := head64.o early_nobss.o
 include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/kernel/als.c b/arch/s390/kernel/als.c
deleted file mode 100644
index d1892bf36cab..000000000000
--- a/arch/s390/kernel/als.c
+++ /dev/null
@@ -1,128 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- *    Copyright IBM Corp. 2016
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <asm/processor.h>
-#include <asm/facility.h>
-#include <asm/lowcore.h>
-#include <asm/sclp.h>
-#include "entry.h"
-
-/*
- * The code within this file will be called very early. It may _not_
- * access anything within the bss section, since that is not cleared
- * yet and may contain data (e.g. initrd) that must be saved by other
- * code.
- * For temporary objects the stack (16k) should be used.
- */
-
-static unsigned long als[] __initdata = { FACILITIES_ALS };
-
-static void __init u16_to_hex(char *str, u16 val)
-{
-	int i, num;
-
-	for (i = 1; i <= 4; i++) {
-		num = (val >> (16 - 4 * i)) & 0xf;
-		if (num >= 10)
-			num += 7;
-		*str++ = '0' + num;
-	}
-	*str = '\0';
-}
-
-static void __init print_machine_type(void)
-{
-	static char mach_str[80] __initdata = "Detected machine-type number: ";
-	char type_str[5];
-	struct cpuid id;
-
-	get_cpu_id(&id);
-	u16_to_hex(type_str, id.machine);
-	strcat(mach_str, type_str);
-	strcat(mach_str, "\n");
-	sclp_early_printk(mach_str);
-}
-
-static void __init u16_to_decimal(char *str, u16 val)
-{
-	int div = 1;
-
-	while (div * 10 <= val)
-		div *= 10;
-	while (div) {
-		*str++ = '0' + val / div;
-		val %= div;
-		div /= 10;
-	}
-	*str = '\0';
-}
-
-static void __init print_missing_facilities(void)
-{
-	static char als_str[80] __initdata = "Missing facilities: ";
-	unsigned long val;
-	char val_str[6];
-	int i, j, first;
-
-	first = 1;
-	for (i = 0; i < ARRAY_SIZE(als); i++) {
-		val = ~S390_lowcore.stfle_fac_list[i] & als[i];
-		for (j = 0; j < BITS_PER_LONG; j++) {
-			if (!(val & (1UL << (BITS_PER_LONG - 1 - j))))
-				continue;
-			if (!first)
-				strcat(als_str, ",");
-			/*
-			 * Make sure we stay within one line. Consider that
-			 * each facility bit adds up to five characters and
-			 * z/VM adds a four character prefix.
-			 */
-			if (strlen(als_str) > 70) {
-				strcat(als_str, "\n");
-				sclp_early_printk(als_str);
-				*als_str = '\0';
-			}
-			u16_to_decimal(val_str, i * BITS_PER_LONG + j);
-			strcat(als_str, val_str);
-			first = 0;
-		}
-	}
-	strcat(als_str, "\n");
-	sclp_early_printk(als_str);
-	sclp_early_printk("See Principles of Operations for facility bits\n");
-}
-
-static void __init facility_mismatch(void)
-{
-	sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
-	print_machine_type();
-	print_missing_facilities();
-	disabled_wait(0x8badcccc);
-}
-
-void __init verify_facilities(void)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(S390_lowcore.stfle_fac_list); i++)
-		S390_lowcore.stfle_fac_list[i] = 0;
-	asm volatile(
-		"	stfl	0(0)\n"
-		: "=m" (S390_lowcore.stfl_fac_list));
-	S390_lowcore.stfle_fac_list[0] = (u64)S390_lowcore.stfl_fac_list << 32;
-	if (S390_lowcore.stfl_fac_list & 0x01000000) {
-		register unsigned long reg0 asm("0") = ARRAY_SIZE(als) - 1;
-
-		asm volatile(".insn s,0xb2b00000,0(%1)" /* stfle */
-			     : "+d" (reg0)
-			     : "a" (&S390_lowcore.stfle_fac_list)
-			     : "memory", "cc");
-	}
-	for (i = 0; i < ARRAY_SIZE(als); i++) {
-		if ((S390_lowcore.stfle_fac_list[i] & als[i]) != als[i])
-			facility_mismatch();
-	}
-}
diff --git a/arch/s390/kernel/entry.h b/arch/s390/kernel/entry.h
index 961abfac2c5f..472fa2f1a4a5 100644
--- a/arch/s390/kernel/entry.h
+++ b/arch/s390/kernel/entry.h
@@ -83,7 +83,6 @@ long sys_s390_sthyi(unsigned long function_code, void __user *buffer, u64 __user
 
 DECLARE_PER_CPU(u64, mt_cycles[8]);
 
-void verify_facilities(void);
 void gs_load_bc_cb(struct pt_regs *regs);
 void set_fs_fixup(void);
 
diff --git a/arch/s390/kernel/head.S b/arch/s390/kernel/head.S
deleted file mode 100644
index 5c42f16a54c4..000000000000
--- a/arch/s390/kernel/head.S
+++ /dev/null
@@ -1,339 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 1999, 2010
- *
- *    Author(s): Hartmut Penner <hp@de.ibm.com>
- *		 Martin Schwidefsky <schwidefsky@de.ibm.com>
- *		 Rob van der Heij <rvdhei@iae.nl>
- *		 Heiko Carstens <heiko.carstens@de.ibm.com>
- *
- * There are 5 different IPL methods
- *  1) load the image directly into ram at address 0 and do an PSW restart
- *  2) linload will load the image from address 0x10000 to memory 0x10000
- *     and start the code thru LPSW 0x0008000080010000 (VM only, deprecated)
- *  3) generate the tape ipl header, store the generated image on a tape
- *     and ipl from it
- *     In case of SL tape you need to IPL 5 times to get past VOL1 etc
- *  4) generate the vm reader ipl header, move the generated image to the
- *     VM reader (use option NOH!) and do a ipl from reader (VM only)
- *  5) direct call of start by the SALIPL loader
- *  We use the cpuid to distinguish between VM and native ipl
- *  params for kernel are pushed to 0x10400 (see setup.h)
- *
- */
-
-#include <linux/init.h>
-#include <linux/linkage.h>
-#include <asm/asm-offsets.h>
-#include <asm/thread_info.h>
-#include <asm/page.h>
-#include <asm/ptrace.h>
-
-#define ARCH_OFFSET	4
-
-__HEAD
-
-#define IPL_BS	0x730
-	.org	0
-	.long	0x00080000,0x80000000+iplstart	# The first 24 bytes are loaded
-	.long	0x02000018,0x60000050		# by ipl to addresses 0-23.
-	.long	0x02000068,0x60000050		# (a PSW and two CCWs).
-	.fill	80-24,1,0x40			# bytes 24-79 are discarded !!
-	.long	0x020000f0,0x60000050		# The next 160 byte are loaded
-	.long	0x02000140,0x60000050		# to addresses 0x18-0xb7
-	.long	0x02000190,0x60000050		# They form the continuation
-	.long	0x020001e0,0x60000050		# of the CCW program started
-	.long	0x02000230,0x60000050		# by ipl and load the range
-	.long	0x02000280,0x60000050		# 0x0f0-0x730 from the image
-	.long	0x020002d0,0x60000050		# to the range 0x0f0-0x730
-	.long	0x02000320,0x60000050		# in memory. At the end of
-	.long	0x02000370,0x60000050		# the channel program the PSW
-	.long	0x020003c0,0x60000050		# at location 0 is loaded.
-	.long	0x02000410,0x60000050		# Initial processing starts
-	.long	0x02000460,0x60000050		# at 0x200 = iplstart.
-	.long	0x020004b0,0x60000050
-	.long	0x02000500,0x60000050
-	.long	0x02000550,0x60000050
-	.long	0x020005a0,0x60000050
-	.long	0x020005f0,0x60000050
-	.long	0x02000640,0x60000050
-	.long	0x02000690,0x60000050
-	.long	0x020006e0,0x20000050
-
-	.org	0x200
-
-#
-# subroutine to wait for end I/O
-#
-.Lirqwait:
-	mvc	__LC_IO_NEW_PSW(16),.Lnewpsw	# set up IO interrupt psw
-	lpsw	.Lwaitpsw
-.Lioint:
-	br	%r14
-	.align	8
-.Lnewpsw:
-	.quad	0x0000000080000000,.Lioint
-.Lwaitpsw:
-	.long	0x020a0000,0x80000000+.Lioint
-
-#
-# subroutine for loading cards from the reader
-#
-.Lloader:
-	la	%r4,0(%r14)
-	la	%r3,.Lorb		# r2 = address of orb into r2
-	la	%r5,.Lirb		# r4 = address of irb
-	la	%r6,.Lccws
-	la	%r7,20
-.Linit:
-	st	%r2,4(%r6)		# initialize CCW data addresses
-	la	%r2,0x50(%r2)
-	la	%r6,8(%r6)
-	bct	7,.Linit
-
-	lctl	%c6,%c6,.Lcr6		# set IO subclass mask
-	slr	%r2,%r2
-.Lldlp:
-	ssch	0(%r3)			# load chunk of 1600 bytes
-	bnz	.Llderr
-.Lwait4irq:
-	bas	%r14,.Lirqwait
-	c	%r1,__LC_SUBCHANNEL_ID	# compare subchannel number
-	bne	.Lwait4irq
-	tsch	0(%r5)
-
-	slr	%r0,%r0
-	ic	%r0,8(%r5)		# get device status
-	chi	%r0,8			# channel end ?
-	be	.Lcont
-	chi	%r0,12			# channel end + device end ?
-	be	.Lcont
-
-	l	%r0,4(%r5)
-	s	%r0,8(%r3)		# r0/8 = number of ccws executed
-	mhi	%r0,10			# *10 = number of bytes in ccws
-	lh	%r3,10(%r5)		# get residual count
-	sr	%r0,%r3 		# #ccws*80-residual=#bytes read
-	ar	%r2,%r0
-
-	br	%r4			# r2 contains the total size
-
-.Lcont:
-	ahi	%r2,0x640		# add 0x640 to total size
-	la	%r6,.Lccws
-	la	%r7,20
-.Lincr:
-	l	%r0,4(%r6)		# update CCW data addresses
-	ahi	%r0,0x640
-	st	%r0,4(%r6)
-	ahi	%r6,8
-	bct	7,.Lincr
-
-	b	.Lldlp
-.Llderr:
-	lpsw	.Lcrash
-
-	.align	8
-.Lorb:	.long	0x00000000,0x0080ff00,.Lccws
-.Lirb:	.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-.Lcr6:	.long	0xff000000
-.Lloadp:.long	0,0
-	.align	8
-.Lcrash:.long	0x000a0000,0x00000000
-
-	.align	8
-.Lccws: .rept	19
-	.long	0x02600050,0x00000000
-	.endr
-	.long	0x02200050,0x00000000
-
-iplstart:
-	mvi	__LC_AR_MODE_ID,1	# set esame flag
-	slr	%r0,%r0			# set cpuid to zero
-	lhi	%r1,2			# mode 2 = esame (dump)
-	sigp	%r1,%r0,0x12		# switch to esame mode
-	bras	%r13,0f
-	.fill	16,4,0x0
-0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
-	sam31				# switch to 31 bit addressing mode
-	lh	%r1,__LC_SUBCHANNEL_ID	# test if subchannel number
-	bct	%r1,.Lnoload		#  is valid
-	l	%r1,__LC_SUBCHANNEL_ID	# load ipl subchannel number
-	la	%r2,IPL_BS		# load start address
-	bas	%r14,.Lloader		# load rest of ipl image
-	l	%r12,.Lparm		# pointer to parameter area
-	st	%r1,IPL_DEVICE+ARCH_OFFSET-PARMAREA(%r12) # save ipl device number
-
-#
-# load parameter file from ipl device
-#
-.Lagain1:
-	l	%r2,.Linitrd		# ramdisk loc. is temp
-	bas	%r14,.Lloader		# load parameter file
-	ltr	%r2,%r2 		# got anything ?
-	bz	.Lnopf
-	chi	%r2,895
-	bnh	.Lnotrunc
-	la	%r2,895
-.Lnotrunc:
-	l	%r4,.Linitrd
-	clc	0(3,%r4),.L_hdr		# if it is HDRx
-	bz	.Lagain1		# skip dataset header
-	clc	0(3,%r4),.L_eof		# if it is EOFx
-	bz	.Lagain1		# skip dateset trailer
-	la	%r5,0(%r4,%r2)
-	lr	%r3,%r2
-	la	%r3,COMMAND_LINE-PARMAREA(%r12) # load adr. of command line
-	mvc	0(256,%r3),0(%r4)
-	mvc	256(256,%r3),256(%r4)
-	mvc	512(256,%r3),512(%r4)
-	mvc	768(122,%r3),768(%r4)
-	slr	%r0,%r0
-	b	.Lcntlp
-.Ldelspc:
-	ic	%r0,0(%r2,%r3)
-	chi	%r0,0x20		# is it a space ?
-	be	.Lcntlp
-	ahi	%r2,1
-	b	.Leolp
-.Lcntlp:
-	brct	%r2,.Ldelspc
-.Leolp:
-	slr	%r0,%r0
-	stc	%r0,0(%r2,%r3)		# terminate buffer
-.Lnopf:
-
-#
-# load ramdisk from ipl device
-#
-.Lagain2:
-	l	%r2,.Linitrd		# addr of ramdisk
-	st	%r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12)
-	bas	%r14,.Lloader		# load ramdisk
-	st	%r2,INITRD_SIZE+ARCH_OFFSET-PARMAREA(%r12) # store size of rd
-	ltr	%r2,%r2
-	bnz	.Lrdcont
-	st	%r2,INITRD_START+ARCH_OFFSET-PARMAREA(%r12) # no ramdisk found
-.Lrdcont:
-	l	%r2,.Linitrd
-
-	clc	0(3,%r2),.L_hdr		# skip HDRx and EOFx
-	bz	.Lagain2
-	clc	0(3,%r2),.L_eof
-	bz	.Lagain2
-
-#
-# reset files in VM reader
-#
-	stidp	.Lcpuid			# store cpuid
-	tm	.Lcpuid,0xff		# running VM ?
-	bno	.Lnoreset
-	la	%r2,.Lreset
-	lhi	%r3,26
-	diag	%r2,%r3,8
-	la	%r5,.Lirb
-	stsch	0(%r5)			# check if irq is pending
-	tm	30(%r5),0x0f		# by verifying if any of the
-	bnz	.Lwaitforirq		# activity or status control
-	tm	31(%r5),0xff		# bits is set in the schib
-	bz	.Lnoreset
-.Lwaitforirq:
-	bas	%r14,.Lirqwait		# wait for IO interrupt
-	c	%r1,__LC_SUBCHANNEL_ID	# compare subchannel number
-	bne	.Lwaitforirq
-	la	%r5,.Lirb
-	tsch	0(%r5)
-.Lnoreset:
-	b	.Lnoload
-
-#
-# everything loaded, go for it
-#
-.Lnoload:
-	l	%r1,.Lstartup
-	br	%r1
-
-.Linitrd:.long _end			# default address of initrd
-.Lparm:	.long  PARMAREA
-.Lstartup: .long startup
-.Lreset:.byte	0xc3,0xc8,0xc1,0xd5,0xc7,0xc5,0x40,0xd9,0xc4,0xd9,0x40
-	.byte	0xc1,0xd3,0xd3,0x40,0xd2,0xc5,0xc5,0xd7,0x40,0xd5,0xd6
-	.byte	0xc8,0xd6,0xd3,0xc4	# "change rdr all keep nohold"
-.L_eof: .long	0xc5d6c600	 /* C'EOF' */
-.L_hdr: .long	0xc8c4d900	 /* C'HDR' */
-	.align	8
-.Lcpuid:.fill	8,1,0
-
-#
-# startup-code at 0x10000, running in absolute addressing mode
-# this is called either by the ipl loader or directly by PSW restart
-# or linload or SALIPL
-#
-	.org	0x10000
-ENTRY(startup)
-	j	.Lep_startup_normal
-	.org	0x10008
-#
-# This is a list of s390 kernel entry points. At address 0x1000f the number of
-# valid entry points is stored.
-#
-# IMPORTANT: Do not change this table, it is s390 kernel ABI!
-#
-	.ascii	"S390EP"
-	.byte	0x00,0x01
-#
-# kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
-#
-	.org	0x10010
-ENTRY(startup_kdump)
-	j	.Lep_startup_kdump
-.Lep_startup_normal:
-	mvi	__LC_AR_MODE_ID,1	# set esame flag
-	slr	%r0,%r0 		# set cpuid to zero
-	lhi	%r1,2			# mode 2 = esame (dump)
-	sigp	%r1,%r0,0x12		# switch to esame mode
-	bras	%r13,0f
-	.fill	16,4,0x0
-0:	lmh	%r0,%r15,0(%r13)	# clear high-order half of gprs
-	sam64				# switch to 64 bit addressing mode
-	basr	%r13,0			# get base
-.LPG0:
-	xc	0x200(256),0x200	# partially clear lowcore
-	xc	0x300(256),0x300
-	xc	0xe00(256),0xe00
-	xc	0xf00(256),0xf00
-	lctlg	%c0,%c15,0x200(%r0)	# initialize control registers
-	stcke	__LC_BOOT_CLOCK
-	mvc	__LC_LAST_UPDATE_CLOCK(8),__LC_BOOT_CLOCK+1
-	spt	6f-.LPG0(%r13)
-	mvc	__LC_LAST_UPDATE_TIMER(8),6f-.LPG0(%r13)
-	l	%r15,.Lstack-.LPG0(%r13)
-	ahi	%r15,-STACK_FRAME_OVERHEAD
-	brasl	%r14,verify_facilities
-# For uncompressed images, continue in
-# arch/s390/kernel/head64.S. For compressed images, continue in
-# arch/s390/boot/compressed/head.S.
-	jg	startup_continue
-
-.Lstack:
-	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
-	.align	8
-6:	.long	0x7fffffff,0xffffffff
-
-#include "head_kdump.S"
-
-#
-# params at 10400 (setup.h)
-#
-	.org	PARMAREA
-	.long	0,0			# IPL_DEVICE
-	.long	0,0			# INITRD_START
-	.long	0,0			# INITRD_SIZE
-	.long	0,0			# OLDMEM_BASE
-	.long	0,0			# OLDMEM_SIZE
-
-	.org	COMMAND_LINE
-	.byte	"root=/dev/ram0 ro"
-	.byte	0
-
-	.org	0x11000
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 53e5cb0d6f7f..6a840bcb2715 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -16,7 +16,7 @@
 #include <asm/page.h>
 
 __HEAD
-	.org	0x100000 - 0x11000		# head.o ends at 0x11000
+	.org	0x100000
 ENTRY(startup_continue)
 	tm	__LC_STFLE_FAC_LIST+5,0x80	# LPP available ?
 	jz	0f
diff --git a/arch/s390/kernel/head_kdump.S b/arch/s390/kernel/head_kdump.S
deleted file mode 100644
index 174d6959bf5b..000000000000
--- a/arch/s390/kernel/head_kdump.S
+++ /dev/null
@@ -1,101 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * S390 kdump lowlevel functions (new kernel)
- *
- * Copyright IBM Corp. 2011
- * Author(s): Michael Holzheu <holzheu@linux.vnet.ibm.com>
- */
-
-#include <asm/sigp.h>
-
-#define DATAMOVER_ADDR	0x4000
-#define COPY_PAGE_ADDR	0x6000
-
-#ifdef CONFIG_CRASH_DUMP
-
-#
-# kdump entry (new kernel - not yet relocated)
-#
-# Note: This code has to be position independent
-#
-
-.align 2
-.Lep_startup_kdump:
-	lhi	%r1,2				# mode 2 = esame (dump)
-	sigp	%r1,%r0,SIGP_SET_ARCHITECTURE	# Switch to esame mode
-	sam64					# Switch to 64 bit addressing
-	basr	%r13,0
-.Lbase:
-	larl	%r2,.Lbase_addr			# Check, if we have been
-	lg	%r2,0(%r2)			# already relocated:
-	clgr	%r2,%r13			#
-	jne	.Lrelocate			# No : Start data mover
-	lghi	%r2,0				# Yes: Start kdump kernel
-	brasl	%r14,startup_kdump_relocated
-
-.Lrelocate:
-	larl	%r4,startup
-	lg	%r2,0x418(%r4)			# Get kdump base
-	lg	%r3,0x420(%r4)			# Get kdump size
-
-	larl	%r10,.Lcopy_start		# Source of data mover
-	lghi	%r8,DATAMOVER_ADDR		# Target of data mover
-	mvc	0(256,%r8),0(%r10)		# Copy data mover code
-
-	agr	%r8,%r2				# Copy data mover to
-	mvc	0(256,%r8),0(%r10)		# reserved mem
-
-	lghi	%r14,DATAMOVER_ADDR		# Jump to copied data mover
-	basr	%r14,%r14
-.Lbase_addr:
-	.quad	.Lbase
-
-#
-# kdump data mover code (runs at address DATAMOVER_ADDR)
-#
-# r2: kdump base address
-# r3: kdump size
-#
-.Lcopy_start:
-	basr	%r13,0				# Base
-0:
-	lgr	%r11,%r2			# Save kdump base address
-	lgr	%r12,%r2
-	agr	%r12,%r3			# Compute kdump end address
-
-	lghi	%r5,0
-	lghi	%r10,COPY_PAGE_ADDR		# Load copy page address
-1:
-	mvc	0(256,%r10),0(%r5)		# Copy old kernel to tmp
-	mvc	0(256,%r5),0(%r11)		# Copy new kernel to old
-	mvc	0(256,%r11),0(%r10)		# Copy tmp to new
-	aghi	%r11,256
-	aghi	%r5,256
-	clgr	%r11,%r12
-	jl	1b
-
-	lg	%r14,.Lstartup_kdump-0b(%r13)
-	basr	%r14,%r14			# Start relocated kernel
-.Lstartup_kdump:
-	.long	0x00000000,0x00000000 + startup_kdump_relocated
-.Lcopy_end:
-
-#
-# Startup of kdump (relocated new kernel)
-#
-.align 2
-startup_kdump_relocated:
-	basr	%r13,0
-0:	lpswe	.Lrestart_psw-0b(%r13)		# Start new kernel...
-.align	8
-.Lrestart_psw:
-	.quad	0x0000000080000000,0x0000000000000000 + startup
-#else
-.align 2
-.Lep_startup_kdump:
-	larl	%r13,startup_kdump_crash
-	lpswe	0(%r13)
-.align 8
-startup_kdump_crash:
-	.quad	0x0002000080000000,0x0000000000000000 + startup_kdump_crash
-#endif /* CONFIG_CRASH_DUMP */
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index f0414f52817b..31f530b8a1b3 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -19,7 +19,7 @@
 
 OUTPUT_FORMAT("elf64-s390", "elf64-s390", "elf64-s390")
 OUTPUT_ARCH(s390:64-bit)
-ENTRY(startup)
+ENTRY(startup_continue)
 jiffies = jiffies_64;
 
 PHDRS {
-- 
cgit v1.2.3


From a5802353b1ee8e4c97e5c255bed7651b924098fa Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 13 Jun 2018 06:25:36 +0200
Subject: s390/decompressor: rename entry point to startup_decompressor

Rename the decompressor entry point to startup_decompressor to
avoid confusion, leaving startup_continue as the entry point of the
uncompressed image.

Also remove obsolete comment, as the decompressor code is
unconditionally called from boot/head.S now.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/head.S | 2 +-
 arch/s390/boot/head.S            | 5 +----
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/arch/s390/boot/compressed/head.S b/arch/s390/boot/compressed/head.S
index 1c69907dba28..df8dbbc17bcc 100644
--- a/arch/s390/boot/compressed/head.S
+++ b/arch/s390/boot/compressed/head.S
@@ -15,7 +15,7 @@
 #include "sizes.h"
 
 __HEAD
-ENTRY(startup_continue)
+ENTRY(startup_decompressor)
 	basr	%r13,0			# get base
 .LPG1:
 	# setup stack
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index 5c42f16a54c4..8d98463ca7d0 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -310,10 +310,7 @@ ENTRY(startup_kdump)
 	l	%r15,.Lstack-.LPG0(%r13)
 	ahi	%r15,-STACK_FRAME_OVERHEAD
 	brasl	%r14,verify_facilities
-# For uncompressed images, continue in
-# arch/s390/kernel/head64.S. For compressed images, continue in
-# arch/s390/boot/compressed/head.S.
-	jg	startup_continue
+	jg	startup_decompressor
 
 .Lstack:
 	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
-- 
cgit v1.2.3


From 2dd26659e3167526212b7b3a18a5c747058aff1e Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 15:14:51 +0200
Subject: s390/als: avoid .init.* sections usage

Since als.c is the part of the decompressor only, there is no point in
using init sections for code and data. That's just creating extra
sections in the decompressor image.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/als.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/arch/s390/boot/als.c b/arch/s390/boot/als.c
index b6287a99a7b8..d592e0d90d9f 100644
--- a/arch/s390/boot/als.c
+++ b/arch/s390/boot/als.c
@@ -3,7 +3,6 @@
  *    Copyright IBM Corp. 2016
  */
 #include <linux/kernel.h>
-#include <linux/init.h>
 #include <asm/processor.h>
 #include <asm/facility.h>
 #include <asm/lowcore.h>
@@ -17,9 +16,9 @@
  * For temporary objects the stack (16k) should be used.
  */
 
-static unsigned long als[] __initdata = { FACILITIES_ALS };
+static unsigned long als[] = { FACILITIES_ALS };
 
-static void __init u16_to_hex(char *str, u16 val)
+static void u16_to_hex(char *str, u16 val)
 {
 	int i, num;
 
@@ -32,9 +31,9 @@ static void __init u16_to_hex(char *str, u16 val)
 	*str = '\0';
 }
 
-static void __init print_machine_type(void)
+static void print_machine_type(void)
 {
-	static char mach_str[80] __initdata = "Detected machine-type number: ";
+	static char mach_str[80] = "Detected machine-type number: ";
 	char type_str[5];
 	struct cpuid id;
 
@@ -45,7 +44,7 @@ static void __init print_machine_type(void)
 	sclp_early_printk(mach_str);
 }
 
-static void __init u16_to_decimal(char *str, u16 val)
+static void u16_to_decimal(char *str, u16 val)
 {
 	int div = 1;
 
@@ -59,9 +58,9 @@ static void __init u16_to_decimal(char *str, u16 val)
 	*str = '\0';
 }
 
-static void __init print_missing_facilities(void)
+static void print_missing_facilities(void)
 {
-	static char als_str[80] __initdata = "Missing facilities: ";
+	static char als_str[80] = "Missing facilities: ";
 	unsigned long val;
 	char val_str[6];
 	int i, j, first;
@@ -94,7 +93,7 @@ static void __init print_missing_facilities(void)
 	sclp_early_printk("See Principles of Operations for facility bits\n");
 }
 
-static void __init facility_mismatch(void)
+static void facility_mismatch(void)
 {
 	sclp_early_printk("The Linux kernel requires more recent processor hardware\n");
 	print_machine_type();
@@ -102,7 +101,7 @@ static void __init facility_mismatch(void)
 	disabled_wait(0x8badcccc);
 }
 
-void __init verify_facilities(void)
+void verify_facilities(void)
 {
 	int i;
 
-- 
cgit v1.2.3


From a1d7d91f105413750b5c8fb6a13a8c969a8b1f81 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 15:52:01 +0200
Subject: s390/decompressor: avoid reusing uncompressed image objects

Re-compile ebcdic.c and sclp_early_core.c for the decompressor,
using proper decompressor CFLAGS. This also allows to potentially use
instrumentation for those files when built for the main kernel image.

With kbuild there is no easy way to re-compile a source file from
another directory. Bypass ugly rules and Makefile meta-programming
with relative path includes of original files.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/Makefile            | 16 ++++++++++------
 arch/s390/boot/compressed/Makefile |  4 +---
 arch/s390/boot/ebcdic.c            |  2 ++
 arch/s390/boot/sclp_early_core.c   |  2 ++
 drivers/s390/char/Makefile         |  5 -----
 5 files changed, 15 insertions(+), 14 deletions(-)
 create mode 100644 arch/s390/boot/ebcdic.c
 create mode 100644 arch/s390/boot/sclp_early_core.c

diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 05e92d43d383..5cf30b732eb6 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -15,14 +15,18 @@ KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 # message if the kernel is started on a machine which is too old
 #
 ifneq ($(CC_FLAGS_MARCH),-march=z900)
-AFLAGS_REMOVE_head.o	+= $(CC_FLAGS_MARCH)
-AFLAGS_head.o		+= -march=z900
-CFLAGS_REMOVE_als.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_als.o		+= -march=z900
+AFLAGS_REMOVE_head.o		+= $(CC_FLAGS_MARCH)
+AFLAGS_head.o			+= -march=z900
+CFLAGS_REMOVE_als.o		+= $(CC_FLAGS_MARCH)
+CFLAGS_als.o			+= -march=z900
+CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
+CFLAGS_sclp_early_core.o	+= -march=z900
 endif
 
-obj-y	:= head.o als.o
-targets	:= bzImage startup.a $(obj-y)
+CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
+
+obj-y	:= head.o als.o ebcdic.o sclp_early_core.o
+targets	:= bzImage setup.a $(obj-y)
 subdir-	:= compressed
 
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 855f7fdb1f61..86fe47509f75 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -16,9 +16,7 @@ targets += misc.o piggy.o sizes.h head.o
 KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
-OBJECTS := $(objtree)/arch/s390/kernel/ebcdic.o
-OBJECTS += $(objtree)/drivers/s390/char/sclp_early_core.o
-OBJECTS += $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
+OBJECTS := $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
diff --git a/arch/s390/boot/ebcdic.c b/arch/s390/boot/ebcdic.c
new file mode 100644
index 000000000000..7391e7d36086
--- /dev/null
+++ b/arch/s390/boot/ebcdic.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../kernel/ebcdic.c"
diff --git a/arch/s390/boot/sclp_early_core.c b/arch/s390/boot/sclp_early_core.c
new file mode 100644
index 000000000000..5a19fd7020b5
--- /dev/null
+++ b/arch/s390/boot/sclp_early_core.c
@@ -0,0 +1,2 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "../../../drivers/s390/char/sclp_early_core.c"
diff --git a/drivers/s390/char/Makefile b/drivers/s390/char/Makefile
index 0a4c13e1e76e..c6ab34f94b1b 100644
--- a/drivers/s390/char/Makefile
+++ b/drivers/s390/char/Makefile
@@ -12,11 +12,6 @@ GCOV_PROFILE_sclp_early_core.o		:= n
 KCOV_INSTRUMENT_sclp_early_core.o	:= n
 UBSAN_SANITIZE_sclp_early_core.o	:= n
 
-ifneq ($(CC_FLAGS_MARCH),-march=z900)
-CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
-CFLAGS_sclp_early_core.o		+= -march=z900
-endif
-
 CFLAGS_sclp_early_core.o		+= -D__NO_FORTIFY
 
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_EXPOLINE)
-- 
cgit v1.2.3


From cad5b35da9f7e429131592421c463a93703bb02e Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 22:58:50 +0200
Subject: s390/decompressor: reuse lib/mem.S for mem functions

Reusing arch/s390/lib/mem.S file solves a problem that sclp_early_core.c
and its dependencies have to be compiled with -march=z900 (no need to
compile compressed/misc.c with -march=z900). This also allows to avoid
mem functions duplicates, makes code a bit smaller and optimized mem
functions are utilized.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/Makefile          |  4 +++-
 arch/s390/boot/compressed/misc.c | 37 -------------------------------------
 arch/s390/boot/mem.S             |  2 ++
 3 files changed, 5 insertions(+), 38 deletions(-)
 create mode 100644 arch/s390/boot/mem.S

diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 5cf30b732eb6..70b50b41eda9 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -17,6 +17,8 @@ KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 ifneq ($(CC_FLAGS_MARCH),-march=z900)
 AFLAGS_REMOVE_head.o		+= $(CC_FLAGS_MARCH)
 AFLAGS_head.o			+= -march=z900
+AFLAGS_REMOVE_mem.o		+= $(CC_FLAGS_MARCH)
+AFLAGS_mem.o			+= -march=z900
 CFLAGS_REMOVE_als.o		+= $(CC_FLAGS_MARCH)
 CFLAGS_als.o			+= -march=z900
 CFLAGS_REMOVE_sclp_early_core.o	+= $(CC_FLAGS_MARCH)
@@ -25,7 +27,7 @@ endif
 
 CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
-obj-y	:= head.o als.o ebcdic.o sclp_early_core.o
+obj-y	:= head.o als.o ebcdic.o sclp_early_core.o mem.o
 targets	:= bzImage setup.a $(obj-y)
 subdir-	:= compressed
 
diff --git a/arch/s390/boot/compressed/misc.c b/arch/s390/boot/compressed/misc.c
index 511b2cc9b91a..f66ad73c205b 100644
--- a/arch/s390/boot/compressed/misc.c
+++ b/arch/s390/boot/compressed/misc.c
@@ -71,43 +71,6 @@ static int puts(const char *s)
 	return 0;
 }
 
-void *memset(void *s, int c, size_t n)
-{
-	char *xs;
-
-	xs = s;
-	while (n--)
-		*xs++ = c;
-	return s;
-}
-
-void *memcpy(void *dest, const void *src, size_t n)
-{
-	const char *s = src;
-	char *d = dest;
-
-	while (n--)
-		*d++ = *s++;
-	return dest;
-}
-
-void *memmove(void *dest, const void *src, size_t n)
-{
-	const char *s = src;
-	char *d = dest;
-
-	if (d <= s) {
-		while (n--)
-			*d++ = *s++;
-	} else {
-		d += n;
-		s += n;
-		while (n--)
-			*--d = *--s;
-	}
-	return dest;
-}
-
 static void error(char *x)
 {
 	unsigned long long psw = 0x000a0000deadbeefULL;
diff --git a/arch/s390/boot/mem.S b/arch/s390/boot/mem.S
new file mode 100644
index 000000000000..b33463633f03
--- /dev/null
+++ b/arch/s390/boot/mem.S
@@ -0,0 +1,2 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include "../lib/mem.S"
-- 
cgit v1.2.3


From 4560ff1386e35f51f7bafa0107fe4e0eb31db090 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 21:52:45 +0200
Subject: s390/decompressor: avoid repeating objects list in Makefile

Optimize the decompressor's Makefile to have a single objects list.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/Makefile | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 86fe47509f75..7cfca96b48ad 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -9,14 +9,15 @@ KCOV_INSTRUMENT := n
 GCOV_PROFILE := n
 UBSAN_SANITIZE := n
 
+obj-y	:= head.o misc.o piggy.o
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
-targets += misc.o piggy.o sizes.h head.o
+targets += sizes.h $(obj-y)
 
 KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
 
-OBJECTS := $(obj)/head.o $(obj)/misc.o $(obj)/piggy.o
+OBJECTS := $(addprefix $(obj)/,$(obj-y))
 
 LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
-- 
cgit v1.2.3


From 78c95647e76d830e8193ac254a012b0e56d5675d Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 16 May 2018 10:50:02 +0200
Subject: s390: add custom target and make path extension optional for .bss
 check

"chkbss-target" could be now used to override default target .bss check
is bound to. Objects to be checked are only path extended when needed.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/scripts/Makefile.chkbss | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
index d92f2d94a5d9..fb0a11bd520c 100644
--- a/arch/s390/scripts/Makefile.chkbss
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -8,7 +8,12 @@ define cmd_chkbss
 	touch $@;
 endef
 
-$(obj)/built-in.a: $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+chkbss-target ?= $(obj)/built-in.a
+ifneq (,$(findstring /,$(chkbss)))
+$(chkbss-target): $(patsubst %, %.chkbss, $(chkbss))
+else
+$(chkbss-target): $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+endif
 
 %.o.chkbss: %.o
 	$(call cmd,chkbss)
-- 
cgit v1.2.3


From 0580bce1312f75362662881c938192856167cf7e Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 16 May 2018 10:57:44 +0200
Subject: s390/decompressor: extend .bss check for early code

Cover the decompressor code with no .bss usage compile time check.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/Makefile            | 4 ++++
 arch/s390/boot/compressed/Makefile | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index 70b50b41eda9..a1ca3b805c74 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -48,3 +48,7 @@ $(obj)/startup.a: $(OBJECTS) FORCE
 install: $(CONFIGURE) $(obj)/bzImage
 	sh -x  $(srctree)/$(obj)/install.sh $(KERNELRELEASE) $(obj)/bzImage \
 	      System.map "$(INSTALL_PATH)"
+
+chkbss := $(OBJECTS)
+chkbss-target := $(obj)/startup.a
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 7cfca96b48ad..9665131b3cb2 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -74,3 +74,7 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
 LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
 $(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
 	$(call if_changed,ld)
+
+chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS))
+chkbss-target := $(obj)/vmlinux.bin
+include $(srctree)/arch/s390/scripts/Makefile.chkbss
-- 
cgit v1.2.3


From b8326bf52e0894004c790183228c1ec18aae7f72 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 21:59:13 +0200
Subject: s390/decompressor: allow preprocessor in piggy.o linker script

Rename vmlinux.scr to vmlinux.scr.lds.S and add it to build rules to
enable preprocessor for it.

Also add vmlinux.scr.lds to local .gitignore

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/.gitignore        |  1 +
 arch/s390/boot/compressed/Makefile          |  4 ++--
 arch/s390/boot/compressed/vmlinux.scr       | 11 -----------
 arch/s390/boot/compressed/vmlinux.scr.lds.S | 11 +++++++++++
 4 files changed, 14 insertions(+), 13 deletions(-)
 delete mode 100644 arch/s390/boot/compressed/vmlinux.scr
 create mode 100644 arch/s390/boot/compressed/vmlinux.scr.lds.S

diff --git a/arch/s390/boot/compressed/.gitignore b/arch/s390/boot/compressed/.gitignore
index 2088cc140629..45aeb4f08752 100644
--- a/arch/s390/boot/compressed/.gitignore
+++ b/arch/s390/boot/compressed/.gitignore
@@ -1,4 +1,5 @@
 sizes.h
 vmlinux
 vmlinux.lds
+vmlinux.scr.lds
 vmlinux.bin.full
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 9665131b3cb2..704c1f4dd802 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -12,7 +12,7 @@ UBSAN_SANITIZE := n
 obj-y	:= head.o misc.o piggy.o
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
-targets += sizes.h $(obj-y)
+targets += vmlinux.scr.lds sizes.h $(obj-y)
 
 KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
@@ -72,7 +72,7 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
 	$(call if_changed,xzkern)
 
 LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr $(obj)/vmlinux.bin.$(suffix-y)
+$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin.$(suffix-y)
 	$(call if_changed,ld)
 
 chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS))
diff --git a/arch/s390/boot/compressed/vmlinux.scr b/arch/s390/boot/compressed/vmlinux.scr
deleted file mode 100644
index 42a242597f34..000000000000
--- a/arch/s390/boot/compressed/vmlinux.scr
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-SECTIONS
-{
-  .rodata.compressed : {
-	input_len = .;
-	LONG(input_data_end - input_data) input_data = .;
-	*(.data)
-	output_len = . - 4;
-	input_data_end = .;
-	}
-}
diff --git a/arch/s390/boot/compressed/vmlinux.scr.lds.S b/arch/s390/boot/compressed/vmlinux.scr.lds.S
new file mode 100644
index 000000000000..42a242597f34
--- /dev/null
+++ b/arch/s390/boot/compressed/vmlinux.scr.lds.S
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+SECTIONS
+{
+  .rodata.compressed : {
+	input_len = .;
+	LONG(input_data_end - input_data) input_data = .;
+	*(.data)
+	output_len = . - 4;
+	input_data_end = .;
+	}
+}
-- 
cgit v1.2.3


From c98b6c679a3b8032a2dd5c9724f489e1b959e5a7 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 13 Jun 2018 06:34:45 +0200
Subject: s390/decompressor: allow to pack uncompressed vmlinux.bin into
 piggy.o

If none of compression methods defined, leave suffix-y empty, so that
plain uncompressed vmlinux.bin could be reused instead.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/Makefile | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 704c1f4dd802..438e1a50e0b5 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -51,12 +51,12 @@ $(obj)/vmlinux.bin: $(obj)/vmlinux.bin.full
 
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
 
-suffix-$(CONFIG_KERNEL_GZIP)  := gz
-suffix-$(CONFIG_KERNEL_BZIP2) := bz2
-suffix-$(CONFIG_KERNEL_LZ4)  := lz4
-suffix-$(CONFIG_KERNEL_LZMA)  := lzma
-suffix-$(CONFIG_KERNEL_LZO)  := lzo
-suffix-$(CONFIG_KERNEL_XZ)  := xz
+suffix-$(CONFIG_KERNEL_GZIP)  := .gz
+suffix-$(CONFIG_KERNEL_BZIP2) := .bz2
+suffix-$(CONFIG_KERNEL_LZ4)  := .lz4
+suffix-$(CONFIG_KERNEL_LZMA)  := .lzma
+suffix-$(CONFIG_KERNEL_LZO)  := .lzo
+suffix-$(CONFIG_KERNEL_XZ)  := .xz
 
 $(obj)/vmlinux.bin.gz: $(vmlinux.bin.all-y)
 	$(call if_changed,gzip)
@@ -72,7 +72,7 @@ $(obj)/vmlinux.bin.xz: $(vmlinux.bin.all-y)
 	$(call if_changed,xzkern)
 
 LDFLAGS_piggy.o := -r --format binary --oformat $(LD_BFD) -T
-$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin.$(suffix-y)
+$(obj)/piggy.o: $(obj)/vmlinux.scr.lds $(obj)/vmlinux.bin$(suffix-y)
 	$(call if_changed,ld)
 
 chkbss := $(filter-out $(obj)/misc.o $(obj)/piggy.o,$(OBJECTS))
-- 
cgit v1.2.3


From f16466af385b985f8d56f3fc50146ab41ec0dd89 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 21:26:35 +0200
Subject: init/Kconfig: add an option for uncompressed kernel

Add "None" as the kernel compression mode.

This option is useful for debugging the kernel in slow simulation
environments, where decompressing and moving the kernel is awfully slow.

Uncompressed kernel implementation might allow early boot code to skip the
decompressor and jump right at uncompressed kernel image entry point.

Platforms implementing that should define HAVE_KERNEL_UNCOMPRESSED.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 init/Kconfig | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index fde3d09e8b27..79036797bf06 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -125,10 +125,13 @@ config HAVE_KERNEL_LZO
 config HAVE_KERNEL_LZ4
 	bool
 
+config HAVE_KERNEL_UNCOMPRESSED
+	bool
+
 choice
 	prompt "Kernel compression mode"
 	default KERNEL_GZIP
-	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4
+	depends on HAVE_KERNEL_GZIP || HAVE_KERNEL_BZIP2 || HAVE_KERNEL_LZMA || HAVE_KERNEL_XZ || HAVE_KERNEL_LZO || HAVE_KERNEL_LZ4 || HAVE_KERNEL_UNCOMPRESSED
 	help
 	  The linux kernel is a kind of self-extracting executable.
 	  Several compression algorithms are available, which differ
@@ -207,6 +210,16 @@ config KERNEL_LZ4
 	  is about 8% bigger than LZO. But the decompression speed is
 	  faster than LZO.
 
+config KERNEL_UNCOMPRESSED
+	bool "None"
+	depends on HAVE_KERNEL_UNCOMPRESSED
+	help
+	  Produce uncompressed kernel image. This option is usually not what
+	  you want. It is useful for debugging the kernel in slow simulation
+	  environments, where decompressing and moving the kernel is awfully
+	  slow. This option allows early boot code to skip the decompressor
+	  and jump right at uncompressed kernel image.
+
 endchoice
 
 config DEFAULT_HOSTNAME
-- 
cgit v1.2.3


From 89b5202e81df9f0f0f0a11cf8c78bc8bfdc52a21 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 13 Jun 2018 00:00:25 +0200
Subject: s390/decompressor: support uncompressed kernel

Implement uncompressed kernel support (when "None" is picked in kernel
compression mode list). In that case an actual decompression code is
skipped and control is passed from boot/head.S to startup_continue in
kernel/head64.S. To achieve that uncompressed kernel payload is
conditionally put at 0x100000 in bzImage.

In reality this is very close to classic uncompressed kernel "image",
but the decompressor has its own build and link process,
kernel/head64.S lives at 0x100000 rather than at 0x11000, and .bss
section is reused for both stages.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig                           |  1 +
 arch/s390/boot/compressed/Makefile          |  4 ++--
 arch/s390/boot/compressed/vmlinux.lds.S     | 12 ++++++++----
 arch/s390/boot/compressed/vmlinux.scr.lds.S |  4 ++++
 arch/s390/boot/head.S                       |  4 ++++
 5 files changed, 19 insertions(+), 6 deletions(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index baed39772c84..3023fa00e4b5 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -146,6 +146,7 @@ config S390
 	select HAVE_KERNEL_LZ4
 	select HAVE_KERNEL_LZMA
 	select HAVE_KERNEL_LZO
+	select HAVE_KERNEL_UNCOMPRESSED
 	select HAVE_KERNEL_XZ
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 438e1a50e0b5..9d3bd7d066e9 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -9,10 +9,10 @@ KCOV_INSTRUMENT := n
 GCOV_PROFILE := n
 UBSAN_SANITIZE := n
 
-obj-y	:= head.o misc.o piggy.o
+obj-y	:= $(if $(CONFIG_KERNEL_UNCOMPRESSED),,head.o misc.o) piggy.o
 targets	:= vmlinux.lds vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2
 targets += vmlinux.bin.xz vmlinux.bin.lzma vmlinux.bin.lzo vmlinux.bin.lz4
-targets += vmlinux.scr.lds sizes.h $(obj-y)
+targets += vmlinux.scr.lds $(obj-y) $(if $(CONFIG_KERNEL_UNCOMPRESSED),,sizes.h)
 
 KBUILD_AFLAGS := $(KBUILD_AFLAGS_DECOMPRESSOR)
 KBUILD_CFLAGS := $(KBUILD_CFLAGS_DECOMPRESSOR)
diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index d43c2db12d30..b8572a81be5f 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -23,13 +23,10 @@ SECTIONS
 		*(.text.*)
 		_etext = . ;
 	}
-	.rodata.compressed : {
-		*(.rodata.compressed)
-	}
 	.rodata : {
 		_rodata = . ;
 		*(.rodata)	 /* read-only data */
-		*(.rodata.*)
+		EXCLUDE_FILE (*piggy.o) *(.rodata.*)
 		_erodata = . ;
 	}
 	.data :	{
@@ -38,6 +35,13 @@ SECTIONS
 		*(.data.*)
 		_edata = . ;
 	}
+	startup_continue = 0x100000;
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+	. = 0x100000;
+#endif
+	.rodata.compressed : {
+		*(.rodata.compressed)
+	}
 	. = ALIGN(256);
 	.bss : {
 		_bss = . ;
diff --git a/arch/s390/boot/compressed/vmlinux.scr.lds.S b/arch/s390/boot/compressed/vmlinux.scr.lds.S
index 42a242597f34..ff01d18c9222 100644
--- a/arch/s390/boot/compressed/vmlinux.scr.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.scr.lds.S
@@ -2,10 +2,14 @@
 SECTIONS
 {
   .rodata.compressed : {
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
 	input_len = .;
 	LONG(input_data_end - input_data) input_data = .;
+#endif
 	*(.data)
+#ifndef CONFIG_KERNEL_UNCOMPRESSED
 	output_len = . - 4;
 	input_data_end = .;
+#endif
 	}
 }
diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index 8d98463ca7d0..f09e792df495 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -310,7 +310,11 @@ ENTRY(startup_kdump)
 	l	%r15,.Lstack-.LPG0(%r13)
 	ahi	%r15,-STACK_FRAME_OVERHEAD
 	brasl	%r14,verify_facilities
+#ifdef CONFIG_KERNEL_UNCOMPRESSED
+	jg	startup_continue
+#else
 	jg	startup_decompressor
+#endif
 
 .Lstack:
 	.long	0x8000 + (1<<(PAGE_SHIFT+THREAD_SIZE_ORDER))
-- 
cgit v1.2.3


From 6075e4ae6e729778ac687a9ffb0c0d5223a0a19e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 12:05:00 +0200
Subject: s390: hypfs: use ktime_get_seconds() instead of get_seconds()

time_t and get_seconds() are deprecated because they will overflow on
32-bit architectures in the future. This is not a problem on 64-bit s390,
but we should use proper interfaces anyway.

Besides moving to the time64_t based interface, the CLOCK_MONOTONIC
based ktime_get_seconds() is preferred for kernel internal timekeeping
because it does not behave in unexpected ways during leap second changes
or settimeofday() calls.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/hypfs/inode.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c
index 06b513d192b9..c681329fdeec 100644
--- a/arch/s390/hypfs/inode.c
+++ b/arch/s390/hypfs/inode.c
@@ -36,7 +36,7 @@ struct hypfs_sb_info {
 	kuid_t uid;			/* uid used for files and dirs */
 	kgid_t gid;			/* gid used for files and dirs */
 	struct dentry *update_file;	/* file to trigger update */
-	time_t last_update;		/* last update time in secs since 1970 */
+	time64_t last_update;		/* last update, CLOCK_MONOTONIC time */
 	struct mutex lock;		/* lock to protect update process */
 };
 
@@ -52,7 +52,7 @@ static void hypfs_update_update(struct super_block *sb)
 	struct hypfs_sb_info *sb_info = sb->s_fs_info;
 	struct inode *inode = d_inode(sb_info->update_file);
 
-	sb_info->last_update = get_seconds();
+	sb_info->last_update = ktime_get_seconds();
 	inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 }
 
@@ -179,7 +179,7 @@ static ssize_t hypfs_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	 *    to restart data collection in this case.
 	 */
 	mutex_lock(&fs_info->lock);
-	if (fs_info->last_update == get_seconds()) {
+	if (fs_info->last_update == ktime_get_seconds()) {
 		rc = -EBUSY;
 		goto out;
 	}
-- 
cgit v1.2.3


From 514211f542dd6eb877adf46d400ce351c81d95ad Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Tue, 12 Jun 2018 16:46:59 +0200
Subject: s390/setup: do not reserve the decompressor code

Introduce PARMAREA_END, and use it for memblock reserve of low
memory, which is used for lowcore, kdump data mover code and page
buffer, early stack and parmarea. There is no need to reserve an
area between PARMAREA_END and the decompressor _ehead.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/setup.h | 1 +
 arch/s390/kernel/setup.c      | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index 9c30ebe046f3..be02f0558048 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -11,6 +11,7 @@
 
 
 #define PARMAREA		0x10400
+#define PARMAREA_END		0x11000
 
 /*
  * Machine features detected in early.c
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index d82a9ec64ea9..c637c12f9e37 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -674,12 +674,12 @@ static void __init reserve_kernel(void)
 #ifdef CONFIG_DMA_API_DEBUG
 	/*
 	 * DMA_API_DEBUG code stumbles over addresses from the
-	 * range [_ehead, _stext]. Mark the memory as reserved
+	 * range [PARMAREA_END, _stext]. Mark the memory as reserved
 	 * so it is not used for CONFIG_DMA_API_DEBUG=y.
 	 */
 	memblock_reserve(0, PFN_PHYS(start_pfn));
 #else
-	memblock_reserve(0, (unsigned long)_ehead);
+	memblock_reserve(0, PARMAREA_END);
 	memblock_reserve((unsigned long)_stext, PFN_PHYS(start_pfn)
 			 - (unsigned long)_stext);
 #endif
-- 
cgit v1.2.3


From ea3c4185efb34e3157caf0529be8f1a68acc0550 Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@de.ibm.com>
Date: Thu, 7 Jun 2018 07:19:48 +0200
Subject: s390/zcrypt: Add ZAPQ inline function.

Added new inline function ap_pqap_zapq()
which is a C inline function wrapper for
the AP PQAP(ZAPQ) instruction.

Signed-off-by: Harald Freudenberger <freude@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/crypto/ap_asm.h | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/s390/crypto/ap_asm.h b/drivers/s390/crypto/ap_asm.h
index 16b59ce5e01d..b22d30aaf810 100644
--- a/drivers/s390/crypto/ap_asm.h
+++ b/drivers/s390/crypto/ap_asm.h
@@ -69,6 +69,25 @@ static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
 	return reg1;
 }
 
+/**
+ * ap_pqap_zapq(): Reset and zeroize adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
+{
+	register unsigned long reg0 asm ("0") = qid | (2UL << 24);
+	register struct ap_queue_status reg1 asm ("1");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(ZAPQ) */
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
 /**
  * ap_aqic(): Control interruption for a specific AP.
  * @qid: The AP queue number
-- 
cgit v1.2.3


From df80c03831331b6254ae9f16b6a10e672e0919c2 Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@de.ibm.com>
Date: Thu, 7 Jun 2018 11:44:19 +0200
Subject: s390/zcrypt: Review inline assembler constraints.

Reviewed and adapted the register use and asm constraints
of the C inline assembler functions in accordance to the
the AP instructions specifications.

Signed-off-by: Harald Freudenberger <freude@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/crypto/ap_asm.h | 40 +++++++++++++++++++++++-----------------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/drivers/s390/crypto/ap_asm.h b/drivers/s390/crypto/ap_asm.h
index b22d30aaf810..e22ee126c9df 100644
--- a/drivers/s390/crypto/ap_asm.h
+++ b/drivers/s390/crypto/ap_asm.h
@@ -20,14 +20,16 @@ static inline int ap_instructions_available(void)
 {
 	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
 	register unsigned long reg1 asm ("1") = -ENODEV;
-	register unsigned long reg2 asm ("2") = 0UL;
+	register unsigned long reg2 asm ("2");
 
 	asm volatile(
 		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
-		"0: la    %1,0\n"
+		"0: la    %0,0\n"
 		"1:\n"
 		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2) : : "cc");
+		: "+d" (reg1), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
 	return reg1;
 }
 
@@ -42,10 +44,12 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
 {
 	register unsigned long reg0 asm ("0") = qid;
 	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
+	register unsigned long reg2 asm ("2");
 
 	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
-		     : "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
+		     : "=d" (reg1), "=d" (reg2)
+		     : "d" (reg0)
+		     : "cc");
 	if (info)
 		*info = reg2;
 	return reg1;
@@ -59,13 +63,14 @@ static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
  */
 static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
 {
-	register unsigned long reg0 asm ("0") = qid | 0x01000000UL;
+	register unsigned long reg0 asm ("0") = qid | (1UL << 24);
 	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = 0UL;
 
 	asm volatile(
 		".long 0xb2af0000"		/* PQAP(RAPQ) */
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2) : : "cc");
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
 	return reg1;
 }
 
@@ -107,8 +112,8 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
 
 	asm volatile(
 		".long 0xb2af0000"		/* PQAP(AQIC) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		:
+		: "=d" (reg1_out)
+		: "d" (reg0), "d" (reg1_in), "d" (reg2)
 		: "cc");
 	return reg1_out;
 }
@@ -120,17 +125,17 @@ static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
  */
 static inline int ap_qci(void *config)
 {
-	register unsigned long reg0 asm ("0") = 0x04000000UL;
+	register unsigned long reg0 asm ("0") = 4UL << 24;
 	register unsigned long reg1 asm ("1") = -EINVAL;
 	register void *reg2 asm ("2") = (void *) config;
 
 	asm volatile(
 		".long 0xb2af0000\n"		/* PQAP(QCI) */
-		"0: la    %1,0\n"
+		"0: la    %0,0\n"
 		"1:\n"
 		EX_TABLE(0b, 1b)
-		: "+d" (reg0), "+d" (reg1), "+d" (reg2)
-		:
+		: "+d" (reg1)
+		: "d" (reg0), "d" (reg2)
 		: "cc", "memory");
 
 	return reg1;
@@ -169,12 +174,13 @@ static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
 		| ((ifbit & 0x01) << 22);
 	register unsigned long reg1_in asm ("1") = apinfo->val;
 	register struct ap_queue_status reg1_out asm ("1");
-	register unsigned long reg2 asm ("2") = 0;
+	register unsigned long reg2 asm ("2");
 
 	asm volatile(
 		".long 0xb2af0000"		/* PQAP(QACT) */
-		: "+d" (reg0), "+d" (reg1_in), "=d" (reg1_out), "+d" (reg2)
-		: : "cc");
+		: "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
 	apinfo->val = reg2;
 	return reg1_out;
 }
-- 
cgit v1.2.3


From 4a07750ba8f3f45f0be730f7370c2c21a7491cd7 Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@de.ibm.com>
Date: Thu, 7 Jun 2018 15:09:48 +0200
Subject: s390/zcrypt: Show load of cards and queues in sysfs

Show the current load value of cards and queues in sysfs.
The load value for each card and queue is maintained by
the zcrypt device driver for dispatching and load
balancing requests over the available devices.

This patch provides the load value to userspace via a
new read only sysfs attribute 'load' per card and queue.

Signed-off-by: Harald Freudenberger <freude@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/crypto/zcrypt_card.c  | 12 ++++++++++++
 drivers/s390/crypto/zcrypt_queue.c | 12 ++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/drivers/s390/crypto/zcrypt_card.c b/drivers/s390/crypto/zcrypt_card.c
index 233e1e695208..da2c8dfd4d74 100644
--- a/drivers/s390/crypto/zcrypt_card.c
+++ b/drivers/s390/crypto/zcrypt_card.c
@@ -83,9 +83,21 @@ static ssize_t zcrypt_card_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_card_online_show,
 		   zcrypt_card_online_store);
 
+static ssize_t zcrypt_card_load_show(struct device *dev,
+				     struct device_attribute *attr,
+				     char *buf)
+{
+	struct zcrypt_card *zc = to_ap_card(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zc->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_card_load_show, NULL);
+
 static struct attribute *zcrypt_card_attrs[] = {
 	&dev_attr_type.attr,
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
diff --git a/drivers/s390/crypto/zcrypt_queue.c b/drivers/s390/crypto/zcrypt_queue.c
index 720434e18007..91a52f268353 100644
--- a/drivers/s390/crypto/zcrypt_queue.c
+++ b/drivers/s390/crypto/zcrypt_queue.c
@@ -75,8 +75,20 @@ static ssize_t zcrypt_queue_online_store(struct device *dev,
 static DEVICE_ATTR(online, 0644, zcrypt_queue_online_show,
 		   zcrypt_queue_online_store);
 
+static ssize_t zcrypt_queue_load_show(struct device *dev,
+				      struct device_attribute *attr,
+				      char *buf)
+{
+	struct zcrypt_queue *zq = to_ap_queue(dev)->private;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", atomic_read(&zq->load));
+}
+
+static DEVICE_ATTR(load, 0444, zcrypt_queue_load_show, NULL);
+
 static struct attribute *zcrypt_queue_attrs[] = {
 	&dev_attr_online.attr,
+	&dev_attr_load.attr,
 	NULL,
 };
 
-- 
cgit v1.2.3


From f1b0a4343c4184bef9fdea8fad41f09bbd3d63ec Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@de.ibm.com>
Date: Tue, 12 Jun 2018 15:42:36 +0200
Subject: s390/zcrypt: Integrate ap_asm.h into include/asm/ap.h.

Move all the inline functions from the ap bus header
file ap_asm.h into the in-kernel api header file
arch/s390/include/asm/ap.h so that KVM can make use
of all the low level AP functions.

Signed-off-by: Harald Freudenberger <freude@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/ap.h     | 284 +++++++++++++++++++++++++++++++++++++----
 drivers/s390/crypto/ap_asm.h   | 261 -------------------------------------
 drivers/s390/crypto/ap_bus.c   |  21 +--
 drivers/s390/crypto/ap_bus.h   |   1 +
 drivers/s390/crypto/ap_card.c  |   1 -
 drivers/s390/crypto/ap_queue.c |  20 ---
 6 files changed, 259 insertions(+), 329 deletions(-)
 delete mode 100644 drivers/s390/crypto/ap_asm.h

diff --git a/arch/s390/include/asm/ap.h b/arch/s390/include/asm/ap.h
index c1bedb4c8de0..046e044a48d0 100644
--- a/arch/s390/include/asm/ap.h
+++ b/arch/s390/include/asm/ap.h
@@ -46,6 +46,50 @@ struct ap_queue_status {
 	unsigned int _pad2		: 16;
 };
 
+/**
+ * ap_intructions_available() - Test if AP instructions are available.
+ *
+ * Returns 0 if the AP instructions are installed.
+ */
+static inline int ap_instructions_available(void)
+{
+	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
+	register unsigned long reg1 asm ("1") = -ENODEV;
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(
+		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
+		"0: la    %0,0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (reg1), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * ap_tapq(): Test adjunct processor queue.
+ * @qid: The AP queue number
+ * @info: Pointer to queue descriptor
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
+{
+	register unsigned long reg0 asm ("0") = qid;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
+		     : "=d" (reg1), "=d" (reg2)
+		     : "d" (reg0)
+		     : "cc");
+	if (info)
+		*info = reg2;
+	return reg1;
+}
+
 /**
  * ap_test_queue(): Test adjunct processor queue.
  * @qid: The AP queue number
@@ -54,10 +98,57 @@ struct ap_queue_status {
  *
  * Returns AP queue status structure.
  */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
-				     int tbit,
-				     unsigned long *info);
+static inline struct ap_queue_status ap_test_queue(ap_qid_t qid,
+						   int tbit,
+						   unsigned long *info)
+{
+	if (tbit)
+		qid |= 1UL << 23; /* set T bit*/
+	return ap_tapq(qid, info);
+}
 
+/**
+ * ap_pqap_rapq(): Reset adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
+{
+	register unsigned long reg0 asm ("0") = qid | (1UL << 24);
+	register struct ap_queue_status reg1 asm ("1");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(RAPQ) */
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * ap_pqap_zapq(): Reset and zeroize adjunct processor queue.
+ * @qid: The AP queue number
+ *
+ * Returns AP queue status structure.
+ */
+static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
+{
+	register unsigned long reg0 asm ("0") = qid | (2UL << 24);
+	register struct ap_queue_status reg1 asm ("1");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(ZAPQ) */
+		: "=d" (reg1)
+		: "d" (reg0)
+		: "cc");
+	return reg1;
+}
+
+/**
+ * struct ap_config_info - convenience struct for AP crypto
+ * config info as returned by the ap_qci() function.
+ */
 struct ap_config_info {
 	unsigned int apsc	 : 1;	/* S bit */
 	unsigned int apxa	 : 1;	/* N bit */
@@ -74,50 +165,189 @@ struct ap_config_info {
 	unsigned char _reserved4[16];
 } __aligned(8);
 
-/*
- * ap_query_configuration(): Fetch cryptographic config info
+/**
+ * ap_qci(): Get AP configuration data
  *
- * Returns the ap configuration info fetched via PQAP(QCI).
- * On success 0 is returned, on failure a negative errno
- * is returned, e.g. if the PQAP(QCI) instruction is not
- * available, the return value will be -EOPNOTSUPP.
+ * Returns 0 on success, or -EOPNOTSUPP.
  */
-int ap_query_configuration(struct ap_config_info *info);
+static inline int ap_qci(struct ap_config_info *config)
+{
+	register unsigned long reg0 asm ("0") = 4UL << 24;
+	register unsigned long reg1 asm ("1") = -EOPNOTSUPP;
+	register struct ap_config_info *reg2 asm ("2") = config;
+
+	asm volatile(
+		".long 0xb2af0000\n"		/* PQAP(QCI) */
+		"0: la    %0,0\n"
+		"1:\n"
+		EX_TABLE(0b, 1b)
+		: "+d" (reg1)
+		: "d" (reg0), "d" (reg2)
+		: "cc", "memory");
+
+	return reg1;
+}
 
 /*
  * struct ap_qirq_ctrl - convenient struct for easy invocation
- * of the ap_queue_irq_ctrl() function. This struct is passed
- * as GR1 parameter to the PQAP(AQIC) instruction. For details
- * please see the AR documentation.
+ * of the ap_aqic() function. This struct is passed as GR1
+ * parameter to the PQAP(AQIC) instruction. For details please
+ * see the AR documentation.
  */
 struct ap_qirq_ctrl {
 	unsigned int _res1 : 8;
-	unsigned int zone  : 8;  /* zone info */
-	unsigned int ir    : 1;  /* ir flag: enable (1) or disable (0) irq */
+	unsigned int zone  : 8;	/* zone info */
+	unsigned int ir    : 1;	/* ir flag: enable (1) or disable (0) irq */
 	unsigned int _res2 : 4;
-	unsigned int gisc  : 3;  /* guest isc field */
+	unsigned int gisc  : 3;	/* guest isc field */
 	unsigned int _res3 : 6;
-	unsigned int gf    : 2;  /* gisa format */
+	unsigned int gf    : 2;	/* gisa format */
 	unsigned int _res4 : 1;
-	unsigned int gisa  : 27; /* gisa origin */
+	unsigned int gisa  : 27;	/* gisa origin */
 	unsigned int _res5 : 1;
-	unsigned int isc   : 3;  /* irq sub class */
+	unsigned int isc   : 3;	/* irq sub class */
 };
 
 /**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
+ * ap_aqic(): Control interruption for a specific AP.
  * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl, see above
+ * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
  * @ind: The notification indicator byte
  *
  * Returns AP queue status.
+ */
+static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
+					     struct ap_qirq_ctrl qirqctrl,
+					     void *ind)
+{
+	register unsigned long reg0 asm ("0") = qid | (3UL << 24);
+	register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
+	register struct ap_queue_status reg1_out asm ("1");
+	register void *reg2 asm ("2") = ind;
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(AQIC) */
+		: "=d" (reg1_out)
+		: "d" (reg0), "d" (reg1_in), "d" (reg2)
+		: "cc");
+	return reg1_out;
+}
+
+/*
+ * union ap_qact_ap_info - used together with the
+ * ap_aqic() function to provide a convenient way
+ * to handle the ap info needed by the qact function.
+ */
+union ap_qact_ap_info {
+	unsigned long val;
+	struct {
+		unsigned int	  : 3;
+		unsigned int mode : 3;
+		unsigned int	  : 26;
+		unsigned int cat  : 8;
+		unsigned int	  : 8;
+		unsigned char ver[2];
+	};
+};
+
+/**
+ * ap_qact(): Query AP combatibility type.
+ * @qid: The AP queue number
+ * @apinfo: On input the info about the AP queue. On output the
+ *	    alternate AP queue info provided by the qact function
+ *	    in GR2 is stored in.
  *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
+ * Returns AP queue status. Check response_code field for failures.
  */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
-					 struct ap_qirq_ctrl qirqctrl,
-					 void *ind);
+static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
+					     union ap_qact_ap_info *apinfo)
+{
+	register unsigned long reg0 asm ("0") = qid | (5UL << 24)
+		| ((ifbit & 0x01) << 22);
+	register unsigned long reg1_in asm ("1") = apinfo->val;
+	register struct ap_queue_status reg1_out asm ("1");
+	register unsigned long reg2 asm ("2");
+
+	asm volatile(
+		".long 0xb2af0000"		/* PQAP(QACT) */
+		: "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2)
+		: "d" (reg0)
+		: "cc");
+	apinfo->val = reg2;
+	return reg1_out;
+}
+
+/**
+ * ap_nqap(): Send message to adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: The program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on NQAP can't happen because the L bit is 1.
+ * Condition code 2 on NQAP also means the send is incomplete,
+ * because a segment boundary was reached. The NQAP is repeated.
+ */
+static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
+					     unsigned long long psmid,
+					     void *msg, size_t length)
+{
+	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm ("2") = (unsigned long) msg;
+	register unsigned long reg3 asm ("3") = (unsigned long) length;
+	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
+	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
+
+	asm volatile (
+		"0: .long 0xb2ad0042\n"		/* NQAP */
+		"   brc   2,0b"
+		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
+		: "d" (reg4), "d" (reg5)
+		: "cc", "memory");
+	return reg1;
+}
+
+/**
+ * ap_dqap(): Receive message from adjunct processor queue.
+ * @qid: The AP queue number
+ * @psmid: Pointer to program supplied message identifier
+ * @msg: The message text
+ * @length: The message length
+ *
+ * Returns AP queue status structure.
+ * Condition code 1 on DQAP means the receive has taken place
+ * but only partially.	The response is incomplete, hence the
+ * DQAP is repeated.
+ * Condition code 2 on DQAP also means the receive is incomplete,
+ * this time because a segment boundary was reached. Again, the
+ * DQAP is repeated.
+ * Note that gpr2 is used by the DQAP instruction to keep track of
+ * any 'residual' length, in case the instruction gets interrupted.
+ * Hence it gets zeroed before the instruction.
+ */
+static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
+					     unsigned long long *psmid,
+					     void *msg, size_t length)
+{
+	register unsigned long reg0 asm("0") = qid | 0x80000000UL;
+	register struct ap_queue_status reg1 asm ("1");
+	register unsigned long reg2 asm("2") = 0UL;
+	register unsigned long reg4 asm("4") = (unsigned long) msg;
+	register unsigned long reg5 asm("5") = (unsigned long) length;
+	register unsigned long reg6 asm("6") = 0UL;
+	register unsigned long reg7 asm("7") = 0UL;
+
+
+	asm volatile(
+		"0: .long 0xb2ae0064\n"		/* DQAP */
+		"   brc   6,0b\n"
+		: "+d" (reg0), "=d" (reg1), "+d" (reg2),
+		  "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
+		: : "cc", "memory");
+	*psmid = (((unsigned long long) reg6) << 32) + reg7;
+	return reg1;
+}
 
 #endif /* _ASM_S390_AP_H_ */
diff --git a/drivers/s390/crypto/ap_asm.h b/drivers/s390/crypto/ap_asm.h
deleted file mode 100644
index e22ee126c9df..000000000000
--- a/drivers/s390/crypto/ap_asm.h
+++ /dev/null
@@ -1,261 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright IBM Corp. 2016
- * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
- *
- * Adjunct processor bus inline assemblies.
- */
-
-#ifndef _AP_ASM_H_
-#define _AP_ASM_H_
-
-#include <asm/isc.h>
-
-/**
- * ap_intructions_available() - Test if AP instructions are available.
- *
- * Returns 0 if the AP instructions are installed.
- */
-static inline int ap_instructions_available(void)
-{
-	register unsigned long reg0 asm ("0") = AP_MKQID(0, 0);
-	register unsigned long reg1 asm ("1") = -ENODEV;
-	register unsigned long reg2 asm ("2");
-
-	asm volatile(
-		"   .long 0xb2af0000\n"		/* PQAP(TAPQ) */
-		"0: la    %0,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg1), "=d" (reg2)
-		: "d" (reg0)
-		: "cc");
-	return reg1;
-}
-
-/**
- * ap_tapq(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_tapq(ap_qid_t qid, unsigned long *info)
-{
-	register unsigned long reg0 asm ("0") = qid;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2");
-
-	asm volatile(".long 0xb2af0000"		/* PQAP(TAPQ) */
-		     : "=d" (reg1), "=d" (reg2)
-		     : "d" (reg0)
-		     : "cc");
-	if (info)
-		*info = reg2;
-	return reg1;
-}
-
-/**
- * ap_pqap_rapq(): Reset adjunct processor queue.
- * @qid: The AP queue number
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_rapq(ap_qid_t qid)
-{
-	register unsigned long reg0 asm ("0") = qid | (1UL << 24);
-	register struct ap_queue_status reg1 asm ("1");
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(RAPQ) */
-		: "=d" (reg1)
-		: "d" (reg0)
-		: "cc");
-	return reg1;
-}
-
-/**
- * ap_pqap_zapq(): Reset and zeroize adjunct processor queue.
- * @qid: The AP queue number
- *
- * Returns AP queue status structure.
- */
-static inline struct ap_queue_status ap_zapq(ap_qid_t qid)
-{
-	register unsigned long reg0 asm ("0") = qid | (2UL << 24);
-	register struct ap_queue_status reg1 asm ("1");
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(ZAPQ) */
-		: "=d" (reg1)
-		: "d" (reg0)
-		: "cc");
-	return reg1;
-}
-
-/**
- * ap_aqic(): Control interruption for a specific AP.
- * @qid: The AP queue number
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- */
-static inline struct ap_queue_status ap_aqic(ap_qid_t qid,
-					     struct ap_qirq_ctrl qirqctrl,
-					     void *ind)
-{
-	register unsigned long reg0 asm ("0") = qid | (3UL << 24);
-	register struct ap_qirq_ctrl reg1_in asm ("1") = qirqctrl;
-	register struct ap_queue_status reg1_out asm ("1");
-	register void *reg2 asm ("2") = ind;
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(AQIC) */
-		: "=d" (reg1_out)
-		: "d" (reg0), "d" (reg1_in), "d" (reg2)
-		: "cc");
-	return reg1_out;
-}
-
-/**
- * ap_qci(): Get AP configuration data
- *
- * Returns 0 on success, or -EOPNOTSUPP.
- */
-static inline int ap_qci(void *config)
-{
-	register unsigned long reg0 asm ("0") = 4UL << 24;
-	register unsigned long reg1 asm ("1") = -EINVAL;
-	register void *reg2 asm ("2") = (void *) config;
-
-	asm volatile(
-		".long 0xb2af0000\n"		/* PQAP(QCI) */
-		"0: la    %0,0\n"
-		"1:\n"
-		EX_TABLE(0b, 1b)
-		: "+d" (reg1)
-		: "d" (reg0), "d" (reg2)
-		: "cc", "memory");
-
-	return reg1;
-}
-
-/*
- * union ap_qact_ap_info - used together with the
- * ap_aqic() function to provide a convenient way
- * to handle the ap info needed by the qact function.
- */
-union ap_qact_ap_info {
-	unsigned long val;
-	struct {
-		unsigned int	  : 3;
-		unsigned int mode : 3;
-		unsigned int	  : 26;
-		unsigned int cat  : 8;
-		unsigned int	  : 8;
-		unsigned char ver[2];
-	};
-};
-
-/**
- * ap_qact(): Query AP combatibility type.
- * @qid: The AP queue number
- * @apinfo: On input the info about the AP queue. On output the
- *	    alternate AP queue info provided by the qact function
- *	    in GR2 is stored in.
- *
- * Returns AP queue status. Check response_code field for failures.
- */
-static inline struct ap_queue_status ap_qact(ap_qid_t qid, int ifbit,
-					     union ap_qact_ap_info *apinfo)
-{
-	register unsigned long reg0 asm ("0") = qid | (5UL << 24)
-		| ((ifbit & 0x01) << 22);
-	register unsigned long reg1_in asm ("1") = apinfo->val;
-	register struct ap_queue_status reg1_out asm ("1");
-	register unsigned long reg2 asm ("2");
-
-	asm volatile(
-		".long 0xb2af0000"		/* PQAP(QACT) */
-		: "+d" (reg1_in), "=d" (reg1_out), "=d" (reg2)
-		: "d" (reg0)
-		: "cc");
-	apinfo->val = reg2;
-	return reg1_out;
-}
-
-/**
- * ap_nqap(): Send message to adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: The program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on NQAP can't happen because the L bit is 1.
- * Condition code 2 on NQAP also means the send is incomplete,
- * because a segment boundary was reached. The NQAP is repeated.
- */
-static inline struct ap_queue_status ap_nqap(ap_qid_t qid,
-					     unsigned long long psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm ("0") = qid | 0x40000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm ("2") = (unsigned long) msg;
-	register unsigned long reg3 asm ("3") = (unsigned long) length;
-	register unsigned long reg4 asm ("4") = (unsigned int) (psmid >> 32);
-	register unsigned long reg5 asm ("5") = psmid & 0xffffffff;
-
-	asm volatile (
-		"0: .long 0xb2ad0042\n"		/* NQAP */
-		"   brc   2,0b"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2), "+d" (reg3)
-		: "d" (reg4), "d" (reg5)
-		: "cc", "memory");
-	return reg1;
-}
-
-/**
- * ap_dqap(): Receive message from adjunct processor queue.
- * @qid: The AP queue number
- * @psmid: Pointer to program supplied message identifier
- * @msg: The message text
- * @length: The message length
- *
- * Returns AP queue status structure.
- * Condition code 1 on DQAP means the receive has taken place
- * but only partially.	The response is incomplete, hence the
- * DQAP is repeated.
- * Condition code 2 on DQAP also means the receive is incomplete,
- * this time because a segment boundary was reached. Again, the
- * DQAP is repeated.
- * Note that gpr2 is used by the DQAP instruction to keep track of
- * any 'residual' length, in case the instruction gets interrupted.
- * Hence it gets zeroed before the instruction.
- */
-static inline struct ap_queue_status ap_dqap(ap_qid_t qid,
-					     unsigned long long *psmid,
-					     void *msg, size_t length)
-{
-	register unsigned long reg0 asm("0") = qid | 0x80000000UL;
-	register struct ap_queue_status reg1 asm ("1");
-	register unsigned long reg2 asm("2") = 0UL;
-	register unsigned long reg4 asm("4") = (unsigned long) msg;
-	register unsigned long reg5 asm("5") = (unsigned long) length;
-	register unsigned long reg6 asm("6") = 0UL;
-	register unsigned long reg7 asm("7") = 0UL;
-
-
-	asm volatile(
-		"0: .long 0xb2ae0064\n"		/* DQAP */
-		"   brc   6,0b\n"
-		: "+d" (reg0), "=d" (reg1), "+d" (reg2),
-		  "+d" (reg4), "+d" (reg5), "+d" (reg6), "+d" (reg7)
-		: : "cc", "memory");
-	*psmid = (((unsigned long long) reg6) << 32) + reg7;
-	return reg1;
-}
-
-#endif /* _AP_ASM_H_ */
diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index 35a0c2b52f82..c0a6723be54b 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -36,7 +36,6 @@
 #include <linux/debugfs.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 #include "ap_debug.h"
 
 /*
@@ -174,24 +173,6 @@ static inline int ap_qact_available(void)
 	return 0;
 }
 
-/**
- * ap_test_queue(): Test adjunct processor queue.
- * @qid: The AP queue number
- * @tbit: Test facilities bit
- * @info: Pointer to queue descriptor
- *
- * Returns AP queue status structure.
- */
-struct ap_queue_status ap_test_queue(ap_qid_t qid,
-				     int tbit,
-				     unsigned long *info)
-{
-	if (tbit)
-		qid |= 1UL << 23; /* set T bit*/
-	return ap_tapq(qid, info);
-}
-EXPORT_SYMBOL(ap_test_queue);
-
 /*
  * ap_query_configuration(): Fetch cryptographic config info
  *
@@ -200,7 +181,7 @@ EXPORT_SYMBOL(ap_test_queue);
  * is returned, e.g. if the PQAP(QCI) instruction is not
  * available, the return value will be -EOPNOTSUPP.
  */
-int ap_query_configuration(struct ap_config_info *info)
+static inline int ap_query_configuration(struct ap_config_info *info)
 {
 	if (!ap_configuration_available())
 		return -EOPNOTSUPP;
diff --git a/drivers/s390/crypto/ap_bus.h b/drivers/s390/crypto/ap_bus.h
index 6a273c5ebca5..936541937e15 100644
--- a/drivers/s390/crypto/ap_bus.h
+++ b/drivers/s390/crypto/ap_bus.h
@@ -15,6 +15,7 @@
 
 #include <linux/device.h>
 #include <linux/types.h>
+#include <asm/isc.h>
 #include <asm/ap.h>
 
 #define AP_DEVICES 256		/* Number of AP devices. */
diff --git a/drivers/s390/crypto/ap_card.c b/drivers/s390/crypto/ap_card.c
index 2c726df210f6..c13e43292cb7 100644
--- a/drivers/s390/crypto/ap_card.c
+++ b/drivers/s390/crypto/ap_card.c
@@ -14,7 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
 
 /*
  * AP card related attributes.
diff --git a/drivers/s390/crypto/ap_queue.c b/drivers/s390/crypto/ap_queue.c
index ba3a2e13b0eb..e365171fe28f 100644
--- a/drivers/s390/crypto/ap_queue.c
+++ b/drivers/s390/crypto/ap_queue.c
@@ -14,26 +14,6 @@
 #include <asm/facility.h>
 
 #include "ap_bus.h"
-#include "ap_asm.h"
-
-/**
- * ap_queue_irq_ctrl(): Control interruption on a AP queue.
- * @qirqctrl: struct ap_qirq_ctrl (64 bit value)
- * @ind: The notification indicator byte
- *
- * Returns AP queue status.
- *
- * Control interruption on the given AP queue.
- * Just a simple wrapper function for the low level PQAP(AQIC)
- * instruction available for other kernel modules.
- */
-struct ap_queue_status ap_queue_irq_ctrl(ap_qid_t qid,
-					 struct ap_qirq_ctrl qirqctrl,
-					 void *ind)
-{
-	return ap_aqic(qid, qirqctrl, ind);
-}
-EXPORT_SYMBOL(ap_queue_irq_ctrl);
 
 /**
  * ap_queue_enable_interruption(): Enable interruption on an AP queue.
-- 
cgit v1.2.3


From e4b08e1f3e86a5acda93fc7adb014840af7248bb Mon Sep 17 00:00:00 2001
From: Michel Pollet <michel.pollet@bp.renesas.com>
Date: Thu, 14 Jun 2018 11:56:31 +0100
Subject: dt-bindings: clock: renesas,r9a06g032-sysctrl: documentation

The Renesas R9A06G032 SYSCTRL node description.

Signed-off-by: Michel Pollet <michel.pollet@bp.renesas.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 .../bindings/clock/renesas,r9a06g032-sysctrl.txt   | 43 ++++++++++++++++++++++
 1 file changed, 43 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.txt

diff --git a/Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.txt b/Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.txt
new file mode 100644
index 000000000000..d60b99756bb9
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/renesas,r9a06g032-sysctrl.txt
@@ -0,0 +1,43 @@
+* Renesas R9A06G032 SYSCTRL
+
+Required Properties:
+
+  - compatible: Must be:
+    - "renesas,r9a06g032-sysctrl"
+  - reg: Base address and length of the SYSCTRL IO block.
+  - #clock-cells: Must be 1
+  - clocks: References to the parent clocks:
+	- external 40mhz crystal.
+	- external (optional) 32.768khz
+	- external (optional) jtag input
+	- external (optional) RGMII_REFCLK
+  - clock-names: Must be:
+        clock-names = "mclk", "rtc", "jtag", "rgmii_ref_ext";
+
+Examples
+--------
+
+  - SYSCTRL node:
+
+	sysctrl: system-controller@4000c000 {
+		compatible = "renesas,r9a06g032-sysctrl";
+		reg = <0x4000c000 0x1000>;
+		#clock-cells = <1>;
+
+		clocks = <&ext_mclk>, <&ext_rtc_clk>,
+				<&ext_jtag_clk>, <&ext_rgmii_ref>;
+		clock-names = "mclk", "rtc", "jtag", "rgmii_ref_ext";
+	};
+
+  - Other nodes can use the clocks provided by SYSCTRL as in:
+
+	#include <dt-bindings/clock/r9a06g032-sysctrl.h>
+	uart0: serial@40060000 {
+		compatible = "snps,dw-apb-uart";
+		reg = <0x40060000 0x400>;
+		interrupts = <GIC_SPI 6 IRQ_TYPE_LEVEL_HIGH>;
+		reg-shift = <2>;
+		reg-io-width = <4>;
+		clocks = <&sysctrl R9A06G032_CLK_UART0>;
+		clock-names = "baudclk";
+	};
-- 
cgit v1.2.3


From 4c3d88526eba214357150764a0e3e5308acbef4a Mon Sep 17 00:00:00 2001
From: Michel Pollet <michel.pollet@bp.renesas.com>
Date: Thu, 14 Jun 2018 11:56:34 +0100
Subject: clk: renesas: Renesas R9A06G032 clock driver

This provides a clock driver for the Renesas R09A06G032.
This uses a structure derived from both the R-Car Gen2 driver as well as
the renesas-cpg-mssr driver.

Signed-off-by: Michel Pollet <michel.pollet@bp.renesas.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
---
 drivers/clk/renesas/Kconfig            |   6 +
 drivers/clk/renesas/Makefile           |   1 +
 drivers/clk/renesas/r9a06g032-clocks.c | 893 +++++++++++++++++++++++++++++++++
 3 files changed, 900 insertions(+)
 create mode 100644 drivers/clk/renesas/r9a06g032-clocks.c

diff --git a/drivers/clk/renesas/Kconfig b/drivers/clk/renesas/Kconfig
index f9ba71311727..9022bbe1297e 100644
--- a/drivers/clk/renesas/Kconfig
+++ b/drivers/clk/renesas/Kconfig
@@ -21,6 +21,7 @@ config CLK_RENESAS
 	select CLK_R8A77980 if ARCH_R8A77980
 	select CLK_R8A77990 if ARCH_R8A77990
 	select CLK_R8A77995 if ARCH_R8A77995
+	select CLK_R9A06G032 if ARCH_R9A06G032
 	select CLK_SH73A0 if ARCH_SH73A0
 
 if CLK_RENESAS
@@ -125,6 +126,11 @@ config CLK_R8A77995
 	bool "R-Car D3 clock support" if COMPILE_TEST
 	select CLK_RCAR_GEN3_CPG
 
+config CLK_R9A06G032
+	bool "Renesas R9A06G032 clock driver"
+	help
+	  This is a driver for R9A06G032 clocks
+
 config CLK_SH73A0
 	bool "SH-Mobile AG5 clock support" if COMPILE_TEST
 	select CLK_RENESAS_CPG_MSTP
diff --git a/drivers/clk/renesas/Makefile b/drivers/clk/renesas/Makefile
index fe5bac9215e5..e4aa3d6143d2 100644
--- a/drivers/clk/renesas/Makefile
+++ b/drivers/clk/renesas/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_CLK_R8A77970)		+= r8a77970-cpg-mssr.o
 obj-$(CONFIG_CLK_R8A77980)		+= r8a77980-cpg-mssr.o
 obj-$(CONFIG_CLK_R8A77990)		+= r8a77990-cpg-mssr.o
 obj-$(CONFIG_CLK_R8A77995)		+= r8a77995-cpg-mssr.o
+obj-$(CONFIG_CLK_R9A06G032)		+= r9a06g032-clocks.o
 obj-$(CONFIG_CLK_SH73A0)		+= clk-sh73a0.o
 
 # Family
diff --git a/drivers/clk/renesas/r9a06g032-clocks.c b/drivers/clk/renesas/r9a06g032-clocks.c
new file mode 100644
index 000000000000..a0b6ecdc63dd
--- /dev/null
+++ b/drivers/clk/renesas/r9a06g032-clocks.c
@@ -0,0 +1,893 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * R9A09G032 clock driver
+ *
+ * Copyright (C) 2018 Renesas Electronics Europe Limited
+ *
+ * Michel Pollet <michel.pollet@bp.renesas.com>, <buserror@gmail.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/math64.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <dt-bindings/clock/r9a06g032-sysctrl.h>
+
+struct r9a06g032_gate {
+	u16 gate, reset, ready, midle,
+		scon, mirack, mistat;
+};
+
+/* This is used to describe a clock for instantiation */
+struct r9a06g032_clkdesc {
+	const char *name;
+	uint32_t type: 3;
+	uint32_t index: 8;
+	uint32_t source : 8; /* source index + 1 (0 == none) */
+	/* these are used to populate the bitsel struct */
+	union {
+		struct r9a06g032_gate gate;
+		/* for dividers */
+		struct {
+			unsigned int div_min : 10, div_max : 10, reg: 10;
+			u16 div_table[4];
+		};
+		/* For fixed-factor ones */
+		struct {
+			u16 div, mul;
+		};
+		unsigned int factor;
+		unsigned int frequency;
+		/* for dual gate */
+		struct {
+			uint16_t group : 1, index: 3;
+			u16 sel, g1, r1, g2, r2;
+		} dual;
+	};
+} __packed;
+
+#define I_GATE(_clk, _rst, _rdy, _midle, _scon, _mirack, _mistat) \
+	{ .gate = _clk, .reset = _rst, \
+		.ready = _rdy, .midle = _midle, \
+		.scon = _scon, .mirack = _mirack, .mistat = _mistat }
+#define D_GATE(_idx, _n, _src, ...) \
+	{ .type = K_GATE, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.gate = I_GATE(__VA_ARGS__), }
+#define D_ROOT(_idx, _n, _mul, _div) \
+	{ .type = K_FFC, .index = R9A06G032_##_idx, .name = _n, \
+		.div = _div, .mul = _mul }
+#define D_FFC(_idx, _n, _src, _div) \
+	{ .type = K_FFC, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.div = _div, .mul = 1}
+#define D_DIV(_idx, _n, _src, _reg, _min, _max, ...) \
+	{ .type = K_DIV, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.reg = _reg, .div_min = _min, .div_max = _max, \
+		.div_table = { __VA_ARGS__ } }
+#define D_UGATE(_idx, _n, _src, _g, _gi, _g1, _r1, _g2, _r2) \
+	{ .type = K_DUALGATE, .index = R9A06G032_##_idx, \
+		.source = 1 + R9A06G032_##_src, .name = _n, \
+		.dual = { .group = _g, .index = _gi, \
+			.g1 = _g1, .r1 = _r1, .g2 = _g2, .r2 = _r2 }, }
+
+enum { K_GATE = 0, K_FFC, K_DIV, K_BITSEL, K_DUALGATE };
+
+/* Internal clock IDs */
+#define R9A06G032_CLKOUT		0
+#define R9A06G032_CLKOUT_D10		2
+#define R9A06G032_CLKOUT_D16		3
+#define R9A06G032_CLKOUT_D160		4
+#define R9A06G032_CLKOUT_D1OR2		5
+#define R9A06G032_CLKOUT_D20		6
+#define R9A06G032_CLKOUT_D40		7
+#define R9A06G032_CLKOUT_D5		8
+#define R9A06G032_CLKOUT_D8		9
+#define R9A06G032_DIV_ADC		10
+#define R9A06G032_DIV_I2C		11
+#define R9A06G032_DIV_NAND		12
+#define R9A06G032_DIV_P1_PG		13
+#define R9A06G032_DIV_P2_PG		14
+#define R9A06G032_DIV_P3_PG		15
+#define R9A06G032_DIV_P4_PG		16
+#define R9A06G032_DIV_P5_PG		17
+#define R9A06G032_DIV_P6_PG		18
+#define R9A06G032_DIV_QSPI0		19
+#define R9A06G032_DIV_QSPI1		20
+#define R9A06G032_DIV_REF_SYNC		21
+#define R9A06G032_DIV_SDIO0		22
+#define R9A06G032_DIV_SDIO1		23
+#define R9A06G032_DIV_SWITCH		24
+#define R9A06G032_DIV_UART		25
+#define R9A06G032_DIV_MOTOR		64
+#define R9A06G032_CLK_DDRPHY_PLLCLK_D4	78
+#define R9A06G032_CLK_ECAT100_D4	79
+#define R9A06G032_CLK_HSR100_D2		80
+#define R9A06G032_CLK_REF_SYNC_D4	81
+#define R9A06G032_CLK_REF_SYNC_D8	82
+#define R9A06G032_CLK_SERCOS100_D2	83
+#define R9A06G032_DIV_CA7		84
+
+#define R9A06G032_UART_GROUP_012	154
+#define R9A06G032_UART_GROUP_34567	155
+
+#define R9A06G032_CLOCK_COUNT		(R9A06G032_UART_GROUP_34567 + 1)
+
+static const struct r9a06g032_clkdesc r9a06g032_clocks[] __initconst = {
+	D_ROOT(CLKOUT, "clkout", 25, 1),
+	D_ROOT(CLK_PLL_USB, "clk_pll_usb", 12, 10),
+	D_FFC(CLKOUT_D10, "clkout_d10", CLKOUT, 10),
+	D_FFC(CLKOUT_D16, "clkout_d16", CLKOUT, 16),
+	D_FFC(CLKOUT_D160, "clkout_d160", CLKOUT, 160),
+	D_DIV(CLKOUT_D1OR2, "clkout_d1or2", CLKOUT, 0, 1, 2),
+	D_FFC(CLKOUT_D20, "clkout_d20", CLKOUT, 20),
+	D_FFC(CLKOUT_D40, "clkout_d40", CLKOUT, 40),
+	D_FFC(CLKOUT_D5, "clkout_d5", CLKOUT, 5),
+	D_FFC(CLKOUT_D8, "clkout_d8", CLKOUT, 8),
+	D_DIV(DIV_ADC, "div_adc", CLKOUT, 77, 50, 250),
+	D_DIV(DIV_I2C, "div_i2c", CLKOUT, 78, 12, 16),
+	D_DIV(DIV_NAND, "div_nand", CLKOUT, 82, 12, 32),
+	D_DIV(DIV_P1_PG, "div_p1_pg", CLKOUT, 68, 12, 200),
+	D_DIV(DIV_P2_PG, "div_p2_pg", CLKOUT, 62, 12, 128),
+	D_DIV(DIV_P3_PG, "div_p3_pg", CLKOUT, 64, 8, 128),
+	D_DIV(DIV_P4_PG, "div_p4_pg", CLKOUT, 66, 8, 128),
+	D_DIV(DIV_P5_PG, "div_p5_pg", CLKOUT, 71, 10, 40),
+	D_DIV(DIV_P6_PG, "div_p6_pg", CLKOUT, 18, 12, 64),
+	D_DIV(DIV_QSPI0, "div_qspi0", CLKOUT, 73, 3, 7),
+	D_DIV(DIV_QSPI1, "div_qspi1", CLKOUT, 25, 3, 7),
+	D_DIV(DIV_REF_SYNC, "div_ref_sync", CLKOUT, 56, 2, 16, 2, 4, 8, 16),
+	D_DIV(DIV_SDIO0, "div_sdio0", CLKOUT, 74, 20, 128),
+	D_DIV(DIV_SDIO1, "div_sdio1", CLKOUT, 75, 20, 128),
+	D_DIV(DIV_SWITCH, "div_switch", CLKOUT, 37, 5, 40),
+	D_DIV(DIV_UART, "div_uart", CLKOUT, 79, 12, 128),
+	D_GATE(CLK_25_PG4, "clk_25_pg4", CLKOUT_D40, 0x749, 0x74a, 0x74b, 0, 0xae3, 0, 0),
+	D_GATE(CLK_25_PG5, "clk_25_pg5", CLKOUT_D40, 0x74c, 0x74d, 0x74e, 0, 0xae4, 0, 0),
+	D_GATE(CLK_25_PG6, "clk_25_pg6", CLKOUT_D40, 0x74f, 0x750, 0x751, 0, 0xae5, 0, 0),
+	D_GATE(CLK_25_PG7, "clk_25_pg7", CLKOUT_D40, 0x752, 0x753, 0x754, 0, 0xae6, 0, 0),
+	D_GATE(CLK_25_PG8, "clk_25_pg8", CLKOUT_D40, 0x755, 0x756, 0x757, 0, 0xae7, 0, 0),
+	D_GATE(CLK_ADC, "clk_adc", DIV_ADC, 0x1ea, 0x1eb, 0, 0, 0, 0, 0),
+	D_GATE(CLK_ECAT100, "clk_ecat100", CLKOUT_D10, 0x405, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_HSR100, "clk_hsr100", CLKOUT_D10, 0x483, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_I2C0, "clk_i2c0", DIV_I2C, 0x1e6, 0x1e7, 0, 0, 0, 0, 0),
+	D_GATE(CLK_I2C1, "clk_i2c1", DIV_I2C, 0x1e8, 0x1e9, 0, 0, 0, 0, 0),
+	D_GATE(CLK_MII_REF, "clk_mii_ref", CLKOUT_D40, 0x342, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_NAND, "clk_nand", DIV_NAND, 0x284, 0x285, 0, 0, 0, 0, 0),
+	D_GATE(CLK_NOUSBP2_PG6, "clk_nousbp2_pg6", DIV_P2_PG, 0x774, 0x775, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P1_PG2, "clk_p1_pg2", DIV_P1_PG, 0x862, 0x863, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P1_PG3, "clk_p1_pg3", DIV_P1_PG, 0x864, 0x865, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P1_PG4, "clk_p1_pg4", DIV_P1_PG, 0x866, 0x867, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P4_PG3, "clk_p4_pg3", DIV_P4_PG, 0x824, 0x825, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P4_PG4, "clk_p4_pg4", DIV_P4_PG, 0x826, 0x827, 0, 0, 0, 0, 0),
+	D_GATE(CLK_P6_PG1, "clk_p6_pg1", DIV_P6_PG, 0x8a0, 0x8a1, 0x8a2, 0, 0xb60, 0, 0),
+	D_GATE(CLK_P6_PG2, "clk_p6_pg2", DIV_P6_PG, 0x8a3, 0x8a4, 0x8a5, 0, 0xb61, 0, 0),
+	D_GATE(CLK_P6_PG3, "clk_p6_pg3", DIV_P6_PG, 0x8a6, 0x8a7, 0x8a8, 0, 0xb62, 0, 0),
+	D_GATE(CLK_P6_PG4, "clk_p6_pg4", DIV_P6_PG, 0x8a9, 0x8aa, 0x8ab, 0, 0xb63, 0, 0),
+	D_GATE(CLK_QSPI0, "clk_qspi0", DIV_QSPI0, 0x2a4, 0x2a5, 0, 0, 0, 0, 0),
+	D_GATE(CLK_QSPI1, "clk_qspi1", DIV_QSPI1, 0x484, 0x485, 0, 0, 0, 0, 0),
+	D_GATE(CLK_RGMII_REF, "clk_rgmii_ref", CLKOUT_D8, 0x340, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_RMII_REF, "clk_rmii_ref", CLKOUT_D20, 0x341, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SDIO0, "clk_sdio0", DIV_SDIO0, 0x64, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SDIO1, "clk_sdio1", DIV_SDIO1, 0x644, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SERCOS100, "clk_sercos100", CLKOUT_D10, 0x425, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SLCD, "clk_slcd", DIV_P1_PG, 0x860, 0x861, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI0, "clk_spi0", DIV_P3_PG, 0x7e0, 0x7e1, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI1, "clk_spi1", DIV_P3_PG, 0x7e2, 0x7e3, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI2, "clk_spi2", DIV_P3_PG, 0x7e4, 0x7e5, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI3, "clk_spi3", DIV_P3_PG, 0x7e6, 0x7e7, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI4, "clk_spi4", DIV_P4_PG, 0x820, 0x821, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SPI5, "clk_spi5", DIV_P4_PG, 0x822, 0x823, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SWITCH, "clk_switch", DIV_SWITCH, 0x982, 0x983, 0, 0, 0, 0, 0),
+	D_DIV(DIV_MOTOR, "div_motor", CLKOUT_D5, 84, 2, 8),
+	D_GATE(HCLK_ECAT125, "hclk_ecat125", CLKOUT_D8, 0x400, 0x401, 0, 0x402, 0, 0x440, 0x441),
+	D_GATE(HCLK_PINCONFIG, "hclk_pinconfig", CLKOUT_D40, 0x740, 0x741, 0x742, 0, 0xae0, 0, 0),
+	D_GATE(HCLK_SERCOS, "hclk_sercos", CLKOUT_D10, 0x420, 0x422, 0, 0x421, 0, 0x460, 0x461),
+	D_GATE(HCLK_SGPIO2, "hclk_sgpio2", DIV_P5_PG, 0x8c3, 0x8c4, 0x8c5, 0, 0xb41, 0, 0),
+	D_GATE(HCLK_SGPIO3, "hclk_sgpio3", DIV_P5_PG, 0x8c6, 0x8c7, 0x8c8, 0, 0xb42, 0, 0),
+	D_GATE(HCLK_SGPIO4, "hclk_sgpio4", DIV_P5_PG, 0x8c9, 0x8ca, 0x8cb, 0, 0xb43, 0, 0),
+	D_GATE(HCLK_TIMER0, "hclk_timer0", CLKOUT_D40, 0x743, 0x744, 0x745, 0, 0xae1, 0, 0),
+	D_GATE(HCLK_TIMER1, "hclk_timer1", CLKOUT_D40, 0x746, 0x747, 0x748, 0, 0xae2, 0, 0),
+	D_GATE(HCLK_USBF, "hclk_usbf", CLKOUT_D8, 0xe3, 0, 0, 0xe4, 0, 0x102, 0x103),
+	D_GATE(HCLK_USBH, "hclk_usbh", CLKOUT_D8, 0xe0, 0xe1, 0, 0xe2, 0, 0x100, 0x101),
+	D_GATE(HCLK_USBPM, "hclk_usbpm", CLKOUT_D8, 0xe5, 0, 0, 0, 0, 0, 0),
+	D_GATE(CLK_48_PG_F, "clk_48_pg_f", CLK_48, 0x78c, 0x78d, 0, 0x78e, 0, 0xb04, 0xb05),
+	D_GATE(CLK_48_PG4, "clk_48_pg4", CLK_48, 0x789, 0x78a, 0x78b, 0, 0xb03, 0, 0),
+	D_FFC(CLK_DDRPHY_PLLCLK_D4, "clk_ddrphy_pllclk_d4", CLK_DDRPHY_PLLCLK, 4),
+	D_FFC(CLK_ECAT100_D4, "clk_ecat100_d4", CLK_ECAT100, 4),
+	D_FFC(CLK_HSR100_D2, "clk_hsr100_d2", CLK_HSR100, 2),
+	D_FFC(CLK_REF_SYNC_D4, "clk_ref_sync_d4", CLK_REF_SYNC, 4),
+	D_FFC(CLK_REF_SYNC_D8, "clk_ref_sync_d8", CLK_REF_SYNC, 8),
+	D_FFC(CLK_SERCOS100_D2, "clk_sercos100_d2", CLK_SERCOS100, 2),
+	D_DIV(DIV_CA7, "div_ca7", CLK_REF_SYNC, 57, 1, 4, 1, 2, 4),
+	D_GATE(HCLK_CAN0, "hclk_can0", CLK_48, 0x783, 0x784, 0x785, 0, 0xb01, 0, 0),
+	D_GATE(HCLK_CAN1, "hclk_can1", CLK_48, 0x786, 0x787, 0x788, 0, 0xb02, 0, 0),
+	D_GATE(HCLK_DELTASIGMA, "hclk_deltasigma", DIV_MOTOR, 0x1ef, 0x1f0, 0x1f1, 0, 0, 0, 0),
+	D_GATE(HCLK_PWMPTO, "hclk_pwmpto", DIV_MOTOR, 0x1ec, 0x1ed, 0x1ee, 0, 0, 0, 0),
+	D_GATE(HCLK_RSV, "hclk_rsv", CLK_48, 0x780, 0x781, 0x782, 0, 0xb00, 0, 0),
+	D_GATE(HCLK_SGPIO0, "hclk_sgpio0", DIV_MOTOR, 0x1e0, 0x1e1, 0x1e2, 0, 0, 0, 0),
+	D_GATE(HCLK_SGPIO1, "hclk_sgpio1", DIV_MOTOR, 0x1e3, 0x1e4, 0x1e5, 0, 0, 0, 0),
+	D_DIV(RTOS_MDC, "rtos_mdc", CLK_REF_SYNC, 100, 80, 640, 80, 160, 320, 640),
+	D_GATE(CLK_CM3, "clk_cm3", CLK_REF_SYNC_D4, 0xba0, 0xba1, 0, 0xba2, 0, 0xbc0, 0xbc1),
+	D_GATE(CLK_DDRC, "clk_ddrc", CLK_DDRPHY_PLLCLK_D4, 0x323, 0x324, 0, 0, 0, 0, 0),
+	D_GATE(CLK_ECAT25, "clk_ecat25", CLK_ECAT100_D4, 0x403, 0x404, 0, 0, 0, 0, 0),
+	D_GATE(CLK_HSR50, "clk_hsr50", CLK_HSR100_D2, 0x484, 0x485, 0, 0, 0, 0, 0),
+	D_GATE(CLK_HW_RTOS, "clk_hw_rtos", CLK_REF_SYNC_D4, 0xc60, 0xc61, 0, 0, 0, 0, 0),
+	D_GATE(CLK_SERCOS50, "clk_sercos50", CLK_SERCOS100_D2, 0x424, 0x423, 0, 0, 0, 0, 0),
+	D_GATE(HCLK_ADC, "hclk_adc", CLK_REF_SYNC_D8, 0x1af, 0x1b0, 0x1b1, 0, 0, 0, 0),
+	D_GATE(HCLK_CM3, "hclk_cm3", CLK_REF_SYNC_D4, 0xc20, 0xc21, 0xc22, 0, 0, 0, 0),
+	D_GATE(HCLK_CRYPTO_EIP150, "hclk_crypto_eip150", CLK_REF_SYNC_D4, 0x123, 0x124, 0x125, 0, 0x142, 0, 0),
+	D_GATE(HCLK_CRYPTO_EIP93, "hclk_crypto_eip93", CLK_REF_SYNC_D4, 0x120, 0x121, 0, 0x122, 0, 0x140, 0x141),
+	D_GATE(HCLK_DDRC, "hclk_ddrc", CLK_REF_SYNC_D4, 0x320, 0x322, 0, 0x321, 0, 0x3a0, 0x3a1),
+	D_GATE(HCLK_DMA0, "hclk_dma0", CLK_REF_SYNC_D4, 0x260, 0x261, 0x262, 0x263, 0x2c0, 0x2c1, 0x2c2),
+	D_GATE(HCLK_DMA1, "hclk_dma1", CLK_REF_SYNC_D4, 0x264, 0x265, 0x266, 0x267, 0x2c3, 0x2c4, 0x2c5),
+	D_GATE(HCLK_GMAC0, "hclk_gmac0", CLK_REF_SYNC_D4, 0x360, 0x361, 0x362, 0x363, 0x3c0, 0x3c1, 0x3c2),
+	D_GATE(HCLK_GMAC1, "hclk_gmac1", CLK_REF_SYNC_D4, 0x380, 0x381, 0x382, 0x383, 0x3e0, 0x3e1, 0x3e2),
+	D_GATE(HCLK_GPIO0, "hclk_gpio0", CLK_REF_SYNC_D4, 0x212, 0x213, 0x214, 0, 0, 0, 0),
+	D_GATE(HCLK_GPIO1, "hclk_gpio1", CLK_REF_SYNC_D4, 0x215, 0x216, 0x217, 0, 0, 0, 0),
+	D_GATE(HCLK_GPIO2, "hclk_gpio2", CLK_REF_SYNC_D4, 0x229, 0x22a, 0x22b, 0, 0, 0, 0),
+	D_GATE(HCLK_HSR, "hclk_hsr", CLK_HSR100_D2, 0x480, 0x482, 0, 0x481, 0, 0x4c0, 0x4c1),
+	D_GATE(HCLK_I2C0, "hclk_i2c0", CLK_REF_SYNC_D8, 0x1a9, 0x1aa, 0x1ab, 0, 0, 0, 0),
+	D_GATE(HCLK_I2C1, "hclk_i2c1", CLK_REF_SYNC_D8, 0x1ac, 0x1ad, 0x1ae, 0, 0, 0, 0),
+	D_GATE(HCLK_LCD, "hclk_lcd", CLK_REF_SYNC_D4, 0x7a0, 0x7a1, 0x7a2, 0, 0xb20, 0, 0),
+	D_GATE(HCLK_MSEBI_M, "hclk_msebi_m", CLK_REF_SYNC_D4, 0x164, 0x165, 0x166, 0, 0x183, 0, 0),
+	D_GATE(HCLK_MSEBI_S, "hclk_msebi_s", CLK_REF_SYNC_D4, 0x160, 0x161, 0x162, 0x163, 0x180, 0x181, 0x182),
+	D_GATE(HCLK_NAND, "hclk_nand", CLK_REF_SYNC_D4, 0x280, 0x281, 0x282, 0x283, 0x2e0, 0x2e1, 0x2e2),
+	D_GATE(HCLK_PG_I, "hclk_pg_i", CLK_REF_SYNC_D4, 0x7ac, 0x7ad, 0, 0x7ae, 0, 0xb24, 0xb25),
+	D_GATE(HCLK_PG19, "hclk_pg19", CLK_REF_SYNC_D4, 0x22c, 0x22d, 0x22e, 0, 0, 0, 0),
+	D_GATE(HCLK_PG20, "hclk_pg20", CLK_REF_SYNC_D4, 0x22f, 0x230, 0x231, 0, 0, 0, 0),
+	D_GATE(HCLK_PG3, "hclk_pg3", CLK_REF_SYNC_D4, 0x7a6, 0x7a7, 0x7a8, 0, 0xb22, 0, 0),
+	D_GATE(HCLK_PG4, "hclk_pg4", CLK_REF_SYNC_D4, 0x7a9, 0x7aa, 0x7ab, 0, 0xb23, 0, 0),
+	D_GATE(HCLK_QSPI0, "hclk_qspi0", CLK_REF_SYNC_D4, 0x2a0, 0x2a1, 0x2a2, 0x2a3, 0x300, 0x301, 0x302),
+	D_GATE(HCLK_QSPI1, "hclk_qspi1", CLK_REF_SYNC_D4, 0x480, 0x481, 0x482, 0x483, 0x4c0, 0x4c1, 0x4c2),
+	D_GATE(HCLK_ROM, "hclk_rom", CLK_REF_SYNC_D4, 0xaa0, 0xaa1, 0xaa2, 0, 0xb80, 0, 0),
+	D_GATE(HCLK_RTC, "hclk_rtc", CLK_REF_SYNC_D8, 0xa00, 0, 0, 0, 0, 0, 0),
+	D_GATE(HCLK_SDIO0, "hclk_sdio0", CLK_REF_SYNC_D4, 0x60, 0x61, 0x62, 0x63, 0x80, 0x81, 0x82),
+	D_GATE(HCLK_SDIO1, "hclk_sdio1", CLK_REF_SYNC_D4, 0x640, 0x641, 0x642, 0x643, 0x660, 0x661, 0x662),
+	D_GATE(HCLK_SEMAP, "hclk_semap", CLK_REF_SYNC_D4, 0x7a3, 0x7a4, 0x7a5, 0, 0xb21, 0, 0),
+	D_GATE(HCLK_SPI0, "hclk_spi0", CLK_REF_SYNC_D4, 0x200, 0x201, 0x202, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI1, "hclk_spi1", CLK_REF_SYNC_D4, 0x203, 0x204, 0x205, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI2, "hclk_spi2", CLK_REF_SYNC_D4, 0x206, 0x207, 0x208, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI3, "hclk_spi3", CLK_REF_SYNC_D4, 0x209, 0x20a, 0x20b, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI4, "hclk_spi4", CLK_REF_SYNC_D4, 0x20c, 0x20d, 0x20e, 0, 0, 0, 0),
+	D_GATE(HCLK_SPI5, "hclk_spi5", CLK_REF_SYNC_D4, 0x20f, 0x210, 0x211, 0, 0, 0, 0),
+	D_GATE(HCLK_SWITCH, "hclk_switch", CLK_REF_SYNC_D4, 0x980, 0, 0x981, 0, 0, 0, 0),
+	D_GATE(HCLK_SWITCH_RG, "hclk_switch_rg", CLK_REF_SYNC_D4, 0xc40, 0xc41, 0xc42, 0, 0, 0, 0),
+	D_GATE(HCLK_UART0, "hclk_uart0", CLK_REF_SYNC_D8, 0x1a0, 0x1a1, 0x1a2, 0, 0, 0, 0),
+	D_GATE(HCLK_UART1, "hclk_uart1", CLK_REF_SYNC_D8, 0x1a3, 0x1a4, 0x1a5, 0, 0, 0, 0),
+	D_GATE(HCLK_UART2, "hclk_uart2", CLK_REF_SYNC_D8, 0x1a6, 0x1a7, 0x1a8, 0, 0, 0, 0),
+	D_GATE(HCLK_UART3, "hclk_uart3", CLK_REF_SYNC_D4, 0x218, 0x219, 0x21a, 0, 0, 0, 0),
+	D_GATE(HCLK_UART4, "hclk_uart4", CLK_REF_SYNC_D4, 0x21b, 0x21c, 0x21d, 0, 0, 0, 0),
+	D_GATE(HCLK_UART5, "hclk_uart5", CLK_REF_SYNC_D4, 0x220, 0x221, 0x222, 0, 0, 0, 0),
+	D_GATE(HCLK_UART6, "hclk_uart6", CLK_REF_SYNC_D4, 0x223, 0x224, 0x225, 0, 0, 0, 0),
+	D_GATE(HCLK_UART7, "hclk_uart7", CLK_REF_SYNC_D4, 0x226, 0x227, 0x228, 0, 0, 0, 0),
+	/*
+	 * These are not hardware clocks, but are needed to handle the special
+	 * case where we have a 'selector bit' that doesn't just change the
+	 * parent for a clock, but also the gate it's suposed to use.
+	 */
+	{
+		.index = R9A06G032_UART_GROUP_012,
+		.name = "uart_group_012",
+		.type = K_BITSEL,
+		.source = 1 + R9A06G032_DIV_UART,
+		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG1_PR2 */
+		.dual.sel = ((0xec / 4) << 5) | 24,
+		.dual.group = 0,
+	},
+	{
+		.index = R9A06G032_UART_GROUP_34567,
+		.name = "uart_group_34567",
+		.type = K_BITSEL,
+		.source = 1 + R9A06G032_DIV_P2_PG,
+		/* R9A06G032_SYSCTRL_REG_PWRCTRL_PG0_0 */
+		.dual.sel = ((0x34 / 4) << 5) | 30,
+		.dual.group = 1,
+	},
+	D_UGATE(CLK_UART0, "clk_uart0", UART_GROUP_012, 0, 0, 0x1b2, 0x1b3, 0x1b4, 0x1b5),
+	D_UGATE(CLK_UART1, "clk_uart1", UART_GROUP_012, 0, 1, 0x1b6, 0x1b7, 0x1b8, 0x1b9),
+	D_UGATE(CLK_UART2, "clk_uart2", UART_GROUP_012, 0, 2, 0x1ba, 0x1bb, 0x1bc, 0x1bd),
+	D_UGATE(CLK_UART3, "clk_uart3", UART_GROUP_34567, 1, 0, 0x760, 0x761, 0x762, 0x763),
+	D_UGATE(CLK_UART4, "clk_uart4", UART_GROUP_34567, 1, 1, 0x764, 0x765, 0x766, 0x767),
+	D_UGATE(CLK_UART5, "clk_uart5", UART_GROUP_34567, 1, 2, 0x768, 0x769, 0x76a, 0x76b),
+	D_UGATE(CLK_UART6, "clk_uart6", UART_GROUP_34567, 1, 3, 0x76c, 0x76d, 0x76e, 0x76f),
+	D_UGATE(CLK_UART7, "clk_uart7", UART_GROUP_34567, 1, 4, 0x770, 0x771, 0x772, 0x773),
+};
+
+struct r9a06g032_priv {
+	struct clk_onecell_data data;
+	spinlock_t lock; /* protects concurent access to gates */
+	void __iomem *reg;
+};
+
+/* register/bit pairs are encoded as an uint16_t */
+static void
+clk_rdesc_set(struct r9a06g032_priv *clocks,
+	      u16 one, unsigned int on)
+{
+	u32 __iomem *reg = clocks->reg + (4 * (one >> 5));
+	u32 val = readl(reg);
+
+	val = (val & ~(1U << (one & 0x1f))) | ((!!on) << (one & 0x1f));
+	writel(val, reg);
+}
+
+static int
+clk_rdesc_get(struct r9a06g032_priv *clocks,
+	      uint16_t one)
+{
+	u32 __iomem *reg = clocks->reg + (4 * (one >> 5));
+	u32 val = readl(reg);
+
+	return !!(val & (1U << (one & 0x1f)));
+}
+
+/*
+ * This implements the R9A09G032 clock gate 'driver'. We cannot use the system's
+ * clock gate framework as the gates on the R9A09G032 have a special enabling
+ * sequence, therefore we use this little proxy.
+ */
+struct r9a06g032_clk_gate {
+	struct clk_hw hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+
+	struct r9a06g032_gate gate;
+};
+
+#define to_r9a06g032_gate(_hw) container_of(_hw, struct r9a06g032_clk_gate, hw)
+
+static void
+r9a06g032_clk_gate_set(struct r9a06g032_priv *clocks,
+		       struct r9a06g032_gate *g, int on)
+{
+	unsigned long flags;
+
+	WARN_ON(!g->gate);
+
+	spin_lock_irqsave(&clocks->lock, flags);
+	clk_rdesc_set(clocks, g->gate, on);
+	/* De-assert reset */
+	if (g->reset)
+		clk_rdesc_set(clocks, g->reset, 1);
+	spin_unlock_irqrestore(&clocks->lock, flags);
+
+	/* Hardware manual recommends 5us delay after enabling clock & reset */
+	udelay(5);
+
+	/* If the peripheral is memory mapped (i.e. an AXI slave), there is an
+	 * associated SLVRDY bit in the System Controller that needs to be set
+	 * so that the FlexWAY bus fabric passes on the read/write requests.
+	 */
+	if (g->ready || g->midle) {
+		spin_lock_irqsave(&clocks->lock, flags);
+		if (g->ready)
+			clk_rdesc_set(clocks, g->ready, on);
+		/* Clear 'Master Idle Request' bit */
+		if (g->midle)
+			clk_rdesc_set(clocks, g->midle, !on);
+		spin_unlock_irqrestore(&clocks->lock, flags);
+	}
+	/* Note: We don't wait for FlexWAY Socket Connection signal */
+}
+
+static int r9a06g032_clk_gate_enable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_gate *g = to_r9a06g032_gate(hw);
+
+	r9a06g032_clk_gate_set(g->clocks, &g->gate, 1);
+	return 0;
+}
+
+static void r9a06g032_clk_gate_disable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_gate *g = to_r9a06g032_gate(hw);
+
+	r9a06g032_clk_gate_set(g->clocks, &g->gate, 0);
+}
+
+static int r9a06g032_clk_gate_is_enabled(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_gate *g = to_r9a06g032_gate(hw);
+
+	/* if clock is in reset, the gate might be on, and still not 'be' on */
+	if (g->gate.reset && !clk_rdesc_get(g->clocks, g->gate.reset))
+		return 0;
+
+	return clk_rdesc_get(g->clocks, g->gate.gate);
+}
+
+static const struct clk_ops r9a06g032_clk_gate_ops = {
+	.enable = r9a06g032_clk_gate_enable,
+	.disable = r9a06g032_clk_gate_disable,
+	.is_enabled = r9a06g032_clk_gate_is_enabled,
+};
+
+static struct clk *
+r9a06g032_register_gate(struct r9a06g032_priv *clocks,
+			const char *parent_name,
+			const struct r9a06g032_clkdesc *desc)
+{
+	struct clk *clk;
+	struct r9a06g032_clk_gate *g;
+	struct clk_init_data init;
+
+	g = kzalloc(sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return NULL;
+
+	init.name = desc->name;
+	init.ops = &r9a06g032_clk_gate_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	g->clocks = clocks;
+	g->index = desc->index;
+	g->gate = desc->gate;
+	g->hw.init = &init;
+
+	/*
+	 * important here, some clocks are already in use by the CM3, we
+	 * have to assume they are not Linux's to play with and try to disable
+	 * at the end of the boot!
+	 */
+	if (r9a06g032_clk_gate_is_enabled(&g->hw)) {
+		init.flags |= CLK_IS_CRITICAL;
+		pr_debug("%s was enabled, making read-only\n", desc->name);
+	}
+
+	clk = clk_register(NULL, &g->hw);
+	if (IS_ERR(clk)) {
+		kfree(g);
+		return NULL;
+	}
+	return clk;
+}
+
+struct r9a06g032_clk_div {
+	struct clk_hw hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+	u16 reg;
+	u16 min, max;
+	u8 table_size;
+	u16 table[8];	/* we know there are no more than 8 */
+};
+
+#define to_r9a06g032_div(_hw) \
+		container_of(_hw, struct r9a06g032_clk_div, hw)
+
+static unsigned long
+r9a06g032_div_recalc_rate(struct clk_hw *hw,
+			  unsigned long parent_rate)
+{
+	struct r9a06g032_clk_div *clk = to_r9a06g032_div(hw);
+	u32 __iomem *reg = clk->clocks->reg + (4 * clk->reg);
+	u32 div = readl(reg);
+
+	if (div < clk->min)
+		div = clk->min;
+	else if (div > clk->max)
+		div = clk->max;
+	return DIV_ROUND_UP(parent_rate, div);
+}
+
+/*
+ * Attempts to find a value that is in range of min,max,
+ * and if a table of set dividers was specified for this
+ * register, try to find the fixed divider that is the closest
+ * to the target frequency
+ */
+static long
+r9a06g032_div_clamp_div(struct r9a06g032_clk_div *clk,
+			unsigned long rate, unsigned long prate)
+{
+	/* + 1 to cope with rates that have the remainder dropped */
+	u32 div = DIV_ROUND_UP(prate, rate + 1);
+	int i;
+
+	if (div <= clk->min)
+		return clk->min;
+	if (div >= clk->max)
+		return clk->max;
+
+	for (i = 0; clk->table_size && i < clk->table_size - 1; i++) {
+		if (div >= clk->table[i] && div <= clk->table[i + 1]) {
+			unsigned long m = rate -
+				DIV_ROUND_UP(prate, clk->table[i]);
+			unsigned long p =
+				DIV_ROUND_UP(prate, clk->table[i + 1]) -
+				rate;
+			/*
+			 * select the divider that generates
+			 * the value closest to the ideal frequency
+			 */
+			div = p >= m ? clk->table[i] : clk->table[i + 1];
+			return div;
+		}
+	}
+	return div;
+}
+
+static long
+r9a06g032_div_round_rate(struct clk_hw *hw,
+			 unsigned long rate, unsigned long *prate)
+{
+	struct r9a06g032_clk_div *clk = to_r9a06g032_div(hw);
+	u32 div = DIV_ROUND_UP(*prate, rate);
+
+	pr_devel("%s %pC %ld (prate %ld) (wanted div %u)\n", __func__,
+		 hw->clk, rate, *prate, div);
+	pr_devel("   min %d (%ld) max %d (%ld)\n",
+		 clk->min, DIV_ROUND_UP(*prate, clk->min),
+		clk->max, DIV_ROUND_UP(*prate, clk->max));
+
+	div = r9a06g032_div_clamp_div(clk, rate, *prate);
+	/*
+	 * this is a hack. Currently the serial driver asks for a clock rate
+	 * that is 16 times the baud rate -- and that is wildly outside the
+	 * range of the UART divider, somehow there is no provision for that
+	 * case of 'let the divider as is if outside range'.
+	 * The serial driver *shouldn't* play with these clocks anyway, there's
+	 * several uarts attached to this divider, and changing this impacts
+	 * everyone.
+	 */
+	if (clk->index == R9A06G032_DIV_UART) {
+		pr_devel("%s div uart hack!\n", __func__);
+		return clk_get_rate(hw->clk);
+	}
+	pr_devel("%s %pC %ld / %u = %ld\n", __func__, hw->clk,
+		 *prate, div, DIV_ROUND_UP(*prate, div));
+	return DIV_ROUND_UP(*prate, div);
+}
+
+static int
+r9a06g032_div_set_rate(struct clk_hw *hw,
+		       unsigned long rate, unsigned long parent_rate)
+{
+	struct r9a06g032_clk_div *clk = to_r9a06g032_div(hw);
+	/* + 1 to cope with rates that have the remainder dropped */
+	u32 div = DIV_ROUND_UP(parent_rate, rate + 1);
+	u32 __iomem *reg = clk->clocks->reg + (4 * clk->reg);
+
+	pr_devel("%s %pC rate %ld parent %ld div %d\n", __func__, hw->clk,
+		 rate, parent_rate, div);
+
+	/*
+	 * Need to write the bit 31 with the divider value to
+	 * latch it. Technically we should wait until it has been
+	 * cleared too.
+	 * TODO: Find whether this callback is sleepable, in case
+	 * the hardware /does/ require some sort of spinloop here.
+	 */
+	writel(div | BIT(31), reg);
+
+	return 0;
+}
+
+static const struct clk_ops r9a06g032_clk_div_ops = {
+	.recalc_rate = r9a06g032_div_recalc_rate,
+	.round_rate = r9a06g032_div_round_rate,
+	.set_rate = r9a06g032_div_set_rate,
+};
+
+static struct clk *
+r9a06g032_register_div(struct r9a06g032_priv *clocks,
+		       const char *parent_name,
+		       const struct r9a06g032_clkdesc *desc)
+{
+	struct r9a06g032_clk_div *div;
+	struct clk *clk;
+	struct clk_init_data init;
+	unsigned int i;
+
+	div = kzalloc(sizeof(*div), GFP_KERNEL);
+	if (!div)
+		return NULL;
+
+	init.name = desc->name;
+	init.ops = &r9a06g032_clk_div_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+
+	div->clocks = clocks;
+	div->index = desc->index;
+	div->reg = desc->reg;
+	div->hw.init = &init;
+	div->min = desc->div_min;
+	div->max = desc->div_max;
+	/* populate (optional) divider table fixed values */
+	for (i = 0; i < ARRAY_SIZE(div->table) &&
+	     i < ARRAY_SIZE(desc->div_table) && desc->div_table[i]; i++) {
+		div->table[div->table_size++] = desc->div_table[i];
+	}
+
+	clk = clk_register(NULL, &div->hw);
+	if (IS_ERR(clk)) {
+		kfree(div);
+		return NULL;
+	}
+	return clk;
+}
+
+/*
+ * This clock provider handles the case of the R9A06G032 where you have
+ * peripherals that have two potential clock source and two gates, one for
+ * each of the clock source - the used clock source (for all sub clocks)
+ * is selected by a single bit.
+ * That single bit affects all sub-clocks, and therefore needs to change the
+ * active gate (and turn the others off) and force a recalculation of the rates.
+ *
+ * This implements two clock providers, one 'bitselect' that
+ * handles the switch between both parents, and another 'dualgate'
+ * that knows which gate to poke at, depending on the parent's bit position.
+ */
+struct r9a06g032_clk_bitsel {
+	struct clk_hw	hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+	u16 selector;		/* selector register + bit */
+};
+
+#define to_clk_bitselect(_hw) \
+		container_of(_hw, struct r9a06g032_clk_bitsel, hw)
+
+static u8 r9a06g032_clk_mux_get_parent(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_bitsel *set = to_clk_bitselect(hw);
+
+	return clk_rdesc_get(set->clocks, set->selector);
+}
+
+static int r9a06g032_clk_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct r9a06g032_clk_bitsel *set = to_clk_bitselect(hw);
+
+	/* a single bit in the register selects one of two parent clocks */
+	clk_rdesc_set(set->clocks, set->selector, !!index);
+
+	return 0;
+}
+
+static const struct clk_ops clk_bitselect_ops = {
+	.get_parent = r9a06g032_clk_mux_get_parent,
+	.set_parent = r9a06g032_clk_mux_set_parent,
+};
+
+static struct clk *
+r9a06g032_register_bitsel(struct r9a06g032_priv *clocks,
+			  const char *parent_name,
+			  const struct r9a06g032_clkdesc *desc)
+{
+	struct clk *clk;
+	struct r9a06g032_clk_bitsel *g;
+	struct clk_init_data init;
+	const char *names[2];
+
+	/* allocate the gate */
+	g = kzalloc(sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return NULL;
+
+	names[0] = parent_name;
+	names[1] = "clk_pll_usb";
+
+	init.name = desc->name;
+	init.ops = &clk_bitselect_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = names;
+	init.num_parents = 2;
+
+	g->clocks = clocks;
+	g->index = desc->index;
+	g->selector = desc->dual.sel;
+	g->hw.init = &init;
+
+	clk = clk_register(NULL, &g->hw);
+	if (IS_ERR(clk)) {
+		kfree(g);
+		return NULL;
+	}
+	return clk;
+}
+
+struct r9a06g032_clk_dualgate {
+	struct clk_hw	hw;
+	struct r9a06g032_priv *clocks;
+	u16 index;
+	u16 selector;		/* selector register + bit */
+	struct r9a06g032_gate gate[2];
+};
+
+#define to_clk_dualgate(_hw) \
+		container_of(_hw, struct r9a06g032_clk_dualgate, hw)
+
+static int
+r9a06g032_clk_dualgate_setenable(struct r9a06g032_clk_dualgate *g, int enable)
+{
+	u8 sel_bit = clk_rdesc_get(g->clocks, g->selector);
+
+	/* we always turn off the 'other' gate, regardless */
+	r9a06g032_clk_gate_set(g->clocks, &g->gate[!sel_bit], 0);
+	r9a06g032_clk_gate_set(g->clocks, &g->gate[sel_bit], enable);
+
+	return 0;
+}
+
+static int r9a06g032_clk_dualgate_enable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_dualgate *gate = to_clk_dualgate(hw);
+
+	r9a06g032_clk_dualgate_setenable(gate, 1);
+
+	return 0;
+}
+
+static void r9a06g032_clk_dualgate_disable(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_dualgate *gate = to_clk_dualgate(hw);
+
+	r9a06g032_clk_dualgate_setenable(gate, 0);
+}
+
+static int r9a06g032_clk_dualgate_is_enabled(struct clk_hw *hw)
+{
+	struct r9a06g032_clk_dualgate *g = to_clk_dualgate(hw);
+	u8 sel_bit = clk_rdesc_get(g->clocks, g->selector);
+
+	return clk_rdesc_get(g->clocks, g->gate[sel_bit].gate);
+}
+
+static const struct clk_ops r9a06g032_clk_dualgate_ops = {
+	.enable = r9a06g032_clk_dualgate_enable,
+	.disable = r9a06g032_clk_dualgate_disable,
+	.is_enabled = r9a06g032_clk_dualgate_is_enabled,
+};
+
+static struct clk *
+r9a06g032_register_dualgate(struct r9a06g032_priv *clocks,
+			    const char *parent_name,
+			    const struct r9a06g032_clkdesc *desc,
+			    uint16_t sel)
+{
+	struct r9a06g032_clk_dualgate *g;
+	struct clk *clk;
+	struct clk_init_data init;
+
+	/* allocate the gate */
+	g = kzalloc(sizeof(*g), GFP_KERNEL);
+	if (!g)
+		return NULL;
+	g->clocks = clocks;
+	g->index = desc->index;
+	g->selector = sel;
+	g->gate[0].gate = desc->dual.g1;
+	g->gate[0].reset = desc->dual.r1;
+	g->gate[1].gate = desc->dual.g2;
+	g->gate[1].reset = desc->dual.r2;
+
+	init.name = desc->name;
+	init.ops = &r9a06g032_clk_dualgate_ops;
+	init.flags = CLK_IS_BASIC | CLK_SET_RATE_PARENT;
+	init.parent_names = &parent_name;
+	init.num_parents = 1;
+	g->hw.init = &init;
+	/*
+	 * important here, some clocks are already in use by the CM3, we
+	 * have to assume they are not Linux's to play with and try to disable
+	 * at the end of the boot!
+	 */
+	if (r9a06g032_clk_dualgate_is_enabled(&g->hw)) {
+		init.flags |= CLK_IS_CRITICAL;
+		pr_debug("%s was enabled, making read-only\n", desc->name);
+	}
+
+	clk = clk_register(NULL, &g->hw);
+	if (IS_ERR(clk)) {
+		kfree(g);
+		return NULL;
+	}
+	return clk;
+}
+
+static void r9a06g032_clocks_del_clk_provider(void *data)
+{
+	of_clk_del_provider(data);
+}
+
+static int __init r9a06g032_clocks_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct r9a06g032_priv *clocks;
+	struct clk **clks;
+	struct clk *mclk;
+	unsigned int i;
+	u16 uart_group_sel[2];
+	int error;
+
+	clocks = devm_kzalloc(dev, sizeof(*clocks), GFP_KERNEL);
+	clks = devm_kcalloc(dev, R9A06G032_CLOCK_COUNT, sizeof(struct clk *),
+			    GFP_KERNEL);
+	if (!clocks || !clks)
+		return -ENOMEM;
+
+	spin_lock_init(&clocks->lock);
+
+	clocks->data.clks = clks;
+	clocks->data.clk_num = R9A06G032_CLOCK_COUNT;
+
+	mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(mclk))
+		return PTR_ERR(mclk);
+
+	clocks->reg = of_iomap(np, 0);
+	if (WARN_ON(!clocks->reg))
+		return -ENOMEM;
+	for (i = 0; i < ARRAY_SIZE(r9a06g032_clocks); ++i) {
+		const struct r9a06g032_clkdesc *d = &r9a06g032_clocks[i];
+		const char *parent_name = d->source ?
+			__clk_get_name(clocks->data.clks[d->source - 1]) :
+			__clk_get_name(mclk);
+		struct clk *clk = NULL;
+
+		switch (d->type) {
+		case K_FFC:
+			clk = clk_register_fixed_factor(NULL, d->name,
+							parent_name, 0,
+							d->mul, d->div);
+			break;
+		case K_GATE:
+			clk = r9a06g032_register_gate(clocks, parent_name, d);
+			break;
+		case K_DIV:
+			clk = r9a06g032_register_div(clocks, parent_name, d);
+			break;
+		case K_BITSEL:
+			/* keep that selector register around */
+			uart_group_sel[d->dual.group] = d->dual.sel;
+			clk = r9a06g032_register_bitsel(clocks, parent_name, d);
+			break;
+		case K_DUALGATE:
+			clk = r9a06g032_register_dualgate(clocks, parent_name,
+							  d,
+							  uart_group_sel[d->dual.group]);
+			break;
+		}
+		clocks->data.clks[d->index] = clk;
+	}
+	error = of_clk_add_provider(np, of_clk_src_onecell_get, &clocks->data);
+	if (error)
+		return error;
+
+	return devm_add_action_or_reset(dev,
+					r9a06g032_clocks_del_clk_provider, np);
+}
+
+static const struct of_device_id r9a06g032_match[] = {
+	{ .compatible = "renesas,r9a06g032-sysctrl" },
+	{ }
+};
+
+static struct platform_driver r9a06g032_clock_driver = {
+	.driver		= {
+		.name	= "renesas,r9a06g032-sysctrl",
+		.of_match_table = r9a06g032_match,
+	},
+};
+
+static int __init r9a06g032_clocks_init(void)
+{
+	return platform_driver_probe(&r9a06g032_clock_driver,
+			r9a06g032_clocks_probe);
+}
+
+subsys_initcall(r9a06g032_clocks_init);
-- 
cgit v1.2.3


From 50c678772a0b3f9dc6b04262f27e2c373fe03a4d Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <jmkrzyszt@gmail.com>
Date: Sun, 24 Jun 2018 20:14:41 +0200
Subject: ASoC: cx20442: Don't ignore regulator_get() errors.

In its current shape, the driver just ignores errors returned by
regulator_get() at component_probe().  This doesn't hurt on Amstrad
Delta board as long as it registers the codec device at late_initcall,
when the regulator which depends on basic-mmio-gpio device (probed as
late as at dev_initcall) is already available.  Otherwise the driver
may end up trying to control a codec which is not powered up.

Remove that dependency on initialization order by handling the error.
If the regulator is not yet available and -ENODEV is returned, convert
it to -EPROBE_DEFER to get another chance.

Signed-off-by: Janusz Krzysztofik <jmkrzyszt@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cx20442.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c
index 07dd33b09596..ab174b5114dc 100644
--- a/sound/soc/codecs/cx20442.c
+++ b/sound/soc/codecs/cx20442.c
@@ -362,8 +362,27 @@ static int cx20442_component_probe(struct snd_soc_component *component)
 		return -ENOMEM;
 
 	cx20442->por = regulator_get(component->dev, "POR");
-	if (IS_ERR(cx20442->por))
-		dev_warn(component->dev, "failed to get the regulator");
+	if (IS_ERR(cx20442->por)) {
+		int err = PTR_ERR(cx20442->por);
+
+		dev_warn(component->dev, "failed to get POR supply (%d)", err);
+		/*
+		 * When running on a non-dt platform and requested regulator
+		 * is not available, regulator_get() never returns
+		 * -EPROBE_DEFER as it is not able to justify if the regulator
+		 * may still appear later.  On the other hand, the board can
+		 * still set full constraints flag at late_initcall in order
+		 * to instruct regulator_get() to return a dummy one if
+		 * sufficient.  Hence, if we get -ENODEV here, let's convert
+		 * it to -EPROBE_DEFER and wait for the board to decide or
+		 * let Deferred Probe infrastructure handle this error.
+		 */
+		if (err == -ENODEV)
+			err = -EPROBE_DEFER;
+		kfree(cx20442);
+		return err;
+	}
+
 	cx20442->tty = NULL;
 
 	snd_soc_component_set_drvdata(component, cx20442);
-- 
cgit v1.2.3


From 1572042a4ab25567e4785b53b947729dfa2dac99 Mon Sep 17 00:00:00 2001
From: David Herrmann <dh.herrmann@gmail.com>
Date: Mon, 18 Jun 2018 16:17:28 +0200
Subject: drm: provide management functions for drm_file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather than doing drm_file allocation/destruction right in the fops, lets
provide separate helpers. This decouples drm_file management from the
still-mandatory drm-fops. It prepares for use of drm_file without the
fops, both by possible separate fops implementations and APIs (not that I
am aware of any such plans), and more importantly from in-kernel use where
no real file is available.

Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618141739.48151-2-noralf@tronnes.org
---
 drivers/gpu/drm/drm_file.c     | 305 +++++++++++++++++++++++------------------
 drivers/gpu/drm/drm_internal.h |   2 +
 2 files changed, 175 insertions(+), 132 deletions(-)

diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 6d9b9453707c..c0410b833043 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -101,6 +101,175 @@ DEFINE_MUTEX(drm_global_mutex);
 
 static int drm_open_helper(struct file *filp, struct drm_minor *minor);
 
+/**
+ * drm_file_alloc - allocate file context
+ * @minor: minor to allocate on
+ *
+ * This allocates a new DRM file context. It is not linked into any context and
+ * can be used by the caller freely. Note that the context keeps a pointer to
+ * @minor, so it must be freed before @minor is.
+ *
+ * RETURNS:
+ * Pointer to newly allocated context, ERR_PTR on failure.
+ */
+struct drm_file *drm_file_alloc(struct drm_minor *minor)
+{
+	struct drm_device *dev = minor->dev;
+	struct drm_file *file;
+	int ret;
+
+	file = kzalloc(sizeof(*file), GFP_KERNEL);
+	if (!file)
+		return ERR_PTR(-ENOMEM);
+
+	file->pid = get_pid(task_pid(current));
+	file->minor = minor;
+
+	/* for compatibility root is always authenticated */
+	file->authenticated = capable(CAP_SYS_ADMIN);
+	file->lock_count = 0;
+
+	INIT_LIST_HEAD(&file->lhead);
+	INIT_LIST_HEAD(&file->fbs);
+	mutex_init(&file->fbs_lock);
+	INIT_LIST_HEAD(&file->blobs);
+	INIT_LIST_HEAD(&file->pending_event_list);
+	INIT_LIST_HEAD(&file->event_list);
+	init_waitqueue_head(&file->event_wait);
+	file->event_space = 4096; /* set aside 4k for event buffer */
+
+	mutex_init(&file->event_read_lock);
+
+	if (drm_core_check_feature(dev, DRIVER_GEM))
+		drm_gem_open(dev, file);
+
+	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		drm_syncobj_open(file);
+
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_init_file_private(&file->prime);
+
+	if (dev->driver->open) {
+		ret = dev->driver->open(dev, file);
+		if (ret < 0)
+			goto out_prime_destroy;
+	}
+
+	if (drm_is_primary_client(file)) {
+		ret = drm_master_open(file);
+		if (ret)
+			goto out_close;
+	}
+
+	return file;
+
+out_close:
+	if (dev->driver->postclose)
+		dev->driver->postclose(dev, file);
+out_prime_destroy:
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_destroy_file_private(&file->prime);
+	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		drm_syncobj_release(file);
+	if (drm_core_check_feature(dev, DRIVER_GEM))
+		drm_gem_release(dev, file);
+	put_pid(file->pid);
+	kfree(file);
+
+	return ERR_PTR(ret);
+}
+
+static void drm_events_release(struct drm_file *file_priv)
+{
+	struct drm_device *dev = file_priv->minor->dev;
+	struct drm_pending_event *e, *et;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+
+	/* Unlink pending events */
+	list_for_each_entry_safe(e, et, &file_priv->pending_event_list,
+				 pending_link) {
+		list_del(&e->pending_link);
+		e->file_priv = NULL;
+	}
+
+	/* Remove unconsumed events */
+	list_for_each_entry_safe(e, et, &file_priv->event_list, link) {
+		list_del(&e->link);
+		kfree(e);
+	}
+
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+/**
+ * drm_file_free - free file context
+ * @file: context to free, or NULL
+ *
+ * This destroys and deallocates a DRM file context previously allocated via
+ * drm_file_alloc(). The caller must make sure to unlink it from any contexts
+ * before calling this.
+ *
+ * If NULL is passed, this is a no-op.
+ *
+ * RETURNS:
+ * 0 on success, or error code on failure.
+ */
+void drm_file_free(struct drm_file *file)
+{
+	struct drm_device *dev;
+
+	if (!file)
+		return;
+
+	dev = file->minor->dev;
+
+	DRM_DEBUG("pid = %d, device = 0x%lx, open_count = %d\n",
+		  task_pid_nr(current),
+		  (long)old_encode_dev(file->minor->kdev->devt),
+		  dev->open_count);
+
+	if (drm_core_check_feature(dev, DRIVER_LEGACY) &&
+	    dev->driver->preclose)
+		dev->driver->preclose(dev, file);
+
+	if (drm_core_check_feature(dev, DRIVER_LEGACY))
+		drm_legacy_lock_release(dev, file->filp);
+
+	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA))
+		drm_legacy_reclaim_buffers(dev, file);
+
+	drm_events_release(file);
+
+	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+		drm_fb_release(file);
+		drm_property_destroy_user_blobs(dev, file);
+	}
+
+	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
+		drm_syncobj_release(file);
+
+	if (drm_core_check_feature(dev, DRIVER_GEM))
+		drm_gem_release(dev, file);
+
+	drm_legacy_ctxbitmap_flush(dev, file);
+
+	if (drm_is_primary_client(file))
+		drm_master_release(file);
+
+	if (dev->driver->postclose)
+		dev->driver->postclose(dev, file);
+
+	if (drm_core_check_feature(dev, DRIVER_PRIME))
+		drm_prime_destroy_file_private(&file->prime);
+
+	WARN_ON(!list_empty(&file->event_list));
+
+	put_pid(file->pid);
+	kfree(file);
+}
+
 static int drm_setup(struct drm_device * dev)
 {
 	int ret;
@@ -196,7 +365,6 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 {
 	struct drm_device *dev = minor->dev;
 	struct drm_file *priv;
-	int ret;
 
 	if (filp->f_flags & O_EXCL)
 		return -EBUSY;	/* No exclusive opens */
@@ -207,51 +375,13 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 
 	DRM_DEBUG("pid = %d, minor = %d\n", task_pid_nr(current), minor->index);
 
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
+	priv = drm_file_alloc(minor);
+	if (IS_ERR(priv))
+		return PTR_ERR(priv);
 
 	filp->private_data = priv;
 	filp->f_mode |= FMODE_UNSIGNED_OFFSET;
 	priv->filp = filp;
-	priv->pid = get_pid(task_pid(current));
-	priv->minor = minor;
-
-	/* for compatibility root is always authenticated */
-	priv->authenticated = capable(CAP_SYS_ADMIN);
-	priv->lock_count = 0;
-
-	INIT_LIST_HEAD(&priv->lhead);
-	INIT_LIST_HEAD(&priv->fbs);
-	mutex_init(&priv->fbs_lock);
-	INIT_LIST_HEAD(&priv->blobs);
-	INIT_LIST_HEAD(&priv->pending_event_list);
-	INIT_LIST_HEAD(&priv->event_list);
-	init_waitqueue_head(&priv->event_wait);
-	priv->event_space = 4096; /* set aside 4k for event buffer */
-
-	mutex_init(&priv->event_read_lock);
-
-	if (drm_core_check_feature(dev, DRIVER_GEM))
-		drm_gem_open(dev, priv);
-
-	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
-		drm_syncobj_open(priv);
-
-	if (drm_core_check_feature(dev, DRIVER_PRIME))
-		drm_prime_init_file_private(&priv->prime);
-
-	if (dev->driver->open) {
-		ret = dev->driver->open(dev, priv);
-		if (ret < 0)
-			goto out_prime_destroy;
-	}
-
-	if (drm_is_primary_client(priv)) {
-		ret = drm_master_open(priv);
-		if (ret)
-			goto out_close;
-	}
 
 	mutex_lock(&dev->filelist_mutex);
 	list_add(&priv->lhead, &dev->filelist);
@@ -278,45 +408,6 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 #endif
 
 	return 0;
-
-out_close:
-	if (dev->driver->postclose)
-		dev->driver->postclose(dev, priv);
-out_prime_destroy:
-	if (drm_core_check_feature(dev, DRIVER_PRIME))
-		drm_prime_destroy_file_private(&priv->prime);
-	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
-		drm_syncobj_release(priv);
-	if (drm_core_check_feature(dev, DRIVER_GEM))
-		drm_gem_release(dev, priv);
-	put_pid(priv->pid);
-	kfree(priv);
-	filp->private_data = NULL;
-	return ret;
-}
-
-static void drm_events_release(struct drm_file *file_priv)
-{
-	struct drm_device *dev = file_priv->minor->dev;
-	struct drm_pending_event *e, *et;
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->event_lock, flags);
-
-	/* Unlink pending events */
-	list_for_each_entry_safe(e, et, &file_priv->pending_event_list,
-				 pending_link) {
-		list_del(&e->pending_link);
-		e->file_priv = NULL;
-	}
-
-	/* Remove unconsumed events */
-	list_for_each_entry_safe(e, et, &file_priv->event_list, link) {
-		list_del(&e->link);
-		kfree(e);
-	}
-
-	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
 static void drm_legacy_dev_reinit(struct drm_device *dev)
@@ -383,57 +474,7 @@ int drm_release(struct inode *inode, struct file *filp)
 	list_del(&file_priv->lhead);
 	mutex_unlock(&dev->filelist_mutex);
 
-	if (drm_core_check_feature(dev, DRIVER_LEGACY) &&
-	    dev->driver->preclose)
-		dev->driver->preclose(dev, file_priv);
-
-	/* ========================================================
-	 * Begin inline drm_release
-	 */
-
-	DRM_DEBUG("pid = %d, device = 0x%lx, open_count = %d\n",
-		  task_pid_nr(current),
-		  (long)old_encode_dev(file_priv->minor->kdev->devt),
-		  dev->open_count);
-
-	if (drm_core_check_feature(dev, DRIVER_LEGACY))
-		drm_legacy_lock_release(dev, filp);
-
-	if (drm_core_check_feature(dev, DRIVER_HAVE_DMA))
-		drm_legacy_reclaim_buffers(dev, file_priv);
-
-	drm_events_release(file_priv);
-
-	if (drm_core_check_feature(dev, DRIVER_MODESET)) {
-		drm_fb_release(file_priv);
-		drm_property_destroy_user_blobs(dev, file_priv);
-	}
-
-	if (drm_core_check_feature(dev, DRIVER_SYNCOBJ))
-		drm_syncobj_release(file_priv);
-
-	if (drm_core_check_feature(dev, DRIVER_GEM))
-		drm_gem_release(dev, file_priv);
-
-	drm_legacy_ctxbitmap_flush(dev, file_priv);
-
-	if (drm_is_primary_client(file_priv))
-		drm_master_release(file_priv);
-
-	if (dev->driver->postclose)
-		dev->driver->postclose(dev, file_priv);
-
-	if (drm_core_check_feature(dev, DRIVER_PRIME))
-		drm_prime_destroy_file_private(&file_priv->prime);
-
-	WARN_ON(!list_empty(&file_priv->event_list));
-
-	put_pid(file_priv->pid);
-	kfree(file_priv);
-
-	/* ========================================================
-	 * End inline drm_release
-	 */
+	drm_file_free(file_priv);
 
 	if (!--dev->open_count) {
 		drm_lastclose(dev);
diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
index b72242e93ea4..40179c5fc6b8 100644
--- a/drivers/gpu/drm/drm_internal.h
+++ b/drivers/gpu/drm/drm_internal.h
@@ -26,6 +26,8 @@
 
 /* drm_file.c */
 extern struct mutex drm_global_mutex;
+struct drm_file *drm_file_alloc(struct drm_minor *minor);
+void drm_file_free(struct drm_file *file);
 void drm_lastclose(struct drm_device *dev);
 
 /* drm_pci.c */
-- 
cgit v1.2.3


From 7eeaeb90a6a5c8dc0de9bbb16a12d474d31d820e Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Mon, 18 Jun 2018 16:17:29 +0200
Subject: drm/file: Don't set master on in-kernel clients
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It only makes sense for userspace clients.

Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618141739.48151-3-noralf@tronnes.org
---
 drivers/gpu/drm/drm_file.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index c0410b833043..66bb403dc8ab 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -155,17 +155,8 @@ struct drm_file *drm_file_alloc(struct drm_minor *minor)
 			goto out_prime_destroy;
 	}
 
-	if (drm_is_primary_client(file)) {
-		ret = drm_master_open(file);
-		if (ret)
-			goto out_close;
-	}
-
 	return file;
 
-out_close:
-	if (dev->driver->postclose)
-		dev->driver->postclose(dev, file);
 out_prime_destroy:
 	if (drm_core_check_feature(dev, DRIVER_PRIME))
 		drm_prime_destroy_file_private(&file->prime);
@@ -365,6 +356,7 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 {
 	struct drm_device *dev = minor->dev;
 	struct drm_file *priv;
+	int ret;
 
 	if (filp->f_flags & O_EXCL)
 		return -EBUSY;	/* No exclusive opens */
@@ -379,6 +371,14 @@ static int drm_open_helper(struct file *filp, struct drm_minor *minor)
 	if (IS_ERR(priv))
 		return PTR_ERR(priv);
 
+	if (drm_is_primary_client(priv)) {
+		ret = drm_master_open(priv);
+		if (ret) {
+			drm_file_free(priv);
+			return ret;
+		}
+	}
+
 	filp->private_data = priv;
 	filp->f_mode |= FMODE_UNSIGNED_OFFSET;
 	priv->filp = filp;
-- 
cgit v1.2.3


From d30827ce0df4410648c3fbba48681d7aafb19f36 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Mon, 18 Jun 2018 16:17:30 +0200
Subject: drm: Make ioctls available for in-kernel clients
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make ioctl wrappers for functions that will be used by the in-kernel API.
The following functions are touched:
- drm_mode_create_dumb_ioctl()
- drm_mode_destroy_dumb_ioctl()
- drm_mode_addfb()
- drm_mode_rmfb()

Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618141739.48151-4-noralf@tronnes.org
---
 drivers/gpu/drm/drm_crtc_internal.h | 19 +++++++++++++----
 drivers/gpu/drm/drm_dumb_buffers.c  | 29 +++++++++++++++++--------
 drivers/gpu/drm/drm_framebuffer.c   | 42 ++++++++++++++++++++++++-------------
 drivers/gpu/drm/drm_ioctl.c         |  4 ++--
 4 files changed, 64 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 34499800932a..235d40fce8b5 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -65,6 +65,12 @@ int drm_mode_getresources(struct drm_device *dev,
 
 
 /* drm_dumb_buffers.c */
+int drm_mode_create_dumb(struct drm_device *dev,
+			 struct drm_mode_create_dumb *args,
+			 struct drm_file *file_priv);
+int drm_mode_destroy_dumb(struct drm_device *dev, u32 handle,
+			  struct drm_file *file_priv);
+
 /* IOCTLs */
 int drm_mode_create_dumb_ioctl(struct drm_device *dev,
 			       void *data, struct drm_file *file_priv);
@@ -166,14 +172,19 @@ int drm_framebuffer_check_src_coords(uint32_t src_x, uint32_t src_y,
 				     const struct drm_framebuffer *fb);
 void drm_fb_release(struct drm_file *file_priv);
 
+int drm_mode_addfb(struct drm_device *dev, struct drm_mode_fb_cmd *or,
+		   struct drm_file *file_priv);
+int drm_mode_rmfb(struct drm_device *dev, u32 fb_id,
+		  struct drm_file *file_priv);
+
 
 /* IOCTL */
-int drm_mode_addfb(struct drm_device *dev,
-		   void *data, struct drm_file *file_priv);
+int drm_mode_addfb_ioctl(struct drm_device *dev,
+			 void *data, struct drm_file *file_priv);
 int drm_mode_addfb2(struct drm_device *dev,
 		    void *data, struct drm_file *file_priv);
-int drm_mode_rmfb(struct drm_device *dev,
-		  void *data, struct drm_file *file_priv);
+int drm_mode_rmfb_ioctl(struct drm_device *dev,
+			void *data, struct drm_file *file_priv);
 int drm_mode_getfb(struct drm_device *dev,
 		   void *data, struct drm_file *file_priv);
 int drm_mode_dirtyfb_ioctl(struct drm_device *dev,
diff --git a/drivers/gpu/drm/drm_dumb_buffers.c b/drivers/gpu/drm/drm_dumb_buffers.c
index 39ac15ce4702..eed9687b8698 100644
--- a/drivers/gpu/drm/drm_dumb_buffers.c
+++ b/drivers/gpu/drm/drm_dumb_buffers.c
@@ -53,10 +53,10 @@
  * a hardware-specific ioctl to allocate suitable buffer objects.
  */
 
-int drm_mode_create_dumb_ioctl(struct drm_device *dev,
-			       void *data, struct drm_file *file_priv)
+int drm_mode_create_dumb(struct drm_device *dev,
+			 struct drm_mode_create_dumb *args,
+			 struct drm_file *file_priv)
 {
-	struct drm_mode_create_dumb *args = data;
 	u32 cpp, stride, size;
 
 	if (!dev->driver->dumb_create)
@@ -91,6 +91,12 @@ int drm_mode_create_dumb_ioctl(struct drm_device *dev,
 	return dev->driver->dumb_create(file_priv, dev, args);
 }
 
+int drm_mode_create_dumb_ioctl(struct drm_device *dev,
+			       void *data, struct drm_file *file_priv)
+{
+	return drm_mode_create_dumb(dev, data, file_priv);
+}
+
 /**
  * drm_mode_mmap_dumb_ioctl - create an mmap offset for a dumb backing storage buffer
  * @dev: DRM device
@@ -122,17 +128,22 @@ int drm_mode_mmap_dumb_ioctl(struct drm_device *dev,
 					       &args->offset);
 }
 
-int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
-				void *data, struct drm_file *file_priv)
+int drm_mode_destroy_dumb(struct drm_device *dev, u32 handle,
+			  struct drm_file *file_priv)
 {
-	struct drm_mode_destroy_dumb *args = data;
-
 	if (!dev->driver->dumb_create)
 		return -ENOSYS;
 
 	if (dev->driver->dumb_destroy)
-		return dev->driver->dumb_destroy(file_priv, dev, args->handle);
+		return dev->driver->dumb_destroy(file_priv, dev, handle);
 	else
-		return drm_gem_dumb_destroy(file_priv, dev, args->handle);
+		return drm_gem_dumb_destroy(file_priv, dev, handle);
 }
 
+int drm_mode_destroy_dumb_ioctl(struct drm_device *dev,
+				void *data, struct drm_file *file_priv)
+{
+	struct drm_mode_destroy_dumb *args = data;
+
+	return drm_mode_destroy_dumb(dev, args->handle, file_priv);
+}
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index 46b11e46edbd..ed90974a452a 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -95,21 +95,20 @@ int drm_framebuffer_check_src_coords(uint32_t src_x, uint32_t src_y,
 /**
  * drm_mode_addfb - add an FB to the graphics configuration
  * @dev: drm device for the ioctl
- * @data: data pointer for the ioctl
- * @file_priv: drm file for the ioctl call
+ * @or: pointer to request structure
+ * @file_priv: drm file
  *
  * Add a new FB to the specified CRTC, given a user request. This is the
  * original addfb ioctl which only supported RGB formats.
  *
- * Called by the user via ioctl.
+ * Called by the user via ioctl, or by an in-kernel client.
  *
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_addfb(struct drm_device *dev,
-		   void *data, struct drm_file *file_priv)
+int drm_mode_addfb(struct drm_device *dev, struct drm_mode_fb_cmd *or,
+		   struct drm_file *file_priv)
 {
-	struct drm_mode_fb_cmd *or = data;
 	struct drm_mode_fb_cmd2 r = {};
 	int ret;
 
@@ -134,6 +133,12 @@ int drm_mode_addfb(struct drm_device *dev,
 	return 0;
 }
 
+int drm_mode_addfb_ioctl(struct drm_device *dev,
+			 void *data, struct drm_file *file_priv)
+{
+	return drm_mode_addfb(dev, data, file_priv);
+}
+
 static int fb_plane_width(int width,
 			  const struct drm_format_info *format, int plane)
 {
@@ -367,29 +372,28 @@ static void drm_mode_rmfb_work_fn(struct work_struct *w)
 
 /**
  * drm_mode_rmfb - remove an FB from the configuration
- * @dev: drm device for the ioctl
- * @data: data pointer for the ioctl
- * @file_priv: drm file for the ioctl call
+ * @dev: drm device
+ * @fb_id: id of framebuffer to remove
+ * @file_priv: drm file
  *
- * Remove the FB specified by the user.
+ * Remove the specified FB.
  *
- * Called by the user via ioctl.
+ * Called by the user via ioctl, or by an in-kernel client.
  *
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_rmfb(struct drm_device *dev,
-		   void *data, struct drm_file *file_priv)
+int drm_mode_rmfb(struct drm_device *dev, u32 fb_id,
+		  struct drm_file *file_priv)
 {
 	struct drm_framebuffer *fb = NULL;
 	struct drm_framebuffer *fbl = NULL;
-	uint32_t *id = data;
 	int found = 0;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET))
 		return -EINVAL;
 
-	fb = drm_framebuffer_lookup(dev, file_priv, *id);
+	fb = drm_framebuffer_lookup(dev, file_priv, fb_id);
 	if (!fb)
 		return -ENOENT;
 
@@ -435,6 +439,14 @@ fail_unref:
 	return -ENOENT;
 }
 
+int drm_mode_rmfb_ioctl(struct drm_device *dev,
+			void *data, struct drm_file *file_priv)
+{
+	uint32_t *fb_id = data;
+
+	return drm_mode_rmfb(dev, *fb_id, file_priv);
+}
+
 /**
  * drm_mode_getfb - get FB info
  * @dev: drm device for the ioctl
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index fe49fb0356b5..3c125041a597 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -644,9 +644,9 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB2, drm_mode_addfb2, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb, DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_RMFB, drm_mode_rmfb_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_PAGE_FLIP, drm_mode_page_flip_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DIRTYFB, drm_mode_dirtyfb_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_CREATE_DUMB, drm_mode_create_dumb_ioctl, DRM_UNLOCKED),
-- 
cgit v1.2.3


From 8d52e447807b350b98ffb4e64bc2fcc1f181c5be Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 23 Jun 2018 11:39:51 +0100
Subject: drm/i915: Defer modeset cleanup to a secondary task

If we avoid cleaning up the old state immediately in
intel_atomic_commit_tail() and defer it to a second task, we can avoid
taking heavily contended locks when the caller is ready to procede.
Subsequent modesets will wait for the cleanup operation (either directly
via the ordered modeset wq or indirectly through the atomic helperr)
which keeps the number of inflight cleanup tasks in check.

As an example, during reset an immediate modeset is performed to disable
the displays before the HW is reset, which must avoid struct_mutex to
avoid recursion. Moving the cleanup to a separate task, defers acquiring
the struct_mutex to after the GPU is running again, allowing it to
complete. Even in a few patches time (optimist!) when we no longer
require struct_mutex to unpin the framebuffers, it will still be good
practice to minimise the number of contention points along reset. The
mutex dependency still exists (as one modeset flushes the other), but in
the short term it resolves the deadlock for simple reset cases.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=101600
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180623103951.23889-1-chris@chris-wilson.co.uk
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/i915/intel_display.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 4db576c3e364..1469a56f6c46 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12555,6 +12555,19 @@ static void intel_atomic_commit_fence_wait(struct intel_atomic_state *intel_stat
 	finish_wait(&dev_priv->gpu_error.wait_queue, &wait_reset);
 }
 
+static void intel_atomic_cleanup_work(struct work_struct *work)
+{
+	struct drm_atomic_state *state =
+		container_of(work, struct drm_atomic_state, commit_work);
+	struct drm_i915_private *i915 = to_i915(state->dev);
+
+	drm_atomic_helper_cleanup_planes(&i915->drm, state);
+	drm_atomic_helper_commit_cleanup_done(state);
+	drm_atomic_state_put(state);
+
+	intel_atomic_helper_free_state(i915);
+}
+
 static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *dev = state->dev;
@@ -12715,13 +12728,16 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 		intel_display_power_put(dev_priv, POWER_DOMAIN_MODESET);
 	}
 
-	drm_atomic_helper_cleanup_planes(dev, state);
-
-	drm_atomic_helper_commit_cleanup_done(state);
-
-	drm_atomic_state_put(state);
-
-	intel_atomic_helper_free_state(dev_priv);
+	/*
+	 * Defer the cleanup of the old state to a separate worker to not
+	 * impede the current task (userspace for blocking modesets) that
+	 * are executed inline. For out-of-line asynchronous modesets/flips,
+	 * deferring to a new worker seems overkill, but we would place a
+	 * schedule point (cond_resched()) here anyway to keep latencies
+	 * down.
+	 */
+	INIT_WORK(&state->commit_work, intel_atomic_cleanup_work);
+	schedule_work(&state->commit_work);
 }
 
 static void intel_atomic_commit_work(struct work_struct *work)
-- 
cgit v1.2.3


From dd12c6ca5b45fd54e80c1424b11a5a25ad913dbb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 25 Jun 2018 11:06:03 +0100
Subject: drm/i915/execlists: Check for ce->state before destroy

As we may cancel the ce->state allocation during context pinning (but
crucially after we mark ce as operational), that means we may be asked
to destroy a nonexistent ce->state. Given the choice in handing a
complex error path on pinning, and just ignoring the lack of state in
destroy, choice the latter for simplicity.

Reported-by: Zhao Yakui <yakui.zhao@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625100604.22598-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 10deebe49543..8f020537a34b 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1338,9 +1338,11 @@ static void execlists_schedule(struct i915_request *request,
 
 static void execlists_context_destroy(struct intel_context *ce)
 {
-	GEM_BUG_ON(!ce->state);
 	GEM_BUG_ON(ce->pin_count);
 
+	if (!ce->state)
+		return;
+
 	intel_ring_free(ce->ring);
 	__i915_gem_object_release_unless_active(ce->state->obj);
 }
-- 
cgit v1.2.3


From efe79d48a7debf57ad156a43a9215f8b0c9210d4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 25 Jun 2018 11:06:04 +0100
Subject: drm/i915: Context objects can never be active when freed

Due to how we only release the pining on the context state on
retirement and never track activity on the context vma itself, the
object can never be active at the point of release. Replace the
conditional transfer of ownership onto an active-reference with an
assert that the object is idle.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625100604.22598-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c        | 4 +++-
 drivers/gpu/drm/i915/intel_ringbuffer.c | 7 +++++--
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 8f020537a34b..46572976c942 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1344,7 +1344,9 @@ static void execlists_context_destroy(struct intel_context *ce)
 		return;
 
 	intel_ring_free(ce->ring);
-	__i915_gem_object_release_unless_active(ce->state->obj);
+
+	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
+	i915_gem_object_put(ce->state->obj);
 }
 
 static void execlists_context_unpin(struct intel_context *ce)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 4dae23885006..d248742b1473 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1167,8 +1167,11 @@ static void intel_ring_context_destroy(struct intel_context *ce)
 {
 	GEM_BUG_ON(ce->pin_count);
 
-	if (ce->state)
-		__i915_gem_object_release_unless_active(ce->state->obj);
+	if (!ce->state)
+		return;
+
+	GEM_BUG_ON(i915_gem_object_is_active(ce->state->obj));
+	i915_gem_object_put(ce->state->obj);
 }
 
 static int __context_pin_ppgtt(struct i915_gem_context *ctx)
-- 
cgit v1.2.3


From e4db5b61c572475bbbcf63e3c8a2606bfccf2c9d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 25 Jun 2018 17:26:02 +0200
Subject: xfrm: policy: remove pcpu policy cache

Kristian Evensen says:
  In a project I am involved in, we are running ipsec (Strongswan) on
  different mt7621-based routers. Each router is configured as an
  initiator and has around ~30 tunnels to different responders (running
  on misc. devices). Before the flow cache was removed (kernel 4.9), we
  got a combined throughput of around 70Mbit/s for all tunnels on one
  router. However, we recently switched to kernel 4.14 (4.14.48), and
  the total throughput is somewhere around 57Mbit/s (best-case). I.e., a
  drop of around 20%. Reverting the flow cache removal restores, as
  expected, performance levels to that of kernel 4.9.

When pcpu xdst exists, it has to be validated first before it can be
used.

A negative hit thus increases cost vs. no-cache.

As number of tunnels increases, hit rate decreases so this pcpu caching
isn't a viable strategy.

Furthermore, the xdst cache also needs to run with BH off, so when
removing this the bh disable/enable pairs can be removed too.

Kristian tested a 4.14.y backport of this change and reported
increased performance:

  In our tests, the throughput reduction has been reduced from around -20%
  to -5%. We also see that the overall throughput is independent of the
  number of tunnels, while before the throughput was reduced as the number
  of tunnels increased.

Reported-by: Kristian Evensen <kristian.evensen@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h     |   1 -
 net/xfrm/xfrm_device.c |  10 ----
 net/xfrm/xfrm_policy.c | 139 +------------------------------------------------
 net/xfrm/xfrm_state.c  |   5 +-
 4 files changed, 3 insertions(+), 152 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 3fa578a6a819..a5378613a49c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -332,7 +332,6 @@ int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int fam
 void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo);
 void km_policy_notify(struct xfrm_policy *xp, int dir,
 		      const struct km_event *c);
-void xfrm_policy_cache_flush(void);
 void km_state_notify(struct xfrm_state *x, const struct km_event *c);
 
 struct xfrm_tmpl;
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 16c1230d20fa..11d56a44e9e8 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -307,12 +307,6 @@ static int xfrm_dev_register(struct net_device *dev)
 	return xfrm_api_check(dev);
 }
 
-static int xfrm_dev_unregister(struct net_device *dev)
-{
-	xfrm_policy_cache_flush();
-	return NOTIFY_DONE;
-}
-
 static int xfrm_dev_feat_change(struct net_device *dev)
 {
 	return xfrm_api_check(dev);
@@ -323,7 +317,6 @@ static int xfrm_dev_down(struct net_device *dev)
 	if (dev->features & NETIF_F_HW_ESP)
 		xfrm_dev_state_flush(dev_net(dev), dev, true);
 
-	xfrm_policy_cache_flush();
 	return NOTIFY_DONE;
 }
 
@@ -335,9 +328,6 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void
 	case NETDEV_REGISTER:
 		return xfrm_dev_register(dev);
 
-	case NETDEV_UNREGISTER:
-		return xfrm_dev_unregister(dev);
-
 	case NETDEV_FEAT_CHANGE:
 		return xfrm_dev_feat_change(dev);
 
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index d960ea6657b5..ef75891450e7 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -45,8 +45,6 @@ struct xfrm_flo {
 	u8 flags;
 };
 
-static DEFINE_PER_CPU(struct xfrm_dst *, xfrm_last_dst);
-static struct work_struct *xfrm_pcpu_work __read_mostly;
 static DEFINE_SPINLOCK(xfrm_if_cb_lock);
 static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly;
 
@@ -1732,108 +1730,6 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 
 }
 
-static void xfrm_last_dst_update(struct xfrm_dst *xdst, struct xfrm_dst *old)
-{
-	this_cpu_write(xfrm_last_dst, xdst);
-	if (old)
-		dst_release(&old->u.dst);
-}
-
-static void __xfrm_pcpu_work_fn(void)
-{
-	struct xfrm_dst *old;
-
-	old = this_cpu_read(xfrm_last_dst);
-	if (old && !xfrm_bundle_ok(old))
-		xfrm_last_dst_update(NULL, old);
-}
-
-static void xfrm_pcpu_work_fn(struct work_struct *work)
-{
-	local_bh_disable();
-	rcu_read_lock();
-	__xfrm_pcpu_work_fn();
-	rcu_read_unlock();
-	local_bh_enable();
-}
-
-void xfrm_policy_cache_flush(void)
-{
-	struct xfrm_dst *old;
-	bool found = false;
-	int cpu;
-
-	might_sleep();
-
-	local_bh_disable();
-	rcu_read_lock();
-	for_each_possible_cpu(cpu) {
-		old = per_cpu(xfrm_last_dst, cpu);
-		if (old && !xfrm_bundle_ok(old)) {
-			if (smp_processor_id() == cpu) {
-				__xfrm_pcpu_work_fn();
-				continue;
-			}
-			found = true;
-			break;
-		}
-	}
-
-	rcu_read_unlock();
-	local_bh_enable();
-
-	if (!found)
-		return;
-
-	get_online_cpus();
-
-	for_each_possible_cpu(cpu) {
-		bool bundle_release;
-
-		rcu_read_lock();
-		old = per_cpu(xfrm_last_dst, cpu);
-		bundle_release = old && !xfrm_bundle_ok(old);
-		rcu_read_unlock();
-
-		if (!bundle_release)
-			continue;
-
-		if (cpu_online(cpu)) {
-			schedule_work_on(cpu, &xfrm_pcpu_work[cpu]);
-			continue;
-		}
-
-		rcu_read_lock();
-		old = per_cpu(xfrm_last_dst, cpu);
-		if (old && !xfrm_bundle_ok(old)) {
-			per_cpu(xfrm_last_dst, cpu) = NULL;
-			dst_release(&old->u.dst);
-		}
-		rcu_read_unlock();
-	}
-
-	put_online_cpus();
-}
-
-static bool xfrm_xdst_can_reuse(struct xfrm_dst *xdst,
-				struct xfrm_state * const xfrm[],
-				int num)
-{
-	const struct dst_entry *dst = &xdst->u.dst;
-	int i;
-
-	if (xdst->num_xfrms != num)
-		return false;
-
-	for (i = 0; i < num; i++) {
-		if (!dst || dst->xfrm != xfrm[i])
-			return false;
-		dst = xfrm_dst_child(dst);
-	}
-
-	return xfrm_bundle_ok(xdst);
-}
-
 static struct xfrm_dst *
 xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 			       const struct flowi *fl, u16 family,
@@ -1842,7 +1738,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 	struct net *net = xp_net(pols[0]);
 	struct xfrm_state *xfrm[XFRM_MAX_DEPTH];
 	struct xfrm_dst *bundle[XFRM_MAX_DEPTH];
-	struct xfrm_dst *xdst, *old;
+	struct xfrm_dst *xdst;
 	struct dst_entry *dst;
 	int err;
 
@@ -1854,22 +1750,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 		return ERR_PTR(err);
 	}
 
-	xdst = this_cpu_read(xfrm_last_dst);
-	if (xdst &&
-	    xdst->u.dst.dev == dst_orig->dev &&
-	    xdst->num_pols == num_pols &&
-	    memcmp(xdst->pols, pols,
-		   sizeof(struct xfrm_policy *) * num_pols) == 0 &&
-	    xfrm_xdst_can_reuse(xdst, xfrm, err)) {
-		dst_hold(&xdst->u.dst);
-		xfrm_pols_put(pols, num_pols);
-		while (err > 0)
-			xfrm_state_put(xfrm[--err]);
-		return xdst;
-	}
-
-	old = xdst;
-
 	dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig);
 	if (IS_ERR(dst)) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR);
@@ -1882,9 +1762,6 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 	memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols);
 	xdst->policy_genid = atomic_read(&pols[0]->genid);
 
-	atomic_set(&xdst->u.dst.__refcnt, 2);
-	xfrm_last_dst_update(xdst, old);
-
 	return xdst;
 }
 
@@ -2085,11 +1962,8 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 	if (num_xfrms <= 0)
 		goto make_dummy_bundle;
 
-	local_bh_disable();
 	xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
 					      xflo->dst_orig);
-	local_bh_enable();
-
 	if (IS_ERR(xdst)) {
 		err = PTR_ERR(xdst);
 		if (err == -EREMOTE) {
@@ -2181,11 +2055,9 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 				goto no_transform;
 			}
 
-			local_bh_disable();
 			xdst = xfrm_resolve_and_create_bundle(
 					pols, num_pols, fl,
 					family, dst_orig);
-			local_bh_enable();
 
 			if (IS_ERR(xdst)) {
 				xfrm_pols_put(pols, num_pols);
@@ -3035,15 +2907,6 @@ static struct pernet_operations __net_initdata xfrm_net_ops = {
 
 void __init xfrm_init(void)
 {
-	int i;
-
-	xfrm_pcpu_work = kmalloc_array(NR_CPUS, sizeof(*xfrm_pcpu_work),
-				       GFP_KERNEL);
-	BUG_ON(!xfrm_pcpu_work);
-
-	for (i = 0; i < NR_CPUS; i++)
-		INIT_WORK(&xfrm_pcpu_work[i], xfrm_pcpu_work_fn);
-
 	register_pernet_subsys(&xfrm_net_ops);
 	xfrm_dev_init();
 	seqcount_init(&xfrm_policy_hash_generation);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 3803b6813fc5..e04a510ec992 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -735,10 +735,9 @@ restart:
 	}
 out:
 	spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-	if (cnt) {
+	if (cnt)
 		err = 0;
-		xfrm_policy_cache_flush();
-	}
+
 	return err;
 }
 EXPORT_SYMBOL(xfrm_state_flush);
-- 
cgit v1.2.3


From 86cd90020688ee8b45268e588a05454cbe979cb7 Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Thu, 21 Jun 2018 16:01:16 -0700
Subject: drm: kirin: Remove useless "Scale not support" error message

The driver doesn't support scaling, but when an atomic test is done
it repeatedly spits out this warning which isn't particularly useful.

So just remove the error message.

Cc: Xinliang Liu <z.liuxinliang@hisilicon.com>
Cc: Rongrong Zou <zourongrong@gmail.com>
Cc: Xinwei Kong <kong.kongxinwei@hisilicon.com>
Cc: Chen Feng <puck.chen@hisilicon.com>
Cc: David Airlie <airlied@linux.ie>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Peter Griffin <peter.griffin@linaro.org>
Cc: dri-devel@lists.freedesktop.org
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1529622076-20386-1-git-send-email-john.stultz@linaro.org
---
 drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
index 2269be91f3e1..bb774202a5a1 100644
--- a/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
+++ b/drivers/gpu/drm/hisilicon/kirin/kirin_drm_ade.c
@@ -859,7 +859,6 @@ static int ade_plane_atomic_check(struct drm_plane *plane,
 		return PTR_ERR(crtc_state);
 
 	if (src_w != crtc_w || src_h != crtc_h) {
-		DRM_ERROR("Scale not support!!!\n");
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 66ddff86f682a635d2beaa1dc90e2a03e83af77e Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@bootlin.com>
Date: Tue, 29 May 2018 11:49:14 +0200
Subject: dt-bindings: panel: Add the Ilitek ILI9881c panel documentation

The LHR050H41 from BananaPi is a 1280x700 4-lanes DSI panel based on the
ILI9881c from Ilitek.

Acked-by: Rob Herring <robh@kernel.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/a348cdd07d3287e8203ee8d840ea279fe10a6204.1527587352.git-series.maxime.ripard@bootlin.com
---
 .../bindings/display/panel/ilitek,ili9881c.txt       | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.txt

diff --git a/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.txt b/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.txt
new file mode 100644
index 000000000000..4a041acb4e18
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/ilitek,ili9881c.txt
@@ -0,0 +1,20 @@
+Ilitek ILI9881c based MIPI-DSI panels
+
+Required properties:
+  - compatible: must be "ilitek,ili9881c" and one of:
+    * "bananapi,lhr050h41"
+  - reg: DSI virtual channel used by that screen
+  - power-supply: phandle to the power regulator
+  - reset-gpios: a GPIO phandle for the reset pin
+
+Optional properties:
+  - backlight: phandle to the backlight used
+
+Example:
+panel@0 {
+	compatible = "bananapi,lhr050h41", "ilitek,ili9881c";
+	reg = <0>;
+	power-supply = <&reg_display>;
+	reset-gpios = <&r_pio 0 5 GPIO_ACTIVE_LOW>; /* PL05 */
+	backlight = <&pwm_bl>;
+};
-- 
cgit v1.2.3


From 26aec25593c2ee2e24f9facabcf85abba54bdb37 Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@bootlin.com>
Date: Tue, 29 May 2018 11:49:15 +0200
Subject: drm/panel: Add Ilitek ILI9881c panel driver

The LHR050H41 panel is the panel shipped with the BananaPi M2-Magic, and is
based on the Ilitek ILI9881c Controller. Add a driver for it, modelled
after the other Ilitek controller drivers.

Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/acb5453112ab7c7b801cf4f1669e351b391e77e8.1527587352.git-series.maxime.ripard@bootlin.com
---
 drivers/gpu/drm/panel/Kconfig                 |   9 +
 drivers/gpu/drm/panel/Makefile                |   1 +
 drivers/gpu/drm/panel/panel-ilitek-ili9881c.c | 503 ++++++++++++++++++++++++++
 3 files changed, 513 insertions(+)
 create mode 100644 drivers/gpu/drm/panel/panel-ilitek-ili9881c.c

diff --git a/drivers/gpu/drm/panel/Kconfig b/drivers/gpu/drm/panel/Kconfig
index 25682ff3449a..6020c30a33b3 100644
--- a/drivers/gpu/drm/panel/Kconfig
+++ b/drivers/gpu/drm/panel/Kconfig
@@ -46,6 +46,15 @@ config DRM_PANEL_ILITEK_IL9322
 	  Say Y here if you want to enable support for Ilitek IL9322
 	  QVGA (320x240) RGB, YUV and ITU-T BT.656 panels.
 
+config DRM_PANEL_ILITEK_ILI9881C
+	tristate "Ilitek ILI9881C-based panels"
+	depends on OF
+	depends on DRM_MIPI_DSI
+	depends on BACKLIGHT_CLASS_DEVICE
+	help
+	  Say Y if you want to enable support for panels based on the
+	  Ilitek ILI9881c controller.
+
 config DRM_PANEL_INNOLUX_P079ZCA
 	tristate "Innolux P079ZCA panel"
 	depends on OF
diff --git a/drivers/gpu/drm/panel/Makefile b/drivers/gpu/drm/panel/Makefile
index f26efc11d746..5ccaaa9d13af 100644
--- a/drivers/gpu/drm/panel/Makefile
+++ b/drivers/gpu/drm/panel/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_DRM_PANEL_ARM_VERSATILE) += panel-arm-versatile.o
 obj-$(CONFIG_DRM_PANEL_LVDS) += panel-lvds.o
 obj-$(CONFIG_DRM_PANEL_SIMPLE) += panel-simple.o
 obj-$(CONFIG_DRM_PANEL_ILITEK_IL9322) += panel-ilitek-ili9322.o
+obj-$(CONFIG_DRM_PANEL_ILITEK_ILI9881C) += panel-ilitek-ili9881c.o
 obj-$(CONFIG_DRM_PANEL_INNOLUX_P079ZCA) += panel-innolux-p079zca.o
 obj-$(CONFIG_DRM_PANEL_JDI_LT070ME05000) += panel-jdi-lt070me05000.o
 obj-$(CONFIG_DRM_PANEL_LG_LG4573) += panel-lg-lg4573.o
diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
new file mode 100644
index 000000000000..e848af235df5
--- /dev/null
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -0,0 +1,503 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017-2018, Bootlin
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/fb.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+
+#include <drm/drm_mipi_dsi.h>
+#include <drm/drm_modes.h>
+#include <drm/drm_panel.h>
+
+#include <video/mipi_display.h>
+
+struct ili9881c {
+	struct drm_panel	panel;
+	struct mipi_dsi_device	*dsi;
+
+	struct backlight_device *backlight;
+	struct regulator	*power;
+	struct gpio_desc	*reset;
+};
+
+enum ili9881c_op {
+	ILI9881C_SWITCH_PAGE,
+	ILI9881C_COMMAND,
+};
+
+struct ili9881c_instr {
+	enum ili9881c_op	op;
+
+	union arg {
+		struct cmd {
+			u8	cmd;
+			u8	data;
+		} cmd;
+		u8	page;
+	} arg;
+};
+
+#define ILI9881C_SWITCH_PAGE_INSTR(_page)	\
+	{					\
+		.op = ILI9881C_SWITCH_PAGE,	\
+		.arg = {			\
+			.page = (_page),	\
+		},				\
+	}
+
+#define ILI9881C_COMMAND_INSTR(_cmd, _data)		\
+	{						\
+		.op = ILI9881C_COMMAND,		\
+		.arg = {				\
+			.cmd = {			\
+				.cmd = (_cmd),		\
+				.data = (_data),	\
+			},				\
+		},					\
+	}
+
+static const struct ili9881c_instr ili9881c_init[] = {
+	ILI9881C_SWITCH_PAGE_INSTR(3),
+	ILI9881C_COMMAND_INSTR(0x01, 0x00),
+	ILI9881C_COMMAND_INSTR(0x02, 0x00),
+	ILI9881C_COMMAND_INSTR(0x03, 0x73),
+	ILI9881C_COMMAND_INSTR(0x04, 0x03),
+	ILI9881C_COMMAND_INSTR(0x05, 0x00),
+	ILI9881C_COMMAND_INSTR(0x06, 0x06),
+	ILI9881C_COMMAND_INSTR(0x07, 0x06),
+	ILI9881C_COMMAND_INSTR(0x08, 0x00),
+	ILI9881C_COMMAND_INSTR(0x09, 0x18),
+	ILI9881C_COMMAND_INSTR(0x0a, 0x04),
+	ILI9881C_COMMAND_INSTR(0x0b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0c, 0x02),
+	ILI9881C_COMMAND_INSTR(0x0d, 0x03),
+	ILI9881C_COMMAND_INSTR(0x0e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x0f, 0x25),
+	ILI9881C_COMMAND_INSTR(0x10, 0x25),
+	ILI9881C_COMMAND_INSTR(0x11, 0x00),
+	ILI9881C_COMMAND_INSTR(0x12, 0x00),
+	ILI9881C_COMMAND_INSTR(0x13, 0x00),
+	ILI9881C_COMMAND_INSTR(0x14, 0x00),
+	ILI9881C_COMMAND_INSTR(0x15, 0x00),
+	ILI9881C_COMMAND_INSTR(0x16, 0x0C),
+	ILI9881C_COMMAND_INSTR(0x17, 0x00),
+	ILI9881C_COMMAND_INSTR(0x18, 0x00),
+	ILI9881C_COMMAND_INSTR(0x19, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x1e, 0xC0),
+	ILI9881C_COMMAND_INSTR(0x1f, 0x80),
+	ILI9881C_COMMAND_INSTR(0x20, 0x04),
+	ILI9881C_COMMAND_INSTR(0x21, 0x01),
+	ILI9881C_COMMAND_INSTR(0x22, 0x00),
+	ILI9881C_COMMAND_INSTR(0x23, 0x00),
+	ILI9881C_COMMAND_INSTR(0x24, 0x00),
+	ILI9881C_COMMAND_INSTR(0x25, 0x00),
+	ILI9881C_COMMAND_INSTR(0x26, 0x00),
+	ILI9881C_COMMAND_INSTR(0x27, 0x00),
+	ILI9881C_COMMAND_INSTR(0x28, 0x33),
+	ILI9881C_COMMAND_INSTR(0x29, 0x03),
+	ILI9881C_COMMAND_INSTR(0x2a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x2f, 0x00),
+	ILI9881C_COMMAND_INSTR(0x30, 0x00),
+	ILI9881C_COMMAND_INSTR(0x31, 0x00),
+	ILI9881C_COMMAND_INSTR(0x32, 0x00),
+	ILI9881C_COMMAND_INSTR(0x33, 0x00),
+	ILI9881C_COMMAND_INSTR(0x34, 0x04),
+	ILI9881C_COMMAND_INSTR(0x35, 0x00),
+	ILI9881C_COMMAND_INSTR(0x36, 0x00),
+	ILI9881C_COMMAND_INSTR(0x37, 0x00),
+	ILI9881C_COMMAND_INSTR(0x38, 0x3C),
+	ILI9881C_COMMAND_INSTR(0x39, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3a, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3b, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3c, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3d, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3e, 0x00),
+	ILI9881C_COMMAND_INSTR(0x3f, 0x00),
+	ILI9881C_COMMAND_INSTR(0x40, 0x00),
+	ILI9881C_COMMAND_INSTR(0x41, 0x00),
+	ILI9881C_COMMAND_INSTR(0x42, 0x00),
+	ILI9881C_COMMAND_INSTR(0x43, 0x00),
+	ILI9881C_COMMAND_INSTR(0x44, 0x00),
+	ILI9881C_COMMAND_INSTR(0x50, 0x01),
+	ILI9881C_COMMAND_INSTR(0x51, 0x23),
+	ILI9881C_COMMAND_INSTR(0x52, 0x45),
+	ILI9881C_COMMAND_INSTR(0x53, 0x67),
+	ILI9881C_COMMAND_INSTR(0x54, 0x89),
+	ILI9881C_COMMAND_INSTR(0x55, 0xab),
+	ILI9881C_COMMAND_INSTR(0x56, 0x01),
+	ILI9881C_COMMAND_INSTR(0x57, 0x23),
+	ILI9881C_COMMAND_INSTR(0x58, 0x45),
+	ILI9881C_COMMAND_INSTR(0x59, 0x67),
+	ILI9881C_COMMAND_INSTR(0x5a, 0x89),
+	ILI9881C_COMMAND_INSTR(0x5b, 0xab),
+	ILI9881C_COMMAND_INSTR(0x5c, 0xcd),
+	ILI9881C_COMMAND_INSTR(0x5d, 0xef),
+	ILI9881C_COMMAND_INSTR(0x5e, 0x11),
+	ILI9881C_COMMAND_INSTR(0x5f, 0x02),
+	ILI9881C_COMMAND_INSTR(0x60, 0x02),
+	ILI9881C_COMMAND_INSTR(0x61, 0x02),
+	ILI9881C_COMMAND_INSTR(0x62, 0x02),
+	ILI9881C_COMMAND_INSTR(0x63, 0x02),
+	ILI9881C_COMMAND_INSTR(0x64, 0x02),
+	ILI9881C_COMMAND_INSTR(0x65, 0x02),
+	ILI9881C_COMMAND_INSTR(0x66, 0x02),
+	ILI9881C_COMMAND_INSTR(0x67, 0x02),
+	ILI9881C_COMMAND_INSTR(0x68, 0x02),
+	ILI9881C_COMMAND_INSTR(0x69, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6a, 0x0C),
+	ILI9881C_COMMAND_INSTR(0x6b, 0x02),
+	ILI9881C_COMMAND_INSTR(0x6c, 0x0F),
+	ILI9881C_COMMAND_INSTR(0x6d, 0x0E),
+	ILI9881C_COMMAND_INSTR(0x6e, 0x0D),
+	ILI9881C_COMMAND_INSTR(0x6f, 0x06),
+	ILI9881C_COMMAND_INSTR(0x70, 0x07),
+	ILI9881C_COMMAND_INSTR(0x71, 0x02),
+	ILI9881C_COMMAND_INSTR(0x72, 0x02),
+	ILI9881C_COMMAND_INSTR(0x73, 0x02),
+	ILI9881C_COMMAND_INSTR(0x74, 0x02),
+	ILI9881C_COMMAND_INSTR(0x75, 0x02),
+	ILI9881C_COMMAND_INSTR(0x76, 0x02),
+	ILI9881C_COMMAND_INSTR(0x77, 0x02),
+	ILI9881C_COMMAND_INSTR(0x78, 0x02),
+	ILI9881C_COMMAND_INSTR(0x79, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7a, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7b, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7c, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7d, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7e, 0x02),
+	ILI9881C_COMMAND_INSTR(0x7f, 0x02),
+	ILI9881C_COMMAND_INSTR(0x80, 0x0C),
+	ILI9881C_COMMAND_INSTR(0x81, 0x02),
+	ILI9881C_COMMAND_INSTR(0x82, 0x0F),
+	ILI9881C_COMMAND_INSTR(0x83, 0x0E),
+	ILI9881C_COMMAND_INSTR(0x84, 0x0D),
+	ILI9881C_COMMAND_INSTR(0x85, 0x06),
+	ILI9881C_COMMAND_INSTR(0x86, 0x07),
+	ILI9881C_COMMAND_INSTR(0x87, 0x02),
+	ILI9881C_COMMAND_INSTR(0x88, 0x02),
+	ILI9881C_COMMAND_INSTR(0x89, 0x02),
+	ILI9881C_COMMAND_INSTR(0x8A, 0x02),
+	ILI9881C_SWITCH_PAGE_INSTR(4),
+	ILI9881C_COMMAND_INSTR(0x6C, 0x15),
+	ILI9881C_COMMAND_INSTR(0x6E, 0x22),
+	ILI9881C_COMMAND_INSTR(0x6F, 0x33),
+	ILI9881C_COMMAND_INSTR(0x3A, 0xA4),
+	ILI9881C_COMMAND_INSTR(0x8D, 0x0D),
+	ILI9881C_COMMAND_INSTR(0x87, 0xBA),
+	ILI9881C_COMMAND_INSTR(0x26, 0x76),
+	ILI9881C_COMMAND_INSTR(0xB2, 0xD1),
+	ILI9881C_SWITCH_PAGE_INSTR(1),
+	ILI9881C_COMMAND_INSTR(0x22, 0x0A),
+	ILI9881C_COMMAND_INSTR(0x53, 0xDC),
+	ILI9881C_COMMAND_INSTR(0x55, 0xA7),
+	ILI9881C_COMMAND_INSTR(0x50, 0x78),
+	ILI9881C_COMMAND_INSTR(0x51, 0x78),
+	ILI9881C_COMMAND_INSTR(0x31, 0x02),
+	ILI9881C_COMMAND_INSTR(0x60, 0x14),
+	ILI9881C_COMMAND_INSTR(0xA0, 0x2A),
+	ILI9881C_COMMAND_INSTR(0xA1, 0x39),
+	ILI9881C_COMMAND_INSTR(0xA2, 0x46),
+	ILI9881C_COMMAND_INSTR(0xA3, 0x0e),
+	ILI9881C_COMMAND_INSTR(0xA4, 0x12),
+	ILI9881C_COMMAND_INSTR(0xA5, 0x25),
+	ILI9881C_COMMAND_INSTR(0xA6, 0x19),
+	ILI9881C_COMMAND_INSTR(0xA7, 0x1d),
+	ILI9881C_COMMAND_INSTR(0xA8, 0xa6),
+	ILI9881C_COMMAND_INSTR(0xA9, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xAA, 0x29),
+	ILI9881C_COMMAND_INSTR(0xAB, 0x85),
+	ILI9881C_COMMAND_INSTR(0xAC, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xAD, 0x1B),
+	ILI9881C_COMMAND_INSTR(0xAE, 0x51),
+	ILI9881C_COMMAND_INSTR(0xAF, 0x22),
+	ILI9881C_COMMAND_INSTR(0xB0, 0x2d),
+	ILI9881C_COMMAND_INSTR(0xB1, 0x4f),
+	ILI9881C_COMMAND_INSTR(0xB2, 0x59),
+	ILI9881C_COMMAND_INSTR(0xB3, 0x3F),
+	ILI9881C_COMMAND_INSTR(0xC0, 0x2A),
+	ILI9881C_COMMAND_INSTR(0xC1, 0x3a),
+	ILI9881C_COMMAND_INSTR(0xC2, 0x45),
+	ILI9881C_COMMAND_INSTR(0xC3, 0x0e),
+	ILI9881C_COMMAND_INSTR(0xC4, 0x11),
+	ILI9881C_COMMAND_INSTR(0xC5, 0x24),
+	ILI9881C_COMMAND_INSTR(0xC6, 0x1a),
+	ILI9881C_COMMAND_INSTR(0xC7, 0x1c),
+	ILI9881C_COMMAND_INSTR(0xC8, 0xaa),
+	ILI9881C_COMMAND_INSTR(0xC9, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xCA, 0x29),
+	ILI9881C_COMMAND_INSTR(0xCB, 0x96),
+	ILI9881C_COMMAND_INSTR(0xCC, 0x1C),
+	ILI9881C_COMMAND_INSTR(0xCD, 0x1B),
+	ILI9881C_COMMAND_INSTR(0xCE, 0x51),
+	ILI9881C_COMMAND_INSTR(0xCF, 0x22),
+	ILI9881C_COMMAND_INSTR(0xD0, 0x2b),
+	ILI9881C_COMMAND_INSTR(0xD1, 0x4b),
+	ILI9881C_COMMAND_INSTR(0xD2, 0x59),
+	ILI9881C_COMMAND_INSTR(0xD3, 0x3F),
+};
+
+static inline struct ili9881c *panel_to_ili9881c(struct drm_panel *panel)
+{
+	return container_of(panel, struct ili9881c, panel);
+}
+
+/*
+ * The panel seems to accept some private DCS commands that map
+ * directly to registers.
+ *
+ * It is organised by page, with each page having its own set of
+ * registers, and the first page looks like it's holding the standard
+ * DCS commands.
+ *
+ * So before any attempt at sending a command or data, we have to be
+ * sure if we're in the right page or not.
+ */
+static int ili9881c_switch_page(struct ili9881c *ctx, u8 page)
+{
+	u8 buf[4] = { 0xff, 0x98, 0x81, page };
+	int ret;
+
+	ret = mipi_dsi_dcs_write_buffer(ctx->dsi, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int ili9881c_send_cmd_data(struct ili9881c *ctx, u8 cmd, u8 data)
+{
+	u8 buf[2] = { cmd, data };
+	int ret;
+
+	ret = mipi_dsi_dcs_write_buffer(ctx->dsi, buf, sizeof(buf));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int ili9881c_prepare(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+	unsigned int i;
+	int ret;
+
+	/* Power the panel */
+	ret = regulator_enable(ctx->power);
+	if (ret)
+		return ret;
+	msleep(5);
+
+	/* And reset it */
+	gpiod_set_value(ctx->reset, 1);
+	msleep(20);
+
+	gpiod_set_value(ctx->reset, 0);
+	msleep(20);
+
+	for (i = 0; i < ARRAY_SIZE(ili9881c_init); i++) {
+		const struct ili9881c_instr *instr = &ili9881c_init[i];
+
+		if (instr->op == ILI9881C_SWITCH_PAGE)
+			ret = ili9881c_switch_page(ctx, instr->arg.page);
+		else if (instr->op == ILI9881C_COMMAND)
+			ret = ili9881c_send_cmd_data(ctx, instr->arg.cmd.cmd,
+						      instr->arg.cmd.data);
+
+		if (ret)
+			return ret;
+	}
+
+	ret = ili9881c_switch_page(ctx, 0);
+	if (ret)
+		return ret;
+
+	ret = mipi_dsi_dcs_set_tear_on(ctx->dsi, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
+	if (ret)
+		return ret;
+
+	mipi_dsi_dcs_exit_sleep_mode(ctx->dsi);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int ili9881c_enable(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+
+	msleep(120);
+
+	mipi_dsi_dcs_set_display_on(ctx->dsi);
+	backlight_enable(ctx->backlight);
+
+	return 0;
+}
+
+static int ili9881c_disable(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+
+	backlight_disable(ctx->backlight);
+	return mipi_dsi_dcs_set_display_off(ctx->dsi);
+}
+
+static int ili9881c_unprepare(struct drm_panel *panel)
+{
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+
+	mipi_dsi_dcs_enter_sleep_mode(ctx->dsi);
+	regulator_disable(ctx->power);
+	gpiod_set_value(ctx->reset, 1);
+
+	return 0;
+}
+
+static const struct drm_display_mode bananapi_default_mode = {
+	.clock		= 62000,
+	.vrefresh	= 60,
+
+	.hdisplay	= 720,
+	.hsync_start	= 720 + 10,
+	.hsync_end	= 720 + 10 + 20,
+	.htotal		= 720 + 10 + 20 + 30,
+
+	.vdisplay	= 1280,
+	.vsync_start	= 1280 + 10,
+	.vsync_end	= 1280 + 10 + 10,
+	.vtotal		= 1280 + 10 + 10 + 20,
+};
+
+static int ili9881c_get_modes(struct drm_panel *panel)
+{
+	struct drm_connector *connector = panel->connector;
+	struct ili9881c *ctx = panel_to_ili9881c(panel);
+	struct drm_display_mode *mode;
+
+	mode = drm_mode_duplicate(panel->drm, &bananapi_default_mode);
+	if (!mode) {
+		dev_err(&ctx->dsi->dev, "failed to add mode %ux%ux@%u\n",
+			bananapi_default_mode.hdisplay,
+			bananapi_default_mode.vdisplay,
+			bananapi_default_mode.vrefresh);
+		return -ENOMEM;
+	}
+
+	drm_mode_set_name(mode);
+
+	mode->type = DRM_MODE_TYPE_DRIVER | DRM_MODE_TYPE_PREFERRED;
+	drm_mode_probed_add(connector, mode);
+
+	panel->connector->display_info.width_mm = 62;
+	panel->connector->display_info.height_mm = 110;
+
+	return 1;
+}
+
+static const struct drm_panel_funcs ili9881c_funcs = {
+	.prepare	= ili9881c_prepare,
+	.unprepare	= ili9881c_unprepare,
+	.enable		= ili9881c_enable,
+	.disable	= ili9881c_disable,
+	.get_modes	= ili9881c_get_modes,
+};
+
+static int ili9881c_dsi_probe(struct mipi_dsi_device *dsi)
+{
+	struct device_node *np;
+	struct ili9881c *ctx;
+	int ret;
+
+	ctx = devm_kzalloc(&dsi->dev, sizeof(*ctx), GFP_KERNEL);
+	if (!ctx)
+		return -ENOMEM;
+	mipi_dsi_set_drvdata(dsi, ctx);
+	ctx->dsi = dsi;
+
+	drm_panel_init(&ctx->panel);
+	ctx->panel.dev = &dsi->dev;
+	ctx->panel.funcs = &ili9881c_funcs;
+
+	ctx->power = devm_regulator_get(&dsi->dev, "power");
+	if (IS_ERR(ctx->power)) {
+		dev_err(&dsi->dev, "Couldn't get our power regulator\n");
+		return PTR_ERR(ctx->power);
+	}
+
+	ctx->reset = devm_gpiod_get(&dsi->dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(ctx->reset)) {
+		dev_err(&dsi->dev, "Couldn't get our reset GPIO\n");
+		return PTR_ERR(ctx->reset);
+	}
+
+	np = of_parse_phandle(dsi->dev.of_node, "backlight", 0);
+	if (np) {
+		ctx->backlight = of_find_backlight_by_node(np);
+		of_node_put(np);
+
+		if (!ctx->backlight)
+			return -EPROBE_DEFER;
+	}
+
+	ret = drm_panel_add(&ctx->panel);
+	if (ret < 0)
+		return ret;
+
+	dsi->mode_flags = MIPI_DSI_MODE_VIDEO_SYNC_PULSE;
+	dsi->format = MIPI_DSI_FMT_RGB888;
+	dsi->lanes = 4;
+
+	return mipi_dsi_attach(dsi);
+}
+
+static int ili9881c_dsi_remove(struct mipi_dsi_device *dsi)
+{
+	struct ili9881c *ctx = mipi_dsi_get_drvdata(dsi);
+
+	mipi_dsi_detach(dsi);
+	drm_panel_remove(&ctx->panel);
+
+	if (ctx->backlight)
+		put_device(&ctx->backlight->dev);
+
+	return 0;
+}
+
+static const struct of_device_id ili9881c_of_match[] = {
+	{ .compatible = "bananapi,lhr050h41" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ili9881c_of_match);
+
+static struct mipi_dsi_driver ili9881c_dsi_driver = {
+	.probe		= ili9881c_dsi_probe,
+	.remove		= ili9881c_dsi_remove,
+	.driver = {
+		.name		= "ili9881c-dsi",
+		.of_match_table	= ili9881c_of_match,
+	},
+};
+module_mipi_dsi_driver(ili9881c_dsi_driver);
+
+MODULE_AUTHOR("Maxime Ripard <maxime.ripard@free-electrons.com>");
+MODULE_DESCRIPTION("Ilitek ILI9881C Controller Driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 5257514d8885b2ebc11bf359ea1527282b47a5fd Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 24 Apr 2018 11:03:39 -0700
Subject: rcu: Make expedited grace period use direct call on last leaf

During expedited grace-period initialization, a work item is scheduled
for each leaf rcu_node structure.  However, that initialization code
is itself (normally) executing from a workqueue, so one of the leaf
rcu_node structures could just as well be handled by that pre-existing
workqueue, and with less overhead.  This commit therefore uses a
shiny new rcu_is_leaf_node() macro to execute the last leaf rcu_node
structure's initialization directly from the pre-existing workqueue.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h      | 3 +++
 kernel/rcu/tree_exp.h | 5 +++--
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 40cea6735c2d..db0870acfdff 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -276,6 +276,9 @@ static inline void rcu_init_levelspread(int *levelspread, const int *levelcnt)
 /* Is this rcu_node a leaf? */
 #define rcu_is_leaf_node(rnp) ((rnp)->level == rcu_num_lvls - 1)
 
+/* Is this rcu_node the last leaf? */
+#define rcu_is_last_leaf_node(rsp, rnp) ((rnp) == &(rsp)->node[rcu_num_nodes - 1])
+
 /*
  * Do a full breadth-first scan of the rcu_node structures for the
  * specified rcu_state structure.
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index d40708e8c5d6..c6385ee1af65 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -486,8 +486,9 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 		rnp->rew.rew_func = func;
 		rnp->rew.rew_rsp = rsp;
 		if (!READ_ONCE(rcu_par_gp_wq) ||
-		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING) {
-			/* No workqueues yet. */
+		    rcu_scheduler_active != RCU_SCHEDULER_RUNNING ||
+		    rcu_is_last_leaf_node(rsp, rnp)) {
+			/* No workqueues yet or last leaf, do direct call. */
 			sync_rcu_exp_select_node_cpus(&rnp->rew.rew_work);
 			continue;
 		}
-- 
cgit v1.2.3


From 5ef98a6328a1506f544a64b28d6a8a7b99af475b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 24 Apr 2018 21:30:13 -0700
Subject: srcu: Fix typos in __call_srcu() header comment

This commit simply changes some copy-pasta call_rcu() instances to
the correct call_srcu().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/srcutree.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index b4123d7a2cec..615e414b0c1e 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -823,17 +823,17 @@ static void srcu_leak_callback(struct rcu_head *rhp)
  * more than one CPU, this means that when "func()" is invoked, each CPU
  * is guaranteed to have executed a full memory barrier since the end of
  * its last corresponding SRCU read-side critical section whose beginning
- * preceded the call to call_rcu().  It also means that each CPU executing
+ * preceded the call to call_srcu().  It also means that each CPU executing
  * an SRCU read-side critical section that continues beyond the start of
- * "func()" must have executed a memory barrier after the call_rcu()
+ * "func()" must have executed a memory barrier after the call_srcu()
  * but before the beginning of that SRCU read-side critical section.
  * Note that these guarantees include CPUs that are offline, idle, or
  * executing in user mode, as well as CPUs that are executing in the kernel.
  *
- * Furthermore, if CPU A invoked call_rcu() and CPU B invoked the
+ * Furthermore, if CPU A invoked call_srcu() and CPU B invoked the
  * resulting SRCU callback function "func()", then both CPU A and CPU
  * B are guaranteed to execute a full memory barrier during the time
- * interval between the call to call_rcu() and the invocation of "func()".
+ * interval between the call to call_srcu() and the invocation of "func()".
  * This guarantee applies even if CPU A and CPU B are the same CPU (but
  * again only if the system has more than one CPU).
  *
-- 
cgit v1.2.3


From 17294ce6a41d3fee6a9bfc52387c107a4607c1c9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 25 Apr 2018 12:03:36 -0700
Subject: srcu: Document that srcu_funnel_gp_start() implies
 srcu_funnel_exp_start()

This commit updates the header comment of srcu_funnel_gp_start() to
document the fact that srcu_funnel_gp_start() does the work of
srcu_funnel_exp_start(), in some cases by invoking it directly.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/srcutree.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 615e414b0c1e..37bef2fe80e6 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -641,6 +641,9 @@ static void srcu_funnel_exp_start(struct srcu_struct *sp, struct srcu_node *snp,
  * period s.  Losers must either ensure that their desired grace-period
  * number is recorded on at least their leaf srcu_node structure, or they
  * must take steps to invoke their own callbacks.
+ *
+ * Note that this function also does the work of srcu_funnel_exp_start(),
+ * in some cases by directly invoking it.
  */
 static void srcu_funnel_gp_start(struct srcu_struct *sp, struct srcu_data *sdp,
 				 unsigned long s, bool do_norm)
-- 
cgit v1.2.3


From 5ab07a8df4d6c958ca63640d3f2ef896f0679c05 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 22 May 2018 12:28:04 -0700
Subject: srcu: Add address of first callback to rcutorture output

This commit adds the address of the first callback to the per-CPU rcutorture
output in order to allow lost wakeups to be more efficiently tracked down.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/srcutree.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 37bef2fe80e6..5a1a9a07b407 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1271,11 +1271,11 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
 		unsigned long l0, l1;
 		unsigned long u0, u1;
 		long c0, c1;
-		struct srcu_data *counts;
+		struct srcu_data *sdp;
 
-		counts = per_cpu_ptr(sp->sda, cpu);
-		u0 = counts->srcu_unlock_count[!idx];
-		u1 = counts->srcu_unlock_count[idx];
+		sdp = per_cpu_ptr(sp->sda, cpu);
+		u0 = sdp->srcu_unlock_count[!idx];
+		u1 = sdp->srcu_unlock_count[idx];
 
 		/*
 		 * Make sure that a lock is always counted if the corresponding
@@ -1283,12 +1283,13 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
 		 */
 		smp_rmb();
 
-		l0 = counts->srcu_lock_count[!idx];
-		l1 = counts->srcu_lock_count[idx];
+		l0 = sdp->srcu_lock_count[!idx];
+		l1 = sdp->srcu_lock_count[idx];
 
 		c0 = l0 - u0;
 		c1 = l1 - u1;
-		pr_cont(" %d(%ld,%ld)", cpu, c0, c1);
+		pr_cont(" %d(%ld,%ld %1p)",
+			cpu, c0, c1, rcu_segcblist_head(&sdp->srcu_cblist));
 		s0 += c0;
 		s1 += c1;
 	}
-- 
cgit v1.2.3


From fd55a281adf6c9b9723d369203fdd92e5ea62a09 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 10:06:03 -0700
Subject: srcu: Introduce srcu_read_{un,}lock_notrace()

Joel Fernandes is using SRCU to protect from-idle tracepoints, which
requires notrace variants of srcu_read_lock() and srcu_read_unlock()
in order to avoid problems with tracepoints in lockdep.  This commit
therefore adds srcu_read_lock_notrace() and srcu_read_unlock_notrace().

[1] http://lkml.kernel.org/r/20180427042656.190746-1-joelaf@google.com

Reported-by: Joel Fernandes <joelaf@google.com>
Intermittently-reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/srcu.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 91494d7e8e41..3e72a291c401 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -195,6 +195,16 @@ static inline int srcu_read_lock(struct srcu_struct *sp) __acquires(sp)
 	return retval;
 }
 
+/* Used by tracing, cannot be traced and cannot invoke lockdep. */
+static inline notrace int
+srcu_read_lock_notrace(struct srcu_struct *sp) __acquires(sp)
+{
+	int retval;
+
+	retval = __srcu_read_lock(sp);
+	return retval;
+}
+
 /**
  * srcu_read_unlock - unregister a old reader from an SRCU-protected structure.
  * @sp: srcu_struct in which to unregister the old reader.
@@ -209,6 +219,13 @@ static inline void srcu_read_unlock(struct srcu_struct *sp, int idx)
 	__srcu_read_unlock(sp, idx);
 }
 
+/* Used by tracing, cannot be traced and cannot call lockdep. */
+static inline notrace void
+srcu_read_unlock_notrace(struct srcu_struct *sp, int idx) __releases(sp)
+{
+	__srcu_read_unlock(sp, idx);
+}
+
 /**
  * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock
  *
-- 
cgit v1.2.3


From 5bfd7d34fe0905421b42f0091ee9c59d83deef9c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 23 Apr 2018 14:03:00 -0700
Subject: torture: Use a single build directory for torture scenarios

The torture scripting currently builds each kernel from a set of parallel
runs in its own build directory.  This can waste quite a bit of space when
running large numbers of concurrent scenarios, and pointlessly given that
the builds are run sequentially (albeit with a largish -j number passed to
"make").  This commit therefore places all build-command output in the
results directory, then does all builds in a single "b1" build directory.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 .../testing/selftests/rcutorture/bin/configinit.sh | 26 ++++++++++------------
 .../testing/selftests/rcutorture/bin/kvm-build.sh  | 11 ++++-----
 .../selftests/rcutorture/bin/kvm-test-1-run.sh     |  5 +++--
 tools/testing/selftests/rcutorture/bin/kvm.sh      |  2 +-
 4 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/rcutorture/bin/configinit.sh b/tools/testing/selftests/rcutorture/bin/configinit.sh
index c15f270e121d..65541c21a544 100755
--- a/tools/testing/selftests/rcutorture/bin/configinit.sh
+++ b/tools/testing/selftests/rcutorture/bin/configinit.sh
@@ -1,6 +1,6 @@
 #!/bin/bash
 #
-# Usage: configinit.sh config-spec-file [ build output dir ]
+# Usage: configinit.sh config-spec-file build-output-dir results-dir
 #
 # Create a .config file from the spec file.  Run from the kernel source tree.
 # Exits with 0 if all went well, with 1 if all went well but the config
@@ -40,20 +40,18 @@ mkdir $T
 
 c=$1
 buildloc=$2
+resdir=$3
 builddir=
-if test -n $buildloc
+if echo $buildloc | grep -q '^O='
 then
-	if echo $buildloc | grep -q '^O='
+	builddir=`echo $buildloc | sed -e 's/^O=//'`
+	if test ! -d $builddir
 	then
-		builddir=`echo $buildloc | sed -e 's/^O=//'`
-		if test ! -d $builddir
-		then
-			mkdir $builddir
-		fi
-	else
-		echo Bad build directory: \"$buildloc\"
-		exit 2
+		mkdir $builddir
 	fi
+else
+	echo Bad build directory: \"$buildloc\"
+	exit 2
 fi
 
 sed -e 's/^\(CONFIG[0-9A-Z_]*\)=.*$/grep -v "^# \1" |/' < $c > $T/u.sh
@@ -61,12 +59,12 @@ sed -e 's/^\(CONFIG[0-9A-Z_]*=\).*$/grep -v \1 |/' < $c >> $T/u.sh
 grep '^grep' < $T/u.sh > $T/upd.sh
 echo "cat - $c" >> $T/upd.sh
 make mrproper
-make $buildloc distclean > $builddir/Make.distclean 2>&1
-make $buildloc $TORTURE_DEFCONFIG > $builddir/Make.defconfig.out 2>&1
+make $buildloc distclean > $resdir/Make.distclean 2>&1
+make $buildloc $TORTURE_DEFCONFIG > $resdir/Make.defconfig.out 2>&1
 mv $builddir/.config $builddir/.config.sav
 sh $T/upd.sh < $builddir/.config.sav > $builddir/.config
 cp $builddir/.config $builddir/.config.new
-yes '' | make $buildloc oldconfig > $builddir/Make.oldconfig.out 2> $builddir/Make.oldconfig.err
+yes '' | make $buildloc oldconfig > $resdir/Make.oldconfig.out 2> $resdir/Make.oldconfig.err
 
 # verify new config matches specification.
 configcheck.sh $builddir/.config $c
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-build.sh b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
index 34d126734cde..9115fcdb5617 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-build.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-build.sh
@@ -2,7 +2,7 @@
 #
 # Build a kvm-ready Linux kernel from the tree in the current directory.
 #
-# Usage: kvm-build.sh config-template build-dir
+# Usage: kvm-build.sh config-template build-dir resdir
 #
 # This program is free software; you can redistribute it and/or modify
 # it under the terms of the GNU General Public License as published by
@@ -29,6 +29,7 @@ then
 	exit 1
 fi
 builddir=${2}
+resdir=${3}
 
 T=${TMPDIR-/tmp}/test-linux.sh.$$
 trap 'rm -rf $T' 0
@@ -41,19 +42,19 @@ CONFIG_VIRTIO_PCI=y
 CONFIG_VIRTIO_CONSOLE=y
 ___EOF___
 
-configinit.sh $T/config O=$builddir
+configinit.sh $T/config O=$builddir $resdir
 retval=$?
 if test $retval -gt 1
 then
 	exit 2
 fi
 ncpus=`cpus2use.sh`
-make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $builddir/Make.out 2>&1
+make O=$builddir -j$ncpus $TORTURE_KMAKE_ARG > $resdir/Make.out 2>&1
 retval=$?
-if test $retval -ne 0 || grep "rcu[^/]*": < $builddir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $builddir/Make.out
+if test $retval -ne 0 || grep "rcu[^/]*": < $resdir/Make.out | egrep -q "Stop|Error|error:|warning:" || egrep -q "Stop|Error|error:" < $resdir/Make.out
 then
 	echo Kernel build error
-	egrep "Stop|Error|error:|warning:" < $builddir/Make.out
+	egrep "Stop|Error|error:|warning:" < $resdir/Make.out
 	echo Run aborted.
 	exit 3
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index c5b0f94341d9..f7247ee00514 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -98,14 +98,15 @@ then
 	ln -s $base_resdir/.config $resdir  # for kvm-recheck.sh
 	# Arch-independent indicator
 	touch $resdir/builtkernel
-elif kvm-build.sh $T/Kc2 $builddir
+elif kvm-build.sh $T/Kc2 $builddir $resdir
 then
 	# Had to build a kernel for this test.
 	QEMU="`identify_qemu $builddir/vmlinux`"
 	BOOT_IMAGE="`identify_boot_image $QEMU`"
-	cp $builddir/Make*.out $resdir
 	cp $builddir/vmlinux $resdir
 	cp $builddir/.config $resdir
+	cp $builddir/Module.symvers $resdir > /dev/null || :
+	cp $builddir/System.map $resdir > /dev/null || :
 	if test -n "$BOOT_IMAGE"
 	then
 		cp $builddir/$BOOT_IMAGE $resdir
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 56610dbbdf73..5a7a62d76a50 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -347,7 +347,7 @@ function dump(first, pastlast, batchnum)
 	print "needqemurun="
 	jn=1
 	for (j = first; j < pastlast; j++) {
-		builddir=KVM "/b" jn
+		builddir=KVM "/b1"
 		cpusr[jn] = cpus[j];
 		if (cfrep[cf[j]] == "") {
 			cfr[jn] = cf[j];
-- 
cgit v1.2.3


From 69409750b28d098e5387310cc9ec4ff66301057b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Apr 2018 16:40:01 -0700
Subject: rcutorture: Remove obsolete TREE08-T.boot file

The TREE08-T.boot file was used to provide alternative options for
debugging, but things have changed, it has not kept up, and it has not
been used or missed.  This commit therefore removes it.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot | 1 -
 1 file changed, 1 deletion(-)
 delete mode 100644 tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot

diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
deleted file mode 100644
index 883149b5f2d1..000000000000
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE08-T.boot
+++ /dev/null
@@ -1 +0,0 @@
-rcutree.rcu_fanout_exact=1
-- 
cgit v1.2.3


From b4c1906f65cff3fbd1f3b7e08b3baa983e142756 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 3 May 2018 14:41:54 -0700
Subject: rcutorture: Make kvm-find-errors.sh find close calls

Although warnings about close calls are printed by kvm-recheck.sh,
kvm-find-errors.sh currently ignores them.  This could easily result
in someone failing to investigate close calls, so this commit makes
them visible to kvm-find-errors.sh.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh | 1 +
 tools/testing/selftests/rcutorture/bin/kvm-recheck.sh     | 1 +
 tools/testing/selftests/rcutorture/bin/parse-console.sh   | 7 +++++++
 3 files changed, 9 insertions(+)

diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
index 477ecb1293ab..0fa8a61ccb7b 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcu.sh
@@ -70,4 +70,5 @@ else
 	else
 		print_warning $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i
 	fi
+	echo $nclosecalls "Reader Batch close calls in" $(($dur/60)) minute run: $i > $i/console.log.rcu.diags
 fi
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
index c27e97824163..c9bab57a77eb 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck.sh
@@ -39,6 +39,7 @@ do
 			head -1 $resdir/log
 		fi
 		TORTURE_SUITE="`cat $i/../TORTURE_SUITE`"
+		rm -f $i/console.log.*.diags
 		kvm-recheck-${TORTURE_SUITE}.sh $i
 		if test -f "$i/console.log"
 		then
diff --git a/tools/testing/selftests/rcutorture/bin/parse-console.sh b/tools/testing/selftests/rcutorture/bin/parse-console.sh
index 17293436f551..84933f6aed77 100755
--- a/tools/testing/selftests/rcutorture/bin/parse-console.sh
+++ b/tools/testing/selftests/rcutorture/bin/parse-console.sh
@@ -163,6 +163,13 @@ then
 	print_warning Summary: $summary
 	cat $T.diags >> $file.diags
 fi
+for i in $file.*.diags
+do
+	if test -f "$i"
+	then
+		cat $i >> $file.diags
+	fi
+done
 if ! test -s $file.diags
 then
 	rm -f $file.diags
-- 
cgit v1.2.3


From 90127d605f403d814f4986436871210bf8ceb335 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 9 May 2018 10:29:18 -0700
Subject: torture: Make online/offline messages appear only for verbose=2

Some bugs reproduce quickly only at high CPU-hotplug rates, so the
rcutorture TREE03 scenario now has only 200 milliseconds spacing between
CPU-hotplug operations.  At this rate, the torture-test pair of console
messages per operation becomes a bit voluminous.  This commit therefore
converts the torture-test set of "verbose" kernel-boot arguments from
bool to int, and prints the extra console messages only when verbose=2.
The default is still verbose=1.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/torture.h      |  2 +-
 kernel/locking/locktorture.c |  2 +-
 kernel/rcu/rcuperf.c         |  2 +-
 kernel/rcu/rcutorture.c      |  2 +-
 kernel/torture.c             | 12 ++++++------
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/torture.h b/include/linux/torture.h
index 66272862070b..a55e80817dae 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -79,7 +79,7 @@ void stutter_wait(const char *title);
 int torture_stutter_init(int s);
 
 /* Initialization and cleanup. */
-bool torture_init_begin(char *ttype, bool v);
+bool torture_init_begin(char *ttype, int v);
 void torture_init_end(void);
 bool torture_cleanup_begin(void);
 void torture_cleanup_end(void);
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8402b3349dca..4a2e13870a9b 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -57,7 +57,7 @@ torture_param(int, shutdown_secs, 0, "Shutdown time (j), <= zero to disable.");
 torture_param(int, stat_interval, 60,
 	     "Number of seconds between stats printk()s");
 torture_param(int, stutter, 5, "Number of jiffies to run/halt test, 0=disable");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
 	     "Enable verbose debugging printk()s");
 
 static char *torture_type = "spin_lock";
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index e232846516b3..fb8094848906 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -88,7 +88,7 @@ torture_param(int, nreaders, -1, "Number of RCU reader threads");
 torture_param(int, nwriters, -1, "Number of RCU updater threads");
 torture_param(bool, shutdown, !IS_ENABLED(MODULE),
 	      "Shutdown at end of performance tests.");
-torture_param(bool, verbose, true, "Enable verbose debugging printk()s");
+torture_param(int, verbose, 1, "Enable verbose debugging printk()s");
 torture_param(int, writer_holdoff, 0, "Holdoff (us) between GPs, zero to disable");
 
 static char *perf_type = "rcu";
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 42fcb7f05fac..a5540bd831c4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -101,7 +101,7 @@ torture_param(int, test_boost_interval, 7,
 	     "Interval between boost tests, seconds.");
 torture_param(bool, test_no_idle_hz, true,
 	     "Test support for tickless idle CPUs");
-torture_param(bool, verbose, true,
+torture_param(int, verbose, 1,
 	     "Enable verbose debugging printk()s");
 
 static char *torture_type = "rcu";
diff --git a/kernel/torture.c b/kernel/torture.c
index 3de1efbecd6a..840fd33c1cda 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -53,7 +53,7 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com>");
 
 static char *torture_type;
-static bool verbose;
+static int verbose;
 
 /* Mediate rmmod and system shutdown.  Concurrent rmmod & shutdown illegal! */
 #define FULLSTOP_DONTSTOP 0	/* Normal operation. */
@@ -98,7 +98,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 	if (!cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
 
-	if (verbose)
+	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
 			 "torture_onoff task: offlining %d\n",
 			 torture_type, cpu);
@@ -111,7 +111,7 @@ bool torture_offline(int cpu, long *n_offl_attempts, long *n_offl_successes,
 				 "torture_onoff task: offline %d failed: errno %d\n",
 				 torture_type, cpu, ret);
 	} else {
-		if (verbose)
+		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
 				 "torture_onoff task: offlined %d\n",
 				 torture_type, cpu);
@@ -147,7 +147,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 	if (cpu_online(cpu) || !cpu_is_hotpluggable(cpu))
 		return false;
 
-	if (verbose)
+	if (verbose > 1)
 		pr_alert("%s" TORTURE_FLAG
 			 "torture_onoff task: onlining %d\n",
 			 torture_type, cpu);
@@ -160,7 +160,7 @@ bool torture_online(int cpu, long *n_onl_attempts, long *n_onl_successes,
 				 "torture_onoff task: online %d failed: errno %d\n",
 				 torture_type, cpu, ret);
 	} else {
-		if (verbose)
+		if (verbose > 1)
 			pr_alert("%s" TORTURE_FLAG
 				 "torture_onoff task: onlined %d\n",
 				 torture_type, cpu);
@@ -647,7 +647,7 @@ static void torture_stutter_cleanup(void)
  * The runnable parameter points to a flag that controls whether or not
  * the test is currently runnable.  If there is no such flag, pass in NULL.
  */
-bool torture_init_begin(char *ttype, bool v)
+bool torture_init_begin(char *ttype, int v)
 {
 	mutex_lock(&fullstop_mutex);
 	if (torture_type != NULL) {
-- 
cgit v1.2.3


From 60500037637397dcc8ea3d3c2f16e05ea6695a86 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 May 2018 12:25:05 -0700
Subject: torture: Keep old-school dmesg format

This commit adds "#define pr_fmt(fmt) fmt" to the torture-test files
in order to keep the current dmesg format.  Once Joe's commits have
hit mainline, these definitions will be changed in order to automatically
generate the dmesg line prefix that the scripts expect.  This will have
the beneficial side-effect of allowing printk() formats to be used more
widely and of shortening some pr_*() lines.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Joe Perches <joe@perches.com>
---
 kernel/locking/locktorture.c | 3 +++
 kernel/rcu/rcuperf.c         | 3 +++
 kernel/rcu/rcutorture.c      | 3 +++
 kernel/torture.c             | 3 +++
 4 files changed, 12 insertions(+)

diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 4a2e13870a9b..57bef4fbfb31 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -21,6 +21,9 @@
  *          Davidlohr Bueso <dave@stgolabs.net>
  *	Based on kernel/rcu/torture.c.
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/kthread.h>
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index fb8094848906..df29119b2013 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -19,6 +19,9 @@
  *
  * Authors: Paul E. McKenney <paulmck@us.ibm.com>
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index a5540bd831c4..5604bfac8df4 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -22,6 +22,9 @@
  *
  * See also:  Documentation/RCU/torture.txt
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
diff --git a/kernel/torture.c b/kernel/torture.c
index 840fd33c1cda..1ac24a826589 100644
--- a/kernel/torture.c
+++ b/kernel/torture.c
@@ -20,6 +20,9 @@
  * Author: Paul E. McKenney <paulmck@us.ibm.com>
  *	Based on kernel/rcu/torture.c.
  */
+
+#define pr_fmt(fmt) fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
-- 
cgit v1.2.3


From d4546c2509b1e9cd082e3682dcec98472e37ee5a Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Sun, 24 Jun 2018 14:13:49 +0900
Subject: net: Convert GRO SKB handling to list_head.

Manage pending per-NAPI GRO packets via list_head.

Return an SKB pointer from the GRO receive handlers.  When GRO receive
handlers return non-NULL, it means that this SKB needs to be completed
at this time and removed from the NAPI queue.

Several operations are greatly simplified by this transformation,
especially timing out the oldest SKB in the list when gro_count
exceeds MAX_GRO_SKBS, and napi_gro_flush() which walks the queue
in reverse order.

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c        | 11 ++++----
 drivers/net/vxlan.c         | 11 ++++----
 include/linux/etherdevice.h |  3 +-
 include/linux/netdevice.h   | 32 ++++++++++-----------
 include/linux/skbuff.h      |  3 +-
 include/linux/udp.h         |  4 +--
 include/net/inet_common.h   |  2 +-
 include/net/tcp.h           |  2 +-
 include/net/udp.h           |  4 +--
 include/net/udp_tunnel.h    |  6 ++--
 net/8021q/vlan.c            | 13 +++++----
 net/core/dev.c              | 68 +++++++++++++++++++--------------------------
 net/core/skbuff.c           |  4 +--
 net/ethernet/eth.c          | 12 ++++----
 net/ipv4/af_inet.c          | 12 ++++----
 net/ipv4/esp4_offload.c     |  4 +--
 net/ipv4/fou.c              | 20 ++++++-------
 net/ipv4/gre_offload.c      |  8 +++---
 net/ipv4/tcp_offload.c      | 14 +++++-----
 net/ipv4/udp_offload.c      | 13 +++++----
 net/ipv6/esp6_offload.c     |  4 +--
 net/ipv6/ip6_offload.c      | 16 +++++------
 net/ipv6/tcpv6_offload.c    |  4 +--
 net/ipv6/udp_offload.c      |  4 +--
 24 files changed, 133 insertions(+), 141 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 750eaa53bf0c..3e94375b9b01 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -418,11 +418,12 @@ static int geneve_hlen(struct genevehdr *gh)
 	return sizeof(*gh) + gh->opt_len * 4;
 }
 
-static struct sk_buff **geneve_gro_receive(struct sock *sk,
-					   struct sk_buff **head,
-					   struct sk_buff *skb)
+static struct sk_buff *geneve_gro_receive(struct sock *sk,
+					  struct list_head *head,
+					  struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
 	struct genevehdr *gh, *gh2;
 	unsigned int hlen, gh_len, off_gnv;
 	const struct packet_offload *ptype;
@@ -449,7 +450,7 @@ static struct sk_buff **geneve_gro_receive(struct sock *sk,
 			goto out;
 	}
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index aee0e60471f1..cc14e0cd5647 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -568,11 +568,12 @@ static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
 	return vh;
 }
 
-static struct sk_buff **vxlan_gro_receive(struct sock *sk,
-					  struct sk_buff **head,
-					  struct sk_buff *skb)
+static struct sk_buff *vxlan_gro_receive(struct sock *sk,
+					 struct list_head *head,
+					 struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
 	struct vxlanhdr *vh, *vh2;
 	unsigned int hlen, off_vx;
 	int flush = 1;
@@ -607,7 +608,7 @@ static struct sk_buff **vxlan_gro_receive(struct sock *sk,
 
 	skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 79563840c295..572e11bb8696 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -59,8 +59,7 @@ struct net_device *devm_alloc_etherdev_mqs(struct device *dev, int sizeof_priv,
 					   unsigned int rxqs);
 #define devm_alloc_etherdev(dev, sizeof_priv) devm_alloc_etherdev_mqs(dev, sizeof_priv, 1, 1)
 
-struct sk_buff **eth_gro_receive(struct sk_buff **head,
-				 struct sk_buff *skb);
+struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb);
 int eth_gro_complete(struct sk_buff *skb, int nhoff);
 
 /* Reserved Ethernet Addresses per IEEE 802.1Q */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3ec9850c7936..f176d9873910 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -322,7 +322,7 @@ struct napi_struct {
 	int			poll_owner;
 #endif
 	struct net_device	*dev;
-	struct sk_buff		*gro_list;
+	struct list_head	gro_list;
 	struct sk_buff		*skb;
 	struct hrtimer		timer;
 	struct list_head	dev_list;
@@ -2255,10 +2255,10 @@ static inline int gro_recursion_inc_test(struct sk_buff *skb)
 	return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
 }
 
-typedef struct sk_buff **(*gro_receive_t)(struct sk_buff **, struct sk_buff *);
-static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
-						struct sk_buff **head,
-						struct sk_buff *skb)
+typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *);
+static inline struct sk_buff *call_gro_receive(gro_receive_t cb,
+					       struct list_head *head,
+					       struct sk_buff *skb)
 {
 	if (unlikely(gro_recursion_inc_test(skb))) {
 		NAPI_GRO_CB(skb)->flush |= 1;
@@ -2268,12 +2268,12 @@ static inline struct sk_buff **call_gro_receive(gro_receive_t cb,
 	return cb(head, skb);
 }
 
-typedef struct sk_buff **(*gro_receive_sk_t)(struct sock *, struct sk_buff **,
-					     struct sk_buff *);
-static inline struct sk_buff **call_gro_receive_sk(gro_receive_sk_t cb,
-						   struct sock *sk,
-						   struct sk_buff **head,
-						   struct sk_buff *skb)
+typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *,
+					    struct sk_buff *);
+static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb,
+						  struct sock *sk,
+						  struct list_head *head,
+						  struct sk_buff *skb)
 {
 	if (unlikely(gro_recursion_inc_test(skb))) {
 		NAPI_GRO_CB(skb)->flush |= 1;
@@ -2299,8 +2299,8 @@ struct packet_type {
 struct offload_callbacks {
 	struct sk_buff		*(*gso_segment)(struct sk_buff *skb,
 						netdev_features_t features);
-	struct sk_buff		**(*gro_receive)(struct sk_buff **head,
-						 struct sk_buff *skb);
+	struct sk_buff		*(*gro_receive)(struct list_head *head,
+						struct sk_buff *skb);
 	int			(*gro_complete)(struct sk_buff *skb, int nhoff);
 };
 
@@ -2568,7 +2568,7 @@ struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
 struct net_device *dev_get_by_napi_id(unsigned int napi_id);
 int netdev_get_name(struct net *net, char *name, int ifindex);
 int dev_restart(struct net_device *dev);
-int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
 
 static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
 {
@@ -2784,13 +2784,13 @@ static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
 }
 
 #ifdef CONFIG_XFRM_OFFLOAD
-static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
 {
 	if (PTR_ERR(pp) != -EINPROGRESS)
 		NAPI_GRO_CB(skb)->flush |= flush;
 }
 #else
-static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff **pp, int flush)
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
 {
 	NAPI_GRO_CB(skb)->flush |= flush;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index c86885954994..7ccc601b55d9 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -677,7 +677,8 @@ struct sk_buff {
 				int			ip_defrag_offset;
 			};
 		};
-		struct rb_node	rbnode; /* used in netem & tcp stack */
+		struct rb_node		rbnode; /* used in netem & tcp stack */
+		struct list_head	list;
 	};
 	struct sock		*sk;
 
diff --git a/include/linux/udp.h b/include/linux/udp.h
index ca840345571b..320d49d85484 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -74,8 +74,8 @@ struct udp_sock {
 	void (*encap_destroy)(struct sock *sk);
 
 	/* GRO functions for UDP socket */
-	struct sk_buff **	(*gro_receive)(struct sock *sk,
-					       struct sk_buff **head,
+	struct sk_buff *	(*gro_receive)(struct sock *sk,
+					       struct list_head *head,
 					       struct sk_buff *skb);
 	int			(*gro_complete)(struct sock *sk,
 						struct sk_buff *skb,
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 384b90c62c0b..3ca969cbd161 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -43,7 +43,7 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family,
 int inet_recv_error(struct sock *sk, struct msghdr *msg, int len,
 		    int *addr_len);
 
-struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb);
 int inet_gro_complete(struct sk_buff *skb, int nhoff);
 struct sk_buff *inet_gso_segment(struct sk_buff *skb,
 				 netdev_features_t features);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 822ee49ed0f9..402a88b0e8a8 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1788,7 +1788,7 @@ void tcp_v4_destroy_sock(struct sock *sk);
 
 struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 				netdev_features_t features);
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb);
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb);
 int tcp_gro_complete(struct sk_buff *skb);
 
 void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr);
diff --git a/include/net/udp.h b/include/net/udp.h
index b1ea8b0f5e6a..5723c6128ae4 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -170,8 +170,8 @@ static inline void udp_csum_pull_header(struct sk_buff *skb)
 typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
 				     __be16 dport);
 
-struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
-				 struct udphdr *uh, udp_lookup_t lookup);
+struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				struct udphdr *uh, udp_lookup_t lookup);
 int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
 
 struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index b95a6927c718..fe680ab6b15a 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -65,9 +65,9 @@ static inline int udp_sock_create(struct net *net,
 
 typedef int (*udp_tunnel_encap_rcv_t)(struct sock *sk, struct sk_buff *skb);
 typedef void (*udp_tunnel_encap_destroy_t)(struct sock *sk);
-typedef struct sk_buff **(*udp_tunnel_gro_receive_t)(struct sock *sk,
-						     struct sk_buff **head,
-						     struct sk_buff *skb);
+typedef struct sk_buff *(*udp_tunnel_gro_receive_t)(struct sock *sk,
+						    struct list_head *head,
+						    struct sk_buff *skb);
 typedef int (*udp_tunnel_gro_complete_t)(struct sock *sk, struct sk_buff *skb,
 					 int nhoff);
 
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 73a65789271b..99141986efa0 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -647,13 +647,14 @@ out:
 	return err;
 }
 
-static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *vlan_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
-	struct vlan_hdr *vhdr;
-	unsigned int hlen, off_vlan;
 	const struct packet_offload *ptype;
+	unsigned int hlen, off_vlan;
+	struct sk_buff *pp = NULL;
+	struct vlan_hdr *vhdr;
+	struct sk_buff *p;
 	__be16 type;
 	int flush = 1;
 
@@ -675,7 +676,7 @@ static struct sk_buff **vlan_gro_receive(struct sk_buff **head,
 
 	flush = 0;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		struct vlan_hdr *vhdr2;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
diff --git a/net/core/dev.c b/net/core/dev.c
index a5aa1c7444e6..aa61b9344b46 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4881,36 +4881,25 @@ out:
  */
 void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	struct sk_buff *skb, *prev = NULL;
-
-	/* scan list and build reverse chain */
-	for (skb = napi->gro_list; skb != NULL; skb = skb->next) {
-		skb->prev = prev;
-		prev = skb;
-	}
-
-	for (skb = prev; skb; skb = prev) {
-		skb->next = NULL;
+	struct sk_buff *skb, *p;
 
+	list_for_each_entry_safe_reverse(skb, p, &napi->gro_list, list) {
 		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
 			return;
-
-		prev = skb->prev;
+		list_del_init(&skb->list);
 		napi_gro_complete(skb);
 		napi->gro_count--;
 	}
-
-	napi->gro_list = NULL;
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
 static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 {
-	struct sk_buff *p;
 	unsigned int maclen = skb->dev->hard_header_len;
 	u32 hash = skb_get_hash_raw(skb);
+	struct sk_buff *p;
 
-	for (p = napi->gro_list; p; p = p->next) {
+	list_for_each_entry(p, &napi->gro_list, list) {
 		unsigned long diffs;
 
 		NAPI_GRO_CB(p)->flush = 0;
@@ -4977,12 +4966,12 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
 
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
-	struct sk_buff **pp = NULL;
+	struct list_head *head = &offload_base;
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
-	struct list_head *head = &offload_base;
-	int same_flow;
+	struct sk_buff *pp = NULL;
 	enum gro_result ret;
+	int same_flow;
 	int grow;
 
 	if (netif_elide_gro(skb->dev))
@@ -5039,11 +5028,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
 
 	if (pp) {
-		struct sk_buff *nskb = *pp;
-
-		*pp = nskb->next;
-		nskb->next = NULL;
-		napi_gro_complete(nskb);
+		list_del_init(&pp->list);
+		napi_gro_complete(pp);
 		napi->gro_count--;
 	}
 
@@ -5054,15 +5040,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		goto normal;
 
 	if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
-		struct sk_buff *nskb = napi->gro_list;
+		struct sk_buff *nskb;
 
-		/* locate the end of the list to select the 'oldest' flow */
-		while (nskb->next) {
-			pp = &nskb->next;
-			nskb = *pp;
-		}
-		*pp = NULL;
-		nskb->next = NULL;
+		nskb = list_last_entry(&napi->gro_list, struct sk_buff, list);
+		list_del(&nskb->list);
 		napi_gro_complete(nskb);
 	} else {
 		napi->gro_count++;
@@ -5071,8 +5052,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	NAPI_GRO_CB(skb)->age = jiffies;
 	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
-	skb->next = napi->gro_list;
-	napi->gro_list = skb;
+	list_add(&skb->list, &napi->gro_list);
 	ret = GRO_HELD;
 
 pull:
@@ -5478,7 +5458,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
-	if (n->gro_list) {
+	if (!list_empty(&n->gro_list)) {
 		unsigned long timeout = 0;
 
 		if (work_done)
@@ -5687,7 +5667,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
-	if (napi->gro_list && !napi_disable_pending(napi) &&
+	if (!list_empty(&napi->gro_list) && !napi_disable_pending(napi) &&
 	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
 		__napi_schedule_irqoff(napi);
 
@@ -5701,7 +5681,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
-	napi->gro_list = NULL;
+	INIT_LIST_HEAD(&napi->gro_list);
 	napi->skb = NULL;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
@@ -5734,6 +5714,14 @@ void napi_disable(struct napi_struct *n)
 }
 EXPORT_SYMBOL(napi_disable);
 
+static void gro_list_free(struct list_head *head)
+{
+	struct sk_buff *skb, *p;
+
+	list_for_each_entry_safe(skb, p, head, list)
+		kfree_skb(skb);
+}
+
 /* Must be called in process context */
 void netif_napi_del(struct napi_struct *napi)
 {
@@ -5743,8 +5731,8 @@ void netif_napi_del(struct napi_struct *napi)
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
 
-	kfree_skb_list(napi->gro_list);
-	napi->gro_list = NULL;
+	gro_list_free(&napi->gro_list);
+	INIT_LIST_HEAD(&napi->gro_list);
 	napi->gro_count = 0;
 }
 EXPORT_SYMBOL(netif_napi_del);
@@ -5787,7 +5775,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
-	if (n->gro_list) {
+	if (!list_empty(&n->gro_list)) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
 		 */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c642304f178c..b1f274f22d85 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3815,14 +3815,14 @@ err:
 }
 EXPORT_SYMBOL_GPL(skb_segment);
 
-int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb)
 {
 	struct skb_shared_info *pinfo, *skbinfo = skb_shinfo(skb);
 	unsigned int offset = skb_gro_offset(skb);
 	unsigned int headlen = skb_headlen(skb);
 	unsigned int len = skb_gro_len(skb);
-	struct sk_buff *lp, *p = *head;
 	unsigned int delta_truesize;
+	struct sk_buff *lp;
 
 	if (unlikely(p->len + len >= 65536))
 		return -E2BIG;
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index ee28440f57c5..fd8faa0dfa61 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -427,13 +427,13 @@ ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len)
 }
 EXPORT_SYMBOL(sysfs_format_mac);
 
-struct sk_buff **eth_gro_receive(struct sk_buff **head,
-				 struct sk_buff *skb)
+struct sk_buff *eth_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
-	struct sk_buff *p, **pp = NULL;
-	struct ethhdr *eh, *eh2;
-	unsigned int hlen, off_eth;
 	const struct packet_offload *ptype;
+	unsigned int hlen, off_eth;
+	struct sk_buff *pp = NULL;
+	struct ethhdr *eh, *eh2;
+	struct sk_buff *p;
 	__be16 type;
 	int flush = 1;
 
@@ -448,7 +448,7 @@ struct sk_buff **eth_gro_receive(struct sk_buff **head,
 
 	flush = 0;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 15e125558c76..06b218a2870f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1384,12 +1384,12 @@ out:
 }
 EXPORT_SYMBOL(inet_gso_segment);
 
-struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff *inet_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
-	struct sk_buff *p;
+	struct sk_buff *pp = NULL;
 	const struct iphdr *iph;
+	struct sk_buff *p;
 	unsigned int hlen;
 	unsigned int off;
 	unsigned int id;
@@ -1425,7 +1425,7 @@ struct sk_buff **inet_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
 	id >>= 16;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		struct iphdr *iph2;
 		u16 flush_id;
 
@@ -1505,8 +1505,8 @@ out:
 }
 EXPORT_SYMBOL(inet_gro_receive);
 
-static struct sk_buff **ipip_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *ipip_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	if (NAPI_GRO_CB(skb)->encap_mark) {
 		NAPI_GRO_CB(skb)->flush = 1;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 7cf755ef9efb..bbeecd13e534 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -28,8 +28,8 @@
 #include <linux/spinlock.h>
 #include <net/udp.h>
 
-static struct sk_buff **esp4_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *esp4_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	int offset = skb_gro_offset(skb);
 	struct xfrm_offload *xo;
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 1540db65241a..efdc9e1f741e 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -224,14 +224,14 @@ drop:
 	return 0;
 }
 
-static struct sk_buff **fou_gro_receive(struct sock *sk,
-					struct sk_buff **head,
-					struct sk_buff *skb)
+static struct sk_buff *fou_gro_receive(struct sock *sk,
+				       struct list_head *head,
+				       struct sk_buff *skb)
 {
-	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
 	u8 proto = fou_from_sock(sk)->protocol;
 	const struct net_offload **offloads;
+	const struct net_offload *ops;
+	struct sk_buff *pp = NULL;
 
 	/* We can clear the encap_mark for FOU as we are essentially doing
 	 * one of two possible things.  We are either adding an L4 tunnel
@@ -305,13 +305,13 @@ static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
 	return guehdr;
 }
 
-static struct sk_buff **gue_gro_receive(struct sock *sk,
-					struct sk_buff **head,
-					struct sk_buff *skb)
+static struct sk_buff *gue_gro_receive(struct sock *sk,
+				       struct list_head *head,
+				       struct sk_buff *skb)
 {
 	const struct net_offload **offloads;
 	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	struct guehdr *guehdr;
 	size_t len, optlen, hdrlen, off;
@@ -397,7 +397,7 @@ static struct sk_buff **gue_gro_receive(struct sock *sk,
 
 	skb_gro_pull(skb, hdrlen);
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		const struct guehdr *guehdr2;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 1859c473b21a..b9673c21be45 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -108,10 +108,10 @@ out:
 	return segs;
 }
 
-static struct sk_buff **gre_gro_receive(struct sk_buff **head,
-					struct sk_buff *skb)
+static struct sk_buff *gre_gro_receive(struct list_head *head,
+				       struct sk_buff *skb)
 {
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	const struct gre_base_hdr *greh;
 	unsigned int hlen, grehlen;
@@ -182,7 +182,7 @@ static struct sk_buff **gre_gro_receive(struct sk_buff **head,
 					     null_compute_pseudo);
 	}
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		const struct gre_base_hdr *greh2;
 
 		if (!NAPI_GRO_CB(p)->same_flow)
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 8cc7c3487330..f5aee641f825 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -180,9 +180,9 @@ out:
 	return segs;
 }
 
-struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	struct tcphdr *th;
 	struct tcphdr *th2;
@@ -220,7 +220,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 	len = skb_gro_len(skb);
 	flags = tcp_flag_word(th);
 
-	for (; (p = *head); head = &p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
@@ -233,7 +233,7 @@ struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb)
 
 		goto found;
 	}
-
+	p = NULL;
 	goto out_check_final;
 
 found:
@@ -263,7 +263,7 @@ found:
 	flush |= (len - 1) >= mss;
 	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
 
-	if (flush || skb_gro_receive(head, skb)) {
+	if (flush || skb_gro_receive(p, skb)) {
 		mss = 1;
 		goto out_check_final;
 	}
@@ -277,7 +277,7 @@ out_check_final:
 					TCP_FLAG_FIN));
 
 	if (p && (!NAPI_GRO_CB(skb)->same_flow || flush))
-		pp = head;
+		pp = p;
 
 out:
 	NAPI_GRO_CB(skb)->flush |= (flush != 0);
@@ -302,7 +302,7 @@ int tcp_gro_complete(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_gro_complete);
 
-static struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
+static struct sk_buff *tcp4_gro_receive(struct list_head *head, struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 92dc9e5a7ff3..ac46c1c55c99 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -343,10 +343,11 @@ out:
 	return segs;
 }
 
-struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
-				 struct udphdr *uh, udp_lookup_t lookup)
+struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				struct udphdr *uh, udp_lookup_t lookup)
 {
-	struct sk_buff *p, **pp = NULL;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
 	struct udphdr *uh2;
 	unsigned int off = skb_gro_offset(skb);
 	int flush = 1;
@@ -371,7 +372,7 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb,
 unflush:
 	flush = 0;
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		if (!NAPI_GRO_CB(p)->same_flow)
 			continue;
 
@@ -399,8 +400,8 @@ out:
 }
 EXPORT_SYMBOL(udp_gro_receive);
 
-static struct sk_buff **udp4_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *udp4_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 27f59b61f70f..ddfa533a84e5 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -49,8 +49,8 @@ static __u16 esp6_nexthdr_esp_offset(struct ipv6hdr *ipv6_hdr, int nhlen)
 	return 0;
 }
 
-static struct sk_buff **esp6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *esp6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	int offset = skb_gro_offset(skb);
 	struct xfrm_offload *xo;
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 5b3f2f89ef41..37ff4805b20c 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -163,11 +163,11 @@ static int ipv6_exthdrs_len(struct ipv6hdr *iph,
 	return len;
 }
 
-static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *ipv6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	const struct net_offload *ops;
-	struct sk_buff **pp = NULL;
+	struct sk_buff *pp = NULL;
 	struct sk_buff *p;
 	struct ipv6hdr *iph;
 	unsigned int nlen;
@@ -214,7 +214,7 @@ static struct sk_buff **ipv6_gro_receive(struct sk_buff **head,
 	flush--;
 	nlen = skb_network_header_len(skb);
 
-	for (p = *head; p; p = p->next) {
+	list_for_each_entry(p, head, list) {
 		const struct ipv6hdr *iph2;
 		__be32 first_word; /* <Version:4><Traffic_Class:8><Flow_Label:20> */
 
@@ -263,8 +263,8 @@ out:
 	return pp;
 }
 
-static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
-					       struct sk_buff *skb)
+static struct sk_buff *sit_ip6ip6_gro_receive(struct list_head *head,
+					      struct sk_buff *skb)
 {
 	/* Common GRO receive for SIT and IP6IP6 */
 
@@ -278,8 +278,8 @@ static struct sk_buff **sit_ip6ip6_gro_receive(struct sk_buff **head,
 	return ipv6_gro_receive(head, skb);
 }
 
-static struct sk_buff **ip4ip6_gro_receive(struct sk_buff **head,
-					   struct sk_buff *skb)
+static struct sk_buff *ip4ip6_gro_receive(struct list_head *head,
+					  struct sk_buff *skb)
 {
 	/* Common GRO receive for SIT and IP6IP6 */
 
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index 278e49cd67d4..e72947c99454 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -15,8 +15,8 @@
 #include <net/ip6_checksum.h>
 #include "ip6_offload.h"
 
-static struct sk_buff **tcp6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *tcp6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	/* Don't bother verifying checksum if we're going to flush anyway. */
 	if (!NAPI_GRO_CB(skb)->flush &&
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 03a2ff3fe1e6..95dee9ca8d22 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -114,8 +114,8 @@ out:
 	return segs;
 }
 
-static struct sk_buff **udp6_gro_receive(struct sk_buff **head,
-					 struct sk_buff *skb)
+static struct sk_buff *udp6_gro_receive(struct list_head *head,
+					struct sk_buff *skb)
 {
 	struct udphdr *uh = udp_gro_udphdr(skb);
 
-- 
cgit v1.2.3


From 07d78363dcffd9cb1bf6f06a6cac0e0847f3c1de Mon Sep 17 00:00:00 2001
From: David Miller <davem@davemloft.net>
Date: Sun, 24 Jun 2018 14:14:02 +0900
Subject: net: Convert NAPI gro list into a small hash table.

Improve the performance of GRO receive by splitting flows into
multiple hash chains.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |   3 +-
 net/core/dev.c            | 105 ++++++++++++++++++++++++++++++++++------------
 2 files changed, 81 insertions(+), 27 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f176d9873910..c6b377a15869 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -305,6 +305,7 @@ int __init netdev_boot_setup(char *str);
 /*
  * Structure for NAPI scheduling similar to tasklet but with weighting
  */
+#define GRO_HASH_BUCKETS	8
 struct napi_struct {
 	/* The poll_list must only be managed by the entity which
 	 * changes the state of the NAPI_STATE_SCHED bit.  This means
@@ -322,7 +323,7 @@ struct napi_struct {
 	int			poll_owner;
 #endif
 	struct net_device	*dev;
-	struct list_head	gro_list;
+	struct list_head	gro_hash[GRO_HASH_BUCKETS];
 	struct sk_buff		*skb;
 	struct hrtimer		timer;
 	struct list_head	dev_list;
diff --git a/net/core/dev.c b/net/core/dev.c
index aa61b9344b46..dffed642e686 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4875,15 +4875,12 @@ out:
 	return netif_receive_skb_internal(skb);
 }
 
-/* napi->gro_list contains packets ordered by age.
- * youngest packets at the head of it.
- * Complete skbs in reverse order to reduce latencies.
- */
-void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *head,
+				   bool flush_old)
 {
 	struct sk_buff *skb, *p;
 
-	list_for_each_entry_safe_reverse(skb, p, &napi->gro_list, list) {
+	list_for_each_entry_safe_reverse(skb, p, head, list) {
 		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
 			return;
 		list_del_init(&skb->list);
@@ -4891,15 +4888,33 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 		napi->gro_count--;
 	}
 }
+
+/* napi->gro_hash contains packets ordered by age.
+ * youngest packets at the head of it.
+ * Complete skbs in reverse order to reduce latencies.
+ */
+void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+{
+	int i;
+
+	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+		struct list_head *head = &napi->gro_hash[i];
+
+		__napi_gro_flush_chain(napi, head, flush_old);
+	}
+}
 EXPORT_SYMBOL(napi_gro_flush);
 
-static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
+static struct list_head *gro_list_prepare(struct napi_struct *napi,
+					  struct sk_buff *skb)
 {
 	unsigned int maclen = skb->dev->hard_header_len;
 	u32 hash = skb_get_hash_raw(skb);
+	struct list_head *head;
 	struct sk_buff *p;
 
-	list_for_each_entry(p, &napi->gro_list, list) {
+	head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)];
+	list_for_each_entry(p, head, list) {
 		unsigned long diffs;
 
 		NAPI_GRO_CB(p)->flush = 0;
@@ -4922,6 +4937,8 @@ static void gro_list_prepare(struct napi_struct *napi, struct sk_buff *skb)
 				       maclen);
 		NAPI_GRO_CB(p)->same_flow = !diffs;
 	}
+
+	return head;
 }
 
 static void skb_gro_reset_offset(struct sk_buff *skb)
@@ -4964,11 +4981,45 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
 	}
 }
 
+static void gro_flush_oldest(struct napi_struct *napi)
+{
+	struct sk_buff *oldest = NULL;
+	unsigned long age = jiffies;
+	int i;
+
+	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+		struct list_head *head = &napi->gro_hash[i];
+		struct sk_buff *skb;
+
+		if (list_empty(head))
+			continue;
+
+		skb = list_last_entry(head, struct sk_buff, list);
+		if (!oldest || time_before(NAPI_GRO_CB(skb)->age, age)) {
+			oldest = skb;
+			age = NAPI_GRO_CB(skb)->age;
+		}
+	}
+
+	/* We are called with napi->gro_count >= MAX_GRO_SKBS, so this is
+	 * impossible.
+	 */
+	if (WARN_ON_ONCE(!oldest))
+		return;
+
+	/* Do not adjust napi->gro_count, caller is adding a new SKB to
+	 * the chain.
+	 */
+	list_del(&oldest->list);
+	napi_gro_complete(oldest);
+}
+
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
 	struct list_head *head = &offload_base;
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
+	struct list_head *gro_head;
 	struct sk_buff *pp = NULL;
 	enum gro_result ret;
 	int same_flow;
@@ -4977,7 +5028,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (netif_elide_gro(skb->dev))
 		goto normal;
 
-	gro_list_prepare(napi, skb);
+	gro_head = gro_list_prepare(napi, skb);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(ptype, head, list) {
@@ -5011,7 +5062,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 			NAPI_GRO_CB(skb)->csum_valid = 0;
 		}
 
-		pp = ptype->callbacks.gro_receive(&napi->gro_list, skb);
+		pp = ptype->callbacks.gro_receive(gro_head, skb);
 		break;
 	}
 	rcu_read_unlock();
@@ -5040,11 +5091,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		goto normal;
 
 	if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
-		struct sk_buff *nskb;
-
-		nskb = list_last_entry(&napi->gro_list, struct sk_buff, list);
-		list_del(&nskb->list);
-		napi_gro_complete(nskb);
+		gro_flush_oldest(napi);
 	} else {
 		napi->gro_count++;
 	}
@@ -5052,7 +5099,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	NAPI_GRO_CB(skb)->age = jiffies;
 	NAPI_GRO_CB(skb)->last = skb;
 	skb_shinfo(skb)->gso_size = skb_gro_len(skb);
-	list_add(&skb->list, &napi->gro_list);
+	list_add(&skb->list, gro_head);
 	ret = GRO_HELD;
 
 pull:
@@ -5458,7 +5505,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
-	if (!list_empty(&n->gro_list)) {
+	if (n->gro_count) {
 		unsigned long timeout = 0;
 
 		if (work_done)
@@ -5667,7 +5714,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
-	if (!list_empty(&napi->gro_list) && !napi_disable_pending(napi) &&
+	if (napi->gro_count && !napi_disable_pending(napi) &&
 	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
 		__napi_schedule_irqoff(napi);
 
@@ -5677,11 +5724,14 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 		    int (*poll)(struct napi_struct *, int), int weight)
 {
+	int i;
+
 	INIT_LIST_HEAD(&napi->poll_list);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
-	INIT_LIST_HEAD(&napi->gro_list);
+	for (i = 0; i < GRO_HASH_BUCKETS; i++)
+		INIT_LIST_HEAD(&napi->gro_hash[i]);
 	napi->skb = NULL;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
@@ -5714,12 +5764,16 @@ void napi_disable(struct napi_struct *n)
 }
 EXPORT_SYMBOL(napi_disable);
 
-static void gro_list_free(struct list_head *head)
+static void flush_gro_hash(struct napi_struct *napi)
 {
-	struct sk_buff *skb, *p;
+	int i;
 
-	list_for_each_entry_safe(skb, p, head, list)
-		kfree_skb(skb);
+	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+		struct sk_buff *skb, *n;
+
+		list_for_each_entry_safe(skb, n, &napi->gro_hash[i], list)
+			kfree_skb(skb);
+	}
 }
 
 /* Must be called in process context */
@@ -5731,8 +5785,7 @@ void netif_napi_del(struct napi_struct *napi)
 	list_del_init(&napi->dev_list);
 	napi_free_frags(napi);
 
-	gro_list_free(&napi->gro_list);
-	INIT_LIST_HEAD(&napi->gro_list);
+	flush_gro_hash(napi);
 	napi->gro_count = 0;
 }
 EXPORT_SYMBOL(netif_napi_del);
@@ -5775,7 +5828,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
-	if (!list_empty(&n->gro_list)) {
+	if (n->gro_count) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
 		 */
-- 
cgit v1.2.3


From fb223502ec0889444965f602f57b1f45f9e9845e Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 24 Jun 2018 10:02:54 -0400
Subject: tcp: add SNMP counter for zero-window drops

It will be helpful if we could display the drops due to zero window or no
enough window space.
So a new SNMP MIB entry is added to track this behavior.
This entry is named LINUX_MIB_TCPZEROWINDOWDROP and published in
/proc/net/netstat in TcpExt line as TCPZeroWindowDrop.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/snmp.h | 1 +
 net/ipv4/proc.c           | 1 +
 net/ipv4/tcp_input.c      | 8 ++++++--
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 750d89120335..97517f36a5f9 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -279,6 +279,7 @@ enum
 	LINUX_MIB_TCPDELIVERED,			/* TCPDelivered */
 	LINUX_MIB_TCPDELIVEREDCE,		/* TCPDeliveredCE */
 	LINUX_MIB_TCPACKCOMPRESSED,		/* TCPAckCompressed */
+	LINUX_MIB_TCPZEROWINDOWDROP,		/* TCPZeroWindowDrop */
 	__LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 77350c1256ce..225ef3433fe5 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -287,6 +287,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED),
 	SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE),
 	SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED),
+	SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 76ca88f63b70..9c5b3415413f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4668,8 +4668,10 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	 *  Out of sequence packets to the out_of_order_queue.
 	 */
 	if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) {
-		if (tcp_receive_window(tp) == 0)
+		if (tcp_receive_window(tp) == 0) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
 			goto out_of_window;
+		}
 
 		/* Ok. In sequence. In window. */
 queue_and_out:
@@ -4735,8 +4737,10 @@ drop:
 		/* If window is closed, drop tail of packet. But after
 		 * remembering D-SACK for its head made in previous line.
 		 */
-		if (!tcp_receive_window(tp))
+		if (!tcp_receive_window(tp)) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPZEROWINDOWDROP);
 			goto out_of_window;
+		}
 		goto queue_and_out;
 	}
 
-- 
cgit v1.2.3


From 9a4903dde2c8633c5fcf887b98c4e047a6154a54 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:48 +0200
Subject: perf/hw_breakpoint: Split attribute parse and commit

arch_validate_hwbkpt_settings() mixes up attribute check and commit into
a single code entity. Therefore the validation may return an error due to
incorrect atributes while still leaving halfway modified architecture
breakpoint data.

This is harmless when we deal with a new breakpoint but it becomes a
problem when we modify an existing breakpoint.

Split attribute parse and commit to fix that. The architecture is
passed a "struct arch_hw_breakpoint" to fill on top of the new attr
and the core takes care about copying the backend data once it's fully
validated. The architectures then need to implement the new API.

Original-patch-by: Andy Lutomirski <luto@kernel.org>
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-2-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/events/hw_breakpoint.c | 57 +++++++++++++++++++++++++++++++------------
 1 file changed, 41 insertions(+), 16 deletions(-)

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 6e28d2866be5..314e2a9040c7 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -400,16 +400,35 @@ int dbg_release_bp_slot(struct perf_event *bp)
 	return 0;
 }
 
-static int validate_hw_breakpoint(struct perf_event *bp)
+#ifndef hw_breakpoint_arch_parse
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	int ret;
+	int err;
 
-	ret = arch_validate_hwbkpt_settings(bp);
-	if (ret)
-		return ret;
+	err = arch_validate_hwbkpt_settings(bp);
+	if (err)
+		return err;
+
+	*hw = bp->hw.info;
+
+	return 0;
+}
+#endif
+
+static int hw_breakpoint_parse(struct perf_event *bp,
+			       const struct perf_event_attr *attr,
+			       struct arch_hw_breakpoint *hw)
+{
+	int err;
+
+	err = hw_breakpoint_arch_parse(bp, attr, hw);
+	if (err)
+		return err;
 
 	if (arch_check_bp_in_kernelspace(bp)) {
-		if (bp->attr.exclude_kernel)
+		if (attr->exclude_kernel)
 			return -EINVAL;
 		/*
 		 * Don't let unprivileged users set a breakpoint in the trap
@@ -424,19 +443,22 @@ static int validate_hw_breakpoint(struct perf_event *bp)
 
 int register_perf_hw_breakpoint(struct perf_event *bp)
 {
-	int ret;
-
-	ret = reserve_bp_slot(bp);
-	if (ret)
-		return ret;
+	struct arch_hw_breakpoint hw;
+	int err;
 
-	ret = validate_hw_breakpoint(bp);
+	err = reserve_bp_slot(bp);
+	if (err)
+		return err;
 
-	/* if arch_validate_hwbkpt_settings() fails then release bp slot */
-	if (ret)
+	err = hw_breakpoint_parse(bp, &bp->attr, &hw);
+	if (err) {
 		release_bp_slot(bp);
+		return err;
+	}
 
-	return ret;
+	bp->hw.info = hw;
+
+	return 0;
 }
 
 /**
@@ -464,6 +486,7 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
 	u64 old_len  = bp->attr.bp_len;
 	int old_type = bp->attr.bp_type;
 	bool modify  = attr->bp_type != old_type;
+	struct arch_hw_breakpoint hw;
 	int err = 0;
 
 	bp->attr.bp_addr = attr->bp_addr;
@@ -473,7 +496,7 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
 	if (check && memcmp(&bp->attr, attr, sizeof(*attr)))
 		return -EINVAL;
 
-	err = validate_hw_breakpoint(bp);
+	err = hw_breakpoint_parse(bp, attr, &hw);
 	if (!err && modify)
 		err = modify_bp_slot(bp, old_type);
 
@@ -484,7 +507,9 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
 		return err;
 	}
 
+	bp->hw.info = hw;
 	bp->attr.disabled = attr->disabled;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 8e983ff9ac02a8fb454ed09c2462bdb3617006a8 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:49 +0200
Subject: perf/hw_breakpoint: Pass arch breakpoint struct to
 arch_check_bp_in_kernelspace()

We can't pass the breakpoint directly on arch_check_bp_in_kernelspace()
anymore because its architecture internal datas (struct arch_hw_breakpoint)
are not yet filled by the time we call the function, and most
implementation need this backend to be up to date. So arrange the
function to take the probing struct instead.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-3-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/hw_breakpoint.h     |  2 +-
 arch/arm/kernel/hw_breakpoint.c          | 11 +++--
 arch/arm64/include/asm/hw_breakpoint.h   |  2 +-
 arch/arm64/kernel/hw_breakpoint.c        |  9 ++--
 arch/powerpc/include/asm/hw_breakpoint.h |  2 +-
 arch/powerpc/kernel/hw_breakpoint.c      |  6 +--
 arch/sh/include/asm/hw_breakpoint.h      |  2 +-
 arch/sh/kernel/hw_breakpoint.c           |  9 ++--
 arch/x86/include/asm/hw_breakpoint.h     |  2 +-
 arch/x86/kernel/hw_breakpoint.c          | 71 +++++++++++++++++---------------
 arch/xtensa/include/asm/hw_breakpoint.h  |  2 +-
 arch/xtensa/kernel/hw_breakpoint.c       |  7 ++--
 kernel/events/hw_breakpoint.c            |  2 +-
 13 files changed, 63 insertions(+), 64 deletions(-)

diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index e46e4e7bdba3..d5a0f52c6755 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -117,7 +117,7 @@ struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 629e25152c0d..385dcf45d64b 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -456,14 +456,13 @@ static int get_hbp_len(u8 hbp_len)
 /*
  * Check whether bp virtual address is in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->ctrl.len);
+	va = hw->address;
+	len = get_hbp_len(hw->ctrl.len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -576,7 +575,7 @@ static int arch_build_bp_info(struct perf_event *bp)
 
 	/* Privilege */
 	info->ctrl.privilege = ARM_BREAKPOINT_USER;
-	if (arch_check_bp_in_kernelspace(bp))
+	if (arch_check_bp_in_kernelspace(info))
 		info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
 
 	/* Enabled? */
@@ -640,7 +639,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 			return -EINVAL;
 
 		/* We don't allow mismatch breakpoints in kernel space. */
-		if (arch_check_bp_in_kernelspace(bp))
+		if (arch_check_bp_in_kernelspace(info))
 			return -EPERM;
 
 		/*
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 41770766d964..9f4a3d48762e 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -124,7 +124,7 @@ struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type, int *offset);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 413dbe530da8..6a90d12e4ff2 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -343,14 +343,13 @@ static int get_hbp_len(u8 hbp_len)
 /*
  * Check whether bp virtual address is in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->ctrl.len);
+	va = hw->address;
+	len = get_hbp_len(hw->ctrl.len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -502,7 +501,7 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * Note that we disallow combined EL0/EL1 breakpoints because
 	 * that would complicate the stepping code.
 	 */
-	if (arch_check_bp_in_kernelspace(bp))
+	if (arch_check_bp_in_kernelspace(info))
 		info->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
 	else
 		info->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 8e7b09703ca4..4d0b1bfcdfd0 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -60,7 +60,7 @@ struct perf_sample_data;
 
 extern int hw_breakpoint_slots(int type);
 extern int arch_bp_generic_fields(int type, int *gen_bp_type);
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 						unsigned long val, void *data);
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 80547dad37da..899bcec3f3c8 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -119,11 +119,9 @@ void arch_unregister_hw_breakpoint(struct perf_event *bp)
 /*
  * Check for virtual address in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	return is_kernel_addr(info->address);
+	return is_kernel_addr(hw->address);
 }
 
 int arch_bp_generic_fields(int type, int *gen_bp_type)
diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index 7431c172c0cb..8a88ed0b3cd7 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -54,7 +54,7 @@ static inline int hw_breakpoint_slots(int type)
 }
 
 /* arch/sh/kernel/hw_breakpoint.c */
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index 8648ed05ccf0..38791fefdd0c 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -124,14 +124,13 @@ static int get_hbp_len(u16 hbp_len)
 /*
  * Check for virtual address in kernel space.
  */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = get_hbp_len(info->len);
+	va = hw->address;
+	len = get_hbp_len(hw->len);
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
@@ -346,7 +345,7 @@ static int __kprobes hw_breakpoint_handler(struct die_args *args)
 		perf_bp_event(bp, args->regs);
 
 		/* Deliver the signal to userspace */
-		if (!arch_check_bp_in_kernelspace(bp)) {
+		if (!arch_check_bp_in_kernelspace(&bp->hw.info)) {
 			force_sig_fault(SIGTRAP, TRAP_HWBKPT,
 					(void __user *)NULL, current);
 		}
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index f59c39835a5a..78924596f51f 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -52,7 +52,7 @@ static inline int hw_breakpoint_slots(int type)
 struct perf_event;
 struct pmu;
 
-extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
+extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index 8771766d46b6..c43379188f4f 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -169,28 +169,29 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 		set_dr_addr_mask(0, i);
 }
 
-/*
- * Check for virtual address in kernel space.
- */
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+static int arch_bp_generic_len(int x86_len)
 {
-	unsigned int len;
-	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	va = info->address;
-	len = bp->attr.bp_len;
-
-	/*
-	 * We don't need to worry about va + len - 1 overflowing:
-	 * we already require that va is aligned to a multiple of len.
-	 */
-	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+	switch (x86_len) {
+	case X86_BREAKPOINT_LEN_1:
+		return HW_BREAKPOINT_LEN_1;
+	case X86_BREAKPOINT_LEN_2:
+		return HW_BREAKPOINT_LEN_2;
+	case X86_BREAKPOINT_LEN_4:
+		return HW_BREAKPOINT_LEN_4;
+#ifdef CONFIG_X86_64
+	case X86_BREAKPOINT_LEN_8:
+		return HW_BREAKPOINT_LEN_8;
+#endif
+	default:
+		return -EINVAL;
+	}
 }
 
 int arch_bp_generic_fields(int x86_len, int x86_type,
 			   int *gen_len, int *gen_type)
 {
+	int len;
+
 	/* Type */
 	switch (x86_type) {
 	case X86_BREAKPOINT_EXECUTE:
@@ -211,28 +212,32 @@ int arch_bp_generic_fields(int x86_len, int x86_type,
 	}
 
 	/* Len */
-	switch (x86_len) {
-	case X86_BREAKPOINT_LEN_1:
-		*gen_len = HW_BREAKPOINT_LEN_1;
-		break;
-	case X86_BREAKPOINT_LEN_2:
-		*gen_len = HW_BREAKPOINT_LEN_2;
-		break;
-	case X86_BREAKPOINT_LEN_4:
-		*gen_len = HW_BREAKPOINT_LEN_4;
-		break;
-#ifdef CONFIG_X86_64
-	case X86_BREAKPOINT_LEN_8:
-		*gen_len = HW_BREAKPOINT_LEN_8;
-		break;
-#endif
-	default:
+	len = arch_bp_generic_len(x86_len);
+	if (len < 0)
 		return -EINVAL;
-	}
+	*gen_len = len;
 
 	return 0;
 }
 
+/*
+ * Check for virtual address in kernel space.
+ */
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
+{
+	unsigned long va;
+	int len;
+
+	va = hw->address;
+	len = arch_bp_generic_len(hw->len);
+	WARN_ON_ONCE(len < 0);
+
+	/*
+	 * We don't need to worry about va + len - 1 overflowing:
+	 * we already require that va is aligned to a multiple of len.
+	 */
+	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
+}
 
 static int arch_build_bp_info(struct perf_event *bp)
 {
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index dbe3053b284a..2525bf6816a6 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -35,7 +35,7 @@ struct pt_regs;
 struct task_struct;
 
 int hw_breakpoint_slots(int type);
-int arch_check_bp_in_kernelspace(struct perf_event *bp);
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 int arch_validate_hwbkpt_settings(struct perf_event *bp);
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data);
diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c
index b35656ab7dbd..6e34c3848885 100644
--- a/arch/xtensa/kernel/hw_breakpoint.c
+++ b/arch/xtensa/kernel/hw_breakpoint.c
@@ -33,14 +33,13 @@ int hw_breakpoint_slots(int type)
 	}
 }
 
-int arch_check_bp_in_kernelspace(struct perf_event *bp)
+int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 {
 	unsigned int len;
 	unsigned long va;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
-	va = info->address;
-	len = bp->attr.bp_len;
+	va = hw->address;
+	len = hw->len;
 
 	return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE);
 }
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 314e2a9040c7..89fe94c9214c 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -427,7 +427,7 @@ static int hw_breakpoint_parse(struct perf_event *bp,
 	if (err)
 		return err;
 
-	if (arch_check_bp_in_kernelspace(bp)) {
+	if (arch_check_bp_in_kernelspace(hw)) {
 		if (attr->exclude_kernel)
 			return -EINVAL;
 		/*
-- 
cgit v1.2.3


From a0baf043c5cfa3a489a63ac50f5201c31a651e21 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:50 +0200
Subject: perf/arch/x86: Implement hw_breakpoint_arch_parse()

Migrate to the new API in order to remove arch_validate_hwbkpt_settings()
that clumsily mixes up architecture validation and commit.

Original-patch-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-4-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/hw_breakpoint.h |  6 +++-
 arch/x86/kernel/hw_breakpoint.c      | 60 ++++++++++++++++++------------------
 2 files changed, 35 insertions(+), 31 deletions(-)

diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 78924596f51f..6c88e8e22678 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -49,11 +49,15 @@ static inline int hw_breakpoint_slots(int type)
 	return HBP_NUM;
 }
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
 extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
+#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c
index c43379188f4f..34a5c1715148 100644
--- a/arch/x86/kernel/hw_breakpoint.c
+++ b/arch/x86/kernel/hw_breakpoint.c
@@ -239,19 +239,20 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 	return (va >= TASK_SIZE_MAX) || ((va + len - 1) >= TASK_SIZE_MAX);
 }
 
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
+	hw->mask = 0;
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_W:
-		info->type = X86_BREAKPOINT_WRITE;
+		hw->type = X86_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = X86_BREAKPOINT_RW;
+		hw->type = X86_BREAKPOINT_RW;
 		break;
 	case HW_BREAKPOINT_X:
 		/*
@@ -259,23 +260,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * acceptable for kprobes.  On non-kprobes kernels, we don't
 		 * allow kernel breakpoints at all.
 		 */
-		if (bp->attr.bp_addr >= TASK_SIZE_MAX) {
+		if (attr->bp_addr >= TASK_SIZE_MAX) {
 #ifdef CONFIG_KPROBES
-			if (within_kprobe_blacklist(bp->attr.bp_addr))
+			if (within_kprobe_blacklist(attr->bp_addr))
 				return -EINVAL;
 #else
 			return -EINVAL;
 #endif
 		}
 
-		info->type = X86_BREAKPOINT_EXECUTE;
+		hw->type = X86_BREAKPOINT_EXECUTE;
 		/*
 		 * x86 inst breakpoints need to have a specific undefined len.
 		 * But we still need to check userspace is not trying to setup
 		 * an unsupported length, to get a range breakpoint for example.
 		 */
-		if (bp->attr.bp_len == sizeof(long)) {
-			info->len = X86_BREAKPOINT_LEN_X;
+		if (attr->bp_len == sizeof(long)) {
+			hw->len = X86_BREAKPOINT_LEN_X;
 			return 0;
 		}
 	default:
@@ -283,28 +284,26 @@ static int arch_build_bp_info(struct perf_event *bp)
 	}
 
 	/* Len */
-	info->mask = 0;
-
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = X86_BREAKPOINT_LEN_2;
+		hw->len = X86_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = X86_BREAKPOINT_LEN_4;
+		hw->len = X86_BREAKPOINT_LEN_4;
 		break;
 #ifdef CONFIG_X86_64
 	case HW_BREAKPOINT_LEN_8:
-		info->len = X86_BREAKPOINT_LEN_8;
+		hw->len = X86_BREAKPOINT_LEN_8;
 		break;
 #endif
 	default:
 		/* AMD range breakpoint */
-		if (!is_power_of_2(bp->attr.bp_len))
+		if (!is_power_of_2(attr->bp_len))
 			return -EINVAL;
-		if (bp->attr.bp_addr & (bp->attr.bp_len - 1))
+		if (attr->bp_addr & (attr->bp_len - 1))
 			return -EINVAL;
 
 		if (!boot_cpu_has(X86_FEATURE_BPEXT))
@@ -317,8 +316,8 @@ static int arch_build_bp_info(struct perf_event *bp)
 		 * breakpoints, then we'll have to check for kprobe-blacklisted
 		 * addresses anywhere in the range.
 		 */
-		info->mask = bp->attr.bp_len - 1;
-		info->len = X86_BREAKPOINT_LEN_1;
+		hw->mask = attr->bp_len - 1;
+		hw->len = X86_BREAKPOINT_LEN_1;
 	}
 
 	return 0;
@@ -327,22 +326,23 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
 	int ret;
 
 
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case X86_BREAKPOINT_LEN_1:
 		align = 0;
-		if (info->mask)
-			align = info->mask;
+		if (hw->mask)
+			align = hw->mask;
 		break;
 	case X86_BREAKPOINT_LEN_2:
 		align = 1;
@@ -363,7 +363,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
-	if (info->address & align)
+	if (hw->address & align)
 		return -EINVAL;
 
 	return 0;
-- 
cgit v1.2.3


From 5d5176baed7abf88bb465a128d414fa8748dcab7 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:51 +0200
Subject: perf/arch/powerpc: Implement hw_breakpoint_arch_parse()

Migrate to the new API in order to remove arch_validate_hwbkpt_settings()
that clumsily mixes up architecture validation and commit

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-5-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/include/asm/hw_breakpoint.h |  6 ++++-
 arch/powerpc/kernel/hw_breakpoint.c      | 41 ++++++++++++++++----------------
 2 files changed, 26 insertions(+), 21 deletions(-)

diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 4d0b1bfcdfd0..38ae180610bd 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -52,6 +52,7 @@ struct arch_hw_breakpoint {
 #include <asm/reg.h>
 #include <asm/debug.h>
 
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 struct perf_sample_data;
@@ -61,7 +62,10 @@ struct perf_sample_data;
 extern int hw_breakpoint_slots(int type);
 extern int arch_bp_generic_fields(int type, int *gen_bp_type);
 extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
+#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 						unsigned long val, void *data);
 int arch_install_hw_breakpoint(struct perf_event *bp);
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 899bcec3f3c8..fec8a6773119 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -139,30 +139,31 @@ int arch_bp_generic_fields(int type, int *gen_bp_type)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
 	int ret = -EINVAL, length_max;
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 
 	if (!bp)
 		return ret;
 
-	info->type = HW_BRK_TYPE_TRANSLATE;
-	if (bp->attr.bp_type & HW_BREAKPOINT_R)
-		info->type |= HW_BRK_TYPE_READ;
-	if (bp->attr.bp_type & HW_BREAKPOINT_W)
-		info->type |= HW_BRK_TYPE_WRITE;
-	if (info->type == HW_BRK_TYPE_TRANSLATE)
+	hw->type = HW_BRK_TYPE_TRANSLATE;
+	if (attr->bp_type & HW_BREAKPOINT_R)
+		hw->type |= HW_BRK_TYPE_READ;
+	if (attr->bp_type & HW_BREAKPOINT_W)
+		hw->type |= HW_BRK_TYPE_WRITE;
+	if (hw->type == HW_BRK_TYPE_TRANSLATE)
 		/* must set alteast read or write */
 		return ret;
-	if (!(bp->attr.exclude_user))
-		info->type |= HW_BRK_TYPE_USER;
-	if (!(bp->attr.exclude_kernel))
-		info->type |= HW_BRK_TYPE_KERNEL;
-	if (!(bp->attr.exclude_hv))
-		info->type |= HW_BRK_TYPE_HYP;
-	info->address = bp->attr.bp_addr;
-	info->len = bp->attr.bp_len;
+	if (!attr->exclude_user)
+		hw->type |= HW_BRK_TYPE_USER;
+	if (!attr->exclude_kernel)
+		hw->type |= HW_BRK_TYPE_KERNEL;
+	if (!attr->exclude_hv)
+		hw->type |= HW_BRK_TYPE_HYP;
+	hw->address = attr->bp_addr;
+	hw->len = attr->bp_len;
 
 	/*
 	 * Since breakpoint length can be a maximum of HW_BREAKPOINT_LEN(8)
@@ -176,12 +177,12 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	if (cpu_has_feature(CPU_FTR_DAWR)) {
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
-		if ((bp->attr.bp_addr >> 9) !=
-		    ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 9))
+		if ((attr->bp_addr >> 9) !=
+		    ((attr->bp_addr + attr->bp_len - 1) >> 9))
 			return -EINVAL;
 	}
-	if (info->len >
-	    (length_max - (info->address & HW_BREAKPOINT_ALIGN)))
+	if (hw->len >
+	    (length_max - (hw->address & HW_BREAKPOINT_ALIGN)))
 		return -EINVAL;
 	return 0;
 }
-- 
cgit v1.2.3


From 9d52718cd392a94414f0ce780d9bae3ed518ab34 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:52 +0200
Subject: perf/arch/arm: Implement hw_breakpoint_arch_parse()

Migrate to the new API in order to remove arch_validate_hwbkpt_settings()
that clumsily mixes up architecture validation and commit.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-6-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/hw_breakpoint.h |  6 ++-
 arch/arm/kernel/hw_breakpoint.c      | 71 ++++++++++++++++++------------------
 2 files changed, 41 insertions(+), 36 deletions(-)

diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index d5a0f52c6755..1e02925c11f4 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -111,6 +111,7 @@ static inline void decode_ctrl_reg(u32 reg,
 	asm volatile("mcr p14, 0, %0, " #N "," #M ", " #OP2 : : "r" (VAL));\
 } while (0)
 
+struct perf_event_attr;
 struct notifier_block;
 struct perf_event;
 struct pmu;
@@ -118,7 +119,10 @@ struct pmu;
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type);
 extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
+#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 385dcf45d64b..1d5fbf1d1c67 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -517,42 +517,42 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
-		if ((info->ctrl.type != ARM_BREAKPOINT_EXECUTE)
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE)
 			&& max_watchpoint_len >= 8)
 			break;
 	default:
@@ -565,24 +565,24 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * by the hardware and must be aligned to the appropriate number of
 	 * bytes.
 	 */
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
-	    info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
-	    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+	    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Privilege */
-	info->ctrl.privilege = ARM_BREAKPOINT_USER;
-	if (arch_check_bp_in_kernelspace(info))
-		info->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
+	hw->ctrl.privilege = ARM_BREAKPOINT_USER;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	/* Mismatch */
-	info->ctrl.mismatch = 0;
+	hw->ctrl.mismatch = 0;
 
 	return 0;
 }
@@ -590,9 +590,10 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings.
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret = 0;
 	u32 offset, alignment_mask = 0x3;
 
@@ -601,14 +602,14 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		return -ENODEV;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		goto out;
 
 	/* Check address alignment. */
-	if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+	if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 		alignment_mask = 0x7;
-	offset = info->address & alignment_mask;
+	offset = hw->address & alignment_mask;
 	switch (offset) {
 	case 0:
 		/* Aligned */
@@ -616,19 +617,19 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	case 1:
 	case 2:
 		/* Allow halfword watchpoints and breakpoints. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 			break;
 	case 3:
 		/* Allow single byte watchpoint. */
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 			break;
 	default:
 		ret = -EINVAL;
 		goto out;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	if (is_default_overflow_handler(bp)) {
 		/*
@@ -639,7 +640,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 			return -EINVAL;
 
 		/* We don't allow mismatch breakpoints in kernel space. */
-		if (arch_check_bp_in_kernelspace(info))
+		if (arch_check_bp_in_kernelspace(hw))
 			return -EPERM;
 
 		/*
@@ -654,8 +655,8 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		 * reports them.
 		 */
 		if (!debug_exception_updates_fsr() &&
-		    (info->ctrl.type == ARM_BREAKPOINT_LOAD ||
-		     info->ctrl.type == ARM_BREAKPOINT_STORE))
+		    (hw->ctrl.type == ARM_BREAKPOINT_LOAD ||
+		     hw->ctrl.type == ARM_BREAKPOINT_STORE))
 			return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 8c449753a681517f0e6f877aad8539ac4c71757d Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:53 +0200
Subject: perf/arch/arm64: Implement hw_breakpoint_arch_parse()

Migrate to the new API in order to remove arch_validate_hwbkpt_settings()
that clumsily mixes up architecture validation and commit.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-7-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm64/include/asm/hw_breakpoint.h |  6 ++-
 arch/arm64/kernel/hw_breakpoint.c      | 79 +++++++++++++++++-----------------
 2 files changed, 45 insertions(+), 40 deletions(-)

diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index 9f4a3d48762e..bf9c305daa62 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -119,13 +119,17 @@ static inline void decode_ctrl_reg(u32 reg,
 
 struct task_struct;
 struct notifier_block;
+struct perf_event_attr;
 struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 				  int *gen_len, int *gen_type, int *offset);
 extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
+#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 6a90d12e4ff2..8c9644376326 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -420,53 +420,53 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->ctrl.type = ARM_BREAKPOINT_EXECUTE;
+		hw->ctrl.type = ARM_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->ctrl.type = ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
+		hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_1;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_3:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_3;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_5:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_5;
 		break;
 	case HW_BREAKPOINT_LEN_6:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_6;
 		break;
 	case HW_BREAKPOINT_LEN_7:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_7;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
+		hw->ctrl.len = ARM_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
@@ -477,37 +477,37 @@ static int arch_build_bp_info(struct perf_event *bp)
 	 * AArch32 also requires breakpoints of length 2 for Thumb.
 	 * Watchpoints can be of length 1, 2, 4 or 8 bytes.
 	 */
-	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
+	if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		if (is_compat_bp(bp)) {
-			if (info->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
-			    info->ctrl.len != ARM_BREAKPOINT_LEN_4)
+			if (hw->ctrl.len != ARM_BREAKPOINT_LEN_2 &&
+			    hw->ctrl.len != ARM_BREAKPOINT_LEN_4)
 				return -EINVAL;
-		} else if (info->ctrl.len != ARM_BREAKPOINT_LEN_4) {
+		} else if (hw->ctrl.len != ARM_BREAKPOINT_LEN_4) {
 			/*
 			 * FIXME: Some tools (I'm looking at you perf) assume
 			 *	  that breakpoints should be sizeof(long). This
 			 *	  is nonsense. For now, we fix up the parameter
 			 *	  but we should probably return -EINVAL instead.
 			 */
-			info->ctrl.len = ARM_BREAKPOINT_LEN_4;
+			hw->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		}
 	}
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/*
 	 * Privilege
 	 * Note that we disallow combined EL0/EL1 breakpoints because
 	 * that would complicate the stepping code.
 	 */
-	if (arch_check_bp_in_kernelspace(info))
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
+	if (arch_check_bp_in_kernelspace(hw))
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL1;
 	else
-		info->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
+		hw->ctrl.privilege = AARCH64_BREAKPOINT_EL0;
 
 	/* Enabled? */
-	info->ctrl.enabled = !bp->attr.disabled;
+	hw->ctrl.enabled = !attr->disabled;
 
 	return 0;
 }
@@ -515,14 +515,15 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings.
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	int ret;
 	u64 alignment_mask, offset;
 
 	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
@@ -536,42 +537,42 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * that here.
 	 */
 	if (is_compat_bp(bp)) {
-		if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
+		if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8)
 			alignment_mask = 0x7;
 		else
 			alignment_mask = 0x3;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 		switch (offset) {
 		case 0:
 			/* Aligned */
 			break;
 		case 1:
 			/* Allow single byte watchpoint. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_1)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1)
 				break;
 		case 2:
 			/* Allow halfword watchpoints and breakpoints. */
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_2)
+			if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2)
 				break;
 		default:
 			return -EINVAL;
 		}
 	} else {
-		if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
+		if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE)
 			alignment_mask = 0x3;
 		else
 			alignment_mask = 0x7;
-		offset = info->address & alignment_mask;
+		offset = hw->address & alignment_mask;
 	}
 
-	info->address &= ~alignment_mask;
-	info->ctrl.len <<= offset;
+	hw->address &= ~alignment_mask;
+	hw->ctrl.len <<= offset;
 
 	/*
 	 * Disallow per-task kernel breakpoints since these would
 	 * complicate the stepping code.
 	 */
-	if (info->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
+	if (hw->ctrl.privilege == AARCH64_BREAKPOINT_EL1 && bp->hw.target)
 		return -EINVAL;
 
 	return 0;
-- 
cgit v1.2.3


From 923442895760df69eedfd3e25aa954af99a753e6 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:54 +0200
Subject: perf/arch/sh: Remove "struct arch_hw_breakpoint::name" unused field

This field seem to be unused, perhaps a leftover from old code...

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-8-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sh/include/asm/hw_breakpoint.h | 1 -
 arch/sh/kernel/hw_breakpoint.c      | 7 -------
 2 files changed, 8 deletions(-)

diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index 8a88ed0b3cd7..dae622d9b10b 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -10,7 +10,6 @@
 #include <linux/types.h>
 
 struct arch_hw_breakpoint {
-	char		*name; /* Contains name of the symbol to set bkpt */
 	unsigned long	address;
 	u16		len;
 	u16		type;
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index 38791fefdd0c..c453a0cea3c2 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -247,13 +247,6 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		return ret;
 	}
 
-	/*
-	 * For kernel-addresses, either the address or symbol name can be
-	 * specified.
-	 */
-	if (info->name)
-		info->address = (unsigned long)kallsyms_lookup_name(info->name);
-
 	/*
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
-- 
cgit v1.2.3


From 551624d6fc6b282cdcc3f8ab395cb03da0a38fc7 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:55 +0200
Subject: perf/arch/sh: Implement hw_breakpoint_arch_parse()

Migrate to the new API in order to remove arch_validate_hwbkpt_settings()
that clumsily mixes up architecture validation and commit

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-9-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/sh/include/asm/hw_breakpoint.h |  6 +++++-
 arch/sh/kernel/hw_breakpoint.c      | 37 +++++++++++++++++++------------------
 2 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index dae622d9b10b..867edcc60e8f 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -40,6 +40,7 @@ struct sh_ubc {
 	struct clk	*clk;	/* optional interface clock / MSTP bit */
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct task_struct;
 struct pmu;
@@ -54,7 +55,10 @@ static inline int hw_breakpoint_slots(int type)
 
 /* arch/sh/kernel/hw_breakpoint.c */
 extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
-extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
+extern int hw_breakpoint_arch_parse(struct perf_event *bp,
+				    const struct perf_event_attr *attr,
+				    struct arch_hw_breakpoint *hw);
+#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/sh/kernel/hw_breakpoint.c b/arch/sh/kernel/hw_breakpoint.c
index c453a0cea3c2..d9ff3b42da7c 100644
--- a/arch/sh/kernel/hw_breakpoint.c
+++ b/arch/sh/kernel/hw_breakpoint.c
@@ -173,40 +173,40 @@ int arch_bp_generic_fields(int sh_len, int sh_type,
 	return 0;
 }
 
-static int arch_build_bp_info(struct perf_event *bp)
+static int arch_build_bp_info(struct perf_event *bp,
+			      const struct perf_event_attr *attr,
+			      struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
-	info->address = bp->attr.bp_addr;
+	hw->address = attr->bp_addr;
 
 	/* Len */
-	switch (bp->attr.bp_len) {
+	switch (attr->bp_len) {
 	case HW_BREAKPOINT_LEN_1:
-		info->len = SH_BREAKPOINT_LEN_1;
+		hw->len = SH_BREAKPOINT_LEN_1;
 		break;
 	case HW_BREAKPOINT_LEN_2:
-		info->len = SH_BREAKPOINT_LEN_2;
+		hw->len = SH_BREAKPOINT_LEN_2;
 		break;
 	case HW_BREAKPOINT_LEN_4:
-		info->len = SH_BREAKPOINT_LEN_4;
+		hw->len = SH_BREAKPOINT_LEN_4;
 		break;
 	case HW_BREAKPOINT_LEN_8:
-		info->len = SH_BREAKPOINT_LEN_8;
+		hw->len = SH_BREAKPOINT_LEN_8;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_READ;
+		hw->type = SH_BREAKPOINT_READ;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = SH_BREAKPOINT_WRITE;
+		hw->type = SH_BREAKPOINT_WRITE;
 		break;
 	case HW_BREAKPOINT_W | HW_BREAKPOINT_R:
-		info->type = SH_BREAKPOINT_RW;
+		hw->type = SH_BREAKPOINT_RW;
 		break;
 	default:
 		return -EINVAL;
@@ -218,19 +218,20 @@ static int arch_build_bp_info(struct perf_event *bp)
 /*
  * Validate the arch-specific HW Breakpoint register settings
  */
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
 	unsigned int align;
 	int ret;
 
-	ret = arch_build_bp_info(bp);
+	ret = arch_build_bp_info(bp, attr, hw);
 	if (ret)
 		return ret;
 
 	ret = -EINVAL;
 
-	switch (info->len) {
+	switch (hw->len) {
 	case SH_BREAKPOINT_LEN_1:
 		align = 0;
 		break;
@@ -251,7 +252,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 	 * Check that the low-order bits of the address are appropriate
 	 * for the alignment implied by len.
 	 */
-	if (info->address & align)
+	if (hw->address & align)
 		return -EINVAL;
 
 	return 0;
-- 
cgit v1.2.3


From ac46c7fddef702dadae18c1fc932530cd31cf9cd Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:56 +0200
Subject: perf/arch/xtensa: Implement hw_breakpoint_arch_parse()

Migrate to the new API in order to remove arch_validate_hwbkpt_settings()
that clumsily mixes up architecture validation and commit

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-10-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/xtensa/include/asm/hw_breakpoint.h |  6 +++++-
 arch/xtensa/kernel/hw_breakpoint.c      | 33 ++++++++++++---------------------
 2 files changed, 17 insertions(+), 22 deletions(-)

diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index 2525bf6816a6..f347c2132e6b 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -30,13 +30,17 @@ struct arch_hw_breakpoint {
 	u16 type;
 };
 
+struct perf_event_attr;
 struct perf_event;
 struct pt_regs;
 struct task_struct;
 
 int hw_breakpoint_slots(int type);
 int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
-int arch_validate_hwbkpt_settings(struct perf_event *bp);
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw);
+#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data);
 
diff --git a/arch/xtensa/kernel/hw_breakpoint.c b/arch/xtensa/kernel/hw_breakpoint.c
index 6e34c3848885..c2e387c19cda 100644
--- a/arch/xtensa/kernel/hw_breakpoint.c
+++ b/arch/xtensa/kernel/hw_breakpoint.c
@@ -47,50 +47,41 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw)
 /*
  * Construct an arch_hw_breakpoint from a perf_event.
  */
-static int arch_build_bp_info(struct perf_event *bp)
+int hw_breakpoint_arch_parse(struct perf_event *bp,
+			     const struct perf_event_attr *attr,
+			     struct arch_hw_breakpoint *hw)
 {
-	struct arch_hw_breakpoint *info = counter_arch_bp(bp);
-
 	/* Type */
-	switch (bp->attr.bp_type) {
+	switch (attr->bp_type) {
 	case HW_BREAKPOINT_X:
-		info->type = XTENSA_BREAKPOINT_EXECUTE;
+		hw->type = XTENSA_BREAKPOINT_EXECUTE;
 		break;
 	case HW_BREAKPOINT_R:
-		info->type = XTENSA_BREAKPOINT_LOAD;
+		hw->type = XTENSA_BREAKPOINT_LOAD;
 		break;
 	case HW_BREAKPOINT_W:
-		info->type = XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_STORE;
 		break;
 	case HW_BREAKPOINT_RW:
-		info->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
+		hw->type = XTENSA_BREAKPOINT_LOAD | XTENSA_BREAKPOINT_STORE;
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	/* Len */
-	info->len = bp->attr.bp_len;
-	if (info->len < 1 || info->len > 64 || !is_power_of_2(info->len))
+	hw->len = attr->bp_len;
+	if (hw->len < 1 || hw->len > 64 || !is_power_of_2(hw->len))
 		return -EINVAL;
 
 	/* Address */
-	info->address = bp->attr.bp_addr;
-	if (info->address & (info->len - 1))
+	hw->address = attr->bp_addr;
+	if (hw->address & (hw->len - 1))
 		return -EINVAL;
 
 	return 0;
 }
 
-int arch_validate_hwbkpt_settings(struct perf_event *bp)
-{
-	int ret;
-
-	/* Build the arch_hw_breakpoint. */
-	ret = arch_build_bp_info(bp);
-	return ret;
-}
-
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data)
 {
-- 
cgit v1.2.3


From cffbb3bd444bc95186b6ab0ed3bf1d5bcf4aa620 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:57 +0200
Subject: perf/hw_breakpoint: Remove default hw_breakpoint_arch_parse()

All architectures have implemented it, we can now remove the poor weak
version.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-11-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/hw_breakpoint.h     |  1 -
 arch/arm64/include/asm/hw_breakpoint.h   |  1 -
 arch/powerpc/include/asm/hw_breakpoint.h |  1 -
 arch/sh/include/asm/hw_breakpoint.h      |  1 -
 arch/x86/include/asm/hw_breakpoint.h     |  1 -
 arch/xtensa/include/asm/hw_breakpoint.h  |  1 -
 kernel/events/hw_breakpoint.c            | 17 -----------------
 7 files changed, 23 deletions(-)

diff --git a/arch/arm/include/asm/hw_breakpoint.h b/arch/arm/include/asm/hw_breakpoint.h
index 1e02925c11f4..ac54c06764e6 100644
--- a/arch/arm/include/asm/hw_breakpoint.h
+++ b/arch/arm/include/asm/hw_breakpoint.h
@@ -122,7 +122,6 @@ extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_arch_parse(struct perf_event *bp,
 				    const struct perf_event_attr *attr,
 				    struct arch_hw_breakpoint *hw);
-#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/arm64/include/asm/hw_breakpoint.h b/arch/arm64/include/asm/hw_breakpoint.h
index bf9c305daa62..6a53e59ced95 100644
--- a/arch/arm64/include/asm/hw_breakpoint.h
+++ b/arch/arm64/include/asm/hw_breakpoint.h
@@ -129,7 +129,6 @@ extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_arch_parse(struct perf_event *bp,
 				    const struct perf_event_attr *attr,
 				    struct arch_hw_breakpoint *hw);
-#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/powerpc/include/asm/hw_breakpoint.h b/arch/powerpc/include/asm/hw_breakpoint.h
index 38ae180610bd..27d6e3c8fde9 100644
--- a/arch/powerpc/include/asm/hw_breakpoint.h
+++ b/arch/powerpc/include/asm/hw_breakpoint.h
@@ -65,7 +65,6 @@ extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_arch_parse(struct perf_event *bp,
 				    const struct perf_event_attr *attr,
 				    struct arch_hw_breakpoint *hw);
-#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 						unsigned long val, void *data);
 int arch_install_hw_breakpoint(struct perf_event *bp);
diff --git a/arch/sh/include/asm/hw_breakpoint.h b/arch/sh/include/asm/hw_breakpoint.h
index 867edcc60e8f..199d17b765f2 100644
--- a/arch/sh/include/asm/hw_breakpoint.h
+++ b/arch/sh/include/asm/hw_breakpoint.h
@@ -58,7 +58,6 @@ extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_arch_parse(struct perf_event *bp,
 				    const struct perf_event_attr *attr,
 				    struct arch_hw_breakpoint *hw);
-#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h
index 6c88e8e22678..a1f0e90d0818 100644
--- a/arch/x86/include/asm/hw_breakpoint.h
+++ b/arch/x86/include/asm/hw_breakpoint.h
@@ -57,7 +57,6 @@ extern int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 extern int hw_breakpoint_arch_parse(struct perf_event *bp,
 				    const struct perf_event_attr *attr,
 				    struct arch_hw_breakpoint *hw);
-#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 					   unsigned long val, void *data);
 
diff --git a/arch/xtensa/include/asm/hw_breakpoint.h b/arch/xtensa/include/asm/hw_breakpoint.h
index f347c2132e6b..9f119c1ca0b5 100644
--- a/arch/xtensa/include/asm/hw_breakpoint.h
+++ b/arch/xtensa/include/asm/hw_breakpoint.h
@@ -40,7 +40,6 @@ int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw);
 int hw_breakpoint_arch_parse(struct perf_event *bp,
 			     const struct perf_event_attr *attr,
 			     struct arch_hw_breakpoint *hw);
-#define hw_breakpoint_arch_parse hw_breakpoint_arch_parse
 int hw_breakpoint_exceptions_notify(struct notifier_block *unused,
 				    unsigned long val, void *data);
 
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 89fe94c9214c..e7bc8d0a5972 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -400,23 +400,6 @@ int dbg_release_bp_slot(struct perf_event *bp)
 	return 0;
 }
 
-#ifndef hw_breakpoint_arch_parse
-int hw_breakpoint_arch_parse(struct perf_event *bp,
-			     const struct perf_event_attr *attr,
-			     struct arch_hw_breakpoint *hw)
-{
-	int err;
-
-	err = arch_validate_hwbkpt_settings(bp);
-	if (err)
-		return err;
-
-	*hw = bp->hw.info;
-
-	return 0;
-}
-#endif
-
 static int hw_breakpoint_parse(struct perf_event *bp,
 			       const struct perf_event_attr *attr,
 			       struct arch_hw_breakpoint *hw)
-- 
cgit v1.2.3


From cb8b78815b68b048303f55c276d2aef147e8f2e7 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:58 +0200
Subject: perf/hw_breakpoint: Pass new breakpoint type to
 modify_breakpoint_slot()

We soon won't be able to rely on bp->attr anymore to get the new
type of the modifying breakpoint because the new attributes are going
to be copied only once we successfully modified the breakpoint slot.

This will fix the current misdesigned layout where the new attr are
copied to the modifying breakpoint before we actually know if the
modification will be validated.

In order to prepare for that, allow modify_breakpoint_slot() to take
the new breakpoint type.

Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-12-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/events/hw_breakpoint.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index e7bc8d0a5972..71387703b5f1 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -345,13 +345,13 @@ void release_bp_slot(struct perf_event *bp)
 	mutex_unlock(&nr_bp_mutex);
 }
 
-static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int __modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int err;
 
 	__release_bp_slot(bp, old_type);
 
-	err = __reserve_bp_slot(bp, bp->attr.bp_type);
+	err = __reserve_bp_slot(bp, new_type);
 	if (err) {
 		/*
 		 * Reserve the old_type slot back in case
@@ -367,12 +367,12 @@ static int __modify_bp_slot(struct perf_event *bp, u64 old_type)
 	return err;
 }
 
-static int modify_bp_slot(struct perf_event *bp, u64 old_type)
+static int modify_bp_slot(struct perf_event *bp, u64 old_type, u64 new_type)
 {
 	int ret;
 
 	mutex_lock(&nr_bp_mutex);
-	ret = __modify_bp_slot(bp, old_type);
+	ret = __modify_bp_slot(bp, old_type, new_type);
 	mutex_unlock(&nr_bp_mutex);
 	return ret;
 }
@@ -481,7 +481,7 @@ modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *a
 
 	err = hw_breakpoint_parse(bp, attr, &hw);
 	if (!err && modify)
-		err = modify_bp_slot(bp, old_type);
+		err = modify_bp_slot(bp, old_type, bp->attr.bp_type);
 
 	if (err) {
 		bp->attr.bp_addr = old_addr;
-- 
cgit v1.2.3


From 26c6ccdf5c06aa83bb78518c72cb287f043db3df Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Tue, 26 Jun 2018 04:58:59 +0200
Subject: perf/hw_breakpoint: Clean up and consolidate
 modify_user_hw_breakpoint_check()

Remove the dance around old and new attributes. Just don't modify the
previous breakpoint at all until we have verified everything.

Original-patch-by: Andy Lutomirski <luto@kernel.org>
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Zankel <chris@zankel.net>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Joel Fernandes <joel.opensrc@gmail.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rich Felker <dalias@libc.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Link: http://lkml.kernel.org/r/1529981939-8231-13-git-send-email-frederic@kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/events/hw_breakpoint.c | 44 ++++++++++++++++++++++++-------------------
 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index 71387703b5f1..b3814fce5ecb 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -461,37 +461,43 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
+static void hw_breakpoint_copy_attr(struct perf_event_attr *to,
+				    struct perf_event_attr *from)
+{
+	to->bp_addr = from->bp_addr;
+	to->bp_type = from->bp_type;
+	to->bp_len  = from->bp_len;
+	to->disabled = from->disabled;
+}
+
 int
 modify_user_hw_breakpoint_check(struct perf_event *bp, struct perf_event_attr *attr,
 			        bool check)
 {
-	u64 old_addr = bp->attr.bp_addr;
-	u64 old_len  = bp->attr.bp_len;
-	int old_type = bp->attr.bp_type;
-	bool modify  = attr->bp_type != old_type;
 	struct arch_hw_breakpoint hw;
-	int err = 0;
+	int err;
 
-	bp->attr.bp_addr = attr->bp_addr;
-	bp->attr.bp_type = attr->bp_type;
-	bp->attr.bp_len  = attr->bp_len;
+	err = hw_breakpoint_parse(bp, attr, &hw);
+	if (err)
+		return err;
 
-	if (check && memcmp(&bp->attr, attr, sizeof(*attr)))
-		return -EINVAL;
+	if (check) {
+		struct perf_event_attr old_attr;
 
-	err = hw_breakpoint_parse(bp, attr, &hw);
-	if (!err && modify)
-		err = modify_bp_slot(bp, old_type, bp->attr.bp_type);
+		old_attr = bp->attr;
+		hw_breakpoint_copy_attr(&old_attr, attr);
+		if (memcmp(&old_attr, attr, sizeof(*attr)))
+			return -EINVAL;
+	}
 
-	if (err) {
-		bp->attr.bp_addr = old_addr;
-		bp->attr.bp_type = old_type;
-		bp->attr.bp_len  = old_len;
-		return err;
+	if (bp->attr.bp_type != attr->bp_type) {
+		err = modify_bp_slot(bp, bp->attr.bp_type, attr->bp_type);
+		if (err)
+			return err;
 	}
 
+	hw_breakpoint_copy_attr(&bp->attr, attr);
 	bp->hw.info = hw;
-	bp->attr.disabled = attr->disabled;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 3a358e22844d4a88d872891c77d7eee4fbca5f37 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 21 Jun 2018 20:54:42 +0200
Subject: w1: Allow compile test of GPIO consumers if !GPIOLIB

The GPIO subsystem provides dummy GPIO consumer functions if GPIOLIB is
not enabled. Hence drivers that depend on GPIOLIB, but use GPIO consumer
functionality only, can still be compiled if GPIOLIB is not enabled.

Relax the dependency on GPIOLIB if COMPILE_TEST is enabled, where
appropriate.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Evgeniy Polyakov <zbr@ioremap.net>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/w1/masters/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/w1/masters/Kconfig b/drivers/w1/masters/Kconfig
index 1708b2300c7a..00827d2897b5 100644
--- a/drivers/w1/masters/Kconfig
+++ b/drivers/w1/masters/Kconfig
@@ -49,7 +49,7 @@ config W1_MASTER_DS1WM
 
 config W1_MASTER_GPIO
 	tristate "GPIO 1-wire busmaster"
-	depends on GPIOLIB
+	depends on GPIOLIB || COMPILE_TEST
 	help
 	  Say Y here if you want to communicate with your 1-wire devices using
 	  GPIO pins. This driver uses the GPIO API to control the wire.
-- 
cgit v1.2.3


From eb7692b4f3b315f7ec1bdb01a0db4b1dbb5c2a32 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 18 Jun 2018 01:00:48 +0200
Subject: pinctrl: gemini: Mask properly

Some logical error in the gemini pin control driver made
it not mask and write properly for the GMAC.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-gemini.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pinctrl/pinctrl-gemini.c b/drivers/pinctrl/pinctrl-gemini.c
index 8c9970ae8505..fa7d998e1d5a 100644
--- a/drivers/pinctrl/pinctrl-gemini.c
+++ b/drivers/pinctrl/pinctrl-gemini.c
@@ -1696,6 +1696,7 @@ static const struct gemini_pin_group gemini_3516_pin_groups[] = {
 		.name = "gmii_gmac0_grp",
 		.pins = gmii_gmac0_3516_pins,
 		.num_pins = ARRAY_SIZE(gmii_gmac0_3516_pins),
+		.mask = GEMINI_GMAC_IOSEL_MASK,
 		.driving_mask = GENMASK(17, 16),
 	},
 	{
@@ -1703,6 +1704,7 @@ static const struct gemini_pin_group gemini_3516_pin_groups[] = {
 		.pins = gmii_gmac1_3516_pins,
 		.num_pins = ARRAY_SIZE(gmii_gmac1_3516_pins),
 		/* Bring out RGMII on the GMAC1 pins */
+		.mask = GEMINI_GMAC_IOSEL_MASK,
 		.value = GEMINI_GMAC_IOSEL_GMAC0_GMAC1_RGMII,
 		.driving_mask = GENMASK(19, 18),
 	},
-- 
cgit v1.2.3


From a63d3bd230772b307c6595469e615d44a1dacdab Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <contact@tzimmermann.org>
Date: Mon, 25 Jun 2018 17:21:48 +0200
Subject: drm/gma500: Replace drm_gem_object_unreference_unlocked with put
 function

This patch unifies the naming of DRM functions for reference counting
of struct drm_gem_object. The resulting code is more aligned with the
rest of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <contact@tzimmermann.org>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625152148.29555-1-contact@tzimmermann.org
---
 drivers/gpu/drm/gma500/framebuffer.c | 2 +-
 drivers/gpu/drm/gma500/gem.c         | 2 +-
 drivers/gpu/drm/gma500/gma_display.c | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/gma500/framebuffer.c b/drivers/gpu/drm/gma500/framebuffer.c
index 8fa4ef192c1e..2f00a37684a2 100644
--- a/drivers/gpu/drm/gma500/framebuffer.c
+++ b/drivers/gpu/drm/gma500/framebuffer.c
@@ -517,7 +517,7 @@ static int psb_fbdev_destroy(struct drm_device *dev, struct psb_fbdev *fbdev)
 	drm_framebuffer_cleanup(&psbfb->base);
 
 	if (psbfb->base.obj[0])
-		drm_gem_object_unreference_unlocked(psbfb->base.obj[0]);
+		drm_gem_object_put_unlocked(psbfb->base.obj[0]);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/gma500/gem.c b/drivers/gpu/drm/gma500/gem.c
index 131239759a75..913bf4c256fa 100644
--- a/drivers/gpu/drm/gma500/gem.c
+++ b/drivers/gpu/drm/gma500/gem.c
@@ -93,7 +93,7 @@ int psb_gem_create(struct drm_file *file, struct drm_device *dev, u64 size,
 		return ret;
 	}
 	/* We have the initial and handle reference but need only one now */
-	drm_gem_object_unreference_unlocked(&r->gem);
+	drm_gem_object_put_unlocked(&r->gem);
 	*handlep = handle;
 	return 0;
 }
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index c8f071c47daf..015dc9f9348d 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -353,7 +353,7 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 			gt = container_of(gma_crtc->cursor_obj,
 					  struct gtt_range, gem);
 			psb_gtt_unpin(gt);
-			drm_gem_object_unreference_unlocked(gma_crtc->cursor_obj);
+			drm_gem_object_put_unlocked(gma_crtc->cursor_obj);
 			gma_crtc->cursor_obj = NULL;
 		}
 		return 0;
@@ -429,7 +429,7 @@ int gma_crtc_cursor_set(struct drm_crtc *crtc,
 	if (gma_crtc->cursor_obj) {
 		gt = container_of(gma_crtc->cursor_obj, struct gtt_range, gem);
 		psb_gtt_unpin(gt);
-		drm_gem_object_unreference_unlocked(gma_crtc->cursor_obj);
+		drm_gem_object_put_unlocked(gma_crtc->cursor_obj);
 	}
 
 	gma_crtc->cursor_obj = obj;
@@ -437,7 +437,7 @@ unlock:
 	return ret;
 
 unref_cursor:
-	drm_gem_object_unreference_unlocked(obj);
+	drm_gem_object_put_unlocked(obj);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 5f15e257e1e2bd17830fdf32ac715ca4a29a504f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 25 Jun 2018 10:48:13 +0300
Subject: mlxsw: spectrum_router: Propagate extack to .fid_get()

In the follow-up patch, mlxsw_sp_rif_vlan_fid_get() will be changed in a
way that could fail. Give that function a possibility to explain the
failure through extack.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 6aaaf3d9ba31..05c52e486330 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -163,7 +163,8 @@ struct mlxsw_sp_rif_ops {
 		      const struct mlxsw_sp_rif_params *params);
 	int (*configure)(struct mlxsw_sp_rif *rif);
 	void (*deconfigure)(struct mlxsw_sp_rif *rif);
-	struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif);
+	struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif,
+					 struct netlink_ext_ack *extack);
 };
 
 static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
@@ -6162,7 +6163,7 @@ mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 	rif->ops = ops;
 
 	if (ops->fid_get) {
-		fid = ops->fid_get(rif);
+		fid = ops->fid_get(rif, extack);
 		if (IS_ERR(fid)) {
 			err = PTR_ERR(fid);
 			goto err_fid_get;
@@ -6267,7 +6268,7 @@ mlxsw_sp_port_vlan_router_join(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan,
 	}
 
 	/* FID was already created, just take a reference */
-	fid = rif->ops->fid_get(rif);
+	fid = rif->ops->fid_get(rif, extack);
 	err = mlxsw_sp_fid_port_vid_map(fid, mlxsw_sp_port, vid);
 	if (err)
 		goto err_fid_port_vid_map;
@@ -6775,7 +6776,8 @@ static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif)
 }
 
 static struct mlxsw_sp_fid *
-mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_subport_fid_get(struct mlxsw_sp_rif *rif,
+			     struct netlink_ext_ack *extack)
 {
 	return mlxsw_sp_fid_rfid_get(rif->mlxsw_sp, rif->rif_index);
 }
@@ -6865,7 +6867,8 @@ static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif)
 }
 
 static struct mlxsw_sp_fid *
-mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
+			  struct netlink_ext_ack *extack)
 {
 	u16 vid = is_vlan_dev(rif->dev) ? vlan_dev_vlan_id(rif->dev) : 1;
 
@@ -6937,7 +6940,8 @@ static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif)
 }
 
 static struct mlxsw_sp_fid *
-mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif)
+mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif,
+			 struct netlink_ext_ack *extack)
 {
 	return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex);
 }
-- 
cgit v1.2.3


From e6f1960ae6c736b7bb65a012809eb7c3654b42d7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 25 Jun 2018 10:48:14 +0300
Subject: mlxsw: spectrum_router: Allocate FID according to PVID

For bridge netdevices, instead of assuming that the router traffic is on
VLAN 1, look at the bridge PVID.

This patch assumes that the PVID doesn't change after the router
interface is created (i.e. after the IP address is assigned).

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 05c52e486330..c7243d3f91df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6870,7 +6870,20 @@ static struct mlxsw_sp_fid *
 mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 			  struct netlink_ext_ack *extack)
 {
-	u16 vid = is_vlan_dev(rif->dev) ? vlan_dev_vlan_id(rif->dev) : 1;
+	u16 vid;
+	int err;
+
+	if (is_vlan_dev(rif->dev)) {
+		vid = vlan_dev_vlan_id(rif->dev);
+	} else {
+		err = br_vlan_get_pvid(rif->dev, &vid);
+		if (!vid)
+			err = -EINVAL;
+		if (err) {
+			NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID");
+			return ERR_PTR(err);
+		}
+	}
 
 	return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid);
 }
-- 
cgit v1.2.3


From 0c41292bc5ffb4e514652731dfeda1552e2df120 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 25 Jun 2018 10:48:15 +0300
Subject: mlxsw: spectrum_router: Publish mlxsw_sp_rif_find_by_dev()

In order to guard against removal of a PVID for which a FID was
allocated, spectrum_switchdev needs to first determine whether there is
a RIF associated with a given bridge. To that end, publish a preexisting
function mlxsw_sp_rif_find_by_dev().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 6 +-----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h | 2 ++
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index c7243d3f91df..880092c6c94c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -343,10 +343,6 @@ static void mlxsw_sp_rif_counters_free(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_rif_counter_free(mlxsw_sp, rif, MLXSW_SP_RIF_COUNTER_EGRESS);
 }
 
-static struct mlxsw_sp_rif *
-mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev);
-
 #define MLXSW_SP_PREFIX_COUNT (sizeof(struct in6_addr) * BITS_PER_BYTE + 1)
 
 struct mlxsw_sp_prefix_usage {
@@ -5968,7 +5964,7 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-static struct mlxsw_sp_rif *
+struct mlxsw_sp_rif *
 mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
 			 const struct net_device *dev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index a01edcf56797..5a258b1db03c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -66,6 +66,8 @@ struct mlxsw_sp_neigh_entry;
 struct mlxsw_sp_nexthop;
 struct mlxsw_sp_ipip_entry;
 
+struct mlxsw_sp_rif *mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
+					      const struct net_device *dev);
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_rif_index(const struct mlxsw_sp_rif *rif);
-- 
cgit v1.2.3


From a28b1ebef72b19bf40fbceacdf33212d820728dd Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 25 Jun 2018 10:48:16 +0300
Subject: mlxsw: spectrum_router: Add mlxsw_sp_rif_fid()

In order to allow querying of the VID for which a RIF was created, add
a new function that returns a FID for a given RIF.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 5 +++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 880092c6c94c..88bd27ace8d9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6122,6 +6122,11 @@ const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif)
 	return rif->dev;
 }
 
+struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif)
+{
+	return rif->fid;
+}
+
 static struct mlxsw_sp_rif *
 mlxsw_sp_rif_create(struct mlxsw_sp *mlxsw_sp,
 		    const struct mlxsw_sp_rif_params *params,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 5a258b1db03c..52e25695625c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -77,6 +77,7 @@ u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);
 u8 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
 const struct net_device *mlxsw_sp_rif_dev(const struct mlxsw_sp_rif *rif);
+struct mlxsw_sp_fid *mlxsw_sp_rif_fid(const struct mlxsw_sp_rif *rif);
 int mlxsw_sp_rif_counter_value_get(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_rif *rif,
 				   enum mlxsw_sp_rif_counter_dir dir,
-- 
cgit v1.2.3


From 567ad1a2bb6c1e2ca9644d1b47263b7d5e1ff900 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 25 Jun 2018 10:48:17 +0300
Subject: mlxsw: spectrum_switchdev: Ban PVID change if bridge has a RIF

When traffic passes through a router port, it needs to be assigned a FID
for ASIC to forward correctly. For bridges, this FID used to be the one
corresponding to VLAN 1. In a previous patch, this was changed to
instead use the PVID at the time that the RIF is created. This patch
guards PVID changes after the RIF was introduced.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 47 +++++++++++++++++++++-
 1 file changed, 45 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index eea5666a86b2..da94e1eb9e16 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1135,6 +1135,39 @@ err_port_vlan_set:
 	return err;
 }
 
+static int
+mlxsw_sp_br_ban_rif_pvid_change(struct mlxsw_sp *mlxsw_sp,
+				const struct net_device *br_dev,
+				const struct switchdev_obj_port_vlan *vlan)
+{
+	struct mlxsw_sp_rif *rif;
+	struct mlxsw_sp_fid *fid;
+	u16 pvid;
+	u16 vid;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev);
+	if (!rif)
+		return 0;
+	fid = mlxsw_sp_rif_fid(rif);
+	pvid = mlxsw_sp_fid_8021q_vid(fid);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		if (vlan->flags & BRIDGE_VLAN_INFO_PVID) {
+			if (vid != pvid) {
+				netdev_err(br_dev, "Can't change PVID, it's used by router interface\n");
+				return -EBUSY;
+			}
+		} else {
+			if (vid == pvid) {
+				netdev_err(br_dev, "Can't remove PVID, it's used by router interface\n");
+				return -EBUSY;
+			}
+		}
+	}
+
+	return 0;
+}
+
 static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 				   const struct switchdev_obj_port_vlan *vlan,
 				   struct switchdev_trans *trans)
@@ -1146,8 +1179,18 @@ static int mlxsw_sp_port_vlans_add(struct mlxsw_sp_port *mlxsw_sp_port,
 	struct mlxsw_sp_bridge_port *bridge_port;
 	u16 vid;
 
-	if (netif_is_bridge_master(orig_dev))
-		return -EOPNOTSUPP;
+	if (netif_is_bridge_master(orig_dev)) {
+		int err = 0;
+
+		if ((vlan->flags & BRIDGE_VLAN_INFO_BRENTRY) &&
+		    br_vlan_enabled(orig_dev) &&
+		    switchdev_trans_ph_prepare(trans))
+			err = mlxsw_sp_br_ban_rif_pvid_change(mlxsw_sp,
+							      orig_dev, vlan);
+		if (!err)
+			err = -EOPNOTSUPP;
+		return err;
+	}
 
 	if (switchdev_trans_ph_prepare(trans))
 		return 0;
-- 
cgit v1.2.3


From 5b1e7f9ebd5653dc4cc026671ca07d8ab2419a99 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 25 Jun 2018 10:48:18 +0300
Subject: selftests: forwarding: Test routed bridge interface

Add test for cases where bridge itself acts as a router interface, with
front panel port attached to the bridge in question.

In the first test (router_bridge.sh), VLAN memberships are not
configured in any way, and everything uses default PVID of 1. Thus
traffic in $h1 and $h2 is untagged. This test ensures that the previous
patches didn't break a currently working scenario.

In the second test (router_bridge_vlan.sh), a VLAN 555 pvid untagged is
added to the bridge CPU port, with that VLAN leaving the bridge tagged
through its sole member port. The traffic is therefore expected to come
out tagged at $h1. This tests the fix introduced in the previous
patches.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/router_bridge.sh      | 113 ++++++++++++++++++
 .../selftests/net/forwarding/router_bridge_vlan.sh | 132 +++++++++++++++++++++
 2 files changed, 245 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge.sh
 create mode 100755 tools/testing/selftests/net/forwarding/router_bridge_vlan.sh

diff --git a/tools/testing/selftests/net/forwarding/router_bridge.sh b/tools/testing/selftests/net/forwarding/router_bridge.sh
new file mode 100755
index 000000000000..ebc596a272f7
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge.sh
@@ -0,0 +1,113 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+	ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:2::/64 vrf v$h1
+	ip -4 route del 192.0.2.128/28 vrf v$h1
+	simple_if_fini $h1 192.0.2.1/28 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+	ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:1::/64 vrf v$h2
+	ip -4 route del 192.0.2.0/28 vrf v$h2
+	simple_if_fini $h2 192.0.2.130/28 2001:db8:2::2/64
+}
+
+router_create()
+{
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 up
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+	__addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+	ip link set dev $swp2 up
+	__addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+	__addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+	ip link set dev $swp2 down
+
+	__addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
diff --git a/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
new file mode 100755
index 000000000000..fef88eb4b873
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_bridge_vlan.sh
@@ -0,0 +1,132 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	vlan
+"
+NUM_NETIFS=4
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1
+	vlan_create $h1 555 v$h1 192.0.2.1/28 2001:db8:1::1/64
+	ip -4 route add 192.0.2.128/28 vrf v$h1 nexthop via 192.0.2.2
+	ip -6 route add 2001:db8:2::/64 vrf v$h1 nexthop via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip -6 route del 2001:db8:2::/64 vrf v$h1
+	ip -4 route del 192.0.2.128/28 vrf v$h1
+	vlan_destroy $h1 555
+	simple_if_fini $h1
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.130/28 2001:db8:2::2/64
+	ip -4 route add 192.0.2.0/28 vrf v$h2 nexthop via 192.0.2.129
+	ip -6 route add 2001:db8:1::/64 vrf v$h2 nexthop via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip -6 route del 2001:db8:1::/64 vrf v$h2
+	ip -4 route del 192.0.2.0/28 vrf v$h2
+	simple_if_fini $h2 192.0.2.130/28
+}
+
+router_create()
+{
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 up
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+
+	bridge vlan add dev br1 vid 555 self pvid untagged
+	bridge vlan add dev $swp1 vid 555
+
+	__addr_add_del br1 add 192.0.2.2/28 2001:db8:1::2/64
+
+	ip link set dev $swp2 up
+	__addr_add_del $swp2 add 192.0.2.129/28 2001:db8:2::1/64
+}
+
+router_destroy()
+{
+	__addr_add_del $swp2 del 192.0.2.129/28 2001:db8:2::1/64
+	ip link set dev $swp2 down
+
+	__addr_add_del br1 del 192.0.2.2/28 2001:db8:1::2/64
+	ip link set dev $swp1 down
+	ip link set dev $swp1 nomaster
+
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+vlan()
+{
+	RET=0
+
+	bridge vlan add dev br1 vid 333 self
+	check_err $? "Can't add a non-PVID VLAN"
+	bridge vlan del dev br1 vid 333 self
+	check_err $? "Can't remove a non-PVID VLAN"
+
+	log_test "vlan"
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.130
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 525280552b21722d2dfb48a7020dcd56f9e2023c Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 21 Jun 2018 21:44:49 +0300
Subject: drm/i915/ddi: Get AUX power domain for DP main link too
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

So far we got an AUX power domain reference only for the duration of DP
AUX transfers. However, the following suggests that we also need these
for main link functionality:
- The specification doesn't state whether it's needed or not for main
  link functionality, but suggests that these power wells need to be
  enabled already during display core initialization (Sequences to
  Initialize Display).
- For PSR we need to keep the AUX power well enabled.
- On ICL combo PHY ports (non-TC) the AUX power well is needed for
  link training too: while the port is enabled with a DP link training
  test pattern trying to toggle the AUX power well will time out.
- On ICL MG PHY ports (TC) the AUX power well is needed also for main
  link functionality (both in DP and HDMI modes).
- Windows enables these power wells both for main and AUX lane
  functionality.

Based on the above take an AUX power reference for main link
functionality too. This makes a difference only on GEN10+ (GLK+)
platforms, where we have separate port specific AUX power wells.

For PSR we still need to distinguish between port A and the other
ports, since on port A DC states must stay enabled for main link
functionality, but DC states must be disabled for driver initiated
AUX transfers. So re-use the corresponding helper from intel_psr.c.

Since we take now a reference for main link functionality on all DP
ports we can forgo taking the separate power ref for PSR functionality.

v2:
- Make sure DC states stay enabled when taking the ref on port A.
  (Ville)

v3: (Ville)
- Fix comment about logic for encoders without a crtc state and
  add FIXME note for a simplification to avoid calling get_power_domains
  in such cases.
- Use intel_crtc_has_dp_encoder() instead !intel_crtc_has_type(HDMI).

Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
[Clarified code comments in intel_ddi_main_link_aux_domain() and
 intel_ddi_get_power_domains() (Imre)]
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180621184449.26634-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_ddi.c        | 54 ++++++++++++++++++++++++++++++---
 drivers/gpu/drm/i915/intel_display.c    | 12 +++++++-
 drivers/gpu/drm/i915/intel_drv.h        |  3 +-
 drivers/gpu/drm/i915/intel_psr.c        | 41 -------------------------
 drivers/gpu/drm/i915/intel_runtime_pm.c |  1 +
 5 files changed, 64 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 044fe1fb9872..0319825b725b 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1983,15 +1983,55 @@ out:
 	return ret;
 }
 
-static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder)
+static inline enum intel_display_power_domain
+intel_ddi_main_link_aux_domain(struct intel_dp *intel_dp)
+{
+	/* CNL HW requires corresponding AUX IOs to be powered up for PSR with
+	 * DC states enabled at the same time, while for driver initiated AUX
+	 * transfers we need the same AUX IOs to be powered but with DC states
+	 * disabled. Accordingly use the AUX power domain here which leaves DC
+	 * states enabled.
+	 * However, for non-A AUX ports the corresponding non-EDP transcoders
+	 * would have already enabled power well 2 and DC_OFF. This means we can
+	 * acquire a wider POWER_DOMAIN_AUX_{B,C,D,F} reference instead of a
+	 * specific AUX_IO reference without powering up any extra wells.
+	 * Note that PSR is enabled only on Port A even though this function
+	 * returns the correct domain for other ports too.
+	 */
+	return intel_dp->aux_ch == AUX_CH_A ? POWER_DOMAIN_AUX_IO_A :
+					      intel_dp->aux_power_domain;
+}
+
+static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
+				       struct intel_crtc_state *crtc_state)
 {
 	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
 	enum pipe pipe;
+	u64 domains;
 
-	if (intel_ddi_get_hw_state(encoder, &pipe))
-		return BIT_ULL(dig_port->ddi_io_power_domain);
+	if (!intel_ddi_get_hw_state(encoder, &pipe))
+		return 0;
 
-	return 0;
+	domains = BIT_ULL(dig_port->ddi_io_power_domain);
+	if (!crtc_state)
+		return domains;
+
+	/*
+	 * TODO: Add support for MST encoders. Atm, the following should never
+	 * happen since this function will be called only for the primary
+	 * encoder which doesn't have its own pipe/crtc_state.
+	 */
+	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
+		return domains;
+
+	/* AUX power is only needed for (e)DP mode, not for HDMI. */
+	if (intel_crtc_has_dp_encoder(crtc_state)) {
+		struct intel_dp *intel_dp = &dig_port->dp;
+
+		domains |= BIT_ULL(intel_ddi_main_link_aux_domain(intel_dp));
+	}
+
+	return domains;
 }
 
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state)
@@ -2631,6 +2671,9 @@ static void intel_ddi_pre_enable_dp(struct intel_encoder *encoder,
 
 	WARN_ON(is_mst && (port == PORT_A || port == PORT_E));
 
+	intel_display_power_get(dev_priv,
+				intel_ddi_main_link_aux_domain(intel_dp));
+
 	intel_dp_set_link_params(intel_dp, crtc_state->port_clock,
 				 crtc_state->lane_count, is_mst);
 
@@ -2775,6 +2818,9 @@ static void intel_ddi_post_disable_dp(struct intel_encoder *encoder,
 	intel_display_power_put(dev_priv, dig_port->ddi_io_power_domain);
 
 	intel_ddi_clk_disable(encoder);
+
+	intel_display_power_put(dev_priv,
+				intel_ddi_main_link_aux_domain(intel_dp));
 }
 
 static void intel_ddi_post_disable_hdmi(struct intel_encoder *encoder,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 1469a56f6c46..0db23292eb35 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15661,11 +15661,21 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
 		u64 get_domains;
 		enum intel_display_power_domain domain;
+		struct intel_crtc_state *crtc_state;
 
 		if (!encoder->get_power_domains)
 			continue;
 
-		get_domains = encoder->get_power_domains(encoder);
+		/*
+		 * For MST and inactive encoders we don't have a crtc state.
+		 * FIXME: no need to call get_power_domains in such cases, it
+		 * will always return 0.
+		 */
+		crtc_state = encoder->base.crtc ?
+			     to_intel_crtc_state(encoder->base.crtc->state) :
+			     NULL;
+
+		get_domains = encoder->get_power_domains(encoder, crtc_state);
 		for_each_power_domain(domain, get_domains)
 			intel_display_power_get(dev_priv, domain);
 	}
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 9e0a8cc48521..0be45b75cca2 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -254,7 +254,8 @@ struct intel_encoder {
 			   struct intel_crtc_state *pipe_config);
 	/* Returns a mask of power domains that need to be referenced as part
 	 * of the hardware state readout code. */
-	u64 (*get_power_domains)(struct intel_encoder *encoder);
+	u64 (*get_power_domains)(struct intel_encoder *encoder,
+				 struct intel_crtc_state *crtc_state);
 	/*
 	 * Called during system suspend after all pending requests for the
 	 * encoder are flushed (for example for DP AUX transactions) and
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index aea81ace854b..f7ae7e33f453 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -56,43 +56,6 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
-static inline enum intel_display_power_domain
-psr_aux_domain(struct intel_dp *intel_dp)
-{
-	/* CNL HW requires corresponding AUX IOs to be powered up for PSR.
-	 * However, for non-A AUX ports the corresponding non-EDP transcoders
-	 * would have already enabled power well 2 and DC_OFF. This means we can
-	 * acquire a wider POWER_DOMAIN_AUX_{B,C,D,F} reference instead of a
-	 * specific AUX_IO reference without powering up any extra wells.
-	 * Note that PSR is enabled only on Port A even though this function
-	 * returns the correct domain for other ports too.
-	 */
-	return intel_dp->aux_ch == AUX_CH_A ? POWER_DOMAIN_AUX_IO_A :
-					      intel_dp->aux_power_domain;
-}
-
-static void psr_aux_io_power_get(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
-
-	if (INTEL_GEN(dev_priv) < 10)
-		return;
-
-	intel_display_power_get(dev_priv, psr_aux_domain(intel_dp));
-}
-
-static void psr_aux_io_power_put(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
-
-	if (INTEL_GEN(dev_priv) < 10)
-		return;
-
-	intel_display_power_put(dev_priv, psr_aux_domain(intel_dp));
-}
-
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug)
 {
 	u32 debug_mask, mask;
@@ -595,8 +558,6 @@ static void hsw_psr_enable_source(struct intel_dp *intel_dp,
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 
-	psr_aux_io_power_get(intel_dp);
-
 	/* Only HSW and BDW have PSR AUX registers that need to be setup. SKL+
 	 * use hardcoded values PSR AUX transactions
 	 */
@@ -717,8 +678,6 @@ static void hsw_psr_disable(struct intel_dp *intel_dp,
 		else
 			WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
 	}
-
-	psr_aux_io_power_put(intel_dp);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index de3a81034f77..2969787201ef 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -1824,6 +1824,7 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define GLK_DISPLAY_AUX_A_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_A) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_IO_A) |		\
 	BIT_ULL(POWER_DOMAIN_INIT))
 #define GLK_DISPLAY_AUX_B_POWER_DOMAINS (		\
 	BIT_ULL(POWER_DOMAIN_AUX_B) |		\
-- 
cgit v1.2.3


From c4015302565c9869bfc16824096211a32ba4d416 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:07 +0800
Subject: fsl/fman: share the event interrupt

This patch is to share fman event interrupt because
the 1588 timer driver will also use this interrupt.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/fman.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/fman/fman.c b/drivers/net/ethernet/freescale/fman/fman.c
index 9530405030a7..c415ac67cb7b 100644
--- a/drivers/net/ethernet/freescale/fman/fman.c
+++ b/drivers/net/ethernet/freescale/fman/fman.c
@@ -2801,7 +2801,8 @@ static struct fman *read_dts_node(struct platform_device *of_dev)
 	of_node_put(muram_node);
 	of_node_put(fm_node);
 
-	err = devm_request_irq(&of_dev->dev, irq, fman_irq, 0, "fman", fman);
+	err = devm_request_irq(&of_dev->dev, irq, fman_irq, IRQF_SHARED,
+			       "fman", fman);
 	if (err < 0) {
 		dev_err(&of_dev->dev, "%s: irq %d allocation failed (error = %d)\n",
 			__func__, irq, err);
-- 
cgit v1.2.3


From a8f62d0c6fe533e07cd1acce7588278f9d6e7720 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:08 +0800
Subject: ptp: support DPAA FMan 1588 timer in ptp_qoriq

This patch is to support DPAA (Data Path Acceleration Architecture)
1588 timer by adding "fsl,fman-ptp-timer" compatible, sharing
interrupt with FMan, adding FSL_DPAA_ETH dependency, and fixing
up register offset.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/Kconfig           |   2 +-
 drivers/ptp/ptp_qoriq.c       | 104 +++++++++++++++++++++++++++---------------
 include/linux/fsl/ptp_qoriq.h |  38 ++++++++++++---
 3 files changed, 98 insertions(+), 46 deletions(-)

diff --git a/drivers/ptp/Kconfig b/drivers/ptp/Kconfig
index 474c988d2e95..d137c480db46 100644
--- a/drivers/ptp/Kconfig
+++ b/drivers/ptp/Kconfig
@@ -43,7 +43,7 @@ config PTP_1588_CLOCK_DTE
 
 config PTP_1588_CLOCK_QORIQ
 	tristate "Freescale QorIQ 1588 timer as PTP clock"
-	depends on GIANFAR
+	depends on GIANFAR || FSL_DPAA_ETH
 	depends on PTP_1588_CLOCK
 	default y
 	help
diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index e8652c148c52..a14c317b5a38 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -39,11 +39,12 @@
 /* Caller must hold qoriq_ptp->lock. */
 static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	u64 ns;
 	u32 lo, hi;
 
-	lo = qoriq_read(&qoriq_ptp->regs->tmr_cnt_l);
-	hi = qoriq_read(&qoriq_ptp->regs->tmr_cnt_h);
+	lo = qoriq_read(&regs->ctrl_regs->tmr_cnt_l);
+	hi = qoriq_read(&regs->ctrl_regs->tmr_cnt_h);
 	ns = ((u64) hi) << 32;
 	ns |= lo;
 	return ns;
@@ -52,16 +53,18 @@ static u64 tmr_cnt_read(struct qoriq_ptp *qoriq_ptp)
 /* Caller must hold qoriq_ptp->lock. */
 static void tmr_cnt_write(struct qoriq_ptp *qoriq_ptp, u64 ns)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	u32 hi = ns >> 32;
 	u32 lo = ns & 0xffffffff;
 
-	qoriq_write(&qoriq_ptp->regs->tmr_cnt_l, lo);
-	qoriq_write(&qoriq_ptp->regs->tmr_cnt_h, hi);
+	qoriq_write(&regs->ctrl_regs->tmr_cnt_l, lo);
+	qoriq_write(&regs->ctrl_regs->tmr_cnt_h, hi);
 }
 
 /* Caller must hold qoriq_ptp->lock. */
 static void set_alarm(struct qoriq_ptp *qoriq_ptp)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	u64 ns;
 	u32 lo, hi;
 
@@ -70,16 +73,18 @@ static void set_alarm(struct qoriq_ptp *qoriq_ptp)
 	ns -= qoriq_ptp->tclk_period;
 	hi = ns >> 32;
 	lo = ns & 0xffffffff;
-	qoriq_write(&qoriq_ptp->regs->tmr_alarm1_l, lo);
-	qoriq_write(&qoriq_ptp->regs->tmr_alarm1_h, hi);
+	qoriq_write(&regs->alarm_regs->tmr_alarm1_l, lo);
+	qoriq_write(&regs->alarm_regs->tmr_alarm1_h, hi);
 }
 
 /* Caller must hold qoriq_ptp->lock. */
 static void set_fipers(struct qoriq_ptp *qoriq_ptp)
 {
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
+
 	set_alarm(qoriq_ptp);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
+	qoriq_write(&regs->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
+	qoriq_write(&regs->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
 }
 
 /*
@@ -89,16 +94,17 @@ static void set_fipers(struct qoriq_ptp *qoriq_ptp)
 static irqreturn_t isr(int irq, void *priv)
 {
 	struct qoriq_ptp *qoriq_ptp = priv;
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	struct ptp_clock_event event;
 	u64 ns;
 	u32 ack = 0, lo, hi, mask, val;
 
-	val = qoriq_read(&qoriq_ptp->regs->tmr_tevent);
+	val = qoriq_read(&regs->ctrl_regs->tmr_tevent);
 
 	if (val & ETS1) {
 		ack |= ETS1;
-		hi = qoriq_read(&qoriq_ptp->regs->tmr_etts1_h);
-		lo = qoriq_read(&qoriq_ptp->regs->tmr_etts1_l);
+		hi = qoriq_read(&regs->etts_regs->tmr_etts1_h);
+		lo = qoriq_read(&regs->etts_regs->tmr_etts1_l);
 		event.type = PTP_CLOCK_EXTTS;
 		event.index = 0;
 		event.timestamp = ((u64) hi) << 32;
@@ -108,8 +114,8 @@ static irqreturn_t isr(int irq, void *priv)
 
 	if (val & ETS2) {
 		ack |= ETS2;
-		hi = qoriq_read(&qoriq_ptp->regs->tmr_etts2_h);
-		lo = qoriq_read(&qoriq_ptp->regs->tmr_etts2_l);
+		hi = qoriq_read(&regs->etts_regs->tmr_etts2_h);
+		lo = qoriq_read(&regs->etts_regs->tmr_etts2_l);
 		event.type = PTP_CLOCK_EXTTS;
 		event.index = 1;
 		event.timestamp = ((u64) hi) << 32;
@@ -130,16 +136,16 @@ static irqreturn_t isr(int irq, void *priv)
 			hi = ns >> 32;
 			lo = ns & 0xffffffff;
 			spin_lock(&qoriq_ptp->lock);
-			qoriq_write(&qoriq_ptp->regs->tmr_alarm2_l, lo);
-			qoriq_write(&qoriq_ptp->regs->tmr_alarm2_h, hi);
+			qoriq_write(&regs->alarm_regs->tmr_alarm2_l, lo);
+			qoriq_write(&regs->alarm_regs->tmr_alarm2_h, hi);
 			spin_unlock(&qoriq_ptp->lock);
 			qoriq_ptp->alarm_value = ns;
 		} else {
-			qoriq_write(&qoriq_ptp->regs->tmr_tevent, ALM2);
+			qoriq_write(&regs->ctrl_regs->tmr_tevent, ALM2);
 			spin_lock(&qoriq_ptp->lock);
-			mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+			mask = qoriq_read(&regs->ctrl_regs->tmr_temask);
 			mask &= ~ALM2EN;
-			qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+			qoriq_write(&regs->ctrl_regs->tmr_temask, mask);
 			spin_unlock(&qoriq_ptp->lock);
 			qoriq_ptp->alarm_value = 0;
 			qoriq_ptp->alarm_interval = 0;
@@ -153,7 +159,7 @@ static irqreturn_t isr(int irq, void *priv)
 	}
 
 	if (ack) {
-		qoriq_write(&qoriq_ptp->regs->tmr_tevent, ack);
+		qoriq_write(&regs->ctrl_regs->tmr_tevent, ack);
 		return IRQ_HANDLED;
 	} else
 		return IRQ_NONE;
@@ -169,6 +175,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	u32 tmr_add;
 	int neg_adj = 0;
 	struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps);
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 
 	if (scaled_ppm < 0) {
 		neg_adj = 1;
@@ -186,7 +193,7 @@ static int ptp_qoriq_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 
 	tmr_add = neg_adj ? tmr_add - diff : tmr_add + diff;
 
-	qoriq_write(&qoriq_ptp->regs->tmr_add, tmr_add);
+	qoriq_write(&regs->ctrl_regs->tmr_add, tmr_add);
 
 	return 0;
 }
@@ -250,6 +257,7 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp,
 			      struct ptp_clock_request *rq, int on)
 {
 	struct qoriq_ptp *qoriq_ptp = container_of(ptp, struct qoriq_ptp, caps);
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 	unsigned long flags;
 	u32 bit, mask;
 
@@ -266,23 +274,23 @@ static int ptp_qoriq_enable(struct ptp_clock_info *ptp,
 			return -EINVAL;
 		}
 		spin_lock_irqsave(&qoriq_ptp->lock, flags);
-		mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+		mask = qoriq_read(&regs->ctrl_regs->tmr_temask);
 		if (on)
 			mask |= bit;
 		else
 			mask &= ~bit;
-		qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+		qoriq_write(&regs->ctrl_regs->tmr_temask, mask);
 		spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
 		return 0;
 
 	case PTP_CLK_REQ_PPS:
 		spin_lock_irqsave(&qoriq_ptp->lock, flags);
-		mask = qoriq_read(&qoriq_ptp->regs->tmr_temask);
+		mask = qoriq_read(&regs->ctrl_regs->tmr_temask);
 		if (on)
 			mask |= PP1EN;
 		else
 			mask &= ~PP1EN;
-		qoriq_write(&qoriq_ptp->regs->tmr_temask, mask);
+		qoriq_write(&regs->ctrl_regs->tmr_temask, mask);
 		spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
 		return 0;
 
@@ -313,10 +321,12 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 {
 	struct device_node *node = dev->dev.of_node;
 	struct qoriq_ptp *qoriq_ptp;
+	struct qoriq_ptp_registers *regs;
 	struct timespec64 now;
 	int err = -ENOMEM;
 	u32 tmr_ctrl;
 	unsigned long flags;
+	void __iomem *base;
 
 	qoriq_ptp = kzalloc(sizeof(*qoriq_ptp), GFP_KERNEL);
 	if (!qoriq_ptp)
@@ -351,7 +361,7 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 		pr_err("irq not in device tree\n");
 		goto no_node;
 	}
-	if (request_irq(qoriq_ptp->irq, isr, 0, DRIVER, qoriq_ptp)) {
+	if (request_irq(qoriq_ptp->irq, isr, IRQF_SHARED, DRIVER, qoriq_ptp)) {
 		pr_err("request_irq failed\n");
 		goto no_node;
 	}
@@ -368,12 +378,27 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 
 	spin_lock_init(&qoriq_ptp->lock);
 
-	qoriq_ptp->regs = ioremap(qoriq_ptp->rsrc->start,
-				resource_size(qoriq_ptp->rsrc));
-	if (!qoriq_ptp->regs) {
+	base = ioremap(qoriq_ptp->rsrc->start,
+		       resource_size(qoriq_ptp->rsrc));
+	if (!base) {
 		pr_err("ioremap ptp registers failed\n");
 		goto no_ioremap;
 	}
+
+	qoriq_ptp->base = base;
+
+	if (of_device_is_compatible(node, "fsl,fman-ptp-timer")) {
+		qoriq_ptp->regs.ctrl_regs = base + FMAN_CTRL_REGS_OFFSET;
+		qoriq_ptp->regs.alarm_regs = base + FMAN_ALARM_REGS_OFFSET;
+		qoriq_ptp->regs.fiper_regs = base + FMAN_FIPER_REGS_OFFSET;
+		qoriq_ptp->regs.etts_regs = base + FMAN_ETTS_REGS_OFFSET;
+	} else {
+		qoriq_ptp->regs.ctrl_regs = base + CTRL_REGS_OFFSET;
+		qoriq_ptp->regs.alarm_regs = base + ALARM_REGS_OFFSET;
+		qoriq_ptp->regs.fiper_regs = base + FIPER_REGS_OFFSET;
+		qoriq_ptp->regs.etts_regs = base + ETTS_REGS_OFFSET;
+	}
+
 	ktime_get_real_ts64(&now);
 	ptp_qoriq_settime(&qoriq_ptp->caps, &now);
 
@@ -383,13 +408,14 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 
 	spin_lock_irqsave(&qoriq_ptp->lock, flags);
 
-	qoriq_write(&qoriq_ptp->regs->tmr_ctrl,   tmr_ctrl);
-	qoriq_write(&qoriq_ptp->regs->tmr_add,    qoriq_ptp->tmr_add);
-	qoriq_write(&qoriq_ptp->regs->tmr_prsc,   qoriq_ptp->tmr_prsc);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
-	qoriq_write(&qoriq_ptp->regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
+	regs = &qoriq_ptp->regs;
+	qoriq_write(&regs->ctrl_regs->tmr_ctrl,   tmr_ctrl);
+	qoriq_write(&regs->ctrl_regs->tmr_add,    qoriq_ptp->tmr_add);
+	qoriq_write(&regs->ctrl_regs->tmr_prsc,   qoriq_ptp->tmr_prsc);
+	qoriq_write(&regs->fiper_regs->tmr_fiper1, qoriq_ptp->tmr_fiper1);
+	qoriq_write(&regs->fiper_regs->tmr_fiper2, qoriq_ptp->tmr_fiper2);
 	set_alarm(qoriq_ptp);
-	qoriq_write(&qoriq_ptp->regs->tmr_ctrl,   tmr_ctrl|FIPERST|RTPE|TE|FRD);
+	qoriq_write(&regs->ctrl_regs->tmr_ctrl,   tmr_ctrl|FIPERST|RTPE|TE|FRD);
 
 	spin_unlock_irqrestore(&qoriq_ptp->lock, flags);
 
@@ -405,7 +431,7 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 	return 0;
 
 no_clock:
-	iounmap(qoriq_ptp->regs);
+	iounmap(qoriq_ptp->base);
 no_ioremap:
 	release_resource(qoriq_ptp->rsrc);
 no_resource:
@@ -419,12 +445,13 @@ no_memory:
 static int qoriq_ptp_remove(struct platform_device *dev)
 {
 	struct qoriq_ptp *qoriq_ptp = platform_get_drvdata(dev);
+	struct qoriq_ptp_registers *regs = &qoriq_ptp->regs;
 
-	qoriq_write(&qoriq_ptp->regs->tmr_temask, 0);
-	qoriq_write(&qoriq_ptp->regs->tmr_ctrl,   0);
+	qoriq_write(&regs->ctrl_regs->tmr_temask, 0);
+	qoriq_write(&regs->ctrl_regs->tmr_ctrl,   0);
 
 	ptp_clock_unregister(qoriq_ptp->clock);
-	iounmap(qoriq_ptp->regs);
+	iounmap(qoriq_ptp->base);
 	release_resource(qoriq_ptp->rsrc);
 	free_irq(qoriq_ptp->irq, qoriq_ptp);
 	kfree(qoriq_ptp);
@@ -434,6 +461,7 @@ static int qoriq_ptp_remove(struct platform_device *dev)
 
 static const struct of_device_id match_table[] = {
 	{ .compatible = "fsl,etsec-ptp" },
+	{ .compatible = "fsl,fman-ptp-timer" },
 	{},
 };
 MODULE_DEVICE_TABLE(of, match_table);
diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h
index b462d9ea8007..dc3dac40f069 100644
--- a/include/linux/fsl/ptp_qoriq.h
+++ b/include/linux/fsl/ptp_qoriq.h
@@ -11,9 +11,8 @@
 
 /*
  * qoriq ptp registers
- * Generated by regen.tcl on Thu May 13 01:38:57 PM CEST 2010
  */
-struct qoriq_ptp_registers {
+struct ctrl_regs {
 	u32 tmr_ctrl;     /* Timer control register */
 	u32 tmr_tevent;   /* Timestamp event register */
 	u32 tmr_temask;   /* Timer event mask register */
@@ -28,22 +27,47 @@ struct qoriq_ptp_registers {
 	u8  res1[4];
 	u32 tmroff_h;     /* Timer offset high */
 	u32 tmroff_l;     /* Timer offset low */
-	u8  res2[8];
+};
+
+struct alarm_regs {
 	u32 tmr_alarm1_h; /* Timer alarm 1 high register */
 	u32 tmr_alarm1_l; /* Timer alarm 1 high register */
 	u32 tmr_alarm2_h; /* Timer alarm 2 high register */
 	u32 tmr_alarm2_l; /* Timer alarm 2 high register */
-	u8  res3[48];
+};
+
+struct fiper_regs {
 	u32 tmr_fiper1;   /* Timer fixed period interval */
 	u32 tmr_fiper2;   /* Timer fixed period interval */
 	u32 tmr_fiper3;   /* Timer fixed period interval */
-	u8  res4[20];
+};
+
+struct etts_regs {
 	u32 tmr_etts1_h;  /* Timestamp of general purpose external trigger */
 	u32 tmr_etts1_l;  /* Timestamp of general purpose external trigger */
 	u32 tmr_etts2_h;  /* Timestamp of general purpose external trigger */
 	u32 tmr_etts2_l;  /* Timestamp of general purpose external trigger */
 };
 
+struct qoriq_ptp_registers {
+	struct ctrl_regs __iomem *ctrl_regs;
+	struct alarm_regs __iomem *alarm_regs;
+	struct fiper_regs __iomem *fiper_regs;
+	struct etts_regs __iomem *etts_regs;
+};
+
+/* Offset definitions for the four register groups */
+#define CTRL_REGS_OFFSET	0x0
+#define ALARM_REGS_OFFSET	0x40
+#define FIPER_REGS_OFFSET	0x80
+#define ETTS_REGS_OFFSET	0xa0
+
+#define FMAN_CTRL_REGS_OFFSET	0x80
+#define FMAN_ALARM_REGS_OFFSET	0xb8
+#define FMAN_FIPER_REGS_OFFSET	0xd0
+#define FMAN_ETTS_REGS_OFFSET	0xe0
+
+
 /* Bit definitions for the TMR_CTRL register */
 #define ALM1P                 (1<<31) /* Alarm1 output polarity */
 #define ALM2P                 (1<<30) /* Alarm2 output polarity */
@@ -105,10 +129,10 @@ struct qoriq_ptp_registers {
 #define DRIVER		"ptp_qoriq"
 #define DEFAULT_CKSEL	1
 #define N_EXT_TS	2
-#define REG_SIZE	sizeof(struct qoriq_ptp_registers)
 
 struct qoriq_ptp {
-	struct qoriq_ptp_registers __iomem *regs;
+	void __iomem *base;
+	struct qoriq_ptp_registers regs;
 	spinlock_t lock; /* protects regs */
 	struct ptp_clock *clock;
 	struct ptp_clock_info caps;
-- 
cgit v1.2.3


From 2cb785b4967aa56b0c4dc9742db413b76a373aa3 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:09 +0800
Subject: dt-binding: ptp_qoriq: add DPAA FMan support

This patch is to add bindings description for DPAA
FMan 1588 timer, and also remove its description in
fsl-fman dt-bindings document.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/fsl-fman.txt | 25 +---------------------
 .../devicetree/bindings/ptp/ptp-qoriq.txt          | 15 ++++++++++---
 2 files changed, 13 insertions(+), 27 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/fsl-fman.txt b/Documentation/devicetree/bindings/net/fsl-fman.txt
index df873d1f3b7c..74603dd0789e 100644
--- a/Documentation/devicetree/bindings/net/fsl-fman.txt
+++ b/Documentation/devicetree/bindings/net/fsl-fman.txt
@@ -356,30 +356,7 @@ ethernet@e0000 {
 ============================================================================
 FMan IEEE 1588 Node
 
-DESCRIPTION
-
-The FMan interface to support IEEE 1588
-
-
-PROPERTIES
-
-- compatible
-		Usage: required
-		Value type: <stringlist>
-		Definition: A standard property.
-		Must include "fsl,fman-ptp-timer".
-
-- reg
-		Usage: required
-		Value type: <prop-encoded-array>
-		Definition: A standard property.
-
-EXAMPLE
-
-ptp-timer@fe000 {
-	compatible = "fsl,fman-ptp-timer";
-	reg = <0xfe000 0x1000>;
-};
+Refer to Documentation/devicetree/bindings/ptp/ptp-qoriq.txt
 
 =============================================================================
 FMan MDIO Node
diff --git a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt
index 0f569d8e73a3..c5d0e7998e2b 100644
--- a/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt
+++ b/Documentation/devicetree/bindings/ptp/ptp-qoriq.txt
@@ -2,7 +2,8 @@
 
 General Properties:
 
-  - compatible   Should be "fsl,etsec-ptp"
+  - compatible   Should be "fsl,etsec-ptp" for eTSEC
+                 Should be "fsl,fman-ptp-timer" for DPAA FMan
   - reg          Offset and length of the register set for the device
   - interrupts   There should be at least two interrupts. Some devices
                  have as many as four PTP related interrupts.
@@ -43,14 +44,22 @@ Clock Properties:
   value, which will be directly written in those bits, that is why,
   according to reference manual, the next clock sources can be used:
 
+  For eTSEC,
   <0> - external high precision timer reference clock (TSEC_TMR_CLK
         input is used for this purpose);
   <1> - eTSEC system clock;
   <2> - eTSEC1 transmit clock;
   <3> - RTC clock input.
 
-  When this attribute is not used, eTSEC system clock will serve as
-  IEEE 1588 timer reference clock.
+  For DPAA FMan,
+  <0> - external high precision timer reference clock (TMR_1588_CLK)
+  <1> - MAC system clock (1/2 FMan clock)
+  <2> - reserved
+  <3> - RTC clock oscillator
+
+  When this attribute is not used, the IEEE 1588 timer reference clock
+  will use the eTSEC system clock (for Gianfar) or the MAC system
+  clock (for DPAA).
 
 Example:
 
-- 
cgit v1.2.3


From dab4a02630d5cb7628bed7f2a58354aca053eda7 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:10 +0800
Subject: powerpc/mpc85xx: move ptp timer out of fman in dts

This patch is to move ptp timer node out of fman.
Because ptp timer will be probed by ptp_qoriq driver,
it should be an independent device in case of conflict
memory mapping.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi   | 14 ++++++++------
 arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi   | 14 ++++++++------
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi  | 14 ++++++++------
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi  | 14 ++++++++------
 arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi | 14 ++++++++------
 5 files changed, 40 insertions(+), 30 deletions(-)

diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi
index abd01d466de4..6b124f73f67a 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi
@@ -37,12 +37,13 @@ fman0: fman@400000 {
 	#size-cells = <1>;
 	cell-index = <0>;
 	compatible = "fsl,fman";
-	ranges = <0 0x400000 0x100000>;
-	reg = <0x400000 0x100000>;
+	ranges = <0 0x400000 0xfe000>;
+	reg = <0x400000 0xfe000>;
 	interrupts = <96 2 0 0>, <16 2 1 1>;
 	clocks = <&clockgen 3 0>;
 	clock-names = "fmanclk";
 	fsl,qman-channel-range = <0x40 0xc>;
+	ptimer-handle = <&ptp_timer0>;
 
 	muram@0 {
 		compatible = "fsl,fman-muram";
@@ -93,9 +94,10 @@ fman0: fman@400000 {
 		reg = <0x87000 0x1000>;
 		status = "disabled";
 	};
+};
 
-	ptp_timer0: ptp-timer@fe000 {
-		compatible = "fsl,fman-ptp-timer";
-		reg = <0xfe000 0x1000>;
-	};
+ptp_timer0: ptp-timer@4fe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0x4fe000 0x1000>;
+	interrupts = <96 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi
index debea75fd3f0..b80aaf5f00a1 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi
@@ -37,12 +37,13 @@ fman1: fman@500000 {
 	#size-cells = <1>;
 	cell-index = <1>;
 	compatible = "fsl,fman";
-	ranges = <0 0x500000 0x100000>;
-	reg = <0x500000 0x100000>;
+	ranges = <0 0x500000 0xfe000>;
+	reg = <0x500000 0xfe000>;
 	interrupts = <97 2 0 0>, <16 2 1 0>;
 	clocks = <&clockgen 3 1>;
 	clock-names = "fmanclk";
 	fsl,qman-channel-range = <0x60 0xc>;
+	ptimer-handle = <&ptp_timer1>;
 
 	muram@0 {
 		compatible = "fsl,fman-muram";
@@ -93,9 +94,10 @@ fman1: fman@500000 {
 		reg = <0x87000 0x1000>;
 		status = "disabled";
 	};
+};
 
-	ptp_timer1: ptp-timer@fe000 {
-		compatible = "fsl,fman-ptp-timer";
-		reg = <0xfe000 0x1000>;
-	};
+ptp_timer1: ptp-timer@5fe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0x5fe000 0x1000>;
+	interrupts = <97 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi
index 3a20e0d1a6d2..d3720fdde26c 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi
@@ -37,12 +37,13 @@ fman0: fman@400000 {
 	#size-cells = <1>;
 	cell-index = <0>;
 	compatible = "fsl,fman";
-	ranges = <0 0x400000 0x100000>;
-	reg = <0x400000 0x100000>;
+	ranges = <0 0x400000 0xfe000>;
+	reg = <0x400000 0xfe000>;
 	interrupts = <96 2 0 0>, <16 2 1 1>;
 	clocks = <&clockgen 3 0>;
 	clock-names = "fmanclk";
 	fsl,qman-channel-range = <0x800 0x10>;
+	ptimer-handle = <&ptp_timer0>;
 
 	muram@0 {
 		compatible = "fsl,fman-muram";
@@ -98,9 +99,10 @@ fman0: fman@400000 {
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xfd000 0x1000>;
 	};
+};
 
-	ptp_timer0: ptp-timer@fe000 {
-		compatible = "fsl,fman-ptp-timer";
-		reg = <0xfe000 0x1000>;
-	};
+ptp_timer0: ptp-timer@4fe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0x4fe000 0x1000>;
+	interrupts = <96 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi
index 82750ac944c7..ae34c204a5bc 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi
@@ -37,12 +37,13 @@ fman1: fman@500000 {
 	#size-cells = <1>;
 	cell-index = <1>;
 	compatible = "fsl,fman";
-	ranges = <0 0x500000 0x100000>;
-	reg = <0x500000 0x100000>;
+	ranges = <0 0x500000 0xfe000>;
+	reg = <0x500000 0xfe000>;
 	interrupts = <97 2 0 0>, <16 2 1 0>;
 	clocks = <&clockgen 3 1>;
 	clock-names = "fmanclk";
 	fsl,qman-channel-range = <0x820 0x10>;
+	ptimer-handle = <&ptp_timer1>;
 
 	muram@0 {
 		compatible = "fsl,fman-muram";
@@ -98,9 +99,10 @@ fman1: fman@500000 {
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xfd000 0x1000>;
 	};
+};
 
-	ptp_timer1: ptp-timer@fe000 {
-		compatible = "fsl,fman-ptp-timer";
-		reg = <0xfe000 0x1000>;
-	};
+ptp_timer1: ptp-timer@5fe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0x5fe000 0x1000>;
+	interrupts = <97 2 0 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
index 7f60b6060176..02f2755842cc 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
@@ -37,12 +37,13 @@ fman0: fman@400000 {
 	#size-cells = <1>;
 	cell-index = <0>;
 	compatible = "fsl,fman";
-	ranges = <0 0x400000 0x100000>;
-	reg = <0x400000 0x100000>;
+	ranges = <0 0x400000 0xfe000>;
+	reg = <0x400000 0xfe000>;
 	interrupts = <96 2 0 0>, <16 2 1 1>;
 	clocks = <&clockgen 3 0>;
 	clock-names = "fmanclk";
 	fsl,qman-channel-range = <0x800 0x10>;
+	ptimer-handle = <&ptp_timer0>;
 
 	muram@0 {
 		compatible = "fsl,fman-muram";
@@ -86,9 +87,10 @@ fman0: fman@400000 {
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xfd000 0x1000>;
 	};
+};
 
-	ptp_timer0: ptp-timer@fe000 {
-		compatible = "fsl,fman-ptp-timer";
-		reg = <0xfe000 0x1000>;
-	};
+ptp_timer0: ptp-timer@4fe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0x4fe000 0x1000>;
+	interrupts = <96 2 0 0>;
 };
-- 
cgit v1.2.3


From 9cd19b52e1c4ba3f097a6ccab9b7595e6b9fbd3c Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:11 +0800
Subject: arm64: dts: fsl: move ptp timer out of fman

This patch is to move ptp timer node out of fman.
Because ptp timer will be probed by ptp_qoriq driver,
it should be an independent device in case of conflict
memory mapping.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
index 4dd06767f839..a56a408e9bf7 100644
--- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
+++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
@@ -11,13 +11,14 @@ fman0: fman@1a00000 {
 	#size-cells = <1>;
 	cell-index = <0>;
 	compatible = "fsl,fman";
-	ranges = <0x0 0x0 0x1a00000 0x100000>;
-	reg = <0x0 0x1a00000 0x0 0x100000>;
+	ranges = <0x0 0x0 0x1a00000 0xfe000>;
+	reg = <0x0 0x1a00000 0x0 0xfe000>;
 	interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>,
 		     <GIC_SPI 45 IRQ_TYPE_LEVEL_HIGH>;
 	clocks = <&clockgen 3 0>;
 	clock-names = "fmanclk";
 	fsl,qman-channel-range = <0x800 0x10>;
+	ptimer-handle = <&ptp_timer0>;
 
 	muram@0 {
 		compatible = "fsl,fman-muram";
@@ -73,9 +74,10 @@ fman0: fman@1a00000 {
 		compatible = "fsl,fman-memac-mdio", "fsl,fman-xmdio";
 		reg = <0xfd000 0x1000>;
 	};
+};
 
-	ptp_timer0: ptp-timer@fe000 {
-		compatible = "fsl,fman-ptp-timer";
-		reg = <0xfe000 0x1000>;
-	};
+ptp_timer0: ptp-timer@1afe000 {
+	compatible = "fsl,fman-ptp-timer";
+	reg = <0x0 0x1afe000 0x0 0x1000>;
+	interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
 };
-- 
cgit v1.2.3


From 0fab782a28e41137a76ca1ebcd5ae8ed7900f8fc Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:12 +0800
Subject: fsl/fman: add set_tstamp interface

This patch is to add set_tstamp interface for memac,
dtsec, and 10GEC controllers to configure HW timestamping.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/fman_dtsec.c | 27 ++++++++++++++++++++++++
 drivers/net/ethernet/freescale/fman/fman_dtsec.h |  1 +
 drivers/net/ethernet/freescale/fman/fman_memac.c |  5 +++++
 drivers/net/ethernet/freescale/fman/fman_memac.h |  1 +
 drivers/net/ethernet/freescale/fman/fman_tgec.c  | 21 ++++++++++++++++++
 drivers/net/ethernet/freescale/fman/fman_tgec.h  |  1 +
 drivers/net/ethernet/freescale/fman/mac.c        |  3 +++
 drivers/net/ethernet/freescale/fman/mac.h        |  1 +
 8 files changed, 60 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index 57b1e2b47c0a..1ca543ac8f2c 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -123,11 +123,13 @@
 #define DTSEC_ECNTRL_R100M		0x00000008
 #define DTSEC_ECNTRL_QSGMIIM		0x00000001
 
+#define TCTRL_TTSE			0x00000040
 #define TCTRL_GTS			0x00000020
 
 #define RCTRL_PAL_MASK			0x001f0000
 #define RCTRL_PAL_SHIFT			16
 #define RCTRL_GHTX			0x00000400
+#define RCTRL_RTSE			0x00000040
 #define RCTRL_GRS			0x00000020
 #define RCTRL_MPROM			0x00000008
 #define RCTRL_RSF			0x00000004
@@ -1136,6 +1138,31 @@ int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable)
 	return 0;
 }
 
+int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable)
+{
+	struct dtsec_regs __iomem *regs = dtsec->regs;
+	u32 rctrl, tctrl;
+
+	if (!is_init_done(dtsec->dtsec_drv_param))
+		return -EINVAL;
+
+	rctrl = ioread32be(&regs->rctrl);
+	tctrl = ioread32be(&regs->tctrl);
+
+	if (enable) {
+		rctrl |= RCTRL_RTSE;
+		tctrl |= TCTRL_TTSE;
+	} else {
+		rctrl &= ~RCTRL_RTSE;
+		tctrl &= ~TCTRL_TTSE;
+	}
+
+	iowrite32be(rctrl, &regs->rctrl);
+	iowrite32be(tctrl, &regs->tctrl);
+
+	return 0;
+}
+
 int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr)
 {
 	struct dtsec_regs __iomem *regs = dtsec->regs;
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.h b/drivers/net/ethernet/freescale/fman/fman_dtsec.h
index 1a689adf5a22..5149d96ec2c1 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.h
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.h
@@ -56,5 +56,6 @@ int dtsec_add_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr);
 int dtsec_del_hash_mac_address(struct fman_mac *dtsec, enet_addr_t *eth_addr);
 int dtsec_get_version(struct fman_mac *dtsec, u32 *mac_version);
 int dtsec_set_allmulti(struct fman_mac *dtsec, bool enable);
+int dtsec_set_tstamp(struct fman_mac *dtsec, bool enable);
 
 #endif /* __DTSEC_H */
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.c b/drivers/net/ethernet/freescale/fman/fman_memac.c
index 446a97b792e3..bc6eb30aa20f 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.c
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.c
@@ -964,6 +964,11 @@ int memac_set_allmulti(struct fman_mac *memac, bool enable)
 	return 0;
 }
 
+int memac_set_tstamp(struct fman_mac *memac, bool enable)
+{
+	return 0; /* Always enabled. */
+}
+
 int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr)
 {
 	struct memac_regs __iomem *regs = memac->regs;
diff --git a/drivers/net/ethernet/freescale/fman/fman_memac.h b/drivers/net/ethernet/freescale/fman/fman_memac.h
index b5a50338ed9a..b2c671ec0ce7 100644
--- a/drivers/net/ethernet/freescale/fman/fman_memac.h
+++ b/drivers/net/ethernet/freescale/fman/fman_memac.h
@@ -58,5 +58,6 @@ int memac_set_exception(struct fman_mac *memac,
 int memac_add_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr);
 int memac_del_hash_mac_address(struct fman_mac *memac, enet_addr_t *eth_addr);
 int memac_set_allmulti(struct fman_mac *memac, bool enable);
+int memac_set_tstamp(struct fman_mac *memac, bool enable);
 
 #endif /* __MEMAC_H */
diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.c b/drivers/net/ethernet/freescale/fman/fman_tgec.c
index 284735d4ebe9..40705938eecc 100644
--- a/drivers/net/ethernet/freescale/fman/fman_tgec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_tgec.c
@@ -44,6 +44,7 @@
 #define TGEC_TX_IPG_LENGTH_MASK	0x000003ff
 
 /* Command and Configuration Register (COMMAND_CONFIG) */
+#define CMD_CFG_EN_TIMESTAMP		0x00100000
 #define CMD_CFG_NO_LEN_CHK		0x00020000
 #define CMD_CFG_PAUSE_IGNORE		0x00000100
 #define CMF_CFG_CRC_FWD			0x00000040
@@ -588,6 +589,26 @@ int tgec_set_allmulti(struct fman_mac *tgec, bool enable)
 	return 0;
 }
 
+int tgec_set_tstamp(struct fman_mac *tgec, bool enable)
+{
+	struct tgec_regs __iomem *regs = tgec->regs;
+	u32 tmp;
+
+	if (!is_init_done(tgec->cfg))
+		return -EINVAL;
+
+	tmp = ioread32be(&regs->command_config);
+
+	if (enable)
+		tmp |= CMD_CFG_EN_TIMESTAMP;
+	else
+		tmp &= ~CMD_CFG_EN_TIMESTAMP;
+
+	iowrite32be(tmp, &regs->command_config);
+
+	return 0;
+}
+
 int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr)
 {
 	struct tgec_regs __iomem *regs = tgec->regs;
diff --git a/drivers/net/ethernet/freescale/fman/fman_tgec.h b/drivers/net/ethernet/freescale/fman/fman_tgec.h
index cbbd3b422a98..3bfd1062b386 100644
--- a/drivers/net/ethernet/freescale/fman/fman_tgec.h
+++ b/drivers/net/ethernet/freescale/fman/fman_tgec.h
@@ -52,5 +52,6 @@ int tgec_add_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr);
 int tgec_del_hash_mac_address(struct fman_mac *tgec, enet_addr_t *eth_addr);
 int tgec_get_version(struct fman_mac *tgec, u32 *mac_version);
 int tgec_set_allmulti(struct fman_mac *tgec, bool enable);
+int tgec_set_tstamp(struct fman_mac *tgec, bool enable);
 
 #endif /* __TGEC_H */
diff --git a/drivers/net/ethernet/freescale/fman/mac.c b/drivers/net/ethernet/freescale/fman/mac.c
index 7b5b95f52c09..a847b9c3b31a 100644
--- a/drivers/net/ethernet/freescale/fman/mac.c
+++ b/drivers/net/ethernet/freescale/fman/mac.c
@@ -471,6 +471,7 @@ static void setup_dtsec(struct mac_device *mac_dev)
 	mac_dev->set_rx_pause		= dtsec_accept_rx_pause_frames;
 	mac_dev->set_exception		= dtsec_set_exception;
 	mac_dev->set_allmulti		= dtsec_set_allmulti;
+	mac_dev->set_tstamp		= dtsec_set_tstamp;
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
@@ -490,6 +491,7 @@ static void setup_tgec(struct mac_device *mac_dev)
 	mac_dev->set_rx_pause		= tgec_accept_rx_pause_frames;
 	mac_dev->set_exception		= tgec_set_exception;
 	mac_dev->set_allmulti		= tgec_set_allmulti;
+	mac_dev->set_tstamp		= tgec_set_tstamp;
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
@@ -509,6 +511,7 @@ static void setup_memac(struct mac_device *mac_dev)
 	mac_dev->set_rx_pause		= memac_accept_rx_pause_frames;
 	mac_dev->set_exception		= memac_set_exception;
 	mac_dev->set_allmulti		= memac_set_allmulti;
+	mac_dev->set_tstamp		= memac_set_tstamp;
 	mac_dev->set_multi		= set_multi;
 	mac_dev->start			= start;
 	mac_dev->stop			= stop;
diff --git a/drivers/net/ethernet/freescale/fman/mac.h b/drivers/net/ethernet/freescale/fman/mac.h
index b520cec120ee..824a81a9f350 100644
--- a/drivers/net/ethernet/freescale/fman/mac.h
+++ b/drivers/net/ethernet/freescale/fman/mac.h
@@ -68,6 +68,7 @@ struct mac_device {
 	int (*set_promisc)(struct fman_mac *mac_dev, bool enable);
 	int (*change_addr)(struct fman_mac *mac_dev, enet_addr_t *enet_addr);
 	int (*set_allmulti)(struct fman_mac *mac_dev, bool enable);
+	int (*set_tstamp)(struct fman_mac *mac_dev, bool enable);
 	int (*set_multi)(struct net_device *net_dev,
 			 struct mac_device *mac_dev);
 	int (*set_rx_pause)(struct fman_mac *mac_dev, bool en);
-- 
cgit v1.2.3


From 880f874cf505681d3cfef867892ac15094afaf2b Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:13 +0800
Subject: fsl/fman_port: support getting timestamp

This patch is to add fman_port_get_tstamp() interface
to get timestamp.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/fman_port.c | 12 ++++++++++++
 drivers/net/ethernet/freescale/fman/fman_port.h |  2 ++
 2 files changed, 14 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c
index ce6e24c74978..4a2d9605bd5e 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.c
+++ b/drivers/net/ethernet/freescale/fman/fman_port.c
@@ -1731,6 +1731,18 @@ int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset)
 }
 EXPORT_SYMBOL(fman_port_get_hash_result_offset);
 
+int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp)
+{
+	if (port->buffer_offsets.time_stamp_offset == ILLEGAL_BASE)
+		return -EINVAL;
+
+	*tstamp = be64_to_cpu(*(__be64 *)(data +
+			port->buffer_offsets.time_stamp_offset));
+
+	return 0;
+}
+EXPORT_SYMBOL(fman_port_get_tstamp);
+
 static int fman_port_probe(struct platform_device *of_dev)
 {
 	struct fman_port *port;
diff --git a/drivers/net/ethernet/freescale/fman/fman_port.h b/drivers/net/ethernet/freescale/fman/fman_port.h
index e86ca6a34e4e..9dbb69f40121 100644
--- a/drivers/net/ethernet/freescale/fman/fman_port.h
+++ b/drivers/net/ethernet/freescale/fman/fman_port.h
@@ -153,6 +153,8 @@ u32 fman_port_get_qman_channel_id(struct fman_port *port);
 
 int fman_port_get_hash_result_offset(struct fman_port *port, u32 *offset);
 
+int fman_port_get_tstamp(struct fman_port *port, const void *data, u64 *tstamp);
+
 struct fman_port *fman_port_bind(struct device *dev);
 
 #endif /* __FMAN_PORT_H */
-- 
cgit v1.2.3


From dcce36ab7130a6ed46e9a9cce8b7452bffd95966 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:14 +0800
Subject: fsl/fman: define frame description command UPD

Defined frame description command FM_FD_CMD_UPD for
prepended data updating.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fman/fman.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/fman/fman.h b/drivers/net/ethernet/freescale/fman/fman.h
index bfa02e0014ae..935c317fa696 100644
--- a/drivers/net/ethernet/freescale/fman/fman.h
+++ b/drivers/net/ethernet/freescale/fman/fman.h
@@ -41,6 +41,7 @@
 /* Frame queue Context Override */
 #define FM_FD_CMD_FCO                   0x80000000
 #define FM_FD_CMD_RPD                   0x40000000  /* Read Prepended Data */
+#define FM_FD_CMD_UPD			0x20000000  /* Update Prepended Data */
 #define FM_FD_CMD_DTC                   0x10000000  /* Do L4 Checksum */
 
 /* TX-Port: Unsupported Format */
-- 
cgit v1.2.3


From 4664856e9ca2e5061718d639bac2741464cf3d23 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:15 +0800
Subject: dpaa_eth: add support for hardware timestamping

This patch is to add hardware timestamping support
for dpaa_eth. On Rx, timestamping is enabled for
all frames. On Tx, we only instruct the hardware
to timestamp the frames marked accordingly by the
stack.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.c | 88 ++++++++++++++++++++++++--
 drivers/net/ethernet/freescale/dpaa/dpaa_eth.h |  3 +
 2 files changed, 86 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
index 5f4e1ffa7b95..52f4a6b46cb2 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
@@ -1168,7 +1168,7 @@ static int dpaa_eth_init_tx_port(struct fman_port *port, struct dpaa_fq *errq,
 	buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
 	buf_prefix_content.pass_prs_result = true;
 	buf_prefix_content.pass_hash_result = true;
-	buf_prefix_content.pass_time_stamp = false;
+	buf_prefix_content.pass_time_stamp = true;
 	buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
 
 	params.specific_params.non_rx_params.err_fqid = errq->fqid;
@@ -1210,7 +1210,7 @@ static int dpaa_eth_init_rx_port(struct fman_port *port, struct dpaa_bp **bps,
 	buf_prefix_content.priv_data_size = buf_layout->priv_data_size;
 	buf_prefix_content.pass_prs_result = true;
 	buf_prefix_content.pass_hash_result = true;
-	buf_prefix_content.pass_time_stamp = false;
+	buf_prefix_content.pass_time_stamp = true;
 	buf_prefix_content.data_align = DPAA_FD_DATA_ALIGNMENT;
 
 	rx_p = &params.specific_params.rx_params;
@@ -1607,14 +1607,28 @@ static struct sk_buff *dpaa_cleanup_tx_fd(const struct dpaa_priv *priv,
 {
 	const enum dma_data_direction dma_dir = DMA_TO_DEVICE;
 	struct device *dev = priv->net_dev->dev.parent;
+	struct skb_shared_hwtstamps shhwtstamps;
 	dma_addr_t addr = qm_fd_addr(fd);
 	const struct qm_sg_entry *sgt;
 	struct sk_buff **skbh, *skb;
 	int nr_frags, i;
+	u64 ns;
 
 	skbh = (struct sk_buff **)phys_to_virt(addr);
 	skb = *skbh;
 
+	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+		memset(&shhwtstamps, 0, sizeof(shhwtstamps));
+
+		if (!fman_port_get_tstamp(priv->mac_dev->port[TX], (void *)skbh,
+					  &ns)) {
+			shhwtstamps.hwtstamp = ns_to_ktime(ns);
+			skb_tstamp_tx(skb, &shhwtstamps);
+		} else {
+			dev_warn(dev, "fman_port_get_tstamp failed!\n");
+		}
+	}
+
 	if (unlikely(qm_fd_get_format(fd) == qm_fd_sg)) {
 		nr_frags = skb_shinfo(skb)->nr_frags;
 		dma_unmap_single(dev, addr, qm_fd_get_offset(fd) +
@@ -2086,6 +2100,11 @@ static int dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
 	if (unlikely(err < 0))
 		goto skb_to_fd_failed;
 
+	if (priv->tx_tstamp && skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) {
+		fd.cmd |= cpu_to_be32(FM_FD_CMD_UPD);
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+	}
+
 	if (likely(dpaa_xmit(priv, percpu_stats, queue_mapping, &fd) == 0))
 		return NETDEV_TX_OK;
 
@@ -2227,6 +2246,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 						struct qman_fq *fq,
 						const struct qm_dqrr_entry *dq)
 {
+	struct skb_shared_hwtstamps *shhwtstamps;
 	struct rtnl_link_stats64 *percpu_stats;
 	struct dpaa_percpu_priv *percpu_priv;
 	const struct qm_fd *fd = &dq->fd;
@@ -2240,6 +2260,7 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	struct sk_buff *skb;
 	int *count_ptr;
 	void *vaddr;
+	u64 ns;
 
 	fd_status = be32_to_cpu(fd->status);
 	fd_format = qm_fd_get_format(fd);
@@ -2304,6 +2325,16 @@ static enum qman_cb_dqrr_result rx_default_dqrr(struct qman_portal *portal,
 	if (!skb)
 		return qman_cb_dqrr_consume;
 
+	if (priv->rx_tstamp) {
+		shhwtstamps = skb_hwtstamps(skb);
+		memset(shhwtstamps, 0, sizeof(*shhwtstamps));
+
+		if (!fman_port_get_tstamp(priv->mac_dev->port[RX], vaddr, &ns))
+			shhwtstamps->hwtstamp = ns_to_ktime(ns);
+		else
+			dev_warn(net_dev->dev.parent, "fman_port_get_tstamp failed!\n");
+	}
+
 	skb->protocol = eth_type_trans(skb, net_dev);
 
 	if (net_dev->features & NETIF_F_RXHASH && priv->keygen_in_use &&
@@ -2523,11 +2554,58 @@ static int dpaa_eth_stop(struct net_device *net_dev)
 	return err;
 }
 
+static int dpaa_ts_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	struct dpaa_priv *priv = netdev_priv(dev);
+	struct hwtstamp_config config;
+
+	if (copy_from_user(&config, rq->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		/* Couldn't disable rx/tx timestamping separately.
+		 * Do nothing here.
+		 */
+		priv->tx_tstamp = false;
+		break;
+	case HWTSTAMP_TX_ON:
+		priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
+		priv->tx_tstamp = true;
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	if (config.rx_filter == HWTSTAMP_FILTER_NONE) {
+		/* Couldn't disable rx/tx timestamping separately.
+		 * Do nothing here.
+		 */
+		priv->rx_tstamp = false;
+	} else {
+		priv->mac_dev->set_tstamp(priv->mac_dev->fman_mac, true);
+		priv->rx_tstamp = true;
+		/* TS is set for all frame types, not only those requested */
+		config.rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	return copy_to_user(rq->ifr_data, &config, sizeof(config)) ?
+			-EFAULT : 0;
+}
+
 static int dpaa_ioctl(struct net_device *net_dev, struct ifreq *rq, int cmd)
 {
-	if (!net_dev->phydev)
-		return -EINVAL;
-	return phy_mii_ioctl(net_dev->phydev, rq, cmd);
+	int ret = -EINVAL;
+
+	if (cmd == SIOCGMIIREG) {
+		if (net_dev->phydev)
+			return phy_mii_ioctl(net_dev->phydev, rq, cmd);
+	}
+
+	if (cmd == SIOCSHWTSTAMP)
+		return dpaa_ts_ioctl(net_dev, rq, cmd);
+
+	return ret;
 }
 
 static const struct net_device_ops dpaa_ops = {
diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
index bd9422082f83..af320f83c742 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h
@@ -182,6 +182,9 @@ struct dpaa_priv {
 
 	struct dpaa_buffer_layout buf_layout[2];
 	u16 rx_headroom;
+
+	bool tx_tstamp; /* Tx timestamping enabled */
+	bool rx_tstamp; /* Rx timestamping enabled */
 };
 
 /* from dpaa_ethtool.c */
-- 
cgit v1.2.3


From 17ae0b0ee9db4d553df186cfa2a92e0ac0225c44 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 25 Jun 2018 20:37:16 +0800
Subject: dpaa_eth: add the get_ts_info interface for ethtool

Added the get_ts_info interface for ethtool to check
the timestamping capability.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Acked-by: Madalin Bucur <madalin.bucur@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c | 39 ++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
index 2f933b6b2f4e..3184c8f7cdd0 100644
--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
@@ -32,6 +32,9 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/string.h>
+#include <linux/of_platform.h>
+#include <linux/net_tstamp.h>
+#include <linux/fsl/ptp_qoriq.h>
 
 #include "dpaa_eth.h"
 #include "mac.h"
@@ -515,6 +518,41 @@ static int dpaa_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
 	return ret;
 }
 
+static int dpaa_get_ts_info(struct net_device *net_dev,
+			    struct ethtool_ts_info *info)
+{
+	struct device *dev = net_dev->dev.parent;
+	struct device_node *mac_node = dev->of_node;
+	struct device_node *fman_node = NULL, *ptp_node = NULL;
+	struct platform_device *ptp_dev = NULL;
+	struct qoriq_ptp *ptp = NULL;
+
+	info->phc_index = -1;
+
+	fman_node = of_get_parent(mac_node);
+	if (fman_node)
+		ptp_node = of_parse_phandle(fman_node, "ptimer-handle", 0);
+
+	if (ptp_node)
+		ptp_dev = of_find_device_by_node(ptp_node);
+
+	if (ptp_dev)
+		ptp = platform_get_drvdata(ptp_dev);
+
+	if (ptp)
+		info->phc_index = ptp->phc_index;
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
+			 (1 << HWTSTAMP_TX_ON);
+	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+			   (1 << HWTSTAMP_FILTER_ALL);
+
+	return 0;
+}
+
 const struct ethtool_ops dpaa_ethtool_ops = {
 	.get_drvinfo = dpaa_get_drvinfo,
 	.get_msglevel = dpaa_get_msglevel,
@@ -530,4 +568,5 @@ const struct ethtool_ops dpaa_ethtool_ops = {
 	.set_link_ksettings = dpaa_set_link_ksettings,
 	.get_rxnfc = dpaa_get_rxnfc,
 	.set_rxnfc = dpaa_set_rxnfc,
+	.get_ts_info = dpaa_get_ts_info,
 };
-- 
cgit v1.2.3


From 80c18ba11a7a84cb97e39e5c9b6cdeee9f3c0728 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 25 Jun 2018 07:18:44 -0500
Subject: drm/gma500: Fix potential NULL pointer dereference
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

fb is being dereferenced before it is null checked, hence there
is a potential null pointer dereference.

Fix this by moving the pointer dereference after fb has been
properly null checked at line 74: if (!fb)

Addresses-Coverity-ID: 1470169 ("Dereference before null check")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625121844.GA12466@embeddedor.com
---
 drivers/gpu/drm/gma500/gma_display.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index 015dc9f9348d..08f17f85b801 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -60,7 +60,7 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
 	struct drm_framebuffer *fb = crtc->primary->fb;
-	struct gtt_range *gtt = to_gtt_range(fb->obj[0]);
+	struct gtt_range *gtt;
 	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
@@ -76,6 +76,8 @@ int gma_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 		goto gma_pipe_cleaner;
 	}
 
+	gtt = to_gtt_range(fb->obj[0]);
+
 	/* We are displaying this buffer, make sure it is actually loaded
 	   into the GTT */
 	ret = psb_gtt_pin(gtt);
-- 
cgit v1.2.3


From 5ae79cf18dc1a97d8d0ab420fc4d3f8674bcf0e8 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 25 Jun 2018 07:33:55 -0500
Subject: drm/gma500: Fix compile warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix the following compile warning:

warning: unused variable ‘psbfb’ [-Wunused-variable]
  struct psb_framebuffer *psbfb = to_psb_fb(fb);

Fixes: c7cbed560ce2 ("drm/gma500: Fix Medfield for drm_framebuffer move")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625123355.GA16757@embeddedor.com
---
 drivers/gpu/drm/gma500/mdfld_intel_display.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/gma500/mdfld_intel_display.c b/drivers/gpu/drm/gma500/mdfld_intel_display.c
index 881d613cc2e5..2b9fa0163dea 100644
--- a/drivers/gpu/drm/gma500/mdfld_intel_display.c
+++ b/drivers/gpu/drm/gma500/mdfld_intel_display.c
@@ -167,7 +167,6 @@ static int mdfld__intel_pipe_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_psb_private *dev_priv = dev->dev_private;
 	struct drm_framebuffer *fb = crtc->primary->fb;
 	struct gma_crtc *gma_crtc = to_gma_crtc(crtc);
-	struct psb_framebuffer *psbfb = to_psb_fb(fb);
 	int pipe = gma_crtc->pipe;
 	const struct psb_offset *map = &dev_priv->regmap[pipe];
 	unsigned long start, offset;
-- 
cgit v1.2.3


From 877375e4856c9d1b98aec30ff736896b333449e7 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 25 Jun 2018 16:07:18 +0200
Subject: l2tp: remove pppol2tp_session_close()

l2tp_core.c verifies that ->session_close() is defined before calling
it. There's no need for a stub.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 55188382845c..eea5d7844473 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -424,12 +424,6 @@ static void pppol2tp_put_sk(struct rcu_head *head)
 	sock_put(ps->__sk);
 }
 
-/* Called by l2tp_core when a session socket is being closed.
- */
-static void pppol2tp_session_close(struct l2tp_session *session)
-{
-}
-
 /* Really kill the session socket. (Called from sock_put() if
  * refcnt == 0.)
  */
@@ -573,7 +567,6 @@ static void pppol2tp_session_init(struct l2tp_session *session)
 	struct dst_entry *dst;
 
 	session->recv_skb = pppol2tp_recv;
-	session->session_close = pppol2tp_session_close;
 #if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
 	session->show = pppol2tp_show;
 #endif
-- 
cgit v1.2.3


From c3612f0e901766e1caddabd18e0a34f0e6d82e20 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 25 Jun 2018 16:07:19 +0200
Subject: l2tp: remove .show from struct l2tp_tunnel

This callback has never been implemented.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.h    | 3 ---
 net/l2tp/l2tp_debugfs.c | 3 ---
 2 files changed, 6 deletions(-)

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index c199020f8a8a..b21c20a4e08f 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -180,9 +180,6 @@ struct l2tp_tunnel {
 	struct net		*l2tp_net;	/* the net we belong to */
 
 	refcount_t		ref_count;
-#ifdef CONFIG_DEBUG_FS
-	void (*show)(struct seq_file *m, void *arg);
-#endif
 	int (*recv_payload_hook)(struct sk_buff *skb);
 	void (*old_sk_destruct)(struct sock *);
 	struct sock		*sock;		/* Parent socket */
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index e87686f7d63c..b5d7dde003ef 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -177,9 +177,6 @@ static void l2tp_dfs_seq_tunnel_show(struct seq_file *m, void *v)
 		   atomic_long_read(&tunnel->stats.rx_packets),
 		   atomic_long_read(&tunnel->stats.rx_bytes),
 		   atomic_long_read(&tunnel->stats.rx_errors));
-
-	if (tunnel->show != NULL)
-		tunnel->show(m, tunnel);
 }
 
 static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
-- 
cgit v1.2.3


From e484b1c227b6c661eba8ae424b271ed5b420ae4a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 25 Jun 2018 16:07:20 +0200
Subject: l2tp: remove l2tp_tunnel_priv()

This function, and the associated .priv field, are unused.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index b21c20a4e08f..15e1171ecf7b 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -187,8 +187,6 @@ struct l2tp_tunnel {
 						 * was created by userspace */
 
 	struct work_struct	del_work;
-
-	uint8_t			priv[0];	/* private data */
 };
 
 struct l2tp_nl_cmd_ops {
@@ -198,11 +196,6 @@ struct l2tp_nl_cmd_ops {
 	int (*session_delete)(struct l2tp_session *session);
 };
 
-static inline void *l2tp_tunnel_priv(struct l2tp_tunnel *tunnel)
-{
-	return &tunnel->priv[0];
-}
-
 static inline void *l2tp_session_priv(struct l2tp_session *session)
 {
 	return &session->priv[0];
-- 
cgit v1.2.3


From 2e67560ef6c53dae273b7c5c47a2ab4fb1ba9b30 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 25 Jun 2018 16:07:22 +0200
Subject: l2tp: don't export l2tp_session_queue_purge()

This function is only used in l2tp_core.c.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 3 +--
 net/l2tp/l2tp_core.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 40261cb68e83..3adef4c35a3a 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -783,7 +783,7 @@ EXPORT_SYMBOL(l2tp_recv_common);
 
 /* Drop skbs from the session's reorder_q
  */
-int l2tp_session_queue_purge(struct l2tp_session *session)
+static int l2tp_session_queue_purge(struct l2tp_session *session)
 {
 	struct sk_buff *skb = NULL;
 	BUG_ON(!session);
@@ -794,7 +794,6 @@ int l2tp_session_queue_purge(struct l2tp_session *session)
 	}
 	return 0;
 }
-EXPORT_SYMBOL_GPL(l2tp_session_queue_purge);
 
 /* Internal UDP receive frame. Do the real work of receiving an L2TP data frame
  * here. The skb is not on a list when we get here.
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 15e1171ecf7b..0a6e582f84d3 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -234,7 +234,6 @@ void l2tp_session_free(struct l2tp_session *session);
 void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      unsigned char *ptr, unsigned char *optr, u16 hdrflags,
 		      int length, int (*payload_hook)(struct sk_buff *skb));
-int l2tp_session_queue_purge(struct l2tp_session *session);
 int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
 void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 
-- 
cgit v1.2.3


From d08532bb5080f234f1ac45f9fc909eb15f51834b Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 25 Jun 2018 16:07:23 +0200
Subject: l2tp: don't export l2tp_tunnel_closeall()

This function is only used in l2tp_core.c.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 3 +--
 net/l2tp/l2tp_core.h | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 3adef4c35a3a..96e31f2ae7cd 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1192,7 +1192,7 @@ end:
 
 /* When the tunnel is closed, all the attached sessions need to go too.
  */
-void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
+static void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel)
 {
 	int hash;
 	struct hlist_node *walk;
@@ -1241,7 +1241,6 @@ again:
 	}
 	write_unlock_bh(&tunnel->hlist_lock);
 }
-EXPORT_SYMBOL_GPL(l2tp_tunnel_closeall);
 
 /* Tunnel socket destroy hook for UDP encapsulation */
 static void l2tp_udp_encap_destroy(struct sock *sk)
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 0a6e582f84d3..a5c09d3a5698 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -219,7 +219,6 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id,
 int l2tp_tunnel_register(struct l2tp_tunnel *tunnel, struct net *net,
 			 struct l2tp_tunnel_cfg *cfg);
 
-void l2tp_tunnel_closeall(struct l2tp_tunnel *tunnel);
 void l2tp_tunnel_delete(struct l2tp_tunnel *tunnel);
 struct l2tp_session *l2tp_session_create(int priv_size,
 					 struct l2tp_tunnel *tunnel,
-- 
cgit v1.2.3


From 363a341d190bde3f6d5f2786feefb9f1a7a45b95 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 25 Jun 2018 16:07:24 +0200
Subject: l2tp: avoid duplicate l2tp_pernet() calls

Replace 'l2tp_pernet(tunnel->l2tp_net)' with 'pn', which has been set
on the preceding line.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 96e31f2ae7cd..88c3001531b4 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -322,8 +322,7 @@ int l2tp_session_register(struct l2tp_session *session,
 
 	if (tunnel->version == L2TP_HDR_VER_3) {
 		pn = l2tp_pernet(tunnel->l2tp_net);
-		g_head = l2tp_session_id_hash_2(l2tp_pernet(tunnel->l2tp_net),
-						session->session_id);
+		g_head = l2tp_session_id_hash_2(pn, session->session_id);
 
 		spin_lock_bh(&pn->l2tp_session_hlist_lock);
 
-- 
cgit v1.2.3


From 2685fbb8044f9bd8d3b5de1fa7854fea655f2df6 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Mon, 25 Jun 2018 16:07:25 +0200
Subject: l2tp: make l2tp_xmit_core() return void

It always returns 0, and nobody reads the return value anyway.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 88c3001531b4..1ea285bad84b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1007,8 +1007,8 @@ static int l2tp_build_l2tpv3_header(struct l2tp_session *session, void *buf)
 	return bufp - optr;
 }
 
-static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
-			  struct flowi *fl, size_t data_len)
+static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
+			   struct flowi *fl, size_t data_len)
 {
 	struct l2tp_tunnel *tunnel = session->tunnel;
 	unsigned int len = skb->len;
@@ -1050,8 +1050,6 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
 		atomic_long_inc(&tunnel->stats.tx_errors);
 		atomic_long_inc(&session->stats.tx_errors);
 	}
-
-	return 0;
 }
 
 /* If caller requires the skb to have a ppp header, the header must be
-- 
cgit v1.2.3


From 99672eb6c63c5207e4e1a6283ec4fc46aafeb07c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 25 Jun 2018 16:43:55 +0200
Subject: selftests: net: Test headroom handling of ip6_gre devices

Commit 5691484df961 ("net: ip6_gre: Fix headroom request in
ip6erspan_tunnel_xmit()") and commit 01b8d064d58b ("net: ip6_gre:
Request headroom in __gre6_xmit()") fix problems in reserving headroom
in the packets tunneled through ip6gre/tap and ip6erspan netdevices.

These two patches included snippets that reproduced the issues. This
patch elevates the snippets to a full-fledged test case.

Suggested-by: David Miller <davem@davemloft.net>
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/ip6_gre_headroom.sh | 65 +++++++++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100755 tools/testing/selftests/net/ip6_gre_headroom.sh

diff --git a/tools/testing/selftests/net/ip6_gre_headroom.sh b/tools/testing/selftests/net/ip6_gre_headroom.sh
new file mode 100755
index 000000000000..5b41e8bb6e2d
--- /dev/null
+++ b/tools/testing/selftests/net/ip6_gre_headroom.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test that enough headroom is reserved for the first packet passing through an
+# IPv6 GRE-like netdevice.
+
+setup_prepare()
+{
+	ip link add h1 type veth peer name swp1
+	ip link add h3 type veth peer name swp3
+
+	ip link set dev h1 up
+	ip address add 192.0.2.1/28 dev h1
+
+	ip link add dev vh3 type vrf table 20
+	ip link set dev h3 master vh3
+	ip link set dev vh3 up
+	ip link set dev h3 up
+
+	ip link set dev swp3 up
+	ip address add dev swp3 2001:db8:2::1/64
+	ip address add dev swp3 2001:db8:2::3/64
+
+	ip link set dev swp1 up
+	tc qdisc add dev swp1 clsact
+
+	ip link add name er6 type ip6erspan \
+	   local 2001:db8:2::1 remote 2001:db8:2::2 oseq okey 123
+	ip link set dev er6 up
+
+	ip link add name gt6 type ip6gretap \
+	   local 2001:db8:2::3 remote 2001:db8:2::4
+	ip link set dev gt6 up
+
+	sleep 1
+}
+
+cleanup()
+{
+	ip link del dev gt6
+	ip link del dev er6
+	ip link del dev swp1
+	ip link del dev swp3
+	ip link del dev vh3
+}
+
+test_headroom()
+{
+	local type=$1; shift
+	local tundev=$1; shift
+
+	tc filter add dev swp1 ingress pref 1000 matchall skip_hw \
+		action mirred egress mirror dev $tundev
+	ping -I h1 192.0.2.2 -c 1 -w 2 &> /dev/null
+	tc filter del dev swp1 ingress pref 1000
+
+	# If it doesn't panic, it passes.
+	printf "TEST: %-60s  [PASS]\n" "$type headroom"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+test_headroom ip6gretap gt6
+test_headroom ip6erspan er6
-- 
cgit v1.2.3


From 2f533f6bd8300b11e8d941c9a8f51183a9d88c9c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 25 Jun 2018 20:34:41 +0200
Subject: r8169: reject unsupported WoL options

So far unsupported WoL options are silently ignored. Change this and
reject attempts to set unsupported options. This prevents situations
where a user tries to set an unsupported WoL option and is under the
impression it was successful because ethtool doesn't complain.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 1d33672c650d..70c13cc282d0 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1712,11 +1712,14 @@ static int rtl8169_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 	struct rtl8169_private *tp = netdev_priv(dev);
 	struct device *d = tp_to_dev(tp);
 
+	if (wol->wolopts & ~WAKE_ANY)
+		return -EINVAL;
+
 	pm_runtime_get_noresume(d);
 
 	rtl_lock_work(tp);
 
-	tp->saved_wolopts = wol->wolopts & WAKE_ANY;
+	tp->saved_wolopts = wol->wolopts;
 
 	if (pm_runtime_active(d))
 		__rtl8169_set_wol(tp, tp->saved_wolopts);
-- 
cgit v1.2.3


From b13ca098fd35bb0cfbe027f2415a17a6ceb6f47f Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 25 Jun 2018 23:36:21 +0300
Subject: sh_eth: fix *enum* RPADIR_BIT

The *enum*  RPADIR_BIT  was declared in the commit 86a74ff21a7a ("net:
sh_eth: add support for Renesas SuperH Ethernet") adding SH771x support,
however the SH771x manual doesn't have the RPADIR register described and,
moreover, tells why the padding insertion must not be used. The newer SoC
manuals do have RPADIR documented, though with somewhat different layout --
update the *enum* according to these manuals...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 726c55a82dd7..ae3ef5d75e40 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -403,8 +403,7 @@ enum DESC_I_BIT {
 
 /* RPADIR */
 enum RPADIR_BIT {
-	RPADIR_PADS1 = 0x20000, RPADIR_PADS0 = 0x10000,
-	RPADIR_PADR = 0x0003f,
+	RPADIR_PADS = 0x1f0000, RPADIR_PADR = 0xffff,
 };
 
 /* FDR */
-- 
cgit v1.2.3


From 470103dc840ec9cda91b5049d82f4bb599cea759 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 25 Jun 2018 23:37:06 +0300
Subject: sh_eth: remove sh_eth_cpu_data::rpadir_value

If RPADIR exists, the value written to it is always the same for all SoCs
(and derived from NET_IP_ALIGN), so there has not  been any need to store
it in the *struct* sh_eth_cpu_data...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 8 +-------
 drivers/net/ethernet/renesas/sh_eth.h | 1 -
 2 files changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index e9007b613f17..f7043ea5eed1 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -622,7 +622,6 @@ static struct sh_eth_cpu_data r7s72100_data = {
 	.tpauser	= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -672,7 +671,6 @@ static struct sh_eth_cpu_data r8a7740_data = {
 	.bculr		= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -798,7 +796,6 @@ static struct sh_eth_cpu_data r8a77980_data = {
 	.hw_swap	= 1,
 	.nbst		= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -851,7 +848,6 @@ static struct sh_eth_cpu_data sh7724_data = {
 	.tpauser	= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value	= 0x00020000, /* NET_IP_ALIGN assumed to be 2 */
 };
 
 static void sh_eth_set_rate_sh7757(struct net_device *ndev)
@@ -898,7 +894,6 @@ static struct sh_eth_cpu_data sh7757_data = {
 	.hw_swap	= 1,
 	.no_ade		= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.rtrate		= 1,
 	.dual_port	= 1,
 };
@@ -978,7 +973,6 @@ static struct sh_eth_cpu_data sh7757_data_giga = {
 	.bculr		= 1,
 	.hw_swap	= 1,
 	.rpadir		= 1,
-	.rpadir_value   = 2 << 16,
 	.no_trimd	= 1,
 	.no_ade		= 1,
 	.xdfar_rw	= 1,
@@ -1467,7 +1461,7 @@ static int sh_eth_dev_init(struct net_device *ndev)
 	/* Descriptor format */
 	sh_eth_ring_format(ndev);
 	if (mdp->cd->rpadir)
-		sh_eth_write(ndev, mdp->cd->rpadir_value, RPADIR);
+		sh_eth_write(ndev, NET_IP_ALIGN << 16, RPADIR);
 
 	/* all sh_eth int mask */
 	sh_eth_write(ndev, 0, EESIPR);
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index ae3ef5d75e40..a03d99f51ccf 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -487,7 +487,6 @@ struct sh_eth_cpu_data {
 	u32 ecsipr_value;
 	u32 fdr_value;
 	u32 fcftr_value;
-	u32 rpadir_value;
 
 	/* interrupt checking mask */
 	u32 tx_check;
-- 
cgit v1.2.3


From 60513bd82c825b659c05957e4f8106ba06f0797f Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 14:30:04 -0700
Subject: net: sched: pass extack pointer to block binds and cb registration

Pass the extact struct from a tc qdisc add to the block bind function and,
in turn, to the setup_tc ndo of binding device via the tc_block_offload
struct. Pass this back to any block callback registrations to allow
netlink logging of fails in the bind process.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c          |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c      |  2 +-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c    |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  2 +-
 drivers/net/ethernet/intel/i40evf/i40evf_main.c    |  2 +-
 drivers/net/ethernet/intel/igb/igb_main.c          |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c   |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 10 +++++----
 drivers/net/ethernet/netronome/nfp/bpf/main.c      |  2 +-
 .../net/ethernet/netronome/nfp/flower/offload.c    |  2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c  |  2 +-
 drivers/net/netdevsim/netdev.c                     |  2 +-
 include/net/pkt_cls.h                              | 11 ++++++----
 net/dsa/slave.c                                    |  2 +-
 net/sched/cls_api.c                                | 25 ++++++++++++++--------
 17 files changed, 43 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 176fc9f4d7de..b5fc6414a951 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7984,7 +7984,7 @@ static int bnxt_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, bnxt_setup_tc_block_cb,
-					     bp, bp);
+					     bp, bp, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, bnxt_setup_tc_block_cb, bp);
 		return 0;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 05d405905906..0745f2dfc80c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -173,7 +173,7 @@ static int bnxt_vf_rep_setup_tc_block(struct net_device *dev,
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
 					     bnxt_vf_rep_setup_tc_block_cb,
-					     vf_rep, vf_rep);
+					     vf_rep, vf_rep, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block,
 					bnxt_vf_rep_setup_tc_block_cb, vf_rep);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index bc03c175a3cd..96bc177d54de 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3016,7 +3016,7 @@ static int cxgb_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, cxgb_setup_tc_block_cb,
-					     pi, dev);
+					     pi, dev, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, cxgb_setup_tc_block_cb, pi);
 		return 0;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 7ad2b1b0b125..426b0ccb1fc6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -7554,7 +7554,7 @@ static int i40e_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, i40e_setup_tc_block_cb,
-					     np, np);
+					     np, np, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, i40e_setup_tc_block_cb, np);
 		return 0;
diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
index dc56a8667495..5906c1c1d19d 100644
--- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c
+++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c
@@ -2926,7 +2926,7 @@ static int i40evf_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, i40evf_setup_tc_block_cb,
-					     adapter, adapter);
+					     adapter, adapter, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, i40evf_setup_tc_block_cb,
 					adapter);
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 6a78d8272eb2..f1e3397bd405 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2728,7 +2728,7 @@ static int igb_setup_tc_block(struct igb_adapter *adapter,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, igb_setup_tc_block_cb,
-					     adapter, adapter);
+					     adapter, adapter, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb,
 					adapter);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 3e87dbbc9024..d29bd8fc3ff3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9325,7 +9325,7 @@ static int ixgbe_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, ixgbe_setup_tc_block_cb,
-					     adapter, adapter);
+					     adapter, adapter, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, ixgbe_setup_tc_block_cb,
 					adapter);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 56c1b6f5593e..134f20a182b5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3371,7 +3371,7 @@ static int mlx5e_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, mlx5e_setup_tc_block_cb,
-					     priv, priv);
+					     priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, mlx5e_setup_tc_block_cb,
 					priv);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 57987f6546e8..3f2fe95e01d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -797,7 +797,7 @@ static int mlx5e_rep_setup_tc_block(struct net_device *dev,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, mlx5e_rep_setup_tc_cb,
-					     priv, priv);
+					     priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, mlx5e_rep_setup_tc_cb, priv);
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 968b88af2ef5..d2bc335dda11 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1503,7 +1503,8 @@ static int mlxsw_sp_setup_tc_block_cb_flower(enum tc_setup_type type,
 
 static int
 mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
-				    struct tcf_block *block, bool ingress)
+				    struct tcf_block *block, bool ingress,
+				    struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 	struct mlxsw_sp_acl_block *acl_block;
@@ -1518,7 +1519,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 			return -ENOMEM;
 		block_cb = __tcf_block_cb_register(block,
 						   mlxsw_sp_setup_tc_block_cb_flower,
-						   mlxsw_sp, acl_block);
+						   mlxsw_sp, acl_block, extack);
 		if (IS_ERR(block_cb)) {
 			err = PTR_ERR(block_cb);
 			goto err_cb_register;
@@ -1596,11 +1597,12 @@ static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		err = tcf_block_cb_register(f->block, cb, mlxsw_sp_port,
-					    mlxsw_sp_port);
+					    mlxsw_sp_port, f->extack);
 		if (err)
 			return err;
 		err = mlxsw_sp_setup_tc_block_flower_bind(mlxsw_sp_port,
-							  f->block, ingress);
+							  f->block, ingress,
+							  f->extack);
 		if (err) {
 			tcf_block_cb_unregister(f->block, cb, mlxsw_sp_port);
 			return err;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index fcdfb8e7fdea..bf46f7bff912 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -206,7 +206,7 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev,
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
 					     nfp_bpf_setup_tc_block_cb,
-					     nn, nn);
+					     nn, nn, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block,
 					nfp_bpf_setup_tc_block_cb,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index c0e74aa4cb5e..a427dab4bf49 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -627,7 +627,7 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
 					     nfp_flower_setup_tc_block_cb,
-					     repr, repr);
+					     repr, repr, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block,
 					nfp_flower_setup_tc_block_cb,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cba46b62a1cd..2354e30caa78 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3776,7 +3776,7 @@ static int stmmac_setup_tc_block(struct stmmac_priv *priv,
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb,
-				priv, priv);
+				priv, priv, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv);
 		return 0;
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index ec68f38213d9..c9dacc6fcd59 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -260,7 +260,7 @@ nsim_setup_tc_block(struct net_device *dev, struct tc_block_offload *f)
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block, nsim_setup_tc_block_cb,
-					     ns, ns);
+					     ns, ns, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, nsim_setup_tc_block_cb, ns);
 		return 0;
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a3c1a2c47cd4..a2c6d35ba057 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -73,10 +73,11 @@ void tcf_block_cb_incref(struct tcf_block_cb *block_cb);
 unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb);
 struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
 					     tc_setup_cb_t *cb, void *cb_ident,
-					     void *cb_priv);
+					     void *cb_priv,
+					     struct netlink_ext_ack *extack);
 int tcf_block_cb_register(struct tcf_block *block,
 			  tc_setup_cb_t *cb, void *cb_ident,
-			  void *cb_priv);
+			  void *cb_priv, struct netlink_ext_ack *extack);
 void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb);
 void tcf_block_cb_unregister(struct tcf_block *block,
 			     tc_setup_cb_t *cb, void *cb_ident);
@@ -161,7 +162,8 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
 static inline
 struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
 					     tc_setup_cb_t *cb, void *cb_ident,
-					     void *cb_priv)
+					     void *cb_priv,
+					     struct netlink_ext_ack *extack)
 {
 	return NULL;
 }
@@ -169,7 +171,7 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
 static inline
 int tcf_block_cb_register(struct tcf_block *block,
 			  tc_setup_cb_t *cb, void *cb_ident,
-			  void *cb_priv)
+			  void *cb_priv, struct netlink_ext_ack *extack)
 {
 	return 0;
 }
@@ -596,6 +598,7 @@ struct tc_block_offload {
 	enum tc_block_command command;
 	enum tcf_block_binder_type binder_type;
 	struct tcf_block *block;
+	struct netlink_ext_ack *extack;
 };
 
 struct tc_cls_common_offload {
diff --git a/net/dsa/slave.c b/net/dsa/slave.c
index 1e3b6a6d8a40..71536c435132 100644
--- a/net/dsa/slave.c
+++ b/net/dsa/slave.c
@@ -900,7 +900,7 @@ static int dsa_slave_setup_tc_block(struct net_device *dev,
 
 	switch (f->command) {
 	case TC_BLOCK_BIND:
-		return tcf_block_cb_register(f->block, cb, dev, dev);
+		return tcf_block_cb_register(f->block, cb, dev, dev, f->extack);
 	case TC_BLOCK_UNBIND:
 		tcf_block_cb_unregister(f->block, cb, dev);
 		return 0;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index cdc3c87c53e6..8c9fb4b827a1 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -277,18 +277,21 @@ static bool tcf_block_offload_in_use(struct tcf_block *block)
 static int tcf_block_offload_cmd(struct tcf_block *block,
 				 struct net_device *dev,
 				 struct tcf_block_ext_info *ei,
-				 enum tc_block_command command)
+				 enum tc_block_command command,
+				 struct netlink_ext_ack *extack)
 {
 	struct tc_block_offload bo = {};
 
 	bo.command = command;
 	bo.binder_type = ei->binder_type;
 	bo.block = block;
+	bo.extack = extack;
 	return dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
 }
 
 static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
-				  struct tcf_block_ext_info *ei)
+				  struct tcf_block_ext_info *ei,
+				  struct netlink_ext_ack *extack)
 {
 	struct net_device *dev = q->dev_queue->dev;
 	int err;
@@ -299,10 +302,12 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
 	/* If tc offload feature is disabled and the block we try to bind
 	 * to already has some offloaded filters, forbid to bind.
 	 */
-	if (!tc_can_offload(dev) && tcf_block_offload_in_use(block))
+	if (!tc_can_offload(dev) && tcf_block_offload_in_use(block)) {
+		NL_SET_ERR_MSG(extack, "Bind to offloaded block failed as dev has offload disabled");
 		return -EOPNOTSUPP;
+	}
 
-	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND);
+	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_BIND, extack);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_inc;
 	return err;
@@ -322,7 +327,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
 
 	if (!dev->netdev_ops->ndo_setup_tc)
 		goto no_offload_dev_dec;
-	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND);
+	err = tcf_block_offload_cmd(block, dev, ei, TC_BLOCK_UNBIND, NULL);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_dec;
 	return;
@@ -612,7 +617,7 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 	if (err)
 		goto err_chain_head_change_cb_add;
 
-	err = tcf_block_offload_bind(block, q, ei);
+	err = tcf_block_offload_bind(block, q, ei, extack);
 	if (err)
 		goto err_block_offload_bind;
 
@@ -748,7 +753,8 @@ EXPORT_SYMBOL(tcf_block_cb_decref);
 
 struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
 					     tc_setup_cb_t *cb, void *cb_ident,
-					     void *cb_priv)
+					     void *cb_priv,
+					     struct netlink_ext_ack *extack)
 {
 	struct tcf_block_cb *block_cb;
 
@@ -772,11 +778,12 @@ EXPORT_SYMBOL(__tcf_block_cb_register);
 
 int tcf_block_cb_register(struct tcf_block *block,
 			  tc_setup_cb_t *cb, void *cb_ident,
-			  void *cb_priv)
+			  void *cb_priv, struct netlink_ext_ack *extack)
 {
 	struct tcf_block_cb *block_cb;
 
-	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv);
+	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
+					   extack);
 	return IS_ERR(block_cb) ? PTR_ERR(block_cb) : 0;
 }
 EXPORT_SYMBOL(tcf_block_cb_register);
-- 
cgit v1.2.3


From e56185c78b500ac4d08768278ad8a25d5b756942 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 14:30:05 -0700
Subject: net: sched: add tcf_proto_op to offload a rule

Create a new tcf_proto_op called 'reoffload' that generates a new offload
message for each node in a tcf_proto. Pointers to the tcf_proto and
whether the offload request is to add or delete the node are included.
Also included is a callback function to send the offload message to and
the option of priv data to go with the cb.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h     | 3 ---
 include/net/sch_generic.h | 6 ++++++
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 9e59ebfded62..5ff11adbe2a6 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -190,9 +190,6 @@ static inline void tcf_action_stats_update(struct tc_action *a, u64 bytes,
 #endif
 }
 
-typedef int tc_setup_cb_t(enum tc_setup_type type,
-			  void *type_data, void *cb_priv);
-
 #ifdef CONFIG_NET_CLS_ACT
 int tc_setup_cb_egdev_register(const struct net_device *dev,
 			       tc_setup_cb_t *cb, void *cb_priv);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 6488daa32f82..18adc9142b18 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -20,6 +20,9 @@ struct qdisc_walker;
 struct tcf_walker;
 struct module;
 
+typedef int tc_setup_cb_t(enum tc_setup_type type,
+			  void *type_data, void *cb_priv);
+
 struct qdisc_rate_table {
 	struct tc_ratespec rate;
 	u32		data[256];
@@ -256,6 +259,9 @@ struct tcf_proto_ops {
 					  bool *last,
 					  struct netlink_ext_ack *);
 	void			(*walk)(struct tcf_proto*, struct tcf_walker *arg);
+	int			(*reoffload)(struct tcf_proto *tp, bool add,
+					     tc_setup_cb_t *cb, void *cb_priv,
+					     struct netlink_ext_ack *extack);
 	void			(*bind_class)(void *, u32, unsigned long);
 
 	/* rtnetlink specific */
-- 
cgit v1.2.3


From 31533cba4327aefeafe8a7d57de0c737a3b2faa6 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 14:30:06 -0700
Subject: net: sched: cls_flower: implement offload tcf_proto_op

Add the reoffload tcf_proto_op in flower to generate an offload message
for each filter in the given tcf_proto. Call the specified callback with
this new offload message. The function only returns an error if the
callback rejects adding a 'hardware only' rule.

A filter contains a flag to indicate if it is in hardware or not. To
ensure the reoffload function properly maintains this flag, keep a
reference counter for the number of instances of the filter that are in
hardware. Only update the flag when this counter changes from or to 0. Add
a generic helper function to implement this behaviour.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 15 +++++++++++++++
 net/sched/cls_flower.c    | 44 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 18adc9142b18..7432100027b7 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -336,6 +336,21 @@ static inline void tcf_block_offload_dec(struct tcf_block *block, u32 *flags)
 	block->offloadcnt--;
 }
 
+static inline void
+tc_cls_offload_cnt_update(struct tcf_block *block, unsigned int *cnt,
+			  u32 *flags, bool add)
+{
+	if (add) {
+		if (!*cnt)
+			tcf_block_offload_inc(block, flags);
+		(*cnt)++;
+	} else {
+		(*cnt)--;
+		if (!*cnt)
+			tcf_block_offload_dec(block, flags);
+	}
+}
+
 static inline void qdisc_cb_private_validate(const struct sk_buff *skb, int sz)
 {
 	struct qdisc_skb_cb *qcb;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9e8b26a80fb3..352876bb901b 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -87,6 +87,7 @@ struct cls_fl_filter {
 	struct list_head list;
 	u32 handle;
 	u32 flags;
+	unsigned int in_hw_count;
 	struct rcu_work rwork;
 	struct net_device *hw_dev;
 };
@@ -289,6 +290,7 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 		fl_hw_destroy_filter(tp, f, NULL);
 		return err;
 	} else if (err > 0) {
+		f->in_hw_count = err;
 		tcf_block_offload_inc(block, &f->flags);
 	}
 
@@ -1087,6 +1089,47 @@ skip:
 	}
 }
 
+static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+			void *cb_priv, struct netlink_ext_ack *extack)
+{
+	struct cls_fl_head *head = rtnl_dereference(tp->root);
+	struct tc_cls_flower_offload cls_flower = {};
+	struct tcf_block *block = tp->chain->block;
+	struct fl_flow_mask *mask;
+	struct cls_fl_filter *f;
+	int err;
+
+	list_for_each_entry(mask, &head->masks, list) {
+		list_for_each_entry(f, &mask->filters, list) {
+			if (tc_skip_hw(f->flags))
+				continue;
+
+			tc_cls_common_offload_init(&cls_flower.common, tp,
+						   f->flags, extack);
+			cls_flower.command = add ?
+				TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
+			cls_flower.cookie = (unsigned long)f;
+			cls_flower.dissector = &mask->dissector;
+			cls_flower.mask = &f->mkey;
+			cls_flower.key = &f->key;
+			cls_flower.exts = &f->exts;
+			cls_flower.classid = f->res.classid;
+
+			err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv);
+			if (err) {
+				if (add && tc_skip_sw(f->flags))
+					return err;
+				continue;
+			}
+
+			tc_cls_offload_cnt_update(block, &f->in_hw_count,
+						  &f->flags, add);
+		}
+	}
+
+	return 0;
+}
+
 static int fl_dump_key_val(struct sk_buff *skb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
@@ -1438,6 +1481,7 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = {
 	.change		= fl_change,
 	.delete		= fl_delete,
 	.walk		= fl_walk,
+	.reoffload	= fl_reoffload,
 	.dump		= fl_dump,
 	.bind_class	= fl_bind_class,
 	.owner		= THIS_MODULE,
-- 
cgit v1.2.3


From 0efd1b3a13bfabc8b70e79bd22aa413d6d2ad7a5 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 14:30:07 -0700
Subject: net: sched: cls_matchall: implement offload tcf_proto_op

Add the reoffload tcf_proto_op in matchall to generate an offload message
for each filter in the given tcf_proto. Call the specified callback with
this new offload message. The function only returns an error if the
callback rejects adding a 'hardware only' rule.

Ensure matchall flags correctly report if the rule is in hw by keeping a
reference counter for the number of instances of the rule offloaded. Only
update the flag when this counter changes from or to 0.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_matchall.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c
index 47b207ef7762..af16f36ed578 100644
--- a/net/sched/cls_matchall.c
+++ b/net/sched/cls_matchall.c
@@ -21,6 +21,7 @@ struct cls_mall_head {
 	struct tcf_result res;
 	u32 handle;
 	u32 flags;
+	unsigned int in_hw_count;
 	struct rcu_work rwork;
 };
 
@@ -95,6 +96,7 @@ static int mall_replace_hw_filter(struct tcf_proto *tp,
 		mall_destroy_hw_filter(tp, head, cookie, NULL);
 		return err;
 	} else if (err > 0) {
+		head->in_hw_count = err;
 		tcf_block_offload_inc(block, &head->flags);
 	}
 
@@ -235,6 +237,35 @@ skip:
 	arg->count++;
 }
 
+static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+			  void *cb_priv, struct netlink_ext_ack *extack)
+{
+	struct cls_mall_head *head = rtnl_dereference(tp->root);
+	struct tc_cls_matchall_offload cls_mall = {};
+	struct tcf_block *block = tp->chain->block;
+	int err;
+
+	if (tc_skip_hw(head->flags))
+		return 0;
+
+	tc_cls_common_offload_init(&cls_mall.common, tp, head->flags, extack);
+	cls_mall.command = add ?
+		TC_CLSMATCHALL_REPLACE : TC_CLSMATCHALL_DESTROY;
+	cls_mall.exts = &head->exts;
+	cls_mall.cookie = (unsigned long)head;
+
+	err = cb(TC_SETUP_CLSMATCHALL, &cls_mall, cb_priv);
+	if (err) {
+		if (add && tc_skip_sw(head->flags))
+			return err;
+		return 0;
+	}
+
+	tc_cls_offload_cnt_update(block, &head->in_hw_count, &head->flags, add);
+
+	return 0;
+}
+
 static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh,
 		     struct sk_buff *skb, struct tcmsg *t)
 {
@@ -289,6 +320,7 @@ static struct tcf_proto_ops cls_mall_ops __read_mostly = {
 	.change		= mall_change,
 	.delete		= mall_delete,
 	.walk		= mall_walk,
+	.reoffload	= mall_reoffload,
 	.dump		= mall_dump,
 	.bind_class	= mall_bind_class,
 	.owner		= THIS_MODULE,
-- 
cgit v1.2.3


From 530d995123fe647d28566d81ff9562fe6cbaff94 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 14:30:08 -0700
Subject: net: sched: cls_u32: implement offload tcf_proto_op

Add the offload tcf_proto_op in cls_u32 to generate an offload message for
each filter and the hashtable in the given tcf_proto. Call the specified
callback with this new offload message. The function only returns an error
if the callback rejects adding a 'hardware only' rule.

A filter contains a flag to indicate if it is in hardware or not. To
ensure the offload function properly maintains this flag, keep a reference
counter for the number of instances of the filter that are in hardware.
Only update the flag when this counter changes from or to 0.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_u32.c | 111 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 111 insertions(+)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index fb861f90fde6..d5d2a6dc3921 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -62,6 +62,7 @@ struct tc_u_knode {
 	struct tc_u32_pcnt __percpu *pf;
 #endif
 	u32			flags;
+	unsigned int		in_hw_count;
 #ifdef CONFIG_CLS_U32_MARK
 	u32			val;
 	u32			mask;
@@ -571,6 +572,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 		u32_remove_hw_knode(tp, n, NULL);
 		return err;
 	} else if (err > 0) {
+		n->in_hw_count = err;
 		tcf_block_offload_inc(block, &n->flags);
 	}
 
@@ -1199,6 +1201,114 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 	}
 }
 
+static int u32_reoffload_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
+			       bool add, tc_setup_cb_t *cb, void *cb_priv,
+			       struct netlink_ext_ack *extack)
+{
+	struct tc_cls_u32_offload cls_u32 = {};
+	int err;
+
+	tc_cls_common_offload_init(&cls_u32.common, tp, ht->flags, extack);
+	cls_u32.command = add ? TC_CLSU32_NEW_HNODE : TC_CLSU32_DELETE_HNODE;
+	cls_u32.hnode.divisor = ht->divisor;
+	cls_u32.hnode.handle = ht->handle;
+	cls_u32.hnode.prio = ht->prio;
+
+	err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv);
+	if (err && add && tc_skip_sw(ht->flags))
+		return err;
+
+	return 0;
+}
+
+static int u32_reoffload_knode(struct tcf_proto *tp, struct tc_u_knode *n,
+			       bool add, tc_setup_cb_t *cb, void *cb_priv,
+			       struct netlink_ext_ack *extack)
+{
+	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
+	struct tcf_block *block = tp->chain->block;
+	struct tc_cls_u32_offload cls_u32 = {};
+	int err;
+
+	tc_cls_common_offload_init(&cls_u32.common, tp, n->flags, extack);
+	cls_u32.command = add ?
+		TC_CLSU32_REPLACE_KNODE : TC_CLSU32_DELETE_KNODE;
+	cls_u32.knode.handle = n->handle;
+
+	if (add) {
+		cls_u32.knode.fshift = n->fshift;
+#ifdef CONFIG_CLS_U32_MARK
+		cls_u32.knode.val = n->val;
+		cls_u32.knode.mask = n->mask;
+#else
+		cls_u32.knode.val = 0;
+		cls_u32.knode.mask = 0;
+#endif
+		cls_u32.knode.sel = &n->sel;
+		cls_u32.knode.exts = &n->exts;
+		if (n->ht_down)
+			cls_u32.knode.link_handle = ht->handle;
+	}
+
+	err = cb(TC_SETUP_CLSU32, &cls_u32, cb_priv);
+	if (err) {
+		if (add && tc_skip_sw(n->flags))
+			return err;
+		return 0;
+	}
+
+	tc_cls_offload_cnt_update(block, &n->in_hw_count, &n->flags, add);
+
+	return 0;
+}
+
+static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+			 void *cb_priv, struct netlink_ext_ack *extack)
+{
+	struct tc_u_common *tp_c = tp->data;
+	struct tc_u_hnode *ht;
+	struct tc_u_knode *n;
+	unsigned int h;
+	int err;
+
+	for (ht = rtnl_dereference(tp_c->hlist);
+	     ht;
+	     ht = rtnl_dereference(ht->next)) {
+		if (ht->prio != tp->prio)
+			continue;
+
+		/* When adding filters to a new dev, try to offload the
+		 * hashtable first. When removing, do the filters before the
+		 * hashtable.
+		 */
+		if (add && !tc_skip_hw(ht->flags)) {
+			err = u32_reoffload_hnode(tp, ht, add, cb, cb_priv,
+						  extack);
+			if (err)
+				return err;
+		}
+
+		for (h = 0; h <= ht->divisor; h++) {
+			for (n = rtnl_dereference(ht->ht[h]);
+			     n;
+			     n = rtnl_dereference(n->next)) {
+				if (tc_skip_hw(n->flags))
+					continue;
+
+				err = u32_reoffload_knode(tp, n, add, cb,
+							  cb_priv, extack);
+				if (err)
+					return err;
+			}
+		}
+
+		if (!add && !tc_skip_hw(ht->flags))
+			u32_reoffload_hnode(tp, ht, add, cb, cb_priv, extack);
+	}
+
+	return 0;
+}
+
 static void u32_bind_class(void *fh, u32 classid, unsigned long cl)
 {
 	struct tc_u_knode *n = fh;
@@ -1336,6 +1446,7 @@ static struct tcf_proto_ops cls_u32_ops __read_mostly = {
 	.change		=	u32_change,
 	.delete		=	u32_delete,
 	.walk		=	u32_walk,
+	.reoffload	=	u32_reoffload,
 	.dump		=	u32_dump,
 	.bind_class	=	u32_bind_class,
 	.owner		=	THIS_MODULE,
-- 
cgit v1.2.3


From 7e916b76805f11c1686a43ab5ead9a9b1a0a5945 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 14:30:09 -0700
Subject: net: sched: cls_bpf: implement offload tcf_proto_op

Add the offload tcf_proto_op in cls_bpf to generate an offload message for
each bpf prog in the given tcf_proto. Call the specified callback with
this new offload message. The function only returns an error if the
callback rejects adding a 'hardware only' prog.

A prog contains a flag to indicate if it is in hardware or not. To
ensure the offload function properly maintains this flag, keep a reference
counter for the number of instances of the prog that are in hardware. Only
update the flag when this counter changes from or to 0.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_bpf.c | 39 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 1aa7f6511065..66e0ac9811f9 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -43,6 +43,7 @@ struct cls_bpf_prog {
 	struct tcf_result res;
 	bool exts_integrated;
 	u32 gen_flags;
+	unsigned int in_hw_count;
 	struct tcf_exts exts;
 	u32 handle;
 	u16 bpf_num_ops;
@@ -174,6 +175,7 @@ static int cls_bpf_offload_cmd(struct tcf_proto *tp, struct cls_bpf_prog *prog,
 			cls_bpf_offload_cmd(tp, oldprog, prog, extack);
 			return err;
 		} else if (err > 0) {
+			prog->in_hw_count = err;
 			tcf_block_offload_inc(block, &prog->gen_flags);
 		}
 	}
@@ -652,6 +654,42 @@ skip:
 	}
 }
 
+static int cls_bpf_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
+			     void *cb_priv, struct netlink_ext_ack *extack)
+{
+	struct cls_bpf_head *head = rtnl_dereference(tp->root);
+	struct tcf_block *block = tp->chain->block;
+	struct tc_cls_bpf_offload cls_bpf = {};
+	struct cls_bpf_prog *prog;
+	int err;
+
+	list_for_each_entry(prog, &head->plist, link) {
+		if (tc_skip_hw(prog->gen_flags))
+			continue;
+
+		tc_cls_common_offload_init(&cls_bpf.common, tp, prog->gen_flags,
+					   extack);
+		cls_bpf.command = TC_CLSBPF_OFFLOAD;
+		cls_bpf.exts = &prog->exts;
+		cls_bpf.prog = add ? prog->filter : NULL;
+		cls_bpf.oldprog = add ? NULL : prog->filter;
+		cls_bpf.name = prog->bpf_name;
+		cls_bpf.exts_integrated = prog->exts_integrated;
+
+		err = cb(TC_SETUP_CLSBPF, &cls_bpf, cb_priv);
+		if (err) {
+			if (add && tc_skip_sw(prog->gen_flags))
+				return err;
+			continue;
+		}
+
+		tc_cls_offload_cnt_update(block, &prog->in_hw_count,
+					  &prog->gen_flags, add);
+	}
+
+	return 0;
+}
+
 static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
 	.kind		=	"bpf",
 	.owner		=	THIS_MODULE,
@@ -662,6 +700,7 @@ static struct tcf_proto_ops cls_bpf_ops __read_mostly = {
 	.change		=	cls_bpf_change,
 	.delete		=	cls_bpf_delete,
 	.walk		=	cls_bpf_walk,
+	.reoffload	=	cls_bpf_reoffload,
 	.dump		=	cls_bpf_dump,
 	.bind_class	=	cls_bpf_bind_class,
 };
-- 
cgit v1.2.3


From 326367427cc09d38e4c1d145131ee2e228ac94c5 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Mon, 25 Jun 2018 14:30:10 -0700
Subject: net: sched: call reoffload op on block callback reg

Call the reoffload tcf_proto_op on all tcf_proto nodes in all chains of a
block when a callback tries to register to a block that already has
offloaded rules. If all existing rules cannot be offloaded then the
registration is rejected. This replaces the previous policy of rejecting
such callback registration outright.

On unregistration of a callback, the rules are flushed for that given cb.
The implementation of block sharing in the NFP driver, for example,
duplicates shared rules to all devs bound to a block. This meant that
rules could still exist in hw even after a device is unbound from a block
(assuming the block still remains active).

Signed-off-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c |  4 +-
 include/net/pkt_cls.h                          |  6 ++-
 net/sched/cls_api.c                            | 54 ++++++++++++++++++++++----
 3 files changed, 52 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d2bc335dda11..52437363766a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1542,7 +1542,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 
 err_block_bind:
 	if (!tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block_cb);
+		__tcf_block_cb_unregister(block, block_cb);
 err_cb_register:
 		mlxsw_sp_acl_block_destroy(acl_block);
 	}
@@ -1572,7 +1572,7 @@ mlxsw_sp_setup_tc_block_flower_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 	err = mlxsw_sp_acl_block_unbind(mlxsw_sp, acl_block,
 					mlxsw_sp_port, ingress);
 	if (!err && !tcf_block_cb_decref(block_cb)) {
-		__tcf_block_cb_unregister(block_cb);
+		__tcf_block_cb_unregister(block, block_cb);
 		mlxsw_sp_acl_block_destroy(acl_block);
 	}
 }
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a2c6d35ba057..4070b8eb6d14 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -78,7 +78,8 @@ struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
 int tcf_block_cb_register(struct tcf_block *block,
 			  tc_setup_cb_t *cb, void *cb_ident,
 			  void *cb_priv, struct netlink_ext_ack *extack);
-void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb);
+void __tcf_block_cb_unregister(struct tcf_block *block,
+			       struct tcf_block_cb *block_cb);
 void tcf_block_cb_unregister(struct tcf_block *block,
 			     tc_setup_cb_t *cb, void *cb_ident);
 
@@ -177,7 +178,8 @@ int tcf_block_cb_register(struct tcf_block *block,
 }
 
 static inline
-void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+void __tcf_block_cb_unregister(struct tcf_block *block,
+			       struct tcf_block_cb *block_cb)
 {
 }
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 8c9fb4b827a1..bbf8dda96b0e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -751,19 +751,53 @@ unsigned int tcf_block_cb_decref(struct tcf_block_cb *block_cb)
 }
 EXPORT_SYMBOL(tcf_block_cb_decref);
 
+static int
+tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb,
+			    void *cb_priv, bool add, bool offload_in_use,
+			    struct netlink_ext_ack *extack)
+{
+	struct tcf_chain *chain;
+	struct tcf_proto *tp;
+	int err;
+
+	list_for_each_entry(chain, &block->chain_list, list) {
+		for (tp = rtnl_dereference(chain->filter_chain); tp;
+		     tp = rtnl_dereference(tp->next)) {
+			if (tp->ops->reoffload) {
+				err = tp->ops->reoffload(tp, add, cb, cb_priv,
+							 extack);
+				if (err && add)
+					goto err_playback_remove;
+			} else if (add && offload_in_use) {
+				err = -EOPNOTSUPP;
+				NL_SET_ERR_MSG(extack, "Filter HW offload failed - classifier without re-offloading support");
+				goto err_playback_remove;
+			}
+		}
+	}
+
+	return 0;
+
+err_playback_remove:
+	tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use,
+				    extack);
+	return err;
+}
+
 struct tcf_block_cb *__tcf_block_cb_register(struct tcf_block *block,
 					     tc_setup_cb_t *cb, void *cb_ident,
 					     void *cb_priv,
 					     struct netlink_ext_ack *extack)
 {
 	struct tcf_block_cb *block_cb;
+	int err;
 
-	/* At this point, playback of previous block cb calls is not supported,
-	 * so forbid to register to block which already has some offloaded
-	 * filters present.
-	 */
-	if (tcf_block_offload_in_use(block))
-		return ERR_PTR(-EOPNOTSUPP);
+	/* Replay any already present rules */
+	err = tcf_block_playback_offloads(block, cb, cb_priv, true,
+					  tcf_block_offload_in_use(block),
+					  extack);
+	if (err)
+		return ERR_PTR(err);
 
 	block_cb = kzalloc(sizeof(*block_cb), GFP_KERNEL);
 	if (!block_cb)
@@ -788,8 +822,12 @@ int tcf_block_cb_register(struct tcf_block *block,
 }
 EXPORT_SYMBOL(tcf_block_cb_register);
 
-void __tcf_block_cb_unregister(struct tcf_block_cb *block_cb)
+void __tcf_block_cb_unregister(struct tcf_block *block,
+			       struct tcf_block_cb *block_cb)
 {
+	tcf_block_playback_offloads(block, block_cb->cb, block_cb->cb_priv,
+				    false, tcf_block_offload_in_use(block),
+				    NULL);
 	list_del(&block_cb->list);
 	kfree(block_cb);
 }
@@ -803,7 +841,7 @@ void tcf_block_cb_unregister(struct tcf_block *block,
 	block_cb = tcf_block_cb_lookup(block, cb, cb_ident);
 	if (!block_cb)
 		return;
-	__tcf_block_cb_unregister(block_cb);
+	__tcf_block_cb_unregister(block, block_cb);
 }
 EXPORT_SYMBOL(tcf_block_cb_unregister);
 
-- 
cgit v1.2.3


From 68cc444dab1e70e59a719b7bf44bcaacbffa7496 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Mon, 25 Jun 2018 15:49:49 -0700
Subject: mdio-mux-gpio: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], this
allocates the values buffer during the callback instead of putting it
on the stack.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-gpio.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/mdio-mux-gpio.c b/drivers/net/phy/mdio-mux-gpio.c
index 082ffef0dec4..bc90764a8b8d 100644
--- a/drivers/net/phy/mdio-mux-gpio.c
+++ b/drivers/net/phy/mdio-mux-gpio.c
@@ -20,23 +20,23 @@
 struct mdio_mux_gpio_state {
 	struct gpio_descs *gpios;
 	void *mux_handle;
+	int values[];
 };
 
 static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
 				   void *data)
 {
 	struct mdio_mux_gpio_state *s = data;
-	int values[s->gpios->ndescs];
 	unsigned int n;
 
 	if (current_child == desired_child)
 		return 0;
 
 	for (n = 0; n < s->gpios->ndescs; n++)
-		values[n] = (desired_child >> n) & 1;
+		s->values[n] = (desired_child >> n) & 1;
 
 	gpiod_set_array_value_cansleep(s->gpios->ndescs, s->gpios->desc,
-				       values);
+				       s->values);
 
 	return 0;
 }
@@ -44,15 +44,21 @@ static int mdio_mux_gpio_switch_fn(int current_child, int desired_child,
 static int mdio_mux_gpio_probe(struct platform_device *pdev)
 {
 	struct mdio_mux_gpio_state *s;
+	struct gpio_descs *gpios;
 	int r;
 
-	s = devm_kzalloc(&pdev->dev, sizeof(*s), GFP_KERNEL);
-	if (!s)
+	gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW);
+	if (IS_ERR(gpios))
+		return PTR_ERR(gpios);
+
+	s = devm_kzalloc(&pdev->dev, struct_size(s, values, gpios->ndescs),
+			 GFP_KERNEL);
+	if (!s) {
+		gpiod_put_array(gpios);
 		return -ENOMEM;
+	}
 
-	s->gpios = gpiod_get_array(&pdev->dev, NULL, GPIOD_OUT_LOW);
-	if (IS_ERR(s->gpios))
-		return PTR_ERR(s->gpios);
+	s->gpios = gpios;
 
 	r = mdio_mux_init(&pdev->dev, pdev->dev.of_node,
 			  mdio_mux_gpio_switch_fn, &s->mux_handle, s, NULL);
-- 
cgit v1.2.3


From 27a2628b3c24ce8ef23bd393f5514f8f45188f08 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 26 Jun 2018 01:20:32 +0200
Subject: selftests: forwarding: mirror_gre_vlan_bridge_1q: Unset rp_filter

The IP addresses of tunnel endpoint at H3 are set at the VLAN device
$h3.555. Therefore when test_gretap_untagged_egress() sets vlan 555 to
egress untagged at $swp3, $h3's rp_filter rejects these packets. The
test then spuriously fails.

Therefore turn off net.ipv4.conf.{all, $h3}.rp_filter.

Fixes: 9c7c8a82442c ("selftests: forwarding: mirror_gre_vlan_bridge_1q: Add more tests")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh        | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
index 5dbc7a08f4bd..1ac5038ae256 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -39,6 +39,12 @@ setup_prepare()
 	swp3=${NETIFS[p5]}
 	h3=${NETIFS[p6]}
 
+	# gt4's remote address is at $h3.555, not $h3. Thus the packets arriving
+	# directly to $h3 for test_gretap_untagged_egress() are rejected by
+	# rp_filter and the test spuriously fails.
+	sysctl_set net.ipv4.conf.all.rp_filter 0
+	sysctl_set net.ipv4.conf.$h3.rp_filter 0
+
 	vrf_prepare
 	mirror_gre_topo_create
 
@@ -65,6 +71,9 @@ cleanup()
 
 	mirror_gre_topo_destroy
 	vrf_cleanup
+
+	sysctl_restore net.ipv4.conf.$h3.rp_filter
+	sysctl_restore net.ipv4.conf.all.rp_filter
 }
 
 test_vlan_match()
-- 
cgit v1.2.3


From b66c9b911fe6ca188002b342b05c43deab4491a3 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 26 Jun 2018 08:58:35 -0300
Subject: ASoC: soc-utils: Fix unregistration order

The unregistration should happen in the opposite order of
the registration, so change it accordingly.

No real issue has been noticed, but it is good practice to
keep the correct unregistration order.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-utils.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c
index 2d9e98bd1530..a863bb3f66c2 100644
--- a/sound/soc/soc-utils.c
+++ b/sound/soc/soc-utils.c
@@ -381,6 +381,6 @@ int __init snd_soc_util_init(void)
 
 void __exit snd_soc_util_exit(void)
 {
-	platform_device_unregister(soc_dummy_dev);
 	platform_driver_unregister(&soc_dummy_driver);
+	platform_device_unregister(soc_dummy_dev);
 }
-- 
cgit v1.2.3


From c486a185744c593417a126aebb119771c1bbe670 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:05 +0100
Subject: ASoC: q6adm: dt-bindings: add compatible string to routing

Add compatible string to routing so that it can support DT based module
autoloading.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/qcom,q6adm.txt | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/qcom,q6adm.txt b/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
index cb709e5dbc44..bbae426cdfb1 100644
--- a/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,q6adm.txt
@@ -18,6 +18,11 @@ used by the apr service device.
 = ADM routing
 "routing" subnode of the ADM node represents adm routing specific configuration
 
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6adm-routing".
+
 - #sound-dai-cells
 	Usage: required
 	Value type: <u32>
@@ -28,6 +33,7 @@ q6adm@8 {
 	compatible = "qcom,q6adm";
 	reg = <APR_SVC_ADM>;
 	q6routing: routing {
+		compatible = "qcom,q6adm-routing";
 		#sound-dai-cells = <0>;
 	};
 };
-- 
cgit v1.2.3


From 9618b706672db1b595c7076389a833078335417c Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:06 +0100
Subject: ASoC: q6asm: dt-bindings: add compatible string to dais

Add compatible string to dais so that it can support DT based module
autoloading.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/qcom,q6asm.txt | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/qcom,q6asm.txt b/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
index 2178eb91146f..f9c7bd8c1bc0 100644
--- a/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,q6asm.txt
@@ -17,6 +17,11 @@ used by the apr service device.
 = ASM DAIs (Digial Audio Interface)
 "dais" subnode of the ASM node represents dai specific configuration
 
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6asm-dais".
+
 - #sound-dai-cells
 	Usage: required
 	Value type: <u32>
@@ -28,6 +33,7 @@ q6asm@7 {
 	compatible = "qcom,q6asm";
 	reg = <APR_SVC_ASM>;
 	q6asmdai: dais {
+		compatible = "qcom,q6asm-dais";
 		#sound-dai-cells = <1>;
 	};
 };
-- 
cgit v1.2.3


From e43792c6e5027ad3f0280f5a2e6952b0d436b19b Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:07 +0100
Subject: ASoC: q6afe: dt-bindings: add compatible string to dais

Add compatible string to dais so that it can support DT based module
autoloading.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/qcom,q6afe.txt | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/qcom,q6afe.txt b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
index bdbf87df8c0b..a8179409c194 100644
--- a/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,q6afe.txt
@@ -17,6 +17,11 @@ used by all apr services. Must contain the following properties.
 subnode of "dais" representing board specific dai setup.
 "dais" node should have following properties followed by dai children.
 
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,q6afe-dais"
+
 - #sound-dai-cells
 	Usage: required
 	Value type: <u32>
@@ -100,6 +105,7 @@ q6afe@4 {
 	reg = <APR_SVC_AFE>;
 
 	dais {
+		compatible = "qcom,q6afe-dais";
 		#sound-dai-cells = <1>;
 		#address-cells = <1>;
 		#size-cells = <0>;
-- 
cgit v1.2.3


From f614c9b070ed149bbaac4edefb2b5fcb7755c4b0 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:08 +0100
Subject: ASoC: qdsp6: q6adm: use of_platform_populate/depopulate()

Now that the child nodes have there own compatible strings,
Use of_platform_populate/depopulate() instead of less common
of_platform_device_create()/destroy().

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6adm.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6adm.c b/sound/soc/qcom/qdsp6/q6adm.c
index 9983c665a941..932c3ebfd252 100644
--- a/sound/soc/qcom/qdsp6/q6adm.c
+++ b/sound/soc/qcom/qdsp6/q6adm.c
@@ -64,7 +64,6 @@ struct q6adm {
 	struct aprv2_ibasic_rsp_result_t result;
 	struct mutex lock;
 	wait_queue_head_t matrix_map_wait;
-	struct platform_device *pdev_routing;
 };
 
 struct q6adm_cmd_device_open_v5 {
@@ -588,7 +587,6 @@ EXPORT_SYMBOL_GPL(q6adm_close);
 static int q6adm_probe(struct apr_device *adev)
 {
 	struct device *dev = &adev->dev;
-	struct device_node *dais_np;
 	struct q6adm *adm;
 
 	adm = devm_kzalloc(&adev->dev, sizeof(*adm), GFP_KERNEL);
@@ -605,22 +603,12 @@ static int q6adm_probe(struct apr_device *adev)
 	INIT_LIST_HEAD(&adm->copps_list);
 	spin_lock_init(&adm->copps_list_lock);
 
-	dais_np = of_get_child_by_name(dev->of_node, "routing");
-	if (dais_np) {
-		adm->pdev_routing = of_platform_device_create(dais_np,
-							   "q6routing", dev);
-		of_node_put(dais_np);
-	}
-
-	return 0;
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
 static int q6adm_remove(struct apr_device *adev)
 {
-	struct q6adm *adm = dev_get_drvdata(&adev->dev);
-
-	if (adm->pdev_routing)
-		of_platform_device_destroy(&adm->pdev_routing->dev, NULL);
+	of_platform_depopulate(&adev->dev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 4aac7e2773030d667491fbb6d97c9f467fdcbc05 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:09 +0100
Subject: ASoC: qdsp6: q6asm: use of_platform_populate/depopulate()

Now that the child nodes have there own compatible strings,
Use of_platform_populate/depopulate() instead of less common
of_platform_device_create()/destroy().

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6asm.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6asm.c b/sound/soc/qcom/qdsp6/q6asm.c
index 530852385cad..c4fd28f168d5 100644
--- a/sound/soc/qcom/qdsp6/q6asm.c
+++ b/sound/soc/qcom/qdsp6/q6asm.c
@@ -177,7 +177,6 @@ struct q6asm {
 	struct platform_device *pcmdev;
 	spinlock_t slock;
 	struct audio_client *session[MAX_SESSIONS + 1];
-	struct platform_device *pdev_dais;
 };
 
 struct audio_client {
@@ -1344,7 +1343,6 @@ EXPORT_SYMBOL_GPL(q6asm_cmd_nowait);
 static int q6asm_probe(struct apr_device *adev)
 {
 	struct device *dev = &adev->dev;
-	struct device_node *dais_np;
 	struct q6asm *q6asm;
 
 	q6asm = devm_kzalloc(dev, sizeof(*q6asm), GFP_KERNEL);
@@ -1359,22 +1357,12 @@ static int q6asm_probe(struct apr_device *adev)
 	spin_lock_init(&q6asm->slock);
 	dev_set_drvdata(dev, q6asm);
 
-	dais_np = of_get_child_by_name(dev->of_node, "dais");
-	if (dais_np) {
-		q6asm->pdev_dais = of_platform_device_create(dais_np,
-							   "q6asm-dai", dev);
-		of_node_put(dais_np);
-	}
-
-	return 0;
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
 static int q6asm_remove(struct apr_device *adev)
 {
-	struct q6asm *q6asm = dev_get_drvdata(&adev->dev);
-
-	if (q6asm->pdev_dais)
-		of_platform_device_destroy(&q6asm->pdev_dais->dev, NULL);
+	of_platform_depopulate(&adev->dev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 01afbd45f78cb0557db18c3ba768eea3e9576cfd Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:10 +0100
Subject: ASoC: qdsp6: q6afe: use of_platform_populate/depopulate()

Now that the child nodes have there own compatible strings,
Use of_platform_populate/depopulate() instead of less common
of_platform_device_create()/destroy().

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c
index 01f43218984b..621b67b34db9 100644
--- a/sound/soc/qcom/qdsp6/q6afe.c
+++ b/sound/soc/qcom/qdsp6/q6afe.c
@@ -316,7 +316,6 @@ struct q6afe {
 	struct mutex lock;
 	struct list_head port_list;
 	spinlock_t port_list_lock;
-	struct platform_device *pdev_dais;
 };
 
 struct afe_port_cmd_device_start {
@@ -1438,7 +1437,6 @@ static int q6afe_probe(struct apr_device *adev)
 {
 	struct q6afe *afe;
 	struct device *dev = &adev->dev;
-	struct device_node *dais_np;
 
 	afe = devm_kzalloc(dev, sizeof(*afe), GFP_KERNEL);
 	if (!afe)
@@ -1453,22 +1451,12 @@ static int q6afe_probe(struct apr_device *adev)
 
 	dev_set_drvdata(dev, afe);
 
-	dais_np = of_get_child_by_name(dev->of_node, "dais");
-	if (dais_np) {
-		afe->pdev_dais = of_platform_device_create(dais_np,
-							   "q6afe-dai", dev);
-		of_node_put(dais_np);
-	}
-
-	return 0;
+	return of_platform_populate(dev->of_node, NULL, NULL, dev);
 }
 
 static int q6afe_remove(struct apr_device *adev)
 {
-	struct q6afe *afe = dev_get_drvdata(&adev->dev);
-
-	if (afe->pdev_dais)
-		of_platform_device_destroy(&afe->pdev_dais->dev, NULL);
+	of_platform_depopulate(&adev->dev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From eb7cc9be6e9ce17e69252a6fc00e75a5b08201ab Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:11 +0100
Subject: ASoC: qdsp6: q6afe-dai: support dt based module loading

This patch uses new compatible string to make DT based module loading work.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe-dai.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index 5002dd05bf27..1d2e5013c121 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -1290,9 +1290,16 @@ static int q6afe_dai_dev_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id q6afe_dai_device_id[] = {
+	{ .compatible = "qcom,q6afe-dais" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6afe_dai_device_id);
+
 static struct platform_driver q6afe_dai_platform_driver = {
 	.driver = {
 		.name = "q6afe-dai",
+		.of_match_table = of_match_ptr(q6afe_dai_device_id),
 	},
 	.probe = q6afe_dai_dev_probe,
 	.remove = q6afe_dai_dev_remove,
-- 
cgit v1.2.3


From 1ce09ef36fb190fa207fdb3e31fc1c8caa292125 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:12 +0100
Subject: ASoC: qdsp6: q6asm-dai: support dt based module loading

This patch uses new compatible string to make DT based module loading work.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6asm-dai.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
index 349c6a883c63..1196dc7483d2 100644
--- a/sound/soc/qcom/qdsp6/q6asm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -611,9 +611,16 @@ static int q6asm_dai_dev_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id q6asm_dai_device_id[] = {
+	{ .compatible = "qcom,q6asm-dais" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6asm_dai_device_id);
+
 static struct platform_driver q6asm_dai_platform_driver = {
 	.driver = {
 		.name = "q6asm-dai",
+		.of_match_table = of_match_ptr(q6asm_dai_device_id),
 	},
 	.probe = q6asm_dai_probe,
 	.remove = q6asm_dai_dev_remove,
-- 
cgit v1.2.3


From f48bde4bfbcf434d6aef604c1c50d68b12a4bc45 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:13 +0100
Subject: ASoC: qdsp6: q6routing: support dt based module loading

This patch uses new compatible string to make DT based module loading work.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6routing.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index 593f66b8622f..ab696bf8d1d3 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -993,9 +993,16 @@ static int q6pcm_routing_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct of_device_id q6pcm_routing_device_id[] = {
+	{ .compatible = "qcom,q6adm-routing" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, q6pcm_routing_device_id);
+
 static struct platform_driver q6pcm_routing_platform_driver = {
 	.driver = {
 		.name = "q6routing",
+		.of_match_table = of_match_ptr(q6pcm_routing_device_id),
 	},
 	.probe = q6pcm_routing_probe,
 	.remove = q6pcm_routing_remove,
-- 
cgit v1.2.3


From 2d12c20b98ad610892151da37367f2d018181455 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:14 +0100
Subject: ASoC: qcom: apq8096: remove redundant owner assignment

module owner is already set in platform_driver_register(), so remove this
redundant assignment.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/apq8096.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index 239b8cb77bdb..cab8c4ff7c00 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -246,7 +246,6 @@ static struct platform_driver msm_snd_apq8096_driver = {
 	.remove = apq8096_platform_remove,
 	.driver = {
 		.name = "msm-snd-apq8096",
-		.owner = THIS_MODULE,
 		.of_match_table = msm_snd_apq8096_dt_match,
 	},
 };
-- 
cgit v1.2.3


From 972562f7aaaa261ec6e1ac14fed0c5bdd0dfb1cb Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:15 +0100
Subject: ASoC: qdsp6: q6routing: add proper error check

q6adm_open can return error pointer or a null in error cases.
Fix the return handling.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6routing.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index ab696bf8d1d3..c80fdbc2442e 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -310,7 +310,7 @@ int q6routing_stream_open(int fedai_id, int perf_mode,
 			      session->channels, topology, perf_mode,
 			      session->bits_per_sample, 0, 0);
 
-	if (!copp) {
+	if (IS_ERR_OR_NULL(copp)) {
 		mutex_unlock(&routing_data->lock);
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From f339155a4063cf3177bb38f6e83760951148e86b Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Tue, 26 Jun 2018 10:20:16 +0100
Subject: ASoC: qdsp6: q6asm: remove unused struct q6asm member

pcmdev in struct q6asm seems be left over and unused, so just remove it.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Acked-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6asm.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/soc/qcom/qdsp6/q6asm.c b/sound/soc/qcom/qdsp6/q6asm.c
index c4fd28f168d5..2b2c7233bb5f 100644
--- a/sound/soc/qcom/qdsp6/q6asm.c
+++ b/sound/soc/qcom/qdsp6/q6asm.c
@@ -174,7 +174,6 @@ struct q6asm {
 	struct device *dev;
 	struct q6core_svc_api_info ainfo;
 	wait_queue_head_t mem_wait;
-	struct platform_device *pcmdev;
 	spinlock_t slock;
 	struct audio_client *session[MAX_SESSIONS + 1];
 };
-- 
cgit v1.2.3


From cccd289f12d0e827070c847b1ff96ba02eb20eaf Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 16 Jun 2018 19:02:03 -0700
Subject: Documentation/process: fix reST table border error

Fix reST error in Documentation/process/:

Documentation/process/2.Process.rst:131: ERROR: Malformed table.
Bottom/header table border does not match top border.

Fixes: 8962e40c1993 ("docs: update kernel versions and dates in tables")

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Tim Bird <tbird20d@gmail.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/process/2.Process.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/process/2.Process.rst b/Documentation/process/2.Process.rst
index a9c46dd0706b..51d0349c7809 100644
--- a/Documentation/process/2.Process.rst
+++ b/Documentation/process/2.Process.rst
@@ -134,7 +134,7 @@ and their maintainers are:
 	4.4	Greg Kroah-Hartman	(very long-term stable kernel)
 	4.9	Greg Kroah-Hartman
 	4.14	Greg Kroah-Hartman
-	======  ======================  ===========================
+	======  ======================  ==============================
 
 The selection of a kernel for long-term support is purely a matter of a
 maintainer having the need and the time to maintain that release.  There
-- 
cgit v1.2.3


From 83d4fcb3a0b36aafb0c9c1c625782a9db561f339 Mon Sep 17 00:00:00 2001
From: Martin Kepplinger <martink@posteo.de>
Date: Fri, 22 Jun 2018 09:32:11 +0200
Subject: Documentation: nommu-map: Fix duplicate word typo

Signed-off-by: Martin Kepplinger <martink@posteo.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/nommu-mmap.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/nommu-mmap.txt b/Documentation/nommu-mmap.txt
index 69556f0d494b..530fed08de2c 100644
--- a/Documentation/nommu-mmap.txt
+++ b/Documentation/nommu-mmap.txt
@@ -47,7 +47,7 @@ and it's also much more restricted in the latter case:
            appropriate mapping protection capabilities. Ramfs, romfs, cramfs
            and mtd might all permit this.
 
-	 - If the backing device device can't or won't permit direct sharing,
+	 - If the backing device can't or won't permit direct sharing,
            but does have the NOMMU_MAP_COPY capability, then a copy of the
            appropriate bit of the file will be read into a contiguous bit of
            memory and any extraneous space beyond the EOF will be cleared
-- 
cgit v1.2.3


From fc1ca3d5b4b9532fff76fa21f7d22efdf02d38b7 Mon Sep 17 00:00:00 2001
From: Yang Shi <yang.shi@linux.alibaba.com>
Date: Tue, 19 Jun 2018 07:59:18 +0800
Subject: doc: add description to dirtytime_expire_seconds

commit 1efff914afac8a965ad63817ecf8861a927c2ace ("fs: add
dirtytime_expire_seconds sysctl") introduced dirtytime_expire_seconds
knob, but there is not description about it in
Documentation/sysctl/vm.txt.

Add the description for it.

Cc: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/sysctl/vm.txt | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 697ef8c225df..960e82759ffb 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -27,6 +27,7 @@ Currently, these files are in /proc/sys/vm:
 - dirty_bytes
 - dirty_expire_centisecs
 - dirty_ratio
+- dirtytime_expire_seconds
 - dirty_writeback_centisecs
 - drop_caches
 - extfrag_threshold
@@ -178,6 +179,18 @@ The total available memory is not equal to total system memory.
 
 ==============================================================
 
+dirtytime_expire_seconds
+
+When a lazytime inode is constantly having its pages dirtied, the inode with
+an updated timestamp will never get chance to be written out.  And, if the
+only thing that has happened on the file system is a dirtytime inode caused
+by an atime update, a worker will be scheduled to make sure that inode
+eventually gets pushed out to disk.  This tunable is used to define when dirty
+inode is old enough to be eligible for writeback by the kernel flusher threads.
+And, it is also used as the interval to wakeup dirtytime_writeback thread.
+
+==============================================================
+
 dirty_writeback_centisecs
 
 The kernel flusher threads will periodically wake up and write `old' data
-- 
cgit v1.2.3


From c1ec85ff408db77f5c97ae71b8854faed40e89f1 Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@vaga.pv.it>
Date: Wed, 6 Jun 2018 00:48:58 +0200
Subject: doc:doc-guide: fix a typo and an error

Fix a typo in sphinx.rst and a minor error in parse-header.rst

Signed-off-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/doc-guide/parse-headers.rst | 2 +-
 Documentation/doc-guide/sphinx.rst        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/doc-guide/parse-headers.rst b/Documentation/doc-guide/parse-headers.rst
index 82a3e43b6864..684490c68acb 100644
--- a/Documentation/doc-guide/parse-headers.rst
+++ b/Documentation/doc-guide/parse-headers.rst
@@ -133,7 +133,7 @@ For both statements, \ **type**\  can be either one of the following:
 
 \ **symbol**\
 
- The ignore or replace statement will apply to the name of enum statements
+ The ignore or replace statement will apply to the name of enum value
  at C_FILE.
 
  For replace statements, \ **new_value**\  will automatically use :c:type:
diff --git a/Documentation/doc-guide/sphinx.rst b/Documentation/doc-guide/sphinx.rst
index a2417633fdd8..f0796daa95b4 100644
--- a/Documentation/doc-guide/sphinx.rst
+++ b/Documentation/doc-guide/sphinx.rst
@@ -28,7 +28,7 @@ The ReST markups currently used by the Documentation/ files are meant to be
 built with ``Sphinx`` version 1.3 or upper. If you're desiring to build
 PDF outputs, it is recommended to use version 1.4.6 or upper.
 
-There's a script that checks for the Spinx requirements. Please see
+There's a script that checks for the Sphinx requirements. Please see
 :ref:`sphinx-pre-install` for further details.
 
 Most distributions are shipped with Sphinx, but its toolchain is fragile,
-- 
cgit v1.2.3


From f3821276f62c80184f4b7543e423ec5c7f43bbe1 Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@vaga.pv.it>
Date: Wed, 6 Jun 2018 00:48:59 +0200
Subject: doc:sphinx: fix parse-header description

The description speaks about the option ``--man`` but it
does not exist. Instead, there is the option ``--usage``

    $ ./Documentation/sphinx/parse-headers.pl --man
    Unknown option: man
    Usage:
        parse_headers.pl [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]

        Where <options> can be: --debug, --help or --man.

Signed-off-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/doc-guide/parse-headers.rst | 2 +-
 Documentation/sphinx/parse-headers.pl     | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/doc-guide/parse-headers.rst b/Documentation/doc-guide/parse-headers.rst
index 684490c68acb..24cfaa15dd81 100644
--- a/Documentation/doc-guide/parse-headers.rst
+++ b/Documentation/doc-guide/parse-headers.rst
@@ -32,7 +32,7 @@ SYNOPSIS
 
 \ **parse_headers.pl**\  [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]
 
-Where <options> can be: --debug, --help or --man.
+Where <options> can be: --debug, --help or --usage.
 
 
 OPTIONS
diff --git a/Documentation/sphinx/parse-headers.pl b/Documentation/sphinx/parse-headers.pl
index d410f47567e9..c518050ffc3f 100755
--- a/Documentation/sphinx/parse-headers.pl
+++ b/Documentation/sphinx/parse-headers.pl
@@ -344,7 +344,7 @@ enums and defines and create cross-references to a Sphinx book.
 
 B<parse_headers.pl> [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]
 
-Where <options> can be: --debug, --help or --man.
+Where <options> can be: --debug, --help or --usage.
 
 =head1 OPTIONS
 
-- 
cgit v1.2.3


From 85c32d9c6f3ebcb6807f2a6a54b2578cf281654a Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@vaga.pv.it>
Date: Wed, 6 Jun 2018 00:49:00 +0200
Subject: doc: move away translations from top-level index

In translations/ we have now a dedicated index.rst where we add/remove
references to translations. Translations are in English alphabetical
order.

Signed-off-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/index.rst              | 24 ++++--------------------
 Documentation/translations/index.rst | 12 ++++++++++++
 2 files changed, 16 insertions(+), 20 deletions(-)
 create mode 100644 Documentation/translations/index.rst

diff --git a/Documentation/index.rst b/Documentation/index.rst
index fdc585703498..20c00a9f2a93 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -102,29 +102,13 @@ implementation.
 
    sh/index
 
-Korean translations
--------------------
+Translations
+------------
 
 .. toctree::
-   :maxdepth: 1
-
-   translations/ko_KR/index
-
-Chinese translations
---------------------
-
-.. toctree::
-   :maxdepth: 1
-
-   translations/zh_CN/index
-
-Japanese translations
----------------------
-
-.. toctree::
-   :maxdepth: 1
+   :maxdepth: 2
 
-   translations/ja_JP/index
+   translations/index
 
 Indices and tables
 ==================
diff --git a/Documentation/translations/index.rst b/Documentation/translations/index.rst
new file mode 100644
index 000000000000..4969c58920ef
--- /dev/null
+++ b/Documentation/translations/index.rst
@@ -0,0 +1,12 @@
+.. _translations:
+
+============
+Translations
+============
+
+.. toctree::
+   :maxdepth: 1
+
+   zh_CN/index
+   ko_KR/index
+   ja_JP/index
-- 
cgit v1.2.3


From aa586e25744ad0a481fdba2da05041af235c110d Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@vaga.pv.it>
Date: Wed, 6 Jun 2018 00:49:01 +0200
Subject: doc: add some chapter labels

The idea is to make it easier to create references (doc-guide does the same).
This will be used, for example but not only, in translations to point to
the main document.

Signed-off-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/index.rst                | 2 ++
 Documentation/kernel-hacking/index.rst | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/Documentation/index.rst b/Documentation/index.rst
index 20c00a9f2a93..5d310d960f82 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -3,6 +3,8 @@
    You can adapt this file completely to your liking, but it should at least
    contain the root `toctree` directive.
 
+.. _linux_doc:
+
 The Linux Kernel documentation
 ==============================
 
diff --git a/Documentation/kernel-hacking/index.rst b/Documentation/kernel-hacking/index.rst
index fcb0eda3cca3..f53027652290 100644
--- a/Documentation/kernel-hacking/index.rst
+++ b/Documentation/kernel-hacking/index.rst
@@ -1,3 +1,5 @@
+.. _kernel_hacking:
+
 =====================
 Kernel Hacking Guides
 =====================
-- 
cgit v1.2.3


From 3ece641656ad6a392ee3a122700923972da53fe8 Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@vaga.pv.it>
Date: Wed, 6 Jun 2018 00:49:02 +0200
Subject: doc: add Italian language skeleton

Signed-off-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/translations/index.rst               |   1 +
 .../translations/it_IT/disclaimer-ita.rst          |  13 +++
 Documentation/translations/it_IT/index.rst         | 112 +++++++++++++++++++++
 MAINTAINERS                                        |   6 ++
 4 files changed, 132 insertions(+)
 create mode 100644 Documentation/translations/it_IT/disclaimer-ita.rst
 create mode 100644 Documentation/translations/it_IT/index.rst

diff --git a/Documentation/translations/index.rst b/Documentation/translations/index.rst
index 4969c58920ef..7f77c52d33aa 100644
--- a/Documentation/translations/index.rst
+++ b/Documentation/translations/index.rst
@@ -8,5 +8,6 @@ Translations
    :maxdepth: 1
 
    zh_CN/index
+   it_IT/index
    ko_KR/index
    ja_JP/index
diff --git a/Documentation/translations/it_IT/disclaimer-ita.rst b/Documentation/translations/it_IT/disclaimer-ita.rst
new file mode 100644
index 000000000000..d68e52de6a5d
--- /dev/null
+++ b/Documentation/translations/it_IT/disclaimer-ita.rst
@@ -0,0 +1,13 @@
+:orphan:
+
+.. note::
+   This document is maintained by Federico Vaga <federico.vaga@vaga.pv.it>.
+   If you find any difference between this document and the original file or a
+   problem with the translation, please contact the maintainer of this file.
+   Following people helped to translate or review:
+   Alessia Mantegazza <amantegazza@vaga.pv.it>
+
+.. warning::
+   The purpose of this file is to be easier to read and understand for Italian
+   speakers and is not intended as a fork. So, if you have any comments or
+   updates for this file please try to update the original English file first.
diff --git a/Documentation/translations/it_IT/index.rst b/Documentation/translations/it_IT/index.rst
new file mode 100644
index 000000000000..7613a9f9e6f9
--- /dev/null
+++ b/Documentation/translations/it_IT/index.rst
@@ -0,0 +1,112 @@
+.. _it_linux_doc:
+
+===================
+Traduzione italiana
+===================
+
+L'obiettivo di questa traduzione è di rendere più facile la lettura e
+la comprensione per chi preferisce leggere in lingua italiana.
+Tenete presente che la documentazione di riferimento rimane comunque
+quella in lingua inglese: :ref:`linux_doc`
+
+Questa traduzione cerca di essere il più fedele possibile all'originale ma
+è ovvio che alcune frasi vadano trasformate: non aspettatevi una traduzione
+letterale. Quando possibile, si eviteranno gli inglesismi ed al loro posto
+verranno utilizzate le corrispettive parole italiane.
+
+Se notate che la traduzione non è più aggiornata potete contattare
+direttamente il manutentore della traduzione italiana.
+
+Se notate che la documentazione contiene errori o dimenticanze, allora
+verificate la documentazione di riferimento in lingua inglese. Se il problema
+è presente anche nella documentazione di riferimento, contattate il suo
+manutentore. Se avete problemi a scrivere in inglese, potete comunque
+riportare il problema al manutentore della traduzione italiana.
+
+Manutentore della traduzione italiana: Federico Vaga <federico.vaga@vaga.pv.it>
+
+La documentazione del kernel Linux
+==================================
+
+Questo è il livello principale della documentazione del kernel in
+lingua italiana. La traduzione è incompleta, noterete degli avvisi
+che vi segnaleranno la mancanza di una traduzione o di un gruppo di
+traduzioni.
+
+Più in generale, la documentazione, come il kernel stesso, sono in
+costante sviluppo; particolarmente vero in quanto stiamo lavorando
+alla riorganizzazione della documentazione in modo più coerente.
+I miglioramenti alla documentazione sono sempre i benvenuti; per cui,
+se vuoi aiutare, iscriviti alla lista di discussione linux-doc presso
+vger.kernel.org.
+
+Documentazione sulla licenza dei sorgenti
+-----------------------------------------
+
+I seguenti documenti descrivono la licenza usata nei sorgenti del kernel Linux
+(GPLv2), come licenziare i singoli file; inoltre troverete i riferimenti al
+testo integrale della licenza.
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione per gli utenti
+-----------------------------
+
+I seguenti manuali sono scritti per gli *utenti* del kernel - ovvero,
+coloro che cercano di farlo funzionare in modo ottimale su un dato sistema
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione per gli sviluppatori di applicazioni
+---------------------------------------------------
+
+Il manuale delle API verso lo spazio utente è una collezione di documenti
+che descrivono le interfacce del kernel viste dagli sviluppatori
+di applicazioni.
+
+.. warning::
+
+    TODO ancora da tradurre
+
+
+Introduzione allo sviluppo del kernel
+-------------------------------------
+
+Questi manuali contengono informazioni su come contribuire allo sviluppo
+del kernel.
+Attorno al kernel Linux gira una comunità molto grande con migliaia di
+sviluppatori che contribuiscono ogni anno. Come in ogni grande comunità,
+sapere come le cose vengono fatte renderà il processo di integrazione delle
+vostre modifiche molto più semplice
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione della API del kernel
+-----------------------------------
+
+Questi manuali forniscono dettagli su come funzionano i sottosistemi del
+kernel dal punto di vista degli sviluppatori del kernel. Molte delle
+informazioni contenute in questi manuali sono prese direttamente dai
+file sorgenti, informazioni aggiuntive vengono aggiunte solo se necessarie
+(o almeno ci proviamo — probabilmente *non* tutto quello che è davvero
+necessario).
+
+.. warning::
+
+    TODO ancora da tradurre
+
+Documentazione specifica per architettura
+-----------------------------------------
+
+Questi manuali forniscono dettagli di programmazione per le diverse
+implementazioni d'architettura.
+
+.. warning::
+
+    TODO ancora da tradurre
diff --git a/MAINTAINERS b/MAINTAINERS
index 9d5eeff51b5f..71aaf3d790a2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4401,6 +4401,12 @@ X:	Documentation/spi
 X:	Documentation/media
 T:	git git://git.lwn.net/linux.git docs-next
 
+DOCUMENTATION/ITALIAN
+M:	Federico Vaga <federico.vaga@vaga.pv.it>
+L:	linux-doc@vger.kernel.org
+S:	Maintained
+F:	Documentation/translations/it_IT
+
 DONGWOON DW9714 LENS VOICE COIL DRIVER
 M:	Sakari Ailus <sakari.ailus@linux.intel.com>
 L:	linux-media@vger.kernel.org
-- 
cgit v1.2.3


From 37912da4387f24368f4c91c5fd9685d0bf3ea4dc Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@vaga.pv.it>
Date: Wed, 6 Jun 2018 00:49:03 +0200
Subject: doc:it_IT: translation for doc-guide

This is the complete translation of 'doc-guide' in Italian.

Please note that code comments will stay in English because
thats the language that everyone should use to write comments.

External files (svg, dot) are taken from Documentation/doc-guide
instead of copying them into the Italian translation.

Signed-off-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Alessia Mantegazza <amantegazza@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 .../translations/it_IT/doc-guide/index.rst         |  24 +
 .../translations/it_IT/doc-guide/kernel-doc.rst    | 554 +++++++++++++++++++++
 .../translations/it_IT/doc-guide/parse-headers.rst | 196 ++++++++
 .../translations/it_IT/doc-guide/sphinx.rst        | 457 +++++++++++++++++
 Documentation/translations/it_IT/index.rst         |   5 +
 5 files changed, 1236 insertions(+)
 create mode 100644 Documentation/translations/it_IT/doc-guide/index.rst
 create mode 100644 Documentation/translations/it_IT/doc-guide/kernel-doc.rst
 create mode 100644 Documentation/translations/it_IT/doc-guide/parse-headers.rst
 create mode 100644 Documentation/translations/it_IT/doc-guide/sphinx.rst

diff --git a/Documentation/translations/it_IT/doc-guide/index.rst b/Documentation/translations/it_IT/doc-guide/index.rst
new file mode 100644
index 000000000000..7a6562b547ee
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/index.rst
@@ -0,0 +1,24 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+.. _it_doc_guide:
+
+==========================================
+Come scrivere la documentazione del kernel
+==========================================
+
+.. toctree::
+   :maxdepth: 1
+
+   sphinx.rst
+   kernel-doc.rst
+   parse-headers.rst
+
+.. only::  subproject and html
+
+   Indices
+   =======
+
+   * :ref:`genindex`
diff --git a/Documentation/translations/it_IT/doc-guide/kernel-doc.rst b/Documentation/translations/it_IT/doc-guide/kernel-doc.rst
new file mode 100644
index 000000000000..2bf1c1e2f394
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/kernel-doc.rst
@@ -0,0 +1,554 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+.. _it_kernel_doc:
+
+Scrivere i commenti in kernel-doc
+=================================
+
+Nei file sorgenti del kernel Linux potrete trovare commenti di documentazione
+strutturanti secondo il formato kernel-doc. Essi possono descrivere funzioni,
+tipi di dati, e l'architettura del codice.
+
+.. note:: Il formato kernel-doc può sembrare simile a gtk-doc o Doxygen ma
+   in realtà è molto differente per ragioni storiche. I sorgenti del kernel
+   contengono decine di migliaia di commenti kernel-doc. Siete pregati
+   d'attenervi allo stile qui descritto.
+
+La struttura kernel-doc è estratta a partire dai commenti; da questi viene
+generato il `dominio Sphinx per il C`_ con un'adeguata descrizione per le
+funzioni ed i tipi di dato con i loro relativi collegamenti. Le descrizioni
+vengono filtrare per cercare i riferimenti ed i marcatori.
+
+Vedere di seguito per maggiori dettagli.
+
+.. _`dominio Sphinx per il C`: http://www.sphinx-doc.org/en/stable/domains.html
+
+Tutte le funzioni esportate verso i moduli esterni utilizzando
+``EXPORT_SYMBOL`` o ``EXPORT_SYMBOL_GPL`` dovrebbero avere un commento
+kernel-doc. Quando l'intenzione è di utilizzarle nei moduli, anche le funzioni
+e le strutture dati nei file d'intestazione dovrebbero avere dei commenti
+kernel-doc.
+
+È considerata una buona pratica quella di fornire una documentazione formattata
+secondo kernel-doc per le funzioni che sono visibili da altri file del kernel
+(ovvero, che non siano dichiarate utilizzando ``static``). Raccomandiamo,
+inoltre, di fornire una documentazione kernel-doc anche per procedure private
+(ovvero, dichiarate "static") al fine di fornire una struttura più coerente
+dei sorgenti. Quest'ultima raccomandazione ha una priorità più bassa ed è a
+discrezione dal manutentore (MAINTAINER) del file sorgente.
+
+
+
+Sicuramente la documentazione formattata con kernel-doc è necessaria per
+le funzioni che sono esportate verso i moduli esterni utilizzando
+``EXPORT_SYMBOL`` o ``EXPORT_SYMBOL_GPL``.
+
+Cerchiamo anche di fornire una documentazione formattata secondo kernel-doc
+per le funzioni che sono visibili da altri file del kernel (ovvero, che non
+siano dichiarate utilizzando "static")
+
+Raccomandiamo, inoltre, di fornire una documentazione formattata con kernel-doc
+anche per procedure private (ovvero, dichiarate "static") al fine di fornire
+una struttura più coerente dei sorgenti. Questa raccomandazione ha una priorità
+più bassa ed è a discrezione dal manutentore (MAINTAINER) del file sorgente.
+
+Le strutture dati visibili nei file di intestazione dovrebbero essere anch'esse
+documentate utilizzando commenti formattati con kernel-doc.
+
+Come formattare i commenti kernel-doc
+-------------------------------------
+
+I commenti kernel-doc iniziano con il marcatore ``/**``. Il programma
+``kernel-doc`` estrarrà i commenti marchiati in questo modo. Il resto
+del commento è formattato come un normale commento multilinea, ovvero
+con un asterisco all'inizio d'ogni riga e che si conclude con ``*/``
+su una riga separata.
+
+I commenti kernel-doc di funzioni e tipi dovrebbero essere posizionati
+appena sopra la funzione od il tipo che descrivono. Questo allo scopo di
+aumentare la probabilità che chi cambia il codice si ricordi di aggiornare
+anche la documentazione. I commenti kernel-doc di tipo più generale possono
+essere posizionati ovunque nel file.
+
+Al fine di verificare che i commenti siano formattati correttamente, potete
+eseguire il programma ``kernel-doc`` con un livello di verbosità alto e senza
+che questo produca alcuna documentazione. Per esempio::
+
+	scripts/kernel-doc -v -none drivers/foo/bar.c
+
+Il formato della documentazione è verificato della procedura di generazione
+del kernel quando viene richiesto di effettuare dei controlli extra con GCC::
+
+	make W=n
+
+Documentare le funzioni
+------------------------
+
+Generalmente il formato di un commento kernel-doc per funzioni e
+macro simil-funzioni è il seguente::
+
+  /**
+   * function_name() - Brief description of function.
+   * @arg1: Describe the first argument.
+   * @arg2: Describe the second argument.
+   *        One can provide multiple line descriptions
+   *        for arguments.
+   *
+   * A longer description, with more discussion of the function function_name()
+   * that might be useful to those using or modifying it. Begins with an
+   * empty comment line, and may include additional embedded empty
+   * comment lines.
+   *
+   * The longer description may have multiple paragraphs.
+   *
+   * Context: Describes whether the function can sleep, what locks it takes,
+   *          releases, or expects to be held. It can extend over multiple
+   *          lines.
+   * Return: Describe the return value of foobar.
+   *
+   * The return value description can also have multiple paragraphs, and should
+   * be placed at the end of the comment block.
+   */
+
+La descrizione introduttiva (*brief description*) che segue il nome della
+funzione può continuare su righe successive e termina con la descrizione di
+un argomento, una linea di commento vuota, oppure la fine del commento.
+
+Parametri delle funzioni
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Ogni argomento di una funzione dovrebbe essere descritto in ordine, subito
+dopo la descrizione introduttiva.  Non lasciare righe vuote né fra la
+descrizione introduttiva e quella degli argomenti, né fra gli argomenti.
+
+Ogni ``@argument:`` può estendersi su più righe.
+
+.. note::
+
+   Se la descrizione di ``@argument:`` si estende su più righe,
+   la continuazione dovrebbe iniziare alla stessa colonna della riga
+   precedente::
+
+      * @argument: some long description
+      *            that continues on next lines
+
+   or::
+
+      * @argument:
+      *		some long description
+      *		that continues on next lines
+
+Se una funzione ha un numero variabile di argomento, la sua descrizione
+dovrebbe essere scritta con la notazione kernel-doc::
+
+      * @...: description
+
+Contesto delle funzioni
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Il contesto in cui le funzioni vengono chiamate viene descritto in una
+sezione chiamata ``Context``. Questo dovrebbe informare sulla possibilità
+che una funzione dorma (*sleep*) o che possa essere chiamata in un contesto
+d'interruzione, così come i *lock* che prende, rilascia e che si aspetta che
+vengano presi dal chiamante.
+
+Esempi::
+
+  * Context: Any context.
+  * Context: Any context. Takes and releases the RCU lock.
+  * Context: Any context. Expects <lock> to be held by caller.
+  * Context: Process context. May sleep if @gfp flags permit.
+  * Context: Process context. Takes and releases <mutex>.
+  * Context: Softirq or process context. Takes and releases <lock>, BH-safe.
+  * Context: Interrupt context.
+
+Valore di ritorno
+~~~~~~~~~~~~~~~~~
+
+Il valore di ritorno, se c'è, viene descritto in una sezione dedicata di nome
+``Return``.
+
+.. note::
+
+  #) La descrizione multiriga non riconosce il termine d'una riga, per cui
+     se provate a formattare bene il vostro testo come nel seguente esempio::
+
+	* Return:
+	* 0 - OK
+	* -EINVAL - invalid argument
+	* -ENOMEM - out of memory
+
+     le righe verranno unite e il risultato sarà::
+
+	Return: 0 - OK -EINVAL - invalid argument -ENOMEM - out of memory
+
+     Quindi, se volete che le righe vengano effettivamente generate, dovete
+     utilizzare una lista ReST, ad esempio::
+
+      * Return:
+      * * 0		- OK to runtime suspend the device
+      * * -EBUSY	- Device should not be runtime suspended
+
+  #) Se il vostro testo ha delle righe che iniziano con una frase seguita dai
+     due punti, allora ognuna di queste frasi verrà considerata come il nome
+     di una nuova sezione, e probabilmente non produrrà gli effetti desiderati.
+
+Documentare strutture, unioni ed enumerazioni
+---------------------------------------------
+
+Generalmente il formato di un commento kernel-doc per struct, union ed enum è::
+
+  /**
+   * struct struct_name - Brief description.
+   * @member1: Description of member1.
+   * @member2: Description of member2.
+   *           One can provide multiple line descriptions
+   *           for members.
+   *
+   * Description of the structure.
+   */
+
+Nell'esempio qui sopra, potete sostituire ``struct`` con ``union`` o ``enum``
+per descrivere unioni ed enumerati. ``member`` viene usato per indicare i
+membri di strutture ed unioni, ma anche i valori di un tipo enumerato.
+
+La descrizione introduttiva (*brief description*) che segue il nome della
+funzione può continuare su righe successive e termina con la descrizione di
+un argomento, una linea di commento vuota, oppure la fine del commento.
+
+Membri
+~~~~~~
+
+I membri di strutture, unioni ed enumerati devo essere documentati come i
+parametri delle funzioni; seguono la descrizione introduttiva e possono
+estendersi su più righe.
+
+All'interno d'una struttura o d'un unione, potete utilizzare le etichette
+``private:`` e ``public:``. I campi che sono nell'area ``private:`` non
+verranno inclusi nella documentazione finale.
+
+Le etichette ``private:`` e ``public:`` devono essere messe subito dopo
+il marcatore di un commento ``/*``. Opzionalmente, possono includere commenti
+fra ``:`` e il marcatore di fine commento ``*/``.
+
+Esempio::
+
+  /**
+   * struct my_struct - short description
+   * @a: first member
+   * @b: second member
+   * @d: fourth member
+   *
+   * Longer description
+   */
+  struct my_struct {
+      int a;
+      int b;
+  /* private: internal use only */
+      int c;
+  /* public: the next one is public */
+      int d;
+  };
+
+Strutture ed unioni annidate
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+È possibile documentare strutture ed unioni annidate, ad esempio::
+
+      /**
+       * struct nested_foobar - a struct with nested unions and structs
+       * @memb1: first member of anonymous union/anonymous struct
+       * @memb2: second member of anonymous union/anonymous struct
+       * @memb3: third member of anonymous union/anonymous struct
+       * @memb4: fourth member of anonymous union/anonymous struct
+       * @bar: non-anonymous union
+       * @bar.st1: struct st1 inside @bar
+       * @bar.st2: struct st2 inside @bar
+       * @bar.st1.memb1: first member of struct st1 on union bar
+       * @bar.st1.memb2: second member of struct st1 on union bar
+       * @bar.st2.memb1: first member of struct st2 on union bar
+       * @bar.st2.memb2: second member of struct st2 on union bar
+       */
+      struct nested_foobar {
+        /* Anonymous union/struct*/
+        union {
+          struct {
+            int memb1;
+            int memb2;
+        }
+          struct {
+            void *memb3;
+            int memb4;
+          }
+        }
+        union {
+          struct {
+            int memb1;
+            int memb2;
+          } st1;
+          struct {
+            void *memb1;
+            int memb2;
+          } st2;
+        } bar;
+      };
+
+.. note::
+
+   #) Quando documentate una struttura od unione annidata, ad esempio
+      di nome ``foo``, il suo campo ``bar`` dev'essere documentato
+      usando ``@foo.bar:``
+   #) Quando la struttura od unione annidata è anonima, il suo campo
+      ``bar`` dev'essere documentato usando ``@bar:``
+
+Commenti in linea per la documentazione dei membri
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+I membri d'una struttura possono essere documentati in linea all'interno
+della definizione stessa. Ci sono due stili: una singola riga di commento
+che inizia con ``/**`` e finisce con ``*/``; commenti multi riga come
+qualsiasi altro commento kernel-doc::
+
+  /**
+   * struct foo - Brief description.
+   * @foo: The Foo member.
+   */
+  struct foo {
+        int foo;
+        /**
+         * @bar: The Bar member.
+         */
+        int bar;
+        /**
+         * @baz: The Baz member.
+         *
+         * Here, the member description may contain several paragraphs.
+         */
+        int baz;
+        union {
+                /** @foobar: Single line description. */
+                int foobar;
+        };
+        /** @bar2: Description for struct @bar2 inside @foo */
+        struct {
+                /**
+                 * @bar2.barbar: Description for @barbar inside @foo.bar2
+                 */
+                int barbar;
+        } bar2;
+  };
+
+
+Documentazione dei tipi di dato
+-------------------------------
+Generalmente il formato di un commento kernel-doc per typedef è
+il seguente::
+
+  /**
+   * typedef type_name - Brief description.
+   *
+   * Description of the type.
+   */
+
+Anche i tipi di dato per prototipi di funzione possono essere documentati::
+
+  /**
+   * typedef type_name - Brief description.
+   * @arg1: description of arg1
+   * @arg2: description of arg2
+   *
+   * Description of the type.
+   *
+   * Context: Locking context.
+   * Return: Meaning of the return value.
+   */
+   typedef void (*type_name)(struct v4l2_ctrl *arg1, void *arg2);
+
+Marcatori e riferimenti
+-----------------------
+
+All'interno dei commenti di tipo kernel-doc vengono riconosciuti i seguenti
+*pattern* che vengono convertiti in marcatori reStructuredText ed in riferimenti
+del `dominio Sphinx per il C`_.
+
+.. attention:: Questi sono riconosciuti **solo** all'interno di commenti
+               kernel-doc, e **non** all'interno di documenti reStructuredText.
+
+``funcname()``
+  Riferimento ad una funzione.
+
+``@parameter``
+  Nome di un parametro di una funzione (nessun riferimento, solo formattazione).
+
+``%CONST``
+  Il nome di una costante (nessun riferimento, solo formattazione)
+
+````literal````
+  Un blocco di testo che deve essere riportato così com'è. La rappresentazione
+  finale utilizzerà caratteri a ``spaziatura fissa``.
+
+  Questo è utile se dovete utilizzare caratteri speciali che altrimenti
+  potrebbero assumere un significato diverso in kernel-doc o in reStructuredText
+
+  Questo è particolarmente utile se dovete scrivere qualcosa come ``%ph``
+  all'interno della descrizione di una funzione.
+
+``$ENVVAR``
+  Il nome di una variabile d'ambiente (nessun riferimento, solo formattazione).
+
+``&struct name``
+  Riferimento ad una struttura.
+
+``&enum name``
+  Riferimento ad un'enumerazione.
+
+``&typedef name``
+  Riferimento ad un tipo di dato.
+
+``&struct_name->member`` or ``&struct_name.member``
+  Riferimento ad un membro di una struttura o di un'unione. Il riferimento sarà
+  la struttura o l'unione, non il memembro.
+
+``&name``
+  Un generico riferimento ad un tipo. Usate, preferibilmente, il riferimento
+  completo come descritto sopra. Questo è dedicato ai commenti obsoleti.
+
+Riferimenti usando reStructuredText
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Per fare riferimento a funzioni e tipi di dato definiti nei commenti kernel-doc
+all'interno dei documenti reStructuredText, utilizzate i riferimenti dal
+`dominio Sphinx per il C`_. Per esempio::
+
+  See function :c:func:`foo` and struct/union/enum/typedef :c:type:`bar`.
+
+Nonostante il riferimento ai tipi di dato funzioni col solo nome,
+ovvero senza specificare struct/union/enum/typedef, potreste preferire il
+seguente::
+
+  See :c:type:`struct foo <foo>`.
+  See :c:type:`union bar <bar>`.
+  See :c:type:`enum baz <baz>`.
+  See :c:type:`typedef meh <meh>`.
+
+Questo produce dei collegamenti migliori, ed è in linea con il modo in cui
+kernel-doc gestisce i riferimenti.
+
+Per maggiori informazioni, siete pregati di consultare la documentazione
+del `dominio Sphinx per il C`_.
+
+Commenti per una documentazione generale
+----------------------------------------
+
+Al fine d'avere il codice ed i commenti nello stesso file, potete includere
+dei blocchi di documentazione kernel-doc con un formato libero invece
+che nel formato specifico per funzioni, strutture, unioni, enumerati o tipi
+di dato. Per esempio, questo tipo di commento potrebbe essere usato per la
+spiegazione delle operazioni di un driver o di una libreria
+
+Questo s'ottiene utilizzando la parola chiave ``DOC:`` a cui viene associato
+un titolo.
+
+Generalmente il formato di un commento generico o di visione d'insieme è
+il seguente::
+
+  /**
+   * DOC: Theory of Operation
+   *
+   * The whizbang foobar is a dilly of a gizmo. It can do whatever you
+   * want it to do, at any time. It reads your mind. Here's how it works.
+   *
+   * foo bar splat
+   *
+   * The only drawback to this gizmo is that is can sometimes damage
+   * hardware, software, or its subject(s).
+   */
+
+Il titolo che segue ``DOC:`` funziona da intestazione all'interno del file
+sorgente, ma anche come identificatore per l'estrazione di questi commenti di
+documentazione. Quindi, il titolo dev'essere unico all'interno del file.
+
+Includere i commenti di tipo kernel-doc
+=======================================
+
+I commenti di documentazione possono essere inclusi in un qualsiasi documento
+di tipo reStructuredText mediante l'apposita direttiva nell'estensione
+kernel-doc per Sphinx.
+
+Le direttive kernel-doc sono nel formato::
+
+  .. kernel-doc:: source
+     :option:
+
+Il campo *source* è il percorso ad un file sorgente, relativo alla cartella
+principale dei sorgenti del kernel. La direttiva supporta le seguenti opzioni:
+
+export: *[source-pattern ...]*
+  Include la documentazione per tutte le funzioni presenti nel file sorgente
+  (*source*) che sono state esportate utilizzando ``EXPORT_SYMBOL`` o
+  ``EXPORT_SYMBOL_GPL`` in *source* o in qualsiasi altro *source-pattern*
+  specificato.
+
+  Il campo *source-patter* è utile quando i commenti kernel-doc sono stati
+  scritti nei file d'intestazione, mentre ``EXPORT_SYMBOL`` e
+  ``EXPORT_SYMBOL_GPL`` si trovano vicino alla definizione delle funzioni.
+
+  Esempi::
+
+    .. kernel-doc:: lib/bitmap.c
+       :export:
+
+    .. kernel-doc:: include/net/mac80211.h
+       :export: net/mac80211/*.c
+
+internal: *[source-pattern ...]*
+  Include la documentazione per tutte le funzioni ed i tipi presenti nel file
+  sorgente (*source*) che **non** sono stati esportati utilizzando
+  ``EXPORT_SYMBOL`` o ``EXPORT_SYMBOL_GPL`` né in *source* né in qualsiasi
+  altro *source-pattern* specificato.
+
+  Esempio::
+
+    .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+       :internal:
+
+doc: *title*
+  Include la documentazione del paragrafo ``DOC:`` identificato dal titolo
+  (*title*) all'interno del file sorgente (*source*). Gli spazi in *title* sono
+  permessi; non virgolettate *title*. Il campo *title* è utilizzato per
+  identificare un paragrafo e per questo non viene incluso nella documentazione
+  finale. Verificate d'avere l'intestazione appropriata nei documenti
+  reStructuredText.
+
+  Esempio::
+
+    .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
+       :doc: High Definition Audio over HDMI and Display Port
+
+functions: *function* *[...]*
+  Dal file sorgente (*source*) include la documentazione per le funzioni
+  elencate (*function*).
+
+  Esempio::
+
+    .. kernel-doc:: lib/bitmap.c
+       :functions: bitmap_parselist bitmap_parselist_user
+
+Senza alcuna opzione, la direttiva kernel-doc include tutti i commenti di
+documentazione presenti nel file sorgente (*source*).
+
+L'estensione kernel-doc fa parte dei sorgenti del kernel, la si può trovare
+in ``Documentation/sphinx/kerneldoc.py``. Internamente, viene utilizzato
+lo script ``scripts/kernel-doc`` per estrarre i commenti di documentazione
+dai file sorgenti.
+
+Come utilizzare kernel-doc per generare pagine man
+--------------------------------------------------
+
+Se volete utilizzare kernel-doc solo per generare delle pagine man, potete
+farlo direttamente dai sorgenti del kernel::
+
+  $ scripts/kernel-doc -man $(git grep -l '/\*\*' -- :^Documentation :^tools) | scripts/split-man.pl /tmp/man
diff --git a/Documentation/translations/it_IT/doc-guide/parse-headers.rst b/Documentation/translations/it_IT/doc-guide/parse-headers.rst
new file mode 100644
index 000000000000..b38918ca637e
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/parse-headers.rst
@@ -0,0 +1,196 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+=========================================
+Includere gli i file di intestazione uAPI
+=========================================
+
+Qualche volta è utile includere dei file di intestazione e degli esempi di codice C
+al fine di descrivere l'API per lo spazio utente e per generare dei riferimenti
+fra il codice e la documentazione. Aggiungere i riferimenti ai file dell'API
+dello spazio utente ha ulteriori vantaggi: Sphinx genererà dei messaggi
+d'avviso se un simbolo non viene trovato nella documentazione. Questo permette
+di mantenere allineate la documentazione della uAPI (API spazio utente)
+con le modifiche del kernel.
+Il programma :ref:`parse_headers.pl <it_parse_headers>` genera questi riferimenti.
+Esso dev'essere invocato attraverso un Makefile, mentre si genera la
+documentazione. Per avere un esempio su come utilizzarlo all'interno del kernel
+consultate ``Documentation/media/Makefile``.
+
+.. _it_parse_headers:
+
+parse_headers.pl
+^^^^^^^^^^^^^^^^
+
+NOME
+****
+
+
+parse_headers.pl - analizza i file C al fine di identificare funzioni,
+strutture, enumerati e definizioni, e creare riferimenti per Sphinx
+
+SINTASSI
+********
+
+
+\ **parse_headers.pl**\  [<options>] <C_FILE> <OUT_FILE> [<EXCEPTIONS_FILE>]
+
+Dove <options> può essere: --debug, --usage o --help.
+
+
+OPZIONI
+*******
+
+
+
+\ **--debug**\
+
+ Lo script viene messo in modalità verbosa, utile per il debugging.
+
+
+\ **--usage**\
+
+ Mostra un messaggio d'aiuto breve e termina.
+
+
+\ **--help**\
+
+ Mostra un messaggio d'aiuto dettagliato e termina.
+
+
+DESCRIZIONE
+***********
+
+Converte un file d'intestazione o un file sorgente C (C_FILE) in un testo
+ReStructuredText incluso mediante il blocco ..parsed-literal
+con riferimenti alla documentazione che descrive l'API. Opzionalmente,
+il programma accetta anche un altro file (EXCEPTIONS_FILE) che
+descrive quali elementi debbano essere ignorati o il cui riferimento
+deve puntare ad elemento diverso dal predefinito.
+
+Il file generato sarà disponibile in (OUT_FILE).
+
+Il programma è capace di identificare *define*, funzioni, strutture,
+tipi di dato, enumerati e valori di enumerati, e di creare i riferimenti
+per ognuno di loro. Inoltre, esso è capace di distinguere le #define
+utilizzate per specificare i comandi ioctl di Linux.
+
+Il file EXCEPTIONS_FILE contiene due tipi di dichiarazioni:
+\ **ignore**\  o \ **replace**\ .
+
+La sintassi per ignore è:
+
+ignore \ **tipo**\  \ **nome**\
+
+La dichiarazione \ **ignore**\  significa che non verrà generato alcun
+riferimento per il simbolo \ **name**\  di tipo \ **tipo**\ .
+
+
+La sintassi per replace è:
+
+replace \ **tipo**\  \ **nome**\  \ **nuovo_valore**\
+
+La dichiarazione \ **replace**\  significa che verrà generato un
+riferimento per il simbolo \ **name**\ di tipo \ **tipo**\ , ma, invece
+di utilizzare il valore predefinito, verrà utilizzato il valore
+\ **nuovo_valore**\ .
+
+Per entrambe le dichiarazioni, il \ **tipo**\  può essere uno dei seguenti:
+
+
+\ **ioctl**\
+
+ La dichiarazione ignore o replace verrà applicata su definizioni di ioctl
+ come la seguente:
+
+ #define	VIDIOC_DBG_S_REGISTER 	 _IOW('V', 79, struct v4l2_dbg_register)
+
+
+
+\ **define**\
+
+ La dichiarazione ignore o replace verrà applicata su una qualsiasi #define
+ trovata in C_FILE.
+
+
+
+\ **typedef**\
+
+ La dichiarazione ignore o replace verrà applicata ad una dichiarazione typedef
+ in C_FILE.
+
+
+
+\ **struct**\
+
+ La dichiarazione ignore o replace verrà applicata ai nomi di strutture
+ in C_FILE.
+
+
+
+\ **enum**\
+
+ La dichiarazione ignore o replace verrà applicata ai nomi di enumerati
+ in C_FILE.
+
+
+
+\ **symbol**\
+
+ La dichiarazione ignore o replace verrà applicata ai nomi di valori di
+ enumerati in C_FILE.
+
+ Per le dichiarazioni di tipo replace, il campo \ **new_value**\  utilizzerà
+ automaticamente i riferimenti :c:type: per \ **typedef**\ , \ **enum**\  e
+ \ **struct**\. Invece, utilizzerà :ref: per \ **ioctl**\ , \ **define**\  e
+ \ **symbol**\. Il tipo di riferimento può essere definito esplicitamente
+ nella dichiarazione stessa.
+
+
+ESEMPI
+******
+
+
+ignore define _VIDEODEV2_H
+
+
+Ignora una definizione #define _VIDEODEV2_H nel file C_FILE.
+
+ignore symbol PRIVATE
+
+
+In un enumerato come il seguente:
+
+enum foo { BAR1, BAR2, PRIVATE };
+
+Non genererà alcun riferimento per \ **PRIVATE**\ .
+
+replace symbol BAR1 :c:type:\`foo\`
+replace symbol BAR2 :c:type:\`foo\`
+
+
+In un enumerato come il seguente:
+
+enum foo { BAR1, BAR2, PRIVATE };
+
+Genererà un riferimento ai valori BAR1 e BAR2 dal simbolo foo nel dominio C.
+
+
+BUGS
+****
+
+Riferire ogni malfunzionamento a Mauro Carvalho Chehab <mchehab@s-opensource.com>
+
+
+COPYRIGHT
+*********
+
+
+Copyright (c) 2016 by Mauro Carvalho Chehab <mchehab@s-opensource.com>.
+
+Licenza GPLv2: GNU GPL version 2 <http://gnu.org/licenses/gpl.html>.
+
+Questo è software libero: siete liberi di cambiarlo e ridistribuirlo.
+Non c'è alcuna garanzia, nei limiti permessi dalla legge.
diff --git a/Documentation/translations/it_IT/doc-guide/sphinx.rst b/Documentation/translations/it_IT/doc-guide/sphinx.rst
new file mode 100644
index 000000000000..474b7e127893
--- /dev/null
+++ b/Documentation/translations/it_IT/doc-guide/sphinx.rst
@@ -0,0 +1,457 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/doc-guide/index.rst <doc_guide>`
+
+Introduzione
+============
+
+Il kernel Linux usa `Sphinx`_ per la generazione della documentazione a partire
+dai file `reStructuredText`_ che si trovano nella cartella ``Documentation``.
+Per generare la documentazione in HTML o PDF, usate comandi ``make htmldocs`` o
+``make pdfdocs``. La documentazione così generata sarà disponibile nella
+cartella ``Documentation/output``.
+
+.. _Sphinx: http://www.sphinx-doc.org/
+.. _reStructuredText: http://docutils.sourceforge.net/rst.html
+
+I file reStructuredText possono contenere delle direttive che permettono di
+includere i commenti di documentazione, o di tipo kernel-doc, dai file
+sorgenti.
+Solitamente questi commenti sono utilizzati per descrivere le funzioni, i tipi
+e l'architettura del codice. I commenti di tipo kernel-doc hanno una struttura
+e formato speciale, ma a parte questo vengono processati come reStructuredText.
+
+Inoltre, ci sono migliaia di altri documenti in formato testo sparsi nella
+cartella ``Documentation``. Alcuni di questi verranno probabilmente convertiti,
+nel tempo, in formato reStructuredText, ma la maggior parte di questi rimarranno
+in formato testo.
+
+.. _it_sphinx_install:
+
+Installazione Sphinx
+====================
+
+I marcatori ReST utilizzati nei file in Documentation/ sono pensati per essere
+processati da ``Sphinx`` nella versione 1.3 o superiore. Se desiderate produrre
+un documento PDF è raccomandato l'utilizzo di una versione superiore alle 1.4.6.
+
+Esiste uno script che verifica i requisiti Sphinx. Per ulteriori dettagli
+consultate :ref:`it_sphinx-pre-install`.
+
+La maggior parte delle distribuzioni Linux forniscono Sphinx, ma l'insieme dei
+programmi e librerie è fragile e non è raro che dopo un aggiornamento di
+Sphinx, o qualche altro pacchetto Python, la documentazione non venga più
+generata correttamente.
+
+Un modo per evitare questo genere di problemi è quello di utilizzare una
+versione diversa da quella fornita dalla vostra distribuzione. Per fare questo,
+vi raccomandiamo di installare Sphinx dentro ad un ambiente virtuale usando
+``virtualenv-3`` o ``virtualenv`` a seconda di come Python 3 è stato
+pacchettizzato dalla vostra distribuzione.
+
+.. note::
+
+   #) Le versioni di Sphinx inferiori alla 1.5 non funzionano bene
+      con il pacchetto Python docutils versione 0.13.1 o superiore.
+      Se volete usare queste versioni, allora dovere eseguire
+      ``pip install 'docutils==0.12'``.
+
+   #) Viene raccomandato l'uso del tema RTD per la documentazione in HTML.
+      A seconda della versione di Sphinx, potrebbe essere necessaria
+      l'installazione tramite il comando ``pip install sphinx_rtd_theme``.
+
+   #) Alcune pagine ReST contengono delle formule matematiche. A causa del
+      modo in cui Sphinx funziona, queste espressioni sono scritte
+      utilizzando LaTeX. Per una corretta interpretazione, è necessario aver
+      installato texlive con i pacchetti amdfonts e amsmath.
+
+Riassumendo, se volete installare la versione 1.4.9 di Sphinx dovete eseguire::
+
+       $ virtualenv sphinx_1.4
+       $ . sphinx_1.4/bin/activate
+       (sphinx_1.4) $ pip install -r Documentation/sphinx/requirements.txt
+
+Dopo aver eseguito ``. sphinx_1.4/bin/activate``, il prompt cambierà per
+indicare che state usando il nuovo ambiente. Se aprite un nuova sessione,
+prima di generare la documentazione, dovrete rieseguire questo comando per
+rientrare nell'ambiente virtuale.
+
+Generazione d'immagini
+----------------------
+
+Il meccanismo che genera la documentazione del kernel contiene un'estensione
+capace di gestire immagini in formato Graphviz e SVG (per maggior informazioni
+vedere :ref:`it_sphinx_kfigure`).
+
+Per far si che questo funzioni, dovete installare entrambe i pacchetti
+Graphviz e ImageMagick. Il sistema di generazione della documentazione è in
+grado di procedere anche se questi pacchetti non sono installati, ma il
+risultato, ovviamente, non includerà le immagini.
+
+Generazione in PDF e LaTeX
+--------------------------
+
+Al momento, la generazione di questi documenti è supportata solo dalle
+versioni di Sphinx superiori alla 1.4.
+
+Per la generazione di PDF e LaTeX, avrete bisogno anche del pacchetto
+``XeLaTeX`` nella versione 3.14159265
+
+Per alcune distribuzioni Linux potrebbe essere necessario installare
+anche una serie di pacchetti ``texlive`` in modo da fornire il supporto
+minimo per il funzionamento di ``XeLaTeX``.
+
+.. _it_sphinx-pre-install:
+
+Verificare le dipendenze Sphinx
+-------------------------------
+
+Esiste uno script che permette di verificare automaticamente le dipendenze di
+Sphinx. Se lo script riesce a riconoscere la vostra distribuzione, allora
+sarà in grado di darvi dei suggerimenti su come procedere per completare
+l'installazione::
+
+	$ ./scripts/sphinx-pre-install
+	Checking if the needed tools for Fedora release 26 (Twenty Six) are available
+	Warning: better to also install "texlive-luatex85".
+	You should run:
+
+		sudo dnf install -y texlive-luatex85
+		/usr/bin/virtualenv sphinx_1.4
+		. sphinx_1.4/bin/activate
+		pip install -r Documentation/sphinx/requirements.txt
+
+	Can't build as 1 mandatory dependency is missing at ./scripts/sphinx-pre-install line 468.
+
+L'impostazione predefinita prevede il controllo dei requisiti per la generazione
+di documenti html e PDF, includendo anche il supporto per le immagini, le
+espressioni matematiche e LaTeX; inoltre, presume che venga utilizzato un
+ambiente virtuale per Python. I requisiti per generare i documenti html
+sono considerati obbligatori, gli altri sono opzionali.
+
+Questo script ha i seguenti parametri:
+
+``--no-pdf``
+	Disabilita i controlli per la generazione di PDF;
+
+``--no-virtualenv``
+	Utilizza l'ambiente predefinito dal sistema operativo invece che
+	l'ambiente virtuale per Python;
+
+
+Generazione della documentazione Sphinx
+=======================================
+
+Per generare la documentazione in formato HTML o PDF si eseguono i rispettivi
+comandi ``make htmldocs`` o ``make pdfdocs``. Esistono anche altri formati
+in cui è possibile generare la documentazione; per maggiori informazioni
+potere eseguire il comando ``make help``.
+La documentazione così generata sarà disponibile nella sottocartella
+``Documentation/output``.
+
+Ovviamente, per generare la documentazione, Sphinx (``sphinx-build``)
+dev'essere installato. Se disponibile, il tema *Read the Docs* per Sphinx
+verrà utilizzato per ottenere una documentazione HTML più gradevole.
+Per la documentazione in formato PDF, invece, avrete bisogno di ``XeLaTeX`
+e di ``convert(1)`` disponibile in ImageMagick (https://www.imagemagick.org).
+Tipicamente, tutti questi pacchetti sono disponibili e pacchettizzati nelle
+distribuzioni Linux.
+
+Per poter passare ulteriori opzioni a Sphinx potete utilizzare la variabile
+make ``SPHINXOPTS``. Per esempio, se volete che Sphinx sia più verboso durante
+la generazione potete usare il seguente comando ``make SPHINXOPTS=-v htmldocs``.
+
+Potete eliminare la documentazione generata tramite il comando
+``make cleandocs``.
+
+Scrivere la documentazione
+==========================
+
+Aggiungere nuova documentazione è semplice:
+
+1. aggiungete un file ``.rst`` nella sottocartella ``Documentation``
+2. aggiungete un riferimento ad esso nell'indice (`TOC tree`_) in
+   ``Documentation/index.rst``.
+
+.. _TOC tree: http://www.sphinx-doc.org/en/stable/markup/toctree.html
+
+Questo, di solito, è sufficiente per la documentazione più semplice (come
+quella che state leggendo ora), ma per una documentazione più elaborata è
+consigliato creare una sottocartella dedicata (o, quando possibile, utilizzarne
+una già esistente). Per esempio, il sottosistema grafico è documentato nella
+sottocartella ``Documentation/gpu``; questa documentazione è divisa in
+diversi file ``.rst`` ed un indice ``index.rst`` (con un ``toctree``
+dedicato) a cui si fa riferimento nell'indice principale.
+
+Consultate la documentazione di `Sphinx`_ e `reStructuredText`_ per maggiori
+informazione circa le loro potenzialità. In particolare, il
+`manuale introduttivo a reStructuredText`_ di Sphinx è un buon punto da
+cui cominciare. Esistono, inoltre, anche alcuni
+`costruttori specifici per Sphinx`_.
+
+.. _`manuale introduttivo a reStructuredText`: http://www.sphinx-doc.org/en/stable/rest.html
+.. _`costruttori specifici per Sphinx`: http://www.sphinx-doc.org/en/stable/markup/index.html
+
+Guide linea per la documentazione del kernel
+--------------------------------------------
+
+In questa sezione troverete alcune linee guida specifiche per la documentazione
+del kernel:
+
+* Non esagerate con i costrutti di reStructuredText. Mantenete la
+  documentazione semplice. La maggior parte della documentazione dovrebbe
+  essere testo semplice con una strutturazione minima che permetta la
+  conversione in diversi formati.
+
+* Mantenete la strutturazione il più fedele possibile all'originale quando
+  convertite un documento in formato reStructuredText.
+
+* Aggiornate i contenuti quando convertite della documentazione, non limitatevi
+  solo alla formattazione.
+
+* Mantenete la decorazione dei livelli di intestazione come segue:
+
+  1. ``=`` con una linea superiore per il titolo del documento::
+
+       ======
+       Titolo
+       ======
+
+  2. ``=`` per i capitoli::
+
+       Capitoli
+       ========
+
+  3. ``-`` per le sezioni::
+
+       Sezioni
+       -------
+
+  4. ``~`` per le sottosezioni::
+
+       Sottosezioni
+       ~~~~~~~~~~~~
+
+  Sebbene RST non forzi alcun ordine specifico (*Piuttosto che imporre
+  un numero ed un ordine fisso di decorazioni, l'ordine utilizzato sarà
+  quello incontrato*), avere uniformità dei livelli principali rende più
+  semplice la lettura dei documenti.
+
+* Per inserire blocchi di testo con caratteri a dimensione fissa (codici di
+  esempio, casi d'uso, eccetera): utilizzate ``::`` quando non è necessario
+  evidenziare la sintassi, specialmente per piccoli frammenti; invece,
+  utilizzate ``.. code-block:: <language>`` per blocchi di più lunghi che
+  potranno beneficiare dell'avere la sintassi evidenziata.
+
+
+Il dominio C
+------------
+
+Il **Dominio Sphinx C** (denominato c) è adatto alla documentazione delle API C.
+Per esempio, un prototipo di una funzione:
+
+.. code-block:: rst
+
+    .. c:function:: int ioctl( int fd, int request )
+
+Il dominio C per kernel-doc ha delle funzionalità aggiuntive. Per esempio,
+potete assegnare un nuovo nome di riferimento ad una funzione con un nome
+molto comune come ``open`` o ``ioctl``:
+
+.. code-block:: rst
+
+     .. c:function:: int ioctl( int fd, int request )
+        :name: VIDIOC_LOG_STATUS
+
+Il nome della funzione (per esempio ioctl) rimane nel testo ma il nome del suo
+riferimento cambia da ``ioctl`` a ``VIDIOC_LOG_STATUS``. Anche la voce
+nell'indice cambia in ``VIDIOC_LOG_STATUS`` e si potrà quindi fare riferimento
+a questa funzione scrivendo:
+
+.. code-block:: rst
+
+     :c:func:`VIDIOC_LOG_STATUS`
+
+
+Tabelle a liste
+---------------
+
+Raccomandiamo l'uso delle tabelle in formato lista (*list table*). Le tabelle
+in formato lista sono liste di liste. In confronto all'ASCII-art potrebbero
+non apparire di facile lettura nei file in formato testo. Il loro vantaggio è
+che sono facili da creare o modificare e che la differenza di una modifica è
+molto più significativa perché limitata alle modifiche del contenuto.
+
+La ``flat-table`` è anch'essa una lista di liste simile alle ``list-table``
+ma con delle funzionalità aggiuntive:
+
+* column-span: col ruolo ``cspan`` una cella può essere estesa attraverso
+  colonne successive
+
+* raw-span: col ruolo ``rspan`` una cella può essere estesa attraverso
+  righe successive
+
+* auto-span: la cella più a destra viene estesa verso destra per compensare
+  la mancanza di celle. Con l'opzione ``:fill-cells:`` questo comportamento
+  può essere cambiato da *auto-span* ad *auto-fill*, il quale inserisce
+  automaticamente celle (vuote) invece che estendere l'ultima.
+
+opzioni:
+
+* ``:header-rows:``   [int] conta le righe di intestazione
+* ``:stub-columns:``  [int] conta le colonne di stub
+* ``:widths:``        [[int] [int] ... ] larghezza delle colonne
+* ``:fill-cells:``    invece di estendere automaticamente una cella su quelle
+  mancanti, ne crea di vuote.
+
+ruoli:
+
+* ``:cspan:`` [int] colonne successive (*morecols*)
+* ``:rspan:`` [int] righe successive (*morerows*)
+
+L'esempio successivo mostra come usare questo marcatore. Il primo livello della
+nostra lista di liste è la *riga*. In una *riga* è possibile inserire solamente
+la lista di celle che compongono la *riga* stessa. Fanno eccezione i *commenti*
+( ``..`` ) ed i *collegamenti* (per esempio, un riferimento a
+``:ref:`last row <last row>``` / :ref:`last row <it last row>`)
+
+.. code-block:: rst
+
+   .. flat-table:: table title
+      :widths: 2 1 1 3
+
+      * - head col 1
+        - head col 2
+        - head col 3
+        - head col 4
+
+      * - column 1
+        - field 1.1
+        - field 1.2 with autospan
+
+      * - column 2
+        - field 2.1
+        - :rspan:`1` :cspan:`1` field 2.2 - 3.3
+
+      * .. _`it last row`:
+
+        - column 3
+
+Che verrà rappresentata nel seguente modo:
+
+   .. flat-table:: table title
+      :widths: 2 1 1 3
+
+      * - head col 1
+        - head col 2
+        - head col 3
+        - head col 4
+
+      * - column 1
+        - field 1.1
+        - field 1.2 with autospan
+
+      * - column 2
+        - field 2.1
+        - :rspan:`1` :cspan:`1` field 2.2 - 3.3
+
+      * .. _`it last row`:
+
+        - column 3
+
+.. _it_sphinx_kfigure:
+
+Figure ed immagini
+==================
+
+Se volete aggiungere un'immagine, utilizzate le direttive ``kernel-figure``
+e ``kernel-image``. Per esempio, per inserire una figura di un'immagine in
+formato SVG::
+
+    .. kernel-figure::  ../../../doc-guide/svg_image.svg
+       :alt:    una semplice immagine SVG
+
+       Una semplice immagine SVG
+
+.. _it_svg_image_example:
+
+.. kernel-figure::  ../../../doc-guide/svg_image.svg
+   :alt:    una semplice immagine SVG
+
+   Una semplice immagine SVG
+
+Le direttive del kernel per figure ed immagini supportano il formato **DOT**,
+per maggiori informazioni
+
+* DOT: http://graphviz.org/pdf/dotguide.pdf
+* Graphviz: http://www.graphviz.org/content/dot-language
+
+Un piccolo esempio (:ref:`it_hello_dot_file`)::
+
+  .. kernel-figure::  ../../../doc-guide/hello.dot
+     :alt:    ciao mondo
+
+     Esempio DOT
+
+.. _it_hello_dot_file:
+
+.. kernel-figure::  ../../../doc-guide/hello.dot
+   :alt:    ciao mondo
+
+   Esempio DOT
+
+Tramite la direttiva ``kernel-render`` è possibile aggiungere codice specifico;
+ad esempio nel formato **DOT** di Graphviz.::
+
+  .. kernel-render:: DOT
+     :alt: foobar digraph
+     :caption: Codice **DOT** (Graphviz) integrato
+
+     digraph foo {
+      "bar" -> "baz";
+     }
+
+La rappresentazione dipenderà dei programmi installati. Se avete Graphviz
+installato, vedrete un'immagine vettoriale. In caso contrario, il codice grezzo
+verrà rappresentato come *blocco testuale* (:ref:`it_hello_dot_render`).
+
+.. _it_hello_dot_render:
+
+.. kernel-render:: DOT
+   :alt: foobar digraph
+   :caption: Codice **DOT** (Graphviz) integrato
+
+   digraph foo {
+      "bar" -> "baz";
+   }
+
+La direttiva *render* ha tutte le opzioni della direttiva *figure*, con
+l'aggiunta dell'opzione ``caption``. Se ``caption`` ha un valore allora
+un nodo *figure* viene aggiunto. Altrimenti verrà aggiunto un nodo *image*.
+L'opzione ``caption`` è necessaria in caso si vogliano aggiungere dei
+riferimenti (:ref:`it_hello_svg_render`).
+
+Per la scrittura di codice **SVG**::
+
+  .. kernel-render:: SVG
+     :caption: Integrare codice **SVG**
+     :alt: so-nw-arrow
+
+     <?xml version="1.0" encoding="UTF-8"?>
+     <svg xmlns="http://www.w3.org/2000/svg" version="1.1" ...>
+        ...
+     </svg>
+
+.. _it_hello_svg_render:
+
+.. kernel-render:: SVG
+   :caption: Integrare codice **SVG**
+   :alt: so-nw-arrow
+
+   <?xml version="1.0" encoding="UTF-8"?>
+   <svg xmlns="http://www.w3.org/2000/svg"
+     version="1.1" baseProfile="full" width="70px" height="40px" viewBox="0 0 700 400">
+   <line x1="180" y1="370" x2="500" y2="50" stroke="black" stroke-width="15px"/>
+   <polygon points="585 0 525 25 585 50" transform="rotate(135 525 25)"/>
+   </svg>
diff --git a/Documentation/translations/it_IT/index.rst b/Documentation/translations/it_IT/index.rst
index 7613a9f9e6f9..dae01886b073 100644
--- a/Documentation/translations/it_IT/index.rst
+++ b/Documentation/translations/it_IT/index.rst
@@ -83,6 +83,11 @@ sviluppatori che contribuiscono ogni anno. Come in ogni grande comunità,
 sapere come le cose vengono fatte renderà il processo di integrazione delle
 vostre modifiche molto più semplice
 
+.. toctree::
+   :maxdepth: 2
+
+   doc-guide/index
+
 .. warning::
 
     TODO ancora da tradurre
-- 
cgit v1.2.3


From 5c10ed433da26ff3509ae11c6b22d21e131484d8 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:24:37 -0300
Subject: sound: restore MultiSound script

This script is mentioned at multisound Kconfig and files. As the
driver still exists, it probably makes sense to restore it.

Fixes: 727dede0ba8a ("sound: Retire OSS")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/cards/multisound.sh | 1137 +++++++++++++++++++++++++++++++
 1 file changed, 1137 insertions(+)
 create mode 100755 Documentation/sound/cards/multisound.sh

diff --git a/Documentation/sound/cards/multisound.sh b/Documentation/sound/cards/multisound.sh
new file mode 100755
index 000000000000..7a7a88256dfd
--- /dev/null
+++ b/Documentation/sound/cards/multisound.sh
@@ -0,0 +1,1137 @@
+#! /bin/sh
+#
+#  Turtle Beach MultiSound Driver Notes
+#  -- Andrew Veliath <andrewtv@usa.net>
+#
+#  Last update:                      September 10, 1998
+#  Corresponding msnd driver:        0.8.3
+#
+# ** This file is a README (top part) and shell archive (bottom part).
+#    The corresponding archived utility sources can be unpacked by
+#    running `sh MultiSound' (the utilities are only needed for the
+#    Pinnacle and Fiji cards). **
+#
+#
+#  -=-=- Getting Firmware -=-=-
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  See the section `Obtaining and Creating Firmware Files' in this
+#  document for instructions on obtaining the necessary firmware
+#  files.
+#
+#
+#  Supported Features
+#  ~~~~~~~~~~~~~~~~~~
+#
+#  Currently, full-duplex digital audio (/dev/dsp only, /dev/audio is
+#  not currently available) and mixer functionality (/dev/mixer) are
+#  supported (memory mapped digital audio is not yet supported).
+#  Digital transfers and monitoring can be done as well if you have
+#  the digital daughterboard (see the section on using the S/PDIF port
+#  for more information).
+#
+#  Support for the Turtle Beach MultiSound Hurricane architecture is
+#  composed of the following modules (these can also operate compiled
+#  into the kernel):
+#
+#  msnd               - MultiSound base (requires soundcore)
+#
+#  msnd_classic       - Base audio/mixer support for Classic, Monetery and
+#                       Tahiti cards
+#
+#  msnd_pinnacle      - Base audio/mixer support for Pinnacle and Fiji cards
+#
+#
+#  Important Notes - Read Before Using
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  The firmware files are not included (may change in future).  You
+#  must obtain these images from Turtle Beach (they are included in
+#  the MultiSound Development Kits), and place them in /etc/sound for
+#  example, and give the full paths in the Linux configuration.  If
+#  you are compiling in support for the MultiSound driver rather than
+#  using it as a module, these firmware files must be accessible
+#  during kernel compilation.
+#
+#  Please note these files must be binary files, not assembler.  See
+#  the section later in this document for instructions to obtain these
+#  files.
+#
+#
+#  Configuring Card Resources
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  ** This section is very important, as your card may not work at all
+#     or your machine may crash if you do not do this correctly. **
+#
+#  * Classic/Monterey/Tahiti
+#
+#  These cards are configured through the driver msnd_classic.  You must
+#  know the io port, then the driver will select the irq and memory resources
+#  on the card.  It is up to you to know if these are free locations or now,
+#  a conflict can lock the machine up.
+#
+#  * Pinnacle/Fiji
+#
+#  The Pinnacle and Fiji cards have an extra config port, either
+#  0x250, 0x260 or 0x270.  This port can be disabled to have the card
+#  configured strictly through PnP, however you lose the ability to
+#  access the IDE controller and joystick devices on this card when
+#  using PnP.  The included pinnaclecfg program in this shell archive
+#  can be used to configure the card in non-PnP mode, and in PnP mode
+#  you can use isapnptools.  These are described briefly here.
+#
+#  pinnaclecfg is not required; you can use the msnd_pinnacle module
+#  to fully configure the card as well.  However, pinnaclecfg can be
+#  used to change the resource values of a particular device after the
+#  msnd_pinnacle module has been loaded.  If you are compiling the
+#  driver into the kernel, you must set these values during compile
+#  time, however other peripheral resource values can be changed with
+#  the pinnaclecfg program after the kernel is loaded.
+#
+#
+#  *** PnP mode
+#
+#  Use pnpdump to obtain a sample configuration if you can; I was able
+#  to obtain one with the command `pnpdump 1 0x203' -- this may vary
+#  for you (running pnpdump by itself did not work for me).  Then,
+#  edit this file and use isapnp to uncomment and set the card values.
+#  Use these values when inserting the msnd_pinnacle module.  Using
+#  this method, you can set the resources for the DSP and the Kurzweil
+#  synth (Pinnacle).  Since Linux does not directly support PnP
+#  devices, you may have difficulty when using the card in PnP mode
+#  when it the driver is compiled into the kernel.  Using non-PnP mode
+#  is preferable in this case.
+#
+#  Here is an example mypinnacle.conf for isapnp that sets the card to
+#  io base 0x210, irq 5 and mem 0xd8000, and also sets the Kurzweil
+#  synth to 0x330 and irq 9 (may need editing for your system):
+#
+#  (READPORT 0x0203)
+#  (CSN 2)
+#  (IDENTIFY *)
+#
+#  # DSP
+#  (CONFIGURE BVJ0440/-1 (LD 0
+#          (INT 0 (IRQ 5 (MODE +E))) (IO 0 (BASE 0x0210)) (MEM 0 (BASE 0x0d8000))
+#          (ACT Y)))
+#
+#  # Kurzweil Synth (Pinnacle Only)
+#  (CONFIGURE BVJ0440/-1 (LD 1
+#          (IO 0 (BASE 0x0330)) (INT 0 (IRQ 9 (MODE +E)))
+#          (ACT Y)))
+#
+#  (WAITFORKEY)
+#
+#
+#  *** Non-PnP mode
+#
+#  The second way is by running the card in non-PnP mode.  This
+#  actually has some advantages in that you can access some other
+#  devices on the card, such as the joystick and IDE controller.  To
+#  configure the card, unpack this shell archive and build the
+#  pinnaclecfg program.  Using this program, you can assign the
+#  resource values to the card's devices, or disable the devices.  As
+#  an alternative to using pinnaclecfg, you can specify many of the
+#  configuration values when loading the msnd_pinnacle module (or
+#  during kernel configuration when compiling the driver into the
+#  kernel).
+#
+#  If you specify cfg=0x250 for the msnd_pinnacle module, it
+#  automatically configure the card to the given io, irq and memory
+#  values using that config port (the config port is jumper selectable
+#  on the card to 0x250, 0x260 or 0x270).
+#
+#  See the `msnd_pinnacle Additional Options' section below for more
+#  information on these parameters (also, if you compile the driver
+#  directly into the kernel, these extra parameters can be useful
+#  here).
+#
+#
+# ** It is very easy to cause problems in your machine if you choose a
+#    resource value which is incorrect. **
+#
+#
+#  Examples
+#  ~~~~~~~~
+#
+#  * MultiSound Classic/Monterey/Tahiti:
+#
+#  modprobe soundcore
+#  insmod msnd
+#  insmod msnd_classic io=0x290 irq=7 mem=0xd0000
+#
+#  * MultiSound Pinnacle in PnP mode:
+#
+#  modprobe soundcore
+#  insmod msnd
+#  isapnp mypinnacle.conf
+#  insmod msnd_pinnacle io=0x210 irq=5 mem=0xd8000 <-- match mypinnacle.conf values
+#
+#  * MultiSound Pinnacle in non-PnP mode (replace 0x250 with your configuration port,
+#    one of 0x250, 0x260 or 0x270):
+#
+#  insmod soundcore
+#  insmod msnd
+#  insmod msnd_pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000
+#
+# * To use the MPU-compatible Kurzweil synth on the Pinnacle in PnP
+#   mode, add the following (assumes you did `isapnp mypinnacle.conf'):
+#
+#  insmod sound
+#  insmod mpu401 io=0x330 irq=9                    <-- match mypinnacle.conf values
+#
+# * To use the MPU-compatible Kurzweil synth on the Pinnacle in non-PnP
+#   mode, add the following.  Note how we first configure the peripheral's
+#   resources, _then_ install a Linux driver for it:
+#
+#  insmod sound
+#  pinnaclecfg 0x250 mpu 0x330 9
+#  insmod mpu401 io=0x330 irq=9
+#
+#  -- OR you can use the following sequence without pinnaclecfg in non-PnP mode:
+#
+#  insmod soundcore
+#  insmod msnd
+#  insmod msnd_pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 mpu_io=0x330 mpu_irq=9
+#  insmod sound
+#  insmod mpu401 io=0x330 irq=9
+#
+# * To setup the joystick port on the Pinnacle in non-PnP mode (though
+#   you have to find the actual Linux joystick driver elsewhere), you
+#   can use pinnaclecfg:
+#
+#   pinnaclecfg 0x250 joystick 0x200
+#
+#  -- OR you can configure this using msnd_pinnacle with the following:
+#
+#  insmod soundcore
+#  insmod msnd
+#  insmod msnd_pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 joystick_io=0x200
+#
+#
+#  msnd_classic, msnd_pinnacle Required Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  If the following options are not given, the module will not load.
+#  Examine the kernel message log for informative error messages.
+#  WARNING--probing isn't supported so try to make sure you have the
+#  correct shared memory area, otherwise you may experience problems.
+#
+#  io                   I/O base of DSP, e.g. io=0x210
+#  irq                  IRQ number, e.g. irq=5
+#  mem                  Shared memory area, e.g. mem=0xd8000
+#
+#
+#  msnd_classic, msnd_pinnacle Additional Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  fifosize             The digital audio FIFOs, in kilobytes.  If not
+#                       specified, the default will be used.  Increasing
+#                       this value will reduce the chance of a FIFO
+#                       underflow at the expense of increasing overall
+#                       latency.  For example, fifosize=512 will
+#                       allocate 512kB read and write FIFOs (1MB total).
+#                       While this may reduce dropouts, a heavy machine
+#                       load will undoubtedly starve the FIFO of data
+#                       and you will eventually get dropouts.  One
+#                       option is to alter the scheduling priority of
+#                       the playback process, using `nice' or some form
+#                       of POSIX soft real-time scheduling.
+#
+#  calibrate_signal     Setting this to one calibrates the ADCs to the
+#                       signal, zero calibrates to the card (defaults
+#                       to zero).
+#
+#
+#  msnd_pinnacle Additional Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  digital              Specify digital=1 to enable the S/PDIF input
+#                       if you have the digital daughterboard
+#                       adapter. This will enable access to the
+#                       DIGITAL1 input for the soundcard in the mixer.
+#                       Some mixer programs might have trouble setting
+#                       the DIGITAL1 source as an input.  If you have
+#                       trouble, you can try the setdigital.c program
+#                       at the bottom of this document.
+#
+#  cfg                  Non-PnP configuration port for the Pinnacle
+#                       and Fiji (typically 0x250, 0x260 or 0x270,
+#                       depending on the jumper configuration).  If
+#                       this option is omitted, then it is assumed
+#                       that the card is in PnP mode, and that the
+#                       specified DSP resource values are already
+#                       configured with PnP (i.e. it won't attempt to
+#                       do any sort of configuration).
+#
+#  When the Pinnacle is in non-PnP mode, you can use the following
+#  options to configure particular devices.  If a full specification
+#  for a device is not given, then the device is not configured.  Note
+#  that you still must use a Linux driver for any of these devices
+#  once their resources are setup (such as the Linux joystick driver,
+#  or the MPU401 driver from OSS for the Kurzweil synth).
+#
+#  mpu_io               I/O port of MPU (on-board Kurzweil synth)
+#  mpu_irq              IRQ of MPU (on-board Kurzweil synth)
+#  ide_io0		First I/O port of IDE controller
+#  ide_io1		Second I/O port of IDE controller
+#  ide_irq		IRQ IDE controller
+#  joystick_io          I/O port of joystick
+#
+#
+#  Obtaining and Creating Firmware Files
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#       For the Classic/Tahiti/Monterey
+#       ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  Download to /tmp and unzip the following file from Turtle Beach:
+#
+#       ftp://ftp.voyetra.com/pub/tbs/msndcl/msndvkit.zip
+#
+#  When unzipped, unzip the file named MsndFiles.zip.  Then copy the
+#  following firmware files to /etc/sound (note the file renaming):
+#
+#    cp DSPCODE/MSNDINIT.BIN /etc/sound/msndinit.bin
+#    cp DSPCODE/MSNDPERM.REB /etc/sound/msndperm.bin
+#
+#  When configuring the Linux kernel, specify /etc/sound/msndinit.bin and
+#  /etc/sound/msndperm.bin for the two firmware files (Linux kernel
+#  versions older than 2.2 do not ask for firmware paths, and are
+#  hardcoded to /etc/sound).
+#
+#  If you are compiling the driver into the kernel, these files must
+#  be accessible during compilation, but will not be needed later.
+#  The files must remain, however, if the driver is used as a module.
+#
+#
+#       For the Pinnacle/Fiji
+#       ~~~~~~~~~~~~~~~~~~~~~
+#
+#  Download to /tmp and unzip the following file from Turtle Beach (be
+#  sure to use the entire URL; some have had trouble navigating to the
+#  URL):
+#
+#       ftp://ftp.voyetra.com/pub/tbs/pinn/pnddk100.zip
+#
+#  Unpack this shell archive, and run make in the created directory
+#  (you need a C compiler and flex to build the utilities).  This
+#  should give you the executables conv, pinnaclecfg and setdigital.
+#  conv is only used temporarily here to create the firmware files,
+#  while pinnaclecfg is used to configure the Pinnacle or Fiji card in
+#  non-PnP mode, and setdigital can be used to set the S/PDIF input on
+#  the mixer (pinnaclecfg and setdigital should be copied to a
+#  convenient place, possibly run during system initialization).
+#
+#  To generating the firmware files with the `conv' program, we create
+#  the binary firmware files by doing the following conversion
+#  (assuming the archive unpacked into a directory named PINNDDK):
+#
+#    ./conv < PINNDDK/dspcode/pndspini.asm > /etc/sound/pndspini.bin
+#    ./conv < PINNDDK/dspcode/pndsperm.asm > /etc/sound/pndsperm.bin
+#
+#  The conv (and conv.l) program is not needed after conversion and can
+#  be safely deleted.  Then, when configuring the Linux kernel, specify
+#  /etc/sound/pndspini.bin and /etc/sound/pndsperm.bin for the two
+#  firmware files (Linux kernel versions older than 2.2 do not ask for
+#  firmware paths, and are hardcoded to /etc/sound).
+#
+#  If you are compiling the driver into the kernel, these files must
+#  be accessible during compilation, but will not be needed later.
+#  The files must remain, however, if the driver is used as a module.
+#
+#
+#  Using Digital I/O with the S/PDIF Port
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#
+#  If you have a Pinnacle or Fiji with the digital daughterboard and
+#  want to set it as the input source, you can use this program if you
+#  have trouble trying to do it with a mixer program (be sure to
+#  insert the module with the digital=1 option, or say Y to the option
+#  during compiled-in kernel operation).  Upon selection of the S/PDIF
+#  port, you should be able monitor and record from it.
+#
+#  There is something to note about using the S/PDIF port.  Digital
+#  timing is taken from the digital signal, so if a signal is not
+#  connected to the port and it is selected as recording input, you
+#  will find PCM playback to be distorted in playback rate.  Also,
+#  attempting to record at a sampling rate other than the DAT rate may
+#  be problematic (i.e. trying to record at 8000Hz when the DAT signal
+#  is 44100Hz).  If you have a problem with this, set the recording
+#  input to analog if you need to record at a rate other than that of
+#  the DAT rate.
+#
+#
+#  -- Shell archive attached below, just run `sh MultiSound' to extract.
+#     Contains Pinnacle/Fiji utilities to convert firmware, configure
+#     in non-PnP mode, and select the DIGITAL1 input for the mixer.
+#
+#
+#!/bin/sh
+# This is a shell archive (produced by GNU sharutils 4.2).
+# To extract the files from this archive, save it to some FILE, remove
+# everything before the `!/bin/sh' line above, then type `sh FILE'.
+#
+# Made on 1998-12-04 10:07 EST by <andrewtv@ztransform.velsoft.com>.
+# Source directory was `/home/andrewtv/programming/pinnacle/pinnacle'.
+#
+# Existing files will *not* be overwritten unless `-c' is specified.
+#
+# This shar contains:
+# length mode       name
+# ------ ---------- ------------------------------------------
+#   2046 -rw-rw-r-- MultiSound.d/setdigital.c
+#  10235 -rw-rw-r-- MultiSound.d/pinnaclecfg.c
+#    106 -rw-rw-r-- MultiSound.d/Makefile
+#    141 -rw-rw-r-- MultiSound.d/conv.l
+#   1472 -rw-rw-r-- MultiSound.d/msndreset.c
+#
+save_IFS="${IFS}"
+IFS="${IFS}:"
+gettext_dir=FAILED
+locale_dir=FAILED
+first_param="$1"
+for dir in $PATH
+do
+  if test "$gettext_dir" = FAILED && test -f $dir/gettext \
+     && ($dir/gettext --version >/dev/null 2>&1)
+  then
+    set `$dir/gettext --version 2>&1`
+    if test "$3" = GNU
+    then
+      gettext_dir=$dir
+    fi
+  fi
+  if test "$locale_dir" = FAILED && test -f $dir/shar \
+     && ($dir/shar --print-text-domain-dir >/dev/null 2>&1)
+  then
+    locale_dir=`$dir/shar --print-text-domain-dir`
+  fi
+done
+IFS="$save_IFS"
+if test "$locale_dir" = FAILED || test "$gettext_dir" = FAILED
+then
+  echo=echo
+else
+  TEXTDOMAINDIR=$locale_dir
+  export TEXTDOMAINDIR
+  TEXTDOMAIN=sharutils
+  export TEXTDOMAIN
+  echo="$gettext_dir/gettext -s"
+fi
+touch -am 1231235999 $$.touch >/dev/null 2>&1
+if test ! -f 1231235999 && test -f $$.touch; then
+  shar_touch=touch
+else
+  shar_touch=:
+  echo
+  $echo 'WARNING: not restoring timestamps.  Consider getting and'
+  $echo "installing GNU \`touch', distributed in GNU File Utilities..."
+  echo
+fi
+rm -f 1231235999 $$.touch
+#
+if mkdir _sh01426; then
+  $echo 'x -' 'creating lock directory'
+else
+  $echo 'failed to create lock directory'
+  exit 1
+fi
+# ============= MultiSound.d/setdigital.c ==============
+if test ! -d 'MultiSound.d'; then
+  $echo 'x -' 'creating directory' 'MultiSound.d'
+  mkdir 'MultiSound.d'
+fi
+if test -f 'MultiSound.d/setdigital.c' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/setdigital.c' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/setdigital.c' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/setdigital.c' &&
+/*********************************************************************
+X *
+X * setdigital.c - sets the DIGITAL1 input for a mixer
+X *
+X * Copyright (C) 1998 Andrew Veliath
+X *
+X * This program is free software; you can redistribute it and/or modify
+X * it under the terms of the GNU General Public License as published by
+X * the Free Software Foundation; either version 2 of the License, or
+X * (at your option) any later version.
+X *
+X * This program is distributed in the hope that it will be useful,
+X * but WITHOUT ANY WARRANTY; without even the implied warranty of
+X * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+X * GNU General Public License for more details.
+X *
+X * You should have received a copy of the GNU General Public License
+X * along with this program; if not, write to the Free Software
+X * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+X *
+X ********************************************************************/
+X
+#include <stdio.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/soundcard.h>
+X
+int main(int argc, char *argv[])
+{
+X	int fd;
+X	unsigned long recmask, recsrc;
+X
+X	if (argc != 2) {
+X		fprintf(stderr, "usage: setdigital <mixer device>\n");
+X		exit(1);
+X	}
+X
+X	if ((fd = open(argv[1], O_RDWR)) < 0) {
+X		perror(argv[1]);
+X		exit(1);
+X	}
+X
+X	if (ioctl(fd, SOUND_MIXER_READ_RECMASK, &recmask) < 0) {
+X		fprintf(stderr, "error: ioctl read recording mask failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	if (!(recmask & SOUND_MASK_DIGITAL1)) {
+X		fprintf(stderr, "error: cannot find DIGITAL1 device in mixer\n");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	if (ioctl(fd, SOUND_MIXER_READ_RECSRC, &recsrc) < 0) {
+X		fprintf(stderr, "error: ioctl read recording source failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	recsrc |= SOUND_MASK_DIGITAL1;
+X
+X	if (ioctl(fd, SOUND_MIXER_WRITE_RECSRC, &recsrc) < 0) {
+X		fprintf(stderr, "error: ioctl write recording source failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	close(fd);
+X
+X	return 0;
+}
+SHAR_EOF
+  $shar_touch -am 1204092598 'MultiSound.d/setdigital.c' &&
+  chmod 0664 'MultiSound.d/setdigital.c' ||
+  $echo 'restore of' 'MultiSound.d/setdigital.c' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/setdigital.c:' 'MD5 check failed'
+e87217fc3e71288102ba41fd81f71ec4  MultiSound.d/setdigital.c
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/setdigital.c'`"
+    test 2046 -eq "$shar_count" ||
+    $echo 'MultiSound.d/setdigital.c:' 'original size' '2046,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/pinnaclecfg.c ==============
+if test -f 'MultiSound.d/pinnaclecfg.c' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/pinnaclecfg.c' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/pinnaclecfg.c' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/pinnaclecfg.c' &&
+/*********************************************************************
+X *
+X * pinnaclecfg.c - Pinnacle/Fiji Device Configuration Program
+X *
+X * This is for NON-PnP mode only.  For PnP mode, use isapnptools.
+X *
+X * This is Linux-specific, and must be run with root permissions.
+X *
+X * Part of the Turtle Beach MultiSound Sound Card Driver for Linux
+X *
+X * Copyright (C) 1998 Andrew Veliath
+X *
+X * This program is free software; you can redistribute it and/or modify
+X * it under the terms of the GNU General Public License as published by
+X * the Free Software Foundation; either version 2 of the License, or
+X * (at your option) any later version.
+X *
+X * This program is distributed in the hope that it will be useful,
+X * but WITHOUT ANY WARRANTY; without even the implied warranty of
+X * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+X * GNU General Public License for more details.
+X *
+X * You should have received a copy of the GNU General Public License
+X * along with this program; if not, write to the Free Software
+X * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+X *
+X ********************************************************************/
+X
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <asm/io.h>
+#include <asm/types.h>
+X
+#define IREG_LOGDEVICE		0x07
+#define IREG_ACTIVATE		0x30
+#define LD_ACTIVATE		0x01
+#define LD_DISACTIVATE		0x00
+#define IREG_EECONTROL		0x3F
+#define IREG_MEMBASEHI		0x40
+#define IREG_MEMBASELO		0x41
+#define IREG_MEMCONTROL		0x42
+#define IREG_MEMRANGEHI		0x43
+#define IREG_MEMRANGELO		0x44
+#define MEMTYPE_8BIT		0x00
+#define MEMTYPE_16BIT		0x02
+#define MEMTYPE_RANGE		0x00
+#define MEMTYPE_HIADDR		0x01
+#define IREG_IO0_BASEHI		0x60
+#define IREG_IO0_BASELO		0x61
+#define IREG_IO1_BASEHI		0x62
+#define IREG_IO1_BASELO		0x63
+#define IREG_IRQ_NUMBER		0x70
+#define IREG_IRQ_TYPE		0x71
+#define IRQTYPE_HIGH		0x02
+#define IRQTYPE_LOW		0x00
+#define IRQTYPE_LEVEL		0x01
+#define IRQTYPE_EDGE		0x00
+X
+#define HIBYTE(w)		((BYTE)(((WORD)(w) >> 8) & 0xFF))
+#define LOBYTE(w)		((BYTE)(w))
+#define MAKEWORD(low,hi)	((WORD)(((BYTE)(low))|(((WORD)((BYTE)(hi)))<<8)))
+X
+typedef __u8			BYTE;
+typedef __u16			USHORT;
+typedef __u16			WORD;
+X
+static int config_port = -1;
+X
+static int msnd_write_cfg(int cfg, int reg, int value)
+{
+X	outb(reg, cfg);
+X	outb(value, cfg + 1);
+X	if (value != inb(cfg + 1)) {
+X		fprintf(stderr, "error: msnd_write_cfg: I/O error\n");
+X		return -EIO;
+X	}
+X	return 0;
+}
+X
+static int msnd_read_cfg(int cfg, int reg)
+{
+X	outb(reg, cfg);
+X	return inb(cfg + 1);
+}
+X
+static int msnd_write_cfg_io0(int cfg, int num, WORD io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO0_BASEHI, HIBYTE(io)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO0_BASELO, LOBYTE(io)))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_io0(int cfg, int num, WORD *io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*io = MAKEWORD(msnd_read_cfg(cfg, IREG_IO0_BASELO),
+X		       msnd_read_cfg(cfg, IREG_IO0_BASEHI));
+X
+X	return 0;
+}
+X
+static int msnd_write_cfg_io1(int cfg, int num, WORD io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO1_BASEHI, HIBYTE(io)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IO1_BASELO, LOBYTE(io)))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_io1(int cfg, int num, WORD *io)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*io = MAKEWORD(msnd_read_cfg(cfg, IREG_IO1_BASELO),
+X		       msnd_read_cfg(cfg, IREG_IO1_BASEHI));
+X
+X	return 0;
+}
+X
+static int msnd_write_cfg_irq(int cfg, int num, WORD irq)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IRQ_NUMBER, LOBYTE(irq)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_IRQ_TYPE, IRQTYPE_EDGE))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_irq(int cfg, int num, WORD *irq)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*irq = msnd_read_cfg(cfg, IREG_IRQ_NUMBER);
+X
+X	return 0;
+}
+X
+static int msnd_write_cfg_mem(int cfg, int num, int mem)
+{
+X	WORD wmem;
+X
+X	mem >>= 8;
+X	mem &= 0xfff;
+X	wmem = (WORD)mem;
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_MEMBASEHI, HIBYTE(wmem)))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_MEMBASELO, LOBYTE(wmem)))
+X		return -EIO;
+X	if (wmem && msnd_write_cfg(cfg, IREG_MEMCONTROL, (MEMTYPE_HIADDR | MEMTYPE_16BIT)))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_mem(int cfg, int num, int *mem)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X
+X	*mem = MAKEWORD(msnd_read_cfg(cfg, IREG_MEMBASELO),
+X			msnd_read_cfg(cfg, IREG_MEMBASEHI));
+X	*mem <<= 8;
+X
+X	return 0;
+}
+X
+static int msnd_activate_logical(int cfg, int num)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg(cfg, IREG_ACTIVATE, LD_ACTIVATE))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_write_cfg_logical(int cfg, int num, WORD io0, WORD io1, WORD irq, int mem)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_write_cfg_io0(cfg, num, io0))
+X		return -EIO;
+X	if (msnd_write_cfg_io1(cfg, num, io1))
+X		return -EIO;
+X	if (msnd_write_cfg_irq(cfg, num, irq))
+X		return -EIO;
+X	if (msnd_write_cfg_mem(cfg, num, mem))
+X		return -EIO;
+X	if (msnd_activate_logical(cfg, num))
+X		return -EIO;
+X	return 0;
+}
+X
+static int msnd_read_cfg_logical(int cfg, int num, WORD *io0, WORD *io1, WORD *irq, int *mem)
+{
+X	if (msnd_write_cfg(cfg, IREG_LOGDEVICE, num))
+X		return -EIO;
+X	if (msnd_read_cfg_io0(cfg, num, io0))
+X		return -EIO;
+X	if (msnd_read_cfg_io1(cfg, num, io1))
+X		return -EIO;
+X	if (msnd_read_cfg_irq(cfg, num, irq))
+X		return -EIO;
+X	if (msnd_read_cfg_mem(cfg, num, mem))
+X		return -EIO;
+X	return 0;
+}
+X
+static void usage(void)
+{
+X	fprintf(stderr,
+X		"\n"
+X		"pinnaclecfg 1.0\n"
+X		"\n"
+X		"usage: pinnaclecfg <config port> [device config]\n"
+X		"\n"
+X		"This is for use with the card in NON-PnP mode only.\n"
+X		"\n"
+X		"Available devices (not all available for Fiji):\n"
+X		"\n"
+X		"        Device                       Description\n"
+X		"        -------------------------------------------------------------------\n"
+X		"        reset                        Reset all devices (i.e. disable)\n"
+X		"        show                         Display current device configurations\n"
+X		"\n"
+X		"        dsp <io> <irq> <mem>         Audio device\n"
+X		"        mpu <io> <irq>               Internal Kurzweil synth\n"
+X		"        ide <io0> <io1> <irq>        On-board IDE controller\n"
+X		"        joystick <io>                Joystick port\n"
+X		"\n");
+X	exit(1);
+}
+X
+static int cfg_reset(void)
+{
+X	int i;
+X
+X	for (i = 0; i < 4; ++i)
+X		msnd_write_cfg_logical(config_port, i, 0, 0, 0, 0);
+X
+X	return 0;
+}
+X
+static int cfg_show(void)
+{
+X	int i;
+X	int count = 0;
+X
+X	for (i = 0; i < 4; ++i) {
+X		WORD io0, io1, irq;
+X		int mem;
+X		msnd_read_cfg_logical(config_port, i, &io0, &io1, &irq, &mem);
+X		switch (i) {
+X		case 0:
+X			if (io0 || irq || mem) {
+X				printf("dsp 0x%x %d 0x%x\n", io0, irq, mem);
+X				++count;
+X			}
+X			break;
+X		case 1:
+X			if (io0 || irq) {
+X				printf("mpu 0x%x %d\n", io0, irq);
+X				++count;
+X			}
+X			break;
+X		case 2:
+X			if (io0 || io1 || irq) {
+X				printf("ide 0x%x 0x%x %d\n", io0, io1, irq);
+X				++count;
+X			}
+X			break;
+X		case 3:
+X			if (io0) {
+X				printf("joystick 0x%x\n", io0);
+X				++count;
+X			}
+X			break;
+X		}
+X	}
+X
+X	if (count == 0)
+X		fprintf(stderr, "no devices configured\n");
+X
+X	return 0;
+}
+X
+static int cfg_dsp(int argc, char *argv[])
+{
+X	int io, irq, mem;
+X
+X	if (argc < 3 ||
+X	    sscanf(argv[0], "0x%x", &io) != 1 ||
+X	    sscanf(argv[1], "%d", &irq) != 1 ||
+X	    sscanf(argv[2], "0x%x", &mem) != 1)
+X		usage();
+X
+X	if (!(io == 0x290 ||
+X	      io == 0x260 ||
+X	      io == 0x250 ||
+X	      io == 0x240 ||
+X	      io == 0x230 ||
+X	      io == 0x220 ||
+X	      io == 0x210 ||
+X	      io == 0x3e0)) {
+X		fprintf(stderr, "error: io must be one of "
+X			"210, 220, 230, 240, 250, 260, 290, or 3E0\n");
+X		usage();
+X	}
+X
+X	if (!(irq == 5 ||
+X	      irq == 7 ||
+X	      irq == 9 ||
+X	      irq == 10 ||
+X	      irq == 11 ||
+X	      irq == 12)) {
+X		fprintf(stderr, "error: irq must be one of "
+X			"5, 7, 9, 10, 11 or 12\n");
+X		usage();
+X	}
+X
+X	if (!(mem == 0xb0000 ||
+X	      mem == 0xc8000 ||
+X	      mem == 0xd0000 ||
+X	      mem == 0xd8000 ||
+X	      mem == 0xe0000 ||
+X	      mem == 0xe8000)) {
+X		fprintf(stderr, "error: mem must be one of "
+X			"0xb0000, 0xc8000, 0xd0000, 0xd8000, 0xe0000 or 0xe8000\n");
+X		usage();
+X	}
+X
+X	return msnd_write_cfg_logical(config_port, 0, io, 0, irq, mem);
+}
+X
+static int cfg_mpu(int argc, char *argv[])
+{
+X	int io, irq;
+X
+X	if (argc < 2 ||
+X	    sscanf(argv[0], "0x%x", &io) != 1 ||
+X	    sscanf(argv[1], "%d", &irq) != 1)
+X		usage();
+X
+X	return msnd_write_cfg_logical(config_port, 1, io, 0, irq, 0);
+}
+X
+static int cfg_ide(int argc, char *argv[])
+{
+X	int io0, io1, irq;
+X
+X	if (argc < 3 ||
+X	    sscanf(argv[0], "0x%x", &io0) != 1 ||
+X	    sscanf(argv[0], "0x%x", &io1) != 1 ||
+X	    sscanf(argv[1], "%d", &irq) != 1)
+X		usage();
+X
+X	return msnd_write_cfg_logical(config_port, 2, io0, io1, irq, 0);
+}
+X
+static int cfg_joystick(int argc, char *argv[])
+{
+X	int io;
+X
+X	if (argc < 1 ||
+X	    sscanf(argv[0], "0x%x", &io) != 1)
+X		usage();
+X
+X	return msnd_write_cfg_logical(config_port, 3, io, 0, 0, 0);
+}
+X
+int main(int argc, char *argv[])
+{
+X	char *device;
+X	int rv = 0;
+X
+X	--argc; ++argv;
+X
+X	if (argc < 2)
+X		usage();
+X
+X	sscanf(argv[0], "0x%x", &config_port);
+X	if (config_port != 0x250 && config_port != 0x260 && config_port != 0x270) {
+X		fprintf(stderr, "error: <config port> must be 0x250, 0x260 or 0x270\n");
+X		exit(1);
+X	}
+X	if (ioperm(config_port, 2, 1)) {
+X		perror("ioperm");
+X		fprintf(stderr, "note: pinnaclecfg must be run as root\n");
+X		exit(1);
+X	}
+X	device = argv[1];
+X
+X	argc -= 2; argv += 2;
+X
+X	if (strcmp(device, "reset") == 0)
+X		rv = cfg_reset();
+X	else if (strcmp(device, "show") == 0)
+X		rv = cfg_show();
+X	else if (strcmp(device, "dsp") == 0)
+X		rv = cfg_dsp(argc, argv);
+X	else if (strcmp(device, "mpu") == 0)
+X		rv = cfg_mpu(argc, argv);
+X	else if (strcmp(device, "ide") == 0)
+X		rv = cfg_ide(argc, argv);
+X	else if (strcmp(device, "joystick") == 0)
+X		rv = cfg_joystick(argc, argv);
+X	else {
+X		fprintf(stderr, "error: unknown device %s\n", device);
+X		usage();
+X	}
+X
+X	if (rv)
+X		fprintf(stderr, "error: device configuration failed\n");
+X
+X	return 0;
+}
+SHAR_EOF
+  $shar_touch -am 1204092598 'MultiSound.d/pinnaclecfg.c' &&
+  chmod 0664 'MultiSound.d/pinnaclecfg.c' ||
+  $echo 'restore of' 'MultiSound.d/pinnaclecfg.c' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/pinnaclecfg.c:' 'MD5 check failed'
+366bdf27f0db767a3c7921d0a6db20fe  MultiSound.d/pinnaclecfg.c
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/pinnaclecfg.c'`"
+    test 10235 -eq "$shar_count" ||
+    $echo 'MultiSound.d/pinnaclecfg.c:' 'original size' '10235,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/Makefile ==============
+if test -f 'MultiSound.d/Makefile' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/Makefile' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/Makefile' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/Makefile' &&
+CC	= gcc
+CFLAGS	= -O
+PROGS	= setdigital msndreset pinnaclecfg conv
+X
+all: $(PROGS)
+X
+clean:
+X	rm -f $(PROGS)
+SHAR_EOF
+  $shar_touch -am 1204092398 'MultiSound.d/Makefile' &&
+  chmod 0664 'MultiSound.d/Makefile' ||
+  $echo 'restore of' 'MultiSound.d/Makefile' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/Makefile:' 'MD5 check failed'
+76ca8bb44e3882edcf79c97df6c81845  MultiSound.d/Makefile
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/Makefile'`"
+    test 106 -eq "$shar_count" ||
+    $echo 'MultiSound.d/Makefile:' 'original size' '106,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/conv.l ==============
+if test -f 'MultiSound.d/conv.l' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/conv.l' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/conv.l' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/conv.l' &&
+%%
+[ \n\t,\r]
+\;.*
+DB
+[0-9A-Fa-f]+H	{ int n; sscanf(yytext, "%xH", &n); printf("%c", n); }
+%%
+int yywrap() { return 1; }
+main() { yylex(); }
+SHAR_EOF
+  $shar_touch -am 0828231798 'MultiSound.d/conv.l' &&
+  chmod 0664 'MultiSound.d/conv.l' ||
+  $echo 'restore of' 'MultiSound.d/conv.l' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/conv.l:' 'MD5 check failed'
+d2411fc32cd71a00dcdc1f009e858dd2  MultiSound.d/conv.l
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/conv.l'`"
+    test 141 -eq "$shar_count" ||
+    $echo 'MultiSound.d/conv.l:' 'original size' '141,' 'current size' "$shar_count!"
+  fi
+fi
+# ============= MultiSound.d/msndreset.c ==============
+if test -f 'MultiSound.d/msndreset.c' && test "$first_param" != -c; then
+  $echo 'x -' SKIPPING 'MultiSound.d/msndreset.c' '(file already exists)'
+else
+  $echo 'x -' extracting 'MultiSound.d/msndreset.c' '(text)'
+  sed 's/^X//' << 'SHAR_EOF' > 'MultiSound.d/msndreset.c' &&
+/*********************************************************************
+X *
+X * msndreset.c - resets the MultiSound card
+X *
+X * Copyright (C) 1998 Andrew Veliath
+X *
+X * This program is free software; you can redistribute it and/or modify
+X * it under the terms of the GNU General Public License as published by
+X * the Free Software Foundation; either version 2 of the License, or
+X * (at your option) any later version.
+X *
+X * This program is distributed in the hope that it will be useful,
+X * but WITHOUT ANY WARRANTY; without even the implied warranty of
+X * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+X * GNU General Public License for more details.
+X *
+X * You should have received a copy of the GNU General Public License
+X * along with this program; if not, write to the Free Software
+X * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+X *
+X ********************************************************************/
+X
+#include <stdio.h>
+#include <unistd.h>
+#include <fcntl.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <sys/ioctl.h>
+#include <sys/soundcard.h>
+X
+int main(int argc, char *argv[])
+{
+X	int fd;
+X
+X	if (argc != 2) {
+X		fprintf(stderr, "usage: msndreset <mixer device>\n");
+X		exit(1);
+X	}
+X
+X	if ((fd = open(argv[1], O_RDWR)) < 0) {
+X		perror(argv[1]);
+X		exit(1);
+X	}
+X
+X	if (ioctl(fd, SOUND_MIXER_PRIVATE1, 0) < 0) {
+X		fprintf(stderr, "error: msnd ioctl reset failed\n");
+X		perror("ioctl");
+X		close(fd);
+X		exit(1);
+X	}
+X
+X	close(fd);
+X
+X	return 0;
+}
+SHAR_EOF
+  $shar_touch -am 1204100698 'MultiSound.d/msndreset.c' &&
+  chmod 0664 'MultiSound.d/msndreset.c' ||
+  $echo 'restore of' 'MultiSound.d/msndreset.c' 'failed'
+  if ( md5sum --help 2>&1 | grep 'sage: md5sum \[' ) >/dev/null 2>&1 \
+  && ( md5sum --version 2>&1 | grep -v 'textutils 1.12' ) >/dev/null; then
+    md5sum -c << SHAR_EOF >/dev/null 2>&1 \
+    || $echo 'MultiSound.d/msndreset.c:' 'MD5 check failed'
+c52f876521084e8eb25e12e01dcccb8a  MultiSound.d/msndreset.c
+SHAR_EOF
+  else
+    shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/msndreset.c'`"
+    test 1472 -eq "$shar_count" ||
+    $echo 'MultiSound.d/msndreset.c:' 'original size' '1472,' 'current size' "$shar_count!"
+  fi
+fi
+rm -fr _sh01426
+exit 0
-- 
cgit v1.2.3


From 06501a6d2d2912b9e357702327c0249a5ecd7c9e Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:24:38 -0300
Subject: ALSA:: multisound.sh: fix script to make it build with modern tools

The script is old and produce some warnings and errors, because
it lacks including stdlib.h and io.h is at sys/io.h.

Fix it to run with the tools found on modern Linux distros.

Tested building it on Fedora 28.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/cards/multisound.sh | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/Documentation/sound/cards/multisound.sh b/Documentation/sound/cards/multisound.sh
index 7a7a88256dfd..0e0cb029421b 100755
--- a/Documentation/sound/cards/multisound.sh
+++ b/Documentation/sound/cards/multisound.sh
@@ -381,11 +381,11 @@
 # This shar contains:
 # length mode       name
 # ------ ---------- ------------------------------------------
-#   2046 -rw-rw-r-- MultiSound.d/setdigital.c
-#  10235 -rw-rw-r-- MultiSound.d/pinnaclecfg.c
+#   2064 -rw-rw-r-- MultiSound.d/setdigital.c
+#  10224 -rw-rw-r-- MultiSound.d/pinnaclecfg.c
 #    106 -rw-rw-r-- MultiSound.d/Makefile
-#    141 -rw-rw-r-- MultiSound.d/conv.l
-#   1472 -rw-rw-r-- MultiSound.d/msndreset.c
+#    146 -rw-rw-r-- MultiSound.d/conv.l
+#   1491 -rw-rw-r-- MultiSound.d/msndreset.c
 #
 save_IFS="${IFS}"
 IFS="${IFS}:"
@@ -471,6 +471,7 @@ X *
 X ********************************************************************/
 X
 #include <stdio.h>
+#include <stdlib.h>
 #include <unistd.h>
 #include <fcntl.h>
 #include <sys/types.h>
@@ -538,8 +539,8 @@ e87217fc3e71288102ba41fd81f71ec4  MultiSound.d/setdigital.c
 SHAR_EOF
   else
     shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/setdigital.c'`"
-    test 2046 -eq "$shar_count" ||
-    $echo 'MultiSound.d/setdigital.c:' 'original size' '2046,' 'current size' "$shar_count!"
+    test 2064 -eq "$shar_count" ||
+    $echo 'MultiSound.d/setdigital.c:' 'original size' '2064,' 'current size' "$shar_count!"
   fi
 fi
 # ============= MultiSound.d/pinnaclecfg.c ==============
@@ -581,8 +582,8 @@ X
 #include <string.h>
 #include <errno.h>
 #include <unistd.h>
-#include <asm/io.h>
 #include <asm/types.h>
+#include <sys/io.h>
 X
 #define IREG_LOGDEVICE		0x07
 #define IREG_ACTIVATE		0x30
@@ -992,8 +993,8 @@ SHAR_EOF
 SHAR_EOF
   else
     shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/pinnaclecfg.c'`"
-    test 10235 -eq "$shar_count" ||
-    $echo 'MultiSound.d/pinnaclecfg.c:' 'original size' '10235,' 'current size' "$shar_count!"
+    test 10224 -eq "$shar_count" ||
+    $echo 'MultiSound.d/pinnaclecfg.c:' 'original size' '10224,' 'current size' "$shar_count!"
   fi
 fi
 # ============= MultiSound.d/Makefile ==============
@@ -1039,7 +1040,7 @@ DB
 [0-9A-Fa-f]+H	{ int n; sscanf(yytext, "%xH", &n); printf("%c", n); }
 %%
 int yywrap() { return 1; }
-main() { yylex(); }
+void main() { yylex(); }
 SHAR_EOF
   $shar_touch -am 0828231798 'MultiSound.d/conv.l' &&
   chmod 0664 'MultiSound.d/conv.l' ||
@@ -1052,8 +1053,8 @@ d2411fc32cd71a00dcdc1f009e858dd2  MultiSound.d/conv.l
 SHAR_EOF
   else
     shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/conv.l'`"
-    test 141 -eq "$shar_count" ||
-    $echo 'MultiSound.d/conv.l:' 'original size' '141,' 'current size' "$shar_count!"
+    test 146 -eq "$shar_count" ||
+    $echo 'MultiSound.d/conv.l:' 'original size' '146,' 'current size' "$shar_count!"
   fi
 fi
 # ============= MultiSound.d/msndreset.c ==============
@@ -1085,6 +1086,7 @@ X *
 X ********************************************************************/
 X
 #include <stdio.h>
+#include <stdlib.h>
 #include <unistd.h>
 #include <fcntl.h>
 #include <sys/types.h>
@@ -1129,8 +1131,8 @@ c52f876521084e8eb25e12e01dcccb8a  MultiSound.d/msndreset.c
 SHAR_EOF
   else
     shar_count="`LC_ALL= LC_CTYPE= LANG= wc -c < 'MultiSound.d/msndreset.c'`"
-    test 1472 -eq "$shar_count" ||
-    $echo 'MultiSound.d/msndreset.c:' 'original size' '1472,' 'current size' "$shar_count!"
+    test 1491 -eq "$shar_count" ||
+    $echo 'MultiSound.d/msndreset.c:' 'original size' '1491,' 'current size' "$shar_count!"
   fi
 fi
 rm -fr _sh01426
-- 
cgit v1.2.3


From 513f930667beca7f67e3aa4558196c143864083f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:24:39 -0300
Subject: ALSA: multisound.sh: update module namespace

The modules for the cards described here changed their names.
Update accordingly.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/cards/multisound.sh | 72 ++++++++++++++++-----------------
 1 file changed, 36 insertions(+), 36 deletions(-)

diff --git a/Documentation/sound/cards/multisound.sh b/Documentation/sound/cards/multisound.sh
index 0e0cb029421b..a915a1affcde 100755
--- a/Documentation/sound/cards/multisound.sh
+++ b/Documentation/sound/cards/multisound.sh
@@ -34,12 +34,12 @@
 #  composed of the following modules (these can also operate compiled
 #  into the kernel):
 #
-#  msnd               - MultiSound base (requires soundcore)
+#  snd-msnd-lib           - MultiSound base (requires snd)
 #
-#  msnd_classic       - Base audio/mixer support for Classic, Monetery and
-#                       Tahiti cards
+#  snd-msnd-classic       - Base audio/mixer support for Classic, Monetery and
+#                           Tahiti cards
 #
-#  msnd_pinnacle      - Base audio/mixer support for Pinnacle and Fiji cards
+#  snd-msnd-pinnacle      - Base audio/mixer support for Pinnacle and Fiji cards
 #
 #
 #  Important Notes - Read Before Using
@@ -66,7 +66,7 @@
 #
 #  * Classic/Monterey/Tahiti
 #
-#  These cards are configured through the driver msnd_classic.  You must
+#  These cards are configured through the driver snd-msnd-classic.  You must
 #  know the io port, then the driver will select the irq and memory resources
 #  on the card.  It is up to you to know if these are free locations or now,
 #  a conflict can lock the machine up.
@@ -81,10 +81,10 @@
 #  can be used to configure the card in non-PnP mode, and in PnP mode
 #  you can use isapnptools.  These are described briefly here.
 #
-#  pinnaclecfg is not required; you can use the msnd_pinnacle module
+#  pinnaclecfg is not required; you can use the snd-msnd-pinnacle module
 #  to fully configure the card as well.  However, pinnaclecfg can be
 #  used to change the resource values of a particular device after the
-#  msnd_pinnacle module has been loaded.  If you are compiling the
+#  snd-msnd-pinnacle module has been loaded.  If you are compiling the
 #  driver into the kernel, you must set these values during compile
 #  time, however other peripheral resource values can be changed with
 #  the pinnaclecfg program after the kernel is loaded.
@@ -96,7 +96,7 @@
 #  to obtain one with the command `pnpdump 1 0x203' -- this may vary
 #  for you (running pnpdump by itself did not work for me).  Then,
 #  edit this file and use isapnp to uncomment and set the card values.
-#  Use these values when inserting the msnd_pinnacle module.  Using
+#  Use these values when inserting the snd-msnd-pinnacle module.  Using
 #  this method, you can set the resources for the DSP and the Kurzweil
 #  synth (Pinnacle).  Since Linux does not directly support PnP
 #  devices, you may have difficulty when using the card in PnP mode
@@ -133,16 +133,16 @@
 #  pinnaclecfg program.  Using this program, you can assign the
 #  resource values to the card's devices, or disable the devices.  As
 #  an alternative to using pinnaclecfg, you can specify many of the
-#  configuration values when loading the msnd_pinnacle module (or
+#  configuration values when loading the snd-msnd-pinnacle module (or
 #  during kernel configuration when compiling the driver into the
 #  kernel).
 #
-#  If you specify cfg=0x250 for the msnd_pinnacle module, it
+#  If you specify cfg=0x250 for the snd-msnd-pinnacle module, it
 #  automatically configure the card to the given io, irq and memory
 #  values using that config port (the config port is jumper selectable
 #  on the card to 0x250, 0x260 or 0x270).
 #
-#  See the `msnd_pinnacle Additional Options' section below for more
+#  See the `snd-msnd-pinnacle Additional Options' section below for more
 #  information on these parameters (also, if you compile the driver
 #  directly into the kernel, these extra parameters can be useful
 #  here).
@@ -157,44 +157,44 @@
 #
 #  * MultiSound Classic/Monterey/Tahiti:
 #
-#  modprobe soundcore
-#  insmod msnd
-#  insmod msnd_classic io=0x290 irq=7 mem=0xd0000
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-classic io=0x290 irq=7 mem=0xd0000
 #
 #  * MultiSound Pinnacle in PnP mode:
 #
-#  modprobe soundcore
-#  insmod msnd
+#  modprobe snd
+#  insmod snd-msnd-lib
 #  isapnp mypinnacle.conf
-#  insmod msnd_pinnacle io=0x210 irq=5 mem=0xd8000 <-- match mypinnacle.conf values
+#  insmod snd-msnd-pinnacle io=0x210 irq=5 mem=0xd8000 <-- match mypinnacle.conf values
 #
 #  * MultiSound Pinnacle in non-PnP mode (replace 0x250 with your configuration port,
 #    one of 0x250, 0x260 or 0x270):
 #
-#  insmod soundcore
-#  insmod msnd
-#  insmod msnd_pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000
 #
 # * To use the MPU-compatible Kurzweil synth on the Pinnacle in PnP
 #   mode, add the following (assumes you did `isapnp mypinnacle.conf'):
 #
-#  insmod sound
+#  insmod snd
 #  insmod mpu401 io=0x330 irq=9                    <-- match mypinnacle.conf values
 #
 # * To use the MPU-compatible Kurzweil synth on the Pinnacle in non-PnP
 #   mode, add the following.  Note how we first configure the peripheral's
 #   resources, _then_ install a Linux driver for it:
 #
-#  insmod sound
+#  insmod snd
 #  pinnaclecfg 0x250 mpu 0x330 9
 #  insmod mpu401 io=0x330 irq=9
 #
 #  -- OR you can use the following sequence without pinnaclecfg in non-PnP mode:
 #
-#  insmod soundcore
-#  insmod msnd
-#  insmod msnd_pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 mpu_io=0x330 mpu_irq=9
-#  insmod sound
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 mpu_io=0x330 mpu_irq=9
+#  insmod snd
 #  insmod mpu401 io=0x330 irq=9
 #
 # * To setup the joystick port on the Pinnacle in non-PnP mode (though
@@ -203,15 +203,15 @@
 #
 #   pinnaclecfg 0x250 joystick 0x200
 #
-#  -- OR you can configure this using msnd_pinnacle with the following:
+#  -- OR you can configure this using snd-msnd-pinnacle with the following:
 #
-#  insmod soundcore
-#  insmod msnd
-#  insmod msnd_pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 joystick_io=0x200
+#  modprobe snd
+#  insmod snd-msnd-lib
+#  insmod snd-msnd-pinnacle cfg=0x250 io=0x290 irq=5 mem=0xd0000 joystick_io=0x200
 #
 #
-#  msnd_classic, msnd_pinnacle Required Options
-#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#  snd-msnd-classic, snd-msnd-pinnacle Required Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 #
 #  If the following options are not given, the module will not load.
 #  Examine the kernel message log for informative error messages.
@@ -223,8 +223,8 @@
 #  mem                  Shared memory area, e.g. mem=0xd8000
 #
 #
-#  msnd_classic, msnd_pinnacle Additional Options
-#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#  snd-msnd-classic, snd-msnd-pinnacle Additional Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 #
 #  fifosize             The digital audio FIFOs, in kilobytes.  If not
 #                       specified, the default will be used.  Increasing
@@ -244,8 +244,8 @@
 #                       to zero).
 #
 #
-#  msnd_pinnacle Additional Options
-#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+#  snd-msnd-pinnacle Additional Options
+#  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 #
 #  digital              Specify digital=1 to enable the S/PDIF input
 #                       if you have the digital daughterboard
-- 
cgit v1.2.3


From 0e6995e3b37bac69b4a815a116f9992d31a7bba0 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:24:40 -0300
Subject: ALSA: Fix references to Documentation/.*/MultiSound

Now that the documentation/script file got restored, fix the
references within the Kernel tree.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/alsa-configuration.rst | 2 +-
 sound/isa/Kconfig                          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/sound/alsa-configuration.rst b/Documentation/sound/alsa-configuration.rst
index 4d83c1c0ca04..4a3cecc8ad38 100644
--- a/Documentation/sound/alsa-configuration.rst
+++ b/Documentation/sound/alsa-configuration.rst
@@ -1568,7 +1568,7 @@ joystick_io
 The driver requires firmware files ``turtlebeach/msndinit.bin`` and
 ``turtlebeach/msndperm.bin`` in the proper firmware directory.
 
-See Documentation/sound/oss/MultiSound for important information
+See Documentation/sound/cards/multisound.sh for important information
 about this driver.  Note that it has been discontinued, but the 
 Voyetra Turtle Beach knowledge base entry for it is still available
 at
diff --git a/sound/isa/Kconfig b/sound/isa/Kconfig
index 43b35a873d78..d7db1eeebc84 100644
--- a/sound/isa/Kconfig
+++ b/sound/isa/Kconfig
@@ -459,7 +459,7 @@ config SND_MSND_CLASSIC
 	  Say M here if you have a Turtle Beach MultiSound Classic, Tahiti or
 	  Monterey (not for the Pinnacle or Fiji).
 
-	  See <file:Documentation/sound/oss/MultiSound> for important information
+	  See <file:Documentation/sound/cards/multisound.sh> for important information
 	  about this driver.  Note that it has been discontinued, but the
 	  Voyetra Turtle Beach knowledge base entry for it is still available
 	  at <http://www.turtlebeach.com/site/kb_ftp/790.asp>.
-- 
cgit v1.2.3


From 38150f7a68ef736c4cbae53b6f1f2a19c55178a3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:26:47 +0200
Subject: scsi: aacraid: stop using deprated get_seconds()

get_seconds() can overflow on 32-bit architectures and is deprecated
because of that. The use in the aacraid driver has the same problem due to
a limited firmware interface, it also overflows in the year 2106.

This changes all calls to get_seconds() to the non-deprecated
ktime_get_real_seconds(), which unfortunately doesn't solve that problem
but gets rid of one user of the deprecated interface.

[mkp: checkpatch]

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/rx.c  | 2 +-
 drivers/scsi/aacraid/sa.c  | 2 +-
 drivers/scsi/aacraid/src.c | 6 ++++--
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/aacraid/rx.c b/drivers/scsi/aacraid/rx.c
index 620166694171..576cdf9cc120 100644
--- a/drivers/scsi/aacraid/rx.c
+++ b/drivers/scsi/aacraid/rx.c
@@ -319,7 +319,7 @@ static void aac_rx_start_adapter(struct aac_dev *dev)
 	union aac_init *init;
 
 	init = dev->init;
-	init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
+	init->r7.host_elapsed_seconds = cpu_to_le32(ktime_get_real_seconds());
 	// We can only use a 32 bit address here
 	rx_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS, (u32)(ulong)dev->init_pa,
 	  0, 0, 0, 0, 0, NULL, NULL, NULL, NULL, NULL);
diff --git a/drivers/scsi/aacraid/sa.c b/drivers/scsi/aacraid/sa.c
index 882f40353b96..efa96c1c6aa3 100644
--- a/drivers/scsi/aacraid/sa.c
+++ b/drivers/scsi/aacraid/sa.c
@@ -251,7 +251,7 @@ static void aac_sa_start_adapter(struct aac_dev *dev)
 	 * Fill in the remaining pieces of the init.
 	 */
 	init = dev->init;
-	init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
+	init->r7.host_elapsed_seconds = cpu_to_le32(ktime_get_real_seconds());
 	/* We can only use a 32 bit address here */
 	sa_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS, 
 			(u32)(ulong)dev->init_pa, 0, 0, 0, 0, 0,
diff --git a/drivers/scsi/aacraid/src.c b/drivers/scsi/aacraid/src.c
index 4ebb35a29caa..7a51ccfa8662 100644
--- a/drivers/scsi/aacraid/src.c
+++ b/drivers/scsi/aacraid/src.c
@@ -409,7 +409,8 @@ static void aac_src_start_adapter(struct aac_dev *dev)
 
 	init = dev->init;
 	if (dev->comm_interface == AAC_COMM_MESSAGE_TYPE3) {
-		init->r8.host_elapsed_seconds = cpu_to_le32(get_seconds());
+		init->r8.host_elapsed_seconds =
+			cpu_to_le32(ktime_get_real_seconds());
 		src_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS,
 			lower_32_bits(dev->init_pa),
 			upper_32_bits(dev->init_pa),
@@ -417,7 +418,8 @@ static void aac_src_start_adapter(struct aac_dev *dev)
 			(AAC_MAX_HRRQ - 1) * sizeof(struct _rrq),
 			0, 0, 0, NULL, NULL, NULL, NULL, NULL);
 	} else {
-		init->r7.host_elapsed_seconds = cpu_to_le32(get_seconds());
+		init->r7.host_elapsed_seconds =
+			cpu_to_le32(ktime_get_real_seconds());
 		// We can only use a 32 bit address here
 		src_sync_cmd(dev, INIT_STRUCT_BASE_ADDRESS,
 			(u32)(ulong)dev->init_pa, 0, 0, 0, 0, 0,
-- 
cgit v1.2.3


From fe7f4e5d11541402f54ebd777a4f49caee891401 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:29:51 +0200
Subject: scsi: scsi_transport_fc: use 64-bit timestamps consistently

The get_seconds() helper returns an 'unsigned long' value, which can
overflow on 32-bit architectures. Since the interface we pass it into
already uses a 64-bit type, we can just use ktime_get_real_seconds()
instead.

While we generally prefer local timestamps in CLOCK_MONOTONIC format
(ktime_get_seconds), this keeps using the CLOCK_REALTIME version in order
to maintain compatibility with existing code.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Reviewed-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_transport_fc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/scsi_transport_fc.c b/drivers/scsi/scsi_transport_fc.c
index 1da3d71e9f61..bb6de88aa724 100644
--- a/drivers/scsi/scsi_transport_fc.c
+++ b/drivers/scsi/scsi_transport_fc.c
@@ -567,7 +567,7 @@ fc_host_post_event(struct Scsi_Host *shost, u32 event_number,
 
 	INIT_SCSI_NL_HDR(&event->snlh, SCSI_NL_TRANSPORT_FC,
 				FC_NL_ASYNC_EVENT, len);
-	event->seconds = get_seconds();
+	event->seconds = ktime_get_real_seconds();
 	event->vendor_id = 0;
 	event->host_no = shost->host_no;
 	event->event_datalen = sizeof(u32);	/* bytes */
@@ -635,7 +635,7 @@ fc_host_post_vendor_event(struct Scsi_Host *shost, u32 event_number,
 
 	INIT_SCSI_NL_HDR(&event->snlh, SCSI_NL_TRANSPORT_FC,
 				FC_NL_ASYNC_EVENT, len);
-	event->seconds = get_seconds();
+	event->seconds = ktime_get_real_seconds();
 	event->vendor_id = vendor_id;
 	event->host_no = shost->host_no;
 	event->event_datalen = data_len;	/* bytes */
-- 
cgit v1.2.3


From c4d6204dc1742581c0450d2ff6a058f61ea4f4ce Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:28:23 +0200
Subject: scsi: lpfc: use monotonic timestamps for statistics

The get_seconds() function suffers from a possible overflow in 2038 or
2106, as well as jitter due to settimeofday or leap second updates, and is
deprecated.

As we are interested in elapsed time only, using ktime_get_seconds() to
read the CLOCK_MONOTONIC timebase is ideal here. This also lets us remove
the hack that tries to deal with get_seconds() going slightly backwards,
which cannot happen with montonic timestamps.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_attr.c | 10 ++--------
 drivers/scsi/lpfc/lpfc_sli.c  |  4 ++--
 drivers/scsi/lpfc/lpfc_sli.h  |  2 +-
 3 files changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 729d343861f4..15c07481fe23 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -5891,7 +5891,6 @@ lpfc_get_stats(struct Scsi_Host *shost)
 	struct lpfc_lnk_stat * lso = &psli->lnk_stat_offsets;
 	LPFC_MBOXQ_t *pmboxq;
 	MAILBOX_t *pmb;
-	unsigned long seconds;
 	int rc = 0;
 
 	/*
@@ -5992,12 +5991,7 @@ lpfc_get_stats(struct Scsi_Host *shost)
 
 	hs->dumped_frames = -1;
 
-	seconds = get_seconds();
-	if (seconds < psli->stats_start)
-		hs->seconds_since_last_reset = seconds +
-				((unsigned long)-1 - psli->stats_start);
-	else
-		hs->seconds_since_last_reset = seconds - psli->stats_start;
+	hs->seconds_since_last_reset = ktime_get_seconds() - psli->stats_start;
 
 	mempool_free(pmboxq, phba->mbox_mem_pool);
 
@@ -6076,7 +6070,7 @@ lpfc_reset_stats(struct Scsi_Host *shost)
 	else
 		lso->link_events = (phba->fc_eventTag >> 1);
 
-	psli->stats_start = get_seconds();
+	psli->stats_start = ktime_get_seconds();
 
 	mempool_free(pmboxq, phba->mbox_mem_pool);
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 6f3c00a233ec..e6786a5db502 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -4591,7 +4591,7 @@ lpfc_sli_brdrestart_s3(struct lpfc_hba *phba)
 	spin_unlock_irq(&phba->hbalock);
 
 	memset(&psli->lnk_stat_offsets, 0, sizeof(psli->lnk_stat_offsets));
-	psli->stats_start = get_seconds();
+	psli->stats_start = ktime_get_seconds();
 
 	/* Give the INITFF and Post time to settle. */
 	mdelay(100);
@@ -4638,7 +4638,7 @@ lpfc_sli_brdrestart_s4(struct lpfc_hba *phba)
 	spin_unlock_irq(&phba->hbalock);
 
 	memset(&psli->lnk_stat_offsets, 0, sizeof(psli->lnk_stat_offsets));
-	psli->stats_start = get_seconds();
+	psli->stats_start = ktime_get_seconds();
 
 	/* Reset HBA AER if it was enabled, note hba_flag was reset above */
 	if (hba_aer_enabled)
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 431754195505..80b191d73190 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -339,7 +339,7 @@ struct lpfc_sli {
 	struct lpfc_iocbq ** iocbq_lookup; /* array to lookup IOCB by IOTAG */
 	size_t iocbq_lookup_len;           /* current lengs of the array */
 	uint16_t  last_iotag;              /* last allocated IOTAG */
-	unsigned long  stats_start;        /* in seconds */
+	time64_t  stats_start;		   /* in seconds */
 	struct lpfc_lnk_stat lnk_stat_offsets;
 };
 
-- 
cgit v1.2.3


From aa3841b56b3b4f68d1e0a64941189ec932c4881b Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 26 Jun 2018 07:42:40 +0200
Subject: ALSA: hda/realtek - Comprehensive model list for ALC662 & co

ALC662 and others have far more fixup entries than the model table.
Let's add more model string entries so that user can test / debug
without compiling kernels at each time.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/hd-audio/models.rst | 36 +++++++++++++++++++++++++++++++++
 sound/pci/hda/patch_realtek.c           | 18 +++++++++++++++++
 2 files changed, 54 insertions(+)

diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index 7c2d37571af0..f2f8402ff899 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -87,8 +87,14 @@ alc700-ref
 
 ALC66x/67x/892
 ==============
+aspire
+    Subwoofer pin fixup for Aspire laptops
+ideapad
+    Subwoofer pin fixup for Ideapad laptops
 mario
     Chromebook mario model fixup
+hp-rp5800
+    Headphone pin fixup for HP RP5800
 asus-mode1
     ASUS
 asus-mode2
@@ -105,10 +111,40 @@ asus-mode7
     ASUS
 asus-mode8
     ASUS
+zotac-z68
+    Front HP fixup for Zotac Z68
 inv-dmic
     Inverted internal mic workaround
+alc662-headset-multi
+    Dell headset jack, which can also be used as mic-in (ALC662)
 dell-headset-multi
     Headset jack, which can also be used as mic-in
+alc662-headset
+    Headset mode support on ALC662
+alc668-headset
+    Headset mode support on ALC668
+bass16
+    Bass speaker fixup on pin 0x16
+bass1a
+    Bass speaker fixup on pin 0x1a
+automute
+    Auto-mute fixups for ALC668
+dell-xps13
+    Dell XPS13 fixups
+asus-nx50
+    ASUS Nx50 fixups
+asus-nx51
+    ASUS Nx51 fixups
+alc891-headset
+    Headset mode support on ALC891
+alc891-headset-multi
+    Dell headset jack, which can also be used as mic-in (ALC891)
+acer-veriton
+    Acer Veriton speaker pin fixup
+asrock-mobo
+    Fix invalid 0x15 / 0x16 pins
+usi-headset
+    Headset support on USI machines
 dual-codecs
     Lenovo laptops with dual codecs
 
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c93e09f9c109..c7c9b47c2d5d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -8012,7 +8012,10 @@ static const struct snd_pci_quirk alc662_fixup_tbl[] = {
 };
 
 static const struct hda_model_fixup alc662_fixup_models[] = {
+	{.id = ALC662_FIXUP_ASPIRE, .name = "aspire"},
+	{.id = ALC662_FIXUP_IDEAPAD, .name = "ideapad"},
 	{.id = ALC272_FIXUP_MARIO, .name = "mario"},
+	{.id = ALC662_FIXUP_HP_RP5800, .name = "hp-rp5800"},
 	{.id = ALC662_FIXUP_ASUS_MODE1, .name = "asus-mode1"},
 	{.id = ALC662_FIXUP_ASUS_MODE2, .name = "asus-mode2"},
 	{.id = ALC662_FIXUP_ASUS_MODE3, .name = "asus-mode3"},
@@ -8021,8 +8024,23 @@ static const struct hda_model_fixup alc662_fixup_models[] = {
 	{.id = ALC662_FIXUP_ASUS_MODE6, .name = "asus-mode6"},
 	{.id = ALC662_FIXUP_ASUS_MODE7, .name = "asus-mode7"},
 	{.id = ALC662_FIXUP_ASUS_MODE8, .name = "asus-mode8"},
+	{.id = ALC662_FIXUP_ZOTAC_Z68, .name = "zotac-z68"},
 	{.id = ALC662_FIXUP_INV_DMIC, .name = "inv-dmic"},
+	{.id = ALC662_FIXUP_DELL_MIC_NO_PRESENCE, .name = "alc662-headset-multi"},
 	{.id = ALC668_FIXUP_DELL_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
+	{.id = ALC662_FIXUP_HEADSET_MODE, .name = "alc662-headset"},
+	{.id = ALC668_FIXUP_HEADSET_MODE, .name = "alc668-headset"},
+	{.id = ALC662_FIXUP_BASS_16, .name = "bass16"},
+	{.id = ALC662_FIXUP_BASS_1A, .name = "bass1a"},
+	{.id = ALC668_FIXUP_AUTO_MUTE, .name = "automute"},
+	{.id = ALC668_FIXUP_DELL_XPS13, .name = "dell-xps13"},
+	{.id = ALC662_FIXUP_ASUS_Nx50, .name = "asus-nx50"},
+	{.id = ALC668_FIXUP_ASUS_Nx51, .name = "asus-nx51"},
+	{.id = ALC891_FIXUP_HEADSET_MODE, .name = "alc891-headset"},
+	{.id = ALC891_FIXUP_DELL_MIC_NO_PRESENCE, .name = "alc891-headset-multi"},
+	{.id = ALC662_FIXUP_ACER_VERITON, .name = "acer-veriton"},
+	{.id = ALC892_FIXUP_ASROCK_MOBO, .name = "asrock-mobo"},
+	{.id = ALC662_FIXUP_USI_HEADSET_MODE, .name = "usi-headset"},
 	{.id = ALC662_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
 	{}
 };
-- 
cgit v1.2.3


From a26d96c7802e09473d5997791829774ba4f7e867 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 26 Jun 2018 15:09:25 +0200
Subject: ALSA: hda/realtek - Comprehensive model list for ALC259 & co

Like the previous commit for ALC662, let's give more comprehensive
list of model entries for ALC269 & co as well.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/hd-audio/models.rst | 156 ++++++++++++++++++++++++++++++++
 sound/pci/hda/patch_realtek.c           |  82 +++++++++++++++++
 2 files changed, 238 insertions(+)

diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index f2f8402ff899..a403a7f34a78 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -70,6 +70,10 @@ dell-headset-multi
     Headset jack, which can also be used as mic-in
 dell-headset-dock
     Headset jack (without mic-in), and also dock I/O
+dell-headset3
+    Headset jack (without mic-in), and also dock I/O, variant 3
+dell-headset4
+    Headset jack (without mic-in), and also dock I/O, variant 4
 alc283-dac-wcaps
     Fixups for Chromebook with ALC283
 alc283-sense-combo
@@ -80,10 +84,162 @@ tpt440
     Lenovo Thinkpad T440s setup
 tpt460
     Lenovo Thinkpad T460/560 setup
+tpt470-dock
+    Lenovo Thinkpad T470 dock setup
 dual-codecs
     Lenovo laptops with dual codecs
 alc700-ref
     Intel reference board with ALC700 codec
+vaio
+    Pin fixups for Sony VAIO laptops
+dell-m101z
+    COEF setup for Dell M101z
+asus-g73jw
+    Subwoofer pin fixup for ASUS G73JW
+lenovo-eapd
+    Inversed EAPD setup for Lenovo laptops
+sony-hweq
+    H/W EQ COEF setup for Sony laptops
+pcm44k
+    Fixed PCM 44kHz constraints (for buggy devices)
+lifebook
+    Dock pin fixups for Fujitsu Lifebook
+lifebook-extmic
+    Headset mic fixup for Fujitsu Lifebook
+lifebook-hp-pin
+    Headphone pin fixup for Fujitsu Lifebook
+lifebook-u7x7
+    Lifebook U7x7 fixups
+alc269vb-amic
+    ALC269VB analog mic pin fixups
+alc269vb-dmic
+    ALC269VB digital mic pin fixups
+hp-mute-led-mic1
+    Mute LED via Mic1 pin on HP
+hp-mute-led-mic2
+    Mute LED via Mic2 pin on HP
+hp-mute-led-mic3
+    Mute LED via Mic3 pin on HP
+hp-gpio-mic1
+    GPIO + Mic1 pin LED on HP
+hp-line1-mic1
+    Mute LED via Line1 + Mic1 pins on HP
+noshutup
+    Skip shutup callback
+sony-nomic
+    Headset mic fixup for Sony laptops
+aspire-headset-mic
+    Headset pin fixup for Acer Aspire
+asus-x101
+    ASUS X101 fixups
+acer-ao7xx
+    Acer AO7xx fixups
+acer-aspire-e1
+    Acer Aspire E1 fixups
+acer-ac700
+    Acer AC700 fixups
+limit-mic-boost
+    Limit internal mic boost on Lenovo machines
+asus-zenbook
+    ASUS Zenbook fixups
+asus-zenbook-ux31a
+    ASUS Zenbook UX31A fixups
+ordissimo
+    Ordissimo EVE2 (or Malata PC-B1303) fixups
+asus-tx300
+    ASUS TX300 fixups
+alc283-int-mic
+    ALC283 COEF setup for Lenovo machines
+mono-speakers
+    Subwoofer and headset fixupes for Dell Inspiron
+alc290-subwoofer
+    Subwoofer fixups for Dell Vostro
+thinkpad
+    Binding with thinkpad_acpi driver for Lenovo machines
+dmic-thinkpad
+    thinkpad_acpi binding + digital mic support
+alc255-acer
+    ALC255 fixups on Acer machines
+alc255-asus
+    ALC255 fixups on ASUS machines
+alc255-dell1
+    ALC255 fixups on Dell machines
+alc255-dell2
+    ALC255 fixups on Dell machines, variant 2
+alc293-dell1
+    ALC293 fixups on Dell machines
+alc283-headset
+    Headset pin fixups on ALC283
+aspire-v5
+    Acer Aspire V5 fixups
+hp-gpio4
+    GPIO and Mic1 pin mute LED fixups for HP
+hp-gpio-led
+    GPIO mute LEDs on HP
+hp-gpio2-hotkey
+    GPIO mute LED with hot key handling on HP
+hp-dock-pins
+    GPIO mute LEDs and dock support on HP
+hp-dock-gpio-mic
+    GPIO, Mic mute LED and dock support on HP
+hp-9480m
+    HP 9480m fixups
+alc288-dell1
+    ALC288 fixups on Dell machines
+alc288-dell-xps13
+    ALC288 fixups on Dell XPS13
+dell-e7x
+    Dell E7x fixups
+alc293-dell
+    ALC293 fixups on Dell machines
+alc298-dell1
+    ALC298 fixups on Dell machines
+alc298-dell-aio
+    ALC298 fixups on Dell AIO machines
+alc275-dell-xps
+    ALC275 fixups on Dell XPS models
+alc256-dell-xps13
+    ALC256 fixups on Dell XPS13
+lenovo-spk-noise
+    Workaround for speaker noise on Lenovo machines
+lenovo-hotkey
+    Hot-key support via Mic2 pin on Lenovo machines
+dell-spk-noise
+    Workaround for speaker noise on Dell machines
+alc255-dell1
+    ALC255 fixups on Dell machines
+alc295-disable-dac3
+    Disable DAC3 routing on ALC295
+alc280-hp-headset
+    HP Elitebook fixups
+alc221-hp-mic
+    Front mic pin fixup on HP machines
+alc298-spk-volume
+    Speaker pin routing workaround on ALC298
+dell-inspiron-7559
+    Dell Inspiron 7559 fixups
+ativ-book
+    Samsung Ativ book 8 fixups
+alc221-hp-mic
+    ALC221 headset fixups on HP machines
+alc256-asus-mic
+    ALC256 fixups on ASUS machines
+alc256-asus-aio
+    ALC256 fixups on ASUS AIO machines
+alc233-eapd
+    ALC233 fixups on ASUS machines
+alc294-lenovo-mic
+    ALC294 Mic pin fixup for Lenovo AIO machines
+alc225-wyse
+    Dell Wyse fixups
+alc274-dell-aio
+    ALC274 fixups on Dell AIO machines
+alc255-dummy-lineout
+    Dell Precision 3930 fixups
+alc255-dell-headset"},
+    Dell Precision 3630 fixups
+alc295-hp-x360
+    HP Spectre X360 fixups
 
 ALC66x/67x/892
 ==============
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c7c9b47c2d5d..a0828befe62a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6620,13 +6620,95 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
 	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic1-led"},
 	{.id = ALC269_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "dell-headset-multi"},
 	{.id = ALC269_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "dell-headset-dock"},
+	{.id = ALC269_FIXUP_DELL3_MIC_NO_PRESENCE, .name = "dell-headset3"},
+	{.id = ALC269_FIXUP_DELL4_MIC_NO_PRESENCE, .name = "dell-headset4"},
 	{.id = ALC283_FIXUP_CHROME_BOOK, .name = "alc283-dac-wcaps"},
 	{.id = ALC283_FIXUP_SENSE_COMBO_JACK, .name = "alc283-sense-combo"},
 	{.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"},
 	{.id = ALC292_FIXUP_TPT440, .name = "tpt440"},
 	{.id = ALC292_FIXUP_TPT460, .name = "tpt460"},
+	{.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"},
 	{.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"},
 	{.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"},
+	{.id = ALC269_FIXUP_SONY_VAIO, .name = "vaio"},
+	{.id = ALC269_FIXUP_DELL_M101Z, .name = "dell-m101z"},
+	{.id = ALC269_FIXUP_ASUS_G73JW, .name = "asus-g73jw"},
+	{.id = ALC269_FIXUP_LENOVO_EAPD, .name = "lenovo-eapd"},
+	{.id = ALC275_FIXUP_SONY_HWEQ, .name = "sony-hweq"},
+	{.id = ALC269_FIXUP_PCM_44K, .name = "pcm44k"},
+	{.id = ALC269_FIXUP_LIFEBOOK, .name = "lifebook"},
+	{.id = ALC269_FIXUP_LIFEBOOK_EXTMIC, .name = "lifebook-extmic"},
+	{.id = ALC269_FIXUP_LIFEBOOK_HP_PIN, .name = "lifebook-hp-pin"},
+	{.id = ALC255_FIXUP_LIFEBOOK_U7x7_HEADSET_MIC, .name = "lifebook-u7x7"},
+	{.id = ALC269VB_FIXUP_AMIC, .name = "alc269vb-amic"},
+	{.id = ALC269VB_FIXUP_DMIC, .name = "alc269vb-dmic"},
+	{.id = ALC269_FIXUP_HP_MUTE_LED_MIC1, .name = "hp-mute-led-mic1"},
+	{.id = ALC269_FIXUP_HP_MUTE_LED_MIC2, .name = "hp-mute-led-mic2"},
+	{.id = ALC269_FIXUP_HP_MUTE_LED_MIC3, .name = "hp-mute-led-mic3"},
+	{.id = ALC269_FIXUP_HP_GPIO_MIC1_LED, .name = "hp-gpio-mic1"},
+	{.id = ALC269_FIXUP_HP_LINE1_MIC1_LED, .name = "hp-line1-mic1"},
+	{.id = ALC269_FIXUP_NO_SHUTUP, .name = "noshutup"},
+	{.id = ALC286_FIXUP_SONY_MIC_NO_PRESENCE, .name = "sony-nomic"},
+	{.id = ALC269_FIXUP_ASPIRE_HEADSET_MIC, .name = "aspire-headset-mic"},
+	{.id = ALC269_FIXUP_ASUS_X101, .name = "asus-x101"},
+	{.id = ALC271_FIXUP_HP_GATE_MIC_JACK, .name = "acer-ao7xx"},
+	{.id = ALC271_FIXUP_HP_GATE_MIC_JACK_E1_572, .name = "acer-aspire-e1"},
+	{.id = ALC269_FIXUP_ACER_AC700, .name = "acer-ac700"},
+	{.id = ALC269_FIXUP_LIMIT_INT_MIC_BOOST, .name = "limit-mic-boost"},
+	{.id = ALC269VB_FIXUP_ASUS_ZENBOOK, .name = "asus-zenbook"},
+	{.id = ALC269VB_FIXUP_ASUS_ZENBOOK_UX31A, .name = "asus-zenbook-ux31a"},
+	{.id = ALC269VB_FIXUP_ORDISSIMO_EVE2, .name = "ordissimo"},
+	{.id = ALC282_FIXUP_ASUS_TX300, .name = "asus-tx300"},
+	{.id = ALC283_FIXUP_INT_MIC, .name = "alc283-int-mic"},
+	{.id = ALC290_FIXUP_MONO_SPEAKERS_HSJACK, .name = "mono-speakers"},
+	{.id = ALC290_FIXUP_SUBWOOFER_HSJACK, .name = "alc290-subwoofer"},
+	{.id = ALC269_FIXUP_THINKPAD_ACPI, .name = "thinkpad"},
+	{.id = ALC269_FIXUP_DMIC_THINKPAD_ACPI, .name = "dmic-thinkpad"},
+	{.id = ALC255_FIXUP_ACER_MIC_NO_PRESENCE, .name = "alc255-acer"},
+	{.id = ALC255_FIXUP_ASUS_MIC_NO_PRESENCE, .name = "alc255-asus"},
+	{.id = ALC255_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc255-dell1"},
+	{.id = ALC255_FIXUP_DELL2_MIC_NO_PRESENCE, .name = "alc255-dell2"},
+	{.id = ALC293_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc293-dell1"},
+	{.id = ALC283_FIXUP_HEADSET_MIC, .name = "alc283-headset"},
+	{.id = ALC255_FIXUP_DELL_WMI_MIC_MUTE_LED, .name = "alc255-dell-mute"},
+	{.id = ALC282_FIXUP_ASPIRE_V5_PINS, .name = "aspire-v5"},
+	{.id = ALC280_FIXUP_HP_GPIO4, .name = "hp-gpio4"},
+	{.id = ALC286_FIXUP_HP_GPIO_LED, .name = "hp-gpio-led"},
+	{.id = ALC280_FIXUP_HP_GPIO2_MIC_HOTKEY, .name = "hp-gpio2-hotkey"},
+	{.id = ALC280_FIXUP_HP_DOCK_PINS, .name = "hp-dock-pins"},
+	{.id = ALC269_FIXUP_HP_DOCK_GPIO_MIC1_LED, .name = "hp-dock-gpio-mic"},
+	{.id = ALC280_FIXUP_HP_9480M, .name = "hp-9480m"},
+	{.id = ALC288_FIXUP_DELL_HEADSET_MODE, .name = "alc288-dell-headset"},
+	{.id = ALC288_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc288-dell1"},
+	{.id = ALC288_FIXUP_DELL_XPS_13, .name = "alc288-dell-xps13"},
+	{.id = ALC292_FIXUP_DELL_E7X, .name = "dell-e7x"},
+	{.id = ALC293_FIXUP_DISABLE_AAMIX_MULTIJACK, .name = "alc293-dell"},
+	{.id = ALC298_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc298-dell1"},
+	{.id = ALC298_FIXUP_DELL_AIO_MIC_NO_PRESENCE, .name = "alc298-dell-aio"},
+	{.id = ALC275_FIXUP_DELL_XPS, .name = "alc275-dell-xps"},
+	{.id = ALC256_FIXUP_DELL_XPS_13_HEADPHONE_NOISE, .name = "alc256-dell-xps13"},
+	{.id = ALC293_FIXUP_LENOVO_SPK_NOISE, .name = "lenovo-spk-noise"},
+	{.id = ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY, .name = "lenovo-hotkey"},
+	{.id = ALC255_FIXUP_DELL_SPK_NOISE, .name = "dell-spk-noise"},
+	{.id = ALC225_FIXUP_DELL1_MIC_NO_PRESENCE, .name = "alc255-dell1"},
+	{.id = ALC295_FIXUP_DISABLE_DAC3, .name = "alc295-disable-dac3"},
+	{.id = ALC280_FIXUP_HP_HEADSET_MIC, .name = "alc280-hp-headset"},
+	{.id = ALC221_FIXUP_HP_FRONT_MIC, .name = "alc221-hp-mic"},
+	{.id = ALC298_FIXUP_SPK_VOLUME, .name = "alc298-spk-volume"},
+	{.id = ALC256_FIXUP_DELL_INSPIRON_7559_SUBWOOFER, .name = "dell-inspiron-7559"},
+	{.id = ALC269_FIXUP_ATIV_BOOK_8, .name = "ativ-book"},
+	{.id = ALC221_FIXUP_HP_MIC_NO_PRESENCE, .name = "alc221-hp-mic"},
+	{.id = ALC256_FIXUP_ASUS_HEADSET_MODE, .name = "alc256-asus-headset"},
+	{.id = ALC256_FIXUP_ASUS_MIC, .name = "alc256-asus-mic"},
+	{.id = ALC256_FIXUP_ASUS_AIO_GPIO2, .name = "alc256-asus-aio"},
+	{.id = ALC233_FIXUP_ASUS_MIC_NO_PRESENCE, .name = "alc233-asus"},
+	{.id = ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE, .name = "alc233-eapd"},
+	{.id = ALC294_FIXUP_LENOVO_MIC_LOCATION, .name = "alc294-lenovo-mic"},
+	{.id = ALC225_FIXUP_DELL_WYSE_MIC_NO_PRESENCE, .name = "alc225-wyse"},
+	{.id = ALC274_FIXUP_DELL_AIO_LINEOUT_VERB, .name = "alc274-dell-aio"},
+	{.id = ALC255_FIXUP_DUMMY_LINEOUT_VERB, .name = "alc255-dummy-lineout"},
+	{.id = ALC255_FIXUP_DELL_HEADSET_MIC, .name = "alc255-dell-headset"},
+	{.id = ALC295_FIXUP_HP_X360, .name = "alc295-hp-x360"},
 	{}
 };
 #define ALC225_STANDARD_PINS \
-- 
cgit v1.2.3


From 03bf11c934c3ced43aa9be3cfb93962ab15d737b Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 26 Jun 2018 16:56:41 +0200
Subject: ALSA: hda/realtek - Comprehensive model list for ALC268

Add the missing entry for ALC268 model strings.
Only "spdif" was missing, and that's it.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/hd-audio/models.rst | 2 ++
 sound/pci/hda/patch_realtek.c           | 1 +
 2 files changed, 3 insertions(+)

diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index a403a7f34a78..323c25c53eaf 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -41,6 +41,8 @@ inv-dmic
     Inverted internal mic workaround
 hp-eapd
     Disable HP EAPD on NID 0x15
+spdif
+    Enable SPDIF output on NID 0x1e
 
 ALC22x/23x/25x/269/27x/28x/29x (and vendor-specific ALC3xxx models)
 ===================================================================
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index a0828befe62a..74540e0fa19d 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2688,6 +2688,7 @@ static const struct hda_fixup alc268_fixups[] = {
 static const struct hda_model_fixup alc268_fixup_models[] = {
 	{.id = ALC268_FIXUP_INV_DMIC, .name = "inv-dmic"},
 	{.id = ALC268_FIXUP_HP_EAPD, .name = "hp-eapd"},
+	{.id = ALC268_FIXUP_SPDIF, .name = "spdif"},
 	{}
 };
 
-- 
cgit v1.2.3


From e43c44d62dbb4d8e2f217198142c97fce1a25ac1 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 26 Jun 2018 17:02:08 +0200
Subject: ALSA: hda/realtek - Comprehensive model list for ALC262

Added a few missing entries for ALC262 model strings.
All about specific hardwares.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/hd-audio/models.rst | 16 ++++++++++++++++
 sound/pci/hda/patch_realtek.c           |  8 ++++++++
 2 files changed, 24 insertions(+)

diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index 323c25c53eaf..560235519555 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -34,6 +34,22 @@ ALC262
 ======
 inv-dmic
     Inverted internal mic workaround
+fsc-h270
+    Fixups for Fujitsu-Siemens Celsius H270
+fsc-s7110
+    Fixups for Fujitsu-Siemens Lifebook S7110
+hp-z200
+    Fixups for HP Z200
+tyan
+    Fixups for Tyan Thunder n6650W
+lenovo-3000
+    Fixups for Lenovo 3000
+benq
+    Fixups for Benq ED8
+benq-t31
+    Fixups for Benq T31
+bayleybay
+    Fixups for Intel BayleyBay
 
 ALC267/268
 ==========
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 74540e0fa19d..fc21e2851b01 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2557,6 +2557,14 @@ static const struct snd_pci_quirk alc262_fixup_tbl[] = {
 
 static const struct hda_model_fixup alc262_fixup_models[] = {
 	{.id = ALC262_FIXUP_INV_DMIC, .name = "inv-dmic"},
+	{.id = ALC262_FIXUP_FSC_H270, .name = "fsc-h270"},
+	{.id = ALC262_FIXUP_FSC_S7110, .name = "fsc-s7110"},
+	{.id = ALC262_FIXUP_HP_Z200, .name = "hp-z200"},
+	{.id = ALC262_FIXUP_TYAN, .name = "tyan"},
+	{.id = ALC262_FIXUP_LENOVO_3000, .name = "lenovo-3000"},
+	{.id = ALC262_FIXUP_BENQ, .name = "benq"},
+	{.id = ALC262_FIXUP_BENQ_T31, .name = "benq-t31"},
+	{.id = ALC262_FIXUP_INTEL_BAYLEYBAY, .name = "bayleybay"},
 	{}
 };
 
-- 
cgit v1.2.3


From 772c2917ff4e3b15c38f74e77062360e5ffd1308 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 26 Jun 2018 17:17:53 +0200
Subject: ALSA: hda/realtek - Comprehensive model list for ALC882 & co

More comprehensive list of model strings for ALC882 & co.

Also corrected the subsection in models.rst, too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 Documentation/sound/hd-audio/models.rst | 54 +++++++++++++++++++++++++++++++--
 sound/pci/hda/patch_realtek.c           | 25 +++++++++++++++
 2 files changed, 77 insertions(+), 2 deletions(-)

diff --git a/Documentation/sound/hd-audio/models.rst b/Documentation/sound/hd-audio/models.rst
index 560235519555..e06238131f77 100644
--- a/Documentation/sound/hd-audio/models.rst
+++ b/Documentation/sound/hd-audio/models.rst
@@ -326,20 +326,70 @@ ALC680
 ======
 N/A
 
-ALC88x/898/1150
-======================
+ALC88x/898/1150/1220
+====================
+abit-aw9d
+    Pin fixups for Abit AW9D-MAX
+lenovo-y530
+    Pin fixups for Lenovo Y530
+acer-aspire-7736
+    Fixup for Acer Aspire 7736
+asus-w90v
+    Pin fixup for ASUS W90V
+cd
+    Enable audio CD pin NID 0x1c
+no-front-hp
+    Disable front HP pin NID 0x1b
+vaio-tt
+    Pin fixup for VAIO TT
+eee1601
+    COEF setups for ASUS Eee 1601
+alc882-eapd
+    Change EAPD COEF mode on ALC882
+alc883-eapd
+    Change EAPD COEF mode on ALC883
+gpio1
+    Enable GPIO1
+gpio2
+    Enable GPIO2
+gpio3
+    Enable GPIO3
+alc889-coef
+    Setup ALC889 COEF
+asus-w2jc
+    Fixups for ASUS W2JC
 acer-aspire-4930g
     Acer Aspire 4930G/5930G/6530G/6930G/7730G
 acer-aspire-8930g
     Acer Aspire 8330G/6935G
 acer-aspire
     Acer Aspire others
+macpro-gpio
+    GPIO setup for Mac Pro
+dac-route
+    Workaround for DAC routing on Acer Aspire
+mbp-vref
+    Vref setup for Macbook Pro
+imac91-vref
+    Vref setup for iMac 9,1
+mba11-vref
+    Vref setup for MacBook Air 1,1
+mba21-vref
+    Vref setup for MacBook Air 2,1
+mp11-vref
+    Vref setup for Mac Pro 1,1
+mp41-vref
+    Vref setup for Mac Pro 4,1
 inv-dmic
     Inverted internal mic workaround
 no-primary-hp
     VAIO Z/VGC-LN51JGB workaround (for fixed speaker DAC)
+asus-bass
+    Bass speaker setup for ASUS ET2700
 dual-codecs
     ALC1220 dual codecs for Gaming mobos
+clevo-p950
+    Fixups for Clevo P950
 
 ALC861/660
 ==========
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index fc21e2851b01..003e2c90e792 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -2374,12 +2374,37 @@ static const struct snd_pci_quirk alc882_fixup_tbl[] = {
 };
 
 static const struct hda_model_fixup alc882_fixup_models[] = {
+	{.id = ALC882_FIXUP_ABIT_AW9D_MAX, .name = "abit-aw9d"},
+	{.id = ALC882_FIXUP_LENOVO_Y530, .name = "lenovo-y530"},
+	{.id = ALC882_FIXUP_ACER_ASPIRE_7736, .name = "acer-aspire-7736"},
+	{.id = ALC882_FIXUP_ASUS_W90V, .name = "asus-w90v"},
+	{.id = ALC889_FIXUP_CD, .name = "cd"},
+	{.id = ALC889_FIXUP_FRONT_HP_NO_PRESENCE, .name = "no-front-hp"},
+	{.id = ALC889_FIXUP_VAIO_TT, .name = "vaio-tt"},
+	{.id = ALC888_FIXUP_EEE1601, .name = "eee1601"},
+	{.id = ALC882_FIXUP_EAPD, .name = "alc882-eapd"},
+	{.id = ALC883_FIXUP_EAPD, .name = "alc883-eapd"},
+	{.id = ALC882_FIXUP_GPIO1, .name = "gpio1"},
+	{.id = ALC882_FIXUP_GPIO2, .name = "gpio2"},
+	{.id = ALC882_FIXUP_GPIO3, .name = "gpio3"},
+	{.id = ALC889_FIXUP_COEF, .name = "alc889-coef"},
+	{.id = ALC882_FIXUP_ASUS_W2JC, .name = "asus-w2jc"},
 	{.id = ALC882_FIXUP_ACER_ASPIRE_4930G, .name = "acer-aspire-4930g"},
 	{.id = ALC882_FIXUP_ACER_ASPIRE_8930G, .name = "acer-aspire-8930g"},
 	{.id = ALC883_FIXUP_ACER_EAPD, .name = "acer-aspire"},
+	{.id = ALC885_FIXUP_MACPRO_GPIO, .name = "macpro-gpio"},
+	{.id = ALC889_FIXUP_DAC_ROUTE, .name = "dac-route"},
+	{.id = ALC889_FIXUP_MBP_VREF, .name = "mbp-vref"},
+	{.id = ALC889_FIXUP_IMAC91_VREF, .name = "imac91-vref"},
+	{.id = ALC889_FIXUP_MBA11_VREF, .name = "mba11-vref"},
+	{.id = ALC889_FIXUP_MBA21_VREF, .name = "mba21-vref"},
+	{.id = ALC889_FIXUP_MP11_VREF, .name = "mp11-vref"},
+	{.id = ALC889_FIXUP_MP41_VREF, .name = "mp41-vref"},
 	{.id = ALC882_FIXUP_INV_DMIC, .name = "inv-dmic"},
 	{.id = ALC882_FIXUP_NO_PRIMARY_HP, .name = "no-primary-hp"},
+	{.id = ALC887_FIXUP_ASUS_BASS, .name = "asus-bass"},
 	{.id = ALC1220_FIXUP_GB_DUAL_CODECS, .name = "dual-codecs"},
+	{.id = ALC1220_FIXUP_CLEVO_P950, .name = "clevo-p950"},
 	{}
 };
 
-- 
cgit v1.2.3


From 0297e962907d98ece34188cb267d3313812b6e42 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 22 Jun 2018 16:40:18 -0500
Subject: scsi: tcmu: delete unused __wait

When this code changed, this was never cleaned up.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Tested-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index e4a76f9771ce..898a5619f2d6 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1564,7 +1564,6 @@ static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
 {
 	struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd;
 	int ret;
-	DEFINE_WAIT(__wait);
 
 	if (!tcmu_kern_cmd_reply_supported)
 		return 0;
-- 
cgit v1.2.3


From 3228691ffec134353cb5bf6fb4342283e0243412 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 22 Jun 2018 16:40:19 -0500
Subject: scsi: tcmu: track nl commands

The next patch is going to fix the hung nl command issue so this adds a
list of outstanding nl commands that we can later abort when the daemon is
restarted.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 68 ++++++++++++++++++++++-----------------
 1 file changed, 39 insertions(+), 29 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 898a5619f2d6..73a57681e312 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -103,9 +103,16 @@ struct tcmu_hba {
 
 #define TCMU_CONFIG_LEN 256
 
+static DEFINE_MUTEX(tcmu_nl_cmd_mutex);
+static LIST_HEAD(tcmu_nl_cmd_list);
+
+struct tcmu_dev;
+
 struct tcmu_nl_cmd {
 	/* wake up thread waiting for reply */
 	struct completion complete;
+	struct list_head nl_list;
+	struct tcmu_dev *udev;
 	int cmd;
 	int status;
 };
@@ -157,7 +164,6 @@ struct tcmu_dev {
 
 	struct list_head timedout_entry;
 
-	spinlock_t nl_cmd_lock;
 	struct tcmu_nl_cmd curr_nl_cmd;
 	/* wake up threads waiting on curr_nl_cmd */
 	wait_queue_head_t nl_cmd_wq;
@@ -270,11 +276,9 @@ static struct nla_policy tcmu_attr_policy[TCMU_ATTR_MAX+1] = {
 
 static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
 {
-	struct se_device *dev;
-	struct tcmu_dev *udev;
+	struct tcmu_dev *udev = NULL;
 	struct tcmu_nl_cmd *nl_cmd;
 	int dev_id, rc, ret = 0;
-	bool is_removed = (completed_cmd == TCMU_CMD_REMOVED_DEVICE);
 
 	if (!info->attrs[TCMU_ATTR_CMD_STATUS] ||
 	    !info->attrs[TCMU_ATTR_DEVICE_ID]) {
@@ -285,33 +289,36 @@ static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
 	dev_id = nla_get_u32(info->attrs[TCMU_ATTR_DEVICE_ID]);
 	rc = nla_get_s32(info->attrs[TCMU_ATTR_CMD_STATUS]);
 
-	dev = target_find_device(dev_id, !is_removed);
-	if (!dev) {
-		printk(KERN_ERR "tcmu nl cmd %u/%u completion could not find device with dev id %u.\n",
-		       completed_cmd, rc, dev_id);
-		return -ENODEV;
+	mutex_lock(&tcmu_nl_cmd_mutex);
+	list_for_each_entry(nl_cmd, &tcmu_nl_cmd_list, nl_list) {
+		if (nl_cmd->udev->se_dev.dev_index == dev_id) {
+			udev = nl_cmd->udev;
+			break;
+		}
 	}
-	udev = TCMU_DEV(dev);
 
-	spin_lock(&udev->nl_cmd_lock);
-	nl_cmd = &udev->curr_nl_cmd;
+	if (!udev) {
+		pr_err(KERN_ERR "tcmu nl cmd %u/%d completion could not find device with dev id %u.\n",
+		       completed_cmd, rc, dev_id);
+		ret = -ENODEV;
+		goto unlock;
+	}
+	list_del(&nl_cmd->nl_list);
 
-	pr_debug("genl cmd done got id %d curr %d done %d rc %d\n", dev_id,
-		 nl_cmd->cmd, completed_cmd, rc);
+	pr_debug("%s genl cmd done got id %d curr %d done %d rc %d\n",
+		 udev->name, dev_id, nl_cmd->cmd, completed_cmd, rc);
 
 	if (nl_cmd->cmd != completed_cmd) {
-		printk(KERN_ERR "Mismatched commands (Expecting reply for %d. Current %d).\n",
-		       completed_cmd, nl_cmd->cmd);
+		pr_err("Mismatched commands on %s (Expecting reply for %d. Current %d).\n",
+		       udev->name, completed_cmd, nl_cmd->cmd);
 		ret = -EINVAL;
-	} else {
-		nl_cmd->status = rc;
+		goto unlock;
 	}
 
-	spin_unlock(&udev->nl_cmd_lock);
-	if (!is_removed)
-		target_undepend_item(&dev->dev_group.cg_item);
-	if (!ret)
-		complete(&nl_cmd->complete);
+	nl_cmd->status = rc;
+	complete(&nl_cmd->complete);
+unlock:
+	mutex_unlock(&tcmu_nl_cmd_mutex);
 	return ret;
 }
 
@@ -1258,7 +1265,6 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	timer_setup(&udev->cmd_timer, tcmu_cmd_timedout, 0);
 
 	init_waitqueue_head(&udev->nl_cmd_wq);
-	spin_lock_init(&udev->nl_cmd_lock);
 
 	INIT_RADIX_TREE(&udev->data_blocks, GFP_KERNEL);
 
@@ -1544,10 +1550,10 @@ static void tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd)
 		return;
 
 relock:
-	spin_lock(&udev->nl_cmd_lock);
+	mutex_lock(&tcmu_nl_cmd_mutex);
 
 	if (nl_cmd->cmd != TCMU_CMD_UNSPEC) {
-		spin_unlock(&udev->nl_cmd_lock);
+		mutex_unlock(&tcmu_nl_cmd_mutex);
 		pr_debug("sleeping for open nl cmd\n");
 		wait_event(udev->nl_cmd_wq, (nl_cmd->cmd == TCMU_CMD_UNSPEC));
 		goto relock;
@@ -1555,9 +1561,13 @@ relock:
 
 	memset(nl_cmd, 0, sizeof(*nl_cmd));
 	nl_cmd->cmd = cmd;
+	nl_cmd->udev = udev;
 	init_completion(&nl_cmd->complete);
+	INIT_LIST_HEAD(&nl_cmd->nl_list);
+
+	list_add_tail(&nl_cmd->nl_list, &tcmu_nl_cmd_list);
 
-	spin_unlock(&udev->nl_cmd_lock);
+	mutex_unlock(&tcmu_nl_cmd_mutex);
 }
 
 static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
@@ -1574,11 +1584,11 @@ static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
 	pr_debug("sleeping for nl reply\n");
 	wait_for_completion(&nl_cmd->complete);
 
-	spin_lock(&udev->nl_cmd_lock);
+	mutex_lock(&tcmu_nl_cmd_mutex);
 	nl_cmd->cmd = TCMU_CMD_UNSPEC;
 	ret = nl_cmd->status;
 	nl_cmd->status = 0;
-	spin_unlock(&udev->nl_cmd_lock);
+	mutex_unlock(&tcmu_nl_cmd_mutex);
 
 	wake_up_all(&udev->nl_cmd_wq);
 
-- 
cgit v1.2.3


From 9de3a1ef032a5ad5d7b642d625b6bd362b1989d6 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 22 Jun 2018 16:40:20 -0500
Subject: scsi: tcmu: simplify nl interface

Just return EBUSY if a nl request comes in while processing one. The upper
layers do not support sending multiple create/remove requests at the same
time (you cannot have a create and remove at the same time or do multiple
creates or removes at the same time) and doing a reconfig while a
create/remove is still executing does not make sense.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Tested-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 73a57681e312..9835ea3c4dcc 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -165,8 +165,6 @@ struct tcmu_dev {
 	struct list_head timedout_entry;
 
 	struct tcmu_nl_cmd curr_nl_cmd;
-	/* wake up threads waiting on curr_nl_cmd */
-	wait_queue_head_t nl_cmd_wq;
 
 	char dev_config[TCMU_CONFIG_LEN];
 
@@ -1264,8 +1262,6 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	timer_setup(&udev->qfull_timer, tcmu_qfull_timedout, 0);
 	timer_setup(&udev->cmd_timer, tcmu_cmd_timedout, 0);
 
-	init_waitqueue_head(&udev->nl_cmd_wq);
-
 	INIT_RADIX_TREE(&udev->data_blocks, GFP_KERNEL);
 
 	return &udev->se_dev;
@@ -1539,24 +1535,23 @@ static int tcmu_release(struct uio_info *info, struct inode *inode)
 	return 0;
 }
 
-static void tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd)
+static int tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd)
 {
 	struct tcmu_nl_cmd *nl_cmd = &udev->curr_nl_cmd;
 
 	if (!tcmu_kern_cmd_reply_supported)
-		return;
+		return 0;
 
 	if (udev->nl_reply_supported <= 0)
-		return;
+		return 0;
 
-relock:
 	mutex_lock(&tcmu_nl_cmd_mutex);
 
 	if (nl_cmd->cmd != TCMU_CMD_UNSPEC) {
 		mutex_unlock(&tcmu_nl_cmd_mutex);
-		pr_debug("sleeping for open nl cmd\n");
-		wait_event(udev->nl_cmd_wq, (nl_cmd->cmd == TCMU_CMD_UNSPEC));
-		goto relock;
+		pr_warn("netlink cmd %d already executing on %s\n",
+			 nl_cmd->cmd, udev->name);
+		return -EBUSY;
 	}
 
 	memset(nl_cmd, 0, sizeof(*nl_cmd));
@@ -1568,6 +1563,7 @@ relock:
 	list_add_tail(&nl_cmd->nl_list, &tcmu_nl_cmd_list);
 
 	mutex_unlock(&tcmu_nl_cmd_mutex);
+	return 0;
 }
 
 static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
@@ -1590,8 +1586,6 @@ static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
 	nl_cmd->status = 0;
 	mutex_unlock(&tcmu_nl_cmd_mutex);
 
-	wake_up_all(&udev->nl_cmd_wq);
-
 	return ret;
 }
 
@@ -1642,7 +1636,11 @@ static int tcmu_netlink_event_send(struct tcmu_dev *udev,
 
 	genlmsg_end(skb, msg_header);
 
-	tcmu_init_genl_cmd_reply(udev, cmd);
+	ret = tcmu_init_genl_cmd_reply(udev, cmd);
+	if (ret) {
+		nlmsg_free(skb);
+		return ret;
+	}
 
 	ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0,
 				      TCMU_MCGRP_CONFIG, GFP_KERNEL);
-- 
cgit v1.2.3


From 06add777bd0aa764a2252e80c46ecc55ddc29dd1 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 22 Jun 2018 16:40:21 -0500
Subject: scsi: tcmu: misc nl code cleanup

Some misc cleanup of the nl rework patches.

1. Fix space instead of tabs use and extra newline

2. Drop initializing variables to 0 when not needed

3. Just pass the skb_buff and msg_header pointers to
   tcmu_netlink_event_send.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Tested-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 9835ea3c4dcc..2a2e9e4e7593 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1628,11 +1628,9 @@ free_skb:
 
 static int tcmu_netlink_event_send(struct tcmu_dev *udev,
 				   enum tcmu_genl_cmd cmd,
-				   struct sk_buff **buf, void **hdr)
+				   struct sk_buff *skb, void *msg_header)
 {
-	int ret = 0;
-	struct sk_buff *skb = *buf;
-	void *msg_header = *hdr;
+	int ret;
 
 	genlmsg_end(skb, msg_header);
 
@@ -1644,7 +1642,7 @@ static int tcmu_netlink_event_send(struct tcmu_dev *udev,
 
 	ret = genlmsg_multicast_allns(&tcmu_genl_family, skb, 0,
 				      TCMU_MCGRP_CONFIG, GFP_KERNEL);
-       /* We don't care if no one is listening */
+	/* We don't care if no one is listening */
 	if (ret == -ESRCH)
 		ret = 0;
 	if (!ret)
@@ -1662,9 +1660,8 @@ static int tcmu_send_dev_add_event(struct tcmu_dev *udev)
 				      &msg_header);
 	if (ret < 0)
 		return ret;
-	return tcmu_netlink_event_send(udev, TCMU_CMD_ADDED_DEVICE, &skb,
-				       &msg_header);
-
+	return tcmu_netlink_event_send(udev, TCMU_CMD_ADDED_DEVICE, skb,
+				       msg_header);
 }
 
 static int tcmu_send_dev_remove_event(struct tcmu_dev *udev)
@@ -1678,7 +1675,7 @@ static int tcmu_send_dev_remove_event(struct tcmu_dev *udev)
 	if (ret < 0)
 		return ret;
 	return tcmu_netlink_event_send(udev, TCMU_CMD_REMOVED_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 static int tcmu_update_uio_info(struct tcmu_dev *udev)
@@ -2197,7 +2194,7 @@ static int tcmu_send_dev_config_event(struct tcmu_dev *udev,
 		return ret;
 	}
 	return tcmu_netlink_event_send(udev, TCMU_CMD_RECONFIG_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 
@@ -2259,7 +2256,7 @@ static int tcmu_send_dev_size_event(struct tcmu_dev *udev, u64 size)
 		return ret;
 	}
 	return tcmu_netlink_event_send(udev, TCMU_CMD_RECONFIG_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page,
@@ -2341,7 +2338,7 @@ static int tcmu_send_emulate_write_cache(struct tcmu_dev *udev, u8 val)
 		return ret;
 	}
 	return tcmu_netlink_event_send(udev, TCMU_CMD_RECONFIG_DEVICE,
-				       &skb, &msg_header);
+				       skb, msg_header);
 }
 
 static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
-- 
cgit v1.2.3


From bdaeedc1bea9e833196b5c7eb0ffd74edf9c863e Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 22 Jun 2018 16:40:22 -0500
Subject: scsi: tcmu: add module wide block/reset_netlink support

This patch based on Xiubo's patches adds 2 tcmu attr to block and reset the
netlink interface. It's used during userspace daemon reinitialization after
the daemon has crashed while there is outstanding nl requests. The daemon
can block the nl interface, kill outstanding requests in the kernel and
then reopen the netlink socket and unblock it to allow new requests.

[mkp: typo]

Signed-off-by: Mike Christie <mchristi@redhat.com>
Tested-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 100 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 97 insertions(+), 3 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 2a2e9e4e7593..95559811d6cc 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -94,6 +94,7 @@
 #define TCMU_GLOBAL_MAX_BLOCKS_DEF (512 * 1024)
 
 static u8 tcmu_kern_cmd_reply_supported;
+static u8 tcmu_netlink_blocked;
 
 static struct device *tcmu_root_device;
 
@@ -255,6 +256,92 @@ MODULE_PARM_DESC(global_max_data_area_mb,
 		 "Max MBs allowed to be allocated to all the tcmu device's "
 		 "data areas.");
 
+static int tcmu_get_block_netlink(char *buffer,
+				  const struct kernel_param *kp)
+{
+	return sprintf(buffer, "%s\n", tcmu_netlink_blocked ?
+		       "blocked" : "unblocked");
+}
+
+static int tcmu_set_block_netlink(const char *str,
+				  const struct kernel_param *kp)
+{
+	int ret;
+	u8 val;
+
+	ret = kstrtou8(str, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (val > 1) {
+		pr_err("Invalid block netlink value %u\n", val);
+		return -EINVAL;
+	}
+
+	tcmu_netlink_blocked = val;
+	return 0;
+}
+
+static const struct kernel_param_ops tcmu_block_netlink_op = {
+	.set = tcmu_set_block_netlink,
+	.get = tcmu_get_block_netlink,
+};
+
+module_param_cb(block_netlink, &tcmu_block_netlink_op, NULL, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(block_netlink, "Block new netlink commands.");
+
+static int tcmu_fail_netlink_cmd(struct tcmu_nl_cmd *nl_cmd)
+{
+	struct tcmu_dev *udev = nl_cmd->udev;
+
+	if (!tcmu_netlink_blocked) {
+		pr_err("Could not reset device's netlink interface. Netlink is not blocked.\n");
+		return -EBUSY;
+	}
+
+	if (nl_cmd->cmd != TCMU_CMD_UNSPEC) {
+		pr_debug("Aborting nl cmd %d on %s\n", nl_cmd->cmd, udev->name);
+		nl_cmd->status = -EINTR;
+		list_del(&nl_cmd->nl_list);
+		complete(&nl_cmd->complete);
+	}
+	return 0;
+}
+
+static int tcmu_set_reset_netlink(const char *str,
+				  const struct kernel_param *kp)
+{
+	struct tcmu_nl_cmd *nl_cmd, *tmp_cmd;
+	int ret;
+	u8 val;
+
+	ret = kstrtou8(str, 0, &val);
+	if (ret < 0)
+		return ret;
+
+	if (val != 1) {
+		pr_err("Invalid reset netlink value %u\n", val);
+		return -EINVAL;
+	}
+
+	mutex_lock(&tcmu_nl_cmd_mutex);
+	list_for_each_entry_safe(nl_cmd, tmp_cmd, &tcmu_nl_cmd_list, nl_list) {
+		ret = tcmu_fail_netlink_cmd(nl_cmd);
+		if (ret)
+			break;
+	}
+	mutex_unlock(&tcmu_nl_cmd_mutex);
+
+	return ret;
+}
+
+static const struct kernel_param_ops tcmu_reset_netlink_op = {
+	.set = tcmu_set_reset_netlink,
+};
+
+module_param_cb(reset_netlink, &tcmu_reset_netlink_op, NULL, S_IWUSR);
+MODULE_PARM_DESC(reset_netlink, "Reset netlink commands.");
+
 /* multicast group */
 enum tcmu_multicast_groups {
 	TCMU_MCGRP_CONFIG,
@@ -303,8 +390,9 @@ static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
 	}
 	list_del(&nl_cmd->nl_list);
 
-	pr_debug("%s genl cmd done got id %d curr %d done %d rc %d\n",
-		 udev->name, dev_id, nl_cmd->cmd, completed_cmd, rc);
+	pr_debug("%s genl cmd done got id %d curr %d done %d rc %d stat %d\n",
+		 udev->name, dev_id, nl_cmd->cmd, completed_cmd, rc,
+		 nl_cmd->status);
 
 	if (nl_cmd->cmd != completed_cmd) {
 		pr_err("Mismatched commands on %s (Expecting reply for %d. Current %d).\n",
@@ -1547,6 +1635,13 @@ static int tcmu_init_genl_cmd_reply(struct tcmu_dev *udev, int cmd)
 
 	mutex_lock(&tcmu_nl_cmd_mutex);
 
+	if (tcmu_netlink_blocked) {
+		mutex_unlock(&tcmu_nl_cmd_mutex);
+		pr_warn("Failing nl cmd %d on %s. Interface is blocked.\n", cmd,
+			udev->name);
+		return -EAGAIN;
+	}
+
 	if (nl_cmd->cmd != TCMU_CMD_UNSPEC) {
 		mutex_unlock(&tcmu_nl_cmd_mutex);
 		pr_warn("netlink cmd %d already executing on %s\n",
@@ -1583,7 +1678,6 @@ static int tcmu_wait_genl_cmd_reply(struct tcmu_dev *udev)
 	mutex_lock(&tcmu_nl_cmd_mutex);
 	nl_cmd->cmd = TCMU_CMD_UNSPEC;
 	ret = nl_cmd->status;
-	nl_cmd->status = 0;
 	mutex_unlock(&tcmu_nl_cmd_mutex);
 
 	return ret;
-- 
cgit v1.2.3


From e2607484370ea1b3595a3c51485e66e0cbd17341 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Fri, 22 Jun 2018 16:40:23 -0500
Subject: scsi: target: remove target_find_device

target_find_device is no longer used, so remove it.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Tested-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_device.c  | 24 ------------------------
 include/target/target_core_backend.h |  2 --
 2 files changed, 26 deletions(-)

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index e27db4d45a9d..a9ad6ecb1812 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -879,30 +879,6 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb)
 }
 EXPORT_SYMBOL(target_to_linux_sector);
 
-/**
- * target_find_device - find a se_device by its dev_index
- * @id: dev_index
- * @do_depend: true if caller needs target_depend_item to be done
- *
- * If do_depend is true, the caller must do a target_undepend_item
- * when finished using the device.
- *
- * If do_depend is false, the caller must be called in a configfs
- * callback or during removal.
- */
-struct se_device *target_find_device(int id, bool do_depend)
-{
-	struct se_device *dev;
-
-	mutex_lock(&device_mutex);
-	dev = idr_find(&devices_idr, id);
-	if (dev && do_depend && target_depend_item(&dev->dev_group.cg_item))
-		dev = NULL;
-	mutex_unlock(&device_mutex);
-	return dev;
-}
-EXPORT_SYMBOL(target_find_device);
-
 struct devices_idr_iter {
 	int (*fn)(struct se_device *dev, void *data);
 	void *data;
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index 34a15d59ed88..c3ac47255218 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -106,8 +106,6 @@ bool	target_lun_is_rdonly(struct se_cmd *);
 sense_reason_t passthrough_parse_cdb(struct se_cmd *cmd,
 	sense_reason_t (*exec_cmd)(struct se_cmd *cmd));
 
-struct	se_device *target_find_device(int id, bool do_depend);
-
 bool target_sense_desc_format(struct se_device *dev);
 sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
-- 
cgit v1.2.3


From 7e63b5a4a68309383868b3582e92c217ad8a5347 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 23 Jun 2018 12:22:14 +0200
Subject: scsi: core: scsi_io_completion: comment on end_request return

scsi_end_request() is called multiple times from scsi_io_completion() which
branches on its bool returned value. Add comment before the static
definition of scsi_end_request() about the meaning of that return.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 41e9ac9fc138..8ac2fa6256da 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -662,6 +662,7 @@ static void scsi_release_bidi_buffers(struct scsi_cmnd *cmd)
 	cmd->request->next_rq->special = NULL;
 }
 
+/* Returns false when no more bytes to process, true if there are more */
 static bool scsi_end_request(struct request *req, blk_status_t error,
 		unsigned int bytes, unsigned int bidi_bytes)
 {
-- 
cgit v1.2.3


From 1f7cbb8e4b04fd33325a5cb279693861e549c03b Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 23 Jun 2018 12:22:15 +0200
Subject: scsi: core: scsi_io_completion: rename variables

Change and add some variable names, adjust some associated comments for
clarity. Correct some misleading comments.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 72 ++++++++++++++++++++++++++-----------------------
 1 file changed, 39 insertions(+), 33 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 8ac2fa6256da..1da1ff46c496 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -787,18 +787,19 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result)
  *		   be put back on the queue and retried using the same
  *		   command as before, possibly after a delay.
  *
- *		c) We can call scsi_end_request() with -EIO to fail
- *		   the remainder of the request.
+ *		c) We can call scsi_end_request() with blk_stat other than
+ *		   BLK_STS_OK, to fail the remainder of the request.
  */
 void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 {
 	int result = cmd->result;
 	struct request_queue *q = cmd->device->request_queue;
 	struct request *req = cmd->request;
-	blk_status_t error = BLK_STS_OK;
+	blk_status_t blk_stat = BLK_STS_OK;
 	struct scsi_sense_hdr sshdr;
 	bool sense_valid = false;
-	int sense_deferred = 0, level = 0;
+	bool sense_current = true;	/* false implies "deferred sense" */
+	int level = 0;
 	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
 	      ACTION_DELAYED_RETRY} action;
 	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
@@ -806,7 +807,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	if (result) {
 		sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
 		if (sense_valid)
-			sense_deferred = scsi_sense_is_deferred(&sshdr);
+			sense_current = !scsi_sense_is_deferred(&sshdr);
 	}
 
 	if (blk_rq_is_passthrough(req)) {
@@ -819,8 +820,9 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 					min(8 + cmd->sense_buffer[7],
 					    SCSI_SENSE_BUFFERSIZE);
 			}
-			if (!sense_deferred)
-				error = scsi_result_to_blk_status(cmd, result);
+			if (sense_current)
+				blk_stat = scsi_result_to_blk_status(cmd,
+								       result);
 		}
 		/*
 		 * scsi_result_to_blk_status may have reset the host_byte
@@ -839,13 +841,13 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				BUG();
 			return;
 		}
-	} else if (blk_rq_bytes(req) == 0 && result && !sense_deferred) {
+	} else if (blk_rq_bytes(req) == 0 && result && sense_current) {
 		/*
 		 * Flush commands do not transfers any data, and thus cannot use
 		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
-		 * This sets the error explicitly for the problem case.
+		 * This sets blk_stat explicitly for the problem case.
 		 */
-		error = scsi_result_to_blk_status(cmd, result);
+		blk_stat = scsi_result_to_blk_status(cmd, result);
 	}
 
 	/* no bidi support for !blk_rq_is_passthrough yet */
@@ -866,17 +868,22 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 * is what gets returned to the user
 	 */
 	if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
-		/* if ATA PASS-THROUGH INFORMATION AVAILABLE skip
+		bool do_print = true;
+
+		/*
+		 * If ATA PASS-THROUGH INFORMATION AVAILABLE skip
 		 * print since caller wants ATA registers. Only occurs on
 		 * SCSI ATA PASS_THROUGH commands when CK_COND=1
 		 */
 		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
-			;
-		else if (!(req->rq_flags & RQF_QUIET))
+			do_print = false;
+		else if (req->rq_flags & RQF_QUIET)
+			do_print = false;
+		if (do_print)
 			scsi_print_sense(cmd);
 		result = 0;
-		/* for passthrough error may be set */
-		error = BLK_STS_OK;
+		/* for passthrough, blk_stat may be set */
+		blk_stat = BLK_STS_OK;
 	}
 	/*
 	 * Another corner case: the SCSI status byte is non-zero but 'good'.
@@ -887,23 +894,22 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 */
 	if (status_byte(result) && scsi_status_is_good(result)) {
 		result = 0;
-		error = BLK_STS_OK;
+		blk_stat = BLK_STS_OK;
 	}
 
 	/*
-	 * special case: failed zero length commands always need to
-	 * drop down into the retry code. Otherwise, if we finished
-	 * all bytes in the request we are done now.
+	 * Next deal with any sectors which we were able to correctly
+	 * handle. Failed, zero length commands always need to drop down
+	 * to retry code. Fast path should return in this block.
 	 */
-	if (!(blk_rq_bytes(req) == 0 && error) &&
-	    !scsi_end_request(req, error, good_bytes, 0))
-		return;
+	if (blk_rq_bytes(req) > 0 || blk_stat == BLK_STS_OK) {
+		if (!scsi_end_request(req, blk_stat, good_bytes, 0))
+			return; /* no bytes remaining */
+	}
 
-	/*
-	 * Kill remainder if no retrys.
-	 */
-	if (error && scsi_noretry_cmd(cmd)) {
-		if (scsi_end_request(req, error, blk_rq_bytes(req), 0))
+	 /* Kill remainder if no retries. */
+	if (blk_stat && scsi_noretry_cmd(cmd)) {
+		if (scsi_end_request(req, blk_stat, blk_rq_bytes(req), 0))
 			BUG();
 		return;
 	}
@@ -915,7 +921,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	if (result == 0)
 		goto requeue;
 
-	error = scsi_result_to_blk_status(cmd, result);
+	blk_stat = scsi_result_to_blk_status(cmd, result);
 
 	if (host_byte(result) == DID_RESET) {
 		/* Third party bus reset or reset for error recovery
@@ -923,7 +929,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		 * happens.
 		 */
 		action = ACTION_RETRY;
-	} else if (sense_valid && !sense_deferred) {
+	} else if (sense_valid && sense_current) {
 		switch (sshdr.sense_key) {
 		case UNIT_ATTENTION:
 			if (cmd->device->removable) {
@@ -959,18 +965,18 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				action = ACTION_REPREP;
 			} else if (sshdr.asc == 0x10) /* DIX */ {
 				action = ACTION_FAIL;
-				error = BLK_STS_PROTECTION;
+				blk_stat = BLK_STS_PROTECTION;
 			/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
 			} else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
 				action = ACTION_FAIL;
-				error = BLK_STS_TARGET;
+				blk_stat = BLK_STS_TARGET;
 			} else
 				action = ACTION_FAIL;
 			break;
 		case ABORTED_COMMAND:
 			action = ACTION_FAIL;
 			if (sshdr.asc == 0x10) /* DIF */
-				error = BLK_STS_PROTECTION;
+				blk_stat = BLK_STS_PROTECTION;
 			break;
 		case NOT_READY:
 			/* If the device is in the process of becoming
@@ -1037,7 +1043,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				scsi_print_command(cmd);
 			}
 		}
-		if (!scsi_end_request(req, error, blk_rq_err_bytes(req), 0))
+		if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req), 0))
 			return;
 		/*FALLTHRU*/
 	case ACTION_REPREP:
-- 
cgit v1.2.3


From ab83108460a2a0d71c5bb22830036c4646e94e63 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 23 Jun 2018 12:22:16 +0200
Subject: scsi: core: add scsi_io_completion_nz_result function

Break out several intertwined paths when cmd->result is non zero and place
them in the scsi_io_completion_nz_result helper function. The logic is not
changed.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 132 +++++++++++++++++++++++++++---------------------
 1 file changed, 75 insertions(+), 57 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 1da1ff46c496..02892408962b 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -761,6 +761,79 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result)
 	}
 }
 
+/*
+ * Helper for scsi_io_completion() when cmd->result is non-zero. Returns a
+ * new result that may suppress further error checking. Also modifies
+ * *blk_statp in some cases.
+ */
+static int scsi_io_completion_nz_result(struct scsi_cmnd *cmd, int result,
+					blk_status_t *blk_statp)
+{
+	bool sense_valid;
+	bool sense_current = true;	/* false implies "deferred sense" */
+	struct request *req = cmd->request;
+	struct scsi_sense_hdr sshdr;
+
+	sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
+	if (sense_valid)
+		sense_current = !scsi_sense_is_deferred(&sshdr);
+
+	if (blk_rq_is_passthrough(req)) {
+		if (sense_valid) {
+			/*
+			 * SG_IO wants current and deferred errors
+			 */
+			scsi_req(req)->sense_len =
+				min(8 + cmd->sense_buffer[7],
+				    SCSI_SENSE_BUFFERSIZE);
+		}
+		if (sense_current)
+			*blk_statp = scsi_result_to_blk_status(cmd, result);
+	} else if (blk_rq_bytes(req) == 0 && sense_current) {
+		/*
+		 * Flush commands do not transfers any data, and thus cannot use
+		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
+		 * This sets *blk_statp explicitly for the problem case.
+		 */
+		*blk_statp = scsi_result_to_blk_status(cmd, result);
+	}
+	/*
+	 * Recovered errors need reporting, but they're always treated as
+	 * success, so fiddle the result code here.  For passthrough requests
+	 * we already took a copy of the original into sreq->result which
+	 * is what gets returned to the user
+	 */
+	if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
+		bool do_print = true;
+		/*
+		 * if ATA PASS-THROUGH INFORMATION AVAILABLE [0x0, 0x1d]
+		 * skip print since caller wants ATA registers. Only occurs
+		 * on SCSI ATA PASS_THROUGH commands when CK_COND=1
+		 */
+		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
+			do_print = false;
+		else if (req->rq_flags & RQF_QUIET)
+			do_print = false;
+		if (do_print)
+			scsi_print_sense(cmd);
+		result = 0;
+		/* for passthrough, *blk_statp may be set */
+		*blk_statp = BLK_STS_OK;
+	}
+	/*
+	 * Another corner case: the SCSI status byte is non-zero but 'good'.
+	 * Example: PRE-FETCH command returns SAM_STAT_CONDITION_MET when
+	 * it is able to fit nominated LBs in its cache (and SAM_STAT_GOOD
+	 * if it can't fit). Treat SAM_STAT_CONDITION_MET and the related
+	 * intermediate statuses (both obsolete in SAM-4) as good.
+	 */
+	if (status_byte(result) && scsi_status_is_good(result)) {
+		result = 0;
+		*blk_statp = BLK_STS_OK;
+	}
+	return result;
+}
+
 /*
  * Function:    scsi_io_completion()
  *
@@ -804,26 +877,14 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	      ACTION_DELAYED_RETRY} action;
 	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
 
-	if (result) {
+	if (result) {	/* does not necessarily mean there is an error */
 		sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
 		if (sense_valid)
 			sense_current = !scsi_sense_is_deferred(&sshdr);
+		result = scsi_io_completion_nz_result(cmd, result, &blk_stat);
 	}
 
 	if (blk_rq_is_passthrough(req)) {
-		if (result) {
-			if (sense_valid) {
-				/*
-				 * SG_IO wants current and deferred errors
-				 */
-				scsi_req(req)->sense_len =
-					min(8 + cmd->sense_buffer[7],
-					    SCSI_SENSE_BUFFERSIZE);
-			}
-			if (sense_current)
-				blk_stat = scsi_result_to_blk_status(cmd,
-								       result);
-		}
 		/*
 		 * scsi_result_to_blk_status may have reset the host_byte
 		 */
@@ -841,13 +902,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 				BUG();
 			return;
 		}
-	} else if (blk_rq_bytes(req) == 0 && result && sense_current) {
-		/*
-		 * Flush commands do not transfers any data, and thus cannot use
-		 * good_bytes != blk_rq_bytes(req) as the signal for an error.
-		 * This sets blk_stat explicitly for the problem case.
-		 */
-		blk_stat = scsi_result_to_blk_status(cmd, result);
 	}
 
 	/* no bidi support for !blk_rq_is_passthrough yet */
@@ -861,42 +915,6 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		"%u sectors total, %d bytes done.\n",
 		blk_rq_sectors(req), good_bytes));
 
-	/*
-	 * Recovered errors need reporting, but they're always treated as
-	 * success, so fiddle the result code here.  For passthrough requests
-	 * we already took a copy of the original into sreq->result which
-	 * is what gets returned to the user
-	 */
-	if (sense_valid && (sshdr.sense_key == RECOVERED_ERROR)) {
-		bool do_print = true;
-
-		/*
-		 * If ATA PASS-THROUGH INFORMATION AVAILABLE skip
-		 * print since caller wants ATA registers. Only occurs on
-		 * SCSI ATA PASS_THROUGH commands when CK_COND=1
-		 */
-		if ((sshdr.asc == 0x0) && (sshdr.ascq == 0x1d))
-			do_print = false;
-		else if (req->rq_flags & RQF_QUIET)
-			do_print = false;
-		if (do_print)
-			scsi_print_sense(cmd);
-		result = 0;
-		/* for passthrough, blk_stat may be set */
-		blk_stat = BLK_STS_OK;
-	}
-	/*
-	 * Another corner case: the SCSI status byte is non-zero but 'good'.
-	 * Example: PRE-FETCH command returns SAM_STAT_CONDITION_MET when
-	 * it is able to fit nominated LBs in its cache (and SAM_STAT_GOOD
-	 * if it can't fit). Treat SAM_STAT_CONDITION_MET and the related
-	 * intermediate statuses (both obsolete in SAM-4) as good.
-	 */
-	if (status_byte(result) && scsi_status_is_good(result)) {
-		result = 0;
-		blk_stat = BLK_STS_OK;
-	}
-
 	/*
 	 * Next deal with any sectors which we were able to correctly
 	 * handle. Failed, zero length commands always need to drop down
-- 
cgit v1.2.3


From da32baea17e36b2bd95cf38b07d1297daf1d98cf Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 23 Jun 2018 12:22:17 +0200
Subject: scsi: core: add scsi_io_completion_action helper

Place scsi_io_completion()'s complex error processing associated with a
local enumeration into a static helper function. That enumeration's values
start with "ACTION_" so use the suffix "_action" in the helper function's
name.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 329 +++++++++++++++++++++++++-----------------------
 1 file changed, 175 insertions(+), 154 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 02892408962b..16a7e6846cac 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -761,6 +761,172 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result)
 	}
 }
 
+/* Helper for scsi_io_completion() when special action required. */
+static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
+{
+	struct request_queue *q = cmd->device->request_queue;
+	struct request *req = cmd->request;
+	int level = 0;
+	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
+	      ACTION_DELAYED_RETRY} action;
+	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
+	struct scsi_sense_hdr sshdr;
+	bool sense_valid;
+	bool sense_current = true;      /* false implies "deferred sense" */
+	blk_status_t blk_stat;
+
+	sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
+	if (sense_valid)
+		sense_current = !scsi_sense_is_deferred(&sshdr);
+
+	blk_stat = scsi_result_to_blk_status(cmd, result);
+
+	if (host_byte(result) == DID_RESET) {
+		/* Third party bus reset or reset for error recovery
+		 * reasons.  Just retry the command and see what
+		 * happens.
+		 */
+		action = ACTION_RETRY;
+	} else if (sense_valid && sense_current) {
+		switch (sshdr.sense_key) {
+		case UNIT_ATTENTION:
+			if (cmd->device->removable) {
+				/* Detected disc change.  Set a bit
+				 * and quietly refuse further access.
+				 */
+				cmd->device->changed = 1;
+				action = ACTION_FAIL;
+			} else {
+				/* Must have been a power glitch, or a
+				 * bus reset.  Could not have been a
+				 * media change, so we just retry the
+				 * command and see what happens.
+				 */
+				action = ACTION_RETRY;
+			}
+			break;
+		case ILLEGAL_REQUEST:
+			/* If we had an ILLEGAL REQUEST returned, then
+			 * we may have performed an unsupported
+			 * command.  The only thing this should be
+			 * would be a ten byte read where only a six
+			 * byte read was supported.  Also, on a system
+			 * where READ CAPACITY failed, we may have
+			 * read past the end of the disk.
+			 */
+			if ((cmd->device->use_10_for_rw &&
+			    sshdr.asc == 0x20 && sshdr.ascq == 0x00) &&
+			    (cmd->cmnd[0] == READ_10 ||
+			     cmd->cmnd[0] == WRITE_10)) {
+				/* This will issue a new 6-byte command. */
+				cmd->device->use_10_for_rw = 0;
+				action = ACTION_REPREP;
+			} else if (sshdr.asc == 0x10) /* DIX */ {
+				action = ACTION_FAIL;
+				blk_stat = BLK_STS_PROTECTION;
+			/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
+			} else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
+				action = ACTION_FAIL;
+				blk_stat = BLK_STS_TARGET;
+			} else
+				action = ACTION_FAIL;
+			break;
+		case ABORTED_COMMAND:
+			action = ACTION_FAIL;
+			if (sshdr.asc == 0x10) /* DIF */
+				blk_stat = BLK_STS_PROTECTION;
+			break;
+		case NOT_READY:
+			/* If the device is in the process of becoming
+			 * ready, or has a temporary blockage, retry.
+			 */
+			if (sshdr.asc == 0x04) {
+				switch (sshdr.ascq) {
+				case 0x01: /* becoming ready */
+				case 0x04: /* format in progress */
+				case 0x05: /* rebuild in progress */
+				case 0x06: /* recalculation in progress */
+				case 0x07: /* operation in progress */
+				case 0x08: /* Long write in progress */
+				case 0x09: /* self test in progress */
+				case 0x14: /* space allocation in progress */
+				case 0x1a: /* start stop unit in progress */
+				case 0x1b: /* sanitize in progress */
+				case 0x1d: /* configuration in progress */
+				case 0x24: /* depopulation in progress */
+					action = ACTION_DELAYED_RETRY;
+					break;
+				default:
+					action = ACTION_FAIL;
+					break;
+				}
+			} else
+				action = ACTION_FAIL;
+			break;
+		case VOLUME_OVERFLOW:
+			/* See SSC3rXX or current. */
+			action = ACTION_FAIL;
+			break;
+		default:
+			action = ACTION_FAIL;
+			break;
+		}
+	} else
+		action = ACTION_FAIL;
+
+	if (action != ACTION_FAIL &&
+	    time_before(cmd->jiffies_at_alloc + wait_for, jiffies))
+		action = ACTION_FAIL;
+
+	switch (action) {
+	case ACTION_FAIL:
+		/* Give up and fail the remainder of the request */
+		if (!(req->rq_flags & RQF_QUIET)) {
+			static DEFINE_RATELIMIT_STATE(_rs,
+					DEFAULT_RATELIMIT_INTERVAL,
+					DEFAULT_RATELIMIT_BURST);
+
+			if (unlikely(scsi_logging_level))
+				level =
+				     SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT,
+						    SCSI_LOG_MLCOMPLETE_BITS);
+
+			/*
+			 * if logging is enabled the failure will be printed
+			 * in scsi_log_completion(), so avoid duplicate messages
+			 */
+			if (!level && __ratelimit(&_rs)) {
+				scsi_print_result(cmd, NULL, FAILED);
+				if (driver_byte(result) & DRIVER_SENSE)
+					scsi_print_sense(cmd);
+				scsi_print_command(cmd);
+			}
+		}
+		if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req), 0))
+			return;
+		/*FALLTHRU*/
+	case ACTION_REPREP:
+		/* Unprep the request and put it back at the head of the queue.
+		 * A new command will be prepared and issued.
+		 */
+		if (q->mq_ops) {
+			scsi_mq_requeue_cmd(cmd);
+		} else {
+			scsi_release_buffers(cmd);
+			scsi_requeue_command(q, cmd);
+		}
+		break;
+	case ACTION_RETRY:
+		/* Retry the same command immediately */
+		__scsi_queue_insert(cmd, SCSI_MLQUEUE_EH_RETRY, false);
+		break;
+	case ACTION_DELAYED_RETRY:
+		/* Retry the same command after a delay */
+		__scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, false);
+		break;
+	}
+}
+
 /*
  * Helper for scsi_io_completion() when cmd->result is non-zero. Returns a
  * new result that may suppress further error checking. Also modifies
@@ -869,20 +1035,9 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	struct request_queue *q = cmd->device->request_queue;
 	struct request *req = cmd->request;
 	blk_status_t blk_stat = BLK_STS_OK;
-	struct scsi_sense_hdr sshdr;
-	bool sense_valid = false;
-	bool sense_current = true;	/* false implies "deferred sense" */
-	int level = 0;
-	enum {ACTION_FAIL, ACTION_REPREP, ACTION_RETRY,
-	      ACTION_DELAYED_RETRY} action;
-	unsigned long wait_for = (cmd->allowed + 1) * req->timeout;
 
-	if (result) {	/* does not necessarily mean there is an error */
-		sense_valid = scsi_command_normalize_sense(cmd, &sshdr);
-		if (sense_valid)
-			sense_current = !scsi_sense_is_deferred(&sshdr);
+	if (result)	/* does not necessarily mean there is an error */
 		result = scsi_io_completion_nz_result(cmd, result, &blk_stat);
-	}
 
 	if (blk_rq_is_passthrough(req)) {
 		/*
@@ -936,138 +1091,12 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 * If there had been no error, but we have leftover bytes in the
 	 * requeues just queue the command up again.
 	 */
-	if (result == 0)
-		goto requeue;
-
-	blk_stat = scsi_result_to_blk_status(cmd, result);
-
-	if (host_byte(result) == DID_RESET) {
-		/* Third party bus reset or reset for error recovery
-		 * reasons.  Just retry the command and see what
-		 * happens.
-		 */
-		action = ACTION_RETRY;
-	} else if (sense_valid && sense_current) {
-		switch (sshdr.sense_key) {
-		case UNIT_ATTENTION:
-			if (cmd->device->removable) {
-				/* Detected disc change.  Set a bit
-				 * and quietly refuse further access.
-				 */
-				cmd->device->changed = 1;
-				action = ACTION_FAIL;
-			} else {
-				/* Must have been a power glitch, or a
-				 * bus reset.  Could not have been a
-				 * media change, so we just retry the
-				 * command and see what happens.
-				 */
-				action = ACTION_RETRY;
-			}
-			break;
-		case ILLEGAL_REQUEST:
-			/* If we had an ILLEGAL REQUEST returned, then
-			 * we may have performed an unsupported
-			 * command.  The only thing this should be
-			 * would be a ten byte read where only a six
-			 * byte read was supported.  Also, on a system
-			 * where READ CAPACITY failed, we may have
-			 * read past the end of the disk.
-			 */
-			if ((cmd->device->use_10_for_rw &&
-			    sshdr.asc == 0x20 && sshdr.ascq == 0x00) &&
-			    (cmd->cmnd[0] == READ_10 ||
-			     cmd->cmnd[0] == WRITE_10)) {
-				/* This will issue a new 6-byte command. */
-				cmd->device->use_10_for_rw = 0;
-				action = ACTION_REPREP;
-			} else if (sshdr.asc == 0x10) /* DIX */ {
-				action = ACTION_FAIL;
-				blk_stat = BLK_STS_PROTECTION;
-			/* INVALID COMMAND OPCODE or INVALID FIELD IN CDB */
-			} else if (sshdr.asc == 0x20 || sshdr.asc == 0x24) {
-				action = ACTION_FAIL;
-				blk_stat = BLK_STS_TARGET;
-			} else
-				action = ACTION_FAIL;
-			break;
-		case ABORTED_COMMAND:
-			action = ACTION_FAIL;
-			if (sshdr.asc == 0x10) /* DIF */
-				blk_stat = BLK_STS_PROTECTION;
-			break;
-		case NOT_READY:
-			/* If the device is in the process of becoming
-			 * ready, or has a temporary blockage, retry.
-			 */
-			if (sshdr.asc == 0x04) {
-				switch (sshdr.ascq) {
-				case 0x01: /* becoming ready */
-				case 0x04: /* format in progress */
-				case 0x05: /* rebuild in progress */
-				case 0x06: /* recalculation in progress */
-				case 0x07: /* operation in progress */
-				case 0x08: /* Long write in progress */
-				case 0x09: /* self test in progress */
-				case 0x14: /* space allocation in progress */
-				case 0x1a: /* start stop unit in progress */
-				case 0x1b: /* sanitize in progress */
-				case 0x1d: /* configuration in progress */
-				case 0x24: /* depopulation in progress */
-					action = ACTION_DELAYED_RETRY;
-					break;
-				default:
-					action = ACTION_FAIL;
-					break;
-				}
-			} else
-				action = ACTION_FAIL;
-			break;
-		case VOLUME_OVERFLOW:
-			/* See SSC3rXX or current. */
-			action = ACTION_FAIL;
-			break;
-		default:
-			action = ACTION_FAIL;
-			break;
-		}
-	} else
-		action = ACTION_FAIL;
-
-	if (action != ACTION_FAIL &&
-	    time_before(cmd->jiffies_at_alloc + wait_for, jiffies))
-		action = ACTION_FAIL;
-
-	switch (action) {
-	case ACTION_FAIL:
-		/* Give up and fail the remainder of the request */
-		if (!(req->rq_flags & RQF_QUIET)) {
-			static DEFINE_RATELIMIT_STATE(_rs,
-					DEFAULT_RATELIMIT_INTERVAL,
-					DEFAULT_RATELIMIT_BURST);
-
-			if (unlikely(scsi_logging_level))
-				level = SCSI_LOG_LEVEL(SCSI_LOG_MLCOMPLETE_SHIFT,
-						       SCSI_LOG_MLCOMPLETE_BITS);
-
-			/*
-			 * if logging is enabled the failure will be printed
-			 * in scsi_log_completion(), so avoid duplicate messages
-			 */
-			if (!level && __ratelimit(&_rs)) {
-				scsi_print_result(cmd, NULL, FAILED);
-				if (driver_byte(result) & DRIVER_SENSE)
-					scsi_print_sense(cmd);
-				scsi_print_command(cmd);
-			}
-		}
-		if (!scsi_end_request(req, blk_stat, blk_rq_err_bytes(req), 0))
-			return;
-		/*FALLTHRU*/
-	case ACTION_REPREP:
-	requeue:
-		/* Unprep the request and put it back at the head of the queue.
-		 * A new command will be prepared and issued.
+	if (result == 0) {
+		/*
+		 * Unprep the request and put it back at the head of the
+		 * queue. A new command will be prepared and issued.
+		 * This block is the same as case ACTION_REPREP in
+		 * scsi_io_completion_action() above.
 		 */
 		if (q->mq_ops) {
 			scsi_mq_requeue_cmd(cmd);
@@ -1075,16 +1104,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			scsi_release_buffers(cmd);
 			scsi_requeue_command(q, cmd);
 		}
-		break;
-	case ACTION_RETRY:
-		/* Retry the same command immediately */
-		__scsi_queue_insert(cmd, SCSI_MLQUEUE_EH_RETRY, false);
-		break;
-	case ACTION_DELAYED_RETRY:
-		/* Retry the same command after a delay */
-		__scsi_queue_insert(cmd, SCSI_MLQUEUE_DEVICE_BUSY, false);
-		break;
-	}
+	} else
+		scsi_io_completion_action(cmd, result);
 }
 
 static int scsi_init_sgtable(struct request *req, struct scsi_data_buffer *sdb)
-- 
cgit v1.2.3


From 4ae61c68f7d72d98e7e41a8d4ec21bbaa46b63d4 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 23 Jun 2018 12:22:18 +0200
Subject: scsi: core: add scsi_io_completion_reprep helper

Since the action "reprep" is called from two places, rather than repeat the
code, make a new scsi_io_completion helper with "reprep" as its suffix.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 41 ++++++++++++++++++-----------------------
 1 file changed, 18 insertions(+), 23 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 16a7e6846cac..63dcb2a94e5d 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -761,6 +761,20 @@ static blk_status_t scsi_result_to_blk_status(struct scsi_cmnd *cmd, int result)
 	}
 }
 
+/* Helper for scsi_io_completion() when "reprep" action required. */
+static void scsi_io_completion_reprep(struct scsi_cmnd *cmd,
+				      struct request_queue *q)
+{
+	/* A new command will be prepared and issued. */
+	if (q->mq_ops) {
+		scsi_mq_requeue_cmd(cmd);
+	} else {
+		/* Unprep request and put it back at head of the queue. */
+		scsi_release_buffers(cmd);
+		scsi_requeue_command(q, cmd);
+	}
+}
+
 /* Helper for scsi_io_completion() when special action required. */
 static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 {
@@ -906,15 +920,7 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 			return;
 		/*FALLTHRU*/
 	case ACTION_REPREP:
-		/* Unprep the request and put it back at the head of the queue.
-		 * A new command will be prepared and issued.
-		 */
-		if (q->mq_ops) {
-			scsi_mq_requeue_cmd(cmd);
-		} else {
-			scsi_release_buffers(cmd);
-			scsi_requeue_command(q, cmd);
-		}
+		scsi_io_completion_reprep(cmd, q);
 		break;
 	case ACTION_RETRY:
 		/* Retry the same command immediately */
@@ -1091,20 +1097,9 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 * If there had been no error, but we have leftover bytes in the
 	 * requeues just queue the command up again.
 	 */
-	if (result == 0) {
-		/*
-		 * Unprep the request and put it back at the head of the
-		 * queue. A new command will be prepared and issued.
-		 * This block is the same as case ACTION_REPREP in
-		 * scsi_io_completion_action() above.
-		 */
-		if (q->mq_ops) {
-			scsi_mq_requeue_cmd(cmd);
-		} else {
-			scsi_release_buffers(cmd);
-			scsi_requeue_command(q, cmd);
-		}
-	} else
+	if (result == 0)
+		scsi_io_completion_reprep(cmd, q);
+	else
 		scsi_io_completion_action(cmd, result);
 }
 
-- 
cgit v1.2.3


From 0d437906f6dca6167b37c8e1f6f6ec395bde6230 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 23 Jun 2018 12:22:19 +0200
Subject: scsi: core: scsi_io_completion hints on fastpath

Add likely() and unlikely() hints to conditionals on or near the fastpath.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 63dcb2a94e5d..19ed11abe886 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1042,17 +1042,17 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	struct request *req = cmd->request;
 	blk_status_t blk_stat = BLK_STS_OK;
 
-	if (result)	/* does not necessarily mean there is an error */
+	if (unlikely(result))	/* a nz result may or may not be an error */
 		result = scsi_io_completion_nz_result(cmd, result, &blk_stat);
 
-	if (blk_rq_is_passthrough(req)) {
+	if (unlikely(blk_rq_is_passthrough(req))) {
 		/*
 		 * scsi_result_to_blk_status may have reset the host_byte
 		 */
 		scsi_req(req)->result = cmd->result;
 		scsi_req(req)->resid_len = scsi_get_resid(cmd);
 
-		if (scsi_bidi_cmnd(cmd)) {
+		if (unlikely(scsi_bidi_cmnd(cmd))) {
 			/*
 			 * Bidi commands Must be complete as a whole,
 			 * both sides at once.
@@ -1065,7 +1065,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 		}
 	}
 
-	/* no bidi support for !blk_rq_is_passthrough yet */
+	/* no bidi support yet, other than in pass-through */
 	BUG_ON(blk_bidi_rq(req));
 
 	/*
@@ -1081,13 +1081,13 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 * handle. Failed, zero length commands always need to drop down
 	 * to retry code. Fast path should return in this block.
 	 */
-	if (blk_rq_bytes(req) > 0 || blk_stat == BLK_STS_OK) {
-		if (!scsi_end_request(req, blk_stat, good_bytes, 0))
+	if (likely(blk_rq_bytes(req) > 0 || blk_stat == BLK_STS_OK)) {
+		if (likely(!scsi_end_request(req, blk_stat, good_bytes, 0)))
 			return; /* no bytes remaining */
 	}
 
-	 /* Kill remainder if no retries. */
-	if (blk_stat && scsi_noretry_cmd(cmd)) {
+	/* Kill remainder if no retries. */
+	if (unlikely(blk_stat && scsi_noretry_cmd(cmd))) {
 		if (scsi_end_request(req, blk_stat, blk_rq_bytes(req), 0))
 			BUG();
 		return;
@@ -1097,7 +1097,7 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	 * If there had been no error, but we have leftover bytes in the
 	 * requeues just queue the command up again.
 	 */
-	if (result == 0)
+	if (likely(result == 0))
 		scsi_io_completion_reprep(cmd, q);
 	else
 		scsi_io_completion_action(cmd, result);
-- 
cgit v1.2.3


From 8e1695a07c7b28e2eb1c02cc01e2b8f5dd28bf87 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 23 Jun 2018 12:22:20 +0200
Subject: scsi: core: scsi_io_completion convert BUGs to WARNs

The scsi_io_completion function contains three BUG() and BUG_ON() calls.
Replace them with WARN variants.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 19ed11abe886..252edd61a688 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1060,13 +1060,21 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 			scsi_req(req->next_rq)->resid_len = scsi_in(cmd)->resid;
 			if (scsi_end_request(req, BLK_STS_OK, blk_rq_bytes(req),
 					blk_rq_bytes(req->next_rq)))
-				BUG();
+				WARN_ONCE(true,
+					  "Bidi command with remaining bytes");
 			return;
 		}
 	}
 
 	/* no bidi support yet, other than in pass-through */
-	BUG_ON(blk_bidi_rq(req));
+	if (unlikely(blk_bidi_rq(req))) {
+		WARN_ONCE(true, "Only support bidi command in passthrough");
+		scmd_printk(KERN_ERR, cmd, "Killing bidi command\n");
+		if (scsi_end_request(req, BLK_STS_IOERR, blk_rq_bytes(req),
+				     blk_rq_bytes(req->next_rq)))
+			WARN_ONCE(true, "Bidi command with remaining bytes");
+		return;
+	}
 
 	/*
 	 * Next deal with any sectors which we were able to correctly
@@ -1089,7 +1097,8 @@ void scsi_io_completion(struct scsi_cmnd *cmd, unsigned int good_bytes)
 	/* Kill remainder if no retries. */
 	if (unlikely(blk_stat && scsi_noretry_cmd(cmd))) {
 		if (scsi_end_request(req, blk_stat, blk_rq_bytes(req), 0))
-			BUG();
+			WARN_ONCE(true,
+			    "Bytes remaining after failed, no-retry command");
 		return;
 	}
 
-- 
cgit v1.2.3


From c65be1a63f1df224c8f22d72b9ec824241ada585 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Mon, 25 Jun 2018 13:20:58 +0200
Subject: scsi: core: check for equality of result byte values

When evaluating a SCSI command's result using the field access macros,
check for equality of the fields and not if a specific bit is set.

This is a preparation patch, for reworking the results field in the
SCSI command.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ch.c                 |  2 +-
 drivers/scsi/dc395x.c             |  5 ++---
 drivers/scsi/scsi.c               |  2 +-
 drivers/scsi/scsi_ioctl.c         |  4 ++--
 drivers/scsi/scsi_lib.c           |  4 ++--
 drivers/scsi/scsi_scan.c          |  2 +-
 drivers/scsi/scsi_transport_spi.c |  2 +-
 drivers/scsi/sd.c                 | 14 +++++++-------
 drivers/scsi/ufs/ufshcd.c         |  2 +-
 9 files changed, 18 insertions(+), 19 deletions(-)

diff --git a/drivers/scsi/ch.c b/drivers/scsi/ch.c
index c535c52e72e5..1c5051b1c125 100644
--- a/drivers/scsi/ch.c
+++ b/drivers/scsi/ch.c
@@ -199,7 +199,7 @@ ch_do_scsi(scsi_changer *ch, unsigned char *cmd, int cmd_len,
 				  buflength, &sshdr, timeout * HZ,
 				  MAX_RETRIES, NULL);
 
-	if (driver_byte(result) & DRIVER_SENSE) {
+	if (driver_byte(result) == DRIVER_SENSE) {
 		if (debug)
 			scsi_print_sense_hdr(ch->device, ch->name, &sshdr);
 		errno = ch_find_errno(&sshdr);
diff --git a/drivers/scsi/dc395x.c b/drivers/scsi/dc395x.c
index 60ef8df42b95..1ed2cd82129d 100644
--- a/drivers/scsi/dc395x.c
+++ b/drivers/scsi/dc395x.c
@@ -3473,9 +3473,8 @@ static void srb_done(struct AdapterCtlBlk *acb, struct DeviceCtlBlk *dcb,
 
 	/*if( srb->cmd->cmnd[0] == INQUIRY && */
 	/*  (host_byte(cmd->result) == DID_OK || status_byte(cmd->result) & CHECK_CONDITION) ) */
-		if ((cmd->result == (DID_OK << 16)
-		     || status_byte(cmd->result) &
-		     CHECK_CONDITION)) {
+		if ((cmd->result == (DID_OK << 16) ||
+		     status_byte(cmd->result) == CHECK_CONDITION)) {
 			if (!dcb->init_tcq_flag) {
 				add_dev(acb, dcb, ptr);
 				dcb->init_tcq_flag = 1;
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 4c60c260c5da..70ef3c39061d 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -162,7 +162,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
 		    (level > 1)) {
 			scsi_print_result(cmd, "Done", disposition);
 			scsi_print_command(cmd);
-			if (status_byte(cmd->result) & CHECK_CONDITION)
+			if (status_byte(cmd->result) == CHECK_CONDITION)
 				scsi_print_sense(cmd);
 			if (level > 3)
 				scmd_printk(KERN_INFO, cmd,
diff --git a/drivers/scsi/scsi_ioctl.c b/drivers/scsi/scsi_ioctl.c
index 0a875491f5a7..cc30fccc1a2e 100644
--- a/drivers/scsi/scsi_ioctl.c
+++ b/drivers/scsi/scsi_ioctl.c
@@ -100,8 +100,8 @@ static int ioctl_internal_command(struct scsi_device *sdev, char *cmd,
 	SCSI_LOG_IOCTL(2, sdev_printk(KERN_INFO, sdev,
 				      "Ioctl returned  0x%x\n", result));
 
-	if ((driver_byte(result) & DRIVER_SENSE) &&
-	    (scsi_sense_valid(&sshdr))) {
+	if (driver_byte(result) == DRIVER_SENSE &&
+	    scsi_sense_valid(&sshdr)) {
 		switch (sshdr.sense_key) {
 		case ILLEGAL_REQUEST:
 			if (cmd[0] == ALLOW_MEDIUM_REMOVAL)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 252edd61a688..a1a0a2903263 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -911,7 +911,7 @@ static void scsi_io_completion_action(struct scsi_cmnd *cmd, int result)
 			 */
 			if (!level && __ratelimit(&_rs)) {
 				scsi_print_result(cmd, NULL, FAILED);
-				if (driver_byte(result) & DRIVER_SENSE)
+				if (driver_byte(result) == DRIVER_SENSE)
 					scsi_print_sense(cmd);
 				scsi_print_command(cmd);
 			}
@@ -2605,7 +2605,7 @@ scsi_mode_sense(struct scsi_device *sdev, int dbd, int modepage,
 	 * ILLEGAL REQUEST if the code page isn't supported */
 
 	if (use_10_for_ms && !scsi_status_is_good(result) &&
-	    (driver_byte(result) & DRIVER_SENSE)) {
+	    driver_byte(result) == DRIVER_SENSE) {
 		if (scsi_sense_valid(sshdr)) {
 			if ((sshdr->sense_key == ILLEGAL_REQUEST) &&
 			    (sshdr->asc == 0x20) && (sshdr->ascq == 0)) {
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 0880d975eed3..78ca63dfba4a 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -614,7 +614,7 @@ static int scsi_probe_lun(struct scsi_device *sdev, unsigned char *inq_result,
 			 * INQUIRY should not yield UNIT_ATTENTION
 			 * but many buggy devices do so anyway. 
 			 */
-			if ((driver_byte(result) & DRIVER_SENSE) &&
+			if (driver_byte(result) == DRIVER_SENSE &&
 			    scsi_sense_valid(&sshdr)) {
 				if ((sshdr.sense_key == UNIT_ATTENTION) &&
 				    ((sshdr.asc == 0x28) ||
diff --git a/drivers/scsi/scsi_transport_spi.c b/drivers/scsi/scsi_transport_spi.c
index 2ca150b16764..40b85b752b79 100644
--- a/drivers/scsi/scsi_transport_spi.c
+++ b/drivers/scsi/scsi_transport_spi.c
@@ -136,7 +136,7 @@ static int spi_execute(struct scsi_device *sdev, const void *cmd,
 				      REQ_FAILFAST_TRANSPORT |
 				      REQ_FAILFAST_DRIVER,
 				      0, NULL);
-		if (!(driver_byte(result) & DRIVER_SENSE) ||
+		if (driver_byte(result) != DRIVER_SENSE ||
 		    sshdr->sense_key != UNIT_ATTENTION)
 			break;
 	}
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 9421d9877730..612aa14c1b26 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1635,7 +1635,7 @@ static int sd_sync_cache(struct scsi_disk *sdkp, struct scsi_sense_hdr *sshdr)
 	if (res) {
 		sd_print_result(sdkp, "Synchronize Cache(10) failed", res);
 
-		if (driver_byte(res) & DRIVER_SENSE)
+		if (driver_byte(res) == DRIVER_SENSE)
 			sd_print_sense_hdr(sdkp, sshdr);
 
 		/* we need to evaluate the error return  */
@@ -1737,8 +1737,8 @@ static int sd_pr_command(struct block_device *bdev, u8 sa,
 	result = scsi_execute_req(sdev, cmd, DMA_TO_DEVICE, &data, sizeof(data),
 			&sshdr, SD_TIMEOUT, SD_MAX_RETRIES, NULL);
 
-	if ((driver_byte(result) & DRIVER_SENSE) &&
-	    (scsi_sense_valid(&sshdr))) {
+	if (driver_byte(result) == DRIVER_SENSE &&
+	    scsi_sense_valid(&sshdr)) {
 		sdev_printk(KERN_INFO, sdev, "PR command failed: %d\n", result);
 		scsi_print_sense_hdr(sdev, NULL, &sshdr);
 	}
@@ -2095,10 +2095,10 @@ sd_spinup_disk(struct scsi_disk *sdkp)
 			retries++;
 		} while (retries < 3 && 
 			 (!scsi_status_is_good(the_result) ||
-			  ((driver_byte(the_result) & DRIVER_SENSE) &&
+			  ((driver_byte(the_result) == DRIVER_SENSE) &&
 			  sense_valid && sshdr.sense_key == UNIT_ATTENTION)));
 
-		if ((driver_byte(the_result) & DRIVER_SENSE) == 0) {
+		if (driver_byte(the_result) != DRIVER_SENSE) {
 			/* no sense, TUR either succeeded or failed
 			 * with a status error */
 			if(!spintime && !scsi_status_is_good(the_result)) {
@@ -2224,7 +2224,7 @@ static void read_capacity_error(struct scsi_disk *sdkp, struct scsi_device *sdp,
 			struct scsi_sense_hdr *sshdr, int sense_valid,
 			int the_result)
 {
-	if (driver_byte(the_result) & DRIVER_SENSE)
+	if (driver_byte(the_result) == DRIVER_SENSE)
 		sd_print_sense_hdr(sdkp, sshdr);
 	else
 		sd_printk(KERN_NOTICE, sdkp, "Sense not available.\n");
@@ -3490,7 +3490,7 @@ static int sd_start_stop_device(struct scsi_disk *sdkp, int start)
 			SD_TIMEOUT, SD_MAX_RETRIES, 0, RQF_PM, NULL);
 	if (res) {
 		sd_print_result(sdkp, "Start/Stop Unit failed", res);
-		if (driver_byte(res) & DRIVER_SENSE)
+		if (driver_byte(res) == DRIVER_SENSE)
 			sd_print_sense_hdr(sdkp, &sshdr);
 		if (scsi_sense_valid(&sshdr) &&
 			/* 0x3a is medium not present */
diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 350f859625f6..3560185002da 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -7303,7 +7303,7 @@ static int ufshcd_set_dev_pwr_mode(struct ufs_hba *hba,
 		sdev_printk(KERN_WARNING, sdp,
 			    "START_STOP failed for power mode: %d, result %x\n",
 			    pwr_mode, ret);
-		if (driver_byte(ret) & DRIVER_SENSE)
+		if (driver_byte(ret) == DRIVER_SENSE)
 			scsi_print_sense_hdr(sdp, NULL, &sshdr);
 	}
 
-- 
cgit v1.2.3


From 6bec4c3842cd7338973839683bbf96273c3b85f7 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Mon, 25 Jun 2018 13:20:59 +0200
Subject: scsi: don't add scsi command result bytes

Some drivers are ADDing the scsi command's result bytes instead of ORing
them.

While this can produce correct results it has unexpected side effects.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/imm.c                  | 2 +-
 drivers/scsi/mesh.c                 | 4 ++--
 drivers/scsi/sym53c8xx_2/sym_glue.c | 2 +-
 drivers/scsi/sym53c8xx_2/sym_glue.h | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/imm.c b/drivers/scsi/imm.c
index 87c94191033b..8c6627bc8a39 100644
--- a/drivers/scsi/imm.c
+++ b/drivers/scsi/imm.c
@@ -892,7 +892,7 @@ static int imm_engine(imm_struct *dev, struct scsi_cmnd *cmd)
 			/* Check for optional message byte */
 			if (imm_wait(dev) == (unsigned char) 0xb8)
 				imm_in(dev, &h, 1);
-			cmd->result = (DID_OK << 16) + (l & STATUS_MASK);
+			cmd->result = (DID_OK << 16) | (l & STATUS_MASK);
 		}
 		if ((dev->mode == IMM_NIBBLE) || (dev->mode == IMM_PS2)) {
 			w_ctr(ppb, 0x4);
diff --git a/drivers/scsi/mesh.c b/drivers/scsi/mesh.c
index 1753e42826dd..82e01dbe90af 100644
--- a/drivers/scsi/mesh.c
+++ b/drivers/scsi/mesh.c
@@ -594,9 +594,9 @@ static void mesh_done(struct mesh_state *ms, int start_next)
 	ms->current_req = NULL;
 	tp->current_req = NULL;
 	if (cmd) {
-		cmd->result = (ms->stat << 16) + cmd->SCp.Status;
+		cmd->result = (ms->stat << 16) | cmd->SCp.Status;
 		if (ms->stat == DID_OK)
-			cmd->result += (cmd->SCp.Message << 8);
+			cmd->result |= cmd->SCp.Message << 8;
 		if (DEBUG_TARGET(cmd)) {
 			printk(KERN_DEBUG "mesh_done: result = %x, data_ptr=%d, buflen=%d\n",
 			       cmd->result, ms->data_ptr, scsi_bufflen(cmd));
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.c b/drivers/scsi/sym53c8xx_2/sym_glue.c
index 7320d5fe4cbc..5f10aa9bad9b 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.c
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.c
@@ -252,7 +252,7 @@ void sym_set_cam_result_error(struct sym_hcb *np, struct sym_ccb *cp, int resid)
 		cam_status = sym_xerr_cam_status(DID_ERROR, cp->xerr_status);
 	}
 	scsi_set_resid(cmd, resid);
-	cmd->result = (drv_status << 24) + (cam_status << 16) + scsi_status;
+	cmd->result = (drv_status << 24) | (cam_status << 16) | scsi_status;
 }
 
 static int sym_scatter(struct sym_hcb *np, struct sym_ccb *cp, struct scsi_cmnd *cmd)
diff --git a/drivers/scsi/sym53c8xx_2/sym_glue.h b/drivers/scsi/sym53c8xx_2/sym_glue.h
index 805369521df8..e34801ae5d69 100644
--- a/drivers/scsi/sym53c8xx_2/sym_glue.h
+++ b/drivers/scsi/sym53c8xx_2/sym_glue.h
@@ -256,7 +256,7 @@ sym_get_cam_status(struct scsi_cmnd *cmd)
 static inline void sym_set_cam_result_ok(struct sym_ccb *cp, struct scsi_cmnd *cmd, int resid)
 {
 	scsi_set_resid(cmd, resid);
-	cmd->result = (((DID_OK) << 16) + ((cp->ssss_status) & 0x7f));
+	cmd->result = (DID_OK << 16) | (cp->ssss_status & 0x7f);
 }
 void sym_set_cam_result_error(struct sym_hcb *np, struct sym_ccb *cp, int resid);
 
-- 
cgit v1.2.3


From c2cdef95160440ed6291bc343139d958ba3261e4 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 25 Jun 2018 08:05:16 -0700
Subject: scsi: qedi: Fix misleading indentation

This patch avoids that smatch reports the following warnings:

drivers/scsi/qedi/qedi_fw_api.c:129: init_sqe() warn: inconsistent indenting
drivers/scsi/qedi/qedi_fw_api.c:137: init_sqe() warn: inconsistent indenting

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: QLogic-Storage-Upstream@cavium.com
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedi/qedi_fw_api.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/qedi/qedi_fw_api.c b/drivers/scsi/qedi/qedi_fw_api.c
index a269da1a6c75..387dc87e4d22 100644
--- a/drivers/scsi/qedi/qedi_fw_api.c
+++ b/drivers/scsi/qedi/qedi_fw_api.c
@@ -126,22 +126,24 @@ static void init_sqe(struct iscsi_task_params *task_params,
 						     sgl_task_params,
 						     dif_task_params);
 
-		if (scsi_is_slow_sgl(sgl_task_params->num_sges,
-				     sgl_task_params->small_mid_sge))
-			num_sges = ISCSI_WQE_NUM_SGES_SLOWIO;
-		else
-			num_sges = min(sgl_task_params->num_sges,
-				       (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
-	}
+			if (scsi_is_slow_sgl(sgl_task_params->num_sges,
+					     sgl_task_params->small_mid_sge))
+				num_sges = ISCSI_WQE_NUM_SGES_SLOWIO;
+			else
+				num_sges = min(sgl_task_params->num_sges,
+					       (u16)SCSI_NUM_SGES_SLOW_SGL_THR);
+		}
 
-	SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES, num_sges);
-	SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN,
-		  buf_size);
+		SET_FIELD(task_params->sqe->flags, ISCSI_WQE_NUM_SGES,
+			  num_sges);
+		SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CONT_LEN,
+			  buf_size);
 
-	if (GET_FIELD(pdu_header->hdr_second_dword,
-		      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
-		SET_FIELD(task_params->sqe->contlen_cdbsize, ISCSI_WQE_CDB_SIZE,
-			  cmd_params->extended_cdb_sge.sge_len);
+		if (GET_FIELD(pdu_header->hdr_second_dword,
+			      ISCSI_CMD_HDR_TOTAL_AHS_LEN))
+			SET_FIELD(task_params->sqe->contlen_cdbsize,
+				  ISCSI_WQE_CDB_SIZE,
+				  cmd_params->extended_cdb_sge.sge_len);
 	}
 		break;
 	case ISCSI_TASK_TYPE_INITIATOR_READ:
-- 
cgit v1.2.3


From 2b33ab371e026cfcea4cbdf233c6b8776dde9ba8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 25 Jun 2018 16:49:38 -0700
Subject: scsi: sd: Remove a superfluous assignment

Since blk_rq_bytes(req) returns req->__data_len, assigning that value to
req->__data_len is superfluous. Hence remove that assignment.

See also commit 5db44863b6eb ("[SCSI] sd: Implement support for WRITE SAME").

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 612aa14c1b26..a84f0923753a 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2028,7 +2028,6 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 				} else {
 					sdkp->device->no_write_same = 1;
 					sd_config_write_same(sdkp);
-					req->__data_len = blk_rq_bytes(req);
 					req->rq_flags |= RQF_QUIET;
 				}
 				break;
-- 
cgit v1.2.3


From c84b023a4c1461498abf0eda54f60e2fd64a1ca2 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 24 Jun 2018 22:03:26 +0800
Subject: scsi: read host_busy via scsi_host_busy()

No functional change.

Just introduce scsi_host_busy() and replace the direct read of
scsi_host->host_busy with this new API.

Cc: Omar Sandoval <osandov@fb.com>,
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>,
Cc: James Bottomley <james.bottomley@hansenpartnership.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: Don Brace <don.brace@microsemi.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>

Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/advansys.c                   |  8 ++++----
 drivers/scsi/hosts.c                      | 10 ++++++++++
 drivers/scsi/libsas/sas_scsi_host.c       |  4 ++--
 drivers/scsi/megaraid/megaraid_sas_base.c |  2 +-
 drivers/scsi/mpt3sas/mpt3sas_base.c       |  4 ++--
 drivers/scsi/qlogicpti.c                  |  2 +-
 drivers/scsi/scsi.c                       |  2 +-
 drivers/scsi/scsi_error.c                 |  6 +++---
 drivers/scsi/scsi_sysfs.c                 |  2 +-
 include/scsi/scsi_host.h                  |  1 +
 10 files changed, 26 insertions(+), 15 deletions(-)

diff --git a/drivers/scsi/advansys.c b/drivers/scsi/advansys.c
index c9a52905070e..713f69033f20 100644
--- a/drivers/scsi/advansys.c
+++ b/drivers/scsi/advansys.c
@@ -2416,8 +2416,8 @@ static void asc_prt_scsi_host(struct Scsi_Host *s)
 	struct asc_board *boardp = shost_priv(s);
 
 	printk("Scsi_Host at addr 0x%p, device %s\n", s, dev_name(boardp->dev));
-	printk(" host_busy %u, host_no %d,\n",
-	       atomic_read(&s->host_busy), s->host_no);
+	printk(" host_busy %d, host_no %d,\n",
+	       scsi_host_busy(s), s->host_no);
 
 	printk(" base 0x%lx, io_port 0x%lx, irq %d,\n",
 	       (ulong)s->base, (ulong)s->io_port, boardp->irq);
@@ -3182,8 +3182,8 @@ static void asc_prt_driver_conf(struct seq_file *m, struct Scsi_Host *shost)
 		shost->host_no);
 
 	seq_printf(m,
-		   " host_busy %u, max_id %u, max_lun %llu, max_channel %u\n",
-		   atomic_read(&shost->host_busy), shost->max_id,
+		   " host_busy %d, max_id %u, max_lun %llu, max_channel %u\n",
+		   scsi_host_busy(shost), shost->max_id,
 		   shost->max_lun, shost->max_channel);
 
 	seq_printf(m,
diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index 3771e59a9fae..ea4b0bb0c1cd 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -563,6 +563,16 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL(scsi_host_get);
 
+/**
+ * scsi_host_busy - Return the host busy counter
+ * @shost:	Pointer to Scsi_Host to inc.
+ **/
+int scsi_host_busy(struct Scsi_Host *shost)
+{
+	return atomic_read(&shost->host_busy);
+}
+EXPORT_SYMBOL(scsi_host_busy);
+
 /**
  * scsi_host_put - dec a Scsi_Host ref count
  * @shost:	Pointer to Scsi_Host to dec.
diff --git a/drivers/scsi/libsas/sas_scsi_host.c b/drivers/scsi/libsas/sas_scsi_host.c
index ceab5e5c41c2..33229348dcb6 100644
--- a/drivers/scsi/libsas/sas_scsi_host.c
+++ b/drivers/scsi/libsas/sas_scsi_host.c
@@ -759,7 +759,7 @@ retry:
 	spin_unlock_irq(shost->host_lock);
 
 	SAS_DPRINTK("Enter %s busy: %d failed: %d\n",
-		    __func__, atomic_read(&shost->host_busy), shost->host_failed);
+		    __func__, scsi_host_busy(shost), shost->host_failed);
 	/*
 	 * Deal with commands that still have SAS tasks (i.e. they didn't
 	 * complete via the normal sas_task completion mechanism),
@@ -801,7 +801,7 @@ out:
 		goto retry;
 
 	SAS_DPRINTK("--- Exit %s: busy: %d failed: %d tries: %d\n",
-		    __func__, atomic_read(&shost->host_busy),
+		    __func__, scsi_host_busy(shost),
 		    shost->host_failed, tries);
 }
 
diff --git a/drivers/scsi/megaraid/megaraid_sas_base.c b/drivers/scsi/megaraid/megaraid_sas_base.c
index e6ba02793610..9aa9590c5373 100644
--- a/drivers/scsi/megaraid/megaraid_sas_base.c
+++ b/drivers/scsi/megaraid/megaraid_sas_base.c
@@ -2834,7 +2834,7 @@ static int megasas_reset_bus_host(struct scsi_cmnd *scmd)
 		"SCSI command pointer: (%p)\t SCSI host state: %d\t"
 		" SCSI host busy: %d\t FW outstanding: %d\n",
 		scmd, scmd->device->host->shost_state,
-		atomic_read((atomic_t *)&scmd->device->host->host_busy),
+		scsi_host_busy(scmd->device->host),
 		atomic_read(&instance->fw_outstanding));
 
 	/*
diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 2053970fc9f8..dc41bd3de08a 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3250,7 +3250,7 @@ _base_recovery_check(struct MPT3SAS_ADAPTER *ioc)
 	 * See _wait_for_commands_to_complete() call with regards to this code.
 	 */
 	if (ioc->shost_recovery && ioc->pending_io_count) {
-		ioc->pending_io_count = atomic_read(&ioc->shost->host_busy);
+		ioc->pending_io_count = scsi_host_busy(ioc->shost);
 		if (ioc->pending_io_count == 0)
 			wake_up(&ioc->reset_wq);
 	}
@@ -6857,7 +6857,7 @@ mpt3sas_wait_for_commands_to_complete(struct MPT3SAS_ADAPTER *ioc)
 		return;
 
 	/* pending command count */
-	ioc->pending_io_count = atomic_read(&ioc->shost->host_busy);
+	ioc->pending_io_count = scsi_host_busy(ioc->shost);
 
 	if (!ioc->pending_io_count)
 		return;
diff --git a/drivers/scsi/qlogicpti.c b/drivers/scsi/qlogicpti.c
index 8578e566ab41..9d09228eee28 100644
--- a/drivers/scsi/qlogicpti.c
+++ b/drivers/scsi/qlogicpti.c
@@ -959,7 +959,7 @@ static inline void update_can_queue(struct Scsi_Host *host, u_int in_ptr, u_int
 	/* Temporary workaround until bug is found and fixed (one bug has been found
 	   already, but fixing it makes things even worse) -jj */
 	int num_free = QLOGICPTI_REQ_QUEUE_LEN - REQ_QUEUE_DEPTH(in_ptr, out_ptr) - 64;
-	host->can_queue = atomic_read(&host->host_busy) + num_free;
+	host->can_queue = scsi_host_busy(host) + num_free;
 	host->sg_tablesize = QLOGICPTI_MAX_SG(num_free);
 }
 
diff --git a/drivers/scsi/scsi.c b/drivers/scsi/scsi.c
index 70ef3c39061d..fc1356d101b0 100644
--- a/drivers/scsi/scsi.c
+++ b/drivers/scsi/scsi.c
@@ -167,7 +167,7 @@ void scsi_log_completion(struct scsi_cmnd *cmd, int disposition)
 			if (level > 3)
 				scmd_printk(KERN_INFO, cmd,
 					    "scsi host busy %d failed %d\n",
-					    atomic_read(&cmd->device->host->host_busy),
+					    scsi_host_busy(cmd->device->host),
 					    cmd->device->host->host_failed);
 		}
 	}
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 8932ae81a15a..6a014fd15fe9 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -66,7 +66,7 @@ void scsi_eh_wakeup(struct Scsi_Host *shost)
 {
 	lockdep_assert_held(shost->host_lock);
 
-	if (atomic_read(&shost->host_busy) == shost->host_failed) {
+	if (scsi_host_busy(shost) == shost->host_failed) {
 		trace_scsi_eh_wakeup(shost);
 		wake_up_process(shost->ehandler);
 		SCSI_LOG_ERROR_RECOVERY(5, shost_printk(KERN_INFO, shost,
@@ -2155,7 +2155,7 @@ int scsi_error_handler(void *data)
 			break;
 
 		if ((shost->host_failed == 0 && shost->host_eh_scheduled == 0) ||
-		    shost->host_failed != atomic_read(&shost->host_busy)) {
+		    shost->host_failed != scsi_host_busy(shost)) {
 			SCSI_LOG_ERROR_RECOVERY(1,
 				shost_printk(KERN_INFO, shost,
 					     "scsi_eh_%d: sleeping\n",
@@ -2170,7 +2170,7 @@ int scsi_error_handler(void *data)
 				     "scsi_eh_%d: waking up %d/%d/%d\n",
 				     shost->host_no, shost->host_eh_scheduled,
 				     shost->host_failed,
-				     atomic_read(&shost->host_busy)));
+				     scsi_host_busy(shost)));
 
 		/*
 		 * We have a host that is failing for some reason.  Figure out
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index 7943b762c12d..de122354d09a 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -382,7 +382,7 @@ static ssize_t
 show_host_busy(struct device *dev, struct device_attribute *attr, char *buf)
 {
 	struct Scsi_Host *shost = class_to_shost(dev);
-	return snprintf(buf, 20, "%d\n", atomic_read(&shost->host_busy));
+	return snprintf(buf, 20, "%d\n", scsi_host_busy(shost));
 }
 static DEVICE_ATTR(host_busy, S_IRUGO, show_host_busy, NULL);
 
diff --git a/include/scsi/scsi_host.h b/include/scsi/scsi_host.h
index 53b485fe9b67..5ea06d310a25 100644
--- a/include/scsi/scsi_host.h
+++ b/include/scsi/scsi_host.h
@@ -758,6 +758,7 @@ extern void scsi_scan_host(struct Scsi_Host *);
 extern void scsi_rescan_device(struct device *);
 extern void scsi_remove_host(struct Scsi_Host *);
 extern struct Scsi_Host *scsi_host_get(struct Scsi_Host *);
+extern int scsi_host_busy(struct Scsi_Host *shost);
 extern void scsi_host_put(struct Scsi_Host *t);
 extern struct Scsi_Host *scsi_host_lookup(unsigned short);
 extern const char *scsi_host_state_name(enum scsi_host_state);
-- 
cgit v1.2.3


From 328728630d9f2bf14b82ca30b5e47489beefe361 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 24 Jun 2018 22:03:27 +0800
Subject: scsi: core: avoid host-wide host_busy counter for scsi_mq

It isn't necessary to check the host depth in scsi_queue_rq() any more
since it has been respected by blk-mq before calling scsi_queue_rq() via
getting driver tag.

Lots of LUNs may attach to same host and per-host IOPS may reach millions,
so we should avoid expensive atomic operations on the host-wide counter in
the IO path.

This patch implements scsi_host_busy() via blk_mq_tagset_busy_iter() for
reading the count of busy IOs for scsi_mq.

It is observed that IOPS is increased by 15% in IO test on scsi_debug (32
LUNs, 32 submit queues, 1024 can_queue, libaio/dio) in a dual-socket
system.

[mkp: clarified commit message]

Cc: Omar Sandoval <osandov@fb.com>,
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>,
Cc: James Bottomley <james.bottomley@hansenpartnership.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: Don Brace <don.brace@microsemi.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hosts.c    | 24 +++++++++++++++++++++++-
 drivers/scsi/scsi_lib.c | 23 +++++++++++++++++------
 2 files changed, 40 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/hosts.c b/drivers/scsi/hosts.c
index ea4b0bb0c1cd..f02dcc875a09 100644
--- a/drivers/scsi/hosts.c
+++ b/drivers/scsi/hosts.c
@@ -563,13 +563,35 @@ struct Scsi_Host *scsi_host_get(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL(scsi_host_get);
 
+struct scsi_host_mq_in_flight {
+	int cnt;
+};
+
+static void scsi_host_check_in_flight(struct request *rq, void *data,
+		bool reserved)
+{
+	struct scsi_host_mq_in_flight *in_flight = data;
+
+	if (blk_mq_request_started(rq))
+		in_flight->cnt++;
+}
+
 /**
  * scsi_host_busy - Return the host busy counter
  * @shost:	Pointer to Scsi_Host to inc.
  **/
 int scsi_host_busy(struct Scsi_Host *shost)
 {
-	return atomic_read(&shost->host_busy);
+	struct scsi_host_mq_in_flight in_flight = {
+		.cnt = 0,
+	};
+
+	if (!shost->use_blk_mq)
+		return atomic_read(&shost->host_busy);
+
+	blk_mq_tagset_busy_iter(&shost->tag_set, scsi_host_check_in_flight,
+			&in_flight);
+	return in_flight.cnt;
 }
 EXPORT_SYMBOL(scsi_host_busy);
 
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index a1a0a2903263..600c78065d62 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -345,7 +345,8 @@ static void scsi_dec_host_busy(struct Scsi_Host *shost)
 	unsigned long flags;
 
 	rcu_read_lock();
-	atomic_dec(&shost->host_busy);
+	if (!shost->use_blk_mq)
+		atomic_dec(&shost->host_busy);
 	if (unlikely(scsi_host_in_recovery(shost))) {
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (shost->host_failed || shost->host_eh_scheduled)
@@ -444,7 +445,12 @@ static inline bool scsi_target_is_busy(struct scsi_target *starget)
 
 static inline bool scsi_host_is_busy(struct Scsi_Host *shost)
 {
-	if (shost->can_queue > 0 &&
+	/*
+	 * blk-mq can handle host queue busy efficiently via host-wide driver
+	 * tag allocation
+	 */
+
+	if (!shost->use_blk_mq && shost->can_queue > 0 &&
 	    atomic_read(&shost->host_busy) >= shost->can_queue)
 		return true;
 	if (atomic_read(&shost->host_blocked) > 0)
@@ -1600,9 +1606,12 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
 	if (scsi_host_in_recovery(shost))
 		return 0;
 
-	busy = atomic_inc_return(&shost->host_busy) - 1;
+	if (!shost->use_blk_mq)
+		busy = atomic_inc_return(&shost->host_busy) - 1;
+	else
+		busy = 0;
 	if (atomic_read(&shost->host_blocked) > 0) {
-		if (busy)
+		if (busy || scsi_host_busy(shost))
 			goto starved;
 
 		/*
@@ -1616,7 +1625,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
 				     "unblocking host at zero depth\n"));
 	}
 
-	if (shost->can_queue > 0 && busy >= shost->can_queue)
+	if (!shost->use_blk_mq && shost->can_queue > 0 && busy >= shost->can_queue)
 		goto starved;
 	if (shost->host_self_blocked)
 		goto starved;
@@ -1702,7 +1711,9 @@ static void scsi_kill_request(struct request *req, struct request_queue *q)
 	 * with the locks as normal issue path does.
 	 */
 	atomic_inc(&sdev->device_busy);
-	atomic_inc(&shost->host_busy);
+
+	if (!shost->use_blk_mq)
+		atomic_inc(&shost->host_busy);
 	if (starget->can_queue > 0)
 		atomic_inc(&starget->target_busy);
 
-- 
cgit v1.2.3


From 0c218e16a8501cfda30f498217b434976cb62fc5 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Tue, 26 Jun 2018 11:47:20 -0500
Subject: scsi: tcmu: Don't pass KERN_ERR to pr_err

Fix warning:

smatch warnings:
drivers/target/target_core_user.c:301 tcmu_genl_cmd_done() warn: KERN_*
level not at start of string

Signed-off-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 95559811d6cc..847707a700cf 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -383,7 +383,7 @@ static int tcmu_genl_cmd_done(struct genl_info *info, int completed_cmd)
 	}
 
 	if (!udev) {
-		pr_err(KERN_ERR "tcmu nl cmd %u/%d completion could not find device with dev id %u.\n",
+		pr_err("tcmu nl cmd %u/%d completion could not find device with dev id %u.\n",
 		       completed_cmd, rc, dev_id);
 		ret = -ENODEV;
 		goto unlock;
-- 
cgit v1.2.3


From cf5d862db2e301b8e487f42f99c5cf6f5228ddae Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Mon, 25 Jun 2018 22:25:36 -0700
Subject: drm/i915/psr: Kill useless function pointers.

At some point we introduced the function pointers
on PSR code to help with VLV/CHV separation logic
because it had a different HW implementation from PSR.

Since all converged to HSW PSR and we dropped the
VLV/CHV support, let's also kill the useless function
pointers and leave the code cleaner.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626052536.15137-1-rodrigo.vivi@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h  |  8 ------
 drivers/gpu/drm/i915/intel_psr.c | 55 +++++++++++++---------------------------
 2 files changed, 18 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6f08ab310118..2b684f431c60 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -631,14 +631,6 @@ struct i915_psr {
 	bool debug;
 	ktime_t last_entry_attempt;
 	ktime_t last_exit;
-
-	void (*enable_source)(struct intel_dp *,
-			      const struct intel_crtc_state *);
-	void (*disable_source)(struct intel_dp *,
-			       const struct intel_crtc_state *);
-	void (*enable_sink)(struct intel_dp *);
-	void (*activate)(struct intel_dp *);
-	void (*setup_vsc)(struct intel_dp *, const struct intel_crtc_state *);
 };
 
 enum intel_pch {
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index f7ae7e33f453..ccaee4a748f2 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -241,8 +241,8 @@ void intel_psr_init_dpcd(struct intel_dp *intel_dp)
 	}
 }
 
-static void hsw_psr_setup_vsc(struct intel_dp *intel_dp,
-			      const struct intel_crtc_state *crtc_state)
+static void intel_psr_setup_vsc(struct intel_dp *intel_dp,
+				const struct intel_crtc_state *crtc_state)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_i915_private *dev_priv = to_i915(intel_dig_port->base.base.dev);
@@ -307,7 +307,7 @@ static void hsw_psr_setup_aux(struct intel_dp *intel_dp)
 	I915_WRITE(EDP_PSR_AUX_CTL, aux_ctl);
 }
 
-static void hsw_psr_enable_sink(struct intel_dp *intel_dp)
+static void intel_psr_enable_sink(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
@@ -419,24 +419,6 @@ static void hsw_activate_psr2(struct intel_dp *intel_dp)
 	I915_WRITE(EDP_PSR2_CTL, val);
 }
 
-static void hsw_psr_activate(struct intel_dp *intel_dp)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_device *dev = dig_port->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	/* On HSW+ after we enable PSR on source it will activate it
-	 * as soon as it match configure idle_frame count. So
-	 * we just actually enable it here on activation time.
-	 */
-
-	/* psr1 and psr2 are mutually exclusive.*/
-	if (dev_priv->psr.psr2_enabled)
-		hsw_activate_psr2(intel_dp);
-	else
-		hsw_activate_psr1(intel_dp);
-}
-
 static bool intel_psr2_config_valid(struct intel_dp *intel_dp,
 				    struct intel_crtc_state *crtc_state)
 {
@@ -546,12 +528,17 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	WARN_ON(dev_priv->psr.active);
 	lockdep_assert_held(&dev_priv->psr.lock);
 
-	dev_priv->psr.activate(intel_dp);
+	/* psr1 and psr2 are mutually exclusive.*/
+	if (dev_priv->psr.psr2_enabled)
+		hsw_activate_psr2(intel_dp);
+	else
+		hsw_activate_psr1(intel_dp);
+
 	dev_priv->psr.active = true;
 }
 
-static void hsw_psr_enable_source(struct intel_dp *intel_dp,
-				  const struct intel_crtc_state *crtc_state)
+static void intel_psr_enable_source(struct intel_dp *intel_dp,
+				    const struct intel_crtc_state *crtc_state)
 {
 	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = dig_port->base.base.dev;
@@ -627,9 +614,9 @@ void intel_psr_enable(struct intel_dp *intel_dp,
 	dev_priv->psr.psr2_enabled = crtc_state->has_psr2;
 	dev_priv->psr.busy_frontbuffer_bits = 0;
 
-	dev_priv->psr.setup_vsc(intel_dp, crtc_state);
-	dev_priv->psr.enable_sink(intel_dp);
-	dev_priv->psr.enable_source(intel_dp, crtc_state);
+	intel_psr_setup_vsc(intel_dp, crtc_state);
+	intel_psr_enable_sink(intel_dp);
+	intel_psr_enable_source(intel_dp, crtc_state);
 	dev_priv->psr.enabled = intel_dp;
 
 	intel_psr_activate(intel_dp);
@@ -638,8 +625,9 @@ unlock:
 	mutex_unlock(&dev_priv->psr.lock);
 }
 
-static void hsw_psr_disable(struct intel_dp *intel_dp,
-			    const struct intel_crtc_state *old_crtc_state)
+static void
+intel_psr_disable_source(struct intel_dp *intel_dp,
+			 const struct intel_crtc_state *old_crtc_state)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
@@ -706,7 +694,7 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 		return;
 	}
 
-	dev_priv->psr.disable_source(intel_dp, old_crtc_state);
+	intel_psr_disable_source(intel_dp, old_crtc_state);
 
 	/* Disable PSR on Sink */
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
@@ -945,11 +933,4 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 
 	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
 	mutex_init(&dev_priv->psr.lock);
-
-	dev_priv->psr.enable_source = hsw_psr_enable_source;
-	dev_priv->psr.disable_source = hsw_psr_disable;
-	dev_priv->psr.enable_sink = hsw_psr_enable_sink;
-	dev_priv->psr.activate = hsw_psr_activate;
-	dev_priv->psr.setup_vsc = hsw_psr_setup_vsc;
-
 }
-- 
cgit v1.2.3


From c12e0643a05d978657877630d4da1ace06ea3720 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@gmail.com>
Date: Sun, 24 Jun 2018 22:47:40 -0700
Subject: drm/i915/psr: Fix race in intel_psr_work()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 5422b37c907e ("drm/i915/psr: Kill delays when activating psr
back.") switched from delayed work to the plain variant and while doing so
removed the check for work_busy() before scheduling a PSR activation.
This appears to cause consecutive executions of psr_activate() in this
scenario - after a worker picks up the PSR work item for execution and
before the work function can acquire the PSR mutex, a psr_flush() can
get hold of the mutex and schedule another PSR work. Without a psr_exit()
between the two psr_activate() calls, warning messages get printed.
Further, since we drop the mutex in the midst of psr_work() to wait for
PSR to idle, another work item can also get scheduled. Fix this by
returning if PSR was already active.

Fixes: 5422b37c907e ("drm/i915/psr: Kill delays when activating psr back.")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106948
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625054741.3919-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index ccaee4a748f2..276070d597e1 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -758,7 +758,7 @@ static void intel_psr_work(struct work_struct *work)
 	 * recheck. Since psr_flush first clears this and then reschedules we
 	 * won't ever miss a flush when bailing out here.
 	 */
-	if (dev_priv->psr.busy_frontbuffer_bits)
+	if (dev_priv->psr.busy_frontbuffer_bits || dev_priv->psr.active)
 		goto unlock;
 
 	intel_psr_activate(dev_priv->psr.enabled);
-- 
cgit v1.2.3


From bcc233b2aa7878bdcfbad6505ac66383a82a73dd Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@gmail.com>
Date: Tue, 26 Jun 2018 02:05:22 -0700
Subject: drm/i915/psr: Warn for erroneous enabling of both PSR1 and PSR2.

Depending whether PSR1 or PSR2 was configured, we print a warning if the
corresponding control mmio indicated PSR was erroneously enabled. As
Chris pointed out, it makes more sense to check for both the mmio's
since we expect neither PSR1 nor PSR2 to be enabled when psr_activate() is
called.

v2: Read PSR2 control register only on supported platforms (Rodrigo)

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626090522.17682-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 276070d597e1..1b439629cb66 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -521,10 +521,9 @@ static void intel_psr_activate(struct intel_dp *intel_dp)
 	struct drm_device *dev = intel_dig_port->base.base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
-	if (dev_priv->psr.psr2_enabled)
+	if (INTEL_GEN(dev_priv) >= 9)
 		WARN_ON(I915_READ(EDP_PSR2_CTL) & EDP_PSR2_ENABLE);
-	else
-		WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
+	WARN_ON(I915_READ(EDP_PSR_CTL) & EDP_PSR_ENABLE);
 	WARN_ON(dev_priv->psr.active);
 	lockdep_assert_held(&dev_priv->psr.lock);
 
-- 
cgit v1.2.3


From 4bc8d55574dd316e43975651b9259c5c18d741fc Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 27 Nov 2017 15:13:56 -0800
Subject: rcu: Add debugging info to assertion

The WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp()) in
rcu_gp_cleanup() triggers (inexplicably, of course) every so often.
This commit therefore extracts more information.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        |  5 ++++-
 kernel/rcu/tree.h        |  2 ++
 kernel/rcu/tree_plugin.h | 38 ++++++++++++++++++++++++++++++++++++--
 3 files changed, 42 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index aa7cade1b9f3..79c7fe978b17 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2084,7 +2084,8 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq_rcu_node(rnp);
-		WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+			dump_blkd_tasks(rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->completed, rsp->gpnum);
 		rdp = this_cpu_ptr(rsp->rda);
@@ -2294,6 +2295,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			return;
 		}
+		rnp->completedqs = rnp->gpnum;
 		mask = rnp->grpmask;
 		if (rnp->parent == NULL) {
 
@@ -3930,6 +3932,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 						   &rcu_fqs_class[i], fqs[i]);
 			rnp->gpnum = rsp->gpnum;
 			rnp->completed = rsp->completed;
+			rnp->completedqs = rsp->completed;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 78e051dffc5b..7365ac53fdd9 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -87,6 +87,7 @@ struct rcu_node {
 	unsigned long completed; /* Last GP completed for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
+	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
 				/*  In leaf rcu_node, each bit corresponds to */
@@ -453,6 +454,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void __init __rcu_init_preempt(void);
+static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 7fd12039e512..17b67ecf7dff 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -260,8 +260,10 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * ->exp_tasks pointers, respectively, to reference the newly
 	 * blocked tasks.
 	 */
-	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD))
+	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
 		rnp->gp_tasks = &t->rcu_node_entry;
+		WARN_ON_ONCE(rnp->completedqs == rnp->gpnum);
+	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
 	WARN_ON_ONCE(!(blkd_state & RCU_GP_BLKD) !=
@@ -535,6 +537,8 @@ void rcu_read_unlock_special(struct task_struct *t)
 		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
+		WARN_ON_ONCE(rnp->completedqs == rnp->gpnum &&
+			     (!empty_norm || rnp->qsmask));
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
 		np = rcu_next_node_entry(t, rnp);
@@ -697,7 +701,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 	struct task_struct *t;
 
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
-	WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp));
+	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
+		dump_blkd_tasks(rnp, 10);
 	if (rcu_preempt_has_tasks(rnp)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
 		t = container_of(rnp->gp_tasks, struct task_struct,
@@ -841,6 +846,27 @@ void exit_rcu(void)
 	__rcu_read_unlock();
 }
 
+/*
+ * Dump the blocked-tasks state, but limit the list dump to the
+ * specified number of elements.
+ */
+static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+{
+	int i;
+	struct list_head *lhp;
+
+	lockdep_assert_held(&rnp->lock);
+	pr_info("%s: grp: %d-%d level: %d ->qamask %#lx ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p &->blkd_tasks: %p offset: %u\n", __func__, rnp->grplo, rnp->grphi, rnp->level, rnp->qsmask, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks, &rnp->blkd_tasks, (unsigned int)offsetof(typeof(*rnp), blkd_tasks));
+	pr_cont("\t->blkd_tasks");
+	i = 0;
+	list_for_each(lhp, &rnp->blkd_tasks) {
+		pr_cont(" %p", lhp);
+		if (++i >= 10)
+			break;
+	}
+	pr_cont("\n");
+}
+
 #else /* #ifdef CONFIG_PREEMPT_RCU */
 
 static struct rcu_state *const rcu_state_p = &rcu_sched_state;
@@ -949,6 +975,14 @@ void exit_rcu(void)
 {
 }
 
+/*
+ * Dump the guaranteed-empty blocked-tasks state.  Trust but verify.
+ */
+static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+{
+	WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
+}
+
 #endif /* #else #ifdef CONFIG_PREEMPT_RCU */
 
 #ifdef CONFIG_RCU_BOOST
-- 
cgit v1.2.3


From ce11fae8d43fe9a36823fbbfe7c44de775b7e346 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Fri, 9 Mar 2018 09:32:18 +0800
Subject: rcu: Use the proper lockdep annotation in dump_blkd_tasks()

Sparse reported this:

| kernel/rcu/tree_plugin.h:814:9: warning: incorrect type in argument 1 (different modifiers)
| kernel/rcu/tree_plugin.h:814:9:    expected struct lockdep_map const *lock
| kernel/rcu/tree_plugin.h:814:9:    got struct lockdep_map [noderef] *<noident>

This is caused by using vanilla lockdep annotations on rcu_node::lock,
and that requires accessing ->lock of rcu_node directly. However we need
to keep rcu_node::lock __private to avoid breaking its extra ordering
guarantee. And we have a dedicated lockdep annotation for
rcu_node::lock, so use it.

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 17b67ecf7dff..e387ea712758 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -855,7 +855,7 @@ static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 	int i;
 	struct list_head *lhp;
 
-	lockdep_assert_held(&rnp->lock);
+	raw_lockdep_assert_held_rcu_node(rnp);
 	pr_info("%s: grp: %d-%d level: %d ->qamask %#lx ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p &->blkd_tasks: %p offset: %u\n", __func__, rnp->grplo, rnp->grphi, rnp->level, rnp->qsmask, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks, &rnp->blkd_tasks, (unsigned int)offsetof(typeof(*rnp), blkd_tasks));
 	pr_cont("\t->blkd_tasks");
 	i = 0;
-- 
cgit v1.2.3


From 8c42b1f39fdf9fde7cfc4024397255f31a860db6 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 9 Apr 2018 11:04:46 -0700
Subject: rcu: Exclude near-simultaneous RCU CPU stall warnings

There is a two-jiffy delay between the time that a CPU will self-report
an RCU CPU stall warning and the time that some other CPU will report a
warning on behalf of the first CPU.  This has worked well in the past,
but on busy systems, it is possible for the two warnings to overlap,
which makes interpreting them extremely difficult.

This commit therefore uses a cmpxchg-based timing decision that
allows only one report in a given one-minute period (assuming default
stall-warning Kconfig parameters).  This approach will of course fail
if you are seeing minute-long vCPU preemption, but in that case the
overlapping RCU CPU stall warnings are the least of your worries.

Reported-by: Dmitry Vyukov <dvyukov@google.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 79c7fe978b17..b1fffa21b9e4 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1368,7 +1368,6 @@ static inline void panic_on_rcu_stall(void)
 static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 {
 	int cpu;
-	long delta;
 	unsigned long flags;
 	unsigned long gpa;
 	unsigned long j;
@@ -1381,18 +1380,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	if (rcu_cpu_stall_suppress)
 		return;
 
-	/* Only let one CPU complain about others per time interval. */
-
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	delta = jiffies - READ_ONCE(rsp->jiffies_stall);
-	if (delta < RCU_STALL_RAT_DELAY || !rcu_gp_in_progress(rsp)) {
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-		return;
-	}
-	WRITE_ONCE(rsp->jiffies_stall,
-		   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-
 	/*
 	 * OK, time to rat on our buddy...
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
@@ -1441,6 +1428,10 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 			sched_show_task(current);
 		}
 	}
+	/* Rewrite if needed in case of slow consoles. */
+	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
+		WRITE_ONCE(rsp->jiffies_stall,
+			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
 
 	rcu_check_gp_kthread_starvation(rsp);
 
@@ -1485,6 +1476,7 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	rcu_dump_cpu_stacks(rsp);
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	/* Rewrite if needed in case of slow consoles. */
 	if (ULONG_CMP_GE(jiffies, READ_ONCE(rsp->jiffies_stall)))
 		WRITE_ONCE(rsp->jiffies_stall,
 			   jiffies + 3 * rcu_jiffies_till_stall_check() + 3);
@@ -1508,6 +1500,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	unsigned long gpnum;
 	unsigned long gps;
 	unsigned long j;
+	unsigned long jn;
 	unsigned long js;
 	struct rcu_node *rnp;
 
@@ -1546,14 +1539,17 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	    ULONG_CMP_GE(gps, js))
 		return; /* No stall or GP completed since entering function. */
 	rnp = rdp->mynode;
+	jn = jiffies + 3 * rcu_jiffies_till_stall_check() + 3;
 	if (rcu_gp_in_progress(rsp) &&
-	    (READ_ONCE(rnp->qsmask) & rdp->grpmask)) {
+	    (READ_ONCE(rnp->qsmask) & rdp->grpmask) &&
+	    cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* We haven't checked in, so go dump stack. */
 		print_cpu_stall(rsp);
 
 	} else if (rcu_gp_in_progress(rsp) &&
-		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY)) {
+		   ULONG_CMP_GE(j, js + RCU_STALL_RAT_DELAY) &&
+		   cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* They had a few time units to dump stack, so complain. */
 		print_other_cpu_stall(rsp, gpnum);
-- 
cgit v1.2.3


From b03799b0cb35dbc39e89602b1203863e2a6e06bf Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 25 Jun 2018 16:49:06 -0500
Subject: PCI: shpchp: Separate existence of SHPC and permission to use it

The shpchp driver registers for all PCI bridge devices.  Its probe method
should fail if either (1) the bridge doesn't have an SHPC or (2) the OS
isn't allowed to use it (the platform firmware may be operating the SHPC
itself).

Separate these two tests into:

  - A new shpc_capable() that looks for the SHPC hardware and is applicable
    on all systems (ACPI and non-ACPI), and

  - A simplified acpi_get_hp_hw_control_from_firmware() that we call only
    when we already know an SHPC exists and there may be ACPI methods to
    either request permission to use it (_OSC) or transfer control to the
    OS (OSHP).

acpi_get_hp_hw_control_from_firmware() is implemented when CONFIG_ACPI=y,
but does nothing if the current platform doesn't support ACPI.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pci/hotplug/acpi_pcihp.c  | 36 +++++++++++++++++++-----------------
 drivers/pci/hotplug/shpchp_core.c | 21 +++++++++++++++++++++
 drivers/pci/pci-acpi.c            | 19 +------------------
 include/linux/pci.h               |  1 +
 4 files changed, 42 insertions(+), 35 deletions(-)

diff --git a/drivers/pci/hotplug/acpi_pcihp.c b/drivers/pci/hotplug/acpi_pcihp.c
index 5bd6c1573295..6b7c1ed58e7e 100644
--- a/drivers/pci/hotplug/acpi_pcihp.c
+++ b/drivers/pci/hotplug/acpi_pcihp.c
@@ -73,20 +73,6 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev)
 	acpi_handle chandle, handle;
 	struct acpi_buffer string = { ACPI_ALLOCATE_BUFFER, NULL };
 
-	/*
-	 * Per PCI firmware specification, we should run the ACPI _OSC
-	 * method to get control of hotplug hardware before using it. If
-	 * an _OSC is missing, we look for an OSHP to do the same thing.
-	 * To handle different BIOS behavior, we look for _OSC on a root
-	 * bridge preferentially (according to PCI fw spec). Later for
-	 * OSHP within the scope of the hotplug controller and its parents,
-	 * up to the host bridge under which this controller exists.
-	 */
-	if (shpchp_is_native(pdev))
-		return 0;
-
-	/* If _OSC exists, we should not evaluate OSHP */
-
 	/*
 	 * If there's no ACPI host bridge (i.e., ACPI support is compiled
 	 * into the kernel but the hardware platform doesn't support ACPI),
@@ -97,9 +83,25 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev)
 	if (!root)
 		return 0;
 
-	if (root->osc_support_set)
-		goto no_control;
+	/*
+	 * If _OSC exists, it determines whether we're allowed to manage
+	 * the SHPC.  We executed it while enumerating the host bridge.
+	 */
+	if (root->osc_support_set) {
+		if (host->native_shpc_hotplug)
+			return 0;
+		return -ENODEV;
+	}
 
+	/*
+	 * In the absence of _OSC, we're always allowed to manage the SHPC.
+	 * However, if an OSHP method is present, we must execute it so the
+	 * firmware can transfer control to the OS, e.g., direct interrupts
+	 * to the OS instead of to the firmware.
+	 *
+	 * N.B. The PCI Firmware Spec (r3.2, sec 4.8) does not endorse
+	 * searching up the ACPI hierarchy, so the loops below are suspect.
+	 */
 	handle = ACPI_HANDLE(&pdev->dev);
 	if (!handle) {
 		/*
@@ -128,7 +130,7 @@ int acpi_get_hp_hw_control_from_firmware(struct pci_dev *pdev)
 		if (ACPI_FAILURE(status))
 			break;
 	}
-no_control:
+
 	pci_info(pdev, "Cannot get control of SHPC hotplug\n");
 	kfree(string.pointer);
 	return -ENODEV;
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index e91be287f292..8e3c6ce12f31 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -270,11 +270,30 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
+static bool shpc_capable(struct pci_dev *bridge)
+{
+	/*
+	 * It is assumed that AMD GOLAM chips support SHPC but they do not
+	 * have SHPC capability.
+	 */
+	if (bridge->vendor == PCI_VENDOR_ID_AMD &&
+	    bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
+		return true;
+
+	if (pci_find_capability(bridge, PCI_CAP_ID_SHPC))
+		return true;
+
+	return false;
+}
+
 static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	int rc;
 	struct controller *ctrl;
 
+	if (!shpc_capable(pdev))
+		return -ENODEV;
+
 	if (acpi_get_hp_hw_control_from_firmware(pdev))
 		return -ENODEV;
 
@@ -303,6 +322,7 @@ static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto err_cleanup_slots;
 
+	pdev->shpc_managed = 1;
 	return 0;
 
 err_cleanup_slots:
@@ -319,6 +339,7 @@ static void shpc_remove(struct pci_dev *dev)
 {
 	struct controller *ctrl = pci_get_drvdata(dev);
 
+	dev->shpc_managed = 0;
 	shpchp_remove_ctrl_files(ctrl);
 	ctrl->hpc_ops->release_ctlr(ctrl);
 	kfree(ctrl);
diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index 65113b6eed14..5100fd2d5a75 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -403,24 +403,7 @@ bool pciehp_is_native(struct pci_dev *bridge)
  */
 bool shpchp_is_native(struct pci_dev *bridge)
 {
-	const struct pci_host_bridge *host;
-
-	if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_SHPC))
-		return false;
-
-	/*
-	 * It is assumed that AMD GOLAM chips support SHPC but they do not
-	 * have SHPC capability.
-	 */
-	if (bridge->vendor == PCI_VENDOR_ID_AMD &&
-	    bridge->device == PCI_DEVICE_ID_AMD_GOLAM_7450)
-		return true;
-
-	if (!pci_find_capability(bridge, PCI_CAP_ID_SHPC))
-		return false;
-
-	host = pci_find_host_bridge(bridge->bus);
-	return host->native_shpc_hotplug;
+	return bridge->shpc_managed;
 }
 
 /**
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..f776a1cce120 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -388,6 +388,7 @@ struct pci_dev {
 	unsigned int	is_virtfn:1;
 	unsigned int	reset_fn:1;
 	unsigned int	is_hotplug_bridge:1;
+	unsigned int	shpc_managed:1;		/* SHPC owned by shpchp */
 	unsigned int	is_thunderbolt:1;	/* Thunderbolt controller */
 	unsigned int	__aer_firmware_first_valid:1;
 	unsigned int	__aer_firmware_first:1;
-- 
cgit v1.2.3


From 42f53ffcad7fcf11b5767767dd0c0ff607d99787 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 26 Jun 2018 13:16:40 -0700
Subject: drm/i915/psr: Remove intel_crtc_state parameter from disable_source()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It was only used in VLV/CHV so after the removal of the PSR support
for those platforms it is not necessary any more.

v7: Rebased

Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626201644.21932-1-jose.souza@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 1b439629cb66..f6d384a11b79 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -625,8 +625,7 @@ unlock:
 }
 
 static void
-intel_psr_disable_source(struct intel_dp *intel_dp,
-			 const struct intel_crtc_state *old_crtc_state)
+intel_psr_disable_source(struct intel_dp *intel_dp)
 {
 	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
 	struct drm_device *dev = intel_dig_port->base.base.dev;
@@ -693,7 +692,7 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 		return;
 	}
 
-	intel_psr_disable_source(intel_dp, old_crtc_state);
+	intel_psr_disable_source(intel_dp);
 
 	/* Disable PSR on Sink */
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
-- 
cgit v1.2.3


From cc3054ff6214f6d14d35ffe629ff8d5032ace7f7 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 26 Jun 2018 13:16:41 -0700
Subject: drm/i915/psr: Begin to handle PSR/PSR2 errors set by sink
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

eDP spec states that sink device will do a short pulse in HPD
line when there is a PSR/PSR2 error that needs to be handled by
source, this is handling the first and most simples error:
DP_PSR_SINK_INTERNAL_ERROR.

Here taking the safest approach and disabling PSR(at least until
the next modeset), to avoid multiple rendering issues due to
bad pannels.

v5:
added lockdep_assert in psr_disable and renamed psr_disable()
to intel_psr_disable_locked()

v4:
Using CAN_PSR instead of HAS_PSR in intel_psr_short_pulse

v3:
disabling PSR instead of exiting on error

Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626201644.21932-2-jose.souza@intel.com
---
 drivers/gpu/drm/i915/intel_dp.c  |  2 ++
 drivers/gpu/drm/i915/intel_drv.h |  1 +
 drivers/gpu/drm/i915/intel_psr.c | 62 +++++++++++++++++++++++++++++++++-------
 3 files changed, 54 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index c1b2f00f324b..5be07e1d816d 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -4491,6 +4491,8 @@ intel_dp_short_pulse(struct intel_dp *intel_dp)
 	if (intel_dp_needs_link_retrain(intel_dp))
 		return false;
 
+	intel_psr_short_pulse(intel_dp);
+
 	if (intel_dp->compliance.test_type == DP_TEST_LINK_TRAINING) {
 		DRM_DEBUG_KMS("Link Training Compliance Test requested\n");
 		/* Send a Hotplug Uevent to userspace to start modeset */
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0be45b75cca2..5a37db292d3a 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1920,6 +1920,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 			      struct intel_crtc_state *crtc_state);
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug);
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir);
+void intel_psr_short_pulse(struct intel_dp *intel_dp);
 
 /* intel_runtime_pm.c */
 int intel_power_domains_init(struct drm_i915_private *);
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index f6d384a11b79..445e97dc791d 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -666,6 +666,25 @@ intel_psr_disable_source(struct intel_dp *intel_dp)
 	}
 }
 
+static void intel_psr_disable_locked(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	lockdep_assert_held(&dev_priv->psr.lock);
+
+	if (!dev_priv->psr.enabled)
+		return;
+
+	intel_psr_disable_source(intel_dp);
+
+	/* Disable PSR on Sink */
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
+
+	dev_priv->psr.enabled = NULL;
+}
+
 /**
  * intel_psr_disable - Disable PSR
  * @intel_dp: Intel DP
@@ -687,17 +706,7 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 		return;
 
 	mutex_lock(&dev_priv->psr.lock);
-	if (!dev_priv->psr.enabled) {
-		mutex_unlock(&dev_priv->psr.lock);
-		return;
-	}
-
-	intel_psr_disable_source(intel_dp);
-
-	/* Disable PSR on Sink */
-	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, 0);
-
-	dev_priv->psr.enabled = NULL;
+	intel_psr_disable_locked(intel_dp);
 	mutex_unlock(&dev_priv->psr.lock);
 	cancel_work_sync(&dev_priv->psr.work);
 }
@@ -932,3 +941,34 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
 	mutex_init(&dev_priv->psr.lock);
 }
+
+void intel_psr_short_pulse(struct intel_dp *intel_dp)
+{
+	struct intel_digital_port *intel_dig_port = dp_to_dig_port(intel_dp);
+	struct drm_device *dev = intel_dig_port->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct i915_psr *psr = &dev_priv->psr;
+	u8 val;
+
+	if (!CAN_PSR(dev_priv) || !intel_dp_is_edp(intel_dp))
+		return;
+
+	mutex_lock(&psr->lock);
+
+	if (psr->enabled != intel_dp)
+		goto exit;
+
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) != 1) {
+		DRM_ERROR("PSR_STATUS dpcd read failed\n");
+		goto exit;
+	}
+
+	if ((val & DP_PSR_SINK_STATE_MASK) == DP_PSR_SINK_INTERNAL_ERROR) {
+		DRM_DEBUG_KMS("PSR sink internal error, disabling PSR\n");
+		intel_psr_disable_locked(intel_dp);
+	}
+
+	/* TODO: handle other PSR/PSR2 errors */
+exit:
+	mutex_unlock(&psr->lock);
+}
-- 
cgit v1.2.3


From 93bf76ed882d5b7c6824e95d868d608f61b4f663 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 26 Jun 2018 13:16:42 -0700
Subject: drm/i915/psr: Handle PSR errors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Sink will interrupt source when it have any PSR error.
DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR is a PSR2 but already
handling it here.
The only missing error to be handled is DP_PSR_LINK_CRC_ERROR that
will be taken in care in a futher patch.

v6:
not handling DP_PSR_LINK_CRC_ERROR here

v5:
handling all PSR errors here, so the commit message and
comment have changed

v3:
disabling PSR instead of exiting on error

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626201644.21932-3-jose.souza@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 445e97dc791d..860b46b72403 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -949,6 +949,8 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp)
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct i915_psr *psr = &dev_priv->psr;
 	u8 val;
+	const u8 errors = DP_PSR_RFB_STORAGE_ERROR |
+			  DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR;
 
 	if (!CAN_PSR(dev_priv) || !intel_dp_is_edp(intel_dp))
 		return;
@@ -968,7 +970,25 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp)
 		intel_psr_disable_locked(intel_dp);
 	}
 
-	/* TODO: handle other PSR/PSR2 errors */
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_ERROR_STATUS, &val) != 1) {
+		DRM_ERROR("PSR_ERROR_STATUS dpcd read failed\n");
+		goto exit;
+	}
+
+	if (val & DP_PSR_RFB_STORAGE_ERROR)
+		DRM_DEBUG_KMS("PSR RFB storage error, disabling PSR\n");
+	if (val & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
+		DRM_DEBUG_KMS("PSR VSC SDP uncorrectable error, disabling PSR\n");
+
+	if (val & ~errors)
+		DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n",
+			  val & ~errors);
+	if (val & errors)
+		intel_psr_disable_locked(intel_dp);
+	/* clear status register */
+	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_ERROR_STATUS, val);
+
+	/* TODO: handle PSR2 errors */
 exit:
 	mutex_unlock(&psr->lock);
 }
-- 
cgit v1.2.3


From 3ebe3df50bb1db45c7bf1ce90c3d61c4eed1ba84 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 26 Jun 2018 13:16:43 -0700
Subject: drm/i915/psr: Avoid PSR exit max time timeout
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Specification requires that max time should be masked from bdw and
forward but it can be also safely enabled to hsw.
This will make PSR exits more deterministic and only when really
needed. If this was used to fix a issue in some panel than can
only self-refresh for a few seconds, that panel will interrupt
and assert one of the PSR errors handled in:
'drm/i915/psr: Handle PSR RFB storage error' and
'drm/i915/psr: Begin to handle PSR/PSR2 errors set by sink'

Spec: 21664

v4:
patch moved to before 'drm/i915/psr/bdw+: Enable CRC check in the
static frame on the sink side' to avoid touch in 2 patches
EDP_PSR_DEBUG.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626201644.21932-4-jose.souza@intel.com
---
 drivers/gpu/drm/i915/intel_psr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 860b46b72403..aa98b62910b4 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -579,7 +579,8 @@ static void intel_psr_enable_source(struct intel_dp *intel_dp,
 			   EDP_PSR_DEBUG_MASK_MEMUP |
 			   EDP_PSR_DEBUG_MASK_HPD |
 			   EDP_PSR_DEBUG_MASK_LPSP |
-			   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE);
+			   EDP_PSR_DEBUG_MASK_DISP_REG_WRITE |
+			   EDP_PSR_DEBUG_MASK_MAX_SLEEP);
 	}
 }
 
-- 
cgit v1.2.3


From 00c8f19463ab42d22332fc9c9fca605f12eadeb7 Mon Sep 17 00:00:00 2001
From: José Roberto de Souza <jose.souza@intel.com>
Date: Tue, 26 Jun 2018 13:16:44 -0700
Subject: drm/i915/psr: Enable CRC check in the static frame on the sink side
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Sink can be configured to calculate the CRC over the static frame and
compare with the CRC calculated and transmited in the VSC SDP by
source, if there is a mismatch sink will do a short pulse in HPD
and set DP_PSR_LINK_CRC_ERROR in DP_PSR_ERROR_STATUS.

Spec: 7723

v6:
andling DP_PSR_LINK_CRC_ERROR here and remove "bdw+" from commit
message

v4:
patch moved to after 'drm/i915/psr: Avoid PSR exit max time timeout'
to avoid touch in 2 patches EDP_PSR_DEBUG.

v3:
disabling PSR instead of exiting on error

Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626201644.21932-5-jose.souza@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h  |  1 +
 drivers/gpu/drm/i915/intel_psr.c | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index caad19f5f557..43db91c19f52 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4044,6 +4044,7 @@ enum {
 #define   EDP_PSR_SKIP_AUX_EXIT			(1 << 12)
 #define   EDP_PSR_TP1_TP2_SEL			(0 << 11)
 #define   EDP_PSR_TP1_TP3_SEL			(1 << 11)
+#define   EDP_PSR_CRC_ENABLE			(1 << 10) /* BDW+ */
 #define   EDP_PSR_TP2_TP3_TIME_500us		(0 << 8)
 #define   EDP_PSR_TP2_TP3_TIME_100us		(1 << 8)
 #define   EDP_PSR_TP2_TP3_TIME_2500us		(2 << 8)
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index aa98b62910b4..45f1cb7d6c04 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -323,6 +323,8 @@ static void intel_psr_enable_sink(struct intel_dp *intel_dp)
 
 	if (dev_priv->psr.link_standby)
 		dpcd_val |= DP_PSR_MAIN_LINK_ACTIVE;
+	if (!dev_priv->psr.psr2_enabled && INTEL_GEN(dev_priv) >= 8)
+		dpcd_val |= DP_PSR_CRC_VERIFICATION;
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_PSR_EN_CFG, dpcd_val);
 
 	drm_dp_dpcd_writeb(&intel_dp->aux, DP_SET_POWER, DP_SET_POWER_D0);
@@ -378,6 +380,9 @@ static void hsw_activate_psr1(struct intel_dp *intel_dp)
 	else
 		val |= EDP_PSR_TP1_TP2_SEL;
 
+	if (INTEL_GEN(dev_priv) >= 8)
+		val |= EDP_PSR_CRC_ENABLE;
+
 	val |= I915_READ(EDP_PSR_CTL) & EDP_PSR_RESTORE_PSR_ACTIVE_CTX_MASK;
 	I915_WRITE(EDP_PSR_CTL, val);
 }
@@ -951,7 +956,8 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp)
 	struct i915_psr *psr = &dev_priv->psr;
 	u8 val;
 	const u8 errors = DP_PSR_RFB_STORAGE_ERROR |
-			  DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR;
+			  DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR |
+			  DP_PSR_LINK_CRC_ERROR;
 
 	if (!CAN_PSR(dev_priv) || !intel_dp_is_edp(intel_dp))
 		return;
@@ -980,6 +986,8 @@ void intel_psr_short_pulse(struct intel_dp *intel_dp)
 		DRM_DEBUG_KMS("PSR RFB storage error, disabling PSR\n");
 	if (val & DP_PSR_VSC_SDP_UNCORRECTABLE_ERROR)
 		DRM_DEBUG_KMS("PSR VSC SDP uncorrectable error, disabling PSR\n");
+	if (val & DP_PSR_LINK_CRC_ERROR)
+		DRM_ERROR("PSR Link CRC error, disabling PSR\n");
 
 	if (val & ~errors)
 		DRM_ERROR("PSR_ERROR_STATUS unhandled errors %x\n",
-- 
cgit v1.2.3


From 3463e51dc337ddd6e608fd595130398e9c60680f Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Mon, 25 Jun 2018 16:55:05 -0700
Subject: net/tls: Remove VLA usage on nonce

It looks like the prior VLA removal, commit b16520f7493d ("net/tls: Remove
VLA usage"), and a new VLA addition, commit c46234ebb4d1e ("tls: RX path
for ktls"), passed in the night. This removes the newly added VLA, which
happens to have its bounds based on the same max value.

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 727433b37bb5..173d8b89072d 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -941,7 +941,7 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(strp->sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
-	char header[tls_ctx->rx.prepend_size];
+	char header[TLS_HEADER_SIZE + MAX_IV_SIZE];
 	struct strp_msg *rxm = strp_msg(skb);
 	size_t cipher_overhead;
 	size_t data_len = 0;
@@ -951,6 +951,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
 	if (rxm->offset + tls_ctx->rx.prepend_size > skb->len)
 		return 0;
 
+	/* Sanity-check size of on-stack buffer. */
+	if (WARN_ON(tls_ctx->rx.prepend_size > sizeof(header))) {
+		ret = -EINVAL;
+		goto read_failure;
+	}
+
 	/* Linearize header to local buffer */
 	ret = skb_copy_bits(skb, rxm->offset, header, tls_ctx->rx.prepend_size);
 
@@ -1108,7 +1114,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	}
 
 	/* Sanity-check the IV size for stack allocations. */
-	if (iv_size > MAX_IV_SIZE) {
+	if (iv_size > MAX_IV_SIZE || nonce_size > MAX_IV_SIZE) {
 		rc = -EINVAL;
 		goto free_priv;
 	}
-- 
cgit v1.2.3


From b2c478723c7f8fa78d4fbdb9d7de4191249b92e0 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 26 Jun 2018 02:06:06 +0200
Subject: selftests: forwarding: Move multipath_eval() to lib.sh

This function will be useful for the GRE multipath test that is coming
later.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh      | 39 ++++++++++++++++++++++
 .../selftests/net/forwarding/router_multipath.sh   | 39 ----------------------
 2 files changed, 39 insertions(+), 39 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 7b18a53aa556..7fae805147ae 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -557,6 +557,45 @@ tests_run()
 	done
 }
 
+multipath_eval()
+{
+       local desc="$1"
+       local weight_rp12=$2
+       local weight_rp13=$3
+       local packets_rp12=$4
+       local packets_rp13=$5
+       local weights_ratio packets_ratio diff
+
+       RET=0
+
+       if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
+              check_err 1 "Packet difference is 0"
+              log_test "Multipath"
+              log_info "Expected ratio $weights_ratio"
+              return
+       fi
+
+       if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
+               weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
+		       | bc -l)
+               packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
+		       | bc -l)
+       else
+               weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \
+		       bc -l)
+               packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \
+		       bc -l)
+       fi
+
+       diff=$(echo $weights_ratio - $packets_ratio | bc -l)
+       diff=${diff#-}
+
+       test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
+       check_err $? "Too large discrepancy between expected and measured ratios"
+       log_test "$desc"
+       log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
+}
+
 ##############################################################################
 # Tests
 
diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh
index 8b6d0fb6d604..79a209927962 100755
--- a/tools/testing/selftests/net/forwarding/router_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/router_multipath.sh
@@ -159,45 +159,6 @@ router2_destroy()
 	vrf_destroy "vrf-r2"
 }
 
-multipath_eval()
-{
-       local desc="$1"
-       local weight_rp12=$2
-       local weight_rp13=$3
-       local packets_rp12=$4
-       local packets_rp13=$5
-       local weights_ratio packets_ratio diff
-
-       RET=0
-
-       if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
-              check_err 1 "Packet difference is 0"
-              log_test "Multipath"
-              log_info "Expected ratio $weights_ratio"
-              return
-       fi
-
-       if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
-               weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
-		       | bc -l)
-               packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
-		       | bc -l)
-       else
-               weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \
-		       bc -l)
-               packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \
-		       bc -l)
-       fi
-
-       diff=$(echo $weights_ratio - $packets_ratio | bc -l)
-       diff=${diff#-}
-
-       test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
-       check_err $? "Too large discrepancy between expected and measured ratios"
-       log_test "$desc"
-       log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
-}
-
 multipath4_test()
 {
        local desc="$1"
-- 
cgit v1.2.3


From 1b86fa3bbacef0a8e9961257557801ab1b5bef78 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 26 Jun 2018 02:07:08 +0200
Subject: selftests: forwarding: multipath_eval(): Improve style

- Change the indentation of the function body from 7 spaces to one tab.
- Move initialization of weights_ratio up so that it can be referenced
  from the error message about packet difference being zero.
- Move |'s consistently to continuation line, which reindent.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 74 ++++++++++++++-------------
 1 file changed, 39 insertions(+), 35 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 7fae805147ae..911d753c4ff0 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -559,41 +559,45 @@ tests_run()
 
 multipath_eval()
 {
-       local desc="$1"
-       local weight_rp12=$2
-       local weight_rp13=$3
-       local packets_rp12=$4
-       local packets_rp13=$5
-       local weights_ratio packets_ratio diff
-
-       RET=0
-
-       if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
-              check_err 1 "Packet difference is 0"
-              log_test "Multipath"
-              log_info "Expected ratio $weights_ratio"
-              return
-       fi
-
-       if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
-               weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
-		       | bc -l)
-               packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
-		       | bc -l)
-       else
-               weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" | \
-		       bc -l)
-               packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" | \
-		       bc -l)
-       fi
-
-       diff=$(echo $weights_ratio - $packets_ratio | bc -l)
-       diff=${diff#-}
-
-       test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
-       check_err $? "Too large discrepancy between expected and measured ratios"
-       log_test "$desc"
-       log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
+	local desc="$1"
+	local weight_rp12=$2
+	local weight_rp13=$3
+	local packets_rp12=$4
+	local packets_rp13=$5
+	local weights_ratio packets_ratio diff
+
+	RET=0
+
+	if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
+		weights_ratio=$(echo "scale=2; $weight_rp12 / $weight_rp13" \
+				| bc -l)
+	else
+		weights_ratio=$(echo "scale=2; $weight_rp13 / $weight_rp12" \
+				| bc -l)
+	fi
+
+	if [[ "$packets_rp12" -eq "0" || "$packets_rp13" -eq "0" ]]; then
+	       check_err 1 "Packet difference is 0"
+	       log_test "Multipath"
+	       log_info "Expected ratio $weights_ratio"
+	       return
+	fi
+
+	if [[ "$weight_rp12" -gt "$weight_rp13" ]]; then
+		packets_ratio=$(echo "scale=2; $packets_rp12 / $packets_rp13" \
+				| bc -l)
+	else
+		packets_ratio=$(echo "scale=2; $packets_rp13 / $packets_rp12" \
+				| bc -l)
+	fi
+
+	diff=$(echo $weights_ratio - $packets_ratio | bc -l)
+	diff=${diff#-}
+
+	test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0
+	check_err $? "Too large discrepancy between expected and measured ratios"
+	log_test "$desc"
+	log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio"
 }
 
 ##############################################################################
-- 
cgit v1.2.3


From a66d62d84225e1c2debaa238cff07a7df86c5aa8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 26 Jun 2018 02:07:45 +0200
Subject: selftests: forwarding: tc_rule_stats_get: Parameterize direction

The GRE multipath tests need stats on an egress counter. Change
tc_rule_stats_get() to take direction as an optional argument, with
default of ingress.

Take the opportunity to change line continuation character from | to \.
Move the | to the next line, which indent.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 911d753c4ff0..f94ea4bafa13 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -383,9 +383,10 @@ tc_rule_stats_get()
 {
 	local dev=$1; shift
 	local pref=$1; shift
+	local dir=$1; shift
 
-	tc -j -s filter show dev $dev ingress pref $pref |
-	jq '.[1].options.actions[].stats.packets'
+	tc -j -s filter show dev $dev ${dir:-ingress} pref $pref \
+	    | jq '.[1].options.actions[].stats.packets'
 }
 
 mac_get()
-- 
cgit v1.2.3


From 3368b22379d67a92b0da8f2a76a6f0764177601d Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 26 Jun 2018 02:08:00 +0200
Subject: selftests: forwarding: lib: Extract interface-init functions

The function simple_if_init() does two things: it creates a VRF, then
moves an interface into this VRF and configures addresses. The latter
comes in handy when adding more interfaces into a VRF later on. The
situation is similar for simple_if_fini().

Therefore split the interface remastering and address de/initialization
logic to a new pair of helpers __simple_if_init() / __simple_if_fini(),
and defer to these helpers from simple_if_init() and simple_if_fini().

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 32 +++++++++++++++++++++------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index f94ea4bafa13..1dfdf14894e2 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -287,6 +287,29 @@ __addr_add_del()
 	done
 }
 
+__simple_if_init()
+{
+	local if_name=$1; shift
+	local vrf_name=$1; shift
+	local addrs=("${@}")
+
+	ip link set dev $if_name master $vrf_name
+	ip link set dev $if_name up
+
+	__addr_add_del $if_name add "${addrs[@]}"
+}
+
+__simple_if_fini()
+{
+	local if_name=$1; shift
+	local addrs=("${@}")
+
+	__addr_add_del $if_name del "${addrs[@]}"
+
+	ip link set dev $if_name down
+	ip link set dev $if_name nomaster
+}
+
 simple_if_init()
 {
 	local if_name=$1
@@ -298,11 +321,8 @@ simple_if_init()
 	array=("${@}")
 
 	vrf_create $vrf_name
-	ip link set dev $if_name master $vrf_name
 	ip link set dev $vrf_name up
-	ip link set dev $if_name up
-
-	__addr_add_del $if_name add "${array[@]}"
+	__simple_if_init $if_name $vrf_name "${array[@]}"
 }
 
 simple_if_fini()
@@ -315,9 +335,7 @@ simple_if_fini()
 	vrf_name=v$if_name
 	array=("${@}")
 
-	__addr_add_del $if_name del "${array[@]}"
-
-	ip link set dev $if_name down
+	__simple_if_fini $if_name "${array[@]}"
 	vrf_destroy $vrf_name
 }
 
-- 
cgit v1.2.3


From 54818c4c4b9379f942db7d19e5ff23fb08f6bc79 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 26 Jun 2018 02:08:05 +0200
Subject: selftests: forwarding: Test multipath tunneling

Add a GRE-tunneling test such that there are two tunnels involved, with
a multipath route listing both as next hops. Similarly to
router_multipath.sh, test that the distribution of traffic to the
tunnels honors the configured weights.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/gre_multipath.sh      | 354 +++++++++++++++++++++
 1 file changed, 354 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/gre_multipath.sh

diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh
new file mode 100755
index 000000000000..982cc8c23200
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh
@@ -0,0 +1,354 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test traffic distribution when a wECMP route forwards traffic to two GRE
+# tunnels.
+#
+# +-------------------------+
+# | H1                      |
+# |               $h1 +     |
+# |      192.0.2.1/28 |     |
+# |  2001:db8:1::1/64 |     |
+# +-------------------|-----+
+#                     |
+# +-------------------|------------------------+
+# | SW1               |                        |
+# |              $ol1 +                        |
+# |      192.0.2.2/28                          |
+# |  2001:db8:1::2/64                          |
+# |                                            |
+# |  + g1a (gre)          + g1b (gre)          |
+# |    loc=192.0.2.65       loc=192.0.2.81     |
+# |    rem=192.0.2.66 --.   rem=192.0.2.82 --. |
+# |    tos=inherit      |   tos=inherit      | |
+# |  .------------------'                    | |
+# |  |                    .------------------' |
+# |  v                    v                    |
+# |  + $ul1.111 (vlan)    + $ul1.222 (vlan)    |
+# |  | 192.0.2.129/28     | 192.0.2.145/28     |
+# |   \                  /                     |
+# |    \________________/                      |
+# |            |                               |
+# |            + $ul1                          |
+# +------------|-------------------------------+
+#              |
+# +------------|-------------------------------+
+# | SW2        + $ul2                          |
+# |     _______|________                       |
+# |    /                \                      |
+# |   /                  \                     |
+# |  + $ul2.111 (vlan)    + $ul2.222 (vlan)    |
+# |  ^ 192.0.2.130/28     ^ 192.0.2.146/28     |
+# |  |                    |                    |
+# |  |                    '------------------. |
+# |  '------------------.                    | |
+# |  + g2a (gre)        | + g2b (gre)        | |
+# |    loc=192.0.2.66   |   loc=192.0.2.82   | |
+# |    rem=192.0.2.65 --'   rem=192.0.2.81 --' |
+# |    tos=inherit          tos=inherit        |
+# |                                            |
+# |              $ol2 +                        |
+# |     192.0.2.17/28 |                        |
+# |  2001:db8:2::1/64 |                        |
+# +-------------------|------------------------+
+#                     |
+# +-------------------|-----+
+# | H2                |     |
+# |               $h2 +     |
+# |     192.0.2.18/28       |
+# |  2001:db8:2::2/64       |
+# +-------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	ping_ipv6
+	multipath_ipv4
+	multipath_ipv6
+	multipath_ipv6_l4
+"
+
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
+	ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+}
+
+h1_destroy()
+{
+	ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
+	ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+sw1_create()
+{
+	simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+	__simple_if_init $ul1 v$ol1
+	vlan_create $ul1 111 v$ol1 192.0.2.129/28
+	vlan_create $ul1 222 v$ol1 192.0.2.145/28
+
+	tunnel_create g1a gre 192.0.2.65 192.0.2.66 tos inherit dev v$ol1
+	__simple_if_init g1a v$ol1 192.0.2.65/32
+	ip route add vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+
+	tunnel_create g1b gre 192.0.2.81 192.0.2.82 tos inherit dev v$ol1
+	__simple_if_init g1b v$ol1 192.0.2.81/32
+	ip route add vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+
+	ip route add vrf v$ol1 192.0.2.16/28 \
+	   nexthop dev g1a \
+	   nexthop dev g1b
+	ip route add vrf v$ol1 2001:db8:2::/64 \
+	   nexthop dev g1a \
+	   nexthop dev g1b
+
+	tc qdisc add dev $ul1 clsact
+	tc filter add dev $ul1 egress pref 111 prot 802.1q \
+	   flower vlan_id 111 action pass
+	tc filter add dev $ul1 egress pref 222 prot 802.1q \
+	   flower vlan_id 222 action pass
+}
+
+sw1_destroy()
+{
+	tc qdisc del dev $ul1 clsact
+
+	ip route del vrf v$ol1 2001:db8:2::/64
+	ip route del vrf v$ol1 192.0.2.16/28
+
+	ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
+	__simple_if_fini g1b 192.0.2.81/32
+	tunnel_destroy g1b
+
+	ip route del vrf v$ol1 192.0.2.66/32 via 192.0.2.130
+	__simple_if_fini g1a 192.0.2.65/32
+	tunnel_destroy g1a
+
+	vlan_destroy $ul1 222
+	vlan_destroy $ul1 111
+	__simple_if_fini $ul1
+	simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+}
+
+sw2_create()
+{
+	simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+	__simple_if_init $ul2 v$ol2
+	vlan_create $ul2 111 v$ol2 192.0.2.130/28
+	vlan_create $ul2 222 v$ol2 192.0.2.146/28
+
+	tunnel_create g2a gre 192.0.2.66 192.0.2.65 tos inherit dev v$ol2
+	__simple_if_init g2a v$ol2 192.0.2.66/32
+	ip route add vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+
+	tunnel_create g2b gre 192.0.2.82 192.0.2.81 tos inherit dev v$ol2
+	__simple_if_init g2b v$ol2 192.0.2.82/32
+	ip route add vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+
+	ip route add vrf v$ol2 192.0.2.0/28 \
+	   nexthop dev g2a \
+	   nexthop dev g2b
+	ip route add vrf v$ol2 2001:db8:1::/64 \
+	   nexthop dev g2a \
+	   nexthop dev g2b
+}
+
+sw2_destroy()
+{
+	ip route del vrf v$ol2 2001:db8:1::/64
+	ip route del vrf v$ol2 192.0.2.0/28
+
+	ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
+	__simple_if_fini g2b 192.0.2.82/32
+	tunnel_destroy g2b
+
+	ip route del vrf v$ol2 192.0.2.65/32 via 192.0.2.129
+	__simple_if_fini g2a 192.0.2.66/32
+	tunnel_destroy g2a
+
+	vlan_destroy $ul2 222
+	vlan_destroy $ul2 111
+	__simple_if_fini $ul2
+	simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+	ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+}
+
+h2_destroy()
+{
+	ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
+	ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	ol1=${NETIFS[p2]}
+
+	ul1=${NETIFS[p3]}
+	ul2=${NETIFS[p4]}
+
+	ol2=${NETIFS[p5]}
+	h2=${NETIFS[p6]}
+
+	vrf_prepare
+	h1_create
+	sw1_create
+	sw2_create
+	h2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	sw2_destroy
+	sw1_destroy
+	h1_destroy
+	vrf_cleanup
+}
+
+multipath4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv4.fib_multipath_hash_policy 1
+	ip route replace vrf v$ol1 192.0.2.16/28 \
+	   nexthop dev g1a weight $weight1 \
+	   nexthop dev g1b weight $weight2
+
+	local t0_111=$(tc_rule_stats_get $ul1 111 egress)
+	local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+
+	ip vrf exec v$h1 \
+	   $MZ $h1 -q -p 64 -A 192.0.2.1 -B 192.0.2.18 \
+	       -d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul1 111 egress)
+	local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip route replace vrf v$ol1 192.0.2.16/28 \
+	   nexthop dev g1a \
+	   nexthop dev g1b
+	sysctl_restore net.ipv4.fib_multipath_hash_policy
+}
+
+multipath6_l4_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	sysctl_set net.ipv6.fib_multipath_hash_policy 1
+	ip route replace vrf v$ol1 2001:db8:2::/64 \
+	   nexthop dev g1a weight $weight1 \
+	   nexthop dev g1b weight $weight2
+
+	local t0_111=$(tc_rule_stats_get $ul1 111 egress)
+	local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+
+	ip vrf exec v$h1 \
+	   $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
+	       -d 1msec -t udp "sp=1024,dp=0-32768"
+
+	local t1_111=$(tc_rule_stats_get $ul1 111 egress)
+	local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip route replace vrf v$ol1 2001:db8:2::/64 \
+	   nexthop dev g1a \
+	   nexthop dev g1b
+	sysctl_restore net.ipv6.fib_multipath_hash_policy
+}
+
+multipath6_test()
+{
+	local what=$1; shift
+	local weight1=$1; shift
+	local weight2=$1; shift
+
+	ip route replace vrf v$ol1 2001:db8:2::/64 \
+	   nexthop dev g1a weight $weight1 \
+	   nexthop dev g1b weight $weight2
+
+	local t0_111=$(tc_rule_stats_get $ul1 111 egress)
+	local t0_222=$(tc_rule_stats_get $ul1 222 egress)
+
+        # Generate 16384 echo requests, each with a random flow label.
+	for ((i=0; i < 16384; ++i)); do
+		ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
+	done
+
+	local t1_111=$(tc_rule_stats_get $ul1 111 egress)
+	local t1_222=$(tc_rule_stats_get $ul1 222 egress)
+
+	local d111=$((t1_111 - t0_111))
+	local d222=$((t1_222 - t0_222))
+	multipath_eval "$what" $weight1 $weight2 $d111 $d222
+
+	ip route replace vrf v$ol1 2001:db8:2::/64 \
+	   nexthop dev g1a \
+	   nexthop dev g1b
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.18
+}
+
+ping_ipv6()
+{
+	ping6_test $h1 2001:db8:2::2
+}
+
+multipath_ipv4()
+{
+	log_info "Running IPv4 multipath tests"
+	multipath4_test "ECMP" 1 1
+	multipath4_test "Weighted MP 2:1" 2 1
+	multipath4_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6()
+{
+	log_info "Running IPv6 multipath tests"
+	multipath6_test "ECMP" 1 1
+	multipath6_test "Weighted MP 2:1" 2 1
+	multipath6_test "Weighted MP 11:45" 11 45
+}
+
+multipath_ipv6_l4()
+{
+	log_info "Running IPv6 L4 hash multipath tests"
+	multipath6_l4_test "ECMP" 1 1
+	multipath6_l4_test "Weighted MP 2:1" 2 1
+	multipath6_l4_test "Weighted MP 11:45" 11 45
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 18ec44f6effbd7bd6f7ec95e8ccd324b05219224 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 26 Jun 2018 02:08:17 +0200
Subject: selftests: forwarding: README: Require diagrams

ASCII art diagrams are well suited for presenting the topology that a
test uses while being easy to embed directly in the test file iteslf.
They make the information very easy to grasp even for simple topologies,
and for more complex ones they are almost essential, as figuring out the
interconnects from the script itself proves to be difficult.

Therefore state the requirement for topology ASCII art in README.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/README | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README
index 4a0964c42860..b8a2af8fcfb7 100644
--- a/tools/testing/selftests/net/forwarding/README
+++ b/tools/testing/selftests/net/forwarding/README
@@ -46,6 +46,8 @@ Guidelines for Writing Tests
 
 o Where possible, reuse an existing topology for different tests instead
   of recreating the same topology.
+o Tests that use anything but the most trivial topologies should include
+  an ASCII art showing the topology.
 o Where possible, IPv6 and IPv4 addresses shall conform to RFC 3849 and
   RFC 5737, respectively.
 o Where possible, tests shall be written so that they can be reused by
-- 
cgit v1.2.3


From 8e326289e3069dfc9fa9c209924668dd031ab8ef Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Mon, 25 Jun 2018 20:32:53 -0700
Subject: neighbour: force neigh_invalidate when NUD_FAILED update is from
 admin

In systems where neigh gc thresh holds are set to high values,
admin deleted neigh entries (eg ip neigh flush or ip neigh del) can
linger around in NUD_FAILED state for a long time until periodic gc kicks
in. This patch forces neigh_invalidate when NUD_FAILED neigh_update is
from an admin.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/neighbour.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 8e3fda9e725c..cbe85d8d4cc2 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -1148,7 +1148,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new,
 		neigh->nud_state = new;
 		err = 0;
 		notify = old & NUD_VALID;
-		if ((old & (NUD_INCOMPLETE | NUD_PROBE)) &&
+		if (((old & (NUD_INCOMPLETE | NUD_PROBE)) ||
+		     (flags & NEIGH_UPDATE_F_ADMIN)) &&
 		    (new & NUD_FAILED)) {
 			neigh_invalidate(neigh);
 			notify = 1;
-- 
cgit v1.2.3


From cc0dff6dc3b44e33cd6b935893db66563ef15ba0 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Tue, 26 Jun 2018 19:48:52 -0700
Subject: nfp: bpf: allow source ptr type be map ptr in memcpy optimization

Map read has been supported on NFP, this patch enables optimization
for memcpy from map to packet.

This patch also fixed one latent bug which will cause copying from
unexpected address once memcpy for map pointer enabled.  The fixed
code path was not exercised before.

Reported-by: Mary Pham <mary.pham@netronome.com>
Reported-by: David Beckett <david.beckett@netronome.com>
Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 8a92088df0d7..33111739b210 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -670,7 +670,7 @@ static int nfp_cpp_memcpy(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	xfer_num = round_up(len, 4) / 4;
 
 	if (src_40bit_addr)
-		addr40_offset(nfp_prog, meta->insn.src_reg, off, &src_base,
+		addr40_offset(nfp_prog, meta->insn.src_reg * 2, off, &src_base,
 			      &off);
 
 	/* Setup PREV_ALU fields to override memory read length. */
@@ -3299,7 +3299,8 @@ curr_pair_is_memcpy(struct nfp_insn_meta *ld_meta,
 	if (!is_mbpf_load(ld_meta) || !is_mbpf_store(st_meta))
 		return false;
 
-	if (ld_meta->ptr.type != PTR_TO_PACKET)
+	if (ld_meta->ptr.type != PTR_TO_PACKET &&
+	    ld_meta->ptr.type != PTR_TO_MAP_VALUE)
 		return false;
 
 	if (st_meta->ptr.type != PTR_TO_PACKET)
-- 
cgit v1.2.3


From 22adedd304668f0a2001284ddf225b49e9c05c64 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Mon, 25 Jun 2018 14:25:02 +0200
Subject: trace_helpers.c: Add helpers to poll multiple perf FDs for events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add two new helper functions to trace_helpers that supports polling
multiple perf file descriptors for events. These are used to the XDP
perf_event_output example, which needs to work with one perf fd per CPU.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/trace_helpers.c | 48 +++++++++++++++++++++++++++--
 tools/testing/selftests/bpf/trace_helpers.h |  4 +++
 2 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c
index 3868dcb63420..cabe2a3a3b30 100644
--- a/tools/testing/selftests/bpf/trace_helpers.c
+++ b/tools/testing/selftests/bpf/trace_helpers.c
@@ -88,7 +88,7 @@ static int page_size;
 static int page_cnt = 8;
 static struct perf_event_mmap_page *header;
 
-int perf_event_mmap(int fd)
+int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header)
 {
 	void *base;
 	int mmap_size;
@@ -102,10 +102,15 @@ int perf_event_mmap(int fd)
 		return -1;
 	}
 
-	header = base;
+	*header = base;
 	return 0;
 }
 
+int perf_event_mmap(int fd)
+{
+	return perf_event_mmap_header(fd, &header);
+}
+
 static int perf_event_poll(int fd)
 {
 	struct pollfd pfd = { .fd = fd, .events = POLLIN };
@@ -163,3 +168,42 @@ int perf_event_poller(int fd, perf_event_print_fn output_fn)
 
 	return ret;
 }
+
+int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers,
+			    int num_fds, perf_event_print_fn output_fn)
+{
+	enum bpf_perf_event_ret ret;
+	struct pollfd *pfds;
+	void *buf = NULL;
+	size_t len = 0;
+	int i;
+
+	pfds = calloc(num_fds, sizeof(*pfds));
+	if (!pfds)
+		return LIBBPF_PERF_EVENT_ERROR;
+
+	for (i = 0; i < num_fds; i++) {
+		pfds[i].fd = fds[i];
+		pfds[i].events = POLLIN;
+	}
+
+	for (;;) {
+		poll(pfds, num_fds, 1000);
+		for (i = 0; i < num_fds; i++) {
+			if (!pfds[i].revents)
+				continue;
+
+			ret = bpf_perf_event_read_simple(headers[i],
+							 page_cnt * page_size,
+							 page_size, &buf, &len,
+							 bpf_perf_event_print,
+							 output_fn);
+			if (ret != LIBBPF_PERF_EVENT_CONT)
+				break;
+		}
+	}
+	free(buf);
+	free(pfds);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h
index 3b4bcf7f5084..18924f23db1b 100644
--- a/tools/testing/selftests/bpf/trace_helpers.h
+++ b/tools/testing/selftests/bpf/trace_helpers.h
@@ -3,6 +3,7 @@
 #define __TRACE_HELPER_H
 
 #include <libbpf.h>
+#include <linux/perf_event.h>
 
 struct ksym {
 	long addr;
@@ -16,6 +17,9 @@ long ksym_get_addr(const char *name);
 typedef enum bpf_perf_event_ret (*perf_event_print_fn)(void *data, int size);
 
 int perf_event_mmap(int fd);
+int perf_event_mmap_header(int fd, struct perf_event_mmap_page **header);
 /* return LIBBPF_PERF_EVENT_DONE or LIBBPF_PERF_EVENT_ERROR */
 int perf_event_poller(int fd, perf_event_print_fn output_fn);
+int perf_event_poller_multi(int *fds, struct perf_event_mmap_page **headers,
+			    int num_fds, perf_event_print_fn output_fn);
 #endif
-- 
cgit v1.2.3


From 1e54ad251a93a524f1a2950b1d65bc7437c57a53 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Mon, 25 Jun 2018 14:25:02 +0200
Subject: samples/bpf: Add xdp_sample_pkts example
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add an example program showing how to sample packets from XDP using the
perf event buffer. The example userspace program just prints the ethernet
header for every packet sampled.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/Makefile               |   4 +
 samples/bpf/xdp_sample_pkts_kern.c |  66 +++++++++++++++
 samples/bpf/xdp_sample_pkts_user.c | 169 +++++++++++++++++++++++++++++++++++++
 3 files changed, 239 insertions(+)
 create mode 100644 samples/bpf/xdp_sample_pkts_kern.c
 create mode 100644 samples/bpf/xdp_sample_pkts_user.c

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 1303af10e54d..9ea2f7b64869 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -52,6 +52,7 @@ hostprogs-y += xdp_adjust_tail
 hostprogs-y += xdpsock
 hostprogs-y += xdp_fwd
 hostprogs-y += task_fd_query
+hostprogs-y += xdp_sample_pkts
 
 # Libbpf dependencies
 LIBBPF = $(TOOLS_PATH)/lib/bpf/libbpf.a
@@ -107,6 +108,7 @@ xdp_adjust_tail-objs := xdp_adjust_tail_user.o
 xdpsock-objs := bpf_load.o xdpsock_user.o
 xdp_fwd-objs := bpf_load.o xdp_fwd_user.o
 task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
+xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
 
 # Tell kbuild to always build the programs
 always := $(hostprogs-y)
@@ -163,6 +165,7 @@ always += xdp_adjust_tail_kern.o
 always += xdpsock_kern.o
 always += xdp_fwd_kern.o
 always += task_fd_query_kern.o
+always += xdp_sample_pkts_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 HOSTCFLAGS += -I$(srctree)/tools/lib/
@@ -179,6 +182,7 @@ HOSTCFLAGS_spintest_user.o += -I$(srctree)/tools/lib/bpf/
 HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
 HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
 HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/
+HOSTCFLAGS_xdp_sample_pkts_user.o += -I$(srctree)/tools/lib/bpf/
 
 HOST_LOADLIBES		+= $(LIBBPF) -lelf
 HOSTLOADLIBES_tracex4		+= -lrt
diff --git a/samples/bpf/xdp_sample_pkts_kern.c b/samples/bpf/xdp_sample_pkts_kern.c
new file mode 100644
index 000000000000..f7ca8b850978
--- /dev/null
+++ b/samples/bpf/xdp_sample_pkts_kern.c
@@ -0,0 +1,66 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/ptrace.h>
+#include <linux/version.h>
+#include <uapi/linux/bpf.h>
+#include "bpf_helpers.h"
+
+#define SAMPLE_SIZE 64ul
+#define MAX_CPUS 128
+
+#define bpf_printk(fmt, ...)					\
+({								\
+	       char ____fmt[] = fmt;				\
+	       bpf_trace_printk(____fmt, sizeof(____fmt),	\
+				##__VA_ARGS__);			\
+})
+
+struct bpf_map_def SEC("maps") my_map = {
+	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
+	.key_size = sizeof(int),
+	.value_size = sizeof(u32),
+	.max_entries = MAX_CPUS,
+};
+
+SEC("xdp_sample")
+int xdp_sample_prog(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+
+	/* Metadata will be in the perf event before the packet data. */
+	struct S {
+		u16 cookie;
+		u16 pkt_len;
+	} __packed metadata;
+
+	if (data < data_end) {
+		/* The XDP perf_event_output handler will use the upper 32 bits
+		 * of the flags argument as a number of bytes to include of the
+		 * packet payload in the event data. If the size is too big, the
+		 * call to bpf_perf_event_output will fail and return -EFAULT.
+		 *
+		 * See bpf_xdp_event_output in net/core/filter.c.
+		 *
+		 * The BPF_F_CURRENT_CPU flag means that the event output fd
+		 * will be indexed by the CPU number in the event map.
+		 */
+		u64 flags = BPF_F_CURRENT_CPU;
+		u16 sample_size;
+		int ret;
+
+		metadata.cookie = 0xdead;
+		metadata.pkt_len = (u16)(data_end - data);
+		sample_size = min(metadata.pkt_len, SAMPLE_SIZE);
+		flags |= (u64)sample_size << 32;
+
+		ret = bpf_perf_event_output(ctx, &my_map, flags,
+					    &metadata, sizeof(metadata));
+		if (ret)
+			bpf_printk("perf_event_output failed: %d\n", ret);
+	}
+
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
+u32 _version SEC("version") = LINUX_VERSION_CODE;
diff --git a/samples/bpf/xdp_sample_pkts_user.c b/samples/bpf/xdp_sample_pkts_user.c
new file mode 100644
index 000000000000..8dd87c1eb560
--- /dev/null
+++ b/samples/bpf/xdp_sample_pkts_user.c
@@ -0,0 +1,169 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <linux/perf_event.h>
+#include <linux/bpf.h>
+#include <net/if.h>
+#include <errno.h>
+#include <assert.h>
+#include <sys/sysinfo.h>
+#include <sys/ioctl.h>
+#include <signal.h>
+#include <libbpf.h>
+#include <bpf/bpf.h>
+
+#include "perf-sys.h"
+#include "trace_helpers.h"
+
+#define MAX_CPUS 128
+static int pmu_fds[MAX_CPUS], if_idx;
+static struct perf_event_mmap_page *headers[MAX_CPUS];
+static char *if_name;
+
+static int do_attach(int idx, int fd, const char *name)
+{
+	int err;
+
+	err = bpf_set_link_xdp_fd(idx, fd, 0);
+	if (err < 0)
+		printf("ERROR: failed to attach program to %s\n", name);
+
+	return err;
+}
+
+static int do_detach(int idx, const char *name)
+{
+	int err;
+
+	err = bpf_set_link_xdp_fd(idx, -1, 0);
+	if (err < 0)
+		printf("ERROR: failed to detach program from %s\n", name);
+
+	return err;
+}
+
+#define SAMPLE_SIZE 64
+
+static int print_bpf_output(void *data, int size)
+{
+	struct {
+		__u16 cookie;
+		__u16 pkt_len;
+		__u8  pkt_data[SAMPLE_SIZE];
+	} __packed *e = data;
+	int i;
+
+	if (e->cookie != 0xdead) {
+		printf("BUG cookie %x sized %d\n",
+		       e->cookie, size);
+		return LIBBPF_PERF_EVENT_ERROR;
+	}
+
+	printf("Pkt len: %-5d bytes. Ethernet hdr: ", e->pkt_len);
+	for (i = 0; i < 14 && i < e->pkt_len; i++)
+		printf("%02x ", e->pkt_data[i]);
+	printf("\n");
+
+	return LIBBPF_PERF_EVENT_CONT;
+}
+
+static void test_bpf_perf_event(int map_fd, int num)
+{
+	struct perf_event_attr attr = {
+		.sample_type = PERF_SAMPLE_RAW,
+		.type = PERF_TYPE_SOFTWARE,
+		.config = PERF_COUNT_SW_BPF_OUTPUT,
+		.wakeup_events = 1, /* get an fd notification for every event */
+	};
+	int i;
+
+	for (i = 0; i < num; i++) {
+		int key = i;
+
+		pmu_fds[i] = sys_perf_event_open(&attr, -1/*pid*/, i/*cpu*/,
+						 -1/*group_fd*/, 0);
+
+		assert(pmu_fds[i] >= 0);
+		assert(bpf_map_update_elem(map_fd, &key,
+					   &pmu_fds[i], BPF_ANY) == 0);
+		ioctl(pmu_fds[i], PERF_EVENT_IOC_ENABLE, 0);
+	}
+}
+
+static void sig_handler(int signo)
+{
+	do_detach(if_idx, if_name);
+	exit(0);
+}
+
+int main(int argc, char **argv)
+{
+	struct bpf_prog_load_attr prog_load_attr = {
+		.prog_type	= BPF_PROG_TYPE_XDP,
+	};
+	struct bpf_object *obj;
+	struct bpf_map *map;
+	int prog_fd, map_fd;
+	char filename[256];
+	int ret, err, i;
+	int numcpus;
+
+	if (argc < 2) {
+		printf("Usage: %s <ifname>\n", argv[0]);
+		return 1;
+	}
+
+	numcpus = get_nprocs();
+	if (numcpus > MAX_CPUS)
+		numcpus = MAX_CPUS;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+	prog_load_attr.file = filename;
+
+	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+		return 1;
+
+	if (!prog_fd) {
+		printf("load_bpf_file: %s\n", strerror(errno));
+		return 1;
+	}
+
+	map = bpf_map__next(NULL, obj);
+	if (!map) {
+		printf("finding a map in obj file failed\n");
+		return 1;
+	}
+	map_fd = bpf_map__fd(map);
+
+	if_idx = if_nametoindex(argv[1]);
+	if (!if_idx)
+		if_idx = strtoul(argv[1], NULL, 0);
+
+	if (!if_idx) {
+		fprintf(stderr, "Invalid ifname\n");
+		return 1;
+	}
+	if_name = argv[1];
+	err = do_attach(if_idx, prog_fd, argv[1]);
+	if (err)
+		return err;
+
+	if (signal(SIGINT, sig_handler) ||
+	    signal(SIGHUP, sig_handler) ||
+	    signal(SIGTERM, sig_handler)) {
+		perror("signal");
+		return 1;
+	}
+
+	test_bpf_perf_event(map_fd, numcpus);
+
+	for (i = 0; i < numcpus; i++)
+		if (perf_event_mmap_header(pmu_fds[i], &headers[i]) < 0)
+			return 1;
+
+	ret = perf_event_poller_multi(pmu_fds, headers, numcpus,
+				      print_bpf_output);
+	kill(0, SIGINT);
+	return ret;
+}
-- 
cgit v1.2.3


From 0d0f6249058834ffe1ceaad0bb31464af66f6e7a Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Fri, 22 Jun 2018 17:39:33 +0200
Subject: x86/speculation/l1tf: Protect PAE swap entries against L1TF

The PAE 3-level paging code currently doesn't mitigate L1TF by flipping the
offset bits, and uses the high PTE word, thus bits 32-36 for type, 37-63 for
offset. The lower word is zeroed, thus systems with less than 4GB memory are
safe. With 4GB to 128GB the swap type selects the memory locations vulnerable
to L1TF; with even more memory, also the swap offfset influences the address.
This might be a problem with 32bit PAE guests running on large 64bit hosts.

By continuing to keep the whole swap entry in either high or low 32bit word of
PTE we would limit the swap size too much. Thus this patch uses the whole PAE
PTE with the same layout as the 64bit version does. The macros just become a
bit tricky since they assume the arch-dependent swp_entry_t to be 32bit.

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michal Hocko <mhocko@suse.com>
---
 arch/x86/include/asm/pgtable-3level.h | 35 +++++++++++++++++++++++++++++++++--
 arch/x86/mm/init.c                    |  2 +-
 2 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 76ab26a99e6e..bb035a4cbc8c 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -241,12 +241,43 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 #endif
 
 /* Encode and de-code a swap entry */
+#define SWP_TYPE_BITS		5
+
+#define SWP_OFFSET_FIRST_BIT	(_PAGE_BIT_PROTNONE + 1)
+
+/* We always extract/encode the offset by shifting it all the way up, and then down again */
+#define SWP_OFFSET_SHIFT	(SWP_OFFSET_FIRST_BIT + SWP_TYPE_BITS)
+
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)			(((x).val) & 0x1f)
 #define __swp_offset(x)			((x).val >> 5)
 #define __swp_entry(type, offset)	((swp_entry_t){(type) | (offset) << 5})
-#define __pte_to_swp_entry(pte)		((swp_entry_t){ (pte).pte_high })
-#define __swp_entry_to_pte(x)		((pte_t){ { .pte_high = (x).val } })
+
+/*
+ * Normally, __swp_entry() converts from arch-independent swp_entry_t to
+ * arch-dependent swp_entry_t, and __swp_entry_to_pte() just stores the result
+ * to pte. But here we have 32bit swp_entry_t and 64bit pte, and need to use the
+ * whole 64 bits. Thus, we shift the "real" arch-dependent conversion to
+ * __swp_entry_to_pte() through the following helper macro based on 64bit
+ * __swp_entry().
+ */
+#define __swp_pteval_entry(type, offset) ((pteval_t) { \
+	(~(pteval_t)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \
+	| ((pteval_t)(type) << (64 - SWP_TYPE_BITS)) })
+
+#define __swp_entry_to_pte(x)	((pte_t){ .pte = \
+		__swp_pteval_entry(__swp_type(x), __swp_offset(x)) })
+/*
+ * Analogically, __pte_to_swp_entry() doesn't just extract the arch-dependent
+ * swp_entry_t, but also has to convert it from 64bit to the 32bit
+ * intermediate representation, using the following macros based on 64bit
+ * __swp_type() and __swp_offset().
+ */
+#define __pteval_swp_type(x) ((unsigned long)((x).pte >> (64 - SWP_TYPE_BITS)))
+#define __pteval_swp_offset(x) ((unsigned long)(~((x).pte) << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT))
+
+#define __pte_to_swp_entry(pte)	(__swp_entry(__pteval_swp_type(pte), \
+					     __pteval_swp_offset(pte)))
 
 #define gup_get_pte gup_get_pte
 /*
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index c0870df32b2d..862191ed3d6e 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -896,7 +896,7 @@ unsigned long max_swapfile_size(void)
 		 * We encode swap offsets also with 3 bits below those for pfn
 		 * which makes the usable limit higher.
 		 */
-#ifdef CONFIG_X86_64
+#if CONFIG_PGTABLE_LEVELS > 2
 		l1tf_limit <<= PAGE_SHIFT - SWP_OFFSET_FIRST_BIT;
 #endif
 		pages = min_t(unsigned long, l1tf_limit, pages);
-- 
cgit v1.2.3


From a7f7547f5e2b90554b0f3d1604899a4f26dba92d Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Tue, 26 Jun 2018 14:22:41 -0700
Subject: selftests/bpf: Test sys_connect BPF hooks with TFO

TCP Fast Open is triggered by sys_sendmsg with MSG_FASTOPEN flag for
SOCK_STREAM socket.

Even though it's sys_sendmsg, it eventually calls __inet_stream_connect
the same way sys_connect does for TCP.  __inet_stream_connect, in turn,
already has BPF hooks for sys_connect.

That means TFO is already covered by BPF_CGROUP_INET{4,6}_CONNECT and
the only missing piece is selftest. The patch adds selftest for TFO.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_sock_addr.c | 37 +++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index a5e76b9219b9..2e45c92d1111 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -998,8 +998,9 @@ int init_pktinfo(int domain, struct cmsghdr *cmsg)
 	return 0;
 }
 
-static int sendmsg_to_server(const struct sockaddr_storage *addr,
-			     socklen_t addr_len, int set_cmsg, int *syscall_err)
+static int sendmsg_to_server(int type, const struct sockaddr_storage *addr,
+			     socklen_t addr_len, int set_cmsg, int flags,
+			     int *syscall_err)
 {
 	union {
 		char buf[CMSG_SPACE(sizeof(struct in6_pktinfo))];
@@ -1022,7 +1023,7 @@ static int sendmsg_to_server(const struct sockaddr_storage *addr,
 		goto err;
 	}
 
-	fd = socket(domain, SOCK_DGRAM, 0);
+	fd = socket(domain, type, 0);
 	if (fd == -1) {
 		log_err("Failed to create client socket");
 		goto err;
@@ -1052,7 +1053,7 @@ static int sendmsg_to_server(const struct sockaddr_storage *addr,
 		}
 	}
 
-	if (sendmsg(fd, &hdr, 0) != sizeof(data)) {
+	if (sendmsg(fd, &hdr, flags) != sizeof(data)) {
 		log_err("Fail to send message to server");
 		*syscall_err = errno;
 		goto err;
@@ -1066,6 +1067,15 @@ out:
 	return fd;
 }
 
+static int fastconnect_to_server(const struct sockaddr_storage *addr,
+				 socklen_t addr_len)
+{
+	int sendmsg_err;
+
+	return sendmsg_to_server(SOCK_STREAM, addr, addr_len, /*set_cmsg*/0,
+				 MSG_FASTOPEN, &sendmsg_err);
+}
+
 static int recvmsg_from_client(int sockfd, struct sockaddr_storage *src_addr)
 {
 	struct timeval tv;
@@ -1185,6 +1195,20 @@ static int run_connect_test_case(const struct sock_addr_test *test)
 	if (cmp_local_ip(clientfd, &expected_src_addr))
 		goto err;
 
+	if (test->type == SOCK_STREAM) {
+		/* Test TCP Fast Open scenario */
+		clientfd = fastconnect_to_server(&requested_addr, addr_len);
+		if (clientfd == -1)
+			goto err;
+
+		/* Make sure src and dst addrs were overridden properly */
+		if (cmp_peer_addr(clientfd, &expected_addr))
+			goto err;
+
+		if (cmp_local_ip(clientfd, &expected_src_addr))
+			goto err;
+	}
+
 	goto out;
 err:
 	err = -1;
@@ -1222,8 +1246,9 @@ static int run_sendmsg_test_case(const struct sock_addr_test *test)
 		if (clientfd >= 0)
 			close(clientfd);
 
-		clientfd = sendmsg_to_server(&requested_addr, addr_len,
-					     set_cmsg, &err);
+		clientfd = sendmsg_to_server(test->type, &requested_addr,
+					     addr_len, set_cmsg, /*flags*/0,
+					     &err);
 		if (err)
 			goto out;
 		else if (clientfd == -1)
-- 
cgit v1.2.3


From 401caff70cd3d3ef3c96e1a1cbf6f973c24ba899 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 27 Jun 2018 11:43:09 +0200
Subject: ALSA: hda - Kill snd_hda_codec_update_cache()

snd_hda_codec_update_cache() used to serve for a slightly different
purpose from snd_hdac_write_cache(), but now both of them became
identical.

Let's unify and replace with the latter one consistently.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_codec.c      | 4 ++--
 sound/pci/hda/hda_codec.h      | 3 ---
 sound/pci/hda/hda_generic.c    | 8 ++++----
 sound/pci/hda/patch_analog.c   | 4 ++--
 sound/pci/hda/patch_conexant.c | 2 +-
 5 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index d91c87e41756..f42af88bd2de 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -3842,7 +3842,7 @@ EXPORT_SYMBOL_GPL(snd_hda_correct_pin_ctl);
  * This function is a helper to set a pin ctl value more safely.
  * It corrects the pin ctl value via snd_hda_correct_pin_ctl(), stores the
  * value in pin target array via snd_hda_codec_set_pin_target(), then
- * actually writes the value via either snd_hda_codec_update_cache() or
+ * actually writes the value via either snd_hda_codec_write_cache() or
  * snd_hda_codec_write() depending on @cached flag.
  */
 int _snd_hda_set_pin_ctl(struct hda_codec *codec, hda_nid_t pin,
@@ -3851,7 +3851,7 @@ int _snd_hda_set_pin_ctl(struct hda_codec *codec, hda_nid_t pin,
 	val = snd_hda_correct_pin_ctl(codec, pin, val);
 	snd_hda_codec_set_pin_target(codec, pin, val);
 	if (cached)
-		return snd_hda_codec_update_cache(codec, pin, 0,
+		return snd_hda_codec_write_cache(codec, pin, 0,
 				AC_VERB_SET_PIN_WIDGET_CONTROL, val);
 	else
 		return snd_hda_codec_write(codec, pin, 0,
diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
index 681c360f29f9..8a095c16ee65 100644
--- a/sound/pci/hda/hda_codec.h
+++ b/sound/pci/hda/hda_codec.h
@@ -381,9 +381,6 @@ snd_hda_codec_write_cache(struct hda_codec *codec, hda_nid_t nid,
 	return snd_hdac_regmap_write(&codec->core, nid, verb, parm);
 }
 
-#define snd_hda_codec_update_cache(codec, nid, flags, verb, parm) \
-	snd_hda_codec_write_cache(codec, nid, flags, verb, parm)
-
 /* the struct for codec->pin_configs */
 struct hda_pincfg {
 	hda_nid_t nid;
diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
index 942f96e184b6..579984ecdec3 100644
--- a/sound/pci/hda/hda_generic.c
+++ b/sound/pci/hda/hda_generic.c
@@ -209,7 +209,7 @@ static void parse_user_hints(struct hda_codec *codec)
  */
 
 #define update_pin_ctl(codec, pin, val) \
-	snd_hda_codec_update_cache(codec, pin, 0, \
+	snd_hda_codec_write_cache(codec, pin, 0, \
 				   AC_VERB_SET_PIN_WIDGET_CONTROL, val)
 
 /* restore the pinctl based on the cached value */
@@ -898,7 +898,7 @@ void snd_hda_activate_path(struct hda_codec *codec, struct nid_path *path,
 		hda_nid_t nid = path->path[i];
 
 		if (enable && path->multi[i])
-			snd_hda_codec_update_cache(codec, nid, 0,
+			snd_hda_codec_write_cache(codec, nid, 0,
 					    AC_VERB_SET_CONNECT_SEL,
 					    path->idx[i]);
 		if (has_amp_in(codec, path, i))
@@ -930,7 +930,7 @@ static void set_pin_eapd(struct hda_codec *codec, hda_nid_t pin, bool enable)
 		return;
 	if (codec->inv_eapd)
 		enable = !enable;
-	snd_hda_codec_update_cache(codec, pin, 0,
+	snd_hda_codec_write_cache(codec, pin, 0,
 				   AC_VERB_SET_EAPD_BTLENABLE,
 				   enable ? 0x02 : 0x00);
 }
@@ -5973,7 +5973,7 @@ static void clear_unsol_on_unused_pins(struct hda_codec *codec)
 		hda_nid_t nid = pin->nid;
 		if (is_jack_detectable(codec, nid) &&
 		    !snd_hda_jack_tbl_get(codec, nid))
-			snd_hda_codec_update_cache(codec, nid, 0,
+			snd_hda_codec_write_cache(codec, nid, 0,
 					AC_VERB_SET_UNSOLICITED_ENABLE, 0);
 	}
 }
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 757857313426..fd476fb40e1b 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -148,7 +148,7 @@ static void ad_vmaster_eapd_hook(void *private_data, int enabled)
 		return;
 	if (codec->inv_eapd)
 		enabled = !enabled;
-	snd_hda_codec_update_cache(codec, spec->eapd_nid, 0,
+	snd_hda_codec_write_cache(codec, spec->eapd_nid, 0,
 				   AC_VERB_SET_EAPD_BTLENABLE,
 				   enabled ? 0x02 : 0x00);
 }
@@ -991,7 +991,7 @@ static void ad1884_vmaster_hp_gpio_hook(void *private_data, int enabled)
 
 	if (spec->eapd_nid)
 		ad_vmaster_eapd_hook(private_data, enabled);
-	snd_hda_codec_update_cache(codec, 0x01, 0,
+	snd_hda_codec_write_cache(codec, 0x01, 0,
 				   AC_VERB_SET_GPIO_DATA,
 				   enabled ? 0x00 : 0x02);
 }
diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 75ba66eb4ccd..8b48352689b4 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -341,7 +341,7 @@ static void cxt_fixup_headset_mic(struct hda_codec *codec,
  * control. */
 
 #define update_mic_pin(codec, nid, val)					\
-	snd_hda_codec_update_cache(codec, nid, 0,			\
+	snd_hda_codec_write_cache(codec, nid, 0,			\
 				   AC_VERB_SET_PIN_WIDGET_CONTROL, val)
 
 static const struct hda_input_mux olpc_xo_dc_bias = {
-- 
cgit v1.2.3


From fc7c460fbb4003bf3f5d2b435079c85888644663 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:26 +0200
Subject: ASoC: Intel: bytcr_rt5651: Add BYT_RT5651_DEFAULT_QUIRKS define

Almost all boards use the mclk and use the same jack-detect settings, add
a BYT_RT5651_DEFAULT_QUIRKS define for this.

This shaves of some lines and makes it easier to see which settings are
unique to a certain model.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 25 +++++++++----------------
 1 file changed, 9 insertions(+), 16 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 987720e203f9..735b8312e275 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -77,6 +77,11 @@ enum {
 #define BYT_RT5651_SSP0_AIF1		BIT(20)
 #define BYT_RT5651_SSP0_AIF2		BIT(21)
 
+#define BYT_RT5651_DEFAULT_QUIRKS	(BYT_RT5651_MCLK_EN | \
+					 BYT_RT5651_JD1_1   | \
+					 BYT_RT5651_OVCD_TH_2000UA | \
+					 BYT_RT5651_OVCD_SF_0P75)
+
 /* jack-detect-source + dmic-en + ovcd-th + -sf + terminating empty entry */
 #define MAX_NO_PROPS 5
 
@@ -86,10 +91,7 @@ struct byt_rt5651_private {
 };
 
 /* Default: jack-detect on JD1_1, internal mic on in2, headsetmic on in3 */
-static unsigned long byt_rt5651_quirk = BYT_RT5651_MCLK_EN |
-					BYT_RT5651_JD1_1 |
-					BYT_RT5651_OVCD_TH_2000UA |
-					BYT_RT5651_OVCD_SF_0P75 |
+static unsigned long byt_rt5651_quirk = BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN2_HS_IN3_MAP;
 
 static void log_quirks(struct device *dev)
@@ -379,10 +381,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "KIANO"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "KIANO SlimNote 14.2"),
 		},
-		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_JD1_1 |
-					BYT_RT5651_OVCD_TH_2000UA |
-					BYT_RT5651_OVCD_SF_0P75 |
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN1_IN2_MAP),
 	},
 	{
@@ -392,10 +391,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
 		},
-		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_JD1_1 |
-					BYT_RT5651_OVCD_TH_2000UA |
-					BYT_RT5651_OVCD_SF_0P75 |
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN2_HS_IN3_MAP),
 	},
 	{
@@ -405,10 +401,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "VIOS"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "LTH17"),
 		},
-		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_JD1_1 |
-					BYT_RT5651_OVCD_TH_2000UA |
-					BYT_RT5651_OVCD_SF_1P0 |
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN1_IN2_MAP),
 	},
 	{}
-- 
cgit v1.2.3


From 10876d24eb40c6bfaa0aabd97e3e143258176c53 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:27 +0200
Subject: ASoC: Intel: bytcr_rt5651: Change default input map from in2 to in1

Further testing on all 6 model x86 tablets with a rt5651 which I have
access to for testing has shown that their single (mono) microphone is
connected to both IN1 *and* IN2.

The previous default mapping of IN2 was based on testing on the same 6
tablets, where the internal mic works fine with a mapping of IN2. But it
works fine too with a mapping of IN1.

This commit changes the default input mapping to to use IN1 instead of
IN2, to match the mapping used for the other mono devices in the DMI quirk
table. So that we need less different mappings.

The same change is made to the Chuwi Vi8 Plus quirks, which is one of the
6 models tested.

This is a preparation patch for simplifying the maps in a follow-up commit.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 735b8312e275..910890de38b0 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -90,9 +90,9 @@ struct byt_rt5651_private {
 	struct snd_soc_jack jack;
 };
 
-/* Default: jack-detect on JD1_1, internal mic on in2, headsetmic on in3 */
+/* Default: jack-detect on JD1_1, internal mic on in1, headsetmic on in3 */
 static unsigned long byt_rt5651_quirk = BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN2_HS_IN3_MAP;
+					BYT_RT5651_IN1_HS_IN3_MAP;
 
 static void log_quirks(struct device *dev)
 {
@@ -392,7 +392,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
 		},
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN2_HS_IN3_MAP),
+					BYT_RT5651_IN1_HS_IN3_MAP),
 	},
 	{
 		/* VIOS LTH17 */
-- 
cgit v1.2.3


From 366780df3e2d40533cc95a4bf25ddd3b934b5fd3 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:28 +0200
Subject: ASoC: Intel: bytcr_rt5651: Fix IN1_IN2_MAP quirk not being logged

Fix the quirk logging code not logging the IN1_IN2_MAP quirk.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 910890de38b0..7cc6e36b7c47 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -102,6 +102,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk IN1_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN2_MAP)
 		dev_info(dev, "quirk IN2_MAP enabled");
+	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_IN2_MAP)
+		dev_info(dev, "quirk IN1_IN2_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_HS_IN3_MAP)
 		dev_info(dev, "quirk IN1_HS_IN3_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN2_HS_IN3_MAP)
-- 
cgit v1.2.3


From fcdf1391caa6f7f01de56eea63e070555771fac7 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:29 +0200
Subject: ASoC: Intel: bytcr_rt5651: Remove IN2 input mappings

BYT_RT5651_IN2_MAP was introduced in commit 39712db878a4 ("SoC: intel: byt:
Introduce new custom IN2 map"), uses in commit 2fe30129b0a6 ("ASoC: intel:
byt: Enable IN2 map quirk for a KIANO laptop"), only to be replaced by a
new BYT_RT5651_IN1_IN2_MAP quirk in commit ea261bd02a67 ("ASoC: intel:
byt: Introduce new map for dual mics") quickly afterwards, because the
KIANO laptop has 2 internal mics on IN1 and IN2 and the headset mic is
not in IN1 where the BYT_RT5651_IN2_MAP maps it, but on IN3.

Now that the KIANO quirk entry uses BYT_RT5651_IN1_IN2_MAP, there are no
users of BYT_RT5651_IN2_MAP left. This makes sense since the headset mic
seems to always be connected to IN3, so BYT_RT5651_IN2_MAP is not useful.

To deal with BYT_RT5651_IN2_MAP wrongly mapping the headset mic to IN1,
BYT_RT5651_IN2_HS_IN3_MAP was added in commit f026e0631780 ("ASoC: Intel:
bytcr_rt5651: Add new IN2_HS_IN3 input map and a quirk using it"). This
was based on the assumption then some devices have the internal mic
connected to IN2 only. Further testing has shown that this is wrong and the
internal mic is always connected to IN1 and sometimes to both IN1 and IN2.

TL;DR: Both BYT_RT5651_IN2_MAP and BYT_RT5651_IN2_HS_IN3_MAP are based on
on wrong assumptions from the past and are no longer useful now, so they
can both be removed.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 30 ++----------------------------
 1 file changed, 2 insertions(+), 28 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 7cc6e36b7c47..b8ca7137d8b2 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -40,10 +40,8 @@
 enum {
 	BYT_RT5651_DMIC_MAP,
 	BYT_RT5651_IN1_MAP,
-	BYT_RT5651_IN2_MAP,
 	BYT_RT5651_IN1_IN2_MAP,
 	BYT_RT5651_IN1_HS_IN3_MAP,
-	BYT_RT5651_IN2_HS_IN3_MAP,
 };
 
 enum {
@@ -100,14 +98,10 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk DMIC_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_MAP)
 		dev_info(dev, "quirk IN1_MAP enabled");
-	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN2_MAP)
-		dev_info(dev, "quirk IN2_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_IN2_MAP)
 		dev_info(dev, "quirk IN1_IN2_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_HS_IN3_MAP)
 		dev_info(dev, "quirk IN1_HS_IN3_MAP enabled");
-	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN2_HS_IN3_MAP)
-		dev_info(dev, "quirk IN2_HS_IN3_MAP enabled");
 	if (BYT_RT5651_JDSRC(byt_rt5651_quirk)) {
 		dev_info(dev, "quirk realtek,jack-detect-source %ld\n",
 			 BYT_RT5651_JDSRC(byt_rt5651_quirk));
@@ -256,12 +250,6 @@ static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_map[] = {
 	{"IN2P", NULL, "Headset Mic"},
 };
 
-static const struct snd_soc_dapm_route byt_rt5651_intmic_in2_map[] = {
-	{"Internal Mic", NULL, "micbias1"},
-	{"IN1P", NULL, "Headset Mic"},
-	{"IN2P", NULL, "Internal Mic"},
-};
-
 static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_in2_map[] = {
 	{"Internal Mic", NULL, "micbias1"},
 	{"IN1P", NULL, "Internal Mic"},
@@ -275,12 +263,6 @@ static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_hs_in3_map[] = {
 	{"IN3P", NULL, "Headset Mic"},
 };
 
-static const struct snd_soc_dapm_route byt_rt5651_intmic_in2_hs_in3_map[] = {
-	{"Internal Mic", NULL, "micbias1"},
-	{"IN2P", NULL, "Internal Mic"},
-	{"IN3P", NULL, "Headset Mic"},
-};
-
 static const struct snd_soc_dapm_route byt_rt5651_ssp0_aif1_map[] = {
 	{"ssp0 Tx", NULL, "modem_out"},
 	{"modem_in", NULL, "ssp0 Rx"},
@@ -462,10 +444,6 @@ static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
 		custom_map = byt_rt5651_intmic_in1_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_map);
 		break;
-	case BYT_RT5651_IN2_MAP:
-		custom_map = byt_rt5651_intmic_in2_map;
-		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in2_map);
-		break;
 	case BYT_RT5651_IN1_IN2_MAP:
 		custom_map = byt_rt5651_intmic_in1_in2_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_in2_map);
@@ -474,10 +452,6 @@ static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
 		custom_map = byt_rt5651_intmic_in1_hs_in3_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_hs_in3_map);
 		break;
-	case BYT_RT5651_IN2_HS_IN3_MAP:
-		custom_map = byt_rt5651_intmic_in2_hs_in3_map;
-		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in2_hs_in3_map);
-		break;
 	default:
 		custom_map = byt_rt5651_intmic_dmic_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_dmic_map);
@@ -723,9 +697,9 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 {
 	const char * const intmic_name[] =
-		{ "dmic", "in1", "in2", "in12", "in1", "in2" };
+		{ "dmic", "in1", "in12", "in1" };
 	const char * const hsmic_name[] =
-		{  "in2", "in2", "in1",  "in3", "in3", "in3" };
+		{  "in2", "in2", "in3", "in3" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *i2c_name = NULL;
-- 
cgit v1.2.3


From de23147983013591bc4d6812ce441f351dec6b9d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:30 +0200
Subject: ASoC: Intel: bytcr_rt5651: Fix IN1 map headsetmic mapping

The initial bytcr_rt5651 machine driver commit mapped IN2 as the headset
mic. In retrospect this is not correct as all known boards have the headset
mic on IN3. To workaround this special IN?_HS_IN3 mappings were added.

This commit fixes the original IN1 mapping to correctly have the headset
mic on IN3, moves all users of the IN1_HS_IN3 mapping over to the fixed
IN1_MAP and drops the now no longer needed IN1_HS_IN3 mapping.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 29 +++++++----------------------
 1 file changed, 7 insertions(+), 22 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index b8ca7137d8b2..bf2adb36f455 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -41,7 +41,6 @@ enum {
 	BYT_RT5651_DMIC_MAP,
 	BYT_RT5651_IN1_MAP,
 	BYT_RT5651_IN1_IN2_MAP,
-	BYT_RT5651_IN1_HS_IN3_MAP,
 };
 
 enum {
@@ -90,7 +89,7 @@ struct byt_rt5651_private {
 
 /* Default: jack-detect on JD1_1, internal mic on in1, headsetmic on in3 */
 static unsigned long byt_rt5651_quirk = BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_HS_IN3_MAP;
+					BYT_RT5651_IN1_MAP;
 
 static void log_quirks(struct device *dev)
 {
@@ -100,8 +99,6 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk IN1_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_IN2_MAP)
 		dev_info(dev, "quirk IN1_IN2_MAP enabled");
-	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_HS_IN3_MAP)
-		dev_info(dev, "quirk IN1_HS_IN3_MAP enabled");
 	if (BYT_RT5651_JDSRC(byt_rt5651_quirk)) {
 		dev_info(dev, "quirk realtek,jack-detect-source %ld\n",
 			 BYT_RT5651_JDSRC(byt_rt5651_quirk));
@@ -247,7 +244,7 @@ static const struct snd_soc_dapm_route byt_rt5651_intmic_dmic_map[] = {
 static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_map[] = {
 	{"Internal Mic", NULL, "micbias1"},
 	{"IN1P", NULL, "Internal Mic"},
-	{"IN2P", NULL, "Headset Mic"},
+	{"IN3P", NULL, "Headset Mic"},
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_in2_map[] = {
@@ -257,12 +254,6 @@ static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_in2_map[] = {
 	{"IN3P", NULL, "Headset Mic"},
 };
 
-static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_hs_in3_map[] = {
-	{"Internal Mic", NULL, "micbias1"},
-	{"IN1P", NULL, "Internal Mic"},
-	{"IN3P", NULL, "Headset Mic"},
-};
-
 static const struct snd_soc_dapm_route byt_rt5651_ssp0_aif1_map[] = {
 	{"ssp0 Tx", NULL, "modem_out"},
 	{"modem_in", NULL, "ssp0 Rx"},
@@ -348,7 +339,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
 		},
-		.driver_data = (void *)(BYT_RT5651_IN1_HS_IN3_MAP),
+		.driver_data = (void *)(BYT_RT5651_IN1_MAP),
 	},
 	{
 		.callback = byt_rt5651_quirk_cb,
@@ -357,7 +348,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Turbot"),
 		},
 		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_IN1_HS_IN3_MAP),
+					BYT_RT5651_IN1_MAP),
 	},
 	{
 		.callback = byt_rt5651_quirk_cb,
@@ -376,7 +367,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
 		},
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_HS_IN3_MAP),
+					BYT_RT5651_IN1_MAP),
 	},
 	{
 		/* VIOS LTH17 */
@@ -448,10 +439,6 @@ static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
 		custom_map = byt_rt5651_intmic_in1_in2_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_in2_map);
 		break;
-	case BYT_RT5651_IN1_HS_IN3_MAP:
-		custom_map = byt_rt5651_intmic_in1_hs_in3_map;
-		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_hs_in3_map);
-		break;
 	default:
 		custom_map = byt_rt5651_intmic_dmic_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_dmic_map);
@@ -696,10 +683,8 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 
 static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 {
-	const char * const intmic_name[] =
-		{ "dmic", "in1", "in12", "in1" };
-	const char * const hsmic_name[] =
-		{  "in2", "in2", "in3", "in3" };
+	const char * const intmic_name[] = { "dmic", "in1", "in12" };
+	const char * const hsmic_name[] = { "in2", "in3", "in3" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *i2c_name = NULL;
-- 
cgit v1.2.3


From 37c7401e8c1f583d197c096152fc87a58f460277 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:31 +0200
Subject: ASoC: Intel: bytcr_rt5651: Fix DMIC map headsetmic mapping

The initial bytcr_rt5651 machine driver commit mapped IN2 as the headset
mic. In retrospect this is not correct as all known boards have the headset
mic on IN3.

This commit fixes the original DMIC mapping to correctly have the headset
mic on IN3.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index bf2adb36f455..042334d9be32 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -236,9 +236,9 @@ static const struct snd_soc_dapm_route byt_rt5651_audio_map[] = {
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_intmic_dmic_map[] = {
-	{"IN2P", NULL, "Headset Mic"},
 	{"DMIC L1", NULL, "Internal Mic"},
 	{"DMIC R1", NULL, "Internal Mic"},
+	{"IN3P", NULL, "Headset Mic"},
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_map[] = {
@@ -684,7 +684,7 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 {
 	const char * const intmic_name[] = { "dmic", "in1", "in12" };
-	const char * const hsmic_name[] = { "in2", "in3", "in3" };
+	const char * const hsmic_name[] = { "in3", "in3", "in3" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *i2c_name = NULL;
-- 
cgit v1.2.3


From 8e69cd640097fa7af53fb476dbd3597608f32b10 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:32 +0200
Subject: ASoC: Intel: bytcr_rt5651: Simplify card long-name

Now that the headset-mic is always IN3 there is no reason to have
the headset-mic mapping in the long-name.

This commit simplifies the long name to "bytcr-rt5651-<intmic-map>-mic".

We can safely do this without causing regressions (UCM profile not found
due to the longname change) as the UCM profiles are not in upstream
alsa-lib yet.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 042334d9be32..e778142b8a6e 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -662,7 +662,7 @@ static struct snd_soc_card byt_rt5651_card = {
 static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
 static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
 static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
-static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-spk-*-mic" */
+static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-mic" */
 
 static bool is_valleyview(void)
 {
@@ -683,8 +683,7 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 
 static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 {
-	const char * const intmic_name[] = { "dmic", "in1", "in12" };
-	const char * const hsmic_name[] = { "in3", "in3", "in3" };
+	const char * const mic_name[] = { "dmic", "in1", "in12" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *i2c_name = NULL;
@@ -831,9 +830,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	}
 
 	snprintf(byt_rt5651_long_name, sizeof(byt_rt5651_long_name),
-		 "bytcr-rt5651-%s-intmic-%s-hsmic",
-		 intmic_name[BYT_RT5651_MAP(byt_rt5651_quirk)],
-		 hsmic_name[BYT_RT5651_MAP(byt_rt5651_quirk)]);
+		 "bytcr-rt5651-%s-mic",
+		 mic_name[BYT_RT5651_MAP(byt_rt5651_quirk)]);
 	byt_rt5651_card.long_name = byt_rt5651_long_name;
 
 	ret_val = devm_snd_soc_register_card(&pdev->dev, &byt_rt5651_card);
-- 
cgit v1.2.3


From 8f250e7009d71e6f3f3aeb95a540c36fc9c03398 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:33 +0200
Subject: ASoC: Intel: bytcr_rt5651: Add BYT_RT5651_HP_LR_SWAPPED quirk

One some models (Chuwi Vi8 Plus, Chuwi Hi8 Pro) the headphone output has
left and right swapped. This can be fixed in with special mixer settings
in the UCM profile, bit this requires these devices loading a different
UCM profile.

This commit adds a BYT_RT5651_HP_LR_SWAPPED quirk for this and postfixes
the longname with "-hp-swapped" if set, so that a different UCM profile
will be loaded.

We can safely do this without causing regressions (UCM profile not found
due to the longname change) as the UCM profiles are not in upstream
alsa-lib yet.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 27 +++++++++++++++++++++++----
 1 file changed, 23 insertions(+), 4 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index e778142b8a6e..ffd62eb5c266 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -73,6 +73,7 @@ enum {
 #define BYT_RT5651_SSP2_AIF2		BIT(19) /* default is using AIF1  */
 #define BYT_RT5651_SSP0_AIF1		BIT(20)
 #define BYT_RT5651_SSP0_AIF2		BIT(21)
+#define BYT_RT5651_HP_LR_SWAPPED	BIT(22)
 
 #define BYT_RT5651_DEFAULT_QUIRKS	(BYT_RT5651_MCLK_EN | \
 					 BYT_RT5651_JD1_1   | \
@@ -359,6 +360,17 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN1_IN2_MAP),
 	},
+	{
+		/* Chuwi Hi8 Pro (CWI513) */
+		.callback = byt_rt5651_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X1D3_C806N"),
+		},
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN1_MAP |
+					BYT_RT5651_HP_LR_SWAPPED),
+	},
 	{
 		/* Chuwi Vi8 Plus (CWI519) */
 		.callback = byt_rt5651_quirk_cb,
@@ -367,7 +379,8 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
 		},
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_MAP),
+					BYT_RT5651_IN1_MAP |
+					BYT_RT5651_HP_LR_SWAPPED),
 	},
 	{
 		/* VIOS LTH17 */
@@ -662,7 +675,7 @@ static struct snd_soc_card byt_rt5651_card = {
 static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
 static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
 static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
-static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-mic" */
+static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-mic[-swapped-hp]" */
 
 static bool is_valleyview(void)
 {
@@ -687,6 +700,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	const char *i2c_name = NULL;
+	const char *hp_swapped;
 	bool is_bytcr = false;
 	int ret_val = 0;
 	int dai_index = 0;
@@ -829,9 +843,14 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (byt_rt5651_quirk & BYT_RT5651_HP_LR_SWAPPED)
+		hp_swapped = "-hp-swapped";
+	else
+		hp_swapped = "";
+
 	snprintf(byt_rt5651_long_name, sizeof(byt_rt5651_long_name),
-		 "bytcr-rt5651-%s-mic",
-		 mic_name[BYT_RT5651_MAP(byt_rt5651_quirk)]);
+		 "bytcr-rt5651-%s-mic%s",
+		 mic_name[BYT_RT5651_MAP(byt_rt5651_quirk)], hp_swapped);
 	byt_rt5651_card.long_name = byt_rt5651_long_name;
 
 	ret_val = devm_snd_soc_register_card(&pdev->dev, &byt_rt5651_card);
-- 
cgit v1.2.3


From 55d69c0309acea65fb3dd99a05a665b51630362d Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 24 Jun 2018 16:06:34 +0200
Subject: ASoC: Intel: bytcr_rt5651: Sort DMI table entries alphabetically

As we get more entries in the DMI quirk table it is nice to have some
sort of ordering in the table, sort it alphabetically.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 41 +++++++++++++++++++----------------
 1 file changed, 22 insertions(+), 19 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index ffd62eb5c266..ba2753e0e12a 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -335,23 +335,29 @@ static int byt_rt5651_quirk_cb(const struct dmi_system_id *id)
 
 static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 	{
+		/* Chuwi Hi8 Pro (CWI513) */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X1D3_C806N"),
 		},
-		.driver_data = (void *)(BYT_RT5651_IN1_MAP),
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN1_MAP |
+					BYT_RT5651_HP_LR_SWAPPED),
 	},
 	{
+		/* Chuwi Vi8 Plus (CWI519) */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "ADI"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Turbot"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
 		},
-		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
-					BYT_RT5651_IN1_MAP),
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN1_MAP |
+					BYT_RT5651_HP_LR_SWAPPED),
 	},
 	{
+		/* KIANO SlimNote 14.2 */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "KIANO"),
@@ -361,26 +367,23 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 					BYT_RT5651_IN1_IN2_MAP),
 	},
 	{
-		/* Chuwi Hi8 Pro (CWI513) */
+		/* Minnowboard Max B3 */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "X1D3_C806N"),
+			DMI_MATCH(DMI_SYS_VENDOR, "Circuitco"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Max B3 PLATFORM"),
 		},
-		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_MAP |
-					BYT_RT5651_HP_LR_SWAPPED),
+		.driver_data = (void *)(BYT_RT5651_IN1_MAP),
 	},
 	{
-		/* Chuwi Vi8 Plus (CWI519) */
+		/* Minnowboard Turbot */
 		.callback = byt_rt5651_quirk_cb,
 		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Hampoo"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
+			DMI_MATCH(DMI_SYS_VENDOR, "ADI"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Minnowboard Turbot"),
 		},
-		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_MAP |
-					BYT_RT5651_HP_LR_SWAPPED),
+		.driver_data = (void *)(BYT_RT5651_MCLK_EN |
+					BYT_RT5651_IN1_MAP),
 	},
 	{
 		/* VIOS LTH17 */
-- 
cgit v1.2.3


From 0ed03e6dc288c50b2e7d71523b99df1afd81cea1 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 26 Jun 2018 14:11:26 +0200
Subject: ASoC: simple-amplifier: remame dio2125 documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The dio2125 is simple enough that we can make it a generic component.
Rename the the dio2125 documentation to simple-amplifier to
prepare this change.

Suggested-by: Nicolò Veronese <nicveronese@gmail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/dioo,dio2125.txt     | 12 ------------
 Documentation/devicetree/bindings/sound/simple-amplifier.txt | 12 ++++++++++++
 2 files changed, 12 insertions(+), 12 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/sound/dioo,dio2125.txt
 create mode 100644 Documentation/devicetree/bindings/sound/simple-amplifier.txt

diff --git a/Documentation/devicetree/bindings/sound/dioo,dio2125.txt b/Documentation/devicetree/bindings/sound/dioo,dio2125.txt
deleted file mode 100644
index 63dbfe0f11d0..000000000000
--- a/Documentation/devicetree/bindings/sound/dioo,dio2125.txt
+++ /dev/null
@@ -1,12 +0,0 @@
-DIO2125 Audio Driver
-
-Required properties:
-- compatible : "dioo,dio2125"
-- enable-gpios : the gpio connected to the enable pin of the dio2125
-
-Example:
-
-amp: analog-amplifier {
-	compatible = "dioo,dio2125";
-	enable-gpios = <&gpio GPIOH_3 0>;
-};
diff --git a/Documentation/devicetree/bindings/sound/simple-amplifier.txt b/Documentation/devicetree/bindings/sound/simple-amplifier.txt
new file mode 100644
index 000000000000..8647edae7af0
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/simple-amplifier.txt
@@ -0,0 +1,12 @@
+Simple Amplifier Audio Driver
+
+Required properties:
+- compatible : "dioo,dio2125" or "simple-audio-amplifier"
+- enable-gpios : the gpio connected to the enable pin of the simple amplifier
+
+Example:
+
+amp: analog-amplifier {
+	compatible = "simple-audio-amplifier";
+	enable-gpios = <&gpio GPIOH_3 0>;
+};
-- 
cgit v1.2.3


From 8d881bb6216d28896112bdc0b42f1f21eb6cd4ee Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 26 Jun 2018 14:11:27 +0200
Subject: ASoC: simple-amplifier: rename dio2125 to simple-amplifer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The dio2125 is simple enough that we can make it a generic component.
Just rename and sed the dio2125 amplifier driver to simple_amplifier.

Suggested-by: Nicolò Veronese <nicveronese@gmail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Kconfig            |  10 +--
 sound/soc/codecs/Makefile           |   4 +-
 sound/soc/codecs/dio2125.c          | 120 -----------------------------------
 sound/soc/codecs/simple-amplifier.c | 121 ++++++++++++++++++++++++++++++++++++
 4 files changed, 128 insertions(+), 127 deletions(-)
 delete mode 100644 sound/soc/codecs/dio2125.c
 create mode 100644 sound/soc/codecs/simple-amplifier.c

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index f6b8d4bf8796..53c2d726bedf 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -74,7 +74,6 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_DA7219 if I2C
 	select SND_SOC_DA732X if I2C
 	select SND_SOC_DA9055 if I2C
-	select SND_SOC_DIO2125
 	select SND_SOC_DMIC if GPIOLIB
 	select SND_SOC_ES8316 if I2C
 	select SND_SOC_ES8328_SPI if SPI_MASTER
@@ -144,6 +143,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_RT5682 if I2C
 	select SND_SOC_SGTL5000 if I2C
 	select SND_SOC_SI476X if MFD_SI476X_CORE
+	select SND_SOC_SIMPLE_AMPLIFIER
 	select SND_SOC_SIRF_AUDIO_CODEC
 	select SND_SOC_SPDIF
 	select SND_SOC_SSM2305
@@ -573,10 +573,6 @@ config SND_SOC_DA732X
 config SND_SOC_DA9055
 	tristate
 
-config SND_SOC_DIO2125
-	tristate "Dioo DIO2125 Amplifier"
-	select GPIOLIB
-
 config SND_SOC_DMIC
 	tristate
 
@@ -897,6 +893,10 @@ config SND_SOC_SIGMADSP_REGMAP
 	tristate
 	select SND_SOC_SIGMADSP
 
+config SND_SOC_SIMPLE_AMPLIFIER
+	tristate "Simple Audio Amplifier"
+	select GPIOLIB
+
 config SND_SOC_SIRF_AUDIO_CODEC
 	tristate "SiRF SoC internal audio codec"
 	select REGMAP_MMIO
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index e43d99a039d3..f26ded89a1e5 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -250,9 +250,9 @@ snd-soc-wm9713-objs := wm9713.o
 snd-soc-wm-hubs-objs := wm_hubs.o
 snd-soc-zx-aud96p22-objs := zx_aud96p22.o
 # Amp
-snd-soc-dio2125-objs := dio2125.o
 snd-soc-max9877-objs := max9877.o
 snd-soc-max98504-objs := max98504.o
+snd-soc-simple-amplifier-objs := simple-amplifier.o
 snd-soc-tpa6130a2-objs := tpa6130a2.o
 snd-soc-tas2552-objs := tas2552.o
 
@@ -509,7 +509,7 @@ obj-$(CONFIG_SND_SOC_WM_HUBS)	+= snd-soc-wm-hubs.o
 obj-$(CONFIG_SND_SOC_ZX_AUD96P22) += snd-soc-zx-aud96p22.o
 
 # Amp
-obj-$(CONFIG_SND_SOC_DIO2125)	+= snd-soc-dio2125.o
 obj-$(CONFIG_SND_SOC_MAX9877)	+= snd-soc-max9877.o
 obj-$(CONFIG_SND_SOC_MAX98504)	+= snd-soc-max98504.o
+obj-$(CONFIG_SND_SOC_SIMPLE_AMPLIFIER)	+= snd-soc-simple-amplifier.o
 obj-$(CONFIG_SND_SOC_TPA6130A2)	+= snd-soc-tpa6130a2.o
diff --git a/sound/soc/codecs/dio2125.c b/sound/soc/codecs/dio2125.c
deleted file mode 100644
index 09451cd44f9b..000000000000
--- a/sound/soc/codecs/dio2125.c
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * Copyright (c) 2017 BayLibre, SAS.
- * Author: Jerome Brunet <jbrunet@baylibre.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, see <http://www.gnu.org/licenses/>.
- * The full GNU General Public License is included in this distribution
- * in the file called COPYING.
- */
-
-#include <linux/gpio/consumer.h>
-#include <linux/module.h>
-#include <sound/soc.h>
-
-#define DRV_NAME "dio2125"
-
-struct dio2125 {
-	struct gpio_desc *gpiod_enable;
-};
-
-static int drv_event(struct snd_soc_dapm_widget *w,
-		     struct snd_kcontrol *control, int event)
-{
-	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
-	struct dio2125 *priv = snd_soc_component_get_drvdata(c);
-	int val;
-
-	switch (event) {
-	case SND_SOC_DAPM_POST_PMU:
-		val = 1;
-		break;
-	case SND_SOC_DAPM_PRE_PMD:
-		val = 0;
-		break;
-	default:
-		WARN(1, "Unexpected event");
-		return -EINVAL;
-	}
-
-	gpiod_set_value_cansleep(priv->gpiod_enable, val);
-
-	return 0;
-}
-
-static const struct snd_soc_dapm_widget dio2125_dapm_widgets[] = {
-	SND_SOC_DAPM_INPUT("INL"),
-	SND_SOC_DAPM_INPUT("INR"),
-	SND_SOC_DAPM_OUT_DRV_E("DRV", SND_SOC_NOPM, 0, 0, NULL, 0, drv_event,
-			       (SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD)),
-	SND_SOC_DAPM_OUTPUT("OUTL"),
-	SND_SOC_DAPM_OUTPUT("OUTR"),
-};
-
-static const struct snd_soc_dapm_route dio2125_dapm_routes[] = {
-	{ "DRV", NULL, "INL" },
-	{ "DRV", NULL, "INR" },
-	{ "OUTL", NULL, "DRV" },
-	{ "OUTR", NULL, "DRV" },
-};
-
-static const struct snd_soc_component_driver dio2125_component_driver = {
-	.dapm_widgets		= dio2125_dapm_widgets,
-	.num_dapm_widgets	= ARRAY_SIZE(dio2125_dapm_widgets),
-	.dapm_routes		= dio2125_dapm_routes,
-	.num_dapm_routes	= ARRAY_SIZE(dio2125_dapm_routes),
-};
-
-static int dio2125_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct dio2125 *priv;
-	int err;
-
-	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
-	if (priv == NULL)
-		return -ENOMEM;
-	platform_set_drvdata(pdev, priv);
-
-	priv->gpiod_enable = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
-	if (IS_ERR(priv->gpiod_enable)) {
-		err = PTR_ERR(priv->gpiod_enable);
-		if (err != -EPROBE_DEFER)
-			dev_err(dev, "Failed to get 'enable' gpio: %d", err);
-		return err;
-	}
-
-	return devm_snd_soc_register_component(dev, &dio2125_component_driver,
-					       NULL, 0);
-}
-
-#ifdef CONFIG_OF
-static const struct of_device_id dio2125_ids[] = {
-	{ .compatible = "dioo,dio2125", },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, dio2125_ids);
-#endif
-
-static struct platform_driver dio2125_driver = {
-	.driver = {
-		.name = DRV_NAME,
-		.of_match_table = of_match_ptr(dio2125_ids),
-	},
-	.probe = dio2125_probe,
-};
-
-module_platform_driver(dio2125_driver);
-
-MODULE_DESCRIPTION("ASoC DIO2125 output driver");
-MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
-MODULE_LICENSE("GPL");
diff --git a/sound/soc/codecs/simple-amplifier.c b/sound/soc/codecs/simple-amplifier.c
new file mode 100644
index 000000000000..6c27d4afaf3a
--- /dev/null
+++ b/sound/soc/codecs/simple-amplifier.c
@@ -0,0 +1,121 @@
+/*
+ * Copyright (c) 2017 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ * The full GNU General Public License is included in this distribution
+ * in the file called COPYING.
+ */
+
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <sound/soc.h>
+
+#define DRV_NAME "simple-amplifier"
+
+struct simple_amp {
+	struct gpio_desc *gpiod_enable;
+};
+
+static int drv_event(struct snd_soc_dapm_widget *w,
+		     struct snd_kcontrol *control, int event)
+{
+	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
+	struct simple_amp *priv = snd_soc_component_get_drvdata(c);
+	int val;
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		val = 1;
+		break;
+	case SND_SOC_DAPM_PRE_PMD:
+		val = 0;
+		break;
+	default:
+		WARN(1, "Unexpected event");
+		return -EINVAL;
+	}
+
+	gpiod_set_value_cansleep(priv->gpiod_enable, val);
+
+	return 0;
+}
+
+static const struct snd_soc_dapm_widget simple_amp_dapm_widgets[] = {
+	SND_SOC_DAPM_INPUT("INL"),
+	SND_SOC_DAPM_INPUT("INR"),
+	SND_SOC_DAPM_OUT_DRV_E("DRV", SND_SOC_NOPM, 0, 0, NULL, 0, drv_event,
+			       (SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD)),
+	SND_SOC_DAPM_OUTPUT("OUTL"),
+	SND_SOC_DAPM_OUTPUT("OUTR"),
+};
+
+static const struct snd_soc_dapm_route simple_amp_dapm_routes[] = {
+	{ "DRV", NULL, "INL" },
+	{ "DRV", NULL, "INR" },
+	{ "OUTL", NULL, "DRV" },
+	{ "OUTR", NULL, "DRV" },
+};
+
+static const struct snd_soc_component_driver simple_amp_component_driver = {
+	.dapm_widgets		= simple_amp_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(simple_amp_dapm_widgets),
+	.dapm_routes		= simple_amp_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(simple_amp_dapm_routes),
+};
+
+static int simple_amp_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct simple_amp *priv;
+	int err;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (priv == NULL)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+
+	priv->gpiod_enable = devm_gpiod_get(dev, "enable", GPIOD_OUT_LOW);
+	if (IS_ERR(priv->gpiod_enable)) {
+		err = PTR_ERR(priv->gpiod_enable);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'enable' gpio: %d", err);
+		return err;
+	}
+
+	return devm_snd_soc_register_component(dev,
+					       &simple_amp_component_driver,
+					       NULL, 0);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id simple_amp_ids[] = {
+	{ .compatible = "dioo,dio2125", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, simple_amp_ids);
+#endif
+
+static struct platform_driver simple_amp_driver = {
+	.driver = {
+		.name = DRV_NAME,
+		.of_match_table = of_match_ptr(simple_amp_ids),
+	},
+	.probe = simple_amp_probe,
+};
+
+module_platform_driver(simple_amp_driver);
+
+MODULE_DESCRIPTION("ASoC Simple Audio Amplifier driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 8ed237e83ce9ff4b3964a6b096beb1cbd3397d5a Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 26 Jun 2018 14:11:28 +0200
Subject: ASoC: simple-amplifer: add simple-amplifier compatible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add simple-audio-amplifier to the list of available compatible

Suggested-by: Nicolò Veronese <nicveronese@gmail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/simple-amplifier.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/simple-amplifier.c b/sound/soc/codecs/simple-amplifier.c
index 6c27d4afaf3a..85524acf3e9c 100644
--- a/sound/soc/codecs/simple-amplifier.c
+++ b/sound/soc/codecs/simple-amplifier.c
@@ -101,6 +101,7 @@ static int simple_amp_probe(struct platform_device *pdev)
 #ifdef CONFIG_OF
 static const struct of_device_id simple_amp_ids[] = {
 	{ .compatible = "dioo,dio2125", },
+	{ .compatible = "simple-audio-amplifier", },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, simple_amp_ids);
-- 
cgit v1.2.3


From 599eb9060c7ccaf6a8f0386ab89e3cb5c1f1fea4 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 27 Jun 2018 09:39:36 +0200
Subject: ASoC: tas571x: add tas5707 compatible

Add the tas5707 to the available compatibles of the tas571x driver

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/tas571x.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/tas571x.txt b/Documentation/devicetree/bindings/sound/tas571x.txt
index b4959f10b74b..7c8fd37c2f9e 100644
--- a/Documentation/devicetree/bindings/sound/tas571x.txt
+++ b/Documentation/devicetree/bindings/sound/tas571x.txt
@@ -7,6 +7,7 @@ powerdown (optional).
 Required properties:
 
 - compatible: should be one of the following:
+  - "ti,tas5707"
   - "ti,tas5711",
   - "ti,tas5717",
   - "ti,tas5719",
-- 
cgit v1.2.3


From f516d32262a4c0fef3fccdf2a82671f54f5c1e33 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 27 Jun 2018 09:39:37 +0200
Subject: ASoC: tas517x: add tas5707 support

Add support for the tas5707 audio power amplifier.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Kconfig   |   5 ++-
 sound/soc/codecs/tas571x.c | 110 +++++++++++++++++++++++++++++++++++++++++++++
 sound/soc/codecs/tas571x.h |  16 +++++++
 3 files changed, 130 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 53c2d726bedf..6d1674699385 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -959,8 +959,11 @@ config SND_SOC_TAS5086
 	depends on I2C
 
 config SND_SOC_TAS571X
-	tristate "Texas Instruments TAS5711/TAS5717/TAS5719/TAS5721 power amplifiers"
+	tristate "Texas Instruments TAS571x power amplifiers"
 	depends on I2C
+	help
+	  Enable support for Texas Instruments TAS5707, TAS5711, TAS5717,
+	  TAS5719 and TAS5721 power amplifiers
 
 config SND_SOC_TAS5720
 	tristate "Texas Instruments TAS5720 Mono Audio amplifier"
diff --git a/sound/soc/codecs/tas571x.c b/sound/soc/codecs/tas571x.c
index 52f34c94ec25..ca2dfe12344e 100644
--- a/sound/soc/codecs/tas571x.c
+++ b/sound/soc/codecs/tas571x.c
@@ -7,6 +7,9 @@
  * TAS5721 support:
  * Copyright (C) 2016 Petr Kulhavy, Barix AG <petr@barix.com>
  *
+ * TAS5707 support:
+ * Copyright (C) 2018 Jerome Brunet, Baylibre SAS <jbrunet@baylibre.com>
+ *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
  * the Free Software Foundation; either version 2 of the License, or
@@ -444,6 +447,111 @@ static const struct tas571x_chip tas5711_chip = {
 	.vol_reg_size			= 1,
 };
 
+static const struct regmap_range tas5707_volatile_regs_range[] = {
+	regmap_reg_range(TAS571X_CLK_CTRL_REG,  TAS571X_ERR_STATUS_REG),
+	regmap_reg_range(TAS571X_OSC_TRIM_REG,  TAS571X_OSC_TRIM_REG),
+	regmap_reg_range(TAS5707_CH1_BQ0_REG, TAS5707_CH2_BQ6_REG),
+};
+
+static const struct regmap_access_table tas5707_volatile_regs = {
+	.yes_ranges =	tas5707_volatile_regs_range,
+	.n_yes_ranges =	ARRAY_SIZE(tas5707_volatile_regs_range),
+
+};
+
+static const DECLARE_TLV_DB_SCALE(tas5707_volume_tlv, -7900, 50, 1);
+
+static const char * const tas5707_volume_slew_step_txt[] = {
+	"256", "512", "1024", "2048",
+};
+
+static const unsigned int tas5707_volume_slew_step_values[] = {
+	3, 0, 1, 2,
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(tas5707_volume_slew_step_enum,
+				  TAS571X_VOL_CFG_REG, 0, 0x3,
+				  tas5707_volume_slew_step_txt,
+				  tas5707_volume_slew_step_values);
+
+static const struct snd_kcontrol_new tas5707_controls[] = {
+	SOC_SINGLE_TLV("Master Volume",
+		       TAS571X_MVOL_REG,
+		       0, 0xff, 1, tas5707_volume_tlv),
+	SOC_DOUBLE_R_TLV("Speaker Volume",
+			 TAS571X_CH1_VOL_REG,
+			 TAS571X_CH2_VOL_REG,
+			 0, 0xff, 1, tas5707_volume_tlv),
+	SOC_DOUBLE("Speaker Switch",
+		   TAS571X_SOFT_MUTE_REG,
+		   TAS571X_SOFT_MUTE_CH1_SHIFT, TAS571X_SOFT_MUTE_CH2_SHIFT,
+		   1, 1),
+
+	SOC_ENUM("Slew Rate Steps", tas5707_volume_slew_step_enum),
+
+	BIQUAD_COEFS("CH1 - Biquad 0", TAS5707_CH1_BQ0_REG),
+	BIQUAD_COEFS("CH1 - Biquad 1", TAS5707_CH1_BQ1_REG),
+	BIQUAD_COEFS("CH1 - Biquad 2", TAS5707_CH1_BQ2_REG),
+	BIQUAD_COEFS("CH1 - Biquad 3", TAS5707_CH1_BQ3_REG),
+	BIQUAD_COEFS("CH1 - Biquad 4", TAS5707_CH1_BQ4_REG),
+	BIQUAD_COEFS("CH1 - Biquad 5", TAS5707_CH1_BQ5_REG),
+	BIQUAD_COEFS("CH1 - Biquad 6", TAS5707_CH1_BQ6_REG),
+
+	BIQUAD_COEFS("CH2 - Biquad 0", TAS5707_CH2_BQ0_REG),
+	BIQUAD_COEFS("CH2 - Biquad 1", TAS5707_CH2_BQ1_REG),
+	BIQUAD_COEFS("CH2 - Biquad 2", TAS5707_CH2_BQ2_REG),
+	BIQUAD_COEFS("CH2 - Biquad 3", TAS5707_CH2_BQ3_REG),
+	BIQUAD_COEFS("CH2 - Biquad 4", TAS5707_CH2_BQ4_REG),
+	BIQUAD_COEFS("CH2 - Biquad 5", TAS5707_CH2_BQ5_REG),
+	BIQUAD_COEFS("CH2 - Biquad 6", TAS5707_CH2_BQ6_REG),
+};
+
+static const struct reg_default tas5707_reg_defaults[] = {
+	{TAS571X_CLK_CTRL_REG,		0x6c},
+	{TAS571X_DEV_ID_REG,		0x70},
+	{TAS571X_ERR_STATUS_REG,	0x00},
+	{TAS571X_SYS_CTRL_1_REG,	0xa0},
+	{TAS571X_SDI_REG,		0x05},
+	{TAS571X_SYS_CTRL_2_REG,	0x40},
+	{TAS571X_SOFT_MUTE_REG,		0x00},
+	{TAS571X_MVOL_REG,		0xff},
+	{TAS571X_CH1_VOL_REG,		0x30},
+	{TAS571X_CH2_VOL_REG,		0x30},
+	{TAS571X_VOL_CFG_REG,		0x91},
+	{TAS571X_MODULATION_LIMIT_REG,	0x02},
+	{TAS571X_IC_DELAY_CH1_REG,	0xac},
+	{TAS571X_IC_DELAY_CH2_REG,	0x54},
+	{TAS571X_IC_DELAY_CH3_REG,	0xac},
+	{TAS571X_IC_DELAY_CH4_REG,	0x54},
+	{TAS571X_START_STOP_PERIOD_REG,	0x0f},
+	{TAS571X_OSC_TRIM_REG,		0x82},
+	{TAS571X_BKND_ERR_REG,		0x02},
+	{TAS571X_INPUT_MUX_REG,		0x17772},
+	{TAS571X_PWM_MUX_REG,		0x1021345},
+};
+
+static const struct regmap_config tas5707_regmap_config = {
+	.reg_bits			= 8,
+	.val_bits			= 32,
+	.max_register			= 0xff,
+	.reg_read			= tas571x_reg_read,
+	.reg_write			= tas571x_reg_write,
+	.reg_defaults			= tas5707_reg_defaults,
+	.num_reg_defaults		= ARRAY_SIZE(tas5707_reg_defaults),
+	.cache_type			= REGCACHE_RBTREE,
+	.wr_table			= &tas571x_write_regs,
+	.volatile_table			= &tas5707_volatile_regs,
+};
+
+static const struct tas571x_chip tas5707_chip = {
+	.supply_names			= tas5711_supply_names,
+	.num_supply_names		= ARRAY_SIZE(tas5711_supply_names),
+	.controls			= tas5707_controls,
+	.num_controls			= ARRAY_SIZE(tas5707_controls),
+	.regmap_config			= &tas5707_regmap_config,
+	.vol_reg_size			= 1,
+};
+
 static const char *const tas5717_supply_names[] = {
 	"AVDD",
 	"DVDD",
@@ -775,6 +883,7 @@ static int tas571x_i2c_remove(struct i2c_client *client)
 }
 
 static const struct of_device_id tas571x_of_match[] = {
+	{ .compatible = "ti,tas5707", .data = &tas5707_chip, },
 	{ .compatible = "ti,tas5711", .data = &tas5711_chip, },
 	{ .compatible = "ti,tas5717", .data = &tas5717_chip, },
 	{ .compatible = "ti,tas5719", .data = &tas5717_chip, },
@@ -784,6 +893,7 @@ static const struct of_device_id tas571x_of_match[] = {
 MODULE_DEVICE_TABLE(of, tas571x_of_match);
 
 static const struct i2c_device_id tas571x_i2c_id[] = {
+	{ "tas5707", (kernel_ulong_t) &tas5707_chip },
 	{ "tas5711", (kernel_ulong_t) &tas5711_chip },
 	{ "tas5717", (kernel_ulong_t) &tas5717_chip },
 	{ "tas5719", (kernel_ulong_t) &tas5717_chip },
diff --git a/sound/soc/codecs/tas571x.h b/sound/soc/codecs/tas571x.h
index c45677bc26ad..bd23e89cfe79 100644
--- a/sound/soc/codecs/tas571x.h
+++ b/sound/soc/codecs/tas571x.h
@@ -53,6 +53,22 @@
 #define TAS571X_PWM_MUX_REG		0x25
 
 /* 20-byte biquad registers */
+#define TAS5707_CH1_BQ0_REG		0x29
+#define TAS5707_CH1_BQ1_REG		0x2a
+#define TAS5707_CH1_BQ2_REG		0x2b
+#define TAS5707_CH1_BQ3_REG		0x2c
+#define TAS5707_CH1_BQ4_REG		0x2d
+#define TAS5707_CH1_BQ5_REG		0x2e
+#define TAS5707_CH1_BQ6_REG		0x2f
+
+#define TAS5707_CH2_BQ0_REG		0x30
+#define TAS5707_CH2_BQ1_REG		0x31
+#define TAS5707_CH2_BQ2_REG		0x32
+#define TAS5707_CH2_BQ3_REG		0x33
+#define TAS5707_CH2_BQ4_REG		0x34
+#define TAS5707_CH2_BQ5_REG		0x35
+#define TAS5707_CH2_BQ6_REG		0x36
+
 #define TAS5717_CH1_BQ0_REG		0x26
 #define TAS5717_CH1_BQ1_REG		0x27
 #define TAS5717_CH1_BQ2_REG		0x28
-- 
cgit v1.2.3


From a3e77e1655961f4ed7ad4eea8763aed418bd932e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:13 +0300
Subject: drm/rockchip: Use drm_crtc_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_crtc_mask() where appropriate.

Cc: Sandy Huang <hjc@rock-chips.com>
Cc: "Heiko Stübner" <heiko@sntech.de>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-7-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index c9222119767d..effecbed2d11 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -1308,7 +1308,7 @@ static int vop_create_crtc(struct vop *vop)
 	for (i = 0; i < vop_data->win_size; i++) {
 		struct vop_win *vop_win = &vop->win[i];
 		const struct vop_win_data *win_data = vop_win->data;
-		unsigned long possible_crtcs = 1 << drm_crtc_index(crtc);
+		unsigned long possible_crtcs = drm_crtc_mask(crtc);
 
 		if (win_data->type != DRM_PLANE_TYPE_OVERLAY)
 			continue;
-- 
cgit v1.2.3


From 106359177a57c7ea4a0c31e9cd24e6313b355ed7 Mon Sep 17 00:00:00 2001
From: Sandy Huang <hjc@rock-chips.com>
Date: Tue, 26 Jun 2018 16:16:44 +0800
Subject: drm/rockchip: vop: fixup linebuffer mode calc error

linebuffer mode should be LB_YUV_3840X5 when width is bigger than 1280
in yuv mode.

Separate yuv and rgb case makes the scl_vop_cal_lb_mode() logic clearer.

Signed-off-by: Sandy Huang <hjc@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://patchwork.freedesktop.org/patch/msgid/1530001004-25036-1-git-send-email-hjc@rock-chips.com
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop.h | 23 +++++++++++++----------
 1 file changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
index 084acdd0019a..fcb91041a666 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.h
@@ -331,16 +331,19 @@ static inline int scl_vop_cal_lb_mode(int width, bool is_yuv)
 {
 	int lb_mode;
 
-	if (width > 2560)
-		lb_mode = LB_RGB_3840X2;
-	else if (width > 1920)
-		lb_mode = LB_RGB_2560X4;
-	else if (!is_yuv)
-		lb_mode = LB_RGB_1920X5;
-	else if (width > 1280)
-		lb_mode = LB_YUV_3840X5;
-	else
-		lb_mode = LB_YUV_2560X8;
+	if (is_yuv) {
+		if (width > 1280)
+			lb_mode = LB_YUV_3840X5;
+		else
+			lb_mode = LB_YUV_2560X8;
+	} else {
+		if (width > 2560)
+			lb_mode = LB_RGB_3840X2;
+		else if (width > 1920)
+			lb_mode = LB_RGB_2560X4;
+		else
+			lb_mode = LB_RGB_1920X5;
+	}
 
 	return lb_mode;
 }
-- 
cgit v1.2.3


From 67ca07e7ac10d7cdc2aa7ac216cab7fb64c95e50 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 26 Jun 2018 17:22:32 +0300
Subject: drm/i915/icl: Add power well support

Add the definition for ICL power wells and their mapping to power
domains. On ICL there are 3 power well control registers, we'll select
the correct one based on higher bits of the power well ID. The offset
for the control and status flags within this register is based on the
lower bits of the ID as on older platforms.

As the DC state programming is also the same as on old platforms we can
reuse the corresponding helpers. For this we mark here the DC-off power
well as shared among multiple platforms.

Other than the above the delta between old platforms and ICL:
- Pipe C has its own power well, so we can save some additional power in the
  pipe A+B and (non-eDP) pipe A configurations.
- Power wells for port E/F DDI/AUX IO and Thunderbolt 1-4 AUX IO

v2:
- Rebase on drm-tip after prep patch for this was merged there as
  requested by Paulo.
- Actually add the new AUX and DDI power well control regs (Rakshmi)

v3:
- Fix power well register names in code comments
- Add TBT AUX->power well 3 dependency

v4:
- Rebase

v5:
- Detach AUX power wells from the INIT power domain. These power wells
  can only be enabled in a TC/TBT connected state and otherwise not
  needed during driver initialization.

v6:
- Use _MMIO_PORT(...) instead _MMIO(_PICK(...)) (Paulo)
  Fix checkpatch warnings.

Cc: Animesh Manna <animesh.manna@intel.com>
Cc: Rakshmi Bhatia <rakshmi.bhatia@intel.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Animesh Manna <animesh.manna@intel.com> (v1)
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626142232.22361-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h         |  78 +++++++-
 drivers/gpu/drm/i915/intel_display.h    |   4 +
 drivers/gpu/drm/i915/intel_runtime_pm.c | 329 +++++++++++++++++++++++++++++++-
 3 files changed, 395 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 43db91c19f52..2c20dc0db648 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1045,13 +1045,13 @@ enum i915_power_well_id {
 
 	/*
 	 * HSW/BDW
-	 *  - HSW_PWR_WELL_CTL_DRIVER(0) (status bit: id*2, req bit: id*2+1)
+	 *  - _HSW_PWR_WELL_CTL1-4 (status bit: id*2, req bit: id*2+1)
 	 */
 	HSW_DISP_PW_GLOBAL = 15,
 
 	/*
 	 * GEN9+
-	 *  - HSW_PWR_WELL_CTL_DRIVER(0) (status bit: id*2, req bit: id*2+1)
+	 *  - _HSW_PWR_WELL_CTL1-4 (status bit: id*2, req bit: id*2+1)
 	 */
 	SKL_DISP_PW_MISC_IO = 0,
 	SKL_DISP_PW_DDI_A_E,
@@ -1075,17 +1075,54 @@ enum i915_power_well_id {
 	SKL_DISP_PW_2,
 
 	/* - custom power wells */
-	SKL_DISP_PW_DC_OFF,
 	BXT_DPIO_CMN_A,
 	BXT_DPIO_CMN_BC,
-	GLK_DPIO_CMN_C,			/* 19 */
+	GLK_DPIO_CMN_C,			/* 18 */
+
+	/*
+	 * GEN11+
+	 *  - _HSW_PWR_WELL_CTL1-4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_1 = 0,
+	ICL_DISP_PW_2,
+	ICL_DISP_PW_3,
+	ICL_DISP_PW_4,
+
+	/*
+	 *  - _HSW_PWR_WELL_CTL_AUX1/2/4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_AUX_A = 16,
+	ICL_DISP_PW_AUX_B,
+	ICL_DISP_PW_AUX_C,
+	ICL_DISP_PW_AUX_D,
+	ICL_DISP_PW_AUX_E,
+	ICL_DISP_PW_AUX_F,
+
+	ICL_DISP_PW_AUX_TBT1 = 24,
+	ICL_DISP_PW_AUX_TBT2,
+	ICL_DISP_PW_AUX_TBT3,
+	ICL_DISP_PW_AUX_TBT4,
+
+	/*
+	 *  - _HSW_PWR_WELL_CTL_DDI1/2/4
+	 *    (status bit: (id&15)*2, req bit:(id&15)*2+1)
+	 */
+	ICL_DISP_PW_DDI_A = 32,
+	ICL_DISP_PW_DDI_B,
+	ICL_DISP_PW_DDI_C,
+	ICL_DISP_PW_DDI_D,
+	ICL_DISP_PW_DDI_E,
+	ICL_DISP_PW_DDI_F,                      /* 37 */
 
 	/*
 	 * Multiple platforms.
 	 * Must start following the highest ID of any platform.
 	 * - custom power wells
 	 */
-	I915_DISP_PW_ALWAYS_ON = 20,
+	SKL_DISP_PW_DC_OFF = 38,
+	I915_DISP_PW_ALWAYS_ON,
 };
 
 #define PUNIT_REG_PWRGT_CTRL			0x60
@@ -1679,6 +1716,13 @@ enum i915_power_well_id {
 #define   IREF1RC_OFFSET_MASK		(0xFF << IREF1RC_OFFSET_SHIFT)
 #define BXT_PORT_CL1CM_DW10(phy)	_BXT_PHY((phy), _PORT_CL1CM_DW10_BC)
 
+#define _ICL_PORT_CL_DW12_A		0x162030
+#define _ICL_PORT_CL_DW12_B		0x6C030
+#define   ICL_LANE_ENABLE_AUX		(1 << 0)
+#define ICL_PORT_CL_DW12(port)		_MMIO_PORT((port),		\
+						   _ICL_PORT_CL_DW12_A, \
+						   _ICL_PORT_CL_DW12_B)
+
 #define _PORT_CL1CM_DW28_A		0x162070
 #define _PORT_CL1CM_DW28_BC		0x6C070
 #define   OCL1_POWER_DOWN_EN		(1 << 23)
@@ -8564,6 +8608,14 @@ enum {
 #define _HSW_PWR_WELL_CTL3			0x45408
 #define _HSW_PWR_WELL_CTL4			0x4540C
 
+#define _ICL_PWR_WELL_CTL_AUX1			0x45440
+#define _ICL_PWR_WELL_CTL_AUX2			0x45444
+#define _ICL_PWR_WELL_CTL_AUX4			0x4544C
+
+#define _ICL_PWR_WELL_CTL_DDI1			0x45450
+#define _ICL_PWR_WELL_CTL_DDI2			0x45454
+#define _ICL_PWR_WELL_CTL_DDI4			0x4545C
+
 /*
  * Each power well control register contains up to 16 (request, status) HW
  * flag tuples. The register index and HW flag shift is determined by the
@@ -8573,14 +8625,20 @@ enum {
  */
 #define _HSW_PW_REG_IDX(pw)			((pw) >> 4)
 #define _HSW_PW_SHIFT(pw)			(((pw) & 0xf) * 2)
-/* TODO: Add all PWR_WELL_CTL registers below for new platforms */
 #define HSW_PWR_WELL_CTL_BIOS(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL1))
+						    _HSW_PWR_WELL_CTL1,	       \
+						    _ICL_PWR_WELL_CTL_AUX1,    \
+						    _ICL_PWR_WELL_CTL_DDI1))
 #define HSW_PWR_WELL_CTL_DRIVER(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL2))
+						    _HSW_PWR_WELL_CTL2,	       \
+						    _ICL_PWR_WELL_CTL_AUX2,    \
+						    _ICL_PWR_WELL_CTL_DDI2))
+/* KVMR doesn't have a reg for AUX or DDI power well control */
 #define HSW_PWR_WELL_CTL_KVMR		_MMIO(_HSW_PWR_WELL_CTL3)
 #define HSW_PWR_WELL_CTL_DEBUG(pw)	_MMIO(_PICK(_HSW_PW_REG_IDX(pw),       \
-						    _HSW_PWR_WELL_CTL4))
+						    _HSW_PWR_WELL_CTL4,	       \
+						    _ICL_PWR_WELL_CTL_AUX4,    \
+						    _ICL_PWR_WELL_CTL_DDI4))
 
 #define   HSW_PWR_WELL_CTL_REQ(pw)		(1 << (_HSW_PW_SHIFT(pw) + 1))
 #define   HSW_PWR_WELL_CTL_STATE(pw)		(1 << _HSW_PW_SHIFT(pw))
@@ -8601,6 +8659,8 @@ enum skl_power_gate {
 #define  SKL_FUSE_DOWNLOAD_STATUS		(1 << 31)
 /* PG0 (HW control->no power well ID), PG1..PG2 (SKL_DISP_PW1..SKL_DISP_PW2) */
 #define  SKL_PW_TO_PG(pw)			((pw) - SKL_DISP_PW_1 + SKL_PG1)
+/* PG0 (HW control->no power well ID), PG1..PG4 (ICL_DISP_PW1..ICL_DISP_PW4) */
+#define  ICL_PW_TO_PG(pw)			((pw) - ICL_DISP_PW_1 + SKL_PG1)
 #define  SKL_FUSE_PG_DIST_STATUS(pg)		(1 << (27 - (pg)))
 
 #define _CNL_AUX_REG_IDX(pw)		((pw) - 9)
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index dfb02da73ac8..a77dd29db2ec 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -199,6 +199,10 @@ enum intel_display_power_domain {
 	POWER_DOMAIN_AUX_E,
 	POWER_DOMAIN_AUX_F,
 	POWER_DOMAIN_AUX_IO_A,
+	POWER_DOMAIN_AUX_TBT1,
+	POWER_DOMAIN_AUX_TBT2,
+	POWER_DOMAIN_AUX_TBT3,
+	POWER_DOMAIN_AUX_TBT4,
 	POWER_DOMAIN_GMBUS,
 	POWER_DOMAIN_MODESET,
 	POWER_DOMAIN_GT_IRQ,
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 2969787201ef..d81b2cfe1c5e 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -134,6 +134,14 @@ intel_display_power_domain_str(enum intel_display_power_domain domain)
 		return "AUX_F";
 	case POWER_DOMAIN_AUX_IO_A:
 		return "AUX_IO_A";
+	case POWER_DOMAIN_AUX_TBT1:
+		return "AUX_TBT1";
+	case POWER_DOMAIN_AUX_TBT2:
+		return "AUX_TBT2";
+	case POWER_DOMAIN_AUX_TBT3:
+		return "AUX_TBT3";
+	case POWER_DOMAIN_AUX_TBT4:
+		return "AUX_TBT4";
 	case POWER_DOMAIN_GMBUS:
 		return "GMBUS";
 	case POWER_DOMAIN_INIT:
@@ -384,7 +392,8 @@ static void hsw_power_well_enable(struct drm_i915_private *dev_priv,
 	u32 val;
 
 	if (wait_fuses) {
-		pg = SKL_PW_TO_PG(id);
+		pg = INTEL_GEN(dev_priv) >= 11 ? ICL_PW_TO_PG(id) :
+						 SKL_PW_TO_PG(id);
 		/*
 		 * For PW1 we have to wait both for the PW0/PG0 fuse state
 		 * before enabling the power well and PW1/PG1's own fuse
@@ -430,6 +439,43 @@ static void hsw_power_well_disable(struct drm_i915_private *dev_priv,
 	hsw_wait_for_power_well_disable(dev_priv, power_well);
 }
 
+#define ICL_AUX_PW_TO_PORT(pw)	((pw) - ICL_DISP_PW_AUX_A)
+
+static void
+icl_combo_phy_aux_power_well_enable(struct drm_i915_private *dev_priv,
+				    struct i915_power_well *power_well)
+{
+	enum i915_power_well_id id = power_well->id;
+	enum port port = ICL_AUX_PW_TO_PORT(id);
+	u32 val;
+
+	val = I915_READ(HSW_PWR_WELL_CTL_DRIVER(id));
+	I915_WRITE(HSW_PWR_WELL_CTL_DRIVER(id), val | HSW_PWR_WELL_CTL_REQ(id));
+
+	val = I915_READ(ICL_PORT_CL_DW12(port));
+	I915_WRITE(ICL_PORT_CL_DW12(port), val | ICL_LANE_ENABLE_AUX);
+
+	hsw_wait_for_power_well_enable(dev_priv, power_well);
+}
+
+static void
+icl_combo_phy_aux_power_well_disable(struct drm_i915_private *dev_priv,
+				     struct i915_power_well *power_well)
+{
+	enum i915_power_well_id id = power_well->id;
+	enum port port = ICL_AUX_PW_TO_PORT(id);
+	u32 val;
+
+	val = I915_READ(ICL_PORT_CL_DW12(port));
+	I915_WRITE(ICL_PORT_CL_DW12(port), val & ~ICL_LANE_ENABLE_AUX);
+
+	val = I915_READ(HSW_PWR_WELL_CTL_DRIVER(id));
+	I915_WRITE(HSW_PWR_WELL_CTL_DRIVER(id),
+		   val & ~HSW_PWR_WELL_CTL_REQ(id));
+
+	hsw_wait_for_power_well_disable(dev_priv, power_well);
+}
+
 /*
  * We should only use the power well if we explicitly asked the hardware to
  * enable it, so check if it's enabled and also check if we've requested it to
@@ -1897,6 +1943,105 @@ void intel_display_power_put(struct drm_i915_private *dev_priv,
 	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
 	BIT_ULL(POWER_DOMAIN_INIT))
 
+/*
+ * ICL PW_0/PG_0 domains (HW/DMC control):
+ * - PCI
+ * - clocks except port PLL
+ * - central power except FBC
+ * - shared functions except pipe interrupts, pipe MBUS, DBUF registers
+ * ICL PW_1/PG_1 domains (HW/DMC control):
+ * - DBUF function
+ * - PIPE_A and its planes, except VGA
+ * - transcoder EDP + PSR
+ * - transcoder DSI
+ * - DDI_A
+ * - FBC
+ */
+#define ICL_PW_4_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PIPE_C) |			\
+	BIT_ULL(POWER_DOMAIN_PIPE_C_PANEL_FITTER) |	\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/* VDSC/joining */
+#define ICL_PW_3_POWER_DOMAINS (			\
+	ICL_PW_4_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_PIPE_B) |			\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_A) |		\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_B) |		\
+	BIT_ULL(POWER_DOMAIN_TRANSCODER_C) |		\
+	BIT_ULL(POWER_DOMAIN_PIPE_B_PANEL_FITTER) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_IO) |		\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_LANES) |	\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_B) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_C) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_D) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_E) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_F) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT1) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT2) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT3) |		\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT4) |		\
+	BIT_ULL(POWER_DOMAIN_VGA) |			\
+	BIT_ULL(POWER_DOMAIN_AUDIO) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/*
+	 * - transcoder WD
+	 * - KVMR (HW control)
+	 */
+#define ICL_PW_2_POWER_DOMAINS (			\
+	ICL_PW_3_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+	/*
+	 * - eDP/DSI VDSC
+	 * - KVMR (HW control)
+	 */
+#define ICL_DISPLAY_DC_OFF_POWER_DOMAINS (		\
+	ICL_PW_2_POWER_DOMAINS |			\
+	BIT_ULL(POWER_DOMAIN_MODESET) |			\
+	BIT_ULL(POWER_DOMAIN_AUX_A) |			\
+	BIT_ULL(POWER_DOMAIN_INIT))
+
+#define ICL_DDI_IO_A_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_A_IO))
+#define ICL_DDI_IO_B_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_B_IO))
+#define ICL_DDI_IO_C_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_C_IO))
+#define ICL_DDI_IO_D_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_D_IO))
+#define ICL_DDI_IO_E_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_E_IO))
+#define ICL_DDI_IO_F_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_PORT_DDI_F_IO))
+
+#define ICL_AUX_A_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_A))
+#define ICL_AUX_B_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_B))
+#define ICL_AUX_C_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_C))
+#define ICL_AUX_D_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_D))
+#define ICL_AUX_E_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_E))
+#define ICL_AUX_F_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_F))
+#define ICL_AUX_TBT1_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT1))
+#define ICL_AUX_TBT2_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT2))
+#define ICL_AUX_TBT3_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT3))
+#define ICL_AUX_TBT4_IO_POWER_DOMAINS (			\
+	BIT_ULL(POWER_DOMAIN_AUX_TBT4))
+
 static const struct i915_power_well_ops i9xx_always_on_power_well_ops = {
 	.sync_hw = i9xx_power_well_sync_hw_noop,
 	.enable = i9xx_always_on_power_well_noop,
@@ -2454,6 +2599,157 @@ static struct i915_power_well cnl_power_wells[] = {
 	},
 };
 
+static const struct i915_power_well_ops icl_combo_phy_aux_power_well_ops = {
+	.sync_hw = hsw_power_well_sync_hw,
+	.enable = icl_combo_phy_aux_power_well_enable,
+	.disable = icl_combo_phy_aux_power_well_disable,
+	.is_enabled = hsw_power_well_enabled,
+};
+
+static struct i915_power_well icl_power_wells[] = {
+	{
+		.name = "always-on",
+		.always_on = 1,
+		.domains = POWER_DOMAIN_MASK,
+		.ops = &i9xx_always_on_power_well_ops,
+		.id = I915_DISP_PW_ALWAYS_ON,
+	},
+	{
+		.name = "power well 1",
+		/* Handled by the DMC firmware */
+		.domains = 0,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_1,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "power well 2",
+		.domains = ICL_PW_2_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_2,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "DC off",
+		.domains = ICL_DISPLAY_DC_OFF_POWER_DOMAINS,
+		.ops = &gen9_dc_off_power_well_ops,
+		.id = SKL_DISP_PW_DC_OFF,
+	},
+	{
+		.name = "power well 3",
+		.domains = ICL_PW_3_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_3,
+		.hsw.irq_pipe_mask = BIT(PIPE_B),
+		.hsw.has_vga = true,
+		.hsw.has_fuses = true,
+	},
+	{
+		.name = "DDI A IO",
+		.domains = ICL_DDI_IO_A_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_A,
+	},
+	{
+		.name = "DDI B IO",
+		.domains = ICL_DDI_IO_B_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_B,
+	},
+	{
+		.name = "DDI C IO",
+		.domains = ICL_DDI_IO_C_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_C,
+	},
+	{
+		.name = "DDI D IO",
+		.domains = ICL_DDI_IO_D_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_D,
+	},
+	{
+		.name = "DDI E IO",
+		.domains = ICL_DDI_IO_E_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_E,
+	},
+	{
+		.name = "DDI F IO",
+		.domains = ICL_DDI_IO_F_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_DDI_F,
+	},
+	{
+		.name = "AUX A",
+		.domains = ICL_AUX_A_IO_POWER_DOMAINS,
+		.ops = &icl_combo_phy_aux_power_well_ops,
+		.id = ICL_DISP_PW_AUX_A,
+	},
+	{
+		.name = "AUX B",
+		.domains = ICL_AUX_B_IO_POWER_DOMAINS,
+		.ops = &icl_combo_phy_aux_power_well_ops,
+		.id = ICL_DISP_PW_AUX_B,
+	},
+	{
+		.name = "AUX C",
+		.domains = ICL_AUX_C_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_C,
+	},
+	{
+		.name = "AUX D",
+		.domains = ICL_AUX_D_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_D,
+	},
+	{
+		.name = "AUX E",
+		.domains = ICL_AUX_E_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_E,
+	},
+	{
+		.name = "AUX F",
+		.domains = ICL_AUX_F_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_F,
+	},
+	{
+		.name = "AUX TBT1",
+		.domains = ICL_AUX_TBT1_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT1,
+	},
+	{
+		.name = "AUX TBT2",
+		.domains = ICL_AUX_TBT2_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT2,
+	},
+	{
+		.name = "AUX TBT3",
+		.domains = ICL_AUX_TBT3_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT3,
+	},
+	{
+		.name = "AUX TBT4",
+		.domains = ICL_AUX_TBT4_IO_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_AUX_TBT4,
+	},
+	{
+		.name = "power well 4",
+		.domains = ICL_PW_4_POWER_DOMAINS,
+		.ops = &hsw_power_well_ops,
+		.id = ICL_DISP_PW_4,
+		.hsw.has_fuses = true,
+		.hsw.irq_pipe_mask = BIT(PIPE_C),
+	},
+};
+
 static int
 sanitize_disable_power_well_option(const struct drm_i915_private *dev_priv,
 				   int disable_power_well)
@@ -2471,7 +2767,7 @@ static uint32_t get_allowed_dc_mask(const struct drm_i915_private *dev_priv,
 	int requested_dc;
 	int max_dc;
 
-	if (IS_GEN9_BC(dev_priv) || IS_CANNONLAKE(dev_priv)) {
+	if (IS_GEN9_BC(dev_priv) || INTEL_INFO(dev_priv)->gen >= 10) {
 		max_dc = 2;
 		mask = 0;
 	} else if (IS_GEN9_LP(dev_priv)) {
@@ -2559,7 +2855,9 @@ int intel_power_domains_init(struct drm_i915_private *dev_priv)
 	 * The enabling order will be from lower to higher indexed wells,
 	 * the disabling order is reversed.
 	 */
-	if (IS_HASWELL(dev_priv)) {
+	if (IS_ICELAKE(dev_priv)) {
+		set_power_wells(power_domains, icl_power_wells);
+	} else if (IS_HASWELL(dev_priv)) {
 		set_power_wells(power_domains, hsw_power_wells);
 	} else if (IS_BROADWELL(dev_priv)) {
 		set_power_wells(power_domains, bdw_power_wells);
@@ -3026,6 +3324,8 @@ static void cnl_display_core_uninit(struct drm_i915_private *dev_priv)
 static void icl_display_core_init(struct drm_i915_private *dev_priv,
 				  bool resume)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *well;
 	enum port port;
 	u32 val;
 
@@ -3054,8 +3354,14 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 		I915_WRITE(ICL_PORT_CL_DW5(port), val);
 	}
 
-	/* 4. Enable power well 1 (PG1) and aux IO power. */
-	/* FIXME: ICL power wells code not here yet. */
+	/*
+	 * 4. Enable Power Well 1 (PG1).
+	 *    The AUX IO power wells will be enabled on demand.
+	 */
+	mutex_lock(&power_domains->lock);
+	well = lookup_power_well(dev_priv, ICL_DISP_PW_1);
+	intel_power_well_enable(dev_priv, well);
+	mutex_unlock(&power_domains->lock);
 
 	/* 5. Enable CDCLK. */
 	icl_init_cdclk(dev_priv);
@@ -3073,6 +3379,8 @@ static void icl_display_core_init(struct drm_i915_private *dev_priv,
 
 static void icl_display_core_uninit(struct drm_i915_private *dev_priv)
 {
+	struct i915_power_domains *power_domains = &dev_priv->power_domains;
+	struct i915_power_well *well;
 	enum port port;
 	u32 val;
 
@@ -3086,8 +3394,15 @@ static void icl_display_core_uninit(struct drm_i915_private *dev_priv)
 	/* 3. Disable CD clock */
 	icl_uninit_cdclk(dev_priv);
 
-	/* 4. Disable Power Well 1 (PG1) and Aux IO Power */
-	/* FIXME: ICL power wells code not here yet. */
+	/*
+	 * 4. Disable Power Well 1 (PG1).
+	 *    The AUX IO power wells are toggled on demand, so they are already
+	 *    disabled at this point.
+	 */
+	mutex_lock(&power_domains->lock);
+	well = lookup_power_well(dev_priv, ICL_DISP_PW_1);
+	intel_power_well_disable(dev_priv, well);
+	mutex_unlock(&power_domains->lock);
 
 	/* 5. Disable Comp */
 	for (port = PORT_A; port <= PORT_B; port++) {
-- 
cgit v1.2.3


From 17121d12a5c1089bdfce429bc6f7ae2c25d9d25d Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Wed, 23 May 2018 05:33:32 -0400
Subject: media: imx258: Check the rotation property has a value of 180

The driver only supports streaming images flipped horizontally and
vertically. In order to ensure that all current users will be fine if or
when support for upright streaming is added, require the presence of the
"rotation" control now.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Tested-by: "Lai, Jim" <jim.lai@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx258.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/media/i2c/imx258.c b/drivers/media/i2c/imx258.c
index f3b124723aa0..31a1e2294843 100644
--- a/drivers/media/i2c/imx258.c
+++ b/drivers/media/i2c/imx258.c
@@ -1221,6 +1221,14 @@ static int imx258_probe(struct i2c_client *client)
 	if (val != 19200000)
 		return -EINVAL;
 
+	/*
+	 * Check that the device is mounted upside down. The driver only
+	 * supports a single pixel order right now.
+	 */
+	ret = device_property_read_u32(&client->dev, "rotation", &val);
+	if (ret || val != 180)
+		return -EINVAL;
+
 	imx258 = devm_kzalloc(&client->dev, sizeof(*imx258), GFP_KERNEL);
 	if (!imx258)
 		return -ENOMEM;
-- 
cgit v1.2.3


From 3c46ab9d37e542dd28ee27ee31defe5f8b5e466c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 25 May 2018 11:25:09 -0400
Subject: media: v4l: cadence: include linux/slab.h

I ran into a randconfig build error with the new driver:

drivers/media/platform/cadence/cdns-csi2tx.c: In function 'csi2tx_probe':
drivers/media/platform/cadence/cdns-csi2tx.c:477:11: error: implicit declaration of function 'kzalloc'; did you mean 'd_alloc'? [-Werror=implicit-function-declaration]

kzalloc() is declared in linux/slab.h, so let's include this to make it
build in all configurations.

Fixes: 84b477e6d4bc ("media: v4l: cadence: Add Cadence MIPI-CSI2 TX driver")

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Maxime Ripard <maxime.ripard@bootlin.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/cadence/cdns-csi2rx.c | 1 +
 drivers/media/platform/cadence/cdns-csi2tx.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/media/platform/cadence/cdns-csi2rx.c b/drivers/media/platform/cadence/cdns-csi2rx.c
index a0f02916006b..43e43c7b3e98 100644
--- a/drivers/media/platform/cadence/cdns-csi2rx.c
+++ b/drivers/media/platform/cadence/cdns-csi2rx.c
@@ -13,6 +13,7 @@
 #include <linux/of_graph.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
diff --git a/drivers/media/platform/cadence/cdns-csi2tx.c b/drivers/media/platform/cadence/cdns-csi2tx.c
index dfa1d88d955b..40d0de690ff4 100644
--- a/drivers/media/platform/cadence/cdns-csi2tx.c
+++ b/drivers/media/platform/cadence/cdns-csi2tx.c
@@ -13,6 +13,7 @@
 #include <linux/of.h>
 #include <linux/of_graph.h>
 #include <linux/platform_device.h>
+#include <linux/slab.h>
 
 #include <media/v4l2-ctrls.h>
 #include <media/v4l2-device.h>
-- 
cgit v1.2.3


From f6f630327de95c251741c1f682a94243c48f2b13 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 30 May 2018 18:07:10 -0400
Subject: media: v4l: cadence: add VIDEO_V4L2 dependency

The cadence media drivers can be built-in while the v4l2 core is a loadable
module. This is a mistake and leads to link errors:

drivers/media/v4l2-core/v4l2-fwnode.o: In function `v4l2_async_register_subdev_sensor_common':
v4l2-fwnode.c:(.text+0x12f0): undefined reference to `v4l2_async_subdev_notifier_register'
v4l2-fwnode.c:(.text+0x1304): undefined reference to `v4l2_async_register_subdev'
v4l2-fwnode.c:(.text+0x1318): undefined reference to `v4l2_async_notifier_unregister'
v4l2-fwnode.c:(.text+0x1338): undefined reference to `v4l2_async_notifier_cleanup'
cdns-csi2rx.c:(.text+0x9f8): undefined reference to `v4l2_subdev_init'
cdns-csi2rx.c:(.text+0xa78): undefined reference to `v4l2_async_register_subdev'
drivers/media/platform/cadence/cdns-csi2tx.o: In function `csi2tx_remove':
cdns-csi2tx.c:(.text+0x88): undefined reference to `v4l2_async_unregister_subdev'
drivers/media/platform/cadence/cdns-csi2tx.o: In function `csi2tx_probe':
cdns-csi2tx.c:(.text+0x884): undefined reference to `v4l2_subdev_init'
cdns-csi2tx.c:(.text+0xa9c): undefined reference to `v4l2_async_register_subdev'

An explicit Kconfig dependency on VIDEO_V4L2 avoids the problem.

Fixes: 1fc3b37f34f6 ("media: v4l: cadence: Add Cadence MIPI-CSI2 RX driver")

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Maxime Ripard <maxime.ripard@bootlin.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/cadence/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/media/platform/cadence/Kconfig b/drivers/media/platform/cadence/Kconfig
index 3bf0f2454384..cf6124da3c54 100644
--- a/drivers/media/platform/cadence/Kconfig
+++ b/drivers/media/platform/cadence/Kconfig
@@ -11,6 +11,7 @@ if VIDEO_CADENCE
 
 config VIDEO_CADENCE_CSI2RX
 	tristate "Cadence MIPI-CSI2 RX Controller"
+	depends on VIDEO_V4L2
 	depends on MEDIA_CONTROLLER
 	depends on VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
@@ -22,6 +23,7 @@ config VIDEO_CADENCE_CSI2RX
 
 config VIDEO_CADENCE_CSI2TX
 	tristate "Cadence MIPI-CSI2 TX Controller"
+	depends on VIDEO_V4L2
 	depends on MEDIA_CONTROLLER
 	depends on VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
-- 
cgit v1.2.3


From 375899cddcbb26881b03cb3fbdcfd600e4e67f4a Mon Sep 17 00:00:00 2001
From: Maninder Singh <maninder1.s@samsung.com>
Date: Fri, 1 Jun 2018 14:26:42 +0530
Subject: printk: make sure to print log on console.

This patch make sure printing of log on console if loglevel
at time of storing log is less than current console loglevel.

@why
In SMP printk can work asynchronously, logs can be missed on console
because it checks current log level at time of console_unlock,
not at time of storing logs.

func()
{
....
....
        console_verbose();  // user wants to have all the logs on console.
        pr_alert();
	dump_backtrace(); //prints with default loglevel.
        ...
        console_silent(); // stop all logs from printing on console.
}

Now if console_lock was owned by another process, the messages might
be handled after the consoles were silenced.

Reused flag LOG_NOCONS as its usage is gone long back by the commit
5c2992ee7fd8a29d0412 ("printk: remove console flushing special cases
for partial buffered lines").

Note that there are still some corner cases where this patch is not enough.
For example, when the messages are flushed later from printk_safe buffers
or when there are races between console_verbose() and console_silent()
callers.

Link: http://lkml.kernel.org/r/20180601090029epcas5p3cc93d4bfbebb3199f0a2684058da7e26~z-a_jkmrI2993329933epcas5p3q@epcas5p3.samsung.com
Cc: linux-kernel@vger.kernel.org
Cc: a.sahrawat@samsung.com
Cc: pankaj.m@samsung.com
Cc: v.narang@samsung.com
Cc: <maninder1.s@samsung.com>
Signed-off-by: Vaneet Narang <v.narang@samsung.com>
Signed-off-by: Maninder Singh <maninder1.s@samsung.com>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 kernel/printk/printk.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 247808333ba4..3999c295d6f7 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -349,7 +349,7 @@ static int console_msg_format = MSG_FORMAT_DEFAULT;
  */
 
 enum log_flags {
-	LOG_NOCONS	= 1,	/* already flushed, do not print to console */
+	LOG_NOCONS	= 1,	/* suppress print, do not print to console */
 	LOG_NEWLINE	= 2,	/* text ended with a newline */
 	LOG_PREFIX	= 4,	/* text started with a prefix */
 	LOG_CONT	= 8,	/* text is a fragment of a continuation line */
@@ -1886,6 +1886,9 @@ asmlinkage int vprintk_emit(int facility, int level,
 	if (dict)
 		lflags |= LOG_PREFIX|LOG_NEWLINE;
 
+	if (suppress_message_printing(level))
+		lflags |= LOG_NOCONS;
+
 	printed_len = log_output(facility, level, lflags, dict, dictlen, text, text_len);
 
 	logbuf_unlock_irqrestore(flags);
@@ -2349,11 +2352,10 @@ skip:
 			break;
 
 		msg = log_from_idx(console_idx);
-		if (suppress_message_printing(msg->level)) {
+		if (msg->flags & LOG_NOCONS) {
 			/*
-			 * Skip record we have buffered and already printed
-			 * directly to the console when we received it, and
-			 * record that has level above the console loglevel.
+			 * Skip record if !ignore_loglevel, and
+			 * record has level above the console loglevel.
 			 */
 			console_idx = log_next(console_idx);
 			console_seq++;
-- 
cgit v1.2.3


From 22eceb8bf3e8f1f9b2f566062d06b25807725d7f Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 19 Jun 2018 13:57:26 +0200
Subject: printk: Make CONSOLE_LOGLEVEL_QUIET configurable

The goal of passing the "quiet" option to the kernel is for the kernel
to be quiet unless something really is wrong.

Sofar passing quiet has been (mostly) equivalent to passing
loglevel=4 on the kernel commandline. Which means to show any messages
with a level of KERN_ERR or higher severity on the console.

In practice this often does not result in a quiet boot though, since
there are many false-positive or otherwise harmless error messages printed,
defeating the purpose of the quiet option. Esp. the ACPICA code is really
bad wrt this, but there are plenty of others too.

This commit makes CONSOLE_LOGLEVEL_QUIET configurable.

This for example will allow distros which want quiet to really mean quiet
to set CONSOLE_LOGLEVEL_QUIET so that only messages with a higher severity
then KERN_ERR (CRIT, ALERT, EMERG) get printed, avoiding an endless game
of whack-a-mole silencing harmless error messages.

Link: http://lkml.kernel.org/r/20180619115726.3098-1-hdegoede@redhat.com
To: Petr Mladek <pmladek@suse.com>
To: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 include/linux/printk.h |  6 +++---
 lib/Kconfig.debug      | 11 +++++++++++
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 6d7e800affd8..18602bb3eca8 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -50,15 +50,15 @@ static inline const char *printk_skip_headers(const char *buffer)
 /* We show everything that is MORE important than this.. */
 #define CONSOLE_LOGLEVEL_SILENT  0 /* Mum's the word */
 #define CONSOLE_LOGLEVEL_MIN	 1 /* Minimum loglevel we let people use */
-#define CONSOLE_LOGLEVEL_QUIET	 4 /* Shhh ..., when booted with "quiet" */
 #define CONSOLE_LOGLEVEL_DEBUG	10 /* issue debug messages */
 #define CONSOLE_LOGLEVEL_MOTORMOUTH 15	/* You can't shut this one up */
 
 /*
- * Default used to be hard-coded at 7, we're now allowing it to be set from
- * kernel config.
+ * Default used to be hard-coded at 7, quiet used to be hardcoded at 4,
+ * we're now allowing both to be set from kernel config.
  */
 #define CONSOLE_LOGLEVEL_DEFAULT CONFIG_CONSOLE_LOGLEVEL_DEFAULT
+#define CONSOLE_LOGLEVEL_QUIET	 CONFIG_CONSOLE_LOGLEVEL_QUIET
 
 extern int console_printk[];
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 76555479ae36..a7ef03009e9e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -30,6 +30,17 @@ config CONSOLE_LOGLEVEL_DEFAULT
 	  usage in the kernel. That is controlled by the MESSAGE_LOGLEVEL_DEFAULT
 	  option.
 
+config CONSOLE_LOGLEVEL_QUIET
+	int "quiet console loglevel (1-15)"
+	range 1 15
+	default "4"
+	help
+	  loglevel to use when "quiet" is passed on the kernel commandline.
+
+	  When "quiet" is passed on the kernel commandline this loglevel
+	  will be used as the loglevel. IOW passing "quiet" will be the
+	  equivalent of passing "loglevel=<CONSOLE_LOGLEVEL_QUIET>"
+
 config MESSAGE_LOGLEVEL_DEFAULT
 	int "Default message log level (1-7)"
 	range 1 7
-- 
cgit v1.2.3


From 63842c21347ecf4685d6ec008e667e61b0ead6e5 Mon Sep 17 00:00:00 2001
From: Namit Gupta <gupta.namit@samsung.com>
Date: Wed, 20 Jun 2018 19:26:19 +0530
Subject: printk: Remove unnecessary kmalloc() from syslog during clear

When the request is only for clearing logs, there is no need for
allocation/deallocation. Only the indexes need to be reset and returned.
Rest of the patch is mostly made up of changes because of indention.

Link: http://lkml.kernel.org/r/20180620135951epcas5p3bd2a8f25ec689ca333bce861b527dba2~54wyKcT0_3155531555epcas5p3y@epcas5p3.samsung.com
Cc: linux-kernel@vger.kernel.org
Cc: pankaj.m@samsung.com
Cc: a.sahrawat@samsung.com
Signed-off-by: Namit Gupta <gupta.namit@samsung.com>
Signed-off-by: Himanshu Maithani <himanshu.m@samsung.com>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 kernel/printk/printk.c | 109 ++++++++++++++++++++++++++-----------------------
 1 file changed, 58 insertions(+), 51 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 3999c295d6f7..16b02cc51a14 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1352,71 +1352,78 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 {
 	char *text;
 	int len = 0;
+	u64 next_seq;
+	u64 seq;
+	u32 idx;
+
+	if (!buf) {
+		if (clear) {
+			logbuf_lock_irq();
+			clear_seq = log_next_seq;
+			clear_idx = log_next_idx;
+			logbuf_unlock_irq();
+		}
+		return 0;
+	}
 
 	text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
 	if (!text)
 		return -ENOMEM;
 
 	logbuf_lock_irq();
-	if (buf) {
-		u64 next_seq;
-		u64 seq;
-		u32 idx;
+	/*
+	 * Find first record that fits, including all following records,
+	 * into the user-provided buffer for this dump.
+	 */
+	seq = clear_seq;
+	idx = clear_idx;
+	while (seq < log_next_seq) {
+		struct printk_log *msg = log_from_idx(idx);
 
-		/*
-		 * Find first record that fits, including all following records,
-		 * into the user-provided buffer for this dump.
-		 */
-		seq = clear_seq;
-		idx = clear_idx;
-		while (seq < log_next_seq) {
-			struct printk_log *msg = log_from_idx(idx);
-
-			len += msg_print_text(msg, true, NULL, 0);
-			idx = log_next(idx);
-			seq++;
-		}
+		len += msg_print_text(msg, true, NULL, 0);
+		idx = log_next(idx);
+		seq++;
+	}
 
-		/* move first record forward until length fits into the buffer */
-		seq = clear_seq;
-		idx = clear_idx;
-		while (len > size && seq < log_next_seq) {
-			struct printk_log *msg = log_from_idx(idx);
+	/* move first record forward until length fits into the buffer */
+	seq = clear_seq;
+	idx = clear_idx;
+	while (len > size && seq < log_next_seq) {
+		struct printk_log *msg = log_from_idx(idx);
 
-			len -= msg_print_text(msg, true, NULL, 0);
-			idx = log_next(idx);
-			seq++;
-		}
+		len -= msg_print_text(msg, true, NULL, 0);
+		idx = log_next(idx);
+		seq++;
+	}
 
-		/* last message fitting into this dump */
-		next_seq = log_next_seq;
+	/* last message fitting into this dump */
+	next_seq = log_next_seq;
 
-		len = 0;
-		while (len >= 0 && seq < next_seq) {
-			struct printk_log *msg = log_from_idx(idx);
-			int textlen;
+	len = 0;
+	while (len >= 0 && seq < next_seq) {
+		struct printk_log *msg = log_from_idx(idx);
+		int textlen;
 
-			textlen = msg_print_text(msg, true, text,
-						 LOG_LINE_MAX + PREFIX_MAX);
-			if (textlen < 0) {
-				len = textlen;
-				break;
-			}
-			idx = log_next(idx);
-			seq++;
+		textlen = msg_print_text(msg, true, text,
+					 LOG_LINE_MAX + PREFIX_MAX);
+		if (textlen < 0) {
+			len = textlen;
+			break;
+		}
+		idx = log_next(idx);
+		seq++;
 
-			logbuf_unlock_irq();
-			if (copy_to_user(buf + len, text, textlen))
-				len = -EFAULT;
-			else
-				len += textlen;
-			logbuf_lock_irq();
+		logbuf_unlock_irq();
+		if (copy_to_user(buf + len, text, textlen))
+			len = -EFAULT;
+		else
+			len += textlen;
+		logbuf_lock_irq();
 
-			if (seq < log_first_seq) {
-				/* messages are gone, move to next one */
-				seq = log_first_seq;
-				idx = log_first_idx;
-			}
+		if (seq < log_first_seq) {
+			/* messages are gone, move to next one */
+			seq = log_first_seq;
+			idx = log_first_idx;
 		}
 	}
 
-- 
cgit v1.2.3


From 4e61d7d1dd4c5b2e6da73852c24160e2ce7f8147 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 18 May 2018 06:51:23 -0400
Subject: media: v4l: rcar_fdp1: Change platform dependency to ARCH_RENESAS

The Renesas Fine Display Processor driver is used on Renesas R-Car SoCs
only.  Since commit 9b5ba0df4ea4f940 ("ARM: shmobile: Introduce
ARCH_RENESAS") is ARCH_RENESAS a more appropriate platform dependency
than the legacy ARCH_SHMOBILE, hence use the former.

This will allow to drop ARCH_SHMOBILE on ARM and ARM64 in the near
future.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 2728376b04b5..210b44a457eb 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -384,7 +384,7 @@ config VIDEO_SH_VEU
 config VIDEO_RENESAS_FDP1
 	tristate "Renesas Fine Display Processor"
 	depends on VIDEO_DEV && VIDEO_V4L2
-	depends on ARCH_SHMOBILE || COMPILE_TEST
+	depends on ARCH_RENESAS || COMPILE_TEST
 	depends on (!ARCH_RENESAS && !VIDEO_RENESAS_FCP) || VIDEO_RENESAS_FCP
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
-- 
cgit v1.2.3


From 9fab166a3e8f9e071de3418d27ffd03cdba2e9df Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 25 May 2018 11:25:10 -0400
Subject: media: cx231xx: fix RC_CORE dependency

With CONFIG_RC_CORE=m and VIDEO_CX231XX=y, we get a link failure:

drivers/media/usb/cx231xx/cx231xx-input.o: In function `cx231xx_ir_init':
cx231xx-input.c:(.text+0xd4): undefined reference to `rc_allocate_device'

This narrows down the dependency so that only valid configurations
are allowed.

Fixes: 84545d2a1436 ("media: cx231xx: Remove RC_CORE dependency")

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/cx231xx/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/cx231xx/Kconfig b/drivers/media/usb/cx231xx/Kconfig
index 0f13192634c7..9e5b3e7c3ef5 100644
--- a/drivers/media/usb/cx231xx/Kconfig
+++ b/drivers/media/usb/cx231xx/Kconfig
@@ -15,7 +15,7 @@ config VIDEO_CX231XX
 
 config VIDEO_CX231XX_RC
 	bool "Conexant cx231xx Remote Controller additional support"
-	depends on RC_CORE
+	depends on RC_CORE=y || RC_CORE=VIDEO_CX231XX
 	depends on VIDEO_CX231XX
 	default y
 	---help---
-- 
cgit v1.2.3


From adb78a8e24bbfe19df0d4dd19ee78cec351a5f04 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Wed, 27 Jun 2018 20:40:13 +0800
Subject: regulator: bd71837: Staticize ldo_2_volts

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd71837-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/bd71837-regulator.c b/drivers/regulator/bd71837-regulator.c
index 6eae4d0432a2..403b45de1262 100644
--- a/drivers/regulator/bd71837-regulator.c
+++ b/drivers/regulator/bd71837-regulator.c
@@ -195,7 +195,7 @@ static const struct regulator_linear_range bd71837_ldo1_voltage_ranges[] = {
  * LDO2
  * 0.8 or 0.9V
  */
-const unsigned int ldo_2_volts[] = {
+static const unsigned int ldo_2_volts[] = {
 	900000, 800000
 };
 
-- 
cgit v1.2.3


From ffdc4984100050d0c8e2f11f76a15ca36f5d9e37 Mon Sep 17 00:00:00 2001
From: Axel Lin <axel.lin@ingics.com>
Date: Wed, 27 Jun 2018 20:40:14 +0800
Subject: regulator: bd71837: Simplify bd71837_set_voltage_sel_restricted
 implementation

Signed-off-by: Axel Lin <axel.lin@ingics.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd71837-regulator.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/regulator/bd71837-regulator.c b/drivers/regulator/bd71837-regulator.c
index 403b45de1262..f57f42ed7160 100644
--- a/drivers/regulator/bd71837-regulator.c
+++ b/drivers/regulator/bd71837-regulator.c
@@ -73,14 +73,10 @@ static int bd71837_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 static int bd71837_set_voltage_sel_restricted(struct regulator_dev *rdev,
 						    unsigned int sel)
 {
-	int ret;
-
-	ret = regulator_is_enabled_regmap(rdev);
-	if (!ret)
-		ret = regulator_set_voltage_sel_regmap(rdev, sel);
-	else if (ret == 1)
-		ret = -EBUSY;
-	return ret;
+	if (regulator_is_enabled_regmap(rdev))
+		return -EBUSY;
+
+	return regulator_set_voltage_sel_regmap(rdev, sel);
 }
 
 static struct regulator_ops bd71837_ldo_regulator_ops = {
-- 
cgit v1.2.3


From 4ec7cece87b3ed21ffcd407c62fb2f151a366bc1 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 19 Jun 2018 02:43:35 -0700
Subject: wlcore: Add missing PM call for
 wlcore_cmd_wait_for_event_or_timeout()

Otherwise we can get:

WARNING: CPU: 0 PID: 55 at drivers/net/wireless/ti/wlcore/io.h:84

I've only seen this few times with the runtime PM patches enabled
so this one is probably not needed before that. This seems to
work currently based on the current PM implementation timer. Let's
apply this separately though in case others are hitting this issue.

Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/cmd.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 761cf8573a80..f48c3f62966d 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -35,6 +35,7 @@
 #include "wl12xx_80211.h"
 #include "cmd.h"
 #include "event.h"
+#include "ps.h"
 #include "tx.h"
 #include "hw_ops.h"
 
@@ -191,6 +192,10 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 
 	timeout_time = jiffies + msecs_to_jiffies(WL1271_EVENT_TIMEOUT);
 
+	ret = wl1271_ps_elp_wakeup(wl);
+	if (ret < 0)
+		return ret;
+
 	do {
 		if (time_after(jiffies, timeout_time)) {
 			wl1271_debug(DEBUG_CMD, "timeout waiting for event %d",
@@ -222,6 +227,7 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 	} while (!event);
 
 out:
+	wl1271_ps_elp_sleep(wl);
 	kfree(events_vector);
 	return ret;
 }
-- 
cgit v1.2.3


From 02edf81362fe8b6a8230ac6610e0c94a0e9d1d62 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 19 Jun 2018 02:43:36 -0700
Subject: wlcore: Make sure PM calls are paired

The call to wl1271_ps_elp_wakeup() in wl12xx_queue_recovery_work() is
unpaired. Let's remove it and add paired calls to wl1271_recovery_work()
instead in preparation for changing things to use runtime PM.

Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/main.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 3a51ab116e79..14bb84cccdf0 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -796,8 +796,6 @@ void wl12xx_queue_recovery_work(struct wl1271 *wl)
 
 		wl->state = WLCORE_STATE_RESTARTING;
 		set_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags);
-		wl1271_ps_elp_wakeup(wl);
-		wlcore_disable_interrupts_nosync(wl);
 		ieee80211_queue_work(wl->hw, &wl->recovery_work);
 	}
 }
@@ -919,12 +917,18 @@ static void wl1271_recovery_work(struct work_struct *work)
 		container_of(work, struct wl1271, recovery_work);
 	struct wl12xx_vif *wlvif;
 	struct ieee80211_vif *vif;
+	int error;
 
 	mutex_lock(&wl->mutex);
 
 	if (wl->state == WLCORE_STATE_OFF || wl->plt)
 		goto out_unlock;
 
+	error = wl1271_ps_elp_wakeup(wl);
+	if (error < 0)
+		wl1271_warning("Enable for recovery failed");
+	wlcore_disable_interrupts_nosync(wl);
+
 	if (!test_bit(WL1271_FLAG_INTENDED_FW_RECOVERY, &wl->flags)) {
 		if (wl->conf.fwlog.output == WL12XX_FWLOG_OUTPUT_HOST)
 			wl12xx_read_fwlog_panic(wl);
@@ -967,6 +971,8 @@ static void wl1271_recovery_work(struct work_struct *work)
 	 */
 	wlcore_wake_queues(wl, WLCORE_QUEUE_STOP_REASON_FW_RESTART);
 
+	wl1271_ps_elp_sleep(wl);
+
 out_unlock:
 	wl->watchdog_recovery = false;
 	clear_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags);
-- 
cgit v1.2.3


From fa2648a34e73fb7a17fd0a82e0335a9451d8f5c8 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 19 Jun 2018 02:43:37 -0700
Subject: wlcore: Add support for runtime PM

We can update wlcore to use PM runtime by adding functions for
wlcore_runtime_suspend() and wlcore_runtime_resume() and replacing
calls to wl1271_ps_elp_wakeup() and wl1271_ps_elp_sleep() with calls
to pm_runtime_get_sync() and pm_runtime_put().

Note that the new wlcore_runtime_suspend() and wlcore_runtime_resume()
functions are based on simplified versions of wl1271_ps_elp_sleep() and
wl1271_ps_elp_wakeup().

We don't want to use the old functions as we can now take advantage of
the runtime PM usage count. And we don't need the old elp_work at all.
And we can also remove WL1271_FLAG_ELP_REQUESTED that is no longer needed.

Pretty much the only place where we are not just converting the existing
functions is wl1271_op_suspend() where we add pm_runtime_put_noidle()
to keep the calls paired.

As the next step is to implement runtime PM autosuspend, let's not add
wrapper functions for the generic runtime PM calls. We would be getting
rid of any wrapper functions anyways.

After autoidle we should be able to start using Linux generic wakeirqs
for the padconf interrupt.

Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wl18xx/debugfs.c    |  26 +-
 drivers/net/wireless/ti/wlcore/acx.c        |   1 -
 drivers/net/wireless/ti/wlcore/cmd.c        |  11 +-
 drivers/net/wireless/ti/wlcore/debugfs.c    |  79 ++++--
 drivers/net/wireless/ti/wlcore/main.c       | 410 ++++++++++++++++++++--------
 drivers/net/wireless/ti/wlcore/ps.c         | 146 ----------
 drivers/net/wireless/ti/wlcore/ps.h         |   3 -
 drivers/net/wireless/ti/wlcore/scan.c       |  10 +-
 drivers/net/wireless/ti/wlcore/sysfs.c      |  12 +-
 drivers/net/wireless/ti/wlcore/testmode.c   |  18 +-
 drivers/net/wireless/ti/wlcore/tx.c         |   9 +-
 drivers/net/wireless/ti/wlcore/vendor_cmd.c |  27 +-
 drivers/net/wireless/ti/wlcore/wlcore.h     |   1 -
 drivers/net/wireless/ti/wlcore/wlcore_i.h   |   1 -
 14 files changed, 416 insertions(+), 338 deletions(-)

diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c
index 86ccf84ea0c6..f84a4963fa81 100644
--- a/drivers/net/wireless/ti/wl18xx/debugfs.c
+++ b/drivers/net/wireless/ti/wl18xx/debugfs.c
@@ -20,6 +20,8 @@
  *
  */
 
+#include <linux/pm_runtime.h>
+
 #include "../wlcore/debugfs.h"
 #include "../wlcore/wlcore.h"
 #include "../wlcore/debug.h"
@@ -276,15 +278,17 @@ static ssize_t radar_detection_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl18xx_cmd_radar_detection_debug(wl, channel);
 	if (ret < 0)
 		count = ret;
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -315,15 +319,17 @@ static ssize_t dynamic_fw_traces_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl18xx_acx_dynamic_fw_traces(wl);
 	if (ret < 0)
 		count = ret;
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -374,9 +380,11 @@ static ssize_t radar_debug_mode_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif_ap(wl, wlvif) {
 		wlcore_cmd_generic_cfg(wl, wlvif,
@@ -384,7 +392,7 @@ static ssize_t radar_debug_mode_write(struct file *file,
 				       wl->radar_debug_mode, 0);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
diff --git a/drivers/net/wireless/ti/wlcore/acx.c b/drivers/net/wireless/ti/wlcore/acx.c
index 3ca9167d6146..7c83915a7c5e 100644
--- a/drivers/net/wireless/ti/wlcore/acx.c
+++ b/drivers/net/wireless/ti/wlcore/acx.c
@@ -31,7 +31,6 @@
 #include "wlcore.h"
 #include "debug.h"
 #include "wl12xx_80211.h"
-#include "ps.h"
 #include "hw_ops.h"
 
 int wl1271_acx_wake_up_conditions(struct wl1271 *wl, struct wl12xx_vif *wlvif,
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index f48c3f62966d..9359e02856dc 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -23,6 +23,7 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/spi/spi.h>
 #include <linux/etherdevice.h>
 #include <linux/ieee80211.h>
@@ -35,7 +36,6 @@
 #include "wl12xx_80211.h"
 #include "cmd.h"
 #include "event.h"
-#include "ps.h"
 #include "tx.h"
 #include "hw_ops.h"
 
@@ -192,9 +192,12 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 
 	timeout_time = jiffies + msecs_to_jiffies(WL1271_EVENT_TIMEOUT);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
+
 		return ret;
+	}
 
 	do {
 		if (time_after(jiffies, timeout_time)) {
@@ -227,7 +230,7 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 	} while (!event);
 
 out:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 	kfree(events_vector);
 	return ret;
 }
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c
index a2cb408be8aa..b33dbec9b531 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.c
+++ b/drivers/net/wireless/ti/wlcore/debugfs.c
@@ -26,6 +26,7 @@
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/pm_runtime.h>
 
 #include "wlcore.h"
 #include "debug.h"
@@ -65,9 +66,11 @@ void wl1271_debugfs_update_stats(struct wl1271 *wl)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (!wl->plt &&
 	    time_after(jiffies, wl->stats.fw_stats_update +
@@ -76,7 +79,7 @@ void wl1271_debugfs_update_stats(struct wl1271 *wl)
 		wl->stats.fw_stats_update = jiffies;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -118,14 +121,17 @@ static void chip_op_handler(struct wl1271 *wl, unsigned long value,
 		return;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
+
 		return;
+	}
 
 	chip_op = arg;
 	chip_op(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 }
 
 
@@ -292,9 +298,11 @@ static ssize_t dynamic_ps_timeout_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* In case we're already in PSM, trigger it again to set new timeout
 	 * immediately without waiting for re-association
@@ -305,7 +313,7 @@ static ssize_t dynamic_ps_timeout_write(struct file *file,
 			wl1271_ps_set_mode(wl, wlvif, STATION_AUTO_PS_MODE);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -359,9 +367,11 @@ static ssize_t forced_ps_write(struct file *file,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* In case we're already in PSM, trigger it again to switch mode
 	 * immediately without waiting for re-association
@@ -374,7 +384,7 @@ static ssize_t forced_ps_write(struct file *file,
 			wl1271_ps_set_mode(wl, wlvif, ps_mode);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -838,15 +848,17 @@ static ssize_t rx_streaming_interval_write(struct file *file,
 
 	wl->conf.rx_streaming.interval = value;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif_sta(wl, wlvif) {
 		wl1271_recalc_rx_streaming(wl, wlvif);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -893,15 +905,17 @@ static ssize_t rx_streaming_always_write(struct file *file,
 
 	wl->conf.rx_streaming.always = value;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif_sta(wl, wlvif) {
 		wl1271_recalc_rx_streaming(wl, wlvif);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -940,15 +954,17 @@ static ssize_t beacon_filtering_write(struct file *file,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		ret = wl1271_acx_beacon_filter_opt(wl, wlvif, !!value);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -1019,16 +1035,18 @@ static ssize_t sleep_auth_write(struct file *file,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_acx_sleep_auth(wl, value);
 	if (ret < 0)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -1083,7 +1101,7 @@ static ssize_t dev_mem_read(struct file *file,
 	 * Don't fail if elp_wakeup returns an error, so the device's memory
 	 * could be read even if the FW crashed
 	 */
-	wl1271_ps_elp_wakeup(wl);
+	pm_runtime_get_sync(wl->dev);
 
 	/* store current partition and switch partition */
 	memcpy(&old_part, &wl->curr_part, sizeof(old_part));
@@ -1102,7 +1120,7 @@ read_err:
 		goto part_err;
 
 part_err:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 skip_read:
 	mutex_unlock(&wl->mutex);
@@ -1164,7 +1182,7 @@ static ssize_t dev_mem_write(struct file *file, const char __user *user_buf,
 	 * Don't fail if elp_wakeup returns an error, so the device's memory
 	 * could be read even if the FW crashed
 	 */
-	wl1271_ps_elp_wakeup(wl);
+	pm_runtime_get_sync(wl->dev);
 
 	/* store current partition and switch partition */
 	memcpy(&old_part, &wl->curr_part, sizeof(old_part));
@@ -1183,7 +1201,7 @@ write_err:
 		goto part_err;
 
 part_err:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 skip_write:
 	mutex_unlock(&wl->mutex);
@@ -1247,8 +1265,9 @@ static ssize_t fw_logger_write(struct file *file,
 	}
 
 	mutex_lock(&wl->mutex);
-	ret = wl1271_ps_elp_wakeup(wl);
+	ret = pm_runtime_get_sync(wl->dev);
 	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		count = ret;
 		goto out;
 	}
@@ -1257,7 +1276,7 @@ static ssize_t fw_logger_write(struct file *file,
 
 	ret = wl12xx_cmd_config_fwlog(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 14bb84cccdf0..8eccd0d1f329 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -26,6 +26,7 @@
 #include <linux/vmalloc.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
+#include <linux/pm_runtime.h>
 
 #include "wlcore.h"
 #include "debug.h"
@@ -43,6 +44,7 @@
 
 #define WL1271_BOOT_RETRIES 3
 #define WL1271_SUSPEND_SLEEP 100
+#define WL1271_WAKEUP_TIMEOUT 500
 
 static char *fwlog_param;
 static int fwlog_mem_blocks = -1;
@@ -153,9 +155,11 @@ static void wl1271_rx_streaming_enable_work(struct work_struct *work)
 	if (!wl->conf.rx_streaming.interval)
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_set_rx_streaming(wl, wlvif, true);
 	if (ret < 0)
@@ -166,7 +170,7 @@ static void wl1271_rx_streaming_enable_work(struct work_struct *work)
 		  jiffies + msecs_to_jiffies(wl->conf.rx_streaming.duration));
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -183,16 +187,18 @@ static void wl1271_rx_streaming_disable_work(struct work_struct *work)
 	if (!test_bit(WLVIF_FLAG_RX_STREAMING_STARTED, &wlvif->flags))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_set_rx_streaming(wl, wlvif, false);
 	if (ret)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -229,9 +235,11 @@ static void wlcore_rc_update_work(struct work_struct *work)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (ieee80211_vif_is_mesh(vif)) {
 		ret = wl1271_acx_set_ht_capabilities(wl, &wlvif->rc_ht_cap,
@@ -243,7 +251,7 @@ static void wlcore_rc_update_work(struct work_struct *work)
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -539,15 +547,16 @@ static int wlcore_irq_locked(struct wl1271 *wl)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	while (!done && loopcount--) {
 		/*
 		 * In order to avoid a race with the hardirq, clear the flag
-		 * before acknowledging the chip. Since the mutex is held,
-		 * wl1271_ps_elp_wakeup cannot be called concurrently.
+		 * before acknowledging the chip.
 		 */
 		clear_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags);
 		smp_mb__after_atomic();
@@ -641,7 +650,7 @@ static int wlcore_irq_locked(struct wl1271 *wl)
 			wl1271_debug(DEBUG_IRQ, "WL1271_ACX_INTR_HW_AVAILABLE");
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	return ret;
@@ -817,6 +826,7 @@ size_t wl12xx_copy_fwlog(struct wl1271 *wl, u8 *memblock, size_t maxlen)
 static void wl12xx_read_fwlog_panic(struct wl1271 *wl)
 {
 	u32 end_of_log = 0;
+	int error;
 
 	if (wl->quirks & WLCORE_QUIRK_FWLOG_NOT_IMPLEMENTED)
 		return;
@@ -828,8 +838,11 @@ static void wl12xx_read_fwlog_panic(struct wl1271 *wl)
 	 * Do not send a stop fwlog command if the fw is hanged or if
 	 * dbgpins are used (due to some fw bug).
 	 */
-	if (wl1271_ps_elp_wakeup(wl))
+	error = pm_runtime_get_sync(wl->dev);
+	if (error < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		return;
+	}
 	if (!wl->watchdog_recovery &&
 	    wl->conf.fwlog.output != WL12XX_FWLOG_OUTPUT_DBG_PINS)
 		wl12xx_cmd_stop_fwlog(wl);
@@ -924,9 +937,11 @@ static void wl1271_recovery_work(struct work_struct *work)
 	if (wl->state == WLCORE_STATE_OFF || wl->plt)
 		goto out_unlock;
 
-	error = wl1271_ps_elp_wakeup(wl);
-	if (error < 0)
+	error = pm_runtime_get_sync(wl->dev);
+	if (error < 0) {
 		wl1271_warning("Enable for recovery failed");
+		pm_runtime_put_noidle(wl->dev);
+	}
 	wlcore_disable_interrupts_nosync(wl);
 
 	if (!test_bit(WL1271_FLAG_INTENDED_FW_RECOVERY, &wl->flags)) {
@@ -971,7 +986,7 @@ static void wl1271_recovery_work(struct work_struct *work)
 	 */
 	wlcore_wake_queues(wl, WLCORE_QUEUE_STOP_REASON_FW_RESTART);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out_unlock:
 	wl->watchdog_recovery = false;
@@ -1190,7 +1205,6 @@ int wl1271_plt_stop(struct wl1271 *wl)
 	wl1271_flush_deferred_work(wl);
 	cancel_work_sync(&wl->netstack_work);
 	cancel_work_sync(&wl->recovery_work);
-	cancel_delayed_work_sync(&wl->elp_work);
 	cancel_delayed_work_sync(&wl->tx_watchdog_work);
 
 	mutex_lock(&wl->mutex);
@@ -1740,8 +1754,9 @@ static int __maybe_unused wl1271_op_suspend(struct ieee80211_hw *hw,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
+	ret = pm_runtime_get_sync(wl->dev);
 	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		mutex_unlock(&wl->mutex);
 		return ret;
 	}
@@ -1771,6 +1786,7 @@ static int __maybe_unused wl1271_op_suspend(struct ieee80211_hw *hw,
 		goto out_sleep;
 
 out_sleep:
+	pm_runtime_put_noidle(wl->dev);
 	mutex_unlock(&wl->mutex);
 
 	if (ret < 0) {
@@ -1795,7 +1811,6 @@ out_sleep:
 
 	wlcore_enable_interrupts(wl);
 	flush_work(&wl->tx_work);
-	flush_delayed_work(&wl->elp_work);
 
 	/*
 	 * Cancel the watchdog even if above tx_flush failed. We will detect
@@ -1863,9 +1878,11 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		goto out_sleep;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		if (wlcore_is_p2p_mgmt(wlvif))
@@ -1884,7 +1901,7 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	wl->wow_enabled = false;
@@ -1951,7 +1968,6 @@ static void wlcore_op_stop_locked(struct wl1271 *wl)
 	cancel_delayed_work_sync(&wl->scan_complete_work);
 	cancel_work_sync(&wl->netstack_work);
 	cancel_work_sync(&wl->tx_work);
-	cancel_delayed_work_sync(&wl->elp_work);
 	cancel_delayed_work_sync(&wl->tx_watchdog_work);
 
 	/* let's notify MAC80211 about the remaining pending TX frames */
@@ -2066,13 +2082,15 @@ static void wlcore_channel_switch_work(struct work_struct *work)
 	vif = wl12xx_wlvif_to_vif(wlvif);
 	ieee80211_chswitch_done(vif, false);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_cmd_stop_channel_switch(wl, wlvif);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -2134,14 +2152,16 @@ static void wlcore_pending_auth_complete_work(struct work_struct *work)
 	if (!time_after(time_spare, wlvif->pending_auth_reply_time))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* cancel the ROC if active */
 	wlcore_update_inconn_sta(wl, wlvif, NULL, false);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -2543,9 +2563,11 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	wl12xx_get_vif_count(hw, vif, &vif_count);
 
 	mutex_lock(&wl->mutex);
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out_unlock;
+	}
 
 	/*
 	 * in some very corner case HW recovery scenarios its possible to
@@ -2628,7 +2650,7 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	else
 		wl->sta_count++;
 out:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out_unlock:
 	mutex_unlock(&wl->mutex);
 
@@ -2683,9 +2705,11 @@ static void __wl1271_op_remove_interface(struct wl1271 *wl,
 
 	if (!test_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags)) {
 		/* disable active roles */
-		ret = wl1271_ps_elp_wakeup(wl);
-		if (ret < 0)
+		ret = pm_runtime_get_sync(wl->dev);
+		if (ret < 0) {
+			pm_runtime_put_noidle(wl->dev);
 			goto deinit;
+		}
 
 		if (wlvif->bss_type == BSS_TYPE_STA_BSS ||
 		    wlvif->bss_type == BSS_TYPE_IBSS) {
@@ -2703,7 +2727,7 @@ static void __wl1271_op_remove_interface(struct wl1271 *wl,
 				goto deinit;
 		}
 
-		wl1271_ps_elp_sleep(wl);
+		pm_runtime_put(wl->dev);
 	}
 deinit:
 	wl12xx_tx_reset_wlvif(wl, wlvif);
@@ -3127,9 +3151,11 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* configure each interface */
 	wl12xx_for_each_wlvif(wl, wlvif) {
@@ -3139,7 +3165,7 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed)
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3208,9 +3234,11 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		if (wlcore_is_p2p_mgmt(wlvif))
@@ -3253,7 +3281,7 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw,
 	 */
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3460,13 +3488,15 @@ static int wlcore_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		goto out_wake_queues;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out_wake_queues;
+	}
 
 	ret = wlcore_hw_set_key(wl, cmd, vif, sta, key_conf);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out_wake_queues:
 	if (might_change_spare)
@@ -3606,9 +3636,11 @@ static void wl1271_op_set_default_key_idx(struct ieee80211_hw *hw,
 		goto out_unlock;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out_unlock;
+	}
 
 	wlvif->default_key = key_idx;
 
@@ -3622,7 +3654,7 @@ static void wl1271_op_set_default_key_idx(struct ieee80211_hw *hw,
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out_unlock:
 	mutex_unlock(&wl->mutex);
@@ -3640,7 +3672,7 @@ void wlcore_regdomain_config(struct wl1271 *wl)
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
+	ret = pm_runtime_get_sync(wl->dev);
 	if (ret < 0)
 		goto out;
 
@@ -3650,7 +3682,7 @@ void wlcore_regdomain_config(struct wl1271 *wl)
 		goto out;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -3684,9 +3716,11 @@ static int wl1271_op_hw_scan(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* fail if there is any role in ROC */
 	if (find_first_bit(wl->roc_map, WL12XX_MAX_ROLES) < WL12XX_MAX_ROLES) {
@@ -3697,7 +3731,7 @@ static int wl1271_op_hw_scan(struct ieee80211_hw *hw,
 
 	ret = wlcore_scan(hw->priv, vif, ssid, len, req);
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3724,9 +3758,11 @@ static void wl1271_op_cancel_hw_scan(struct ieee80211_hw *hw,
 	if (wl->scan.state == WL1271_SCAN_STATE_IDLE)
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (wl->scan.state != WL1271_SCAN_STATE_DONE) {
 		ret = wl->ops->scan_stop(wl, wlvif);
@@ -3747,7 +3783,7 @@ static void wl1271_op_cancel_hw_scan(struct ieee80211_hw *hw,
 	ieee80211_scan_completed(wl->hw, &info);
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3772,9 +3808,11 @@ static int wl1271_op_sched_scan_start(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl->ops->sched_scan_start(wl, wlvif, req, ies);
 	if (ret < 0)
@@ -3783,7 +3821,7 @@ static int wl1271_op_sched_scan_start(struct ieee80211_hw *hw,
 	wl->sched_vif = wlvif;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return ret;
@@ -3803,13 +3841,15 @@ static int wl1271_op_sched_scan_stop(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl->ops->sched_scan_stop(wl, wlvif);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3828,15 +3868,17 @@ static int wl1271_op_set_frag_threshold(struct ieee80211_hw *hw, u32 value)
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_acx_frag_threshold(wl, value);
 	if (ret < 0)
 		wl1271_warning("wl1271_op_set_frag_threshold failed: %d", ret);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3857,16 +3899,18 @@ static int wl1271_op_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		ret = wl1271_acx_rts_threshold(wl, wlvif, value);
 		if (ret < 0)
 			wl1271_warning("set rts threshold failed: %d", ret);
 	}
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4613,9 +4657,11 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw,
 	if (unlikely(!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if ((changed & BSS_CHANGED_TXPOWER) &&
 	    bss_conf->txpower != wlvif->power_level) {
@@ -4632,7 +4678,7 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw,
 	else
 		wl1271_bss_info_changed_sta(wl, vif, bss_conf, changed);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4671,9 +4717,11 @@ static void wlcore_op_change_chanctx(struct ieee80211_hw *hw,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl12xx_for_each_wlvif(wl, wlvif) {
 		struct ieee80211_vif *vif = wl12xx_wlvif_to_vif(wlvif);
@@ -4696,7 +4744,7 @@ static void wlcore_op_change_chanctx(struct ieee80211_hw *hw,
 		}
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -4725,9 +4773,11 @@ static int wlcore_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 	if (unlikely(!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wlvif->band = ctx->def.chan->band;
 	wlvif->channel = channel;
@@ -4743,7 +4793,7 @@ static int wlcore_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		wlvif->radar_enabled = true;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -4774,9 +4824,11 @@ static void wlcore_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	if (unlikely(!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags)))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (wlvif->radar_enabled) {
 		wl1271_debug(DEBUG_MAC80211, "Stop radar detection");
@@ -4784,7 +4836,7 @@ static void wlcore_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 		wlvif->radar_enabled = false;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -4841,9 +4893,11 @@ wlcore_op_switch_vif_chanctx(struct ieee80211_hw *hw,
 
 	mutex_lock(&wl->mutex);
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	for (i = 0; i < n_vifs; i++) {
 		struct wl12xx_vif *wlvif = wl12xx_vif_to_data(vifs[i].vif);
@@ -4853,7 +4907,7 @@ wlcore_op_switch_vif_chanctx(struct ieee80211_hw *hw,
 			goto out_sleep;
 	}
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -4884,9 +4938,11 @@ static int wl1271_op_conf_tx(struct ieee80211_hw *hw,
 	if (!test_bit(WLVIF_FLAG_INITIALIZED, &wlvif->flags))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/*
 	 * the txop is confed in units of 32us by the mac80211,
@@ -4905,7 +4961,7 @@ static int wl1271_op_conf_tx(struct ieee80211_hw *hw,
 				 0, 0);
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4929,16 +4985,18 @@ static u64 wl1271_op_get_tsf(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl12xx_acx_tsf_info(wl, wlvif, &mactime);
 	if (ret < 0)
 		goto out_sleep;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5244,13 +5302,15 @@ static int wl12xx_op_sta_state(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl12xx_update_sta_state(wl, wlvif, sta, old_state, new_state);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	if (new_state < old_state)
@@ -5299,9 +5359,11 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 
 	ba_bitmap = &wl->links[hlid].ba_bitmap;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 ampdu: Rx tid %d action %d",
 		     tid, action);
@@ -5374,7 +5436,7 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 		ret = -EINVAL;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5408,16 +5470,18 @@ static int wl12xx_set_bitrate_mask(struct ieee80211_hw *hw,
 	if (wlvif->bss_type == BSS_TYPE_STA_BSS &&
 	    !test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags)) {
 
-		ret = wl1271_ps_elp_wakeup(wl);
-		if (ret < 0)
+		ret = pm_runtime_get_sync(wl->dev);
+		if (ret < 0) {
+			pm_runtime_put_noidle(wl->dev);
 			goto out;
+		}
 
 		wl1271_set_band_rate(wl, wlvif);
 		wlvif->basic_rate =
 			wl1271_tx_min_rate_get(wl, wlvif->basic_rate_set);
 		ret = wl1271_acx_sta_rate_policies(wl, wlvif);
 
-		wl1271_ps_elp_sleep(wl);
+		pm_runtime_put(wl->dev);
 	}
 out:
 	mutex_unlock(&wl->mutex);
@@ -5447,9 +5511,11 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	/* TODO: change mac80211 to pass vif as param */
 
@@ -5471,7 +5537,7 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5538,9 +5604,11 @@ static void wlcore_op_channel_switch_beacon(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl->ops->channel_switch(wl, wlvif, &ch_switch);
 	if (ret)
@@ -5549,7 +5617,7 @@ static void wlcore_op_channel_switch_beacon(struct ieee80211_hw *hw,
 	set_bit(WLVIF_FLAG_CS_PROGRESS, &wlvif->flags);
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -5590,9 +5658,11 @@ static int wlcore_op_remain_on_channel(struct ieee80211_hw *hw,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl12xx_start_dev(wl, wlvif, chan->band, channel);
 	if (ret < 0)
@@ -5602,7 +5672,7 @@ static int wlcore_op_remain_on_channel(struct ieee80211_hw *hw,
 	ieee80211_queue_delayed_work(hw, &wl->roc_complete_work,
 				     msecs_to_jiffies(duration));
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return ret;
@@ -5644,13 +5714,15 @@ static int wlcore_roc_completed(struct wl1271 *wl)
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = __wlcore_roc_completed(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -5725,9 +5797,11 @@ static void wlcore_op_sta_statistics(struct ieee80211_hw *hw,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out_sleep;
+	}
 
 	ret = wlcore_acx_average_rssi(wl, wlvif, &rssi_dbm);
 	if (ret < 0)
@@ -5737,7 +5811,7 @@ static void wlcore_op_sta_statistics(struct ieee80211_hw *hw,
 	sinfo->signal = rssi_dbm;
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -6306,7 +6380,6 @@ struct ieee80211_hw *wlcore_alloc_hw(size_t priv_size, u32 aggr_buf_size,
 	skb_queue_head_init(&wl->deferred_rx_queue);
 	skb_queue_head_init(&wl->deferred_tx_queue);
 
-	INIT_DELAYED_WORK(&wl->elp_work, wl1271_elp_work);
 	INIT_WORK(&wl->netstack_work, wl1271_netstack_work);
 	INIT_WORK(&wl->tx_work, wl1271_tx_work);
 	INIT_WORK(&wl->recovery_work, wl1271_recovery_work);
@@ -6581,6 +6654,99 @@ out:
 	complete_all(&wl->nvs_loading_complete);
 }
 
+static int __maybe_unused wlcore_runtime_suspend(struct device *dev)
+{
+	struct wl1271 *wl = dev_get_drvdata(dev);
+	struct wl12xx_vif *wlvif;
+	int error;
+
+	/* We do not enter elp sleep in PLT mode */
+	if (wl->plt)
+		return 0;
+
+	/* Nothing to do if no ELP mode requested */
+	if (wl->sleep_auth != WL1271_PSM_ELP)
+		return 0;
+
+	wl12xx_for_each_wlvif(wl, wlvif) {
+		if (!test_bit(WLVIF_FLAG_IN_PS, &wlvif->flags) &&
+		    test_bit(WLVIF_FLAG_IN_USE, &wlvif->flags))
+			return -EBUSY;
+	}
+
+	wl1271_debug(DEBUG_PSM, "chip to elp");
+	error = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_SLEEP);
+	if (error < 0) {
+		wl12xx_queue_recovery_work(wl);
+
+		return error;
+	}
+
+	set_bit(WL1271_FLAG_IN_ELP, &wl->flags);
+
+	return 0;
+}
+
+static int __maybe_unused wlcore_runtime_resume(struct device *dev)
+{
+	struct wl1271 *wl = dev_get_drvdata(dev);
+	DECLARE_COMPLETION_ONSTACK(compl);
+	unsigned long flags;
+	int ret;
+	unsigned long start_time = jiffies;
+	bool pending = false;
+
+	/* Nothing to do if no ELP mode requested */
+	if (!test_bit(WL1271_FLAG_IN_ELP, &wl->flags))
+		return 0;
+
+	wl1271_debug(DEBUG_PSM, "waking up chip from elp");
+
+	spin_lock_irqsave(&wl->wl_lock, flags);
+	if (test_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags))
+		pending = true;
+	else
+		wl->elp_compl = &compl;
+	spin_unlock_irqrestore(&wl->wl_lock, flags);
+
+	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_WAKE_UP);
+	if (ret < 0) {
+		wl12xx_queue_recovery_work(wl);
+		goto err;
+	}
+
+	if (!pending) {
+		ret = wait_for_completion_timeout(&compl,
+			msecs_to_jiffies(WL1271_WAKEUP_TIMEOUT));
+		if (ret == 0) {
+			wl1271_error("ELP wakeup timeout!");
+			wl12xx_queue_recovery_work(wl);
+
+			/* Return no error for runtime PM for recovery */
+			return 0;
+		}
+	}
+
+	clear_bit(WL1271_FLAG_IN_ELP, &wl->flags);
+
+	wl1271_debug(DEBUG_PSM, "wakeup time: %u ms",
+		     jiffies_to_msecs(jiffies - start_time));
+
+	return 0;
+
+err:
+	spin_lock_irqsave(&wl->wl_lock, flags);
+	wl->elp_compl = NULL;
+	spin_unlock_irqrestore(&wl->wl_lock, flags);
+	return ret;
+}
+
+static const struct dev_pm_ops wlcore_pm_ops = {
+	SET_RUNTIME_PM_OPS(wlcore_runtime_suspend,
+			   wlcore_runtime_resume,
+			   NULL)
+};
+
 int wlcore_probe(struct wl1271 *wl, struct platform_device *pdev)
 {
 	struct wlcore_platdev_data *pdev_data = dev_get_platdata(&pdev->dev);
@@ -6608,6 +6774,9 @@ int wlcore_probe(struct wl1271 *wl, struct platform_device *pdev)
 		wlcore_nvs_cb(NULL, wl);
 	}
 
+	wl->dev->driver->pm = &wlcore_pm_ops;
+	pm_runtime_enable(wl->dev);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(wlcore_probe);
@@ -6616,6 +6785,13 @@ int wlcore_remove(struct platform_device *pdev)
 {
 	struct wlcore_platdev_data *pdev_data = dev_get_platdata(&pdev->dev);
 	struct wl1271 *wl = platform_get_drvdata(pdev);
+	int error;
+
+	error = pm_runtime_get_sync(wl->dev);
+	if (error < 0)
+		dev_warn(wl->dev, "PM runtime failed: %i\n", error);
+
+	wl->dev->driver->pm = NULL;
 
 	if (pdev_data->family && pdev_data->family->nvs_name)
 		wait_for_completion(&wl->nvs_loading_complete);
@@ -6627,6 +6803,10 @@ int wlcore_remove(struct platform_device *pdev)
 		disable_irq_wake(wl->irq);
 	}
 	wl1271_unregister_hw(wl);
+
+	pm_runtime_put_sync(wl->dev);
+	pm_runtime_disable(wl->dev);
+
 	free_irq(wl->irq, wl);
 	wlcore_free_hw(wl);
 
diff --git a/drivers/net/wireless/ti/wlcore/ps.c b/drivers/net/wireless/ti/wlcore/ps.c
index b36133b739cb..9de843d1984b 100644
--- a/drivers/net/wireless/ti/wlcore/ps.c
+++ b/drivers/net/wireless/ti/wlcore/ps.c
@@ -26,152 +26,6 @@
 #include "tx.h"
 #include "debug.h"
 
-#define WL1271_WAKEUP_TIMEOUT 500
-
-#define ELP_ENTRY_DELAY  30
-#define ELP_ENTRY_DELAY_FORCE_PS  5
-
-void wl1271_elp_work(struct work_struct *work)
-{
-	struct delayed_work *dwork;
-	struct wl1271 *wl;
-	struct wl12xx_vif *wlvif;
-	int ret;
-
-	dwork = to_delayed_work(work);
-	wl = container_of(dwork, struct wl1271, elp_work);
-
-	wl1271_debug(DEBUG_PSM, "elp work");
-
-	mutex_lock(&wl->mutex);
-
-	if (unlikely(wl->state != WLCORE_STATE_ON))
-		goto out;
-
-	/* our work might have been already cancelled */
-	if (unlikely(!test_bit(WL1271_FLAG_ELP_REQUESTED, &wl->flags)))
-		goto out;
-
-	if (test_bit(WL1271_FLAG_IN_ELP, &wl->flags))
-		goto out;
-
-	wl12xx_for_each_wlvif(wl, wlvif) {
-		if (!test_bit(WLVIF_FLAG_IN_PS, &wlvif->flags) &&
-		    test_bit(WLVIF_FLAG_IN_USE, &wlvif->flags))
-			goto out;
-	}
-
-	wl1271_debug(DEBUG_PSM, "chip to elp");
-	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_SLEEP);
-	if (ret < 0) {
-		wl12xx_queue_recovery_work(wl);
-		goto out;
-	}
-
-	set_bit(WL1271_FLAG_IN_ELP, &wl->flags);
-
-out:
-	mutex_unlock(&wl->mutex);
-}
-
-/* Routines to toggle sleep mode while in ELP */
-void wl1271_ps_elp_sleep(struct wl1271 *wl)
-{
-	struct wl12xx_vif *wlvif;
-	u32 timeout;
-
-	/* We do not enter elp sleep in PLT mode */
-	if (wl->plt)
-		return;
-
-	if (wl->sleep_auth != WL1271_PSM_ELP)
-		return;
-
-	/* we shouldn't get consecutive sleep requests */
-	if (WARN_ON(test_and_set_bit(WL1271_FLAG_ELP_REQUESTED, &wl->flags)))
-		return;
-
-	wl12xx_for_each_wlvif(wl, wlvif) {
-		if (!test_bit(WLVIF_FLAG_IN_PS, &wlvif->flags) &&
-		    test_bit(WLVIF_FLAG_IN_USE, &wlvif->flags))
-			return;
-	}
-
-	timeout = wl->conf.conn.forced_ps ?
-			ELP_ENTRY_DELAY_FORCE_PS : ELP_ENTRY_DELAY;
-	ieee80211_queue_delayed_work(wl->hw, &wl->elp_work,
-				     msecs_to_jiffies(timeout));
-}
-EXPORT_SYMBOL_GPL(wl1271_ps_elp_sleep);
-
-int wl1271_ps_elp_wakeup(struct wl1271 *wl)
-{
-	DECLARE_COMPLETION_ONSTACK(compl);
-	unsigned long flags;
-	int ret;
-	unsigned long start_time = jiffies;
-	bool pending = false;
-
-	/*
-	 * we might try to wake up even if we didn't go to sleep
-	 * before (e.g. on boot)
-	 */
-	if (!test_and_clear_bit(WL1271_FLAG_ELP_REQUESTED, &wl->flags))
-		return 0;
-
-	/* don't cancel_sync as it might contend for a mutex and deadlock */
-	cancel_delayed_work(&wl->elp_work);
-
-	if (!test_bit(WL1271_FLAG_IN_ELP, &wl->flags))
-		return 0;
-
-	wl1271_debug(DEBUG_PSM, "waking up chip from elp");
-
-	/*
-	 * The spinlock is required here to synchronize both the work and
-	 * the completion variable in one entity.
-	 */
-	spin_lock_irqsave(&wl->wl_lock, flags);
-	if (test_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags))
-		pending = true;
-	else
-		wl->elp_compl = &compl;
-	spin_unlock_irqrestore(&wl->wl_lock, flags);
-
-	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_WAKE_UP);
-	if (ret < 0) {
-		wl12xx_queue_recovery_work(wl);
-		goto err;
-	}
-
-	if (!pending) {
-		ret = wait_for_completion_timeout(
-			&compl, msecs_to_jiffies(WL1271_WAKEUP_TIMEOUT));
-		if (ret == 0) {
-			wl1271_error("ELP wakeup timeout!");
-			wl12xx_queue_recovery_work(wl);
-			ret = -ETIMEDOUT;
-			goto err;
-		}
-	}
-
-	clear_bit(WL1271_FLAG_IN_ELP, &wl->flags);
-
-	wl1271_debug(DEBUG_PSM, "wakeup time: %u ms",
-		     jiffies_to_msecs(jiffies - start_time));
-	goto out;
-
-err:
-	spin_lock_irqsave(&wl->wl_lock, flags);
-	wl->elp_compl = NULL;
-	spin_unlock_irqrestore(&wl->wl_lock, flags);
-	return ret;
-
-out:
-	return 0;
-}
-EXPORT_SYMBOL_GPL(wl1271_ps_elp_wakeup);
-
 int wl1271_ps_set_mode(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 		       enum wl1271_cmd_ps_mode mode)
 {
diff --git a/drivers/net/wireless/ti/wlcore/ps.h b/drivers/net/wireless/ti/wlcore/ps.h
index de4f9da8ed26..411727587f95 100644
--- a/drivers/net/wireless/ti/wlcore/ps.h
+++ b/drivers/net/wireless/ti/wlcore/ps.h
@@ -29,9 +29,6 @@
 
 int wl1271_ps_set_mode(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 		       enum wl1271_cmd_ps_mode mode);
-void wl1271_ps_elp_sleep(struct wl1271 *wl);
-int wl1271_ps_elp_wakeup(struct wl1271 *wl);
-void wl1271_elp_work(struct work_struct *work);
 void wl12xx_ps_link_start(struct wl1271 *wl, struct wl12xx_vif *wlvif,
 			  u8 hlid, bool clean_queues);
 void wl12xx_ps_link_end(struct wl1271 *wl, struct wl12xx_vif *wlvif, u8 hlid);
diff --git a/drivers/net/wireless/ti/wlcore/scan.c b/drivers/net/wireless/ti/wlcore/scan.c
index 5612f5916b4e..69d0f28fc0dd 100644
--- a/drivers/net/wireless/ti/wlcore/scan.c
+++ b/drivers/net/wireless/ti/wlcore/scan.c
@@ -22,13 +22,13 @@
  */
 
 #include <linux/ieee80211.h>
+#include <linux/pm_runtime.h>
 
 #include "wlcore.h"
 #include "debug.h"
 #include "cmd.h"
 #include "scan.h"
 #include "acx.h"
-#include "ps.h"
 #include "tx.h"
 
 void wl1271_scan_complete_work(struct work_struct *work)
@@ -67,16 +67,18 @@ void wl1271_scan_complete_work(struct work_struct *work)
 	wl->scan.req = NULL;
 	wl->scan_wlvif = NULL;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	if (test_bit(WLVIF_FLAG_STA_ASSOCIATED, &wlvif->flags)) {
 		/* restore hardware connection monitoring template */
 		wl1271_cmd_build_ap_probe_req(wl, wlvif, wlvif->probereq);
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
 	if (wl->scan.failed) {
 		wl1271_info("Scan completed due to error.");
diff --git a/drivers/net/wireless/ti/wlcore/sysfs.c b/drivers/net/wireless/ti/wlcore/sysfs.c
index d31eb775e023..fc20fba6bb18 100644
--- a/drivers/net/wireless/ti/wlcore/sysfs.c
+++ b/drivers/net/wireless/ti/wlcore/sysfs.c
@@ -19,9 +19,11 @@
  *
  */
 
+#include <linux/pm_runtime.h>
+
+#include "acx.h"
 #include "wlcore.h"
 #include "debug.h"
-#include "ps.h"
 #include "sysfs.h"
 
 static ssize_t wl1271_sysfs_show_bt_coex_state(struct device *dev,
@@ -68,12 +70,14 @@ static ssize_t wl1271_sysfs_store_bt_coex_state(struct device *dev,
 	if (unlikely(wl->state != WLCORE_STATE_ON))
 		goto out;
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	wl1271_acx_sg_enable(wl, wl->sg_enabled);
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 
  out:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/ti/wlcore/testmode.c b/drivers/net/wireless/ti/wlcore/testmode.c
index 009ec07c4cec..f87709134238 100644
--- a/drivers/net/wireless/ti/wlcore/testmode.c
+++ b/drivers/net/wireless/ti/wlcore/testmode.c
@@ -22,13 +22,13 @@
  */
 #include "testmode.h"
 
+#include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <net/genetlink.h>
 
 #include "wlcore.h"
 #include "debug.h"
 #include "acx.h"
-#include "ps.h"
 #include "io.h"
 
 #define WL1271_TM_MAX_DATA_LENGTH 1024
@@ -97,9 +97,11 @@ static int wl1271_tm_cmd_test(struct wl1271 *wl, struct nlattr *tb[])
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wl1271_cmd_test(wl, buf, buf_len, answer);
 	if (ret < 0) {
@@ -141,7 +143,7 @@ static int wl1271_tm_cmd_test(struct wl1271 *wl, struct nlattr *tb[])
 	}
 
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -169,9 +171,11 @@ static int wl1271_tm_cmd_interrogate(struct wl1271 *wl, struct nlattr *tb[])
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	cmd = kzalloc(sizeof(*cmd), GFP_KERNEL);
 	if (!cmd) {
@@ -205,7 +209,7 @@ static int wl1271_tm_cmd_interrogate(struct wl1271 *wl, struct nlattr *tb[])
 out_free:
 	kfree(cmd);
 out_sleep:
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c
index 00e9b4624dcf..12920d1c1c65 100644
--- a/drivers/net/wireless/ti/wlcore/tx.c
+++ b/drivers/net/wireless/ti/wlcore/tx.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/etherdevice.h>
+#include <linux/pm_runtime.h>
 #include <linux/spinlock.h>
 
 #include "wlcore.h"
@@ -868,9 +869,11 @@ void wl1271_tx_work(struct work_struct *work)
 	int ret;
 
 	mutex_lock(&wl->mutex);
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_tx_work_locked(wl);
 	if (ret < 0) {
@@ -878,7 +881,7 @@ void wl1271_tx_work(struct work_struct *work)
 		goto out;
 	}
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
index 5c0bcb1fe1a1..c5008c633e59 100644
--- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c
+++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
@@ -8,12 +8,13 @@
  * version 2 as published by the Free Software Foundation.
  */
 
+#include <linux/pm_runtime.h>
+
 #include <net/mac80211.h>
 #include <net/netlink.h>
 
 #include "wlcore.h"
 #include "debug.h"
-#include "ps.h"
 #include "hw_ops.h"
 #include "vendor_cmd.h"
 
@@ -55,14 +56,16 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_smart_config_start(wl,
 			nla_get_u32(tb[WLCORE_VENDOR_ATTR_GROUP_ID]));
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -87,13 +90,15 @@ wlcore_vendor_cmd_smart_config_stop(struct wiphy *wiphy,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_smart_config_stop(wl);
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -131,16 +136,18 @@ wlcore_vendor_cmd_smart_config_set_group_key(struct wiphy *wiphy,
 		goto out;
 	}
 
-	ret = wl1271_ps_elp_wakeup(wl);
-	if (ret < 0)
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
 		goto out;
+	}
 
 	ret = wlcore_smart_config_set_group_key(wl,
 			nla_get_u32(tb[WLCORE_VENDOR_ATTR_GROUP_ID]),
 			nla_len(tb[WLCORE_VENDOR_ATTR_GROUP_KEY]),
 			nla_data(tb[WLCORE_VENDOR_ATTR_GROUP_KEY]));
 
-	wl1271_ps_elp_sleep(wl);
+	pm_runtime_put(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
diff --git a/drivers/net/wireless/ti/wlcore/wlcore.h b/drivers/net/wireless/ti/wlcore/wlcore.h
index 95fbedc8ea34..d4b1f66ef457 100644
--- a/drivers/net/wireless/ti/wlcore/wlcore.h
+++ b/drivers/net/wireless/ti/wlcore/wlcore.h
@@ -348,7 +348,6 @@ struct wl1271 {
 	enum nl80211_band band;
 
 	struct completion *elp_compl;
-	struct delayed_work elp_work;
 
 	/* in dBm */
 	int power_level;
diff --git a/drivers/net/wireless/ti/wlcore/wlcore_i.h b/drivers/net/wireless/ti/wlcore/wlcore_i.h
index e840985385fc..32ec121ccac2 100644
--- a/drivers/net/wireless/ti/wlcore/wlcore_i.h
+++ b/drivers/net/wireless/ti/wlcore/wlcore_i.h
@@ -233,7 +233,6 @@ enum wl12xx_flags {
 	WL1271_FLAG_TX_QUEUE_STOPPED,
 	WL1271_FLAG_TX_PENDING,
 	WL1271_FLAG_IN_ELP,
-	WL1271_FLAG_ELP_REQUESTED,
 	WL1271_FLAG_IRQ_RUNNING,
 	WL1271_FLAG_FW_TX_BUSY,
 	WL1271_FLAG_DUMMY_PACKET_PENDING,
-- 
cgit v1.2.3


From 3ebbabea4219816ff148209473e074adaaa5f610 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 19 Jun 2018 02:43:38 -0700
Subject: wlcore: Fix misplaced PM call for scan_complete_work()

With runtime PM enabled, we now need to have wlcore enabled longer
until after we're done calling wlcore_cmd_regdomain_config_locked():

scan_complete_work()
 wlcore_cmd_regdomain_config_locked()
   wlcore_cmd_send_failsafe()
     wl12xx_sdio_raw_read()

Note that this is not needed before runtime PM support as the
custom PM code had it's own timer. We have not yet enabled runtime
PM autosuspend for wlcore and this is why this issue now shows up.

Let's fix the issues first before we enable runtime PM autosuspend.

Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/scan.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/scan.c b/drivers/net/wireless/ti/wlcore/scan.c
index 69d0f28fc0dd..6f927eabbe39 100644
--- a/drivers/net/wireless/ti/wlcore/scan.c
+++ b/drivers/net/wireless/ti/wlcore/scan.c
@@ -78,8 +78,6 @@ void wl1271_scan_complete_work(struct work_struct *work)
 		wl1271_cmd_build_ap_probe_req(wl, wlvif, wlvif->probereq);
 	}
 
-	pm_runtime_put(wl->dev);
-
 	if (wl->scan.failed) {
 		wl1271_info("Scan completed due to error.");
 		wl12xx_queue_recovery_work(wl);
@@ -87,6 +85,8 @@ void wl1271_scan_complete_work(struct work_struct *work)
 
 	wlcore_cmd_regdomain_config_locked(wl);
 
+	pm_runtime_put(wl->dev);
+
 	ieee80211_scan_completed(wl->hw, &info);
 
 out:
-- 
cgit v1.2.3


From db68052bdf581eb5e7f74da4a5bb5933113dbaaf Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 19 Jun 2018 02:43:39 -0700
Subject: wlcore: Fix timout errors after recovery

After enabling runtime PM, if we force hardware reset multiple times with:

# echo 1 > /sys/kernel/debug/ieee80211/phy0/wlcore/start_recovery

We will after few tries get the following error:

wlcore: ERROR timeout waiting for the hardware to complete initialization

And then wlcore is unable to reconnect until after the wlcore related modules
are reloaded.

Let's fix this by moving pm_runtime_put() earlier before we restart the hardware.
And let's use the sync version to make sure we're done before we restart.

Note that we still will get -EBUSY warning from wl12xx_sdio_set_power() but let's
fix that separately once we know exactly why we get the warning.

Reported-by: Eyal Reizer <eyalr@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/main.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 8eccd0d1f329..398d6d983046 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -977,6 +977,7 @@ static void wl1271_recovery_work(struct work_struct *work)
 	}
 
 	wlcore_op_stop_locked(wl);
+	pm_runtime_put_sync(wl->dev);
 
 	ieee80211_restart_hw(wl->hw);
 
@@ -986,8 +987,6 @@ static void wl1271_recovery_work(struct work_struct *work)
 	 */
 	wlcore_wake_queues(wl, WLCORE_QUEUE_STOP_REASON_FW_RESTART);
 
-	pm_runtime_put(wl->dev);
-
 out_unlock:
 	wl->watchdog_recovery = false;
 	clear_bit(WL1271_FLAG_RECOVERY_IN_PROGRESS, &wl->flags);
-- 
cgit v1.2.3


From 45aa7f071b06c8481afed4c7b93e07c9584741e8 Mon Sep 17 00:00:00 2001
From: Eyal Reizer <eyalreizer@gmail.com>
Date: Tue, 19 Jun 2018 02:43:40 -0700
Subject: wlcore: Use generic runtime pm calls for wowlan elp configuration

With runtime PM enabled, we can now use calls to pm_runtime_force_suspend
and pm_runtime_force_resume for enabling elp during suspend when wowlan
is enabled and waking the chip from elp on resume.

Remove the custom API that was used to ensure that the command
that is used to allow ELP during suspend is completed before the system
suspend.

Signed-off-by: Eyal Reizer <eyalr@ti.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/main.c | 51 +++++++++--------------------------
 1 file changed, 13 insertions(+), 38 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 398d6d983046..7ae2c7508c4c 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -998,24 +998,6 @@ static int wlcore_fw_wakeup(struct wl1271 *wl)
 	return wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_WAKE_UP);
 }
 
-static int wlcore_fw_sleep(struct wl1271 *wl)
-{
-	int ret;
-
-	mutex_lock(&wl->mutex);
-	ret = wlcore_raw_write32(wl, HW_ACCESS_ELP_CTRL_REG, ELPCTRL_SLEEP);
-	if (ret < 0) {
-		wl12xx_queue_recovery_work(wl);
-		goto out;
-	}
-	set_bit(WL1271_FLAG_IN_ELP, &wl->flags);
-out:
-	mutex_unlock(&wl->mutex);
-	mdelay(WL1271_SUSPEND_SLEEP);
-
-	return 0;
-}
-
 static int wl1271_setup(struct wl1271 *wl)
 {
 	wl->raw_fw_status = kzalloc(wl->fw_status_len, GFP_KERNEL);
@@ -1738,6 +1720,7 @@ static int __maybe_unused wl1271_op_suspend(struct ieee80211_hw *hw,
 {
 	struct wl1271 *wl = hw->priv;
 	struct wl12xx_vif *wlvif;
+	unsigned long flags;
 	int ret;
 
 	wl1271_debug(DEBUG_MAC80211, "mac80211 suspend wow=%d", !!wow);
@@ -1796,19 +1779,6 @@ out_sleep:
 	/* flush any remaining work */
 	wl1271_debug(DEBUG_MAC80211, "flushing remaining works");
 
-	/*
-	 * disable and re-enable interrupts in order to flush
-	 * the threaded_irq
-	 */
-	wlcore_disable_interrupts(wl);
-
-	/*
-	 * set suspended flag to avoid triggering a new threaded_irq
-	 * work. no need for spinlock as interrupts are disabled.
-	 */
-	set_bit(WL1271_FLAG_SUSPENDED, &wl->flags);
-
-	wlcore_enable_interrupts(wl);
 	flush_work(&wl->tx_work);
 
 	/*
@@ -1818,15 +1788,14 @@ out_sleep:
 	cancel_delayed_work(&wl->tx_watchdog_work);
 
 	/*
-	 * Use an immediate call for allowing the firmware to go into power
-	 * save during suspend.
-	 * Using a workque for this last write was only hapenning on resume
-	 * leaving the firmware with power save disabled during suspend,
-	 * while consuming full power during wowlan suspend.
+	 * set suspended flag to avoid triggering a new threaded_irq
+	 * work.
 	 */
-	wlcore_fw_sleep(wl);
+	spin_lock_irqsave(&wl->wl_lock, flags);
+	set_bit(WL1271_FLAG_SUSPENDED, &wl->flags);
+	spin_unlock_irqrestore(&wl->wl_lock, flags);
 
-	return 0;
+	return pm_runtime_force_suspend(wl->dev);
 }
 
 static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
@@ -1841,6 +1810,12 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		     wl->wow_enabled);
 	WARN_ON(!wl->wow_enabled);
 
+	ret = pm_runtime_force_resume(wl->dev);
+	if (ret < 0) {
+		wl1271_error("ELP wakeup failure!");
+		goto out_sleep;
+	}
+
 	/*
 	 * re-enable irq_work enqueuing, and call irq_work directly if
 	 * there is a pending work.
-- 
cgit v1.2.3


From c40aad28a3cf762c4f842fdb8f6e7fa653a2241e Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 19 Jun 2018 02:43:41 -0700
Subject: wlcore: Make sure firmware is initialized in
 wl1271_op_add_interface()

We have wl12xx_boot() call wl12xx_enable_interrupts() and if we have
wl1271_op_add_interface() call pm_runtime_get_sync() before the interrupts
are enabled. And then we get the following error during boot:

wlcore: ERROR ELP wakeup timeout!

Let's fix this by first checking if we need to boot the firmware. And
only after that call pm_runtime_get_sync() when interrupts are enabled.
And only after that do the check for wl12xx_need_fw_change().

Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/main.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 7ae2c7508c4c..2ac8a12beb24 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -2537,11 +2537,6 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	wl12xx_get_vif_count(hw, vif, &vif_count);
 
 	mutex_lock(&wl->mutex);
-	ret = pm_runtime_get_sync(wl->dev);
-	if (ret < 0) {
-		pm_runtime_put_noidle(wl->dev);
-		goto out_unlock;
-	}
 
 	/*
 	 * in some very corner case HW recovery scenarios its possible to
@@ -2570,14 +2565,6 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	if (ret < 0)
 		goto out;
 
-	if (wl12xx_need_fw_change(wl, vif_count, true)) {
-		wl12xx_force_active_psm(wl);
-		set_bit(WL1271_FLAG_INTENDED_FW_RECOVERY, &wl->flags);
-		mutex_unlock(&wl->mutex);
-		wl1271_recovery_work(&wl->recovery_work);
-		return 0;
-	}
-
 	/*
 	 * TODO: after the nvs issue will be solved, move this block
 	 * to start(), and make sure here the driver is ON.
@@ -2594,6 +2581,24 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 			goto out;
 	}
 
+	/*
+	 * Call runtime PM only after possible wl12xx_init_fw() above
+	 * is done. Otherwise we do not have interrupts enabled.
+	 */
+	ret = pm_runtime_get_sync(wl->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(wl->dev);
+		goto out_unlock;
+	}
+
+	if (wl12xx_need_fw_change(wl, vif_count, true)) {
+		wl12xx_force_active_psm(wl);
+		set_bit(WL1271_FLAG_INTENDED_FW_RECOVERY, &wl->flags);
+		mutex_unlock(&wl->mutex);
+		wl1271_recovery_work(&wl->recovery_work);
+		return 0;
+	}
+
 	if (!wlcore_is_p2p_mgmt(wlvif)) {
 		ret = wl12xx_cmd_role_enable(wl, vif->addr,
 					     role_type, &wlvif->role_id);
-- 
cgit v1.2.3


From 9b71578de08748defb3bcae3ce8ed1a75cb6a8d7 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Tue, 19 Jun 2018 02:43:42 -0700
Subject: wlcore: Enable runtime PM autosuspend support

With runtime PM tested working for wlcore with no autosuspend, we can
now enable autosuspend to cut down on enable/disable for interrupts.
Basically we just replace pm_runtime_put() with the autosuspend variants.

Let's use autosuspend delay of 50ms that MMC drivers typically use.

Signed-off-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wl18xx/debugfs.c    |   9 ++-
 drivers/net/wireless/ti/wlcore/cmd.c        |   3 +-
 drivers/net/wireless/ti/wlcore/debugfs.c    |  33 ++++++---
 drivers/net/wireless/ti/wlcore/main.c       | 111 +++++++++++++++++++---------
 drivers/net/wireless/ti/wlcore/scan.c       |   3 +-
 drivers/net/wireless/ti/wlcore/sysfs.c      |   3 +-
 drivers/net/wireless/ti/wlcore/testmode.c   |   6 +-
 drivers/net/wireless/ti/wlcore/tx.c         |   3 +-
 drivers/net/wireless/ti/wlcore/vendor_cmd.c |   9 ++-
 9 files changed, 121 insertions(+), 59 deletions(-)

diff --git a/drivers/net/wireless/ti/wl18xx/debugfs.c b/drivers/net/wireless/ti/wl18xx/debugfs.c
index f84a4963fa81..597e934c4630 100644
--- a/drivers/net/wireless/ti/wl18xx/debugfs.c
+++ b/drivers/net/wireless/ti/wl18xx/debugfs.c
@@ -288,7 +288,8 @@ static ssize_t radar_detection_write(struct file *file,
 	if (ret < 0)
 		count = ret;
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -329,7 +330,8 @@ static ssize_t dynamic_fw_traces_write(struct file *file,
 	if (ret < 0)
 		count = ret;
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -392,7 +394,8 @@ static ssize_t radar_debug_mode_write(struct file *file,
 				       wl->radar_debug_mode, 0);
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 9359e02856dc..836c61663803 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -230,7 +230,8 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 	} while (!event);
 
 out:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 	kfree(events_vector);
 	return ret;
 }
diff --git a/drivers/net/wireless/ti/wlcore/debugfs.c b/drivers/net/wireless/ti/wlcore/debugfs.c
index b33dbec9b531..aeb74e74698e 100644
--- a/drivers/net/wireless/ti/wlcore/debugfs.c
+++ b/drivers/net/wireless/ti/wlcore/debugfs.c
@@ -79,7 +79,8 @@ void wl1271_debugfs_update_stats(struct wl1271 *wl)
 		wl->stats.fw_stats_update = jiffies;
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -131,7 +132,8 @@ static void chip_op_handler(struct wl1271 *wl, unsigned long value,
 	chip_op = arg;
 	chip_op(wl);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 }
 
 
@@ -313,7 +315,8 @@ static ssize_t dynamic_ps_timeout_write(struct file *file,
 			wl1271_ps_set_mode(wl, wlvif, STATION_AUTO_PS_MODE);
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -384,7 +387,8 @@ static ssize_t forced_ps_write(struct file *file,
 			wl1271_ps_set_mode(wl, wlvif, ps_mode);
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -858,7 +862,8 @@ static ssize_t rx_streaming_interval_write(struct file *file,
 		wl1271_recalc_rx_streaming(wl, wlvif);
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -915,7 +920,8 @@ static ssize_t rx_streaming_always_write(struct file *file,
 		wl1271_recalc_rx_streaming(wl, wlvif);
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -964,7 +970,8 @@ static ssize_t beacon_filtering_write(struct file *file,
 		ret = wl1271_acx_beacon_filter_opt(wl, wlvif, !!value);
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -1046,7 +1053,8 @@ static ssize_t sleep_auth_write(struct file *file,
 		goto out_sleep;
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return count;
@@ -1120,7 +1128,8 @@ read_err:
 		goto part_err;
 
 part_err:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 skip_read:
 	mutex_unlock(&wl->mutex);
@@ -1201,7 +1210,8 @@ write_err:
 		goto part_err;
 
 part_err:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 skip_write:
 	mutex_unlock(&wl->mutex);
@@ -1276,7 +1286,8 @@ static ssize_t fw_logger_write(struct file *file,
 
 	ret = wl12xx_cmd_config_fwlog(wl);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 2ac8a12beb24..09c40e7f7701 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -170,7 +170,8 @@ static void wl1271_rx_streaming_enable_work(struct work_struct *work)
 		  jiffies + msecs_to_jiffies(wl->conf.rx_streaming.duration));
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -198,7 +199,8 @@ static void wl1271_rx_streaming_disable_work(struct work_struct *work)
 		goto out_sleep;
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -251,7 +253,8 @@ static void wlcore_rc_update_work(struct work_struct *work)
 	}
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -650,7 +653,8 @@ static int wlcore_irq_locked(struct wl1271 *wl)
 			wl1271_debug(DEBUG_IRQ, "WL1271_ACX_INTR_HW_AVAILABLE");
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	return ret;
@@ -977,7 +981,8 @@ static void wl1271_recovery_work(struct work_struct *work)
 	}
 
 	wlcore_op_stop_locked(wl);
-	pm_runtime_put_sync(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 	ieee80211_restart_hw(wl->hw);
 
@@ -1875,7 +1880,8 @@ static int __maybe_unused wl1271_op_resume(struct ieee80211_hw *hw)
 		goto out_sleep;
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	wl->wow_enabled = false;
@@ -2064,7 +2070,8 @@ static void wlcore_channel_switch_work(struct work_struct *work)
 
 	wl12xx_cmd_stop_channel_switch(wl, wlvif);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -2135,7 +2142,8 @@ static void wlcore_pending_auth_complete_work(struct work_struct *work)
 	/* cancel the ROC if active */
 	wlcore_update_inconn_sta(wl, wlvif, NULL, false);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -2629,7 +2637,8 @@ static int wl1271_op_add_interface(struct ieee80211_hw *hw,
 	else
 		wl->sta_count++;
 out:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out_unlock:
 	mutex_unlock(&wl->mutex);
 
@@ -2706,7 +2715,8 @@ static void __wl1271_op_remove_interface(struct wl1271 *wl,
 				goto deinit;
 		}
 
-		pm_runtime_put(wl->dev);
+		pm_runtime_mark_last_busy(wl->dev);
+		pm_runtime_put_autosuspend(wl->dev);
 	}
 deinit:
 	wl12xx_tx_reset_wlvif(wl, wlvif);
@@ -3144,7 +3154,8 @@ static int wl1271_op_config(struct ieee80211_hw *hw, u32 changed)
 	}
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3260,7 +3271,8 @@ static void wl1271_op_configure_filter(struct ieee80211_hw *hw,
 	 */
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3475,7 +3487,8 @@ static int wlcore_op_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 	ret = wlcore_hw_set_key(wl, cmd, vif, sta, key_conf);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out_wake_queues:
 	if (might_change_spare)
@@ -3633,7 +3646,8 @@ static void wl1271_op_set_default_key_idx(struct ieee80211_hw *hw,
 	}
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out_unlock:
 	mutex_unlock(&wl->mutex);
@@ -3661,7 +3675,8 @@ void wlcore_regdomain_config(struct wl1271 *wl)
 		goto out;
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -3710,7 +3725,8 @@ static int wl1271_op_hw_scan(struct ieee80211_hw *hw,
 
 	ret = wlcore_scan(hw->priv, vif, ssid, len, req);
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3762,7 +3778,8 @@ static void wl1271_op_cancel_hw_scan(struct ieee80211_hw *hw,
 	ieee80211_scan_completed(wl->hw, &info);
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3800,7 +3817,8 @@ static int wl1271_op_sched_scan_start(struct ieee80211_hw *hw,
 	wl->sched_vif = wlvif;
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return ret;
@@ -3828,7 +3846,8 @@ static int wl1271_op_sched_scan_stop(struct ieee80211_hw *hw,
 
 	wl->ops->sched_scan_stop(wl, wlvif);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -3857,7 +3876,8 @@ static int wl1271_op_set_frag_threshold(struct ieee80211_hw *hw, u32 value)
 	if (ret < 0)
 		wl1271_warning("wl1271_op_set_frag_threshold failed: %d", ret);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -3889,7 +3909,8 @@ static int wl1271_op_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 		if (ret < 0)
 			wl1271_warning("set rts threshold failed: %d", ret);
 	}
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4657,7 +4678,8 @@ static void wl1271_op_bss_info_changed(struct ieee80211_hw *hw,
 	else
 		wl1271_bss_info_changed_sta(wl, vif, bss_conf, changed);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4723,7 +4745,8 @@ static void wlcore_op_change_chanctx(struct ieee80211_hw *hw,
 		}
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -4772,7 +4795,8 @@ static int wlcore_op_assign_vif_chanctx(struct ieee80211_hw *hw,
 		wlvif->radar_enabled = true;
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -4815,7 +4839,8 @@ static void wlcore_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 		wlvif->radar_enabled = false;
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -4886,7 +4911,8 @@ wlcore_op_switch_vif_chanctx(struct ieee80211_hw *hw,
 			goto out_sleep;
 	}
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -4940,7 +4966,8 @@ static int wl1271_op_conf_tx(struct ieee80211_hw *hw,
 				 0, 0);
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -4975,7 +5002,8 @@ static u64 wl1271_op_get_tsf(struct ieee80211_hw *hw,
 		goto out_sleep;
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5289,7 +5317,8 @@ static int wl12xx_op_sta_state(struct ieee80211_hw *hw,
 
 	ret = wl12xx_update_sta_state(wl, wlvif, sta, old_state, new_state);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	if (new_state < old_state)
@@ -5415,7 +5444,8 @@ static int wl1271_op_ampdu_action(struct ieee80211_hw *hw,
 		ret = -EINVAL;
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5460,7 +5490,8 @@ static int wl12xx_set_bitrate_mask(struct ieee80211_hw *hw,
 			wl1271_tx_min_rate_get(wl, wlvif->basic_rate_set);
 		ret = wl1271_acx_sta_rate_policies(wl, wlvif);
 
-		pm_runtime_put(wl->dev);
+		pm_runtime_mark_last_busy(wl->dev);
+		pm_runtime_put_autosuspend(wl->dev);
 	}
 out:
 	mutex_unlock(&wl->mutex);
@@ -5516,7 +5547,8 @@ static void wl12xx_op_channel_switch(struct ieee80211_hw *hw,
 	}
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -5596,7 +5628,8 @@ static void wlcore_op_channel_switch_beacon(struct ieee80211_hw *hw,
 	set_bit(WLVIF_FLAG_CS_PROGRESS, &wlvif->flags);
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
@@ -5651,7 +5684,8 @@ static int wlcore_op_remain_on_channel(struct ieee80211_hw *hw,
 	ieee80211_queue_delayed_work(hw, &wl->roc_complete_work,
 				     msecs_to_jiffies(duration));
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 	return ret;
@@ -5701,7 +5735,8 @@ static int wlcore_roc_completed(struct wl1271 *wl)
 
 	ret = __wlcore_roc_completed(wl);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -5790,7 +5825,8 @@ static void wlcore_op_sta_statistics(struct ieee80211_hw *hw,
 	sinfo->signal = rssi_dbm;
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 out:
 	mutex_unlock(&wl->mutex);
@@ -6754,6 +6790,8 @@ int wlcore_probe(struct wl1271 *wl, struct platform_device *pdev)
 	}
 
 	wl->dev->driver->pm = &wlcore_pm_ops;
+	pm_runtime_set_autosuspend_delay(wl->dev, 50);
+	pm_runtime_use_autosuspend(wl->dev);
 	pm_runtime_enable(wl->dev);
 
 	return ret;
@@ -6784,6 +6822,7 @@ int wlcore_remove(struct platform_device *pdev)
 	wl1271_unregister_hw(wl);
 
 	pm_runtime_put_sync(wl->dev);
+	pm_runtime_dont_use_autosuspend(wl->dev);
 	pm_runtime_disable(wl->dev);
 
 	free_irq(wl->irq, wl);
diff --git a/drivers/net/wireless/ti/wlcore/scan.c b/drivers/net/wireless/ti/wlcore/scan.c
index 6f927eabbe39..764e723e4ef9 100644
--- a/drivers/net/wireless/ti/wlcore/scan.c
+++ b/drivers/net/wireless/ti/wlcore/scan.c
@@ -85,7 +85,8 @@ void wl1271_scan_complete_work(struct work_struct *work)
 
 	wlcore_cmd_regdomain_config_locked(wl);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
 	ieee80211_scan_completed(wl->hw, &info);
 
diff --git a/drivers/net/wireless/ti/wlcore/sysfs.c b/drivers/net/wireless/ti/wlcore/sysfs.c
index fc20fba6bb18..7425ba9471d0 100644
--- a/drivers/net/wireless/ti/wlcore/sysfs.c
+++ b/drivers/net/wireless/ti/wlcore/sysfs.c
@@ -77,7 +77,8 @@ static ssize_t wl1271_sysfs_store_bt_coex_state(struct device *dev,
 	}
 
 	wl1271_acx_sg_enable(wl, wl->sg_enabled);
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 
  out:
 	mutex_unlock(&wl->mutex);
diff --git a/drivers/net/wireless/ti/wlcore/testmode.c b/drivers/net/wireless/ti/wlcore/testmode.c
index f87709134238..dcb2c8b0feb6 100644
--- a/drivers/net/wireless/ti/wlcore/testmode.c
+++ b/drivers/net/wireless/ti/wlcore/testmode.c
@@ -143,7 +143,8 @@ static int wl1271_tm_cmd_test(struct wl1271 *wl, struct nlattr *tb[])
 	}
 
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -209,7 +210,8 @@ static int wl1271_tm_cmd_interrogate(struct wl1271 *wl, struct nlattr *tb[])
 out_free:
 	kfree(cmd);
 out_sleep:
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
diff --git a/drivers/net/wireless/ti/wlcore/tx.c b/drivers/net/wireless/ti/wlcore/tx.c
index 12920d1c1c65..b6e19c2d66b0 100644
--- a/drivers/net/wireless/ti/wlcore/tx.c
+++ b/drivers/net/wireless/ti/wlcore/tx.c
@@ -881,7 +881,8 @@ void wl1271_tx_work(struct work_struct *work)
 		goto out;
 	}
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 }
diff --git a/drivers/net/wireless/ti/wlcore/vendor_cmd.c b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
index c5008c633e59..dbe78d8491ef 100644
--- a/drivers/net/wireless/ti/wlcore/vendor_cmd.c
+++ b/drivers/net/wireless/ti/wlcore/vendor_cmd.c
@@ -65,7 +65,8 @@ wlcore_vendor_cmd_smart_config_start(struct wiphy *wiphy,
 	ret = wlcore_smart_config_start(wl,
 			nla_get_u32(tb[WLCORE_VENDOR_ATTR_GROUP_ID]));
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -98,7 +99,8 @@ wlcore_vendor_cmd_smart_config_stop(struct wiphy *wiphy,
 
 	ret = wlcore_smart_config_stop(wl);
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
@@ -147,7 +149,8 @@ wlcore_vendor_cmd_smart_config_set_group_key(struct wiphy *wiphy,
 			nla_len(tb[WLCORE_VENDOR_ATTR_GROUP_KEY]),
 			nla_data(tb[WLCORE_VENDOR_ATTR_GROUP_KEY]));
 
-	pm_runtime_put(wl->dev);
+	pm_runtime_mark_last_busy(wl->dev);
+	pm_runtime_put_autosuspend(wl->dev);
 out:
 	mutex_unlock(&wl->mutex);
 
-- 
cgit v1.2.3


From ed9f34bb9d338734ed8ec3d7f1269a28ef0a553e Mon Sep 17 00:00:00 2001
From: Igor Mitsyanko <igor.mitsyanko.os@quantenna.com>
Date: Thu, 31 May 2018 12:10:57 +0300
Subject: qtnfmac: implement net_device_ops callback to set MAC address

Implement net_device_ops::ndo_set_mac_address callback to allow for
setting interface MAC address. Implementation is done through existing
CHANGE_INTF firmware command. All validation is to be done by firmware.

Signed-off-by: Igor Mitsyanko <igor.mitsyanko.os@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/core.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c
index a6a450984f9a..c318340e1bd5 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.c
@@ -179,6 +179,30 @@ static void qtnf_netdev_tx_timeout(struct net_device *ndev)
 	}
 }
 
+static int qtnf_netdev_set_mac_address(struct net_device *ndev, void *addr)
+{
+	struct qtnf_vif *vif = qtnf_netdev_get_priv(ndev);
+	struct sockaddr *sa = addr;
+	int ret;
+	unsigned char old_addr[ETH_ALEN];
+
+	memcpy(old_addr, sa->sa_data, sizeof(old_addr));
+
+	ret = eth_mac_addr(ndev, sa);
+	if (ret)
+		return ret;
+
+	qtnf_scan_done(vif->mac, true);
+
+	ret = qtnf_cmd_send_change_intf_type(vif, vif->wdev.iftype,
+					     sa->sa_data);
+
+	if (ret)
+		memcpy(ndev->dev_addr, old_addr, ETH_ALEN);
+
+	return ret;
+}
+
 /* Network device ops handlers */
 const struct net_device_ops qtnf_netdev_ops = {
 	.ndo_open = qtnf_netdev_open,
@@ -186,6 +210,7 @@ const struct net_device_ops qtnf_netdev_ops = {
 	.ndo_start_xmit = qtnf_netdev_hard_start_xmit,
 	.ndo_tx_timeout = qtnf_netdev_tx_timeout,
 	.ndo_get_stats64 = qtnf_netdev_get_stats64,
+	.ndo_set_mac_address = qtnf_netdev_set_mac_address,
 };
 
 static int qtnf_mac_init_single_band(struct wiphy *wiphy,
-- 
cgit v1.2.3


From 6fbef9540af027276deaabc43e1270b5e7952401 Mon Sep 17 00:00:00 2001
From: Andrey Shevchenko <ashevchenko@quantenna.com>
Date: Thu, 31 May 2018 12:10:58 +0300
Subject: qtnfmac: enable source MAC address randomization support

Enable support for source MAC address randomization of probe request
frames. Pass addr/mask randomization parameters to firmware.

Signed-off-by: Andrey Shevchenko <ashevchenko@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/cfg80211.c |  3 +++
 drivers/net/wireless/quantenna/qtnfmac/commands.c | 25 +++++++++++++++++++++++
 drivers/net/wireless/quantenna/qtnfmac/qlink.h    | 20 ++++++++++++++++++
 3 files changed, 48 insertions(+)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index 220e2b710208..23366be9e394 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -1014,6 +1014,9 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac)
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_STA_INACT_TIMEOUT)
 		wiphy->features |= NL80211_FEATURE_INACTIVITY_TIMER;
 
+	if (hw_info->hw_capab & QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR)
+		wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
+
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_REG_UPDATE) {
 		wiphy->regulatory_flags |= REGULATORY_STRICT_REG |
 			REGULATORY_CUSTOM_REG;
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index c5d94a95e21a..713fd3f047e4 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -2234,6 +2234,22 @@ static void qtnf_cmd_channel_tlv_add(struct sk_buff *cmd_skb,
 	qchan->chan.flags = cpu_to_le32(flags);
 }
 
+static void qtnf_cmd_randmac_tlv_add(struct sk_buff *cmd_skb,
+				     const u8 *mac_addr,
+				     const u8 *mac_addr_mask)
+{
+	struct qlink_random_mac_addr *randmac;
+	struct qlink_tlv_hdr *hdr =
+		skb_put(cmd_skb, sizeof(*hdr) + sizeof(*randmac));
+
+	hdr->type = cpu_to_le16(QTN_TLV_ID_RANDOM_MAC_ADDR);
+	hdr->len = cpu_to_le16(sizeof(*randmac));
+	randmac = (struct qlink_random_mac_addr *)hdr->val;
+
+	memcpy(randmac->mac_addr, mac_addr, ETH_ALEN);
+	memcpy(randmac->mac_addr_mask, mac_addr_mask, ETH_ALEN);
+}
+
 int qtnf_cmd_send_scan(struct qtnf_wmac *mac)
 {
 	struct sk_buff *cmd_skb;
@@ -2291,6 +2307,15 @@ int qtnf_cmd_send_scan(struct qtnf_wmac *mac)
 		}
 	}
 
+	if (scan_req->flags & NL80211_SCAN_FLAG_RANDOM_ADDR) {
+		pr_debug("MAC%u: scan with random addr=%pM, mask=%pM\n",
+			 mac->macid,
+			 scan_req->mac_addr, scan_req->mac_addr_mask);
+
+		qtnf_cmd_randmac_tlv_add(cmd_skb, scan_req->mac_addr,
+					 scan_req->mac_addr_mask);
+	}
+
 	ret = qtnf_cmd_send(mac->bus, cmd_skb, &res_code);
 
 	if (unlikely(ret))
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
index f85deda703fb..4a32967d0479 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
@@ -69,11 +69,14 @@ struct qlink_msg_header {
  *	associated STAs due to inactivity. Inactivity timeout period is taken
  *	from QLINK_CMD_START_AP parameters.
  * @QLINK_HW_CAPAB_DFS_OFFLOAD: device implements DFS offload functionality
+ * @QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR: device supports MAC Address
+ *	Randomization in probe requests.
  */
 enum qlink_hw_capab {
 	QLINK_HW_CAPAB_REG_UPDATE		= BIT(0),
 	QLINK_HW_CAPAB_STA_INACT_TIMEOUT	= BIT(1),
 	QLINK_HW_CAPAB_DFS_OFFLOAD		= BIT(2),
+	QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR	= BIT(3),
 };
 
 enum qlink_iface_type {
@@ -1089,6 +1092,7 @@ enum qlink_tlv_id {
 	QTN_TLV_ID_HW_ID		= 0x0405,
 	QTN_TLV_ID_CALIBRATION_VER	= 0x0406,
 	QTN_TLV_ID_UBOOT_VER		= 0x0407,
+	QTN_TLV_ID_RANDOM_MAC_ADDR	= 0x0408,
 };
 
 struct qlink_tlv_hdr {
@@ -1360,4 +1364,20 @@ struct qlink_sta_stats {
 	u8 rsvd[1];
 };
 
+/**
+ * struct qlink_random_mac_addr - data for QTN_TLV_ID_RANDOM_MAC_ADDR TLV
+ *
+ * Specifies MAC address mask/value for generation random MAC address
+ * during scan.
+ *
+ * @mac_addr: MAC address used with randomisation
+ * @mac_addr_mask: MAC address mask used with randomisation, bits that
+ *	are 0 in the mask should be randomised, bits that are 1 should
+ *	be taken from the @mac_addr
+ */
+struct qlink_random_mac_addr {
+	u8 mac_addr[ETH_ALEN];
+	u8 mac_addr_mask[ETH_ALEN];
+} __packed;
+
 #endif /* _QTN_QLINK_H_ */
-- 
cgit v1.2.3


From eb5d2f3afc0f924e55b508576d7d6366e02b6af2 Mon Sep 17 00:00:00 2001
From: Varsha Rao <rvarsha016@gmail.com>
Date: Fri, 1 Jun 2018 07:44:12 +0530
Subject: brcmsmac: Remove unnecessary parentheses

This patch fixes the clang warning of extraneous parentheses, with the
following coccinelle script.

@@
identifier i;
expression e;
statement s;
@@
if (
-(i == e)
+i == e
 )
s

Suggested-by: Lukas Bulwahn <lukas.bulwahn@gmail.com>
Signed-off-by: Varsha Rao <rvarsha016@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
index 3a13d176b221..35e3b101e5cf 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_cmn.c
@@ -159,7 +159,7 @@ u16 read_radio_reg(struct brcms_phy *pi, u16 addr)
 {
 	u16 data;
 
-	if ((addr == RADIO_IDCODE))
+	if (addr == RADIO_IDCODE)
 		return 0xffff;
 
 	switch (pi->pubpi.phy_type) {
-- 
cgit v1.2.3


From c9a61469fc97672a08b2f798830a55ea6e03dc4a Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 17 Jun 2018 12:33:50 +0200
Subject: brcmsmac: fix wrap around in conversion from constant to s16

The last value in the log_table wraps around to a negative value
since s16 has a value range of -32768 to 32767. This is not what
the table intends to represent. Use the closest positive value
32767.

This fixes a warning seen with clang:
drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c:216:2: warning:
      implicit conversion from 'int' to 's16' (aka 'short') changes
value from 32768
      to -32768 [-Wconstant-conversion]
        32768
        ^~~~~
1 warning generated.

Fixes: 4c0bfeaae9f9 ("brcmsmac: fix array out-of-bounds access in qm_log10")
Cc: Tobias Regnery <tobias.regnery@gmail.com>
Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c
index b9672da24a9d..b24bc57ca91b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_qmath.c
@@ -213,7 +213,7 @@ static const s16 log_table[] = {
 	30498,
 	31267,
 	32024,
-	32768
+	32767
 };
 
 #define LOG_TABLE_SIZE 32       /* log_table size */
-- 
cgit v1.2.3


From ab8d904654e2bb55b2964588700c31f974382894 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 23 Jun 2018 23:15:31 +0100
Subject: brcmsmac: make function wlc_phy_workarounds_nphy_rev1 static

The function wlc_phy_workarounds_nphy_rev1 is local to the source and
does not need to be in global scope, so make it static.

Cleans up sparse warning:
symbol 'wlc_phy_workarounds_nphy_rev1' was not declared. Should it
be static?

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
index 1a187557982e..bedec1606caa 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_n.c
@@ -16904,7 +16904,7 @@ static void wlc_phy_workarounds_nphy_rev3(struct brcms_phy *pi)
 	}
 }
 
-void wlc_phy_workarounds_nphy_rev1(struct brcms_phy *pi)
+static void wlc_phy_workarounds_nphy_rev1(struct brcms_phy *pi)
 {
 	static const u8 rfseq_rx2tx_events[] = {
 		NPHY_RFSEQ_CMD_NOP,
-- 
cgit v1.2.3


From e7d4a95da86e0b048702765bbdcdc968aaf312e7 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes@sipsolutions.net>
Date: Wed, 20 Jun 2018 08:58:28 +0200
Subject: bitfield: fix *_encode_bits()

There's a bug in *_encode_bits() in using ~field_multiplier() for
the check whether or not the constant value fits into the field,
this is wrong and clearly ~field_mask() was intended. This was
triggering for me for both constant and non-constant values.

Additionally, make this case actually into an compile error.
Declaring the extern function that will never exist with just a
warning is pointless as then later we'll just get a link error.

While at it, also fix the indentation in those lines I'm touching.

Finally, as suggested by Andy Shevchenko, add some tests and for
that introduce also u8 helpers. The tests don't compile without
the fix, showing that it's necessary.

Fixes: 00b0c9b82663 ("Add primitives for manipulating bitfields both in host- and fixed-endian.")
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 include/linux/bitfield.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index cf2588d81148..147a7bb341dd 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -104,7 +104,7 @@
 		(typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask));	\
 	})
 
-extern void __compiletime_warning("value doesn't fit into mask")
+extern void __compiletime_error("value doesn't fit into mask")
 __field_overflow(void);
 extern void __compiletime_error("bad bitfield mask")
 __bad_mask(void);
@@ -121,8 +121,8 @@ static __always_inline u64 field_mask(u64 field)
 #define ____MAKE_OP(type,base,to,from)					\
 static __always_inline __##type type##_encode_bits(base v, base field)	\
 {									\
-        if (__builtin_constant_p(v) &&	(v & ~field_multiplier(field)))	\
-			    __field_overflow();				\
+	if (__builtin_constant_p(v) && (v & ~field_mask(field)))	\
+		__field_overflow();					\
 	return to((v & field_mask(field)) * field_multiplier(field));	\
 }									\
 static __always_inline __##type type##_replace_bits(__##type old,	\
-- 
cgit v1.2.3


From 37a3862e1238262e9866d5d66e5f5f9069cee3a1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes@sipsolutions.net>
Date: Wed, 20 Jun 2018 08:58:29 +0200
Subject: bitfield: add u8 helpers

There's no reason why we shouldn't pack/unpack bits into/from
u8 values/registers/etc., so add u8 helpers.

Use the ____MAKE_OP() macro directly to avoid having nonsense
le8_encode_bits() and similar functions.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 include/linux/bitfield.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 147a7bb341dd..65a6981eef7b 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -143,6 +143,7 @@ static __always_inline base type##_get_bits(__##type v, base field)	\
 	____MAKE_OP(le##size,u##size,cpu_to_le##size,le##size##_to_cpu)	\
 	____MAKE_OP(be##size,u##size,cpu_to_be##size,be##size##_to_cpu)	\
 	____MAKE_OP(u##size,u##size,,)
+____MAKE_OP(u8,u8,,)
 __MAKE_OP(16)
 __MAKE_OP(32)
 __MAKE_OP(64)
-- 
cgit v1.2.3


From 0e2dc70e3d0d503b0cc9c5f74db3eb6db52c9e22 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes@sipsolutions.net>
Date: Wed, 20 Jun 2018 08:58:30 +0200
Subject: bitfield: add tests

Add tests for the bitfield helpers. The constant ones will all
be folded to nothing by the compiler (if everything is correct
in the header file), and the variable ones do some tests against
open-coding the necessary shifts.

A few test cases that should fail/warn compilation are provided
under ifdef.

Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Johannes Berg <johannes@sipsolutions.net>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 lib/Kconfig.debug   |   7 +++
 lib/Makefile        |   1 +
 lib/test_bitfield.c | 168 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 176 insertions(+)
 create mode 100644 lib/test_bitfield.c

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8838d1158d19..d3d82eccdfa5 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1802,6 +1802,13 @@ config TEST_BITMAP
 
 	  If unsure, say N.
 
+config TEST_BITFIELD
+	tristate "Test bitfield functions at runtime"
+	help
+	  Enable this option to test the bitfield functions at boot.
+
+	  If unsure, say N.
+
 config TEST_UUID
 	tristate "Test functions located in the uuid module at runtime"
 
diff --git a/lib/Makefile b/lib/Makefile
index 956b320292fe..701717a23d32 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -68,6 +68,7 @@ obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_keys.o
 obj-$(CONFIG_TEST_STATIC_KEYS) += test_static_key_base.o
 obj-$(CONFIG_TEST_PRINTF) += test_printf.o
 obj-$(CONFIG_TEST_BITMAP) += test_bitmap.o
+obj-$(CONFIG_TEST_BITFIELD) += test_bitfield.o
 obj-$(CONFIG_TEST_UUID) += test_uuid.o
 obj-$(CONFIG_TEST_PARMAN) += test_parman.o
 obj-$(CONFIG_TEST_KMOD) += test_kmod.o
diff --git a/lib/test_bitfield.c b/lib/test_bitfield.c
new file mode 100644
index 000000000000..5b8f4108662d
--- /dev/null
+++ b/lib/test_bitfield.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Test cases for bitfield helpers.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/bitfield.h>
+
+#define CHECK_ENC_GET_U(tp, v, field, res) do {				\
+		{							\
+			u##tp _res;					\
+									\
+			_res = u##tp##_encode_bits(v, field);		\
+			if (_res != res) {				\
+				pr_warn("u" #tp "_encode_bits(" #v ", " #field ") is 0x%llx != " #res "\n",\
+					(u64)_res);			\
+				return -EINVAL;				\
+			}						\
+			if (u##tp##_get_bits(_res, field) != v)		\
+				return -EINVAL;				\
+		}							\
+	} while (0)
+
+#define CHECK_ENC_GET_LE(tp, v, field, res) do {			\
+		{							\
+			__le##tp _res;					\
+									\
+			_res = le##tp##_encode_bits(v, field);		\
+			if (_res != cpu_to_le##tp(res)) {		\
+				pr_warn("le" #tp "_encode_bits(" #v ", " #field ") is 0x%llx != 0x%llx\n",\
+					(u64)le##tp##_to_cpu(_res),	\
+					(u64)(res));			\
+				return -EINVAL;				\
+			}						\
+			if (le##tp##_get_bits(_res, field) != v)	\
+				return -EINVAL;				\
+		}							\
+	} while (0)
+
+#define CHECK_ENC_GET_BE(tp, v, field, res) do {			\
+		{							\
+			__be##tp _res;					\
+									\
+			_res = be##tp##_encode_bits(v, field);		\
+			if (_res != cpu_to_be##tp(res)) {		\
+				pr_warn("be" #tp "_encode_bits(" #v ", " #field ") is 0x%llx != 0x%llx\n",\
+					(u64)be##tp##_to_cpu(_res),	\
+					(u64)(res));			\
+				return -EINVAL;				\
+			}						\
+			if (be##tp##_get_bits(_res, field) != v)	\
+				return -EINVAL;				\
+		}							\
+	} while (0)
+
+#define CHECK_ENC_GET(tp, v, field, res) do {				\
+		CHECK_ENC_GET_U(tp, v, field, res);			\
+		CHECK_ENC_GET_LE(tp, v, field, res);			\
+		CHECK_ENC_GET_BE(tp, v, field, res);			\
+	} while (0)
+
+static int test_constants(void)
+{
+	/*
+	 * NOTE
+	 * This whole function compiles (or at least should, if everything
+	 * is going according to plan) to nothing after optimisation.
+	 */
+
+	CHECK_ENC_GET(16,  1, 0x000f, 0x0001);
+	CHECK_ENC_GET(16,  3, 0x00f0, 0x0030);
+	CHECK_ENC_GET(16,  5, 0x0f00, 0x0500);
+	CHECK_ENC_GET(16,  7, 0xf000, 0x7000);
+	CHECK_ENC_GET(16, 14, 0x000f, 0x000e);
+	CHECK_ENC_GET(16, 15, 0x00f0, 0x00f0);
+
+	CHECK_ENC_GET_U(8,  1, 0x0f, 0x01);
+	CHECK_ENC_GET_U(8,  3, 0xf0, 0x30);
+	CHECK_ENC_GET_U(8, 14, 0x0f, 0x0e);
+	CHECK_ENC_GET_U(8, 15, 0xf0, 0xf0);
+
+	CHECK_ENC_GET(32,  1, 0x00000f00, 0x00000100);
+	CHECK_ENC_GET(32,  3, 0x0000f000, 0x00003000);
+	CHECK_ENC_GET(32,  5, 0x000f0000, 0x00050000);
+	CHECK_ENC_GET(32,  7, 0x00f00000, 0x00700000);
+	CHECK_ENC_GET(32, 14, 0x0f000000, 0x0e000000);
+	CHECK_ENC_GET(32, 15, 0xf0000000, 0xf0000000);
+
+	CHECK_ENC_GET(64,  1, 0x00000f0000000000ull, 0x0000010000000000ull);
+	CHECK_ENC_GET(64,  3, 0x0000f00000000000ull, 0x0000300000000000ull);
+	CHECK_ENC_GET(64,  5, 0x000f000000000000ull, 0x0005000000000000ull);
+	CHECK_ENC_GET(64,  7, 0x00f0000000000000ull, 0x0070000000000000ull);
+	CHECK_ENC_GET(64, 14, 0x0f00000000000000ull, 0x0e00000000000000ull);
+	CHECK_ENC_GET(64, 15, 0xf000000000000000ull, 0xf000000000000000ull);
+
+	return 0;
+}
+
+#define CHECK(tp, mask) do {						\
+		u64 v;							\
+									\
+		for (v = 0; v < 1 << hweight32(mask); v++)		\
+			if (tp##_encode_bits(v, mask) != v << __ffs64(mask)) \
+				return -EINVAL;				\
+	} while (0)
+
+static int test_variables(void)
+{
+	CHECK(u8, 0x0f);
+	CHECK(u8, 0xf0);
+	CHECK(u8, 0x38);
+
+	CHECK(u16, 0x0038);
+	CHECK(u16, 0x0380);
+	CHECK(u16, 0x3800);
+	CHECK(u16, 0x8000);
+
+	CHECK(u32, 0x80000000);
+	CHECK(u32, 0x7f000000);
+	CHECK(u32, 0x07e00000);
+	CHECK(u32, 0x00018000);
+
+	CHECK(u64, 0x8000000000000000ull);
+	CHECK(u64, 0x7f00000000000000ull);
+	CHECK(u64, 0x0001800000000000ull);
+	CHECK(u64, 0x0000000080000000ull);
+	CHECK(u64, 0x000000007f000000ull);
+	CHECK(u64, 0x0000000018000000ull);
+	CHECK(u64, 0x0000001f8000000ull);
+
+	return 0;
+}
+
+static int __init test_bitfields(void)
+{
+	int ret = test_constants();
+
+	if (ret) {
+		pr_warn("constant tests failed!\n");
+		return ret;
+	}
+
+	ret = test_variables();
+	if (ret) {
+		pr_warn("variable tests failed!\n");
+		return ret;
+	}
+
+#ifdef TEST_BITFIELD_COMPILE
+	/* these should fail compilation */
+	CHECK_ENC_GET(16, 16, 0x0f00, 0x1000);
+	u32_encode_bits(7, 0x06000000);
+
+	/* this should at least give a warning */
+	u16_encode_bits(0, 0x60000);
+#endif
+
+	pr_info("tests passed\n");
+
+	return 0;
+}
+module_init(test_bitfields)
+
+MODULE_AUTHOR("Johannes Berg <johannes@sipsolutions.net>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 38013eef0233bdd1133570e74192eefe989cb87d Mon Sep 17 00:00:00 2001
From: Xinming Hu <huxm@marvell.com>
Date: Fri, 1 Jun 2018 15:53:40 +0800
Subject: mwifiex: uap: do not chok ethernet header in bridge path

Do not chock ethernet header for uap bridge data path,
as it is still needed to send skb to dest station.

Signed-off-by: Xinming Hu <huxm@marvell.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/uap_txrx.c | 52 ++++++++++++-------------
 1 file changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index 1e6a62c69ac5..5ce85d5727e4 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -289,32 +289,6 @@ int mwifiex_uap_recv_packet(struct mwifiex_private *priv,
 		src_node->stats.rx_packets++;
 	}
 
-	skb->dev = priv->netdev;
-	skb->protocol = eth_type_trans(skb, priv->netdev);
-	skb->ip_summed = CHECKSUM_NONE;
-
-	/* This is required only in case of 11n and USB/PCIE as we alloc
-	 * a buffer of 4K only if its 11N (to be able to receive 4K
-	 * AMSDU packets). In case of SD we allocate buffers based
-	 * on the size of packet and hence this is not needed.
-	 *
-	 * Modifying the truesize here as our allocation for each
-	 * skb is 4K but we only receive 2K packets and this cause
-	 * the kernel to start dropping packets in case where
-	 * application has allocated buffer based on 2K size i.e.
-	 * if there a 64K packet received (in IP fragments and
-	 * application allocates 64K to receive this packet but
-	 * this packet would almost double up because we allocate
-	 * each 1.5K fragment in 4K and pass it up. As soon as the
-	 * 64K limit hits kernel will start to drop rest of the
-	 * fragments. Currently we fail the Filesndl-ht.scr script
-	 * for UDP, hence this fix
-	 */
-	if ((adapter->iface_type == MWIFIEX_USB ||
-	     adapter->iface_type == MWIFIEX_PCIE) &&
-	    (skb->truesize > MWIFIEX_RX_DATA_BUF_SIZE))
-		skb->truesize += (skb->len - MWIFIEX_RX_DATA_BUF_SIZE);
-
 	if (is_multicast_ether_addr(p_ethhdr->h_dest) ||
 	    mwifiex_get_sta_entry(priv, p_ethhdr->h_dest)) {
 		if (skb_headroom(skb) < MWIFIEX_MIN_DATA_HEADER_LEN)
@@ -350,6 +324,32 @@ int mwifiex_uap_recv_packet(struct mwifiex_private *priv,
 			return 0;
 	}
 
+	skb->dev = priv->netdev;
+	skb->protocol = eth_type_trans(skb, priv->netdev);
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* This is required only in case of 11n and USB/PCIE as we alloc
+	 * a buffer of 4K only if its 11N (to be able to receive 4K
+	 * AMSDU packets). In case of SD we allocate buffers based
+	 * on the size of packet and hence this is not needed.
+	 *
+	 * Modifying the truesize here as our allocation for each
+	 * skb is 4K but we only receive 2K packets and this cause
+	 * the kernel to start dropping packets in case where
+	 * application has allocated buffer based on 2K size i.e.
+	 * if there a 64K packet received (in IP fragments and
+	 * application allocates 64K to receive this packet but
+	 * this packet would almost double up because we allocate
+	 * each 1.5K fragment in 4K and pass it up. As soon as the
+	 * 64K limit hits kernel will start to drop rest of the
+	 * fragments. Currently we fail the Filesndl-ht.scr script
+	 * for UDP, hence this fix
+	 */
+	if ((adapter->iface_type == MWIFIEX_USB ||
+	     adapter->iface_type == MWIFIEX_PCIE) &&
+	    skb->truesize > MWIFIEX_RX_DATA_BUF_SIZE)
+		skb->truesize += (skb->len - MWIFIEX_RX_DATA_BUF_SIZE);
+
 	/* Forward multicast/broadcast packet to upper layer*/
 	if (in_interrupt())
 		netif_rx(skb);
-- 
cgit v1.2.3


From 4e5f881d430aa243c8723c0de48fa16af30b292d Mon Sep 17 00:00:00 2001
From: Varsha Rao <rvarsha016@gmail.com>
Date: Sun, 3 Jun 2018 16:41:35 +0530
Subject: net: ipw2x00: Replace NULL comparison with !priv

Remove extra parentheses and replace NULL comparison with !priv, to fix
clang warning of extraneous parentheses and check patch issue. Following
coccinelle script is used to fix it.

@disable is_null,paren@
expression e;
statement s;
@@
if (
- (e==NULL)
+!e
 )
s

Signed-off-by: Varsha Rao <rvarsha016@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/ipw2x00/ipw2200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index 8a858f7e36f4..62140109d2ac 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -7112,7 +7112,7 @@ static u32 ipw_qos_get_burst_duration(struct ipw_priv *priv)
 {
 	u32 ret = 0;
 
-	if ((priv == NULL))
+	if (!priv)
 		return 0;
 
 	if (!(priv->ieee->modulation & LIBIPW_OFDM_MODULATION))
-- 
cgit v1.2.3


From 2d1e9be0016230f3707812243561fbd16f1aea4b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 4 Jun 2018 11:19:41 +0200
Subject: mt76x2: fix mrr idx/count estimation in mt76x2_mac_fill_tx_status()

Fix mcs and attempt count estimation in mt76x2_mac_fill_tx_status routine
if the number of tx retries reported by the hw is grater than
IEEE80211_TX_MAX_RATES

Fixes: 7bc04215a66b ("mt76: add driver code for MT76x2e")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
index b49aea4da2d6..8985446570bd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
@@ -439,15 +439,13 @@ mt76x2_mac_fill_tx_status(struct mt76x2_dev *dev,
 	if (last_rate < IEEE80211_TX_MAX_RATES - 1)
 		rate[last_rate + 1].idx = -1;
 
-	cur_idx = rate[last_rate].idx + st->retry;
+	cur_idx = rate[last_rate].idx + last_rate;
 	for (i = 0; i <= last_rate; i++) {
 		rate[i].flags = rate[last_rate].flags;
 		rate[i].idx = max_t(int, 0, cur_idx - i);
 		rate[i].count = 1;
 	}
-
-	if (last_rate > 0)
-		rate[last_rate - 1].count = st->retry + 1 - last_rate;
+	rate[last_rate].count = st->retry + 1 - last_rate;
 
 	info->status.ampdu_len = n_frames;
 	info->status.ampdu_ack_len = st->success ? n_frames : 0;
-- 
cgit v1.2.3


From 8668f9a57c8c551f3e6a45d2733e64686c7b7904 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 4 Jun 2018 18:32:10 +0800
Subject: atmel: use memdup_user to simplify the code

use existing memdup_user() helper function instead of open-coding

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/atmel/atmel.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index b01dc34d55af..0d8e0af3f74b 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -2646,14 +2646,9 @@ static int atmel_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 			break;
 		}
 
-		if (!(new_firmware = kmalloc(com.len, GFP_KERNEL))) {
-			rc = -ENOMEM;
-			break;
-		}
-
-		if (copy_from_user(new_firmware, com.data, com.len)) {
-			kfree(new_firmware);
-			rc = -EFAULT;
+		new_firmware = memdup_user(com.data, com.len);
+		if (IS_ERR(new_firmware)) {
+			rc = PTR_ERR(new_firmware);
 			break;
 		}
 
-- 
cgit v1.2.3


From ae636fb1554833ee5133ca47bf4b2791b6739c52 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 5 Jun 2018 14:31:39 +0300
Subject: rndis_wlan: potential buffer overflow in rndis_wlan_auth_indication()

This is a static checker fix, not something I have tested.  The issue
is that on the second iteration through the loop, we jump forward by
le32_to_cpu(auth_req->length) bytes.  The problem is that if the length
is more than "buflen" then we end up with a negative "buflen".  A
negative buflen is type promoted to a high positive value and the loop
continues but it's accessing beyond the end of the buffer.

I believe the "auth_req->length" comes from the firmware and if the
firmware is malicious or buggy, you're already toasted so the impact of
this bug is probably not very severe.

Fixes: 030645aceb3d ("rndis_wlan: handle 802.11 indications from device")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rndis_wlan.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index 9935bd09db1f..d4947e3a909e 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -2928,6 +2928,8 @@ static void rndis_wlan_auth_indication(struct usbnet *usbdev,
 
 	while (buflen >= sizeof(*auth_req)) {
 		auth_req = (void *)buf;
+		if (buflen < le32_to_cpu(auth_req->length))
+			return;
 		type = "unknown";
 		flags = le32_to_cpu(auth_req->flags);
 		pairwise_error = false;
-- 
cgit v1.2.3


From 22d0d2fafca93ba1d92a2fbd4a60463c919a12ad Mon Sep 17 00:00:00 2001
From: Omer Efrat <omer.efrat@tandemg.com>
Date: Sun, 17 Jun 2018 13:07:13 +0300
Subject: wireless-drivers: use BIT_ULL for NL80211_STA_INFO_ attribute types

The BIT macro uses unsigned long which some architectures handle as 32 bit
and therefore might cause macro's shift to overflow when used on a value
equals or larger than 32 (NL80211_STA_INFO_RX_DURATION and afterwards).

Since 'filled' member in station_info changed to u64, BIT_ULL macro
should be used with all NL80211_STA_INFO_* attribute types instead of BIT
to prevent future possible bugs when one will use BIT macro for higher
attributes by mistake.

This commit cleans up all usages of BIT macro with the above field
in wireless-drivers by changing it to BIT_ULL instead. In addition, there are
some places which don't use BIT nor BIT_ULL macros so align those as well.

Signed-off-by: Omer Efrat <omer.efrat@tandemg.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c              |  4 +--
 drivers/net/wireless/ath/ath6kl/cfg80211.c         | 14 ++++----
 drivers/net/wireless/ath/wil6210/cfg80211.c        | 18 +++++-----
 .../broadcom/brcm80211/brcmfmac/cfg80211.c         | 40 +++++++++++-----------
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  |  6 ++--
 drivers/net/wireless/marvell/libertas/cfg.c        | 12 +++----
 drivers/net/wireless/marvell/mwifiex/cfg80211.c    | 14 ++++----
 drivers/net/wireless/quantenna/qtnfmac/commands.c  | 32 ++++++++---------
 drivers/net/wireless/rndis_wlan.c                  |  4 +--
 drivers/net/wireless/ti/wlcore/main.c              |  2 +-
 10 files changed, 73 insertions(+), 73 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index f31ae3be4778..fcbd3aeb692c 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -7725,7 +7725,7 @@ static void ath10k_sta_statistics(struct ieee80211_hw *hw,
 		return;
 
 	sinfo->rx_duration = arsta->rx_duration;
-	sinfo->filled |= 1ULL << NL80211_STA_INFO_RX_DURATION;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION);
 
 	if (!arsta->txrate.legacy && !arsta->txrate.nss)
 		return;
@@ -7738,7 +7738,7 @@ static void ath10k_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->txrate.bw = arsta->txrate.bw;
 	}
 	sinfo->txrate.flags = arsta->txrate.flags;
-	sinfo->filled |= 1ULL << NL80211_STA_INFO_TX_BITRATE;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 }
 
 static const struct ieee80211_ops ath10k_ops = {
diff --git a/drivers/net/wireless/ath/ath6kl/cfg80211.c b/drivers/net/wireless/ath/ath6kl/cfg80211.c
index 4e56a2d4a5cf..e121187f371f 100644
--- a/drivers/net/wireless/ath/ath6kl/cfg80211.c
+++ b/drivers/net/wireless/ath/ath6kl/cfg80211.c
@@ -1811,20 +1811,20 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 
 	if (vif->target_stats.rx_byte) {
 		sinfo->rx_bytes = vif->target_stats.rx_byte;
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
 		sinfo->rx_packets = vif->target_stats.rx_pkt;
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 	}
 
 	if (vif->target_stats.tx_byte) {
 		sinfo->tx_bytes = vif->target_stats.tx_byte;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
 		sinfo->tx_packets = vif->target_stats.tx_pkt;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 	}
 
 	sinfo->signal = vif->target_stats.cs_rssi;
-	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 
 	rate = vif->target_stats.tx_ucast_rate;
 
@@ -1857,12 +1857,12 @@ static int ath6kl_get_station(struct wiphy *wiphy, struct net_device *dev,
 		return 0;
 	}
 
-	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 
 	if (test_bit(CONNECTED, &vif->flags) &&
 	    test_bit(DTIM_PERIOD_AVAIL, &vif->flags) &&
 	    vif->nw_type == INFRA_NETWORK) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BSS_PARAM);
 		sinfo->bss_param.flags = 0;
 		sinfo->bss_param.dtim_period = vif->assoc_bss_dtim_period;
 		sinfo->bss_param.beacon_interval = vif->assoc_bss_beacon_int;
diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 78946f28d0c7..013d056a7a4c 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -302,14 +302,14 @@ int wil_cid_fill_sinfo(struct wil6210_vif *vif, int cid,
 
 	sinfo->generation = wil->sinfo_gen;
 
-	sinfo->filled = BIT(NL80211_STA_INFO_RX_BYTES) |
-			BIT(NL80211_STA_INFO_TX_BYTES) |
-			BIT(NL80211_STA_INFO_RX_PACKETS) |
-			BIT(NL80211_STA_INFO_TX_PACKETS) |
-			BIT(NL80211_STA_INFO_RX_BITRATE) |
-			BIT(NL80211_STA_INFO_TX_BITRATE) |
-			BIT(NL80211_STA_INFO_RX_DROP_MISC) |
-			BIT(NL80211_STA_INFO_TX_FAILED);
+	sinfo->filled = BIT_ULL(NL80211_STA_INFO_RX_BYTES) |
+			BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+			BIT_ULL(NL80211_STA_INFO_RX_PACKETS) |
+			BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			BIT_ULL(NL80211_STA_INFO_RX_BITRATE) |
+			BIT_ULL(NL80211_STA_INFO_TX_BITRATE) |
+			BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC) |
+			BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 
 	sinfo->txrate.flags = RATE_INFO_FLAGS_60G;
 	sinfo->txrate.mcs = le16_to_cpu(reply.evt.bf_mcs);
@@ -322,7 +322,7 @@ int wil_cid_fill_sinfo(struct wil6210_vif *vif, int cid,
 	sinfo->tx_failed = stats->tx_errors;
 
 	if (test_bit(wil_vif_fwconnected, vif->status)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 		if (test_bit(WMI_FW_CAPABILITY_RSSI_REPORTING,
 			     wil->fw_capabilities))
 			sinfo->signal = reply.evt.rssi;
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index b6122aad639e..24c4e18e7d80 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -2434,7 +2434,7 @@ static void brcmf_convert_sta_flags(u32 fw_sta_flags, struct station_info *si)
 	struct nl80211_sta_flag_update *sfu;
 
 	brcmf_dbg(TRACE, "flags %08x\n", fw_sta_flags);
-	si->filled |= BIT(NL80211_STA_INFO_STA_FLAGS);
+	si->filled |= BIT_ULL(NL80211_STA_INFO_STA_FLAGS);
 	sfu = &si->sta_flags;
 	sfu->mask = BIT(NL80211_STA_FLAG_WME) |
 		    BIT(NL80211_STA_FLAG_AUTHENTICATED) |
@@ -2470,7 +2470,7 @@ static void brcmf_fill_bss_param(struct brcmf_if *ifp, struct station_info *si)
 		brcmf_err("Failed to get bss info (%d)\n", err);
 		goto out_kfree;
 	}
-	si->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
+	si->filled |= BIT_ULL(NL80211_STA_INFO_BSS_PARAM);
 	si->bss_param.beacon_interval = le16_to_cpu(buf->bss_le.beacon_period);
 	si->bss_param.dtim_period = buf->bss_le.dtim_period;
 	capability = le16_to_cpu(buf->bss_le.capability);
@@ -2501,7 +2501,7 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
 		brcmf_err("BRCMF_C_GET_RATE error (%d)\n", err);
 		return err;
 	}
-	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 	sinfo->txrate.legacy = rate * 5;
 
 	memset(&scbval, 0, sizeof(scbval));
@@ -2512,7 +2512,7 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
 		return err;
 	}
 	rssi = le32_to_cpu(scbval.val);
-	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	sinfo->signal = rssi;
 
 	err = brcmf_fil_cmd_data_get(ifp, BRCMF_C_GET_GET_PKTCNTS, &pktcnt,
@@ -2521,10 +2521,10 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
 		brcmf_err("BRCMF_C_GET_GET_PKTCNTS error (%d)\n", err);
 		return err;
 	}
-	sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS) |
-			 BIT(NL80211_STA_INFO_RX_DROP_MISC) |
-			 BIT(NL80211_STA_INFO_TX_PACKETS) |
-			 BIT(NL80211_STA_INFO_TX_FAILED);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS) |
+			 BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC) |
+			 BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			 BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 	sinfo->rx_packets = le32_to_cpu(pktcnt.rx_good_pkt);
 	sinfo->rx_dropped_misc = le32_to_cpu(pktcnt.rx_bad_pkt);
 	sinfo->tx_packets = le32_to_cpu(pktcnt.tx_good_pkt);
@@ -2571,7 +2571,7 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 		}
 	}
 	brcmf_dbg(TRACE, "version %d\n", le16_to_cpu(sta_info_le.ver));
-	sinfo->filled = BIT(NL80211_STA_INFO_INACTIVE_TIME);
+	sinfo->filled = BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME);
 	sinfo->inactive_time = le32_to_cpu(sta_info_le.idle) * 1000;
 	sta_flags = le32_to_cpu(sta_info_le.flags);
 	brcmf_convert_sta_flags(sta_flags, sinfo);
@@ -2581,33 +2581,33 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 	else
 		sinfo->sta_flags.set &= ~BIT(NL80211_STA_FLAG_TDLS_PEER);
 	if (sta_flags & BRCMF_STA_ASSOC) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_CONNECTED_TIME);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME);
 		sinfo->connected_time = le32_to_cpu(sta_info_le.in);
 		brcmf_fill_bss_param(ifp, sinfo);
 	}
 	if (sta_flags & BRCMF_STA_SCBSTATS) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 		sinfo->tx_failed = le32_to_cpu(sta_info_le.tx_failures);
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 		sinfo->tx_packets = le32_to_cpu(sta_info_le.tx_pkts);
 		sinfo->tx_packets += le32_to_cpu(sta_info_le.tx_mcast_pkts);
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 		sinfo->rx_packets = le32_to_cpu(sta_info_le.rx_ucast_pkts);
 		sinfo->rx_packets += le32_to_cpu(sta_info_le.rx_mcast_pkts);
 		if (sinfo->tx_packets) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 			sinfo->txrate.legacy =
 				le32_to_cpu(sta_info_le.tx_rate) / 100;
 		}
 		if (sinfo->rx_packets) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
 			sinfo->rxrate.legacy =
 				le32_to_cpu(sta_info_le.rx_rate) / 100;
 		}
 		if (le16_to_cpu(sta_info_le.ver) >= 4) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES);
 			sinfo->tx_bytes = le64_to_cpu(sta_info_le.tx_tot_bytes);
-			sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES);
 			sinfo->rx_bytes = le64_to_cpu(sta_info_le.rx_tot_bytes);
 		}
 		total_rssi = 0;
@@ -2623,10 +2623,10 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 			}
 		}
 		if (count_rssi) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL);
 			sinfo->chains = count_rssi;
 
-			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 			total_rssi /= count_rssi;
 			sinfo->signal = total_rssi;
 		} else if (test_bit(BRCMF_VIF_STATUS_CONNECTED,
@@ -2639,7 +2639,7 @@ brcmf_cfg80211_get_station(struct wiphy *wiphy, struct net_device *ndev,
 				goto done;
 			} else {
 				rssi = le32_to_cpu(scb_val.val);
-				sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+				sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 				sinfo->signal = rssi;
 				brcmf_dbg(CONN, "RSSI %d dBm\n", rssi);
 			}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a6e072234398..26021bc55e98 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4216,7 +4216,7 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 
 	if (mvmsta->avg_energy) {
 		sinfo->signal_avg = mvmsta->avg_energy;
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 	}
 
 	if (!fw_has_capa(&mvm->fw->ucode_capa,
@@ -4240,11 +4240,11 @@ static void iwl_mvm_mac_sta_statistics(struct ieee80211_hw *hw,
 
 	sinfo->rx_beacon = mvmvif->beacon_stats.num_beacons +
 			   mvmvif->beacon_stats.accu_num_beacons;
-	sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX);
 	if (mvmvif->beacon_stats.avg_signal) {
 		/* firmware only reports a value after RXing a few beacons */
 		sinfo->rx_beacon_signal_avg = mvmvif->beacon_stats.avg_signal;
-		sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
 	}
  unlock:
 	mutex_unlock(&mvm->mutex);
diff --git a/drivers/net/wireless/marvell/libertas/cfg.c b/drivers/net/wireless/marvell/libertas/cfg.c
index f99031cfdf86..57edfada0665 100644
--- a/drivers/net/wireless/marvell/libertas/cfg.c
+++ b/drivers/net/wireless/marvell/libertas/cfg.c
@@ -1559,10 +1559,10 @@ static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
 	int ret;
 	size_t i;
 
-	sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES) |
-			 BIT(NL80211_STA_INFO_TX_PACKETS) |
-			 BIT(NL80211_STA_INFO_RX_BYTES) |
-			 BIT(NL80211_STA_INFO_RX_PACKETS);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+			 BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			 BIT_ULL(NL80211_STA_INFO_RX_BYTES) |
+			 BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 	sinfo->tx_bytes = priv->dev->stats.tx_bytes;
 	sinfo->tx_packets = priv->dev->stats.tx_packets;
 	sinfo->rx_bytes = priv->dev->stats.rx_bytes;
@@ -1572,14 +1572,14 @@ static int lbs_cfg_get_station(struct wiphy *wiphy, struct net_device *dev,
 	ret = lbs_get_rssi(priv, &signal, &noise);
 	if (ret == 0) {
 		sinfo->signal = signal;
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	}
 
 	/* Convert priv->cur_rate from hw_value to NL80211 value */
 	for (i = 0; i < ARRAY_SIZE(lbs_rates); i++) {
 		if (priv->cur_rate == lbs_rates[i].hw_value) {
 			sinfo->txrate.legacy = lbs_rates[i].bitrate;
-			sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 			break;
 		}
 	}
diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index 4b5ae9098504..c02e02c17c9c 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -1353,17 +1353,17 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 {
 	u32 rate;
 
-	sinfo->filled = BIT(NL80211_STA_INFO_RX_BYTES) | BIT(NL80211_STA_INFO_TX_BYTES) |
-			BIT(NL80211_STA_INFO_RX_PACKETS) | BIT(NL80211_STA_INFO_TX_PACKETS) |
-			BIT(NL80211_STA_INFO_TX_BITRATE) |
-			BIT(NL80211_STA_INFO_SIGNAL) | BIT(NL80211_STA_INFO_SIGNAL_AVG);
+	sinfo->filled = BIT_ULL(NL80211_STA_INFO_RX_BYTES) | BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+			BIT_ULL(NL80211_STA_INFO_RX_PACKETS) | BIT_ULL(NL80211_STA_INFO_TX_PACKETS) |
+			BIT_ULL(NL80211_STA_INFO_TX_BITRATE) |
+			BIT_ULL(NL80211_STA_INFO_SIGNAL) | BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 
 	if (GET_BSS_ROLE(priv) == MWIFIEX_BSS_ROLE_UAP) {
 		if (!node)
 			return -ENOENT;
 
-		sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) |
-				BIT(NL80211_STA_INFO_TX_FAILED);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) |
+				BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 		sinfo->inactive_time =
 			jiffies_to_msecs(jiffies - node->stats.last_rx);
 
@@ -1413,7 +1413,7 @@ mwifiex_dump_station_info(struct mwifiex_private *priv,
 	sinfo->txrate.legacy = rate * 5;
 
 	if (priv->bss_mode == NL80211_IFTYPE_STATION) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_BSS_PARAM);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BSS_PARAM);
 		sinfo->bss_param.flags = 0;
 		if (priv->curr_bss_params.bss_descriptor.cap_info_bitmap &
 						WLAN_CAPABILITY_SHORT_PREAMBLE)
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index 713fd3f047e4..42a598f92539 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -640,83 +640,83 @@ qtnf_cmd_sta_info_parse(struct station_info *sinfo,
 		return;
 
 	if (qtnf_sta_stat_avail(inactive_time, QLINK_STA_INFO_INACTIVE_TIME)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME);
 		sinfo->inactive_time = le32_to_cpu(stats->inactive_time);
 	}
 
 	if (qtnf_sta_stat_avail(connected_time,
 				QLINK_STA_INFO_CONNECTED_TIME)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_CONNECTED_TIME);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME);
 		sinfo->connected_time = le32_to_cpu(stats->connected_time);
 	}
 
 	if (qtnf_sta_stat_avail(signal, QLINK_STA_INFO_SIGNAL)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 		sinfo->signal = stats->signal - QLINK_RSSI_OFFSET;
 	}
 
 	if (qtnf_sta_stat_avail(signal_avg, QLINK_STA_INFO_SIGNAL_AVG)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 		sinfo->signal_avg = stats->signal_avg - QLINK_RSSI_OFFSET;
 	}
 
 	if (qtnf_sta_stat_avail(rxrate, QLINK_STA_INFO_RX_BITRATE)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
 		qtnf_sta_info_parse_rate(&sinfo->rxrate, &stats->rxrate);
 	}
 
 	if (qtnf_sta_stat_avail(txrate, QLINK_STA_INFO_TX_BITRATE)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 		qtnf_sta_info_parse_rate(&sinfo->txrate, &stats->txrate);
 	}
 
 	if (qtnf_sta_stat_avail(sta_flags, QLINK_STA_INFO_STA_FLAGS)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_STA_FLAGS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_STA_FLAGS);
 		qtnf_sta_info_parse_flags(&sinfo->sta_flags, &stats->sta_flags);
 	}
 
 	if (qtnf_sta_stat_avail(rx_bytes, QLINK_STA_INFO_RX_BYTES)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES);
 		sinfo->rx_bytes = le64_to_cpu(stats->rx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(tx_bytes, QLINK_STA_INFO_TX_BYTES)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES);
 		sinfo->tx_bytes = le64_to_cpu(stats->tx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(rx_bytes, QLINK_STA_INFO_RX_BYTES64)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
 		sinfo->rx_bytes = le64_to_cpu(stats->rx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(tx_bytes, QLINK_STA_INFO_TX_BYTES64)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
 		sinfo->tx_bytes = le64_to_cpu(stats->tx_bytes);
 	}
 
 	if (qtnf_sta_stat_avail(rx_packets, QLINK_STA_INFO_RX_PACKETS)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 		sinfo->rx_packets = le32_to_cpu(stats->rx_packets);
 	}
 
 	if (qtnf_sta_stat_avail(tx_packets, QLINK_STA_INFO_TX_PACKETS)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 		sinfo->tx_packets = le32_to_cpu(stats->tx_packets);
 	}
 
 	if (qtnf_sta_stat_avail(rx_beacon, QLINK_STA_INFO_BEACON_RX)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX);
 		sinfo->rx_beacon = le64_to_cpu(stats->rx_beacon);
 	}
 
 	if (qtnf_sta_stat_avail(rx_dropped_misc, QLINK_STA_INFO_RX_DROP_MISC)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_DROP_MISC);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC);
 		sinfo->rx_dropped_misc = le32_to_cpu(stats->rx_dropped_misc);
 	}
 
 	if (qtnf_sta_stat_avail(tx_failed, QLINK_STA_INFO_TX_FAILED)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 		sinfo->tx_failed = le32_to_cpu(stats->tx_failed);
 	}
 
diff --git a/drivers/net/wireless/rndis_wlan.c b/drivers/net/wireless/rndis_wlan.c
index d4947e3a909e..51e4e92d95a0 100644
--- a/drivers/net/wireless/rndis_wlan.c
+++ b/drivers/net/wireless/rndis_wlan.c
@@ -2480,7 +2480,7 @@ static void rndis_fill_station_info(struct usbnet *usbdev,
 	ret = rndis_query_oid(usbdev, RNDIS_OID_GEN_LINK_SPEED, &linkspeed, &len);
 	if (ret == 0) {
 		sinfo->txrate.legacy = le32_to_cpu(linkspeed) / 1000;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 	}
 
 	len = sizeof(rssi);
@@ -2488,7 +2488,7 @@ static void rndis_fill_station_info(struct usbnet *usbdev,
 			      &rssi, &len);
 	if (ret == 0) {
 		sinfo->signal = level_to_qual(le32_to_cpu(rssi));
-		sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	}
 }
 
diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 09c40e7f7701..37f785f601c1 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -5821,7 +5821,7 @@ static void wlcore_op_sta_statistics(struct ieee80211_hw *hw,
 	if (ret < 0)
 		goto out_sleep;
 
-	sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	sinfo->signal = rssi_dbm;
 
 out_sleep:
-- 
cgit v1.2.3


From 71e140b57151425829f87a0aaaa87636860dd7d2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:11:15 +0200
Subject: zd1211rw: stop using deprecated get_seconds()

The get_seconds() function is deprecated because of the y2038 overflow.
In zd1211rw we don't even care about the absolute value, so this is
not a problem, but it's equally trivial to change to the non-deprecated
ktime_get_seconds().

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/zydas/zd1211rw/zd_chip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_chip.c b/drivers/net/wireless/zydas/zd1211rw/zd_chip.c
index 07b94eda9604..dd6a86b899eb 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_chip.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_chip.c
@@ -1341,7 +1341,7 @@ int zd_chip_control_leds(struct zd_chip *chip, enum led_status status)
 	case ZD_LED_SCANNING:
 		ioreqs[0].value = FW_LINK_OFF;
 		ioreqs[1].value = v[1] & ~other_led;
-		if (get_seconds() % 3 == 0) {
+		if ((u32)ktime_get_seconds() % 3 == 0) {
 			ioreqs[1].value &= ~chip->link_led;
 		} else {
 			ioreqs[1].value |= chip->link_led;
-- 
cgit v1.2.3


From 3cade2f3d98a7fcfd36fcb0d743f5ed5cdffb119 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:11:16 +0200
Subject: ipw2x00: track time using boottime

The ipw2x00 driver family uses get_seconds() to read the current time
for various purposes. This function is deprecated because of the 32-bit
time_t overflow, and it can cause unexpected behavior when the time
changes due to settimeofday() calls or leap second updates.

In many cases, we want to use monotonic time instead, however ipw2x00
explicitly tracks the time spent in suspend, so this changes the
driver over to use ktime_get_boottime_seconds(), which is slightly
slower, but not used in a fastpath here.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Stanislav Yakovlev <stas.yakovlev@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/ipw2x00/ipw2100.c | 18 +++++++++---------
 drivers/net/wireless/intel/ipw2x00/ipw2100.h | 12 ++++++------
 drivers/net/wireless/intel/ipw2x00/ipw2200.c |  4 ++--
 drivers/net/wireless/intel/ipw2x00/ipw2200.h |  6 +++---
 4 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index b8fd3cc90634..1ad83ef5f202 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -692,7 +692,7 @@ static void printk_buf(int level, const u8 * data, u32 len)
 
 static void schedule_reset(struct ipw2100_priv *priv)
 {
-	unsigned long now = get_seconds();
+	time64_t now = ktime_get_boottime_seconds();
 
 	/* If we haven't received a reset request within the backoff period,
 	 * then we can reset the backoff interval so this reset occurs
@@ -701,10 +701,10 @@ static void schedule_reset(struct ipw2100_priv *priv)
 	    (now - priv->last_reset > priv->reset_backoff))
 		priv->reset_backoff = 0;
 
-	priv->last_reset = get_seconds();
+	priv->last_reset = now;
 
 	if (!(priv->status & STATUS_RESET_PENDING)) {
-		IPW_DEBUG_INFO("%s: Scheduling firmware restart (%ds).\n",
+		IPW_DEBUG_INFO("%s: Scheduling firmware restart (%llds).\n",
 			       priv->net_dev->name, priv->reset_backoff);
 		netif_carrier_off(priv->net_dev);
 		netif_stop_queue(priv->net_dev);
@@ -2079,7 +2079,7 @@ static void isr_indicate_associated(struct ipw2100_priv *priv, u32 status)
 	memcpy(priv->bssid, bssid, ETH_ALEN);
 
 	priv->status |= STATUS_ASSOCIATING;
-	priv->connect_start = get_seconds();
+	priv->connect_start = ktime_get_boottime_seconds();
 
 	schedule_delayed_work(&priv->wx_event_work, HZ / 10);
 }
@@ -4070,8 +4070,8 @@ static ssize_t show_internals(struct device *d, struct device_attribute *attr,
 #define DUMP_VAR(x,y) len += sprintf(buf + len, # x ": %" y "\n", priv-> x)
 
 	if (priv->status & STATUS_ASSOCIATED)
-		len += sprintf(buf + len, "connected: %lu\n",
-			       get_seconds() - priv->connect_start);
+		len += sprintf(buf + len, "connected: %llu\n",
+			       ktime_get_boottime_seconds() - priv->connect_start);
 	else
 		len += sprintf(buf + len, "not connected\n");
 
@@ -4108,7 +4108,7 @@ static ssize_t show_internals(struct device *d, struct device_attribute *attr,
 	DUMP_VAR(txq_stat.lo, "d");
 
 	DUMP_VAR(ieee->scans, "d");
-	DUMP_VAR(reset_backoff, "d");
+	DUMP_VAR(reset_backoff, "lld");
 
 	return len;
 }
@@ -6437,7 +6437,7 @@ static int ipw2100_suspend(struct pci_dev *pci_dev, pm_message_t state)
 	pci_disable_device(pci_dev);
 	pci_set_power_state(pci_dev, PCI_D3hot);
 
-	priv->suspend_at = get_seconds();
+	priv->suspend_at = ktime_get_boottime_seconds();
 
 	mutex_unlock(&priv->action_mutex);
 
@@ -6482,7 +6482,7 @@ static int ipw2100_resume(struct pci_dev *pci_dev)
 	 * the queue of needed */
 	netif_device_attach(dev);
 
-	priv->suspend_time = get_seconds() - priv->suspend_at;
+	priv->suspend_time = ktime_get_boottime_seconds() - priv->suspend_at;
 
 	/* Bring the device back up */
 	if (!(priv->status & STATUS_RF_KILL_SW))
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.h b/drivers/net/wireless/intel/ipw2x00/ipw2100.h
index ce3e35f6b60f..8c11c7fa2eef 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.h
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.h
@@ -491,7 +491,7 @@ struct ipw2100_priv {
 
 	/* Statistics */
 	int resets;
-	int reset_backoff;
+	time64_t reset_backoff;
 
 	/* Context */
 	u8 essid[IW_ESSID_MAX_SIZE];
@@ -500,8 +500,8 @@ struct ipw2100_priv {
 	u8 channel;
 	int last_mode;
 
-	unsigned long connect_start;
-	unsigned long last_reset;
+	time64_t connect_start;
+	time64_t last_reset;
 
 	u32 channel_mask;
 	u32 fatal_error;
@@ -581,9 +581,9 @@ struct ipw2100_priv {
 
 	int user_requested_scan;
 
-	/* Track time in suspend */
-	unsigned long suspend_at;
-	unsigned long suspend_time;
+	/* Track time in suspend, using CLOCK_BOOTTIME */
+	time64_t suspend_at;
+	time64_t suspend_time;
 
 	u32 interrupts;
 	int tx_interrupts;
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index 62140109d2ac..9644e7b93645 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -11888,7 +11888,7 @@ static int ipw_pci_suspend(struct pci_dev *pdev, pm_message_t state)
 	pci_disable_device(pdev);
 	pci_set_power_state(pdev, pci_choose_state(pdev, state));
 
-	priv->suspend_at = get_seconds();
+	priv->suspend_at = ktime_get_boottime_seconds();
 
 	return 0;
 }
@@ -11925,7 +11925,7 @@ static int ipw_pci_resume(struct pci_dev *pdev)
 	 * the queue of needed */
 	netif_device_attach(dev);
 
-	priv->suspend_time = get_seconds() - priv->suspend_at;
+	priv->suspend_time = ktime_get_boottime_seconds() - priv->suspend_at;
 
 	/* Bring the device back up */
 	schedule_work(&priv->up);
diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.h b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
index aa301d1eee3c..f98ab1f71edd 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.h
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.h
@@ -1343,9 +1343,9 @@ struct ipw_priv {
 
 	s8 tx_power;
 
-	/* Track time in suspend */
-	unsigned long suspend_at;
-	unsigned long suspend_time;
+	/* Track time in suspend using CLOCK_BOOTIME */
+	time64_t suspend_at;
+	time64_t suspend_time;
 
 #ifdef CONFIG_PM
 	u32 pm_state[16];
-- 
cgit v1.2.3


From c288248f5b26cd5563112fcdc077bf44964a942d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 27 Jun 2018 14:59:00 +0200
Subject: ALSA: intel_hdmi: Use strlcpy() instead of strncpy()

hdmi_lpe_audio_probe() copies the pcm name string via strncpy(), but
as a gcc8 warning suggests, it misses a NUL terminator, and unlikely
the expected result.

Use the proper one, strlcpy() instead.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/x86/intel_hdmi_audio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c
index 4ed9d0c41843..edc9f5a34eff 100644
--- a/sound/x86/intel_hdmi_audio.c
+++ b/sound/x86/intel_hdmi_audio.c
@@ -1854,7 +1854,7 @@ static int hdmi_lpe_audio_probe(struct platform_device *pdev)
 		/* setup private data which can be retrieved when required */
 		pcm->private_data = ctx;
 		pcm->info_flags = 0;
-		strncpy(pcm->name, card->shortname, strlen(card->shortname));
+		strlcpy(pcm->name, card->shortname, strlen(card->shortname));
 		/* setup the ops for playabck */
 		snd_pcm_set_ops(pcm, SNDRV_PCM_STREAM_PLAYBACK, &had_pcm_ops);
 
-- 
cgit v1.2.3


From fc75122fabb54d38a0cedcc6e99004dc99af9631 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:36:46 +0200
Subject: libertas_tf: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

I am removing the
	BUG_ON(!in_interrupt());

check because it serves no purpose. Running the completion callback in
BH context makes in_interrupt() still return true but the interrupts
could be enabled. The important part is that ->driver_lock is acquired
with disabled interrupts which is the case now.

Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-wireless@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/libertas_tf/if_usb.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas_tf/if_usb.c b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
index 5153922e7ce1..e92fc5001171 100644
--- a/drivers/net/wireless/marvell/libertas_tf/if_usb.c
+++ b/drivers/net/wireless/marvell/libertas_tf/if_usb.c
@@ -603,6 +603,8 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 				      struct if_usb_card *cardp,
 				      struct lbtf_private *priv)
 {
+	unsigned long flags;
+
 	if (recvlength > LBS_CMD_BUFFER_SIZE) {
 		lbtf_deb_usbd(&cardp->udev->dev,
 			     "The receive buffer is too large\n");
@@ -610,14 +612,12 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 		return;
 	}
 
-	BUG_ON(!in_interrupt());
-
-	spin_lock(&priv->driver_lock);
+	spin_lock_irqsave(&priv->driver_lock, flags);
 	memcpy(priv->cmd_resp_buff, recvbuff + MESSAGE_HEADER_LEN,
 	       recvlength - MESSAGE_HEADER_LEN);
 	kfree_skb(skb);
 	lbtf_cmd_response_rx(priv);
-	spin_unlock(&priv->driver_lock);
+	spin_unlock_irqrestore(&priv->driver_lock, flags);
 }
 
 /**
-- 
cgit v1.2.3


From a3128feef6d516fecc33b6299266a4673454815f Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:36:47 +0200
Subject: libertas: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

I am removing the
	BUG_ON(!in_interrupt());

check because it serves no purpose. Running the completion callback in
BH context makes in_interrupt() still return true but the interrupts
could be enabled. The important part is that ->driver_lock is acquired
with disabled interrupts which is the case now.

Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: libertas-dev@lists.infradead.org
Cc: linux-wireless@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/libertas/if_usb.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/if_usb.c b/drivers/net/wireless/marvell/libertas/if_usb.c
index ffea610f67e2..c67a8e7be310 100644
--- a/drivers/net/wireless/marvell/libertas/if_usb.c
+++ b/drivers/net/wireless/marvell/libertas/if_usb.c
@@ -614,6 +614,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 				      struct if_usb_card *cardp,
 				      struct lbs_private *priv)
 {
+	unsigned long flags;
 	u8 i;
 
 	if (recvlength > LBS_CMD_BUFFER_SIZE) {
@@ -623,9 +624,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 		return;
 	}
 
-	BUG_ON(!in_interrupt());
-
-	spin_lock(&priv->driver_lock);
+	spin_lock_irqsave(&priv->driver_lock, flags);
 
 	i = (priv->resp_idx == 0) ? 1 : 0;
 	BUG_ON(priv->resp_len[i]);
@@ -635,7 +634,7 @@ static inline void process_cmdrequest(int recvlength, uint8_t *recvbuff,
 	kfree_skb(skb);
 	lbs_notify_command_response(priv, i);
 
-	spin_unlock(&priv->driver_lock);
+	spin_unlock_irqrestore(&priv->driver_lock, flags);
 
 	lbs_deb_usbd(&cardp->udev->dev,
 		    "Wake up main thread to handle cmd response\n");
-- 
cgit v1.2.3


From 81454b8405f24df8b24984698d62c5f560d01fe3 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:36:48 +0200
Subject: zd1211rw: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: Daniel Drake <dsd@gentoo.org>
Cc: Ulrich Kunitz <kune@deine-taler.de>
Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-wireless@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/zydas/zd1211rw/zd_usb.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
index c30bf118c67d..c2cda3acd4af 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_usb.c
@@ -371,25 +371,27 @@ static inline void handle_regs_int_override(struct urb *urb)
 {
 	struct zd_usb *usb = urb->context;
 	struct zd_usb_interrupt *intr = &usb->intr;
+	unsigned long flags;
 
-	spin_lock(&intr->lock);
+	spin_lock_irqsave(&intr->lock, flags);
 	if (atomic_read(&intr->read_regs_enabled)) {
 		atomic_set(&intr->read_regs_enabled, 0);
 		intr->read_regs_int_overridden = 1;
 		complete(&intr->read_regs.completion);
 	}
-	spin_unlock(&intr->lock);
+	spin_unlock_irqrestore(&intr->lock, flags);
 }
 
 static inline void handle_regs_int(struct urb *urb)
 {
 	struct zd_usb *usb = urb->context;
 	struct zd_usb_interrupt *intr = &usb->intr;
+	unsigned long flags;
 	int len;
 	u16 int_num;
 
 	ZD_ASSERT(in_interrupt());
-	spin_lock(&intr->lock);
+	spin_lock_irqsave(&intr->lock, flags);
 
 	int_num = le16_to_cpu(*(__le16 *)(urb->transfer_buffer+2));
 	if (int_num == CR_INTERRUPT) {
@@ -425,7 +427,7 @@ static inline void handle_regs_int(struct urb *urb)
 	}
 
 out:
-	spin_unlock(&intr->lock);
+	spin_unlock_irqrestore(&intr->lock, flags);
 
 	/* CR_INTERRUPT might override read_reg too. */
 	if (int_num == CR_INTERRUPT && atomic_read(&intr->read_regs_enabled))
@@ -665,6 +667,7 @@ static void rx_urb_complete(struct urb *urb)
 	struct zd_usb_rx *rx;
 	const u8 *buffer;
 	unsigned int length;
+	unsigned long flags;
 
 	switch (urb->status) {
 	case 0:
@@ -693,14 +696,14 @@ static void rx_urb_complete(struct urb *urb)
 		/* If there is an old first fragment, we don't care. */
 		dev_dbg_f(urb_dev(urb), "*** first fragment ***\n");
 		ZD_ASSERT(length <= ARRAY_SIZE(rx->fragment));
-		spin_lock(&rx->lock);
+		spin_lock_irqsave(&rx->lock, flags);
 		memcpy(rx->fragment, buffer, length);
 		rx->fragment_length = length;
-		spin_unlock(&rx->lock);
+		spin_unlock_irqrestore(&rx->lock, flags);
 		goto resubmit;
 	}
 
-	spin_lock(&rx->lock);
+	spin_lock_irqsave(&rx->lock, flags);
 	if (rx->fragment_length > 0) {
 		/* We are on a second fragment, we believe */
 		ZD_ASSERT(length + rx->fragment_length <=
@@ -710,9 +713,9 @@ static void rx_urb_complete(struct urb *urb)
 		handle_rx_packet(usb, rx->fragment,
 			         rx->fragment_length + length);
 		rx->fragment_length = 0;
-		spin_unlock(&rx->lock);
+		spin_unlock_irqrestore(&rx->lock, flags);
 	} else {
-		spin_unlock(&rx->lock);
+		spin_unlock_irqrestore(&rx->lock, flags);
 		handle_rx_packet(usb, buffer, length);
 	}
 
-- 
cgit v1.2.3


From aea38272920c227865af25c7d7710f1ab0d8a1ce Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:17:53 +0200
Subject: mt76: fix beacon timer drift

The beacon timer drifts by 1 microsecond every TBTT. After 20 minutes
with a beacon interval of 100, the drift will be almost 12 ms, enough to
cause weird issues for devices in powersave mode.

Since the beacon timer is configured in units of 1/16 TU (64 us), we
need to adjust it once every 64 beacons and only for one beacon.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2.h      |  5 +++-
 drivers/net/wireless/mediatek/mt76/mt76x2_main.c |  5 +++-
 drivers/net/wireless/mediatek/mt76/mt76x2_tx.c   | 33 ++++++++++++++++++++++++
 3 files changed, 41 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index dc12bbdbb2ee..06ca5a77dfdf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -120,10 +120,13 @@ struct mt76x2_dev {
 	u8 beacon_mask;
 	u8 beacon_data_mask;
 
-	u32 rxfilter;
+	u8 tbtt_count;
+	u16 beacon_int;
 
 	u16 chainmask;
 
+	u32 rxfilter;
+
 	struct mt76x2_calibration cal;
 
 	s8 target_power;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
index ce90ff999b49..e4e41faf6739 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
@@ -238,10 +238,13 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (changed & BSS_CHANGED_BSSID)
 		mt76x2_mac_set_bssid(dev, mvif->idx, info->bssid);
 
-	if (changed & BSS_CHANGED_BEACON_INT)
+	if (changed & BSS_CHANGED_BEACON_INT) {
 		mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
 			       MT_BEACON_TIME_CFG_INTVAL,
 			       info->beacon_int << 4);
+		dev->beacon_int = info->beacon_int;
+		dev->tbtt_count = 0;
+	}
 
 	if (changed & BSS_CHANGED_BEACON_ENABLED) {
 		tasklet_disable(&dev->pre_tbtt_tasklet);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
index e46eafc4c436..560376dd1133 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
@@ -218,6 +218,37 @@ mt76x2_add_buffered_bc(void *priv, u8 *mac, struct ieee80211_vif *vif)
 	data->tail[mvif->idx] = skb;
 }
 
+static void
+mt76x2_resync_beacon_timer(struct mt76x2_dev *dev)
+{
+	u32 timer_val = dev->beacon_int << 4;
+
+	dev->tbtt_count++;
+
+	/*
+	 * Beacon timer drifts by 1us every tick, the timer is configured
+	 * in 1/16 TU (64us) units.
+	 */
+	if (dev->tbtt_count < 62)
+		return;
+
+	if (dev->tbtt_count >= 64) {
+		dev->tbtt_count = 0;
+		return;
+	}
+
+	/*
+	 * The updated beacon interval takes effect after two TBTT, because
+	 * at this point the original interval has already been loaded into
+	 * the next TBTT_TIMER value
+	 */
+	if (dev->tbtt_count == 62)
+		timer_val -= 1;
+
+	mt76_rmw_field(dev, MT_BEACON_TIME_CFG,
+		       MT_BEACON_TIME_CFG_INTVAL, timer_val);
+}
+
 void mt76x2_pre_tbtt_tasklet(unsigned long arg)
 {
 	struct mt76x2_dev *dev = (struct mt76x2_dev *) arg;
@@ -226,6 +257,8 @@ void mt76x2_pre_tbtt_tasklet(unsigned long arg)
 	struct sk_buff *skb;
 	int i, nframes;
 
+	mt76x2_resync_beacon_timer(dev);
+
 	data.dev = dev;
 	__skb_queue_head_init(&data.q);
 
-- 
cgit v1.2.3


From 9afef0fddaa1879ae4e14fc3079e38f1fbdd7427 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:17:54 +0200
Subject: mt76: fix threshold for gain adjustment

The gain should be reduced only for very strong connections, not for mid
range.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index c1c38ca3330a..4ed6641c3a32 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -530,7 +530,7 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 	else
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560423);
 
-	if (low_gain) {
+	if (low_gain == 2) {
 		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
 		mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808);
 		mt76_wr(dev, MT_BBP(AGC, 37), 0x08080808);
-- 
cgit v1.2.3


From 6cdb9614a818b7e318328c9e30d3ee4046308678 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:17:55 +0200
Subject: mt76: fix swapped values for RXO-18 in gain control

The lowest bit should be set to 0 only for strong links, not for weak
ones.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 4ed6641c3a32..a510f116d52a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -531,7 +531,7 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560423);
 
 	if (low_gain == 2) {
-		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
+		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
 		mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808);
 		mt76_wr(dev, MT_BBP(AGC, 37), 0x08080808);
 		if (mt76x2_has_ext_lna(dev))
@@ -539,7 +539,7 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 		else
 			gain_delta = 14;
 	} else {
-		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
+		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
 		if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
 			mt76_wr(dev, MT_BBP(AGC, 35), 0x10101014);
 		else
-- 
cgit v1.2.3


From 929211687197adcb252129aed43ff81d9bb90110 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:17:56 +0200
Subject: mt76: adjust AGC control register 26 based on gain for VHT80

Use values based on the vendor driver

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index a510f116d52a..a2c3f0e35f86 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -525,10 +525,17 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 
 	dev->cal.low_gain = low_gain;
 
-	if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
+	if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80) {
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560211);
-	else
+		val = mt76_rr(dev, MT_BBP(AGC, 26)) & ~0xf;
+		if (low_gain == 2)
+			val |= 0x3;
+		else
+			val |= 0x5;
+		mt76_wr(dev, MT_BBP(AGC, 26), val);
+	} else {
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560423);
+	}
 
 	if (low_gain == 2) {
 		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
-- 
cgit v1.2.3


From fa967b5860318d1e77bf01b5102ce5ea4e56efef Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:17:57 +0200
Subject: mt76: clear false CCA counters after changing gain settings

They will be read on the next calibration step without gain change and
must not count earlier events

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index a2c3f0e35f86..51fd7ddfa8f5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -559,6 +559,9 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 	dev->cal.agc_gain_cur[1] = gain[1] - gain_delta;
 	dev->cal.agc_gain_adjust = 0;
 	mt76x2_phy_set_gain_val(dev);
+
+	/* clear false CCA counters */
+	mt76_rr(dev, MT_RX_STAT_1);
 }
 
 int mt76x2_phy_set_channel(struct mt76x2_dev *dev,
-- 
cgit v1.2.3


From 8e31f0d35a881537cf9b4ebabf63791dde3bbb0a Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:17:58 +0200
Subject: mt76: fix variable gain adjustment range

The range should only be limited to 4 for really weak signals, for all
other gain settings the range is 16.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 51fd7ddfa8f5..9c7b19ce73f2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -485,7 +485,7 @@ static void
 mt76x2_phy_adjust_vga_gain(struct mt76x2_dev *dev)
 {
 	u32 false_cca;
-	u8 limit = dev->cal.low_gain > 1 ? 4 : 16;
+	u8 limit = dev->cal.low_gain > 0 ? 16 : 4;
 
 	false_cca = FIELD_GET(MT_RX_STAT_1_CCA_ERRORS, mt76_rr(dev, MT_RX_STAT_1));
 	if (false_cca > 800 && dev->cal.agc_gain_adjust < limit)
-- 
cgit v1.2.3


From 108ec4dafd6166bcf5804aaa0486c9f02649e809 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:17:59 +0200
Subject: mt76: add a debugfs file to dump agc calibration information

Useful for debugging gain adjustment issues triggered by signal strength
changes.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2.h         |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c | 14 ++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c     |  1 +
 3 files changed, 16 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 06ca5a77dfdf..21de1168076d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -72,6 +72,7 @@ struct mt76x2_calibration {
 	int avg_rssi[MT_MAX_CHAINS];
 	int avg_rssi_all;
 
+	u16 false_cca;
 	s8 agc_gain_adjust;
 	s8 low_gain;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
index 955ea3e692dd..3f86e01049f3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
@@ -115,6 +115,18 @@ static const struct file_operations fops_dfs_stat = {
 	.release = single_release,
 };
 
+static int read_agc(struct seq_file *file, void *data)
+{
+	struct mt76x2_dev *dev = dev_get_drvdata(file->private);
+
+	seq_printf(file, "avg_rssi: %d\n", dev->cal.avg_rssi_all);
+	seq_printf(file, "low_gain: %d\n", dev->cal.low_gain);
+	seq_printf(file, "false_cca: %d\n", dev->cal.false_cca);
+	seq_printf(file, "agc_gain_adjust: %d\n", dev->cal.agc_gain_adjust);
+
+	return 0;
+}
+
 void mt76x2_init_debugfs(struct mt76x2_dev *dev)
 {
 	struct dentry *dir;
@@ -130,4 +142,6 @@ void mt76x2_init_debugfs(struct mt76x2_dev *dev)
 	debugfs_create_file("dfs_stats", 0400, dir, dev, &fops_dfs_stat);
 	debugfs_create_devm_seqfile(dev->mt76.dev, "txpower", dir,
 				    read_txpower);
+
+	debugfs_create_devm_seqfile(dev->mt76.dev, "agc", dir, read_agc);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 9c7b19ce73f2..94943aeb249d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -488,6 +488,7 @@ mt76x2_phy_adjust_vga_gain(struct mt76x2_dev *dev)
 	u8 limit = dev->cal.low_gain > 0 ? 16 : 4;
 
 	false_cca = FIELD_GET(MT_RX_STAT_1_CCA_ERRORS, mt76_rr(dev, MT_RX_STAT_1));
+	dev->cal.false_cca = false_cca;
 	if (false_cca > 800 && dev->cal.agc_gain_adjust < limit)
 		dev->cal.agc_gain_adjust += 2;
 	else if (false_cca < 10 && dev->cal.agc_gain_adjust > 0)
-- 
cgit v1.2.3


From 32e49efe0f15706021fda62e341fa6308e8d7c1e Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:18:00 +0200
Subject: mt76: track ewma rssi for gain adjustment per station

This preserves more sensitivity when weak stations are active and avoids
counting signal measurements from other unrelated networks

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2.h      | 10 ++--
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.c  | 33 ++++++++++----
 drivers/net/wireless/mediatek/mt76/mt76x2_main.c |  2 +
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c  | 58 ++++++++++++++++++++----
 4 files changed, 83 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 21de1168076d..71fcfa44fb2e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -27,6 +27,7 @@
 #include <linux/mutex.h>
 #include <linux/bitops.h>
 #include <linux/kfifo.h>
+#include <linux/average.h>
 
 #define MT7662_FIRMWARE		"mt7662.bin"
 #define MT7662_ROM_PATCH	"mt7662_rom_patch.bin"
@@ -47,6 +48,8 @@
 #include "mt76x2_mac.h"
 #include "mt76x2_dfs.h"
 
+DECLARE_EWMA(signal, 10, 8)
+
 struct mt76x2_mcu {
 	struct mutex mutex;
 
@@ -69,10 +72,8 @@ struct mt76x2_calibration {
 	u8 agc_gain_init[MT_MAX_CHAINS];
 	u8 agc_gain_cur[MT_MAX_CHAINS];
 
-	int avg_rssi[MT_MAX_CHAINS];
-	int avg_rssi_all;
-
 	u16 false_cca;
+	s8 avg_rssi_all;
 	s8 agc_gain_adjust;
 	s8 low_gain;
 
@@ -153,6 +154,9 @@ struct mt76x2_sta {
 	struct mt76x2_vif *vif;
 	struct mt76x2_tx_status status;
 	int n_frames;
+
+	struct ewma_signal rssi;
+	int inactive_count;
 };
 
 static inline bool is_mt7612(struct mt76x2_dev *dev)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
index 8985446570bd..fc9af79b3e69 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
@@ -269,21 +269,31 @@ static void mt76x2_remove_hdr_pad(struct sk_buff *skb, int len)
 	skb_pull(skb, len);
 }
 
-static struct mt76_wcid *
-mt76x2_rx_get_sta_wcid(struct mt76x2_dev *dev, u8 idx, bool unicast)
+static struct mt76x2_sta *
+mt76x2_rx_get_sta(struct mt76x2_dev *dev, u8 idx)
 {
-	struct mt76x2_sta *sta;
 	struct mt76_wcid *wcid;
 
 	if (idx >= ARRAY_SIZE(dev->wcid))
 		return NULL;
 
 	wcid = rcu_dereference(dev->wcid[idx]);
-	if (unicast || !wcid)
-		return wcid;
+	if (!wcid)
+		return NULL;
 
-	sta = container_of(wcid, struct mt76x2_sta, wcid);
-	return &sta->vif->group_wcid;
+	return container_of(wcid, struct mt76x2_sta, wcid);
+}
+
+static struct mt76_wcid *
+mt76x2_rx_get_sta_wcid(struct mt76x2_dev *dev, struct mt76x2_sta *sta, bool unicast)
+{
+	if (!sta)
+		return NULL;
+
+	if (unicast)
+		return &sta->wcid;
+	else
+		return &sta->vif->group_wcid;
 }
 
 int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
@@ -291,6 +301,7 @@ int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
 {
 	struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
 	struct mt76x2_rxwi *rxwi = rxi;
+	struct mt76x2_sta *sta;
 	u32 rxinfo = le32_to_cpu(rxwi->rxinfo);
 	u32 ctl = le32_to_cpu(rxwi->ctl);
 	u16 rate = le16_to_cpu(rxwi->rate);
@@ -315,7 +326,8 @@ int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
 	}
 
 	wcid = FIELD_GET(MT_RXWI_CTL_WCID, ctl);
-	status->wcid = mt76x2_rx_get_sta_wcid(dev, wcid, unicast);
+	sta = mt76x2_rx_get_sta(dev, wcid);
+	status->wcid = mt76x2_rx_get_sta_wcid(dev, sta, unicast);
 
 	len = FIELD_GET(MT_RXWI_CTL_MPDU_LEN, ctl);
 	pn_len = FIELD_GET(MT_RXINFO_PN_LEN, rxinfo);
@@ -361,6 +373,11 @@ int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
 	status->tid = FIELD_GET(MT_RXWI_TID, tid_sn);
 	status->seqno = FIELD_GET(MT_RXWI_SN, tid_sn);
 
+	if (sta) {
+		ewma_signal_add(&sta->rssi, status->signal);
+		sta->inactive_count = 0;
+	}
+
 	return mt76x2_mac_process_rate(status, rate);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
index e4e41faf6739..3c0ebe6d231c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
@@ -294,6 +294,8 @@ mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (vif->type == NL80211_IFTYPE_AP)
 		set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
 
+	ewma_signal_init(&msta->rssi);
+
 	rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
 
 out:
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 94943aeb249d..14aedc3ef731 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -499,22 +499,62 @@ mt76x2_phy_adjust_vga_gain(struct mt76x2_dev *dev)
 	mt76x2_phy_set_gain_val(dev);
 }
 
+static int
+mt76x2_phy_get_min_avg_rssi(struct mt76x2_dev *dev)
+{
+	struct mt76x2_sta *sta;
+	struct mt76_wcid *wcid;
+	int i, j, min_rssi = 0;
+	s8 cur_rssi;
+
+	local_bh_disable();
+	rcu_read_lock();
+
+	for (i = 0; i < ARRAY_SIZE(dev->wcid_mask); i++) {
+		unsigned long mask = dev->wcid_mask[i];
+
+		if (!mask)
+			continue;
+
+		for (j = i * BITS_PER_LONG; mask; j++, mask >>= 1) {
+			if (!(mask & 1))
+				continue;
+
+			wcid = rcu_dereference(dev->wcid[j]);
+			if (!wcid)
+				continue;
+
+			sta = container_of(wcid, struct mt76x2_sta, wcid);
+			spin_lock(&dev->mt76.rx_lock);
+			if (sta->inactive_count++ < 5)
+				cur_rssi = ewma_signal_read(&sta->rssi);
+			else
+				cur_rssi = 0;
+			spin_unlock(&dev->mt76.rx_lock);
+
+			if (cur_rssi < min_rssi)
+				min_rssi = cur_rssi;
+		}
+	}
+
+	rcu_read_unlock();
+	local_bh_enable();
+
+	if (!min_rssi)
+		return -75;
+
+	return min_rssi;
+}
+
 static void
 mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 {
-	u32 val = mt76_rr(dev, MT_BBP(AGC, 20));
-	int rssi0 = (s8) FIELD_GET(MT_BBP_AGC20_RSSI0, val);
-	int rssi1 = (s8) FIELD_GET(MT_BBP_AGC20_RSSI1, val);
 	u8 *gain = dev->cal.agc_gain_init;
 	u8 gain_delta;
 	int low_gain;
+	u32 val;
 
-	dev->cal.avg_rssi[0] = (dev->cal.avg_rssi[0] * 15) / 16 +
-			       (rssi0 << 8) / 16;
-	dev->cal.avg_rssi[1] = (dev->cal.avg_rssi[1] * 15) / 16 +
-			       (rssi1 << 8) / 16;
-	dev->cal.avg_rssi_all = (dev->cal.avg_rssi[0] +
-				 dev->cal.avg_rssi[1]) / 512;
+	dev->cal.avg_rssi_all = mt76x2_phy_get_min_avg_rssi(dev);
 
 	low_gain = (dev->cal.avg_rssi_all > mt76x2_get_rssi_gain_thresh(dev)) +
 		   (dev->cal.avg_rssi_all > mt76x2_get_low_rssi_gain_thresh(dev));
-- 
cgit v1.2.3


From c3ae2103e06953b1521a96c3e6934136b835e027 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Thu, 21 Jun 2018 11:18:01 +0200
Subject: mt76: improve gain adjustment in noisy environments

When switching between low gain (high RSSI) and high gain settings, it
can take a few seconds to adjust to the current environment.
This can lead to short periods of time with extreme packet loss.

When switching from low_gain=1 to low_gain=2, start with the same gain
adjustment value instead of the lowest to avoid spikes of huge numbers
of false CCA events

Also avoid resetting adjustment values on switching between low_gain
values 0 and 1, since it affects only the upper limit of vga adjustment

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c | 26 +++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 14aedc3ef731..20ffa6a40d39 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -491,7 +491,8 @@ mt76x2_phy_adjust_vga_gain(struct mt76x2_dev *dev)
 	dev->cal.false_cca = false_cca;
 	if (false_cca > 800 && dev->cal.agc_gain_adjust < limit)
 		dev->cal.agc_gain_adjust += 2;
-	else if (false_cca < 10 && dev->cal.agc_gain_adjust > 0)
+	else if ((false_cca < 10 && dev->cal.agc_gain_adjust > 0) ||
+		 (dev->cal.agc_gain_adjust >= limit && false_cca < 500))
 		dev->cal.agc_gain_adjust -= 2;
 	else
 		return;
@@ -550,7 +551,8 @@ static void
 mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 {
 	u8 *gain = dev->cal.agc_gain_init;
-	u8 gain_delta;
+	u8 low_gain_delta, gain_delta;
+	bool gain_change;
 	int low_gain;
 	u32 val;
 
@@ -559,13 +561,14 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 	low_gain = (dev->cal.avg_rssi_all > mt76x2_get_rssi_gain_thresh(dev)) +
 		   (dev->cal.avg_rssi_all > mt76x2_get_low_rssi_gain_thresh(dev));
 
-	if (dev->cal.low_gain == low_gain) {
+	gain_change = (dev->cal.low_gain & 2) ^ (low_gain & 2);
+	dev->cal.low_gain = low_gain;
+
+	if (!gain_change) {
 		mt76x2_phy_adjust_vga_gain(dev);
 		return;
 	}
 
-	dev->cal.low_gain = low_gain;
-
 	if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80) {
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560211);
 		val = mt76_rr(dev, MT_BBP(AGC, 26)) & ~0xf;
@@ -578,14 +581,17 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 		mt76_wr(dev, MT_BBP(RXO, 14), 0x00560423);
 	}
 
+	if (mt76x2_has_ext_lna(dev))
+		low_gain_delta = 10;
+	else
+		low_gain_delta = 14;
+
 	if (low_gain == 2) {
 		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a990);
 		mt76_wr(dev, MT_BBP(AGC, 35), 0x08080808);
 		mt76_wr(dev, MT_BBP(AGC, 37), 0x08080808);
-		if (mt76x2_has_ext_lna(dev))
-			gain_delta = 10;
-		else
-			gain_delta = 14;
+		gain_delta = low_gain_delta;
+		dev->cal.agc_gain_adjust = 0;
 	} else {
 		mt76_wr(dev, MT_BBP(RXO, 18), 0xf000a991);
 		if (dev->mt76.chandef.width == NL80211_CHAN_WIDTH_80)
@@ -594,11 +600,11 @@ mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 			mt76_wr(dev, MT_BBP(AGC, 35), 0x11111116);
 		mt76_wr(dev, MT_BBP(AGC, 37), 0x2121262C);
 		gain_delta = 0;
+		dev->cal.agc_gain_adjust = low_gain_delta;
 	}
 
 	dev->cal.agc_gain_cur[0] = gain[0] - gain_delta;
 	dev->cal.agc_gain_cur[1] = gain[1] - gain_delta;
-	dev->cal.agc_gain_adjust = 0;
 	mt76x2_phy_set_gain_val(dev);
 
 	/* clear false CCA counters */
-- 
cgit v1.2.3


From 5a2fbbd832758157a85a7f5a83ea33e06cf92217 Mon Sep 17 00:00:00 2001
From: CK Hu <ck.hu@mediatek.com>
Date: Wed, 27 Jun 2018 21:04:05 +0800
Subject: drm/mediatek: Split line to not over 80 characters

Split the long line into two short line to make sure eache line
not over 80 characters.

Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_drv.c | 54 ++++++++++++++++++++++------------
 1 file changed, 36 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 3d279a299383..1f0657233a3e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -365,24 +365,42 @@ static const struct component_master_ops mtk_drm_ops = {
 };
 
 static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
-	{ .compatible = "mediatek,mt2701-disp-ovl",   .data = (void *)MTK_DISP_OVL },
-	{ .compatible = "mediatek,mt8173-disp-ovl",   .data = (void *)MTK_DISP_OVL },
-	{ .compatible = "mediatek,mt2701-disp-rdma",  .data = (void *)MTK_DISP_RDMA },
-	{ .compatible = "mediatek,mt8173-disp-rdma",  .data = (void *)MTK_DISP_RDMA },
-	{ .compatible = "mediatek,mt8173-disp-wdma",  .data = (void *)MTK_DISP_WDMA },
-	{ .compatible = "mediatek,mt2701-disp-color", .data = (void *)MTK_DISP_COLOR },
-	{ .compatible = "mediatek,mt8173-disp-color", .data = (void *)MTK_DISP_COLOR },
-	{ .compatible = "mediatek,mt8173-disp-aal",   .data = (void *)MTK_DISP_AAL},
-	{ .compatible = "mediatek,mt8173-disp-gamma", .data = (void *)MTK_DISP_GAMMA, },
-	{ .compatible = "mediatek,mt8173-disp-ufoe",  .data = (void *)MTK_DISP_UFOE },
-	{ .compatible = "mediatek,mt2701-dsi",	      .data = (void *)MTK_DSI },
-	{ .compatible = "mediatek,mt8173-dsi",        .data = (void *)MTK_DSI },
-	{ .compatible = "mediatek,mt8173-dpi",        .data = (void *)MTK_DPI },
-	{ .compatible = "mediatek,mt2701-disp-mutex", .data = (void *)MTK_DISP_MUTEX },
-	{ .compatible = "mediatek,mt8173-disp-mutex", .data = (void *)MTK_DISP_MUTEX },
-	{ .compatible = "mediatek,mt2701-disp-pwm",   .data = (void *)MTK_DISP_BLS },
-	{ .compatible = "mediatek,mt8173-disp-pwm",   .data = (void *)MTK_DISP_PWM },
-	{ .compatible = "mediatek,mt8173-disp-od",    .data = (void *)MTK_DISP_OD },
+	{ .compatible = "mediatek,mt2701-disp-ovl",
+	  .data = (void *)MTK_DISP_OVL },
+	{ .compatible = "mediatek,mt8173-disp-ovl",
+	  .data = (void *)MTK_DISP_OVL },
+	{ .compatible = "mediatek,mt2701-disp-rdma",
+	  .data = (void *)MTK_DISP_RDMA },
+	{ .compatible = "mediatek,mt8173-disp-rdma",
+	  .data = (void *)MTK_DISP_RDMA },
+	{ .compatible = "mediatek,mt8173-disp-wdma",
+	  .data = (void *)MTK_DISP_WDMA },
+	{ .compatible = "mediatek,mt2701-disp-color",
+	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8173-disp-color",
+	  .data = (void *)MTK_DISP_COLOR },
+	{ .compatible = "mediatek,mt8173-disp-aal",
+	  .data = (void *)MTK_DISP_AAL},
+	{ .compatible = "mediatek,mt8173-disp-gamma",
+	  .data = (void *)MTK_DISP_GAMMA, },
+	{ .compatible = "mediatek,mt8173-disp-ufoe",
+	  .data = (void *)MTK_DISP_UFOE },
+	{ .compatible = "mediatek,mt2701-dsi",
+	  .data = (void *)MTK_DSI },
+	{ .compatible = "mediatek,mt8173-dsi",
+	  .data = (void *)MTK_DSI },
+	{ .compatible = "mediatek,mt8173-dpi",
+	  .data = (void *)MTK_DPI },
+	{ .compatible = "mediatek,mt2701-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt8173-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt2701-disp-pwm",
+	  .data = (void *)MTK_DISP_BLS },
+	{ .compatible = "mediatek,mt8173-disp-pwm",
+	  .data = (void *)MTK_DISP_PWM },
+	{ .compatible = "mediatek,mt8173-disp-od",
+	  .data = (void *)MTK_DISP_OD },
 	{ }
 };
 
-- 
cgit v1.2.3


From e6ab087a224fd7bcf712db698fbade673cc9addd Mon Sep 17 00:00:00 2001
From: "stu.hsieh@mediatek.com" <stu.hsieh@mediatek.com>
Date: Wed, 20 Jun 2018 16:19:31 +0800
Subject: drm/mediatek: Add support for mediatek SOC MT2712

This patch add support for the Mediatek MT2712 DISP subsystem.
There are two OVL engine and three disp output in MT2712.

Signed-off-by: Stu Hsieh <stu.hsieh@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_ddp.c | 39 ++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/mediatek/mtk_drm_drv.c | 39 ++++++++++++++++++++++++++++++++++
 2 files changed, 78 insertions(+)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
index 15e436d4e8a0..87e4191c250e 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_ddp.c
@@ -65,6 +65,24 @@
 #define MT8173_MUTEX_MOD_DISP_PWM1		24
 #define MT8173_MUTEX_MOD_DISP_OD		25
 
+#define MT2712_MUTEX_MOD_DISP_PWM2		10
+#define MT2712_MUTEX_MOD_DISP_OVL0		11
+#define MT2712_MUTEX_MOD_DISP_OVL1		12
+#define MT2712_MUTEX_MOD_DISP_RDMA0		13
+#define MT2712_MUTEX_MOD_DISP_RDMA1		14
+#define MT2712_MUTEX_MOD_DISP_RDMA2		15
+#define MT2712_MUTEX_MOD_DISP_WDMA0		16
+#define MT2712_MUTEX_MOD_DISP_WDMA1		17
+#define MT2712_MUTEX_MOD_DISP_COLOR0		18
+#define MT2712_MUTEX_MOD_DISP_COLOR1		19
+#define MT2712_MUTEX_MOD_DISP_AAL0		20
+#define MT2712_MUTEX_MOD_DISP_UFOE		22
+#define MT2712_MUTEX_MOD_DISP_PWM0		23
+#define MT2712_MUTEX_MOD_DISP_PWM1		24
+#define MT2712_MUTEX_MOD_DISP_OD0		25
+#define MT2712_MUTEX_MOD2_DISP_AAL1		33
+#define MT2712_MUTEX_MOD2_DISP_OD1		34
+
 #define MT2701_MUTEX_MOD_DISP_OVL		3
 #define MT2701_MUTEX_MOD_DISP_WDMA		6
 #define MT2701_MUTEX_MOD_DISP_COLOR		7
@@ -138,6 +156,26 @@ static const unsigned int mt2701_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_WDMA0] = MT2701_MUTEX_MOD_DISP_WDMA,
 };
 
+static const unsigned int mt2712_mutex_mod[DDP_COMPONENT_ID_MAX] = {
+	[DDP_COMPONENT_AAL0] = MT2712_MUTEX_MOD_DISP_AAL0,
+	[DDP_COMPONENT_AAL1] = MT2712_MUTEX_MOD2_DISP_AAL1,
+	[DDP_COMPONENT_COLOR0] = MT2712_MUTEX_MOD_DISP_COLOR0,
+	[DDP_COMPONENT_COLOR1] = MT2712_MUTEX_MOD_DISP_COLOR1,
+	[DDP_COMPONENT_OD0] = MT2712_MUTEX_MOD_DISP_OD0,
+	[DDP_COMPONENT_OD1] = MT2712_MUTEX_MOD2_DISP_OD1,
+	[DDP_COMPONENT_OVL0] = MT2712_MUTEX_MOD_DISP_OVL0,
+	[DDP_COMPONENT_OVL1] = MT2712_MUTEX_MOD_DISP_OVL1,
+	[DDP_COMPONENT_PWM0] = MT2712_MUTEX_MOD_DISP_PWM0,
+	[DDP_COMPONENT_PWM1] = MT2712_MUTEX_MOD_DISP_PWM1,
+	[DDP_COMPONENT_PWM2] = MT2712_MUTEX_MOD_DISP_PWM2,
+	[DDP_COMPONENT_RDMA0] = MT2712_MUTEX_MOD_DISP_RDMA0,
+	[DDP_COMPONENT_RDMA1] = MT2712_MUTEX_MOD_DISP_RDMA1,
+	[DDP_COMPONENT_RDMA2] = MT2712_MUTEX_MOD_DISP_RDMA2,
+	[DDP_COMPONENT_UFOE] = MT2712_MUTEX_MOD_DISP_UFOE,
+	[DDP_COMPONENT_WDMA0] = MT2712_MUTEX_MOD_DISP_WDMA0,
+	[DDP_COMPONENT_WDMA1] = MT2712_MUTEX_MOD_DISP_WDMA1,
+};
+
 static const unsigned int mt8173_mutex_mod[DDP_COMPONENT_ID_MAX] = {
 	[DDP_COMPONENT_AAL0] = MT8173_MUTEX_MOD_DISP_AAL,
 	[DDP_COMPONENT_COLOR0] = MT8173_MUTEX_MOD_DISP_COLOR0,
@@ -533,6 +571,7 @@ static int mtk_ddp_remove(struct platform_device *pdev)
 
 static const struct of_device_id ddp_driver_dt_match[] = {
 	{ .compatible = "mediatek,mt2701-disp-mutex", .data = mt2701_mutex_mod},
+	{ .compatible = "mediatek,mt2712-disp-mutex", .data = mt2712_mutex_mod},
 	{ .compatible = "mediatek,mt8173-disp-mutex", .data = mt8173_mutex_mod},
 	{},
 };
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
index 1f0657233a3e..39721119713b 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
@@ -146,6 +146,32 @@ static const enum mtk_ddp_comp_id mt2701_mtk_ddp_ext[] = {
 	DDP_COMPONENT_DPI0,
 };
 
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_main[] = {
+	DDP_COMPONENT_OVL0,
+	DDP_COMPONENT_COLOR0,
+	DDP_COMPONENT_AAL0,
+	DDP_COMPONENT_OD0,
+	DDP_COMPONENT_RDMA0,
+	DDP_COMPONENT_DPI0,
+	DDP_COMPONENT_PWM0,
+};
+
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_ext[] = {
+	DDP_COMPONENT_OVL1,
+	DDP_COMPONENT_COLOR1,
+	DDP_COMPONENT_AAL1,
+	DDP_COMPONENT_OD1,
+	DDP_COMPONENT_RDMA1,
+	DDP_COMPONENT_DPI1,
+	DDP_COMPONENT_PWM1,
+};
+
+static const enum mtk_ddp_comp_id mt2712_mtk_ddp_third[] = {
+	DDP_COMPONENT_RDMA2,
+	DDP_COMPONENT_DSI3,
+	DDP_COMPONENT_PWM2,
+};
+
 static const enum mtk_ddp_comp_id mt8173_mtk_ddp_main[] = {
 	DDP_COMPONENT_OVL0,
 	DDP_COMPONENT_COLOR0,
@@ -173,6 +199,15 @@ static const struct mtk_mmsys_driver_data mt2701_mmsys_driver_data = {
 	.shadow_register = true,
 };
 
+static const struct mtk_mmsys_driver_data mt2712_mmsys_driver_data = {
+	.main_path = mt2712_mtk_ddp_main,
+	.main_len = ARRAY_SIZE(mt2712_mtk_ddp_main),
+	.ext_path = mt2712_mtk_ddp_ext,
+	.ext_len = ARRAY_SIZE(mt2712_mtk_ddp_ext),
+	.third_path = mt2712_mtk_ddp_third,
+	.third_len = ARRAY_SIZE(mt2712_mtk_ddp_third),
+};
+
 static const struct mtk_mmsys_driver_data mt8173_mmsys_driver_data = {
 	.main_path = mt8173_mtk_ddp_main,
 	.main_len = ARRAY_SIZE(mt8173_mtk_ddp_main),
@@ -393,6 +428,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
 	  .data = (void *)MTK_DPI },
 	{ .compatible = "mediatek,mt2701-disp-mutex",
 	  .data = (void *)MTK_DISP_MUTEX },
+	{ .compatible = "mediatek,mt2712-disp-mutex",
+	  .data = (void *)MTK_DISP_MUTEX },
 	{ .compatible = "mediatek,mt8173-disp-mutex",
 	  .data = (void *)MTK_DISP_MUTEX },
 	{ .compatible = "mediatek,mt2701-disp-pwm",
@@ -575,6 +612,8 @@ static SIMPLE_DEV_PM_OPS(mtk_drm_pm_ops, mtk_drm_sys_suspend,
 static const struct of_device_id mtk_drm_of_ids[] = {
 	{ .compatible = "mediatek,mt2701-mmsys",
 	  .data = &mt2701_mmsys_driver_data},
+	{ .compatible = "mediatek,mt2712-mmsys",
+	  .data = &mt2712_mmsys_driver_data},
 	{ .compatible = "mediatek,mt8173-mmsys",
 	  .data = &mt8173_mmsys_driver_data},
 	{ }
-- 
cgit v1.2.3


From 06ede493a9d755185ba8a97225ce1352fa5c310c Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 14:47:03 +0100
Subject: drm/mtk: Remove impossible internal error

We cannot create a framebuffer with no objects, so there's no point
testing for it.

v2: Remove the error entirely. (Sean, CK, Thierry)

Signed-off-by: Daniel Stone <daniels@collabora.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: Thierry Reding <treding@nvidia.com>
Cc: CK Hu <ck.hu@mediatek.com>
Cc: Philipp Zabel <p.zabel@pengutronix.de>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
---
 drivers/gpu/drm/mediatek/mtk_drm_plane.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 2f4b0ffee598..149fc4372917 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -95,11 +95,6 @@ static int mtk_plane_atomic_check(struct drm_plane *plane,
 	if (!fb)
 		return 0;
 
-	if (!mtk_fb_get_gem_obj(fb)) {
-		DRM_DEBUG_KMS("buffer is null\n");
-		return -EFAULT;
-	}
-
 	if (!state->crtc)
 		return 0;
 
-- 
cgit v1.2.3


From 548cb82538582f1b2badbc78df83c46899b6c694 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 14:47:04 +0100
Subject: drm/mtk: Move GEM BO to drm_framebuffer

Since drm_framebuffer can now store GEM objects directly, place them
there rather than in our own subclass. As this makes the framebuffer
create_handle and destroy functions the same as the GEM framebuffer
helper, we can reuse those.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Cc: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/mediatek/mtk_drm_fb.c    | 38 +++++---------------------------
 drivers/gpu/drm/mediatek/mtk_drm_fb.h    |  1 -
 drivers/gpu/drm/mediatek/mtk_drm_plane.c |  2 +-
 3 files changed, 6 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.c b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
index 0d8d506695f9..f130e37123b5 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
@@ -15,6 +15,7 @@
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_gem.h>
+#include <drm/drm_gem_framebuffer_helper.h>
 #include <linux/dma-buf.h>
 #include <linux/reservation.h>
 
@@ -30,42 +31,13 @@
  */
 struct mtk_drm_fb {
 	struct drm_framebuffer	base;
-	/* For now we only support a single plane */
-	struct drm_gem_object	*gem_obj;
 };
 
 #define to_mtk_fb(x) container_of(x, struct mtk_drm_fb, base)
 
-struct drm_gem_object *mtk_fb_get_gem_obj(struct drm_framebuffer *fb)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	return mtk_fb->gem_obj;
-}
-
-static int mtk_drm_fb_create_handle(struct drm_framebuffer *fb,
-				    struct drm_file *file_priv,
-				    unsigned int *handle)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	return drm_gem_handle_create(file_priv, mtk_fb->gem_obj, handle);
-}
-
-static void mtk_drm_fb_destroy(struct drm_framebuffer *fb)
-{
-	struct mtk_drm_fb *mtk_fb = to_mtk_fb(fb);
-
-	drm_framebuffer_cleanup(fb);
-
-	drm_gem_object_put_unlocked(mtk_fb->gem_obj);
-
-	kfree(mtk_fb);
-}
-
 static const struct drm_framebuffer_funcs mtk_drm_fb_funcs = {
-	.create_handle = mtk_drm_fb_create_handle,
-	.destroy = mtk_drm_fb_destroy,
+	.create_handle = drm_gem_fb_create_handle,
+	.destroy = drm_gem_fb_destroy,
 };
 
 static struct mtk_drm_fb *mtk_drm_framebuffer_init(struct drm_device *dev,
@@ -84,7 +56,7 @@ static struct mtk_drm_fb *mtk_drm_framebuffer_init(struct drm_device *dev,
 
 	drm_helper_mode_fill_fb_struct(dev, &mtk_fb->base, mode);
 
-	mtk_fb->gem_obj = obj;
+	mtk_fb->base.obj[0] = obj;
 
 	ret = drm_framebuffer_init(dev, &mtk_fb->base, &mtk_drm_fb_funcs);
 	if (ret) {
@@ -110,7 +82,7 @@ int mtk_fb_wait(struct drm_framebuffer *fb)
 	if (!fb)
 		return 0;
 
-	gem = mtk_fb_get_gem_obj(fb);
+	gem = fb->obj[0];
 	if (!gem || !gem->dma_buf || !gem->dma_buf->resv)
 		return 0;
 
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.h b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
index 9b2ae345a4e9..7f976b196a15 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.h
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.h
@@ -14,7 +14,6 @@
 #ifndef MTK_DRM_FB_H
 #define MTK_DRM_FB_H
 
-struct drm_gem_object *mtk_fb_get_gem_obj(struct drm_framebuffer *fb);
 int mtk_fb_wait(struct drm_framebuffer *fb);
 struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 					       struct drm_file *file,
diff --git a/drivers/gpu/drm/mediatek/mtk_drm_plane.c b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
index 149fc4372917..f7e6aa1b5b7d 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_plane.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_plane.c
@@ -122,7 +122,7 @@ static void mtk_plane_atomic_update(struct drm_plane *plane,
 	if (!crtc || WARN_ON(!fb))
 		return;
 
-	gem = mtk_fb_get_gem_obj(fb);
+	gem = fb->obj[0];
 	mtk_gem = to_mtk_gem_obj(gem);
 	addr = mtk_gem->dma_addr;
 	pitch = fb->pitches[0];
-- 
cgit v1.2.3


From 57c7f58111806faa0165b88155bff15679024122 Mon Sep 17 00:00:00 2001
From: Daniel Stone <daniels@collabora.com>
Date: Fri, 18 May 2018 14:47:05 +0100
Subject: drm/mtk: mtk_drm_fb -> drm_framebuffer

Now that mtk_drm_fb is an empty wrapper around drm_framebuffer, we can
just delete it.

Signed-off-by: Daniel Stone <daniels@collabora.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Cc: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/mediatek/mtk_drm_fb.c | 40 ++++++++++++-----------------------
 1 file changed, 14 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_fb.c b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
index f130e37123b5..be5f6f1daf55 100644
--- a/drivers/gpu/drm/mediatek/mtk_drm_fb.c
+++ b/drivers/gpu/drm/mediatek/mtk_drm_fb.c
@@ -23,49 +23,37 @@
 #include "mtk_drm_fb.h"
 #include "mtk_drm_gem.h"
 
-/*
- * mtk specific framebuffer structure.
- *
- * @fb: drm framebuffer object.
- * @gem_obj: array of gem objects.
- */
-struct mtk_drm_fb {
-	struct drm_framebuffer	base;
-};
-
-#define to_mtk_fb(x) container_of(x, struct mtk_drm_fb, base)
-
 static const struct drm_framebuffer_funcs mtk_drm_fb_funcs = {
 	.create_handle = drm_gem_fb_create_handle,
 	.destroy = drm_gem_fb_destroy,
 };
 
-static struct mtk_drm_fb *mtk_drm_framebuffer_init(struct drm_device *dev,
+static struct drm_framebuffer *mtk_drm_framebuffer_init(struct drm_device *dev,
 					const struct drm_mode_fb_cmd2 *mode,
 					struct drm_gem_object *obj)
 {
-	struct mtk_drm_fb *mtk_fb;
+	struct drm_framebuffer *fb;
 	int ret;
 
 	if (drm_format_num_planes(mode->pixel_format) != 1)
 		return ERR_PTR(-EINVAL);
 
-	mtk_fb = kzalloc(sizeof(*mtk_fb), GFP_KERNEL);
-	if (!mtk_fb)
+	fb = kzalloc(sizeof(*fb), GFP_KERNEL);
+	if (!fb)
 		return ERR_PTR(-ENOMEM);
 
-	drm_helper_mode_fill_fb_struct(dev, &mtk_fb->base, mode);
+	drm_helper_mode_fill_fb_struct(dev, fb, mode);
 
-	mtk_fb->base.obj[0] = obj;
+	fb->obj[0] = obj;
 
-	ret = drm_framebuffer_init(dev, &mtk_fb->base, &mtk_drm_fb_funcs);
+	ret = drm_framebuffer_init(dev, fb, &mtk_drm_fb_funcs);
 	if (ret) {
 		DRM_ERROR("failed to initialize framebuffer\n");
-		kfree(mtk_fb);
+		kfree(fb);
 		return ERR_PTR(ret);
 	}
 
-	return mtk_fb;
+	return fb;
 }
 
 /*
@@ -100,7 +88,7 @@ struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 					       struct drm_file *file,
 					       const struct drm_mode_fb_cmd2 *cmd)
 {
-	struct mtk_drm_fb *mtk_fb;
+	struct drm_framebuffer *fb;
 	struct drm_gem_object *gem;
 	unsigned int width = cmd->width;
 	unsigned int height = cmd->height;
@@ -123,13 +111,13 @@ struct drm_framebuffer *mtk_drm_mode_fb_create(struct drm_device *dev,
 		goto unreference;
 	}
 
-	mtk_fb = mtk_drm_framebuffer_init(dev, cmd, gem);
-	if (IS_ERR(mtk_fb)) {
-		ret = PTR_ERR(mtk_fb);
+	fb = mtk_drm_framebuffer_init(dev, cmd, gem);
+	if (IS_ERR(fb)) {
+		ret = PTR_ERR(fb);
 		goto unreference;
 	}
 
-	return &mtk_fb->base;
+	return fb;
 
 unreference:
 	drm_gem_object_put_unlocked(gem);
-- 
cgit v1.2.3


From 24a95f7578f517e78367d6fb61aba238497a046b Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:41 +0200
Subject: clk: sunxi-ng: r40: Add minimal rate for video PLLs

According to documentation and experience with other similar SoCs, video
PLLs don't work stable if their output frequency is set below 192 MHz.

Because of that, set minimal rate to both R40 video PLLs to 192 MHz.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
---
 drivers/clk/sunxi-ng/ccu-sun8i-r40.c | 46 +++++++++++++++++++-----------------
 1 file changed, 24 insertions(+), 22 deletions(-)

diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
index 65ba6455feb7..d52af1785644 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
@@ -66,17 +66,18 @@ static SUNXI_CCU_NM_WITH_GATE_LOCK(pll_audio_base_clk, "pll-audio-base",
 				   CLK_SET_RATE_UNGATE);
 
 /* TODO: The result of N/M is required to be in [8, 25] range. */
-static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_video0_clk, "pll-video0",
-					"osc24M", 0x0010,
-					8, 7,		/* N */
-					0, 4,		/* M */
-					BIT(24),	/* frac enable */
-					BIT(25),	/* frac select */
-					270000000,	/* frac rate 0 */
-					297000000,	/* frac rate 1 */
-					BIT(31),	/* gate */
-					BIT(28),	/* lock */
-					CLK_SET_RATE_UNGATE);
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK_MIN(pll_video0_clk, "pll-video0",
+					    "osc24M", 0x0010,
+					    192000000,	/* Minimum rate */
+					    8, 7,	/* N */
+					    0, 4,	/* M */
+					    BIT(24),	/* frac enable */
+					    BIT(25),	/* frac select */
+					    270000000,	/* frac rate 0 */
+					    297000000,	/* frac rate 1 */
+					    BIT(31),	/* gate */
+					    BIT(28),	/* lock */
+					    CLK_SET_RATE_UNGATE);
 
 /* TODO: The result of N/M is required to be in [8, 25] range. */
 static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_ve_clk, "pll-ve",
@@ -152,17 +153,18 @@ static struct ccu_nk pll_periph1_clk = {
 };
 
 /* TODO: The result of N/M is required to be in [8, 25] range. */
-static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK(pll_video1_clk, "pll-video1",
-					"osc24M", 0x030,
-					8, 7,		/* N */
-					0, 4,		/* M */
-					BIT(24),	/* frac enable */
-					BIT(25),	/* frac select */
-					270000000,	/* frac rate 0 */
-					297000000,	/* frac rate 1 */
-					BIT(31),	/* gate */
-					BIT(28),	/* lock */
-					CLK_SET_RATE_UNGATE);
+static SUNXI_CCU_NM_WITH_FRAC_GATE_LOCK_MIN(pll_video1_clk, "pll-video1",
+					    "osc24M", 0x030,
+					    192000000,	/* Minimum rate */
+					    8, 7,	/* N */
+					    0, 4,	/* M */
+					    BIT(24),	/* frac enable */
+					    BIT(25),	/* frac select */
+					    270000000,	/* frac rate 0 */
+					    297000000,	/* frac rate 1 */
+					    BIT(31),	/* gate */
+					    BIT(28),	/* lock */
+					    CLK_SET_RATE_UNGATE);
 
 static struct ccu_nkm pll_sata_clk = {
 	.enable		= BIT(31),
-- 
cgit v1.2.3


From fb4aa0f64380d94bf10b5da63a6760962d824dbc Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:42 +0200
Subject: clk: sunxi-ng: r40: Allow setting parent rate to display related
 clocks

Display related peripherals need precise clocks to operate correctly.

Allow DE2, TCONs and HDMI to set parent clock.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
---
 drivers/clk/sunxi-ng/ccu-sun8i-r40.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
index d52af1785644..0f388f6944d5 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.c
@@ -656,7 +656,8 @@ static SUNXI_CCU_GATE(dram_deinterlace_clk,	"dram-deinterlace",	"dram",
 
 static const char * const de_parents[] = { "pll-periph0-2x", "pll-de" };
 static SUNXI_CCU_M_WITH_MUX_GATE(de_clk, "de", de_parents,
-				 0x104, 0, 4, 24, 3, BIT(31), 0);
+				 0x104, 0, 4, 24, 3, BIT(31),
+				 CLK_SET_RATE_PARENT);
 static SUNXI_CCU_M_WITH_MUX_GATE(mp_clk, "mp", de_parents,
 				 0x108, 0, 4, 24, 3, BIT(31), 0);
 
@@ -668,9 +669,11 @@ static SUNXI_CCU_MUX_WITH_GATE(tcon_lcd0_clk, "tcon-lcd0", tcon_parents,
 static SUNXI_CCU_MUX_WITH_GATE(tcon_lcd1_clk, "tcon-lcd1", tcon_parents,
 			       0x114, 24, 3, BIT(31), CLK_SET_RATE_PARENT);
 static SUNXI_CCU_M_WITH_MUX_GATE(tcon_tv0_clk, "tcon-tv0", tcon_parents,
-				 0x118, 0, 4, 24, 3, BIT(31), 0);
+				 0x118, 0, 4, 24, 3, BIT(31),
+				 CLK_SET_RATE_PARENT);
 static SUNXI_CCU_M_WITH_MUX_GATE(tcon_tv1_clk, "tcon-tv1", tcon_parents,
-				 0x11c, 0, 4, 24, 3, BIT(31), 0);
+				 0x11c, 0, 4, 24, 3, BIT(31),
+				 CLK_SET_RATE_PARENT);
 
 static const char * const deinterlace_parents[] = { "pll-periph0",
 						    "pll-periph1" };
@@ -700,7 +703,8 @@ static SUNXI_CCU_GATE(avs_clk,		"avs",		"osc24M",
 
 static const char * const hdmi_parents[] = { "pll-video0", "pll-video1" };
 static SUNXI_CCU_M_WITH_MUX_GATE(hdmi_clk, "hdmi", hdmi_parents,
-				 0x150, 0, 4, 24, 2, BIT(31), 0);
+				 0x150, 0, 4, 24, 2, BIT(31),
+				 CLK_SET_RATE_PARENT);
 
 static SUNXI_CCU_GATE(hdmi_slow_clk,	"hdmi-slow",	"osc24M",
 		      0x154, BIT(31), 0);
-- 
cgit v1.2.3


From d18e85349f6a65baa69b8ee397efb93e4ca31909 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:43 +0200
Subject: clk: sunxi-ng: r40: Export video PLLs

Video PLLs need to be referenced in R40 DT as possible HDMI PHY parent.

Export them.

Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
---
 drivers/clk/sunxi-ng/ccu-sun8i-r40.h      | 8 ++++++--
 include/dt-bindings/clock/sun8i-r40-ccu.h | 4 ++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
index 0db8e1e97af8..db2a1243f9ff 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-r40.h
@@ -25,7 +25,9 @@
 #define CLK_PLL_AUDIO_2X	4
 #define CLK_PLL_AUDIO_4X	5
 #define CLK_PLL_AUDIO_8X	6
-#define CLK_PLL_VIDEO0		7
+
+/* PLL_VIDEO0 is exported */
+
 #define CLK_PLL_VIDEO0_2X	8
 #define CLK_PLL_VE		9
 #define CLK_PLL_DDR0		10
@@ -34,7 +36,9 @@
 #define CLK_PLL_PERIPH0_2X	13
 #define CLK_PLL_PERIPH1		14
 #define CLK_PLL_PERIPH1_2X	15
-#define CLK_PLL_VIDEO1		16
+
+/* PLL_VIDEO1 is exported */
+
 #define CLK_PLL_VIDEO1_2X	17
 #define CLK_PLL_SATA		18
 #define CLK_PLL_SATA_OUT	19
diff --git a/include/dt-bindings/clock/sun8i-r40-ccu.h b/include/dt-bindings/clock/sun8i-r40-ccu.h
index 4fa5f69fc297..f9e15a235626 100644
--- a/include/dt-bindings/clock/sun8i-r40-ccu.h
+++ b/include/dt-bindings/clock/sun8i-r40-ccu.h
@@ -43,6 +43,10 @@
 #ifndef _DT_BINDINGS_CLK_SUN8I_R40_H_
 #define _DT_BINDINGS_CLK_SUN8I_R40_H_
 
+#define CLK_PLL_VIDEO0		7
+
+#define CLK_PLL_VIDEO1		16
+
 #define CLK_CPU			24
 
 #define CLK_BUS_MIPI_DSI	29
-- 
cgit v1.2.3


From 248d4e59616c632f37f04c233eec6d5008384926 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 6 Apr 2018 16:55:35 +0200
Subject: PCI: aardvark: Introduce an advk_pcie_valid_device() helper

In other to mimic other PCIe host controller drivers, introduce an
advk_pcie_valid_device() helper, used in the configuration read/write
functions.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
[lorenzo.pieralisi@arm.com: updated host->controller dir move]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-aardvark.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index d3172d5d3d35..7b363437d851 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -433,6 +433,15 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie)
 	return -ETIMEDOUT;
 }
 
+static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
+				  int devfn)
+{
+	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+		return false;
+
+	return true;
+}
+
 static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 			     int where, int size, u32 *val)
 {
@@ -440,7 +449,7 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	u32 reg;
 	int ret;
 
-	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0) {
+	if (!advk_pcie_valid_device(pcie, bus, devfn)) {
 		*val = 0xffffffff;
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	}
@@ -494,7 +503,7 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	int offset;
 	int ret;
 
-	if ((bus->number == pcie->root_bus_nr) && PCI_SLOT(devfn) != 0)
+	if (!advk_pcie_valid_device(pcie, bus, devfn))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	if (where % size)
-- 
cgit v1.2.3


From 6df6ba974a55678a2c7d9a0c06eb15cde0c4b184 Mon Sep 17 00:00:00 2001
From: Evan Wang <xswang@marvell.com>
Date: Fri, 6 Apr 2018 16:55:36 +0200
Subject: PCI: aardvark: Remove PCIe outbound window configuration

Outbound window is used to translate CPU space addresses to PCIe space
addresses when the CPU initiates PCIe transactions.

According to the suggestion of the HW designers, the recommended
solution is to use the default outbound parameters, even though the
current outbound window setting does not cause any known functional
issue.

This patch doesn't address any known functional issue, but aligns to
HW design guidelines, and removes code that isn't needed.

Signed-off-by: Evan Wang <xswang@marvell.com>
[Thomas: tweak commit log.]
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
[lorenzo.pieralisi@arm.com: handled host->controller dir move]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Victor Gu <xigu@marvell.com>
Reviewed-by: Nadav Haklai <nadavh@marvell.com>
---
 drivers/pci/controller/pci-aardvark.c | 55 -----------------------------------
 1 file changed, 55 deletions(-)

diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 7b363437d851..c9c72595bd20 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -111,24 +111,6 @@
 #define PCIE_MSI_MASK_REG			(CONTROL_BASE_ADDR + 0x5C)
 #define PCIE_MSI_PAYLOAD_REG			(CONTROL_BASE_ADDR + 0x9C)
 
-/* PCIe window configuration */
-#define OB_WIN_BASE_ADDR			0x4c00
-#define OB_WIN_BLOCK_SIZE			0x20
-#define OB_WIN_REG_ADDR(win, offset)		(OB_WIN_BASE_ADDR + \
-						 OB_WIN_BLOCK_SIZE * (win) + \
-						 (offset))
-#define OB_WIN_MATCH_LS(win)			OB_WIN_REG_ADDR(win, 0x00)
-#define OB_WIN_MATCH_MS(win)			OB_WIN_REG_ADDR(win, 0x04)
-#define OB_WIN_REMAP_LS(win)			OB_WIN_REG_ADDR(win, 0x08)
-#define OB_WIN_REMAP_MS(win)			OB_WIN_REG_ADDR(win, 0x0c)
-#define OB_WIN_MASK_LS(win)			OB_WIN_REG_ADDR(win, 0x10)
-#define OB_WIN_MASK_MS(win)			OB_WIN_REG_ADDR(win, 0x14)
-#define OB_WIN_ACTIONS(win)			OB_WIN_REG_ADDR(win, 0x18)
-
-/* PCIe window types */
-#define OB_PCIE_MEM				0x0
-#define OB_PCIE_IO				0x4
-
 /* LMI registers base address and register offsets */
 #define LMI_BASE_ADDR				0x6000
 #define CFG_REG					(LMI_BASE_ADDR + 0x0)
@@ -247,34 +229,9 @@ static int advk_pcie_wait_for_link(struct advk_pcie *pcie)
 	return -ETIMEDOUT;
 }
 
-/*
- * Set PCIe address window register which could be used for memory
- * mapping.
- */
-static void advk_pcie_set_ob_win(struct advk_pcie *pcie,
-				 u32 win_num, u32 match_ms,
-				 u32 match_ls, u32 mask_ms,
-				 u32 mask_ls, u32 remap_ms,
-				 u32 remap_ls, u32 action)
-{
-	advk_writel(pcie, match_ls, OB_WIN_MATCH_LS(win_num));
-	advk_writel(pcie, match_ms, OB_WIN_MATCH_MS(win_num));
-	advk_writel(pcie, mask_ms, OB_WIN_MASK_MS(win_num));
-	advk_writel(pcie, mask_ls, OB_WIN_MASK_LS(win_num));
-	advk_writel(pcie, remap_ms, OB_WIN_REMAP_MS(win_num));
-	advk_writel(pcie, remap_ls, OB_WIN_REMAP_LS(win_num));
-	advk_writel(pcie, action, OB_WIN_ACTIONS(win_num));
-	advk_writel(pcie, match_ls | BIT(0), OB_WIN_MATCH_LS(win_num));
-}
-
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
 	u32 reg;
-	int i;
-
-	/* Point PCIe unit MBUS decode windows to DRAM space */
-	for (i = 0; i < 8; i++)
-		advk_pcie_set_ob_win(pcie, i, 0, 0, 0, 0, 0, 0, 0);
 
 	/* Set to Direct mode */
 	reg = advk_readl(pcie, CTRL_CONFIG_REG);
@@ -852,12 +809,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
 
 		switch (resource_type(res)) {
 		case IORESOURCE_IO:
-			advk_pcie_set_ob_win(pcie, 1,
-					     upper_32_bits(res->start),
-					     lower_32_bits(res->start),
-					     0,	0xF8000000, 0,
-					     lower_32_bits(res->start),
-					     OB_PCIE_IO);
 			err = pci_remap_iospace(res, iobase);
 			if (err) {
 				dev_warn(dev, "error %d: failed to map resource %pR\n",
@@ -866,12 +817,6 @@ static int advk_pcie_parse_request_of_pci_ranges(struct advk_pcie *pcie)
 			}
 			break;
 		case IORESOURCE_MEM:
-			advk_pcie_set_ob_win(pcie, 0,
-					     upper_32_bits(res->start),
-					     lower_32_bits(res->start),
-					     0x0, 0xF8000000, 0,
-					     lower_32_bits(res->start),
-					     (2 << 20) | OB_PCIE_MEM);
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
 			break;
 		case IORESOURCE_BUS:
-- 
cgit v1.2.3


From a61b47f672c1ebd56b273a55cfed9621448d253e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 27 Jun 2018 12:53:34 +0100
Subject: drm/i915: Wait for engines to idle before retiring

In the next^W forthcoming patch, we will start to defer retiring the
request from the engine list if it is still active on the submission
backend. To preserve the semantics that after wait-for-idle completes
the system is idle and fully retired, we need to therefore wait for the
backends to idle before calling i915_retire_requests().

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627115334.16282-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 858d188dd33b..5a9cae604e2b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3810,10 +3810,13 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 			if (err)
 				return err;
 		}
+
+		err = wait_for_engines(i915);
+		if (err)
+			return err;
+
 		i915_retire_requests(i915);
 		GEM_BUG_ON(i915->gt.active_requests);
-
-		return wait_for_engines(i915);
 	} else {
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
@@ -3824,9 +3827,9 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 			if (err)
 				return err;
 		}
-
-		return 0;
 	}
+
+	return 0;
 }
 
 static void __i915_gem_object_flush_for_display(struct drm_i915_gem_object *obj)
-- 
cgit v1.2.3


From 10cfc747835e34c5ee09599c236128067b990723 Mon Sep 17 00:00:00 2001
From: David Lechner <david@lechnology.com>
Date: Fri, 25 May 2018 14:36:20 -0500
Subject: MAINTAINERS: fix path to ilitek, ili9225 device tree bindings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes the path to the ilitek,ili9225 device tree binding file.

Signed-off-by: David Lechner <david@lechnology.com>
Reviewed-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525193623.15533-2-david@lechnology.com
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index c7fe1c331bb1..e507c34798ff 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4476,7 +4476,7 @@ DRM DRIVER FOR ILITEK ILI9225 PANELS
 M:	David Lechner <david@lechnology.com>
 S:	Maintained
 F:	drivers/gpu/drm/tinydrm/ili9225.c
-F:	Documentation/devicetree/bindings/display/ili9225.txt
+F:	Documentation/devicetree/bindings/display/ilitek,ili9225.txt
 
 DRM DRIVER FOR INTEL I810 VIDEO CARDS
 S:	Orphan / Obsolete
-- 
cgit v1.2.3


From bb2a9b6eb1f6d1a6efee629198beafdcb188b851 Mon Sep 17 00:00:00 2001
From: David Lechner <david@lechnology.com>
Date: Fri, 25 May 2018 14:36:21 -0500
Subject: dt-bindings: Add vendor prefix for Adafruit

This adds a device tree vendor prefix for Adafruit Industries, LLC.

Signed-off-by: David Lechner <david@lechnology.com>
Acked-by: Rob Herring <robh@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525193623.15533-3-david@lechnology.com
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index a38d8bfae19c..ff7e024ef0f7 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -8,6 +8,7 @@ abracon	Abracon Corporation
 actions	Actions Semiconductor Co., Ltd.
 active-semi	Active-Semi International Inc
 ad	Avionic Design GmbH
+adafruit	Adafruit Industries, LLC
 adapteva	Adapteva, Inc.
 adaptrum	Adaptrum, Inc.
 adh	AD Holdings Plc.
-- 
cgit v1.2.3


From 7b59d2d8d7980522bb4b532dcecb39bac3639726 Mon Sep 17 00:00:00 2001
From: David Lechner <david@lechnology.com>
Date: Fri, 25 May 2018 14:36:22 -0500
Subject: dt-bindings: new binding for Ilitek ILI9341 display panels

This adds a new binding for Ilitek ILI9341 display panels. It includes
a compatible string for one display (more can be added in the future).

The YX240QV29-T panel[1] is found, for example, in an Adafruit breakout
board[2] and in Mindsensors' PiStorms[3].

The vendor prefix "adafruit" is used because the actual vendor is not
known, but Adafruit is the most common source for a product that
contains this panel.

[1]: https://cdn-learn.adafruit.com/assets/assets/000/046/879/original/SPEC-YX240QV29-T_Rev.A__1_.pdf
[2]: https://www.adafruit.com/product/2478
[3]: http://www.mindsensors.com/stem-with-robotics/13-pistorms-v2-base-kit-raspberry-pi-brain-for-lego-robot

Signed-off-by: David Lechner <david@lechnology.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525193623.15533-4-david@lechnology.com
---
 .../devicetree/bindings/display/ilitek,ili9341.txt | 27 ++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/ilitek,ili9341.txt

diff --git a/Documentation/devicetree/bindings/display/ilitek,ili9341.txt b/Documentation/devicetree/bindings/display/ilitek,ili9341.txt
new file mode 100644
index 000000000000..169b32e4ee4e
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/ilitek,ili9341.txt
@@ -0,0 +1,27 @@
+Ilitek ILI9341 display panels
+
+This binding is for display panels using an Ilitek ILI9341 controller in SPI
+mode.
+
+Required properties:
+- compatible:	"adafruit,yx240qv29", "ilitek,ili9341"
+- dc-gpios:	D/C pin
+- reset-gpios:	Reset pin
+
+The node for this driver must be a child node of a SPI controller, hence
+all mandatory properties described in ../spi/spi-bus.txt must be specified.
+
+Optional properties:
+- rotation:	panel rotation in degrees counter clockwise (0,90,180,270)
+- backlight:	phandle of the backlight device attached to the panel
+
+Example:
+	display@0{
+		compatible = "adafruit,yx240qv29", "ilitek,ili9341";
+		reg = <0>;
+		spi-max-frequency = <32000000>;
+		dc-gpios = <&gpio0 9 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio0 8 GPIO_ACTIVE_HIGH>;
+		rotation = <270>;
+		backlight = <&backlight>;
+	};
-- 
cgit v1.2.3


From 3fa0e8f6f9609ba195b8b3e4cf3e61420451fc7b Mon Sep 17 00:00:00 2001
From: David Lechner <david@lechnology.com>
Date: Fri, 25 May 2018 14:36:23 -0500
Subject: drm/tinydrm: new driver for ILI9341 display panels
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds a new driver for display panels that use the Ilitek ILI9341
controller. It currently supports a single display panel, namely
the YX240QV29-T (e.g. Adafruit 2.4" TFT).

The init sequence is from the Adafruit Python library for the ILI9341
controller. https://github.com/adafruit/Adafruit_Python_ILI9341

Signed-off-by: David Lechner <david@lechnology.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Reviewed-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180525193623.15533-5-david@lechnology.com
---
 MAINTAINERS                       |   6 +
 drivers/gpu/drm/tinydrm/Kconfig   |  10 ++
 drivers/gpu/drm/tinydrm/Makefile  |   1 +
 drivers/gpu/drm/tinydrm/ili9341.c | 233 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 250 insertions(+)
 create mode 100644 drivers/gpu/drm/tinydrm/ili9341.c

diff --git a/MAINTAINERS b/MAINTAINERS
index e507c34798ff..e3e44326e553 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4478,6 +4478,12 @@ S:	Maintained
 F:	drivers/gpu/drm/tinydrm/ili9225.c
 F:	Documentation/devicetree/bindings/display/ilitek,ili9225.txt
 
+DRM DRIVER FOR ILITEK ILI9341 PANELS
+M:	David Lechner <david@lechnology.com>
+S:	Maintained
+F:	drivers/gpu/drm/tinydrm/ili9341.c
+F:	Documentation/devicetree/bindings/display/ilitek,ili9341.txt
+
 DRM DRIVER FOR INTEL I810 VIDEO CARDS
 S:	Orphan / Obsolete
 F:	drivers/gpu/drm/i810/
diff --git a/drivers/gpu/drm/tinydrm/Kconfig b/drivers/gpu/drm/tinydrm/Kconfig
index 4592a5e3f20b..7a8008b0783f 100644
--- a/drivers/gpu/drm/tinydrm/Kconfig
+++ b/drivers/gpu/drm/tinydrm/Kconfig
@@ -20,6 +20,16 @@ config TINYDRM_ILI9225
 
 	  If M is selected the module will be called ili9225.
 
+config TINYDRM_ILI9341
+	tristate "DRM support for ILI9341 display panels"
+	depends on DRM_TINYDRM && SPI
+	select TINYDRM_MIPI_DBI
+	help
+	  DRM driver for the following Ilitek ILI9341 panels:
+	  * YX240QV29-T 2.4" 240x320 TFT (Adafruit 2.4")
+
+	  If M is selected the module will be called ili9341.
+
 config TINYDRM_MI0283QT
 	tristate "DRM support for MI0283QT"
 	depends on DRM_TINYDRM && SPI
diff --git a/drivers/gpu/drm/tinydrm/Makefile b/drivers/gpu/drm/tinydrm/Makefile
index 49a111929724..14d99080665a 100644
--- a/drivers/gpu/drm/tinydrm/Makefile
+++ b/drivers/gpu/drm/tinydrm/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_TINYDRM_MIPI_DBI)		+= mipi-dbi.o
 
 # Displays
 obj-$(CONFIG_TINYDRM_ILI9225)		+= ili9225.o
+obj-$(CONFIG_TINYDRM_ILI9341)		+= ili9341.o
 obj-$(CONFIG_TINYDRM_MI0283QT)		+= mi0283qt.o
 obj-$(CONFIG_TINYDRM_REPAPER)		+= repaper.o
 obj-$(CONFIG_TINYDRM_ST7586)		+= st7586.o
diff --git a/drivers/gpu/drm/tinydrm/ili9341.c b/drivers/gpu/drm/tinydrm/ili9341.c
new file mode 100644
index 000000000000..8864dcde6edc
--- /dev/null
+++ b/drivers/gpu/drm/tinydrm/ili9341.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * DRM driver for Ilitek ILI9341 panels
+ *
+ * Copyright 2018 David Lechner <david@lechnology.com>
+ *
+ * Based on mi0283qt.c:
+ * Copyright 2016 Noralf Trønnes
+ */
+
+#include <linux/backlight.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
+#include <linux/property.h>
+#include <linux/spi/spi.h>
+
+#include <drm/drm_fb_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_modeset_helper.h>
+#include <drm/tinydrm/mipi-dbi.h>
+#include <drm/tinydrm/tinydrm-helpers.h>
+#include <video/mipi_display.h>
+
+#define ILI9341_FRMCTR1		0xb1
+#define ILI9341_DISCTRL		0xb6
+#define ILI9341_ETMOD		0xb7
+
+#define ILI9341_PWCTRL1		0xc0
+#define ILI9341_PWCTRL2		0xc1
+#define ILI9341_VMCTRL1		0xc5
+#define ILI9341_VMCTRL2		0xc7
+#define ILI9341_PWCTRLA		0xcb
+#define ILI9341_PWCTRLB		0xcf
+
+#define ILI9341_PGAMCTRL	0xe0
+#define ILI9341_NGAMCTRL	0xe1
+#define ILI9341_DTCTRLA		0xe8
+#define ILI9341_DTCTRLB		0xea
+#define ILI9341_PWRSEQ		0xed
+
+#define ILI9341_EN3GAM		0xf2
+#define ILI9341_PUMPCTRL	0xf7
+
+#define ILI9341_MADCTL_BGR	BIT(3)
+#define ILI9341_MADCTL_MV	BIT(5)
+#define ILI9341_MADCTL_MX	BIT(6)
+#define ILI9341_MADCTL_MY	BIT(7)
+
+static void yx240qv29_enable(struct drm_simple_display_pipe *pipe,
+			     struct drm_crtc_state *crtc_state,
+			     struct drm_plane_state *plane_state)
+{
+	struct tinydrm_device *tdev = pipe_to_tinydrm(pipe);
+	struct mipi_dbi *mipi = mipi_dbi_from_tinydrm(tdev);
+	u8 addr_mode;
+	int ret;
+
+	DRM_DEBUG_KMS("\n");
+
+	ret = mipi_dbi_poweron_conditional_reset(mipi);
+	if (ret < 0)
+		return;
+	if (ret == 1)
+		goto out_enable;
+
+	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_OFF);
+
+	mipi_dbi_command(mipi, ILI9341_PWCTRLB, 0x00, 0xc1, 0x30);
+	mipi_dbi_command(mipi, ILI9341_PWRSEQ, 0x64, 0x03, 0x12, 0x81);
+	mipi_dbi_command(mipi, ILI9341_DTCTRLA, 0x85, 0x00, 0x78);
+	mipi_dbi_command(mipi, ILI9341_PWCTRLA, 0x39, 0x2c, 0x00, 0x34, 0x02);
+	mipi_dbi_command(mipi, ILI9341_PUMPCTRL, 0x20);
+	mipi_dbi_command(mipi, ILI9341_DTCTRLB, 0x00, 0x00);
+
+	/* Power Control */
+	mipi_dbi_command(mipi, ILI9341_PWCTRL1, 0x23);
+	mipi_dbi_command(mipi, ILI9341_PWCTRL2, 0x10);
+	/* VCOM */
+	mipi_dbi_command(mipi, ILI9341_VMCTRL1, 0x3e, 0x28);
+	mipi_dbi_command(mipi, ILI9341_VMCTRL2, 0x86);
+
+	/* Memory Access Control */
+	mipi_dbi_command(mipi, MIPI_DCS_SET_PIXEL_FORMAT, MIPI_DCS_PIXEL_FMT_16BIT);
+
+	/* Frame Rate */
+	mipi_dbi_command(mipi, ILI9341_FRMCTR1, 0x00, 0x1b);
+
+	/* Gamma */
+	mipi_dbi_command(mipi, ILI9341_EN3GAM, 0x00);
+	mipi_dbi_command(mipi, MIPI_DCS_SET_GAMMA_CURVE, 0x01);
+	mipi_dbi_command(mipi, ILI9341_PGAMCTRL,
+			 0x0f, 0x31, 0x2b, 0x0c, 0x0e, 0x08, 0x4e, 0xf1,
+			 0x37, 0x07, 0x10, 0x03, 0x0e, 0x09, 0x00);
+	mipi_dbi_command(mipi, ILI9341_NGAMCTRL,
+			 0x00, 0x0e, 0x14, 0x03, 0x11, 0x07, 0x31, 0xc1,
+			 0x48, 0x08, 0x0f, 0x0c, 0x31, 0x36, 0x0f);
+
+	/* DDRAM */
+	mipi_dbi_command(mipi, ILI9341_ETMOD, 0x07);
+
+	/* Display */
+	mipi_dbi_command(mipi, ILI9341_DISCTRL, 0x08, 0x82, 0x27, 0x00);
+	mipi_dbi_command(mipi, MIPI_DCS_EXIT_SLEEP_MODE);
+	msleep(100);
+
+	mipi_dbi_command(mipi, MIPI_DCS_SET_DISPLAY_ON);
+	msleep(100);
+
+out_enable:
+	switch (mipi->rotation) {
+	default:
+		addr_mode = ILI9341_MADCTL_MX;
+		break;
+	case 90:
+		addr_mode = ILI9341_MADCTL_MV;
+		break;
+	case 180:
+		addr_mode = ILI9341_MADCTL_MY;
+		break;
+	case 270:
+		addr_mode = ILI9341_MADCTL_MV | ILI9341_MADCTL_MY |
+			    ILI9341_MADCTL_MX;
+		break;
+	}
+	addr_mode |= ILI9341_MADCTL_BGR;
+	mipi_dbi_command(mipi, MIPI_DCS_SET_ADDRESS_MODE, addr_mode);
+	mipi_dbi_enable_flush(mipi, crtc_state, plane_state);
+}
+
+static const struct drm_simple_display_pipe_funcs ili9341_pipe_funcs = {
+	.enable = yx240qv29_enable,
+	.disable = mipi_dbi_pipe_disable,
+	.update = tinydrm_display_pipe_update,
+	.prepare_fb = drm_gem_fb_simple_display_pipe_prepare_fb,
+};
+
+static const struct drm_display_mode yx240qv29_mode = {
+	TINYDRM_MODE(240, 320, 37, 49),
+};
+
+DEFINE_DRM_GEM_CMA_FOPS(ili9341_fops);
+
+static struct drm_driver ili9341_driver = {
+	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC,
+	.fops			= &ili9341_fops,
+	TINYDRM_GEM_DRIVER_OPS,
+	.lastclose		= drm_fb_helper_lastclose,
+	.debugfs_init		= mipi_dbi_debugfs_init,
+	.name			= "ili9341",
+	.desc			= "Ilitek ILI9341",
+	.date			= "20180514",
+	.major			= 1,
+	.minor			= 0,
+};
+
+static const struct of_device_id ili9341_of_match[] = {
+	{ .compatible = "adafruit,yx240qv29" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ili9341_of_match);
+
+static const struct spi_device_id ili9341_id[] = {
+	{ "yx240qv29", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(spi, ili9341_id);
+
+static int ili9341_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct mipi_dbi *mipi;
+	struct gpio_desc *dc;
+	u32 rotation = 0;
+	int ret;
+
+	mipi = devm_kzalloc(dev, sizeof(*mipi), GFP_KERNEL);
+	if (!mipi)
+		return -ENOMEM;
+
+	mipi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(mipi->reset)) {
+		DRM_DEV_ERROR(dev, "Failed to get gpio 'reset'\n");
+		return PTR_ERR(mipi->reset);
+	}
+
+	dc = devm_gpiod_get_optional(dev, "dc", GPIOD_OUT_LOW);
+	if (IS_ERR(dc)) {
+		DRM_DEV_ERROR(dev, "Failed to get gpio 'dc'\n");
+		return PTR_ERR(dc);
+	}
+
+	mipi->backlight = devm_of_find_backlight(dev);
+	if (IS_ERR(mipi->backlight))
+		return PTR_ERR(mipi->backlight);
+
+	device_property_read_u32(dev, "rotation", &rotation);
+
+	ret = mipi_dbi_spi_init(spi, mipi, dc);
+	if (ret)
+		return ret;
+
+	ret = mipi_dbi_init(&spi->dev, mipi, &ili9341_pipe_funcs,
+			    &ili9341_driver, &yx240qv29_mode, rotation);
+	if (ret)
+		return ret;
+
+	spi_set_drvdata(spi, mipi);
+
+	return devm_tinydrm_register(&mipi->tinydrm);
+}
+
+static void ili9341_shutdown(struct spi_device *spi)
+{
+	struct mipi_dbi *mipi = spi_get_drvdata(spi);
+
+	tinydrm_shutdown(&mipi->tinydrm);
+}
+
+static struct spi_driver ili9341_spi_driver = {
+	.driver = {
+		.name = "ili9341",
+		.of_match_table = ili9341_of_match,
+	},
+	.id_table = ili9341_id,
+	.probe = ili9341_probe,
+	.shutdown = ili9341_shutdown,
+};
+module_spi_driver(ili9341_spi_driver);
+
+MODULE_DESCRIPTION("Ilitek ILI9341 DRM driver");
+MODULE_AUTHOR("David Lechner <david@lechnology.com>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From f7486bc38c21b24ca418f0c740dd44db9849078d Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <icenowy@aosc.io>
Date: Fri, 22 Jun 2018 20:26:09 +0800
Subject: dt-bindings: add compatible string for the A64 DE2 CCU

The Allwinner A64 SoC has a DE2 CCU like the one in the DE2 of Allwinner
H5 SoC.

Add a compatible string for it.

Signed-off-by: Icenowy Zheng <icenowy@aosc.io>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
---
 Documentation/devicetree/bindings/clock/sun8i-de2.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/clock/sun8i-de2.txt b/Documentation/devicetree/bindings/clock/sun8i-de2.txt
index f2fa87c4765c..e94582e8b8a9 100644
--- a/Documentation/devicetree/bindings/clock/sun8i-de2.txt
+++ b/Documentation/devicetree/bindings/clock/sun8i-de2.txt
@@ -6,6 +6,7 @@ Required properties :
 		- "allwinner,sun8i-a83t-de2-clk"
 		- "allwinner,sun8i-h3-de2-clk"
 		- "allwinner,sun8i-v3s-de2-clk"
+		- "allwinner,sun50i-a64-de2-clk"
 		- "allwinner,sun50i-h5-de2-clk"
 
 - reg: Must contain the registers base address and length
-- 
cgit v1.2.3


From 0195156340d365540c7dfa239232065826904f59 Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <icenowy@aosc.io>
Date: Fri, 22 Jun 2018 20:45:37 +0800
Subject: clk: sunxi-ng: add A64 compatible string

As claiming Allwinner A64 SRAM C is a prerequisite for all sub-blocks of
the A64 DE2, not only the CCU sub-block, a bus driver is then written for
enabling the access to the whole DE2 part by claiming the SRAM.

In this situation, the A64 compatible string will be just added with no
other requirments, as they're processed by the parent bus driver.

Signed-off-by: Icenowy Zheng <icenowy@aosc.io>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
---
 drivers/clk/sunxi-ng/ccu-sun8i-de2.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/clk/sunxi-ng/ccu-sun8i-de2.c b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
index 468d1abaf0ee..bae5ee67a797 100644
--- a/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
+++ b/drivers/clk/sunxi-ng/ccu-sun8i-de2.c
@@ -288,17 +288,14 @@ static const struct of_device_id sunxi_de2_clk_ids[] = {
 		.compatible = "allwinner,sun8i-v3s-de2-clk",
 		.data = &sun8i_v3s_de2_clk_desc,
 	},
+	{
+		.compatible = "allwinner,sun50i-a64-de2-clk",
+		.data = &sun50i_a64_de2_clk_desc,
+	},
 	{
 		.compatible = "allwinner,sun50i-h5-de2-clk",
 		.data = &sun50i_a64_de2_clk_desc,
 	},
-	/*
-	 * The Allwinner A64 SoC needs some bit to be poke in syscon to make
-	 * DE2 really working.
-	 * So there's currently no A64 compatible here.
-	 * H5 shares the same reset line with A64, so here H5 is using the
-	 * clock description of A64.
-	 */
 	{ }
 };
 
-- 
cgit v1.2.3


From 59a9c39544cd1e5952c2a33028d71aa8180648f8 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:44 +0200
Subject: dt-bindings: display: sunxi-drm: Add TCON TOP description

TCON TOP main purpose is to configure whole display pipeline. It
determines relationships between mixers and TCONs, selects source TCON
for HDMI, muxes LCD and TV encoder GPIO output, selects TV encoder
clock source and contains additional TV TCON and DSI gates.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-5-jernej.skrabec@siol.net
---
 .../bindings/display/sunxi/sun4i-drm.txt           | 56 ++++++++++++++++++++++
 include/dt-bindings/clock/sun8i-tcon-top.h         | 11 +++++
 2 files changed, 67 insertions(+)
 create mode 100644 include/dt-bindings/clock/sun8i-tcon-top.h

diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
index 3346c1e2a7a0..fe31b1510717 100644
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
@@ -187,6 +187,62 @@ And on the A23, A31, A31s and A33, you need one more clock line:
    - 'lvds-alt': An alternative clock source, separate from the TCON channel 0
                  clock, that can be used to drive the LVDS clock
 
+TCON TOP
+--------
+
+TCON TOPs main purpose is to configure whole display pipeline. It determines
+relationships between mixers and TCONs, selects source TCON for HDMI, muxes
+LCD and TV encoder GPIO output, selects TV encoder clock source and contains
+additional TV TCON and DSI gates.
+
+It allows display pipeline to be configured in very different ways:
+
+                                / LCD0/LVDS0
+                 / [0] TCON-LCD0
+                 |              \ MIPI DSI
+ mixer0          |
+        \        / [1] TCON-LCD1 - LCD1/LVDS1
+         TCON-TOP
+        /        \ [2] TCON-TV0 [0] - TVE0/RGB
+ mixer1          |                  \
+                 |                   TCON-TOP - HDMI
+                 |                  /
+                 \ [3] TCON-TV1 [1] - TVE1/RGB
+
+Note that both TCON TOP references same physical unit. Both mixers can be
+connected to any TCON.
+
+Required properties:
+  - compatible: value must be one of:
+    * allwinner,sun8i-r40-tcon-top
+  - reg: base address and size of the memory-mapped region.
+  - clocks: phandle to the clocks feeding the TCON TOP
+    * bus: TCON TOP interface clock
+    * tcon-tv0: TCON TV0 clock
+    * tve0: TVE0 clock
+    * tcon-tv1: TCON TV1 clock
+    * tve1: TVE0 clock
+    * dsi: MIPI DSI clock
+  - clock-names: clock name mentioned above
+  - resets: phandle to the reset line driving the TCON TOP
+  - #clock-cells : must contain 1
+  - clock-output-names: Names of clocks created for TCON TV0 channel clock,
+    TCON TV1 channel clock and DSI channel clock, in that order.
+
+- ports: A ports node with endpoint definitions as defined in
+    Documentation/devicetree/bindings/media/video-interfaces.txt. 6 ports should
+    be defined:
+    * port 0 is input for mixer0 mux
+    * port 1 is output for mixer0 mux
+    * port 2 is input for mixer1 mux
+    * port 3 is output for mixer1 mux
+    * port 4 is input for HDMI mux
+    * port 5 is output for HDMI mux
+    All output endpoints for mixer muxes and input endpoints for HDMI mux should
+    have reg property with the id of the target TCON, as shown in above graph
+    (0-3 for mixer muxes and 0-1 for HDMI mux). All ports should have only one
+    endpoint connected to remote endpoint.
+
 DRC
 ---
 
diff --git a/include/dt-bindings/clock/sun8i-tcon-top.h b/include/dt-bindings/clock/sun8i-tcon-top.h
new file mode 100644
index 000000000000..25164d767835
--- /dev/null
+++ b/include/dt-bindings/clock/sun8i-tcon-top.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+/* Copyright (C) 2018 Jernej Skrabec <jernej.skrabec@siol.net> */
+
+#ifndef _DT_BINDINGS_CLOCK_SUN8I_TCON_TOP_H_
+#define _DT_BINDINGS_CLOCK_SUN8I_TCON_TOP_H_
+
+#define CLK_TCON_TOP_TV0	0
+#define CLK_TCON_TOP_TV1	1
+#define CLK_TCON_TOP_DSI	2
+
+#endif /* _DT_BINDINGS_CLOCK_SUN8I_TCON_TOP_H_ */
-- 
cgit v1.2.3


From 19f3ebed3f3612f97ee28af26d53656f5776f89a Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:45 +0200
Subject: drm/sun4i: Add TCON TOP driver

As already described in DT binding, TCON TOP is responsible for
configuring display pipeline. In this initial driver focus is on HDMI
pipeline, so TVE and LCD configuration is not implemented.

Implemented features:
- HDMI source selection
- clock driver (TCON and DSI gating)
- connecting mixers and TCONS

Something similar also existed in previous SoCs, except that it was part
of first TCON.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-6-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/Makefile         |   2 +-
 drivers/gpu/drm/sun4i/sun8i_tcon_top.c | 300 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/sun4i/sun8i_tcon_top.h |  40 +++++
 3 files changed, 341 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/sun4i/sun8i_tcon_top.c
 create mode 100644 drivers/gpu/drm/sun4i/sun8i_tcon_top.h

diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile
index 2589f4acd5ae..14f420f1d4ae 100644
--- a/drivers/gpu/drm/sun4i/Makefile
+++ b/drivers/gpu/drm/sun4i/Makefile
@@ -36,4 +36,4 @@ obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o sun4i-frontend.o
 obj-$(CONFIG_DRM_SUN4I_HDMI)	+= sun4i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN6I_DSI)	+= sun6i-dsi.o
 obj-$(CONFIG_DRM_SUN8I_DW_HDMI)	+= sun8i-drm-hdmi.o
-obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o
+obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o sun8i_tcon_top.o
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
new file mode 100644
index 000000000000..8da0460e0028
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -0,0 +1,300 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (c) 2018 Jernej Skrabec <jernej.skrabec@siol.net> */
+
+#include <drm/drmP.h>
+
+#include <dt-bindings/clock/sun8i-tcon-top.h>
+
+#include <linux/bitfield.h>
+#include <linux/component.h>
+#include <linux/device.h>
+#include <linux/module.h>
+#include <linux/of_graph.h>
+#include <linux/platform_device.h>
+
+#include "sun8i_tcon_top.h"
+
+static int sun8i_tcon_top_get_connected_ep_id(struct device_node *node,
+					      int port_id)
+{
+	struct device_node *ep, *remote, *port;
+	struct of_endpoint endpoint;
+
+	port = of_graph_get_port_by_id(node, port_id);
+	if (!port)
+		return -ENOENT;
+
+	for_each_available_child_of_node(port, ep) {
+		remote = of_graph_get_remote_port_parent(ep);
+		if (!remote)
+			continue;
+
+		if (of_device_is_available(remote)) {
+			of_graph_parse_endpoint(ep, &endpoint);
+
+			of_node_put(remote);
+
+			return endpoint.id;
+		}
+
+		of_node_put(remote);
+	}
+
+	return -ENOENT;
+}
+
+static struct clk_hw *sun8i_tcon_top_register_gate(struct device *dev,
+						   struct clk *parent,
+						   void __iomem *regs,
+						   spinlock_t *lock,
+						   u8 bit, int name_index)
+{
+	const char *clk_name, *parent_name;
+	int ret;
+
+	parent_name = __clk_get_name(parent);
+	ret = of_property_read_string_index(dev->of_node,
+					    "clock-output-names", name_index,
+					    &clk_name);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return clk_hw_register_gate(dev, clk_name, parent_name,
+				    CLK_SET_RATE_PARENT,
+				    regs + TCON_TOP_GATE_SRC_REG,
+				    bit, 0, lock);
+};
+
+static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
+			       void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct clk *dsi, *tcon_tv0, *tcon_tv1, *tve0, *tve1;
+	struct clk_hw_onecell_data *clk_data;
+	struct sun8i_tcon_top *tcon_top;
+	bool mixer0_unused = false;
+	struct resource *res;
+	void __iomem *regs;
+	int ret, i, id;
+	u32 val;
+
+	tcon_top = devm_kzalloc(dev, sizeof(*tcon_top), GFP_KERNEL);
+	if (!tcon_top)
+		return -ENOMEM;
+
+	clk_data = devm_kzalloc(dev, sizeof(*clk_data) +
+				sizeof(*clk_data->hws) * CLK_NUM,
+				GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+	tcon_top->clk_data = clk_data;
+
+	spin_lock_init(&tcon_top->reg_lock);
+
+	tcon_top->rst = devm_reset_control_get(dev, NULL);
+	if (IS_ERR(tcon_top->rst)) {
+		dev_err(dev, "Couldn't get our reset line\n");
+		return PTR_ERR(tcon_top->rst);
+	}
+
+	tcon_top->bus = devm_clk_get(dev, "bus");
+	if (IS_ERR(tcon_top->bus)) {
+		dev_err(dev, "Couldn't get the bus clock\n");
+		return PTR_ERR(tcon_top->bus);
+	}
+
+	dsi = devm_clk_get(dev, "dsi");
+	if (IS_ERR(dsi)) {
+		dev_err(dev, "Couldn't get the dsi clock\n");
+		return PTR_ERR(dsi);
+	}
+
+	tcon_tv0 = devm_clk_get(dev, "tcon-tv0");
+	if (IS_ERR(tcon_tv0)) {
+		dev_err(dev, "Couldn't get the tcon-tv0 clock\n");
+		return PTR_ERR(tcon_tv0);
+	}
+
+	tcon_tv1 = devm_clk_get(dev, "tcon-tv1");
+	if (IS_ERR(tcon_tv1)) {
+		dev_err(dev, "Couldn't get the tcon-tv1 clock\n");
+		return PTR_ERR(tcon_tv1);
+	}
+
+	tve0 = devm_clk_get(dev, "tve0");
+	if (IS_ERR(tve0)) {
+		dev_err(dev, "Couldn't get the tve0 clock\n");
+		return PTR_ERR(tve0);
+	}
+
+	tve1 = devm_clk_get(dev, "tve1");
+	if (IS_ERR(tve1)) {
+		dev_err(dev, "Couldn't get the tve1 clock\n");
+		return PTR_ERR(tve1);
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	ret = reset_control_deassert(tcon_top->rst);
+	if (ret) {
+		dev_err(dev, "Could not deassert ctrl reset control\n");
+		return ret;
+	}
+
+	ret = clk_prepare_enable(tcon_top->bus);
+	if (ret) {
+		dev_err(dev, "Could not enable bus clock\n");
+		goto err_assert_reset;
+	}
+
+	val = 0;
+
+	/* check if HDMI mux output is connected */
+	if (sun8i_tcon_top_get_connected_ep_id(dev->of_node, 5) >= 0) {
+		/* find HDMI input endpoint id, if it is connected at all*/
+		id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 4);
+		if (id >= 0)
+			val = FIELD_PREP(TCON_TOP_HDMI_SRC_MSK, id + 1);
+		else
+			DRM_DEBUG_DRIVER("TCON TOP HDMI input is not connected\n");
+	} else {
+		DRM_DEBUG_DRIVER("TCON TOP HDMI output is not connected\n");
+	}
+
+	writel(val, regs + TCON_TOP_GATE_SRC_REG);
+
+	val = 0;
+
+	/* process mixer0 mux output */
+	id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 1);
+	if (id >= 0) {
+		val = FIELD_PREP(TCON_TOP_PORT_DE0_MSK, id);
+	} else {
+		DRM_DEBUG_DRIVER("TCON TOP mixer0 output is not connected\n");
+		mixer0_unused = true;
+	}
+
+	/* process mixer1 mux output */
+	id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 3);
+	if (id >= 0) {
+		val |= FIELD_PREP(TCON_TOP_PORT_DE1_MSK, id);
+
+		/*
+		 * mixer0 mux has priority over mixer1 mux. We have to
+		 * make sure mixer0 doesn't overtake TCON from mixer1.
+		 */
+		if (mixer0_unused && id == 0)
+			val |= FIELD_PREP(TCON_TOP_PORT_DE0_MSK, 1);
+	} else {
+		DRM_DEBUG_DRIVER("TCON TOP mixer1 output is not connected\n");
+	}
+
+	writel(val, regs + TCON_TOP_PORT_SEL_REG);
+
+	/*
+	 * TCON TOP has two muxes, which select parent clock for each TCON TV
+	 * channel clock. Parent could be either TCON TV or TVE clock. For now
+	 * we leave this fixed to TCON TV, since TVE driver for R40 is not yet
+	 * implemented. Once it is, graph needs to be traversed to determine
+	 * if TVE is active on each TCON TV. If it is, mux should be switched
+	 * to TVE clock parent.
+	 */
+	clk_data->hws[CLK_TCON_TOP_TV0] =
+		sun8i_tcon_top_register_gate(dev, tcon_tv0, regs,
+					     &tcon_top->reg_lock,
+					     TCON_TOP_TCON_TV0_GATE, 0);
+
+	clk_data->hws[CLK_TCON_TOP_TV1] =
+		sun8i_tcon_top_register_gate(dev, tcon_tv1, regs,
+					     &tcon_top->reg_lock,
+					     TCON_TOP_TCON_TV1_GATE, 1);
+
+	clk_data->hws[CLK_TCON_TOP_DSI] =
+		sun8i_tcon_top_register_gate(dev, dsi, regs,
+					     &tcon_top->reg_lock,
+					     TCON_TOP_TCON_DSI_GATE, 2);
+
+	for (i = 0; i < CLK_NUM; i++)
+		if (IS_ERR(clk_data->hws[i])) {
+			ret = PTR_ERR(clk_data->hws[i]);
+			goto err_unregister_gates;
+		}
+
+	clk_data->num = CLK_NUM;
+
+	ret = of_clk_add_hw_provider(dev->of_node, of_clk_hw_onecell_get,
+				     clk_data);
+	if (ret)
+		goto err_unregister_gates;
+
+	dev_set_drvdata(dev, tcon_top);
+
+	return 0;
+
+err_unregister_gates:
+	for (i = 0; i < CLK_NUM; i++)
+		if (clk_data->hws[i])
+			clk_hw_unregister_gate(clk_data->hws[i]);
+	clk_disable_unprepare(tcon_top->bus);
+err_assert_reset:
+	reset_control_assert(tcon_top->rst);
+
+	return ret;
+}
+
+static void sun8i_tcon_top_unbind(struct device *dev, struct device *master,
+				  void *data)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	struct clk_hw_onecell_data *clk_data = tcon_top->clk_data;
+	int i;
+
+	of_clk_del_provider(dev->of_node);
+	for (i = 0; i < CLK_NUM; i++)
+		clk_hw_unregister_gate(clk_data->hws[i]);
+
+	clk_disable_unprepare(tcon_top->bus);
+	reset_control_assert(tcon_top->rst);
+}
+
+static const struct component_ops sun8i_tcon_top_ops = {
+	.bind	= sun8i_tcon_top_bind,
+	.unbind	= sun8i_tcon_top_unbind,
+};
+
+static int sun8i_tcon_top_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &sun8i_tcon_top_ops);
+}
+
+static int sun8i_tcon_top_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &sun8i_tcon_top_ops);
+
+	return 0;
+}
+
+/* sun4i_drv uses this list to check if a device node is a TCON TOP */
+const struct of_device_id sun8i_tcon_top_of_table[] = {
+	{ .compatible = "allwinner,sun8i-r40-tcon-top" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sun8i_tcon_top_of_table);
+EXPORT_SYMBOL(sun8i_tcon_top_of_table);
+
+static struct platform_driver sun8i_tcon_top_platform_driver = {
+	.probe		= sun8i_tcon_top_probe,
+	.remove		= sun8i_tcon_top_remove,
+	.driver		= {
+		.name		= "sun8i-tcon-top",
+		.of_match_table	= sun8i_tcon_top_of_table,
+	},
+};
+module_platform_driver(sun8i_tcon_top_platform_driver);
+
+MODULE_AUTHOR("Jernej Skrabec <jernej.skrabec@siol.net>");
+MODULE_DESCRIPTION("Allwinner R40 TCON TOP driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.h b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
new file mode 100644
index 000000000000..39838bbfeaee
--- /dev/null
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2018 Jernej Skrabec <jernej.skrabec@siol.net> */
+
+#ifndef _SUN8I_TCON_TOP_H_
+#define _SUN8I_TCON_TOP_H_
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/reset.h>
+#include <linux/spinlock.h>
+
+#define TCON_TOP_TCON_TV_SETUP_REG	0x00
+
+#define TCON_TOP_PORT_SEL_REG		0x1C
+#define TCON_TOP_PORT_DE0_MSK			GENMASK(1, 0)
+#define TCON_TOP_PORT_DE1_MSK			GENMASK(5, 4)
+
+#define TCON_TOP_GATE_SRC_REG		0x20
+#define TCON_TOP_HDMI_SRC_MSK			GENMASK(29, 28)
+#define TCON_TOP_TCON_TV1_GATE			24
+#define TCON_TOP_TCON_TV0_GATE			20
+#define TCON_TOP_TCON_DSI_GATE			16
+
+#define CLK_NUM					3
+
+struct sun8i_tcon_top {
+	struct clk			*bus;
+	struct clk_hw_onecell_data	*clk_data;
+	struct reset_control		*rst;
+
+	/*
+	 * spinlock is used to synchronize access to same
+	 * register where multiple clock gates can be set.
+	 */
+	spinlock_t			reg_lock;
+};
+
+extern const struct of_device_id sun8i_tcon_top_of_table[];
+
+#endif /* _SUN8I_TCON_TOP_H_ */
-- 
cgit v1.2.3


From 367c359aa8637b15ee8df6335c5a29b7623966ec Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:46 +0200
Subject: drm/sun4i: Fix releasing node when enumerating enpoints

sun4i_drv_add_endpoints() has a memory leak since it uses of_node_put()
when remote is equal to NULL and does nothing when remote has a valid
pointer.

Invert the logic to fix memory leak.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-7-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_drv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 50d19605c38f..e15fa2389e3f 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -283,7 +283,6 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 		remote = of_graph_get_remote_port_parent(ep);
 		if (!remote) {
 			DRM_DEBUG_DRIVER("Error retrieving the output node\n");
-			of_node_put(remote);
 			continue;
 		}
 
@@ -297,11 +296,13 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 
 			if (of_graph_parse_endpoint(ep, &endpoint)) {
 				DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
+				of_node_put(remote);
 				continue;
 			}
 
 			if (!endpoint.id) {
 				DRM_DEBUG_DRIVER("Endpoint is our panel... skipping\n");
+				of_node_put(remote);
 				continue;
 			}
 		}
-- 
cgit v1.2.3


From 71f4796ac09d6b634f4756388cfdbe9d778499e9 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:47 +0200
Subject: drm/sun4i: Split out code for enumerating endpoints in output port

Until now, each node has one input port and one output port. However,
with TCON TOP this is no longer true. It has 3 input and 3 output ports.

In order to prepare to this situation, split out the code which checks
all endpoints in input port and adds available components to fifo.

This patch doesn't do any functional change.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-8-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_drv.c | 84 +++++++++++++++++++++------------------
 1 file changed, 46 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index e15fa2389e3f..20193d6f33ba 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -231,12 +231,55 @@ struct endpoint_list {
 	DECLARE_KFIFO(fifo, struct device_node *, 16);
 };
 
+static void sun4i_drv_traverse_endpoints(struct endpoint_list *list,
+					 struct device_node *node,
+					 int port_id)
+{
+	struct device_node *ep, *remote, *port;
+
+	port = of_graph_get_port_by_id(node, port_id);
+	if (!port) {
+		DRM_DEBUG_DRIVER("No output to bind on port %d\n", port_id);
+		return;
+	}
+
+	for_each_available_child_of_node(port, ep) {
+		remote = of_graph_get_remote_port_parent(ep);
+		if (!remote) {
+			DRM_DEBUG_DRIVER("Error retrieving the output node\n");
+			continue;
+		}
+
+		/*
+		 * If the node is our TCON, the first port is used for
+		 * panel or bridges, and will not be part of the
+		 * component framework.
+		 */
+		if (sun4i_drv_node_is_tcon(node)) {
+			struct of_endpoint endpoint;
+
+			if (of_graph_parse_endpoint(ep, &endpoint)) {
+				DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
+				of_node_put(remote);
+				continue;
+			}
+
+			if (!endpoint.id) {
+				DRM_DEBUG_DRIVER("Endpoint is our panel... skipping\n");
+				of_node_put(remote);
+				continue;
+			}
+		}
+
+		kfifo_put(&list->fifo, remote);
+	}
+}
+
 static int sun4i_drv_add_endpoints(struct device *dev,
 				   struct endpoint_list *list,
 				   struct component_match **match,
 				   struct device_node *node)
 {
-	struct device_node *port, *ep, *remote;
 	int count = 0;
 
 	/*
@@ -272,43 +315,8 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 		count++;
 	}
 
-	/* Inputs are listed first, then outputs */
-	port = of_graph_get_port_by_id(node, 1);
-	if (!port) {
-		DRM_DEBUG_DRIVER("No output to bind\n");
-		return count;
-	}
-
-	for_each_available_child_of_node(port, ep) {
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote) {
-			DRM_DEBUG_DRIVER("Error retrieving the output node\n");
-			continue;
-		}
-
-		/*
-		 * If the node is our TCON, the first port is used for
-		 * panel or bridges, and will not be part of the
-		 * component framework.
-		 */
-		if (sun4i_drv_node_is_tcon(node)) {
-			struct of_endpoint endpoint;
-
-			if (of_graph_parse_endpoint(ep, &endpoint)) {
-				DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
-				of_node_put(remote);
-				continue;
-			}
-
-			if (!endpoint.id) {
-				DRM_DEBUG_DRIVER("Endpoint is our panel... skipping\n");
-				of_node_put(remote);
-				continue;
-			}
-		}
-
-		kfifo_put(&list->fifo, remote);
-	}
+	/* each node has at least one output */
+	sun4i_drv_traverse_endpoints(list, node, 1);
 
 	return count;
 }
-- 
cgit v1.2.3


From ef0cf6441fbb1ac4390e4fa4223d421a924fd458 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:48 +0200
Subject: drm/sun4i: Add support for traversing graph with TCON TOP

TCON TOP is different from other nodes in graph by having 3 input and 3
output ports. Additionally, connection to TV TCON might lead back to
HDMI mux input port, creating loops.

Add support for traversing such graph.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-9-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_drv.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 20193d6f33ba..e6c62c079146 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -26,6 +26,7 @@
 #include "sun4i_frontend.h"
 #include "sun4i_framebuffer.h"
 #include "sun4i_tcon.h"
+#include "sun8i_tcon_top.h"
 
 DEFINE_DRM_GEM_CMA_FOPS(sun4i_drv_fops);
 
@@ -197,6 +198,11 @@ static bool sun4i_drv_node_is_tcon(struct device_node *node)
 	return !!of_match_node(sun4i_tcon_of_table, node);
 }
 
+static bool sun4i_drv_node_is_tcon_top(struct device_node *node)
+{
+	return !!of_match_node(sun8i_tcon_top_of_table, node);
+}
+
 static int compare_of(struct device *dev, void *data)
 {
 	DRM_DEBUG_DRIVER("Comparing of node %pOF with %pOF\n",
@@ -258,6 +264,18 @@ static void sun4i_drv_traverse_endpoints(struct endpoint_list *list,
 		if (sun4i_drv_node_is_tcon(node)) {
 			struct of_endpoint endpoint;
 
+			/*
+			 * TCON TOP is always probed before TCON. However, TCON
+			 * points back to TCON TOP when it is source for HDMI.
+			 * We have to skip it here to prevent infinite looping
+			 * between TCON TOP and TCON.
+			 */
+			if (sun4i_drv_node_is_tcon_top(remote)) {
+				DRM_DEBUG_DRIVER("TCON output endpoint is TCON TOP... skipping\n");
+				of_node_put(remote);
+				continue;
+			}
+
 			if (of_graph_parse_endpoint(ep, &endpoint)) {
 				DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
 				of_node_put(remote);
@@ -318,6 +336,12 @@ static int sun4i_drv_add_endpoints(struct device *dev,
 	/* each node has at least one output */
 	sun4i_drv_traverse_endpoints(list, node, 1);
 
+	/* TCON TOP has second and third output */
+	if (sun4i_drv_node_is_tcon_top(node)) {
+		sun4i_drv_traverse_endpoints(list, node, 3);
+		sun4i_drv_traverse_endpoints(list, node, 5);
+	}
+
 	return count;
 }
 
-- 
cgit v1.2.3


From c5cf04df56e62f5a3ef09452181ee1dc51106080 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:49 +0200
Subject: drm/sun4i: Don't skip TCONs if they don't have channel 0

TV TCONs (channel 1 only) are always connected to TV or HDMI encoder.
Because of that, all output endpoints on such TCON node will point to a
encoder which is part of component framework.

Correct current graph traversing algorithm in such way that it doesn't
skip output enpoints with id 0 on TV TCONs.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-10-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_drv.c | 52 ++++++++++++++++++++++++++-------------
 1 file changed, 35 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index e6c62c079146..6ddf4eaccb40 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -198,6 +198,22 @@ static bool sun4i_drv_node_is_tcon(struct device_node *node)
 	return !!of_match_node(sun4i_tcon_of_table, node);
 }
 
+static bool sun4i_drv_node_is_tcon_with_ch0(struct device_node *node)
+{
+	const struct of_device_id *match;
+
+	match = of_match_node(sun4i_tcon_of_table, node);
+	if (match) {
+		struct sun4i_tcon_quirks *quirks;
+
+		quirks = (struct sun4i_tcon_quirks *)match->data;
+
+		return quirks->has_channel_0;
+	}
+
+	return false;
+}
+
 static bool sun4i_drv_node_is_tcon_top(struct device_node *node)
 {
 	return !!of_match_node(sun8i_tcon_top_of_table, node);
@@ -256,14 +272,7 @@ static void sun4i_drv_traverse_endpoints(struct endpoint_list *list,
 			continue;
 		}
 
-		/*
-		 * If the node is our TCON, the first port is used for
-		 * panel or bridges, and will not be part of the
-		 * component framework.
-		 */
 		if (sun4i_drv_node_is_tcon(node)) {
-			struct of_endpoint endpoint;
-
 			/*
 			 * TCON TOP is always probed before TCON. However, TCON
 			 * points back to TCON TOP when it is source for HDMI.
@@ -276,16 +285,25 @@ static void sun4i_drv_traverse_endpoints(struct endpoint_list *list,
 				continue;
 			}
 
-			if (of_graph_parse_endpoint(ep, &endpoint)) {
-				DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
-				of_node_put(remote);
-				continue;
-			}
-
-			if (!endpoint.id) {
-				DRM_DEBUG_DRIVER("Endpoint is our panel... skipping\n");
-				of_node_put(remote);
-				continue;
+			/*
+			 * If the node is our TCON with channel 0, the first
+			 * port is used for panel or bridges, and will not be
+			 * part of the component framework.
+			 */
+			if (sun4i_drv_node_is_tcon_with_ch0(node)) {
+				struct of_endpoint endpoint;
+
+				if (of_graph_parse_endpoint(ep, &endpoint)) {
+					DRM_DEBUG_DRIVER("Couldn't parse endpoint\n");
+					of_node_put(remote);
+					continue;
+				}
+
+				if (!endpoint.id) {
+					DRM_DEBUG_DRIVER("Endpoint is our panel... skipping\n");
+					of_node_put(remote);
+					continue;
+				}
 			}
 		}
 
-- 
cgit v1.2.3


From 49836b11fe71b93bd0124cbaecac0814aadec9eb Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:50 +0200
Subject: drm/sun4i: tcon: Generalize engine search algorithm

Current "old" method to find engine worked pretty well for DE2. However,
it doesn't work when TCON TOP is between  mixer (engine) and TCON. TCON
TOP has multiple input ports, but current engine search algorithm
expects only one.

This can be fixed by first looking for output port id and selecting
matching input by subtracting 1 for the next round. This work even if
there is only one input and output.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-11-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_tcon.c | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 08747fc3ee71..264bcc43da11 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -791,12 +791,14 @@ static int sun4i_tcon_init_regmap(struct device *dev,
  */
 static struct sunxi_engine *
 sun4i_tcon_find_engine_traverse(struct sun4i_drv *drv,
-				struct device_node *node)
+				struct device_node *node,
+				u32 port_id)
 {
 	struct device_node *port, *ep, *remote;
 	struct sunxi_engine *engine = ERR_PTR(-EINVAL);
+	u32 reg = 0;
 
-	port = of_graph_get_port_by_id(node, 0);
+	port = of_graph_get_port_by_id(node, port_id);
 	if (!port)
 		return ERR_PTR(-EINVAL);
 
@@ -826,8 +828,20 @@ sun4i_tcon_find_engine_traverse(struct sun4i_drv *drv,
 		if (remote == engine->node)
 			goto out_put_remote;
 
+	/*
+	 * According to device tree binding input ports have even id
+	 * number and output ports have odd id. Since component with
+	 * more than one input and one output (TCON TOP) exits, correct
+	 * remote input id has to be calculated by subtracting 1 from
+	 * remote output id. If this for some reason can't be done, 0
+	 * is used as input port id.
+	 */
+	port = of_graph_get_remote_port(ep);
+	if (!of_property_read_u32(port, "reg", &reg) && reg > 0)
+		reg -= 1;
+
 	/* keep looking through upstream ports */
-	engine = sun4i_tcon_find_engine_traverse(drv, remote);
+	engine = sun4i_tcon_find_engine_traverse(drv, remote, reg);
 
 out_put_remote:
 	of_node_put(remote);
@@ -950,7 +964,7 @@ static struct sunxi_engine *sun4i_tcon_find_engine(struct sun4i_drv *drv,
 
 	/* Fallback to old method by traversing input endpoints */
 	of_node_put(port);
-	return sun4i_tcon_find_engine_traverse(drv, node);
+	return sun4i_tcon_find_engine_traverse(drv, node, 0);
 }
 
 static int sun4i_tcon_bind(struct device *dev, struct device *master,
-- 
cgit v1.2.3


From 2a72d0c5796b7ec90ebf51e714b3d305d4367341 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:51 +0200
Subject: drm/sun4i: Don't check for LVDS and RGB when TCON has only ch1

LVDS and RGB interfaces are always connected to TCONs which have channel
0. It doesn't make sense to try to init them on TV TCONs.

Add a check if TCON has channel 0 before trying to init LVDS or RGB
interface.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-12-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_tcon.c | 32 +++++++++++++++++---------------
 1 file changed, 17 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 264bcc43da11..761687ebacba 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -1106,23 +1106,25 @@ static int sun4i_tcon_bind(struct device *dev, struct device *master,
 		goto err_free_dotclock;
 	}
 
-	/*
-	 * If we have an LVDS panel connected to the TCON, we should
-	 * just probe the LVDS connector. Otherwise, just probe RGB as
-	 * we used to.
-	 */
-	remote = of_graph_get_remote_node(dev->of_node, 1, 0);
-	if (of_device_is_compatible(remote, "panel-lvds"))
-		if (can_lvds)
-			ret = sun4i_lvds_init(drm, tcon);
+	if (tcon->quirks->has_channel_0) {
+		/*
+		 * If we have an LVDS panel connected to the TCON, we should
+		 * just probe the LVDS connector. Otherwise, just probe RGB as
+		 * we used to.
+		 */
+		remote = of_graph_get_remote_node(dev->of_node, 1, 0);
+		if (of_device_is_compatible(remote, "panel-lvds"))
+			if (can_lvds)
+				ret = sun4i_lvds_init(drm, tcon);
+			else
+				ret = -EINVAL;
 		else
-			ret = -EINVAL;
-	else
-		ret = sun4i_rgb_init(drm, tcon);
-	of_node_put(remote);
+			ret = sun4i_rgb_init(drm, tcon);
+		of_node_put(remote);
 
-	if (ret < 0)
-		goto err_free_dotclock;
+		if (ret < 0)
+			goto err_free_dotclock;
+	}
 
 	if (tcon->quirks->needs_de_be_mux) {
 		/*
-- 
cgit v1.2.3


From 63d6310f6cc63735f08b86b3c8390b9f066a2221 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:52 +0200
Subject: drm/sun4i: Don't check for panel or bridge on TV TCONs

TV TCONs are always connected to TV or HDMI encoder, so it doesn't make
sense to check if panel or bridge is connected to them.

Check if TCON has channel 0 and only then check for connected panel or
bridges.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-13-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_tcon.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index 761687ebacba..a41c7bb0d557 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -1178,13 +1178,19 @@ static const struct component_ops sun4i_tcon_ops = {
 static int sun4i_tcon_probe(struct platform_device *pdev)
 {
 	struct device_node *node = pdev->dev.of_node;
+	const struct sun4i_tcon_quirks *quirks;
 	struct drm_bridge *bridge;
 	struct drm_panel *panel;
 	int ret;
 
-	ret = drm_of_find_panel_or_bridge(node, 1, 0, &panel, &bridge);
-	if (ret == -EPROBE_DEFER)
-		return ret;
+	quirks = of_device_get_match_data(&pdev->dev);
+
+	/* panels and bridges are present only on TCONs with channel 0 */
+	if (quirks->has_channel_0) {
+		ret = drm_of_find_panel_or_bridge(node, 1, 0, &panel, &bridge);
+		if (ret == -EPROBE_DEFER)
+			return ret;
+	}
 
 	return component_add(&pdev->dev, &sun4i_tcon_ops);
 }
-- 
cgit v1.2.3


From 0740845909b1e0089ff60ee62b55622759875e4f Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:54 +0200
Subject: drm/sun4i: Add support for R40 mixers

Both mixers have similar capabilities as others SoCs with DE2.

First mixer has 1 VI and 3 UI planes and supports HW scaling on all
planes.

Second mixer has 1 VI and 1 UI planes and also supports HW scaling on
all planes.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-15-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_mixer.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index 126899d6f0d3..ee8febb25903 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -500,6 +500,22 @@ static const struct sun8i_mixer_cfg sun8i_h3_mixer0_cfg = {
 	.vi_num		= 1,
 };
 
+static const struct sun8i_mixer_cfg sun8i_r40_mixer0_cfg = {
+	.ccsc		= 0,
+	.mod_rate	= 297000000,
+	.scaler_mask	= 0xf,
+	.ui_num		= 3,
+	.vi_num		= 1,
+};
+
+static const struct sun8i_mixer_cfg sun8i_r40_mixer1_cfg = {
+	.ccsc		= 1,
+	.mod_rate	= 297000000,
+	.scaler_mask	= 0x3,
+	.ui_num		= 1,
+	.vi_num		= 1,
+};
+
 static const struct sun8i_mixer_cfg sun8i_v3s_mixer_cfg = {
 	.vi_num = 2,
 	.ui_num = 1,
@@ -521,6 +537,14 @@ static const struct of_device_id sun8i_mixer_of_table[] = {
 		.compatible = "allwinner,sun8i-h3-de2-mixer-0",
 		.data = &sun8i_h3_mixer0_cfg,
 	},
+	{
+		.compatible = "allwinner,sun8i-r40-de2-mixer-0",
+		.data = &sun8i_r40_mixer0_cfg,
+	},
+	{
+		.compatible = "allwinner,sun8i-r40-de2-mixer-1",
+		.data = &sun8i_r40_mixer1_cfg,
+	},
 	{
 		.compatible = "allwinner,sun8i-v3s-de2-mixer",
 		.data = &sun8i_v3s_mixer_cfg,
-- 
cgit v1.2.3


From 03c35dbf73e0726136bad921cb2649728ce909d5 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:55 +0200
Subject: dt-bindings: display: sun4i-drm: Add description of A64 HDMI PHY

A64 HDMI PHY is similar to H3 HDMI PHY except it has two possible PLL
clock parents. It is compatible to other HDMI PHYs, like that found in
R40.

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-16-jernej.skrabec@siol.net
---
 Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
index fe31b1510717..5a9319ad8861 100644
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
@@ -101,6 +101,7 @@ DWC HDMI PHY
 
 Required properties:
   - compatible: value must be one of:
+    * allwinner,sun50i-a64-hdmi-phy
     * allwinner,sun8i-a83t-hdmi-phy
     * allwinner,sun8i-h3-hdmi-phy
   - reg: base address and size of memory-mapped region
@@ -111,8 +112,9 @@ Required properties:
   - resets: phandle to the reset controller driving the PHY
   - reset-names: must be "phy"
 
-H3 HDMI PHY requires additional clock:
+H3 and A64 HDMI PHY require additional clocks:
   - pll-0: parent of phy clock
+  - pll-1: second possible phy clock parent (A64 only)
 
 TV Encoder
 ----------
-- 
cgit v1.2.3


From 09773c532d30187f86a142901c27c93e629ce6ba Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:56 +0200
Subject: drm/sun4i: Enable DW HDMI PHY clock

Current DW HDMI PHY code never prepares and enables PHY clock after it is
created. It's just used as it is. This may work in some cases, but it's
clearly wrong. Fix it by adding proper calls to enable/disable PHY
clock.

Fixes: 4f86e81748fe ("drm/sun4i: Add support for H3 HDMI PHY variant")

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-17-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index 5a52fc489a9d..966688f04741 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -477,13 +477,15 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 			dev_err(dev, "Couldn't create the PHY clock\n");
 			goto err_put_clk_pll0;
 		}
+
+		clk_prepare_enable(phy->clk_phy);
 	}
 
 	phy->rst_phy = of_reset_control_get_shared(node, "phy");
 	if (IS_ERR(phy->rst_phy)) {
 		dev_err(dev, "Could not get phy reset control\n");
 		ret = PTR_ERR(phy->rst_phy);
-		goto err_put_clk_pll0;
+		goto err_disable_clk_phy;
 	}
 
 	ret = reset_control_deassert(phy->rst_phy);
@@ -514,6 +516,8 @@ err_deassert_rst_phy:
 	reset_control_assert(phy->rst_phy);
 err_put_rst_phy:
 	reset_control_put(phy->rst_phy);
+err_disable_clk_phy:
+	clk_disable_unprepare(phy->clk_phy);
 err_put_clk_pll0:
 	if (phy->variant->has_phy_clk)
 		clk_put(phy->clk_pll0);
@@ -531,6 +535,7 @@ void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi)
 
 	clk_disable_unprepare(phy->clk_mod);
 	clk_disable_unprepare(phy->clk_bus);
+	clk_disable_unprepare(phy->clk_phy);
 
 	reset_control_assert(phy->rst_phy);
 
-- 
cgit v1.2.3


From 09f380e3ba4103a32faf4fad35d90dc144578214 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:57 +0200
Subject: drm/sun4i: Don't change clock bits in DW HDMI PHY driver

DW HDMI PHY driver and PHY clock driver share same registers. Make sure
that DW HDMI PHY setup code doesn't change any clock related bits.
During initialization, set PHY PLL parent bit to 0.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-18-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h  |  2 +-
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c | 12 +++++++++++-
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
index 79154f0f674a..3ba71aff92fc 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
@@ -98,7 +98,7 @@
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO2_EN		BIT(29)
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO1_EN		BIT(28)
 #define SUN8I_HDMI_PHY_PLL_CFG1_HV_IS_33	BIT(27)
-#define SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL	BIT(26)
+#define SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK	BIT(26)
 #define SUN8I_HDMI_PHY_PLL_CFG1_PLLEN		BIT(25)
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO_VSET(x)	((x) << 22)
 #define SUN8I_HDMI_PHY_PLL_CFG1_UNKNOWN(x)	((x) << 20)
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index 966688f04741..e56b9e5b1c42 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -183,7 +183,13 @@ static int sun8i_hdmi_phy_config_h3(struct dw_hdmi *hdmi,
 	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_ANA_CFG1_REG,
 			   SUN8I_HDMI_PHY_ANA_CFG1_TXEN_MASK, 0);
 
-	regmap_write(phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG, pll_cfg1_init);
+	/*
+	 * NOTE: We have to be careful not to overwrite PHY parent
+	 * clock selection bit and clock divider.
+	 */
+	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG,
+			   (u32)~SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK,
+			   pll_cfg1_init);
 	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_PLL_CFG2_REG,
 			   (u32)~SUN8I_HDMI_PHY_PLL_CFG2_PREDIV_MSK,
 			   pll_cfg2_init);
@@ -352,6 +358,10 @@ static void sun8i_hdmi_phy_init_h3(struct sun8i_hdmi_phy *phy)
 			   SUN8I_HDMI_PHY_ANA_CFG3_SCLEN |
 			   SUN8I_HDMI_PHY_ANA_CFG3_SDAEN);
 
+	/* reset PHY PLL clock parent */
+	regmap_update_bits(phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG,
+			   SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK, 0);
+
 	/* set HW control of CEC pins */
 	regmap_write(phy->regs, SUN8I_HDMI_PHY_CEC_REG, 0);
 
-- 
cgit v1.2.3


From aef13fd8426279fcd9e0b2b5b446d35c0d49ec5d Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:58 +0200
Subject: drm/sun4i: DW HDMI PHY: Add support for second PLL

Some DW HDMI PHYs, like those found in A64 and R40 SoCs, can select
between two clock parents.

Add code which reads second PLL from DT.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-19-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h  |  2 ++
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c | 20 +++++++++++++++-----
 2 files changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
index 3ba71aff92fc..46a3aa6a53a9 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
@@ -147,6 +147,7 @@ struct sun8i_hdmi_phy;
 
 struct sun8i_hdmi_phy_variant {
 	bool has_phy_clk;
+	bool has_second_pll;
 	void (*phy_init)(struct sun8i_hdmi_phy *phy);
 	void (*phy_disable)(struct dw_hdmi *hdmi,
 			    struct sun8i_hdmi_phy *phy);
@@ -160,6 +161,7 @@ struct sun8i_hdmi_phy {
 	struct clk			*clk_mod;
 	struct clk			*clk_phy;
 	struct clk			*clk_pll0;
+	struct clk			*clk_pll1;
 	unsigned int			rcal;
 	struct regmap			*regs;
 	struct reset_control		*rst_phy;
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index e56b9e5b1c42..f0877b3f67e7 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -482,10 +482,19 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 			goto err_put_clk_mod;
 		}
 
+		if (phy->variant->has_second_pll) {
+			phy->clk_pll1 = of_clk_get_by_name(node, "pll-1");
+			if (IS_ERR(phy->clk_pll1)) {
+				dev_err(dev, "Could not get pll-1 clock\n");
+				ret = PTR_ERR(phy->clk_pll1);
+				goto err_put_clk_pll0;
+			}
+		}
+
 		ret = sun8i_phy_clk_create(phy, dev);
 		if (ret) {
 			dev_err(dev, "Couldn't create the PHY clock\n");
-			goto err_put_clk_pll0;
+			goto err_put_clk_pll1;
 		}
 
 		clk_prepare_enable(phy->clk_phy);
@@ -528,9 +537,10 @@ err_put_rst_phy:
 	reset_control_put(phy->rst_phy);
 err_disable_clk_phy:
 	clk_disable_unprepare(phy->clk_phy);
+err_put_clk_pll1:
+	clk_put(phy->clk_pll1);
 err_put_clk_pll0:
-	if (phy->variant->has_phy_clk)
-		clk_put(phy->clk_pll0);
+	clk_put(phy->clk_pll0);
 err_put_clk_mod:
 	clk_put(phy->clk_mod);
 err_put_clk_bus:
@@ -551,8 +561,8 @@ void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi)
 
 	reset_control_put(phy->rst_phy);
 
-	if (phy->variant->has_phy_clk)
-		clk_put(phy->clk_pll0);
+	clk_put(phy->clk_pll0);
+	clk_put(phy->clk_pll1);
 	clk_put(phy->clk_mod);
 	clk_put(phy->clk_bus);
 }
-- 
cgit v1.2.3


From c891a65a7fc940ed387ad822732f711cae554b24 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:02:59 +0200
Subject: drm/sun4i: Add support for second clock parent to DW HDMI PHY clk
 driver

Expand HDMI PHY clock driver to support second clock parent.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-20-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h      |  4 +-
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c     |  3 +-
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c | 90 ++++++++++++++++++++++--------
 3 files changed, 73 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
index 46a3aa6a53a9..aadbe0a10b0c 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.h
@@ -99,6 +99,7 @@
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO1_EN		BIT(28)
 #define SUN8I_HDMI_PHY_PLL_CFG1_HV_IS_33	BIT(27)
 #define SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK	BIT(26)
+#define SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_SHIFT	26
 #define SUN8I_HDMI_PHY_PLL_CFG1_PLLEN		BIT(25)
 #define SUN8I_HDMI_PHY_PLL_CFG1_LDO_VSET(x)	((x) << 22)
 #define SUN8I_HDMI_PHY_PLL_CFG1_UNKNOWN(x)	((x) << 20)
@@ -190,6 +191,7 @@ void sun8i_hdmi_phy_remove(struct sun8i_dw_hdmi *hdmi);
 void sun8i_hdmi_phy_init(struct sun8i_hdmi_phy *phy);
 const struct dw_hdmi_phy_ops *sun8i_hdmi_phy_get_ops(void);
 
-int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev);
+int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev,
+			 bool second_parent);
 
 #endif /* _SUN8I_DW_HDMI_H_ */
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index f0877b3f67e7..aea46b08f127 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -491,7 +491,8 @@ int sun8i_hdmi_phy_probe(struct sun8i_dw_hdmi *hdmi, struct device_node *node)
 			}
 		}
 
-		ret = sun8i_phy_clk_create(phy, dev);
+		ret = sun8i_phy_clk_create(phy, dev,
+					   phy->variant->has_second_pll);
 		if (ret) {
 			dev_err(dev, "Couldn't create the PHY clock\n");
 			goto err_put_clk_pll1;
diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c
index faea449812f8..a4d31fe3abff 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy_clk.c
@@ -22,35 +22,45 @@ static int sun8i_phy_clk_determine_rate(struct clk_hw *hw,
 {
 	unsigned long rate = req->rate;
 	unsigned long best_rate = 0;
+	struct clk_hw *best_parent = NULL;
 	struct clk_hw *parent;
 	int best_div = 1;
-	int i;
+	int i, p;
 
-	parent = clk_hw_get_parent(hw);
-
-	for (i = 1; i <= 16; i++) {
-		unsigned long ideal = rate * i;
-		unsigned long rounded;
-
-		rounded = clk_hw_round_rate(parent, ideal);
+	for (p = 0; p < clk_hw_get_num_parents(hw); p++) {
+		parent = clk_hw_get_parent_by_index(hw, p);
+		if (!parent)
+			continue;
 
-		if (rounded == ideal) {
-			best_rate = rounded;
-			best_div = i;
-			break;
+		for (i = 1; i <= 16; i++) {
+			unsigned long ideal = rate * i;
+			unsigned long rounded;
+
+			rounded = clk_hw_round_rate(parent, ideal);
+
+			if (rounded == ideal) {
+				best_rate = rounded;
+				best_div = i;
+				best_parent = parent;
+				break;
+			}
+
+			if (!best_rate ||
+			    abs(rate - rounded / i) <
+			    abs(rate - best_rate / best_div)) {
+				best_rate = rounded;
+				best_div = i;
+				best_parent = parent;
+			}
 		}
 
-		if (!best_rate ||
-		    abs(rate - rounded / i) <
-		    abs(rate - best_rate / best_div)) {
-			best_rate = rounded;
-			best_div = i;
-		}
+		if (best_rate / best_div == rate)
+			break;
 	}
 
 	req->rate = best_rate / best_div;
 	req->best_parent_rate = best_rate;
-	req->best_parent_hw = parent;
+	req->best_parent_hw = best_parent;
 
 	return 0;
 }
@@ -95,22 +105,58 @@ static int sun8i_phy_clk_set_rate(struct clk_hw *hw, unsigned long rate,
 	return 0;
 }
 
+static u8 sun8i_phy_clk_get_parent(struct clk_hw *hw)
+{
+	struct sun8i_phy_clk *priv = hw_to_phy_clk(hw);
+	u32 reg;
+
+	regmap_read(priv->phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG, &reg);
+	reg = (reg & SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK) >>
+	      SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_SHIFT;
+
+	return reg;
+}
+
+static int sun8i_phy_clk_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct sun8i_phy_clk *priv = hw_to_phy_clk(hw);
+
+	if (index > 1)
+		return -EINVAL;
+
+	regmap_update_bits(priv->phy->regs, SUN8I_HDMI_PHY_PLL_CFG1_REG,
+			   SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_MSK,
+			   index << SUN8I_HDMI_PHY_PLL_CFG1_CKIN_SEL_SHIFT);
+
+	return 0;
+}
+
 static const struct clk_ops sun8i_phy_clk_ops = {
 	.determine_rate	= sun8i_phy_clk_determine_rate,
 	.recalc_rate	= sun8i_phy_clk_recalc_rate,
 	.set_rate	= sun8i_phy_clk_set_rate,
+
+	.get_parent	= sun8i_phy_clk_get_parent,
+	.set_parent	= sun8i_phy_clk_set_parent,
 };
 
-int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev)
+int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev,
+			 bool second_parent)
 {
 	struct clk_init_data init;
 	struct sun8i_phy_clk *priv;
-	const char *parents[1];
+	const char *parents[2];
 
 	parents[0] = __clk_get_name(phy->clk_pll0);
 	if (!parents[0])
 		return -ENODEV;
 
+	if (second_parent) {
+		parents[1] = __clk_get_name(phy->clk_pll1);
+		if (!parents[1])
+			return -ENODEV;
+	}
+
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -118,7 +164,7 @@ int sun8i_phy_clk_create(struct sun8i_hdmi_phy *phy, struct device *dev)
 	init.name = "hdmi-phy-clk";
 	init.ops = &sun8i_phy_clk_ops;
 	init.parent_names = parents;
-	init.num_parents = 1;
+	init.num_parents = second_parent ? 2 : 1;
 	init.flags = CLK_SET_RATE_PARENT;
 
 	priv->phy = phy;
-- 
cgit v1.2.3


From b46e2c9f5f64a3bbd925856cab5336680ca2e9be Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:03:00 +0200
Subject: drm/sun4i: Add support for A64 HDMI PHY

PHY is the same as in H3, except it can switch between two clock
parents.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-21-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
index aea46b08f127..82502b351aec 100644
--- a/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
+++ b/drivers/gpu/drm/sun4i/sun8i_hdmi_phy.c
@@ -396,6 +396,14 @@ static struct regmap_config sun8i_hdmi_phy_regmap_config = {
 	.name		= "phy"
 };
 
+static const struct sun8i_hdmi_phy_variant sun50i_a64_hdmi_phy = {
+	.has_phy_clk = true,
+	.has_second_pll = true,
+	.phy_init = &sun8i_hdmi_phy_init_h3,
+	.phy_disable = &sun8i_hdmi_phy_disable_h3,
+	.phy_config = &sun8i_hdmi_phy_config_h3,
+};
+
 static const struct sun8i_hdmi_phy_variant sun8i_a83t_hdmi_phy = {
 	.phy_init = &sun8i_hdmi_phy_init_a83t,
 	.phy_disable = &sun8i_hdmi_phy_disable_a83t,
@@ -410,6 +418,10 @@ static const struct sun8i_hdmi_phy_variant sun8i_h3_hdmi_phy = {
 };
 
 static const struct of_device_id sun8i_hdmi_phy_of_table[] = {
+	{
+		.compatible = "allwinner,sun50i-a64-hdmi-phy",
+		.data = &sun50i_a64_hdmi_phy,
+	},
 	{
 		.compatible = "allwinner,sun8i-a83t-hdmi-phy",
 		.data = &sun8i_a83t_hdmi_phy,
-- 
cgit v1.2.3


From 8b5f7a62464a24cb83d6290c01d6cf9c8871774a Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:03:01 +0200
Subject: drm: of: Export and rename drm_crtc_port_mask()

Function is useful when drm_of_find_possible_crtcs() can't be used and
custom parsing is needed. This can happen for example when there is a
node with multiple muxes between crtc and encoder.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
[maxime: change the function to have a consistent prefix]
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-22-jernej.skrabec@siol.net
---
 drivers/gpu/drm/drm_of.c | 9 +++++----
 include/drm/drm_of.h     | 8 ++++++++
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 1fe122461298..3b8c7a6a5720 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -15,15 +15,15 @@ static void drm_release_of(struct device *dev, void *data)
 }
 
 /**
- * drm_crtc_port_mask - find the mask of a registered CRTC by port OF node
+ * drm_of_crtc_port_mask - find the mask of a registered CRTC by port OF node
  * @dev: DRM device
  * @port: port OF node
  *
  * Given a port OF node, return the possible mask of the corresponding
  * CRTC within a device's list of CRTCs.  Returns zero if not found.
  */
-static uint32_t drm_crtc_port_mask(struct drm_device *dev,
-				   struct device_node *port)
+uint32_t drm_of_crtc_port_mask(struct drm_device *dev,
+			    struct device_node *port)
 {
 	unsigned int index = 0;
 	struct drm_crtc *tmp;
@@ -37,6 +37,7 @@ static uint32_t drm_crtc_port_mask(struct drm_device *dev,
 
 	return 0;
 }
+EXPORT_SYMBOL(drm_of_crtc_port_mask);
 
 /**
  * drm_of_find_possible_crtcs - find the possible CRTCs for an encoder port
@@ -62,7 +63,7 @@ uint32_t drm_of_find_possible_crtcs(struct drm_device *dev,
 			return 0;
 		}
 
-		possible_crtcs |= drm_crtc_port_mask(dev, remote_port);
+		possible_crtcs |= drm_of_crtc_port_mask(dev, remote_port);
 
 		of_node_put(remote_port);
 	}
diff --git a/include/drm/drm_of.h b/include/drm/drm_of.h
index b93c239afb60..ead34ab5ca4e 100644
--- a/include/drm/drm_of.h
+++ b/include/drm/drm_of.h
@@ -17,6 +17,8 @@ struct drm_bridge;
 struct device_node;
 
 #ifdef CONFIG_OF
+uint32_t drm_of_crtc_port_mask(struct drm_device *dev,
+			    struct device_node *port);
 uint32_t drm_of_find_possible_crtcs(struct drm_device *dev,
 				    struct device_node *port);
 void drm_of_component_match_add(struct device *master,
@@ -34,6 +36,12 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 				struct drm_panel **panel,
 				struct drm_bridge **bridge);
 #else
+static inline uint32_t drm_of_crtc_port_mask(struct drm_device *dev,
+					  struct device_node *port)
+{
+	return 0;
+}
+
 static inline uint32_t drm_of_find_possible_crtcs(struct drm_device *dev,
 						  struct device_node *port)
 {
-- 
cgit v1.2.3


From 57e23de02f4878061818fd118129a6b0e1516b11 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Mon, 25 Jun 2018 14:03:02 +0200
Subject: drm/sun4i: DW HDMI: Expand algorithm for possible crtcs

drm_of_find_possible_crtcs() doesn't work when DW HDMI encoder is
connected to TCON (crtc) through mux in TCON TOP.

In that case TCON TOP HDMI mux input port has to be manually traversed
and checked if it matches any known crtc.

Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625120304.7543-23-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c | 46 ++++++++++++++++++++++++++++++++++-
 1 file changed, 45 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index 9f40a44b456b..3459b9ec56c9 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -12,6 +12,7 @@
 #include <drm/drm_crtc_helper.h>
 
 #include "sun8i_dw_hdmi.h"
+#include "sun8i_tcon_top.h"
 
 static void sun8i_dw_hdmi_encoder_mode_set(struct drm_encoder *encoder,
 					   struct drm_display_mode *mode,
@@ -41,6 +42,48 @@ sun8i_dw_hdmi_mode_valid(struct drm_connector *connector,
 	return MODE_OK;
 }
 
+static bool sun8i_dw_hdmi_node_is_tcon_top(struct device_node *node)
+{
+	return !!of_match_node(sun8i_tcon_top_of_table, node);
+}
+
+static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
+					     struct device_node *node)
+{
+	struct device_node *port, *ep, *remote, *remote_port;
+	u32 crtcs = 0;
+
+	port = of_graph_get_port_by_id(node, 0);
+	if (!port)
+		return 0;
+
+	ep = of_get_next_available_child(port, NULL);
+	if (!ep)
+		return 0;
+
+	remote = of_graph_get_remote_port_parent(ep);
+	if (!remote)
+		return 0;
+
+	if (sun8i_dw_hdmi_node_is_tcon_top(remote)) {
+		port = of_graph_get_port_by_id(remote, 4);
+		if (!port)
+			return 0;
+
+		for_each_child_of_node(port, ep) {
+			remote_port = of_graph_get_remote_port(ep);
+			if (remote_port) {
+				crtcs |= drm_of_crtc_port_mask(drm, remote_port);
+				of_node_put(remote_port);
+			}
+		}
+	} else {
+		crtcs = drm_of_find_possible_crtcs(drm, node);
+	}
+
+	return crtcs;
+}
+
 static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master,
 			      void *data)
 {
@@ -63,7 +106,8 @@ static int sun8i_dw_hdmi_bind(struct device *dev, struct device *master,
 	hdmi->dev = &pdev->dev;
 	encoder = &hdmi->encoder;
 
-	encoder->possible_crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
+	encoder->possible_crtcs =
+		sun8i_dw_hdmi_find_possible_crtcs(drm, dev->of_node);
 	/*
 	 * If we failed to find the CRTC(s) which this encoder is
 	 * supposed to be connected to, it's because the CRTC has
-- 
cgit v1.2.3


From 3160422251b214c7a7a8ef91bb76da012bb44b57 Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Tue, 26 Jun 2018 13:52:23 -0700
Subject: drm/i915/icp: Add Interrupt Support

This patch addresses Interrupts from south display engine (SDE).

ICP has two registers - SHOTPLUG_CTL_DDI and SHOTPLUG_CTL_TC.
Introduce these registers and their intended values.

Introduce icp_irq_handler().

The icp_irq_postinstall() takes care of
enabling all PCH interrupt sources, to unmask
them as needed with SDEIMR, as is done
done by ibx_irq_pre_postinstall() for earlier platforms.
We do not need to explicitly call the ibx_irq_pre_postinstall().

Also, while changing these,
s/CPT/PPT/CPT-CNP comment.

v2:
- remove redundant register defines.(Lucas)
- Change register names to be more consistent with
previous platforms (Lucas)

v3:
-Reorder bit defines to a more appropriate location.
 Change the comments. Confirm in the commit message that
 icp_irq_postinstall() need not go to
 ibx_irq_pre_postinstall() and ibx_irq_postinstall()
 as in earlier platforms. (Paulo)

Cc: Lucas De Marchi <lucas.de.marchi@gmail.com>
Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
[Paulo: coding style bikesheds and rebases].
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530046343-30649-1-git-send-email-anusha.srivatsa@intel.com
---
 drivers/gpu/drm/i915/i915_irq.c | 134 +++++++++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h |  41 +++++++++++-
 2 files changed, 172 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 46aaef5c1851..7a7c4a2bd778 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -122,6 +122,15 @@ static const u32 hpd_gen11[HPD_NUM_PINS] = {
 	[HPD_PORT_F] = GEN11_TC4_HOTPLUG | GEN11_TBT4_HOTPLUG
 };
 
+static const u32 hpd_icp[HPD_NUM_PINS] = {
+	[HPD_PORT_A] = SDE_DDIA_HOTPLUG_ICP,
+	[HPD_PORT_B] = SDE_DDIB_HOTPLUG_ICP,
+	[HPD_PORT_C] = SDE_TC1_HOTPLUG_ICP,
+	[HPD_PORT_D] = SDE_TC2_HOTPLUG_ICP,
+	[HPD_PORT_E] = SDE_TC3_HOTPLUG_ICP,
+	[HPD_PORT_F] = SDE_TC4_HOTPLUG_ICP
+};
+
 /* IIR can theoretically queue up two events. Be paranoid. */
 #define GEN8_IRQ_RESET_NDX(type, which) do { \
 	I915_WRITE(GEN8_##type##_IMR(which), 0xffffffff); \
@@ -1586,6 +1595,34 @@ static bool bxt_port_hotplug_long_detect(enum port port, u32 val)
 	}
 }
 
+static bool icp_ddi_port_hotplug_long_detect(enum port port, u32 val)
+{
+	switch (port) {
+	case PORT_A:
+		return val & ICP_DDIA_HPD_LONG_DETECT;
+	case PORT_B:
+		return val & ICP_DDIB_HPD_LONG_DETECT;
+	default:
+		return false;
+	}
+}
+
+static bool icp_tc_port_hotplug_long_detect(enum port port, u32 val)
+{
+	switch (port) {
+	case PORT_C:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC1);
+	case PORT_D:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC2);
+	case PORT_E:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC3);
+	case PORT_F:
+		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC4);
+	default:
+		return false;
+	}
+}
+
 static bool spt_port_hotplug2_long_detect(enum port port, u32 val)
 {
 	switch (port) {
@@ -2385,6 +2422,43 @@ static void cpt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 		cpt_serr_int_handler(dev_priv);
 }
 
+static void icp_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
+{
+	u32 ddi_hotplug_trigger = pch_iir & SDE_DDI_MASK_ICP;
+	u32 tc_hotplug_trigger = pch_iir & SDE_TC_MASK_ICP;
+	u32 pin_mask = 0, long_mask = 0;
+
+	if (ddi_hotplug_trigger) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_DDI);
+		I915_WRITE(SHOTPLUG_CTL_DDI, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   ddi_hotplug_trigger,
+				   dig_hotplug_reg, hpd_icp,
+				   icp_ddi_port_hotplug_long_detect);
+	}
+
+	if (tc_hotplug_trigger) {
+		u32 dig_hotplug_reg;
+
+		dig_hotplug_reg = I915_READ(SHOTPLUG_CTL_TC);
+		I915_WRITE(SHOTPLUG_CTL_TC, dig_hotplug_reg);
+
+		intel_get_hpd_pins(dev_priv, &pin_mask, &long_mask,
+				   tc_hotplug_trigger,
+				   dig_hotplug_reg, hpd_icp,
+				   icp_tc_port_hotplug_long_detect);
+	}
+
+	if (pin_mask)
+		intel_hpd_irq_handler(dev_priv, pin_mask, long_mask);
+
+	if (pch_iir & SDE_GMBUS_ICP)
+		gmbus_irq_handler(dev_priv);
+}
+
 static void spt_irq_handler(struct drm_i915_private *dev_priv, u32 pch_iir)
 {
 	u32 hotplug_trigger = pch_iir & SDE_HOTPLUG_MASK_SPT &
@@ -2804,8 +2878,11 @@ gen8_de_irq_handler(struct drm_i915_private *dev_priv, u32 master_ctl)
 			I915_WRITE(SDEIIR, iir);
 			ret = IRQ_HANDLED;
 
-			if (HAS_PCH_SPT(dev_priv) || HAS_PCH_KBP(dev_priv) ||
-			    HAS_PCH_CNP(dev_priv))
+			if (HAS_PCH_ICP(dev_priv))
+				icp_irq_handler(dev_priv, iir);
+			else if (HAS_PCH_SPT(dev_priv) ||
+				 HAS_PCH_KBP(dev_priv) ||
+				 HAS_PCH_CNP(dev_priv))
 				spt_irq_handler(dev_priv, iir);
 			else
 				cpt_irq_handler(dev_priv, iir);
@@ -3584,6 +3661,9 @@ static void gen11_irq_reset(struct drm_device *dev)
 	GEN3_IRQ_RESET(GEN11_DE_HPD_);
 	GEN3_IRQ_RESET(GEN11_GU_MISC_);
 	GEN3_IRQ_RESET(GEN8_PCU_);
+
+	if (HAS_PCH_ICP(dev_priv))
+		GEN3_IRQ_RESET(SDE);
 }
 
 void gen8_irq_power_well_post_enable(struct drm_i915_private *dev_priv,
@@ -3700,6 +3780,35 @@ static void ibx_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	ibx_hpd_detection_setup(dev_priv);
 }
 
+static void icp_hpd_detection_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug;
+
+	hotplug = I915_READ(SHOTPLUG_CTL_DDI);
+	hotplug |= ICP_DDIA_HPD_ENABLE |
+		   ICP_DDIB_HPD_ENABLE;
+	I915_WRITE(SHOTPLUG_CTL_DDI, hotplug);
+
+	hotplug = I915_READ(SHOTPLUG_CTL_TC);
+	hotplug |= ICP_TC_HPD_ENABLE(PORT_TC1) |
+		   ICP_TC_HPD_ENABLE(PORT_TC2) |
+		   ICP_TC_HPD_ENABLE(PORT_TC3) |
+		   ICP_TC_HPD_ENABLE(PORT_TC4);
+	I915_WRITE(SHOTPLUG_CTL_TC, hotplug);
+}
+
+static void icp_hpd_irq_setup(struct drm_i915_private *dev_priv)
+{
+	u32 hotplug_irqs, enabled_irqs;
+
+	hotplug_irqs = SDE_DDI_MASK_ICP | SDE_TC_MASK_ICP;
+	enabled_irqs = intel_hpd_enabled_irqs(dev_priv, hpd_icp);
+
+	ibx_display_interrupt_update(dev_priv, hotplug_irqs, enabled_irqs);
+
+	icp_hpd_detection_setup(dev_priv);
+}
+
 static void gen11_hpd_detection_setup(struct drm_i915_private *dev_priv)
 {
 	u32 hotplug;
@@ -3733,6 +3842,9 @@ static void gen11_hpd_irq_setup(struct drm_i915_private *dev_priv)
 	POSTING_READ(GEN11_DE_HPD_IMR);
 
 	gen11_hpd_detection_setup(dev_priv);
+
+	if (HAS_PCH_ICP(dev_priv))
+		icp_hpd_irq_setup(dev_priv);
 }
 
 static void spt_hpd_detection_setup(struct drm_i915_private *dev_priv)
@@ -4168,11 +4280,29 @@ static void gen11_gt_irq_postinstall(struct drm_i915_private *dev_priv)
 	I915_WRITE(GEN11_GPM_WGBOXPERF_INTR_MASK,  ~0);
 }
 
+static void icp_irq_postinstall(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 mask = SDE_GMBUS_ICP;
+
+	WARN_ON(I915_READ(SDEIER) != 0);
+	I915_WRITE(SDEIER, 0xffffffff);
+	POSTING_READ(SDEIER);
+
+	gen3_assert_iir_is_zero(dev_priv, SDEIIR);
+	I915_WRITE(SDEIMR, ~mask);
+
+	icp_hpd_detection_setup(dev_priv);
+}
+
 static int gen11_irq_postinstall(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	u32 gu_misc_masked = GEN11_GU_MISC_GSE;
 
+	if (HAS_PCH_ICP(dev_priv))
+		icp_irq_postinstall(dev);
+
 	gen11_gt_irq_postinstall(dev_priv);
 	gen8_de_irq_postinstall(dev_priv);
 
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2c20dc0db648..c30cfcd90754 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7462,7 +7462,7 @@ enum {
 #define SDE_TRANSA_FIFO_UNDER	(1 << 0)
 #define SDE_TRANS_MASK		(0x3f)
 
-/* south display engine interrupt: CPT/PPT */
+/* south display engine interrupt: CPT - CNP */
 #define SDE_AUDIO_POWER_D_CPT	(1 << 31)
 #define SDE_AUDIO_POWER_C_CPT	(1 << 30)
 #define SDE_AUDIO_POWER_B_CPT	(1 << 29)
@@ -7510,6 +7510,21 @@ enum {
 				 SDE_FDI_RXB_CPT | \
 				 SDE_FDI_RXA_CPT)
 
+/* south display engine interrupt: ICP */
+#define SDE_TC4_HOTPLUG_ICP		(1 << 27)
+#define SDE_TC3_HOTPLUG_ICP		(1 << 26)
+#define SDE_TC2_HOTPLUG_ICP		(1 << 25)
+#define SDE_TC1_HOTPLUG_ICP		(1 << 24)
+#define SDE_GMBUS_ICP			(1 << 23)
+#define SDE_DDIB_HOTPLUG_ICP		(1 << 17)
+#define SDE_DDIA_HOTPLUG_ICP		(1 << 16)
+#define SDE_DDI_MASK_ICP		(SDE_DDIB_HOTPLUG_ICP |	\
+					 SDE_DDIA_HOTPLUG_ICP)
+#define SDE_TC_MASK_ICP			(SDE_TC4_HOTPLUG_ICP |	\
+					 SDE_TC3_HOTPLUG_ICP |	\
+					 SDE_TC2_HOTPLUG_ICP |	\
+					 SDE_TC1_HOTPLUG_ICP)
+
 #define SDEISR  _MMIO(0xc4000)
 #define SDEIMR  _MMIO(0xc4004)
 #define SDEIIR  _MMIO(0xc4008)
@@ -7570,6 +7585,30 @@ enum {
 #define  PORTE_HOTPLUG_SHORT_DETECT	(1 << 0)
 #define  PORTE_HOTPLUG_LONG_DETECT	(2 << 0)
 
+/* This register is a reuse of PCH_PORT_HOTPLUG register. The
+ * functionality covered in PCH_PORT_HOTPLUG is split into
+ * SHOTPLUG_CTL_DDI and SHOTPLUG_CTL_TC.
+ */
+
+#define SHOTPLUG_CTL_DDI			_MMIO(0xc4030)
+#define   ICP_DDIB_HPD_ENABLE			(1 << 7)
+#define   ICP_DDIB_HPD_STATUS_MASK		(3 << 4)
+#define   ICP_DDIB_HPD_NO_DETECT		(0 << 4)
+#define   ICP_DDIB_HPD_SHORT_DETECT		(1 << 4)
+#define   ICP_DDIB_HPD_LONG_DETECT		(2 << 4)
+#define   ICP_DDIB_HPD_SHORT_LONG_DETECT	(3 << 4)
+#define   ICP_DDIA_HPD_ENABLE			(1 << 3)
+#define   ICP_DDIA_HPD_STATUS_MASK		(3 << 0)
+#define   ICP_DDIA_HPD_NO_DETECT		(0 << 0)
+#define   ICP_DDIA_HPD_SHORT_DETECT		(1 << 0)
+#define   ICP_DDIA_HPD_LONG_DETECT		(2 << 0)
+#define   ICP_DDIA_HPD_SHORT_LONG_DETECT	(3 << 0)
+
+#define SHOTPLUG_CTL_TC				_MMIO(0xc4034)
+#define   ICP_TC_HPD_ENABLE(tc_port)		(8 << (tc_port) * 4)
+#define   ICP_TC_HPD_LONG_DETECT(tc_port)	(2 << (tc_port) * 4)
+#define   ICP_TC_HPD_SHORT_DETECT(tc_port)	(1 << (tc_port) * 4)
+
 #define PCH_GPIOA               _MMIO(0xc5010)
 #define PCH_GPIOB               _MMIO(0xc5014)
 #define PCH_GPIOC               _MMIO(0xc5018)
-- 
cgit v1.2.3


From feb20faec73ba0b30f949d54c4153cf0ad3807c8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 27 Jun 2018 09:03:51 +0200
Subject: ALSA: hda - Move in_pm accessors to HDA core

The in_pm atomic in hdac_device is an important field used as a flag
as well as a refcount for PM.  The existing snd_hdac_power_up/down
helpers already refer to it in the HD-audio core code, while the code
to actually setting the value (atomic_inc() / _dec()) is open-coded in
HDA legacy side, which is hard to find.

This patch adds the helper functions to set/reset the in_pm counter to
HDA core and use them in HDA legacy side, for making it clearer who /
where the PM is managed.

There is no functional changes, just code refactoring.

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio.h    | 27 +++++++++++++++++++++++++++
 sound/pci/hda/hda_codec.c  | 21 ++++++---------------
 sound/pci/hda/patch_hdmi.c |  2 +-
 3 files changed, 34 insertions(+), 16 deletions(-)

diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index c052afc27547..294a5a21937b 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -8,6 +8,7 @@
 
 #include <linux/device.h>
 #include <linux/interrupt.h>
+#include <linux/pm_runtime.h>
 #include <linux/timecounter.h>
 #include <sound/core.h>
 #include <sound/memalloc.h>
@@ -171,12 +172,38 @@ int snd_hdac_power_down(struct hdac_device *codec);
 int snd_hdac_power_up_pm(struct hdac_device *codec);
 int snd_hdac_power_down_pm(struct hdac_device *codec);
 int snd_hdac_keep_power_up(struct hdac_device *codec);
+
+/* call this at entering into suspend/resume callbacks in codec driver */
+static inline void snd_hdac_enter_pm(struct hdac_device *codec)
+{
+	atomic_inc(&codec->in_pm);
+}
+
+/* call this at leaving from suspend/resume callbacks in codec driver */
+static inline void snd_hdac_leave_pm(struct hdac_device *codec)
+{
+	atomic_dec(&codec->in_pm);
+}
+
+static inline bool snd_hdac_is_in_pm(struct hdac_device *codec)
+{
+	return atomic_read(&codec->in_pm);
+}
+
+static inline bool snd_hdac_is_power_on(struct hdac_device *codec)
+{
+	return !pm_runtime_suspended(&codec->dev);
+}
 #else
 static inline int snd_hdac_power_up(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_power_down(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_power_up_pm(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_power_down_pm(struct hdac_device *codec) { return 0; }
 static inline int snd_hdac_keep_power_up(struct hdac_device *codec) { return 0; }
+static inline void snd_hdac_enter_pm(struct hdac_device *codec) {}
+static inline void snd_hdac_leave_pm(struct hdac_device *codec) {}
+static inline bool snd_hdac_is_in_pm(struct hdac_device *codec) { return 0; }
+static inline bool snd_hdac_is_power_on(struct hdac_device *codec) { return 1; }
 #endif
 
 /*
diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index f42af88bd2de..decd46b51087 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -37,15 +37,8 @@
 #include "hda_jack.h"
 #include <sound/hda_hwdep.h>
 
-#ifdef CONFIG_PM
-#define codec_in_pm(codec)	atomic_read(&(codec)->core.in_pm)
-#define hda_codec_is_power_on(codec) \
-	(!pm_runtime_suspended(hda_codec_dev(codec)))
-#else
-#define codec_in_pm(codec)	0
-#define hda_codec_is_power_on(codec)	1
-#endif
-
+#define codec_in_pm(codec)		snd_hdac_is_in_pm(&codec->core)
+#define hda_codec_is_power_on(codec)	snd_hdac_is_power_on(&codec->core)
 #define codec_has_epss(codec) \
 	((codec)->core.power_caps & AC_PWRST_EPSS)
 #define codec_has_clkstop(codec) \
@@ -2846,14 +2839,13 @@ static unsigned int hda_call_codec_suspend(struct hda_codec *codec)
 {
 	unsigned int state;
 
-	atomic_inc(&codec->core.in_pm);
-
+	snd_hdac_enter_pm(&codec->core);
 	if (codec->patch_ops.suspend)
 		codec->patch_ops.suspend(codec);
 	hda_cleanup_all_streams(codec);
 	state = hda_set_power_state(codec, AC_PWRST_D3);
 	update_power_acct(codec, true);
-	atomic_dec(&codec->core.in_pm);
+	snd_hdac_leave_pm(&codec->core);
 	return state;
 }
 
@@ -2862,8 +2854,7 @@ static unsigned int hda_call_codec_suspend(struct hda_codec *codec)
  */
 static void hda_call_codec_resume(struct hda_codec *codec)
 {
-	atomic_inc(&codec->core.in_pm);
-
+	snd_hdac_enter_pm(&codec->core);
 	if (codec->core.regmap)
 		regcache_mark_dirty(codec->core.regmap);
 
@@ -2886,7 +2877,7 @@ static void hda_call_codec_resume(struct hda_codec *codec)
 		hda_jackpoll_work(&codec->jackpoll_work.work);
 	else
 		snd_hda_jack_report_sync(codec);
-	atomic_dec(&codec->core.in_pm);
+	snd_hdac_leave_pm(&codec->core);
 }
 
 static int hda_codec_runtime_suspend(struct device *dev)
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 8840daf9c6a3..ed2318f79e3c 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2489,7 +2489,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe)
 	if (snd_power_get_state(codec->card) != SNDRV_CTL_POWER_D0)
 		return;
 	/* ditto during suspend/resume process itself */
-	if (atomic_read(&(codec)->core.in_pm))
+	if (snd_hdac_is_in_pm(&codec->core))
 		return;
 
 	snd_hdac_i915_set_bclk(&codec->bus->core);
-- 
cgit v1.2.3


From a081e11536a716da3fd2b09061e75c09e691b2f8 Mon Sep 17 00:00:00 2001
From: Casey Leedom <leedom@chelsio.com>
Date: Tue, 26 Jun 2018 14:48:48 +0530
Subject: cxgb4: Add flag tc_flower_initialized

Add flag tc_flower_initialized to indicate the
completion if tc flower initialization.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h           | 1 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c | 8 ++++++++
 drivers/net/ethernet/chelsio/cxgb4/sched.c           | 3 +++
 3 files changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 1adb968b8354..f27b2f0ade0b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -957,6 +957,7 @@ struct adapter {
 	struct chcr_stats_debug chcr_stats;
 
 	/* TC flower offload */
+	bool tc_flower_initialized;
 	struct rhashtable flower_tbl;
 	struct rhashtable_params flower_ht_params;
 	struct timer_list flower_stats_timer;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
index 3ddd2c4acf68..623f73dd7738 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_tc_flower.c
@@ -874,6 +874,9 @@ int cxgb4_init_tc_flower(struct adapter *adap)
 {
 	int ret;
 
+	if (adap->tc_flower_initialized)
+		return -EEXIST;
+
 	adap->flower_ht_params = cxgb4_tc_flower_ht_params;
 	ret = rhashtable_init(&adap->flower_tbl, &adap->flower_ht_params);
 	if (ret)
@@ -882,13 +885,18 @@ int cxgb4_init_tc_flower(struct adapter *adap)
 	INIT_WORK(&adap->flower_stats_work, ch_flower_stats_handler);
 	timer_setup(&adap->flower_stats_timer, ch_flower_stats_cb, 0);
 	mod_timer(&adap->flower_stats_timer, jiffies + STATS_CHECK_PERIOD);
+	adap->tc_flower_initialized = true;
 	return 0;
 }
 
 void cxgb4_cleanup_tc_flower(struct adapter *adap)
 {
+	if (!adap->tc_flower_initialized)
+		return;
+
 	if (adap->flower_stats_timer.function)
 		del_timer_sync(&adap->flower_stats_timer);
 	cancel_work_sync(&adap->flower_stats_work);
 	rhashtable_destroy(&adap->flower_tbl);
+	adap->tc_flower_initialized = false;
 }
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sched.c b/drivers/net/ethernet/chelsio/cxgb4/sched.c
index 9148abb7994c..7fc656680299 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sched.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sched.c
@@ -539,6 +539,9 @@ void t4_cleanup_sched(struct adapter *adap)
 		struct port_info *pi = netdev2pinfo(adap->port[j]);
 
 		s = pi->sched_tbl;
+		if (!s)
+			continue;
+
 		for (i = 0; i < s->sched_size; i++) {
 			struct sched_class *e;
 
-- 
cgit v1.2.3


From 964fc35c0910c7970120f893fa866e6b3468dcf0 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Tue, 26 Jun 2018 14:51:13 +0530
Subject: cxgb4: Add new T5 PCI device id 0x50ae

Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index c7f8d0441278..e3adf435913e 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -188,6 +188,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x50ac), /* Custom T540-BT */
 	CH_PCI_ID_TABLE_FENTRY(0x50ad), /* Custom T520-CR */
+	CH_PCI_ID_TABLE_FENTRY(0x50ae), /* Custom T540-XL-SO */
 
 	/* T6 adapters:
 	 */
-- 
cgit v1.2.3


From dc96ee3730fc41d2d1efb4213c3a4656ed272e9e Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 26 Jun 2018 14:28:48 +0200
Subject: net: mscc: ocelot: add bonding support

Add link aggregation hardware offload support for Ocelot.

ocelot_get_link_ksettings() is not great but it does work until the driver
is reworked to switch to phylink.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 160 +++++++++++++++++++++++++++++++++++++
 drivers/net/ethernet/mscc/ocelot.h |   2 +-
 2 files changed, 161 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 776a8a9be8e3..6f05b69a6ca0 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -780,6 +780,8 @@ static const struct ethtool_ops ocelot_ethtool_ops = {
 	.get_strings		= ocelot_get_strings,
 	.get_ethtool_stats	= ocelot_get_ethtool_stats,
 	.get_sset_count		= ocelot_get_sset_count,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 static int ocelot_port_attr_get(struct net_device *dev,
@@ -1088,6 +1090,137 @@ static void ocelot_port_bridge_leave(struct ocelot_port *ocelot_port,
 		ocelot->hw_bridge_dev = NULL;
 }
 
+static void ocelot_set_aggr_pgids(struct ocelot *ocelot)
+{
+	int i, port, lag;
+
+	/* Reset destination and aggregation PGIDS */
+	for (port = 0; port < ocelot->num_phys_ports; port++)
+		ocelot_write_rix(ocelot, BIT(port), ANA_PGID_PGID, port);
+
+	for (i = PGID_AGGR; i < PGID_SRC; i++)
+		ocelot_write_rix(ocelot, GENMASK(ocelot->num_phys_ports - 1, 0),
+				 ANA_PGID_PGID, i);
+
+	/* Now, set PGIDs for each LAG */
+	for (lag = 0; lag < ocelot->num_phys_ports; lag++) {
+		unsigned long bond_mask;
+		int aggr_count = 0;
+		u8 aggr_idx[16];
+
+		bond_mask = ocelot->lags[lag];
+		if (!bond_mask)
+			continue;
+
+		for_each_set_bit(port, &bond_mask, ocelot->num_phys_ports) {
+			// Destination mask
+			ocelot_write_rix(ocelot, bond_mask,
+					 ANA_PGID_PGID, port);
+			aggr_idx[aggr_count] = port;
+			aggr_count++;
+		}
+
+		for (i = PGID_AGGR; i < PGID_SRC; i++) {
+			u32 ac;
+
+			ac = ocelot_read_rix(ocelot, ANA_PGID_PGID, i);
+			ac &= ~bond_mask;
+			ac |= BIT(aggr_idx[i % aggr_count]);
+			ocelot_write_rix(ocelot, ac, ANA_PGID_PGID, i);
+		}
+	}
+}
+
+static void ocelot_setup_lag(struct ocelot *ocelot, int lag)
+{
+	unsigned long bond_mask = ocelot->lags[lag];
+	unsigned int p;
+
+	for_each_set_bit(p, &bond_mask, ocelot->num_phys_ports) {
+		u32 port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p);
+
+		port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M;
+
+		/* Use lag port as logical port for port i */
+		ocelot_write_gix(ocelot, port_cfg |
+				 ANA_PORT_PORT_CFG_PORTID_VAL(lag),
+				 ANA_PORT_PORT_CFG, p);
+	}
+}
+
+static int ocelot_port_lag_join(struct ocelot_port *ocelot_port,
+				struct net_device *bond)
+{
+	struct ocelot *ocelot = ocelot_port->ocelot;
+	int p = ocelot_port->chip_port;
+	int lag, lp;
+	struct net_device *ndev;
+	u32 bond_mask = 0;
+
+	rcu_read_lock();
+	for_each_netdev_in_bond_rcu(bond, ndev) {
+		struct ocelot_port *port = netdev_priv(ndev);
+
+		bond_mask |= BIT(port->chip_port);
+	}
+	rcu_read_unlock();
+
+	lp = __ffs(bond_mask);
+
+	/* If the new port is the lowest one, use it as the logical port from
+	 * now on
+	 */
+	if (p == lp) {
+		lag = p;
+		ocelot->lags[p] = bond_mask;
+		bond_mask &= ~BIT(p);
+		if (bond_mask) {
+			lp = __ffs(bond_mask);
+			ocelot->lags[lp] = 0;
+		}
+	} else {
+		lag = lp;
+		ocelot->lags[lp] |= BIT(p);
+	}
+
+	ocelot_setup_lag(ocelot, lag);
+	ocelot_set_aggr_pgids(ocelot);
+
+	return 0;
+}
+
+static void ocelot_port_lag_leave(struct ocelot_port *ocelot_port,
+				  struct net_device *bond)
+{
+	struct ocelot *ocelot = ocelot_port->ocelot;
+	int p = ocelot_port->chip_port;
+	u32 port_cfg;
+	int i;
+
+	/* Remove port from any lag */
+	for (i = 0; i < ocelot->num_phys_ports; i++)
+		ocelot->lags[i] &= ~BIT(ocelot_port->chip_port);
+
+	/* if it was the logical port of the lag, move the lag config to the
+	 * next port
+	 */
+	if (ocelot->lags[p]) {
+		int n = __ffs(ocelot->lags[p]);
+
+		ocelot->lags[n] = ocelot->lags[p];
+		ocelot->lags[p] = 0;
+
+		ocelot_setup_lag(ocelot, n);
+	}
+
+	port_cfg = ocelot_read_gix(ocelot, ANA_PORT_PORT_CFG, p);
+	port_cfg &= ~ANA_PORT_PORT_CFG_PORTID_VAL_M;
+	ocelot_write_gix(ocelot, port_cfg | ANA_PORT_PORT_CFG_PORTID_VAL(p),
+			 ANA_PORT_PORT_CFG, p);
+
+	ocelot_set_aggr_pgids(ocelot);
+}
+
 /* Checks if the net_device instance given to us originate from our driver. */
 static bool ocelot_netdevice_dev_check(const struct net_device *dev)
 {
@@ -1114,6 +1247,14 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 				ocelot_port_bridge_leave(ocelot_port,
 							 info->upper_dev);
 		}
+		if (netif_is_lag_master(info->upper_dev)) {
+			if (info->linking)
+				err = ocelot_port_lag_join(ocelot_port,
+							   info->upper_dev);
+			else
+				ocelot_port_lag_leave(ocelot_port,
+						      info->upper_dev);
+		}
 		break;
 	default:
 		break;
@@ -1129,6 +1270,20 @@ static int ocelot_netdevice_event(struct notifier_block *unused,
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	int ret = 0;
 
+	if (event == NETDEV_PRECHANGEUPPER &&
+	    netif_is_lag_master(info->upper_dev)) {
+		struct netdev_lag_upper_info *lag_upper_info = info->upper_info;
+		struct netlink_ext_ack *extack;
+
+		if (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH) {
+			extack = netdev_notifier_info_to_extack(&info->info);
+			NL_SET_ERR_MSG_MOD(extack, "LAG device using unsupported Tx type");
+
+			ret = -EINVAL;
+			goto notify;
+		}
+	}
+
 	if (netif_is_lag_master(dev)) {
 		struct net_device *slave;
 		struct list_head *iter;
@@ -1201,6 +1356,11 @@ int ocelot_init(struct ocelot *ocelot)
 	int i, cpu = ocelot->num_phys_ports;
 	char queue_name[32];
 
+	ocelot->lags = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports,
+				    sizeof(u32), GFP_KERNEL);
+	if (!ocelot->lags)
+		return -ENOMEM;
+
 	ocelot->stats = devm_kcalloc(ocelot->dev,
 				     ocelot->num_phys_ports * ocelot->num_stats,
 				     sizeof(u64), GFP_KERNEL);
diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h
index 097bd12a10d4..616bec30dfa3 100644
--- a/drivers/net/ethernet/mscc/ocelot.h
+++ b/drivers/net/ethernet/mscc/ocelot.h
@@ -493,7 +493,7 @@ struct ocelot {
 	u8 num_cpu_ports;
 	struct ocelot_port **ports;
 
-	u16 lags[16];
+	u32 *lags;
 
 	/* Keep track of the vlan port masks */
 	u32 vlan_mask[VLAN_N_VID];
-- 
cgit v1.2.3


From 7142529f168846065eaf4e8126e3de7c8ffc292d Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Tue, 26 Jun 2018 14:28:49 +0200
Subject: net: mscc: ocelot: add VLAN filtering

Add hardware VLAN filtering offloading on ocelot.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c | 285 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 283 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 6f05b69a6ca0..1a4f2bb48ead 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -148,12 +148,191 @@ static inline int ocelot_vlant_wait_for_completion(struct ocelot *ocelot)
 	return 0;
 }
 
+static int ocelot_vlant_set_mask(struct ocelot *ocelot, u16 vid, u32 mask)
+{
+	/* Select the VID to configure */
+	ocelot_write(ocelot, ANA_TABLES_VLANTIDX_V_INDEX(vid),
+		     ANA_TABLES_VLANTIDX);
+	/* Set the vlan port members mask and issue a write command */
+	ocelot_write(ocelot, ANA_TABLES_VLANACCESS_VLAN_PORT_MASK(mask) |
+			     ANA_TABLES_VLANACCESS_CMD_WRITE,
+		     ANA_TABLES_VLANACCESS);
+
+	return ocelot_vlant_wait_for_completion(ocelot);
+}
+
+static void ocelot_vlan_mode(struct ocelot_port *port,
+			     netdev_features_t features)
+{
+	struct ocelot *ocelot = port->ocelot;
+	u8 p = port->chip_port;
+	u32 val;
+
+	/* Filtering */
+	val = ocelot_read(ocelot, ANA_VLANMASK);
+	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		val |= BIT(p);
+	else
+		val &= ~BIT(p);
+	ocelot_write(ocelot, val, ANA_VLANMASK);
+}
+
+static void ocelot_vlan_port_apply(struct ocelot *ocelot,
+				   struct ocelot_port *port)
+{
+	u32 val;
+
+	/* Ingress clasification (ANA_PORT_VLAN_CFG) */
+	/* Default vlan to clasify for untagged frames (may be zero) */
+	val = ANA_PORT_VLAN_CFG_VLAN_VID(port->pvid);
+	if (port->vlan_aware)
+		val |= ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1);
+
+	ocelot_rmw_gix(ocelot, val,
+		       ANA_PORT_VLAN_CFG_VLAN_VID_M |
+		       ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
+		       ANA_PORT_VLAN_CFG, port->chip_port);
+
+	/* Drop frames with multicast source address */
+	val = ANA_PORT_DROP_CFG_DROP_MC_SMAC_ENA;
+	if (port->vlan_aware && !port->vid)
+		/* If port is vlan-aware and tagged, drop untagged and priority
+		 * tagged frames.
+		 */
+		val |= ANA_PORT_DROP_CFG_DROP_UNTAGGED_ENA |
+		       ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
+		       ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
+	ocelot_write_gix(ocelot, val, ANA_PORT_DROP_CFG, port->chip_port);
+
+	/* Egress configuration (REW_TAG_CFG): VLAN tag type to 8021Q. */
+	val = REW_TAG_CFG_TAG_TPID_CFG(0);
+
+	if (port->vlan_aware) {
+		if (port->vid)
+			/* Tag all frames except when VID == DEFAULT_VLAN */
+			val |= REW_TAG_CFG_TAG_CFG(1);
+		else
+			/* Tag all frames */
+			val |= REW_TAG_CFG_TAG_CFG(3);
+	}
+	ocelot_rmw_gix(ocelot, val,
+		       REW_TAG_CFG_TAG_TPID_CFG_M |
+		       REW_TAG_CFG_TAG_CFG_M,
+		       REW_TAG_CFG, port->chip_port);
+
+	/* Set default VLAN and tag type to 8021Q. */
+	val = REW_PORT_VLAN_CFG_PORT_TPID(ETH_P_8021Q) |
+	      REW_PORT_VLAN_CFG_PORT_VID(port->vid);
+	ocelot_rmw_gix(ocelot, val,
+		       REW_PORT_VLAN_CFG_PORT_TPID_M |
+		       REW_PORT_VLAN_CFG_PORT_VID_M,
+		       REW_PORT_VLAN_CFG, port->chip_port);
+}
+
+static int ocelot_vlan_vid_add(struct net_device *dev, u16 vid, bool pvid,
+			       bool untagged)
+{
+	struct ocelot_port *port = netdev_priv(dev);
+	struct ocelot *ocelot = port->ocelot;
+	int ret;
+
+	/* Add the port MAC address to with the right VLAN information */
+	ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, vid,
+			  ENTRYTYPE_LOCKED);
+
+	/* Make the port a member of the VLAN */
+	ocelot->vlan_mask[vid] |= BIT(port->chip_port);
+	ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+	if (ret)
+		return ret;
+
+	/* Default ingress vlan classification */
+	if (pvid)
+		port->pvid = vid;
+
+	/* Untagged egress vlan clasification */
+	if (untagged)
+		port->vid = vid;
+
+	ocelot_vlan_port_apply(ocelot, port);
+
+	return 0;
+}
+
+static int ocelot_vlan_vid_del(struct net_device *dev, u16 vid)
+{
+	struct ocelot_port *port = netdev_priv(dev);
+	struct ocelot *ocelot = port->ocelot;
+	int ret;
+
+	/* 8021q removes VID 0 on module unload for all interfaces
+	 * with VLAN filtering feature. We need to keep it to receive
+	 * untagged traffic.
+	 */
+	if (vid == 0)
+		return 0;
+
+	/* Del the port MAC address to with the right VLAN information */
+	ocelot_mact_forget(ocelot, dev->dev_addr, vid);
+
+	/* Stop the port from being a member of the vlan */
+	ocelot->vlan_mask[vid] &= ~BIT(port->chip_port);
+	ret = ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+	if (ret)
+		return ret;
+
+	/* Ingress */
+	if (port->pvid == vid)
+		port->pvid = 0;
+
+	/* Egress */
+	if (port->vid == vid)
+		port->vid = 0;
+
+	ocelot_vlan_port_apply(ocelot, port);
+
+	return 0;
+}
+
 static void ocelot_vlan_init(struct ocelot *ocelot)
 {
+	u16 port, vid;
+
 	/* Clear VLAN table, by default all ports are members of all VLANs */
 	ocelot_write(ocelot, ANA_TABLES_VLANACCESS_CMD_INIT,
 		     ANA_TABLES_VLANACCESS);
 	ocelot_vlant_wait_for_completion(ocelot);
+
+	/* Configure the port VLAN memberships */
+	for (vid = 1; vid < VLAN_N_VID; vid++) {
+		ocelot->vlan_mask[vid] = 0;
+		ocelot_vlant_set_mask(ocelot, vid, ocelot->vlan_mask[vid]);
+	}
+
+	/* Because VLAN filtering is enabled, we need VID 0 to get untagged
+	 * traffic.  It is added automatically if 8021q module is loaded, but
+	 * we can't rely on it since module may be not loaded.
+	 */
+	ocelot->vlan_mask[0] = GENMASK(ocelot->num_phys_ports - 1, 0);
+	ocelot_vlant_set_mask(ocelot, 0, ocelot->vlan_mask[0]);
+
+	/* Configure the CPU port to be VLAN aware */
+	ocelot_write_gix(ocelot, ANA_PORT_VLAN_CFG_VLAN_VID(0) |
+				 ANA_PORT_VLAN_CFG_VLAN_AWARE_ENA |
+				 ANA_PORT_VLAN_CFG_VLAN_POP_CNT(1),
+			 ANA_PORT_VLAN_CFG, ocelot->num_phys_ports);
+
+	/* Set vlan ingress filter mask to all ports but the CPU port by
+	 * default.
+	 */
+	ocelot_write(ocelot, GENMASK(9, 0), ANA_VLANMASK);
+
+	for (port = 0; port < ocelot->num_phys_ports; port++) {
+		ocelot_write_gix(ocelot, 0, REW_PORT_VLAN_CFG, port);
+		ocelot_write_gix(ocelot, 0, REW_TAG_CFG, port);
+	}
 }
 
 /* Watermark encode
@@ -539,6 +718,20 @@ static int ocelot_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 	struct ocelot_port *port = netdev_priv(dev);
 	struct ocelot *ocelot = port->ocelot;
 
+	if (!vid) {
+		if (!port->vlan_aware)
+			/* If the bridge is not VLAN aware and no VID was
+			 * provided, set it to pvid to ensure the MAC entry
+			 * matches incoming untagged packets
+			 */
+			vid = port->pvid;
+		else
+			/* If the bridge is VLAN aware a VID must be provided as
+			 * otherwise the learnt entry wouldn't match any frame.
+			 */
+			return -EINVAL;
+	}
+
 	return ocelot_mact_learn(ocelot, port->chip_port, addr, vid,
 				 ENTRYTYPE_NORMAL);
 }
@@ -690,6 +883,30 @@ end:
 	return ret;
 }
 
+static int ocelot_vlan_rx_add_vid(struct net_device *dev, __be16 proto,
+				  u16 vid)
+{
+	return ocelot_vlan_vid_add(dev, vid, false, true);
+}
+
+static int ocelot_vlan_rx_kill_vid(struct net_device *dev, __be16 proto,
+				   u16 vid)
+{
+	return ocelot_vlan_vid_del(dev, vid);
+}
+
+static int ocelot_set_features(struct net_device *dev,
+			       netdev_features_t features)
+{
+	struct ocelot_port *port = netdev_priv(dev);
+	netdev_features_t changed = dev->features ^ features;
+
+	if (changed & NETIF_F_HW_VLAN_CTAG_FILTER)
+		ocelot_vlan_mode(port, features);
+
+	return 0;
+}
+
 static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_open			= ocelot_port_open,
 	.ndo_stop			= ocelot_port_stop,
@@ -701,6 +918,9 @@ static const struct net_device_ops ocelot_port_netdev_ops = {
 	.ndo_fdb_add			= ocelot_fdb_add,
 	.ndo_fdb_del			= ocelot_fdb_del,
 	.ndo_fdb_dump			= ocelot_fdb_dump,
+	.ndo_vlan_rx_add_vid		= ocelot_vlan_rx_add_vid,
+	.ndo_vlan_rx_kill_vid		= ocelot_vlan_rx_kill_vid,
+	.ndo_set_features		= ocelot_set_features,
 };
 
 static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data)
@@ -916,6 +1136,10 @@ static int ocelot_port_attr_set(struct net_device *dev,
 	case SWITCHDEV_ATTR_ID_BRIDGE_AGEING_TIME:
 		ocelot_port_attr_ageing_set(ocelot_port, attr->u.ageing_time);
 		break;
+	case SWITCHDEV_ATTR_ID_BRIDGE_VLAN_FILTERING:
+		ocelot_port->vlan_aware = attr->u.vlan_filtering;
+		ocelot_vlan_port_apply(ocelot_port->ocelot, ocelot_port);
+		break;
 	case SWITCHDEV_ATTR_ID_BRIDGE_MC_DISABLED:
 		ocelot_port_attr_mc_set(ocelot_port, !attr->u.mc_disabled);
 		break;
@@ -927,6 +1151,40 @@ static int ocelot_port_attr_set(struct net_device *dev,
 	return err;
 }
 
+static int ocelot_port_obj_add_vlan(struct net_device *dev,
+				    const struct switchdev_obj_port_vlan *vlan,
+				    struct switchdev_trans *trans)
+{
+	int ret;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		ret = ocelot_vlan_vid_add(dev, vid,
+					  vlan->flags & BRIDGE_VLAN_INFO_PVID,
+					  vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int ocelot_port_vlan_del_vlan(struct net_device *dev,
+				     const struct switchdev_obj_port_vlan *vlan)
+{
+	int ret;
+	u16 vid;
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; vid++) {
+		ret = ocelot_vlan_vid_del(dev, vid);
+
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static struct ocelot_multicast *ocelot_multicast_get(struct ocelot *ocelot,
 						     const unsigned char *addr,
 						     u16 vid)
@@ -953,7 +1211,7 @@ static int ocelot_port_obj_add_mdb(struct net_device *dev,
 	bool new = false;
 
 	if (!vid)
-		vid = 1;
+		vid = port->pvid;
 
 	mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
 	if (!mc) {
@@ -994,7 +1252,7 @@ static int ocelot_port_obj_del_mdb(struct net_device *dev,
 	u16 vid = mdb->vid;
 
 	if (!vid)
-		vid = 1;
+		vid = port->pvid;
 
 	mc = ocelot_multicast_get(ocelot, mdb->addr, vid);
 	if (!mc)
@@ -1026,6 +1284,11 @@ static int ocelot_port_obj_add(struct net_device *dev,
 	int ret = 0;
 
 	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		ret = ocelot_port_obj_add_vlan(dev,
+					       SWITCHDEV_OBJ_PORT_VLAN(obj),
+					       trans);
+		break;
 	case SWITCHDEV_OBJ_ID_PORT_MDB:
 		ret = ocelot_port_obj_add_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj),
 					      trans);
@@ -1043,6 +1306,10 @@ static int ocelot_port_obj_del(struct net_device *dev,
 	int ret = 0;
 
 	switch (obj->id) {
+	case SWITCHDEV_OBJ_ID_PORT_VLAN:
+		ret = ocelot_port_vlan_del_vlan(dev,
+						SWITCHDEV_OBJ_PORT_VLAN(obj));
+		break;
 	case SWITCHDEV_OBJ_ID_PORT_MDB:
 		ret = ocelot_port_obj_del_mdb(dev, SWITCHDEV_OBJ_PORT_MDB(obj));
 		break;
@@ -1088,6 +1355,11 @@ static void ocelot_port_bridge_leave(struct ocelot_port *ocelot_port,
 
 	if (!ocelot->bridge_mask)
 		ocelot->hw_bridge_dev = NULL;
+
+	/* Clear bridge vlan settings before calling ocelot_vlan_port_apply */
+	ocelot_port->vlan_aware = 0;
+	ocelot_port->pvid = 0;
+	ocelot_port->vid = 0;
 }
 
 static void ocelot_set_aggr_pgids(struct ocelot *ocelot)
@@ -1246,6 +1518,9 @@ static int ocelot_netdevice_port_event(struct net_device *dev,
 			else
 				ocelot_port_bridge_leave(ocelot_port,
 							 info->upper_dev);
+
+			ocelot_vlan_port_apply(ocelot_port->ocelot,
+					       ocelot_port);
 		}
 		if (netif_is_lag_master(info->upper_dev)) {
 			if (info->linking)
@@ -1331,6 +1606,9 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 	dev->ethtool_ops = &ocelot_ethtool_ops;
 	dev->switchdev_ops = &ocelot_port_switchdev_ops;
 
+	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+
 	memcpy(dev->dev_addr, ocelot->base_mac, ETH_ALEN);
 	dev->dev_addr[ETH_ALEN - 1] += port;
 	ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid,
@@ -1342,6 +1620,9 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port,
 		goto err_register_netdev;
 	}
 
+	/* Basic L2 initialization */
+	ocelot_vlan_port_apply(ocelot, ocelot_port);
+
 	return 0;
 
 err_register_netdev:
-- 
cgit v1.2.3


From 5092ad4dd52dddc9957ebb8adde99f7a22c29f6a Mon Sep 17 00:00:00 2001
From: Keara Leibovitz <kleib@mojatatu.com>
Date: Tue, 26 Jun 2018 10:16:28 -0400
Subject: tc-tests: add an extreme-case csum action test

Added an extreme-case test for all 7 csum action headers.

Signed-off-by: Keara Leibovitz <kleib@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/csum.json          | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
index 3a2f51fc7fd4..a022792d392a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json
@@ -335,6 +335,30 @@
             "$TC actions flush action csum"
         ]
     },
+    {
+        "id": "b10b",
+        "name": "Add all 7 csum actions",
+        "category": [
+            "actions",
+            "csum"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action csum",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action csum icmp ip4h sctp igmp udplite udp tcp index 7",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action csum index 7",
+        "matchPattern": "action order [0-9]*: csum \\(iph, icmp, igmp, tcp, udp, udplite, sctp\\).*index 7 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action csum"
+        ]
+    },
     {
         "id": "ce92",
         "name": "Add csum udp action with cookie",
-- 
cgit v1.2.3


From 3787a39852b0d6a9e67336f8fb5815c13ab78bb6 Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Fri, 1 Jun 2018 22:53:49 -0500
Subject: ALSA: hdac: Remove usage of struct hdac_ext_device and use
 hdac_device instead

This patch removes the hdac_ext_device structure. The legacy and
enhanced HDaudio capabilities can be handled in a backward-compatible
way without separate definitions.

Follow-up patches in this series handle the bus and driver definitions.

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio_ext.h  |  36 +---
 sound/hda/ext/hdac_ext_bus.c |  25 ++-
 sound/soc/codecs/hdac_hdmi.c | 396 +++++++++++++++++++++----------------------
 3 files changed, 204 insertions(+), 253 deletions(-)

diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index 9c14e21dda85..c1a5ad0e6e39 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -181,48 +181,20 @@ struct hda_dai_map {
 	u32	maxbps;
 };
 
-#define HDA_MAX_NIDS 16
-
-/**
- * struct hdac_ext_device - HDAC Ext device
- *
- * @hdac: hdac core device
- * @nid_list - the dai map which matches the dai-name with the nid
- * @map_cur_idx - the idx in use in dai_map
- * @ops - the hda codec ops common to all codec drivers
- * @pvt_data - private data, for asoc contains asoc codec object
- */
-struct hdac_ext_device {
-	struct hdac_device hdev;
-	struct hdac_ext_bus *ebus;
-
-	/* soc-dai to nid map */
-	struct hda_dai_map nid_list[HDA_MAX_NIDS];
-	unsigned int map_cur_idx;
-
-	/* codec ops */
-	struct hdac_ext_codec_ops ops;
-
-	struct snd_card *card;
-	void *scodec;
-	void *private_data;
-};
-
 struct hdac_ext_dma_params {
 	u32 format;
 	u8 stream_tag;
 };
-#define to_ehdac_device(dev) (container_of((dev), \
-				 struct hdac_ext_device, hdev))
+
 /*
  * HD-audio codec base driver
  */
 struct hdac_ext_driver {
 	struct hdac_driver hdac;
 
-	int	(*probe)(struct hdac_ext_device *dev);
-	int	(*remove)(struct hdac_ext_device *dev);
-	void	(*shutdown)(struct hdac_ext_device *dev);
+	int	(*probe)(struct hdac_device *dev);
+	int	(*remove)(struct hdac_device *dev);
+	void	(*shutdown)(struct hdac_device *dev);
 };
 
 int snd_hda_ext_driver_register(struct hdac_ext_driver *drv);
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index 0daf31383084..0e4823fdd411 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -137,17 +137,16 @@ static void default_release(struct device *dev)
  */
 int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *ebus, int addr)
 {
-	struct hdac_ext_device *edev;
 	struct hdac_device *hdev = NULL;
 	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	char name[15];
 	int ret;
 
-	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
-	if (!edev)
+	hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
+	if (!hdev)
 		return -ENOMEM;
-	hdev = &edev->hdev;
-	edev->ebus = ebus;
+
+	hdev->bus = bus;
 
 	snprintf(name, sizeof(name), "ehdaudio%dD%d", ebus->idx, addr);
 
@@ -176,10 +175,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_init);
  */
 void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev)
 {
-	struct hdac_ext_device *edev = to_ehdac_device(hdev);
-
 	snd_hdac_device_exit(hdev);
-	kfree(edev);
+	kfree(hdev);
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_exit);
 
@@ -212,27 +209,25 @@ static inline struct hdac_ext_driver *get_edrv(struct device *dev)
 	return edrv;
 }
 
-static inline struct hdac_ext_device *get_edev(struct device *dev)
+static inline struct hdac_device *get_hdev(struct device *dev)
 {
 	struct hdac_device *hdev = dev_to_hdac_dev(dev);
-	struct hdac_ext_device *edev = to_ehdac_device(hdev);
-
-	return edev;
+	return hdev;
 }
 
 static int hda_ext_drv_probe(struct device *dev)
 {
-	return (get_edrv(dev))->probe(get_edev(dev));
+	return (get_edrv(dev))->probe(get_hdev(dev));
 }
 
 static int hdac_ext_drv_remove(struct device *dev)
 {
-	return (get_edrv(dev))->remove(get_edev(dev));
+	return (get_edrv(dev))->remove(get_hdev(dev));
 }
 
 static void hdac_ext_drv_shutdown(struct device *dev)
 {
-	return (get_edrv(dev))->shutdown(get_edev(dev));
+	return (get_edrv(dev))->shutdown(get_hdev(dev));
 }
 
 /**
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 84f7a7a36e4b..f1e235817a65 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -85,7 +85,7 @@ struct hdac_hdmi_pin {
 	bool mst_capable;
 	struct hdac_hdmi_port *ports;
 	int num_ports;
-	struct hdac_ext_device *edev;
+	struct hdac_device *hdev;
 };
 
 struct hdac_hdmi_port {
@@ -126,6 +126,9 @@ struct hdac_hdmi_drv_data {
 };
 
 struct hdac_hdmi_priv {
+	struct hdac_device *hdev;
+	struct snd_soc_component *component;
+	struct snd_card *card;
 	struct hdac_hdmi_dai_port_map dai_map[HDA_MAX_CVTS];
 	struct list_head pin_list;
 	struct list_head cvt_list;
@@ -139,7 +142,7 @@ struct hdac_hdmi_priv {
 	struct snd_soc_dai_driver *dai_drv;
 };
 
-#define hdev_to_hdmi_priv(_hdev) ((to_ehdac_device(_hdev))->private_data)
+#define hdev_to_hdmi_priv(_hdev) dev_get_drvdata(&(_hdev)->dev)
 
 static struct hdac_hdmi_pcm *
 hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi,
@@ -158,7 +161,7 @@ hdac_hdmi_get_pcm_from_cvt(struct hdac_hdmi_priv *hdmi,
 static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
 		struct hdac_hdmi_port *port, bool is_connect)
 {
-	struct hdac_ext_device *edev = port->pin->edev;
+	struct hdac_device *hdev = port->pin->hdev;
 
 	if (is_connect)
 		snd_soc_dapm_enable_pin(port->dapm, port->jack_pin);
@@ -172,7 +175,7 @@ static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
 		 * ports.
 		 */
 		if (pcm->jack_event == 0) {
-			dev_dbg(&edev->hdev.dev,
+			dev_dbg(&hdev->dev,
 					"jack report for pcm=%d\n",
 					pcm->pcm_id);
 			snd_soc_jack_report(pcm->jack, SND_JACK_AVOUT,
@@ -198,19 +201,18 @@ static void hdac_hdmi_jack_report(struct hdac_hdmi_pcm *pcm,
 /*
  * Get the no devices that can be connected to a port on the Pin widget.
  */
-static int hdac_hdmi_get_port_len(struct hdac_ext_device *edev, hda_nid_t nid)
+static int hdac_hdmi_get_port_len(struct hdac_device *hdev, hda_nid_t nid)
 {
 	unsigned int caps;
 	unsigned int type, param;
 
-	caps = get_wcaps(&edev->hdev, nid);
+	caps = get_wcaps(hdev, nid);
 	type = get_wcaps_type(caps);
 
 	if (!(caps & AC_WCAP_DIGITAL) || (type != AC_WID_PIN))
 		return 0;
 
-	param = snd_hdac_read_parm_uncached(&edev->hdev, nid,
-					AC_PAR_DEVLIST_LEN);
+	param = snd_hdac_read_parm_uncached(hdev, nid, AC_PAR_DEVLIST_LEN);
 	if (param == -1)
 		return param;
 
@@ -222,10 +224,10 @@ static int hdac_hdmi_get_port_len(struct hdac_ext_device *edev, hda_nid_t nid)
  * id selected on the pin. Return 0 means the first port entry
  * is selected or MST is not supported.
  */
-static int hdac_hdmi_port_select_get(struct hdac_ext_device *edev,
+static int hdac_hdmi_port_select_get(struct hdac_device *hdev,
 					struct hdac_hdmi_port *port)
 {
-	return snd_hdac_codec_read(&edev->hdev, port->pin->nid,
+	return snd_hdac_codec_read(hdev, port->pin->nid,
 				0, AC_VERB_GET_DEVICE_SEL, 0);
 }
 
@@ -233,7 +235,7 @@ static int hdac_hdmi_port_select_get(struct hdac_ext_device *edev,
  * Sets the selected port entry for the configuring Pin widget verb.
  * returns error if port set is not equal to port get otherwise success
  */
-static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev,
+static int hdac_hdmi_port_select_set(struct hdac_device *hdev,
 					struct hdac_hdmi_port *port)
 {
 	int num_ports;
@@ -242,8 +244,7 @@ static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev,
 		return 0;
 
 	/* AC_PAR_DEVLIST_LEN is 0 based. */
-	num_ports = hdac_hdmi_get_port_len(edev, port->pin->nid);
-
+	num_ports = hdac_hdmi_get_port_len(hdev, port->pin->nid);
 	if (num_ports < 0)
 		return -EIO;
 	/*
@@ -253,13 +254,13 @@ static int hdac_hdmi_port_select_set(struct hdac_ext_device *edev,
 	if (num_ports + 1  < port->id)
 		return 0;
 
-	snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+	snd_hdac_codec_write(hdev, port->pin->nid, 0,
 			AC_VERB_SET_DEVICE_SEL, port->id);
 
-	if (port->id != hdac_hdmi_port_select_get(edev, port))
+	if (port->id != hdac_hdmi_port_select_get(hdev, port))
 		return -EIO;
 
-	dev_dbg(&edev->hdev.dev, "Selected the port=%d\n", port->id);
+	dev_dbg(&hdev->dev, "Selected the port=%d\n", port->id);
 
 	return 0;
 }
@@ -277,13 +278,6 @@ static struct hdac_hdmi_pcm *get_hdmi_pcm_from_id(struct hdac_hdmi_priv *hdmi,
 	return NULL;
 }
 
-static inline struct hdac_ext_device *to_hda_ext_device(struct device *dev)
-{
-	struct hdac_device *hdev = dev_to_hdac_dev(dev);
-
-	return to_ehdac_device(hdev);
-}
-
 static unsigned int sad_format(const u8 *sad)
 {
 	return ((sad[0] >> 0x3) & 0x1f);
@@ -324,15 +318,13 @@ format_constraint:
 }
 
 static void
-hdac_hdmi_set_dip_index(struct hdac_ext_device *edev, hda_nid_t pin_nid,
+hdac_hdmi_set_dip_index(struct hdac_device *hdev, hda_nid_t pin_nid,
 				int packet_index, int byte_index)
 {
 	int val;
 
 	val = (packet_index << 5) | (byte_index & 0x1f);
-
-	snd_hdac_codec_write(&edev->hdev, pin_nid, 0,
-				AC_VERB_SET_HDMI_DIP_INDEX, val);
+	snd_hdac_codec_write(hdev, pin_nid, 0, AC_VERB_SET_HDMI_DIP_INDEX, val);
 }
 
 struct dp_audio_infoframe {
@@ -347,14 +339,14 @@ struct dp_audio_infoframe {
 	u8 LFEPBL01_LSV36_DM_INH7;
 };
 
-static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev,
+static int hdac_hdmi_setup_audio_infoframe(struct hdac_device *hdev,
 		   struct hdac_hdmi_pcm *pcm, struct hdac_hdmi_port *port)
 {
 	uint8_t buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AUDIO_INFOFRAME_SIZE];
 	struct hdmi_audio_infoframe frame;
 	struct hdac_hdmi_pin *pin = port->pin;
 	struct dp_audio_infoframe dp_ai;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_cvt *cvt = pcm->cvt;
 	u8 *dip;
 	int ret;
@@ -363,11 +355,11 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev,
 	u8 conn_type;
 	int channels, ca;
 
-	ca = snd_hdac_channel_allocation(&edev->hdev, port->eld.info.spk_alloc,
+	ca = snd_hdac_channel_allocation(hdev, port->eld.info.spk_alloc,
 			pcm->channels, pcm->chmap_set, true, pcm->chmap);
 
 	channels = snd_hdac_get_active_channels(ca);
-	hdmi->chmap.ops.set_channel_count(&edev->hdev, cvt->nid, channels);
+	hdmi->chmap.ops.set_channel_count(hdev, cvt->nid, channels);
 
 	snd_hdac_setup_channel_mapping(&hdmi->chmap, pin->nid, false, ca,
 				pcm->channels, pcm->chmap, pcm->chmap_set);
@@ -400,32 +392,31 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *edev,
 		break;
 
 	default:
-		dev_err(&edev->hdev.dev, "Invalid connection type: %d\n",
-						conn_type);
+		dev_err(&hdev->dev, "Invalid connection type: %d\n", conn_type);
 		return -EIO;
 	}
 
 	/* stop infoframe transmission */
-	hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0);
-	snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+	hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0);
+	snd_hdac_codec_write(hdev, pin->nid, 0,
 			AC_VERB_SET_HDMI_DIP_XMIT, AC_DIPXMIT_DISABLE);
 
 
 	/*  Fill infoframe. Index auto-incremented */
-	hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0);
+	hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0);
 	if (conn_type == DRM_ELD_CONN_TYPE_HDMI) {
 		for (i = 0; i < sizeof(buffer); i++)
-			snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+			snd_hdac_codec_write(hdev, pin->nid, 0,
 				AC_VERB_SET_HDMI_DIP_DATA, buffer[i]);
 	} else {
 		for (i = 0; i < sizeof(dp_ai); i++)
-			snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+			snd_hdac_codec_write(hdev, pin->nid, 0,
 				AC_VERB_SET_HDMI_DIP_DATA, dip[i]);
 	}
 
 	/* Start infoframe */
-	hdac_hdmi_set_dip_index(edev, pin->nid, 0x0, 0x0);
-	snd_hdac_codec_write(&edev->hdev, pin->nid, 0,
+	hdac_hdmi_set_dip_index(hdev, pin->nid, 0x0, 0x0);
+	snd_hdac_codec_write(hdev, pin->nid, 0,
 			AC_VERB_SET_HDMI_DIP_XMIT, AC_DIPXMIT_BEST);
 
 	return 0;
@@ -435,12 +426,12 @@ static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai,
 		unsigned int tx_mask, unsigned int rx_mask,
 		int slots, int slot_width)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_pcm *pcm;
 
-	dev_dbg(&edev->hdev.dev, "%s: strm_tag: %d\n", __func__, tx_mask);
+	dev_dbg(&hdev->dev, "%s: strm_tag: %d\n", __func__, tx_mask);
 
 	dai_map = &hdmi->dai_map[dai->id];
 
@@ -455,8 +446,8 @@ static int hdac_hdmi_set_tdm_slot(struct snd_soc_dai *dai,
 static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *hparams, struct snd_soc_dai *dai)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_port *port;
 	struct hdac_hdmi_pcm *pcm;
@@ -469,7 +460,7 @@ static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream,
 		return -ENODEV;
 
 	if ((!port->eld.monitor_present) || (!port->eld.eld_valid)) {
-		dev_err(&edev->hdev.dev,
+		dev_err(&hdev->dev,
 			"device is not configured for this pin:port%d:%d\n",
 					port->pin->nid, port->id);
 		return -ENODEV;
@@ -489,28 +480,28 @@ static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream,
 	return 0;
 }
 
-static int hdac_hdmi_query_port_connlist(struct hdac_ext_device *edev,
+static int hdac_hdmi_query_port_connlist(struct hdac_device *hdev,
 					struct hdac_hdmi_pin *pin,
 					struct hdac_hdmi_port *port)
 {
-	if (!(get_wcaps(&edev->hdev, pin->nid) & AC_WCAP_CONN_LIST)) {
-		dev_warn(&edev->hdev.dev,
+	if (!(get_wcaps(hdev, pin->nid) & AC_WCAP_CONN_LIST)) {
+		dev_warn(&hdev->dev,
 			"HDMI: pin %d wcaps %#x does not support connection list\n",
-			pin->nid, get_wcaps(&edev->hdev, pin->nid));
+			pin->nid, get_wcaps(hdev, pin->nid));
 		return -EINVAL;
 	}
 
-	if (hdac_hdmi_port_select_set(edev, port) < 0)
+	if (hdac_hdmi_port_select_set(hdev, port) < 0)
 		return -EIO;
 
-	port->num_mux_nids = snd_hdac_get_connections(&edev->hdev, pin->nid,
+	port->num_mux_nids = snd_hdac_get_connections(hdev, pin->nid,
 			port->mux_nids, HDA_MAX_CONNECTIONS);
 	if (port->num_mux_nids == 0)
-		dev_warn(&edev->hdev.dev,
+		dev_warn(&hdev->dev,
 			"No connections found for pin:port %d:%d\n",
 						pin->nid, port->id);
 
-	dev_dbg(&edev->hdev.dev, "num_mux_nids %d for pin:port %d:%d\n",
+	dev_dbg(&hdev->dev, "num_mux_nids %d for pin:port %d:%d\n",
 			port->num_mux_nids, pin->nid, port->id);
 
 	return port->num_mux_nids;
@@ -526,7 +517,7 @@ static int hdac_hdmi_query_port_connlist(struct hdac_ext_device *edev,
  * connected.
  */
 static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt(
-			struct hdac_ext_device *edev,
+			struct hdac_device *hdev,
 			struct hdac_hdmi_priv *hdmi,
 			struct hdac_hdmi_cvt *cvt)
 {
@@ -541,7 +532,7 @@ static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt(
 
 			list_for_each_entry(port, &pcm->port_list, head) {
 				mutex_lock(&pcm->lock);
-				ret = hdac_hdmi_query_port_connlist(edev,
+				ret = hdac_hdmi_query_port_connlist(hdev,
 							port->pin, port);
 				mutex_unlock(&pcm->lock);
 				if (ret < 0)
@@ -568,8 +559,8 @@ static struct hdac_hdmi_port *hdac_hdmi_get_port_from_cvt(
 static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 			struct snd_soc_dai *dai)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_cvt *cvt;
 	struct hdac_hdmi_port *port;
@@ -578,7 +569,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 	dai_map = &hdmi->dai_map[dai->id];
 
 	cvt = dai_map->cvt;
-	port = hdac_hdmi_get_port_from_cvt(edev, hdmi, cvt);
+	port = hdac_hdmi_get_port_from_cvt(hdev, hdmi, cvt);
 
 	/*
 	 * To make PA and other userland happy.
@@ -589,7 +580,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 	if ((!port->eld.monitor_present) ||
 			(!port->eld.eld_valid)) {
 
-		dev_warn(&edev->hdev.dev,
+		dev_warn(&hdev->dev,
 			"Failed: present?:%d ELD valid?:%d pin:port: %d:%d\n",
 			port->eld.monitor_present, port->eld.eld_valid,
 			port->pin->nid, port->id);
@@ -611,8 +602,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 static void hdac_hdmi_pcm_close(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_device *edev = snd_soc_dai_get_drvdata(dai);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_dai_get_drvdata(dai);
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_pcm *pcm;
 
@@ -695,10 +685,10 @@ static void hdac_hdmi_fill_route(struct snd_soc_dapm_route *route,
 	route->connected = handler;
 }
 
-static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_ext_device *edev,
+static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_device *hdev,
 					struct hdac_hdmi_port *port)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm = NULL;
 	struct hdac_hdmi_port *p;
 
@@ -715,33 +705,32 @@ static struct hdac_hdmi_pcm *hdac_hdmi_get_pcm(struct hdac_ext_device *edev,
 	return NULL;
 }
 
-static void hdac_hdmi_set_power_state(struct hdac_ext_device *edev,
+static void hdac_hdmi_set_power_state(struct hdac_device *hdev,
 			     hda_nid_t nid, unsigned int pwr_state)
 {
 	int count;
 	unsigned int state;
 
-	if (get_wcaps(&edev->hdev, nid) & AC_WCAP_POWER) {
-		if (!snd_hdac_check_power_state(&edev->hdev, nid, pwr_state)) {
+	if (get_wcaps(hdev, nid) & AC_WCAP_POWER) {
+		if (!snd_hdac_check_power_state(hdev, nid, pwr_state)) {
 			for (count = 0; count < 10; count++) {
-				snd_hdac_codec_read(&edev->hdev, nid, 0,
+				snd_hdac_codec_read(hdev, nid, 0,
 						AC_VERB_SET_POWER_STATE,
 						pwr_state);
-				state = snd_hdac_sync_power_state(&edev->hdev,
+				state = snd_hdac_sync_power_state(hdev,
 						nid, pwr_state);
 				if (!(state & AC_PWRST_ERROR))
 					break;
 			}
 		}
-
 	}
 }
 
-static void hdac_hdmi_set_amp(struct hdac_ext_device *edev,
+static void hdac_hdmi_set_amp(struct hdac_device *hdev,
 				   hda_nid_t nid, int val)
 {
-	if (get_wcaps(&edev->hdev, nid) & AC_WCAP_OUT_AMP)
-		snd_hdac_codec_write(&edev->hdev, nid, 0,
+	if (get_wcaps(hdev, nid) & AC_WCAP_OUT_AMP)
+		snd_hdac_codec_write(hdev, nid, 0,
 					AC_VERB_SET_AMP_GAIN_MUTE, val);
 }
 
@@ -750,40 +739,40 @@ static int hdac_hdmi_pin_output_widget_event(struct snd_soc_dapm_widget *w,
 					struct snd_kcontrol *kc, int event)
 {
 	struct hdac_hdmi_port *port = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev);
+	struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev);
 	struct hdac_hdmi_pcm *pcm;
 
-	dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n",
+	dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n",
 			__func__, w->name, event);
 
-	pcm = hdac_hdmi_get_pcm(edev, port);
+	pcm = hdac_hdmi_get_pcm(hdev, port);
 	if (!pcm)
 		return -EIO;
 
 	/* set the device if pin is mst_capable */
-	if (hdac_hdmi_port_select_set(edev, port) < 0)
+	if (hdac_hdmi_port_select_set(hdev, port) < 0)
 		return -EIO;
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
-		hdac_hdmi_set_power_state(edev, port->pin->nid, AC_PWRST_D0);
+		hdac_hdmi_set_power_state(hdev, port->pin->nid, AC_PWRST_D0);
 
 		/* Enable out path for this pin widget */
-		snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+		snd_hdac_codec_write(hdev, port->pin->nid, 0,
 				AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
 
-		hdac_hdmi_set_amp(edev, port->pin->nid, AMP_OUT_UNMUTE);
+		hdac_hdmi_set_amp(hdev, port->pin->nid, AMP_OUT_UNMUTE);
 
-		return hdac_hdmi_setup_audio_infoframe(edev, pcm, port);
+		return hdac_hdmi_setup_audio_infoframe(hdev, pcm, port);
 
 	case SND_SOC_DAPM_POST_PMD:
-		hdac_hdmi_set_amp(edev, port->pin->nid, AMP_OUT_MUTE);
+		hdac_hdmi_set_amp(hdev, port->pin->nid, AMP_OUT_MUTE);
 
 		/* Disable out path for this pin widget */
-		snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+		snd_hdac_codec_write(hdev, port->pin->nid, 0,
 				AC_VERB_SET_PIN_WIDGET_CONTROL, 0);
 
-		hdac_hdmi_set_power_state(edev, port->pin->nid, AC_PWRST_D3);
+		hdac_hdmi_set_power_state(hdev, port->pin->nid, AC_PWRST_D3);
 		break;
 
 	}
@@ -795,11 +784,11 @@ static int hdac_hdmi_cvt_output_widget_event(struct snd_soc_dapm_widget *w,
 					struct snd_kcontrol *kc, int event)
 {
 	struct hdac_hdmi_cvt *cvt = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm;
 
-	dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n",
+	dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n",
 			__func__, w->name, event);
 
 	pcm = hdac_hdmi_get_pcm_from_cvt(hdmi, cvt);
@@ -808,29 +797,29 @@ static int hdac_hdmi_cvt_output_widget_event(struct snd_soc_dapm_widget *w,
 
 	switch (event) {
 	case SND_SOC_DAPM_PRE_PMU:
-		hdac_hdmi_set_power_state(edev, cvt->nid, AC_PWRST_D0);
+		hdac_hdmi_set_power_state(hdev, cvt->nid, AC_PWRST_D0);
 
 		/* Enable transmission */
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 			AC_VERB_SET_DIGI_CONVERT_1, 1);
 
 		/* Category Code (CC) to zero */
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 			AC_VERB_SET_DIGI_CONVERT_2, 0);
 
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_CHANNEL_STREAMID, pcm->stream_tag);
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_STREAM_FORMAT, pcm->format);
 		break;
 
 	case SND_SOC_DAPM_POST_PMD:
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_CHANNEL_STREAMID, 0);
-		snd_hdac_codec_write(&edev->hdev, cvt->nid, 0,
+		snd_hdac_codec_write(hdev, cvt->nid, 0,
 				AC_VERB_SET_STREAM_FORMAT, 0);
 
-		hdac_hdmi_set_power_state(edev, cvt->nid, AC_PWRST_D3);
+		hdac_hdmi_set_power_state(hdev, cvt->nid, AC_PWRST_D3);
 		break;
 
 	}
@@ -842,10 +831,10 @@ static int hdac_hdmi_pin_mux_widget_event(struct snd_soc_dapm_widget *w,
 					struct snd_kcontrol *kc, int event)
 {
 	struct hdac_hdmi_port *port = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(w->dapm->dev);
+	struct hdac_device *hdev = dev_to_hdac_dev(w->dapm->dev);
 	int mux_idx;
 
-	dev_dbg(&edev->hdev.dev, "%s: widget: %s event: %x\n",
+	dev_dbg(&hdev->dev, "%s: widget: %s event: %x\n",
 			__func__, w->name, event);
 
 	if (!kc)
@@ -854,11 +843,11 @@ static int hdac_hdmi_pin_mux_widget_event(struct snd_soc_dapm_widget *w,
 	mux_idx = dapm_kcontrol_get_value(kc);
 
 	/* set the device if pin is mst_capable */
-	if (hdac_hdmi_port_select_set(edev, port) < 0)
+	if (hdac_hdmi_port_select_set(hdev, port) < 0)
 		return -EIO;
 
 	if (mux_idx > 0) {
-		snd_hdac_codec_write(&edev->hdev, port->pin->nid, 0,
+		snd_hdac_codec_write(hdev, port->pin->nid, 0,
 			AC_VERB_SET_CONNECT_SEL, (mux_idx - 1));
 	}
 
@@ -877,8 +866,8 @@ static int hdac_hdmi_set_pin_port_mux(struct snd_kcontrol *kcontrol,
 	struct snd_soc_dapm_widget *w = snd_soc_dapm_kcontrol_widget(kcontrol);
 	struct snd_soc_dapm_context *dapm = w->dapm;
 	struct hdac_hdmi_port *port = w->priv;
-	struct hdac_ext_device *edev = to_hda_ext_device(dapm->dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = dev_to_hdac_dev(dapm->dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm = NULL;
 	const char *cvt_name =  e->texts[ucontrol->value.enumerated.item[0]];
 
@@ -931,12 +920,12 @@ static int hdac_hdmi_set_pin_port_mux(struct snd_kcontrol *kcontrol,
  * care of selecting the right one and leaving all other inputs selected to
  * "NONE"
  */
-static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev,
+static int hdac_hdmi_create_pin_port_muxs(struct hdac_device *hdev,
 				struct hdac_hdmi_port *port,
 				struct snd_soc_dapm_widget *widget,
 				const char *widget_name)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin = port->pin;
 	struct snd_kcontrol_new *kc;
 	struct hdac_hdmi_cvt *cvt;
@@ -948,17 +937,17 @@ static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev,
 	int i = 0;
 	int num_items = hdmi->num_cvt + 1;
 
-	kc = devm_kzalloc(&edev->hdev.dev, sizeof(*kc), GFP_KERNEL);
+	kc = devm_kzalloc(&hdev->dev, sizeof(*kc), GFP_KERNEL);
 	if (!kc)
 		return -ENOMEM;
 
-	se = devm_kzalloc(&edev->hdev.dev, sizeof(*se), GFP_KERNEL);
+	se = devm_kzalloc(&hdev->dev, sizeof(*se), GFP_KERNEL);
 	if (!se)
 		return -ENOMEM;
 
 	snprintf(kc_name, NAME_SIZE, "Pin %d port %d Input",
 						pin->nid, port->id);
-	kc->name = devm_kstrdup(&edev->hdev.dev, kc_name, GFP_KERNEL);
+	kc->name = devm_kstrdup(&hdev->dev, kc_name, GFP_KERNEL);
 	if (!kc->name)
 		return -ENOMEM;
 
@@ -976,35 +965,35 @@ static int hdac_hdmi_create_pin_port_muxs(struct hdac_ext_device *edev,
 	se->mask = roundup_pow_of_two(se->items) - 1;
 
 	sprintf(mux_items, "NONE");
-	items[i] = devm_kstrdup(&edev->hdev.dev, mux_items, GFP_KERNEL);
+	items[i] = devm_kstrdup(&hdev->dev, mux_items, GFP_KERNEL);
 	if (!items[i])
 		return -ENOMEM;
 
 	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
 		i++;
 		sprintf(mux_items, "cvt %d", cvt->nid);
-		items[i] = devm_kstrdup(&edev->hdev.dev, mux_items, GFP_KERNEL);
+		items[i] = devm_kstrdup(&hdev->dev, mux_items, GFP_KERNEL);
 		if (!items[i])
 			return -ENOMEM;
 	}
 
-	se->texts = devm_kmemdup(&edev->hdev.dev, items,
+	se->texts = devm_kmemdup(&hdev->dev, items,
 			(num_items  * sizeof(char *)), GFP_KERNEL);
 	if (!se->texts)
 		return -ENOMEM;
 
-	return hdac_hdmi_fill_widget_info(&edev->hdev.dev, widget,
+	return hdac_hdmi_fill_widget_info(&hdev->dev, widget,
 			snd_soc_dapm_mux, port, widget_name, NULL, kc, 1,
 			hdac_hdmi_pin_mux_widget_event,
 			SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_REG);
 }
 
 /* Add cvt <- input <- mux route map */
-static void hdac_hdmi_add_pinmux_cvt_route(struct hdac_ext_device *edev,
+static void hdac_hdmi_add_pinmux_cvt_route(struct hdac_device *hdev,
 			struct snd_soc_dapm_widget *widgets,
 			struct snd_soc_dapm_route *route, int rindex)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	const struct snd_kcontrol_new *kc;
 	struct soc_enum *se;
 	int mux_index = hdmi->num_cvt + hdmi->num_ports;
@@ -1046,8 +1035,8 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 {
 	struct snd_soc_dapm_widget *widgets;
 	struct snd_soc_dapm_route *route;
-	struct hdac_ext_device *edev = to_hda_ext_device(dapm->dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = dev_to_hdac_dev(dapm->dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct snd_soc_dai_driver *dai_drv = hdmi->dai_drv;
 	char widget_name[NAME_SIZE];
 	struct hdac_hdmi_cvt *cvt;
@@ -1099,7 +1088,7 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 		for (j = 0; j < pin->num_ports; j++) {
 			sprintf(widget_name, "Pin%d-Port%d Mux",
 				pin->nid, pin->ports[j].id);
-			ret = hdac_hdmi_create_pin_port_muxs(edev,
+			ret = hdac_hdmi_create_pin_port_muxs(hdev,
 						&pin->ports[j], &widgets[i],
 						widget_name);
 			if (ret < 0)
@@ -1134,7 +1123,7 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 		}
 	}
 
-	hdac_hdmi_add_pinmux_cvt_route(edev, widgets, route, i);
+	hdac_hdmi_add_pinmux_cvt_route(hdev, widgets, route, i);
 
 	snd_soc_dapm_new_controls(dapm, widgets,
 		((2 * hdmi->num_ports) + hdmi->num_cvt));
@@ -1146,9 +1135,9 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 
 }
 
-static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
+static int hdac_hdmi_init_dai_map(struct hdac_device *hdev)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_dai_port_map *dai_map;
 	struct hdac_hdmi_cvt *cvt;
 	int dai_id = 0;
@@ -1164,7 +1153,7 @@ static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
 		dai_id++;
 
 		if (dai_id == HDA_MAX_CVTS) {
-			dev_warn(&edev->hdev.dev,
+			dev_warn(&hdev->dev,
 				"Max dais supported: %d\n", dai_id);
 			break;
 		}
@@ -1173,9 +1162,9 @@ static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
 	return 0;
 }
 
-static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid)
+static int hdac_hdmi_add_cvt(struct hdac_device *hdev, hda_nid_t nid)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_cvt *cvt;
 	char name[NAME_SIZE];
 
@@ -1190,10 +1179,10 @@ static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid)
 	list_add_tail(&cvt->head, &hdmi->cvt_list);
 	hdmi->num_cvt++;
 
-	return hdac_hdmi_query_cvt_params(&edev->hdev, cvt);
+	return hdac_hdmi_query_cvt_params(hdev, cvt);
 }
 
-static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
+static int hdac_hdmi_parse_eld(struct hdac_device *hdev,
 			struct hdac_hdmi_port *port)
 {
 	unsigned int ver, mnl;
@@ -1202,7 +1191,7 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
 						>> DRM_ELD_VER_SHIFT;
 
 	if (ver != ELD_VER_CEA_861D && ver != ELD_VER_PARTIAL) {
-		dev_err(&edev->hdev.dev, "HDMI: Unknown ELD version %d\n", ver);
+		dev_err(&hdev->dev, "HDMI: Unknown ELD version %d\n", ver);
 		return -EINVAL;
 	}
 
@@ -1210,7 +1199,7 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
 		DRM_ELD_MNL_MASK) >> DRM_ELD_MNL_SHIFT;
 
 	if (mnl > ELD_MAX_MNL) {
-		dev_err(&edev->hdev.dev, "HDMI: MNL Invalid %d\n", mnl);
+		dev_err(&hdev->dev, "HDMI: MNL Invalid %d\n", mnl);
 		return -EINVAL;
 	}
 
@@ -1222,8 +1211,8 @@ static int hdac_hdmi_parse_eld(struct hdac_ext_device *edev,
 static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin,
 				    struct hdac_hdmi_port *port)
 {
-	struct hdac_ext_device *edev = pin->edev;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = pin->hdev;
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm;
 	int size = 0;
 	int port_id = -1;
@@ -1241,14 +1230,14 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin,
 	if (pin->mst_capable)
 		port_id = port->id;
 
-	size = snd_hdac_acomp_get_eld(&edev->hdev, pin->nid, port_id,
+	size = snd_hdac_acomp_get_eld(hdev, pin->nid, port_id,
 				&port->eld.monitor_present,
 				port->eld.eld_buffer,
 				ELD_MAX_SIZE);
 
 	if (size > 0) {
 		size = min(size, ELD_MAX_SIZE);
-		if (hdac_hdmi_parse_eld(edev, port) < 0)
+		if (hdac_hdmi_parse_eld(hdev, port) < 0)
 			size = -EINVAL;
 	}
 
@@ -1260,11 +1249,11 @@ static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin,
 		port->eld.eld_size = 0;
 	}
 
-	pcm = hdac_hdmi_get_pcm(edev, port);
+	pcm = hdac_hdmi_get_pcm(hdev, port);
 
 	if (!port->eld.monitor_present || !port->eld.eld_valid) {
 
-		dev_err(&edev->hdev.dev, "%s: disconnect for pin:port %d:%d\n",
+		dev_err(&hdev->dev, "%s: disconnect for pin:port %d:%d\n",
 						__func__, pin->nid, port->id);
 
 		/*
@@ -1316,9 +1305,9 @@ static int hdac_hdmi_add_ports(struct hdac_hdmi_priv *hdmi,
 	return 0;
 }
 
-static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
+static int hdac_hdmi_add_pin(struct hdac_device *hdev, hda_nid_t nid)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin;
 	int ret;
 
@@ -1328,7 +1317,7 @@ static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
 
 	pin->nid = nid;
 	pin->mst_capable = false;
-	pin->edev = edev;
+	pin->hdev = hdev;
 	ret = hdac_hdmi_add_ports(hdmi, pin);
 	if (ret < 0)
 		return ret;
@@ -1459,15 +1448,14 @@ static int hdac_hdmi_create_dais(struct hdac_device *hdev,
  * Parse all nodes and store the cvt/pin nids in array
  * Add one time initialization for pin and cvt widgets
  */
-static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev,
+static int hdac_hdmi_parse_and_map_nid(struct hdac_device *hdev,
 		struct snd_soc_dai_driver **dais, int *num_dais)
 {
 	hda_nid_t nid;
 	int i, num_nodes;
 	struct hdac_hdmi_cvt *temp_cvt, *cvt_next;
 	struct hdac_hdmi_pin *temp_pin, *pin_next;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	int ret;
 
 	hdac_hdmi_skl_enable_all_pins(hdev);
@@ -1492,13 +1480,13 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev,
 		switch (type) {
 
 		case AC_WID_AUD_OUT:
-			ret = hdac_hdmi_add_cvt(edev, nid);
+			ret = hdac_hdmi_add_cvt(hdev, nid);
 			if (ret < 0)
 				goto free_widgets;
 			break;
 
 		case AC_WID_PIN:
-			ret = hdac_hdmi_add_pin(edev, nid);
+			ret = hdac_hdmi_add_pin(hdev, nid);
 			if (ret < 0)
 				goto free_widgets;
 			break;
@@ -1518,7 +1506,7 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev,
 	}
 
 	*num_dais = hdmi->num_cvt;
-	ret = hdac_hdmi_init_dai_map(edev);
+	ret = hdac_hdmi_init_dai_map(hdev);
 	if (ret < 0)
 		goto free_widgets;
 
@@ -1544,17 +1532,17 @@ free_widgets:
 
 static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 {
-	struct hdac_ext_device *edev = aptr;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_device *hdev = aptr;
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin = NULL;
 	struct hdac_hdmi_port *hport = NULL;
-	struct snd_soc_component *component = edev->scodec;
+	struct snd_soc_component *component = hdmi->component;
 	int i;
 
 	/* Don't know how this mapping is derived */
 	hda_nid_t pin_nid = port + 0x04;
 
-	dev_dbg(&edev->hdev.dev, "%s: for pin:%d port=%d\n", __func__,
+	dev_dbg(&hdev->dev, "%s: for pin:%d port=%d\n", __func__,
 							pin_nid, pipe);
 
 	/*
@@ -1567,7 +1555,7 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 			SNDRV_CTL_POWER_D0)
 		return;
 
-	if (atomic_read(&edev->hdev.in_pm))
+	if (atomic_read(&hdev->in_pm))
 		return;
 
 	list_for_each_entry(pin, &hdmi->pin_list, head) {
@@ -1614,15 +1602,15 @@ static struct snd_pcm *hdac_hdmi_get_pcm_from_id(struct snd_soc_card *card,
 
 /* create jack pin kcontrols */
 static int create_fill_jack_kcontrols(struct snd_soc_card *card,
-				    struct hdac_ext_device *edev)
+				    struct hdac_device *hdev)
 {
 	struct hdac_hdmi_pin *pin;
 	struct snd_kcontrol_new *kc;
 	char kc_name[NAME_SIZE], xname[NAME_SIZE];
 	char *name;
 	int i = 0, j;
-	struct snd_soc_component *component = edev->scodec;
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
+	struct snd_soc_component *component = hdmi->component;
 
 	kc = devm_kcalloc(component->dev, hdmi->num_ports,
 				sizeof(*kc), GFP_KERNEL);
@@ -1659,8 +1647,8 @@ static int create_fill_jack_kcontrols(struct snd_soc_card *card,
 int hdac_hdmi_jack_port_init(struct snd_soc_component *component,
 			struct snd_soc_dapm_context *dapm)
 {
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_pin *pin;
 	struct snd_soc_dapm_widget *widgets;
 	struct snd_soc_dapm_route *route;
@@ -1715,7 +1703,7 @@ int hdac_hdmi_jack_port_init(struct snd_soc_component *component,
 		return ret;
 
 	/* Add Jack Pin switch Kcontrol */
-	ret = create_fill_jack_kcontrols(dapm->card, edev);
+	ret = create_fill_jack_kcontrols(dapm->card, hdev);
 
 	if (ret < 0)
 		return ret;
@@ -1735,8 +1723,8 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device,
 				struct snd_soc_jack *jack)
 {
 	struct snd_soc_component *component = dai->component;
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct hdac_hdmi_pcm *pcm;
 	struct snd_pcm *snd_pcm;
 	int err;
@@ -1758,7 +1746,7 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device,
 	if (snd_pcm) {
 		err = snd_hdac_add_chmap_ctls(snd_pcm, device, &hdmi->chmap);
 		if (err < 0) {
-			dev_err(&edev->hdev.dev,
+			dev_err(&hdev->dev,
 				"chmap control add failed with err: %d for pcm: %d\n",
 				err, device);
 			kfree(pcm);
@@ -1772,7 +1760,7 @@ int hdac_hdmi_jack_init(struct snd_soc_dai *dai, int device,
 }
 EXPORT_SYMBOL_GPL(hdac_hdmi_jack_init);
 
-static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev,
+static void hdac_hdmi_present_sense_all_pins(struct hdac_device *hdev,
 			struct hdac_hdmi_priv *hdmi, bool detect_pin_caps)
 {
 	int i;
@@ -1781,7 +1769,7 @@ static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev,
 	list_for_each_entry(pin, &hdmi->pin_list, head) {
 		if (detect_pin_caps) {
 
-			if (hdac_hdmi_get_port_len(edev, pin->nid)  == 0)
+			if (hdac_hdmi_get_port_len(hdev, pin->nid)  == 0)
 				pin->mst_capable = false;
 			else
 				pin->mst_capable = true;
@@ -1798,68 +1786,68 @@ static void hdac_hdmi_present_sense_all_pins(struct hdac_ext_device *edev,
 
 static int hdmi_codec_probe(struct snd_soc_component *component)
 {
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 	struct snd_soc_dapm_context *dapm =
 		snd_soc_component_get_dapm(component);
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
-	edev->scodec = component;
+	hdmi->component = component;
 
 	/*
 	 * hold the ref while we probe, also no need to drop the ref on
 	 * exit, we call pm_runtime_suspend() so that will do for us
 	 */
-	hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdev.dev));
+	hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus),
+						dev_name(&hdev->dev));
 	if (!hlink) {
-		dev_err(&edev->hdev.dev, "hdac link not found\n");
+		dev_err(&hdev->dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(edev->ebus, hlink);
+	snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink);
 
 	ret = create_fill_widget_route_map(dapm);
 	if (ret < 0)
 		return ret;
 
-	aops.audio_ptr = edev;
+	aops.audio_ptr = hdev;
 	ret = snd_hdac_i915_register_notifier(&aops);
 	if (ret < 0) {
-		dev_err(&edev->hdev.dev, "notifier register failed: err: %d\n",
-				ret);
+		dev_err(&hdev->dev, "notifier register failed: err: %d\n", ret);
 		return ret;
 	}
 
-	hdac_hdmi_present_sense_all_pins(edev, hdmi, true);
+	hdac_hdmi_present_sense_all_pins(hdev, hdmi, true);
 	/* Imp: Store the card pointer in hda_codec */
-	edev->card = dapm->card->snd_card;
+	hdmi->card = dapm->card->snd_card;
 
 	/*
 	 * hdac_device core already sets the state to active and calls
 	 * get_noresume. So enable runtime and set the device to suspend.
 	 */
-	pm_runtime_enable(&edev->hdev.dev);
-	pm_runtime_put(&edev->hdev.dev);
-	pm_runtime_suspend(&edev->hdev.dev);
+	pm_runtime_enable(&hdev->dev);
+	pm_runtime_put(&hdev->dev);
+	pm_runtime_suspend(&hdev->dev);
 
 	return 0;
 }
 
 static void hdmi_codec_remove(struct snd_soc_component *component)
 {
-	struct hdac_ext_device *edev = snd_soc_component_get_drvdata(component);
+	struct hdac_hdmi_priv *hdmi = snd_soc_component_get_drvdata(component);
+	struct hdac_device *hdev = hdmi->hdev;
 
-	pm_runtime_disable(&edev->hdev.dev);
+	pm_runtime_disable(&hdev->dev);
 }
 
 #ifdef CONFIG_PM
 static int hdmi_codec_prepare(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 
-	pm_runtime_get_sync(&edev->hdev.dev);
+	pm_runtime_get_sync(&hdev->dev);
 
 	/*
 	 * Power down afg.
@@ -1876,16 +1864,15 @@ static int hdmi_codec_prepare(struct device *dev)
 
 static void hdmi_codec_complete(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 
 	/* Power up afg */
 	snd_hdac_codec_read(hdev, hdev->afg, 0,	AC_VERB_SET_POWER_STATE,
 							AC_PWRST_D0);
 
-	hdac_hdmi_skl_enable_all_pins(&edev->hdev);
-	hdac_hdmi_skl_enable_dp12(&edev->hdev);
+	hdac_hdmi_skl_enable_all_pins(hdev);
+	hdac_hdmi_skl_enable_dp12(hdev);
 
 	/*
 	 * As the ELD notify callback request is not entertained while the
@@ -1893,9 +1880,9 @@ static void hdmi_codec_complete(struct device *dev)
 	 * all pins here. pin capablity change is not support, so use the
 	 * already set pin caps.
 	 */
-	hdac_hdmi_present_sense_all_pins(edev, hdmi, false);
+	hdac_hdmi_present_sense_all_pins(hdev, hdmi, false);
 
-	pm_runtime_put_sync(&edev->hdev.dev);
+	pm_runtime_put_sync(&hdev->dev);
 }
 #else
 #define hdmi_codec_prepare NULL
@@ -1922,7 +1909,6 @@ static void hdac_hdmi_get_chmap(struct hdac_device *hdev, int pcm_idx,
 static void hdac_hdmi_set_chmap(struct hdac_device *hdev, int pcm_idx,
 				unsigned char *chmap, int prepared)
 {
-	struct hdac_ext_device *edev = to_ehdac_device(hdev);
 	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pcm *pcm = get_hdmi_pcm_from_id(hdmi, pcm_idx);
 	struct hdac_hdmi_port *port;
@@ -1938,7 +1924,7 @@ static void hdac_hdmi_set_chmap(struct hdac_device *hdev, int pcm_idx,
 	memcpy(pcm->chmap, chmap, ARRAY_SIZE(pcm->chmap));
 	list_for_each_entry(port, &pcm->port_list, head)
 		if (prepared)
-			hdac_hdmi_setup_audio_infoframe(edev, pcm, port);
+			hdac_hdmi_setup_audio_infoframe(hdev, pcm, port);
 	mutex_unlock(&pcm->lock);
 }
 
@@ -1987,10 +1973,9 @@ static struct hdac_hdmi_drv_data intel_drv_data  = {
 	.vendor_nid = INTEL_VENDOR_NID,
 };
 
-static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
+static int hdac_hdmi_dev_probe(struct hdac_device *hdev)
 {
-	struct hdac_device *hdev = &edev->hdev;
-	struct hdac_hdmi_priv *hdmi_priv;
+	struct hdac_hdmi_priv *hdmi_priv = NULL;
 	struct snd_soc_dai_driver *hdmi_dais = NULL;
 	struct hdac_ext_link *hlink = NULL;
 	int num_dais = 0;
@@ -1999,24 +1984,25 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	const struct hda_device_id *hdac_id = hdac_get_device_id(hdev, hdrv);
 
 	/* hold the ref while we probe */
-	hlink = snd_hdac_ext_bus_get_link(edev->ebus, dev_name(&edev->hdev.dev));
+	hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus),
+						dev_name(&hdev->dev));
 	if (!hlink) {
-		dev_err(&edev->hdev.dev, "hdac link not found\n");
+		dev_err(&hdev->dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(edev->ebus, hlink);
+	snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink);
 
 	hdmi_priv = devm_kzalloc(&hdev->dev, sizeof(*hdmi_priv), GFP_KERNEL);
 	if (hdmi_priv == NULL)
 		return -ENOMEM;
 
-	edev->private_data = hdmi_priv;
 	snd_hdac_register_chmap_ops(hdev, &hdmi_priv->chmap);
 	hdmi_priv->chmap.ops.get_chmap = hdac_hdmi_get_chmap;
 	hdmi_priv->chmap.ops.set_chmap = hdac_hdmi_set_chmap;
 	hdmi_priv->chmap.ops.is_pcm_attached = is_hdac_hdmi_pcm_attached;
 	hdmi_priv->chmap.ops.get_spk_alloc = hdac_hdmi_get_spk_alloc;
+	hdmi_priv->hdev = hdev;
 
 	if (!hdac_id)
 		return -ENODEV;
@@ -2027,7 +2013,7 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	else
 		hdmi_priv->drv_data = &intel_drv_data;
 
-	dev_set_drvdata(&hdev->dev, edev);
+	dev_set_drvdata(&hdev->dev, hdmi_priv);
 
 	INIT_LIST_HEAD(&hdmi_priv->pin_list);
 	INIT_LIST_HEAD(&hdmi_priv->cvt_list);
@@ -2038,15 +2024,15 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	 * Turned off in the runtime_suspend during the first explicit
 	 * pm_runtime_suspend call.
 	 */
-	ret = snd_hdac_display_power(edev->hdev.bus, true);
+	ret = snd_hdac_display_power(hdev->bus, true);
 	if (ret < 0) {
-		dev_err(&edev->hdev.dev,
+		dev_err(&hdev->dev,
 			"Cannot turn on display power on i915 err: %d\n",
 			ret);
 		return ret;
 	}
 
-	ret = hdac_hdmi_parse_and_map_nid(edev, &hdmi_dais, &num_dais);
+	ret = hdac_hdmi_parse_and_map_nid(hdev, &hdmi_dais, &num_dais);
 	if (ret < 0) {
 		dev_err(&hdev->dev,
 			"Failed in parse and map nid with err: %d\n", ret);
@@ -2058,14 +2044,14 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	ret = devm_snd_soc_register_component(&hdev->dev, &hdmi_hda_codec,
 					hdmi_dais, num_dais);
 
-	snd_hdac_ext_bus_link_put(edev->ebus, hlink);
+	snd_hdac_ext_bus_link_put(hbus_to_ebus(hdev->bus), hlink);
 
 	return ret;
 }
 
-static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
+static int hdac_hdmi_dev_remove(struct hdac_device *hdev)
 {
-	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(&edev->hdev);
+	struct hdac_hdmi_priv *hdmi = hdev_to_hdmi_priv(hdev);
 	struct hdac_hdmi_pin *pin, *pin_next;
 	struct hdac_hdmi_cvt *cvt, *cvt_next;
 	struct hdac_hdmi_pcm *pcm, *pcm_next;
@@ -2105,8 +2091,7 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
 #ifdef CONFIG_PM
 static int hdac_hdmi_runtime_suspend(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 	struct hdac_bus *bus = hdev->bus;
 	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink = NULL;
@@ -2129,7 +2114,7 @@ static int hdac_hdmi_runtime_suspend(struct device *dev)
 							AC_PWRST_D3);
 	err = snd_hdac_display_power(bus, false);
 	if (err < 0) {
-		dev_err(bus->dev, "Cannot turn on display power on i915\n");
+		dev_err(dev, "Cannot turn on display power on i915\n");
 		return err;
 	}
 
@@ -2146,8 +2131,7 @@ static int hdac_hdmi_runtime_suspend(struct device *dev)
 
 static int hdac_hdmi_runtime_resume(struct device *dev)
 {
-	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-	struct hdac_device *hdev = &edev->hdev;
+	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 	struct hdac_bus *bus = hdev->bus;
 	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink = NULL;
@@ -2169,12 +2153,12 @@ static int hdac_hdmi_runtime_resume(struct device *dev)
 
 	err = snd_hdac_display_power(bus, true);
 	if (err < 0) {
-		dev_err(bus->dev, "Cannot turn on display power on i915\n");
+		dev_err(dev, "Cannot turn on display power on i915\n");
 		return err;
 	}
 
-	hdac_hdmi_skl_enable_all_pins(&edev->hdev);
-	hdac_hdmi_skl_enable_dp12(&edev->hdev);
+	hdac_hdmi_skl_enable_all_pins(hdev);
+	hdac_hdmi_skl_enable_dp12(hdev);
 
 	/* Power up afg */
 	snd_hdac_codec_read(hdev, hdev->afg, 0,	AC_VERB_SET_POWER_STATE,
-- 
cgit v1.2.3


From 76f56fae1cf9040325a58d1375291baf71dfaf03 Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Fri, 1 Jun 2018 22:53:50 -0500
Subject: ALSA: hdac: Remove usage of struct hdac_ext_bus and use hdac_bus
 instead

This patch removes the hdac_ext_bus structure. The legacy and
enhanced HDaudio capabilities can be handled in a backward-compatible
way without separate definitions.

Follow-up patches in this series handle the driver definition.

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio.h                |  15 +++
 include/sound/hdaudio_ext.h            |  74 +++++--------
 sound/hda/ext/hdac_ext_bus.c           |  27 +++--
 sound/hda/ext/hdac_ext_controller.c    |  55 +++++-----
 sound/hda/ext/hdac_ext_stream.c        | 104 ++++++++-----------
 sound/soc/codecs/hdac_hdmi.c           |  22 ++--
 sound/soc/intel/skylake/skl-messages.c |  50 ++++-----
 sound/soc/intel/skylake/skl-nhlt.c     |   8 +-
 sound/soc/intel/skylake/skl-pcm.c      | 112 ++++++++++----------
 sound/soc/intel/skylake/skl-topology.c |  20 ++--
 sound/soc/intel/skylake/skl-topology.h |   6 +-
 sound/soc/intel/skylake/skl.c          | 184 +++++++++++++++------------------
 sound/soc/intel/skylake/skl.h          |   7 +-
 13 files changed, 308 insertions(+), 376 deletions(-)

diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index c052afc27547..9735b51aef08 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -250,6 +250,11 @@ struct hdac_rb {
  * @mlcap: MultiLink capabilities pointer
  * @gtscap: gts capabilities pointer
  * @drsmcap: dma resume capabilities pointer
+ * @num_streams: streams supported
+ * @idx: HDA link index
+ * @hlink_list: link list of HDA links
+ * @lock: lock for link mgmt
+ * @cmd_dma_state: state of cmd DMAs: CORB and RIRB
  */
 struct hdac_bus {
 	struct device *dev;
@@ -317,6 +322,16 @@ struct hdac_bus {
 	/* i915 component interface */
 	struct i915_audio_component *audio_component;
 	int i915_power_refcount;
+
+	/* parameters required for enhanced capabilities */
+	int num_streams;
+	int idx;
+
+	struct list_head hlink_list;
+
+	struct mutex lock;
+	bool cmd_dma_state;
+
 };
 
 int snd_hdac_bus_init(struct hdac_bus *bus, struct device *dev,
diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index c1a5ad0e6e39..e5b0cd1ade19 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -4,38 +4,14 @@
 
 #include <sound/hdaudio.h>
 
-/**
- * hdac_ext_bus: HDAC extended bus for extended HDA caps
- *
- * @bus: hdac bus
- * @num_streams: streams supported
- * @hlink_list: link list of HDA links
- * @lock: lock for link mgmt
- * @cmd_dma_state: state of cmd DMAs: CORB and RIRB
- */
-struct hdac_ext_bus {
-	struct hdac_bus bus;
-	int num_streams;
-	int idx;
-
-	struct list_head hlink_list;
-
-	struct mutex lock;
-	bool cmd_dma_state;
-};
-
-int snd_hdac_ext_bus_init(struct hdac_ext_bus *sbus, struct device *dev,
+int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 		      const struct hdac_bus_ops *ops,
 		      const struct hdac_io_ops *io_ops);
 
-void snd_hdac_ext_bus_exit(struct hdac_ext_bus *sbus);
-int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *sbus, int addr);
+void snd_hdac_ext_bus_exit(struct hdac_bus *bus);
+int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr);
 void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev);
-void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus);
-
-#define ebus_to_hbus(ebus)	(&(ebus)->bus)
-#define hbus_to_ebus(_bus) \
-	container_of(_bus, struct hdac_ext_bus, bus)
+void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus);
 
 #define HDA_CODEC_REV_EXT_ENTRY(_vid, _rev, _name, drv_data) \
 	{ .vendor_id = (_vid), .rev_id = (_rev), .name = (_name), \
@@ -44,14 +20,14 @@ void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus);
 #define HDA_CODEC_EXT_ENTRY(_vid, _revid, _name, _drv_data) \
 	HDA_CODEC_REV_EXT_ENTRY(_vid, _revid, _name, _drv_data)
 
-void snd_hdac_ext_bus_ppcap_enable(struct hdac_ext_bus *chip, bool enable);
-void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_ext_bus *chip, bool enable);
+void snd_hdac_ext_bus_ppcap_enable(struct hdac_bus *chip, bool enable);
+void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_bus *chip, bool enable);
 
-void snd_hdac_ext_stream_spbcap_enable(struct hdac_ext_bus *chip,
+void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *chip,
 				 bool enable, int index);
 
-int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *bus);
-struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *bus,
+int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_bus *bus);
+struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus,
 						const char *codec_name);
 
 enum hdac_ext_stream_type {
@@ -100,28 +76,28 @@ struct hdac_ext_stream {
 #define stream_to_hdac_ext_stream(s) \
 	container_of(s, struct hdac_ext_stream, hstream)
 
-void snd_hdac_ext_stream_init(struct hdac_ext_bus *bus,
+void snd_hdac_ext_stream_init(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream, int idx,
 				int direction, int tag);
-int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx,
+int snd_hdac_ext_stream_init_all(struct hdac_bus *bus, int start_idx,
 		int num_stream, int dir);
-void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus);
-void snd_hdac_link_free_all(struct hdac_ext_bus *ebus);
-struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_ext_bus *bus,
+void snd_hdac_stream_free_all(struct hdac_bus *bus);
+void snd_hdac_link_free_all(struct hdac_bus *bus);
+struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_bus *bus,
 					   struct snd_pcm_substream *substream,
 					   int type);
 void snd_hdac_ext_stream_release(struct hdac_ext_stream *azx_dev, int type);
-void snd_hdac_ext_stream_decouple(struct hdac_ext_bus *bus,
+void snd_hdac_ext_stream_decouple(struct hdac_bus *bus,
 				struct hdac_ext_stream *azx_dev, bool decouple);
-void snd_hdac_ext_stop_streams(struct hdac_ext_bus *sbus);
+void snd_hdac_ext_stop_streams(struct hdac_bus *bus);
 
-int snd_hdac_ext_stream_set_spib(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_spib(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream, u32 value);
-int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream);
-void snd_hdac_ext_stream_drsm_enable(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus,
 				bool enable, int index);
-int snd_hdac_ext_stream_set_dpibr(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_dpibr(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream, u32 value);
 int snd_hdac_ext_stream_set_lpib(struct hdac_ext_stream *stream, u32 value);
 
@@ -144,17 +120,15 @@ struct hdac_ext_link {
 
 int snd_hdac_ext_bus_link_power_up(struct hdac_ext_link *link);
 int snd_hdac_ext_bus_link_power_down(struct hdac_ext_link *link);
-int snd_hdac_ext_bus_link_power_up_all(struct hdac_ext_bus *ebus);
-int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus);
+int snd_hdac_ext_bus_link_power_up_all(struct hdac_bus *bus);
+int snd_hdac_ext_bus_link_power_down_all(struct hdac_bus *bus);
 void snd_hdac_ext_link_set_stream_id(struct hdac_ext_link *link,
 				 int stream);
 void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link,
 				 int stream);
 
-int snd_hdac_ext_bus_link_get(struct hdac_ext_bus *ebus,
-				struct hdac_ext_link *link);
-int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
-				struct hdac_ext_link *link);
+int snd_hdac_ext_bus_link_get(struct hdac_bus *bus, struct hdac_ext_link *link);
+int snd_hdac_ext_bus_link_put(struct hdac_bus *bus, struct hdac_ext_link *link);
 
 /* update register macro */
 #define snd_hdac_updatel(addr, reg, mask, val)		\
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index 0e4823fdd411..77547ede9ae8 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -87,7 +87,7 @@ static const struct hdac_io_ops hdac_ext_default_io = {
  *
  * Returns 0 if successful, or a negative error code.
  */
-int snd_hdac_ext_bus_init(struct hdac_ext_bus *ebus, struct device *dev,
+int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 			const struct hdac_bus_ops *ops,
 			const struct hdac_io_ops *io_ops)
 {
@@ -98,15 +98,15 @@ int snd_hdac_ext_bus_init(struct hdac_ext_bus *ebus, struct device *dev,
 	if (io_ops == NULL)
 		io_ops = &hdac_ext_default_io;
 
-	ret = snd_hdac_bus_init(&ebus->bus, dev, ops, io_ops);
+	ret = snd_hdac_bus_init(bus, dev, ops, io_ops);
 	if (ret < 0)
 		return ret;
 
-	INIT_LIST_HEAD(&ebus->hlink_list);
-	ebus->idx = idx++;
+	INIT_LIST_HEAD(&bus->hlink_list);
+	bus->idx = idx++;
 
-	mutex_init(&ebus->lock);
-	ebus->cmd_dma_state = true;
+	mutex_init(&bus->lock);
+	bus->cmd_dma_state = true;
 
 	return 0;
 }
@@ -116,10 +116,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_init);
  * snd_hdac_ext_bus_exit - clean up a HD-audio extended bus
  * @ebus: the pointer to extended bus object
  */
-void snd_hdac_ext_bus_exit(struct hdac_ext_bus *ebus)
+void snd_hdac_ext_bus_exit(struct hdac_bus *bus)
 {
-	snd_hdac_bus_exit(&ebus->bus);
-	WARN_ON(!list_empty(&ebus->hlink_list));
+	snd_hdac_bus_exit(bus);
+	WARN_ON(!list_empty(&bus->hlink_list));
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_exit);
 
@@ -135,10 +135,9 @@ static void default_release(struct device *dev)
  *
  * Returns zero for success or a negative error code.
  */
-int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *ebus, int addr)
+int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr)
 {
 	struct hdac_device *hdev = NULL;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	char name[15];
 	int ret;
 
@@ -148,7 +147,7 @@ int snd_hdac_ext_bus_device_init(struct hdac_ext_bus *ebus, int addr)
 
 	hdev->bus = bus;
 
-	snprintf(name, sizeof(name), "ehdaudio%dD%d", ebus->idx, addr);
+	snprintf(name, sizeof(name), "ehdaudio%dD%d", bus->idx, addr);
 
 	ret  = snd_hdac_device_init(hdev, bus, name, addr);
 	if (ret < 0) {
@@ -185,14 +184,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_exit);
  *
  * @ebus: HD-audio extended bus
  */
-void snd_hdac_ext_bus_device_remove(struct hdac_ext_bus *ebus)
+void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus)
 {
 	struct hdac_device *codec, *__codec;
 	/*
 	 * we need to remove all the codec devices objects created in the
 	 * snd_hdac_ext_bus_device_init
 	 */
-	list_for_each_entry_safe(codec, __codec, &ebus->bus.codec_list, list) {
+	list_for_each_entry_safe(codec, __codec, &bus->codec_list, list) {
 		snd_hdac_device_unregister(codec);
 		put_device(&codec->dev);
 	}
diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index 84f3b8168716..72774119dd11 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -39,9 +39,8 @@
  * @ebus: HD-audio extended core bus
  * @enable: flag to turn on/off the capability
  */
-void snd_hdac_ext_bus_ppcap_enable(struct hdac_ext_bus *ebus, bool enable)
+void snd_hdac_ext_bus_ppcap_enable(struct hdac_bus *bus, bool enable)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->ppcap) {
 		dev_err(bus->dev, "Address of PP capability is NULL");
@@ -60,9 +59,8 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_ppcap_enable);
  * @ebus: HD-audio extended core bus
  * @enable: flag to enable/disable interrupt
  */
-void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_ext_bus *ebus, bool enable)
+void snd_hdac_ext_bus_ppcap_int_enable(struct hdac_bus *bus, bool enable)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->ppcap) {
 		dev_err(bus->dev, "Address of PP capability is NULL\n");
@@ -89,12 +87,11 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_ppcap_int_enable);
  * in hlink_list of extended hdac bus
  * Note: this will be freed on bus exit by driver
  */
-int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *ebus)
+int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_bus *bus)
 {
 	int idx;
 	u32 link_count;
 	struct hdac_ext_link *hlink;
-	struct hdac_bus *bus = &ebus->bus;
 
 	link_count = readl(bus->mlcap + AZX_REG_ML_MLCD) + 1;
 
@@ -114,7 +111,7 @@ int snd_hdac_ext_bus_get_ml_capabilities(struct hdac_ext_bus *ebus)
 		/* since link in On, update the ref */
 		hlink->ref_count = 1;
 
-		list_add_tail(&hlink->list, &ebus->hlink_list);
+		list_add_tail(&hlink->list, &bus->hlink_list);
 	}
 
 	return 0;
@@ -127,12 +124,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_get_ml_capabilities);
  * @ebus: HD-audio ext core bus
  */
 
-void snd_hdac_link_free_all(struct hdac_ext_bus *ebus)
+void snd_hdac_link_free_all(struct hdac_bus *bus)
 {
 	struct hdac_ext_link *l;
 
-	while (!list_empty(&ebus->hlink_list)) {
-		l = list_first_entry(&ebus->hlink_list, struct hdac_ext_link, list);
+	while (!list_empty(&bus->hlink_list)) {
+		l = list_first_entry(&bus->hlink_list, struct hdac_ext_link, list);
 		list_del(&l->list);
 		kfree(l);
 	}
@@ -144,7 +141,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_link_free_all);
  * @ebus: HD-audio extended core bus
  * @codec_name: codec name
  */
-struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *ebus,
+struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_bus *bus,
 						 const char *codec_name)
 {
 	int i;
@@ -153,10 +150,10 @@ struct hdac_ext_link *snd_hdac_ext_bus_get_link(struct hdac_ext_bus *ebus,
 
 	if (sscanf(codec_name, "ehdaudio%dD%d", &bus_idx, &addr) != 2)
 		return NULL;
-	if (ebus->idx != bus_idx)
+	if (bus->idx != bus_idx)
 		return NULL;
 
-	list_for_each_entry(hlink, &ebus->hlink_list, list) {
+	list_for_each_entry(hlink, &bus->hlink_list, list) {
 		for (i = 0; i < HDA_MAX_CODECS; i++) {
 			if (hlink->lsdiid & (0x1 << addr))
 				return hlink;
@@ -219,12 +216,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down);
  * snd_hdac_ext_bus_link_power_up_all -power up all hda link
  * @ebus: HD-audio extended bus
  */
-int snd_hdac_ext_bus_link_power_up_all(struct hdac_ext_bus *ebus)
+int snd_hdac_ext_bus_link_power_up_all(struct hdac_bus *bus)
 {
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
-	list_for_each_entry(hlink, &ebus->hlink_list, list) {
+	list_for_each_entry(hlink, &bus->hlink_list, list) {
 		snd_hdac_updatel(hlink->ml_addr,
 				AZX_REG_ML_LCTL, 0, AZX_MLCTL_SPA);
 		ret = check_hdac_link_power_active(hlink, true);
@@ -240,12 +237,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_up_all);
  * snd_hdac_ext_bus_link_power_down_all -power down all hda link
  * @ebus: HD-audio extended bus
  */
-int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus)
+int snd_hdac_ext_bus_link_power_down_all(struct hdac_bus *bus)
 {
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
-	list_for_each_entry(hlink, &ebus->hlink_list, list) {
+	list_for_each_entry(hlink, &bus->hlink_list, list) {
 		snd_hdac_updatel(hlink->ml_addr, AZX_REG_ML_LCTL, AZX_MLCTL_SPA, 0);
 		ret = check_hdac_link_power_active(hlink, false);
 		if (ret < 0)
@@ -256,39 +253,39 @@ int snd_hdac_ext_bus_link_power_down_all(struct hdac_ext_bus *ebus)
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_power_down_all);
 
-int snd_hdac_ext_bus_link_get(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
 				struct hdac_ext_link *link)
 {
 	int ret = 0;
 
-	mutex_lock(&ebus->lock);
+	mutex_lock(&bus->lock);
 
 	/*
 	 * if we move from 0 to 1, count will be 1 so power up this link
 	 * as well, also check the dma status and trigger that
 	 */
 	if (++link->ref_count == 1) {
-		if (!ebus->cmd_dma_state) {
-			snd_hdac_bus_init_cmd_io(&ebus->bus);
-			ebus->cmd_dma_state = true;
+		if (!bus->cmd_dma_state) {
+			snd_hdac_bus_init_cmd_io(bus);
+			bus->cmd_dma_state = true;
 		}
 
 		ret = snd_hdac_ext_bus_link_power_up(link);
 	}
 
-	mutex_unlock(&ebus->lock);
+	mutex_unlock(&bus->lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_get);
 
-int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_bus_link_put(struct hdac_bus *bus,
 				struct hdac_ext_link *link)
 {
 	int ret = 0;
 	struct hdac_ext_link *hlink;
 	bool link_up = false;
 
-	mutex_lock(&ebus->lock);
+	mutex_lock(&bus->lock);
 
 	/*
 	 * if we move from 1 to 0, count will be 0
@@ -301,7 +298,7 @@ int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
 		 * now check if all links are off, if so turn off
 		 * cmd dma as well
 		 */
-		list_for_each_entry(hlink, &ebus->hlink_list, list) {
+		list_for_each_entry(hlink, &bus->hlink_list, list) {
 			if (hlink->ref_count) {
 				link_up = true;
 				break;
@@ -309,12 +306,12 @@ int snd_hdac_ext_bus_link_put(struct hdac_ext_bus *ebus,
 		}
 
 		if (!link_up) {
-			snd_hdac_bus_stop_cmd_io(&ebus->bus);
-			ebus->cmd_dma_state = false;
+			snd_hdac_bus_stop_cmd_io(bus);
+			bus->cmd_dma_state = false;
 		}
 	}
 
-	mutex_unlock(&ebus->lock);
+	mutex_unlock(&bus->lock);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_link_put);
diff --git a/sound/hda/ext/hdac_ext_stream.c b/sound/hda/ext/hdac_ext_stream.c
index c96d7a7a36af..1bd27576db98 100644
--- a/sound/hda/ext/hdac_ext_stream.c
+++ b/sound/hda/ext/hdac_ext_stream.c
@@ -25,7 +25,7 @@
 
 /**
  * snd_hdac_ext_stream_init - initialize each stream (aka device)
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: HD-audio ext core stream object to initialize
  * @idx: stream index number
  * @direction: stream direction (SNDRV_PCM_STREAM_PLAYBACK or SNDRV_PCM_STREAM_CAPTURE)
@@ -34,18 +34,16 @@
  * initialize the stream, if ppcap is enabled then init those and then
  * invoke hdac stream initialization routine
  */
-void snd_hdac_ext_stream_init(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_init(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream,
 				int idx, int direction, int tag)
 {
-	struct hdac_bus *bus = &ebus->bus;
-
 	if (bus->ppcap) {
 		stream->pphc_addr = bus->ppcap + AZX_PPHC_BASE +
 				AZX_PPHC_INTERVAL * idx;
 
 		stream->pplc_addr = bus->ppcap + AZX_PPLC_BASE +
-				AZX_PPLC_MULTI * ebus->num_streams +
+				AZX_PPLC_MULTI * bus->num_streams +
 				AZX_PPLC_INTERVAL * idx;
 	}
 
@@ -71,12 +69,12 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init);
 /**
  * snd_hdac_ext_stream_init_all - create and initialize the stream objects
  *   for an extended hda bus
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @start_idx: start index for streams
  * @num_stream: number of streams to initialize
  * @dir: direction of streams
  */
-int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx,
+int snd_hdac_ext_stream_init_all(struct hdac_bus *bus, int start_idx,
 		int num_stream, int dir)
 {
 	int stream_tag = 0;
@@ -88,7 +86,7 @@ int snd_hdac_ext_stream_init_all(struct hdac_ext_bus *ebus, int start_idx,
 		if (!stream)
 			return -ENOMEM;
 		tag = ++stream_tag;
-		snd_hdac_ext_stream_init(ebus, stream, idx, dir, tag);
+		snd_hdac_ext_stream_init(bus, stream, idx, dir, tag);
 		idx++;
 	}
 
@@ -100,17 +98,16 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_init_all);
 /**
  * snd_hdac_stream_free_all - free hdac extended stream objects
  *
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  */
-void snd_hdac_stream_free_all(struct hdac_ext_bus *ebus)
+void snd_hdac_stream_free_all(struct hdac_bus *bus)
 {
 	struct hdac_stream *s, *_s;
 	struct hdac_ext_stream *stream;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 
 	list_for_each_entry_safe(s, _s, &bus->stream_list, list) {
 		stream = stream_to_hdac_ext_stream(s);
-		snd_hdac_ext_stream_decouple(ebus, stream, false);
+		snd_hdac_ext_stream_decouple(bus, stream, false);
 		list_del(&s->list);
 		kfree(stream);
 	}
@@ -119,15 +116,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_stream_free_all);
 
 /**
  * snd_hdac_ext_stream_decouple - decouple the hdac stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: HD-audio ext core stream object to initialize
  * @decouple: flag to decouple
  */
-void snd_hdac_ext_stream_decouple(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_decouple(struct hdac_bus *bus,
 				struct hdac_ext_stream *stream, bool decouple)
 {
 	struct hdac_stream *hstream = &stream->hstream;
-	struct hdac_bus *bus = &ebus->bus;
 	u32 val;
 	int mask = AZX_PPCTL_PROCEN(hstream->index);
 
@@ -251,19 +247,18 @@ void snd_hdac_ext_link_clear_stream_id(struct hdac_ext_link *link,
 EXPORT_SYMBOL_GPL(snd_hdac_ext_link_clear_stream_id);
 
 static struct hdac_ext_stream *
-hdac_ext_link_stream_assign(struct hdac_ext_bus *ebus,
+hdac_ext_link_stream_assign(struct hdac_bus *bus,
 				struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *res = NULL;
 	struct hdac_stream *stream = NULL;
-	struct hdac_bus *hbus = &ebus->bus;
 
-	if (!hbus->ppcap) {
-		dev_err(hbus->dev, "stream type not supported\n");
+	if (!bus->ppcap) {
+		dev_err(bus->dev, "stream type not supported\n");
 		return NULL;
 	}
 
-	list_for_each_entry(stream, &hbus->stream_list, list) {
+	list_for_each_entry(stream, &bus->stream_list, list) {
 		struct hdac_ext_stream *hstream = container_of(stream,
 						struct hdac_ext_stream,
 						hstream);
@@ -277,34 +272,33 @@ hdac_ext_link_stream_assign(struct hdac_ext_bus *ebus,
 		}
 
 		if (!hstream->link_locked) {
-			snd_hdac_ext_stream_decouple(ebus, hstream, true);
+			snd_hdac_ext_stream_decouple(bus, hstream, true);
 			res = hstream;
 			break;
 		}
 	}
 	if (res) {
-		spin_lock_irq(&hbus->reg_lock);
+		spin_lock_irq(&bus->reg_lock);
 		res->link_locked = 1;
 		res->link_substream = substream;
-		spin_unlock_irq(&hbus->reg_lock);
+		spin_unlock_irq(&bus->reg_lock);
 	}
 	return res;
 }
 
 static struct hdac_ext_stream *
-hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
+hdac_ext_host_stream_assign(struct hdac_bus *bus,
 				struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *res = NULL;
 	struct hdac_stream *stream = NULL;
-	struct hdac_bus *hbus = &ebus->bus;
 
-	if (!hbus->ppcap) {
-		dev_err(hbus->dev, "stream type not supported\n");
+	if (!bus->ppcap) {
+		dev_err(bus->dev, "stream type not supported\n");
 		return NULL;
 	}
 
-	list_for_each_entry(stream, &hbus->stream_list, list) {
+	list_for_each_entry(stream, &bus->stream_list, list) {
 		struct hdac_ext_stream *hstream = container_of(stream,
 						struct hdac_ext_stream,
 						hstream);
@@ -313,17 +307,17 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
 
 		if (!stream->opened) {
 			if (!hstream->decoupled)
-				snd_hdac_ext_stream_decouple(ebus, hstream, true);
+				snd_hdac_ext_stream_decouple(bus, hstream, true);
 			res = hstream;
 			break;
 		}
 	}
 	if (res) {
-		spin_lock_irq(&hbus->reg_lock);
+		spin_lock_irq(&bus->reg_lock);
 		res->hstream.opened = 1;
 		res->hstream.running = 0;
 		res->hstream.substream = substream;
-		spin_unlock_irq(&hbus->reg_lock);
+		spin_unlock_irq(&bus->reg_lock);
 	}
 
 	return res;
@@ -331,7 +325,7 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
 
 /**
  * snd_hdac_ext_stream_assign - assign a stream for the PCM
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @substream: PCM substream to assign
  * @type: type of stream (coupled, host or link stream)
  *
@@ -346,27 +340,26 @@ hdac_ext_host_stream_assign(struct hdac_ext_bus *ebus,
  * the same stream object when it's used beforehand.  when a stream is
  * decoupled, it becomes a host stream and link stream.
  */
-struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_ext_bus *ebus,
+struct hdac_ext_stream *snd_hdac_ext_stream_assign(struct hdac_bus *bus,
 					   struct snd_pcm_substream *substream,
 					   int type)
 {
 	struct hdac_ext_stream *hstream = NULL;
 	struct hdac_stream *stream = NULL;
-	struct hdac_bus *hbus = &ebus->bus;
 
 	switch (type) {
 	case HDAC_EXT_STREAM_TYPE_COUPLED:
-		stream = snd_hdac_stream_assign(hbus, substream);
+		stream = snd_hdac_stream_assign(bus, substream);
 		if (stream)
 			hstream = container_of(stream,
 					struct hdac_ext_stream, hstream);
 		return hstream;
 
 	case HDAC_EXT_STREAM_TYPE_HOST:
-		return hdac_ext_host_stream_assign(ebus, substream);
+		return hdac_ext_host_stream_assign(bus, substream);
 
 	case HDAC_EXT_STREAM_TYPE_LINK:
-		return hdac_ext_link_stream_assign(ebus, substream);
+		return hdac_ext_link_stream_assign(bus, substream);
 
 	default:
 		return NULL;
@@ -384,7 +377,6 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_assign);
 void snd_hdac_ext_stream_release(struct hdac_ext_stream *stream, int type)
 {
 	struct hdac_bus *bus = stream->hstream.bus;
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 
 	switch (type) {
 	case HDAC_EXT_STREAM_TYPE_COUPLED:
@@ -393,13 +385,13 @@ void snd_hdac_ext_stream_release(struct hdac_ext_stream *stream, int type)
 
 	case HDAC_EXT_STREAM_TYPE_HOST:
 		if (stream->decoupled && !stream->link_locked)
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		snd_hdac_stream_release(&stream->hstream);
 		break;
 
 	case HDAC_EXT_STREAM_TYPE_LINK:
 		if (stream->decoupled && !stream->hstream.opened)
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		spin_lock_irq(&bus->reg_lock);
 		stream->link_locked = 0;
 		stream->link_substream = NULL;
@@ -415,16 +407,15 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_release);
 
 /**
  * snd_hdac_ext_stream_spbcap_enable - enable SPIB for a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @enable: flag to enable/disable SPIB
  * @index: stream index for which SPIB need to be enabled
  */
-void snd_hdac_ext_stream_spbcap_enable(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_spbcap_enable(struct hdac_bus *bus,
 				 bool enable, int index)
 {
 	u32 mask = 0;
 	u32 register_mask = 0;
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->spbcap) {
 		dev_err(bus->dev, "Address of SPB capability is NULL\n");
@@ -446,14 +437,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_spbcap_enable);
 
 /**
  * snd_hdac_ext_stream_set_spib - sets the spib value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  * @value: spib value to set
  */
-int snd_hdac_ext_stream_set_spib(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_spib(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream, u32 value)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->spbcap) {
 		dev_err(bus->dev, "Address of SPB capability is NULL\n");
@@ -468,15 +458,14 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_set_spib);
 
 /**
  * snd_hdac_ext_stream_get_spbmaxfifo - gets the spib value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  *
  * Return maxfifo for the stream
  */
-int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_get_spbmaxfifo(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->spbcap) {
 		dev_err(bus->dev, "Address of SPB capability is NULL\n");
@@ -490,11 +479,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_get_spbmaxfifo);
 
 /**
  * snd_hdac_ext_stop_streams - stop all stream if running
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  */
-void snd_hdac_ext_stop_streams(struct hdac_ext_bus *ebus)
+void snd_hdac_ext_stop_streams(struct hdac_bus *bus)
 {
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	struct hdac_stream *stream;
 
 	if (bus->chip_init) {
@@ -507,16 +495,15 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stop_streams);
 
 /**
  * snd_hdac_ext_stream_drsm_enable - enable DMA resume for a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @enable: flag to enable/disable DRSM
  * @index: stream index for which DRSM need to be enabled
  */
-void snd_hdac_ext_stream_drsm_enable(struct hdac_ext_bus *ebus,
+void snd_hdac_ext_stream_drsm_enable(struct hdac_bus *bus,
 				bool enable, int index)
 {
 	u32 mask = 0;
 	u32 register_mask = 0;
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->drsmcap) {
 		dev_err(bus->dev, "Address of DRSM capability is NULL\n");
@@ -538,14 +525,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_drsm_enable);
 
 /**
  * snd_hdac_ext_stream_set_dpibr - sets the dpibr value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  * @value: dpib value to set
  */
-int snd_hdac_ext_stream_set_dpibr(struct hdac_ext_bus *ebus,
+int snd_hdac_ext_stream_set_dpibr(struct hdac_bus *bus,
 				 struct hdac_ext_stream *stream, u32 value)
 {
-	struct hdac_bus *bus = &ebus->bus;
 
 	if (!bus->drsmcap) {
 		dev_err(bus->dev, "Address of DRSM capability is NULL\n");
@@ -560,7 +546,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_stream_set_dpibr);
 
 /**
  * snd_hdac_ext_stream_set_lpib - sets the lpib value of a stream
- * @ebus: HD-audio ext core bus
+ * @bus: HD-audio core bus
  * @stream: hdac_ext_stream
  * @value: lpib value to set
  */
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index f1e235817a65..c3ccc8d9c91d 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1799,14 +1799,13 @@ static int hdmi_codec_probe(struct snd_soc_component *component)
 	 * hold the ref while we probe, also no need to drop the ref on
 	 * exit, we call pm_runtime_suspend() so that will do for us
 	 */
-	hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus),
-						dev_name(&hdev->dev));
+	hlink = snd_hdac_ext_bus_get_link(hdev->bus, dev_name(&hdev->dev));
 	if (!hlink) {
 		dev_err(&hdev->dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink);
+	snd_hdac_ext_bus_link_get(hdev->bus, hlink);
 
 	ret = create_fill_widget_route_map(dapm);
 	if (ret < 0)
@@ -1984,14 +1983,13 @@ static int hdac_hdmi_dev_probe(struct hdac_device *hdev)
 	const struct hda_device_id *hdac_id = hdac_get_device_id(hdev, hdrv);
 
 	/* hold the ref while we probe */
-	hlink = snd_hdac_ext_bus_get_link(hbus_to_ebus(hdev->bus),
-						dev_name(&hdev->dev));
+	hlink = snd_hdac_ext_bus_get_link(hdev->bus, dev_name(&hdev->dev));
 	if (!hlink) {
 		dev_err(&hdev->dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(hbus_to_ebus(hdev->bus), hlink);
+	snd_hdac_ext_bus_link_get(hdev->bus, hlink);
 
 	hdmi_priv = devm_kzalloc(&hdev->dev, sizeof(*hdmi_priv), GFP_KERNEL);
 	if (hdmi_priv == NULL)
@@ -2044,7 +2042,7 @@ static int hdac_hdmi_dev_probe(struct hdac_device *hdev)
 	ret = devm_snd_soc_register_component(&hdev->dev, &hdmi_hda_codec,
 					hdmi_dais, num_dais);
 
-	snd_hdac_ext_bus_link_put(hbus_to_ebus(hdev->bus), hlink);
+	snd_hdac_ext_bus_link_put(hdev->bus, hlink);
 
 	return ret;
 }
@@ -2093,7 +2091,6 @@ static int hdac_hdmi_runtime_suspend(struct device *dev)
 {
 	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 	struct hdac_bus *bus = hdev->bus;
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink = NULL;
 	int err;
 
@@ -2118,13 +2115,13 @@ static int hdac_hdmi_runtime_suspend(struct device *dev)
 		return err;
 	}
 
-	hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev));
+	hlink = snd_hdac_ext_bus_get_link(bus, dev_name(dev));
 	if (!hlink) {
 		dev_err(dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_put(ebus, hlink);
+	snd_hdac_ext_bus_link_put(bus, hlink);
 
 	return 0;
 }
@@ -2133,7 +2130,6 @@ static int hdac_hdmi_runtime_resume(struct device *dev)
 {
 	struct hdac_device *hdev = dev_to_hdac_dev(dev);
 	struct hdac_bus *bus = hdev->bus;
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink = NULL;
 	int err;
 
@@ -2143,13 +2139,13 @@ static int hdac_hdmi_runtime_resume(struct device *dev)
 	if (!bus)
 		return 0;
 
-	hlink = snd_hdac_ext_bus_get_link(ebus, dev_name(dev));
+	hlink = snd_hdac_ext_bus_get_link(bus, dev_name(dev));
 	if (!hlink) {
 		dev_err(dev, "hdac link not found\n");
 		return -EIO;
 	}
 
-	snd_hdac_ext_bus_link_get(ebus, hlink);
+	snd_hdac_ext_bus_link_get(bus, hlink);
 
 	err = snd_hdac_display_power(bus, true);
 	if (err < 0) {
diff --git a/sound/soc/intel/skylake/skl-messages.c b/sound/soc/intel/skylake/skl-messages.c
index d5f9c30eba32..8bfb8b0fa3d5 100644
--- a/sound/soc/intel/skylake/skl-messages.c
+++ b/sound/soc/intel/skylake/skl-messages.c
@@ -33,8 +33,7 @@
 static int skl_alloc_dma_buf(struct device *dev,
 		struct snd_dma_buffer *dmab, size_t size)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 
 	if (!bus)
 		return -ENODEV;
@@ -44,8 +43,7 @@ static int skl_alloc_dma_buf(struct device *dev,
 
 static int skl_free_dma_buf(struct device *dev, struct snd_dma_buffer *dmab)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 
 	if (!bus)
 		return -ENODEV;
@@ -89,8 +87,7 @@ void skl_dsp_enable_notification(struct skl_sst *ctx, bool enable)
 static int skl_dsp_setup_spib(struct device *dev, unsigned int size,
 				int stream_tag, int enable)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_stream *stream = snd_hdac_get_stream(bus,
 			SNDRV_PCM_STREAM_PLAYBACK, stream_tag);
 	struct hdac_ext_stream *estream;
@@ -100,10 +97,10 @@ static int skl_dsp_setup_spib(struct device *dev, unsigned int size,
 
 	estream = stream_to_hdac_ext_stream(stream);
 	/* enable/disable SPIB for this hdac stream */
-	snd_hdac_ext_stream_spbcap_enable(ebus, enable, stream->index);
+	snd_hdac_ext_stream_spbcap_enable(bus, enable, stream->index);
 
 	/* set the spib value */
-	snd_hdac_ext_stream_set_spib(ebus, estream, size);
+	snd_hdac_ext_stream_set_spib(bus, estream, size);
 
 	return 0;
 }
@@ -111,8 +108,7 @@ static int skl_dsp_setup_spib(struct device *dev, unsigned int size,
 static int skl_dsp_prepare(struct device *dev, unsigned int format,
 			unsigned int size, struct snd_dma_buffer *dmab)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_ext_stream *estream;
 	struct hdac_stream *stream;
 	struct snd_pcm_substream substream;
@@ -124,7 +120,7 @@ static int skl_dsp_prepare(struct device *dev, unsigned int format,
 	memset(&substream, 0, sizeof(substream));
 	substream.stream = SNDRV_PCM_STREAM_PLAYBACK;
 
-	estream = snd_hdac_ext_stream_assign(ebus, &substream,
+	estream = snd_hdac_ext_stream_assign(bus, &substream,
 					HDAC_EXT_STREAM_TYPE_HOST);
 	if (!estream)
 		return -ENODEV;
@@ -143,9 +139,8 @@ static int skl_dsp_prepare(struct device *dev, unsigned int format,
 
 static int skl_dsp_trigger(struct device *dev, bool start, int stream_tag)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_stream *stream;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 
 	if (!bus)
 		return -ENODEV;
@@ -163,10 +158,9 @@ static int skl_dsp_trigger(struct device *dev, bool start, int stream_tag)
 static int skl_dsp_cleanup(struct device *dev,
 		struct snd_dma_buffer *dmab, int stream_tag)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	struct hdac_stream *stream;
 	struct hdac_ext_stream *estream;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 
 	if (!bus)
 		return -ENODEV;
@@ -270,8 +264,7 @@ const struct skl_dsp_ops *skl_get_dsp_ops(int pci_id)
 int skl_init_dsp(struct skl *skl)
 {
 	void __iomem *mmio_base;
-	struct hdac_ext_bus *ebus = &skl->ebus;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct skl_dsp_loader_ops loader_ops;
 	int irq = bus->irq;
 	const struct skl_dsp_ops *ops;
@@ -279,8 +272,8 @@ int skl_init_dsp(struct skl *skl)
 	int ret;
 
 	/* enable ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_enable(&skl->ebus, true);
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, true);
+	snd_hdac_ext_bus_ppcap_enable(bus, true);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, true);
 
 	/* read the BAR of the ADSP MMIO */
 	mmio_base = pci_ioremap_bar(skl->pci, 4);
@@ -335,12 +328,11 @@ unmap_mmio:
 
 int skl_free_dsp(struct skl *skl)
 {
-	struct hdac_ext_bus *ebus = &skl->ebus;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct skl_sst *ctx = skl->skl_sst;
 
 	/* disable  ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, false);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, false);
 
 	ctx->dsp_ops->cleanup(bus->dev, ctx);
 
@@ -383,10 +375,11 @@ int skl_suspend_late_dsp(struct skl *skl)
 int skl_suspend_dsp(struct skl *skl)
 {
 	struct skl_sst *ctx = skl->skl_sst;
+	struct hdac_bus *bus = skl_to_bus(skl);
 	int ret;
 
 	/* if ppcap is not supported return 0 */
-	if (!skl->ebus.bus.ppcap)
+	if (!bus->ppcap)
 		return 0;
 
 	ret = skl_dsp_sleep(ctx->dsp);
@@ -394,8 +387,8 @@ int skl_suspend_dsp(struct skl *skl)
 		return ret;
 
 	/* disable ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, false);
-	snd_hdac_ext_bus_ppcap_enable(&skl->ebus, false);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, false);
+	snd_hdac_ext_bus_ppcap_enable(bus, false);
 
 	return 0;
 }
@@ -403,15 +396,16 @@ int skl_suspend_dsp(struct skl *skl)
 int skl_resume_dsp(struct skl *skl)
 {
 	struct skl_sst *ctx = skl->skl_sst;
+	struct hdac_bus *bus = skl_to_bus(skl);
 	int ret;
 
 	/* if ppcap is not supported return 0 */
-	if (!skl->ebus.bus.ppcap)
+	if (!bus->ppcap)
 		return 0;
 
 	/* enable ppcap interrupt */
-	snd_hdac_ext_bus_ppcap_enable(&skl->ebus, true);
-	snd_hdac_ext_bus_ppcap_int_enable(&skl->ebus, true);
+	snd_hdac_ext_bus_ppcap_enable(bus, true);
+	snd_hdac_ext_bus_ppcap_int_enable(bus, true);
 
 	/* check if DSP 1st boot is done */
 	if (skl->skl_sst->is_first_boot == true)
diff --git a/sound/soc/intel/skylake/skl-nhlt.c b/sound/soc/intel/skylake/skl-nhlt.c
index b9b140275be0..01a050cf8775 100644
--- a/sound/soc/intel/skylake/skl-nhlt.c
+++ b/sound/soc/intel/skylake/skl-nhlt.c
@@ -141,7 +141,7 @@ struct nhlt_specific_cfg
 {
 	struct nhlt_fmt *fmt;
 	struct nhlt_endpoint *epnt;
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct device *dev = bus->dev;
 	struct nhlt_specific_cfg *sp_config;
 	struct nhlt_acpi_table *nhlt = skl->nhlt;
@@ -228,7 +228,7 @@ static void skl_nhlt_trim_space(char *trim)
 int skl_nhlt_update_topology_bin(struct skl *skl)
 {
 	struct nhlt_acpi_table *nhlt = (struct nhlt_acpi_table *)skl->nhlt;
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct device *dev = bus->dev;
 
 	dev_dbg(dev, "oem_id %.6s, oem_table_id %8s oem_revision %d\n",
@@ -248,8 +248,8 @@ static ssize_t skl_nhlt_platform_id_show(struct device *dev,
 			struct device_attribute *attr, char *buf)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl = bus_to_skl(bus);
 	struct nhlt_acpi_table *nhlt = (struct nhlt_acpi_table *)skl->nhlt;
 	char platform_id[32];
 
diff --git a/sound/soc/intel/skylake/skl-pcm.c b/sound/soc/intel/skylake/skl-pcm.c
index afa86b9e4dcf..d7fc3b2d3e68 100644
--- a/sound/soc/intel/skylake/skl-pcm.c
+++ b/sound/soc/intel/skylake/skl-pcm.c
@@ -67,16 +67,15 @@ struct hdac_ext_stream *get_hdac_ext_stream(struct snd_pcm_substream *substream)
 	return substream->runtime->private_data;
 }
 
-static struct hdac_ext_bus *get_bus_ctx(struct snd_pcm_substream *substream)
+static struct hdac_bus *get_bus_ctx(struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct hdac_stream *hstream = hdac_stream(stream);
 	struct hdac_bus *bus = hstream->bus;
-
-	return hbus_to_ebus(bus);
+	return bus;
 }
 
-static int skl_substream_alloc_pages(struct hdac_ext_bus *ebus,
+static int skl_substream_alloc_pages(struct hdac_bus *bus,
 				 struct snd_pcm_substream *substream,
 				 size_t size)
 {
@@ -95,7 +94,7 @@ static int skl_substream_free_pages(struct hdac_bus *bus,
 	return snd_pcm_lib_free_pages(substream);
 }
 
-static void skl_set_pcm_constrains(struct hdac_ext_bus *ebus,
+static void skl_set_pcm_constrains(struct hdac_bus *bus,
 				 struct snd_pcm_runtime *runtime)
 {
 	snd_pcm_hw_constraint_integer(runtime, SNDRV_PCM_HW_PARAM_PERIODS);
@@ -105,9 +104,9 @@ static void skl_set_pcm_constrains(struct hdac_ext_bus *ebus,
 				     20, 178000000);
 }
 
-static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_ext_bus *ebus)
+static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_bus *bus)
 {
-	if ((ebus_to_hbus(ebus))->ppcap)
+	if (bus->ppcap)
 		return HDAC_EXT_STREAM_TYPE_HOST;
 	else
 		return HDAC_EXT_STREAM_TYPE_COUPLED;
@@ -123,9 +122,9 @@ static enum hdac_ext_stream_type skl_get_host_stream_type(struct hdac_ext_bus *e
 static void skl_set_suspend_active(struct snd_pcm_substream *substream,
 					 struct snd_soc_dai *dai, bool enable)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct snd_soc_dapm_widget *w;
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
 		w = dai->playback_widget;
@@ -140,8 +139,7 @@ static void skl_set_suspend_active(struct snd_pcm_substream *substream,
 
 int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	unsigned int format_val;
 	struct hdac_stream *hstream;
 	struct hdac_ext_stream *stream;
@@ -153,7 +151,7 @@ int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 		return -EINVAL;
 
 	stream = stream_to_hdac_ext_stream(hstream);
-	snd_hdac_ext_stream_decouple(ebus, stream, true);
+	snd_hdac_ext_stream_decouple(bus, stream, true);
 
 	format_val = snd_hdac_calc_stream_format(params->s_freq,
 			params->ch, params->format, params->host_bps, 0);
@@ -177,8 +175,7 @@ int skl_pcm_host_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 
 int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 	unsigned int format_val;
 	struct hdac_stream *hstream;
 	struct hdac_ext_stream *stream;
@@ -190,7 +187,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 		return -EINVAL;
 
 	stream = stream_to_hdac_ext_stream(hstream);
-	snd_hdac_ext_stream_decouple(ebus, stream, true);
+	snd_hdac_ext_stream_decouple(bus, stream, true);
 	format_val = snd_hdac_calc_stream_format(params->s_freq, params->ch,
 					params->format, params->link_bps, 0);
 
@@ -201,7 +198,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 
 	snd_hdac_ext_link_stream_setup(stream, format_val);
 
-	list_for_each_entry(link, &ebus->hlink_list, list) {
+	list_for_each_entry(link, &bus->hlink_list, list) {
 		if (link->index == params->link_index)
 			snd_hdac_ext_link_set_stream_id(link,
 					hstream->stream_tag);
@@ -215,7 +212,7 @@ int skl_pcm_link_dma_prepare(struct device *dev, struct skl_pipe_params *params)
 static int skl_pcm_open(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *stream;
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct skl_dma_params *dma_params;
@@ -224,12 +221,12 @@ static int skl_pcm_open(struct snd_pcm_substream *substream,
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
-	stream = snd_hdac_ext_stream_assign(ebus, substream,
-					skl_get_host_stream_type(ebus));
+	stream = snd_hdac_ext_stream_assign(bus, substream,
+					skl_get_host_stream_type(bus));
 	if (stream == NULL)
 		return -EBUSY;
 
-	skl_set_pcm_constrains(ebus, runtime);
+	skl_set_pcm_constrains(bus, runtime);
 
 	/*
 	 * disable WALLCLOCK timestamps for capture streams
@@ -301,7 +298,7 @@ static int skl_pcm_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params,
 				struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct skl_pipe_params p_params = {0};
@@ -309,7 +306,7 @@ static int skl_pcm_hw_params(struct snd_pcm_substream *substream,
 	int ret, dma_id;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
-	ret = skl_substream_alloc_pages(ebus, substream,
+	ret = skl_substream_alloc_pages(bus, substream,
 					  params_buffer_bytes(params));
 	if (ret < 0)
 		return ret;
@@ -343,14 +340,14 @@ static void skl_pcm_close(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct skl_dma_params *dma_params = NULL;
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_module_cfg *mconfig;
 
 	dev_dbg(dai->dev, "%s: %s\n", __func__, dai->name);
 
-	snd_hdac_ext_stream_release(stream, skl_get_host_stream_type(ebus));
+	snd_hdac_ext_stream_release(stream, skl_get_host_stream_type(bus));
 
 	dma_params = snd_soc_dai_get_dma_data(dai, substream);
 	/*
@@ -380,7 +377,7 @@ static void skl_pcm_close(struct snd_pcm_substream *substream,
 static int skl_pcm_hw_free(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct skl *skl = get_skl_ctx(dai->dev);
 	struct skl_module_cfg *mconfig;
@@ -400,7 +397,7 @@ static int skl_pcm_hw_free(struct snd_pcm_substream *substream,
 	snd_hdac_stream_cleanup(hdac_stream(stream));
 	hdac_stream(stream)->prepared = 0;
 
-	return skl_substream_free_pages(ebus_to_hbus(ebus), substream);
+	return skl_substream_free_pages(bus, substream);
 }
 
 static int skl_be_hw_params(struct snd_pcm_substream *substream,
@@ -420,8 +417,7 @@ static int skl_be_hw_params(struct snd_pcm_substream *substream,
 static int skl_decoupled_trigger(struct snd_pcm_substream *substream,
 		int cmd)
 {
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream;
 	int start;
 	unsigned long cookie;
@@ -470,7 +466,7 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 	struct skl *skl = get_skl_ctx(dai->dev);
 	struct skl_sst *ctx = skl->skl_sst;
 	struct skl_module_cfg *mconfig;
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 	struct snd_soc_dapm_widget *w;
 	int ret;
@@ -492,9 +488,9 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 			 * dpib & lpib position to resume before starting the
 			 * DMA
 			 */
-			snd_hdac_ext_stream_drsm_enable(ebus, true,
+			snd_hdac_ext_stream_drsm_enable(bus, true,
 						hdac_stream(stream)->index);
-			snd_hdac_ext_stream_set_dpibr(ebus, stream,
+			snd_hdac_ext_stream_set_dpibr(bus, stream,
 							stream->lpib);
 			snd_hdac_ext_stream_set_lpib(stream, stream->lpib);
 		}
@@ -528,14 +524,14 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 		ret = skl_decoupled_trigger(substream, cmd);
 		if ((cmd == SNDRV_PCM_TRIGGER_SUSPEND) && !w->ignore_suspend) {
 			/* save the dpib and lpib positions */
-			stream->dpib = readl(ebus->bus.remap_addr +
+			stream->dpib = readl(bus->remap_addr +
 					AZX_REG_VS_SDXDPIB_XBASE +
 					(AZX_REG_VS_SDXDPIB_XINTERVAL *
 					hdac_stream(stream)->index));
 
 			stream->lpib = snd_hdac_stream_get_pos_lpib(
 							hdac_stream(stream));
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		}
 		break;
 
@@ -546,11 +542,12 @@ static int skl_pcm_trigger(struct snd_pcm_substream *substream, int cmd,
 	return 0;
 }
 
+
 static int skl_link_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params,
 				struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct hdac_ext_stream *link_dev;
 	struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream);
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
@@ -558,14 +555,14 @@ static int skl_link_hw_params(struct snd_pcm_substream *substream,
 	struct hdac_ext_link *link;
 	int stream_tag;
 
-	link_dev = snd_hdac_ext_stream_assign(ebus, substream,
+	link_dev = snd_hdac_ext_stream_assign(bus, substream,
 					HDAC_EXT_STREAM_TYPE_LINK);
 	if (!link_dev)
 		return -EBUSY;
 
 	snd_soc_dai_set_dma_data(dai, substream, (void *)link_dev);
 
-	link = snd_hdac_ext_bus_get_link(ebus, codec_dai->component->name);
+	link = snd_hdac_ext_bus_get_link(bus, codec_dai->component->name);
 	if (!link)
 		return -EINVAL;
 
@@ -610,7 +607,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream,
 {
 	struct hdac_ext_stream *link_dev =
 				snd_soc_dai_get_dma_data(dai, substream);
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream = get_hdac_ext_stream(substream);
 
 	dev_dbg(dai->dev, "In %s cmd=%d\n", __func__, cmd);
@@ -626,7 +623,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream,
 	case SNDRV_PCM_TRIGGER_STOP:
 		snd_hdac_ext_link_stream_clear(link_dev);
 		if (cmd == SNDRV_PCM_TRIGGER_SUSPEND)
-			snd_hdac_ext_stream_decouple(ebus, stream, false);
+			snd_hdac_ext_stream_decouple(bus, stream, false);
 		break;
 
 	default:
@@ -638,7 +635,7 @@ static int skl_link_pcm_trigger(struct snd_pcm_substream *substream,
 static int skl_link_hw_free(struct snd_pcm_substream *substream,
 		struct snd_soc_dai *dai)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct snd_soc_pcm_runtime *rtd = snd_pcm_substream_chip(substream);
 	struct hdac_ext_stream *link_dev =
 				snd_soc_dai_get_dma_data(dai, substream);
@@ -648,7 +645,7 @@ static int skl_link_hw_free(struct snd_pcm_substream *substream,
 
 	link_dev->link_prepared = 0;
 
-	link = snd_hdac_ext_bus_get_link(ebus, rtd->codec_dai->component->name);
+	link = snd_hdac_ext_bus_get_link(bus, rtd->codec_dai->component->name);
 	if (!link)
 		return -EINVAL;
 
@@ -1041,8 +1038,7 @@ static int skl_platform_open(struct snd_pcm_substream *substream)
 static int skl_coupled_trigger(struct snd_pcm_substream *substream,
 					int cmd)
 {
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	struct hdac_ext_stream *stream;
 	struct snd_pcm_substream *s;
 	bool start;
@@ -1115,9 +1111,9 @@ static int skl_coupled_trigger(struct snd_pcm_substream *substream,
 static int skl_platform_pcm_trigger(struct snd_pcm_substream *substream,
 					int cmd)
 {
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 
-	if (!(ebus_to_hbus(ebus))->ppcap)
+	if (!bus->ppcap)
 		return skl_coupled_trigger(substream, cmd);
 
 	return 0;
@@ -1127,7 +1123,7 @@ static snd_pcm_uframes_t skl_platform_pcm_pointer
 			(struct snd_pcm_substream *substream)
 {
 	struct hdac_ext_stream *hstream = get_hdac_ext_stream(substream);
-	struct hdac_ext_bus *ebus = get_bus_ctx(substream);
+	struct hdac_bus *bus = get_bus_ctx(substream);
 	unsigned int pos;
 
 	/*
@@ -1152,12 +1148,12 @@ static snd_pcm_uframes_t skl_platform_pcm_pointer
 	 */
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-		pos = readl(ebus->bus.remap_addr + AZX_REG_VS_SDXDPIB_XBASE +
+		pos = readl(bus->remap_addr + AZX_REG_VS_SDXDPIB_XBASE +
 				(AZX_REG_VS_SDXDPIB_XINTERVAL *
 				hdac_stream(hstream)->index));
 	} else {
 		udelay(20);
-		readl(ebus->bus.remap_addr +
+		readl(bus->remap_addr +
 				AZX_REG_VS_SDXDPIB_XBASE +
 				(AZX_REG_VS_SDXDPIB_XINTERVAL *
 				 hdac_stream(hstream)->index));
@@ -1242,11 +1238,11 @@ static void skl_pcm_free(struct snd_pcm *pcm)
 static int skl_pcm_new(struct snd_soc_pcm_runtime *rtd)
 {
 	struct snd_soc_dai *dai = rtd->cpu_dai;
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dai->dev);
+	struct hdac_bus *bus = dev_get_drvdata(dai->dev);
 	struct snd_pcm *pcm = rtd->pcm;
 	unsigned int size;
 	int retval = 0;
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 
 	if (dai->driver->playback.channels_min ||
 		dai->driver->capture.channels_min) {
@@ -1356,19 +1352,19 @@ static int skl_populate_modules(struct skl *skl)
 
 static int skl_platform_soc_probe(struct snd_soc_component *component)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(component->dev);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(component->dev);
+	struct skl *skl = bus_to_skl(bus);
 	const struct skl_dsp_ops *ops;
 	int ret;
 
 	pm_runtime_get_sync(component->dev);
-	if ((ebus_to_hbus(ebus))->ppcap) {
+	if (bus->ppcap) {
 		skl->component = component;
 
 		/* init debugfs */
 		skl->debugfs = skl_debugfs_init(skl);
 
-		ret = skl_tplg_init(component, ebus);
+		ret = skl_tplg_init(component, bus);
 		if (ret < 0) {
 			dev_err(component->dev, "Failed to init topology!\n");
 			return ret;
@@ -1425,10 +1421,10 @@ static const struct snd_soc_component_driver skl_component  = {
 int skl_platform_register(struct device *dev)
 {
 	int ret;
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct skl *skl = ebus_to_skl(ebus);
 	struct snd_soc_dai_driver *dais;
 	int num_dais = ARRAY_SIZE(skl_platform_dai);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
+	struct skl *skl = bus_to_skl(bus);
 
 	INIT_LIST_HEAD(&skl->ppl_list);
 	INIT_LIST_HEAD(&skl->bind_list);
@@ -1464,8 +1460,8 @@ err:
 
 int skl_platform_unregister(struct device *dev)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_module_deferred_bind *modules, *tmp;
 
 	if (!list_empty(&skl->bind_list)) {
diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index fcdc716754b6..abfdb67c05cc 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -934,7 +934,7 @@ static int skl_tplg_find_moduleid_from_uuid(struct skl *skl,
 	struct soc_bytes_ext *sb = (void *) k->private_value;
 	struct skl_algo_data *bc = (struct skl_algo_data *)sb->dobj.private;
 	struct skl_kpb_params *uuid_params, *params;
-	struct hdac_bus *bus = ebus_to_hbus(skl_to_ebus(skl));
+	struct hdac_bus *bus = skl_to_bus(skl);
 	int i, size, module_id;
 
 	if (bc->set_params == SKL_PARAM_BIND && bc->max) {
@@ -3029,9 +3029,8 @@ static int skl_tplg_widget_load(struct snd_soc_component *cmpnt,
 				struct snd_soc_tplg_dapm_widget *tplg_w)
 {
 	int ret;
-	struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt);
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = snd_soc_component_get_drvdata(cmpnt);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_module_cfg *mconfig;
 
 	if (!tplg_w->priv.size)
@@ -3137,8 +3136,7 @@ static int skl_tplg_control_load(struct snd_soc_component *cmpnt,
 	struct soc_bytes_ext *sb;
 	struct snd_soc_tplg_bytes_control *tplg_bc;
 	struct snd_soc_tplg_enum_control *tplg_ec;
-	struct hdac_ext_bus *ebus  = snd_soc_component_get_drvdata(cmpnt);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus  = snd_soc_component_get_drvdata(cmpnt);
 	struct soc_enum *se;
 
 	switch (hdr->ops.info) {
@@ -3622,9 +3620,8 @@ static int skl_tplg_get_manifest_data(struct snd_soc_tplg_manifest *manifest,
 static int skl_manifest_load(struct snd_soc_component *cmpnt,
 				struct snd_soc_tplg_manifest *manifest)
 {
-	struct hdac_ext_bus *ebus = snd_soc_component_get_drvdata(cmpnt);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = snd_soc_component_get_drvdata(cmpnt);
+	struct skl *skl = bus_to_skl(bus);
 
 	/* proceed only if we have private data defined */
 	if (manifest->priv.size == 0)
@@ -3713,12 +3710,11 @@ static void skl_tplg_set_pipe_type(struct skl *skl, struct skl_pipe *pipe)
 /*
  * SKL topology init routine
  */
-int skl_tplg_init(struct snd_soc_component *component, struct hdac_ext_bus *ebus)
+int skl_tplg_init(struct snd_soc_component *component, struct hdac_bus *bus)
 {
 	int ret;
 	const struct firmware *fw;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct skl_pipeline *ppl;
 
 	ret = request_firmware(&fw, skl->tplg_name, bus->dev);
diff --git a/sound/soc/intel/skylake/skl-topology.h b/sound/soc/intel/skylake/skl-topology.h
index 6d7e0569695f..daeb6d2bb7fc 100644
--- a/sound/soc/intel/skylake/skl-topology.h
+++ b/sound/soc/intel/skylake/skl-topology.h
@@ -458,9 +458,9 @@ enum skl_channel {
 
 static inline struct skl *get_skl_ctx(struct device *dev)
 {
-	struct hdac_ext_bus *ebus = dev_get_drvdata(dev);
+	struct hdac_bus *bus = dev_get_drvdata(dev);
 
-	return ebus_to_skl(ebus);
+	return bus_to_skl(bus);
 }
 
 int skl_tplg_be_update_params(struct snd_soc_dai *dai,
@@ -470,7 +470,7 @@ int skl_dsp_set_dma_control(struct skl_sst *ctx, u32 *caps,
 void skl_tplg_set_be_dmic_config(struct snd_soc_dai *dai,
 	struct skl_pipe_params *params, int stream);
 int skl_tplg_init(struct snd_soc_component *component,
-				struct hdac_ext_bus *ebus);
+				struct hdac_bus *ebus);
 struct skl_module_cfg *skl_tplg_fe_get_cpr_module(
 		struct snd_soc_dai *dai, int stream);
 int skl_tplg_update_pipe_params(struct device *dev,
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index f0d9793f872a..9c5a701d68ac 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -54,7 +54,7 @@ static void skl_update_pci_byte(struct pci_dev *pci, unsigned int reg,
 
 static void skl_init_pci(struct skl *skl)
 {
-	struct hdac_ext_bus *ebus = &skl->ebus;
+	struct hdac_bus *bus = skl_to_bus(skl);
 
 	/*
 	 * Clear bits 0-2 of PCI register TCSEL (at offset 0x44)
@@ -63,7 +63,7 @@ static void skl_init_pci(struct skl *skl)
 	 * codecs.
 	 * The PCI register TCSEL is defined in the Intel manuals.
 	 */
-	dev_dbg(ebus_to_hbus(ebus)->dev, "Clearing TCSEL\n");
+	dev_dbg(bus->dev, "Clearing TCSEL\n");
 	skl_update_pci_byte(skl->pci, AZX_PCIREG_TCSEL, 0x07, 0);
 }
 
@@ -103,8 +103,7 @@ static void skl_enable_miscbdcge(struct device *dev, bool enable)
 static void skl_clock_power_gating(struct device *dev, bool enable)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 	u32 val;
 
 	/* Update PDCGE bit of CGCTL register */
@@ -127,7 +126,6 @@ static void skl_clock_power_gating(struct device *dev, bool enable)
  */
 static int skl_init_chip(struct hdac_bus *bus, bool full_reset)
 {
-	struct hdac_ext_bus *ebus = hbus_to_ebus(bus);
 	struct hdac_ext_link *hlink;
 	int ret;
 
@@ -135,7 +133,7 @@ static int skl_init_chip(struct hdac_bus *bus, bool full_reset)
 	ret = snd_hdac_bus_init_chip(bus, full_reset);
 
 	/* Reset stream-to-link mapping */
-	list_for_each_entry(hlink, &ebus->hlink_list, list)
+	list_for_each_entry(hlink, &bus->hlink_list, list)
 		bus->io_ops->reg_writel(0, hlink->ml_addr + AZX_REG_ML_LOSIDV);
 
 	skl_enable_miscbdcge(bus->dev, true);
@@ -146,8 +144,7 @@ static int skl_init_chip(struct hdac_bus *bus, bool full_reset)
 void skl_update_d0i3c(struct device *dev, bool enable)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 	u8 reg;
 	int timeout = 50;
 
@@ -197,8 +194,7 @@ static void skl_stream_update(struct hdac_bus *bus, struct hdac_stream *hstr)
 
 static irqreturn_t skl_interrupt(int irq, void *dev_id)
 {
-	struct hdac_ext_bus *ebus = dev_id;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_id;
 	u32 status;
 
 	if (!pm_runtime_active(bus->dev))
@@ -227,8 +223,7 @@ static irqreturn_t skl_interrupt(int irq, void *dev_id)
 
 static irqreturn_t skl_threaded_handler(int irq, void *dev_id)
 {
-	struct hdac_ext_bus *ebus = dev_id;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = dev_id;
 	u32 status;
 
 	status = snd_hdac_chip_readl(bus, INTSTS);
@@ -238,16 +233,15 @@ static irqreturn_t skl_threaded_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static int skl_acquire_irq(struct hdac_ext_bus *ebus, int do_disconnect)
+static int skl_acquire_irq(struct hdac_bus *bus, int do_disconnect)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	int ret;
 
 	ret = request_threaded_irq(skl->pci->irq, skl_interrupt,
 			skl_threaded_handler,
 			IRQF_SHARED,
-			KBUILD_MODNAME, ebus);
+			KBUILD_MODNAME, bus);
 	if (ret) {
 		dev_err(bus->dev,
 			"unable to grab IRQ %d, disabling device\n",
@@ -264,21 +258,20 @@ static int skl_acquire_irq(struct hdac_ext_bus *ebus, int do_disconnect)
 static int skl_suspend_late(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl = bus_to_skl(bus);
 
 	return skl_suspend_late_dsp(skl);
 }
 
 #ifdef CONFIG_PM
-static int _skl_suspend(struct hdac_ext_bus *ebus)
+static int _skl_suspend(struct hdac_bus *bus)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct pci_dev *pci = to_pci_dev(bus->dev);
 	int ret;
 
-	snd_hdac_ext_bus_link_power_down_all(ebus);
+	snd_hdac_ext_bus_link_power_down_all(bus);
 
 	ret = skl_suspend_dsp(skl);
 	if (ret < 0)
@@ -295,10 +288,9 @@ static int _skl_suspend(struct hdac_ext_bus *ebus)
 	return 0;
 }
 
-static int _skl_resume(struct hdac_ext_bus *ebus)
+static int _skl_resume(struct hdac_bus *bus)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 
 	skl_init_pci(skl);
 	skl_init_chip(bus, true);
@@ -314,9 +306,8 @@ static int _skl_resume(struct hdac_ext_bus *ebus)
 static int skl_suspend(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl  = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl  = bus_to_skl(bus);
 	int ret = 0;
 
 	/*
@@ -325,15 +316,15 @@ static int skl_suspend(struct device *dev)
 	 */
 	if (skl->supend_active) {
 		/* turn off the links and stop the CORB/RIRB DMA if it is On */
-		snd_hdac_ext_bus_link_power_down_all(ebus);
+		snd_hdac_ext_bus_link_power_down_all(bus);
 
-		if (ebus->cmd_dma_state)
-			snd_hdac_bus_stop_cmd_io(&ebus->bus);
+		if (bus->cmd_dma_state)
+			snd_hdac_bus_stop_cmd_io(bus);
 
 		enable_irq_wake(bus->irq);
 		pci_save_state(pci);
 	} else {
-		ret = _skl_suspend(ebus);
+		ret = _skl_suspend(bus);
 		if (ret < 0)
 			return ret;
 		skl->skl_sst->fw_loaded = false;
@@ -352,9 +343,8 @@ static int skl_suspend(struct device *dev)
 static int skl_resume(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl  = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl  = bus_to_skl(bus);
 	struct hdac_ext_link *hlink = NULL;
 	int ret;
 
@@ -374,32 +364,32 @@ static int skl_resume(struct device *dev)
 	 */
 	if (skl->supend_active) {
 		pci_restore_state(pci);
-		snd_hdac_ext_bus_link_power_up_all(ebus);
+		snd_hdac_ext_bus_link_power_up_all(bus);
 		disable_irq_wake(bus->irq);
 		/*
 		 * turn On the links which are On before active suspend
 		 * and start the CORB/RIRB DMA if On before
 		 * active suspend.
 		 */
-		list_for_each_entry(hlink, &ebus->hlink_list, list) {
+		list_for_each_entry(hlink, &bus->hlink_list, list) {
 			if (hlink->ref_count)
 				snd_hdac_ext_bus_link_power_up(hlink);
 		}
 
-		if (ebus->cmd_dma_state)
-			snd_hdac_bus_init_cmd_io(&ebus->bus);
 		ret = 0;
+		if (bus->cmd_dma_state)
+			snd_hdac_bus_init_cmd_io(bus);
 	} else {
-		ret = _skl_resume(ebus);
+		ret = _skl_resume(bus);
 
 		/* turn off the links which are off before suspend */
-		list_for_each_entry(hlink, &ebus->hlink_list, list) {
+		list_for_each_entry(hlink, &bus->hlink_list, list) {
 			if (!hlink->ref_count)
 				snd_hdac_ext_bus_link_power_down(hlink);
 		}
 
-		if (!ebus->cmd_dma_state)
-			snd_hdac_bus_stop_cmd_io(&ebus->bus);
+		if (!bus->cmd_dma_state)
+			snd_hdac_bus_stop_cmd_io(bus);
 	}
 
 	return ret;
@@ -410,23 +400,21 @@ static int skl_resume(struct device *dev)
 static int skl_runtime_suspend(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 
 	dev_dbg(bus->dev, "in %s\n", __func__);
 
-	return _skl_suspend(ebus);
+	return _skl_suspend(bus);
 }
 
 static int skl_runtime_resume(struct device *dev)
 {
 	struct pci_dev *pci = to_pci_dev(dev);
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 
 	dev_dbg(bus->dev, "in %s\n", __func__);
 
-	return _skl_resume(ebus);
+	return _skl_resume(bus);
 }
 #endif /* CONFIG_PM */
 
@@ -439,20 +427,19 @@ static const struct dev_pm_ops skl_pm = {
 /*
  * destructor
  */
-static int skl_free(struct hdac_ext_bus *ebus)
+static int skl_free(struct hdac_bus *bus)
 {
-	struct skl *skl  = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl  = bus_to_skl(bus);
 
 	skl->init_done = 0; /* to be sure */
 
-	snd_hdac_ext_stop_streams(ebus);
+	snd_hdac_ext_stop_streams(bus);
 
 	if (bus->irq >= 0)
-		free_irq(bus->irq, (void *)ebus);
+		free_irq(bus->irq, (void *)bus);
 	snd_hdac_bus_free_stream_pages(bus);
-	snd_hdac_stream_free_all(ebus);
-	snd_hdac_link_free_all(ebus);
+	snd_hdac_stream_free_all(bus);
+	snd_hdac_link_free_all(bus);
 
 	if (bus->remap_addr)
 		iounmap(bus->remap_addr);
@@ -460,11 +447,11 @@ static int skl_free(struct hdac_ext_bus *ebus)
 	pci_release_regions(skl->pci);
 	pci_disable_device(skl->pci);
 
-	snd_hdac_ext_bus_exit(ebus);
+	snd_hdac_ext_bus_exit(bus);
 
 	cancel_work_sync(&skl->probe_work);
 	if (IS_ENABLED(CONFIG_SND_SOC_HDAC_HDMI))
-		snd_hdac_i915_exit(&ebus->bus);
+		snd_hdac_i915_exit(bus);
 
 	return 0;
 }
@@ -488,8 +475,8 @@ static struct skl_ssp_clk skl_ssp_clks[] = {
 
 static int skl_find_machine(struct skl *skl, void *driver_data)
 {
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct snd_soc_acpi_mach *mach = driver_data;
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
 	struct skl_machine_pdata *pdata;
 
 	mach = snd_soc_acpi_find_machine(mach);
@@ -510,7 +497,7 @@ static int skl_find_machine(struct skl *skl, void *driver_data)
 
 static int skl_machine_device_register(struct skl *skl)
 {
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct snd_soc_acpi_mach *mach = skl->mach;
 	struct platform_device *pdev;
 	int ret;
@@ -544,7 +531,7 @@ static void skl_machine_device_unregister(struct skl *skl)
 
 static int skl_dmic_device_register(struct skl *skl)
 {
-	struct hdac_bus *bus = ebus_to_hbus(&skl->ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct platform_device *pdev;
 	int ret;
 
@@ -643,9 +630,8 @@ static void skl_clock_device_unregister(struct skl *skl)
 /*
  * Probe the given codec address
  */
-static int probe_codec(struct hdac_ext_bus *ebus, int addr)
+static int probe_codec(struct hdac_bus *bus, int addr)
 {
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	unsigned int cmd = (addr << 28) | (AC_NODE_ROOT << 20) |
 		(AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID;
 	unsigned int res = -1;
@@ -658,13 +644,12 @@ static int probe_codec(struct hdac_ext_bus *ebus, int addr)
 		return -EIO;
 	dev_dbg(bus->dev, "codec #%d probed OK\n", addr);
 
-	return snd_hdac_ext_bus_device_init(ebus, addr);
+	return snd_hdac_ext_bus_device_init(bus, addr);
 }
 
 /* Codec initialization */
-static void skl_codec_create(struct hdac_ext_bus *ebus)
+static void skl_codec_create(struct hdac_bus *bus)
 {
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
 	int c, max_slots;
 
 	max_slots = HDA_MAX_CODECS;
@@ -672,7 +657,7 @@ static void skl_codec_create(struct hdac_ext_bus *ebus)
 	/* First try to probe all given codec slots */
 	for (c = 0; c < max_slots; c++) {
 		if ((bus->codec_mask & (1 << c))) {
-			if (probe_codec(ebus, c) < 0) {
+			if (probe_codec(bus, c) < 0) {
 				/*
 				 * Some BIOSen give you wrong codec addresses
 				 * that don't exist
@@ -722,8 +707,7 @@ static int skl_i915_init(struct hdac_bus *bus)
 static void skl_probe_work(struct work_struct *work)
 {
 	struct skl *skl = container_of(work, struct skl, probe_work);
-	struct hdac_ext_bus *ebus = &skl->ebus;
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = skl_to_bus(skl);
 	struct hdac_ext_link *hlink = NULL;
 	int err;
 
@@ -744,7 +728,7 @@ static void skl_probe_work(struct work_struct *work)
 		dev_info(bus->dev, "no hda codecs found!\n");
 
 	/* create codec instances */
-	skl_codec_create(ebus);
+	skl_codec_create(bus);
 
 	/* register platform dai and controls */
 	err = skl_platform_register(bus->dev);
@@ -773,8 +757,8 @@ static void skl_probe_work(struct work_struct *work)
 	/*
 	 * we are done probing so decrement link counts
 	 */
-	list_for_each_entry(hlink, &ebus->hlink_list, list)
-		snd_hdac_ext_bus_link_put(ebus, hlink);
+	list_for_each_entry(hlink, &bus->hlink_list, list)
+		snd_hdac_ext_bus_link_put(bus, hlink);
 
 	/* configure PM */
 	pm_runtime_put_noidle(bus->dev);
@@ -796,7 +780,7 @@ static int skl_create(struct pci_dev *pci,
 		      struct skl **rskl)
 {
 	struct skl *skl;
-	struct hdac_ext_bus *ebus;
+	struct hdac_bus *bus;
 
 	int err;
 
@@ -811,23 +795,22 @@ static int skl_create(struct pci_dev *pci,
 		pci_disable_device(pci);
 		return -ENOMEM;
 	}
-	ebus = &skl->ebus;
-	snd_hdac_ext_bus_init(ebus, &pci->dev, &bus_core_ops, io_ops);
-	ebus->bus.use_posbuf = 1;
+
+	bus = skl_to_bus(skl);
+	snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops);
+	bus->use_posbuf = 1;
 	skl->pci = pci;
 	INIT_WORK(&skl->probe_work, skl_probe_work);
-
-	ebus->bus.bdl_pos_adj = 0;
+	bus->bdl_pos_adj = 0;
 
 	*rskl = skl;
 
 	return 0;
 }
 
-static int skl_first_init(struct hdac_ext_bus *ebus)
+static int skl_first_init(struct hdac_bus *bus)
 {
-	struct skl *skl = ebus_to_skl(ebus);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct skl *skl = bus_to_skl(bus);
 	struct pci_dev *pci = skl->pci;
 	int err;
 	unsigned short gcap;
@@ -848,7 +831,7 @@ static int skl_first_init(struct hdac_ext_bus *ebus)
 
 	snd_hdac_bus_parse_capabilities(bus);
 
-	if (skl_acquire_irq(ebus, 0) < 0)
+	if (skl_acquire_irq(bus, 0) < 0)
 		return -EBUSY;
 
 	pci_set_master(pci);
@@ -872,14 +855,14 @@ static int skl_first_init(struct hdac_ext_bus *ebus)
 	if (!pb_streams && !cp_streams)
 		return -EIO;
 
-	ebus->num_streams = cp_streams + pb_streams;
+	bus->num_streams = cp_streams + pb_streams;
 
 	/* initialize streams */
 	snd_hdac_ext_stream_init_all
-		(ebus, 0, cp_streams, SNDRV_PCM_STREAM_CAPTURE);
+		(bus, 0, cp_streams, SNDRV_PCM_STREAM_CAPTURE);
 	start_idx = cp_streams;
 	snd_hdac_ext_stream_init_all
-		(ebus, start_idx, pb_streams, SNDRV_PCM_STREAM_PLAYBACK);
+		(bus, start_idx, pb_streams, SNDRV_PCM_STREAM_PLAYBACK);
 
 	err = snd_hdac_bus_alloc_stream_pages(bus);
 	if (err < 0)
@@ -895,7 +878,6 @@ static int skl_probe(struct pci_dev *pci,
 		     const struct pci_device_id *pci_id)
 {
 	struct skl *skl;
-	struct hdac_ext_bus *ebus = NULL;
 	struct hdac_bus *bus = NULL;
 	int err;
 
@@ -904,10 +886,9 @@ static int skl_probe(struct pci_dev *pci,
 	if (err < 0)
 		return err;
 
-	ebus = &skl->ebus;
-	bus = ebus_to_hbus(ebus);
+	bus = skl_to_bus(skl);
 
-	err = skl_first_init(ebus);
+	err = skl_first_init(bus);
 	if (err < 0)
 		goto out_free;
 
@@ -928,7 +909,7 @@ static int skl_probe(struct pci_dev *pci,
 
 	skl_nhlt_update_topology_bin(skl);
 
-	pci_set_drvdata(skl->pci, ebus);
+	pci_set_drvdata(skl->pci, bus);
 
 	skl_dmic_data.dmic_num = skl_get_dmic_geo(skl);
 
@@ -952,7 +933,7 @@ static int skl_probe(struct pci_dev *pci,
 		skl->skl_sst->clock_power_gating = skl_clock_power_gating;
 	}
 	if (bus->mlcap)
-		snd_hdac_ext_bus_get_ml_capabilities(ebus);
+		snd_hdac_ext_bus_get_ml_capabilities(bus);
 
 	snd_hdac_bus_stop_chip(bus);
 
@@ -972,31 +953,30 @@ out_clk_free:
 out_nhlt_free:
 	skl_nhlt_free(skl->nhlt);
 out_free:
-	skl_free(ebus);
+	skl_free(bus);
 
 	return err;
 }
 
 static void skl_shutdown(struct pci_dev *pci)
 {
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct hdac_bus *bus = ebus_to_hbus(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
 	struct hdac_stream *s;
 	struct hdac_ext_stream *stream;
 	struct skl *skl;
 
-	if (ebus == NULL)
+	if (!bus)
 		return;
 
-	skl = ebus_to_skl(ebus);
+	skl = bus_to_skl(bus);
 
 	if (!skl->init_done)
 		return;
 
-	snd_hdac_ext_stop_streams(ebus);
+	snd_hdac_ext_stop_streams(bus);
 	list_for_each_entry(s, &bus->stream_list, list) {
 		stream = stream_to_hdac_ext_stream(s);
-		snd_hdac_ext_stream_decouple(ebus, stream, false);
+		snd_hdac_ext_stream_decouple(bus, stream, false);
 	}
 
 	snd_hdac_bus_stop_chip(bus);
@@ -1004,15 +984,15 @@ static void skl_shutdown(struct pci_dev *pci)
 
 static void skl_remove(struct pci_dev *pci)
 {
-	struct hdac_ext_bus *ebus = pci_get_drvdata(pci);
-	struct skl *skl = ebus_to_skl(ebus);
+	struct hdac_bus *bus = pci_get_drvdata(pci);
+	struct skl *skl = bus_to_skl(bus);
 
 	release_firmware(skl->tplg);
 
 	pm_runtime_get_noresume(&pci->dev);
 
 	/* codec removal, invoke bus_device_remove */
-	snd_hdac_ext_bus_device_remove(ebus);
+	snd_hdac_ext_bus_device_remove(bus);
 
 	skl->debugfs = NULL;
 	skl_platform_unregister(&pci->dev);
@@ -1022,7 +1002,7 @@ static void skl_remove(struct pci_dev *pci)
 	skl_clock_device_unregister(skl);
 	skl_nhlt_remove_sysfs(skl);
 	skl_nhlt_free(skl->nhlt);
-	skl_free(ebus);
+	skl_free(bus);
 	dev_set_drvdata(&pci->dev, NULL);
 }
 
diff --git a/sound/soc/intel/skylake/skl.h b/sound/soc/intel/skylake/skl.h
index 0d5375cbcf6e..78aa8bdcb619 100644
--- a/sound/soc/intel/skylake/skl.h
+++ b/sound/soc/intel/skylake/skl.h
@@ -71,7 +71,7 @@ struct skl_fw_config {
 };
 
 struct skl {
-	struct hdac_ext_bus ebus;
+	struct hdac_bus hbus;
 	struct pci_dev *pci;
 
 	unsigned int init_done:1; /* delayed init status */
@@ -105,9 +105,8 @@ struct skl {
 	struct snd_soc_acpi_mach *mach;
 };
 
-#define skl_to_ebus(s)	(&(s)->ebus)
-#define ebus_to_skl(sbus) \
-	container_of(sbus, struct skl, sbus)
+#define skl_to_bus(s)  (&(s)->hbus)
+#define bus_to_skl(bus) container_of(bus, struct skl, hbus)
 
 /* to pass dai dma data */
 struct skl_dma_params {
-- 
cgit v1.2.3


From e1df9317cbb192582ed7aa88c5f294c2336a3c75 Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Fri, 1 Jun 2018 22:53:51 -0500
Subject: ALSA: hdac: Remove usage of struct hdac_ext_driver, use hdac_driver
 instead

This patch removes the hdac_ext_driver structure. The legacy and
enhanced HDaudio capabilities can be handled in a backward-compatible
way without separate definitions.

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio.h      |  5 +++++
 include/sound/hdaudio_ext.h  | 17 ++---------------
 sound/hda/ext/hdac_ext_bus.c | 30 ++++++++++++++----------------
 sound/soc/codecs/hdac_hdmi.c | 12 +++++-------
 4 files changed, 26 insertions(+), 38 deletions(-)

diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index 9735b51aef08..59ffe63cf194 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -188,6 +188,11 @@ struct hdac_driver {
 	const struct hda_device_id *id_table;
 	int (*match)(struct hdac_device *dev, struct hdac_driver *drv);
 	void (*unsol_event)(struct hdac_device *dev, unsigned int event);
+
+	/* fields used by ext bus APIs */
+	int (*probe)(struct hdac_device *dev);
+	int (*remove)(struct hdac_device *dev);
+	void (*shutdown)(struct hdac_device *dev);
 };
 
 #define drv_to_hdac_driver(_drv) container_of(_drv, struct hdac_driver, driver)
diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index e5b0cd1ade19..3c302477750b 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -160,20 +160,7 @@ struct hdac_ext_dma_params {
 	u8 stream_tag;
 };
 
-/*
- * HD-audio codec base driver
- */
-struct hdac_ext_driver {
-	struct hdac_driver hdac;
-
-	int	(*probe)(struct hdac_device *dev);
-	int	(*remove)(struct hdac_device *dev);
-	void	(*shutdown)(struct hdac_device *dev);
-};
-
-int snd_hda_ext_driver_register(struct hdac_ext_driver *drv);
-void snd_hda_ext_driver_unregister(struct hdac_ext_driver *drv);
-
-#define to_ehdac_driver(_drv) container_of(_drv, struct hdac_ext_driver, hdac)
+int snd_hda_ext_driver_register(struct hdac_driver *drv);
+void snd_hda_ext_driver_unregister(struct hdac_driver *drv);
 
 #endif /* __SOUND_HDAUDIO_EXT_H */
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index 77547ede9ae8..52f07766fff3 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -200,12 +200,10 @@ EXPORT_SYMBOL_GPL(snd_hdac_ext_bus_device_remove);
 #define dev_to_hdac(dev) (container_of((dev), \
 			struct hdac_device, dev))
 
-static inline struct hdac_ext_driver *get_edrv(struct device *dev)
+static inline struct hdac_driver *get_hdrv(struct device *dev)
 {
 	struct hdac_driver *hdrv = drv_to_hdac_driver(dev->driver);
-	struct hdac_ext_driver *edrv = to_ehdac_driver(hdrv);
-
-	return edrv;
+	return hdrv;
 }
 
 static inline struct hdac_device *get_hdev(struct device *dev)
@@ -216,17 +214,17 @@ static inline struct hdac_device *get_hdev(struct device *dev)
 
 static int hda_ext_drv_probe(struct device *dev)
 {
-	return (get_edrv(dev))->probe(get_hdev(dev));
+	return (get_hdrv(dev))->probe(get_hdev(dev));
 }
 
 static int hdac_ext_drv_remove(struct device *dev)
 {
-	return (get_edrv(dev))->remove(get_hdev(dev));
+	return (get_hdrv(dev))->remove(get_hdev(dev));
 }
 
 static void hdac_ext_drv_shutdown(struct device *dev)
 {
-	return (get_edrv(dev))->shutdown(get_hdev(dev));
+	return (get_hdrv(dev))->shutdown(get_hdev(dev));
 }
 
 /**
@@ -234,20 +232,20 @@ static void hdac_ext_drv_shutdown(struct device *dev)
  *
  * @drv: ext hda driver structure
  */
-int snd_hda_ext_driver_register(struct hdac_ext_driver *drv)
+int snd_hda_ext_driver_register(struct hdac_driver *drv)
 {
-	drv->hdac.type = HDA_DEV_ASOC;
-	drv->hdac.driver.bus = &snd_hda_bus_type;
+	drv->type = HDA_DEV_ASOC;
+	drv->driver.bus = &snd_hda_bus_type;
 	/* we use default match */
 
 	if (drv->probe)
-		drv->hdac.driver.probe = hda_ext_drv_probe;
+		drv->driver.probe = hda_ext_drv_probe;
 	if (drv->remove)
-		drv->hdac.driver.remove = hdac_ext_drv_remove;
+		drv->driver.remove = hdac_ext_drv_remove;
 	if (drv->shutdown)
-		drv->hdac.driver.shutdown = hdac_ext_drv_shutdown;
+		drv->driver.shutdown = hdac_ext_drv_shutdown;
 
-	return driver_register(&drv->hdac.driver);
+	return driver_register(&drv->driver);
 }
 EXPORT_SYMBOL_GPL(snd_hda_ext_driver_register);
 
@@ -256,8 +254,8 @@ EXPORT_SYMBOL_GPL(snd_hda_ext_driver_register);
  *
  * @drv: ext hda driver structure
  */
-void snd_hda_ext_driver_unregister(struct hdac_ext_driver *drv)
+void snd_hda_ext_driver_unregister(struct hdac_driver *drv)
 {
-	driver_unregister(&drv->hdac.driver);
+	driver_unregister(&drv->driver);
 }
 EXPORT_SYMBOL_GPL(snd_hda_ext_driver_unregister);
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index c3ccc8d9c91d..3e3a2a9ef310 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -2186,14 +2186,12 @@ static const struct hda_device_id hdmi_list[] = {
 
 MODULE_DEVICE_TABLE(hdaudio, hdmi_list);
 
-static struct hdac_ext_driver hdmi_driver = {
-	. hdac = {
-		.driver = {
-			.name   = "HDMI HDA Codec",
-			.pm = &hdac_hdmi_pm,
-		},
-		.id_table       = hdmi_list,
+static struct hdac_driver hdmi_driver = {
+	.driver = {
+		.name   = "HDMI HDA Codec",
+		.pm = &hdac_hdmi_pm,
 	},
+	.id_table       = hdmi_list,
 	.probe          = hdac_hdmi_dev_probe,
 	.remove         = hdac_hdmi_dev_remove,
 };
-- 
cgit v1.2.3


From f8a7fe1aea215e25eaf3bf04dff66fc7621ec9d7 Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Fri, 1 Jun 2018 22:54:00 -0500
Subject: ALSA: hdac: ext: add wait for codec to respond after link reset

As per HDA spec section 4.3 - Codec Discovery, the software shall wait
for atleast 521usec for codec to respond after link reset.
With the multi-link capability each link is turned ON/OFF individually.
Link controller drives reset signal when it is turned ON.

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/ext/hdac_ext_controller.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/sound/hda/ext/hdac_ext_controller.c b/sound/hda/ext/hdac_ext_controller.c
index 72774119dd11..5bc4a1d587d4 100644
--- a/sound/hda/ext/hdac_ext_controller.c
+++ b/sound/hda/ext/hdac_ext_controller.c
@@ -271,6 +271,15 @@ int snd_hdac_ext_bus_link_get(struct hdac_bus *bus,
 		}
 
 		ret = snd_hdac_ext_bus_link_power_up(link);
+
+		/*
+		 *  wait for 521usec for codec to report status
+		 *  HDA spec section 4.3 - Codec Discovery
+		 */
+		udelay(521);
+		bus->codec_mask = snd_hdac_chip_readw(bus, STATESTS);
+		dev_dbg(bus->dev, "codec_mask = 0x%lx\n", bus->codec_mask);
+		snd_hdac_chip_writew(bus, STATESTS, bus->codec_mask);
 	}
 
 	mutex_unlock(&bus->lock);
-- 
cgit v1.2.3


From 24494d3f939774c3c21d78b5e95d37f9e74d154c Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Fri, 1 Jun 2018 22:53:56 -0500
Subject: ALSA: hda: split snd_hda_codec_new function

Split snd_hda_codec_new into two separate functions.
snd_hda_codec_device_init allocates memory and registers with bus.
snd_hda_codec_device_new initialializes the fields and performs
snd_device_new. This enables reuse of legacy HDA codec drivers as ASoC
codec drivers.

In addition mark some functions with EXPORT_SYMBOL_GPL so that it can
be called by ASoC wrapper around the legacy HDA driver (hdac_hda).

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_codec.c | 68 +++++++++++++++++++++++++++++++++++------------
 sound/pci/hda/hda_codec.h |  2 ++
 2 files changed, 53 insertions(+), 17 deletions(-)

diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index d91c87e41756..059cfade05cc 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -858,6 +858,39 @@ static void snd_hda_codec_dev_release(struct device *dev)
 	kfree(codec);
 }
 
+#define DEV_NAME_LEN 31
+
+static int snd_hda_codec_device_init(struct hda_bus *bus, struct snd_card *card,
+			unsigned int codec_addr, struct hda_codec **codecp)
+{
+	char name[DEV_NAME_LEN];
+	struct hda_codec *codec;
+	int err;
+
+	dev_dbg(card->dev, "%s: entry\n", __func__);
+
+	if (snd_BUG_ON(!bus))
+		return -EINVAL;
+	if (snd_BUG_ON(codec_addr > HDA_MAX_CODEC_ADDRESS))
+		return -EINVAL;
+
+	codec = kzalloc(sizeof(*codec), GFP_KERNEL);
+	if (!codec)
+		return -ENOMEM;
+
+	sprintf(name, "hdaudioC%dD%d", card->number, codec_addr);
+	err = snd_hdac_device_init(&codec->core, &bus->core, name, codec_addr);
+	if (err < 0) {
+		kfree(codec);
+		return err;
+	}
+
+	codec->core.type = HDA_DEV_LEGACY;
+	*codecp = codec;
+
+	return err;
+}
+
 /**
  * snd_hda_codec_new - create a HDA codec
  * @bus: the bus to assign
@@ -869,7 +902,19 @@ static void snd_hda_codec_dev_release(struct device *dev)
 int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 		      unsigned int codec_addr, struct hda_codec **codecp)
 {
-	struct hda_codec *codec;
+	int ret;
+
+	ret = snd_hda_codec_device_init(bus, card, codec_addr, codecp);
+	if (ret < 0)
+		return ret;
+
+	return snd_hda_codec_device_new(bus, card, codec_addr, *codecp);
+}
+EXPORT_SYMBOL_GPL(snd_hda_codec_new);
+
+int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card,
+			unsigned int codec_addr, struct hda_codec *codec)
+{
 	char component[31];
 	hda_nid_t fg;
 	int err;
@@ -879,25 +924,14 @@ int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 		.dev_free = snd_hda_codec_dev_free,
 	};
 
+	dev_dbg(card->dev, "%s: entry\n", __func__);
+
 	if (snd_BUG_ON(!bus))
 		return -EINVAL;
 	if (snd_BUG_ON(codec_addr > HDA_MAX_CODEC_ADDRESS))
 		return -EINVAL;
 
-	codec = kzalloc(sizeof(*codec), GFP_KERNEL);
-	if (!codec)
-		return -ENOMEM;
-
-	sprintf(component, "hdaudioC%dD%d", card->number, codec_addr);
-	err = snd_hdac_device_init(&codec->core, &bus->core, component,
-				   codec_addr);
-	if (err < 0) {
-		kfree(codec);
-		return err;
-	}
-
 	codec->core.dev.release = snd_hda_codec_dev_release;
-	codec->core.type = HDA_DEV_LEGACY;
 	codec->core.exec_verb = codec_exec_verb;
 
 	codec->bus = bus;
@@ -957,15 +991,13 @@ int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 	if (err < 0)
 		goto error;
 
-	if (codecp)
-		*codecp = codec;
 	return 0;
 
  error:
 	put_device(hda_codec_dev(codec));
 	return err;
 }
-EXPORT_SYMBOL_GPL(snd_hda_codec_new);
+EXPORT_SYMBOL_GPL(snd_hda_codec_device_new);
 
 /**
  * snd_hda_codec_update_widgets - Refresh widget caps and pin defaults
@@ -2991,6 +3023,7 @@ int snd_hda_codec_build_controls(struct hda_codec *codec)
 	sync_power_up_states(codec);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(snd_hda_codec_build_controls);
 
 /*
  * PCM stuff
@@ -3196,6 +3229,7 @@ int snd_hda_codec_parse_pcms(struct hda_codec *codec)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(snd_hda_codec_parse_pcms);
 
 /* assign all PCMs of the given codec */
 int snd_hda_codec_build_pcms(struct hda_codec *codec)
diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
index 681c360f29f9..8bbedf7f3f54 100644
--- a/sound/pci/hda/hda_codec.h
+++ b/sound/pci/hda/hda_codec.h
@@ -307,6 +307,8 @@ struct hda_codec {
  */
 int snd_hda_codec_new(struct hda_bus *bus, struct snd_card *card,
 		      unsigned int codec_addr, struct hda_codec **codecp);
+int snd_hda_codec_device_new(struct hda_bus *bus, struct snd_card *card,
+		      unsigned int codec_addr, struct hda_codec *codec);
 int snd_hda_codec_configure(struct hda_codec *codec);
 int snd_hda_codec_update_widgets(struct hda_codec *codec);
 
-- 
cgit v1.2.3


From 6298542fa33b6ba0e3effbace5b99b70b93ed9ae Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Fri, 1 Jun 2018 22:53:57 -0500
Subject: ALSA: hdac: remove memory allocation from
 snd_hdac_ext_bus_device_init

Remove memory allocation within snd_hdac_ext_bus_device_init, to make
its behaviour identical to snd_hdac_bus_device_init. So that caller
can allocate the parent data structure containing hdac_device.
This API change helps in reusing the legacy HDA codec drivers with
ASoC platform drivers.

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio_ext.h   | 3 ++-
 sound/hda/ext/hdac_ext_bus.c  | 8 ++------
 sound/soc/intel/skylake/skl.c | 8 +++++++-
 3 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index 3c302477750b..c188b801239f 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -9,7 +9,8 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 		      const struct hdac_io_ops *io_ops);
 
 void snd_hdac_ext_bus_exit(struct hdac_bus *bus);
-int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr);
+int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
+						struct hdac_device *hdev);
 void snd_hdac_ext_bus_device_exit(struct hdac_device *hdev);
 void snd_hdac_ext_bus_device_remove(struct hdac_bus *bus);
 
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index 52f07766fff3..1eb58244688e 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -135,16 +135,12 @@ static void default_release(struct device *dev)
  *
  * Returns zero for success or a negative error code.
  */
-int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr)
+int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
+					struct hdac_device *hdev)
 {
-	struct hdac_device *hdev = NULL;
 	char name[15];
 	int ret;
 
-	hdev = kzalloc(sizeof(*hdev), GFP_KERNEL);
-	if (!hdev)
-		return -ENOMEM;
-
 	hdev->bus = bus;
 
 	snprintf(name, sizeof(name), "ehdaudio%dD%d", bus->idx, addr);
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 9c5a701d68ac..3a7f5eb4902b 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -635,6 +635,8 @@ static int probe_codec(struct hdac_bus *bus, int addr)
 	unsigned int cmd = (addr << 28) | (AC_NODE_ROOT << 20) |
 		(AC_VERB_PARAMETERS << 8) | AC_PAR_VENDOR_ID;
 	unsigned int res = -1;
+	struct skl *skl = bus_to_skl(bus);
+	struct hdac_device *hdev;
 
 	mutex_lock(&bus->cmd_mutex);
 	snd_hdac_bus_send_cmd(bus, cmd);
@@ -644,7 +646,11 @@ static int probe_codec(struct hdac_bus *bus, int addr)
 		return -EIO;
 	dev_dbg(bus->dev, "codec #%d probed OK\n", addr);
 
-	return snd_hdac_ext_bus_device_init(bus, addr);
+	hdev = devm_kzalloc(&skl->pci->dev, sizeof(*hdev), GFP_KERNEL);
+	if (!hdev)
+		return -ENOMEM;
+
+	return snd_hdac_ext_bus_device_init(bus, addr, hdev);
 }
 
 /* Codec initialization */
-- 
cgit v1.2.3


From cb04ba33187ca571142b67c2fb60d0a8c24994c8 Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Fri, 1 Jun 2018 22:53:58 -0500
Subject: ALSA: hdac: add extended ops in the hdac_bus

Add extended ops in the hdac_bus to allow calling the ASoC HDAC library
ops to reuse the legacy HDA codec drivers with ASoC framework.
Extended ops are used by the legacy codec drivers to call into
hdac_hda library, in the subsequent patches..

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio.h       | 9 +++++++++
 include/sound/hdaudio_ext.h   | 3 ++-
 sound/hda/ext/hdac_ext_bus.c  | 4 +++-
 sound/soc/intel/skylake/skl.c | 2 +-
 4 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index 59ffe63cf194..f1baaa88e766 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -213,6 +213,14 @@ struct hdac_bus_ops {
 	int (*link_power)(struct hdac_bus *bus, bool enable);
 };
 
+/*
+ * ops used for ASoC HDA codec drivers
+ */
+struct hdac_ext_bus_ops {
+	int (*hdev_attach)(struct hdac_device *hdev);
+	int (*hdev_detach)(struct hdac_device *hdev);
+};
+
 /*
  * Lowlevel I/O operators
  */
@@ -265,6 +273,7 @@ struct hdac_bus {
 	struct device *dev;
 	const struct hdac_bus_ops *ops;
 	const struct hdac_io_ops *io_ops;
+	const struct hdac_ext_bus_ops *ext_ops;
 
 	/* h/w resources */
 	unsigned long addr;
diff --git a/include/sound/hdaudio_ext.h b/include/sound/hdaudio_ext.h
index c188b801239f..f34aced69ca8 100644
--- a/include/sound/hdaudio_ext.h
+++ b/include/sound/hdaudio_ext.h
@@ -6,7 +6,8 @@
 
 int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 		      const struct hdac_bus_ops *ops,
-		      const struct hdac_io_ops *io_ops);
+		      const struct hdac_io_ops *io_ops,
+		      const struct hdac_ext_bus_ops *ext_ops);
 
 void snd_hdac_ext_bus_exit(struct hdac_bus *bus);
 int snd_hdac_ext_bus_device_init(struct hdac_bus *bus, int addr,
diff --git a/sound/hda/ext/hdac_ext_bus.c b/sound/hda/ext/hdac_ext_bus.c
index 1eb58244688e..9c37d9af3023 100644
--- a/sound/hda/ext/hdac_ext_bus.c
+++ b/sound/hda/ext/hdac_ext_bus.c
@@ -89,7 +89,8 @@ static const struct hdac_io_ops hdac_ext_default_io = {
  */
 int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 			const struct hdac_bus_ops *ops,
-			const struct hdac_io_ops *io_ops)
+			const struct hdac_io_ops *io_ops,
+			const struct hdac_ext_bus_ops *ext_ops)
 {
 	int ret;
 	static int idx;
@@ -102,6 +103,7 @@ int snd_hdac_ext_bus_init(struct hdac_bus *bus, struct device *dev,
 	if (ret < 0)
 		return ret;
 
+	bus->ext_ops = ext_ops;
 	INIT_LIST_HEAD(&bus->hlink_list);
 	bus->idx = idx++;
 
diff --git a/sound/soc/intel/skylake/skl.c b/sound/soc/intel/skylake/skl.c
index 3a7f5eb4902b..00e051467a40 100644
--- a/sound/soc/intel/skylake/skl.c
+++ b/sound/soc/intel/skylake/skl.c
@@ -803,7 +803,7 @@ static int skl_create(struct pci_dev *pci,
 	}
 
 	bus = skl_to_bus(skl);
-	snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops);
+	snd_hdac_ext_bus_init(bus, &pci->dev, &bus_core_ops, io_ops, NULL);
 	bus->use_posbuf = 1;
 	skl->pci = pci;
 	INIT_WORK(&skl->probe_work, skl_probe_work);
-- 
cgit v1.2.3


From 782e85c5f7aee0294cefb52a190b05e082c178d5 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Tue, 26 Jun 2018 18:42:33 +0300
Subject: sh_eth: fix *enum* {A|M}PR_BIT

The *enum* {A|M}PR_BIT were declared in the commit 86a74ff21a7a ("net:
sh_eth: add support for  Renesas SuperH Ethernet") adding SH771x support,
however the SH771x manual  doesn't have the APR/MPR registers described
and the code writing to them for SH7710 was later removed by the commit
380af9e390ec ("net: sh_eth: CPU dependency code collect to "struct
sh_eth_cpu_data""). All the newer SoC manuals have these registers
documented as having a 16-bit TIME parameter of the PAUSE frame, not
1-bit -- update the *enum* accordingly, fixing up the APR/MPR writes...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++--
 drivers/net/ethernet/renesas/sh_eth.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index f7043ea5eed1..71651e47660a 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -1521,9 +1521,9 @@ static int sh_eth_dev_init(struct net_device *ndev)
 
 	/* mask reset */
 	if (mdp->cd->apr)
-		sh_eth_write(ndev, APR_AP, APR);
+		sh_eth_write(ndev, 1, APR);
 	if (mdp->cd->mpr)
-		sh_eth_write(ndev, MPR_MP, MPR);
+		sh_eth_write(ndev, 1, MPR);
 	if (mdp->cd->tpauser)
 		sh_eth_write(ndev, TPAUSER_UNLIMITED, TPAUSER);
 
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index a03d99f51ccf..140ad2c57095 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -383,12 +383,12 @@ enum ECSIPR_STATUS_MASK_BIT {
 
 /* APR */
 enum APR_BIT {
-	APR_AP = 0x00000001,
+	APR_AP = 0x0000ffff,
 };
 
 /* MPR */
 enum MPR_BIT {
-	MPR_MP = 0x00000001,
+	MPR_MP = 0x0000ffff,
 };
 
 /* TRSCER */
-- 
cgit v1.2.3


From 242b1bbe5144de3577ad12da058e70ef88167146 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 26 Jun 2018 08:45:49 -0700
Subject: tcp: remove one indentation level in tcp_create_openreq_child

Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 223 ++++++++++++++++++++++++-----------------------
 1 file changed, 113 insertions(+), 110 deletions(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1dda1341a223..dac5893a52b4 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -449,119 +449,122 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 				      struct sk_buff *skb)
 {
 	struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC);
+	const struct inet_request_sock *ireq = inet_rsk(req);
+	struct tcp_request_sock *treq = tcp_rsk(req);
+	struct inet_connection_sock *newicsk;
+	struct tcp_sock *oldtp, *newtp;
 
-	if (newsk) {
-		const struct inet_request_sock *ireq = inet_rsk(req);
-		struct tcp_request_sock *treq = tcp_rsk(req);
-		struct inet_connection_sock *newicsk = inet_csk(newsk);
-		struct tcp_sock *newtp = tcp_sk(newsk);
-		struct tcp_sock *oldtp = tcp_sk(sk);
-
-		smc_check_reset_syn_req(oldtp, req, newtp);
-
-		/* Now setup tcp_sock */
-		newtp->pred_flags = 0;
-
-		newtp->rcv_wup = newtp->copied_seq =
-		newtp->rcv_nxt = treq->rcv_isn + 1;
-		newtp->segs_in = 1;
-
-		newtp->snd_sml = newtp->snd_una =
-		newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
-
-		INIT_LIST_HEAD(&newtp->tsq_node);
-		INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
-
-		tcp_init_wl(newtp, treq->rcv_isn);
-
-		newtp->srtt_us = 0;
-		newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
-		minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U);
-		newicsk->icsk_rto = TCP_TIMEOUT_INIT;
-		newicsk->icsk_ack.lrcvtime = tcp_jiffies32;
-
-		newtp->packets_out = 0;
-		newtp->retrans_out = 0;
-		newtp->sacked_out = 0;
-		newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-		newtp->tlp_high_seq = 0;
-		newtp->lsndtime = tcp_jiffies32;
-		newsk->sk_txhash = treq->txhash;
-		newtp->last_oow_ack_time = 0;
-		newtp->total_retrans = req->num_retrans;
-
-		/* So many TCP implementations out there (incorrectly) count the
-		 * initial SYN frame in their delayed-ACK and congestion control
-		 * algorithms that we must have the following bandaid to talk
-		 * efficiently to them.  -DaveM
-		 */
-		newtp->snd_cwnd = TCP_INIT_CWND;
-		newtp->snd_cwnd_cnt = 0;
-
-		/* There's a bubble in the pipe until at least the first ACK. */
-		newtp->app_limited = ~0U;
-
-		tcp_init_xmit_timers(newsk);
-		newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
-
-		newtp->rx_opt.saw_tstamp = 0;
-
-		newtp->rx_opt.dsack = 0;
-		newtp->rx_opt.num_sacks = 0;
-
-		newtp->urg_data = 0;
-
-		if (sock_flag(newsk, SOCK_KEEPOPEN))
-			inet_csk_reset_keepalive_timer(newsk,
-						       keepalive_time_when(newtp));
-
-		newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
-		newtp->rx_opt.sack_ok = ireq->sack_ok;
-		newtp->window_clamp = req->rsk_window_clamp;
-		newtp->rcv_ssthresh = req->rsk_rcv_wnd;
-		newtp->rcv_wnd = req->rsk_rcv_wnd;
-		newtp->rx_opt.wscale_ok = ireq->wscale_ok;
-		if (newtp->rx_opt.wscale_ok) {
-			newtp->rx_opt.snd_wscale = ireq->snd_wscale;
-			newtp->rx_opt.rcv_wscale = ireq->rcv_wscale;
-		} else {
-			newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
-			newtp->window_clamp = min(newtp->window_clamp, 65535U);
-		}
-		newtp->snd_wnd = (ntohs(tcp_hdr(skb)->window) <<
-				  newtp->rx_opt.snd_wscale);
-		newtp->max_window = newtp->snd_wnd;
-
-		if (newtp->rx_opt.tstamp_ok) {
-			newtp->rx_opt.ts_recent = req->ts_recent;
-			newtp->rx_opt.ts_recent_stamp = get_seconds();
-			newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
-		} else {
-			newtp->rx_opt.ts_recent_stamp = 0;
-			newtp->tcp_header_len = sizeof(struct tcphdr);
-		}
-		newtp->tsoffset = treq->ts_off;
+	if (!newsk)
+		return NULL;
+
+	newicsk = inet_csk(newsk);
+	newtp = tcp_sk(newsk);
+	oldtp = tcp_sk(sk);
+
+	smc_check_reset_syn_req(oldtp, req, newtp);
+
+	/* Now setup tcp_sock */
+	newtp->pred_flags = 0;
+
+	newtp->rcv_wup = newtp->copied_seq =
+	newtp->rcv_nxt = treq->rcv_isn + 1;
+	newtp->segs_in = 1;
+
+	newtp->snd_sml = newtp->snd_una =
+	newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
+
+	INIT_LIST_HEAD(&newtp->tsq_node);
+	INIT_LIST_HEAD(&newtp->tsorted_sent_queue);
+
+	tcp_init_wl(newtp, treq->rcv_isn);
+
+	newtp->srtt_us = 0;
+	newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
+	minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U);
+	newicsk->icsk_rto = TCP_TIMEOUT_INIT;
+	newicsk->icsk_ack.lrcvtime = tcp_jiffies32;
+
+	newtp->packets_out = 0;
+	newtp->retrans_out = 0;
+	newtp->sacked_out = 0;
+	newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
+	newtp->tlp_high_seq = 0;
+	newtp->lsndtime = tcp_jiffies32;
+	newsk->sk_txhash = treq->txhash;
+	newtp->last_oow_ack_time = 0;
+	newtp->total_retrans = req->num_retrans;
+
+	/* So many TCP implementations out there (incorrectly) count the
+	 * initial SYN frame in their delayed-ACK and congestion control
+	 * algorithms that we must have the following bandaid to talk
+	 * efficiently to them.  -DaveM
+	 */
+	newtp->snd_cwnd = TCP_INIT_CWND;
+	newtp->snd_cwnd_cnt = 0;
+
+	/* There's a bubble in the pipe until at least the first ACK. */
+	newtp->app_limited = ~0U;
+
+	tcp_init_xmit_timers(newsk);
+	newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
+
+	newtp->rx_opt.saw_tstamp = 0;
+
+	newtp->rx_opt.dsack = 0;
+	newtp->rx_opt.num_sacks = 0;
+
+	newtp->urg_data = 0;
+
+	if (sock_flag(newsk, SOCK_KEEPOPEN))
+		inet_csk_reset_keepalive_timer(newsk,
+					       keepalive_time_when(newtp));
+
+	newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
+	newtp->rx_opt.sack_ok = ireq->sack_ok;
+	newtp->window_clamp = req->rsk_window_clamp;
+	newtp->rcv_ssthresh = req->rsk_rcv_wnd;
+	newtp->rcv_wnd = req->rsk_rcv_wnd;
+	newtp->rx_opt.wscale_ok = ireq->wscale_ok;
+	if (newtp->rx_opt.wscale_ok) {
+		newtp->rx_opt.snd_wscale = ireq->snd_wscale;
+		newtp->rx_opt.rcv_wscale = ireq->rcv_wscale;
+	} else {
+		newtp->rx_opt.snd_wscale = newtp->rx_opt.rcv_wscale = 0;
+		newtp->window_clamp = min(newtp->window_clamp, 65535U);
+	}
+	newtp->snd_wnd = ntohs(tcp_hdr(skb)->window) << newtp->rx_opt.snd_wscale;
+	newtp->max_window = newtp->snd_wnd;
+
+	if (newtp->rx_opt.tstamp_ok) {
+		newtp->rx_opt.ts_recent = req->ts_recent;
+		newtp->rx_opt.ts_recent_stamp = get_seconds();
+		newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
+	} else {
+		newtp->rx_opt.ts_recent_stamp = 0;
+		newtp->tcp_header_len = sizeof(struct tcphdr);
+	}
+	newtp->tsoffset = treq->ts_off;
 #ifdef CONFIG_TCP_MD5SIG
-		newtp->md5sig_info = NULL;	/*XXX*/
-		if (newtp->af_specific->md5_lookup(sk, newsk))
-			newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
+	newtp->md5sig_info = NULL;	/*XXX*/
+	if (newtp->af_specific->md5_lookup(sk, newsk))
+		newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
 #endif
-		if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
-			newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
-		newtp->rx_opt.mss_clamp = req->mss;
-		tcp_ecn_openreq_child(newtp, req);
-		newtp->fastopen_req = NULL;
-		newtp->fastopen_rsk = NULL;
-		newtp->syn_data_acked = 0;
-		newtp->rack.mstamp = 0;
-		newtp->rack.advanced = 0;
-		newtp->rack.reo_wnd_steps = 1;
-		newtp->rack.last_delivered = 0;
-		newtp->rack.reo_wnd_persist = 0;
-		newtp->rack.dsack_seen = 0;
-
-		__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
-	}
+	if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
+		newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
+	newtp->rx_opt.mss_clamp = req->mss;
+	tcp_ecn_openreq_child(newtp, req);
+	newtp->fastopen_req = NULL;
+	newtp->fastopen_rsk = NULL;
+	newtp->syn_data_acked = 0;
+	newtp->rack.mstamp = 0;
+	newtp->rack.advanced = 0;
+	newtp->rack.reo_wnd_steps = 1;
+	newtp->rack.last_delivered = 0;
+	newtp->rack.reo_wnd_persist = 0;
+	newtp->rack.dsack_seen = 0;
+
+	__TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS);
+
 	return newsk;
 }
 EXPORT_SYMBOL(tcp_create_openreq_child);
-- 
cgit v1.2.3


From a408194aa050f9a820f5a64301c7a08880f8af7d Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Tue, 26 Jun 2018 18:41:36 +0200
Subject: l2tp: define helper for parsing struct sockaddr_pppol2tp*

'sockaddr_len' is checked against various values when entering
pppol2tp_connect(), to verify its validity. It is used again later, to
find out which sockaddr structure was passed from user space. This
patch combines these two operations into one new function in order to
simplify pppol2tp_connect().

A new structure, l2tp_connect_info, is used to pass sockaddr data back
to pppol2tp_connect(), to avoid passing too many parameters to
l2tp_sockaddr_get_info(). Also, the first parameter is void* in order
to avoid casting between all sockaddr_* structures manually.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 173 +++++++++++++++++++++++++++++++---------------------
 1 file changed, 103 insertions(+), 70 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index eea5d7844473..d3a9355ac8ac 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -588,40 +588,113 @@ static void pppol2tp_session_init(struct l2tp_session *session)
 	}
 }
 
+struct l2tp_connect_info {
+	u8 version;
+	int fd;
+	u32 tunnel_id;
+	u32 peer_tunnel_id;
+	u32 session_id;
+	u32 peer_session_id;
+};
+
+static int pppol2tp_sockaddr_get_info(const void *sa, int sa_len,
+				      struct l2tp_connect_info *info)
+{
+	switch (sa_len) {
+	case sizeof(struct sockaddr_pppol2tp):
+	{
+		const struct sockaddr_pppol2tp *sa_v2in4 = sa;
+
+		if (sa_v2in4->sa_protocol != PX_PROTO_OL2TP)
+			return -EINVAL;
+
+		info->version = 2;
+		info->fd = sa_v2in4->pppol2tp.fd;
+		info->tunnel_id = sa_v2in4->pppol2tp.s_tunnel;
+		info->peer_tunnel_id = sa_v2in4->pppol2tp.d_tunnel;
+		info->session_id = sa_v2in4->pppol2tp.s_session;
+		info->peer_session_id = sa_v2in4->pppol2tp.d_session;
+
+		break;
+	}
+	case sizeof(struct sockaddr_pppol2tpv3):
+	{
+		const struct sockaddr_pppol2tpv3 *sa_v3in4 = sa;
+
+		if (sa_v3in4->sa_protocol != PX_PROTO_OL2TP)
+			return -EINVAL;
+
+		info->version = 3;
+		info->fd = sa_v3in4->pppol2tp.fd;
+		info->tunnel_id = sa_v3in4->pppol2tp.s_tunnel;
+		info->peer_tunnel_id = sa_v3in4->pppol2tp.d_tunnel;
+		info->session_id = sa_v3in4->pppol2tp.s_session;
+		info->peer_session_id = sa_v3in4->pppol2tp.d_session;
+
+		break;
+	}
+	case sizeof(struct sockaddr_pppol2tpin6):
+	{
+		const struct sockaddr_pppol2tpin6 *sa_v2in6 = sa;
+
+		if (sa_v2in6->sa_protocol != PX_PROTO_OL2TP)
+			return -EINVAL;
+
+		info->version = 2;
+		info->fd = sa_v2in6->pppol2tp.fd;
+		info->tunnel_id = sa_v2in6->pppol2tp.s_tunnel;
+		info->peer_tunnel_id = sa_v2in6->pppol2tp.d_tunnel;
+		info->session_id = sa_v2in6->pppol2tp.s_session;
+		info->peer_session_id = sa_v2in6->pppol2tp.d_session;
+
+		break;
+	}
+	case sizeof(struct sockaddr_pppol2tpv3in6):
+	{
+		const struct sockaddr_pppol2tpv3in6 *sa_v3in6 = sa;
+
+		if (sa_v3in6->sa_protocol != PX_PROTO_OL2TP)
+			return -EINVAL;
+
+		info->version = 3;
+		info->fd = sa_v3in6->pppol2tp.fd;
+		info->tunnel_id = sa_v3in6->pppol2tp.s_tunnel;
+		info->peer_tunnel_id = sa_v3in6->pppol2tp.d_tunnel;
+		info->session_id = sa_v3in6->pppol2tp.s_session;
+		info->peer_session_id = sa_v3in6->pppol2tp.d_session;
+
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
  */
 static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 			    int sockaddr_len, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_pppol2tp *sp = (struct sockaddr_pppol2tp *) uservaddr;
 	struct pppox_sock *po = pppox_sk(sk);
 	struct l2tp_session *session = NULL;
+	struct l2tp_connect_info info;
 	struct l2tp_tunnel *tunnel;
 	struct pppol2tp_session *ps;
 	struct l2tp_session_cfg cfg = { 0, };
-	int error = 0;
-	u32 tunnel_id, peer_tunnel_id;
-	u32 session_id, peer_session_id;
 	bool drop_refcnt = false;
 	bool drop_tunnel = false;
 	bool new_session = false;
 	bool new_tunnel = false;
-	int ver = 2;
-	int fd;
-
-	lock_sock(sk);
-
-	error = -EINVAL;
+	int error;
 
-	if (sockaddr_len != sizeof(struct sockaddr_pppol2tp) &&
-	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3) &&
-	    sockaddr_len != sizeof(struct sockaddr_pppol2tpin6) &&
-	    sockaddr_len != sizeof(struct sockaddr_pppol2tpv3in6))
-		goto end;
+	error = pppol2tp_sockaddr_get_info(uservaddr, sockaddr_len, &info);
+	if (error < 0)
+		return error;
 
-	if (sp->sa_protocol != PX_PROTO_OL2TP)
-		goto end;
+	lock_sock(sk);
 
 	/* Check for already bound sockets */
 	error = -EBUSY;
@@ -633,56 +706,12 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	if (sk->sk_user_data)
 		goto end; /* socket is already attached */
 
-	/* Get params from socket address. Handle L2TPv2 and L2TPv3.
-	 * This is nasty because there are different sockaddr_pppol2tp
-	 * structs for L2TPv2, L2TPv3, over IPv4 and IPv6. We use
-	 * the sockaddr size to determine which structure the caller
-	 * is using.
-	 */
-	peer_tunnel_id = 0;
-	if (sockaddr_len == sizeof(struct sockaddr_pppol2tp)) {
-		fd = sp->pppol2tp.fd;
-		tunnel_id = sp->pppol2tp.s_tunnel;
-		peer_tunnel_id = sp->pppol2tp.d_tunnel;
-		session_id = sp->pppol2tp.s_session;
-		peer_session_id = sp->pppol2tp.d_session;
-	} else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3)) {
-		struct sockaddr_pppol2tpv3 *sp3 =
-			(struct sockaddr_pppol2tpv3 *) sp;
-		ver = 3;
-		fd = sp3->pppol2tp.fd;
-		tunnel_id = sp3->pppol2tp.s_tunnel;
-		peer_tunnel_id = sp3->pppol2tp.d_tunnel;
-		session_id = sp3->pppol2tp.s_session;
-		peer_session_id = sp3->pppol2tp.d_session;
-	} else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpin6)) {
-		struct sockaddr_pppol2tpin6 *sp6 =
-			(struct sockaddr_pppol2tpin6 *) sp;
-		fd = sp6->pppol2tp.fd;
-		tunnel_id = sp6->pppol2tp.s_tunnel;
-		peer_tunnel_id = sp6->pppol2tp.d_tunnel;
-		session_id = sp6->pppol2tp.s_session;
-		peer_session_id = sp6->pppol2tp.d_session;
-	} else if (sockaddr_len == sizeof(struct sockaddr_pppol2tpv3in6)) {
-		struct sockaddr_pppol2tpv3in6 *sp6 =
-			(struct sockaddr_pppol2tpv3in6 *) sp;
-		ver = 3;
-		fd = sp6->pppol2tp.fd;
-		tunnel_id = sp6->pppol2tp.s_tunnel;
-		peer_tunnel_id = sp6->pppol2tp.d_tunnel;
-		session_id = sp6->pppol2tp.s_session;
-		peer_session_id = sp6->pppol2tp.d_session;
-	} else {
-		error = -EINVAL;
-		goto end; /* bad socket address */
-	}
-
 	/* Don't bind if tunnel_id is 0 */
 	error = -EINVAL;
-	if (tunnel_id == 0)
+	if (!info.tunnel_id)
 		goto end;
 
-	tunnel = l2tp_tunnel_get(sock_net(sk), tunnel_id);
+	tunnel = l2tp_tunnel_get(sock_net(sk), info.tunnel_id);
 	if (tunnel)
 		drop_tunnel = true;
 
@@ -690,7 +719,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	 * peer_session_id is 0. Otherwise look up tunnel using supplied
 	 * tunnel id.
 	 */
-	if ((session_id == 0) && (peer_session_id == 0)) {
+	if (!info.session_id && !info.peer_session_id) {
 		if (tunnel == NULL) {
 			struct l2tp_tunnel_cfg tcfg = {
 				.encap = L2TP_ENCAPTYPE_UDP,
@@ -700,12 +729,16 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 			/* Prevent l2tp_tunnel_register() from trying to set up
 			 * a kernel socket.
 			 */
-			if (fd < 0) {
+			if (info.fd < 0) {
 				error = -EBADF;
 				goto end;
 			}
 
-			error = l2tp_tunnel_create(sock_net(sk), fd, ver, tunnel_id, peer_tunnel_id, &tcfg, &tunnel);
+			error = l2tp_tunnel_create(sock_net(sk), info.fd,
+						   info.version,
+						   info.tunnel_id,
+						   info.peer_tunnel_id, &tcfg,
+						   &tunnel);
 			if (error < 0)
 				goto end;
 
@@ -734,9 +767,9 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		tunnel->recv_payload_hook = pppol2tp_recv_payload_hook;
 
 	if (tunnel->peer_tunnel_id == 0)
-		tunnel->peer_tunnel_id = peer_tunnel_id;
+		tunnel->peer_tunnel_id = info.peer_tunnel_id;
 
-	session = l2tp_session_get(sock_net(sk), tunnel, session_id);
+	session = l2tp_session_get(sock_net(sk), tunnel, info.session_id);
 	if (session) {
 		drop_refcnt = true;
 
@@ -765,8 +798,8 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 		cfg.pw_type = L2TP_PWTYPE_PPP;
 
 		session = l2tp_session_create(sizeof(struct pppol2tp_session),
-					      tunnel, session_id,
-					      peer_session_id, &cfg);
+					      tunnel, info.session_id,
+					      info.peer_session_id, &cfg);
 		if (IS_ERR(session)) {
 			error = PTR_ERR(session);
 			goto end;
-- 
cgit v1.2.3


From fd0e418d6b1d6dfa193f2196534aef1c95c205fc Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Tue, 26 Jun 2018 10:07:52 -0700
Subject: selftests: rtnetlink: clear the return code at start of ipsec test

Following the custom from the other functions, clear the global
ret code before starting the test so as to not have previously
failed tests cause us to thing this test has failed.

Reported-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index a90eb31abd59..a80a489a7296 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -525,6 +525,8 @@ kci_test_macsec()
 #-------------------------------------------------------------------
 kci_test_ipsec()
 {
+	ret=0
+
 	# find an ip address on this machine and make up a destination
 	srcip=`ip -o addr | awk '/inet / { print $4; }' | grep -v "^127" | head -1 | cut -f1 -d/`
 	net=`echo $srcip | cut -f1-3 -d.`
-- 
cgit v1.2.3


From c3eba0a4ebf0dedabf30804d4cfc31cdd87b5398 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Tue, 26 Jun 2018 10:07:53 -0700
Subject: selftests: rtnetlink: use dummydev as a test device

We really shouldn't mess with local system settings, so let's
use the already created dummy device instead for ipsec testing.
Oh, and let's put the temp file into a proper directory.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index a80a489a7296..d92905f18c7c 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -526,21 +526,19 @@ kci_test_macsec()
 kci_test_ipsec()
 {
 	ret=0
-
-	# find an ip address on this machine and make up a destination
-	srcip=`ip -o addr | awk '/inet / { print $4; }' | grep -v "^127" | head -1 | cut -f1 -d/`
-	net=`echo $srcip | cut -f1-3 -d.`
-	base=`echo $srcip | cut -f4 -d.`
-	dstip="$net."`expr $base + 1`
-
 	algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+	srcip=192.168.123.1
+	dstip=192.168.123.2
+	spi=7
+
+	ip addr add $srcip dev $devdummy
 
 	# flush to be sure there's nothing configured
 	ip x s flush ; ip x p flush
 	check_err $?
 
 	# start the monitor in the background
-	tmpfile=`mktemp ipsectestXXX`
+	tmpfile=`mktemp /var/run/ipsectestXXX`
 	mpid=`(ip x m > $tmpfile & echo $!) 2>/dev/null`
 	sleep 0.2
 
@@ -604,6 +602,7 @@ kci_test_ipsec()
 	check_err $?
 	ip x p flush
 	check_err $?
+	ip addr del $srcip/32 dev $devdummy
 
 	if [ $ret -ne 0 ]; then
 		echo "FAIL: ipsec"
-- 
cgit v1.2.3


From 7699353da875c2ae0d87a4f5a995c144115b31bb Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Tue, 26 Jun 2018 10:07:54 -0700
Subject: netdevsim: add ipsec offload testing

Implement the IPsec/XFRM offload API for testing.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/Makefile    |   4 +
 drivers/net/netdevsim/ipsec.c     | 297 ++++++++++++++++++++++++++++++++++++++
 drivers/net/netdevsim/netdev.c    |   7 +
 drivers/net/netdevsim/netdevsim.h |  41 ++++++
 4 files changed, 349 insertions(+)
 create mode 100644 drivers/net/netdevsim/ipsec.c

diff --git a/drivers/net/netdevsim/Makefile b/drivers/net/netdevsim/Makefile
index 449b2a1a1800..0fee1d06c084 100644
--- a/drivers/net/netdevsim/Makefile
+++ b/drivers/net/netdevsim/Makefile
@@ -13,3 +13,7 @@ endif
 ifneq ($(CONFIG_NET_DEVLINK),)
 netdevsim-objs += devlink.o fib.o
 endif
+
+ifneq ($(CONFIG_XFRM_OFFLOAD),)
+netdevsim-objs += ipsec.o
+endif
diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c
new file mode 100644
index 000000000000..ceff544510b9
--- /dev/null
+++ b/drivers/net/netdevsim/ipsec.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2018 Oracle and/or its affiliates. All rights reserved. */
+
+#include <crypto/aead.h>
+#include <linux/debugfs.h>
+#include <net/xfrm.h>
+
+#include "netdevsim.h"
+
+#define NSIM_IPSEC_AUTH_BITS	128
+
+static ssize_t nsim_dbg_netdev_ops_read(struct file *filp,
+					char __user *buffer,
+					size_t count, loff_t *ppos)
+{
+	struct netdevsim *ns = filp->private_data;
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	size_t bufsize;
+	char *buf, *p;
+	int len;
+	int i;
+
+	/* the buffer needed is
+	 * (num SAs * 3 lines each * ~60 bytes per line) + one more line
+	 */
+	bufsize = (ipsec->count * 4 * 60) + 60;
+	buf = kzalloc(bufsize, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	p = buf;
+	p += snprintf(p, bufsize - (p - buf),
+		      "SA count=%u tx=%u\n",
+		      ipsec->count, ipsec->tx);
+
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		struct nsim_sa *sap = &ipsec->sa[i];
+
+		if (!sap->used)
+			continue;
+
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i] %cx ipaddr=0x%08x %08x %08x %08x\n",
+			      i, (sap->rx ? 'r' : 't'), sap->ipaddr[0],
+			      sap->ipaddr[1], sap->ipaddr[2], sap->ipaddr[3]);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    spi=0x%08x proto=0x%x salt=0x%08x crypt=%d\n",
+			      i, be32_to_cpu(sap->xs->id.spi),
+			      sap->xs->id.proto, sap->salt, sap->crypt);
+		p += snprintf(p, bufsize - (p - buf),
+			      "sa[%i]    key=0x%08x %08x %08x %08x\n",
+			      i, sap->key[0], sap->key[1],
+			      sap->key[2], sap->key[3]);
+	}
+
+	len = simple_read_from_buffer(buffer, count, ppos, buf, p - buf);
+
+	kfree(buf);
+	return len;
+}
+
+static const struct file_operations ipsec_dbg_fops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = nsim_dbg_netdev_ops_read,
+};
+
+static int nsim_ipsec_find_empty_idx(struct nsim_ipsec *ipsec)
+{
+	u32 i;
+
+	if (ipsec->count == NSIM_IPSEC_MAX_SA_COUNT)
+		return -ENOSPC;
+
+	/* search sa table */
+	for (i = 0; i < NSIM_IPSEC_MAX_SA_COUNT; i++) {
+		if (!ipsec->sa[i].used)
+			return i;
+	}
+
+	return -ENOSPC;
+}
+
+static int nsim_ipsec_parse_proto_keys(struct xfrm_state *xs,
+				       u32 *mykey, u32 *mysalt)
+{
+	const char aes_gcm_name[] = "rfc4106(gcm(aes))";
+	struct net_device *dev = xs->xso.dev;
+	unsigned char *key_data;
+	char *alg_name = NULL;
+	int key_len;
+
+	if (!xs->aead) {
+		netdev_err(dev, "Unsupported IPsec algorithm\n");
+		return -EINVAL;
+	}
+
+	if (xs->aead->alg_icv_len != NSIM_IPSEC_AUTH_BITS) {
+		netdev_err(dev, "IPsec offload requires %d bit authentication\n",
+			   NSIM_IPSEC_AUTH_BITS);
+		return -EINVAL;
+	}
+
+	key_data = &xs->aead->alg_key[0];
+	key_len = xs->aead->alg_key_len;
+	alg_name = xs->aead->alg_name;
+
+	if (strcmp(alg_name, aes_gcm_name)) {
+		netdev_err(dev, "Unsupported IPsec algorithm - please use %s\n",
+			   aes_gcm_name);
+		return -EINVAL;
+	}
+
+	/* 160 accounts for 16 byte key and 4 byte salt */
+	if (key_len > NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = ((u32 *)key_data)[4];
+	} else if (key_len == NSIM_IPSEC_AUTH_BITS) {
+		*mysalt = 0;
+	} else {
+		netdev_err(dev, "IPsec hw offload only supports 128 bit keys with optional 32 bit salt\n");
+		return -EINVAL;
+	}
+	memcpy(mykey, key_data, 16);
+
+	return 0;
+}
+
+static int nsim_ipsec_add_sa(struct xfrm_state *xs)
+{
+	struct nsim_ipsec *ipsec;
+	struct net_device *dev;
+	struct netdevsim *ns;
+	struct nsim_sa sa;
+	u16 sa_idx;
+	int ret;
+
+	dev = xs->xso.dev;
+	ns = netdev_priv(dev);
+	ipsec = &ns->ipsec;
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(dev, "Unsupported protocol 0x%04x for ipsec offload\n",
+			   xs->id.proto);
+		return -EINVAL;
+	}
+
+	if (xs->calg) {
+		netdev_err(dev, "Compression offload not supported\n");
+		return -EINVAL;
+	}
+
+	/* find the first unused index */
+	ret = nsim_ipsec_find_empty_idx(ipsec);
+	if (ret < 0) {
+		netdev_err(dev, "No space for SA in Rx table!\n");
+		return ret;
+	}
+	sa_idx = (u16)ret;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.used = true;
+	sa.xs = xs;
+
+	if (sa.xs->id.proto & IPPROTO_ESP)
+		sa.crypt = xs->ealg || xs->aead;
+
+	/* get the key and salt */
+	ret = nsim_ipsec_parse_proto_keys(xs, sa.key, &sa.salt);
+	if (ret) {
+		netdev_err(dev, "Failed to get key data for SA table\n");
+		return ret;
+	}
+
+	if (xs->xso.flags & XFRM_OFFLOAD_INBOUND) {
+		sa.rx = true;
+
+		if (xs->props.family == AF_INET6)
+			memcpy(sa.ipaddr, &xs->id.daddr.a6, 16);
+		else
+			memcpy(&sa.ipaddr[3], &xs->id.daddr.a4, 4);
+	}
+
+	/* the preparations worked, so save the info */
+	memcpy(&ipsec->sa[sa_idx], &sa, sizeof(sa));
+
+	/* the XFRM stack doesn't like offload_handle == 0,
+	 * so add a bitflag in case our array index is 0
+	 */
+	xs->xso.offload_handle = sa_idx | NSIM_IPSEC_VALID;
+	ipsec->count++;
+
+	return 0;
+}
+
+static void nsim_ipsec_del_sa(struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	u16 sa_idx;
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (!ipsec->sa[sa_idx].used) {
+		netdev_err(ns->netdev, "Invalid SA for delete sa_idx=%d\n",
+			   sa_idx);
+		return;
+	}
+
+	memset(&ipsec->sa[sa_idx], 0, sizeof(struct nsim_sa));
+	ipsec->count--;
+}
+
+static bool nsim_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+{
+	struct netdevsim *ns = netdev_priv(xs->xso.dev);
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	ipsec->ok++;
+
+	return true;
+}
+
+static const struct xfrmdev_ops nsim_xfrmdev_ops = {
+	.xdo_dev_state_add	= nsim_ipsec_add_sa,
+	.xdo_dev_state_delete	= nsim_ipsec_del_sa,
+	.xdo_dev_offload_ok	= nsim_ipsec_offload_ok,
+};
+
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+	struct xfrm_state *xs;
+	struct nsim_sa *tsa;
+	u32 sa_idx;
+
+	/* do we even need to check this packet? */
+	if (!skb->sp)
+		return true;
+
+	if (unlikely(!skb->sp->len)) {
+		netdev_err(ns->netdev, "no xfrm state len = %d\n",
+			   skb->sp->len);
+		return false;
+	}
+
+	xs = xfrm_input_state(skb);
+	if (unlikely(!xs)) {
+		netdev_err(ns->netdev, "no xfrm_input_state() xs = %p\n", xs);
+		return false;
+	}
+
+	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
+	if (unlikely(sa_idx > NSIM_IPSEC_MAX_SA_COUNT)) {
+		netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n",
+			   sa_idx, NSIM_IPSEC_MAX_SA_COUNT);
+		return false;
+	}
+
+	tsa = &ipsec->sa[sa_idx];
+	if (unlikely(!tsa->used)) {
+		netdev_err(ns->netdev, "unused sa_idx=%d\n", sa_idx);
+		return false;
+	}
+
+	if (xs->id.proto != IPPROTO_ESP && xs->id.proto != IPPROTO_AH) {
+		netdev_err(ns->netdev, "unexpected proto=%d\n", xs->id.proto);
+		return false;
+	}
+
+	ipsec->tx++;
+
+	return true;
+}
+
+void nsim_ipsec_init(struct netdevsim *ns)
+{
+	ns->netdev->xfrmdev_ops = &nsim_xfrmdev_ops;
+
+#define NSIM_ESP_FEATURES	(NETIF_F_HW_ESP | \
+				 NETIF_F_HW_ESP_TX_CSUM | \
+				 NETIF_F_GSO_ESP)
+
+	ns->netdev->features |= NSIM_ESP_FEATURES;
+	ns->netdev->hw_enc_features |= NSIM_ESP_FEATURES;
+
+	ns->ipsec.pfile = debugfs_create_file("ipsec", 0400, ns->ddir, ns,
+					      &ipsec_dbg_fops);
+}
+
+void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+	struct nsim_ipsec *ipsec = &ns->ipsec;
+
+	if (ipsec->count)
+		netdev_err(ns->netdev, "tearing down IPsec offload with %d SAs left\n",
+			   ipsec->count);
+	debugfs_remove_recursive(ipsec->pfile);
+}
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index c9dacc6fcd59..b2f9d0df93b0 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -171,6 +171,8 @@ static int nsim_init(struct net_device *dev)
 	if (err)
 		goto err_unreg_dev;
 
+	nsim_ipsec_init(ns);
+
 	return 0;
 
 err_unreg_dev:
@@ -186,6 +188,7 @@ static void nsim_uninit(struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
+	nsim_ipsec_teardown(ns);
 	nsim_devlink_teardown(ns);
 	debugfs_remove_recursive(ns->ddir);
 	nsim_bpf_uninit(ns);
@@ -203,11 +206,15 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
+	if (!nsim_ipsec_tx(ns, skb))
+		goto out;
+
 	u64_stats_update_begin(&ns->syncp);
 	ns->tx_packets++;
 	ns->tx_bytes += skb->len;
 	u64_stats_update_end(&ns->syncp);
 
+out:
 	dev_kfree_skb(skb);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 8ca50b72c328..d8a7cc995e88 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -29,6 +29,27 @@ struct bpf_prog;
 struct dentry;
 struct nsim_vf_config;
 
+#define NSIM_IPSEC_MAX_SA_COUNT		33
+#define NSIM_IPSEC_VALID		BIT(31)
+
+struct nsim_sa {
+	struct xfrm_state *xs;
+	__be32 ipaddr[4];
+	u32 key[4];
+	u32 salt;
+	bool used;
+	bool crypt;
+	bool rx;
+};
+
+struct nsim_ipsec {
+	struct nsim_sa sa[NSIM_IPSEC_MAX_SA_COUNT];
+	struct dentry *pfile;
+	u32 count;
+	u32 tx;
+	u32 ok;
+};
+
 struct netdevsim {
 	struct net_device *netdev;
 
@@ -67,6 +88,7 @@ struct netdevsim {
 #if IS_ENABLED(CONFIG_NET_DEVLINK)
 	struct devlink *devlink;
 #endif
+	struct nsim_ipsec ipsec;
 };
 
 extern struct dentry *nsim_ddir;
@@ -148,6 +170,25 @@ static inline void nsim_devlink_exit(void)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_XFRM_OFFLOAD)
+void nsim_ipsec_init(struct netdevsim *ns);
+void nsim_ipsec_teardown(struct netdevsim *ns);
+bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb);
+#else
+static inline void nsim_ipsec_init(struct netdevsim *ns)
+{
+}
+
+static inline void nsim_ipsec_teardown(struct netdevsim *ns)
+{
+}
+
+static inline bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
+{
+	return true;
+}
+#endif
+
 static inline struct netdevsim *to_nsim(struct device *ptr)
 {
 	return container_of(ptr, struct netdevsim, dev);
-- 
cgit v1.2.3


From 2766a11161cc6995421bc5730eb4819231f40cfb Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Tue, 26 Jun 2018 10:07:55 -0700
Subject: selftests: rtnetlink: add ipsec offload API test

Using the netdevsim as a device for testing, try out the XFRM commands
for setting up IPsec hardware offloads.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/rtnetlink.sh | 114 +++++++++++++++++++++++++++++++
 1 file changed, 114 insertions(+)

diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh
index d92905f18c7c..08c341b49760 100755
--- a/tools/testing/selftests/net/rtnetlink.sh
+++ b/tools/testing/selftests/net/rtnetlink.sh
@@ -611,6 +611,119 @@ kci_test_ipsec()
 	echo "PASS: ipsec"
 }
 
+#-------------------------------------------------------------------
+# Example commands
+#   ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \
+#            spi 0x07 mode transport reqid 0x07 replay-window 32 \
+#            aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \
+#            sel src 14.0.0.52/24 dst 14.0.0.70/24
+#            offload dev sim1 dir out
+#   ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \
+#            tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \
+#            spi 0x07 mode transport reqid 0x07
+#
+#-------------------------------------------------------------------
+kci_test_ipsec_offload()
+{
+	ret=0
+	algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128"
+	srcip=192.168.123.3
+	dstip=192.168.123.4
+	dev=simx1
+	sysfsd=/sys/kernel/debug/netdevsim/$dev
+	sysfsf=$sysfsd/ipsec
+
+	# setup netdevsim since dummydev doesn't have offload support
+	modprobe netdevsim
+	check_err $?
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: ipsec_offload can't load netdevsim"
+		return 1
+	fi
+
+	ip link add $dev type netdevsim
+	ip addr add $srcip dev $dev
+	ip link set $dev up
+	if [ ! -d $sysfsd ] ; then
+		echo "FAIL: ipsec_offload can't create device $dev"
+		return 1
+	fi
+	if [ ! -f $sysfsf ] ; then
+		echo "FAIL: ipsec_offload netdevsim doesn't support IPsec offload"
+		return 1
+	fi
+
+	# flush to be sure there's nothing configured
+	ip x s flush ; ip x p flush
+
+	# create offloaded SAs, both in and out
+	ip x p add dir out src $srcip/24 dst $dstip/24 \
+	    tmpl proto esp src $srcip dst $dstip spi 9 \
+	    mode transport reqid 42
+	check_err $?
+	ip x p add dir out src $dstip/24 dst $srcip/24 \
+	    tmpl proto esp src $dstip dst $srcip spi 9 \
+	    mode transport reqid 42
+	check_err $?
+
+	ip x s add proto esp src $srcip dst $dstip spi 9 \
+	    mode transport reqid 42 $algo sel src $srcip/24 dst $dstip/24 \
+	    offload dev $dev dir out
+	check_err $?
+	ip x s add proto esp src $dstip dst $srcip spi 9 \
+	    mode transport reqid 42 $algo sel src $dstip/24 dst $srcip/24 \
+	    offload dev $dev dir in
+	check_err $?
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: ipsec_offload can't create SA"
+		return 1
+	fi
+
+	# does offload show up in ip output
+	lines=`ip x s list | grep -c "crypto offload parameters: dev $dev dir"`
+	if [ $lines -ne 2 ] ; then
+		echo "FAIL: ipsec_offload SA offload missing from list output"
+		check_err 1
+	fi
+
+	# use ping to exercise the Tx path
+	ping -I $dev -c 3 -W 1 -i 0 $dstip >/dev/null
+
+	# does driver have correct offload info
+	diff $sysfsf - << EOF
+SA count=2 tx=3
+sa[0] tx ipaddr=0x00000000 00000000 00000000 00000000
+sa[0]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
+sa[0]    key=0x34333231 38373635 32313039 36353433
+sa[1] rx ipaddr=0x00000000 00000000 00000000 037ba8c0
+sa[1]    spi=0x00000009 proto=0x32 salt=0x61626364 crypt=1
+sa[1]    key=0x34333231 38373635 32313039 36353433
+EOF
+	if [ $? -ne 0 ] ; then
+		echo "FAIL: ipsec_offload incorrect driver data"
+		check_err 1
+	fi
+
+	# does offload get removed from driver
+	ip x s flush
+	ip x p flush
+	lines=`grep -c "SA count=0" $sysfsf`
+	if [ $lines -ne 1 ] ; then
+		echo "FAIL: ipsec_offload SA not removed from driver"
+		check_err 1
+	fi
+
+	# clean up any leftovers
+	ip link del $dev
+	rmmod netdevsim
+
+	if [ $ret -ne 0 ]; then
+		echo "FAIL: ipsec_offload"
+		return 1
+	fi
+	echo "PASS: ipsec_offload"
+}
+
 kci_test_gretap()
 {
 	testns="testns"
@@ -865,6 +978,7 @@ kci_test_rtnl()
 	kci_test_encap
 	kci_test_macsec
 	kci_test_ipsec
+	kci_test_ipsec_offload
 
 	kci_del_dummy
 }
-- 
cgit v1.2.3


From ab4e6ee578e88a659938db8fbf33720bc048d29c Mon Sep 17 00:00:00 2001
From: Brandon Maier <brandon.maier@rockwellcollins.com>
Date: Tue, 26 Jun 2018 12:50:48 -0500
Subject: net: phy: xgmiitorgmii: Check phy_driver ready before accessing

Since a phy_device is added to the global mdio_bus list during
phy_device_register(), but a phy_device's phy_driver doesn't get
attached until phy_probe(). It's possible of_phy_find_device() in
xgmiitorgmii will return a valid phy with a NULL phy_driver. Leading to
a NULL pointer access during the memcpy().

Fixes this Oops:

Unable to handle kernel NULL pointer dereference at virtual address 00000000
pgd = c0004000
[00000000] *pgd=00000000
Internal error: Oops: 5 [#1] PREEMPT SMP ARM
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.14.40 #1
Hardware name: Xilinx Zynq Platform
task: ce4c8d00 task.stack: ce4ca000
PC is at memcpy+0x48/0x330
LR is at xgmiitorgmii_probe+0x90/0xe8
pc : [<c074bc68>]    lr : [<c0529548>]    psr: 20000013
sp : ce4cbb54  ip : 00000000  fp : ce4cbb8c
r10: 00000000  r9 : 00000000  r8 : c0c49178
r7 : 00000000  r6 : cdc14718  r5 : ce762800  r4 : cdc14710
r3 : 00000000  r2 : 00000054  r1 : 00000000  r0 : cdc14718
Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
Control: 18c5387d  Table: 0000404a  DAC: 00000051
Process swapper/0 (pid: 1, stack limit = 0xce4ca210)
...
[<c074bc68>] (memcpy) from [<c0529548>] (xgmiitorgmii_probe+0x90/0xe8)
[<c0529548>] (xgmiitorgmii_probe) from [<c0526a94>] (mdio_probe+0x28/0x34)
[<c0526a94>] (mdio_probe) from [<c04db98c>] (driver_probe_device+0x254/0x414)
[<c04db98c>] (driver_probe_device) from [<c04dbd58>] (__device_attach_driver+0xac/0x10c)
[<c04dbd58>] (__device_attach_driver) from [<c04d96f4>] (bus_for_each_drv+0x84/0xc8)
[<c04d96f4>] (bus_for_each_drv) from [<c04db5bc>] (__device_attach+0xd0/0x134)
[<c04db5bc>] (__device_attach) from [<c04dbdd4>] (device_initial_probe+0x1c/0x20)
[<c04dbdd4>] (device_initial_probe) from [<c04da8fc>] (bus_probe_device+0x98/0xa0)
[<c04da8fc>] (bus_probe_device) from [<c04d8660>] (device_add+0x43c/0x5d0)
[<c04d8660>] (device_add) from [<c0526cb8>] (mdio_device_register+0x34/0x80)
[<c0526cb8>] (mdio_device_register) from [<c0580b48>] (of_mdiobus_register+0x170/0x30c)
[<c0580b48>] (of_mdiobus_register) from [<c05349c4>] (macb_probe+0x710/0xc00)
[<c05349c4>] (macb_probe) from [<c04dd700>] (platform_drv_probe+0x44/0x80)
[<c04dd700>] (platform_drv_probe) from [<c04db98c>] (driver_probe_device+0x254/0x414)
[<c04db98c>] (driver_probe_device) from [<c04dbc58>] (__driver_attach+0x10c/0x118)
[<c04dbc58>] (__driver_attach) from [<c04d9600>] (bus_for_each_dev+0x8c/0xd0)
[<c04d9600>] (bus_for_each_dev) from [<c04db1fc>] (driver_attach+0x2c/0x30)
[<c04db1fc>] (driver_attach) from [<c04daa98>] (bus_add_driver+0x50/0x260)
[<c04daa98>] (bus_add_driver) from [<c04dc440>] (driver_register+0x88/0x108)
[<c04dc440>] (driver_register) from [<c04dd6b4>] (__platform_driver_register+0x50/0x58)
[<c04dd6b4>] (__platform_driver_register) from [<c0b31248>] (macb_driver_init+0x24/0x28)
[<c0b31248>] (macb_driver_init) from [<c010203c>] (do_one_initcall+0x60/0x1a4)
[<c010203c>] (do_one_initcall) from [<c0b00f78>] (kernel_init_freeable+0x15c/0x1f8)
[<c0b00f78>] (kernel_init_freeable) from [<c0763d10>] (kernel_init+0x18/0x124)
[<c0763d10>] (kernel_init) from [<c0112d74>] (ret_from_fork+0x14/0x20)
Code: ba000002 f5d1f03c f5d1f05c f5d1f07c (e8b151f8)
---[ end trace 3e4ec21905820a1f ]---

Signed-off-by: Brandon Maier <brandon.maier@rockwellcollins.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 2e5150b0b8d5..04c8bec1c4c1 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -81,6 +81,11 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev)
 		return -EPROBE_DEFER;
 	}
 
+	if (!priv->phy_dev->drv) {
+		dev_info(dev, "Attached phy not ready\n");
+		return -EPROBE_DEFER;
+	}
+
 	priv->addr = mdiodev->addr;
 	priv->phy_drv = priv->phy_dev->drv;
 	memcpy(&priv->conv_phy_drv, priv->phy_dev->drv,
-- 
cgit v1.2.3


From cf31ea71c0593ca6227bd3f4958c098753267f44 Mon Sep 17 00:00:00 2001
From: Brandon Maier <brandon.maier@rockwellcollins.com>
Date: Tue, 26 Jun 2018 12:50:49 -0500
Subject: net: phy: xgmiitorgmii: Use correct mdio bus

The xgmiitorgmii is using the mii_bus of the device it's attached to,
instead of the bus it was given during probe.

Signed-off-by: Brandon Maier <brandon.maier@rockwellcollins.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 04c8bec1c4c1..d6f8b64cddbe 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -33,17 +33,19 @@ struct gmii2rgmii {
 	struct phy_device *phy_dev;
 	struct phy_driver *phy_drv;
 	struct phy_driver conv_phy_drv;
-	int addr;
+	struct mdio_device *mdio;
 };
 
 static int xgmiitorgmii_read_status(struct phy_device *phydev)
 {
 	struct gmii2rgmii *priv = phydev->priv;
+	struct mii_bus *bus = priv->mdio->bus;
+	int addr = priv->mdio->addr;
 	u16 val = 0;
 
 	priv->phy_drv->read_status(phydev);
 
-	val = mdiobus_read(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG);
+	val = mdiobus_read(bus, addr, XILINX_GMII2RGMII_REG);
 	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
 
 	if (phydev->speed == SPEED_1000)
@@ -53,7 +55,7 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	else
 		val |= BMCR_SPEED10;
 
-	mdiobus_write(phydev->mdio.bus, priv->addr, XILINX_GMII2RGMII_REG, val);
+	mdiobus_write(bus, addr, XILINX_GMII2RGMII_REG, val);
 
 	return 0;
 }
@@ -86,7 +88,7 @@ static int xgmiitorgmii_probe(struct mdio_device *mdiodev)
 		return -EPROBE_DEFER;
 	}
 
-	priv->addr = mdiodev->addr;
+	priv->mdio = mdiodev;
 	priv->phy_drv = priv->phy_dev->drv;
 	memcpy(&priv->conv_phy_drv, priv->phy_dev->drv,
 	       sizeof(struct phy_driver));
-- 
cgit v1.2.3


From 8d0752d11312be830c33e84dfd1016e6a47c2938 Mon Sep 17 00:00:00 2001
From: Brandon Maier <brandon.maier@rockwellcollins.com>
Date: Tue, 26 Jun 2018 12:50:50 -0500
Subject: net: phy: xgmiitorgmii: Check read_status results

We're ignoring the result of the attached phy device's read_status().
Return it so we can detect errors.

Signed-off-by: Brandon Maier <brandon.maier@rockwellcollins.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/xilinx_gmii2rgmii.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index d6f8b64cddbe..74a8782313cf 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -42,8 +42,11 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	struct mii_bus *bus = priv->mdio->bus;
 	int addr = priv->mdio->addr;
 	u16 val = 0;
+	int err;
 
-	priv->phy_drv->read_status(phydev);
+	err = priv->phy_drv->read_status(phydev);
+	if (err < 0)
+		return err;
 
 	val = mdiobus_read(bus, addr, XILINX_GMII2RGMII_REG);
 	val &= ~XILINX_GMII2RGMII_SPEED_MASK;
-- 
cgit v1.2.3


From 7861552cedd81a164c0d5d1c89fe2cb45a3ed41b Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@gmail.com>
Date: Tue, 26 Jun 2018 12:39:18 -0700
Subject: netlink: Return extack message if attribute validation fails

Have one extack message for parsing and validating.

Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/nlattr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/lib/nlattr.c b/lib/nlattr.c
index dfa55c873c13..e335bcafa9e4 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -253,8 +253,8 @@ int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head,
 			if (policy) {
 				err = validate_nla(nla, maxtype, policy);
 				if (err < 0) {
-					if (extack)
-						extack->bad_attr = nla;
+					NL_SET_ERR_MSG_ATTR(extack, nla,
+							    "Attribute failed policy validation");
 					goto errout;
 				}
 			}
-- 
cgit v1.2.3


From 1adca4b0cd65c14cb8b8c9c257720385869c3d5f Mon Sep 17 00:00:00 2001
From: Kai-Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 28 Jun 2018 15:28:24 +0800
Subject: ALSA: hda: Add AZX_DCAPS_PM_RUNTIME for AMD Raven Ridge

This patch can make audio controller in AMD Raven Ridge gets runtime
suspended to D3, to save ~1W power when it's not in use.

Cc: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 1ae1850b3bfd..a9b55d65f2bd 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2535,7 +2535,8 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
 	/* AMD Raven */
 	{ PCI_DEVICE(0x1022, 0x15e3),
-	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB },
+	  .driver_data = AZX_DRIVER_GENERIC | AZX_DCAPS_PRESET_ATI_SB |
+			 AZX_DCAPS_PM_RUNTIME },
 	/* ATI HDMI */
 	{ PCI_DEVICE(0x1002, 0x0002),
 	  .driver_data = AZX_DRIVER_ATIHDMI_NS | AZX_DCAPS_PRESET_ATI_HDMI_NS },
-- 
cgit v1.2.3


From c8291988806407e02a01b4b15b4504eafbcc04e0 Mon Sep 17 00:00:00 2001
From: Zhi Chen <zhichen@codeaurora.org>
Date: Mon, 18 Jun 2018 17:00:39 +0300
Subject: ath10k: fix scan crash due to incorrect length calculation

Length of WMI scan message was not calculated correctly. The allocated
buffer was smaller than what we expected. So WMI message corrupted
skb_info, which is at the end of skb->data. This fix takes TLV header
into account even if the element is zero-length.

Crash log:
  [49.629986] Unhandled kernel unaligned access[#1]:
  [49.634932] CPU: 0 PID: 1176 Comm: logd Not tainted 4.4.60 #180
  [49.641040] task: 83051460 ti: 8329c000 task.ti: 8329c000
  [49.646608] $ 0   : 00000000 00000001 80984a80 00000000
  [49.652038] $ 4   : 45259e89 8046d484 8046df30 8024ba70
  [49.657468] $ 8   : 00000000 804cc4c0 00000001 20306320
  [49.662898] $12   : 33322037 000110f2 00000000 31203930
  [49.668327] $16   : 82792b40 80984a80 00000001 804207fc
  [49.673757] $20   : 00000000 0000012c 00000040 80470000
  [49.679186] $24   : 00000000 8024af7c
  [49.684617] $28   : 8329c000 8329db88 00000001 802c58d0
  [49.690046] Hi    : 00000000
  [49.693022] Lo    : 453c0000
  [49.696013] epc   : 800efae4 put_page+0x0/0x58
  [49.700615] ra    : 802c58d0 skb_release_data+0x148/0x1d4
  [49.706184] Status: 1000fc03 KERNEL EXL IE
  [49.710531] Cause : 00800010 (ExcCode 04)
  [49.714669] BadVA : 45259e89
  [49.717644] PrId  : 00019374 (MIPS 24Kc)

Signed-off-by: Zhi Chen <zhichen@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 8c49a26fc571..455ce18918bd 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -1614,10 +1614,10 @@ ath10k_wmi_tlv_op_gen_start_scan(struct ath10k *ar,
 	bssid_len = arg->n_bssids * sizeof(struct wmi_mac_addr);
 	ie_len = roundup(arg->ie_len, 4);
 	len = (sizeof(*tlv) + sizeof(*cmd)) +
-	      (arg->n_channels ? sizeof(*tlv) + chan_len : 0) +
-	      (arg->n_ssids ? sizeof(*tlv) + ssid_len : 0) +
-	      (arg->n_bssids ? sizeof(*tlv) + bssid_len : 0) +
-	      (arg->ie_len ? sizeof(*tlv) + ie_len : 0);
+	      sizeof(*tlv) + chan_len +
+	      sizeof(*tlv) + ssid_len +
+	      sizeof(*tlv) + bssid_len +
+	      sizeof(*tlv) + ie_len;
 
 	skb = ath10k_wmi_alloc_skb(ar, len);
 	if (!skb)
-- 
cgit v1.2.3


From 98dc04ba60b9c2df1e70c2fe1ea480476a570615 Mon Sep 17 00:00:00 2001
From: Zhi Chen <zhichen@codeaurora.org>
Date: Mon, 18 Jun 2018 17:00:43 +0300
Subject: ath10k: fix tlv 5ghz channel missing issue

The 5ghz channel parameters of TLV target wasn't passed to host, it caused
host can only use lower channels from 36 to 64.

Signed-off-by: Zhi Chen <zhichen@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 455ce18918bd..b04f86f8038a 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -1076,6 +1076,8 @@ static int ath10k_wmi_tlv_op_pull_svc_rdy_ev(struct ath10k *ar,
 	arg->phy_capab = ev->phy_capability;
 	arg->num_rf_chains = ev->num_rf_chains;
 	arg->eeprom_rd = reg->eeprom_rd;
+	arg->low_5ghz_chan = reg->low_5ghz_chan;
+	arg->high_5ghz_chan = reg->high_5ghz_chan;
 	arg->num_mem_reqs = ev->num_mem_reqs;
 	arg->service_map = svc_bmap;
 	arg->service_map_len = ath10k_wmi_tlv_len(svc_bmap);
-- 
cgit v1.2.3


From 3f04950f32d5d592ab4fcaecac2178558a6f7437 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Mon, 18 Jun 2018 17:00:49 +0300
Subject: ath10k: transmit queued frames after processing rx packets

When running iperf on ath10k SDIO, TX can stop working:

iperf -c 192.168.1.1 -i 1 -t 20 -w 10K
[  3]  0.0- 1.0 sec  2.00 MBytes  16.8 Mbits/sec
[  3]  1.0- 2.0 sec  3.12 MBytes  26.2 Mbits/sec
[  3]  2.0- 3.0 sec  3.25 MBytes  27.3 Mbits/sec
[  3]  3.0- 4.0 sec   655 KBytes  5.36 Mbits/sec
[  3]  4.0- 5.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  5.0- 6.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  6.0- 7.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  7.0- 8.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  8.0- 9.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  9.0-10.0 sec  0.00 Bytes  0.00 bits/sec
[  3]  0.0-10.3 sec  9.01 MBytes  7.32 Mbits/sec

There are frames in the ieee80211_txq and there are frames that have
been removed from from this queue, but haven't yet been sent on the wire
(num_pending_tx).

When num_pending_tx reaches max_num_pending_tx, we will stop the queues
by calling ieee80211_stop_queues().

As frames that have previously been sent for transmission
(num_pending_tx) are completed, we will decrease num_pending_tx and wake
the queues by calling ieee80211_wake_queue(). ieee80211_wake_queue()
does not call wake_tx_queue, so we might still have frames in the
queue at this point.

While the queues were stopped, the socket buffer might have filled up,
and in order for user space to write more, we need to free the frames
in the queue, since they are accounted to the socket. In order to free
them, we first need to transmit them.

This problem cannot be reproduced on low-latency devices, e.g. pci,
since they call ath10k_mac_tx_push_pending() from
ath10k_htt_txrx_compl_task(). ath10k_htt_txrx_compl_task() is not called
on high-latency devices.
Fix the problem by calling ath10k_mac_tx_push_pending(), after
processing rx packets, just like for low-latency devices, also in the
SDIO case. Since we are calling ath10k_mac_tx_push_pending() directly,
we also need to export it.

Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c  | 1 +
 drivers/net/wireless/ath/ath10k/sdio.c | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index f31ae3be4778..a6a34486eca3 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4047,6 +4047,7 @@ void ath10k_mac_tx_push_pending(struct ath10k *ar)
 	rcu_read_unlock();
 	spin_unlock_bh(&ar->txqs_lock);
 }
+EXPORT_SYMBOL(ath10k_mac_tx_push_pending);
 
 /************/
 /* Scanning */
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index d612ce8c9cff..2856c75f9011 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -30,6 +30,7 @@
 #include "debug.h"
 #include "hif.h"
 #include "htc.h"
+#include "mac.h"
 #include "targaddrs.h"
 #include "trace.h"
 #include "sdio.h"
@@ -1342,6 +1343,8 @@ static void ath10k_sdio_irq_handler(struct sdio_func *func)
 			break;
 	} while (time_before(jiffies, timeout) && !done);
 
+	ath10k_mac_tx_push_pending(ar);
+
 	sdio_claim_host(ar_sdio->func);
 
 	if (ret && ret != -ECANCELED)
-- 
cgit v1.2.3


From 168f75f11fe68455e0d058a818ebccfc329d8685 Mon Sep 17 00:00:00 2001
From: Ben Greear <greearb@candelatech.com>
Date: Mon, 18 Jun 2018 17:00:56 +0300
Subject: ath10k: protect ath10k_htt_rx_ring_free with rx_ring.lock

While debugging driver crashes related to a buggy firmware
crashing under load, I noticed that ath10k_htt_rx_ring_free
could be called without being under lock.  I'm not sure if this
is the root cause of the crash or not, but it seems prudent to
protect it.

Originally tested on 4.16+ kernel with ath10k-ct 10.4 firmware
running on 9984 NIC.

Signed-off-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index c72d8af122a2..2840ef75e3a6 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -268,11 +268,12 @@ int ath10k_htt_rx_ring_refill(struct ath10k *ar)
 	spin_lock_bh(&htt->rx_ring.lock);
 	ret = ath10k_htt_rx_ring_fill_n(htt, (htt->rx_ring.fill_level -
 					      htt->rx_ring.fill_cnt));
-	spin_unlock_bh(&htt->rx_ring.lock);
 
 	if (ret)
 		ath10k_htt_rx_ring_free(htt);
 
+	spin_unlock_bh(&htt->rx_ring.lock);
+
 	return ret;
 }
 
@@ -284,7 +285,9 @@ void ath10k_htt_rx_free(struct ath10k_htt *htt)
 	skb_queue_purge(&htt->rx_in_ord_compl_q);
 	skb_queue_purge(&htt->tx_fetch_ind_q);
 
+	spin_lock_bh(&htt->rx_ring.lock);
 	ath10k_htt_rx_ring_free(htt);
+	spin_unlock_bh(&htt->rx_ring.lock);
 
 	dma_free_coherent(htt->ar->dev,
 			  ath10k_htt_get_rx_ring_size(htt),
-- 
cgit v1.2.3


From d1a566bec5887988cd7e4b7cf98b05e1ff7a0f8a Mon Sep 17 00:00:00 2001
From: Erik Stromdahl <erik.stromdahl@gmail.com>
Date: Mon, 18 Jun 2018 17:01:21 +0300
Subject: ath10k: fix bug in masking of TID value

Although the TID mask is 0xf, the modulus operation does still not
produce identical results as the bitwise and operator. If the TID is 15, the
modulus operation will "convert" it to 0, whereas the bitwise and will keep it
as 15.

This was found during code review.

Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htt_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index 89157c5b5e5f..be5b52aaffa6 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -1056,7 +1056,7 @@ static u8 ath10k_htt_tx_get_tid(struct sk_buff *skb, bool is_eth)
 	if (!is_eth && ieee80211_is_mgmt(hdr->frame_control))
 		return HTT_DATA_TX_EXT_TID_MGMT;
 	else if (cb->flags & ATH10K_SKB_F_QOS)
-		return skb->priority % IEEE80211_QOS_CTL_TID_MASK;
+		return skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 	else
 		return HTT_DATA_TX_EXT_TID_NON_QOS_MCAST_BCAST;
 }
-- 
cgit v1.2.3


From ab687de9535c5178c1d9141664205c84493225c8 Mon Sep 17 00:00:00 2001
From: Erik Stromdahl <erik.stromdahl@gmail.com>
Date: Mon, 18 Jun 2018 17:01:23 +0300
Subject: ath10k: rename HTC_HOST_MAX_MSG_PER_BUNDLE define

This define is only used for RX bundling so it is more descriptive if
RX is added to the define-name.

Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htc.c  | 4 ++--
 drivers/net/wireless/ath/ath10k/htc.h  | 2 +-
 drivers/net/wireless/ath/ath10k/sdio.c | 4 ++--
 drivers/net/wireless/ath/ath10k/sdio.h | 8 ++++----
 4 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htc.c b/drivers/net/wireless/ath/ath10k/htc.c
index 8902720b4e49..331b8d558791 100644
--- a/drivers/net/wireless/ath/ath10k/htc.c
+++ b/drivers/net/wireless/ath/ath10k/htc.c
@@ -274,7 +274,7 @@ ath10k_htc_process_lookahead_bundle(struct ath10k_htc *htc,
 	struct ath10k *ar = htc->ar;
 	int bundle_cnt = len / sizeof(*report);
 
-	if (!bundle_cnt || (bundle_cnt > HTC_HOST_MAX_MSG_PER_BUNDLE)) {
+	if (!bundle_cnt || (bundle_cnt > HTC_HOST_MAX_MSG_PER_RX_BUNDLE)) {
 		ath10k_warn(ar, "Invalid lookahead bundle count: %d\n",
 			    bundle_cnt);
 		return -EINVAL;
@@ -655,7 +655,7 @@ int ath10k_htc_wait_target(struct ath10k_htc *htc)
 	    sizeof(msg->hdr) + sizeof(msg->ready_ext)) {
 		htc->max_msgs_per_htc_bundle =
 			min_t(u8, msg->ready_ext.max_msgs_per_htc_bundle,
-			      HTC_HOST_MAX_MSG_PER_BUNDLE);
+			      HTC_HOST_MAX_MSG_PER_RX_BUNDLE);
 		ath10k_dbg(ar, ATH10K_DBG_HTC,
 			   "Extended ready message. RX bundle size: %d\n",
 			   htc->max_msgs_per_htc_bundle);
diff --git a/drivers/net/wireless/ath/ath10k/htc.h b/drivers/net/wireless/ath/ath10k/htc.h
index 34877597dd6a..e60fbea698a9 100644
--- a/drivers/net/wireless/ath/ath10k/htc.h
+++ b/drivers/net/wireless/ath/ath10k/htc.h
@@ -50,7 +50,7 @@ struct ath10k;
  * 4-byte aligned.
  */
 
-#define HTC_HOST_MAX_MSG_PER_BUNDLE        8
+#define HTC_HOST_MAX_MSG_PER_RX_BUNDLE        8
 
 enum ath10k_htc_tx_flags {
 	ATH10K_HTC_FLAG_NEED_CREDIT_UPDATE = 0x01,
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 2856c75f9011..926e4c3ea256 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -506,11 +506,11 @@ static int ath10k_sdio_mbox_alloc_pkt_bundle(struct ath10k *ar,
 
 	*bndl_cnt = FIELD_GET(ATH10K_HTC_FLAG_BUNDLE_MASK, htc_hdr->flags);
 
-	if (*bndl_cnt > HTC_HOST_MAX_MSG_PER_BUNDLE) {
+	if (*bndl_cnt > HTC_HOST_MAX_MSG_PER_RX_BUNDLE) {
 		ath10k_warn(ar,
 			    "HTC bundle length %u exceeds maximum %u\n",
 			    le16_to_cpu(htc_hdr->len),
-			    HTC_HOST_MAX_MSG_PER_BUNDLE);
+			    HTC_HOST_MAX_MSG_PER_RX_BUNDLE);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/net/wireless/ath/ath10k/sdio.h b/drivers/net/wireless/ath/ath10k/sdio.h
index 4ff7b545293b..453eb6263143 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.h
+++ b/drivers/net/wireless/ath/ath10k/sdio.h
@@ -96,14 +96,14 @@
  * way:
  *
  * Let's assume that each packet in a bundle of the maximum bundle size
- * (HTC_HOST_MAX_MSG_PER_BUNDLE) has the HTC header bundle count set
- * to the maximum value (HTC_HOST_MAX_MSG_PER_BUNDLE).
+ * (HTC_HOST_MAX_MSG_PER_RX_BUNDLE) has the HTC header bundle count set
+ * to the maximum value (HTC_HOST_MAX_MSG_PER_RX_BUNDLE).
  *
  * in this case the driver must allocate
- * (HTC_HOST_MAX_MSG_PER_BUNDLE * HTC_HOST_MAX_MSG_PER_BUNDLE) skb's.
+ * (HTC_HOST_MAX_MSG_PER_RX_BUNDLE * HTC_HOST_MAX_MSG_PER_RX_BUNDLE) skb's.
  */
 #define ATH10K_SDIO_MAX_RX_MSGS \
-	(HTC_HOST_MAX_MSG_PER_BUNDLE * HTC_HOST_MAX_MSG_PER_BUNDLE)
+	(HTC_HOST_MAX_MSG_PER_RX_BUNDLE * HTC_HOST_MAX_MSG_PER_RX_BUNDLE)
 
 #define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL   0x00000868u
 #define ATH10K_FIFO_TIMEOUT_AND_CHIP_CONTROL_DISABLE_SLEEP_OFF 0xFFFEFFFF
-- 
cgit v1.2.3


From e4568eac0464ae6d5b361b186b1ee6eb7bf0bdbb Mon Sep 17 00:00:00 2001
From: Erik Stromdahl <erik.stromdahl@gmail.com>
Date: Mon, 18 Jun 2018 17:01:29 +0300
Subject: ath10k: replace hardcoded constant with define

The hardcoded values used in ath10k_mac_tx_push_pending and
ath10k_mac_op_wake_tx_queue set an upper limit of how many packets that
can be consumed from the TX queue.

HTC_HOST_MAX_MSG_PER_TX_BUNDLE is a proper name for this constant, as
the value effectively limits the number of messages that can be consumed
in one step. Thus, the value is an upper limit of the number of messages
that can be added to a TX message bundle.

Signed-off-by: Erik Stromdahl <erik.stromdahl@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htc.h | 1 +
 drivers/net/wireless/ath/ath10k/mac.c | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htc.h b/drivers/net/wireless/ath/ath10k/htc.h
index e60fbea698a9..d69bb83049c4 100644
--- a/drivers/net/wireless/ath/ath10k/htc.h
+++ b/drivers/net/wireless/ath/ath10k/htc.h
@@ -51,6 +51,7 @@ struct ath10k;
  */
 
 #define HTC_HOST_MAX_MSG_PER_RX_BUNDLE        8
+#define HTC_HOST_MAX_MSG_PER_TX_BUNDLE        16
 
 enum ath10k_htc_tx_flags {
 	ATH10K_HTC_FLAG_NEED_CREDIT_UPDATE = 0x01,
diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index a6a34486eca3..1cfb774be2eb 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -4026,7 +4026,7 @@ void ath10k_mac_tx_push_pending(struct ath10k *ar)
 				   drv_priv);
 
 		/* Prevent aggressive sta/tid taking over tx queue */
-		max = 16;
+		max = HTC_HOST_MAX_MSG_PER_TX_BUNDLE;
 		ret = 0;
 		while (ath10k_mac_tx_can_push(hw, txq) && max--) {
 			ret = ath10k_mac_tx_push_txq(hw, txq);
@@ -4288,7 +4288,7 @@ static void ath10k_mac_op_wake_tx_queue(struct ieee80211_hw *hw,
 	struct ieee80211_txq *f_txq;
 	struct ath10k_txq *f_artxq;
 	int ret = 0;
-	int max = 16;
+	int max = HTC_HOST_MAX_MSG_PER_TX_BUNDLE;
 
 	spin_lock_bh(&ar->txqs_lock);
 	if (list_empty(&artxq->list))
-- 
cgit v1.2.3


From de15d7ff5bef98746fcb76a0db7ac46de48d3560 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 26 Jun 2018 12:07:25 +0200
Subject: ASoC: dpcm: improve runtime update predictability

As it is, dpcm_runtime_update() performs the old path and new path
update of a frontend before going on to the next frontend DAI.
Depending the order of the FEs within the rtd list, the result of
the update might be different.

For example:
 * Frontend A connected to backend C, with a 48kHz playback
 * Frontend B connected to backend D, with a 44.1kHz playback
 * FE A appears before FE B in the rtd list of the card.

If we reparent BE C to FE B (disconnecting BE D):
* old path update of FE A will run first, and BE C will get hw_free()
  and shutdown()
* new path update of FE B will run after and BE C, which is stopped,
  so it will be configured at 44.1kHz, as expected

If we reparent BE D to FE A (disconnecting BE C):
* new path update of FE A will run first but since BE D is still running
  at 44.1kHz, it won't be reconfigured (no call to startup() or
  hw_params())
* old path update of FE B runs after, nothing happens
* In this case, we end up with a BE playing at 44.1kHz a stream which is
  supposed to be played at 48Khz (too slow)

To improve this situation, this patch performs all the FE old paths update
before going on to update the new paths. With this, the result should
no longer depend on the order of the FE within the card rtd list.

Please note that there might be a small performance penalty since
dpcm_process_paths() is called twice per stream direction.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-pcm.c | 165 +++++++++++++++++++++++++++-------------------------
 1 file changed, 86 insertions(+), 79 deletions(-)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 19ebfc958b9d..63f96cde046a 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -2597,106 +2597,113 @@ static int dpcm_run_old_update(struct snd_soc_pcm_runtime *fe, int stream)
 	return ret;
 }
 
-/* Called by DAPM mixer/mux changes to update audio routing between PCMs and
- * any DAI links.
- */
-int soc_dpcm_runtime_update(struct snd_soc_card *card)
+static int soc_dpcm_fe_runtime_update(struct snd_soc_pcm_runtime *fe, int new)
 {
-	struct snd_soc_pcm_runtime *fe;
-	int old, new, paths;
+	struct snd_soc_dapm_widget_list *list;
+	int count, paths;
 
-	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
-	list_for_each_entry(fe, &card->rtd_list, list) {
-		struct snd_soc_dapm_widget_list *list;
+	if (!fe->dai_link->dynamic)
+		return 0;
 
-		/* make sure link is FE */
-		if (!fe->dai_link->dynamic)
-			continue;
+	/* only check active links */
+	if (!fe->cpu_dai->active)
+		return 0;
 
-		/* only check active links */
-		if (!fe->cpu_dai->active)
-			continue;
+	/* DAPM sync will call this to update DSP paths */
+	dev_dbg(fe->dev, "ASoC: DPCM %s runtime update for FE %s\n",
+		new ? "new" : "old", fe->dai_link->name);
 
-		/* DAPM sync will call this to update DSP paths */
-		dev_dbg(fe->dev, "ASoC: DPCM runtime update for FE %s\n",
-			fe->dai_link->name);
+	/* skip if FE doesn't have playback capability */
+	if (!fe->cpu_dai->driver->playback.channels_min ||
+	    !fe->codec_dai->driver->playback.channels_min)
+		goto capture;
 
-		/* skip if FE doesn't have playback capability */
-		if (!fe->cpu_dai->driver->playback.channels_min
-		    || !fe->codec_dai->driver->playback.channels_min)
-			goto capture;
-
-		/* skip if FE isn't currently playing */
-		if (!fe->cpu_dai->playback_active
-		    || !fe->codec_dai->playback_active)
-			goto capture;
-
-		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
-		if (paths < 0) {
-			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
-					fe->dai_link->name,  "playback");
-			mutex_unlock(&card->mutex);
-			return paths;
-		}
+	/* skip if FE isn't currently playing */
+	if (!fe->cpu_dai->playback_active || !fe->codec_dai->playback_active)
+		goto capture;
 
-		/* update any new playback paths */
-		new = dpcm_process_paths(fe, SNDRV_PCM_STREAM_PLAYBACK, &list, 1);
-		if (new) {
-			dpcm_run_new_update(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
-		}
+	paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_PLAYBACK, &list);
+	if (paths < 0) {
+		dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
+			 fe->dai_link->name,  "playback");
+		return paths;
+	}
 
-		/* update any old playback paths */
-		old = dpcm_process_paths(fe, SNDRV_PCM_STREAM_PLAYBACK, &list, 0);
-		if (old) {
+	/* update any playback paths */
+	count = dpcm_process_paths(fe, SNDRV_PCM_STREAM_PLAYBACK, &list, new);
+	if (count) {
+		if (new)
+			dpcm_run_new_update(fe, SNDRV_PCM_STREAM_PLAYBACK);
+		else
 			dpcm_run_old_update(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_PLAYBACK);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
-		}
 
-		dpcm_path_put(&list);
+		dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_PLAYBACK);
+		dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_PLAYBACK);
+	}
+
+	dpcm_path_put(&list);
+
 capture:
-		/* skip if FE doesn't have capture capability */
-		if (!fe->cpu_dai->driver->capture.channels_min
-		    || !fe->codec_dai->driver->capture.channels_min)
-			continue;
+	/* skip if FE doesn't have capture capability */
+	if (!fe->cpu_dai->driver->capture.channels_min ||
+	    !fe->codec_dai->driver->capture.channels_min)
+		return 0;
 
-		/* skip if FE isn't currently capturing */
-		if (!fe->cpu_dai->capture_active
-		    || !fe->codec_dai->capture_active)
-			continue;
+	/* skip if FE isn't currently capturing */
+	if (!fe->cpu_dai->capture_active || !fe->codec_dai->capture_active)
+		return 0;
 
-		paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
-		if (paths < 0) {
-			dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
-					fe->dai_link->name,  "capture");
-			mutex_unlock(&card->mutex);
-			return paths;
-		}
+	paths = dpcm_path_get(fe, SNDRV_PCM_STREAM_CAPTURE, &list);
+	if (paths < 0) {
+		dev_warn(fe->dev, "ASoC: %s no valid %s path\n",
+			 fe->dai_link->name,  "capture");
+		return paths;
+	}
 
-		/* update any new capture paths */
-		new = dpcm_process_paths(fe, SNDRV_PCM_STREAM_CAPTURE, &list, 1);
-		if (new) {
+	/* update any old capture paths */
+	count = dpcm_process_paths(fe, SNDRV_PCM_STREAM_CAPTURE, &list, new);
+	if (count) {
+		if (new)
 			dpcm_run_new_update(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_CAPTURE);
-		}
-
-		/* update any old capture paths */
-		old = dpcm_process_paths(fe, SNDRV_PCM_STREAM_CAPTURE, &list, 0);
-		if (old) {
+		else
 			dpcm_run_old_update(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_CAPTURE);
-			dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_CAPTURE);
-		}
 
-		dpcm_path_put(&list);
+		dpcm_clear_pending_state(fe, SNDRV_PCM_STREAM_CAPTURE);
+		dpcm_be_disconnect(fe, SNDRV_PCM_STREAM_CAPTURE);
 	}
 
-	mutex_unlock(&card->mutex);
+	dpcm_path_put(&list);
+
 	return 0;
 }
+
+/* Called by DAPM mixer/mux changes to update audio routing between PCMs and
+ * any DAI links.
+ */
+int soc_dpcm_runtime_update(struct snd_soc_card *card)
+{
+	struct snd_soc_pcm_runtime *fe;
+	int ret = 0;
+
+	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+	/* shutdown all old paths first */
+	list_for_each_entry(fe, &card->rtd_list, list) {
+		ret = soc_dpcm_fe_runtime_update(fe, 0);
+		if (ret)
+			goto out;
+	}
+
+	/* bring new paths up */
+	list_for_each_entry(fe, &card->rtd_list, list) {
+		ret = soc_dpcm_fe_runtime_update(fe, 1);
+		if (ret)
+			goto out;
+	}
+
+out:
+	mutex_unlock(&card->mutex);
+	return ret;
+}
 int soc_dpcm_be_digital_mute(struct snd_soc_pcm_runtime *fe, int mute)
 {
 	struct snd_soc_dpcm *dpcm;
-- 
cgit v1.2.3


From c54c1c5ee8e73b7cb752834e52e2129b1dab00bd Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 27 Jun 2018 11:56:53 +0300
Subject: ASoC: qdsp6: qdafe: fix some off by one bugs

The > should be >= or we could read one element beyond the end of the
port_maps[] array.

Fixes: 7fa2d70f9766 ("ASoC: qdsp6: q6afe: Add q6afe driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c
index 621b67b34db9..671743453fbb 100644
--- a/sound/soc/qcom/qdsp6/q6afe.c
+++ b/sound/soc/qcom/qdsp6/q6afe.c
@@ -776,7 +776,7 @@ static int q6afe_callback(struct apr_device *adev, struct apr_resp_pkt *data)
  */
 int q6afe_get_port_id(int index)
 {
-	if (index < 0 || index > AFE_PORT_MAX)
+	if (index < 0 || index >= AFE_PORT_MAX)
 		return -EINVAL;
 
 	return port_maps[index].port_id;
@@ -1013,7 +1013,7 @@ int q6afe_port_stop(struct q6afe_port *port)
 
 	port_id = port->id;
 	index = port->token;
-	if (index < 0 || index > AFE_PORT_MAX) {
+	if (index < 0 || index >= AFE_PORT_MAX) {
 		dev_err(afe->dev, "AFE port index[%d] invalid!\n", index);
 		return -EINVAL;
 	}
@@ -1354,7 +1354,7 @@ struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id)
 	unsigned long flags;
 	int cfg_type;
 
-	if (id < 0 || id > AFE_PORT_MAX) {
+	if (id < 0 || id >= AFE_PORT_MAX) {
 		dev_err(dev, "AFE port token[%d] invalid!\n", id);
 		return ERR_PTR(-EINVAL);
 	}
-- 
cgit v1.2.3


From 4f2bd18b191a10660782f2f1ccc989b000b2be63 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 27 Jun 2018 11:48:18 +0200
Subject: ASoC: dpcm: extend channel merging to the backend cpu dai

Extend dpcm_merge_chan to also check backend cpu dai channels
capabilities. Apply the same policy as soc_pcm_init_runtime_hw() for
multicodec links and only check cpu dai in this case.

Cc: Jiada Wang <jiada_wang@mentor.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-pcm.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 63f96cde046a..6ee4131941df 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1736,12 +1736,26 @@ static void dpcm_runtime_base_chan(struct snd_pcm_substream *substream,
 
 	list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be) {
 		struct snd_soc_pcm_runtime *be = dpcm->be;
+		struct snd_soc_dai_driver *cpu_dai_drv =  be->cpu_dai->driver;
 		struct snd_soc_dai_driver *codec_dai_drv;
 		struct snd_soc_pcm_stream *codec_stream;
-		int i;
+		struct snd_soc_pcm_stream *cpu_stream;
+
+		if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+			cpu_stream = &cpu_dai_drv->playback;
+		else
+			cpu_stream = &cpu_dai_drv->capture;
+
+		*channels_min = max(*channels_min, cpu_stream->channels_min);
+		*channels_max = min(*channels_max, cpu_stream->channels_max);
+
+		/*
+		 * chan min/max cannot be enforced if there are multiple CODEC
+		 * DAIs connected to a single CPU DAI, use CPU DAI's directly
+		 */
+		if (be->num_codecs == 1) {
+			codec_dai_drv = be->codec_dais[0]->driver;
 
-		for (i = 0; i < be->num_codecs; i++) {
-			codec_dai_drv = be->codec_dais[i]->driver;
 			if (stream == SNDRV_PCM_STREAM_PLAYBACK)
 				codec_stream = &codec_dai_drv->playback;
 			else
-- 
cgit v1.2.3


From 4febced15ac8ddb9cf3e603edb111842e4863d9a Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 27 Jun 2018 17:36:38 +0200
Subject: ASoC: dpcm: don't merge format from invalid codec dai

When merging codec formats, dpcm_runtime_base_format() should skip
the codecs which are not supporting the current stream direction.

At the moment, if a BE link has more than one codec, and only one
of these codecs has no capture DAI, it becomes impossible to start
a capture stream because the merged format would be 0.

Skipping invalid codec DAI solves the problem.

Fixes: b073ed4e2126 ("ASoC: soc-pcm: DPCM cares BE format")
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
---
 sound/soc/soc-pcm.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 5e7ae47a9658..5feae9666822 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1694,6 +1694,14 @@ static u64 dpcm_runtime_base_format(struct snd_pcm_substream *substream)
 		int i;
 
 		for (i = 0; i < be->num_codecs; i++) {
+			/*
+			 * Skip CODECs which don't support the current stream
+			 * type. See soc_pcm_init_runtime_hw() for more details
+			 */
+			if (!snd_soc_dai_stream_valid(be->codec_dais[i],
+						      stream))
+				continue;
+
 			codec_dai_drv = be->codec_dais[i]->driver;
 			if (stream == SNDRV_PCM_STREAM_PLAYBACK)
 				codec_stream = &codec_dai_drv->playback;
-- 
cgit v1.2.3


From 64bac6916ef7d9cc57367893aea1544fcad91b9b Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Fri, 25 May 2018 17:54:00 -0400
Subject: media: tc358743: release device_node in tc358743_probe_of()

of_graph_get_next_endpoint() returns device_node with refcnt increased,
but these is no of_node_put() for it.

The patch adds one on error and normal paths.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Reviewed-by: Nicholas Mc Guire <der.herr@hofr.at>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/tc358743.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/media/i2c/tc358743.c b/drivers/media/i2c/tc358743.c
index 393bbbbbaad7..44c41933415a 100644
--- a/drivers/media/i2c/tc358743.c
+++ b/drivers/media/i2c/tc358743.c
@@ -1918,7 +1918,8 @@ static int tc358743_probe_of(struct tc358743_state *state)
 	endpoint = v4l2_fwnode_endpoint_alloc_parse(of_fwnode_handle(ep));
 	if (IS_ERR(endpoint)) {
 		dev_err(dev, "failed to parse endpoint\n");
-		return PTR_ERR(endpoint);
+		ret = PTR_ERR(endpoint);
+		goto put_node;
 	}
 
 	if (endpoint->bus_type != V4L2_MBUS_CSI2 ||
@@ -2013,6 +2014,8 @@ disable_clk:
 	clk_disable_unprepare(refclk);
 free_endpoint:
 	v4l2_fwnode_endpoint_free(endpoint);
+put_node:
+	of_node_put(ep);
 	return ret;
 }
 #else
-- 
cgit v1.2.3


From 42f073d7656bcfe6915b7023cb01427caa29a9be Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 26 May 2018 09:45:07 -0400
Subject: media: mtk-vpu: fix spelling mistake: "Prosessor" -> "Processor"

Trivial fix to spelling mistake in module description text.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/mtk-vpu/mtk_vpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/mtk-vpu/mtk_vpu.c b/drivers/media/platform/mtk-vpu/mtk_vpu.c
index 1ff6a93262b7..f8d35e3ac1dc 100644
--- a/drivers/media/platform/mtk-vpu/mtk_vpu.c
+++ b/drivers/media/platform/mtk-vpu/mtk_vpu.c
@@ -960,4 +960,4 @@ static struct platform_driver mtk_vpu_driver = {
 module_platform_driver(mtk_vpu_driver);
 
 MODULE_LICENSE("GPL v2");
-MODULE_DESCRIPTION("Mediatek Video Prosessor Unit driver");
+MODULE_DESCRIPTION("Mediatek Video Processor Unit driver");
-- 
cgit v1.2.3


From 6ada1328642b8ffc25917c89569d3e16354b43d2 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Tue, 22 May 2018 23:43:57 +0530
Subject: gpu: drm: omapdrm: Adding new typedef vm_fault_t

Use new return type vm_fault_t for fault handler. For
now, this is just documenting that the function returns
a VM_FAULT value rather than an errno. Once all instances
are converted, vm_fault_t will become a distinct type.

Ref-> commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Previously vm_insert_mixed() returns err which driver
mapped into VM_FAULT_* type. Also return value of
vm_insert_mixed() not handled correctly and 0 was
returned inside fault_2d() as default. The new function
vmf_insert_mixed() will replace this inefficiency by
returning correct VM_FAULT_* type.

vmf_error() is the newly introduce inline function
in 4.17-rc6.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_gem.c | 51 +++++++++++++++++---------------------
 drivers/gpu/drm/omapdrm/omap_gem.h |  3 ++-
 2 files changed, 25 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 17a53d207978..6030de7ec2ba 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -371,7 +371,7 @@ size_t omap_gem_mmap_size(struct drm_gem_object *obj)
  */
 
 /* Normal handling for the case of faulting in non-tiled buffers */
-static int fault_1d(struct drm_gem_object *obj,
+static vm_fault_t fault_1d(struct drm_gem_object *obj,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
@@ -392,11 +392,12 @@ static int fault_1d(struct drm_gem_object *obj,
 	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 			pfn, pfn << PAGE_SHIFT);
 
-	return vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
+	return vmf_insert_mixed(vma, vmf->address,
+			__pfn_to_pfn_t(pfn, PFN_DEV));
 }
 
 /* Special handling for the case of faulting in 2d tiled buffers */
-static int fault_2d(struct drm_gem_object *obj,
+static vm_fault_t fault_2d(struct drm_gem_object *obj,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
@@ -407,7 +408,8 @@ static int fault_2d(struct drm_gem_object *obj,
 	unsigned long pfn;
 	pgoff_t pgoff, base_pgoff;
 	unsigned long vaddr;
-	int i, ret, slots;
+	int i, err, slots;
+	vm_fault_t ret = VM_FAULT_NOPAGE;
 
 	/*
 	 * Note the height of the slot is also equal to the number of pages
@@ -473,9 +475,10 @@ static int fault_2d(struct drm_gem_object *obj,
 	memset(pages + slots, 0,
 			sizeof(struct page *) * (n - slots));
 
-	ret = tiler_pin(entry->block, pages, ARRAY_SIZE(pages), 0, true);
-	if (ret) {
-		dev_err(obj->dev->dev, "failed to pin: %d\n", ret);
+	err = tiler_pin(entry->block, pages, ARRAY_SIZE(pages), 0, true);
+	if (err) {
+		ret = vmf_error(err);
+		dev_err(obj->dev->dev, "failed to pin: %d\n", err);
 		return ret;
 	}
 
@@ -485,7 +488,10 @@ static int fault_2d(struct drm_gem_object *obj,
 			pfn, pfn << PAGE_SHIFT);
 
 	for (i = n; i > 0; i--) {
-		vm_insert_mixed(vma, vaddr, __pfn_to_pfn_t(pfn, PFN_DEV));
+		ret = vmf_insert_mixed(vma,
+			vaddr, __pfn_to_pfn_t(pfn, PFN_DEV));
+		if (ret & VM_FAULT_ERROR)
+			break;
 		pfn += priv->usergart[fmt].stride_pfn;
 		vaddr += PAGE_SIZE * m;
 	}
@@ -494,7 +500,7 @@ static int fault_2d(struct drm_gem_object *obj,
 	priv->usergart[fmt].last = (priv->usergart[fmt].last + 1)
 				 % NUM_USERGART_ENTRIES;
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -509,14 +515,15 @@ static int fault_2d(struct drm_gem_object *obj,
  * vma->vm_private_data points to the GEM object that is backing this
  * mapping.
  */
-int omap_gem_fault(struct vm_fault *vmf)
+vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	struct drm_device *dev = obj->dev;
 	struct page **pages;
-	int ret;
+	int err;
+	vm_fault_t ret;
 
 	/* Make sure we don't parallel update on a fault, nor move or remove
 	 * something from beneath our feet
@@ -524,9 +531,11 @@ int omap_gem_fault(struct vm_fault *vmf)
 	mutex_lock(&dev->struct_mutex);
 
 	/* if a shmem backed object, make sure we have pages attached now */
-	ret = get_pages(obj, &pages);
-	if (ret)
+	err = get_pages(obj, &pages);
+	if (err) {
+		ret = vmf_error(err);
 		goto fail;
+	}
 
 	/* where should we do corresponding put_pages().. we are mapping
 	 * the original page, rather than thru a GART, so we can't rely
@@ -542,21 +551,7 @@ int omap_gem_fault(struct vm_fault *vmf)
 
 fail:
 	mutex_unlock(&dev->struct_mutex);
-	switch (ret) {
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return ret;
 }
 
 /** We override mainly to fix up some of the vm mapping flags.. */
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.h b/drivers/gpu/drm/omapdrm/omap_gem.h
index a78bde05193a..c1c45fbde155 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.h
+++ b/drivers/gpu/drm/omapdrm/omap_gem.h
@@ -21,6 +21,7 @@
 #define __OMAPDRM_GEM_H__
 
 #include <linux/types.h>
+#include <linux/mm_types.h>
 
 enum dma_data_direction;
 
@@ -80,7 +81,7 @@ struct dma_buf *omap_gem_prime_export(struct drm_device *dev,
 struct drm_gem_object *omap_gem_prime_import(struct drm_device *dev,
 		struct dma_buf *buffer);
 
-int omap_gem_fault(struct vm_fault *vmf);
+vm_fault_t omap_gem_fault(struct vm_fault *vmf);
 int omap_gem_roll(struct drm_gem_object *obj, u32 roll);
 void omap_gem_cpu_sync_page(struct drm_gem_object *obj, int pgoff);
 void omap_gem_dma_sync_buffer(struct drm_gem_object *obj,
-- 
cgit v1.2.3


From c618a3a93b5a118fcf4afe5fe85e83c190f4b127 Mon Sep 17 00:00:00 2001
From: Venkateswara Rao Mandela <venkat.mandela@ti.com>
Date: Wed, 24 Jan 2018 16:15:09 +0530
Subject: drm/omap: Implement workaround for DRA7 errata ID:i932

Description of DRA7 Errata i932:

In rare circumstances DPLL_VIDEO1 and DPLL_VIDEO2 PLL's may not lock on
the first attempt during DSS initialization. When this occurs, a
subsequent attempt to relock the PLL will result in PLL successfully
locking.

This patch does the following as per the errata recommendation:

- retries locking the PLL upto 20 times.

- The time to wait for a PLL lock set to 1000 REFCLK cycles. We use
usleep_range to wait for 1000 REFCLK cycles in the us range. This tight
constraint is imposed as a lock later than 1000 REFCLK cycles may have
high jitter.

- Criteria for PLL lock is extended from check on just the PLL_LOCK bit
to check on 6 PLL_STATUS bits.

Silicon Versions Impacted:
DRA71, DRA72, DRA74, DRA76 - All silicon revisions
AM57x - All silicon revisions

OMAP4/5 are not impacted by this errata

Signed-off-by: Venkateswara Rao Mandela <venkat.mandela@ti.com>
[tomi.valkeinen@ti.com: ported to v4.14]
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/dss/dss.h       |  3 ++
 drivers/gpu/drm/omapdrm/dss/pll.c       | 73 ++++++++++++++++++++++++++++-----
 drivers/gpu/drm/omapdrm/dss/video-pll.c |  1 +
 3 files changed, 67 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/dss/dss.h b/drivers/gpu/drm/omapdrm/dss/dss.h
index 847c78ade024..9f9a700bb6d5 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.h
+++ b/drivers/gpu/drm/omapdrm/dss/dss.h
@@ -180,6 +180,9 @@ struct dss_pll_hw {
 
 	/* DRA7 errata i886: use high N & M to avoid jitter */
 	bool errata_i886;
+
+	/* DRA7 errata i932: retry pll lock on failure */
+	bool errata_i932;
 };
 
 struct dss_pll {
diff --git a/drivers/gpu/drm/omapdrm/dss/pll.c b/drivers/gpu/drm/omapdrm/dss/pll.c
index 078b0e8216c3..ff362b38bf0d 100644
--- a/drivers/gpu/drm/omapdrm/dss/pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/pll.c
@@ -16,6 +16,7 @@
 
 #define DSS_SUBSYS_NAME "PLL"
 
+#include <linux/delay.h>
 #include <linux/clk.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
@@ -381,6 +382,22 @@ static int dss_wait_hsdiv_ack(struct dss_pll *pll, u32 hsdiv_ack_mask)
 	return -ETIMEDOUT;
 }
 
+static bool pll_is_locked(u32 stat)
+{
+	/*
+	 * Required value for each bitfield listed below
+	 *
+	 * PLL_STATUS[6] = 0  PLL_BYPASS
+	 * PLL_STATUS[5] = 0  PLL_HIGHJITTER
+	 *
+	 * PLL_STATUS[3] = 0  PLL_LOSSREF
+	 * PLL_STATUS[2] = 0  PLL_RECAL
+	 * PLL_STATUS[1] = 1  PLL_LOCK
+	 * PLL_STATUS[0] = 1  PLL_CTRL_RESET_DONE
+	 */
+	return ((stat & 0x6f) == 0x3);
+}
+
 int dss_pll_write_config_type_a(struct dss_pll *pll,
 		const struct dss_pll_clock_info *cinfo)
 {
@@ -436,18 +453,54 @@ int dss_pll_write_config_type_a(struct dss_pll *pll,
 	l = FLD_MOD(l, 0, 25, 25);		/* M7_CLOCK_EN */
 	writel_relaxed(l, base + PLL_CONFIGURATION2);
 
-	writel_relaxed(1, base + PLL_GO);	/* PLL_GO */
+	if (hw->errata_i932) {
+		int cnt = 0;
+		u32 sleep_time;
+		const u32 max_lock_retries = 20;
 
-	if (wait_for_bit_change(base + PLL_GO, 0, 0) != 0) {
-		DSSERR("DSS DPLL GO bit not going down.\n");
-		r = -EIO;
-		goto err;
-	}
+		/*
+		 * Calculate wait time for PLL LOCK
+		 * 1000 REFCLK cycles in us.
+		 */
+		sleep_time = DIV_ROUND_UP(1000*1000*1000, cinfo->fint);
 
-	if (wait_for_bit_change(base + PLL_STATUS, 1, 1) != 1) {
-		DSSERR("cannot lock DSS DPLL\n");
-		r = -EIO;
-		goto err;
+		for (cnt = 0; cnt < max_lock_retries; cnt++) {
+			writel_relaxed(1, base + PLL_GO);	/* PLL_GO */
+
+			/**
+			 * read the register back to ensure the write is
+			 * flushed
+			 */
+			readl_relaxed(base + PLL_GO);
+
+			usleep_range(sleep_time, sleep_time + 5);
+			l = readl_relaxed(base + PLL_STATUS);
+
+			if (pll_is_locked(l) &&
+			    !(readl_relaxed(base + PLL_GO) & 0x1))
+				break;
+
+		}
+
+		if (cnt == max_lock_retries) {
+			DSSERR("cannot lock PLL\n");
+			r = -EIO;
+			goto err;
+		}
+	} else {
+		writel_relaxed(1, base + PLL_GO);	/* PLL_GO */
+
+		if (wait_for_bit_change(base + PLL_GO, 0, 0) != 0) {
+			DSSERR("DSS DPLL GO bit not going down.\n");
+			r = -EIO;
+			goto err;
+		}
+
+		if (wait_for_bit_change(base + PLL_STATUS, 1, 1) != 1) {
+			DSSERR("cannot lock DSS DPLL\n");
+			r = -EIO;
+			goto err;
+		}
 	}
 
 	l = readl_relaxed(base + PLL_CONFIGURATION2);
diff --git a/drivers/gpu/drm/omapdrm/dss/video-pll.c b/drivers/gpu/drm/omapdrm/dss/video-pll.c
index 585ed94ccf17..cb46311f92c9 100644
--- a/drivers/gpu/drm/omapdrm/dss/video-pll.c
+++ b/drivers/gpu/drm/omapdrm/dss/video-pll.c
@@ -134,6 +134,7 @@ static const struct dss_pll_hw dss_dra7_video_pll_hw = {
 	.has_refsel = true,
 
 	.errata_i886 = true,
+	.errata_i932 = true,
 };
 
 struct dss_pll *dss_video_pll_init(struct dss_device *dss,
-- 
cgit v1.2.3


From 6505d75cd23291565ca668dd1e66f4e38b5c8f38 Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Thu, 24 May 2018 14:46:19 +0300
Subject: drm/omap: fix email address

Change tomi.valkeinen@nokia.com to tomi.valkeinen@ti.com.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c | 2 +-
 drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c | 2 +-
 drivers/gpu/drm/omapdrm/dss/core.c                      | 4 ++--
 drivers/gpu/drm/omapdrm/dss/dispc.c                     | 2 +-
 drivers/gpu/drm/omapdrm/dss/display.c                   | 2 +-
 drivers/gpu/drm/omapdrm/dss/dpi.c                       | 2 +-
 drivers/gpu/drm/omapdrm/dss/dsi.c                       | 2 +-
 drivers/gpu/drm/omapdrm/dss/dss.c                       | 2 +-
 drivers/gpu/drm/omapdrm/dss/dss.h                       | 2 +-
 drivers/gpu/drm/omapdrm/dss/sdi.c                       | 2 +-
 drivers/gpu/drm/omapdrm/dss/venc.c                      | 2 +-
 11 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
index 92fe125ce22e..f34c06bb5bd7 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-sony-acx565akm.c
@@ -4,7 +4,7 @@
  * Copyright (C) 2010 Nokia Corporation
  *
  * Original Driver Author: Imre Deak <imre.deak@nokia.com>
- * Based on panel-generic.c by Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Based on panel-generic.c by Tomi Valkeinen <tomi.valkeinen@ti.com>
  * Adapted to new DSS2 framework: Roger Quadros <roger.quadros@nokia.com>
  *
  * This program is free software; you can redistribute it and/or modify it
diff --git a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
index b5d8a00df811..a1f1dc18407a 100644
--- a/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
+++ b/drivers/gpu/drm/omapdrm/displays/panel-tpo-td028ttec1.c
@@ -2,7 +2,7 @@
  * Toppoly TD028TTEC1 panel support
  *
  * Copyright (C) 2008 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Neo 1973 code (jbt6k74.c):
  * Copyright (C) 2006-2007 by OpenMoko, Inc.
diff --git a/drivers/gpu/drm/omapdrm/dss/core.c b/drivers/gpu/drm/omapdrm/dss/core.c
index acef7ece5783..07d00a186f15 100644
--- a/drivers/gpu/drm/omapdrm/dss/core.c
+++ b/drivers/gpu/drm/omapdrm/dss/core.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
@@ -82,7 +82,7 @@ static void __exit omap_dss_exit(void)
 module_init(omap_dss_init);
 module_exit(omap_dss_exit);
 
-MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@nokia.com>");
+MODULE_AUTHOR("Tomi Valkeinen <tomi.valkeinen@ti.com>");
 MODULE_DESCRIPTION("OMAP2/3 Display Subsystem");
 MODULE_LICENSE("GPL v2");
 
diff --git a/drivers/gpu/drm/omapdrm/dss/dispc.c b/drivers/gpu/drm/omapdrm/dss/dispc.c
index 7f3ac6b13b56..84f274c4a4cb 100644
--- a/drivers/gpu/drm/omapdrm/dss/dispc.c
+++ b/drivers/gpu/drm/omapdrm/dss/dispc.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/display.c b/drivers/gpu/drm/omapdrm/dss/display.c
index 424143128cd4..9e7fcbd57e52 100644
--- a/drivers/gpu/drm/omapdrm/dss/display.c
+++ b/drivers/gpu/drm/omapdrm/dss/display.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/dpi.c b/drivers/gpu/drm/omapdrm/dss/dpi.c
index 3d662e6805eb..9fcc50217133 100644
--- a/drivers/gpu/drm/omapdrm/dss/dpi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dpi.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/dsi.c b/drivers/gpu/drm/omapdrm/dss/dsi.c
index d4a680629825..74467b308721 100644
--- a/drivers/gpu/drm/omapdrm/dss/dsi.c
+++ b/drivers/gpu/drm/omapdrm/dss/dsi.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published by
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.c b/drivers/gpu/drm/omapdrm/dss/dss.c
index 0b908e9de792..cb80ddaa19d2 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.c
+++ b/drivers/gpu/drm/omapdrm/dss/dss.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/dss.h b/drivers/gpu/drm/omapdrm/dss/dss.h
index 9f9a700bb6d5..38302631b64b 100644
--- a/drivers/gpu/drm/omapdrm/dss/dss.h
+++ b/drivers/gpu/drm/omapdrm/dss/dss.h
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * Some code and ideas taken from drivers/video/omap/ driver
  * by Imre Deak.
diff --git a/drivers/gpu/drm/omapdrm/dss/sdi.c b/drivers/gpu/drm/omapdrm/dss/sdi.c
index 1e2c931f6acf..69c3b7a3d5c7 100644
--- a/drivers/gpu/drm/omapdrm/dss/sdi.c
+++ b/drivers/gpu/drm/omapdrm/dss/sdi.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published by
diff --git a/drivers/gpu/drm/omapdrm/dss/venc.c b/drivers/gpu/drm/omapdrm/dss/venc.c
index 24d1ced210bd..ac01907dcc34 100644
--- a/drivers/gpu/drm/omapdrm/dss/venc.c
+++ b/drivers/gpu/drm/omapdrm/dss/venc.c
@@ -1,6 +1,6 @@
 /*
  * Copyright (C) 2009 Nokia Corporation
- * Author: Tomi Valkeinen <tomi.valkeinen@nokia.com>
+ * Author: Tomi Valkeinen <tomi.valkeinen@ti.com>
  *
  * VENC settings from TI's DSS driver
  *
-- 
cgit v1.2.3


From 620063e10ed48c63027c4f59dab97d2ead67f9f1 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Fri, 25 May 2018 19:39:20 +0300
Subject: drm/omap: gem: Rename GEM function with omap_gem_* prefix

get_pages() as a local function name is too generic and easily confused
for a generic MM kernel function. Rename it to __omap_gem_get_pages().

Rename the is_contiguous(), is_cache_coherent(), evict(), evict_entry(),
fault_1d() and fault_2d() functions for the same reason.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_gem.c | 48 +++++++++++++++++++++-----------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 6030de7ec2ba..7a4ee4edab5b 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -156,7 +156,7 @@ static u64 mmap_offset(struct drm_gem_object *obj)
 	return drm_vma_node_offset_addr(&obj->vma_node);
 }
 
-static bool is_contiguous(struct omap_gem_object *omap_obj)
+static bool omap_gem_is_contiguous(struct omap_gem_object *omap_obj)
 {
 	if (omap_obj->flags & OMAP_BO_MEM_DMA_API)
 		return true;
@@ -171,7 +171,7 @@ static bool is_contiguous(struct omap_gem_object *omap_obj)
  * Eviction
  */
 
-static void evict_entry(struct drm_gem_object *obj,
+static void omap_gem_evict_entry(struct drm_gem_object *obj,
 		enum tiler_fmt fmt, struct omap_drm_usergart_entry *entry)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
@@ -199,7 +199,7 @@ static void evict_entry(struct drm_gem_object *obj,
 }
 
 /* Evict a buffer from usergart, if it is mapped there */
-static void evict(struct drm_gem_object *obj)
+static void omap_gem_evict(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	struct omap_drm_private *priv = obj->dev->dev_private;
@@ -213,7 +213,7 @@ static void evict(struct drm_gem_object *obj)
 				&priv->usergart[fmt].entry[i];
 
 			if (entry->obj == obj)
-				evict_entry(obj, fmt, entry);
+				omap_gem_evict_entry(obj, fmt, entry);
 		}
 	}
 }
@@ -291,7 +291,8 @@ free_pages:
 /* acquire pages when needed (for example, for DMA where physically
  * contiguous buffer is not required
  */
-static int get_pages(struct drm_gem_object *obj, struct page ***pages)
+static int __omap_gem_get_pages(struct drm_gem_object *obj,
+				struct page ***pages)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret = 0;
@@ -371,7 +372,7 @@ size_t omap_gem_mmap_size(struct drm_gem_object *obj)
  */
 
 /* Normal handling for the case of faulting in non-tiled buffers */
-static vm_fault_t fault_1d(struct drm_gem_object *obj,
+static vm_fault_t omap_gem_fault_1d(struct drm_gem_object *obj,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
@@ -385,7 +386,7 @@ static vm_fault_t fault_1d(struct drm_gem_object *obj,
 		omap_gem_cpu_sync_page(obj, pgoff);
 		pfn = page_to_pfn(omap_obj->pages[pgoff]);
 	} else {
-		BUG_ON(!is_contiguous(omap_obj));
+		BUG_ON(!omap_gem_is_contiguous(omap_obj));
 		pfn = (omap_obj->dma_addr >> PAGE_SHIFT) + pgoff;
 	}
 
@@ -397,7 +398,7 @@ static vm_fault_t fault_1d(struct drm_gem_object *obj,
 }
 
 /* Special handling for the case of faulting in 2d tiled buffers */
-static vm_fault_t fault_2d(struct drm_gem_object *obj,
+static vm_fault_t omap_gem_fault_2d(struct drm_gem_object *obj,
 		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
@@ -445,7 +446,7 @@ static vm_fault_t fault_2d(struct drm_gem_object *obj,
 
 	/* evict previous buffer using this usergart entry, if any: */
 	if (entry->obj)
-		evict_entry(entry->obj, fmt, entry);
+		omap_gem_evict_entry(entry->obj, fmt, entry);
 
 	entry->obj = obj;
 	entry->obj_pgoff = base_pgoff;
@@ -531,7 +532,7 @@ vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 	mutex_lock(&dev->struct_mutex);
 
 	/* if a shmem backed object, make sure we have pages attached now */
-	err = get_pages(obj, &pages);
+	err = __omap_gem_get_pages(obj, &pages);
 	if (err) {
 		ret = vmf_error(err);
 		goto fail;
@@ -544,9 +545,9 @@ vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 	 */
 
 	if (omap_obj->flags & OMAP_BO_TILED)
-		ret = fault_2d(obj, vma, vmf);
+		ret = omap_gem_fault_2d(obj, vma, vmf);
 	else
-		ret = fault_1d(obj, vma, vmf);
+		ret = omap_gem_fault_1d(obj, vma, vmf);
 
 
 fail:
@@ -689,7 +690,8 @@ int omap_gem_roll(struct drm_gem_object *obj, u32 roll)
 	/* if we aren't mapped yet, we don't need to do anything */
 	if (omap_obj->block) {
 		struct page **pages;
-		ret = get_pages(obj, &pages);
+
+		ret = __omap_gem_get_pages(obj, &pages);
 		if (ret)
 			goto fail;
 		ret = tiler_pin(omap_obj->block, pages, npages, roll, true);
@@ -717,7 +719,7 @@ fail:
  * the omap_obj->dma_addrs[i] is set to the DMA address, and the page is
  * unmapped from the CPU.
  */
-static inline bool is_cached_coherent(struct drm_gem_object *obj)
+static inline bool omap_gem_is_cached_coherent(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 
@@ -733,7 +735,7 @@ void omap_gem_cpu_sync_page(struct drm_gem_object *obj, int pgoff)
 	struct drm_device *dev = obj->dev;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 
-	if (is_cached_coherent(obj))
+	if (omap_gem_is_cached_coherent(obj))
 		return;
 
 	if (omap_obj->dma_addrs[pgoff]) {
@@ -753,7 +755,7 @@ void omap_gem_dma_sync_buffer(struct drm_gem_object *obj,
 	struct page **pages = omap_obj->pages;
 	bool dirty = false;
 
-	if (is_cached_coherent(obj))
+	if (omap_gem_is_cached_coherent(obj))
 		return;
 
 	for (i = 0; i < npages; i++) {
@@ -801,7 +803,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 
 	mutex_lock(&obj->dev->struct_mutex);
 
-	if (!is_contiguous(omap_obj) && priv->has_dmm) {
+	if (!omap_gem_is_contiguous(omap_obj) && priv->has_dmm) {
 		if (omap_obj->dma_addr_cnt == 0) {
 			struct page **pages;
 			u32 npages = obj->size >> PAGE_SHIFT;
@@ -810,7 +812,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 
 			BUG_ON(omap_obj->block);
 
-			ret = get_pages(obj, &pages);
+			ret = __omap_gem_get_pages(obj, &pages);
 			if (ret)
 				goto fail;
 
@@ -848,7 +850,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 		omap_obj->dma_addr_cnt++;
 
 		*dma_addr = omap_obj->dma_addr;
-	} else if (is_contiguous(omap_obj)) {
+	} else if (omap_gem_is_contiguous(omap_obj)) {
 		*dma_addr = omap_obj->dma_addr;
 	} else {
 		ret = -EINVAL;
@@ -948,7 +950,7 @@ int omap_gem_get_pages(struct drm_gem_object *obj, struct page ***pages,
 		return 0;
 	}
 	mutex_lock(&obj->dev->struct_mutex);
-	ret = get_pages(obj, pages);
+	ret = __omap_gem_get_pages(obj, pages);
 	mutex_unlock(&obj->dev->struct_mutex);
 	return ret;
 }
@@ -974,7 +976,9 @@ void *omap_gem_vaddr(struct drm_gem_object *obj)
 	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
 	if (!omap_obj->vaddr) {
 		struct page **pages;
-		int ret = get_pages(obj, &pages);
+		int ret;
+
+		ret = __omap_gem_get_pages(obj, &pages);
 		if (ret)
 			return ERR_PTR(ret);
 		omap_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
@@ -1076,7 +1080,7 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 	struct omap_drm_private *priv = dev->dev_private;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 
-	evict(obj);
+	omap_gem_evict(obj);
 
 	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
 
-- 
cgit v1.2.3


From 2491244d7709d4e35f61d75ed3f6b4ea31b0a6f3 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Fri, 25 May 2018 19:39:21 +0300
Subject: drm/omap: gem: Merge __omap_gem_get_pages() and
 omap_gem_attach_pages()

The __omap_gem_get_pages() function is a wrapper around
omap_gem_attach_pages() that returns the omap_obj->pages pointer through
a function argument. Some callers don't need the pages pointer, and all
of them can access omap_obj->pages directly. To simplify the code merge
the __omap_gem_get_pages() wrapper with omap_gem_attach_pages() and
update the callers accordingly.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_gem.c | 59 +++++++++++++-------------------------
 1 file changed, 20 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 7a4ee4edab5b..a3efac4abd4b 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -222,7 +222,7 @@ static void omap_gem_evict(struct drm_gem_object *obj)
  * Page Management
  */
 
-/** ensure backing pages are allocated */
+/* Ensure backing pages are allocated. */
 static int omap_gem_attach_pages(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
@@ -232,7 +232,12 @@ static int omap_gem_attach_pages(struct drm_gem_object *obj)
 	int i, ret;
 	dma_addr_t *addrs;
 
-	WARN_ON(omap_obj->pages);
+	/*
+	 * If not using shmem (in which case backing pages don't need to be
+	 * allocated) or if pages are already allocated we're done.
+	 */
+	if (!(omap_obj->flags & OMAP_BO_MEM_SHMEM) || omap_obj->pages)
+		return 0;
 
 	pages = drm_gem_get_pages(obj);
 	if (IS_ERR(pages)) {
@@ -288,29 +293,6 @@ free_pages:
 	return ret;
 }
 
-/* acquire pages when needed (for example, for DMA where physically
- * contiguous buffer is not required
- */
-static int __omap_gem_get_pages(struct drm_gem_object *obj,
-				struct page ***pages)
-{
-	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	int ret = 0;
-
-	if ((omap_obj->flags & OMAP_BO_MEM_SHMEM) && !omap_obj->pages) {
-		ret = omap_gem_attach_pages(obj);
-		if (ret) {
-			dev_err(obj->dev->dev, "could not attach pages\n");
-			return ret;
-		}
-	}
-
-	/* TODO: even phys-contig.. we should have a list of pages? */
-	*pages = omap_obj->pages;
-
-	return 0;
-}
-
 /** release backing pages */
 static void omap_gem_detach_pages(struct drm_gem_object *obj)
 {
@@ -522,7 +504,6 @@ vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	struct drm_device *dev = obj->dev;
-	struct page **pages;
 	int err;
 	vm_fault_t ret;
 
@@ -532,7 +513,7 @@ vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 	mutex_lock(&dev->struct_mutex);
 
 	/* if a shmem backed object, make sure we have pages attached now */
-	err = __omap_gem_get_pages(obj, &pages);
+	err = omap_gem_attach_pages(obj);
 	if (err) {
 		ret = vmf_error(err);
 		goto fail;
@@ -689,12 +670,12 @@ int omap_gem_roll(struct drm_gem_object *obj, u32 roll)
 
 	/* if we aren't mapped yet, we don't need to do anything */
 	if (omap_obj->block) {
-		struct page **pages;
-
-		ret = __omap_gem_get_pages(obj, &pages);
+		ret = omap_gem_attach_pages(obj);
 		if (ret)
 			goto fail;
-		ret = tiler_pin(omap_obj->block, pages, npages, roll, true);
+
+		ret = tiler_pin(omap_obj->block, omap_obj->pages, npages,
+				roll, true);
 		if (ret)
 			dev_err(obj->dev->dev, "could not repin: %d\n", ret);
 	}
@@ -805,14 +786,13 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 
 	if (!omap_gem_is_contiguous(omap_obj) && priv->has_dmm) {
 		if (omap_obj->dma_addr_cnt == 0) {
-			struct page **pages;
 			u32 npages = obj->size >> PAGE_SHIFT;
 			enum tiler_fmt fmt = gem2fmt(omap_obj->flags);
 			struct tiler_block *block;
 
 			BUG_ON(omap_obj->block);
 
-			ret = __omap_gem_get_pages(obj, &pages);
+			ret = omap_gem_attach_pages(obj);
 			if (ret)
 				goto fail;
 
@@ -832,7 +812,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 			}
 
 			/* TODO: enable async refill.. */
-			ret = tiler_pin(block, pages, npages,
+			ret = tiler_pin(block, omap_obj->pages, npages,
 					omap_obj->roll, true);
 			if (ret) {
 				tiler_release(block);
@@ -941,16 +921,18 @@ int omap_gem_tiled_stride(struct drm_gem_object *obj, u32 orient)
 int omap_gem_get_pages(struct drm_gem_object *obj, struct page ***pages,
 		bool remap)
 {
+	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret;
+
 	if (!remap) {
-		struct omap_gem_object *omap_obj = to_omap_bo(obj);
 		if (!omap_obj->pages)
 			return -ENOMEM;
 		*pages = omap_obj->pages;
 		return 0;
 	}
 	mutex_lock(&obj->dev->struct_mutex);
-	ret = __omap_gem_get_pages(obj, pages);
+	ret = omap_gem_attach_pages(obj);
+	*pages = omap_obj->pages;
 	mutex_unlock(&obj->dev->struct_mutex);
 	return ret;
 }
@@ -975,13 +957,12 @@ void *omap_gem_vaddr(struct drm_gem_object *obj)
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
 	if (!omap_obj->vaddr) {
-		struct page **pages;
 		int ret;
 
-		ret = __omap_gem_get_pages(obj, &pages);
+		ret = omap_gem_attach_pages(obj);
 		if (ret)
 			return ERR_PTR(ret);
-		omap_obj->vaddr = vmap(pages, obj->size >> PAGE_SHIFT,
+		omap_obj->vaddr = vmap(omap_obj->pages, obj->size >> PAGE_SHIFT,
 				VM_MAP, pgprot_writecombine(PAGE_KERNEL));
 	}
 	return omap_obj->vaddr;
-- 
cgit v1.2.3


From dc8c9aeee5098688c1085691213fb9a703bf20ad Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Fri, 25 May 2018 19:39:22 +0300
Subject: drm/omap: gem: Don't take struct_mutex to get GEM object mmap offset

GEM objects mmap offsets are created by calling
drm_gem_create_mmap_offset_size() that doesn't need struct_mutex
protection as it includes its own locking, based on a size that is
static across the object's life time. Remove the unneeded struct_mutex
locking.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_gem.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index a3efac4abd4b..623856d9b85a 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -137,14 +137,12 @@ struct omap_drm_usergart {
  */
 
 /** get mmap offset */
-static u64 mmap_offset(struct drm_gem_object *obj)
+u64 omap_gem_mmap_offset(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
 	int ret;
 	size_t size;
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
 	/* Make it mmapable */
 	size = omap_gem_mmap_size(obj);
 	ret = drm_gem_create_mmap_offset_size(obj, size);
@@ -178,7 +176,7 @@ static void omap_gem_evict_entry(struct drm_gem_object *obj,
 	struct omap_drm_private *priv = obj->dev->dev_private;
 	int n = priv->usergart[fmt].height;
 	size_t size = PAGE_SIZE * n;
-	loff_t off = mmap_offset(obj) +
+	loff_t off = omap_gem_mmap_offset(obj) +
 			(entry->obj_pgoff << PAGE_SHIFT);
 	const int m = DIV_ROUND_UP(omap_obj->width << fmt, PAGE_SIZE);
 
@@ -319,16 +317,6 @@ u32 omap_gem_flags(struct drm_gem_object *obj)
 	return to_omap_bo(obj)->flags;
 }
 
-u64 omap_gem_mmap_offset(struct drm_gem_object *obj)
-{
-	u64 offset;
-
-	mutex_lock(&obj->dev->struct_mutex);
-	offset = mmap_offset(obj);
-	mutex_unlock(&obj->dev->struct_mutex);
-	return offset;
-}
-
 /** get mmap size */
 size_t omap_gem_mmap_size(struct drm_gem_object *obj)
 {
-- 
cgit v1.2.3


From 3cbd0c587b129beaefb1405bbe43831e6bc9461e Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Sat, 26 May 2018 19:54:33 +0300
Subject: drm/omap: gem: Replace struct_mutex usage with omap_obj private lock

The DRM device struct_mutex is used to protect against concurrent GEM
object operations that deal with memory allocation and pinning. All
those operations are local to a GEM object and don't need to be
serialized across different GEM objects. Replace the struct_mutex with
a local omap_obj.lock or drop it altogether where not needed.

Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_debugfs.c |   7 --
 drivers/gpu/drm/omapdrm/omap_fbdev.c   |   8 +--
 drivers/gpu/drm/omapdrm/omap_gem.c     | 127 ++++++++++++++++++++++-----------
 3 files changed, 86 insertions(+), 56 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_debugfs.c b/drivers/gpu/drm/omapdrm/omap_debugfs.c
index b42e286616b0..95ade441caa8 100644
--- a/drivers/gpu/drm/omapdrm/omap_debugfs.c
+++ b/drivers/gpu/drm/omapdrm/omap_debugfs.c
@@ -30,17 +30,10 @@ static int gem_show(struct seq_file *m, void *arg)
 	struct drm_info_node *node = (struct drm_info_node *) m->private;
 	struct drm_device *dev = node->minor->dev;
 	struct omap_drm_private *priv = dev->dev_private;
-	int ret;
-
-	ret = mutex_lock_interruptible(&dev->struct_mutex);
-	if (ret)
-		return ret;
 
 	seq_printf(m, "All Objects:\n");
 	omap_gem_describe_objects(&priv->obj_list, m);
 
-	mutex_unlock(&dev->struct_mutex);
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c
index 0f66c74a54b0..d958cc813a94 100644
--- a/drivers/gpu/drm/omapdrm/omap_fbdev.c
+++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c
@@ -170,13 +170,11 @@ static int omap_fbdev_create(struct drm_fb_helper *helper,
 		goto fail;
 	}
 
-	mutex_lock(&dev->struct_mutex);
-
 	fbi = drm_fb_helper_alloc_fbi(helper);
 	if (IS_ERR(fbi)) {
 		dev_err(dev->dev, "failed to allocate fb info\n");
 		ret = PTR_ERR(fbi);
-		goto fail_unlock;
+		goto fail;
 	}
 
 	DBG("fbi=%p, dev=%p", fbi, dev);
@@ -212,12 +210,8 @@ static int omap_fbdev_create(struct drm_fb_helper *helper,
 	DBG("par=%p, %dx%d", fbi->par, fbi->var.xres, fbi->var.yres);
 	DBG("allocated %dx%d fb", fbdev->fb->width, fbdev->fb->height);
 
-	mutex_unlock(&dev->struct_mutex);
-
 	return 0;
 
-fail_unlock:
-	mutex_unlock(&dev->struct_mutex);
 fail:
 
 	if (ret) {
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 623856d9b85a..cebbdf081e5d 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -47,6 +47,9 @@ struct omap_gem_object {
 	/** roll applied when mapping to DMM */
 	u32 roll;
 
+	/** protects dma_addr_cnt, block, pages, dma_addrs and vaddr */
+	struct mutex lock;
+
 	/**
 	 * dma_addr contains the buffer DMA address. It is valid for
 	 *
@@ -220,7 +223,10 @@ static void omap_gem_evict(struct drm_gem_object *obj)
  * Page Management
  */
 
-/* Ensure backing pages are allocated. */
+/*
+ * Ensure backing pages are allocated. Must be called with the omap_obj.lock
+ * held.
+ */
 static int omap_gem_attach_pages(struct drm_gem_object *obj)
 {
 	struct drm_device *dev = obj->dev;
@@ -230,6 +236,8 @@ static int omap_gem_attach_pages(struct drm_gem_object *obj)
 	int i, ret;
 	dma_addr_t *addrs;
 
+	lockdep_assert_held(&omap_obj->lock);
+
 	/*
 	 * If not using shmem (in which case backing pages don't need to be
 	 * allocated) or if pages are already allocated we're done.
@@ -291,13 +299,15 @@ free_pages:
 	return ret;
 }
 
-/** release backing pages */
+/* Release backing pages. Must be called with the omap_obj.lock held. */
 static void omap_gem_detach_pages(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	unsigned int npages = obj->size >> PAGE_SHIFT;
 	unsigned int i;
 
+	lockdep_assert_held(&omap_obj->lock);
+
 	for (i = 0; i < npages; i++) {
 		if (omap_obj->dma_addrs[i])
 			dma_unmap_page(obj->dev->dev, omap_obj->dma_addrs[i],
@@ -491,14 +501,13 @@ vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	struct drm_device *dev = obj->dev;
 	int err;
 	vm_fault_t ret;
 
 	/* Make sure we don't parallel update on a fault, nor move or remove
 	 * something from beneath our feet
 	 */
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
 
 	/* if a shmem backed object, make sure we have pages attached now */
 	err = omap_gem_attach_pages(obj);
@@ -520,7 +529,7 @@ vm_fault_t omap_gem_fault(struct vm_fault *vmf)
 
 
 fail:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 	return ret;
 }
 
@@ -654,7 +663,7 @@ int omap_gem_roll(struct drm_gem_object *obj, u32 roll)
 
 	omap_obj->roll = roll;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
 
 	/* if we aren't mapped yet, we don't need to do anything */
 	if (omap_obj->block) {
@@ -669,7 +678,7 @@ int omap_gem_roll(struct drm_gem_object *obj, u32 roll)
 	}
 
 fail:
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 
 	return ret;
 }
@@ -770,7 +779,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret = 0;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
 
 	if (!omap_gem_is_contiguous(omap_obj) && priv->has_dmm) {
 		if (omap_obj->dma_addr_cnt == 0) {
@@ -826,7 +835,7 @@ int omap_gem_pin(struct drm_gem_object *obj, dma_addr_t *dma_addr)
 	}
 
 fail:
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 
 	return ret;
 }
@@ -844,7 +853,8 @@ void omap_gem_unpin(struct drm_gem_object *obj)
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
+
 	if (omap_obj->dma_addr_cnt > 0) {
 		omap_obj->dma_addr_cnt--;
 		if (omap_obj->dma_addr_cnt == 0) {
@@ -863,7 +873,7 @@ void omap_gem_unpin(struct drm_gem_object *obj)
 		}
 	}
 
-	mutex_unlock(&obj->dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 }
 
 /* Get rotated scanout address (only valid if already pinned), at the
@@ -876,13 +886,16 @@ int omap_gem_rotated_dma_addr(struct drm_gem_object *obj, u32 orient,
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
 	int ret = -EINVAL;
 
-	mutex_lock(&obj->dev->struct_mutex);
+	mutex_lock(&omap_obj->lock);
+
 	if ((omap_obj->dma_addr_cnt > 0) && omap_obj->block &&
 			(omap_obj->flags & OMAP_BO_TILED)) {
 		*dma_addr = tiler_tsptr(omap_obj->block, orient, x, y);
 		ret = 0;
 	}
-	mutex_unlock(&obj->dev->struct_mutex);
+
+	mutex_unlock(&omap_obj->lock);
+
 	return ret;
 }
 
@@ -910,18 +923,26 @@ int omap_gem_get_pages(struct drm_gem_object *obj, struct page ***pages,
 		bool remap)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	int ret;
+	int ret = 0;
 
-	if (!remap) {
-		if (!omap_obj->pages)
-			return -ENOMEM;
-		*pages = omap_obj->pages;
-		return 0;
+	mutex_lock(&omap_obj->lock);
+
+	if (remap) {
+		ret = omap_gem_attach_pages(obj);
+		if (ret)
+			goto unlock;
 	}
-	mutex_lock(&obj->dev->struct_mutex);
-	ret = omap_gem_attach_pages(obj);
+
+	if (!omap_obj->pages) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+
 	*pages = omap_obj->pages;
-	mutex_unlock(&obj->dev->struct_mutex);
+
+unlock:
+	mutex_unlock(&omap_obj->lock);
+
 	return ret;
 }
 
@@ -936,24 +957,34 @@ int omap_gem_put_pages(struct drm_gem_object *obj)
 }
 
 #ifdef CONFIG_DRM_FBDEV_EMULATION
-/* Get kernel virtual address for CPU access.. this more or less only
- * exists for omap_fbdev.  This should be called with struct_mutex
- * held.
+/*
+ * Get kernel virtual address for CPU access.. this more or less only
+ * exists for omap_fbdev.
  */
 void *omap_gem_vaddr(struct drm_gem_object *obj)
 {
 	struct omap_gem_object *omap_obj = to_omap_bo(obj);
-	WARN_ON(!mutex_is_locked(&obj->dev->struct_mutex));
-	if (!omap_obj->vaddr) {
-		int ret;
+	void *vaddr;
+	int ret;
+
+	mutex_lock(&omap_obj->lock);
 
+	if (!omap_obj->vaddr) {
 		ret = omap_gem_attach_pages(obj);
-		if (ret)
-			return ERR_PTR(ret);
+		if (ret) {
+			vaddr = ERR_PTR(ret);
+			goto unlock;
+		}
+
 		omap_obj->vaddr = vmap(omap_obj->pages, obj->size >> PAGE_SHIFT,
 				VM_MAP, pgprot_writecombine(PAGE_KERNEL));
 	}
-	return omap_obj->vaddr;
+
+	vaddr = omap_obj->vaddr;
+
+unlock:
+	mutex_unlock(&omap_obj->lock);
+	return vaddr;
 }
 #endif
 
@@ -1001,6 +1032,8 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 
 	off = drm_vma_node_start(&obj->vma_node);
 
+	mutex_lock(&omap_obj->lock);
+
 	seq_printf(m, "%08x: %2d (%2d) %08llx %pad (%2d) %p %4d",
 			omap_obj->flags, obj->name, kref_read(&obj->refcount),
 			off, &omap_obj->dma_addr, omap_obj->dma_addr_cnt,
@@ -1018,6 +1051,8 @@ void omap_gem_describe(struct drm_gem_object *obj, struct seq_file *m)
 		seq_printf(m, " %zu", obj->size);
 	}
 
+	mutex_unlock(&omap_obj->lock);
+
 	seq_printf(m, "\n");
 }
 
@@ -1051,15 +1086,19 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 
 	omap_gem_evict(obj);
 
-	WARN_ON(!mutex_is_locked(&dev->struct_mutex));
-
 	spin_lock(&priv->list_lock);
 	list_del(&omap_obj->mm_list);
 	spin_unlock(&priv->list_lock);
 
-	/* this means the object is still pinned.. which really should
-	 * not happen.  I think..
+	/*
+	 * We own the sole reference to the object at this point, but to keep
+	 * lockdep happy, we must still take the omap_obj_lock to call
+	 * omap_gem_detach_pages(). This should hardly make any difference as
+	 * there can't be any lock contention.
 	 */
+	mutex_lock(&omap_obj->lock);
+
+	/* The object should not be pinned. */
 	WARN_ON(omap_obj->dma_addr_cnt > 0);
 
 	if (omap_obj->pages) {
@@ -1078,8 +1117,12 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 		drm_prime_gem_destroy(obj, omap_obj->sgt);
 	}
 
+	mutex_unlock(&omap_obj->lock);
+
 	drm_gem_object_release(obj);
 
+	mutex_destroy(&omap_obj->lock);
+
 	kfree(omap_obj);
 }
 
@@ -1135,6 +1178,7 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 
 	obj = &omap_obj->base;
 	omap_obj->flags = flags;
+	mutex_init(&omap_obj->lock);
 
 	if (flags & OMAP_BO_TILED) {
 		/*
@@ -1199,16 +1243,15 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size,
 	if (sgt->orig_nents != 1 && !priv->has_dmm)
 		return ERR_PTR(-EINVAL);
 
-	mutex_lock(&dev->struct_mutex);
-
 	gsize.bytes = PAGE_ALIGN(size);
 	obj = omap_gem_new(dev, gsize, OMAP_BO_MEM_DMABUF | OMAP_BO_WC);
-	if (!obj) {
-		obj = ERR_PTR(-ENOMEM);
-		goto done;
-	}
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
 
 	omap_obj = to_omap_bo(obj);
+
+	mutex_lock(&omap_obj->lock);
+
 	omap_obj->sgt = sgt;
 
 	if (sgt->orig_nents == 1) {
@@ -1244,7 +1287,7 @@ struct drm_gem_object *omap_gem_new_dmabuf(struct drm_device *dev, size_t size,
 	}
 
 done:
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&omap_obj->lock);
 	return obj;
 }
 
-- 
cgit v1.2.3


From 5117bd898e8c0a31e8ab3a9b8523aecf0706e997 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 25 May 2018 19:39:24 +0300
Subject: drm/omap: gem: Fix mm_list locking

- None of the list walkings where protected.

- Switch to a mutex since the list walking at device resume time can
  sleep when pinning buffers through the tiler.

Only thing we need to be careful with here is that while we walk the
list we can't unreference any gem objects, since the final unref would
result in a recursive deadlock. But the only functions that walk the
list is the device resume and debugfs dumping, so all safe.

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_debugfs.c |  2 ++
 drivers/gpu/drm/omapdrm/omap_drv.c     |  2 +-
 drivers/gpu/drm/omapdrm/omap_drv.h     |  2 +-
 drivers/gpu/drm/omapdrm/omap_gem.c     | 15 +++++++++------
 4 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_debugfs.c b/drivers/gpu/drm/omapdrm/omap_debugfs.c
index 95ade441caa8..91cf043f2b6b 100644
--- a/drivers/gpu/drm/omapdrm/omap_debugfs.c
+++ b/drivers/gpu/drm/omapdrm/omap_debugfs.c
@@ -32,7 +32,9 @@ static int gem_show(struct seq_file *m, void *arg)
 	struct omap_drm_private *priv = dev->dev_private;
 
 	seq_printf(m, "All Objects:\n");
+	mutex_lock(&priv->list_lock);
 	omap_gem_describe_objects(&priv->obj_list, m);
+	mutex_unlock(&priv->list_lock);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index ef3b0e3571ec..5fcf9eaf3eaf 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -540,7 +540,7 @@ static int omapdrm_init(struct omap_drm_private *priv, struct device *dev)
 	priv->omaprev = soc ? (unsigned int)soc->data : 0;
 	priv->wq = alloc_ordered_workqueue("omapdrm", 0);
 
-	spin_lock_init(&priv->list_lock);
+	mutex_init(&priv->list_lock);
 	INIT_LIST_HEAD(&priv->obj_list);
 
 	/* Allocate and initialize the DRM device. */
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.h b/drivers/gpu/drm/omapdrm/omap_drv.h
index 6eaee4df4559..f27c8e216adf 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.h
+++ b/drivers/gpu/drm/omapdrm/omap_drv.h
@@ -71,7 +71,7 @@ struct omap_drm_private {
 	struct workqueue_struct *wq;
 
 	/* lock for obj_list below */
-	spinlock_t list_lock;
+	struct mutex list_lock;
 
 	/* list of GEM objects: */
 	struct list_head obj_list;
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index cebbdf081e5d..4ba5d035c590 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -1000,6 +1000,7 @@ int omap_gem_resume(struct drm_device *dev)
 	struct omap_gem_object *omap_obj;
 	int ret = 0;
 
+	mutex_lock(&priv->list_lock);
 	list_for_each_entry(omap_obj, &priv->obj_list, mm_list) {
 		if (omap_obj->block) {
 			struct drm_gem_object *obj = &omap_obj->base;
@@ -1011,12 +1012,14 @@ int omap_gem_resume(struct drm_device *dev)
 					omap_obj->roll, true);
 			if (ret) {
 				dev_err(dev->dev, "could not repin: %d\n", ret);
-				return ret;
+				goto done;
 			}
 		}
 	}
 
-	return 0;
+done:
+	mutex_unlock(&priv->list_lock);
+	return ret;
 }
 #endif
 
@@ -1086,9 +1089,9 @@ void omap_gem_free_object(struct drm_gem_object *obj)
 
 	omap_gem_evict(obj);
 
-	spin_lock(&priv->list_lock);
+	mutex_lock(&priv->list_lock);
 	list_del(&omap_obj->mm_list);
-	spin_unlock(&priv->list_lock);
+	mutex_unlock(&priv->list_lock);
 
 	/*
 	 * We own the sole reference to the object at this point, but to keep
@@ -1218,9 +1221,9 @@ struct drm_gem_object *omap_gem_new(struct drm_device *dev,
 			goto err_release;
 	}
 
-	spin_lock(&priv->list_lock);
+	mutex_lock(&priv->list_lock);
 	list_add(&omap_obj->mm_list, &priv->obj_list);
-	spin_unlock(&priv->list_lock);
+	mutex_unlock(&priv->list_lock);
 
 	return obj;
 
-- 
cgit v1.2.3


From f8466184bd5b5c21eb6196cd0e44668725a2e47a Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 25 May 2018 19:39:25 +0300
Subject: drm/omap: gem: Switch to gem_free_object_unlocked()

The only thing that omap_gem_free_object does that might need the magic
protection of struct_mutex (of keeping all objects alive if that lock is
held, even if the last reference is gone) is the mm_list manipulation.
This is already protected by the separate omapdrm->list_lock, which
means that struct_mutex is not needed by omapdrm. We can switch to
gem_free_object_unlocked()

Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Reviewed-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
---
 drivers/gpu/drm/omapdrm/omap_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 5fcf9eaf3eaf..5005ecc284d2 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -493,7 +493,7 @@ static struct drm_driver omap_drm_driver = {
 	.prime_fd_to_handle = drm_gem_prime_fd_to_handle,
 	.gem_prime_export = omap_gem_prime_export,
 	.gem_prime_import = omap_gem_prime_import,
-	.gem_free_object = omap_gem_free_object,
+	.gem_free_object_unlocked = omap_gem_free_object,
 	.gem_vm_ops = &omap_gem_vm_ops,
 	.dumb_create = omap_gem_dumb_create,
 	.dumb_map_offset = omap_gem_dumb_map_offset,
-- 
cgit v1.2.3


From 854dca5053d3653394aad319e3bd70c245401f12 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Sat, 26 May 2018 10:33:55 -0400
Subject: media: dt: bindings: tegra-vde: Document new optional Memory Client
 reset property

Recently binding of the Memory Controller has been extended, exposing
the Memory Client reset controls and hence it is now a reset controller.
Tegra video-decoder device is among the Memory Controller reset users,
document the new optional VDE HW reset property.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt b/Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt
index 470237ed6fe5..7302e949e662 100644
--- a/Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt
+++ b/Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt
@@ -27,9 +27,15 @@ Required properties:
   - sxe
 - clocks : Must include the following entries:
   - vde
-- resets : Must include the following entries:
+- resets : Must contain an entry for each entry in reset-names.
+- reset-names : Should include the following entries:
   - vde
 
+Optional properties:
+- resets : Must contain an entry for each entry in reset-names.
+- reset-names : Must include the following entries:
+  - mc
+
 Example:
 
 video-codec@6001a000 {
@@ -51,5 +57,6 @@ video-codec@6001a000 {
 		     <GIC_SPI 12 IRQ_TYPE_LEVEL_HIGH>; /* SXE interrupt */
 	interrupt-names = "sync-token", "bsev", "sxe";
 	clocks = <&tegra_car TEGRA20_CLK_VDE>;
-	resets = <&tegra_car 61>;
+	reset-names = "vde", "mc";
+	resets = <&tegra_car 61>, <&mc TEGRA20_MC_RESET_VDE>;
 };
-- 
cgit v1.2.3


From 5a0996af33879c027725daa58becdf172e0f166d Mon Sep 17 00:00:00 2001
From: Janani Sankara Babu <jananis37@gmail.com>
Date: Tue, 29 May 2018 19:08:22 -0400
Subject: media: Staging:media:imx Fix multiple assignments in a line

This patch solves multiple assignments warning shown by checkpatch
script.

Signed-off-by: Janani Sankara Babu <jananis37@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/imx/imx-media-csi.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 95d7805f3485..06af76d31c0b 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -1192,10 +1192,12 @@ static int csi_enum_frame_size(struct v4l2_subdev *sd,
 	} else {
 		crop = __csi_get_crop(priv, cfg, fse->which);
 
-		fse->min_width = fse->max_width = fse->index & 1 ?
+		fse->min_width = fse->index & 1 ?
 			crop->width / 2 : crop->width;
-		fse->min_height = fse->max_height = fse->index & 2 ?
+		fse->max_width = fse->min_width;
+		fse->min_height = fse->index & 2 ?
 			crop->height / 2 : crop->height;
+		fse->max_height = fse->min_height;
 	}
 
 	mutex_unlock(&priv->lock);
-- 
cgit v1.2.3


From 7fc77a2fdaa985393d84b8967db2c27664ec384b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 30 May 2018 18:07:11 -0400
Subject: media: v4l: omap: add VIDEO_V4L2 dependency

The omap media driver can be built-in while the v4l2 core is a loadable
module. This is a mistake and leads to link errors:

drivers/media/platform/omap/omap_vout.o: In function `omap_vout_remove':
omap_vout.c:(.text+0xec): undefined reference to `v4l2_device_unregister'
omap_vout.c:(.text+0x140): undefined reference to `video_device_release'
omap_vout.c:(.text+0x150): undefined reference to `video_unregister_device'
omap_vout.c:(.text+0x15c): undefined reference to `v4l2_ctrl_handler_free'

An explicit Kconfig dependency on VIDEO_V4L2 avoids the problem.
I ran into this problem for the first time today during my randconfig
builds, but could not find what caused it.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/omap/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/platform/omap/Kconfig b/drivers/media/platform/omap/Kconfig
index d827b6c285a6..4b5e55d41ad4 100644
--- a/drivers/media/platform/omap/Kconfig
+++ b/drivers/media/platform/omap/Kconfig
@@ -8,6 +8,7 @@ config VIDEO_OMAP2_VOUT
 	depends on MMU
 	depends on FB_OMAP2 || (COMPILE_TEST && FB_OMAP2=n)
 	depends on ARCH_OMAP2 || ARCH_OMAP3 || COMPILE_TEST
+	depends on VIDEO_V4L2
 	select VIDEOBUF_GEN
 	select VIDEOBUF_DMA_CONTIG
 	select OMAP2_VRFB if ARCH_OMAP2 || ARCH_OMAP3
-- 
cgit v1.2.3


From e32eb0d8a6cdc965347b964e45e40c9254bd7408 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@opentech.at>
Date: Fri, 1 Jun 2018 05:21:32 -0400
Subject: media: adv7604: simplify of_node_put()

As the of_node_put() is unconditional here there is no need to have it
twice.

Signed-off-by: Nicholas Mc Guire <hofrat@opentech.at>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/adv7604.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index cac2081e876e..1a3b2c04d9f9 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -3108,12 +3108,9 @@ static int adv76xx_parse_dt(struct adv76xx_state *state)
 		return -EINVAL;
 
 	ret = v4l2_fwnode_endpoint_parse(of_fwnode_handle(endpoint), &bus_cfg);
-	if (ret) {
-		of_node_put(endpoint);
-		return ret;
-	}
-
 	of_node_put(endpoint);
+	if (ret)
+		return ret;
 
 	if (!of_property_read_u32(np, "default-input", &v))
 		state->pdata.default_input = v;
-- 
cgit v1.2.3


From e8ced209510164f0b54d4bb2a34d243a8af8f561 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Fri, 1 Jun 2018 08:46:14 -0400
Subject: media: atmel-isi: drop unnecessary while loop

As there is no way this can loop it actually makes no sense to have
a while(1){} around the body - all three possible paths end in a return
statement.

Fixes: commit c1d82b895380 "[media] atmel-isi: move out of soc_camera to atmel"

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Acked-by: Ludovic Desroches <ludovic.desroches@microchip.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/atmel/atmel-isi.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/media/platform/atmel/atmel-isi.c b/drivers/media/platform/atmel/atmel-isi.c
index e5be21a31640..85fc7b98b660 100644
--- a/drivers/media/platform/atmel/atmel-isi.c
+++ b/drivers/media/platform/atmel/atmel-isi.c
@@ -1106,23 +1106,21 @@ static int isi_graph_parse(struct atmel_isi *isi, struct device_node *node)
 	struct device_node *ep = NULL;
 	struct device_node *remote;
 
-	while (1) {
-		ep = of_graph_get_next_endpoint(node, ep);
-		if (!ep)
-			return -EINVAL;
-
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote) {
-			of_node_put(ep);
-			return -EINVAL;
-		}
+	ep = of_graph_get_next_endpoint(node, ep);
+	if (!ep)
+		return -EINVAL;
 
-		/* Remote node to connect */
-		isi->entity.node = remote;
-		isi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
-		isi->entity.asd.match.fwnode = of_fwnode_handle(remote);
-		return 0;
+	remote = of_graph_get_remote_port_parent(ep);
+	if (!remote) {
+		of_node_put(ep);
+		return -EINVAL;
 	}
+
+	/* Remote node to connect */
+	isi->entity.node = remote;
+	isi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
+	isi->entity.asd.match.fwnode = of_fwnode_handle(remote);
+	return 0;
 }
 
 static int isi_graph_init(struct atmel_isi *isi)
-- 
cgit v1.2.3


From 4f9195e3f88c13de94f5828f53d0ffab00d20e6d Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Fri, 1 Jun 2018 09:30:14 -0400
Subject: media: atmel-isi: move of_node_put() to cover success branch as well

The of_node_put() was only covering the error branch but missed the
success branch so the refcount for ep which
of_graph_get_remote_port_parent() incremented on success would was
not being decremented.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Acked-by: Ludovic Desroches <ludovic.desroches@microchip.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/atmel/atmel-isi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/atmel/atmel-isi.c b/drivers/media/platform/atmel/atmel-isi.c
index 85fc7b98b660..e8db4df1e7c4 100644
--- a/drivers/media/platform/atmel/atmel-isi.c
+++ b/drivers/media/platform/atmel/atmel-isi.c
@@ -1111,10 +1111,9 @@ static int isi_graph_parse(struct atmel_isi *isi, struct device_node *node)
 		return -EINVAL;
 
 	remote = of_graph_get_remote_port_parent(ep);
-	if (!remote) {
-		of_node_put(ep);
+	of_node_put(ep);
+	if (!remote)
 		return -EINVAL;
-	}
 
 	/* Remote node to connect */
 	isi->entity.node = remote;
-- 
cgit v1.2.3


From 055eceebecfe0d0997b6f7902b36cd6bb5fac860 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Wed, 6 Jun 2018 09:21:53 -0400
Subject: media: renesas-ceu: Add support for YUYV permutations

Add support for YUYV permutations, passing down to the subdevice the media bus
format with components ordering that reflect the output pixel format one.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/renesas-ceu.c | 91 ++++++++++++++++++++++++++++++------
 1 file changed, 78 insertions(+), 13 deletions(-)

diff --git a/drivers/media/platform/renesas-ceu.c b/drivers/media/platform/renesas-ceu.c
index fe4fe944592d..ad782901cd7a 100644
--- a/drivers/media/platform/renesas-ceu.c
+++ b/drivers/media/platform/renesas-ceu.c
@@ -254,6 +254,18 @@ static const struct ceu_fmt ceu_fmt_list[] = {
 		.fourcc	= V4L2_PIX_FMT_YUYV,
 		.bpp	= 16,
 	},
+	{
+		.fourcc	= V4L2_PIX_FMT_UYVY,
+		.bpp	= 16,
+	},
+	{
+		.fourcc	= V4L2_PIX_FMT_YVYU,
+		.bpp	= 16,
+	},
+	{
+		.fourcc	= V4L2_PIX_FMT_VYUY,
+		.bpp	= 16,
+	},
 };
 
 static const struct ceu_fmt *get_ceu_fmt_from_fourcc(unsigned int fourcc)
@@ -272,6 +284,9 @@ static bool ceu_fmt_mplane(struct v4l2_pix_format_mplane *pix)
 {
 	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
 		return false;
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
@@ -380,7 +395,9 @@ static int ceu_hw_config(struct ceu_device *ceudev)
 	switch (pix->pixelformat) {
 	/* Data fetch sync mode */
 	case V4L2_PIX_FMT_YUYV:
-		/* TODO: handle YUYV permutations through DTARY bits. */
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_VYUY:
 		camcr	= CEU_CAMCR_JPEG;
 		cdocr	|= CEU_CDOCR_NO_DOWSAMPLE;
 		cfzsr	= (pix->height << 16) | pix->width;
@@ -568,6 +585,9 @@ static void ceu_calc_plane_sizes(struct ceu_device *ceudev,
 
 	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
 		pix->num_planes	= 1;
 		bpl		= pix->width * ceu_fmt->bpp / 8;
 		szimage		= pix->height * bpl;
@@ -762,42 +782,59 @@ static const struct vb2_ops ceu_vb2_ops = {
 /* --- CEU image formats handling --- */
 
 /*
- * ceu_try_fmt() - test format on CEU and sensor
+ * __ceu_try_fmt() - test format on CEU and sensor
  * @ceudev: The CEU device.
  * @v4l2_fmt: format to test.
+ * @sd_mbus_code: the media bus code accepted by the subdevice; output param.
  *
  * Returns 0 for success, < 0 for errors.
  */
-static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
+static int __ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt,
+			 u32 *sd_mbus_code)
 {
 	struct ceu_subdev *ceu_sd = ceudev->sd;
 	struct v4l2_pix_format_mplane *pix = &v4l2_fmt->fmt.pix_mp;
 	struct v4l2_subdev *v4l2_sd = ceu_sd->v4l2_sd;
 	struct v4l2_subdev_pad_config pad_cfg;
 	const struct ceu_fmt *ceu_fmt;
+	u32 mbus_code_old;
+	u32 mbus_code;
 	int ret;
 
 	/*
 	 * Set format on sensor sub device: bus format used to produce memory
-	 * format is selected at initialization time.
+	 * format is selected depending on YUV component ordering or
+	 * at initialization time.
 	 */
 	struct v4l2_subdev_format sd_format = {
 		.which	= V4L2_SUBDEV_FORMAT_TRY,
-		.format	= {
-			.code = ceu_sd->mbus_fmt.mbus_code,
-		},
 	};
 
+	mbus_code_old = ceu_sd->mbus_fmt.mbus_code;
+
 	switch (pix->pixelformat) {
 	case V4L2_PIX_FMT_YUYV:
+		mbus_code = MEDIA_BUS_FMT_YUYV8_2X8;
+		break;
+	case V4L2_PIX_FMT_UYVY:
+		mbus_code = MEDIA_BUS_FMT_UYVY8_2X8;
+		break;
+	case V4L2_PIX_FMT_YVYU:
+		mbus_code = MEDIA_BUS_FMT_YVYU8_2X8;
+		break;
+	case V4L2_PIX_FMT_VYUY:
+		mbus_code = MEDIA_BUS_FMT_VYUY8_2X8;
+		break;
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
 	case V4L2_PIX_FMT_NV12:
 	case V4L2_PIX_FMT_NV21:
+		mbus_code = ceu_sd->mbus_fmt.mbus_code;
 		break;
 
 	default:
 		pix->pixelformat = V4L2_PIX_FMT_NV16;
+		mbus_code = ceu_sd->mbus_fmt.mbus_code;
 		break;
 	}
 
@@ -808,9 +845,25 @@ static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 			      &pix->height, 4, CEU_MAX_HEIGHT, 4, 0);
 
 	v4l2_fill_mbus_format_mplane(&sd_format.format, pix);
+
+	/*
+	 * Try with the mbus_code matching YUYV components ordering first,
+	 * if that one fails, fallback to default selected at initialization
+	 * time.
+	 */
+	sd_format.format.code = mbus_code;
 	ret = v4l2_subdev_call(v4l2_sd, pad, set_fmt, &pad_cfg, &sd_format);
-	if (ret)
-		return ret;
+	if (ret) {
+		if (ret == -EINVAL) {
+			/* fallback */
+			sd_format.format.code = mbus_code_old;
+			ret = v4l2_subdev_call(v4l2_sd, pad, set_fmt,
+					       &pad_cfg, &sd_format);
+		}
+
+		if (ret)
+			return ret;
+	}
 
 	/* Apply size returned by sensor as the CEU can't scale. */
 	v4l2_fill_pix_format_mplane(pix, &sd_format.format);
@@ -818,9 +871,22 @@ static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 	/* Calculate per-plane sizes based on image format. */
 	ceu_calc_plane_sizes(ceudev, ceu_fmt, pix);
 
+	/* Report to caller the configured mbus format. */
+	*sd_mbus_code = sd_format.format.code;
+
 	return 0;
 }
 
+/*
+ * ceu_try_fmt() - Wrapper for __ceu_try_fmt; discard configured mbus_fmt
+ */
+static int ceu_try_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
+{
+	u32 mbus_code;
+
+	return __ceu_try_fmt(ceudev, v4l2_fmt, &mbus_code);
+}
+
 /*
  * ceu_set_fmt() - Apply the supplied format to both sensor and CEU
  */
@@ -828,6 +894,7 @@ static int ceu_set_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 {
 	struct ceu_subdev *ceu_sd = ceudev->sd;
 	struct v4l2_subdev *v4l2_sd = ceu_sd->v4l2_sd;
+	u32 mbus_code;
 	int ret;
 
 	/*
@@ -836,15 +903,13 @@ static int ceu_set_fmt(struct ceu_device *ceudev, struct v4l2_format *v4l2_fmt)
 	 */
 	struct v4l2_subdev_format format = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-		.format	= {
-			.code = ceu_sd->mbus_fmt.mbus_code,
-		},
 	};
 
-	ret = ceu_try_fmt(ceudev, v4l2_fmt);
+	ret = __ceu_try_fmt(ceudev, v4l2_fmt, &mbus_code);
 	if (ret)
 		return ret;
 
+	format.format.code = mbus_code;
 	v4l2_fill_mbus_format_mplane(&format.format, &v4l2_fmt->fmt.pix_mp);
 	ret = v4l2_subdev_call(v4l2_sd, pad, set_fmt, NULL, &format);
 	if (ret)
-- 
cgit v1.2.3


From ce3ff60f02349471b3bb24516b87da799a5b61e6 Mon Sep 17 00:00:00 2001
From: Gabriel Fanelli <gabrielfanelli61@gmail.com>
Date: Thu, 7 Jun 2018 03:12:16 -0400
Subject: media: staging: media: bcm2048: match alignment with open parenthesis

This patch fixes the checkpatch.pl issue:

CHECK: Alignment should match open parenthesis

Signed-off-by: Gabriel Fanelli <gabrielfanelli61@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/bcm2048/radio-bcm2048.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/media/bcm2048/radio-bcm2048.c b/drivers/staging/media/bcm2048/radio-bcm2048.c
index 06d1920150da..a90b2eb112f9 100644
--- a/drivers/staging/media/bcm2048/radio-bcm2048.c
+++ b/drivers/staging/media/bcm2048/radio-bcm2048.c
@@ -2175,7 +2175,7 @@ static int bcm2048_fops_release(struct file *file)
 }
 
 static __poll_t bcm2048_fops_poll(struct file *file,
-				      struct poll_table_struct *pts)
+				  struct poll_table_struct *pts)
 {
 	struct bcm2048_device *bdev = video_drvdata(file);
 	__poll_t retval = 0;
-- 
cgit v1.2.3


From 653d500ccaadd76ccade9f07469cdc66759315b6 Mon Sep 17 00:00:00 2001
From: Pavel Machek <pavel@ucw.cz>
Date: Sun, 6 May 2018 04:06:07 -0400
Subject: media: i2c: lm3560: add support for lm3559 chip

Add support for LM3559, as found in Motorola Droid 4 phone, for
example. SW interface seems to be identical.

Signed-off-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/lm3560.c | 3 ++-
 include/media/i2c/lm3560.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/i2c/lm3560.c b/drivers/media/i2c/lm3560.c
index b600e03aa94b..49c6644cbba7 100644
--- a/drivers/media/i2c/lm3560.c
+++ b/drivers/media/i2c/lm3560.c
@@ -1,6 +1,6 @@
 /*
  * drivers/media/i2c/lm3560.c
- * General device driver for TI lm3560, FLASH LED Driver
+ * General device driver for TI lm3559, lm3560, FLASH LED Driver
  *
  * Copyright (C) 2013 Texas Instruments
  *
@@ -465,6 +465,7 @@ static int lm3560_remove(struct i2c_client *client)
 }
 
 static const struct i2c_device_id lm3560_id_table[] = {
+	{LM3559_NAME, 0},
 	{LM3560_NAME, 0},
 	{}
 };
diff --git a/include/media/i2c/lm3560.h b/include/media/i2c/lm3560.h
index a5bd310c9e1e..0e2b1c751a5d 100644
--- a/include/media/i2c/lm3560.h
+++ b/include/media/i2c/lm3560.h
@@ -22,6 +22,7 @@
 
 #include <media/v4l2-subdev.h>
 
+#define LM3559_NAME	"lm3559"
 #define LM3560_NAME	"lm3560"
 #define LM3560_I2C_ADDR	(0x53)
 
-- 
cgit v1.2.3


From fd59ccb9b6cb5051b84ec7ac9df32631ec43da2a Mon Sep 17 00:00:00 2001
From: Simon Horman <horms+renesas@verge.net.au>
Date: Wed, 9 May 2018 14:45:58 -0400
Subject: media: rcar-vin: Drop unnecessary register properties from example
 vin port
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The example vin port node does not have an address and thus does not
need address-cells or address size-properties.

Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/rcar_vin.txt | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index a19517e1c669..2a0c59e97f40 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -107,9 +107,6 @@ Board setup example for Gen2 platforms (vin1 composite video input)
         status = "okay";
 
         port {
-                #address-cells = <1>;
-                #size-cells = <0>;
-
                 vin1ep0: endpoint {
                         remote-endpoint = <&adv7180>;
                         bus-width = <8>;
-- 
cgit v1.2.3


From 6ad48c27fc08e1cc931798399eccfdc46b45f4b8 Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Sun, 13 May 2018 14:58:18 -0400
Subject: media: dt-bindings: media: rcar_vin: add support for r8a77965
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Rob Herring <robh@kernel.org>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/rcar_vin.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index 2a0c59e97f40..c65e638f0f24 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -21,6 +21,7 @@ on Gen3 platforms to a CSI-2 receiver.
    - "renesas,vin-r8a7794" for the R8A7794 device
    - "renesas,vin-r8a7795" for the R8A7795 device
    - "renesas,vin-r8a7796" for the R8A7796 device
+   - "renesas,vin-r8a77965" for the R8A77965 device
    - "renesas,vin-r8a77970" for the R8A77970 device
    - "renesas,rcar-gen2-vin" for a generic R-Car Gen2 or RZ/G1 compatible
      device.
-- 
cgit v1.2.3


From e10cf92ead486b24a3169bb3b3215cf5775225fd Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Mon, 28 May 2018 19:17:04 -0400
Subject: media: dt-bindings: media: rcar_vin: fix style for ports and
 endpoints
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The style for referring to ports and endpoint are wrong. Refer to them
using lowercase and a unit address, port@x and endpoint@x.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/rcar_vin.txt | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index c65e638f0f24..638cecdde474 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -45,23 +45,23 @@ The per-board settings Gen2 platforms:
 The per-board settings Gen3 platforms:
 
 Gen3 platforms can support both a single connected parallel input source
-from external SoC pins (port0) and/or multiple parallel input sources
-from local SoC CSI-2 receivers (port1) depending on SoC.
+from external SoC pins (port@0) and/or multiple parallel input sources
+from local SoC CSI-2 receivers (port@1) depending on SoC.
 
 - renesas,id - ID number of the VIN, VINx in the documentation.
 - ports
-    - port 0 - sub-node describing a single endpoint connected to the VIN
+    - port@0 - sub-node describing a single endpoint connected to the VIN
       from external SoC pins described in video-interfaces.txt[1].
-      Describing more then one endpoint in port 0 is invalid. Only VIN
-      instances that are connected to external pins should have port 0.
-    - port 1 - sub-nodes describing one or more endpoints connected to
+      Describing more than one endpoint in port@0 is invalid. Only VIN
+      instances that are connected to external pins should have port@0.
+    - port@1 - sub-nodes describing one or more endpoints connected to
       the VIN from local SoC CSI-2 receivers. The endpoint numbers must
       use the following schema.
 
-        - Endpoint 0 - sub-node describing the endpoint connected to CSI20
-        - Endpoint 1 - sub-node describing the endpoint connected to CSI21
-        - Endpoint 2 - sub-node describing the endpoint connected to CSI40
-        - Endpoint 3 - sub-node describing the endpoint connected to CSI41
+        - endpoint@0 - sub-node describing the endpoint connected to CSI20
+        - endpoint@1 - sub-node describing the endpoint connected to CSI21
+        - endpoint@2 - sub-node describing the endpoint connected to CSI40
+        - endpoint@3 - sub-node describing the endpoint connected to CSI41
 
 Device node example for Gen2 platforms
 --------------------------------------
-- 
cgit v1.2.3


From 23689ab1add36964b69b6e4fdb97d52f315119f5 Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Mon, 28 May 2018 19:26:37 -0400
Subject: media: rcar-vin: sync which hardware buffer to start capture from
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When starting the VIN capture procedure we are not guaranteed that the
first buffer written to is VnMB1 to which we assigned the first buffer
queued. This is problematic for two reasons. Buffers might not be
dequeued in the same order they where queued for capture. Future
features planed for the VIN driver is support for outputting frames in
SEQ_TB/BT format and to do that it's important that capture starts from
the first buffer slot, VnMB1.

We are guaranteed that capturing always happens in sequence (VnMB1 ->
VnMB2 -> VnMB3 -> VnMB1). So drop up to two frames when starting
capturing so that the driver always returns buffers in the same order
they are queued and prepare for SEQ_TB/BT output.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-dma.c | 16 +++++++++++++++-
 drivers/media/platform/rcar-vin/rcar-vin.h |  2 ++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
index ac07f99e3516..cfe5d7a9d44e 100644
--- a/drivers/media/platform/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -856,7 +856,7 @@ static int rvin_capture_start(struct rvin_dev *vin)
 	/* Continuous Frame Capture Mode */
 	rvin_write(vin, VNFC_C_FRAME, VNFC_REG);
 
-	vin->state = RUNNING;
+	vin->state = STARTING;
 
 	return 0;
 }
@@ -910,6 +910,20 @@ static irqreturn_t rvin_irq(int irq, void *data)
 	vnms = rvin_read(vin, VNMS_REG);
 	slot = (vnms & VNMS_FBS_MASK) >> VNMS_FBS_SHIFT;
 
+	/*
+	 * To hand buffers back in a known order to userspace start
+	 * to capture first from slot 0.
+	 */
+	if (vin->state == STARTING) {
+		if (slot != 0) {
+			vin_dbg(vin, "Starting sync slot: %d\n", slot);
+			goto done;
+		}
+
+		vin_dbg(vin, "Capture start synced!\n");
+		vin->state = RUNNING;
+	}
+
 	/* Capture frame */
 	if (vin->queue_buf[slot]) {
 		vin->queue_buf[slot]->field = vin->format.field;
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
index c2aef789b491..ff747e22d8cf 100644
--- a/drivers/media/platform/rcar-vin/rcar-vin.h
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -53,11 +53,13 @@ enum rvin_csi_id {
 
 /**
  * STOPPED  - No operation in progress
+ * STARTING - Capture starting up
  * RUNNING  - Operation in progress have buffers
  * STOPPING - Stopping operation
  */
 enum rvin_dma_state {
 	STOPPED = 0,
+	STARTING,
 	RUNNING,
 	STOPPING,
 };
-- 
cgit v1.2.3


From a740e3b2f7a26c5dd13741d399b69e22660b1b96 Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Mon, 28 May 2018 19:49:06 -0400
Subject: media: rcar-vin: enable support for r8a77965
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the SoC specific information for Renesas r8a77965.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 48 +++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index d3072e166a1c..e6a010ee4ba1 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -974,6 +974,50 @@ static const struct rvin_info rcar_info_r8a7796 = {
 	.routes = rcar_info_r8a7796_routes,
 };
 
+static const struct rvin_group_route rcar_info_r8a77965_routes[] = {
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 0, .mask = BIT(0) | BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 0, .mask = BIT(1) | BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 0, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 1, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 1, .mask = BIT(1) | BIT(3) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 1, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 1, .mask = BIT(4) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 2, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 2, .mask = BIT(1) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 2, .mask = BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 2, .vin = 2, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 2, .vin = 2, .mask = BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 3, .mask = BIT(0) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 3, .mask = BIT(1) | BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 3, .vin = 3, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 3, .vin = 3, .mask = BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 4, .mask = BIT(0) | BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 4, .mask = BIT(1) | BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 4, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 5, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 5, .mask = BIT(1) | BIT(3) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 5, .mask = BIT(2) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 5, .mask = BIT(4) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 6, .mask = BIT(0) },
+	{ .csi = RVIN_CSI40, .channel = 0, .vin = 6, .mask = BIT(1) },
+	{ .csi = RVIN_CSI20, .channel = 0, .vin = 6, .mask = BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 2, .vin = 6, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 2, .vin = 6, .mask = BIT(4) },
+	{ .csi = RVIN_CSI40, .channel = 1, .vin = 7, .mask = BIT(0) },
+	{ .csi = RVIN_CSI20, .channel = 1, .vin = 7, .mask = BIT(1) | BIT(2) },
+	{ .csi = RVIN_CSI40, .channel = 3, .vin = 7, .mask = BIT(3) },
+	{ .csi = RVIN_CSI20, .channel = 3, .vin = 7, .mask = BIT(4) },
+	{ /* Sentinel */ }
+};
+
+static const struct rvin_info rcar_info_r8a77965 = {
+	.model = RCAR_GEN3,
+	.use_mc = true,
+	.max_width = 4096,
+	.max_height = 4096,
+	.routes = rcar_info_r8a77965_routes,
+};
+
 static const struct rvin_group_route _rcar_info_r8a77970_routes[] = {
 	{ .csi = RVIN_CSI40, .channel = 0, .vin = 0, .mask = BIT(0) | BIT(3) },
 	{ .csi = RVIN_CSI40, .channel = 0, .vin = 1, .mask = BIT(2) },
@@ -1030,6 +1074,10 @@ static const struct of_device_id rvin_of_id_table[] = {
 		.compatible = "renesas,vin-r8a7796",
 		.data = &rcar_info_r8a7796,
 	},
+	{
+		.compatible = "renesas,vin-r8a77965",
+		.data = &rcar_info_r8a77965,
+	},
 	{
 		.compatible = "renesas,vin-r8a77970",
 		.data = &rcar_info_r8a77970,
-- 
cgit v1.2.3


From f187352dcd45d6f48c43c78dcc0d88d5508ecb11 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 28 May 2018 12:37:07 -0400
Subject: media: i2c: Copy rj54n1cb0c soc_camera sensor driver

Copy the soc_camera based driver in v4l2 sensor driver directory.
This commit just copies the original file without modifying it.
No modification to KConfig and Makefile as soc_camera framework
dependencies need to be removed first in next commit.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/rj54n1cb0c.c | 1416 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 1416 insertions(+)
 create mode 100644 drivers/media/i2c/rj54n1cb0c.c

diff --git a/drivers/media/i2c/rj54n1cb0c.c b/drivers/media/i2c/rj54n1cb0c.c
new file mode 100644
index 000000000000..02398d0bc649
--- /dev/null
+++ b/drivers/media/i2c/rj54n1cb0c.c
@@ -0,0 +1,1416 @@
+/*
+ * Driver for RJ54N1CB0C CMOS Image Sensor from Sharp
+ *
+ * Copyright (C) 2009, Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/slab.h>
+#include <linux/v4l2-mediabus.h>
+#include <linux/videodev2.h>
+#include <linux/module.h>
+
+#include <media/i2c/rj54n1cb0c.h>
+#include <media/soc_camera.h>
+#include <media/v4l2-clk.h>
+#include <media/v4l2-subdev.h>
+#include <media/v4l2-ctrls.h>
+
+#define RJ54N1_DEV_CODE			0x0400
+#define RJ54N1_DEV_CODE2		0x0401
+#define RJ54N1_OUT_SEL			0x0403
+#define RJ54N1_XY_OUTPUT_SIZE_S_H	0x0404
+#define RJ54N1_X_OUTPUT_SIZE_S_L	0x0405
+#define RJ54N1_Y_OUTPUT_SIZE_S_L	0x0406
+#define RJ54N1_XY_OUTPUT_SIZE_P_H	0x0407
+#define RJ54N1_X_OUTPUT_SIZE_P_L	0x0408
+#define RJ54N1_Y_OUTPUT_SIZE_P_L	0x0409
+#define RJ54N1_LINE_LENGTH_PCK_S_H	0x040a
+#define RJ54N1_LINE_LENGTH_PCK_S_L	0x040b
+#define RJ54N1_LINE_LENGTH_PCK_P_H	0x040c
+#define RJ54N1_LINE_LENGTH_PCK_P_L	0x040d
+#define RJ54N1_RESIZE_N			0x040e
+#define RJ54N1_RESIZE_N_STEP		0x040f
+#define RJ54N1_RESIZE_STEP		0x0410
+#define RJ54N1_RESIZE_HOLD_H		0x0411
+#define RJ54N1_RESIZE_HOLD_L		0x0412
+#define RJ54N1_H_OBEN_OFS		0x0413
+#define RJ54N1_V_OBEN_OFS		0x0414
+#define RJ54N1_RESIZE_CONTROL		0x0415
+#define RJ54N1_STILL_CONTROL		0x0417
+#define RJ54N1_INC_USE_SEL_H		0x0425
+#define RJ54N1_INC_USE_SEL_L		0x0426
+#define RJ54N1_MIRROR_STILL_MODE	0x0427
+#define RJ54N1_INIT_START		0x0428
+#define RJ54N1_SCALE_1_2_LEV		0x0429
+#define RJ54N1_SCALE_4_LEV		0x042a
+#define RJ54N1_Y_GAIN			0x04d8
+#define RJ54N1_APT_GAIN_UP		0x04fa
+#define RJ54N1_RA_SEL_UL		0x0530
+#define RJ54N1_BYTE_SWAP		0x0531
+#define RJ54N1_OUT_SIGPO		0x053b
+#define RJ54N1_WB_SEL_WEIGHT_I		0x054e
+#define RJ54N1_BIT8_WB			0x0569
+#define RJ54N1_HCAPS_WB			0x056a
+#define RJ54N1_VCAPS_WB			0x056b
+#define RJ54N1_HCAPE_WB			0x056c
+#define RJ54N1_VCAPE_WB			0x056d
+#define RJ54N1_EXPOSURE_CONTROL		0x058c
+#define RJ54N1_FRAME_LENGTH_S_H		0x0595
+#define RJ54N1_FRAME_LENGTH_S_L		0x0596
+#define RJ54N1_FRAME_LENGTH_P_H		0x0597
+#define RJ54N1_FRAME_LENGTH_P_L		0x0598
+#define RJ54N1_PEAK_H			0x05b7
+#define RJ54N1_PEAK_50			0x05b8
+#define RJ54N1_PEAK_60			0x05b9
+#define RJ54N1_PEAK_DIFF		0x05ba
+#define RJ54N1_IOC			0x05ef
+#define RJ54N1_TG_BYPASS		0x0700
+#define RJ54N1_PLL_L			0x0701
+#define RJ54N1_PLL_N			0x0702
+#define RJ54N1_PLL_EN			0x0704
+#define RJ54N1_RATIO_TG			0x0706
+#define RJ54N1_RATIO_T			0x0707
+#define RJ54N1_RATIO_R			0x0708
+#define RJ54N1_RAMP_TGCLK_EN		0x0709
+#define RJ54N1_OCLK_DSP			0x0710
+#define RJ54N1_RATIO_OP			0x0711
+#define RJ54N1_RATIO_O			0x0712
+#define RJ54N1_OCLK_SEL_EN		0x0713
+#define RJ54N1_CLK_RST			0x0717
+#define RJ54N1_RESET_STANDBY		0x0718
+#define RJ54N1_FWFLG			0x07fe
+
+#define E_EXCLK				(1 << 7)
+#define SOFT_STDBY			(1 << 4)
+#define SEN_RSTX			(1 << 2)
+#define TG_RSTX				(1 << 1)
+#define DSP_RSTX			(1 << 0)
+
+#define RESIZE_HOLD_SEL			(1 << 2)
+#define RESIZE_GO			(1 << 1)
+
+/*
+ * When cropping, the camera automatically centers the cropped region, there
+ * doesn't seem to be a way to specify an explicit location of the rectangle.
+ */
+#define RJ54N1_COLUMN_SKIP		0
+#define RJ54N1_ROW_SKIP			0
+#define RJ54N1_MAX_WIDTH		1600
+#define RJ54N1_MAX_HEIGHT		1200
+
+#define PLL_L				2
+#define PLL_N				0x31
+
+/* I2C addresses: 0x50, 0x51, 0x60, 0x61 */
+
+/* RJ54N1CB0C has only one fixed colorspace per pixelcode */
+struct rj54n1_datafmt {
+	u32	code;
+	enum v4l2_colorspace		colorspace;
+};
+
+/* Find a data format by a pixel code in an array */
+static const struct rj54n1_datafmt *rj54n1_find_datafmt(
+	u32 code, const struct rj54n1_datafmt *fmt,
+	int n)
+{
+	int i;
+	for (i = 0; i < n; i++)
+		if (fmt[i].code == code)
+			return fmt + i;
+
+	return NULL;
+}
+
+static const struct rj54n1_datafmt rj54n1_colour_fmts[] = {
+	{MEDIA_BUS_FMT_YUYV8_2X8, V4L2_COLORSPACE_JPEG},
+	{MEDIA_BUS_FMT_YVYU8_2X8, V4L2_COLORSPACE_JPEG},
+	{MEDIA_BUS_FMT_RGB565_2X8_LE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_RGB565_2X8_BE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE, V4L2_COLORSPACE_SRGB},
+	{MEDIA_BUS_FMT_SBGGR10_1X10, V4L2_COLORSPACE_SRGB},
+};
+
+struct rj54n1_clock_div {
+	u8 ratio_tg;	/* can be 0 or an odd number */
+	u8 ratio_t;
+	u8 ratio_r;
+	u8 ratio_op;
+	u8 ratio_o;
+};
+
+struct rj54n1 {
+	struct v4l2_subdev subdev;
+	struct v4l2_ctrl_handler hdl;
+	struct v4l2_clk *clk;
+	struct rj54n1_clock_div clk_div;
+	const struct rj54n1_datafmt *fmt;
+	struct v4l2_rect rect;	/* Sensor window */
+	unsigned int tgclk_mhz;
+	bool auto_wb;
+	unsigned short width;	/* Output window */
+	unsigned short height;
+	unsigned short resize;	/* Sensor * 1024 / resize = Output */
+	unsigned short scale;
+	u8 bank;
+};
+
+struct rj54n1_reg_val {
+	u16 reg;
+	u8 val;
+};
+
+static const struct rj54n1_reg_val bank_4[] = {
+	{0x417, 0},
+	{0x42c, 0},
+	{0x42d, 0xf0},
+	{0x42e, 0},
+	{0x42f, 0x50},
+	{0x430, 0xf5},
+	{0x431, 0x16},
+	{0x432, 0x20},
+	{0x433, 0},
+	{0x434, 0xc8},
+	{0x43c, 8},
+	{0x43e, 0x90},
+	{0x445, 0x83},
+	{0x4ba, 0x58},
+	{0x4bb, 4},
+	{0x4bc, 0x20},
+	{0x4db, 4},
+	{0x4fe, 2},
+};
+
+static const struct rj54n1_reg_val bank_5[] = {
+	{0x514, 0},
+	{0x516, 0},
+	{0x518, 0},
+	{0x51a, 0},
+	{0x51d, 0xff},
+	{0x56f, 0x28},
+	{0x575, 0x40},
+	{0x5bc, 0x48},
+	{0x5c1, 6},
+	{0x5e5, 0x11},
+	{0x5e6, 0x43},
+	{0x5e7, 0x33},
+	{0x5e8, 0x21},
+	{0x5e9, 0x30},
+	{0x5ea, 0x0},
+	{0x5eb, 0xa5},
+	{0x5ec, 0xff},
+	{0x5fe, 2},
+};
+
+static const struct rj54n1_reg_val bank_7[] = {
+	{0x70a, 0},
+	{0x714, 0xff},
+	{0x715, 0xff},
+	{0x716, 0x1f},
+	{0x7FE, 2},
+};
+
+static const struct rj54n1_reg_val bank_8[] = {
+	{0x800, 0x00},
+	{0x801, 0x01},
+	{0x802, 0x61},
+	{0x805, 0x00},
+	{0x806, 0x00},
+	{0x807, 0x00},
+	{0x808, 0x00},
+	{0x809, 0x01},
+	{0x80A, 0x61},
+	{0x80B, 0x00},
+	{0x80C, 0x01},
+	{0x80D, 0x00},
+	{0x80E, 0x00},
+	{0x80F, 0x00},
+	{0x810, 0x00},
+	{0x811, 0x01},
+	{0x812, 0x61},
+	{0x813, 0x00},
+	{0x814, 0x11},
+	{0x815, 0x00},
+	{0x816, 0x41},
+	{0x817, 0x00},
+	{0x818, 0x51},
+	{0x819, 0x01},
+	{0x81A, 0x1F},
+	{0x81B, 0x00},
+	{0x81C, 0x01},
+	{0x81D, 0x00},
+	{0x81E, 0x11},
+	{0x81F, 0x00},
+	{0x820, 0x41},
+	{0x821, 0x00},
+	{0x822, 0x51},
+	{0x823, 0x00},
+	{0x824, 0x00},
+	{0x825, 0x00},
+	{0x826, 0x47},
+	{0x827, 0x01},
+	{0x828, 0x4F},
+	{0x829, 0x00},
+	{0x82A, 0x00},
+	{0x82B, 0x00},
+	{0x82C, 0x30},
+	{0x82D, 0x00},
+	{0x82E, 0x40},
+	{0x82F, 0x00},
+	{0x830, 0xB3},
+	{0x831, 0x00},
+	{0x832, 0xE3},
+	{0x833, 0x00},
+	{0x834, 0x00},
+	{0x835, 0x00},
+	{0x836, 0x00},
+	{0x837, 0x00},
+	{0x838, 0x00},
+	{0x839, 0x01},
+	{0x83A, 0x61},
+	{0x83B, 0x00},
+	{0x83C, 0x01},
+	{0x83D, 0x00},
+	{0x83E, 0x00},
+	{0x83F, 0x00},
+	{0x840, 0x00},
+	{0x841, 0x01},
+	{0x842, 0x61},
+	{0x843, 0x00},
+	{0x844, 0x1D},
+	{0x845, 0x00},
+	{0x846, 0x00},
+	{0x847, 0x00},
+	{0x848, 0x00},
+	{0x849, 0x01},
+	{0x84A, 0x1F},
+	{0x84B, 0x00},
+	{0x84C, 0x05},
+	{0x84D, 0x00},
+	{0x84E, 0x19},
+	{0x84F, 0x01},
+	{0x850, 0x21},
+	{0x851, 0x01},
+	{0x852, 0x5D},
+	{0x853, 0x00},
+	{0x854, 0x00},
+	{0x855, 0x00},
+	{0x856, 0x19},
+	{0x857, 0x01},
+	{0x858, 0x21},
+	{0x859, 0x00},
+	{0x85A, 0x00},
+	{0x85B, 0x00},
+	{0x85C, 0x00},
+	{0x85D, 0x00},
+	{0x85E, 0x00},
+	{0x85F, 0x00},
+	{0x860, 0xB3},
+	{0x861, 0x00},
+	{0x862, 0xE3},
+	{0x863, 0x00},
+	{0x864, 0x00},
+	{0x865, 0x00},
+	{0x866, 0x00},
+	{0x867, 0x00},
+	{0x868, 0x00},
+	{0x869, 0xE2},
+	{0x86A, 0x00},
+	{0x86B, 0x01},
+	{0x86C, 0x06},
+	{0x86D, 0x00},
+	{0x86E, 0x00},
+	{0x86F, 0x00},
+	{0x870, 0x60},
+	{0x871, 0x8C},
+	{0x872, 0x10},
+	{0x873, 0x00},
+	{0x874, 0xE0},
+	{0x875, 0x00},
+	{0x876, 0x27},
+	{0x877, 0x01},
+	{0x878, 0x00},
+	{0x879, 0x00},
+	{0x87A, 0x00},
+	{0x87B, 0x03},
+	{0x87C, 0x00},
+	{0x87D, 0x00},
+	{0x87E, 0x00},
+	{0x87F, 0x00},
+	{0x880, 0x00},
+	{0x881, 0x00},
+	{0x882, 0x00},
+	{0x883, 0x00},
+	{0x884, 0x00},
+	{0x885, 0x00},
+	{0x886, 0xF8},
+	{0x887, 0x00},
+	{0x888, 0x03},
+	{0x889, 0x00},
+	{0x88A, 0x64},
+	{0x88B, 0x00},
+	{0x88C, 0x03},
+	{0x88D, 0x00},
+	{0x88E, 0xB1},
+	{0x88F, 0x00},
+	{0x890, 0x03},
+	{0x891, 0x01},
+	{0x892, 0x1D},
+	{0x893, 0x00},
+	{0x894, 0x03},
+	{0x895, 0x01},
+	{0x896, 0x4B},
+	{0x897, 0x00},
+	{0x898, 0xE5},
+	{0x899, 0x00},
+	{0x89A, 0x01},
+	{0x89B, 0x00},
+	{0x89C, 0x01},
+	{0x89D, 0x04},
+	{0x89E, 0xC8},
+	{0x89F, 0x00},
+	{0x8A0, 0x01},
+	{0x8A1, 0x01},
+	{0x8A2, 0x61},
+	{0x8A3, 0x00},
+	{0x8A4, 0x01},
+	{0x8A5, 0x00},
+	{0x8A6, 0x00},
+	{0x8A7, 0x00},
+	{0x8A8, 0x00},
+	{0x8A9, 0x00},
+	{0x8AA, 0x7F},
+	{0x8AB, 0x03},
+	{0x8AC, 0x00},
+	{0x8AD, 0x00},
+	{0x8AE, 0x00},
+	{0x8AF, 0x00},
+	{0x8B0, 0x00},
+	{0x8B1, 0x00},
+	{0x8B6, 0x00},
+	{0x8B7, 0x01},
+	{0x8B8, 0x00},
+	{0x8B9, 0x00},
+	{0x8BA, 0x02},
+	{0x8BB, 0x00},
+	{0x8BC, 0xFF},
+	{0x8BD, 0x00},
+	{0x8FE, 2},
+};
+
+static const struct rj54n1_reg_val bank_10[] = {
+	{0x10bf, 0x69}
+};
+
+/* Clock dividers - these are default register values, divider = register + 1 */
+static const struct rj54n1_clock_div clk_div = {
+	.ratio_tg	= 3 /* default: 5 */,
+	.ratio_t	= 4 /* default: 1 */,
+	.ratio_r	= 4 /* default: 0 */,
+	.ratio_op	= 1 /* default: 5 */,
+	.ratio_o	= 9 /* default: 0 */,
+};
+
+static struct rj54n1 *to_rj54n1(const struct i2c_client *client)
+{
+	return container_of(i2c_get_clientdata(client), struct rj54n1, subdev);
+}
+
+static int reg_read(struct i2c_client *client, const u16 reg)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret;
+
+	/* set bank */
+	if (rj54n1->bank != reg >> 8) {
+		dev_dbg(&client->dev, "[0x%x] = 0x%x\n", 0xff, reg >> 8);
+		ret = i2c_smbus_write_byte_data(client, 0xff, reg >> 8);
+		if (ret < 0)
+			return ret;
+		rj54n1->bank = reg >> 8;
+	}
+	return i2c_smbus_read_byte_data(client, reg & 0xff);
+}
+
+static int reg_write(struct i2c_client *client, const u16 reg,
+		     const u8 data)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret;
+
+	/* set bank */
+	if (rj54n1->bank != reg >> 8) {
+		dev_dbg(&client->dev, "[0x%x] = 0x%x\n", 0xff, reg >> 8);
+		ret = i2c_smbus_write_byte_data(client, 0xff, reg >> 8);
+		if (ret < 0)
+			return ret;
+		rj54n1->bank = reg >> 8;
+	}
+	dev_dbg(&client->dev, "[0x%x] = 0x%x\n", reg & 0xff, data);
+	return i2c_smbus_write_byte_data(client, reg & 0xff, data);
+}
+
+static int reg_set(struct i2c_client *client, const u16 reg,
+		   const u8 data, const u8 mask)
+{
+	int ret;
+
+	ret = reg_read(client, reg);
+	if (ret < 0)
+		return ret;
+	return reg_write(client, reg, (ret & ~mask) | (data & mask));
+}
+
+static int reg_write_multiple(struct i2c_client *client,
+			      const struct rj54n1_reg_val *rv, const int n)
+{
+	int i, ret;
+
+	for (i = 0; i < n; i++) {
+		ret = reg_write(client, rv->reg, rv->val);
+		if (ret < 0)
+			return ret;
+		rv++;
+	}
+
+	return 0;
+}
+
+static int rj54n1_enum_mbus_code(struct v4l2_subdev *sd,
+		struct v4l2_subdev_pad_config *cfg,
+		struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->pad || code->index >= ARRAY_SIZE(rj54n1_colour_fmts))
+		return -EINVAL;
+
+	code->code = rj54n1_colour_fmts[code->index].code;
+	return 0;
+}
+
+static int rj54n1_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	/* Switch between preview and still shot modes */
+	return reg_set(client, RJ54N1_STILL_CONTROL, (!enable) << 7, 0x80);
+}
+
+static int rj54n1_set_rect(struct i2c_client *client,
+			   u16 reg_x, u16 reg_y, u16 reg_xy,
+			   u32 width, u32 height)
+{
+	int ret;
+
+	ret = reg_write(client, reg_xy,
+			((width >> 4) & 0x70) |
+			((height >> 8) & 7));
+
+	if (!ret)
+		ret = reg_write(client, reg_x, width & 0xff);
+	if (!ret)
+		ret = reg_write(client, reg_y, height & 0xff);
+
+	return ret;
+}
+
+/*
+ * Some commands, specifically certain initialisation sequences, require
+ * a commit operation.
+ */
+static int rj54n1_commit(struct i2c_client *client)
+{
+	int ret = reg_write(client, RJ54N1_INIT_START, 1);
+	msleep(10);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_INIT_START, 0);
+	return ret;
+}
+
+static int rj54n1_sensor_scale(struct v4l2_subdev *sd, s32 *in_w, s32 *in_h,
+			       s32 *out_w, s32 *out_h);
+
+static int rj54n1_set_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	const struct v4l2_rect *rect = &sel->r;
+	int dummy = 0, output_w, output_h,
+		input_w = rect->width, input_h = rect->height;
+	int ret;
+
+	if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE ||
+	    sel->target != V4L2_SEL_TGT_CROP)
+		return -EINVAL;
+
+	/* arbitrary minimum width and height, edges unimportant */
+	soc_camera_limit_side(&dummy, &input_w,
+		     RJ54N1_COLUMN_SKIP, 8, RJ54N1_MAX_WIDTH);
+
+	soc_camera_limit_side(&dummy, &input_h,
+		     RJ54N1_ROW_SKIP, 8, RJ54N1_MAX_HEIGHT);
+
+	output_w = (input_w * 1024 + rj54n1->resize / 2) / rj54n1->resize;
+	output_h = (input_h * 1024 + rj54n1->resize / 2) / rj54n1->resize;
+
+	dev_dbg(&client->dev, "Scaling for %dx%d : %u = %dx%d\n",
+		input_w, input_h, rj54n1->resize, output_w, output_h);
+
+	ret = rj54n1_sensor_scale(sd, &input_w, &input_h, &output_w, &output_h);
+	if (ret < 0)
+		return ret;
+
+	rj54n1->width		= output_w;
+	rj54n1->height		= output_h;
+	rj54n1->resize		= ret;
+	rj54n1->rect.width	= input_w;
+	rj54n1->rect.height	= input_h;
+
+	return 0;
+}
+
+static int rj54n1_get_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+
+	if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP_BOUNDS:
+	case V4L2_SEL_TGT_CROP_DEFAULT:
+		sel->r.left = RJ54N1_COLUMN_SKIP;
+		sel->r.top = RJ54N1_ROW_SKIP;
+		sel->r.width = RJ54N1_MAX_WIDTH;
+		sel->r.height = RJ54N1_MAX_HEIGHT;
+		return 0;
+	case V4L2_SEL_TGT_CROP:
+		sel->r = rj54n1->rect;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int rj54n1_get_fmt(struct v4l2_subdev *sd,
+		struct v4l2_subdev_pad_config *cfg,
+		struct v4l2_subdev_format *format)
+{
+	struct v4l2_mbus_framefmt *mf = &format->format;
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+
+	if (format->pad)
+		return -EINVAL;
+
+	mf->code	= rj54n1->fmt->code;
+	mf->colorspace	= rj54n1->fmt->colorspace;
+	mf->field	= V4L2_FIELD_NONE;
+	mf->width	= rj54n1->width;
+	mf->height	= rj54n1->height;
+
+	return 0;
+}
+
+/*
+ * The actual geometry configuration routine. It scales the input window into
+ * the output one, updates the window sizes and returns an error or the resize
+ * coefficient on success. Note: we only use the "Fixed Scaling" on this camera.
+ */
+static int rj54n1_sensor_scale(struct v4l2_subdev *sd, s32 *in_w, s32 *in_h,
+			       s32 *out_w, s32 *out_h)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	unsigned int skip, resize, input_w = *in_w, input_h = *in_h,
+		output_w = *out_w, output_h = *out_h;
+	u16 inc_sel, wb_bit8, wb_left, wb_right, wb_top, wb_bottom;
+	unsigned int peak, peak_50, peak_60;
+	int ret;
+
+	/*
+	 * We have a problem with crops, where the window is larger than 512x384
+	 * and output window is larger than a half of the input one. In this
+	 * case we have to either reduce the input window to equal or below
+	 * 512x384 or the output window to equal or below 1/2 of the input.
+	 */
+	if (output_w > max(512U, input_w / 2)) {
+		if (2 * output_w > RJ54N1_MAX_WIDTH) {
+			input_w = RJ54N1_MAX_WIDTH;
+			output_w = RJ54N1_MAX_WIDTH / 2;
+		} else {
+			input_w = output_w * 2;
+		}
+
+		dev_dbg(&client->dev, "Adjusted output width: in %u, out %u\n",
+			input_w, output_w);
+	}
+
+	if (output_h > max(384U, input_h / 2)) {
+		if (2 * output_h > RJ54N1_MAX_HEIGHT) {
+			input_h = RJ54N1_MAX_HEIGHT;
+			output_h = RJ54N1_MAX_HEIGHT / 2;
+		} else {
+			input_h = output_h * 2;
+		}
+
+		dev_dbg(&client->dev, "Adjusted output height: in %u, out %u\n",
+			input_h, output_h);
+	}
+
+	/* Idea: use the read mode for snapshots, handle separate geometries */
+	ret = rj54n1_set_rect(client, RJ54N1_X_OUTPUT_SIZE_S_L,
+			      RJ54N1_Y_OUTPUT_SIZE_S_L,
+			      RJ54N1_XY_OUTPUT_SIZE_S_H, output_w, output_h);
+	if (!ret)
+		ret = rj54n1_set_rect(client, RJ54N1_X_OUTPUT_SIZE_P_L,
+			      RJ54N1_Y_OUTPUT_SIZE_P_L,
+			      RJ54N1_XY_OUTPUT_SIZE_P_H, output_w, output_h);
+
+	if (ret < 0)
+		return ret;
+
+	if (output_w > input_w && output_h > input_h) {
+		input_w = output_w;
+		input_h = output_h;
+
+		resize = 1024;
+	} else {
+		unsigned int resize_x, resize_y;
+		resize_x = (input_w * 1024 + output_w / 2) / output_w;
+		resize_y = (input_h * 1024 + output_h / 2) / output_h;
+
+		/* We want max(resize_x, resize_y), check if it still fits */
+		if (resize_x > resize_y &&
+		    (output_h * resize_x + 512) / 1024 > RJ54N1_MAX_HEIGHT)
+			resize = (RJ54N1_MAX_HEIGHT * 1024 + output_h / 2) /
+				output_h;
+		else if (resize_y > resize_x &&
+			 (output_w * resize_y + 512) / 1024 > RJ54N1_MAX_WIDTH)
+			resize = (RJ54N1_MAX_WIDTH * 1024 + output_w / 2) /
+				output_w;
+		else
+			resize = max(resize_x, resize_y);
+
+		/* Prohibited value ranges */
+		switch (resize) {
+		case 2040 ... 2047:
+			resize = 2039;
+			break;
+		case 4080 ... 4095:
+			resize = 4079;
+			break;
+		case 8160 ... 8191:
+			resize = 8159;
+			break;
+		case 16320 ... 16384:
+			resize = 16319;
+		}
+	}
+
+	/* Set scaling */
+	ret = reg_write(client, RJ54N1_RESIZE_HOLD_L, resize & 0xff);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESIZE_HOLD_H, resize >> 8);
+
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Configure a skipping bitmask. The sensor will select a skipping value
+	 * among set bits automatically. This is very unclear in the datasheet
+	 * too. I was told, in this register one enables all skipping values,
+	 * that are required for a specific resize, and the camera selects
+	 * automatically, which ones to use. But it is unclear how to identify,
+	 * which cropping values are needed. Secondly, why don't we just set all
+	 * bits and let the camera choose? Would it increase processing time and
+	 * reduce the framerate? Using 0xfffc for INC_USE_SEL doesn't seem to
+	 * improve the image quality or stability for larger frames (see comment
+	 * above), but I didn't check the framerate.
+	 */
+	skip = min(resize / 1024, 15U);
+
+	inc_sel = 1 << skip;
+
+	if (inc_sel <= 2)
+		inc_sel = 0xc;
+	else if (resize & 1023 && skip < 15)
+		inc_sel |= 1 << (skip + 1);
+
+	ret = reg_write(client, RJ54N1_INC_USE_SEL_L, inc_sel & 0xfc);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_INC_USE_SEL_H, inc_sel >> 8);
+
+	if (!rj54n1->auto_wb) {
+		/* Auto white balance window */
+		wb_left	  = output_w / 16;
+		wb_right  = (3 * output_w / 4 - 3) / 4;
+		wb_top	  = output_h / 16;
+		wb_bottom = (3 * output_h / 4 - 3) / 4;
+		wb_bit8	  = ((wb_left >> 2) & 0x40) | ((wb_top >> 4) & 0x10) |
+			((wb_right >> 6) & 4) | ((wb_bottom >> 8) & 1);
+
+		if (!ret)
+			ret = reg_write(client, RJ54N1_BIT8_WB, wb_bit8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_HCAPS_WB, wb_left);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_VCAPS_WB, wb_top);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_HCAPE_WB, wb_right);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_VCAPE_WB, wb_bottom);
+	}
+
+	/* Antiflicker */
+	peak = 12 * RJ54N1_MAX_WIDTH * (1 << 14) * resize / rj54n1->tgclk_mhz /
+		10000;
+	peak_50 = peak / 6;
+	peak_60 = peak / 5;
+
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_H,
+				((peak_50 >> 4) & 0xf0) | (peak_60 >> 8));
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_50, peak_50);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_60, peak_60);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PEAK_DIFF, peak / 150);
+
+	/* Start resizing */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESIZE_CONTROL,
+				RESIZE_HOLD_SEL | RESIZE_GO | 1);
+
+	if (ret < 0)
+		return ret;
+
+	/* Constant taken from manufacturer's example */
+	msleep(230);
+
+	ret = reg_write(client, RJ54N1_RESIZE_CONTROL, RESIZE_HOLD_SEL | 1);
+	if (ret < 0)
+		return ret;
+
+	*in_w = (output_w * resize + 512) / 1024;
+	*in_h = (output_h * resize + 512) / 1024;
+	*out_w = output_w;
+	*out_h = output_h;
+
+	dev_dbg(&client->dev, "Scaled for %dx%d : %u = %ux%u, skip %u\n",
+		*in_w, *in_h, resize, output_w, output_h, skip);
+
+	return resize;
+}
+
+static int rj54n1_set_clock(struct i2c_client *client)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret;
+
+	/* Enable external clock */
+	ret = reg_write(client, RJ54N1_RESET_STANDBY, E_EXCLK | SOFT_STDBY);
+	/* Leave stand-by. Note: use this when implementing suspend / resume */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY, E_EXCLK);
+
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PLL_L, PLL_L);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PLL_N, PLL_N);
+
+	/* TGCLK dividers */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_TG,
+				rj54n1->clk_div.ratio_tg);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_T,
+				rj54n1->clk_div.ratio_t);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_R,
+				rj54n1->clk_div.ratio_r);
+
+	/* Enable TGCLK & RAMP */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RAMP_TGCLK_EN, 3);
+
+	/* Disable clock output */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_OCLK_DSP, 0);
+
+	/* Set divisors */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_OP,
+				rj54n1->clk_div.ratio_op);
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RATIO_O,
+				rj54n1->clk_div.ratio_o);
+
+	/* Enable OCLK */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_OCLK_SEL_EN, 1);
+
+	/* Use PLL for Timing Generator, write 2 to reserved bits */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_TG_BYPASS, 2);
+
+	/* Take sensor out of reset */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY,
+				E_EXCLK | SEN_RSTX);
+	/* Enable PLL */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_PLL_EN, 1);
+
+	/* Wait for PLL to stabilise */
+	msleep(10);
+
+	/* Enable clock to frequency divider */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_CLK_RST, 1);
+
+	if (!ret)
+		ret = reg_read(client, RJ54N1_CLK_RST);
+	if (ret != 1) {
+		dev_err(&client->dev,
+			"Resetting RJ54N1CB0C clock failed: %d!\n", ret);
+		return -EIO;
+	}
+
+	/* Start the PLL */
+	ret = reg_set(client, RJ54N1_OCLK_DSP, 1, 1);
+
+	/* Enable OCLK */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_OCLK_SEL_EN, 1);
+
+	return ret;
+}
+
+static int rj54n1_reg_init(struct i2c_client *client)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int ret = rj54n1_set_clock(client);
+
+	if (!ret)
+		ret = reg_write_multiple(client, bank_7, ARRAY_SIZE(bank_7));
+	if (!ret)
+		ret = reg_write_multiple(client, bank_10, ARRAY_SIZE(bank_10));
+
+	/* Set binning divisors */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_SCALE_1_2_LEV, 3 | (7 << 4));
+	if (!ret)
+		ret = reg_write(client, RJ54N1_SCALE_4_LEV, 0xf);
+
+	/* Switch to fixed resize mode */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESIZE_CONTROL,
+				RESIZE_HOLD_SEL | 1);
+
+	/* Set gain */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_Y_GAIN, 0x84);
+
+	/*
+	 * Mirror the image back: default is upside down and left-to-right...
+	 * Set manual preview / still shot switching
+	 */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_MIRROR_STILL_MODE, 0x27);
+
+	if (!ret)
+		ret = reg_write_multiple(client, bank_4, ARRAY_SIZE(bank_4));
+
+	/* Auto exposure area */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_EXPOSURE_CONTROL, 0x80);
+	/* Check current auto WB config */
+	if (!ret)
+		ret = reg_read(client, RJ54N1_WB_SEL_WEIGHT_I);
+	if (ret >= 0) {
+		rj54n1->auto_wb = ret & 0x80;
+		ret = reg_write_multiple(client, bank_5, ARRAY_SIZE(bank_5));
+	}
+	if (!ret)
+		ret = reg_write_multiple(client, bank_8, ARRAY_SIZE(bank_8));
+
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY,
+				E_EXCLK | DSP_RSTX | SEN_RSTX);
+
+	/* Commit init */
+	if (!ret)
+		ret = rj54n1_commit(client);
+
+	/* Take DSP, TG, sensor out of reset */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_RESET_STANDBY,
+				E_EXCLK | DSP_RSTX | TG_RSTX | SEN_RSTX);
+
+	/* Start register update? Same register as 0x?FE in many bank_* sets */
+	if (!ret)
+		ret = reg_write(client, RJ54N1_FWFLG, 2);
+
+	/* Constant taken from manufacturer's example */
+	msleep(700);
+
+	return ret;
+}
+
+static int rj54n1_set_fmt(struct v4l2_subdev *sd,
+		struct v4l2_subdev_pad_config *cfg,
+		struct v4l2_subdev_format *format)
+{
+	struct v4l2_mbus_framefmt *mf = &format->format;
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	const struct rj54n1_datafmt *fmt;
+	int output_w, output_h, max_w, max_h,
+		input_w = rj54n1->rect.width, input_h = rj54n1->rect.height;
+	int align = mf->code == MEDIA_BUS_FMT_SBGGR10_1X10 ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE ||
+		mf->code == MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE;
+	int ret;
+
+	if (format->pad)
+		return -EINVAL;
+
+	dev_dbg(&client->dev, "%s: code = %d, width = %u, height = %u\n",
+		__func__, mf->code, mf->width, mf->height);
+
+	fmt = rj54n1_find_datafmt(mf->code, rj54n1_colour_fmts,
+				  ARRAY_SIZE(rj54n1_colour_fmts));
+	if (!fmt) {
+		fmt = rj54n1->fmt;
+		mf->code = fmt->code;
+	}
+
+	mf->field	= V4L2_FIELD_NONE;
+	mf->colorspace	= fmt->colorspace;
+
+	v4l_bound_align_image(&mf->width, 112, RJ54N1_MAX_WIDTH, align,
+			      &mf->height, 84, RJ54N1_MAX_HEIGHT, align, 0);
+
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+		cfg->try_fmt = *mf;
+		return 0;
+	}
+
+	/*
+	 * Verify if the sensor has just been powered on. TODO: replace this
+	 * with proper PM, when a suitable API is available.
+	 */
+	ret = reg_read(client, RJ54N1_RESET_STANDBY);
+	if (ret < 0)
+		return ret;
+
+	if (!(ret & E_EXCLK)) {
+		ret = rj54n1_reg_init(client);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* RA_SEL_UL is only relevant for raw modes, ignored otherwise. */
+	switch (mf->code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		break;
+	case MEDIA_BUS_FMT_RGB565_2X8_LE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0x11);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		break;
+	case MEDIA_BUS_FMT_RGB565_2X8_BE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 0x11);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_LE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 0);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 8, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 8);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADLO_BE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 0);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_BE:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 4);
+		if (!ret)
+			ret = reg_set(client, RJ54N1_BYTE_SWAP, 0, 8);
+		if (!ret)
+			ret = reg_write(client, RJ54N1_RA_SEL_UL, 8);
+		break;
+	case MEDIA_BUS_FMT_SBGGR10_1X10:
+		ret = reg_write(client, RJ54N1_OUT_SEL, 5);
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	/* Special case: a raw mode with 10 bits of data per clock tick */
+	if (!ret)
+		ret = reg_set(client, RJ54N1_OCLK_SEL_EN,
+			      (mf->code == MEDIA_BUS_FMT_SBGGR10_1X10) << 1, 2);
+
+	if (ret < 0)
+		return ret;
+
+	/* Supported scales 1:1 >= scale > 1:16 */
+	max_w = mf->width * (16 * 1024 - 1) / 1024;
+	if (input_w > max_w)
+		input_w = max_w;
+	max_h = mf->height * (16 * 1024 - 1) / 1024;
+	if (input_h > max_h)
+		input_h = max_h;
+
+	output_w = mf->width;
+	output_h = mf->height;
+
+	ret = rj54n1_sensor_scale(sd, &input_w, &input_h, &output_w, &output_h);
+	if (ret < 0)
+		return ret;
+
+	fmt = rj54n1_find_datafmt(mf->code, rj54n1_colour_fmts,
+				  ARRAY_SIZE(rj54n1_colour_fmts));
+
+	rj54n1->fmt		= fmt;
+	rj54n1->resize		= ret;
+	rj54n1->rect.width	= input_w;
+	rj54n1->rect.height	= input_h;
+	rj54n1->width		= output_w;
+	rj54n1->height		= output_h;
+
+	mf->width		= output_w;
+	mf->height		= output_h;
+	mf->field		= V4L2_FIELD_NONE;
+	mf->colorspace		= fmt->colorspace;
+
+	return 0;
+}
+
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+static int rj54n1_g_register(struct v4l2_subdev *sd,
+			     struct v4l2_dbg_register *reg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	if (reg->reg < 0x400 || reg->reg > 0x1fff)
+		/* Registers > 0x0800 are only available from Sharp support */
+		return -EINVAL;
+
+	reg->size = 1;
+	reg->val = reg_read(client, reg->reg);
+
+	if (reg->val > 0xff)
+		return -EIO;
+
+	return 0;
+}
+
+static int rj54n1_s_register(struct v4l2_subdev *sd,
+			     const struct v4l2_dbg_register *reg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+
+	if (reg->reg < 0x400 || reg->reg > 0x1fff)
+		/* Registers >= 0x0800 are only available from Sharp support */
+		return -EINVAL;
+
+	if (reg_write(client, reg->reg, reg->val) < 0)
+		return -EIO;
+
+	return 0;
+}
+#endif
+
+static int rj54n1_s_power(struct v4l2_subdev *sd, int on)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+
+	return soc_camera_set_power(&client->dev, ssdd, rj54n1->clk, on);
+}
+
+static int rj54n1_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct rj54n1 *rj54n1 = container_of(ctrl->handler, struct rj54n1, hdl);
+	struct v4l2_subdev *sd = &rj54n1->subdev;
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	int data;
+
+	switch (ctrl->id) {
+	case V4L2_CID_VFLIP:
+		if (ctrl->val)
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 0, 1);
+		else
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 1, 1);
+		if (data < 0)
+			return -EIO;
+		return 0;
+	case V4L2_CID_HFLIP:
+		if (ctrl->val)
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 0, 2);
+		else
+			data = reg_set(client, RJ54N1_MIRROR_STILL_MODE, 2, 2);
+		if (data < 0)
+			return -EIO;
+		return 0;
+	case V4L2_CID_GAIN:
+		if (reg_write(client, RJ54N1_Y_GAIN, ctrl->val * 2) < 0)
+			return -EIO;
+		return 0;
+	case V4L2_CID_AUTO_WHITE_BALANCE:
+		/* Auto WB area - whole image */
+		if (reg_set(client, RJ54N1_WB_SEL_WEIGHT_I, ctrl->val << 7,
+			    0x80) < 0)
+			return -EIO;
+		rj54n1->auto_wb = ctrl->val;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops rj54n1_ctrl_ops = {
+	.s_ctrl = rj54n1_s_ctrl,
+};
+
+static const struct v4l2_subdev_core_ops rj54n1_subdev_core_ops = {
+#ifdef CONFIG_VIDEO_ADV_DEBUG
+	.g_register	= rj54n1_g_register,
+	.s_register	= rj54n1_s_register,
+#endif
+	.s_power	= rj54n1_s_power,
+};
+
+static int rj54n1_g_mbus_config(struct v4l2_subdev *sd,
+				struct v4l2_mbus_config *cfg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
+
+	cfg->flags =
+		V4L2_MBUS_PCLK_SAMPLE_RISING | V4L2_MBUS_PCLK_SAMPLE_FALLING |
+		V4L2_MBUS_MASTER | V4L2_MBUS_DATA_ACTIVE_HIGH |
+		V4L2_MBUS_HSYNC_ACTIVE_HIGH | V4L2_MBUS_VSYNC_ACTIVE_HIGH;
+	cfg->type = V4L2_MBUS_PARALLEL;
+	cfg->flags = soc_camera_apply_board_flags(ssdd, cfg);
+
+	return 0;
+}
+
+static int rj54n1_s_mbus_config(struct v4l2_subdev *sd,
+				const struct v4l2_mbus_config *cfg)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(sd);
+	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
+
+	/* Figures 2.5-1 to 2.5-3 - default falling pixclk edge */
+	if (soc_camera_apply_board_flags(ssdd, cfg) &
+	    V4L2_MBUS_PCLK_SAMPLE_RISING)
+		return reg_write(client, RJ54N1_OUT_SIGPO, 1 << 4);
+	else
+		return reg_write(client, RJ54N1_OUT_SIGPO, 0);
+}
+
+static const struct v4l2_subdev_video_ops rj54n1_subdev_video_ops = {
+	.s_stream	= rj54n1_s_stream,
+	.g_mbus_config	= rj54n1_g_mbus_config,
+	.s_mbus_config	= rj54n1_s_mbus_config,
+};
+
+static const struct v4l2_subdev_pad_ops rj54n1_subdev_pad_ops = {
+	.enum_mbus_code = rj54n1_enum_mbus_code,
+	.get_selection	= rj54n1_get_selection,
+	.set_selection	= rj54n1_set_selection,
+	.get_fmt	= rj54n1_get_fmt,
+	.set_fmt	= rj54n1_set_fmt,
+};
+
+static const struct v4l2_subdev_ops rj54n1_subdev_ops = {
+	.core	= &rj54n1_subdev_core_ops,
+	.video	= &rj54n1_subdev_video_ops,
+	.pad	= &rj54n1_subdev_pad_ops,
+};
+
+/*
+ * Interface active, can use i2c. If it fails, it can indeed mean, that
+ * this wasn't our capture interface, so, we wait for the right one
+ */
+static int rj54n1_video_probe(struct i2c_client *client,
+			      struct rj54n1_pdata *priv)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	int data1, data2;
+	int ret;
+
+	ret = rj54n1_s_power(&rj54n1->subdev, 1);
+	if (ret < 0)
+		return ret;
+
+	/* Read out the chip version register */
+	data1 = reg_read(client, RJ54N1_DEV_CODE);
+	data2 = reg_read(client, RJ54N1_DEV_CODE2);
+
+	if (data1 != 0x51 || data2 != 0x10) {
+		ret = -ENODEV;
+		dev_info(&client->dev, "No RJ54N1CB0C found, read 0x%x:0x%x\n",
+			 data1, data2);
+		goto done;
+	}
+
+	/* Configure IOCTL polarity from the platform data: 0 or 1 << 7. */
+	ret = reg_write(client, RJ54N1_IOC, priv->ioctl_high << 7);
+	if (ret < 0)
+		goto done;
+
+	dev_info(&client->dev, "Detected a RJ54N1CB0C chip ID 0x%x:0x%x\n",
+		 data1, data2);
+
+	ret = v4l2_ctrl_handler_setup(&rj54n1->hdl);
+
+done:
+	rj54n1_s_power(&rj54n1->subdev, 0);
+	return ret;
+}
+
+static int rj54n1_probe(struct i2c_client *client,
+			const struct i2c_device_id *did)
+{
+	struct rj54n1 *rj54n1;
+	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
+	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+	struct rj54n1_pdata *rj54n1_priv;
+	int ret;
+
+	if (!ssdd || !ssdd->drv_priv) {
+		dev_err(&client->dev, "RJ54N1CB0C: missing platform data!\n");
+		return -EINVAL;
+	}
+
+	rj54n1_priv = ssdd->drv_priv;
+
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
+		dev_warn(&adapter->dev,
+			 "I2C-Adapter doesn't support I2C_FUNC_SMBUS_BYTE\n");
+		return -EIO;
+	}
+
+	rj54n1 = devm_kzalloc(&client->dev, sizeof(struct rj54n1), GFP_KERNEL);
+	if (!rj54n1)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&rj54n1->subdev, client, &rj54n1_subdev_ops);
+	v4l2_ctrl_handler_init(&rj54n1->hdl, 4);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_VFLIP, 0, 1, 1, 0);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_HFLIP, 0, 1, 1, 0);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_GAIN, 0, 127, 1, 66);
+	v4l2_ctrl_new_std(&rj54n1->hdl, &rj54n1_ctrl_ops,
+			V4L2_CID_AUTO_WHITE_BALANCE, 0, 1, 1, 1);
+	rj54n1->subdev.ctrl_handler = &rj54n1->hdl;
+	if (rj54n1->hdl.error)
+		return rj54n1->hdl.error;
+
+	rj54n1->clk_div		= clk_div;
+	rj54n1->rect.left	= RJ54N1_COLUMN_SKIP;
+	rj54n1->rect.top	= RJ54N1_ROW_SKIP;
+	rj54n1->rect.width	= RJ54N1_MAX_WIDTH;
+	rj54n1->rect.height	= RJ54N1_MAX_HEIGHT;
+	rj54n1->width		= RJ54N1_MAX_WIDTH;
+	rj54n1->height		= RJ54N1_MAX_HEIGHT;
+	rj54n1->fmt		= &rj54n1_colour_fmts[0];
+	rj54n1->resize		= 1024;
+	rj54n1->tgclk_mhz	= (rj54n1_priv->mclk_freq / PLL_L * PLL_N) /
+		(clk_div.ratio_tg + 1) / (clk_div.ratio_t + 1);
+
+	rj54n1->clk = v4l2_clk_get(&client->dev, "mclk");
+	if (IS_ERR(rj54n1->clk)) {
+		ret = PTR_ERR(rj54n1->clk);
+		goto eclkget;
+	}
+
+	ret = rj54n1_video_probe(client, rj54n1_priv);
+	if (ret < 0) {
+		v4l2_clk_put(rj54n1->clk);
+eclkget:
+		v4l2_ctrl_handler_free(&rj54n1->hdl);
+	}
+
+	return ret;
+}
+
+static int rj54n1_remove(struct i2c_client *client)
+{
+	struct rj54n1 *rj54n1 = to_rj54n1(client);
+	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
+
+	v4l2_clk_put(rj54n1->clk);
+	v4l2_device_unregister_subdev(&rj54n1->subdev);
+	if (ssdd->free_bus)
+		ssdd->free_bus(ssdd);
+	v4l2_ctrl_handler_free(&rj54n1->hdl);
+
+	return 0;
+}
+
+static const struct i2c_device_id rj54n1_id[] = {
+	{ "rj54n1cb0c", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, rj54n1_id);
+
+static struct i2c_driver rj54n1_i2c_driver = {
+	.driver = {
+		.name = "rj54n1cb0c",
+	},
+	.probe		= rj54n1_probe,
+	.remove		= rj54n1_remove,
+	.id_table	= rj54n1_id,
+};
+
+module_i2c_driver(rj54n1_i2c_driver);
+
+MODULE_DESCRIPTION("Sharp RJ54N1CB0C Camera driver");
+MODULE_AUTHOR("Guennadi Liakhovetski <g.liakhovetski@gmx.de>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 8cba1ae675f2b4662a62e8c83a4a172360bdf3ea Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 28 May 2018 12:37:08 -0400
Subject: media: i2c: rj54n1: Remove soc_camera dependencies

Remove soc_camera framework dependencies from rj54n1 sensor driver.
- Handle clock
- Handle GPIOs (named 'powerup' and 'enable')
- Register the async subdevice
- Remove g/s_mbus_config as they're deprecated.
- Adjust build system
- List the driver as maintained for 'Odd Fixes' as I don't have HW to test.

This commits does not remove the original soc_camera based driver.

Compiled tested only.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 MAINTAINERS                    |   8 +++
 drivers/media/i2c/Kconfig      |  11 +++
 drivers/media/i2c/Makefile     |   1 +
 drivers/media/i2c/rj54n1cb0c.c | 153 +++++++++++++++++++++++------------------
 4 files changed, 107 insertions(+), 66 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 6cfd16790add..5f4b8d14e75d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12845,6 +12845,14 @@ W:	http://www.ibm.com/developerworks/linux/linux390/
 S:	Supported
 F:	net/smc/
 
+SHARP RJ54N1CB0C SENSOR DRIVER
+M:	Jacopo Mondi <jacopo@jmondi.org>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Odd fixes
+F:	drivers/media/i2c/rj54n1cb0c.c
+F:	include/media/i2c/rj54n1cb0c.h
+
 SH_VEU V4L2 MEM2MEM DRIVER
 L:	linux-media@vger.kernel.org
 S:	Orphan
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 341452fe98df..1d5efef77e77 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -857,6 +857,17 @@ config VIDEO_NOON010PC30
 
 source "drivers/media/i2c/m5mols/Kconfig"
 
+config VIDEO_RJ54N1
+	tristate "Sharp RJ54N1CB0C sensor support"
+	depends on I2C && VIDEO_V4L2
+	depends on MEDIA_CAMERA_SUPPORT
+	help
+	  This is a V4L2 sensor-level driver for Sharp RJ54N1CB0C CMOS image
+	  sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called rj54n1.
+
 config VIDEO_S5K6AA
 	tristate "Samsung S5K6AAFX sensor support"
 	depends on MEDIA_CAMERA_SUPPORT
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index d679d57cd3b3..33cf2a415657 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -86,6 +86,7 @@ obj-$(CONFIG_VIDEO_MT9V011) += mt9v011.o
 obj-$(CONFIG_VIDEO_MT9V032) += mt9v032.o
 obj-$(CONFIG_VIDEO_SR030PC30)	+= sr030pc30.o
 obj-$(CONFIG_VIDEO_NOON010PC30)	+= noon010pc30.o
+obj-$(CONFIG_VIDEO_RJ54N1)	+= rj54n1cb0c.o
 obj-$(CONFIG_VIDEO_S5K6AA)	+= s5k6aa.o
 obj-$(CONFIG_VIDEO_S5K6A3)	+= s5k6a3.o
 obj-$(CONFIG_VIDEO_S5K4ECGX)	+= s5k4ecgx.o
diff --git a/drivers/media/i2c/rj54n1cb0c.c b/drivers/media/i2c/rj54n1cb0c.c
index 02398d0bc649..6ad998ad1b16 100644
--- a/drivers/media/i2c/rj54n1cb0c.c
+++ b/drivers/media/i2c/rj54n1cb0c.c
@@ -1,25 +1,25 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Driver for RJ54N1CB0C CMOS Image Sensor from Sharp
  *
- * Copyright (C) 2009, Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+ * Copyright (C) 2018, Jacopo Mondi <jacopo@jmondi.org>
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2009, Guennadi Liakhovetski <g.liakhovetski@gmx.de>
  */
 
+#include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
+#include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/v4l2-mediabus.h>
 #include <linux/videodev2.h>
-#include <linux/module.h>
 
 #include <media/i2c/rj54n1cb0c.h>
-#include <media/soc_camera.h>
-#include <media/v4l2-clk.h>
-#include <media/v4l2-subdev.h>
+#include <media/v4l2-device.h>
 #include <media/v4l2-ctrls.h>
+#include <media/v4l2-subdev.h>
 
 #define RJ54N1_DEV_CODE			0x0400
 #define RJ54N1_DEV_CODE2		0x0401
@@ -151,7 +151,9 @@ struct rj54n1_clock_div {
 struct rj54n1 {
 	struct v4l2_subdev subdev;
 	struct v4l2_ctrl_handler hdl;
-	struct v4l2_clk *clk;
+	struct clk *clk;
+	struct gpio_desc *pwup_gpio;
+	struct gpio_desc *enable_gpio;
 	struct rj54n1_clock_div clk_div;
 	const struct rj54n1_datafmt *fmt;
 	struct v4l2_rect rect;	/* Sensor window */
@@ -545,8 +547,7 @@ static int rj54n1_set_selection(struct v4l2_subdev *sd,
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct rj54n1 *rj54n1 = to_rj54n1(client);
 	const struct v4l2_rect *rect = &sel->r;
-	int dummy = 0, output_w, output_h,
-		input_w = rect->width, input_h = rect->height;
+	int output_w, output_h, input_w = rect->width, input_h = rect->height;
 	int ret;
 
 	if (sel->which != V4L2_SUBDEV_FORMAT_ACTIVE ||
@@ -554,11 +555,8 @@ static int rj54n1_set_selection(struct v4l2_subdev *sd,
 		return -EINVAL;
 
 	/* arbitrary minimum width and height, edges unimportant */
-	soc_camera_limit_side(&dummy, &input_w,
-		     RJ54N1_COLUMN_SKIP, 8, RJ54N1_MAX_WIDTH);
-
-	soc_camera_limit_side(&dummy, &input_h,
-		     RJ54N1_ROW_SKIP, 8, RJ54N1_MAX_HEIGHT);
+	v4l_bound_align_image(&input_w, 8, RJ54N1_MAX_WIDTH, 0,
+			      &input_h, 8, RJ54N1_MAX_HEIGHT, 0, 0);
 
 	output_w = (input_w * 1024 + rj54n1->resize / 2) / rj54n1->resize;
 	output_h = (input_h * 1024 + rj54n1->resize / 2) / rj54n1->resize;
@@ -618,6 +616,9 @@ static int rj54n1_get_fmt(struct v4l2_subdev *sd,
 
 	mf->code	= rj54n1->fmt->code;
 	mf->colorspace	= rj54n1->fmt->colorspace;
+	mf->ycbcr_enc	= V4L2_YCBCR_ENC_601;
+	mf->xfer_func	= V4L2_XFER_FUNC_SRGB;
+	mf->quantization = V4L2_QUANTIZATION_DEFAULT;
 	mf->field	= V4L2_FIELD_NONE;
 	mf->width	= rj54n1->width;
 	mf->height	= rj54n1->height;
@@ -1163,10 +1164,27 @@ static int rj54n1_s_register(struct v4l2_subdev *sd,
 static int rj54n1_s_power(struct v4l2_subdev *sd, int on)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
-	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
 	struct rj54n1 *rj54n1 = to_rj54n1(client);
 
-	return soc_camera_set_power(&client->dev, ssdd, rj54n1->clk, on);
+	if (on) {
+		if (rj54n1->pwup_gpio)
+			gpiod_set_value(rj54n1->pwup_gpio, 1);
+		if (rj54n1->enable_gpio)
+			gpiod_set_value(rj54n1->enable_gpio, 1);
+
+		msleep(1);
+
+		return clk_prepare_enable(rj54n1->clk);
+	}
+
+	clk_disable_unprepare(rj54n1->clk);
+
+	if (rj54n1->enable_gpio)
+		gpiod_set_value(rj54n1->enable_gpio, 0);
+	if (rj54n1->pwup_gpio)
+		gpiod_set_value(rj54n1->pwup_gpio, 0);
+
+	return 0;
 }
 
 static int rj54n1_s_ctrl(struct v4l2_ctrl *ctrl)
@@ -1221,40 +1239,8 @@ static const struct v4l2_subdev_core_ops rj54n1_subdev_core_ops = {
 	.s_power	= rj54n1_s_power,
 };
 
-static int rj54n1_g_mbus_config(struct v4l2_subdev *sd,
-				struct v4l2_mbus_config *cfg)
-{
-	struct i2c_client *client = v4l2_get_subdevdata(sd);
-	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
-
-	cfg->flags =
-		V4L2_MBUS_PCLK_SAMPLE_RISING | V4L2_MBUS_PCLK_SAMPLE_FALLING |
-		V4L2_MBUS_MASTER | V4L2_MBUS_DATA_ACTIVE_HIGH |
-		V4L2_MBUS_HSYNC_ACTIVE_HIGH | V4L2_MBUS_VSYNC_ACTIVE_HIGH;
-	cfg->type = V4L2_MBUS_PARALLEL;
-	cfg->flags = soc_camera_apply_board_flags(ssdd, cfg);
-
-	return 0;
-}
-
-static int rj54n1_s_mbus_config(struct v4l2_subdev *sd,
-				const struct v4l2_mbus_config *cfg)
-{
-	struct i2c_client *client = v4l2_get_subdevdata(sd);
-	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
-
-	/* Figures 2.5-1 to 2.5-3 - default falling pixclk edge */
-	if (soc_camera_apply_board_flags(ssdd, cfg) &
-	    V4L2_MBUS_PCLK_SAMPLE_RISING)
-		return reg_write(client, RJ54N1_OUT_SIGPO, 1 << 4);
-	else
-		return reg_write(client, RJ54N1_OUT_SIGPO, 0);
-}
-
 static const struct v4l2_subdev_video_ops rj54n1_subdev_video_ops = {
 	.s_stream	= rj54n1_s_stream,
-	.g_mbus_config	= rj54n1_g_mbus_config,
-	.s_mbus_config	= rj54n1_s_mbus_config,
 };
 
 static const struct v4l2_subdev_pad_ops rj54n1_subdev_pad_ops = {
@@ -1316,17 +1302,16 @@ static int rj54n1_probe(struct i2c_client *client,
 			const struct i2c_device_id *did)
 {
 	struct rj54n1 *rj54n1;
-	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
-	struct i2c_adapter *adapter = to_i2c_adapter(client->dev.parent);
+	struct i2c_adapter *adapter = client->adapter;
 	struct rj54n1_pdata *rj54n1_priv;
 	int ret;
 
-	if (!ssdd || !ssdd->drv_priv) {
+	if (!client->dev.platform_data) {
 		dev_err(&client->dev, "RJ54N1CB0C: missing platform data!\n");
 		return -EINVAL;
 	}
 
-	rj54n1_priv = ssdd->drv_priv;
+	rj54n1_priv = client->dev.platform_data;
 
 	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
 		dev_warn(&adapter->dev,
@@ -1364,32 +1349,68 @@ static int rj54n1_probe(struct i2c_client *client,
 	rj54n1->tgclk_mhz	= (rj54n1_priv->mclk_freq / PLL_L * PLL_N) /
 		(clk_div.ratio_tg + 1) / (clk_div.ratio_t + 1);
 
-	rj54n1->clk = v4l2_clk_get(&client->dev, "mclk");
+	rj54n1->clk = clk_get(&client->dev, NULL);
 	if (IS_ERR(rj54n1->clk)) {
 		ret = PTR_ERR(rj54n1->clk);
-		goto eclkget;
+		goto err_free_ctrl;
 	}
 
-	ret = rj54n1_video_probe(client, rj54n1_priv);
-	if (ret < 0) {
-		v4l2_clk_put(rj54n1->clk);
-eclkget:
-		v4l2_ctrl_handler_free(&rj54n1->hdl);
+	rj54n1->pwup_gpio = gpiod_get_optional(&client->dev, "powerup",
+					       GPIOD_OUT_LOW);
+	if (IS_ERR(rj54n1->pwup_gpio)) {
+		dev_info(&client->dev, "Unable to get GPIO \"powerup\": %ld\n",
+			 PTR_ERR(rj54n1->pwup_gpio));
+		ret = PTR_ERR(rj54n1->pwup_gpio);
+		goto err_clk_put;
+	}
+
+	rj54n1->enable_gpio = gpiod_get_optional(&client->dev, "enable",
+						 GPIOD_OUT_LOW);
+	if (IS_ERR(rj54n1->enable_gpio)) {
+		dev_info(&client->dev, "Unable to get GPIO \"enable\": %ld\n",
+			 PTR_ERR(rj54n1->enable_gpio));
+		ret = PTR_ERR(rj54n1->enable_gpio);
+		goto err_gpio_put;
 	}
 
+	ret = rj54n1_video_probe(client, rj54n1_priv);
+	if (ret < 0)
+		goto err_gpio_put;
+
+	ret = v4l2_async_register_subdev(&rj54n1->subdev);
+	if (ret)
+		goto err_gpio_put;
+
+	return 0;
+
+err_gpio_put:
+	if (rj54n1->enable_gpio)
+		gpiod_put(rj54n1->enable_gpio);
+
+	if (rj54n1->pwup_gpio)
+		gpiod_put(rj54n1->pwup_gpio);
+
+err_clk_put:
+	clk_put(rj54n1->clk);
+
+err_free_ctrl:
+	v4l2_ctrl_handler_free(&rj54n1->hdl);
+
 	return ret;
 }
 
 static int rj54n1_remove(struct i2c_client *client)
 {
 	struct rj54n1 *rj54n1 = to_rj54n1(client);
-	struct soc_camera_subdev_desc *ssdd = soc_camera_i2c_to_desc(client);
 
-	v4l2_clk_put(rj54n1->clk);
-	v4l2_device_unregister_subdev(&rj54n1->subdev);
-	if (ssdd->free_bus)
-		ssdd->free_bus(ssdd);
+	if (rj54n1->enable_gpio)
+		gpiod_put(rj54n1->enable_gpio);
+	if (rj54n1->pwup_gpio)
+		gpiod_put(rj54n1->pwup_gpio);
+
+	clk_put(rj54n1->clk);
 	v4l2_ctrl_handler_free(&rj54n1->hdl);
+	v4l2_async_unregister_subdev(&rj54n1->subdev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From f3590dc329744dc8426dc9c76e37f4bd27ca8594 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 28 May 2018 12:37:09 -0400
Subject: media: arch: sh: kfr2r09: Use new renesas-ceu camera driver

Use the new renesas-ceu camera driver in kfr2r09 board file instead of
the soc_camera based sh_mobile_ceu_camera driver.

Get rid of soc_camera specific components, and move clk and gpio handling
away from board file, registering the clock source and the enable gpios
for driver consumption.

Memory for the CEU video buffers is now reserved with membocks APIs,
and need to be declared as dma_coherent during machine initialization to
remove that architecture specific part from CEU driver.

While at there update license to SPDX header and sort headers alphabetically.

No need to udapte the clock source names, as
commit c2f9b05fd5c1 ("media: arch: sh: ecovec: Use new renesas-ceu camera driver")
already updated it to the new ceu driver name for all SH7724 boards (possibly
breaking kfr2r09 before this commit).

Compile tested only.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 arch/sh/boards/mach-kfr2r09/setup.c | 217 +++++++++++++++++-------------------
 1 file changed, 103 insertions(+), 114 deletions(-)

diff --git a/arch/sh/boards/mach-kfr2r09/setup.c b/arch/sh/boards/mach-kfr2r09/setup.c
index 6af7777332fc..e59c577ed871 100644
--- a/arch/sh/boards/mach-kfr2r09/setup.c
+++ b/arch/sh/boards/mach-kfr2r09/setup.c
@@ -1,41 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * KFR2R09 board support code
  *
  * Copyright (C) 2009 Magnus Damm
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
  */
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/interrupt.h>
-#include <linux/mmc/host.h>
-#include <linux/mfd/tmio.h>
-#include <linux/mtd/physmap.h>
-#include <linux/mtd/onenand.h>
+
+#include <asm/clock.h>
+#include <asm/io.h>
+#include <asm/machvec.h>
+#include <asm/suspend.h>
+
+#include <cpu/sh7724.h>
+
+#include <linux/clkdev.h>
 #include <linux/delay.h>
-#include <linux/clk.h>
+#include <linux/dma-mapping.h>
 #include <linux/gpio.h>
+#include <linux/gpio/machine.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
 #include <linux/input.h>
 #include <linux/input/sh_keysc.h>
-#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/memblock.h>
+#include <linux/mfd/tmio.h>
+#include <linux/mmc/host.h>
+#include <linux/mtd/onenand.h>
+#include <linux/mtd/physmap.h>
 #include <linux/platform_data/lv5207lp.h>
+#include <linux/platform_device.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
+#include <linux/sh_intc.h>
 #include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
-#include <linux/sh_intc.h>
+
+#include <mach/kfr2r09.h>
+
+#include <media/drv-intf/renesas-ceu.h>
 #include <media/i2c/rj54n1cb0c.h>
-#include <media/soc_camera.h>
-#include <media/drv-intf/sh_mobile_ceu.h>
+
 #include <video/sh_mobile_lcdc.h>
-#include <asm/suspend.h>
-#include <asm/clock.h>
-#include <asm/machvec.h>
-#include <asm/io.h>
-#include <cpu/sh7724.h>
-#include <mach/kfr2r09.h>
+
+#define CEU_BUFFER_MEMORY_SIZE		(4 << 20)
+static phys_addr_t ceu_dma_membase;
+
+/* set VIO_CKO clock to 25MHz */
+#define CEU_MCLK_FREQ			25000000
+#define DRVCRB				0xA405018C
 
 static struct mtd_partition kfr2r09_nor_flash_partitions[] =
 {
@@ -230,8 +242,17 @@ static struct platform_device kfr2r09_usb0_gadget_device = {
 	.resource	= kfr2r09_usb0_gadget_resources,
 };
 
-static struct sh_mobile_ceu_info sh_mobile_ceu_info = {
-	.flags = SH_CEU_FLAG_USE_8BIT_BUS,
+static struct ceu_platform_data ceu_pdata = {
+	.num_subdevs			= 1,
+	.subdevs = {
+		{ /* [0] = rj54n1cb0c */
+			.flags		= 0,
+			.bus_width	= 8,
+			.bus_shift	= 0,
+			.i2c_adapter_id	= 1,
+			.i2c_address	= 0x50,
+		},
+	},
 };
 
 static struct resource kfr2r09_ceu_resources[] = {
@@ -246,109 +267,35 @@ static struct resource kfr2r09_ceu_resources[] = {
 		.end	= evt2irq(0x880),
 		.flags  = IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* place holder for contiguous memory */
-	},
 };
 
 static struct platform_device kfr2r09_ceu_device = {
-	.name		= "sh_mobile_ceu",
+	.name		= "renesas-ceu",
 	.id             = 0, /* "ceu0" clock */
 	.num_resources	= ARRAY_SIZE(kfr2r09_ceu_resources),
 	.resource	= kfr2r09_ceu_resources,
 	.dev	= {
-		.platform_data	= &sh_mobile_ceu_info,
+		.platform_data	= &ceu_pdata,
 	},
 };
 
-static struct i2c_board_info kfr2r09_i2c_camera = {
-	I2C_BOARD_INFO("rj54n1cb0c", 0x50),
-};
-
-static struct clk *camera_clk;
-
-/* set VIO_CKO clock to 25MHz */
-#define CEU_MCLK_FREQ 25000000
-
-#define DRVCRB 0xA405018C
-static int camera_power(struct device *dev, int mode)
-{
-	int ret;
-
-	if (mode) {
-		long rate;
-
-		camera_clk = clk_get(NULL, "video_clk");
-		if (IS_ERR(camera_clk))
-			return PTR_ERR(camera_clk);
-
-		rate = clk_round_rate(camera_clk, CEU_MCLK_FREQ);
-		ret = clk_set_rate(camera_clk, rate);
-		if (ret < 0)
-			goto eclkrate;
-
-		/* set DRVCRB
-		 *
-		 * use 1.8 V for VccQ_VIO
-		 * use 2.85V for VccQ_SR
-		 */
-		__raw_writew((__raw_readw(DRVCRB) & ~0x0003) | 0x0001, DRVCRB);
-
-		/* reset clear */
-		ret = gpio_request(GPIO_PTB4, NULL);
-		if (ret < 0)
-			goto eptb4;
-		ret = gpio_request(GPIO_PTB7, NULL);
-		if (ret < 0)
-			goto eptb7;
-
-		ret = gpio_direction_output(GPIO_PTB4, 1);
-		if (!ret)
-			ret = gpio_direction_output(GPIO_PTB7, 1);
-		if (ret < 0)
-			goto egpioout;
-		msleep(1);
-
-		ret = clk_enable(camera_clk);	/* start VIO_CKO */
-		if (ret < 0)
-			goto eclkon;
-
-		return 0;
-	}
-
-	ret = 0;
-
-	clk_disable(camera_clk);
-eclkon:
-	gpio_set_value(GPIO_PTB7, 0);
-egpioout:
-	gpio_set_value(GPIO_PTB4, 0);
-	gpio_free(GPIO_PTB7);
-eptb7:
-	gpio_free(GPIO_PTB4);
-eptb4:
-eclkrate:
-	clk_put(camera_clk);
-	return ret;
-}
-
 static struct rj54n1_pdata rj54n1_priv = {
 	.mclk_freq	= CEU_MCLK_FREQ,
 	.ioctl_high	= false,
 };
 
-static struct soc_camera_link rj54n1_link = {
-	.power		= camera_power,
-	.board_info	= &kfr2r09_i2c_camera,
-	.i2c_adapter_id	= 1,
-	.priv		= &rj54n1_priv,
+static struct i2c_board_info kfr2r09_i2c_camera = {
+	I2C_BOARD_INFO("rj54n1cb0c", 0x50),
+	.platform_data = &rj54n1_priv,
 };
 
-static struct platform_device kfr2r09_camera = {
-	.name	= "soc-camera-pdrv",
-	.id	= 0,
-	.dev	= {
-		.platform_data = &rj54n1_link,
+static struct gpiod_lookup_table rj54n1_gpios = {
+	.dev_id		= "1-0050",
+	.table		= {
+		GPIO_LOOKUP("sh7724_pfc", GPIO_PTB4, "poweron",
+			    GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("sh7724_pfc", GPIO_PTB7, "enable",
+			    GPIO_ACTIVE_HIGH),
 	},
 };
 
@@ -393,8 +340,6 @@ static struct platform_device *kfr2r09_devices[] __initdata = {
 	&kfr2r09_nand_flash_device,
 	&kfr2r09_sh_keysc_device,
 	&kfr2r09_sh_lcdc_device,
-	&kfr2r09_ceu_device,
-	&kfr2r09_camera,
 	&kfr2r09_sh_sdhi0_device,
 };
 
@@ -533,6 +478,8 @@ extern char kfr2r09_sdram_leave_end;
 
 static int __init kfr2r09_devices_setup(void)
 {
+	static struct clk *camera_clk;
+
 	/* register board specific self-refresh code */
 	sh_mobile_register_self_refresh(SUSP_SH_STANDBY | SUSP_SH_SF |
 					SUSP_SH_RSTANDBY,
@@ -622,8 +569,6 @@ static int __init kfr2r09_devices_setup(void)
 	gpio_request(GPIO_FN_VIO0_D1, NULL);
 	gpio_request(GPIO_FN_VIO0_D0, NULL);
 
-	platform_resource_setup_memory(&kfr2r09_ceu_device, "ceu", 4 << 20);
-
 	/* SDHI0 connected to yc304 */
 	gpio_request(GPIO_FN_SDHI0CD, NULL);
 	gpio_request(GPIO_FN_SDHI0D3, NULL);
@@ -635,6 +580,36 @@ static int __init kfr2r09_devices_setup(void)
 
 	i2c_register_board_info(0, &kfr2r09_backlight_board_info, 1);
 
+	/* Set camera clock frequency and register and alias for rj54n1. */
+	camera_clk = clk_get(NULL, "video_clk");
+	if (!IS_ERR(camera_clk)) {
+		clk_set_rate(camera_clk,
+			     clk_round_rate(camera_clk, CEU_MCLK_FREQ));
+		clk_put(camera_clk);
+	}
+	clk_add_alias(NULL, "1-0050", "video_clk", NULL);
+
+	/* set DRVCRB
+	 *
+	 * use 1.8 V for VccQ_VIO
+	 * use 2.85V for VccQ_SR
+	 */
+	__raw_writew((__raw_readw(DRVCRB) & ~0x0003) | 0x0001, DRVCRB);
+
+	gpiod_add_lookup_table(&rj54n1_gpios);
+
+	i2c_register_board_info(1, &kfr2r09_i2c_camera, 1);
+
+	/* Initialize CEU platform device separately to map memory first */
+	device_initialize(&kfr2r09_ceu_device.dev);
+	arch_setup_pdev_archdata(&kfr2r09_ceu_device);
+	dma_declare_coherent_memory(&kfr2r09_ceu_device.dev,
+				    ceu_dma_membase, ceu_dma_membase,
+				    ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1,
+				    DMA_MEMORY_EXCLUSIVE);
+
+	platform_device_add(&kfr2r09_ceu_device);
+
 	return platform_add_devices(kfr2r09_devices,
 				    ARRAY_SIZE(kfr2r09_devices));
 }
@@ -651,10 +626,24 @@ static int kfr2r09_mode_pins(void)
 	return MODE_PIN0 | MODE_PIN1 | MODE_PIN5 | MODE_PIN8;
 }
 
+/* Reserve a portion of memory for CEU buffers */
+static void __init kfr2r09_mv_mem_reserve(void)
+{
+	phys_addr_t phys;
+	phys_addr_t size = CEU_BUFFER_MEMORY_SIZE;
+
+	phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE);
+	memblock_free(phys, size);
+	memblock_remove(phys, size);
+
+	ceu_dma_membase = phys;
+}
+
 /*
  * The Machine Vector
  */
 static struct sh_machine_vector mv_kfr2r09 __initmv = {
 	.mv_name		= "kfr2r09",
 	.mv_mode_pins		= kfr2r09_mode_pins,
+	.mv_mem_reserve         = kfr2r09_mv_mem_reserve,
 };
-- 
cgit v1.2.3


From 1a3c230b415169b7110a5d937145a56fc12b13bf Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 28 May 2018 12:37:10 -0400
Subject: media: arch: sh: ms7724se: Use new renesas-ceu camera driver

Use the new renesas-ceu camera driver is ms7724se board file instead of
the soc_camera based sh_mobile_ceu_camera driver.

Get rid of soc_camera specific components, and register CEU0 and CEU1 with
no active video subdevices.

Memory for the CEU video buffers is now reserved with membocks APIs
and need to be declared as dma_coherent during machine initialization to
remove that architecture specific part from CEU driver.

While at there update license to SPDX header and sort headers
alphabetically.

No need to udapte the clock source names, as
commit c2f9b05fd5c1 ("media: arch: sh: ecovec: Use new renesas-ceu camera driver")
already updated it to the new ceu driver name for all SH7724 boards
(possibly breaking ms7724se before this commit).

Compile tested only.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 arch/sh/boards/mach-se/7724/setup.c | 120 ++++++++++++++++++++++++------------
 1 file changed, 79 insertions(+), 41 deletions(-)

diff --git a/arch/sh/boards/mach-se/7724/setup.c b/arch/sh/boards/mach-se/7724/setup.c
index 255952555656..fdbec22ae687 100644
--- a/arch/sh/boards/mach-se/7724/setup.c
+++ b/arch/sh/boards/mach-se/7724/setup.c
@@ -1,43 +1,49 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * linux/arch/sh/boards/se/7724/setup.c
  *
  * Copyright (C) 2009 Renesas Solutions Corp.
  *
  * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
  */
+#include <asm/clock.h>
+#include <asm/heartbeat.h>
+#include <asm/io.h>
+#include <asm/suspend.h>
 
-#include <linux/init.h>
+#include <cpu/sh7724.h>
+
+#include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/gpio.h>
+#include <linux/init.h>
+#include <linux/input.h>
+#include <linux/input/sh_keysc.h>
 #include <linux/interrupt.h>
-#include <linux/platform_device.h>
-#include <linux/mmc/host.h>
+#include <linux/memblock.h>
 #include <linux/mfd/tmio.h>
+#include <linux/mmc/host.h>
 #include <linux/mtd/physmap.h>
-#include <linux/delay.h>
+#include <linux/platform_device.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
-#include <linux/smc91x.h>
-#include <linux/gpio.h>
-#include <linux/input.h>
-#include <linux/input/sh_keysc.h>
-#include <linux/usb/r8a66597.h>
 #include <linux/sh_eth.h>
 #include <linux/sh_intc.h>
+#include <linux/smc91x.h>
+#include <linux/usb/r8a66597.h>
 #include <linux/videodev2.h>
-#include <video/sh_mobile_lcdc.h>
-#include <media/drv-intf/sh_mobile_ceu.h>
+
+#include <mach-se/mach/se7724.h>
+#include <media/drv-intf/renesas-ceu.h>
+
 #include <sound/sh_fsi.h>
 #include <sound/simple_card.h>
-#include <asm/io.h>
-#include <asm/heartbeat.h>
-#include <asm/clock.h>
-#include <asm/suspend.h>
-#include <cpu/sh7724.h>
-#include <mach-se/mach/se7724.h>
+
+#include <video/sh_mobile_lcdc.h>
+
+#define CEU_BUFFER_MEMORY_SIZE		(4 << 20)
+static phys_addr_t ceu0_dma_membase;
+static phys_addr_t ceu1_dma_membase;
 
 /*
  * SWx    1234 5678
@@ -216,8 +222,8 @@ static struct platform_device lcdc_device = {
 };
 
 /* CEU0 */
-static struct sh_mobile_ceu_info sh_mobile_ceu0_info = {
-	.flags = SH_CEU_FLAG_USE_8BIT_BUS,
+static struct ceu_platform_data ceu0_pdata = {
+	.num_subdevs = 0,
 };
 
 static struct resource ceu0_resources[] = {
@@ -231,24 +237,21 @@ static struct resource ceu0_resources[] = {
 		.start  = evt2irq(0x880),
 		.flags  = IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* place holder for contiguous memory */
-	},
 };
 
 static struct platform_device ceu0_device = {
-	.name		= "sh_mobile_ceu",
-	.id             = 0, /* "ceu0" clock */
+	.name		= "renesas-ceu",
+	.id             = 0, /* "ceu.0" clock */
 	.num_resources	= ARRAY_SIZE(ceu0_resources),
 	.resource	= ceu0_resources,
 	.dev	= {
-		.platform_data	= &sh_mobile_ceu0_info,
+		.platform_data	= &ceu0_pdata,
 	},
 };
 
 /* CEU1 */
-static struct sh_mobile_ceu_info sh_mobile_ceu1_info = {
-	.flags = SH_CEU_FLAG_USE_8BIT_BUS,
+static struct ceu_platform_data ceu1_pdata = {
+	.num_subdevs = 0,
 };
 
 static struct resource ceu1_resources[] = {
@@ -262,18 +265,15 @@ static struct resource ceu1_resources[] = {
 		.start  = evt2irq(0x9e0),
 		.flags  = IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* place holder for contiguous memory */
-	},
 };
 
 static struct platform_device ceu1_device = {
-	.name		= "sh_mobile_ceu",
-	.id             = 1, /* "ceu1" clock */
+	.name		= "renesas-ceu",
+	.id             = 1, /* "ceu.1" clock */
 	.num_resources	= ARRAY_SIZE(ceu1_resources),
 	.resource	= ceu1_resources,
 	.dev	= {
-		.platform_data	= &sh_mobile_ceu1_info,
+		.platform_data	= &ceu1_pdata,
 	},
 };
 
@@ -574,13 +574,16 @@ static struct platform_device vou_device = {
 	},
 };
 
+static struct platform_device *ms7724se_ceu_devices[] __initdata = {
+	&ceu0_device,
+	&ceu1_device,
+};
+
 static struct platform_device *ms7724se_devices[] __initdata = {
 	&heartbeat_device,
 	&smc91x_eth_device,
 	&lcdc_device,
 	&nor_flash_device,
-	&ceu0_device,
-	&ceu1_device,
 	&keysc_device,
 	&sh_eth_device,
 	&sh7724_usb0_host_device,
@@ -797,7 +800,6 @@ static int __init devices_setup(void)
 	gpio_request(GPIO_FN_VIO0_CLK, NULL);
 	gpio_request(GPIO_FN_VIO0_FLD, NULL);
 	gpio_request(GPIO_FN_VIO0_HD,  NULL);
-	platform_resource_setup_memory(&ceu0_device, "ceu0", 4 << 20);
 
 	/* enable CEU1 */
 	gpio_request(GPIO_FN_VIO1_D7,  NULL);
@@ -812,7 +814,6 @@ static int __init devices_setup(void)
 	gpio_request(GPIO_FN_VIO1_HD,  NULL);
 	gpio_request(GPIO_FN_VIO1_VD,  NULL);
 	gpio_request(GPIO_FN_VIO1_CLK, NULL);
-	platform_resource_setup_memory(&ceu1_device, "ceu1", 4 << 20);
 
 	/* KEYSC */
 	gpio_request(GPIO_FN_KEYOUT5_IN5, NULL);
@@ -934,12 +935,49 @@ static int __init devices_setup(void)
 	gpio_request(GPIO_FN_DV_VSYNC, NULL);
 	gpio_request(GPIO_FN_DV_HSYNC, NULL);
 
+	/* Initialize CEU platform devices separately to map memory first */
+	device_initialize(&ms7724se_ceu_devices[0]->dev);
+	arch_setup_pdev_archdata(ms7724se_ceu_devices[0]);
+	dma_declare_coherent_memory(&ms7724se_ceu_devices[0]->dev,
+				    ceu0_dma_membase, ceu0_dma_membase,
+				    ceu0_dma_membase +
+				    CEU_BUFFER_MEMORY_SIZE - 1,
+				    DMA_MEMORY_EXCLUSIVE);
+	platform_device_add(ms7724se_ceu_devices[0]);
+
+	device_initialize(&ms7724se_ceu_devices[1]->dev);
+	arch_setup_pdev_archdata(ms7724se_ceu_devices[1]);
+	dma_declare_coherent_memory(&ms7724se_ceu_devices[1]->dev,
+				    ceu1_dma_membase, ceu1_dma_membase,
+				    ceu1_dma_membase +
+				    CEU_BUFFER_MEMORY_SIZE - 1,
+				    DMA_MEMORY_EXCLUSIVE);
+	platform_device_add(ms7724se_ceu_devices[1]);
+
 	return platform_add_devices(ms7724se_devices,
 				    ARRAY_SIZE(ms7724se_devices));
 }
 device_initcall(devices_setup);
 
+/* Reserve a portion of memory for CEU 0 and CEU 1 buffers */
+static void __init ms7724se_mv_mem_reserve(void)
+{
+	phys_addr_t phys;
+	phys_addr_t size = CEU_BUFFER_MEMORY_SIZE;
+
+	phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE);
+	memblock_free(phys, size);
+	memblock_remove(phys, size);
+	ceu0_dma_membase = phys;
+
+	phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE);
+	memblock_free(phys, size);
+	memblock_remove(phys, size);
+	ceu1_dma_membase = phys;
+}
+
 static struct sh_machine_vector mv_ms7724se __initmv = {
 	.mv_name	= "ms7724se",
 	.mv_init_irq	= init_se7724_IRQ,
+	.mv_mem_reserve	= ms7724se_mv_mem_reserve,
 };
-- 
cgit v1.2.3


From 39fb993038e158d4cbba47f6dbda6fe77a0e8cb9 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 28 May 2018 12:37:11 -0400
Subject: media: arch: sh: ap325rxa: Use new renesas-ceu camera driver

Use the new renesas-ceu camera driver in ap325rxa board file instead of
the soc_camera based sh_mobile_ceu_camera driver.

Get rid of soc_camera specific components, and register CEU0 with a single
video sensor (ov7725).

Memory for the CEU video buffers is now reserved with membocks APIs
and need to be declared as dma_coherent during machine initialization to
remove that architecture specific part from CEU driver.

The ap325rxa board file registers another camera (ncm03j) for which I found no
driver in mainline kernel version, and that was configured/probed by sending
i2c messages (of 'magic blobs) from the board file itself. I removed the
sensor registration from this new version as it used soc_camera components
that will be later removed.

While at there update license to SPDX header and sort headers alphabetically.

Compile tested only.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 arch/sh/boards/mach-ap325rxa/setup.c   | 282 +++++++++------------------------
 arch/sh/kernel/cpu/sh4a/clock-sh7723.c |   2 +-
 2 files changed, 80 insertions(+), 204 deletions(-)

diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index de8393cb7313..8f234d0435aa 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -1,40 +1,45 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Renesas - AP-325RXA
  * (Compatible with Algo System ., LTD. - AP-320A)
  *
  * Copyright (C) 2008 Renesas Solutions Corp.
  * Author : Yusuke Goda <goda.yuske@renesas.com>
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
  */
 
-#include <linux/init.h>
+#include <asm/clock.h>
+#include <asm/io.h>
+#include <asm/suspend.h>
+
+#include <cpu/sh7723.h>
+
+#include <linux/clkdev.h>
+#include <linux/delay.h>
 #include <linux/device.h>
+#include <linux/gpio.h>
+#include <linux/gpio/machine.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
 #include <linux/interrupt.h>
-#include <linux/platform_device.h>
+#include <linux/memblock.h>
+#include <linux/mfd/tmio.h>
 #include <linux/mmc/host.h>
 #include <linux/mtd/physmap.h>
 #include <linux/mtd/sh_flctl.h>
-#include <linux/mfd/tmio.h>
-#include <linux/delay.h>
-#include <linux/i2c.h>
+#include <linux/platform_device.h>
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
+#include <linux/sh_intc.h>
 #include <linux/smsc911x.h>
-#include <linux/gpio.h>
 #include <linux/videodev2.h>
-#include <linux/sh_intc.h>
+
+#include <media/drv-intf/renesas-ceu.h>
 #include <media/i2c/ov772x.h>
-#include <media/soc_camera.h>
-#include <linux/platform_data/media/soc_camera_platform.h>
-#include <media/drv-intf/sh_mobile_ceu.h>
+
 #include <video/sh_mobile_lcdc.h>
-#include <asm/io.h>
-#include <asm/clock.h>
-#include <asm/suspend.h>
-#include <cpu/sh7723.h>
+
+#define CEU_BUFFER_MEMORY_SIZE		(4 << 20)
+static phys_addr_t ceu_dma_membase;
 
 /* Dummy supplies, where voltage doesn't matter */
 static struct regulator_consumer_supply dummy_supplies[] = {
@@ -253,150 +258,25 @@ static struct platform_device lcdc_device = {
 	},
 };
 
-static void camera_power(int val)
-{
-	gpio_set_value(GPIO_PTZ5, val); /* RST_CAM/RSTB */
-	mdelay(10);
-}
-
-#ifdef CONFIG_I2C
-/* support for the old ncm03j camera */
-static unsigned char camera_ncm03j_magic[] =
-{
-	0x87, 0x00, 0x88, 0x08, 0x89, 0x01, 0x8A, 0xE8,
-	0x1D, 0x00, 0x1E, 0x8A, 0x21, 0x00, 0x33, 0x36,
-	0x36, 0x60, 0x37, 0x08, 0x3B, 0x31, 0x44, 0x0F,
-	0x46, 0xF0, 0x4B, 0x28, 0x4C, 0x21, 0x4D, 0x55,
-	0x4E, 0x1B, 0x4F, 0xC7, 0x50, 0xFC, 0x51, 0x12,
-	0x58, 0x02, 0x66, 0xC0, 0x67, 0x46, 0x6B, 0xA0,
-	0x6C, 0x34, 0x7E, 0x25, 0x7F, 0x25, 0x8D, 0x0F,
-	0x92, 0x40, 0x93, 0x04, 0x94, 0x26, 0x95, 0x0A,
-	0x99, 0x03, 0x9A, 0xF0, 0x9B, 0x14, 0x9D, 0x7A,
-	0xC5, 0x02, 0xD6, 0x07, 0x59, 0x00, 0x5A, 0x1A,
-	0x5B, 0x2A, 0x5C, 0x37, 0x5D, 0x42, 0x5E, 0x56,
-	0xC8, 0x00, 0xC9, 0x1A, 0xCA, 0x2A, 0xCB, 0x37,
-	0xCC, 0x42, 0xCD, 0x56, 0xCE, 0x00, 0xCF, 0x1A,
-	0xD0, 0x2A, 0xD1, 0x37, 0xD2, 0x42, 0xD3, 0x56,
-	0x5F, 0x68, 0x60, 0x87, 0x61, 0xA3, 0x62, 0xBC,
-	0x63, 0xD4, 0x64, 0xEA, 0xD6, 0x0F,
-};
-
-static int camera_probe(void)
-{
-	struct i2c_adapter *a = i2c_get_adapter(0);
-	struct i2c_msg msg;
-	int ret;
-
-	if (!a)
-		return -ENODEV;
-
-	camera_power(1);
-	msg.addr = 0x6e;
-	msg.buf = camera_ncm03j_magic;
-	msg.len = 2;
-	msg.flags = 0;
-	ret = i2c_transfer(a, &msg, 1);
-	camera_power(0);
-
-	return ret;
-}
-
-static int camera_set_capture(struct soc_camera_platform_info *info,
-			      int enable)
-{
-	struct i2c_adapter *a = i2c_get_adapter(0);
-	struct i2c_msg msg;
-	int ret = 0;
-	int i;
-
-	camera_power(0);
-	if (!enable)
-		return 0; /* no disable for now */
-
-	camera_power(1);
-	for (i = 0; i < ARRAY_SIZE(camera_ncm03j_magic); i += 2) {
-		u_int8_t buf[8];
-
-		msg.addr = 0x6e;
-		msg.buf = buf;
-		msg.len = 2;
-		msg.flags = 0;
-
-		buf[0] = camera_ncm03j_magic[i];
-		buf[1] = camera_ncm03j_magic[i + 1];
-
-		ret = (ret < 0) ? ret : i2c_transfer(a, &msg, 1);
-	}
-
-	return ret;
-}
-
-static int ap325rxa_camera_add(struct soc_camera_device *icd);
-static void ap325rxa_camera_del(struct soc_camera_device *icd);
-
-static struct soc_camera_platform_info camera_info = {
-	.format_name = "UYVY",
-	.format_depth = 16,
-	.format = {
-		.code = MEDIA_BUS_FMT_UYVY8_2X8,
-		.colorspace = V4L2_COLORSPACE_SMPTE170M,
-		.field = V4L2_FIELD_NONE,
-		.width = 640,
-		.height = 480,
+/* Powerdown/reset gpios for CEU image sensors */
+static struct gpiod_lookup_table ov7725_gpios = {
+	.dev_id		= "0-0021",
+	.table		= {
+		GPIO_LOOKUP("sh7723_pfc", GPIO_PTZ5, "reset", GPIO_ACTIVE_LOW),
 	},
-	.mbus_param = V4L2_MBUS_PCLK_SAMPLE_RISING | V4L2_MBUS_MASTER |
-	V4L2_MBUS_VSYNC_ACTIVE_HIGH | V4L2_MBUS_HSYNC_ACTIVE_HIGH |
-	V4L2_MBUS_DATA_ACTIVE_HIGH,
-	.mbus_type = V4L2_MBUS_PARALLEL,
-	.set_capture = camera_set_capture,
-};
-
-static struct soc_camera_link camera_link = {
-	.bus_id		= 0,
-	.add_device	= ap325rxa_camera_add,
-	.del_device	= ap325rxa_camera_del,
-	.module_name	= "soc_camera_platform",
-	.priv		= &camera_info,
 };
 
-static struct platform_device *camera_device;
-
-static void ap325rxa_camera_release(struct device *dev)
-{
-	soc_camera_platform_release(&camera_device);
-}
-
-static int ap325rxa_camera_add(struct soc_camera_device *icd)
-{
-	int ret = soc_camera_platform_add(icd, &camera_device, &camera_link,
-					  ap325rxa_camera_release, 0);
-	if (ret < 0)
-		return ret;
-
-	ret = camera_probe();
-	if (ret < 0)
-		soc_camera_platform_del(icd, camera_device, &camera_link);
-
-	return ret;
-}
-
-static void ap325rxa_camera_del(struct soc_camera_device *icd)
-{
-	soc_camera_platform_del(icd, camera_device, &camera_link);
-}
-#endif /* CONFIG_I2C */
-
-static int ov7725_power(struct device *dev, int mode)
-{
-	camera_power(0);
-	if (mode)
-		camera_power(1);
-
-	return 0;
-}
-
-static struct sh_mobile_ceu_info sh_mobile_ceu_info = {
-	.flags = SH_CEU_FLAG_USE_8BIT_BUS,
+static struct ceu_platform_data ceu0_pdata = {
+	.num_subdevs			= 1,
+	.subdevs = {
+		{ /* [0] = ov7725  */
+			.flags		= 0,
+			.bus_width	= 8,
+			.bus_shift	= 0,
+			.i2c_adapter_id	= 0,
+			.i2c_address	= 0x21,
+		},
+	},
 };
 
 static struct resource ceu_resources[] = {
@@ -410,18 +290,15 @@ static struct resource ceu_resources[] = {
 		.start  = evt2irq(0x880),
 		.flags  = IORESOURCE_IRQ,
 	},
-	[2] = {
-		/* place holder for contiguous memory */
-	},
 };
 
-static struct platform_device ceu_device = {
-	.name		= "sh_mobile_ceu",
-	.id             = 0, /* "ceu0" clock */
+static struct platform_device ap325rxa_ceu_device = {
+	.name		= "renesas-ceu",
+	.id             = 0, /* "ceu.0" clock */
 	.num_resources	= ARRAY_SIZE(ceu_resources),
 	.resource	= ceu_resources,
 	.dev		= {
-		.platform_data	= &sh_mobile_ceu_info,
+		.platform_data	= &ceu0_pdata,
 	},
 };
 
@@ -488,44 +365,18 @@ static struct platform_device sdhi1_cn7_device = {
 	},
 };
 
-static struct i2c_board_info __initdata ap325rxa_i2c_devices[] = {
-	{
-		I2C_BOARD_INFO("pcf8563", 0x51),
-	},
-};
-
-static struct i2c_board_info ap325rxa_i2c_camera[] = {
-	{
-		I2C_BOARD_INFO("ov772x", 0x21),
-	},
-};
-
 static struct ov772x_camera_info ov7725_info = {
 	.flags		= OV772X_FLAG_VFLIP | OV772X_FLAG_HFLIP,
 	.edgectrl	= OV772X_AUTO_EDGECTRL(0xf, 0),
 };
 
-static struct soc_camera_link ov7725_link = {
-	.bus_id		= 0,
-	.power		= ov7725_power,
-	.board_info	= &ap325rxa_i2c_camera[0],
-	.i2c_adapter_id	= 0,
-	.priv		= &ov7725_info,
-};
-
-static struct platform_device ap325rxa_camera[] = {
+static struct i2c_board_info ap325rxa_i2c_devices[] __initdata = {
 	{
-		.name	= "soc-camera-pdrv",
-		.id	= 0,
-		.dev	= {
-			.platform_data = &ov7725_link,
-		},
-	}, {
-		.name	= "soc-camera-pdrv",
-		.id	= 1,
-		.dev	= {
-			.platform_data = &camera_link,
-		},
+		I2C_BOARD_INFO("pcf8563", 0x51),
+	},
+	{
+		I2C_BOARD_INFO("ov772x", 0x21),
+		.platform_data = &ov7725_info,
 	},
 };
 
@@ -533,12 +384,9 @@ static struct platform_device *ap325rxa_devices[] __initdata = {
 	&smsc9118_device,
 	&ap325rxa_nor_flash_device,
 	&lcdc_device,
-	&ceu_device,
 	&nand_flash_device,
 	&sdhi0_cn3_device,
 	&sdhi1_cn7_device,
-	&ap325rxa_camera[0],
-	&ap325rxa_camera[1],
 };
 
 extern char ap325rxa_sdram_enter_start;
@@ -649,8 +497,6 @@ static int __init ap325rxa_devices_setup(void)
 	__raw_writew(0xFFFF, PORT_DRVCRA);
 	__raw_writew(0xFFFF, PORT_DRVCRB);
 
-	platform_resource_setup_memory(&ceu_device, "ceu", 4 << 20);
-
 	/* SDHI0 - CN3 - SD CARD */
 	gpio_request(GPIO_FN_SDHI0CD_PTD, NULL);
 	gpio_request(GPIO_FN_SDHI0WP_PTD, NULL);
@@ -670,9 +516,25 @@ static int __init ap325rxa_devices_setup(void)
 	gpio_request(GPIO_FN_SDHI1CMD, NULL);
 	gpio_request(GPIO_FN_SDHI1CLK, NULL);
 
+	/* Add a clock alias for ov7725 xclk source. */
+	clk_add_alias(NULL, "0-0021", "video_clk", NULL);
+
+	/* Register RSTB gpio for ov7725 camera sensor. */
+	gpiod_add_lookup_table(&ov7725_gpios);
+
 	i2c_register_board_info(0, ap325rxa_i2c_devices,
 				ARRAY_SIZE(ap325rxa_i2c_devices));
 
+	/* Initialize CEU platform device separately to map memory first */
+	device_initialize(&ap325rxa_ceu_device.dev);
+	arch_setup_pdev_archdata(&ap325rxa_ceu_device);
+	dma_declare_coherent_memory(&ap325rxa_ceu_device.dev,
+				    ceu_dma_membase, ceu_dma_membase,
+				    ceu_dma_membase + CEU_BUFFER_MEMORY_SIZE - 1,
+				    DMA_MEMORY_EXCLUSIVE);
+
+	platform_device_add(&ap325rxa_ceu_device);
+
 	return platform_add_devices(ap325rxa_devices,
 				ARRAY_SIZE(ap325rxa_devices));
 }
@@ -689,7 +551,21 @@ static int ap325rxa_mode_pins(void)
 	return MODE_PIN5 | MODE_PIN8;
 }
 
+/* Reserve a portion of memory for CEU buffers */
+static void __init ap325rxa_mv_mem_reserve(void)
+{
+	phys_addr_t phys;
+	phys_addr_t size = CEU_BUFFER_MEMORY_SIZE;
+
+	phys = memblock_alloc_base(size, PAGE_SIZE, MEMBLOCK_ALLOC_ANYWHERE);
+	memblock_free(phys, size);
+	memblock_remove(phys, size);
+
+	ceu_dma_membase = phys;
+}
+
 static struct sh_machine_vector mv_ap325rxa __initmv = {
 	.mv_name = "AP-325RXA",
 	.mv_mode_pins = ap325rxa_mode_pins,
+	.mv_mem_reserve	= ap325rxa_mv_mem_reserve,
 };
diff --git a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c
index fe844222f3f6..af01664f7b4c 100644
--- a/arch/sh/kernel/cpu/sh4a/clock-sh7723.c
+++ b/arch/sh/kernel/cpu/sh4a/clock-sh7723.c
@@ -260,7 +260,7 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_CON_ID("veu1", &mstp_clks[HWBLK_VEU2H1]),
 	CLKDEV_DEV_ID("sh-vou.0", &mstp_clks[HWBLK_VOU]),
 	CLKDEV_CON_ID("beu0", &mstp_clks[HWBLK_BEU]),
-	CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[HWBLK_CEU]),
+	CLKDEV_DEV_ID("ceu.0", &mstp_clks[HWBLK_CEU]),
 	CLKDEV_CON_ID("veu0", &mstp_clks[HWBLK_VEU2H0]),
 	CLKDEV_CON_ID("vpu0", &mstp_clks[HWBLK_VPU]),
 
-- 
cgit v1.2.3


From aa2f88712718d045855acc6686dbce6a7286d010 Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Thu, 17 May 2018 10:30:15 -0400
Subject: media: v4l2-ioctl: create helper to fill in v4l2_standard for ENUMSTD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Prepare for adding a new IOCTL VIDIOC_SUBDEV_ENUMSTD which would
enumerate the standards for a subdevice by breaking out the code which
could be shared between the video and subdevice versions of this IOCTL.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
[hans.verkuil@cisco.com: fixed 'sdandard' typos in v4l2-ioctl.h]
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-ioctl.c | 66 ++++++++++++++++++++----------------
 include/media/v4l2-ioctl.h           | 15 ++++++--
 2 files changed, 50 insertions(+), 31 deletions(-)

diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index dd210067151f..eeed14468a17 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -125,6 +125,42 @@ int v4l2_video_std_construct(struct v4l2_standard *vs,
 }
 EXPORT_SYMBOL(v4l2_video_std_construct);
 
+/* Fill in the fields of a v4l2_standard structure according to the
+ * 'id' and 'vs->index' parameters. Returns negative on error. */
+int v4l_video_std_enumstd(struct v4l2_standard *vs, v4l2_std_id id)
+{
+	v4l2_std_id curr_id = 0;
+	unsigned int index = vs->index, i, j = 0;
+	const char *descr = "";
+
+	/* Return -ENODATA if the id for the current input
+	   or output is 0, meaning that it doesn't support this API. */
+	if (id == 0)
+		return -ENODATA;
+
+	/* Return norm array in a canonical way */
+	for (i = 0; i <= index && id; i++) {
+		/* last std value in the standards array is 0, so this
+		   while always ends there since (id & 0) == 0. */
+		while ((id & standards[j].std) != standards[j].std)
+			j++;
+		curr_id = standards[j].std;
+		descr = standards[j].descr;
+		j++;
+		if (curr_id == 0)
+			break;
+		if (curr_id != V4L2_STD_PAL &&
+				curr_id != V4L2_STD_SECAM &&
+				curr_id != V4L2_STD_NTSC)
+			id &= ~curr_id;
+	}
+	if (i <= index)
+		return -EINVAL;
+
+	v4l2_video_std_construct(vs, curr_id, descr);
+	return 0;
+}
+
 /* ----------------------------------------------------------------- */
 /* some arrays for pretty-printing debug messages of enum types      */
 
@@ -1753,36 +1789,8 @@ static int v4l_enumstd(const struct v4l2_ioctl_ops *ops,
 {
 	struct video_device *vfd = video_devdata(file);
 	struct v4l2_standard *p = arg;
-	v4l2_std_id id = vfd->tvnorms, curr_id = 0;
-	unsigned int index = p->index, i, j = 0;
-	const char *descr = "";
-
-	/* Return -ENODATA if the tvnorms for the current input
-	   or output is 0, meaning that it doesn't support this API. */
-	if (id == 0)
-		return -ENODATA;
 
-	/* Return norm array in a canonical way */
-	for (i = 0; i <= index && id; i++) {
-		/* last std value in the standards array is 0, so this
-		   while always ends there since (id & 0) == 0. */
-		while ((id & standards[j].std) != standards[j].std)
-			j++;
-		curr_id = standards[j].std;
-		descr = standards[j].descr;
-		j++;
-		if (curr_id == 0)
-			break;
-		if (curr_id != V4L2_STD_PAL &&
-				curr_id != V4L2_STD_SECAM &&
-				curr_id != V4L2_STD_NTSC)
-			id &= ~curr_id;
-	}
-	if (i <= index)
-		return -EINVAL;
-
-	v4l2_video_std_construct(p, curr_id, descr);
-	return 0;
+	return v4l_video_std_enumstd(p, vfd->tvnorms);
 }
 
 static int v4l_s_std(const struct v4l2_ioctl_ops *ops,
diff --git a/include/media/v4l2-ioctl.h b/include/media/v4l2-ioctl.h
index a8dbf5b54b5c..5848d92c30da 100644
--- a/include/media/v4l2-ioctl.h
+++ b/include/media/v4l2-ioctl.h
@@ -621,7 +621,7 @@ const char *v4l2_norm_to_name(v4l2_std_id id);
  * v4l2_video_std_frame_period - Ancillary routine that fills a
  *	struct &v4l2_fract pointer with the default framerate fraction.
  *
- * @id: analog TV sdandard ID.
+ * @id: analog TV standard ID.
  * @frameperiod: struct &v4l2_fract pointer to be filled
  *
  */
@@ -632,7 +632,7 @@ void v4l2_video_std_frame_period(int id, struct v4l2_fract *frameperiod);
  *	a &v4l2_standard structure according to the @id parameter.
  *
  * @vs: struct &v4l2_standard pointer to be filled
- * @id: analog TV sdandard ID.
+ * @id: analog TV standard ID.
  * @name: name of the standard to be used
  *
  * .. note::
@@ -642,6 +642,17 @@ void v4l2_video_std_frame_period(int id, struct v4l2_fract *frameperiod);
 int v4l2_video_std_construct(struct v4l2_standard *vs,
 				    int id, const char *name);
 
+/**
+ * v4l_video_std_enumstd - Ancillary routine that fills in the fields of
+ *	a &v4l2_standard structure according to the @id and @vs->index
+ *	parameters.
+ *
+ * @vs: struct &v4l2_standard pointer to be filled.
+ * @id: analog TV standard ID.
+ *
+ */
+int v4l_video_std_enumstd(struct v4l2_standard *vs, v4l2_std_id id);
+
 /**
  * v4l_printk_ioctl - Ancillary routine that prints the ioctl in a
  *	human-readable format.
-- 
cgit v1.2.3


From fdd49c510021d389bf5979282193e084f328e031 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 27 Jun 2018 09:54:46 +0200
Subject: ALSA: hda/hdmi - Don't fall back to generic when i915 binding fails

When i915 component binding fails, it means that HDMI isn't applicable
anyway.  Although the probe with the generic HDMI parser would still
work, it's essentially useless, hence better to be left unbound.

This patch mimics the probe_id field at failing the i915 component
binding so that the generic HDMI won't be bound after that.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_codec.h  | 1 +
 sound/pci/hda/patch_hdmi.c | 2 ++
 2 files changed, 3 insertions(+)

diff --git a/sound/pci/hda/hda_codec.h b/sound/pci/hda/hda_codec.h
index 8a095c16ee65..993294c8fd0a 100644
--- a/sound/pci/hda/hda_codec.h
+++ b/sound/pci/hda/hda_codec.h
@@ -84,6 +84,7 @@ struct hda_bus {
  */
 typedef int (*hda_codec_patch_t)(struct hda_codec *);
 	
+#define HDA_CODEC_ID_SKIP_PROBE		0x00000001
 #define HDA_CODEC_ID_GENERIC_HDMI	0x00000101
 #define HDA_CODEC_ID_GENERIC		0x00000201
 
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index ed2318f79e3c..cbf5f4e30027 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2542,6 +2542,8 @@ static int alloc_intel_hdmi(struct hda_codec *codec)
 	/* requires i915 binding */
 	if (!codec->bus->core.audio_component) {
 		codec_info(codec, "No i915 binding for Intel HDMI/DP codec\n");
+		/* set probe_id here to prevent generic fallback binding */
+		codec->probe_id = HDA_CODEC_ID_SKIP_PROBE;
 		return -ENODEV;
 	}
 
-- 
cgit v1.2.3


From c9dc4cfa10a1266376dde151485f7b493447258b Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Date: Thu, 28 Jun 2018 14:22:23 +0300
Subject: regulator: bd71837: Editorial cleanups.

Address issues spotted by Andy Shevchenko during review of original patch
No functional changes intended

Signed-off-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd71837-regulator.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/regulator/bd71837-regulator.c b/drivers/regulator/bd71837-regulator.c
index f57f42ed7160..3a487255482c 100644
--- a/drivers/regulator/bd71837-regulator.c
+++ b/drivers/regulator/bd71837-regulator.c
@@ -2,19 +2,18 @@
 // Copyright (C) 2018 ROHM Semiconductors
 // bd71837-regulator.c ROHM BD71837MWV regulator driver
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
+#include <linux/delay.h>
 #include <linux/err.h>
+#include <linux/gpio.h>
 #include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/bd71837.h>
+#include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/gpio.h>
-#include <linux/mfd/bd71837.h>
 #include <linux/regulator/of_regulator.h>
+#include <linux/slab.h>
 
 struct bd71837_pmic {
 	struct regulator_desc descs[BD71837_REGULATOR_CNT];
@@ -39,7 +38,7 @@ static int bd71837_buck1234_set_ramp_delay(struct regulator_dev *rdev,
 	int id = rdev->desc->id;
 	unsigned int ramp_value = BUCK_RAMPRATE_10P00MV;
 
-	dev_dbg(&(pmic->pdev->dev), "Buck[%d] Set Ramp = %d\n", id + 1,
+	dev_dbg(&pmic->pdev->dev, "Buck[%d] Set Ramp = %d\n", id + 1,
 		ramp_delay);
 	switch (ramp_delay) {
 	case 1 ... 1250:
@@ -544,8 +543,7 @@ static int bd71837_probe(struct platform_device *pdev)
 
 	int i, err;
 
-	pmic = devm_kzalloc(&pdev->dev, sizeof(struct bd71837_pmic),
-			    GFP_KERNEL);
+	pmic = devm_kzalloc(&pdev->dev, sizeof(*pmic), GFP_KERNEL);
 	if (!pmic)
 		return -ENOMEM;
 
@@ -569,8 +567,8 @@ static int bd71837_probe(struct platform_device *pdev)
 		dev_err(&pmic->pdev->dev, "Failed to unlock PMIC (%d)\n", err);
 		goto err;
 	} else {
-		dev_dbg(&pmic->pdev->dev, "%s: Unlocked lock register 0x%x\n",
-			__func__, BD71837_REG_REGLOCK);
+		dev_dbg(&pmic->pdev->dev, "Unlocked lock register 0x%x\n",
+			BD71837_REG_REGLOCK);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(pmic_regulator_inits); i++) {
@@ -615,8 +613,6 @@ static int bd71837_probe(struct platform_device *pdev)
 		pmic->rdev[i] = rdev;
 	}
 
-	return 0;
-
 err:
 	return err;
 }
@@ -624,7 +620,6 @@ err:
 static struct platform_driver bd71837_regulator = {
 	.driver = {
 		.name = "bd71837-pmic",
-		.owner = THIS_MODULE,
 	},
 	.probe = bd71837_probe,
 };
-- 
cgit v1.2.3


From bfe75f76d7bee4513bc7851ba1699f4bc472d6ca Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 11 Jun 2018 05:41:19 -0400
Subject: media: stm32-dcmi: increase max width/height to 2592

DCMI can capture 5Mp raw frames, increase limit accordingly.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 19 ++++---------------
 1 file changed, 4 insertions(+), 15 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index 2e1933d872ee..db2dab335fa8 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -89,14 +89,9 @@ enum state {
 };
 
 #define MIN_WIDTH	16U
-#define MAX_WIDTH	2048U
+#define MAX_WIDTH	2592U
 #define MIN_HEIGHT	16U
-#define MAX_HEIGHT	2048U
-
-#define MIN_JPEG_WIDTH	16U
-#define MAX_JPEG_WIDTH	2592U
-#define MIN_JPEG_HEIGHT	16U
-#define MAX_JPEG_HEIGHT	2592U
+#define MAX_HEIGHT	2592U
 
 #define TIMEOUT_MS	1000
 
@@ -843,14 +838,8 @@ static int dcmi_try_fmt(struct stm32_dcmi *dcmi, struct v4l2_format *f,
 	}
 
 	/* Limit to hardware capabilities */
-	if (pix->pixelformat == V4L2_PIX_FMT_JPEG) {
-		pix->width = clamp(pix->width, MIN_JPEG_WIDTH, MAX_JPEG_WIDTH);
-		pix->height =
-			clamp(pix->height, MIN_JPEG_HEIGHT, MAX_JPEG_HEIGHT);
-	} else {
-		pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH);
-		pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT);
-	}
+	pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH);
+	pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT);
 
 	/* No crop if JPEG is requested */
 	do_crop = dcmi->do_crop && (pix->pixelformat != V4L2_PIX_FMT_JPEG);
-- 
cgit v1.2.3


From 312ae0ae7479d30f8876bafbc4cca24f0605c65f Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Date: Thu, 28 Jun 2018 14:23:04 +0300
Subject: regulator: bd71837: Remove duplicate description from DT bindings

Same general chip description was written in MFD and Regulator
binding documents for ROHM bd71837 PMIC. Remove description from
regulator binding as suggested by Rob H.

Signed-off-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/regulator/rohm,bd71837-regulator.txt      | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt b/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt
index 4edf3137d9f7..76ead07072b1 100644
--- a/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/rohm,bd71837-regulator.txt
@@ -1,13 +1,5 @@
 ROHM BD71837 Power Management Integrated Circuit (PMIC) regulator bindings
 
-BD71837MWV is a programmable Power Management
-IC (PMIC) for powering single-core, dual-core, and
-quad-core SoC’s such as NXP-i.MX 8M. It is optimized
-for low BOM cost and compact solution footprint. It
-integrates 8 Buck regulators and 7 LDO’s to provide all
-the power rails required by the SoC and the commonly
-used peripherals.
-
 Required properties:
  - regulator-name: should be "buck1", ..., "buck8" and "ldo1", ..., "ldo7"
 
-- 
cgit v1.2.3


From 4b84e75020a6b136e7160a9c53443b4c26e5d518 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 11 Jun 2018 05:50:09 -0400
Subject: media: stm32-dcmi: code cleanup

Minor non-functional fixes around comments, variable namings
and trace point enhancement.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index db2dab335fa8..b78583dc972b 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -248,13 +248,12 @@ static int dcmi_restart_capture(struct stm32_dcmi *dcmi)
 static void dcmi_dma_callback(void *param)
 {
 	struct stm32_dcmi *dcmi = (struct stm32_dcmi *)param;
-	struct dma_chan *chan = dcmi->dma_chan;
 	struct dma_tx_state state;
 	enum dma_status status;
 	struct dcmi_buf *buf = dcmi->active;
 
 	/* Check DMA status */
-	status = dmaengine_tx_status(chan, dcmi->dma_cookie, &state);
+	status = dmaengine_tx_status(dcmi->dma_chan, dcmi->dma_cookie, &state);
 
 	switch (status) {
 	case DMA_IN_PROGRESS:
@@ -308,10 +307,11 @@ static int dcmi_start_dma(struct stm32_dcmi *dcmi,
 	/* Prepare a DMA transaction */
 	desc = dmaengine_prep_slave_single(dcmi->dma_chan, buf->paddr,
 					   buf->size,
-					   DMA_DEV_TO_MEM, DMA_PREP_INTERRUPT);
+					   DMA_DEV_TO_MEM,
+					   DMA_PREP_INTERRUPT);
 	if (!desc) {
-		dev_err(dcmi->dev, "%s: DMA dmaengine_prep_slave_single failed for buffer size %zu\n",
-			__func__, buf->size);
+		dev_err(dcmi->dev, "%s: DMA dmaengine_prep_slave_single failed for buffer phy=%pad size=%zu\n",
+			__func__, &buf->paddr, buf->size);
 		return -EINVAL;
 	}
 
@@ -377,7 +377,6 @@ static void dcmi_process_jpeg(struct stm32_dcmi *dcmi)
 {
 	struct dma_tx_state state;
 	enum dma_status status;
-	struct dma_chan *chan = dcmi->dma_chan;
 	struct dcmi_buf *buf = dcmi->active;
 
 	if (!buf)
@@ -385,8 +384,7 @@ static void dcmi_process_jpeg(struct stm32_dcmi *dcmi)
 
 	/*
 	 * Because of variable JPEG buffer size sent by sensor,
-	 * DMA transfer never completes due to transfer size
-	 * never reached.
+	 * DMA transfer never completes due to transfer size never reached.
 	 * In order to ensure that all the JPEG data are transferred
 	 * in active buffer memory, DMA is drained.
 	 * Then DMA tx status gives the amount of data transferred
@@ -395,10 +393,10 @@ static void dcmi_process_jpeg(struct stm32_dcmi *dcmi)
 	 */
 
 	/* Drain DMA */
-	dmaengine_synchronize(chan);
+	dmaengine_synchronize(dcmi->dma_chan);
 
 	/* Get DMA residue to get JPEG size */
-	status = dmaengine_tx_status(chan, dcmi->dma_cookie, &state);
+	status = dmaengine_tx_status(dcmi->dma_chan, dcmi->dma_cookie, &state);
 	if (status != DMA_ERROR && state.residue < buf->size) {
 		/* Return JPEG buffer to V4L2 with received JPEG buffer size */
 		dcmi_buffer_done(dcmi, buf, buf->size - state.residue, 0);
-- 
cgit v1.2.3


From b53a24fc2849a4d56961ac74a7aaeca9f5953a5a Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 11 Jun 2018 05:50:24 -0400
Subject: media: stm32-dcmi: do not fall into error on buffer starvation

Return silently instead of falling into error when running
out of available buffers when restarting capture.
Capture will be restarted when new buffers will be
provided by V4L2 client.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index b78583dc972b..fc72a57d8478 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -227,13 +227,10 @@ static int dcmi_restart_capture(struct stm32_dcmi *dcmi)
 
 	/* Restart a new DMA transfer with next buffer */
 	if (list_empty(&dcmi->buffers)) {
-		dev_err(dcmi->dev, "%s: No more buffer queued, cannot capture buffer\n",
-			__func__);
-		dcmi->errors_count++;
+		dev_dbg(dcmi->dev, "Capture restart is deferred to next buffer queueing\n");
 		dcmi->active = NULL;
-
 		spin_unlock_irq(&dcmi->irqlock);
-		return -EINVAL;
+		return 0;
 	}
 
 	dcmi->active = list_entry(dcmi->buffers.next,
-- 
cgit v1.2.3


From a331df3cb3a121ed9d6c2010f28ca0fccc4153ba Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 11 Jun 2018 05:50:25 -0400
Subject: media: stm32-dcmi: return buffer in error state on dma error

Return buffer to V4L2 in error state if DMA error occurs.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index fc72a57d8478..526d8311df4a 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -261,6 +261,9 @@ static void dcmi_dma_callback(void *param)
 		break;
 	case DMA_ERROR:
 		dev_err(dcmi->dev, "%s: Received DMA_ERROR\n", __func__);
+
+		/* Return buffer to V4L2 in error state */
+		dcmi_buffer_done(dcmi, buf, 0, -EIO);
 		break;
 	case DMA_COMPLETE:
 		dev_dbg(dcmi->dev, "%s: Received DMA_COMPLETE\n", __func__);
-- 
cgit v1.2.3


From 2d494d4a09c027fd656862dc0a1aa7a14db42e2a Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 11 Jun 2018 05:50:26 -0400
Subject: media: stm32-dcmi: clarify state logic on buffer starvation

Introduce WAIT_FOR_BUFFER state instead of "active" field checking
to manage buffer starvation case.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index 526d8311df4a..61daa1e0514a 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -84,6 +84,7 @@
 
 enum state {
 	STOPPED = 0,
+	WAIT_FOR_BUFFER,
 	RUNNING,
 	STOPPING,
 };
@@ -229,6 +230,7 @@ static int dcmi_restart_capture(struct stm32_dcmi *dcmi)
 	if (list_empty(&dcmi->buffers)) {
 		dev_dbg(dcmi->dev, "Capture restart is deferred to next buffer queueing\n");
 		dcmi->active = NULL;
+		dcmi->state = WAIT_FOR_BUFFER;
 		spin_unlock_irq(&dcmi->irqlock);
 		return 0;
 	}
@@ -547,9 +549,11 @@ static void dcmi_buf_queue(struct vb2_buffer *vb)
 
 	spin_lock_irq(&dcmi->irqlock);
 
-	if (dcmi->state == RUNNING && !dcmi->active) {
 		dcmi->active = buf;
 
+	if (dcmi->state == WAIT_FOR_BUFFER) {
+		dcmi->state = RUNNING;
+
 		dev_dbg(dcmi->dev, "Starting capture on buffer[%d] queued\n",
 			buf->vb.vb2_buf.index);
 
@@ -629,8 +633,6 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	/* Enable dcmi */
 	reg_set(dcmi->regs, DCMI_CR, CR_ENABLE);
 
-	dcmi->state = RUNNING;
-
 	dcmi->sequence = 0;
 	dcmi->errors_count = 0;
 	dcmi->overrun_count = 0;
@@ -643,6 +645,7 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	 */
 	if (list_empty(&dcmi->buffers)) {
 		dev_dbg(dcmi->dev, "Start streaming is deferred to next buffer queueing\n");
+		dcmi->state = WAIT_FOR_BUFFER;
 		spin_unlock_irq(&dcmi->irqlock);
 		return 0;
 	}
@@ -652,6 +655,8 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 
 	dev_dbg(dcmi->dev, "Start streaming, starting capture\n");
 
+	dcmi->state = RUNNING;
+
 	spin_unlock_irq(&dcmi->irqlock);
 	ret = dcmi_start_capture(dcmi);
 	if (ret) {
-- 
cgit v1.2.3


From 49bcc1746ffbf94f41840718c5fab1a8d56c82d8 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 11 Jun 2018 05:50:27 -0400
Subject: media: stm32-dcmi: revisit buffer list management

Cleanup "active" field usage and enhance list management
to avoid exceptions when releasing buffers on error or
stopping streaming.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 65 +++++++++++++++----------------
 1 file changed, 31 insertions(+), 34 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index 61daa1e0514a..5d866ac69d5c 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -190,7 +190,7 @@ static inline void reg_clear(void __iomem *base, u32 reg, u32 mask)
 	reg_write(base, reg, reg_read(base, reg) & ~mask);
 }
 
-static int dcmi_start_capture(struct stm32_dcmi *dcmi);
+static int dcmi_start_capture(struct stm32_dcmi *dcmi, struct dcmi_buf *buf);
 
 static void dcmi_buffer_done(struct stm32_dcmi *dcmi,
 			     struct dcmi_buf *buf,
@@ -202,6 +202,8 @@ static void dcmi_buffer_done(struct stm32_dcmi *dcmi,
 	if (!buf)
 		return;
 
+	list_del_init(&buf->list);
+
 	vbuf = &buf->vb;
 
 	vbuf->sequence = dcmi->sequence++;
@@ -219,6 +221,8 @@ static void dcmi_buffer_done(struct stm32_dcmi *dcmi,
 
 static int dcmi_restart_capture(struct stm32_dcmi *dcmi)
 {
+	struct dcmi_buf *buf;
+
 	spin_lock_irq(&dcmi->irqlock);
 
 	if (dcmi->state != RUNNING) {
@@ -229,19 +233,16 @@ static int dcmi_restart_capture(struct stm32_dcmi *dcmi)
 	/* Restart a new DMA transfer with next buffer */
 	if (list_empty(&dcmi->buffers)) {
 		dev_dbg(dcmi->dev, "Capture restart is deferred to next buffer queueing\n");
-		dcmi->active = NULL;
 		dcmi->state = WAIT_FOR_BUFFER;
 		spin_unlock_irq(&dcmi->irqlock);
 		return 0;
 	}
-
-	dcmi->active = list_entry(dcmi->buffers.next,
-				  struct dcmi_buf, list);
-	list_del_init(&dcmi->active->list);
+	buf = list_entry(dcmi->buffers.next, struct dcmi_buf, list);
+	dcmi->active = buf;
 
 	spin_unlock_irq(&dcmi->irqlock);
 
-	return dcmi_start_capture(dcmi);
+	return dcmi_start_capture(dcmi, buf);
 }
 
 static void dcmi_dma_callback(void *param)
@@ -251,6 +252,8 @@ static void dcmi_dma_callback(void *param)
 	enum dma_status status;
 	struct dcmi_buf *buf = dcmi->active;
 
+	spin_lock_irq(&dcmi->irqlock);
+
 	/* Check DMA status */
 	status = dmaengine_tx_status(dcmi->dma_chan, dcmi->dma_cookie, &state);
 
@@ -273,15 +276,19 @@ static void dcmi_dma_callback(void *param)
 		/* Return buffer to V4L2 */
 		dcmi_buffer_done(dcmi, buf, buf->size, 0);
 
+		spin_unlock_irq(&dcmi->irqlock);
+
 		/* Restart capture */
 		if (dcmi_restart_capture(dcmi))
 			dev_err(dcmi->dev, "%s: Cannot restart capture on DMA complete\n",
 				__func__);
-		break;
+		return;
 	default:
 		dev_err(dcmi->dev, "%s: Received unknown status\n", __func__);
 		break;
 	}
+
+	spin_unlock_irq(&dcmi->irqlock);
 }
 
 static int dcmi_start_dma(struct stm32_dcmi *dcmi,
@@ -333,10 +340,9 @@ static int dcmi_start_dma(struct stm32_dcmi *dcmi,
 	return 0;
 }
 
-static int dcmi_start_capture(struct stm32_dcmi *dcmi)
+static int dcmi_start_capture(struct stm32_dcmi *dcmi, struct dcmi_buf *buf)
 {
 	int ret;
-	struct dcmi_buf *buf = dcmi->active;
 
 	if (!buf)
 		return -EINVAL;
@@ -490,8 +496,6 @@ static int dcmi_queue_setup(struct vb2_queue *vq,
 	*nplanes = 1;
 	sizes[0] = size;
 
-	dcmi->active = NULL;
-
 	dev_dbg(dcmi->dev, "Setup queue, count=%d, size=%d\n",
 		*nbuffers, size);
 
@@ -549,23 +553,24 @@ static void dcmi_buf_queue(struct vb2_buffer *vb)
 
 	spin_lock_irq(&dcmi->irqlock);
 
-		dcmi->active = buf;
+	/* Enqueue to video buffers list */
+	list_add_tail(&buf->list, &dcmi->buffers);
 
 	if (dcmi->state == WAIT_FOR_BUFFER) {
 		dcmi->state = RUNNING;
+		dcmi->active = buf;
 
 		dev_dbg(dcmi->dev, "Starting capture on buffer[%d] queued\n",
 			buf->vb.vb2_buf.index);
 
 		spin_unlock_irq(&dcmi->irqlock);
-		if (dcmi_start_capture(dcmi))
+		if (dcmi_start_capture(dcmi, buf))
 			dev_err(dcmi->dev, "%s: Cannot restart capture on overflow or error\n",
 				__func__);
-	} else {
-		/* Enqueue to video buffers list */
-		list_add_tail(&buf->list, &dcmi->buffers);
-		spin_unlock_irq(&dcmi->irqlock);
+		return;
 	}
+
+	spin_unlock_irq(&dcmi->irqlock);
 }
 
 static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
@@ -637,7 +642,6 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	dcmi->errors_count = 0;
 	dcmi->overrun_count = 0;
 	dcmi->buffers_count = 0;
-	dcmi->active = NULL;
 
 	/*
 	 * Start transfer if at least one buffer has been queued,
@@ -650,15 +654,15 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 		return 0;
 	}
 
-	dcmi->active = list_entry(dcmi->buffers.next, struct dcmi_buf, list);
-	list_del_init(&dcmi->active->list);
-
-	dev_dbg(dcmi->dev, "Start streaming, starting capture\n");
+	buf = list_entry(dcmi->buffers.next, struct dcmi_buf, list);
+	dcmi->active = buf;
 
 	dcmi->state = RUNNING;
 
+	dev_dbg(dcmi->dev, "Start streaming, starting capture\n");
+
 	spin_unlock_irq(&dcmi->irqlock);
-	ret = dcmi_start_capture(dcmi);
+	ret = dcmi_start_capture(dcmi, buf);
 	if (ret) {
 		dev_err(dcmi->dev, "%s: Start streaming failed, cannot start capture\n",
 			__func__);
@@ -682,15 +686,11 @@ err_release_buffers:
 	 * Return all buffers to vb2 in QUEUED state.
 	 * This will give ownership back to userspace
 	 */
-	if (dcmi->active) {
-		buf = dcmi->active;
-		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
-		dcmi->active = NULL;
-	}
 	list_for_each_entry_safe(buf, node, &dcmi->buffers, list) {
 		list_del_init(&buf->list);
 		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED);
 	}
+	dcmi->active = NULL;
 	spin_unlock_irq(&dcmi->irqlock);
 
 	return ret;
@@ -732,16 +732,13 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 	}
 
 	/* Return all queued buffers to vb2 in ERROR state */
-	if (dcmi->active) {
-		buf = dcmi->active;
-		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
-		dcmi->active = NULL;
-	}
 	list_for_each_entry_safe(buf, node, &dcmi->buffers, list) {
 		list_del_init(&buf->list);
 		vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_ERROR);
 	}
 
+	dcmi->active = NULL;
+
 	spin_unlock_irq(&dcmi->irqlock);
 
 	/* Stop all pending DMA operations */
-- 
cgit v1.2.3


From fdaf59582c037ca5bd23f23ab28c1c5c384c0520 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 11 Jun 2018 05:52:17 -0400
Subject: media: stm32-dcmi: revisit stop streaming ops

Do not wait for interrupt completion when stopping streaming,
stopping sensor and disabling interruptions are enough.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 29 +----------------------------
 1 file changed, 1 insertion(+), 28 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index 5d866ac69d5c..db49db78e00d 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -86,7 +86,6 @@ enum state {
 	STOPPED = 0,
 	WAIT_FOR_BUFFER,
 	RUNNING,
-	STOPPING,
 };
 
 #define MIN_WIDTH	16U
@@ -431,18 +430,6 @@ static irqreturn_t dcmi_irq_thread(int irq, void *arg)
 
 	spin_lock_irq(&dcmi->irqlock);
 
-	/* Stop capture is required */
-	if (dcmi->state == STOPPING) {
-		reg_clear(dcmi->regs, DCMI_IER, IT_FRAME | IT_OVR | IT_ERR);
-
-		dcmi->state = STOPPED;
-
-		complete(&dcmi->complete);
-
-		spin_unlock_irq(&dcmi->irqlock);
-		return IRQ_HANDLED;
-	}
-
 	if ((dcmi->misr & IT_OVR) || (dcmi->misr & IT_ERR)) {
 		dcmi->errors_count++;
 		if (dcmi->misr & IT_OVR)
@@ -700,8 +687,6 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 {
 	struct stm32_dcmi *dcmi = vb2_get_drv_priv(vq);
 	struct dcmi_buf *buf, *node;
-	unsigned long time_ms = msecs_to_jiffies(TIMEOUT_MS);
-	long timeout;
 	int ret;
 
 	/* Disable stream on the sub device */
@@ -710,13 +695,6 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 		dev_err(dcmi->dev, "%s: Failed to stop streaming, subdev streamoff error (%d)\n",
 			__func__, ret);
 
-	spin_lock_irq(&dcmi->irqlock);
-	dcmi->state = STOPPING;
-	spin_unlock_irq(&dcmi->irqlock);
-
-	timeout = wait_for_completion_interruptible_timeout(&dcmi->complete,
-							    time_ms);
-
 	spin_lock_irq(&dcmi->irqlock);
 
 	/* Disable interruptions */
@@ -725,12 +703,6 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 	/* Disable DCMI */
 	reg_clear(dcmi->regs, DCMI_CR, CR_ENABLE);
 
-	if (!timeout) {
-		dev_err(dcmi->dev, "%s: Timeout during stop streaming\n",
-			__func__);
-		dcmi->state = STOPPED;
-	}
-
 	/* Return all queued buffers to vb2 in ERROR state */
 	list_for_each_entry_safe(buf, node, &dcmi->buffers, list) {
 		list_del_init(&buf->list);
@@ -738,6 +710,7 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 	}
 
 	dcmi->active = NULL;
+	dcmi->state = STOPPED;
 
 	spin_unlock_irq(&dcmi->irqlock);
 
-- 
cgit v1.2.3


From f8eb8e5c1f31f059677a80e0a902e64065695fa8 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Tue, 12 Jun 2018 13:22:17 -0400
Subject: media: stm32-dcmi: drop unnecessary while(1) loop

The while(1) is effectively useless as all possible paths within it
return thus there is no way to loop.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 28 +++++++++++++---------------
 1 file changed, 13 insertions(+), 15 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index db49db78e00d..9f6bb4165e54 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -1567,23 +1567,21 @@ static int dcmi_graph_parse(struct stm32_dcmi *dcmi, struct device_node *node)
 	struct device_node *ep = NULL;
 	struct device_node *remote;
 
-	while (1) {
-		ep = of_graph_get_next_endpoint(node, ep);
-		if (!ep)
-			return -EINVAL;
-
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote) {
-			of_node_put(ep);
-			return -EINVAL;
-		}
+	ep = of_graph_get_next_endpoint(node, ep);
+	if (!ep)
+		return -EINVAL;
 
-		/* Remote node to connect */
-		dcmi->entity.node = remote;
-		dcmi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
-		dcmi->entity.asd.match.fwnode = of_fwnode_handle(remote);
-		return 0;
+	remote = of_graph_get_remote_port_parent(ep);
+	if (!remote) {
+		of_node_put(ep);
+		return -EINVAL;
 	}
+
+	/* Remote node to connect */
+	dcmi->entity.node = remote;
+	dcmi->entity.asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
+	dcmi->entity.asd.match.fwnode = of_fwnode_handle(remote);
+	return 0;
 }
 
 static int dcmi_graph_init(struct stm32_dcmi *dcmi)
-- 
cgit v1.2.3


From c2ee2243ce3763fef8da097851b2c07b73e18cdb Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Tue, 12 Jun 2018 13:22:18 -0400
Subject: media: stm32-dcmi: add mandatory of_node_put() in success path

The endpoint allocated by of_graph_get_next_endpoint() needs an of_node_put()
in both error and success path. As  ep  is not used the refcount decrement
can be right after the last use of  ep.

Fixes: commit 37404f91ef8b ("[media] stm32-dcmi: STM32 DCMI camera interface driver")

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index 9f6bb4165e54..fcad6de06009 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -1572,10 +1572,9 @@ static int dcmi_graph_parse(struct stm32_dcmi *dcmi, struct device_node *node)
 		return -EINVAL;
 
 	remote = of_graph_get_remote_port_parent(ep);
-	if (!remote) {
-		of_node_put(ep);
+	of_node_put(ep);
+	if (!remote)
 		return -EINVAL;
-	}
 
 	/* Remote node to connect */
 	dcmi->entity.node = remote;
-- 
cgit v1.2.3


From f11552d030e8e5a0a945b1920e31eaf48fe3fad4 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Tue, 12 Jun 2018 13:23:16 -0400
Subject: media: stm32-dcmi: simplify of_node_put usage

This does not fix any bug - this is just a code simplification. As
np is not used after passing it to v4l2_fwnode_endpoint_parse() its
refcount can be decremented immediately and at one location.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index fcad6de06009..4f65f14fbbc1 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -1655,23 +1655,20 @@ static int dcmi_probe(struct platform_device *pdev)
 	}
 
 	ret = v4l2_fwnode_endpoint_parse(of_fwnode_handle(np), &ep);
+	of_node_put(np);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not parse the endpoint\n");
-		of_node_put(np);
 		return -ENODEV;
 	}
 
 	if (ep.bus_type == V4L2_MBUS_CSI2) {
 		dev_err(&pdev->dev, "CSI bus not supported\n");
-		of_node_put(np);
 		return -ENODEV;
 	}
 	dcmi->bus.flags = ep.bus.parallel.flags;
 	dcmi->bus.bus_width = ep.bus.parallel.bus_width;
 	dcmi->bus.data_shift = ep.bus.parallel.data_shift;
 
-	of_node_put(np);
-
 	irq = platform_get_irq(pdev, 0);
 	if (irq <= 0) {
 		dev_err(&pdev->dev, "Could not get irq\n");
-- 
cgit v1.2.3


From 152e0bf60219ba589254c7aff4c095943c36cf68 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Wed, 13 Jun 2018 05:59:39 -0400
Subject: media: stm32-dcmi: add power saving support

Implements runtime & system sleep power management ops.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/stm32/stm32-dcmi.c | 81 +++++++++++++++++++++++++------
 1 file changed, 65 insertions(+), 16 deletions(-)

diff --git a/drivers/media/platform/stm32/stm32-dcmi.c b/drivers/media/platform/stm32/stm32-dcmi.c
index 4f65f14fbbc1..721564176d8c 100644
--- a/drivers/media/platform/stm32/stm32-dcmi.c
+++ b/drivers/media/platform/stm32/stm32-dcmi.c
@@ -22,7 +22,9 @@
 #include <linux/of.h>
 #include <linux/of_device.h>
 #include <linux/of_graph.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 #include <linux/videodev2.h>
 
@@ -567,9 +569,9 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	u32 val = 0;
 	int ret;
 
-	ret = clk_enable(dcmi->mclk);
+	ret = pm_runtime_get_sync(dcmi->dev);
 	if (ret) {
-		dev_err(dcmi->dev, "%s: Failed to start streaming, cannot enable clock\n",
+		dev_err(dcmi->dev, "%s: Failed to start streaming, cannot get sync\n",
 			__func__);
 		goto err_release_buffers;
 	}
@@ -579,7 +581,7 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 	if (ret && ret != -ENOIOCTLCMD) {
 		dev_err(dcmi->dev, "%s: Failed to start streaming, subdev streamon error",
 			__func__);
-		goto err_disable_clock;
+		goto err_pm_put;
 	}
 
 	spin_lock_irq(&dcmi->irqlock);
@@ -664,8 +666,8 @@ static int dcmi_start_streaming(struct vb2_queue *vq, unsigned int count)
 err_subdev_streamoff:
 	v4l2_subdev_call(dcmi->entity.subdev, video, s_stream, 0);
 
-err_disable_clock:
-	clk_disable(dcmi->mclk);
+err_pm_put:
+	pm_runtime_put(dcmi->dev);
 
 err_release_buffers:
 	spin_lock_irq(&dcmi->irqlock);
@@ -717,7 +719,7 @@ static void dcmi_stop_streaming(struct vb2_queue *vq)
 	/* Stop all pending DMA operations */
 	dmaengine_terminate_all(dcmi->dma_chan);
 
-	clk_disable(dcmi->mclk);
+	pm_runtime_put(dcmi->dev);
 
 	if (dcmi->errors_count)
 		dev_warn(dcmi->dev, "Some errors found while streaming: errors=%d (overrun=%d), buffers=%d\n",
@@ -1707,12 +1709,6 @@ static int dcmi_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	ret = clk_prepare(mclk);
-	if (ret) {
-		dev_err(&pdev->dev, "Unable to prepare mclk %p\n", mclk);
-		goto err_dma_release;
-	}
-
 	spin_lock_init(&dcmi->irqlock);
 	mutex_init(&dcmi->lock);
 	init_completion(&dcmi->complete);
@@ -1728,7 +1724,7 @@ static int dcmi_probe(struct platform_device *pdev)
 	/* Initialize the top-level structure */
 	ret = v4l2_device_register(&pdev->dev, &dcmi->v4l2_dev);
 	if (ret)
-		goto err_clk_unprepare;
+		goto err_dma_release;
 
 	dcmi->vdev = video_device_alloc();
 	if (!dcmi->vdev) {
@@ -1788,14 +1784,15 @@ static int dcmi_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "Probe done\n");
 
 	platform_set_drvdata(pdev, dcmi);
+
+	pm_runtime_enable(&pdev->dev);
+
 	return 0;
 
 err_device_release:
 	video_device_release(dcmi->vdev);
 err_device_unregister:
 	v4l2_device_unregister(&dcmi->v4l2_dev);
-err_clk_unprepare:
-	clk_unprepare(dcmi->mclk);
 err_dma_release:
 	dma_release_channel(dcmi->dma_chan);
 
@@ -1806,20 +1803,72 @@ static int dcmi_remove(struct platform_device *pdev)
 {
 	struct stm32_dcmi *dcmi = platform_get_drvdata(pdev);
 
+	pm_runtime_disable(&pdev->dev);
+
 	v4l2_async_notifier_unregister(&dcmi->notifier);
 	v4l2_device_unregister(&dcmi->v4l2_dev);
-	clk_unprepare(dcmi->mclk);
+
 	dma_release_channel(dcmi->dma_chan);
 
 	return 0;
 }
 
+static __maybe_unused int dcmi_runtime_suspend(struct device *dev)
+{
+	struct stm32_dcmi *dcmi = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(dcmi->mclk);
+
+	return 0;
+}
+
+static __maybe_unused int dcmi_runtime_resume(struct device *dev)
+{
+	struct stm32_dcmi *dcmi = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(dcmi->mclk);
+	if (ret)
+		dev_err(dev, "%s: Failed to prepare_enable clock\n", __func__);
+
+	return ret;
+}
+
+static __maybe_unused int dcmi_suspend(struct device *dev)
+{
+	/* disable clock */
+	pm_runtime_force_suspend(dev);
+
+	/* change pinctrl state */
+	pinctrl_pm_select_sleep_state(dev);
+
+	return 0;
+}
+
+static __maybe_unused int dcmi_resume(struct device *dev)
+{
+	/* restore pinctl default state */
+	pinctrl_pm_select_default_state(dev);
+
+	/* clock enable */
+	pm_runtime_force_resume(dev);
+
+	return 0;
+}
+
+static const struct dev_pm_ops dcmi_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(dcmi_suspend, dcmi_resume)
+	SET_RUNTIME_PM_OPS(dcmi_runtime_suspend,
+			   dcmi_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_dcmi_driver = {
 	.probe		= dcmi_probe,
 	.remove		= dcmi_remove,
 	.driver		= {
 		.name = DRV_NAME,
 		.of_match_table = of_match_ptr(stm32_dcmi_of_match),
+		.pm = &dcmi_pm_ops,
 	},
 };
 
-- 
cgit v1.2.3


From cc00f5845af5ef2e0b8fb921517d57bf5d987917 Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Thu, 7 Jun 2018 16:02:21 -0400
Subject: media: cx25821: remove cx25821-audio-upstream.c and
 cx25821-video-upstream.c

Those two files are unused since commit 486a7a2813c7 ("[media] cx25821: remove cx25821-audio-upstream.c")
and commit b6f21dc3541a ("[media] cx25821: remove video output support")
Remove them from tree.

Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx25821/cx25821-audio-upstream.c | 679 ---------------------
 drivers/media/pci/cx25821/cx25821-audio-upstream.h |  58 --
 drivers/media/pci/cx25821/cx25821-video-upstream.c | 673 --------------------
 drivers/media/pci/cx25821/cx25821-video-upstream.h | 135 ----
 drivers/media/pci/cx25821/cx25821.h                |  12 -
 5 files changed, 1557 deletions(-)
 delete mode 100644 drivers/media/pci/cx25821/cx25821-audio-upstream.c
 delete mode 100644 drivers/media/pci/cx25821/cx25821-audio-upstream.h
 delete mode 100644 drivers/media/pci/cx25821/cx25821-video-upstream.c
 delete mode 100644 drivers/media/pci/cx25821/cx25821-video-upstream.h

diff --git a/drivers/media/pci/cx25821/cx25821-audio-upstream.c b/drivers/media/pci/cx25821/cx25821-audio-upstream.c
deleted file mode 100644
index ada26d4acfb4..000000000000
--- a/drivers/media/pci/cx25821/cx25821-audio-upstream.c
+++ /dev/null
@@ -1,679 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "cx25821-video.h"
-#include "cx25821-audio-upstream.h"
-
-#include <linux/fs.h>
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/syscalls.h>
-#include <linux/file.h>
-#include <linux/fcntl.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-
-MODULE_DESCRIPTION("v4l2 driver module for cx25821 based TV cards");
-MODULE_AUTHOR("Hiep Huynh <hiep.huynh@conexant.com>");
-MODULE_LICENSE("GPL");
-
-static int _intr_msk = FLD_AUD_SRC_RISCI1 | FLD_AUD_SRC_OF |
-			FLD_AUD_SRC_SYNC | FLD_AUD_SRC_OPC_ERR;
-
-static int cx25821_sram_channel_setup_upstream_audio(struct cx25821_dev *dev,
-					      const struct sram_channel *ch,
-					      unsigned int bpl, u32 risc)
-{
-	unsigned int i, lines;
-	u32 cdt;
-
-	if (ch->cmds_start == 0) {
-		cx_write(ch->ptr1_reg, 0);
-		cx_write(ch->ptr2_reg, 0);
-		cx_write(ch->cnt2_reg, 0);
-		cx_write(ch->cnt1_reg, 0);
-		return 0;
-	}
-
-	bpl = (bpl + 7) & ~7;	/* alignment */
-	cdt = ch->cdt;
-	lines = ch->fifo_size / bpl;
-
-	if (lines > 3)
-		lines = 3;
-
-	BUG_ON(lines < 2);
-
-	/* write CDT */
-	for (i = 0; i < lines; i++) {
-		cx_write(cdt + 16 * i, ch->fifo_start + bpl * i);
-		cx_write(cdt + 16 * i + 4, 0);
-		cx_write(cdt + 16 * i + 8, 0);
-		cx_write(cdt + 16 * i + 12, 0);
-	}
-
-	/* write CMDS */
-	cx_write(ch->cmds_start + 0, risc);
-
-	cx_write(ch->cmds_start + 4, 0);
-	cx_write(ch->cmds_start + 8, cdt);
-	cx_write(ch->cmds_start + 12, AUDIO_CDT_SIZE_QW);
-	cx_write(ch->cmds_start + 16, ch->ctrl_start);
-
-	/* IQ size */
-	cx_write(ch->cmds_start + 20, AUDIO_IQ_SIZE_DW);
-
-	for (i = 24; i < 80; i += 4)
-		cx_write(ch->cmds_start + i, 0);
-
-	/* fill registers */
-	cx_write(ch->ptr1_reg, ch->fifo_start);
-	cx_write(ch->ptr2_reg, cdt);
-	cx_write(ch->cnt2_reg, AUDIO_CDT_SIZE_QW);
-	cx_write(ch->cnt1_reg, AUDIO_CLUSTER_SIZE_QW - 1);
-
-	return 0;
-}
-
-static __le32 *cx25821_risc_field_upstream_audio(struct cx25821_dev *dev,
-						 __le32 *rp,
-						 dma_addr_t databuf_phys_addr,
-						 unsigned int bpl,
-						 int fifo_enable)
-{
-	unsigned int line;
-	const struct sram_channel *sram_ch =
-		dev->channels[dev->_audio_upstream_channel].sram_channels;
-	int offset = 0;
-
-	/* scan lines */
-	for (line = 0; line < LINES_PER_AUDIO_BUFFER; line++) {
-		*(rp++) = cpu_to_le32(RISC_READ | RISC_SOL | RISC_EOL | bpl);
-		*(rp++) = cpu_to_le32(databuf_phys_addr + offset);
-		*(rp++) = cpu_to_le32(0);	/* bits 63-32 */
-
-		/* Check if we need to enable the FIFO
-		 * after the first 3 lines.
-		 * For the upstream audio channel,
-		 * the risc engine will enable the FIFO */
-		if (fifo_enable && line == 2) {
-			*(rp++) = RISC_WRITECR;
-			*(rp++) = sram_ch->dma_ctl;
-			*(rp++) = sram_ch->fld_aud_fifo_en;
-			*(rp++) = 0x00000020;
-		}
-
-		offset += AUDIO_LINE_SIZE;
-	}
-
-	return rp;
-}
-
-static int cx25821_risc_buffer_upstream_audio(struct cx25821_dev *dev,
-				       struct pci_dev *pci,
-				       unsigned int bpl, unsigned int lines)
-{
-	__le32 *rp;
-	int fifo_enable = 0;
-	int frame = 0, i = 0;
-	int frame_size = AUDIO_DATA_BUF_SZ;
-	int databuf_offset = 0;
-	int risc_flag = RISC_CNT_INC;
-	dma_addr_t risc_phys_jump_addr;
-
-	/* Virtual address of Risc buffer program */
-	rp = dev->_risc_virt_addr;
-
-	/* sync instruction */
-	*(rp++) = cpu_to_le32(RISC_RESYNC | AUDIO_SYNC_LINE);
-
-	for (frame = 0; frame < NUM_AUDIO_FRAMES; frame++) {
-		databuf_offset = frame_size * frame;
-
-		if (frame == 0) {
-			fifo_enable = 1;
-			risc_flag = RISC_CNT_RESET;
-		} else {
-			fifo_enable = 0;
-			risc_flag = RISC_CNT_INC;
-		}
-
-		/* Calculate physical jump address */
-		if ((frame + 1) == NUM_AUDIO_FRAMES) {
-			risc_phys_jump_addr =
-			    dev->_risc_phys_start_addr +
-			    RISC_SYNC_INSTRUCTION_SIZE;
-		} else {
-			risc_phys_jump_addr =
-			    dev->_risc_phys_start_addr +
-			    RISC_SYNC_INSTRUCTION_SIZE +
-			    AUDIO_RISC_DMA_BUF_SIZE * (frame + 1);
-		}
-
-		rp = cx25821_risc_field_upstream_audio(dev, rp,
-				dev->_audiodata_buf_phys_addr + databuf_offset,
-				bpl, fifo_enable);
-
-		if (USE_RISC_NOOP_AUDIO) {
-			for (i = 0; i < NUM_NO_OPS; i++)
-				*(rp++) = cpu_to_le32(RISC_NOOP);
-		}
-
-		/* Loop to (Nth)FrameRISC or to Start of Risc program &
-		 * generate IRQ */
-		*(rp++) = cpu_to_le32(RISC_JUMP | RISC_IRQ1 | risc_flag);
-		*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-		*(rp++) = cpu_to_le32(0);
-
-		/* Recalculate virtual address based on frame index */
-		rp = dev->_risc_virt_addr + RISC_SYNC_INSTRUCTION_SIZE / 4 +
-			(AUDIO_RISC_DMA_BUF_SIZE * (frame + 1) / 4);
-	}
-
-	return 0;
-}
-
-static void cx25821_free_memory_audio(struct cx25821_dev *dev)
-{
-	if (dev->_risc_virt_addr) {
-		pci_free_consistent(dev->pci, dev->_audiorisc_size,
-				    dev->_risc_virt_addr, dev->_risc_phys_addr);
-		dev->_risc_virt_addr = NULL;
-	}
-
-	if (dev->_audiodata_buf_virt_addr) {
-		pci_free_consistent(dev->pci, dev->_audiodata_buf_size,
-				    dev->_audiodata_buf_virt_addr,
-				    dev->_audiodata_buf_phys_addr);
-		dev->_audiodata_buf_virt_addr = NULL;
-	}
-}
-
-void cx25821_stop_upstream_audio(struct cx25821_dev *dev)
-{
-	const struct sram_channel *sram_ch =
-		dev->channels[AUDIO_UPSTREAM_SRAM_CHANNEL_B].sram_channels;
-	u32 tmp = 0;
-
-	if (!dev->_audio_is_running) {
-		printk(KERN_DEBUG
-		       pr_fmt("No audio file is currently running so return!\n"));
-		return;
-	}
-	/* Disable RISC interrupts */
-	cx_write(sram_ch->int_msk, 0);
-
-	/* Turn OFF risc and fifo enable in AUD_DMA_CNTRL */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_write(sram_ch->dma_ctl,
-		 tmp & ~(sram_ch->fld_aud_fifo_en | sram_ch->fld_aud_risc_en));
-
-	/* Clear data buffer memory */
-	if (dev->_audiodata_buf_virt_addr)
-		memset(dev->_audiodata_buf_virt_addr, 0,
-		       dev->_audiodata_buf_size);
-
-	dev->_audio_is_running = 0;
-	dev->_is_first_audio_frame = 0;
-	dev->_audioframe_count = 0;
-	dev->_audiofile_status = END_OF_FILE;
-
-	flush_work(&dev->_audio_work_entry);
-
-	kfree(dev->_audiofilename);
-}
-
-void cx25821_free_mem_upstream_audio(struct cx25821_dev *dev)
-{
-	if (dev->_audio_is_running)
-		cx25821_stop_upstream_audio(dev);
-
-	cx25821_free_memory_audio(dev);
-}
-
-static int cx25821_get_audio_data(struct cx25821_dev *dev,
-			   const struct sram_channel *sram_ch)
-{
-	struct file *file;
-	int frame_index_temp = dev->_audioframe_index;
-	int i = 0;
-	int frame_size = AUDIO_DATA_BUF_SZ;
-	int frame_offset = frame_size * frame_index_temp;
-	char mybuf[AUDIO_LINE_SIZE];
-	loff_t file_offset = dev->_audioframe_count * frame_size;
-	char *p = NULL;
-
-	if (dev->_audiofile_status == END_OF_FILE)
-		return 0;
-
-	file = filp_open(dev->_audiofilename, O_RDONLY | O_LARGEFILE, 0);
-	if (IS_ERR(file)) {
-		pr_err("%s(): ERROR opening file(%s) with errno = %ld!\n",
-		       __func__, dev->_audiofilename, -PTR_ERR(file));
-		return PTR_ERR(file);
-	}
-
-	if (dev->_audiodata_buf_virt_addr)
-		p = (char *)dev->_audiodata_buf_virt_addr + frame_offset;
-
-	for (i = 0; i < dev->_audio_lines_count; i++) {
-		int n = kernel_read(file, mybuf, AUDIO_LINE_SIZE, &file_offset);
-		if (n < AUDIO_LINE_SIZE) {
-			pr_info("Done: exit %s() since no more bytes to read from Audio file\n",
-				__func__);
-			dev->_audiofile_status = END_OF_FILE;
-			fput(file);
-			return 0;
-		}
-		dev->_audiofile_status = IN_PROGRESS;
-		if (p) {
-			memcpy(p, mybuf, n);
-			p += n;
-		}
-	}
-	dev->_audioframe_count++;
-	fput(file);
-
-	return 0;
-}
-
-static void cx25821_audioups_handler(struct work_struct *work)
-{
-	struct cx25821_dev *dev = container_of(work, struct cx25821_dev,
-			_audio_work_entry);
-
-	if (!dev) {
-		pr_err("ERROR %s(): since container_of(work_struct) FAILED!\n",
-			__func__);
-		return;
-	}
-
-	cx25821_get_audio_data(dev, dev->channels[dev->_audio_upstream_channel].
-			sram_channels);
-}
-
-static int cx25821_openfile_audio(struct cx25821_dev *dev,
-			   const struct sram_channel *sram_ch)
-{
-	char *p = (void *)dev->_audiodata_buf_virt_addr;
-	struct file *file;
-	loff_t file_offset = 0;
-	int i, j;
-
-	file = filp_open(dev->_audiofilename, O_RDONLY | O_LARGEFILE, 0);
-	if (IS_ERR(file)) {
-		pr_err("%s(): ERROR opening file(%s) with errno = %ld!\n",
-			__func__, dev->_audiofilename, PTR_ERR(file));
-		return PTR_ERR(file);
-	}
-
-	for (j = 0; j < NUM_AUDIO_FRAMES; j++) {
-		for (i = 0; i < dev->_audio_lines_count; i++) {
-			char buf[AUDIO_LINE_SIZE];
-			loff_t offset = file_offset;
-			int n = kernel_read(file, buf, AUDIO_LINE_SIZE, &file_offset);
-
-			if (n < AUDIO_LINE_SIZE) {
-				pr_info("Done: exit %s() since no more bytes to read from Audio file\n",
-					__func__);
-				dev->_audiofile_status = END_OF_FILE;
-				fput(file);
-				return 0;
-			}
-
-			if (p)
-				memcpy(p + offset, buf, n);
-		}
-		dev->_audioframe_count++;
-	}
-	dev->_audiofile_status = IN_PROGRESS;
-	fput(file);
-	return 0;
-}
-
-static int cx25821_audio_upstream_buffer_prepare(struct cx25821_dev *dev,
-						 const struct sram_channel *sram_ch,
-						 int bpl)
-{
-	int ret = 0;
-	dma_addr_t dma_addr;
-	dma_addr_t data_dma_addr;
-
-	cx25821_free_memory_audio(dev);
-
-	dev->_risc_virt_addr = pci_alloc_consistent(dev->pci,
-			dev->audio_upstream_riscbuf_size, &dma_addr);
-	dev->_risc_virt_start_addr = dev->_risc_virt_addr;
-	dev->_risc_phys_start_addr = dma_addr;
-	dev->_risc_phys_addr = dma_addr;
-	dev->_audiorisc_size = dev->audio_upstream_riscbuf_size;
-
-	if (!dev->_risc_virt_addr) {
-		printk(KERN_DEBUG
-			pr_fmt("ERROR: pci_alloc_consistent() FAILED to allocate memory for RISC program! Returning\n"));
-		return -ENOMEM;
-	}
-	/* Clear out memory at address */
-	memset(dev->_risc_virt_addr, 0, dev->_audiorisc_size);
-
-	/* For Audio Data buffer allocation */
-	dev->_audiodata_buf_virt_addr = pci_alloc_consistent(dev->pci,
-			dev->audio_upstream_databuf_size, &data_dma_addr);
-	dev->_audiodata_buf_phys_addr = data_dma_addr;
-	dev->_audiodata_buf_size = dev->audio_upstream_databuf_size;
-
-	if (!dev->_audiodata_buf_virt_addr) {
-		printk(KERN_DEBUG
-			pr_fmt("ERROR: pci_alloc_consistent() FAILED to allocate memory for data buffer! Returning\n"));
-		return -ENOMEM;
-	}
-	/* Clear out memory at address */
-	memset(dev->_audiodata_buf_virt_addr, 0, dev->_audiodata_buf_size);
-
-	ret = cx25821_openfile_audio(dev, sram_ch);
-	if (ret < 0)
-		return ret;
-
-	/* Creating RISC programs */
-	ret = cx25821_risc_buffer_upstream_audio(dev, dev->pci, bpl,
-						dev->_audio_lines_count);
-	if (ret < 0) {
-		printk(KERN_DEBUG
-			pr_fmt("ERROR creating audio upstream RISC programs!\n"));
-		goto error;
-	}
-
-	return 0;
-
-error:
-	return ret;
-}
-
-static int cx25821_audio_upstream_irq(struct cx25821_dev *dev, int chan_num,
-			       u32 status)
-{
-	int i = 0;
-	u32 int_msk_tmp;
-	const struct sram_channel *channel = dev->channels[chan_num].sram_channels;
-	dma_addr_t risc_phys_jump_addr;
-	__le32 *rp;
-
-	if (status & FLD_AUD_SRC_RISCI1) {
-		/* Get interrupt_index of the program that interrupted */
-		u32 prog_cnt = cx_read(channel->gpcnt);
-
-		/* Since we've identified our IRQ, clear our bits from the
-		 * interrupt mask and interrupt status registers */
-		cx_write(channel->int_msk, 0);
-		cx_write(channel->int_stat, cx_read(channel->int_stat));
-
-		spin_lock(&dev->slock);
-
-		while (prog_cnt != dev->_last_index_irq) {
-			/* Update _last_index_irq */
-			if (dev->_last_index_irq < (NUMBER_OF_PROGRAMS - 1))
-				dev->_last_index_irq++;
-			else
-				dev->_last_index_irq = 0;
-
-			dev->_audioframe_index = dev->_last_index_irq;
-
-			schedule_work(&dev->_audio_work_entry);
-		}
-
-		if (dev->_is_first_audio_frame) {
-			dev->_is_first_audio_frame = 0;
-
-			if (dev->_risc_virt_start_addr != NULL) {
-				risc_phys_jump_addr =
-					dev->_risc_phys_start_addr +
-					RISC_SYNC_INSTRUCTION_SIZE +
-					AUDIO_RISC_DMA_BUF_SIZE;
-
-				rp = cx25821_risc_field_upstream_audio(dev,
-						dev->_risc_virt_start_addr + 1,
-						dev->_audiodata_buf_phys_addr,
-						AUDIO_LINE_SIZE, FIFO_DISABLE);
-
-				if (USE_RISC_NOOP_AUDIO) {
-					for (i = 0; i < NUM_NO_OPS; i++) {
-						*(rp++) =
-						    cpu_to_le32(RISC_NOOP);
-					}
-				}
-				/* Jump to 2nd Audio Frame */
-				*(rp++) = cpu_to_le32(RISC_JUMP | RISC_IRQ1 |
-						RISC_CNT_RESET);
-				*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-				*(rp++) = cpu_to_le32(0);
-			}
-		}
-
-		spin_unlock(&dev->slock);
-	} else {
-		if (status & FLD_AUD_SRC_OF)
-			pr_warn("%s(): Audio Received Overflow Error Interrupt!\n",
-				__func__);
-
-		if (status & FLD_AUD_SRC_SYNC)
-			pr_warn("%s(): Audio Received Sync Error Interrupt!\n",
-				__func__);
-
-		if (status & FLD_AUD_SRC_OPC_ERR)
-			pr_warn("%s(): Audio Received OpCode Error Interrupt!\n",
-				__func__);
-
-		/* Read and write back the interrupt status register to clear
-		 * our bits */
-		cx_write(channel->int_stat, cx_read(channel->int_stat));
-	}
-
-	if (dev->_audiofile_status == END_OF_FILE) {
-		pr_warn("EOF Channel Audio Framecount = %d\n",
-			dev->_audioframe_count);
-		return -1;
-	}
-	/* ElSE, set the interrupt mask register, re-enable irq. */
-	int_msk_tmp = cx_read(channel->int_msk);
-	cx_write(channel->int_msk, int_msk_tmp |= _intr_msk);
-
-	return 0;
-}
-
-static irqreturn_t cx25821_upstream_irq_audio(int irq, void *dev_id)
-{
-	struct cx25821_dev *dev = dev_id;
-	u32 audio_status;
-	int handled = 0;
-	const struct sram_channel *sram_ch;
-
-	if (!dev)
-		return -1;
-
-	sram_ch = dev->channels[dev->_audio_upstream_channel].sram_channels;
-
-	audio_status = cx_read(sram_ch->int_stat);
-
-	/* Only deal with our interrupt */
-	if (audio_status) {
-		handled = cx25821_audio_upstream_irq(dev,
-				dev->_audio_upstream_channel, audio_status);
-	}
-
-	if (handled < 0)
-		cx25821_stop_upstream_audio(dev);
-	else
-		handled += handled;
-
-	return IRQ_RETVAL(handled);
-}
-
-static void cx25821_wait_fifo_enable(struct cx25821_dev *dev,
-				     const struct sram_channel *sram_ch)
-{
-	int count = 0;
-	u32 tmp;
-
-	do {
-		/* Wait 10 microsecond before checking to see if the FIFO is
-		 * turned ON. */
-		udelay(10);
-
-		tmp = cx_read(sram_ch->dma_ctl);
-
-		/* 10 millisecond timeout */
-		if (count++ > 1000) {
-			pr_err("ERROR: %s() fifo is NOT turned on. Timeout!\n",
-				__func__);
-			return;
-		}
-
-	} while (!(tmp & sram_ch->fld_aud_fifo_en));
-
-}
-
-static int cx25821_start_audio_dma_upstream(struct cx25821_dev *dev,
-					    const struct sram_channel *sram_ch)
-{
-	u32 tmp = 0;
-	int err = 0;
-
-	/* Set the physical start address of the RISC program in the initial
-	 * program counter(IPC) member of the CMDS. */
-	cx_write(sram_ch->cmds_start + 0, dev->_risc_phys_addr);
-	/* Risc IPC High 64 bits 63-32 */
-	cx_write(sram_ch->cmds_start + 4, 0);
-
-	/* reset counter */
-	cx_write(sram_ch->gpcnt_ctl, 3);
-
-	/* Set the line length       (It looks like we do not need to set the
-	 * line length) */
-	cx_write(sram_ch->aud_length, AUDIO_LINE_SIZE & FLD_AUD_DST_LN_LNGTH);
-
-	/* Set the input mode to 16-bit */
-	tmp = cx_read(sram_ch->aud_cfg);
-	tmp |= FLD_AUD_SRC_ENABLE | FLD_AUD_DST_PK_MODE | FLD_AUD_CLK_ENABLE |
-		FLD_AUD_MASTER_MODE | FLD_AUD_CLK_SELECT_PLL_D |
-		FLD_AUD_SONY_MODE;
-	cx_write(sram_ch->aud_cfg, tmp);
-
-	/* Read and write back the interrupt status register to clear it */
-	tmp = cx_read(sram_ch->int_stat);
-	cx_write(sram_ch->int_stat, tmp);
-
-	/* Clear our bits from the interrupt status register. */
-	cx_write(sram_ch->int_stat, _intr_msk);
-
-	/* Set the interrupt mask register, enable irq. */
-	cx_set(PCI_INT_MSK, cx_read(PCI_INT_MSK) | (1 << sram_ch->irq_bit));
-	tmp = cx_read(sram_ch->int_msk);
-	cx_write(sram_ch->int_msk, tmp |= _intr_msk);
-
-	err = request_irq(dev->pci->irq, cx25821_upstream_irq_audio,
-			IRQF_SHARED, dev->name, dev);
-	if (err < 0) {
-		pr_err("%s: can't get upstream IRQ %d\n", dev->name,
-				dev->pci->irq);
-		goto fail_irq;
-	}
-
-	/* Start the DMA  engine */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_set(sram_ch->dma_ctl, tmp | sram_ch->fld_aud_risc_en);
-
-	dev->_audio_is_running = 1;
-	dev->_is_first_audio_frame = 1;
-
-	/* The fifo_en bit turns on by the first Risc program */
-	cx25821_wait_fifo_enable(dev, sram_ch);
-
-	return 0;
-
-fail_irq:
-	cx25821_dev_unregister(dev);
-	return err;
-}
-
-int cx25821_audio_upstream_init(struct cx25821_dev *dev, int channel_select)
-{
-	const struct sram_channel *sram_ch;
-	int err = 0;
-
-	if (dev->_audio_is_running) {
-		pr_warn("Audio Channel is still running so return!\n");
-		return 0;
-	}
-
-	dev->_audio_upstream_channel = channel_select;
-	sram_ch = dev->channels[channel_select].sram_channels;
-
-	/* Work queue */
-	INIT_WORK(&dev->_audio_work_entry, cx25821_audioups_handler);
-
-	dev->_last_index_irq = 0;
-	dev->_audio_is_running = 0;
-	dev->_audioframe_count = 0;
-	dev->_audiofile_status = RESET_STATUS;
-	dev->_audio_lines_count = LINES_PER_AUDIO_BUFFER;
-	_line_size = AUDIO_LINE_SIZE;
-
-	if ((dev->input_audiofilename) &&
-	    (strcmp(dev->input_audiofilename, "") != 0))
-		dev->_audiofilename = kstrdup(dev->input_audiofilename,
-					      GFP_KERNEL);
-	else
-		dev->_audiofilename = kstrdup(_defaultAudioName,
-					      GFP_KERNEL);
-
-	if (!dev->_audiofilename) {
-		err = -ENOMEM;
-		goto error;
-	}
-
-	cx25821_sram_channel_setup_upstream_audio(dev, sram_ch,
-						  _line_size, 0);
-
-	dev->audio_upstream_riscbuf_size =
-		AUDIO_RISC_DMA_BUF_SIZE * NUM_AUDIO_PROGS +
-		RISC_SYNC_INSTRUCTION_SIZE;
-	dev->audio_upstream_databuf_size = AUDIO_DATA_BUF_SZ * NUM_AUDIO_PROGS;
-
-	/* Allocating buffers and prepare RISC program */
-	err = cx25821_audio_upstream_buffer_prepare(dev, sram_ch,
-							_line_size);
-	if (err < 0) {
-		pr_err("%s: Failed to set up Audio upstream buffers!\n",
-			dev->name);
-		goto error;
-	}
-	/* Start RISC engine */
-	cx25821_start_audio_dma_upstream(dev, sram_ch);
-
-	return 0;
-
-error:
-	cx25821_dev_unregister(dev);
-
-	return err;
-}
diff --git a/drivers/media/pci/cx25821/cx25821-audio-upstream.h b/drivers/media/pci/cx25821/cx25821-audio-upstream.h
deleted file mode 100644
index 2bc875d1ec9f..000000000000
--- a/drivers/media/pci/cx25821/cx25821-audio-upstream.h
+++ /dev/null
@@ -1,58 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#include <linux/mutex.h>
-#include <linux/workqueue.h>
-
-#define NUM_AUDIO_PROGS       8
-#define NUM_AUDIO_FRAMES      8
-#define END_OF_FILE           0
-#define IN_PROGRESS           1
-#define RESET_STATUS          -1
-#define FIFO_DISABLE          0
-#define FIFO_ENABLE           1
-#define NUM_NO_OPS            4
-
-#define RISC_READ_INSTRUCTION_SIZE      12
-#define RISC_JUMP_INSTRUCTION_SIZE      12
-#define RISC_WRITECR_INSTRUCTION_SIZE   16
-#define RISC_SYNC_INSTRUCTION_SIZE      4
-#define DWORD_SIZE                      4
-#define AUDIO_SYNC_LINE                 4
-
-#define LINES_PER_AUDIO_BUFFER      15
-#define AUDIO_LINE_SIZE             128
-#define AUDIO_DATA_BUF_SZ           (AUDIO_LINE_SIZE * LINES_PER_AUDIO_BUFFER)
-
-#define USE_RISC_NOOP_AUDIO   1
-
-#ifdef USE_RISC_NOOP_AUDIO
-#define AUDIO_RISC_DMA_BUF_SIZE						\
-	(LINES_PER_AUDIO_BUFFER * RISC_READ_INSTRUCTION_SIZE +		\
-	 RISC_WRITECR_INSTRUCTION_SIZE + NUM_NO_OPS * DWORD_SIZE +	\
-	 RISC_JUMP_INSTRUCTION_SIZE)
-#endif
-
-#ifndef USE_RISC_NOOP_AUDIO
-#define AUDIO_RISC_DMA_BUF_SIZE						\
-	(LINES_PER_AUDIO_BUFFER * RISC_READ_INSTRUCTION_SIZE +		\
-	 RISC_WRITECR_INSTRUCTION_SIZE + RISC_JUMP_INSTRUCTION_SIZE)
-#endif
-
-static int _line_size;
-char *_defaultAudioName = "/root/audioGOOD.wav";
diff --git a/drivers/media/pci/cx25821/cx25821-video-upstream.c b/drivers/media/pci/cx25821/cx25821-video-upstream.c
deleted file mode 100644
index 6c838c8a7924..000000000000
--- a/drivers/media/pci/cx25821/cx25821-video-upstream.c
+++ /dev/null
@@ -1,673 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include "cx25821-video.h"
-#include "cx25821-video-upstream.h"
-
-#include <linux/errno.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-
-MODULE_DESCRIPTION("v4l2 driver module for cx25821 based TV cards");
-MODULE_AUTHOR("Hiep Huynh <hiep.huynh@conexant.com>");
-MODULE_LICENSE("GPL");
-
-static int _intr_msk = FLD_VID_SRC_RISC1 | FLD_VID_SRC_UF | FLD_VID_SRC_SYNC |
-			FLD_VID_SRC_OPC_ERR;
-
-int cx25821_sram_channel_setup_upstream(struct cx25821_dev *dev,
-					const struct sram_channel *ch,
-					unsigned int bpl, u32 risc)
-{
-	unsigned int i, lines;
-	u32 cdt;
-
-	if (ch->cmds_start == 0) {
-		cx_write(ch->ptr1_reg, 0);
-		cx_write(ch->ptr2_reg, 0);
-		cx_write(ch->cnt2_reg, 0);
-		cx_write(ch->cnt1_reg, 0);
-		return 0;
-	}
-
-	bpl = (bpl + 7) & ~7;	/* alignment */
-	cdt = ch->cdt;
-	lines = ch->fifo_size / bpl;
-
-	if (lines > 4)
-		lines = 4;
-
-	BUG_ON(lines < 2);
-
-	/* write CDT */
-	for (i = 0; i < lines; i++) {
-		cx_write(cdt + 16 * i, ch->fifo_start + bpl * i);
-		cx_write(cdt + 16 * i + 4, 0);
-		cx_write(cdt + 16 * i + 8, 0);
-		cx_write(cdt + 16 * i + 12, 0);
-	}
-
-	/* write CMDS */
-	cx_write(ch->cmds_start + 0, risc);
-
-	cx_write(ch->cmds_start + 4, 0);
-	cx_write(ch->cmds_start + 8, cdt);
-	cx_write(ch->cmds_start + 12, (lines * 16) >> 3);
-	cx_write(ch->cmds_start + 16, ch->ctrl_start);
-
-	cx_write(ch->cmds_start + 20, VID_IQ_SIZE_DW);
-
-	for (i = 24; i < 80; i += 4)
-		cx_write(ch->cmds_start + i, 0);
-
-	/* fill registers */
-	cx_write(ch->ptr1_reg, ch->fifo_start);
-	cx_write(ch->ptr2_reg, cdt);
-	cx_write(ch->cnt2_reg, (lines * 16) >> 3);
-	cx_write(ch->cnt1_reg, (bpl >> 3) - 1);
-
-	return 0;
-}
-
-static __le32 *cx25821_update_riscprogram(struct cx25821_channel *chan,
-					  __le32 *rp, unsigned int offset,
-					  unsigned int bpl, u32 sync_line,
-					  unsigned int lines, int fifo_enable,
-					  int field_type)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	unsigned int line, i;
-	int dist_betwn_starts = bpl * 2;
-
-	*(rp++) = cpu_to_le32(RISC_RESYNC | sync_line);
-
-	if (USE_RISC_NOOP_VIDEO) {
-		for (i = 0; i < NUM_NO_OPS; i++)
-			*(rp++) = cpu_to_le32(RISC_NOOP);
-	}
-
-	/* scan lines */
-	for (line = 0; line < lines; line++) {
-		*(rp++) = cpu_to_le32(RISC_READ | RISC_SOL | RISC_EOL | bpl);
-		*(rp++) = cpu_to_le32(out->_data_buf_phys_addr + offset);
-		*(rp++) = cpu_to_le32(0);	/* bits 63-32 */
-
-		if ((lines <= NTSC_FIELD_HEIGHT)
-		    || (line < (NTSC_FIELD_HEIGHT - 1)) || !(out->is_60hz)) {
-			offset += dist_betwn_starts;
-		}
-	}
-
-	return rp;
-}
-
-static __le32 *cx25821_risc_field_upstream(struct cx25821_channel *chan, __le32 *rp,
-					   dma_addr_t databuf_phys_addr,
-					   unsigned int offset, u32 sync_line,
-					   unsigned int bpl, unsigned int lines,
-					   int fifo_enable, int field_type)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	unsigned int line, i;
-	const struct sram_channel *sram_ch = chan->sram_channels;
-	int dist_betwn_starts = bpl * 2;
-
-	/* sync instruction */
-	if (sync_line != NO_SYNC_LINE)
-		*(rp++) = cpu_to_le32(RISC_RESYNC | sync_line);
-
-	if (USE_RISC_NOOP_VIDEO) {
-		for (i = 0; i < NUM_NO_OPS; i++)
-			*(rp++) = cpu_to_le32(RISC_NOOP);
-	}
-
-	/* scan lines */
-	for (line = 0; line < lines; line++) {
-		*(rp++) = cpu_to_le32(RISC_READ | RISC_SOL | RISC_EOL | bpl);
-		*(rp++) = cpu_to_le32(databuf_phys_addr + offset);
-		*(rp++) = cpu_to_le32(0);	/* bits 63-32 */
-
-		if ((lines <= NTSC_FIELD_HEIGHT)
-		    || (line < (NTSC_FIELD_HEIGHT - 1)) || !(out->is_60hz))
-			/* to skip the other field line */
-			offset += dist_betwn_starts;
-
-		/* check if we need to enable the FIFO after the first 4 lines
-		 * For the upstream video channel, the risc engine will enable
-		 * the FIFO. */
-		if (fifo_enable && line == 3) {
-			*(rp++) = cpu_to_le32(RISC_WRITECR);
-			*(rp++) = cpu_to_le32(sram_ch->dma_ctl);
-			*(rp++) = cpu_to_le32(FLD_VID_FIFO_EN);
-			*(rp++) = cpu_to_le32(0x00000001);
-		}
-	}
-
-	return rp;
-}
-
-static int cx25821_risc_buffer_upstream(struct cx25821_channel *chan,
-					struct pci_dev *pci,
-					unsigned int top_offset,
-					unsigned int bpl, unsigned int lines)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	__le32 *rp;
-	int fifo_enable = 0;
-	/* get line count for single field */
-	int singlefield_lines = lines >> 1;
-	int odd_num_lines = singlefield_lines;
-	int frame = 0;
-	int frame_size = 0;
-	int databuf_offset = 0;
-	int risc_program_size = 0;
-	int risc_flag = RISC_CNT_RESET;
-	unsigned int bottom_offset = bpl;
-	dma_addr_t risc_phys_jump_addr;
-
-	if (out->is_60hz) {
-		odd_num_lines = singlefield_lines + 1;
-		risc_program_size = FRAME1_VID_PROG_SIZE;
-		frame_size = (bpl == Y411_LINE_SZ) ?
-			FRAME_SIZE_NTSC_Y411 : FRAME_SIZE_NTSC_Y422;
-	} else {
-		risc_program_size = PAL_VID_PROG_SIZE;
-		frame_size = (bpl == Y411_LINE_SZ) ?
-			FRAME_SIZE_PAL_Y411 : FRAME_SIZE_PAL_Y422;
-	}
-
-	/* Virtual address of Risc buffer program */
-	rp = out->_dma_virt_addr;
-
-	for (frame = 0; frame < NUM_FRAMES; frame++) {
-		databuf_offset = frame_size * frame;
-
-		if (UNSET != top_offset) {
-			fifo_enable = (frame == 0) ? FIFO_ENABLE : FIFO_DISABLE;
-			rp = cx25821_risc_field_upstream(chan, rp,
-					out->_data_buf_phys_addr +
-					databuf_offset, top_offset, 0, bpl,
-					odd_num_lines, fifo_enable, ODD_FIELD);
-		}
-
-		fifo_enable = FIFO_DISABLE;
-
-		/* Even Field */
-		rp = cx25821_risc_field_upstream(chan, rp,
-						 out->_data_buf_phys_addr +
-						 databuf_offset, bottom_offset,
-						 0x200, bpl, singlefield_lines,
-						 fifo_enable, EVEN_FIELD);
-
-		if (frame == 0) {
-			risc_flag = RISC_CNT_RESET;
-			risc_phys_jump_addr = out->_dma_phys_start_addr +
-				risc_program_size;
-		} else {
-			risc_phys_jump_addr = out->_dma_phys_start_addr;
-			risc_flag = RISC_CNT_INC;
-		}
-
-		/* Loop to 2ndFrameRISC or to Start of Risc
-		 * program & generate IRQ
-		 */
-		*(rp++) = cpu_to_le32(RISC_JUMP | RISC_IRQ1 | risc_flag);
-		*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-		*(rp++) = cpu_to_le32(0);
-	}
-
-	return 0;
-}
-
-void cx25821_stop_upstream_video(struct cx25821_channel *chan)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	const struct sram_channel *sram_ch = chan->sram_channels;
-	u32 tmp = 0;
-
-	if (!out->_is_running) {
-		pr_info("No video file is currently running so return!\n");
-		return;
-	}
-
-	/* Set the interrupt mask register, disable irq. */
-	cx_set(PCI_INT_MSK, cx_read(PCI_INT_MSK) & ~(1 << sram_ch->irq_bit));
-
-	/* Disable RISC interrupts */
-	tmp = cx_read(sram_ch->int_msk);
-	cx_write(sram_ch->int_msk, tmp & ~_intr_msk);
-
-	/* Turn OFF risc and fifo enable */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_write(sram_ch->dma_ctl, tmp & ~(FLD_VID_FIFO_EN | FLD_VID_RISC_EN));
-
-	free_irq(dev->pci->irq, chan);
-
-	/* Clear data buffer memory */
-	if (out->_data_buf_virt_addr)
-		memset(out->_data_buf_virt_addr, 0, out->_data_buf_size);
-
-	out->_is_running = 0;
-	out->_is_first_frame = 0;
-	out->_frame_count = 0;
-	out->_file_status = END_OF_FILE;
-
-	tmp = cx_read(VID_CH_MODE_SEL);
-	cx_write(VID_CH_MODE_SEL, tmp & 0xFFFFFE00);
-}
-
-void cx25821_free_mem_upstream(struct cx25821_channel *chan)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-
-	if (out->_is_running)
-		cx25821_stop_upstream_video(chan);
-
-	if (out->_dma_virt_addr) {
-		pci_free_consistent(dev->pci, out->_risc_size,
-				    out->_dma_virt_addr, out->_dma_phys_addr);
-		out->_dma_virt_addr = NULL;
-	}
-
-	if (out->_data_buf_virt_addr) {
-		pci_free_consistent(dev->pci, out->_data_buf_size,
-				    out->_data_buf_virt_addr,
-				    out->_data_buf_phys_addr);
-		out->_data_buf_virt_addr = NULL;
-	}
-}
-
-int cx25821_write_frame(struct cx25821_channel *chan,
-		const char __user *data, size_t count)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	int line_size = (out->_pixel_format == PIXEL_FRMT_411) ?
-		Y411_LINE_SZ : Y422_LINE_SZ;
-	int frame_size = 0;
-	int frame_offset = 0;
-	int curpos = out->curpos;
-
-	if (out->is_60hz)
-		frame_size = (line_size == Y411_LINE_SZ) ?
-			FRAME_SIZE_NTSC_Y411 : FRAME_SIZE_NTSC_Y422;
-	else
-		frame_size = (line_size == Y411_LINE_SZ) ?
-			FRAME_SIZE_PAL_Y411 : FRAME_SIZE_PAL_Y422;
-
-	if (curpos == 0) {
-		out->cur_frame_index = out->_frame_index;
-		if (wait_event_interruptible(out->waitq, out->cur_frame_index != out->_frame_index))
-			return -EINTR;
-		out->cur_frame_index = out->_frame_index;
-	}
-
-	frame_offset = out->cur_frame_index ? frame_size : 0;
-
-	if (frame_size - curpos < count)
-		count = frame_size - curpos;
-	if (copy_from_user((__force char *)out->_data_buf_virt_addr + frame_offset + curpos,
-				data, count))
-		return -EFAULT;
-	curpos += count;
-	if (curpos == frame_size) {
-		out->_frame_count++;
-		curpos = 0;
-	}
-	out->curpos = curpos;
-
-	return count;
-}
-
-static int cx25821_upstream_buffer_prepare(struct cx25821_channel *chan,
-					   const struct sram_channel *sram_ch,
-					   int bpl)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	int ret = 0;
-	dma_addr_t dma_addr;
-	dma_addr_t data_dma_addr;
-
-	if (out->_dma_virt_addr != NULL)
-		pci_free_consistent(dev->pci, out->upstream_riscbuf_size,
-				out->_dma_virt_addr, out->_dma_phys_addr);
-
-	out->_dma_virt_addr = pci_alloc_consistent(dev->pci,
-			out->upstream_riscbuf_size, &dma_addr);
-	out->_dma_virt_start_addr = out->_dma_virt_addr;
-	out->_dma_phys_start_addr = dma_addr;
-	out->_dma_phys_addr = dma_addr;
-	out->_risc_size = out->upstream_riscbuf_size;
-
-	if (!out->_dma_virt_addr) {
-		pr_err("FAILED to allocate memory for Risc buffer! Returning\n");
-		return -ENOMEM;
-	}
-
-	/* Clear memory at address */
-	memset(out->_dma_virt_addr, 0, out->_risc_size);
-
-	if (out->_data_buf_virt_addr != NULL)
-		pci_free_consistent(dev->pci, out->upstream_databuf_size,
-				out->_data_buf_virt_addr,
-				out->_data_buf_phys_addr);
-	/* For Video Data buffer allocation */
-	out->_data_buf_virt_addr = pci_alloc_consistent(dev->pci,
-			out->upstream_databuf_size, &data_dma_addr);
-	out->_data_buf_phys_addr = data_dma_addr;
-	out->_data_buf_size = out->upstream_databuf_size;
-
-	if (!out->_data_buf_virt_addr) {
-		pr_err("FAILED to allocate memory for data buffer! Returning\n");
-		return -ENOMEM;
-	}
-
-	/* Clear memory at address */
-	memset(out->_data_buf_virt_addr, 0, out->_data_buf_size);
-
-	/* Create RISC programs */
-	ret = cx25821_risc_buffer_upstream(chan, dev->pci, 0, bpl,
-			out->_lines_count);
-	if (ret < 0) {
-		pr_info("Failed creating Video Upstream Risc programs!\n");
-		goto error;
-	}
-
-	return 0;
-
-error:
-	return ret;
-}
-
-static int cx25821_video_upstream_irq(struct cx25821_channel *chan, u32 status)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	u32 int_msk_tmp;
-	const struct sram_channel *channel = chan->sram_channels;
-	int singlefield_lines = NTSC_FIELD_HEIGHT;
-	int line_size_in_bytes = Y422_LINE_SZ;
-	int odd_risc_prog_size = 0;
-	dma_addr_t risc_phys_jump_addr;
-	__le32 *rp;
-
-	if (status & FLD_VID_SRC_RISC1) {
-		/* We should only process one program per call */
-		u32 prog_cnt = cx_read(channel->gpcnt);
-
-		/* Since we've identified our IRQ, clear our bits from the
-		 * interrupt mask and interrupt status registers */
-		int_msk_tmp = cx_read(channel->int_msk);
-		cx_write(channel->int_msk, int_msk_tmp & ~_intr_msk);
-		cx_write(channel->int_stat, _intr_msk);
-
-		wake_up(&out->waitq);
-
-		spin_lock(&dev->slock);
-
-		out->_frame_index = prog_cnt;
-
-		if (out->_is_first_frame) {
-			out->_is_first_frame = 0;
-
-			if (out->is_60hz) {
-				singlefield_lines += 1;
-				odd_risc_prog_size = ODD_FLD_NTSC_PROG_SIZE;
-			} else {
-				singlefield_lines = PAL_FIELD_HEIGHT;
-				odd_risc_prog_size = ODD_FLD_PAL_PROG_SIZE;
-			}
-
-			if (out->_dma_virt_start_addr != NULL) {
-				line_size_in_bytes =
-				    (out->_pixel_format ==
-				     PIXEL_FRMT_411) ? Y411_LINE_SZ :
-				    Y422_LINE_SZ;
-				risc_phys_jump_addr =
-				    out->_dma_phys_start_addr +
-				    odd_risc_prog_size;
-
-				rp = cx25821_update_riscprogram(chan,
-					out->_dma_virt_start_addr, TOP_OFFSET,
-					line_size_in_bytes, 0x0,
-					singlefield_lines, FIFO_DISABLE,
-					ODD_FIELD);
-
-				/* Jump to Even Risc program of 1st Frame */
-				*(rp++) = cpu_to_le32(RISC_JUMP);
-				*(rp++) = cpu_to_le32(risc_phys_jump_addr);
-				*(rp++) = cpu_to_le32(0);
-			}
-		}
-
-		spin_unlock(&dev->slock);
-	} else {
-		if (status & FLD_VID_SRC_UF)
-			pr_err("%s(): Video Received Underflow Error Interrupt!\n",
-			       __func__);
-
-		if (status & FLD_VID_SRC_SYNC)
-			pr_err("%s(): Video Received Sync Error Interrupt!\n",
-			       __func__);
-
-		if (status & FLD_VID_SRC_OPC_ERR)
-			pr_err("%s(): Video Received OpCode Error Interrupt!\n",
-			       __func__);
-	}
-
-	if (out->_file_status == END_OF_FILE) {
-		pr_err("EOF Channel 1 Framecount = %d\n", out->_frame_count);
-		return -1;
-	}
-	/* ElSE, set the interrupt mask register, re-enable irq. */
-	int_msk_tmp = cx_read(channel->int_msk);
-	cx_write(channel->int_msk, int_msk_tmp |= _intr_msk);
-
-	return 0;
-}
-
-static irqreturn_t cx25821_upstream_irq(int irq, void *dev_id)
-{
-	struct cx25821_channel *chan = dev_id;
-	struct cx25821_dev *dev = chan->dev;
-	u32 vid_status;
-	int handled = 0;
-	const struct sram_channel *sram_ch;
-
-	if (!dev)
-		return -1;
-
-	sram_ch = chan->sram_channels;
-
-	vid_status = cx_read(sram_ch->int_stat);
-
-	/* Only deal with our interrupt */
-	if (vid_status)
-		handled = cx25821_video_upstream_irq(chan, vid_status);
-
-	return IRQ_RETVAL(handled);
-}
-
-static void cx25821_set_pixelengine(struct cx25821_channel *chan,
-				    const struct sram_channel *ch,
-				    int pix_format)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	int width = WIDTH_D1;
-	int height = out->_lines_count;
-	int num_lines, odd_num_lines;
-	u32 value;
-	int vip_mode = OUTPUT_FRMT_656;
-
-	value = ((pix_format & 0x3) << 12) | (vip_mode & 0x7);
-	value &= 0xFFFFFFEF;
-	value |= out->is_60hz ? 0 : 0x10;
-	cx_write(ch->vid_fmt_ctl, value);
-
-	/* set number of active pixels in each line.
-	 * Default is 720 pixels in both NTSC and PAL format */
-	cx_write(ch->vid_active_ctl1, width);
-
-	num_lines = (height / 2) & 0x3FF;
-	odd_num_lines = num_lines;
-
-	if (out->is_60hz)
-		odd_num_lines += 1;
-
-	value = (num_lines << 16) | odd_num_lines;
-
-	/* set number of active lines in field 0 (top) and field 1 (bottom) */
-	cx_write(ch->vid_active_ctl2, value);
-
-	cx_write(ch->vid_cdt_size, VID_CDT_SIZE >> 3);
-}
-
-static int cx25821_start_video_dma_upstream(struct cx25821_channel *chan,
-					    const struct sram_channel *sram_ch)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	u32 tmp = 0;
-	int err = 0;
-
-	/* 656/VIP SRC Upstream Channel I & J and 7 - Host Bus Interface for
-	 * channel A-C
-	 */
-	tmp = cx_read(VID_CH_MODE_SEL);
-	cx_write(VID_CH_MODE_SEL, tmp | 0x1B0001FF);
-
-	/* Set the physical start address of the RISC program in the initial
-	 * program counter(IPC) member of the cmds.
-	 */
-	cx_write(sram_ch->cmds_start + 0, out->_dma_phys_addr);
-	/* Risc IPC High 64 bits 63-32 */
-	cx_write(sram_ch->cmds_start + 4, 0);
-
-	/* reset counter */
-	cx_write(sram_ch->gpcnt_ctl, 3);
-
-	/* Clear our bits from the interrupt status register. */
-	cx_write(sram_ch->int_stat, _intr_msk);
-
-	/* Set the interrupt mask register, enable irq. */
-	cx_set(PCI_INT_MSK, cx_read(PCI_INT_MSK) | (1 << sram_ch->irq_bit));
-	tmp = cx_read(sram_ch->int_msk);
-	cx_write(sram_ch->int_msk, tmp |= _intr_msk);
-
-	err = request_irq(dev->pci->irq, cx25821_upstream_irq,
-			IRQF_SHARED, dev->name, chan);
-	if (err < 0) {
-		pr_err("%s: can't get upstream IRQ %d\n",
-		       dev->name, dev->pci->irq);
-		goto fail_irq;
-	}
-
-	/* Start the DMA  engine */
-	tmp = cx_read(sram_ch->dma_ctl);
-	cx_set(sram_ch->dma_ctl, tmp | FLD_VID_RISC_EN);
-
-	out->_is_running = 1;
-	out->_is_first_frame = 1;
-
-	return 0;
-
-fail_irq:
-	cx25821_dev_unregister(dev);
-	return err;
-}
-
-int cx25821_vidupstream_init(struct cx25821_channel *chan,
-				 int pixel_format)
-{
-	struct cx25821_video_out_data *out = chan->out;
-	struct cx25821_dev *dev = chan->dev;
-	const struct sram_channel *sram_ch;
-	u32 tmp;
-	int err = 0;
-	int data_frame_size = 0;
-	int risc_buffer_size = 0;
-
-	if (out->_is_running) {
-		pr_info("Video Channel is still running so return!\n");
-		return 0;
-	}
-
-	sram_ch = chan->sram_channels;
-
-	out->is_60hz = dev->tvnorm & V4L2_STD_525_60;
-
-	/* 656/VIP SRC Upstream Channel I & J and 7 - Host Bus Interface for
-	 * channel A-C
-	 */
-	tmp = cx_read(VID_CH_MODE_SEL);
-	cx_write(VID_CH_MODE_SEL, tmp | 0x1B0001FF);
-
-	out->_is_running = 0;
-	out->_frame_count = 0;
-	out->_file_status = RESET_STATUS;
-	out->_lines_count = out->is_60hz ? 480 : 576;
-	out->_pixel_format = pixel_format;
-	out->_line_size = (out->_pixel_format == PIXEL_FRMT_422) ?
-		(WIDTH_D1 * 2) : (WIDTH_D1 * 3) / 2;
-	data_frame_size = out->is_60hz ? NTSC_DATA_BUF_SZ : PAL_DATA_BUF_SZ;
-	risc_buffer_size = out->is_60hz ?
-		NTSC_RISC_BUF_SIZE : PAL_RISC_BUF_SIZE;
-
-	out->_is_running = 0;
-	out->_frame_count = 0;
-	out->_file_status = RESET_STATUS;
-	out->_lines_count = out->is_60hz ? 480 : 576;
-	out->_pixel_format = pixel_format;
-	out->_line_size = (out->_pixel_format == PIXEL_FRMT_422) ?
-		(WIDTH_D1 * 2) : (WIDTH_D1 * 3) / 2;
-	out->curpos = 0;
-	init_waitqueue_head(&out->waitq);
-
-	err = cx25821_sram_channel_setup_upstream(dev, sram_ch,
-			out->_line_size, 0);
-
-	/* setup fifo + format */
-	cx25821_set_pixelengine(chan, sram_ch, out->_pixel_format);
-
-	out->upstream_riscbuf_size = risc_buffer_size * 2;
-	out->upstream_databuf_size = data_frame_size * 2;
-
-	/* Allocating buffers and prepare RISC program */
-	err = cx25821_upstream_buffer_prepare(chan, sram_ch, out->_line_size);
-	if (err < 0) {
-		pr_err("%s: Failed to set up Video upstream buffers!\n",
-		       dev->name);
-		goto error;
-	}
-
-	cx25821_start_video_dma_upstream(chan, sram_ch);
-
-	return 0;
-
-error:
-	cx25821_dev_unregister(dev);
-
-	return err;
-}
diff --git a/drivers/media/pci/cx25821/cx25821-video-upstream.h b/drivers/media/pci/cx25821/cx25821-video-upstream.h
deleted file mode 100644
index b6cf95f2d11b..000000000000
--- a/drivers/media/pci/cx25821/cx25821-video-upstream.h
+++ /dev/null
@@ -1,135 +0,0 @@
-/*
- *  Driver for the Conexant CX25821 PCIe bridge
- *
- *  Copyright (C) 2009 Conexant Systems Inc.
- *  Authors  <hiep.huynh@conexant.com>, <shu.lin@conexant.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or
- *  (at your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *
- *  GNU General Public License for more details.
- */
-
-#include <linux/mutex.h>
-#include <linux/workqueue.h>
-
-#define OUTPUT_FRMT_656       0
-#define OPEN_FILE_1           0
-#define NUM_PROGS             8
-#define NUM_FRAMES            2
-#define ODD_FIELD             0
-#define EVEN_FIELD            1
-#define TOP_OFFSET            0
-#define FIFO_DISABLE          0
-#define FIFO_ENABLE           1
-#define TEST_FRAMES           5
-#define END_OF_FILE           0
-#define IN_PROGRESS           1
-#define RESET_STATUS          -1
-#define NUM_NO_OPS            5
-
-/* PAL and NTSC line sizes and number of lines. */
-#define WIDTH_D1              720
-#define NTSC_LINES_PER_FRAME  480
-#define PAL_LINES_PER_FRAME   576
-#define PAL_LINE_SZ           1440
-#define Y422_LINE_SZ          1440
-#define Y411_LINE_SZ          1080
-#define NTSC_FIELD_HEIGHT     240
-#define NTSC_ODD_FLD_LINES    241
-#define PAL_FIELD_HEIGHT      288
-
-#define FRAME_SIZE_NTSC_Y422    (NTSC_LINES_PER_FRAME * Y422_LINE_SZ)
-#define FRAME_SIZE_NTSC_Y411    (NTSC_LINES_PER_FRAME * Y411_LINE_SZ)
-#define FRAME_SIZE_PAL_Y422     (PAL_LINES_PER_FRAME * Y422_LINE_SZ)
-#define FRAME_SIZE_PAL_Y411     (PAL_LINES_PER_FRAME * Y411_LINE_SZ)
-
-#define NTSC_DATA_BUF_SZ        (Y422_LINE_SZ * NTSC_LINES_PER_FRAME)
-#define PAL_DATA_BUF_SZ         (Y422_LINE_SZ * PAL_LINES_PER_FRAME)
-
-#define RISC_WRITECR_INSTRUCTION_SIZE   16
-#define RISC_SYNC_INSTRUCTION_SIZE      4
-#define JUMP_INSTRUCTION_SIZE           12
-#define MAXSIZE_NO_OPS                  36
-#define DWORD_SIZE                      4
-
-#define USE_RISC_NOOP_VIDEO   1
-
-#ifdef USE_RISC_NOOP_VIDEO
-#define PAL_US_VID_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_WRITECR_INSTRUCTION_SIZE + RISC_SYNC_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define PAL_RISC_BUF_SIZE           (2 * PAL_US_VID_PROG_SIZE)
-
-#define PAL_VID_PROG_SIZE						\
-	((PAL_FIELD_HEIGHT * 2) * 3 * DWORD_SIZE +			\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE + 2 * NUM_NO_OPS * DWORD_SIZE)
-
-#define ODD_FLD_PAL_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define ODD_FLD_NTSC_PROG_SIZE						\
-	(NTSC_ODD_FLD_LINES * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define NTSC_US_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + 1) * 3 * DWORD_SIZE +			\
-	 RISC_WRITECR_INSTRUCTION_SIZE + JUMP_INSTRUCTION_SIZE +	\
-	 NUM_NO_OPS * DWORD_SIZE)
-
-#define NTSC_RISC_BUF_SIZE						\
-	(2 * (RISC_SYNC_INSTRUCTION_SIZE + NTSC_US_VID_PROG_SIZE))
-
-#define FRAME1_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + NTSC_FIELD_HEIGHT) * 3 * DWORD_SIZE +	\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE + 2 * NUM_NO_OPS * DWORD_SIZE)
-
-#endif
-
-#ifndef USE_RISC_NOOP_VIDEO
-#define PAL_US_VID_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_WRITECR_INSTRUCTION_SIZE + RISC_SYNC_INSTRUCTION_SIZE +	\
-	 JUMP_INSTRUCTION_SIZE)
-
-#define PAL_RISC_BUF_SIZE		(2 * PAL_US_VID_PROG_SIZE)
-
-#define PAL_VID_PROG_SIZE						\
-	((PAL_FIELD_HEIGHT * 2) * 3 * DWORD_SIZE +			\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE)
-
-#define ODD_FLD_PAL_PROG_SIZE						\
-	(PAL_FIELD_HEIGHT * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE)
-
-#define ODD_FLD_NTSC_PROG_SIZE						\
-	(NTSC_ODD_FLD_LINES * 3 * DWORD_SIZE +				\
-	 RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE)
-
-#define NTSC_US_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + 1) * 3 * DWORD_SIZE +			\
-	 RISC_WRITECR_INSTRUCTION_SIZE + JUMP_INSTRUCTION_SIZE)
-
-#define NTSC_RISC_BUF_SIZE						\
-	(2 * (RISC_SYNC_INSTRUCTION_SIZE + NTSC_US_VID_PROG_SIZE))
-
-#define FRAME1_VID_PROG_SIZE						\
-	((NTSC_ODD_FLD_LINES + NTSC_FIELD_HEIGHT) * 3 * DWORD_SIZE +	\
-	 2 * RISC_SYNC_INSTRUCTION_SIZE + RISC_WRITECR_INSTRUCTION_SIZE + \
-	 JUMP_INSTRUCTION_SIZE)
-
-#endif
diff --git a/drivers/media/pci/cx25821/cx25821.h b/drivers/media/pci/cx25821/cx25821.h
index b3eb2dabb30b..25eba4ac4499 100644
--- a/drivers/media/pci/cx25821/cx25821.h
+++ b/drivers/media/pci/cx25821/cx25821.h
@@ -432,18 +432,6 @@ extern int cx25821_sram_channel_setup_audio(struct cx25821_dev *dev,
 					    const struct sram_channel *ch,
 					    unsigned int bpl, u32 risc);
 
-extern int cx25821_vidupstream_init(struct cx25821_channel *chan, int pixel_format);
-extern int cx25821_audio_upstream_init(struct cx25821_dev *dev,
-				       int channel_select);
-extern int cx25821_write_frame(struct cx25821_channel *chan,
-		const char __user *data, size_t count);
-extern void cx25821_free_mem_upstream(struct cx25821_channel *chan);
-extern void cx25821_free_mem_upstream_audio(struct cx25821_dev *dev);
-extern void cx25821_stop_upstream_video(struct cx25821_channel *chan);
-extern void cx25821_stop_upstream_audio(struct cx25821_dev *dev);
-extern int cx25821_sram_channel_setup_upstream(struct cx25821_dev *dev,
-					       const struct sram_channel *ch,
-					       unsigned int bpl, u32 risc);
 extern void cx25821_set_pixel_format(struct cx25821_dev *dev, int channel,
 				     u32 format);
 
-- 
cgit v1.2.3


From 22d71a5097ec7059b6cbbee678a4f88484695941 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Thu, 28 Jun 2018 13:52:23 +0300
Subject: spi: pxa2xx: Add support for Intel Ice Lake

Intel Ice Lake SPI host controller follows the Intel Cannon Lake but the
PCI IDs are different. Add the new PCI IDs to the driver supported
devices list.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/spi/spi-pxa2xx.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/spi/spi-pxa2xx.c b/drivers/spi/spi-pxa2xx.c
index 0b2d60d30f69..14f4ea59caff 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -1391,6 +1391,10 @@ static const struct pci_device_id pxa2xx_spi_pci_compound_match[] = {
 	{ PCI_VDEVICE(INTEL, 0x31c2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x31c4), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x31c6), LPSS_BXT_SSP },
+	/* ICL-LP */
+	{ PCI_VDEVICE(INTEL, 0x34aa), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x34ab), LPSS_CNL_SSP },
+	{ PCI_VDEVICE(INTEL, 0x34fb), LPSS_CNL_SSP },
 	/* APL */
 	{ PCI_VDEVICE(INTEL, 0x5ac2), LPSS_BXT_SSP },
 	{ PCI_VDEVICE(INTEL, 0x5ac4), LPSS_BXT_SSP },
-- 
cgit v1.2.3


From b7bf15c43c90c13c15db23612409783db97f680a Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Fri, 8 Jun 2018 17:45:51 -0400
Subject: media: i2c: adv748x: csi2: set entity function to video interface
 bridge

The ADV748x CSI-2 subdevices are HDMI/AFE to MIPI CSI-2 bridges.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Acked-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/adv748x/adv748x-csi2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/adv748x/adv748x-csi2.c b/drivers/media/i2c/adv748x/adv748x-csi2.c
index 820b44ed56a8..469be87a3761 100644
--- a/drivers/media/i2c/adv748x/adv748x-csi2.c
+++ b/drivers/media/i2c/adv748x/adv748x-csi2.c
@@ -284,7 +284,7 @@ int adv748x_csi2_init(struct adv748x_state *state, struct adv748x_csi2 *tx)
 	adv748x_csi2_set_virtual_channel(tx, 0);
 
 	adv748x_subdev_init(&tx->sd, state, &adv748x_csi2_ops,
-			    MEDIA_ENT_F_UNKNOWN,
+			    MEDIA_ENT_F_VID_IF_BRIDGE,
 			    is_txa(tx) ? "txa" : "txb");
 
 	/* Ensure that matching is based upon the endpoint fwnodes */
-- 
cgit v1.2.3


From f91b84171b618dfd565b10c1a7feead0af869ba5 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 11 Jun 2018 04:32:20 -0400
Subject: media: bt8xx: bttv: fix spelling mistake: "culpit" -> "culprit"

Trivial fix to spelling mistake in pr_notice message text

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/bt8xx/bttv-driver.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/bt8xx/bttv-driver.c b/drivers/media/pci/bt8xx/bttv-driver.c
index de3f44b8dec6..cf05e11da01b 100644
--- a/drivers/media/pci/bt8xx/bttv-driver.c
+++ b/drivers/media/pci/bt8xx/bttv-driver.c
@@ -3511,7 +3511,7 @@ static void bttv_irq_debug_low_latency(struct bttv *btv, u32 rc)
 	}
 	pr_notice("%d: Uhm. Looks like we have unusual high IRQ latencies\n",
 		  btv->c.nr);
-	pr_notice("%d: Lets try to catch the culpit red-handed ...\n",
+	pr_notice("%d: Lets try to catch the culprit red-handed ...\n",
 		  btv->c.nr);
 	dump_stack();
 }
-- 
cgit v1.2.3


From a9c24b8977c216cd7a8bf5a9f9d0621668e49746 Mon Sep 17 00:00:00 2001
From: Anton Leontiev <scileont@gmail.com>
Date: Tue, 12 Jun 2018 06:11:01 -0400
Subject: media: vim2m: Remove surplus name initialization

Name is already initialized by assignment from vim2m_videodev.

Signed-off-by: Anton Leontiev <scileont@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vim2m.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index 065483e62db4..1393aa806462 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -1020,7 +1020,6 @@ static int vim2m_probe(struct platform_device *pdev)
 	}
 
 	video_set_drvdata(vfd, dev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", vim2m_videodev.name);
 	v4l2_info(&dev->v4l2_dev,
 			"Device registered as /dev/video%d\n", vfd->num);
 
-- 
cgit v1.2.3


From 0d961c8998d7e8ea6dd0e00a7fdc629a0a0753cd Mon Sep 17 00:00:00 2001
From: Anton Leontiev <scileont@gmail.com>
Date: Tue, 12 Jun 2018 06:11:02 -0400
Subject: media: ti-vpe: Remove surplus name initialization

Name is already initialized by assignment from vpe_videodev.

Signed-off-by: Anton Leontiev <scileont@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/ti-vpe/vpe.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index e395aa85c8ad..de968295ca7d 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -2485,7 +2485,6 @@ static void vpe_fw_cb(struct platform_device *pdev)
 	}
 
 	video_set_drvdata(vfd, dev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", vpe_videodev.name);
 	dev_info(dev->v4l2_dev.dev, "Device registered as /dev/video%d\n",
 		vfd->num);
 }
-- 
cgit v1.2.3


From 4fb5288b1965f33c7c0056c55b3ec5d9d4a52044 Mon Sep 17 00:00:00 2001
From: Anton Leontiev <scileont@gmail.com>
Date: Tue, 12 Jun 2018 06:11:03 -0400
Subject: media: s5p-g2d: Remove surplus name initialization

Name is already initialized by assignment from g2d_videodev.

Signed-off-by: Anton Leontiev <scileont@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/s5p-g2d/g2d.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 66aa8cf1d048..3735c204e9ac 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -702,7 +702,6 @@ static int g2d_probe(struct platform_device *pdev)
 		goto rel_vdev;
 	}
 	video_set_drvdata(vfd, dev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", g2d_videodev.name);
 	dev->vfd = vfd;
 	v4l2_info(&dev->v4l2_dev, "device registered as /dev/video%d\n",
 								vfd->num);
-- 
cgit v1.2.3


From 0874f0295d4e7f61b7c2c8b3ce3a7c70727693bd Mon Sep 17 00:00:00 2001
From: Anton Leontiev <scileont@gmail.com>
Date: Tue, 12 Jun 2018 06:11:04 -0400
Subject: media: mx2: Remove surplus name initialization

Name is already initialized by assignment from emmaprp_videodev.

Signed-off-by: Anton Leontiev <scileont@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/mx2_emmaprp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c
index 5a8eff60e95f..2e64729134b2 100644
--- a/drivers/media/platform/mx2_emmaprp.c
+++ b/drivers/media/platform/mx2_emmaprp.c
@@ -934,7 +934,6 @@ static int emmaprp_probe(struct platform_device *pdev)
 	vfd->v4l2_dev = &pcdev->v4l2_dev;
 
 	video_set_drvdata(vfd, pcdev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", emmaprp_videodev.name);
 	pcdev->vfd = vfd;
 	v4l2_info(&pcdev->v4l2_dev, EMMAPRP_MODULE_NAME
 		  " Device registered as /dev/video%d\n", vfd->num);
-- 
cgit v1.2.3


From 661e7e8178fba7bbaf0845326b36fd99887982d3 Mon Sep 17 00:00:00 2001
From: Anton Leontiev <scileont@gmail.com>
Date: Tue, 12 Jun 2018 06:11:05 -0400
Subject: media: m2m-deinterlace: Remove surplus name initialization

Name is already initialized by assignment from deinterlace_videodev.

Signed-off-by: Anton Leontiev <scileont@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/m2m-deinterlace.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 1e4195144f39..3008892eb8dd 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -1040,7 +1040,6 @@ static int deinterlace_probe(struct platform_device *pdev)
 	}
 
 	video_set_drvdata(vfd, pcdev);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", deinterlace_videodev.name);
 	v4l2_info(&pcdev->v4l2_dev, MEM2MEM_TEST_MODULE_NAME
 			" Device registered as /dev/video%d\n", vfd->num);
 
-- 
cgit v1.2.3


From a4367ff42dde5d24f5217edba7c54cd13e21b2b6 Mon Sep 17 00:00:00 2001
From: Anton Leontiev <scileont@gmail.com>
Date: Tue, 12 Jun 2018 06:11:06 -0400
Subject: media: rga: Remove surplus name initialization

Name is already initialized by assignment from rga_videodev.

Signed-off-by: Anton Leontiev <scileont@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rockchip/rga/rga.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
index d508a8ba6f89..e8dffca669a1 100644
--- a/drivers/media/platform/rockchip/rga/rga.c
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -882,7 +882,6 @@ static int rga_probe(struct platform_device *pdev)
 	vfd->v4l2_dev = &rga->v4l2_dev;
 
 	video_set_drvdata(vfd, rga);
-	snprintf(vfd->name, sizeof(vfd->name), "%s", rga_videodev.name);
 	rga->vfd = vfd;
 
 	platform_set_drvdata(pdev, rga);
-- 
cgit v1.2.3


From 34dbb848d5e47f0a16abeb40885f93dd43045ff1 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Tue, 12 Jun 2018 09:22:51 -0400
Subject: media: mem2mem: Remove excessive try_run call

If there is a schedulable job, v4l2_m2m_try_schedule() calls
v4l2_m2m_try_run(). This makes the unconditional v4l2_m2m_try_run()
called by v4l2_m2m_job_finish superfluous. Remove it.

Fixes: 7f98639def42 ("V4L/DVB: add memory-to-memory device helper framework for videobuf")

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-mem2mem.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index c4f963d96a79..5f9cd5b74cda 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -339,7 +339,6 @@ void v4l2_m2m_job_finish(struct v4l2_m2m_dev *m2m_dev,
 	 * allow more than one job on the job_queue per instance, each has
 	 * to be scheduled separately after the previous one finishes. */
 	v4l2_m2m_try_schedule(m2m_ctx);
-	v4l2_m2m_try_run(m2m_dev);
 }
 EXPORT_SYMBOL(v4l2_m2m_job_finish);
 
-- 
cgit v1.2.3


From 7534122d60066a50859c422ced4636deb23760bf Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 12 Jun 2018 05:42:00 -0400
Subject: media: cx18: remove redundant zero check on retval

The check for a zero retval is redundant as all paths that lead to
this point have set retval to an error return value that is non-zero.
Remove the redundant check.

Detected by CoverityScan, CID#102589 ("Logically dead code")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx18/cx18-driver.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/pci/cx18/cx18-driver.c b/drivers/media/pci/cx18/cx18-driver.c
index 8f314ca320c7..0c389a3fb4e5 100644
--- a/drivers/media/pci/cx18/cx18-driver.c
+++ b/drivers/media/pci/cx18/cx18-driver.c
@@ -1134,8 +1134,6 @@ free_mem:
 free_workqueues:
 	destroy_workqueue(cx->in_work_queue);
 err:
-	if (retval == 0)
-		retval = -ENODEV;
 	CX18_ERR("Error %d on initialization\n", retval);
 
 	v4l2_device_unregister(&cx->v4l2_dev);
-- 
cgit v1.2.3


From 6c8871baebc781f27ec9ccc1324afd9802941b11 Mon Sep 17 00:00:00 2001
From: Zhouyang Jia <jiazhouyang09@gmail.com>
Date: Mon, 11 Jun 2018 03:41:58 -0400
Subject: media: cx88: add error handling for snd_ctl_add

When snd_ctl_add fails, the lack of error-handling code may
cause unexpected results.

This patch adds error-handling code after calling snd_ctl_add.

Signed-off-by: Zhouyang Jia <jiazhouyang09@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx88/cx88-alsa.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/media/pci/cx88/cx88-alsa.c b/drivers/media/pci/cx88/cx88-alsa.c
index e5c3387cd1e8..89a65478ae36 100644
--- a/drivers/media/pci/cx88/cx88-alsa.c
+++ b/drivers/media/pci/cx88/cx88-alsa.c
@@ -962,8 +962,11 @@ static int cx88_audio_initdev(struct pci_dev *pci,
 		goto error;
 
 	/* If there's a wm8775 then add a Line-In ALC switch */
-	if (core->sd_wm8775)
-		snd_ctl_add(card, snd_ctl_new1(&snd_cx88_alc_switch, chip));
+	if (core->sd_wm8775) {
+		err = snd_ctl_add(card, snd_ctl_new1(&snd_cx88_alc_switch, chip));
+		if (err < 0)
+			goto error;
+	}
 
 	strcpy(card->driver, "CX88x");
 	sprintf(card->shortname, "Conexant CX%x", pci->device);
-- 
cgit v1.2.3


From e95d7c6eb94c634852eaa5ff4caf3db05b5d2e86 Mon Sep 17 00:00:00 2001
From: Zhouyang Jia <jiazhouyang09@gmail.com>
Date: Mon, 11 Jun 2018 00:39:20 -0400
Subject: media: tm6000: add error handling for dvb_register_adapter

When dvb_register_adapter fails, the lack of error-handling code may
cause unexpected results.

This patch adds error-handling code after calling dvb_register_adapter.

Signed-off-by: Zhouyang Jia <jiazhouyang09@gmail.com>
[hans.verkuil@cisco.com: use pr_err and fix typo: adater -> adapter]
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/tm6000/tm6000-dvb.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/media/usb/tm6000/tm6000-dvb.c b/drivers/media/usb/tm6000/tm6000-dvb.c
index c811fc6cf48a..3a4e545c6037 100644
--- a/drivers/media/usb/tm6000/tm6000-dvb.c
+++ b/drivers/media/usb/tm6000/tm6000-dvb.c
@@ -266,6 +266,11 @@ static int register_dvb(struct tm6000_core *dev)
 
 	ret = dvb_register_adapter(&dvb->adapter, "Trident TVMaster 6000 DVB-T",
 					THIS_MODULE, &dev->udev->dev, adapter_nr);
+	if (ret < 0) {
+		pr_err("tm6000: couldn't register the adapter!\n");
+		goto err;
+	}
+
 	dvb->adapter.priv = dev;
 
 	if (dvb->frontend) {
-- 
cgit v1.2.3


From 1946117b8f135a62eea5cfa18be63b1741174b9f Mon Sep 17 00:00:00 2001
From: Alexandre Courbot <acourbot@chromium.org>
Date: Tue, 5 Jun 2018 00:50:46 -0400
Subject: media: venus: keep resolution when adjusting format

When checking a format for validity, the resolution is reset to 1280x720
whenever the pixel format is not supported. This behavior can mislead
user-space into believing that this is the only resolution supported,
and looks strange considering that if we try/set the same format with
just the pixel format changed to a valid one, the call will this time
succeed without altering the resolution.

Resolution is managed independently of the pixel format, so remove this
reset.

Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
Acked-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/vdec.c | 2 --
 drivers/media/platform/qcom/venus/venc.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 49bbd1861d3a..f89a91d43cc9 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -173,8 +173,6 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 		else
 			return NULL;
 		fmt = find_format(inst, pixmp->pixelformat, f->type);
-		pixmp->width = 1280;
-		pixmp->height = 720;
 	}
 
 	pixmp->width = clamp(pixmp->width, inst->cap_width.min,
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 6b2ce479584e..11dafc7848c5 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -297,8 +297,6 @@ venc_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 		else
 			return NULL;
 		fmt = find_format(inst, pixmp->pixelformat, f->type);
-		pixmp->width = 1280;
-		pixmp->height = 720;
 	}
 
 	pixmp->width = clamp(pixmp->width, inst->cap_width.min,
-- 
cgit v1.2.3


From 9aecc03555825a79a8a4ca45199cb866e8684623 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 1 Jun 2018 15:49:51 -0400
Subject: media: rockchip/rga: Fix broken .start_streaming

Currently, rga_buf_start_streaming() is expecting
pm_runtime_get_sync to return zero on success, which
is wrong.

As per the documentation, pm_runtime_get_sync increments
the device's usage counter and return its result.
This means it will typically return a positive integer
on success and a negative error code.

Therefore, rockchip-rga driver is currently unusable
failing to start_streaming in most cases. Fix it and
while here, cleanup the buffer return-to-core logic.

Fixes: f7e7b48e6d79 ("[media] rockchip/rga: v4l2 m2m support")

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Reviewed-by: Jacob Chen <jacob-chen@iotwrt.com>
[hans.verkuil@cisco.com: fix line over 80 cols warning]
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rockchip/rga/rga-buf.c | 45 ++++++++++++++-------------
 1 file changed, 23 insertions(+), 22 deletions(-)

diff --git a/drivers/media/platform/rockchip/rga/rga-buf.c b/drivers/media/platform/rockchip/rga/rga-buf.c
index fa1ba98c96dc..356821c2dacf 100644
--- a/drivers/media/platform/rockchip/rga/rga-buf.c
+++ b/drivers/media/platform/rockchip/rga/rga-buf.c
@@ -64,43 +64,44 @@ static void rga_buf_queue(struct vb2_buffer *vb)
 	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
 }
 
+static void rga_buf_return_buffers(struct vb2_queue *q,
+				   enum vb2_buffer_state state)
+{
+	struct rga_ctx *ctx = vb2_get_drv_priv(q);
+	struct vb2_v4l2_buffer *vbuf;
+
+	for (;;) {
+		if (V4L2_TYPE_IS_OUTPUT(q->type))
+			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		else
+			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+		if (!vbuf)
+			break;
+		v4l2_m2m_buf_done(vbuf, state);
+	}
+}
+
 static int rga_buf_start_streaming(struct vb2_queue *q, unsigned int count)
 {
 	struct rga_ctx *ctx = vb2_get_drv_priv(q);
 	struct rockchip_rga *rga = ctx->rga;
-	int ret, i;
+	int ret;
 
 	ret = pm_runtime_get_sync(rga->dev);
-
-	if (!ret)
-		return 0;
-
-	for (i = 0; i < q->num_buffers; ++i) {
-		if (q->bufs[i]->state == VB2_BUF_STATE_ACTIVE) {
-			v4l2_m2m_buf_done(to_vb2_v4l2_buffer(q->bufs[i]),
-					  VB2_BUF_STATE_QUEUED);
-		}
+	if (ret < 0) {
+		rga_buf_return_buffers(q, VB2_BUF_STATE_QUEUED);
+		return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 static void rga_buf_stop_streaming(struct vb2_queue *q)
 {
 	struct rga_ctx *ctx = vb2_get_drv_priv(q);
 	struct rockchip_rga *rga = ctx->rga;
-	struct vb2_v4l2_buffer *vbuf;
-
-	for (;;) {
-		if (V4L2_TYPE_IS_OUTPUT(q->type))
-			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
-		else
-			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
-		if (!vbuf)
-			break;
-		v4l2_m2m_buf_done(vbuf, VB2_BUF_STATE_ERROR);
-	}
 
+	rga_buf_return_buffers(q, VB2_BUF_STATE_ERROR);
 	pm_runtime_put(rga->dev);
 }
 
-- 
cgit v1.2.3


From 1b97e5275ba6ef862a09f8b993fa3e8b373dfe9b Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 1 Jun 2018 15:49:52 -0400
Subject: media: rockchip/rga: Remove unrequired wait in .job_abort

As per the documentation, job_abort is not required
to wait until the current job finishes. It is redundant
to do so, as the core will perform the wait operation.

Remove the wait infrastructure completely.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Reviewed-by: Jacob Chen <jacob-chen@iotwrt.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rockchip/rga/rga.c | 13 +------------
 drivers/media/platform/rockchip/rga/rga.h |  2 --
 2 files changed, 1 insertion(+), 14 deletions(-)

diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
index e8dffca669a1..8ace1873202a 100644
--- a/drivers/media/platform/rockchip/rga/rga.c
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -41,14 +41,7 @@ module_param(debug, int, 0644);
 
 static void job_abort(void *prv)
 {
-	struct rga_ctx *ctx = prv;
-	struct rockchip_rga *rga = ctx->rga;
-
-	if (!rga->curr)	/* No job currently running */
-		return;
-
-	wait_event_timeout(rga->irq_queue,
-			   !rga->curr, msecs_to_jiffies(RGA_TIMEOUT));
+	/* Can't do anything rational here */
 }
 
 static void device_run(void *prv)
@@ -104,8 +97,6 @@ static irqreturn_t rga_isr(int irq, void *prv)
 		v4l2_m2m_buf_done(src, VB2_BUF_STATE_DONE);
 		v4l2_m2m_buf_done(dst, VB2_BUF_STATE_DONE);
 		v4l2_m2m_job_finish(rga->m2m_dev, ctx->fh.m2m_ctx);
-
-		wake_up(&rga->irq_queue);
 	}
 
 	return IRQ_HANDLED;
@@ -838,8 +829,6 @@ static int rga_probe(struct platform_device *pdev)
 	spin_lock_init(&rga->ctrl_lock);
 	mutex_init(&rga->mutex);
 
-	init_waitqueue_head(&rga->irq_queue);
-
 	ret = rga_parse_dt(rga);
 	if (ret)
 		dev_err(&pdev->dev, "Unable to parse OF data\n");
diff --git a/drivers/media/platform/rockchip/rga/rga.h b/drivers/media/platform/rockchip/rga/rga.h
index 5d43e7ea88af..72d8a159fa7b 100644
--- a/drivers/media/platform/rockchip/rga/rga.h
+++ b/drivers/media/platform/rockchip/rga/rga.h
@@ -86,8 +86,6 @@ struct rockchip_rga {
 	/* ctrl parm lock */
 	spinlock_t ctrl_lock;
 
-	wait_queue_head_t irq_queue;
-
 	struct rga_ctx *curr;
 	dma_addr_t cmdbuf_phy;
 	void *cmdbuf_virt;
-- 
cgit v1.2.3


From d7e913cc58c5f6db5159c72e8f8d1f2be9e2fe2f Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Thu, 14 Jun 2018 11:34:03 -0400
Subject: media: mem2mem: Remove unused v4l2_m2m_ops .lock/.unlock

Commit f1a81afc98e3 ("[media] m2m: fix bad unlock balance")
removed the last use of v4l2_m2m_ops.lock and
v4l2_m2m_ops.unlock hooks. They are not actually
used anymore. Remove them.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-common.c          | 26 ++++------------------
 drivers/media/platform/m2m-deinterlace.c           | 20 ++---------------
 drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c | 18 ---------------
 drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c | 16 -------------
 drivers/media/platform/mx2_emmaprp.c               | 16 -------------
 drivers/media/platform/sti/delta/delta-v4l2.c      | 18 ---------------
 drivers/media/platform/ti-vpe/vpe.c                | 19 ----------------
 include/media/v4l2-mem2mem.h                       |  6 -----
 8 files changed, 6 insertions(+), 133 deletions(-)

diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index c7631e117dd3..b86d704ae10c 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -1297,28 +1297,10 @@ static void coda_job_abort(void *priv)
 		 "Aborting task\n");
 }
 
-static void coda_lock(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-	struct coda_dev *pcdev = ctx->dev;
-
-	mutex_lock(&pcdev->dev_mutex);
-}
-
-static void coda_unlock(void *m2m_priv)
-{
-	struct coda_ctx *ctx = m2m_priv;
-	struct coda_dev *pcdev = ctx->dev;
-
-	mutex_unlock(&pcdev->dev_mutex);
-}
-
 static const struct v4l2_m2m_ops coda_m2m_ops = {
 	.device_run	= coda_device_run,
 	.job_ready	= coda_job_ready,
 	.job_abort	= coda_job_abort,
-	.lock		= coda_lock,
-	.unlock		= coda_unlock,
 };
 
 static void set_default_params(struct coda_ctx *ctx)
@@ -2092,9 +2074,9 @@ static int coda_open(struct file *file)
 	INIT_LIST_HEAD(&ctx->buffer_meta_list);
 	spin_lock_init(&ctx->buffer_meta_lock);
 
-	coda_lock(ctx);
+	mutex_lock(&dev->dev_mutex);
 	list_add(&ctx->list, &dev->instances);
-	coda_unlock(ctx);
+	mutex_unlock(&dev->dev_mutex);
 
 	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "Created instance %d (%p)\n",
 		 ctx->idx, ctx);
@@ -2142,9 +2124,9 @@ static int coda_release(struct file *file)
 		flush_work(&ctx->seq_end_work);
 	}
 
-	coda_lock(ctx);
+	mutex_lock(&dev->dev_mutex);
 	list_del(&ctx->list);
-	coda_unlock(ctx);
+	mutex_unlock(&dev->dev_mutex);
 
 	if (ctx->dev->devtype->product == CODA_DX6)
 		coda_free_aux_buf(dev, &ctx->workbuf);
diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index 3008892eb8dd..a566ec566cec 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -181,20 +181,6 @@ static void deinterlace_job_abort(void *priv)
 	v4l2_m2m_job_finish(pcdev->m2m_dev, ctx->m2m_ctx);
 }
 
-static void deinterlace_lock(void *priv)
-{
-	struct deinterlace_ctx *ctx = priv;
-	struct deinterlace_dev *pcdev = ctx->dev;
-	mutex_lock(&pcdev->dev_mutex);
-}
-
-static void deinterlace_unlock(void *priv)
-{
-	struct deinterlace_ctx *ctx = priv;
-	struct deinterlace_dev *pcdev = ctx->dev;
-	mutex_unlock(&pcdev->dev_mutex);
-}
-
 static void dma_callback(void *data)
 {
 	struct deinterlace_ctx *curr_ctx = data;
@@ -956,9 +942,9 @@ static __poll_t deinterlace_poll(struct file *file,
 	struct deinterlace_ctx *ctx = file->private_data;
 	__poll_t ret;
 
-	deinterlace_lock(ctx);
+	mutex_lock(&ctx->dev->dev_mutex);
 	ret = v4l2_m2m_poll(file, ctx->m2m_ctx, wait);
-	deinterlace_unlock(ctx);
+	mutex_unlock(&ctx->dev->dev_mutex);
 
 	return ret;
 }
@@ -992,8 +978,6 @@ static const struct v4l2_m2m_ops m2m_ops = {
 	.device_run	= deinterlace_device_run,
 	.job_ready	= deinterlace_job_ready,
 	.job_abort	= deinterlace_job_abort,
-	.lock		= deinterlace_lock,
-	.unlock		= deinterlace_unlock,
 };
 
 static int deinterlace_probe(struct platform_device *pdev)
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
index 86f0a7134365..5523edadb86c 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
@@ -1411,28 +1411,10 @@ int mtk_vcodec_dec_ctrls_setup(struct mtk_vcodec_ctx *ctx)
 	return 0;
 }
 
-static void m2mops_vdec_lock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mtk_v4l2_debug(3, "[%d]", ctx->id);
-	mutex_lock(&ctx->dev->dev_mutex);
-}
-
-static void m2mops_vdec_unlock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mtk_v4l2_debug(3, "[%d]", ctx->id);
-	mutex_unlock(&ctx->dev->dev_mutex);
-}
-
 const struct v4l2_m2m_ops mtk_vdec_m2m_ops = {
 	.device_run	= m2mops_vdec_device_run,
 	.job_ready	= m2mops_vdec_job_ready,
 	.job_abort	= m2mops_vdec_job_abort,
-	.lock		= m2mops_vdec_lock,
-	.unlock		= m2mops_vdec_unlock,
 };
 
 static const struct vb2_ops mtk_vdec_vb2_ops = {
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
index 1b1a28abbf1f..6ad408514a99 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_enc.c
@@ -1181,26 +1181,10 @@ static void m2mops_venc_job_abort(void *priv)
 	ctx->state = MTK_STATE_ABORT;
 }
 
-static void m2mops_venc_lock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mutex_lock(&ctx->dev->dev_mutex);
-}
-
-static void m2mops_venc_unlock(void *m2m_priv)
-{
-	struct mtk_vcodec_ctx *ctx = m2m_priv;
-
-	mutex_unlock(&ctx->dev->dev_mutex);
-}
-
 const struct v4l2_m2m_ops mtk_venc_m2m_ops = {
 	.device_run	= m2mops_venc_device_run,
 	.job_ready	= m2mops_venc_job_ready,
 	.job_abort	= m2mops_venc_job_abort,
-	.lock		= m2mops_venc_lock,
-	.unlock		= m2mops_venc_unlock,
 };
 
 void mtk_vcodec_enc_set_default_params(struct mtk_vcodec_ctx *ctx)
diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c
index 2e64729134b2..83b9db895a64 100644
--- a/drivers/media/platform/mx2_emmaprp.c
+++ b/drivers/media/platform/mx2_emmaprp.c
@@ -250,20 +250,6 @@ static void emmaprp_job_abort(void *priv)
 	v4l2_m2m_job_finish(pcdev->m2m_dev, ctx->m2m_ctx);
 }
 
-static void emmaprp_lock(void *priv)
-{
-	struct emmaprp_ctx *ctx = priv;
-	struct emmaprp_dev *pcdev = ctx->dev;
-	mutex_lock(&pcdev->dev_mutex);
-}
-
-static void emmaprp_unlock(void *priv)
-{
-	struct emmaprp_ctx *ctx = priv;
-	struct emmaprp_dev *pcdev = ctx->dev;
-	mutex_unlock(&pcdev->dev_mutex);
-}
-
 static inline void emmaprp_dump_regs(struct emmaprp_dev *pcdev)
 {
 	dprintk(pcdev,
@@ -885,8 +871,6 @@ static const struct video_device emmaprp_videodev = {
 static const struct v4l2_m2m_ops m2m_ops = {
 	.device_run	= emmaprp_device_run,
 	.job_abort	= emmaprp_job_abort,
-	.lock		= emmaprp_lock,
-	.unlock		= emmaprp_unlock,
 };
 
 static int emmaprp_probe(struct platform_device *pdev)
diff --git a/drivers/media/platform/sti/delta/delta-v4l2.c b/drivers/media/platform/sti/delta/delta-v4l2.c
index 232d508c5b66..0b42acd4e3a6 100644
--- a/drivers/media/platform/sti/delta/delta-v4l2.c
+++ b/drivers/media/platform/sti/delta/delta-v4l2.c
@@ -339,22 +339,6 @@ static void register_decoders(struct delta_dev *delta)
 	}
 }
 
-static void delta_lock(void *priv)
-{
-	struct delta_ctx *ctx = priv;
-	struct delta_dev *delta = ctx->dev;
-
-	mutex_lock(&delta->lock);
-}
-
-static void delta_unlock(void *priv)
-{
-	struct delta_ctx *ctx = priv;
-	struct delta_dev *delta = ctx->dev;
-
-	mutex_unlock(&delta->lock);
-}
-
 static int delta_open_decoder(struct delta_ctx *ctx, u32 streamformat,
 			      u32 pixelformat, const struct delta_dec **pdec)
 {
@@ -1099,8 +1083,6 @@ static const struct v4l2_m2m_ops delta_m2m_ops = {
 	.device_run     = delta_device_run,
 	.job_ready	= delta_job_ready,
 	.job_abort      = delta_job_abort,
-	.lock		= delta_lock,
-	.unlock		= delta_unlock,
 };
 
 /*
diff --git a/drivers/media/platform/ti-vpe/vpe.c b/drivers/media/platform/ti-vpe/vpe.c
index de968295ca7d..d70871d0ad2d 100644
--- a/drivers/media/platform/ti-vpe/vpe.c
+++ b/drivers/media/platform/ti-vpe/vpe.c
@@ -953,23 +953,6 @@ static void job_abort(void *priv)
 	ctx->aborting = 1;
 }
 
-/*
- * Lock access to the device
- */
-static void vpe_lock(void *priv)
-{
-	struct vpe_ctx *ctx = priv;
-	struct vpe_dev *dev = ctx->dev;
-	mutex_lock(&dev->dev_mutex);
-}
-
-static void vpe_unlock(void *priv)
-{
-	struct vpe_ctx *ctx = priv;
-	struct vpe_dev *dev = ctx->dev;
-	mutex_unlock(&dev->dev_mutex);
-}
-
 static void vpe_dump_regs(struct vpe_dev *dev)
 {
 #define DUMPREG(r) vpe_dbg(dev, "%-35s %08x\n", #r, read_reg(dev, VPE_##r))
@@ -2434,8 +2417,6 @@ static const struct v4l2_m2m_ops m2m_ops = {
 	.device_run	= device_run,
 	.job_ready	= job_ready,
 	.job_abort	= job_abort,
-	.lock		= vpe_lock,
-	.unlock		= vpe_unlock,
 };
 
 static int vpe_runtime_get(struct platform_device *pdev)
diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index 3d07ba3a8262..8f4b208cfee7 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -40,17 +40,11 @@
  *		v4l2_m2m_job_finish() (as if the transaction ended normally).
  *		This function does not have to (and will usually not) wait
  *		until the device enters a state when it can be stopped.
- * @lock:	optional. Define a driver's own lock callback, instead of using
- *		&v4l2_m2m_ctx->q_lock.
- * @unlock:	optional. Define a driver's own unlock callback, instead of
- *		using &v4l2_m2m_ctx->q_lock.
  */
 struct v4l2_m2m_ops {
 	void (*device_run)(void *priv);
 	int (*job_ready)(void *priv);
 	void (*job_abort)(void *priv);
-	void (*lock)(void *priv);
-	void (*unlock)(void *priv);
 };
 
 struct v4l2_m2m_dev;
-- 
cgit v1.2.3


From aed19754c491b336cb40bbd3f072b0e9e1397200 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Thu, 14 Jun 2018 11:34:05 -0400
Subject: media: rcar_vpu: Drop unneeded job_ready

It is not required to implement job_ready().
Since this one is dummy, we can drop it.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar_jpu.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index 8b44a849ab41..690631747c5e 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -1494,11 +1494,6 @@ static void jpu_device_run(void *priv)
 	spin_unlock_irqrestore(&ctx->jpu->lock, flags);
 }
 
-static int jpu_job_ready(void *priv)
-{
-	return 1;
-}
-
 static void jpu_job_abort(void *priv)
 {
 	struct jpu_ctx *ctx = priv;
@@ -1510,7 +1505,6 @@ static void jpu_job_abort(void *priv)
 
 static const struct v4l2_m2m_ops jpu_m2m_ops = {
 	.device_run	= jpu_device_run,
-	.job_ready	= jpu_job_ready,
 	.job_abort	= jpu_job_abort,
 };
 
-- 
cgit v1.2.3


From 1831af092308aa5a59ae61e47494e441c8be6b93 Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javierm@redhat.com>
Date: Sun, 10 Jun 2018 16:43:02 -0400
Subject: media: Revert "[media] tvp5150: fix pad format frame height"

This reverts commit 0866df8dffd514185bfab0d205db76e4c02cf1e4.

The v4l uAPI documentation [0] makes clear that in the case of interlaced
video (i.e: field is V4L2_FIELD_ALTERNATE) the height refers to the number
of lines in the field and not the number of lines in the full frame (which
is twice the field height for interlaced formats).

So the original height calculation was correct, and it shouldn't had been
changed by the mentioned commit.

[0]:https://linuxtv.org/downloads/v4l-dvb-apis/uapi/v4l/subdev-formats.html

Fixes: 0866df8dffd5 ("[media] tvp5150: fix pad format frame height")

Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
Cc: <stable@vger.kernel.org>      # for v4.12 and up
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/tvp5150.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/tvp5150.c b/drivers/media/i2c/tvp5150.c
index b162c2fe62c3..76e6bed5a1da 100644
--- a/drivers/media/i2c/tvp5150.c
+++ b/drivers/media/i2c/tvp5150.c
@@ -872,7 +872,7 @@ static int tvp5150_fill_fmt(struct v4l2_subdev *sd,
 	f = &format->format;
 
 	f->width = decoder->rect.width;
-	f->height = decoder->rect.height;
+	f->height = decoder->rect.height / 2;
 
 	f->code = MEDIA_BUS_FMT_UYVY8_2X8;
 	f->field = V4L2_FIELD_ALTERNATE;
-- 
cgit v1.2.3


From 8c4fe24812e65703658d93005046f34aa27e3557 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Fri, 15 Jun 2018 09:19:44 -0400
Subject: media: Documentation/media/uapi/mediactl: redo tables

Drop the '-  .. row 1' lines to make it easier to add new rows to
the tables in the future without having to renumber these lines.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../media/uapi/mediactl/media-ioc-device-info.rst  |  48 +-
 .../uapi/mediactl/media-ioc-enum-entities.rst      |  83 +---
 .../media/uapi/mediactl/media-ioc-enum-links.rst   |  70 +--
 .../media/uapi/mediactl/media-ioc-g-topology.rst   | 204 ++-------
 Documentation/media/uapi/mediactl/media-types.rst  | 499 +++++----------------
 5 files changed, 185 insertions(+), 719 deletions(-)

diff --git a/Documentation/media/uapi/mediactl/media-ioc-device-info.rst b/Documentation/media/uapi/mediactl/media-ioc-device-info.rst
index f690f9afc470..649cb3d9e058 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-device-info.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-device-info.rst
@@ -48,12 +48,8 @@ ioctl never fails.
     :widths:       1 1 2
 
 
-    -  .. row 1
-
-       -  char
-
+    *  -  char
        -  ``driver``\ [16]
-
        -  Name of the driver implementing the media API as a NUL-terminated
 	  ASCII string. The driver version is stored in the
 	  ``driver_version`` field.
@@ -62,66 +58,38 @@ ioctl never fails.
 	  the driver identity. It is also useful to work around known bugs,
 	  or to identify drivers in error reports.
 
-    -  .. row 2
-
-       -  char
-
+    *  -  char
        -  ``model``\ [32]
-
        -  Device model name as a NUL-terminated UTF-8 string. The device
 	  version is stored in the ``device_version`` field and is not be
 	  appended to the model name.
 
-    -  .. row 3
-
-       -  char
-
+    *  -  char
        -  ``serial``\ [40]
-
        -  Serial number as a NUL-terminated ASCII string.
 
-    -  .. row 4
-
-       -  char
-
+    *  -  char
        -  ``bus_info``\ [32]
-
        -  Location of the device in the system as a NUL-terminated ASCII
 	  string. This includes the bus type name (PCI, USB, ...) and a
 	  bus-specific identifier.
 
-    -  .. row 5
-
-       -  __u32
-
+    *  -  __u32
        -  ``media_version``
-
        -  Media API version, formatted with the ``KERNEL_VERSION()`` macro.
 
-    -  .. row 6
-
-       -  __u32
-
+    *  -  __u32
        -  ``hw_revision``
-
        -  Hardware device revision in a driver-specific format.
 
-    -  .. row 7
-
-       -  __u32
-
+    *  -  __u32
        -  ``driver_version``
-
        -  Media device driver version, formatted with the
 	  ``KERNEL_VERSION()`` macro. Together with the ``driver`` field
 	  this identifies a particular driver.
 
-    -  .. row 8
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved``\ [31]
-
        -  Reserved for future extensions. Drivers and applications must set
 	  this array to zero.
 
diff --git a/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst b/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst
index 582fda488810..961466ae821d 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst
@@ -58,142 +58,87 @@ id's until they get an error.
     :stub-columns: 0
     :widths: 1 1 1 1 8
 
-
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``id``
-
        -
        -
        -  Entity id, set by the application. When the id is or'ed with
 	  ``MEDIA_ENT_ID_FLAG_NEXT``, the driver clears the flag and returns
 	  the first entity with a larger id.
 
-    -  .. row 2
-
-       -  char
-
+    *  -  char
        -  ``name``\ [32]
-
        -
        -
        -  Entity name as an UTF-8 NULL-terminated string.
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``type``
-
        -
        -
        -  Entity type, see :ref:`media-entity-functions` for details.
 
-    -  .. row 4
-
-       -  __u32
-
+    *  -  __u32
        -  ``revision``
-
        -
        -
        -  Entity revision. Always zero (obsolete)
 
-    -  .. row 5
-
-       -  __u32
-
+    *  -  __u32
        -  ``flags``
-
        -
        -
        -  Entity flags, see :ref:`media-entity-flag` for details.
 
-    -  .. row 6
-
-       -  __u32
-
+    *  -  __u32
        -  ``group_id``
-
        -
        -
        -  Entity group ID. Always zero (obsolete)
 
-    -  .. row 7
-
-       -  __u16
-
+    *  -  __u16
        -  ``pads``
-
        -
        -
        -  Number of pads
 
-    -  .. row 8
-
-       -  __u16
-
+    *  -  __u16
        -  ``links``
-
        -
        -
        -  Total number of outbound links. Inbound links are not counted in
 	  this field.
 
-    -  .. row 9
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved[4]``
-
        -
        -
        -  Reserved for future extensions. Drivers and applications must set
           the array to zero.
 
-    -  .. row 10
-
-       -  union
-
-    -  .. row 11
+    *  -  union
 
-       -
+    *  -
        -  struct
-
        -  ``dev``
-
        -
        -  Valid for (sub-)devices that create a single device node.
 
-    -  .. row 12
-
-       -
+    *  -
        -
        -  __u32
-
        -  ``major``
-
        -  Device node major number.
 
-    -  .. row 13
-
-       -
+    *  -
        -
        -  __u32
-
        -  ``minor``
-
        -  Device node minor number.
 
-    -  .. row 14
-
-       -
+    *  -
        -  __u8
-
        -  ``raw``\ [184]
-
        -
        -
 
diff --git a/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst b/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst
index 256168b3c3be..17abdeed1a9c 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst
@@ -62,35 +62,21 @@ returned during the enumeration process.
     :stub-columns: 0
     :widths:       1 1 2
 
-
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``entity``
-
        -  Entity id, set by the application.
 
-    -  .. row 2
-
-       -  struct :c:type:`media_pad_desc`
-
+    *  -  struct :c:type:`media_pad_desc`
        -  \*\ ``pads``
-
        -  Pointer to a pads array allocated by the application. Ignored if
 	  NULL.
 
-    -  .. row 3
-
-       -  struct :c:type:`media_link_desc`
-
+    *  -  struct :c:type:`media_link_desc`
        -  \*\ ``links``
-
        -  Pointer to a links array allocated by the application. Ignored if
 	  NULL.
 
 
-
 .. c:type:: media_pad_desc
 
 .. tabularcolumns:: |p{4.4cm}|p{4.4cm}|p{8.7cm}|
@@ -100,37 +86,20 @@ returned during the enumeration process.
     :stub-columns: 0
     :widths:       1 1 2
 
-
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``entity``
-
        -  ID of the entity this pad belongs to.
 
-    -  .. row 2
-
-       -  __u16
-
+    *  -  __u16
        -  ``index``
-
        -  0-based pad index.
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``flags``
-
        -  Pad flags, see :ref:`media-pad-flag` for more details.
 
-    -  .. row 4
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved[2]``
-
        -  Reserved for future extensions. Drivers and applications must set
           the array to zero.
 
@@ -145,37 +114,20 @@ returned during the enumeration process.
     :stub-columns: 0
     :widths:       1 1 2
 
-
-    -  .. row 1
-
-       -  struct :c:type:`media_pad_desc`
-
+    *  -  struct :c:type:`media_pad_desc`
        -  ``source``
-
        -  Pad at the origin of this link.
 
-    -  .. row 2
-
-       -  struct :c:type:`media_pad_desc`
-
+    *  -  struct :c:type:`media_pad_desc`
        -  ``sink``
-
        -  Pad at the target of this link.
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``flags``
-
        -  Link flags, see :ref:`media-link-flag` for more details.
 
-    -  .. row 4
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved[4]``
-
        -  Reserved for future extensions. Drivers and applications must set
           the array to zero.
 
diff --git a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
index c4055ddf070a..a3f259f83b25 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
@@ -55,119 +55,66 @@ desired arrays with the media graph elements.
     :stub-columns: 0
     :widths: 1 2 8
 
-
-    -  .. row 1
-
-       -  __u64
-
+    *  -  __u64
        -  ``topology_version``
-
        -  Version of the media graph topology. When the graph is created,
 	  this field starts with zero. Every time a graph element is added
 	  or removed, this field is incremented.
 
-    -  .. row 2
-
-       -  __u32
-
+    *  -  __u32
        -  ``num_entities``
-
        -  Number of entities in the graph
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved1``
-
        -  Applications and drivers shall set this to 0.
 
-    -  .. row 4
-
-       -  __u64
-
+    *  -  __u64
        -  ``ptr_entities``
-
        -  A pointer to a memory area where the entities array will be
 	  stored, converted to a 64-bits integer. It can be zero. if zero,
 	  the ioctl won't store the entities. It will just update
 	  ``num_entities``
 
-    -  .. row 5
-
-       -  __u32
-
+    *  -  __u32
        -  ``num_interfaces``
-
        -  Number of interfaces in the graph
 
-    -  .. row 6
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved2``
-
        -  Applications and drivers shall set this to 0.
 
-    -  .. row 7
-
-       -  __u64
-
+    *  -  __u64
        -  ``ptr_interfaces``
-
        -  A pointer to a memory area where the interfaces array will be
 	  stored, converted to a 64-bits integer. It can be zero. if zero,
 	  the ioctl won't store the interfaces. It will just update
 	  ``num_interfaces``
 
-    -  .. row 8
-
-       -  __u32
-
+    *  -  __u32
        -  ``num_pads``
-
        -  Total number of pads in the graph
 
-    -  .. row 9
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved3``
-
        -  Applications and drivers shall set this to 0.
 
-    -  .. row 10
-
-       -  __u64
-
+    *  -  __u64
        -  ``ptr_pads``
-
        -  A pointer to a memory area where the pads array will be stored,
 	  converted to a 64-bits integer. It can be zero. if zero, the ioctl
 	  won't store the pads. It will just update ``num_pads``
 
-    -  .. row 11
-
-       -  __u32
-
+    *  -  __u32
        -  ``num_links``
-
        -  Total number of data and interface links in the graph
 
-    -  .. row 12
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved4``
-
        -  Applications and drivers shall set this to 0.
 
-    -  .. row 13
-
-       -  __u64
-
+    *  -  __u64
        -  ``ptr_links``
-
        -  A pointer to a memory area where the links array will be stored,
 	  converted to a 64-bits integer. It can be zero. if zero, the ioctl
 	  won't store the links. It will just update ``num_links``
@@ -182,37 +129,20 @@ desired arrays with the media graph elements.
     :stub-columns: 0
     :widths: 1 2 8
 
-
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``id``
-
        -  Unique ID for the entity.
 
-    -  .. row 2
-
-       -  char
-
+    *  -  char
        -  ``name``\ [64]
-
        -  Entity name as an UTF-8 NULL-terminated string.
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``function``
-
        -  Entity main function, see :ref:`media-entity-functions` for details.
 
-    -  .. row 4
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved``\ [6]
-
        -  Reserved for future extensions. Drivers and applications must set
 	  this array to zero.
 
@@ -226,45 +156,25 @@ desired arrays with the media graph elements.
     :stub-columns: 0
     :widths: 1 2 8
 
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``id``
-
        -  Unique ID for the interface.
 
-    -  .. row 2
-
-       -  __u32
-
+    *  -  __u32
        -  ``intf_type``
-
        -  Interface type, see :ref:`media-intf-type` for details.
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``flags``
-
        -  Interface flags. Currently unused.
 
-    -  .. row 4
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved``\ [9]
-
        -  Reserved for future extensions. Drivers and applications must set
 	  this array to zero.
 
-    -  .. row 5
-
-       -  struct media_v2_intf_devnode
-
+    *  -  struct media_v2_intf_devnode
        -  ``devnode``
-
        -  Used only for device node interfaces. See
 	  :c:type:`media_v2_intf_devnode` for details..
 
@@ -278,24 +188,14 @@ desired arrays with the media graph elements.
     :stub-columns: 0
     :widths: 1 2 8
 
-
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``major``
-
        -  Device node major number.
 
-    -  .. row 2
-
-       -  __u32
-
+    *  -  __u32
        -  ``minor``
-
        -  Device node minor number.
 
-
 .. tabularcolumns:: |p{1.6cm}|p{3.2cm}|p{12.7cm}|
 
 .. c:type:: media_v2_pad
@@ -305,37 +205,20 @@ desired arrays with the media graph elements.
     :stub-columns: 0
     :widths: 1 2 8
 
-
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``id``
-
        -  Unique ID for the pad.
 
-    -  .. row 2
-
-       -  __u32
-
+    *  -  __u32
        -  ``entity_id``
-
        -  Unique ID for the entity where this pad belongs.
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``flags``
-
        -  Pad flags, see :ref:`media-pad-flag` for more details.
 
-    -  .. row 4
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved``\ [5]
-
        -  Reserved for future extensions. Drivers and applications must set
 	  this array to zero.
 
@@ -349,49 +232,28 @@ desired arrays with the media graph elements.
     :stub-columns: 0
     :widths: 1 2 8
 
-
-    -  .. row 1
-
-       -  __u32
-
+    *  -  __u32
        -  ``id``
-
        -  Unique ID for the link.
 
-    -  .. row 2
-
-       -  __u32
-
+    *  -  __u32
        -  ``source_id``
-
        -  On pad to pad links: unique ID for the source pad.
 
 	  On interface to entity links: unique ID for the interface.
 
-    -  .. row 3
-
-       -  __u32
-
+    *  -  __u32
        -  ``sink_id``
-
        -  On pad to pad links: unique ID for the sink pad.
 
 	  On interface to entity links: unique ID for the entity.
 
-    -  .. row 4
-
-       -  __u32
-
+    *  -  __u32
        -  ``flags``
-
        -  Link flags, see :ref:`media-link-flag` for more details.
 
-    -  .. row 5
-
-       -  __u32
-
+    *  -  __u32
        -  ``reserved``\ [6]
-
        -  Reserved for future extensions. Drivers and applications must set
 	  this array to zero.
 
diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst
index 2dda14bd89b7..96910cf2eaaa 100644
--- a/Documentation/media/uapi/mediactl/media-types.rst
+++ b/Documentation/media/uapi/mediactl/media-types.rst
@@ -8,6 +8,38 @@ Types and flags used to represent the media graph elements
 ..  tabularcolumns:: |p{8.2cm}|p{10.3cm}|
 
 .. _media-entity-functions:
+.. _MEDIA-ENT-F-UNKNOWN:
+.. _MEDIA-ENT-F-V4L2-SUBDEV-UNKNOWN:
+.. _MEDIA-ENT-F-IO-V4L:
+.. _MEDIA-ENT-F-IO-VBI:
+.. _MEDIA-ENT-F-IO-SWRADIO:
+.. _MEDIA-ENT-F-IO-DTV:
+.. _MEDIA-ENT-F-DTV-DEMOD:
+.. _MEDIA-ENT-F-TS-DEMUX:
+.. _MEDIA-ENT-F-DTV-CA:
+.. _MEDIA-ENT-F-DTV-NET-DECAP:
+.. _MEDIA-ENT-F-CONN-RF:
+.. _MEDIA-ENT-F-CONN-SVIDEO:
+.. _MEDIA-ENT-F-CONN-COMPOSITE:
+.. _MEDIA-ENT-F-CAM-SENSOR:
+.. _MEDIA-ENT-F-FLASH:
+.. _MEDIA-ENT-F-LENS:
+.. _MEDIA-ENT-F-ATV-DECODER:
+.. _MEDIA-ENT-F-TUNER:
+.. _MEDIA-ENT-F-IF-VID-DECODER:
+.. _MEDIA-ENT-F-IF-AUD-DECODER:
+.. _MEDIA-ENT-F-AUDIO-CAPTURE:
+.. _MEDIA-ENT-F-AUDIO-PLAYBACK:
+.. _MEDIA-ENT-F-AUDIO-MIXER:
+.. _MEDIA-ENT-F-PROC-VIDEO-COMPOSER:
+.. _MEDIA-ENT-F-PROC-VIDEO-PIXEL-FORMATTER:
+.. _MEDIA-ENT-F-PROC-VIDEO-PIXEL-ENC-CONV:
+.. _MEDIA-ENT-F-PROC-VIDEO-LUT:
+.. _MEDIA-ENT-F-PROC-VIDEO-SCALER:
+.. _MEDIA-ENT-F-PROC-VIDEO-STATISTICS:
+.. _MEDIA-ENT-F-VID-MUX:
+.. _MEDIA-ENT-F-VID-IF-BRIDGE:
+.. _MEDIA-ENT-F-DTV-DECODER:
 
 .. cssclass:: longtable
 
@@ -15,139 +47,56 @@ Types and flags used to represent the media graph elements
     :header-rows:  0
     :stub-columns: 0
 
-
-    -  .. row 1
-
-       .. _MEDIA-ENT-F-UNKNOWN:
-       .. _MEDIA-ENT-F-V4L2-SUBDEV-UNKNOWN:
-
-       -  ``MEDIA_ENT_F_UNKNOWN`` and
-
+    *  -  ``MEDIA_ENT_F_UNKNOWN`` and
 	  ``MEDIA_ENT_F_V4L2_SUBDEV_UNKNOWN``
-
        -  Unknown entity. That generally indicates that a driver didn't
 	  initialize properly the entity, which is a Kernel bug
 
-    -  .. row 2
-
-       ..  _MEDIA-ENT-F-IO-V4L:
-
-       -  ``MEDIA_ENT_F_IO_V4L``
-
+    *  -  ``MEDIA_ENT_F_IO_V4L``
        -  Data streaming input and/or output entity.
 
-    -  .. row 3
-
-       ..  _MEDIA-ENT-F-IO-VBI:
-
-       -  ``MEDIA_ENT_F_IO_VBI``
-
+    *  -  ``MEDIA_ENT_F_IO_VBI``
        -  V4L VBI streaming input or output entity
 
-    -  .. row 4
-
-       ..  _MEDIA-ENT-F-IO-SWRADIO:
-
-       -  ``MEDIA_ENT_F_IO_SWRADIO``
-
+    *  -  ``MEDIA_ENT_F_IO_SWRADIO``
        -  V4L Software Digital Radio (SDR) streaming input or output entity
 
-    -  .. row 5
-
-       ..  _MEDIA-ENT-F-IO-DTV:
-
-       -  ``MEDIA_ENT_F_IO_DTV``
-
+    *  -  ``MEDIA_ENT_F_IO_DTV``
        -  DVB Digital TV streaming input or output entity
 
-    -  .. row 6
-
-       ..  _MEDIA-ENT-F-DTV-DEMOD:
-
-       -  ``MEDIA_ENT_F_DTV_DEMOD``
-
+    *  -  ``MEDIA_ENT_F_DTV_DEMOD``
        -  Digital TV demodulator entity.
 
-    -  .. row 7
-
-       ..  _MEDIA-ENT-F-TS-DEMUX:
-
-       -  ``MEDIA_ENT_F_TS_DEMUX``
-
+    *  -  ``MEDIA_ENT_F_TS_DEMUX``
        -  MPEG Transport stream demux entity. Could be implemented on
 	  hardware or in Kernelspace by the Linux DVB subsystem.
 
-    -  .. row 8
-
-       ..  _MEDIA-ENT-F-DTV-CA:
-
-       -  ``MEDIA_ENT_F_DTV_CA``
-
+    *  -  ``MEDIA_ENT_F_DTV_CA``
        -  Digital TV Conditional Access module (CAM) entity
 
-    -  .. row 9
-
-       ..  _MEDIA-ENT-F-DTV-NET-DECAP:
-
-       -  ``MEDIA_ENT_F_DTV_NET_DECAP``
-
+    *  -  ``MEDIA_ENT_F_DTV_NET_DECAP``
        -  Digital TV network ULE/MLE desencapsulation entity. Could be
 	  implemented on hardware or in Kernelspace
 
-    -  .. row 10
-
-       ..  _MEDIA-ENT-F-CONN-RF:
-
-       -  ``MEDIA_ENT_F_CONN_RF``
-
+    *  -  ``MEDIA_ENT_F_CONN_RF``
        -  Connector for a Radio Frequency (RF) signal.
 
-    -  .. row 11
-
-       ..  _MEDIA-ENT-F-CONN-SVIDEO:
-
-       -  ``MEDIA_ENT_F_CONN_SVIDEO``
-
+    *  -  ``MEDIA_ENT_F_CONN_SVIDEO``
        -  Connector for a S-Video signal.
 
-    -  .. row 12
-
-       ..  _MEDIA-ENT-F-CONN-COMPOSITE:
-
-       -  ``MEDIA_ENT_F_CONN_COMPOSITE``
-
+    *  -  ``MEDIA_ENT_F_CONN_COMPOSITE``
        -  Connector for a RGB composite signal.
 
-    -  .. row 13
-
-       ..  _MEDIA-ENT-F-CAM-SENSOR:
-
-       -  ``MEDIA_ENT_F_CAM_SENSOR``
-
+    *  -  ``MEDIA_ENT_F_CAM_SENSOR``
        -  Camera video sensor entity.
 
-    -  .. row 14
-
-       ..  _MEDIA-ENT-F-FLASH:
-
-       -  ``MEDIA_ENT_F_FLASH``
-
+    *  -  ``MEDIA_ENT_F_FLASH``
        -  Flash controller entity.
 
-    -  .. row 15
-
-       ..  _MEDIA-ENT-F-LENS:
-
-       -  ``MEDIA_ENT_F_LENS``
-
+    *  -  ``MEDIA_ENT_F_LENS``
        -  Lens controller entity.
 
-    -  .. row 16
-
-       ..  _MEDIA-ENT-F-ATV-DECODER:
-
-       -  ``MEDIA_ENT_F_ATV_DECODER``
-
+    *  -  ``MEDIA_ENT_F_ATV_DECODER``
        -  Analog video decoder, the basic function of the video decoder is
 	  to accept analogue video from a wide variety of sources such as
 	  broadcast, DVD players, cameras and video cassette recorders, in
@@ -155,36 +104,21 @@ Types and flags used to represent the media graph elements
 	  its component parts, luminance and chrominance, and output it in
 	  some digital video standard, with appropriate timing signals.
 
-    -  .. row 17
-
-       ..  _MEDIA-ENT-F-TUNER:
-
-       -  ``MEDIA_ENT_F_TUNER``
-
+    *  -  ``MEDIA_ENT_F_TUNER``
        -  Digital TV, analog TV, radio and/or software radio tuner, with
 	  consists on a PLL tuning stage that converts radio frequency (RF)
 	  signal into an Intermediate Frequency (IF). Modern tuners have
 	  internally IF-PLL decoders for audio and video, but older models
 	  have those stages implemented on separate entities.
 
-    -  .. row 18
-
-       ..  _MEDIA-ENT-F-IF-VID-DECODER:
-
-       -  ``MEDIA_ENT_F_IF_VID_DECODER``
-
+    *  -  ``MEDIA_ENT_F_IF_VID_DECODER``
        -  IF-PLL video decoder. It receives the IF from a PLL and decodes
 	  the analog TV video signal. This is commonly found on some very
 	  old analog tuners, like Philips MK3 designs. They all contain a
 	  tda9887 (or some software compatible similar chip, like tda9885).
 	  Those devices use a different I2C address than the tuner PLL.
 
-    -  .. row 19
-
-       ..  _MEDIA-ENT-F-IF-AUD-DECODER:
-
-       -  ``MEDIA_ENT_F_IF_AUD_DECODER``
-
+    *  -  ``MEDIA_ENT_F_IF_AUD_DECODER``
        -  IF-PLL sound decoder. It receives the IF from a PLL and decodes
 	  the analog TV audio signal. This is commonly found on some very
 	  old analog hardware, like Micronas msp3400, Philips tda9840,
@@ -192,36 +126,16 @@ Types and flags used to represent the media graph elements
 	  tuner PLL and should be controlled together with the IF-PLL video
 	  decoder.
 
-    -  .. row 20
-
-       ..  _MEDIA-ENT-F-AUDIO-CAPTURE:
-
-       -  ``MEDIA_ENT_F_AUDIO_CAPTURE``
-
+    *  -  ``MEDIA_ENT_F_AUDIO_CAPTURE``
        -  Audio Capture Function Entity.
 
-    -  .. row 21
-
-       ..  _MEDIA-ENT-F-AUDIO-PLAYBACK:
-
-       -  ``MEDIA_ENT_F_AUDIO_PLAYBACK``
-
+    *  -  ``MEDIA_ENT_F_AUDIO_PLAYBACK``
        -  Audio Playback Function Entity.
 
-    -  .. row 22
-
-       ..  _MEDIA-ENT-F-AUDIO-MIXER:
-
-       -  ``MEDIA_ENT_F_AUDIO_MIXER``
-
+    *  -  ``MEDIA_ENT_F_AUDIO_MIXER``
        -  Audio Mixer Function Entity.
 
-    -  .. row 23
-
-       ..  _MEDIA-ENT-F-PROC-VIDEO-COMPOSER:
-
-       -  ``MEDIA_ENT_F_PROC_VIDEO_COMPOSER``
-
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_COMPOSER``
        -  Video composer (blender). An entity capable of video
 	  composing must have at least two sink pads and one source
 	  pad, and composes input video frames onto output video
@@ -229,12 +143,7 @@ Types and flags used to represent the media graph elements
 	  color keying, raster operations (ROP), stitching or any other
 	  means.
 
-    -  ..  row 24
-
-       ..  _MEDIA-ENT-F-PROC-VIDEO-PIXEL-FORMATTER:
-
-       -  ``MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER``
-
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER``
        -  Video pixel formatter. An entity capable of pixel formatting
 	  must have at least one sink pad and one source pad. Read
 	  pixel formatters read pixels from memory and perform a subset
@@ -243,12 +152,7 @@ Types and flags used to represent the media graph elements
 	  a subset of dithering, pixel encoding conversion and packing
 	  and write pixels to memory.
 
-    -  ..  row 25
-
-       ..  _MEDIA-ENT-F-PROC-VIDEO-PIXEL-ENC-CONV:
-
-       -  ``MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV``
-
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_PIXEL_ENC_CONV``
        -  Video pixel encoding converter. An entity capable of pixel
 	  enconding conversion must have at least one sink pad and one
 	  source pad, and convert the encoding of pixels received on
@@ -257,12 +161,7 @@ Types and flags used to represent the media graph elements
 	  to RGB to/from HSV, RGB to/from YUV and CFA (Bayer) to RGB
 	  conversions.
 
-    -  ..  row 26
-
-       ..  _MEDIA-ENT-F-PROC-VIDEO-LUT:
-
-       -  ``MEDIA_ENT_F_PROC_VIDEO_LUT``
-
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_LUT``
        -  Video look-up table. An entity capable of video lookup table
 	  processing must have one sink pad and one source pad. It uses
 	  the values of the pixels received on its sink pad to look up
@@ -271,12 +170,7 @@ Types and flags used to represent the media graph elements
 	  separately or combine them for multi-dimensional table
 	  lookups.
 
-    -  ..  row 27
-
-       ..  _MEDIA-ENT-F-PROC-VIDEO-SCALER:
-
-       -  ``MEDIA_ENT_F_PROC_VIDEO_SCALER``
-
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_SCALER``
        -  Video scaler. An entity capable of video scaling must have
 	  at least one sink pad and one source pad, and scale the
 	  video frame(s) received on its sink pad(s) to a different
@@ -287,46 +181,26 @@ Types and flags used to represent the media graph elements
 	  sub-sampling (occasionally also referred to as skipping) are
 	  considered as scaling.
 
-    -  ..  row 28
-
-       ..  _MEDIA-ENT-F-PROC-VIDEO-STATISTICS:
-
-       -  ``MEDIA_ENT_F_PROC_VIDEO_STATISTICS``
-
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_STATISTICS``
        -  Video statistics computation (histogram, 3A, etc.). An entity
 	  capable of statistics computation must have one sink pad and
 	  one source pad. It computes statistics over the frames
 	  received on its sink pad and outputs the statistics data on
 	  its source pad.
 
-    -  ..  row 29
-
-       ..  _MEDIA-ENT-F-VID-MUX:
-
-       -  ``MEDIA_ENT_F_VID_MUX``
-
+    *  -  ``MEDIA_ENT_F_VID_MUX``
        - Video multiplexer. An entity capable of multiplexing must have at
          least two sink pads and one source pad, and must pass the video
          frame(s) received from the active sink pad to the source pad.
 
-    -  ..  row 30
-
-       ..  _MEDIA-ENT-F-VID-IF-BRIDGE:
-
-       -  ``MEDIA_ENT_F_VID_IF_BRIDGE``
-
+    *  -  ``MEDIA_ENT_F_VID_IF_BRIDGE``
        - Video interface bridge. A video interface bridge entity must have at
          least one sink pad and at least one source pad. It receives video
          frames on its sink pad from an input video bus of one type (HDMI, eDP,
          MIPI CSI-2, etc.), and outputs them on its source pad to an output
          video bus of another type (eDP, MIPI CSI-2, parallel, etc.).
 
-    -  ..  row 31
-
-       ..  _MEDIA-ENT-F-DTV-DECODER:
-
-       -  ``MEDIA_ENT_F_DTV_DECODER``
-
+    *  -  ``MEDIA_ENT_F_DTV_DECODER``
        -  Digital video decoder. The basic function of the video decoder is
 	  to accept digital video from a wide variety of sources
 	  and output it in some digital video standard, with appropriate
@@ -335,263 +209,145 @@ Types and flags used to represent the media graph elements
 ..  tabularcolumns:: |p{5.5cm}|p{12.0cm}|
 
 .. _media-entity-flag:
+.. _MEDIA-ENT-FL-DEFAULT:
+.. _MEDIA-ENT-FL-CONNECTOR:
 
 .. flat-table:: Media entity flags
     :header-rows:  0
     :stub-columns: 0
 
-
-    -  .. row 1
-
-       ..  _MEDIA-ENT-FL-DEFAULT:
-
-       -  ``MEDIA_ENT_FL_DEFAULT``
-
+    *  -  ``MEDIA_ENT_FL_DEFAULT``
        -  Default entity for its type. Used to discover the default audio,
 	  VBI and video devices, the default camera sensor, etc.
 
-    -  .. row 2
-
-       ..  _MEDIA-ENT-FL-CONNECTOR:
-
-       -  ``MEDIA_ENT_FL_CONNECTOR``
-
+    *  -  ``MEDIA_ENT_FL_CONNECTOR``
        -  The entity represents a connector.
 
 
 ..  tabularcolumns:: |p{6.5cm}|p{6.0cm}|p{5.0cm}|
 
 .. _media-intf-type:
+.. _MEDIA-INTF-T-DVB-FE:
+.. _MEDIA-INTF-T-DVB-DEMUX:
+.. _MEDIA-INTF-T-DVB-DVR:
+.. _MEDIA-INTF-T-DVB-CA:
+.. _MEDIA-INTF-T-DVB-NET:
+.. _MEDIA-INTF-T-V4L-VIDEO:
+.. _MEDIA-INTF-T-V4L-VBI:
+.. _MEDIA-INTF-T-V4L-RADIO:
+.. _MEDIA-INTF-T-V4L-SUBDEV:
+.. _MEDIA-INTF-T-V4L-SWRADIO:
+.. _MEDIA-INTF-T-V4L-TOUCH:
+.. _MEDIA-INTF-T-ALSA-PCM-CAPTURE:
+.. _MEDIA-INTF-T-ALSA-PCM-PLAYBACK:
+.. _MEDIA-INTF-T-ALSA-CONTROL:
+.. _MEDIA-INTF-T-ALSA-COMPRESS:
+.. _MEDIA-INTF-T-ALSA-RAWMIDI:
+.. _MEDIA-INTF-T-ALSA-HWDEP:
+.. _MEDIA-INTF-T-ALSA-SEQUENCER:
+.. _MEDIA-INTF-T-ALSA-TIMER:
 
 .. flat-table:: Media interface types
     :header-rows:  0
     :stub-columns: 0
 
-
-    -  .. row 1
-
-       ..  _MEDIA-INTF-T-DVB-FE:
-
-       -  ``MEDIA_INTF_T_DVB_FE``
-
+    *  -  ``MEDIA_INTF_T_DVB_FE``
        -  Device node interface for the Digital TV frontend
-
        -  typically, /dev/dvb/adapter?/frontend?
 
-    -  .. row 2
-
-       ..  _MEDIA-INTF-T-DVB-DEMUX:
-
-       -  ``MEDIA_INTF_T_DVB_DEMUX``
-
+    *  -  ``MEDIA_INTF_T_DVB_DEMUX``
        -  Device node interface for the Digital TV demux
-
        -  typically, /dev/dvb/adapter?/demux?
 
-    -  .. row 3
-
-       ..  _MEDIA-INTF-T-DVB-DVR:
-
-       -  ``MEDIA_INTF_T_DVB_DVR``
-
+    *  -  ``MEDIA_INTF_T_DVB_DVR``
        -  Device node interface for the Digital TV DVR
-
        -  typically, /dev/dvb/adapter?/dvr?
 
-    -  .. row 4
-
-       ..  _MEDIA-INTF-T-DVB-CA:
-
-       -  ``MEDIA_INTF_T_DVB_CA``
-
+    *  -  ``MEDIA_INTF_T_DVB_CA``
        -  Device node interface for the Digital TV Conditional Access
-
        -  typically, /dev/dvb/adapter?/ca?
 
-    -  .. row 5
-
-       ..  _MEDIA-INTF-T-DVB-NET:
-
-       -  ``MEDIA_INTF_T_DVB_NET``
-
+    *  -  ``MEDIA_INTF_T_DVB_NET``
        -  Device node interface for the Digital TV network control
-
        -  typically, /dev/dvb/adapter?/net?
 
-    -  .. row 6
-
-       ..  _MEDIA-INTF-T-V4L-VIDEO:
-
-       -  ``MEDIA_INTF_T_V4L_VIDEO``
-
+    *  -  ``MEDIA_INTF_T_V4L_VIDEO``
        -  Device node interface for video (V4L)
-
        -  typically, /dev/video?
 
-    -  .. row 7
-
-       ..  _MEDIA-INTF-T-V4L-VBI:
-
-       -  ``MEDIA_INTF_T_V4L_VBI``
-
+    *  -  ``MEDIA_INTF_T_V4L_VBI``
        -  Device node interface for VBI (V4L)
-
        -  typically, /dev/vbi?
 
-    -  .. row 8
-
-       ..  _MEDIA-INTF-T-V4L-RADIO:
-
-       -  ``MEDIA_INTF_T_V4L_RADIO``
-
+    *  -  ``MEDIA_INTF_T_V4L_RADIO``
        -  Device node interface for radio (V4L)
-
        -  typically, /dev/radio?
 
-    -  .. row 9
-
-       ..  _MEDIA-INTF-T-V4L-SUBDEV:
-
-       -  ``MEDIA_INTF_T_V4L_SUBDEV``
-
+    *  -  ``MEDIA_INTF_T_V4L_SUBDEV``
        -  Device node interface for a V4L subdevice
-
        -  typically, /dev/v4l-subdev?
 
-    -  .. row 10
-
-       ..  _MEDIA-INTF-T-V4L-SWRADIO:
-
-       -  ``MEDIA_INTF_T_V4L_SWRADIO``
-
+    *  -  ``MEDIA_INTF_T_V4L_SWRADIO``
        -  Device node interface for Software Defined Radio (V4L)
-
        -  typically, /dev/swradio?
 
-    -  .. row 11
-
-       ..  _MEDIA-INTF-T-V4L-TOUCH:
-
-       -  ``MEDIA_INTF_T_V4L_TOUCH``
-
+    *  -  ``MEDIA_INTF_T_V4L_TOUCH``
        -  Device node interface for Touch device (V4L)
-
        -  typically, /dev/v4l-touch?
 
-    -  .. row 12
-
-       ..  _MEDIA-INTF-T-ALSA-PCM-CAPTURE:
-
-       -  ``MEDIA_INTF_T_ALSA_PCM_CAPTURE``
-
+    *  -  ``MEDIA_INTF_T_ALSA_PCM_CAPTURE``
        -  Device node interface for ALSA PCM Capture
-
        -  typically, /dev/snd/pcmC?D?c
 
-    -  .. row 13
-
-       ..  _MEDIA-INTF-T-ALSA-PCM-PLAYBACK:
-
-       -  ``MEDIA_INTF_T_ALSA_PCM_PLAYBACK``
-
+    *  -  ``MEDIA_INTF_T_ALSA_PCM_PLAYBACK``
        -  Device node interface for ALSA PCM Playback
-
        -  typically, /dev/snd/pcmC?D?p
 
-    -  .. row 14
-
-       ..  _MEDIA-INTF-T-ALSA-CONTROL:
-
-       -  ``MEDIA_INTF_T_ALSA_CONTROL``
-
+    *  -  ``MEDIA_INTF_T_ALSA_CONTROL``
        -  Device node interface for ALSA Control
-
        -  typically, /dev/snd/controlC?
 
-    -  .. row 15
-
-       ..  _MEDIA-INTF-T-ALSA-COMPRESS:
-
-       -  ``MEDIA_INTF_T_ALSA_COMPRESS``
-
+    *  -  ``MEDIA_INTF_T_ALSA_COMPRESS``
        -  Device node interface for ALSA Compress
-
        -  typically, /dev/snd/compr?
 
-    -  .. row 16
-
-       ..  _MEDIA-INTF-T-ALSA-RAWMIDI:
-
-       -  ``MEDIA_INTF_T_ALSA_RAWMIDI``
-
+    *  -  ``MEDIA_INTF_T_ALSA_RAWMIDI``
        -  Device node interface for ALSA Raw MIDI
-
        -  typically, /dev/snd/midi?
 
-    -  .. row 17
-
-       ..  _MEDIA-INTF-T-ALSA-HWDEP:
-
-       -  ``MEDIA_INTF_T_ALSA_HWDEP``
-
+    *  -  ``MEDIA_INTF_T_ALSA_HWDEP``
        -  Device node interface for ALSA Hardware Dependent
-
        -  typically, /dev/snd/hwC?D?
 
-    -  .. row 18
-
-       ..  _MEDIA-INTF-T-ALSA-SEQUENCER:
-
-       -  ``MEDIA_INTF_T_ALSA_SEQUENCER``
-
+    *  -  ``MEDIA_INTF_T_ALSA_SEQUENCER``
        -  Device node interface for ALSA Sequencer
-
        -  typically, /dev/snd/seq
 
-    -  .. row 19
-
-       ..  _MEDIA-INTF-T-ALSA-TIMER:
-
-       -  ``MEDIA_INTF_T_ALSA_TIMER``
-
+    *  -  ``MEDIA_INTF_T_ALSA_TIMER``
        -  Device node interface for ALSA Timer
-
        -  typically, /dev/snd/timer
 
 
 .. tabularcolumns:: |p{5.5cm}|p{12.0cm}|
 
 .. _media-pad-flag:
+.. _MEDIA-PAD-FL-SINK:
+.. _MEDIA-PAD-FL-SOURCE:
+.. _MEDIA-PAD-FL-MUST-CONNECT:
 
 .. flat-table:: Media pad flags
     :header-rows:  0
     :stub-columns: 0
 
-
-    -  .. row 1
-
-       ..  _MEDIA-PAD-FL-SINK:
-
-       -  ``MEDIA_PAD_FL_SINK``
-
+    *  -  ``MEDIA_PAD_FL_SINK``
        -  Input pad, relative to the entity. Input pads sink data and are
 	  targets of links.
 
-    -  .. row 2
-
-       ..  _MEDIA-PAD-FL-SOURCE:
-
-       -  ``MEDIA_PAD_FL_SOURCE``
-
+    *  -  ``MEDIA_PAD_FL_SOURCE``
        -  Output pad, relative to the entity. Output pads source data and
 	  are origins of links.
 
-    -  .. row 3
-
-       ..  _MEDIA-PAD-FL-MUST-CONNECT:
-
-       -  ``MEDIA_PAD_FL_MUST_CONNECT``
-
+    *  -  ``MEDIA_PAD_FL_MUST_CONNECT``
        -  If this flag is set and the pad is linked to any other pad, then
 	  at least one of those links must be enabled for the entity to be
 	  able to stream. There could be temporary reasons (e.g. device
@@ -606,46 +362,29 @@ must be set for every pad.
 .. tabularcolumns:: |p{5.5cm}|p{12.0cm}|
 
 .. _media-link-flag:
+.. _MEDIA-LNK-FL-ENABLED:
+.. _MEDIA-LNK-FL-IMMUTABLE:
+.. _MEDIA-LNK-FL-DYNAMIC:
+.. _MEDIA-LNK-FL-LINK-TYPE:
 
 .. flat-table:: Media link flags
     :header-rows:  0
     :stub-columns: 0
 
-
-    -  .. row 1
-
-       ..  _MEDIA-LNK-FL-ENABLED:
-
-       -  ``MEDIA_LNK_FL_ENABLED``
-
+    *  -  ``MEDIA_LNK_FL_ENABLED``
        -  The link is enabled and can be used to transfer media data. When
 	  two or more links target a sink pad, only one of them can be
 	  enabled at a time.
 
-    -  .. row 2
-
-       ..  _MEDIA-LNK-FL-IMMUTABLE:
-
-       -  ``MEDIA_LNK_FL_IMMUTABLE``
-
+    *  -  ``MEDIA_LNK_FL_IMMUTABLE``
        -  The link enabled state can't be modified at runtime. An immutable
 	  link is always enabled.
 
-    -  .. row 3
-
-       ..  _MEDIA-LNK-FL-DYNAMIC:
-
-       -  ``MEDIA_LNK_FL_DYNAMIC``
-
+    *  -  ``MEDIA_LNK_FL_DYNAMIC``
        -  The link enabled state can be modified during streaming. This flag
 	  is set by drivers and is read-only for applications.
 
-    -  .. row 4
-
-       ..  _MEDIA-LNK-FL-LINK-TYPE:
-
-       -  ``MEDIA_LNK_FL_LINK_TYPE``
-
+    *  -  ``MEDIA_LNK_FL_LINK_TYPE``
        -  This is a bitmask that defines the type of the link. Currently,
 	  two types of links are supported:
 
-- 
cgit v1.2.3


From 00af4635a1de10644ed76fee973b44a001499108 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Fri, 15 Jun 2018 09:19:45 -0400
Subject: media: subdev-formats.rst: fix incorrect types

The ycbcr_enc, quantization and xfer_func fields are __u16 and not enums.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/subdev-formats.rst | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/Documentation/media/uapi/v4l/subdev-formats.rst b/Documentation/media/uapi/v4l/subdev-formats.rst
index 9fcabe7f9367..a4739f79d9c3 100644
--- a/Documentation/media/uapi/v4l/subdev-formats.rst
+++ b/Documentation/media/uapi/v4l/subdev-formats.rst
@@ -37,19 +37,22 @@ Media Bus Formats
       - Image colorspace, from enum
 	:c:type:`v4l2_colorspace`. See
 	:ref:`colorspaces` for details.
-    * - enum :c:type:`v4l2_ycbcr_encoding`
+    * - __u16
       - ``ycbcr_enc``
-      - This information supplements the ``colorspace`` and must be set by
+      - Y'CbCr encoding, from enum :c:type:`v4l2_ycbcr_encoding`.
+        This information supplements the ``colorspace`` and must be set by
 	the driver for capture streams and by the application for output
 	streams, see :ref:`colorspaces`.
-    * - enum :c:type:`v4l2_quantization`
+    * - __u16
       - ``quantization``
-      - This information supplements the ``colorspace`` and must be set by
+      - Quantization range, from enum :c:type:`v4l2_quantization`.
+        This information supplements the ``colorspace`` and must be set by
 	the driver for capture streams and by the application for output
 	streams, see :ref:`colorspaces`.
-    * - enum :c:type:`v4l2_xfer_func`
+    * - __u16
       - ``xfer_func``
-      - This information supplements the ``colorspace`` and must be set by
+      - Transfer function, from enum :c:type:`v4l2_xfer_func`.
+        This information supplements the ``colorspace`` and must be set by
 	the driver for capture streams and by the application for output
 	streams, see :ref:`colorspaces`.
     * - __u16
-- 
cgit v1.2.3


From e1a98c163eb276b5b5e1bece560ed7f0b9eb3b49 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Fri, 15 Jun 2018 09:19:46 -0400
Subject: media: media.h: remove __NEED_MEDIA_LEGACY_API

The __NEED_MEDIA_LEGACY_API define is 1) ugly and 2) dangerous
since it is all too easy for drivers to define it to get hold of
legacy defines. Instead just define what we need in media-device.c
which is the only place where we need the legacy define
(MEDIA_ENT_T_DEVNODE_UNKNOWN).

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Mauro Carvalho Chehab <mchehab@s-opensource.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/media-device.c | 13 ++++++++++---
 include/uapi/linux/media.h   |  2 +-
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index ae59c3177555..47bb2254fbfd 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -16,9 +16,6 @@
  * GNU General Public License for more details.
  */
 
-/* We need to access legacy defines from linux/media.h */
-#define __NEED_MEDIA_LEGACY_API
-
 #include <linux/compat.h>
 #include <linux/export.h>
 #include <linux/idr.h>
@@ -35,6 +32,16 @@
 
 #ifdef CONFIG_MEDIA_CONTROLLER
 
+/*
+ * Legacy defines from linux/media.h. This is the only place we need this
+ * so we just define it here. The media.h header doesn't expose it to the
+ * kernel to prevent it from being used by drivers, but here (and only here!)
+ * we need it to handle the legacy behavior.
+ */
+#define MEDIA_ENT_SUBTYPE_MASK			0x0000ffff
+#define MEDIA_ENT_T_DEVNODE_UNKNOWN		(MEDIA_ENT_F_OLD_BASE | \
+						 MEDIA_ENT_SUBTYPE_MASK)
+
 /* -----------------------------------------------------------------------------
  * Userspace API
  */
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index c7e9a5cba24e..86c7dcc9cba3 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -348,7 +348,7 @@ struct media_v2_topology {
 #define MEDIA_IOC_SETUP_LINK	_IOWR('|', 0x03, struct media_link_desc)
 #define MEDIA_IOC_G_TOPOLOGY	_IOWR('|', 0x04, struct media_v2_topology)
 
-#if !defined(__KERNEL__) || defined(__NEED_MEDIA_LEGACY_API)
+#ifndef __KERNEL__
 
 /*
  * Legacy symbols used to avoid userspace compilation breakages.
-- 
cgit v1.2.3


From 6d4e7919d7b5ffc388ec9d8babd72368e6d65d6e Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Wed, 2 May 2018 16:47:20 -0400
Subject: media: dt-bindings: media: Define "rotation" property for sensors

Sensors are occasionally mounted upside down to systems such as mobile
phones or tablets. In order to use such a sensor without having to turn
every image upside down, most camera sensors support reversing the readout
order by setting both horizontal and vertical flipping.

This patch documents the "rotation" property for camera sensors, mirroring
what is defined for displays in
Documentation/devicetree/bindings/display/panel/panel.txt .

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/video-interfaces.txt | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/video-interfaces.txt b/Documentation/devicetree/bindings/media/video-interfaces.txt
index 258b8dfddf48..52b7c7b57842 100644
--- a/Documentation/devicetree/bindings/media/video-interfaces.txt
+++ b/Documentation/devicetree/bindings/media/video-interfaces.txt
@@ -85,6 +85,10 @@ Optional properties
 
 - lens-focus: A phandle to the node of the focus lens controller.
 
+- rotation: The device, typically an image sensor, is not mounted upright,
+  but a number of degrees counter clockwise. Typical values are 0 and 180
+  (upside down).
+
 
 Optional endpoint properties
 ----------------------------
-- 
cgit v1.2.3


From 691faafa78e1a0eae2fa7db87a1b9c3e95dc9292 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 14 Jun 2018 08:17:29 -0400
Subject: media: dt-bindings: smia: Add "rotation" property

Add the rotation property to list of optional properties for the smia
sensors.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/i2c/nokia,smia.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt b/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt
index 33f10a94c381..8ee7c7972ac7 100644
--- a/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt
+++ b/Documentation/devicetree/bindings/media/i2c/nokia,smia.txt
@@ -29,6 +29,9 @@ Optional properties
 - reset-gpios: XSHUTDOWN GPIO
 - flash-leds: See ../video-interfaces.txt
 - lens-focus: See ../video-interfaces.txt
+- rotation: Integer property; valid values are 0 (sensor mounted upright)
+	    and 180 (sensor mounted upside down). See
+	    ../video-interfaces.txt .
 
 
 Endpoint node mandatory properties
-- 
cgit v1.2.3


From 5f9e711b75a51b96c05f61a93b3f7c0d79dc20e2 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Wed, 2 May 2018 16:59:00 -0400
Subject: media: smiapp: Support the "rotation" property

Use the "rotation" property to tell that the sensor is mounted upside
down. This reverses the behaviour of the VFLIP and HFLIP controls as well
as the pixel order.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/smiapp/smiapp-core.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index e1f8208581aa..e9e0f21efc2a 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -2764,6 +2764,7 @@ static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev)
 	struct v4l2_fwnode_endpoint *bus_cfg;
 	struct fwnode_handle *ep;
 	struct fwnode_handle *fwnode = dev_fwnode(dev);
+	u32 rotation;
 	int i;
 	int rval;
 
@@ -2800,6 +2801,21 @@ static struct smiapp_hwconfig *smiapp_get_hwconfig(struct device *dev)
 
 	dev_dbg(dev, "lanes %u\n", hwcfg->lanes);
 
+	rval = fwnode_property_read_u32(fwnode, "rotation", &rotation);
+	if (!rval) {
+		switch (rotation) {
+		case 180:
+			hwcfg->module_board_orient =
+				SMIAPP_MODULE_BOARD_ORIENT_180;
+			/* Fall through */
+		case 0:
+			break;
+		default:
+			dev_err(dev, "invalid rotation %u\n", rotation);
+			goto out_err;
+		}
+	}
+
 	/* NVM size is not mandatory */
 	fwnode_property_read_u32(fwnode, "nokia,nvm-size", &hwcfg->nvm_size);
 
-- 
cgit v1.2.3


From ce85705a2abb4324e18ded9d6df2b278b952edb6 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 18 Jun 2018 06:29:17 -0400
Subject: media: ov5640: add HFLIP/VFLIP controls support

Add HFLIP/VFLIP controls support by setting registers REG21/REG20.
Useless values in hardcoded mode sequences are removed and
remaining binning values are now set after mode sequence being set.
Note that due to BSI (Back Side Illuminated) technology, image capture
is physically mirrored, mirror logic is so inversed in REG21 register
to cancel this effect.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov5640.c | 103 +++++++++++++++++++++++++++++++++++++--------
 1 file changed, 85 insertions(+), 18 deletions(-)

diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index f6e40cc9745c..41039e535499 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -64,6 +64,7 @@
 #define OV5640_REG_TIMING_DVPVO		0x380a
 #define OV5640_REG_TIMING_HTS		0x380c
 #define OV5640_REG_TIMING_VTS		0x380e
+#define OV5640_REG_TIMING_TC_REG20	0x3820
 #define OV5640_REG_TIMING_TC_REG21	0x3821
 #define OV5640_REG_AEC_CTRL00		0x3a00
 #define OV5640_REG_AEC_B50_STEP		0x3a08
@@ -199,6 +200,8 @@ struct ov5640_ctrls {
 	struct v4l2_ctrl *contrast;
 	struct v4l2_ctrl *hue;
 	struct v4l2_ctrl *test_pattern;
+	struct v4l2_ctrl *hflip;
+	struct v4l2_ctrl *vflip;
 };
 
 struct ov5640_dev {
@@ -341,7 +344,7 @@ static const struct reg_value ov5640_init_setting_30fps_VGA[] = {
 static const struct reg_value ov5640_setting_30fps_VGA_640_480[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -360,7 +363,7 @@ static const struct reg_value ov5640_setting_30fps_VGA_640_480[] = {
 static const struct reg_value ov5640_setting_15fps_VGA_640_480[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -379,7 +382,7 @@ static const struct reg_value ov5640_setting_15fps_VGA_640_480[] = {
 static const struct reg_value ov5640_setting_30fps_XGA_1024_768[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -399,7 +402,7 @@ static const struct reg_value ov5640_setting_30fps_XGA_1024_768[] = {
 static const struct reg_value ov5640_setting_15fps_XGA_1024_768[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -418,7 +421,7 @@ static const struct reg_value ov5640_setting_15fps_XGA_1024_768[] = {
 static const struct reg_value ov5640_setting_30fps_QVGA_320_240[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -437,7 +440,7 @@ static const struct reg_value ov5640_setting_30fps_QVGA_320_240[] = {
 static const struct reg_value ov5640_setting_15fps_QVGA_320_240[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -456,7 +459,7 @@ static const struct reg_value ov5640_setting_15fps_QVGA_320_240[] = {
 static const struct reg_value ov5640_setting_30fps_QCIF_176_144[] = {
 	{0x3035, 0x14, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -475,7 +478,7 @@ static const struct reg_value ov5640_setting_30fps_QCIF_176_144[] = {
 static const struct reg_value ov5640_setting_15fps_QCIF_176_144[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -494,7 +497,7 @@ static const struct reg_value ov5640_setting_15fps_QCIF_176_144[] = {
 static const struct reg_value ov5640_setting_30fps_NTSC_720_480[] = {
 	{0x3035, 0x12, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -513,7 +516,7 @@ static const struct reg_value ov5640_setting_30fps_NTSC_720_480[] = {
 static const struct reg_value ov5640_setting_15fps_NTSC_720_480[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -532,7 +535,7 @@ static const struct reg_value ov5640_setting_15fps_NTSC_720_480[] = {
 static const struct reg_value ov5640_setting_30fps_PAL_720_576[] = {
 	{0x3035, 0x12, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -551,7 +554,7 @@ static const struct reg_value ov5640_setting_30fps_PAL_720_576[] = {
 static const struct reg_value ov5640_setting_15fps_PAL_720_576[] = {
 	{0x3035, 0x22, 0, 0}, {0x3036, 0x38, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x04, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9b, 0, 0},
@@ -571,7 +574,7 @@ static const struct reg_value ov5640_setting_30fps_720P_1280_720[] = {
 	{0x3008, 0x42, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x07, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0xfa, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x06, 0, 0}, {0x3807, 0xa9, 0, 0},
@@ -591,7 +594,7 @@ static const struct reg_value ov5640_setting_30fps_720P_1280_720[] = {
 static const struct reg_value ov5640_setting_15fps_720P_1280_720[] = {
 	{0x3035, 0x41, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x07, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x41, 0, 0}, {0x3821, 0x07, 0, 0}, {0x3814, 0x31, 0, 0},
+	{0x3814, 0x31, 0, 0},
 	{0x3815, 0x31, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0xfa, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x06, 0, 0}, {0x3807, 0xa9, 0, 0},
@@ -611,7 +614,7 @@ static const struct reg_value ov5640_setting_30fps_1080P_1920_1080[] = {
 	{0x3008, 0x42, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0}, {0x3814, 0x11, 0, 0},
+	{0x3814, 0x11, 0, 0},
 	{0x3815, 0x11, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x00, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9f, 0, 0},
@@ -644,7 +647,7 @@ static const struct reg_value ov5640_setting_15fps_1080P_1920_1080[] = {
 	{0x3008, 0x42, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0}, {0x3814, 0x11, 0, 0},
+	{0x3814, 0x11, 0, 0},
 	{0x3815, 0x11, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x00, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9f, 0, 0},
@@ -673,10 +676,9 @@ static const struct reg_value ov5640_setting_15fps_1080P_1920_1080[] = {
 };
 
 static const struct reg_value ov5640_setting_15fps_QSXGA_2592_1944[] = {
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0},
 	{0x3035, 0x21, 0, 0}, {0x3036, 0x54, 0, 0}, {0x3c07, 0x08, 0, 0},
 	{0x3c09, 0x1c, 0, 0}, {0x3c0a, 0x9c, 0, 0}, {0x3c0b, 0x40, 0, 0},
-	{0x3820, 0x40, 0, 0}, {0x3821, 0x06, 0, 0}, {0x3814, 0x11, 0, 0},
+	{0x3814, 0x11, 0, 0},
 	{0x3815, 0x11, 0, 0}, {0x3800, 0x00, 0, 0}, {0x3801, 0x00, 0, 0},
 	{0x3802, 0x00, 0, 0}, {0x3803, 0x00, 0, 0}, {0x3804, 0x0a, 0, 0},
 	{0x3805, 0x3f, 0, 0}, {0x3806, 0x07, 0, 0}, {0x3807, 0x9f, 0, 0},
@@ -1340,6 +1342,27 @@ static int ov5640_binning_on(struct ov5640_dev *sensor)
 	return temp ? 1 : 0;
 }
 
+static int ov5640_set_binning(struct ov5640_dev *sensor, bool enable)
+{
+	int ret;
+
+	/*
+	 * TIMING TC REG21:
+	 * - [0]:	Horizontal binning enable
+	 */
+	ret = ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG21,
+			     BIT(0), enable ? BIT(0) : 0);
+	if (ret)
+		return ret;
+	/*
+	 * TIMING TC REG20:
+	 * - [0]:	Undocumented, but hardcoded init sequences
+	 *		are always setting REG21/REG20 bit 0 to same value...
+	 */
+	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG20,
+			      BIT(0), enable ? BIT(0) : 0);
+}
+
 static int ov5640_set_virtual_channel(struct ov5640_dev *sensor)
 {
 	struct i2c_client *client = sensor->i2c_client;
@@ -1640,6 +1663,9 @@ static int ov5640_set_mode(struct ov5640_dev *sensor,
 	if (ret < 0)
 		return ret;
 
+	ret = ov5640_set_binning(sensor, dn_mode != SCALING);
+	if (ret < 0)
+		return ret;
 	ret = ov5640_set_ae_target(sensor, sensor->ae_target);
 	if (ret < 0)
 		return ret;
@@ -2193,6 +2219,37 @@ static int ov5640_set_ctrl_light_freq(struct ov5640_dev *sensor, int value)
 			      BIT(2) : 0);
 }
 
+static int ov5640_set_ctrl_hflip(struct ov5640_dev *sensor, int value)
+{
+	/*
+	 * Sensor is a BSI (Back Side Illuminated) one,
+	 * so image captured is physically mirrored.
+	 * This is why mirror logic is inversed in
+	 * order to cancel this mirror effect.
+	 */
+
+	/*
+	 * TIMING TC REG21:
+	 * - [2]:	ISP mirror
+	 * - [1]:	Sensor mirror
+	 */
+	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG21,
+			      BIT(2) | BIT(1),
+			      (!value) ? (BIT(2) | BIT(1)) : 0);
+}
+
+static int ov5640_set_ctrl_vflip(struct ov5640_dev *sensor, int value)
+{
+	/*
+	 * TIMING TC REG20:
+	 * - [2]:	ISP vflip
+	 * - [1]:	Sensor vflip
+	 */
+	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG20,
+			      BIT(2) | BIT(1),
+			      value ? (BIT(2) | BIT(1)) : 0);
+}
+
 static int ov5640_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 {
 	struct v4l2_subdev *sd = ctrl_to_sd(ctrl);
@@ -2264,6 +2321,12 @@ static int ov5640_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_POWER_LINE_FREQUENCY:
 		ret = ov5640_set_ctrl_light_freq(sensor, ctrl->val);
 		break;
+	case V4L2_CID_HFLIP:
+		ret = ov5640_set_ctrl_hflip(sensor, ctrl->val);
+		break;
+	case V4L2_CID_VFLIP:
+		ret = ov5640_set_ctrl_vflip(sensor, ctrl->val);
+		break;
 	default:
 		ret = -EINVAL;
 		break;
@@ -2325,6 +2388,10 @@ static int ov5640_init_controls(struct ov5640_dev *sensor)
 		v4l2_ctrl_new_std_menu_items(hdl, ops, V4L2_CID_TEST_PATTERN,
 					     ARRAY_SIZE(test_pattern_menu) - 1,
 					     0, 0, test_pattern_menu);
+	ctrls->hflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_HFLIP,
+					 0, 1, 1, 0);
+	ctrls->vflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_VFLIP,
+					 0, 1, 1, 0);
 
 	ctrls->light_freq =
 		v4l2_ctrl_new_std_menu(hdl, ops,
-- 
cgit v1.2.3


From 7e5dd6fd1283bde6cea7e09db6e9635602b5fc21 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 18 Jun 2018 06:29:18 -0400
Subject: media: dt-bindings: ov5640: Add "rotation" property

Add the rotation property to the list of optional properties
for the OV5640 camera sensor.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/i2c/ov5640.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/i2c/ov5640.txt b/Documentation/devicetree/bindings/media/i2c/ov5640.txt
index 8e36da0d8406..c97c2f2da12d 100644
--- a/Documentation/devicetree/bindings/media/i2c/ov5640.txt
+++ b/Documentation/devicetree/bindings/media/i2c/ov5640.txt
@@ -13,6 +13,10 @@ Optional Properties:
 	       This is an active low signal to the OV5640.
 - powerdown-gpios: reference to the GPIO connected to the powerdown pin,
 		   if any. This is an active high signal to the OV5640.
+- rotation: as defined in
+	    Documentation/devicetree/bindings/media/video-interfaces.txt,
+	    valid values are 0 (sensor mounted upright) and 180 (sensor
+	    mounted upside down).
 
 The device node must contain one 'port' child node for its digital output
 video port, in accordance with the video interface bindings defined in
@@ -51,6 +55,7 @@ Examples:
 		DVDD-supply = <&vgen2_reg>;  /* 1.5v */
 		powerdown-gpios = <&gpio1 19 GPIO_ACTIVE_HIGH>;
 		reset-gpios = <&gpio1 20 GPIO_ACTIVE_LOW>;
+		rotation = <180>;
 
 		port {
 			/* MIPI CSI-2 bus endpoint */
-- 
cgit v1.2.3


From c3f3ba3e6f78ea2159fca284e18840c6b3c1bfb6 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Mon, 18 Jun 2018 06:29:19 -0400
Subject: media: ov5640: add support of module orientation

Add support of module being physically mounted upside down.
In this case, mirror and flip are enabled to fix captured images
orientation.

[Sakari Ailus: Use dev_fwnode() instead of accessing device's of_node]

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov5640.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 41039e535499..9e1078632375 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -215,6 +215,7 @@ struct ov5640_dev {
 	struct regulator_bulk_data supplies[OV5640_NUM_SUPPLIES];
 	struct gpio_desc *reset_gpio;
 	struct gpio_desc *pwdn_gpio;
+	bool   upside_down;
 
 	/* lock to protect all members below */
 	struct mutex lock;
@@ -2222,6 +2223,8 @@ static int ov5640_set_ctrl_light_freq(struct ov5640_dev *sensor, int value)
 static int ov5640_set_ctrl_hflip(struct ov5640_dev *sensor, int value)
 {
 	/*
+	 * If sensor is mounted upside down, mirror logic is inversed.
+	 *
 	 * Sensor is a BSI (Back Side Illuminated) one,
 	 * so image captured is physically mirrored.
 	 * This is why mirror logic is inversed in
@@ -2235,11 +2238,14 @@ static int ov5640_set_ctrl_hflip(struct ov5640_dev *sensor, int value)
 	 */
 	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG21,
 			      BIT(2) | BIT(1),
-			      (!value) ? (BIT(2) | BIT(1)) : 0);
+			      (!(value ^ sensor->upside_down)) ?
+			      (BIT(2) | BIT(1)) : 0);
 }
 
 static int ov5640_set_ctrl_vflip(struct ov5640_dev *sensor, int value)
 {
+	/* If sensor is mounted upside down, flip logic is inversed */
+
 	/*
 	 * TIMING TC REG20:
 	 * - [2]:	ISP vflip
@@ -2247,7 +2253,8 @@ static int ov5640_set_ctrl_vflip(struct ov5640_dev *sensor, int value)
 	 */
 	return ov5640_mod_reg(sensor, OV5640_REG_TIMING_TC_REG20,
 			      BIT(2) | BIT(1),
-			      value ? (BIT(2) | BIT(1)) : 0);
+			      (value ^ sensor->upside_down) ?
+			      (BIT(2) | BIT(1)) : 0);
 }
 
 static int ov5640_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
@@ -2625,6 +2632,7 @@ static int ov5640_probe(struct i2c_client *client,
 	struct fwnode_handle *endpoint;
 	struct ov5640_dev *sensor;
 	struct v4l2_mbus_framefmt *fmt;
+	u32 rotation;
 	int ret;
 
 	sensor = devm_kzalloc(dev, sizeof(*sensor), GFP_KERNEL);
@@ -2650,6 +2658,22 @@ static int ov5640_probe(struct i2c_client *client,
 
 	sensor->ae_target = 52;
 
+	/* optional indication of physical rotation of sensor */
+	ret = fwnode_property_read_u32(dev_fwnode(&client->dev), "rotation",
+				       &rotation);
+	if (!ret) {
+		switch (rotation) {
+		case 180:
+			sensor->upside_down = true;
+			/* fall through */
+		case 0:
+			break;
+		default:
+			dev_warn(dev, "%u degrees rotation is not supported, ignoring...\n",
+				 rotation);
+		}
+	}
+
 	endpoint = fwnode_graph_get_next_endpoint(dev_fwnode(&client->dev),
 						  NULL);
 	if (!endpoint) {
-- 
cgit v1.2.3


From 0b964d183cbf3f95a062ad9f3eec87ffa2790558 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:18 -0400
Subject: media: ov772x: allow i2c controllers without
 I2C_FUNC_PROTOCOL_MANGLING

The ov772x driver only works when the i2c controller have
I2C_FUNC_PROTOCOL_MANGLING.  However, many i2c controller drivers don't
support it.

The reason that the ov772x requires I2C_FUNC_PROTOCOL_MANGLING is that
it doesn't support repeated starts.

This changes the reading ov772x register method so that it doesn't
require I2C_FUNC_PROTOCOL_MANGLING by calling two separated i2c messages.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Wolfram Sang <wsa@the-dreams.de>
Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index e2550708abc8..b6223bfc022b 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -542,9 +542,19 @@ static struct ov772x_priv *to_ov772x(struct v4l2_subdev *sd)
 	return container_of(sd, struct ov772x_priv, subdev);
 }
 
-static inline int ov772x_read(struct i2c_client *client, u8 addr)
+static int ov772x_read(struct i2c_client *client, u8 addr)
 {
-	return i2c_smbus_read_byte_data(client, addr);
+	int ret;
+	u8 val;
+
+	ret = i2c_master_send(client, &addr, 1);
+	if (ret < 0)
+		return ret;
+	ret = i2c_master_recv(client, &val, 1);
+	if (ret < 0)
+		return ret;
+
+	return val;
 }
 
 static inline int ov772x_write(struct i2c_client *client, u8 addr, u8 value)
@@ -1255,13 +1265,11 @@ static int ov772x_probe(struct i2c_client *client,
 		return -EINVAL;
 	}
 
-	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA |
-					      I2C_FUNC_PROTOCOL_MANGLING)) {
+	if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA)) {
 		dev_err(&adapter->dev,
-			"I2C-Adapter doesn't support SMBUS_BYTE_DATA or PROTOCOL_MANGLING\n");
+			"I2C-Adapter doesn't support SMBUS_BYTE_DATA\n");
 		return -EIO;
 	}
-	client->flags |= I2C_CLIENT_SCCB;
 
 	priv = devm_kzalloc(&client->dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
-- 
cgit v1.2.3


From 30f3b17eaf4913e9e56be15915ce57aae69db701 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:19 -0400
Subject: media: ov772x: add checks for register read errors

This change adds checks for register read errors and returns correct
error code.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jacopo Mondi <jacopo@jmondi.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index b6223bfc022b..3fdbe644648a 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -1146,7 +1146,7 @@ static int ov772x_set_fmt(struct v4l2_subdev *sd,
 static int ov772x_video_probe(struct ov772x_priv *priv)
 {
 	struct i2c_client  *client = v4l2_get_subdevdata(&priv->subdev);
-	u8                  pid, ver;
+	int		    pid, ver, midh, midl;
 	const char         *devname;
 	int		    ret;
 
@@ -1156,7 +1156,11 @@ static int ov772x_video_probe(struct ov772x_priv *priv)
 
 	/* Check and show product ID and manufacturer ID. */
 	pid = ov772x_read(client, PID);
+	if (pid < 0)
+		return pid;
 	ver = ov772x_read(client, VER);
+	if (ver < 0)
+		return ver;
 
 	switch (VERSION(pid, ver)) {
 	case OV7720:
@@ -1172,13 +1176,17 @@ static int ov772x_video_probe(struct ov772x_priv *priv)
 		goto done;
 	}
 
+	midh = ov772x_read(client, MIDH);
+	if (midh < 0)
+		return midh;
+	midl = ov772x_read(client, MIDL);
+	if (midl < 0)
+		return midl;
+
 	dev_info(&client->dev,
 		 "%s Product ID %0x:%0x Manufacturer ID %x:%x\n",
-		 devname,
-		 pid,
-		 ver,
-		 ov772x_read(client, MIDH),
-		 ov772x_read(client, MIDL));
+		 devname, pid, ver, midh, midl);
+
 	ret = v4l2_ctrl_handler_setup(&priv->hdl);
 
 done:
-- 
cgit v1.2.3


From 4b610d6d03eed17a035eba49826d1f47baf83396 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:20 -0400
Subject: media: ov772x: add media controller support

Create a source pad and set the media controller type to the sensor.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jacopo Mondi <jacopo@jmondi.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index 3fdbe644648a..bb5327f4cb48 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -424,6 +424,9 @@ struct ov772x_priv {
 	/* band_filter = COM8[5] ? 256 - BDBASE : 0 */
 	unsigned short                    band_filter;
 	unsigned int			  fps;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_pad pad;
+#endif
 };
 
 /*
@@ -1316,16 +1319,26 @@ static int ov772x_probe(struct i2c_client *client,
 	if (ret < 0)
 		goto error_gpio_put;
 
+#ifdef CONFIG_MEDIA_CONTROLLER
+	priv->pad.flags = MEDIA_PAD_FL_SOURCE;
+	priv->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+	ret = media_entity_pads_init(&priv->subdev.entity, 1, &priv->pad);
+	if (ret < 0)
+		goto error_gpio_put;
+#endif
+
 	priv->cfmt = &ov772x_cfmts[0];
 	priv->win = &ov772x_win_sizes[0];
 	priv->fps = 15;
 
 	ret = v4l2_async_register_subdev(&priv->subdev);
 	if (ret)
-		goto error_gpio_put;
+		goto error_entity_cleanup;
 
 	return 0;
 
+error_entity_cleanup:
+	media_entity_cleanup(&priv->subdev.entity);
 error_gpio_put:
 	if (priv->pwdn_gpio)
 		gpiod_put(priv->pwdn_gpio);
@@ -1341,6 +1354,7 @@ static int ov772x_remove(struct i2c_client *client)
 {
 	struct ov772x_priv *priv = to_ov772x(i2c_get_clientdata(client));
 
+	media_entity_cleanup(&priv->subdev.entity);
 	clk_put(priv->clk);
 	if (priv->pwdn_gpio)
 		gpiod_put(priv->pwdn_gpio);
-- 
cgit v1.2.3


From 40519d545824355fff7b94cf6e58efffe2908e7d Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:21 -0400
Subject: media: ov772x: use generic names for reset and powerdown gpios

The ov772x driver uses "rstb-gpios" and "pwdn-gpios" for reset and
powerdown pins.  However, using generic names for these gpios is
preferred.  ("reset-gpios" and "powerdown-gpios" respectively)

There is only one mainline user for these gpios, so rename to generic
names.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jacopo Mondi <jacopo@jmondi.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 arch/sh/boards/mach-migor/setup.c | 5 +++--
 drivers/media/i2c/ov772x.c        | 8 ++++----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 3d7d0046cf49..3849b89c8f80 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -351,8 +351,9 @@ static struct platform_device migor_ceu_device = {
 static struct gpiod_lookup_table ov7725_gpios = {
 	.dev_id		= "0-0021",
 	.table		= {
-		GPIO_LOOKUP("sh7722_pfc", GPIO_PTT0, "pwdn", GPIO_ACTIVE_HIGH),
-		GPIO_LOOKUP("sh7722_pfc", GPIO_PTT3, "rstb", GPIO_ACTIVE_LOW),
+		GPIO_LOOKUP("sh7722_pfc", GPIO_PTT0, "powerdown",
+			    GPIO_ACTIVE_HIGH),
+		GPIO_LOOKUP("sh7722_pfc", GPIO_PTT3, "reset", GPIO_ACTIVE_LOW),
 	},
 };
 
diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index bb5327f4cb48..97a65ce53efa 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -837,10 +837,10 @@ static int ov772x_power_on(struct ov772x_priv *priv)
 	 * available to handle this cleanly, request the GPIO temporarily
 	 * to avoid conflicts.
 	 */
-	priv->rstb_gpio = gpiod_get_optional(&client->dev, "rstb",
+	priv->rstb_gpio = gpiod_get_optional(&client->dev, "reset",
 					     GPIOD_OUT_LOW);
 	if (IS_ERR(priv->rstb_gpio)) {
-		dev_info(&client->dev, "Unable to get GPIO \"rstb\"");
+		dev_info(&client->dev, "Unable to get GPIO \"reset\"");
 		return PTR_ERR(priv->rstb_gpio);
 	}
 
@@ -1307,10 +1307,10 @@ static int ov772x_probe(struct i2c_client *client,
 		goto error_ctrl_free;
 	}
 
-	priv->pwdn_gpio = gpiod_get_optional(&client->dev, "pwdn",
+	priv->pwdn_gpio = gpiod_get_optional(&client->dev, "powerdown",
 					     GPIOD_OUT_LOW);
 	if (IS_ERR(priv->pwdn_gpio)) {
-		dev_info(&client->dev, "Unable to get GPIO \"pwdn\"");
+		dev_info(&client->dev, "Unable to get GPIO \"powerdown\"");
 		ret = PTR_ERR(priv->pwdn_gpio);
 		goto error_clk_put;
 	}
-- 
cgit v1.2.3


From 89ce93fd5b75d515ca4f9df15ef1507bff47b203 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:22 -0400
Subject: media: ov772x: omit consumer ID when getting clock reference

Currently the ov772x driver obtains a clock with a specific consumer ID.
As there's a single clock for this driver, we could omit clock-names
property in device tree by passing NULL as a consumer ID to clk_get().

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Suggested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Tested-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 arch/sh/boards/mach-migor/setup.c | 2 +-
 drivers/media/i2c/ov772x.c        | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 3849b89c8f80..26543cc30d26 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -593,7 +593,7 @@ static int __init migor_devices_setup(void)
 	}
 
 	/* Add a clock alias for ov7725 xclk source. */
-	clk_add_alias("xclk", "0-0021", "video_clk", NULL);
+	clk_add_alias(NULL, "0-0021", "video_clk", NULL);
 
 	/* Register GPIOs for video sources. */
 	gpiod_add_lookup_table(&ov7725_gpios);
diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index 97a65ce53efa..f939e28ecaaf 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -1300,7 +1300,7 @@ static int ov772x_probe(struct i2c_client *client,
 	if (priv->hdl.error)
 		return priv->hdl.error;
 
-	priv->clk = clk_get(&client->dev, "xclk");
+	priv->clk = clk_get(&client->dev, NULL);
 	if (IS_ERR(priv->clk)) {
 		dev_err(&client->dev, "Unable to get xclk clock\n");
 		ret = PTR_ERR(priv->clk);
-- 
cgit v1.2.3


From c2cae8951772aff8355171882fcc8e4eb9f53840 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:23 -0400
Subject: media: ov772x: support device tree probing

The ov772x driver currently only supports legacy platform data probe.
This change enables device tree probing.

Note that the platform data probe can select auto or manual edge control
mode, but the device tree probling can only select auto edge control mode
for now.

[Sakari Ailus: Remove direct OF dependencies from device ID table]

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jacopo Mondi <jacopo@jmondi.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 62 ++++++++++++++++++++++++++++++++--------------
 1 file changed, 43 insertions(+), 19 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index f939e28ecaaf..b5ae88e69b94 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -749,13 +749,13 @@ static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_VFLIP:
 		val = ctrl->val ? VFLIP_IMG : 0x00;
 		priv->flag_vflip = ctrl->val;
-		if (priv->info->flags & OV772X_FLAG_VFLIP)
+		if (priv->info && (priv->info->flags & OV772X_FLAG_VFLIP))
 			val ^= VFLIP_IMG;
 		return ov772x_mask_set(client, COM3, VFLIP_IMG, val);
 	case V4L2_CID_HFLIP:
 		val = ctrl->val ? HFLIP_IMG : 0x00;
 		priv->flag_hflip = ctrl->val;
-		if (priv->info->flags & OV772X_FLAG_HFLIP)
+		if (priv->info && (priv->info->flags & OV772X_FLAG_HFLIP))
 			val ^= HFLIP_IMG;
 		return ov772x_mask_set(client, COM3, HFLIP_IMG, val);
 	case V4L2_CID_BAND_STOP_FILTER:
@@ -914,19 +914,14 @@ static void ov772x_select_params(const struct v4l2_mbus_framefmt *mf,
 	*win = ov772x_select_win(mf->width, mf->height);
 }
 
-static int ov772x_set_params(struct ov772x_priv *priv,
-			     const struct ov772x_color_format *cfmt,
-			     const struct ov772x_win_size *win)
+static int ov772x_edgectrl(struct ov772x_priv *priv)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
-	struct v4l2_fract tpf;
 	int ret;
-	u8  val;
 
-	/* Reset hardware. */
-	ov772x_reset(client);
+	if (!priv->info)
+		return 0;
 
-	/* Edge Ctrl. */
 	if (priv->info->edgectrl.strength & OV772X_MANUAL_EDGE_CTRL) {
 		/*
 		 * Manual Edge Control Mode.
@@ -937,19 +932,19 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 
 		ret = ov772x_mask_set(client, DSPAUTO, EDGE_ACTRL, 0x00);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 		ret = ov772x_mask_set(client,
 				      EDGE_TRSHLD, OV772X_EDGE_THRESHOLD_MASK,
 				      priv->info->edgectrl.threshold);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 		ret = ov772x_mask_set(client,
 				      EDGE_STRNGT, OV772X_EDGE_STRENGTH_MASK,
 				      priv->info->edgectrl.strength);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 	} else if (priv->info->edgectrl.upper > priv->info->edgectrl.lower) {
 		/*
@@ -961,15 +956,35 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 				      EDGE_UPPER, OV772X_EDGE_UPPER_MASK,
 				      priv->info->edgectrl.upper);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 
 		ret = ov772x_mask_set(client,
 				      EDGE_LOWER, OV772X_EDGE_LOWER_MASK,
 				      priv->info->edgectrl.lower);
 		if (ret < 0)
-			goto ov772x_set_fmt_error;
+			return ret;
 	}
 
+	return 0;
+}
+
+static int ov772x_set_params(struct ov772x_priv *priv,
+			     const struct ov772x_color_format *cfmt,
+			     const struct ov772x_win_size *win)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
+	struct v4l2_fract tpf;
+	int ret;
+	u8  val;
+
+	/* Reset hardware. */
+	ov772x_reset(client);
+
+	/* Edge Ctrl. */
+	ret = ov772x_edgectrl(priv);
+	if (ret < 0)
+		return ret;
+
 	/* Format and window size. */
 	ret = ov772x_write(client, HSTART, win->rect.left >> 2);
 	if (ret < 0)
@@ -1020,9 +1035,9 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 
 	/* Set COM3. */
 	val = cfmt->com3;
-	if (priv->info->flags & OV772X_FLAG_VFLIP)
+	if (priv->info && (priv->info->flags & OV772X_FLAG_VFLIP))
 		val |= VFLIP_IMG;
-	if (priv->info->flags & OV772X_FLAG_HFLIP)
+	if (priv->info && (priv->info->flags & OV772X_FLAG_HFLIP))
 		val |= HFLIP_IMG;
 	if (priv->flag_vflip)
 		val ^= VFLIP_IMG;
@@ -1271,8 +1286,9 @@ static int ov772x_probe(struct i2c_client *client,
 	struct i2c_adapter	*adapter = client->adapter;
 	int			ret;
 
-	if (!client->dev.platform_data) {
-		dev_err(&client->dev, "Missing ov772x platform data\n");
+	if (!client->dev.of_node && !client->dev.platform_data) {
+		dev_err(&client->dev,
+			"Missing ov772x platform data for non-DT device\n");
 		return -EINVAL;
 	}
 
@@ -1370,9 +1386,17 @@ static const struct i2c_device_id ov772x_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, ov772x_id);
 
+static const struct of_device_id ov772x_of_match[] = {
+	{ .compatible = "ovti,ov7725", },
+	{ .compatible = "ovti,ov7720", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ov772x_of_match);
+
 static struct i2c_driver ov772x_i2c_driver = {
 	.driver = {
 		.name = "ov772x",
+		.of_match_table = ov772x_of_match,
 	},
 	.probe    = ov772x_probe,
 	.remove   = ov772x_remove,
-- 
cgit v1.2.3


From 0a9fe5c375b57fab6d18ed0a6a7f935eefb09db3 Mon Sep 17 00:00:00 2001
From: Yousuk Seung <ysseung@google.com>
Date: Wed, 27 Jun 2018 10:32:19 -0700
Subject: netem: slotting with non-uniform distribution

Extend slotting with support for non-uniform distributions. This is
similar to netem's non-uniform distribution delay feature.

Commit f043efeae2f1 ("netem: support delivering packets in delayed
time slots") added the slotting feature to approximate the behaviors
of media with packet aggregation but only supported a uniform
distribution for delays between transmission attempts. Tests with TCP
BBR with emulated wifi links with non-uniform distributions produced
more useful results.

Syntax:
   slot dist DISTRIBUTION DELAY JITTER [packets MAX_PACKETS] \
      [bytes MAX_BYTES]

The syntax and use of the distribution table is the same as in the
non-uniform distribution delay feature. A file DISTRIBUTION must be
present in TC_LIB_DIR (e.g. /usr/lib/tc) containing numbers scaled by
NETEM_DIST_SCALE. A random value x is selected from the table and it
takes DELAY + ( x * JITTER ) as delay. Correlation between values is not
supported.

Examples:
  Normal distribution delay with mean = 800us and stdev = 100us.
  > tc qdisc add dev eth0 root netem slot dist normal 800us 100us

  Optionally set the max slot size in bytes and/or packets.
  > tc qdisc add dev eth0 root netem slot dist normal 800us 100us \
    bytes 64k packets 42

Signed-off-by: Yousuk Seung <ysseung@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  3 ++
 net/sched/sch_netem.c          | 73 ++++++++++++++++++++++++++++--------------
 2 files changed, 52 insertions(+), 24 deletions(-)

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 37b5096ae97b..bad3c03bcf43 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -539,6 +539,7 @@ enum {
 	TCA_NETEM_LATENCY64,
 	TCA_NETEM_JITTER64,
 	TCA_NETEM_SLOT,
+	TCA_NETEM_SLOT_DIST,
 	__TCA_NETEM_MAX,
 };
 
@@ -581,6 +582,8 @@ struct tc_netem_slot {
 	__s64   max_delay;
 	__s32   max_packets;
 	__s32   max_bytes;
+	__s64	dist_delay; /* nsec */
+	__s64	dist_jitter; /* nsec */
 };
 
 enum {
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 7d6801fc5340..ad18a2052416 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -68,6 +68,11 @@
 		 Fabio Ludovici <fabio.ludovici at yahoo.it>
 */
 
+struct disttable {
+	u32  size;
+	s16 table[0];
+};
+
 struct netem_sched_data {
 	/* internal t(ime)fifo qdisc uses t_root and sch->limit */
 	struct rb_root t_root;
@@ -99,10 +104,7 @@ struct netem_sched_data {
 		u32 rho;
 	} delay_cor, loss_cor, dup_cor, reorder_cor, corrupt_cor;
 
-	struct disttable {
-		u32  size;
-		s16 table[0];
-	} *delay_dist;
+	struct disttable *delay_dist;
 
 	enum  {
 		CLG_RANDOM,
@@ -142,6 +144,7 @@ struct netem_sched_data {
 		s32 bytes_left;
 	} slot;
 
+	struct disttable *slot_dist;
 };
 
 /* Time stamp put into socket buffer control block
@@ -180,7 +183,7 @@ static u32 get_crandom(struct crndstate *state)
 	u64 value, rho;
 	unsigned long answer;
 
-	if (state->rho == 0)	/* no correlation */
+	if (!state || state->rho == 0)	/* no correlation */
 		return prandom_u32();
 
 	value = prandom_u32();
@@ -601,10 +604,19 @@ finish_segs:
 
 static void get_slot_next(struct netem_sched_data *q, u64 now)
 {
-	q->slot.slot_next = now + q->slot_config.min_delay +
-		(prandom_u32() *
-			(q->slot_config.max_delay -
-				q->slot_config.min_delay) >> 32);
+	s64 next_delay;
+
+	if (!q->slot_dist)
+		next_delay = q->slot_config.min_delay +
+				(prandom_u32() *
+				 (q->slot_config.max_delay -
+				  q->slot_config.min_delay) >> 32);
+	else
+		next_delay = tabledist(q->slot_config.dist_delay,
+				       (s32)(q->slot_config.dist_jitter),
+				       NULL, q->slot_dist);
+
+	q->slot.slot_next = now + next_delay;
 	q->slot.packets_left = q->slot_config.max_packets;
 	q->slot.bytes_left = q->slot_config.max_bytes;
 }
@@ -721,9 +733,9 @@ static void dist_free(struct disttable *d)
  * signed 16 bit values.
  */
 
-static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
+static int get_dist_table(struct Qdisc *sch, struct disttable **tbl,
+			  const struct nlattr *attr)
 {
-	struct netem_sched_data *q = qdisc_priv(sch);
 	size_t n = nla_len(attr)/sizeof(__s16);
 	const __s16 *data = nla_data(attr);
 	spinlock_t *root_lock;
@@ -744,7 +756,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr)
 	root_lock = qdisc_root_sleeping_lock(sch);
 
 	spin_lock_bh(root_lock);
-	swap(q->delay_dist, d);
+	swap(*tbl, d);
 	spin_unlock_bh(root_lock);
 
 	dist_free(d);
@@ -762,7 +774,8 @@ static void get_slot(struct netem_sched_data *q, const struct nlattr *attr)
 		q->slot_config.max_bytes = INT_MAX;
 	q->slot.packets_left = q->slot_config.max_packets;
 	q->slot.bytes_left = q->slot_config.max_bytes;
-	if (q->slot_config.min_delay | q->slot_config.max_delay)
+	if (q->slot_config.min_delay | q->slot_config.max_delay |
+	    q->slot_config.dist_jitter)
 		q->slot.slot_next = ktime_get_ns();
 	else
 		q->slot.slot_next = 0;
@@ -926,16 +939,17 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	if (tb[TCA_NETEM_DELAY_DIST]) {
-		ret = get_dist_table(sch, tb[TCA_NETEM_DELAY_DIST]);
-		if (ret) {
-			/* recover clg and loss_model, in case of
-			 * q->clg and q->loss_model were modified
-			 * in get_loss_clg()
-			 */
-			q->clg = old_clg;
-			q->loss_model = old_loss_model;
-			return ret;
-		}
+		ret = get_dist_table(sch, &q->delay_dist,
+				     tb[TCA_NETEM_DELAY_DIST]);
+		if (ret)
+			goto get_table_failure;
+	}
+
+	if (tb[TCA_NETEM_SLOT_DIST]) {
+		ret = get_dist_table(sch, &q->slot_dist,
+				     tb[TCA_NETEM_SLOT_DIST]);
+		if (ret)
+			goto get_table_failure;
 	}
 
 	sch->limit = qopt->limit;
@@ -983,6 +997,15 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt,
 		get_slot(q, tb[TCA_NETEM_SLOT]);
 
 	return ret;
+
+get_table_failure:
+	/* recover clg and loss_model, in case of
+	 * q->clg and q->loss_model were modified
+	 * in get_loss_clg()
+	 */
+	q->clg = old_clg;
+	q->loss_model = old_loss_model;
+	return ret;
 }
 
 static int netem_init(struct Qdisc *sch, struct nlattr *opt,
@@ -1011,6 +1034,7 @@ static void netem_destroy(struct Qdisc *sch)
 	if (q->qdisc)
 		qdisc_destroy(q->qdisc);
 	dist_free(q->delay_dist);
+	dist_free(q->slot_dist);
 }
 
 static int dump_loss_model(const struct netem_sched_data *q,
@@ -1127,7 +1151,8 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (dump_loss_model(q, skb) != 0)
 		goto nla_put_failure;
 
-	if (q->slot_config.min_delay | q->slot_config.max_delay) {
+	if (q->slot_config.min_delay | q->slot_config.max_delay |
+	    q->slot_config.dist_jitter) {
 		slot = q->slot_config;
 		if (slot.max_packets == INT_MAX)
 			slot.max_packets = 0;
-- 
cgit v1.2.3


From 34af7d920b766ffa582231ff3ce526d0c6179cd0 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:24 -0400
Subject: media: ov772x: handle nested s_power() calls

Depending on the v4l2 driver, calling s_power() could be nested.  So the
actual transitions between power saving mode and normal operation mode
should only happen at the first power on and the last power off.

This adds an s_power() nesting counter and updates the power state if the
counter is modified from 0 to != 0 or from != 0 to 0.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Jacopo Mondi <jacopo@jmondi.org>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index b5ae88e69b94..4a30a4338445 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -424,6 +424,9 @@ struct ov772x_priv {
 	/* band_filter = COM8[5] ? 256 - BDBASE : 0 */
 	unsigned short                    band_filter;
 	unsigned int			  fps;
+	/* lock to protect power_count */
+	struct mutex			  lock;
+	int				  power_count;
 #ifdef CONFIG_MEDIA_CONTROLLER
 	struct media_pad pad;
 #endif
@@ -871,9 +874,26 @@ static int ov772x_power_off(struct ov772x_priv *priv)
 static int ov772x_s_power(struct v4l2_subdev *sd, int on)
 {
 	struct ov772x_priv *priv = to_ov772x(sd);
+	int ret = 0;
+
+	mutex_lock(&priv->lock);
+
+	/* If the power count is modified from 0 to != 0 or from != 0 to 0,
+	 * update the power state.
+	 */
+	if (priv->power_count == !on)
+		ret = on ? ov772x_power_on(priv) : ov772x_power_off(priv);
+
+	if (!ret) {
+		/* Update the power count. */
+		priv->power_count += on ? 1 : -1;
+		WARN(priv->power_count < 0, "Unbalanced power count\n");
+		WARN(priv->power_count > 1, "Duplicated s_power call\n");
+	}
+
+	mutex_unlock(&priv->lock);
 
-	return on ? ov772x_power_on(priv) :
-		    ov772x_power_off(priv);
+	return ret;
 }
 
 static const struct ov772x_win_size *ov772x_select_win(u32 width, u32 height)
@@ -1303,6 +1323,7 @@ static int ov772x_probe(struct i2c_client *client,
 		return -ENOMEM;
 
 	priv->info = client->dev.platform_data;
+	mutex_init(&priv->lock);
 
 	v4l2_i2c_subdev_init(&priv->subdev, client, &ov772x_subdev_ops);
 	v4l2_ctrl_handler_init(&priv->hdl, 3);
@@ -1313,8 +1334,10 @@ static int ov772x_probe(struct i2c_client *client,
 	v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
 			  V4L2_CID_BAND_STOP_FILTER, 0, 256, 1, 0);
 	priv->subdev.ctrl_handler = &priv->hdl;
-	if (priv->hdl.error)
-		return priv->hdl.error;
+	if (priv->hdl.error) {
+		ret = priv->hdl.error;
+		goto error_mutex_destroy;
+	}
 
 	priv->clk = clk_get(&client->dev, NULL);
 	if (IS_ERR(priv->clk)) {
@@ -1362,6 +1385,8 @@ error_clk_put:
 	clk_put(priv->clk);
 error_ctrl_free:
 	v4l2_ctrl_handler_free(&priv->hdl);
+error_mutex_destroy:
+	mutex_destroy(&priv->lock);
 
 	return ret;
 }
@@ -1376,6 +1401,7 @@ static int ov772x_remove(struct i2c_client *client)
 		gpiod_put(priv->pwdn_gpio);
 	v4l2_async_unregister_subdev(&priv->subdev);
 	v4l2_ctrl_handler_free(&priv->hdl);
+	mutex_destroy(&priv->lock);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 80f0f574cc615b2c61bdfb0e3c2449478d63c488 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 27 Jun 2018 13:33:30 -0400
Subject: net sched actions: fix coding style in pedit action

Fix coding style issues in tc pedit action detected by the
checkpatch script.

Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 8a925c72db5f..e4b29ee79ba8 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -136,15 +136,15 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 	struct nlattr *tb[TCA_PEDIT_MAX + 1];
-	struct nlattr *pattr;
-	struct tc_pedit *parm;
-	int ret = 0, err;
-	struct tcf_pedit *p;
 	struct tc_pedit_key *keys = NULL;
 	struct tcf_pedit_key_ex *keys_ex;
+	struct tc_pedit *parm;
+	struct nlattr *pattr;
+	struct tcf_pedit *p;
+	int ret = 0, err;
 	int ksize;
 
-	if (nla == NULL)
+	if (!nla)
 		return -EINVAL;
 
 	err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy, NULL);
@@ -175,7 +175,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			return ret;
 		p = to_pedit(*a);
 		keys = kmalloc(ksize, GFP_KERNEL);
-		if (keys == NULL) {
+		if (!keys) {
 			tcf_idr_release(*a, bind);
 			kfree(keys_ex);
 			return -ENOMEM;
@@ -220,6 +220,7 @@ static void tcf_pedit_cleanup(struct tc_action *a)
 {
 	struct tcf_pedit *p = to_pedit(a);
 	struct tc_pedit_key *keys = p->tcfp_keys;
+
 	kfree(keys);
 	kfree(p->tcfp_keys_ex);
 }
@@ -284,7 +285,8 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 	if (p->tcfp_nkeys > 0) {
 		struct tc_pedit_key *tkey = p->tcfp_keys;
 		struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex;
-		enum pedit_header_type htype = TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
+		enum pedit_header_type htype =
+			TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
 		enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET;
 
 		for (i = p->tcfp_nkeys; i > 0; i--, tkey++) {
@@ -316,16 +318,15 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 						hoffset + tkey->at);
 					goto bad;
 				}
-				d = skb_header_pointer(skb, hoffset + tkey->at, 1,
-						       &_d);
+				d = skb_header_pointer(skb, hoffset + tkey->at,
+						       1, &_d);
 				if (!d)
 					goto bad;
 				offset += (*d & tkey->offmask) >> tkey->shift;
 			}
 
 			if (offset % 4) {
-				pr_info("tc filter pedit"
-					" offset must be on 32 bit boundaries\n");
+				pr_info("tc filter pedit offset must be on 32 bit boundaries\n");
 				goto bad;
 			}
 
@@ -335,7 +336,8 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 				goto bad;
 			}
 
-			ptr = skb_header_pointer(skb, hoffset + offset, 4, &_data);
+			ptr = skb_header_pointer(skb, hoffset + offset,
+						 4, &_data);
 			if (!ptr)
 				goto bad;
 			/* just do it, baby */
@@ -358,8 +360,9 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 		}
 
 		goto done;
-	} else
+	} else {
 		WARN(1, "pedit BUG: index %d\n", p->tcf_index);
+	}
 
 bad:
 	p->tcf_qstats.overlimits++;
-- 
cgit v1.2.3


From d020d4559de9baf47cafa2669f29ea59d11a914c Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 27 Jun 2018 13:33:31 -0400
Subject: net sched actions: fix coding style in pedit headers

Fix coding style issues in tc pedit headers detected by the
checkpatch script.

Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_pedit.h        | 1 +
 include/uapi/linux/tc_act/tc_pedit.h | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/net/tc_act/tc_pedit.h b/include/net/tc_act/tc_pedit.h
index 227a6f1d02f4..fac3ad4a86de 100644
--- a/include/net/tc_act/tc_pedit.h
+++ b/include/net/tc_act/tc_pedit.h
@@ -17,6 +17,7 @@ struct tcf_pedit {
 	struct tc_pedit_key	*tcfp_keys;
 	struct tcf_pedit_key_ex	*tcfp_keys_ex;
 };
+
 #define to_pedit(a) ((struct tcf_pedit *)a)
 
 static inline bool is_tcf_pedit(const struct tc_action *a)
diff --git a/include/uapi/linux/tc_act/tc_pedit.h b/include/uapi/linux/tc_act/tc_pedit.h
index 162d1094c41c..24ec792dacc1 100644
--- a/include/uapi/linux/tc_act/tc_pedit.h
+++ b/include/uapi/linux/tc_act/tc_pedit.h
@@ -17,13 +17,15 @@ enum {
 	TCA_PEDIT_KEY_EX,
 	__TCA_PEDIT_MAX
 };
+
 #define TCA_PEDIT_MAX (__TCA_PEDIT_MAX - 1)
-                                                                                
+
 enum {
 	TCA_PEDIT_KEY_EX_HTYPE = 1,
 	TCA_PEDIT_KEY_EX_CMD = 2,
 	__TCA_PEDIT_KEY_EX_MAX
 };
+
 #define TCA_PEDIT_KEY_EX_MAX (__TCA_PEDIT_KEY_EX_MAX - 1)
 
  /* TCA_PEDIT_KEY_EX_HDR_TYPE_NETWROK is a special case for legacy users. It
@@ -38,6 +40,7 @@ enum pedit_header_type {
 	TCA_PEDIT_KEY_EX_HDR_TYPE_UDP = 5,
 	__PEDIT_HDR_TYPE_MAX,
 };
+
 #define TCA_PEDIT_HDR_TYPE_MAX (__PEDIT_HDR_TYPE_MAX - 1)
 
 enum pedit_cmd {
@@ -45,6 +48,7 @@ enum pedit_cmd {
 	TCA_PEDIT_KEY_EX_CMD_ADD = 1,
 	__PEDIT_CMD_MAX,
 };
+
 #define TCA_PEDIT_CMD_MAX (__PEDIT_CMD_MAX - 1)
 
 struct tc_pedit_key {
@@ -55,13 +59,14 @@ struct tc_pedit_key {
 	__u32           offmask;
 	__u32           shift;
 };
-                                                                                
+
 struct tc_pedit_sel {
 	tc_gen;
 	unsigned char           nkeys;
 	unsigned char           flags;
 	struct tc_pedit_key     keys[0];
 };
+
 #define tc_pedit tc_pedit_sel
 
 #endif
-- 
cgit v1.2.3


From 544377cd2545f33cc6cd5458301749d828adacb0 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 27 Jun 2018 13:33:32 -0400
Subject: net sched actions: fix sparse warning

The variable _data in include/asm-generic/sections.h defines sections,
this causes sparse warning in pedit:

net/sched/act_pedit.c:293:35: warning: symbol '_data' shadows an earlier one
./include/asm-generic/sections.h:36:13: originally declared here

Therefore rename the variable.

Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index e4b29ee79ba8..9c2d8a31a5c5 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -290,7 +290,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 		enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET;
 
 		for (i = p->tcfp_nkeys; i > 0; i--, tkey++) {
-			u32 *ptr, _data;
+			u32 *ptr, hdata;
 			int offset = tkey->off;
 			int hoffset;
 			u32 val;
@@ -337,7 +337,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			}
 
 			ptr = skb_header_pointer(skb, hoffset + offset,
-						 4, &_data);
+						 4, &hdata);
 			if (!ptr)
 				goto bad;
 			/* just do it, baby */
@@ -355,7 +355,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			}
 
 			*ptr = ((*ptr & tkey->mask) ^ val);
-			if (ptr == &_data)
+			if (ptr == &hdata)
 				skb_store_bits(skb, hoffset + offset, ptr, 4);
 		}
 
-- 
cgit v1.2.3


From 6ff7586e382cb4274adefd56501d428ea39a5af3 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 27 Jun 2018 13:33:33 -0400
Subject: net sched actions: use sizeof operator for buffer length

Replace constant integer with sizeof() to clearly indicate
the destination buffer length in skb_header_pointer() calls.

Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 9c2d8a31a5c5..3b775f54cee5 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -319,7 +319,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 					goto bad;
 				}
 				d = skb_header_pointer(skb, hoffset + tkey->at,
-						       1, &_d);
+						       sizeof(_d), &_d);
 				if (!d)
 					goto bad;
 				offset += (*d & tkey->offmask) >> tkey->shift;
@@ -337,7 +337,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			}
 
 			ptr = skb_header_pointer(skb, hoffset + offset,
-						 4, &hdata);
+						 sizeof(hdata), &hdata);
 			if (!ptr)
 				goto bad;
 			/* just do it, baby */
-- 
cgit v1.2.3


From 95b0d2dc13c7e7ea51675836680732e8c16e378a Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 27 Jun 2018 13:33:34 -0400
Subject: net sched actions: fix misleading text strings in pedit action

Change "tc filter pedit .." to "tc actions pedit .." in error
messages to clearly refer to pedit action.

Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 3b775f54cee5..caa6927a992c 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -305,7 +305,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 
 			rc = pedit_skb_hdr_offset(skb, htype, &hoffset);
 			if (rc) {
-				pr_info("tc filter pedit bad header type specified (0x%x)\n",
+				pr_info("tc action pedit bad header type specified (0x%x)\n",
 					htype);
 				goto bad;
 			}
@@ -314,7 +314,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 				char *d, _d;
 
 				if (!offset_valid(skb, hoffset + tkey->at)) {
-					pr_info("tc filter pedit 'at' offset %d out of bounds\n",
+					pr_info("tc action pedit 'at' offset %d out of bounds\n",
 						hoffset + tkey->at);
 					goto bad;
 				}
@@ -326,12 +326,12 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			}
 
 			if (offset % 4) {
-				pr_info("tc filter pedit offset must be on 32 bit boundaries\n");
+				pr_info("tc action pedit offset must be on 32 bit boundaries\n");
 				goto bad;
 			}
 
 			if (!offset_valid(skb, hoffset + offset)) {
-				pr_info("tc filter pedit offset %d out of bounds\n",
+				pr_info("tc action pedit offset %d out of bounds\n",
 					hoffset + offset);
 				goto bad;
 			}
@@ -349,7 +349,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 				val = (*ptr + tkey->val) & ~tkey->mask;
 				break;
 			default:
-				pr_info("tc filter pedit bad command (%d)\n",
+				pr_info("tc action pedit bad command (%d)\n",
 					cmd);
 				goto bad;
 			}
-- 
cgit v1.2.3


From 430527415398cf7e741f5e2f11324a8df9093327 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Wed, 27 Jun 2018 13:33:35 -0400
Subject: net sched actions: avoid bitwise operation on signed value in pedit

Since char can be unsigned or signed, and bitwise operators may have
implementation-dependent results when performed on signed operands,
declare 'u8 *' operand instead.

Suggested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index caa6927a992c..ab151346d3d4 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -311,7 +311,7 @@ static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
 			}
 
 			if (tkey->offmask) {
-				char *d, _d;
+				u8 *d, _d;
 
 				if (!offset_valid(skb, hoffset + tkey->at)) {
 					pr_info("tc action pedit 'at' offset %d out of bounds\n",
-- 
cgit v1.2.3


From 80dc2a49ba040b3ce09c13d5a7be1799bc75a166 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:25 -0400
Subject: media: ov772x: reconstruct s_frame_interval()

This splits the s_frame_interval() in subdev video ops into selecting the
frame interval and setting up the registers.

This is a preparatory change to avoid accessing registers under power
saving mode.

Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 56 +++++++++++++++++++++++++++++-----------------
 1 file changed, 35 insertions(+), 21 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index 4a30a4338445..633a1b31b6d7 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -617,25 +617,16 @@ static int ov772x_s_stream(struct v4l2_subdev *sd, int enable)
 	return 0;
 }
 
-static int ov772x_set_frame_rate(struct ov772x_priv *priv,
-				 struct v4l2_fract *tpf,
-				 const struct ov772x_color_format *cfmt,
-				 const struct ov772x_win_size *win)
+static unsigned int ov772x_select_fps(struct ov772x_priv *priv,
+				      struct v4l2_fract *tpf)
 {
-	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
-	unsigned long fin = clk_get_rate(priv->clk);
 	unsigned int fps = tpf->numerator ?
 			   tpf->denominator / tpf->numerator :
 			   tpf->denominator;
 	unsigned int best_diff;
-	unsigned int fsize;
-	unsigned int pclk;
 	unsigned int diff;
 	unsigned int idx;
 	unsigned int i;
-	u8 clkrc = 0;
-	u8 com4 = 0;
-	int ret;
 
 	/* Approximate to the closest supported frame interval. */
 	best_diff = ~0L;
@@ -646,7 +637,25 @@ static int ov772x_set_frame_rate(struct ov772x_priv *priv,
 			best_diff = diff;
 		}
 	}
-	fps = ov772x_frame_intervals[idx];
+
+	return ov772x_frame_intervals[idx];
+}
+
+static int ov772x_set_frame_rate(struct ov772x_priv *priv,
+				 unsigned int fps,
+				 const struct ov772x_color_format *cfmt,
+				 const struct ov772x_win_size *win)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
+	unsigned long fin = clk_get_rate(priv->clk);
+	unsigned int best_diff;
+	unsigned int fsize;
+	unsigned int pclk;
+	unsigned int diff;
+	unsigned int i;
+	u8 clkrc = 0;
+	u8 com4 = 0;
+	int ret;
 
 	/* Use image size (with blankings) to calculate desired pixel clock. */
 	switch (cfmt->com7 & OFMT_MASK) {
@@ -711,10 +720,6 @@ static int ov772x_set_frame_rate(struct ov772x_priv *priv,
 	if (ret < 0)
 		return ret;
 
-	tpf->numerator = 1;
-	tpf->denominator = fps;
-	priv->fps = tpf->denominator;
-
 	return 0;
 }
 
@@ -735,8 +740,20 @@ static int ov772x_s_frame_interval(struct v4l2_subdev *sd,
 {
 	struct ov772x_priv *priv = to_ov772x(sd);
 	struct v4l2_fract *tpf = &ival->interval;
+	unsigned int fps;
+	int ret;
+
+	fps = ov772x_select_fps(priv, tpf);
+
+	ret = ov772x_set_frame_rate(priv, fps, priv->cfmt, priv->win);
+	if (ret)
+		return ret;
 
-	return ov772x_set_frame_rate(priv, tpf, priv->cfmt, priv->win);
+	tpf->numerator = 1;
+	tpf->denominator = fps;
+	priv->fps = fps;
+
+	return 0;
 }
 
 static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
@@ -993,7 +1010,6 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 			     const struct ov772x_win_size *win)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(&priv->subdev);
-	struct v4l2_fract tpf;
 	int ret;
 	u8  val;
 
@@ -1075,9 +1091,7 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 		goto ov772x_set_fmt_error;
 
 	/* COM4, CLKRC: Set pixel clock and framerate. */
-	tpf.numerator = 1;
-	tpf.denominator = priv->fps;
-	ret = ov772x_set_frame_rate(priv, &tpf, cfmt, win);
+	ret = ov772x_set_frame_rate(priv, priv->fps, cfmt, win);
 	if (ret < 0)
 		goto ov772x_set_fmt_error;
 
-- 
cgit v1.2.3


From 09e620c6af57ecc94411895eec78c5799a6e2a8d Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:26 -0400
Subject: media: ov772x: use v4l2_ctrl to get current control value

The ov772x driver provides three V4L2 controls and the current value of
each control is saved as a variable in the private data structure.

We don't need to keep track of the current value by ourself, if we use
v4l2_ctrl returned from v4l2_ctrl_new_std() instead.

This is a preparatory change to avoid accessing registers under power
saving mode.  This simplifies s_ctrl() by making it just return without
saving the current control value in private area when it is called under
power saving mode.

Cc: Jacopo Mondi <jacopo+renesas@jmondi.org>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index 633a1b31b6d7..553c334c55b6 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -419,10 +419,10 @@ struct ov772x_priv {
 	struct gpio_desc		 *rstb_gpio;
 	const struct ov772x_color_format *cfmt;
 	const struct ov772x_win_size     *win;
-	unsigned short                    flag_vflip:1;
-	unsigned short                    flag_hflip:1;
+	struct v4l2_ctrl		 *vflip_ctrl;
+	struct v4l2_ctrl		 *hflip_ctrl;
 	/* band_filter = COM8[5] ? 256 - BDBASE : 0 */
-	unsigned short                    band_filter;
+	struct v4l2_ctrl		 *band_filter_ctrl;
 	unsigned int			  fps;
 	/* lock to protect power_count */
 	struct mutex			  lock;
@@ -768,13 +768,11 @@ static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
 	switch (ctrl->id) {
 	case V4L2_CID_VFLIP:
 		val = ctrl->val ? VFLIP_IMG : 0x00;
-		priv->flag_vflip = ctrl->val;
 		if (priv->info && (priv->info->flags & OV772X_FLAG_VFLIP))
 			val ^= VFLIP_IMG;
 		return ov772x_mask_set(client, COM3, VFLIP_IMG, val);
 	case V4L2_CID_HFLIP:
 		val = ctrl->val ? HFLIP_IMG : 0x00;
-		priv->flag_hflip = ctrl->val;
 		if (priv->info && (priv->info->flags & OV772X_FLAG_HFLIP))
 			val ^= HFLIP_IMG;
 		return ov772x_mask_set(client, COM3, HFLIP_IMG, val);
@@ -794,8 +792,7 @@ static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
 				ret = ov772x_mask_set(client, BDBASE,
 						      0xff, val);
 		}
-		if (!ret)
-			priv->band_filter = ctrl->val;
+
 		return ret;
 	}
 
@@ -1075,9 +1072,9 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 		val |= VFLIP_IMG;
 	if (priv->info && (priv->info->flags & OV772X_FLAG_HFLIP))
 		val |= HFLIP_IMG;
-	if (priv->flag_vflip)
+	if (priv->vflip_ctrl->val)
 		val ^= VFLIP_IMG;
-	if (priv->flag_hflip)
+	if (priv->hflip_ctrl->val)
 		val ^= HFLIP_IMG;
 
 	ret = ov772x_mask_set(client,
@@ -1096,11 +1093,13 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 		goto ov772x_set_fmt_error;
 
 	/* Set COM8. */
-	if (priv->band_filter) {
+	if (priv->band_filter_ctrl->val) {
+		unsigned short band_filter = priv->band_filter_ctrl->val;
+
 		ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, BNDF_ON_OFF);
 		if (!ret)
 			ret = ov772x_mask_set(client, BDBASE,
-					      0xff, 256 - priv->band_filter);
+					      0xff, 256 - band_filter);
 		if (ret < 0)
 			goto ov772x_set_fmt_error;
 	}
@@ -1341,12 +1340,13 @@ static int ov772x_probe(struct i2c_client *client,
 
 	v4l2_i2c_subdev_init(&priv->subdev, client, &ov772x_subdev_ops);
 	v4l2_ctrl_handler_init(&priv->hdl, 3);
-	v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
-			  V4L2_CID_VFLIP, 0, 1, 1, 0);
-	v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
-			  V4L2_CID_HFLIP, 0, 1, 1, 0);
-	v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
-			  V4L2_CID_BAND_STOP_FILTER, 0, 256, 1, 0);
+	priv->vflip_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
+					     V4L2_CID_VFLIP, 0, 1, 1, 0);
+	priv->hflip_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
+					     V4L2_CID_HFLIP, 0, 1, 1, 0);
+	priv->band_filter_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
+						   V4L2_CID_BAND_STOP_FILTER,
+						   0, 256, 1, 0);
 	priv->subdev.ctrl_handler = &priv->hdl;
 	if (priv->hdl.error) {
 		ret = priv->hdl.error;
-- 
cgit v1.2.3


From 95f5a45aea8800e011698fef1c4f535e9afb374a Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:27 -0400
Subject: media: ov772x: avoid accessing registers under power saving mode

The set_fmt() in subdev pad ops, the s_ctrl() for subdev control handler,
and the s_frame_interval() in subdev video ops could be called when the
device is under power saving mode.  These callbacks for ov772x driver
cause updating H/W registers that will fail under power saving mode.

This avoids it by not apply any changes to H/W if the device is not powered
up.  Instead the changes will be restored right after power-up.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 79 +++++++++++++++++++++++++++++++++++++---------
 1 file changed, 64 insertions(+), 15 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index 553c334c55b6..d380e75db760 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -741,19 +741,30 @@ static int ov772x_s_frame_interval(struct v4l2_subdev *sd,
 	struct ov772x_priv *priv = to_ov772x(sd);
 	struct v4l2_fract *tpf = &ival->interval;
 	unsigned int fps;
-	int ret;
+	int ret = 0;
 
 	fps = ov772x_select_fps(priv, tpf);
 
-	ret = ov772x_set_frame_rate(priv, fps, priv->cfmt, priv->win);
-	if (ret)
-		return ret;
+	mutex_lock(&priv->lock);
+	/*
+	 * If the device is not powered up by the host driver do
+	 * not apply any changes to H/W at this time. Instead
+	 * the frame rate will be restored right after power-up.
+	 */
+	if (priv->power_count > 0) {
+		ret = ov772x_set_frame_rate(priv, fps, priv->cfmt, priv->win);
+		if (ret)
+			goto error;
+	}
 
 	tpf->numerator = 1;
 	tpf->denominator = fps;
 	priv->fps = fps;
 
-	return 0;
+error:
+	mutex_unlock(&priv->lock);
+
+	return ret;
 }
 
 static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
@@ -765,6 +776,16 @@ static int ov772x_s_ctrl(struct v4l2_ctrl *ctrl)
 	int ret = 0;
 	u8 val;
 
+	/* v4l2_ctrl_lock() locks our own mutex */
+
+	/*
+	 * If the device is not powered up by the host driver do
+	 * not apply any controls to H/W at this time. Instead
+	 * the controls will be restored right after power-up.
+	 */
+	if (priv->power_count == 0)
+		return 0;
+
 	switch (ctrl->id) {
 	case V4L2_CID_VFLIP:
 		val = ctrl->val ? VFLIP_IMG : 0x00;
@@ -885,6 +906,10 @@ static int ov772x_power_off(struct ov772x_priv *priv)
 	return 0;
 }
 
+static int ov772x_set_params(struct ov772x_priv *priv,
+			     const struct ov772x_color_format *cfmt,
+			     const struct ov772x_win_size *win);
+
 static int ov772x_s_power(struct v4l2_subdev *sd, int on)
 {
 	struct ov772x_priv *priv = to_ov772x(sd);
@@ -895,8 +920,20 @@ static int ov772x_s_power(struct v4l2_subdev *sd, int on)
 	/* If the power count is modified from 0 to != 0 or from != 0 to 0,
 	 * update the power state.
 	 */
-	if (priv->power_count == !on)
-		ret = on ? ov772x_power_on(priv) : ov772x_power_off(priv);
+	if (priv->power_count == !on) {
+		if (on) {
+			ret = ov772x_power_on(priv);
+			/*
+			 * Restore the format, the frame rate, and
+			 * the controls
+			 */
+			if (!ret)
+				ret = ov772x_set_params(priv, priv->cfmt,
+							priv->win);
+		} else {
+			ret = ov772x_power_off(priv);
+		}
+	}
 
 	if (!ret) {
 		/* Update the power count. */
@@ -1163,7 +1200,7 @@ static int ov772x_set_fmt(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *mf = &format->format;
 	const struct ov772x_color_format *cfmt;
 	const struct ov772x_win_size *win;
-	int ret;
+	int ret = 0;
 
 	if (format->pad)
 		return -EINVAL;
@@ -1184,14 +1221,24 @@ static int ov772x_set_fmt(struct v4l2_subdev *sd,
 		return 0;
 	}
 
-	ret = ov772x_set_params(priv, cfmt, win);
-	if (ret < 0)
-		return ret;
-
+	mutex_lock(&priv->lock);
+	/*
+	 * If the device is not powered up by the host driver do
+	 * not apply any changes to H/W at this time. Instead
+	 * the format will be restored right after power-up.
+	 */
+	if (priv->power_count > 0) {
+		ret = ov772x_set_params(priv, cfmt, win);
+		if (ret < 0)
+			goto error;
+	}
 	priv->win = win;
 	priv->cfmt = cfmt;
 
-	return 0;
+error:
+	mutex_unlock(&priv->lock);
+
+	return ret;
 }
 
 static int ov772x_video_probe(struct ov772x_priv *priv)
@@ -1201,7 +1248,7 @@ static int ov772x_video_probe(struct ov772x_priv *priv)
 	const char         *devname;
 	int		    ret;
 
-	ret = ov772x_s_power(&priv->subdev, 1);
+	ret = ov772x_power_on(priv);
 	if (ret < 0)
 		return ret;
 
@@ -1241,7 +1288,7 @@ static int ov772x_video_probe(struct ov772x_priv *priv)
 	ret = v4l2_ctrl_handler_setup(&priv->hdl);
 
 done:
-	ov772x_s_power(&priv->subdev, 0);
+	ov772x_power_off(priv);
 
 	return ret;
 }
@@ -1340,6 +1387,8 @@ static int ov772x_probe(struct i2c_client *client,
 
 	v4l2_i2c_subdev_init(&priv->subdev, client, &ov772x_subdev_ops);
 	v4l2_ctrl_handler_init(&priv->hdl, 3);
+	/* Use our mutex for the controls */
+	priv->hdl.lock = &priv->lock;
 	priv->vflip_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
 					     V4L2_CID_VFLIP, 0, 1, 1, 0);
 	priv->hflip_ctrl = v4l2_ctrl_new_std(&priv->hdl, &ov772x_ctrl_ops,
-- 
cgit v1.2.3


From 7b9998c9361950040af1c6e7a914519e891052a1 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:28 -0400
Subject: media: ov772x: make set_fmt() and s_frame_interval() return -EBUSY
 while streaming

The ov772x driver is going to offer a V4L2 sub-device interface, so
changing the output data format and the frame interval on this sub-device
can be made anytime.  However, these requests are preferred to fail while
the video stream on the device is active.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 43 +++++++++++++++++++++++++++++++++----------
 1 file changed, 33 insertions(+), 10 deletions(-)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index d380e75db760..9ff8e60c67b8 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -424,9 +424,10 @@ struct ov772x_priv {
 	/* band_filter = COM8[5] ? 256 - BDBASE : 0 */
 	struct v4l2_ctrl		 *band_filter_ctrl;
 	unsigned int			  fps;
-	/* lock to protect power_count */
+	/* lock to protect power_count and streaming */
 	struct mutex			  lock;
 	int				  power_count;
+	int				  streaming;
 #ifdef CONFIG_MEDIA_CONTROLLER
 	struct media_pad pad;
 #endif
@@ -603,18 +604,28 @@ static int ov772x_s_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct i2c_client *client = v4l2_get_subdevdata(sd);
 	struct ov772x_priv *priv = to_ov772x(sd);
+	int ret = 0;
 
-	if (!enable) {
-		ov772x_mask_set(client, COM2, SOFT_SLEEP_MODE, SOFT_SLEEP_MODE);
-		return 0;
-	}
+	mutex_lock(&priv->lock);
 
-	ov772x_mask_set(client, COM2, SOFT_SLEEP_MODE, 0);
+	if (priv->streaming == enable)
+		goto done;
 
-	dev_dbg(&client->dev, "format %d, win %s\n",
-		priv->cfmt->code, priv->win->name);
+	ret = ov772x_mask_set(client, COM2, SOFT_SLEEP_MODE,
+			      enable ? 0 : SOFT_SLEEP_MODE);
+	if (ret)
+		goto done;
 
-	return 0;
+	if (enable) {
+		dev_dbg(&client->dev, "format %d, win %s\n",
+			priv->cfmt->code, priv->win->name);
+	}
+	priv->streaming = enable;
+
+done:
+	mutex_unlock(&priv->lock);
+
+	return ret;
 }
 
 static unsigned int ov772x_select_fps(struct ov772x_priv *priv,
@@ -743,9 +754,15 @@ static int ov772x_s_frame_interval(struct v4l2_subdev *sd,
 	unsigned int fps;
 	int ret = 0;
 
+	mutex_lock(&priv->lock);
+
+	if (priv->streaming) {
+		ret = -EBUSY;
+		goto error;
+	}
+
 	fps = ov772x_select_fps(priv, tpf);
 
-	mutex_lock(&priv->lock);
 	/*
 	 * If the device is not powered up by the host driver do
 	 * not apply any changes to H/W at this time. Instead
@@ -1222,6 +1239,12 @@ static int ov772x_set_fmt(struct v4l2_subdev *sd,
 	}
 
 	mutex_lock(&priv->lock);
+
+	if (priv->streaming) {
+		ret = -EBUSY;
+		goto error;
+	}
+
 	/*
 	 * If the device is not powered up by the host driver do
 	 * not apply any changes to H/W at this time. Instead
-- 
cgit v1.2.3


From 795bce437f4ef9bdc116af1d7575c9f73f783a0c Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 6 May 2018 10:19:29 -0400
Subject: media: ov772x: create subdevice device node

Set the V4L2_SUBDEV_FL_HAS_DEVNODE flag for the subdevice so that the
subdevice device node is created.

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov772x.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/i2c/ov772x.c b/drivers/media/i2c/ov772x.c
index 9ff8e60c67b8..7158c31d8403 100644
--- a/drivers/media/i2c/ov772x.c
+++ b/drivers/media/i2c/ov772x.c
@@ -1409,6 +1409,7 @@ static int ov772x_probe(struct i2c_client *client,
 	mutex_init(&priv->lock);
 
 	v4l2_i2c_subdev_init(&priv->subdev, client, &ov772x_subdev_ops);
+	priv->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	v4l2_ctrl_handler_init(&priv->hdl, 3);
 	/* Use our mutex for the controls */
 	priv->hdl.lock = &priv->lock;
-- 
cgit v1.2.3


From 6f3de8388efcede60a7aee04022c4d02719f44c8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 25 May 2018 11:25:08 -0400
Subject: media: omap3isp: fix warning for !CONFIG_PM

The final version of the COMPILE_TEST patch for this driver missed
one warning about suspend/resume functions that can now appear
on platforms that don't always set CONFIG_PM:

drivers/media/platform/omap3isp/isp.c:1008:13: error: 'isp_resume_modules' defined but not used [-Werror=unused-function]
 static void isp_resume_modules(struct isp_device *isp)
             ^~~~~~~~~~~~~~~~~~
drivers/media/platform/omap3isp/isp.c:974:12: error: 'isp_suspend_modules' defined but not used [-Werror=unused-function]
 static int isp_suspend_modules(struct isp_device *isp)

This marks the respective functions as __maybe_unused as an easy
workaround.

Fixes: 243131134be4 ("media: omap3isp: Allow it to build with COMPILE_TEST")

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/omap3isp/isp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index f22cf351e3ee..a658c12eead1 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -971,7 +971,7 @@ static void isp_resume_module_pipeline(struct media_entity *me)
  * Returns 0 if suspend left in idle state all the submodules properly,
  * or returns 1 if a general Reset is required to suspend the submodules.
  */
-static int isp_suspend_modules(struct isp_device *isp)
+static int __maybe_unused isp_suspend_modules(struct isp_device *isp)
 {
 	unsigned long timeout;
 
@@ -1005,7 +1005,7 @@ static int isp_suspend_modules(struct isp_device *isp)
  * isp_resume_modules - Resume ISP submodules.
  * @isp: OMAP3 ISP device
  */
-static void isp_resume_modules(struct isp_device *isp)
+static void __maybe_unused isp_resume_modules(struct isp_device *isp)
 {
 	omap3isp_stat_resume(&isp->isp_aewb);
 	omap3isp_stat_resume(&isp->isp_af);
-- 
cgit v1.2.3


From 6882e01bf8b9e176f9a1f7f7431e269363c19b84 Mon Sep 17 00:00:00 2001
From: Yong Zhi <yong.zhi@intel.com>
Date: Wed, 30 May 2018 18:51:17 -0400
Subject: media: MAINTAINERS: Update entry for Intel IPU3 cio2 driver

This patch adds Bingbu as additional maintainer, and both Tian Shu and Jian Xu
as reviewers for IPU3 CIO2 driver.

Signed-off-by: Yong Zhi <yong.zhi@intel.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 5f4b8d14e75d..ed6f068e7ce1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7240,6 +7240,9 @@ F:	drivers/dma/iop-adma.c
 INTEL IPU3 CSI-2 CIO2 DRIVER
 M:	Yong Zhi <yong.zhi@intel.com>
 M:	Sakari Ailus <sakari.ailus@linux.intel.com>
+M:	Bingbu Cao <bingbu.cao@intel.com>
+R:	Tian Shu Qiu <tian.shu.qiu@intel.com>
+R:	Jian Xu Zheng <jian.xu.zheng@intel.com>
 L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	drivers/media/pci/intel/ipu3/
-- 
cgit v1.2.3


From 5129c0e1f6ac65eb1524aa520b06c6c742f0430e Mon Sep 17 00:00:00 2001
From: Alan Chiang <alanx.chiang@intel.com>
Date: Tue, 24 Apr 2018 22:12:07 -0400
Subject: media: dt-bindings: Add bindings for Dongwoon DW9807 voice coil

Dongwoon DW9807 is a voice coil lens driver.

Signed-off-by: Alan Chiang <alanx.chiang@intel.com>
Signed-off-by: Andy Yeh <andy.yeh@intel.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807.txt | 9 +++++++++
 1 file changed, 9 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807.txt

diff --git a/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807.txt b/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807.txt
new file mode 100644
index 000000000000..c4701f1eaaf6
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/dongwoon,dw9807.txt
@@ -0,0 +1,9 @@
+Dongwoon Anatech DW9807 voice coil lens driver
+
+DW9807 is a 10-bit DAC with current sink capability. It is intended for
+controlling voice coil lenses.
+
+Mandatory properties:
+
+- compatible: "dongwoon,dw9807-vcm"
+- reg: I2C slave address
-- 
cgit v1.2.3


From d48de54a9dab5370edd2e991f78cc7996cf5483e Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 28 Jun 2018 15:20:27 +0200
Subject: printk: Export is_console_locked

This is a preparation patch for adding a number of WARN_CONSOLE_UNLOCKED()
calls to the fbcon code, which may be built as a module (event though
usually it is not).

Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Acked-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
---
 kernel/printk/printk.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 247808333ba4..3f041e7cbfc9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2243,6 +2243,7 @@ int is_console_locked(void)
 {
 	return console_locked;
 }
+EXPORT_SYMBOL(is_console_locked);
 
 /*
  * Check if we have any console that is capable of printing while cpu is
-- 
cgit v1.2.3


From 3bd3a0e330aae4fffa8028aba2407ef615ab040b Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 28 Jun 2018 15:20:28 +0200
Subject: fbcon: Call WARN_CONSOLE_UNLOCKED() where applicable

Replace comments about places where the console lock should be held with
calls to WARN_CONSOLE_UNLOCKED() to assert that it is actually held.

Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
---
 drivers/video/fbdev/core/fbcon.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index c910e74d46ff..cd8d52a967aa 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -828,6 +828,8 @@ static int set_con2fb_map(int unit, int newidx, int user)
 	struct fb_info *oldinfo = NULL;
  	int found, err = 0;
 
+	WARN_CONSOLE_UNLOCKED();
+
 	if (oldidx == newidx)
 		return 0;
 
@@ -3044,6 +3046,8 @@ static int fbcon_fb_unbind(int idx)
 {
 	int i, new_idx = -1, ret = 0;
 
+	WARN_CONSOLE_UNLOCKED();
+
 	if (!fbcon_has_console_bind)
 		return 0;
 
@@ -3094,6 +3098,8 @@ static int fbcon_fb_unregistered(struct fb_info *info)
 {
 	int i, idx;
 
+	WARN_CONSOLE_UNLOCKED();
+
 	idx = info->node;
 	for (i = first_fb_vc; i <= last_fb_vc; i++) {
 		if (con2fb_map[i] == idx)
@@ -3131,6 +3137,9 @@ static int fbcon_fb_unregistered(struct fb_info *info)
 static void fbcon_remap_all(int idx)
 {
 	int i;
+
+	WARN_CONSOLE_UNLOCKED();
+
 	for (i = first_fb_vc; i <= last_fb_vc; i++)
 		set_con2fb_map(i, idx, 0);
 
@@ -3177,6 +3186,8 @@ static int fbcon_fb_registered(struct fb_info *info)
 {
 	int ret = 0, i, idx;
 
+	WARN_CONSOLE_UNLOCKED();
+
 	idx = info->node;
 	fbcon_select_primary(info);
 
-- 
cgit v1.2.3


From 83d83bebf40132e2d55ec58af666713cc76f9764 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 28 Jun 2018 15:20:30 +0200
Subject: console/fbcon: Add support for deferred console takeover

Currently fbcon claims fbdevs as soon as they are registered and takes over
the console as soon as the first fbdev gets registered.

This behavior is undesirable in cases where a smooth graphical bootup is
desired, in such cases we typically want the contents of the framebuffer
(typically a vendor logo) to stay in place as is.

The current solution for this problem (on embedded systems) is to not
enable fbcon.

This commit adds a new FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER config option,
which when enabled defers fbcon taking over the console from the dummy
console until the first text is displayed on the console. Together with the
"quiet" kernel commandline option, this allows fbcon to still be used
together with a smooth graphical bootup, having it take over the console as
soon as e.g. an error message is logged.

Note the choice to detect the first console output in the dummycon driver,
rather then handling this entirely inside the fbcon code, was made after
2 failed attempts to handle this entirely inside the fbcon code. The fbcon
code is woven quite tightly into the console code, making this to only
feasible option.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
---
 Documentation/fb/fbcon.txt       |  7 ++++
 drivers/video/console/Kconfig    | 11 ++++++
 drivers/video/console/dummycon.c | 67 ++++++++++++++++++++++++++++++++-----
 drivers/video/fbdev/core/fbcon.c | 72 ++++++++++++++++++++++++++++++++++++++++
 include/linux/console.h          |  5 +++
 5 files changed, 154 insertions(+), 8 deletions(-)

diff --git a/Documentation/fb/fbcon.txt b/Documentation/fb/fbcon.txt
index 79c22d096bbc..d4d642e1ce9c 100644
--- a/Documentation/fb/fbcon.txt
+++ b/Documentation/fb/fbcon.txt
@@ -155,6 +155,13 @@ C. Boot options
 	used by text. By default, this area will be black. The 'color' value
 	is an integer number that depends on the framebuffer driver being used.
 
+6. fbcon=nodefer
+
+	If the kernel is compiled with deferred fbcon takeover support, normally
+	the framebuffer contents, left in place by the firmware/bootloader, will
+	be preserved until there actually is some text is output to the console.
+	This option causes fbcon to bind immediately to the fbdev device.
+
 C. Attaching, Detaching and Unloading
 
 Before going on how to attach, detach and unload the framebuffer console, an
diff --git a/drivers/video/console/Kconfig b/drivers/video/console/Kconfig
index 4110ba7d7ca9..e91edef98633 100644
--- a/drivers/video/console/Kconfig
+++ b/drivers/video/console/Kconfig
@@ -150,6 +150,17 @@ config FRAMEBUFFER_CONSOLE_ROTATION
          such that other users of the framebuffer will remain normally
          oriented.
 
+config FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+	bool "Framebuffer Console Deferred Takeover"
+	depends on FRAMEBUFFER_CONSOLE=y && DUMMY_CONSOLE=y
+	help
+	  If enabled this defers the framebuffer console taking over the
+	  console from the dummy console until the first text is displayed on
+	  the console. This is useful in combination with the "quiet" kernel
+	  commandline option to keep the framebuffer contents initially put up
+	  by the firmware in place, rather then replacing the contents with a
+	  black screen as soon as fbcon loads.
+
 config STI_CONSOLE
         bool "STI text console"
 	depends on PARISC && HAS_IOMEM
diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index f2eafe2ed980..45ad925ad5f8 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -26,6 +26,65 @@
 #define DUMMY_ROWS	CONFIG_DUMMY_CONSOLE_ROWS
 #endif
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+/* These are both protected by the console_lock */
+static RAW_NOTIFIER_HEAD(dummycon_output_nh);
+static bool dummycon_putc_called;
+
+void dummycon_register_output_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_register(&dummycon_output_nh, nb);
+
+	if (dummycon_putc_called)
+		nb->notifier_call(nb, 0, NULL);
+}
+
+void dummycon_unregister_output_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_unregister(&dummycon_output_nh, nb);
+}
+
+static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos)
+{
+	dummycon_putc_called = true;
+	raw_notifier_call_chain(&dummycon_output_nh, 0, NULL);
+}
+
+static void dummycon_putcs(struct vc_data *vc, const unsigned short *s,
+			   int count, int ypos, int xpos)
+{
+	int i;
+
+	if (!dummycon_putc_called) {
+		/* Ignore erases */
+		for (i = 0 ; i < count; i++) {
+			if (s[i] != vc->vc_video_erase_char)
+				break;
+		}
+		if (i == count)
+			return;
+
+		dummycon_putc_called = true;
+	}
+
+	raw_notifier_call_chain(&dummycon_output_nh, 0, NULL);
+}
+
+static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch)
+{
+	/* Redraw, so that we get putc(s) for output done while blanked */
+	return 1;
+}
+#else
+static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { }
+static void dummycon_putcs(struct vc_data *vc, const unsigned short *s,
+			   int count, int ypos, int xpos) { }
+static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch)
+{
+	return 0;
+}
+#endif
+
 static const char *dummycon_startup(void)
 {
     return "dummy device";
@@ -44,9 +103,6 @@ static void dummycon_init(struct vc_data *vc, int init)
 static void dummycon_deinit(struct vc_data *vc) { }
 static void dummycon_clear(struct vc_data *vc, int sy, int sx, int height,
 			   int width) { }
-static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos) { }
-static void dummycon_putcs(struct vc_data *vc, const unsigned short *s,
-			   int count, int ypos, int xpos) { }
 static void dummycon_cursor(struct vc_data *vc, int mode) { }
 
 static bool dummycon_scroll(struct vc_data *vc, unsigned int top,
@@ -61,11 +117,6 @@ static int dummycon_switch(struct vc_data *vc)
 	return 0;
 }
 
-static int dummycon_blank(struct vc_data *vc, int blank, int mode_switch)
-{
-	return 0;
-}
-
 static int dummycon_font_set(struct vc_data *vc, struct console_font *font,
 			     unsigned int flags)
 {
diff --git a/drivers/video/fbdev/core/fbcon.c b/drivers/video/fbdev/core/fbcon.c
index cd8d52a967aa..5fb156bdcf4e 100644
--- a/drivers/video/fbdev/core/fbcon.c
+++ b/drivers/video/fbdev/core/fbcon.c
@@ -129,6 +129,12 @@ static inline void fbcon_map_override(void)
 }
 #endif /* CONFIG_FRAMEBUFFER_CONSOLE_DETECT_PRIMARY */
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+static bool deferred_takeover = true;
+#else
+#define deferred_takeover false
+#endif
+
 /* font data */
 static char fontname[40];
 
@@ -499,6 +505,12 @@ static int __init fb_console_setup(char *this_opt)
 				margin_color = simple_strtoul(options, &options, 0);
 			continue;
 		}
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+		if (!strcmp(options, "nodefer")) {
+			deferred_takeover = false;
+			continue;
+		}
+#endif
 	}
 	return 1;
 }
@@ -3100,6 +3112,9 @@ static int fbcon_fb_unregistered(struct fb_info *info)
 
 	WARN_CONSOLE_UNLOCKED();
 
+	if (deferred_takeover)
+		return 0;
+
 	idx = info->node;
 	for (i = first_fb_vc; i <= last_fb_vc; i++) {
 		if (con2fb_map[i] == idx)
@@ -3140,6 +3155,13 @@ static void fbcon_remap_all(int idx)
 
 	WARN_CONSOLE_UNLOCKED();
 
+	if (deferred_takeover) {
+		for (i = first_fb_vc; i <= last_fb_vc; i++)
+			con2fb_map_boot[i] = idx;
+		fbcon_map_override();
+		return;
+	}
+
 	for (i = first_fb_vc; i <= last_fb_vc; i++)
 		set_con2fb_map(i, idx, 0);
 
@@ -3191,6 +3213,11 @@ static int fbcon_fb_registered(struct fb_info *info)
 	idx = info->node;
 	fbcon_select_primary(info);
 
+	if (deferred_takeover) {
+		pr_info("fbcon: Deferring console take-over\n");
+		return 0;
+	}
+
 	if (info_idx == -1) {
 		for (i = first_fb_vc; i <= last_fb_vc; i++) {
 			if (con2fb_map_boot[i] == idx) {
@@ -3566,8 +3593,46 @@ static int fbcon_init_device(void)
 	return 0;
 }
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+static struct notifier_block fbcon_output_nb;
+
+static int fbcon_output_notifier(struct notifier_block *nb,
+				 unsigned long action, void *data)
+{
+	int i;
+
+	WARN_CONSOLE_UNLOCKED();
+
+	pr_info("fbcon: Taking over console\n");
+
+	dummycon_unregister_output_notifier(&fbcon_output_nb);
+	deferred_takeover = false;
+	logo_shown = FBCON_LOGO_DONTSHOW;
+
+	for (i = 0; i < FB_MAX; i++) {
+		if (registered_fb[i])
+			fbcon_fb_registered(registered_fb[i]);
+	}
+
+	return NOTIFY_OK;
+}
+
+static void fbcon_register_output_notifier(void)
+{
+	fbcon_output_nb.notifier_call = fbcon_output_notifier;
+	dummycon_register_output_notifier(&fbcon_output_nb);
+}
+#else
+static inline void fbcon_register_output_notifier(void) {}
+#endif
+
 static void fbcon_start(void)
 {
+	if (deferred_takeover) {
+		fbcon_register_output_notifier();
+		return;
+	}
+
 	if (num_registered_fb) {
 		int i;
 
@@ -3594,6 +3659,13 @@ static void fbcon_exit(void)
 	if (fbcon_has_exited)
 		return;
 
+#ifdef CONFIG_FRAMEBUFFER_CONSOLE_DEFERRED_TAKEOVER
+	if (deferred_takeover) {
+		dummycon_unregister_output_notifier(&fbcon_output_nb);
+		deferred_takeover = false;
+	}
+#endif
+
 	kfree((void *)softback_buf);
 	softback_buf = 0UL;
 
diff --git a/include/linux/console.h b/include/linux/console.h
index dfd6b0e97855..f59f3dbca65c 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -21,6 +21,7 @@ struct console_font_op;
 struct console_font;
 struct module;
 struct tty_struct;
+struct notifier_block;
 
 /*
  * this is what the terminal answers to a ESC-Z or csi0c query.
@@ -220,4 +221,8 @@ static inline bool vgacon_text_force(void) { return false; }
 
 extern void console_init(void);
 
+/* For deferred console takeover */
+void dummycon_register_output_notifier(struct notifier_block *nb);
+void dummycon_unregister_output_notifier(struct notifier_block *nb);
+
 #endif /* _LINUX_CONSOLE_H */
-- 
cgit v1.2.3


From f564650106a6e85702660fefd59fdff0877ab46a Mon Sep 17 00:00:00 2001
From: Flavio Leitner <fbl@redhat.com>
Date: Wed, 27 Jun 2018 10:34:25 -0300
Subject: netfilter: check if the socket netns is correct.

Netfilter assumes that if the socket is present in the skb, then
it can be used because that reference is cleaned up while the skb
is crossing netns.

We want to change that to preserve the socket reference in a future
patch, so this is a preparation updating netfilter to check if the
socket netns matches before use it.

Signed-off-by: Flavio Leitner <fbl@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netfilter/nf_log.h         | 3 ++-
 net/ipv4/netfilter/nf_log_ipv4.c       | 8 ++++----
 net/ipv6/netfilter/nf_log_ipv6.c       | 8 ++++----
 net/netfilter/nf_conntrack_broadcast.c | 2 +-
 net/netfilter/nf_log_common.c          | 5 +++--
 net/netfilter/nf_nat_core.c            | 6 +++++-
 net/netfilter/nft_meta.c               | 9 ++++++---
 net/netfilter/nft_socket.c             | 5 ++++-
 net/netfilter/xt_cgroup.c              | 6 ++++--
 net/netfilter/xt_owner.c               | 2 +-
 net/netfilter/xt_recent.c              | 3 ++-
 net/netfilter/xt_socket.c              | 8 ++++++++
 12 files changed, 44 insertions(+), 21 deletions(-)

diff --git a/include/net/netfilter/nf_log.h b/include/net/netfilter/nf_log.h
index e811ac07ea94..0d3920896d50 100644
--- a/include/net/netfilter/nf_log.h
+++ b/include/net/netfilter/nf_log.h
@@ -106,7 +106,8 @@ int nf_log_dump_udp_header(struct nf_log_buf *m, const struct sk_buff *skb,
 int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb,
 			   u8 proto, int fragment, unsigned int offset,
 			   unsigned int logflags);
-void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk);
+void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m,
+			    struct sock *sk);
 void nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
 			       unsigned int hooknum, const struct sk_buff *skb,
 			       const struct net_device *in,
diff --git a/net/ipv4/netfilter/nf_log_ipv4.c b/net/ipv4/netfilter/nf_log_ipv4.c
index 4388de0e5380..1e6f28c97d3a 100644
--- a/net/ipv4/netfilter/nf_log_ipv4.c
+++ b/net/ipv4/netfilter/nf_log_ipv4.c
@@ -35,7 +35,7 @@ static const struct nf_loginfo default_loginfo = {
 };
 
 /* One level of recursion won't kill us */
-static void dump_ipv4_packet(struct nf_log_buf *m,
+static void dump_ipv4_packet(struct net *net, struct nf_log_buf *m,
 			     const struct nf_loginfo *info,
 			     const struct sk_buff *skb, unsigned int iphoff)
 {
@@ -183,7 +183,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m,
 			/* Max length: 3+maxlen */
 			if (!iphoff) { /* Only recurse once. */
 				nf_log_buf_add(m, "[");
-				dump_ipv4_packet(m, info, skb,
+				dump_ipv4_packet(net, m, info, skb,
 					    iphoff + ih->ihl*4+sizeof(_icmph));
 				nf_log_buf_add(m, "] ");
 			}
@@ -251,7 +251,7 @@ static void dump_ipv4_packet(struct nf_log_buf *m,
 
 	/* Max length: 15 "UID=4294967295 " */
 	if ((logflags & NF_LOG_UID) && !iphoff)
-		nf_log_dump_sk_uid_gid(m, skb->sk);
+		nf_log_dump_sk_uid_gid(net, m, skb->sk);
 
 	/* Max length: 16 "MARK=0xFFFFFFFF " */
 	if (!iphoff && skb->mark)
@@ -333,7 +333,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf,
 	if (in != NULL)
 		dump_ipv4_mac_header(m, loginfo, skb);
 
-	dump_ipv4_packet(m, loginfo, skb, 0);
+	dump_ipv4_packet(net, m, loginfo, skb, 0);
 
 	nf_log_buf_close(m);
 }
diff --git a/net/ipv6/netfilter/nf_log_ipv6.c b/net/ipv6/netfilter/nf_log_ipv6.c
index b397a8fe88b9..c6bf580d0f33 100644
--- a/net/ipv6/netfilter/nf_log_ipv6.c
+++ b/net/ipv6/netfilter/nf_log_ipv6.c
@@ -36,7 +36,7 @@ static const struct nf_loginfo default_loginfo = {
 };
 
 /* One level of recursion won't kill us */
-static void dump_ipv6_packet(struct nf_log_buf *m,
+static void dump_ipv6_packet(struct net *net, struct nf_log_buf *m,
 			     const struct nf_loginfo *info,
 			     const struct sk_buff *skb, unsigned int ip6hoff,
 			     int recurse)
@@ -258,7 +258,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m,
 			/* Max length: 3+maxlen */
 			if (recurse) {
 				nf_log_buf_add(m, "[");
-				dump_ipv6_packet(m, info, skb,
+				dump_ipv6_packet(net, m, info, skb,
 						 ptr + sizeof(_icmp6h), 0);
 				nf_log_buf_add(m, "] ");
 			}
@@ -278,7 +278,7 @@ static void dump_ipv6_packet(struct nf_log_buf *m,
 
 	/* Max length: 15 "UID=4294967295 " */
 	if ((logflags & NF_LOG_UID) && recurse)
-		nf_log_dump_sk_uid_gid(m, skb->sk);
+		nf_log_dump_sk_uid_gid(net, m, skb->sk);
 
 	/* Max length: 16 "MARK=0xFFFFFFFF " */
 	if (recurse && skb->mark)
@@ -365,7 +365,7 @@ static void nf_log_ip6_packet(struct net *net, u_int8_t pf,
 	if (in != NULL)
 		dump_ipv6_mac_header(m, loginfo, skb);
 
-	dump_ipv6_packet(m, loginfo, skb, skb_network_offset(skb), 1);
+	dump_ipv6_packet(net, m, loginfo, skb, skb_network_offset(skb), 1);
 
 	nf_log_buf_close(m);
 }
diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c
index a1086bdec242..5423b197d98a 100644
--- a/net/netfilter/nf_conntrack_broadcast.c
+++ b/net/netfilter/nf_conntrack_broadcast.c
@@ -32,7 +32,7 @@ int nf_conntrack_broadcast_help(struct sk_buff *skb,
 	__be32 mask = 0;
 
 	/* we're only interested in locally generated packets */
-	if (skb->sk == NULL)
+	if (skb->sk == NULL || !net_eq(nf_ct_net(ct), sock_net(skb->sk)))
 		goto out;
 	if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST))
 		goto out;
diff --git a/net/netfilter/nf_log_common.c b/net/netfilter/nf_log_common.c
index dc61399e30be..a8c5c846aec1 100644
--- a/net/netfilter/nf_log_common.c
+++ b/net/netfilter/nf_log_common.c
@@ -132,9 +132,10 @@ int nf_log_dump_tcp_header(struct nf_log_buf *m, const struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_log_dump_tcp_header);
 
-void nf_log_dump_sk_uid_gid(struct nf_log_buf *m, struct sock *sk)
+void nf_log_dump_sk_uid_gid(struct net *net, struct nf_log_buf *m,
+			    struct sock *sk)
 {
-	if (!sk || !sk_fullsock(sk))
+	if (!sk || !sk_fullsock(sk) || !net_eq(net, sock_net(sk)))
 		return;
 
 	read_lock_bh(&sk->sk_callback_lock);
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 46f9df99d276..86df2a1666fd 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -108,6 +108,7 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family)
 	struct flowi fl;
 	unsigned int hh_len;
 	struct dst_entry *dst;
+	struct sock *sk = skb->sk;
 	int err;
 
 	err = xfrm_decode_session(skb, &fl, family);
@@ -119,7 +120,10 @@ int nf_xfrm_me_harder(struct net *net, struct sk_buff *skb, unsigned int family)
 		dst = ((struct xfrm_dst *)dst)->route;
 	dst_hold(dst);
 
-	dst = xfrm_lookup(net, dst, &fl, skb->sk, 0);
+	if (sk && !net_eq(net, sock_net(sk)))
+		sk = NULL;
+
+	dst = xfrm_lookup(net, dst, &fl, sk, 0);
 	if (IS_ERR(dst))
 		return PTR_ERR(dst);
 
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 1105a23bda5e..2b94dcc43456 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -107,7 +107,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr,
 		break;
 	case NFT_META_SKUID:
 		sk = skb_to_full_sk(skb);
-		if (!sk || !sk_fullsock(sk))
+		if (!sk || !sk_fullsock(sk) ||
+		    !net_eq(nft_net(pkt), sock_net(sk)))
 			goto err;
 
 		read_lock_bh(&sk->sk_callback_lock);
@@ -123,7 +124,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr,
 		break;
 	case NFT_META_SKGID:
 		sk = skb_to_full_sk(skb);
-		if (!sk || !sk_fullsock(sk))
+		if (!sk || !sk_fullsock(sk) ||
+		    !net_eq(nft_net(pkt), sock_net(sk)))
 			goto err;
 
 		read_lock_bh(&sk->sk_callback_lock);
@@ -214,7 +216,8 @@ static void nft_meta_get_eval(const struct nft_expr *expr,
 #ifdef CONFIG_CGROUP_NET_CLASSID
 	case NFT_META_CGROUP:
 		sk = skb_to_full_sk(skb);
-		if (!sk || !sk_fullsock(sk))
+		if (!sk || !sk_fullsock(sk) ||
+		    !net_eq(nft_net(pkt), sock_net(sk)))
 			goto err;
 		*dest = sock_cgroup_classid(&sk->sk_cgrp_data);
 		break;
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 74e1b3bd6954..998c2b546f6d 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -23,6 +23,9 @@ static void nft_socket_eval(const struct nft_expr *expr,
 	struct sock *sk = skb->sk;
 	u32 *dest = &regs->data[priv->dreg];
 
+	if (sk && !net_eq(nft_net(pkt), sock_net(sk)))
+		sk = NULL;
+
 	if (!sk)
 		switch(nft_pf(pkt)) {
 		case NFPROTO_IPV4:
@@ -39,7 +42,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 			return;
 		}
 
-	if(!sk) {
+	if (!sk) {
 		nft_reg_store8(dest, 0);
 		return;
 	}
diff --git a/net/netfilter/xt_cgroup.c b/net/netfilter/xt_cgroup.c
index 7df2dece57d3..5d92e1781980 100644
--- a/net/netfilter/xt_cgroup.c
+++ b/net/netfilter/xt_cgroup.c
@@ -72,8 +72,9 @@ static bool
 cgroup_mt_v0(const struct sk_buff *skb, struct xt_action_param *par)
 {
 	const struct xt_cgroup_info_v0 *info = par->matchinfo;
+	struct sock *sk = skb->sk;
 
-	if (skb->sk == NULL || !sk_fullsock(skb->sk))
+	if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk)))
 		return false;
 
 	return (info->id == sock_cgroup_classid(&skb->sk->sk_cgrp_data)) ^
@@ -85,8 +86,9 @@ static bool cgroup_mt_v1(const struct sk_buff *skb, struct xt_action_param *par)
 	const struct xt_cgroup_info_v1 *info = par->matchinfo;
 	struct sock_cgroup_data *skcd = &skb->sk->sk_cgrp_data;
 	struct cgroup *ancestor = info->priv;
+	struct sock *sk = skb->sk;
 
-	if (!skb->sk || !sk_fullsock(skb->sk))
+	if (!sk || !sk_fullsock(sk) || !net_eq(xt_net(par), sock_net(sk)))
 		return false;
 
 	if (ancestor)
diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c
index 3d705c688a27..46686fb73784 100644
--- a/net/netfilter/xt_owner.c
+++ b/net/netfilter/xt_owner.c
@@ -67,7 +67,7 @@ owner_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	struct sock *sk = skb_to_full_sk(skb);
 	struct net *net = xt_net(par);
 
-	if (sk == NULL || sk->sk_socket == NULL)
+	if (!sk || !sk->sk_socket || !net_eq(net, sock_net(sk)))
 		return (info->match ^ info->invert) == 0;
 	else if (info->match & info->invert & XT_OWNER_SOCKET)
 		/*
diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c
index 07085c22b19c..f44de4bc2100 100644
--- a/net/netfilter/xt_recent.c
+++ b/net/netfilter/xt_recent.c
@@ -265,7 +265,8 @@ recent_mt(const struct sk_buff *skb, struct xt_action_param *par)
 	}
 
 	/* use TTL as seen before forwarding */
-	if (xt_out(par) != NULL && skb->sk == NULL)
+	if (xt_out(par) != NULL &&
+	    (!skb->sk || !net_eq(net, sock_net(skb->sk))))
 		ttl++;
 
 	spin_lock_bh(&recent_lock);
diff --git a/net/netfilter/xt_socket.c b/net/netfilter/xt_socket.c
index 5c0779c4fa3c..0472f3472842 100644
--- a/net/netfilter/xt_socket.c
+++ b/net/netfilter/xt_socket.c
@@ -56,8 +56,12 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 	struct sk_buff *pskb = (struct sk_buff *)skb;
 	struct sock *sk = skb->sk;
 
+	if (!net_eq(xt_net(par), sock_net(sk)))
+		sk = NULL;
+
 	if (!sk)
 		sk = nf_sk_lookup_slow_v4(xt_net(par), skb, xt_in(par));
+
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;
@@ -113,8 +117,12 @@ socket_mt6_v1_v2_v3(const struct sk_buff *skb, struct xt_action_param *par)
 	struct sk_buff *pskb = (struct sk_buff *)skb;
 	struct sock *sk = skb->sk;
 
+	if (!net_eq(xt_net(par), sock_net(sk)))
+		sk = NULL;
+
 	if (!sk)
 		sk = nf_sk_lookup_slow_v6(xt_net(par), skb, xt_in(par));
+
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;
-- 
cgit v1.2.3


From 9c4c325252c54b34d53b3d0ffd535182b744e03d Mon Sep 17 00:00:00 2001
From: Flavio Leitner <fbl@redhat.com>
Date: Wed, 27 Jun 2018 10:34:26 -0300
Subject: skbuff: preserve sock reference when scrubbing the skb.

The sock reference is lost when scrubbing the packet and that breaks
TSQ (TCP Small Queues) and XPS (Transmit Packet Steering) causing
performance impacts of about 50% in a single TCP stream when crossing
network namespaces.

XPS breaks because the queue mapping stored in the socket is not
available, so another random queue might be selected when the stack
needs to transmit something like a TCP ACK, or TCP Retransmissions.
That causes packet re-ordering and/or performance issues.

TSQ breaks because it orphans the packet while it is still in the
host, so packets are queued contributing to the buffer bloat problem.

Preserving the sock reference fixes both issues. The socket is
orphaned anyways in the receiving path before any relevant action
and on TX side the netfilter checks if the reference is local before
use it.

Signed-off-by: Flavio Leitner <fbl@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 10 +++++-----
 net/core/skbuff.c                      |  1 -
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index ce8fbf5aa63c..f4c042be0216 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -733,11 +733,11 @@ tcp_limit_output_bytes - INTEGER
 	Controls TCP Small Queue limit per tcp socket.
 	TCP bulk sender tends to increase packets in flight until it
 	gets losses notifications. With SNDBUF autotuning, this can
-	result in a large amount of packets queued in qdisc/device
-	on the local machine, hurting latency of other flows, for
-	typical pfifo_fast qdiscs.
-	tcp_limit_output_bytes limits the number of bytes on qdisc
-	or device to reduce artificial RTT/cwnd and reduce bufferbloat.
+	result in a large amount of packets queued on the local machine
+	(e.g.: qdiscs, CPU backlog, or device) hurting latency of other
+	flows, for typical pfifo_fast qdiscs.  tcp_limit_output_bytes
+	limits the number of bytes on qdisc or device to reduce artificial
+	RTT/cwnd and reduce bufferbloat.
 	Default: 262144
 
 tcp_challenge_ack_limit - INTEGER
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index b1f274f22d85..f59e98ca72c5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4911,7 +4911,6 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 		return;
 
 	ipvs_reset(skb);
-	skb_orphan(skb);
 	skb->mark = 0;
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
-- 
cgit v1.2.3


From 5b0a205466578432ce8faadd08f8d7ef895a180f Mon Sep 17 00:00:00 2001
From: Alan Chiang <alanx.chiang@intel.com>
Date: Tue, 24 Apr 2018 22:12:08 -0400
Subject: media: dw9807: Add dw9807 vcm driver

DW9807 is a 10 bit DAC from Dongwoon, designed for linear
control of voice coil motor.

This driver creates a V4L2 subdevice and
provides control to set the desired focus.

Signed-off-by: Alan Chiang <alanx.chiang@intel.com>
Signed-off-by: Andy Yeh <andy.yeh@intel.com>
Reviewed-by: Jacopo Mondi <jacopo@jmondi.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 MAINTAINERS                |   7 +
 drivers/media/i2c/Kconfig  |  10 ++
 drivers/media/i2c/Makefile |   1 +
 drivers/media/i2c/dw9807.c | 329 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 347 insertions(+)
 create mode 100644 drivers/media/i2c/dw9807.c

diff --git a/MAINTAINERS b/MAINTAINERS
index ed6f068e7ce1..bd147aee7f80 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4403,6 +4403,13 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/i2c/dw9714.c
 
+DONGWOON DW9807 LENS VOICE COIL DRIVER
+M:	Sakari Ailus <sakari.ailus@linux.intel.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/i2c/dw9807.c
+
 DOUBLETALK DRIVER
 M:	"James R. Van Zandt" <jrv@vanzandt.mv.com>
 L:	blinux-list@redhat.com
diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 1d5efef77e77..1cf91bce2613 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -336,6 +336,16 @@ config VIDEO_DW9714
 	  capability. This is designed for linear control of
 	  voice coil motors, controlled via I2C serial interface.
 
+config VIDEO_DW9807
+	tristate "DW9807 lens voice coil support"
+	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
+	depends on VIDEO_V4L2_SUBDEV_API
+	---help---
+	  This is a driver for the DW9807 camera lens voice coil.
+	  DW9807 is a 10 bit DAC with 100mA output current sink
+	  capability. This is designed for linear control of
+	  voice coil motors, controlled via I2C serial interface.
+
 config VIDEO_SAA7110
 	tristate "Philips SAA7110 video decoder"
 	depends on VIDEO_V4L2 && I2C
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index 33cf2a415657..1d994658a9d4 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_VIDEO_SAA7185) += saa7185.o
 obj-$(CONFIG_VIDEO_SAA6752HS) += saa6752hs.o
 obj-$(CONFIG_VIDEO_AD5820)  += ad5820.o
 obj-$(CONFIG_VIDEO_DW9714)  += dw9714.o
+obj-$(CONFIG_VIDEO_DW9807)  += dw9807.o
 obj-$(CONFIG_VIDEO_ADV7170) += adv7170.o
 obj-$(CONFIG_VIDEO_ADV7175) += adv7175.o
 obj-$(CONFIG_VIDEO_ADV7180) += adv7180.o
diff --git a/drivers/media/i2c/dw9807.c b/drivers/media/i2c/dw9807.c
new file mode 100644
index 000000000000..8ba3920b6e2f
--- /dev/null
+++ b/drivers/media/i2c/dw9807.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Intel Corporation
+
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+
+#define DW9807_MAX_FOCUS_POS	1023
+/*
+ * This sets the minimum granularity for the focus positions.
+ * A value of 1 gives maximum accuracy for a desired focus position.
+ */
+#define DW9807_FOCUS_STEPS	1
+/*
+ * This acts as the minimum granularity of lens movement.
+ * Keep this value power of 2, so the control steps can be
+ * uniformly adjusted for gradual lens movement, with desired
+ * number of control steps.
+ */
+#define DW9807_CTRL_STEPS	16
+#define DW9807_CTRL_DELAY_US	1000
+
+#define DW9807_CTL_ADDR		0x02
+/*
+ * DW9807 separates two registers to control the VCM position.
+ * One for MSB value, another is LSB value.
+ */
+#define DW9807_MSB_ADDR		0x03
+#define DW9807_LSB_ADDR		0x04
+#define DW9807_STATUS_ADDR	0x05
+#define DW9807_MODE_ADDR	0x06
+#define DW9807_RESONANCE_ADDR	0x07
+
+#define MAX_RETRY		10
+
+struct dw9807_device {
+	struct v4l2_ctrl_handler ctrls_vcm;
+	struct v4l2_subdev sd;
+	u16 current_val;
+};
+
+static inline struct dw9807_device *sd_to_dw9807_vcm(
+					struct v4l2_subdev *subdev)
+{
+	return container_of(subdev, struct dw9807_device, sd);
+}
+
+static int dw9807_i2c_check(struct i2c_client *client)
+{
+	const char status_addr = DW9807_STATUS_ADDR;
+	char status_result;
+	int ret;
+
+	ret = i2c_master_send(client, &status_addr, sizeof(status_addr));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write STATUS address fail ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = i2c_master_recv(client, &status_result, sizeof(status_result));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C read STATUS value fail ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	return status_result;
+}
+
+static int dw9807_set_dac(struct i2c_client *client, u16 data)
+{
+	const char tx_data[3] = {
+		DW9807_MSB_ADDR, ((data >> 8) & 0x03), (data & 0xff)
+	};
+	int val, ret;
+
+	/*
+	 * According to the datasheet, need to check the bus status before we
+	 * write VCM position. This ensure that we really write the value
+	 * into the register
+	 */
+	ret = readx_poll_timeout(dw9807_i2c_check, client, val, val <= 0,
+			DW9807_CTRL_DELAY_US, MAX_RETRY * DW9807_CTRL_DELAY_US);
+
+	if (ret || val < 0) {
+		if (ret) {
+			dev_warn(&client->dev,
+				"Cannot do the write operation because VCM is busy\n");
+		}
+
+		return ret ? -EBUSY : val;
+	}
+
+	/* Write VCM position to registers */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"I2C write MSB fail ret=%d\n", ret);
+
+		return ret;
+	}
+
+	return 0;
+}
+
+static int dw9807_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct dw9807_device *dev_vcm = container_of(ctrl->handler,
+		struct dw9807_device, ctrls_vcm);
+
+	if (ctrl->id == V4L2_CID_FOCUS_ABSOLUTE) {
+		struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
+
+		dev_vcm->current_val = ctrl->val;
+		return dw9807_set_dac(client, ctrl->val);
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops dw9807_vcm_ctrl_ops = {
+	.s_ctrl = dw9807_set_ctrl,
+};
+
+static int dw9807_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	int rval;
+
+	rval = pm_runtime_get_sync(sd->dev);
+	if (rval < 0) {
+		pm_runtime_put_noidle(sd->dev);
+		return rval;
+	}
+
+	return 0;
+}
+
+static int dw9807_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	pm_runtime_put(sd->dev);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_internal_ops dw9807_int_ops = {
+	.open = dw9807_open,
+	.close = dw9807_close,
+};
+
+static const struct v4l2_subdev_ops dw9807_ops = { };
+
+static void dw9807_subdev_cleanup(struct dw9807_device *dw9807_dev)
+{
+	v4l2_async_unregister_subdev(&dw9807_dev->sd);
+	v4l2_ctrl_handler_free(&dw9807_dev->ctrls_vcm);
+	media_entity_cleanup(&dw9807_dev->sd.entity);
+}
+
+static int dw9807_init_controls(struct dw9807_device *dev_vcm)
+{
+	struct v4l2_ctrl_handler *hdl = &dev_vcm->ctrls_vcm;
+	const struct v4l2_ctrl_ops *ops = &dw9807_vcm_ctrl_ops;
+	struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
+
+	v4l2_ctrl_handler_init(hdl, 1);
+
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FOCUS_ABSOLUTE,
+			  0, DW9807_MAX_FOCUS_POS, DW9807_FOCUS_STEPS, 0);
+
+	dev_vcm->sd.ctrl_handler = hdl;
+	if (hdl->error) {
+		dev_err(&client->dev, "%s fail error: 0x%x\n",
+			__func__, hdl->error);
+		return hdl->error;
+	}
+
+	return 0;
+}
+
+static int dw9807_probe(struct i2c_client *client)
+{
+	struct dw9807_device *dw9807_dev;
+	int rval;
+
+	dw9807_dev = devm_kzalloc(&client->dev, sizeof(*dw9807_dev),
+				  GFP_KERNEL);
+	if (dw9807_dev == NULL)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&dw9807_dev->sd, client, &dw9807_ops);
+	dw9807_dev->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	dw9807_dev->sd.internal_ops = &dw9807_int_ops;
+
+	rval = dw9807_init_controls(dw9807_dev);
+	if (rval)
+		goto err_cleanup;
+
+	rval = media_entity_pads_init(&dw9807_dev->sd.entity, 0, NULL);
+	if (rval < 0)
+		goto err_cleanup;
+
+	dw9807_dev->sd.entity.function = MEDIA_ENT_F_LENS;
+
+	rval = v4l2_async_register_subdev(&dw9807_dev->sd);
+	if (rval < 0)
+		goto err_cleanup;
+
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_enable(&client->dev);
+	pm_runtime_idle(&client->dev);
+
+	return 0;
+
+err_cleanup:
+	dw9807_subdev_cleanup(dw9807_dev);
+
+	return rval;
+}
+
+static int dw9807_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+
+	pm_runtime_disable(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
+
+	dw9807_subdev_cleanup(dw9807_dev);
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position, so it consumes least current
+ * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int __maybe_unused dw9807_vcm_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+	const char tx_data[2] = { DW9807_CTL_ADDR, 0x01 };
+	int ret, val;
+
+	for (val = dw9807_dev->current_val & ~(DW9807_CTRL_STEPS - 1);
+	     val >= 0; val -= DW9807_CTRL_STEPS) {
+		ret = dw9807_set_dac(client, val);
+		if (ret)
+			dev_err_once(dev, "%s I2C failure: %d", __func__, ret);
+		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
+	}
+
+	/* Power down */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position to the value set by the user
+ * through v4l2_ctrl_ops s_ctrl handler
+ * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int  __maybe_unused dw9807_vcm_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+	const char tx_data[2] = { DW9807_CTL_ADDR, 0x00 };
+	int ret, val;
+
+	/* Power on */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
+		return ret;
+	}
+
+	for (val = dw9807_dev->current_val % DW9807_CTRL_STEPS;
+	     val < dw9807_dev->current_val + DW9807_CTRL_STEPS - 1;
+	     val += DW9807_CTRL_STEPS) {
+		ret = dw9807_set_dac(client, val);
+		if (ret)
+			dev_err_ratelimited(dev, "%s I2C failure: %d",
+						__func__, ret);
+		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id dw9807_of_table[] = {
+	{ .compatible = "dongwoon,dw9807-vcm" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, dw9807_of_table);
+
+static const struct dev_pm_ops dw9807_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume)
+	SET_RUNTIME_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume, NULL)
+};
+
+static struct i2c_driver dw9807_i2c_driver = {
+	.driver = {
+		.name = "dw9807",
+		.pm = &dw9807_pm_ops,
+		.of_match_table = dw9807_of_table,
+	},
+	.probe_new = dw9807_probe,
+	.remove = dw9807_remove,
+};
+
+module_i2c_driver(dw9807_i2c_driver);
+
+MODULE_AUTHOR("Chiang, Alan <alanx.chiang@intel.com>");
+MODULE_DESCRIPTION("DW9807 VCM driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 2ec7debd44b49927a6e2861521994cc075a389ed Mon Sep 17 00:00:00 2001
From: Javier Martinez Canillas <javierm@redhat.com>
Date: Sat, 9 Jun 2018 08:22:45 -0400
Subject: media: omap3isp: zero-initialize the isp cam_xclk{a,b} initial data

The struct clk_init_data init variable is declared in the isp_xclk_init()
function so is an automatic variable allocated in the stack. But it's not
explicitly zero-initialized, so some init fields are left uninitialized.

This causes the data structure to have undefined values that may confuse
the common clock framework when the clock is registered.

For example, the uninitialized .flags field could have the CLK_IS_CRITICAL
bit set, causing the framework to wrongly prepare the clk on registration.
This leads to the isp_xclk_prepare() callback being called, which in turn
calls to the omap3isp_get() function that increments the isp dev refcount.

Since this omap3isp_get() call is unexpected, this leads to an unbalanced
omap3isp_get() call that prevents the requested IRQ to be later enabled,
due the refcount not being 0 when the correct omap3isp_get() call happens.

Fixes: 9b28ee3c9122 ("[media] omap3isp: Use the common clock framework")

Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/omap3isp/isp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index a658c12eead1..03354d513311 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -300,7 +300,7 @@ static struct clk *isp_xclk_src_get(struct of_phandle_args *clkspec, void *data)
 static int isp_xclk_init(struct isp_device *isp)
 {
 	struct device_node *np = isp->dev->of_node;
-	struct clk_init_data init;
+	struct clk_init_data init = { 0 };
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(isp->xclks); ++i)
-- 
cgit v1.2.3


From 30ed2b83343bd1e07884ca7355dac70d25ffc158 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 10 Jun 2018 11:42:01 -0400
Subject: media: s3c-camif: ignore -ENOIOCTLCMD from v4l2_subdev_call for
 s_power

When the subdevice doesn't provide s_power core ops callback, the
v4l2_subdev_call for s_power returns -ENOIOCTLCMD.  If the subdevice
doesn't have the special handling for its power saving mode, the s_power
isn't required.  So -ENOIOCTLCMD from the v4l2_subdev_call should be
ignored.

Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Acked-by: Sylwester Nawrocki <sylvester.nawrocki@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/s3c-camif/camif-capture.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
index 9ab8e7ee2e1e..b1d9f3857d3d 100644
--- a/drivers/media/platform/s3c-camif/camif-capture.c
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -117,6 +117,8 @@ static int sensor_set_power(struct camif_dev *camif, int on)
 
 	if (camif->sensor.power_count == !on)
 		err = v4l2_subdev_call(sensor->sd, core, s_power, on);
+	if (err == -ENOIOCTLCMD)
+		err = 0;
 	if (!err)
 		sensor->power_count += on ? 1 : -1;
 
-- 
cgit v1.2.3


From 22216ec41e919682c15345e95928f266e8ba6f9e Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Sun, 10 Jun 2018 11:42:26 -0400
Subject: media: soc_camera: ov772x: correct setting of banding filter

The banding filter ON/OFF is controlled via bit 5 of COM8 register.  It
is attempted to be enabled in ov772x_set_params() by the following line.

	ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, 1);

But this unexpectedly results disabling the banding filter, because the
mask and set bits are exclusive.

On the other hand, ov772x_s_ctrl() correctly sets the bit by:

	ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, BNDF_ON_OFF);

The same fix was already applied to non-soc_camera version of ov772x
driver in the commit commit a024ee14cd36 ("media: ov772x: correct setting
of banding filter")

Cc: Jacopo Mondi <jacopo+renesas@jmondi.org>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/soc_camera/ov772x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/soc_camera/ov772x.c b/drivers/media/i2c/soc_camera/ov772x.c
index 806383500313..14377af7c888 100644
--- a/drivers/media/i2c/soc_camera/ov772x.c
+++ b/drivers/media/i2c/soc_camera/ov772x.c
@@ -834,7 +834,7 @@ static int ov772x_set_params(struct ov772x_priv *priv,
 	 * set COM8
 	 */
 	if (priv->band_filter) {
-		ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, 1);
+		ret = ov772x_mask_set(client, COM8, BNDF_ON_OFF, BNDF_ON_OFF);
 		if (!ret)
 			ret = ov772x_mask_set(client, BDBASE,
 					      0xff, 256 - priv->band_filter);
-- 
cgit v1.2.3


From 41cb1c739dcddf9905a5a3e3da9429b89cd5c616 Mon Sep 17 00:00:00 2001
From: Philipp Puschmann <pp@emlix.com>
Date: Wed, 6 Jun 2018 05:11:38 -0400
Subject: media: ov5640: adjust xclk_max

According to ov5640 datasheet xvclk is allowed to be between 6 and 54 MHz.
I run a successful test with 27 MHz.

Signed-off-by: Philipp Puschmann <pp@emlix.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov5640.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 9e1078632375..e0a6264a6a12 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -30,7 +30,7 @@
 
 /* min/typical/max system clock (xclk) frequencies */
 #define OV5640_XCLK_MIN  6000000
-#define OV5640_XCLK_MAX 24000000
+#define OV5640_XCLK_MAX 54000000
 
 #define OV5640_DEFAULT_SLAVE_ID 0x3c
 
-- 
cgit v1.2.3


From 2bbc46e811f0d40ed92ff9c104fce6618049f726 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Thu, 21 Jun 2018 05:41:21 -0400
Subject: media: v4l-common: Make v4l2_find_nearest_size more sparse-friendly

This sparse warning is emitted by using v4l2_find_nearest_size in some
cases. Fix it in the framework.

>> drivers/media/i2c/ov5640.c:1394:14: sparse: incorrect type in assignment
+(different base types) @@    expected struct ov5640_mode_info const *mode @@
+got ststruct ov5640_mode_info const *mode @@
   drivers/media/i2c/ov5640.c:1394:14:    expected struct ov5640_mode_info const
+*mode
   drivers/media/i2c/ov5640.c:1394:14:    got struct ov5640_mode_info const ( *<
+noident> )[9]

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 include/media/v4l2-common.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/media/v4l2-common.h b/include/media/v4l2-common.h
index 160bca96d524..cdc87ec61e54 100644
--- a/include/media/v4l2-common.h
+++ b/include/media/v4l2-common.h
@@ -338,7 +338,7 @@ void v4l_bound_align_image(unsigned int *width, unsigned int wmin,
 	({								\
 		BUILD_BUG_ON(sizeof((array)->width_field) != sizeof(u32) || \
 			     sizeof((array)->height_field) != sizeof(u32)); \
-		(typeof(&(*(array))))__v4l2_find_nearest_size(		\
+		(typeof(&(array)[0]))__v4l2_find_nearest_size(		\
 			(array), array_size, sizeof(*(array)),		\
 			offsetof(typeof(*(array)), width_field),	\
 			offsetof(typeof(*(array)), height_field),	\
-- 
cgit v1.2.3


From 3c4a737267e89aafa6308c6c456d2ebea3fcd085 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Wed, 20 Jun 2018 04:40:57 -0400
Subject: media: ov5640: fix frame interval enumeration

Driver must reject frame interval enumeration of unsupported resolution.
This was detected by v4l2-compliance format ioctl test:
v4l2-compliance Format ioctls:
    info: found 2 frameintervals for pixel format 4745504a and size 176x144
  fail: v4l2-test-formats.cpp(123):
                           found frame intervals for invalid size 177x144
    test VIDIOC_ENUM_FMT/FRAMESIZES/FRAMEINTERVALS: FAIL

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov5640.c | 34 ++++++++++++++++------------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index e0a6264a6a12..1ecbb7a4a2ee 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -1413,24 +1413,16 @@ static const struct ov5640_mode_info *
 ov5640_find_mode(struct ov5640_dev *sensor, enum ov5640_frame_rate fr,
 		 int width, int height, bool nearest)
 {
-	const struct ov5640_mode_info *mode = NULL;
-	int i;
-
-	for (i = OV5640_NUM_MODES - 1; i >= 0; i--) {
-		mode = &ov5640_mode_data[fr][i];
-
-		if (!mode->reg_data)
-			continue;
+	const struct ov5640_mode_info *mode;
 
-		if ((nearest && mode->hact <= width &&
-		     mode->vact <= height) ||
-		    (!nearest && mode->hact == width &&
-		     mode->vact == height))
-			break;
-	}
+	mode = v4l2_find_nearest_size(ov5640_mode_data[fr],
+				      ARRAY_SIZE(ov5640_mode_data[fr]),
+				      hact, vact,
+				      width, height);
 
-	if (nearest && i < 0)
-		mode = &ov5640_mode_data[fr][0];
+	if (!mode ||
+	    (!nearest && (mode->hact != width || mode->vact != height)))
+		return NULL;
 
 	return mode;
 }
@@ -2509,8 +2501,14 @@ static int ov5640_s_frame_interval(struct v4l2_subdev *sd,
 
 	sensor->current_fr = frame_rate;
 	sensor->frame_interval = fi->interval;
-	sensor->current_mode = ov5640_find_mode(sensor, frame_rate, mode->hact,
-						mode->vact, true);
+	mode = ov5640_find_mode(sensor, frame_rate, mode->hact,
+				mode->vact, true);
+	if (!mode) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	sensor->current_mode = mode;
 	sensor->pending_mode_change = true;
 out:
 	mutex_unlock(&sensor->lock);
-- 
cgit v1.2.3


From a319b56175ad6e9b619f9c6fddf7fde747791a7c Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 18 Jun 2018 14:25:06 +0300
Subject: pinctrl: cedarfork: Correct EAST pin ordering

The driver missed the fact that PECI_SMB_DATA has moved from EAST
community 224 to 182 instead. Correct the pin ordering accordingly.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/pinctrl-cedarfork.c | 92 +++++++++++++++----------------
 1 file changed, 46 insertions(+), 46 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-cedarfork.c b/drivers/pinctrl/intel/pinctrl-cedarfork.c
index 59216b0533d9..b2a2456f019e 100644
--- a/drivers/pinctrl/intel/pinctrl-cedarfork.c
+++ b/drivers/pinctrl/intel/pinctrl-cedarfork.c
@@ -240,51 +240,51 @@ static const struct pinctrl_pin_desc cdf_pins[] = {
 	PINCTRL_PIN(179, "GBE_GPIO10"),
 	PINCTRL_PIN(180, "GBE_GPIO11"),
 	PINCTRL_PIN(181, "GBE_GPIO12"),
-	PINCTRL_PIN(182, "SATA0_LED_N"),
-	PINCTRL_PIN(183, "SATA1_LED_N"),
-	PINCTRL_PIN(184, "SATA_PDETECT0"),
-	PINCTRL_PIN(185, "SATA_PDETECT1"),
-	PINCTRL_PIN(186, "SATA0_SDOUT"),
-	PINCTRL_PIN(187, "SATA1_SDOUT"),
-	PINCTRL_PIN(188, "SATA2_LED_N"),
-	PINCTRL_PIN(189, "SATA_PDETECT2"),
-	PINCTRL_PIN(190, "SATA2_SDOUT"),
+	PINCTRL_PIN(182, "PECI_SMB_DATA"),
+	PINCTRL_PIN(183, "SATA0_LED_N"),
+	PINCTRL_PIN(184, "SATA1_LED_N"),
+	PINCTRL_PIN(185, "SATA_PDETECT0"),
+	PINCTRL_PIN(186, "SATA_PDETECT1"),
+	PINCTRL_PIN(187, "SATA0_SDOUT"),
+	PINCTRL_PIN(188, "SATA1_SDOUT"),
+	PINCTRL_PIN(189, "SATA2_LED_N"),
+	PINCTRL_PIN(190, "SATA_PDETECT2"),
+	PINCTRL_PIN(191, "SATA2_SDOUT"),
 	/* EAST3 */
-	PINCTRL_PIN(191, "ESPI_IO0"),
-	PINCTRL_PIN(192, "ESPI_IO1"),
-	PINCTRL_PIN(193, "ESPI_IO2"),
-	PINCTRL_PIN(194, "ESPI_IO3"),
-	PINCTRL_PIN(195, "ESPI_CLK"),
-	PINCTRL_PIN(196, "ESPI_RST_N"),
-	PINCTRL_PIN(197, "ESPI_CS0_N"),
-	PINCTRL_PIN(198, "ESPI_ALRT0_N"),
-	PINCTRL_PIN(199, "ESPI_CS1_N"),
-	PINCTRL_PIN(200, "ESPI_ALRT1_N"),
-	PINCTRL_PIN(201, "ESPI_CLK_LOOPBK"),
+	PINCTRL_PIN(192, "ESPI_IO0"),
+	PINCTRL_PIN(193, "ESPI_IO1"),
+	PINCTRL_PIN(194, "ESPI_IO2"),
+	PINCTRL_PIN(195, "ESPI_IO3"),
+	PINCTRL_PIN(196, "ESPI_CLK"),
+	PINCTRL_PIN(197, "ESPI_RST_N"),
+	PINCTRL_PIN(198, "ESPI_CS0_N"),
+	PINCTRL_PIN(199, "ESPI_ALRT0_N"),
+	PINCTRL_PIN(200, "ESPI_CS1_N"),
+	PINCTRL_PIN(201, "ESPI_ALRT1_N"),
+	PINCTRL_PIN(202, "ESPI_CLK_LOOPBK"),
 	/* EAST0 */
-	PINCTRL_PIN(202, "SPI_CS0_N"),
-	PINCTRL_PIN(203, "SPI_CS1_N"),
-	PINCTRL_PIN(204, "SPI_MOSI_IO0"),
-	PINCTRL_PIN(205, "SPI_MISO_IO1"),
-	PINCTRL_PIN(206, "SPI_IO2"),
-	PINCTRL_PIN(207, "SPI_IO3"),
-	PINCTRL_PIN(208, "SPI_CLK"),
-	PINCTRL_PIN(209, "SPI_CLK_LOOPBK"),
-	PINCTRL_PIN(210, "SUSPWRDNACK"),
-	PINCTRL_PIN(211, "PMU_SUSCLK"),
-	PINCTRL_PIN(212, "ADR_COMPLETE"),
-	PINCTRL_PIN(213, "ADR_TRIGGER_N"),
-	PINCTRL_PIN(214, "PMU_SLP_S45_N"),
-	PINCTRL_PIN(215, "PMU_SLP_S3_N"),
-	PINCTRL_PIN(216, "PMU_WAKE_N"),
-	PINCTRL_PIN(217, "PMU_PWRBTN_N"),
-	PINCTRL_PIN(218, "PMU_RESETBUTTON_N"),
-	PINCTRL_PIN(219, "PMU_PLTRST_N"),
-	PINCTRL_PIN(220, "SUS_STAT_N"),
-	PINCTRL_PIN(221, "PMU_I2C_CLK"),
-	PINCTRL_PIN(222, "PMU_I2C_DATA"),
-	PINCTRL_PIN(223, "PECI_SMB_CLK"),
-	PINCTRL_PIN(224, "PECI_SMB_DATA"),
+	PINCTRL_PIN(203, "SPI_CS0_N"),
+	PINCTRL_PIN(204, "SPI_CS1_N"),
+	PINCTRL_PIN(205, "SPI_MOSI_IO0"),
+	PINCTRL_PIN(206, "SPI_MISO_IO1"),
+	PINCTRL_PIN(207, "SPI_IO2"),
+	PINCTRL_PIN(208, "SPI_IO3"),
+	PINCTRL_PIN(209, "SPI_CLK"),
+	PINCTRL_PIN(210, "SPI_CLK_LOOPBK"),
+	PINCTRL_PIN(211, "SUSPWRDNACK"),
+	PINCTRL_PIN(212, "PMU_SUSCLK"),
+	PINCTRL_PIN(213, "ADR_COMPLETE"),
+	PINCTRL_PIN(214, "ADR_TRIGGER_N"),
+	PINCTRL_PIN(215, "PMU_SLP_S45_N"),
+	PINCTRL_PIN(216, "PMU_SLP_S3_N"),
+	PINCTRL_PIN(217, "PMU_WAKE_N"),
+	PINCTRL_PIN(218, "PMU_PWRBTN_N"),
+	PINCTRL_PIN(219, "PMU_RESETBUTTON_N"),
+	PINCTRL_PIN(220, "PMU_PLTRST_N"),
+	PINCTRL_PIN(221, "SUS_STAT_N"),
+	PINCTRL_PIN(222, "PMU_I2C_CLK"),
+	PINCTRL_PIN(223, "PMU_I2C_DATA"),
+	PINCTRL_PIN(224, "PECI_SMB_CLK"),
 	PINCTRL_PIN(225, "PECI_SMB_ALRT_N"),
 	/* EMMC */
 	PINCTRL_PIN(226, "EMMC_CMD"),
@@ -315,9 +315,9 @@ static const struct intel_padgroup cdf_community0_gpps[] = {
 };
 
 static const struct intel_padgroup cdf_community1_gpps[] = {
-	CDF_GPP(0, 168, 190),	/* EAST2 */
-	CDF_GPP(1, 191, 201),	/* EAST3 */
-	CDF_GPP(2, 202, 225),	/* EAST0 */
+	CDF_GPP(0, 168, 191),	/* EAST2 */
+	CDF_GPP(1, 192, 202),	/* EAST3 */
+	CDF_GPP(2, 203, 225),	/* EAST0 */
 	CDF_GPP(3, 226, 236),	/* EMMC */
 };
 
-- 
cgit v1.2.3


From 746777012c982c251d4cb173e02494c483ce4a35 Mon Sep 17 00:00:00 2001
From: Joel Stanley <joel@jms.id.au>
Date: Mon, 18 Jun 2018 22:15:06 +0930
Subject: pinctrl: aspeed: Fix documentation

Fixes these warnings:

  pinctrl-aspeed.c:112: warning: Function parameter or member 'map' not
  described in 'aspeed_sig_desc_eval'
  pinctrl-aspeed.c:112: warning: Excess function parameter 'regmap'
  description in 'aspeed_sig_desc_eval'

Signed-off-by: Joel Stanley <joel@jms.id.au>
Reviewed-by: Andrew Jeffery <andrew@aj.id.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/aspeed/pinctrl-aspeed.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/aspeed/pinctrl-aspeed.c b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
index 7f13ce8450a3..aefe3c33dffd 100644
--- a/drivers/pinctrl/aspeed/pinctrl-aspeed.c
+++ b/drivers/pinctrl/aspeed/pinctrl-aspeed.c
@@ -95,7 +95,7 @@ static inline void aspeed_sig_desc_print_val(
  *
  * @desc: The signal descriptor of interest
  * @enabled: True to query the enabled state, false to query disabled state
- * @regmap: The IP block's regmap instance
+ * @map: The IP block's regmap instance
  *
  * Return: 1 if the descriptor's bitfield is configured to the state
  * selected by @enabled, 0 if not, and less than zero if an unrecoverable
@@ -594,7 +594,7 @@ static inline const struct aspeed_pin_config *find_pinconf_config(
 /**
  * @param: pinconf configuration parameter
  * @arg: The supported argument for @param, or -1 if any value is supported
- * @value: The register value to write to configure @arg for @param
+ * @val: The register value to write to configure @arg for @param
  *
  * The map is to be used in conjunction with the configuration array supplied
  * by the driver implementation.
-- 
cgit v1.2.3


From c1e802f68ca057a5ce73ce81eb78dd6f455ff512 Mon Sep 17 00:00:00 2001
From: Christian Lamparter <chunkeey@gmail.com>
Date: Mon, 28 May 2018 13:06:01 +0200
Subject: dt-bindings: pinctrl: qcom: add gpio-ranges, gpio-reserved-ranges

This patch adds the gpio-ranges and gpio-reserved-ranges property
definitions to the binding text files supported by the pinctrl-msm
driver framework.

gpio-ranges:
For DT-based platforms the pinctrl-msm framework currently relies
on the deprecated-for-DT gpiochip_add_pin_range() function to add
the range of GPIOs to be handled by the pin controller. Due to
interactions within gpiolib code, this causes the pinctrl-msm
driver to bail out (-517) during boot when a gpio-hog is declared.
This can be fatal and cause the system to not boot or reset
(for a detailed explanation and call-trace, refer to patch:
"pinctrl: msm: fix gpio-hog related boot issues" in this series).

gpio-reserved-ranges:
The binding has been added as a precaution since the TrustZone
firmware (aka QSEE), which is running as the hypervisor, might
have reserved certain, but undisclosed pins. Hence reading or
writing to the registers for those pins will cause an
XPU violation and this subsequently crashes the kernel.

Signed-off-by: Christian Lamparter <chunkeey@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt         | 6 ++++++
 .../devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt         | 9 +++++++++
 .../devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt         | 6 ++++++
 .../devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt         | 6 ++++++
 .../devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt         | 9 +++++++++
 .../devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt         | 9 +++++++++
 .../devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt         | 6 ++++++
 .../devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt         | 9 +++++++++
 .../devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt         | 9 +++++++++
 .../devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt         | 6 ++++++
 .../devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt         | 9 +++++++++
 .../devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt         | 9 +++++++++
 12 files changed, 93 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
index a752a4716486..c2dbb3e8d840 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,apq8064-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -67,6 +72,7 @@ Example:
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&gsbi5_uart_default>;
+		gpio-ranges = <&msmgpio 0 0 90>;
 
 		gsbi5_uart_default: gsbi5_uart_default {
 			mux {
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt
index c4ea61ac56f2..68e93d5b7ede 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,apq8084-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8960 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -154,6 +162,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 147>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 208 0>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
index 93374f478b9e..991be0cd0948 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq4019-pinctrl.txt
@@ -13,6 +13,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -64,6 +69,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 100>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 208 0>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt
index 6e88e91feb11..7ed56a1b70fc 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8064-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -67,6 +72,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&pinmux 0 0 69>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 32 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt
index 407b9443629d..6dd72f8599e9 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,ipq8074-pinctrl.txt
@@ -40,6 +40,14 @@ IPQ8074 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -148,6 +156,7 @@ Example:
 		interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 70>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt
index 1b52f01ddcb7..86ecdcfc4fb8 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,mdm9615-pinctrl.txt
@@ -40,6 +40,14 @@ MDM9615 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -127,6 +135,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 88>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 16 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
index df9a838ec5f9..cdc4787e59d2 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8660-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -62,6 +67,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 173>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 16 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt
index 498caff6029e..195a7a0ef0cc 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8916-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8916 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -162,6 +170,7 @@ Example:
 		interrupts = <0 208 0>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&tlmm 0 0 122>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt
index eb8d8aa41f20..5034eb6653c7 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8960-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8960 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -156,6 +164,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 152>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 16 0x4>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
index 453bd7c76d6b..c22e6c425d0b 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8974-pinctrl.txt
@@ -10,6 +10,11 @@ Required properties:
 - #gpio-cells : Should be two.
                 The first cell is the gpio pin number and the
                 second cell is used for optional parameters.
+- gpio-ranges: see ../gpio/gpio.txt
+
+Optional properties:
+
+- gpio-reserved-ranges: see ../gpio/gpio.txt
 
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
@@ -87,6 +92,7 @@ Example:
 
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 146>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 		interrupts = <0 208 0>;
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt
index 13cd629f896e..f15443f6e78e 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8994-pinctrl.txt
@@ -42,6 +42,14 @@ MSM8994 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -160,6 +168,7 @@ Example:
 		interrupts = <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>;
 		gpio-controller;
 		#gpio-cells = <2>;
+		gpio-ranges = <&msmgpio 0 0 146>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
 
diff --git a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
index aaf01e929eea..fa97f609fe45 100644
--- a/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/qcom,msm8996-pinctrl.txt
@@ -40,6 +40,14 @@ MSM8996 platform.
 	Definition: must be 2. Specifying the pin number and flags, as defined
 		    in <dt-bindings/gpio/gpio.h>
 
+- gpio-ranges:
+	Usage: required
+	Definition:  see ../gpio/gpio.txt
+
+- gpio-reserved-ranges:
+	Usage: optional
+	Definition: see ../gpio/gpio.txt
+
 Please refer to ../gpio/gpio.txt and ../interrupt-controller/interrupts.txt for
 a general description of GPIO and interrupt bindings.
 
@@ -180,6 +188,7 @@ Example:
 		reg = <0x01010000 0x300000>;
 		interrupts = <0 208 0>;
 		gpio-controller;
+		gpio-ranges = <&tlmm 0 0 150>;
 		#gpio-cells = <2>;
 		interrupt-controller;
 		#interrupt-cells = <2>;
-- 
cgit v1.2.3


From 4b09791ba059cc5a5ec7d69049f5d05da65b6418 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnáček <omosnace@redhat.com>
Date: Tue, 26 Jun 2018 13:04:42 +0200
Subject: cred: conditionally declare groups-related functions

The groups-related functions declared in include/linux/cred.h are
defined in kernel/groups.c, which is compiled only when
CONFIG_MULTIUSER=y. Move all these function declarations under #ifdef
CONFIG_MULTIUSER to help avoid accidental usage in contexts where
CONFIG_MULTIUSER might be disabled.

This patch also adds a fallback for groups_search(). Currently this
function is only called from kernel/groups.c itself and
security/keys/permissions.c, where the call is (by coincidence)
optimized away in case CONFIG_MULTIUSER=n. However, the audit subsystem
(which does not depend on CONFIG_MULTIUSER) calls this function in
-next, so the fallback will be needed to avoid compilation errors or
ugly workarounds.

See also:
https://lkml.org/lkml/2018/6/20/670
https://git.kernel.org/pub/scm/linux/kernel/git/pcmoore/audit.git/commit/?h=next&id=af85d1772e31fed34165a1b3decef340cf4080c0

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/cred.h | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/include/linux/cred.h b/include/linux/cred.h
index 631286535d0f..7eed6101c791 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -65,6 +65,12 @@ extern void groups_free(struct group_info *);
 
 extern int in_group_p(kgid_t);
 extern int in_egroup_p(kgid_t);
+extern int groups_search(const struct group_info *, kgid_t);
+
+extern int set_current_groups(struct group_info *);
+extern void set_groups(struct cred *, struct group_info *);
+extern bool may_setgroups(void);
+extern void groups_sort(struct group_info *);
 #else
 static inline void groups_free(struct group_info *group_info)
 {
@@ -78,12 +84,11 @@ static inline int in_egroup_p(kgid_t grp)
 {
         return 1;
 }
+static inline int groups_search(const struct group_info *group_info, kgid_t grp)
+{
+	return 1;
+}
 #endif
-extern int set_current_groups(struct group_info *);
-extern void set_groups(struct cred *, struct group_info *);
-extern int groups_search(const struct group_info *, kgid_t);
-extern bool may_setgroups(void);
-extern void groups_sort(struct group_info *);
 
 /*
  * The security context of a task
-- 
cgit v1.2.3


From 65a8766f5f50a5cd342f3d8f77a30917648ddb67 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Thu, 14 Jun 2018 16:20:05 -0400
Subject: audit: check audit_enabled in audit_tree_log_remove_rule()

Respect the audit_enabled flag when printing tree rule config change
records.

See: https://github.com/linux-audit/audit-kernel/issues/50

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
[PM: tweak the subject line]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/audit_tree.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index c99ebaae5abc..9f6eaeb6919f 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -497,6 +497,8 @@ static void audit_tree_log_remove_rule(struct audit_krule *rule)
 {
 	struct audit_buffer *ab;
 
+	if (!audit_enabled)
+		return;
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_CONFIG_CHANGE);
 	if (unlikely(!ab))
 		return;
-- 
cgit v1.2.3


From 4fa7f086993594e79f456a04656da2fcb5691209 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Thu, 14 Jun 2018 16:20:06 -0400
Subject: audit: simplify audit_enabled check in audit_watch_log_rule_change()

Check the audit_enabled flag and bail immediately.  This does not change
the functionality, but brings the code format in line with similar
checks in audit_tree_log_remove_rule(), audit_mark_log_rule_change(),
and elsewhere in the audit code.

See: https://github.com/linux-audit/audit-kernel/issues/50

Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
[PM: tweaked subject line]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/audit_watch.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index c17c0c268436..6f249bdf2d84 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -238,20 +238,21 @@ out:
 
 static void audit_watch_log_rule_change(struct audit_krule *r, struct audit_watch *w, char *op)
 {
-	if (audit_enabled) {
-		struct audit_buffer *ab;
-		ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
-		if (unlikely(!ab))
-			return;
-		audit_log_format(ab, "auid=%u ses=%u op=%s",
-				 from_kuid(&init_user_ns, audit_get_loginuid(current)),
-				 audit_get_sessionid(current), op);
-		audit_log_format(ab, " path=");
-		audit_log_untrustedstring(ab, w->path);
-		audit_log_key(ab, r->filterkey);
-		audit_log_format(ab, " list=%d res=1", r->listnr);
-		audit_log_end(ab);
-	}
+	struct audit_buffer *ab;
+
+	if (!audit_enabled)
+		return;
+	ab = audit_log_start(NULL, GFP_NOFS, AUDIT_CONFIG_CHANGE);
+	if (!ab)
+		return;
+	audit_log_format(ab, "auid=%u ses=%u op=%s",
+			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
+			 audit_get_sessionid(current), op);
+	audit_log_format(ab, " path=");
+	audit_log_untrustedstring(ab, w->path);
+	audit_log_key(ab, r->filterkey);
+	audit_log_format(ab, " list=%d res=1", r->listnr);
+	audit_log_end(ab);
 }
 
 /* Update inode info in audit rules based on filesystem event. */
-- 
cgit v1.2.3


From a7f58b9ecfd3c0f63703ec10f4a592cc38dbd1b8 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Tue, 8 May 2018 10:00:22 -0600
Subject: PCI: vmd: White list for fast interrupt handlers

Devices with slow interrupt handlers are significantly harming
performance when their interrupt vector is shared with a fast device.

Create a class code white list for devices with known fast interrupt
handlers and let all other devices share a single vector so that they
don't interfere with performance.

At the moment, only the NVM Express class code is on the list, but more
may be added if VMD users desire to use other low-latency devices in
these domains.

Signed-off-by: Keith Busch <keith.busch@intel.com>
[lorenzo.pieralisi@arm.com: changelog]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Jon Derrick: <jonathan.derrick@intel.com>
---
 drivers/pci/controller/vmd.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 942b64fc7f1f..fd2dbd7eed7b 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -197,9 +197,20 @@ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *d
 	int i, best = 1;
 	unsigned long flags;
 
-	if (pci_is_bridge(msi_desc_to_pci_dev(desc)) || vmd->msix_count == 1)
+	if (vmd->msix_count == 1)
 		return &vmd->irqs[0];
 
+	/*
+	 * White list for fast-interrupt handlers. All others will share the
+	 * "slow" interrupt vector.
+	 */
+	switch (msi_desc_to_pci_dev(desc)->class) {
+	case PCI_CLASS_STORAGE_EXPRESS:
+		break;
+	default:
+		return &vmd->irqs[0];
+	}
+
 	raw_spin_lock_irqsave(&list_lock, flags);
 	for (i = 1; i < vmd->msix_count; i++)
 		if (vmd->irqs[i].count < vmd->irqs[best].count)
-- 
cgit v1.2.3


From ef196b5c2f4fb7a701a8f189cdcba94f422c9009 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 13:01:50 +0200
Subject: drm/i915: Replace drm_connector_{un/reference} with put,get functions

This patch unifies the naming of DRM functions for reference counting
of struct drm_connector. The resulting code is more aligned with the
rest of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618110154.30462-2-tdz@users.sourceforge.net
---
 drivers/gpu/drm/i915/intel_display.c | 4 ++--
 drivers/gpu/drm/i915/intel_dp_mst.c  | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 0db23292eb35..fca72ce0b3b3 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -10737,7 +10737,7 @@ static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
 	drm_connector_list_iter_begin(dev, &conn_iter);
 	for_each_intel_connector_iter(connector, &conn_iter) {
 		if (connector->base.state->crtc)
-			drm_connector_unreference(&connector->base);
+			drm_connector_put(&connector->base);
 
 		if (connector->base.encoder) {
 			connector->base.state->best_encoder =
@@ -10745,7 +10745,7 @@ static void intel_modeset_update_connector_atomic_state(struct drm_device *dev)
 			connector->base.state->crtc =
 				connector->base.encoder->crtc;
 
-			drm_connector_reference(&connector->base);
+			drm_connector_get(&connector->base);
 		} else {
 			connector->base.state->best_encoder = NULL;
 			connector->base.state->crtc = NULL;
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 5890500a3a8b..789a403e9f99 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -524,7 +524,7 @@ static void intel_dp_destroy_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 	intel_connector->mst_port = NULL;
 	drm_modeset_unlock(&connector->dev->mode_config.connection_mutex);
 
-	drm_connector_unreference(connector);
+	drm_connector_put(connector);
 }
 
 static void intel_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
-- 
cgit v1.2.3


From 0f67706e6600cab897e1806133eea7f5000a2789 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 13:01:51 +0200
Subject: drm/i915: Replace drm_gem_object_{un/reference} with {put,get}
 functions

This patch unifies the naming of DRM functions for reference counting
of struct drm_gem_object. The resulting code is more aligned with the
rest of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618110154.30462-3-tdz@users.sourceforge.net
---
 drivers/gpu/drm/i915/i915_gem_object.h | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 54f00b350779..da6e849f41a4 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -337,13 +337,10 @@ __attribute__((nonnull))
 static inline struct drm_i915_gem_object *
 i915_gem_object_get(struct drm_i915_gem_object *obj)
 {
-	drm_gem_object_reference(&obj->base);
+	drm_gem_object_get(&obj->base);
 	return obj;
 }
 
-__deprecated
-extern void drm_gem_object_reference(struct drm_gem_object *);
-
 __attribute__((nonnull))
 static inline void
 i915_gem_object_put(struct drm_i915_gem_object *obj)
@@ -351,9 +348,6 @@ i915_gem_object_put(struct drm_i915_gem_object *obj)
 	__drm_gem_object_unreference(&obj->base);
 }
 
-__deprecated
-extern void drm_gem_object_unreference(struct drm_gem_object *);
-
 __deprecated
 extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *);
 
-- 
cgit v1.2.3


From 55f95c2723daedb44b0552c6ab10401e0bd32a22 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 13:01:52 +0200
Subject: drm/i915: Replace __drm_gem_object_unreference with
 __drm_gem_object_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_gem_object. The resulting code is more aligned with the
rest of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618110154.30462-4-tdz@users.sourceforge.net
---
 drivers/gpu/drm/i915/i915_gem_object.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index da6e849f41a4..0042496216fe 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -345,7 +345,7 @@ __attribute__((nonnull))
 static inline void
 i915_gem_object_put(struct drm_i915_gem_object *obj)
 {
-	__drm_gem_object_unreference(&obj->base);
+	__drm_gem_object_put(&obj->base);
 }
 
 __deprecated
-- 
cgit v1.2.3


From 01159b47a400fa8ba7026dd647d52e89ef7322bd Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 13:01:53 +0200
Subject: drm/i915: Replace drm_gem_object_unreference_unlocked with put
 function

This patch unifies the naming of DRM functions for reference counting
of struct drm_gem_object. The resulting code is more aligned with the
rest of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618110154.30462-5-tdz@users.sourceforge.net
---
 drivers/gpu/drm/i915/i915_gem_object.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 0042496216fe..c3c6f2e588fb 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -348,9 +348,6 @@ i915_gem_object_put(struct drm_i915_gem_object *obj)
 	__drm_gem_object_put(&obj->base);
 }
 
-__deprecated
-extern void drm_gem_object_unreference_unlocked(struct drm_gem_object *);
-
 static inline void i915_gem_object_lock(struct drm_i915_gem_object *obj)
 {
 	reservation_object_lock(obj->resv, NULL);
-- 
cgit v1.2.3


From a24362ead99ab5d39b594a7b4ff48abc9addc059 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 13:01:54 +0200
Subject: drm/i915: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618110154.30462-6-tdz@users.sourceforge.net
---
 drivers/gpu/drm/i915/selftests/huge_pages.c        | 2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_context.c  | 2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c   | 2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c    | 2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c      | 2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_object.c   | 2 +-
 drivers/gpu/drm/i915/selftests/i915_request.c      | 2 +-
 drivers/gpu/drm/i915/selftests/i915_vma.c          | 2 +-
 drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c | 2 +-
 9 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index fbe4324116d7..b5e87fcdcdae 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -1724,7 +1724,7 @@ out_unlock:
 
 	i915_modparams.enable_ppgtt = saved_ppgtt;
 
-	drm_dev_unref(&dev_priv->drm);
+	drm_dev_put(&dev_priv->drm);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 90c3c36173ba..c0c26fae45c7 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -586,7 +586,7 @@ int i915_gem_context_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
index 89dc25a5a53b..a7055b12e53c 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_dmabuf.c
@@ -389,7 +389,7 @@ int i915_gem_dmabuf_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 2dc72a984d45..8059268800fa 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -490,7 +490,7 @@ int i915_gem_evict_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index a4060238bef0..a28ee0cc6a63 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1644,7 +1644,7 @@ int i915_gem_gtt_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 2b2dde94526f..549707b9d738 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -586,7 +586,7 @@ int i915_gem_object_mock_selftests(void)
 
 	err = i915_subtests(tests, i915);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 63cd9486cc13..521ae4a90ddf 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -262,7 +262,7 @@ int i915_request_mock_selftests(void)
 		return -ENOMEM;
 
 	err = i915_subtests(tests, i915);
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/selftests/i915_vma.c b/drivers/gpu/drm/i915/selftests/i915_vma.c
index 8400a8cc5cf2..ffa74290e054 100644
--- a/drivers/gpu/drm/i915/selftests/i915_vma.c
+++ b/drivers/gpu/drm/i915/selftests/i915_vma.c
@@ -733,7 +733,7 @@ int i915_vma_mock_selftests(void)
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
 
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
index d6926e7820e5..f03b407fdbe2 100644
--- a/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/selftests/intel_breadcrumbs.c
@@ -464,7 +464,7 @@ int intel_breadcrumbs_mock_selftests(void)
 		return -ENOMEM;
 
 	err = i915_subtests(tests, i915->engine[RCS]);
-	drm_dev_unref(&i915->drm);
+	drm_dev_put(&i915->drm);
 
 	return err;
 }
-- 
cgit v1.2.3


From b0c6108ecf64fce3987f80c1610472a56d480d9a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 May 2018 10:55:01 -0400
Subject: nfs_instantiate(): prevent multiple aliases for directory inode

Since NFS allows open-by-fhandle, we have to cope with the possibility
of mkdir vs. open-by-guessed-handle races.  A local filesystem could
decide what the inumber of the new object will be and insert a locked
inode with that inumber into icache _before_ the on-disk data structures
begin to look good and unlock it only once it has a dentry alias, so
that open-by-handle coming first would quietly fail and mkdir coming
first would have open-by-handle grab its dentry.

For NFS it's a non-starter - the icache key is server-supplied fhandle
and we do not get that until the object has been fully created on server.
We really have to deal with the possibility that open-by-handle gets
the in-core inode and attaches a dentry to it before mkdir does.

Solution: let nfs_mkdir() use d_splice_alias() to catch those.  We can
	* get an error.  Just return it to our caller.
	* get NULL - no preexisting dentry aliases, we'd just done what
d_add() would've done.  Success.
	* get a reference to preexisting alias.  In that case the alias
had been moved in place of nfs_mkdir() argument (and hashed there), while
nfs_mkdir() argument is left unhashed negative.  Which is just fine for
->mkdir() callers, all we need is to release the reference we'd got from
d_splice_alias() and report success.

Cc: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/nfs/dir.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 7a9c14426855..df6fd4e5b068 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1641,6 +1641,7 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 	struct dentry *parent = dget_parent(dentry);
 	struct inode *dir = d_inode(parent);
 	struct inode *inode;
+	struct dentry *d;
 	int error = -EACCES;
 
 	d_drop(dentry);
@@ -1662,10 +1663,12 @@ int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
 			goto out_error;
 	}
 	inode = nfs_fhget(dentry->d_sb, fhandle, fattr, label);
-	error = PTR_ERR(inode);
-	if (IS_ERR(inode))
+	d = d_splice_alias(inode, dentry);
+	if (IS_ERR(d)) {
+		error = PTR_ERR(d);
 		goto out_error;
-	d_add(dentry, inode);
+	}
+	dput(d);
 out:
 	dput(parent);
 	return 0;
-- 
cgit v1.2.3


From 8cb21086cc6359c6d4f003a788050308afb211ad Mon Sep 17 00:00:00 2001
From: "Raffaello D. Di Napoli" <rafdev@dinapo.li>
Date: Mon, 25 Jun 2018 08:50:02 -0400
Subject: leds: Modify PC Engines apu/apu2 driver to support apu3

PC Engines apu3 is an improved version of the apu2, using the same SoC
and almost everything else.

This patch reuses as much as possible from the apu2 definitions, to
avoid redundancy.

Signed-off-by: Raffaello D. Di Napoli <rafdev@dinapo.li>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/Kconfig    |  5 +++--
 drivers/leds/leds-apu.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 46 insertions(+), 3 deletions(-)

diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 6e3a998f3370..44097a3e0fcc 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -57,12 +57,13 @@ config LEDS_AAT1290
 	depends on PINCTRL
 	help
 	 This option enables support for the LEDs on the AAT1290.
+
 config LEDS_APU
-	tristate "Front panel LED support for PC Engines APU/APU2 boards"
+	tristate "Front panel LED support for PC Engines APU/APU2/APU3 boards"
 	depends on LEDS_CLASS
 	depends on X86 && DMI
 	help
-	  This driver makes the PC Engines APU/APU2 front panel LEDs
+	  This driver makes the PC Engines APU/APU2/APU3 front panel LEDs
 	  accessible from userspace programs through the LED subsystem.
 
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/leds/leds-apu.c b/drivers/leds/leds-apu.c
index 8c93d68964c7..8d42e46e2de3 100644
--- a/drivers/leds/leds-apu.c
+++ b/drivers/leds/leds-apu.c
@@ -102,6 +102,13 @@ static const struct apu_led_profile apu2_led_profile[] = {
 	{ "apu2:green:3", LED_OFF, APU2_FCH_GPIO_BASE + 70 * APU2_IOSIZE },
 };
 
+/* Same as apu2_led_profile, but with "3" in the LED names. */
+static const struct apu_led_profile apu3_led_profile[] = {
+	{ "apu3:green:1", LED_ON,  APU2_FCH_GPIO_BASE + 68 * APU2_IOSIZE },
+	{ "apu3:green:2", LED_OFF, APU2_FCH_GPIO_BASE + 69 * APU2_IOSIZE },
+	{ "apu3:green:3", LED_OFF, APU2_FCH_GPIO_BASE + 70 * APU2_IOSIZE },
+};
+
 static const struct dmi_system_id apu_led_dmi_table[] __initconst = {
 	{
 		.ident = "apu",
@@ -134,6 +141,30 @@ static const struct dmi_system_id apu_led_dmi_table[] __initconst = {
 			DMI_MATCH(DMI_BOARD_NAME, "PC Engines apu2")
 		}
 	},
+	/* PC Engines APU3 with "Legacy" bios < 4.0.8 */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "APU3")
+		}
+	},
+	/* PC Engines APU3 with "Legacy" bios >= 4.0.8 */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "apu3")
+		}
+	},
+	/* PC Engines APU2 with "Mainline" bios */
+	{
+		.ident = "apu3",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "PC Engines"),
+			DMI_MATCH(DMI_BOARD_NAME, "PC Engines apu3")
+		}
+	},
 	{}
 };
 MODULE_DEVICE_TABLE(dmi, apu_led_dmi_table);
@@ -235,6 +266,14 @@ static int __init apu_led_probe(struct platform_device *pdev)
 		apu_led->platform = APU2_LED_PLATFORM;
 		apu_led->num_led_instances = ARRAY_SIZE(apu2_led_profile);
 		apu_led->iosize = APU2_IOSIZE;
+	} else if (dmi_match(DMI_BOARD_NAME, "APU3") ||
+		   dmi_match(DMI_BOARD_NAME, "apu3") ||
+		   dmi_match(DMI_BOARD_NAME, "PC Engines apu3")) {
+		apu_led->profile = apu3_led_profile;
+		/* Otherwise identical to APU2. */
+		apu_led->platform = APU2_LED_PLATFORM;
+		apu_led->num_led_instances = ARRAY_SIZE(apu3_led_profile);
+		apu_led->iosize = APU2_IOSIZE;
 	}
 
 	spin_lock_init(&apu_led->lock);
@@ -259,7 +298,10 @@ static int __init apu_led_init(void)
 	if (!(dmi_match(DMI_PRODUCT_NAME, "APU") ||
 	      dmi_match(DMI_PRODUCT_NAME, "APU2") ||
 	      dmi_match(DMI_PRODUCT_NAME, "apu2") ||
-	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu2"))) {
+	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu2") ||
+	      dmi_match(DMI_PRODUCT_NAME, "APU3") ||
+	      dmi_match(DMI_PRODUCT_NAME, "apu3") ||
+	      dmi_match(DMI_PRODUCT_NAME, "PC Engines apu3"))) {
 		pr_err("Unknown PC Engines board: %s\n",
 				dmi_get_system_info(DMI_PRODUCT_NAME));
 		return -ENODEV;
-- 
cgit v1.2.3


From 3d74243db89f9c7cea7afc471f67e15b96cc6278 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Tue, 26 Jun 2018 11:37:58 +0200
Subject: leds: triggers: don't depend on LEDS_TRIGGERS twice
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All the triggers are defined in a big if LEDS_TRIGGERS...endif block.
So there is no need to let each driver depend on LEDS_TRIGGERS explicitly
once more.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/Kconfig | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
index a2559b4fdfff..4018af769969 100644
--- a/drivers/leds/trigger/Kconfig
+++ b/drivers/leds/trigger/Kconfig
@@ -10,7 +10,6 @@ if LEDS_TRIGGERS
 
 config LEDS_TRIGGER_TIMER
 	tristate "LED Timer Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by a programmable timer
 	  via sysfs. Some LED hardware can be programmed to start
@@ -21,7 +20,6 @@ config LEDS_TRIGGER_TIMER
 
 config LEDS_TRIGGER_ONESHOT
 	tristate "LED One-shot Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to blink in one-shot pulses with parameters
 	  controlled via sysfs.  It's useful to notify the user on
@@ -36,7 +34,6 @@ config LEDS_TRIGGER_ONESHOT
 config LEDS_TRIGGER_DISK
 	bool "LED Disk Trigger"
 	depends on IDE_GD_ATA || ATA
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by disk activity.
 	  If unsure, say Y.
@@ -44,14 +41,12 @@ config LEDS_TRIGGER_DISK
 config LEDS_TRIGGER_MTD
 	bool "LED MTD (NAND/NOR) Trigger"
 	depends on MTD
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by MTD activity.
 	  If unsure, say N.
 
 config LEDS_TRIGGER_HEARTBEAT
 	tristate "LED Heartbeat Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by a CPU load average.
 	  The flash frequency is a hyperbolic function of the 1-minute
@@ -60,7 +55,6 @@ config LEDS_TRIGGER_HEARTBEAT
 
 config LEDS_TRIGGER_BACKLIGHT
 	tristate "LED backlight Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled as a backlight device: they
 	  turn off and on when the display is blanked and unblanked.
@@ -69,7 +63,6 @@ config LEDS_TRIGGER_BACKLIGHT
 
 config LEDS_TRIGGER_CPU
 	bool "LED CPU Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by active CPUs. This shows
 	  the active CPUs across an array of LEDs so you can see which
@@ -79,7 +72,6 @@ config LEDS_TRIGGER_CPU
 
 config LEDS_TRIGGER_ACTIVITY
 	tristate "LED activity Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled by an immediate CPU usage.
 	  The flash frequency and duty cycle varies from faint flashes to
@@ -88,7 +80,6 @@ config LEDS_TRIGGER_ACTIVITY
 
 config LEDS_TRIGGER_GPIO
 	tristate "LED GPIO Trigger"
-	depends on LEDS_TRIGGERS
 	depends on GPIOLIB || COMPILE_TEST
 	help
 	  This allows LEDs to be controlled by gpio events. It's good
@@ -101,7 +92,6 @@ config LEDS_TRIGGER_GPIO
 
 config LEDS_TRIGGER_DEFAULT_ON
 	tristate "LED Default ON Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be initialised in the ON state.
 	  If unsure, say Y.
@@ -111,7 +101,6 @@ comment "iptables trigger is under Netfilter config (LED target)"
 
 config LEDS_TRIGGER_TRANSIENT
 	tristate "LED Transient Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows one time activation of a transient state on
 	  GPIO/PWM based hardware.
@@ -119,7 +108,6 @@ config LEDS_TRIGGER_TRANSIENT
 
 config LEDS_TRIGGER_CAMERA
 	tristate "LED Camera Flash/Torch Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be controlled as a camera flash/torch device.
 	  This enables direct flash/torch on/off by the driver, kernel space.
@@ -127,7 +115,6 @@ config LEDS_TRIGGER_CAMERA
 
 config LEDS_TRIGGER_PANIC
 	bool "LED Panic Trigger"
-	depends on LEDS_TRIGGERS
 	help
 	  This allows LEDs to be configured to blink on a kernel panic.
 	  Enabling this option will allow to mark certain LEDs as panic indicators,
@@ -137,7 +124,7 @@ config LEDS_TRIGGER_PANIC
 
 config LEDS_TRIGGER_NETDEV
 	tristate "LED Netdev Trigger"
-	depends on NET && LEDS_TRIGGERS
+	depends on NET
 	help
 	  This allows LEDs to be controlled by network device activity.
 	  If unsure, say Y.
-- 
cgit v1.2.3


From 868ec1cad0d93365ddbb1cba2b671c6c8c9221ba Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:06 -0300
Subject: devicectree: bindings: fix location of leds common file

The leds.txt was moved and renamed. Fix references to
it accordingly.

Fixes: f67605394f0b ("devicetree/bindings: Move gpio-leds binding into leds directory")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 Documentation/devicetree/bindings/leds/common.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/leds/common.txt b/Documentation/devicetree/bindings/leds/common.txt
index 1d4afe9644b6..aa1399814a2a 100644
--- a/Documentation/devicetree/bindings/leds/common.txt
+++ b/Documentation/devicetree/bindings/leds/common.txt
@@ -31,7 +31,7 @@ Optional properties for child nodes:
      "backlight" - LED will act as a back-light, controlled by the framebuffer
 		   system
      "default-on" - LED will turn on (but for leds-gpio see "default-state"
-		    property in Documentation/devicetree/bindings/gpio/led.txt)
+		    property in Documentation/devicetree/bindings/leds/leds-gpio.txt)
      "heartbeat" - LED "double" flashes at a load average based rate
      "disk-activity" - LED indicates disk activity
      "ide-disk" - LED indicates IDE disk activity (deprecated),
-- 
cgit v1.2.3


From 30f3b42147ba6f29bc95c1bba34468740762d91b Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Wed, 27 Jun 2018 11:20:52 +0200
Subject: can: mark led trigger as broken
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The driver was suggested for deletion as it implements a subset of the
netdev trigger. It's in the way for further cleanups in the trigger
code but doesn't get an Ack by someone who can actually test and confirm
that the netdev trigger works for can devices. So marking as broken to
get forward with the cleanups.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/net/can/Kconfig | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/can/Kconfig b/drivers/net/can/Kconfig
index 2cb75988b328..7cdd0cead693 100644
--- a/drivers/net/can/Kconfig
+++ b/drivers/net/can/Kconfig
@@ -73,6 +73,12 @@ config CAN_CALC_BITTIMING
 config CAN_LEDS
 	bool "Enable LED triggers for Netlink based drivers"
 	depends on LEDS_CLASS
+	# The netdev trigger (LEDS_TRIGGER_NETDEV) should be able to do
+	# everything that this driver is doing. This is marked as broken
+	# because it uses stuff that is intended to be changed or removed.
+	# Please consider switching to the netdev trigger and confirm it
+	# fulfills your needs instead of fixing this driver.
+	depends on BROKEN
 	select LEDS_TRIGGERS
 	---help---
 	  This option adds two LED triggers for packet receive and transmit
-- 
cgit v1.2.3


From 10195b1e4411191a30456e3e60bc539531b17053 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 14:22:06 +0100
Subject: drm/i915: Show vma allocator stack when in doubt

At the moment, gem_exec_gttfill fails with a sporadic EBUSY due to us
wanting to unbind a pinned batch. Let's dump who first bound that vma to
see if that helps us identify who still unexpectedly has it pinned.

v2: We cannot allocate inside the printer (as it may be on an fs-reclaim
path), so hope for the best and build the string on the stack
v3: stack depth of 16 routinely overflows a 512 character string, limit
it to 12 to avoid unsightly truncation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628132206.8329-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_vma.c | 39 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 37 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index e82aa804cdba..d0e606e9b27a 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -21,7 +21,7 @@
  * IN THE SOFTWARE.
  *
  */
- 
+
 #include "i915_vma.h"
 
 #include "i915_drv.h"
@@ -30,6 +30,39 @@
 
 #include <drm/drm_gem.h>
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && IS_ENABLED(CONFIG_DRM_DEBUG_MM)
+
+#include <linux/stackdepot.h>
+
+static void vma_print_allocator(struct i915_vma *vma, const char *reason)
+{
+	unsigned long entries[12];
+	struct stack_trace trace = {
+		.entries = entries,
+		.max_entries = ARRAY_SIZE(entries),
+	};
+	char buf[512];
+
+	if (!vma->node.stack) {
+		DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: unknown owner\n",
+				 vma->node.start, vma->node.size, reason);
+		return;
+	}
+
+	depot_fetch_stack(vma->node.stack, &trace);
+	snprint_stack_trace(buf, sizeof(buf), &trace, 0);
+	DRM_DEBUG_DRIVER("vma.node [%08llx + %08llx] %s: inserted at %s\n",
+			 vma->node.start, vma->node.size, reason, buf);
+}
+
+#else
+
+static void vma_print_allocator(struct i915_vma *vma, const char *reason)
+{
+}
+
+#endif
+
 static void
 i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
 {
@@ -875,8 +908,10 @@ int i915_vma_unbind(struct i915_vma *vma)
 	}
 	GEM_BUG_ON(i915_vma_is_active(vma));
 
-	if (i915_vma_is_pinned(vma))
+	if (i915_vma_is_pinned(vma)) {
+		vma_print_allocator(vma, "is pinned");
 		return -EBUSY;
+	}
 
 	if (!drm_mm_node_allocated(&vma->node))
 		return 0;
-- 
cgit v1.2.3


From 3f88325c2e396658a17632a19b59958750d7ad89 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 27 Jun 2018 21:13:01 +0100
Subject: drm/i915: Reduce spinlock hold time during notify_ring() interrupt

By taking advantage of the RCU protection of the task struct, we can find
the appropriate signaler under the spinlock and then release the spinlock
before waking the task and signaling the fence.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627201304.15817-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c | 32 +++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 7a7c4a2bd778..8893e795f672 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1154,21 +1154,23 @@ static void ironlake_rps_change_irq_handler(struct drm_i915_private *dev_priv)
 
 static void notify_ring(struct intel_engine_cs *engine)
 {
+	const u32 seqno = intel_engine_get_seqno(engine);
 	struct i915_request *rq = NULL;
+	struct task_struct *tsk = NULL;
 	struct intel_wait *wait;
 
-	if (!engine->breadcrumbs.irq_armed)
+	if (unlikely(!engine->breadcrumbs.irq_armed))
 		return;
 
 	atomic_inc(&engine->irq_count);
-	set_bit(ENGINE_IRQ_BREADCRUMB, &engine->irq_posted);
+
+	rcu_read_lock();
 
 	spin_lock(&engine->breadcrumbs.irq_lock);
 	wait = engine->breadcrumbs.irq_wait;
 	if (wait) {
-		bool wakeup = engine->irq_seqno_barrier;
-
-		/* We use a callback from the dma-fence to submit
+		/*
+		 * We use a callback from the dma-fence to submit
 		 * requests after waiting on our own requests. To
 		 * ensure minimum delay in queuing the next request to
 		 * hardware, signal the fence now rather than wait for
@@ -1179,19 +1181,22 @@ static void notify_ring(struct intel_engine_cs *engine)
 		 * and to handle coalescing of multiple seqno updates
 		 * and many waiters.
 		 */
-		if (i915_seqno_passed(intel_engine_get_seqno(engine),
-				      wait->seqno)) {
+		if (i915_seqno_passed(seqno, wait->seqno)) {
 			struct i915_request *waiter = wait->request;
 
-			wakeup = true;
 			if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
 				      &waiter->fence.flags) &&
 			    intel_wait_check_request(wait, waiter))
 				rq = i915_request_get(waiter);
-		}
 
-		if (wakeup)
-			wake_up_process(wait->tsk);
+			tsk = wait->tsk;
+		} else {
+			if (engine->irq_seqno_barrier) {
+				set_bit(ENGINE_IRQ_BREADCRUMB,
+					&engine->irq_posted);
+				tsk = wait->tsk;
+			}
+		}
 	} else {
 		if (engine->breadcrumbs.irq_armed)
 			__intel_engine_disarm_breadcrumbs(engine);
@@ -1204,6 +1209,11 @@ static void notify_ring(struct intel_engine_cs *engine)
 		i915_request_put(rq);
 	}
 
+	if (tsk && tsk->state & TASK_NORMAL)
+		wake_up_process(tsk);
+
+	rcu_read_unlock();
+
 	trace_intel_engine_notify(engine, wait);
 }
 
-- 
cgit v1.2.3


From 69dc4d003e3b7c262fd5fea3f25852e853eb6d4f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 27 Jun 2018 21:13:02 +0100
Subject: drm/i915: Only trigger missed-seqno checking next to boundary

If we have more interrupts pending (because we know there are more
breadcrumb signals before the completion), then we do not need to
trigger an irq_seqno_barrier or even wakeup the task on this interrupt
as there will be another. To allow some margin of error (we are trying
to work around incoherent seqno after all), we wakeup the breadcrumb
before the target as well as on the target.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627201304.15817-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 8893e795f672..4f137eeaf395 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1191,7 +1191,8 @@ static void notify_ring(struct intel_engine_cs *engine)
 
 			tsk = wait->tsk;
 		} else {
-			if (engine->irq_seqno_barrier) {
+			if (engine->irq_seqno_barrier &&
+			    i915_seqno_passed(seqno, wait->seqno - 1)) {
 				set_bit(ENGINE_IRQ_BREADCRUMB,
 					&engine->irq_posted);
 				tsk = wait->tsk;
-- 
cgit v1.2.3


From 78796877c37cb2c3898c4bcd2a12238d83858287 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 27 Jun 2018 21:13:03 +0100
Subject: drm/i915: Move the irq_counter inside the spinlock

Rather than have multiple locked instructions inside the notify_ring()
irq handler, move them inside the spinlock and reduce their intrinsic
locking.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627201304.15817-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c          |  4 ++--
 drivers/gpu/drm/i915/i915_request.c      |  4 ++--
 drivers/gpu/drm/i915/intel_breadcrumbs.c | 11 +++++++----
 drivers/gpu/drm/i915/intel_ringbuffer.h  |  2 +-
 4 files changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4f137eeaf395..c81b4c1877cc 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1162,8 +1162,6 @@ static void notify_ring(struct intel_engine_cs *engine)
 	if (unlikely(!engine->breadcrumbs.irq_armed))
 		return;
 
-	atomic_inc(&engine->irq_count);
-
 	rcu_read_lock();
 
 	spin_lock(&engine->breadcrumbs.irq_lock);
@@ -1198,6 +1196,8 @@ static void notify_ring(struct intel_engine_cs *engine)
 				tsk = wait->tsk;
 			}
 		}
+
+		engine->breadcrumbs.irq_count++;
 	} else {
 		if (engine->breadcrumbs.irq_armed)
 			__intel_engine_disarm_breadcrumbs(engine);
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index e1dbb544046f..39b296878ba2 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1196,7 +1196,7 @@ static bool __i915_spin_request(const struct i915_request *rq,
 	 * takes to sleep on a request, on the order of a microsecond.
 	 */
 
-	irq = atomic_read(&engine->irq_count);
+	irq = READ_ONCE(engine->breadcrumbs.irq_count);
 	timeout_us += local_clock_us(&cpu);
 	do {
 		if (i915_seqno_passed(intel_engine_get_seqno(engine), seqno))
@@ -1208,7 +1208,7 @@ static bool __i915_spin_request(const struct i915_request *rq,
 		 * assume we won't see one in the near future but require
 		 * the engine->seqno_barrier() to fixup coherency.
 		 */
-		if (atomic_read(&engine->irq_count) != irq)
+		if (READ_ONCE(engine->breadcrumbs.irq_count) != irq)
 			break;
 
 		if (signal_pending_state(state, current))
diff --git a/drivers/gpu/drm/i915/intel_breadcrumbs.c b/drivers/gpu/drm/i915/intel_breadcrumbs.c
index 86a987b8ac66..1db6ba7d926e 100644
--- a/drivers/gpu/drm/i915/intel_breadcrumbs.c
+++ b/drivers/gpu/drm/i915/intel_breadcrumbs.c
@@ -98,12 +98,14 @@ static void intel_breadcrumbs_hangcheck(struct timer_list *t)
 	struct intel_engine_cs *engine =
 		from_timer(engine, t, breadcrumbs.hangcheck);
 	struct intel_breadcrumbs *b = &engine->breadcrumbs;
+	unsigned int irq_count;
 
 	if (!b->irq_armed)
 		return;
 
-	if (b->hangcheck_interrupts != atomic_read(&engine->irq_count)) {
-		b->hangcheck_interrupts = atomic_read(&engine->irq_count);
+	irq_count = READ_ONCE(b->irq_count);
+	if (b->hangcheck_interrupts != irq_count) {
+		b->hangcheck_interrupts = irq_count;
 		mod_timer(&b->hangcheck, wait_timeout());
 		return;
 	}
@@ -272,13 +274,14 @@ static bool use_fake_irq(const struct intel_breadcrumbs *b)
 	if (!test_bit(engine->id, &engine->i915->gpu_error.missed_irq_rings))
 		return false;
 
-	/* Only start with the heavy weight fake irq timer if we have not
+	/*
+	 * Only start with the heavy weight fake irq timer if we have not
 	 * seen any interrupts since enabling it the first time. If the
 	 * interrupts are still arriving, it means we made a mistake in our
 	 * engine->seqno_barrier(), a timing error that should be transient
 	 * and unlikely to reoccur.
 	 */
-	return atomic_read(&engine->irq_count) == b->hangcheck_interrupts;
+	return READ_ONCE(b->irq_count) == b->hangcheck_interrupts;
 }
 
 static void enable_fake_irq(struct intel_breadcrumbs *b)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index a0bc7a8222b4..44ac90ec540c 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -345,7 +345,6 @@ struct intel_engine_cs {
 	struct drm_i915_gem_object *default_state;
 	void *pinned_default_state;
 
-	atomic_t irq_count;
 	unsigned long irq_posted;
 #define ENGINE_IRQ_BREADCRUMB 0
 #define ENGINE_IRQ_EXECLIST 1
@@ -380,6 +379,7 @@ struct intel_engine_cs {
 
 		unsigned int hangcheck_interrupts;
 		unsigned int irq_enabled;
+		unsigned int irq_count;
 
 		bool irq_armed : 1;
 		I915_SELFTEST_DECLARE(bool mock : 1);
-- 
cgit v1.2.3


From e3be4079ea91c8b7bcb97cf44889ec5663c55fb4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 27 Jun 2018 21:13:04 +0100
Subject: drm/i915: Only signal from interrupt when requested

Avoid calling dma_fence_signal() from inside the interrupt if we haven't
enabled signaling on the request.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627201304.15817-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c         | 8 ++++++--
 drivers/gpu/drm/i915/i915_request.c     | 2 +-
 drivers/gpu/drm/i915/intel_ringbuffer.h | 5 ++---
 3 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c81b4c1877cc..4be56aec99b3 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1182,7 +1182,8 @@ static void notify_ring(struct intel_engine_cs *engine)
 		if (i915_seqno_passed(seqno, wait->seqno)) {
 			struct i915_request *waiter = wait->request;
 
-			if (!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+			if (waiter &&
+			    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
 				      &waiter->fence.flags) &&
 			    intel_wait_check_request(wait, waiter))
 				rq = i915_request_get(waiter);
@@ -1205,8 +1206,11 @@ static void notify_ring(struct intel_engine_cs *engine)
 	spin_unlock(&engine->breadcrumbs.irq_lock);
 
 	if (rq) {
-		dma_fence_signal(&rq->fence);
+		spin_lock(&rq->lock);
+		dma_fence_signal_locked(&rq->fence);
 		GEM_BUG_ON(!i915_request_completed(rq));
+		spin_unlock(&rq->lock);
+
 		i915_request_put(rq);
 	}
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 39b296878ba2..a2f7e9358450 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1285,7 +1285,7 @@ long i915_request_wait(struct i915_request *rq,
 	if (flags & I915_WAIT_LOCKED)
 		add_wait_queue(errq, &reset);
 
-	intel_wait_init(&wait, rq);
+	intel_wait_init(&wait);
 
 restart:
 	do {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 44ac90ec540c..78f01a35823a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -928,11 +928,10 @@ static inline u32 intel_hws_preempt_done_address(struct intel_engine_cs *engine)
 /* intel_breadcrumbs.c -- user interrupt bottom-half for waiters */
 int intel_engine_init_breadcrumbs(struct intel_engine_cs *engine);
 
-static inline void intel_wait_init(struct intel_wait *wait,
-				   struct i915_request *rq)
+static inline void intel_wait_init(struct intel_wait *wait)
 {
 	wait->tsk = current;
-	wait->request = rq;
+	wait->request = NULL;
 }
 
 static inline void intel_wait_init_for_seqno(struct intel_wait *wait, u32 seqno)
-- 
cgit v1.2.3


From 97c8580e85cf81cbc785102a1180f81ff431b1f0 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 22 Jun 2018 10:55:47 -0700
Subject: MIPS: Annotate cpu_wait implementations with __cpuidle

Annotate cpu_wait implementations using the __cpuidle macro which
places these functions in the .cpuidle.text section. This allows
cpu_in_idle() to return true for PC values which fall within these
functions, allowing nmi_backtrace() to produce cleaner output for CPUs
running idle functions. For example:

  # echo l >/proc/sysrq-trigger
  [   38.587170] sysrq: SysRq : Show backtrace of all active CPUs
  [   38.593657] NMI backtrace for cpu 1
  [   38.597611] CPU: 1 PID: 161 Comm: sh Not tainted 4.18.0-rc1+ #27
  [   38.604306] Stack : 00000000 00000004 00000006 80486724 00000000 00000000 00000000 00000000
  [   38.613647]         80e17eda 00000034 00000000 00000000 80d20000 80b67e98 8e559c90 0ffe1e88
  [   38.622986]         00000000 00000000 80e70000 00000000 8f61db18 38312e34 722d302e 202b3163
  [   38.632324]         8e559d3c 8e559adc 00000001 6b636162 80d20000 80000000 00000000 80d1cfa4
  [   38.641664]         00000001 80d20000 80d19520 00000000 00000003 80836724 00000004 80e10004
  [   38.650993]         ...
  [   38.653724] Call Trace:
  [   38.656499] [<8040cdd0>] show_stack+0xa0/0x144
  [   38.661475] [<80b67e98>] dump_stack+0xe8/0x120
  [   38.666455] [<80b6f6d4>] nmi_cpu_backtrace+0x1b4/0x1cc
  [   38.672189] [<80b6f81c>] nmi_trigger_cpumask_backtrace+0x130/0x1e4
  [   38.679081] [<808295d8>] __handle_sysrq+0xc0/0x180
  [   38.684421] [<80829b84>] write_sysrq_trigger+0x50/0x64
  [   38.690176] [<8061c984>] proc_reg_write+0xd0/0xfc
  [   38.695447] [<805aac1c>] __vfs_write+0x54/0x194
  [   38.700500] [<805aaf24>] vfs_write+0xe0/0x18c
  [   38.705360] [<805ab190>] ksys_write+0x7c/0xf0
  [   38.710238] [<80416018>] syscall_common+0x34/0x58
  [   38.715558] Sending NMI from CPU 1 to CPUs 0,2-3:
  [   38.720916] NMI backtrace for cpu 0 skipped: idling at r4k_wait_irqoff+0x2c/0x34
  [   38.729186] NMI backtrace for cpu 3 skipped: idling at r4k_wait_irqoff+0x2c/0x34
  [   38.737449] NMI backtrace for cpu 2 skipped: idling at r4k_wait_irqoff+0x2c/0x34

Without this we get register value & backtrace output from all CPUs,
which is generally useless for those running the idle function & serves
only to overwhelm & obfuscate the meaningful output from non-idle CPUs.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/19598/
---
 arch/mips/kernel/idle.c       | 12 ++++++------
 arch/mips/vr41xx/common/pmu.c |  3 ++-
 2 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 7c246b69c545..046846999efd 100644
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -33,21 +33,21 @@
 void (*cpu_wait)(void);
 EXPORT_SYMBOL(cpu_wait);
 
-static void r3081_wait(void)
+static void __cpuidle r3081_wait(void)
 {
 	unsigned long cfg = read_c0_conf();
 	write_c0_conf(cfg | R30XX_CONF_HALT);
 	local_irq_enable();
 }
 
-static void r39xx_wait(void)
+static void __cpuidle r39xx_wait(void)
 {
 	if (!need_resched())
 		write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
 	local_irq_enable();
 }
 
-void r4k_wait(void)
+void __cpuidle r4k_wait(void)
 {
 	local_irq_enable();
 	__r4k_wait();
@@ -60,7 +60,7 @@ void r4k_wait(void)
  * interrupt is requested" restriction in the MIPS32/MIPS64 architecture makes
  * using this version a gamble.
  */
-void r4k_wait_irqoff(void)
+void __cpuidle r4k_wait_irqoff(void)
 {
 	if (!need_resched())
 		__asm__(
@@ -75,7 +75,7 @@ void r4k_wait_irqoff(void)
  * The RM7000 variant has to handle erratum 38.	 The workaround is to not
  * have any pending stores when the WAIT instruction is executed.
  */
-static void rm7k_wait_irqoff(void)
+static void __cpuidle rm7k_wait_irqoff(void)
 {
 	if (!need_resched())
 		__asm__(
@@ -96,7 +96,7 @@ static void rm7k_wait_irqoff(void)
  * since coreclock (and the cp0 counter) stops upon executing it. Only an
  * interrupt can wake it, so they must be enabled before entering idle modes.
  */
-static void au1k_wait(void)
+static void __cpuidle au1k_wait(void)
 {
 	unsigned long c0status = read_c0_status() | 1;	/* irqs on */
 
diff --git a/arch/mips/vr41xx/common/pmu.c b/arch/mips/vr41xx/common/pmu.c
index 39a0db3e2b34..16e684b59875 100644
--- a/arch/mips/vr41xx/common/pmu.c
+++ b/arch/mips/vr41xx/common/pmu.c
@@ -17,6 +17,7 @@
  *  along with this program; if not, write to the Free Software
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
+#include <linux/cpu.h>
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/ioport.h>
@@ -46,7 +47,7 @@ static void __iomem *pmu_base;
 #define pmu_read(offset)		readw(pmu_base + (offset))
 #define pmu_write(offset, value)	writew((value), pmu_base + (offset))
 
-static void vr41xx_cpu_wait(void)
+static void __cpuidle vr41xx_cpu_wait(void)
 {
 	local_irq_disable();
 	if (!need_resched())
-- 
cgit v1.2.3


From 8e5c88bfbb8cca797e9e108abf6ef63028f678d8 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Fri, 22 Jun 2018 23:29:28 -0700
Subject: MIPS: ath25: Convert random_ether_addr to eth_random_addr

random_ether_addr is a #define for eth_random_addr which is
generally preferred in kernel code by ~3:1

Convert the uses of random_ether_addr to enable removing the #define

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19600/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/ath25/board.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/mips/ath25/board.c b/arch/mips/ath25/board.c
index 6d11ae581ea7..989e71015ee6 100644
--- a/arch/mips/ath25/board.c
+++ b/arch/mips/ath25/board.c
@@ -146,10 +146,10 @@ int __init ath25_find_config(phys_addr_t base, unsigned long size)
 			pr_info("Fixing up empty mac addresses\n");
 			config->reset_config_gpio = 0xffff;
 			config->sys_led_gpio = 0xffff;
-			random_ether_addr(config->wlan0_mac);
+			eth_random_addr(config->wlan0_mac);
 			config->wlan0_mac[0] &= ~0x06;
-			random_ether_addr(config->enet0_mac);
-			random_ether_addr(config->enet1_mac);
+			eth_random_addr(config->enet0_mac);
+			eth_random_addr(config->enet1_mac);
 		}
 	}
 
-- 
cgit v1.2.3


From 344ebf09949c31bcb8818d8458b65add29f1d67b Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 18 Jun 2018 17:37:59 -0700
Subject: MIPS: Always use -march=<arch>, not -<arch> shortcuts

The VDSO Makefile filters CFLAGS to select a subset which it uses whilst
building the VDSO ELF. One of the flags it allows through is the -march=
flag that selects the architecture/ISA to target.

Unfortunately in cases where CONFIG_CPU_MIPS32_R{1,2}=y and the
toolchain defaults to building for MIPS64, the main MIPS Makefile ends
up using the short-form -<arch> flags in cflags-y. This is because the
calls to cc-option always fail to use the long-form -march=<arch> flag
due to the lack of an -mabi=<abi> flag in KBUILD_CFLAGS at the point
where the cc-option function is executed. The resulting GCC invocation
is something like:

  $ mips64-linux-gcc -Werror -march=mips32r2 -c -x c /dev/null -o tmp
  cc1: error: '-march=mips32r2' is not compatible with the selected ABI

These short-form -<arch> flags are dropped by the VDSO Makefile's
filtering, and so we attempt to build the VDSO without specifying any
architecture. This results in an attempt to build the VDSO using
whatever the compiler's default architecture is, regardless of whether
that is suitable for the kernel configuration.

One encountered build failure resulting from this mismatch is a
rejection of the sync instruction if the kernel is configured for a
MIPS32 or MIPS64 r1 or r2 target but the toolchain defaults to an older
architecture revision such as MIPS1 which did not include the sync
instruction:

    CC      arch/mips/vdso/gettimeofday.o
  /tmp/ccGQKoOj.s: Assembler messages:
  /tmp/ccGQKoOj.s:273: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:329: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:520: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:714: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1009: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1066: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1114: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1279: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1334: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1374: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1459: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1514: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:1814: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:2002: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  /tmp/ccGQKoOj.s:2066: Error: opcode not supported on this processor: mips1 (mips1) `sync'
  make[2]: *** [scripts/Makefile.build:318: arch/mips/vdso/gettimeofday.o] Error 1
  make[1]: *** [scripts/Makefile.build:558: arch/mips/vdso] Error 2
  make[1]: *** Waiting for unfinished jobs....

This can be reproduced for example by attempting to build
pistachio_defconfig using Arnd's GCC 8.1.0 mips64 toolchain from
kernel.org:

  https://mirrors.edge.kernel.org/pub/tools/crosstool/files/bin/x86_64/8.1.0/x86_64-gcc-8.1.0-nolibc-mips64-linux.tar.xz

Resolve this problem by using the long-form -march=<arch> in all cases,
which makes it through the arch/mips/vdso/Makefile's filtering & is thus
consistently used to build both the kernel proper & the VDSO.

The use of cc-option to prefer the long-form & fall back to the
short-form flags makes no sense since the short-form is just an
abbreviation for the also-supported long-form in all GCC versions that
we support building with. This means there is no case in which we have
to use the short-form -<arch> flags, so we can simply remove them.

The manual redefinition of _MIPS_ISA is removed naturally along with the
use of the short-form flags that it accompanied, and whilst here we
remove the separate assembler ISA selection. I suspect that both of
these were only required due to the mips32 vs mips2 mismatch that was
introduced by commit 59b3e8e9aac6 ("[MIPS] Makefile crapectomy.") and
fixed but not cleaned up by commit 9200c0b2a07c ("[MIPS] Fix Makefile
bugs for MIPS32/MIPS64 R1 and R2.").

I've marked this for backport as far as v4.4 where the MIPS VDSO was
introduced. In earlier kernels there should be no ill effect to using
the short-form flags.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: stable@vger.kernel.org # v4.4+
Reviewed-by: James Hogan <jhogan@kernel.org>
Patchwork: https://patchwork.linux-mips.org/patch/19579/
---
 arch/mips/Makefile | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index e2122cca4ae2..1e98d22ec119 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -155,15 +155,11 @@ cflags-$(CONFIG_CPU_R4300)	+= -march=r4300 -Wa,--trap
 cflags-$(CONFIG_CPU_VR41XX)	+= -march=r4100 -Wa,--trap
 cflags-$(CONFIG_CPU_R4X00)	+= -march=r4600 -Wa,--trap
 cflags-$(CONFIG_CPU_TX49XX)	+= -march=r4600 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R1)	+= $(call cc-option,-march=mips32,-mips32 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-			-Wa,-mips32 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS32_R2)	+= $(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-			-Wa,-mips32r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R1)	+= -march=mips32 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS32_R2)	+= -march=mips32r2 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS32_R6)	+= -march=mips32r6 -Wa,--trap -modd-spreg
-cflags-$(CONFIG_CPU_MIPS64_R1)	+= $(call cc-option,-march=mips64,-mips64 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
-			-Wa,-mips64 -Wa,--trap
-cflags-$(CONFIG_CPU_MIPS64_R2)	+= $(call cc-option,-march=mips64r2,-mips64r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS64) \
-			-Wa,-mips64r2 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R1)	+= -march=mips64 -Wa,--trap
+cflags-$(CONFIG_CPU_MIPS64_R2)	+= -march=mips64r2 -Wa,--trap
 cflags-$(CONFIG_CPU_MIPS64_R6)	+= -march=mips64r6 -Wa,--trap
 cflags-$(CONFIG_CPU_R5000)	+= -march=r5000 -Wa,--trap
 cflags-$(CONFIG_CPU_R5432)	+= $(call cc-option,-march=r5400,-march=r5000) \
-- 
cgit v1.2.3


From 6b5939d2e528525a1514adabe635f5f8f7328744 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 11 Jun 2018 10:44:22 +0200
Subject: MIPS: AR7: Normalize clk API

Coldfire still provides its own variant of the clk API rather than using
the generic COMMON_CLK API.  This generally works, but it causes some
link errors with drivers using the clk_round_rate(), clk_set_rate(),
clk_set_parent(), or clk_get_parent() functions when a platform lacks
those interfaces.

This adds empty stub implementations for each of them, and I don't even
try to do something useful here but instead just print a WARN() message
to make it obvious what is going on if they ever end up being called.

The drivers that call these won't be used on these platforms (otherwise
we'd get a link error today), so the added code is harmless bloat and
will warn about accidental use.

Based on commit bd7fefe1f06ca6cc ("ARM: w90x900: normalize clk API").

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19503/
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: linux-m68k@lists.linux-m68k.org
Cc: linux-mips@linux-mips.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/ar7/clock.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c
index 0137656107a9..6b64fd96dba8 100644
--- a/arch/mips/ar7/clock.c
+++ b/arch/mips/ar7/clock.c
@@ -476,3 +476,32 @@ void __init ar7_init_clocks(void)
 	/* adjust vbus clock rate */
 	vbus_clk.rate = bus_clk.rate / 2;
 }
+
+/* dummy functions, should not be called */
+long clk_round_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_round_rate);
+
+int clk_set_rate(struct clk *clk, unsigned long rate)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_rate);
+
+int clk_set_parent(struct clk *clk, struct clk *parent)
+{
+	WARN_ON(clk);
+	return 0;
+}
+EXPORT_SYMBOL(clk_set_parent);
+
+struct clk *clk_get_parent(struct clk *clk)
+{
+	WARN_ON(clk);
+	return NULL;
+}
+EXPORT_SYMBOL(clk_get_parent);
-- 
cgit v1.2.3


From 689adf0d4892680f5998ea424e0ace560b492dc2 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Thu, 31 May 2018 15:29:42 +0300
Subject: net/mlx5e: Add UDP GSO support

This patch enables UDP GSO support. We enable this by using two WQEs
the first is a UDP LSO WQE for all segments with equal length, and the
second is for the last segment in case it has different length.
Due to HW limitation, before sending, we must adjust the packet length fields.

We measure performance between two Intel(R) Xeon(R) CPU E5-2643 v2 @3.50GHz
machines connected back-to-back with Connectx4-Lx (40Gbps) NICs.
We compare single stream UDP, UDP GSO and UDP GSO with offload.
Performance:
		| MSS (bytes)	| Throughput (Gbps)	| CPU utilization (%)
UDP GSO offload	| 1472		| 35.6			| 8%
UDP GSO 	| 1472		| 25.5			| 17%
UDP 		| 1472		| 10.2			| 17%
UDP GSO offload	| 1024		| 35.6			| 8%
UDP GSO		| 1024		| 19.2			| 17%
UDP 		| 1024		| 5.7			| 17%
UDP GSO offload	| 512		| 33.8			| 16%
UDP GSO		| 512		| 10.4			| 17%
UDP 		| 512		| 3.5			| 17%

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Yossi Kuperman <yossiku@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   4 +-
 .../mellanox/mlx5/core/en_accel/en_accel.h         |  11 ++-
 .../ethernet/mellanox/mlx5/core/en_accel/rxtx.c    | 108 +++++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/en_accel/rxtx.h    |  14 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c    |   8 +-
 6 files changed, 139 insertions(+), 9 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9efbf193ad5a..d923f2f58608 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \
-		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
+		en_tx.o en_rx.o en_dim.o en_txrx.o en_accel/rxtx.o en_stats.o  \
+		vxlan.o en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index f20074dbef32..39a5d13ba459 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -34,12 +34,11 @@
 #ifndef __MLX5E_EN_ACCEL_H__
 #define __MLX5E_EN_ACCEL_H__
 
-#ifdef CONFIG_MLX5_ACCEL
-
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
+#include "en_accel/rxtx.h"
 #include "en.h"
 
 static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
@@ -64,9 +63,13 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
 	}
 #endif
 
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
+		skb = mlx5e_udp_gso_handle_tx_skb(dev, sq, skb, wqe, pi);
+		if (unlikely(!skb))
+			return NULL;
+	}
+
 	return skb;
 }
 
-#endif /* CONFIG_MLX5_ACCEL */
-
 #endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
new file mode 100644
index 000000000000..4bb1f3b12b96
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
@@ -0,0 +1,108 @@
+#include "en_accel/rxtx.h"
+
+static void mlx5e_udp_gso_prepare_last_skb(struct sk_buff *skb,
+					   struct sk_buff *nskb,
+					   int remaining)
+{
+	int bytes_needed = remaining, remaining_headlen, remaining_page_offset;
+	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+	int payload_len = remaining + sizeof(struct udphdr);
+	int k = 0, i, j;
+
+	skb_copy_bits(skb, 0, nskb->data, headlen);
+	nskb->dev = skb->dev;
+	skb_reset_mac_header(nskb);
+	skb_set_network_header(nskb, skb_network_offset(skb));
+	skb_set_transport_header(nskb, skb_transport_offset(skb));
+	skb_set_tail_pointer(nskb, headlen);
+
+	/* How many frags do we need? */
+	for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
+		bytes_needed -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
+		k++;
+		if (bytes_needed <= 0)
+			break;
+	}
+
+	/* Fill the first frag and split it if necessary */
+	j = skb_shinfo(skb)->nr_frags - k;
+	remaining_page_offset = -bytes_needed;
+	skb_fill_page_desc(nskb, 0,
+			   skb_shinfo(skb)->frags[j].page.p,
+			   skb_shinfo(skb)->frags[j].page_offset + remaining_page_offset,
+			   skb_shinfo(skb)->frags[j].size - remaining_page_offset);
+
+	skb_frag_ref(skb, j);
+
+	/* Fill the rest of the frags */
+	for (i = 1; i < k; i++) {
+		j = skb_shinfo(skb)->nr_frags - k + i;
+
+		skb_fill_page_desc(nskb, i,
+				   skb_shinfo(skb)->frags[j].page.p,
+				   skb_shinfo(skb)->frags[j].page_offset,
+				   skb_shinfo(skb)->frags[j].size);
+		skb_frag_ref(skb, j);
+	}
+	skb_shinfo(nskb)->nr_frags = k;
+
+	remaining_headlen = remaining - skb->data_len;
+
+	/* headlen contains remaining data? */
+	if (remaining_headlen > 0)
+		skb_copy_bits(skb, skb->len - remaining, nskb->data + headlen,
+			      remaining_headlen);
+	nskb->len = remaining + headlen;
+	nskb->data_len =  payload_len - sizeof(struct udphdr) +
+		max_t(int, 0, remaining_headlen);
+	nskb->protocol = skb->protocol;
+	if (nskb->protocol == htons(ETH_P_IP)) {
+		ip_hdr(nskb)->id = htons(ntohs(ip_hdr(nskb)->id) +
+					 skb_shinfo(skb)->gso_segs);
+		ip_hdr(nskb)->tot_len =
+			htons(payload_len + sizeof(struct iphdr));
+	} else {
+		ipv6_hdr(nskb)->payload_len = htons(payload_len);
+	}
+	udp_hdr(nskb)->len = htons(payload_len);
+	skb_shinfo(nskb)->gso_size = 0;
+	nskb->ip_summed = skb->ip_summed;
+	nskb->csum_start = skb->csum_start;
+	nskb->csum_offset = skb->csum_offset;
+	nskb->queue_mapping = skb->queue_mapping;
+}
+
+/* might send skbs and update wqe and pi */
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+					    struct mlx5e_txqsq *sq,
+					    struct sk_buff *skb,
+					    struct mlx5e_tx_wqe **wqe,
+					    u16 *pi)
+{
+	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
+	int remaining = (skb->len - headlen) % skb_shinfo(skb)->gso_size;
+	struct sk_buff *nskb;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		ip_hdr(skb)->tot_len = htons(payload_len + sizeof(struct iphdr));
+	else
+		ipv6_hdr(skb)->payload_len = htons(payload_len);
+	udp_hdr(skb)->len = htons(payload_len);
+	if (!remaining)
+		return skb;
+
+	nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC);
+	if (unlikely(!nskb)) {
+		sq->stats->dropped++;
+		return NULL;
+	}
+
+	mlx5e_udp_gso_prepare_last_skb(skb, nskb, remaining);
+
+	skb_shinfo(skb)->gso_segs--;
+	pskb_trim(skb, skb->len - remaining);
+	mlx5e_sq_xmit(sq, skb, *wqe, *pi);
+	mlx5e_sq_fetch_wqe(sq, wqe, pi);
+	return nskb;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
new file mode 100644
index 000000000000..ed42699a78b3
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
@@ -0,0 +1,14 @@
+
+#ifndef __MLX5E_EN_ACCEL_RX_TX_H__
+#define __MLX5E_EN_ACCEL_RX_TX_H__
+
+#include <linux/skbuff.h>
+#include "en.h"
+
+struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
+					    struct mlx5e_txqsq *sq,
+					    struct sk_buff *skb,
+					    struct mlx5e_tx_wqe **wqe,
+					    u16 *pi);
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 134f20a182b5..e2ef68b1daa2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4592,6 +4592,9 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->features         |= NETIF_F_HIGHDMA;
 	netdev->features         |= NETIF_F_HW_VLAN_STAG_FILTER;
 
+	netdev->features         |= NETIF_F_GSO_UDP_L4;
+	netdev->hw_features      |= NETIF_F_GSO_UDP_L4;
+
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f29deb44bf3b..f450d9ca31fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -228,7 +228,10 @@ mlx5e_tx_get_gso_ihs(struct mlx5e_txqsq *sq, struct sk_buff *skb)
 		stats->tso_inner_packets++;
 		stats->tso_inner_bytes += skb->len - ihs;
 	} else {
-		ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
+		else
+			ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
 		stats->tso_packets++;
 		stats->tso_bytes += skb->len - ihs;
 	}
@@ -443,12 +446,11 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	sq = priv->txq2sq[skb_get_queue_mapping(skb)];
 	mlx5e_sq_fetch_wqe(sq, &wqe, &pi);
 
-#ifdef CONFIG_MLX5_ACCEL
 	/* might send skbs and update wqe and pi */
 	skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi);
 	if (unlikely(!skb))
 		return NETDEV_TX_OK;
-#endif
+
 	return mlx5e_sq_xmit(sq, skb, wqe, pi);
 }
 
-- 
cgit v1.2.3


From bc5a7ccd9a6025e2ba555ab7dcd5043e2bfde315 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Mon, 11 Jun 2018 17:24:58 +0300
Subject: net/mlx5e: Add UDP GSO remaining counter

This patch adds a counter for tx UDP GSO packets that contain a segment
that is not aligned to MSS - remaining segment.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c      | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h      | 2 ++
 3 files changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
index 4bb1f3b12b96..7b7ec3998e84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
@@ -92,6 +92,7 @@ struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
 	if (!remaining)
 		return skb;
 
+	sq->stats->udp_seg_rem++;
 	nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC);
 	if (unlikely(!nskb)) {
 		sq->stats->dropped++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 1646859974ce..7e7155b4e0f0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -68,6 +68,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
@@ -159,6 +160,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
+			s->tx_udp_seg_rem	+= sq_stats->udp_seg_rem;
 			s->tx_queue_dropped	+= sq_stats->dropped;
 			s->tx_cqe_err		+= sq_stats->cqe_err;
 			s->tx_recover		+= sq_stats->recover;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 643153bb3607..d416bb86e747 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -79,6 +79,7 @@ struct mlx5e_sw_stats {
 	u64 tx_xmit_more;
 	u64 tx_recover;
 	u64 tx_queue_wake;
+	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
 	u64 rx_wqe_err;
 	u64 rx_mpwqe_filler;
@@ -196,6 +197,7 @@ struct mlx5e_sq_stats {
 	u64 csum_partial_inner;
 	u64 added_vlan_packets;
 	u64 nop;
+	u64 udp_seg_rem;
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_ooo;
 	u64 tls_resync_bytes;
-- 
cgit v1.2.3


From ca11b798998a62c2bf87ea0477b5c60af25ba46d Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 5 Jun 2018 11:47:04 +0300
Subject: net/mlx5e: Convert large order kzalloc allocations to kvzalloc

Replace calls to kzalloc_node with kvzalloc_node, as it fallsback
to lower-order pages if the higher-order trials fail.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 44 +++++++++++------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e2ef68b1daa2..42ef8c818544 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -352,8 +352,8 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-	rq->mpwqe.info = kcalloc_node(wq_sz, sizeof(*rq->mpwqe.info),
-				      GFP_KERNEL, cpu_to_node(c->cpu));
+	rq->mpwqe.info = kvzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
+				       GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
 		return -ENOMEM;
 
@@ -670,7 +670,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 err_free:
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -702,7 +702,7 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq)
 
 	switch (rq->wq_type) {
 	case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
-		kfree(rq->mpwqe.info);
+		kvfree(rq->mpwqe.info);
 		mlx5_core_destroy_mkey(rq->mdev, &rq->umr_mkey);
 		break;
 	default: /* MLX5_WQ_TYPE_CYCLIC */
@@ -965,15 +965,15 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kfree(sq->db.di);
+	kvfree(sq->db.di);
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.di = kcalloc_node(wq_sz, sizeof(*sq->db.di),
-				     GFP_KERNEL, numa);
+	sq->db.di = kvzalloc_node(sizeof(*sq->db.di) * wq_sz,
+				  GFP_KERNEL, numa);
 	if (!sq->db.di) {
 		mlx5e_free_xdpsq_db(sq);
 		return -ENOMEM;
@@ -1024,15 +1024,15 @@ static void mlx5e_free_xdpsq(struct mlx5e_xdpsq *sq)
 
 static void mlx5e_free_icosq_db(struct mlx5e_icosq *sq)
 {
-	kfree(sq->db.ico_wqe);
+	kvfree(sq->db.ico_wqe);
 }
 
 static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.ico_wqe = kcalloc_node(wq_sz, sizeof(*sq->db.ico_wqe),
-				      GFP_KERNEL, numa);
+	sq->db.ico_wqe = kvzalloc_node(sizeof(*sq->db.ico_wqe) * wq_sz,
+				       GFP_KERNEL, numa);
 	if (!sq->db.ico_wqe)
 		return -ENOMEM;
 
@@ -1077,8 +1077,8 @@ static void mlx5e_free_icosq(struct mlx5e_icosq *sq)
 
 static void mlx5e_free_txqsq_db(struct mlx5e_txqsq *sq)
 {
-	kfree(sq->db.wqe_info);
-	kfree(sq->db.dma_fifo);
+	kvfree(sq->db.wqe_info);
+	kvfree(sq->db.dma_fifo);
 }
 
 static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
@@ -1086,10 +1086,10 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
 
-	sq->db.dma_fifo = kcalloc_node(df_sz, sizeof(*sq->db.dma_fifo),
-					   GFP_KERNEL, numa);
-	sq->db.wqe_info = kcalloc_node(wq_sz, sizeof(*sq->db.wqe_info),
-					   GFP_KERNEL, numa);
+	sq->db.dma_fifo = kvzalloc_node(df_sz * sizeof(*sq->db.dma_fifo),
+					GFP_KERNEL, numa);
+	sq->db.wqe_info = kvzalloc_node(wq_sz * sizeof(*sq->db.wqe_info),
+					GFP_KERNEL, numa);
 	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
 		mlx5e_free_txqsq_db(sq);
 		return -ENOMEM;
@@ -1893,7 +1893,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	int err;
 	int eqn;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	c = kvzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
 	if (!c)
 		return -ENOMEM;
 
@@ -1979,7 +1979,7 @@ err_close_icosq_cq:
 
 err_napi_del:
 	netif_napi_del(&c->napi);
-	kfree(c);
+	kvfree(c);
 
 	return err;
 }
@@ -2018,7 +2018,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	mlx5e_close_cq(&c->icosq.cq);
 	netif_napi_del(&c->napi);
 
-	kfree(c);
+	kvfree(c);
 }
 
 #define DEFAULT_FRAG_SIZE (2048)
@@ -2276,7 +2276,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 	chs->num = chs->params.num_channels;
 
 	chs->c = kcalloc(chs->num, sizeof(struct mlx5e_channel *), GFP_KERNEL);
-	cparam = kzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
+	cparam = kvzalloc(sizeof(struct mlx5e_channel_param), GFP_KERNEL);
 	if (!chs->c || !cparam)
 		goto err_free;
 
@@ -2287,7 +2287,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv,
 			goto err_close_channels;
 	}
 
-	kfree(cparam);
+	kvfree(cparam);
 	return 0;
 
 err_close_channels:
@@ -2296,7 +2296,7 @@ err_close_channels:
 
 err_free:
 	kfree(chs->c);
-	kfree(cparam);
+	kvfree(cparam);
 	chs->num = 0;
 	return err;
 }
-- 
cgit v1.2.3


From c400028371e54d0b247c65809b97d7cf44c2999c Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 3 Jun 2018 17:41:48 +0300
Subject: net/mlx5e: RX, Use existing WQ local variable

Local variable 'wq' already points to &sq->wq, use it.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index d3a1dd20e41d..a2d91eaa99c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -487,7 +487,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->db.ico_wqe[pi].opcode = MLX5_OPCODE_UMR;
 	sq->pc += MLX5E_UMR_WQEBBS;
-	mlx5e_notify_hw(&sq->wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &umr_wqe->ctrl);
 
 	return 0;
 
-- 
cgit v1.2.3


From 861556569645f907d50b70b663196291cf65cd34 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 18 Apr 2018 13:33:15 +0300
Subject: net/mlx5e: Add TX completions statistics

Add per-ring and global ethtool counters for TX completions.
This helps us monitor and analyze TX flow performance.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c    | 9 +++++++--
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 7e7155b4e0f0..d35361b1b3fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -67,6 +67,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_dropped) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xmit_more) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_recover) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
@@ -172,6 +173,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tls_ooo		+= sq_stats->tls_ooo;
 			s->tx_tls_resync_bytes	+= sq_stats->tls_resync_bytes;
 #endif
+			s->tx_cqes		+= sq_stats->cqes;
 		}
 	}
 
@@ -1142,6 +1144,7 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, dropped) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, xmit_more) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, recover) },
+	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqes) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, wake) },
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index d416bb86e747..8f2dfe56fdef 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -78,6 +78,7 @@ struct mlx5e_sw_stats {
 	u64 tx_queue_dropped;
 	u64 tx_xmit_more;
 	u64 tx_recover;
+	u64 tx_cqes;
 	u64 tx_queue_wake;
 	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
@@ -208,7 +209,8 @@ struct mlx5e_sq_stats {
 	u64 dropped;
 	u64 recover;
 	/* dirtied @completion */
-	u64 wake ____cacheline_aligned_in_smp;
+	u64 cqes ____cacheline_aligned_in_smp;
+	u64 wake;
 	u64 cqe_err;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f450d9ca31fb..f0739dae7b56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -468,6 +468,7 @@ static void mlx5e_dump_error_cqe(struct mlx5e_txqsq *sq,
 
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
+	struct mlx5e_sq_stats *stats;
 	struct mlx5e_txqsq *sq;
 	struct mlx5_cqe64 *cqe;
 	u32 dma_fifo_cc;
@@ -485,6 +486,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 	if (!cqe)
 		return false;
 
+	stats = sq->stats;
+
 	npkts = 0;
 	nbytes = 0;
 
@@ -513,7 +516,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				queue_work(cq->channel->priv->wq,
 					   &sq->recover.recover_work);
 			}
-			sq->stats->cqe_err++;
+			stats->cqe_err++;
 		}
 
 		do {
@@ -558,6 +561,8 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	stats->cqes += i;
+
 	mlx5_cqwq_update_db_record(&cq->wq);
 
 	/* ensure cq space is freed before enabling more cqes */
@@ -573,7 +578,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 				   MLX5E_SQ_STOP_ROOM) &&
 	    !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
 		netif_tx_wake_queue(sq->txq);
-		sq->stats->wake++;
+		stats->wake++;
 	}
 
 	return (i == MLX5E_TX_CQ_POLL_BUDGET);
-- 
cgit v1.2.3


From cbe73aaeecaee5157f5db282da21f407ab41805f Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 4 Mar 2018 10:35:00 +0200
Subject: net/mlx5e: Add XDP_TX completions statistics

Add per-ring and global ethtool counters for XDP_TX completions.
This helps us monitor and analyze XDP_TX flow performance.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 ++
 3 files changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index a2d91eaa99c4..733c5d2c99f2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1383,6 +1383,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
+	rq->stats->xdp_tx_cqe += i;
+
 	mlx5_cqwq_update_db_record(&cq->wq);
 
 	/* ensure cq space is freed before enabling more cqes */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index d35361b1b3fe..98aefa6eb266 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -59,6 +59,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
@@ -135,6 +136,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop += rq_stats->xdp_drop;
 		s->rx_xdp_tx += rq_stats->xdp_tx;
+		s->rx_xdp_tx_cqe  += rq_stats->xdp_tx_cqe;
 		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
 		s->rx_wqe_err   += rq_stats->wqe_err;
 		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
@@ -1111,6 +1113,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_cqe) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 8f2dfe56fdef..b598a21bb4d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -70,6 +70,7 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_tx;
+	u64 rx_xdp_tx_cqe;
 	u64 rx_xdp_tx_full;
 	u64 tx_csum_none;
 	u64 tx_csum_partial;
@@ -171,6 +172,7 @@ struct mlx5e_rq_stats {
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
 	u64 xdp_tx;
+	u64 xdp_tx_cqe;
 	u64 xdp_tx_full;
 	u64 wqe_err;
 	u64 mpwqe_filler;
-- 
cgit v1.2.3


From 2d7103c800add14d9ea3194a704130622474d54f Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 2 May 2018 18:29:42 +0300
Subject: net/mlx5e: Add NAPI statistics

Add per-channel and global ethtool counters for NAPI.
This helps us monitor and analyze performance in general.

- ch[i]_poll:
  the number of times the channel's NAPI poll was invoked.

- ch[i]_arm:
  the number of times the channel's NAPI poll completed
  and armed the completion queues.

- ch[i]_aff_change:
  the number of times the channel's NAPI poll explicitly
  stopped execution on a cpu due to a change in affinity.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 9 +++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 6 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c  | 6 ++++++
 3 files changed, 21 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 98aefa6eb266..ec7784189dc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -83,6 +83,9 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_eq_rearm) },
 };
 
@@ -149,6 +152,9 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
 		s->rx_cache_waive += rq_stats->cache_waive;
+		s->ch_poll        += ch_stats->poll;
+		s->ch_arm         += ch_stats->arm;
+		s->ch_aff_change  += ch_stats->aff_change;
 		s->ch_eq_rearm += ch_stats->eq_rearm;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
@@ -1153,6 +1159,9 @@ static const struct counter_desc sq_stats_desc[] = {
 };
 
 static const struct counter_desc ch_stats_desc[] = {
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, eq_rearm) },
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index b598a21bb4d6..0cd08b9f46ff 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -94,6 +94,9 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_empty;
 	u64 rx_cache_busy;
 	u64 rx_cache_waive;
+	u64 ch_poll;
+	u64 ch_arm;
+	u64 ch_aff_change;
 	u64 ch_eq_rearm;
 
 #ifdef CONFIG_MLX5_EN_TLS
@@ -217,6 +220,9 @@ struct mlx5e_sq_stats {
 };
 
 struct mlx5e_ch_stats {
+	u64 poll;
+	u64 arm;
+	u64 aff_change;
 	u64 eq_rearm;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 1b17f682693b..9f6e97883cbc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -74,10 +74,13 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel,
 					       napi);
+	struct mlx5e_ch_stats *ch_stats = c->stats;
 	bool busy = false;
 	int work_done = 0;
 	int i;
 
+	ch_stats->poll++;
+
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
@@ -94,6 +97,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (busy) {
 		if (likely(mlx5e_channel_no_affinity_change(c)))
 			return budget;
+		ch_stats->aff_change++;
 		if (budget && work_done == budget)
 			work_done--;
 	}
@@ -101,6 +105,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	if (unlikely(!napi_complete_done(napi, work_done)))
 		return work_done;
 
+	ch_stats->arm++;
+
 	for (i = 0; i < c->num_tc; i++) {
 		mlx5e_handle_tx_dim(&c->sq[i]);
 		mlx5e_cq_arm(&c->sq[i].cq);
-- 
cgit v1.2.3


From dc983f0e2b6e2b514cdb1c687fdf7b5a007f8ea4 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 4 Mar 2018 14:25:00 +0200
Subject: net/mlx5e: Add a counter for congested UMRs

Add per-ring and global ethtool counters for congested UMR requests.
These events indicate congestion in UMR handlers in HW.

Such event is concluded when there's an outstanding UMR post,
yet the SW consumed at least two additional MPWQEs in the meanwhile.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/wq.h       | 5 +++++
 4 files changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 733c5d2c99f2..6f20ce76c11c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -601,6 +601,8 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq)
 
 	if (!rq->mpwqe.umr_in_progress)
 		mlx5e_alloc_rx_mpwqe(rq, wq->head);
+	else
+		rq->stats->congst_umr += mlx5_wq_ll_missing(wq) > 2;
 
 	return false;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index ec7784189dc2..dd3b5a028a97 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -83,6 +83,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_empty) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
@@ -152,6 +153,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_cache_empty += rq_stats->cache_empty;
 		s->rx_cache_busy  += rq_stats->cache_busy;
 		s->rx_cache_waive += rq_stats->cache_waive;
+		s->rx_congst_umr  += rq_stats->congst_umr;
 		s->ch_poll        += ch_stats->poll;
 		s->ch_arm         += ch_stats->arm;
 		s->ch_aff_change  += ch_stats->aff_change;
@@ -1135,6 +1137,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_empty) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_busy) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) },
 };
 
 static const struct counter_desc sq_stats_desc[] = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 0cd08b9f46ff..4e54cb86fece 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -94,6 +94,7 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_empty;
 	u64 rx_cache_busy;
 	u64 rx_cache_waive;
+	u64 rx_congst_umr;
 	u64 ch_poll;
 	u64 ch_arm;
 	u64 ch_aff_change;
@@ -188,6 +189,7 @@ struct mlx5e_rq_stats {
 	u64 cache_empty;
 	u64 cache_busy;
 	u64 cache_waive;
+	u64 congst_umr;
 };
 
 struct mlx5e_sq_stats {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
index 0b47126815b6..2bd4c3184eba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h
@@ -229,6 +229,11 @@ static inline int mlx5_wq_ll_is_empty(struct mlx5_wq_ll *wq)
 	return !wq->cur_sz;
 }
 
+static inline int mlx5_wq_ll_missing(struct mlx5_wq_ll *wq)
+{
+	return wq->fbc.sz_m1 - wq->cur_sz;
+}
+
 static inline void *mlx5_wq_ll_get_wqe(struct mlx5_wq_ll *wq, u16 ix)
 {
 	return mlx5_frag_buf_get_wqe(&wq->fbc, ix);
-- 
cgit v1.2.3


From a1bf74dc6e66f91325cc8d35231e151a24a1f9ff Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 13 Mar 2018 11:19:28 +0200
Subject: net/mlx5e: Add channel events counter

Add per-channel and global ethtool counters for channel events.
Each event indicates an interrupt on one of the channel's
completion queues.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c  | 3 ++-
 3 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index dd3b5a028a97..0c18b20c2c18 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -84,6 +84,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_busy) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_aff_change) },
@@ -154,6 +155,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_cache_busy  += rq_stats->cache_busy;
 		s->rx_cache_waive += rq_stats->cache_waive;
 		s->rx_congst_umr  += rq_stats->congst_umr;
+		s->ch_events      += ch_stats->events;
 		s->ch_poll        += ch_stats->poll;
 		s->ch_arm         += ch_stats->arm;
 		s->ch_aff_change  += ch_stats->aff_change;
@@ -1162,6 +1164,7 @@ static const struct counter_desc sq_stats_desc[] = {
 };
 
 static const struct counter_desc ch_stats_desc[] = {
+	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, arm) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, aff_change) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 4e54cb86fece..70a05298851e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -95,6 +95,7 @@ struct mlx5e_sw_stats {
 	u64 rx_cache_busy;
 	u64 rx_cache_waive;
 	u64 rx_congst_umr;
+	u64 ch_events;
 	u64 ch_poll;
 	u64 ch_arm;
 	u64 ch_aff_change;
@@ -222,6 +223,7 @@ struct mlx5e_sq_stats {
 };
 
 struct mlx5e_ch_stats {
+	u64 events;
 	u64 poll;
 	u64 arm;
 	u64 aff_change;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 9f6e97883cbc..4e1f99a98d5d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -124,8 +124,9 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
-	cq->event_ctr++;
 	napi_schedule(cq->napi);
+	cq->event_ctr++;
+	cq->channel->stats->events++;
 }
 
 void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event)
-- 
cgit v1.2.3


From b71ba6b46ffeeb99f4b5f52892e9029b700a9068 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 28 Jun 2017 19:27:18 +0300
Subject: net/mlx5e: Add counter for MPWQE filler strides

Add ethtool counter to indicate the number of strides consumed
by filler CQEs.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    | 5 ++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 9 ++++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 6 ++++--
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 6f20ce76c11c..f763a6aebc2d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1263,7 +1263,10 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	}
 
 	if (unlikely(mpwrq_is_filler_cqe(cqe))) {
-		rq->stats->mpwqe_filler++;
+		struct mlx5e_rq_stats *stats = rq->stats;
+
+		stats->mpwqe_filler_cqes++;
+		stats->mpwqe_filler_strides += cstrides;
 		goto mpwrq_cqe_out;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 0c18b20c2c18..76107ed3a651 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -73,7 +73,8 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_buff_alloc_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_blks) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cqe_compress_pkts) },
@@ -144,7 +145,8 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_xdp_tx_cqe  += rq_stats->xdp_tx_cqe;
 		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
 		s->rx_wqe_err   += rq_stats->wqe_err;
-		s->rx_mpwqe_filler += rq_stats->mpwqe_filler;
+		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
+		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
 		s->rx_buff_alloc_err += rq_stats->buff_alloc_err;
 		s->rx_cqe_compress_blks += rq_stats->cqe_compress_blks;
 		s->rx_cqe_compress_pkts += rq_stats->cqe_compress_pkts;
@@ -1129,7 +1131,8 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, wqe_err) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_cqes) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, mpwqe_filler_strides) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, buff_alloc_err) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_blks) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cqe_compress_pkts) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 70a05298851e..1d641b012afa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -84,7 +84,8 @@ struct mlx5e_sw_stats {
 	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
 	u64 rx_wqe_err;
-	u64 rx_mpwqe_filler;
+	u64 rx_mpwqe_filler_cqes;
+	u64 rx_mpwqe_filler_strides;
 	u64 rx_buff_alloc_err;
 	u64 rx_cqe_compress_blks;
 	u64 rx_cqe_compress_pkts;
@@ -180,7 +181,8 @@ struct mlx5e_rq_stats {
 	u64 xdp_tx_cqe;
 	u64 xdp_tx_full;
 	u64 wqe_err;
-	u64 mpwqe_filler;
+	u64 mpwqe_filler_cqes;
+	u64 mpwqe_filler_strides;
 	u64 buff_alloc_err;
 	u64 cqe_compress_blks;
 	u64 cqe_compress_pkts;
-- 
cgit v1.2.3


From 2ad9ecdbe7d482867000d3da7cbccc63689a7f70 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 13 May 2018 13:42:16 +0300
Subject: net/mlx5e: Add counter for total num of NOP operations

A per-ring counter for NOP operations already exists.
Here I add a counter that sums them up.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 76107ed3a651..c0507fada0be 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -44,6 +44,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_nop) },
 
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) },
@@ -173,6 +174,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 			s->tx_tso_inner_packets	+= sq_stats->tso_inner_packets;
 			s->tx_tso_inner_bytes	+= sq_stats->tso_inner_bytes;
 			s->tx_added_vlan_packets += sq_stats->added_vlan_packets;
+			s->tx_nop               += sq_stats->nop;
 			s->tx_queue_stopped	+= sq_stats->stopped;
 			s->tx_queue_wake	+= sq_stats->wake;
 			s->tx_udp_seg_rem	+= sq_stats->udp_seg_rem;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 1d641b012afa..fc3f66003edd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -61,6 +61,7 @@ struct mlx5e_sw_stats {
 	u64 tx_tso_inner_packets;
 	u64 tx_tso_inner_bytes;
 	u64 tx_added_vlan_packets;
+	u64 tx_nop;
 	u64 rx_lro_packets;
 	u64 rx_lro_bytes;
 	u64 rx_removed_vlan_packets;
-- 
cgit v1.2.3


From ed56c5193ad89d1097cdbdc87abeb062e03a06eb Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 23 May 2018 18:26:09 -0700
Subject: net/mlx5e: Update NIC HW stats on demand only

Disable periodic stats update background thread and update stats in
background on demand when ndo_get_stats is called.

Having a background thread running in the driver all the time is bad for
power consumption and normally a user space daemon will query the stats
once every specific interval, so ideally the background thread and its
interval can be done in user space..

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 +++++-----
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c  |  3 +++
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index eb9eb7aa953a..e2b7586ed7a0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -137,7 +137,6 @@ struct page_pool;
 #define MLX5E_MAX_NUM_CHANNELS         (MLX5E_INDIR_RQT_SIZE >> 1)
 #define MLX5E_MAX_NUM_SQS              (MLX5E_MAX_NUM_CHANNELS * MLX5E_MAX_NUM_TC)
 #define MLX5E_TX_CQ_POLL_BUDGET        128
-#define MLX5E_UPDATE_STATS_INTERVAL    200 /* msecs */
 #define MLX5E_SQ_RECOVER_MIN_INTERVAL  500 /* msecs */
 
 #define MLX5E_UMR_WQE_INLINE_SZ \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 42ef8c818544..ba9ae05efe09 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -270,12 +270,9 @@ void mlx5e_update_stats_work(struct work_struct *work)
 	struct delayed_work *dwork = to_delayed_work(work);
 	struct mlx5e_priv *priv = container_of(dwork, struct mlx5e_priv,
 					       update_stats_work);
+
 	mutex_lock(&priv->state_lock);
-	if (test_bit(MLX5E_STATE_OPENED, &priv->state)) {
-		priv->profile->update_stats(priv);
-		queue_delayed_work(priv->wq, dwork,
-				   msecs_to_jiffies(MLX5E_UPDATE_STATS_INTERVAL));
-	}
+	priv->profile->update_stats(priv);
 	mutex_unlock(&priv->state_lock);
 }
 
@@ -3405,6 +3402,9 @@ mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 	struct mlx5e_vport_stats *vstats = &priv->stats.vport;
 	struct mlx5e_pport_stats *pstats = &priv->stats.pport;
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	if (mlx5e_is_uplink_rep(priv)) {
 		stats->rx_packets = PPORT_802_3_GET(pstats, a_frames_received_ok);
 		stats->rx_bytes   = PPORT_802_3_GET(pstats, a_octets_received_ok);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3f2fe95e01d9..7db7552b7e3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -893,6 +893,9 @@ mlx5e_rep_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 
+	/* update HW stats in background for next time */
+	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
+
 	memcpy(stats, &priv->stats.vf_vport, sizeof(*stats));
 }
 
-- 
cgit v1.2.3


From 0d25c43ab988766ad52ff2930af3bf47d92c20ac Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 25 Jun 2018 16:27:43 +0200
Subject: samples/bpf: extend xdp_rxq_info to read packet payload
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a cost associated with reading the packet data payload
that this test ignored.  Add option --read to allow enabling
reading part of the payload.

This sample/tool helps us analyse an issue observed with a NIC
mlx5 (ConnectX-5 Ex) and an Intel(R) Xeon(R) CPU E5-1650 v4.

With no_touch of data:

Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:no_touch
XDP stats       CPU     pps         issue-pps
XDP-RX CPU      0       14,465,157  0
XDP-RX CPU      1       14,464,728  0
XDP-RX CPU      2       14,465,283  0
XDP-RX CPU      3       14,465,282  0
XDP-RX CPU      4       14,464,159  0
XDP-RX CPU      5       14,465,379  0
XDP-RX CPU      total   86,789,992

When not touching data, we observe that the CPUs have idle cycles.
When reading data the CPUs are 100% busy in softirq.

With reading data:

Running XDP on dev:mlx5p1 (ifindex:8) action:XDP_DROP options:read
XDP stats       CPU     pps         issue-pps
XDP-RX CPU      0       9,620,639   0
XDP-RX CPU      1       9,489,843   0
XDP-RX CPU      2       9,407,854   0
XDP-RX CPU      3       9,422,289   0
XDP-RX CPU      4       9,321,959   0
XDP-RX CPU      5       9,395,242   0
XDP-RX CPU      total   56,657,828

The effect seen above is a result of cache-misses occuring when
more RXQs are being used.  Based on perf-event observations, our
conclusion is that the CPUs DDIO (Direct Data I/O) choose to
deliver packet into main memory, instead of L3-cache.  We also
found, that this can be mitigated by either using less RXQs or by
reducing NICs the RX-ring size.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/xdp_rxq_info_kern.c | 19 +++++++++++++++++++
 samples/bpf/xdp_rxq_info_user.c | 34 ++++++++++++++++++++++++++++------
 2 files changed, 47 insertions(+), 6 deletions(-)

diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c
index 3fd209291653..61af6210df2f 100644
--- a/samples/bpf/xdp_rxq_info_kern.c
+++ b/samples/bpf/xdp_rxq_info_kern.c
@@ -4,6 +4,8 @@
  *  Example howto extract XDP RX-queue info
  */
 #include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/in.h>
 #include "bpf_helpers.h"
 
 /* Config setup from with userspace
@@ -14,6 +16,11 @@
 struct config {
 	__u32 action;
 	int ifindex;
+	__u32 options;
+};
+enum cfg_options_flags {
+	NO_TOUCH = 0x0U,
+	READ_MEM = 0x1U,
 };
 struct bpf_map_def SEC("maps") config_map = {
 	.type		= BPF_MAP_TYPE_ARRAY,
@@ -90,6 +97,18 @@ int  xdp_prognum0(struct xdp_md *ctx)
 	if (key == MAX_RXQs)
 		rxq_rec->issue++;
 
+	/* Default: Don't touch packet data, only count packets */
+	if (unlikely(config->options & READ_MEM)) {
+		struct ethhdr *eth = data;
+
+		if (eth + 1 > data_end)
+			return XDP_ABORTED;
+
+		/* Avoid compiler removing this: Drop non 802.3 Ethertypes */
+		if (ntohs(eth->h_proto) < ETH_P_802_3_MIN)
+			return XDP_ABORTED;
+	}
+
 	return config->action;
 }
 
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index e4e9ba52bff0..435485d4f49e 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -50,6 +50,7 @@ static const struct option long_options[] = {
 	{"sec",		required_argument,	NULL, 's' },
 	{"no-separators", no_argument,		NULL, 'z' },
 	{"action",	required_argument,	NULL, 'a' },
+	{"readmem", 	no_argument,		NULL, 'r' },
 	{0, 0, NULL,  0 }
 };
 
@@ -66,6 +67,11 @@ static void int_exit(int sig)
 struct config {
 	__u32 action;
 	int ifindex;
+	__u32 options;
+};
+enum cfg_options_flags {
+	NO_TOUCH = 0x0U,
+	READ_MEM = 0x1U,
 };
 #define XDP_ACTION_MAX (XDP_TX + 1)
 #define XDP_ACTION_MAX_STRLEN 11
@@ -109,6 +115,16 @@ static void list_xdp_actions(void)
 	printf("\n");
 }
 
+static char* options2str(enum cfg_options_flags flag)
+{
+	if (flag == NO_TOUCH)
+		return "no_touch";
+	if (flag & READ_MEM)
+		return "read";
+	fprintf(stderr, "ERR: Unknown config option flags");
+	exit(EXIT_FAIL);
+}
+
 static void usage(char *argv[])
 {
 	int i;
@@ -305,7 +321,7 @@ static __u64 calc_errs_pps(struct datarec *r,
 
 static void stats_print(struct stats_record *stats_rec,
 			struct stats_record *stats_prev,
-			int action)
+			int action, __u32 cfg_opt)
 {
 	unsigned int nr_rxqs = bpf_map__def(rx_queue_index_map)->max_entries;
 	unsigned int nr_cpus = bpf_num_possible_cpus();
@@ -316,8 +332,8 @@ static void stats_print(struct stats_record *stats_rec,
 	int i;
 
 	/* Header */
-	printf("\nRunning XDP on dev:%s (ifindex:%d) action:%s\n",
-	       ifname, ifindex, action2str(action));
+	printf("\nRunning XDP on dev:%s (ifindex:%d) action:%s options:%s\n",
+	       ifname, ifindex, action2str(action), options2str(cfg_opt));
 
 	/* stats_global_map */
 	{
@@ -399,7 +415,7 @@ static inline void swap(struct stats_record **a, struct stats_record **b)
 	*b = tmp;
 }
 
-static void stats_poll(int interval, int action)
+static void stats_poll(int interval, int action, __u32 cfg_opt)
 {
 	struct stats_record *record, *prev;
 
@@ -410,7 +426,7 @@ static void stats_poll(int interval, int action)
 	while (1) {
 		swap(&prev, &record);
 		stats_collect(record);
-		stats_print(record, prev, action);
+		stats_print(record, prev, action, cfg_opt);
 		sleep(interval);
 	}
 
@@ -421,6 +437,7 @@ static void stats_poll(int interval, int action)
 
 int main(int argc, char **argv)
 {
+	__u32 cfg_options= NO_TOUCH ; /* Default: Don't touch packet memory */
 	struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY};
 	struct bpf_prog_load_attr prog_load_attr = {
 		.prog_type	= BPF_PROG_TYPE_XDP,
@@ -435,6 +452,7 @@ int main(int argc, char **argv)
 	int interval = 2;
 	__u32 key = 0;
 
+
 	char action_str_buf[XDP_ACTION_MAX_STRLEN + 1 /* for \0 */] = { 0 };
 	int action = XDP_PASS; /* Default action */
 	char *action_str = NULL;
@@ -496,6 +514,9 @@ int main(int argc, char **argv)
 			action_str = (char *)&action_str_buf;
 			strncpy(action_str, optarg, XDP_ACTION_MAX_STRLEN);
 			break;
+		case 'r':
+			cfg_options |= READ_MEM;
+			break;
 		case 'h':
 		error:
 		default:
@@ -522,6 +543,7 @@ int main(int argc, char **argv)
 		}
 	}
 	cfg.action = action;
+	cfg.options = cfg_options;
 
 	/* Trick to pretty printf with thousands separators use %' */
 	if (use_separators)
@@ -542,6 +564,6 @@ int main(int argc, char **argv)
 		return EXIT_FAIL_XDP;
 	}
 
-	stats_poll(interval, action);
+	stats_poll(interval, action, cfg_options);
 	return EXIT_OK;
 }
-- 
cgit v1.2.3


From 509fda105ba8f9a1a5c6f8b79e4c7fc50b35c1e3 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 25 Jun 2018 16:27:48 +0200
Subject: samples/bpf: xdp_rxq_info action XDP_TX must adjust MAC-addrs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

XDP_TX requires also changing the MAC-addrs, else some hardware
may drop the TX packet before reaching the wire.  This was
observed with driver mlx5.

If xdp_rxq_info select --action XDP_TX the swapmac functionality
is activated.  It is also possible to manually enable via cmdline
option --swapmac.  This is practical if wanting to measure the
overhead of writing/updating payload for other action types.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/xdp_rxq_info_kern.c | 26 +++++++++++++++++++++++++-
 samples/bpf/xdp_rxq_info_user.c | 11 +++++++++++
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/xdp_rxq_info_kern.c b/samples/bpf/xdp_rxq_info_kern.c
index 61af6210df2f..222a83eed1cb 100644
--- a/samples/bpf/xdp_rxq_info_kern.c
+++ b/samples/bpf/xdp_rxq_info_kern.c
@@ -21,6 +21,7 @@ struct config {
 enum cfg_options_flags {
 	NO_TOUCH = 0x0U,
 	READ_MEM = 0x1U,
+	SWAP_MAC = 0x2U,
 };
 struct bpf_map_def SEC("maps") config_map = {
 	.type		= BPF_MAP_TYPE_ARRAY,
@@ -52,6 +53,23 @@ struct bpf_map_def SEC("maps") rx_queue_index_map = {
 	.max_entries	= MAX_RXQs + 1,
 };
 
+static __always_inline
+void swap_src_dst_mac(void *data)
+{
+	unsigned short *p = data;
+	unsigned short dst[3];
+
+	dst[0] = p[0];
+	dst[1] = p[1];
+	dst[2] = p[2];
+	p[0] = p[3];
+	p[1] = p[4];
+	p[2] = p[5];
+	p[3] = dst[0];
+	p[4] = dst[1];
+	p[5] = dst[2];
+}
+
 SEC("xdp_prog0")
 int  xdp_prognum0(struct xdp_md *ctx)
 {
@@ -98,7 +116,7 @@ int  xdp_prognum0(struct xdp_md *ctx)
 		rxq_rec->issue++;
 
 	/* Default: Don't touch packet data, only count packets */
-	if (unlikely(config->options & READ_MEM)) {
+	if (unlikely(config->options & (READ_MEM|SWAP_MAC))) {
 		struct ethhdr *eth = data;
 
 		if (eth + 1 > data_end)
@@ -107,6 +125,12 @@ int  xdp_prognum0(struct xdp_md *ctx)
 		/* Avoid compiler removing this: Drop non 802.3 Ethertypes */
 		if (ntohs(eth->h_proto) < ETH_P_802_3_MIN)
 			return XDP_ABORTED;
+
+		/* XDP_TX requires changing MAC-addrs, else HW may drop.
+		 * Can also be enabled with --swapmac (for test purposes)
+		 */
+		if (unlikely(config->options & SWAP_MAC))
+			swap_src_dst_mac(data);
 	}
 
 	return config->action;
diff --git a/samples/bpf/xdp_rxq_info_user.c b/samples/bpf/xdp_rxq_info_user.c
index 435485d4f49e..248a7eab9531 100644
--- a/samples/bpf/xdp_rxq_info_user.c
+++ b/samples/bpf/xdp_rxq_info_user.c
@@ -51,6 +51,7 @@ static const struct option long_options[] = {
 	{"no-separators", no_argument,		NULL, 'z' },
 	{"action",	required_argument,	NULL, 'a' },
 	{"readmem", 	no_argument,		NULL, 'r' },
+	{"swapmac", 	no_argument,		NULL, 'm' },
 	{0, 0, NULL,  0 }
 };
 
@@ -72,6 +73,7 @@ struct config {
 enum cfg_options_flags {
 	NO_TOUCH = 0x0U,
 	READ_MEM = 0x1U,
+	SWAP_MAC = 0x2U,
 };
 #define XDP_ACTION_MAX (XDP_TX + 1)
 #define XDP_ACTION_MAX_STRLEN 11
@@ -119,6 +121,8 @@ static char* options2str(enum cfg_options_flags flag)
 {
 	if (flag == NO_TOUCH)
 		return "no_touch";
+	if (flag & SWAP_MAC)
+		return "swapmac";
 	if (flag & READ_MEM)
 		return "read";
 	fprintf(stderr, "ERR: Unknown config option flags");
@@ -517,6 +521,9 @@ int main(int argc, char **argv)
 		case 'r':
 			cfg_options |= READ_MEM;
 			break;
+		case 'm':
+			cfg_options |= SWAP_MAC;
+			break;
 		case 'h':
 		error:
 		default:
@@ -543,6 +550,10 @@ int main(int argc, char **argv)
 		}
 	}
 	cfg.action = action;
+
+	/* XDP_TX requires changing MAC-addrs, else HW may drop */
+	if (action == XDP_TX)
+		cfg_options |= SWAP_MAC;
 	cfg.options = cfg_options;
 
 	/* Trick to pretty printf with thousands separators use %' */
-- 
cgit v1.2.3


From c39d2e7e35f6f357e59c7313dab8e90f7d1ff93e Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 28 Jun 2018 14:15:20 +0000
Subject: drm/i915/guc: Use intel_guc_init_misc to hide GuC internals

We will add more init steps to misc phase and there is no need
to expose them separately for use in uc_init_misc function.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628141522.62788-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c | 28 ++++++++++++++++++++++++----
 drivers/gpu/drm/i915/intel_guc.h |  5 ++---
 drivers/gpu/drm/i915/intel_uc.c  |  6 ++----
 3 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index f651e57b4c61..0b06f27d3e1a 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -27,6 +27,8 @@
 #include "intel_guc_submission.h"
 #include "i915_drv.h"
 
+static void guc_init_ggtt_pin_bias(struct intel_guc *guc);
+
 static void gen8_guc_raise_irq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -73,7 +75,7 @@ void intel_guc_init_early(struct intel_guc *guc)
 	guc->notify = gen8_guc_raise_irq;
 }
 
-int intel_guc_init_wq(struct intel_guc *guc)
+static int guc_init_wq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
@@ -124,7 +126,7 @@ int intel_guc_init_wq(struct intel_guc *guc)
 	return 0;
 }
 
-void intel_guc_fini_wq(struct intel_guc *guc)
+static void guc_fini_wq(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
 
@@ -135,6 +137,24 @@ void intel_guc_fini_wq(struct intel_guc *guc)
 	destroy_workqueue(guc->log.relay.flush_wq);
 }
 
+int intel_guc_init_misc(struct intel_guc *guc)
+{
+	int ret;
+
+	guc_init_ggtt_pin_bias(guc);
+
+	ret = guc_init_wq(guc);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void intel_guc_fini_misc(struct intel_guc *guc)
+{
+	guc_fini_wq(guc);
+}
+
 static int guc_shared_data_create(struct intel_guc *guc)
 {
 	struct i915_vma *vma;
@@ -582,13 +602,13 @@ int intel_guc_resume(struct intel_guc *guc)
  */
 
 /**
- * intel_guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
+ * guc_init_ggtt_pin_bias() - Initialize the GuC ggtt_pin_bias value.
  * @guc: intel_guc structure.
  *
  * This function will calculate and initialize the ggtt_pin_bias value based on
  * overall WOPCM size and GuC WOPCM size.
  */
-void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc)
+static void guc_init_ggtt_pin_bias(struct intel_guc *guc)
 {
 	struct drm_i915_private *i915 = guc_to_i915(guc);
 
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index f1265e122d30..4121928a495e 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -151,11 +151,10 @@ static inline u32 intel_guc_ggtt_offset(struct intel_guc *guc,
 void intel_guc_init_early(struct intel_guc *guc);
 void intel_guc_init_send_regs(struct intel_guc *guc);
 void intel_guc_init_params(struct intel_guc *guc);
-void intel_guc_init_ggtt_pin_bias(struct intel_guc *guc);
-int intel_guc_init_wq(struct intel_guc *guc);
-void intel_guc_fini_wq(struct intel_guc *guc);
+int intel_guc_init_misc(struct intel_guc *guc);
 int intel_guc_init(struct intel_guc *guc);
 void intel_guc_fini(struct intel_guc *guc);
+void intel_guc_fini_misc(struct intel_guc *guc);
 int intel_guc_send_nop(struct intel_guc *guc, const u32 *action, u32 len,
 		       u32 *response_buf, u32 response_buf_size);
 int intel_guc_send_mmio(struct intel_guc *guc, const u32 *action, u32 len,
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 94e8863bd97c..cd49b4f510f0 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -257,9 +257,7 @@ int intel_uc_init_misc(struct drm_i915_private *i915)
 	if (!USES_GUC(i915))
 		return 0;
 
-	intel_guc_init_ggtt_pin_bias(guc);
-
-	ret = intel_guc_init_wq(guc);
+	ret = intel_guc_init_misc(guc);
 	if (ret)
 		return ret;
 
@@ -273,7 +271,7 @@ void intel_uc_fini_misc(struct drm_i915_private *i915)
 	if (!USES_GUC(i915))
 		return;
 
-	intel_guc_fini_wq(guc);
+	intel_guc_fini_misc(guc);
 }
 
 int intel_uc_init(struct drm_i915_private *i915)
-- 
cgit v1.2.3


From f7dc0157e4b5f23780559c6b71d3f7282f6c7f1b Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Thu, 28 Jun 2018 14:15:21 +0000
Subject: drm/i915/uc: Fetch GuC/HuC firmwares from guc/huc specific init

We're fetching GuC/HuC firmwares directly from uc level during
init_early stage but this breaks guc/huc struct isolation and
also strict SW-only initialization rule for init_early. Move fw
fetching to init phase and do it separately per guc/huc struct.

v2: don't forget to move wopcm_init - Michele
v3: fetch in init_misc phase - Michal

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com> #2
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628141522.62788-2-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/i915_gem.c  |  7 ++++---
 drivers/gpu/drm/i915/intel_guc.c |  9 ++++++++-
 drivers/gpu/drm/i915/intel_huc.c |  8 ++++++++
 drivers/gpu/drm/i915/intel_huc.h |  6 ++++++
 drivers/gpu/drm/i915/intel_uc.c  | 28 +++++++++++++++-------------
 5 files changed, 41 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5a9cae604e2b..8954db6ab083 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5459,13 +5459,13 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	if (ret)
 		return ret;
 
-	ret = intel_wopcm_init(&dev_priv->wopcm);
+	ret = intel_uc_init_misc(dev_priv);
 	if (ret)
 		return ret;
 
-	ret = intel_uc_init_misc(dev_priv);
+	ret = intel_wopcm_init(&dev_priv->wopcm);
 	if (ret)
-		return ret;
+		goto err_uc_misc;
 
 	/* This is just a security blanket to placate dragons.
 	 * On some systems, we very sporadically observe that the first TLBs
@@ -5563,6 +5563,7 @@ err_unlock:
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
+err_uc_misc:
 	intel_uc_fini_misc(dev_priv);
 
 	if (ret != -EIO)
diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 0b06f27d3e1a..53b43bc73c01 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -139,6 +139,7 @@ static void guc_fini_wq(struct intel_guc *guc)
 
 int intel_guc_init_misc(struct intel_guc *guc)
 {
+	struct drm_i915_private *i915 = guc_to_i915(guc);
 	int ret;
 
 	guc_init_ggtt_pin_bias(guc);
@@ -147,11 +148,14 @@ int intel_guc_init_misc(struct intel_guc *guc)
 	if (ret)
 		return ret;
 
+	intel_uc_fw_fetch(i915, &guc->fw);
+
 	return 0;
 }
 
 void intel_guc_fini_misc(struct intel_guc *guc)
 {
+	intel_uc_fw_fini(&guc->fw);
 	guc_fini_wq(guc);
 }
 
@@ -189,7 +193,7 @@ int intel_guc_init(struct intel_guc *guc)
 
 	ret = guc_shared_data_create(guc);
 	if (ret)
-		return ret;
+		goto err_fetch;
 	GEM_BUG_ON(!guc->shared_data);
 
 	ret = intel_guc_log_create(&guc->log);
@@ -210,6 +214,8 @@ err_log:
 	intel_guc_log_destroy(&guc->log);
 err_shared:
 	guc_shared_data_destroy(guc);
+err_fetch:
+	intel_uc_fw_fini(&guc->fw);
 	return ret;
 }
 
@@ -221,6 +227,7 @@ void intel_guc_fini(struct intel_guc *guc)
 	intel_guc_ads_destroy(guc);
 	intel_guc_log_destroy(&guc->log);
 	guc_shared_data_destroy(guc);
+	intel_uc_fw_fini(&guc->fw);
 }
 
 static u32 guc_ctl_debug_flags(struct intel_guc *guc)
diff --git a/drivers/gpu/drm/i915/intel_huc.c b/drivers/gpu/drm/i915/intel_huc.c
index 291285277403..ffcad5fad6a7 100644
--- a/drivers/gpu/drm/i915/intel_huc.c
+++ b/drivers/gpu/drm/i915/intel_huc.c
@@ -32,6 +32,14 @@ void intel_huc_init_early(struct intel_huc *huc)
 	intel_huc_fw_init_early(huc);
 }
 
+int intel_huc_init_misc(struct intel_huc *huc)
+{
+	struct drm_i915_private *i915 = huc_to_i915(huc);
+
+	intel_uc_fw_fetch(i915, &huc->fw);
+	return 0;
+}
+
 /**
  * intel_huc_auth() - Authenticate HuC uCode
  * @huc: intel_huc structure
diff --git a/drivers/gpu/drm/i915/intel_huc.h b/drivers/gpu/drm/i915/intel_huc.h
index aa854907abac..7e41d870b509 100644
--- a/drivers/gpu/drm/i915/intel_huc.h
+++ b/drivers/gpu/drm/i915/intel_huc.h
@@ -36,9 +36,15 @@ struct intel_huc {
 };
 
 void intel_huc_init_early(struct intel_huc *huc);
+int intel_huc_init_misc(struct intel_huc *huc);
 int intel_huc_auth(struct intel_huc *huc);
 int intel_huc_check_status(struct intel_huc *huc);
 
+static inline void intel_huc_fini_misc(struct intel_huc *huc)
+{
+	intel_uc_fw_fini(&huc->fw);
+}
+
 static inline int intel_huc_sanitize(struct intel_huc *huc)
 {
 	intel_uc_fw_sanitize(&huc->fw);
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index cd49b4f510f0..7c95697e1a35 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -171,24 +171,11 @@ void intel_uc_init_early(struct drm_i915_private *i915)
 	intel_huc_init_early(huc);
 
 	sanitize_options_early(i915);
-
-	if (USES_GUC(i915))
-		intel_uc_fw_fetch(i915, &guc->fw);
-
-	if (USES_HUC(i915))
-		intel_uc_fw_fetch(i915, &huc->fw);
 }
 
 void intel_uc_cleanup_early(struct drm_i915_private *i915)
 {
 	struct intel_guc *guc = &i915->guc;
-	struct intel_huc *huc = &i915->huc;
-
-	if (USES_HUC(i915))
-		intel_uc_fw_fini(&huc->fw);
-
-	if (USES_GUC(i915))
-		intel_uc_fw_fini(&guc->fw);
 
 	guc_free_load_err_log(guc);
 }
@@ -252,6 +239,7 @@ static void guc_disable_communication(struct intel_guc *guc)
 int intel_uc_init_misc(struct drm_i915_private *i915)
 {
 	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 	int ret;
 
 	if (!USES_GUC(i915))
@@ -261,16 +249,30 @@ int intel_uc_init_misc(struct drm_i915_private *i915)
 	if (ret)
 		return ret;
 
+	if (USES_HUC(i915)) {
+		ret = intel_huc_init_misc(huc);
+		if (ret)
+			goto err_guc;
+	}
+
 	return 0;
+
+err_guc:
+	intel_guc_fini_misc(guc);
+	return ret;
 }
 
 void intel_uc_fini_misc(struct drm_i915_private *i915)
 {
 	struct intel_guc *guc = &i915->guc;
+	struct intel_huc *huc = &i915->huc;
 
 	if (!USES_GUC(i915))
 		return;
 
+	if (USES_HUC(i915))
+		intel_huc_fini_misc(huc);
+
 	intel_guc_fini_misc(guc);
 }
 
-- 
cgit v1.2.3


From 74093f3eccac232447ef95536c6a359ee7661650 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:03 +0100
Subject: drm/i915: Drop posting reads to flush master interrupts

We do not need to do a posting read of our uncached mmio write to
re-enable the master interrupt lines after handling an interrupt, so
don't. This saves us a slow UC read before we can process the interrupt,
most noticeable in execlists where any stalls imposes extra latency on
GPU command execution.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjala <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 4be56aec99b3..02fe0d32382e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2183,7 +2183,6 @@ static irqreturn_t valleyview_irq_handler(int irq, void *arg)
 
 		I915_WRITE(VLV_IER, ier);
 		I915_WRITE(VLV_MASTER_IER, MASTER_INTERRUPT_ENABLE);
-		POSTING_READ(VLV_MASTER_IER);
 
 		if (gt_iir)
 			snb_gt_irq_handler(dev_priv, gt_iir);
@@ -2268,7 +2267,6 @@ static irqreturn_t cherryview_irq_handler(int irq, void *arg)
 
 		I915_WRITE(VLV_IER, ier);
 		I915_WRITE(GEN8_MASTER_IRQ, GEN8_MASTER_IRQ_CONTROL);
-		POSTING_READ(GEN8_MASTER_IRQ);
 
 		gen8_gt_irq_handler(dev_priv, master_ctl, gt_iir);
 
@@ -2637,7 +2635,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	/* disable master interrupt before clearing iir  */
 	de_ier = I915_READ(DEIER);
 	I915_WRITE(DEIER, de_ier & ~DE_MASTER_IRQ_CONTROL);
-	POSTING_READ(DEIER);
 
 	/* Disable south interrupts. We'll only write to SDEIIR once, so further
 	 * interrupts will will be stored on its back queue, and then we'll be
@@ -2647,7 +2644,6 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	if (!HAS_PCH_NOP(dev_priv)) {
 		sde_ier = I915_READ(SDEIER);
 		I915_WRITE(SDEIER, 0);
-		POSTING_READ(SDEIER);
 	}
 
 	/* Find, clear, then process each source of interrupt */
@@ -2682,11 +2678,8 @@ static irqreturn_t ironlake_irq_handler(int irq, void *arg)
 	}
 
 	I915_WRITE(DEIER, de_ier);
-	POSTING_READ(DEIER);
-	if (!HAS_PCH_NOP(dev_priv)) {
+	if (!HAS_PCH_NOP(dev_priv))
 		I915_WRITE(SDEIER, sde_ier);
-		POSTING_READ(SDEIER);
-	}
 
 	/* IRQs are synced during runtime_suspend, we don't require a wakeref */
 	enable_rpm_wakeref_asserts(dev_priv);
-- 
cgit v1.2.3


From 0b02befa828c0be67a5416e10a0244e181fde0d3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:04 +0100
Subject: drm/i915/execlists: Pull submit after dequeue under timeline lock

In the next patch, we will begin processing the CSB from inside the
submission path (underneath an irqsoff section, and even from inside
interrupt handlers). This means that updating the execlists->port[] will
no longer be serialised by the tasklet but needs to be locked by the
engine->timeline.lock instead. Pull dequeue and submit under the same
lock for protection. (An alternate future plan is to keep the in/out
arrays separate for concurrent processing and reduced lock coverage.)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 32 ++++++++++++--------------------
 1 file changed, 12 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 46572976c942..af94949d08c8 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -567,7 +567,7 @@ static void complete_preempt_context(struct intel_engine_execlists *execlists)
 	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
-static bool __execlists_dequeue(struct intel_engine_cs *engine)
+static void __execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
@@ -622,11 +622,11 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * the HW to indicate that it has had a chance to respond.
 		 */
 		if (!execlists_is_active(execlists, EXECLISTS_ACTIVE_HWACK))
-			return false;
+			return;
 
 		if (need_preempt(engine, last, execlists->queue_priority)) {
 			inject_preempt_context(engine);
-			return false;
+			return;
 		}
 
 		/*
@@ -651,7 +651,7 @@ static bool __execlists_dequeue(struct intel_engine_cs *engine)
 		 * priorities of the ports haven't been switch.
 		 */
 		if (port_count(&port[1]))
-			return false;
+			return;
 
 		/*
 		 * WaIdleLiteRestore:bdw,skl
@@ -751,8 +751,10 @@ done:
 		port != execlists->port ? rq_prio(last) : INT_MIN;
 
 	execlists->first = rb;
-	if (submit)
+	if (submit) {
 		port_assign(port, last);
+		execlists_submit_ports(engine);
+	}
 
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
@@ -761,24 +763,19 @@ done:
 	if (last)
 		execlists_user_begin(execlists, execlists->port);
 
-	return submit;
+	/* If the engine is now idle, so should be the flag; and vice versa. */
+	GEM_BUG_ON(execlists_is_active(&engine->execlists,
+				       EXECLISTS_ACTIVE_USER) ==
+		   !port_isset(engine->execlists.port));
 }
 
 static void execlists_dequeue(struct intel_engine_cs *engine)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	unsigned long flags;
-	bool submit;
 
 	spin_lock_irqsave(&engine->timeline.lock, flags);
-	submit = __execlists_dequeue(engine);
+	__execlists_dequeue(engine);
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
-
-	if (submit)
-		execlists_submit_ports(engine);
-
-	GEM_BUG_ON(port_isset(execlists->port) &&
-		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
 }
 
 void
@@ -1162,11 +1159,6 @@ static void execlists_submission_tasklet(unsigned long data)
 
 	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
 		execlists_dequeue(engine);
-
-	/* If the engine is now idle, so should be the flag; and vice versa. */
-	GEM_BUG_ON(execlists_is_active(&engine->execlists,
-				       EXECLISTS_ACTIVE_USER) ==
-		   !port_isset(engine->execlists.port));
 }
 
 static void queue_request(struct intel_engine_cs *engine,
-- 
cgit v1.2.3


From d8857d541c67110cdcedb330e9677efdc9c5844d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:05 +0100
Subject: drm/i915/execlists: Pull CSB reset under the timeline.lock

In the following patch, we will process the CSB events under the
timeline.lock and not serialised by the tasklet. This also means that we
will need to protect access to common variables such as
execlists->csb_head with the timeline.lock during reset.

v2: Move sync_irq to avoid deadlocks between taking timeline.lock from
our interrupt handler.
v3: Kill off the synchronize_hardirq as it raises more questions than
answered; now we use the timeline.lock entirely for CSB serialisation
between the irq and elsewhere, we don't need to be so heavy handed with
flushing
v4: Treat request cancellation (wedging after failed reset) similarly

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index af94949d08c8..0cee34e39343 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -872,7 +872,6 @@ static void reset_irq(struct intel_engine_cs *engine)
 {
 	/* Mark all CS interrupts as complete */
 	smp_store_mb(engine->execlists.active, 0);
-	synchronize_hardirq(engine->i915->drm.irq);
 
 	clear_gtiir(engine);
 
@@ -909,14 +908,12 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	 * submission's irq state, we also wish to remind ourselves that
 	 * it is irq state.)
 	 */
-	local_irq_save(flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	/* Cancel the requests on the HW and clear the ELSP tracker. */
 	execlists_cancel_port_requests(execlists);
 	reset_irq(engine);
 
-	spin_lock(&engine->timeline.lock);
-
 	/* Mark all executing requests as skipped. */
 	list_for_each_entry(rq, &engine->timeline.requests, link) {
 		GEM_BUG_ON(!rq->global_seqno);
@@ -950,9 +947,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	execlists->first = NULL;
 	GEM_BUG_ON(port_isset(execlists->port));
 
-	spin_unlock(&engine->timeline.lock);
-
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
 static void process_csb(struct intel_engine_cs *engine)
@@ -1970,8 +1965,7 @@ static void execlists_reset(struct intel_engine_cs *engine,
 		  engine->name, request ? request->global_seqno : 0,
 		  intel_engine_get_seqno(engine));
 
-	/* See execlists_cancel_requests() for the irq/spinlock split. */
-	local_irq_save(flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	/*
 	 * Catch up with any missed context-switch interrupts.
@@ -1986,14 +1980,12 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	reset_irq(engine);
 
 	/* Push back any incomplete requests for replay after the reset. */
-	spin_lock(&engine->timeline.lock);
 	__unwind_incomplete_requests(engine);
-	spin_unlock(&engine->timeline.lock);
 
 	/* Following the reset, we need to reload the CSB read/write pointers */
 	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
 
-	local_irq_restore(flags);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	/*
 	 * If the request was innocent, we leave the request in the ELSP
-- 
cgit v1.2.3


From 8ea397fa70be357f52988eb156b324105b286607 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:06 +0100
Subject: drm/i915/execlists: Process one CSB update at a time

In the next patch, we will process the CSB events directly from the
submission path, rather than only after a CS interrupt. Hence, we will
no longer have the need for a loop until the has-interrupt bit is clear,
and in the meantime can remove that small optimisation.

v2: Tvrtko pointed out it was safer to unconditionally kick the tasklet
after each irq, when assuming that the tasklet is called for each irq.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c  |   7 +-
 drivers/gpu/drm/i915/intel_lrc.c | 278 +++++++++++++++++++--------------------
 2 files changed, 141 insertions(+), 144 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 02fe0d32382e..c95cb278a8bc 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1497,9 +1497,10 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 	bool tasklet = false;
 
 	if (iir & GT_CONTEXT_SWITCH_INTERRUPT) {
-		if (READ_ONCE(engine->execlists.active))
-			tasklet = !test_and_set_bit(ENGINE_IRQ_EXECLIST,
-						    &engine->irq_posted);
+		if (READ_ONCE(engine->execlists.active)) {
+			set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
+			tasklet = true;
+		}
 	}
 
 	if (iir & GT_RENDER_USER_INTERRUPT) {
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 0cee34e39343..c8d3d41011ce 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -955,166 +955,162 @@ static void process_csb(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
 	struct drm_i915_private *i915 = engine->i915;
+
+	/* The HWSP contains a (cacheable) mirror of the CSB */
+	const u32 *buf =
+		&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+	unsigned int head, tail;
 	bool fw = false;
 
-	do {
-		/* The HWSP contains a (cacheable) mirror of the CSB */
-		const u32 *buf =
-			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
-		unsigned int head, tail;
-
-		/* Clear before reading to catch new interrupts */
-		clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-		smp_mb__after_atomic();
-
-		if (unlikely(execlists->csb_use_mmio)) {
-			if (!fw) {
-				intel_uncore_forcewake_get(i915, execlists->fw_domains);
-				fw = true;
-			}
+	/* Clear before reading to catch new interrupts */
+	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
+	smp_mb__after_atomic();
 
-			buf = (u32 * __force)
-				(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+	if (unlikely(execlists->csb_use_mmio)) {
+		intel_uncore_forcewake_get(i915, execlists->fw_domains);
+		fw = true;
 
-			head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-			tail = GEN8_CSB_WRITE_PTR(head);
-			head = GEN8_CSB_READ_PTR(head);
-			execlists->csb_head = head;
-		} else {
-			const int write_idx =
-				intel_hws_csb_write_index(i915) -
-				I915_HWS_CSB_BUF0_INDEX;
+		buf = (u32 * __force)
+			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
 
-			head = execlists->csb_head;
-			tail = READ_ONCE(buf[write_idx]);
-			rmb(); /* Hopefully paired with a wmb() in HW */
-		}
-		GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
-			  engine->name,
-			  head, GEN8_CSB_READ_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
-			  tail, GEN8_CSB_WRITE_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
+		head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
+		tail = GEN8_CSB_WRITE_PTR(head);
+		head = GEN8_CSB_READ_PTR(head);
+		execlists->csb_head = head;
+	} else {
+		const int write_idx =
+			intel_hws_csb_write_index(i915) -
+			I915_HWS_CSB_BUF0_INDEX;
 
-		while (head != tail) {
-			struct i915_request *rq;
-			unsigned int status;
-			unsigned int count;
+		head = execlists->csb_head;
+		tail = READ_ONCE(buf[write_idx]);
+		rmb(); /* Hopefully paired with a wmb() in HW */
+	}
+	GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
+		  engine->name,
+		  head, GEN8_CSB_READ_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
+		  tail, GEN8_CSB_WRITE_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
 
-			if (++head == GEN8_CSB_ENTRIES)
-				head = 0;
+	while (head != tail) {
+		struct i915_request *rq;
+		unsigned int status;
+		unsigned int count;
 
-			/*
-			 * We are flying near dragons again.
-			 *
-			 * We hold a reference to the request in execlist_port[]
-			 * but no more than that. We are operating in softirq
-			 * context and so cannot hold any mutex or sleep. That
-			 * prevents us stopping the requests we are processing
-			 * in port[] from being retired simultaneously (the
-			 * breadcrumb will be complete before we see the
-			 * context-switch). As we only hold the reference to the
-			 * request, any pointer chasing underneath the request
-			 * is subject to a potential use-after-free. Thus we
-			 * store all of the bookkeeping within port[] as
-			 * required, and avoid using unguarded pointers beneath
-			 * request itself. The same applies to the atomic
-			 * status notifier.
-			 */
+		if (++head == GEN8_CSB_ENTRIES)
+			head = 0;
 
-			status = READ_ONCE(buf[2 * head]); /* maybe mmio! */
-			GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
-				  engine->name, head,
-				  status, buf[2*head + 1],
-				  execlists->active);
-
-			if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
-				      GEN8_CTX_STATUS_PREEMPTED))
-				execlists_set_active(execlists,
-						     EXECLISTS_ACTIVE_HWACK);
-			if (status & GEN8_CTX_STATUS_ACTIVE_IDLE)
-				execlists_clear_active(execlists,
-						       EXECLISTS_ACTIVE_HWACK);
-
-			if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
-				continue;
+		/*
+		 * We are flying near dragons again.
+		 *
+		 * We hold a reference to the request in execlist_port[]
+		 * but no more than that. We are operating in softirq
+		 * context and so cannot hold any mutex or sleep. That
+		 * prevents us stopping the requests we are processing
+		 * in port[] from being retired simultaneously (the
+		 * breadcrumb will be complete before we see the
+		 * context-switch). As we only hold the reference to the
+		 * request, any pointer chasing underneath the request
+		 * is subject to a potential use-after-free. Thus we
+		 * store all of the bookkeeping within port[] as
+		 * required, and avoid using unguarded pointers beneath
+		 * request itself. The same applies to the atomic
+		 * status notifier.
+		 */
 
-			/* We should never get a COMPLETED | IDLE_ACTIVE! */
-			GEM_BUG_ON(status & GEN8_CTX_STATUS_IDLE_ACTIVE);
+		status = READ_ONCE(buf[2 * head]); /* maybe mmio! */
+		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
+			  engine->name, head,
+			  status, buf[2*head + 1],
+			  execlists->active);
+
+		if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
+			      GEN8_CTX_STATUS_PREEMPTED))
+			execlists_set_active(execlists,
+					     EXECLISTS_ACTIVE_HWACK);
+		if (status & GEN8_CTX_STATUS_ACTIVE_IDLE)
+			execlists_clear_active(execlists,
+					       EXECLISTS_ACTIVE_HWACK);
+
+		if (!(status & GEN8_CTX_STATUS_COMPLETED_MASK))
+			continue;
 
-			if (status & GEN8_CTX_STATUS_COMPLETE &&
-			    buf[2*head + 1] == execlists->preempt_complete_status) {
-				GEM_TRACE("%s preempt-idle\n", engine->name);
-				complete_preempt_context(execlists);
-				continue;
-			}
+		/* We should never get a COMPLETED | IDLE_ACTIVE! */
+		GEM_BUG_ON(status & GEN8_CTX_STATUS_IDLE_ACTIVE);
 
-			if (status & GEN8_CTX_STATUS_PREEMPTED &&
-			    execlists_is_active(execlists,
-						EXECLISTS_ACTIVE_PREEMPT))
-				continue;
+		if (status & GEN8_CTX_STATUS_COMPLETE &&
+		    buf[2*head + 1] == execlists->preempt_complete_status) {
+			GEM_TRACE("%s preempt-idle\n", engine->name);
+			complete_preempt_context(execlists);
+			continue;
+		}
 
-			GEM_BUG_ON(!execlists_is_active(execlists,
-							EXECLISTS_ACTIVE_USER));
+		if (status & GEN8_CTX_STATUS_PREEMPTED &&
+		    execlists_is_active(execlists,
+					EXECLISTS_ACTIVE_PREEMPT))
+			continue;
 
-			rq = port_unpack(port, &count);
-			GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
-				  engine->name,
-				  port->context_id, count,
-				  rq ? rq->global_seqno : 0,
-				  rq ? rq->fence.context : 0,
-				  rq ? rq->fence.seqno : 0,
-				  intel_engine_get_seqno(engine),
-				  rq ? rq_prio(rq) : 0);
+		GEM_BUG_ON(!execlists_is_active(execlists,
+						EXECLISTS_ACTIVE_USER));
 
-			/* Check the context/desc id for this event matches */
-			GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
+		rq = port_unpack(port, &count);
+		GEM_TRACE("%s out[0]: ctx=%d.%d, global=%d (fence %llx:%d) (current %d), prio=%d\n",
+			  engine->name,
+			  port->context_id, count,
+			  rq ? rq->global_seqno : 0,
+			  rq ? rq->fence.context : 0,
+			  rq ? rq->fence.seqno : 0,
+			  intel_engine_get_seqno(engine),
+			  rq ? rq_prio(rq) : 0);
+
+		/* Check the context/desc id for this event matches */
+		GEM_DEBUG_BUG_ON(buf[2 * head + 1] != port->context_id);
+
+		GEM_BUG_ON(count == 0);
+		if (--count == 0) {
+			/*
+			 * On the final event corresponding to the
+			 * submission of this context, we expect either
+			 * an element-switch event or a completion
+			 * event (and on completion, the active-idle
+			 * marker). No more preemptions, lite-restore
+			 * or otherwise.
+			 */
+			GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
+			GEM_BUG_ON(port_isset(&port[1]) &&
+				   !(status & GEN8_CTX_STATUS_ELEMENT_SWITCH));
+			GEM_BUG_ON(!port_isset(&port[1]) &&
+				   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
 
-			GEM_BUG_ON(count == 0);
-			if (--count == 0) {
-				/*
-				 * On the final event corresponding to the
-				 * submission of this context, we expect either
-				 * an element-switch event or a completion
-				 * event (and on completion, the active-idle
-				 * marker). No more preemptions, lite-restore
-				 * or otherwise.
-				 */
-				GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
-				GEM_BUG_ON(port_isset(&port[1]) &&
-					   !(status & GEN8_CTX_STATUS_ELEMENT_SWITCH));
-				GEM_BUG_ON(!port_isset(&port[1]) &&
-					   !(status & GEN8_CTX_STATUS_ACTIVE_IDLE));
+			/*
+			 * We rely on the hardware being strongly
+			 * ordered, that the breadcrumb write is
+			 * coherent (visible from the CPU) before the
+			 * user interrupt and CSB is processed.
+			 */
+			GEM_BUG_ON(!i915_request_completed(rq));
 
-				/*
-				 * We rely on the hardware being strongly
-				 * ordered, that the breadcrumb write is
-				 * coherent (visible from the CPU) before the
-				 * user interrupt and CSB is processed.
-				 */
-				GEM_BUG_ON(!i915_request_completed(rq));
-
-				execlists_context_schedule_out(rq,
-							       INTEL_CONTEXT_SCHEDULE_OUT);
-				i915_request_put(rq);
-
-				GEM_TRACE("%s completed ctx=%d\n",
-					  engine->name, port->context_id);
-
-				port = execlists_port_complete(execlists, port);
-				if (port_isset(port))
-					execlists_user_begin(execlists, port);
-				else
-					execlists_user_end(execlists);
-			} else {
-				port_set(port, port_pack(rq, count));
-			}
-		}
+			execlists_context_schedule_out(rq,
+						       INTEL_CONTEXT_SCHEDULE_OUT);
+			i915_request_put(rq);
 
-		if (head != execlists->csb_head) {
-			execlists->csb_head = head;
-			writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
-			       i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
+			GEM_TRACE("%s completed ctx=%d\n",
+				  engine->name, port->context_id);
+
+			port = execlists_port_complete(execlists, port);
+			if (port_isset(port))
+				execlists_user_begin(execlists, port);
+			else
+				execlists_user_end(execlists);
+		} else {
+			port_set(port, port_pack(rq, count));
 		}
-	} while (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted));
+	}
+
+	if (head != execlists->csb_head) {
+		execlists->csb_head = head;
+		writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
+		       i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
+	}
 
 	if (unlikely(fw))
 		intel_uncore_forcewake_put(i915, execlists->fw_domains);
-- 
cgit v1.2.3


From bc4237ec8deaaee5f75d1afa91a19bfe6f948c6f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:07 +0100
Subject: drm/i915/execlists: Unify CSB access pointers

Following the removal of the last workarounds, the only CSB mmio access
is for the old vGPU interface. The mmio registers presented by vGPU do
not require forcewake and can be treated as ordinary volatile memory,
i.e. they behave just like the HWSP access just at a different location.
We can reduce the CSB access to a set of read/write/buffer pointers and
treat the various paths identically and not worry about forcewake.
(Forcewake is nightmare for worstcase latency, and we want to process
this all with irqsoff -- no latency allowed!)

v2: Comments, comments, comments. Well, 2 bonus comments.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c  |  12 ---
 drivers/gpu/drm/i915/intel_lrc.c        | 133 ++++++++++++++++----------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  23 ++++--
 3 files changed, 82 insertions(+), 86 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index d3264bd6e9dc..7209c22798e6 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -25,7 +25,6 @@
 #include <drm/drm_print.h>
 
 #include "i915_drv.h"
-#include "i915_vgpu.h"
 #include "intel_ringbuffer.h"
 #include "intel_lrc.h"
 
@@ -456,21 +455,10 @@ static void intel_engine_init_batch_pool(struct intel_engine_cs *engine)
 	i915_gem_batch_pool_init(&engine->batch_pool, engine);
 }
 
-static bool csb_force_mmio(struct drm_i915_private *i915)
-{
-	/* Older GVT emulation depends upon intercepting CSB mmio */
-	if (intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915))
-		return true;
-
-	return false;
-}
-
 static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
-	execlists->csb_use_mmio = csb_force_mmio(engine->i915);
-
 	execlists->port_mask = 1;
 	BUILD_BUG_ON_NOT_POWER_OF_2(execlists_num_ports(execlists));
 	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c8d3d41011ce..81f000c245ab 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -137,6 +137,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_gem_render_state.h"
+#include "i915_vgpu.h"
 #include "intel_lrc_reg.h"
 #include "intel_mocs.h"
 #include "intel_workarounds.h"
@@ -954,44 +955,40 @@ static void process_csb(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
-	struct drm_i915_private *i915 = engine->i915;
-
-	/* The HWSP contains a (cacheable) mirror of the CSB */
-	const u32 *buf =
-		&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
-	unsigned int head, tail;
-	bool fw = false;
+	const u32 * const buf = execlists->csb_status;
+	u8 head, tail;
 
 	/* Clear before reading to catch new interrupts */
 	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 	smp_mb__after_atomic();
 
-	if (unlikely(execlists->csb_use_mmio)) {
-		intel_uncore_forcewake_get(i915, execlists->fw_domains);
-		fw = true;
-
-		buf = (u32 * __force)
-			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
-
-		head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-		tail = GEN8_CSB_WRITE_PTR(head);
-		head = GEN8_CSB_READ_PTR(head);
-		execlists->csb_head = head;
-	} else {
-		const int write_idx =
-			intel_hws_csb_write_index(i915) -
-			I915_HWS_CSB_BUF0_INDEX;
+	/*
+	 * Note that csb_write, csb_status may be either in HWSP or mmio.
+	 * When reading from the csb_write mmio register, we have to be
+	 * careful to only use the GEN8_CSB_WRITE_PTR portion, which is
+	 * the low 4bits. As it happens we know the next 4bits are always
+	 * zero and so we can simply masked off the low u8 of the register
+	 * and treat it identically to reading from the HWSP (without having
+	 * to use explicit shifting and masking, and probably bifurcating
+	 * the code to handle the legacy mmio read).
+	 */
+	head = execlists->csb_head;
+	tail = READ_ONCE(*execlists->csb_write);
+	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
+	if (unlikely(head == tail))
+		return;
 
-		head = execlists->csb_head;
-		tail = READ_ONCE(buf[write_idx]);
-		rmb(); /* Hopefully paired with a wmb() in HW */
-	}
-	GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
-		  engine->name,
-		  head, GEN8_CSB_READ_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
-		  tail, GEN8_CSB_WRITE_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
+	/*
+	 * Hopefully paired with a wmb() in HW!
+	 *
+	 * We must complete the read of the write pointer before any reads
+	 * from the CSB, so that we do not see stale values. Without an rmb
+	 * (lfence) the HW may speculatively perform the CSB[] reads *before*
+	 * we perform the READ_ONCE(*csb_write).
+	 */
+	rmb();
 
-	while (head != tail) {
+	do {
 		struct i915_request *rq;
 		unsigned int status;
 		unsigned int count;
@@ -1017,12 +1014,12 @@ static void process_csb(struct intel_engine_cs *engine)
 		 * status notifier.
 		 */
 
-		status = READ_ONCE(buf[2 * head]); /* maybe mmio! */
 		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
 			  engine->name, head,
-			  status, buf[2*head + 1],
+			  buf[2 * head + 0], buf[2 * head + 1],
 			  execlists->active);
 
+		status = buf[2 * head];
 		if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
 			      GEN8_CTX_STATUS_PREEMPTED))
 			execlists_set_active(execlists,
@@ -1104,16 +1101,11 @@ static void process_csb(struct intel_engine_cs *engine)
 		} else {
 			port_set(port, port_pack(rq, count));
 		}
-	}
-
-	if (head != execlists->csb_head) {
-		execlists->csb_head = head;
-		writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
-		       i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-	}
+	} while (head != tail);
 
-	if (unlikely(fw))
-		intel_uncore_forcewake_put(i915, execlists->fw_domains);
+	writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
+	       execlists->csb_read);
+	execlists->csb_head = head;
 }
 
 /*
@@ -2431,28 +2423,11 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 static void
 logical_ring_setup(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-	enum forcewake_domains fw_domains;
-
 	intel_engine_setup_common(engine);
 
 	/* Intentionally left blank. */
 	engine->buffer = NULL;
 
-	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
-						    RING_ELSP(engine),
-						    FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_PTR(engine),
-						     FW_REG_READ | FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_BUF_BASE(engine),
-						     FW_REG_READ);
-
-	engine->execlists.fw_domains = fw_domains;
-
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 
@@ -2460,34 +2435,56 @@ logical_ring_setup(struct intel_engine_cs *engine)
 	logical_ring_default_irqs(engine);
 }
 
+static bool csb_force_mmio(struct drm_i915_private *i915)
+{
+	/* Older GVT emulation depends upon intercepting CSB mmio */
+	return intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915);
+}
+
 static int logical_ring_init(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	int ret;
 
 	ret = intel_engine_init_common(engine);
 	if (ret)
 		goto error;
 
-	if (HAS_LOGICAL_RING_ELSQ(engine->i915)) {
-		engine->execlists.submit_reg = engine->i915->regs +
+	if (HAS_LOGICAL_RING_ELSQ(i915)) {
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_SQ_CONTENTS(engine));
-		engine->execlists.ctrl_reg = engine->i915->regs +
+		execlists->ctrl_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_CONTROL(engine));
 	} else {
-		engine->execlists.submit_reg = engine->i915->regs +
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_ELSP(engine));
 	}
 
-	engine->execlists.preempt_complete_status = ~0u;
-	if (engine->i915->preempt_context) {
+	execlists->preempt_complete_status = ~0u;
+	if (i915->preempt_context) {
 		struct intel_context *ce =
-			to_intel_context(engine->i915->preempt_context, engine);
+			to_intel_context(i915->preempt_context, engine);
 
-		engine->execlists.preempt_complete_status =
+		execlists->preempt_complete_status =
 			upper_32_bits(ce->lrc_desc);
 	}
 
-	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
+	execlists->csb_head = GEN8_CSB_ENTRIES - 1;
+	execlists->csb_read =
+		i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine));
+	if (csb_force_mmio(i915)) {
+		execlists->csb_status = (u32 __force *)
+			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+
+		execlists->csb_write = (u32 __force *)execlists->csb_read;
+	} else {
+		execlists->csb_status =
+			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+
+		execlists->csb_write =
+			&engine->status_page.page_addr[intel_hws_csb_write_index(i915)];
+	}
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 78f01a35823a..25792889dbf4 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -300,24 +300,35 @@ struct intel_engine_execlists {
 	struct rb_node *first;
 
 	/**
-	 * @fw_domains: forcewake domains for irq tasklet
+	 * @csb_read: control register for Context Switch buffer
+	 *
+	 * Note this register is always in mmio.
 	 */
-	unsigned int fw_domains;
+	u32 __iomem *csb_read;
 
 	/**
-	 * @csb_head: context status buffer head
+	 * @csb_write: control register for Context Switch buffer
+	 *
+	 * Note this register may be either mmio or HWSP shadow.
 	 */
-	unsigned int csb_head;
+	u32 *csb_write;
 
 	/**
-	 * @csb_use_mmio: access csb through mmio, instead of hwsp
+	 * @csb_status: status array for Context Switch buffer
+	 *
+	 * Note these register may be either mmio or HWSP shadow.
 	 */
-	bool csb_use_mmio;
+	u32 *csb_status;
 
 	/**
 	 * @preempt_complete_status: expected CSB upon completing preemption
 	 */
 	u32 preempt_complete_status;
+
+	/**
+	 * @csb_head: context status buffer head
+	 */
+	u8 csb_head;
 };
 
 #define INTEL_ENGINE_CS_MAX_NAME 8
-- 
cgit v1.2.3


From f4b58f0438ba53002e2032e3817c8e847da9a9e1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:08 +0100
Subject: drm/i915/execlists: Reset CSB write pointer after reset

On HW reset, the HW clears the write pointer (to 0). But since it also
writes its first CSB entry to slot 0, we need to reset the write pointer
back to the element before (so the first entry we read is 0).

This is required for the next patch, where we trust the CSB completely!

v2: Use _MASKED_FIELD
v3: Store the reset value, so that we differentiate between mmio/hwsp
transparently and without pretense.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-6-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c        | 23 +++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.h |  9 +++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 81f000c245ab..88289d1d07e7 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -885,6 +885,21 @@ static void reset_irq(struct intel_engine_cs *engine)
 	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 }
 
+static void reset_csb_pointers(struct intel_engine_execlists *execlists)
+{
+	/*
+	 * After a reset, the HW starts writing into CSB entry [0]. We
+	 * therefore have to set our HEAD pointer back one entry so that
+	 * the *first* entry we check is entry 0. To complicate this further,
+	 * as we don't wait for the first interrupt after reset, we have to
+	 * fake the HW write to point back to the last entry so that our
+	 * inline comparison of our cached head position against the last HW
+	 * write works even before the first interrupt.
+	 */
+	execlists->csb_head = execlists->csb_write_reset;
+	WRITE_ONCE(*execlists->csb_write, execlists->csb_write_reset);
+}
+
 static void execlists_cancel_requests(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1971,7 +1986,7 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	__unwind_incomplete_requests(engine);
 
 	/* Following the reset, we need to reload the CSB read/write pointers */
-	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
+	reset_csb_pointers(&engine->execlists);
 
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
@@ -2470,7 +2485,6 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 			upper_32_bits(ce->lrc_desc);
 	}
 
-	execlists->csb_head = GEN8_CSB_ENTRIES - 1;
 	execlists->csb_read =
 		i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine));
 	if (csb_force_mmio(i915)) {
@@ -2478,13 +2492,18 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
 
 		execlists->csb_write = (u32 __force *)execlists->csb_read;
+		execlists->csb_write_reset =
+			_MASKED_FIELD(GEN8_CSB_WRITE_PTR_MASK,
+				      GEN8_CSB_ENTRIES - 1);
 	} else {
 		execlists->csb_status =
 			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
 
 		execlists->csb_write =
 			&engine->status_page.page_addr[intel_hws_csb_write_index(i915)];
+		execlists->csb_write_reset = GEN8_CSB_ENTRIES - 1;
 	}
+	reset_csb_pointers(execlists);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 25792889dbf4..b02620990859 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -325,6 +325,15 @@ struct intel_engine_execlists {
 	 */
 	u32 preempt_complete_status;
 
+	/**
+	 * @csb_write_reset: reset value for CSB write pointer
+	 *
+	 * As the CSB write pointer maybe either in HWSP or as a field
+	 * inside an mmio register, we want to reprogram it slightly
+	 * differently to avoid later confusion.
+	 */
+	u32 csb_write_reset;
+
 	/**
 	 * @csb_head: context status buffer head
 	 */
-- 
cgit v1.2.3


From 3800cd1953059b64593c7ca1022071b96bc40ef3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:09 +0100
Subject: drm/i915/execlists: Stop storing the CSB read pointer in the mmio
 register

As we now never read back our current head position from the CSB
pointers register, and the HW itself doesn't use it to prevent
overwriting unread CSB entries, we do not need to keep updating the
register. As it turns out this register is not listed as being shadowed,
and so requires forcewake -- but we haven't been taking forcewake around
it so the writes has probably been regularly dropped. Fortuitously, we
only read the value after a reset where it did not matter, and zero was
the right answer (well, close enough).

Mika pointed out that this was how we used to do it (accidentally!)
before he fixed it in commit cc53699b25b5 ("drm/i915: Use masked write
for Context Status Buffer Pointer").

References: cc53699b25b5 ("drm/i915: Use masked write for Context Status Buffer Pointer")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-7-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 88289d1d07e7..ed81f8ac60ca 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1118,8 +1118,6 @@ static void process_csb(struct intel_engine_cs *engine)
 		}
 	} while (head != tail);
 
-	writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
-	       execlists->csb_read);
 	execlists->csb_head = head;
 }
 
-- 
cgit v1.2.3


From fd8526e509020ed30298ab57d03edc97bef83962 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:10 +0100
Subject: drm/i915/execlists: Trust the CSB

Now that we use the CSB stored in the CPU friendly HWSP, we do not need
to track interrupts for when the mmio CSB registers are valid and can
just check where we read up to last from the cached HWSP. This means we
can forgo the atomic bit tracking from interrupt, and in the next patch
it means we can check the CSB at any time.

v2: Change the splitting inside reset_prepare, we only want to lose
testing the interrupt in this patch, the next patch requires the change
in locking

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-8-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c         | 11 +++--------
 drivers/gpu/drm/i915/intel_engine_cs.c  |  8 ++------
 drivers/gpu/drm/i915/intel_lrc.c        | 29 ++++-------------------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  1 -
 4 files changed, 9 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c95cb278a8bc..435a4444314c 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1493,15 +1493,10 @@ static void snb_gt_irq_handler(struct drm_i915_private *dev_priv,
 static void
 gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 {
-	struct intel_engine_execlists * const execlists = &engine->execlists;
 	bool tasklet = false;
 
-	if (iir & GT_CONTEXT_SWITCH_INTERRUPT) {
-		if (READ_ONCE(engine->execlists.active)) {
-			set_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-			tasklet = true;
-		}
-	}
+	if (iir & GT_CONTEXT_SWITCH_INTERRUPT)
+		tasklet = true;
 
 	if (iir & GT_RENDER_USER_INTERRUPT) {
 		notify_ring(engine);
@@ -1509,7 +1504,7 @@ gen8_cs_irq_handler(struct intel_engine_cs *engine, u32 iir)
 	}
 
 	if (tasklet)
-		tasklet_hi_schedule(&execlists->tasklet);
+		tasklet_hi_schedule(&engine->execlists.tasklet);
 }
 
 static void gen8_gt_irq_ack(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 7209c22798e6..ace93958689e 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1353,12 +1353,10 @@ static void intel_engine_print_registers(const struct intel_engine_cs *engine,
 		ptr = I915_READ(RING_CONTEXT_STATUS_PTR(engine));
 		read = GEN8_CSB_READ_PTR(ptr);
 		write = GEN8_CSB_WRITE_PTR(ptr);
-		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], interrupt posted? %s, tasklet queued? %s (%s)\n",
+		drm_printf(m, "\tExeclist CSB read %d [%d cached], write %d [%d from hws], tasklet queued? %s (%s)\n",
 			   read, execlists->csb_head,
 			   write,
 			   intel_read_status_page(engine, intel_hws_csb_write_index(engine->i915)),
-			   yesno(test_bit(ENGINE_IRQ_EXECLIST,
-					  &engine->irq_posted)),
 			   yesno(test_bit(TASKLET_STATE_SCHED,
 					  &engine->execlists.tasklet.state)),
 			   enableddisabled(!atomic_read(&engine->execlists.tasklet.count)));
@@ -1570,11 +1568,9 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	spin_unlock(&b->rb_lock);
 	local_irq_restore(flags);
 
-	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s) (execlists? %s)\n",
+	drm_printf(m, "IRQ? 0x%lx (breadcrumbs? %s)\n",
 		   engine->irq_posted,
 		   yesno(test_bit(ENGINE_IRQ_BREADCRUMB,
-				  &engine->irq_posted)),
-		   yesno(test_bit(ENGINE_IRQ_EXECLIST,
 				  &engine->irq_posted)));
 
 	drm_printf(m, "HWSP:\n");
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ed81f8ac60ca..d835da128a17 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -875,14 +875,6 @@ static void reset_irq(struct intel_engine_cs *engine)
 	smp_store_mb(engine->execlists.active, 0);
 
 	clear_gtiir(engine);
-
-	/*
-	 * The port is checked prior to scheduling a tasklet, but
-	 * just in case we have suspended the tasklet to do the
-	 * wedging make sure that when it wakes, it decides there
-	 * is no work to do by clearing the irq_posted bit.
-	 */
-	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 }
 
 static void reset_csb_pointers(struct intel_engine_execlists *execlists)
@@ -973,10 +965,6 @@ static void process_csb(struct intel_engine_cs *engine)
 	const u32 * const buf = execlists->csb_status;
 	u8 head, tail;
 
-	/* Clear before reading to catch new interrupts */
-	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
-	smp_mb__after_atomic();
-
 	/*
 	 * Note that csb_write, csb_status may be either in HWSP or mmio.
 	 * When reading from the csb_write mmio register, we have to be
@@ -1129,11 +1117,10 @@ static void execlists_submission_tasklet(unsigned long data)
 {
 	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
 
-	GEM_TRACE("%s awake?=%d, active=%x, irq-posted?=%d\n",
+	GEM_TRACE("%s awake?=%d, active=%x\n",
 		  engine->name,
 		  engine->i915->gt.awake,
-		  engine->execlists.active,
-		  test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted));
+		  engine->execlists.active);
 
 	/*
 	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
@@ -1145,14 +1132,7 @@ static void execlists_submission_tasklet(unsigned long data)
 	 */
 	GEM_BUG_ON(!engine->i915->gt.awake);
 
-	/*
-	 * Prefer doing test_and_clear_bit() as a two stage operation to avoid
-	 * imposing the cost of a locked atomic transaction when submitting a
-	 * new request (outside of the context-switch interrupt).
-	 */
-	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
-		process_csb(engine);
-
+	process_csb(engine);
 	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
 		execlists_dequeue(engine);
 }
@@ -1920,8 +1900,7 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	 * and avoid blaming an innocent request if the stall was due to the
 	 * preemption itself.
 	 */
-	if (test_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted))
-		process_csb(engine);
+	process_csb(engine);
 
 	/*
 	 * The last active request can then be no later than the last request
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index b02620990859..ce6cc2a6cf7a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -367,7 +367,6 @@ struct intel_engine_cs {
 
 	unsigned long irq_posted;
 #define ENGINE_IRQ_BREADCRUMB 0
-#define ENGINE_IRQ_EXECLIST 1
 
 	/* Rather than have every client wait upon all user interrupts,
 	 * with the herd waking after every interrupt and each doing the
-- 
cgit v1.2.3


From 9512f985c32d45ab439a210981e0d73071da395a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 28 Jun 2018 21:12:11 +0100
Subject: drm/i915/execlists: Direct submission of new requests (avoid
 tasklet/ksoftirqd)

Back in commit 27af5eea54d1 ("drm/i915: Move execlists irq handler to a
bottom half"), we came to the conclusion that running our CSB processing
and ELSP submission from inside the irq handler was a bad idea. A really
bad idea as we could impose nearly 1s latency on other users of the
system, on average! Deferring our work to a tasklet allowed us to do the
processing with irqs enabled, reducing the impact to an average of about
50us.

We have since eradicated the use of forcewaked mmio from inside the CSB
processing and ELSP submission, bringing the impact down to around 5us
(on Kabylake); an order of magnitude better than our measurements 2
years ago on Broadwell and only about 2x worse on average than the
gem_syslatency on an unladen system.

In this iteration of the tasklet-vs-direct submission debate, we seek a
compromise where by we submit new requests immediately to the HW but
defer processing the CS interrupt onto a tasklet. We gain the advantage
of low-latency and ksoftirqd avoidance when waking up the HW, while
avoiding the system-wide starvation of our CS irq-storms.

Comparing the impact on the maximum latency observed (that is the time
stolen from an RT process) over a 120s interval, repeated several times
(using gem_syslatency, similar to RT's cyclictest) while the system is
fully laden with i915 nops, we see that direct submission an actually
improve the worse case.

Maximum latency in microseconds of a third party RT thread
(gem_syslatency -t 120 -f 2)
  x Always using tasklets (a couple of >1000us outliers removed)
  + Only using tasklets from CS irq, direct submission of requests
+------------------------------------------------------------------------+
|          +                                                             |
|          +                                                             |
|          +                                                             |
|          +       +                                                     |
|          + +     +                                                     |
|       +  + +     +  x     x     x                                      |
|      +++ + +     +  x  x  x  x  x  x                                   |
|      +++ + ++  + +  *x x  x  x  x  x                                   |
|      +++ + ++  + *  *x x  *  x  x  x                                   |
|    + +++ + ++  * * +*xxx  *  x  x  xx                                  |
|    * +++ + ++++* *x+**xx+ *  x  x xxxx x                               |
|   **x++++*++**+*x*x****x+ * +x xx xxxx x          x                    |
|x* ******+***************++*+***xxxxxx* xx*x     xxx +                x+|
|             |__________MA___________|                                  |
|      |______M__A________|                                              |
+------------------------------------------------------------------------+
    N           Min           Max        Median           Avg        Stddev
x 118            91           186           124     125.28814     16.279137
+ 120            92           187           109     112.00833     13.458617
Difference at 95.0% confidence
	-13.2798 +/- 3.79219
	-10.5994% +/- 3.02677%
	(Student's t, pooled s = 14.9237)

However the mean latency is adversely affected:

Mean latency in microseconds of a third party RT thread
(gem_syslatency -t 120 -f 1)
  x Always using tasklets
  + Only using tasklets from CS irq, direct submission of requests
+------------------------------------------------------------------------+
|           xxxxxx                                        +   ++         |
|           xxxxxx                                        +   ++         |
|           xxxxxx                                      + +++ ++         |
|           xxxxxxx                                     +++++ ++         |
|           xxxxxxx                                     +++++ ++         |
|           xxxxxxx                                     +++++ +++        |
|           xxxxxxx                                   + ++++++++++       |
|           xxxxxxxx                                 ++ ++++++++++       |
|           xxxxxxxx                                 ++ ++++++++++       |
|          xxxxxxxxxx                                +++++++++++++++     |
|         xxxxxxxxxxx    x                           +++++++++++++++     |
|x       xxxxxxxxxxxxx   x           +            + ++++++++++++++++++  +|
|           |__A__|                                                      |
|                                                      |____A___|        |
+------------------------------------------------------------------------+
    N           Min           Max        Median           Avg        Stddev
x 120         3.506         3.727         3.631     3.6321417    0.02773109
+ 120         3.834         4.149         4.039     4.0375167   0.041221676
Difference at 95.0% confidence
	0.405375 +/- 0.00888913
	11.1608% +/- 0.244735%
	(Student's t, pooled s = 0.03513)

However, since the mean latency corresponds to the amount of irqsoff
processing we have to do for a CS interrupt, we only need to speed that
up to benefit not just system latency but our own throughput.

v2: Remember to defer submissions when under reset.
v4: Only use direct submission for new requests
v5: Be aware that with mixing direct tasklet evaluation and deferred
tasklets, we may end up idling before running the deferred tasklet.
v6: Remove the redudant likely() from tasklet_is_enabled(), restrict the
annotation to reset_in_progress().
v7: Take the full timeline.lock when enabling perf_pmu stats as the
tasklet is no longer a valid guard. A consequence is that the stats are
now only valid for engines also using the timeline.lock to process
state.

Testcase: igt/gem_exec_latency/*rthog*
References: 27af5eea54d1 ("drm/i915: Move execlists irq handler to a bottom half")
Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-9-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.h        |   5 ++
 drivers/gpu/drm/i915/intel_engine_cs.c |   8 +--
 drivers/gpu/drm/i915/intel_lrc.c       | 102 +++++++++++++++++++++------------
 3 files changed, 75 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.h b/drivers/gpu/drm/i915/i915_gem.h
index 261da577829a..e46592956872 100644
--- a/drivers/gpu/drm/i915/i915_gem.h
+++ b/drivers/gpu/drm/i915/i915_gem.h
@@ -88,4 +88,9 @@ static inline void __tasklet_enable_sync_once(struct tasklet_struct *t)
 		tasklet_kill(t);
 }
 
+static inline bool __tasklet_is_enabled(const struct tasklet_struct *t)
+{
+	return !atomic_read(&t->count);
+}
+
 #endif /* __I915_GEM_H__ */
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index ace93958689e..01862884a436 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -1619,8 +1619,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	if (!intel_engine_supports_stats(engine))
 		return -ENODEV;
 
-	tasklet_disable(&execlists->tasklet);
-	write_seqlock_irqsave(&engine->stats.lock, flags);
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+	write_seqlock(&engine->stats.lock);
 
 	if (unlikely(engine->stats.enabled == ~0)) {
 		err = -EBUSY;
@@ -1644,8 +1644,8 @@ int intel_enable_engine_stats(struct intel_engine_cs *engine)
 	}
 
 unlock:
-	write_sequnlock_irqrestore(&engine->stats.lock, flags);
-	tasklet_enable(&execlists->tasklet);
+	write_sequnlock(&engine->stats.lock);
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 
 	return err;
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d835da128a17..6ab6ddb103d1 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -563,12 +563,14 @@ static void complete_preempt_context(struct intel_engine_execlists *execlists)
 	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
 
 	execlists_cancel_port_requests(execlists);
-	execlists_unwind_incomplete_requests(execlists);
+	__unwind_incomplete_requests(container_of(execlists,
+						  struct intel_engine_cs,
+						  execlists));
 
 	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
-static void __execlists_dequeue(struct intel_engine_cs *engine)
+static void execlists_dequeue(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
@@ -578,9 +580,8 @@ static void __execlists_dequeue(struct intel_engine_cs *engine)
 	struct rb_node *rb;
 	bool submit = false;
 
-	lockdep_assert_held(&engine->timeline.lock);
-
-	/* Hardware submission is through 2 ports. Conceptually each port
+	/*
+	 * Hardware submission is through 2 ports. Conceptually each port
 	 * has a (RING_START, RING_HEAD, RING_TAIL) tuple. RING_START is
 	 * static for a context, and unique to each, so we only execute
 	 * requests belonging to a single context from each ring. RING_HEAD
@@ -770,15 +771,6 @@ done:
 		   !port_isset(engine->execlists.port));
 }
 
-static void execlists_dequeue(struct intel_engine_cs *engine)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&engine->timeline.lock, flags);
-	__execlists_dequeue(engine);
-	spin_unlock_irqrestore(&engine->timeline.lock, flags);
-}
-
 void
 execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
 {
@@ -958,6 +950,12 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
+static inline bool
+reset_in_progress(const struct intel_engine_execlists *execlists)
+{
+	return unlikely(!__tasklet_is_enabled(&execlists->tasklet));
+}
+
 static void process_csb(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -1109,18 +1107,9 @@ static void process_csb(struct intel_engine_cs *engine)
 	execlists->csb_head = head;
 }
 
-/*
- * Check the unread Context Status Buffers and manage the submission of new
- * contexts to the ELSP accordingly.
- */
-static void execlists_submission_tasklet(unsigned long data)
+static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 {
-	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
-
-	GEM_TRACE("%s awake?=%d, active=%x\n",
-		  engine->name,
-		  engine->i915->gt.awake,
-		  engine->execlists.active);
+	lockdep_assert_held(&engine->timeline.lock);
 
 	/*
 	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
@@ -1137,6 +1126,28 @@ static void execlists_submission_tasklet(unsigned long data)
 		execlists_dequeue(engine);
 }
 
+/*
+ * Check the unread Context Status Buffers and manage the submission of new
+ * contexts to the ELSP accordingly.
+ */
+static void execlists_submission_tasklet(unsigned long data)
+{
+	struct intel_engine_cs * const engine = (struct intel_engine_cs *)data;
+	unsigned long flags;
+
+	GEM_TRACE("%s awake?=%d, active=%x\n",
+		  engine->name,
+		  engine->i915->gt.awake,
+		  engine->execlists.active);
+
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+
+	if (engine->i915->gt.awake) /* we may be delayed until after we idle! */
+		__execlists_submission_tasklet(engine);
+
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
+}
+
 static void queue_request(struct intel_engine_cs *engine,
 			  struct i915_sched_node *node,
 			  int prio)
@@ -1145,16 +1156,30 @@ static void queue_request(struct intel_engine_cs *engine,
 		      &lookup_priolist(engine, prio)->requests);
 }
 
-static void __submit_queue(struct intel_engine_cs *engine, int prio)
+static void __update_queue(struct intel_engine_cs *engine, int prio)
 {
 	engine->execlists.queue_priority = prio;
-	tasklet_hi_schedule(&engine->execlists.tasklet);
+}
+
+static void __submit_queue_imm(struct intel_engine_cs *engine)
+{
+	struct intel_engine_execlists * const execlists = &engine->execlists;
+
+	if (reset_in_progress(execlists))
+		return; /* defer until we restart the engine following reset */
+
+	if (execlists->tasklet.func == execlists_submission_tasklet)
+		__execlists_submission_tasklet(engine);
+	else
+		tasklet_hi_schedule(&execlists->tasklet);
 }
 
 static void submit_queue(struct intel_engine_cs *engine, int prio)
 {
-	if (prio > engine->execlists.queue_priority)
-		__submit_queue(engine, prio);
+	if (prio > engine->execlists.queue_priority) {
+		__update_queue(engine, prio);
+		__submit_queue_imm(engine);
+	}
 }
 
 static void execlists_submit_request(struct i915_request *request)
@@ -1166,11 +1191,12 @@ static void execlists_submit_request(struct i915_request *request)
 	spin_lock_irqsave(&engine->timeline.lock, flags);
 
 	queue_request(engine, &request->sched, rq_prio(request));
-	submit_queue(engine, rq_prio(request));
 
 	GEM_BUG_ON(!engine->execlists.first);
 	GEM_BUG_ON(list_empty(&request->sched.link));
 
+	submit_queue(engine, rq_prio(request));
+
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
@@ -1297,8 +1323,11 @@ static void execlists_schedule(struct i915_request *request,
 		}
 
 		if (prio > engine->execlists.queue_priority &&
-		    i915_sw_fence_done(&sched_to_request(node)->submit))
-			__submit_queue(engine, prio);
+		    i915_sw_fence_done(&sched_to_request(node)->submit)) {
+			/* defer submission until after all of our updates */
+			__update_queue(engine, prio);
+			tasklet_hi_schedule(&engine->execlists.tasklet);
+		}
 	}
 
 	spin_unlock_irq(&engine->timeline.lock);
@@ -1879,6 +1908,7 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct i915_request *request, *active;
+	unsigned long flags;
 
 	GEM_TRACE("%s\n", engine->name);
 
@@ -1893,6 +1923,8 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	 */
 	__tasklet_disable_sync_once(&execlists->tasklet);
 
+	spin_lock_irqsave(&engine->timeline.lock, flags);
+
 	/*
 	 * We want to flush the pending context switches, having disabled
 	 * the tasklet above, we can assume exclusive access to the execlists.
@@ -1910,15 +1942,12 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 	active = NULL;
 	request = port_request(execlists->port);
 	if (request) {
-		unsigned long flags;
-
 		/*
 		 * Prevent the breadcrumb from advancing before we decide
 		 * which request is currently active.
 		 */
 		intel_engine_stop_cs(engine);
 
-		spin_lock_irqsave(&engine->timeline.lock, flags);
 		list_for_each_entry_from_reverse(request,
 						 &engine->timeline.requests,
 						 link) {
@@ -1928,9 +1957,10 @@ execlists_reset_prepare(struct intel_engine_cs *engine)
 
 			active = request;
 		}
-		spin_unlock_irqrestore(&engine->timeline.lock, flags);
 	}
 
+	spin_unlock_irqrestore(&engine->timeline.lock, flags);
+
 	return active;
 }
 
-- 
cgit v1.2.3


From b204bc74840080136bf11643e998dc83afc2c11e Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:19 +0800
Subject: net: hns3: remove hclge_get_vector_index from
 hclge_bind_ring_with_vector

In hclge_unmap_ring_frm_vector, there are 2 steps:
step 1: get vector index.
step 2 unbind ring with vector.

But it gets vector id again in step 2 interface. This patch
removes hclge_get_vector_index from hclge_bind_ring_with_vector,
and make the step the same with hns3 PF driver.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 24 +++++++++++++---------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index a17872aab168..b3d8237b83d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -547,24 +547,18 @@ static int hclgevf_get_tc_size(struct hnae3_handle *handle)
 }
 
 static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
-				       int vector,
+				       int vector_id,
 				       struct hnae3_ring_chain_node *ring_chain)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
 	struct hnae3_ring_chain_node *node;
 	struct hclge_mbx_vf_to_pf_cmd *req;
 	struct hclgevf_desc desc;
-	int i = 0, vector_id;
+	int i = 0;
 	int status;
 	u8 type;
 
 	req = (struct hclge_mbx_vf_to_pf_cmd *)desc.data;
-	vector_id = hclgevf_get_vector_index(hdev, vector);
-	if (vector_id < 0) {
-		dev_err(&handle->pdev->dev,
-			"Get vector index fail. ret =%d\n", vector_id);
-		return vector_id;
-	}
 
 	for (node = ring_chain; node; node = node->next) {
 		int idx_offset = HCLGE_MBX_RING_MAP_BASIC_MSG_NUM +
@@ -617,7 +611,17 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
 static int hclgevf_map_ring_to_vector(struct hnae3_handle *handle, int vector,
 				      struct hnae3_ring_chain_node *ring_chain)
 {
-	return hclgevf_bind_ring_to_vector(handle, true, vector, ring_chain);
+	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int vector_id;
+
+	vector_id = hclgevf_get_vector_index(hdev, vector);
+	if (vector_id < 0) {
+		dev_err(&handle->pdev->dev,
+			"Get vector index fail. ret =%d\n", vector_id);
+		return vector_id;
+	}
+
+	return hclgevf_bind_ring_to_vector(handle, true, vector_id, ring_chain);
 }
 
 static int hclgevf_unmap_ring_from_vector(
@@ -635,7 +639,7 @@ static int hclgevf_unmap_ring_from_vector(
 		return vector_id;
 	}
 
-	ret = hclgevf_bind_ring_to_vector(handle, false, vector, ring_chain);
+	ret = hclgevf_bind_ring_to_vector(handle, false, vector_id, ring_chain);
 	if (ret)
 		dev_err(&handle->pdev->dev,
 			"Unmap ring from vector fail. vector=%d, ret =%d\n",
-- 
cgit v1.2.3


From e718a93fee036fa8f9b09c76319c81713473287b Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:20 +0800
Subject: net: hns3: rename the interface for init_client_instance and
 uninit_client_instance

The interface init_client_instance and uninit_client_instance
do not register anything, only initialize the client instance.
This patch rename the related interface to make the function
name to indicate the purpose.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 31 +++++++---------------
 1 file changed, 9 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index b3d8237b83d9..3a8d7e0f4f56 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1586,9 +1586,10 @@ static void hclgevf_misc_irq_uninit(struct hclgevf_dev *hdev)
 	hclgevf_free_vector(hdev, 0);
 }
 
-static int hclgevf_init_instance(struct hclgevf_dev *hdev,
-				 struct hnae3_client *client)
+static int hclgevf_init_client_instance(struct hnae3_client *client,
+					struct hnae3_ae_dev *ae_dev)
 {
+	struct hclgevf_dev *hdev = ae_dev->priv;
 	int ret;
 
 	switch (client->type) {
@@ -1639,9 +1640,11 @@ static int hclgevf_init_instance(struct hclgevf_dev *hdev,
 	return 0;
 }
 
-static void hclgevf_uninit_instance(struct hclgevf_dev *hdev,
-				    struct hnae3_client *client)
+static void hclgevf_uninit_client_instance(struct hnae3_client *client,
+					   struct hnae3_ae_dev *ae_dev)
 {
+	struct hclgevf_dev *hdev = ae_dev->priv;
+
 	/* un-init roce, if it exists */
 	if (hdev->roce_client)
 		hdev->roce_client->ops->uninit_instance(&hdev->roce, 0);
@@ -1652,22 +1655,6 @@ static void hclgevf_uninit_instance(struct hclgevf_dev *hdev,
 		client->ops->uninit_instance(&hdev->nic, 0);
 }
 
-static int hclgevf_register_client(struct hnae3_client *client,
-				   struct hnae3_ae_dev *ae_dev)
-{
-	struct hclgevf_dev *hdev = ae_dev->priv;
-
-	return hclgevf_init_instance(hdev, client);
-}
-
-static void hclgevf_unregister_client(struct hnae3_client *client,
-				      struct hnae3_ae_dev *ae_dev)
-{
-	struct hclgevf_dev *hdev = ae_dev->priv;
-
-	hclgevf_uninit_instance(hdev, client);
-}
-
 static int hclgevf_pci_init(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
@@ -1928,8 +1915,8 @@ void hclgevf_update_speed_duplex(struct hclgevf_dev *hdev, u32 speed,
 static const struct hnae3_ae_ops hclgevf_ops = {
 	.init_ae_dev = hclgevf_init_ae_dev,
 	.uninit_ae_dev = hclgevf_uninit_ae_dev,
-	.init_client_instance = hclgevf_register_client,
-	.uninit_client_instance = hclgevf_unregister_client,
+	.init_client_instance = hclgevf_init_client_instance,
+	.uninit_client_instance = hclgevf_uninit_client_instance,
 	.start = hclgevf_ae_start,
 	.stop = hclgevf_ae_stop,
 	.map_ring_to_vector = hclgevf_map_ring_to_vector,
-- 
cgit v1.2.3


From 36cbbdf6439729878271ff15422a643d13f133d4 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:21 +0800
Subject: net: hns3: add vector status check before free vector

If the hdev->vector_status[vector_id] is already HCLGE_INVALID_VPORT,
should log the error and return.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c   | 6 ++++++
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 6 ++++++
 2 files changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index d318d35e598f..2b903f476149 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2614,6 +2614,12 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data)
 
 static void hclge_free_vector(struct hclge_dev *hdev, int vector_id)
 {
+	if (hdev->vector_status[vector_id] == HCLGE_INVALID_VPORT) {
+		dev_warn(&hdev->pdev->dev,
+			 "vector(vector_id %d) has been freed.\n", vector_id);
+		return;
+	}
+
 	hdev->vector_status[vector_id] = HCLGE_INVALID_VPORT;
 	hdev->num_msi_left += 1;
 	hdev->num_msi_used -= 1;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 3a8d7e0f4f56..1eb61c126988 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -330,6 +330,12 @@ static int hclgevf_set_handle_info(struct hclgevf_dev *hdev)
 
 static void hclgevf_free_vector(struct hclgevf_dev *hdev, int vector_id)
 {
+	if (hdev->vector_status[vector_id] == HCLGEVF_INVALID_VPORT) {
+		dev_warn(&hdev->pdev->dev,
+			 "vector(vector_id %d) has been freed.\n", vector_id);
+		return;
+	}
+
 	hdev->vector_status[vector_id] = HCLGEVF_INVALID_VPORT;
 	hdev->num_msi_left += 1;
 	hdev->num_msi_used -= 1;
-- 
cgit v1.2.3


From 94c5e532130207f6ecfe0e1afd4ed3495ec1706f Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:22 +0800
Subject: net: hns3: add l4_type check for both ipv4 and ipv6

HW supports UDP, TCP and SCTP packets checksum for both ipv4 and
ipv6,  but do not support other type packets checksum for ipv4 or
ipv6.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 25a73bb2e642..99bb6a82626a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2103,11 +2103,11 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		skb->csum_level = 1;
 	case HNS3_OL4_TYPE_NO_TUN:
 		/* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */
-		if (l3_type == HNS3_L3_TYPE_IPV4 ||
-		    (l3_type == HNS3_L3_TYPE_IPV6 &&
-		     (l4_type == HNS3_L4_TYPE_UDP ||
-		      l4_type == HNS3_L4_TYPE_TCP ||
-		      l4_type == HNS3_L4_TYPE_SCTP)))
+		if ((l3_type == HNS3_L3_TYPE_IPV4 ||
+		     l3_type == HNS3_L3_TYPE_IPV6) &&
+		    (l4_type == HNS3_L4_TYPE_UDP ||
+		     l4_type == HNS3_L4_TYPE_TCP ||
+		     l4_type == HNS3_L4_TYPE_SCTP))
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 		break;
 	}
-- 
cgit v1.2.3


From 0e6084aa1c4eba8913143ea30254d50ed01724eb Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:23 +0800
Subject: net: hns3: add unlikely for error check

The first bd of a packet is invalid and invalid ring head for tx
IRQ is not offen, they may occur when there is error,
Add unlikely for error check branch is better for performance.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 99bb6a82626a..1a68952339c2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1917,7 +1917,7 @@ bool hns3_clean_tx_ring(struct hns3_enet_ring *ring, int budget)
 	if (is_ring_empty(ring) || head == ring->next_to_clean)
 		return true; /* no data to poll */
 
-	if (!is_valid_clean_head(ring, head)) {
+	if (unlikely(!is_valid_clean_head(ring, head))) {
 		netdev_err(netdev, "wrong head (%d, %d-%d)\n", head,
 			   ring->next_to_use, ring->next_to_clean);
 
@@ -2174,7 +2174,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
 	/* Check valid BD */
-	if (!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))
+	if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
 		return -EFAULT;
 
 	va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
-- 
cgit v1.2.3


From fe589e0454b3a18ab9aaddaa8b4925e629d46792 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:24 +0800
Subject: net: hns3: remove unused head file in hnae3.c

linux/slab.h is not used in hnae3.h, this patch removes it.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 9d79dad2c6aa..3e5c83f6d8b1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/list.h>
-#include <linux/slab.h>
 #include <linux/spinlock.h>
 
 #include "hnae3.h"
-- 
cgit v1.2.3


From 48569cdaaf8b624915b9ec07ce90e9d4b35af33a Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:25 +0800
Subject: net: hns3: extraction an interface for state init|uninit

Extraction an interface for state init|uninit to make the code
easier to read.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 42 +++++++++++++---------
 1 file changed, 26 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 2b903f476149..805c7807ec72 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5568,6 +5568,30 @@ static void hclge_pci_uninit(struct hclge_dev *hdev)
 	pci_disable_device(pdev);
 }
 
+static void hclge_state_init(struct hclge_dev *hdev)
+{
+	set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state);
+	set_bit(HCLGE_STATE_DOWN, &hdev->state);
+	clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state);
+	clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+	clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state);
+	clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
+}
+
+static void hclge_state_uninit(struct hclge_dev *hdev)
+{
+	set_bit(HCLGE_STATE_DOWN, &hdev->state);
+
+	if (hdev->service_timer.function)
+		del_timer_sync(&hdev->service_timer);
+	if (hdev->service_task.func)
+		cancel_work_sync(&hdev->service_task);
+	if (hdev->rst_service_task.func)
+		cancel_work_sync(&hdev->rst_service_task);
+	if (hdev->mbx_service_task.func)
+		cancel_work_sync(&hdev->mbx_service_task);
+}
+
 static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 {
 	struct pci_dev *pdev = ae_dev->pdev;
@@ -5708,12 +5732,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	/* Enable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, true);
 
-	set_bit(HCLGE_STATE_SERVICE_INITED, &hdev->state);
-	set_bit(HCLGE_STATE_DOWN, &hdev->state);
-	clear_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state);
-	clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
-	clear_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state);
-	clear_bit(HCLGE_STATE_MBX_HANDLING, &hdev->state);
+	hclge_state_init(hdev);
 
 	pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME);
 	return 0;
@@ -5818,16 +5837,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 	struct hclge_dev *hdev = ae_dev->priv;
 	struct hclge_mac *mac = &hdev->hw.mac;
 
-	set_bit(HCLGE_STATE_DOWN, &hdev->state);
-
-	if (hdev->service_timer.function)
-		del_timer_sync(&hdev->service_timer);
-	if (hdev->service_task.func)
-		cancel_work_sync(&hdev->service_task);
-	if (hdev->rst_service_task.func)
-		cancel_work_sync(&hdev->rst_service_task);
-	if (hdev->mbx_service_task.func)
-		cancel_work_sync(&hdev->mbx_service_task);
+	hclge_state_uninit(hdev);
 
 	if (mac->phydev)
 		mdiobus_unregister(mac->mdio_bus);
-- 
cgit v1.2.3


From ccc2bef8298031f5a74f0d9b39010379370035a2 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:26 +0800
Subject: net: hns3: print the ret value in error information

Print the ret value in error information can help find the reason.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 3e5c83f6d8b1..1a02620b281a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -94,7 +94,7 @@ static int hnae3_match_n_instantiate(struct hnae3_client *client,
 		ret = ae_dev->ops->init_client_instance(client, ae_dev);
 		if (ret) {
 			dev_err(&ae_dev->pdev->dev,
-				"fail to instantiate client\n");
+				"fail to instantiate client, ret = %d\n", ret);
 			return ret;
 		}
 
@@ -134,7 +134,8 @@ int hnae3_register_client(struct hnae3_client *client)
 		ret = hnae3_match_n_instantiate(client, ae_dev, true);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
-				"match and instantiation failed for port\n");
+				"match and instantiation failed for port, ret = %d\n",
+				ret);
 	}
 
 exit:
@@ -184,7 +185,8 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 		ae_dev->ops = ae_algo->ops;
 		ret = ae_algo->ops->init_ae_dev(ae_dev);
 		if (ret) {
-			dev_err(&ae_dev->pdev->dev, "init ae_dev error.\n");
+			dev_err(&ae_dev->pdev->dev,
+				"init ae_dev error, ret = %d\n", ret);
 			continue;
 		}
 
@@ -197,7 +199,8 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 			ret = hnae3_match_n_instantiate(client, ae_dev, true);
 			if (ret)
 				dev_err(&ae_dev->pdev->dev,
-					"match and instantiation failed\n");
+					"match and instantiation failed, ret = %d\n",
+					ret);
 		}
 	}
 
@@ -270,7 +273,8 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 		/* ae_dev init should set flag */
 		ret = ae_dev->ops->init_ae_dev(ae_dev);
 		if (ret) {
-			dev_err(&ae_dev->pdev->dev, "init ae_dev error\n");
+			dev_err(&ae_dev->pdev->dev,
+				"init ae_dev error, ret = %d\n", ret);
 			goto out_err;
 		}
 
@@ -285,7 +289,8 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 		ret = hnae3_match_n_instantiate(client, ae_dev, true);
 		if (ret)
 			dev_err(&ae_dev->pdev->dev,
-				"match and instantiation failed\n");
+				"match and instantiation failed, ret = %d\n",
+				ret);
 	}
 
 out_err:
-- 
cgit v1.2.3


From 43e2b1c7f4a498520c741b4c0a89f8475bd8b950 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Thu, 28 Jun 2018 12:12:27 +0800
Subject: net: hns3: remove the Redundant put_vector in hns3_client_uninit

The interface h->ae_algo->ops->put_vector is called in both
hns3_nic_dealloc_vector_data and hns3_nic_uninit_vector_data in
hns3_client_uninit, this will cause vector freed twice.
This patch remove the Redundant put_vector to make vector freed
only once.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 1a68952339c2..beca36491025 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2745,10 +2745,6 @@ static int hns3_nic_uninit_vector_data(struct hns3_nic_priv *priv)
 		if (ret)
 			return ret;
 
-		ret = h->ae_algo->ops->put_vector(h, tqp_vector->vector_irq);
-		if (ret)
-			return ret;
-
 		hns3_free_vector_ring_chain(tqp_vector, &vector_ring_chain);
 
 		if (priv->tqp_vector[i].irq_init_flag == HNS3_VECTOR_INITED) {
-- 
cgit v1.2.3


From 541a7bd6bf23a1f4b5a1353b175279e0ba407871 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 Jun 2018 12:12:28 +0800
Subject: net: hns3: remove back in struct hclge_hw

hclge_hw is embedded in hclge_dev, so use container_of instead of
back to get hclge_dev.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c  | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 1 -
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 -
 3 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index c36d64710fa6..7049d0bc72ac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -152,7 +152,7 @@ static void hclge_cmd_init_regs(struct hclge_hw *hw)
 
 static int hclge_cmd_csq_clean(struct hclge_hw *hw)
 {
-	struct hclge_dev *hdev = (struct hclge_dev *)hw->back;
+	struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
 	struct hclge_cmq_ring *csq = &hw->cmq.csq;
 	u16 ntc = csq->next_to_clean;
 	struct hclge_desc *desc;
@@ -216,7 +216,7 @@ static bool hclge_is_special_opcode(u16 opcode)
  **/
 int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 {
-	struct hclge_dev *hdev = (struct hclge_dev *)hw->back;
+	struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
 	struct hclge_desc *desc_to_use;
 	bool complete = false;
 	u32 timeout = 0;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 805c7807ec72..14a6991375d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5537,7 +5537,6 @@ static int hclge_pci_init(struct hclge_dev *hdev)
 
 	pci_set_master(pdev);
 	hw = &hdev->hw;
-	hw->back = hdev;
 	hw->io_base = pcim_iomap(pdev, 2, 0);
 	if (!hw->io_base) {
 		dev_err(&pdev->dev, "Can't map configuration register space\n");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 7488534528cd..71d38b852c56 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -190,7 +190,6 @@ struct hclge_hw {
 	int num_vec;
 	struct hclge_cmq cmq;
 	struct hclge_caps caps;
-	void *back;
 };
 
 /* TQP stats */
-- 
cgit v1.2.3


From ab68059e15d7a05d162716fc0b3ca04b7df46c65 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Thu, 28 Jun 2018 12:12:29 +0800
Subject: net: hns3: use lower_32_bits and upper_32_bits

MACRO lower_32_bits and upper_32_bits can help to get bits 0-31
and bits 32-63 of a number, so just use it.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 7049d0bc72ac..383ecf036e31 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -123,9 +123,9 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 
 	if (ring->flag == HCLGE_TYPE_CSQ) {
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG,
-				(u32)dma);
+				lower_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG,
-				(u32)((dma >> 31) >> 1));
+				upper_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG,
 				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
 				HCLGE_NIC_CMQ_ENABLE);
@@ -133,9 +133,9 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0);
 	} else {
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG,
-				(u32)dma);
+				lower_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_H_REG,
-				(u32)((dma >> 31) >> 1));
+				upper_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG,
 				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
 				HCLGE_NIC_CMQ_ENABLE);
-- 
cgit v1.2.3


From f7a2ba5ab9c5e7cf9036ec68d3528ccdf9e81b0a Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Wed, 27 Jun 2018 14:38:59 -0700
Subject: ila: Fix use of rhashtable walk in ila_xlat.c

Perform better EAGAIN handling, handle case where ila_dump_info
fails and we missed objects in the dump, and add a skip index
to skip over ila entires in a list on a rhashtable node that have
already been visited (by a previous call to ila_nl_dump).

Signed-off-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ila/ila_xlat.c | 70 ++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 54 insertions(+), 16 deletions(-)

diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 10ae13560b40..40f3f640e856 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -475,24 +475,31 @@ out_free:
 
 struct ila_dump_iter {
 	struct rhashtable_iter rhiter;
+	int skip;
 };
 
 static int ila_nl_dump_start(struct netlink_callback *cb)
 {
 	struct net *net = sock_net(cb->skb->sk);
 	struct ila_net *ilan = net_generic(net, ila_net_id);
-	struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
+	struct ila_dump_iter *iter;
+	int ret;
 
-	if (!iter) {
-		iter = kmalloc(sizeof(*iter), GFP_KERNEL);
-		if (!iter)
-			return -ENOMEM;
+	iter = kmalloc(sizeof(*iter), GFP_KERNEL);
+	if (!iter)
+		return -ENOMEM;
 
-		cb->args[0] = (long)iter;
+	ret = rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter,
+				   GFP_KERNEL);
+	if (ret) {
+		kfree(iter);
+		return ret;
 	}
 
-	return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter,
-				    GFP_KERNEL);
+	iter->skip = 0;
+	cb->args[0] = (long)iter;
+
+	return ret;
 }
 
 static int ila_nl_dump_done(struct netlink_callback *cb)
@@ -510,20 +517,45 @@ static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
 	struct rhashtable_iter *rhiter = &iter->rhiter;
+	int skip = iter->skip;
 	struct ila_map *ila;
 	int ret;
 
 	rhashtable_walk_start(rhiter);
 
-	for (;;) {
-		ila = rhashtable_walk_next(rhiter);
+	/* Get first entry */
+	ila = rhashtable_walk_peek(rhiter);
+
+	if (ila && !IS_ERR(ila) && skip) {
+		/* Skip over visited entries */
+
+		while (ila && skip) {
+			/* Skip over any ila entries in this list that we
+			 * have already dumped.
+			 */
+			ila = rcu_access_pointer(ila->next);
+			skip--;
+		}
+	}
 
+	skip = 0;
+
+	for (;;) {
 		if (IS_ERR(ila)) {
-			if (PTR_ERR(ila) == -EAGAIN)
-				continue;
 			ret = PTR_ERR(ila);
-			goto done;
+			if (ret == -EAGAIN) {
+				/* Table has changed and iter has reset. Return
+				 * -EAGAIN to the application even if we have
+				 * written data to the skb. The application
+				 * needs to deal with this.
+				 */
+
+				goto out_ret;
+			} else {
+				break;
+			}
 		} else if (!ila) {
+			ret = 0;
 			break;
 		}
 
@@ -532,15 +564,21 @@ static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 					     cb->nlh->nlmsg_seq, NLM_F_MULTI,
 					     skb, ILA_CMD_GET);
 			if (ret)
-				goto done;
+				goto out;
 
+			skip++;
 			ila = rcu_access_pointer(ila->next);
 		}
+
+		skip = 0;
+		ila = rhashtable_walk_next(rhiter);
 	}
 
-	ret = skb->len;
+out:
+	iter->skip = skip;
+	ret = (skb->len ? : ret);
 
-done:
+out_ret:
 	rhashtable_walk_stop(rhiter);
 	return ret;
 }
-- 
cgit v1.2.3


From b893281715ab4ea0e63034165b4fa11d1bb984c5 Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Wed, 27 Jun 2018 14:39:00 -0700
Subject: ila: Call library function alloc_bucket_locks

To allocate the array of bucket locks for the hash table we now
call library function alloc_bucket_spinlocks.

Signed-off-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ila/ila_xlat.c | 23 +++++------------------
 1 file changed, 5 insertions(+), 18 deletions(-)

diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 40f3f640e856..9cc8beedc2ca 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -31,27 +31,14 @@ struct ila_net {
 	bool hooks_registered;
 };
 
+#define MAX_LOCKS 1024
 #define	LOCKS_PER_CPU 10
 
 static int alloc_ila_locks(struct ila_net *ilan)
 {
-	unsigned int i, size;
-	unsigned int nr_pcpus = num_possible_cpus();
-
-	nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL);
-	size = roundup_pow_of_two(nr_pcpus * LOCKS_PER_CPU);
-
-	if (sizeof(spinlock_t) != 0) {
-		ilan->locks = kvmalloc_array(size, sizeof(spinlock_t),
-					     GFP_KERNEL);
-		if (!ilan->locks)
-			return -ENOMEM;
-		for (i = 0; i < size; i++)
-			spin_lock_init(&ilan->locks[i]);
-	}
-	ilan->locks_mask = size - 1;
-
-	return 0;
+	return alloc_bucket_spinlocks(&ilan->locks, &ilan->locks_mask,
+				      MAX_LOCKS, LOCKS_PER_CPU,
+				      GFP_KERNEL);
 }
 
 static u32 hashrnd __read_mostly;
@@ -640,7 +627,7 @@ static __net_exit void ila_exit_net(struct net *net)
 
 	rhashtable_free_and_destroy(&ilan->rhash_table, ila_free_cb, NULL);
 
-	kvfree(ilan->locks);
+	free_bucket_spinlocks(ilan->locks);
 
 	if (ilan->hooks_registered)
 		nf_unregister_net_hooks(net, ila_nf_hook_ops,
-- 
cgit v1.2.3


From ad68147ef2878cad0cb9aba2a682c4bb8832cca7 Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Wed, 27 Jun 2018 14:39:01 -0700
Subject: ila: Create main ila source file

Create a main ila file that contains the module initialization functions
as well as netlink definitions. Previously these were defined in
ila_xlat and ila_common. This approach allows better extensibility.

Signed-off-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ila/Makefile     |   2 +-
 net/ipv6/ila/ila.h        |  26 ++++++++-
 net/ipv6/ila/ila_common.c |  30 ----------
 net/ipv6/ila/ila_main.c   | 115 +++++++++++++++++++++++++++++++++++++
 net/ipv6/ila/ila_xlat.c   | 142 +++++++++-------------------------------------
 5 files changed, 168 insertions(+), 147 deletions(-)
 create mode 100644 net/ipv6/ila/ila_main.c

diff --git a/net/ipv6/ila/Makefile b/net/ipv6/ila/Makefile
index 4b32e5921e5c..b7739aba6e68 100644
--- a/net/ipv6/ila/Makefile
+++ b/net/ipv6/ila/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_IPV6_ILA) += ila.o
 
-ila-objs := ila_common.o ila_lwt.o ila_xlat.o
+ila-objs := ila_main.o ila_common.o ila_lwt.o ila_xlat.o
diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h
index 3c7a11b62334..faba7824ea56 100644
--- a/net/ipv6/ila/ila.h
+++ b/net/ipv6/ila/ila.h
@@ -19,6 +19,7 @@
 #include <linux/skbuff.h>
 #include <linux/types.h>
 #include <net/checksum.h>
+#include <net/genetlink.h>
 #include <net/ip.h>
 #include <net/protocol.h>
 #include <uapi/linux/ila.h>
@@ -104,9 +105,30 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
 
 void ila_init_saved_csum(struct ila_params *p);
 
+struct ila_net {
+	struct {
+		struct rhashtable rhash_table;
+		spinlock_t *locks; /* Bucket locks for entry manipulation */
+		unsigned int locks_mask;
+		bool hooks_registered;
+	} xlat;
+};
+
 int ila_lwt_init(void);
 void ila_lwt_fini(void);
-int ila_xlat_init(void);
-void ila_xlat_fini(void);
+
+int ila_xlat_init_net(struct net *net);
+void ila_xlat_exit_net(struct net *net);
+
+int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_dump_start(struct netlink_callback *cb);
+int ila_xlat_nl_dump_done(struct netlink_callback *cb);
+int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb);
+
+extern unsigned int ila_net_id;
+
+extern struct genl_family ila_nl_family;
 
 #endif /* __ILA_H */
diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 8c88ecf29b93..579310466eac 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -154,33 +154,3 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
 	iaddr->loc = p->locator;
 }
 
-static int __init ila_init(void)
-{
-	int ret;
-
-	ret = ila_lwt_init();
-
-	if (ret)
-		goto fail_lwt;
-
-	ret = ila_xlat_init();
-	if (ret)
-		goto fail_xlat;
-
-	return 0;
-fail_xlat:
-	ila_lwt_fini();
-fail_lwt:
-	return ret;
-}
-
-static void __exit ila_fini(void)
-{
-	ila_xlat_fini();
-	ila_lwt_fini();
-}
-
-module_init(ila_init);
-module_exit(ila_fini);
-MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>");
-MODULE_LICENSE("GPL");
diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c
new file mode 100644
index 000000000000..f6ac6b14577e
--- /dev/null
+++ b/net/ipv6/ila/ila_main.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <net/genetlink.h>
+#include <net/ila.h>
+#include <net/netns/generic.h>
+#include <uapi/linux/genetlink.h>
+#include "ila.h"
+
+static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
+	[ILA_ATTR_LOCATOR] = { .type = NLA_U64, },
+	[ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, },
+	[ILA_ATTR_IFINDEX] = { .type = NLA_U32, },
+	[ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, },
+	[ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, },
+};
+
+static const struct genl_ops ila_nl_ops[] = {
+	{
+		.cmd = ILA_CMD_ADD,
+		.doit = ila_xlat_nl_cmd_add_mapping,
+		.policy = ila_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = ILA_CMD_DEL,
+		.doit = ila_xlat_nl_cmd_del_mapping,
+		.policy = ila_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
+	{
+		.cmd = ILA_CMD_GET,
+		.doit = ila_xlat_nl_cmd_get_mapping,
+		.start = ila_xlat_nl_dump_start,
+		.dumpit = ila_xlat_nl_dump,
+		.done = ila_xlat_nl_dump_done,
+		.policy = ila_nl_policy,
+	},
+};
+
+unsigned int ila_net_id;
+
+struct genl_family ila_nl_family __ro_after_init = {
+	.hdrsize	= 0,
+	.name		= ILA_GENL_NAME,
+	.version	= ILA_GENL_VERSION,
+	.maxattr	= ILA_ATTR_MAX,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.ops		= ila_nl_ops,
+	.n_ops		= ARRAY_SIZE(ila_nl_ops),
+};
+
+static __net_init int ila_init_net(struct net *net)
+{
+	int err;
+
+	err = ila_xlat_init_net(net);
+	if (err)
+		goto ila_xlat_init_fail;
+
+	return 0;
+
+ila_xlat_init_fail:
+	return err;
+}
+
+static __net_exit void ila_exit_net(struct net *net)
+{
+	ila_xlat_exit_net(net);
+}
+
+static struct pernet_operations ila_net_ops = {
+	.init = ila_init_net,
+	.exit = ila_exit_net,
+	.id   = &ila_net_id,
+	.size = sizeof(struct ila_net),
+};
+
+static int __init ila_init(void)
+{
+	int ret;
+
+	ret = register_pernet_device(&ila_net_ops);
+	if (ret)
+		goto register_device_fail;
+
+	ret = genl_register_family(&ila_nl_family);
+	if (ret)
+		goto register_family_fail;
+
+	ret = ila_lwt_init();
+	if (ret)
+		goto fail_lwt;
+
+	return 0;
+
+fail_lwt:
+	genl_unregister_family(&ila_nl_family);
+register_family_fail:
+	unregister_pernet_device(&ila_net_ops);
+register_device_fail:
+	return ret;
+}
+
+static void __exit ila_fini(void)
+{
+	ila_lwt_fini();
+	genl_unregister_family(&ila_nl_family);
+	unregister_pernet_device(&ila_net_ops);
+}
+
+module_init(ila_init);
+module_exit(ila_fini);
+MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>");
+MODULE_LICENSE("GPL");
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 9cc8beedc2ca..d05de891dfb6 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -22,21 +22,12 @@ struct ila_map {
 	struct rcu_head rcu;
 };
 
-static unsigned int ila_net_id;
-
-struct ila_net {
-	struct rhashtable rhash_table;
-	spinlock_t *locks; /* Bucket locks for entry manipulation */
-	unsigned int locks_mask;
-	bool hooks_registered;
-};
-
 #define MAX_LOCKS 1024
 #define	LOCKS_PER_CPU 10
 
 static int alloc_ila_locks(struct ila_net *ilan)
 {
-	return alloc_bucket_spinlocks(&ilan->locks, &ilan->locks_mask,
+	return alloc_bucket_spinlocks(&ilan->xlat.locks, &ilan->xlat.locks_mask,
 				      MAX_LOCKS, LOCKS_PER_CPU,
 				      GFP_KERNEL);
 }
@@ -58,7 +49,7 @@ static inline u32 ila_locator_hash(struct ila_locator loc)
 static inline spinlock_t *ila_get_lock(struct ila_net *ilan,
 				       struct ila_locator loc)
 {
-	return &ilan->locks[ila_locator_hash(loc) & ilan->locks_mask];
+	return &ilan->xlat.locks[ila_locator_hash(loc) & ilan->xlat.locks_mask];
 }
 
 static inline int ila_cmp_wildcards(struct ila_map *ila,
@@ -102,16 +93,6 @@ static const struct rhashtable_params rht_params = {
 	.obj_cmpfn = ila_cmpfn,
 };
 
-static struct genl_family ila_nl_family;
-
-static const struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = {
-	[ILA_ATTR_LOCATOR] = { .type = NLA_U64, },
-	[ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, },
-	[ILA_ATTR_IFINDEX] = { .type = NLA_U32, },
-	[ILA_ATTR_CSUM_MODE] = { .type = NLA_U8, },
-	[ILA_ATTR_IDENT_TYPE] = { .type = NLA_U8, },
-};
-
 static int parse_nl_config(struct genl_info *info,
 			   struct ila_xlat_params *xp)
 {
@@ -149,7 +130,7 @@ static inline struct ila_map *ila_lookup_wildcards(struct ila_addr *iaddr,
 {
 	struct ila_map *ila;
 
-	ila = rhashtable_lookup_fast(&ilan->rhash_table, &iaddr->loc,
+	ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table, &iaddr->loc,
 				     rht_params);
 	while (ila) {
 		if (!ila_cmp_wildcards(ila, iaddr, ifindex))
@@ -166,7 +147,7 @@ static inline struct ila_map *ila_lookup_by_params(struct ila_xlat_params *xp,
 {
 	struct ila_map *ila;
 
-	ila = rhashtable_lookup_fast(&ilan->rhash_table,
+	ila = rhashtable_lookup_fast(&ilan->xlat.rhash_table,
 				     &xp->ip.locator_match,
 				     rht_params);
 	while (ila) {
@@ -222,7 +203,7 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp)
 	spinlock_t *lock = ila_get_lock(ilan, xp->ip.locator_match);
 	int err = 0, order;
 
-	if (!ilan->hooks_registered) {
+	if (!ilan->xlat.hooks_registered) {
 		/* We defer registering net hooks in the namespace until the
 		 * first mapping is added.
 		 */
@@ -231,7 +212,7 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp)
 		if (err)
 			return err;
 
-		ilan->hooks_registered = true;
+		ilan->xlat.hooks_registered = true;
 	}
 
 	ila = kzalloc(sizeof(*ila), GFP_KERNEL);
@@ -246,12 +227,12 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp)
 
 	spin_lock(lock);
 
-	head = rhashtable_lookup_fast(&ilan->rhash_table,
+	head = rhashtable_lookup_fast(&ilan->xlat.rhash_table,
 				      &xp->ip.locator_match,
 				      rht_params);
 	if (!head) {
 		/* New entry for the rhash_table */
-		err = rhashtable_lookup_insert_fast(&ilan->rhash_table,
+		err = rhashtable_lookup_insert_fast(&ilan->xlat.rhash_table,
 						    &ila->node, rht_params);
 	} else {
 		struct ila_map *tila = head, *prev = NULL;
@@ -277,7 +258,7 @@ static int ila_add_mapping(struct net *net, struct ila_xlat_params *xp)
 		} else {
 			/* Make this ila new head */
 			RCU_INIT_POINTER(ila->next, head);
-			err = rhashtable_replace_fast(&ilan->rhash_table,
+			err = rhashtable_replace_fast(&ilan->xlat.rhash_table,
 						      &head->node,
 						      &ila->node, rht_params);
 			if (err)
@@ -303,7 +284,7 @@ static int ila_del_mapping(struct net *net, struct ila_xlat_params *xp)
 
 	spin_lock(lock);
 
-	head = rhashtable_lookup_fast(&ilan->rhash_table,
+	head = rhashtable_lookup_fast(&ilan->xlat.rhash_table,
 				      &xp->ip.locator_match, rht_params);
 	ila = head;
 
@@ -333,15 +314,15 @@ static int ila_del_mapping(struct net *net, struct ila_xlat_params *xp)
 				 * table
 				 */
 				err = rhashtable_replace_fast(
-					&ilan->rhash_table, &ila->node,
+					&ilan->xlat.rhash_table, &ila->node,
 					&head->node, rht_params);
 				if (err)
 					goto out;
 			} else {
 				/* Entry no longer used */
-				err = rhashtable_remove_fast(&ilan->rhash_table,
-							     &ila->node,
-							     rht_params);
+				err = rhashtable_remove_fast(
+						&ilan->xlat.rhash_table,
+						&ila->node, rht_params);
 			}
 		}
 
@@ -356,7 +337,7 @@ out:
 	return err;
 }
 
-static int ila_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info)
+int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
 	struct ila_xlat_params p;
@@ -369,7 +350,7 @@ static int ila_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info)
 	return ila_add_mapping(net, &p);
 }
 
-static int ila_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info)
+int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
 	struct ila_xlat_params xp;
@@ -421,7 +402,7 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
-static int ila_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info)
+int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
 	struct ila_net *ilan = net_generic(net, ila_net_id);
@@ -465,7 +446,7 @@ struct ila_dump_iter {
 	int skip;
 };
 
-static int ila_nl_dump_start(struct netlink_callback *cb)
+int ila_xlat_nl_dump_start(struct netlink_callback *cb)
 {
 	struct net *net = sock_net(cb->skb->sk);
 	struct ila_net *ilan = net_generic(net, ila_net_id);
@@ -476,7 +457,7 @@ static int ila_nl_dump_start(struct netlink_callback *cb)
 	if (!iter)
 		return -ENOMEM;
 
-	ret = rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter,
+	ret = rhashtable_walk_init(&ilan->xlat.rhash_table, &iter->rhiter,
 				   GFP_KERNEL);
 	if (ret) {
 		kfree(iter);
@@ -489,7 +470,7 @@ static int ila_nl_dump_start(struct netlink_callback *cb)
 	return ret;
 }
 
-static int ila_nl_dump_done(struct netlink_callback *cb)
+int ila_xlat_nl_dump_done(struct netlink_callback *cb)
 {
 	struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
 
@@ -500,7 +481,7 @@ static int ila_nl_dump_done(struct netlink_callback *cb)
 	return 0;
 }
 
-static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
+int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args[0];
 	struct rhashtable_iter *rhiter = &iter->rhiter;
@@ -570,77 +551,35 @@ out_ret:
 	return ret;
 }
 
-static const struct genl_ops ila_nl_ops[] = {
-	{
-		.cmd = ILA_CMD_ADD,
-		.doit = ila_nl_cmd_add_mapping,
-		.policy = ila_nl_policy,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = ILA_CMD_DEL,
-		.doit = ila_nl_cmd_del_mapping,
-		.policy = ila_nl_policy,
-		.flags = GENL_ADMIN_PERM,
-	},
-	{
-		.cmd = ILA_CMD_GET,
-		.doit = ila_nl_cmd_get_mapping,
-		.start = ila_nl_dump_start,
-		.dumpit = ila_nl_dump,
-		.done = ila_nl_dump_done,
-		.policy = ila_nl_policy,
-	},
-};
-
-static struct genl_family ila_nl_family __ro_after_init = {
-	.hdrsize	= 0,
-	.name		= ILA_GENL_NAME,
-	.version	= ILA_GENL_VERSION,
-	.maxattr	= ILA_ATTR_MAX,
-	.netnsok	= true,
-	.parallel_ops	= true,
-	.module		= THIS_MODULE,
-	.ops		= ila_nl_ops,
-	.n_ops		= ARRAY_SIZE(ila_nl_ops),
-};
-
 #define ILA_HASH_TABLE_SIZE 1024
 
-static __net_init int ila_init_net(struct net *net)
+int ila_xlat_init_net(struct net *net)
 {
-	int err;
 	struct ila_net *ilan = net_generic(net, ila_net_id);
+	int err;
 
 	err = alloc_ila_locks(ilan);
 	if (err)
 		return err;
 
-	rhashtable_init(&ilan->rhash_table, &rht_params);
+	rhashtable_init(&ilan->xlat.rhash_table, &rht_params);
 
 	return 0;
 }
 
-static __net_exit void ila_exit_net(struct net *net)
+void ila_xlat_exit_net(struct net *net)
 {
 	struct ila_net *ilan = net_generic(net, ila_net_id);
 
-	rhashtable_free_and_destroy(&ilan->rhash_table, ila_free_cb, NULL);
+	rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL);
 
-	free_bucket_spinlocks(ilan->locks);
+	free_bucket_spinlocks(ilan->xlat.locks);
 
-	if (ilan->hooks_registered)
+	if (ilan->xlat.hooks_registered)
 		nf_unregister_net_hooks(net, ila_nf_hook_ops,
 					ARRAY_SIZE(ila_nf_hook_ops));
 }
 
-static struct pernet_operations ila_net_ops = {
-	.init = ila_init_net,
-	.exit = ila_exit_net,
-	.id   = &ila_net_id,
-	.size = sizeof(struct ila_net),
-};
-
 static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila)
 {
 	struct ila_map *ila;
@@ -667,28 +606,3 @@ static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila)
 	return 0;
 }
 
-int __init ila_xlat_init(void)
-{
-	int ret;
-
-	ret = register_pernet_device(&ila_net_ops);
-	if (ret)
-		goto exit;
-
-	ret = genl_register_family(&ila_nl_family);
-	if (ret < 0)
-		goto unregister;
-
-	return 0;
-
-unregister:
-	unregister_pernet_device(&ila_net_ops);
-exit:
-	return ret;
-}
-
-void ila_xlat_fini(void)
-{
-	genl_unregister_family(&ila_nl_family);
-	unregister_pernet_device(&ila_net_ops);
-}
-- 
cgit v1.2.3


From b6e71bdebb12cb79f931db358066a33f5f526b6a Mon Sep 17 00:00:00 2001
From: Tom Herbert <tom@herbertland.com>
Date: Wed, 27 Jun 2018 14:39:02 -0700
Subject: ila: Flush netlink command to clear xlat table

Add ILA_CMD_FLUSH netlink command to clear the ILA translation table.

Signed-off-by: Tom Herbert <tom@quantonium.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ila.h |  1 +
 net/ipv6/ila/ila.h       |  1 +
 net/ipv6/ila/ila_main.c  |  6 +++++
 net/ipv6/ila/ila_xlat.c  | 62 ++++++++++++++++++++++++++++++++++++++++++++++--
 4 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/ila.h b/include/uapi/linux/ila.h
index 483b77af4eb8..db45d3e49a12 100644
--- a/include/uapi/linux/ila.h
+++ b/include/uapi/linux/ila.h
@@ -30,6 +30,7 @@ enum {
 	ILA_CMD_ADD,
 	ILA_CMD_DEL,
 	ILA_CMD_GET,
+	ILA_CMD_FLUSH,
 
 	__ILA_CMD_MAX,
 };
diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h
index faba7824ea56..1f747bcbec29 100644
--- a/net/ipv6/ila/ila.h
+++ b/net/ipv6/ila/ila.h
@@ -123,6 +123,7 @@ void ila_xlat_exit_net(struct net *net);
 int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info);
 int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info);
 int ila_xlat_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info);
+int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info);
 int ila_xlat_nl_dump_start(struct netlink_callback *cb);
 int ila_xlat_nl_dump_done(struct netlink_callback *cb);
 int ila_xlat_nl_dump(struct sk_buff *skb, struct netlink_callback *cb);
diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c
index f6ac6b14577e..18fac76b9520 100644
--- a/net/ipv6/ila/ila_main.c
+++ b/net/ipv6/ila/ila_main.c
@@ -26,6 +26,12 @@ static const struct genl_ops ila_nl_ops[] = {
 		.policy = ila_nl_policy,
 		.flags = GENL_ADMIN_PERM,
 	},
+	{
+		.cmd = ILA_CMD_FLUSH,
+		.doit = ila_xlat_nl_cmd_flush,
+		.policy = ila_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+	},
 	{
 		.cmd = ILA_CMD_GET,
 		.doit = ila_xlat_nl_cmd_get_mapping,
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index d05de891dfb6..51a15ce50a64 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -164,9 +164,9 @@ static inline void ila_release(struct ila_map *ila)
 	kfree_rcu(ila, rcu);
 }
 
-static void ila_free_cb(void *ptr, void *arg)
+static void ila_free_node(struct ila_map *ila)
 {
-	struct ila_map *ila = (struct ila_map *)ptr, *next;
+	struct ila_map *next;
 
 	/* Assume rcu_readlock held */
 	while (ila) {
@@ -176,6 +176,11 @@ static void ila_free_cb(void *ptr, void *arg)
 	}
 }
 
+static void ila_free_cb(void *ptr, void *arg)
+{
+	ila_free_node((struct ila_map *)ptr);
+}
+
 static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila);
 
 static unsigned int
@@ -365,6 +370,59 @@ int ila_xlat_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+static inline spinlock_t *lock_from_ila_map(struct ila_net *ilan,
+					    struct ila_map *ila)
+{
+	return ila_get_lock(ilan, ila->xp.ip.locator_match);
+}
+
+int ila_xlat_nl_cmd_flush(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct ila_net *ilan = net_generic(net, ila_net_id);
+	struct rhashtable_iter iter;
+	struct ila_map *ila;
+	spinlock_t *lock;
+	int ret;
+
+	ret = rhashtable_walk_init(&ilan->xlat.rhash_table, &iter, GFP_KERNEL);
+	if (ret)
+		goto done;
+
+	rhashtable_walk_start(&iter);
+
+	for (;;) {
+		ila = rhashtable_walk_next(&iter);
+
+		if (IS_ERR(ila)) {
+			if (PTR_ERR(ila) == -EAGAIN)
+				continue;
+			ret = PTR_ERR(ila);
+			goto done;
+		} else if (!ila) {
+			break;
+		}
+
+		lock = lock_from_ila_map(ilan, ila);
+
+		spin_lock(lock);
+
+		ret = rhashtable_remove_fast(&ilan->xlat.rhash_table,
+					     &ila->node, rht_params);
+		if (!ret)
+			ila_free_node(ila);
+
+		spin_unlock(lock);
+
+		if (ret)
+			break;
+	}
+
+done:
+	rhashtable_walk_stop(&iter);
+	return ret;
+}
+
 static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg)
 {
 	if (nla_put_u64_64bit(msg, ILA_ATTR_LOCATOR,
-- 
cgit v1.2.3


From fe0984d38938249f3f11fc558a8845fc6f8a0105 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:11:14 +0200
Subject: cfg80211: track time using boottime

The cfg80211 layer uses get_seconds() to read the current time
in its supend handling. This function is deprecated because of the 32-bit
time_t overflow, and it can cause unexpected behavior when the time
changes due to settimeofday() calls or leap second updates.

In many cases, we want to use monotonic time instead, however cfg80211
explicitly tracks the time spent in suspend, so this changes the
driver over to use ktime_get_boottime_seconds(), which is slightly
slower, but not used in a fastpath here.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.h  | 2 +-
 net/wireless/sysfs.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/wireless/core.h b/net/wireless/core.h
index 63eb1b5fdd04..7f52ef569320 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -76,7 +76,7 @@ struct cfg80211_registered_device {
 	struct cfg80211_scan_request *scan_req; /* protected by RTNL */
 	struct sk_buff *scan_msg;
 	struct list_head sched_scan_req_list;
-	unsigned long suspend_at;
+	time64_t suspend_at;
 	struct work_struct scan_done_wk;
 
 	struct genl_info *cur_cmd_info;
diff --git a/net/wireless/sysfs.c b/net/wireless/sysfs.c
index 570a2b67ca10..6ab32f6a1961 100644
--- a/net/wireless/sysfs.c
+++ b/net/wireless/sysfs.c
@@ -102,7 +102,7 @@ static int wiphy_suspend(struct device *dev)
 	struct cfg80211_registered_device *rdev = dev_to_rdev(dev);
 	int ret = 0;
 
-	rdev->suspend_at = get_seconds();
+	rdev->suspend_at = ktime_get_boottime_seconds();
 
 	rtnl_lock();
 	if (rdev->wiphy.registered) {
@@ -130,7 +130,7 @@ static int wiphy_resume(struct device *dev)
 	int ret = 0;
 
 	/* Age scan results with time spent in suspend */
-	cfg80211_bss_age(rdev, get_seconds() - rdev->suspend_at);
+	cfg80211_bss_age(rdev, ktime_get_boottime_seconds() - rdev->suspend_at);
 
 	rtnl_lock();
 	if (rdev->wiphy.registered && rdev->ops->resume)
-- 
cgit v1.2.3


From 47aa7861b9bf8e8a540f3b11971e4a3f631e8ff4 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 18 Jun 2018 07:41:34 -0500
Subject: mac80211: fix potential null pointer dereference

he_op is being dereferenced before it is null checked, hence there
is a potential null pointer dereference.

Fix this by moving the pointer dereference after he_op has been
properly null checked.

Notice that, currently, he_op is already being null checked before
calling this function at 4593:

4593	if (!he_oper ||
4594	    !ieee80211_verify_sta_he_mcs_support(sband, he_oper))
4595		ifmgd->flags |= IEEE80211_STA_DISABLE_HE;

but in case ieee80211_verify_sta_he_mcs_support is ever called
without verifying he_oper is not null, we will end up having a
null pointer dereference. So, we better don't take any chances.

Addresses-Coverity-ID: 1470068 ("Dereference before null check")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 0322d78007ad..f4513031f1bc 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4458,12 +4458,14 @@ ieee80211_verify_sta_he_mcs_support(struct ieee80211_supported_band *sband,
 {
 	const struct ieee80211_sta_he_cap *sta_he_cap =
 		ieee80211_get_he_sta_cap(sband);
-	u16 ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set);
+	u16 ap_min_req_set;
 	int i;
 
 	if (!sta_he_cap || !he_op)
 		return false;
 
+	ap_min_req_set = le16_to_cpu(he_op->he_mcs_nss_set);
+
 	/* Need to go over for 80MHz, 160MHz and for 80+80 */
 	for (i = 0; i < 3; i++) {
 		const struct ieee80211_he_mcs_nss_supp *sta_mcs_nss_supp =
-- 
cgit v1.2.3


From f0c0407d2a9fc3b2be33ec6c67ebc1f73595d2cb Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 29 Jun 2018 09:51:39 +0200
Subject: mac80211: remove unnecessary NULL check

We don't need to check if he_oper is NULL before calling
ieee80211_verify_sta_he_mcs_support() as it - now - will
correctly check this itself. Remove the redundant check.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f4513031f1bc..7fb9957359a3 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4592,8 +4592,7 @@ static int ieee80211_prep_channel(struct ieee80211_sub_if_data *sdata,
 		else
 			he_oper = NULL;
 
-		if (!he_oper ||
-		    !ieee80211_verify_sta_he_mcs_support(sband, he_oper))
+		if (!ieee80211_verify_sta_he_mcs_support(sband, he_oper))
 			ifmgd->flags |= IEEE80211_STA_DISABLE_HE;
 	}
 
-- 
cgit v1.2.3


From 397c657a0644e7607c6aebea84d2b0f08ab59dfc Mon Sep 17 00:00:00 2001
From: Omer Efrat <omer.efrat@tandemg.com>
Date: Sun, 17 Jun 2018 13:06:14 +0300
Subject: cfg80211: use BIT_ULL for NL80211_STA_INFO_* attribute types

The BIT macro uses unsigned long which some architectures handle as 32 bit
and therefore might cause macro's shift to overflow when used on a value
equals or larger than 32 (NL80211_STA_INFO_RX_DURATION and afterwards).

Since 'filled' member in station_info changed to u64, BIT_ULL macro
should be used with all NL80211_STA_INFO_* attribute types instead of BIT
to prevent future possible bugs when one will use BIT macro for higher
attributes by mistake.

This commit cleans up all usages of BIT macro with the above field
in cfg80211 by changing it to BIT_ULL instead. In addition, there are
some places which don't use BIT nor BIT_ULL macros so align those as well.

Signed-off-by: Omer Efrat <omer.efrat@tandemg.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c     | 26 +++++++++++++-------------
 net/wireless/wext-compat.c | 10 +++++-----
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 0ccce338a66e..350d2962524c 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4619,13 +4619,13 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 
 #define PUT_SINFO(attr, memb, type) do {				\
 	BUILD_BUG_ON(sizeof(type) == sizeof(u64));			\
-	if (sinfo->filled & (1ULL << NL80211_STA_INFO_ ## attr) &&	\
+	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_ ## attr) &&	\
 	    nla_put_ ## type(msg, NL80211_STA_INFO_ ## attr,		\
 			     sinfo->memb))				\
 		goto nla_put_failure;					\
 	} while (0)
 #define PUT_SINFO_U64(attr, memb) do {					\
-	if (sinfo->filled & (1ULL << NL80211_STA_INFO_ ## attr) &&	\
+	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_ ## attr) &&	\
 	    nla_put_u64_64bit(msg, NL80211_STA_INFO_ ## attr,		\
 			      sinfo->memb, NL80211_STA_INFO_PAD))	\
 		goto nla_put_failure;					\
@@ -4634,14 +4634,14 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO(CONNECTED_TIME, connected_time, u32);
 	PUT_SINFO(INACTIVE_TIME, inactive_time, u32);
 
-	if (sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES) |
-			     BIT(NL80211_STA_INFO_RX_BYTES64)) &&
+	if (sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES) |
+			     BIT_ULL(NL80211_STA_INFO_RX_BYTES64)) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_RX_BYTES,
 			(u32)sinfo->rx_bytes))
 		goto nla_put_failure;
 
-	if (sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES) |
-			     BIT(NL80211_STA_INFO_TX_BYTES64)) &&
+	if (sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES) |
+			     BIT_ULL(NL80211_STA_INFO_TX_BYTES64)) &&
 	    nla_put_u32(msg, NL80211_STA_INFO_TX_BYTES,
 			(u32)sinfo->tx_bytes))
 		goto nla_put_failure;
@@ -4661,24 +4661,24 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	default:
 		break;
 	}
-	if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL)) {
+	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL)) {
 		if (!nl80211_put_signal(msg, sinfo->chains,
 					sinfo->chain_signal,
 					NL80211_STA_INFO_CHAIN_SIGNAL))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) {
+	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)) {
 		if (!nl80211_put_signal(msg, sinfo->chains,
 					sinfo->chain_signal_avg,
 					NL80211_STA_INFO_CHAIN_SIGNAL_AVG))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE)) {
+	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)) {
 		if (!nl80211_put_sta_rate(msg, &sinfo->txrate,
 					  NL80211_STA_INFO_TX_BITRATE))
 			goto nla_put_failure;
 	}
-	if (sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE)) {
+	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE)) {
 		if (!nl80211_put_sta_rate(msg, &sinfo->rxrate,
 					  NL80211_STA_INFO_RX_BITRATE))
 			goto nla_put_failure;
@@ -4694,7 +4694,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO(PEER_PM, peer_pm, u32);
 	PUT_SINFO(NONPEER_PM, nonpeer_pm, u32);
 
-	if (sinfo->filled & BIT(NL80211_STA_INFO_BSS_PARAM)) {
+	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) {
 		bss_param = nla_nest_start(msg, NL80211_STA_INFO_BSS_PARAM);
 		if (!bss_param)
 			goto nla_put_failure;
@@ -4713,7 +4713,7 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 
 		nla_nest_end(msg, bss_param);
 	}
-	if ((sinfo->filled & BIT(NL80211_STA_INFO_STA_FLAGS)) &&
+	if ((sinfo->filled & BIT_ULL(NL80211_STA_INFO_STA_FLAGS)) &&
 	    nla_put(msg, NL80211_STA_INFO_STA_FLAGS,
 		    sizeof(struct nl80211_sta_flag_update),
 		    &sinfo->sta_flags))
@@ -10266,7 +10266,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev,
 		if (err)
 			return err;
 
-		if (sinfo.filled & BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG))
+		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG))
 			wdev->cqm_config->last_rssi_event_value =
 				(s8) sinfo.rx_beacon_signal_avg;
 	}
diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c
index 05186a47878f..167f7025ac98 100644
--- a/net/wireless/wext-compat.c
+++ b/net/wireless/wext-compat.c
@@ -1278,7 +1278,7 @@ static int cfg80211_wext_giwrate(struct net_device *dev,
 	if (err)
 		return err;
 
-	if (!(sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)))
+	if (!(sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE)))
 		return -EOPNOTSUPP;
 
 	rate->value = 100000 * cfg80211_calculate_bitrate(&sinfo.txrate);
@@ -1320,7 +1320,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 
 	switch (rdev->wiphy.signal_type) {
 	case CFG80211_SIGNAL_TYPE_MBM:
-		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
+		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) {
 			int sig = sinfo.signal;
 			wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
 			wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
@@ -1334,7 +1334,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 			break;
 		}
 	case CFG80211_SIGNAL_TYPE_UNSPEC:
-		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL)) {
+		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) {
 			wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED;
 			wstats.qual.updated |= IW_QUAL_QUAL_UPDATED;
 			wstats.qual.level = sinfo.signal;
@@ -1347,9 +1347,9 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev)
 	}
 
 	wstats.qual.updated |= IW_QUAL_NOISE_INVALID;
-	if (sinfo.filled & BIT(NL80211_STA_INFO_RX_DROP_MISC))
+	if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC))
 		wstats.discard.misc = sinfo.rx_dropped_misc;
-	if (sinfo.filled & BIT(NL80211_STA_INFO_TX_FAILED))
+	if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED))
 		wstats.discard.retries = sinfo.tx_failed;
 
 	return &wstats;
-- 
cgit v1.2.3


From a4217750586975dee7d6dd8829a1be24a7678b3d Mon Sep 17 00:00:00 2001
From: Omer Efrat <omer.efrat@tandemg.com>
Date: Sun, 17 Jun 2018 13:06:25 +0300
Subject: mac80211: use BIT_ULL for NL80211_STA_INFO_* attribute types

The BIT macro uses unsigned long which some architectures handle as 32 bit
and therefore might cause macro's shift to overflow when used on a value
equals or larger than 32 (NL80211_STA_INFO_RX_DURATION and afterwards).

Since 'filled' member in station_info changed to u64, BIT_ULL macro
should be used with all NL80211_STA_INFO_* attribute types instead of BIT
to prevent future possible bugs when one will use BIT macro for higher
attributes by mistake.

This commit cleans up all usages of BIT macro with the above field
in mac80211 by changing it to BIT_ULL instead.

Signed-off-by: Omer Efrat <omer.efrat@tandemg.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ethtool.c  |  6 ++--
 net/mac80211/sta_info.c | 84 ++++++++++++++++++++++++-------------------------
 2 files changed, 45 insertions(+), 45 deletions(-)

diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c
index 690c142a7a44..5ac743816b59 100644
--- a/net/mac80211/ethtool.c
+++ b/net/mac80211/ethtool.c
@@ -116,16 +116,16 @@ static void ieee80211_get_stats(struct net_device *dev,
 		data[i++] = sta->sta_state;
 
 
-		if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE))
+		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))
 			data[i] = 100000ULL *
 				cfg80211_calculate_bitrate(&sinfo.txrate);
 		i++;
-		if (sinfo.filled & BIT(NL80211_STA_INFO_RX_BITRATE))
+		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE))
 			data[i] = 100000ULL *
 				cfg80211_calculate_bitrate(&sinfo.rxrate);
 		i++;
 
-		if (sinfo.filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))
+		if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG))
 			data[i] = (u8)sinfo.signal_avg;
 		i++;
 	} else {
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index aa8fe771a8db..f34202242d24 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2114,38 +2114,38 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 
 	drv_sta_statistics(local, sdata, &sta->sta, sinfo);
 
-	sinfo->filled |= BIT(NL80211_STA_INFO_INACTIVE_TIME) |
-			 BIT(NL80211_STA_INFO_STA_FLAGS) |
-			 BIT(NL80211_STA_INFO_BSS_PARAM) |
-			 BIT(NL80211_STA_INFO_CONNECTED_TIME) |
-			 BIT(NL80211_STA_INFO_RX_DROP_MISC);
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_INACTIVE_TIME) |
+			 BIT_ULL(NL80211_STA_INFO_STA_FLAGS) |
+			 BIT_ULL(NL80211_STA_INFO_BSS_PARAM) |
+			 BIT_ULL(NL80211_STA_INFO_CONNECTED_TIME) |
+			 BIT_ULL(NL80211_STA_INFO_RX_DROP_MISC);
 
 	if (sdata->vif.type == NL80211_IFTYPE_STATION) {
 		sinfo->beacon_loss_count = sdata->u.mgd.beacon_loss_count;
-		sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_LOSS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_LOSS);
 	}
 
 	sinfo->connected_time = ktime_get_seconds() - sta->last_connected;
 	sinfo->inactive_time =
 		jiffies_to_msecs(jiffies - ieee80211_sta_last_active(sta));
 
-	if (!(sinfo->filled & (BIT(NL80211_STA_INFO_TX_BYTES64) |
-			       BIT(NL80211_STA_INFO_TX_BYTES)))) {
+	if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_TX_BYTES64) |
+			       BIT_ULL(NL80211_STA_INFO_TX_BYTES)))) {
 		sinfo->tx_bytes = 0;
 		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
 			sinfo->tx_bytes += sta->tx_stats.bytes[ac];
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
 	}
 
-	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_PACKETS))) {
+	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_PACKETS))) {
 		sinfo->tx_packets = 0;
 		for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
 			sinfo->tx_packets += sta->tx_stats.packets[ac];
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 	}
 
-	if (!(sinfo->filled & (BIT(NL80211_STA_INFO_RX_BYTES64) |
-			       BIT(NL80211_STA_INFO_RX_BYTES)))) {
+	if (!(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_RX_BYTES64) |
+			       BIT_ULL(NL80211_STA_INFO_RX_BYTES)))) {
 		sinfo->rx_bytes += sta_get_stats_bytes(&sta->rx_stats);
 
 		if (sta->pcpu_rx_stats) {
@@ -2157,10 +2157,10 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 			}
 		}
 
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_BYTES64);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
 	}
 
-	if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_PACKETS))) {
+	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_PACKETS))) {
 		sinfo->rx_packets = sta->rx_stats.packets;
 		if (sta->pcpu_rx_stats) {
 			for_each_possible_cpu(cpu) {
@@ -2170,17 +2170,17 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 				sinfo->rx_packets += cpurxs->packets;
 			}
 		}
-		sinfo->filled |= BIT(NL80211_STA_INFO_RX_PACKETS);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 	}
 
-	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_RETRIES))) {
+	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_RETRIES))) {
 		sinfo->tx_retries = sta->status_stats.retry_count;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_RETRIES);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
 	}
 
-	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_FAILED))) {
+	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_FAILED))) {
 		sinfo->tx_failed = sta->status_stats.retry_failed;
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_FAILED);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 	}
 
 	sinfo->rx_dropped_misc = sta->rx_stats.dropped;
@@ -2195,23 +2195,23 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 
 	if (sdata->vif.type == NL80211_IFTYPE_STATION &&
 	    !(sdata->vif.driver_flags & IEEE80211_VIF_BEACON_FILTER)) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_BEACON_RX) |
-				 BIT(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_BEACON_RX) |
+				 BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG);
 		sinfo->rx_beacon_signal_avg = ieee80211_ave_rssi(&sdata->vif);
 	}
 
 	if (ieee80211_hw_check(&sta->local->hw, SIGNAL_DBM) ||
 	    ieee80211_hw_check(&sta->local->hw, SIGNAL_UNSPEC)) {
-		if (!(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL))) {
+		if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL))) {
 			sinfo->signal = (s8)last_rxstats->last_signal;
-			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 		}
 
 		if (!sta->pcpu_rx_stats &&
-		    !(sinfo->filled & BIT(NL80211_STA_INFO_SIGNAL_AVG))) {
+		    !(sinfo->filled & BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG))) {
 			sinfo->signal_avg =
 				-ewma_signal_read(&sta->rx_stats_avg.signal);
-			sinfo->filled |= BIT(NL80211_STA_INFO_SIGNAL_AVG);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 		}
 	}
 
@@ -2220,11 +2220,11 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 	 * pcpu statistics
 	 */
 	if (last_rxstats->chains &&
-	    !(sinfo->filled & (BIT(NL80211_STA_INFO_CHAIN_SIGNAL) |
-			       BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL);
+	    !(sinfo->filled & (BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL) |
+			       BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG)))) {
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL);
 		if (!sta->pcpu_rx_stats)
-			sinfo->filled |= BIT(NL80211_STA_INFO_CHAIN_SIGNAL_AVG);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_CHAIN_SIGNAL_AVG);
 
 		sinfo->chains = last_rxstats->chains;
 
@@ -2236,15 +2236,15 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 		}
 	}
 
-	if (!(sinfo->filled & BIT(NL80211_STA_INFO_TX_BITRATE))) {
+	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_BITRATE))) {
 		sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate,
 				     &sinfo->txrate);
-		sinfo->filled |= BIT(NL80211_STA_INFO_TX_BITRATE);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 	}
 
-	if (!(sinfo->filled & BIT(NL80211_STA_INFO_RX_BITRATE))) {
+	if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_BITRATE))) {
 		if (sta_set_rate_info_rx(sta, &sinfo->rxrate) == 0)
-			sinfo->filled |= BIT(NL80211_STA_INFO_RX_BITRATE);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BITRATE);
 	}
 
 	if (tidstats && !cfg80211_sinfo_alloc_tid_stats(sinfo, GFP_KERNEL)) {
@@ -2257,18 +2257,18 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 
 	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
-		sinfo->filled |= BIT(NL80211_STA_INFO_LLID) |
-				 BIT(NL80211_STA_INFO_PLID) |
-				 BIT(NL80211_STA_INFO_PLINK_STATE) |
-				 BIT(NL80211_STA_INFO_LOCAL_PM) |
-				 BIT(NL80211_STA_INFO_PEER_PM) |
-				 BIT(NL80211_STA_INFO_NONPEER_PM);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_LLID) |
+				 BIT_ULL(NL80211_STA_INFO_PLID) |
+				 BIT_ULL(NL80211_STA_INFO_PLINK_STATE) |
+				 BIT_ULL(NL80211_STA_INFO_LOCAL_PM) |
+				 BIT_ULL(NL80211_STA_INFO_PEER_PM) |
+				 BIT_ULL(NL80211_STA_INFO_NONPEER_PM);
 
 		sinfo->llid = sta->mesh->llid;
 		sinfo->plid = sta->mesh->plid;
 		sinfo->plink_state = sta->mesh->plink_state;
 		if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) {
-			sinfo->filled |= BIT(NL80211_STA_INFO_T_OFFSET);
+			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_T_OFFSET);
 			sinfo->t_offset = sta->mesh->t_offset;
 		}
 		sinfo->local_pm = sta->mesh->local_pm;
@@ -2313,7 +2313,7 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 	thr = sta_get_expected_throughput(sta);
 
 	if (thr != 0) {
-		sinfo->filled |= BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT);
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_EXPECTED_THROUGHPUT);
 		sinfo->expected_throughput = thr;
 	}
 
-- 
cgit v1.2.3


From c9855a561afa5b21db7f2218f0b7baaa555fa90c Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Mon, 25 Jun 2018 18:37:57 +0200
Subject: drm/i915: Block enabling FBC until flips have been completed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is a small race window in which FBC can be enabled after
pre_plane_update is called, but before the page flip has been
queued or completed.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103167
Link: https://patchwork.freedesktop.org/patch/msgid/20180625163758.10871-1-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h  |  1 +
 drivers/gpu/drm/i915/intel_fbc.c | 35 +++++++++++------------------------
 2 files changed, 12 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 2b684f431c60..615ed807ea32 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -512,6 +512,7 @@ struct intel_fbc {
 
 	bool enabled;
 	bool active;
+	bool flip_pending;
 
 	bool underrun_detected;
 	struct work_struct underrun_work;
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index b431b6733cc1..9f9ea0b5452f 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -924,13 +924,6 @@ static void intel_fbc_get_reg_params(struct intel_crtc *crtc,
 						32 * fbc->threshold) * 8;
 }
 
-static bool intel_fbc_reg_params_equal(struct intel_fbc_reg_params *params1,
-				       struct intel_fbc_reg_params *params2)
-{
-	/* We can use this since intel_fbc_get_reg_params() does a memset. */
-	return memcmp(params1, params2, sizeof(*params1)) == 0;
-}
-
 void intel_fbc_pre_update(struct intel_crtc *crtc,
 			  struct intel_crtc_state *crtc_state,
 			  struct intel_plane_state *plane_state)
@@ -953,6 +946,7 @@ void intel_fbc_pre_update(struct intel_crtc *crtc,
 		goto unlock;
 
 	intel_fbc_update_state_cache(crtc, crtc_state, plane_state);
+	fbc->flip_pending = true;
 
 deactivate:
 	intel_fbc_deactivate(dev_priv, reason);
@@ -988,13 +982,15 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_reg_params old_params;
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
 	if (!fbc->enabled || fbc->crtc != crtc)
 		return;
 
+	fbc->flip_pending = false;
+	WARN_ON(fbc->active);
+
 	if (!i915_modparams.enable_fbc) {
 		intel_fbc_deactivate(dev_priv, "disabled at runtime per module param");
 		__intel_fbc_disable(dev_priv);
@@ -1002,25 +998,16 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 		return;
 	}
 
-	if (!intel_fbc_can_activate(crtc)) {
-		WARN_ON(fbc->active);
-		return;
-	}
-
-	old_params = fbc->params;
 	intel_fbc_get_reg_params(crtc, &fbc->params);
 
-	/* If the scanout has not changed, don't modify the FBC settings.
-	 * Note that we make the fundamental assumption that the fb->obj
-	 * cannot be unpinned (and have its GTT offset and fence revoked)
-	 * without first being decoupled from the scanout and FBC disabled.
-	 */
-	if (fbc->active &&
-	    intel_fbc_reg_params_equal(&old_params, &fbc->params))
+	if (!intel_fbc_can_activate(crtc))
 		return;
 
-	intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
-	intel_fbc_schedule_activation(crtc);
+	if (!fbc->busy_bits) {
+		intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
+		intel_fbc_schedule_activation(crtc);
+	} else
+		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 }
 
 void intel_fbc_post_update(struct intel_crtc *crtc)
@@ -1085,7 +1072,7 @@ void intel_fbc_flush(struct drm_i915_private *dev_priv,
 	    (frontbuffer_bits & intel_fbc_get_frontbuffer_bit(fbc))) {
 		if (fbc->active)
 			intel_fbc_recompress(dev_priv);
-		else
+		else if (!fbc->flip_pending)
 			__intel_fbc_post_update(fbc->crtc);
 	}
 
-- 
cgit v1.2.3


From 457209595789a3acd57990e2e9dade95bbea8fba Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Mon, 25 Jun 2018 18:37:58 +0200
Subject: drm/i915: Remove delayed FBC activation.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only time we should start FBC is when we have waited a vblank
after the atomic update. We've already forced a vblank wait by doing
wait_for_flip_done before intel_post_plane_update(), so we don't need
to wait a second time before enabling.

Removing the worker simplifies the code and removes possible race
conditions, like happening in 103167.

Cc: Paulo Zanoni <paulo.r.zanoni@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103167
Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180625163758.10871-2-maarten.lankhorst@linux.intel.com
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c |  5 --
 drivers/gpu/drm/i915/i915_drv.h     |  6 ---
 drivers/gpu/drm/i915/intel_fbc.c    | 96 +------------------------------------
 3 files changed, 1 insertion(+), 106 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index c400f42a54ec..48a57c0636bf 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1659,11 +1659,6 @@ static int i915_fbc_status(struct seq_file *m, void *unused)
 	else
 		seq_printf(m, "FBC disabled: %s\n", fbc->no_fbc_reason);
 
-	if (fbc->work.scheduled)
-		seq_printf(m, "FBC worker scheduled on vblank %llu, now %llu\n",
-			   fbc->work.scheduled_vblank,
-			   drm_crtc_vblank_count(&fbc->crtc->base));
-
 	if (intel_fbc_is_active(dev_priv)) {
 		u32 mask;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 615ed807ea32..ce7d06332884 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -580,12 +580,6 @@ struct intel_fbc {
 		unsigned int gen9_wa_cfb_stride;
 	} params;
 
-	struct intel_fbc_work {
-		bool scheduled;
-		u64 scheduled_vblank;
-		struct work_struct work;
-	} work;
-
 	const char *no_fbc_reason;
 };
 
diff --git a/drivers/gpu/drm/i915/intel_fbc.c b/drivers/gpu/drm/i915/intel_fbc.c
index 9f9ea0b5452f..01d1d2088f04 100644
--- a/drivers/gpu/drm/i915/intel_fbc.c
+++ b/drivers/gpu/drm/i915/intel_fbc.c
@@ -399,89 +399,6 @@ bool intel_fbc_is_active(struct drm_i915_private *dev_priv)
 	return dev_priv->fbc.active;
 }
 
-static void intel_fbc_work_fn(struct work_struct *__work)
-{
-	struct drm_i915_private *dev_priv =
-		container_of(__work, struct drm_i915_private, fbc.work.work);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_work *work = &fbc->work;
-	struct intel_crtc *crtc = fbc->crtc;
-	struct drm_vblank_crtc *vblank = &dev_priv->drm.vblank[crtc->pipe];
-
-	if (drm_crtc_vblank_get(&crtc->base)) {
-		/* CRTC is now off, leave FBC deactivated */
-		mutex_lock(&fbc->lock);
-		work->scheduled = false;
-		mutex_unlock(&fbc->lock);
-		return;
-	}
-
-retry:
-	/* Delay the actual enabling to let pageflipping cease and the
-	 * display to settle before starting the compression. Note that
-	 * this delay also serves a second purpose: it allows for a
-	 * vblank to pass after disabling the FBC before we attempt
-	 * to modify the control registers.
-	 *
-	 * WaFbcWaitForVBlankBeforeEnable:ilk,snb
-	 *
-	 * It is also worth mentioning that since work->scheduled_vblank can be
-	 * updated multiple times by the other threads, hitting the timeout is
-	 * not an error condition. We'll just end up hitting the "goto retry"
-	 * case below.
-	 */
-	wait_event_timeout(vblank->queue,
-		drm_crtc_vblank_count(&crtc->base) != work->scheduled_vblank,
-		msecs_to_jiffies(50));
-
-	mutex_lock(&fbc->lock);
-
-	/* Were we cancelled? */
-	if (!work->scheduled)
-		goto out;
-
-	/* Were we delayed again while this function was sleeping? */
-	if (drm_crtc_vblank_count(&crtc->base) == work->scheduled_vblank) {
-		mutex_unlock(&fbc->lock);
-		goto retry;
-	}
-
-	intel_fbc_hw_activate(dev_priv);
-
-	work->scheduled = false;
-
-out:
-	mutex_unlock(&fbc->lock);
-	drm_crtc_vblank_put(&crtc->base);
-}
-
-static void intel_fbc_schedule_activation(struct intel_crtc *crtc)
-{
-	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
-	struct intel_fbc *fbc = &dev_priv->fbc;
-	struct intel_fbc_work *work = &fbc->work;
-
-	WARN_ON(!mutex_is_locked(&fbc->lock));
-	if (WARN_ON(!fbc->enabled))
-		return;
-
-	if (drm_crtc_vblank_get(&crtc->base)) {
-		DRM_ERROR("vblank not available for FBC on pipe %c\n",
-			  pipe_name(crtc->pipe));
-		return;
-	}
-
-	/* It is useless to call intel_fbc_cancel_work() or cancel_work() in
-	 * this function since we're not releasing fbc.lock, so it won't have an
-	 * opportunity to grab it to discover that it was cancelled. So we just
-	 * update the expected jiffy count. */
-	work->scheduled = true;
-	work->scheduled_vblank = drm_crtc_vblank_count(&crtc->base);
-	drm_crtc_vblank_put(&crtc->base);
-
-	schedule_work(&work->work);
-}
-
 static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 				 const char *reason)
 {
@@ -489,11 +406,6 @@ static void intel_fbc_deactivate(struct drm_i915_private *dev_priv,
 
 	WARN_ON(!mutex_is_locked(&fbc->lock));
 
-	/* Calling cancel_work() here won't help due to the fact that the work
-	 * function grabs fbc->lock. Just set scheduled to false so the work
-	 * function can know it was cancelled. */
-	fbc->work.scheduled = false;
-
 	if (fbc->active)
 		intel_fbc_hw_deactivate(dev_priv);
 
@@ -1005,7 +917,7 @@ static void __intel_fbc_post_update(struct intel_crtc *crtc)
 
 	if (!fbc->busy_bits) {
 		intel_fbc_deactivate(dev_priv, "FBC enabled (active or scheduled)");
-		intel_fbc_schedule_activation(crtc);
+		intel_fbc_hw_activate(dev_priv);
 	} else
 		intel_fbc_deactivate(dev_priv, "frontbuffer write");
 }
@@ -1212,8 +1124,6 @@ void intel_fbc_disable(struct intel_crtc *crtc)
 	if (fbc->crtc == crtc)
 		__intel_fbc_disable(dev_priv);
 	mutex_unlock(&fbc->lock);
-
-	cancel_work_sync(&fbc->work.work);
 }
 
 /**
@@ -1235,8 +1145,6 @@ void intel_fbc_global_disable(struct drm_i915_private *dev_priv)
 		__intel_fbc_disable(dev_priv);
 	}
 	mutex_unlock(&fbc->lock);
-
-	cancel_work_sync(&fbc->work.work);
 }
 
 static void intel_fbc_underrun_work_fn(struct work_struct *work)
@@ -1387,12 +1295,10 @@ void intel_fbc_init(struct drm_i915_private *dev_priv)
 {
 	struct intel_fbc *fbc = &dev_priv->fbc;
 
-	INIT_WORK(&fbc->work.work, intel_fbc_work_fn);
 	INIT_WORK(&fbc->underrun_work, intel_fbc_underrun_work_fn);
 	mutex_init(&fbc->lock);
 	fbc->enabled = false;
 	fbc->active = false;
-	fbc->work.scheduled = false;
 
 	if (need_fbc_vtd_wa(dev_priv))
 		mkwrite_device_info(dev_priv)->has_fbc = false;
-- 
cgit v1.2.3


From 334bb8972a131e604a741e9b284d8867190c723e Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 29 Jun 2018 11:46:19 +0200
Subject: console: dummycon: export dummycon_[un]register_output_notifier

Export dummycon_[un]register_output_notifier, the fbcon code needs this
and may be build as a module.

Fixes: 83d83bebf401 ("console/fbcon: Add support for deferred console takeover")
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
---
 drivers/video/console/dummycon.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/video/console/dummycon.c b/drivers/video/console/dummycon.c
index 45ad925ad5f8..0254251fdd79 100644
--- a/drivers/video/console/dummycon.c
+++ b/drivers/video/console/dummycon.c
@@ -38,11 +38,13 @@ void dummycon_register_output_notifier(struct notifier_block *nb)
 	if (dummycon_putc_called)
 		nb->notifier_call(nb, 0, NULL);
 }
+EXPORT_SYMBOL_GPL(dummycon_register_output_notifier);
 
 void dummycon_unregister_output_notifier(struct notifier_block *nb)
 {
 	raw_notifier_chain_unregister(&dummycon_output_nh, nb);
 }
+EXPORT_SYMBOL_GPL(dummycon_unregister_output_notifier);
 
 static void dummycon_putc(struct vc_data *vc, int c, int ypos, int xpos)
 {
-- 
cgit v1.2.3


From 8f54061d001ad2da24dba89fc48adbbf4c85222b Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Thu, 28 Jun 2018 22:08:37 +0200
Subject: ASoC: pxa: remove the dmaengine compat need

As the pxa architecture switched towards the dmaengine slave map, the
old compatibility mechanism to acquire the dma requestor line number and
priority are not needed anymore.

This patch simplifies the dma resource acquisition, using the more
generic function dma_request_slave_channel().

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/arm/pxa2xx-ac97.c     | 14 ++------------
 sound/arm/pxa2xx-pcm-lib.c  |  6 +++---
 sound/soc/pxa/pxa2xx-ac97.c | 32 +++++---------------------------
 sound/soc/pxa/pxa2xx-i2s.c  |  6 ++----
 4 files changed, 12 insertions(+), 46 deletions(-)

diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 4bc244c40f80..236a63cdaf9f 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -63,28 +63,18 @@ static struct snd_ac97_bus_ops pxa2xx_ac97_ops = {
 	.reset	= pxa2xx_ac97_legacy_reset,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_out_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 12,
-};
-
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_out = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "pcm_pcm_stereo_out",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_out_req,
-};
-
-static struct pxad_param pxa2xx_ac97_pcm_in_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 11,
 };
 
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_in = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "pcm_pcm_stereo_in",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_in_req,
 };
 
 static struct snd_pcm *pxa2xx_ac97_pcm;
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index e8da3b8ee721..dcbe7ecc1835 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -125,9 +125,9 @@ int __pxa2xx_pcm_open(struct snd_pcm_substream *substream)
 	if (ret < 0)
 		return ret;
 
-	return snd_dmaengine_pcm_open_request_chan(substream,
-					pxad_filter_fn,
-					dma_params->filter_data);
+	return snd_dmaengine_pcm_open(
+		substream, dma_request_slave_channel(rtd->cpu_dai->dev,
+						     dma_params->chan_name));
 }
 EXPORT_SYMBOL(__pxa2xx_pcm_open);
 
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index 5738a0abcd6a..c52b33802bf2 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -68,61 +68,39 @@ static struct snd_ac97_bus_ops pxa2xx_ac97_ops = {
 	.reset	= pxa2xx_ac97_cold_reset,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_stereo_in_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 11,
-};
-
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_in = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "pcm_pcm_stereo_in",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_stereo_in_req,
-};
-
-static struct pxad_param pxa2xx_ac97_pcm_stereo_out_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 12,
 };
 
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_stereo_out = {
 	.addr		= __PREG(PCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "pcm_pcm_stereo_out",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_ac97_pcm_stereo_out_req,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_aux_mono_out_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 10,
-};
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_aux_mono_out = {
 	.addr		= __PREG(MODR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_2_BYTES,
+	.chan_name	= "pcm_aux_mono_out",
 	.maxburst	= 16,
-	.filter_data	= &pxa2xx_ac97_pcm_aux_mono_out_req,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_aux_mono_in_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 9,
-};
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_aux_mono_in = {
 	.addr		= __PREG(MODR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_2_BYTES,
+	.chan_name	= "pcm_aux_mono_in",
 	.maxburst	= 16,
-	.filter_data	= &pxa2xx_ac97_pcm_aux_mono_in_req,
 };
 
-static struct pxad_param pxa2xx_ac97_pcm_aux_mic_mono_req = {
-	.prio = PXAD_PRIO_LOWEST,
-	.drcmr = 8,
-};
 static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_mic_mono_in = {
 	.addr		= __PREG(MCDR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_2_BYTES,
+	.chan_name	= "pcm_aux_mic_mono",
 	.maxburst	= 16,
-	.filter_data	= &pxa2xx_ac97_pcm_aux_mic_mono_req,
 };
 
 static int pxa2xx_ac97_hifi_startup(struct snd_pcm_substream *substream,
diff --git a/sound/soc/pxa/pxa2xx-i2s.c b/sound/soc/pxa/pxa2xx-i2s.c
index 3fb60baf6eab..e7184de0de04 100644
--- a/sound/soc/pxa/pxa2xx-i2s.c
+++ b/sound/soc/pxa/pxa2xx-i2s.c
@@ -82,20 +82,18 @@ static struct pxa_i2s_port pxa_i2s;
 static struct clk *clk_i2s;
 static int clk_ena = 0;
 
-static unsigned long pxa2xx_i2s_pcm_stereo_out_req = 3;
 static struct snd_dmaengine_dai_dma_data pxa2xx_i2s_pcm_stereo_out = {
 	.addr		= __PREG(SADR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "tx",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_i2s_pcm_stereo_out_req,
 };
 
-static unsigned long pxa2xx_i2s_pcm_stereo_in_req = 2;
 static struct snd_dmaengine_dai_dma_data pxa2xx_i2s_pcm_stereo_in = {
 	.addr		= __PREG(SADR),
 	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
+	.chan_name	= "rx",
 	.maxburst	= 32,
-	.filter_data	= &pxa2xx_i2s_pcm_stereo_in_req,
 };
 
 static int pxa2xx_i2s_startup(struct snd_pcm_substream *substream,
-- 
cgit v1.2.3


From 95acb005fef2aeaeb63c20de98aca0ed5bd0efa2 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 21:33:53 +0200
Subject: ASoC: fold pxa2xx-pcm into its only user, pxa2xx-ac97

Now that the PXA SSP bits are ported over to generic DMA, the pxa2xx-pcm
code only has a single user left. This patch folds the remaining bits into
its only user and removes the unnecessary glue layer along with its header
file.

The include dependency to linux/dma/pxa-dma.h is also gone now.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/arm/Kconfig          |   5 --
 sound/arm/Makefile         |   3 --
 sound/arm/pxa2xx-ac97.c    | 114 ++++++++++++++++++++++++++-------------
 sound/arm/pxa2xx-pcm-lib.c |   2 -
 sound/arm/pxa2xx-pcm.c     | 129 ---------------------------------------------
 sound/arm/pxa2xx-pcm.h     |  27 ----------
 sound/soc/pxa/pxa-ssp.c    |   1 -
 sound/soc/pxa/pxa2xx-pcm.c |   2 -
 8 files changed, 76 insertions(+), 207 deletions(-)
 delete mode 100644 sound/arm/pxa2xx-pcm.c
 delete mode 100644 sound/arm/pxa2xx-pcm.h

diff --git a/sound/arm/Kconfig b/sound/arm/Kconfig
index 65171f6657a2..5fbd47a9177e 100644
--- a/sound/arm/Kconfig
+++ b/sound/arm/Kconfig
@@ -17,14 +17,9 @@ config SND_ARMAACI
 	select SND_PCM
 	select SND_AC97_CODEC
 
-config SND_PXA2XX_PCM
-	tristate
-	select SND_PCM
-
 config SND_PXA2XX_AC97
 	tristate "AC97 driver for the Intel PXA2xx chip"
 	depends on ARCH_PXA
-	select SND_PXA2XX_PCM
 	select SND_AC97_CODEC
 	select SND_PXA2XX_LIB
 	select SND_PXA2XX_LIB_AC97
diff --git a/sound/arm/Makefile b/sound/arm/Makefile
index e10d5b169565..34c769489877 100644
--- a/sound/arm/Makefile
+++ b/sound/arm/Makefile
@@ -6,9 +6,6 @@
 obj-$(CONFIG_SND_ARMAACI)	+= snd-aaci.o
 snd-aaci-objs			:= aaci.o
 
-obj-$(CONFIG_SND_PXA2XX_PCM)	+= snd-pxa2xx-pcm.o
-snd-pxa2xx-pcm-objs		:= pxa2xx-pcm.o
-
 obj-$(CONFIG_SND_PXA2XX_LIB)	+= snd-pxa2xx-lib.o
 snd-pxa2xx-lib-y		:= pxa2xx-pcm-lib.o
 snd-pxa2xx-lib-$(CONFIG_SND_PXA2XX_LIB_AC97)	+= pxa2xx-ac97-lib.o
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 236a63cdaf9f..7d8d7b7199dc 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/dmaengine.h>
-#include <linux/dma/pxa-dma.h>
+#include <linux/dma-mapping.h>
 
 #include <sound/core.h>
 #include <sound/pcm.h>
@@ -27,8 +27,6 @@
 #include <mach/regs-ac97.h>
 #include <mach/audio.h>
 
-#include "pxa2xx-pcm.h"
-
 static void pxa2xx_ac97_legacy_reset(struct snd_ac97 *ac97)
 {
 	if (!pxa2xx_ac97_try_cold_reset())
@@ -63,51 +61,46 @@ static struct snd_ac97_bus_ops pxa2xx_ac97_ops = {
 	.reset	= pxa2xx_ac97_legacy_reset,
 };
 
-static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_out = {
-	.addr		= __PREG(PCDR),
-	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
-	.chan_name	= "pcm_pcm_stereo_out",
-	.maxburst	= 32,
-};
-
-static struct snd_dmaengine_dai_dma_data pxa2xx_ac97_pcm_in = {
-	.addr		= __PREG(PCDR),
-	.addr_width	= DMA_SLAVE_BUSWIDTH_4_BYTES,
-	.chan_name	= "pcm_pcm_stereo_in",
-	.maxburst	= 32,
-};
-
 static struct snd_pcm *pxa2xx_ac97_pcm;
 static struct snd_ac97 *pxa2xx_ac97_ac97;
 
-static int pxa2xx_ac97_pcm_startup(struct snd_pcm_substream *substream)
+static int pxa2xx_ac97_pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	pxa2xx_audio_ops_t *platform_ops;
-	int r;
+	int ret, i;
+
+	ret = __pxa2xx_pcm_open(substream);
+	if (ret)
+		return ret;
 
 	runtime->hw.channels_min = 2;
 	runtime->hw.channels_max = 2;
 
-	r = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
-	    AC97_RATES_FRONT_DAC : AC97_RATES_ADC;
-	runtime->hw.rates = pxa2xx_ac97_ac97->rates[r];
+	i = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
+		AC97_RATES_FRONT_DAC : AC97_RATES_ADC;
+	runtime->hw.rates = pxa2xx_ac97_ac97->rates[i];
 	snd_pcm_limit_hw_rates(runtime);
 
-       	platform_ops = substream->pcm->card->dev->platform_data;
-	if (platform_ops && platform_ops->startup)
-		return platform_ops->startup(substream, platform_ops->priv);
-	else
-		return 0;
+	platform_ops = substream->pcm->card->dev->platform_data;
+	if (platform_ops && platform_ops->startup) {
+		ret = platform_ops->startup(substream, platform_ops->priv);
+		if (ret < 0)
+			__pxa2xx_pcm_close(substream);
+	}
+
+	return ret;
 }
 
-static void pxa2xx_ac97_pcm_shutdown(struct snd_pcm_substream *substream)
+static int pxa2xx_ac97_pcm_close(struct snd_pcm_substream *substream)
 {
 	pxa2xx_audio_ops_t *platform_ops;
 
-       	platform_ops = substream->pcm->card->dev->platform_data;
+	platform_ops = substream->pcm->card->dev->platform_data;
 	if (platform_ops && platform_ops->shutdown)
 		platform_ops->shutdown(substream, platform_ops->priv);
+
+	return 0;
 }
 
 static int pxa2xx_ac97_pcm_prepare(struct snd_pcm_substream *substream)
@@ -115,17 +108,15 @@ static int pxa2xx_ac97_pcm_prepare(struct snd_pcm_substream *substream)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	int reg = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
 		  AC97_PCM_FRONT_DAC_RATE : AC97_PCM_LR_ADC_RATE;
+	int ret;
+
+	ret = __pxa2xx_pcm_prepare(substream);
+	if (ret < 0)
+		return ret;
+
 	return snd_ac97_set_rate(pxa2xx_ac97_ac97, reg, runtime->rate);
 }
 
-static struct pxa2xx_pcm_client pxa2xx_ac97_pcm_client = {
-	.playback_params	= &pxa2xx_ac97_pcm_out,
-	.capture_params		= &pxa2xx_ac97_pcm_in,
-	.startup		= pxa2xx_ac97_pcm_startup,
-	.shutdown		= pxa2xx_ac97_pcm_shutdown,
-	.prepare		= pxa2xx_ac97_pcm_prepare,
-};
-
 #ifdef CONFIG_PM_SLEEP
 
 static int pxa2xx_ac97_do_suspend(struct snd_card *card)
@@ -183,6 +174,53 @@ static int pxa2xx_ac97_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(pxa2xx_ac97_pm_ops, pxa2xx_ac97_suspend, pxa2xx_ac97_resume);
 #endif
 
+static const struct snd_pcm_ops pxa2xx_pcm_ops = {
+	.open		= pxa2xx_ac97_pcm_open,
+	.close		= pxa2xx_ac97_pcm_close,
+	.ioctl		= snd_pcm_lib_ioctl,
+	.hw_params	= __pxa2xx_pcm_hw_params,
+	.hw_free	= __pxa2xx_pcm_hw_free,
+	.prepare	= pxa2xx_ac97_pcm_prepare,
+	.trigger	= pxa2xx_pcm_trigger,
+	.pointer	= pxa2xx_pcm_pointer,
+	.mmap		= pxa2xx_pcm_mmap,
+};
+
+
+static int pxa2xx_ac97_pcm_new(struct snd_card *card)
+{
+	struct snd_pcm *pcm;
+	int stream, ret;
+
+	ret = snd_pcm_new(card, "PXA2xx-PCM", 0, 1, 1, &pcm);
+	if (ret)
+		goto out;
+
+	pcm->private_free = pxa2xx_pcm_free_dma_buffers;
+
+	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
+	if (ret)
+		goto out;
+
+	stream = SNDRV_PCM_STREAM_PLAYBACK;
+	snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
+	ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
+	if (ret)
+		goto out;
+
+	stream = SNDRV_PCM_STREAM_CAPTURE;
+	snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
+	ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
+	if (ret)
+		goto out;
+
+	pxa2xx_ac97_pcm = pcm;
+	ret = 0;
+
+ out:
+	return ret;
+}
+
 static int pxa2xx_ac97_probe(struct platform_device *dev)
 {
 	struct snd_card *card;
@@ -204,7 +242,7 @@ static int pxa2xx_ac97_probe(struct platform_device *dev)
 
 	strlcpy(card->driver, dev->dev.driver->name, sizeof(card->driver));
 
-	ret = pxa2xx_pcm_new(card, &pxa2xx_ac97_pcm_client, &pxa2xx_ac97_pcm);
+	ret = pxa2xx_ac97_pcm_new(card);
 	if (ret)
 		goto err;
 
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index dcbe7ecc1835..b927fa5ddbc0 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -16,8 +16,6 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include "pxa2xx-pcm.h"
-
 static const struct snd_pcm_hardware pxa2xx_pcm_hardware = {
 	.info			= SNDRV_PCM_INFO_MMAP |
 				  SNDRV_PCM_INFO_MMAP_VALID |
diff --git a/sound/arm/pxa2xx-pcm.c b/sound/arm/pxa2xx-pcm.c
deleted file mode 100644
index 1c6f4b436de3..000000000000
--- a/sound/arm/pxa2xx-pcm.c
+++ /dev/null
@@ -1,129 +0,0 @@
-/*
- * linux/sound/arm/pxa2xx-pcm.c -- ALSA PCM interface for the Intel PXA2xx chip
- *
- * Author:	Nicolas Pitre
- * Created:	Nov 30, 2004
- * Copyright:	(C) 2004 MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/module.h>
-#include <linux/dma-mapping.h>
-#include <linux/dmaengine.h>
-
-#include <mach/dma.h>
-
-#include <sound/core.h>
-#include <sound/pxa2xx-lib.h>
-#include <sound/dmaengine_pcm.h>
-
-#include "pxa2xx-pcm.h"
-
-static int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream)
-{
-	struct pxa2xx_pcm_client *client = substream->private_data;
-
-	__pxa2xx_pcm_prepare(substream);
-
-	return client->prepare(substream);
-}
-
-static int pxa2xx_pcm_open(struct snd_pcm_substream *substream)
-{
-	struct pxa2xx_pcm_client *client = substream->private_data;
-	struct snd_pcm_runtime *runtime = substream->runtime;
-	struct pxa2xx_runtime_data *rtd;
-	int ret;
-
-	ret = __pxa2xx_pcm_open(substream);
-	if (ret)
-		goto out;
-
-	rtd = runtime->private_data;
-
-	rtd->params = (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) ?
-		      client->playback_params : client->capture_params;
-
-	ret = client->startup(substream);
-	if (!ret)
-		goto err2;
-
-	return 0;
-
- err2:
-	__pxa2xx_pcm_close(substream);
- out:
-	return ret;
-}
-
-static int pxa2xx_pcm_close(struct snd_pcm_substream *substream)
-{
-	struct pxa2xx_pcm_client *client = substream->private_data;
-
-	client->shutdown(substream);
-
-	return __pxa2xx_pcm_close(substream);
-}
-
-static const struct snd_pcm_ops pxa2xx_pcm_ops = {
-	.open		= pxa2xx_pcm_open,
-	.close		= pxa2xx_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= __pxa2xx_pcm_hw_params,
-	.hw_free	= __pxa2xx_pcm_hw_free,
-	.prepare	= pxa2xx_pcm_prepare,
-	.trigger	= pxa2xx_pcm_trigger,
-	.pointer	= pxa2xx_pcm_pointer,
-	.mmap		= pxa2xx_pcm_mmap,
-};
-
-int pxa2xx_pcm_new(struct snd_card *card, struct pxa2xx_pcm_client *client,
-		   struct snd_pcm **rpcm)
-{
-	struct snd_pcm *pcm;
-	int play = client->playback_params ? 1 : 0;
-	int capt = client->capture_params ? 1 : 0;
-	int ret;
-
-	ret = snd_pcm_new(card, "PXA2xx-PCM", 0, play, capt, &pcm);
-	if (ret)
-		goto out;
-
-	pcm->private_data = client;
-	pcm->private_free = pxa2xx_pcm_free_dma_buffers;
-
-	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
-	if (ret)
-		goto out;
-
-	if (play) {
-		int stream = SNDRV_PCM_STREAM_PLAYBACK;
-		snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
-		if (ret)
-			goto out;
-	}
-	if (capt) {
-		int stream = SNDRV_PCM_STREAM_CAPTURE;
-		snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
-		if (ret)
-			goto out;
-	}
-
-	if (rpcm)
-		*rpcm = pcm;
-	ret = 0;
-
- out:
-	return ret;
-}
-
-EXPORT_SYMBOL(pxa2xx_pcm_new);
-
-MODULE_AUTHOR("Nicolas Pitre");
-MODULE_DESCRIPTION("Intel PXA2xx PCM DMA module");
-MODULE_LICENSE("GPL");
diff --git a/sound/arm/pxa2xx-pcm.h b/sound/arm/pxa2xx-pcm.h
deleted file mode 100644
index 8fa2b7c9e6b8..000000000000
--- a/sound/arm/pxa2xx-pcm.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * linux/sound/arm/pxa2xx-pcm.h -- ALSA PCM interface for the Intel PXA2xx chip
- *
- * Author:	Nicolas Pitre
- * Created:	Nov 30, 2004
- * Copyright:	MontaVista Software, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-struct pxa2xx_runtime_data {
-	int dma_ch;
-	struct snd_dmaengine_dai_dma_data *params;
-};
-
-struct pxa2xx_pcm_client {
-	struct snd_dmaengine_dai_dma_data *playback_params;
-	struct snd_dmaengine_dai_dma_data *capture_params;
-	int (*startup)(struct snd_pcm_substream *);
-	void (*shutdown)(struct snd_pcm_substream *);
-	int (*prepare)(struct snd_pcm_substream *);
-};
-
-extern int pxa2xx_pcm_new(struct snd_card *, struct pxa2xx_pcm_client *, struct snd_pcm **);
-
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 0b441338bdd4..c1f4af869289 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -34,7 +34,6 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include "../../arm/pxa2xx-pcm.h"
 #include "pxa-ssp.h"
 
 /*
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index 8b6a70e94c01..445e691126e5 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -20,8 +20,6 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-#include "../../arm/pxa2xx-pcm.h"
-
 static int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
 	struct snd_pcm_hw_params *params)
 {
-- 
cgit v1.2.3


From a7160670b5e2d6b59e0f7a5b7e5bcef3b532c24c Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 21:33:54 +0200
Subject: ASoC: pxa: clean up function names in pxa2xx-lib

Clean up the namespace a bit and drop the __ prefix of all functions
exported by pxa2xx-lib. This improves the readability of the code.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/pxa2xx-lib.h | 10 +++++-----
 sound/arm/pxa2xx-ac97.c    | 10 +++++-----
 sound/arm/pxa2xx-pcm-lib.c | 22 +++++++++++-----------
 sound/soc/pxa/pxa2xx-pcm.c | 21 +++++++--------------
 4 files changed, 28 insertions(+), 35 deletions(-)

diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h
index 63f75450d3db..b43de38de8b2 100644
--- a/include/sound/pxa2xx-lib.h
+++ b/include/sound/pxa2xx-lib.h
@@ -10,14 +10,14 @@ struct snd_pcm_substream;
 struct snd_pcm_hw_params;
 struct snd_pcm;
 
-extern int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
+extern int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
 				struct snd_pcm_hw_params *params);
-extern int __pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream);
 extern int pxa2xx_pcm_trigger(struct snd_pcm_substream *substream, int cmd);
 extern snd_pcm_uframes_t pxa2xx_pcm_pointer(struct snd_pcm_substream *substream);
-extern int __pxa2xx_pcm_prepare(struct snd_pcm_substream *substream);
-extern int __pxa2xx_pcm_open(struct snd_pcm_substream *substream);
-extern int __pxa2xx_pcm_close(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_open(struct snd_pcm_substream *substream);
+extern int pxa2xx_pcm_close(struct snd_pcm_substream *substream);
 extern int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma);
 extern int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream);
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 7d8d7b7199dc..0d624337857b 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -70,7 +70,7 @@ static int pxa2xx_ac97_pcm_open(struct snd_pcm_substream *substream)
 	pxa2xx_audio_ops_t *platform_ops;
 	int ret, i;
 
-	ret = __pxa2xx_pcm_open(substream);
+	ret = pxa2xx_pcm_open(substream);
 	if (ret)
 		return ret;
 
@@ -86,7 +86,7 @@ static int pxa2xx_ac97_pcm_open(struct snd_pcm_substream *substream)
 	if (platform_ops && platform_ops->startup) {
 		ret = platform_ops->startup(substream, platform_ops->priv);
 		if (ret < 0)
-			__pxa2xx_pcm_close(substream);
+			pxa2xx_pcm_close(substream);
 	}
 
 	return ret;
@@ -110,7 +110,7 @@ static int pxa2xx_ac97_pcm_prepare(struct snd_pcm_substream *substream)
 		  AC97_PCM_FRONT_DAC_RATE : AC97_PCM_LR_ADC_RATE;
 	int ret;
 
-	ret = __pxa2xx_pcm_prepare(substream);
+	ret = pxa2xx_pcm_prepare(substream);
 	if (ret < 0)
 		return ret;
 
@@ -178,8 +178,8 @@ static const struct snd_pcm_ops pxa2xx_pcm_ops = {
 	.open		= pxa2xx_ac97_pcm_open,
 	.close		= pxa2xx_ac97_pcm_close,
 	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= __pxa2xx_pcm_hw_params,
-	.hw_free	= __pxa2xx_pcm_hw_free,
+	.hw_params	= pxa2xx_pcm_hw_params,
+	.hw_free	= pxa2xx_pcm_hw_free,
 	.prepare	= pxa2xx_ac97_pcm_prepare,
 	.trigger	= pxa2xx_pcm_trigger,
 	.pointer	= pxa2xx_pcm_pointer,
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index b927fa5ddbc0..dc56dbebf441 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -33,8 +33,8 @@ static const struct snd_pcm_hardware pxa2xx_pcm_hardware = {
 	.fifo_size		= 32,
 };
 
-int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
-				struct snd_pcm_hw_params *params)
+int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
+			 struct snd_pcm_hw_params *params)
 {
 	struct dma_chan *chan = snd_dmaengine_pcm_get_chan(substream);
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
@@ -62,14 +62,14 @@ int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
 
 	return 0;
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_hw_params);
+EXPORT_SYMBOL(pxa2xx_pcm_hw_params);
 
-int __pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream)
 {
 	snd_pcm_set_runtime_buffer(substream, NULL);
 	return 0;
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_hw_free);
+EXPORT_SYMBOL(pxa2xx_pcm_hw_free);
 
 int pxa2xx_pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 {
@@ -84,13 +84,13 @@ pxa2xx_pcm_pointer(struct snd_pcm_substream *substream)
 }
 EXPORT_SYMBOL(pxa2xx_pcm_pointer);
 
-int __pxa2xx_pcm_prepare(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_prepare(struct snd_pcm_substream *substream)
 {
 	return 0;
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_prepare);
+EXPORT_SYMBOL(pxa2xx_pcm_prepare);
 
-int __pxa2xx_pcm_open(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_open(struct snd_pcm_substream *substream)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -127,13 +127,13 @@ int __pxa2xx_pcm_open(struct snd_pcm_substream *substream)
 		substream, dma_request_slave_channel(rtd->cpu_dai->dev,
 						     dma_params->chan_name));
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_open);
+EXPORT_SYMBOL(pxa2xx_pcm_open);
 
-int __pxa2xx_pcm_close(struct snd_pcm_substream *substream)
+int pxa2xx_pcm_close(struct snd_pcm_substream *substream)
 {
 	return snd_dmaengine_pcm_close_release_chan(substream);
 }
-EXPORT_SYMBOL(__pxa2xx_pcm_close);
+EXPORT_SYMBOL(pxa2xx_pcm_close);
 
 int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma)
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index 445e691126e5..da252d1f732e 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -20,8 +20,8 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-static int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
-	struct snd_pcm_hw_params *params)
+static int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_dmaengine_dai_dma_data *dma;
@@ -33,23 +33,16 @@ static int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
 	if (!dma)
 		return 0;
 
-	return __pxa2xx_pcm_hw_params(substream, params);
-}
-
-static int pxa2xx_pcm_hw_free(struct snd_pcm_substream *substream)
-{
-	__pxa2xx_pcm_hw_free(substream);
-
-	return 0;
+	return pxa2xx_pcm_hw_params(substream, params);
 }
 
 static const struct snd_pcm_ops pxa2xx_pcm_ops = {
-	.open		= __pxa2xx_pcm_open,
-	.close		= __pxa2xx_pcm_close,
+	.open		= pxa2xx_pcm_open,
+	.close		= pxa2xx_pcm_close,
 	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= pxa2xx_pcm_hw_params,
+	.hw_params	= __pxa2xx_pcm_hw_params,
 	.hw_free	= pxa2xx_pcm_hw_free,
-	.prepare	= __pxa2xx_pcm_prepare,
+	.prepare	= pxa2xx_pcm_prepare,
 	.trigger	= pxa2xx_pcm_trigger,
 	.pointer	= pxa2xx_pcm_pointer,
 	.mmap		= pxa2xx_pcm_mmap,
-- 
cgit v1.2.3


From 7afd1b0b2ef9a8120951188a955010ef92bdf885 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 21:33:55 +0200
Subject: ASoC: pxa: move some functions to pxa2xx-lib

To get rid of some intermediate platform layers, move pxa2xx_soc_pcm_new()
and pxa2xx_pcm_ops in pxa2xx-lib.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/pxa2xx-lib.h |  3 +++
 sound/arm/pxa2xx-ac97.c    |  6 ++---
 sound/arm/pxa2xx-pcm-lib.c | 41 ++++++++++++++++++++++++++++++++++
 sound/soc/pxa/pxa2xx-pcm.c | 55 ----------------------------------------------
 4 files changed, 47 insertions(+), 58 deletions(-)

diff --git a/include/sound/pxa2xx-lib.h b/include/sound/pxa2xx-lib.h
index b43de38de8b2..6758fc12fa84 100644
--- a/include/sound/pxa2xx-lib.h
+++ b/include/sound/pxa2xx-lib.h
@@ -8,6 +8,7 @@
 /* PCM */
 struct snd_pcm_substream;
 struct snd_pcm_hw_params;
+struct snd_soc_pcm_runtime;
 struct snd_pcm;
 
 extern int pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
@@ -22,6 +23,8 @@ extern int pxa2xx_pcm_mmap(struct snd_pcm_substream *substream,
 	struct vm_area_struct *vma);
 extern int pxa2xx_pcm_preallocate_dma_buffer(struct snd_pcm *pcm, int stream);
 extern void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm);
+extern int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd);
+extern const struct snd_pcm_ops pxa2xx_pcm_ops;
 
 /* AC97 */
 
diff --git a/sound/arm/pxa2xx-ac97.c b/sound/arm/pxa2xx-ac97.c
index 0d624337857b..1f72672262d0 100644
--- a/sound/arm/pxa2xx-ac97.c
+++ b/sound/arm/pxa2xx-ac97.c
@@ -174,7 +174,7 @@ static int pxa2xx_ac97_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(pxa2xx_ac97_pm_ops, pxa2xx_ac97_suspend, pxa2xx_ac97_resume);
 #endif
 
-static const struct snd_pcm_ops pxa2xx_pcm_ops = {
+static const struct snd_pcm_ops pxa2xx_ac97_pcm_ops = {
 	.open		= pxa2xx_ac97_pcm_open,
 	.close		= pxa2xx_ac97_pcm_close,
 	.ioctl		= snd_pcm_lib_ioctl,
@@ -203,13 +203,13 @@ static int pxa2xx_ac97_pcm_new(struct snd_card *card)
 		goto out;
 
 	stream = SNDRV_PCM_STREAM_PLAYBACK;
-	snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
+	snd_pcm_set_ops(pcm, stream, &pxa2xx_ac97_pcm_ops);
 	ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
 	if (ret)
 		goto out;
 
 	stream = SNDRV_PCM_STREAM_CAPTURE;
-	snd_pcm_set_ops(pcm, stream, &pxa2xx_pcm_ops);
+	snd_pcm_set_ops(pcm, stream, &pxa2xx_ac97_pcm_ops);
 	ret = pxa2xx_pcm_preallocate_dma_buffer(pcm, stream);
 	if (ret)
 		goto out;
diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index dc56dbebf441..add23d9b4ef6 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -179,6 +179,47 @@ void pxa2xx_pcm_free_dma_buffers(struct snd_pcm *pcm)
 }
 EXPORT_SYMBOL(pxa2xx_pcm_free_dma_buffers);
 
+int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_card *card = rtd->card->snd_card;
+	struct snd_pcm *pcm = rtd->pcm;
+	int ret;
+
+	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
+	if (ret)
+		return ret;
+
+	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
+		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
+			SNDRV_PCM_STREAM_PLAYBACK);
+		if (ret)
+			goto out;
+	}
+
+	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
+		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
+			SNDRV_PCM_STREAM_CAPTURE);
+		if (ret)
+			goto out;
+	}
+ out:
+	return ret;
+}
+EXPORT_SYMBOL(pxa2xx_soc_pcm_new);
+
+const struct snd_pcm_ops pxa2xx_pcm_ops = {
+	.open		= pxa2xx_pcm_open,
+	.close		= pxa2xx_pcm_close,
+	.ioctl		= snd_pcm_lib_ioctl,
+	.hw_params	= pxa2xx_pcm_hw_params,
+	.hw_free	= pxa2xx_pcm_hw_free,
+	.prepare	= pxa2xx_pcm_prepare,
+	.trigger	= pxa2xx_pcm_trigger,
+	.pointer	= pxa2xx_pcm_pointer,
+	.mmap		= pxa2xx_pcm_mmap,
+};
+EXPORT_SYMBOL(pxa2xx_pcm_ops);
+
 MODULE_AUTHOR("Nicolas Pitre");
 MODULE_DESCRIPTION("Intel PXA2xx sound library");
 MODULE_LICENSE("GPL");
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index da252d1f732e..a1df4ec76cbd 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -20,61 +20,6 @@
 #include <sound/pxa2xx-lib.h>
 #include <sound/dmaengine_pcm.h>
 
-static int __pxa2xx_pcm_hw_params(struct snd_pcm_substream *substream,
-				  struct snd_pcm_hw_params *params)
-{
-	struct snd_soc_pcm_runtime *rtd = substream->private_data;
-	struct snd_dmaengine_dai_dma_data *dma;
-
-	dma = snd_soc_dai_get_dma_data(rtd->cpu_dai, substream);
-
-	/* return if this is a bufferless transfer e.g.
-	 * codec <--> BT codec or GSM modem -- lg FIXME */
-	if (!dma)
-		return 0;
-
-	return pxa2xx_pcm_hw_params(substream, params);
-}
-
-static const struct snd_pcm_ops pxa2xx_pcm_ops = {
-	.open		= pxa2xx_pcm_open,
-	.close		= pxa2xx_pcm_close,
-	.ioctl		= snd_pcm_lib_ioctl,
-	.hw_params	= __pxa2xx_pcm_hw_params,
-	.hw_free	= pxa2xx_pcm_hw_free,
-	.prepare	= pxa2xx_pcm_prepare,
-	.trigger	= pxa2xx_pcm_trigger,
-	.pointer	= pxa2xx_pcm_pointer,
-	.mmap		= pxa2xx_pcm_mmap,
-};
-
-static int pxa2xx_soc_pcm_new(struct snd_soc_pcm_runtime *rtd)
-{
-	struct snd_card *card = rtd->card->snd_card;
-	struct snd_pcm *pcm = rtd->pcm;
-	int ret;
-
-	ret = dma_coerce_mask_and_coherent(card->dev, DMA_BIT_MASK(32));
-	if (ret)
-		return ret;
-
-	if (pcm->streams[SNDRV_PCM_STREAM_PLAYBACK].substream) {
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_PLAYBACK);
-		if (ret)
-			goto out;
-	}
-
-	if (pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream) {
-		ret = pxa2xx_pcm_preallocate_dma_buffer(pcm,
-			SNDRV_PCM_STREAM_CAPTURE);
-		if (ret)
-			goto out;
-	}
- out:
-	return ret;
-}
-
 static const struct snd_soc_component_driver pxa2xx_soc_platform = {
 	.ops		= &pxa2xx_pcm_ops,
 	.pcm_new	= pxa2xx_soc_pcm_new,
-- 
cgit v1.2.3


From 456ec80876564edb74a0fff78499beb7ca286302 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 21:33:56 +0200
Subject: ASoC: pxa2xx-pcm-lib: fix indenting

While at it, also fix some indenting.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/arm/pxa2xx-pcm-lib.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/arm/pxa2xx-pcm-lib.c b/sound/arm/pxa2xx-pcm-lib.c
index add23d9b4ef6..7931789d4a9f 100644
--- a/sound/arm/pxa2xx-pcm-lib.c
+++ b/sound/arm/pxa2xx-pcm-lib.c
@@ -23,8 +23,8 @@ static const struct snd_pcm_hardware pxa2xx_pcm_hardware = {
 				  SNDRV_PCM_INFO_PAUSE |
 				  SNDRV_PCM_INFO_RESUME,
 	.formats		= SNDRV_PCM_FMTBIT_S16_LE |
-					SNDRV_PCM_FMTBIT_S24_LE |
-					SNDRV_PCM_FMTBIT_S32_LE,
+				  SNDRV_PCM_FMTBIT_S24_LE |
+				  SNDRV_PCM_FMTBIT_S32_LE,
 	.period_bytes_min	= 32,
 	.period_bytes_max	= 8192 - 32,
 	.periods_min		= 1,
-- 
cgit v1.2.3


From d767d3ce5c48b3378e20e8cfd5d5379c4ca6001b Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 21:33:57 +0200
Subject: ASoC: pxa: provide PCM ops for ssp, i2s and ac97 components

Now that the functions are now available through pxa2xx-lib, hook them up
to pxa-sspi, pxa-ac97 and pxa-i2s. This allows DT platforms to use the DAIs
without a platform driver.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/pxa/pxa-ssp.c     | 3 +++
 sound/soc/pxa/pxa2xx-ac97.c | 3 +++
 sound/soc/pxa/pxa2xx-i2s.c  | 3 +++
 3 files changed, 9 insertions(+)

diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index c1f4af869289..01d54697ede4 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -841,6 +841,9 @@ static struct snd_soc_dai_driver pxa_ssp_dai = {
 
 static const struct snd_soc_component_driver pxa_ssp_component = {
 	.name		= "pxa-ssp",
+	.ops		= &pxa2xx_pcm_ops,
+	.pcm_new	= pxa2xx_soc_pcm_new,
+	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
 };
 
 #ifdef CONFIG_OF
diff --git a/sound/soc/pxa/pxa2xx-ac97.c b/sound/soc/pxa/pxa2xx-ac97.c
index c52b33802bf2..9f779657bc86 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -214,6 +214,9 @@ static struct snd_soc_dai_driver pxa_ac97_dai_driver[] = {
 
 static const struct snd_soc_component_driver pxa_ac97_component = {
 	.name		= "pxa-ac97",
+	.ops		= &pxa2xx_pcm_ops,
+	.pcm_new	= pxa2xx_soc_pcm_new,
+	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
 };
 
 #ifdef CONFIG_OF
diff --git a/sound/soc/pxa/pxa2xx-i2s.c b/sound/soc/pxa/pxa2xx-i2s.c
index e7184de0de04..42820121e5b9 100644
--- a/sound/soc/pxa/pxa2xx-i2s.c
+++ b/sound/soc/pxa/pxa2xx-i2s.c
@@ -364,6 +364,9 @@ static struct snd_soc_dai_driver pxa_i2s_dai = {
 
 static const struct snd_soc_component_driver pxa_i2s_component = {
 	.name		= "pxa-i2s",
+	.ops		= &pxa2xx_pcm_ops,
+	.pcm_new	= pxa2xx_soc_pcm_new,
+	.pcm_free	= pxa2xx_pcm_free_dma_buffers,
 };
 
 static int pxa2xx_i2s_drv_probe(struct platform_device *pdev)
-- 
cgit v1.2.3


From c7b4f15ddb4f28451679019374027f5223c616ce Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 21:33:58 +0200
Subject: ASoC: pxa: remove bindings from pxa2xx-pcm

This platform is no longer needed on DT boards, so let's remove them to
avoid confusion. DT bindings should use the CPU DAIs (I2S/SSP/AC97)
directly.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt         | 15 ---------------
 sound/soc/pxa/pxa2xx-pcm.c                                |  9 ---------
 2 files changed, 24 deletions(-)
 delete mode 100644 Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt

diff --git a/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt b/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt
deleted file mode 100644
index 551fbb8348c2..000000000000
--- a/Documentation/devicetree/bindings/sound/mrvl,pxa2xx-pcm.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-DT bindings for ARM PXA2xx PCM platform driver
-
-This is just a dummy driver that registers the PXA ASoC platform driver.
-It does not have any resources assigned.
-
-Required properties:
-
-	- compatible		'mrvl,pxa-pcm-audio'
-
-Example:
-
-	pxa_pcm_audio: snd_soc_pxa_audio {
-		compatible = "mrvl,pxa-pcm-audio";
-	};
-
diff --git a/sound/soc/pxa/pxa2xx-pcm.c b/sound/soc/pxa/pxa2xx-pcm.c
index a1df4ec76cbd..72eaaef1b426 100644
--- a/sound/soc/pxa/pxa2xx-pcm.c
+++ b/sound/soc/pxa/pxa2xx-pcm.c
@@ -32,18 +32,9 @@ static int pxa2xx_soc_platform_probe(struct platform_device *pdev)
 					       NULL, 0);
 }
 
-#ifdef CONFIG_OF
-static const struct of_device_id snd_soc_pxa_audio_match[] = {
-	{ .compatible   = "mrvl,pxa-pcm-audio" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, snd_soc_pxa_audio_match);
-#endif
-
 static struct platform_driver pxa_pcm_driver = {
 	.driver = {
 		.name = "pxa-pcm-audio",
-		.of_match_table = of_match_ptr(snd_soc_pxa_audio_match),
 	},
 
 	.probe = pxa2xx_soc_platform_probe,
-- 
cgit v1.2.3


From 0a94cf3457408058f894cc4d95e58d8e18eb7f75 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 21:33:59 +0200
Subject: ASoC: pxa: make SND_PXA2XX_SOC_I2S selectable

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/pxa/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 960744e46edc..95dcf97a6271 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -31,7 +31,7 @@ config SND_PXA2XX_SOC_I2S
 	tristate
 
 config SND_PXA_SOC_SSP
-	tristate
+	tristate "Soc Audio via PXA2xx/PXA3xx SSP ports"
 	select PXA_SSP
 
 config SND_MMP_SOC_SSPA
-- 
cgit v1.2.3


From fe041deba4f6a857cd9d0c08a84b9f1709ede2b1 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 17:11:17 +0200
Subject: ath9k: use timespec64 for tsf_ts

ath9k is the last remaining user of the deprecated getrawmonotonic()
interface. There is nothing wrong with this usage, but migrating
to a timespec64 based interface lets us clean up the old API.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ath9k.h   |  4 ++--
 drivers/net/wireless/ath/ath9k/channel.c | 14 +++++++-------
 drivers/net/wireless/ath/ath9k/hw.c      | 10 +++++-----
 drivers/net/wireless/ath/ath9k/hw.h      |  2 +-
 drivers/net/wireless/ath/ath9k/main.c    |  4 ++--
 5 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index ef0de4f1312c..21ba20981a80 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -342,7 +342,7 @@ struct ath_chanctx {
 
 	struct ath_beacon_config beacon;
 	struct ath9k_hw_cal_data caldata;
-	struct timespec tsf_ts;
+	struct timespec64 tsf_ts;
 	u64 tsf_val;
 	u32 last_beacon;
 
@@ -1021,7 +1021,7 @@ struct ath_softc {
 	struct ath_offchannel offchannel;
 	struct ath_chanctx *next_chan;
 	struct completion go_beacon;
-	struct timespec last_event_time;
+	struct timespec64 last_event_time;
 #endif
 
 	unsigned long driver_data;
diff --git a/drivers/net/wireless/ath/ath9k/channel.c b/drivers/net/wireless/ath/ath9k/channel.c
index 1b05b5d7a038..fd61ae4782b6 100644
--- a/drivers/net/wireless/ath/ath9k/channel.c
+++ b/drivers/net/wireless/ath/ath9k/channel.c
@@ -233,9 +233,9 @@ static const char *chanctx_state_string(enum ath_chanctx_state state)
 static u32 chanctx_event_delta(struct ath_softc *sc)
 {
 	u64 ms;
-	struct timespec ts, *old;
+	struct timespec64 ts, *old;
 
-	getrawmonotonic(&ts);
+	ktime_get_raw_ts64(&ts);
 	old = &sc->last_event_time;
 	ms = ts.tv_sec * 1000 + ts.tv_nsec / 1000000;
 	ms -= old->tv_sec * 1000 + old->tv_nsec / 1000000;
@@ -334,7 +334,7 @@ ath_chanctx_get_next(struct ath_softc *sc, struct ath_chanctx *ctx)
 static void ath_chanctx_adjust_tbtt_delta(struct ath_softc *sc)
 {
 	struct ath_chanctx *prev, *cur;
-	struct timespec ts;
+	struct timespec64 ts;
 	u32 cur_tsf, prev_tsf, beacon_int;
 	s32 offset;
 
@@ -346,7 +346,7 @@ static void ath_chanctx_adjust_tbtt_delta(struct ath_softc *sc)
 	if (!prev->switch_after_beacon)
 		return;
 
-	getrawmonotonic(&ts);
+	ktime_get_raw_ts64(&ts);
 	cur_tsf = (u32) cur->tsf_val +
 		  ath9k_hw_get_tsf_offset(&cur->tsf_ts, &ts);
 
@@ -1230,7 +1230,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force)
 {
 	struct ath_common *common = ath9k_hw_common(sc->sc_ah);
 	struct ath_chanctx *old_ctx;
-	struct timespec ts;
+	struct timespec64 ts;
 	bool measure_time = false;
 	bool send_ps = false;
 	bool queues_stopped = false;
@@ -1260,7 +1260,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force)
 		spin_unlock_bh(&sc->chan_lock);
 
 		if (sc->next_chan == &sc->offchannel.chan) {
-			getrawmonotonic(&ts);
+			ktime_get_raw_ts64(&ts);
 			measure_time = true;
 		}
 
@@ -1277,7 +1277,7 @@ void ath_chanctx_set_next(struct ath_softc *sc, bool force)
 		spin_lock_bh(&sc->chan_lock);
 
 		if (sc->cur_chan != &sc->offchannel.chan) {
-			getrawmonotonic(&sc->cur_chan->tsf_ts);
+			ktime_get_raw_ts64(&sc->cur_chan->tsf_ts);
 			sc->cur_chan->tsf_val = ath9k_hw_gettsf64(sc->sc_ah);
 		}
 	}
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index e60bea4604e4..e8e1f785bc5c 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1835,13 +1835,13 @@ fail:
 	return -EINVAL;
 }
 
-u32 ath9k_hw_get_tsf_offset(struct timespec *last, struct timespec *cur)
+u32 ath9k_hw_get_tsf_offset(struct timespec64 *last, struct timespec64 *cur)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	s64 usec;
 
 	if (!cur) {
-		getrawmonotonic(&ts);
+		ktime_get_raw_ts64(&ts);
 		cur = &ts;
 	}
 
@@ -1859,7 +1859,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan,
 	u32 saveLedState;
 	u32 saveDefAntenna;
 	u32 macStaId1;
-	struct timespec tsf_ts;
+	struct timespec64 tsf_ts;
 	u32 tsf_offset;
 	u64 tsf = 0;
 	int r;
@@ -1905,7 +1905,7 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan,
 	macStaId1 = REG_READ(ah, AR_STA_ID1) & AR_STA_ID1_BASE_RATE_11B;
 
 	/* Save TSF before chip reset, a cold reset clears it */
-	getrawmonotonic(&tsf_ts);
+	ktime_get_raw_ts64(&tsf_ts);
 	tsf = ath9k_hw_gettsf64(ah);
 
 	saveLedState = REG_READ(ah, AR_CFG_LED) &
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 9804a24a2dc0..68956cdc8c9a 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -1060,7 +1060,7 @@ u32 ath9k_hw_gettsf32(struct ath_hw *ah);
 u64 ath9k_hw_gettsf64(struct ath_hw *ah);
 void ath9k_hw_settsf64(struct ath_hw *ah, u64 tsf64);
 void ath9k_hw_reset_tsf(struct ath_hw *ah);
-u32 ath9k_hw_get_tsf_offset(struct timespec *last, struct timespec *cur);
+u32 ath9k_hw_get_tsf_offset(struct timespec64 *last, struct timespec64 *cur);
 void ath9k_hw_set_tsfadjust(struct ath_hw *ah, bool set);
 void ath9k_hw_init_global_settings(struct ath_hw *ah);
 u32 ar9003_get_pll_sqsum_dvc(struct ath_hw *ah);
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index 5eb1c0aea41d..1049773378f2 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -1865,7 +1865,7 @@ static void ath9k_set_tsf(struct ieee80211_hw *hw,
 	mutex_lock(&sc->mutex);
 	ath9k_ps_wakeup(sc);
 	tsf -= le64_to_cpu(avp->tsf_adjust);
-	getrawmonotonic(&avp->chanctx->tsf_ts);
+	ktime_get_raw_ts64(&avp->chanctx->tsf_ts);
 	if (sc->cur_chan == avp->chanctx)
 		ath9k_hw_settsf64(sc->sc_ah, tsf);
 	avp->chanctx->tsf_val = tsf;
@@ -1881,7 +1881,7 @@ static void ath9k_reset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	mutex_lock(&sc->mutex);
 
 	ath9k_ps_wakeup(sc);
-	getrawmonotonic(&avp->chanctx->tsf_ts);
+	ktime_get_raw_ts64(&avp->chanctx->tsf_ts);
 	if (sc->cur_chan == avp->chanctx)
 		ath9k_hw_reset_tsf(sc->sc_ah);
 	avp->chanctx->tsf_val = 0;
-- 
cgit v1.2.3


From 84a0d4669c8fdbe6e3e23937c5083af99a1946f2 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 20 Jun 2018 21:36:45 +0200
Subject: ath9k: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: QCA ath9k Development <ath9k-devel@qca.qualcomm.com>
Cc: Kalle Valo <kvalo@codeaurora.org>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: linux-wireless@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/hif_usb.c      |  7 ++++---
 drivers/net/wireless/ath/ath9k/htc_drv_txrx.c |  9 +++++----
 drivers/net/wireless/ath/ath9k/wmi.c          | 11 ++++++-----
 3 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
index cb0eef13af1c..fb649d85b8fc 100644
--- a/drivers/net/wireless/ath/ath9k/hif_usb.c
+++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
@@ -138,6 +138,7 @@ static void hif_usb_mgmt_cb(struct urb *urb)
 {
 	struct cmd_buf *cmd = (struct cmd_buf *)urb->context;
 	struct hif_device_usb *hif_dev;
+	unsigned long flags;
 	bool txok = true;
 
 	if (!cmd || !cmd->skb || !cmd->hif_dev)
@@ -158,14 +159,14 @@ static void hif_usb_mgmt_cb(struct urb *urb)
 		 * If the URBs are being flushed, no need to complete
 		 * this packet.
 		 */
-		spin_lock(&hif_dev->tx.tx_lock);
+		spin_lock_irqsave(&hif_dev->tx.tx_lock, flags);
 		if (hif_dev->tx.flags & HIF_USB_TX_FLUSH) {
-			spin_unlock(&hif_dev->tx.tx_lock);
+			spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 			dev_kfree_skb_any(cmd->skb);
 			kfree(cmd);
 			return;
 		}
-		spin_unlock(&hif_dev->tx.tx_lock);
+		spin_unlock_irqrestore(&hif_dev->tx.tx_lock, flags);
 
 		break;
 	default:
diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
index 585736a837ed..799010ed04e0 100644
--- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
+++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
@@ -1107,25 +1107,26 @@ void ath9k_htc_rxep(void *drv_priv, struct sk_buff *skb,
 	struct ath_hw *ah = priv->ah;
 	struct ath_common *common = ath9k_hw_common(ah);
 	struct ath9k_htc_rxbuf *rxbuf = NULL, *tmp_buf = NULL;
+	unsigned long flags;
 
-	spin_lock(&priv->rx.rxbuflock);
+	spin_lock_irqsave(&priv->rx.rxbuflock, flags);
 	list_for_each_entry(tmp_buf, &priv->rx.rxbuf, list) {
 		if (!tmp_buf->in_process) {
 			rxbuf = tmp_buf;
 			break;
 		}
 	}
-	spin_unlock(&priv->rx.rxbuflock);
+	spin_unlock_irqrestore(&priv->rx.rxbuflock, flags);
 
 	if (rxbuf == NULL) {
 		ath_dbg(common, ANY, "No free RX buffer\n");
 		goto err;
 	}
 
-	spin_lock(&priv->rx.rxbuflock);
+	spin_lock_irqsave(&priv->rx.rxbuflock, flags);
 	rxbuf->skb = skb;
 	rxbuf->in_process = true;
-	spin_unlock(&priv->rx.rxbuflock);
+	spin_unlock_irqrestore(&priv->rx.rxbuflock, flags);
 
 	tasklet_schedule(&priv->rx_tasklet);
 	return;
diff --git a/drivers/net/wireless/ath/ath9k/wmi.c b/drivers/net/wireless/ath/ath9k/wmi.c
index b0b5579b7560..d1f6710ca63b 100644
--- a/drivers/net/wireless/ath/ath9k/wmi.c
+++ b/drivers/net/wireless/ath/ath9k/wmi.c
@@ -209,6 +209,7 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb,
 {
 	struct wmi *wmi = priv;
 	struct wmi_cmd_hdr *hdr;
+	unsigned long flags;
 	u16 cmd_id;
 
 	if (unlikely(wmi->stopped))
@@ -218,20 +219,20 @@ static void ath9k_wmi_ctrl_rx(void *priv, struct sk_buff *skb,
 	cmd_id = be16_to_cpu(hdr->command_id);
 
 	if (cmd_id & 0x1000) {
-		spin_lock(&wmi->wmi_lock);
+		spin_lock_irqsave(&wmi->wmi_lock, flags);
 		__skb_queue_tail(&wmi->wmi_event_queue, skb);
-		spin_unlock(&wmi->wmi_lock);
+		spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 		tasklet_schedule(&wmi->wmi_event_tasklet);
 		return;
 	}
 
 	/* Check if there has been a timeout. */
-	spin_lock(&wmi->wmi_lock);
+	spin_lock_irqsave(&wmi->wmi_lock, flags);
 	if (be16_to_cpu(hdr->seq_no) != wmi->last_seq_id) {
-		spin_unlock(&wmi->wmi_lock);
+		spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 		goto free_skb;
 	}
-	spin_unlock(&wmi->wmi_lock);
+	spin_unlock_irqrestore(&wmi->wmi_lock, flags);
 
 	/* WMI command response */
 	ath9k_wmi_rsp_callback(wmi, skb);
-- 
cgit v1.2.3


From 62652555c616cad23a572f76cb5e870ab5395191 Mon Sep 17 00:00:00 2001
From: Bob Copeland <me@bobcopeland.com>
Date: Thu, 21 Jun 2018 08:25:48 -0400
Subject: ath10k: use locked skb_dequeue for rx completions

In our environment we are occasionally seeing the following stack trace
in ath10k:

Unable to handle kernel paging request at virtual address 0000a800
pgd = c0204000
[0000a800] *pgd=00000000
Internal error: Oops: 17 [#1] SMP ARM
Modules linked in: dwc3 dwc3_of_simple phy_qcom_dwc3 nf_nat xt_connmark
CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.9.31 #2
Hardware name: Generic DT based system
task: c09f4f40 task.stack: c09ee000
PC is at kfree_skb_list+0x1c/0x2c
LR is at skb_release_data+0x6c/0x108
pc : [<c065dcc4>]    lr : [<c065da5c>]    psr: 200f0113
sp : c09efb68  ip : c09efb80  fp : c09efb7c
r10: 00000000  r9 : 00000000  r8 : 043fddd1
r7 : bf15d160  r6 : 00000000  r5 : d4ca2f00  r4 : ca7c6480
r3 : 000000a0  r2 : 01000000  r1 : c0a57470  r0 : 0000a800
Flags: nzCv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
Control: 10c5787d  Table: 56e6006a  DAC: 00000051
Process swapper/0 (pid: 0, stack limit = 0xc09ee210)
Stack: (0xc09efb68 to 0xc09f0000)
fb60:                   ca7c6480 d4ca2f00 c09efb9c c09efb80 c065da5c c065dcb4
fb80: d4ca2f00 00000000 dcbf8400 bf15d160 c09efbb4 c09efba0 c065db28 c065d9fc
fba0: d4ca2f00 00000000 c09efbcc c09efbb8 c065db48 c065db04 d4ca2f00 00000000
fbc0: c09efbe4 c09efbd0 c065ddd0 c065db38 d4ca2f00 00000000 c09efc64 c09efbe8
fbe0: bf09bd00 c065dd10 00000003 7fffffff c09efc24 dcbfc9c0 01200000 00000000
fc00: 00000000 00000000 ddb7e440 c09e9440 c09efc48 1d195000 c09efc7c c09efc28
fc20: c027bb68 c028aa00 ddb7e4f8 bf13231c ddb7e454 0004091f bf154571 d4ca2f00
fc40: dcbf8d00 ca7c5df6 bf154538 01200000 00000000 bf154538 c09efd1c c09efc68
fc60: bf132458 bf09bbbc ca7c5dec 00000041 bf154538 bf154539 000007bf bf154545
fc80: bf154538 bf154538 bf154538 bf154538 bf154538 00000000 00000000 000016c1
fca0: 00000001 c09efcb0 01200000 00000000 00000000 00000000 00000000 00000001
fcc0: bf154539 00000041 00000000 00000007 00000000 000000d0 ffffffff 3160ffff
fce0: 9ad93e97 3e973160 7bf09ad9 0004091f d4ca2f00 c09efdb0 dcbf94e8 00000000
fd00: dcbf8d00 01200000 00000000 dcbf8d00 c09efd44 c09efd20 bf132544 bf132130
fd20: dcbf8d00 00000000 d4ca2f00 c09efdb0 00000001 d4ca2f00 c09efdec c09efd48
fd40: bf133630 bf1324d0 ca7c5cc0 000007c0 c09efd88 c09efd70 c0764230 c02277d8
fd60: 200f0113 ffffffff dcbf94c8 bf000000 dcbf93b0 dcbf8d00 00000040 dcbf945c
fd80: dcbf94e8 00000000 c09efdcc 00000000 c09efd90 c09efd90 00000000 00000024
fda0: dcbf8d00 00000000 00000005 dcbf8d00 c09efdb0 c09efdb0 00000000 00000040
fdc0: c09efdec dcbf8d00 dcbfc9c0 c09ed140 00000040 00000000 00000100 00000040
fde0: c09efe14 c09efdf0 bf1739b4 bf132840 dcbfc9c0 ddb82140 c09ed140 1d195000
fe00: 00000001 00000100 c09efe64 c09efe18 c067136c bf173958 ddb7fac8 c09f0d00
fe20: 001df678 0000012c c09efe28 c09efe28 c09efe30 c09efe30 c0a7fb28 ffffe000
fe40: c09f008c 00000003 00000008 c0a598c0 00000100 c09f0080 c09efeb4 c09efe68
fe60: c02096e0 c0671278 c0494584 00000080 dd5c3300 c09f0d00 00000004 001df677
fe80: 0000000a 00200100 dd5c3300 00000000 00000000 c09eaa70 00000060 dd410800
fea0: c09ee000 00000000 c09efecc c09efeb8 c0227944 c02094c4 00000000 00000000
fec0: c09efef4 c09efed0 c0268b64 c02278ac de802000 c09f1b1c c09eff20 c0a16cc0
fee0: de803000 c09ee000 c09eff1c c09efef8 c020947c c0268ae0 c02103dc 600f0013
ff00: ffffffff c09eff54 ffffe000 c09ee000 c09eff7c c09eff20 c021448c c0209424
ff20: 00000001 00000000 00000000 c021ddc0 00000000 00000000 c09f1024 00000001
ff40: ffffe000 c09f1078 00000000 c09eff7c c09eff80 c09eff70 c02103ec c02103dc
ff60: 600f0013 ffffffff 00000051 00000000 c09eff8c c09eff80 c0763cc4 c02103bc
ff80: c09effa4 c09eff90 c025f0e4 c0763c98 c0a59040 c09f1000 c09effb4 c09effa8
ffa0: c075efe0 c025efd4 c09efff4 c09effb8 c097dcac c075ef7c ffffffff ffffffff
ffc0: 00000000 c097d6c4 00000000 c09c1a28 c0a59294 c09f101c c09c1a24 c09f61c0
ffe0: 4220406a 512f04d0 00000000 c09efff8 4220807c c097d95c 00000000 00000000
[<c065dcc4>] (kfree_skb_list) from [<c065da5c>] (skb_release_data+0x6c/0x108)
[<c065da5c>] (skb_release_data) from [<c065db28>] (skb_release_all+0x30/0x34)
[<c065db28>] (skb_release_all) from [<c065db48>] (__kfree_skb+0x1c/0x9c)
[<c065db48>] (__kfree_skb) from [<c065ddd0>] (consume_skb+0xcc/0xd8)
[<c065ddd0>] (consume_skb) from [<bf09bd00>] (ieee80211_rx_napi+0x150/0x82c [mac80211])
[<bf09bd00>] (ieee80211_rx_napi [mac80211]) from [<bf132458>] (ath10k_htt_t2h_msg_handler+0x15e8/0x19c4 [ath10k_core])
[<bf132458>] (ath10k_htt_t2h_msg_handler [ath10k_core]) from [<bf132544>] (ath10k_htt_t2h_msg_handler+0x16d4/0x19c4 [ath10k_core])
[<bf132544>] (ath10k_htt_t2h_msg_handler [ath10k_core]) from [<bf133630>] (ath10k_htt_txrx_compl_task+0xdfc/0x12cc [ath10k_core])
[<bf133630>] (ath10k_htt_txrx_compl_task [ath10k_core]) from [<bf1739b4>] (ath10k_pci_napi_poll+0x68/0xf4 [ath10k_pci])
[<bf1739b4>] (ath10k_pci_napi_poll [ath10k_pci]) from [<c067136c>] (net_rx_action+0x100/0x33c)
[<c067136c>] (net_rx_action) from [<c02096e0>] (__do_softirq+0x228/0x31c)
[<c02096e0>] (__do_softirq) from [<c0227944>] (irq_exit+0xa4/0x114)

The trace points to a corrupt skb inside kfree_skb(), seemingly because
one of the shared skb queues is getting corrupted.  Most of the skb queues
ath10k uses are local to a single call stack, but three are shared among
multiple codepaths:

 - rx_msdus_q,
 - rx_in_ord_compl_q, and
 - tx_fetch_ind_q

Of the three, the first two are manipulated using the unlocked skb_queue
functions without any additional lock protecting them.  Use the locked
variants of skb_queue_* functions to protect these manipulations.

Signed-off-by: Bob Copeland <bobcopeland@fb.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htt_rx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c
index 2840ef75e3a6..4d1cd90d6d27 100644
--- a/drivers/net/wireless/ath/ath10k/htt_rx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_rx.c
@@ -1092,7 +1092,7 @@ static void ath10k_htt_rx_h_queue_msdu(struct ath10k *ar,
 	status = IEEE80211_SKB_RXCB(skb);
 	*status = *rx_status;
 
-	__skb_queue_tail(&ar->htt.rx_msdus_q, skb);
+	skb_queue_tail(&ar->htt.rx_msdus_q, skb);
 }
 
 static void ath10k_process_rx(struct ath10k *ar, struct sk_buff *skb)
@@ -2813,7 +2813,7 @@ bool ath10k_htt_t2h_msg_handler(struct ath10k *ar, struct sk_buff *skb)
 		break;
 	}
 	case HTT_T2H_MSG_TYPE_RX_IN_ORD_PADDR_IND: {
-		__skb_queue_tail(&htt->rx_in_ord_compl_q, skb);
+		skb_queue_tail(&htt->rx_in_ord_compl_q, skb);
 		return false;
 	}
 	case HTT_T2H_MSG_TYPE_TX_CREDIT_UPDATE_IND:
@@ -2877,7 +2877,7 @@ static int ath10k_htt_rx_deliver_msdu(struct ath10k *ar, int quota, int budget)
 		if (skb_queue_empty(&ar->htt.rx_msdus_q))
 			break;
 
-		skb = __skb_dequeue(&ar->htt.rx_msdus_q);
+		skb = skb_dequeue(&ar->htt.rx_msdus_q);
 		if (!skb)
 			break;
 		ath10k_process_rx(ar, skb);
@@ -2908,7 +2908,7 @@ int ath10k_htt_txrx_compl_task(struct ath10k *ar, int budget)
 		goto exit;
 	}
 
-	while ((skb = __skb_dequeue(&htt->rx_in_ord_compl_q))) {
+	while ((skb = skb_dequeue(&htt->rx_in_ord_compl_q))) {
 		spin_lock_bh(&htt->rx_ring.lock);
 		ret = ath10k_htt_rx_in_ord_ind(ar, skb);
 		spin_unlock_bh(&htt->rx_ring.lock);
-- 
cgit v1.2.3


From 10db60b9fab7d45a9c3b983ead41cd1416eb1cb3 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Wed, 20 Jun 2018 09:57:58 +0200
Subject: wcn36xx: Fix WEP104 encryption type

This is an obvious copy & paste bug.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wcn36xx/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index aeb5e6e806be..4648a78c4a5c 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -512,7 +512,7 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		vif_priv->encrypt_type = WCN36XX_HAL_ED_WEP40;
 		break;
 	case WLAN_CIPHER_SUITE_WEP104:
-		vif_priv->encrypt_type = WCN36XX_HAL_ED_WEP40;
+		vif_priv->encrypt_type = WCN36XX_HAL_ED_WEP104;
 		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 		vif_priv->encrypt_type = WCN36XX_HAL_ED_CCMP;
-- 
cgit v1.2.3


From e3160542ab488cff4e12c81066c51928c08e384d Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Wed, 20 Jun 2018 09:57:59 +0200
Subject: wcn36xx: Track associated stations

Add list of associated stations(STA, AP, peer...) per vif.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wcn36xx/main.c    | 5 +++++
 drivers/net/wireless/ath/wcn36xx/wcn36xx.h | 3 +++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 4648a78c4a5c..6fd0bf66da5d 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -567,6 +567,7 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 				key_conf->keyidx,
 				key_conf->keylen,
 				key);
+
 			if ((WLAN_CIPHER_SUITE_WEP40 == key_conf->cipher) ||
 			    (WLAN_CIPHER_SUITE_WEP104 == key_conf->cipher)) {
 				sta_priv->is_data_encrypted = true;
@@ -984,6 +985,7 @@ static int wcn36xx_add_interface(struct ieee80211_hw *hw,
 	mutex_lock(&wcn->conf_mutex);
 
 	vif_priv->bss_index = WCN36XX_HAL_BSS_INVALID_IDX;
+	INIT_LIST_HEAD(&vif_priv->sta_list);
 	list_add(&vif_priv->list, &wcn->vif_list);
 	wcn36xx_smd_add_sta_self(wcn, vif);
 
@@ -1005,6 +1007,8 @@ static int wcn36xx_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	spin_lock_init(&sta_priv->ampdu_lock);
 	sta_priv->vif = vif_priv;
+	list_add(&sta_priv->list, &vif_priv->sta_list);
+
 	/*
 	 * For STA mode HW will be configured on BSS_CHANGED_ASSOC because
 	 * at this stage AID is not available yet.
@@ -1032,6 +1036,7 @@ static int wcn36xx_sta_remove(struct ieee80211_hw *hw,
 
 	mutex_lock(&wcn->conf_mutex);
 
+	list_del(&sta_priv->list);
 	wcn36xx_smd_delete_sta(wcn, sta_priv->sta_index);
 	sta_priv->vif = NULL;
 
diff --git a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
index 11e74015c79a..a58f313983b9 100644
--- a/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
+++ b/drivers/net/wireless/ath/wcn36xx/wcn36xx.h
@@ -129,6 +129,8 @@ struct wcn36xx_vif {
 	u8 self_sta_index;
 	u8 self_dpu_desc_index;
 	u8 self_ucast_dpu_sign;
+
+	struct list_head sta_list;
 };
 
 /**
@@ -154,6 +156,7 @@ struct wcn36xx_vif {
  * |______________|_____________|_______________|
  */
 struct wcn36xx_sta {
+	struct list_head list;
 	struct wcn36xx_vif *vif;
 	u16 aid;
 	u16 tid;
-- 
cgit v1.2.3


From 216da1287a8a9e8a2dbef59c8bfc2f4dda11b92a Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Wed, 20 Jun 2018 09:58:00 +0200
Subject: wcn36xx: Fix WEP encryption

In case of WEP encryption, driver has to configure shared key for
associated station(s). Note that sta pointer is NULL in case of non
pairwise key, causing NULL pointer dereference with existing code
(sta_priv->is_data_encrypted). Fix this by using associated sta list
instead. This enables WEP support as client, WEP AP is non-functional.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wcn36xx/main.c | 19 +++++++++++--------
 drivers/net/wireless/ath/wcn36xx/smd.c  | 20 ++++++++++++++------
 2 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index 6fd0bf66da5d..e38443ecaab4 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -493,7 +493,7 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 {
 	struct wcn36xx *wcn = hw->priv;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	struct wcn36xx_sta *sta_priv = wcn36xx_sta_to_priv(sta);
+	struct wcn36xx_sta *sta_priv = sta ? wcn36xx_sta_to_priv(sta) : NULL;
 	int ret = 0;
 	u8 key[WLAN_MAX_KEY_LEN];
 
@@ -570,13 +570,16 @@ static int wcn36xx_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 			if ((WLAN_CIPHER_SUITE_WEP40 == key_conf->cipher) ||
 			    (WLAN_CIPHER_SUITE_WEP104 == key_conf->cipher)) {
-				sta_priv->is_data_encrypted = true;
-				wcn36xx_smd_set_stakey(wcn,
-					vif_priv->encrypt_type,
-					key_conf->keyidx,
-					key_conf->keylen,
-					key,
-					get_sta_index(vif, sta_priv));
+				list_for_each_entry(sta_priv,
+						    &vif_priv->sta_list, list) {
+					sta_priv->is_data_encrypted = true;
+					wcn36xx_smd_set_stakey(wcn,
+						vif_priv->encrypt_type,
+						key_conf->keyidx,
+						key_conf->keylen,
+						key,
+						get_sta_index(vif, sta_priv));
+				}
 			}
 		}
 		break;
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index b4dadf75d565..304a86c7dcd2 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -1708,12 +1708,20 @@ int wcn36xx_smd_set_stakey(struct wcn36xx *wcn,
 	msg_body.set_sta_key_params.sta_index = sta_index;
 	msg_body.set_sta_key_params.enc_type = enc_type;
 
-	msg_body.set_sta_key_params.key[0].id = keyidx;
-	msg_body.set_sta_key_params.key[0].unicast = 1;
-	msg_body.set_sta_key_params.key[0].direction = WCN36XX_HAL_TX_RX;
-	msg_body.set_sta_key_params.key[0].pae_role = 0;
-	msg_body.set_sta_key_params.key[0].length = keylen;
-	memcpy(msg_body.set_sta_key_params.key[0].key, key, keylen);
+	if (enc_type == WCN36XX_HAL_ED_WEP104 ||
+	    enc_type == WCN36XX_HAL_ED_WEP40) {
+		/* Use bss key for wep (static) */
+		msg_body.set_sta_key_params.def_wep_idx = keyidx;
+		msg_body.set_sta_key_params.wep_type = 0;
+	} else {
+		msg_body.set_sta_key_params.key[0].id = keyidx;
+		msg_body.set_sta_key_params.key[0].unicast = 1;
+		msg_body.set_sta_key_params.key[0].direction = WCN36XX_HAL_TX_RX;
+		msg_body.set_sta_key_params.key[0].pae_role = 0;
+		msg_body.set_sta_key_params.key[0].length = keylen;
+		memcpy(msg_body.set_sta_key_params.key[0].key, key, keylen);
+	}
+
 	msg_body.set_sta_key_params.single_tid_rc = 1;
 
 	PREPARE_HAL_BUF(wcn->hal_buf, msg_body);
-- 
cgit v1.2.3


From e3bc2ebd922dadfdc9eea569a2c93d70eb75fc07 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Sat, 23 Jun 2018 10:29:52 +0530
Subject: dt-bindings: pinctrl: Add gpio interrupt bindings for Actions S900
 SoC

Add gpio interrupt bindings for Actions Semi S900 SoC.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../devicetree/bindings/pinctrl/actions,s900-pinctrl.txt       | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt
index 8fb5a53775e8..81b58dddd3ed 100644
--- a/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/actions,s900-pinctrl.txt
@@ -19,6 +19,10 @@ Required Properties:
                     defines the interrupt number, the second encodes
                     the trigger flags described in
                     bindings/interrupt-controller/interrupts.txt
+- interrupts: The interrupt outputs from the controller. There is one GPIO
+              interrupt per GPIO bank. The number of interrupts listed depends
+              on the number of GPIO banks on the SoC. The interrupts must be
+              ordered by bank, starting with bank 0.
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
 common pinctrl bindings used by client devices, including the meaning of the
@@ -180,6 +184,12 @@ Example:
                   #gpio-cells = <2>;
                   interrupt-controller;
                   #interrupt-cells = <2>;
+                  interrupts = <GIC_SPI 36 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 37 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 38 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 39 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 40 IRQ_TYPE_LEVEL_HIGH>,
+                               <GIC_SPI 16 IRQ_TYPE_LEVEL_HIGH>;
 
                   uart2-default: uart2-default {
                           pinmux {
-- 
cgit v1.2.3


From 6c5d0736e9c09f00f5549f20390d6daae98a1bfd Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Sat, 23 Jun 2018 10:29:54 +0530
Subject: pinctrl: actions: Add interrupt support for OWL S900 SoC

Add interrupt support for Actions Semi OWL S900 SoC.

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/actions/Kconfig        |   1 +
 drivers/pinctrl/actions/pinctrl-owl.c  | 271 ++++++++++++++++++++++++++++++++-
 drivers/pinctrl/actions/pinctrl-owl.h  |  22 ++-
 drivers/pinctrl/actions/pinctrl-s900.c |  31 ++--
 4 files changed, 307 insertions(+), 18 deletions(-)

diff --git a/drivers/pinctrl/actions/Kconfig b/drivers/pinctrl/actions/Kconfig
index 490927b4ea76..2397cb0f6011 100644
--- a/drivers/pinctrl/actions/Kconfig
+++ b/drivers/pinctrl/actions/Kconfig
@@ -5,6 +5,7 @@ config PINCTRL_OWL
 	select PINCONF
 	select GENERIC_PINCONF
 	select GPIOLIB
+	select GPIOLIB_IRQCHIP
 	help
 	  Say Y here to enable Actions Semi OWL pinctrl driver
 
diff --git a/drivers/pinctrl/actions/pinctrl-owl.c b/drivers/pinctrl/actions/pinctrl-owl.c
index 76243caa08c6..ce032d71dad5 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.c
+++ b/drivers/pinctrl/actions/pinctrl-owl.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/gpio/driver.h>
 #include <linux/io.h>
+#include <linux/irq.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -45,6 +46,9 @@ struct owl_pinctrl {
 	struct clk *clk;
 	const struct owl_pinctrl_soc_data *soc;
 	void __iomem *base;
+	struct irq_chip irq_chip;
+	unsigned int num_irq;
+	unsigned int *irq;
 };
 
 static void owl_update_bits(void __iomem *base, u32 mask, u32 val)
@@ -701,10 +705,213 @@ static int owl_gpio_direction_output(struct gpio_chip *chip,
 	return 0;
 }
 
+static void irq_set_type(struct owl_pinctrl *pctrl, int gpio, unsigned int type)
+{
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int offset, value, irq_type = 0;
+
+	switch (type) {
+	case IRQ_TYPE_EDGE_BOTH:
+		/*
+		 * Since the hardware doesn't support interrupts on both edges,
+		 * emulate it in the software by setting the single edge
+		 * interrupt and switching to the opposite edge while ACKing
+		 * the interrupt
+		 */
+		if (owl_gpio_get(&pctrl->chip, gpio))
+			irq_type = OWL_GPIO_INT_EDGE_FALLING;
+		else
+			irq_type = OWL_GPIO_INT_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_RISING:
+		irq_type = OWL_GPIO_INT_EDGE_RISING;
+		break;
+
+	case IRQ_TYPE_EDGE_FALLING:
+		irq_type = OWL_GPIO_INT_EDGE_FALLING;
+		break;
+
+	case IRQ_TYPE_LEVEL_HIGH:
+		irq_type = OWL_GPIO_INT_LEVEL_HIGH;
+		break;
+
+	case IRQ_TYPE_LEVEL_LOW:
+		irq_type = OWL_GPIO_INT_LEVEL_LOW;
+		break;
+
+	default:
+		break;
+	}
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	offset = (gpio < 16) ? 4 : 0;
+	value = readl_relaxed(gpio_base + port->intc_type + offset);
+	value &= ~(OWL_GPIO_INT_MASK << ((gpio % 16) * 2));
+	value |= irq_type << ((gpio % 16) * 2);
+	writel_relaxed(value, gpio_base + port->intc_type + offset);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_mask(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+	u32 val;
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	owl_gpio_update_reg(gpio_base + port->intc_msk, gpio, false);
+
+	/* disable port interrupt if no interrupt pending bit is active */
+	val = readl_relaxed(gpio_base + port->intc_msk);
+	if (val == 0)
+		owl_gpio_update_reg(gpio_base + port->intc_ctl,
+					OWL_GPIO_CTLR_ENABLE, false);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_unmask(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+	u32 value;
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	/* enable port interrupt */
+	value = readl_relaxed(gpio_base + port->intc_ctl);
+	value |= BIT(OWL_GPIO_CTLR_ENABLE) | BIT(OWL_GPIO_CTLR_SAMPLE_CLK_24M);
+	writel_relaxed(value, gpio_base + port->intc_ctl);
+
+	/* enable GPIO interrupt */
+	owl_gpio_update_reg(gpio_base + port->intc_msk, gpio, true);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static void owl_gpio_irq_ack(struct irq_data *data)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+	const struct owl_gpio_port *port;
+	void __iomem *gpio_base;
+	unsigned long flags;
+	unsigned int gpio = data->hwirq;
+
+	/*
+	 * Switch the interrupt edge to the opposite edge of the interrupt
+	 * which got triggered for the case of emulating both edges
+	 */
+	if (irqd_get_trigger_type(data) == IRQ_TYPE_EDGE_BOTH) {
+		if (owl_gpio_get(gc, gpio))
+			irq_set_type(pctrl, gpio, IRQ_TYPE_EDGE_FALLING);
+		else
+			irq_set_type(pctrl, gpio, IRQ_TYPE_EDGE_RISING);
+	}
+
+	port = owl_gpio_get_port(pctrl, &gpio);
+	if (WARN_ON(port == NULL))
+		return;
+
+	gpio_base = pctrl->base + port->offset;
+
+	raw_spin_lock_irqsave(&pctrl->lock, flags);
+
+	owl_gpio_update_reg(gpio_base + port->intc_ctl,
+				OWL_GPIO_CTLR_PENDING, true);
+
+	raw_spin_unlock_irqrestore(&pctrl->lock, flags);
+}
+
+static int owl_gpio_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(data);
+	struct owl_pinctrl *pctrl = gpiochip_get_data(gc);
+
+	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
+		irq_set_handler_locked(data, handle_level_irq);
+	else
+		irq_set_handler_locked(data, handle_edge_irq);
+
+	irq_set_type(pctrl, data->hwirq, type);
+
+	return 0;
+}
+
+static void owl_gpio_irq_handler(struct irq_desc *desc)
+{
+	struct owl_pinctrl *pctrl = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct irq_domain *domain = pctrl->chip.irq.domain;
+	unsigned int parent = irq_desc_get_irq(desc);
+	const struct owl_gpio_port *port;
+	void __iomem *base;
+	unsigned int pin, irq, offset = 0, i;
+	unsigned long pending_irq;
+
+	chained_irq_enter(chip, desc);
+
+	for (i = 0; i < pctrl->soc->nports; i++) {
+		port = &pctrl->soc->ports[i];
+		base = pctrl->base + port->offset;
+
+		/* skip ports that are not associated with this irq */
+		if (parent != pctrl->irq[i])
+			goto skip;
+
+		pending_irq = readl_relaxed(base + port->intc_pd);
+
+		for_each_set_bit(pin, &pending_irq, port->pins) {
+			irq = irq_find_mapping(domain, offset + pin);
+			generic_handle_irq(irq);
+
+			/* clear pending interrupt */
+			owl_gpio_update_reg(base + port->intc_pd, pin, true);
+		}
+
+skip:
+		offset += port->pins;
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
 static int owl_gpio_init(struct owl_pinctrl *pctrl)
 {
 	struct gpio_chip *chip;
-	int ret;
+	struct gpio_irq_chip *gpio_irq;
+	int ret, i, j, offset;
 
 	chip = &pctrl->chip;
 	chip->base = -1;
@@ -714,6 +921,35 @@ static int owl_gpio_init(struct owl_pinctrl *pctrl)
 	chip->owner = THIS_MODULE;
 	chip->of_node = pctrl->dev->of_node;
 
+	pctrl->irq_chip.name = chip->of_node->name;
+	pctrl->irq_chip.irq_ack = owl_gpio_irq_ack;
+	pctrl->irq_chip.irq_mask = owl_gpio_irq_mask;
+	pctrl->irq_chip.irq_unmask = owl_gpio_irq_unmask;
+	pctrl->irq_chip.irq_set_type = owl_gpio_irq_set_type;
+
+	gpio_irq = &chip->irq;
+	gpio_irq->chip = &pctrl->irq_chip;
+	gpio_irq->handler = handle_simple_irq;
+	gpio_irq->default_type = IRQ_TYPE_NONE;
+	gpio_irq->parent_handler = owl_gpio_irq_handler;
+	gpio_irq->parent_handler_data = pctrl;
+	gpio_irq->num_parents = pctrl->num_irq;
+	gpio_irq->parents = pctrl->irq;
+
+	gpio_irq->map = devm_kcalloc(pctrl->dev, chip->ngpio,
+				sizeof(*gpio_irq->map), GFP_KERNEL);
+	if (!gpio_irq->map)
+		return -ENOMEM;
+
+	for (i = 0, offset = 0; i < pctrl->soc->nports; i++) {
+		const struct owl_gpio_port *port = &pctrl->soc->ports[i];
+
+		for (j = 0; j < port->pins; j++)
+			gpio_irq->map[offset + j] = gpio_irq->parents[i];
+
+		offset += port->pins;
+	}
+
 	ret = gpiochip_add_data(&pctrl->chip, pctrl);
 	if (ret) {
 		dev_err(pctrl->dev, "failed to register gpiochip\n");
@@ -728,7 +964,7 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 {
 	struct resource *res;
 	struct owl_pinctrl *pctrl;
-	int ret;
+	int ret, i;
 
 	pctrl = devm_kzalloc(&pdev->dev, sizeof(*pctrl), GFP_KERNEL);
 	if (!pctrl)
@@ -772,14 +1008,41 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 					&owl_pinctrl_desc, pctrl);
 	if (IS_ERR(pctrl->pctrldev)) {
 		dev_err(&pdev->dev, "could not register Actions OWL pinmux driver\n");
-		return PTR_ERR(pctrl->pctrldev);
+		ret = PTR_ERR(pctrl->pctrldev);
+		goto err_exit;
+	}
+
+	ret = platform_irq_count(pdev);
+	if (ret < 0)
+		goto err_exit;
+
+	pctrl->num_irq = ret;
+
+	pctrl->irq = devm_kcalloc(&pdev->dev, pctrl->num_irq,
+					sizeof(*pctrl->irq), GFP_KERNEL);
+	if (!pctrl->irq) {
+		ret = -ENOMEM;
+		goto err_exit;
+	}
+
+	for (i = 0; i < pctrl->num_irq ; i++) {
+		pctrl->irq[i] = platform_get_irq(pdev, i);
+		if (pctrl->irq[i] < 0) {
+			ret = pctrl->irq[i];
+			goto err_exit;
+		}
 	}
 
 	ret = owl_gpio_init(pctrl);
 	if (ret)
-		return ret;
+		goto err_exit;
 
 	platform_set_drvdata(pdev, pctrl);
 
 	return 0;
+
+err_exit:
+	clk_disable_unprepare(pctrl->clk);
+
+	return ret;
 }
diff --git a/drivers/pinctrl/actions/pinctrl-owl.h b/drivers/pinctrl/actions/pinctrl-owl.h
index 74342378937c..a724d1d406d4 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.h
+++ b/drivers/pinctrl/actions/pinctrl-owl.h
@@ -29,6 +29,18 @@ enum owl_pinconf_drv {
 	OWL_PINCONF_DRV_12MA,
 };
 
+/* GPIO CTRL Bit Definition */
+#define OWL_GPIO_CTLR_PENDING		0
+#define OWL_GPIO_CTLR_ENABLE		1
+#define OWL_GPIO_CTLR_SAMPLE_CLK_24M	2
+
+/* GPIO TYPE Bit Definition */
+#define OWL_GPIO_INT_LEVEL_HIGH		0
+#define OWL_GPIO_INT_LEVEL_LOW		1
+#define OWL_GPIO_INT_EDGE_RISING	2
+#define OWL_GPIO_INT_EDGE_FALLING	3
+#define OWL_GPIO_INT_MASK		3
+
 /**
  * struct owl_pullctl - Actions pad pull control register
  * @reg: offset to the pull control register
@@ -121,6 +133,10 @@ struct owl_pinmux_func {
  * @outen: offset of the output enable register.
  * @inen: offset of the input enable register.
  * @dat: offset of the data register.
+ * @intc_ctl: offset of the interrupt control register.
+ * @intc_pd: offset of the interrupt pending register.
+ * @intc_msk: offset of the interrupt mask register.
+ * @intc_type: offset of the interrupt type register.
  */
 struct owl_gpio_port {
 	unsigned int offset;
@@ -128,6 +144,10 @@ struct owl_gpio_port {
 	unsigned int outen;
 	unsigned int inen;
 	unsigned int dat;
+	unsigned int intc_ctl;
+	unsigned int intc_pd;
+	unsigned int intc_msk;
+	unsigned int intc_type;
 };
 
 /**
@@ -140,7 +160,7 @@ struct owl_gpio_port {
  * @ngroups: number of entries in @groups.
  * @padinfo: array describing the pad info of this SoC.
  * @ngpios: number of pingroups the driver should expose as GPIOs.
- * @port: array describing all GPIO ports of this SoC.
+ * @ports: array describing all GPIO ports of this SoC.
  * @nports: number of GPIO ports in this SoC.
  */
 struct owl_pinctrl_soc_data {
diff --git a/drivers/pinctrl/actions/pinctrl-s900.c b/drivers/pinctrl/actions/pinctrl-s900.c
index 5503c7945764..ea67b14ef93b 100644
--- a/drivers/pinctrl/actions/pinctrl-s900.c
+++ b/drivers/pinctrl/actions/pinctrl-s900.c
@@ -1821,22 +1821,27 @@ static struct owl_padinfo s900_padinfo[NUM_PADS] = {
 	[SGPIO3] = PAD_INFO_PULLCTL_ST(SGPIO3)
 };
 
-#define OWL_GPIO_PORT(port, base, count, _outen, _inen, _dat)	\
-	[OWL_GPIO_PORT_##port] = {				\
-		.offset = base,					\
-		.pins = count,					\
-		.outen = _outen,				\
-		.inen = _inen,					\
-		.dat = _dat,					\
+#define OWL_GPIO_PORT(port, base, count, _outen, _inen, _dat,		\
+			_intc_ctl, _intc_pd, _intc_msk, _intc_type)	\
+	[OWL_GPIO_PORT_##port] = {					\
+		.offset = base,						\
+		.pins = count,						\
+		.outen = _outen,					\
+		.inen = _inen,						\
+		.dat = _dat,						\
+		.intc_ctl = _intc_ctl,					\
+		.intc_pd = _intc_pd,					\
+		.intc_msk = _intc_msk,					\
+		.intc_type = _intc_type,				\
 	}
 
 static const struct owl_gpio_port s900_gpio_ports[] = {
-	OWL_GPIO_PORT(A, 0x0000, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(B, 0x000C, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(C, 0x0018, 12, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(D, 0x0024, 30, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(E, 0x0030, 32, 0x0, 0x4, 0x8),
-	OWL_GPIO_PORT(F, 0x00F0, 8, 0x0, 0x4, 0x8)
+	OWL_GPIO_PORT(A, 0x0000, 32, 0x0, 0x4, 0x8, 0x204, 0x208, 0x20C, 0x240),
+	OWL_GPIO_PORT(B, 0x000C, 32, 0x0, 0x4, 0x8, 0x534, 0x204, 0x208, 0x23C),
+	OWL_GPIO_PORT(C, 0x0018, 12, 0x0, 0x4, 0x8, 0x52C, 0x200, 0x204, 0x238),
+	OWL_GPIO_PORT(D, 0x0024, 30, 0x0, 0x4, 0x8, 0x524, 0x1FC, 0x200, 0x234),
+	OWL_GPIO_PORT(E, 0x0030, 32, 0x0, 0x4, 0x8, 0x51C, 0x1F8, 0x1FC, 0x230),
+	OWL_GPIO_PORT(F, 0x00F0, 8, 0x0, 0x4, 0x8, 0x460, 0x140, 0x144, 0x178)
 };
 
 static struct owl_pinctrl_soc_data s900_pinctrl_data = {
-- 
cgit v1.2.3


From f11c5db770ab675d270cb4d5a2bb90923066ef49 Mon Sep 17 00:00:00 2001
From: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
Date: Fri, 29 Jun 2018 20:29:44 +0800
Subject: ASoC: mediatek: sub dai use list_head

use list_head for sub_dais,
since original sub_dais array is sparsely occupied

Signed-off-by: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../soc/mediatek/common/mtk-afe-platform-driver.c  | 64 ++++++++--------------
 sound/soc/mediatek/common/mtk-base-afe.h           |  6 +-
 2 files changed, 28 insertions(+), 42 deletions(-)

diff --git a/sound/soc/mediatek/common/mtk-afe-platform-driver.c b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
index 51ec4ff6ed95..697aa50aff9a 100644
--- a/sound/soc/mediatek/common/mtk-afe-platform-driver.c
+++ b/sound/soc/mediatek/common/mtk-afe-platform-driver.c
@@ -15,20 +15,12 @@
 
 int mtk_afe_combine_sub_dai(struct mtk_base_afe *afe)
 {
-	struct snd_soc_dai_driver *sub_dai_drivers;
+	struct mtk_base_afe_dai *dai;
 	size_t num_dai_drivers = 0, dai_idx = 0;
-	int i;
-
-	if (!afe->sub_dais) {
-		dev_err(afe->dev, "%s(), sub_dais == NULL\n", __func__);
-		return -EINVAL;
-	}
 
 	/* calcualte total dai driver size */
-	for (i = 0; i < afe->num_sub_dais; i++) {
-		if (afe->sub_dais[i].dai_drivers &&
-		    afe->sub_dais[i].num_dai_drivers != 0)
-			num_dai_drivers += afe->sub_dais[i].num_dai_drivers;
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		num_dai_drivers += dai->num_dai_drivers;
 	}
 
 	dev_info(afe->dev, "%s(), num of dai %zd\n", __func__, num_dai_drivers);
@@ -42,19 +34,14 @@ int mtk_afe_combine_sub_dai(struct mtk_base_afe *afe)
 	if (!afe->dai_drivers)
 		return -ENOMEM;
 
-	for (i = 0; i < afe->num_sub_dais; i++) {
-		if (afe->sub_dais[i].dai_drivers &&
-		    afe->sub_dais[i].num_dai_drivers != 0) {
-			sub_dai_drivers = afe->sub_dais[i].dai_drivers;
-			/* dai driver */
-			memcpy(&afe->dai_drivers[dai_idx],
-			       sub_dai_drivers,
-			       afe->sub_dais[i].num_dai_drivers *
-			       sizeof(struct snd_soc_dai_driver));
-			dai_idx += afe->sub_dais[i].num_dai_drivers;
-		}
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		/* dai driver */
+		memcpy(&afe->dai_drivers[dai_idx],
+		       dai->dai_drivers,
+		       dai->num_dai_drivers *
+		       sizeof(struct snd_soc_dai_driver));
+		dai_idx += dai->num_dai_drivers;
 	}
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mtk_afe_combine_sub_dai);
@@ -62,28 +49,25 @@ EXPORT_SYMBOL_GPL(mtk_afe_combine_sub_dai);
 int mtk_afe_add_sub_dai_control(struct snd_soc_component *component)
 {
 	struct mtk_base_afe *afe = snd_soc_component_get_drvdata(component);
-	int i;
+	struct mtk_base_afe_dai *dai;
 
-	if (!afe->sub_dais) {
-		dev_err(afe->dev, "%s(), sub_dais == NULL\n", __func__);
-		return -EINVAL;
-	}
-
-	for (i = 0; i < afe->num_sub_dais; i++) {
-		if (afe->sub_dais[i].controls)
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		if (dai->controls)
 			snd_soc_add_component_controls(component,
-				afe->sub_dais[i].controls,
-				afe->sub_dais[i].num_controls);
+						       dai->controls,
+						       dai->num_controls);
 
-		if (afe->sub_dais[i].dapm_widgets)
+		if (dai->dapm_widgets)
 			snd_soc_dapm_new_controls(&component->dapm,
-				afe->sub_dais[i].dapm_widgets,
-				afe->sub_dais[i].num_dapm_widgets);
-
-		if (afe->sub_dais[i].dapm_routes)
+						  dai->dapm_widgets,
+						  dai->num_dapm_widgets);
+	}
+	/* add routes after all widgets are added */
+	list_for_each_entry(dai, &afe->sub_dais, list) {
+		if (dai->dapm_routes)
 			snd_soc_dapm_add_routes(&component->dapm,
-				afe->sub_dais[i].dapm_routes,
-				afe->sub_dais[i].num_dapm_routes);
+						dai->dapm_routes,
+						dai->num_dapm_routes);
 	}
 
 	snd_soc_dapm_new_widgets(component->dapm.card);
diff --git a/sound/soc/mediatek/common/mtk-base-afe.h b/sound/soc/mediatek/common/mtk-base-afe.h
index bcf562f029b6..bd8d5e0c6843 100644
--- a/sound/soc/mediatek/common/mtk-base-afe.h
+++ b/sound/soc/mediatek/common/mtk-base-afe.h
@@ -46,6 +46,7 @@ struct mtk_base_irq_data {
 };
 
 struct device;
+struct list_head;
 struct mtk_base_afe_memif;
 struct mtk_base_afe_irq;
 struct mtk_base_afe_dai;
@@ -72,8 +73,7 @@ struct mtk_base_afe {
 	struct mtk_base_afe_irq *irqs;
 	int irqs_size;
 
-	struct mtk_base_afe_dai *sub_dais;
-	int num_sub_dais;
+	struct list_head sub_dais;
 	struct snd_soc_dai_driver *dai_drivers;
 	unsigned int num_dai_drivers;
 
@@ -110,6 +110,8 @@ struct mtk_base_afe_dai {
 	unsigned int num_dapm_widgets;
 	const struct snd_soc_dapm_route *dapm_routes;
 	unsigned int num_dapm_routes;
+
+	struct list_head list;
 };
 
 #endif
-- 
cgit v1.2.3


From c1d9b4196ba6b311bd48a9320cd46aa125e0b034 Mon Sep 17 00:00:00 2001
From: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
Date: Fri, 29 Jun 2018 20:29:45 +0800
Subject: ASoC: mt6797: sub dai use list_head

Signed-off-by: KaiChieh Chuang <kaichieh.chuang@mediatek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/mediatek/mt6797/mt6797-afe-common.h   |  1 +
 sound/soc/mediatek/mt6797/mt6797-afe-pcm.c      | 65 +++++++++++++++++--------
 sound/soc/mediatek/mt6797/mt6797-dai-adda.c     | 20 +++++---
 sound/soc/mediatek/mt6797/mt6797-dai-hostless.c | 16 ++++--
 sound/soc/mediatek/mt6797/mt6797-dai-pcm.c      | 19 +++++---
 5 files changed, 81 insertions(+), 40 deletions(-)

diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-common.h b/sound/soc/mediatek/mt6797/mt6797-afe-common.h
index 22eb7b455cf1..4eac9977b2b0 100644
--- a/sound/soc/mediatek/mt6797/mt6797-afe-common.h
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-common.h
@@ -10,6 +10,7 @@
 #define _MT_6797_AFE_COMMON_H_
 
 #include <sound/soc.h>
+#include <linux/list.h>
 #include <linux/regmap.h>
 #include "../common/mtk-base-afe.h"
 
diff --git a/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
index 6c5dd9fc9976..192f4d7b37b6 100644
--- a/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
+++ b/sound/soc/mediatek/mt6797/mt6797-afe-pcm.c
@@ -733,6 +733,34 @@ static const struct snd_soc_component_driver mt6797_afe_component = {
 	.probe = mt6797_afe_component_probe,
 };
 
+static int mt6797_dai_memif_register(struct mtk_base_afe *afe)
+{
+	struct mtk_base_afe_dai *dai;
+
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
+
+	list_add(&dai->list, &afe->sub_dais);
+
+	dai->dai_drivers = mt6797_memif_dai_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mt6797_memif_dai_driver);
+
+	dai->dapm_widgets = mt6797_memif_widgets;
+	dai->num_dapm_widgets = ARRAY_SIZE(mt6797_memif_widgets);
+	dai->dapm_routes = mt6797_memif_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mt6797_memif_routes);
+	return 0;
+}
+
+typedef int (*dai_register_cb)(struct mtk_base_afe *);
+static const dai_register_cb dai_register_cbs[] = {
+	mt6797_dai_adda_register,
+	mt6797_dai_pcm_register,
+	mt6797_dai_hostless_register,
+	mt6797_dai_memif_register,
+};
+
 static int mt6797_afe_pcm_dev_probe(struct platform_device *pdev)
 {
 	struct mtk_base_afe *afe;
@@ -811,29 +839,24 @@ static int mt6797_afe_pcm_dev_probe(struct platform_device *pdev)
 	}
 
 	/* init sub_dais */
-	afe->num_sub_dais = MT6797_DAI_NUM;
-	afe->sub_dais = devm_kcalloc(dev, afe->num_sub_dais,
-				     sizeof(*afe->sub_dais),
-				     GFP_KERNEL);
-	if (!afe->sub_dais)
-		return -ENOMEM;
-
-	mt6797_dai_adda_register(afe);
-	mt6797_dai_pcm_register(afe);
-	mt6797_dai_hostless_register(afe);
-
-	afe->sub_dais[MT6797_MEMIF_DL1].dai_drivers = mt6797_memif_dai_driver;
-	afe->sub_dais[MT6797_MEMIF_DL1].num_dai_drivers =
-		ARRAY_SIZE(mt6797_memif_dai_driver);
-	afe->sub_dais[MT6797_MEMIF_DL1].dapm_widgets = mt6797_memif_widgets;
-	afe->sub_dais[MT6797_MEMIF_DL1].num_dapm_widgets =
-		ARRAY_SIZE(mt6797_memif_widgets);
-	afe->sub_dais[MT6797_MEMIF_DL1].dapm_routes = mt6797_memif_routes;
-	afe->sub_dais[MT6797_MEMIF_DL1].num_dapm_routes =
-		ARRAY_SIZE(mt6797_memif_routes);
+	INIT_LIST_HEAD(&afe->sub_dais);
+
+	for (i = 0; i < ARRAY_SIZE(dai_register_cbs); i++) {
+		ret = dai_register_cbs[i](afe);
+		if (ret) {
+			dev_warn(afe->dev, "dai register i %d fail, ret %d\n",
+				 i, ret);
+			return ret;
+		}
+	}
 
 	/* init dai_driver and component_driver */
-	mtk_afe_combine_sub_dai(afe);
+	ret = mtk_afe_combine_sub_dai(afe);
+	if (ret) {
+		dev_warn(afe->dev, "mtk_afe_combine_sub_dai fail, ret %d\n",
+			 ret);
+		return ret;
+	}
 
 	afe->mtk_afe_hardware = &mt6797_afe_hardware;
 	afe->memif_fs = mt6797_memif_fs;
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-adda.c b/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
index ad083265ce94..0ac6409c6d61 100644
--- a/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-adda.c
@@ -383,14 +383,20 @@ static struct snd_soc_dai_driver mtk_dai_adda_driver[] = {
 
 int mt6797_dai_adda_register(struct mtk_base_afe *afe)
 {
-	int id = MT6797_DAI_ADDA;
+	struct mtk_base_afe_dai *dai;
 
-	afe->sub_dais[id].dai_drivers = mtk_dai_adda_driver;
-	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_adda_driver);
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
 
-	afe->sub_dais[id].dapm_widgets = mtk_dai_adda_widgets;
-	afe->sub_dais[id].num_dapm_widgets = ARRAY_SIZE(mtk_dai_adda_widgets);
-	afe->sub_dais[id].dapm_routes = mtk_dai_adda_routes;
-	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_adda_routes);
+	list_add(&dai->list, &afe->sub_dais);
+
+	dai->dai_drivers = mtk_dai_adda_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mtk_dai_adda_driver);
+
+	dai->dapm_widgets = mtk_dai_adda_widgets;
+	dai->num_dapm_widgets = ARRAY_SIZE(mtk_dai_adda_widgets);
+	dai->dapm_routes = mtk_dai_adda_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mtk_dai_adda_routes);
 	return 0;
 }
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c b/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
index 4cf985b15a11..ed23e6a53b08 100644
--- a/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-hostless.c
@@ -100,13 +100,19 @@ static struct snd_soc_dai_driver mtk_dai_hostless_driver[] = {
 
 int mt6797_dai_hostless_register(struct mtk_base_afe *afe)
 {
-	int id = MT6797_DAI_HOSTLESS_LPBK;
+	struct mtk_base_afe_dai *dai;
 
-	afe->sub_dais[id].dai_drivers = mtk_dai_hostless_driver;
-	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_hostless_driver);
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
 
-	afe->sub_dais[id].dapm_routes = mtk_dai_hostless_routes;
-	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_hostless_routes);
+	list_add(&dai->list, &afe->sub_dais);
+
+	dai->dai_drivers = mtk_dai_hostless_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mtk_dai_hostless_driver);
+
+	dai->dapm_routes = mtk_dai_hostless_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mtk_dai_hostless_routes);
 
 	return 0;
 }
diff --git a/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c b/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
index 16d5b5067204..3136f0bc7827 100644
--- a/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
+++ b/sound/soc/mediatek/mt6797/mt6797-dai-pcm.c
@@ -298,15 +298,20 @@ static struct snd_soc_dai_driver mtk_dai_pcm_driver[] = {
 
 int mt6797_dai_pcm_register(struct mtk_base_afe *afe)
 {
-	int id = MT6797_DAI_PCM_1;
+	struct mtk_base_afe_dai *dai;
 
-	afe->sub_dais[id].dai_drivers = mtk_dai_pcm_driver;
-	afe->sub_dais[id].num_dai_drivers = ARRAY_SIZE(mtk_dai_pcm_driver);
+	dai = devm_kzalloc(afe->dev, sizeof(*dai), GFP_KERNEL);
+	if (!dai)
+		return -ENOMEM;
 
-	afe->sub_dais[id].dapm_widgets = mtk_dai_pcm_widgets;
-	afe->sub_dais[id].num_dapm_widgets = ARRAY_SIZE(mtk_dai_pcm_widgets);
-	afe->sub_dais[id].dapm_routes = mtk_dai_pcm_routes;
-	afe->sub_dais[id].num_dapm_routes = ARRAY_SIZE(mtk_dai_pcm_routes);
+	list_add(&dai->list, &afe->sub_dais);
 
+	dai->dai_drivers = mtk_dai_pcm_driver;
+	dai->num_dai_drivers = ARRAY_SIZE(mtk_dai_pcm_driver);
+
+	dai->dapm_widgets = mtk_dai_pcm_widgets;
+	dai->num_dapm_widgets = ARRAY_SIZE(mtk_dai_pcm_widgets);
+	dai->dapm_routes = mtk_dai_pcm_routes;
+	dai->num_dapm_routes = ARRAY_SIZE(mtk_dai_pcm_routes);
 	return 0;
 }
-- 
cgit v1.2.3


From 6a230edd5d6e02655ad3a7ac718f521e96b9830c Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Tue, 26 Jun 2018 16:06:13 +0200
Subject: pinctrl: armada-37xx: add suspend/resume support

Add suspend/resume hooks in pinctrl driver to handle S2RAM operations.

Beyond the traditional register save/restore operations, these hooks
also keep the GPIOs used for both-edge IRQ synchronized between their
level (low/high) and expected IRQ polarity (falling/rising edge).

Since pinctrl is an infrastructure module, its resume should be issued
prior to other IO drivers. The pinctrl PM operations are requested at
early/late stages for this reason.

Suggested-by: Ken Ma <make@marvell.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mvebu/pinctrl-armada-37xx.c | 118 ++++++++++++++++++++++++++++
 1 file changed, 118 insertions(+)

diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index 53cf800688e9..aa48b3f23c7f 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -80,6 +80,18 @@ struct armada_37xx_pmx_func {
 	unsigned int		ngroups;
 };
 
+struct armada_37xx_pm_state {
+	u32 out_en_l;
+	u32 out_en_h;
+	u32 out_val_l;
+	u32 out_val_h;
+	u32 irq_en_l;
+	u32 irq_en_h;
+	u32 irq_pol_l;
+	u32 irq_pol_h;
+	u32 selection;
+};
+
 struct armada_37xx_pinctrl {
 	struct regmap			*regmap;
 	void __iomem			*base;
@@ -94,6 +106,7 @@ struct armada_37xx_pinctrl {
 	unsigned int			ngroups;
 	struct armada_37xx_pmx_func	*funcs;
 	unsigned int			nfuncs;
+	struct armada_37xx_pm_state	pm;
 };
 
 #define PIN_GRP(_name, _start, _nr, _mask, _func1, _func2)	\
@@ -996,6 +1009,110 @@ static int armada_37xx_pinctrl_register(struct platform_device *pdev,
 	return 0;
 }
 
+#if defined(CONFIG_PM)
+static int armada_3700_pinctrl_suspend(struct device *dev)
+{
+	struct armada_37xx_pinctrl *info = dev_get_drvdata(dev);
+
+	/* Save GPIO state */
+	regmap_read(info->regmap, OUTPUT_EN, &info->pm.out_en_l);
+	regmap_read(info->regmap, OUTPUT_EN + sizeof(u32), &info->pm.out_en_h);
+	regmap_read(info->regmap, OUTPUT_VAL, &info->pm.out_val_l);
+	regmap_read(info->regmap, OUTPUT_VAL + sizeof(u32),
+		    &info->pm.out_val_h);
+
+	info->pm.irq_en_l = readl(info->base + IRQ_EN);
+	info->pm.irq_en_h = readl(info->base + IRQ_EN + sizeof(u32));
+	info->pm.irq_pol_l = readl(info->base + IRQ_POL);
+	info->pm.irq_pol_h = readl(info->base + IRQ_POL + sizeof(u32));
+
+	/* Save pinctrl state */
+	regmap_read(info->regmap, SELECTION, &info->pm.selection);
+
+	return 0;
+}
+
+static int armada_3700_pinctrl_resume(struct device *dev)
+{
+	struct armada_37xx_pinctrl *info = dev_get_drvdata(dev);
+	struct gpio_chip *gc;
+	struct irq_domain *d;
+	int i;
+
+	/* Restore GPIO state */
+	regmap_write(info->regmap, OUTPUT_EN, info->pm.out_en_l);
+	regmap_write(info->regmap, OUTPUT_EN + sizeof(u32),
+		     info->pm.out_en_h);
+	regmap_write(info->regmap, OUTPUT_VAL, info->pm.out_val_l);
+	regmap_write(info->regmap, OUTPUT_VAL + sizeof(u32),
+		     info->pm.out_val_h);
+
+	/*
+	 * Input levels may change during suspend, which is not monitored at
+	 * that time. GPIOs used for both-edge IRQs may not be synchronized
+	 * anymore with their polarities (rising/falling edge) and must be
+	 * re-configured manually.
+	 */
+	gc = &info->gpio_chip;
+	d = gc->irq.domain;
+	for (i = 0; i < gc->ngpio; i++) {
+		u32 irq_bit = BIT(i % GPIO_PER_REG);
+		u32 mask, *irq_pol, input_reg, virq, type, level;
+
+		if (i < GPIO_PER_REG) {
+			mask = info->pm.irq_en_l;
+			irq_pol = &info->pm.irq_pol_l;
+			input_reg = INPUT_VAL;
+		} else {
+			mask = info->pm.irq_en_h;
+			irq_pol = &info->pm.irq_pol_h;
+			input_reg = INPUT_VAL + sizeof(u32);
+		}
+
+		if (!(mask & irq_bit))
+			continue;
+
+		virq = irq_find_mapping(d, i);
+		type = irq_get_trigger_type(virq);
+
+		/*
+		 * Synchronize level and polarity for both-edge irqs:
+		 *     - a high input level expects a falling edge,
+		 *     - a low input level exepects a rising edge.
+		 */
+		if ((type & IRQ_TYPE_SENSE_MASK) ==
+		    IRQ_TYPE_EDGE_BOTH) {
+			regmap_read(info->regmap, input_reg, &level);
+			if ((*irq_pol ^ level) & irq_bit)
+				*irq_pol ^= irq_bit;
+		}
+	}
+
+	writel(info->pm.irq_en_l, info->base + IRQ_EN);
+	writel(info->pm.irq_en_h, info->base + IRQ_EN + sizeof(u32));
+	writel(info->pm.irq_pol_l, info->base + IRQ_POL);
+	writel(info->pm.irq_pol_h, info->base + IRQ_POL + sizeof(u32));
+
+	/* Restore pinctrl state */
+	regmap_write(info->regmap, SELECTION, info->pm.selection);
+
+	return 0;
+}
+
+/*
+ * Since pinctrl is an infrastructure module, its resume should be issued prior
+ * to other IO drivers.
+ */
+static const struct dev_pm_ops armada_3700_pinctrl_pm_ops = {
+	.suspend_late = armada_3700_pinctrl_suspend,
+	.resume_early = armada_3700_pinctrl_resume,
+};
+
+#define PINCTRL_ARMADA_37XX_DEV_PM_OPS (&armada_3700_pinctrl_pm_ops)
+#else
+#define PINCTRL_ARMADA_37XX_DEV_PM_OPS NULL
+#endif /* CONFIG_PM */
+
 static const struct of_device_id armada_37xx_pinctrl_of_match[] = {
 	{
 		.compatible = "marvell,armada3710-sb-pinctrl",
@@ -1049,6 +1166,7 @@ static struct platform_driver armada_37xx_pinctrl_driver = {
 	.driver = {
 		.name = "armada-37xx-pinctrl",
 		.of_match_table = armada_37xx_pinctrl_of_match,
+		.pm = PINCTRL_ARMADA_37XX_DEV_PM_OPS,
 	},
 };
 
-- 
cgit v1.2.3


From e6800d2601fafb51f5feb3c216c884c2efb4c77d Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 27 Jun 2018 15:05:53 +0300
Subject: pinctrl: intel: Add Ice Lake PCH pin controller support

This adds pinctrl/GPIO support for Intel Ice Lake PCH. The Ice Lake PCH
GPIO is based on the same version of the Intel GPIO hardware than Intel
Cannon Lake with different set of pins and ACPI ID.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/Kconfig           |   8 +
 drivers/pinctrl/intel/Makefile          |   1 +
 drivers/pinctrl/intel/pinctrl-icelake.c | 436 ++++++++++++++++++++++++++++++++
 3 files changed, 445 insertions(+)
 create mode 100644 drivers/pinctrl/intel/pinctrl-icelake.c

diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index 4aea1b8504f7..490497896581 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -90,6 +90,14 @@ config PINCTRL_GEMINILAKE
 	  This pinctrl driver provides an interface that allows configuring
 	  of Intel Gemini Lake SoC pins and using them as GPIOs.
 
+config PINCTRL_ICELAKE
+	tristate "Intel Ice Lake PCH pinctrl and GPIO driver"
+	depends on ACPI
+	select PINCTRL_INTEL
+	help
+	  This pinctrl driver provides an interface that allows configuring
+	  of Intel Ice Lake PCH pins and using them as GPIOs.
+
 config PINCTRL_LEWISBURG
 	tristate "Intel Lewisburg pinctrl and GPIO driver"
 	depends on ACPI
diff --git a/drivers/pinctrl/intel/Makefile b/drivers/pinctrl/intel/Makefile
index fadfe3ea2b04..cb491e655749 100644
--- a/drivers/pinctrl/intel/Makefile
+++ b/drivers/pinctrl/intel/Makefile
@@ -10,5 +10,6 @@ obj-$(CONFIG_PINCTRL_CANNONLAKE)	+= pinctrl-cannonlake.o
 obj-$(CONFIG_PINCTRL_CEDARFORK)		+= pinctrl-cedarfork.o
 obj-$(CONFIG_PINCTRL_DENVERTON)		+= pinctrl-denverton.o
 obj-$(CONFIG_PINCTRL_GEMINILAKE)	+= pinctrl-geminilake.o
+obj-$(CONFIG_PINCTRL_ICELAKE)		+= pinctrl-icelake.o
 obj-$(CONFIG_PINCTRL_LEWISBURG)		+= pinctrl-lewisburg.o
 obj-$(CONFIG_PINCTRL_SUNRISEPOINT)	+= pinctrl-sunrisepoint.o
diff --git a/drivers/pinctrl/intel/pinctrl-icelake.c b/drivers/pinctrl/intel/pinctrl-icelake.c
new file mode 100644
index 000000000000..630b966ce081
--- /dev/null
+++ b/drivers/pinctrl/intel/pinctrl-icelake.c
@@ -0,0 +1,436 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Ice Lake PCH pinctrl/GPIO driver
+ *
+ * Copyright (C) 2018, Intel Corporation
+ * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
+ *	    Mika Westerberg <mika.westerberg@linux.intel.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-intel.h"
+
+#define ICL_PAD_OWN	0x020
+#define ICL_PADCFGLOCK	0x080
+#define ICL_HOSTSW_OWN	0x0b0
+#define ICL_GPI_IE	0x110
+
+#define ICL_GPP(r, s, e, g)				\
+	{						\
+		.reg_num = (r),				\
+		.base = (s),				\
+		.size = ((e) - (s) + 1),		\
+		.gpio_base = (g),			\
+	}
+
+#define ICL_NO_GPIO	-1
+
+#define ICL_COMMUNITY(b, s, e, g)			\
+	{						\
+		.barno = (b),				\
+		.padown_offset = ICL_PAD_OWN,		\
+		.padcfglock_offset = ICL_PADCFGLOCK,	\
+		.hostown_offset = ICL_HOSTSW_OWN,	\
+		.ie_offset = ICL_GPI_IE,		\
+		.pin_base = (s),			\
+		.npins = ((e) - (s) + 1),		\
+		.gpps = (g),				\
+		.ngpps = ARRAY_SIZE(g),			\
+	}
+
+/* Ice Lake-LP */
+static const struct pinctrl_pin_desc icllp_pins[] = {
+	/* GPP_G */
+	PINCTRL_PIN(0, "SD3_CMD"),
+	PINCTRL_PIN(1, "SD3_D0"),
+	PINCTRL_PIN(2, "SD3_D1"),
+	PINCTRL_PIN(3, "SD3_D2"),
+	PINCTRL_PIN(4, "SD3_D3"),
+	PINCTRL_PIN(5, "SD3_CDB"),
+	PINCTRL_PIN(6, "SD3_CLK"),
+	PINCTRL_PIN(7, "SD3_WP"),
+	/* GPP_B */
+	PINCTRL_PIN(8, "CORE_VID_0"),
+	PINCTRL_PIN(9, "CORE_VID_1"),
+	PINCTRL_PIN(10, "VRALERTB"),
+	PINCTRL_PIN(11, "CPU_GP_2"),
+	PINCTRL_PIN(12, "CPU_GP_3"),
+	PINCTRL_PIN(13, "ISH_I2C0_SDA"),
+	PINCTRL_PIN(14, "ISH_I2C0_SCL"),
+	PINCTRL_PIN(15, "ISH_I2C1_SDA"),
+	PINCTRL_PIN(16, "ISH_I2C1_SCL"),
+	PINCTRL_PIN(17, "I2C5_SDA"),
+	PINCTRL_PIN(18, "I2C5_SCL"),
+	PINCTRL_PIN(19, "PMCALERTB"),
+	PINCTRL_PIN(20, "SLP_S0B"),
+	PINCTRL_PIN(21, "PLTRSTB"),
+	PINCTRL_PIN(22, "SPKR"),
+	PINCTRL_PIN(23, "GSPI0_CS0B"),
+	PINCTRL_PIN(24, "GSPI0_CLK"),
+	PINCTRL_PIN(25, "GSPI0_MISO"),
+	PINCTRL_PIN(26, "GSPI0_MOSI"),
+	PINCTRL_PIN(27, "GSPI1_CS0B"),
+	PINCTRL_PIN(28, "GSPI1_CLK"),
+	PINCTRL_PIN(29, "GSPI1_MISO"),
+	PINCTRL_PIN(30, "GSPI1_MOSI"),
+	PINCTRL_PIN(31, "SML1ALERTB"),
+	PINCTRL_PIN(32, "GSPI0_CLK_LOOPBK"),
+	PINCTRL_PIN(33, "GSPI1_CLK_LOOPBK"),
+	/* GPP_A */
+	PINCTRL_PIN(34, "ESPI_IO_0"),
+	PINCTRL_PIN(35, "ESPI_IO_1"),
+	PINCTRL_PIN(36, "ESPI_IO_2"),
+	PINCTRL_PIN(37, "ESPI_IO_3"),
+	PINCTRL_PIN(38, "ESPI_CSB"),
+	PINCTRL_PIN(39, "ESPI_CLK"),
+	PINCTRL_PIN(40, "ESPI_RESETB"),
+	PINCTRL_PIN(41, "I2S2_SCLK"),
+	PINCTRL_PIN(42, "I2S2_SFRM"),
+	PINCTRL_PIN(43, "I2S2_TXD"),
+	PINCTRL_PIN(44, "I2S2_RXD"),
+	PINCTRL_PIN(45, "SATA_DEVSLP_2"),
+	PINCTRL_PIN(46, "SATAXPCIE_1"),
+	PINCTRL_PIN(47, "SATAXPCIE_2"),
+	PINCTRL_PIN(48, "USB2_OCB_1"),
+	PINCTRL_PIN(49, "USB2_OCB_2"),
+	PINCTRL_PIN(50, "USB2_OCB_3"),
+	PINCTRL_PIN(51, "DDSP_HPD_C"),
+	PINCTRL_PIN(52, "DDSP_HPD_B"),
+	PINCTRL_PIN(53, "DDSP_HPD_1"),
+	PINCTRL_PIN(54, "DDSP_HPD_2"),
+	PINCTRL_PIN(55, "I2S5_TXD"),
+	PINCTRL_PIN(56, "I2S5_RXD"),
+	PINCTRL_PIN(57, "I2S1_SCLK"),
+	PINCTRL_PIN(58, "ESPI_CLK_LOOPBK"),
+	/* GPP_H */
+	PINCTRL_PIN(59, "SD_1P8_SEL"),
+	PINCTRL_PIN(60, "SD_PWR_EN_B"),
+	PINCTRL_PIN(61, "GPPC_H_2"),
+	PINCTRL_PIN(62, "SX_EXIT_HOLDOFFB"),
+	PINCTRL_PIN(63, "I2C2_SDA"),
+	PINCTRL_PIN(64, "I2C2_SCL"),
+	PINCTRL_PIN(65, "I2C3_SDA"),
+	PINCTRL_PIN(66, "I2C3_SCL"),
+	PINCTRL_PIN(67, "I2C4_SDA"),
+	PINCTRL_PIN(68, "I2C4_SCL"),
+	PINCTRL_PIN(69, "SRCCLKREQB_4"),
+	PINCTRL_PIN(70, "SRCCLKREQB_5"),
+	PINCTRL_PIN(71, "M2_SKT2_CFG_0"),
+	PINCTRL_PIN(72, "M2_SKT2_CFG_1"),
+	PINCTRL_PIN(73, "M2_SKT2_CFG_2"),
+	PINCTRL_PIN(74, "M2_SKT2_CFG_3"),
+	PINCTRL_PIN(75, "DDPB_CTRLCLK"),
+	PINCTRL_PIN(76, "DDPB_CTRLDATA"),
+	PINCTRL_PIN(77, "CPU_VCCIO_PWR_GATEB"),
+	PINCTRL_PIN(78, "TIME_SYNC_0"),
+	PINCTRL_PIN(79, "IMGCLKOUT_1"),
+	PINCTRL_PIN(80, "IMGCLKOUT_2"),
+	PINCTRL_PIN(81, "IMGCLKOUT_3"),
+	PINCTRL_PIN(82, "IMGCLKOUT_4"),
+	/* GPP_D */
+	PINCTRL_PIN(83, "ISH_GP_0"),
+	PINCTRL_PIN(84, "ISH_GP_1"),
+	PINCTRL_PIN(85, "ISH_GP_2"),
+	PINCTRL_PIN(86, "ISH_GP_3"),
+	PINCTRL_PIN(87, "IMGCLKOUT_0"),
+	PINCTRL_PIN(88, "SRCCLKREQB_0"),
+	PINCTRL_PIN(89, "SRCCLKREQB_1"),
+	PINCTRL_PIN(90, "SRCCLKREQB_2"),
+	PINCTRL_PIN(91, "SRCCLKREQB_3"),
+	PINCTRL_PIN(92, "ISH_SPI_CSB"),
+	PINCTRL_PIN(93, "ISH_SPI_CLK"),
+	PINCTRL_PIN(94, "ISH_SPI_MISO"),
+	PINCTRL_PIN(95, "ISH_SPI_MOSI"),
+	PINCTRL_PIN(96, "ISH_UART0_RXD"),
+	PINCTRL_PIN(97, "ISH_UART0_TXD"),
+	PINCTRL_PIN(98, "ISH_UART0_RTSB"),
+	PINCTRL_PIN(99, "ISH_UART0_CTSB"),
+	PINCTRL_PIN(100, "ISH_GP_4"),
+	PINCTRL_PIN(101, "ISH_GP_5"),
+	PINCTRL_PIN(102, "I2S_MCLK"),
+	PINCTRL_PIN(103, "GSPI2_CLK_LOOPBK"),
+	/* GPP_F */
+	PINCTRL_PIN(104, "CNV_BRI_DT"),
+	PINCTRL_PIN(105, "CNV_BRI_RSP"),
+	PINCTRL_PIN(106, "CNV_RGI_DT"),
+	PINCTRL_PIN(107, "CNV_RGI_RSP"),
+	PINCTRL_PIN(108, "CNV_RF_RESET_B"),
+	PINCTRL_PIN(109, "EMMC_HIP_MON"),
+	PINCTRL_PIN(110, "CNV_PA_BLANKING"),
+	PINCTRL_PIN(111, "EMMC_CMD"),
+	PINCTRL_PIN(112, "EMMC_DATA0"),
+	PINCTRL_PIN(113, "EMMC_DATA1"),
+	PINCTRL_PIN(114, "EMMC_DATA2"),
+	PINCTRL_PIN(115, "EMMC_DATA3"),
+	PINCTRL_PIN(116, "EMMC_DATA4"),
+	PINCTRL_PIN(117, "EMMC_DATA5"),
+	PINCTRL_PIN(118, "EMMC_DATA6"),
+	PINCTRL_PIN(119, "EMMC_DATA7"),
+	PINCTRL_PIN(120, "EMMC_RCLK"),
+	PINCTRL_PIN(121, "EMMC_CLK"),
+	PINCTRL_PIN(122, "EMMC_RESETB"),
+	PINCTRL_PIN(123, "A4WP_PRESENT"),
+	/* vGPIO */
+	PINCTRL_PIN(124, "CNV_BTEN"),
+	PINCTRL_PIN(125, "CNV_WCEN"),
+	PINCTRL_PIN(126, "CNV_BT_HOST_WAKEB"),
+	PINCTRL_PIN(127, "CNV_BT_IF_SELECT"),
+	PINCTRL_PIN(128, "vCNV_BT_UART_TXD"),
+	PINCTRL_PIN(129, "vCNV_BT_UART_RXD"),
+	PINCTRL_PIN(130, "vCNV_BT_UART_CTS_B"),
+	PINCTRL_PIN(131, "vCNV_BT_UART_RTS_B"),
+	PINCTRL_PIN(132, "vCNV_MFUART1_TXD"),
+	PINCTRL_PIN(133, "vCNV_MFUART1_RXD"),
+	PINCTRL_PIN(134, "vCNV_MFUART1_CTS_B"),
+	PINCTRL_PIN(135, "vCNV_MFUART1_RTS_B"),
+	PINCTRL_PIN(136, "vUART0_TXD"),
+	PINCTRL_PIN(137, "vUART0_RXD"),
+	PINCTRL_PIN(138, "vUART0_CTS_B"),
+	PINCTRL_PIN(139, "vUART0_RTS_B"),
+	PINCTRL_PIN(140, "vISH_UART0_TXD"),
+	PINCTRL_PIN(141, "vISH_UART0_RXD"),
+	PINCTRL_PIN(142, "vISH_UART0_CTS_B"),
+	PINCTRL_PIN(143, "vISH_UART0_RTS_B"),
+	PINCTRL_PIN(144, "vCNV_BT_I2S_BCLK"),
+	PINCTRL_PIN(145, "vCNV_BT_I2S_WS_SYNC"),
+	PINCTRL_PIN(146, "vCNV_BT_I2S_SDO"),
+	PINCTRL_PIN(147, "vCNV_BT_I2S_SDI"),
+	PINCTRL_PIN(148, "vI2S2_SCLK"),
+	PINCTRL_PIN(149, "vI2S2_SFRM"),
+	PINCTRL_PIN(150, "vI2S2_TXD"),
+	PINCTRL_PIN(151, "vI2S2_RXD"),
+	PINCTRL_PIN(152, "vSD3_CD_B"),
+	/* GPP_C */
+	PINCTRL_PIN(153, "SMBCLK"),
+	PINCTRL_PIN(154, "SMBDATA"),
+	PINCTRL_PIN(155, "SMBALERTB"),
+	PINCTRL_PIN(156, "SML0CLK"),
+	PINCTRL_PIN(157, "SML0DATA"),
+	PINCTRL_PIN(158, "SML0ALERTB"),
+	PINCTRL_PIN(159, "SML1CLK"),
+	PINCTRL_PIN(160, "SML1DATA"),
+	PINCTRL_PIN(161, "UART0_RXD"),
+	PINCTRL_PIN(162, "UART0_TXD"),
+	PINCTRL_PIN(163, "UART0_RTSB"),
+	PINCTRL_PIN(164, "UART0_CTSB"),
+	PINCTRL_PIN(165, "UART1_RXD"),
+	PINCTRL_PIN(166, "UART1_TXD"),
+	PINCTRL_PIN(167, "UART1_RTSB"),
+	PINCTRL_PIN(168, "UART1_CTSB"),
+	PINCTRL_PIN(169, "I2C0_SDA"),
+	PINCTRL_PIN(170, "I2C0_SCL"),
+	PINCTRL_PIN(171, "I2C1_SDA"),
+	PINCTRL_PIN(172, "I2C1_SCL"),
+	PINCTRL_PIN(173, "UART2_RXD"),
+	PINCTRL_PIN(174, "UART2_TXD"),
+	PINCTRL_PIN(175, "UART2_RTSB"),
+	PINCTRL_PIN(176, "UART2_CTSB"),
+	/* HVCMOS */
+	PINCTRL_PIN(177, "L_BKLTEN"),
+	PINCTRL_PIN(178, "L_BKLTCTL"),
+	PINCTRL_PIN(179, "L_VDDEN"),
+	PINCTRL_PIN(180, "SYS_PWROK"),
+	PINCTRL_PIN(181, "SYS_RESETB"),
+	PINCTRL_PIN(182, "MLK_RSTB"),
+	/* GPP_E */
+	PINCTRL_PIN(183, "SATAXPCIE_0"),
+	PINCTRL_PIN(184, "SPI1_IO_2"),
+	PINCTRL_PIN(185, "SPI1_IO_3"),
+	PINCTRL_PIN(186, "CPU_GP_0"),
+	PINCTRL_PIN(187, "SATA_DEVSLP_0"),
+	PINCTRL_PIN(188, "SATA_DEVSLP_1"),
+	PINCTRL_PIN(189, "GPPC_E_6"),
+	PINCTRL_PIN(190, "CPU_GP_1"),
+	PINCTRL_PIN(191, "SATA_LEDB"),
+	PINCTRL_PIN(192, "USB2_OCB_0"),
+	PINCTRL_PIN(193, "SPI1_CSB"),
+	PINCTRL_PIN(194, "SPI1_CLK"),
+	PINCTRL_PIN(195, "SPI1_MISO_IO_1"),
+	PINCTRL_PIN(196, "SPI1_MOSI_IO_0"),
+	PINCTRL_PIN(197, "DDSP_HPD_A"),
+	PINCTRL_PIN(198, "ISH_GP_6"),
+	PINCTRL_PIN(199, "ISH_GP_7"),
+	PINCTRL_PIN(200, "DISP_MISC_4"),
+	PINCTRL_PIN(201, "DDP1_CTRLCLK"),
+	PINCTRL_PIN(202, "DDP1_CTRLDATA"),
+	PINCTRL_PIN(203, "DDP2_CTRLCLK"),
+	PINCTRL_PIN(204, "DDP2_CTRLDATA"),
+	PINCTRL_PIN(205, "DDPA_CTRLCLK"),
+	PINCTRL_PIN(206, "DDPA_CTRLDATA"),
+	/* JTAG */
+	PINCTRL_PIN(207, "JTAG_TDO"),
+	PINCTRL_PIN(208, "JTAGX"),
+	PINCTRL_PIN(209, "PRDYB"),
+	PINCTRL_PIN(210, "PREQB"),
+	PINCTRL_PIN(211, "CPU_TRSTB"),
+	PINCTRL_PIN(212, "JTAG_TDI"),
+	PINCTRL_PIN(213, "JTAG_TMS"),
+	PINCTRL_PIN(214, "JTAG_TCK"),
+	PINCTRL_PIN(215, "ITP_PMODE"),
+	/* GPP_R */
+	PINCTRL_PIN(216, "HDA_BCLK"),
+	PINCTRL_PIN(217, "HDA_SYNC"),
+	PINCTRL_PIN(218, "HDA_SDO"),
+	PINCTRL_PIN(219, "HDA_SDI_0"),
+	PINCTRL_PIN(220, "HDA_RSTB"),
+	PINCTRL_PIN(221, "HDA_SDI_1"),
+	PINCTRL_PIN(222, "I2S1_TXD"),
+	PINCTRL_PIN(223, "I2S1_RXD"),
+	/* GPP_S */
+	PINCTRL_PIN(224, "SNDW1_CLK"),
+	PINCTRL_PIN(225, "SNDW1_DATA"),
+	PINCTRL_PIN(226, "SNDW2_CLK"),
+	PINCTRL_PIN(227, "SNDW2_DATA"),
+	PINCTRL_PIN(228, "SNDW3_CLK"),
+	PINCTRL_PIN(229, "SNDW3_DATA"),
+	PINCTRL_PIN(230, "SNDW4_CLK"),
+	PINCTRL_PIN(231, "SNDW4_DATA"),
+	/* SPI */
+	PINCTRL_PIN(232, "SPI0_IO_2"),
+	PINCTRL_PIN(233, "SPI0_IO_3"),
+	PINCTRL_PIN(234, "SPI0_MOSI_IO_0"),
+	PINCTRL_PIN(235, "SPI0_MISO_IO_1"),
+	PINCTRL_PIN(236, "SPI0_TPM_CSB"),
+	PINCTRL_PIN(237, "SPI0_FLASH_0_CSB"),
+	PINCTRL_PIN(238, "SPI0_FLASH_1_CSB"),
+	PINCTRL_PIN(239, "SPI0_CLK"),
+	PINCTRL_PIN(240, "SPI0_CLK_LOOPBK"),
+};
+
+static const struct intel_padgroup icllp_community0_gpps[] = {
+	ICL_GPP(0, 0, 7, 0),			/* GPP_G */
+	ICL_GPP(1, 8, 33, 32),			/* GPP_B */
+	ICL_GPP(2, 34, 58, 64),			/* GPP_A */
+};
+
+static const struct intel_padgroup icllp_community1_gpps[] = {
+	ICL_GPP(0, 59, 82, 96),			/* GPP_H */
+	ICL_GPP(1, 83, 103, 128),		/* GPP_D */
+	ICL_GPP(2, 104, 123, 160),		/* GPP_F */
+	ICL_GPP(3, 124, 152, 192),		/* vGPIO */
+};
+
+static const struct intel_padgroup icllp_community4_gpps[] = {
+	ICL_GPP(0, 153, 176, 224),		/* GPP_C */
+	ICL_GPP(1, 177, 182, ICL_NO_GPIO),	/* HVCMOS */
+	ICL_GPP(2, 183, 206, 256),		/* GPP_E */
+	ICL_GPP(3, 207, 215, ICL_NO_GPIO),	/* JTAG */
+};
+
+static const struct intel_padgroup icllp_community5_gpps[] = {
+	ICL_GPP(0, 216, 223, 288),		/* GPP_R */
+	ICL_GPP(1, 224, 231, 320),		/* GPP_S */
+	ICL_GPP(2, 232, 240, ICL_NO_GPIO),	/* SPI */
+};
+
+static const struct intel_community icllp_communities[] = {
+	ICL_COMMUNITY(0, 0, 58, icllp_community0_gpps),
+	ICL_COMMUNITY(1, 59, 152, icllp_community1_gpps),
+	ICL_COMMUNITY(2, 153, 215, icllp_community4_gpps),
+	ICL_COMMUNITY(3, 216, 240, icllp_community5_gpps),
+};
+
+static const unsigned int icllp_spi0_pins[] = { 22, 23, 24, 25, 26 };
+static const unsigned int icllp_spi0_modes[] = { 3, 1, 1, 1, 1 };
+static const unsigned int icllp_spi1_pins[] = { 27, 28, 29, 30, 31 };
+static const unsigned int icllp_spi1_modes[] = { 1, 1, 1, 1, 3 };
+static const unsigned int icllp_spi2_pins[] = { 92, 93, 94, 95, 98 };
+static const unsigned int icllp_spi2_modes[] = { 3, 3, 3, 3, 2 };
+
+static const unsigned int icllp_i2c0_pins[] = { 169, 170 };
+static const unsigned int icllp_i2c1_pins[] = { 171, 172 };
+static const unsigned int icllp_i2c2_pins[] = { 63, 64 };
+static const unsigned int icllp_i2c3_pins[] = { 65, 66 };
+static const unsigned int icllp_i2c4_pins[] = { 67, 68 };
+
+static const unsigned int icllp_uart0_pins[] = { 161, 162, 163, 164 };
+static const unsigned int icllp_uart1_pins[] = { 165, 166, 167, 168 };
+static const unsigned int icllp_uart2_pins[] = { 173, 174, 175, 176 };
+
+static const struct intel_pingroup icllp_groups[] = {
+	PIN_GROUP("spi0_grp", icllp_spi0_pins, icllp_spi0_modes),
+	PIN_GROUP("spi1_grp", icllp_spi1_pins, icllp_spi1_modes),
+	PIN_GROUP("spi2_grp", icllp_spi2_pins, icllp_spi2_modes),
+	PIN_GROUP("i2c0_grp", icllp_i2c0_pins, 1),
+	PIN_GROUP("i2c1_grp", icllp_i2c1_pins, 1),
+	PIN_GROUP("i2c2_grp", icllp_i2c2_pins, 1),
+	PIN_GROUP("i2c3_grp", icllp_i2c3_pins, 1),
+	PIN_GROUP("i2c4_grp", icllp_i2c4_pins, 1),
+	PIN_GROUP("uart0_grp", icllp_uart0_pins, 1),
+	PIN_GROUP("uart1_grp", icllp_uart1_pins, 1),
+	PIN_GROUP("uart2_grp", icllp_uart2_pins, 1),
+};
+
+static const char * const icllp_spi0_groups[] = { "spi0_grp" };
+static const char * const icllp_spi1_groups[] = { "spi1_grp" };
+static const char * const icllp_spi2_groups[] = { "spi2_grp" };
+static const char * const icllp_i2c0_groups[] = { "i2c0_grp" };
+static const char * const icllp_i2c1_groups[] = { "i2c1_grp" };
+static const char * const icllp_i2c2_groups[] = { "i2c2_grp" };
+static const char * const icllp_i2c3_groups[] = { "i2c3_grp" };
+static const char * const icllp_i2c4_groups[] = { "i2c4_grp" };
+static const char * const icllp_uart0_groups[] = { "uart0_grp" };
+static const char * const icllp_uart1_groups[] = { "uart1_grp" };
+static const char * const icllp_uart2_groups[] = { "uart2_grp" };
+
+static const struct intel_function icllp_functions[] = {
+	FUNCTION("spi0", icllp_spi0_groups),
+	FUNCTION("spi1", icllp_spi1_groups),
+	FUNCTION("spi2", icllp_spi2_groups),
+	FUNCTION("i2c0", icllp_i2c0_groups),
+	FUNCTION("i2c1", icllp_i2c1_groups),
+	FUNCTION("i2c2", icllp_i2c2_groups),
+	FUNCTION("i2c3", icllp_i2c3_groups),
+	FUNCTION("i2c4", icllp_i2c4_groups),
+	FUNCTION("uart0", icllp_uart0_groups),
+	FUNCTION("uart1", icllp_uart1_groups),
+	FUNCTION("uart2", icllp_uart2_groups),
+};
+
+static const struct intel_pinctrl_soc_data icllp_soc_data = {
+	.pins = icllp_pins,
+	.npins = ARRAY_SIZE(icllp_pins),
+	.groups = icllp_groups,
+	.ngroups = ARRAY_SIZE(icllp_groups),
+	.functions = icllp_functions,
+	.nfunctions = ARRAY_SIZE(icllp_functions),
+	.communities = icllp_communities,
+	.ncommunities = ARRAY_SIZE(icllp_communities),
+};
+
+static int icl_pinctrl_probe(struct platform_device *pdev)
+{
+	return intel_pinctrl_probe(pdev, &icllp_soc_data);
+}
+
+static const struct dev_pm_ops icl_pinctrl_pm_ops = {
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(intel_pinctrl_suspend,
+				     intel_pinctrl_resume)
+};
+
+static const struct acpi_device_id icl_pinctrl_acpi_match[] = {
+	{ "INT3455" },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, icl_pinctrl_acpi_match);
+
+static struct platform_driver icl_pinctrl_driver = {
+	.probe = icl_pinctrl_probe,
+	.driver = {
+		.name = "icelake-pinctrl",
+		.acpi_match_table = icl_pinctrl_acpi_match,
+		.pm = &icl_pinctrl_pm_ops,
+	},
+};
+
+module_platform_driver(icl_pinctrl_driver);
+
+MODULE_AUTHOR("Andy Shevchenko <andriy.shevchenko@linux.intel.com>");
+MODULE_AUTHOR("Mika Westerberg <mika.westerberg@linux.intel.com>");
+MODULE_DESCRIPTION("Intel Ice Lake PCH pinctrl/GPIO driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 9b10000f4921e9f9f8231f9ceecae4446928844a Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 27 Jun 2018 20:45:24 -0500
Subject: tg3: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/tg3.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3be87efdc93d..0a796d5ec893 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -721,6 +721,7 @@ static int tg3_ape_lock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return 0;
+		/* else: fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -781,6 +782,7 @@ static void tg3_ape_unlock(struct tg3 *tp, int locknum)
 	case TG3_APE_LOCK_GPIO:
 		if (tg3_asic_rev(tp) == ASIC_REV_5761)
 			return;
+		/* else: fall through */
 	case TG3_APE_LOCK_GRC:
 	case TG3_APE_LOCK_MEM:
 		if (!tp->pci_fn)
@@ -10706,28 +10708,40 @@ static int tg3_reset_hw(struct tg3 *tp, bool reset_phy)
 	switch (limit) {
 	case 16:
 		tw32(MAC_RCV_RULE_15,  0); tw32(MAC_RCV_VALUE_15,  0);
+		/* fall through */
 	case 15:
 		tw32(MAC_RCV_RULE_14,  0); tw32(MAC_RCV_VALUE_14,  0);
+		/* fall through */
 	case 14:
 		tw32(MAC_RCV_RULE_13,  0); tw32(MAC_RCV_VALUE_13,  0);
+		/* fall through */
 	case 13:
 		tw32(MAC_RCV_RULE_12,  0); tw32(MAC_RCV_VALUE_12,  0);
+		/* fall through */
 	case 12:
 		tw32(MAC_RCV_RULE_11,  0); tw32(MAC_RCV_VALUE_11,  0);
+		/* fall through */
 	case 11:
 		tw32(MAC_RCV_RULE_10,  0); tw32(MAC_RCV_VALUE_10,  0);
+		/* fall through */
 	case 10:
 		tw32(MAC_RCV_RULE_9,  0); tw32(MAC_RCV_VALUE_9,  0);
+		/* fall through */
 	case 9:
 		tw32(MAC_RCV_RULE_8,  0); tw32(MAC_RCV_VALUE_8,  0);
+		/* fall through */
 	case 8:
 		tw32(MAC_RCV_RULE_7,  0); tw32(MAC_RCV_VALUE_7,  0);
+		/* fall through */
 	case 7:
 		tw32(MAC_RCV_RULE_6,  0); tw32(MAC_RCV_VALUE_6,  0);
+		/* fall through */
 	case 6:
 		tw32(MAC_RCV_RULE_5,  0); tw32(MAC_RCV_VALUE_5,  0);
+		/* fall through */
 	case 5:
 		tw32(MAC_RCV_RULE_4,  0); tw32(MAC_RCV_VALUE_4,  0);
+		/* fall through */
 	case 4:
 		/* tw32(MAC_RCV_RULE_3,  0); tw32(MAC_RCV_VALUE_3,  0); */
 	case 3:
-- 
cgit v1.2.3


From 23c94d63a7e395c5706f7d9edde1ff839b050c5f Mon Sep 17 00:00:00 2001
From: David Wu <david.wu@rock-chips.com>
Date: Thu, 28 Jun 2018 09:33:21 +0800
Subject: net: ethernet: stmmac: dwmac-rk: Add GMAC support for px30

Add constants and callback functions for the dwmac on px30 Soc.
The base structure is the same, but registers and the bits in
them are moved slightly, and add the clk_mac_speed for selecting
mac speed.

Signed-off-by: David Wu <david.wu@rock-chips.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/rockchip-dwmac.txt     |  1 +
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c     | 69 ++++++++++++++++++++++
 2 files changed, 70 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
index 9c16ee2965a2..3b71da7e8742 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.txt
@@ -4,6 +4,7 @@ The device node has following properties.
 
 Required properties:
  - compatible: should be "rockchip,<name>-gamc"
+   "rockchip,px30-gmac":   found on PX30 SoCs
    "rockchip,rk3128-gmac": found on RK312x SoCs
    "rockchip,rk3228-gmac": found on RK322x SoCs
    "rockchip,rk3288-gmac": found on RK3288 SoCs
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index f08625a02cea..7b923362ee55 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -61,6 +61,7 @@ struct rk_priv_data {
 	struct clk *mac_clk_tx;
 	struct clk *clk_mac_ref;
 	struct clk *clk_mac_refout;
+	struct clk *clk_mac_speed;
 	struct clk *aclk_mac;
 	struct clk *pclk_mac;
 	struct clk *clk_phy;
@@ -83,6 +84,64 @@ struct rk_priv_data {
 	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
 	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
 
+#define PX30_GRF_GMAC_CON1		0x0904
+
+/* PX30_GRF_GMAC_CON1 */
+#define PX30_GMAC_PHY_INTF_SEL_RMII	(GRF_CLR_BIT(4) | GRF_CLR_BIT(5) | \
+					 GRF_BIT(6))
+#define PX30_GMAC_SPEED_10M		GRF_CLR_BIT(2)
+#define PX30_GMAC_SPEED_100M		GRF_BIT(2)
+
+static void px30_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
+		return;
+	}
+
+	regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+		     PX30_GMAC_PHY_INTF_SEL_RMII);
+}
+
+static void px30_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	int ret;
+
+	if (IS_ERR(bsp_priv->clk_mac_speed)) {
+		dev_err(dev, "%s: Missing clk_mac_speed clock\n", __func__);
+		return;
+	}
+
+	if (speed == 10) {
+		regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+			     PX30_GMAC_SPEED_10M);
+
+		ret = clk_set_rate(bsp_priv->clk_mac_speed, 2500000);
+		if (ret)
+			dev_err(dev, "%s: set clk_mac_speed rate 2500000 failed: %d\n",
+				__func__, ret);
+	} else if (speed == 100) {
+		regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
+			     PX30_GMAC_SPEED_100M);
+
+		ret = clk_set_rate(bsp_priv->clk_mac_speed, 25000000);
+		if (ret)
+			dev_err(dev, "%s: set clk_mac_speed rate 25000000 failed: %d\n",
+				__func__, ret);
+
+	} else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+	}
+}
+
+static const struct rk_gmac_ops px30_ops = {
+	.set_to_rmii = px30_set_to_rmii,
+	.set_rmii_speed = px30_set_rmii_speed,
+};
+
 #define RK3128_GRF_MAC_CON0	0x0168
 #define RK3128_GRF_MAC_CON1	0x016c
 
@@ -1042,6 +1101,10 @@ static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat)
 		}
 	}
 
+	bsp_priv->clk_mac_speed = devm_clk_get(dev, "clk_mac_speed");
+	if (IS_ERR(bsp_priv->clk_mac_speed))
+		dev_err(dev, "cannot get clock %s\n", "clk_mac_speed");
+
 	if (bsp_priv->clock_input) {
 		dev_info(dev, "clock input from PHY\n");
 	} else {
@@ -1094,6 +1157,9 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable)
 			if (!IS_ERR(bsp_priv->mac_clk_tx))
 				clk_prepare_enable(bsp_priv->mac_clk_tx);
 
+			if (!IS_ERR(bsp_priv->clk_mac_speed))
+				clk_prepare_enable(bsp_priv->clk_mac_speed);
+
 			/**
 			 * if (!IS_ERR(bsp_priv->clk_mac))
 			 *	clk_prepare_enable(bsp_priv->clk_mac);
@@ -1118,6 +1184,8 @@ static int gmac_clk_enable(struct rk_priv_data *bsp_priv, bool enable)
 			clk_disable_unprepare(bsp_priv->pclk_mac);
 
 			clk_disable_unprepare(bsp_priv->mac_clk_tx);
+
+			clk_disable_unprepare(bsp_priv->clk_mac_speed);
 			/**
 			 * if (!IS_ERR(bsp_priv->clk_mac))
 			 *	clk_disable_unprepare(bsp_priv->clk_mac);
@@ -1414,6 +1482,7 @@ static int rk_gmac_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk_gmac_pm_ops, rk_gmac_suspend, rk_gmac_resume);
 
 static const struct of_device_id rk_gmac_dwmac_match[] = {
+	{ .compatible = "rockchip,px30-gmac",	.data = &px30_ops   },
 	{ .compatible = "rockchip,rk3128-gmac", .data = &rk3128_ops },
 	{ .compatible = "rockchip,rk3228-gmac", .data = &rk3228_ops },
 	{ .compatible = "rockchip,rk3288-gmac", .data = &rk3288_ops },
-- 
cgit v1.2.3


From b0e9a2fe3ff971950833bc0ffc383babd9443bc4 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Thu, 28 Jun 2018 15:31:00 +0800
Subject: sctp: add support for SCTP_REUSE_PORT sockopt

This feature is actually already supported by sk->sk_reuse which can be
set by socket level opt SO_REUSEADDR. But it's not working exactly as
RFC6458 demands in section 8.1.27, like:

  - This option only supports one-to-one style SCTP sockets
  - This socket option must not be used after calling bind()
    or sctp_bindx().

Besides, SCTP_REUSE_PORT sockopt should be provided for user's programs.
Otherwise, the programs with SCTP_REUSE_PORT from other systems will not
work in linux.

To separate it from the socket level version, this patch adds 'reuse' in
sctp_sock and it works pretty much as sk->sk_reuse, but with some extra
setup limitations that are needed when it is being enabled.

"It should be noted that the behavior of the socket-level socket option
to reuse ports and/or addresses for SCTP sockets is unspecified", so it
leaves SO_REUSEADDR as is for the compatibility.

Note that the name SCTP_REUSE_PORT is somewhat confusing, as its
functionality is nearly identical to SO_REUSEADDR, but with some
extra restrictions. Here it uses 'reuse' in sctp_sock instead of
'reuseport'. As for sk->sk_reuseport support for SCTP, it will be
added in another patch.

Thanks to Neil to make this clear.

v1->v2:
  - add sctp_sk->reuse to separate it from the socket level version.
v2->v3:
  - improve changelog according to Marcelo's suggestion.

Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  1 +
 include/uapi/linux/sctp.h  |  1 +
 net/sctp/socket.c          | 62 ++++++++++++++++++++++++++++++++++++++++------
 3 files changed, 57 insertions(+), 7 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index e0f962d27386..701a51736fa5 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -220,6 +220,7 @@ struct sctp_sock {
 	__u32 adaptation_ind;
 	__u32 pd_point;
 	__u16	nodelay:1,
+		reuse:1,
 		disable_fragments:1,
 		v4mapped:1,
 		frag_interleave:1,
diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index b64d583bf053..c02986a284db 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -100,6 +100,7 @@ typedef __s32 sctp_assoc_t;
 #define SCTP_RECVNXTINFO	33
 #define SCTP_DEFAULT_SNDINFO	34
 #define SCTP_AUTH_DEACTIVATE_KEY	35
+#define SCTP_REUSE_PORT		36
 
 /* Internal Socket Options. Some of the sctp library functions are
  * implemented using these socket options.
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 0e91e83eea5a..bf11f9cacb63 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -4170,6 +4170,28 @@ out:
 	return retval;
 }
 
+static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval,
+				      unsigned int optlen)
+{
+	int val;
+
+	if (!sctp_style(sk, TCP))
+		return -EOPNOTSUPP;
+
+	if (sctp_sk(sk)->ep->base.bind_addr.port)
+		return -EFAULT;
+
+	if (optlen < sizeof(int))
+		return -EINVAL;
+
+	if (get_user(val, (int __user *)optval))
+		return -EFAULT;
+
+	sctp_sk(sk)->reuse = !!val;
+
+	return 0;
+}
+
 /* API 6.2 setsockopt(), getsockopt()
  *
  * Applications use setsockopt() and getsockopt() to set or retrieve
@@ -4364,6 +4386,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_setsockopt_interleaving_supported(sk, optval,
 								optlen);
 		break;
+	case SCTP_REUSE_PORT:
+		retval = sctp_setsockopt_reuse_port(sk, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -7197,6 +7222,26 @@ out:
 	return retval;
 }
 
+static int sctp_getsockopt_reuse_port(struct sock *sk, int len,
+				      char __user *optval,
+				      int __user *optlen)
+{
+	int val;
+
+	if (len < sizeof(int))
+		return -EINVAL;
+
+	len = sizeof(int);
+	val = sctp_sk(sk)->reuse;
+	if (put_user(len, optlen))
+		return -EFAULT;
+
+	if (copy_to_user(optval, &val, len))
+		return -EFAULT;
+
+	return 0;
+}
+
 static int sctp_getsockopt(struct sock *sk, int level, int optname,
 			   char __user *optval, int __user *optlen)
 {
@@ -7392,6 +7437,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname,
 		retval = sctp_getsockopt_interleaving_supported(sk, len, optval,
 								optlen);
 		break;
+	case SCTP_REUSE_PORT:
+		retval = sctp_getsockopt_reuse_port(sk, len, optval, optlen);
+		break;
 	default:
 		retval = -ENOPROTOOPT;
 		break;
@@ -7429,6 +7477,7 @@ static struct sctp_bind_bucket *sctp_bucket_create(
 
 static long sctp_get_port_local(struct sock *sk, union sctp_addr *addr)
 {
+	bool reuse = (sk->sk_reuse || sctp_sk(sk)->reuse);
 	struct sctp_bind_hashbucket *head; /* hash list */
 	struct sctp_bind_bucket *pp;
 	unsigned short snum;
@@ -7501,13 +7550,11 @@ pp_found:
 		 * used by other socket (pp->owner not empty); that other
 		 * socket is going to be sk2.
 		 */
-		int reuse = sk->sk_reuse;
 		struct sock *sk2;
 
 		pr_debug("%s: found a possible match\n", __func__);
 
-		if (pp->fastreuse && sk->sk_reuse &&
-			sk->sk_state != SCTP_SS_LISTENING)
+		if (pp->fastreuse && reuse && sk->sk_state != SCTP_SS_LISTENING)
 			goto success;
 
 		/* Run through the list of sockets bound to the port
@@ -7525,7 +7572,7 @@ pp_found:
 			ep2 = sctp_sk(sk2)->ep;
 
 			if (sk == sk2 ||
-			    (reuse && sk2->sk_reuse &&
+			    (reuse && (sk2->sk_reuse || sctp_sk(sk2)->reuse) &&
 			     sk2->sk_state != SCTP_SS_LISTENING))
 				continue;
 
@@ -7549,12 +7596,12 @@ pp_not_found:
 	 * SO_REUSEADDR on this socket -sk-).
 	 */
 	if (hlist_empty(&pp->owner)) {
-		if (sk->sk_reuse && sk->sk_state != SCTP_SS_LISTENING)
+		if (reuse && sk->sk_state != SCTP_SS_LISTENING)
 			pp->fastreuse = 1;
 		else
 			pp->fastreuse = 0;
 	} else if (pp->fastreuse &&
-		(!sk->sk_reuse || sk->sk_state == SCTP_SS_LISTENING))
+		   (!reuse || sk->sk_state == SCTP_SS_LISTENING))
 		pp->fastreuse = 0;
 
 	/* We are set, so fill up all the data in the hash table
@@ -7685,7 +7732,7 @@ int sctp_inet_listen(struct socket *sock, int backlog)
 		err = 0;
 		sctp_unhash_endpoint(ep);
 		sk->sk_state = SCTP_SS_CLOSED;
-		if (sk->sk_reuse)
+		if (sk->sk_reuse || sctp_sk(sk)->reuse)
 			sctp_sk(sk)->bind_hash->fastreuse = 1;
 		goto out;
 	}
@@ -8550,6 +8597,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk,
 	newsk->sk_no_check_tx = sk->sk_no_check_tx;
 	newsk->sk_no_check_rx = sk->sk_no_check_rx;
 	newsk->sk_reuse = sk->sk_reuse;
+	sctp_sk(newsk)->reuse = sp->reuse;
 
 	newsk->sk_shutdown = sk->sk_shutdown;
 	newsk->sk_destruct = sctp_destruct_sock;
-- 
cgit v1.2.3


From d5fbda61ac923e0adb89fd59fdf4a1d99406b86e Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Tue, 26 Jun 2018 17:10:25 +0530
Subject: cxgb4: Add support for FW_ETH_TX_PKT_VM_WR

The present TX workrequest(FW_ETH_TX_PKT_WR) cant be used for
host->vf communication, since it doesn't loopback the outgoing
packets to virtual interfaces on the same port. This can be done
using FW_ETH_TX_PKT_VM_WR.
This fix depends on ethtool_flags to determine what WR to use for
TX path. Support for setting this flags by user is added in next
commit.

Based on the original work by : Casey Leedom <leedom@chelsio.com>

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h      |  13 +-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c |   2 +-
 drivers/net/ethernet/chelsio/cxgb4/sge.c        | 372 +++++++++++++++++++++++-
 3 files changed, 383 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index f27b2f0ade0b..4a8cbd864ef7 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -522,6 +522,15 @@ enum {
 	MAX_INGQ = MAX_ETH_QSETS + INGQ_EXTRAS,
 };
 
+enum {
+	PRIV_FLAG_PORT_TX_VM_BIT,
+};
+
+#define PRIV_FLAG_PORT_TX_VM		BIT(PRIV_FLAG_PORT_TX_VM_BIT)
+
+#define PRIV_FLAGS_ADAP			0
+#define PRIV_FLAGS_PORT			PRIV_FLAG_PORT_TX_VM
+
 struct adapter;
 struct sge_rspq;
 
@@ -558,6 +567,7 @@ struct port_info {
 	struct hwtstamp_config tstamp_config;
 	bool ptp_enable;
 	struct sched_table *sched_tbl;
+	u32 eth_flags;
 };
 
 struct dentry;
@@ -868,6 +878,7 @@ struct adapter {
 	unsigned int flags;
 	unsigned int adap_idx;
 	enum chip_type chip;
+	u32 eth_flags;
 
 	int msg_enable;
 	__be16 vxlan_port;
@@ -1335,7 +1346,7 @@ void t4_os_link_changed(struct adapter *adap, int port_id, int link_stat);
 void t4_free_sge_resources(struct adapter *adap);
 void t4_free_ofld_rxqs(struct adapter *adap, int n, struct sge_ofld_rxq *q);
 irq_handler_t t4_intr_handler(struct adapter *adap);
-netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev);
+netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev);
 int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp,
 		     const struct pkt_gl *gl);
 int t4_mgmt_tx(struct adapter *adap, struct sk_buff *skb);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 96bc177d54de..1c0374cbb890 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -3217,7 +3217,7 @@ static netdev_features_t cxgb_fix_features(struct net_device *dev,
 static const struct net_device_ops cxgb4_netdev_ops = {
 	.ndo_open             = cxgb_open,
 	.ndo_stop             = cxgb_close,
-	.ndo_start_xmit       = t4_eth_xmit,
+	.ndo_start_xmit       = t4_start_xmit,
 	.ndo_select_queue     =	cxgb_select_queue,
 	.ndo_get_stats64      = cxgb_get_stats,
 	.ndo_set_rx_mode      = cxgb_set_rxmode,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index 395e2a0e8d7f..ebb46c472d52 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -1288,13 +1288,13 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb,
 }
 
 /**
- *	t4_eth_xmit - add a packet to an Ethernet Tx queue
+ *	cxgb4_eth_xmit - add a packet to an Ethernet Tx queue
  *	@skb: the packet
  *	@dev: the egress net device
  *
  *	Add a packet to an SGE Ethernet Tx queue.  Runs with softirqs disabled.
  */
-netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t cxgb4_eth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	u32 wr_mid, ctrl0, op;
 	u64 cntrl, *end, *sgl;
@@ -1547,6 +1547,374 @@ out_free:	dev_kfree_skb_any(skb);
 	return NETDEV_TX_OK;
 }
 
+/* Constants ... */
+enum {
+	/* Egress Queue sizes, producer and consumer indices are all in units
+	 * of Egress Context Units bytes.  Note that as far as the hardware is
+	 * concerned, the free list is an Egress Queue (the host produces free
+	 * buffers which the hardware consumes) and free list entries are
+	 * 64-bit PCI DMA addresses.
+	 */
+	EQ_UNIT = SGE_EQ_IDXSIZE,
+	FL_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64),
+	TXD_PER_EQ_UNIT = EQ_UNIT / sizeof(__be64),
+
+	T4VF_ETHTXQ_MAX_HDR = (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+			       sizeof(struct cpl_tx_pkt_lso_core) +
+			       sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64),
+};
+
+/**
+ *	t4vf_is_eth_imm - can an Ethernet packet be sent as immediate data?
+ *	@skb: the packet
+ *
+ *	Returns whether an Ethernet packet is small enough to fit completely as
+ *	immediate data.
+ */
+static inline int t4vf_is_eth_imm(const struct sk_buff *skb)
+{
+	/* The VF Driver uses the FW_ETH_TX_PKT_VM_WR firmware Work Request
+	 * which does not accommodate immediate data.  We could dike out all
+	 * of the support code for immediate data but that would tie our hands
+	 * too much if we ever want to enhace the firmware.  It would also
+	 * create more differences between the PF and VF Drivers.
+	 */
+	return false;
+}
+
+/**
+ *	t4vf_calc_tx_flits - calculate the number of flits for a packet TX WR
+ *	@skb: the packet
+ *
+ *	Returns the number of flits needed for a TX Work Request for the
+ *	given Ethernet packet, including the needed WR and CPL headers.
+ */
+static inline unsigned int t4vf_calc_tx_flits(const struct sk_buff *skb)
+{
+	unsigned int flits;
+
+	/* If the skb is small enough, we can pump it out as a work request
+	 * with only immediate data.  In that case we just have to have the
+	 * TX Packet header plus the skb data in the Work Request.
+	 */
+	if (t4vf_is_eth_imm(skb))
+		return DIV_ROUND_UP(skb->len + sizeof(struct cpl_tx_pkt),
+				    sizeof(__be64));
+
+	/* Otherwise, we're going to have to construct a Scatter gather list
+	 * of the skb body and fragments.  We also include the flits necessary
+	 * for the TX Packet Work Request and CPL.  We always have a firmware
+	 * Write Header (incorporated as part of the cpl_tx_pkt_lso and
+	 * cpl_tx_pkt structures), followed by either a TX Packet Write CPL
+	 * message or, if we're doing a Large Send Offload, an LSO CPL message
+	 * with an embedded TX Packet Write CPL message.
+	 */
+	flits = sgl_len(skb_shinfo(skb)->nr_frags + 1);
+	if (skb_shinfo(skb)->gso_size)
+		flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+			  sizeof(struct cpl_tx_pkt_lso_core) +
+			  sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64);
+	else
+		flits += (sizeof(struct fw_eth_tx_pkt_vm_wr) +
+			  sizeof(struct cpl_tx_pkt_core)) / sizeof(__be64);
+	return flits;
+}
+
+/**
+ *	cxgb4_vf_eth_xmit - add a packet to an Ethernet TX queue
+ *	@skb: the packet
+ *	@dev: the egress net device
+ *
+ *	Add a packet to an SGE Ethernet TX queue.  Runs with softirqs disabled.
+ */
+static netdev_tx_t cxgb4_vf_eth_xmit(struct sk_buff *skb,
+				     struct net_device *dev)
+{
+	dma_addr_t addr[MAX_SKB_FRAGS + 1];
+	const struct skb_shared_info *ssi;
+	struct fw_eth_tx_pkt_vm_wr *wr;
+	int qidx, credits, max_pkt_len;
+	struct cpl_tx_pkt_core *cpl;
+	const struct port_info *pi;
+	unsigned int flits, ndesc;
+	struct sge_eth_txq *txq;
+	struct adapter *adapter;
+	u64 cntrl, *end;
+	u32 wr_mid;
+	const size_t fw_hdr_copy_len = sizeof(wr->ethmacdst) +
+				       sizeof(wr->ethmacsrc) +
+				       sizeof(wr->ethtype) +
+				       sizeof(wr->vlantci);
+
+	/* The chip minimum packet length is 10 octets but the firmware
+	 * command that we are using requires that we copy the Ethernet header
+	 * (including the VLAN tag) into the header so we reject anything
+	 * smaller than that ...
+	 */
+	if (unlikely(skb->len < fw_hdr_copy_len))
+		goto out_free;
+
+	/* Discard the packet if the length is greater than mtu */
+	max_pkt_len = ETH_HLEN + dev->mtu;
+	if (skb_vlan_tag_present(skb))
+		max_pkt_len += VLAN_HLEN;
+	if (!skb_shinfo(skb)->gso_size && (unlikely(skb->len > max_pkt_len)))
+		goto out_free;
+
+	/* Figure out which TX Queue we're going to use. */
+	pi = netdev_priv(dev);
+	adapter = pi->adapter;
+	qidx = skb_get_queue_mapping(skb);
+	WARN_ON(qidx >= pi->nqsets);
+	txq = &adapter->sge.ethtxq[pi->first_qset + qidx];
+
+	/* Take this opportunity to reclaim any TX Descriptors whose DMA
+	 * transfers have completed.
+	 */
+	cxgb4_reclaim_completed_tx(adapter, &txq->q, true);
+
+	/* Calculate the number of flits and TX Descriptors we're going to
+	 * need along with how many TX Descriptors will be left over after
+	 * we inject our Work Request.
+	 */
+	flits = t4vf_calc_tx_flits(skb);
+	ndesc = flits_to_desc(flits);
+	credits = txq_avail(&txq->q) - ndesc;
+
+	if (unlikely(credits < 0)) {
+		/* Not enough room for this packet's Work Request.  Stop the
+		 * TX Queue and return a "busy" condition.  The queue will get
+		 * started later on when the firmware informs us that space
+		 * has opened up.
+		 */
+		eth_txq_stop(txq);
+		dev_err(adapter->pdev_dev,
+			"%s: TX ring %u full while queue awake!\n",
+			dev->name, qidx);
+		return NETDEV_TX_BUSY;
+	}
+
+	if (!t4vf_is_eth_imm(skb) &&
+	    unlikely(cxgb4_map_skb(adapter->pdev_dev, skb, addr) < 0)) {
+		/* We need to map the skb into PCI DMA space (because it can't
+		 * be in-lined directly into the Work Request) and the mapping
+		 * operation failed.  Record the error and drop the packet.
+		 */
+		txq->mapping_err++;
+		goto out_free;
+	}
+
+	wr_mid = FW_WR_LEN16_V(DIV_ROUND_UP(flits, 2));
+	if (unlikely(credits < ETHTXQ_STOP_THRES)) {
+		/* After we're done injecting the Work Request for this
+		 * packet, we'll be below our "stop threshold" so stop the TX
+		 * Queue now and schedule a request for an SGE Egress Queue
+		 * Update message.  The queue will get started later on when
+		 * the firmware processes this Work Request and sends us an
+		 * Egress Queue Status Update message indicating that space
+		 * has opened up.
+		 */
+		eth_txq_stop(txq);
+		wr_mid |= FW_WR_EQUEQ_F | FW_WR_EQUIQ_F;
+	}
+
+	/* Start filling in our Work Request.  Note that we do _not_ handle
+	 * the WR Header wrapping around the TX Descriptor Ring.  If our
+	 * maximum header size ever exceeds one TX Descriptor, we'll need to
+	 * do something else here.
+	 */
+	WARN_ON(DIV_ROUND_UP(T4VF_ETHTXQ_MAX_HDR, TXD_PER_EQ_UNIT) > 1);
+	wr = (void *)&txq->q.desc[txq->q.pidx];
+	wr->equiq_to_len16 = cpu_to_be32(wr_mid);
+	wr->r3[0] = cpu_to_be32(0);
+	wr->r3[1] = cpu_to_be32(0);
+	skb_copy_from_linear_data(skb, (void *)wr->ethmacdst, fw_hdr_copy_len);
+	end = (u64 *)wr + flits;
+
+	/* If this is a Large Send Offload packet we'll put in an LSO CPL
+	 * message with an encapsulated TX Packet CPL message.  Otherwise we
+	 * just use a TX Packet CPL message.
+	 */
+	ssi = skb_shinfo(skb);
+	if (ssi->gso_size) {
+		struct cpl_tx_pkt_lso_core *lso = (void *)(wr + 1);
+		bool v6 = (ssi->gso_type & SKB_GSO_TCPV6) != 0;
+		int l3hdr_len = skb_network_header_len(skb);
+		int eth_xtra_len = skb_network_offset(skb) - ETH_HLEN;
+
+		wr->op_immdlen =
+			cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) |
+				    FW_WR_IMMDLEN_V(sizeof(*lso) +
+						    sizeof(*cpl)));
+		 /* Fill in the LSO CPL message. */
+		lso->lso_ctrl =
+			cpu_to_be32(LSO_OPCODE_V(CPL_TX_PKT_LSO) |
+				    LSO_FIRST_SLICE_F |
+				    LSO_LAST_SLICE_F |
+				    LSO_IPV6_V(v6) |
+				    LSO_ETHHDR_LEN_V(eth_xtra_len / 4) |
+				    LSO_IPHDR_LEN_V(l3hdr_len / 4) |
+				    LSO_TCPHDR_LEN_V(tcp_hdr(skb)->doff));
+		lso->ipid_ofst = cpu_to_be16(0);
+		lso->mss = cpu_to_be16(ssi->gso_size);
+		lso->seqno_offset = cpu_to_be32(0);
+		if (is_t4(adapter->params.chip))
+			lso->len = cpu_to_be32(skb->len);
+		else
+			lso->len = cpu_to_be32(LSO_T5_XFER_SIZE_V(skb->len));
+
+		/* Set up TX Packet CPL pointer, control word and perform
+		 * accounting.
+		 */
+		cpl = (void *)(lso + 1);
+
+		if (CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5)
+			cntrl = TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+		else
+			cntrl = T6_TXPKT_ETHHDR_LEN_V(eth_xtra_len);
+
+		cntrl |= TXPKT_CSUM_TYPE_V(v6 ?
+					   TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) |
+			 TXPKT_IPHDR_LEN_V(l3hdr_len);
+		txq->tso++;
+		txq->tx_cso += ssi->gso_segs;
+	} else {
+		int len;
+
+		len = (t4vf_is_eth_imm(skb)
+		       ? skb->len + sizeof(*cpl)
+		       : sizeof(*cpl));
+		wr->op_immdlen =
+			cpu_to_be32(FW_WR_OP_V(FW_ETH_TX_PKT_VM_WR) |
+				    FW_WR_IMMDLEN_V(len));
+
+		/* Set up TX Packet CPL pointer, control word and perform
+		 * accounting.
+		 */
+		cpl = (void *)(wr + 1);
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			cntrl = hwcsum(adapter->params.chip, skb) |
+				TXPKT_IPCSUM_DIS_F;
+			txq->tx_cso++;
+		} else {
+			cntrl = TXPKT_L4CSUM_DIS_F | TXPKT_IPCSUM_DIS_F;
+		}
+	}
+
+	/* If there's a VLAN tag present, add that to the list of things to
+	 * do in this Work Request.
+	 */
+	if (skb_vlan_tag_present(skb)) {
+		txq->vlan_ins++;
+		cntrl |= TXPKT_VLAN_VLD_F | TXPKT_VLAN_V(skb_vlan_tag_get(skb));
+	}
+
+	 /* Fill in the TX Packet CPL message header. */
+	cpl->ctrl0 = cpu_to_be32(TXPKT_OPCODE_V(CPL_TX_PKT_XT) |
+				 TXPKT_INTF_V(pi->port_id) |
+				 TXPKT_PF_V(0));
+	cpl->pack = cpu_to_be16(0);
+	cpl->len = cpu_to_be16(skb->len);
+	cpl->ctrl1 = cpu_to_be64(cntrl);
+
+	/* Fill in the body of the TX Packet CPL message with either in-lined
+	 * data or a Scatter/Gather List.
+	 */
+	if (t4vf_is_eth_imm(skb)) {
+		/* In-line the packet's data and free the skb since we don't
+		 * need it any longer.
+		 */
+		cxgb4_inline_tx_skb(skb, &txq->q, cpl + 1);
+		dev_consume_skb_any(skb);
+	} else {
+		/* Write the skb's Scatter/Gather list into the TX Packet CPL
+		 * message and retain a pointer to the skb so we can free it
+		 * later when its DMA completes.  (We store the skb pointer
+		 * in the Software Descriptor corresponding to the last TX
+		 * Descriptor used by the Work Request.)
+		 *
+		 * The retained skb will be freed when the corresponding TX
+		 * Descriptors are reclaimed after their DMAs complete.
+		 * However, this could take quite a while since, in general,
+		 * the hardware is set up to be lazy about sending DMA
+		 * completion notifications to us and we mostly perform TX
+		 * reclaims in the transmit routine.
+		 *
+		 * This is good for performamce but means that we rely on new
+		 * TX packets arriving to run the destructors of completed
+		 * packets, which open up space in their sockets' send queues.
+		 * Sometimes we do not get such new packets causing TX to
+		 * stall.  A single UDP transmitter is a good example of this
+		 * situation.  We have a clean up timer that periodically
+		 * reclaims completed packets but it doesn't run often enough
+		 * (nor do we want it to) to prevent lengthy stalls.  A
+		 * solution to this problem is to run the destructor early,
+		 * after the packet is queued but before it's DMAd.  A con is
+		 * that we lie to socket memory accounting, but the amount of
+		 * extra memory is reasonable (limited by the number of TX
+		 * descriptors), the packets do actually get freed quickly by
+		 * new packets almost always, and for protocols like TCP that
+		 * wait for acks to really free up the data the extra memory
+		 * is even less.  On the positive side we run the destructors
+		 * on the sending CPU rather than on a potentially different
+		 * completing CPU, usually a good thing.
+		 *
+		 * Run the destructor before telling the DMA engine about the
+		 * packet to make sure it doesn't complete and get freed
+		 * prematurely.
+		 */
+		struct ulptx_sgl *sgl = (struct ulptx_sgl *)(cpl + 1);
+		struct sge_txq *tq = &txq->q;
+		int last_desc;
+
+		/* If the Work Request header was an exact multiple of our TX
+		 * Descriptor length, then it's possible that the starting SGL
+		 * pointer lines up exactly with the end of our TX Descriptor
+		 * ring.  If that's the case, wrap around to the beginning
+		 * here ...
+		 */
+		if (unlikely((void *)sgl == (void *)tq->stat)) {
+			sgl = (void *)tq->desc;
+			end = (void *)((void *)tq->desc +
+				       ((void *)end - (void *)tq->stat));
+		}
+
+		cxgb4_write_sgl(skb, tq, sgl, end, 0, addr);
+		skb_orphan(skb);
+
+		last_desc = tq->pidx + ndesc - 1;
+		if (last_desc >= tq->size)
+			last_desc -= tq->size;
+		tq->sdesc[last_desc].skb = skb;
+		tq->sdesc[last_desc].sgl = sgl;
+	}
+
+	/* Advance our internal TX Queue state, tell the hardware about
+	 * the new TX descriptors and return success.
+	 */
+	txq_advance(&txq->q, ndesc);
+
+	cxgb4_ring_tx_db(adapter, &txq->q, ndesc);
+	return NETDEV_TX_OK;
+
+out_free:
+	/* An error of some sort happened.  Free the TX skb and tell the
+	 * OS that we've "dealt" with the packet ...
+	 */
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t t4_start_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct port_info *pi = netdev_priv(dev);
+
+	if (unlikely(pi->eth_flags & PRIV_FLAG_PORT_TX_VM))
+		return cxgb4_vf_eth_xmit(skb, dev);
+
+	return cxgb4_eth_xmit(skb, dev);
+}
+
 /**
  *	reclaim_completed_tx_imm - reclaim completed control-queue Tx descs
  *	@q: the SGE control Tx queue
-- 
cgit v1.2.3


From c90d160487c4f82ba128730bcbaf7da760c5bdf1 Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Tue, 26 Jun 2018 17:10:50 +0530
Subject: cxgb4: Support ethtool private flags

This is used to change TX workrequests, which helps in
host->vf communication.

Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 42 ++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index f7eef93ffc87..ddb8b9eba6bf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -177,6 +177,10 @@ static char loopback_stats_strings[][ETH_GSTRING_LEN] = {
 	"bg3_frames_trunc       ",
 };
 
+static const char cxgb4_priv_flags_strings[][ETH_GSTRING_LEN] = {
+	[PRIV_FLAG_PORT_TX_VM_BIT] = "port_tx_vm_wr",
+};
+
 static int get_sset_count(struct net_device *dev, int sset)
 {
 	switch (sset) {
@@ -185,6 +189,8 @@ static int get_sset_count(struct net_device *dev, int sset)
 		       ARRAY_SIZE(adapter_stats_strings) +
 		       ARRAY_SIZE(channel_stats_strings) +
 		       ARRAY_SIZE(loopback_stats_strings);
+	case ETH_SS_PRIV_FLAGS:
+		return ARRAY_SIZE(cxgb4_priv_flags_strings);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -235,6 +241,7 @@ static void get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
 			 FW_HDR_FW_VER_MINOR_G(exprom_vers),
 			 FW_HDR_FW_VER_MICRO_G(exprom_vers),
 			 FW_HDR_FW_VER_BUILD_G(exprom_vers));
+	info->n_priv_flags = ARRAY_SIZE(cxgb4_priv_flags_strings);
 }
 
 static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
@@ -250,6 +257,9 @@ static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
 		data += sizeof(channel_stats_strings);
 		memcpy(data, loopback_stats_strings,
 		       sizeof(loopback_stats_strings));
+	} else if (stringset == ETH_SS_PRIV_FLAGS) {
+		memcpy(data, cxgb4_priv_flags_strings,
+		       sizeof(cxgb4_priv_flags_strings));
 	}
 }
 
@@ -1499,6 +1509,36 @@ static int cxgb4_get_module_eeprom(struct net_device *dev,
 			 offset, len, &data[eprom->len - len]);
 }
 
+static u32 cxgb4_get_priv_flags(struct net_device *netdev)
+{
+	struct port_info *pi = netdev_priv(netdev);
+	struct adapter *adapter = pi->adapter;
+
+	return (adapter->eth_flags | pi->eth_flags);
+}
+
+/**
+ *	set_flags - set/unset specified flags if passed in new_flags
+ *	@cur_flags: pointer to current flags
+ *	@new_flags: new incoming flags
+ *	@flags: set of flags to set/unset
+ */
+static inline void set_flags(u32 *cur_flags, u32 new_flags, u32 flags)
+{
+	*cur_flags = (*cur_flags & ~flags) | (new_flags & flags);
+}
+
+static int cxgb4_set_priv_flags(struct net_device *netdev, u32 flags)
+{
+	struct port_info *pi = netdev_priv(netdev);
+	struct adapter *adapter = pi->adapter;
+
+	set_flags(&adapter->eth_flags, flags, PRIV_FLAGS_ADAP);
+	set_flags(&pi->eth_flags, flags, PRIV_FLAGS_PORT);
+
+	return 0;
+}
+
 static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_link_ksettings = get_link_ksettings,
 	.set_link_ksettings = set_link_ksettings,
@@ -1535,6 +1575,8 @@ static const struct ethtool_ops cxgb_ethtool_ops = {
 	.get_dump_data     = get_dump_data,
 	.get_module_info   = cxgb4_get_module_info,
 	.get_module_eeprom = cxgb4_get_module_eeprom,
+	.get_priv_flags    = cxgb4_get_priv_flags,
+	.set_priv_flags    = cxgb4_set_priv_flags,
 };
 
 void cxgb4_set_ethtool_ops(struct net_device *netdev)
-- 
cgit v1.2.3


From a1165b591925551d7c8f1ed45484ebc2847ec8fa Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Tue, 26 Jun 2018 21:39:34 -0700
Subject: net/sched: act_tunnel_key: disambiguate metadata dst error cases

Metadata may be NULL for one of two reasons:
* Missing user input
* Failure to allocate the metadata dst

Disambiguate these case by returning -EINVAL for the former and -ENOMEM
for the latter rather than -EINVAL for both cases.

This is in preparation for using extended ack to provide more information
to users when parsing their input.

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 626dac81a48a..2edd389e7c92 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -143,10 +143,13 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port,
 						      0, flags,
 						      key_id, 0);
+		} else {
+			ret = -EINVAL;
+			goto err_out;
 		}
 
 		if (!metadata) {
-			ret = -EINVAL;
+			ret = -ENOMEM;
 			goto err_out;
 		}
 
-- 
cgit v1.2.3


From 9d7298cd1dc55ebe053686f9bce74bfdcc812399 Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Tue, 26 Jun 2018 21:39:35 -0700
Subject: net/sched: act_tunnel_key: add extended ack support

Add extended ack support for the tunnel key action by using NL_SET_ERR_MSG
during validation of user input.

Cc: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 27 +++++++++++++++++++++------
 1 file changed, 21 insertions(+), 6 deletions(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 2edd389e7c92..20e98ed8d498 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -86,16 +86,22 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	int ret = 0;
 	int err;
 
-	if (!nla)
+	if (!nla) {
+		NL_SET_ERR_MSG(extack, "Tunnel requires attributes to be passed");
 		return -EINVAL;
+	}
 
 	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_MAX, nla, tunnel_key_policy,
-			       NULL);
-	if (err < 0)
+			       extack);
+	if (err < 0) {
+		NL_SET_ERR_MSG(extack, "Failed to parse nested tunnel key attributes");
 		return err;
+	}
 
-	if (!tb[TCA_TUNNEL_KEY_PARMS])
+	if (!tb[TCA_TUNNEL_KEY_PARMS]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key parameters");
 		return -EINVAL;
+	}
 
 	parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
 	exists = tcf_idr_check(tn, parm->index, a, bind);
@@ -107,6 +113,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		break;
 	case TCA_TUNNEL_KEY_ACT_SET:
 		if (!tb[TCA_TUNNEL_KEY_ENC_KEY_ID]) {
+			NL_SET_ERR_MSG(extack, "Missing tunnel key id");
 			ret = -EINVAL;
 			goto err_out;
 		}
@@ -144,11 +151,13 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 						      0, flags,
 						      key_id, 0);
 		} else {
+			NL_SET_ERR_MSG(extack, "Missing either ipv4 or ipv6 src and dst");
 			ret = -EINVAL;
 			goto err_out;
 		}
 
 		if (!metadata) {
+			NL_SET_ERR_MSG(extack, "Cannot allocate tunnel metadata dst");
 			ret = -ENOMEM;
 			goto err_out;
 		}
@@ -156,6 +165,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
 		break;
 	default:
+		NL_SET_ERR_MSG(extack, "Unknown tunnel key action");
 		ret = -EINVAL;
 		goto err_out;
 	}
@@ -163,14 +173,18 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_tunnel_key_ops, bind, true);
-		if (ret)
+		if (ret) {
+			NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
 			return ret;
+		}
 
 		ret = ACT_P_CREATED;
 	} else {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			NL_SET_ERR_MSG(extack, "TC IDR already exists");
 			return -EEXIST;
+		}
 	}
 
 	t = to_tunnel_key(*a);
@@ -180,6 +194,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	if (unlikely(!params_new)) {
 		if (ret == ACT_P_CREATED)
 			tcf_idr_release(*a, bind);
+		NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters");
 		return -ENOMEM;
 	}
 
-- 
cgit v1.2.3


From 256c87c17c53e60882a43dcf3e98f3bf859eaf6f Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 26 Jun 2018 21:39:36 -0700
Subject: net: check tunnel option type in tunnel flags

Check the tunnel option type stored in tunnel flags when creating options
for tunnels. Thereby ensuring we do not set geneve, vxlan or erspan tunnel
options on interfaces that are not associated with them.

Make sure all users of the infrastructure set correct flags, for the BPF
helper we have to set all bits to keep backward compatibility.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/geneve.c           | 6 ++++--
 drivers/net/vxlan.c            | 3 ++-
 include/net/ip_tunnels.h       | 8 ++++++--
 net/core/filter.c              | 2 +-
 net/ipv4/ip_gre.c              | 2 ++
 net/ipv6/ip6_gre.c             | 2 ++
 net/openvswitch/flow_netlink.c | 7 ++++++-
 7 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 3e94375b9b01..471edd76ff55 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -236,7 +236,8 @@ static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
 		}
 		/* Update tunnel dst according to Geneve options. */
 		ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
-					gnvh->options, gnvh->opt_len * 4);
+					gnvh->options, gnvh->opt_len * 4,
+					TUNNEL_GENEVE_OPT);
 	} else {
 		/* Drop packets w/ critical options,
 		 * since we don't support any...
@@ -675,7 +676,8 @@ static void geneve_build_header(struct genevehdr *geneveh,
 	geneveh->proto_type = htons(ETH_P_TEB);
 	geneveh->rsvd2 = 0;
 
-	ip_tunnel_info_opts_get(geneveh->options, info);
+	if (info->key.tun_flags & TUNNEL_GENEVE_OPT)
+		ip_tunnel_info_opts_get(geneveh->options, info);
 }
 
 static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index cc14e0cd5647..7eb30d7c8bd7 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2122,7 +2122,8 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		vni = tunnel_id_to_key32(info->key.tun_id);
 		ifindex = 0;
 		dst_cache = &info->dst_cache;
-		if (info->options_len)
+		if (info->options_len &&
+		    info->key.tun_flags & TUNNEL_VXLAN_OPT)
 			md = ip_tunnel_info_opts(info);
 		ttl = info->key.ttl;
 		tos = info->key.tos;
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 90ff430f5e9d..b0d022ff6ea1 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -466,10 +466,12 @@ static inline void ip_tunnel_info_opts_get(void *to,
 }
 
 static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
-					   const void *from, int len)
+					   const void *from, int len,
+					   __be16 flags)
 {
 	memcpy(ip_tunnel_info_opts(info), from, len);
 	info->options_len = len;
+	info->key.tun_flags |= flags;
 }
 
 static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstate)
@@ -511,9 +513,11 @@ static inline void ip_tunnel_info_opts_get(void *to,
 }
 
 static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
-					   const void *from, int len)
+					   const void *from, int len,
+					   __be16 flags)
 {
 	info->options_len = 0;
+	info->key.tun_flags |= flags;
 }
 
 #endif /* CONFIG_INET */
diff --git a/net/core/filter.c b/net/core/filter.c
index e7f12e9f598c..dade922678f6 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3582,7 +3582,7 @@ BPF_CALL_3(bpf_skb_set_tunnel_opt, struct sk_buff *, skb,
 	if (unlikely(size > IP_TUNNEL_OPTS_MAX))
 		return -ENOMEM;
 
-	ip_tunnel_info_opts_set(info, from, size);
+	ip_tunnel_info_opts_set(info, from, size, TUNNEL_OPTIONS_PRESENT);
 
 	return 0;
 }
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2d8efeecf619..c8ca5d8f0f75 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -587,6 +587,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
 		goto err_free_skb;
 
 	key = &tun_info->key;
+	if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
+		goto err_free_rt;
 	md = ip_tunnel_info_opts(tun_info);
 	if (!md)
 		goto err_free_rt;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c8cf2fdbb13b..367177786e34 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -990,6 +990,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb,
 		fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL);
 
 		dsfield = key->tos;
+		if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT))
+			goto tx_err;
 		md = ip_tunnel_info_opts(tun_info);
 		if (!md)
 			goto tx_err;
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 492ab0c36f7c..391c4073a6dc 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2516,7 +2516,9 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	struct ovs_tunnel_info *ovs_tun;
 	struct nlattr *a;
 	int err = 0, start, opts_type;
+	__be16 dst_opt_type;
 
+	dst_opt_type = 0;
 	ovs_match_init(&match, &key, true, NULL);
 	opts_type = ip_tun_from_nlattr(nla_data(attr), &match, false, log);
 	if (opts_type < 0)
@@ -2528,10 +2530,13 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 			err = validate_geneve_opts(&key);
 			if (err < 0)
 				return err;
+			dst_opt_type = TUNNEL_GENEVE_OPT;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_VXLAN_OPTS:
+			dst_opt_type = TUNNEL_VXLAN_OPT;
 			break;
 		case OVS_TUNNEL_KEY_ATTR_ERSPAN_OPTS:
+			dst_opt_type = TUNNEL_ERSPAN_OPT;
 			break;
 		}
 	}
@@ -2574,7 +2579,7 @@ static int validate_and_copy_set_tun(const struct nlattr *attr,
 	 */
 	ip_tunnel_info_opts_set(tun_info,
 				TUN_METADATA_OPTS(&key, key.tun_opts_len),
-				key.tun_opts_len);
+				key.tun_opts_len, dst_opt_type);
 	add_nested_action_end(*sfa, start);
 
 	return err;
-- 
cgit v1.2.3


From 0ed5269f9e41f495c8e9020c85f5e1644c1afc57 Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Tue, 26 Jun 2018 21:39:37 -0700
Subject: net/sched: add tunnel option support to act_tunnel_key

Allow setting tunnel options using the act_tunnel_key action.

Options are expressed as class:type:data and multiple options
may be listed using a comma delimiter.

 # ip link add name geneve0 type geneve dstport 0 external
 # tc qdisc add dev eth0 ingress
 # tc filter add dev eth0 protocol ip parent ffff: \
     flower indev eth0 \
        ip_proto udp \
        action tunnel_key \
            set src_ip 10.0.99.192 \
            dst_ip 10.0.99.193 \
            dst_port 6081 \
            id 11 \
            geneve_opts 0102:80:00800022,0102:80:00800022 \
    action mirred egress redirect dev geneve0

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tc_act/tc_tunnel_key.h |  26 ++++
 net/sched/act_tunnel_key.c                | 214 +++++++++++++++++++++++++++++-
 2 files changed, 236 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index 72bbefe5d1d1..e284fec8c467 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -36,9 +36,35 @@ enum {
 	TCA_TUNNEL_KEY_PAD,
 	TCA_TUNNEL_KEY_ENC_DST_PORT,	/* be16 */
 	TCA_TUNNEL_KEY_NO_CSUM,		/* u8 */
+	TCA_TUNNEL_KEY_ENC_OPTS,	/* Nested TCA_TUNNEL_KEY_ENC_OPTS_
+					 * attributes
+					 */
 	__TCA_TUNNEL_KEY_MAX,
 };
 
 #define TCA_TUNNEL_KEY_MAX (__TCA_TUNNEL_KEY_MAX - 1)
 
+enum {
+	TCA_TUNNEL_KEY_ENC_OPTS_UNSPEC,
+	TCA_TUNNEL_KEY_ENC_OPTS_GENEVE,		/* Nested
+						 * TCA_TUNNEL_KEY_ENC_OPTS_
+						 * attributes
+						 */
+	__TCA_TUNNEL_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPTS_MAX (__TCA_TUNNEL_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_TUNNEL_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS,		/* be16 */
+	TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE,		/* u8 */
+	TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA,		/* 4 to 128 bytes */
+
+	__TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX \
+	(__TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX - 1)
+
 #endif
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 20e98ed8d498..ea203e386a92 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/skbuff.h>
 #include <linux/rtnetlink.h>
+#include <net/geneve.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
 #include <net/dst.h>
@@ -57,6 +58,135 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 	return action;
 }
 
+static const struct nla_policy
+enc_opts_policy[TCA_TUNNEL_KEY_ENC_OPTS_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPTS_GENEVE]	= { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+geneve_opt_policy[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1] = {
+	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]	   = { .type = NLA_U16 },
+	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]	   = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]	   = { .type = NLA_BINARY,
+						       .len = 128 },
+};
+
+static int
+tunnel_key_copy_geneve_opt(const struct nlattr *nla, void *dst, int dst_len,
+			   struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX + 1];
+	int err, data_len, opt_len;
+	u8 *data;
+
+	err = nla_parse_nested(tb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_MAX,
+			       nla, geneve_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS] ||
+	    !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE] ||
+	    !tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data");
+		return -EINVAL;
+	}
+
+	data = nla_data(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]);
+	data_len = nla_len(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA]);
+	if (data_len < 4) {
+		NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long");
+		return -ERANGE;
+	}
+	if (data_len % 4) {
+		NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long");
+		return -ERANGE;
+	}
+
+	opt_len = sizeof(struct geneve_opt) + data_len;
+	if (dst) {
+		struct geneve_opt *opt = dst;
+
+		WARN_ON(dst_len < opt_len);
+
+		opt->opt_class =
+			nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS]);
+		opt->type = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE]);
+		opt->length = data_len / 4; /* length is in units of 4 bytes */
+		opt->r1 = 0;
+		opt->r2 = 0;
+		opt->r3 = 0;
+
+		memcpy(opt + 1, data, data_len);
+	}
+
+	return opt_len;
+}
+
+static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst,
+				int dst_len, struct netlink_ext_ack *extack)
+{
+	int err, rem, opt_len, len = nla_len(nla), opts_len = 0;
+	const struct nlattr *attr, *head = nla_data(nla);
+
+	err = nla_validate(head, len, TCA_TUNNEL_KEY_ENC_OPTS_MAX,
+			   enc_opts_policy, extack);
+	if (err)
+		return err;
+
+	nla_for_each_attr(attr, head, len, rem) {
+		switch (nla_type(attr)) {
+		case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
+			opt_len = tunnel_key_copy_geneve_opt(attr, dst,
+							     dst_len, extack);
+			if (opt_len < 0)
+				return opt_len;
+			opts_len += opt_len;
+			if (dst) {
+				dst_len -= opt_len;
+				dst += opt_len;
+			}
+			break;
+		}
+	}
+
+	if (!opts_len) {
+		NL_SET_ERR_MSG(extack, "Empty list of tunnel options");
+		return -EINVAL;
+	}
+
+	if (rem > 0) {
+		NL_SET_ERR_MSG(extack, "Trailing data after parsing tunnel key options attributes");
+		return -EINVAL;
+	}
+
+	return opts_len;
+}
+
+static int tunnel_key_get_opts_len(struct nlattr *nla,
+				   struct netlink_ext_ack *extack)
+{
+	return tunnel_key_copy_opts(nla, NULL, 0, extack);
+}
+
+static int tunnel_key_opts_set(struct nlattr *nla, struct ip_tunnel_info *info,
+			       int opts_len, struct netlink_ext_ack *extack)
+{
+	info->options_len = opts_len;
+	switch (nla_type(nla_data(nla))) {
+	case TCA_TUNNEL_KEY_ENC_OPTS_GENEVE:
+#if IS_ENABLED(CONFIG_INET)
+		info->key.tun_flags |= TUNNEL_GENEVE_OPT;
+		return tunnel_key_copy_opts(nla, ip_tunnel_info_opts(info),
+					    opts_len, extack);
+#else
+		return -EAFNOSUPPORT;
+#endif
+	default:
+		NL_SET_ERR_MSG(extack, "Cannot set tunnel options for unknown tunnel type");
+		return -EINVAL;
+	}
+}
+
 static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 	[TCA_TUNNEL_KEY_PARMS]	    = { .len = sizeof(struct tc_tunnel_key) },
 	[TCA_TUNNEL_KEY_ENC_IPV4_SRC] = { .type = NLA_U32 },
@@ -66,6 +196,7 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_KEY_ID]   = { .type = NLA_U32 },
 	[TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16},
 	[TCA_TUNNEL_KEY_NO_CSUM]      = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_OPTS]     = { .type = NLA_NESTED },
 };
 
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
@@ -81,6 +212,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	struct tcf_tunnel_key *t;
 	bool exists = false;
 	__be16 dst_port = 0;
+	int opts_len = 0;
 	__be64 key_id;
 	__be16 flags;
 	int ret = 0;
@@ -128,6 +260,15 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		if (tb[TCA_TUNNEL_KEY_ENC_DST_PORT])
 			dst_port = nla_get_be16(tb[TCA_TUNNEL_KEY_ENC_DST_PORT]);
 
+		if (tb[TCA_TUNNEL_KEY_ENC_OPTS]) {
+			opts_len = tunnel_key_get_opts_len(tb[TCA_TUNNEL_KEY_ENC_OPTS],
+							   extack);
+			if (opts_len < 0) {
+				ret = opts_len;
+				goto err_out;
+			}
+		}
+
 		if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
 		    tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
 			__be32 saddr;
@@ -138,7 +279,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 
 			metadata = __ip_tun_set_dst(saddr, daddr, 0, 0,
 						    dst_port, flags,
-						    key_id, 0);
+						    key_id, opts_len);
 		} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
 			   tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]) {
 			struct in6_addr saddr;
@@ -162,6 +303,14 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			goto err_out;
 		}
 
+		if (opts_len) {
+			ret = tunnel_key_opts_set(tb[TCA_TUNNEL_KEY_ENC_OPTS],
+						  &metadata->u.tun_info,
+						  opts_len, extack);
+			if (ret < 0)
+				goto err_out;
+		}
+
 		metadata->u.tun_info.mode |= IP_TUNNEL_INFO_TX;
 		break;
 	default:
@@ -234,6 +383,61 @@ static void tunnel_key_release(struct tc_action *a)
 	}
 }
 
+static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
+				       const struct ip_tunnel_info *info)
+{
+	int len = info->options_len;
+	u8 *src = (u8 *)(info + 1);
+	struct nlattr *start;
+
+	start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE);
+	if (!start)
+		return -EMSGSIZE;
+
+	while (len > 0) {
+		struct geneve_opt *opt = (struct geneve_opt *)src;
+
+		if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS,
+				 opt->opt_class) ||
+		    nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_TYPE,
+			       opt->type) ||
+		    nla_put(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_DATA,
+			    opt->length * 4, opt + 1))
+			return -EMSGSIZE;
+
+		len -= sizeof(struct geneve_opt) + opt->length * 4;
+		src += sizeof(struct geneve_opt) + opt->length * 4;
+	}
+
+	nla_nest_end(skb, start);
+	return 0;
+}
+
+static int tunnel_key_opts_dump(struct sk_buff *skb,
+				const struct ip_tunnel_info *info)
+{
+	struct nlattr *start;
+	int err;
+
+	if (!info->options_len)
+		return 0;
+
+	start = nla_nest_start(skb, TCA_TUNNEL_KEY_ENC_OPTS);
+	if (!start)
+		return -EMSGSIZE;
+
+	if (info->key.tun_flags & TUNNEL_GENEVE_OPT) {
+		err = tunnel_key_geneve_opts_dump(skb, info);
+		if (err)
+			return err;
+	} else {
+		return -EINVAL;
+	}
+
+	nla_nest_end(skb, start);
+	return 0;
+}
+
 static int tunnel_key_dump_addresses(struct sk_buff *skb,
 				     const struct ip_tunnel_info *info)
 {
@@ -284,8 +488,9 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 		goto nla_put_failure;
 
 	if (params->tcft_action == TCA_TUNNEL_KEY_ACT_SET) {
-		struct ip_tunnel_key *key =
-			&params->tcft_enc_metadata->u.tun_info.key;
+		struct ip_tunnel_info *info =
+			&params->tcft_enc_metadata->u.tun_info;
+		struct ip_tunnel_key *key = &info->key;
 		__be32 key_id = tunnel_id_to_key32(key->tun_id);
 
 		if (nla_put_be32(skb, TCA_TUNNEL_KEY_ENC_KEY_ID, key_id) ||
@@ -293,7 +498,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 					      &params->tcft_enc_metadata->u.tun_info) ||
 		    nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_DST_PORT, key->tp_dst) ||
 		    nla_put_u8(skb, TCA_TUNNEL_KEY_NO_CSUM,
-			       !(key->tun_flags & TUNNEL_CSUM)))
+			       !(key->tun_flags & TUNNEL_CSUM)) ||
+		    tunnel_key_opts_dump(skb, info))
 			goto nla_put_failure;
 	}
 
-- 
cgit v1.2.3


From 8ab1416a6d51a6cbc4875b496f01f70dc43612f8 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 29 Jun 2018 14:52:01 +0200
Subject: doc: dev-tools: kselftest.rst: update contributing new tests

Add a description that kernel config options should be added into a
config file that is placed next to the newly added test.

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Reviewed-by: Shuah Khan (Samsung OSG) <shuah@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/dev-tools/kselftest.rst | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/dev-tools/kselftest.rst b/Documentation/dev-tools/kselftest.rst
index 3bf371a938d0..6f653acea248 100644
--- a/Documentation/dev-tools/kselftest.rst
+++ b/Documentation/dev-tools/kselftest.rst
@@ -156,6 +156,11 @@ Contributing new tests (details)
    installed by the distro on the system should be the primary focus to be able
    to find regressions.
 
+ * If a test needs specific kernel config options enabled, add a config file in
+   the test directory to enable them.
+
+   e.g: tools/testing/selftests/android/ion/config
+
 Test Harness
 ============
 
-- 
cgit v1.2.3


From 351f10a3ce93dc3db29f8ab1ce4173115dadd3d3 Mon Sep 17 00:00:00 2001
From: Michael Rodin <michael-git@rodin.online>
Date: Sun, 3 Jun 2018 20:16:09 +0200
Subject: Documentation/admin-guide/README.rst: add a label for
 cross-referencing

Add a label to the top of the file to allow cross-referencing.
Currently it's not possible to cross-reference this file from
Documentation/process/howto.rst because of the missing label.

Signed-off-by: Michael Rodin <michael-git@rodin.online>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/admin-guide/README.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index 02caa7efd5ef..15ea785b2dfa 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -1,3 +1,5 @@
+.. _readme:
+
 Linux kernel release 4.x <http://kernel.org/>
 =============================================
 
-- 
cgit v1.2.3


From dad05139541359d61ea0850a7fc5311d9ca560f0 Mon Sep 17 00:00:00 2001
From: Michael Rodin <michael-git@rodin.online>
Date: Sun, 3 Jun 2018 20:17:33 +0200
Subject: Documentation/process/howto.rst: add a missing cross-reference

Add a missing cross-reference from Documentation/process/howto.rst
to Documentation/admin-guide/README.rst.

Signed-off-by: Michael Rodin <michael-git@rodin.online>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/process/howto.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/process/howto.rst b/Documentation/process/howto.rst
index 3df55811b916..130bf0f48875 100644
--- a/Documentation/process/howto.rst
+++ b/Documentation/process/howto.rst
@@ -85,7 +85,7 @@ linux-api@vger.kernel.org.
 Here is a list of files that are in the kernel source tree that are
 required reading:
 
-  README
+  :ref:`Documentation/admin-guide/README.rst <readme>`
     This file gives a short background on the Linux kernel and describes
     what is necessary to do to configure and build the kernel.  People
     who are new to the kernel should start here.
-- 
cgit v1.2.3


From 7403bd14d7b545ef89c3443c09ccdb3c631a9a27 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sun, 18 Mar 2018 22:53:28 +0800
Subject: PCI: hv: Replace GFP_ATOMIC with GFP_KERNEL in new_pcichild_device()

new_pcichild_device() is not called in atomic context.

The call chain ending up at new_pcichild_device() is:
[1] new_pcichild_device() <- pci_devices_present_work()
pci_devices_present_work() is only set in INIT_WORK().

Despite never getting called from atomic context,
new_pcichild_device() calls kzalloc with GFP_ATOMIC,
which waits busily for allocation.

GFP_ATOMIC is not necessary and can be replaced with GFP_KERNEL
to avoid busy waiting.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
[lorenzo.pieralisi@arm.com: reworked commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
---
 drivers/pci/controller/pci-hyperv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 6cc5036ac83c..ba1d4b556064 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1543,7 +1543,7 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus,
 	unsigned long flags;
 	int ret;
 
-	hpdev = kzalloc(sizeof(*hpdev), GFP_ATOMIC);
+	hpdev = kzalloc(sizeof(*hpdev), GFP_KERNEL);
 	if (!hpdev)
 		return NULL;
 
-- 
cgit v1.2.3


From e8f127caf63ad29e2b4cb01894b97730384ad1ab Mon Sep 17 00:00:00 2001
From: Mike Looijmans <mike.looijmans@topic.nl>
Date: Mon, 4 Jun 2018 07:34:39 +0200
Subject: clk-si514, clk-si544: Implement prepare/unprepare/is_prepared
 operations

This adds prepare/unprepare/is_prepared functionality to the drivers for
the SI544 and SI514 chips, allowing the clock output to be disabled when
the clock is not in use.

Signed-off-by: Mike Looijmans <mike.looijmans@topic.nl>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-si514.c | 38 +++++++++++++++++++++++++++++++++++++-
 drivers/clk/clk-si544.c | 38 +++++++++++++++++++++++++++++++++++++-
 2 files changed, 74 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/clk-si514.c b/drivers/clk/clk-si514.c
index 09b6718956bd..153b3a2b5857 100644
--- a/drivers/clk/clk-si514.c
+++ b/drivers/clk/clk-si514.c
@@ -74,6 +74,33 @@ static int si514_enable_output(struct clk_si514 *data, bool enable)
 		SI514_CONTROL_OE, enable ? SI514_CONTROL_OE : 0);
 }
 
+static int si514_prepare(struct clk_hw *hw)
+{
+	struct clk_si514 *data = to_clk_si514(hw);
+
+	return si514_enable_output(data, true);
+}
+
+static void si514_unprepare(struct clk_hw *hw)
+{
+	struct clk_si514 *data = to_clk_si514(hw);
+
+	si514_enable_output(data, false);
+}
+
+static int si514_is_prepared(struct clk_hw *hw)
+{
+	struct clk_si514 *data = to_clk_si514(hw);
+	unsigned int val;
+	int err;
+
+	err = regmap_read(data->regmap, SI514_REG_CONTROL, &val);
+	if (err < 0)
+		return err;
+
+	return !!(val & SI514_CONTROL_OE);
+}
+
 /* Retrieve clock multiplier and dividers from hardware */
 static int si514_get_muldiv(struct clk_si514 *data,
 	struct clk_si514_muldiv *settings)
@@ -235,12 +262,17 @@ static int si514_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct clk_si514 *data = to_clk_si514(hw);
 	struct clk_si514_muldiv settings;
+	unsigned int old_oe_state;
 	int err;
 
 	err = si514_calc_muldiv(&settings, rate);
 	if (err)
 		return err;
 
+	err = regmap_read(data->regmap, SI514_REG_CONTROL, &old_oe_state);
+	if (err)
+		return err;
+
 	si514_enable_output(data, false);
 
 	err = si514_set_muldiv(data, &settings);
@@ -255,12 +287,16 @@ static int si514_set_rate(struct clk_hw *hw, unsigned long rate,
 	/* Applying a new frequency can take up to 10ms */
 	usleep_range(10000, 12000);
 
-	si514_enable_output(data, true);
+	if (old_oe_state & SI514_CONTROL_OE)
+		si514_enable_output(data, true);
 
 	return err;
 }
 
 static const struct clk_ops si514_clk_ops = {
+	.prepare = si514_prepare,
+	.unprepare = si514_unprepare,
+	.is_prepared = si514_is_prepared,
 	.recalc_rate = si514_recalc_rate,
 	.round_rate = si514_round_rate,
 	.set_rate = si514_set_rate,
diff --git a/drivers/clk/clk-si544.c b/drivers/clk/clk-si544.c
index 1e2a3b8f9454..64e607f3232a 100644
--- a/drivers/clk/clk-si544.c
+++ b/drivers/clk/clk-si544.c
@@ -86,6 +86,33 @@ static int si544_enable_output(struct clk_si544 *data, bool enable)
 		SI544_OE_STATE_ODC_OE, enable ? SI544_OE_STATE_ODC_OE : 0);
 }
 
+static int si544_prepare(struct clk_hw *hw)
+{
+	struct clk_si544 *data = to_clk_si544(hw);
+
+	return si544_enable_output(data, true);
+}
+
+static void si544_unprepare(struct clk_hw *hw)
+{
+	struct clk_si544 *data = to_clk_si544(hw);
+
+	si544_enable_output(data, false);
+}
+
+static int si544_is_prepared(struct clk_hw *hw)
+{
+	struct clk_si544 *data = to_clk_si544(hw);
+	unsigned int val;
+	int err;
+
+	err = regmap_read(data->regmap, SI544_REG_OE_STATE, &val);
+	if (err < 0)
+		return err;
+
+	return !!(val & SI544_OE_STATE_ODC_OE);
+}
+
 /* Retrieve clock multiplier and dividers from hardware */
 static int si544_get_muldiv(struct clk_si544 *data,
 	struct clk_si544_muldiv *settings)
@@ -273,6 +300,7 @@ static int si544_set_rate(struct clk_hw *hw, unsigned long rate,
 {
 	struct clk_si544 *data = to_clk_si544(hw);
 	struct clk_si544_muldiv settings;
+	unsigned int old_oe_state;
 	int err;
 
 	if (!is_valid_frequency(data, rate))
@@ -282,6 +310,10 @@ static int si544_set_rate(struct clk_hw *hw, unsigned long rate,
 	if (err)
 		return err;
 
+	err = regmap_read(data->regmap, SI544_REG_OE_STATE, &old_oe_state);
+	if (err)
+		return err;
+
 	si544_enable_output(data, false);
 
 	/* Allow FCAL for this frequency update */
@@ -303,12 +335,16 @@ static int si544_set_rate(struct clk_hw *hw, unsigned long rate,
 	/* Applying a new frequency can take up to 10ms */
 	usleep_range(10000, 12000);
 
-	si544_enable_output(data, true);
+	if (old_oe_state & SI544_OE_STATE_ODC_OE)
+		si544_enable_output(data, true);
 
 	return err;
 }
 
 static const struct clk_ops si544_clk_ops = {
+	.prepare = si544_prepare,
+	.unprepare = si544_unprepare,
+	.is_prepared = si544_is_prepared,
 	.recalc_rate = si544_recalc_rate,
 	.round_rate = si544_round_rate,
 	.set_rate = si544_set_rate,
-- 
cgit v1.2.3


From 54614d1218fdf5ccf87ac1499514755fd9c4a179 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Mon, 4 Jun 2018 09:06:43 +0800
Subject: clk: imx6q: remove clks_init_on array

Clock framework will enable those clocks registered
with CLK_IS_CRITICAL flag, so no need to have
clks_init_on array during clock initialization now.

ARM clock is busy divider type which has the
CLK_IS_CRITICAL flag set by default when registered.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6q.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index b9ea7037e193..8754c6197ef6 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -96,12 +96,6 @@ static const char *pll7_bypass_sels[] = { "pll7", "pll7_bypass_src", };
 static struct clk *clk[IMX6QDL_CLK_END];
 static struct clk_onecell_data clk_data;
 
-static unsigned int const clks_init_on[] __initconst = {
-	IMX6QDL_CLK_MMDC_CH0_AXI,
-	IMX6QDL_CLK_ROM,
-	IMX6QDL_CLK_ARM,
-};
-
 static struct clk_div_table clk_enet_ref_table[] = {
 	{ .val = 0, .div = 20, },
 	{ .val = 1, .div = 10, },
@@ -417,7 +411,6 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *anatop_base, *base;
-	int i;
 	int ret;
 
 	clk[IMX6QDL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
@@ -794,7 +787,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 		clk[IMX6QDL_CLK_MLB] = imx_clk_gate2("mlb",            "mlb_podf",   base + 0x74, 18);
 	else
 		clk[IMX6QDL_CLK_MLB] = imx_clk_gate2("mlb",            "axi",               base + 0x74, 18);
-	clk[IMX6QDL_CLK_MMDC_CH0_AXI] = imx_clk_gate2("mmdc_ch0_axi",  "mmdc_ch0_axi_podf", base + 0x74, 20);
+	clk[IMX6QDL_CLK_MMDC_CH0_AXI] = imx_clk_gate2_flags("mmdc_ch0_axi",  "mmdc_ch0_axi_podf", base + 0x74, 20, CLK_IS_CRITICAL);
 	clk[IMX6QDL_CLK_MMDC_CH1_AXI] = imx_clk_gate2("mmdc_ch1_axi",  "mmdc_ch1_axi_podf", base + 0x74, 22);
 	clk[IMX6QDL_CLK_OCRAM]        = imx_clk_gate2("ocram",         "ahb",               base + 0x74, 28);
 	clk[IMX6QDL_CLK_OPENVG_AXI]   = imx_clk_gate2("openvg_axi",    "axi",               base + 0x74, 30);
@@ -808,7 +801,7 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	clk[IMX6QDL_CLK_GPMI_BCH]     = imx_clk_gate2("gpmi_bch",      "usdhc4",            base + 0x78, 26);
 	clk[IMX6QDL_CLK_GPMI_IO]      = imx_clk_gate2("gpmi_io",       "enfc",              base + 0x78, 28);
 	clk[IMX6QDL_CLK_GPMI_APB]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
-	clk[IMX6QDL_CLK_ROM]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
+	clk[IMX6QDL_CLK_ROM]          = imx_clk_gate2_flags("rom",     "ahb",               base + 0x7c, 0, CLK_IS_CRITICAL);
 	clk[IMX6QDL_CLK_SATA]         = imx_clk_gate2("sata",          "ahb",               base + 0x7c, 4);
 	clk[IMX6QDL_CLK_SDMA]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clk[IMX6QDL_CLK_SPBA]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
@@ -878,9 +871,6 @@ static void __init imx6q_clocks_init(struct device_node *ccm_node)
 	 */
 	clk_set_parent(clk[IMX6QDL_CLK_ENFC_SEL], clk[IMX6QDL_CLK_PLL2_PFD2_396M]);
 
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clk[clks_init_on[i]]);
-
 	if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
 		clk_prepare_enable(clk[IMX6QDL_CLK_USBPHY1_GATE]);
 		clk_prepare_enable(clk[IMX6QDL_CLK_USBPHY2_GATE]);
-- 
cgit v1.2.3


From 8e12ce99541bdf5ec7cee08683bf455d8c882e49 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Mon, 4 Jun 2018 09:06:44 +0800
Subject: clk: imx6sl: remove clks_init_on array

Clock framework will enable those clocks registered
with CLK_IS_CRITICAL flag, so no need to have
clks_init_on array during clock initialization now.

ARM clock is busy divider type which has the
CLK_IS_CRITICAL flag set by default when registered.

IPG clock has no clock gate and its parent AHB clock
is busy divider type, so no need to add CLK_IS_CRITICAL
flag for IPG clock.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6sl.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/clk/imx/clk-imx6sl.c b/drivers/clk/imx/clk-imx6sl.c
index 66b1dd1cfad0..eb6bcbf345a3 100644
--- a/drivers/clk/imx/clk-imx6sl.c
+++ b/drivers/clk/imx/clk-imx6sl.c
@@ -104,10 +104,6 @@ static struct clk_onecell_data clk_data;
 static void __iomem *ccm_base;
 static void __iomem *anatop_base;
 
-static const u32 clks_init_on[] __initconst = {
-	IMX6SL_CLK_IPG, IMX6SL_CLK_ARM, IMX6SL_CLK_MMDC_ROOT,
-};
-
 /*
  * ERR005311 CCM: After exit from WAIT mode, unwanted interrupt(s) taken
  *           during WAIT mode entry process could cause cache memory
@@ -195,7 +191,6 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *base;
-	int i;
 	int ret;
 
 	clks[IMX6SL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
@@ -426,13 +421,6 @@ static void __init imx6sl_clocks_init(struct device_node *ccm_node)
 		pr_warn("%s: failed to set AHB clock rate %d!\n",
 			__func__, ret);
 
-	/*
-	 * Make sure those always on clocks are enabled to maintain the correct
-	 * usecount and enabling/disabling of parent PLLs.
-	 */
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clks[clks_init_on[i]]);
-
 	if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
 		clk_prepare_enable(clks[IMX6SL_CLK_USBPHY1_GATE]);
 		clk_prepare_enable(clks[IMX6SL_CLK_USBPHY2_GATE]);
-- 
cgit v1.2.3


From 566f5b67fc0c3bffec03a963334eb7c1df30204d Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Mon, 4 Jun 2018 09:06:45 +0800
Subject: clk: imx6sx: remove clks_init_on array

Clock framework will enable those clocks registered
with CLK_IS_CRITICAL flag, so no need to have
clks_init_on array during clock initialization now.

ARM clock is busy divider type which has the
CLK_IS_CRITICAL flag set by default when registered.

IPG clock has no clock gate and its parent AHB clock
is busy divider type, so no need to add CLK_IS_CRITICAL
flag for IPG clock.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6sx.c | 40 ++++++++++++++--------------------------
 1 file changed, 14 insertions(+), 26 deletions(-)

diff --git a/drivers/clk/imx/clk-imx6sx.c b/drivers/clk/imx/clk-imx6sx.c
index 10c771b91ef6..aed43910e26e 100644
--- a/drivers/clk/imx/clk-imx6sx.c
+++ b/drivers/clk/imx/clk-imx6sx.c
@@ -92,14 +92,6 @@ static const char *pll7_bypass_sels[] = { "pll7", "pll7_bypass_src", };
 static struct clk *clks[IMX6SX_CLK_CLK_END];
 static struct clk_onecell_data clk_data;
 
-static int const clks_init_on[] __initconst = {
-	IMX6SX_CLK_AIPS_TZ1, IMX6SX_CLK_AIPS_TZ2, IMX6SX_CLK_AIPS_TZ3,
-	IMX6SX_CLK_IPMUX1, IMX6SX_CLK_IPMUX2, IMX6SX_CLK_IPMUX3,
-	IMX6SX_CLK_WAKEUP, IMX6SX_CLK_MMDC_P0_FAST, IMX6SX_CLK_MMDC_P0_IPG,
-	IMX6SX_CLK_ROM, IMX6SX_CLK_ARM, IMX6SX_CLK_IPG, IMX6SX_CLK_OCRAM,
-	IMX6SX_CLK_PER2_MAIN, IMX6SX_CLK_PERCLK, IMX6SX_CLK_TZASC1,
-};
-
 static const struct clk_div_table clk_enet_ref_table[] = {
 	{ .val = 0, .div = 20, },
 	{ .val = 1, .div = 10, },
@@ -142,7 +134,6 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *base;
-	int i;
 
 	clks[IMX6SX_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
 
@@ -332,7 +323,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_QSPI1_PODF]         = imx_clk_divider("qspi1_podf",     "qspi1_sel",         base + 0x1c, 26,   3);
 	clks[IMX6SX_CLK_EIM_SLOW_PODF]      = imx_clk_divider("eim_slow_podf",  "eim_slow_sel",      base + 0x1c, 23,   3);
 	clks[IMX6SX_CLK_LCDIF2_PODF]        = imx_clk_divider("lcdif2_podf",    "lcdif2_pred",       base + 0x1c, 20,   3);
-	clks[IMX6SX_CLK_PERCLK]             = imx_clk_divider("perclk",         "perclk_sel",        base + 0x1c, 0,    6);
+	clks[IMX6SX_CLK_PERCLK]             = imx_clk_divider_flags("perclk", "perclk_sel", base + 0x1c, 0, 6, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_VID_PODF]           = imx_clk_divider("vid_podf",       "vid_sel",           base + 0x20, 24,   2);
 	clks[IMX6SX_CLK_CAN_PODF]           = imx_clk_divider("can_podf",       "can_sel",           base + 0x20, 2,    6);
 	clks[IMX6SX_CLK_USDHC4_PODF]        = imx_clk_divider("usdhc4_podf",    "usdhc4_sel",        base + 0x24, 22,   3);
@@ -380,8 +371,8 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 
 	/*                                            name             parent_name          reg         shift */
 	/* CCGR0 */
-	clks[IMX6SX_CLK_AIPS_TZ1]     = imx_clk_gate2("aips_tz1",      "ahb",               base + 0x68, 0);
-	clks[IMX6SX_CLK_AIPS_TZ2]     = imx_clk_gate2("aips_tz2",      "ahb",               base + 0x68, 2);
+	clks[IMX6SX_CLK_AIPS_TZ1]     = imx_clk_gate2_flags("aips_tz1", "ahb", base + 0x68, 0, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_AIPS_TZ2]     = imx_clk_gate2_flags("aips_tz2", "ahb", base + 0x68, 2, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_APBH_DMA]     = imx_clk_gate2("apbh_dma",      "usdhc3",            base + 0x68, 4);
 	clks[IMX6SX_CLK_ASRC_MEM]     = imx_clk_gate2_shared("asrc_mem", "ahb",             base + 0x68, 6, &share_count_asrc);
 	clks[IMX6SX_CLK_ASRC_IPG]     = imx_clk_gate2_shared("asrc_ipg", "ahb",             base + 0x68, 6, &share_count_asrc);
@@ -394,7 +385,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_CAN2_SERIAL]  = imx_clk_gate2("can2_serial",   "can_podf",          base + 0x68, 20);
 	clks[IMX6SX_CLK_DCIC1]        = imx_clk_gate2("dcic1",         "display_podf",      base + 0x68, 24);
 	clks[IMX6SX_CLK_DCIC2]        = imx_clk_gate2("dcic2",         "display_podf",      base + 0x68, 26);
-	clks[IMX6SX_CLK_AIPS_TZ3]     = imx_clk_gate2("aips_tz3",      "ahb",               base + 0x68, 30);
+	clks[IMX6SX_CLK_AIPS_TZ3]     = imx_clk_gate2_flags("aips_tz3", "ahb", base + 0x68, 30, CLK_IS_CRITICAL);
 
 	/* CCGR1 */
 	clks[IMX6SX_CLK_ECSPI1]       = imx_clk_gate2("ecspi1",        "ecspi_podf",        base + 0x6c, 0);
@@ -407,7 +398,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_ESAI_EXTAL]   = imx_clk_gate2_shared("esai_extal", "esai_podf",     base + 0x6c, 16, &share_count_esai);
 	clks[IMX6SX_CLK_ESAI_IPG]     = imx_clk_gate2_shared("esai_ipg",   "ahb",           base + 0x6c, 16, &share_count_esai);
 	clks[IMX6SX_CLK_ESAI_MEM]     = imx_clk_gate2_shared("esai_mem",   "ahb",           base + 0x6c, 16, &share_count_esai);
-	clks[IMX6SX_CLK_WAKEUP]       = imx_clk_gate2("wakeup",        "ipg",               base + 0x6c, 18);
+	clks[IMX6SX_CLK_WAKEUP]       = imx_clk_gate2_flags("wakeup", "ipg", base + 0x6c, 18, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_GPT_BUS]      = imx_clk_gate2("gpt_bus",       "perclk",            base + 0x6c, 20);
 	clks[IMX6SX_CLK_GPT_SERIAL]   = imx_clk_gate2("gpt_serial",    "perclk",            base + 0x6c, 22);
 	clks[IMX6SX_CLK_GPU]          = imx_clk_gate2("gpu",           "gpu_core_podf",     base + 0x6c, 26);
@@ -420,10 +411,10 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_I2C3]         = imx_clk_gate2("i2c3",          "perclk",            base + 0x70, 10);
 	clks[IMX6SX_CLK_OCOTP]        = imx_clk_gate2("ocotp",         "ipg",               base + 0x70, 12);
 	clks[IMX6SX_CLK_IOMUXC]       = imx_clk_gate2("iomuxc",        "lcdif1_podf",       base + 0x70, 14);
-	clks[IMX6SX_CLK_IPMUX1]       = imx_clk_gate2("ipmux1",        "ahb",               base + 0x70, 16);
-	clks[IMX6SX_CLK_IPMUX2]       = imx_clk_gate2("ipmux2",        "ahb",               base + 0x70, 18);
-	clks[IMX6SX_CLK_IPMUX3]       = imx_clk_gate2("ipmux3",        "ahb",               base + 0x70, 20);
-	clks[IMX6SX_CLK_TZASC1]       = imx_clk_gate2("tzasc1",        "mmdc_podf",         base + 0x70, 22);
+	clks[IMX6SX_CLK_IPMUX1]       = imx_clk_gate2_flags("ipmux1", "ahb", base + 0x70, 16, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_IPMUX2]       = imx_clk_gate2_flags("ipmux2", "ahb", base + 0x70, 18, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_IPMUX3]       = imx_clk_gate2_flags("ipmux3", "ahb", base + 0x70, 20, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_TZASC1]       = imx_clk_gate2_flags("tzasc1", "mmdc_podf", base + 0x70, 22, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_LCDIF_APB]    = imx_clk_gate2("lcdif_apb",     "display_podf",      base + 0x70, 28);
 	clks[IMX6SX_CLK_PXP_AXI]      = imx_clk_gate2("pxp_axi",       "display_podf",      base + 0x70, 30);
 
@@ -437,15 +428,15 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_LDB_DI0]      = imx_clk_gate2("ldb_di0",       "ldb_di0_div_sel",   base + 0x74, 12);
 	clks[IMX6SX_CLK_QSPI1]        = imx_clk_gate2("qspi1",         "qspi1_podf",        base + 0x74, 14);
 	clks[IMX6SX_CLK_MLB]          = imx_clk_gate2("mlb",           "ahb",               base + 0x74, 18);
-	clks[IMX6SX_CLK_MMDC_P0_FAST] = imx_clk_gate2("mmdc_p0_fast",  "mmdc_podf",         base + 0x74, 20);
-	clks[IMX6SX_CLK_MMDC_P0_IPG]  = imx_clk_gate2("mmdc_p0_ipg",   "ipg",               base + 0x74, 24);
-	clks[IMX6SX_CLK_OCRAM]        = imx_clk_gate2("ocram",         "ocram_podf",        base + 0x74, 28);
+	clks[IMX6SX_CLK_MMDC_P0_FAST] = imx_clk_gate2_flags("mmdc_p0_fast", "mmdc_podf", base + 0x74, 20, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_MMDC_P0_IPG]  = imx_clk_gate2_flags("mmdc_p0_ipg", "ipg", base + 0x74, 24, CLK_IS_CRITICAL);
+	clks[IMX6SX_CLK_OCRAM]        = imx_clk_gate2_flags("ocram", "ocram_podf", base + 0x74, 28, CLK_IS_CRITICAL);
 
 	/* CCGR4 */
 	clks[IMX6SX_CLK_PCIE_AXI]     = imx_clk_gate2("pcie_axi",      "display_podf",      base + 0x78, 0);
 	clks[IMX6SX_CLK_QSPI2]        = imx_clk_gate2("qspi2",         "qspi2_podf",        base + 0x78, 10);
 	clks[IMX6SX_CLK_PER1_BCH]     = imx_clk_gate2("per1_bch",      "usdhc3",            base + 0x78, 12);
-	clks[IMX6SX_CLK_PER2_MAIN]    = imx_clk_gate2("per2_main",     "ahb",               base + 0x78, 14);
+	clks[IMX6SX_CLK_PER2_MAIN]    = imx_clk_gate2_flags("per2_main", "ahb", base + 0x78, 14, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_PWM1]         = imx_clk_gate2("pwm1",          "perclk",            base + 0x78, 16);
 	clks[IMX6SX_CLK_PWM2]         = imx_clk_gate2("pwm2",          "perclk",            base + 0x78, 18);
 	clks[IMX6SX_CLK_PWM3]         = imx_clk_gate2("pwm3",          "perclk",            base + 0x78, 20);
@@ -456,7 +447,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_GPMI_APB]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
 
 	/* CCGR5 */
-	clks[IMX6SX_CLK_ROM]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
+	clks[IMX6SX_CLK_ROM]          = imx_clk_gate2_flags("rom", "ahb", base + 0x7c, 0, CLK_IS_CRITICAL);
 	clks[IMX6SX_CLK_SDMA]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clks[IMX6SX_CLK_SPBA]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
 	clks[IMX6SX_CLK_AUDIO]        = imx_clk_gate2_shared("audio",  "audio_podf",        base + 0x7c, 14, &share_count_audio);
@@ -502,9 +493,6 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clk_data.clk_num = ARRAY_SIZE(clks);
 	of_clk_add_provider(np, of_clk_src_onecell_get, &clk_data);
 
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clks[clks_init_on[i]]);
-
 	if (IS_ENABLED(CONFIG_USB_MXS_PHY)) {
 		clk_prepare_enable(clks[IMX6SX_CLK_USBPHY1_GATE]);
 		clk_prepare_enable(clks[IMX6SX_CLK_USBPHY2_GATE]);
-- 
cgit v1.2.3


From 222bce5eb88d1af656419db04bcd84b2419fb900 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Fri, 29 Jun 2018 19:07:42 +0200
Subject: ALSA: snd-aoa: add of_node_put() in error path

 Both calls to of_find_node_by_name() and of_get_next_child() return a
node pointer with refcount incremented thus it must be explicidly
decremented here after the last usage. As we are assured to have a
refcounted  np  either from the initial
of_find_node_by_name(NULL, name); or from the of_get_next_child(gpio, np)
in the while loop if we reached the error code path below, an
x of_node_put(np) is needed.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Fixes: commit f3d9478b2ce4 ("[ALSA] snd-aoa: add snd-aoa")
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/aoa/core/gpio-feature.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/aoa/core/gpio-feature.c b/sound/aoa/core/gpio-feature.c
index 71960089e207..65557421fe0b 100644
--- a/sound/aoa/core/gpio-feature.c
+++ b/sound/aoa/core/gpio-feature.c
@@ -88,8 +88,10 @@ static struct device_node *get_gpio(char *name,
 	}
 
 	reg = of_get_property(np, "reg", NULL);
-	if (!reg)
+	if (!reg) {
+		of_node_put(np);
 		return NULL;
+	}
 
 	*gpioptr = *reg;
 
-- 
cgit v1.2.3


From debef195bd5c79210d60f1d6dec38bde3dae2b88 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Sun, 3 Jun 2018 09:44:04 +0800
Subject: clk: imx6ul: add GPIO clock gates

i.MX6UL has GPIO clock gates in CCM CCGR,
add them into clock tree for clock management.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6ul.c             | 5 +++++
 include/dt-bindings/clock/imx6ul-clock.h | 8 +++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
index ba563ba50b40..3ea2d97562fd 100644
--- a/drivers/clk/imx/clk-imx6ul.c
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -360,6 +360,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_UART2_SERIAL]	= imx_clk_gate2("uart2_serial",	"uart_podf",	base + 0x68,	28);
 	if (clk_on_imx6ull())
 		clks[IMX6UL_CLK_AIPSTZ3]	= imx_clk_gate2("aips_tz3",	"ahb",		 base + 0x80,	18);
+	clks[IMX6UL_CLK_GPIO2]		= imx_clk_gate2("gpio2",	"ipg",		base + 0x68,	30);
 
 	/* CCGR1 */
 	clks[IMX6UL_CLK_ECSPI1]		= imx_clk_gate2("ecspi1",	"ecspi_podf",	base + 0x6c,	0);
@@ -376,6 +377,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_GPT1_SERIAL]	= imx_clk_gate2("gpt1_serial",	"perclk",	base + 0x6c,	22);
 	clks[IMX6UL_CLK_UART4_IPG]	= imx_clk_gate2("uart4_ipg",	"ipg",		base + 0x6c,	24);
 	clks[IMX6UL_CLK_UART4_SERIAL]	= imx_clk_gate2("uart4_serial",	"uart_podf",	base + 0x6c,	24);
+	clks[IMX6UL_CLK_GPIO1]		= imx_clk_gate2("gpio1",	"ipg",		base + 0x6c,	26);
+	clks[IMX6UL_CLK_GPIO5]		= imx_clk_gate2("gpio5",	"ipg",		base + 0x6c,	30);
 
 	/* CCGR2 */
 	if (clk_on_imx6ull()) {
@@ -389,6 +392,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_I2C3]		= imx_clk_gate2("i2c3",		"perclk",	base + 0x70,	10);
 	clks[IMX6UL_CLK_OCOTP]		= imx_clk_gate2("ocotp",	"ipg",		base + 0x70,	12);
 	clks[IMX6UL_CLK_IOMUXC]		= imx_clk_gate2("iomuxc",	"lcdif_podf",	base + 0x70,	14);
+	clks[IMX6UL_CLK_GPIO3]		= imx_clk_gate2("gpio3",	"ipg",		base + 0x70,	26);
 	clks[IMX6UL_CLK_LCDIF_APB]	= imx_clk_gate2("lcdif_apb",	"axi",		base + 0x70,	28);
 	clks[IMX6UL_CLK_PXP]		= imx_clk_gate2("pxp",		"axi",		base + 0x70,	30);
 
@@ -405,6 +409,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_UART6_IPG]	= imx_clk_gate2("uart6_ipg",	"ipg",		base + 0x74,	6);
 	clks[IMX6UL_CLK_UART6_SERIAL]	= imx_clk_gate2("uart6_serial",	"uart_podf",	base + 0x74,	6);
 	clks[IMX6UL_CLK_LCDIF_PIX]	= imx_clk_gate2("lcdif_pix",	"lcdif_podf",	base + 0x74,	10);
+	clks[IMX6UL_CLK_GPIO4]		= imx_clk_gate2("gpio4",	"ipg",		base + 0x74,	12);
 	clks[IMX6UL_CLK_QSPI]		= imx_clk_gate2("qspi1",	"qspi1_podf",	base + 0x74,	14);
 	clks[IMX6UL_CLK_WDOG1]		= imx_clk_gate2("wdog1",	"ipg",		base + 0x74,	16);
 	clks[IMX6UL_CLK_MMDC_P0_FAST]	= imx_clk_gate("mmdc_p0_fast", "mmdc_podf", base + 0x74,	20);
diff --git a/include/dt-bindings/clock/imx6ul-clock.h b/include/dt-bindings/clock/imx6ul-clock.h
index 0aa1d9c3e0b9..f8e0476a3a0e 100644
--- a/include/dt-bindings/clock/imx6ul-clock.h
+++ b/include/dt-bindings/clock/imx6ul-clock.h
@@ -254,6 +254,12 @@
 #define IMX6UL_CLK_CKO2_PODF		241
 #define IMX6UL_CLK_CKO2			242
 #define IMX6UL_CLK_CKO			243
-#define IMX6UL_CLK_END			244
+#define IMX6UL_CLK_GPIO1		244
+#define IMX6UL_CLK_GPIO2		245
+#define IMX6UL_CLK_GPIO3		246
+#define IMX6UL_CLK_GPIO4		247
+#define IMX6UL_CLK_GPIO5		248
+
+#define IMX6UL_CLK_END			249
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6UL_H */
-- 
cgit v1.2.3


From 4a2eaa8e2567297d4dc6e2709841a874927c83aa Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Mon, 4 Jun 2018 09:06:46 +0800
Subject: clk: imx6ul: remove clks_init_on array

Clock framework will enable those clocks registered
with CLK_IS_CRITICAL flag, so no need to have
clks_init_on array during clock initialization now.

ARM clock is busy divider type which has the
CLK_IS_CRITICAL flag set by default when registered.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6ul.c | 23 ++++++-----------------
 1 file changed, 6 insertions(+), 17 deletions(-)

diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
index 3ea2d97562fd..d3f7f4db80af 100644
--- a/drivers/clk/imx/clk-imx6ul.c
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -79,12 +79,6 @@ static const char *cko_sels[] = { "cko1", "cko2", };
 static struct clk *clks[IMX6UL_CLK_END];
 static struct clk_onecell_data clk_data;
 
-static int const clks_init_on[] __initconst = {
-	IMX6UL_CLK_AIPSTZ1, IMX6UL_CLK_AIPSTZ2,
-	IMX6UL_CLK_AXI, IMX6UL_CLK_ARM, IMX6UL_CLK_ROM,
-	IMX6UL_CLK_MMDC_P0_FAST, IMX6UL_CLK_MMDC_P0_IPG,
-};
-
 static const struct clk_div_table clk_enet_ref_table[] = {
 	{ .val = 0, .div = 20, },
 	{ .val = 1, .div = 10, },
@@ -129,7 +123,6 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 {
 	struct device_node *np;
 	void __iomem *base;
-	int i;
 
 	clks[IMX6UL_CLK_DUMMY] = imx_clk_fixed("dummy", 0);
 
@@ -336,8 +329,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_AHB]		= imx_clk_busy_divider("ahb",	    "periph",	base +  0x14, 10, 3,  base + 0x48, 1);
 
 	/* CCGR0 */
-	clks[IMX6UL_CLK_AIPSTZ1]	= imx_clk_gate2("aips_tz1",	"ahb",		base + 0x68,	0);
-	clks[IMX6UL_CLK_AIPSTZ2]	= imx_clk_gate2("aips_tz2",	"ahb",		base + 0x68,	2);
+	clks[IMX6UL_CLK_AIPSTZ1]	= imx_clk_gate2_flags("aips_tz1", "ahb", base + 0x68, 0, CLK_IS_CRITICAL);
+	clks[IMX6UL_CLK_AIPSTZ2]	= imx_clk_gate2_flags("aips_tz2", "ahb", base + 0x68, 2, CLK_IS_CRITICAL);
 	clks[IMX6UL_CLK_APBHDMA]	= imx_clk_gate2("apbh_dma",	"bch_podf",	base + 0x68,	4);
 	clks[IMX6UL_CLK_ASRC_IPG]	= imx_clk_gate2_shared("asrc_ipg",	"ahb",	base + 0x68,	6, &share_count_asrc);
 	clks[IMX6UL_CLK_ASRC_MEM]	= imx_clk_gate2_shared("asrc_mem",	"ahb",	base + 0x68,	6, &share_count_asrc);
@@ -412,9 +405,9 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_GPIO4]		= imx_clk_gate2("gpio4",	"ipg",		base + 0x74,	12);
 	clks[IMX6UL_CLK_QSPI]		= imx_clk_gate2("qspi1",	"qspi1_podf",	base + 0x74,	14);
 	clks[IMX6UL_CLK_WDOG1]		= imx_clk_gate2("wdog1",	"ipg",		base + 0x74,	16);
-	clks[IMX6UL_CLK_MMDC_P0_FAST]	= imx_clk_gate("mmdc_p0_fast", "mmdc_podf", base + 0x74,	20);
-	clks[IMX6UL_CLK_MMDC_P0_IPG]	= imx_clk_gate2("mmdc_p0_ipg",	"ipg",		base + 0x74,	24);
-	clks[IMX6UL_CLK_AXI]		= imx_clk_gate("axi",	"axi_podf",	base + 0x74,	28);
+	clks[IMX6UL_CLK_MMDC_P0_FAST]	= imx_clk_gate_flags("mmdc_p0_fast", "mmdc_podf", base + 0x74,	20, CLK_IS_CRITICAL);
+	clks[IMX6UL_CLK_MMDC_P0_IPG]	= imx_clk_gate2_flags("mmdc_p0_ipg",	"ipg",		base + 0x74,	24, CLK_IS_CRITICAL);
+	clks[IMX6UL_CLK_AXI]		= imx_clk_gate_flags("axi",	"axi_podf",	base + 0x74,	28, CLK_IS_CRITICAL);
 
 	/* CCGR4 */
 	clks[IMX6UL_CLK_PER_BCH]	= imx_clk_gate2("per_bch",	"bch_podf",	base + 0x78,	12);
@@ -428,7 +421,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clks[IMX6UL_CLK_GPMI_APB]	= imx_clk_gate2("gpmi_apb",	"bch_podf",	base + 0x78,	30);
 
 	/* CCGR5 */
-	clks[IMX6UL_CLK_ROM]		= imx_clk_gate2("rom",		"ahb",		base + 0x7c,	0);
+	clks[IMX6UL_CLK_ROM]		= imx_clk_gate2_flags("rom",	"ahb",		base + 0x7c,	0,	CLK_IS_CRITICAL);
 	clks[IMX6UL_CLK_SDMA]		= imx_clk_gate2("sdma",		"ahb",		base + 0x7c,	6);
 	clks[IMX6UL_CLK_KPP]		= imx_clk_gate2("kpp",		"ipg",		base + 0x7c,	8);
 	clks[IMX6UL_CLK_WDOG2]		= imx_clk_gate2("wdog2",	"ipg",		base + 0x7c,	10);
@@ -502,10 +495,6 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 	clk_set_rate(clks[IMX6UL_CLK_ENET2_REF], 50000000);
 	clk_set_rate(clks[IMX6UL_CLK_CSI], 24000000);
 
-	/* keep all the clks on just for bringup */
-	for (i = 0; i < ARRAY_SIZE(clks_init_on); i++)
-		clk_prepare_enable(clks[clks_init_on[i]]);
-
 	if (clk_on_imx6ull())
 		clk_prepare_enable(clks[IMX6UL_CLK_AIPSTZ3]);
 
-- 
cgit v1.2.3


From a7047564fef3ddf0092e64a229ddb17596717120 Mon Sep 17 00:00:00 2001
From: Philipp Puschmann <pp@emlix.com>
Date: Fri, 8 Jun 2018 12:19:24 +0200
Subject: clk: imx6: fix video_27m parent for IMX6QDL_CLK_CKO1_SEL

q/dl datasheets list the 5th selection value for ck01_sel as
video_27M_clk_root.

By replacing the dummy value we then can set IMX6QDL_CLK_VIDEO_27M
as parent for IMX6QDL_CLK_CKO1_SEL.

Signed-off-by: Philipp Puschmann <pp@emlix.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6q.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/imx/clk-imx6q.c b/drivers/clk/imx/clk-imx6q.c
index b9ea7037e193..0662db5d37c6 100644
--- a/drivers/clk/imx/clk-imx6q.c
+++ b/drivers/clk/imx/clk-imx6q.c
@@ -65,7 +65,7 @@ static const char *ipg_per_sels[] = { "ipg", "osc", };
 static const char *ecspi_sels[] = { "pll3_60m", "osc", };
 static const char *can_sels[] = { "pll3_60m", "osc", "pll3_80m", };
 static const char *cko1_sels[]	= { "pll3_usb_otg", "pll2_bus", "pll1_sys", "pll5_video_div",
-				    "dummy", "axi", "enfc", "ipu1_di0", "ipu1_di1", "ipu2_di0",
+				    "video_27m", "axi", "enfc", "ipu1_di0", "ipu1_di1", "ipu2_di0",
 				    "ipu2_di1", "ahb", "ipg", "ipg_per", "ckil", "pll4_audio_div", };
 static const char *cko2_sels[] = {
 	"mmdc_ch0_axi", "mmdc_ch1_axi", "usdhc4", "usdhc1",
-- 
cgit v1.2.3


From e14d7dfb41f5807a0c1c26a13f2b8ef16af24935 Mon Sep 17 00:00:00 2001
From: Michal Hocko <mhocko@suse.cz>
Date: Wed, 27 Jun 2018 17:46:50 +0200
Subject: x86/speculation/l1tf: Fix up pte->pfn conversion for PAE

Jan has noticed that pte_pfn and co. resp. pfn_pte are incorrect for
CONFIG_PAE because phys_addr_t is wider than unsigned long and so the
pte_val reps. shift left would get truncated. Fix this up by using proper
types.

Fixes: 6b28baca9b1f ("x86/speculation/l1tf: Protect PROT_NONE PTEs against speculation")
Reported-by: Jan Beulich <JBeulich@suse.com>
Signed-off-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
---
 arch/x86/include/asm/pgtable.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 6a090a76fdca..26fd42a91946 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -191,21 +191,21 @@ static inline u64 protnone_mask(u64 val);
 
 static inline unsigned long pte_pfn(pte_t pte)
 {
-	unsigned long pfn = pte_val(pte);
+	phys_addr_t pfn = pte_val(pte);
 	pfn ^= protnone_mask(pfn);
 	return (pfn & PTE_PFN_MASK) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pmd_pfn(pmd_t pmd)
 {
-	unsigned long pfn = pmd_val(pmd);
+	phys_addr_t pfn = pmd_val(pmd);
 	pfn ^= protnone_mask(pfn);
 	return (pfn & pmd_pfn_mask(pmd)) >> PAGE_SHIFT;
 }
 
 static inline unsigned long pud_pfn(pud_t pud)
 {
-	unsigned long pfn = pud_val(pud);
+	phys_addr_t pfn = pud_val(pud);
 	pfn ^= protnone_mask(pfn);
 	return (pfn & pud_pfn_mask(pud)) >> PAGE_SHIFT;
 }
@@ -555,7 +555,7 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot)
 
 static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 {
-	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
 	pfn ^= protnone_mask(pgprot_val(pgprot));
 	pfn &= PTE_PFN_MASK;
 	return __pte(pfn | check_pgprot(pgprot));
@@ -563,7 +563,7 @@ static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
 
 static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 {
-	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
 	pfn ^= protnone_mask(pgprot_val(pgprot));
 	pfn &= PHYSICAL_PMD_PAGE_MASK;
 	return __pmd(pfn | check_pgprot(pgprot));
@@ -571,7 +571,7 @@ static inline pmd_t pfn_pmd(unsigned long page_nr, pgprot_t pgprot)
 
 static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 {
-	phys_addr_t pfn = page_nr << PAGE_SHIFT;
+	phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
 	pfn ^= protnone_mask(pgprot_val(pgprot));
 	pfn &= PHYSICAL_PUD_PAGE_MASK;
 	return __pud(pfn | check_pgprot(pgprot));
-- 
cgit v1.2.3


From d78e2bbf483faa48f060c2454c56c3ff9cd74573 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 29 Jun 2018 14:37:16 +0100
Subject: drm/i915/selftests: Mark up write into scratch vma

We correctly attach the exclusive fetch for the scratch object when
emitting a request that writes into it, but for completeness we should
also declared the write to i915_vma_move_to_active()

Reported-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180629133717.11761-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index c0c26fae45c7..cc848ceeb3c3 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -175,7 +175,7 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 	i915_vma_unpin(batch);
 	i915_vma_close(batch);
 
-	i915_vma_move_to_active(vma, rq, 0);
+	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 	i915_vma_unpin(vma);
 
 	reservation_object_lock(obj->resv, NULL);
-- 
cgit v1.2.3


From be01de596ef65ad1fc66a795d45e7334d197e594 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 29 Jun 2018 14:37:17 +0100
Subject: drm/i915/selftests: Attach the fence to the object when making busy

make_obj_busy() makes a dummy busy object, but didn't attach the fence
to the reservation object, so it would not have registered as busy. For
completeness, attach the dummy request as the exclusive fence and mark
the object as written (in i915_vma_move_to_active)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180629133717.11761-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_object.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 549707b9d738..77dd7a510ea6 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -454,7 +454,12 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 		return PTR_ERR(rq);
 	}
 
-	i915_vma_move_to_active(vma, rq, 0);
+	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+
+	reservation_object_lock(vma->resv, NULL);
+	reservation_object_add_excl_fence(vma->resv, &rq->fence);
+	reservation_object_unlock(vma->resv);
+
 	i915_request_add(rq);
 
 	i915_gem_object_set_active_reference(obj);
-- 
cgit v1.2.3


From 3e2b88cbd225f0867fee6ba63ffe3c38a2e98822 Mon Sep 17 00:00:00 2001
From: "Dirk Hohndel (VMware)" <dirk@hohndel.org>
Date: Mon, 7 May 2018 01:16:19 +0200
Subject: drm: add SPDX idenitifier and clarify license

This is dual licensed under GPL-2.0 or MIT.

Signed-off-by: Dirk Hohndel (VMware) <dirk@hohndel.org>
Signed-off-by: David Herrmann <dh.herrmann@gmail.com>
Signed-off-by: David Airlie <airlied@linux.ie>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180506231626.115996-2-dirk@hohndel.org
---
 drivers/gpu/drm/drm_vma_manager.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/drm_vma_manager.c b/drivers/gpu/drm/drm_vma_manager.c
index 23c749c05b5a..a6b2fe36b025 100644
--- a/drivers/gpu/drm/drm_vma_manager.c
+++ b/drivers/gpu/drm/drm_vma_manager.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright (c) 2006-2009 VMware, Inc., Palo Alto, CA., USA
  * Copyright (c) 2012 David Airlie <airlied@linux.ie>
-- 
cgit v1.2.3


From 4f960dcf75421033b00052abcfc4454e4d302655 Mon Sep 17 00:00:00 2001
From: "Dirk Hohndel (VMware)" <dirk@hohndel.org>
Date: Mon, 7 May 2018 01:16:21 +0200
Subject: drm: add SPDX identifier and clarify license

This is dual licensed under GPL-2.0 or MIT.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dirk Hohndel (VMware) <dirk@hohndel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180506231626.115996-4-dirk@hohndel.org
---
 drivers/gpu/drm/drm_global.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_global.c b/drivers/gpu/drm/drm_global.c
index b2dc21e33ae0..5799e2782dd1 100644
--- a/drivers/gpu/drm/drm_global.c
+++ b/drivers/gpu/drm/drm_global.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
  * Copyright 2008-2009 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
-- 
cgit v1.2.3


From eee3dc56e22eb8bf54eab925bba30bd94ae403bd Mon Sep 17 00:00:00 2001
From: "Dirk Hohndel (VMware)" <dirk@hohndel.org>
Date: Mon, 7 May 2018 01:16:22 +0200
Subject: drm/noveau: add SPDX identifier and clarify license

This is dual licensed under GPL-2.0 or MIT.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dirk Hohndel (VMware) <dirk@hohndel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180506231626.115996-5-dirk@hohndel.org
---
 drivers/gpu/drm/nouveau/nouveau_ttm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 8c093ca4222e..8edb9f2a4269 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -1,8 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright (c) 2007-2008 Tungsten Graphics, Inc., Cedar Park, TX., USA,
- * All Rights Reserved.
  * Copyright (c) 2009 VMware, Inc., Palo Alto, CA., USA,
- * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the "Software"),
-- 
cgit v1.2.3


From a3be6f6c6e3e9fc93cf0ac19aae039c7135686e3 Mon Sep 17 00:00:00 2001
From: "Dirk Hohndel (VMware)" <dirk@hohndel.org>
Date: Mon, 7 May 2018 01:16:25 +0200
Subject: drm/vmwgfx: add SPDX idenitifier and clarify license

These files are licensed under GPL-2.0.
Removing the MIT boilerplate as that really didn't make any sense for
those two header files.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dirk Hohndel (VMware) <dirk@hohndel.org>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180506231626.115996-8-dirk@hohndel.org
---
 drivers/gpu/drm/vmwgfx/Kconfig                     |  1 +
 .../drm/vmwgfx/device_include/vmware_pack_begin.h  | 25 +---------------------
 .../drm/vmwgfx/device_include/vmware_pack_end.h    | 25 +---------------------
 3 files changed, 3 insertions(+), 48 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/Kconfig b/drivers/gpu/drm/vmwgfx/Kconfig
index 8c308dac99c5..6b28a326f8bb 100644
--- a/drivers/gpu/drm/vmwgfx/Kconfig
+++ b/drivers/gpu/drm/vmwgfx/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 config DRM_VMWGFX
 	tristate "DRM driver for VMware Virtual GPU"
 	depends on DRM && PCI && X86 && MMU
diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
index 7e7b0ce34aa2..75308bd0d970 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_begin.h
@@ -1,25 +1,2 @@
-/**********************************************************
- * Copyright 2015 VMware, Inc.  All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, sublicense, and/or sell copies
- * of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be
- * included in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- **********************************************************/
+/* SPDX-License-Identifier: GPL-2.0 */
 #include <linux/compiler.h>
diff --git a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
index e2e440ed3d44..e93d6f28b68c 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/vmware_pack_end.h
@@ -1,25 +1,2 @@
-/**********************************************************
- * Copyright 2015 VMware, Inc.  All rights reserved.
- *
- * Permission is hereby granted, free of charge, to any person
- * obtaining a copy of this software and associated documentation
- * files (the "Software"), to deal in the Software without
- * restriction, including without limitation the rights to use, copy,
- * modify, merge, publish, distribute, sublicense, and/or sell copies
- * of the Software, and to permit persons to whom the Software is
- * furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be
- * included in all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- **********************************************************/
+/* SPDX-License-Identifier: GPL-2.0 */
 __packed
-- 
cgit v1.2.3


From dff96888860a9ebaa618be973b51f4d86aec1211 Mon Sep 17 00:00:00 2001
From: "Dirk Hohndel (VMware)" <dirk@hohndel.org>
Date: Mon, 7 May 2018 01:16:26 +0200
Subject: drm/vmwgfx: add SPDX idenitifier and clarify license

This is dual licensed under GPL-2.0 or MIT.
vmwgfx_msg.h is the odd one out that is GPL-2.0+ or MIT.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dirk Hohndel (VMware) <dirk@hohndel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180506231626.115996-9-dirk@hohndel.org
---
 .../gpu/drm/vmwgfx/device_include/svga3d_caps.h    |  3 +-
 drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h |  3 +-
 .../gpu/drm/vmwgfx/device_include/svga3d_devcaps.h |  3 +-
 drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h  |  3 +-
 .../gpu/drm/vmwgfx/device_include/svga3d_limits.h  |  3 +-
 drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h |  3 +-
 .../drm/vmwgfx/device_include/svga3d_surfacedefs.h |  4 +--
 .../gpu/drm/vmwgfx/device_include/svga3d_types.h   |  3 +-
 .../gpu/drm/vmwgfx/device_include/svga_escape.h    |  3 +-
 .../gpu/drm/vmwgfx/device_include/svga_overlay.h   |  3 +-
 drivers/gpu/drm/vmwgfx/device_include/svga_reg.h   |  3 +-
 drivers/gpu/drm/vmwgfx/device_include/svga_types.h |  3 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_binding.c            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_binding.h            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_blit.c               |  3 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c             |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c             |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c         |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_context.c            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c             |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_fence.c              |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_fence.h              |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c               |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c      |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c              |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_irq.c                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.h                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_marker.c             |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_mob.c                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.h                | 35 +++++++++++++++-------
 drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_prime.c              |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_reg.h                |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c           |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h      |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c               |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_shader.c             |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c    |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_so.c                 |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_so.h                 |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c               |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c            |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c           |  4 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_va.c                 |  4 +--
 52 files changed, 126 insertions(+), 101 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
index 9ce2466a5d00..69c4253fbfbb 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_caps.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
index 2dfd57c5f463..3bf75978e155 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
index c18b663f360f..e1c0d94cc1e9 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
index 8c5ae608cfb4..f4606d04556b 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2012-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2012-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
index a1c36877ad55..8732490d45d5 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
index b44ce648f592..bdfc404c91e3 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_reg.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
index babe7cb84fc2..b45e96309233 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2008-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2008-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
index 27b33ba88430..df63f24c2e10 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2012-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2012-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
index 884b1d1fb85f..acb41e28e46f 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_escape.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
index faf6d9b2b891..e5385146e7fc 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_overlay.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2007-2015 VMware, Inc.  All rights reserved.
+ * Copyright 2007-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
index 88e72bf9a534..847e3301c478 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 1998-2015 VMware, Inc.  All rights reserved.
+ * Copyright 1998-2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
index 2e8ba4df8de9..53602a4e7957 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
@@ -1,5 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**********************************************************
- * Copyright 2015 VMware, Inc.  All rights reserved.
+ * Copyright 2015 VMware, Inc.
  *
  * Permission is hereby granted, free of charge, to any person
  * obtaining a copy of this software and associated documentation
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
index 55d32ae43aa4..0b9ee7fb45d6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h
index bf2e77ad5a20..6a2a9d69043b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_binding.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
index e8c94b19db7b..fc6673cde289 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
@@ -1,6 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2017 VMware, Inc., Palo Alto, CA., USA
+ * Copyright 2017 VMware, Inc., Palo Alto, CA., USA
  * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
index 21111fd091f9..02de216d55a1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
index 9f45d5004cae..e7e4655d3f36 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
index 36c7b6c839c0..3b75af9bf85f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cmdbuf_res.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index 3767ac335aca..750319d95458 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index cbf54ea7b4c0..df55e7d8b4cf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
index d59d9dd16ebc..df7d1c97eb82 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2011-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 09cc721160c4..af88cb737be3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 5fcbe1620d50..422eef114b98 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index c9d5cc237124..47bb7e58a368 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009 - 2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009 - 2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 9ed544f8958f..c2eeb677cdfc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2011-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2011-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
index 20224dba9d8e..c9382933c2b9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2011-2012 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2011-2012 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
index a1c68e6a689e..d0fd147ef75f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fifo.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
index 66ffa1d4759c..007a0cc7f232 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmr.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
index f2f9d88131f2..ddb1e9365a3e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_gmrid_manager.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright (c) 2007-2010 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2007-2010 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index c5e8eae0dbe2..78fce406e1d4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
index b9239ba067c4..c3ad4478266b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_irq.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index ef96ba7432ad..6317672070cd 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 6b7c012719f1..27c41c227120 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 4a5907e3f560..dc0cfda26b1b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c b/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c
index efd1ffd68185..e53bc639a754 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_marker.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright (C) 2010 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2010 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index d07c585e3c1d..0963d0438190 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2012-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2012-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 21d746bdc922..4437c41c585a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -1,6 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
- * Copyright © 2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
index 8545488aa0cf..4907e50fb20a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.h
@@ -1,16 +1,29 @@
-/*
- * Copyright (C) 2016, VMware, Inc.
+/* SPDX-License-Identifier: GPL-2.0+ OR MIT */
+/**************************************************************************
+ *
+ * Copyright 2016 VMware, Inc., Palo Alto, CA., USA
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
  *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT.  See the GNU General Public License for more
- * details.
+ **************************************************************************
  *
  * Based on code from vmware.c and vmmouse.c.
  * Author:
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
index 222c9c2123a1..3ced89e70a64 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
index 373bc6da2f84..0861c821a7fe 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2013 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2013 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h b/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h
index dce798053a96..e99f6cdbb091 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_reg.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2009-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 6b3a942b18df..3063a3e4bd40 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h
index ac05968a832b..a8c1c5ebd71d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource_priv.h
@@ -1,7 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
  *
- * Copyright © 2012-2014 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2012-2014 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 9798640cbfcd..73cf3c6e1591 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2011-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index 73b8e9a16368..e3ba63da396d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c
index a0cb310665cc..6ebc5affde14 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_simple_resource.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
index d3573c37c436..e9b6b7baa009 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.c
@@ -1,6 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_so.h b/drivers/gpu/drm/vmwgfx/vmwgfx_so.h
index 268738387b5e..b80c7252f2fd 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_so.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_so.h
@@ -1,6 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
 /**************************************************************************
- * Copyright © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 152e96cb1c01..a474d87b1af3 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /******************************************************************************
  *
- * COPYRIGHT © 2014-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * COPYRIGHT (C) 2014-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index b236c48bf265..40a439797ae2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2015 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
index e771091d2cd3..7b1e5a5cbd2c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2009-2011 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2009-2011 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_va.c b/drivers/gpu/drm/vmwgfx/vmwgfx_va.c
index b4162fd78600..ebc1d83c34b4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_va.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_va.c
@@ -1,7 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /**************************************************************************
  *
- * Copyright © 2012-2016 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
+ * Copyright 2012-2016 VMware, Inc., Palo Alto, CA., USA
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
  * copy of this software and associated documentation files (the
-- 
cgit v1.2.3


From 14d9deeb273c2bf4ec256589adabd8df65395d36 Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Wed, 20 Jun 2018 17:17:03 -0700
Subject: drm/v3d: Define the fourcc modifier for the Broadcom UIF format.

This will be used by Mesa, and potentially other drivers in the
future, to describe tiled buffers.

Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180621001703.13522-1-eric@anholt.net
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 include/uapi/drm/drm_fourcc.h | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index 64bf67abff7e..d5e52350a3aa 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -464,6 +464,27 @@ extern "C" {
 #define DRM_FORMAT_MOD_BROADCOM_SAND256 \
 	DRM_FORMAT_MOD_BROADCOM_SAND256_COL_HEIGHT(0)
 
+/* Broadcom UIF format
+ *
+ * This is the common format for the current Broadcom multimedia
+ * blocks, including V3D 3.x and newer, newer video codecs, and
+ * displays.
+ *
+ * The image consists of utiles (64b blocks), UIF blocks (2x2 utiles),
+ * and macroblocks (4x4 UIF blocks).  Those 4x4 UIF block groups are
+ * stored in columns, with padding between the columns to ensure that
+ * moving from one column to the next doesn't hit the same SDRAM page
+ * bank.
+ *
+ * To calculate the padding, it is assumed that each hardware block
+ * and the software driving it knows the platform's SDRAM page size,
+ * number of banks, and XOR address, and that it's identical between
+ * all blocks using the format.  This tiling modifier will use XOR as
+ * necessary to reduce the padding.  If a hardware block can't do XOR,
+ * the assumption is that a no-XOR tiling modifier will be created.
+ */
+#define DRM_FORMAT_MOD_BROADCOM_UIF fourcc_mod_code(BROADCOM, 6)
+
 #if defined(__cplusplus)
 }
 #endif
-- 
cgit v1.2.3


From 491657a915601febfb9d0c253d843124438ae35d Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Thu, 21 Jun 2018 16:17:59 -0700
Subject: drm/vc4: Make DSI call into the bridge after the DSI link is enabled.

This allows panels or bridges that need to send DSI commands during
pre_enable() to successfully send them.  We delay DISP0 (aka the
actual display) enabling until after pre_enable so that pixels aren't
streaming before then.

v2: Just clear out the encoder->bridge value to disable the midlayer
    calls (idea by Andrzej Hajda).

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Andrzej Hajda <a.hajda@samsung.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180621231759.29604-1-eric@anholt.net
Reviewed-by: Andrzej Hajda <a.hajda@samsung.com>
---
 drivers/gpu/drm/vc4/vc4_dsi.c | 42 +++++++++++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 8aa897835118..9c8e89372d1c 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -814,7 +814,9 @@ static void vc4_dsi_encoder_disable(struct drm_encoder *encoder)
 	struct vc4_dsi *dsi = vc4_encoder->dsi;
 	struct device *dev = &dsi->pdev->dev;
 
+	drm_bridge_disable(dsi->bridge);
 	vc4_dsi_ulps(dsi, true);
+	drm_bridge_post_disable(dsi->bridge);
 
 	clk_disable_unprepare(dsi->pll_phy_clock);
 	clk_disable_unprepare(dsi->escape_clock);
@@ -1089,21 +1091,6 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 	/* Display reset sequence timeout */
 	DSI_PORT_WRITE(PR_TO_CNT, 100000);
 
-	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
-		DSI_PORT_WRITE(DISP0_CTRL,
-			       VC4_SET_FIELD(dsi->divider,
-					     DSI_DISP0_PIX_CLK_DIV) |
-			       VC4_SET_FIELD(dsi->format, DSI_DISP0_PFORMAT) |
-			       VC4_SET_FIELD(DSI_DISP0_LP_STOP_PERFRAME,
-					     DSI_DISP0_LP_STOP_CTRL) |
-			       DSI_DISP0_ST_END |
-			       DSI_DISP0_ENABLE);
-	} else {
-		DSI_PORT_WRITE(DISP0_CTRL,
-			       DSI_DISP0_COMMAND_MODE |
-			       DSI_DISP0_ENABLE);
-	}
-
 	/* Set up DISP1 for transferring long command payloads through
 	 * the pixfifo.
 	 */
@@ -1128,6 +1115,25 @@ static void vc4_dsi_encoder_enable(struct drm_encoder *encoder)
 
 	vc4_dsi_ulps(dsi, false);
 
+	drm_bridge_pre_enable(dsi->bridge);
+
+	if (dsi->mode_flags & MIPI_DSI_MODE_VIDEO) {
+		DSI_PORT_WRITE(DISP0_CTRL,
+			       VC4_SET_FIELD(dsi->divider,
+					     DSI_DISP0_PIX_CLK_DIV) |
+			       VC4_SET_FIELD(dsi->format, DSI_DISP0_PFORMAT) |
+			       VC4_SET_FIELD(DSI_DISP0_LP_STOP_PERFRAME,
+					     DSI_DISP0_LP_STOP_CTRL) |
+			       DSI_DISP0_ST_END |
+			       DSI_DISP0_ENABLE);
+	} else {
+		DSI_PORT_WRITE(DISP0_CTRL,
+			       DSI_DISP0_COMMAND_MODE |
+			       DSI_DISP0_ENABLE);
+	}
+
+	drm_bridge_enable(dsi->bridge);
+
 	if (debug_dump_regs) {
 		DRM_INFO("DSI regs after:\n");
 		vc4_dsi_dump_regs(dsi);
@@ -1639,6 +1645,12 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 		dev_err(dev, "bridge attach failed: %d\n", ret);
 		return ret;
 	}
+	/* Disable the atomic helper calls into the bridge.  We
+	 * manually call the bridge pre_enable / enable / etc. calls
+	 * from our driver, since we need to sequence them within the
+	 * encoder's enable/disable paths.
+	 */
+	dsi->encoder->bridge = NULL;
 
 	pm_runtime_enable(dev);
 
-- 
cgit v1.2.3


From 1ea29bbd47cf5640fd67f8bcca1f934aa468c428 Mon Sep 17 00:00:00 2001
From: Michal Wajdeczko <michal.wajdeczko@intel.com>
Date: Mon, 18 Jun 2018 11:18:20 +0000
Subject: drm/i915/guc: Print CTL params passed to Guc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

While debugging we may want to examine params passed to GuC.

v2: drop #ifdef DEBUG_GUC - Michal

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com> #1
Cc: Michal Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618111821.47088-1-michal.wajdeczko@intel.com
---
 drivers/gpu/drm/i915/intel_guc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index 53b43bc73c01..e12bd259df17 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -351,6 +351,9 @@ void intel_guc_init_params(struct intel_guc *guc)
 	params[GUC_CTL_DEBUG] = guc_ctl_debug_flags(guc);
 	params[GUC_CTL_CTXINFO] = guc_ctl_ctxinfo_flags(guc);
 
+	for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
+		DRM_DEBUG_DRIVER("param[%2d] = %#x\n", i, params[i]);
+
 	/*
 	 * All SOFT_SCRATCH registers are in FORCEWAKE_BLITTER domain and
 	 * they are power context saved so it's ok to release forcewake
-- 
cgit v1.2.3


From d3252ace0bc652a1a244455556b6a549f969bf99 Mon Sep 17 00:00:00 2001
From: Christian König <ckoenig.leichtzumerken@gmail.com>
Date: Fri, 29 Jun 2018 19:54:55 -0500
Subject: PCI: Restore resized BAR state on resume
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Resize BARs after resume to the expected size again.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=199959
Fixes: d6895ad39f3b ("drm/amdgpu: resize VRAM BAR for CPU access v6")
Fixes: 276b738deb5b ("PCI: Add resizable BAR infrastructure")
Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
CC: stable@vger.kernel.org      # v4.15+
---
 drivers/pci/pci.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..44ccfb31363e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1171,6 +1171,33 @@ static void pci_restore_config_space(struct pci_dev *pdev)
 	}
 }
 
+static void pci_restore_rebar_state(struct pci_dev *pdev)
+{
+	unsigned int pos, nbars, i;
+	u32 ctrl;
+
+	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR);
+	if (!pos)
+		return;
+
+	pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
+	nbars = (ctrl & PCI_REBAR_CTRL_NBAR_MASK) >>
+		    PCI_REBAR_CTRL_NBAR_SHIFT;
+
+	for (i = 0; i < nbars; i++, pos += 8) {
+		struct resource *res;
+		int bar_idx, size;
+
+		pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
+		bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX;
+		res = pdev->resource + bar_idx;
+		size = order_base_2((resource_size(res) >> 20) | 1) - 1;
+		ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
+		ctrl |= size << 8;
+		pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
+	}
+}
+
 /**
  * pci_restore_state - Restore the saved state of a PCI device
  * @dev: - PCI device that we're dealing with
@@ -1186,6 +1213,7 @@ void pci_restore_state(struct pci_dev *dev)
 	pci_restore_pri_state(dev);
 	pci_restore_ats_state(dev);
 	pci_restore_vc_state(dev);
+	pci_restore_rebar_state(dev);
 
 	pci_cleanup_aer_error_status_regs(dev);
 
-- 
cgit v1.2.3


From b1277a226d8c519b8c33e23fe68b4e1658f15963 Mon Sep 17 00:00:00 2001
From: Christian König <ckoenig.leichtzumerken@gmail.com>
Date: Fri, 29 Jun 2018 19:55:03 -0500
Subject: PCI: Cleanup PCI_REBAR_CTRL_BAR_SHIFT handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Cleanup PCI_REBAR_CTRL_BAR_SHIFT handling.  That was hard coded instead of
properly defined in the header for some reason.

Signed-off-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c             | 6 +++---
 include/uapi/linux/pci_regs.h | 3 ++-
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 44ccfb31363e..1b20c4392f09 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1193,7 +1193,7 @@ static void pci_restore_rebar_state(struct pci_dev *pdev)
 		res = pdev->resource + bar_idx;
 		size = order_base_2((resource_size(res) >> 20) | 1) - 1;
 		ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
-		ctrl |= size << 8;
+		ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT;
 		pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
 	}
 }
@@ -3098,7 +3098,7 @@ int pci_rebar_get_current_size(struct pci_dev *pdev, int bar)
 		return pos;
 
 	pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
-	return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> 8;
+	return (ctrl & PCI_REBAR_CTRL_BAR_SIZE) >> PCI_REBAR_CTRL_BAR_SHIFT;
 }
 
 /**
@@ -3121,7 +3121,7 @@ int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size)
 
 	pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl);
 	ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE;
-	ctrl |= size << 8;
+	ctrl |= size << PCI_REBAR_CTRL_BAR_SHIFT;
 	pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl);
 	return 0;
 }
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 4da87e2ef8a8..82e6b361204e 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -960,8 +960,9 @@
 #define PCI_REBAR_CTRL		8	/* control register */
 #define  PCI_REBAR_CTRL_BAR_IDX		0x00000007  /* BAR index */
 #define  PCI_REBAR_CTRL_NBAR_MASK	0x000000E0  /* # of resizable BARs */
-#define  PCI_REBAR_CTRL_NBAR_SHIFT	5  	    /* shift for # of BARs */
+#define  PCI_REBAR_CTRL_NBAR_SHIFT	5	    /* shift for # of BARs */
 #define  PCI_REBAR_CTRL_BAR_SIZE	0x00001F00  /* BAR size */
+#define  PCI_REBAR_CTRL_BAR_SHIFT	8	    /* shift for BAR size */
 
 /* Dynamic Power Allocation */
 #define PCI_DPA_CAP		4	/* capability register */
-- 
cgit v1.2.3


From 11eb0e0e8dea8b97cff972b09cf6fb033b729dff Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Mon, 4 Jun 2018 22:16:09 -0400
Subject: PCI: Make early dump functionality generic

Move early dump functionality into common code so that it is available for
all architectures.  No need to carry arch-specific reads around as the read
hooks are already initialized by the time pci_setup_device() is getting
called during scan.

Tested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  2 +-
 arch/x86/include/asm/pci-direct.h               |  4 ---
 arch/x86/kernel/setup.c                         |  5 ---
 arch/x86/pci/common.c                           |  4 ---
 arch/x86/pci/early.c                            | 44 -------------------------
 drivers/pci/pci.c                               |  5 +++
 drivers/pci/pci.h                               |  1 +
 drivers/pci/probe.c                             | 17 ++++++++++
 8 files changed, 24 insertions(+), 58 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..f11b9485ed7f 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2995,7 +2995,7 @@
 			See also Documentation/blockdev/paride.txt.
 
 	pci=option[,option...]	[PCI] various PCI subsystem options:
-		earlydump	[X86] dump PCI config space before the kernel
+		earlydump	dump PCI config space before the kernel
 				changes anything
 		off		[X86] don't probe for the PCI bus
 		bios		[X86-32] force use of PCI BIOS, don't access
diff --git a/arch/x86/include/asm/pci-direct.h b/arch/x86/include/asm/pci-direct.h
index e1084f71a295..94597a3cf3d0 100644
--- a/arch/x86/include/asm/pci-direct.h
+++ b/arch/x86/include/asm/pci-direct.h
@@ -15,8 +15,4 @@ extern void write_pci_config_byte(u8 bus, u8 slot, u8 func, u8 offset, u8 val);
 extern void write_pci_config_16(u8 bus, u8 slot, u8 func, u8 offset, u16 val);
 
 extern int early_pci_allowed(void);
-
-extern unsigned int pci_early_dump_regs;
-extern void early_dump_pci_device(u8 bus, u8 slot, u8 func);
-extern void early_dump_pci_devices(void);
 #endif /* _ASM_X86_PCI_DIRECT_H */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2f86d883dd95..480f250b3c4f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -991,11 +991,6 @@ void __init setup_arch(char **cmdline_p)
 		setup_clear_cpu_cap(X86_FEATURE_APIC);
 	}
 
-#ifdef CONFIG_PCI
-	if (pci_early_dump_regs)
-		early_dump_pci_devices();
-#endif
-
 	e820__reserve_setup_data();
 	e820__finish_early_params();
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 563049c483a1..d4ec117c1142 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -22,7 +22,6 @@
 unsigned int pci_probe = PCI_PROBE_BIOS | PCI_PROBE_CONF1 | PCI_PROBE_CONF2 |
 				PCI_PROBE_MMCONF;
 
-unsigned int pci_early_dump_regs;
 static int pci_bf_sort;
 int pci_routeirq;
 int noioapicquirk;
@@ -599,9 +598,6 @@ char *__init pcibios_setup(char *str)
 		pci_probe |= PCI_BIG_ROOT_WINDOW;
 		return NULL;
 #endif
-	} else if (!strcmp(str, "earlydump")) {
-		pci_early_dump_regs = 1;
-		return NULL;
 	} else if (!strcmp(str, "routeirq")) {
 		pci_routeirq = 1;
 		return NULL;
diff --git a/arch/x86/pci/early.c b/arch/x86/pci/early.c
index e5f753cbb1c3..f5fc953e5848 100644
--- a/arch/x86/pci/early.c
+++ b/arch/x86/pci/early.c
@@ -57,47 +57,3 @@ int early_pci_allowed(void)
 			PCI_PROBE_CONF1;
 }
 
-void early_dump_pci_device(u8 bus, u8 slot, u8 func)
-{
-	u32 value[256 / 4];
-	int i;
-
-	pr_info("pci 0000:%02x:%02x.%d config space:\n", bus, slot, func);
-
-	for (i = 0; i < 256; i += 4)
-		value[i / 4] = read_pci_config(bus, slot, func, i);
-
-	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1, value, 256, false);
-}
-
-void early_dump_pci_devices(void)
-{
-	unsigned bus, slot, func;
-
-	if (!early_pci_allowed())
-		return;
-
-	for (bus = 0; bus < 256; bus++) {
-		for (slot = 0; slot < 32; slot++) {
-			for (func = 0; func < 8; func++) {
-				u32 class;
-				u8 type;
-
-				class = read_pci_config(bus, slot, func,
-							PCI_CLASS_REVISION);
-				if (class == 0xffffffff)
-					continue;
-
-				early_dump_pci_device(bus, slot, func);
-
-				if (func == 0) {
-					type = read_pci_config_byte(bus, slot,
-								    func,
-							       PCI_HEADER_TYPE);
-					if (!(type & 0x80))
-						break;
-				}
-			}
-		}
-	}
-}
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1b20c4392f09..e1b0bbd05fa3 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -115,6 +115,9 @@ static bool pcie_ari_disabled;
 /* If set, the PCIe ATS capability will not be used. */
 static bool pcie_ats_disabled;
 
+/* If set, the PCI config space of each device is printed during boot. */
+bool pci_early_dump;
+
 bool pci_ats_disabled(void)
 {
 	return pcie_ats_disabled;
@@ -5833,6 +5836,8 @@ static int __init pci_setup(char *str)
 				pcie_ats_disabled = true;
 			} else if (!strcmp(str, "noaer")) {
 				pci_no_aer();
+			} else if (!strcmp(str, "earlydump")) {
+				pci_early_dump = true;
 			} else if (!strncmp(str, "realloc=", 8)) {
 				pci_realloc_get_opt(str + 8);
 			} else if (!strncmp(str, "realloc", 7)) {
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c358e7a07f3f..c33265e02c3a 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -7,6 +7,7 @@
 #define PCI_VSEC_ID_INTEL_TBT	0x1234	/* Thunderbolt */
 
 extern const unsigned char pcie_link_speed[];
+extern bool pci_early_dump;
 
 bool pcie_cap_has_lnkctl(const struct pci_dev *dev);
 
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..84034a685f83 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1549,6 +1549,20 @@ static int pci_intx_mask_broken(struct pci_dev *dev)
 	return 0;
 }
 
+static void early_dump_pci_device(struct pci_dev *pdev)
+{
+	u32 value[256 / 4];
+	int i;
+
+	pci_info(pdev, "config space:\n");
+
+	for (i = 0; i < 256; i += 4)
+		pci_read_config_dword(pdev, i, &value[i / 4]);
+
+	print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1,
+		       value, 256, false);
+}
+
 /**
  * pci_setup_device - Fill in class and map information of a device
  * @dev: the device structure to fill
@@ -1598,6 +1612,9 @@ int pci_setup_device(struct pci_dev *dev)
 	pci_printk(KERN_DEBUG, dev, "[%04x:%04x] type %02x class %#08x\n",
 		   dev->vendor, dev->device, dev->hdr_type, dev->class);
 
+	if (pci_early_dump)
+		early_dump_pci_device(dev);
+
 	/* Need to have dev->class ready */
 	dev->cfg_size = pci_cfg_space_size(dev);
 
-- 
cgit v1.2.3


From cfdfc14e7fb8ae77290e9d5afaeecc0a234a3846 Mon Sep 17 00:00:00 2001
From: Doug Meyer <dmeyer@gigaio.com>
Date: Wed, 23 May 2018 13:18:05 -0700
Subject: switchtec: Use generic PCI Vendor ID and Class Code

Move the Microsemi Switchtec PCI Vendor ID (same as
PCI_VENDOR_ID_PMC_Sierra) to pci_ids.h.   Also, replace Microsemi class
constants with the standard PCI definitions.

Signed-off-by: Doug Meyer <dmeyer@gigaio.com>
[bhelgaas: restore SPDX (I assume it was removed by mistake), remove
device ID definitions]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
---
 drivers/ntb/hw/mscc/ntb_hw_switchtec.c |  3 ++-
 drivers/pci/switch/switchtec.c         | 14 +++++++-------
 include/linux/pci_ids.h                |  1 +
 include/linux/switchtec.h              |  4 ----
 4 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
index f624ae27eabe..5ee5f40b4dfc 100644
--- a/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
+++ b/drivers/ntb/hw/mscc/ntb_hw_switchtec.c
@@ -19,6 +19,7 @@
 #include <linux/kthread.h>
 #include <linux/interrupt.h>
 #include <linux/ntb.h>
+#include <linux/pci.h>
 
 MODULE_DESCRIPTION("Microsemi Switchtec(tm) NTB Driver");
 MODULE_VERSION("0.1");
@@ -1487,7 +1488,7 @@ static int switchtec_ntb_add(struct device *dev,
 
 	stdev->sndev = NULL;
 
-	if (stdev->pdev->class != MICROSEMI_NTB_CLASSCODE)
+	if (stdev->pdev->class != (PCI_CLASS_BRIDGE_OTHER << 8))
 		return -ENODEV;
 
 	sndev = kzalloc_node(sizeof(*sndev), GFP_KERNEL, dev_to_node(dev));
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index 47cd0c037433..9940cc70f38b 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -641,7 +641,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev,
 
 	for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) {
 		reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id);
-		if (reg != MICROSEMI_VENDOR_ID)
+		if (reg != PCI_VENDOR_ID_MICROSEMI)
 			break;
 
 		reg = ioread32(&stdev->mmio_pff_csr[i].pff_event_summary);
@@ -1203,7 +1203,7 @@ static void init_pff(struct switchtec_dev *stdev)
 
 	for (i = 0; i < SWITCHTEC_MAX_PFF_CSR; i++) {
 		reg = ioread16(&stdev->mmio_pff_csr[i].vendor_id);
-		if (reg != MICROSEMI_VENDOR_ID)
+		if (reg != PCI_VENDOR_ID_MICROSEMI)
 			break;
 	}
 
@@ -1267,7 +1267,7 @@ static int switchtec_pci_probe(struct pci_dev *pdev,
 	struct switchtec_dev *stdev;
 	int rc;
 
-	if (pdev->class == MICROSEMI_NTB_CLASSCODE)
+	if (pdev->class == (PCI_CLASS_BRIDGE_OTHER << 8))
 		request_module_nowait("ntb_hw_switchtec");
 
 	stdev = stdev_create(pdev);
@@ -1321,19 +1321,19 @@ static void switchtec_pci_remove(struct pci_dev *pdev)
 
 #define SWITCHTEC_PCI_DEVICE(device_id) \
 	{ \
-		.vendor     = MICROSEMI_VENDOR_ID, \
+		.vendor     = PCI_VENDOR_ID_MICROSEMI, \
 		.device     = device_id, \
 		.subvendor  = PCI_ANY_ID, \
 		.subdevice  = PCI_ANY_ID, \
-		.class      = MICROSEMI_MGMT_CLASSCODE, \
+		.class      = (PCI_CLASS_MEMORY_OTHER << 8), \
 		.class_mask = 0xFFFFFFFF, \
 	}, \
 	{ \
-		.vendor     = MICROSEMI_VENDOR_ID, \
+		.vendor     = PCI_VENDOR_ID_MICROSEMI, \
 		.device     = device_id, \
 		.subvendor  = PCI_ANY_ID, \
 		.subdevice  = PCI_ANY_ID, \
-		.class      = MICROSEMI_NTB_CLASSCODE, \
+		.class      = (PCI_CLASS_BRIDGE_OTHER << 8), \
 		.class_mask = 0xFFFFFFFF, \
 	}
 
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 29502238e510..80aec5b9a6c1 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1668,6 +1668,7 @@
 #define PCI_DEVICE_ID_COMPEX_ENET100VG4	0x0112
 
 #define PCI_VENDOR_ID_PMC_Sierra	0x11f8
+#define PCI_VENDOR_ID_MICROSEMI		0x11f8
 
 #define PCI_VENDOR_ID_RP		0x11fe
 #define PCI_DEVICE_ID_RP32INTF		0x0001
diff --git a/include/linux/switchtec.h b/include/linux/switchtec.h
index ec93e93371fa..ab400af6f0ce 100644
--- a/include/linux/switchtec.h
+++ b/include/linux/switchtec.h
@@ -19,10 +19,6 @@
 #include <linux/pci.h>
 #include <linux/cdev.h>
 
-#define MICROSEMI_VENDOR_ID         0x11f8
-#define MICROSEMI_NTB_CLASSCODE     0x068000
-#define MICROSEMI_MGMT_CLASSCODE    0x058000
-
 #define SWITCHTEC_MRPC_PAYLOAD_SIZE 1024
 #define SWITCHTEC_MAX_PFF_CSR 48
 
-- 
cgit v1.2.3


From ad281ecf1c7d4c905607e049b967bb6412587ca1 Mon Sep 17 00:00:00 2001
From: Doug Meyer <dmeyer@gigaio.com>
Date: Wed, 23 May 2018 13:18:06 -0700
Subject: PCI: Add DMA alias quirk for Microsemi Switchtec NTB

Add a quirk for the Microsemi Switchtec parts to allow DMA access via
non-transparent bridging to work when the IOMMU is turned on.

This exclusively addresses the ability of a remote NT endpoint to perform
DMA accesses through the locally enumerated NT endpoint.  Other aspects of
the Switchtec NTB functionality, such as interrupts for doorbells and
messages are independent of this quirk, and will work whether the IOMMU is
on or off.

When a requestor on one NT endpoint accesses memory on another NT endpoint,
it does this via a devfn proxy ID.  Proxy IDs are statically assigned to
each NT endpoint by the NTB hardware as part of the release-from-reset
sequence prior to PCI enumeration.  These proxy IDs cannot be modified
dynamically, and are not visible to the host during enumeration.

When the Switchtec NTB driver loads it will map local requestor IDs, such
as the root complex and transparent bridge DMA engines, to proxy IDs by
populating those requestor IDs in hardware mapping table table entries.
This establishes a fixed relationship between a requestor ID and a proxy
ID.

When a peer on a remote NT endpoint performs an access within a particular
translation window in it's NT endpoint BAR address space, that access is
translated to a DMA request on the local endpoint's bus.  As part of the
translation process, the original requestor ID has its devfn replaced with
the proxy ID, and the bus portion of the BDF is replaced with the bus of
the local NT endpoint.  Thus, the DMA access from a remote NT endpoint will
appear on the local bus to have come from the unknown devfn which the IOMMU
will reject.

Interrogate NTB hardware registers for each remote NT endpoint to obtain
the proxy IDs that have been assigned to it and alias them to the local
(enumerated) NT endpoint's device.  The IOMMU then accepts the remote proxy
IDs as if they were requests coming directly from the enumerated endpoint,
giving remote requestors access to memory resources which the local host
has made available.

Note that the aliasing of the proxy IDs cannot be performed at the driver
level given the current IOMMU architecture.  Superficially this is because
pci_add_dma_alias() symbol is not exported.  Functionally, the current
IOMMU design requires the aliasing to be performed prior to the creation of
IOMMU groups.  If a driver were to attempt to use pci_add_dma_alias() in
its probe routine it would fail since the IOMMU groups have been set up by
that time.  If the Switchtec hardware supported dynamic proxy ID
(re-)assignment this would be an issue, but it does not.

To further clarify static proxy ID assignment: While the requester ID to
proxy ID mapping can be dynamically changed, the number and value of proxy
IDs given to an NT EP cannot, even for dynamic reconfiguration such as
hot-add.  Therefore, the chip configuration must account a priori for the
proxy IDs needs, considering both static and dynamic system configurations.
For example, a port on the chip may not having anything plugged into it at
start of day; but it must have a sufficient number of proxy IDs assigned to
accommodate the supported devices which may be hot-added.

Switchtec NTB functionality with the IOMMU off is unchanged by this quirk.

Signed-off-by: Doug Meyer <dmeyer@gigaio.com>
[bhelgaas: use hard-coded Device IDs instead of adding #defines for each]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
---
 drivers/pci/quirks.c | 140 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 140 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f439de848658..d54a182a09cf 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -27,6 +27,7 @@
 #include <linux/mm.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pm_runtime.h>
+#include <linux/switchtec.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
 #include "pci.h"
 
@@ -4753,3 +4754,142 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMD, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
+
+/*
+ * Microsemi Switchtec NTB uses devfn proxy IDs to move TLPs between
+ * NT endpoints via the internal switch fabric. These IDs replace the
+ * originating requestor ID TLPs which access host memory on peer NTB
+ * ports. Therefore, all proxy IDs must be aliased to the NTB device
+ * to permit access when the IOMMU is turned on.
+ */
+static void quirk_switchtec_ntb_dma_alias(struct pci_dev *pdev)
+{
+	void __iomem *mmio;
+	struct ntb_info_regs __iomem *mmio_ntb;
+	struct ntb_ctrl_regs __iomem *mmio_ctrl;
+	struct sys_info_regs __iomem *mmio_sys_info;
+	u64 partition_map;
+	u8 partition;
+	int pp;
+
+	if (pci_enable_device(pdev)) {
+		pci_err(pdev, "Cannot enable Switchtec device\n");
+		return;
+	}
+
+	mmio = pci_iomap(pdev, 0, 0);
+	if (mmio == NULL) {
+		pci_disable_device(pdev);
+		pci_err(pdev, "Cannot iomap Switchtec device\n");
+		return;
+	}
+
+	pci_info(pdev, "Setting Switchtec proxy ID aliases\n");
+
+	mmio_ntb = mmio + SWITCHTEC_GAS_NTB_OFFSET;
+	mmio_ctrl = (void __iomem *) mmio_ntb + SWITCHTEC_NTB_REG_CTRL_OFFSET;
+	mmio_sys_info = mmio + SWITCHTEC_GAS_SYS_INFO_OFFSET;
+
+	partition = ioread8(&mmio_ntb->partition_id);
+
+	partition_map = ioread32(&mmio_ntb->ep_map);
+	partition_map |= ((u64) ioread32(&mmio_ntb->ep_map + 4)) << 32;
+	partition_map &= ~(1ULL << partition);
+
+	for (pp = 0; pp < (sizeof(partition_map) * 8); pp++) {
+		struct ntb_ctrl_regs __iomem *mmio_peer_ctrl;
+		u32 table_sz = 0;
+		int te;
+
+		if (!(partition_map & (1ULL << pp)))
+			continue;
+
+		pci_dbg(pdev, "Processing partition %d\n", pp);
+
+		mmio_peer_ctrl = &mmio_ctrl[pp];
+
+		table_sz = ioread16(&mmio_peer_ctrl->req_id_table_size);
+		if (!table_sz) {
+			pci_warn(pdev, "Partition %d table_sz 0\n", pp);
+			continue;
+		}
+
+		if (table_sz > 512) {
+			pci_warn(pdev,
+				 "Invalid Switchtec partition %d table_sz %d\n",
+				 pp, table_sz);
+			continue;
+		}
+
+		for (te = 0; te < table_sz; te++) {
+			u32 rid_entry;
+			u8 devfn;
+
+			rid_entry = ioread32(&mmio_peer_ctrl->req_id_table[te]);
+			devfn = (rid_entry >> 1) & 0xFF;
+			pci_dbg(pdev,
+				"Aliasing Partition %d Proxy ID %02x.%d\n",
+				pp, PCI_SLOT(devfn), PCI_FUNC(devfn));
+			pci_add_dma_alias(pdev, devfn);
+		}
+	}
+
+	pci_iounmap(pdev, mmio);
+	pci_disable_device(pdev);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8531,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8532,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8533,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8534,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8535,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8536,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8543,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8544,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8545,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8546,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8551,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8552,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8553,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8554,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8555,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8556,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8561,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8562,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8563,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8564,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8565,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8566,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8571,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8572,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8573,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8574,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8575,
+			quirk_switchtec_ntb_dma_alias);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_MICROSEMI, 0x8576,
+			quirk_switchtec_ntb_dma_alias);
-- 
cgit v1.2.3


From 445ec321e71b3124abacfb358f72ac6a70d87602 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Tue, 5 Jun 2018 09:46:45 +0800
Subject: PCI: Avoid accessing memory outside the ROM BAR

pci_get_rom_size() accepts the base and size of the ROM BAR as arguments.
The byte at "rom + size" is the first byte *past* the ROM, so change ">" to
">=" to avoid accessing beyond the actual length of the ROM BAR.

Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
[bhelgaas: changelog]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/pci/rom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index a7b5c37a85ec..946795fc0071 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -106,7 +106,7 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
 		length = readw(pds + 16);
 		image += length * 512;
 		/* Avoid iterating through memory outside the resource window */
-		if (image > rom + size)
+		if (image >= rom + size)
 			break;
 	} while (length && !last_image);
 
-- 
cgit v1.2.3


From beced88e6af43c9653cee09f5111ae7495824e07 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Tue, 5 Jun 2018 09:46:46 +0800
Subject: PCI: Add check code for last image indicator not set

If the "last image" indicator was not set in the PCI data struct, print "No
more image in the PCI ROM" instead of looping back and printing "Invalid
PCI ROM header signature".

Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/pci/rom.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 946795fc0071..3a33f5ce314a 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -108,6 +108,12 @@ size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
 		/* Avoid iterating through memory outside the resource window */
 		if (image >= rom + size)
 			break;
+		if (!last_image) {
+			if (readw(image) != 0xAA55) {
+				pci_info(pdev, "No more image in the PCI ROM\n");
+				break;
+			}
+		}
 	} while (length && !last_image);
 
 	/* never return a size larger than the PCI resource window */
-- 
cgit v1.2.3


From 783e84961b1d7a75045383586b8c49e02b7704cd Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 29 Jun 2018 21:17:26 -0500
Subject: PCI: Make pci_get_rom_size() static

pci_get_rom_size() is called only from pci_map_rom(), so it can be static.
Make it static and remove the declaration from include/linux/pci.h.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/rom.c   | 3 ++-
 include/linux/pci.h | 1 -
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c
index 3a33f5ce314a..137bf0cee897 100644
--- a/drivers/pci/rom.c
+++ b/drivers/pci/rom.c
@@ -80,7 +80,8 @@ EXPORT_SYMBOL_GPL(pci_disable_rom);
  * The PCI window size could be much larger than the
  * actual image size.
  */
-size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size)
+static size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom,
+			       size_t size)
 {
 	void __iomem *image;
 	int last_image;
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..f40d3e05ccd1 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1122,7 +1122,6 @@ int pci_enable_rom(struct pci_dev *pdev);
 void pci_disable_rom(struct pci_dev *pdev);
 void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size);
 void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom);
-size_t pci_get_rom_size(struct pci_dev *pdev, void __iomem *rom, size_t size);
 void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size);
 
 /* Power management related routines */
-- 
cgit v1.2.3


From 1f705bc61aee5fab2826bcf6de152a5d92378a85 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 27 Jun 2018 15:57:02 +0100
Subject: net: stmmac: Add support for CBS QDISC

This adds support for CBS reconfiguration using the TC application.

A new callback was added to TC ops struct and another one to DMA ops to
reconfigure the channel mode.

Tested in GMAC5.10.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Vitor Soares <soares@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c  | 15 ++++++
 drivers/net/ethernet/stmicro/stmmac/hwif.h        |  8 +++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c |  2 +
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c   | 62 +++++++++++++++++++++++
 4 files changed, 87 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
index d37f17ca62fe..6e32f8a3710b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c
@@ -407,6 +407,19 @@ static void dwmac4_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
 	}
 }
 
+static void dwmac4_qmode(void __iomem *ioaddr, u32 channel, u8 qmode)
+{
+	u32 mtl_tx_op = readl(ioaddr + MTL_CHAN_TX_OP_MODE(channel));
+
+	mtl_tx_op &= ~MTL_OP_MODE_TXQEN_MASK;
+	if (qmode != MTL_QUEUE_AVB)
+		mtl_tx_op |= MTL_OP_MODE_TXQEN;
+	else
+		mtl_tx_op |= MTL_OP_MODE_TXQEN_AV;
+
+	writel(mtl_tx_op, ioaddr +  MTL_CHAN_TX_OP_MODE(channel));
+}
+
 const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.reset = dwmac4_dma_reset,
 	.init = dwmac4_dma_init,
@@ -431,6 +444,7 @@ const struct stmmac_dma_ops dwmac4_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.qmode = dwmac4_qmode,
 };
 
 const struct stmmac_dma_ops dwmac410_dma_ops = {
@@ -457,4 +471,5 @@ const struct stmmac_dma_ops dwmac410_dma_ops = {
 	.set_rx_tail_ptr = dwmac4_set_rx_tail_ptr,
 	.set_tx_tail_ptr = dwmac4_set_tx_tail_ptr,
 	.enable_tso = dwmac4_enable_tso,
+	.qmode = dwmac4_qmode,
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index e44e7b26ce82..e2a965790648 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -183,6 +183,7 @@ struct stmmac_dma_ops {
 	void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan);
 	void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan);
+	void (*qmode)(void __iomem *ioaddr, u32 channel, u8 qmode);
 };
 
 #define stmmac_reset(__priv, __args...) \
@@ -235,6 +236,8 @@ struct stmmac_dma_ops {
 	stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args)
 #define stmmac_enable_tso(__priv, __args...) \
 	stmmac_do_void_callback(__priv, dma, enable_tso, __args)
+#define stmmac_dma_qmode(__priv, __args...) \
+	stmmac_do_void_callback(__priv, dma, qmode, __args)
 
 struct mac_device_info;
 struct net_device;
@@ -441,17 +444,22 @@ struct stmmac_mode_ops {
 
 struct stmmac_priv;
 struct tc_cls_u32_offload;
+struct tc_cbs_qopt_offload;
 
 struct stmmac_tc_ops {
 	int (*init)(struct stmmac_priv *priv);
 	int (*setup_cls_u32)(struct stmmac_priv *priv,
 			     struct tc_cls_u32_offload *cls);
+	int (*setup_cbs)(struct stmmac_priv *priv,
+			 struct tc_cbs_qopt_offload *qopt);
 };
 
 #define stmmac_tc_init(__priv, __args...) \
 	stmmac_do_callback(__priv, tc, init, __args)
 #define stmmac_tc_setup_cls_u32(__priv, __args...) \
 	stmmac_do_callback(__priv, tc, setup_cls_u32, __args)
+#define stmmac_tc_setup_cbs(__priv, __args...) \
+	stmmac_do_callback(__priv, tc, setup_cbs, __args)
 
 struct stmmac_regs_off {
 	u32 ptp_off;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 2354e30caa78..93a3bea8576e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3793,6 +3793,8 @@ static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 	switch (type) {
 	case TC_SETUP_BLOCK:
 		return stmmac_setup_tc_block(priv, type_data);
+	case TC_SETUP_QDISC_CBS:
+		return stmmac_tc_setup_cbs(priv, priv, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 2258cd8cc844..0b0fca0200b2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -289,7 +289,69 @@ static int tc_init(struct stmmac_priv *priv)
 	return 0;
 }
 
+static int tc_setup_cbs(struct stmmac_priv *priv,
+			struct tc_cbs_qopt_offload *qopt)
+{
+	u32 tx_queues_count = priv->plat->tx_queues_to_use;
+	u32 queue = qopt->queue;
+	u32 ptr, speed_div;
+	u32 mode_to_use;
+	u64 value;
+	int ret;
+
+	/* Queue 0 is not AVB capable */
+	if (queue <= 0 || queue >= tx_queues_count)
+		return -EINVAL;
+	if (priv->speed != SPEED_100 && priv->speed != SPEED_1000)
+		return -EOPNOTSUPP;
+
+	mode_to_use = priv->plat->tx_queues_cfg[queue].mode_to_use;
+	if (mode_to_use == MTL_QUEUE_DCB && qopt->enable) {
+		ret = stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_AVB);
+		if (ret)
+			return ret;
+
+		priv->plat->tx_queues_cfg[queue].mode_to_use = MTL_QUEUE_AVB;
+	} else if (!qopt->enable) {
+		return stmmac_dma_qmode(priv, priv->ioaddr, queue, MTL_QUEUE_DCB);
+	}
+
+	/* Port Transmit Rate and Speed Divider */
+	ptr = (priv->speed == SPEED_100) ? 4 : 8;
+	speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000;
+
+	/* Final adjustments for HW */
+	value = qopt->idleslope * 1024 * ptr;
+	do_div(value, speed_div);
+	priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0);
+
+	value = -qopt->sendslope * 1024UL * ptr;
+	do_div(value, speed_div);
+	priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0);
+
+	value = qopt->hicredit * 1024 * 8;
+	priv->plat->tx_queues_cfg[queue].high_credit = value & GENMASK(31, 0);
+
+	value = qopt->locredit * 1024 * 8;
+	priv->plat->tx_queues_cfg[queue].low_credit = value & GENMASK(31, 0);
+
+	ret = stmmac_config_cbs(priv, priv->hw,
+				priv->plat->tx_queues_cfg[queue].send_slope,
+				priv->plat->tx_queues_cfg[queue].idle_slope,
+				priv->plat->tx_queues_cfg[queue].high_credit,
+				priv->plat->tx_queues_cfg[queue].low_credit,
+				queue);
+	if (ret)
+		return ret;
+
+	dev_info(priv->device, "CBS queue %d: send %d, idle %d, hi %d, lo %d\n",
+			queue, qopt->sendslope, qopt->idleslope,
+			qopt->hicredit, qopt->locredit);
+	return 0;
+}
+
 const struct stmmac_tc_ops dwmac510_tc_ops = {
 	.init = tc_init,
 	.setup_cls_u32 = tc_setup_cls_u32,
+	.setup_cbs = tc_setup_cbs,
 };
-- 
cgit v1.2.3


From 83607344d667315687e1a5ddd2ad2fbbff22cc43 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 27 Jun 2018 20:32:23 -0500
Subject: bnx2x: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c  | 3 +++
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c  | 4 ++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c    | 4 ++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c | 1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 2 +-
 5 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
index 22243c480a05..98d4c5a3ff21 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_link.c
@@ -6339,6 +6339,7 @@ int bnx2x_set_led(struct link_params *params,
 		 */
 		if (!vars->link_up)
 			break;
+		/* else: fall through */
 	case LED_MODE_ON:
 		if (((params->phy[EXT_PHY1].type ==
 			  PORT_HW_CFG_XGXS_EXT_PHY_TYPE_BCM8727) ||
@@ -12521,11 +12522,13 @@ static void bnx2x_phy_def_cfg(struct link_params *params,
 	switch (link_config  & PORT_FEATURE_LINK_SPEED_MASK) {
 	case PORT_FEATURE_LINK_SPEED_10M_HALF:
 		phy->req_duplex = DUPLEX_HALF;
+		/* fall through */
 	case PORT_FEATURE_LINK_SPEED_10M_FULL:
 		phy->req_line_speed = SPEED_10;
 		break;
 	case PORT_FEATURE_LINK_SPEED_100M_HALF:
 		phy->req_duplex = DUPLEX_HALF;
+		/* fall through */
 	case PORT_FEATURE_LINK_SPEED_100M_FULL:
 		phy->req_line_speed = SPEED_100;
 		break;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index 5b1ed240bf18..44a6f2802bab 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -8561,11 +8561,11 @@ int bnx2x_set_int_mode(struct bnx2x *bp)
 			       bp->num_queues,
 			       1 + bp->num_cnic_queues);
 
-		/* falling through... */
+		/* fall through */
 	case BNX2X_INT_MODE_MSI:
 		bnx2x_enable_msi(bp);
 
-		/* falling through... */
+		/* fall through */
 	case BNX2X_INT_MODE_INTX:
 		bp->num_ethernet_queues = 1;
 		bp->num_queues = bp->num_ethernet_queues + bp->num_cnic_queues;
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
index 8baf9d3eb4b1..3f4d2c8da21a 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -3258,7 +3258,7 @@ static int bnx2x_mcast_validate_e2(struct bnx2x *bp,
 	/* DEL command deletes all currently configured MACs */
 	case BNX2X_MCAST_CMD_DEL:
 		o->set_registry_size(o, 0);
-		/* Don't break */
+		/* fall through */
 
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
@@ -3592,7 +3592,7 @@ static int bnx2x_mcast_validate_e1(struct bnx2x *bp,
 	/* DEL command deletes all currently configured MACs */
 	case BNX2X_MCAST_CMD_DEL:
 		o->set_registry_size(o, 0);
-		/* Don't break */
+		/* fall through */
 
 	/* RESTORE command will restore the entire multicast configuration */
 	case BNX2X_MCAST_CMD_RESTORE:
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
index dc77bfded865..62da46537734 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c
@@ -1827,6 +1827,7 @@ get_vf:
 		DP(BNX2X_MSG_IOV, "got VF [%d:%d] RSS update ramrod\n",
 		   vf->abs_vfid, qidx);
 		bnx2x_vf_handle_rss_update_eqe(bp, vf);
+		/* fall through */
 	case EVENT_RING_OPCODE_VF_FLR:
 		/* Do nothing for now */
 		return 0;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b5fc6414a951..d2dadade1d0e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1727,7 +1727,7 @@ static int bnxt_async_event_process(struct bnxt *bp,
 					    speed);
 		}
 		set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event);
-		/* fall thru */
+		/* fall through */
 	}
 	case ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
 		set_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event);
-- 
cgit v1.2.3


From ea5d0c32498e1a08ff5f3dbeafa4d74895851b0d Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Thu, 28 Jun 2018 00:22:56 -0400
Subject: tcp: add new SNMP counter for drops when try to queue in rcv queue

When sk_rmem_alloc is larger than the receive buffer and we can't
schedule more memory for it, the skb will be dropped.

In above situation, if this skb is put into the ofo queue,
LINUX_MIB_TCPOFODROP is incremented to track it.

While if this skb is put into the receive queue, there's no record.
So a new SNMP counter is introduced to track this behavior.

LINUX_MIB_TCPRCVQDROP:  Number of packets meant to be queued in rcv queue
			but dropped because socket rcvbuf limit hit.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/snmp.h | 1 +
 net/ipv4/proc.c           | 1 +
 net/ipv4/tcp_input.c      | 8 ++++++--
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 97517f36a5f9..e5ebc83827ab 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -280,6 +280,7 @@ enum
 	LINUX_MIB_TCPDELIVEREDCE,		/* TCPDeliveredCE */
 	LINUX_MIB_TCPACKCOMPRESSED,		/* TCPAckCompressed */
 	LINUX_MIB_TCPZEROWINDOWDROP,		/* TCPZeroWindowDrop */
+	LINUX_MIB_TCPRCVQDROP,			/* TCPRcvQDrop */
 	__LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 225ef3433fe5..b46e4cf9a55a 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -288,6 +288,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE),
 	SNMP_MIB_ITEM("TCPAckCompressed", LINUX_MIB_TCPACKCOMPRESSED),
 	SNMP_MIB_ITEM("TCPZeroWindowDrop", LINUX_MIB_TCPZEROWINDOWDROP),
+	SNMP_MIB_ITEM("TCPRcvQDrop", LINUX_MIB_TCPRCVQDROP),
 	SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9c5b3415413f..eecd359595fc 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4611,8 +4611,10 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
 	skb->data_len = data_len;
 	skb->len = size;
 
-	if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+	if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
 		goto err_free;
+	}
 
 	err = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
 	if (err)
@@ -4677,8 +4679,10 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 queue_and_out:
 		if (skb_queue_len(&sk->sk_receive_queue) == 0)
 			sk_forced_mem_schedule(sk, skb->truesize);
-		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
+		else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) {
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP);
 			goto drop;
+		}
 
 		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
 		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
-- 
cgit v1.2.3


From 7b9c7d7dc539308e4b08974ebeba9cc1f685320b Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 28 Jun 2018 14:42:04 +0200
Subject: net: mvpp2: Make TX / RX descriptors little-endian

The PPv2 controller always expect descriptors to be in little endian. We
must therefore force descriptors to use that format, and convert to the
host endianness when necessary.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h      | 56 ++++++++++++-------------
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 41 +++++++++---------
 2 files changed, 50 insertions(+), 47 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index def00dc3eb4e..fa314b272853 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -831,52 +831,52 @@ struct mvpp2_port {
 
 /* HW TX descriptor for PPv2.1 */
 struct mvpp21_tx_desc {
-	u32 command;		/* Options used by HW for packet transmitting.*/
+	__le32 command;		/* Options used by HW for packet transmitting.*/
 	u8  packet_offset;	/* the offset from the buffer beginning	*/
 	u8  phys_txq;		/* destination queue ID			*/
-	u16 data_size;		/* data size of transmitted packet in bytes */
-	u32 buf_dma_addr;	/* physical addr of transmitted buffer	*/
-	u32 buf_cookie;		/* cookie for access to TX buffer in tx path */
-	u32 reserved1[3];	/* hw_cmd (for future use, BM, PON, PNC) */
-	u32 reserved2;		/* reserved (for future use)		*/
+	__le16 data_size;	/* data size of transmitted packet in bytes */
+	__le32 buf_dma_addr;	/* physical addr of transmitted buffer	*/
+	__le32 buf_cookie;	/* cookie for access to TX buffer in tx path */
+	__le32 reserved1[3];	/* hw_cmd (for future use, BM, PON, PNC) */
+	__le32 reserved2;	/* reserved (for future use)		*/
 };
 
 /* HW RX descriptor for PPv2.1 */
 struct mvpp21_rx_desc {
-	u32 status;		/* info about received packet		*/
-	u16 reserved1;		/* parser_info (for future use, PnC)	*/
-	u16 data_size;		/* size of received packet in bytes	*/
-	u32 buf_dma_addr;	/* physical address of the buffer	*/
-	u32 buf_cookie;		/* cookie for access to RX buffer in rx path */
-	u16 reserved2;		/* gem_port_id (for future use, PON)	*/
-	u16 reserved3;		/* csum_l4 (for future use, PnC)	*/
+	__le32 status;		/* info about received packet		*/
+	__le16 reserved1;	/* parser_info (for future use, PnC)	*/
+	__le16 data_size;	/* size of received packet in bytes	*/
+	__le32 buf_dma_addr;	/* physical address of the buffer	*/
+	__le32 buf_cookie;	/* cookie for access to RX buffer in rx path */
+	__le16 reserved2;	/* gem_port_id (for future use, PON)	*/
+	__le16 reserved3;	/* csum_l4 (for future use, PnC)	*/
 	u8  reserved4;		/* bm_qset (for future use, BM)		*/
 	u8  reserved5;
-	u16 reserved6;		/* classify_info (for future use, PnC)	*/
-	u32 reserved7;		/* flow_id (for future use, PnC) */
-	u32 reserved8;
+	__le16 reserved6;	/* classify_info (for future use, PnC)	*/
+	__le32 reserved7;	/* flow_id (for future use, PnC) */
+	__le32 reserved8;
 };
 
 /* HW TX descriptor for PPv2.2 */
 struct mvpp22_tx_desc {
-	u32 command;
+	__le32 command;
 	u8  packet_offset;
 	u8  phys_txq;
-	u16 data_size;
-	u64 reserved1;
-	u64 buf_dma_addr_ptp;
-	u64 buf_cookie_misc;
+	__le16 data_size;
+	__le64 reserved1;
+	__le64 buf_dma_addr_ptp;
+	__le64 buf_cookie_misc;
 };
 
 /* HW RX descriptor for PPv2.2 */
 struct mvpp22_rx_desc {
-	u32 status;
-	u16 reserved1;
-	u16 data_size;
-	u32 reserved2;
-	u32 reserved3;
-	u64 buf_dma_addr_key_hash;
-	u64 buf_cookie_misc;
+	__le32 status;
+	__le16 reserved1;
+	__le16 data_size;
+	__le32 reserved2;
+	__le32 reserved3;
+	__le64 buf_dma_addr_key_hash;
+	__le64 buf_cookie_misc;
 };
 
 /* Opaque type used by the driver to manipulate the HW TX and RX
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 0319ed9ef8b8..ded187a20b6c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -151,9 +151,10 @@ static dma_addr_t mvpp2_txdesc_dma_addr_get(struct mvpp2_port *port,
 					    struct mvpp2_tx_desc *tx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return tx_desc->pp21.buf_dma_addr;
+		return le32_to_cpu(tx_desc->pp21.buf_dma_addr);
 	else
-		return tx_desc->pp22.buf_dma_addr_ptp & MVPP2_DESC_DMA_MASK;
+		return le64_to_cpu(tx_desc->pp22.buf_dma_addr_ptp) &
+		       MVPP2_DESC_DMA_MASK;
 }
 
 static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
@@ -166,12 +167,12 @@ static void mvpp2_txdesc_dma_addr_set(struct mvpp2_port *port,
 	offset = dma_addr & MVPP2_TX_DESC_ALIGN;
 
 	if (port->priv->hw_version == MVPP21) {
-		tx_desc->pp21.buf_dma_addr = addr;
+		tx_desc->pp21.buf_dma_addr = cpu_to_le32(addr);
 		tx_desc->pp21.packet_offset = offset;
 	} else {
-		u64 val = (u64)addr;
+		__le64 val = cpu_to_le64(addr);
 
-		tx_desc->pp22.buf_dma_addr_ptp &= ~MVPP2_DESC_DMA_MASK;
+		tx_desc->pp22.buf_dma_addr_ptp &= ~cpu_to_le64(MVPP2_DESC_DMA_MASK);
 		tx_desc->pp22.buf_dma_addr_ptp |= val;
 		tx_desc->pp22.packet_offset = offset;
 	}
@@ -181,9 +182,9 @@ static size_t mvpp2_txdesc_size_get(struct mvpp2_port *port,
 				    struct mvpp2_tx_desc *tx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return tx_desc->pp21.data_size;
+		return le16_to_cpu(tx_desc->pp21.data_size);
 	else
-		return tx_desc->pp22.data_size;
+		return le16_to_cpu(tx_desc->pp22.data_size);
 }
 
 static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
@@ -191,9 +192,9 @@ static void mvpp2_txdesc_size_set(struct mvpp2_port *port,
 				  size_t size)
 {
 	if (port->priv->hw_version == MVPP21)
-		tx_desc->pp21.data_size = size;
+		tx_desc->pp21.data_size = cpu_to_le16(size);
 	else
-		tx_desc->pp22.data_size = size;
+		tx_desc->pp22.data_size = cpu_to_le16(size);
 }
 
 static void mvpp2_txdesc_txq_set(struct mvpp2_port *port,
@@ -211,9 +212,9 @@ static void mvpp2_txdesc_cmd_set(struct mvpp2_port *port,
 				 unsigned int command)
 {
 	if (port->priv->hw_version == MVPP21)
-		tx_desc->pp21.command = command;
+		tx_desc->pp21.command = cpu_to_le32(command);
 	else
-		tx_desc->pp22.command = command;
+		tx_desc->pp22.command = cpu_to_le32(command);
 }
 
 static unsigned int mvpp2_txdesc_offset_get(struct mvpp2_port *port,
@@ -229,36 +230,38 @@ static dma_addr_t mvpp2_rxdesc_dma_addr_get(struct mvpp2_port *port,
 					    struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.buf_dma_addr;
+		return le32_to_cpu(rx_desc->pp21.buf_dma_addr);
 	else
-		return rx_desc->pp22.buf_dma_addr_key_hash & MVPP2_DESC_DMA_MASK;
+		return le64_to_cpu(rx_desc->pp22.buf_dma_addr_key_hash) &
+		       MVPP2_DESC_DMA_MASK;
 }
 
 static unsigned long mvpp2_rxdesc_cookie_get(struct mvpp2_port *port,
 					     struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.buf_cookie;
+		return le32_to_cpu(rx_desc->pp21.buf_cookie);
 	else
-		return rx_desc->pp22.buf_cookie_misc & MVPP2_DESC_DMA_MASK;
+		return le64_to_cpu(rx_desc->pp22.buf_cookie_misc) &
+		       MVPP2_DESC_DMA_MASK;
 }
 
 static size_t mvpp2_rxdesc_size_get(struct mvpp2_port *port,
 				    struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.data_size;
+		return le16_to_cpu(rx_desc->pp21.data_size);
 	else
-		return rx_desc->pp22.data_size;
+		return le16_to_cpu(rx_desc->pp22.data_size);
 }
 
 static u32 mvpp2_rxdesc_status_get(struct mvpp2_port *port,
 				   struct mvpp2_rx_desc *rx_desc)
 {
 	if (port->priv->hw_version == MVPP21)
-		return rx_desc->pp21.status;
+		return le32_to_cpu(rx_desc->pp21.status);
 	else
-		return rx_desc->pp22.status;
+		return le32_to_cpu(rx_desc->pp22.status);
 }
 
 static void mvpp2_txq_inc_get(struct mvpp2_txq_pcpu *txq_pcpu)
-- 
cgit v1.2.3


From bd43d1ba12b71bda33bac82cff623bb8fa19b953 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 28 Jun 2018 14:42:05 +0200
Subject: net: mvpp2: prs: Drop unions representing TCAM and SRAM entries

PPv2's Header Parser use some large TCAM and SRAM entries, that are
duplicated in software so that we can write them to hardware only when
we are done modifying them.

Currently, PPv2 uses a union containing arrays of u32 and u8 to represent
these entries, to facilitate byte per byte access. This representation is
broken when we want to support big endian, and this makes the code
confusing to read.

This patch drops the union, and simply stores the TCAM and SRAM entries
as u32 arrays, each entry corresponding to a 32-bit register.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h     |   2 +
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 149 +++++++++++--------------
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h |  41 ++++---
 3 files changed, 87 insertions(+), 105 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index fa314b272853..81a66cce7fa8 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -553,6 +553,8 @@
 	((total_size) - NET_SKB_PAD - MVPP2_SKB_SHINFO_SIZE)
 
 #define MVPP2_BIT_TO_BYTE(bit)		((bit) / 8)
+#define MVPP2_BIT_TO_WORD(bit)		((bit) / 32)
+#define MVPP2_BIT_IN_WORD(bit)		((bit) % 32)
 
 /* IPv6 max L3 address size */
 #define MVPP2_MAX_L3_ADDR_SIZE		16
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 6bb69f086794..af11feea681c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -30,17 +30,17 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 		return -EINVAL;
 
 	/* Clear entry invalidation bit */
-	pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
+	pe->tcam[MVPP2_PRS_TCAM_INV_WORD] &= ~MVPP2_PRS_TCAM_INV_MASK;
 
 	/* Write tcam index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
 	for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
-		mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam.word[i]);
+		mvpp2_write(priv, MVPP2_PRS_TCAM_DATA_REG(i), pe->tcam[i]);
 
 	/* Write sram index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
 	for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
-		mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram.word[i]);
+		mvpp2_write(priv, MVPP2_PRS_SRAM_DATA_REG(i), pe->sram[i]);
 
 	return 0;
 }
@@ -60,18 +60,18 @@ static int mvpp2_prs_init_from_hw(struct mvpp2 *priv,
 	/* Write tcam index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_TCAM_IDX_REG, pe->index);
 
-	pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
+	pe->tcam[MVPP2_PRS_TCAM_INV_WORD] = mvpp2_read(priv,
 			      MVPP2_PRS_TCAM_DATA_REG(MVPP2_PRS_TCAM_INV_WORD));
-	if (pe->tcam.word[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
+	if (pe->tcam[MVPP2_PRS_TCAM_INV_WORD] & MVPP2_PRS_TCAM_INV_MASK)
 		return MVPP2_PRS_TCAM_ENTRY_INVALID;
 
 	for (i = 0; i < MVPP2_PRS_TCAM_WORDS; i++)
-		pe->tcam.word[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
+		pe->tcam[i] = mvpp2_read(priv, MVPP2_PRS_TCAM_DATA_REG(i));
 
 	/* Write sram index - indirect access */
 	mvpp2_write(priv, MVPP2_PRS_SRAM_IDX_REG, pe->index);
 	for (i = 0; i < MVPP2_PRS_SRAM_WORDS; i++)
-		pe->sram.word[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
+		pe->sram[i] = mvpp2_read(priv, MVPP2_PRS_SRAM_DATA_REG(i));
 
 	return 0;
 }
@@ -103,42 +103,35 @@ static void mvpp2_prs_shadow_ri_set(struct mvpp2 *priv, int index,
 /* Update lookup field in tcam sw entry */
 static void mvpp2_prs_tcam_lu_set(struct mvpp2_prs_entry *pe, unsigned int lu)
 {
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_LU_BYTE);
-
-	pe->tcam.byte[MVPP2_PRS_TCAM_LU_BYTE] = lu;
-	pe->tcam.byte[enable_off] = MVPP2_PRS_LU_MASK;
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU(MVPP2_PRS_LU_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] &= ~MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU(lu & MVPP2_PRS_LU_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_LU_WORD] |= MVPP2_PRS_TCAM_LU_EN(MVPP2_PRS_LU_MASK);
 }
 
 /* Update mask for single port in tcam sw entry */
 static void mvpp2_prs_tcam_port_set(struct mvpp2_prs_entry *pe,
 				    unsigned int port, bool add)
 {
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
 	if (add)
-		pe->tcam.byte[enable_off] &= ~(1 << port);
+		pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(BIT(port));
 	else
-		pe->tcam.byte[enable_off] |= 1 << port;
+		pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(BIT(port));
 }
 
 /* Update port map in tcam sw entry */
 static void mvpp2_prs_tcam_port_map_set(struct mvpp2_prs_entry *pe,
 					unsigned int ports)
 {
-	unsigned char port_mask = MVPP2_PRS_PORT_MASK;
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
-	pe->tcam.byte[MVPP2_PRS_TCAM_PORT_BYTE] = 0;
-	pe->tcam.byte[enable_off] &= ~port_mask;
-	pe->tcam.byte[enable_off] |= ~ports & MVPP2_PRS_PORT_MASK;
+	pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT(MVPP2_PRS_PORT_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] &= ~MVPP2_PRS_TCAM_PORT_EN(MVPP2_PRS_PORT_MASK);
+	pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] |= MVPP2_PRS_TCAM_PORT_EN(~ports & MVPP2_PRS_PORT_MASK);
 }
 
 /* Obtain port map from tcam sw entry */
 static unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
 {
-	int enable_off = MVPP2_PRS_TCAM_EN_OFFS(MVPP2_PRS_TCAM_PORT_BYTE);
-
-	return ~(pe->tcam.byte[enable_off]) & MVPP2_PRS_PORT_MASK;
+	return (~pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] >> 24) & MVPP2_PRS_PORT_MASK;
 }
 
 /* Set byte of data and its enable bits in tcam sw entry */
@@ -146,8 +139,12 @@ static void mvpp2_prs_tcam_data_byte_set(struct mvpp2_prs_entry *pe,
 					 unsigned int offs, unsigned char byte,
 					 unsigned char enable)
 {
-	pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)] = byte;
-	pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)] = enable;
+	int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(0xff << pos);
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] &= ~(MVPP2_PRS_TCAM_EN(0xff) << pos);
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= byte << pos;
+	pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] |= MVPP2_PRS_TCAM_EN(enable << pos);
 }
 
 /* Get byte of data and its enable bits from tcam sw entry */
@@ -155,46 +152,45 @@ static void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
 					 unsigned int offs, unsigned char *byte,
 					 unsigned char *enable)
 {
-	*byte = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(offs)];
-	*enable = pe->tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)];
+	int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
+
+	*byte = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> pos) & 0xff;
+	*enable = (pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] >> (pos + 16)) & 0xff;
 }
 
 /* Compare tcam data bytes with a pattern */
 static bool mvpp2_prs_tcam_data_cmp(struct mvpp2_prs_entry *pe, int offs,
 				    u16 data)
 {
-	int off = MVPP2_PRS_TCAM_DATA_BYTE(offs);
 	u16 tcam_data;
 
-	tcam_data = (pe->tcam.byte[off + 1] << 8) | pe->tcam.byte[off];
-	if (tcam_data != data)
-		return false;
-	return true;
+	tcam_data = pe->tcam[MVPP2_PRS_BYTE_TO_WORD(offs)] & 0xffff;
+	return tcam_data == data;
 }
 
 /* Update ai bits in tcam sw entry */
 static void mvpp2_prs_tcam_ai_update(struct mvpp2_prs_entry *pe,
 				     unsigned int bits, unsigned int enable)
 {
-	int i, ai_idx = MVPP2_PRS_TCAM_AI_BYTE;
+	int i;
 
 	for (i = 0; i < MVPP2_PRS_AI_BITS; i++) {
 		if (!(enable & BIT(i)))
 			continue;
 
 		if (bits & BIT(i))
-			pe->tcam.byte[ai_idx] |= 1 << i;
+			pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= BIT(i);
 		else
-			pe->tcam.byte[ai_idx] &= ~(1 << i);
+			pe->tcam[MVPP2_PRS_TCAM_AI_WORD] &= ~BIT(i);
 	}
 
-	pe->tcam.byte[MVPP2_PRS_TCAM_EN_OFFS(ai_idx)] |= enable;
+	pe->tcam[MVPP2_PRS_TCAM_AI_WORD] |= MVPP2_PRS_TCAM_AI_EN(enable);
 }
 
 /* Get ai bits from tcam sw entry */
 static int mvpp2_prs_tcam_ai_get(struct mvpp2_prs_entry *pe)
 {
-	return pe->tcam.byte[MVPP2_PRS_TCAM_AI_BYTE];
+	return pe->tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK;
 }
 
 /* Set ethertype in tcam sw entry */
@@ -215,16 +211,16 @@ static void mvpp2_prs_match_vid(struct mvpp2_prs_entry *pe, int offset,
 
 /* Set bits in sram sw entry */
 static void mvpp2_prs_sram_bits_set(struct mvpp2_prs_entry *pe, int bit_num,
-				    int val)
+				    u32 val)
 {
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] |= (val << (bit_num % 8));
+	pe->sram[MVPP2_BIT_TO_WORD(bit_num)] |= (val << (MVPP2_BIT_IN_WORD(bit_num)));
 }
 
 /* Clear bits in sram sw entry */
 static void mvpp2_prs_sram_bits_clear(struct mvpp2_prs_entry *pe, int bit_num,
-				      int val)
+				      u32 val)
 {
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(bit_num)] &= ~(val << (bit_num % 8));
+	pe->sram[MVPP2_BIT_TO_WORD(bit_num)] &= ~(val << (MVPP2_BIT_IN_WORD(bit_num)));
 }
 
 /* Update ri bits in sram sw entry */
@@ -234,15 +230,16 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe,
 	unsigned int i;
 
 	for (i = 0; i < MVPP2_PRS_SRAM_RI_CTRL_BITS; i++) {
-		int ri_off = MVPP2_PRS_SRAM_RI_OFFS;
-
 		if (!(mask & BIT(i)))
 			continue;
 
 		if (bits & BIT(i))
-			mvpp2_prs_sram_bits_set(pe, ri_off + i, 1);
+			mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_OFFS + i,
+						1);
 		else
-			mvpp2_prs_sram_bits_clear(pe, ri_off + i, 1);
+			mvpp2_prs_sram_bits_clear(pe,
+						  MVPP2_PRS_SRAM_RI_OFFS + i,
+						  1);
 
 		mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_RI_CTRL_OFFS + i, 1);
 	}
@@ -251,7 +248,7 @@ static void mvpp2_prs_sram_ri_update(struct mvpp2_prs_entry *pe,
 /* Obtain ri bits from sram sw entry */
 static int mvpp2_prs_sram_ri_get(struct mvpp2_prs_entry *pe)
 {
-	return pe->sram.word[MVPP2_PRS_SRAM_RI_WORD];
+	return pe->sram[MVPP2_PRS_SRAM_RI_WORD];
 }
 
 /* Update ai bits in sram sw entry */
@@ -259,16 +256,18 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe,
 				     unsigned int bits, unsigned int mask)
 {
 	unsigned int i;
-	int ai_off = MVPP2_PRS_SRAM_AI_OFFS;
 
 	for (i = 0; i < MVPP2_PRS_SRAM_AI_CTRL_BITS; i++) {
 		if (!(mask & BIT(i)))
 			continue;
 
 		if (bits & BIT(i))
-			mvpp2_prs_sram_bits_set(pe, ai_off + i, 1);
+			mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_OFFS + i,
+						1);
 		else
-			mvpp2_prs_sram_bits_clear(pe, ai_off + i, 1);
+			mvpp2_prs_sram_bits_clear(pe,
+						  MVPP2_PRS_SRAM_AI_OFFS + i,
+						  1);
 
 		mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_AI_CTRL_OFFS + i, 1);
 	}
@@ -278,12 +277,12 @@ static void mvpp2_prs_sram_ai_update(struct mvpp2_prs_entry *pe,
 static int mvpp2_prs_sram_ai_get(struct mvpp2_prs_entry *pe)
 {
 	u8 bits;
-	int ai_off = MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_AI_OFFS);
-	int ai_en_off = ai_off + 1;
-	int ai_shift = MVPP2_PRS_SRAM_AI_OFFS % 8;
+	/* ai is stored on bits 90->97; so it spreads across two u32 */
+	int ai_off = MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_AI_OFFS);
+	int ai_shift = MVPP2_BIT_IN_WORD(MVPP2_PRS_SRAM_AI_OFFS);
 
-	bits = (pe->sram.byte[ai_off] >> ai_shift) |
-	       (pe->sram.byte[ai_en_off] << (8 - ai_shift));
+	bits = (pe->sram[ai_off] >> ai_shift) |
+	       (pe->sram[ai_off + 1] << (32 - ai_shift));
 
 	return bits;
 }
@@ -316,8 +315,7 @@ static void mvpp2_prs_sram_shift_set(struct mvpp2_prs_entry *pe, int shift,
 	}
 
 	/* Set value */
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_SHIFT_OFFS)] =
-							   (unsigned char)shift;
+	pe->sram[MVPP2_BIT_TO_WORD(MVPP2_PRS_SRAM_SHIFT_OFFS)] = shift & MVPP2_PRS_SRAM_SHIFT_MASK;
 
 	/* Reset and set operation */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_SHIFT_OFFS,
@@ -346,13 +344,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe,
 	/* Set value */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_OFFS,
 				  MVPP2_PRS_SRAM_UDF_MASK);
-	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS, offset);
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
-					MVPP2_PRS_SRAM_UDF_BITS)] &=
-	      ~(MVPP2_PRS_SRAM_UDF_MASK >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_UDF_OFFS +
-					MVPP2_PRS_SRAM_UDF_BITS)] |=
-				(offset >> (8 - (MVPP2_PRS_SRAM_UDF_OFFS % 8)));
+	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_UDF_OFFS,
+				offset & MVPP2_PRS_SRAM_UDF_MASK);
 
 	/* Set offset type */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_UDF_TYPE_OFFS,
@@ -362,16 +355,8 @@ static void mvpp2_prs_sram_offset_set(struct mvpp2_prs_entry *pe,
 	/* Set offset operation */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
 				  MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
-	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS, op);
-
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
-					MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] &=
-					     ~(MVPP2_PRS_SRAM_OP_SEL_UDF_MASK >>
-				    (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
-
-	pe->sram.byte[MVPP2_BIT_TO_BYTE(MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS +
-					MVPP2_PRS_SRAM_OP_SEL_UDF_BITS)] |=
-			     (op >> (8 - (MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS % 8)));
+	mvpp2_prs_sram_bits_set(pe, MVPP2_PRS_SRAM_OP_SEL_UDF_OFFS,
+				op & MVPP2_PRS_SRAM_OP_SEL_UDF_MASK);
 
 	/* Set base offset as current */
 	mvpp2_prs_sram_bits_clear(pe, MVPP2_PRS_SRAM_OP_SEL_BASE_OFFS, 1);
@@ -932,8 +917,8 @@ static int mvpp2_prs_ip4_proto(struct mvpp2 *priv, unsigned short proto,
 
 	pe.index = tid;
 	/* Clear ri before updating */
-	pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
-	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, ri, ri_mask);
 
 	mvpp2_prs_sram_ri_update(&pe, ri | MVPP2_PRS_RI_IP_FRAG_TRUE,
@@ -1433,17 +1418,13 @@ static int mvpp2_prs_etype_init(struct mvpp2 *priv)
 
 	pe.index = tid;
 
-	/* Clear tcam data before updating */
-	pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE(MVPP2_ETH_TYPE_LEN)] = 0x0;
-	pe.tcam.byte[MVPP2_PRS_TCAM_DATA_BYTE_EN(MVPP2_ETH_TYPE_LEN)] = 0x0;
-
 	mvpp2_prs_tcam_data_byte_set(&pe, MVPP2_ETH_TYPE_LEN,
 				     MVPP2_PRS_IPV4_HEAD,
 				     MVPP2_PRS_IPV4_HEAD_MASK);
 
 	/* Clear ri before updating */
-	pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
-	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4_OPT,
 				 MVPP2_PRS_RI_L3_PROTO_MASK);
 
@@ -1644,8 +1625,8 @@ static int mvpp2_prs_pppoe_init(struct mvpp2 *priv)
 				     MVPP2_PRS_IPV4_IHL_MASK);
 
 	/* Clear ri before updating */
-	pe.sram.word[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
-	pe.sram.word[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_WORD] = 0x0;
+	pe.sram[MVPP2_PRS_SRAM_RI_CTRL_WORD] = 0x0;
 	mvpp2_prs_sram_ri_update(&pe, MVPP2_PRS_RI_L3_IP4,
 				 MVPP2_PRS_RI_L3_PROTO_MASK);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index 22fbbc4c8b28..a7c8d0818432 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -50,17 +50,25 @@
  * The fields are represented by MVPP2_PRS_TCAM_DATA_REG(5)->(0).
  */
 #define MVPP2_PRS_AI_BITS			8
+#define MVPP2_PRS_AI_MASK			0xff
 #define MVPP2_PRS_PORT_MASK			0xff
 #define MVPP2_PRS_LU_MASK			0xf
-#define MVPP2_PRS_TCAM_DATA_BYTE(offs)		\
-				    (((offs) - ((offs) % 2)) * 2 + ((offs) % 2))
-#define MVPP2_PRS_TCAM_DATA_BYTE_EN(offs)	\
-					      (((offs) * 2) - ((offs) % 2)  + 2)
-#define MVPP2_PRS_TCAM_AI_BYTE			16
-#define MVPP2_PRS_TCAM_PORT_BYTE		17
-#define MVPP2_PRS_TCAM_LU_BYTE			20
-#define MVPP2_PRS_TCAM_EN_OFFS(offs)		((offs) + 2)
-#define MVPP2_PRS_TCAM_INV_WORD			5
+
+/* TCAM entries in registers are accessed using 16 data bits + 16 enable bits */
+#define MVPP2_PRS_BYTE_TO_WORD(byte)	((byte) / 2)
+#define MVPP2_PRS_BYTE_IN_WORD(byte)	((byte) % 2)
+
+#define MVPP2_PRS_TCAM_EN(data)		((data) << 16)
+#define MVPP2_PRS_TCAM_AI_WORD		4
+#define MVPP2_PRS_TCAM_AI(ai)		(ai)
+#define MVPP2_PRS_TCAM_AI_EN(ai)	MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_AI(ai))
+#define MVPP2_PRS_TCAM_PORT_WORD	4
+#define MVPP2_PRS_TCAM_PORT(p)		((p) << 8)
+#define MVPP2_PRS_TCAM_PORT_EN(p)	MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_PORT(p))
+#define MVPP2_PRS_TCAM_LU_WORD		5
+#define MVPP2_PRS_TCAM_LU(lu)		(lu)
+#define MVPP2_PRS_TCAM_LU_EN(lu)	MVPP2_PRS_TCAM_EN(MVPP2_PRS_TCAM_LU(lu))
+#define MVPP2_PRS_TCAM_INV_WORD		5
 
 #define MVPP2_PRS_VID_TCAM_BYTE         2
 
@@ -146,6 +154,7 @@
 #define MVPP2_PRS_SRAM_RI_CTRL_BITS		32
 #define MVPP2_PRS_SRAM_SHIFT_OFFS		64
 #define MVPP2_PRS_SRAM_SHIFT_SIGN_BIT		72
+#define MVPP2_PRS_SRAM_SHIFT_MASK		0xff
 #define MVPP2_PRS_SRAM_UDF_OFFS			73
 #define MVPP2_PRS_SRAM_UDF_BITS			8
 #define MVPP2_PRS_SRAM_UDF_MASK			0xff
@@ -255,20 +264,10 @@ enum mvpp2_prs_lookup {
 	MVPP2_PRS_LU_LAST,
 };
 
-union mvpp2_prs_tcam_entry {
-	u32 word[MVPP2_PRS_TCAM_WORDS];
-	u8  byte[MVPP2_PRS_TCAM_WORDS * 4];
-};
-
-union mvpp2_prs_sram_entry {
-	u32 word[MVPP2_PRS_SRAM_WORDS];
-	u8  byte[MVPP2_PRS_SRAM_WORDS * 4];
-};
-
 struct mvpp2_prs_entry {
 	u32 index;
-	union mvpp2_prs_tcam_entry tcam;
-	union mvpp2_prs_sram_entry sram;
+	u32 tcam[MVPP2_PRS_TCAM_WORDS];
+	u32 sram[MVPP2_PRS_SRAM_WORDS];
 };
 
 struct mvpp2_prs_shadow {
-- 
cgit v1.2.3


From 432b59426bcaf217137a27c384bc1d215946912d Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 28 Jun 2018 14:42:06 +0200
Subject: net: mvpp2: prs: Drop unnecessary swab16 in vlan detection

Vlan IDs must not be swapped when creating Header Parser entries. This
has no effect on little-endian systems, but is wrong for big-endian.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index af11feea681c..a882c14d7d77 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -647,7 +647,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai)
 			continue;
 
 		mvpp2_prs_init_from_hw(priv, &pe, tid);
-		match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid));
+		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
 		if (!match)
 			continue;
 
@@ -775,8 +775,8 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1,
 
 		mvpp2_prs_init_from_hw(priv, &pe, tid);
 
-		match = mvpp2_prs_tcam_data_cmp(&pe, 0, swab16(tpid1)) &&
-			mvpp2_prs_tcam_data_cmp(&pe, 4, swab16(tpid2));
+		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
+			mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
 
 		if (!match)
 			continue;
-- 
cgit v1.2.3


From dc734dbe99695862e4d9121b6b0af8716b8e09fa Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 28 Jun 2018 14:42:07 +0200
Subject: net: mvpp2: Use htons when checking protocol info

When checking the skb->protocol field, we have to make sure we use the
proper endianness using htons, and not swab16.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index ded187a20b6c..88f3da184d76 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1738,7 +1738,7 @@ static u32 mvpp2_txq_desc_csum(int l3_offs, int l3_proto,
 	command |= (ip_hdr_len << MVPP2_TXD_IP_HLEN_SHIFT);
 	command |= MVPP2_TXD_IP_CSUM_DISABLE;
 
-	if (l3_proto == swab16(ETH_P_IP)) {
+	if (l3_proto == htons(ETH_P_IP)) {
 		command &= ~MVPP2_TXD_IP_CSUM_DISABLE;	/* enable IPv4 csum */
 		command &= ~MVPP2_TXD_L3_IP6;		/* enable IPv4 */
 	} else {
-- 
cgit v1.2.3


From 21d61166cada03405db7ad2d985b3c2c0e46e074 Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Date: Thu, 28 Jun 2018 18:41:46 +0530
Subject: net: emaclite: Use __func__ instead of hardcoded name

Switch hardcoded function name with a reference to __func__ making
the code more maintainable. Address below checkpatch warning:

WARNING: Prefer using '"%s...", __func__' to using 'xemaclite_mdio_read',
this function's name, in a string
+               "xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",

WARNING: Prefer using '"%s...", __func__' to using 'xemaclite_mdio_write',
this function's name, in a string
+               "xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n",

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_emaclite.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 2a0c06e0f730..0544134959bf 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -757,7 +757,7 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
 	rc = xemaclite_readl(lp->base_addr + XEL_MDIORD_OFFSET);
 
 	dev_dbg(&lp->ndev->dev,
-		"xemaclite_mdio_read(phy_id=%i, reg=%x) == %x\n",
+		"%s(phy_id=%i, reg=%x) == %x\n", __func__,
 		phy_id, reg, rc);
 
 	return rc;
@@ -780,7 +780,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 	u32 ctrl_reg;
 
 	dev_dbg(&lp->ndev->dev,
-		"xemaclite_mdio_write(phy_id=%i, reg=%x, val=%x)\n",
+		"%s(phy_id=%i, reg=%x, val=%x)\n", __func__,
 		phy_id, reg, val);
 
 	if (xemaclite_mdio_wait(lp))
-- 
cgit v1.2.3


From aa5848bc4043abf92c0b72a636bbc0cbe2828fed Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Date: Thu, 28 Jun 2018 18:41:47 +0530
Subject: net: emaclite: Simplify if-else statements

Remove else as it is not required with if doing a return.
It also coalesce the format onto a single line and add the
missing space after the comma. Fixes below checkpatch warning-

WARNING: else is not generally useful after a break or return

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_emaclite.c | 34 +++++++++++++--------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index 0544134959bf..b2c7afe6efe5 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -564,19 +564,18 @@ static void xemaclite_tx_handler(struct net_device *dev)
 	struct net_local *lp = netdev_priv(dev);
 
 	dev->stats.tx_packets++;
-	if (lp->deferred_skb) {
-		if (xemaclite_send_data(lp,
-					(u8 *) lp->deferred_skb->data,
-					lp->deferred_skb->len) != 0)
-			return;
-		else {
-			dev->stats.tx_bytes += lp->deferred_skb->len;
-			dev_kfree_skb_irq(lp->deferred_skb);
-			lp->deferred_skb = NULL;
-			netif_trans_update(dev); /* prevent tx timeout */
-			netif_wake_queue(dev);
-		}
-	}
+	if (!lp->deferred_skb)
+		return;
+
+	if (xemaclite_send_data(lp, (u8 *) lp->deferred_skb->data,
+				lp->deferred_skb->len))
+		return;
+
+	dev->stats.tx_bytes += lp->deferred_skb->len;
+	dev_kfree_skb_irq(lp->deferred_skb);
+	lp->deferred_skb = NULL;
+	netif_trans_update(dev); /* prevent tx timeout */
+	netif_wake_queue(dev);
 }
 
 /**
@@ -1052,13 +1051,12 @@ static bool get_bool(struct platform_device *ofdev, const char *s)
 {
 	u32 *p = (u32 *)of_get_property(ofdev->dev.of_node, s, NULL);
 
-	if (p) {
-		return (bool)*p;
-	} else {
-		dev_warn(&ofdev->dev, "Parameter %s not found,"
-			"defaulting to false\n", s);
+	if (!p) {
+		dev_warn(&ofdev->dev, "Parameter %s not found, defaulting to false\n", s);
 		return false;
 	}
+
+	return (bool)*p;
 }
 
 static const struct net_device_ops xemaclite_netdev_ops;
-- 
cgit v1.2.3


From f713d50f33c1fbd1046832f30cf95921840a0150 Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Date: Thu, 28 Jun 2018 18:41:48 +0530
Subject: net: emaclite: update kernel-doc comments

This patch fixes below kernel-doc warnings:

Function parameter or member 'maxlen' not described in 'xemaclite_recv_data'
Function parameter or member 'address'not described in 'xemaclite_set_mac_address'
Excess function parameter 'addr' description in 'xemaclite_set_mac_address'
No description found for return value of 'xemaclite_interrupt'
No description found for return value of 'xemaclite_mdio_write'
Function parameter or member 'dev' not described in 'xemaclite_mdio_setup'
Excess function parameter 'ofdev' description in 'xemaclite_mdio_setup'
No description found for return value of 'xemaclite_open'
No description found for return value of 'xemaclite_close'
Excess function parameter 'match' description in 'xemaclite_of_probe'

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_emaclite.c | 15 ++++++++++++---
 1 file changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index b2c7afe6efe5..a17f0b60810e 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -369,6 +369,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
  * xemaclite_recv_data - Receive a frame
  * @drvdata:	Pointer to the Emaclite device private data
  * @data:	Address where the data is to be received
+ * @maxlen:    Maximum supported ethernet packet length
  *
  * This function is intended to be called from the interrupt context or
  * with a wrapper which waits for the receive frame to be available.
@@ -488,7 +489,7 @@ static void xemaclite_update_address(struct net_local *drvdata,
 /**
  * xemaclite_set_mac_address - Set the MAC address for this device
  * @dev:	Pointer to the network device instance
- * @addr:	Void pointer to the sockaddr structure
+ * @address:	Void pointer to the sockaddr structure
  *
  * This function copies the HW address from the sockaddr strucutre to the
  * net_device structure and updates the address in HW.
@@ -638,6 +639,8 @@ static void xemaclite_rx_handler(struct net_device *dev)
  * @dev_id:	Void pointer to the network device instance used as callback
  *		reference
  *
+ * Return:	IRQ_HANDLED
+ *
  * This function handles the Tx and Rx interrupts of the EmacLite device.
  */
 static irqreturn_t xemaclite_interrupt(int irq, void *dev_id)
@@ -771,6 +774,8 @@ static int xemaclite_mdio_read(struct mii_bus *bus, int phy_id, int reg)
  *
  * This function waits till the device is ready to accept a new MDIO
  * request and then writes the val to the MDIO Write Data register.
+ *
+ * Return:      0 upon success or a negative error upon failure
  */
 static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 				u16 val)
@@ -804,7 +809,7 @@ static int xemaclite_mdio_write(struct mii_bus *bus, int phy_id, int reg,
 /**
  * xemaclite_mdio_setup - Register mii_bus for the Emaclite device
  * @lp:		Pointer to the Emaclite device private data
- * @ofdev:	Pointer to OF device structure
+ * @dev:	Pointer to OF device structure
  *
  * This function enables MDIO bus in the Emaclite device and registers a
  * mii_bus.
@@ -904,6 +909,9 @@ static void xemaclite_adjust_link(struct net_device *ndev)
  * This function sets the MAC address, requests an IRQ and enables interrupts
  * for the Emaclite device and starts the Tx queue.
  * It also connects to the phy device, if MDIO is included in Emaclite device.
+ *
+ * Return:	0 on success. -ENODEV, if PHY cannot be connected.
+ *		Non-zero error value on failure.
  */
 static int xemaclite_open(struct net_device *dev)
 {
@@ -974,6 +982,8 @@ static int xemaclite_open(struct net_device *dev)
  * This function stops the Tx queue, disables interrupts and frees the IRQ for
  * the Emaclite device.
  * It also disconnects the phy device associated with the Emaclite device.
+ *
+ * Return:	0, always.
  */
 static int xemaclite_close(struct net_device *dev)
 {
@@ -1064,7 +1074,6 @@ static const struct net_device_ops xemaclite_netdev_ops;
 /**
  * xemaclite_of_probe - Probe method for the Emaclite device.
  * @ofdev:	Pointer to OF device structure
- * @match:	Pointer to the structure used for matching a device
  *
  * This function probes for the Emaclite device in the device tree.
  * It initializes the driver data structure and the hardware, sets the MAC
-- 
cgit v1.2.3


From 49a83f002731dbfacb292d66399c828eb1e9f50f Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Date: Thu, 28 Jun 2018 18:41:49 +0530
Subject: net: emaclite: Fix block comments style

This patch fixes below checkpatch warnings-

WARNING: Block comments use a trailing */ on a separate line
WARNING: Block comments use * on subsequent lines
WARNING: networking block comments don't use an empty /* line,
use /* Comment

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_emaclite.c | 34 +++++++++++++++++----------
 1 file changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index a17f0b60810e..f96c9209039b 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -70,7 +70,8 @@
 #define XEL_TSR_XMIT_IE_MASK	 0x00000008	/* Tx interrupt enable bit */
 #define XEL_TSR_XMIT_ACTIVE_MASK 0x80000000	/* Buffer is active, SW bit
 						 * only. This is not documented
-						 * in the HW spec */
+						 * in the HW spec
+						 */
 
 /* Define for programming the MAC address into the EmacLite */
 #define XEL_TSR_PROG_MAC_ADDR	(XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_PROGRAM_MASK)
@@ -336,7 +337,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 			drvdata->next_tx_buf_to_use ^= XEL_BUFFER_OFFSET;
 	} else if (drvdata->tx_ping_pong != 0) {
 		/* If the expected buffer is full, try the other buffer,
-		 * if it is configured in HW */
+		 * if it is configured in HW
+		 */
 
 		addr = (void __iomem __force *)((u32 __force)addr ^
 						 XEL_BUFFER_OFFSET);
@@ -357,7 +359,8 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 	/* Update the Tx Status Register to indicate that there is a
 	 * frame to send. Set the XEL_TSR_XMIT_ACTIVE_MASK flag which
 	 * is used by the interrupt handler to check whether a frame
-	 * has been transmitted */
+	 * has been transmitted
+	 */
 	reg_data = xemaclite_readl(addr + XEL_TSR_OFFSET);
 	reg_data |= (XEL_TSR_XMIT_BUSY_MASK | XEL_TSR_XMIT_ACTIVE_MASK);
 	xemaclite_writel(reg_data, addr + XEL_TSR_OFFSET);
@@ -395,7 +398,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 		/* The instance is out of sync, try other buffer if other
 		 * buffer is configured, return 0 otherwise. If the instance is
 		 * out of sync, do not update the 'next_rx_buf_to_use' since it
-		 * will correct on subsequent calls */
+		 * will correct on subsequent calls
+		 */
 		if (drvdata->rx_ping_pong != 0)
 			addr = (void __iomem __force *)((u32 __force)addr ^
 							 XEL_BUFFER_OFFSET);
@@ -409,13 +413,15 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 			return 0;	/* No data was available */
 	}
 
-	/* Get the protocol type of the ethernet frame that arrived */
+	/* Get the protocol type of the ethernet frame that arrived
+	 */
 	proto_type = ((ntohl(xemaclite_readl(addr + XEL_HEADER_OFFSET +
 			XEL_RXBUFF_OFFSET)) >> XEL_HEADER_SHIFT) &
 			XEL_RPLR_LENGTH_MASK);
 
 	/* Check if received ethernet frame is a raw ethernet frame
-	 * or an IP packet or an ARP packet */
+	 * or an IP packet or an ARP packet
+	 */
 	if (proto_type > ETH_DATA_LEN) {
 
 		if (proto_type == ETH_P_IP) {
@@ -431,7 +437,8 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 			length = XEL_ARP_PACKET_SIZE + ETH_HLEN + ETH_FCS_LEN;
 		else
 			/* Field contains type other than IP or ARP, use max
-			 * frame size and let user parse it */
+			 * frame size and let user parse it
+			 */
 			length = ETH_FRAME_LEN + ETH_FCS_LEN;
 	} else
 		/* Use the length in the frame, plus the header and trailer */
@@ -602,11 +609,11 @@ static void xemaclite_rx_handler(struct net_device *dev)
 		return;
 	}
 
-	/*
-	 * A new skb should have the data halfword aligned, but this code is
+	/* A new skb should have the data halfword aligned, but this code is
 	 * here just in case that isn't true. Calculate how many
 	 * bytes we should reserve to get the data to start on a word
-	 * boundary */
+	 * boundary
+	 */
 	align = BUFFER_ALIGN(skb->data);
 	if (align)
 		skb_reserve(skb, align);
@@ -708,8 +715,8 @@ static int xemaclite_mdio_wait(struct net_local *lp)
 	unsigned long end = jiffies + 2;
 
 	/* wait for the MDIO interface to not be busy or timeout
-	   after some time.
-	*/
+	 * after some time.
+	 */
 	while (xemaclite_readl(lp->base_addr + XEL_MDIOCTRL_OFFSET) &
 			XEL_MDIOCTRL_MDIOSTS_MASK) {
 		if (time_before_eq(end, jiffies)) {
@@ -1029,7 +1036,8 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev)
 	if (xemaclite_send_data(lp, (u8 *) new_skb->data, len) != 0) {
 		/* If the Emaclite Tx buffer is busy, stop the Tx queue and
 		 * defer the skb for transmission during the ISR, after the
-		 * current transmission is complete */
+		 * current transmission is complete
+		 */
 		netif_stop_queue(dev);
 		lp->deferred_skb = new_skb;
 		/* Take the time stamp now, since we can't do this in an ISR. */
-- 
cgit v1.2.3


From 14291d10a8f5908224ecc219e8b77934f86e315c Mon Sep 17 00:00:00 2001
From: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Date: Thu, 28 Jun 2018 18:41:50 +0530
Subject: net: emaclite: Remove unnecessary spaces

This patch fixes below checkpatch checks-

CHECK: spaces preferred around that '*' (ctx:VxV)
CHECK: No space is necessary after a cast

Signed-off-by: Radhey Shyam Pandey <radhey.shyam.pandey@xilinx.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/xilinx/xilinx_emaclite.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_emaclite.c b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
index f96c9209039b..42f1f518dad6 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -95,11 +95,11 @@
 
 
 
-#define TX_TIMEOUT		(60*HZ)		/* Tx timeout is 60 seconds. */
+#define TX_TIMEOUT		(60 * HZ)	/* Tx timeout is 60 seconds. */
 #define ALIGNMENT		4
 
 /* BUFFER_ALIGN(adr) calculates the number of bytes to the next alignment. */
-#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32) adr)) % ALIGNMENT)
+#define BUFFER_ALIGN(adr) ((ALIGNMENT - ((u32)adr)) % ALIGNMENT)
 
 #ifdef __BIG_ENDIAN
 #define xemaclite_readl		ioread32be
@@ -239,8 +239,8 @@ static void xemaclite_aligned_write(void *src_ptr, u32 *dest_ptr,
 
 		/* Set up to output the remaining data */
 		align_buffer = 0;
-		to_u8_ptr = (u8 *) &align_buffer;
-		from_u8_ptr = (u8 *) from_u16_ptr;
+		to_u8_ptr = (u8 *)&align_buffer;
+		from_u8_ptr = (u8 *)from_u16_ptr;
 
 		/* Output the remaining data */
 		for (; length > 0; length--)
@@ -273,7 +273,7 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr,
 	u32 align_buffer;
 
 	from_u32_ptr = src_ptr;
-	to_u16_ptr = (u16 *) dest_ptr;
+	to_u16_ptr = (u16 *)dest_ptr;
 
 	for (; length > 3; length -= 4) {
 		/* Copy each word into the temporary buffer */
@@ -289,9 +289,9 @@ static void xemaclite_aligned_read(u32 *src_ptr, u8 *dest_ptr,
 		u8 *to_u8_ptr, *from_u8_ptr;
 
 		/* Set up to read the remaining data */
-		to_u8_ptr = (u8 *) to_u16_ptr;
+		to_u8_ptr = (u8 *)to_u16_ptr;
 		align_buffer = *from_u32_ptr++;
-		from_u8_ptr = (u8 *) &align_buffer;
+		from_u8_ptr = (u8 *)&align_buffer;
 
 		/* Read the remaining data */
 		for (; length > 0; length--)
@@ -351,7 +351,7 @@ static int xemaclite_send_data(struct net_local *drvdata, u8 *data,
 		return -1; /* Buffer was full, return failure */
 
 	/* Write the frame to the buffer */
-	xemaclite_aligned_write(data, (u32 __force *) addr, byte_count);
+	xemaclite_aligned_write(data, (u32 __force *)addr, byte_count);
 
 	xemaclite_writel((byte_count & XEL_TPLR_LENGTH_MASK),
 			 addr + XEL_TPLR_OFFSET);
@@ -448,7 +448,7 @@ static u16 xemaclite_recv_data(struct net_local *drvdata, u8 *data, int maxlen)
 		length = maxlen;
 
 	/* Read from the EmacLite device */
-	xemaclite_aligned_read((u32 __force *) (addr + XEL_RXBUFF_OFFSET),
+	xemaclite_aligned_read((u32 __force *)(addr + XEL_RXBUFF_OFFSET),
 				data, length);
 
 	/* Acknowledge the frame */
@@ -479,7 +479,7 @@ static void xemaclite_update_address(struct net_local *drvdata,
 	/* Determine the expected Tx buffer address */
 	addr = drvdata->base_addr + drvdata->next_tx_buf_to_use;
 
-	xemaclite_aligned_write(address_ptr, (u32 __force *) addr, ETH_ALEN);
+	xemaclite_aligned_write(address_ptr, (u32 __force *)addr, ETH_ALEN);
 
 	xemaclite_writel(ETH_ALEN, addr + XEL_TPLR_OFFSET);
 
@@ -572,10 +572,11 @@ static void xemaclite_tx_handler(struct net_device *dev)
 	struct net_local *lp = netdev_priv(dev);
 
 	dev->stats.tx_packets++;
+
 	if (!lp->deferred_skb)
 		return;
 
-	if (xemaclite_send_data(lp, (u8 *) lp->deferred_skb->data,
+	if (xemaclite_send_data(lp, (u8 *)lp->deferred_skb->data,
 				lp->deferred_skb->len))
 		return;
 
@@ -620,7 +621,7 @@ static void xemaclite_rx_handler(struct net_device *dev)
 
 	skb_reserve(skb, 2);
 
-	len = xemaclite_recv_data(lp, (u8 *) skb->data, len);
+	len = xemaclite_recv_data(lp, (u8 *)skb->data, len);
 
 	if (!len) {
 		dev->stats.rx_errors++;
@@ -1033,7 +1034,7 @@ static int xemaclite_send(struct sk_buff *orig_skb, struct net_device *dev)
 	new_skb = orig_skb;
 
 	spin_lock_irqsave(&lp->reset_lock, flags);
-	if (xemaclite_send_data(lp, (u8 *) new_skb->data, len) != 0) {
+	if (xemaclite_send_data(lp, (u8 *)new_skb->data, len) != 0) {
 		/* If the Emaclite Tx buffer is busy, stop the Tx queue and
 		 * defer the skb for transmission during the ISR, after the
 		 * current transmission is complete
-- 
cgit v1.2.3


From 010079bac0ce294f0ce177c0363e0e7579ed7f0c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 28 Jun 2018 18:56:20 +0200
Subject: selftests: forwarding: lib: Split out setup_wait_dev()

Split out of setup_wait() a function setup_wait_dev() that waits for a
single device. This gives tests the opportunity to wait for a selected
device after they tinkered with its upness.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 1dfdf14894e2..ac1df4860fbe 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -185,18 +185,25 @@ log_info()
 	echo "INFO: $msg"
 }
 
+setup_wait_dev()
+{
+	local dev=$1; shift
+
+	while true; do
+		ip link show dev $dev up \
+			| grep 'state UP' &> /dev/null
+		if [[ $? -ne 0 ]]; then
+			sleep 1
+		else
+			break
+		fi
+	done
+}
+
 setup_wait()
 {
 	for i in $(eval echo {1..$NUM_NETIFS}); do
-		while true; do
-			ip link show dev ${NETIFS[p$i]} up \
-				| grep 'state UP' &> /dev/null
-			if [[ $? -ne 0 ]]; then
-				sleep 1
-			else
-				break
-			fi
-		done
+		setup_wait_dev ${NETIFS[p$i]}
 	done
 
 	# Make sure links are ready.
-- 
cgit v1.2.3


From ac0fcadf03f8f86be28980d7aa0a09c202ec4f78 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 28 Jun 2018 18:56:28 +0200
Subject: selftests: forwarding: lib: Avoid trapping soft devices

There are several cases where traffic that would normally be forwarded
in silicon needs to be observed in slow path. That's achieved by
trapping such traffic, and the functions trap_install() and
trap_uninstall() realize that. However, such treatment is obviously
wrong if the device in question is actually a soft device not backed by
an ASIC.

Therefore try to trap if possible, but fall back to inserting a continue
if not.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ac1df4860fbe..d1f14f83979e 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -479,9 +479,15 @@ trap_install()
 	local dev=$1; shift
 	local direction=$1; shift
 
-	# For slow-path testing, we need to install a trap to get to
-	# slow path the packets that would otherwise be switched in HW.
-	tc filter add dev $dev $direction pref 1 flower skip_sw action trap
+	# Some devices may not support or need in-hardware trapping of traffic
+	# (e.g. the veth pairs that this library creates for non-existent
+	# loopbacks). Use continue instead, so that there is a filter in there
+	# (some tests check counters), and so that other filters are still
+	# processed.
+	tc filter add dev $dev $direction pref 1 \
+		flower skip_sw action trap 2>/dev/null \
+	    || tc filter add dev $dev $direction pref 1 \
+		       flower action continue
 }
 
 trap_uninstall()
@@ -489,11 +495,13 @@ trap_uninstall()
 	local dev=$1; shift
 	local direction=$1; shift
 
-	tc filter del dev $dev $direction pref 1 flower skip_sw
+	tc filter del dev $dev $direction pref 1 flower
 }
 
 slow_path_trap_install()
 {
+	# For slow-path testing, we need to install a trap to get to
+	# slow path the packets that would otherwise be switched in HW.
 	if [ "${tcflags/skip_hw}" != "$tcflags" ]; then
 		trap_install "$@"
 	fi
-- 
cgit v1.2.3


From ec9fdc99f5a6a2cfe4061e807fcb0cc1129f0a2d Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 28 Jun 2018 18:56:33 +0200
Subject: selftests: forwarding: Tweak tc filters for mirror-to-gretap tests

When running mirror_gre_bridge_1d_vlan tests on veth, several issues
cause spurious failures:

- vlan_ethtype should be ip, not ipv6 even in mirror-to-ip6gretap case,
  because the overlay packet is still IPv4.
- Similarly ip_proto matches the innermost IP protocol, so can't be used
  to filter out GRE packet. Drop the corresponding condition.
- Because the above fixes the filters to match in slow path as well,
  they need to be made skip_hw so as not to double-count packets.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh | 6 ++++--
 tools/testing/selftests/net/forwarding/mirror_gre_lib.sh            | 2 +-
 tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh | 6 ++++--
 3 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
index 3bb4c2ba7b14..197e769c2ed1 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d_vlan.sh
@@ -74,12 +74,14 @@ test_vlan_match()
 
 test_gretap()
 {
-	test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+	test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \
+			"mirror to gretap"
 }
 
 test_ip6gretap()
 {
-	test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+	test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \
+			"mirror to ip6gretap"
 }
 
 test_gretap_stp()
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
index 619b469365be..1c18e332cd4f 100644
--- a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
@@ -62,7 +62,7 @@ full_test_span_gre_dir_vlan_ips()
 			  "$backward_type" "$ip1" "$ip2"
 
 	tc filter add dev $h3 ingress pref 77 prot 802.1q \
-		flower $vlan_match ip_proto 0x2f \
+		flower $vlan_match \
 		action pass
 	mirror_test v$h1 $ip1 $ip2 $h3 77 10
 	tc filter del dev $h3 ingress pref 77
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
index 1ac5038ae256..d3e75bb6a2d8 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -88,12 +88,14 @@ test_vlan_match()
 
 test_gretap()
 {
-	test_vlan_match gt4 'vlan_id 555 vlan_ethtype ip' "mirror to gretap"
+	test_vlan_match gt4 'skip_hw vlan_id 555 vlan_ethtype ip' \
+			"mirror to gretap"
 }
 
 test_ip6gretap()
 {
-	test_vlan_match gt6 'vlan_id 555 vlan_ethtype ipv6' "mirror to ip6gretap"
+	test_vlan_match gt6 'skip_hw vlan_id 555 vlan_ethtype ip' \
+			"mirror to ip6gretap"
 }
 
 test_span_gre_forbidden_cpu()
-- 
cgit v1.2.3


From 4e74cc7c5d3f58cb0e2534cd68716c5746d52d07 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 28 Jun 2018 18:56:39 +0200
Subject: selftests: forwarding: mirror_gre_changes: Fix waiting for neighbor

When running the test on soft devices, there's no mechanism to
gratuitously start resolving the neighbor for remote tunnel endpoint.
So instead of passively waiting, wait for the device to be up, and then
probe the neighbor with a ping.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/mirror_gre_changes.sh | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
index aa29d46186a8..135902aa8b11 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh
@@ -122,15 +122,8 @@ test_span_gre_egress_up()
 	# After setting the device up, wait for neighbor to get resolved so that
 	# we can expect mirroring to work.
 	ip link set dev $swp3 up
-	while true; do
-		ip neigh sh dev $swp3 $remote_ip nud reachable |
-		    grep -q ^
-		if [[ $? -ne 0 ]]; then
-			sleep 1
-		else
-			break
-		fi
-	done
+	setup_wait_dev $swp3
+	ping -c 1 -I $swp3 $remote_ip &>/dev/null
 
 	quick_test_span_gre_dir $tundev ingress
 	mirror_uninstall $swp1 ingress
-- 
cgit v1.2.3


From be6a3f38ff2a2bfd2e591fdc566940a0d4d9428c Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:04 +0200
Subject: net/smc: determine port attributes independent from pnet table

For SMC it is important to know the current port state of RoCE devices.
Monitoring port states has been triggered, when a RoCE device was added
to the pnet table. To support future alternatives to the pnet table the
monitoring of ports is made independent of the existence of a pnet table.
It starts once the smc_ib_device is established.

Due to this change smc_ib_remember_port_attr() is now a local function
and shuffling its location and the location of its used functions
makes any forward references obsolete.

And the duplicate SMC_MAX_PORTS definition is removed.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc.h      |   2 -
 net/smc/smc_ib.c   | 130 ++++++++++++++++++++++++++++-------------------------
 net/smc/smc_ib.h   |   1 -
 net/smc/smc_pnet.c |   7 +--
 4 files changed, 72 insertions(+), 68 deletions(-)

diff --git a/net/smc/smc.h b/net/smc/smc.h
index 51ae1f10d81a..7c86f716a92e 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -21,8 +21,6 @@
 #define SMCPROTO_SMC		0	/* SMC protocol, IPv4 */
 #define SMCPROTO_SMC6		1	/* SMC protocol, IPv6 */
 
-#define SMC_MAX_PORTS		2	/* Max # of ports */
-
 extern struct proto smc_proto;
 extern struct proto smc_proto6;
 
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 0eed7ab9f28b..f8b159ced032 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -143,6 +143,62 @@ out:
 	return rc;
 }
 
+static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	struct ib_gid_attr gattr;
+	int rc;
+
+	rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
+			  &smcibdev->gid[ibport - 1], &gattr);
+	if (rc || !gattr.ndev)
+		return -ENODEV;
+
+	memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
+	dev_put(gattr.ndev);
+	return 0;
+}
+
+/* Create an identifier unique for this instance of SMC-R.
+ * The MAC-address of the first active registered IB device
+ * plus a random 2-byte number is used to create this identifier.
+ * This name is delivered to the peer during connection initialization.
+ */
+static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
+						u8 ibport)
+{
+	memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
+	       sizeof(smcibdev->mac[ibport - 1]));
+	get_random_bytes(&local_systemid[0], 2);
+}
+
+bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
+}
+
+static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
+{
+	int rc;
+
+	memset(&smcibdev->pattr[ibport - 1], 0,
+	       sizeof(smcibdev->pattr[ibport - 1]));
+	rc = ib_query_port(smcibdev->ibdev, ibport,
+			   &smcibdev->pattr[ibport - 1]);
+	if (rc)
+		goto out;
+	/* the SMC protocol requires specification of the RoCE MAC address */
+	rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
+	if (rc)
+		goto out;
+	if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
+		     sizeof(local_systemid)) &&
+	    smc_ib_port_active(smcibdev, ibport))
+		/* create unique system identifier */
+		smc_ib_define_local_systemid(smcibdev, ibport);
+out:
+	return rc;
+}
+
 /* process context wrapper for might_sleep smc_ib_remember_port_attr */
 static void smc_ib_port_event_work(struct work_struct *work)
 {
@@ -370,62 +426,6 @@ void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
 	buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address = 0;
 }
 
-static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
-{
-	struct ib_gid_attr gattr;
-	int rc;
-
-	rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
-			  &smcibdev->gid[ibport - 1], &gattr);
-	if (rc || !gattr.ndev)
-		return -ENODEV;
-
-	memcpy(smcibdev->mac[ibport - 1], gattr.ndev->dev_addr, ETH_ALEN);
-	dev_put(gattr.ndev);
-	return 0;
-}
-
-/* Create an identifier unique for this instance of SMC-R.
- * The MAC-address of the first active registered IB device
- * plus a random 2-byte number is used to create this identifier.
- * This name is delivered to the peer during connection initialization.
- */
-static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
-						u8 ibport)
-{
-	memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
-	       sizeof(smcibdev->mac[ibport - 1]));
-	get_random_bytes(&local_systemid[0], 2);
-}
-
-bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
-{
-	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
-}
-
-int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
-{
-	int rc;
-
-	memset(&smcibdev->pattr[ibport - 1], 0,
-	       sizeof(smcibdev->pattr[ibport - 1]));
-	rc = ib_query_port(smcibdev->ibdev, ibport,
-			   &smcibdev->pattr[ibport - 1]);
-	if (rc)
-		goto out;
-	/* the SMC protocol requires specification of the RoCE MAC address */
-	rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
-	if (rc)
-		goto out;
-	if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
-		     sizeof(local_systemid)) &&
-	    smc_ib_port_active(smcibdev, ibport))
-		/* create unique system identifier */
-		smc_ib_define_local_systemid(smcibdev, ibport);
-out:
-	return rc;
-}
-
 long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
 {
 	struct ib_cq_init_attr cqattr =	{
@@ -454,9 +454,6 @@ long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
 		smcibdev->roce_cq_recv = NULL;
 		goto err;
 	}
-	INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
-			      smc_ib_global_event_handler);
-	ib_register_event_handler(&smcibdev->event_handler);
 	smc_wr_add_dev(smcibdev);
 	smcibdev->initialized = 1;
 	return rc;
@@ -472,7 +469,6 @@ static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev)
 		return;
 	smcibdev->initialized = 0;
 	smc_wr_remove_dev(smcibdev);
-	ib_unregister_event_handler(&smcibdev->event_handler);
 	ib_destroy_cq(smcibdev->roce_cq_recv);
 	ib_destroy_cq(smcibdev->roce_cq_send);
 }
@@ -483,6 +479,8 @@ static struct ib_client smc_ib_client;
 static void smc_ib_add_dev(struct ib_device *ibdev)
 {
 	struct smc_ib_device *smcibdev;
+	u8 port_cnt;
+	int i;
 
 	if (ibdev->node_type != RDMA_NODE_IB_CA)
 		return;
@@ -498,6 +496,17 @@ static void smc_ib_add_dev(struct ib_device *ibdev)
 	list_add_tail(&smcibdev->list, &smc_ib_devices.list);
 	spin_unlock(&smc_ib_devices.lock);
 	ib_set_client_data(ibdev, &smc_ib_client, smcibdev);
+	INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
+			      smc_ib_global_event_handler);
+	ib_register_event_handler(&smcibdev->event_handler);
+
+	/* trigger reading of the port attributes */
+	port_cnt = smcibdev->ibdev->phys_port_cnt;
+	for (i = 0;
+	     i < min_t(size_t, port_cnt, SMC_MAX_PORTS);
+	     i++)
+		set_bit(i, &smcibdev->port_event_mask);
+	schedule_work(&smcibdev->port_event_work);
 }
 
 /* callback function for ib_register_client() */
@@ -512,6 +521,7 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
 	spin_unlock(&smc_ib_devices.lock);
 	smc_pnet_remove_by_ibdev(smcibdev);
 	smc_ib_cleanup_per_ibdev(smcibdev);
+	ib_unregister_event_handler(&smcibdev->event_handler);
 	kfree(smcibdev);
 }
 
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index e90630dadf8e..2c480b352928 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -51,7 +51,6 @@ struct smc_link;
 int smc_ib_register_client(void) __init;
 void smc_ib_unregister_client(void);
 bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport);
-int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport);
 int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
 		      struct smc_buf_desc *buf_slot,
 		      enum dma_data_direction data_direction);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index d7b88b2d1b22..a82a5cad0282 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -358,9 +358,6 @@ static int smc_pnet_add(struct sk_buff *skb, struct genl_info *info)
 		kfree(pnetelem);
 		return rc;
 	}
-	rc = smc_ib_remember_port_attr(pnetelem->smcibdev, pnetelem->ib_port);
-	if (rc)
-		smc_pnet_remove_by_pnetid(pnetelem->pnet_name);
 	return rc;
 }
 
@@ -485,10 +482,10 @@ static int smc_pnet_netdev_event(struct notifier_block *this,
 	case NETDEV_REBOOT:
 	case NETDEV_UNREGISTER:
 		smc_pnet_remove_by_ndev(event_dev);
+		return NOTIFY_OK;
 	default:
-		break;
+		return NOTIFY_DONE;
 	}
-	return NOTIFY_DONE;
 }
 
 static struct notifier_block smc_netdev_notifier = {
-- 
cgit v1.2.3


From 0afff91c6f5ecef27715ea71e34dc2baacba1060 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:05 +0200
Subject: net/smc: add pnetid support

s390 hardware supports the definition of a so-call Physical NETwork
IDentifier (short PNETID) per network device port. These PNETIDS
can be used to identify network devices that are attached to the same
physical network (broadcast domain).

On s390 try to use the PNETID of the ethernet device port used for
initial connecting, and derive the IB device port used for SMC RDMA
traffic.

On platforms without PNETID support fall back to the existing
solution of a configured pnet table.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/smc.h  |   2 +
 net/smc/smc_ib.c   |   6 ++-
 net/smc/smc_ib.h   |   3 ++
 net/smc/smc_pnet.c | 109 +++++++++++++++++++++++++++++++++++++++++++----------
 net/smc/smc_pnet.h |  14 +++++++
 5 files changed, 114 insertions(+), 20 deletions(-)

diff --git a/include/net/smc.h b/include/net/smc.h
index 8381d163fefa..2173932fab9d 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -11,6 +11,8 @@
 #ifndef _SMC_H
 #define _SMC_H
 
+#define SMC_MAX_PNETID_LEN	16	/* Max. length of PNET id */
+
 struct smc_hashinfo {
 	rwlock_t lock;
 	struct hlist_head ht;
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index f8b159ced032..36de2fd76170 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -504,8 +504,12 @@ static void smc_ib_add_dev(struct ib_device *ibdev)
 	port_cnt = smcibdev->ibdev->phys_port_cnt;
 	for (i = 0;
 	     i < min_t(size_t, port_cnt, SMC_MAX_PORTS);
-	     i++)
+	     i++) {
 		set_bit(i, &smcibdev->port_event_mask);
+		/* determine pnetids of the port */
+		smc_pnetid_by_dev_port(ibdev->dev.parent, i,
+				       smcibdev->pnetid[i]);
+	}
 	schedule_work(&smcibdev->port_event_work);
 }
 
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 2c480b352928..7c1223c91229 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -15,6 +15,7 @@
 #include <linux/interrupt.h>
 #include <linux/if_ether.h>
 #include <rdma/ib_verbs.h>
+#include <net/smc.h>
 
 #define SMC_MAX_PORTS			2	/* Max # of ports */
 #define SMC_GID_SIZE			sizeof(union ib_gid)
@@ -40,6 +41,8 @@ struct smc_ib_device {				/* ib-device infos for smc */
 	char			mac[SMC_MAX_PORTS][ETH_ALEN];
 						/* mac address per port*/
 	union ib_gid		gid[SMC_MAX_PORTS]; /* gid per port */
+	u8			pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
+						/* pnetid per port */
 	u8			initialized : 1; /* ib dev CQ, evthdl done */
 	struct work_struct	port_event_work;
 	unsigned long		port_event_mask;
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index a82a5cad0282..cdc6e23b6ce1 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -23,12 +23,10 @@
 #include "smc_pnet.h"
 #include "smc_ib.h"
 
-#define SMC_MAX_PNET_ID_LEN	16	/* Max. length of PNET id */
-
 static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
 	[SMC_PNETID_NAME] = {
 		.type = NLA_NUL_STRING,
-		.len = SMC_MAX_PNET_ID_LEN - 1
+		.len = SMC_MAX_PNETID_LEN - 1
 	},
 	[SMC_PNETID_ETHNAME] = {
 		.type = NLA_NUL_STRING,
@@ -65,7 +63,7 @@ static struct smc_pnettable {
  */
 struct smc_pnetentry {
 	struct list_head list;
-	char pnet_name[SMC_MAX_PNET_ID_LEN + 1];
+	char pnet_name[SMC_MAX_PNETID_LEN + 1];
 	struct net_device *ndev;
 	struct smc_ib_device *smcibdev;
 	u8 ib_port;
@@ -209,7 +207,7 @@ static bool smc_pnetid_valid(const char *pnet_name, char *pnetid)
 		return false;
 	while (--end >= bf && isspace(*end))
 		;
-	if (end - bf >= SMC_MAX_PNET_ID_LEN)
+	if (end - bf >= SMC_MAX_PNETID_LEN)
 		return false;
 	while (bf <= end) {
 		if (!isalnum(*bf))
@@ -512,26 +510,70 @@ void smc_pnet_exit(void)
 	genl_unregister_family(&smc_pnet_nl_family);
 }
 
-/* PNET table analysis for a given sock:
- * determine ib_device and port belonging to used internal TCP socket
- * ethernet interface.
+/* Determine one base device for stacked net devices.
+ * If the lower device level contains more than one devices
+ * (for instance with bonding slaves), just the first device
+ * is used to reach a base device.
  */
-void smc_pnet_find_roce_resource(struct sock *sk,
-				 struct smc_ib_device **smcibdev, u8 *ibport)
+static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 {
-	struct dst_entry *dst = sk_dst_get(sk);
-	struct smc_pnetentry *pnetelem;
+	int i, nest_lvl;
 
-	*smcibdev = NULL;
-	*ibport = 0;
+	rtnl_lock();
+	nest_lvl = dev_get_nest_level(ndev);
+	for (i = 0; i < nest_lvl; i++) {
+		struct list_head *lower = &ndev->adj_list.lower;
+
+		if (list_empty(lower))
+			break;
+		lower = lower->next;
+		ndev = netdev_lower_get_next(ndev, &lower);
+	}
+	rtnl_unlock();
+	return ndev;
+}
+
+/* Determine the corresponding IB device port based on the hardware PNETID.
+ * Searching stops at the first matching active IB device port.
+ */
+static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
+					 struct smc_ib_device **smcibdev,
+					 u8 *ibport)
+{
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct smc_ib_device *ibdev;
+	int i;
+
+	ndev = pnet_find_base_ndev(ndev);
+	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+				   ndev_pnetid))
+		return; /* pnetid could not be determined */
+
+	spin_lock(&smc_ib_devices.lock);
+	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
+		for (i = 1; i <= SMC_MAX_PORTS; i++) {
+			if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid,
+				    SMC_MAX_PNETID_LEN) &&
+			    smc_ib_port_active(ibdev, i)) {
+				*smcibdev = ibdev;
+				*ibport = i;
+				break;
+			}
+		}
+	}
+	spin_unlock(&smc_ib_devices.lock);
+}
+
+/* Lookup of coupled ib_device via SMC pnet table */
+static void smc_pnet_find_roce_by_table(struct net_device *netdev,
+					struct smc_ib_device **smcibdev,
+					u8 *ibport)
+{
+	struct smc_pnetentry *pnetelem;
 
-	if (!dst)
-		return;
-	if (!dst->dev)
-		goto out_rel;
 	read_lock(&smc_pnettable.lock);
 	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
-		if (dst->dev == pnetelem->ndev) {
+		if (netdev == pnetelem->ndev) {
 			if (smc_ib_port_active(pnetelem->smcibdev,
 					       pnetelem->ib_port)) {
 				*smcibdev = pnetelem->smcibdev;
@@ -541,6 +583,35 @@ void smc_pnet_find_roce_resource(struct sock *sk,
 		}
 	}
 	read_unlock(&smc_pnettable.lock);
+}
+
+/* PNET table analysis for a given sock:
+ * determine ib_device and port belonging to used internal TCP socket
+ * ethernet interface.
+ */
+void smc_pnet_find_roce_resource(struct sock *sk,
+				 struct smc_ib_device **smcibdev, u8 *ibport)
+{
+	struct dst_entry *dst = sk_dst_get(sk);
+
+	*smcibdev = NULL;
+	*ibport = 0;
+
+	if (!dst)
+		goto out;
+	if (!dst->dev)
+		goto out_rel;
+
+	/* if possible, lookup via hardware-defined pnetid */
+	smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport);
+	if (*smcibdev)
+		goto out_rel;
+
+	/* lookup via SMC PNET table */
+	smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport);
+
 out_rel:
 	dst_release(dst);
+out:
+	return;
 }
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 5a29519db976..ad4455cde9e7 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -12,8 +12,22 @@
 #ifndef _SMC_PNET_H
 #define _SMC_PNET_H
 
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+#include <asm/pnet.h>
+#endif
+
 struct smc_ib_device;
 
+static inline int smc_pnetid_by_dev_port(struct device *dev,
+					 unsigned short port, u8 *pnetid)
+{
+#if IS_ENABLED(CONFIG_HAVE_PNETID)
+	return pnet_id_by_dev_port(dev, port, pnetid);
+#else
+	return -ENOENT;
+#endif
+}
+
 int smc_pnet_init(void) __init;
 void smc_pnet_exit(void);
 int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
-- 
cgit v1.2.3


From e82f2e31f5597a3de44bd27b7427f577f637c552 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ursula.braun@de.ibm.com>
Date: Thu, 28 Jun 2018 19:05:06 +0200
Subject: net/smc: optimize consumer cursor updates

The SMC protocol requires to send a separate consumer cursor update,
if it cannot be piggybacked to updates of the producer cursor.
Currently the decision to send a separate consumer cursor update
just considers the amount of data already received by the socket
program. It does not consider the amount of data already arrived, but
not yet consumed by the receiver. Basing the decision on the
difference between already confirmed and already arrived data
(instead of difference between already confirmed and already consumed
data), may lead to a somewhat earlier consumer cursor update send in
fast unidirectional traffic scenarios, and thus to better throughput.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_tx.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index cee666400752..f82886b7d1d8 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -495,7 +495,8 @@ out:
 
 void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 {
-	union smc_host_cursor cfed, cons;
+	union smc_host_cursor cfed, cons, prod;
+	int sender_free = conn->rmb_desc->len;
 	int to_confirm;
 
 	smc_curs_write(&cons,
@@ -505,11 +506,18 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 		       smc_curs_read(&conn->rx_curs_confirmed, conn),
 		       conn);
 	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
+	if (to_confirm > conn->rmbe_update_limit) {
+		smc_curs_write(&prod,
+			       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
+			       conn);
+		sender_free = conn->rmb_desc->len -
+			      smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
+	}
 
 	if (conn->local_rx_ctrl.prod_flags.cons_curs_upd_req ||
 	    force ||
 	    ((to_confirm > conn->rmbe_update_limit) &&
-	     ((to_confirm > (conn->rmb_desc->len / 2)) ||
+	     ((sender_free <= (conn->rmb_desc->len / 2)) ||
 	      conn->local_rx_ctrl.prod_flags.write_blocked))) {
 		if ((smc_cdc_get_slot_and_msg_send(conn) < 0) &&
 		    conn->alert_token_local) { /* connection healthy */
-- 
cgit v1.2.3


From c6ba7c9ba43de1b57e9a53946e7ff988554c84ed Mon Sep 17 00:00:00 2001
From: Hans Wippel <hwippel@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:07 +0200
Subject: net/smc: add base infrastructure for SMC-D and ISM

SMC supports two variants: SMC-R and SMC-D. For data transport, SMC-R
uses RDMA devices, SMC-D uses so-called Internal Shared Memory (ISM)
devices. An ISM device only allows shared memory communication between
SMC instances on the same machine. For example, this allows virtual
machines on the same host to communicate via SMC without RDMA devices.

This patch adds the base infrastructure for SMC-D and ISM devices to
the existing SMC code. It contains the following:

* ISM driver interface:
  This interface allows an ISM driver to register ISM devices in SMC. In
  the process, the driver provides a set of device ops for each device.
  SMC uses these ops to execute SMC specific operations on or transfer
  data over the device.

* Core SMC-D link group, connection, and buffer support:
  Link groups, SMC connections and SMC buffers (in smc_core) are
  extended to support SMC-D.

* SMC type checks:
  Some type checks are added to prevent using SMC-R specific code for
  SMC-D and vice versa.

To actually use SMC-D, additional changes to pnetid, CLC, CDC, etc. are
required. These are added in follow-up patches.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/smc.h  |  62 +++++++++++
 net/smc/Makefile   |   2 +-
 net/smc/af_smc.c   |  11 +-
 net/smc/smc_core.c | 270 +++++++++++++++++++++++++++++++++++------------
 net/smc/smc_core.h |  71 +++++++++----
 net/smc/smc_diag.c |   3 +-
 net/smc/smc_ism.c  | 304 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 net/smc/smc_ism.h  |  48 +++++++++
 8 files changed, 679 insertions(+), 92 deletions(-)
 create mode 100644 net/smc/smc_ism.c
 create mode 100644 net/smc/smc_ism.h

diff --git a/include/net/smc.h b/include/net/smc.h
index 2173932fab9d..824a7af8d654 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -20,4 +20,66 @@ struct smc_hashinfo {
 
 int smc_hash_sk(struct sock *sk);
 void smc_unhash_sk(struct sock *sk);
+
+/* SMCD/ISM device driver interface */
+struct smcd_dmb {
+	u64 dmb_tok;
+	u64 rgid;
+	u32 dmb_len;
+	u32 sba_idx;
+	u32 vlan_valid;
+	u32 vlan_id;
+	void *cpu_addr;
+	dma_addr_t dma_addr;
+};
+
+#define ISM_EVENT_DMB	0
+#define ISM_EVENT_GID	1
+#define ISM_EVENT_SWR	2
+
+struct smcd_event {
+	u32 type;
+	u32 code;
+	u64 tok;
+	u64 time;
+	u64 info;
+};
+
+struct smcd_dev;
+
+struct smcd_ops {
+	int (*query_remote_gid)(struct smcd_dev *dev, u64 rgid, u32 vid_valid,
+				u32 vid);
+	int (*register_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb);
+	int (*unregister_dmb)(struct smcd_dev *dev, struct smcd_dmb *dmb);
+	int (*add_vlan_id)(struct smcd_dev *dev, u64 vlan_id);
+	int (*del_vlan_id)(struct smcd_dev *dev, u64 vlan_id);
+	int (*set_vlan_required)(struct smcd_dev *dev);
+	int (*reset_vlan_required)(struct smcd_dev *dev);
+	int (*signal_event)(struct smcd_dev *dev, u64 rgid, u32 trigger_irq,
+			    u32 event_code, u64 info);
+	int (*move_data)(struct smcd_dev *dev, u64 dmb_tok, unsigned int idx,
+			 bool sf, unsigned int offset, void *data,
+			 unsigned int size);
+};
+
+struct smcd_dev {
+	const struct smcd_ops *ops;
+	struct device dev;
+	void *priv;
+	u64 local_gid;
+	struct list_head list;
+	spinlock_t lock;
+	struct smc_connection **conn;
+	struct list_head vlan;
+	struct workqueue_struct *event_wq;
+};
+
+struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
+				const struct smcd_ops *ops, int max_dmbs);
+int smcd_register_dev(struct smcd_dev *smcd);
+void smcd_unregister_dev(struct smcd_dev *smcd);
+void smcd_free_dev(struct smcd_dev *smcd);
+void smcd_handle_event(struct smcd_dev *dev, struct smcd_event *event);
+void smcd_handle_irq(struct smcd_dev *dev, unsigned int bit);
 #endif	/* _SMC_H */
diff --git a/net/smc/Makefile b/net/smc/Makefile
index 188104654b54..4df96b4b8130 100644
--- a/net/smc/Makefile
+++ b/net/smc/Makefile
@@ -1,4 +1,4 @@
 obj-$(CONFIG_SMC)	+= smc.o
 obj-$(CONFIG_SMC_DIAG)	+= smc_diag.o
 smc-y := af_smc.o smc_pnet.o smc_ib.o smc_clc.o smc_core.o smc_wr.o smc_llc.o
-smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o
+smc-y += smc_cdc.o smc_tx.o smc_rx.o smc_close.o smc_ism.o
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index da7f02edcd37..8ce48799cf68 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -475,8 +475,8 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	int reason_code = 0;
 
 	mutex_lock(&smc_create_lgr_pending);
-	local_contact = smc_conn_create(smc, ibdev, ibport, &aclc->lcl,
-					aclc->hdr.flag);
+	local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev,
+					ibport, &aclc->lcl, NULL, 0);
 	if (local_contact < 0) {
 		if (local_contact == -ENOMEM)
 			reason_code = SMC_CLC_DECL_MEM;/* insufficient memory*/
@@ -491,7 +491,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	smc_conn_save_peer_info(smc, aclc);
 
 	/* create send buffer and rmb */
-	if (smc_buf_create(smc))
+	if (smc_buf_create(smc, false))
 		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
 
 	if (local_contact == SMC_FIRST_CONTACT)
@@ -894,7 +894,8 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc,
 				int *local_contact)
 {
 	/* allocate connection / link group */
-	*local_contact = smc_conn_create(new_smc, ibdev, ibport, &pclc->lcl, 0);
+	*local_contact = smc_conn_create(new_smc, false, 0, ibdev, ibport,
+					 &pclc->lcl, NULL, 0);
 	if (*local_contact < 0) {
 		if (*local_contact == -ENOMEM)
 			return SMC_CLC_DECL_MEM;/* insufficient memory*/
@@ -902,7 +903,7 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc,
 	}
 
 	/* create send buffer and rmb */
-	if (smc_buf_create(new_smc))
+	if (smc_buf_create(new_smc, false))
 		return SMC_CLC_DECL_MEM;
 
 	return 0;
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index add82b0266f3..daa88db1841a 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -25,6 +25,7 @@
 #include "smc_llc.h"
 #include "smc_cdc.h"
 #include "smc_close.h"
+#include "smc_ism.h"
 
 #define SMC_LGR_NUM_INCR		256
 #define SMC_LGR_FREE_DELAY_SERV		(600 * HZ)
@@ -46,8 +47,8 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
 	 * otherwise there is a risk of out-of-sync link groups.
 	 */
 	mod_delayed_work(system_wq, &lgr->free_work,
-			 lgr->role == SMC_CLNT ? SMC_LGR_FREE_DELAY_CLNT :
-						 SMC_LGR_FREE_DELAY_SERV);
+			 (!lgr->is_smcd && lgr->role == SMC_CLNT) ?
+			 SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV);
 }
 
 /* Register connection's alert token in our lookup structure.
@@ -153,16 +154,18 @@ static void smc_lgr_free_work(struct work_struct *work)
 free:
 	spin_unlock_bh(&smc_lgr_list.lock);
 	if (!delayed_work_pending(&lgr->free_work)) {
-		if (lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE)
+		if (!lgr->is_smcd &&
+		    lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE)
 			smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
 		smc_lgr_free(lgr);
 	}
 }
 
 /* create a new SMC link group */
-static int smc_lgr_create(struct smc_sock *smc,
+static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
 			  struct smc_ib_device *smcibdev, u8 ibport,
-			  char *peer_systemid, unsigned short vlan_id)
+			  char *peer_systemid, unsigned short vlan_id,
+			  struct smcd_dev *smcismdev, u64 peer_gid)
 {
 	struct smc_link_group *lgr;
 	struct smc_link *lnk;
@@ -170,17 +173,23 @@ static int smc_lgr_create(struct smc_sock *smc,
 	int rc = 0;
 	int i;
 
+	if (is_smcd && vlan_id) {
+		rc = smc_ism_get_vlan(smcismdev, vlan_id);
+		if (rc)
+			goto out;
+	}
+
 	lgr = kzalloc(sizeof(*lgr), GFP_KERNEL);
 	if (!lgr) {
 		rc = -ENOMEM;
 		goto out;
 	}
-	lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
+	lgr->is_smcd = is_smcd;
 	lgr->sync_err = 0;
-	memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
 	lgr->vlan_id = vlan_id;
 	rwlock_init(&lgr->sndbufs_lock);
 	rwlock_init(&lgr->rmbs_lock);
+	rwlock_init(&lgr->conns_lock);
 	for (i = 0; i < SMC_RMBE_SIZES; i++) {
 		INIT_LIST_HEAD(&lgr->sndbufs[i]);
 		INIT_LIST_HEAD(&lgr->rmbs[i]);
@@ -189,36 +198,44 @@ static int smc_lgr_create(struct smc_sock *smc,
 	memcpy(&lgr->id, (u8 *)&smc_lgr_list.num, SMC_LGR_ID_SIZE);
 	INIT_DELAYED_WORK(&lgr->free_work, smc_lgr_free_work);
 	lgr->conns_all = RB_ROOT;
-
-	lnk = &lgr->lnk[SMC_SINGLE_LINK];
-	/* initialize link */
-	lnk->state = SMC_LNK_ACTIVATING;
-	lnk->link_id = SMC_SINGLE_LINK;
-	lnk->smcibdev = smcibdev;
-	lnk->ibport = ibport;
-	lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
-	if (!smcibdev->initialized)
-		smc_ib_setup_per_ibdev(smcibdev);
-	get_random_bytes(rndvec, sizeof(rndvec));
-	lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) + (rndvec[2] << 16);
-	rc = smc_llc_link_init(lnk);
-	if (rc)
-		goto free_lgr;
-	rc = smc_wr_alloc_link_mem(lnk);
-	if (rc)
-		goto clear_llc_lnk;
-	rc = smc_ib_create_protection_domain(lnk);
-	if (rc)
-		goto free_link_mem;
-	rc = smc_ib_create_queue_pair(lnk);
-	if (rc)
-		goto dealloc_pd;
-	rc = smc_wr_create_link(lnk);
-	if (rc)
-		goto destroy_qp;
-
+	if (is_smcd) {
+		/* SMC-D specific settings */
+		lgr->peer_gid = peer_gid;
+		lgr->smcd = smcismdev;
+	} else {
+		/* SMC-R specific settings */
+		lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT;
+		memcpy(lgr->peer_systemid, peer_systemid, SMC_SYSTEMID_LEN);
+
+		lnk = &lgr->lnk[SMC_SINGLE_LINK];
+		/* initialize link */
+		lnk->state = SMC_LNK_ACTIVATING;
+		lnk->link_id = SMC_SINGLE_LINK;
+		lnk->smcibdev = smcibdev;
+		lnk->ibport = ibport;
+		lnk->path_mtu = smcibdev->pattr[ibport - 1].active_mtu;
+		if (!smcibdev->initialized)
+			smc_ib_setup_per_ibdev(smcibdev);
+		get_random_bytes(rndvec, sizeof(rndvec));
+		lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
+			(rndvec[2] << 16);
+		rc = smc_llc_link_init(lnk);
+		if (rc)
+			goto free_lgr;
+		rc = smc_wr_alloc_link_mem(lnk);
+		if (rc)
+			goto clear_llc_lnk;
+		rc = smc_ib_create_protection_domain(lnk);
+		if (rc)
+			goto free_link_mem;
+		rc = smc_ib_create_queue_pair(lnk);
+		if (rc)
+			goto dealloc_pd;
+		rc = smc_wr_create_link(lnk);
+		if (rc)
+			goto destroy_qp;
+	}
 	smc->conn.lgr = lgr;
-	rwlock_init(&lgr->conns_lock);
 	spin_lock_bh(&smc_lgr_list.lock);
 	list_add(&lgr->list, &smc_lgr_list.list);
 	spin_unlock_bh(&smc_lgr_list.lock);
@@ -264,7 +281,10 @@ void smc_conn_free(struct smc_connection *conn)
 {
 	if (!conn->lgr)
 		return;
-	smc_cdc_tx_dismiss_slots(conn);
+	if (conn->lgr->is_smcd)
+		smc_ism_unset_conn(conn);
+	else
+		smc_cdc_tx_dismiss_slots(conn);
 	smc_lgr_unregister_conn(conn);
 	smc_buf_unuse(conn);
 }
@@ -280,8 +300,8 @@ static void smc_link_clear(struct smc_link *lnk)
 	smc_wr_free_link_mem(lnk);
 }
 
-static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
-			 struct smc_buf_desc *buf_desc)
+static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb,
+			  struct smc_buf_desc *buf_desc)
 {
 	struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
 
@@ -301,6 +321,25 @@ static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
 	kfree(buf_desc);
 }
 
+static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb,
+			  struct smc_buf_desc *buf_desc)
+{
+	if (is_dmb)
+		smc_ism_unregister_dmb(lgr->smcd, buf_desc);
+	else
+		kfree(buf_desc->cpu_addr);
+	kfree(buf_desc);
+}
+
+static void smc_buf_free(struct smc_link_group *lgr, bool is_rmb,
+			 struct smc_buf_desc *buf_desc)
+{
+	if (lgr->is_smcd)
+		smcd_buf_free(lgr, is_rmb, buf_desc);
+	else
+		smcr_buf_free(lgr, is_rmb, buf_desc);
+}
+
 static void __smc_lgr_free_bufs(struct smc_link_group *lgr, bool is_rmb)
 {
 	struct smc_buf_desc *buf_desc, *bf_desc;
@@ -332,7 +371,10 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr)
 void smc_lgr_free(struct smc_link_group *lgr)
 {
 	smc_lgr_free_bufs(lgr);
-	smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
+	if (lgr->is_smcd)
+		smc_ism_put_vlan(lgr->smcd, lgr->vlan_id);
+	else
+		smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]);
 	kfree(lgr);
 }
 
@@ -357,7 +399,8 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr)
 	lgr->terminating = 1;
 	if (!list_empty(&lgr->list)) /* forget lgr */
 		list_del_init(&lgr->list);
-	smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+	if (!lgr->is_smcd)
+		smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
 
 	write_lock_bh(&lgr->conns_lock);
 	node = rb_first(&lgr->conns_all);
@@ -374,7 +417,8 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr)
 		node = rb_first(&lgr->conns_all);
 	}
 	write_unlock_bh(&lgr->conns_lock);
-	wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait);
+	if (!lgr->is_smcd)
+		wake_up(&lgr->lnk[SMC_SINGLE_LINK].wr_reg_wait);
 	smc_lgr_schedule_free_work(lgr);
 }
 
@@ -392,13 +436,40 @@ void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport)
 
 	spin_lock_bh(&smc_lgr_list.lock);
 	list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
-		if (lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev &&
+		if (!lgr->is_smcd &&
+		    lgr->lnk[SMC_SINGLE_LINK].smcibdev == smcibdev &&
 		    lgr->lnk[SMC_SINGLE_LINK].ibport == ibport)
 			__smc_lgr_terminate(lgr);
 	}
 	spin_unlock_bh(&smc_lgr_list.lock);
 }
 
+/* Called when SMC-D device is terminated or peer is lost */
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
+{
+	struct smc_link_group *lgr, *l;
+	LIST_HEAD(lgr_free_list);
+
+	/* run common cleanup function and build free list */
+	spin_lock_bh(&smc_lgr_list.lock);
+	list_for_each_entry_safe(lgr, l, &smc_lgr_list.list, list) {
+		if (lgr->is_smcd && lgr->smcd == dev &&
+		    (!peer_gid || lgr->peer_gid == peer_gid) &&
+		    !list_empty(&lgr->list)) {
+			__smc_lgr_terminate(lgr);
+			list_move(&lgr->list, &lgr_free_list);
+		}
+	}
+	spin_unlock_bh(&smc_lgr_list.lock);
+
+	/* cancel the regular free workers and actually free lgrs */
+	list_for_each_entry_safe(lgr, l, &lgr_free_list, list) {
+		list_del_init(&lgr->list);
+		cancel_delayed_work_sync(&lgr->free_work);
+		smc_lgr_free(lgr);
+	}
+}
+
 /* Determine vlan of internal TCP socket.
  * @vlan_id: address to store the determined vlan id into
  */
@@ -477,10 +548,30 @@ static int smc_link_determine_gid(struct smc_link_group *lgr)
 	return -ENODEV;
 }
 
+static bool smcr_lgr_match(struct smc_link_group *lgr,
+			   struct smc_clc_msg_local *lcl,
+			   enum smc_lgr_role role)
+{
+	return !memcmp(lgr->peer_systemid, lcl->id_for_peer,
+		       SMC_SYSTEMID_LEN) &&
+		!memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid,
+			SMC_GID_SIZE) &&
+		!memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
+			sizeof(lcl->mac)) &&
+		lgr->role == role;
+}
+
+static bool smcd_lgr_match(struct smc_link_group *lgr,
+			   struct smcd_dev *smcismdev, u64 peer_gid)
+{
+	return lgr->peer_gid == peer_gid && lgr->smcd == smcismdev;
+}
+
 /* create a new SMC connection (and a new link group if necessary) */
-int smc_conn_create(struct smc_sock *smc,
+int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 		    struct smc_ib_device *smcibdev, u8 ibport,
-		    struct smc_clc_msg_local *lcl, int srv_first_contact)
+		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
+		    u64 peer_gid)
 {
 	struct smc_connection *conn = &smc->conn;
 	int local_contact = SMC_FIRST_CONTACT;
@@ -502,17 +593,12 @@ int smc_conn_create(struct smc_sock *smc,
 	spin_lock_bh(&smc_lgr_list.lock);
 	list_for_each_entry(lgr, &smc_lgr_list.list, list) {
 		write_lock_bh(&lgr->conns_lock);
-		if (!memcmp(lgr->peer_systemid, lcl->id_for_peer,
-			    SMC_SYSTEMID_LEN) &&
-		    !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_gid, &lcl->gid,
-			    SMC_GID_SIZE) &&
-		    !memcmp(lgr->lnk[SMC_SINGLE_LINK].peer_mac, lcl->mac,
-			    sizeof(lcl->mac)) &&
+		if ((is_smcd ? smcd_lgr_match(lgr, smcd, peer_gid) :
+		     smcr_lgr_match(lgr, lcl, role)) &&
 		    !lgr->sync_err &&
-		    (lgr->role == role) &&
-		    (lgr->vlan_id == vlan_id) &&
-		    ((role == SMC_CLNT) ||
-		     (lgr->conns_num < SMC_RMBS_PER_LGR_MAX))) {
+		    lgr->vlan_id == vlan_id &&
+		    (role == SMC_CLNT ||
+		     lgr->conns_num < SMC_RMBS_PER_LGR_MAX)) {
 			/* link group found */
 			local_contact = SMC_REUSE_CONTACT;
 			conn->lgr = lgr;
@@ -535,12 +621,13 @@ int smc_conn_create(struct smc_sock *smc,
 
 create:
 	if (local_contact == SMC_FIRST_CONTACT) {
-		rc = smc_lgr_create(smc, smcibdev, ibport,
-				    lcl->id_for_peer, vlan_id);
+		rc = smc_lgr_create(smc, is_smcd, smcibdev, ibport,
+				    lcl->id_for_peer, vlan_id, smcd, peer_gid);
 		if (rc)
 			goto out;
 		smc_lgr_register_conn(conn); /* add smc conn to lgr */
-		rc = smc_link_determine_gid(conn->lgr);
+		if (!is_smcd)
+			rc = smc_link_determine_gid(conn->lgr);
 	}
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
@@ -609,8 +696,8 @@ static inline int smc_rmb_wnd_update_limit(int rmbe_size)
 	return min_t(int, rmbe_size / 10, SOCK_MIN_SNDBUF / 2);
 }
 
-static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr,
-					       bool is_rmb, int bufsize)
+static struct smc_buf_desc *smcr_new_buf_create(struct smc_link_group *lgr,
+						bool is_rmb, int bufsize)
 {
 	struct smc_buf_desc *buf_desc;
 	struct smc_link *lnk;
@@ -668,7 +755,43 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr,
 	return buf_desc;
 }
 
-static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
+#define SMCD_DMBE_SIZES		7 /* 0 -> 16KB, 1 -> 32KB, .. 6 -> 1MB */
+
+static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
+						bool is_dmb, int bufsize)
+{
+	struct smc_buf_desc *buf_desc;
+	int rc;
+
+	if (smc_compress_bufsize(bufsize) > SMCD_DMBE_SIZES)
+		return ERR_PTR(-EAGAIN);
+
+	/* try to alloc a new DMB */
+	buf_desc = kzalloc(sizeof(*buf_desc), GFP_KERNEL);
+	if (!buf_desc)
+		return ERR_PTR(-ENOMEM);
+	if (is_dmb) {
+		rc = smc_ism_register_dmb(lgr, bufsize, buf_desc);
+		if (rc) {
+			kfree(buf_desc);
+			return ERR_PTR(-EAGAIN);
+		}
+		memset(buf_desc->cpu_addr, 0, bufsize);
+		buf_desc->len = bufsize;
+	} else {
+		buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL |
+					     __GFP_NOWARN | __GFP_NORETRY |
+					     __GFP_NOMEMALLOC);
+		if (!buf_desc->cpu_addr) {
+			kfree(buf_desc);
+			return ERR_PTR(-EAGAIN);
+		}
+		buf_desc->len = bufsize;
+	}
+	return buf_desc;
+}
+
+static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 {
 	struct smc_buf_desc *buf_desc = ERR_PTR(-ENOMEM);
 	struct smc_connection *conn = &smc->conn;
@@ -706,7 +829,11 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
 			break; /* found reusable slot */
 		}
 
-		buf_desc = smc_new_buf_create(lgr, is_rmb, bufsize);
+		if (is_smcd)
+			buf_desc = smcd_new_buf_create(lgr, is_rmb, bufsize);
+		else
+			buf_desc = smcr_new_buf_create(lgr, is_rmb, bufsize);
+
 		if (PTR_ERR(buf_desc) == -ENOMEM)
 			break;
 		if (IS_ERR(buf_desc))
@@ -728,6 +855,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_rmb)
 		smc->sk.sk_rcvbuf = bufsize * 2;
 		atomic_set(&conn->bytes_to_rcv, 0);
 		conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
+		if (is_smcd)
+			smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */
 	} else {
 		conn->sndbuf_desc = buf_desc;
 		smc->sk.sk_sndbuf = bufsize * 2;
@@ -740,6 +869,8 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
 
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
 	smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
 			       conn->sndbuf_desc, DMA_TO_DEVICE);
 }
@@ -748,6 +879,8 @@ void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
 
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
 	smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
 				  conn->sndbuf_desc, DMA_TO_DEVICE);
 }
@@ -756,6 +889,8 @@ void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
 
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
 	smc_ib_sync_sg_for_cpu(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
 			       conn->rmb_desc, DMA_FROM_DEVICE);
 }
@@ -764,6 +899,8 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
 
+	if (!conn->lgr || conn->lgr->is_smcd)
+		return;
 	smc_ib_sync_sg_for_device(lgr->lnk[SMC_SINGLE_LINK].smcibdev,
 				  conn->rmb_desc, DMA_FROM_DEVICE);
 }
@@ -774,16 +911,16 @@ void smc_rmb_sync_sg_for_device(struct smc_connection *conn)
  * the Linux implementation uses just one RMB-element per RMB, i.e. uses an
  * extra RMB for every connection in a link group
  */
-int smc_buf_create(struct smc_sock *smc)
+int smc_buf_create(struct smc_sock *smc, bool is_smcd)
 {
 	int rc;
 
 	/* create send buffer */
-	rc = __smc_buf_create(smc, false);
+	rc = __smc_buf_create(smc, is_smcd, false);
 	if (rc)
 		return rc;
 	/* create rmb */
-	rc = __smc_buf_create(smc, true);
+	rc = __smc_buf_create(smc, is_smcd, true);
 	if (rc)
 		smc_buf_free(smc->conn.lgr, false, smc->conn.sndbuf_desc);
 	return rc;
@@ -865,7 +1002,8 @@ void smc_core_exit(void)
 	spin_unlock_bh(&smc_lgr_list.lock);
 	list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) {
 		list_del_init(&lgr->list);
-		smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+		if (!lgr->is_smcd)
+			smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
 		cancel_delayed_work_sync(&lgr->free_work);
 		smc_lgr_free(lgr); /* free link group */
 	}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 93cb3523bf50..cd9268a9570e 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -124,15 +124,28 @@ struct smc_buf_desc {
 	void			*cpu_addr;	/* virtual address of buffer */
 	struct page		*pages;
 	int			len;		/* length of buffer */
-	struct sg_table		sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */
-	struct ib_mr		*mr_rx[SMC_LINKS_PER_LGR_MAX];
-						/* for rmb only: memory region
-						 * incl. rkey provided to peer
-						 */
-	u32			order;		/* allocation order */
 	u32			used;		/* currently used / unused */
 	u8			reused	: 1;	/* new created / reused */
 	u8			regerr	: 1;	/* err during registration */
+	union {
+		struct { /* SMC-R */
+			struct sg_table		sgt[SMC_LINKS_PER_LGR_MAX];
+						/* virtual buffer */
+			struct ib_mr		*mr_rx[SMC_LINKS_PER_LGR_MAX];
+						/* for rmb only: memory region
+						 * incl. rkey provided to peer
+						 */
+			u32			order;	/* allocation order */
+		};
+		struct { /* SMC-D */
+			unsigned short		sba_idx;
+						/* SBA index number */
+			u64			token;
+						/* DMB token number */
+			dma_addr_t		dma_addr;
+						/* DMA address */
+		};
+	};
 };
 
 struct smc_rtoken {				/* address/key of remote RMB */
@@ -148,12 +161,10 @@ struct smc_rtoken {				/* address/key of remote RMB */
  * struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15)
  */
 
+struct smcd_dev;
+
 struct smc_link_group {
 	struct list_head	list;
-	enum smc_lgr_role	role;		/* client or server */
-	struct smc_link		lnk[SMC_LINKS_PER_LGR_MAX];	/* smc link */
-	char			peer_systemid[SMC_SYSTEMID_LEN];
-						/* unique system_id of peer */
 	struct rb_root		conns_all;	/* connection tree */
 	rwlock_t		conns_lock;	/* protects conns_all */
 	unsigned int		conns_num;	/* current # of connections */
@@ -163,17 +174,35 @@ struct smc_link_group {
 	rwlock_t		sndbufs_lock;	/* protects tx buffers */
 	struct list_head	rmbs[SMC_RMBE_SIZES];	/* rx buffers */
 	rwlock_t		rmbs_lock;	/* protects rx buffers */
-	struct smc_rtoken	rtokens[SMC_RMBS_PER_LGR_MAX]
-				       [SMC_LINKS_PER_LGR_MAX];
-						/* remote addr/key pairs */
-	unsigned long		rtokens_used_mask[BITS_TO_LONGS(
-							SMC_RMBS_PER_LGR_MAX)];
-						/* used rtoken elements */
 
 	u8			id[SMC_LGR_ID_SIZE];	/* unique lgr id */
 	struct delayed_work	free_work;	/* delayed freeing of an lgr */
 	u8			sync_err : 1;	/* lgr no longer fits to peer */
 	u8			terminating : 1;/* lgr is terminating */
+
+	bool			is_smcd;	/* SMC-R or SMC-D */
+	union {
+		struct { /* SMC-R */
+			enum smc_lgr_role	role;
+						/* client or server */
+			struct smc_link		lnk[SMC_LINKS_PER_LGR_MAX];
+						/* smc link */
+			char			peer_systemid[SMC_SYSTEMID_LEN];
+						/* unique system_id of peer */
+			struct smc_rtoken	rtokens[SMC_RMBS_PER_LGR_MAX]
+						[SMC_LINKS_PER_LGR_MAX];
+						/* remote addr/key pairs */
+			unsigned long		rtokens_used_mask[BITS_TO_LONGS
+							(SMC_RMBS_PER_LGR_MAX)];
+						/* used rtoken elements */
+		};
+		struct { /* SMC-D */
+			u64			peer_gid;
+						/* Peer GID (remote) */
+			struct smcd_dev		*smcd;
+						/* ISM device for VLAN reg. */
+		};
+	};
 };
 
 /* Find the connection associated with the given alert token in the link group.
@@ -217,7 +246,8 @@ void smc_lgr_free(struct smc_link_group *lgr);
 void smc_lgr_forget(struct smc_link_group *lgr);
 void smc_lgr_terminate(struct smc_link_group *lgr);
 void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
-int smc_buf_create(struct smc_sock *smc);
+void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid);
+int smc_buf_create(struct smc_sock *smc, bool is_smcd);
 int smc_uncompress_bufsize(u8 compressed);
 int smc_rmb_rtoken_handling(struct smc_connection *conn,
 			    struct smc_clc_msg_accept_confirm *clc);
@@ -227,9 +257,12 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
 void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
 void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
 void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
+
 void smc_conn_free(struct smc_connection *conn);
-int smc_conn_create(struct smc_sock *smc,
+int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 		    struct smc_ib_device *smcibdev, u8 ibport,
-		    struct smc_clc_msg_local *lcl, int srv_first_contact);
+		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
+		    u64 peer_gid);
+void smcd_conn_free(struct smc_connection *conn);
 void smc_core_exit(void);
 #endif
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 839354402215..64ce107c24d9 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -136,7 +136,8 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 			goto errout;
 	}
 
-	if ((req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) && smc->conn.lgr &&
+	if (smc->conn.lgr && !smc->conn.lgr->is_smcd &&
+	    (req->diag_ext & (1 << (SMC_DIAG_LGRINFO - 1))) &&
 	    !list_empty(&smc->conn.lgr->list)) {
 		struct smc_diag_lgrinfo linfo = {
 			.role = smc->conn.lgr->role,
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
new file mode 100644
index 000000000000..ca1ce42fd49f
--- /dev/null
+++ b/net/smc/smc_ism.c
@@ -0,0 +1,304 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Shared Memory Communications Direct over ISM devices (SMC-D)
+ *
+ * Functions for ISM device.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <asm/page.h>
+
+#include "smc.h"
+#include "smc_core.h"
+#include "smc_ism.h"
+
+struct smcd_dev_list smcd_dev_list = {
+	.list = LIST_HEAD_INIT(smcd_dev_list.list),
+	.lock = __SPIN_LOCK_UNLOCKED(smcd_dev_list.lock)
+};
+
+/* Test if an ISM communication is possible. */
+int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *smcd)
+{
+	return smcd->ops->query_remote_gid(smcd, peer_gid, vlan_id ? 1 : 0,
+					   vlan_id);
+}
+
+int smc_ism_write(struct smcd_dev *smcd, const struct smc_ism_position *pos,
+		  void *data, size_t len)
+{
+	int rc;
+
+	rc = smcd->ops->move_data(smcd, pos->token, pos->index, pos->signal,
+				  pos->offset, data, len);
+
+	return rc < 0 ? rc : 0;
+}
+
+/* Set a connection using this DMBE. */
+void smc_ism_set_conn(struct smc_connection *conn)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&conn->lgr->smcd->lock, flags);
+	conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = conn;
+	spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags);
+}
+
+/* Unset a connection using this DMBE. */
+void smc_ism_unset_conn(struct smc_connection *conn)
+{
+	unsigned long flags;
+
+	if (!conn->rmb_desc)
+		return;
+
+	spin_lock_irqsave(&conn->lgr->smcd->lock, flags);
+	conn->lgr->smcd->conn[conn->rmb_desc->sba_idx] = NULL;
+	spin_unlock_irqrestore(&conn->lgr->smcd->lock, flags);
+}
+
+/* Register a VLAN identifier with the ISM device. Use a reference count
+ * and add a VLAN identifier only when the first DMB using this VLAN is
+ * registered.
+ */
+int smc_ism_get_vlan(struct smcd_dev *smcd, unsigned short vlanid)
+{
+	struct smc_ism_vlanid *new_vlan, *vlan;
+	unsigned long flags;
+	int rc = 0;
+
+	if (!vlanid)			/* No valid vlan id */
+		return -EINVAL;
+
+	/* create new vlan entry, in case we need it */
+	new_vlan = kzalloc(sizeof(*new_vlan), GFP_KERNEL);
+	if (!new_vlan)
+		return -ENOMEM;
+	new_vlan->vlanid = vlanid;
+	refcount_set(&new_vlan->refcnt, 1);
+
+	/* if there is an existing entry, increase count and return */
+	spin_lock_irqsave(&smcd->lock, flags);
+	list_for_each_entry(vlan, &smcd->vlan, list) {
+		if (vlan->vlanid == vlanid) {
+			refcount_inc(&vlan->refcnt);
+			kfree(new_vlan);
+			goto out;
+		}
+	}
+
+	/* no existing entry found.
+	 * add new entry to device; might fail, e.g., if HW limit reached
+	 */
+	if (smcd->ops->add_vlan_id(smcd, vlanid)) {
+		kfree(new_vlan);
+		rc = -EIO;
+		goto out;
+	}
+	list_add_tail(&new_vlan->list, &smcd->vlan);
+out:
+	spin_unlock_irqrestore(&smcd->lock, flags);
+	return rc;
+}
+
+/* Unregister a VLAN identifier with the ISM device. Use a reference count
+ * and remove a VLAN identifier only when the last DMB using this VLAN is
+ * unregistered.
+ */
+int smc_ism_put_vlan(struct smcd_dev *smcd, unsigned short vlanid)
+{
+	struct smc_ism_vlanid *vlan;
+	unsigned long flags;
+	bool found = false;
+	int rc = 0;
+
+	if (!vlanid)			/* No valid vlan id */
+		return -EINVAL;
+
+	spin_lock_irqsave(&smcd->lock, flags);
+	list_for_each_entry(vlan, &smcd->vlan, list) {
+		if (vlan->vlanid == vlanid) {
+			if (!refcount_dec_and_test(&vlan->refcnt))
+				goto out;
+			found = true;
+			break;
+		}
+	}
+	if (!found) {
+		rc = -ENOENT;
+		goto out;		/* VLAN id not in table */
+	}
+
+	/* Found and the last reference just gone */
+	if (smcd->ops->del_vlan_id(smcd, vlanid))
+		rc = -EIO;
+	list_del(&vlan->list);
+	kfree(vlan);
+out:
+	spin_unlock_irqrestore(&smcd->lock, flags);
+	return rc;
+}
+
+int smc_ism_unregister_dmb(struct smcd_dev *smcd, struct smc_buf_desc *dmb_desc)
+{
+	struct smcd_dmb dmb;
+
+	memset(&dmb, 0, sizeof(dmb));
+	dmb.dmb_tok = dmb_desc->token;
+	dmb.sba_idx = dmb_desc->sba_idx;
+	dmb.cpu_addr = dmb_desc->cpu_addr;
+	dmb.dma_addr = dmb_desc->dma_addr;
+	dmb.dmb_len = dmb_desc->len;
+	return smcd->ops->unregister_dmb(smcd, &dmb);
+}
+
+int smc_ism_register_dmb(struct smc_link_group *lgr, int dmb_len,
+			 struct smc_buf_desc *dmb_desc)
+{
+	struct smcd_dmb dmb;
+	int rc;
+
+	memset(&dmb, 0, sizeof(dmb));
+	dmb.dmb_len = dmb_len;
+	dmb.sba_idx = dmb_desc->sba_idx;
+	dmb.vlan_id = lgr->vlan_id;
+	dmb.rgid = lgr->peer_gid;
+	rc = lgr->smcd->ops->register_dmb(lgr->smcd, &dmb);
+	if (!rc) {
+		dmb_desc->sba_idx = dmb.sba_idx;
+		dmb_desc->token = dmb.dmb_tok;
+		dmb_desc->cpu_addr = dmb.cpu_addr;
+		dmb_desc->dma_addr = dmb.dma_addr;
+		dmb_desc->len = dmb.dmb_len;
+	}
+	return rc;
+}
+
+struct smc_ism_event_work {
+	struct work_struct work;
+	struct smcd_dev *smcd;
+	struct smcd_event event;
+};
+
+/* worker for SMC-D events */
+static void smc_ism_event_work(struct work_struct *work)
+{
+	struct smc_ism_event_work *wrk =
+		container_of(work, struct smc_ism_event_work, work);
+
+	switch (wrk->event.type) {
+	case ISM_EVENT_GID:	/* GID event, token is peer GID */
+		smc_smcd_terminate(wrk->smcd, wrk->event.tok);
+		break;
+	case ISM_EVENT_DMB:
+		break;
+	}
+	kfree(wrk);
+}
+
+static void smcd_release(struct device *dev)
+{
+	struct smcd_dev *smcd = container_of(dev, struct smcd_dev, dev);
+
+	kfree(smcd->conn);
+	kfree(smcd);
+}
+
+struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
+				const struct smcd_ops *ops, int max_dmbs)
+{
+	struct smcd_dev *smcd;
+
+	smcd = kzalloc(sizeof(*smcd), GFP_KERNEL);
+	if (!smcd)
+		return NULL;
+	smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *),
+			     GFP_KERNEL);
+	if (!smcd->conn) {
+		kfree(smcd);
+		return NULL;
+	}
+
+	smcd->dev.parent = parent;
+	smcd->dev.release = smcd_release;
+	device_initialize(&smcd->dev);
+	dev_set_name(&smcd->dev, name);
+	smcd->ops = ops;
+
+	spin_lock_init(&smcd->lock);
+	INIT_LIST_HEAD(&smcd->vlan);
+	smcd->event_wq = alloc_ordered_workqueue("ism_evt_wq-%s)",
+						 WQ_MEM_RECLAIM, name);
+	return smcd;
+}
+EXPORT_SYMBOL_GPL(smcd_alloc_dev);
+
+int smcd_register_dev(struct smcd_dev *smcd)
+{
+	spin_lock(&smcd_dev_list.lock);
+	list_add_tail(&smcd->list, &smcd_dev_list.list);
+	spin_unlock(&smcd_dev_list.lock);
+
+	return device_add(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_register_dev);
+
+void smcd_unregister_dev(struct smcd_dev *smcd)
+{
+	spin_lock(&smcd_dev_list.lock);
+	list_del(&smcd->list);
+	spin_unlock(&smcd_dev_list.lock);
+	flush_workqueue(smcd->event_wq);
+	destroy_workqueue(smcd->event_wq);
+	smc_smcd_terminate(smcd, 0);
+
+	device_del(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_unregister_dev);
+
+void smcd_free_dev(struct smcd_dev *smcd)
+{
+	put_device(&smcd->dev);
+}
+EXPORT_SYMBOL_GPL(smcd_free_dev);
+
+/* SMCD Device event handler. Called from ISM device interrupt handler.
+ * Parameters are smcd device pointer,
+ * - event->type (0 --> DMB, 1 --> GID),
+ * - event->code (event code),
+ * - event->tok (either DMB token when event type 0, or GID when event type 1)
+ * - event->time (time of day)
+ * - event->info (debug info).
+ *
+ * Context:
+ * - Function called in IRQ context from ISM device driver event handler.
+ */
+void smcd_handle_event(struct smcd_dev *smcd, struct smcd_event *event)
+{
+	struct smc_ism_event_work *wrk;
+
+	/* copy event to event work queue, and let it be handled there */
+	wrk = kmalloc(sizeof(*wrk), GFP_ATOMIC);
+	if (!wrk)
+		return;
+	INIT_WORK(&wrk->work, smc_ism_event_work);
+	wrk->smcd = smcd;
+	wrk->event = *event;
+	queue_work(smcd->event_wq, &wrk->work);
+}
+EXPORT_SYMBOL_GPL(smcd_handle_event);
+
+/* SMCD Device interrupt handler. Called from ISM device interrupt handler.
+ * Parameters are smcd device pointer and DMB number. Find the connection and
+ * schedule the tasklet for this connection.
+ *
+ * Context:
+ * - Function called in IRQ context from ISM device driver IRQ handler.
+ */
+void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno)
+{
+}
+EXPORT_SYMBOL_GPL(smcd_handle_irq);
diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h
new file mode 100644
index 000000000000..aee45b860b79
--- /dev/null
+++ b/net/smc/smc_ism.h
@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Shared Memory Communications Direct over ISM devices (SMC-D)
+ *
+ * SMC-D ISM device structure definitions.
+ *
+ * Copyright IBM Corp. 2018
+ */
+
+#ifndef SMCD_ISM_H
+#define SMCD_ISM_H
+
+#include <linux/uio.h>
+
+#include "smc.h"
+
+struct smcd_dev_list {	/* List of SMCD devices */
+	struct list_head list;
+	spinlock_t lock;	/* Protects list of devices */
+};
+
+extern struct smcd_dev_list	smcd_dev_list; /* list of smcd devices */
+
+struct smc_ism_vlanid {			/* VLAN id set on ISM device */
+	struct list_head list;
+	unsigned short vlanid;		/* Vlan id */
+	refcount_t refcnt;		/* Reference count */
+};
+
+struct smc_ism_position {	/* ISM device position to write to */
+	u64 token;		/* Token of DMB */
+	u32 offset;		/* Offset into DMBE */
+	u8 index;		/* Index of DMBE */
+	u8 signal;		/* Generate interrupt on owner side */
+};
+
+struct smcd_dev;
+
+int smc_ism_cantalk(u64 peer_gid, unsigned short vlan_id, struct smcd_dev *dev);
+void smc_ism_set_conn(struct smc_connection *conn);
+void smc_ism_unset_conn(struct smc_connection *conn);
+int smc_ism_get_vlan(struct smcd_dev *dev, unsigned short vlan_id);
+int smc_ism_put_vlan(struct smcd_dev *dev, unsigned short vlan_id);
+int smc_ism_register_dmb(struct smc_link_group *lgr, int buf_size,
+			 struct smc_buf_desc *dmb_desc);
+int smc_ism_unregister_dmb(struct smcd_dev *dev, struct smc_buf_desc *dmb_desc);
+int smc_ism_write(struct smcd_dev *dev, const struct smc_ism_position *pos,
+		  void *data, size_t len);
+#endif
-- 
cgit v1.2.3


From 1619f770589a183af56f248de261534b255122de Mon Sep 17 00:00:00 2001
From: Hans Wippel <hwippel@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:08 +0200
Subject: net/smc: add pnetid support for SMC-D and ISM

SMC-D relies on PNETIDs to find usable SMC-D/ISM devices for a SMC
connection. This patch adds SMC-D/ISM support to the current PNETID
implementation.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/smc.h  |  1 +
 net/smc/smc_ism.c  |  2 ++
 net/smc/smc_pnet.c | 41 +++++++++++++++++++++++++++++++++++++++++
 net/smc/smc_pnet.h |  2 ++
 4 files changed, 46 insertions(+)

diff --git a/include/net/smc.h b/include/net/smc.h
index 824a7af8d654..9ef49f8b1002 100644
--- a/include/net/smc.h
+++ b/include/net/smc.h
@@ -73,6 +73,7 @@ struct smcd_dev {
 	struct smc_connection **conn;
 	struct list_head vlan;
 	struct workqueue_struct *event_wq;
+	u8 pnetid[SMC_MAX_PNETID_LEN];
 };
 
 struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index ca1ce42fd49f..f44e4dff244a 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -13,6 +13,7 @@
 #include "smc.h"
 #include "smc_core.h"
 #include "smc_ism.h"
+#include "smc_pnet.h"
 
 struct smcd_dev_list smcd_dev_list = {
 	.list = LIST_HEAD_INIT(smcd_dev_list.list),
@@ -227,6 +228,7 @@ struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name,
 	device_initialize(&smcd->dev);
 	dev_set_name(&smcd->dev, name);
 	smcd->ops = ops;
+	smc_pnetid_by_dev_port(parent, 0, smcd->pnetid);
 
 	spin_lock_init(&smcd->lock);
 	INIT_LIST_HEAD(&smcd->vlan);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index cdc6e23b6ce1..1b6c066d3495 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -22,6 +22,7 @@
 
 #include "smc_pnet.h"
 #include "smc_ib.h"
+#include "smc_ism.h"
 
 static struct nla_policy smc_pnet_policy[SMC_PNETID_MAX + 1] = {
 	[SMC_PNETID_NAME] = {
@@ -564,6 +565,27 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
 	spin_unlock(&smc_ib_devices.lock);
 }
 
+static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
+					struct smcd_dev **smcismdev)
+{
+	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct smcd_dev *ismdev;
+
+	ndev = pnet_find_base_ndev(ndev);
+	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+				   ndev_pnetid))
+		return; /* pnetid could not be determined */
+
+	spin_lock(&smcd_dev_list.lock);
+	list_for_each_entry(ismdev, &smcd_dev_list.list, list) {
+		if (!memcmp(ismdev->pnetid, ndev_pnetid, SMC_MAX_PNETID_LEN)) {
+			*smcismdev = ismdev;
+			break;
+		}
+	}
+	spin_unlock(&smcd_dev_list.lock);
+}
+
 /* Lookup of coupled ib_device via SMC pnet table */
 static void smc_pnet_find_roce_by_table(struct net_device *netdev,
 					struct smc_ib_device **smcibdev,
@@ -615,3 +637,22 @@ out_rel:
 out:
 	return;
 }
+
+void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev)
+{
+	struct dst_entry *dst = sk_dst_get(sk);
+
+	*smcismdev = NULL;
+	if (!dst)
+		goto out;
+	if (!dst->dev)
+		goto out_rel;
+
+	/* if possible, lookup via hardware-defined pnetid */
+	smc_pnet_find_ism_by_pnetid(dst->dev, smcismdev);
+
+out_rel:
+	dst_release(dst);
+out:
+	return;
+}
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index ad4455cde9e7..1e94fd4df7bc 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -17,6 +17,7 @@
 #endif
 
 struct smc_ib_device;
+struct smcd_dev;
 
 static inline int smc_pnetid_by_dev_port(struct device *dev,
 					 unsigned short port, u8 *pnetid)
@@ -33,5 +34,6 @@ void smc_pnet_exit(void);
 int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
 void smc_pnet_find_roce_resource(struct sock *sk,
 				 struct smc_ib_device **smcibdev, u8 *ibport);
+void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
 
 #endif
-- 
cgit v1.2.3


From c758dfddc1b5b1c9b8c64e5e4bb9bf24b74f4a59 Mon Sep 17 00:00:00 2001
From: Hans Wippel <hwippel@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:09 +0200
Subject: net/smc: add SMC-D support in CLC messages

There are two types of SMC: SMC-R and SMC-D. These types are signaled
within the CLC messages during the CLC handshake. This patch adds
support for and checks of the SMC type.

Also, SMC-R and SMC-D need to exchange different information during the
CLC handshake. So, this patch extends the current message formats to
support the SMC-D header fields. The Proposal message can contain both
SMC-R and SMC-D information. The Accept and Confirm messages contain
either SMC-R or SMC-D information.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c  |   9 +--
 net/smc/smc_clc.c | 193 ++++++++++++++++++++++++++++++++++++++----------------
 net/smc/smc_clc.h |  81 ++++++++++++++++++-----
 3 files changed, 205 insertions(+), 78 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 8ce48799cf68..20afa94be8bb 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -451,14 +451,14 @@ static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
 }
 
 /* CLC handshake during connect */
-static int smc_connect_clc(struct smc_sock *smc,
+static int smc_connect_clc(struct smc_sock *smc, int smc_type,
 			   struct smc_clc_msg_accept_confirm *aclc,
 			   struct smc_ib_device *ibdev, u8 ibport)
 {
 	int rc = 0;
 
 	/* do inband token exchange */
-	rc = smc_clc_send_proposal(smc, ibdev, ibport);
+	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, NULL);
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
@@ -564,7 +564,7 @@ static int __smc_connect(struct smc_sock *smc)
 		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
 
 	/* perform CLC handshake */
-	rc = smc_connect_clc(smc, &aclc, ibdev, ibport);
+	rc = smc_connect_clc(smc, SMC_TYPE_R, &aclc, ibdev, ibport);
 	if (rc)
 		return smc_connect_decline_fallback(smc, rc);
 
@@ -1008,7 +1008,8 @@ static void smc_listen_work(struct work_struct *work)
 	smc_tx_init(new_smc);
 
 	/* check if RDMA is available */
-	if (smc_check_rdma(new_smc, &ibdev, &ibport) ||
+	if ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
+	    smc_check_rdma(new_smc, &ibdev, &ibport) ||
 	    smc_listen_rdma_check(new_smc, pclc) ||
 	    smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
 				 &local_contact) ||
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 717449b1da0b..038d70ef7892 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -23,9 +23,15 @@
 #include "smc_core.h"
 #include "smc_clc.h"
 #include "smc_ib.h"
+#include "smc_ism.h"
+
+#define SMCR_CLC_ACCEPT_CONFIRM_LEN 68
+#define SMCD_CLC_ACCEPT_CONFIRM_LEN 48
 
 /* eye catcher "SMCR" EBCDIC for CLC messages */
 static const char SMC_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xd9'};
+/* eye catcher "SMCD" EBCDIC for CLC messages */
+static const char SMCD_EYECATCHER[4] = {'\xe2', '\xd4', '\xc3', '\xc4'};
 
 /* check if received message has a correct header length and contains valid
  * heading and trailing eyecatchers
@@ -38,10 +44,14 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm)
 	struct smc_clc_msg_decline *dclc;
 	struct smc_clc_msg_trail *trl;
 
-	if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)))
+	if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) &&
+	    memcmp(clcm->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)))
 		return false;
 	switch (clcm->type) {
 	case SMC_CLC_PROPOSAL:
+		if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D &&
+		    clcm->path != SMC_TYPE_B)
+			return false;
 		pclc = (struct smc_clc_msg_proposal *)clcm;
 		pclc_prfx = smc_clc_proposal_get_prefix(pclc);
 		if (ntohs(pclc->hdr.length) !=
@@ -56,10 +66,16 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm)
 		break;
 	case SMC_CLC_ACCEPT:
 	case SMC_CLC_CONFIRM:
+		if (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D)
+			return false;
 		clc = (struct smc_clc_msg_accept_confirm *)clcm;
-		if (ntohs(clc->hdr.length) != sizeof(*clc))
+		if ((clcm->path == SMC_TYPE_R &&
+		     ntohs(clc->hdr.length) != SMCR_CLC_ACCEPT_CONFIRM_LEN) ||
+		    (clcm->path == SMC_TYPE_D &&
+		     ntohs(clc->hdr.length) != SMCD_CLC_ACCEPT_CONFIRM_LEN))
 			return false;
-		trl = &clc->trl;
+		trl = (struct smc_clc_msg_trail *)
+			((u8 *)clc + ntohs(clc->hdr.length) - sizeof(*trl));
 		break;
 	case SMC_CLC_DECLINE:
 		dclc = (struct smc_clc_msg_decline *)clcm;
@@ -70,7 +86,8 @@ static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm)
 	default:
 		return false;
 	}
-	if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)))
+	if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) &&
+	    memcmp(trl->eyecatcher, SMCD_EYECATCHER, sizeof(SMCD_EYECATCHER)))
 		return false;
 	return true;
 }
@@ -295,6 +312,9 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 	datlen = ntohs(clcm->length);
 	if ((len < sizeof(struct smc_clc_msg_hdr)) ||
 	    (datlen > buflen) ||
+	    (clcm->version != SMC_CLC_V1) ||
+	    (clcm->path != SMC_TYPE_R && clcm->path != SMC_TYPE_D &&
+	     clcm->path != SMC_TYPE_B) ||
 	    ((clcm->type != SMC_CLC_DECLINE) &&
 	     (clcm->type != expected_type))) {
 		smc->sk.sk_err = EPROTO;
@@ -356,17 +376,18 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 }
 
 /* send CLC PROPOSAL message across internal TCP socket */
-int smc_clc_send_proposal(struct smc_sock *smc,
-			  struct smc_ib_device *smcibdev,
-			  u8 ibport)
+int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
+			  struct smc_ib_device *ibdev, u8 ibport,
+			  struct smcd_dev *ismdev)
 {
 	struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
 	struct smc_clc_msg_proposal_prefix pclc_prfx;
+	struct smc_clc_msg_smcd pclc_smcd;
 	struct smc_clc_msg_proposal pclc;
 	struct smc_clc_msg_trail trl;
 	int len, i, plen, rc;
 	int reason_code = 0;
-	struct kvec vec[4];
+	struct kvec vec[5];
 	struct msghdr msg;
 
 	/* retrieve ip prefixes for CLC proposal msg */
@@ -381,18 +402,34 @@ int smc_clc_send_proposal(struct smc_sock *smc,
 	memset(&pclc, 0, sizeof(pclc));
 	memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	pclc.hdr.type = SMC_CLC_PROPOSAL;
-	pclc.hdr.length = htons(plen);
 	pclc.hdr.version = SMC_CLC_V1;		/* SMC version */
-	memcpy(pclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
-	memcpy(&pclc.lcl.gid, &smcibdev->gid[ibport - 1], SMC_GID_SIZE);
-	memcpy(&pclc.lcl.mac, &smcibdev->mac[ibport - 1], ETH_ALEN);
-	pclc.iparea_offset = htons(0);
+	pclc.hdr.path = smc_type;
+	if (smc_type == SMC_TYPE_R || smc_type == SMC_TYPE_B) {
+		/* add SMC-R specifics */
+		memcpy(pclc.lcl.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
+		memcpy(&pclc.lcl.gid, &ibdev->gid[ibport - 1], SMC_GID_SIZE);
+		memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
+		pclc.iparea_offset = htons(0);
+	}
+	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+		/* add SMC-D specifics */
+		memset(&pclc_smcd, 0, sizeof(pclc_smcd));
+		plen += sizeof(pclc_smcd);
+		pclc.iparea_offset = htons(SMC_CLC_PROPOSAL_MAX_OFFSET);
+		pclc_smcd.gid = ismdev->local_gid;
+	}
+	pclc.hdr.length = htons(plen);
 
 	memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	memset(&msg, 0, sizeof(msg));
 	i = 0;
 	vec[i].iov_base = &pclc;
 	vec[i++].iov_len = sizeof(pclc);
+	if (smc_type == SMC_TYPE_D || smc_type == SMC_TYPE_B) {
+		vec[i].iov_base = &pclc_smcd;
+		vec[i++].iov_len = sizeof(pclc_smcd);
+	}
 	vec[i].iov_base = &pclc_prfx;
 	vec[i++].iov_len = sizeof(pclc_prfx);
 	if (pclc_prfx.ipv6_prefixes_cnt > 0) {
@@ -428,35 +465,56 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 	struct kvec vec;
 	int len;
 
-	link = &conn->lgr->lnk[SMC_SINGLE_LINK];
 	/* send SMC Confirm CLC msg */
 	memset(&cclc, 0, sizeof(cclc));
-	memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	cclc.hdr.type = SMC_CLC_CONFIRM;
-	cclc.hdr.length = htons(sizeof(cclc));
 	cclc.hdr.version = SMC_CLC_V1;		/* SMC version */
-	memcpy(cclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
-	memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
-	       SMC_GID_SIZE);
-	memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
-	hton24(cclc.qpn, link->roce_qp->qp_num);
-	cclc.rmb_rkey =
-		htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
-	cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
-	cclc.rmbe_alert_token = htonl(conn->alert_token_local);
-	cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
-	cclc.rmbe_size = conn->rmbe_size_short;
-	cclc.rmb_dma_addr = cpu_to_be64(
-		(u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
-	hton24(cclc.psn, link->psn_initial);
-
-	memcpy(cclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+	if (smc->conn.lgr->is_smcd) {
+		/* SMC-D specific settings */
+		memcpy(cclc.hdr.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+		cclc.hdr.path = SMC_TYPE_D;
+		cclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+		cclc.gid = conn->lgr->smcd->local_gid;
+		cclc.token = conn->rmb_desc->token;
+		cclc.dmbe_size = conn->rmbe_size_short;
+		cclc.dmbe_idx = 0;
+		memcpy(&cclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+		memcpy(cclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+	} else {
+		/* SMC-R specific settings */
+		link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+		memcpy(cclc.hdr.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+		cclc.hdr.path = SMC_TYPE_R;
+		cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+		memcpy(cclc.lcl.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
+		memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
+		       SMC_GID_SIZE);
+		memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
+		       ETH_ALEN);
+		hton24(cclc.qpn, link->roce_qp->qp_num);
+		cclc.rmb_rkey =
+			htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		cclc.rmbe_idx = 1; /* for now: 1 RMB = 1 RMBE */
+		cclc.rmbe_alert_token = htonl(conn->alert_token_local);
+		cclc.qp_mtu = min(link->path_mtu, link->peer_mtu);
+		cclc.rmbe_size = conn->rmbe_size_short;
+		cclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
+				(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+		hton24(cclc.psn, link->psn_initial);
+		memcpy(cclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+	}
 
 	memset(&msg, 0, sizeof(msg));
 	vec.iov_base = &cclc;
-	vec.iov_len = sizeof(cclc);
-	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(cclc));
-	if (len < sizeof(cclc)) {
+	vec.iov_len = ntohs(cclc.hdr.length);
+	len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1,
+			     ntohs(cclc.hdr.length));
+	if (len < ntohs(cclc.hdr.length)) {
 		if (len >= 0) {
 			reason_code = -ENETUNREACH;
 			smc->sk.sk_err = -reason_code;
@@ -479,35 +537,58 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 	int rc = 0;
 	int len;
 
-	link = &conn->lgr->lnk[SMC_SINGLE_LINK];
 	memset(&aclc, 0, sizeof(aclc));
-	memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
 	aclc.hdr.type = SMC_CLC_ACCEPT;
-	aclc.hdr.length = htons(sizeof(aclc));
 	aclc.hdr.version = SMC_CLC_V1;		/* SMC version */
 	if (srv_first_contact)
 		aclc.hdr.flag = 1;
-	memcpy(aclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid));
-	memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
-	       SMC_GID_SIZE);
-	memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1], ETH_ALEN);
-	hton24(aclc.qpn, link->roce_qp->qp_num);
-	aclc.rmb_rkey =
-		htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
-	aclc.rmbe_idx = 1;			/* as long as 1 RMB = 1 RMBE */
-	aclc.rmbe_alert_token = htonl(conn->alert_token_local);
-	aclc.qp_mtu = link->path_mtu;
-	aclc.rmbe_size = conn->rmbe_size_short,
-	aclc.rmb_dma_addr = cpu_to_be64(
-		(u64)sg_dma_address(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
-	hton24(aclc.psn, link->psn_initial);
-	memcpy(aclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER));
+
+	if (new_smc->conn.lgr->is_smcd) {
+		/* SMC-D specific settings */
+		aclc.hdr.length = htons(SMCD_CLC_ACCEPT_CONFIRM_LEN);
+		memcpy(aclc.hdr.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+		aclc.hdr.path = SMC_TYPE_D;
+		aclc.gid = conn->lgr->smcd->local_gid;
+		aclc.token = conn->rmb_desc->token;
+		aclc.dmbe_size = conn->rmbe_size_short;
+		aclc.dmbe_idx = 0;
+		memcpy(&aclc.linkid, conn->lgr->id, SMC_LGR_ID_SIZE);
+		memcpy(aclc.smcd_trl.eyecatcher, SMCD_EYECATCHER,
+		       sizeof(SMCD_EYECATCHER));
+	} else {
+		/* SMC-R specific settings */
+		aclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
+		memcpy(aclc.hdr.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+		aclc.hdr.path = SMC_TYPE_R;
+		link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+		memcpy(aclc.lcl.id_for_peer, local_systemid,
+		       sizeof(local_systemid));
+		memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
+		       SMC_GID_SIZE);
+		memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
+		       ETH_ALEN);
+		hton24(aclc.qpn, link->roce_qp->qp_num);
+		aclc.rmb_rkey =
+			htonl(conn->rmb_desc->mr_rx[SMC_SINGLE_LINK]->rkey);
+		aclc.rmbe_idx = 1;		/* as long as 1 RMB = 1 RMBE */
+		aclc.rmbe_alert_token = htonl(conn->alert_token_local);
+		aclc.qp_mtu = link->path_mtu;
+		aclc.rmbe_size = conn->rmbe_size_short,
+		aclc.rmb_dma_addr = cpu_to_be64((u64)sg_dma_address
+				(conn->rmb_desc->sgt[SMC_SINGLE_LINK].sgl));
+		hton24(aclc.psn, link->psn_initial);
+		memcpy(aclc.smcr_trl.eyecatcher, SMC_EYECATCHER,
+		       sizeof(SMC_EYECATCHER));
+	}
 
 	memset(&msg, 0, sizeof(msg));
 	vec.iov_base = &aclc;
-	vec.iov_len = sizeof(aclc);
-	len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1, sizeof(aclc));
-	if (len < sizeof(aclc)) {
+	vec.iov_len = ntohs(aclc.hdr.length);
+	len = kernel_sendmsg(new_smc->clcsock, &msg, &vec, 1,
+			     ntohs(aclc.hdr.length));
+	if (len < ntohs(aclc.hdr.length)) {
 		if (len >= 0)
 			new_smc->sk.sk_err = EPROTO;
 		else
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 41ff9ea96139..100e988ad1a8 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -23,6 +23,9 @@
 #define SMC_CLC_DECLINE		0x04
 
 #define SMC_CLC_V1		0x1		/* SMC version                */
+#define SMC_TYPE_R		0		/* SMC-R only		      */
+#define SMC_TYPE_D		1		/* SMC-D only		      */
+#define SMC_TYPE_B		3		/* SMC-R and SMC-D	      */
 #define CLC_WAIT_TIME		(6 * HZ)	/* max. wait time on clcsock  */
 #define SMC_CLC_DECL_MEM	0x01010000  /* insufficient memory resources  */
 #define SMC_CLC_DECL_TIMEOUT	0x02000000  /* timeout                        */
@@ -42,9 +45,11 @@ struct smc_clc_msg_hdr {	/* header1 of clc messages */
 #if defined(__BIG_ENDIAN_BITFIELD)
 	u8 version : 4,
 	   flag    : 1,
-	   rsvd    : 3;
+	   rsvd	   : 1,
+	   path	   : 2;
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	u8 rsvd    : 3,
+	u8 path    : 2,
+	   rsvd    : 1,
 	   flag    : 1,
 	   version : 4;
 #endif
@@ -77,6 +82,11 @@ struct smc_clc_msg_proposal_prefix {	/* prefix part of clc proposal message*/
 	u8 ipv6_prefixes_cnt;	/* number of IPv6 prefixes in prefix array */
 } __aligned(4);
 
+struct smc_clc_msg_smcd {	/* SMC-D GID information */
+	u64 gid;		/* ISM GID of requestor */
+	u8 res[32];
+};
+
 struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
 	struct smc_clc_msg_hdr hdr;
 	struct smc_clc_msg_local lcl;
@@ -94,23 +104,45 @@ struct smc_clc_msg_proposal {	/* clc proposal message sent by Linux */
 
 struct smc_clc_msg_accept_confirm {	/* clc accept / confirm message */
 	struct smc_clc_msg_hdr hdr;
-	struct smc_clc_msg_local lcl;
-	u8 qpn[3];		/* QP number */
-	__be32 rmb_rkey;	/* RMB rkey */
-	u8 rmbe_idx;		/* Index of RMBE in RMB */
-	__be32 rmbe_alert_token;/* unique connection id */
+	union {
+		struct { /* SMC-R */
+			struct smc_clc_msg_local lcl;
+			u8 qpn[3];		/* QP number */
+			__be32 rmb_rkey;	/* RMB rkey */
+			u8 rmbe_idx;		/* Index of RMBE in RMB */
+			__be32 rmbe_alert_token;/* unique connection id */
 #if defined(__BIG_ENDIAN_BITFIELD)
-	u8 rmbe_size : 4,	/* RMBE buf size (compressed notation) */
-	   qp_mtu   : 4;	/* QP mtu */
+			u8 rmbe_size : 4,	/* buf size (compressed) */
+			   qp_mtu   : 4;	/* QP mtu */
 #elif defined(__LITTLE_ENDIAN_BITFIELD)
-	u8 qp_mtu   : 4,
-	   rmbe_size : 4;
+			u8 qp_mtu   : 4,
+			   rmbe_size : 4;
 #endif
-	u8 reserved;
-	__be64 rmb_dma_addr;	/* RMB virtual address */
-	u8 reserved2;
-	u8 psn[3];		/* initial packet sequence number */
-	struct smc_clc_msg_trail trl; /* eye catcher "SMCR" EBCDIC */
+			u8 reserved;
+			__be64 rmb_dma_addr;	/* RMB virtual address */
+			u8 reserved2;
+			u8 psn[3];		/* packet sequence number */
+			struct smc_clc_msg_trail smcr_trl;
+						/* eye catcher "SMCR" EBCDIC */
+		} __packed;
+		struct { /* SMC-D */
+			u64 gid;		/* Sender GID */
+			u64 token;		/* DMB token */
+			u8 dmbe_idx;		/* DMBE index */
+#if defined(__BIG_ENDIAN_BITFIELD)
+			u8 dmbe_size : 4,	/* buf size (compressed) */
+			   reserved3 : 4;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+			u8 reserved3 : 4,
+			   dmbe_size : 4;
+#endif
+			u16 reserved4;
+			u32 linkid;		/* Link identifier */
+			u32 reserved5[3];
+			struct smc_clc_msg_trail smcd_trl;
+						/* eye catcher "SMCD" EBCDIC */
+		} __packed;
+	};
 } __packed;			/* format defined in RFC7609 */
 
 struct smc_clc_msg_decline {	/* clc decline message */
@@ -129,13 +161,26 @@ smc_clc_proposal_get_prefix(struct smc_clc_msg_proposal *pclc)
 	       ((u8 *)pclc + sizeof(*pclc) + ntohs(pclc->iparea_offset));
 }
 
+/* get SMC-D info from proposal message */
+static inline struct smc_clc_msg_smcd *
+smc_get_clc_msg_smcd(struct smc_clc_msg_proposal *prop)
+{
+	if (ntohs(prop->iparea_offset) != sizeof(struct smc_clc_msg_smcd))
+		return NULL;
+
+	return (struct smc_clc_msg_smcd *)(prop + 1);
+}
+
+struct smcd_dev;
+
 int smc_clc_prfx_match(struct socket *clcsock,
 		       struct smc_clc_msg_proposal_prefix *prop);
 int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type);
 int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
-int smc_clc_send_proposal(struct smc_sock *smc, struct smc_ib_device *smcibdev,
-			  u8 ibport);
+int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
+			  struct smc_ib_device *smcibdev, u8 ibport,
+			  struct smcd_dev *ismdev);
 int smc_clc_send_confirm(struct smc_sock *smc);
 int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
 
-- 
cgit v1.2.3


From be244f28d22f77d939ba2b973c102ad2b49d3496 Mon Sep 17 00:00:00 2001
From: Hans Wippel <hwippel@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:10 +0200
Subject: net/smc: add SMC-D support in data transfer

The data transfer and CDC message headers differ in SMC-R and SMC-D.
This patch adds support for the SMC-D data transfer to the existing SMC
code. It consists of the following:

* SMC-D CDC support
* SMC-D tx support
* SMC-D rx support

The CDC header is stored at the beginning of the receive buffer. Thus, a
rx_offset variable is added for the CDC header offset within the buffer
(0 for SMC-R).

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc.h      |   5 ++
 net/smc/smc_cdc.c  |  86 +++++++++++++++++++++++-
 net/smc/smc_cdc.h  |  43 +++++++++++-
 net/smc/smc_core.c |  25 +++++--
 net/smc/smc_ism.c  |   8 +++
 net/smc/smc_rx.c   |   2 +-
 net/smc/smc_tx.c   | 193 +++++++++++++++++++++++++++++++++++++++++------------
 net/smc/smc_tx.h   |   2 +
 8 files changed, 308 insertions(+), 56 deletions(-)

diff --git a/net/smc/smc.h b/net/smc/smc.h
index 7c86f716a92e..8c6231011779 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -183,6 +183,11 @@ struct smc_connection {
 	spinlock_t		acurs_lock;	/* protect cursors */
 #endif
 	struct work_struct	close_work;	/* peer sent some closing */
+	struct tasklet_struct	rx_tsklet;	/* Receiver tasklet for SMC-D */
+	u8			rx_off;		/* receive offset:
+						 * 0 for SMC-R, 32 for SMC-D
+						 */
+	u64			peer_token;	/* SMC-D token of peer */
 };
 
 struct smc_sock {				/* smc sock container */
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index a7e8d63fc8ae..621d8cca570b 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -117,7 +117,7 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	return rc;
 }
 
-int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
+static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 {
 	struct smc_cdc_tx_pend *pend;
 	struct smc_wr_buf *wr_buf;
@@ -130,6 +130,21 @@ int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 	return smc_cdc_msg_send(conn, wr_buf, pend);
 }
 
+int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn)
+{
+	int rc;
+
+	if (conn->lgr->is_smcd) {
+		spin_lock_bh(&conn->send_lock);
+		rc = smcd_cdc_msg_send(conn);
+		spin_unlock_bh(&conn->send_lock);
+	} else {
+		rc = smcr_cdc_get_slot_and_msg_send(conn);
+	}
+
+	return rc;
+}
+
 static bool smc_cdc_tx_filter(struct smc_wr_tx_pend_priv *tx_pend,
 			      unsigned long data)
 {
@@ -157,6 +172,45 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn)
 				(unsigned long)conn);
 }
 
+/* Send a SMC-D CDC header.
+ * This increments the free space available in our send buffer.
+ * Also update the confirmed receive buffer with what was sent to the peer.
+ */
+int smcd_cdc_msg_send(struct smc_connection *conn)
+{
+	struct smc_sock *smc = container_of(conn, struct smc_sock, conn);
+	struct smcd_cdc_msg cdc;
+	int rc, diff;
+
+	memset(&cdc, 0, sizeof(cdc));
+	cdc.common.type = SMC_CDC_MSG_TYPE;
+	cdc.prod_wrap = conn->local_tx_ctrl.prod.wrap;
+	cdc.prod_count = conn->local_tx_ctrl.prod.count;
+
+	cdc.cons_wrap = conn->local_tx_ctrl.cons.wrap;
+	cdc.cons_count = conn->local_tx_ctrl.cons.count;
+	cdc.prod_flags = conn->local_tx_ctrl.prod_flags;
+	cdc.conn_state_flags = conn->local_tx_ctrl.conn_state_flags;
+	rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1);
+	if (rc)
+		return rc;
+	smc_curs_write(&conn->rx_curs_confirmed,
+		       smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn);
+	/* Calculate transmitted data and increment free send buffer space */
+	diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
+			     &conn->tx_curs_sent);
+	/* increased by confirmed number of bytes */
+	smp_mb__before_atomic();
+	atomic_add(diff, &conn->sndbuf_space);
+	/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
+	smp_mb__after_atomic();
+	smc_curs_write(&conn->tx_curs_fin,
+		       smc_curs_read(&conn->tx_curs_sent, conn), conn);
+
+	smc_tx_sndbuf_nonfull(smc);
+	return rc;
+}
+
 /********************************* receive ***********************************/
 
 static inline bool smc_cdc_before(u16 seq1, u16 seq2)
@@ -178,7 +232,7 @@ static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc,
 	if (!sock_flag(&smc->sk, SOCK_URGINLINE))
 		/* we'll skip the urgent byte, so don't account for it */
 		(*diff_prod)--;
-	base = (char *)conn->rmb_desc->cpu_addr;
+	base = (char *)conn->rmb_desc->cpu_addr + conn->rx_off;
 	if (conn->urg_curs.count)
 		conn->urg_rx_byte = *(base + conn->urg_curs.count - 1);
 	else
@@ -276,6 +330,34 @@ static void smc_cdc_msg_recv(struct smc_sock *smc, struct smc_cdc_msg *cdc)
 	sock_put(&smc->sk); /* no free sk in softirq-context */
 }
 
+/* Schedule a tasklet for this connection. Triggered from the ISM device IRQ
+ * handler to indicate update in the DMBE.
+ *
+ * Context:
+ * - tasklet context
+ */
+static void smcd_cdc_rx_tsklet(unsigned long data)
+{
+	struct smc_connection *conn = (struct smc_connection *)data;
+	struct smcd_cdc_msg cdc;
+	struct smc_sock *smc;
+
+	if (!conn)
+		return;
+
+	memcpy(&cdc, conn->rmb_desc->cpu_addr, sizeof(cdc));
+	smc = container_of(conn, struct smc_sock, conn);
+	smc_cdc_msg_recv(smc, (struct smc_cdc_msg *)&cdc);
+}
+
+/* Initialize receive tasklet. Called from ISM device IRQ handler to start
+ * receiver side.
+ */
+void smcd_cdc_rx_init(struct smc_connection *conn)
+{
+	tasklet_init(&conn->rx_tsklet, smcd_cdc_rx_tsklet, (unsigned long)conn);
+}
+
 /***************************** init, exit, misc ******************************/
 
 static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index f60082fee5b8..8fbce4fee3e4 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -50,6 +50,20 @@ struct smc_cdc_msg {
 	u8				reserved[18];
 } __packed;					/* format defined in RFC7609 */
 
+/* CDC message for SMC-D */
+struct smcd_cdc_msg {
+	struct smc_wr_rx_hdr common;	/* Type = 0xFE */
+	u8 res1[7];
+	u16 prod_wrap;
+	u32 prod_count;
+	u8 res2[2];
+	u16 cons_wrap;
+	u32 cons_count;
+	struct smc_cdc_producer_flags	prod_flags;
+	struct smc_cdc_conn_state_flags conn_state_flags;
+	u8 res3[8];
+} __packed;
+
 static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn)
 {
 	return conn->local_rx_ctrl.conn_state_flags.peer_conn_abort ||
@@ -204,9 +218,9 @@ static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local,
 	smc_curs_write(local, smc_curs_read(&temp, conn), conn);
 }
 
-static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
-				       struct smc_cdc_msg *peer,
-				       struct smc_connection *conn)
+static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+					struct smc_cdc_msg *peer,
+					struct smc_connection *conn)
 {
 	local->common.type = peer->common.type;
 	local->len = peer->len;
@@ -218,6 +232,27 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
 	local->conn_state_flags = peer->conn_state_flags;
 }
 
+static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+					struct smcd_cdc_msg *peer)
+{
+	local->prod.wrap = peer->prod_wrap;
+	local->prod.count = peer->prod_count;
+	local->cons.wrap = peer->cons_wrap;
+	local->cons.count = peer->cons_count;
+	local->prod_flags = peer->prod_flags;
+	local->conn_state_flags = peer->conn_state_flags;
+}
+
+static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local,
+				       struct smc_cdc_msg *peer,
+				       struct smc_connection *conn)
+{
+	if (conn->lgr->is_smcd)
+		smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer);
+	else
+		smcr_cdc_msg_to_host(local, peer, conn);
+}
+
 struct smc_cdc_tx_pend;
 
 int smc_cdc_get_free_slot(struct smc_connection *conn,
@@ -227,6 +262,8 @@ void smc_cdc_tx_dismiss_slots(struct smc_connection *conn);
 int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
 		     struct smc_cdc_tx_pend *pend);
 int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
+int smcd_cdc_msg_send(struct smc_connection *conn);
 int smc_cdc_init(void) __init;
+void smcd_cdc_rx_init(struct smc_connection *conn);
 
 #endif /* SMC_CDC_H */
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index daa88db1841a..434c028162a4 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -281,10 +281,12 @@ void smc_conn_free(struct smc_connection *conn)
 {
 	if (!conn->lgr)
 		return;
-	if (conn->lgr->is_smcd)
+	if (conn->lgr->is_smcd) {
 		smc_ism_unset_conn(conn);
-	else
+		tasklet_kill(&conn->rx_tsklet);
+	} else {
 		smc_cdc_tx_dismiss_slots(conn);
+	}
 	smc_lgr_unregister_conn(conn);
 	smc_buf_unuse(conn);
 }
@@ -324,10 +326,13 @@ static void smcr_buf_free(struct smc_link_group *lgr, bool is_rmb,
 static void smcd_buf_free(struct smc_link_group *lgr, bool is_dmb,
 			  struct smc_buf_desc *buf_desc)
 {
-	if (is_dmb)
+	if (is_dmb) {
+		/* restore original buf len */
+		buf_desc->len += sizeof(struct smcd_cdc_msg);
 		smc_ism_unregister_dmb(lgr->smcd, buf_desc);
-	else
+	} else {
 		kfree(buf_desc->cpu_addr);
+	}
 	kfree(buf_desc);
 }
 
@@ -632,6 +637,10 @@ create:
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
 	conn->urg_state = SMC_URG_READ;
+	if (is_smcd) {
+		conn->rx_off = sizeof(struct smcd_cdc_msg);
+		smcd_cdc_rx_init(conn); /* init tasklet for this conn */
+	}
 #ifndef KERNEL_HAS_ATOMIC64
 	spin_lock_init(&conn->acurs_lock);
 #endif
@@ -776,8 +785,9 @@ static struct smc_buf_desc *smcd_new_buf_create(struct smc_link_group *lgr,
 			kfree(buf_desc);
 			return ERR_PTR(-EAGAIN);
 		}
-		memset(buf_desc->cpu_addr, 0, bufsize);
-		buf_desc->len = bufsize;
+		buf_desc->pages = virt_to_page(buf_desc->cpu_addr);
+		/* CDC header stored in buf. So, pretend it was smaller */
+		buf_desc->len = bufsize - sizeof(struct smcd_cdc_msg);
 	} else {
 		buf_desc->cpu_addr = kzalloc(bufsize, GFP_KERNEL |
 					     __GFP_NOWARN | __GFP_NORETRY |
@@ -854,7 +864,8 @@ static int __smc_buf_create(struct smc_sock *smc, bool is_smcd, bool is_rmb)
 		conn->rmbe_size_short = bufsize_short;
 		smc->sk.sk_rcvbuf = bufsize * 2;
 		atomic_set(&conn->bytes_to_rcv, 0);
-		conn->rmbe_update_limit = smc_rmb_wnd_update_limit(bufsize);
+		conn->rmbe_update_limit =
+			smc_rmb_wnd_update_limit(buf_desc->len);
 		if (is_smcd)
 			smc_ism_set_conn(conn); /* map RMB/smcd_dev to conn */
 	} else {
diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index f44e4dff244a..cfade7fdcc6d 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -302,5 +302,13 @@ EXPORT_SYMBOL_GPL(smcd_handle_event);
  */
 void smcd_handle_irq(struct smcd_dev *smcd, unsigned int dmbno)
 {
+	struct smc_connection *conn = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&smcd->lock, flags);
+	conn = smcd->conn[dmbno];
+	if (conn)
+		tasklet_schedule(&conn->rx_tsklet);
+	spin_unlock_irqrestore(&smcd->lock, flags);
 }
 EXPORT_SYMBOL_GPL(smcd_handle_irq);
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index 3d77b383cccd..b329803c8339 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -305,7 +305,7 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg,
 	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);
 
 	/* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */
-	rcvbuf_base = conn->rmb_desc->cpu_addr;
+	rcvbuf_base = conn->rx_off + conn->rmb_desc->cpu_addr;
 
 	do { /* while (read_remaining) */
 		if (read_done >= target || (pipe && read_done))
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index f82886b7d1d8..142bcb134dd6 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -24,6 +24,7 @@
 #include "smc.h"
 #include "smc_wr.h"
 #include "smc_cdc.h"
+#include "smc_ism.h"
 #include "smc_tx.h"
 
 #define SMC_TX_WORK_DELAY	HZ
@@ -250,6 +251,24 @@ out_err:
 
 /***************************** sndbuf consumer *******************************/
 
+/* sndbuf consumer: actual data transfer of one target chunk with ISM write */
+int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
+		      u32 offset, int signal)
+{
+	struct smc_ism_position pos;
+	int rc;
+
+	memset(&pos, 0, sizeof(pos));
+	pos.token = conn->peer_token;
+	pos.index = conn->peer_rmbe_idx;
+	pos.offset = conn->tx_off + offset;
+	pos.signal = signal;
+	rc = smc_ism_write(conn->lgr->smcd, &pos, data, len);
+	if (rc)
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+	return rc;
+}
+
 /* sndbuf consumer: actual data transfer of one target chunk with RDMA write */
 static int smc_tx_rdma_write(struct smc_connection *conn, int peer_rmbe_offset,
 			     int num_sges, struct ib_sge sges[])
@@ -297,21 +316,104 @@ static inline void smc_tx_advance_cursors(struct smc_connection *conn,
 	smc_curs_add(conn->sndbuf_desc->len, sent, len);
 }
 
+/* SMC-R helper for smc_tx_rdma_writes() */
+static int smcr_tx_rdma_writes(struct smc_connection *conn, size_t len,
+			       size_t src_off, size_t src_len,
+			       size_t dst_off, size_t dst_len)
+{
+	dma_addr_t dma_addr =
+		sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
+	struct smc_link *link = &conn->lgr->lnk[SMC_SINGLE_LINK];
+	int src_len_sum = src_len, dst_len_sum = dst_len;
+	struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
+	int sent_count = src_off;
+	int srcchunk, dstchunk;
+	int num_sges;
+	int rc;
+
+	for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+		num_sges = 0;
+		for (srcchunk = 0; srcchunk < 2; srcchunk++) {
+			sges[srcchunk].addr = dma_addr + src_off;
+			sges[srcchunk].length = src_len;
+			sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
+			num_sges++;
+
+			src_off += src_len;
+			if (src_off >= conn->sndbuf_desc->len)
+				src_off -= conn->sndbuf_desc->len;
+						/* modulo in send ring */
+			if (src_len_sum == dst_len)
+				break; /* either on 1st or 2nd iteration */
+			/* prepare next (== 2nd) iteration */
+			src_len = dst_len - src_len; /* remainder */
+			src_len_sum += src_len;
+		}
+		rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
+		if (rc)
+			return rc;
+		if (dst_len_sum == len)
+			break; /* either on 1st or 2nd iteration */
+		/* prepare next (== 2nd) iteration */
+		dst_off = 0; /* modulo offset in RMBE ring buffer */
+		dst_len = len - dst_len; /* remainder */
+		dst_len_sum += dst_len;
+		src_len = min_t(int, dst_len, conn->sndbuf_desc->len -
+				sent_count);
+		src_len_sum = src_len;
+	}
+	return 0;
+}
+
+/* SMC-D helper for smc_tx_rdma_writes() */
+static int smcd_tx_rdma_writes(struct smc_connection *conn, size_t len,
+			       size_t src_off, size_t src_len,
+			       size_t dst_off, size_t dst_len)
+{
+	int src_len_sum = src_len, dst_len_sum = dst_len;
+	int srcchunk, dstchunk;
+	int rc;
+
+	for (dstchunk = 0; dstchunk < 2; dstchunk++) {
+		for (srcchunk = 0; srcchunk < 2; srcchunk++) {
+			void *data = conn->sndbuf_desc->cpu_addr + src_off;
+
+			rc = smcd_tx_ism_write(conn, data, src_len, dst_off +
+					       sizeof(struct smcd_cdc_msg), 0);
+			if (rc)
+				return rc;
+			dst_off += src_len;
+			src_off += src_len;
+			if (src_off >= conn->sndbuf_desc->len)
+				src_off -= conn->sndbuf_desc->len;
+						/* modulo in send ring */
+			if (src_len_sum == dst_len)
+				break; /* either on 1st or 2nd iteration */
+			/* prepare next (== 2nd) iteration */
+			src_len = dst_len - src_len; /* remainder */
+			src_len_sum += src_len;
+		}
+		if (dst_len_sum == len)
+			break; /* either on 1st or 2nd iteration */
+		/* prepare next (== 2nd) iteration */
+		dst_off = 0; /* modulo offset in RMBE ring buffer */
+		dst_len = len - dst_len; /* remainder */
+		dst_len_sum += dst_len;
+		src_len = min_t(int, dst_len, conn->sndbuf_desc->len - src_off);
+		src_len_sum = src_len;
+	}
+	return 0;
+}
+
 /* sndbuf consumer: prepare all necessary (src&dst) chunks of data transmit;
  * usable snd_wnd as max transmit
  */
 static int smc_tx_rdma_writes(struct smc_connection *conn)
 {
-	size_t src_off, src_len, dst_off, dst_len; /* current chunk values */
-	size_t len, dst_len_sum, src_len_sum, dstchunk, srcchunk;
+	size_t len, src_len, dst_off, dst_len; /* current chunk values */
 	union smc_host_cursor sent, prep, prod, cons;
-	struct ib_sge sges[SMC_IB_MAX_SEND_SGE];
-	struct smc_link_group *lgr = conn->lgr;
 	struct smc_cdc_producer_flags *pflags;
 	int to_send, rmbespace;
-	struct smc_link *link;
-	dma_addr_t dma_addr;
-	int num_sges;
 	int rc;
 
 	/* source: sndbuf */
@@ -341,7 +443,6 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 	len = min(to_send, rmbespace);
 
 	/* initialize variables for first iteration of subsequent nested loop */
-	link = &lgr->lnk[SMC_SINGLE_LINK];
 	dst_off = prod.count;
 	if (prod.wrap == cons.wrap) {
 		/* the filled destination area is unwrapped,
@@ -358,8 +459,6 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 		 */
 		dst_len = len;
 	}
-	dst_len_sum = dst_len;
-	src_off = sent.count;
 	/* dst_len determines the maximum src_len */
 	if (sent.count + dst_len <= conn->sndbuf_desc->len) {
 		/* unwrapped src case: single chunk of entire dst_len */
@@ -368,38 +467,15 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 		/* wrapped src case: 2 chunks of sum dst_len; start with 1st: */
 		src_len = conn->sndbuf_desc->len - sent.count;
 	}
-	src_len_sum = src_len;
-	dma_addr = sg_dma_address(conn->sndbuf_desc->sgt[SMC_SINGLE_LINK].sgl);
-	for (dstchunk = 0; dstchunk < 2; dstchunk++) {
-		num_sges = 0;
-		for (srcchunk = 0; srcchunk < 2; srcchunk++) {
-			sges[srcchunk].addr = dma_addr + src_off;
-			sges[srcchunk].length = src_len;
-			sges[srcchunk].lkey = link->roce_pd->local_dma_lkey;
-			num_sges++;
-			src_off += src_len;
-			if (src_off >= conn->sndbuf_desc->len)
-				src_off -= conn->sndbuf_desc->len;
-						/* modulo in send ring */
-			if (src_len_sum == dst_len)
-				break; /* either on 1st or 2nd iteration */
-			/* prepare next (== 2nd) iteration */
-			src_len = dst_len - src_len; /* remainder */
-			src_len_sum += src_len;
-		}
-		rc = smc_tx_rdma_write(conn, dst_off, num_sges, sges);
-		if (rc)
-			return rc;
-		if (dst_len_sum == len)
-			break; /* either on 1st or 2nd iteration */
-		/* prepare next (== 2nd) iteration */
-		dst_off = 0; /* modulo offset in RMBE ring buffer */
-		dst_len = len - dst_len; /* remainder */
-		dst_len_sum += dst_len;
-		src_len = min_t(int,
-				dst_len, conn->sndbuf_desc->len - sent.count);
-		src_len_sum = src_len;
-	}
+
+	if (conn->lgr->is_smcd)
+		rc = smcd_tx_rdma_writes(conn, len, sent.count, src_len,
+					 dst_off, dst_len);
+	else
+		rc = smcr_tx_rdma_writes(conn, len, sent.count, src_len,
+					 dst_off, dst_len);
+	if (rc)
+		return rc;
 
 	if (conn->urg_tx_pend && len == to_send)
 		pflags->urg_data_present = 1;
@@ -420,7 +496,7 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 /* Wakeup sndbuf consumers from any context (IRQ or process)
  * since there is more data to transmit; usable snd_wnd as max transmit
  */
-int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
+static int smcr_tx_sndbuf_nonempty(struct smc_connection *conn)
 {
 	struct smc_cdc_producer_flags *pflags;
 	struct smc_cdc_tx_pend *pend;
@@ -467,6 +543,37 @@ out_unlock:
 	return rc;
 }
 
+static int smcd_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+	struct smc_cdc_producer_flags *pflags = &conn->local_tx_ctrl.prod_flags;
+	int rc = 0;
+
+	spin_lock_bh(&conn->send_lock);
+	if (!pflags->urg_data_present)
+		rc = smc_tx_rdma_writes(conn);
+	if (!rc)
+		rc = smcd_cdc_msg_send(conn);
+
+	if (!rc && pflags->urg_data_present) {
+		pflags->urg_data_pending = 0;
+		pflags->urg_data_present = 0;
+	}
+	spin_unlock_bh(&conn->send_lock);
+	return rc;
+}
+
+int smc_tx_sndbuf_nonempty(struct smc_connection *conn)
+{
+	int rc;
+
+	if (conn->lgr->is_smcd)
+		rc = smcd_tx_sndbuf_nonempty(conn);
+	else
+		rc = smcr_tx_sndbuf_nonempty(conn);
+
+	return rc;
+}
+
 /* Wakeup sndbuf consumers from process context
  * since there is more data to transmit
  */
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index 9d2238909fa0..b22bdc5694c4 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -33,5 +33,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);
 int smc_tx_sndbuf_nonempty(struct smc_connection *conn);
 void smc_tx_sndbuf_nonfull(struct smc_sock *smc);
 void smc_tx_consumer_update(struct smc_connection *conn, bool force);
+int smcd_tx_ism_write(struct smc_connection *conn, void *data, size_t len,
+		      u32 offset, int signal);
 
 #endif /* SMC_TX_H */
-- 
cgit v1.2.3


From 413498440e30bfe381ac99dfc31628a3d8d4382a Mon Sep 17 00:00:00 2001
From: Hans Wippel <hwippel@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:11 +0200
Subject: net/smc: add SMC-D support in af_smc

This patch ties together the previous SMC-D patches. It adds support for
SMC-D to the listen and connect functions and, thus, enables SMC-D
support in the SMC code. If a connection supports both SMC-R and SMC-D,
SMC-D is preferred.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c   | 216 ++++++++++++++++++++++++++++++++++++++++++++++++-----
 net/smc/smc_core.c |   2 +-
 net/smc/smc_core.h |   1 +
 3 files changed, 200 insertions(+), 19 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 20afa94be8bb..cbbb947dbfcf 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -23,6 +23,7 @@
 #include <linux/workqueue.h>
 #include <linux/in.h>
 #include <linux/sched/signal.h>
+#include <linux/if_vlan.h>
 
 #include <net/sock.h>
 #include <net/tcp.h>
@@ -35,6 +36,7 @@
 #include "smc_cdc.h"
 #include "smc_core.h"
 #include "smc_ib.h"
+#include "smc_ism.h"
 #include "smc_pnet.h"
 #include "smc_tx.h"
 #include "smc_rx.h"
@@ -372,8 +374,8 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 	return 0;
 }
 
-static void smc_conn_save_peer_info(struct smc_sock *smc,
-				    struct smc_clc_msg_accept_confirm *clc)
+static void smcr_conn_save_peer_info(struct smc_sock *smc,
+				     struct smc_clc_msg_accept_confirm *clc)
 {
 	int bufsize = smc_uncompress_bufsize(clc->rmbe_size);
 
@@ -384,6 +386,28 @@ static void smc_conn_save_peer_info(struct smc_sock *smc,
 	smc->conn.tx_off = bufsize * (smc->conn.peer_rmbe_idx - 1);
 }
 
+static void smcd_conn_save_peer_info(struct smc_sock *smc,
+				     struct smc_clc_msg_accept_confirm *clc)
+{
+	int bufsize = smc_uncompress_bufsize(clc->dmbe_size);
+
+	smc->conn.peer_rmbe_idx = clc->dmbe_idx;
+	smc->conn.peer_token = clc->token;
+	/* msg header takes up space in the buffer */
+	smc->conn.peer_rmbe_size = bufsize - sizeof(struct smcd_cdc_msg);
+	atomic_set(&smc->conn.peer_rmbe_space, smc->conn.peer_rmbe_size);
+	smc->conn.tx_off = bufsize * smc->conn.peer_rmbe_idx;
+}
+
+static void smc_conn_save_peer_info(struct smc_sock *smc,
+				    struct smc_clc_msg_accept_confirm *clc)
+{
+	if (smc->conn.lgr->is_smcd)
+		smcd_conn_save_peer_info(smc, clc);
+	else
+		smcr_conn_save_peer_info(smc, clc);
+}
+
 static void smc_link_save_peer_info(struct smc_link *link,
 				    struct smc_clc_msg_accept_confirm *clc)
 {
@@ -450,15 +474,51 @@ static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
 	return reason_code;
 }
 
+/* check if there is an ISM device available for this connection. */
+/* called for connect and listen */
+static int smc_check_ism(struct smc_sock *smc, struct smcd_dev **ismdev)
+{
+	/* Find ISM device with same PNETID as connecting interface  */
+	smc_pnet_find_ism_resource(smc->clcsock->sk, ismdev);
+	if (!(*ismdev))
+		return SMC_CLC_DECL_CNFERR; /* configuration error */
+	return 0;
+}
+
+/* Check for VLAN ID and register it on ISM device just for CLC handshake */
+static int smc_connect_ism_vlan_setup(struct smc_sock *smc,
+				      struct smcd_dev *ismdev,
+				      unsigned short vlan_id)
+{
+	if (vlan_id && smc_ism_get_vlan(ismdev, vlan_id))
+		return SMC_CLC_DECL_CNFERR;
+	return 0;
+}
+
+/* cleanup temporary VLAN ID registration used for CLC handshake. If ISM is
+ * used, the VLAN ID will be registered again during the connection setup.
+ */
+static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
+					struct smcd_dev *ismdev,
+					unsigned short vlan_id)
+{
+	if (!is_smcd)
+		return 0;
+	if (vlan_id && smc_ism_put_vlan(ismdev, vlan_id))
+		return SMC_CLC_DECL_CNFERR;
+	return 0;
+}
+
 /* CLC handshake during connect */
 static int smc_connect_clc(struct smc_sock *smc, int smc_type,
 			   struct smc_clc_msg_accept_confirm *aclc,
-			   struct smc_ib_device *ibdev, u8 ibport)
+			   struct smc_ib_device *ibdev, u8 ibport,
+			   struct smcd_dev *ismdev)
 {
 	int rc = 0;
 
 	/* do inband token exchange */
-	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, NULL);
+	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, ismdev);
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
@@ -538,11 +598,50 @@ static int smc_connect_rdma(struct smc_sock *smc,
 	return 0;
 }
 
+/* setup for ISM connection of client */
+static int smc_connect_ism(struct smc_sock *smc,
+			   struct smc_clc_msg_accept_confirm *aclc,
+			   struct smcd_dev *ismdev)
+{
+	int local_contact = SMC_FIRST_CONTACT;
+	int rc = 0;
+
+	mutex_lock(&smc_create_lgr_pending);
+	local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0,
+					NULL, ismdev, aclc->gid);
+	if (local_contact < 0)
+		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0);
+
+	/* Create send and receive buffers */
+	if (smc_buf_create(smc, true))
+		return smc_connect_abort(smc, SMC_CLC_DECL_MEM, local_contact);
+
+	smc_conn_save_peer_info(smc, aclc);
+	smc_close_init(smc);
+	smc_rx_init(smc);
+	smc_tx_init(smc);
+
+	rc = smc_clc_send_confirm(smc);
+	if (rc)
+		return smc_connect_abort(smc, rc, local_contact);
+	mutex_unlock(&smc_create_lgr_pending);
+
+	smc_copy_sock_settings_to_clc(smc);
+	if (smc->sk.sk_state == SMC_INIT)
+		smc->sk.sk_state = SMC_ACTIVE;
+
+	return 0;
+}
+
 /* perform steps before actually connecting */
 static int __smc_connect(struct smc_sock *smc)
 {
+	bool ism_supported = false, rdma_supported = false;
 	struct smc_clc_msg_accept_confirm aclc;
 	struct smc_ib_device *ibdev;
+	struct smcd_dev *ismdev;
+	unsigned short vlan;
+	int smc_type;
 	int rc = 0;
 	u8 ibport;
 
@@ -559,20 +658,52 @@ static int __smc_connect(struct smc_sock *smc)
 	if (using_ipsec(smc))
 		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_IPSEC);
 
-	/* check if a RDMA device is available; if not, fall back */
-	if (smc_check_rdma(smc, &ibdev, &ibport))
+	/* check for VLAN ID */
+	if (smc_vlan_by_tcpsk(smc->clcsock, &vlan))
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+
+	/* check if there is an ism device available */
+	if (!smc_check_ism(smc, &ismdev) &&
+	    !smc_connect_ism_vlan_setup(smc, ismdev, vlan)) {
+		/* ISM is supported for this connection */
+		ism_supported = true;
+		smc_type = SMC_TYPE_D;
+	}
+
+	/* check if there is a rdma device available */
+	if (!smc_check_rdma(smc, &ibdev, &ibport)) {
+		/* RDMA is supported for this connection */
+		rdma_supported = true;
+		if (ism_supported)
+			smc_type = SMC_TYPE_B; /* both */
+		else
+			smc_type = SMC_TYPE_R; /* only RDMA */
+	}
+
+	/* if neither ISM nor RDMA are supported, fallback */
+	if (!rdma_supported && !ism_supported)
 		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
 
 	/* perform CLC handshake */
-	rc = smc_connect_clc(smc, SMC_TYPE_R, &aclc, ibdev, ibport);
-	if (rc)
+	rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, ismdev);
+	if (rc) {
+		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
 		return smc_connect_decline_fallback(smc, rc);
+	}
 
-	/* connect using rdma */
-	rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
-	if (rc)
+	/* depending on previous steps, connect using rdma or ism */
+	if (rdma_supported && aclc.hdr.path == SMC_TYPE_R)
+		rc = smc_connect_rdma(smc, &aclc, ibdev, ibport);
+	else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
+		rc = smc_connect_ism(smc, &aclc, ismdev);
+	else
+		rc = SMC_CLC_DECL_CNFERR;
+	if (rc) {
+		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
 		return smc_connect_decline_fallback(smc, rc);
+	}
 
+	smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
 	return 0;
 }
 
@@ -909,6 +1040,44 @@ static int smc_listen_rdma_init(struct smc_sock *new_smc,
 	return 0;
 }
 
+/* listen worker: initialize connection and buffers for SMC-D */
+static int smc_listen_ism_init(struct smc_sock *new_smc,
+			       struct smc_clc_msg_proposal *pclc,
+			       struct smcd_dev *ismdev,
+			       int *local_contact)
+{
+	struct smc_clc_msg_smcd *pclc_smcd;
+
+	pclc_smcd = smc_get_clc_msg_smcd(pclc);
+	*local_contact = smc_conn_create(new_smc, true, 0, NULL, 0, NULL,
+					 ismdev, pclc_smcd->gid);
+	if (*local_contact < 0) {
+		if (*local_contact == -ENOMEM)
+			return SMC_CLC_DECL_MEM;/* insufficient memory*/
+		return SMC_CLC_DECL_INTERR; /* other error */
+	}
+
+	/* Check if peer can be reached via ISM device */
+	if (smc_ism_cantalk(new_smc->conn.lgr->peer_gid,
+			    new_smc->conn.lgr->vlan_id,
+			    new_smc->conn.lgr->smcd)) {
+		if (*local_contact == SMC_FIRST_CONTACT)
+			smc_lgr_forget(new_smc->conn.lgr);
+		smc_conn_free(&new_smc->conn);
+		return SMC_CLC_DECL_CNFERR;
+	}
+
+	/* Create send and receive buffers */
+	if (smc_buf_create(new_smc, true)) {
+		if (*local_contact == SMC_FIRST_CONTACT)
+			smc_lgr_forget(new_smc->conn.lgr);
+		smc_conn_free(&new_smc->conn);
+		return SMC_CLC_DECL_MEM;
+	}
+
+	return 0;
+}
+
 /* listen worker: register buffers */
 static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
 {
@@ -967,6 +1136,8 @@ static void smc_listen_work(struct work_struct *work)
 	struct smc_clc_msg_accept_confirm cclc;
 	struct smc_clc_msg_proposal *pclc;
 	struct smc_ib_device *ibdev;
+	bool ism_supported = false;
+	struct smcd_dev *ismdev;
 	u8 buf[SMC_CLC_MAX_LEN];
 	int local_contact = 0;
 	int reason_code = 0;
@@ -1007,13 +1178,21 @@ static void smc_listen_work(struct work_struct *work)
 	smc_rx_init(new_smc);
 	smc_tx_init(new_smc);
 
+	/* check if ISM is available */
+	if ((pclc->hdr.path == SMC_TYPE_D || pclc->hdr.path == SMC_TYPE_B) &&
+	    !smc_check_ism(new_smc, &ismdev) &&
+	    !smc_listen_ism_init(new_smc, pclc, ismdev, &local_contact)) {
+		ism_supported = true;
+	}
+
 	/* check if RDMA is available */
-	if ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
-	    smc_check_rdma(new_smc, &ibdev, &ibport) ||
-	    smc_listen_rdma_check(new_smc, pclc) ||
-	    smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
-				 &local_contact) ||
-	    smc_listen_rdma_reg(new_smc, local_contact)) {
+	if (!ism_supported &&
+	    ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
+	     smc_check_rdma(new_smc, &ibdev, &ibport) ||
+	     smc_listen_rdma_check(new_smc, pclc) ||
+	     smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
+				  &local_contact) ||
+	     smc_listen_rdma_reg(new_smc, local_contact))) {
 		/* SMC not supported, decline */
 		mutex_unlock(&smc_create_lgr_pending);
 		smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact);
@@ -1038,7 +1217,8 @@ static void smc_listen_work(struct work_struct *work)
 	}
 
 	/* finish worker */
-	smc_listen_rdma_finish(new_smc, &cclc, local_contact);
+	if (!ism_supported)
+		smc_listen_rdma_finish(new_smc, &cclc, local_contact);
 	smc_conn_save_peer_info(new_smc, &cclc);
 	mutex_unlock(&smc_create_lgr_pending);
 	smc_listen_out_connected(new_smc);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 434c028162a4..66741e61a3b0 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -478,7 +478,7 @@ void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid)
 /* Determine vlan of internal TCP socket.
  * @vlan_id: address to store the determined vlan id into
  */
-static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
+int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
 {
 	struct dst_entry *dst = sk_dst_get(clcsock->sk);
 	struct net_device *ndev;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index cd9268a9570e..8b47e0168fc3 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -257,6 +257,7 @@ void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
 void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
 void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
 void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
+int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id);
 
 void smc_conn_free(struct smc_connection *conn);
 int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
-- 
cgit v1.2.3


From 4b1b7d3b30a6d32ac1a1dcede284e76ef8a8542d Mon Sep 17 00:00:00 2001
From: Hans Wippel <hwippel@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:12 +0200
Subject: net/smc: add SMC-D diag support

This patch adds diag support for SMC-D.

Signed-off-by: Hans Wippel <hwippel@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/smc_diag.h | 10 ++++++++++
 net/smc/smc_diag.c            | 15 +++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h
index 0ae5d4685ba3..92be255e534c 100644
--- a/include/uapi/linux/smc_diag.h
+++ b/include/uapi/linux/smc_diag.h
@@ -35,6 +35,7 @@ enum {
 	SMC_DIAG_CONNINFO,
 	SMC_DIAG_LGRINFO,
 	SMC_DIAG_SHUTDOWN,
+	SMC_DIAG_DMBINFO,
 	__SMC_DIAG_MAX,
 };
 
@@ -83,4 +84,13 @@ struct smc_diag_lgrinfo {
 	struct smc_diag_linkinfo	lnk[1];
 	__u8				role;
 };
+
+struct smcd_diag_dmbinfo {		/* SMC-D Socket internals */
+	__u32 linkid;			/* Link identifier */
+	__u64 peer_gid;			/* Peer GID */
+	__u64 my_gid;			/* My GID */
+	__u64 token;			/* Token of DMB */
+	__u64 peer_token;		/* Token of remote DMBE */
+};
+
 #endif /* _UAPI_SMC_DIAG_H_ */
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 64ce107c24d9..6d83eef1b743 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -156,6 +156,21 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 		if (nla_put(skb, SMC_DIAG_LGRINFO, sizeof(linfo), &linfo) < 0)
 			goto errout;
 	}
+	if (smc->conn.lgr && smc->conn.lgr->is_smcd &&
+	    (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) &&
+	    !list_empty(&smc->conn.lgr->list)) {
+		struct smc_connection *conn = &smc->conn;
+		struct smcd_diag_dmbinfo dinfo = {
+			.linkid = *((u32 *)conn->lgr->id),
+			.peer_gid = conn->lgr->peer_gid,
+			.my_gid = conn->lgr->smcd->local_gid,
+			.token = conn->rmb_desc->token,
+			.peer_token = conn->peer_token
+		};
+
+		if (nla_put(skb, SMC_DIAG_DMBINFO, sizeof(dinfo), &dinfo) < 0)
+			goto errout;
+	}
 
 	nlmsg_end(skb, nlh);
 	return 0;
-- 
cgit v1.2.3


From 684b89bc39ce4f204b1a2b180f39f2eb36a6b695 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:05:13 +0200
Subject: s390/ism: add device driver for internal shared memory

Add support for the Internal Shared Memory vPCI Adapter.
This driver implements the interfaces of the SMC-D protocol.

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/Kconfig   |  10 +
 drivers/s390/net/Makefile  |   3 +
 drivers/s390/net/ism.h     | 221 ++++++++++++++++
 drivers/s390/net/ism_drv.c | 623 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 857 insertions(+)
 create mode 100644 drivers/s390/net/ism.h
 create mode 100644 drivers/s390/net/ism_drv.c

diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index c7e484f70654..7c5a25ddf832 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -95,4 +95,14 @@ config CCWGROUP
 	tristate
 	default (LCS || CTCM || QETH)
 
+config ISM
+	tristate "Support for ISM vPCI Adapter"
+	depends on PCI && SMC
+	default n
+	help
+	  Select this option if you want to use the Internal Shared Memory
+	  vPCI Adapter.
+
+	  To compile as a module choose M. The module name is ism.
+	  If unsure, choose N.
 endmenu
diff --git a/drivers/s390/net/Makefile b/drivers/s390/net/Makefile
index 513b7ae64980..f2d6bbe57a6f 100644
--- a/drivers/s390/net/Makefile
+++ b/drivers/s390/net/Makefile
@@ -15,3 +15,6 @@ qeth_l2-y += qeth_l2_main.o qeth_l2_sys.o
 obj-$(CONFIG_QETH_L2) += qeth_l2.o
 qeth_l3-y += qeth_l3_main.o qeth_l3_sys.o
 obj-$(CONFIG_QETH_L3) += qeth_l3.o
+
+ism-y := ism_drv.o
+obj-$(CONFIG_ISM) += ism.o
diff --git a/drivers/s390/net/ism.h b/drivers/s390/net/ism.h
new file mode 100644
index 000000000000..0aab90817326
--- /dev/null
+++ b/drivers/s390/net/ism.h
@@ -0,0 +1,221 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef S390_ISM_H
+#define S390_ISM_H
+
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/pci.h>
+#include <net/smc.h>
+
+#define UTIL_STR_LEN	16
+
+/*
+ * Do not use the first word of the DMB bits to ensure 8 byte aligned access.
+ */
+#define ISM_DMB_WORD_OFFSET	1
+#define ISM_DMB_BIT_OFFSET	(ISM_DMB_WORD_OFFSET * 32)
+#define ISM_NR_DMBS		1920
+
+#define ISM_REG_SBA	0x1
+#define ISM_REG_IEQ	0x2
+#define ISM_READ_GID	0x3
+#define ISM_ADD_VLAN_ID	0x4
+#define ISM_DEL_VLAN_ID	0x5
+#define ISM_SET_VLAN	0x6
+#define ISM_RESET_VLAN	0x7
+#define ISM_QUERY_INFO	0x8
+#define ISM_QUERY_RGID	0x9
+#define ISM_REG_DMB	0xA
+#define ISM_UNREG_DMB	0xB
+#define ISM_SIGNAL_IEQ	0xE
+#define ISM_UNREG_SBA	0x11
+#define ISM_UNREG_IEQ	0x12
+
+#define ISM_ERROR	0xFFFF
+
+struct ism_req_hdr {
+	u32 cmd;
+	u16 : 16;
+	u16 len;
+};
+
+struct ism_resp_hdr {
+	u32 cmd;
+	u16 ret;
+	u16 len;
+};
+
+union ism_reg_sba {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 sba;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_reg_ieq {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 ieq;
+		u64 len;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_read_gid {
+	struct {
+		struct ism_req_hdr hdr;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+		u64 gid;
+	} response;
+} __aligned(16);
+
+union ism_qi {
+	struct {
+		struct ism_req_hdr hdr;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+		u32 version;
+		u32 max_len;
+		u64 ism_state;
+		u64 my_gid;
+		u64 sba;
+		u64 ieq;
+		u32 ieq_len;
+		u32 : 32;
+		u32 dmbs_owned;
+		u32 dmbs_used;
+		u32 vlan_required;
+		u32 vlan_nr_ids;
+		u16 vlan_id[64];
+	} response;
+} __aligned(64);
+
+union ism_query_rgid {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 rgid;
+		u32 vlan_valid;
+		u32 vlan_id;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_reg_dmb {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 dmb;
+		u32 dmb_len;
+		u32 sba_idx;
+		u32 vlan_valid;
+		u32 vlan_id;
+		u64 rgid;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+		u64 dmb_tok;
+	} response;
+} __aligned(32);
+
+union ism_sig_ieq {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 rgid;
+		u32 trigger_irq;
+		u32 event_code;
+		u64 info;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(32);
+
+union ism_unreg_dmb {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 dmb_tok;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+union ism_cmd_simple {
+	struct {
+		struct ism_req_hdr hdr;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(8);
+
+union ism_set_vlan_id {
+	struct {
+		struct ism_req_hdr hdr;
+		u64 vlan_id;
+	} request;
+	struct {
+		struct ism_resp_hdr hdr;
+	} response;
+} __aligned(16);
+
+struct ism_eq_header {
+	u64 idx;
+	u64 ieq_len;
+	u64 entry_len;
+	u64 : 64;
+};
+
+struct ism_eq {
+	struct ism_eq_header header;
+	struct smcd_event entry[15];
+};
+
+struct ism_sba {
+	u32 s : 1;	/* summary bit */
+	u32 e : 1;	/* event bit */
+	u32 : 30;
+	u32 dmb_bits[ISM_NR_DMBS / 32];
+	u32 reserved[3];
+	u16 dmbe_mask[ISM_NR_DMBS];
+};
+
+struct ism_dev {
+	spinlock_t lock;
+	struct pci_dev *pdev;
+	struct smcd_dev *smcd;
+
+	void __iomem *ctl;
+
+	struct ism_sba *sba;
+	dma_addr_t sba_dma_addr;
+	DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS);
+
+	struct ism_eq *ieq;
+	dma_addr_t ieq_dma_addr;
+
+	int ieq_idx;
+};
+
+#define ISM_CREATE_REQ(dmb, idx, sf, offset)		\
+	((dmb) | (idx) << 24 | (sf) << 23 | (offset))
+
+static inline int __ism_move(struct ism_dev *ism, u64 dmb_req, void *data,
+			     unsigned int size)
+{
+	struct zpci_dev *zdev = to_zpci(ism->pdev);
+	u64 req = ZPCI_CREATE_REQ(zdev->fh, 0, size);
+
+	return zpci_write_block(req, data, dmb_req);
+}
+
+#endif /* S390_ISM_H */
diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
new file mode 100644
index 000000000000..c0631895154e
--- /dev/null
+++ b/drivers/s390/net/ism_drv.c
@@ -0,0 +1,623 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ISM driver for s390.
+ *
+ * Copyright IBM Corp. 2018
+ */
+#define KMSG_COMPONENT "ism"
+#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/pci.h>
+#include <linux/err.h>
+#include <net/smc.h>
+
+#include <asm/debug.h>
+
+#include "ism.h"
+
+MODULE_DESCRIPTION("ISM driver for s390");
+MODULE_LICENSE("GPL");
+
+#define PCI_DEVICE_ID_IBM_ISM 0x04ED
+#define DRV_NAME "ism"
+
+static const struct pci_device_id ism_device_table[] = {
+	{ PCI_VDEVICE(IBM, PCI_DEVICE_ID_IBM_ISM), 0 },
+	{ 0, }
+};
+MODULE_DEVICE_TABLE(pci, ism_device_table);
+
+static debug_info_t *ism_debug_info;
+
+static int ism_cmd(struct ism_dev *ism, void *cmd)
+{
+	struct ism_req_hdr *req = cmd;
+	struct ism_resp_hdr *resp = cmd;
+
+	memcpy_toio(ism->ctl + sizeof(*req), req + 1, req->len - sizeof(*req));
+	memcpy_toio(ism->ctl, req, sizeof(*req));
+
+	WRITE_ONCE(resp->ret, ISM_ERROR);
+
+	memcpy_fromio(resp, ism->ctl, sizeof(*resp));
+	if (resp->ret) {
+		debug_text_event(ism_debug_info, 0, "cmd failure");
+		debug_event(ism_debug_info, 0, resp, sizeof(*resp));
+		goto out;
+	}
+	memcpy_fromio(resp + 1, ism->ctl + sizeof(*resp),
+		      resp->len - sizeof(*resp));
+out:
+	return resp->ret;
+}
+
+static int ism_cmd_simple(struct ism_dev *ism, u32 cmd_code)
+{
+	union ism_cmd_simple cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = cmd_code;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int query_info(struct ism_dev *ism)
+{
+	union ism_qi cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_QUERY_INFO;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	if (ism_cmd(ism, &cmd))
+		goto out;
+
+	debug_text_event(ism_debug_info, 3, "query info");
+	debug_event(ism_debug_info, 3, &cmd.response, sizeof(cmd.response));
+out:
+	return 0;
+}
+
+static int register_sba(struct ism_dev *ism)
+{
+	union ism_reg_sba cmd;
+	dma_addr_t dma_handle;
+	struct ism_sba *sba;
+
+	sba = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE,
+				  &dma_handle, GFP_KERNEL);
+	if (!sba)
+		return -ENOMEM;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_REG_SBA;
+	cmd.request.hdr.len = sizeof(cmd.request);
+	cmd.request.sba = dma_handle;
+
+	if (ism_cmd(ism, &cmd)) {
+		dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, sba, dma_handle);
+		return -EIO;
+	}
+
+	ism->sba = sba;
+	ism->sba_dma_addr = dma_handle;
+
+	return 0;
+}
+
+static int register_ieq(struct ism_dev *ism)
+{
+	union ism_reg_ieq cmd;
+	dma_addr_t dma_handle;
+	struct ism_eq *ieq;
+
+	ieq = dma_zalloc_coherent(&ism->pdev->dev, PAGE_SIZE,
+				  &dma_handle, GFP_KERNEL);
+	if (!ieq)
+		return -ENOMEM;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_REG_IEQ;
+	cmd.request.hdr.len = sizeof(cmd.request);
+	cmd.request.ieq = dma_handle;
+	cmd.request.len = sizeof(*ieq);
+
+	if (ism_cmd(ism, &cmd)) {
+		dma_free_coherent(&ism->pdev->dev, PAGE_SIZE, ieq, dma_handle);
+		return -EIO;
+	}
+
+	ism->ieq = ieq;
+	ism->ieq_idx = -1;
+	ism->ieq_dma_addr = dma_handle;
+
+	return 0;
+}
+
+static int unregister_sba(struct ism_dev *ism)
+{
+	if (!ism->sba)
+		return 0;
+
+	if (ism_cmd_simple(ism, ISM_UNREG_SBA))
+		return -EIO;
+
+	dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
+			  ism->sba, ism->sba_dma_addr);
+
+	ism->sba = NULL;
+	ism->sba_dma_addr = 0;
+
+	return 0;
+}
+
+static int unregister_ieq(struct ism_dev *ism)
+{
+	if (!ism->ieq)
+		return 0;
+
+	if (ism_cmd_simple(ism, ISM_UNREG_IEQ))
+		return -EIO;
+
+	dma_free_coherent(&ism->pdev->dev, PAGE_SIZE,
+			  ism->ieq, ism->ieq_dma_addr);
+
+	ism->ieq = NULL;
+	ism->ieq_dma_addr = 0;
+
+	return 0;
+}
+
+static int ism_read_local_gid(struct ism_dev *ism)
+{
+	union ism_read_gid cmd;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_READ_GID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	ret = ism_cmd(ism, &cmd);
+	if (ret)
+		goto out;
+
+	ism->smcd->local_gid = cmd.response.gid;
+out:
+	return ret;
+}
+
+static int ism_query_rgid(struct smcd_dev *smcd, u64 rgid, u32 vid_valid,
+			  u32 vid)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_query_rgid cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_QUERY_RGID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.vlan_valid = vid_valid;
+	cmd.request.vlan_id = vid;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static void ism_free_dmb(struct ism_dev *ism, struct smcd_dmb *dmb)
+{
+	clear_bit(dmb->sba_idx, ism->sba_bitmap);
+	dma_free_coherent(&ism->pdev->dev, dmb->dmb_len,
+			  dmb->cpu_addr, dmb->dma_addr);
+}
+
+static int ism_alloc_dmb(struct ism_dev *ism, struct smcd_dmb *dmb)
+{
+	unsigned long bit;
+
+	if (PAGE_ALIGN(dmb->dmb_len) > dma_get_max_seg_size(&ism->pdev->dev))
+		return -EINVAL;
+
+	if (!dmb->sba_idx) {
+		bit = find_next_zero_bit(ism->sba_bitmap, ISM_NR_DMBS,
+					 ISM_DMB_BIT_OFFSET);
+		if (bit == ISM_NR_DMBS)
+			return -ENOMEM;
+
+		dmb->sba_idx = bit;
+	}
+	if (dmb->sba_idx < ISM_DMB_BIT_OFFSET ||
+	    test_and_set_bit(dmb->sba_idx, ism->sba_bitmap))
+		return -EINVAL;
+
+	dmb->cpu_addr = dma_zalloc_coherent(&ism->pdev->dev, dmb->dmb_len,
+					    &dmb->dma_addr, GFP_KERNEL |
+					    __GFP_NOWARN | __GFP_NOMEMALLOC |
+					    __GFP_COMP | __GFP_NORETRY);
+	if (!dmb->cpu_addr)
+		clear_bit(dmb->sba_idx, ism->sba_bitmap);
+
+	return dmb->cpu_addr ? 0 : -ENOMEM;
+}
+
+static int ism_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_reg_dmb cmd;
+	int ret;
+
+	ret = ism_alloc_dmb(ism, dmb);
+	if (ret)
+		goto out;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_REG_DMB;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.dmb = dmb->dma_addr;
+	cmd.request.dmb_len = dmb->dmb_len;
+	cmd.request.sba_idx = dmb->sba_idx;
+	cmd.request.vlan_valid = dmb->vlan_valid;
+	cmd.request.vlan_id = dmb->vlan_id;
+	cmd.request.rgid = dmb->rgid;
+
+	ret = ism_cmd(ism, &cmd);
+	if (ret) {
+		ism_free_dmb(ism, dmb);
+		goto out;
+	}
+	dmb->dmb_tok = cmd.response.dmb_tok;
+out:
+	return ret;
+}
+
+static int ism_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_unreg_dmb cmd;
+	int ret;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_UNREG_DMB;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.dmb_tok = dmb->dmb_tok;
+
+	ret = ism_cmd(ism, &cmd);
+	if (ret)
+		goto out;
+
+	ism_free_dmb(ism, dmb);
+out:
+	return ret;
+}
+
+static int ism_add_vlan_id(struct smcd_dev *smcd, u64 vlan_id)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_set_vlan_id cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_ADD_VLAN_ID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.vlan_id = vlan_id;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int ism_del_vlan_id(struct smcd_dev *smcd, u64 vlan_id)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_set_vlan_id cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_DEL_VLAN_ID;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.vlan_id = vlan_id;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static int ism_set_vlan_required(struct smcd_dev *smcd)
+{
+	return ism_cmd_simple(smcd->priv, ISM_SET_VLAN);
+}
+
+static int ism_reset_vlan_required(struct smcd_dev *smcd)
+{
+	return ism_cmd_simple(smcd->priv, ISM_RESET_VLAN);
+}
+
+static int ism_signal_ieq(struct smcd_dev *smcd, u64 rgid, u32 trigger_irq,
+			  u32 event_code, u64 info)
+{
+	struct ism_dev *ism = smcd->priv;
+	union ism_sig_ieq cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.request.hdr.cmd = ISM_SIGNAL_IEQ;
+	cmd.request.hdr.len = sizeof(cmd.request);
+
+	cmd.request.rgid = rgid;
+	cmd.request.trigger_irq = trigger_irq;
+	cmd.request.event_code = event_code;
+	cmd.request.info = info;
+
+	return ism_cmd(ism, &cmd);
+}
+
+static unsigned int max_bytes(unsigned int start, unsigned int len,
+			      unsigned int boundary)
+{
+	return min(boundary - (start & (boundary - 1)), len);
+}
+
+static int ism_move(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx,
+		    bool sf, unsigned int offset, void *data, unsigned int size)
+{
+	struct ism_dev *ism = smcd->priv;
+	unsigned int bytes;
+	u64 dmb_req;
+	int ret;
+
+	while (size) {
+		bytes = max_bytes(offset, size, PAGE_SIZE);
+		dmb_req = ISM_CREATE_REQ(dmb_tok, idx, size == bytes ? sf : 0,
+					 offset);
+
+		ret = __ism_move(ism, dmb_req, data, bytes);
+		if (ret)
+			return ret;
+
+		size -= bytes;
+		data += bytes;
+		offset += bytes;
+	}
+
+	return 0;
+}
+
+static void ism_handle_event(struct ism_dev *ism)
+{
+	struct smcd_event *entry;
+
+	while ((ism->ieq_idx + 1) != READ_ONCE(ism->ieq->header.idx)) {
+		if (++(ism->ieq_idx) == ARRAY_SIZE(ism->ieq->entry))
+			ism->ieq_idx = 0;
+
+		entry = &ism->ieq->entry[ism->ieq_idx];
+		debug_event(ism_debug_info, 2, entry, sizeof(*entry));
+		smcd_handle_event(ism->smcd, entry);
+	}
+}
+
+static irqreturn_t ism_handle_irq(int irq, void *data)
+{
+	struct ism_dev *ism = data;
+	unsigned long bit, end;
+	unsigned long *bv;
+
+	bv = (void *) &ism->sba->dmb_bits[ISM_DMB_WORD_OFFSET];
+	end = sizeof(ism->sba->dmb_bits) * BITS_PER_BYTE - ISM_DMB_BIT_OFFSET;
+
+	spin_lock(&ism->lock);
+	ism->sba->s = 0;
+	barrier();
+	for (bit = 0;;) {
+		bit = find_next_bit_inv(bv, end, bit);
+		if (bit >= end)
+			break;
+
+		clear_bit_inv(bit, bv);
+		barrier();
+		smcd_handle_irq(ism->smcd, bit + ISM_DMB_BIT_OFFSET);
+		ism->sba->dmbe_mask[bit + ISM_DMB_BIT_OFFSET] = 0;
+	}
+
+	if (ism->sba->e) {
+		ism->sba->e = 0;
+		barrier();
+		ism_handle_event(ism);
+	}
+	spin_unlock(&ism->lock);
+	return IRQ_HANDLED;
+}
+
+static const struct smcd_ops ism_ops = {
+	.query_remote_gid = ism_query_rgid,
+	.register_dmb = ism_register_dmb,
+	.unregister_dmb = ism_unregister_dmb,
+	.add_vlan_id = ism_add_vlan_id,
+	.del_vlan_id = ism_del_vlan_id,
+	.set_vlan_required = ism_set_vlan_required,
+	.reset_vlan_required = ism_reset_vlan_required,
+	.signal_event = ism_signal_ieq,
+	.move_data = ism_move,
+};
+
+static int ism_dev_init(struct ism_dev *ism)
+{
+	struct pci_dev *pdev = ism->pdev;
+	int ret;
+
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+	if (ret <= 0)
+		goto out;
+
+	ret = request_irq(pci_irq_vector(pdev, 0), ism_handle_irq, 0,
+			  pci_name(pdev), ism);
+	if (ret)
+		goto free_vectors;
+
+	ret = register_sba(ism);
+	if (ret)
+		goto free_irq;
+
+	ret = register_ieq(ism);
+	if (ret)
+		goto unreg_sba;
+
+	ret = ism_read_local_gid(ism);
+	if (ret)
+		goto unreg_ieq;
+
+	ret = smcd_register_dev(ism->smcd);
+	if (ret)
+		goto unreg_ieq;
+
+	query_info(ism);
+	return 0;
+
+unreg_ieq:
+	unregister_ieq(ism);
+unreg_sba:
+	unregister_sba(ism);
+free_irq:
+	free_irq(pci_irq_vector(pdev, 0), ism);
+free_vectors:
+	pci_free_irq_vectors(pdev);
+out:
+	return ret;
+}
+
+static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct ism_dev *ism;
+	int ret;
+
+	ism = kzalloc(sizeof(*ism), GFP_KERNEL);
+	if (!ism)
+		return -ENOMEM;
+
+	spin_lock_init(&ism->lock);
+	dev_set_drvdata(&pdev->dev, ism);
+	ism->pdev = pdev;
+
+	ret = pci_enable_device_mem(pdev);
+	if (ret)
+		goto err;
+
+	ret = pci_request_mem_regions(pdev, DRV_NAME);
+	if (ret)
+		goto err_disable;
+
+	ism->ctl = pci_iomap(pdev, 2, 0);
+	if (!ism->ctl)
+		goto err_resource;
+
+	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (ret)
+		goto err_unmap;
+
+	pci_set_dma_seg_boundary(pdev, SZ_1M - 1);
+	pci_set_dma_max_seg_size(pdev, SZ_1M);
+	pci_set_master(pdev);
+
+	ism->smcd = smcd_alloc_dev(&pdev->dev, dev_name(&pdev->dev), &ism_ops,
+				   ISM_NR_DMBS);
+	if (!ism->smcd)
+		goto err_unmap;
+
+	ism->smcd->priv = ism;
+	ret = ism_dev_init(ism);
+	if (ret)
+		goto err_free;
+
+	return 0;
+
+err_free:
+	smcd_free_dev(ism->smcd);
+err_unmap:
+	pci_iounmap(pdev, ism->ctl);
+err_resource:
+	pci_release_mem_regions(pdev);
+err_disable:
+	pci_disable_device(pdev);
+err:
+	kfree(ism);
+	dev_set_drvdata(&pdev->dev, NULL);
+	return ret;
+}
+
+static void ism_dev_exit(struct ism_dev *ism)
+{
+	struct pci_dev *pdev = ism->pdev;
+
+	smcd_unregister_dev(ism->smcd);
+	unregister_ieq(ism);
+	unregister_sba(ism);
+	free_irq(pci_irq_vector(pdev, 0), ism);
+	pci_free_irq_vectors(pdev);
+}
+
+static void ism_remove(struct pci_dev *pdev)
+{
+	struct ism_dev *ism = dev_get_drvdata(&pdev->dev);
+
+	ism_dev_exit(ism);
+
+	smcd_free_dev(ism->smcd);
+	pci_iounmap(pdev, ism->ctl);
+	pci_release_mem_regions(pdev);
+	pci_disable_device(pdev);
+	dev_set_drvdata(&pdev->dev, NULL);
+	kfree(ism);
+}
+
+static int ism_suspend(struct device *dev)
+{
+	struct ism_dev *ism = dev_get_drvdata(dev);
+
+	ism_dev_exit(ism);
+	return 0;
+}
+
+static int ism_resume(struct device *dev)
+{
+	struct ism_dev *ism = dev_get_drvdata(dev);
+
+	return ism_dev_init(ism);
+}
+
+static SIMPLE_DEV_PM_OPS(ism_pm_ops, ism_suspend, ism_resume);
+
+static struct pci_driver ism_driver = {
+	.name	  = DRV_NAME,
+	.id_table = ism_device_table,
+	.probe	  = ism_probe,
+	.remove	  = ism_remove,
+	.driver	  = {
+		.pm = &ism_pm_ops,
+	},
+};
+
+static int __init ism_init(void)
+{
+	int ret;
+
+	ism_debug_info = debug_register("ism", 2, 1, 16);
+	if (!ism_debug_info)
+		return -ENODEV;
+
+	debug_register_view(ism_debug_info, &debug_hex_ascii_view);
+	ret = pci_register_driver(&ism_driver);
+	if (ret)
+		debug_unregister(ism_debug_info);
+
+	return ret;
+}
+
+static void __exit ism_exit(void)
+{
+	pci_unregister_driver(&ism_driver);
+	debug_unregister(ism_debug_info);
+}
+
+module_init(ism_init);
+module_exit(ism_exit);
-- 
cgit v1.2.3


From 49d17512560b5d9384b9da1f12395be960602420 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 28 Jun 2018 20:36:15 +0200
Subject: r8169: use standard debug output functions

I see no need to define a private debug output symbol, let's use the
standard debug output functions instead. In this context also remove
the deprecated PFX define.

The one assertion is wrong IMO anyway, this code path is used also
by chip version 01.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 36 ++++++++++++------------------------
 1 file changed, 12 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 70c13cc282d0..21ffaf10e942 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -34,7 +34,6 @@
 
 #define RTL8169_VERSION "2.3LK-NAPI"
 #define MODULENAME "r8169"
-#define PFX MODULENAME ": "
 
 #define FIRMWARE_8168D_1	"rtl_nic/rtl8168d-1.fw"
 #define FIRMWARE_8168D_2	"rtl_nic/rtl8168d-2.fw"
@@ -56,19 +55,6 @@
 #define FIRMWARE_8107E_1	"rtl_nic/rtl8107e-1.fw"
 #define FIRMWARE_8107E_2	"rtl_nic/rtl8107e-2.fw"
 
-#ifdef RTL8169_DEBUG
-#define assert(expr) \
-	if (!(expr)) {					\
-		printk( "Assertion failed! %s,%s,%s,line=%d\n",	\
-		#expr,__FILE__,__func__,__LINE__);		\
-	}
-#define dprintk(fmt, args...) \
-	do { printk(KERN_DEBUG PFX fmt, ## args); } while (0)
-#else
-#define assert(expr) do {} while (0)
-#define dprintk(fmt, args...)	do {} while (0)
-#endif /* RTL8169_DEBUG */
-
 #define R8169_MSG_DEFAULT \
 	(NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN)
 
@@ -2552,7 +2538,7 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 
 static void rtl8169_print_mac_version(struct rtl8169_private *tp)
 {
-	dprintk("mac_version = 0x%02x\n", tp->mac_version);
+	netif_dbg(tp, drv, tp->dev, "mac_version = 0x%02x\n", tp->mac_version);
 }
 
 struct phy_reg {
@@ -4409,8 +4395,6 @@ static void rtl_phy_work(struct rtl8169_private *tp)
 	struct timer_list *timer = &tp->timer;
 	unsigned long timeout = RTL8169_PHY_TIMEOUT;
 
-	assert(tp->mac_version > RTL_GIGA_MAC_VER_01);
-
 	if (tp->phy_reset_pending(tp)) {
 		/*
 		 * A busy loop could burn quite a few cycles on nowadays CPU.
@@ -4467,7 +4451,8 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 	rtl_hw_phy_config(dev);
 
 	if (tp->mac_version <= RTL_GIGA_MAC_VER_06) {
-		dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
+		netif_dbg(tp, drv, dev,
+			  "Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
 		RTL_W8(tp, 0x82, 0x01);
 	}
 
@@ -4477,9 +4462,11 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 		pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08);
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_02) {
-		dprintk("Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
+		netif_dbg(tp, drv, dev,
+			  "Set MAC Reg C+CR Offset 0x82h = 0x01h\n");
 		RTL_W8(tp, 0x82, 0x01);
-		dprintk("Set PHY Reg 0x0bh = 0x00h\n");
+		netif_dbg(tp, drv, dev,
+			  "Set PHY Reg 0x0bh = 0x00h\n");
 		rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0
 	}
 
@@ -5171,8 +5158,8 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp)
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_03) {
-		dprintk("Set MAC Reg C+CR Offset 0xe0. "
-			"Bit-3 and bit-14 MUST be 1\n");
+		netif_dbg(tp, drv, tp->dev,
+			  "Set MAC Reg C+CR Offset 0xe0. Bit 3 and Bit 14 MUST be 1\n");
 		tp->cp_cmd |= (1 << 14);
 	}
 
@@ -6017,8 +6004,9 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp)
 		break;
 
 	default:
-		printk(KERN_ERR PFX "%s: unknown chipset (mac_version = %d).\n",
-		       tp->dev->name, tp->mac_version);
+		netif_err(tp, drv, tp->dev,
+			  "unknown chipset (mac_version = %d)\n",
+			  tp->mac_version);
 		break;
 	}
 }
-- 
cgit v1.2.3


From d241d4aac93f25a48ed42c246163b6c28354b1e5 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 28 Jun 2018 20:46:45 +0200
Subject: net: phy: realtek: add support for RTL8211

In preparation of adding phylib support to the r8169 driver we need
PHY drivers for all chip-internal PHY types. Fortunately almost all
of them are either supported by the Realtek PHY driver already or work
with the genphy driver.
Still missing is support for the PHY of RTL8169s, it requires a quirk
to properly support 100Mbit-fixed mode. The quirk was copied from
r8169 driver which copied it from the vendor driver.
Based on the PHYID the internal PHY seems to be a RTL8211.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 082fb40c656d..9757b16231f9 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -128,6 +128,28 @@ static int rtl8211f_config_intr(struct phy_device *phydev)
 	return phy_write_paged(phydev, 0xa42, RTL821x_INER, val);
 }
 
+static int rtl8211_config_aneg(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_config_aneg(phydev);
+	if (ret < 0)
+		return ret;
+
+	/* Quirk was copied from vendor driver. Unfortunately it includes no
+	 * description of the magic numbers.
+	 */
+	if (phydev->speed == SPEED_100 && phydev->autoneg == AUTONEG_DISABLE) {
+		phy_write(phydev, 0x17, 0x2138);
+		phy_write(phydev, 0x0e, 0x0260);
+	} else {
+		phy_write(phydev, 0x17, 0x2108);
+		phy_write(phydev, 0x0e, 0x0000);
+	}
+
+	return 0;
+}
+
 static int rtl8211f_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -178,6 +200,14 @@ static struct phy_driver realtek_drvs[] = {
 		.resume		= genphy_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
+	}, {
+		.phy_id		= 0x001cc910,
+		.name		= "RTL8211 Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.config_aneg	= rtl8211_config_aneg,
+		.read_mmd	= &genphy_read_mmd_unsupported,
+		.write_mmd	= &genphy_write_mmd_unsupported,
 	}, {
 		.phy_id		= 0x001cc912,
 		.name		= "RTL8211B Gigabit Ethernet",
-- 
cgit v1.2.3


From 9ca78674eb6a19acbb1d69e86273ebd1d3edf087 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 28 Jun 2018 13:50:48 -0500
Subject: net: usb: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/catc.c       | 1 +
 drivers/net/usb/cdc-phonet.c | 1 +
 drivers/net/usb/r8152.c      | 2 ++
 3 files changed, 4 insertions(+)

diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index 18d36dff97ea..424053bd8b21 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -869,6 +869,7 @@ static int catc_probe(struct usb_interface *intf, const struct usb_device_id *id
 		default:
 			dev_warn(&intf->dev,
 				 "Couldn't detect memory size, assuming 32k\n");
+			/* fall through */
 		case 0x87654321:
 			catc_set_reg(catc, TxBufCount, 4);
 			catc_set_reg(catc, RxBufCount, 16);
diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c
index 3c40312fa453..78b16eb9e58c 100644
--- a/drivers/net/usb/cdc-phonet.c
+++ b/drivers/net/usb/cdc-phonet.c
@@ -110,6 +110,7 @@ static void tx_complete(struct urb *req)
 	case -ECONNRESET:
 	case -ESHUTDOWN:
 		dev->stats.tx_aborted_errors++;
+		/* fall through */
 	default:
 		dev->stats.tx_errors++;
 		dev_dbg(&dev->dev, "TX error (%d)\n", status);
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index c08c0d633407..a3e06a8bf9c6 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -1376,6 +1376,7 @@ static void intr_callback(struct urb *urb)
 	case -ECONNRESET:	/* unlink */
 	case -ESHUTDOWN:
 		netif_device_detach(tp->netdev);
+		/* fall through */
 	case -ENOENT:
 	case -EPROTO:
 		netif_info(tp, intr, tp->netdev,
@@ -2741,6 +2742,7 @@ static void r8153b_ups_en(struct r8152 *tp, bool enable)
 			r8152_mdio_write(tp, MII_BMCR, data);
 
 			data = r8153_phy_status(tp, PHY_STAT_LAN_ON);
+			/* fall through */
 
 		default:
 			if (data != PHY_STAT_LAN_ON)
-- 
cgit v1.2.3


From ef9be755697f1b841c2a219a05df1a72ccd6f471 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Date: Thu, 28 Jun 2018 22:25:04 +0200
Subject: tipc: eliminate buffer cloning in function tipc_msg_extract()

The function tipc_msg_extract() is using skb_clone() to clone inner
messages from a message bundle buffer. Although this method is safe,
it has an undesired effect that each buffer clone inherits the
true-size of the bundling buffer. As a result, the buffer clone
almost always ends up with being copied anyway by the message
validation function. This makes the cloning into a sub-optimization.

In this commit we take the consequence of this realization, and copy
each inner message to a separately allocated buffer up front in the
extraction function.

As a bonus we can now eliminate the two cases where we had to copy
re-routed packets that may potentially go out on the wire again.

Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/msg.c | 35 +++++++++++++++--------------------
 1 file changed, 15 insertions(+), 20 deletions(-)

diff --git a/net/tipc/msg.c b/net/tipc/msg.c
index b6c45dccba3d..b61891054709 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -416,26 +416,31 @@ bool tipc_msg_bundle(struct sk_buff *skb, struct tipc_msg *msg, u32 mtu)
  */
 bool tipc_msg_extract(struct sk_buff *skb, struct sk_buff **iskb, int *pos)
 {
-	struct tipc_msg *msg;
-	int imsz, offset;
+	struct tipc_msg *hdr, *ihdr;
+	int imsz;
 
 	*iskb = NULL;
 	if (unlikely(skb_linearize(skb)))
 		goto none;
 
-	msg = buf_msg(skb);
-	offset = msg_hdr_sz(msg) + *pos;
-	if (unlikely(offset > (msg_size(msg) - MIN_H_SIZE)))
+	hdr = buf_msg(skb);
+	if (unlikely(*pos > (msg_data_sz(hdr) - MIN_H_SIZE)))
 		goto none;
 
-	*iskb = skb_clone(skb, GFP_ATOMIC);
-	if (unlikely(!*iskb))
+	ihdr = (struct tipc_msg *)(msg_data(hdr) + *pos);
+	imsz = msg_size(ihdr);
+
+	if ((*pos + imsz) > msg_data_sz(hdr))
 		goto none;
-	skb_pull(*iskb, offset);
-	imsz = msg_size(buf_msg(*iskb));
-	skb_trim(*iskb, imsz);
+
+	*iskb = tipc_buf_acquire(imsz, GFP_ATOMIC);
+	if (!*iskb)
+		goto none;
+
+	skb_copy_to_linear_data(*iskb, ihdr, imsz);
 	if (unlikely(!tipc_msg_validate(iskb)))
 		goto none;
+
 	*pos += align(imsz);
 	return true;
 none:
@@ -531,12 +536,6 @@ bool tipc_msg_reverse(u32 own_node,  struct sk_buff **skb, int err)
 		msg_set_hdr_sz(hdr, BASIC_H_SIZE);
 	}
 
-	if (skb_cloned(_skb) &&
-	    pskb_expand_head(_skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC))
-		goto exit;
-
-	/* reassign after skb header modifications */
-	hdr = buf_msg(_skb);
 	/* Now reverse the concerned fields */
 	msg_set_errcode(hdr, err);
 	msg_set_non_seq(hdr, 0);
@@ -595,10 +594,6 @@ bool tipc_msg_lookup_dest(struct net *net, struct sk_buff *skb, int *err)
 	if (!skb_cloned(skb))
 		return true;
 
-	/* Unclone buffer in case it was bundled */
-	if (pskb_expand_head(skb, BUF_HEADROOM, BUF_TAILROOM, GFP_ATOMIC))
-		return false;
-
 	return true;
 }
 
-- 
cgit v1.2.3


From 759f29b62fb9af5274e7f761f9f4cdfa7bb5a1f2 Mon Sep 17 00:00:00 2001
From: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Date: Thu, 28 Jun 2018 22:39:25 +0200
Subject: tipc: optimize function tipc_node_timeout()

In single-link usage, the function tipc_node_timeout() still iterates
over the whole link array to handle each link. Given that the maximum
number of bearers are 3, there are 2 redundant iterations with lock
grab/release. Since this function is executing very frequently it makes
sense to optimize it.

This commit adds conditional checking to exit from the loop if the
known number of configured links has already been accessed.

Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Tung Nguyen <tung.q.nguyen@dektech.com.au>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 6a44eb812baf..8972ca1c654c 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -551,21 +551,23 @@ static void tipc_node_timeout(struct timer_list *t)
 	struct tipc_node *n = from_timer(n, t, timer);
 	struct tipc_link_entry *le;
 	struct sk_buff_head xmitq;
+	int remains = n->link_cnt;
 	int bearer_id;
 	int rc = 0;
 
 	__skb_queue_head_init(&xmitq);
 
-	for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+	for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) {
 		tipc_node_read_lock(n);
 		le = &n->links[bearer_id];
-		spin_lock_bh(&le->lock);
 		if (le->link) {
+			spin_lock_bh(&le->lock);
 			/* Link tolerance may change asynchronously: */
 			tipc_node_calculate_timer(n, le->link);
 			rc = tipc_link_timeout(le->link, &xmitq);
+			spin_unlock_bh(&le->lock);
+			remains--;
 		}
-		spin_unlock_bh(&le->lock);
 		tipc_node_read_unlock(n);
 		tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr);
 		if (rc & TIPC_LINK_DOWN_EVT)
-- 
cgit v1.2.3


From e397286b8e89bf38f4f56c0dcf6626e79dc2a323 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 29 Jun 2018 08:07:04 +0200
Subject: r8169: remove TBI 1000BaseX support

The very first version of RTL8169 from 2002 (and only this one) has
support for a TBI 1000BaseX fiber interface. The TBI support in the
driver makes switching to phylib tricky, so best would be to get
rid of it. I found no report from anybody using a device with RTL8169
and fiber interface, also the vendor driver doesn't support this mode
(any longer).
So remove TBI support and bail out with a message if a card with
activated TBI is detected. If there really should be any user of it
out there, we could add a stripped-down version of the driver
supporting chip version 01 and TBI only (and maybe move it to
staging).

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 156 +++++------------------------------
 1 file changed, 20 insertions(+), 136 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 21ffaf10e942..d943a00dbccf 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -384,12 +384,6 @@ enum rtl_registers {
 	FuncForceEvent	= 0xfc,
 };
 
-enum rtl8110_registers {
-	TBICSR			= 0x64,
-	TBI_ANAR		= 0x68,
-	TBI_LPAR		= 0x6a,
-};
-
 enum rtl8168_8101_registers {
 	CSIDR			= 0x64,
 	CSIAR			= 0x68,
@@ -556,14 +550,6 @@ enum rtl_register_content {
 	PMEStatus	= (1 << 0),	/* PME status can be reset by PCI RST# */
 	ASPM_en		= (1 << 0),	/* ASPM enable */
 
-	/* TBICSR p.28 */
-	TBIReset	= 0x80000000,
-	TBILoopback	= 0x40000000,
-	TBINwEnable	= 0x20000000,
-	TBINwRestart	= 0x10000000,
-	TBILinkOk	= 0x02000000,
-	TBINwComplete	= 0x01000000,
-
 	/* CPlusCmd p.31 */
 	EnableBist	= (1 << 15),	// 8168 8101
 	Mac_dbgo_oe	= (1 << 14),	// 8168 8101
@@ -761,14 +747,7 @@ struct rtl8169_private {
 		void (*disable)(struct rtl8169_private *);
 	} jumbo_ops;
 
-	int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv);
-	int (*get_link_ksettings)(struct net_device *,
-				  struct ethtool_link_ksettings *);
-	void (*phy_reset_enable)(struct rtl8169_private *tp);
 	void (*hw_start)(struct rtl8169_private *tp);
-	unsigned int (*phy_reset_pending)(struct rtl8169_private *tp);
-	unsigned int (*link_ok)(struct rtl8169_private *tp);
-	int (*do_ioctl)(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd);
 	bool (*tso_csum)(struct rtl8169_private *, struct sk_buff *, u32 *);
 
 	struct {
@@ -1463,31 +1442,16 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 	RTL_R8(tp, ChipCmd);
 }
 
-static unsigned int rtl8169_tbi_reset_pending(struct rtl8169_private *tp)
-{
-	return RTL_R32(tp, TBICSR) & TBIReset;
-}
-
 static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp)
 {
 	return rtl_readphy(tp, MII_BMCR) & BMCR_RESET;
 }
 
-static unsigned int rtl8169_tbi_link_ok(struct rtl8169_private *tp)
-{
-	return RTL_R32(tp, TBICSR) & TBILinkOk;
-}
-
 static unsigned int rtl8169_xmii_link_ok(struct rtl8169_private *tp)
 {
 	return RTL_R8(tp, PHYstatus) & LinkStatus;
 }
 
-static void rtl8169_tbi_reset_enable(struct rtl8169_private *tp)
-{
-	RTL_W32(tp, TBICSR, RTL_R32(tp, TBICSR) | TBIReset);
-}
-
 static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp)
 {
 	unsigned int val;
@@ -1557,7 +1521,7 @@ static void rtl8169_check_link_status(struct net_device *dev,
 {
 	struct device *d = tp_to_dev(tp);
 
-	if (tp->link_ok(tp)) {
+	if (rtl8169_xmii_link_ok(tp)) {
 		rtl_link_chg_patch(tp);
 		/* This is to cancel a scheduled suspend if there's one. */
 		pm_request_resume(d);
@@ -1744,28 +1708,6 @@ static int rtl8169_get_regs_len(struct net_device *dev)
 	return R8169_REGS_SIZE;
 }
 
-static int rtl8169_set_speed_tbi(struct net_device *dev,
-				 u8 autoneg, u16 speed, u8 duplex, u32 ignored)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int ret = 0;
-	u32 reg;
-
-	reg = RTL_R32(tp, TBICSR);
-	if ((autoneg == AUTONEG_DISABLE) && (speed == SPEED_1000) &&
-	    (duplex == DUPLEX_FULL)) {
-		RTL_W32(tp, TBICSR, reg & ~(TBINwEnable | TBINwRestart));
-	} else if (autoneg == AUTONEG_ENABLE)
-		RTL_W32(tp, TBICSR, reg | TBINwEnable | TBINwRestart);
-	else {
-		netif_warn(tp, link, dev,
-			   "incorrect speed setting refused in TBI mode\n");
-		ret = -EOPNOTSUPP;
-	}
-
-	return ret;
-}
-
 static int rtl8169_set_speed_xmii(struct net_device *dev,
 				  u8 autoneg, u16 speed, u8 duplex, u32 adv)
 {
@@ -1849,7 +1791,7 @@ static int rtl8169_set_speed(struct net_device *dev,
 	struct rtl8169_private *tp = netdev_priv(dev);
 	int ret;
 
-	ret = tp->set_speed(dev, autoneg, speed, duplex, advertising);
+	ret = rtl8169_set_speed_xmii(dev, autoneg, speed, duplex, advertising);
 	if (ret < 0)
 		goto out;
 
@@ -1925,53 +1867,14 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
 }
 
-static int rtl8169_get_link_ksettings_tbi(struct net_device *dev,
-					  struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	u32 status;
-	u32 supported, advertising;
-
-	supported =
-		SUPPORTED_1000baseT_Full | SUPPORTED_Autoneg | SUPPORTED_FIBRE;
-	cmd->base.port = PORT_FIBRE;
-
-	status = RTL_R32(tp, TBICSR);
-	advertising = (status & TBINwEnable) ?  ADVERTISED_Autoneg : 0;
-	cmd->base.autoneg = !!(status & TBINwEnable);
-
-	cmd->base.speed = SPEED_1000;
-	cmd->base.duplex = DUPLEX_FULL; /* Always set */
-
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.supported,
-						supported);
-	ethtool_convert_legacy_u32_to_link_mode(cmd->link_modes.advertising,
-						advertising);
-
-	return 0;
-}
-
-static int rtl8169_get_link_ksettings_xmii(struct net_device *dev,
-					   struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	mii_ethtool_get_link_ksettings(&tp->mii, cmd);
-
-	return 0;
-}
-
 static int rtl8169_get_link_ksettings(struct net_device *dev,
 				      struct ethtool_link_ksettings *cmd)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
-	int rc;
 
-	rtl_lock_work(tp);
-	rc = tp->get_link_ksettings(dev, cmd);
-	rtl_unlock_work(tp);
+	mii_ethtool_get_link_ksettings(&tp->mii, cmd);
 
-	return rc;
+	return 0;
 }
 
 static int rtl8169_set_link_ksettings(struct net_device *dev,
@@ -4395,7 +4298,7 @@ static void rtl_phy_work(struct rtl8169_private *tp)
 	struct timer_list *timer = &tp->timer;
 	unsigned long timeout = RTL8169_PHY_TIMEOUT;
 
-	if (tp->phy_reset_pending(tp)) {
+	if (rtl8169_xmii_reset_pending(tp)) {
 		/*
 		 * A busy loop could burn quite a few cycles on nowadays CPU.
 		 * Let's delay the execution of the timer for a few ticks.
@@ -4404,12 +4307,12 @@ static void rtl_phy_work(struct rtl8169_private *tp)
 		goto out_mod_timer;
 	}
 
-	if (tp->link_ok(tp))
+	if (rtl8169_xmii_link_ok(tp))
 		return;
 
 	netif_dbg(tp, link, tp->dev, "PHY reset until link up\n");
 
-	tp->phy_reset_enable(tp);
+	rtl8169_xmii_reset_enable(tp);
 
 out_mod_timer:
 	mod_timer(timer, jiffies + timeout);
@@ -4430,20 +4333,20 @@ static void rtl8169_phy_timer(struct timer_list *t)
 
 DECLARE_RTL_COND(rtl_phy_reset_cond)
 {
-	return tp->phy_reset_pending(tp);
+	return rtl8169_xmii_reset_pending(tp);
 }
 
 static void rtl8169_phy_reset(struct net_device *dev,
 			      struct rtl8169_private *tp)
 {
-	tp->phy_reset_enable(tp);
+	rtl8169_xmii_reset_enable(tp);
 	rtl_msleep_loop_wait_low(tp, &rtl_phy_reset_cond, 1, 100);
 }
 
 static bool rtl_tbi_enabled(struct rtl8169_private *tp)
 {
 	return (tp->mac_version == RTL_GIGA_MAC_VER_01) &&
-	    (RTL_R8(tp, PHYstatus) & TBI_Enable);
+	       (RTL_R8(tp, PHYstatus) & TBI_Enable);
 }
 
 static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
@@ -4478,9 +4381,6 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 			  (tp->mii.supports_gmii ?
 			   ADVERTISED_1000baseT_Half |
 			   ADVERTISED_1000baseT_Full : 0));
-
-	if (rtl_tbi_enabled(tp))
-		netif_info(tp, link, dev, "TBI auto-negotiating\n");
 }
 
 static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
@@ -4523,14 +4423,6 @@ static int rtl_set_mac_address(struct net_device *dev, void *p)
 	return 0;
 }
 
-static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	struct mii_ioctl_data *data = if_mii(ifr);
-
-	return netif_running(dev) ? tp->do_ioctl(tp, data, cmd) : -ENODEV;
-}
-
 static int rtl_xmii_ioctl(struct rtl8169_private *tp,
 			  struct mii_ioctl_data *data, int cmd)
 {
@@ -4550,9 +4442,12 @@ static int rtl_xmii_ioctl(struct rtl8169_private *tp,
 	return -EOPNOTSUPP;
 }
 
-static int rtl_tbi_ioctl(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd)
+static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	return -EOPNOTSUPP;
+	struct rtl8169_private *tp = netdev_priv(dev);
+	struct mii_ioctl_data *data = if_mii(ifr);
+
+	return netif_running(dev) ? rtl_xmii_ioctl(tp, data, cmd) : -ENODEV;
 }
 
 static void rtl_init_mdio_ops(struct rtl8169_private *tp)
@@ -7676,6 +7571,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Identify chip attached to board */
 	rtl8169_get_mac_version(tp, cfg->default_ver);
 
+	if (rtl_tbi_enabled(tp)) {
+		dev_err(&pdev->dev, "TBI fiber mode not supported\n");
+		return -ENODEV;
+	}
+
 	tp->cp_cmd = RTL_R16(tp, CPlusCmd);
 
 	if ((sizeof(dma_addr_t) > 4) &&
@@ -7724,22 +7624,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* override BIOS settings, use userspace tools to enable WOL */
 	__rtl8169_set_wol(tp, 0);
 
-	if (rtl_tbi_enabled(tp)) {
-		tp->set_speed = rtl8169_set_speed_tbi;
-		tp->get_link_ksettings = rtl8169_get_link_ksettings_tbi;
-		tp->phy_reset_enable = rtl8169_tbi_reset_enable;
-		tp->phy_reset_pending = rtl8169_tbi_reset_pending;
-		tp->link_ok = rtl8169_tbi_link_ok;
-		tp->do_ioctl = rtl_tbi_ioctl;
-	} else {
-		tp->set_speed = rtl8169_set_speed_xmii;
-		tp->get_link_ksettings = rtl8169_get_link_ksettings_xmii;
-		tp->phy_reset_enable = rtl8169_xmii_reset_enable;
-		tp->phy_reset_pending = rtl8169_xmii_reset_pending;
-		tp->link_ok = rtl8169_xmii_link_ok;
-		tp->do_ioctl = rtl_xmii_ioctl;
-	}
-
 	mutex_init(&tp->wk.mutex);
 	u64_stats_init(&tp->rx_stats.syncp);
 	u64_stats_init(&tp->tx_stats.syncp);
-- 
cgit v1.2.3


From 6a939f365bdb03a74b4617bdb4402fc08da088b9 Mon Sep 17 00:00:00 2001
From: GhantaKrishnamurthy MohanKrishna
 <mohan.krishna.ghanta.krishnamurthy@ericsson.com>
Date: Fri, 29 Jun 2018 13:23:41 +0200
Subject: tipc: Auto removal of peer down node instance

A peer node is considered down if there are no
active links (or) lost contact to the node. In current implementation,
a peer node instance is deleted either if

a) TIPC module is removed (or)
b) Application can use a netlink/iproute2 interface to delete a
specific down node.

Thus, a down node instance lives in the system forever, unless the
application explicitly removes it.

We fix this by deleting the nodes which are down for
a specified amount of time (5 minutes).
Existing node supervision timer is used to achieve this.

Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: GhantaKrishnamurthy MohanKrishna <mohan.krishna.ghanta.krishnamurthy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 55 insertions(+), 11 deletions(-)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 8972ca1c654c..cfdbaf479fd1 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -45,6 +45,7 @@
 #include "netlink.h"
 
 #define INVALID_NODE_SIG	0x10000
+#define NODE_CLEANUP_AFTER	300000
 
 /* Flags used to take different actions according to flag type
  * TIPC_NOTIFY_NODE_DOWN: notify node is down
@@ -96,6 +97,7 @@ struct tipc_bclink_entry {
  * @link_id: local and remote bearer ids of changing link, if any
  * @publ_list: list of publications
  * @rcu: rcu struct for tipc_node
+ * @delete_at: indicates the time for deleting a down node
  */
 struct tipc_node {
 	u32 addr;
@@ -121,6 +123,7 @@ struct tipc_node {
 	unsigned long keepalive_intv;
 	struct timer_list timer;
 	struct rcu_head rcu;
+	unsigned long delete_at;
 };
 
 /* Node FSM states and events:
@@ -160,6 +163,7 @@ static struct tipc_node *tipc_node_find(struct net *net, u32 addr);
 static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id);
 static void tipc_node_put(struct tipc_node *node);
 static bool node_is_up(struct tipc_node *n);
+static void tipc_node_delete_from_list(struct tipc_node *node);
 
 struct tipc_sock_conn {
 	u32 port;
@@ -390,6 +394,7 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
 	for (i = 0; i < MAX_BEARERS; i++)
 		spin_lock_init(&n->links[i].lock);
 	n->state = SELF_DOWN_PEER_LEAVING;
+	n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
 	n->signature = INVALID_NODE_SIG;
 	n->active_links[0] = INVALID_BEARER_ID;
 	n->active_links[1] = INVALID_BEARER_ID;
@@ -433,11 +438,16 @@ static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l)
 	tipc_link_set_abort_limit(l, tol / n->keepalive_intv);
 }
 
-static void tipc_node_delete(struct tipc_node *node)
+static void tipc_node_delete_from_list(struct tipc_node *node)
 {
 	list_del_rcu(&node->list);
 	hlist_del_rcu(&node->hash);
 	tipc_node_put(node);
+}
+
+static void tipc_node_delete(struct tipc_node *node)
+{
+	tipc_node_delete_from_list(node);
 
 	del_timer_sync(&node->timer);
 	tipc_node_put(node);
@@ -544,6 +554,42 @@ void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
 	tipc_node_put(node);
 }
 
+static void  tipc_node_clear_links(struct tipc_node *node)
+{
+	int i;
+
+	for (i = 0; i < MAX_BEARERS; i++) {
+		struct tipc_link_entry *le = &node->links[i];
+
+		if (le->link) {
+			kfree(le->link);
+			le->link = NULL;
+			node->link_cnt--;
+		}
+	}
+}
+
+/* tipc_node_cleanup - delete nodes that does not
+ * have active links for NODE_CLEANUP_AFTER time
+ */
+static int tipc_node_cleanup(struct tipc_node *peer)
+{
+	struct tipc_net *tn = tipc_net(peer->net);
+	bool deleted = false;
+
+	spin_lock_bh(&tn->node_list_lock);
+	tipc_node_write_lock(peer);
+
+	if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {
+		tipc_node_clear_links(peer);
+		tipc_node_delete_from_list(peer);
+		deleted = true;
+	}
+	tipc_node_write_unlock(peer);
+	spin_unlock_bh(&tn->node_list_lock);
+	return deleted;
+}
+
 /* tipc_node_timeout - handle expiration of node timer
  */
 static void tipc_node_timeout(struct timer_list *t)
@@ -555,6 +601,12 @@ static void tipc_node_timeout(struct timer_list *t)
 	int bearer_id;
 	int rc = 0;
 
+	if (!node_is_up(n) && tipc_node_cleanup(n)) {
+		/*Removing the reference of Timer*/
+		tipc_node_put(n);
+		return;
+	}
+
 	__skb_queue_head_init(&xmitq);
 
 	for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) {
@@ -1173,6 +1225,7 @@ static void node_lost_contact(struct tipc_node *n,
 	uint i;
 
 	pr_debug("Lost contact with %x\n", n->addr);
+	n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
 
 	/* Clean up broadcast state */
 	tipc_bcast_remove_peer(n->net, n->bc_entry.link);
@@ -1742,7 +1795,6 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 	struct tipc_node *peer;
 	u32 addr;
 	int err;
-	int i;
 
 	/* We identify the peer by its net */
 	if (!info->attrs[TIPC_NLA_NET])
@@ -1777,15 +1829,7 @@ int tipc_nl_peer_rm(struct sk_buff *skb, struct genl_info *info)
 		goto err_out;
 	}
 
-	for (i = 0; i < MAX_BEARERS; i++) {
-		struct tipc_link_entry *le = &peer->links[i];
-
-		if (le->link) {
-			kfree(le->link);
-			le->link = NULL;
-			peer->link_cnt--;
-		}
-	}
+	tipc_node_clear_links(peer);
 	tipc_node_write_unlock(peer);
 	tipc_node_delete(peer);
 
-- 
cgit v1.2.3


From a1be5a20f137bdf436bab86c18998229908ce951 Mon Sep 17 00:00:00 2001
From: GhantaKrishnamurthy MohanKrishna
 <mohan.krishna.ghanta.krishnamurthy@ericsson.com>
Date: Fri, 29 Jun 2018 13:26:18 +0200
Subject: tipc: extend sock diag for group communication

This commit extends the existing TIPC socket diagnostics framework
for information related to TIPC group communication.

Acked-by: Ying Xue <ying.xue@windriver.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: GhantaKrishnamurthy MohanKrishna <mohan.krishna.ghanta.krishnamurthy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tipc_netlink.h | 14 ++++++++++++++
 net/tipc/group.c                  | 32 ++++++++++++++++++++++++++++++++
 net/tipc/group.h                  |  1 +
 net/tipc/socket.c                 |  5 +++++
 4 files changed, 52 insertions(+)

diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h
index 85c11982c89b..0ebe02ef1a86 100644
--- a/include/uapi/linux/tipc_netlink.h
+++ b/include/uapi/linux/tipc_netlink.h
@@ -121,6 +121,7 @@ enum {
 	TIPC_NLA_SOCK_TIPC_STATE,	/* u32 */
 	TIPC_NLA_SOCK_COOKIE,		/* u64 */
 	TIPC_NLA_SOCK_PAD,		/* flag */
+	TIPC_NLA_SOCK_GROUP,		/* nest */
 
 	__TIPC_NLA_SOCK_MAX,
 	TIPC_NLA_SOCK_MAX = __TIPC_NLA_SOCK_MAX - 1
@@ -233,6 +234,19 @@ enum {
 	TIPC_NLA_MON_PEER_MAX = __TIPC_NLA_MON_PEER_MAX - 1
 };
 
+/* Nest, socket group info */
+enum {
+	TIPC_NLA_SOCK_GROUP_ID,			/* u32 */
+	TIPC_NLA_SOCK_GROUP_OPEN,		/* flag */
+	TIPC_NLA_SOCK_GROUP_NODE_SCOPE,		/* flag */
+	TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE,	/* flag */
+	TIPC_NLA_SOCK_GROUP_INSTANCE,		/* u32 */
+	TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT,	/* u32 */
+
+	__TIPC_NLA_SOCK_GROUP_MAX,
+	TIPC_NLA_SOCK_GROUP_MAX = __TIPC_NLA_SOCK_GROUP_MAX - 1
+};
+
 /* Nest, connection info */
 enum {
 	TIPC_NLA_CON_UNSPEC,
diff --git a/net/tipc/group.c b/net/tipc/group.c
index d7a7befeddd4..cbe39e8db39c 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -918,3 +918,35 @@ void tipc_group_member_evt(struct tipc_group *grp,
 	}
 	*sk_rcvbuf = tipc_group_rcvbuf_limit(grp);
 }
+
+int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb)
+{
+	struct nlattr *group = nla_nest_start(skb, TIPC_NLA_SOCK_GROUP);
+
+	if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID,
+			grp->type) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE,
+			grp->instance) ||
+	    nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT,
+			grp->bc_snd_nxt))
+		goto group_msg_cancel;
+
+	if (grp->scope == TIPC_NODE_SCOPE)
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE))
+			goto group_msg_cancel;
+
+	if (grp->scope == TIPC_CLUSTER_SCOPE)
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE))
+			goto group_msg_cancel;
+
+	if (*grp->open)
+		if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN))
+			goto group_msg_cancel;
+
+	nla_nest_end(skb, group);
+	return 0;
+
+group_msg_cancel:
+	nla_nest_cancel(skb, group);
+	return -1;
+}
diff --git a/net/tipc/group.h b/net/tipc/group.h
index 5996af6e9f1d..76b4e5a7b39d 100644
--- a/net/tipc/group.h
+++ b/net/tipc/group.h
@@ -72,4 +72,5 @@ void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node,
 			       u32 port, struct sk_buff_head *xmitq);
 u16 tipc_group_bc_snd_nxt(struct tipc_group *grp);
 void tipc_group_update_member(struct tipc_member *m, int len);
+int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb);
 #endif
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 14a5d055717d..840dd995f631 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -3316,6 +3316,11 @@ int tipc_sk_fill_sock_diag(struct sk_buff *skb, struct netlink_callback *cb,
 		goto stat_msg_cancel;
 
 	nla_nest_end(skb, stat);
+
+	if (tsk->group)
+		if (tipc_group_fill_sock_diag(tsk->group, skb))
+			goto stat_msg_cancel;
+
 	nla_nest_end(skb, attrs);
 
 	return 0;
-- 
cgit v1.2.3


From 180390c470e1b6e3e19b4f969524182eeb5e4e6c Mon Sep 17 00:00:00 2001
From: Keara Leibovitz <kleib@mojatatu.com>
Date: Fri, 29 Jun 2018 10:47:31 -0400
Subject: tc-testing: initial version of tunnel_key unit tests

Create unittests for the tc tunnel_key action.

v2:
For the tests expecting failures, added non-zero exit codes in the
teardowns. This prevents those tests from failing if the act_tunnel_key
module is unloaded.

Signed-off-by: Keara Leibovitz <kleib@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/tunnel_key.json    | 749 +++++++++++++++++++++
 1 file changed, 749 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
new file mode 100644
index 000000000000..d878ce1c7d08
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
@@ -0,0 +1,749 @@
+[
+    {
+        "id": "2b11",
+        "name": "Add tunnel_key set action with mandatory parameters",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "dc6b",
+        "name": "Add tunnel_key set action with missing mandatory src_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set dst_ip 20.20.20.2 id 100",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*dst_ip 20.20.20.2.*key_id 100",
+        "matchCount": "0",
+        "teardown": [
+	    [
+		"$TC actions flush action tunnel_key",
+		0,
+		1,
+		255
+	    ]
+        ]
+    },
+    {
+        "id": "7f25",
+        "name": "Add tunnel_key set action with missing mandatory dst_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 id 100",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*key_id 100",
+        "matchCount": "0",
+        "teardown": [
+	    [
+		"$TC actions flush action tunnel_key",
+		0,
+		1,
+		255
+	    ]
+        ]
+    },
+    {
+        "id": "ba4e",
+        "name": "Add tunnel_key set action with missing mandatory id parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2",
+        "matchCount": "0",
+        "teardown": [
+	    [
+		"$TC actions flush action tunnel_key",
+		0,
+		1,
+		255
+	    ]
+        ]
+    },
+    {
+        "id": "a5e0",
+        "name": "Add tunnel_key set action with invalid src_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 300.168.100.1 dst_ip 192.168.200.1 id 7 index 1",
+        "expExitCode": "1",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 300.168.100.1.*dst_ip 192.168.200.1.*key_id 7.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+	    [
+		"$TC actions flush action tunnel_key",
+		0,
+		1,
+		255
+	    ]
+        ]
+    },
+    {
+        "id": "eaa8",
+        "name": "Add tunnel_key set action with invalid dst_ip parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.800.1 id 10 index 11",
+        "expExitCode": "1",
+        "verifyCmd": "$TC actions get action tunnel_key index 11",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 192.168.100.1.*dst_ip 192.168.800.1.*key_id 10.*index 11 ref",
+        "matchCount": "0",
+        "teardown": [
+	    [
+		"$TC actions flush action tunnel_key",
+		0,
+		1,
+		255
+	    ]
+        ]
+    },
+    {
+        "id": "3b09",
+        "name": "Add tunnel_key set action with invalid id parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 112233445566778899 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 112233445566778899.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+	    [
+		"$TC actions flush action tunnel_key",
+		0,
+		1,
+		255
+	    ]
+        ]
+    },
+    {
+        "id": "9625",
+        "name": "Add tunnel_key set action with invalid dst_port parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 dst_port 998877 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 11.*dst_port 998877.*index 1 ref",
+        "matchCount": "0",
+        "teardown": [
+	    [
+		"$TC actions flush action tunnel_key",
+		0,
+		1,
+		255
+	    ]
+        ]
+    },
+    {
+        "id": "05af",
+        "name": "Add tunnel_key set action with optional dst_port parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.100.1 dst_ip 192.168.200.1 id 789 dst_port 4000 index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 10",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.100.1.*dst_ip 192.168.200.1.*key_id 789.*dst_port 4000.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "da80",
+        "name": "Add tunnel_key set action with index at 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 4294967295",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*id 11.*index 4294967295 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "d407",
+        "name": "Add tunnel_key set action with index exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 11 index 4294967295678",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 4294967295678",
+        "matchPattern": "action order [0-9]+: tunnel_key set.*index 4294967295678 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "5cba",
+        "name": "Add tunnel_key set action with id value at 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 4294967295 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 4294967295.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "e84a",
+        "name": "Add tunnel_key set action with id value exceeding 32-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42949672955 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 4294967295",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42949672955.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+	]
+    },
+    {
+        "id": "9c19",
+        "name": "Add tunnel_key set action with dst_port value at 16-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "3bd9",
+        "name": "Add tunnel_key set action with dst_port value exceeding 16-bit maximum",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 429 dst_port 65535789 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 429.*dst_port 65535789.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+	]
+    },
+    {
+        "id": "68e2",
+        "name": "Add tunnel_key unset action",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key unset index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*unset.*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "6192",
+        "name": "Add tunnel_key unset continue action",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key unset continue index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*unset continue.*index 1 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "061d",
+        "name": "Add tunnel_key set continue action with cookie",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "8acb",
+        "name": "Add tunnel_key set continue action with invalid cookie",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 192.168.10.1 dst_ip 192.168.20.2 id 123 continue index 1 cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 192.168.10.1.*dst_ip 192.168.20.2.*key_id 123.*csum continue.*index 1.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+	]
+    },
+    {
+        "id": "a07e",
+        "name": "Add tunnel_key action with no set/unset command specified",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "b227",
+        "name": "Add tunnel_key action with csum option",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 id 1 csum index 99",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 99",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*csum pipe.*index 99",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "58a7",
+        "name": "Add tunnel_key action with nocsum option",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7823 nocsum index 234",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 234",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7823.*nocsum pipe.*index 234",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "2575",
+        "name": "Add tunnel_key action with not-supported parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 foobar 999 index 4",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 4",
+        "matchPattern": "action order [0-9]+: tunnel_key.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*foobar 999.*index 4",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "7a88",
+        "name": "Add tunnel_key action with cookie parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 10.10.10.2 id 7 index 4 cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 4",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 10.10.10.2.*key_id 7.*dst_port 0.*csum pipe.*index 4 ref.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "7afc",
+        "name": "Replace tunnel_key set action with all parameters",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 csum id 1 index 1"
+        ],
+        "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 nocsum id 11 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*nocsum pipe.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "364d",
+        "name": "Replace tunnel_key set action with all parameters and cookie",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 index 1 cookie aabbccddeeff112233445566778800a"
+        ],
+        "cmdUnderTest": "$TC actions replace action tunnel_key set src_ip 11.11.11.1 dst_ip 21.21.21.2 dst_port 3129 id 11 csum reclassify index 1 cookie a1b1c1d1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 11.11.11.1.*dst_ip 21.21.21.2.*key_id 11.*dst_port 3129.*csum reclassify.*index 1.*cookie a1b1c1d1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "937c",
+        "name": "Fetch all existing tunnel_key actions",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1",
+            "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 jump 10 index 2",
+            "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3",
+            "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4"
+        ],
+        "cmdUnderTest": "$TC actions list action tunnel_key",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 10.10.10.1.*dst_ip 20.20.20.2.*key_id 1.*dst_port 3128.*nocsum pipe.*index 1.*set.*src_ip 11.10.10.1.*dst_ip 21.20.20.2.*key_id 2.*dst_port 3129.*csum jump 10.*index 2.*set.*src_ip 12.10.10.1.*dst_ip 22.20.20.2.*key_id 3.*dst_port 3130.*csum pass.*index 3.*set.*src_ip 13.10.10.1.*dst_ip 23.20.20.2.*key_id 4.*dst_port 3131.*nocsum continue.*index 4",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "6783",
+        "name": "Flush all existing tunnel_key actions",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ],
+            "$TC actions add action tunnel_key set src_ip 10.10.10.1 dst_ip 20.20.20.2 dst_port 3128 nocsum id 1 pipe index 1",
+            "$TC actions add action tunnel_key set src_ip 11.10.10.1 dst_ip 21.20.20.2 dst_port 3129 csum id 2 reclassify index 2",
+            "$TC actions add action tunnel_key set src_ip 12.10.10.1 dst_ip 22.20.20.2 dst_port 3130 csum id 3 pass index 3",
+            "$TC actions add action tunnel_key set src_ip 13.10.10.1 dst_ip 23.20.20.2 dst_port 3131 nocsum id 4 continue index 4"
+        ],
+        "cmdUnderTest": "$TC actions flush action tunnel_key",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions list action tunnel_key",
+        "matchPattern": "action order [0-9]+:.*",
+        "matchCount": "0",
+        "teardown": [
+	    "$TC actions flush action tunnel_key"
+	]
+    }
+]
-- 
cgit v1.2.3


From 4e485d06bb8c7811a0d69a811c77befd54b9ab0c Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Sat, 30 Jun 2018 00:45:55 +0530
Subject: strparser: Call skb_unclone conditionally

Calling skb_unclone() is expensive as it triggers a memcpy operation.
Instead of calling skb_unclone() unconditionally, call it only when skb
has a shared frag_list. This improves tls rx throughout significantly.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Suggested-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 26 +++++++++++++++-----------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 373836615c57..4f40a90ca016 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -155,11 +155,13 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 			/* We are going to append to the frags_list of head.
 			 * Need to unshare the frag_list.
 			 */
-			err = skb_unclone(head, GFP_ATOMIC);
-			if (err) {
-				STRP_STATS_INCR(strp->stats.mem_fail);
-				desc->error = err;
-				return 0;
+			if (skb_has_frag_list(head)) {
+				err = skb_unclone(head, GFP_ATOMIC);
+				if (err) {
+					STRP_STATS_INCR(strp->stats.mem_fail);
+					desc->error = err;
+					return 0;
+				}
 			}
 
 			if (unlikely(skb_shinfo(head)->frag_list)) {
@@ -216,14 +218,16 @@ static int __strp_recv(read_descriptor_t *desc, struct sk_buff *orig_skb,
 			memset(stm, 0, sizeof(*stm));
 			stm->strp.offset = orig_offset + eaten;
 		} else {
-			/* Unclone since we may be appending to an skb that we
+			/* Unclone if we are appending to an skb that we
 			 * already share a frag_list with.
 			 */
-			err = skb_unclone(skb, GFP_ATOMIC);
-			if (err) {
-				STRP_STATS_INCR(strp->stats.mem_fail);
-				desc->error = err;
-				break;
+			if (skb_has_frag_list(skb)) {
+				err = skb_unclone(skb, GFP_ATOMIC);
+				if (err) {
+					STRP_STATS_INCR(strp->stats.mem_fail);
+					desc->error = err;
+					break;
+				}
 			}
 
 			stm = _strp_msg(head);
-- 
cgit v1.2.3


From f055a9dfee8508173a35169372bdedcfac49d0f6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 29 Jun 2018 17:04:34 -0700
Subject: nfp: expose ring stats of inactive rings via ethtool

After user changes the ring count statistics for deactivated
rings disappear from ethtool -S output.  This causes loss of
information to the user and means that ethtool stats may not
add up to interface stats.  Always expose counters from all
the rings.  Note that we allocate at most num_possible_cpus()
rings so number of rings should be reasonable.

The alternative of only listing stats for rings which were
ever in use could be confusing.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/netronome/nfp/nfp_net_ethtool.c   | 50 ++++++++--------------
 1 file changed, 19 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 26d1cc4e2906..2aeb4622f1ea 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -452,7 +452,7 @@ static unsigned int nfp_vnic_get_sw_stats_count(struct net_device *netdev)
 {
 	struct nfp_net *nn = netdev_priv(netdev);
 
-	return NN_RVEC_GATHER_STATS + nn->dp.num_r_vecs * NN_RVEC_PER_Q_STATS;
+	return NN_RVEC_GATHER_STATS + nn->max_r_vecs * NN_RVEC_PER_Q_STATS;
 }
 
 static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
@@ -460,7 +460,7 @@ static u8 *nfp_vnic_get_sw_stats_strings(struct net_device *netdev, u8 *data)
 	struct nfp_net *nn = netdev_priv(netdev);
 	int i;
 
-	for (i = 0; i < nn->dp.num_r_vecs; i++) {
+	for (i = 0; i < nn->max_r_vecs; i++) {
 		data = nfp_pr_et(data, "rvec_%u_rx_pkts", i);
 		data = nfp_pr_et(data, "rvec_%u_tx_pkts", i);
 		data = nfp_pr_et(data, "rvec_%u_tx_busy", i);
@@ -486,7 +486,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 	u64 tmp[NN_RVEC_GATHER_STATS];
 	unsigned int i, j;
 
-	for (i = 0; i < nn->dp.num_r_vecs; i++) {
+	for (i = 0; i < nn->max_r_vecs; i++) {
 		unsigned int start;
 
 		do {
@@ -521,15 +521,13 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data)
 	return data;
 }
 
-static unsigned int
-nfp_vnic_get_hw_stats_count(unsigned int rx_rings, unsigned int tx_rings)
+static unsigned int nfp_vnic_get_hw_stats_count(unsigned int num_vecs)
 {
-	return NN_ET_GLOBAL_STATS_LEN + (rx_rings + tx_rings) * 2;
+	return NN_ET_GLOBAL_STATS_LEN + num_vecs * 4;
 }
 
 static u8 *
-nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings,
-			      unsigned int tx_rings, bool repr)
+nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int num_vecs, bool repr)
 {
 	int swap_off, i;
 
@@ -549,36 +547,29 @@ nfp_vnic_get_hw_stats_strings(u8 *data, unsigned int rx_rings,
 	for (i = NN_ET_SWITCH_STATS_LEN * 2; i < NN_ET_GLOBAL_STATS_LEN; i++)
 		data = nfp_pr_et(data, nfp_net_et_stats[i].name);
 
-	for (i = 0; i < tx_rings; i++) {
-		data = nfp_pr_et(data, "txq_%u_pkts", i);
-		data = nfp_pr_et(data, "txq_%u_bytes", i);
-	}
-
-	for (i = 0; i < rx_rings; i++) {
+	for (i = 0; i < num_vecs; i++) {
 		data = nfp_pr_et(data, "rxq_%u_pkts", i);
 		data = nfp_pr_et(data, "rxq_%u_bytes", i);
+		data = nfp_pr_et(data, "txq_%u_pkts", i);
+		data = nfp_pr_et(data, "txq_%u_bytes", i);
 	}
 
 	return data;
 }
 
 static u64 *
-nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem,
-		      unsigned int rx_rings, unsigned int tx_rings)
+nfp_vnic_get_hw_stats(u64 *data, u8 __iomem *mem, unsigned int num_vecs)
 {
 	unsigned int i;
 
 	for (i = 0; i < NN_ET_GLOBAL_STATS_LEN; i++)
 		*data++ = readq(mem + nfp_net_et_stats[i].off);
 
-	for (i = 0; i < tx_rings; i++) {
-		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i));
-		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8);
-	}
-
-	for (i = 0; i < rx_rings; i++) {
+	for (i = 0; i < num_vecs; i++) {
 		*data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i));
 		*data++ = readq(mem + NFP_NET_CFG_RXR_STATS(i) + 8);
+		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i));
+		*data++ = readq(mem + NFP_NET_CFG_TXR_STATS(i) + 8);
 	}
 
 	return data;
@@ -633,8 +624,7 @@ static void nfp_net_get_strings(struct net_device *netdev,
 	switch (stringset) {
 	case ETH_SS_STATS:
 		data = nfp_vnic_get_sw_stats_strings(netdev, data);
-		data = nfp_vnic_get_hw_stats_strings(data, nn->dp.num_rx_rings,
-						     nn->dp.num_tx_rings,
+		data = nfp_vnic_get_hw_stats_strings(data, nn->max_r_vecs,
 						     false);
 		data = nfp_mac_get_stats_strings(netdev, data);
 		data = nfp_app_port_get_stats_strings(nn->port, data);
@@ -649,8 +639,7 @@ nfp_net_get_stats(struct net_device *netdev, struct ethtool_stats *stats,
 	struct nfp_net *nn = netdev_priv(netdev);
 
 	data = nfp_vnic_get_sw_stats(netdev, data);
-	data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar,
-				     nn->dp.num_rx_rings, nn->dp.num_tx_rings);
+	data = nfp_vnic_get_hw_stats(data, nn->dp.ctrl_bar, nn->max_r_vecs);
 	data = nfp_mac_get_stats(netdev, data);
 	data = nfp_app_port_get_stats(nn->port, data);
 }
@@ -662,8 +651,7 @@ static int nfp_net_get_sset_count(struct net_device *netdev, int sset)
 	switch (sset) {
 	case ETH_SS_STATS:
 		return nfp_vnic_get_sw_stats_count(netdev) +
-		       nfp_vnic_get_hw_stats_count(nn->dp.num_rx_rings,
-						   nn->dp.num_tx_rings) +
+		       nfp_vnic_get_hw_stats_count(nn->max_r_vecs) +
 		       nfp_mac_get_stats_count(netdev) +
 		       nfp_app_port_get_stats_count(nn->port);
 	default:
@@ -679,7 +667,7 @@ static void nfp_port_get_strings(struct net_device *netdev,
 	switch (stringset) {
 	case ETH_SS_STATS:
 		if (nfp_port_is_vnic(port))
-			data = nfp_vnic_get_hw_stats_strings(data, 0, 0, true);
+			data = nfp_vnic_get_hw_stats_strings(data, 0, true);
 		else
 			data = nfp_mac_get_stats_strings(netdev, data);
 		data = nfp_app_port_get_stats_strings(port, data);
@@ -694,7 +682,7 @@ nfp_port_get_stats(struct net_device *netdev, struct ethtool_stats *stats,
 	struct nfp_port *port = nfp_port_from_netdev(netdev);
 
 	if (nfp_port_is_vnic(port))
-		data = nfp_vnic_get_hw_stats(data, port->vnic, 0, 0);
+		data = nfp_vnic_get_hw_stats(data, port->vnic, 0);
 	else
 		data = nfp_mac_get_stats(netdev, data);
 	data = nfp_app_port_get_stats(port, data);
@@ -708,7 +696,7 @@ static int nfp_port_get_sset_count(struct net_device *netdev, int sset)
 	switch (sset) {
 	case ETH_SS_STATS:
 		if (nfp_port_is_vnic(port))
-			count = nfp_vnic_get_hw_stats_count(0, 0);
+			count = nfp_vnic_get_hw_stats_count(0);
 		else
 			count = nfp_mac_get_stats_count(netdev);
 		count += nfp_app_port_get_stats_count(port);
-- 
cgit v1.2.3


From 18aa5b180f00a10c2f63944b4f0ab116bf8ea19b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 29 Jun 2018 17:04:35 -0700
Subject: nfp: fail probe if serial or interface id is missing

On some platforms with broken ACPI tables we may not have access
to the Serial Number PCIe capability.  This capability is crucial
for us for switchdev operation as we use serial number as switch ID,
and for communication with management FW where interface ID is used.

If we can't determine the Serial Number we have to fail device probe.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c  | 16 ++++++++++------
 .../net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h   |  4 ++--
 .../ethernet/netronome/nfp/nfpcore/nfp_cppcore.c   | 22 ++++++++++++++++------
 3 files changed, 28 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
index 749655c329b2..c8d0b1016a64 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c
@@ -1248,7 +1248,7 @@ static void nfp6000_free(struct nfp_cpp *cpp)
 	kfree(nfp);
 }
 
-static void nfp6000_read_serial(struct device *dev, u8 *serial)
+static int nfp6000_read_serial(struct device *dev, u8 *serial)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int pos;
@@ -1256,25 +1256,29 @@ static void nfp6000_read_serial(struct device *dev, u8 *serial)
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
 	if (!pos) {
-		memset(serial, 0, NFP_SERIAL_LEN);
-		return;
+		dev_err(dev, "can't find PCIe Serial Number Capability\n");
+		return -EINVAL;
 	}
 
 	pci_read_config_dword(pdev, pos + 4, &reg);
 	put_unaligned_be16(reg >> 16, serial + 4);
 	pci_read_config_dword(pdev, pos + 8, &reg);
 	put_unaligned_be32(reg, serial);
+
+	return 0;
 }
 
-static u16 nfp6000_get_interface(struct device *dev)
+static int nfp6000_get_interface(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int pos;
 	u32 reg;
 
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN);
-	if (!pos)
-		return NFP_CPP_INTERFACE(NFP_CPP_INTERFACE_TYPE_PCI, 0, 0xff);
+	if (!pos) {
+		dev_err(dev, "can't find PCIe Serial Number Capability\n");
+		return -EINVAL;
+	}
 
 	pci_read_config_dword(pdev, pos + 4, &reg);
 
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h
index b0da3d436850..c338d539fa96 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h
@@ -364,8 +364,8 @@ struct nfp_cpp_operations {
 	int (*init)(struct nfp_cpp *cpp);
 	void (*free)(struct nfp_cpp *cpp);
 
-	void (*read_serial)(struct device *dev, u8 *serial);
-	u16 (*get_interface)(struct device *dev);
+	int (*read_serial)(struct device *dev, u8 *serial);
+	int (*get_interface)(struct device *dev);
 
 	int (*area_init)(struct nfp_cpp_area *area,
 			 u32 dest, unsigned long long address,
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
index ef30597aa319..73de57a09800 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cppcore.c
@@ -1163,10 +1163,10 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 {
 	const u32 arm = NFP_CPP_ID(NFP_CPP_TARGET_ARM, NFP_CPP_ACTION_RW, 0);
 	struct nfp_cpp *cpp;
+	int ifc, err;
 	u32 mask[2];
 	u32 xpbaddr;
 	size_t tgt;
-	int err;
 
 	cpp = kzalloc(sizeof(*cpp), GFP_KERNEL);
 	if (!cpp) {
@@ -1176,9 +1176,19 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 
 	cpp->op = ops;
 	cpp->priv = priv;
-	cpp->interface = ops->get_interface(parent);
-	if (ops->read_serial)
-		ops->read_serial(parent, cpp->serial);
+
+	ifc = ops->get_interface(parent);
+	if (ifc < 0) {
+		err = ifc;
+		goto err_free_cpp;
+	}
+	cpp->interface = ifc;
+	if (ops->read_serial) {
+		err = ops->read_serial(parent, cpp->serial);
+		if (err)
+			goto err_free_cpp;
+	}
+
 	rwlock_init(&cpp->resource_lock);
 	init_waitqueue_head(&cpp->waitq);
 	lockdep_set_class(&cpp->resource_lock, &nfp_cpp_resource_lock_key);
@@ -1191,7 +1201,7 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 	err = device_register(&cpp->dev);
 	if (err < 0) {
 		put_device(&cpp->dev);
-		goto err_dev;
+		goto err_free_cpp;
 	}
 
 	dev_set_drvdata(&cpp->dev, cpp);
@@ -1238,7 +1248,7 @@ nfp_cpp_from_operations(const struct nfp_cpp_operations *ops,
 
 err_out:
 	device_unregister(&cpp->dev);
-err_dev:
+err_free_cpp:
 	kfree(cpp);
 err_malloc:
 	return ERR_PTR(err);
-- 
cgit v1.2.3


From 670b5274ff976a7eed57fd303460a8a9de267c0e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 29 Jun 2018 17:04:36 -0700
Subject: nfp: implement netpoll ndo (thus enabling netconsole)

NFP NAPI handling will only complete the TXed packets when called
with budget of 0, implement ndo_poll_controller by scheduling NAPI
on all TX queues.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index d4c27f849f9b..edc6ef682f6d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3115,6 +3115,21 @@ nfp_net_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid)
 	return nfp_net_reconfig_mbox(nn, NFP_NET_CFG_MBOX_CMD_CTAG_FILTER_KILL);
 }
 
+#ifdef CONFIG_NET_POLL_CONTROLLER
+static void nfp_net_netpoll(struct net_device *netdev)
+{
+	struct nfp_net *nn = netdev_priv(netdev);
+	int i;
+
+	/* nfp_net's NAPIs are statically allocated so even if there is a race
+	 * with reconfig path this will simply try to schedule some disabled
+	 * NAPI instances.
+	 */
+	for (i = 0; i < nn->dp.num_stack_tx_rings; i++)
+		napi_schedule_irqoff(&nn->r_vecs[i].napi);
+}
+#endif
+
 static void nfp_net_stat64(struct net_device *netdev,
 			   struct rtnl_link_stats64 *stats)
 {
@@ -3482,6 +3497,9 @@ const struct net_device_ops nfp_net_netdev_ops = {
 	.ndo_get_stats64	= nfp_net_stat64,
 	.ndo_vlan_rx_add_vid	= nfp_net_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= nfp_net_vlan_rx_kill_vid,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller	= nfp_net_netpoll,
+#endif
 	.ndo_set_vf_mac         = nfp_app_set_vf_mac,
 	.ndo_set_vf_vlan        = nfp_app_set_vf_vlan,
 	.ndo_set_vf_spoofchk    = nfp_app_set_vf_spoofchk,
-- 
cgit v1.2.3


From d387b8a19a3921e291ebeb26b55495479cd36b21 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 29 Jun 2018 17:04:37 -0700
Subject: nfp: make use of napi_consume_skb()

Use napi_consume_skb() in nfp_net_tx_complete() to get bulk free.
Pass 0 as budget for ctrl queue completion since it runs out of
a tasklet.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index edc6ef682f6d..7df5ca37bfb8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -945,11 +945,12 @@ err_free:
 
 /**
  * nfp_net_tx_complete() - Handled completed TX packets
- * @tx_ring:   TX ring structure
+ * @tx_ring:	TX ring structure
+ * @budget:	NAPI budget (only used as bool to determine if in NAPI context)
  *
  * Return: Number of completed TX descriptors
  */
-static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
+static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
@@ -999,7 +1000,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring)
 
 		/* check for last gather fragment */
 		if (fidx == nr_frags - 1)
-			dev_consume_skb_any(skb);
+			napi_consume_skb(skb, budget);
 
 		tx_ring->txbufs[idx].dma_addr = 0;
 		tx_ring->txbufs[idx].skb = NULL;
@@ -1828,7 +1829,7 @@ static int nfp_net_poll(struct napi_struct *napi, int budget)
 	unsigned int pkts_polled = 0;
 
 	if (r_vec->tx_ring)
-		nfp_net_tx_complete(r_vec->tx_ring);
+		nfp_net_tx_complete(r_vec->tx_ring, budget);
 	if (r_vec->rx_ring)
 		pkts_polled = nfp_net_rx(r_vec->rx_ring, budget);
 
@@ -2062,7 +2063,7 @@ static void nfp_ctrl_poll(unsigned long arg)
 	struct nfp_net_r_vector *r_vec = (void *)arg;
 
 	spin_lock_bh(&r_vec->lock);
-	nfp_net_tx_complete(r_vec->tx_ring);
+	nfp_net_tx_complete(r_vec->tx_ring, 0);
 	__nfp_ctrl_tx_queued(r_vec);
 	spin_unlock_bh(&r_vec->lock);
 
-- 
cgit v1.2.3


From 5d4b0b4068f1dc637d8a9b53c2960bbad8ce654d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 29 Jun 2018 17:04:38 -0700
Subject: nfp: populate bus-info on representors

We used to leave bus-info in ethtool driver info empty for
representors in case multi-PCIe-to-single-host cards make
the association between PCIe device and NFP many to one.
It seems these attempts are futile, we need to link the
representors to one PCIe device in sysfs to get consistent
naming, plus devlink uses one PCIe as a handle, anyway.
The multi-PCIe-to-single-system support won't be clean,
if it ever comes.

Turns out some user space (RHEL tests) likes to read bus-info
so just populate it.

While at it remove unnecessary app NULL-check, representors
are spawned by an app, so it must exist.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
index 2aeb4622f1ea..6a79c8e4a7a4 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c
@@ -233,12 +233,10 @@ nfp_net_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 static void
 nfp_app_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo)
 {
-	struct nfp_app *app;
-
-	app = nfp_app_from_netdev(netdev);
-	if (!app)
-		return;
+	struct nfp_app *app = nfp_app_from_netdev(netdev);
 
+	strlcpy(drvinfo->bus_info, pci_name(app->pdev),
+		sizeof(drvinfo->bus_info));
 	nfp_get_drvinfo(app, app->pdev, "*", drvinfo);
 }
 
-- 
cgit v1.2.3


From ed8f2b52b622bbc550dadb69d3f10d81528f9fbc Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Fri, 29 Jun 2018 17:04:39 -0700
Subject: nfp: flower: ignore checksum actions when performing pedit actions

Hardware will automatically update csum in headers when a set action has
been performed. This means we could in the driver ignore the explicit
checksum action when performing a set action.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 80 +++++++++++++++++++---
 1 file changed, 72 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 4a6d2db75071..61ba8d4f99f1 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -34,6 +34,7 @@
 #include <linux/bitfield.h>
 #include <net/pkt_cls.h>
 #include <net/switchdev.h>
+#include <net/tc_act/tc_csum.h>
 #include <net/tc_act/tc_gact.h>
 #include <net/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_pedit.h>
@@ -398,8 +399,27 @@ nfp_fl_set_tport(const struct tc_action *action, int idx, u32 off,
 	return 0;
 }
 
+static u32 nfp_fl_csum_l4_to_flag(u8 ip_proto)
+{
+	switch (ip_proto) {
+	case 0:
+		/* Filter doesn't force proto match,
+		 * both TCP and UDP will be updated if encountered
+		 */
+		return TCA_CSUM_UPDATE_FLAG_TCP | TCA_CSUM_UPDATE_FLAG_UDP;
+	case IPPROTO_TCP:
+		return TCA_CSUM_UPDATE_FLAG_TCP;
+	case IPPROTO_UDP:
+		return TCA_CSUM_UPDATE_FLAG_UDP;
+	default:
+		/* All other protocols will be ignored by FW */
+		return 0;
+	}
+}
+
 static int
-nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
+nfp_fl_pedit(const struct tc_action *action, struct tc_cls_flower_offload *flow,
+	     char *nfp_action, int *a_len, u32 *csum_updated)
 {
 	struct nfp_fl_set_ipv6_addr set_ip6_dst, set_ip6_src;
 	struct nfp_fl_set_ip4_addrs set_ip_addr;
@@ -409,6 +429,7 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 	int idx, nkeys, err;
 	size_t act_size;
 	u32 offset, cmd;
+	u8 ip_proto = 0;
 
 	memset(&set_ip6_dst, 0, sizeof(set_ip6_dst));
 	memset(&set_ip6_src, 0, sizeof(set_ip6_src));
@@ -451,6 +472,15 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 			return err;
 	}
 
+	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *basic;
+
+		basic = skb_flow_dissector_target(flow->dissector,
+						  FLOW_DISSECTOR_KEY_BASIC,
+						  flow->key);
+		ip_proto = basic->ip_proto;
+	}
+
 	if (set_eth.head.len_lw) {
 		act_size = sizeof(set_eth);
 		memcpy(nfp_action, &set_eth, act_size);
@@ -459,6 +489,10 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 		act_size = sizeof(set_ip_addr);
 		memcpy(nfp_action, &set_ip_addr, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix IPv4 and TCP/UDP checksum. */
+		*csum_updated |= TCA_CSUM_UPDATE_FLAG_IPV4HDR |
+				nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_ip6_dst.head.len_lw && set_ip6_src.head.len_lw) {
 		/* TC compiles set src and dst IPv6 address as a single action,
 		 * the hardware requires this to be 2 separate actions.
@@ -471,18 +505,30 @@ nfp_fl_pedit(const struct tc_action *action, char *nfp_action, int *a_len)
 		memcpy(&nfp_action[sizeof(set_ip6_src)], &set_ip6_dst,
 		       act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_ip6_dst.head.len_lw) {
 		act_size = sizeof(set_ip6_dst);
 		memcpy(nfp_action, &set_ip6_dst, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_ip6_src.head.len_lw) {
 		act_size = sizeof(set_ip6_src);
 		memcpy(nfp_action, &set_ip6_src, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	} else if (set_tport.head.len_lw) {
 		act_size = sizeof(set_tport);
 		memcpy(nfp_action, &set_tport, act_size);
 		*a_len += act_size;
+
+		/* Hardware will automatically fix TCP/UDP checksum. */
+		*csum_updated |= nfp_fl_csum_l4_to_flag(ip_proto);
 	}
 
 	return 0;
@@ -493,12 +539,18 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 			 struct nfp_fl_payload *nfp_fl, int *a_len,
 			 struct net_device *netdev, bool last,
 			 enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
-			 int *out_cnt)
+			 int *out_cnt, u32 *csum_updated)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct nfp_fl_output *output;
 	int err, prelag_size;
 
+	/* If csum_updated has not been reset by now, it means HW will
+	 * incorrectly update csums when they are not requested.
+	 */
+	if (*csum_updated)
+		return -EOPNOTSUPP;
+
 	if (*a_len + sizeof(struct nfp_fl_output) > NFP_FL_MAX_A_SIZ)
 		return -EOPNOTSUPP;
 
@@ -529,10 +581,11 @@ nfp_flower_output_action(struct nfp_app *app, const struct tc_action *a,
 
 static int
 nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
+		       struct tc_cls_flower_offload *flow,
 		       struct nfp_fl_payload *nfp_fl, int *a_len,
 		       struct net_device *netdev,
 		       enum nfp_flower_tun_type *tun_type, int *tun_out_cnt,
-		       int *out_cnt)
+		       int *out_cnt, u32 *csum_updated)
 {
 	struct nfp_fl_set_ipv4_udp_tun *set_tun;
 	struct nfp_fl_pre_tunnel *pre_tun;
@@ -545,14 +598,14 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 	} else if (is_tcf_mirred_egress_redirect(a)) {
 		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
 					       true, tun_type, tun_out_cnt,
-					       out_cnt);
+					       out_cnt, csum_updated);
 		if (err)
 			return err;
 
 	} else if (is_tcf_mirred_egress_mirror(a)) {
 		err = nfp_flower_output_action(app, a, nfp_fl, a_len, netdev,
 					       false, tun_type, tun_out_cnt,
-					       out_cnt);
+					       out_cnt, csum_updated);
 		if (err)
 			return err;
 
@@ -602,8 +655,17 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 		/* Tunnel decap is handled by default so accept action. */
 		return 0;
 	} else if (is_tcf_pedit(a)) {
-		if (nfp_fl_pedit(a, &nfp_fl->action_data[*a_len], a_len))
+		if (nfp_fl_pedit(a, flow, &nfp_fl->action_data[*a_len],
+				 a_len, csum_updated))
 			return -EOPNOTSUPP;
+	} else if (is_tcf_csum(a)) {
+		/* csum action requests recalc of something we have not fixed */
+		if (tcf_csum_update_flags(a) & ~*csum_updated)
+			return -EOPNOTSUPP;
+		/* If we will correctly fix the csum we can remove it from the
+		 * csum update list. Which will later be used to check support.
+		 */
+		*csum_updated &= ~tcf_csum_update_flags(a);
 	} else {
 		/* Currently we do not handle any other actions. */
 		return -EOPNOTSUPP;
@@ -620,6 +682,7 @@ int nfp_flower_compile_action(struct nfp_app *app,
 	int act_len, act_cnt, err, tun_out_cnt, out_cnt;
 	enum nfp_flower_tun_type tun_type;
 	const struct tc_action *a;
+	u32 csum_updated = 0;
 	LIST_HEAD(actions);
 
 	memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ);
@@ -632,8 +695,9 @@ int nfp_flower_compile_action(struct nfp_app *app,
 
 	tcf_exts_to_list(flow->exts, &actions);
 	list_for_each_entry(a, &actions, list) {
-		err = nfp_flower_loop_action(app, a, nfp_flow, &act_len, netdev,
-					     &tun_type, &tun_out_cnt, &out_cnt);
+		err = nfp_flower_loop_action(app, a, flow, nfp_flow, &act_len,
+					     netdev, &tun_type, &tun_out_cnt,
+					     &out_cnt, &csum_updated);
 		if (err)
 			return err;
 		act_cnt++;
-- 
cgit v1.2.3


From ed21b637e940e7680fc52eb10a5d9ee74715cd38 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 29 Jun 2018 17:04:40 -0700
Subject: nfp: flower: extract ipv4 udp tunnel ttl from route

Previously the ttl for ipv4 udp tunnels was set to the namespace default.
Modify this to attempt to extract the ttl from a full route lookup on the
tunnel destination. If this is not possible then resort to the default.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 61ba8d4f99f1..d421b7fbce96 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -236,9 +236,12 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
 	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
 	u32 tmp_set_ip_tun_type_index = 0;
+	struct flowi4 flow = {};
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
+	struct rtable *rt;
 	struct net *net;
+	int err;
 
 	if (ip_tun->options_len)
 		return -EOPNOTSUPP;
@@ -255,7 +258,21 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 
 	set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
 	set_tun->tun_id = ip_tun->key.tun_id;
-	set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+
+	/* Do a route lookup to determine ttl - if fails then use default.
+	 * Note that CONFIG_INET is a requirement of CONFIG_NET_SWITCHDEV so
+	 * must be defined here.
+	 */
+	flow.daddr = ip_tun->key.u.ipv4.dst;
+	flow.flowi4_proto = IPPROTO_UDP;
+	rt = ip_route_output_key(net, &flow);
+	err = PTR_ERR_OR_ZERO(rt);
+	if (!err) {
+		set_tun->ttl = ip4_dst_hoplimit(&rt->dst);
+		ip_rt_put(rt);
+	} else {
+		set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+	}
 
 	/* Complete pre_tunnel action. */
 	pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
-- 
cgit v1.2.3


From 51a8cefc6e3d8dd4bb18918b07faa5715f877aa6 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 29 Jun 2018 17:04:41 -0700
Subject: nfp: flower: offload tos and tunnel flags for ipv4 udp tunnels

Extract the tos and the tunnel flags from the tunnel key and offload these
action fields. Only the checksum and tunnel key flags are implemented in
fw so reject offloads of other flags. The tunnel key flag is always
considered set in the fw so enforce that it is set in the rule. Note that
the compulsory setting of the tunnel key flag and optional setting of
checksum is inline with how tc currently generates ipv4 udp tunnel
actions.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 9 +++++++++
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   | 4 ++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index d421b7fbce96..e56b815a8dc6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -45,6 +45,8 @@
 #include "main.h"
 #include "../nfp_net_repr.h"
 
+#define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS	(TUNNEL_CSUM | TUNNEL_KEY)
+
 static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan)
 {
 	size_t act_size = sizeof(struct nfp_fl_pop_vlan);
@@ -274,6 +276,13 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 		set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
 	}
 
+	set_tun->tos = ip_tun->key.tos;
+
+	if (!(ip_tun->key.tun_flags & TUNNEL_KEY) ||
+	    ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS)
+		return -EOPNOTSUPP;
+	set_tun->tun_flags = ip_tun->key.tun_flags;
+
 	/* Complete pre_tunnel action. */
 	pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 4a7f3510a296..15f1eacd76b6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -203,9 +203,9 @@ struct nfp_fl_set_ipv4_udp_tun {
 	__be16 reserved;
 	__be64 tun_id __packed;
 	__be32 tun_type_index;
-	__be16 reserved2;
+	__be16 tun_flags;
 	u8 ttl;
-	u8 reserved3;
+	u8 tos;
 	__be32 extra[2];
 };
 
-- 
cgit v1.2.3


From 635cf43dbddd166cd702c7883c837b9a3ace4565 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Fri, 29 Jun 2018 17:04:42 -0700
Subject: nfp: flower: enabled offloading of Team LAG

Currently the NFP fw only supports L3/L4 hashing so rejects the offload of
filters that output to LAG ports implementing other hash algorithms. Team,
however, uses a BPF function for the hash that is not defined. To support
Team offload, accept hashes that are defined as 'unknown' (only Team
defines such hash types). In this case, use the NFP default of L3/L4
hashing for egress port selection.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/lag_conf.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
index 0c4c957717ea..bf10598f66ae 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/lag_conf.c
@@ -564,8 +564,9 @@ nfp_fl_lag_changeupper_event(struct nfp_fl_lag *lag,
 	if (lag_upper_info &&
 	    lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_ACTIVEBACKUP &&
 	    (lag_upper_info->tx_type != NETDEV_LAG_TX_TYPE_HASH ||
-	    (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 &&
-	    lag_upper_info->hash_type != NETDEV_LAG_HASH_E34))) {
+	     (lag_upper_info->hash_type != NETDEV_LAG_HASH_L34 &&
+	      lag_upper_info->hash_type != NETDEV_LAG_HASH_E34 &&
+	      lag_upper_info->hash_type != NETDEV_LAG_HASH_UNKNOWN))) {
 		can_offload = false;
 		nfp_flower_cmsg_warn(priv->app,
 				     "Unable to offload tx_type %u hash %u\n",
-- 
cgit v1.2.3


From 87d8fb18cbe919342a1909a1e4168c9a63b9bbbf Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Sat, 30 Jun 2018 02:45:19 +0200
Subject: selftests: forwarding: Allow lib.sh sourcing from other directories

The devlink related scripts are mlxsw-specific. As a result, they'll
reside in a different directory - but would still need the common logic
implemented in lib.sh.
So as a preliminary step, allow lib.sh to be sourced from other
directories as well.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index d1f14f83979e..59272824ef37 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -14,8 +14,13 @@ PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no}
 NETIF_TYPE=${NETIF_TYPE:=veth}
 NETIF_CREATE=${NETIF_CREATE:=yes}
 
-if [[ -f forwarding.config ]]; then
-	source forwarding.config
+relative_path="${BASH_SOURCE%/*}"
+if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
+	relative_path="."
+fi
+
+if [[ -f $relative_path/forwarding.config ]]; then
+	source "$relative_path/forwarding.config"
 fi
 
 ##############################################################################
-- 
cgit v1.2.3


From 96fa91d281229390b75a004d49582400b5f93cb1 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:45:47 +0200
Subject: selftests: forwarding: lib: Add check_err_fail()

In the scale testing scenarios, one usually has a condition that is
expected to either fail, or pass, depending on which side of the scale
is being tested.

To capture this logic, add a function check_err_fail(), which dispatches
either to check_err() or check_fail(), depending on the value of the
first argument, should_fail.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 59272824ef37..5f4b7ed2c65a 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -156,6 +156,19 @@ check_fail()
 	fi
 }
 
+check_err_fail()
+{
+	local should_fail=$1; shift
+	local err=$1; shift
+	local what=$1; shift
+
+	if ((should_fail)); then
+		check_fail $err "$what succeeded, but should have failed"
+	else
+		check_err $err "$what failed"
+	fi
+}
+
 log_test()
 {
 	local test_name=$1
-- 
cgit v1.2.3


From 68d9cea594b5da185e5b048e9b4fa0dadeafe88a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:46:05 +0200
Subject: selftests: forwarding: lib: Parameterize NUM_NETIFS in two functions

setup_wait() and tc_offload_check() both assume that all NUM_NETIFS
interfaces are relevant for a given test. However, the scale test script
acts as an umbrella for a number of sub-tests, some of which may not
require all the interfaces.

Thus it's suboptimal for tc_offload_check() to query all the interfaces.
In case of setup_wait() it's incorrect, because the sub-test in question
of course doesn't configure any interfaces beyond what it needs, and
setup_wait() then ends up waiting indefinitely for the extraneous
interfaces to come up.

For that reason, give setup_wait() and tc_offload_check() an optional
parameter with a number of interfaces to probe. Fall back to global
NUM_NETIFS if the parameter is not given.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 5f4b7ed2c65a..e073918bbe15 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -220,7 +220,9 @@ setup_wait_dev()
 
 setup_wait()
 {
-	for i in $(eval echo {1..$NUM_NETIFS}); do
+	local num_netifs=${1:-$NUM_NETIFS}
+
+	for ((i = 1; i <= num_netifs; ++i)); do
 		setup_wait_dev ${NETIFS[p$i]}
 	done
 
@@ -481,7 +483,9 @@ forwarding_restore()
 
 tc_offload_check()
 {
-	for i in $(eval echo {1..$NUM_NETIFS}); do
+	local num_netifs=${1:-$NUM_NETIFS}
+
+	for ((i = 1; i <= num_netifs; ++i)); do
 		ethtool -k ${NETIFS[p$i]} \
 			| grep "hw-tc-offload: on" &> /dev/null
 		if [[ $? -ne 0 ]]; then
-- 
cgit v1.2.3


From bc7cbb1e9f4ccb147fefb7502ab8acdcd52b9a29 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:47:08 +0200
Subject: selftests: forwarding: Add devlink_lib.sh

This helper library contains wrappers to devlink functionality agnostic
to the underlying device.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
[petrm@mellanox.com: Split this out from another patch.]
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/devlink_lib.sh        | 108 +++++++++++++++++++++
 1 file changed, 108 insertions(+)
 create mode 100644 tools/testing/selftests/net/forwarding/devlink_lib.sh

diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
new file mode 100644
index 000000000000..5ab1e5f43022
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
@@ -0,0 +1,108 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+##############################################################################
+# Source library
+
+relative_path="${BASH_SOURCE%/*}"
+if [[ "$relative_path" == "${BASH_SOURCE}" ]]; then
+	relative_path="."
+fi
+
+source "$relative_path/lib.sh"
+
+##############################################################################
+# Defines
+
+DEVLINK_DEV=$(devlink port show | grep "${NETIFS[p1]}" | \
+	      grep -v "${NETIFS[p1]}[0-9]" | cut -d" " -f1 | \
+	      rev | cut -d"/" -f2- | rev)
+if [ -z "$DEVLINK_DEV" ]; then
+	echo "SKIP: ${NETIFS[p1]} has no devlink device registered for it"
+	exit 1
+fi
+if [[ "$(echo $DEVLINK_DEV | grep -c pci)" -eq 0 ]]; then
+	echo "SKIP: devlink device's bus is not PCI"
+	exit 1
+fi
+
+DEVLINK_VIDDID=$(lspci -s $(echo $DEVLINK_DEV | cut -d"/" -f2) \
+		 -n | cut -d" " -f3)
+
+##############################################################################
+# Sanity checks
+
+devlink -j resource show "$DEVLINK_DEV" &> /dev/null
+if [ $? -ne 0 ]; then
+	echo "SKIP: iproute2 too old, missing devlink resource support"
+	exit 1
+fi
+
+##############################################################################
+# Devlink helpers
+
+devlink_resource_names_to_path()
+{
+	local resource
+	local path=""
+
+	for resource in "${@}"; do
+		if [ "$path" == "" ]; then
+			path="$resource"
+		else
+			path="${path}/$resource"
+		fi
+	done
+
+	echo "$path"
+}
+
+devlink_resource_get()
+{
+	local name=$1
+	local resource_name=.[][\"$DEVLINK_DEV\"]
+
+	resource_name="$resource_name | .[] | select (.name == \"$name\")"
+
+	shift
+	for resource in "${@}"; do
+		resource_name="${resource_name} | .[\"resources\"][] | \
+			       select (.name == \"$resource\")"
+	done
+
+	devlink -j resource show "$DEVLINK_DEV" | jq "$resource_name"
+}
+
+devlink_resource_size_get()
+{
+	local size=$(devlink_resource_get "$@" | jq '.["size_new"]')
+
+	if [ "$size" == "null" ]; then
+		devlink_resource_get "$@" | jq '.["size"]'
+	else
+		echo "$size"
+	fi
+}
+
+devlink_resource_size_set()
+{
+	local new_size=$1
+	local path
+
+	shift
+	path=$(devlink_resource_names_to_path "$@")
+	devlink resource set "$DEVLINK_DEV" path "$path" size "$new_size"
+	check_err $? "Failed setting path $path to size $size"
+}
+
+devlink_reload()
+{
+	local still_pending
+
+	devlink dev reload "$DEVLINK_DEV" &> /dev/null
+	check_err $? "Failed reload"
+
+	still_pending=$(devlink resource show "$DEVLINK_DEV" | \
+			grep -c "size_new")
+	check_err $still_pending "Failed reload - There are still unset sizes"
+}
-- 
cgit v1.2.3


From 5aeba3e89b3ee4e541dc882d23c7332893dd4b5a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:48:12 +0200
Subject: selftests: mlxsw: Add devlink_lib_spectrum.sh

This library builds on top of devlink_lib.sh and contains functionality
specific to Spectrum ASICs, e.g., re-partitioning the various KVD
sub-parts.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
[petrm@mellanox.com: Split this out from another patch. Fix line length
in devlink_sp_read_kvd_defaults().]
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                                        |   1 +
 .../net/mlxsw/spectrum/devlink_lib_spectrum.sh     | 119 +++++++++++++++++++++
 2 files changed, 120 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh

diff --git a/MAINTAINERS b/MAINTAINERS
index 3b2e592aa521..7ed37c057ebd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9154,6 +9154,7 @@ S:	Supported
 W:	http://www.mellanox.com
 Q:	http://patchwork.ozlabs.org/project/netdev/list/
 F:	drivers/net/ethernet/mellanox/mlxsw/
+F:	tools/testing/selftests/drivers/net/mlxsw/
 
 MELLANOX FIRMWARE FLASH LIBRARY (mlxfw)
 M:	mlxsw@mellanox.com
diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh
new file mode 100644
index 000000000000..73035e25085d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_lib_spectrum.sh
@@ -0,0 +1,119 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source "../../../../net/forwarding/devlink_lib.sh"
+
+if [ "$DEVLINK_VIDDID" != "15b3:cb84" ]; then
+	echo "SKIP: test is tailored for Mellanox Spectrum"
+	exit 1
+fi
+
+# Needed for returning to default
+declare -A KVD_DEFAULTS
+
+KVD_CHILDREN="linear hash_single hash_double"
+KVDL_CHILDREN="singles chunks large_chunks"
+
+devlink_sp_resource_minimize()
+{
+	local size
+	local i
+
+	for i in $KVD_CHILDREN; do
+		size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]')
+		devlink_resource_size_set "$size" kvd "$i"
+	done
+
+	for i in $KVDL_CHILDREN; do
+		size=$(devlink_resource_get kvd linear "$i" | \
+		       jq '.["size_min"]')
+		devlink_resource_size_set "$size" kvd linear "$i"
+	done
+}
+
+devlink_sp_size_kvd_to_default()
+{
+	local need_reload=0
+	local i
+
+	for i in $KVD_CHILDREN; do
+		local size=$(echo "${KVD_DEFAULTS[kvd_$i]}" | jq '.["size"]')
+		current_size=$(devlink_resource_size_get kvd "$i")
+
+		if [ "$size" -ne "$current_size" ]; then
+			devlink_resource_size_set "$size" kvd "$i"
+			need_reload=1
+		fi
+	done
+
+	for i in $KVDL_CHILDREN; do
+		local size=$(echo "${KVD_DEFAULTS[kvd_linear_$i]}" | \
+			     jq '.["size"]')
+		current_size=$(devlink_resource_size_get kvd linear "$i")
+
+		if [ "$size" -ne "$current_size" ]; then
+			devlink_resource_size_set "$size" kvd linear "$i"
+			need_reload=1
+		fi
+	done
+
+	if [ "$need_reload" -ne "0" ]; then
+		devlink_reload
+	fi
+}
+
+devlink_sp_read_kvd_defaults()
+{
+	local key
+	local i
+
+	KVD_DEFAULTS[kvd]=$(devlink_resource_get "kvd")
+	for i in $KVD_CHILDREN; do
+		key=kvd_$i
+		KVD_DEFAULTS[$key]=$(devlink_resource_get kvd "$i")
+	done
+
+	for i in $KVDL_CHILDREN; do
+		key=kvd_linear_$i
+		KVD_DEFAULTS[$key]=$(devlink_resource_get kvd linear "$i")
+	done
+}
+
+KVD_PROFILES="default scale ipv4_max"
+
+devlink_sp_resource_kvd_profile_set()
+{
+	local profile=$1
+
+	case "$profile" in
+	scale)
+		devlink_resource_size_set 64000 kvd linear
+		devlink_resource_size_set 15616 kvd linear singles
+		devlink_resource_size_set 32000 kvd linear chunks
+		devlink_resource_size_set 16384 kvd linear large_chunks
+		devlink_resource_size_set 128000 kvd hash_single
+		devlink_resource_size_set 48000 kvd hash_double
+		devlink_reload
+		;;
+	ipv4_max)
+		devlink_resource_size_set 64000 kvd linear
+		devlink_resource_size_set 15616 kvd linear singles
+		devlink_resource_size_set 32000 kvd linear chunks
+		devlink_resource_size_set 16384 kvd linear large_chunks
+		devlink_resource_size_set 144000 kvd hash_single
+		devlink_resource_size_set 32768 kvd hash_double
+		devlink_reload
+		;;
+	default)
+		devlink_resource_size_set 98304 kvd linear
+		devlink_resource_size_set 16384 kvd linear singles
+		devlink_resource_size_set 49152 kvd linear chunks
+		devlink_resource_size_set 32768 kvd linear large_chunks
+		devlink_resource_size_set 87040 kvd hash_single
+		devlink_resource_size_set 60416 kvd hash_double
+		devlink_reload
+		;;
+	*)
+		check_err 1 "Unknown profile $profile"
+	esac
+}
-- 
cgit v1.2.3


From b030c338116438700fc61fe572d82034f190d3e8 Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Sat, 30 Jun 2018 02:48:27 +0200
Subject: selftests: mlxsw: Add devlink KVD resource test

Add a selftest that can be used to perform basic sanity of the devlink
resource API as well as test the behavior of KVD manipulation in the
driver.

This is the first case of a HW-only test - in order to test the devlink
resource a driver capable of exposing resources has to be provided
first.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
[petrm@mellanox.com: Extracted two patches out of this patch. Tweaked
commit message.]
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/mlxsw/spectrum/devlink_resources.sh        | 117 +++++++++++++++++++++
 1 file changed, 117 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh
new file mode 100755
index 000000000000..b1fe960e398a
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/devlink_resources.sh
@@ -0,0 +1,117 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NUM_NETIFS=1
+source devlink_lib_spectrum.sh
+
+setup_prepare()
+{
+	devlink_sp_read_kvd_defaults
+}
+
+cleanup()
+{
+	pre_cleanup
+	devlink_sp_size_kvd_to_default
+}
+
+trap cleanup EXIT
+
+setup_prepare
+
+profiles_test()
+{
+	local i
+
+	log_info "Running profile tests"
+
+	for i in $KVD_PROFILES; do
+		RET=0
+		devlink_sp_resource_kvd_profile_set $i
+		log_test "'$i' profile"
+	done
+
+	# Default is explicitly tested at end to ensure it's actually applied
+	RET=0
+	devlink_sp_resource_kvd_profile_set "default"
+	log_test "'default' profile"
+}
+
+resources_min_test()
+{
+	local size
+	local i
+	local j
+
+	log_info "Running KVD-minimum tests"
+
+	for i in $KVD_CHILDREN; do
+		RET=0
+		size=$(devlink_resource_get kvd "$i" | jq '.["size_min"]')
+		devlink_resource_size_set "$size" kvd "$i"
+
+		# In case of linear, need to minimize sub-resources as well
+		if [[ "$i" == "linear" ]]; then
+			for j in $KVDL_CHILDREN; do
+				devlink_resource_size_set 0 kvd linear "$j"
+			done
+		fi
+
+		devlink_reload
+		devlink_sp_size_kvd_to_default
+		log_test "'$i' minimize [$size]"
+	done
+}
+
+resources_max_test()
+{
+	local min_size
+	local size
+	local i
+	local j
+
+	log_info "Running KVD-maximum tests"
+	for i in $KVD_CHILDREN; do
+		RET=0
+		devlink_sp_resource_minimize
+
+		# Calculate the maximum possible size for the given partition
+		size=$(devlink_resource_size_get kvd)
+		for j in $KVD_CHILDREN; do
+			if [ "$i" != "$j" ]; then
+				min_size=$(devlink_resource_get kvd "$j" | \
+					   jq '.["size_min"]')
+				size=$((size - min_size))
+			fi
+		done
+
+		# Test almost maximum size
+		devlink_resource_size_set "$((size - 128))" kvd "$i"
+		devlink_reload
+		log_test "'$i' almost maximize [$((size - 128))]"
+
+		# Test above maximum size
+		devlink resource set "$DEVLINK_DEV" \
+			path "kvd/$i" size $((size + 128)) &> /dev/null
+		check_fail $? "Set kvd/$i to size $((size + 128)) should fail"
+		log_test "'$i' Overflow rejection [$((size + 128))]"
+
+		# Test maximum size
+		if [ "$i" == "hash_single" ] || [ "$i" == "hash_double" ]; then
+			echo "SKIP: Observed problem with exact max $i"
+			continue
+		fi
+
+		devlink_resource_size_set "$size" kvd "$i"
+		devlink_reload
+		log_test "'$i' maximize [$size]"
+
+		devlink_sp_size_kvd_to_default
+	done
+}
+
+profiles_test
+resources_min_test
+resources_max_test
+
+exit "$RET"
-- 
cgit v1.2.3


From d98307c52b19354830af205a1a8346d13e2b1fa7 Mon Sep 17 00:00:00 2001
From: Arkadi Sharshevsky <arkadis@mellanox.com>
Date: Sat, 30 Jun 2018 02:49:32 +0200
Subject: selftests: mlxsw: Add router test

This test aims for both stand alone and internal usage by the resource
infra. The test receives the number routes to offload and checks:
- The routes were offloaded correctly
- Traffic for each route.

Signed-off-by: Arkadi Sharshevsky <arkadis@mellanox.com>
Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/router_scale.sh    | 167 +++++++++++++++++++++
 1 file changed, 167 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/router_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
new file mode 100644
index 000000000000..d231649b4f01
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/router_scale.sh
@@ -0,0 +1,167 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ROUTER_NUM_NETIFS=4
+
+router_h1_create()
+{
+	simple_if_init $h1 192.0.1.1/24
+	ip route add 193.0.0.0/8 via 192.0.1.2 dev $h1
+}
+
+router_h1_destroy()
+{
+	ip route del 193.0.0.0/8 via 192.0.1.2 dev $h1
+	simple_if_fini $h1 192.0.1.1/24
+}
+
+router_h2_create()
+{
+	simple_if_init $h2 192.0.2.1/24
+	tc qdisc add dev $h2 handle ffff: ingress
+}
+
+router_h2_destroy()
+{
+	tc qdisc del dev $h2 handle ffff: ingress
+	simple_if_fini $h2 192.0.2.1/24
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+
+	ip address add 192.0.1.2/24 dev $rp1
+	ip address add 192.0.2.2/24 dev $rp2
+}
+
+router_destroy()
+{
+	ip address del 192.0.2.2/24 dev $rp2
+	ip address del 192.0.1.2/24 dev $rp1
+
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+router_setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	h1mac=$(mac_get $h1)
+	rp1mac=$(mac_get $rp1)
+
+	vrf_prepare
+
+	router_h1_create
+	router_h2_create
+
+	router_create
+}
+
+router_offload_validate()
+{
+	local route_count=$1
+	local offloaded_count
+
+	offloaded_count=$(ip route | grep -o 'offload' | wc -l)
+	[[ $offloaded_count -ge $route_count ]]
+}
+
+router_routes_create()
+{
+	local route_count=$1
+	local count=0
+
+	ROUTE_FILE="$(mktemp)"
+
+	for i in {0..255}
+	do
+		for j in {0..255}
+		do
+			for k in {0..255}
+			do
+				if [[ $count -eq $route_count ]]; then
+					break 3
+				fi
+
+				echo route add 193.${i}.${j}.${k}/32 via \
+				       192.0.2.1 dev $rp2  >> $ROUTE_FILE
+				((count++))
+			done
+		done
+	done
+
+	ip -b $ROUTE_FILE &> /dev/null
+}
+
+router_routes_destroy()
+{
+	if [[ -v ROUTE_FILE ]]; then
+		rm -f $ROUTE_FILE
+	fi
+}
+
+router_test()
+{
+	local route_count=$1
+	local should_fail=$2
+	local count=0
+
+	RET=0
+
+	router_routes_create $route_count
+
+	router_offload_validate $route_count
+	check_err_fail $should_fail $? "Offload of $route_count routes"
+	if [[ $RET -ne 0 ]] || [[ $should_fail -eq 1 ]]; then
+		return
+	fi
+
+	tc filter add dev $h2 ingress protocol ip pref 1 flower \
+		skip_sw dst_ip 193.0.0.0/8 action drop
+
+	for i in {0..255}
+	do
+		for j in {0..255}
+		do
+			for k in {0..255}
+			do
+				if [[ $count -eq $route_count ]]; then
+					break 3
+				fi
+
+				$MZ $h1 -c 1 -p 64 -a $h1mac -b $rp1mac \
+					-A 192.0.1.1 -B 193.${i}.${j}.${k} \
+					-t ip -q
+				((count++))
+			done
+		done
+	done
+
+	tc_check_packets "dev $h2 ingress" 1 $route_count
+	check_err $? "Offload mismatch"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 flower \
+		skip_sw dst_ip 193.0.0.0/8 action drop
+
+	router_routes_destroy
+}
+
+router_cleanup()
+{
+	pre_cleanup
+
+	router_routes_destroy
+	router_destroy
+
+	router_h2_destroy
+	router_h1_destroy
+
+	vrf_cleanup
+}
-- 
cgit v1.2.3


From c51a744a28bad6faec696b56c176519bea0e73bc Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Sat, 30 Jun 2018 02:50:28 +0200
Subject: selftests: mlxsw: Add target for router test on spectrum

IPv4 routes in Spectrum are based on the kvd single-hash, but as it's
a hash we need to assume we cannot reach 100% of its capacity.

Add a wrapper that provides us with good/bad target numbers for the
Spectrum ASIC.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
[petrm@mellanox.com: Drop shebang.]
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum/router_scale.sh         | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh
new file mode 100644
index 000000000000..21c4697d5bab
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/router_scale.sh
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../router_scale.sh
+
+router_get_target()
+{
+	local should_fail=$1
+	local target
+
+	target=$(devlink_resource_size_get kvd hash_single)
+
+	if [[ $should_fail -eq 0 ]]; then
+		target=$((target * 85 / 100))
+	else
+		target=$((target + 1))
+	fi
+
+	echo $target
+}
-- 
cgit v1.2.3


From d67a94e81fda793fc2cd8562501117720e221634 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:51:05 +0200
Subject: selftests: mlxsw: Add tc flower scale test

Add test of capacity to offload flower.

This is a generic portion of the test that is meant to be called from a
driver that supplies a particular number of rules to be tested with.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/tc_flower_scale.sh | 134 +++++++++++++++++++++
 1 file changed, 134 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
new file mode 100644
index 000000000000..a6d733d2a4b4
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/tc_flower_scale.sh
@@ -0,0 +1,134 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for resource limit of offloaded flower rules. The test adds a given
+# number of flower matches for different IPv6 addresses, then generates traffic,
+# and ensures each was hit exactly once. This file contains functions to set up
+# a testing topology and run the test, and is meant to be sourced from a test
+# script that calls the testing routine with a given number of rules.
+
+TC_FLOWER_NUM_NETIFS=2
+
+tc_flower_h1_create()
+{
+	simple_if_init $h1
+	tc qdisc add dev $h1 clsact
+}
+
+tc_flower_h1_destroy()
+{
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1
+}
+
+tc_flower_h2_create()
+{
+	simple_if_init $h2
+	tc qdisc add dev $h2 clsact
+}
+
+tc_flower_h2_destroy()
+{
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2
+}
+
+tc_flower_setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+
+	vrf_prepare
+
+	tc_flower_h1_create
+	tc_flower_h2_create
+}
+
+tc_flower_cleanup()
+{
+	pre_cleanup
+
+	tc_flower_h2_destroy
+	tc_flower_h1_destroy
+
+	vrf_cleanup
+
+	if [[ -v TC_FLOWER_BATCH_FILE ]]; then
+		rm -f $TC_FLOWER_BATCH_FILE
+	fi
+}
+
+tc_flower_addr()
+{
+	local num=$1; shift
+
+	printf "2001:db8:1::%x" $num
+}
+
+tc_flower_rules_create()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	TC_FLOWER_BATCH_FILE="$(mktemp)"
+
+	for ((i = 0; i < count; ++i)); do
+		cat >> $TC_FLOWER_BATCH_FILE <<-EOF
+			filter add dev $h2 ingress \
+				prot ipv6 \
+				pref 1000 \
+				flower $tcflags dst_ip $(tc_flower_addr $i) \
+				action drop
+		EOF
+	done
+
+	tc -b $TC_FLOWER_BATCH_FILE
+	check_err_fail $should_fail $? "Rule insertion"
+}
+
+__tc_flower_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+	local last=$((count - 1))
+
+	tc_flower_rules_create $count $should_fail
+
+	for ((i = 0; i < count; ++i)); do
+		$MZ $h1 -q -c 1 -t ip -p 20 -b bc -6 \
+			-A 2001:db8:2::1 \
+			-B $(tc_flower_addr $i)
+	done
+
+	MISMATCHES=$(
+		tc -j -s filter show dev $h2 ingress |
+		jq -r '[ .[] | select(.kind == "flower") | .options |
+		         values as $rule | .actions[].stats.packets |
+		         select(. != 1) | "\(.) on \($rule.keys.dst_ip)" ] |
+		       join(", ")'
+	)
+
+	test -z "$MISMATCHES"
+	check_err $? "Expected to capture 1 packet for each IP, but got $MISMATCHES"
+}
+
+tc_flower_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	# We use lower 16 bits of IPv6 address for match. Also there are only 16
+	# bits of rule priority space.
+	if ((count > 65536)); then
+		check_err 1 "Invalid count of $count. At most 65536 rules supported"
+		return
+	fi
+
+	if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
+		check_err 1 "Could not test offloaded functionality"
+		return
+	fi
+
+	tcflags="skip_sw"
+	__tc_flower_test $count $should_fail
+}
-- 
cgit v1.2.3


From 741a7661f077bf906761fbaef31f3b5aa393c734 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:51:55 +0200
Subject: selftests: mlxsw: Add target for tc flower test on spectrum

Add a wrapper around mlxsw/tc_flower_scale.sh that parameterizes the
generic tc flower scale test template with Spectrum-specific target
values.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum/tc_flower_scale.sh     | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh
new file mode 100644
index 000000000000..f9bfd8937765
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/tc_flower_scale.sh
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../tc_flower_scale.sh
+
+tc_flower_get_target()
+{
+	local should_fail=$1; shift
+
+	# 6144 (6x1024) is the theoretical maximum.
+	# One bank of 512 rules is taken by the 18-byte MC router rule.
+	# One rule is the ACL catch-all.
+	# 6144 - 512 - 1 = 5631
+	local target=5631
+
+	if ((! should_fail)); then
+		echo $target
+	else
+		echo $((target + 1))
+	fi
+}
-- 
cgit v1.2.3


From b973b78aaeae44d650f534b617a2b62e5a83327a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:52:34 +0200
Subject: selftests: mlxsw: Add scale test for mirror-to-gretap

Test that it's possible to offload a given number of mirrors.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/mirror_gre_scale.sh          | 197 +++++++++++++++++++++
 1 file changed, 197 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
new file mode 100644
index 000000000000..6f3a70df63bc
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre_scale.sh
@@ -0,0 +1,197 @@
+# SPDX-License-Identifier: GPL-2.0
+
+# Test offloading a number of mirrors-to-gretap. The test creates a number of
+# tunnels. Then it adds one flower mirror for each of the tunnels, matching a
+# given host IP. Then it generates traffic at each of the host IPs and checks
+# that the traffic has been mirrored at the appropriate tunnel.
+#
+#   +--------------------------+                   +--------------------------+
+#   | H1                       |                   |                       H2 |
+#   |     + $h1                |                   |                $h2 +     |
+#   |     | 2001:db8:1:X::1/64 |                   | 2001:db8:1:X::2/64 |     |
+#   +-----|--------------------+                   +--------------------|-----+
+#         |                                                             |
+#   +-----|-------------------------------------------------------------|-----+
+#   | SW  o--> mirrors                                                  |     |
+#   | +---|-------------------------------------------------------------|---+ |
+#   | |   + $swp1                    BR                           $swp2 +   | |
+#   | +---------------------------------------------------------------------+ |
+#   |                                                                         |
+#   |     + $swp3                          + gt6-<X> (ip6gretap)              |
+#   |     | 2001:db8:2:X::1/64             : loc=2001:db8:2:X::1              |
+#   |     |                                : rem=2001:db8:2:X::2              |
+#   |     |                                : ttl=100                          |
+#   |     |                                : tos=inherit                      |
+#   |     |                                :                                  |
+#   +-----|--------------------------------:----------------------------------+
+#         |                                :
+#   +-----|--------------------------------:----------------------------------+
+#   | H3  + $h3                            + h3-gt6-<X> (ip6gretap)           |
+#   |       2001:db8:2:X::2/64               loc=2001:db8:2:X::2              |
+#   |                                        rem=2001:db8:2:X::1              |
+#   |                                        ttl=100                          |
+#   |                                        tos=inherit                      |
+#   |                                                                         |
+#   +-------------------------------------------------------------------------+
+
+source ../../../../net/forwarding/mirror_lib.sh
+
+MIRROR_NUM_NETIFS=6
+
+mirror_gre_ipv6_addr()
+{
+	local net=$1; shift
+	local num=$1; shift
+
+	printf "2001:db8:%x:%x" $net $num
+}
+
+mirror_gre_tunnels_create()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	MIRROR_GRE_BATCH_FILE="$(mktemp)"
+	for ((i=0; i < count; ++i)); do
+		local match_dip=$(mirror_gre_ipv6_addr 1 $i)::2
+		local htun=h3-gt6-$i
+		local tun=gt6-$i
+
+		((mirror_gre_tunnels++))
+
+		ip address add dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64
+		ip address add dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64
+
+		ip address add dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64
+		ip address add dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64
+
+		tunnel_create $tun ip6gretap \
+			      $(mirror_gre_ipv6_addr 2 $i)::1 \
+			      $(mirror_gre_ipv6_addr 2 $i)::2 \
+			      ttl 100 tos inherit allow-localremote
+
+		tunnel_create $htun ip6gretap \
+			      $(mirror_gre_ipv6_addr 2 $i)::2 \
+			      $(mirror_gre_ipv6_addr 2 $i)::1
+		ip link set $htun vrf v$h3
+		matchall_sink_create $htun
+
+		cat >> $MIRROR_GRE_BATCH_FILE <<-EOF
+			filter add dev $swp1 ingress pref 1000 \
+				protocol ipv6 \
+				flower $tcflags dst_ip $match_dip \
+				action mirred egress mirror dev $tun
+		EOF
+	done
+
+	tc -b $MIRROR_GRE_BATCH_FILE
+	check_err_fail $should_fail $? "Mirror rule insertion"
+}
+
+mirror_gre_tunnels_destroy()
+{
+	local count=$1; shift
+
+	for ((i=0; i < count; ++i)); do
+		local htun=h3-gt6-$i
+		local tun=gt6-$i
+
+		ip address del dev $h3 $(mirror_gre_ipv6_addr 2 $i)::2/64
+		ip address del dev $swp3 $(mirror_gre_ipv6_addr 2 $i)::1/64
+
+		ip address del dev $h2 $(mirror_gre_ipv6_addr 1 $i)::2/64
+		ip address del dev $h1 $(mirror_gre_ipv6_addr 1 $i)::1/64
+
+		tunnel_destroy $htun
+		tunnel_destroy $tun
+	done
+}
+
+__mirror_gre_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	mirror_gre_tunnels_create $count $should_fail
+	if ((should_fail)); then
+	    return
+	fi
+
+	sleep 5
+
+	for ((i = 0; i < count; ++i)); do
+		local dip=$(mirror_gre_ipv6_addr 1 $i)::2
+		local htun=h3-gt6-$i
+		local message
+
+		icmp6_capture_install $htun
+		mirror_test v$h1 "" $dip $htun 100 10
+		icmp6_capture_uninstall $htun
+	done
+}
+
+mirror_gre_test()
+{
+	local count=$1; shift
+	local should_fail=$1; shift
+
+	if ! tc_offload_check $TC_FLOWER_NUM_NETIFS; then
+		check_err 1 "Could not test offloaded functionality"
+		return
+	fi
+
+	tcflags="skip_sw"
+	__mirror_gre_test $count $should_fail
+}
+
+mirror_gre_setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	mirror_gre_tunnels=0
+
+	vrf_prepare
+
+	simple_if_init $h1
+	simple_if_init $h2
+	simple_if_init $h3
+
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 up
+
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+	tc qdisc add dev $swp1 clsact
+
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+
+	ip link set dev $swp3 up
+}
+
+mirror_gre_cleanup()
+{
+	mirror_gre_tunnels_destroy $mirror_gre_tunnels
+
+	ip link set dev $swp3 down
+
+	ip link set dev $swp2 down
+
+	tc qdisc del dev $swp1 clsact
+	ip link set dev $swp1 down
+
+	ip link del dev br1
+
+	simple_if_fini $h3
+	simple_if_fini $h2
+	simple_if_fini $h1
+
+	vrf_cleanup
+}
-- 
cgit v1.2.3


From 9136074d56419fc502efeea1c80b63af0e4da3e7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 30 Jun 2018 02:53:14 +0200
Subject: selftests: mlxsw: Add target for mirror-to-gretap test on spectrum

Add a wrapper around mlxsw/mirror_gre_scale.sh that parameterized number
of offloadable mirrors on Spectrum machines.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum/mirror_gre_scale.sh          | 13 +++++++++++++
 1 file changed, 13 insertions(+)
 create mode 100644 tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh
new file mode 100644
index 000000000000..8d2186c7c62b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/mirror_gre_scale.sh
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+source ../mirror_gre_scale.sh
+
+mirror_gre_get_target()
+{
+	local should_fail=$1; shift
+
+	if ((! should_fail)); then
+		echo 3
+	else
+		echo 4
+	fi
+}
-- 
cgit v1.2.3


From 1b6130df62d0346698c5465736e36d935605af0c Mon Sep 17 00:00:00 2001
From: Yuval Mintz <yuvalm@mellanox.com>
Date: Sat, 30 Jun 2018 02:53:52 +0200
Subject: selftests: mlxsw: Add scale test for resources

Add a scale test capable of validating that offloaded network
functionality is indeed functional at scale when configured to
the different KVD profiles available.

Start by testing offloaded routes are functional at scale by
passing traffic on each one of them in turn.

Signed-off-by: Yuval Mintz <yuvalm@mellanox.com>
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum/resource_scale.sh   | 55 ++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
new file mode 100755
index 000000000000..a0a80e1a69e8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum/resource_scale.sh
@@ -0,0 +1,55 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+NUM_NETIFS=6
+source ../../../../net/forwarding/lib.sh
+source ../../../../net/forwarding/tc_common.sh
+source devlink_lib_spectrum.sh
+
+current_test=""
+
+cleanup()
+{
+	pre_cleanup
+	if [ ! -z $current_test ]; then
+		${current_test}_cleanup
+	fi
+	devlink_sp_size_kvd_to_default
+}
+
+devlink_sp_read_kvd_defaults
+trap cleanup EXIT
+
+ALL_TESTS="router tc_flower mirror_gre"
+for current_test in ${TESTS:-$ALL_TESTS}; do
+	source ${current_test}_scale.sh
+
+	num_netifs_var=${current_test^^}_NUM_NETIFS
+	num_netifs=${!num_netifs_var:-$NUM_NETIFS}
+
+	for profile in $KVD_PROFILES; do
+		RET=0
+		devlink_sp_resource_kvd_profile_set $profile
+		if [[ $RET -gt 0 ]]; then
+			log_test "'$current_test' [$profile] setting"
+			continue
+		fi
+
+		for should_fail in 0 1; do
+			RET=0
+			target=$(${current_test}_get_target "$should_fail")
+			${current_test}_setup_prepare
+			setup_wait $num_netifs
+			${current_test}_test "$target" "$should_fail"
+			${current_test}_cleanup
+			if [[ "$should_fail" -eq 0 ]]; then
+				log_test "'$current_test' [$profile] $target"
+			else
+				log_test "'$current_test' [$profile] overflow $target"
+			fi
+		done
+	done
+done
+current_test=""
+
+exit "$RET"
-- 
cgit v1.2.3


From e876c445df4009d7b1ebdd2a92ca23566ca05440 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 23 Jun 2018 20:33:59 -0400
Subject: hpfs: fix an inode leak in lookup, switch to d_splice_alias()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/hpfs/dir.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/fs/hpfs/dir.c b/fs/hpfs/dir.c
index c83ece7facc5..d85230c84ef2 100644
--- a/fs/hpfs/dir.c
+++ b/fs/hpfs/dir.c
@@ -244,6 +244,7 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 	result = iget_locked(dir->i_sb, ino);
 	if (!result) {
 		hpfs_error(dir->i_sb, "hpfs_lookup: can't get inode");
+		result = ERR_PTR(-ENOMEM);
 		goto bail1;
 	}
 	if (result->i_state & I_NEW) {
@@ -266,6 +267,8 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 
 	if (de->has_acl || de->has_xtd_perm) if (!sb_rdonly(dir->i_sb)) {
 		hpfs_error(result->i_sb, "ACLs or XPERM found. This is probably HPFS386. This driver doesn't support it now. Send me some info on these structures");
+		iput(result);
+		result = ERR_PTR(-EINVAL);
 		goto bail1;
 	}
 
@@ -301,29 +304,17 @@ struct dentry *hpfs_lookup(struct inode *dir, struct dentry *dentry, unsigned in
 		}
 	}
 
+bail1:
 	hpfs_brelse4(&qbh);
 
 	/*
 	 * Made it.
 	 */
 
-	end:
-	end_add:
+end:
+end_add:
 	hpfs_unlock(dir->i_sb);
-	d_add(dentry, result);
-	return NULL;
-
-	/*
-	 * Didn't.
-	 */
-	bail1:
-	
-	hpfs_brelse4(&qbh);
-	
-	/*bail:*/
-
-	hpfs_unlock(dir->i_sb);
-	return ERR_PTR(-ENOENT);
+	return d_splice_alias(result, dentry);
 }
 
 const struct file_operations hpfs_dir_ops =
-- 
cgit v1.2.3


From f2e8603604aae9251d91249d8438f02234f17464 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 00:05:10 +0300
Subject: Documentation/sphinx: allow "functions" with no parameters

When kernel-doc:: specified in .rst document without explicit directives,
it outputs both comment and DOC: sections. If a DOC: section was explicitly
included in the same document it will be duplicated. For example, the
output generated for Documentation/core-api/idr.rst [1] has "IDA
description" in the "IDA usage" section and in the middle of the API
reference.

This patch enables using "functions" directive without parameters to output
all the documentation excluding DOC: sections.

[1] https://www.kernel.org/doc/html/v4.17/core-api/idr.html

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/doc-guide/kernel-doc.rst |  9 +++++++--
 Documentation/sphinx/kerneldoc.py      | 10 +++++++---
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/Documentation/doc-guide/kernel-doc.rst b/Documentation/doc-guide/kernel-doc.rst
index 80383b1a574a..8db53cdc225f 100644
--- a/Documentation/doc-guide/kernel-doc.rst
+++ b/Documentation/doc-guide/kernel-doc.rst
@@ -488,14 +488,19 @@ doc: *title*
     .. kernel-doc:: drivers/gpu/drm/i915/intel_audio.c
        :doc: High Definition Audio over HDMI and Display Port
 
-functions: *function* *[...]*
+functions: *[ function ...]*
   Include documentation for each *function* in *source*.
+  If no *function* if specified, the documentaion for all functions
+  and types in the *source* will be included.
 
-  Example::
+  Examples::
 
     .. kernel-doc:: lib/bitmap.c
        :functions: bitmap_parselist bitmap_parselist_user
 
+    .. kernel-doc:: lib/idr.c
+       :functions:
+
 Without options, the kernel-doc directive includes all documentation comments
 from the source file.
 
diff --git a/Documentation/sphinx/kerneldoc.py b/Documentation/sphinx/kerneldoc.py
index fbedcc39460b..9d0a7f08f93b 100644
--- a/Documentation/sphinx/kerneldoc.py
+++ b/Documentation/sphinx/kerneldoc.py
@@ -47,7 +47,7 @@ class KernelDocDirective(Directive):
     optional_arguments = 4
     option_spec = {
         'doc': directives.unchanged_required,
-        'functions': directives.unchanged_required,
+        'functions': directives.unchanged,
         'export': directives.unchanged,
         'internal': directives.unchanged,
     }
@@ -75,8 +75,12 @@ class KernelDocDirective(Directive):
         elif 'doc' in self.options:
             cmd += ['-function', str(self.options.get('doc'))]
         elif 'functions' in self.options:
-            for f in str(self.options.get('functions')).split():
-                cmd += ['-function', f]
+            functions = self.options.get('functions').split()
+            if functions:
+                for f in functions:
+                    cmd += ['-function', f]
+            else:
+                cmd += ['-no-doc-sections']
 
         for pattern in export_file_patterns:
             for f in glob.glob(env.config.kerneldoc_srctree + '/' + pattern):
-- 
cgit v1.2.3


From 5105730fbf6789ff9e20837bdefe32e8ba133595 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 00:05:11 +0300
Subject: docs/idr: use empty "functions" directive

to avoid duplication of DOC: sections in the middle of the API reference.

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/core-api/idr.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/core-api/idr.rst b/Documentation/core-api/idr.rst
index 9078a5c3ac95..d351e880a2f6 100644
--- a/Documentation/core-api/idr.rst
+++ b/Documentation/core-api/idr.rst
@@ -76,4 +76,6 @@ Functions and structures
 ========================
 
 .. kernel-doc:: include/linux/idr.h
+   :functions:
 .. kernel-doc:: lib/idr.c
+   :functions:
-- 
cgit v1.2.3


From f778a0d26fe3912424401e7b997155094de36487 Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Wed, 30 May 2018 14:13:11 -0600
Subject: PCI: Expand documentation for pci_add_dma_alias()

Seeing there's been some confusion about the use of pci_add_dma_alias(),
expand the comment to describe why it must be called early and how
early it must be called.

Also, expand on the purpose of this function and common reasons it would
be used.

[The comment was reworded to some extent by Alex Williamson]

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Doug Meyer <dmeyer@gigaio.com>
---
 drivers/pci/pci.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..ea4a9d3be9f9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5387,8 +5387,19 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode,
  * @dev: the PCI device for which alias is added
  * @devfn: alias slot and function
  *
- * This helper encodes 8-bit devfn as bit number in dma_alias_mask.
- * It should be called early, preferably as PCI fixup header quirk.
+ * This helper encodes an 8-bit devfn as a bit number in dma_alias_mask
+ * which is used to program permissible bus-devfn source addresses for DMA
+ * requests in an IOMMU.  These aliases factor into IOMMU group creation
+ * and are useful for devices generating DMA requests beyond or different
+ * from their logical bus-devfn.  Examples include device quirks where the
+ * device simply uses the wrong devfn, as well as non-transparent bridges
+ * where the alias may be a proxy for devices in another domain.
+ *
+ * IOMMU group creation is performed during device discovery or addition,
+ * prior to any potential DMA mapping and therefore prior to driver probing
+ * (especially for userspace assigned devices where IOMMU group definition
+ * cannot be left as a userspace activity).  DMA aliases should therefore
+ * be configured via quirks, such as the PCI fixup header quirk.
  */
 void pci_add_dma_alias(struct pci_dev *dev, u8 devfn)
 {
-- 
cgit v1.2.3


From 7ce3f912ae0a79e5d738a3ae1f158b281973e849 Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Sat, 30 Jun 2018 11:24:24 -0400
Subject: PCI: Enable PASID only if entire path supports End-End TLP prefixes

A PCIe endpoint carries the process address space identifier (PASID) in
the TLP prefix as part of the memory read/write transaction. The address
information in the TLP is relevant only for a given PASID context.

An IOMMU takes PASID value and the address information from the
TLP to look up the physical address in the system.

PASID is an End-End TLP Prefix (PCIe r4.0, sec 6.20).  Sec 2.2.10.2 says

  It is an error to receive a TLP with an End-End TLP Prefix by a
  Receiver that does not support End-End TLP Prefixes. A TLP in
  violation of this rule is handled as a Malformed TLP. This is a
  reported error associated with the Receiving Port (see Section 6.2).

Prevent error condition by proactively requiring End-End TLP prefix to be
supported on the entire data path between the endpoint and the root port
before enabling PASID.

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/ats.c             |  3 +++
 drivers/pci/probe.c           | 24 ++++++++++++++++++++++++
 include/linux/pci.h           |  1 +
 include/uapi/linux/pci_regs.h |  1 +
 4 files changed, 29 insertions(+)

diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 4923a2a8e14b..5b78f3b1b918 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -273,6 +273,9 @@ int pci_enable_pasid(struct pci_dev *pdev, int features)
 	if (WARN_ON(pdev->pasid_enabled))
 		return -EBUSY;
 
+	if (!pdev->eetlp_prefix_path)
+		return -EINVAL;
+
 	pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_PASID);
 	if (!pos)
 		return -EINVAL;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..4c35c2909d57 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2042,6 +2042,29 @@ static void pci_configure_ltr(struct pci_dev *dev)
 #endif
 }
 
+static void pci_configure_eetlp_prefix(struct pci_dev *dev)
+{
+#ifdef CONFIG_PCI_PASID
+	struct pci_dev *bridge;
+	u32 cap;
+
+	if (!pci_is_pcie(dev))
+		return;
+
+	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP2, &cap);
+	if (!(cap & PCI_EXP_DEVCAP2_EE_PREFIX))
+		return;
+
+	if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT)
+		dev->eetlp_prefix_path = 1;
+	else {
+		bridge = pci_upstream_bridge(dev);
+		if (bridge && bridge->eetlp_prefix_path)
+			dev->eetlp_prefix_path = 1;
+	}
+#endif
+}
+
 static void pci_configure_device(struct pci_dev *dev)
 {
 	struct hotplug_params hpp;
@@ -2051,6 +2074,7 @@ static void pci_configure_device(struct pci_dev *dev)
 	pci_configure_extended_tags(dev, NULL);
 	pci_configure_relaxed_ordering(dev);
 	pci_configure_ltr(dev);
+	pci_configure_eetlp_prefix(dev);
 
 	memset(&hpp, 0, sizeof(hpp));
 	ret = pci_get_hp_params(dev, &hpp);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..6ba818449095 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -350,6 +350,7 @@ struct pci_dev {
 	unsigned int	ltr_path:1;	/* Latency Tolerance Reporting
 					   supported from root to here */
 #endif
+	unsigned int	eetlp_prefix_path:1;	/* End-to-End TLP Prefix */
 
 	pci_channel_state_t error_state;	/* Current connectivity state */
 	struct device	dev;			/* Generic device interface */
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index 4da87e2ef8a8..04d7480db714 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -636,6 +636,7 @@
 #define  PCI_EXP_DEVCAP2_OBFF_MASK	0x000c0000 /* OBFF support mechanism */
 #define  PCI_EXP_DEVCAP2_OBFF_MSG	0x00040000 /* New message signaling */
 #define  PCI_EXP_DEVCAP2_OBFF_WAKE	0x00080000 /* Re-use WAKE# for OBFF */
+#define PCI_EXP_DEVCAP2_EE_PREFIX	0x00200000 /* End-End TLP Prefix */
 #define PCI_EXP_DEVCTL2		40	/* Device Control 2 */
 #define  PCI_EXP_DEVCTL2_COMP_TIMEOUT	0x000f	/* Completion Timeout Value */
 #define  PCI_EXP_DEVCTL2_COMP_TMOUT_DIS	0x0010	/* Completion Timeout Disable */
-- 
cgit v1.2.3


From c256429fbd01d6993a2e19ff24f252514a0b84a5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:35 -0700
Subject: tools: bpftool: use correct make variable type to improve compilation
 time

Commit 4bfe3bd3cc35 ("tools/bpftool: use version from the kernel
source tree") added version to bpftool.  The version used is
equal to the kernel version and obtained by running make kernelversion
against kernel source tree.  Version is then communicated
to the sources with a command line define set in CFLAGS.

Use a simply expanded variable for the version, otherwise the
recursive make will run every time CFLAGS are used.

This brings the single-job compilation time for me from almost
16 sec down to less than 4 sec.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 892dbf095bff..0911b00b25cc 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -23,7 +23,7 @@ endif
 
 LIBBPF = $(BPF_PATH)libbpf.a
 
-BPFTOOL_VERSION=$(shell make --no-print-directory -sC ../../.. kernelversion)
+BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion)
 
 $(LIBBPF): FORCE
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
-- 
cgit v1.2.3


From d9b683d7464ec9e8298d82c00b9033c96e27a187 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:36 -0700
Subject: tools: libbpf: add section names for missing program types

Specify default section names for BPF_PROG_TYPE_LIRC_MODE2
and BPF_PROG_TYPE_LWT_SEG6LOCAL, these are the only two
missing right now.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1e96b5de5ff..a1491e95edd0 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2037,9 +2037,11 @@ static const struct {
 	BPF_PROG_SEC("lwt_in",		BPF_PROG_TYPE_LWT_IN),
 	BPF_PROG_SEC("lwt_out",		BPF_PROG_TYPE_LWT_OUT),
 	BPF_PROG_SEC("lwt_xmit",	BPF_PROG_TYPE_LWT_XMIT),
+	BPF_PROG_SEC("lwt_seg6local",	BPF_PROG_TYPE_LWT_SEG6LOCAL),
 	BPF_PROG_SEC("sockops",		BPF_PROG_TYPE_SOCK_OPS),
 	BPF_PROG_SEC("sk_skb",		BPF_PROG_TYPE_SK_SKB),
 	BPF_PROG_SEC("sk_msg",		BPF_PROG_TYPE_SK_MSG),
+	BPF_PROG_SEC("lirc_mode2",	BPF_PROG_TYPE_LIRC_MODE2),
 	BPF_SA_PROG_SEC("cgroup/bind4",	BPF_CGROUP_INET4_BIND),
 	BPF_SA_PROG_SEC("cgroup/bind6",	BPF_CGROUP_INET6_BIND),
 	BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT),
-- 
cgit v1.2.3


From 9aba36139a5f9ee1d11a60d0a3a90944b8d56385 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:37 -0700
Subject: tools: libbpf: allow setting ifindex for programs and maps

Users of bpf_object__open()/bpf_object__load() APIs may want to
load the programs and maps onto a device for offload.  Allow
setting ifindex on those sub-objects.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 10 ++++++++++
 tools/lib/bpf/libbpf.h |  2 ++
 2 files changed, 12 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index a1491e95edd0..7bc02d93e277 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1896,6 +1896,11 @@ void *bpf_program__priv(struct bpf_program *prog)
 	return prog ? prog->priv : ERR_PTR(-EINVAL);
 }
 
+void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex)
+{
+	prog->prog_ifindex = ifindex;
+}
+
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy)
 {
 	const char *title;
@@ -2122,6 +2127,11 @@ void *bpf_map__priv(struct bpf_map *map)
 	return map ? map->priv : ERR_PTR(-EINVAL);
 }
 
+void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
+{
+	map->map_ifindex = ifindex;
+}
+
 struct bpf_map *
 bpf_map__next(struct bpf_map *prev, struct bpf_object *obj)
 {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 09976531aa74..564f4be9bae0 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -109,6 +109,7 @@ int bpf_program__set_priv(struct bpf_program *prog, void *priv,
 			  bpf_program_clear_priv_t clear_priv);
 
 void *bpf_program__priv(struct bpf_program *prog);
+void bpf_program__set_ifindex(struct bpf_program *prog, __u32 ifindex);
 
 const char *bpf_program__title(struct bpf_program *prog, bool needs_copy);
 
@@ -251,6 +252,7 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		      bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
+void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 int bpf_map__pin(struct bpf_map *map, const char *path);
 
 long libbpf_get_error(const void *ptr);
-- 
cgit v1.2.3


From 9a94f277c4fb84815f450418d37bfc568d57b5cc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:38 -0700
Subject: tools: libbpf: restore the ability to load programs from .text
 section

libbpf used to be able to load programs from the default section
called '.text'.  It's not very common to leave sections unnamed,
but if it happens libbpf will fail to load the programs reporting
-EINVAL from the kernel.  The -EINVAL comes from bpf_obj_name_cpy()
because since 48cca7e44f9f ("libbpf: add support for bpf_call")
libbpf does not resolve program names for programs in '.text',
defaulting to '.text'.  '.text', however, does not pass the
(isalnum(*src) || *src == '_') check in bpf_obj_name_cpy().

With few extra lines of code we can limit the pseudo call
assumptions only to objects which actually contain code relocations.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 7bc02d93e277..e2401b95f08d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -234,6 +234,7 @@ struct bpf_object {
 	size_t nr_maps;
 
 	bool loaded;
+	bool has_pseudo_calls;
 
 	/*
 	 * Information when doing elf related work. Only valid if fd
@@ -400,10 +401,6 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 		const char *name = NULL;
 
 		prog = &obj->programs[pi];
-		if (prog->idx == obj->efile.text_shndx) {
-			name = ".text";
-			goto skip_search;
-		}
 
 		for (si = 0; si < symbols->d_size / sizeof(GElf_Sym) && !name;
 		     si++) {
@@ -426,12 +423,15 @@ bpf_object__init_prog_names(struct bpf_object *obj)
 			}
 		}
 
+		if (!name && prog->idx == obj->efile.text_shndx)
+			name = ".text";
+
 		if (!name) {
 			pr_warning("failed to find sym for prog %s\n",
 				   prog->section_name);
 			return -EINVAL;
 		}
-skip_search:
+
 		prog->name = strdup(name);
 		if (!prog->name) {
 			pr_warning("failed to allocate memory for prog sym %s\n",
@@ -981,6 +981,7 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 			prog->reloc_desc[i].type = RELO_CALL;
 			prog->reloc_desc[i].insn_idx = insn_idx;
 			prog->reloc_desc[i].text_off = sym.st_value;
+			obj->has_pseudo_calls = true;
 			continue;
 		}
 
@@ -1426,6 +1427,12 @@ out:
 	return err;
 }
 
+static bool bpf_program__is_function_storage(struct bpf_program *prog,
+					     struct bpf_object *obj)
+{
+	return prog->idx == obj->efile.text_shndx && obj->has_pseudo_calls;
+}
+
 static int
 bpf_object__load_progs(struct bpf_object *obj)
 {
@@ -1433,7 +1440,7 @@ bpf_object__load_progs(struct bpf_object *obj)
 	int err;
 
 	for (i = 0; i < obj->nr_programs; i++) {
-		if (obj->programs[i].idx == obj->efile.text_shndx)
+		if (bpf_program__is_function_storage(&obj->programs[i], obj))
 			continue;
 		err = bpf_program__load(&obj->programs[i],
 					obj->license,
@@ -2247,7 +2254,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 		bpf_program__set_expected_attach_type(prog,
 						      expected_attach_type);
 
-		if (prog->idx != obj->efile.text_shndx && !first_prog)
+		if (!bpf_program__is_function_storage(prog, obj) && !first_prog)
 			first_prog = prog;
 	}
 
-- 
cgit v1.2.3


From eac7d84519a35fc9fc8071b7d93803b2b075e2a7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:39 -0700
Subject: tools: libbpf: don't return '.text' as a program for multi-function
 programs

Make bpf_program__next() skip over '.text' section if object file
has pseudo calls.  The '.text' section is hardly a program in that
case, it's more of a storage for code of functions other than main.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index e2401b95f08d..38ed3e92e393 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1865,8 +1865,8 @@ void *bpf_object__priv(struct bpf_object *obj)
 	return obj ? obj->priv : ERR_PTR(-EINVAL);
 }
 
-struct bpf_program *
-bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+static struct bpf_program *
+__bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 {
 	size_t idx;
 
@@ -1887,6 +1887,18 @@ bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
 	return &obj->programs[idx];
 }
 
+struct bpf_program *
+bpf_program__next(struct bpf_program *prev, struct bpf_object *obj)
+{
+	struct bpf_program *prog = prev;
+
+	do {
+		prog = __bpf_program__next(prog, obj);
+	} while (prog && bpf_program__is_function_storage(prog, obj));
+
+	return prog;
+}
+
 int bpf_program__set_priv(struct bpf_program *prog, void *priv,
 			  bpf_program_clear_priv_t clear_priv)
 {
-- 
cgit v1.2.3


From 71e07ddcdc03000e37acfc6e757f70c81a963d58 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:40 -0700
Subject: tools: bpftool: drop unnecessary Author comments

Drop my author comments, those are from the early days of
bpftool and make little sense in tree, where we have quite
a few people contributing and git to attribute the work.

While at it bump some copyrights.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/common.c | 2 --
 tools/bpf/bpftool/main.c   | 4 +---
 tools/bpf/bpftool/main.h   | 2 --
 tools/bpf/bpftool/map.c    | 2 --
 tools/bpf/bpftool/prog.c   | 4 +---
 5 files changed, 2 insertions(+), 12 deletions(-)

diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 32f9e397a6c0..b432daea4520 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #include <ctype.h>
 #include <errno.h>
 #include <fcntl.h>
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index eea7f14355f3..d15a62be6cf0 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #include <bfd.h>
 #include <ctype.h>
 #include <errno.h>
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 63fdb310b9a4..d39f7ef01d23 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #ifndef __BPF_TOOL_H
 #define __BPF_TOOL_H
 
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 097b1a5e046b..5989e1575ae4 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 05f42a46d6ed..fd8cd9b51621 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (C) 2017 Netronome Systems, Inc.
+ * Copyright (C) 2017-2018 Netronome Systems, Inc.
  *
  * This software is dual licensed under the GNU General License Version 2,
  * June 1991 as shown in the file COPYING in the top-level directory of this
@@ -31,8 +31,6 @@
  * SOFTWARE.
  */
 
-/* Author: Jakub Kicinski <kubakici@wp.pl> */
-
 #include <errno.h>
 #include <fcntl.h>
 #include <stdarg.h>
-- 
cgit v1.2.3


From ef347a340b1a8507c22ee3cf981cd5cd64188431 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:41 -0700
Subject: tools: bpftool: add missing --bpffs to completions

--bpffs is not suggested by bash completions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/bash-completion/bpftool | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 1e1083321643..b0b8022d3570 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -182,7 +182,7 @@ _bpftool()
     if [[ -z $object ]]; then
         case $cur in
             -*)
-                local c='--version --json --pretty'
+                local c='--version --json --pretty --bpffs'
                 COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
                 return 0
                 ;;
-- 
cgit v1.2.3


From 121c58bed01a45043381ce52b8556e851dbaa123 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 28 Jun 2018 14:41:42 -0700
Subject: tools: bpftool: deal with options upfront

Remove options (in getopt() sense, i.e. starting with a dash like
-n or --NAME) while parsing arguments for bash completions.  This
allows us to refer to position-dependent parameters better, and
complete options at any point.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/bash-completion/bpftool | 32 ++++++++++++++++++++-----------
 1 file changed, 21 insertions(+), 11 deletions(-)

diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index b0b8022d3570..fffd76f4998b 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -153,6 +153,13 @@ _bpftool()
     local cur prev words objword
     _init_completion || return
 
+    # Deal with options
+    if [[ ${words[cword]} == -* ]]; then
+        local c='--version --json --pretty --bpffs'
+        COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
+        return 0
+    fi
+
     # Deal with simplest keywords
     case $prev in
         help|hex|opcodes|visual)
@@ -172,20 +179,23 @@ _bpftool()
             ;;
     esac
 
-    # Search for object and command
-    local object command cmdword
-    for (( cmdword=1; cmdword < ${#words[@]}-1; cmdword++ )); do
-        [[ -n $object ]] && command=${words[cmdword]} && break
-        [[ ${words[cmdword]} != -* ]] && object=${words[cmdword]}
+    # Remove all options so completions don't have to deal with them.
+    local i
+    for (( i=1; i < ${#words[@]}; )); do
+        if [[ ${words[i]::1} == - ]]; then
+            words=( "${words[@]:0:i}" "${words[@]:i+1}" )
+            [[ $i -le $cword ]] && cword=$(( cword - 1 ))
+        else
+            i=$(( ++i ))
+        fi
     done
+    cur=${words[cword]}
+    prev=${words[cword - 1]}
 
-    if [[ -z $object ]]; then
+    local object=${words[1]} command=${words[2]}
+
+    if [[ -z $object || $cword -eq 1 ]]; then
         case $cur in
-            -*)
-                local c='--version --json --pretty --bpffs'
-                COMPREPLY=( $( compgen -W "$c" -- "$cur" ) )
-                return 0
-                ;;
             *)
                 COMPREPLY=( $( compgen -W "$( bpftool help 2>&1 | \
                     command sed \
-- 
cgit v1.2.3


From 73bf20ef3df262026c3470241ae4ac8196943ffa Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 18 Jun 2018 10:22:37 -0700
Subject: crypto: vmac - require a block cipher with 128-bit block size

The VMAC template assumes the block cipher has a 128-bit block size, but
it failed to check for that.  Thus it was possible to instantiate it
using a 64-bit block size cipher, e.g. "vmac(cast5)", causing
uninitialized memory to be used.

Add the needed check when instantiating the template.

Fixes: f1939f7c5645 ("crypto: vmac - New hash algorithm for intel_txt support")
Cc: <stable@vger.kernel.org> # v2.6.32+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/vmac.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/crypto/vmac.c b/crypto/vmac.c
index df76a816cfb2..3034454a3713 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -655,6 +655,10 @@ static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
 	if (IS_ERR(alg))
 		return PTR_ERR(alg);
 
+	err = -EINVAL;
+	if (alg->cra_blocksize != 16)
+		goto out_put_alg;
+
 	inst = shash_alloc_instance("vmac", alg);
 	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
-- 
cgit v1.2.3


From bb29648102335586e9a66289a1d98a0cb392b6e5 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 18 Jun 2018 10:22:38 -0700
Subject: crypto: vmac - separate tfm and request context

syzbot reported a crash in vmac_final() when multiple threads
concurrently use the same "vmac(aes)" transform through AF_ALG.  The bug
is pretty fundamental: the VMAC template doesn't separate per-request
state from per-tfm (per-key) state like the other hash algorithms do,
but rather stores it all in the tfm context.  That's wrong.

Also, vmac_final() incorrectly zeroes most of the state including the
derived keys and cached pseudorandom pad.  Therefore, only the first
VMAC invocation with a given key calculates the correct digest.

Fix these bugs by splitting the per-tfm state from the per-request state
and using the proper init/update/final sequencing for requests.

Reproducer for the crash:

    #include <linux/if_alg.h>
    #include <sys/socket.h>
    #include <unistd.h>

    int main()
    {
            int fd;
            struct sockaddr_alg addr = {
                    .salg_type = "hash",
                    .salg_name = "vmac(aes)",
            };
            char buf[256] = { 0 };

            fd = socket(AF_ALG, SOCK_SEQPACKET, 0);
            bind(fd, (void *)&addr, sizeof(addr));
            setsockopt(fd, SOL_ALG, ALG_SET_KEY, buf, 16);
            fork();
            fd = accept(fd, NULL, NULL);
            for (;;)
                    write(fd, buf, 256);
    }

The immediate cause of the crash is that vmac_ctx_t.partial_size exceeds
VMAC_NHBYTES, causing vmac_final() to memset() a negative length.

Reported-by: syzbot+264bca3a6e8d645550d3@syzkaller.appspotmail.com
Fixes: f1939f7c5645 ("crypto: vmac - New hash algorithm for intel_txt support")
Cc: <stable@vger.kernel.org> # v2.6.32+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/vmac.c         | 408 ++++++++++++++++++++++----------------------------
 include/crypto/vmac.h |  63 --------
 2 files changed, 181 insertions(+), 290 deletions(-)
 delete mode 100644 include/crypto/vmac.h

diff --git a/crypto/vmac.c b/crypto/vmac.c
index 3034454a3713..bb2fc787d615 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -1,6 +1,10 @@
 /*
- * Modified to interface to the Linux kernel
+ * VMAC: Message Authentication Code using Universal Hashing
+ *
+ * Reference: https://tools.ietf.org/html/draft-krovetz-vmac-01
+ *
  * Copyright (c) 2009, Intel Corporation.
+ * Copyright (c) 2018, Google Inc.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -16,14 +20,15 @@
  * Place - Suite 330, Boston, MA 02111-1307 USA.
  */
 
-/* --------------------------------------------------------------------------
- * VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai.
- * This implementation is herby placed in the public domain.
- * The authors offers no warranty. Use at your own risk.
- * Please send bug reports to the authors.
- * Last modified: 17 APR 08, 1700 PDT
- * ----------------------------------------------------------------------- */
+/*
+ * Derived from:
+ *	VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai.
+ *	This implementation is herby placed in the public domain.
+ *	The authors offers no warranty. Use at your own risk.
+ *	Last modified: 17 APR 08, 1700 PDT
+ */
 
+#include <asm/unaligned.h>
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/crypto.h>
@@ -31,9 +36,35 @@
 #include <linux/scatterlist.h>
 #include <asm/byteorder.h>
 #include <crypto/scatterwalk.h>
-#include <crypto/vmac.h>
 #include <crypto/internal/hash.h>
 
+/*
+ * User definable settings.
+ */
+#define VMAC_TAG_LEN	64
+#define VMAC_KEY_SIZE	128/* Must be 128, 192 or 256			*/
+#define VMAC_KEY_LEN	(VMAC_KEY_SIZE/8)
+#define VMAC_NHBYTES	128/* Must 2^i for any 3 < i < 13 Standard = 128*/
+
+/* per-transform (per-key) context */
+struct vmac_tfm_ctx {
+	struct crypto_cipher *cipher;
+	u64 nhkey[(VMAC_NHBYTES/8)+2*(VMAC_TAG_LEN/64-1)];
+	u64 polykey[2*VMAC_TAG_LEN/64];
+	u64 l3key[2*VMAC_TAG_LEN/64];
+};
+
+/* per-request context */
+struct vmac_desc_ctx {
+	union {
+		u8 partial[VMAC_NHBYTES];	/* partial block */
+		__le64 partial_words[VMAC_NHBYTES / 8];
+	};
+	unsigned int partial_size;	/* size of the partial block */
+	bool first_block_processed;
+	u64 polytmp[2*VMAC_TAG_LEN/64];	/* running total of L2-hash */
+};
+
 /*
  * Constants and masks
  */
@@ -318,13 +349,6 @@ static void poly_step_func(u64 *ahi, u64 *alo,
 	} while (0)
 #endif
 
-static void vhash_abort(struct vmac_ctx *ctx)
-{
-	ctx->polytmp[0] = ctx->polykey[0] ;
-	ctx->polytmp[1] = ctx->polykey[1] ;
-	ctx->first_block_processed = 0;
-}
-
 static u64 l3hash(u64 p1, u64 p2, u64 k1, u64 k2, u64 len)
 {
 	u64 rh, rl, t, z = 0;
@@ -364,280 +388,209 @@ static u64 l3hash(u64 p1, u64 p2, u64 k1, u64 k2, u64 len)
 	return rl;
 }
 
-static void vhash_update(const unsigned char *m,
-			unsigned int mbytes, /* Pos multiple of VMAC_NHBYTES */
-			struct vmac_ctx *ctx)
+/* L1 and L2-hash one or more VMAC_NHBYTES-byte blocks */
+static void vhash_blocks(const struct vmac_tfm_ctx *tctx,
+			 struct vmac_desc_ctx *dctx,
+			 const __le64 *mptr, unsigned int blocks)
 {
-	u64 rh, rl, *mptr;
-	const u64 *kptr = (u64 *)ctx->nhkey;
-	int i;
-	u64 ch, cl;
-	u64 pkh = ctx->polykey[0];
-	u64 pkl = ctx->polykey[1];
-
-	if (!mbytes)
-		return;
-
-	BUG_ON(mbytes % VMAC_NHBYTES);
-
-	mptr = (u64 *)m;
-	i = mbytes / VMAC_NHBYTES;  /* Must be non-zero */
-
-	ch = ctx->polytmp[0];
-	cl = ctx->polytmp[1];
-
-	if (!ctx->first_block_processed) {
-		ctx->first_block_processed = 1;
+	const u64 *kptr = tctx->nhkey;
+	const u64 pkh = tctx->polykey[0];
+	const u64 pkl = tctx->polykey[1];
+	u64 ch = dctx->polytmp[0];
+	u64 cl = dctx->polytmp[1];
+	u64 rh, rl;
+
+	if (!dctx->first_block_processed) {
+		dctx->first_block_processed = true;
 		nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl);
 		rh &= m62;
 		ADD128(ch, cl, rh, rl);
 		mptr += (VMAC_NHBYTES/sizeof(u64));
-		i--;
+		blocks--;
 	}
 
-	while (i--) {
+	while (blocks--) {
 		nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl);
 		rh &= m62;
 		poly_step(ch, cl, pkh, pkl, rh, rl);
 		mptr += (VMAC_NHBYTES/sizeof(u64));
 	}
 
-	ctx->polytmp[0] = ch;
-	ctx->polytmp[1] = cl;
+	dctx->polytmp[0] = ch;
+	dctx->polytmp[1] = cl;
 }
 
-static u64 vhash(unsigned char m[], unsigned int mbytes,
-			u64 *tagl, struct vmac_ctx *ctx)
+static int vmac_setkey(struct crypto_shash *tfm,
+		       const u8 *key, unsigned int keylen)
 {
-	u64 rh, rl, *mptr;
-	const u64 *kptr = (u64 *)ctx->nhkey;
-	int i, remaining;
-	u64 ch, cl;
-	u64 pkh = ctx->polykey[0];
-	u64 pkl = ctx->polykey[1];
-
-	mptr = (u64 *)m;
-	i = mbytes / VMAC_NHBYTES;
-	remaining = mbytes % VMAC_NHBYTES;
-
-	if (ctx->first_block_processed) {
-		ch = ctx->polytmp[0];
-		cl = ctx->polytmp[1];
-	} else if (i) {
-		nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, ch, cl);
-		ch &= m62;
-		ADD128(ch, cl, pkh, pkl);
-		mptr += (VMAC_NHBYTES/sizeof(u64));
-		i--;
-	} else if (remaining) {
-		nh_16(mptr, kptr, 2*((remaining+15)/16), ch, cl);
-		ch &= m62;
-		ADD128(ch, cl, pkh, pkl);
-		mptr += (VMAC_NHBYTES/sizeof(u64));
-		goto do_l3;
-	} else {/* Empty String */
-		ch = pkh; cl = pkl;
-		goto do_l3;
-	}
-
-	while (i--) {
-		nh_vmac_nhbytes(mptr, kptr, VMAC_NHBYTES/8, rh, rl);
-		rh &= m62;
-		poly_step(ch, cl, pkh, pkl, rh, rl);
-		mptr += (VMAC_NHBYTES/sizeof(u64));
-	}
-	if (remaining) {
-		nh_16(mptr, kptr, 2*((remaining+15)/16), rh, rl);
-		rh &= m62;
-		poly_step(ch, cl, pkh, pkl, rh, rl);
-	}
-
-do_l3:
-	vhash_abort(ctx);
-	remaining *= 8;
-	return l3hash(ch, cl, ctx->l3key[0], ctx->l3key[1], remaining);
-}
+	struct vmac_tfm_ctx *tctx = crypto_shash_ctx(tfm);
+	__be64 out[2];
+	u8 in[16] = { 0 };
+	unsigned int i;
+	int err;
 
-static u64 vmac(unsigned char m[], unsigned int mbytes,
-			const unsigned char n[16], u64 *tagl,
-			struct vmac_ctx_t *ctx)
-{
-	u64 *in_n, *out_p;
-	u64 p, h;
-	int i;
-
-	in_n = ctx->__vmac_ctx.cached_nonce;
-	out_p = ctx->__vmac_ctx.cached_aes;
-
-	i = n[15] & 1;
-	if ((*(u64 *)(n+8) != in_n[1]) || (*(u64 *)(n) != in_n[0])) {
-		in_n[0] = *(u64 *)(n);
-		in_n[1] = *(u64 *)(n+8);
-		((unsigned char *)in_n)[15] &= 0xFE;
-		crypto_cipher_encrypt_one(ctx->child,
-			(unsigned char *)out_p, (unsigned char *)in_n);
-
-		((unsigned char *)in_n)[15] |= (unsigned char)(1-i);
+	if (keylen != VMAC_KEY_LEN) {
+		crypto_shash_set_flags(tfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
 	}
-	p = be64_to_cpup(out_p + i);
-	h = vhash(m, mbytes, (u64 *)0, &ctx->__vmac_ctx);
-	return le64_to_cpu(p + h);
-}
 
-static int vmac_set_key(unsigned char user_key[], struct vmac_ctx_t *ctx)
-{
-	u64 in[2] = {0}, out[2];
-	unsigned i;
-	int err = 0;
-
-	err = crypto_cipher_setkey(ctx->child, user_key, VMAC_KEY_LEN);
+	err = crypto_cipher_setkey(tctx->cipher, key, keylen);
 	if (err)
 		return err;
 
 	/* Fill nh key */
-	((unsigned char *)in)[0] = 0x80;
-	for (i = 0; i < sizeof(ctx->__vmac_ctx.nhkey)/8; i += 2) {
-		crypto_cipher_encrypt_one(ctx->child,
-			(unsigned char *)out, (unsigned char *)in);
-		ctx->__vmac_ctx.nhkey[i] = be64_to_cpup(out);
-		ctx->__vmac_ctx.nhkey[i+1] = be64_to_cpup(out+1);
-		((unsigned char *)in)[15] += 1;
+	in[0] = 0x80;
+	for (i = 0; i < ARRAY_SIZE(tctx->nhkey); i += 2) {
+		crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in);
+		tctx->nhkey[i] = be64_to_cpu(out[0]);
+		tctx->nhkey[i+1] = be64_to_cpu(out[1]);
+		in[15]++;
 	}
 
 	/* Fill poly key */
-	((unsigned char *)in)[0] = 0xC0;
-	in[1] = 0;
-	for (i = 0; i < sizeof(ctx->__vmac_ctx.polykey)/8; i += 2) {
-		crypto_cipher_encrypt_one(ctx->child,
-			(unsigned char *)out, (unsigned char *)in);
-		ctx->__vmac_ctx.polytmp[i] =
-			ctx->__vmac_ctx.polykey[i] =
-				be64_to_cpup(out) & mpoly;
-		ctx->__vmac_ctx.polytmp[i+1] =
-			ctx->__vmac_ctx.polykey[i+1] =
-				be64_to_cpup(out+1) & mpoly;
-		((unsigned char *)in)[15] += 1;
+	in[0] = 0xC0;
+	in[15] = 0;
+	for (i = 0; i < ARRAY_SIZE(tctx->polykey); i += 2) {
+		crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in);
+		tctx->polykey[i] = be64_to_cpu(out[0]) & mpoly;
+		tctx->polykey[i+1] = be64_to_cpu(out[1]) & mpoly;
+		in[15]++;
 	}
 
 	/* Fill ip key */
-	((unsigned char *)in)[0] = 0xE0;
-	in[1] = 0;
-	for (i = 0; i < sizeof(ctx->__vmac_ctx.l3key)/8; i += 2) {
+	in[0] = 0xE0;
+	in[15] = 0;
+	for (i = 0; i < ARRAY_SIZE(tctx->l3key); i += 2) {
 		do {
-			crypto_cipher_encrypt_one(ctx->child,
-				(unsigned char *)out, (unsigned char *)in);
-			ctx->__vmac_ctx.l3key[i] = be64_to_cpup(out);
-			ctx->__vmac_ctx.l3key[i+1] = be64_to_cpup(out+1);
-			((unsigned char *)in)[15] += 1;
-		} while (ctx->__vmac_ctx.l3key[i] >= p64
-			|| ctx->__vmac_ctx.l3key[i+1] >= p64);
+			crypto_cipher_encrypt_one(tctx->cipher, (u8 *)out, in);
+			tctx->l3key[i] = be64_to_cpu(out[0]);
+			tctx->l3key[i+1] = be64_to_cpu(out[1]);
+			in[15]++;
+		} while (tctx->l3key[i] >= p64 || tctx->l3key[i+1] >= p64);
 	}
 
-	/* Invalidate nonce/aes cache and reset other elements */
-	ctx->__vmac_ctx.cached_nonce[0] = (u64)-1; /* Ensure illegal nonce */
-	ctx->__vmac_ctx.cached_nonce[1] = (u64)0;  /* Ensure illegal nonce */
-	ctx->__vmac_ctx.first_block_processed = 0;
-
-	return err;
+	return 0;
 }
 
-static int vmac_setkey(struct crypto_shash *parent,
-		const u8 *key, unsigned int keylen)
+static int vmac_init(struct shash_desc *desc)
 {
-	struct vmac_ctx_t *ctx = crypto_shash_ctx(parent);
-
-	if (keylen != VMAC_KEY_LEN) {
-		crypto_shash_set_flags(parent, CRYPTO_TFM_RES_BAD_KEY_LEN);
-		return -EINVAL;
-	}
-
-	return vmac_set_key((u8 *)key, ctx);
-}
+	const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
 
-static int vmac_init(struct shash_desc *pdesc)
-{
+	dctx->partial_size = 0;
+	dctx->first_block_processed = false;
+	memcpy(dctx->polytmp, tctx->polykey, sizeof(dctx->polytmp));
 	return 0;
 }
 
-static int vmac_update(struct shash_desc *pdesc, const u8 *p,
-		unsigned int len)
+static int vmac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
 {
-	struct crypto_shash *parent = pdesc->tfm;
-	struct vmac_ctx_t *ctx = crypto_shash_ctx(parent);
-	int expand;
-	int min;
-
-	expand = VMAC_NHBYTES - ctx->partial_size > 0 ?
-			VMAC_NHBYTES - ctx->partial_size : 0;
-
-	min = len < expand ? len : expand;
-
-	memcpy(ctx->partial + ctx->partial_size, p, min);
-	ctx->partial_size += min;
-
-	if (len < expand)
-		return 0;
-
-	vhash_update(ctx->partial, VMAC_NHBYTES, &ctx->__vmac_ctx);
-	ctx->partial_size = 0;
-
-	len -= expand;
-	p += expand;
+	const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
+	unsigned int n;
+
+	if (dctx->partial_size) {
+		n = min(len, VMAC_NHBYTES - dctx->partial_size);
+		memcpy(&dctx->partial[dctx->partial_size], p, n);
+		dctx->partial_size += n;
+		p += n;
+		len -= n;
+		if (dctx->partial_size == VMAC_NHBYTES) {
+			vhash_blocks(tctx, dctx, dctx->partial_words, 1);
+			dctx->partial_size = 0;
+		}
+	}
 
-	if (len % VMAC_NHBYTES) {
-		memcpy(ctx->partial, p + len - (len % VMAC_NHBYTES),
-			len % VMAC_NHBYTES);
-		ctx->partial_size = len % VMAC_NHBYTES;
+	if (len >= VMAC_NHBYTES) {
+		n = round_down(len, VMAC_NHBYTES);
+		/* TODO: 'p' may be misaligned here */
+		vhash_blocks(tctx, dctx, (const __le64 *)p, n / VMAC_NHBYTES);
+		p += n;
+		len -= n;
 	}
 
-	vhash_update(p, len - len % VMAC_NHBYTES, &ctx->__vmac_ctx);
+	if (len) {
+		memcpy(dctx->partial, p, len);
+		dctx->partial_size = len;
+	}
 
 	return 0;
 }
 
-static int vmac_final(struct shash_desc *pdesc, u8 *out)
+static u64 vhash_final(const struct vmac_tfm_ctx *tctx,
+		       struct vmac_desc_ctx *dctx)
 {
-	struct crypto_shash *parent = pdesc->tfm;
-	struct vmac_ctx_t *ctx = crypto_shash_ctx(parent);
-	vmac_t mac;
-	u8 nonce[16] = {};
-
-	/* vmac() ends up accessing outside the array bounds that
-	 * we specify.  In appears to access up to the next 2-word
-	 * boundary.  We'll just be uber cautious and zero the
-	 * unwritten bytes in the buffer.
-	 */
-	if (ctx->partial_size) {
-		memset(ctx->partial + ctx->partial_size, 0,
-			VMAC_NHBYTES - ctx->partial_size);
+	unsigned int partial = dctx->partial_size;
+	u64 ch = dctx->polytmp[0];
+	u64 cl = dctx->polytmp[1];
+
+	/* L1 and L2-hash the final block if needed */
+	if (partial) {
+		/* Zero-pad to next 128-bit boundary */
+		unsigned int n = round_up(partial, 16);
+		u64 rh, rl;
+
+		memset(&dctx->partial[partial], 0, n - partial);
+		nh_16(dctx->partial_words, tctx->nhkey, n / 8, rh, rl);
+		rh &= m62;
+		if (dctx->first_block_processed)
+			poly_step(ch, cl, tctx->polykey[0], tctx->polykey[1],
+				  rh, rl);
+		else
+			ADD128(ch, cl, rh, rl);
 	}
-	mac = vmac(ctx->partial, ctx->partial_size, nonce, NULL, ctx);
-	memcpy(out, &mac, sizeof(vmac_t));
-	memzero_explicit(&mac, sizeof(vmac_t));
-	memset(&ctx->__vmac_ctx, 0, sizeof(struct vmac_ctx));
-	ctx->partial_size = 0;
+
+	/* L3-hash the 128-bit output of L2-hash */
+	return l3hash(ch, cl, tctx->l3key[0], tctx->l3key[1], partial * 8);
+}
+
+static int vmac_final(struct shash_desc *desc, u8 *out)
+{
+	const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
+	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
+	static const u8 nonce[16] = {}; /* TODO: this is insecure */
+	union {
+		u8 bytes[16];
+		__be64 pads[2];
+	} block;
+	int index;
+	u64 hash, pad;
+
+	/* Finish calculating the VHASH of the message */
+	hash = vhash_final(tctx, dctx);
+
+	/* Generate pseudorandom pad by encrypting the nonce */
+	memcpy(&block, nonce, 16);
+	index = block.bytes[15] & 1;
+	block.bytes[15] &= ~1;
+	crypto_cipher_encrypt_one(tctx->cipher, block.bytes, block.bytes);
+	pad = be64_to_cpu(block.pads[index]);
+
+	/* The VMAC is the sum of VHASH and the pseudorandom pad */
+	put_unaligned_le64(hash + pad, out);
 	return 0;
 }
 
 static int vmac_init_tfm(struct crypto_tfm *tfm)
 {
-	struct crypto_cipher *cipher;
-	struct crypto_instance *inst = (void *)tfm->__crt_alg;
+	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
 	struct crypto_spawn *spawn = crypto_instance_ctx(inst);
-	struct vmac_ctx_t *ctx = crypto_tfm_ctx(tfm);
+	struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
+	struct crypto_cipher *cipher;
 
 	cipher = crypto_spawn_cipher(spawn);
 	if (IS_ERR(cipher))
 		return PTR_ERR(cipher);
 
-	ctx->child = cipher;
+	tctx->cipher = cipher;
 	return 0;
 }
 
 static void vmac_exit_tfm(struct crypto_tfm *tfm)
 {
-	struct vmac_ctx_t *ctx = crypto_tfm_ctx(tfm);
-	crypto_free_cipher(ctx->child);
+	struct vmac_tfm_ctx *tctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_cipher(tctx->cipher);
 }
 
 static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
@@ -674,11 +627,12 @@ static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
 	inst->alg.base.cra_blocksize = alg->cra_blocksize;
 	inst->alg.base.cra_alignmask = alg->cra_alignmask;
 
-	inst->alg.digestsize = sizeof(vmac_t);
-	inst->alg.base.cra_ctxsize = sizeof(struct vmac_ctx_t);
+	inst->alg.base.cra_ctxsize = sizeof(struct vmac_tfm_ctx);
 	inst->alg.base.cra_init = vmac_init_tfm;
 	inst->alg.base.cra_exit = vmac_exit_tfm;
 
+	inst->alg.descsize = sizeof(struct vmac_desc_ctx);
+	inst->alg.digestsize = VMAC_TAG_LEN / 8;
 	inst->alg.init = vmac_init;
 	inst->alg.update = vmac_update;
 	inst->alg.final = vmac_final;
diff --git a/include/crypto/vmac.h b/include/crypto/vmac.h
deleted file mode 100644
index 6b700c7b2fe1..000000000000
--- a/include/crypto/vmac.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Modified to interface to the Linux kernel
- * Copyright (c) 2009, Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- *
- * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc., 59 Temple
- * Place - Suite 330, Boston, MA 02111-1307 USA.
- */
-
-#ifndef __CRYPTO_VMAC_H
-#define __CRYPTO_VMAC_H
-
-/* --------------------------------------------------------------------------
- * VMAC and VHASH Implementation by Ted Krovetz (tdk@acm.org) and Wei Dai.
- * This implementation is herby placed in the public domain.
- * The authors offers no warranty. Use at your own risk.
- * Please send bug reports to the authors.
- * Last modified: 17 APR 08, 1700 PDT
- * ----------------------------------------------------------------------- */
-
-/*
- * User definable settings.
- */
-#define VMAC_TAG_LEN	64
-#define VMAC_KEY_SIZE	128/* Must be 128, 192 or 256			*/
-#define VMAC_KEY_LEN	(VMAC_KEY_SIZE/8)
-#define VMAC_NHBYTES	128/* Must 2^i for any 3 < i < 13 Standard = 128*/
-
-/*
- * This implementation uses u32 and u64 as names for unsigned 32-
- * and 64-bit integer types. These are defined in C99 stdint.h. The
- * following may need adaptation if you are not running a C99 or
- * Microsoft C environment.
- */
-struct vmac_ctx {
-	u64 nhkey[(VMAC_NHBYTES/8)+2*(VMAC_TAG_LEN/64-1)];
-	u64 polykey[2*VMAC_TAG_LEN/64];
-	u64 l3key[2*VMAC_TAG_LEN/64];
-	u64 polytmp[2*VMAC_TAG_LEN/64];
-	u64 cached_nonce[2];
-	u64 cached_aes[2];
-	int first_block_processed;
-};
-
-typedef u64 vmac_t;
-
-struct vmac_ctx_t {
-	struct crypto_cipher *child;
-	struct vmac_ctx __vmac_ctx;
-	u8 partial[VMAC_NHBYTES];	/* partial block */
-	int partial_size;		/* size of the partial block */
-};
-
-#endif /* __CRYPTO_VMAC_H */
-- 
cgit v1.2.3


From ed331adab35bcddc595dae066522ca6336ee9210 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 18 Jun 2018 10:22:39 -0700
Subject: crypto: vmac - add nonced version with big endian digest

Currently the VMAC template uses a "nonce" hardcoded to 0, which makes
it insecure unless a unique key is set for every message.  Also, the
endianness of the final digest is wrong: the implementation uses little
endian, but the VMAC specification has it as big endian, as do other
VMAC implementations such as the one in Crypto++.

Add a new VMAC template where the nonce is passed as the first 16 bytes
of data (similar to what is done for Poly1305's nonce), and the digest
is big endian.  Call it "vmac64", since the old name of simply "vmac"
didn't clarify whether the implementation is of VMAC-64 or of VMAC-128
(which produce 64-bit and 128-bit digests respectively); so we fix the
naming ambiguity too.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/testmgr.c |   6 +++
 crypto/testmgr.h | 155 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 crypto/vmac.c    | 130 +++++++++++++++++++++++++++++++++++++++-------
 3 files changed, 273 insertions(+), 18 deletions(-)

diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 11e45352fd0b..60a557b0f8d3 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -3483,6 +3483,12 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.hash = __VECS(aes_vmac128_tv_template)
 		}
+	}, {
+		.alg = "vmac64(aes)",
+		.test = alg_test_hash,
+		.suite = {
+			.hash = __VECS(vmac64_aes_tv_template)
+		}
 	}, {
 		.alg = "wp256",
 		.test = alg_test_hash,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index b950aa234e43..7b022c47a623 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -4705,6 +4705,161 @@ static const struct hash_testvec aes_vmac128_tv_template[] = {
 	},
 };
 
+static const char vmac64_string1[144] = {
+	'\0',     '\0',   '\0',   '\0',   '\0',   '\0',   '\0',   '\0',
+	'\0',     '\0',   '\0',   '\0',   '\0',   '\0',   '\0',   '\0',
+	'\x01', '\x01', '\x01', '\x01', '\x02', '\x03', '\x02', '\x02',
+	'\x02', '\x04', '\x01', '\x07', '\x04', '\x01', '\x04', '\x03',
+};
+
+static const char vmac64_string2[144] = {
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	 'a',  'b',  'c',
+};
+
+static const char vmac64_string3[144] = {
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	 'a',  'b',  'c',  'a',  'b',  'c',  'a',  'b',
+	 'c',  'a',  'b',  'c',  'a',  'b',  'c',  'a',
+	 'b',  'c',  'a',  'b',  'c',  'a',  'b',  'c',
+	 'a',  'b',  'c',  'a',  'b',  'c',  'a',  'b',
+	 'c',  'a',  'b',  'c',  'a',  'b',  'c',  'a',
+	 'b',  'c',  'a',  'b',  'c',  'a',  'b',  'c',
+};
+
+static const char vmac64_string4[33] = {
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	'b',   'c',  'e',  'f',  'i',  'j',  'l',  'm',
+	'o',   'p',  'r',  's',  't',  'u',  'w',  'x',
+	'z',
+};
+
+static const char vmac64_string5[143] = {
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	 'r',  'm',  'b',  't',  'c',  'o',  'l',  'k',
+	 ']',  '%',  '9',  '2',  '7',  '!',  'A',
+};
+
+static const char vmac64_string6[145] = {
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	'\0', '\0', '\0', '\0', '\0', '\0', '\0', '\0',
+	 'p',  't',  '*',  '7',  'l',  'i',  '!',  '#',
+	 'w',  '0',  'z',  '/',  '4',  'A',  'n',
+};
+
+static const struct hash_testvec vmac64_aes_tv_template[] = {
+	{ /* draft-krovetz-vmac-01 test vector 1 */
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = "\0\0\0\0\0\0\0\0bcdefghi",
+		.psize	= 16,
+		.digest	= "\x25\x76\xbe\x1c\x56\xd8\xb8\x1b",
+	}, { /* draft-krovetz-vmac-01 test vector 2 */
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = "\0\0\0\0\0\0\0\0bcdefghiabc",
+		.psize	= 19,
+		.digest	= "\x2d\x37\x6c\xf5\xb1\x81\x3c\xe5",
+	}, { /* draft-krovetz-vmac-01 test vector 3 */
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = "\0\0\0\0\0\0\0\0bcdefghi"
+			  "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc",
+		.psize	= 64,
+		.digest	= "\xe8\x42\x1f\x61\xd5\x73\xd2\x98",
+	}, { /* draft-krovetz-vmac-01 test vector 4 */
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = "\0\0\0\0\0\0\0\0bcdefghi"
+			  "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc"
+			  "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc"
+			  "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc"
+			  "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc"
+			  "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabcabc"
+			  "abcabcabcabcabcabcabcabcabcabcabcabcabcabcabc",
+		.psize	= 316,
+		.digest	= "\x44\x92\xdf\x6c\x5c\xac\x1b\xbe",
+		.tap	= { 1, 100, 200, 15 },
+		.np	= 4,
+	}, {
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ksize	= 16,
+		.plaintext = "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize	= 16,
+		.digest	= "\x54\x7b\xa4\x77\x35\x80\x58\x07",
+	}, {
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ksize	= 16,
+		.plaintext = vmac64_string1,
+		.psize	= sizeof(vmac64_string1),
+		.digest	= "\xa1\x8c\x68\xae\xd3\x3c\xf5\xce",
+	}, {
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ksize	= 16,
+		.plaintext = vmac64_string2,
+		.psize	= sizeof(vmac64_string2),
+		.digest	= "\x2d\x14\xbd\x81\x73\xb0\x27\xc9",
+	}, {
+		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
+			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
+		.ksize	= 16,
+		.plaintext = vmac64_string3,
+		.psize	= sizeof(vmac64_string3),
+		.digest	= "\x19\x0b\x47\x98\x8c\x95\x1a\x8d",
+	}, {
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = "\x00\x00\x00\x00\x00\x00\x00\x00"
+			  "\x00\x00\x00\x00\x00\x00\x00\x00",
+		.psize	= 16,
+		.digest	= "\x84\x8f\x55\x9e\x26\xa1\x89\x3b",
+	}, {
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = vmac64_string1,
+		.psize	= sizeof(vmac64_string1),
+		.digest	= "\xc2\x74\x8d\xf6\xb0\xab\x5e\xab",
+	}, {
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = vmac64_string2,
+		.psize	= sizeof(vmac64_string2),
+		.digest	= "\xdf\x09\x7b\x3d\x42\x68\x15\x11",
+	}, {
+		.key	= "abcdefghijklmnop",
+		.ksize	= 16,
+		.plaintext = vmac64_string3,
+		.psize	= sizeof(vmac64_string3),
+		.digest	= "\xd4\xfa\x8f\xed\xe1\x8f\x32\x8b",
+	}, {
+		.key	= "a09b5cd!f#07K\x00\x00\x00",
+		.ksize	= 16,
+		.plaintext = vmac64_string4,
+		.psize	= sizeof(vmac64_string4),
+		.digest	= "\x5f\xa1\x4e\x42\xea\x0f\xa5\xab",
+	}, {
+		.key	= "a09b5cd!f#07K\x00\x00\x00",
+		.ksize	= 16,
+		.plaintext = vmac64_string5,
+		.psize	= sizeof(vmac64_string5),
+		.digest	= "\x60\x67\xe8\x1d\xbc\x98\x31\x25",
+	}, {
+		.key	= "a09b5cd!f#07K\x00\x00\x00",
+		.ksize	= 16,
+		.plaintext = vmac64_string6,
+		.psize	= sizeof(vmac64_string6),
+		.digest	= "\x41\xeb\x65\x95\x47\x9b\xae\xc4",
+	},
+};
+
 /*
  * SHA384 HMAC test vectors from RFC4231
  */
diff --git a/crypto/vmac.c b/crypto/vmac.c
index bb2fc787d615..bf1e385bc684 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -45,6 +45,7 @@
 #define VMAC_KEY_SIZE	128/* Must be 128, 192 or 256			*/
 #define VMAC_KEY_LEN	(VMAC_KEY_SIZE/8)
 #define VMAC_NHBYTES	128/* Must 2^i for any 3 < i < 13 Standard = 128*/
+#define VMAC_NONCEBYTES	16
 
 /* per-transform (per-key) context */
 struct vmac_tfm_ctx {
@@ -63,6 +64,11 @@ struct vmac_desc_ctx {
 	unsigned int partial_size;	/* size of the partial block */
 	bool first_block_processed;
 	u64 polytmp[2*VMAC_TAG_LEN/64];	/* running total of L2-hash */
+	union {
+		u8 bytes[VMAC_NONCEBYTES];
+		__be64 pads[VMAC_NONCEBYTES / 8];
+	} nonce;
+	unsigned int nonce_size; /* nonce bytes filled so far */
 };
 
 /*
@@ -480,6 +486,17 @@ static int vmac_init(struct shash_desc *desc)
 	dctx->partial_size = 0;
 	dctx->first_block_processed = false;
 	memcpy(dctx->polytmp, tctx->polykey, sizeof(dctx->polytmp));
+	dctx->nonce_size = 0;
+	return 0;
+}
+
+static int vmac_init_with_hardcoded_nonce(struct shash_desc *desc)
+{
+	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
+
+	vmac_init(desc);
+	memset(&dctx->nonce, 0, VMAC_NONCEBYTES);
+	dctx->nonce_size = VMAC_NONCEBYTES;
 	return 0;
 }
 
@@ -489,6 +506,15 @@ static int vmac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
 	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
 	unsigned int n;
 
+	/* Nonce is passed as first VMAC_NONCEBYTES bytes of data */
+	if (dctx->nonce_size < VMAC_NONCEBYTES) {
+		n = min(len, VMAC_NONCEBYTES - dctx->nonce_size);
+		memcpy(&dctx->nonce.bytes[dctx->nonce_size], p, n);
+		dctx->nonce_size += n;
+		p += n;
+		len -= n;
+	}
+
 	if (dctx->partial_size) {
 		n = min(len, VMAC_NHBYTES - dctx->partial_size);
 		memcpy(&dctx->partial[dctx->partial_size], p, n);
@@ -544,30 +570,62 @@ static u64 vhash_final(const struct vmac_tfm_ctx *tctx,
 	return l3hash(ch, cl, tctx->l3key[0], tctx->l3key[1], partial * 8);
 }
 
-static int vmac_final(struct shash_desc *desc, u8 *out)
+static int __vmac_final(struct shash_desc *desc, u64 *mac)
 {
 	const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
-	static const u8 nonce[16] = {}; /* TODO: this is insecure */
-	union {
-		u8 bytes[16];
-		__be64 pads[2];
-	} block;
 	int index;
 	u64 hash, pad;
 
+	if (dctx->nonce_size != VMAC_NONCEBYTES)
+		return -EINVAL;
+
+	/*
+	 * The VMAC specification requires a nonce at least 1 bit shorter than
+	 * the block cipher's block length, so we actually only accept a 127-bit
+	 * nonce.  We define the unused bit to be the first one and require that
+	 * it be 0, so the needed prepending of a 0 bit is implicit.
+	 */
+	if (dctx->nonce.bytes[0] & 0x80)
+		return -EINVAL;
+
 	/* Finish calculating the VHASH of the message */
 	hash = vhash_final(tctx, dctx);
 
 	/* Generate pseudorandom pad by encrypting the nonce */
-	memcpy(&block, nonce, 16);
-	index = block.bytes[15] & 1;
-	block.bytes[15] &= ~1;
-	crypto_cipher_encrypt_one(tctx->cipher, block.bytes, block.bytes);
-	pad = be64_to_cpu(block.pads[index]);
+	BUILD_BUG_ON(VMAC_NONCEBYTES != 2 * (VMAC_TAG_LEN / 8));
+	index = dctx->nonce.bytes[VMAC_NONCEBYTES - 1] & 1;
+	dctx->nonce.bytes[VMAC_NONCEBYTES - 1] &= ~1;
+	crypto_cipher_encrypt_one(tctx->cipher, dctx->nonce.bytes,
+				  dctx->nonce.bytes);
+	pad = be64_to_cpu(dctx->nonce.pads[index]);
 
 	/* The VMAC is the sum of VHASH and the pseudorandom pad */
-	put_unaligned_le64(hash + pad, out);
+	*mac = hash + pad;
+	return 0;
+}
+
+static int vmac_final_le(struct shash_desc *desc, u8 *out)
+{
+	u64 mac;
+	int err;
+
+	err = __vmac_final(desc, &mac);
+	if (err)
+		return err;
+	put_unaligned_le64(mac, out);
+	return 0;
+}
+
+static int vmac_final_be(struct shash_desc *desc, u8 *out)
+{
+	u64 mac;
+	int err;
+
+	err = __vmac_final(desc, &mac);
+	if (err)
+		return err;
+	put_unaligned_be64(mac, out);
 	return 0;
 }
 
@@ -593,7 +651,8 @@ static void vmac_exit_tfm(struct crypto_tfm *tfm)
 	crypto_free_cipher(tctx->cipher);
 }
 
-static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
+static int vmac_create_common(struct crypto_template *tmpl, struct rtattr **tb,
+			      bool vmac64)
 {
 	struct shash_instance *inst;
 	struct crypto_alg *alg;
@@ -609,10 +668,10 @@ static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
 		return PTR_ERR(alg);
 
 	err = -EINVAL;
-	if (alg->cra_blocksize != 16)
+	if (alg->cra_blocksize != VMAC_NONCEBYTES)
 		goto out_put_alg;
 
-	inst = shash_alloc_instance("vmac", alg);
+	inst = shash_alloc_instance(tmpl->name, alg);
 	err = PTR_ERR(inst);
 	if (IS_ERR(inst))
 		goto out_put_alg;
@@ -633,9 +692,15 @@ static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
 
 	inst->alg.descsize = sizeof(struct vmac_desc_ctx);
 	inst->alg.digestsize = VMAC_TAG_LEN / 8;
-	inst->alg.init = vmac_init;
+	if (vmac64) {
+		inst->alg.init = vmac_init;
+		inst->alg.final = vmac_final_be;
+	} else {
+		pr_warn("vmac: using insecure hardcoded nonce\n");
+		inst->alg.init = vmac_init_with_hardcoded_nonce;
+		inst->alg.final = vmac_final_le;
+	}
 	inst->alg.update = vmac_update;
-	inst->alg.final = vmac_final;
 	inst->alg.setkey = vmac_setkey;
 
 	err = shash_register_instance(tmpl, inst);
@@ -649,6 +714,16 @@ out_put_alg:
 	return err;
 }
 
+static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	return vmac_create_common(tmpl, tb, false);
+}
+
+static int vmac64_create(struct crypto_template *tmpl, struct rtattr **tb)
+{
+	return vmac_create_common(tmpl, tb, true);
+}
+
 static struct crypto_template vmac_tmpl = {
 	.name = "vmac",
 	.create = vmac_create,
@@ -656,14 +731,32 @@ static struct crypto_template vmac_tmpl = {
 	.module = THIS_MODULE,
 };
 
+static struct crypto_template vmac64_tmpl = {
+	.name = "vmac64",
+	.create = vmac64_create,
+	.free = shash_free_instance,
+	.module = THIS_MODULE,
+};
+
 static int __init vmac_module_init(void)
 {
-	return crypto_register_template(&vmac_tmpl);
+	int err;
+
+	err = crypto_register_template(&vmac_tmpl);
+	if (err)
+		return err;
+
+	err = crypto_register_template(&vmac64_tmpl);
+	if (err)
+		crypto_unregister_template(&vmac_tmpl);
+
+	return err;
 }
 
 static void __exit vmac_module_exit(void)
 {
 	crypto_unregister_template(&vmac_tmpl);
+	crypto_unregister_template(&vmac64_tmpl);
 }
 
 module_init(vmac_module_init);
@@ -672,3 +765,4 @@ module_exit(vmac_module_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("VMAC hash algorithm");
 MODULE_ALIAS_CRYPTO("vmac");
+MODULE_ALIAS_CRYPTO("vmac64");
-- 
cgit v1.2.3


From 0917b873127cebd4a259b92d43af5963484981ae Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 18 Jun 2018 10:22:40 -0700
Subject: crypto: vmac - remove insecure version with hardcoded nonce

Remove the original version of the VMAC template that had the nonce
hardcoded to 0 and produced a digest with the wrong endianness.  I'm
unsure whether this had users or not (there are no explicit in-kernel
references to it), but given that the hardcoded nonce made it wildly
insecure unless a unique key was used for each message, let's try
removing it and see if anyone complains.

Leave the new "vmac64" template that requires the nonce to be explicitly
specified as the first 16 bytes of data and uses the correct endianness
for the digest.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/tcrypt.c  |   2 +-
 crypto/testmgr.c |   6 ----
 crypto/testmgr.h | 102 -------------------------------------------------------
 crypto/vmac.c    |  84 ++++-----------------------------------------
 4 files changed, 8 insertions(+), 186 deletions(-)

diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index d5bcdd905007..078ec36007bf 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1939,7 +1939,7 @@ static int do_test(const char *alg, u32 type, u32 mask, int m, u32 num_mb)
 		break;
 
 	case 109:
-		ret += tcrypt_test("vmac(aes)");
+		ret += tcrypt_test("vmac64(aes)");
 		break;
 
 	case 111:
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 60a557b0f8d3..63f263fd1dae 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -3477,12 +3477,6 @@ static const struct alg_test_desc alg_test_descs[] = {
 		.suite = {
 			.hash = __VECS(tgr192_tv_template)
 		}
-	}, {
-		.alg = "vmac(aes)",
-		.test = alg_test_hash,
-		.suite = {
-			.hash = __VECS(aes_vmac128_tv_template)
-		}
 	}, {
 		.alg = "vmac64(aes)",
 		.test = alg_test_hash,
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 7b022c47a623..b6362169771a 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -4603,108 +4603,6 @@ static const struct hash_testvec aes_xcbc128_tv_template[] = {
 	}
 };
 
-static const char vmac_string1[128] = {'\x01', '\x01', '\x01', '\x01',
-				       '\x02', '\x03', '\x02', '\x02',
-				       '\x02', '\x04', '\x01', '\x07',
-				       '\x04', '\x01', '\x04', '\x03',};
-static const char vmac_string2[128] = {'a', 'b', 'c',};
-static const char vmac_string3[128] = {'a', 'b', 'c', 'a', 'b', 'c',
-				       'a', 'b', 'c', 'a', 'b', 'c',
-				       'a', 'b', 'c', 'a', 'b', 'c',
-				       'a', 'b', 'c', 'a', 'b', 'c',
-				       'a', 'b', 'c', 'a', 'b', 'c',
-				       'a', 'b', 'c', 'a', 'b', 'c',
-				       'a', 'b', 'c', 'a', 'b', 'c',
-				       'a', 'b', 'c', 'a', 'b', 'c',
-				      };
-
-static const char vmac_string4[17] = {'b', 'c', 'e', 'f',
-				      'i', 'j', 'l', 'm',
-				      'o', 'p', 'r', 's',
-				      't', 'u', 'w', 'x', 'z'};
-
-static const char vmac_string5[127] = {'r', 'm', 'b', 't', 'c',
-				       'o', 'l', 'k', ']', '%',
-				       '9', '2', '7', '!', 'A'};
-
-static const char vmac_string6[129] = {'p', 't', '*', '7', 'l',
-				       'i', '!', '#', 'w', '0',
-				       'z', '/', '4', 'A', 'n'};
-
-static const struct hash_testvec aes_vmac128_tv_template[] = {
-	{
-		.key	= "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.plaintext = NULL,
-		.digest	= "\x07\x58\x80\x35\x77\xa4\x7b\x54",
-		.psize	= 0,
-		.ksize	= 16,
-	}, {
-		.key    = "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.plaintext = vmac_string1,
-		.digest = "\xce\xf5\x3c\xd3\xae\x68\x8c\xa1",
-		.psize  = 128,
-		.ksize  = 16,
-	}, {
-		.key    = "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.plaintext = vmac_string2,
-		.digest = "\xc9\x27\xb0\x73\x81\xbd\x14\x2d",
-		.psize  = 128,
-		.ksize  = 16,
-	}, {
-		.key    = "\x00\x01\x02\x03\x04\x05\x06\x07"
-			  "\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f",
-		.plaintext = vmac_string3,
-		.digest = "\x8d\x1a\x95\x8c\x98\x47\x0b\x19",
-		.psize  = 128,
-		.ksize  = 16,
-	}, {
-		.key	= "abcdefghijklmnop",
-		.plaintext = NULL,
-		.digest	= "\x3b\x89\xa1\x26\x9e\x55\x8f\x84",
-		.psize	= 0,
-		.ksize	= 16,
-	}, {
-		.key    = "abcdefghijklmnop",
-		.plaintext = vmac_string1,
-		.digest = "\xab\x5e\xab\xb0\xf6\x8d\x74\xc2",
-		.psize  = 128,
-		.ksize  = 16,
-	}, {
-		.key    = "abcdefghijklmnop",
-		.plaintext = vmac_string2,
-		.digest = "\x11\x15\x68\x42\x3d\x7b\x09\xdf",
-		.psize  = 128,
-		.ksize  = 16,
-	}, {
-		.key    = "abcdefghijklmnop",
-		.plaintext = vmac_string3,
-		.digest = "\x8b\x32\x8f\xe1\xed\x8f\xfa\xd4",
-		.psize  = 128,
-		.ksize  = 16,
-	}, {
-		.key = "a09b5cd!f#07K\x00\x00\x00",
-		.plaintext = vmac_string4,
-		.digest = "\xab\xa5\x0f\xea\x42\x4e\xa1\x5f",
-		.psize = sizeof(vmac_string4),
-		.ksize = 16,
-	}, {
-		.key = "a09b5cd!f#07K\x00\x00\x00",
-		.plaintext = vmac_string5,
-		.digest = "\x25\x31\x98\xbc\x1d\xe8\x67\x60",
-		.psize = sizeof(vmac_string5),
-		.ksize = 16,
-	}, {
-		.key = "a09b5cd!f#07K\x00\x00\x00",
-		.plaintext = vmac_string6,
-		.digest = "\xc4\xae\x9b\x47\x95\x65\xeb\x41",
-		.psize = sizeof(vmac_string6),
-		.ksize = 16,
-	},
-};
-
 static const char vmac64_string1[144] = {
 	'\0',     '\0',   '\0',   '\0',   '\0',   '\0',   '\0',   '\0',
 	'\0',     '\0',   '\0',   '\0',   '\0',   '\0',   '\0',   '\0',
diff --git a/crypto/vmac.c b/crypto/vmac.c
index bf1e385bc684..5f436dfdfc61 100644
--- a/crypto/vmac.c
+++ b/crypto/vmac.c
@@ -490,16 +490,6 @@ static int vmac_init(struct shash_desc *desc)
 	return 0;
 }
 
-static int vmac_init_with_hardcoded_nonce(struct shash_desc *desc)
-{
-	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
-
-	vmac_init(desc);
-	memset(&dctx->nonce, 0, VMAC_NONCEBYTES);
-	dctx->nonce_size = VMAC_NONCEBYTES;
-	return 0;
-}
-
 static int vmac_update(struct shash_desc *desc, const u8 *p, unsigned int len)
 {
 	const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
@@ -570,7 +560,7 @@ static u64 vhash_final(const struct vmac_tfm_ctx *tctx,
 	return l3hash(ch, cl, tctx->l3key[0], tctx->l3key[1], partial * 8);
 }
 
-static int __vmac_final(struct shash_desc *desc, u64 *mac)
+static int vmac_final(struct shash_desc *desc, u8 *out)
 {
 	const struct vmac_tfm_ctx *tctx = crypto_shash_ctx(desc->tfm);
 	struct vmac_desc_ctx *dctx = shash_desc_ctx(desc);
@@ -601,31 +591,7 @@ static int __vmac_final(struct shash_desc *desc, u64 *mac)
 	pad = be64_to_cpu(dctx->nonce.pads[index]);
 
 	/* The VMAC is the sum of VHASH and the pseudorandom pad */
-	*mac = hash + pad;
-	return 0;
-}
-
-static int vmac_final_le(struct shash_desc *desc, u8 *out)
-{
-	u64 mac;
-	int err;
-
-	err = __vmac_final(desc, &mac);
-	if (err)
-		return err;
-	put_unaligned_le64(mac, out);
-	return 0;
-}
-
-static int vmac_final_be(struct shash_desc *desc, u8 *out)
-{
-	u64 mac;
-	int err;
-
-	err = __vmac_final(desc, &mac);
-	if (err)
-		return err;
-	put_unaligned_be64(mac, out);
+	put_unaligned_be64(hash + pad, out);
 	return 0;
 }
 
@@ -651,8 +617,7 @@ static void vmac_exit_tfm(struct crypto_tfm *tfm)
 	crypto_free_cipher(tctx->cipher);
 }
 
-static int vmac_create_common(struct crypto_template *tmpl, struct rtattr **tb,
-			      bool vmac64)
+static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
 {
 	struct shash_instance *inst;
 	struct crypto_alg *alg;
@@ -692,15 +657,9 @@ static int vmac_create_common(struct crypto_template *tmpl, struct rtattr **tb,
 
 	inst->alg.descsize = sizeof(struct vmac_desc_ctx);
 	inst->alg.digestsize = VMAC_TAG_LEN / 8;
-	if (vmac64) {
-		inst->alg.init = vmac_init;
-		inst->alg.final = vmac_final_be;
-	} else {
-		pr_warn("vmac: using insecure hardcoded nonce\n");
-		inst->alg.init = vmac_init_with_hardcoded_nonce;
-		inst->alg.final = vmac_final_le;
-	}
+	inst->alg.init = vmac_init;
 	inst->alg.update = vmac_update;
+	inst->alg.final = vmac_final;
 	inst->alg.setkey = vmac_setkey;
 
 	err = shash_register_instance(tmpl, inst);
@@ -714,48 +673,20 @@ out_put_alg:
 	return err;
 }
 
-static int vmac_create(struct crypto_template *tmpl, struct rtattr **tb)
-{
-	return vmac_create_common(tmpl, tb, false);
-}
-
-static int vmac64_create(struct crypto_template *tmpl, struct rtattr **tb)
-{
-	return vmac_create_common(tmpl, tb, true);
-}
-
-static struct crypto_template vmac_tmpl = {
-	.name = "vmac",
-	.create = vmac_create,
-	.free = shash_free_instance,
-	.module = THIS_MODULE,
-};
-
 static struct crypto_template vmac64_tmpl = {
 	.name = "vmac64",
-	.create = vmac64_create,
+	.create = vmac_create,
 	.free = shash_free_instance,
 	.module = THIS_MODULE,
 };
 
 static int __init vmac_module_init(void)
 {
-	int err;
-
-	err = crypto_register_template(&vmac_tmpl);
-	if (err)
-		return err;
-
-	err = crypto_register_template(&vmac64_tmpl);
-	if (err)
-		crypto_unregister_template(&vmac_tmpl);
-
-	return err;
+	return crypto_register_template(&vmac64_tmpl);
 }
 
 static void __exit vmac_module_exit(void)
 {
-	crypto_unregister_template(&vmac_tmpl);
 	crypto_unregister_template(&vmac64_tmpl);
 }
 
@@ -764,5 +695,4 @@ module_exit(vmac_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("VMAC hash algorithm");
-MODULE_ALIAS_CRYPTO("vmac");
 MODULE_ALIAS_CRYPTO("vmac64");
-- 
cgit v1.2.3


From b551bac14acab9c601269e2007a6b6cad2250a4c Mon Sep 17 00:00:00 2001
From: Farhan Ali <alifm@linux.ibm.com>
Date: Tue, 19 Jun 2018 11:41:33 -0400
Subject: crypto: virtio - Read crypto services and algorithm masks

Read the crypto services and algorithm masks which provides
information about the services and algorithms supported by
virtio-crypto backend.

Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
Acked-by: Gonglei <arei.gonglei@huawei.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/virtio/virtio_crypto_common.h | 14 ++++++++++++++
 drivers/crypto/virtio/virtio_crypto_core.c   | 29 ++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h
index 66501a5a2b7b..931a3bd5b51a 100644
--- a/drivers/crypto/virtio/virtio_crypto_common.h
+++ b/drivers/crypto/virtio/virtio_crypto_common.h
@@ -55,6 +55,20 @@ struct virtio_crypto {
 	/* Number of queue currently used by the driver */
 	u32 curr_queue;
 
+	/*
+	 * Specifies the services mask which the device support,
+	 * see VIRTIO_CRYPTO_SERVICE_*
+	 */
+	u32 crypto_services;
+
+	/* Detailed algorithms mask */
+	u32 cipher_algo_l;
+	u32 cipher_algo_h;
+	u32 hash_algo;
+	u32 mac_algo_l;
+	u32 mac_algo_h;
+	u32 aead_algo;
+
 	/* Maximum length of cipher key */
 	u32 max_cipher_key_len;
 	/* Maximum length of authenticated key */
diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index 83326986c113..8f745f28f78b 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -303,6 +303,13 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 	u32 max_data_queues = 0, max_cipher_key_len = 0;
 	u32 max_auth_key_len = 0;
 	u64 max_size = 0;
+	u32 cipher_algo_l = 0;
+	u32 cipher_algo_h = 0;
+	u32 hash_algo = 0;
+	u32 mac_algo_l = 0;
+	u32 mac_algo_h = 0;
+	u32 aead_algo = 0;
+	u32 crypto_services = 0;
 
 	if (!virtio_has_feature(vdev, VIRTIO_F_VERSION_1))
 		return -ENODEV;
@@ -339,6 +346,20 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 		max_auth_key_len, &max_auth_key_len);
 	virtio_cread(vdev, struct virtio_crypto_config,
 		max_size, &max_size);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		crypto_services, &crypto_services);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		cipher_algo_l, &cipher_algo_l);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		cipher_algo_h, &cipher_algo_h);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		hash_algo, &hash_algo);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		mac_algo_l, &mac_algo_l);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		mac_algo_h, &mac_algo_h);
+	virtio_cread(vdev, struct virtio_crypto_config,
+		aead_algo, &aead_algo);
 
 	/* Add virtio crypto device to global table */
 	err = virtcrypto_devmgr_add_dev(vcrypto);
@@ -358,6 +379,14 @@ static int virtcrypto_probe(struct virtio_device *vdev)
 	vcrypto->max_cipher_key_len = max_cipher_key_len;
 	vcrypto->max_auth_key_len = max_auth_key_len;
 	vcrypto->max_size = max_size;
+	vcrypto->crypto_services = crypto_services;
+	vcrypto->cipher_algo_l = cipher_algo_l;
+	vcrypto->cipher_algo_h = cipher_algo_h;
+	vcrypto->mac_algo_l = mac_algo_l;
+	vcrypto->mac_algo_h = mac_algo_h;
+	vcrypto->hash_algo = hash_algo;
+	vcrypto->aead_algo = aead_algo;
+
 
 	dev_info(&vdev->dev,
 		"max_queues: %u, max_cipher_key_len: %u, max_auth_key_len: %u, max_size 0x%llx\n",
-- 
cgit v1.2.3


From d0d859bb87ac3b4df1cb6692531fc95d093357c5 Mon Sep 17 00:00:00 2001
From: Farhan Ali <alifm@linux.vnet.ibm.com>
Date: Tue, 19 Jun 2018 11:41:34 -0400
Subject: crypto: virtio - Register an algo only if it's supported

Register a crypto algo with the Linux crypto layer only if
the algorithm is supported by the backend virtio-crypto
device.

Also route crypto requests to a virtio-crypto
device, only if it can support the requested service and
algorithm.

Signed-off-by: Farhan Ali <alifm@linux.ibm.com>
Acked-by: Gonglei <arei.gonglei@huawei.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/virtio/virtio_crypto_algs.c   | 112 ++++++++++++++++++---------
 drivers/crypto/virtio/virtio_crypto_common.h |  11 ++-
 drivers/crypto/virtio/virtio_crypto_mgr.c    |  81 +++++++++++++++++--
 3 files changed, 159 insertions(+), 45 deletions(-)

diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index af6a908dfa7a..7a104f636f11 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -49,12 +49,18 @@ struct virtio_crypto_sym_request {
 	bool encrypt;
 };
 
+struct virtio_crypto_algo {
+	uint32_t algonum;
+	uint32_t service;
+	unsigned int active_devs;
+	struct crypto_alg algo;
+};
+
 /*
  * The algs_lock protects the below global virtio_crypto_active_devs
  * and crypto algorithms registion.
  */
 static DEFINE_MUTEX(algs_lock);
-static unsigned int virtio_crypto_active_devs;
 static void virtio_crypto_ablkcipher_finalize_req(
 	struct virtio_crypto_sym_request *vc_sym_req,
 	struct ablkcipher_request *req,
@@ -312,15 +318,21 @@ static int virtio_crypto_ablkcipher_setkey(struct crypto_ablkcipher *tfm,
 					 unsigned int keylen)
 {
 	struct virtio_crypto_ablkcipher_ctx *ctx = crypto_ablkcipher_ctx(tfm);
+	uint32_t alg;
 	int ret;
 
+	ret = virtio_crypto_alg_validate_key(keylen, &alg);
+	if (ret)
+		return ret;
+
 	if (!ctx->vcrypto) {
 		/* New key */
 		int node = virtio_crypto_get_current_node();
 		struct virtio_crypto *vcrypto =
-				      virtcrypto_get_dev_node(node);
+				      virtcrypto_get_dev_node(node,
+				      VIRTIO_CRYPTO_SERVICE_CIPHER, alg);
 		if (!vcrypto) {
-			pr_err("virtio_crypto: Could not find a virtio device in the system\n");
+			pr_err("virtio_crypto: Could not find a virtio device in the system or unsupported algo\n");
 			return -ENODEV;
 		}
 
@@ -571,57 +583,85 @@ static void virtio_crypto_ablkcipher_finalize_req(
 	virtcrypto_clear_request(&vc_sym_req->base);
 }
 
-static struct crypto_alg virtio_crypto_algs[] = { {
-	.cra_name = "cbc(aes)",
-	.cra_driver_name = "virtio_crypto_aes_cbc",
-	.cra_priority = 150,
-	.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
-	.cra_blocksize = AES_BLOCK_SIZE,
-	.cra_ctxsize  = sizeof(struct virtio_crypto_ablkcipher_ctx),
-	.cra_alignmask = 0,
-	.cra_module = THIS_MODULE,
-	.cra_type = &crypto_ablkcipher_type,
-	.cra_init = virtio_crypto_ablkcipher_init,
-	.cra_exit = virtio_crypto_ablkcipher_exit,
-	.cra_u = {
-	   .ablkcipher = {
-			.setkey = virtio_crypto_ablkcipher_setkey,
-			.decrypt = virtio_crypto_ablkcipher_decrypt,
-			.encrypt = virtio_crypto_ablkcipher_encrypt,
-			.min_keysize = AES_MIN_KEY_SIZE,
-			.max_keysize = AES_MAX_KEY_SIZE,
-			.ivsize = AES_BLOCK_SIZE,
+static struct virtio_crypto_algo virtio_crypto_algs[] = { {
+	.algonum = VIRTIO_CRYPTO_CIPHER_AES_CBC,
+	.service = VIRTIO_CRYPTO_SERVICE_CIPHER,
+	.algo = {
+		.cra_name = "cbc(aes)",
+		.cra_driver_name = "virtio_crypto_aes_cbc",
+		.cra_priority = 150,
+		.cra_flags = CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC,
+		.cra_blocksize = AES_BLOCK_SIZE,
+		.cra_ctxsize  = sizeof(struct virtio_crypto_ablkcipher_ctx),
+		.cra_alignmask = 0,
+		.cra_module = THIS_MODULE,
+		.cra_type = &crypto_ablkcipher_type,
+		.cra_init = virtio_crypto_ablkcipher_init,
+		.cra_exit = virtio_crypto_ablkcipher_exit,
+		.cra_u = {
+			.ablkcipher = {
+				.setkey = virtio_crypto_ablkcipher_setkey,
+				.decrypt = virtio_crypto_ablkcipher_decrypt,
+				.encrypt = virtio_crypto_ablkcipher_encrypt,
+				.min_keysize = AES_MIN_KEY_SIZE,
+				.max_keysize = AES_MAX_KEY_SIZE,
+				.ivsize = AES_BLOCK_SIZE,
+			},
 		},
 	},
 } };
 
-int virtio_crypto_algs_register(void)
+int virtio_crypto_algs_register(struct virtio_crypto *vcrypto)
 {
 	int ret = 0;
+	int i = 0;
 
 	mutex_lock(&algs_lock);
-	if (++virtio_crypto_active_devs != 1)
-		goto unlock;
 
-	ret = crypto_register_algs(virtio_crypto_algs,
-			ARRAY_SIZE(virtio_crypto_algs));
-	if (ret)
-		virtio_crypto_active_devs--;
+	for (i = 0; i < ARRAY_SIZE(virtio_crypto_algs); i++) {
+
+		uint32_t service = virtio_crypto_algs[i].service;
+		uint32_t algonum = virtio_crypto_algs[i].algonum;
+
+		if (!virtcrypto_algo_is_supported(vcrypto, service, algonum))
+			continue;
+
+		if (virtio_crypto_algs[i].active_devs == 0) {
+			ret = crypto_register_alg(&virtio_crypto_algs[i].algo);
+			if (ret)
+				goto unlock;
+		}
+
+		virtio_crypto_algs[i].active_devs++;
+		dev_info(&vcrypto->vdev->dev, "Registered algo %s\n",
+			 virtio_crypto_algs[i].algo.cra_name);
+	}
 
 unlock:
 	mutex_unlock(&algs_lock);
 	return ret;
 }
 
-void virtio_crypto_algs_unregister(void)
+void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto)
 {
+	int i = 0;
+
 	mutex_lock(&algs_lock);
-	if (--virtio_crypto_active_devs != 0)
-		goto unlock;
 
-	crypto_unregister_algs(virtio_crypto_algs,
-			ARRAY_SIZE(virtio_crypto_algs));
+	for (i = 0; i < ARRAY_SIZE(virtio_crypto_algs); i++) {
+
+		uint32_t service = virtio_crypto_algs[i].service;
+		uint32_t algonum = virtio_crypto_algs[i].algonum;
+
+		if (virtio_crypto_algs[i].active_devs == 0 ||
+		    !virtcrypto_algo_is_supported(vcrypto, service, algonum))
+			continue;
+
+		if (virtio_crypto_algs[i].active_devs == 1)
+			crypto_unregister_alg(&virtio_crypto_algs[i].algo);
+
+		virtio_crypto_algs[i].active_devs--;
+	}
 
-unlock:
 	mutex_unlock(&algs_lock);
 }
diff --git a/drivers/crypto/virtio/virtio_crypto_common.h b/drivers/crypto/virtio/virtio_crypto_common.h
index 931a3bd5b51a..63ef7f7924ea 100644
--- a/drivers/crypto/virtio/virtio_crypto_common.h
+++ b/drivers/crypto/virtio/virtio_crypto_common.h
@@ -116,7 +116,12 @@ int virtcrypto_dev_in_use(struct virtio_crypto *vcrypto_dev);
 int virtcrypto_dev_get(struct virtio_crypto *vcrypto_dev);
 void virtcrypto_dev_put(struct virtio_crypto *vcrypto_dev);
 int virtcrypto_dev_started(struct virtio_crypto *vcrypto_dev);
-struct virtio_crypto *virtcrypto_get_dev_node(int node);
+bool virtcrypto_algo_is_supported(struct virtio_crypto *vcrypto_dev,
+				  uint32_t service,
+				  uint32_t algo);
+struct virtio_crypto *virtcrypto_get_dev_node(int node,
+					      uint32_t service,
+					      uint32_t algo);
 int virtcrypto_dev_start(struct virtio_crypto *vcrypto);
 void virtcrypto_dev_stop(struct virtio_crypto *vcrypto);
 int virtio_crypto_ablkcipher_crypt_req(
@@ -136,7 +141,7 @@ static inline int virtio_crypto_get_current_node(void)
 	return node;
 }
 
-int virtio_crypto_algs_register(void);
-void virtio_crypto_algs_unregister(void);
+int virtio_crypto_algs_register(struct virtio_crypto *vcrypto);
+void virtio_crypto_algs_unregister(struct virtio_crypto *vcrypto);
 
 #endif /* _VIRTIO_CRYPTO_COMMON_H */
diff --git a/drivers/crypto/virtio/virtio_crypto_mgr.c b/drivers/crypto/virtio/virtio_crypto_mgr.c
index a69ff71de2c4..d70de3a4f7d7 100644
--- a/drivers/crypto/virtio/virtio_crypto_mgr.c
+++ b/drivers/crypto/virtio/virtio_crypto_mgr.c
@@ -181,14 +181,20 @@ int virtcrypto_dev_started(struct virtio_crypto *vcrypto_dev)
 /*
  * virtcrypto_get_dev_node() - Get vcrypto_dev on the node.
  * @node:  Node id the driver works.
+ * @service: Crypto service that needs to be supported by the
+ *	      dev
+ * @algo: The algorithm number that needs to be supported by the
+ *	  dev
  *
- * Function returns the virtio crypto device used fewest on the node.
+ * Function returns the virtio crypto device used fewest on the node,
+ * and supports the given crypto service and algorithm.
  *
  * To be used by virtio crypto device specific drivers.
  *
  * Return: pointer to vcrypto_dev or NULL if not found.
  */
-struct virtio_crypto *virtcrypto_get_dev_node(int node)
+struct virtio_crypto *virtcrypto_get_dev_node(int node, uint32_t service,
+					      uint32_t algo)
 {
 	struct virtio_crypto *vcrypto_dev = NULL, *tmp_dev;
 	unsigned long best = ~0;
@@ -199,7 +205,8 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node)
 
 		if ((node == dev_to_node(&tmp_dev->vdev->dev) ||
 		     dev_to_node(&tmp_dev->vdev->dev) < 0) &&
-		    virtcrypto_dev_started(tmp_dev)) {
+		    virtcrypto_dev_started(tmp_dev) &&
+		    virtcrypto_algo_is_supported(tmp_dev, service, algo)) {
 			ctr = atomic_read(&tmp_dev->ref_count);
 			if (best > ctr) {
 				vcrypto_dev = tmp_dev;
@@ -214,7 +221,9 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node)
 		/* Get any started device */
 		list_for_each_entry(tmp_dev,
 				virtcrypto_devmgr_get_head(), list) {
-			if (virtcrypto_dev_started(tmp_dev)) {
+			if (virtcrypto_dev_started(tmp_dev) &&
+			    virtcrypto_algo_is_supported(tmp_dev,
+			    service, algo)) {
 				vcrypto_dev = tmp_dev;
 				break;
 			}
@@ -240,7 +249,7 @@ struct virtio_crypto *virtcrypto_get_dev_node(int node)
  */
 int virtcrypto_dev_start(struct virtio_crypto *vcrypto)
 {
-	if (virtio_crypto_algs_register()) {
+	if (virtio_crypto_algs_register(vcrypto)) {
 		pr_err("virtio_crypto: Failed to register crypto algs\n");
 		return -EFAULT;
 	}
@@ -260,5 +269,65 @@ int virtcrypto_dev_start(struct virtio_crypto *vcrypto)
  */
 void virtcrypto_dev_stop(struct virtio_crypto *vcrypto)
 {
-	virtio_crypto_algs_unregister();
+	virtio_crypto_algs_unregister(vcrypto);
+}
+
+/*
+ * vcrypto_algo_is_supported()
+ * @vcrypto: Pointer to virtio crypto device.
+ * @service: The bit number for service validate.
+ *	      See VIRTIO_CRYPTO_SERVICE_*
+ * @algo : The bit number for the algorithm to validate.
+ *
+ *
+ * Validate if the virtio crypto device supports a service and
+ * algo.
+ *
+ * Return true if device supports a service and algo.
+ */
+
+bool virtcrypto_algo_is_supported(struct virtio_crypto *vcrypto,
+				  uint32_t service,
+				  uint32_t algo)
+{
+	uint32_t service_mask = 1u << service;
+	uint32_t algo_mask = 0;
+	bool low = true;
+
+	if (algo > 31) {
+		algo -= 32;
+		low = false;
+	}
+
+	if (!(vcrypto->crypto_services & service_mask))
+		return false;
+
+	switch (service) {
+	case VIRTIO_CRYPTO_SERVICE_CIPHER:
+		if (low)
+			algo_mask = vcrypto->cipher_algo_l;
+		else
+			algo_mask = vcrypto->cipher_algo_h;
+		break;
+
+	case VIRTIO_CRYPTO_SERVICE_HASH:
+		algo_mask = vcrypto->hash_algo;
+		break;
+
+	case VIRTIO_CRYPTO_SERVICE_MAC:
+		if (low)
+			algo_mask = vcrypto->mac_algo_l;
+		else
+			algo_mask = vcrypto->mac_algo_h;
+		break;
+
+	case VIRTIO_CRYPTO_SERVICE_AEAD:
+		algo_mask = vcrypto->aead_algo;
+		break;
+	}
+
+	if (!(algo_mask & (1u << algo)))
+		return false;
+
+	return true;
 }
-- 
cgit v1.2.3


From e4e4730698c9138f09ed73dadd1f35d4bb95ada5 Mon Sep 17 00:00:00 2001
From: Denis Efremov <efremov@linux.com>
Date: Tue, 19 Jun 2018 23:23:57 +0300
Subject: crypto: skcipher - remove the exporting of skcipher_walk_next

The function skcipher_walk_next declared as static and marked as
EXPORT_SYMBOL_GPL. It's a bit confusing for internal function to be
exported. The area of visibility for such function is its .c file
and all other modules. Other *.c files of the same module can't use it,
despite all other modules can. Relying on the fact that this is the
internal function and it's not a crucial part of the API, the patch
just removes the EXPORT_SYMBOL_GPL marking of skcipher_walk_next.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Denis Efremov <efremov@linux.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/skcipher.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 0fe2a2923ad0..7d6a49fe3047 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -387,7 +387,6 @@ set_phys_lowmem:
 	}
 	return err;
 }
-EXPORT_SYMBOL_GPL(skcipher_walk_next);
 
 static int skcipher_copy_iv(struct skcipher_walk *walk)
 {
-- 
cgit v1.2.3


From 6d8e85ffe17895d7bc632dfbaa9e2e33b22fe873 Mon Sep 17 00:00:00 2001
From: Nathan Harold <nharold@google.com>
Date: Fri, 29 Jun 2018 15:07:10 -0700
Subject: xfrm: Allow Set Mark to be Updated Using UPDSA

Allow UPDSA to change "set mark" to permit
policy separation of packet routing decisions from
SA keying in systems that use mark-based routing.

The set mark, used as a routing and firewall mark
for outbound packets, is made update-able which
allows routing decisions to be handled independently
of keying/SA creation. To maintain consistency with
other optional attributes, the set mark is only
updated if sent with a non-zero value.

The per-SA lock and the xfrm_state_lock are taken in
that order to avoid a deadlock with
xfrm_timer_handler(), which also takes the locks in
that order.

Signed-off-by: Nathan Harold <nharold@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index e04a510ec992..c9ffcdfa89f6 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1562,6 +1562,15 @@ out:
 		if (x1->curlft.use_time)
 			xfrm_state_check_expire(x1);
 
+		if (x->props.smark.m || x->props.smark.v) {
+			spin_lock_bh(&net->xfrm.xfrm_state_lock);
+
+			x1->props.smark = x->props.smark;
+
+			__xfrm_state_bump_genids(x1);
+			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+		}
+
 		err = 0;
 		x->km.state = XFRM_STATE_DEAD;
 		__xfrm_state_put(x);
-- 
cgit v1.2.3


From e08015e7d6a4b5395e75cc286ab6400667c63dc0 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 21 Jun 2018 20:44:50 +0200
Subject: drm/pl111: Support Nomadik LCDC variant

The Nomadik has a variant of the PL110 known as "Color LCD
Controller" LCDC. This variant has the same bit ordering as
the DRM subsystem (in difference from the other variants)
and adds a few bits for the control of 5551, 565 etc in the
control register. Notably it also adds a packed RGB888
24BPP mode.

We add support by detecting this variant and also adding a
small plug-in that will mux the LCDC out if the ASIC happens
to be muxed to the other graphics controller (they are
mutually exclusive).

Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180621184450.25377-1-linus.walleij@linaro.org
---
 drivers/gpu/drm/pl111/Makefile        |  1 +
 drivers/gpu/drm/pl111/pl111_display.c | 54 +++++++++++++++++++++++++++++------
 drivers/gpu/drm/pl111/pl111_drm.h     |  5 ++++
 drivers/gpu/drm/pl111/pl111_drv.c     | 44 +++++++++++++++++++++++++---
 drivers/gpu/drm/pl111/pl111_nomadik.c | 36 +++++++++++++++++++++++
 drivers/gpu/drm/pl111/pl111_nomadik.h | 18 ++++++++++++
 6 files changed, 145 insertions(+), 13 deletions(-)
 create mode 100644 drivers/gpu/drm/pl111/pl111_nomadik.c
 create mode 100644 drivers/gpu/drm/pl111/pl111_nomadik.h

diff --git a/drivers/gpu/drm/pl111/Makefile b/drivers/gpu/drm/pl111/Makefile
index 19a8189dc54f..0c70f0e91d21 100644
--- a/drivers/gpu/drm/pl111/Makefile
+++ b/drivers/gpu/drm/pl111/Makefile
@@ -4,6 +4,7 @@ pl111_drm-y +=	pl111_display.o \
 		pl111_drv.o
 
 pl111_drm-$(CONFIG_ARCH_VEXPRESS) += pl111_vexpress.o
+pl111_drm-$(CONFIG_ARCH_NOMADIK) += pl111_nomadik.o
 pl111_drm-$(CONFIG_DEBUG_FS) += pl111_debugfs.o
 
 obj-$(CONFIG_DRM_PL111) += pl111_drm.o
diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index 19b0d006a54a..a432eb7ad445 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -223,48 +223,84 @@ static void pl111_display_enable(struct drm_simple_display_pipe *pipe,
 
 	/* Hard-code TFT panel */
 	cntl = CNTL_LCDEN | CNTL_LCDTFT | CNTL_LCDVCOMP(1);
+	/* On the ST Micro variant, assume all 24 bits are connected */
+	if (priv->variant->st_bitmux_control)
+		cntl |= CNTL_ST_CDWID_24;
 
-	/* Note that the the hardware's format reader takes 'r' from
+	/*
+	 * Note that the the ARM hardware's format reader takes 'r' from
 	 * the low bit, while DRM formats list channels from high bit
-	 * to low bit as you read left to right.
+	 * to low bit as you read left to right. The ST Micro version of
+	 * the PL110 (LCDC) however uses the standard DRM format.
 	 */
 	switch (fb->format->format) {
+	case DRM_FORMAT_BGR888:
+		/* Only supported on the ST Micro variant */
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_LCDBPP24_PACKED | CNTL_BGR;
+		break;
+	case DRM_FORMAT_RGB888:
+		/* Only supported on the ST Micro variant */
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_LCDBPP24_PACKED;
+		break;
 	case DRM_FORMAT_ABGR8888:
 	case DRM_FORMAT_XBGR8888:
-		cntl |= CNTL_LCDBPP24;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP24 | CNTL_BGR;
+		else
+			cntl |= CNTL_LCDBPP24;
 		break;
 	case DRM_FORMAT_ARGB8888:
 	case DRM_FORMAT_XRGB8888:
-		cntl |= CNTL_LCDBPP24 | CNTL_BGR;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP24;
+		else
+			cntl |= CNTL_LCDBPP24 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_BGR565:
 		if (priv->variant->is_pl110)
 			cntl |= CNTL_LCDBPP16;
+		else if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP16 | CNTL_ST_1XBPP_565 | CNTL_BGR;
 		else
 			cntl |= CNTL_LCDBPP16_565;
 		break;
 	case DRM_FORMAT_RGB565:
 		if (priv->variant->is_pl110)
-			cntl |= CNTL_LCDBPP16;
+			cntl |= CNTL_LCDBPP16 | CNTL_BGR;
+		else if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_LCDBPP16 | CNTL_ST_1XBPP_565;
 		else
-			cntl |= CNTL_LCDBPP16_565;
-		cntl |= CNTL_BGR;
+			cntl |= CNTL_LCDBPP16_565 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_ABGR1555:
 	case DRM_FORMAT_XBGR1555:
 		cntl |= CNTL_LCDBPP16;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_5551 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_ARGB1555:
 	case DRM_FORMAT_XRGB1555:
-		cntl |= CNTL_LCDBPP16 | CNTL_BGR;
+		cntl |= CNTL_LCDBPP16;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_5551;
+		else
+			cntl |= CNTL_BGR;
 		break;
 	case DRM_FORMAT_ABGR4444:
 	case DRM_FORMAT_XBGR4444:
 		cntl |= CNTL_LCDBPP16_444;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_444 | CNTL_BGR;
 		break;
 	case DRM_FORMAT_ARGB4444:
 	case DRM_FORMAT_XRGB4444:
-		cntl |= CNTL_LCDBPP16_444 | CNTL_BGR;
+		cntl |= CNTL_LCDBPP16_444;
+		if (priv->variant->st_bitmux_control)
+			cntl |= CNTL_ST_1XBPP_444;
+		else
+			cntl |= CNTL_BGR;
 		break;
 	default:
 		WARN_ONCE(true, "Unknown FB format 0x%08x\n",
diff --git a/drivers/gpu/drm/pl111/pl111_drm.h b/drivers/gpu/drm/pl111/pl111_drm.h
index ce4501d0ab48..1aa015ccacef 100644
--- a/drivers/gpu/drm/pl111/pl111_drm.h
+++ b/drivers/gpu/drm/pl111/pl111_drm.h
@@ -36,11 +36,14 @@ struct drm_minor;
  * struct pl111_variant_data - encodes IP differences
  * @name: the name of this variant
  * @is_pl110: this is the early PL110 variant
+ * @is_lcdc: this is the ST Microelectronics Nomadik LCDC variant
  * @external_bgr: this is the Versatile Pl110 variant with external
  *	BGR/RGB routing
  * @broken_clockdivider: the clock divider is broken and we need to
  *	use the supplied clock directly
  * @broken_vblank: the vblank IRQ is broken on this variant
+ * @st_bitmux_control: this variant is using the ST Micro bitmux
+ *	extensions to the control register
  * @formats: array of supported pixel formats on this variant
  * @nformats: the length of the array of supported pixel formats
  * @fb_bpp: desired bits per pixel on the default framebuffer
@@ -48,9 +51,11 @@ struct drm_minor;
 struct pl111_variant_data {
 	const char *name;
 	bool is_pl110;
+	bool is_lcdc;
 	bool external_bgr;
 	bool broken_clockdivider;
 	bool broken_vblank;
+	bool st_bitmux_control;
 	const u32 *formats;
 	unsigned int nformats;
 	unsigned int fb_bpp;
diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index 454ff0804642..054b93689d94 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -75,6 +75,7 @@
 
 #include "pl111_drm.h"
 #include "pl111_versatile.h"
+#include "pl111_nomadik.h"
 
 #define DRIVER_DESC      "DRM module for PL111"
 
@@ -288,8 +289,8 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 		priv->memory_bw = 0;
 	}
 
-	/* The two variants swap this register */
-	if (variant->is_pl110) {
+	/* The two main variants swap this register */
+	if (variant->is_pl110 || variant->is_lcdc) {
 		priv->ienb = CLCD_PL110_IENB;
 		priv->ctrl = CLCD_PL110_CNTL;
 	} else {
@@ -308,6 +309,7 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	ret = pl111_versatile_init(dev, priv);
 	if (ret)
 		goto dev_unref;
+	pl111_nomadik_init(dev);
 
 	/* turn off interrupts before requesting the irq */
 	writel(0, priv->regs + priv->ienb);
@@ -400,16 +402,50 @@ static const struct pl111_variant_data pl111_variant = {
 	.fb_bpp = 32,
 };
 
+static const u32 pl110_nomadik_pixel_formats[] = {
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_BGR565,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_XBGR1555,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_XRGB1555,
+	DRM_FORMAT_ABGR4444,
+	DRM_FORMAT_XBGR4444,
+	DRM_FORMAT_ARGB4444,
+	DRM_FORMAT_XRGB4444,
+};
+
+static const struct pl111_variant_data pl110_nomadik_variant = {
+	.name = "LCDC (PL110 Nomadik)",
+	.formats = pl110_nomadik_pixel_formats,
+	.nformats = ARRAY_SIZE(pl110_nomadik_pixel_formats),
+	.is_lcdc = true,
+	.st_bitmux_control = true,
+	.broken_vblank = true,
+	.fb_bpp = 16,
+};
+
 static const struct amba_id pl111_id_table[] = {
 	{
 		.id = 0x00041110,
 		.mask = 0x000fffff,
-		.data = (void*)&pl110_variant,
+		.data = (void *)&pl110_variant,
+	},
+	{
+		.id = 0x00180110,
+		.mask = 0x00fffffe,
+		.data = (void *)&pl110_nomadik_variant,
 	},
 	{
 		.id = 0x00041111,
 		.mask = 0x000fffff,
-		.data = (void*)&pl111_variant,
+		.data = (void *)&pl111_variant,
 	},
 	{0, 0},
 };
diff --git a/drivers/gpu/drm/pl111/pl111_nomadik.c b/drivers/gpu/drm/pl111/pl111_nomadik.c
new file mode 100644
index 000000000000..6f385e59be22
--- /dev/null
+++ b/drivers/gpu/drm/pl111/pl111_nomadik.c
@@ -0,0 +1,36 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/device.h>
+#include <linux/regmap.h>
+#include <linux/mfd/syscon.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include "pl111_nomadik.h"
+
+#define PMU_CTRL_OFFSET 0x0000
+#define PMU_CTRL_LCDNDIF BIT(26)
+
+void pl111_nomadik_init(struct device *dev)
+{
+	struct regmap *pmu_regmap;
+
+	/*
+	 * Just bail out of this is not found, we could be running
+	 * multiplatform on something else than Nomadik.
+	 */
+	pmu_regmap =
+		syscon_regmap_lookup_by_compatible("stericsson,nomadik-pmu");
+	if (IS_ERR(pmu_regmap))
+		return;
+
+	/*
+	 * This bit in the PMU controller multiplexes the two graphics
+	 * blocks found in the Nomadik STn8815. The other one is called
+	 * MDIF (Master Display Interface) and gets muxed out here.
+	 */
+	regmap_update_bits(pmu_regmap,
+			   PMU_CTRL_OFFSET,
+			   PMU_CTRL_LCDNDIF,
+			   0);
+	dev_info(dev, "set Nomadik PMU mux to CLCD mode\n");
+}
+EXPORT_SYMBOL_GPL(pl111_nomadik_init);
diff --git a/drivers/gpu/drm/pl111/pl111_nomadik.h b/drivers/gpu/drm/pl111/pl111_nomadik.h
new file mode 100644
index 000000000000..19d663d46353
--- /dev/null
+++ b/drivers/gpu/drm/pl111/pl111_nomadik.h
@@ -0,0 +1,18 @@
+// SPDX-License-Identifier: GPL-2.0+
+#include <linux/device.h>
+
+#ifndef PL111_NOMADIK_H
+#define PL111_NOMADIK_H
+#endif
+
+#ifdef CONFIG_ARCH_NOMADIK
+
+void pl111_nomadik_init(struct device *dev);
+
+#else
+
+static inline void pl111_nomadik_init(struct device *dev)
+{
+}
+
+#endif
-- 
cgit v1.2.3


From 80d19669ecd34423e85ca04f2210b0e42a47cb16 Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 29 Jun 2018 21:26:41 -0700
Subject: net: Refactor XPS for CPUs and Rx queues

Refactor XPS code to support Tx queue selection based on
CPU(s) map or Rx queue(s) map.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cpumask.h   |  11 ++-
 include/linux/netdevice.h |  98 ++++++++++++++++++++-
 net/core/dev.c            | 211 ++++++++++++++++++++++++++++++----------------
 net/core/net-sysfs.c      |   4 +-
 4 files changed, 244 insertions(+), 80 deletions(-)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index bf53d893ad02..57f20a0a7794 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -115,12 +115,17 @@ extern struct cpumask __cpu_active_mask;
 #define cpu_active(cpu)		((cpu) == 0)
 #endif
 
-/* verify cpu argument to cpumask_* operators */
-static inline unsigned int cpumask_check(unsigned int cpu)
+static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits)
 {
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
-	WARN_ON_ONCE(cpu >= nr_cpumask_bits);
+	WARN_ON_ONCE(cpu >= bits);
 #endif /* CONFIG_DEBUG_PER_CPU_MAPS */
+}
+
+/* verify cpu argument to cpumask_* operators */
+static inline unsigned int cpumask_check(unsigned int cpu)
+{
+	cpu_max_bits_warn(cpu, nr_cpumask_bits);
 	return cpu;
 }
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c6b377a15869..8bf8d6149f79 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -731,10 +731,15 @@ struct xps_map {
  */
 struct xps_dev_maps {
 	struct rcu_head rcu;
-	struct xps_map __rcu *cpu_map[0];
+	struct xps_map __rcu *attr_map[0]; /* Either CPUs map or RXQs map */
 };
-#define XPS_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) +		\
+
+#define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) +	\
 	(nr_cpu_ids * (_tcs) * sizeof(struct xps_map *)))
+
+#define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\
+	(_rxqs * (_tcs) * sizeof(struct xps_map *)))
+
 #endif /* CONFIG_XPS */
 
 #define TC_MAX_QUEUE	16
@@ -1910,7 +1915,8 @@ struct net_device {
 	int			watchdog_timeo;
 
 #ifdef CONFIG_XPS
-	struct xps_dev_maps __rcu *xps_maps;
+	struct xps_dev_maps __rcu *xps_cpus_map;
+	struct xps_dev_maps __rcu *xps_rxqs_map;
 #endif
 #ifdef CONFIG_NET_CLS_ACT
 	struct mini_Qdisc __rcu	*miniq_egress;
@@ -3259,6 +3265,92 @@ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
 #ifdef CONFIG_XPS
 int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 			u16 index);
+int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
+			  u16 index, bool is_rxqs_map);
+
+/**
+ *	netif_attr_test_mask - Test a CPU or Rx queue set in a mask
+ *	@j: CPU/Rx queue index
+ *	@mask: bitmask of all cpus/rx queues
+ *	@nr_bits: number of bits in the bitmask
+ *
+ * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues.
+ */
+static inline bool netif_attr_test_mask(unsigned long j,
+					const unsigned long *mask,
+					unsigned int nr_bits)
+{
+	cpu_max_bits_warn(j, nr_bits);
+	return test_bit(j, mask);
+}
+
+/**
+ *	netif_attr_test_online - Test for online CPU/Rx queue
+ *	@j: CPU/Rx queue index
+ *	@online_mask: bitmask for CPUs/Rx queues that are online
+ *	@nr_bits: number of bits in the bitmask
+ *
+ * Returns true if a CPU/Rx queue is online.
+ */
+static inline bool netif_attr_test_online(unsigned long j,
+					  const unsigned long *online_mask,
+					  unsigned int nr_bits)
+{
+	cpu_max_bits_warn(j, nr_bits);
+
+	if (online_mask)
+		return test_bit(j, online_mask);
+
+	return (j < nr_bits);
+}
+
+/**
+ *	netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask
+ *	@n: CPU/Rx queue index
+ *	@srcp: the cpumask/Rx queue mask pointer
+ *	@nr_bits: number of bits in the bitmask
+ *
+ * Returns >= nr_bits if no further CPUs/Rx queues set.
+ */
+static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp,
+					       unsigned int nr_bits)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpu_max_bits_warn(n, nr_bits);
+
+	if (srcp)
+		return find_next_bit(srcp, nr_bits, n + 1);
+
+	return n + 1;
+}
+
+/**
+ *	netif_attrmask_next_and - get the next CPU/Rx queue in *src1p & *src2p
+ *	@n: CPU/Rx queue index
+ *	@src1p: the first CPUs/Rx queues mask pointer
+ *	@src2p: the second CPUs/Rx queues mask pointer
+ *	@nr_bits: number of bits in the bitmask
+ *
+ * Returns >= nr_bits if no further CPUs/Rx queues set in both.
+ */
+static inline int netif_attrmask_next_and(int n, const unsigned long *src1p,
+					  const unsigned long *src2p,
+					  unsigned int nr_bits)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpu_max_bits_warn(n, nr_bits);
+
+	if (src1p && src2p)
+		return find_next_and_bit(src1p, src2p, nr_bits, n + 1);
+	else if (src1p)
+		return find_next_bit(src1p, nr_bits, n + 1);
+	else if (src2p)
+		return find_next_bit(src2p, nr_bits, n + 1);
+
+	return n + 1;
+}
 #else
 static inline int netif_set_xps_queue(struct net_device *dev,
 				      const struct cpumask *mask,
diff --git a/net/core/dev.c b/net/core/dev.c
index dffed642e686..71059558dc39 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2092,7 +2092,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
 	int pos;
 
 	if (dev_maps)
-		map = xmap_dereference(dev_maps->cpu_map[tci]);
+		map = xmap_dereference(dev_maps->attr_map[tci]);
 	if (!map)
 		return false;
 
@@ -2105,7 +2105,7 @@ static bool remove_xps_queue(struct xps_dev_maps *dev_maps,
 			break;
 		}
 
-		RCU_INIT_POINTER(dev_maps->cpu_map[tci], NULL);
+		RCU_INIT_POINTER(dev_maps->attr_map[tci], NULL);
 		kfree_rcu(map, rcu);
 		return false;
 	}
@@ -2135,31 +2135,58 @@ static bool remove_xps_queue_cpu(struct net_device *dev,
 	return active;
 }
 
+static void clean_xps_maps(struct net_device *dev, const unsigned long *mask,
+			   struct xps_dev_maps *dev_maps, unsigned int nr_ids,
+			   u16 offset, u16 count, bool is_rxqs_map)
+{
+	bool active = false;
+	int i, j;
+
+	for (j = -1; j = netif_attrmask_next(j, mask, nr_ids),
+	     j < nr_ids;)
+		active |= remove_xps_queue_cpu(dev, dev_maps, j, offset,
+					       count);
+	if (!active) {
+		if (is_rxqs_map) {
+			RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+		} else {
+			RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
+
+			for (i = offset + (count - 1); count--; i--)
+				netdev_queue_numa_node_write(
+					netdev_get_tx_queue(dev, i),
+							NUMA_NO_NODE);
+		}
+		kfree_rcu(dev_maps, rcu);
+	}
+}
+
 static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
 				   u16 count)
 {
+	const unsigned long *possible_mask = NULL;
 	struct xps_dev_maps *dev_maps;
-	int cpu, i;
-	bool active = false;
+	unsigned int nr_ids;
 
 	mutex_lock(&xps_map_mutex);
-	dev_maps = xmap_dereference(dev->xps_maps);
 
-	if (!dev_maps)
-		goto out_no_maps;
-
-	for_each_possible_cpu(cpu)
-		active |= remove_xps_queue_cpu(dev, dev_maps, cpu,
-					       offset, count);
+	dev_maps = xmap_dereference(dev->xps_rxqs_map);
+	if (dev_maps) {
+		nr_ids = dev->num_rx_queues;
+		clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset,
+			       count, true);
 
-	if (!active) {
-		RCU_INIT_POINTER(dev->xps_maps, NULL);
-		kfree_rcu(dev_maps, rcu);
 	}
 
-	for (i = offset + (count - 1); count--; i--)
-		netdev_queue_numa_node_write(netdev_get_tx_queue(dev, i),
-					     NUMA_NO_NODE);
+	dev_maps = xmap_dereference(dev->xps_cpus_map);
+	if (!dev_maps)
+		goto out_no_maps;
+
+	if (num_possible_cpus() > 1)
+		possible_mask = cpumask_bits(cpu_possible_mask);
+	nr_ids = nr_cpu_ids;
+	clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset, count,
+		       false);
 
 out_no_maps:
 	mutex_unlock(&xps_map_mutex);
@@ -2170,8 +2197,8 @@ static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
 	netif_reset_xps_queues(dev, index, dev->num_tx_queues - index);
 }
 
-static struct xps_map *expand_xps_map(struct xps_map *map,
-				      int cpu, u16 index)
+static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index,
+				      u16 index, bool is_rxqs_map)
 {
 	struct xps_map *new_map;
 	int alloc_len = XPS_MIN_MAP_ALLOC;
@@ -2183,7 +2210,7 @@ static struct xps_map *expand_xps_map(struct xps_map *map,
 		return map;
 	}
 
-	/* Need to add queue to this CPU's existing map */
+	/* Need to add tx-queue to this CPU's/rx-queue's existing map */
 	if (map) {
 		if (pos < map->alloc_len)
 			return map;
@@ -2191,9 +2218,14 @@ static struct xps_map *expand_xps_map(struct xps_map *map,
 		alloc_len = map->alloc_len * 2;
 	}
 
-	/* Need to allocate new map to store queue on this CPU's map */
-	new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
-			       cpu_to_node(cpu));
+	/* Need to allocate new map to store tx-queue on this CPU's/rx-queue's
+	 *  map
+	 */
+	if (is_rxqs_map)
+		new_map = kzalloc(XPS_MAP_SIZE(alloc_len), GFP_KERNEL);
+	else
+		new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), GFP_KERNEL,
+				       cpu_to_node(attr_index));
 	if (!new_map)
 		return NULL;
 
@@ -2205,14 +2237,16 @@ static struct xps_map *expand_xps_map(struct xps_map *map,
 	return new_map;
 }
 
-int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
-			u16 index)
+int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
+			  u16 index, bool is_rxqs_map)
 {
+	const unsigned long *online_mask = NULL, *possible_mask = NULL;
 	struct xps_dev_maps *dev_maps, *new_dev_maps = NULL;
-	int i, cpu, tci, numa_node_id = -2;
+	int i, j, tci, numa_node_id = -2;
 	int maps_sz, num_tc = 1, tc = 0;
 	struct xps_map *map, *new_map;
 	bool active = false;
+	unsigned int nr_ids;
 
 	if (dev->num_tc) {
 		num_tc = dev->num_tc;
@@ -2221,16 +2255,27 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 			return -EINVAL;
 	}
 
-	maps_sz = XPS_DEV_MAPS_SIZE(num_tc);
-	if (maps_sz < L1_CACHE_BYTES)
-		maps_sz = L1_CACHE_BYTES;
-
 	mutex_lock(&xps_map_mutex);
+	if (is_rxqs_map) {
+		maps_sz = XPS_RXQ_DEV_MAPS_SIZE(num_tc, dev->num_rx_queues);
+		dev_maps = xmap_dereference(dev->xps_rxqs_map);
+		nr_ids = dev->num_rx_queues;
+	} else {
+		maps_sz = XPS_CPU_DEV_MAPS_SIZE(num_tc);
+		if (num_possible_cpus() > 1) {
+			online_mask = cpumask_bits(cpu_online_mask);
+			possible_mask = cpumask_bits(cpu_possible_mask);
+		}
+		dev_maps = xmap_dereference(dev->xps_cpus_map);
+		nr_ids = nr_cpu_ids;
+	}
 
-	dev_maps = xmap_dereference(dev->xps_maps);
+	if (maps_sz < L1_CACHE_BYTES)
+		maps_sz = L1_CACHE_BYTES;
 
 	/* allocate memory for queue storage */
-	for_each_cpu_and(cpu, cpu_online_mask, mask) {
+	for (j = -1; j = netif_attrmask_next_and(j, online_mask, mask, nr_ids),
+	     j < nr_ids;) {
 		if (!new_dev_maps)
 			new_dev_maps = kzalloc(maps_sz, GFP_KERNEL);
 		if (!new_dev_maps) {
@@ -2238,73 +2283,81 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 			return -ENOMEM;
 		}
 
-		tci = cpu * num_tc + tc;
-		map = dev_maps ? xmap_dereference(dev_maps->cpu_map[tci]) :
+		tci = j * num_tc + tc;
+		map = dev_maps ? xmap_dereference(dev_maps->attr_map[tci]) :
 				 NULL;
 
-		map = expand_xps_map(map, cpu, index);
+		map = expand_xps_map(map, j, index, is_rxqs_map);
 		if (!map)
 			goto error;
 
-		RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+		RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
 	}
 
 	if (!new_dev_maps)
 		goto out_no_new_maps;
 
-	for_each_possible_cpu(cpu) {
+	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+	     j < nr_ids;) {
 		/* copy maps belonging to foreign traffic classes */
-		for (i = tc, tci = cpu * num_tc; dev_maps && i--; tci++) {
+		for (i = tc, tci = j * num_tc; dev_maps && i--; tci++) {
 			/* fill in the new device map from the old device map */
-			map = xmap_dereference(dev_maps->cpu_map[tci]);
-			RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+			map = xmap_dereference(dev_maps->attr_map[tci]);
+			RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
 		}
 
 		/* We need to explicitly update tci as prevous loop
 		 * could break out early if dev_maps is NULL.
 		 */
-		tci = cpu * num_tc + tc;
+		tci = j * num_tc + tc;
 
-		if (cpumask_test_cpu(cpu, mask) && cpu_online(cpu)) {
-			/* add queue to CPU maps */
+		if (netif_attr_test_mask(j, mask, nr_ids) &&
+		    netif_attr_test_online(j, online_mask, nr_ids)) {
+			/* add tx-queue to CPU/rx-queue maps */
 			int pos = 0;
 
-			map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+			map = xmap_dereference(new_dev_maps->attr_map[tci]);
 			while ((pos < map->len) && (map->queues[pos] != index))
 				pos++;
 
 			if (pos == map->len)
 				map->queues[map->len++] = index;
 #ifdef CONFIG_NUMA
-			if (numa_node_id == -2)
-				numa_node_id = cpu_to_node(cpu);
-			else if (numa_node_id != cpu_to_node(cpu))
-				numa_node_id = -1;
+			if (!is_rxqs_map) {
+				if (numa_node_id == -2)
+					numa_node_id = cpu_to_node(j);
+				else if (numa_node_id != cpu_to_node(j))
+					numa_node_id = -1;
+			}
 #endif
 		} else if (dev_maps) {
 			/* fill in the new device map from the old device map */
-			map = xmap_dereference(dev_maps->cpu_map[tci]);
-			RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+			map = xmap_dereference(dev_maps->attr_map[tci]);
+			RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
 		}
 
 		/* copy maps belonging to foreign traffic classes */
 		for (i = num_tc - tc, tci++; dev_maps && --i; tci++) {
 			/* fill in the new device map from the old device map */
-			map = xmap_dereference(dev_maps->cpu_map[tci]);
-			RCU_INIT_POINTER(new_dev_maps->cpu_map[tci], map);
+			map = xmap_dereference(dev_maps->attr_map[tci]);
+			RCU_INIT_POINTER(new_dev_maps->attr_map[tci], map);
 		}
 	}
 
-	rcu_assign_pointer(dev->xps_maps, new_dev_maps);
+	if (is_rxqs_map)
+		rcu_assign_pointer(dev->xps_rxqs_map, new_dev_maps);
+	else
+		rcu_assign_pointer(dev->xps_cpus_map, new_dev_maps);
 
 	/* Cleanup old maps */
 	if (!dev_maps)
 		goto out_no_old_maps;
 
-	for_each_possible_cpu(cpu) {
-		for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
-			new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
-			map = xmap_dereference(dev_maps->cpu_map[tci]);
+	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+	     j < nr_ids;) {
+		for (i = num_tc, tci = j * num_tc; i--; tci++) {
+			new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
+			map = xmap_dereference(dev_maps->attr_map[tci]);
 			if (map && map != new_map)
 				kfree_rcu(map, rcu);
 		}
@@ -2317,19 +2370,23 @@ out_no_old_maps:
 	active = true;
 
 out_no_new_maps:
-	/* update Tx queue numa node */
-	netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
-				     (numa_node_id >= 0) ? numa_node_id :
-				     NUMA_NO_NODE);
+	if (!is_rxqs_map) {
+		/* update Tx queue numa node */
+		netdev_queue_numa_node_write(netdev_get_tx_queue(dev, index),
+					     (numa_node_id >= 0) ?
+					     numa_node_id : NUMA_NO_NODE);
+	}
 
 	if (!dev_maps)
 		goto out_no_maps;
 
-	/* removes queue from unused CPUs */
-	for_each_possible_cpu(cpu) {
-		for (i = tc, tci = cpu * num_tc; i--; tci++)
+	/* removes tx-queue from unused CPUs/rx-queues */
+	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+	     j < nr_ids;) {
+		for (i = tc, tci = j * num_tc; i--; tci++)
 			active |= remove_xps_queue(dev_maps, tci, index);
-		if (!cpumask_test_cpu(cpu, mask) || !cpu_online(cpu))
+		if (!netif_attr_test_mask(j, mask, nr_ids) ||
+		    !netif_attr_test_online(j, online_mask, nr_ids))
 			active |= remove_xps_queue(dev_maps, tci, index);
 		for (i = num_tc - tc, tci++; --i; tci++)
 			active |= remove_xps_queue(dev_maps, tci, index);
@@ -2337,7 +2394,10 @@ out_no_new_maps:
 
 	/* free map if not active */
 	if (!active) {
-		RCU_INIT_POINTER(dev->xps_maps, NULL);
+		if (is_rxqs_map)
+			RCU_INIT_POINTER(dev->xps_rxqs_map, NULL);
+		else
+			RCU_INIT_POINTER(dev->xps_cpus_map, NULL);
 		kfree_rcu(dev_maps, rcu);
 	}
 
@@ -2347,11 +2407,12 @@ out_no_maps:
 	return 0;
 error:
 	/* remove any maps that we added */
-	for_each_possible_cpu(cpu) {
-		for (i = num_tc, tci = cpu * num_tc; i--; tci++) {
-			new_map = xmap_dereference(new_dev_maps->cpu_map[tci]);
+	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
+	     j < nr_ids;) {
+		for (i = num_tc, tci = j * num_tc; i--; tci++) {
+			new_map = xmap_dereference(new_dev_maps->attr_map[tci]);
 			map = dev_maps ?
-			      xmap_dereference(dev_maps->cpu_map[tci]) :
+			      xmap_dereference(dev_maps->attr_map[tci]) :
 			      NULL;
 			if (new_map && new_map != map)
 				kfree(new_map);
@@ -2363,6 +2424,12 @@ error:
 	kfree(new_dev_maps);
 	return -ENOMEM;
 }
+
+int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
+			u16 index)
+{
+	return __netif_set_xps_queue(dev, cpumask_bits(mask), index, false);
+}
 EXPORT_SYMBOL(netif_set_xps_queue);
 
 #endif
@@ -3384,7 +3451,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 	int queue_index = -1;
 
 	rcu_read_lock();
-	dev_maps = rcu_dereference(dev->xps_maps);
+	dev_maps = rcu_dereference(dev->xps_cpus_map);
 	if (dev_maps) {
 		unsigned int tci = skb->sender_cpu - 1;
 
@@ -3393,7 +3460,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 			tci += netdev_get_prio_tc_map(dev, skb->priority);
 		}
 
-		map = rcu_dereference(dev_maps->cpu_map[tci]);
+		map = rcu_dereference(dev_maps->attr_map[tci]);
 		if (map) {
 			if (map->len == 1)
 				queue_index = map->queues[0];
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bb7e80f4ced3..b39987c81d53 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1227,13 +1227,13 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 		return -ENOMEM;
 
 	rcu_read_lock();
-	dev_maps = rcu_dereference(dev->xps_maps);
+	dev_maps = rcu_dereference(dev->xps_cpus_map);
 	if (dev_maps) {
 		for_each_possible_cpu(cpu) {
 			int i, tci = cpu * num_tc + tc;
 			struct xps_map *map;
 
-			map = rcu_dereference(dev_maps->cpu_map[tci]);
+			map = rcu_dereference(dev_maps->attr_map[tci]);
 			if (!map)
 				continue;
 
-- 
cgit v1.2.3


From 04157469b7b848f4a9978b63b1ea2ce62ad3a0a3 Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 29 Jun 2018 21:26:46 -0700
Subject: net: Use static_key for XPS maps

Use static_key for XPS maps to reduce the cost of extra map checks,
similar to how it is used for RPS and RFS. This includes static_key
'xps_needed' for XPS and another for 'xps_rxqs_needed' for XPS using
Rx queues map.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 31 +++++++++++++++++++++++++------
 1 file changed, 25 insertions(+), 6 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 71059558dc39..43b5575e40c5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2081,6 +2081,10 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
 EXPORT_SYMBOL(netdev_txq_to_tc);
 
 #ifdef CONFIG_XPS
+struct static_key xps_needed __read_mostly;
+EXPORT_SYMBOL(xps_needed);
+struct static_key xps_rxqs_needed __read_mostly;
+EXPORT_SYMBOL(xps_rxqs_needed);
 static DEFINE_MUTEX(xps_map_mutex);
 #define xmap_dereference(P)		\
 	rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex))
@@ -2168,14 +2172,18 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
 	struct xps_dev_maps *dev_maps;
 	unsigned int nr_ids;
 
-	mutex_lock(&xps_map_mutex);
+	if (!static_key_false(&xps_needed))
+		return;
 
-	dev_maps = xmap_dereference(dev->xps_rxqs_map);
-	if (dev_maps) {
-		nr_ids = dev->num_rx_queues;
-		clean_xps_maps(dev, possible_mask, dev_maps, nr_ids, offset,
-			       count, true);
+	mutex_lock(&xps_map_mutex);
 
+	if (static_key_false(&xps_rxqs_needed)) {
+		dev_maps = xmap_dereference(dev->xps_rxqs_map);
+		if (dev_maps) {
+			nr_ids = dev->num_rx_queues;
+			clean_xps_maps(dev, possible_mask, dev_maps, nr_ids,
+				       offset, count, true);
+		}
 	}
 
 	dev_maps = xmap_dereference(dev->xps_cpus_map);
@@ -2189,6 +2197,10 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
 		       false);
 
 out_no_maps:
+	if (static_key_enabled(&xps_rxqs_needed))
+		static_key_slow_dec(&xps_rxqs_needed);
+
+	static_key_slow_dec(&xps_needed);
 	mutex_unlock(&xps_map_mutex);
 }
 
@@ -2297,6 +2309,10 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	if (!new_dev_maps)
 		goto out_no_new_maps;
 
+	static_key_slow_inc(&xps_needed);
+	if (is_rxqs_map)
+		static_key_slow_inc(&xps_rxqs_needed);
+
 	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
 	     j < nr_ids;) {
 		/* copy maps belonging to foreign traffic classes */
@@ -3450,6 +3466,9 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 	struct xps_map *map;
 	int queue_index = -1;
 
+	if (!static_key_false(&xps_needed))
+		return -1;
+
 	rcu_read_lock();
 	dev_maps = rcu_dereference(dev->xps_cpus_map);
 	if (dev_maps) {
-- 
cgit v1.2.3


From 755c31cd85aea35cf7a5e7253851b52c08eff6e9 Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 29 Jun 2018 21:26:51 -0700
Subject: net: sock: Change tx_queue_mapping in sock_common to unsigned short

Change 'skc_tx_queue_mapping' field in sock_common structure from
'int' to 'unsigned short' type with ~0 indicating unset and
other positive queue values being set. This will accommodate adding
a new 'unsigned short' field in sock_common in the next patch for
rx_queue_mapping.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index b3b75419eafe..37b09c84504b 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -214,7 +214,7 @@ struct sock_common {
 		struct hlist_node	skc_node;
 		struct hlist_nulls_node skc_nulls_node;
 	};
-	int			skc_tx_queue_mapping;
+	unsigned short		skc_tx_queue_mapping;
 	union {
 		int		skc_incoming_cpu;
 		u32		skc_rcv_wnd;
@@ -1681,17 +1681,25 @@ static inline int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 
 static inline void sk_tx_queue_set(struct sock *sk, int tx_queue)
 {
+	/* sk_tx_queue_mapping accept only upto a 16-bit value */
+	if (WARN_ON_ONCE((unsigned short)tx_queue >= USHRT_MAX))
+		return;
 	sk->sk_tx_queue_mapping = tx_queue;
 }
 
+#define NO_QUEUE_MAPPING	USHRT_MAX
+
 static inline void sk_tx_queue_clear(struct sock *sk)
 {
-	sk->sk_tx_queue_mapping = -1;
+	sk->sk_tx_queue_mapping = NO_QUEUE_MAPPING;
 }
 
 static inline int sk_tx_queue_get(const struct sock *sk)
 {
-	return sk ? sk->sk_tx_queue_mapping : -1;
+	if (sk && sk->sk_tx_queue_mapping != NO_QUEUE_MAPPING)
+		return sk->sk_tx_queue_mapping;
+
+	return -1;
 }
 
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
-- 
cgit v1.2.3


From c6345ce7d361dce1b5d02a2181ccb598c27fd7ae Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 29 Jun 2018 21:26:57 -0700
Subject: net: Record receive queue number for a connection

This patch adds a new field to sock_common 'skc_rx_queue_mapping'
which holds the receive queue number for the connection. The Rx queue
is marked in tcp_finish_connect() to allow a client app to do
SO_INCOMING_NAPI_ID after a connect() call to get the right queue
association for a socket. Rx queue is also marked in tcp_conn_request()
to allow syn-ack to go on the right tx-queue associated with
the queue on which syn is received.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/busy_poll.h |  1 +
 include/net/sock.h      | 28 ++++++++++++++++++++++++++++
 net/core/sock.c         |  2 ++
 net/ipv4/tcp_input.c    |  3 +++
 4 files changed, 34 insertions(+)

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c5187438af38..9e36fda652b7 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -151,6 +151,7 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	sk->sk_napi_id = skb->napi_id;
 #endif
+	sk_rx_queue_set(sk, skb);
 }
 
 /* variant used for unconnected sockets */
diff --git a/include/net/sock.h b/include/net/sock.h
index 37b09c84504b..2b097cc89727 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -139,6 +139,7 @@ typedef __u64 __bitwise __addrpair;
  *	@skc_node: main hash linkage for various protocol lookup tables
  *	@skc_nulls_node: main hash linkage for TCP/UDP/UDP-Lite protocol
  *	@skc_tx_queue_mapping: tx queue number for this connection
+ *	@skc_rx_queue_mapping: rx queue number for this connection
  *	@skc_flags: place holder for sk_flags
  *		%SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		%SO_OOBINLINE settings, %SO_TIMESTAMPING settings
@@ -215,6 +216,9 @@ struct sock_common {
 		struct hlist_nulls_node skc_nulls_node;
 	};
 	unsigned short		skc_tx_queue_mapping;
+#ifdef CONFIG_XPS
+	unsigned short		skc_rx_queue_mapping;
+#endif
 	union {
 		int		skc_incoming_cpu;
 		u32		skc_rcv_wnd;
@@ -326,6 +330,9 @@ struct sock {
 #define sk_nulls_node		__sk_common.skc_nulls_node
 #define sk_refcnt		__sk_common.skc_refcnt
 #define sk_tx_queue_mapping	__sk_common.skc_tx_queue_mapping
+#ifdef CONFIG_XPS
+#define sk_rx_queue_mapping	__sk_common.skc_rx_queue_mapping
+#endif
 
 #define sk_dontcopy_begin	__sk_common.skc_dontcopy_begin
 #define sk_dontcopy_end		__sk_common.skc_dontcopy_end
@@ -1702,6 +1709,27 @@ static inline int sk_tx_queue_get(const struct sock *sk)
 	return -1;
 }
 
+static inline void sk_rx_queue_set(struct sock *sk, const struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+	if (skb_rx_queue_recorded(skb)) {
+		u16 rx_queue = skb_get_rx_queue(skb);
+
+		if (WARN_ON_ONCE(rx_queue == NO_QUEUE_MAPPING))
+			return;
+
+		sk->sk_rx_queue_mapping = rx_queue;
+	}
+#endif
+}
+
+static inline void sk_rx_queue_clear(struct sock *sk)
+{
+#ifdef CONFIG_XPS
+	sk->sk_rx_queue_mapping = NO_QUEUE_MAPPING;
+#endif
+}
+
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
 	sk_tx_queue_clear(sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index bcc41829a16d..dac6d785186b 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2818,6 +2818,8 @@ void sock_init_data(struct socket *sock, struct sock *sk)
 	sk->sk_pacing_rate = ~0U;
 	sk->sk_pacing_shift = 10;
 	sk->sk_incoming_cpu = -1;
+
+	sk_rx_queue_clear(sk);
 	/*
 	 * Before updating sk_refcnt, we must commit prior changes to memory
 	 * (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eecd359595fc..a4731995e899 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -78,6 +78,7 @@
 #include <linux/errqueue.h>
 #include <trace/events/tcp.h>
 #include <linux/static_key.h>
+#include <net/busy_poll.h>
 
 int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 
@@ -5592,6 +5593,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	if (skb) {
 		icsk->icsk_af_ops->sk_rx_dst_set(sk, skb);
 		security_inet_conn_established(sk, skb);
+		sk_mark_napi_id(sk, skb);
 	}
 
 	tcp_init_transfer(sk, BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB);
@@ -6420,6 +6422,7 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	tcp_rsk(req)->snt_isn = isn;
 	tcp_rsk(req)->txhash = net_tx_rndhash();
 	tcp_openreq_init_rwin(req, sk, dst);
+	sk_rx_queue_set(req_to_sk(req), skb);
 	if (!want_cookie) {
 		tcp_reqsk_record_syn(sk, req, skb);
 		fastopen_sk = tcp_try_fastopen(sk, skb, req, &foc, dst);
-- 
cgit v1.2.3


From fc9bab24e9c654f62f3d411fc0b041be9e487e9d Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 29 Jun 2018 21:27:02 -0700
Subject: net: Enable Tx queue selection based on Rx queues

This patch adds support to pick Tx queue based on the Rx queue(s) map
configuration set by the admin through the sysfs attribute
for each Tx queue. If the user configuration for receive queue(s) map
does not apply, then the Tx queue selection falls back to CPU(s) map
based selection and finally to hashing.

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 10 +++++++++
 net/core/dev.c     | 62 +++++++++++++++++++++++++++++++++++++++---------------
 2 files changed, 55 insertions(+), 17 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 2b097cc89727..2ed99bfa4595 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1730,6 +1730,16 @@ static inline void sk_rx_queue_clear(struct sock *sk)
 #endif
 }
 
+#ifdef CONFIG_XPS
+static inline int sk_rx_queue_get(const struct sock *sk)
+{
+	if (sk && sk->sk_rx_queue_mapping != NO_QUEUE_MAPPING)
+		return sk->sk_rx_queue_mapping;
+
+	return -1;
+}
+#endif
+
 static inline void sk_set_socket(struct sock *sk, struct socket *sock)
 {
 	sk_tx_queue_clear(sk);
diff --git a/net/core/dev.c b/net/core/dev.c
index 43b5575e40c5..08d58e0debe5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3459,35 +3459,63 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 }
 #endif /* CONFIG_NET_EGRESS */
 
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+#ifdef CONFIG_XPS
+static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
+			       struct xps_dev_maps *dev_maps, unsigned int tci)
+{
+	struct xps_map *map;
+	int queue_index = -1;
+
+	if (dev->num_tc) {
+		tci *= dev->num_tc;
+		tci += netdev_get_prio_tc_map(dev, skb->priority);
+	}
+
+	map = rcu_dereference(dev_maps->attr_map[tci]);
+	if (map) {
+		if (map->len == 1)
+			queue_index = map->queues[0];
+		else
+			queue_index = map->queues[reciprocal_scale(
+						skb_get_hash(skb), map->len)];
+		if (unlikely(queue_index >= dev->real_num_tx_queues))
+			queue_index = -1;
+	}
+	return queue_index;
+}
+#endif
+
+static int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 {
 #ifdef CONFIG_XPS
 	struct xps_dev_maps *dev_maps;
-	struct xps_map *map;
+	struct sock *sk = skb->sk;
 	int queue_index = -1;
 
 	if (!static_key_false(&xps_needed))
 		return -1;
 
 	rcu_read_lock();
-	dev_maps = rcu_dereference(dev->xps_cpus_map);
+	if (!static_key_false(&xps_rxqs_needed))
+		goto get_cpus_map;
+
+	dev_maps = rcu_dereference(dev->xps_rxqs_map);
 	if (dev_maps) {
-		unsigned int tci = skb->sender_cpu - 1;
+		int tci = sk_rx_queue_get(sk);
 
-		if (dev->num_tc) {
-			tci *= dev->num_tc;
-			tci += netdev_get_prio_tc_map(dev, skb->priority);
-		}
+		if (tci >= 0 && tci < dev->num_rx_queues)
+			queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
+							  tci);
+	}
 
-		map = rcu_dereference(dev_maps->attr_map[tci]);
-		if (map) {
-			if (map->len == 1)
-				queue_index = map->queues[0];
-			else
-				queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
-									   map->len)];
-			if (unlikely(queue_index >= dev->real_num_tx_queues))
-				queue_index = -1;
+get_cpus_map:
+	if (queue_index < 0) {
+		dev_maps = rcu_dereference(dev->xps_cpus_map);
+		if (dev_maps) {
+			unsigned int tci = skb->sender_cpu - 1;
+
+			queue_index = __get_xps_queue_idx(dev, skb, dev_maps,
+							  tci);
 		}
 	}
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 8af2c06ff4b144064b51b7f688194474123d9c9c Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 29 Jun 2018 21:27:07 -0700
Subject: net-sysfs: Add interface for Rx queue(s) map per Tx queue

Extend transmit queue sysfs attribute to configure Rx queue(s) map
per Tx queue. By default no receive queues are configured for the
Tx queue.

- /sys/class/net/eth0/queues/tx-*/xps_rxqs

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index b39987c81d53..f25ac5ff48a6 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1283,6 +1283,88 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 
 static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
 	= __ATTR_RW(xps_cpus);
+
+static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
+{
+	struct net_device *dev = queue->dev;
+	struct xps_dev_maps *dev_maps;
+	unsigned long *mask, index;
+	int j, len, num_tc = 1, tc = 0;
+
+	index = get_netdev_queue_index(queue);
+
+	if (dev->num_tc) {
+		num_tc = dev->num_tc;
+		tc = netdev_txq_to_tc(dev, index);
+		if (tc < 0)
+			return -EINVAL;
+	}
+	mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long),
+		       GFP_KERNEL);
+	if (!mask)
+		return -ENOMEM;
+
+	rcu_read_lock();
+	dev_maps = rcu_dereference(dev->xps_rxqs_map);
+	if (!dev_maps)
+		goto out_no_maps;
+
+	for (j = -1; j = netif_attrmask_next(j, NULL, dev->num_rx_queues),
+	     j < dev->num_rx_queues;) {
+		int i, tci = j * num_tc + tc;
+		struct xps_map *map;
+
+		map = rcu_dereference(dev_maps->attr_map[tci]);
+		if (!map)
+			continue;
+
+		for (i = map->len; i--;) {
+			if (map->queues[i] == index) {
+				set_bit(j, mask);
+				break;
+			}
+		}
+	}
+out_no_maps:
+	rcu_read_unlock();
+
+	len = bitmap_print_to_pagebuf(false, buf, mask, dev->num_rx_queues);
+	kfree(mask);
+
+	return len < PAGE_SIZE ? len : -EINVAL;
+}
+
+static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
+			      size_t len)
+{
+	struct net_device *dev = queue->dev;
+	struct net *net = dev_net(dev);
+	unsigned long *mask, index;
+	int err;
+
+	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	mask = kcalloc(BITS_TO_LONGS(dev->num_rx_queues), sizeof(long),
+		       GFP_KERNEL);
+	if (!mask)
+		return -ENOMEM;
+
+	index = get_netdev_queue_index(queue);
+
+	err = bitmap_parse(buf, len, mask, dev->num_rx_queues);
+	if (err) {
+		kfree(mask);
+		return err;
+	}
+
+	err = __netif_set_xps_queue(dev, mask, index, true);
+	kfree(mask);
+	return err ? : len;
+}
+
+static struct netdev_queue_attribute xps_rxqs_attribute __ro_after_init
+	= __ATTR_RW(xps_rxqs);
 #endif /* CONFIG_XPS */
 
 static struct attribute *netdev_queue_default_attrs[] __ro_after_init = {
@@ -1290,6 +1372,7 @@ static struct attribute *netdev_queue_default_attrs[] __ro_after_init = {
 	&queue_traffic_class.attr,
 #ifdef CONFIG_XPS
 	&xps_cpus_attribute.attr,
+	&xps_rxqs_attribute.attr,
 	&queue_tx_maxrate.attr,
 #endif
 	NULL
-- 
cgit v1.2.3


From a4fd1f4babe3fac5887faa5b1b88bde4cd4d1b0d Mon Sep 17 00:00:00 2001
From: Amritha Nambiar <amritha.nambiar@intel.com>
Date: Fri, 29 Jun 2018 21:27:12 -0700
Subject: Documentation: Add explanation for XPS using Rx-queue(s) map

Signed-off-by: Amritha Nambiar <amritha.nambiar@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/ABI/testing/sysfs-class-net-queues | 11 +++++
 Documentation/networking/scaling.txt             | 61 +++++++++++++++++++-----
 2 files changed, 61 insertions(+), 11 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-class-net-queues b/Documentation/ABI/testing/sysfs-class-net-queues
index 0c0df91b1516..978b76358661 100644
--- a/Documentation/ABI/testing/sysfs-class-net-queues
+++ b/Documentation/ABI/testing/sysfs-class-net-queues
@@ -42,6 +42,17 @@ Description:
 		network device transmit queue. Possible vaules depend on the
 		number of available CPU(s) in the system.
 
+What:		/sys/class/<iface>/queues/tx-<queue>/xps_rxqs
+Date:		June 2018
+KernelVersion:	4.18.0
+Contact:	netdev@vger.kernel.org
+Description:
+		Mask of the receive queue(s) currently enabled to participate
+		into the Transmit Packet Steering packet processing flow for this
+		network device transmit queue. Possible values depend on the
+		number of available receive queue(s) in the network device.
+		Default is disabled.
+
 What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
 Date:		November 2011
 KernelVersion:	3.3
diff --git a/Documentation/networking/scaling.txt b/Documentation/networking/scaling.txt
index f55639d71d35..b7056a8a0540 100644
--- a/Documentation/networking/scaling.txt
+++ b/Documentation/networking/scaling.txt
@@ -366,8 +366,13 @@ XPS: Transmit Packet Steering
 
 Transmit Packet Steering is a mechanism for intelligently selecting
 which transmit queue to use when transmitting a packet on a multi-queue
-device. To accomplish this, a mapping from CPU to hardware queue(s) is
-recorded. The goal of this mapping is usually to assign queues
+device. This can be accomplished by recording two kinds of maps, either
+a mapping of CPU to hardware queue(s) or a mapping of receive queue(s)
+to hardware transmit queue(s).
+
+1. XPS using CPUs map
+
+The goal of this mapping is usually to assign queues
 exclusively to a subset of CPUs, where the transmit completions for
 these queues are processed on a CPU within this set. This choice
 provides two benefits. First, contention on the device queue lock is
@@ -377,15 +382,40 @@ transmit queue). Secondly, cache miss rate on transmit completion is
 reduced, in particular for data cache lines that hold the sk_buff
 structures.
 
-XPS is configured per transmit queue by setting a bitmap of CPUs that
-may use that queue to transmit. The reverse mapping, from CPUs to
-transmit queues, is computed and maintained for each network device.
-When transmitting the first packet in a flow, the function
-get_xps_queue() is called to select a queue. This function uses the ID
-of the running CPU as a key into the CPU-to-queue lookup table. If the
+2. XPS using receive queues map
+
+This mapping is used to pick transmit queue based on the receive
+queue(s) map configuration set by the administrator. A set of receive
+queues can be mapped to a set of transmit queues (many:many), although
+the common use case is a 1:1 mapping. This will enable sending packets
+on the same queue associations for transmit and receive. This is useful for
+busy polling multi-threaded workloads where there are challenges in
+associating a given CPU to a given application thread. The application
+threads are not pinned to CPUs and each thread handles packets
+received on a single queue. The receive queue number is cached in the
+socket for the connection. In this model, sending the packets on the same
+transmit queue corresponding to the associated receive queue has benefits
+in keeping the CPU overhead low. Transmit completion work is locked into
+the same queue-association that a given application is polling on. This
+avoids the overhead of triggering an interrupt on another CPU. When the
+application cleans up the packets during the busy poll, transmit completion
+may be processed along with it in the same thread context and so result in
+reduced latency.
+
+XPS is configured per transmit queue by setting a bitmap of
+CPUs/receive-queues that may use that queue to transmit. The reverse
+mapping, from CPUs to transmit queues or from receive-queues to transmit
+queues, is computed and maintained for each network device. When
+transmitting the first packet in a flow, the function get_xps_queue() is
+called to select a queue. This function uses the ID of the receive queue
+for the socket connection for a match in the receive queue-to-transmit queue
+lookup table. Alternatively, this function can also use the ID of the
+running CPU as a key into the CPU-to-queue lookup table. If the
 ID matches a single queue, that is used for transmission. If multiple
 queues match, one is selected by using the flow hash to compute an index
-into the set.
+into the set. When selecting the transmit queue based on receive queue(s)
+map, the transmit device is not validated against the receive device as it
+requires expensive lookup operation in the datapath.
 
 The queue chosen for transmitting a particular flow is saved in the
 corresponding socket structure for the flow (e.g. a TCP connection).
@@ -404,11 +434,15 @@ acknowledged.
 
 XPS is only available if the kconfig symbol CONFIG_XPS is enabled (on by
 default for SMP). The functionality remains disabled until explicitly
-configured. To enable XPS, the bitmap of CPUs that may use a transmit
-queue is configured using the sysfs file entry:
+configured. To enable XPS, the bitmap of CPUs/receive-queues that may
+use a transmit queue is configured using the sysfs file entry:
 
+For selection based on CPUs map:
 /sys/class/net/<dev>/queues/tx-<n>/xps_cpus
 
+For selection based on receive-queues map:
+/sys/class/net/<dev>/queues/tx-<n>/xps_rxqs
+
 == Suggested Configuration
 
 For a network device with a single transmission queue, XPS configuration
@@ -421,6 +455,11 @@ best CPUs to share a given queue are probably those that share the cache
 with the CPU that processes transmit completions for that queue
 (transmit interrupts).
 
+For transmit queue selection based on receive queue(s), XPS has to be
+explicitly configured mapping receive-queue(s) to transmit queue(s). If the
+user configuration for receive-queue map does not apply, then the transmit
+queue is selected based on the CPUs map.
+
 Per TX Queue rate limitation:
 =============================
 
-- 
cgit v1.2.3


From efc6362c6f8c1e74b340e2611f1b35e7d557ce7b Mon Sep 17 00:00:00 2001
From: Peter Rosin <peda@axentia.se>
Date: Thu, 29 Mar 2018 15:10:54 +0200
Subject: mtd: rawnand: atmel: add module param to avoid using dma

On a sama5d31 with a Full-HD dual LVDS panel (132MHz pixel clock) NAND
flash accesses have a tendency to cause display disturbances. Add a
module param to disable DMA from the NAND controller, since that fixes
the display problem for me.

Signed-off-by: Peter Rosin <peda@axentia.se>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 12f6753d47ae..e686fe73159e 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -129,6 +129,11 @@
 #define DEFAULT_TIMEOUT_MS			1000
 #define MIN_DMA_LEN				128
 
+static bool atmel_nand_avoid_dma __read_mostly;
+
+MODULE_PARM_DESC(avoiddma, "Avoid using DMA");
+module_param_named(avoiddma, atmel_nand_avoid_dma, bool, 0400);
+
 enum atmel_nand_rb_type {
 	ATMEL_NAND_NO_RB,
 	ATMEL_NAND_NATIVE_RB,
@@ -1977,7 +1982,7 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 		return ret;
 	}
 
-	if (nc->caps->has_dma) {
+	if (nc->caps->has_dma && !atmel_nand_avoid_dma) {
 		dma_cap_mask_t mask;
 
 		dma_cap_zero(mask);
-- 
cgit v1.2.3


From ac8cf0b9e784acaf6fa20de89cb23b156834ca01 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 20 Jun 2018 09:44:43 +0200
Subject: mtd: rawnand: micron: Update ecc_stats.corrected

Even if we can't update ecc_stats.corrected with an accurate value we
should at least increase the number of bitflips so that MTD users can
know that there was some bitflips.

Just add chip->ecc.strength to mtd->ecc_stats.corrected which should
account for the worst case situation.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 5ec4c90a637d..203faba0a9c1 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -137,18 +137,19 @@ micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
 	if (ret)
 		goto out;
 
-	if (status & NAND_STATUS_FAIL)
+	if (status & NAND_STATUS_FAIL) {
 		mtd->ecc_stats.failed++;
-
-	/*
-	 * The internal ECC doesn't tell us the number of bitflips
-	 * that have been corrected, but tells us if it recommends to
-	 * rewrite the block. If it's the case, then we pretend we had
-	 * a number of bitflips equal to the ECC strength, which will
-	 * hint the NAND core to rewrite the block.
-	 */
-	else if (status & NAND_STATUS_WRITE_RECOMMENDED)
+	} else if (status & NAND_STATUS_WRITE_RECOMMENDED) {
+		/*
+		 * The internal ECC doesn't tell us the number of bitflips
+		 * that have been corrected, but tells us if it recommends to
+		 * rewrite the block. If it's the case, then we pretend we had
+		 * a number of bitflips equal to the ECC strength, which will
+		 * hint the NAND core to rewrite the block.
+		 */
+		mtd->ecc_stats.corrected += chip->ecc.strength;
 		max_bitflips = chip->ecc.strength;
+	}
 
 	ret = nand_read_data_op(chip, buf, mtd->writesize, false);
 	if (!ret && oob_required)
-- 
cgit v1.2.3


From 16c4fba03a45ac8c6048a96e02abc933e1354852 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Sun, 24 Jun 2018 22:53:55 +0200
Subject: mtd: rawnand: hynix: fix decoding the OOB size on H27UCG8T2BTR

The datasheet of the H27UCG8T2BTR states that this chip has a page size
of "16,384 + 1,280(Spare) bytes". The description of the "4th Byte of
Device Identifier Description" indicates that bits 6, 3 and 2 are
encoding the "Redundant Area Size / 8KB", where 640 bytes is a value of
0x6 (110 in binary notation).

hynix_nand_extract_oobsize decodes an OOB size of 640 bytes for this
chip. Kernel boot log extract before this patch:
nand: Could not find valid ONFI parameter page; aborting
nand: device found, Manufacturer ID: 0xad, Chip ID: 0xde
nand: Hynix NAND 8GiB 3,3V 8-bit
nand: 8192 MiB, MLC, erase size: 4096 KiB, page size: 16384,
      OOB size: 640

However, based on the description in the datasheet we need to multiply
the OOB size with 2, because it's "640 spare bytes per 8192 bytes page
size" and this NAND chip has a page size of 16384 (= 2 * 8192). After
this patch the kernel boot log reports:
nand: Could not find valid ONFI parameter page; aborting
nand: device found, Manufacturer ID: 0xad, Chip ID: 0xde
nand: Hynix NAND 8GiB 3,3V 8-bit
nand: 8192 MiB, MLC, erase size: 4096 KiB, page size: 16384,
      OOB size: 1280

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_hynix.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c
index d542908a0ebb..8cbe77f447c7 100644
--- a/drivers/mtd/nand/raw/nand_hynix.c
+++ b/drivers/mtd/nand/raw/nand_hynix.c
@@ -473,6 +473,19 @@ static void hynix_nand_extract_oobsize(struct nand_chip *chip,
 			WARN(1, "Invalid OOB size");
 			break;
 		}
+
+		/*
+		 * The datasheet of H27UCG8T2BTR mentions that the "Redundant
+		 * Area Size" is encoded "per 8KB" (page size). This chip uses
+		 * a page size of 16KiB. The datasheet mentions an OOB size of
+		 * 1.280 bytes, but the OOB size encoded in the ID bytes (using
+		 * the existing logic above) is 640 bytes.
+		 * Update the OOB size for this chip by taking the value
+		 * determined above and scaling it to the actual page size (so
+		 * the actual OOB size for this chip is: 640 * 16k / 8k).
+		 */
+		if (chip->id.data[1] == 0xde)
+			mtd->oobsize *= mtd->writesize / SZ_8K;
 	}
 }
 
-- 
cgit v1.2.3


From f308d7353d1f5c3ddedc784a367edc72fc51bbaa Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 24 Jun 2018 23:27:22 +0200
Subject: mtd: rawnand: add Reed-Solomon error correction algorithm

Add Reed-Solomon (RS) to the enumeration of ECC algorithms.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/nand.txt | 2 +-
 drivers/mtd/nand/raw/nand_base.c               | 1 +
 include/linux/mtd/rawnand.h                    | 1 +
 3 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt
index 8bb11d809429..eaef8c657aa5 100644
--- a/Documentation/devicetree/bindings/mtd/nand.txt
+++ b/Documentation/devicetree/bindings/mtd/nand.txt
@@ -25,7 +25,7 @@ Optional NAND chip properties:
 		  Deprecated values:
 		  "soft_bch": use "soft" and nand-ecc-algo instead
 - nand-ecc-algo: string, algorithm of NAND ECC.
-		 Supported values are: "hamming", "bch".
+		 Valid values are: "hamming", "bch", "rs".
 - nand-bus-width : 8 or 16 bus width if not present 8
 - nand-on-flash-bbt: boolean to enable on flash bbt option if not present false
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index b01d15ec4c56..d0af5347f89d 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5777,6 +5777,7 @@ static int of_get_nand_ecc_mode(struct device_node *np)
 static const char * const nand_ecc_algos[] = {
 	[NAND_ECC_HAMMING]	= "hamming",
 	[NAND_ECC_BCH]		= "bch",
+	[NAND_ECC_RS]		= "rs",
 };
 
 static int of_get_nand_ecc_algo(struct device_node *np)
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 3e8ec3b8a39c..2d9cb7acbc3d 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -121,6 +121,7 @@ enum nand_ecc_algo {
 	NAND_ECC_UNKNOWN,
 	NAND_ECC_HAMMING,
 	NAND_ECC_BCH,
+	NAND_ECC_RS,
 };
 
 /*
-- 
cgit v1.2.3


From f922bd798bb94e0adcce26ddd811245443173268 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 24 Jun 2018 23:27:23 +0200
Subject: mtd: rawnand: add an option to specify NAND chip as a boot device

Allow to define a NAND chip as a boot device. This can be helpful
for the selection of the ECC algorithm and strength in case the boot
ROM supports only a subset of controller provided options.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/nand.txt | 4 ++++
 drivers/mtd/nand/raw/nand_base.c               | 3 +++
 include/linux/mtd/rawnand.h                    | 6 ++++++
 3 files changed, 13 insertions(+)

diff --git a/Documentation/devicetree/bindings/mtd/nand.txt b/Documentation/devicetree/bindings/mtd/nand.txt
index eaef8c657aa5..e949c778e983 100644
--- a/Documentation/devicetree/bindings/mtd/nand.txt
+++ b/Documentation/devicetree/bindings/mtd/nand.txt
@@ -43,6 +43,10 @@ Optional NAND chip properties:
 		     This is particularly useful when only the in-band area is
 		     used by the upper layers, and you want to make your NAND
 		     as reliable as possible.
+- nand-is-boot-medium: Whether the NAND chip is a boot medium. Drivers might use
+		       this information to select ECC algorithms supported by
+		       the boot ROM or similar restrictions.
+
 - nand-rb: shall contain the native Ready/Busy ids.
 
 The ECC strength and ECC step size properties define the correction capability
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index d0af5347f89d..1c633f80c3e1 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5859,6 +5859,9 @@ static int nand_dt_init(struct nand_chip *chip)
 	if (of_get_nand_bus_width(dn) == 16)
 		chip->options |= NAND_BUSWIDTH_16;
 
+	if (of_property_read_bool(dn, "nand-is-boot-medium"))
+		chip->options |= NAND_IS_BOOT_MEDIUM;
+
 	if (of_get_nand_on_flash_bbt(dn))
 		chip->bbt_options |= NAND_BBT_USE_FLASH;
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 2d9cb7acbc3d..80aeeca03f36 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -219,6 +219,12 @@ enum nand_ecc_algo {
  */
 #define NAND_WAIT_TCCS		0x00200000
 
+/*
+ * Whether the NAND chip is a boot medium. Drivers might use this information
+ * to select ECC algorithms supported by the boot ROM or similar restrictions.
+ */
+#define NAND_IS_BOOT_MEDIUM	0x00400000
+
 /* Options set by nand scan */
 /* Nand scan has allocated controller struct */
 #define NAND_CONTROLLER_ALLOC	0x80000000
-- 
cgit v1.2.3


From f8a53187a25fdb9fb9b3cbde63f9abdc5c0b7dec Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 24 Jun 2018 23:27:24 +0200
Subject: dt-bindings: mtd: add tegra NAND controller binding

This adds the devicetree binding for the Tegra 2 NAND flash
controller.

Signed-off-by: Lucas Stach <dev@lynxeye.de>
Signed-off-by: Stefan Agner <stefan@agner.ch>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 .../bindings/mtd/nvidia-tegra20-nand.txt           | 64 ++++++++++++++++++++++
 1 file changed, 64 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt

diff --git a/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt b/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
new file mode 100644
index 000000000000..b2f2ca12f9e6
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
@@ -0,0 +1,64 @@
+NVIDIA Tegra NAND Flash controller
+
+Required properties:
+- compatible: Must be one of:
+  - "nvidia,tegra20-nand"
+- reg: MMIO address range
+- interrupts: interrupt output of the NFC controller
+- clocks: Must contain an entry for each entry in clock-names.
+  See ../clocks/clock-bindings.txt for details.
+- clock-names: Must include the following entries:
+  - nand
+- resets: Must contain an entry for each entry in reset-names.
+  See ../reset/reset.txt for details.
+- reset-names: Must include the following entries:
+  - nand
+
+Optional children nodes:
+Individual NAND chips are children of the NAND controller node. Currently
+only one NAND chip supported.
+
+Required children node properties:
+- reg: An integer ranging from 1 to 6 representing the CS line to use.
+
+Optional children node properties:
+- nand-ecc-mode: String, operation mode of the NAND ecc mode. Currently only
+		 "hw" is supported.
+- nand-ecc-algo: string, algorithm of NAND ECC.
+		 Supported values with "hw" ECC mode are: "rs", "bch".
+- nand-bus-width : See nand.txt
+- nand-on-flash-bbt: See nand.txt
+- nand-ecc-strength: integer representing the number of bits to correct
+		     per ECC step (always 512). Supported strength using HW ECC
+		     modes are:
+		     - RS: 4, 6, 8
+		     - BCH: 4, 8, 14, 16
+- nand-ecc-maximize: See nand.txt
+- nand-is-boot-medium: Makes sure only ECC strengths supported by the boot ROM
+		       are chosen.
+- wp-gpios: GPIO specifier for the write protect pin.
+
+Optional child node of NAND chip nodes:
+Partitions: see partition.txt
+
+  Example:
+	nand-controller@70008000 {
+		compatible = "nvidia,tegra20-nand";
+		reg = <0x70008000 0x100>;
+		interrupts = <GIC_SPI 24 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&tegra_car TEGRA20_CLK_NDFLASH>;
+		clock-names = "nand";
+		resets = <&tegra_car 13>;
+		reset-names = "nand";
+
+		nand@0 {
+			reg = <0>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			nand-bus-width = <8>;
+			nand-on-flash-bbt;
+			nand-ecc-algo = "bch";
+			nand-ecc-strength = <8>;
+			wp-gpios = <&gpio TEGRA_GPIO(S, 0) GPIO_ACTIVE_LOW>;
+		};
+	};
-- 
cgit v1.2.3


From d7d9f8ec77fe90472a649d1c2adba43a2e306eeb Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 24 Jun 2018 23:27:25 +0200
Subject: mtd: rawnand: add NVIDIA Tegra NAND Flash controller driver

Add support for the NAND flash controller found on NVIDIA
Tegra 2 SoCs. This implementation does not make use of the
command queue feature. Regular operations using ->exec_op()
use PIO mode for data transfers. Raw, ECC and OOB read/writes
make use of the DMA mode for data transfer.

Signed-off-by: Lucas Stach <dev@lynxeye.de>
Signed-off-by: Stefan Agner <stefan@agner.ch>
Reviewed-by: Dmitry Osipenko <digetx@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 MAINTAINERS                       |    7 +
 drivers/mtd/nand/raw/Kconfig      |   10 +
 drivers/mtd/nand/raw/Makefile     |    1 +
 drivers/mtd/nand/raw/tegra_nand.c | 1230 +++++++++++++++++++++++++++++++++++++
 4 files changed, 1248 insertions(+)
 create mode 100644 drivers/mtd/nand/raw/tegra_nand.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 07d1576fc766..63700cefbf56 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -14054,6 +14054,13 @@ M:	Laxman Dewangan <ldewangan@nvidia.com>
 S:	Supported
 F:	drivers/input/keyboard/tegra-kbc.c
 
+TEGRA NAND DRIVER
+M:	Stefan Agner <stefan@agner.ch>
+M:	Lucas Stach <dev@lynxeye.de>
+S:	Maintained
+F:	Documentation/devicetree/bindings/mtd/nvidia-tegra20-nand.txt
+F:	drivers/mtd/nand/raw/tegra_nand.c
+
 TEGRA PWM DRIVER
 M:	Thierry Reding <thierry.reding@gmail.com>
 S:	Supported
diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6871ff0fd300..6074a946708a 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -530,4 +530,14 @@ config MTD_NAND_MTK
 	  Enables support for NAND controller on MTK SoCs.
 	  This controller is found on mt27xx, mt81xx, mt65xx SoCs.
 
+config MTD_NAND_TEGRA
+	tristate "Support for NAND controller on NVIDIA Tegra"
+	depends on ARCH_TEGRA || COMPILE_TEST
+	help
+	  Enables support for NAND flash controller on NVIDIA Tegra SoC.
+	  The driver has been developed and tested on a Tegra 2 SoC. DMA
+	  support, raw read/write page as well as HW ECC read/write page
+	  is supported. Extra OOB bytes when using HW ECC are currently
+	  not supported.
+
 endif # MTD_NAND
diff --git a/drivers/mtd/nand/raw/Makefile b/drivers/mtd/nand/raw/Makefile
index 165b7ef9e9a1..d5a5f9832b88 100644
--- a/drivers/mtd/nand/raw/Makefile
+++ b/drivers/mtd/nand/raw/Makefile
@@ -56,6 +56,7 @@ obj-$(CONFIG_MTD_NAND_HISI504)	        += hisi504_nand.o
 obj-$(CONFIG_MTD_NAND_BRCMNAND)		+= brcmnand/
 obj-$(CONFIG_MTD_NAND_QCOM)		+= qcom_nandc.o
 obj-$(CONFIG_MTD_NAND_MTK)		+= mtk_ecc.o mtk_nand.o
+obj-$(CONFIG_MTD_NAND_TEGRA)		+= tegra_nand.o
 
 nand-objs := nand_base.o nand_bbt.o nand_timings.o nand_ids.o
 nand-objs += nand_amd.o
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
new file mode 100644
index 000000000000..9f7de36be893
--- /dev/null
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -0,0 +1,1230 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Stefan Agner <stefan@agner.ch>
+ * Copyright (C) 2014-2015 Lucas Stach <dev@lynxeye.de>
+ * Copyright (C) 2012 Avionic Design GmbH
+ */
+
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/dma-mapping.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/mtd/partitions.h>
+#include <linux/mtd/rawnand.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#define COMMAND					0x00
+#define   COMMAND_GO				BIT(31)
+#define   COMMAND_CLE				BIT(30)
+#define   COMMAND_ALE				BIT(29)
+#define   COMMAND_PIO				BIT(28)
+#define   COMMAND_TX				BIT(27)
+#define   COMMAND_RX				BIT(26)
+#define   COMMAND_SEC_CMD			BIT(25)
+#define   COMMAND_AFT_DAT			BIT(24)
+#define   COMMAND_TRANS_SIZE(size)		((((size) - 1) & 0xf) << 20)
+#define   COMMAND_A_VALID			BIT(19)
+#define   COMMAND_B_VALID			BIT(18)
+#define   COMMAND_RD_STATUS_CHK			BIT(17)
+#define   COMMAND_RBSY_CHK			BIT(16)
+#define   COMMAND_CE(x)				BIT(8 + ((x) & 0x7))
+#define   COMMAND_CLE_SIZE(size)		((((size) - 1) & 0x3) << 4)
+#define   COMMAND_ALE_SIZE(size)		((((size) - 1) & 0xf) << 0)
+
+#define STATUS					0x04
+
+#define ISR					0x08
+#define   ISR_CORRFAIL_ERR			BIT(24)
+#define   ISR_UND				BIT(7)
+#define   ISR_OVR				BIT(6)
+#define   ISR_CMD_DONE				BIT(5)
+#define   ISR_ECC_ERR				BIT(4)
+
+#define IER					0x0c
+#define   IER_ERR_TRIG_VAL(x)			(((x) & 0xf) << 16)
+#define   IER_UND				BIT(7)
+#define   IER_OVR				BIT(6)
+#define   IER_CMD_DONE				BIT(5)
+#define   IER_ECC_ERR				BIT(4)
+#define   IER_GIE				BIT(0)
+
+#define CONFIG					0x10
+#define   CONFIG_HW_ECC				BIT(31)
+#define   CONFIG_ECC_SEL			BIT(30)
+#define   CONFIG_ERR_COR			BIT(29)
+#define   CONFIG_PIPE_EN			BIT(28)
+#define   CONFIG_TVAL_4				(0 << 24)
+#define   CONFIG_TVAL_6				(1 << 24)
+#define   CONFIG_TVAL_8				(2 << 24)
+#define   CONFIG_SKIP_SPARE			BIT(23)
+#define   CONFIG_BUS_WIDTH_16			BIT(21)
+#define   CONFIG_COM_BSY			BIT(20)
+#define   CONFIG_PS_256				(0 << 16)
+#define   CONFIG_PS_512				(1 << 16)
+#define   CONFIG_PS_1024			(2 << 16)
+#define   CONFIG_PS_2048			(3 << 16)
+#define   CONFIG_PS_4096			(4 << 16)
+#define   CONFIG_SKIP_SPARE_SIZE_4		(0 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_8		(1 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_12		(2 << 14)
+#define   CONFIG_SKIP_SPARE_SIZE_16		(3 << 14)
+#define   CONFIG_TAG_BYTE_SIZE(x)			((x) & 0xff)
+
+#define TIMING_1				0x14
+#define   TIMING_TRP_RESP(x)			(((x) & 0xf) << 28)
+#define   TIMING_TWB(x)				(((x) & 0xf) << 24)
+#define   TIMING_TCR_TAR_TRR(x)			(((x) & 0xf) << 20)
+#define   TIMING_TWHR(x)			(((x) & 0xf) << 16)
+#define   TIMING_TCS(x)				(((x) & 0x3) << 14)
+#define   TIMING_TWH(x)				(((x) & 0x3) << 12)
+#define   TIMING_TWP(x)				(((x) & 0xf) <<  8)
+#define   TIMING_TRH(x)				(((x) & 0x3) <<  4)
+#define   TIMING_TRP(x)				(((x) & 0xf) <<  0)
+
+#define RESP					0x18
+
+#define TIMING_2				0x1c
+#define   TIMING_TADL(x)			((x) & 0xf)
+
+#define CMD_REG1				0x20
+#define CMD_REG2				0x24
+#define ADDR_REG1				0x28
+#define ADDR_REG2				0x2c
+
+#define DMA_MST_CTRL				0x30
+#define   DMA_MST_CTRL_GO			BIT(31)
+#define   DMA_MST_CTRL_IN			(0 << 30)
+#define   DMA_MST_CTRL_OUT			BIT(30)
+#define   DMA_MST_CTRL_PERF_EN			BIT(29)
+#define   DMA_MST_CTRL_IE_DONE			BIT(28)
+#define   DMA_MST_CTRL_REUSE			BIT(27)
+#define   DMA_MST_CTRL_BURST_1			(2 << 24)
+#define   DMA_MST_CTRL_BURST_4			(3 << 24)
+#define   DMA_MST_CTRL_BURST_8			(4 << 24)
+#define   DMA_MST_CTRL_BURST_16			(5 << 24)
+#define   DMA_MST_CTRL_IS_DONE			BIT(20)
+#define   DMA_MST_CTRL_EN_A			BIT(2)
+#define   DMA_MST_CTRL_EN_B			BIT(1)
+
+#define DMA_CFG_A				0x34
+#define DMA_CFG_B				0x38
+
+#define FIFO_CTRL				0x3c
+#define   FIFO_CTRL_CLR_ALL			BIT(3)
+
+#define DATA_PTR				0x40
+#define TAG_PTR					0x44
+#define ECC_PTR					0x48
+
+#define DEC_STATUS				0x4c
+#define   DEC_STATUS_A_ECC_FAIL			BIT(1)
+#define   DEC_STATUS_ERR_COUNT_MASK		0x00ff0000
+#define   DEC_STATUS_ERR_COUNT_SHIFT		16
+
+#define HWSTATUS_CMD				0x50
+#define HWSTATUS_MASK				0x54
+#define   HWSTATUS_RDSTATUS_MASK(x)		(((x) & 0xff) << 24)
+#define   HWSTATUS_RDSTATUS_VALUE(x)		(((x) & 0xff) << 16)
+#define   HWSTATUS_RBSY_MASK(x)			(((x) & 0xff) << 8)
+#define   HWSTATUS_RBSY_VALUE(x)		(((x) & 0xff) << 0)
+
+#define BCH_CONFIG				0xcc
+#define   BCH_ENABLE				BIT(0)
+#define   BCH_TVAL_4				(0 << 4)
+#define   BCH_TVAL_8				(1 << 4)
+#define   BCH_TVAL_14				(2 << 4)
+#define   BCH_TVAL_16				(3 << 4)
+
+#define DEC_STAT_RESULT				0xd0
+#define DEC_STAT_BUF				0xd4
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_MASK	0xff000000
+#define   DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT	24
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_MASK	0x00ff0000
+#define   DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT	16
+#define   DEC_STAT_BUF_MAX_CORR_CNT_MASK	0x00001f00
+#define   DEC_STAT_BUF_MAX_CORR_CNT_SHIFT	8
+
+#define OFFSET(val, off)	((val) < (off) ? 0 : (val) - (off))
+
+#define SKIP_SPARE_BYTES	4
+#define BITS_PER_STEP_RS	18
+#define BITS_PER_STEP_BCH	13
+
+#define INT_MASK		(IER_UND | IER_OVR | IER_CMD_DONE | IER_GIE)
+#define HWSTATUS_CMD_DEFAULT	NAND_STATUS_READY
+#define HWSTATUS_MASK_DEFAULT	(HWSTATUS_RDSTATUS_MASK(1) | \
+				HWSTATUS_RDSTATUS_VALUE(0) | \
+				HWSTATUS_RBSY_MASK(NAND_STATUS_READY) | \
+				HWSTATUS_RBSY_VALUE(NAND_STATUS_READY))
+
+struct tegra_nand_controller {
+	struct nand_hw_control controller;
+	struct device *dev;
+	void __iomem *regs;
+	int irq;
+	struct clk *clk;
+	struct completion command_complete;
+	struct completion dma_complete;
+	bool last_read_error;
+	int cur_cs;
+	struct nand_chip *chip;
+};
+
+struct tegra_nand_chip {
+	struct nand_chip chip;
+	struct gpio_desc *wp_gpio;
+	struct mtd_oob_region ecc;
+	u32 config;
+	u32 config_ecc;
+	u32 bch_config;
+	int cs[1];
+};
+
+static inline struct tegra_nand_controller *
+			to_tegra_ctrl(struct nand_hw_control *hw_ctrl)
+{
+	return container_of(hw_ctrl, struct tegra_nand_controller, controller);
+}
+
+static inline struct tegra_nand_chip *to_tegra_chip(struct nand_chip *chip)
+{
+	return container_of(chip, struct tegra_nand_chip, chip);
+}
+
+static int tegra_nand_ooblayout_rs_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_RS * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static int tegra_nand_ooblayout_no_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	return -ERANGE;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_rs_ops = {
+	.ecc = tegra_nand_ooblayout_rs_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static int tegra_nand_ooblayout_bch_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	int bytes_per_step = DIV_ROUND_UP(BITS_PER_STEP_BCH * chip->ecc.strength,
+					  BITS_PER_BYTE);
+
+	if (section > 0)
+		return -ERANGE;
+
+	oobregion->offset = SKIP_SPARE_BYTES;
+	oobregion->length = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops tegra_nand_oob_bch_ops = {
+	.ecc = tegra_nand_ooblayout_bch_ecc,
+	.free = tegra_nand_ooblayout_no_free,
+};
+
+static irqreturn_t tegra_nand_irq(int irq, void *data)
+{
+	struct tegra_nand_controller *ctrl = data;
+	u32 isr, dma;
+
+	isr = readl_relaxed(ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	dev_dbg(ctrl->dev, "isr %08x\n", isr);
+
+	if (!isr && !(dma & DMA_MST_CTRL_IS_DONE))
+		return IRQ_NONE;
+
+	/*
+	 * The bit name is somewhat missleading: This is also set when
+	 * HW ECC was successful. The data sheet states:
+	 * Correctable OR Un-correctable errors occurred in the DMA transfer...
+	 */
+	if (isr & ISR_CORRFAIL_ERR)
+		ctrl->last_read_error = true;
+
+	if (isr & ISR_CMD_DONE)
+		complete(&ctrl->command_complete);
+
+	if (isr & ISR_UND)
+		dev_err(ctrl->dev, "FIFO underrun\n");
+
+	if (isr & ISR_OVR)
+		dev_err(ctrl->dev, "FIFO overrun\n");
+
+	/* handle DMA interrupts */
+	if (dma & DMA_MST_CTRL_IS_DONE) {
+		writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+		complete(&ctrl->dma_complete);
+	}
+
+	/* clear interrupts */
+	writel_relaxed(isr, ctrl->regs + ISR);
+
+	return IRQ_HANDLED;
+}
+
+static const char * const tegra_nand_reg_names[] = {
+	"COMMAND",
+	"STATUS",
+	"ISR",
+	"IER",
+	"CONFIG",
+	"TIMING",
+	NULL,
+	"TIMING2",
+	"CMD_REG1",
+	"CMD_REG2",
+	"ADDR_REG1",
+	"ADDR_REG2",
+	"DMA_MST_CTRL",
+	"DMA_CFG_A",
+	"DMA_CFG_B",
+	"FIFO_CTRL",
+};
+
+static void tegra_nand_dump_reg(struct tegra_nand_controller *ctrl)
+{
+	u32 reg;
+	int i;
+
+	dev_err(ctrl->dev, "Tegra NAND controller register dump\n");
+	for (i = 0; i < ARRAY_SIZE(tegra_nand_reg_names); i++) {
+		const char *reg_name = tegra_nand_reg_names[i];
+
+		if (!reg_name)
+			continue;
+
+		reg = readl_relaxed(ctrl->regs + (i * 4));
+		dev_err(ctrl->dev, "%s: 0x%08x\n", reg_name, reg);
+	}
+}
+
+static void tegra_nand_controller_abort(struct tegra_nand_controller *ctrl)
+{
+	u32 isr, dma;
+
+	disable_irq(ctrl->irq);
+
+	/* Abort current command/DMA operation */
+	writel_relaxed(0, ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(0, ctrl->regs + COMMAND);
+
+	/* clear interrupts */
+	isr = readl_relaxed(ctrl->regs + ISR);
+	writel_relaxed(isr, ctrl->regs + ISR);
+	dma = readl_relaxed(ctrl->regs + DMA_MST_CTRL);
+	writel_relaxed(dma, ctrl->regs + DMA_MST_CTRL);
+
+	reinit_completion(&ctrl->command_complete);
+	reinit_completion(&ctrl->dma_complete);
+
+	enable_irq(ctrl->irq);
+}
+
+static int tegra_nand_cmd(struct nand_chip *chip,
+			  const struct nand_subop *subop)
+{
+	const struct nand_op_instr *instr;
+	const struct nand_op_instr *instr_data_in = NULL;
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	unsigned int op_id, size = 0, offset = 0;
+	bool first_cmd = true;
+	u32 reg, cmd = 0;
+	int ret;
+
+	for (op_id = 0; op_id < subop->ninstrs; op_id++) {
+		unsigned int naddrs, i;
+		const u8 *addrs;
+		u32 addr1 = 0, addr2 = 0;
+
+		instr = &subop->instrs[op_id];
+
+		switch (instr->type) {
+		case NAND_OP_CMD_INSTR:
+			if (first_cmd) {
+				cmd |= COMMAND_CLE;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG1);
+			} else {
+				cmd |= COMMAND_SEC_CMD;
+				writel_relaxed(instr->ctx.cmd.opcode,
+					       ctrl->regs + CMD_REG2);
+			}
+			first_cmd = false;
+			break;
+
+		case NAND_OP_ADDR_INSTR:
+			offset = nand_subop_get_addr_start_off(subop, op_id);
+			naddrs = nand_subop_get_num_addr_cyc(subop, op_id);
+			addrs = &instr->ctx.addr.addrs[offset];
+
+			cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(naddrs);
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr1 |= *addrs++ << (BITS_PER_BYTE * i);
+			naddrs -= i;
+			for (i = 0; i < min_t(unsigned int, 4, naddrs); i++)
+				addr2 |= *addrs++ << (BITS_PER_BYTE * i);
+
+			writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+			writel_relaxed(addr2, ctrl->regs + ADDR_REG2);
+			break;
+
+		case NAND_OP_DATA_IN_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_RX | COMMAND_A_VALID;
+
+			instr_data_in = instr;
+			break;
+
+		case NAND_OP_DATA_OUT_INSTR:
+			size = nand_subop_get_data_len(subop, op_id);
+			offset = nand_subop_get_data_start_off(subop, op_id);
+
+			cmd |= COMMAND_TRANS_SIZE(size) | COMMAND_PIO |
+				COMMAND_TX | COMMAND_A_VALID;
+			memcpy(&reg, instr->ctx.data.buf.out + offset, size);
+
+			writel_relaxed(reg, ctrl->regs + RESP);
+			break;
+
+		case NAND_OP_WAITRDY_INSTR:
+			cmd |= COMMAND_RBSY_CHK;
+			break;
+		}
+	}
+
+	cmd |= COMMAND_GO | COMMAND_CE(ctrl->cur_cs);
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		return -ETIMEDOUT;
+	}
+
+	if (instr_data_in) {
+		reg = readl_relaxed(ctrl->regs + RESP);
+		memcpy(instr_data_in->ctx.data.buf.in + offset, &reg, size);
+	}
+
+	return 0;
+}
+
+static const struct nand_op_parser tegra_nand_op_parser = NAND_OP_PARSER(
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_DATA_OUT_ELEM(false, 4)),
+	NAND_OP_PARSER_PATTERN(tegra_nand_cmd,
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_ADDR_ELEM(true, 8),
+		NAND_OP_PARSER_PAT_CMD_ELEM(true),
+		NAND_OP_PARSER_PAT_WAITRDY_ELEM(true),
+		NAND_OP_PARSER_PAT_DATA_IN_ELEM(true, 4)),
+	);
+
+static int tegra_nand_exec_op(struct nand_chip *chip,
+			      const struct nand_operation *op,
+			      bool check_only)
+{
+	return nand_op_parser_exec_op(chip, &tegra_nand_op_parser, op,
+				      check_only);
+}
+
+static void tegra_nand_select_chip(struct mtd_info *mtd, int die_nr)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+
+	if (die_nr < 0 || die_nr > 1) {
+		ctrl->cur_cs = -1;
+		return;
+	}
+
+	ctrl->cur_cs = nand->cs[die_nr];
+}
+
+static void tegra_nand_hw_ecc(struct tegra_nand_controller *ctrl,
+			      struct nand_chip *chip, bool enable)
+{
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+
+	if (chip->ecc.algo == NAND_ECC_BCH && enable)
+		writel_relaxed(nand->bch_config, ctrl->regs + BCH_CONFIG);
+	else
+		writel_relaxed(0, ctrl->regs + BCH_CONFIG);
+
+	if (enable)
+		writel_relaxed(nand->config_ecc, ctrl->regs + CONFIG);
+	else
+		writel_relaxed(nand->config, ctrl->regs + CONFIG);
+}
+
+static int tegra_nand_page_xfer(struct mtd_info *mtd, struct nand_chip *chip,
+				void *buf, void *oob_buf, int oob_len, int page,
+				bool read)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	enum dma_data_direction dir = read ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
+	dma_addr_t dma_addr = 0, dma_addr_oob = 0;
+	u32 addr1, cmd, dma_ctrl;
+	int ret;
+
+	if (read) {
+		writel_relaxed(NAND_CMD_READ0, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_READSTART, ctrl->regs + CMD_REG2);
+	} else {
+		writel_relaxed(NAND_CMD_SEQIN, ctrl->regs + CMD_REG1);
+		writel_relaxed(NAND_CMD_PAGEPROG, ctrl->regs + CMD_REG2);
+	}
+	cmd = COMMAND_CLE | COMMAND_SEC_CMD;
+
+	/* Lower 16-bits are column, by default 0 */
+	addr1 = page << 16;
+
+	if (!buf)
+		addr1 |= mtd->writesize;
+	writel_relaxed(addr1, ctrl->regs + ADDR_REG1);
+
+	if (chip->options & NAND_ROW_ADDR_3) {
+		writel_relaxed(page >> 16, ctrl->regs + ADDR_REG2);
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(5);
+	} else {
+		cmd |= COMMAND_ALE | COMMAND_ALE_SIZE(4);
+	}
+
+	if (buf) {
+		dma_addr = dma_map_single(ctrl->dev, buf, mtd->writesize, dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			return -EINVAL;
+		}
+
+		writel_relaxed(mtd->writesize - 1, ctrl->regs + DMA_CFG_A);
+		writel_relaxed(dma_addr, ctrl->regs + DATA_PTR);
+	}
+
+	if (oob_buf) {
+		dma_addr_oob = dma_map_single(ctrl->dev, oob_buf, mtd->oobsize,
+					      dir);
+		ret = dma_mapping_error(ctrl->dev, dma_addr_oob);
+		if (ret) {
+			dev_err(ctrl->dev, "dma mapping error\n");
+			ret = -EINVAL;
+			goto err_unmap_dma_page;
+		}
+
+		writel_relaxed(oob_len - 1, ctrl->regs + DMA_CFG_B);
+		writel_relaxed(dma_addr_oob, ctrl->regs + TAG_PTR);
+	}
+
+	dma_ctrl = DMA_MST_CTRL_GO | DMA_MST_CTRL_PERF_EN |
+		   DMA_MST_CTRL_IE_DONE | DMA_MST_CTRL_IS_DONE |
+		   DMA_MST_CTRL_BURST_16;
+
+	if (buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_A;
+	if (oob_buf)
+		dma_ctrl |= DMA_MST_CTRL_EN_B;
+
+	if (read)
+		dma_ctrl |= DMA_MST_CTRL_IN | DMA_MST_CTRL_REUSE;
+	else
+		dma_ctrl |= DMA_MST_CTRL_OUT;
+
+	writel_relaxed(dma_ctrl, ctrl->regs + DMA_MST_CTRL);
+
+	cmd |= COMMAND_GO | COMMAND_RBSY_CHK | COMMAND_TRANS_SIZE(9) |
+	       COMMAND_CE(ctrl->cur_cs);
+
+	if (buf)
+		cmd |= COMMAND_A_VALID;
+	if (oob_buf)
+		cmd |= COMMAND_B_VALID;
+
+	if (read)
+		cmd |= COMMAND_RX;
+	else
+		cmd |= COMMAND_TX | COMMAND_AFT_DAT;
+
+	writel_relaxed(cmd, ctrl->regs + COMMAND);
+
+	ret = wait_for_completion_timeout(&ctrl->command_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "COMMAND timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+
+	ret = wait_for_completion_timeout(&ctrl->dma_complete,
+					  msecs_to_jiffies(500));
+	if (!ret) {
+		dev_err(ctrl->dev, "DMA timeout\n");
+		tegra_nand_dump_reg(ctrl);
+		tegra_nand_controller_abort(ctrl);
+		ret = -ETIMEDOUT;
+		goto err_unmap_dma;
+	}
+	ret = 0;
+
+err_unmap_dma:
+	if (oob_buf)
+		dma_unmap_single(ctrl->dev, dma_addr_oob, mtd->oobsize, dir);
+err_unmap_dma_page:
+	if (buf)
+		dma_unmap_single(ctrl->dev, dma_addr, mtd->writesize, dir);
+
+	return ret;
+}
+
+static int tegra_nand_read_page_raw(struct mtd_info *mtd,
+				    struct nand_chip *chip, u8 *buf,
+				    int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, buf, oob_buf,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_page_raw(struct mtd_info *mtd,
+				     struct nand_chip *chip, const u8 *buf,
+				     int oob_required, int page)
+{
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+
+	return tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				     mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
+			       int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, true);
+}
+
+static int tegra_nand_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
+				int page)
+{
+	return tegra_nand_page_xfer(mtd, chip, NULL, chip->oob_poi,
+				    mtd->oobsize, page, false);
+}
+
+static int tegra_nand_read_page_hwecc(struct mtd_info *mtd,
+				      struct nand_chip *chip, u8 *buf,
+				      int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	u32 dec_stat, max_corr_cnt;
+	unsigned long fail_sec_flag;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, buf, oob_buf, 0, page, true);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+	if (ret)
+		return ret;
+
+	/* No correctable or un-correctable errors, page must have 0 bitflips */
+	if (!ctrl->last_read_error)
+		return 0;
+
+	/*
+	 * Correctable or un-correctable errors occurred. Use DEC_STAT_BUF
+	 * which contains information for all ECC selections.
+	 *
+	 * Note that since we do not use Command Queues DEC_RESULT does not
+	 * state the number of pages we can read from the DEC_STAT_BUF. But
+	 * since CORRFAIL_ERR did occur during page read we do have a valid
+	 * result in DEC_STAT_BUF.
+	 */
+	ctrl->last_read_error = false;
+	dec_stat = readl_relaxed(ctrl->regs + DEC_STAT_BUF);
+
+	fail_sec_flag = (dec_stat & DEC_STAT_BUF_FAIL_SEC_FLAG_MASK) >>
+			DEC_STAT_BUF_FAIL_SEC_FLAG_SHIFT;
+
+	max_corr_cnt = (dec_stat & DEC_STAT_BUF_MAX_CORR_CNT_MASK) >>
+		       DEC_STAT_BUF_MAX_CORR_CNT_SHIFT;
+
+	if (fail_sec_flag) {
+		int bit, max_bitflips = 0;
+
+		/*
+		 * Since we do not support subpage writes, a complete page
+		 * is either written or not. We can take a shortcut here by
+		 * checking wheather any of the sector has been successful
+		 * read. If at least one sectors has been read successfully,
+		 * the page must have been a written previously. It cannot
+		 * be an erased page.
+		 *
+		 * E.g. controller might return fail_sec_flag with 0x4, which
+		 * would mean only the third sector failed to correct. The
+		 * page must have been written and the third sector is really
+		 * not correctable anymore.
+		 */
+		if (fail_sec_flag ^ GENMASK(chip->ecc.steps - 1, 0)) {
+			mtd->ecc_stats.failed += hweight8(fail_sec_flag);
+			return max_corr_cnt;
+		}
+
+		/*
+		 * All sectors failed to correct, but the ECC isn't smart
+		 * enough to figure out if a page is really just erased.
+		 * Read OOB data and check whether data/OOB is completely
+		 * erased or if error correction just failed for all sub-
+		 * pages.
+		 */
+		ret = tegra_nand_read_oob(mtd, chip, page);
+		if (ret < 0)
+			return ret;
+
+		for_each_set_bit(bit, &fail_sec_flag, chip->ecc.steps) {
+			u8 *data = buf + (chip->ecc.size * bit);
+			u8 *oob = chip->oob_poi + nand->ecc.offset +
+				  (chip->ecc.bytes * bit);
+
+			ret = nand_check_erased_ecc_chunk(data, chip->ecc.size,
+							  oob, chip->ecc.bytes,
+							  NULL, 0,
+							  chip->ecc.strength);
+			if (ret < 0) {
+				mtd->ecc_stats.failed++;
+			} else {
+				mtd->ecc_stats.corrected += ret;
+				max_bitflips = max(ret, max_bitflips);
+			}
+		}
+
+		return max_t(unsigned int, max_corr_cnt, max_bitflips);
+	} else {
+		int corr_sec_flag;
+
+		corr_sec_flag = (dec_stat & DEC_STAT_BUF_CORR_SEC_FLAG_MASK) >>
+				DEC_STAT_BUF_CORR_SEC_FLAG_SHIFT;
+
+		/*
+		 * The value returned in the register is the maximum of
+		 * bitflips encountered in any of the ECC regions. As there is
+		 * no way to get the number of bitflips in a specific regions
+		 * we are not able to deliver correct stats but instead
+		 * overestimate the number of corrected bitflips by assuming
+		 * that all regions where errors have been corrected
+		 * encountered the maximum number of bitflips.
+		 */
+		mtd->ecc_stats.corrected += max_corr_cnt * hweight8(corr_sec_flag);
+
+		return max_corr_cnt;
+	}
+}
+
+static int tegra_nand_write_page_hwecc(struct mtd_info *mtd,
+				       struct nand_chip *chip, const u8 *buf,
+				       int oob_required, int page)
+{
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	void *oob_buf = oob_required ? chip->oob_poi : NULL;
+	int ret;
+
+	tegra_nand_hw_ecc(ctrl, chip, true);
+	ret = tegra_nand_page_xfer(mtd, chip, (void *)buf, oob_buf,
+				   0, page, false);
+	tegra_nand_hw_ecc(ctrl, chip, false);
+
+	return ret;
+}
+
+static void tegra_nand_setup_timing(struct tegra_nand_controller *ctrl,
+				    const struct nand_sdr_timings *timings)
+{
+	/*
+	 * The period (and all other timings in this function) is in ps,
+	 * so need to take care here to avoid integer overflows.
+	 */
+	unsigned int rate = clk_get_rate(ctrl->clk) / 1000000;
+	unsigned int period = DIV_ROUND_UP(1000000, rate);
+	u32 val, reg = 0;
+
+	val = DIV_ROUND_UP(max3(timings->tAR_min, timings->tRR_min,
+				timings->tRC_min), period);
+	reg |= TIMING_TCR_TAR_TRR(OFFSET(val, 3));
+
+	val = DIV_ROUND_UP(max(max(timings->tCS_min, timings->tCH_min),
+			       max(timings->tALS_min, timings->tALH_min)),
+			   period);
+	reg |= TIMING_TCS(OFFSET(val, 2));
+
+	val = DIV_ROUND_UP(max(timings->tRP_min, timings->tREA_max) + 6000,
+			   period);
+	reg |= TIMING_TRP(OFFSET(val, 1)) | TIMING_TRP_RESP(OFFSET(val, 1));
+
+	reg |= TIMING_TWB(OFFSET(DIV_ROUND_UP(timings->tWB_max, period), 1));
+	reg |= TIMING_TWHR(OFFSET(DIV_ROUND_UP(timings->tWHR_min, period), 1));
+	reg |= TIMING_TWH(OFFSET(DIV_ROUND_UP(timings->tWH_min, period), 1));
+	reg |= TIMING_TWP(OFFSET(DIV_ROUND_UP(timings->tWP_min, period), 1));
+	reg |= TIMING_TRH(OFFSET(DIV_ROUND_UP(timings->tREH_min, period), 1));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_1);
+
+	val = DIV_ROUND_UP(timings->tADL_min, period);
+	reg = TIMING_TADL(OFFSET(val, 3));
+
+	writel_relaxed(reg, ctrl->regs + TIMING_2);
+}
+
+static int tegra_nand_setup_data_interface(struct mtd_info *mtd, int csline,
+					const struct nand_data_interface *conf)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	const struct nand_sdr_timings *timings;
+
+	timings = nand_get_sdr_timings(conf);
+	if (IS_ERR(timings))
+		return PTR_ERR(timings);
+
+	if (csline == NAND_DATA_IFACE_CHECK_ONLY)
+		return 0;
+
+	tegra_nand_setup_timing(ctrl, timings);
+
+	return 0;
+}
+
+static const int rs_strength_bootable[] = { 4 };
+static const int rs_strength[] = { 4, 6, 8 };
+static const int bch_strength_bootable[] = { 8, 16 };
+static const int bch_strength[] = { 4, 8, 14, 16 };
+
+static int tegra_nand_get_strength(struct nand_chip *chip, const int *strength,
+				   int strength_len, int bits_per_step,
+				   int oobsize)
+{
+	bool maximize = chip->ecc.options & NAND_ECC_MAXIMIZE;
+	int i;
+
+	/*
+	 * Loop through available strengths. Backwards in case we try to
+	 * maximize the BCH strength.
+	 */
+	for (i = 0; i < strength_len; i++) {
+		int strength_sel, bytes_per_step, bytes_per_page;
+
+		if (maximize) {
+			strength_sel = strength[strength_len - i - 1];
+		} else {
+			strength_sel = strength[i];
+
+			if (strength_sel < chip->ecc_strength_ds)
+				continue;
+		}
+
+		bytes_per_step = DIV_ROUND_UP(bits_per_step * strength_sel,
+					      BITS_PER_BYTE);
+		bytes_per_page = round_up(bytes_per_step * chip->ecc.steps, 4);
+
+		/* Check whether strength fits OOB */
+		if (bytes_per_page < (oobsize - SKIP_SPARE_BYTES))
+			return strength_sel;
+	}
+
+	return -EINVAL;
+}
+
+static int tegra_nand_select_strength(struct nand_chip *chip, int oobsize)
+{
+	const int *strength;
+	int strength_len, bits_per_step;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = rs_strength_bootable;
+			strength_len = ARRAY_SIZE(rs_strength_bootable);
+		} else {
+			strength = rs_strength;
+			strength_len = ARRAY_SIZE(rs_strength);
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH;
+		if (chip->options & NAND_IS_BOOT_MEDIUM) {
+			strength = bch_strength_bootable;
+			strength_len = ARRAY_SIZE(bch_strength_bootable);
+		} else {
+			strength = bch_strength;
+			strength_len = ARRAY_SIZE(bch_strength);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return tegra_nand_get_strength(chip, strength, strength_len,
+				       bits_per_step, oobsize);
+}
+
+static int tegra_nand_chips_init(struct device *dev,
+				 struct tegra_nand_controller *ctrl)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *np_nand;
+	int nsels, nchips = of_get_child_count(np);
+	struct tegra_nand_chip *nand;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int bits_per_step;
+	int ret;
+	u32 cs;
+
+	if (nchips != 1) {
+		dev_err(dev, "Currently only one NAND chip supported\n");
+		return -EINVAL;
+	}
+
+	np_nand = of_get_next_child(np, NULL);
+
+	nsels = of_property_count_elems_of_size(np_nand, "reg", sizeof(u32));
+	if (nsels != 1) {
+		dev_err(dev, "Missing/invalid reg property\n");
+		return -EINVAL;
+	}
+
+	/* Retrieve CS id, currently only single die NAND supported */
+	ret = of_property_read_u32(np_nand, "reg", &cs);
+	if (ret) {
+		dev_err(dev, "could not retrieve reg property: %d\n", ret);
+		return ret;
+	}
+
+	nand = devm_kzalloc(dev, sizeof(*nand), GFP_KERNEL);
+	if (!nand)
+		return -ENOMEM;
+
+	nand->cs[0] = cs;
+
+	nand->wp_gpio = devm_gpiod_get_optional(dev, "wp", GPIOD_OUT_LOW);
+
+	if (IS_ERR(nand->wp_gpio)) {
+		ret = PTR_ERR(nand->wp_gpio);
+		dev_err(dev, "Failed to request WP GPIO: %d\n", ret);
+		return ret;
+	}
+
+	chip = &nand->chip;
+	chip->controller = &ctrl->controller;
+
+	mtd = nand_to_mtd(chip);
+
+	mtd->dev.parent = dev;
+	mtd->owner = THIS_MODULE;
+
+	nand_set_flash_node(chip, np_nand);
+
+	if (!mtd->name)
+		mtd->name = "tegra_nand";
+
+	chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER;
+	chip->exec_op = tegra_nand_exec_op;
+	chip->select_chip = tegra_nand_select_chip;
+	chip->setup_data_interface = tegra_nand_setup_data_interface;
+
+	ret = nand_scan_ident(mtd, 1, NULL);
+	if (ret)
+		return ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	chip->ecc.steps = mtd->writesize / chip->ecc.size;
+	if (chip->ecc_step_ds != 512) {
+		dev_err(dev, "Unsupported step size %d\n", chip->ecc_step_ds);
+		return -EINVAL;
+	}
+
+	chip->ecc.read_page = tegra_nand_read_page_hwecc;
+	chip->ecc.write_page = tegra_nand_write_page_hwecc;
+	chip->ecc.read_page_raw = tegra_nand_read_page_raw;
+	chip->ecc.write_page_raw = tegra_nand_write_page_raw;
+	chip->ecc.read_oob = tegra_nand_read_oob;
+	chip->ecc.write_oob = tegra_nand_write_oob;
+
+	if (chip->options & NAND_BUSWIDTH_16)
+		nand->config |= CONFIG_BUS_WIDTH_16;
+
+	if (chip->ecc.algo == NAND_ECC_UNKNOWN) {
+		if (mtd->writesize < 2048)
+			chip->ecc.algo = NAND_ECC_RS;
+		else
+			chip->ecc.algo = NAND_ECC_BCH;
+	}
+
+	if (chip->ecc.algo == NAND_ECC_BCH && mtd->writesize < 2048) {
+		dev_err(dev, "BCH supports 2K or 4K page size only\n");
+		return -EINVAL;
+	}
+
+	if (!chip->ecc.strength) {
+		ret = tegra_nand_select_strength(chip, mtd->oobsize);
+		if (ret < 0) {
+			dev_err(dev, "No valid strength found, minimum %d\n",
+				chip->ecc_strength_ds);
+			return ret;
+		}
+
+		chip->ecc.strength = ret;
+	}
+
+	nand->config_ecc = CONFIG_PIPE_EN | CONFIG_SKIP_SPARE |
+			   CONFIG_SKIP_SPARE_SIZE_4;
+
+	switch (chip->ecc.algo) {
+	case NAND_ECC_RS:
+		bits_per_step = BITS_PER_STEP_RS * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_rs_ops);
+		nand->config_ecc |= CONFIG_HW_ECC | CONFIG_ECC_SEL |
+				    CONFIG_ERR_COR;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->config_ecc |= CONFIG_TVAL_4;
+			break;
+		case 6:
+			nand->config_ecc |= CONFIG_TVAL_6;
+			break;
+		case 8:
+			nand->config_ecc |= CONFIG_TVAL_8;
+			break;
+		default:
+			dev_err(dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	case NAND_ECC_BCH:
+		bits_per_step = BITS_PER_STEP_BCH * chip->ecc.strength;
+		mtd_set_ooblayout(mtd, &tegra_nand_oob_bch_ops);
+		nand->bch_config = BCH_ENABLE;
+		switch (chip->ecc.strength) {
+		case 4:
+			nand->bch_config |= BCH_TVAL_4;
+			break;
+		case 8:
+			nand->bch_config |= BCH_TVAL_8;
+			break;
+		case 14:
+			nand->bch_config |= BCH_TVAL_14;
+			break;
+		case 16:
+			nand->bch_config |= BCH_TVAL_16;
+			break;
+		default:
+			dev_err(dev, "ECC strength %d not supported\n",
+				chip->ecc.strength);
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err(dev, "ECC algorithm not supported\n");
+		return -EINVAL;
+	}
+
+	dev_info(dev, "Using %s with strength %d per 512 byte step\n",
+		 chip->ecc.algo == NAND_ECC_BCH ? "BCH" : "RS",
+		 chip->ecc.strength);
+
+	chip->ecc.bytes = DIV_ROUND_UP(bits_per_step, BITS_PER_BYTE);
+
+	switch (mtd->writesize) {
+	case 256:
+		nand->config |= CONFIG_PS_256;
+		break;
+	case 512:
+		nand->config |= CONFIG_PS_512;
+		break;
+	case 1024:
+		nand->config |= CONFIG_PS_1024;
+		break;
+	case 2048:
+		nand->config |= CONFIG_PS_2048;
+		break;
+	case 4096:
+		nand->config |= CONFIG_PS_4096;
+		break;
+	default:
+		dev_err(dev, "Unsupported writesize %d\n", mtd->writesize);
+		return -ENODEV;
+	}
+
+	/* Store complete configuration for HW ECC in config_ecc */
+	nand->config_ecc |= nand->config;
+
+	/* Non-HW ECC read/writes complete OOB */
+	nand->config |= CONFIG_TAG_BYTE_SIZE(mtd->oobsize - 1);
+	writel_relaxed(nand->config, ctrl->regs + CONFIG);
+
+	ret = nand_scan_tail(mtd);
+	if (ret)
+		return ret;
+
+	mtd_ooblayout_ecc(mtd, 0, &nand->ecc);
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
+		return ret;
+	}
+
+	ctrl->chip = chip;
+
+	return 0;
+}
+
+static int tegra_nand_probe(struct platform_device *pdev)
+{
+	struct reset_control *rst;
+	struct tegra_nand_controller *ctrl;
+	struct resource *res;
+	int err = 0;
+
+	ctrl = devm_kzalloc(&pdev->dev, sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return -ENOMEM;
+
+	ctrl->dev = &pdev->dev;
+	nand_hw_control_init(&ctrl->controller);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	ctrl->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(ctrl->regs))
+		return PTR_ERR(ctrl->regs);
+
+	rst = devm_reset_control_get(&pdev->dev, "nand");
+	if (IS_ERR(rst))
+		return PTR_ERR(rst);
+
+	ctrl->clk = devm_clk_get(&pdev->dev, "nand");
+	if (IS_ERR(ctrl->clk))
+		return PTR_ERR(ctrl->clk);
+
+	err = clk_prepare_enable(ctrl->clk);
+	if (err)
+		return err;
+
+	err = reset_control_reset(rst);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to reset HW: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(HWSTATUS_CMD_DEFAULT, ctrl->regs + HWSTATUS_CMD);
+	writel_relaxed(HWSTATUS_MASK_DEFAULT, ctrl->regs + HWSTATUS_MASK);
+	writel_relaxed(INT_MASK, ctrl->regs + IER);
+
+	init_completion(&ctrl->command_complete);
+	init_completion(&ctrl->dma_complete);
+
+	ctrl->irq = platform_get_irq(pdev, 0);
+	err = devm_request_irq(&pdev->dev, ctrl->irq, tegra_nand_irq, 0,
+			       dev_name(&pdev->dev), ctrl);
+	if (err) {
+		dev_err(ctrl->dev, "Failed to get IRQ: %d\n", err);
+		goto err_disable_clk;
+	}
+
+	writel_relaxed(DMA_MST_CTRL_IS_DONE, ctrl->regs + DMA_MST_CTRL);
+
+	err = tegra_nand_chips_init(ctrl->dev, ctrl);
+	if (err)
+		goto err_disable_clk;
+
+	platform_set_drvdata(pdev, ctrl);
+
+	return 0;
+
+err_disable_clk:
+	clk_disable_unprepare(ctrl->clk);
+	return err;
+}
+
+static int tegra_nand_remove(struct platform_device *pdev)
+{
+	struct tegra_nand_controller *ctrl = platform_get_drvdata(pdev);
+	struct nand_chip *chip = ctrl->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	nand_cleanup(chip);
+
+	clk_disable_unprepare(ctrl->clk);
+
+	return 0;
+}
+
+static const struct of_device_id tegra_nand_of_match[] = {
+	{ .compatible = "nvidia,tegra20-nand" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, tegra_nand_of_match);
+
+static struct platform_driver tegra_nand_driver = {
+	.driver = {
+		.name = "tegra-nand",
+		.of_match_table = tegra_nand_of_match,
+	},
+	.probe = tegra_nand_probe,
+	.remove = tegra_nand_remove,
+};
+module_platform_driver(tegra_nand_driver);
+
+MODULE_DESCRIPTION("NVIDIA Tegra NAND driver");
+MODULE_AUTHOR("Thierry Reding <thierry.reding@nvidia.com>");
+MODULE_AUTHOR("Lucas Stach <dev@lynxeye.de>");
+MODULE_AUTHOR("Stefan Agner <stefan@agner.ch>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From ed6d0285f81cbf27d8294b47ac0bc8f28041b186 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Mon, 25 Jun 2018 10:44:43 +1200
Subject: mtd: rawnand: marvell: Handle on-die ECC

>From the controllers point of view this is the same as no or
software only ECC.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/marvell_nand.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index ebb1d141b900..ba6889bbe802 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2157,6 +2157,7 @@ static int marvell_nand_ecc_init(struct mtd_info *mtd,
 		break;
 	case NAND_ECC_NONE:
 	case NAND_ECC_SOFT:
+	case NAND_ECC_ON_DIE:
 		if (!nfc->caps->is_nfcv2 && mtd->writesize != SZ_512 &&
 		    mtd->writesize != SZ_2K) {
 			dev_err(nfc->dev, "NFCv1 cannot write %d bytes pages\n",
-- 
cgit v1.2.3


From 00ce4e039ad5bded462931606c3063ff691964b7 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Mon, 25 Jun 2018 10:44:44 +1200
Subject: mtd: rawnand: add manufacturer fixup for ONFI parameter page

This is called after the ONFI parameter page checksum is verified
and allows us to override the contents of the parameter page.

Suggested-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 4 ++++
 include/linux/mtd/rawnand.h      | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 1c633f80c3e1..f362c09a71d7 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5168,6 +5168,10 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		}
 	}
 
+	if (chip->manufacturer.desc && chip->manufacturer.desc->ops &&
+	    chip->manufacturer.desc->ops->fixup_onfi_param_page)
+		chip->manufacturer.desc->ops->fixup_onfi_param_page(chip, p);
+
 	/* Check version */
 	val = le16_to_cpu(p->revision);
 	if (val & (1 << 5))
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 80aeeca03f36..dc4538b58b84 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -785,11 +785,15 @@ nand_get_sdr_timings(const struct nand_data_interface *conf)
  *	  implementation) if any.
  * @cleanup: the ->init() function may have allocated resources, ->cleanup()
  *	     is here to let vendor specific code release those resources.
+ * @fixup_onfi_param_page: apply vendor specific fixups to the ONFI parameter
+ *			   page. This is called after the checksum is verified.
  */
 struct nand_manufacturer_ops {
 	void (*detect)(struct nand_chip *chip);
 	int (*init)(struct nand_chip *chip);
 	void (*cleanup)(struct nand_chip *chip);
+	void (*fixup_onfi_param_page)(struct nand_chip *chip,
+				      struct nand_onfi_params *p);
 };
 
 /**
-- 
cgit v1.2.3


From 872b71ff084ab125c68073d9e69acfd7095f2015 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Mon, 25 Jun 2018 10:44:45 +1200
Subject: mtd: rawnand: add defines for ONFI version bits

Add defines for the ONFI version bits and use them in
nand_flash_detect_onfi().

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 10 +++++-----
 include/linux/mtd/rawnand.h      | 11 +++++++++++
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index f362c09a71d7..dbf6e80e9ab5 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5174,15 +5174,15 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 
 	/* Check version */
 	val = le16_to_cpu(p->revision);
-	if (val & (1 << 5))
+	if (val & ONFI_VERSION_2_3)
 		chip->parameters.onfi.version = 23;
-	else if (val & (1 << 4))
+	else if (val & ONFI_VERSION_2_2)
 		chip->parameters.onfi.version = 22;
-	else if (val & (1 << 3))
+	else if (val & ONFI_VERSION_2_1)
 		chip->parameters.onfi.version = 21;
-	else if (val & (1 << 2))
+	else if (val & ONFI_VERSION_2_0)
 		chip->parameters.onfi.version = 20;
-	else if (val & (1 << 1))
+	else if (val & ONFI_VERSION_1_0)
 		chip->parameters.onfi.version = 10;
 
 	if (!chip->parameters.onfi.version) {
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index dc4538b58b84..fbac4741da52 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -237,6 +237,17 @@ enum nand_ecc_algo {
 /* Keep gcc happy */
 struct nand_chip;
 
+/* ONFI version bits */
+#define ONFI_VERSION_1_0		BIT(1)
+#define ONFI_VERSION_2_0		BIT(2)
+#define ONFI_VERSION_2_1		BIT(3)
+#define ONFI_VERSION_2_2		BIT(4)
+#define ONFI_VERSION_2_3		BIT(5)
+#define ONFI_VERSION_3_0		BIT(6)
+#define ONFI_VERSION_3_1		BIT(7)
+#define ONFI_VERSION_3_2		BIT(8)
+#define ONFI_VERSION_4_0		BIT(9)
+
 /* ONFI features */
 #define ONFI_FEATURE_16_BIT_BUS		(1 << 0)
 #define ONFI_FEATURE_EXT_PARAM_PAGE	(1 << 7)
-- 
cgit v1.2.3


From 243f37cb1f63dfdc4451802aa519fb3c3d9c9d32 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Mon, 25 Jun 2018 10:44:46 +1200
Subject: mtd: rawnand: micron: add fixup for ONFI revision

Some Micron NAND chips (MT29F1G08ABAFAWP-ITE:F) report 00 00 for the
revision number field of the ONFI parameter page. Rather than rejecting
these outright assume ONFI version 1.0 if the revision number is 00 00.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 203faba0a9c1..d30bd4df9b12 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -290,6 +290,19 @@ static int micron_nand_init(struct nand_chip *chip)
 	return 0;
 }
 
+static void micron_fixup_onfi_param_page(struct nand_chip *chip,
+					 struct nand_onfi_params *p)
+{
+	/*
+	 * MT29F1G08ABAFAWP-ITE:F and possibly others report 00 00 for the
+	 * revision number field of the ONFI parameter page. Assume ONFI
+	 * version 1.0 if the revision number is 00 00.
+	 */
+	if (le16_to_cpu(p->revision) == 0)
+		p->revision = cpu_to_le16(ONFI_VERSION_1_0);
+}
+
 const struct nand_manufacturer_ops micron_nand_manuf_ops = {
 	.init = micron_nand_init,
+	.fixup_onfi_param_page = micron_fixup_onfi_param_page,
 };
-- 
cgit v1.2.3


From 1b48b7202c43e41c9f05d39901567dbcad5dc307 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:25:49 +0200
Subject: dma-fence: remove fill_driver_data callback
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Noticed while I was typing docs. Entirely unused.

v2: Remove reference in @timeline_value_str too. While at it clarify
why timeline_value_str has a fence parameter - we don't have an
explicit timeline structure unfortunately.

Cc: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Christian König <christian.koenig@amd.com> (v1)
Cc: Christian König <christian.koenig@amd.com> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-2-daniel.vetter@ffwll.ch
---
 include/linux/dma-fence.h | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index eb9b05aa5aea..111aefe1c956 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -217,17 +217,6 @@ struct dma_fence_ops {
 	 */
 	void (*release)(struct dma_fence *fence);
 
-	/**
-	 * @fill_driver_data:
-	 *
-	 * Callback to fill in free-form debug info.
-	 *
-	 * Returns amount of bytes filled, or negative error on failure.
-	 *
-	 * This callback is optional.
-	 */
-	int (*fill_driver_data)(struct dma_fence *fence, void *data, int size);
-
 	/**
 	 * @fence_value_str:
 	 *
@@ -242,8 +231,9 @@ struct dma_fence_ops {
 	 * @timeline_value_str:
 	 *
 	 * Fills in the current value of the timeline as a string, like the
-	 * sequence number. This should match what @fill_driver_data prints for
-	 * the most recently signalled fence (assuming no delayed signalling).
+	 * sequence number. Note that the specific fence passed to this function
+	 * should not matter, drivers should only use it to look up the
+	 * corresponding timeline structures.
 	 */
 	void (*timeline_value_str)(struct dma_fence *fence,
 				   char *str, int size);
-- 
cgit v1.2.3


From c701317a3eb8c012364a8d468f20eabf6df1ad77 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 4 May 2018 16:10:34 +0200
Subject: dma-fence: Make ->enable_signaling optional
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Many drivers have a trivial implementation for ->enable_signaling.
Let's make it optional by assuming that signalling is already
available when the callback isn't present.

v2: Don't do the trick to set the ENABLE_SIGNAL_BIT
unconditionally, it results in an expensive spinlock take for
everyone. Instead just check if the callback is present. Suggested by
Maarten.

Also move misplaced kerneldoc hunk to the right patch.

Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com> (v1)
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180504141034.27727-1-daniel.vetter@ffwll.ch
---
 drivers/dma-buf/dma-fence.c | 9 +++++----
 include/linux/dma-fence.h   | 3 ++-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 4edb9fd3cf47..dd01a1720be9 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -200,7 +200,8 @@ void dma_fence_enable_sw_signaling(struct dma_fence *fence)
 
 	if (!test_and_set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
 			      &fence->flags) &&
-	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)) {
+	    !test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags) &&
+	    fence->ops->enable_signaling) {
 		trace_dma_fence_enable_signal(fence);
 
 		spin_lock_irqsave(fence->lock, flags);
@@ -260,7 +261,7 @@ int dma_fence_add_callback(struct dma_fence *fence, struct dma_fence_cb *cb,
 
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		ret = -ENOENT;
-	else if (!was_set) {
+	else if (!was_set && fence->ops->enable_signaling) {
 		trace_dma_fence_enable_signal(fence);
 
 		if (!fence->ops->enable_signaling(fence)) {
@@ -388,7 +389,7 @@ dma_fence_default_wait(struct dma_fence *fence, bool intr, signed long timeout)
 	if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags))
 		goto out;
 
-	if (!was_set) {
+	if (!was_set && fence->ops->enable_signaling) {
 		trace_dma_fence_enable_signal(fence);
 
 		if (!fence->ops->enable_signaling(fence)) {
@@ -560,7 +561,7 @@ dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
 	       spinlock_t *lock, u64 context, unsigned seqno)
 {
 	BUG_ON(!lock);
-	BUG_ON(!ops || !ops->wait || !ops->enable_signaling ||
+	BUG_ON(!ops || !ops->wait ||
 	       !ops->get_driver_name || !ops->get_timeline_name);
 
 	kref_init(&fence->refcount);
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index 111aefe1c956..c053d19e1e24 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -166,7 +166,8 @@ struct dma_fence_ops {
 	 * released when the fence is signalled (through e.g. the interrupt
 	 * handler).
 	 *
-	 * This callback is mandatory.
+	 * This callback is optional. If this callback is not present, then the
+	 * driver must always have signaling enabled.
 	 */
 	bool (*enable_signaling)(struct dma_fence *fence);
 
-- 
cgit v1.2.3


From 796422f227eef662256dcf74f609abd48cfd1cc9 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:25:51 +0200
Subject: dma-fence: Allow wait_any_timeout for all fences
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When this was introduced in

commit a519435a96597d8cd96123246fea4ae5a6c90b02
Author: Christian König <christian.koenig@amd.com>
Date:   Tue Oct 20 16:34:16 2015 +0200

    dma-buf/fence: add fence_wait_any_timeout function v2

there was a restriction added that this only works if the dma-fence
uses the dma_fence_default_wait hook. Which works for amdgpu, which is
the only caller. Well, until you share some buffers with e.g. i915,
then you get an -EINVAL.

But there's really no reason for this, because all drivers must
support callbacks. The special ->wait hook is only as an optimization;
if the driver needs to create a worker thread for an active callback,
then it can avoid to do that if it knows that there's a process
context available already. So ->wait is just an optimization, just
using the logic in dma_fence_default_wait() should work for all
drivers.

Let's remove this restriction.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-4-daniel.vetter@ffwll.ch
---
 drivers/dma-buf/dma-fence.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index dd01a1720be9..ea343f992112 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -497,11 +497,6 @@ dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count,
 	for (i = 0; i < count; ++i) {
 		struct dma_fence *fence = fences[i];
 
-		if (fence->ops->wait != dma_fence_default_wait) {
-			ret = -EINVAL;
-			goto fence_rm_cb;
-		}
-
 		cb[i].task = current;
 		if (dma_fence_add_callback(fence, &cb[i].base,
 					   dma_fence_default_wait_cb)) {
-- 
cgit v1.2.3


From b17e3abb0af404cb62ad4ef1a5962f58b06e2b78 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 24 Jun 2018 09:21:59 +0200
Subject: s390/dasd: correct numa_node in dasd_alloc_queue

The numa_node field of the tag_set struct has to be explicitly
initialized, otherwise it stays as 0, which is a valid numa node id and
cause memory allocation failure if node 0 is offline.

Acked-by: Stefan Haberland <sth@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/dasd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index d3a38c421503..7c3dddeb781c 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -3118,6 +3118,7 @@ static int dasd_alloc_queue(struct dasd_block *block)
 	block->tag_set.nr_hw_queues = DASD_NR_HW_QUEUES;
 	block->tag_set.queue_depth = DASD_MAX_LCU_DEV * DASD_REQ_PER_DEV;
 	block->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	block->tag_set.numa_node = NUMA_NO_NODE;
 
 	rc = blk_mq_alloc_tag_set(&block->tag_set);
 	if (rc)
-- 
cgit v1.2.3


From d642d6262f4fcfa5d200ec6e218c17f0c15b3390 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 25 Jun 2018 14:30:42 +0200
Subject: s390/scm_blk: correct numa_node in scm_blk_dev_setup

The numa_node field of the tag_set struct has to be explicitly
initialized, otherwise it stays as 0, which is a valid numa node id and
cause memory allocation failure if node 0 is offline.

Acked-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/scm_blk.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/block/scm_blk.c b/drivers/s390/block/scm_blk.c
index b1fcb76dd272..98f66b7b6794 100644
--- a/drivers/s390/block/scm_blk.c
+++ b/drivers/s390/block/scm_blk.c
@@ -455,6 +455,7 @@ int scm_blk_dev_setup(struct scm_blk_dev *bdev, struct scm_device *scmdev)
 	bdev->tag_set.nr_hw_queues = nr_requests;
 	bdev->tag_set.queue_depth = nr_requests_per_io * nr_requests;
 	bdev->tag_set.flags = BLK_MQ_F_SHOULD_MERGE;
+	bdev->tag_set.numa_node = NUMA_NO_NODE;
 
 	ret = blk_mq_alloc_tag_set(&bdev->tag_set);
 	if (ret)
-- 
cgit v1.2.3


From 6b2ddf33baec23dace85bd647e3fc4ac070963e8 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 17 Jun 2018 00:30:43 +0200
Subject: s390/extmem: fix gcc 8 stringop-overflow warning

arch/s390/mm/extmem.c: In function '__segment_load':
arch/s390/mm/extmem.c:436:2: warning: 'strncat' specified bound 7 equals
source length [-Wstringop-overflow=]
  strncat(seg->res_name, " (DCSS)", 7);

What gcc complains about here is the misuse of strncat function, which
in this case does not limit a number of bytes taken from "src", so it is
in the end the same as strcat(seg->res_name, " (DCSS)");

Keeping in mind that a res_name is 15 bytes, strncat in this case
would overflow the buffer and write 0 into alignment byte between the
fields in the struct. To avoid that increasing res_name size to 16,
and reusing strlcat.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/extmem.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c
index 6ad15d3fab81..84111a43ea29 100644
--- a/arch/s390/mm/extmem.c
+++ b/arch/s390/mm/extmem.c
@@ -80,7 +80,7 @@ struct qin64 {
 struct dcss_segment {
 	struct list_head list;
 	char dcss_name[8];
-	char res_name[15];
+	char res_name[16];
 	unsigned long start_addr;
 	unsigned long end;
 	atomic_t ref_count;
@@ -433,7 +433,7 @@ __segment_load (char *name, int do_nonshared, unsigned long *addr, unsigned long
 	memcpy(&seg->res_name, seg->dcss_name, 8);
 	EBCASC(seg->res_name, 8);
 	seg->res_name[8] = '\0';
-	strncat(seg->res_name, " (DCSS)", 7);
+	strlcat(seg->res_name, " (DCSS)", sizeof(seg->res_name));
 	seg->res->name = seg->res_name;
 	rc = seg->vm_segtype;
 	if (rc == SEG_TYPE_SC ||
-- 
cgit v1.2.3


From c6756b7d0c5d57233c985dd1e50ce7b33a15ce6b Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 17 Jun 2018 11:56:17 +0200
Subject: s390/dasd,zfcp: fix gcc 8 stringop-truncation warnings

ccw "busid" should always be NUL-terminated, as evident from e.g.
get_ccwdev_by_busid doing "return (strcmp(bus_id, dev_name(dev)) == 0)".

Replace all strncpy initializing busid with strlcpy. This fixes the
following gcc 8 warnings:

drivers/s390/scsi/zfcp_aux.c:104:2: warning: 'strncpy' specified bound 20
equals destination size [-Wstringop-truncation]
  strncpy(busid, token, ZFCP_BUS_ID_SIZE);

drivers/s390/block/dasd_eer.c:316:2: warning: 'strncpy' specified bound 10
equals destination size [-Wstringop-truncation]
  strncpy(header.busid, dev_name(&device->cdev->dev), DASD_EER_BUSID_SIZE);

drivers/s390/block/dasd_eer.c:359:2: warning: 'strncpy' specified bound 10
equals destination size [-Wstringop-truncation]
  strncpy(header.busid, dev_name(&device->cdev->dev), DASD_EER_BUSID_SIZE);

drivers/s390/block/dasd_devmap.c:429:3: warning: 'strncpy' specified bound
20 equals destination size [-Wstringop-truncation]
   strncpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);

Acked-by: Stefan Haberland <sth@linux.ibm.com>
Acked-by: Steffen Maier <maier@linux.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/dasd_devmap.c | 2 +-
 drivers/s390/block/dasd_eer.c    | 4 ++--
 drivers/s390/scsi/zfcp_aux.c     | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
index b9ebb565ee2c..fab35c6170cc 100644
--- a/drivers/s390/block/dasd_devmap.c
+++ b/drivers/s390/block/dasd_devmap.c
@@ -426,7 +426,7 @@ dasd_add_busid(const char *bus_id, int features)
 	if (!devmap) {
 		/* This bus_id is new. */
 		new->devindex = dasd_max_devindex++;
-		strncpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
+		strlcpy(new->bus_id, bus_id, DASD_BUS_ID_SIZE);
 		new->features = features;
 		new->device = NULL;
 		list_add(&new->list, &dasd_hashlists[hash]);
diff --git a/drivers/s390/block/dasd_eer.c b/drivers/s390/block/dasd_eer.c
index 6ef8714dc693..93bb09da7fdc 100644
--- a/drivers/s390/block/dasd_eer.c
+++ b/drivers/s390/block/dasd_eer.c
@@ -313,7 +313,7 @@ static void dasd_eer_write_standard_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
@@ -356,7 +356,7 @@ static void dasd_eer_write_snss_trigger(struct dasd_device *device,
 	ktime_get_real_ts64(&ts);
 	header.tv_sec = ts.tv_sec;
 	header.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-	strncpy(header.busid, dev_name(&device->cdev->dev),
+	strlcpy(header.busid, dev_name(&device->cdev->dev),
 		DASD_EER_BUSID_SIZE);
 
 	spin_lock_irqsave(&bufferlock, flags);
diff --git a/drivers/s390/scsi/zfcp_aux.c b/drivers/s390/scsi/zfcp_aux.c
index a3a8c8d9d717..94f4d8fe85e0 100644
--- a/drivers/s390/scsi/zfcp_aux.c
+++ b/drivers/s390/scsi/zfcp_aux.c
@@ -101,7 +101,7 @@ static void __init zfcp_init_device_setup(char *devstr)
 	token = strsep(&str, ",");
 	if (!token || strlen(token) >= ZFCP_BUS_ID_SIZE)
 		goto err_out;
-	strncpy(busid, token, ZFCP_BUS_ID_SIZE);
+	strlcpy(busid, token, ZFCP_BUS_ID_SIZE);
 
 	token = strsep(&str, ",");
 	if (!token || kstrtoull(token, 0, (unsigned long long *) &wwpn))
-- 
cgit v1.2.3


From 4e0f5e916f7f4623b312e4fcf9f9fe45c4bea290 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 17 Jun 2018 12:18:56 +0200
Subject: s390/dasd: fix gcc 8 stringop-truncation warning

drivers/s390/block/dasd_alias.c:711:2: warning: 'strncpy' output truncated
before terminating nul copying 4 bytes from a string of the same length
[-Wstringop-truncation]
  strncpy((char *) &cqr->magic, "ECKD", 4);

Replace strncpy to int as a buffer with memcpy.

Acked-by: Stefan Haberland <sth@linux.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/dasd_alias.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/block/dasd_alias.c b/drivers/s390/block/dasd_alias.c
index e36a114354fc..b9ce93e9df89 100644
--- a/drivers/s390/block/dasd_alias.c
+++ b/drivers/s390/block/dasd_alias.c
@@ -708,7 +708,7 @@ static int reset_summary_unit_check(struct alias_lcu *lcu,
 	struct ccw1 *ccw;
 
 	cqr = lcu->rsu_cqr;
-	strncpy((char *) &cqr->magic, "ECKD", 4);
+	memcpy((char *) &cqr->magic, "ECKD", 4);
 	ASCEBC((char *) &cqr->magic, 4);
 	ccw = cqr->cpaddr;
 	ccw->cmd_code = DASD_ECKD_CCW_RSCK;
-- 
cgit v1.2.3


From f6ea4d25e95972f482e14cdcefaa0789e6158d35 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 18 Jun 2018 16:50:42 +0200
Subject: s390: fix gcc 8 stringop-truncation warnings in proc handlers

arch/s390/kernel/topology.c:591:3: warning: 'strncpy' output truncated
before terminating nul copying 2 bytes from a string of the same length
[-Wstringop-truncation]
   strncpy(buf, topology_is_enabled() ? "1\n" : "0\n", ARRAY_SIZE(buf));

arch/s390/appldata/appldata_base.c:326:3: warning: 'strncpy' output truncated
before terminating nul copying 2 bytes from a string of the same length
[-Wstringop-truncation]
   strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));

arch/s390/appldata/appldata_base.c:217:3: warning: 'strncpy' output truncated
before terminating nul copying 2 bytes from a string of the same length
[-Wstringop-truncation]
   strncpy(buf, appldata_timer_active ? "1\n" : "0\n", ARRAY_SIZE(buf));

To avoid the warning, just reuse memcpy.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/appldata/appldata_base.c | 5 ++---
 arch/s390/kernel/topology.c        | 3 +--
 2 files changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index ee6a9c387c87..25c1399b0787 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -214,8 +214,7 @@ appldata_timer_handler(struct ctl_table *ctl, int write,
 		return 0;
 	}
 	if (!write) {
-		strncpy(buf, appldata_timer_active ? "1\n" : "0\n",
-			ARRAY_SIZE(buf));
+		memcpy(buf, appldata_timer_active ? "1\n" : "0\n", ARRAY_SIZE(buf));
 		len = strnlen(buf, ARRAY_SIZE(buf));
 		if (len > *lenp)
 			len = *lenp;
@@ -323,7 +322,7 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 		return 0;
 	}
 	if (!write) {
-		strncpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));
+		memcpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));
 		len = strnlen(buf, ARRAY_SIZE(buf));
 		if (len > *lenp)
 			len = *lenp;
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 4b6e0397f66d..33ebb423c613 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -588,8 +588,7 @@ static int topology_ctl_handler(struct ctl_table *ctl, int write,
 		return 0;
 	}
 	if (!write) {
-		strncpy(buf, topology_is_enabled() ? "1\n" : "0\n",
-			ARRAY_SIZE(buf));
+		memcpy(buf, topology_is_enabled() ? "1\n" : "0\n", ARRAY_SIZE(buf));
 		len = strnlen(buf, ARRAY_SIZE(buf));
 		if (len > *lenp)
 			len = *lenp;
-- 
cgit v1.2.3


From ad82a928eb58471adb2dec2001f5fbe57e5ee4b5 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 18 Jun 2018 17:51:29 +0200
Subject: s390/perf: fix gcc 8 array-bounds warning

arch/s390/kernel/perf_regs.c:36:19: warning: array subscript 16 is above
array bounds of 'long unsigned int[16]' [-Warray-bounds]
  return regs->gprs[idx];

gcc tries to be smart here and since there is a condition:
if (idx >= PERF_REG_S390_R0 && idx <= PERF_REG_S390_R15)
	return regs->gprs[idx];
which covers all possible array subscripts, it gives the warning
for the last function return statement:
	return regs->gprs[idx];
which in presence of that condition does not really make sense and
should be replaced with "return 0;"

Also move WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX) to the end of the
function.

Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/perf_regs.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/arch/s390/kernel/perf_regs.c b/arch/s390/kernel/perf_regs.c
index 54e2d634b849..4352a504f235 100644
--- a/arch/s390/kernel/perf_regs.c
+++ b/arch/s390/kernel/perf_regs.c
@@ -12,9 +12,6 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
 	freg_t fp;
 
-	if (WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX))
-		return 0;
-
 	if (idx >= PERF_REG_S390_R0 && idx <= PERF_REG_S390_R15)
 		return regs->gprs[idx];
 
@@ -33,7 +30,8 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	if (idx == PERF_REG_S390_PC)
 		return regs->psw.addr;
 
-	return regs->gprs[idx];
+	WARN_ON_ONCE((u32)idx >= PERF_REG_S390_MAX);
+	return 0;
 }
 
 #define REG_RESERVED (~((1UL << PERF_REG_S390_MAX) - 1))
-- 
cgit v1.2.3


From 1fee96264a718fc5a2a94a09d5c7e2915a1c76b2 Mon Sep 17 00:00:00 2001
From: Harald Freudenberger <freude@linux.ibm.com>
Date: Wed, 27 Jun 2018 09:50:43 +0200
Subject: s390/zcrypt: add copy_from_user length plausibility checks

There have been identified some places in the zcrypt
device driver where copy_from_user() is called but the
length value is not explicitly checked.

So now some plausibility checks and comments have been
introduced there.

Signed-off-by: Harald Freudenberger <freude@linux.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/crypto/zcrypt_cca_key.h  | 20 +++++++++++++++++++-
 drivers/s390/crypto/zcrypt_msgtype6.c | 20 ++++++++++++++++++--
 2 files changed, 37 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/crypto/zcrypt_cca_key.h b/drivers/s390/crypto/zcrypt_cca_key.h
index 011d61d8a4ae..1752622b95f7 100644
--- a/drivers/s390/crypto/zcrypt_cca_key.h
+++ b/drivers/s390/crypto/zcrypt_cca_key.h
@@ -99,7 +99,7 @@ struct cca_pvt_ext_CRT_sec {
  * @mex: pointer to user input data
  * @p: pointer to memory area for the key
  *
- * Returns the size of the key area or -EFAULT
+ * Returns the size of the key area or negative errno value.
  */
 static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 {
@@ -118,6 +118,15 @@ static inline int zcrypt_type6_mex_key_en(struct ica_rsa_modexpo *mex, void *p)
 	unsigned char *temp;
 	int i;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	key->pubHdr = static_pub_hdr;
@@ -178,6 +187,15 @@ static inline int zcrypt_type6_crt_key(struct ica_rsa_modexpo_crt *crt, void *p)
 	struct cca_public_sec *pub;
 	int short_len, long_len, pad_len, key_len, size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, do a plausibility check
+	 * here to make sure the following copy_from_user() can't be utilized
+	 * to compromise the system.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > 512))
+		return -EINVAL;
+
 	memset(key, 0, sizeof(*key));
 
 	short_len = (crt->inputdatalength + 1) / 2;
diff --git a/drivers/s390/crypto/zcrypt_msgtype6.c b/drivers/s390/crypto/zcrypt_msgtype6.c
index 97d4bacbc442..e70ae078c86b 100644
--- a/drivers/s390/crypto/zcrypt_msgtype6.c
+++ b/drivers/s390/crypto/zcrypt_msgtype6.c
@@ -246,7 +246,7 @@ int speed_idx_ep11(int req_type)
  * @ap_msg: pointer to AP message
  * @mex: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -272,6 +272,14 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_modexpo(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(mex->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = mex->inputdatalength + 2;
 	if (copy_from_user(msg->text, mex->inputdata, mex->inputdatalength))
@@ -307,7 +315,7 @@ static int ICAMEX_msg_to_type6MEX_msgX(struct zcrypt_queue *zq,
  * @ap_msg: pointer to AP message
  * @crt: pointer to user input data
  *
- * Returns 0 on success or -EFAULT.
+ * Returns 0 on success or negative errno value.
  */
 static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 				       struct ap_message *ap_msg,
@@ -334,6 +342,14 @@ static int ICACRT_msg_to_type6CRT_msgX(struct zcrypt_queue *zq,
 	} __packed * msg = ap_msg->message;
 	int size;
 
+	/*
+	 * The inputdatalength was a selection criteria in the dispatching
+	 * function zcrypt_rsa_crt(). However, make sure the following
+	 * copy_from_user() never exceeds the allocated buffer space.
+	 */
+	if (WARN_ON_ONCE(crt->inputdatalength > PAGE_SIZE))
+		return -EINVAL;
+
 	/* VUD.ciphertext */
 	msg->length = crt->inputdatalength + 2;
 	if (copy_from_user(msg->text, crt->inputdata, crt->inputdatalength))
-- 
cgit v1.2.3


From 4778dc08ef99825d2931d44888fda8d49319d93a Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 27 Jun 2018 14:46:57 +0200
Subject: s390/decompressor: discard ___kcrctab section

___kcrctab section is not used during the decompressor phase and could be
discarded to save the memory. It is currently generated due to lib/mem.S
usage, which exports few symbols.

Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/vmlinux.lds.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index b8572a81be5f..93ab95cf16fb 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -58,5 +58,6 @@ SECTIONS
 		*(.eh_frame)
 		*(__ex_table)
 		*(*__ksymtab*)
+		*(___kcrctab*)
 	}
 }
-- 
cgit v1.2.3


From 94cbc0ea163f58ec3ce167a1ccbdf55ff1e88111 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 27 Jun 2018 14:58:46 +0200
Subject: s390: put expoline execute-trampolines into .text section

Currently none of the vmlinux linker script patterns in .text section
match expoline execute-trampolines, and they end up as separate
sections:
.text.__s390_indirect_jump_r1,
.text.__s390x_indirect_jump_r1use_r9,
.text.__s390x_indirect_branch_4_1use_6, ...

Add a pattern to match them all.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/vmlinux.lds.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 31f530b8a1b3..51adfe251bcd 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -47,6 +47,7 @@ SECTIONS
 		KPROBES_TEXT
 		IRQENTRY_TEXT
 		SOFTIRQENTRY_TEXT
+		*(.text.*_indirect_*)
 		*(.fixup)
 		*(.gnu.warning)
 	} :text = 0x0700
-- 
cgit v1.2.3


From 8e533fdd092598db73312af801dbddea8cab6f9c Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 27 Jun 2018 16:59:26 +0200
Subject: s390: remove unused _ehead symbol

Since startup code now reserves memory ranges [0, PARMAREA_END] and
[_stext, <end of kernel>] _ehead symbol is not used and could be
cleaned up.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/sections.h | 2 --
 arch/s390/kernel/head64.S        | 2 --
 2 files changed, 4 deletions(-)

diff --git a/arch/s390/include/asm/sections.h b/arch/s390/include/asm/sections.h
index 54f81f8ed662..724faede8ac5 100644
--- a/arch/s390/include/asm/sections.h
+++ b/arch/s390/include/asm/sections.h
@@ -4,6 +4,4 @@
 
 #include <asm-generic/sections.h>
 
-extern char _ehead[];
-
 #endif
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 6a840bcb2715..161b795d3109 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -87,8 +87,6 @@ ENTRY(startup_continue)
 .Llinkage_stack:
 	.long	0,0,0x89000000,0,0,0,0x8a000000,0
 
-ENTRY(_ehead)
-
 #
 # startup-code, running in absolute addressing mode
 #
-- 
cgit v1.2.3


From 183ab05ff285555c56b7f00bb4fd52d80a9513fb Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 27 Jun 2018 17:10:14 +0200
Subject: s390: get rid of the first mb of uncompressed image

Instead of generating uncompressed kernel image starting at 0, filling
first mb with zeros (with ".org 0x100000") and then trimming it off
from vmlinux.bin before compression, simply generate a kernel image
starting from 0x100000.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/Makefile | 15 ++++-----------
 arch/s390/kernel/head64.S          |  1 -
 arch/s390/kernel/vmlinux.lds.S     |  2 +-
 3 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/arch/s390/boot/compressed/Makefile b/arch/s390/boot/compressed/Makefile
index 9d3bd7d066e9..04609478d18b 100644
--- a/arch/s390/boot/compressed/Makefile
+++ b/arch/s390/boot/compressed/Makefile
@@ -23,16 +23,12 @@ LDFLAGS_vmlinux := --oformat $(LD_BFD) -e startup -T
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(objtree)/arch/s390/boot/startup.a $(OBJECTS)
 	$(call if_changed,ld)
 
-TRIM_HEAD_SIZE := 0x100000
-
-sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - $(TRIM_HEAD_SIZE))/p'
+# extract required uncompressed vmlinux symbols and adjust them to reflect offsets inside vmlinux.bin
+sed-sizes := -e 's/^\([0-9a-fA-F]*\) . \(__bss_start\|_end\)$$/\#define SZ\2 (0x\1 - 0x100000)/p'
 
 quiet_cmd_sizes = GEN     $@
       cmd_sizes = $(NM) $< | sed -n $(sed-sizes) > $@
 
-quiet_cmd_trim_head = TRIM    $@
-      cmd_trim_head = tail -c +$$(($(TRIM_HEAD_SIZE) + 1)) $< > $@
-
 $(obj)/sizes.h: vmlinux
 	$(call if_changed,sizes)
 
@@ -42,13 +38,10 @@ $(obj)/head.o: $(obj)/sizes.h
 CFLAGS_misc.o += -I$(objtree)/$(obj)
 $(obj)/misc.o: $(obj)/sizes.h
 
-OBJCOPYFLAGS_vmlinux.bin.full :=  -R .comment -S
-$(obj)/vmlinux.bin.full: vmlinux
+OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
+$(obj)/vmlinux.bin: vmlinux
 	$(call if_changed,objcopy)
 
-$(obj)/vmlinux.bin: $(obj)/vmlinux.bin.full
-	$(call if_changed,trim_head)
-
 vmlinux.bin.all-y := $(obj)/vmlinux.bin
 
 suffix-$(CONFIG_KERNEL_GZIP)  := .gz
diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 161b795d3109..6f43faeaaf32 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -16,7 +16,6 @@
 #include <asm/page.h>
 
 __HEAD
-	.org	0x100000
 ENTRY(startup_continue)
 	tm	__LC_STFLE_FAC_LIST+5,0x80	# LPP available ?
 	jz	0f
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 51adfe251bcd..35f7ca8a1685 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -30,7 +30,7 @@ PHDRS {
 
 SECTIONS
 {
-	. = 0x00000000;
+	. = 0x100000;
 	.text : {
 		/* Text and read-only data */
 		HEAD_TEXT
-- 
cgit v1.2.3


From c949786450d6e19ef21f0837488a3dc1554131d6 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 27 Jun 2018 17:32:53 +0200
Subject: s390: correct _stext offset

Avoid unnecessary rewrite of psw and merge _stext into
startup_continue. This allows to move _stext definition to vmlinux.lds.S,
where _etext is also defined and set _stext to the actual beginning of
.text at 0x100000.

This fixes the problem with setting the last .text page as
not-executable due to vmem_map_init relying on page alinged _stext and
_etext.

Fixes: bd79d6632958 ("s390/decompressor: trim the kernel image up to 1M")
Reported-by: Nils Hoppmann <niho@de.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/head64.S      | 40 +++++++++++++++-------------------------
 arch/s390/kernel/vmlinux.lds.S |  1 +
 2 files changed, 16 insertions(+), 25 deletions(-)

diff --git a/arch/s390/kernel/head64.S b/arch/s390/kernel/head64.S
index 6f43faeaaf32..6d14ad42ba88 100644
--- a/arch/s390/kernel/head64.S
+++ b/arch/s390/kernel/head64.S
@@ -48,11 +48,23 @@ ENTRY(startup_continue)
 # Early machine initialization and detection functions.
 #
 	brasl	%r14,startup_init
-	lpswe	.Lentry-.LPG1(13)	# jump to _stext in primary-space,
-					# virtual and never return ...
+
+# check control registers
+	stctg	%c0,%c15,0(%r15)
+	oi	6(%r15),0x60		# enable sigp emergency & external call
+	oi	4(%r15),0x10		# switch on low address proctection
+	lctlg	%c0,%c15,0(%r15)
+
+	lam	0,15,.Laregs-.LPG1(%r13)	# load acrs needed by uaccess
+	brasl	%r14,start_kernel		# go to C code
+#
+# We returned from start_kernel ?!? PANIK
+#
+	basr	%r13,0
+	lpswe	.Ldw-.(%r13)		# load disabled wait psw
+
 	.align	16
 .LPG1:
-.Lentry:.quad	0x0000000180000000,_stext
 .Lctl:	.quad	0x04040000		# cr0: AFP registers & secondary space
 	.quad	0			# cr1: primary space segment table
 	.quad	.Lduct			# cr2: dispatchable unit control table
@@ -85,27 +97,5 @@ ENTRY(startup_continue)
 	.endr
 .Llinkage_stack:
 	.long	0,0,0x89000000,0,0,0,0x8a000000,0
-
-#
-# startup-code, running in absolute addressing mode
-#
-ENTRY(_stext)
-	basr	%r13,0			# get base
-.LPG3:
-# check control registers
-	stctg	%c0,%c15,0(%r15)
-	oi	6(%r15),0x60		# enable sigp emergency & external call
-	oi	4(%r15),0x10		# switch on low address proctection
-	lctlg	%c0,%c15,0(%r15)
-
-	lam	0,15,.Laregs-.LPG3(%r13)	# load acrs needed by uaccess
-	brasl	%r14,start_kernel	# go to C code
-#
-# We returned from start_kernel ?!? PANIK
-#
-	basr	%r13,0
-	lpswe	.Ldw-.(%r13)		# load disabled wait psw
-
-	.align	8
 .Ldw:	.quad	0x0002000180000000,0x0000000000000000
 .Laregs:.long	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index 35f7ca8a1685..b3e95b9d99de 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -31,6 +31,7 @@ PHDRS {
 SECTIONS
 {
 	. = 0x100000;
+	_stext = .;		/* Start of text section */
 	.text : {
 		/* Text and read-only data */
 		HEAD_TEXT
-- 
cgit v1.2.3


From f56506ef3061f3362bb35a396f6951f7035b8294 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Wed, 27 Jun 2018 17:53:40 +0200
Subject: s390: move _text to an actual .text start

Since the uncompressed image .text section starts at 0x100000 now there
is no need to redefine _text to something else to make perf happy.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/vmlinux.lds.S | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
index b3e95b9d99de..b43f8d33a369 100644
--- a/arch/s390/kernel/vmlinux.lds.S
+++ b/arch/s390/kernel/vmlinux.lds.S
@@ -34,13 +34,8 @@ SECTIONS
 	_stext = .;		/* Start of text section */
 	.text : {
 		/* Text and read-only data */
+		_text = .;
 		HEAD_TEXT
-		/*
-		 * E.g. perf doesn't like symbols starting at address zero,
-		 * therefore skip the initial PSW and channel program located
-		 * at address zero and let _text start at 0x200.
-		 */
-	_text = 0x200;
 		TEXT_TEXT
 		SCHED_TEXT
 		CPUIDLE_TEXT
-- 
cgit v1.2.3


From 2d6f74f797f26e14bdd672b3547ad29199bbb6b8 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 28 Jun 2018 07:39:24 +0200
Subject: s390/decompressor: correct EXCLUDE_FILE construct

The following linker construct is problematic with linkers of
binutils < 2.28:

EXCLUDE_FILE (*piggy.o) *(.rodata.*)

from 8f1732fc2a11dc of binutils:
"though the linker accepts this without complaint the
EXCLUDE_FILE part is silently ignored and has no effect."

Silent ignoring of EXCLUDE_FILE construct made .rodata.compressed be
part of .rodata, and in case of .rodata.compressed following some
unaligned data, input_len would also become unaligned.

from arch/s390/boot/compressed/vmlinux.map:
 .rodata.compressed
                0x0000000000012fea   0x4d57e7 arch/s390/boot/compressed/piggy.o
                0x0000000000012fea                input_len
                0x0000000000012fee                input_data

input_len is later used here:
arch/s390/boot/compressed/misc.c:113
	__decompress(input_data, input_len, NULL, NULL, output, 0, NULL, error);

asm generated by gcc looks like:
	.loc 3 113 0
egfrl	%r11,input_len

from what assembler generates invalid (the second operand must be aligned
on a doubleword boundary):
   0x00000000000129b4 <+148>:   c4 bc 00 00 03 1b       lgfrl   %r11,0x12fea
hence specification exception is recognized.

To avoid an issue use EXCLUDE_FILE construct which is recognized by
older linkers (since at least binutils-2_11)
	*(EXCLUDE_FILE (*piggy.o) .rodata.compressed)

Also ensure that .rodata.compressed is at least doubleword aligned.

Fixes: 89b5202e81df ("s390/decompressor: support uncompressed kernel")
Reported-by: Halil Pasic <pasic@linux.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/compressed/vmlinux.lds.S | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/s390/boot/compressed/vmlinux.lds.S b/arch/s390/boot/compressed/vmlinux.lds.S
index 93ab95cf16fb..b16ac8b3c439 100644
--- a/arch/s390/boot/compressed/vmlinux.lds.S
+++ b/arch/s390/boot/compressed/vmlinux.lds.S
@@ -26,7 +26,7 @@ SECTIONS
 	.rodata : {
 		_rodata = . ;
 		*(.rodata)	 /* read-only data */
-		EXCLUDE_FILE (*piggy.o) *(.rodata.*)
+		*(EXCLUDE_FILE (*piggy.o) .rodata.compressed)
 		_erodata = . ;
 	}
 	.data :	{
@@ -38,6 +38,8 @@ SECTIONS
 	startup_continue = 0x100000;
 #ifdef CONFIG_KERNEL_UNCOMPRESSED
 	. = 0x100000;
+#else
+	. = ALIGN(8);
 #endif
 	.rodata.compressed : {
 		*(.rodata.compressed)
-- 
cgit v1.2.3


From 3ad4c05a53b5f816fb0480ca0c55cc7957bbf5f1 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 28 Jun 2018 13:12:27 +0200
Subject: s390: align struct lowcore to double page size

Aligning struct lowcore to double page size allows to get rid of this
gcc warning:

In file included from ./arch/s390/include/asm/setup.h:56,
                 from ./arch/s390/include/asm/page.h:36,
                 from ./arch/s390/include/asm/user.h:11,
                 from ./include/linux/user.h:1,
                 from ./include/linux/elfcore.h:5,
                 from ./include/linux/crash_core.h:6,
                 from ./include/linux/kexec.h:18,
                 from arch/s390/purgatory/purgatory.c:10:
./arch/s390/include/asm/lowcore.h:189:1: warning: alignment 1 of 'struct
lowcore' is less than 8 [-Wpacked-not-aligned]
 } __packed;

Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/lowcore.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/lowcore.h b/arch/s390/include/asm/lowcore.h
index 5bc888841eaf..406d940173ab 100644
--- a/arch/s390/include/asm/lowcore.h
+++ b/arch/s390/include/asm/lowcore.h
@@ -185,7 +185,7 @@ struct lowcore {
 	/* Transaction abort diagnostic block */
 	__u8	pgm_tdb[256];			/* 0x1800 */
 	__u8	pad_0x1900[0x2000-0x1900];	/* 0x1900 */
-} __packed;
+} __packed __aligned(8192);
 
 #define S390_lowcore (*((struct lowcore *) 0))
 
-- 
cgit v1.2.3


From 5d2f6e26b318a41e4e588bb270377da13b78b3c8 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 18 Jun 2018 22:49:32 +0200
Subject: s390/tape: fix stringop-truncation gcc 8 warnings

Use strlcpy to make sure strings are NUL-terminated. Fixes the following
gcc 8 warning:

inlined from 'register_tape_dev' at drivers/s390/char/tape_class.c:57:2:
./include/linux/string.h:246:9: warning: '__builtin_strncpy' specified
bound 32 equals destination size [-Wstringop-truncation]

Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/char/tape_class.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/char/tape_class.c b/drivers/s390/char/tape_class.c
index a07102472ce9..e403edf92e00 100644
--- a/drivers/s390/char/tape_class.c
+++ b/drivers/s390/char/tape_class.c
@@ -54,10 +54,10 @@ struct tape_class_device *register_tape_dev(
 	if (!tcd)
 		return ERR_PTR(-ENOMEM);
 
-	strncpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->device_name, device_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->device_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
-	strncpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
+	strlcpy(tcd->mode_name, mode_name, TAPECLASS_NAME_LEN);
 	for (s = strchr(tcd->mode_name, '/'); s; s = strchr(s, '/'))
 		*s = '!';
 
-- 
cgit v1.2.3


From 276d605081fbbc96be02318abb36119625b47bb3 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 28 Jun 2018 13:28:37 +0200
Subject: s390/tape: fix gcc 8 stringop-truncation warning

Replace strncpy which is used to deliberately avoid string NUL-termination
with memcpy. This allows to get rid of gcc 8 stringop-truncation warning:

    inlined from 'ext_to_int_kekl' at drivers/s390/char/tape_3590.c:123:2:
./include/linux/string.h:246:9: warning: '__builtin_strncpy'
output may be truncated copying 64 bytes from a string of length 64
[-Wstringop-truncation]

Also replaces "for" loop on memset.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/char/tape_3590.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/char/tape_3590.c b/drivers/s390/char/tape_3590.c
index 37e65a05517f..cdcde18e7220 100644
--- a/drivers/s390/char/tape_3590.c
+++ b/drivers/s390/char/tape_3590.c
@@ -113,16 +113,16 @@ static int crypt_enabled(struct tape_device *device)
 static void ext_to_int_kekl(struct tape390_kekl *in,
 			    struct tape3592_kekl *out)
 {
-	int i;
+	int len;
 
 	memset(out, 0, sizeof(*out));
 	if (in->type == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x40;
 	if (in->type_on_tape == TAPE390_KEKL_TYPE_HASH)
 		out->flags |= 0x80;
-	strncpy(out->label, in->label, 64);
-	for (i = strlen(in->label); i < sizeof(out->label); i++)
-		out->label[i] = ' ';
+	len = min(sizeof(out->label), strlen(in->label));
+	memcpy(out->label, in->label, len);
+	memset(out->label + len, ' ', sizeof(out->label) - len);
 	ASCEBC(out->label, sizeof(out->label));
 }
 
-- 
cgit v1.2.3


From 9acdb3bb070167c257252e131f56fb8daaa99766 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 28 Jun 2018 13:16:14 +0200
Subject: s390/monwriter: fix gcc 8 stringop-truncation warning

The following gcc warning is issued for strncpy which is used to
deliberately avoid string NUL-termination. Reuse memcpy to avoid the
warning.

    inlined from 'monwrite_diag' at drivers/s390/char/monwriter.c:64:2:
./include/linux/string.h:246:9: warning: '__builtin_strncpy' output
truncated before terminating nul copying 7 bytes from a string of the
same length [-Wstringop-truncation]

Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/char/monwriter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/char/monwriter.c b/drivers/s390/char/monwriter.c
index 76c158c41510..4f1a69c9d81d 100644
--- a/drivers/s390/char/monwriter.c
+++ b/drivers/s390/char/monwriter.c
@@ -61,7 +61,7 @@ static int monwrite_diag(struct monwrite_hdr *myhdr, char *buffer, int fcn)
 	struct appldata_product_id id;
 	int rc;
 
-	strncpy(id.prod_nr, "LNXAPPL", 7);
+	memcpy(id.prod_nr, "LNXAPPL", 7);
 	id.prod_fn = myhdr->applid;
 	id.record_nr = myhdr->record_num;
 	id.version_nr = myhdr->version;
-- 
cgit v1.2.3


From 627c9b62058ebfd368b7411e7ea5a27df48486c8 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 25 Jun 2018 13:59:35 +0200
Subject: s390/boot: block uncompressed vmlinux booting attempts

Since the plain vmlinux ELF file no longer carries all necessary parts
for starting up (like the entry point and decompressor), add a check
which would block boot process and encourage users to use bzImage or
arch/s390/boot/compressed/vmlinux instead.

The check relies on s390 linux entry point ABI definition, which is only
present in bzImage and arch/s390/boot/compressed/vmlinux.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Cornelia Huck <cohuck@redhat.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/head.S         |  4 ++--
 arch/s390/include/asm/setup.h |  3 ++-
 arch/s390/kernel/early.c      | 12 ++++++++++++
 3 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/arch/s390/boot/head.S b/arch/s390/boot/head.S
index f09e792df495..f721913b73f1 100644
--- a/arch/s390/boot/head.S
+++ b/arch/s390/boot/head.S
@@ -272,14 +272,14 @@ iplstart:
 	.org	0x10000
 ENTRY(startup)
 	j	.Lep_startup_normal
-	.org	0x10008
+	.org	EP_OFFSET
 #
 # This is a list of s390 kernel entry points. At address 0x1000f the number of
 # valid entry points is stored.
 #
 # IMPORTANT: Do not change this table, it is s390 kernel ABI!
 #
-	.ascii	"S390EP"
+	.ascii	EP_STRING
 	.byte	0x00,0x01
 #
 # kdump startup-code at 0x10010, running in 64 bit absolute addressing mode
diff --git a/arch/s390/include/asm/setup.h b/arch/s390/include/asm/setup.h
index be02f0558048..1d66016f4170 100644
--- a/arch/s390/include/asm/setup.h
+++ b/arch/s390/include/asm/setup.h
@@ -9,7 +9,8 @@
 #include <linux/const.h>
 #include <uapi/asm/setup.h>
 
-
+#define EP_OFFSET		0x10008
+#define EP_STRING		"S390EP"
 #define PARMAREA		0x10400
 #define PARMAREA_END		0x11000
 
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index 827699eb48fa..5b28b434f8a1 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -331,8 +331,20 @@ static void __init setup_boot_command_line(void)
 	append_to_cmdline(append_ipl_scpdata);
 }
 
+static void __init check_image_bootable(void)
+{
+	if (!memcmp(EP_STRING, (void *)EP_OFFSET, strlen(EP_STRING)))
+		return;
+
+	sclp_early_printk("Linux kernel boot failure: An attempt to boot a vmlinux ELF image failed.\n");
+	sclp_early_printk("This image does not contain all parts necessary for starting up. Use\n");
+	sclp_early_printk("bzImage or arch/s390/boot/compressed/vmlinux instead.\n");
+	disabled_wait(0xbadb007);
+}
+
 void __init startup_init(void)
 {
+	check_image_bootable();
 	time_early_init();
 	init_kernel_storage_key();
 	lockdep_off();
-- 
cgit v1.2.3


From d053d639f00c58122ac0e3fe3a08aa8dc2a08ce6 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 29 Jun 2018 17:32:09 +0200
Subject: s390/tools: fix gcc 8 stringop-truncation warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace strncpy which has been used to copy a substring into buf
without NUL-termination with memcpy to avoid the following gcc 8
warnings:

arch/s390/tools/gen_opcode_table.c: In function ‘add_to_group.isra.4’:
arch/s390/tools/gen_opcode_table.c:260:2: warning: ‘strncpy’
output may be truncated copying 2 bytes from a string of length 19
[-Wstringop-truncation]
  strncpy(group->opcode, insn->opcode, 2);

In function ‘print_opcode_table’,
    inlined from ‘main’ at arch/s390/tools/gen_opcode_table.c:333:2:
arch/s390/tools/gen_opcode_table.c:286:4: warning: ‘strncpy’
output may be truncated copying 2 bytes from a string of length 19
[-Wstringop-truncation]
    strncpy(opcode, insn->opcode, 2);

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/tools/gen_opcode_table.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/tools/gen_opcode_table.c b/arch/s390/tools/gen_opcode_table.c
index 259aa0680d1a..a1bc02b29c81 100644
--- a/arch/s390/tools/gen_opcode_table.c
+++ b/arch/s390/tools/gen_opcode_table.c
@@ -257,7 +257,7 @@ static void add_to_group(struct gen_opcode *desc, struct insn *insn, int offset)
 	if (!desc->group)
 		exit(EXIT_FAILURE);
 	group = &desc->group[desc->nr_groups - 1];
-	strncpy(group->opcode, insn->opcode, 2);
+	memcpy(group->opcode, insn->opcode, 2);
 	group->type = insn->type;
 	group->offset = offset;
 	group->count = 1;
@@ -283,7 +283,7 @@ static void print_opcode_table(struct gen_opcode *desc)
 			continue;
 		add_to_group(desc, insn, offset);
 		if (strncmp(opcode, insn->opcode, 2)) {
-			strncpy(opcode, insn->opcode, 2);
+			memcpy(opcode, insn->opcode, 2);
 			printf("\t/* %.2s */ \\\n", opcode);
 		}
 		print_opcode(insn, offset);
-- 
cgit v1.2.3


From 506a66f374891ff08e064a058c446b336c5ac760 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 29 Jun 2018 16:05:47 +0200
Subject: Revert "x86/apic: Ignore secondary threads if nosmt=force"

Dave Hansen reported, that it's outright dangerous to keep SMT siblings
disabled completely so they are stuck in the BIOS and wait for SIPI.

The reason is that Machine Check Exceptions are broadcasted to siblings and
the soft disabled sibling has CR4.MCE = 0. If a MCE is delivered to a
logical core with CR4.MCE = 0, it asserts IERR#, which shuts down or
reboots the machine. The MCE chapter in the SDM contains the following
blurb:

    Because the logical processors within a physical package are tightly
    coupled with respect to shared hardware resources, both logical
    processors are notified of machine check errors that occur within a
    given physical processor. If machine-check exceptions are enabled when
    a fatal error is reported, all the logical processors within a physical
    package are dispatched to the machine-check exception handler. If
    machine-check exceptions are disabled, the logical processors enter the
    shutdown state and assert the IERR# signal. When enabling machine-check
    exceptions, the MCE flag in control register CR4 should be set for each
    logical processor.

Reverting the commit which ignores siblings at enumeration time solves only
half of the problem. The core cpuhotplug logic needs to be adjusted as
well.

This thoughtful engineered mechanism also turns the boot process on all
Intel HT enabled systems into a MCE lottery. MCE is enabled on the boot CPU
before the secondary CPUs are brought up. Depending on the number of
physical cores the window in which this situation can happen is smaller or
larger. On a HSW-EX it's about 750ms:

MCE is enabled on the boot CPU:

[    0.244017] mce: CPU supports 22 MCE banks

The corresponding sibling #72 boots:

[    1.008005] .... node  #0, CPUs:    #72

That means if an MCE hits on physical core 0 (logical CPUs 0 and 72)
between these two points the machine is going to shutdown. At least it's a
known safe state.

It's obvious that the early boot can be hit by an MCE as well and then runs
into the same situation because MCEs are not yet enabled on the boot CPU.
But after enabling them on the boot CPU, it does not make any sense to
prevent the kernel from recovering.

Adjust the nosmt kernel parameter documentation as well.

Reverts: 2207def700f9 ("x86/apic: Ignore secondary threads if nosmt=force")
Reported-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Tony Luck <tony.luck@intel.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  8 ++------
 arch/x86/include/asm/apic.h                     |  2 --
 arch/x86/kernel/acpi/boot.c                     |  3 +--
 arch/x86/kernel/apic/apic.c                     | 19 -------------------
 4 files changed, 3 insertions(+), 29 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 8e29c4b6756f..5da7b0b30432 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2688,12 +2688,8 @@
 			Equivalent to smt=1.
 
 			[KNL,x86] Disable symmetric multithreading (SMT).
-			nosmt=force: Force disable SMT, similar to disabling
-				     it in the BIOS except that some of the
-				     resource partitioning effects which are
-				     caused by having SMT enabled in the BIOS
-				     cannot be undone. Depending on the CPU
-				     type this might have a performance impact.
+			nosmt=force: Force disable SMT, cannot be undone
+				     via the sysfs control file.
 
 	nospectre_v2	[X86] Disable all mitigations for the Spectre variant 2
 			(indirect branch prediction) vulnerability. System may
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index ef40e4acd7c2..9362a3aae927 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -504,10 +504,8 @@ extern int default_check_phys_apicid_present(int phys_apicid);
 
 #ifdef CONFIG_SMP
 bool apic_id_is_primary_thread(unsigned int id);
-bool apic_id_disabled(unsigned int id);
 #else
 static inline bool apic_id_is_primary_thread(unsigned int id) { return false; }
-static inline bool apic_id_disabled(unsigned int id) { return false; }
 #endif
 
 extern void irq_enter(void);
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index db4c118a7e4d..3b20607d581b 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -181,8 +181,7 @@ static int acpi_register_lapic(int id, u32 acpiid, u8 enabled)
 	}
 
 	if (!enabled) {
-		if (!apic_id_disabled(id))
-			++disabled_cpus;
+		++disabled_cpus;
 		return -EINVAL;
 	}
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index b86091add294..8703caa9d6db 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2204,16 +2204,6 @@ bool apic_id_is_primary_thread(unsigned int apicid)
 	return !(apicid & mask);
 }
 
-/**
- * apic_id_disabled - Check whether APIC ID is disabled via SMT control
- * @id:	APIC ID to check
- */
-bool apic_id_disabled(unsigned int id)
-{
-	return (cpu_smt_control == CPU_SMT_FORCE_DISABLED &&
-		!apic_id_is_primary_thread(id));
-}
-
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
  * and cpuid_to_apicid[] synchronized.
@@ -2309,15 +2299,6 @@ int generic_processor_info(int apicid, int version)
 		return -EINVAL;
 	}
 
-	/*
-	 * If SMT is force disabled and the APIC ID belongs to
-	 * a secondary thread, ignore it.
-	 */
-	if (apic_id_disabled(apicid)) {
-		pr_info_once("Ignoring secondary SMT threads\n");
-		return -EINVAL;
-	}
-
 	if (apicid == boot_cpu_physical_apicid) {
 		/*
 		 * x86_bios_cpu_apicid is required to have processors listed
-- 
cgit v1.2.3


From 0cc3cd21657be04cb0559fe8063f2130493f92cf Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 29 Jun 2018 16:05:48 +0200
Subject: cpu/hotplug: Boot HT siblings at least once

Due to the way Machine Check Exceptions work on X86 hyperthreads it's
required to boot up _all_ logical cores at least once in order to set the
CR4.MCE bit.

So instead of ignoring the sibling threads right away, let them boot up
once so they can configure themselves. After they came out of the initial
boot stage check whether its a "secondary" sibling and cancel the operation
which puts the CPU back into offline state.

Reported-by: Dave Hansen <dave.hansen@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Tony Luck <tony.luck@intel.com>
---
 kernel/cpu.c | 72 ++++++++++++++++++++++++++++++++++++++++--------------------
 1 file changed, 48 insertions(+), 24 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index d29fdd7e57bb..6f3a3cde8b83 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -60,6 +60,7 @@ struct cpuhp_cpu_state {
 	bool			rollback;
 	bool			single;
 	bool			bringup;
+	bool			booted_once;
 	struct hlist_node	*node;
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
@@ -342,6 +343,40 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
+#ifdef CONFIG_HOTPLUG_SMT
+enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_control = CPU_SMT_DISABLED;
+	if (str && !strcmp(str, "force")) {
+		pr_info("SMT: Force disabled\n");
+		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	}
+	return 0;
+}
+early_param("nosmt", smt_cmdline_disable);
+
+static inline bool cpu_smt_allowed(unsigned int cpu)
+{
+	if (cpu_smt_control == CPU_SMT_ENABLED)
+		return true;
+
+	if (topology_is_primary_thread(cpu))
+		return true;
+
+	/*
+	 * On x86 it's required to boot all logical CPUs at least once so
+	 * that the init code can get a chance to set CR4.MCE on each
+	 * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+	 * core will shutdown the machine.
+	 */
+	return !per_cpu(cpuhp_state, cpu).booted_once;
+}
+#else
+static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
+#endif
+
 static inline enum cpuhp_state
 cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 {
@@ -422,6 +457,16 @@ static int bringup_wait_for_ap(unsigned int cpu)
 	stop_machine_unpark(cpu);
 	kthread_unpark(st->thread);
 
+	/*
+	 * SMT soft disabling on X86 requires to bring the CPU out of the
+	 * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit.  The
+	 * CPU marked itself as booted_once in cpu_notify_starting() so the
+	 * cpu_smt_allowed() check will now return false if this is not the
+	 * primary sibling.
+	 */
+	if (!cpu_smt_allowed(cpu))
+		return -ECANCELED;
+
 	if (st->target <= CPUHP_AP_ONLINE_IDLE)
 		return 0;
 
@@ -933,29 +978,6 @@ EXPORT_SYMBOL(cpu_down);
 #define takedown_cpu		NULL
 #endif /*CONFIG_HOTPLUG_CPU*/
 
-#ifdef CONFIG_HOTPLUG_SMT
-enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
-
-static int __init smt_cmdline_disable(char *str)
-{
-	cpu_smt_control = CPU_SMT_DISABLED;
-	if (str && !strcmp(str, "force")) {
-		pr_info("SMT: Force disabled\n");
-		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
-	}
-	return 0;
-}
-early_param("nosmt", smt_cmdline_disable);
-
-static inline bool cpu_smt_allowed(unsigned int cpu)
-{
-	return cpu_smt_control == CPU_SMT_ENABLED ||
-		topology_is_primary_thread(cpu);
-}
-#else
-static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
-#endif
-
 /**
  * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
  * @cpu: cpu that just started
@@ -970,6 +992,7 @@ void notify_cpu_starting(unsigned int cpu)
 	int ret;
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
+	st->booted_once = true;
 	while (st->state < target) {
 		st->state++;
 		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
@@ -2180,5 +2203,6 @@ void __init boot_cpu_init(void)
  */
 void __init boot_cpu_state_init(void)
 {
-	per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
+	this_cpu_write(cpuhp_state.booted_once, true);
+	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
-- 
cgit v1.2.3


From 1111b7836c80ec4094318e1dfb3a5abe6df95afb Mon Sep 17 00:00:00 2001
From: Xie Yisheng <xieyisheng1@huawei.com>
Date: Thu, 31 May 2018 19:11:15 +0800
Subject: cpufreq: intel_pstate: use match_string() helper

match_string() returns the index of an array for a matching string,
which can be used instead of open coded variant.

Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Yisheng Xie <xieyisheng1@huawei.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index ece120da3353..a5c368425e36 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -657,21 +657,18 @@ static ssize_t store_energy_performance_preference(
 {
 	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
 	char str_preference[21];
-	int ret, i = 0;
+	int ret;
 
 	ret = sscanf(buf, "%20s", str_preference);
 	if (ret != 1)
 		return -EINVAL;
 
-	while (energy_perf_strings[i] != NULL) {
-		if (!strcmp(str_preference, energy_perf_strings[i])) {
-			intel_pstate_set_energy_pref_index(cpu_data, i);
-			return count;
-		}
-		++i;
-	}
+	ret = match_string(energy_perf_strings, -1, str_preference);
+	if (ret < 0)
+		return ret;
 
-	return -EINVAL;
+	intel_pstate_set_energy_pref_index(cpu_data, ret);
+	return count;
 }
 
 static ssize_t show_energy_performance_preference(
-- 
cgit v1.2.3


From a1d0015423920672c3f32e69bd9feef2ec629b57 Mon Sep 17 00:00:00 2001
From: Bastian Stender <bst@pengutronix.de>
Date: Fri, 8 Jun 2018 11:06:39 +0200
Subject: cpufreq: imx6q/thermal: imx: register cooling device depending on OF

The cooling device should be part of the i.MX cpufreq driver, but it
cannot be removed for the sake of DT stability. So turn the cooling
device registration into a separate function and perform the
registration only if the CPU OF node does not have the #cooling-cells
property.

Use of_cpufreq_power_cooling_register in imx_thermal code to link the
cooling device to the device tree node provided.

This makes it possible to bind the cpufreq cooling device to a custom
thermal zone via a cooling-maps entry like:

	cooling-maps {
		map0 {
			trip = <&board_alert>;
			cooling-device = <&cpu0 THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
		};
	};

Assuming a cpu node exists with label "cpu0" and #cooling-cells
property.

Signed-off-by: Bastian Stender <bst@pengutronix.de>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/imx6q-cpufreq.c | 21 +++++++++++++++++++++
 drivers/thermal/imx_thermal.c   | 28 ++++++++++++++++++++++++----
 2 files changed, 45 insertions(+), 4 deletions(-)

diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 8b3c2a79ad6c..b2ff423ad7f8 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -9,6 +9,7 @@
 #include <linux/clk.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
+#include <linux/cpu_cooling.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -50,6 +51,7 @@ static struct clk_bulk_data clks[] = {
 };
 
 static struct device *cpu_dev;
+static struct thermal_cooling_device *cdev;
 static bool free_opp;
 static struct cpufreq_frequency_table *freq_table;
 static unsigned int max_freq;
@@ -191,6 +193,16 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	return 0;
 }
 
+static void imx6q_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	cdev = of_cpufreq_cooling_register(policy);
+
+	if (!cdev)
+		dev_err(cpu_dev,
+			"running cpufreq without cooling device: %ld\n",
+			PTR_ERR(cdev));
+}
+
 static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret;
@@ -202,13 +214,22 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static int imx6q_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_cooling_unregister(cdev);
+
+	return 0;
+}
+
 static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK,
 	.verify = cpufreq_generic_frequency_table_verify,
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
+	.exit = imx6q_cpufreq_exit,
 	.name = "imx6q-cpufreq",
+	.ready = imx6q_cpufreq_ready,
 	.attr = cpufreq_generic_attr,
 	.suspend = cpufreq_generic_suspend,
 };
diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index 334d98be03b9..cbfcca828cd7 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -3,6 +3,7 @@
 // Copyright 2013 Freescale Semiconductor, Inc.
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpu_cooling.h>
 #include <linux/delay.h>
@@ -644,6 +645,27 @@ static const struct of_device_id of_imx_thermal_match[] = {
 };
 MODULE_DEVICE_TABLE(of, of_imx_thermal_match);
 
+/*
+ * Create cooling device in case no #cooling-cells property is available in
+ * CPU node
+ */
+static int imx_thermal_register_legacy_cooling(struct imx_thermal_data *data)
+{
+	struct device_node *np = of_get_cpu_node(data->policy->cpu, NULL);
+	int ret;
+
+	if (!np || !of_find_property(np, "#cooling-cells", NULL)) {
+		data->cdev = cpufreq_cooling_register(data->policy);
+		if (IS_ERR(data->cdev)) {
+			ret = PTR_ERR(data->cdev);
+			cpufreq_cpu_put(data->policy);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static int imx_thermal_probe(struct platform_device *pdev)
 {
 	struct imx_thermal_data *data;
@@ -724,12 +746,10 @@ static int imx_thermal_probe(struct platform_device *pdev)
 		return -EPROBE_DEFER;
 	}
 
-	data->cdev = cpufreq_cooling_register(data->policy);
-	if (IS_ERR(data->cdev)) {
-		ret = PTR_ERR(data->cdev);
+	ret = imx_thermal_register_legacy_cooling(data);
+	if (ret) {
 		dev_err(&pdev->dev,
 			"failed to register cpufreq cooling device: %d\n", ret);
-		cpufreq_cpu_put(data->policy);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From 6fec64e1c92d5c715c6d0f50786daa7708266bde Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 26 Jun 2018 15:21:31 +0200
Subject: posix-timers: Make forward callback return s64

The posix timer ti_overrun handling is broken because the forwarding
functions can return a huge number of overruns which does not fit in an
int. As a consequence timer_getoverrun(2) and siginfo::si_overrun can turn
into random number generators.

As a first step to address that let the timer_forward() callbacks return
the full 64 bit value.

Cast it to (int) temporarily until k_itimer::ti_overrun is converted to
64bit and the conversion to user space visible values is sanitized.

Reported-by: Team OWL337 <icytxw@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <john.stultz@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Link: https://lkml.kernel.org/r/20180626132704.922098090@linutronix.de
---
 kernel/time/alarmtimer.c   | 4 ++--
 kernel/time/posix-timers.c | 6 +++---
 kernel/time/posix-timers.h | 2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 639321bf2e39..78a3cc555823 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -581,11 +581,11 @@ static void alarm_timer_rearm(struct k_itimer *timr)
  * @timr:	Pointer to the posixtimer data struct
  * @now:	Current time to forward the timer against
  */
-static int alarm_timer_forward(struct k_itimer *timr, ktime_t now)
+static s64 alarm_timer_forward(struct k_itimer *timr, ktime_t now)
 {
 	struct alarm *alarm = &timr->it.alarm.alarmtimer;
 
-	return (int) alarm_forward(alarm, timr->it_interval, now);
+	return alarm_forward(alarm, timr->it_interval, now);
 }
 
 /**
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index 80d59333c76e..db1d65963a57 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -645,11 +645,11 @@ static ktime_t common_hrtimer_remaining(struct k_itimer *timr, ktime_t now)
 	return __hrtimer_expires_remaining_adjusted(timer, now);
 }
 
-static int common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
+static s64 common_hrtimer_forward(struct k_itimer *timr, ktime_t now)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
 
-	return (int)hrtimer_forward(timer, now, timr->it_interval);
+	return hrtimer_forward(timer, now, timr->it_interval);
 }
 
 /*
@@ -702,7 +702,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 	 * expiry time forward by intervals, so expiry is > now.
 	 */
 	if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none))
-		timr->it_overrun += kc->timer_forward(timr, now);
+		timr->it_overrun += (int)kc->timer_forward(timr, now);
 
 	remaining = kc->timer_remaining(timr, now);
 	/* Return 0 only, when the timer is expired and not pending */
diff --git a/kernel/time/posix-timers.h b/kernel/time/posix-timers.h
index 151e28f5bf30..ddb21145211a 100644
--- a/kernel/time/posix-timers.h
+++ b/kernel/time/posix-timers.h
@@ -19,7 +19,7 @@ struct k_clock {
 	void	(*timer_get)(struct k_itimer *timr,
 			     struct itimerspec64 *cur_setting);
 	void	(*timer_rearm)(struct k_itimer *timr);
-	int	(*timer_forward)(struct k_itimer *timr, ktime_t now);
+	s64	(*timer_forward)(struct k_itimer *timr, ktime_t now);
 	ktime_t	(*timer_remaining)(struct k_itimer *timr, ktime_t now);
 	int	(*timer_try_to_cancel)(struct k_itimer *timr);
 	void	(*timer_arm)(struct k_itimer *timr, ktime_t expires,
-- 
cgit v1.2.3


From 78c9c4dfbf8c04883941445a195276bb4bb92c76 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 26 Jun 2018 15:21:32 +0200
Subject: posix-timers: Sanitize overrun handling

The posix timer overrun handling is broken because the forwarding functions
can return a huge number of overruns which does not fit in an int. As a
consequence timer_getoverrun(2) and siginfo::si_overrun can turn into
random number generators.

The k_clock::timer_forward() callbacks return a 64 bit value now. Make
k_itimer::ti_overrun[_last] 64bit as well, so the kernel internal
accounting is correct. 3Remove the temporary (int) casts.

Add a helper function which clamps the overrun value returned to user space
via timer_getoverrun(2) or siginfo::si_overrun limited to a positive value
between 0 and INT_MAX. INT_MAX is an indicator for user space that the
overrun value has been clamped.

Reported-by: Team OWL337 <icytxw@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <john.stultz@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Link: https://lkml.kernel.org/r/20180626132705.018623573@linutronix.de
---
 include/linux/posix-timers.h   |  4 ++--
 kernel/time/posix-cpu-timers.c |  2 +-
 kernel/time/posix-timers.c     | 31 ++++++++++++++++++++-----------
 3 files changed, 23 insertions(+), 14 deletions(-)

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index c85704fcdbd2..ee7e987ea1b4 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -95,8 +95,8 @@ struct k_itimer {
 	clockid_t		it_clock;
 	timer_t			it_id;
 	int			it_active;
-	int			it_overrun;
-	int			it_overrun_last;
+	s64			it_overrun;
+	s64			it_overrun_last;
 	int			it_requeue_pending;
 	int			it_sigev_notify;
 	ktime_t			it_interval;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 5a6251ac6f7a..562cc3891b57 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -85,7 +85,7 @@ static void bump_cpu_timer(struct k_itimer *timer, u64 now)
 			continue;
 
 		timer->it.cpu.expires += incr;
-		timer->it_overrun += 1 << i;
+		timer->it_overrun += 1LL << i;
 		delta -= incr;
 	}
 }
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index db1d65963a57..3ac7295306dc 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -283,6 +283,17 @@ static __init int init_posix_timers(void)
 }
 __initcall(init_posix_timers);
 
+/*
+ * The siginfo si_overrun field and the return value of timer_getoverrun(2)
+ * are of type int. Clamp the overrun value to INT_MAX
+ */
+static inline int timer_overrun_to_int(struct k_itimer *timr, int baseval)
+{
+	s64 sum = timr->it_overrun_last + (s64)baseval;
+
+	return sum > (s64)INT_MAX ? INT_MAX : (int)sum;
+}
+
 static void common_hrtimer_rearm(struct k_itimer *timr)
 {
 	struct hrtimer *timer = &timr->it.real.timer;
@@ -290,9 +301,8 @@ static void common_hrtimer_rearm(struct k_itimer *timr)
 	if (!timr->it_interval)
 		return;
 
-	timr->it_overrun += (unsigned int) hrtimer_forward(timer,
-						timer->base->get_time(),
-						timr->it_interval);
+	timr->it_overrun += hrtimer_forward(timer, timer->base->get_time(),
+					    timr->it_interval);
 	hrtimer_restart(timer);
 }
 
@@ -321,10 +331,10 @@ void posixtimer_rearm(struct siginfo *info)
 
 		timr->it_active = 1;
 		timr->it_overrun_last = timr->it_overrun;
-		timr->it_overrun = -1;
+		timr->it_overrun = -1LL;
 		++timr->it_requeue_pending;
 
-		info->si_overrun += timr->it_overrun_last;
+		info->si_overrun = timer_overrun_to_int(timr, info->si_overrun);
 	}
 
 	unlock_timer(timr, flags);
@@ -418,9 +428,8 @@ static enum hrtimer_restart posix_timer_fn(struct hrtimer *timer)
 					now = ktime_add(now, kj);
 			}
 #endif
-			timr->it_overrun += (unsigned int)
-				hrtimer_forward(timer, now,
-						timr->it_interval);
+			timr->it_overrun += hrtimer_forward(timer, now,
+							    timr->it_interval);
 			ret = HRTIMER_RESTART;
 			++timr->it_requeue_pending;
 			timr->it_active = 1;
@@ -524,7 +533,7 @@ static int do_timer_create(clockid_t which_clock, struct sigevent *event,
 	new_timer->it_id = (timer_t) new_timer_id;
 	new_timer->it_clock = which_clock;
 	new_timer->kclock = kc;
-	new_timer->it_overrun = -1;
+	new_timer->it_overrun = -1LL;
 
 	if (event) {
 		rcu_read_lock();
@@ -702,7 +711,7 @@ void common_timer_get(struct k_itimer *timr, struct itimerspec64 *cur_setting)
 	 * expiry time forward by intervals, so expiry is > now.
 	 */
 	if (iv && (timr->it_requeue_pending & REQUEUE_PENDING || sig_none))
-		timr->it_overrun += (int)kc->timer_forward(timr, now);
+		timr->it_overrun += kc->timer_forward(timr, now);
 
 	remaining = kc->timer_remaining(timr, now);
 	/* Return 0 only, when the timer is expired and not pending */
@@ -791,7 +800,7 @@ SYSCALL_DEFINE1(timer_getoverrun, timer_t, timer_id)
 	if (!timr)
 		return -EINVAL;
 
-	overrun = timr->it_overrun_last;
+	overrun = timer_overrun_to_int(timr, 0);
 	unlock_timer(timr, flags);
 
 	return overrun;
-- 
cgit v1.2.3


From 5f936e19cc0ef97dbe3a56e9498922ad5ba1edef Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 2 Jul 2018 09:34:29 +0200
Subject: alarmtimer: Prevent overflow for relative nanosleep

Air Icy reported:

  UBSAN: Undefined behaviour in kernel/time/alarmtimer.c:811:7
  signed integer overflow:
  1529859276030040771 + 9223372036854775807 cannot be represented in type 'long long int'
  Call Trace:
   alarm_timer_nsleep+0x44c/0x510 kernel/time/alarmtimer.c:811
   __do_sys_clock_nanosleep kernel/time/posix-timers.c:1235 [inline]
   __se_sys_clock_nanosleep kernel/time/posix-timers.c:1213 [inline]
   __x64_sys_clock_nanosleep+0x326/0x4e0 kernel/time/posix-timers.c:1213
   do_syscall_64+0xb8/0x3a0 arch/x86/entry/common.c:290

alarm_timer_nsleep() uses ktime_add() to add the current time and the
relative expiry value. ktime_add() has no sanity checks so the addition
can overflow when the relative timeout is large enough.

Use ktime_add_safe() which has the necessary sanity checks in place and
limits the result to the valid range.

Fixes: 9a7adcf5c6de ("timers: Posix interface for alarm-timers")
Reported-by: Team OWL337 <icytxw@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: John Stultz <john.stultz@linaro.org>
Link: https://lkml.kernel.org/r/alpine.DEB.2.21.1807020926360.1595@nanos.tec.linutronix.de
---
 kernel/time/alarmtimer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c
index 78a3cc555823..fa5de5e8de61 100644
--- a/kernel/time/alarmtimer.c
+++ b/kernel/time/alarmtimer.c
@@ -808,7 +808,8 @@ static int alarm_timer_nsleep(const clockid_t which_clock, int flags,
 	/* Convert (if necessary) to absolute time */
 	if (flags != TIMER_ABSTIME) {
 		ktime_t now = alarm_bases[type].gettime();
-		exp = ktime_add(now, exp);
+
+		exp = ktime_add_safe(now, exp);
 	}
 
 	ret = alarmtimer_do_nsleep(&alarm, exp, type);
-- 
cgit v1.2.3


From 90aff8d091c9c1fa46df45ddd8e73e4c6b6e2b0b Mon Sep 17 00:00:00 2001
From: Peng Donglin <dolinux.peng@gmail.com>
Date: Wed, 13 Jun 2018 09:11:56 +0800
Subject: ARM64: dump: Convert to use DEFINE_SHOW_ATTRIBUTE macro

Use DEFINE_SHOW_ATTRIBUTE macro to simplify the code.

Signed-off-by: Peng Donglin <dolinux.peng@gmail.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/mm/ptdump_debugfs.c | 13 +------------
 1 file changed, 1 insertion(+), 12 deletions(-)

diff --git a/arch/arm64/mm/ptdump_debugfs.c b/arch/arm64/mm/ptdump_debugfs.c
index 02b18f8b2905..24d786fc3a4c 100644
--- a/arch/arm64/mm/ptdump_debugfs.c
+++ b/arch/arm64/mm/ptdump_debugfs.c
@@ -10,18 +10,7 @@ static int ptdump_show(struct seq_file *m, void *v)
 	ptdump_walk_pgd(m, info);
 	return 0;
 }
-
-static int ptdump_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, ptdump_show, inode->i_private);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
+DEFINE_SHOW_ATTRIBUTE(ptdump);
 
 int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
 {
-- 
cgit v1.2.3


From d5641c64c48f4408500a348301bff01fbf2c1ec5 Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Mon, 25 Jun 2018 13:30:58 +0800
Subject: PM / hibernate: cast PAGE_SIZE to int when comparing with error code

If PAGE_SIZE is unsigned type then negative error code will be
larger than PAGE_SIZE.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/swap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index c2bcf97d24c8..d7f6c1a288d3 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -923,7 +923,7 @@ int swsusp_write(unsigned int flags)
 	}
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
 	error = snapshot_read_next(&snapshot);
-	if (error < PAGE_SIZE) {
+	if (error < (int)PAGE_SIZE) {
 		if (error >= 0)
 			error = -EFAULT;
 
@@ -1483,7 +1483,7 @@ int swsusp_read(unsigned int *flags_p)
 
 	memset(&snapshot, 0, sizeof(struct snapshot_handle));
 	error = snapshot_write_next(&snapshot);
-	if (error < PAGE_SIZE)
+	if (error < (int)PAGE_SIZE)
 		return error < 0 ? error : -EFAULT;
 	header = (struct swsusp_info *)data_of(snapshot);
 	error = get_swap_reader(&handle, flags_p);
-- 
cgit v1.2.3


From 464a5686e6c9df364fbfa9a6d0f61276a777d550 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Sun, 1 Jul 2018 22:18:27 -0300
Subject: regulator: Revert "regulator: pfuze100: add enable/disable for
 switch"

This reverts commit 5fe156f1cab4f340ddb6283c993912be77594016.

Commit 5fe156f1cab4 ("regulator: pfuze100: add enable/disable for switch")
causes boot regression on some platforms such as imx6sl-evk and
imx6sll-evk.

After this commit the SW4 regulator will be turned
off and since it supplies the DDR voltage on these boards, a
kernel hang is observed.

Revert it to avoid breaking old dtb's.

Fixes: 5fe156f1cab4 ("regulator: pfuze100: add enable/disable for switch")
Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pfuze100-regulator.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index 32f9af7f87c4..cde6eda1d283 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -163,9 +163,6 @@ static const struct regulator_ops pfuze100_fixed_regulator_ops = {
 };
 
 static const struct regulator_ops pfuze100_sw_regulator_ops = {
-	.enable = regulator_enable_regmap,
-	.disable = regulator_disable_regmap,
-	.is_enabled = regulator_is_enabled_regmap,
 	.list_voltage = regulator_list_voltage_linear,
 	.set_voltage_sel = regulator_set_voltage_sel_regmap,
 	.get_voltage_sel = regulator_get_voltage_sel_regmap,
@@ -212,11 +209,6 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 			.uV_step = (step),	\
 			.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
 			.vsel_mask = 0x3f,	\
-			.enable_reg = (base) + PFUZE100_MODE_OFFSET,	\
-			.enable_val = 0xc,	\
-			.disable_val = 0x0,	\
-			.enable_mask = 0xf,	\
-			.enable_time = 500,	\
 		},	\
 		.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
 		.stby_mask = 0x3f,	\
-- 
cgit v1.2.3


From d573454d9b4f00061da314460908e19476d2ff6d Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:30:28 +0000
Subject: ASoC: simple-card: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/simple_card.h     |  7 ++-----
 sound/soc/generic/simple-card.c | 17 +++++++----------
 2 files changed, 9 insertions(+), 15 deletions(-)

diff --git a/include/sound/simple_card.h b/include/sound/simple_card.h
index a6a2e1547092..d264e5463f22 100644
--- a/include/sound/simple_card.h
+++ b/include/sound/simple_card.h
@@ -1,12 +1,9 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * ASoC simple sound card support
  *
  * Copyright (C) 2012 Renesas Solutions Corp.
  * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __SIMPLE_CARD_H
diff --git a/sound/soc/generic/simple-card.c b/sound/soc/generic/simple-card.c
index c5b6e04cd926..64bf3560c1d1 100644
--- a/sound/soc/generic/simple-card.c
+++ b/sound/soc/generic/simple-card.c
@@ -1,13 +1,10 @@
-/*
- * ASoC simple sound card support
- *
- * Copyright (C) 2012 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC simple sound card support
+//
+// Copyright (C) 2012 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/module.h>
-- 
cgit v1.2.3


From d613a7f45ebb2f113444630fcbbb8a074c741998 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:30:44 +0000
Subject: ASoC: simple-card-utils: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/simple_card_utils.h     |  8 +++-----
 sound/soc/generic/simple-card-utils.c | 15 ++++++---------
 2 files changed, 9 insertions(+), 14 deletions(-)

diff --git a/include/sound/simple_card_utils.h b/include/sound/simple_card_utils.h
index f82acef3b992..8bc5e2d8b13c 100644
--- a/include/sound/simple_card_utils.h
+++ b/include/sound/simple_card_utils.h
@@ -1,12 +1,10 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * simple_card_utils.h
  *
  * Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
+
 #ifndef __SIMPLE_CARD_UTILS_H
 #define __SIMPLE_CARD_UTILS_H
 
diff --git a/sound/soc/generic/simple-card-utils.c b/sound/soc/generic/simple-card-utils.c
index 4398c9580929..d3f3f0fec74c 100644
--- a/sound/soc/generic/simple-card-utils.c
+++ b/sound/soc/generic/simple-card-utils.c
@@ -1,12 +1,9 @@
-/*
- * simple-card-utils.c
- *
- * Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// simple-card-utils.c
+//
+// Copyright (c) 2016 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+
 #include <linux/clk.h>
 #include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
-- 
cgit v1.2.3


From 9afe58f1cbd1fb5e9426483656ae6f65de4130e4 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:30:58 +0000
Subject: ASoC: simple-scu-card.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/simple-scu-card.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/sound/soc/generic/simple-scu-card.c b/sound/soc/generic/simple-scu-card.c
index 487716559deb..16a83bc51e0e 100644
--- a/sound/soc/generic/simple-scu-card.c
+++ b/sound/soc/generic/simple-scu-card.c
@@ -1,15 +1,12 @@
-/*
- * ASoC simple SCU sound card support
- *
- * Copyright (C) 2015 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * based on ${LINUX}/sound/soc/generic/simple-card.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC simple SCU sound card support
+//
+// Copyright (C) 2015 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// based on ${LINUX}/sound/soc/generic/simple-card.c
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/module.h>
-- 
cgit v1.2.3


From decd896121f965db2fdee0f0475c3e404746b333 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:31:16 +0000
Subject: ASoC: audio-graph-card.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/audio-graph-card.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/sound/soc/generic/audio-graph-card.c b/sound/soc/generic/audio-graph-card.c
index a2a3e630f11c..2094d2c8919f 100644
--- a/sound/soc/generic/audio-graph-card.c
+++ b/sound/soc/generic/audio-graph-card.c
@@ -1,15 +1,12 @@
-/*
- * ASoC audio graph sound card support
- *
- * Copyright (C) 2016 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * based on ${LINUX}/sound/soc/generic/simple-card.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC audio graph sound card support
+//
+// Copyright (C) 2016 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// based on ${LINUX}/sound/soc/generic/simple-card.c
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/gpio.h>
-- 
cgit v1.2.3


From ac204c9b030fe2d27cf3a63386811254d99b3ce4 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:31:33 +0000
Subject: ASoC: audio-graph-scu-card.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/generic/audio-graph-scu-card.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/sound/soc/generic/audio-graph-scu-card.c b/sound/soc/generic/audio-graph-scu-card.c
index 095ef6426d42..92882e392d6c 100644
--- a/sound/soc/generic/audio-graph-scu-card.c
+++ b/sound/soc/generic/audio-graph-scu-card.c
@@ -1,17 +1,14 @@
-/*
- * ASoC audio graph SCU sound card support
- *
- * Copyright (C) 2017 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * based on
- *	${LINUX}/sound/soc/generic/simple-scu-card.c
- *	${LINUX}/sound/soc/generic/audio-graph-card.c
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ASoC audio graph SCU sound card support
+//
+// Copyright (C) 2017 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// based on
+//	${LINUX}/sound/soc/generic/simple-scu-card.c
+//	${LINUX}/sound/soc/generic/audio-graph-card.c
+
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/gpio.h>
-- 
cgit v1.2.3


From d1aaa2e68619ca4c1cc05ce7bc029cda5a8cbe87 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:21:54 +0000
Subject: ASoC: soc-io.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-io.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/sound/soc/soc-io.c b/sound/soc/soc-io.c
index 026cd5347e53..1ff9175e9d5e 100644
--- a/sound/soc/soc-io.c
+++ b/sound/soc/soc-io.c
@@ -1,15 +1,10 @@
-/*
- * soc-io.c  --  ASoC register I/O helpers
- *
- * Copyright 2009-2011 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-io.c  --  ASoC register I/O helpers
+//
+// Copyright 2009-2011 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/i2c.h>
 #include <linux/spi/spi.h>
-- 
cgit v1.2.3


From e2cfd2c9673f4e9d08971fed53fe1f41d8270ef0 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:22:15 +0000
Subject: ASoC: soc-dai.h: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index e6f8c40ed43c..a14bc0608ae9 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -1,12 +1,9 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-dai.h -- ALSA SoC Layer
  *
  * Copyright:	2005-2008 Wolfson Microelectronics. PLC.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Digital Audio Interface (DAI) API.
  */
 
-- 
cgit v1.2.3


From 4eef5a90ca8b2aab61c98853141f9242af4a8339 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:22:30 +0000
Subject: ASoC: soc-ops.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-ops.c | 29 ++++++++++++-----------------
 1 file changed, 12 insertions(+), 17 deletions(-)

diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 7144a51ddfa9..592efb370c44 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -1,20 +1,15 @@
-/*
- * soc-ops.c  --  Generic ASoC operations
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *         with code, comments and ideas from :-
- *         Richard Purdie <richard@openedhand.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-ops.c  --  Generic ASoC operations
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//         with code, comments and ideas from :-
+//         Richard Purdie <richard@openedhand.com>
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-- 
cgit v1.2.3


From ed51758247c51dfdb526d279164cfd925496f187 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:22:44 +0000
Subject: ASoC: soc-pcm.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-pcm.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 6ee4131941df..c2a31b51da4f 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1,20 +1,14 @@
-/*
- * soc-pcm.c  --  ALSA SoC PCM
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Authors: Liam Girdwood <lrg@ti.com>
- *          Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-pcm.c  --  ALSA SoC PCM
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Authors: Liam Girdwood <lrg@ti.com>
+//          Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-- 
cgit v1.2.3


From b53c34b4b73eb65e6480ada6ec8ddbcc2d4e9817 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:22:58 +0000
Subject: ASoC: soc-dpcm.h: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dpcm.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/include/sound/soc-dpcm.h b/include/sound/soc-dpcm.h
index 806059052bfc..9bb92f187af8 100644
--- a/include/sound/soc-dpcm.h
+++ b/include/sound/soc-dpcm.h
@@ -1,11 +1,8 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-dpcm.h -- ALSA SoC Dynamic PCM Support
  *
  * Author:		Liam Girdwood <lrg@ti.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_SND_SOC_DPCM_H
-- 
cgit v1.2.3


From 8ab0215c11817fc0a89f1f82cdf10fd4c0eb9e86 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:23:16 +0000
Subject: ASoC: soc-jack.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-jack.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/sound/soc/soc-jack.c b/sound/soc/soc-jack.c
index b2b16044ae80..c7b990abdbaa 100644
--- a/sound/soc/soc-jack.c
+++ b/sound/soc/soc-jack.c
@@ -1,15 +1,10 @@
-/*
- * soc-jack.c  --  ALSA SoC jack handling
- *
- * Copyright 2008 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-jack.c  --  ALSA SoC jack handling
+//
+// Copyright 2008 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
 
 #include <sound/jack.h>
 #include <sound/soc.h>
-- 
cgit v1.2.3


From 632628df453ccda727fbcc1e346600162ac995e9 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:23:30 +0000
Subject: ASoC: soc-utils.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-utils.c | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/sound/soc/soc-utils.c b/sound/soc/soc-utils.c
index 2d9e98bd1530..ea024236c643 100644
--- a/sound/soc/soc-utils.c
+++ b/sound/soc/soc-utils.c
@@ -1,17 +1,11 @@
-/*
- * soc-util.c  --  ALSA SoC Audio Layer utility functions
- *
- * Copyright 2009 Wolfson Microelectronics PLC.
- *
- * Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
- *         Liam Girdwood <lrg@slimlogic.co.uk>
- *         
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-util.c  --  ALSA SoC Audio Layer utility functions
+//
+// Copyright 2009 Wolfson Microelectronics PLC.
+//
+// Author: Mark Brown <broonie@opensource.wolfsonmicro.com>
+//         Liam Girdwood <lrg@slimlogic.co.uk>
 
 #include <linux/platform_device.h>
 #include <linux/export.h>
-- 
cgit v1.2.3


From 9e14035c7fac144f31a822f0034fe5ed79c9ef8a Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:23:45 +0000
Subject: ASoC: soc-devres.c: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-devres.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/sound/soc/soc-devres.c b/sound/soc/soc-devres.c
index 7ac745df1412..a9ea172a66a7 100644
--- a/sound/soc/soc-devres.c
+++ b/sound/soc/soc-devres.c
@@ -1,13 +1,8 @@
-/*
- * soc-devres.c  --  ALSA SoC Audio Layer devres functions
- *
- * Copyright (C) 2013 Linaro Ltd
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-devres.c  --  ALSA SoC Audio Layer devres functions
+//
+// Copyright (C) 2013 Linaro Ltd
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-- 
cgit v1.2.3


From 7730bb13c7472620b585783f248b2dccd09d1819 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:24:04 +0000
Subject: ASoC: soc-acpi: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-acpi-intel-match.h | 14 ++------------
 include/sound/soc-acpi.h             | 13 ++-----------
 sound/soc/soc-acpi.c                 | 20 +++++---------------
 3 files changed, 9 insertions(+), 38 deletions(-)

diff --git a/include/sound/soc-acpi-intel-match.h b/include/sound/soc-acpi-intel-match.h
index 917ddd0f2762..bb1d24b703fb 100644
--- a/include/sound/soc-acpi-intel-match.h
+++ b/include/sound/soc-acpi-intel-match.h
@@ -1,16 +1,6 @@
-
-/*
- * Copyright (C) 2017, Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0
  *
+ * Copyright (C) 2017, Intel Corporation. All rights reserved.
  */
 
 #ifndef __LINUX_SND_SOC_ACPI_INTEL_MATCH_H
diff --git a/include/sound/soc-acpi.h b/include/sound/soc-acpi.h
index 082224275f52..e45b2330d16a 100644
--- a/include/sound/soc-acpi.h
+++ b/include/sound/soc-acpi.h
@@ -1,15 +1,6 @@
-/*
- * Copyright (C) 2013-15, Intel Corporation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License version
- * 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
+/* SPDX-License-Identifier: GPL-2.0
  *
+ * Copyright (C) 2013-15, Intel Corporation. All rights reserved.
  */
 
 #ifndef __LINUX_SND_SOC_ACPI_H
diff --git a/sound/soc/soc-acpi.c b/sound/soc/soc-acpi.c
index 3d7e1ff79139..b8e72b52db30 100644
--- a/sound/soc/soc-acpi.c
+++ b/sound/soc/soc-acpi.c
@@ -1,18 +1,8 @@
-/*
- * soc-apci.c - support for ACPI enumeration.
- *
- * Copyright (c) 2013-15, Intel Corporation.
- *
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// soc-apci.c - support for ACPI enumeration.
+//
+// Copyright (c) 2013-15, Intel Corporation.
 
 #include <sound/soc-acpi.h>
 
-- 
cgit v1.2.3


From 873486ed4af3e11bfc20832dff7b124ba652bf77 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:24:18 +0000
Subject: ASoC: soc-core: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  | 11 ++++-------
 sound/soc/soc-core.c | 41 ++++++++++++++++++-----------------------
 2 files changed, 22 insertions(+), 30 deletions(-)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index f7579f82cc00..16f0bf10cc42 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1,13 +1,10 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc.h -- ALSA SoC Layer
  *
- * Author:		Liam Girdwood
- * Created:		Aug 11th 2005
+ * Author:	Liam Girdwood
+ * Created:	Aug 11th 2005
  * Copyright:	Wolfson Microelectronics. PLC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_SND_SOC_H
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 4663de3cf495..68b08781c832 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1,26 +1,21 @@
-/*
- * soc-core.c  --  ALSA SoC Audio Layer
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *         with code, comments and ideas from :-
- *         Richard Purdie <richard@openedhand.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- *  TODO:
- *   o Add hw rules to enforce rates, etc.
- *   o More testing with other codecs/machines.
- *   o Add more codecs and platforms to ensure good API coverage.
- *   o Support TDM on PCM and I2S
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-core.c  --  ALSA SoC Audio Layer
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//         with code, comments and ideas from :-
+//         Richard Purdie <richard@openedhand.com>
+//
+//  TODO:
+//   o Add hw rules to enforce rates, etc.
+//   o More testing with other codecs/machines.
+//   o Add more codecs and platforms to ensure good API coverage.
+//   o Support TDM on PCM and I2S
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-- 
cgit v1.2.3


From c01f3af4d32071915119ffcb933e75d7c165378e Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:24:31 +0000
Subject: ASoC: soc-dapm: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dapm.h | 11 ++++-------
 sound/soc/soc-dapm.c     | 42 ++++++++++++++++++------------------------
 2 files changed, 22 insertions(+), 31 deletions(-)

diff --git a/include/sound/soc-dapm.h b/include/sound/soc-dapm.h
index a6ce2de4e20a..af9ef16cc34d 100644
--- a/include/sound/soc-dapm.h
+++ b/include/sound/soc-dapm.h
@@ -1,13 +1,10 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-dapm.h -- ALSA SoC Dynamic Audio Power Management
  *
- * Author:		Liam Girdwood
- * Created:		Aug 11th 2005
+ * Author:	Liam Girdwood
+ * Created:	Aug 11th 2005
  * Copyright:	Wolfson Microelectronics. PLC.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef __LINUX_SND_SOC_DAPM_H
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index a099c3e45504..0602b2888d52 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -1,27 +1,21 @@
-/*
- * soc-dapm.c  --  ALSA SoC Dynamic Audio Power Management
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- *  Features:
- *    o Changes power status of internal codec blocks depending on the
- *      dynamic configuration of codec internal audio paths and active
- *      DACs/ADCs.
- *    o Platform power domain - can support external components i.e. amps and
- *      mic/headphone insertion events.
- *    o Automatic Mic Bias support
- *    o Jack insertion power event initiation - e.g. hp insertion will enable
- *      sinks, dacs, etc
- *    o Delayed power down of audio subsystem to reduce pops between a quick
- *      device reopen.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-dapm.c  --  ALSA SoC Dynamic Audio Power Management
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//
+//  Features:
+//    o Changes power status of internal codec blocks depending on the
+//      dynamic configuration of codec internal audio paths and active
+//      DACs/ADCs.
+//    o Platform power domain - can support external components i.e. amps and
+//      mic/headphone insertion events.
+//    o Automatic Mic Bias support
+//    o Jack insertion power event initiation - e.g. hp insertion will enable
+//      sinks, dacs, etc
+//    o Delayed power down of audio subsystem to reduce pops between a quick
+//      device reopen.
 
 #include <linux/module.h>
 #include <linux/moduleparam.h>
-- 
cgit v1.2.3


From f2b6a1b25fecc48a46c8a41636101af8a41c88a8 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:24:45 +0000
Subject: ASoC: soc-topology: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-topology.h |  7 ++-----
 sound/soc/soc-topology.c     | 47 ++++++++++++++++++++------------------------
 2 files changed, 23 insertions(+), 31 deletions(-)

diff --git a/include/sound/soc-topology.h b/include/sound/soc-topology.h
index 401ef2c45d6c..fa4b8413d2e2 100644
--- a/include/sound/soc-topology.h
+++ b/include/sound/soc-topology.h
@@ -1,13 +1,10 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * linux/sound/soc-topology.h -- ALSA SoC Firmware Controls and DAPM
  *
  * Copyright (C) 2012 Texas Instruments Inc.
  * Copyright (C) 2015 Intel Corporation.
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Simple file API to load FW that includes mixers, coefficients, DAPM graphs,
  * algorithms, equalisers, DAIs, widgets, FE caps, BE caps, codec link caps etc.
  */
diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
index 05d177d689e2..66e77e020745 100644
--- a/sound/soc/soc-topology.c
+++ b/sound/soc/soc-topology.c
@@ -1,29 +1,24 @@
-/*
- * soc-topology.c  --  ALSA SoC Topology
- *
- * Copyright (C) 2012 Texas Instruments Inc.
- * Copyright (C) 2015 Intel Corporation.
- *
- * Authors: Liam Girdwood <liam.r.girdwood@linux.intel.com>
- *		K, Mythri P <mythri.p.k@intel.com>
- *		Prusty, Subhransu S <subhransu.s.prusty@intel.com>
- *		B, Jayachandran <jayachandran.b@intel.com>
- *		Abdullah, Omair M <omair.m.abdullah@intel.com>
- *		Jin, Yao <yao.jin@intel.com>
- *		Lin, Mengdong <mengdong.lin@intel.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- *  Add support to read audio firmware topology alongside firmware text. The
- *  topology data can contain kcontrols, DAPM graphs, widgets, DAIs, DAI links,
- *  equalizers, firmware, coefficients etc.
- *
- *  This file only manages the core ALSA and ASoC components, all other bespoke
- *  firmware topology data is passed to component drivers for bespoke handling.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-topology.c  --  ALSA SoC Topology
+//
+// Copyright (C) 2012 Texas Instruments Inc.
+// Copyright (C) 2015 Intel Corporation.
+//
+// Authors: Liam Girdwood <liam.r.girdwood@linux.intel.com>
+//		K, Mythri P <mythri.p.k@intel.com>
+//		Prusty, Subhransu S <subhransu.s.prusty@intel.com>
+//		B, Jayachandran <jayachandran.b@intel.com>
+//		Abdullah, Omair M <omair.m.abdullah@intel.com>
+//		Jin, Yao <yao.jin@intel.com>
+//		Lin, Mengdong <mengdong.lin@intel.com>
+//
+//  Add support to read audio firmware topology alongside firmware text. The
+//  topology data can contain kcontrols, DAPM graphs, widgets, DAIs, DAI links,
+//  equalizers, firmware, coefficients etc.
+//
+//  This file only manages the core ALSA and ASoC components, all other bespoke
+//  firmware topology data is passed to component drivers for bespoke handling.
 
 #include <linux/kernel.h>
 #include <linux/export.h>
-- 
cgit v1.2.3


From b3ed4c86a700b494fc5058a52531eeb14d6fe00f Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:24:57 +0000
Subject: ASoC: soc-compress: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/compress_driver.h | 21 +++------------------
 sound/soc/soc-compress.c        | 24 +++++++++---------------
 2 files changed, 12 insertions(+), 33 deletions(-)

diff --git a/include/sound/compress_driver.h b/include/sound/compress_driver.h
index 9924bc9cbc7c..ea8c93bbb0e0 100644
--- a/include/sound/compress_driver.h
+++ b/include/sound/compress_driver.h
@@ -1,27 +1,12 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  *  compress_driver.h - compress offload driver definations
  *
  *  Copyright (C) 2011 Intel Corporation
  *  Authors:	Vinod Koul <vinod.koul@linux.intel.com>
  *		Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
- *  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; version 2 of the License.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
  */
+
 #ifndef __COMPRESS_DRIVER_H
 #define __COMPRESS_DRIVER_H
 
diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index e095115fa9f9..b9e1673fea51 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -1,18 +1,12 @@
-/*
- * soc-compress.c  --  ALSA SoC Compress
- *
- * Copyright (C) 2012 Intel Corp.
- *
- * Authors: Namarta Kohli <namartax.kohli@intel.com>
- *          Ramesh Babu K V <ramesh.babu@linux.intel.com>
- *          Vinod Koul <vinod.koul@linux.intel.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-compress.c  --  ALSA SoC Compress
+//
+// Copyright (C) 2012 Intel Corp.
+//
+// Authors: Namarta Kohli <namartax.kohli@intel.com>
+//          Ramesh Babu K V <ramesh.babu@linux.intel.com>
+//          Vinod Koul <vinod.koul@linux.intel.com>
 
 #include <linux/kernel.h>
 #include <linux/init.h>
-- 
cgit v1.2.3


From 1356a6071cf4d7187652cd2b18dfab4763e0dba6 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:25:11 +0000
Subject: ASoC: soc-generic-dmaengine-pcm: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/dmaengine_pcm.h         | 14 +++-----------
 sound/soc/soc-generic-dmaengine-pcm.c | 19 +++++--------------
 2 files changed, 8 insertions(+), 25 deletions(-)

diff --git a/include/sound/dmaengine_pcm.h b/include/sound/dmaengine_pcm.h
index e3481eebdd98..2c4cfaa135a6 100644
--- a/include/sound/dmaengine_pcm.h
+++ b/include/sound/dmaengine_pcm.h
@@ -1,17 +1,9 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0+
+ *
  *  Copyright (C) 2012, Analog Devices Inc.
  *	Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under  the terms of the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the License, or (at your
- *  option) any later version.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  675 Mass Ave, Cambridge, MA 02139, USA.
- *
  */
+
 #ifndef __SOUND_DMAENGINE_PCM_H__
 #define __SOUND_DMAENGINE_PCM_H__
 
diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 56a541b9ff9e..13bdca6e41c5 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -1,17 +1,8 @@
-/*
- *  Copyright (C) 2013, Analog Devices Inc.
- *	Author: Lars-Peter Clausen <lars@metafoo.de>
- *
- *  This program is free software; you can redistribute it and/or modify it
- *  under  the terms of the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the License, or (at your
- *  option) any later version.
- *
- *  You should have received a copy of the GNU General Public License along
- *  with this program; if not, write to the Free Software Foundation, Inc.,
- *  675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+//  Copyright (C) 2013, Analog Devices Inc.
+//	Author: Lars-Peter Clausen <lars@metafoo.de>
+
 #include <linux/module.h>
 #include <linux/init.h>
 #include <linux/dmaengine.h>
-- 
cgit v1.2.3


From 1a8f0a3c13c136951de7ea24ccb148e745db98a2 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 2 Jul 2018 06:26:27 +0000
Subject: ASoC: ac97: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/ac97/codec.h      |  8 +++-----
 include/sound/ac97/compat.h     |  9 +++------
 include/sound/ac97/controller.h |  8 +++-----
 include/sound/ac97/regs.h       | 20 ++------------------
 include/sound/ac97_codec.h      | 25 +++++--------------------
 sound/soc/soc-ac97.c            | 29 ++++++++++++-----------------
 6 files changed, 28 insertions(+), 71 deletions(-)

diff --git a/include/sound/ac97/codec.h b/include/sound/ac97/codec.h
index ec04be9ab119..9792d25fa369 100644
--- a/include/sound/ac97/codec.h
+++ b/include/sound/ac97/codec.h
@@ -1,10 +1,8 @@
-/*
- *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
+/* SPDX-License-Identifier: GPL-2.0
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
  */
+
 #ifndef __SOUND_AC97_CODEC2_H
 #define __SOUND_AC97_CODEC2_H
 
diff --git a/include/sound/ac97/compat.h b/include/sound/ac97/compat.h
index 1351cba40048..57e19afa31ab 100644
--- a/include/sound/ac97/compat.h
+++ b/include/sound/ac97/compat.h
@@ -1,14 +1,11 @@
-/*
- *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
+/* SPDX-License-Identifier: GPL-2.0
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
  *
  * This file is for backward compatibility with snd_ac97 structure and its
  * multiple usages, such as the snd_ac97_bus and snd_ac97_build_ops.
- *
  */
+
 #ifndef AC97_COMPAT_H
 #define AC97_COMPAT_H
 
diff --git a/include/sound/ac97/controller.h b/include/sound/ac97/controller.h
index b36ecdd64f14..06b5afb7fa6b 100644
--- a/include/sound/ac97/controller.h
+++ b/include/sound/ac97/controller.h
@@ -1,10 +1,8 @@
-/*
- *  Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
+/* SPDX-License-Identifier: GPL-2.0
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
+ * Copyright (C) 2016 Robert Jarzmik <robert.jarzmik@free.fr>
  */
+
 #ifndef AC97_CONTROLLER_H
 #define AC97_CONTROLLER_H
 
diff --git a/include/sound/ac97/regs.h b/include/sound/ac97/regs.h
index 9a4fa0c3264a..843f73f3705a 100644
--- a/include/sound/ac97/regs.h
+++ b/include/sound/ac97/regs.h
@@ -1,27 +1,11 @@
-/*
+/* SPDX-License-Identifier: GPL-2.0+
+ *
  *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>
  *  Universal interface for Audio Codec '97
  *
  *  For more details look to AC '97 component specification revision 2.1
  *  by Intel Corporation (http://developer.intel.com).
- *
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
-
 /*
  *  AC'97 codec registers
  */
diff --git a/include/sound/ac97_codec.h b/include/sound/ac97_codec.h
index 89d311a503d3..cc383991c0fe 100644
--- a/include/sound/ac97_codec.h
+++ b/include/sound/ac97_codec.h
@@ -1,30 +1,15 @@
-#ifndef __SOUND_AC97_CODEC_H
-#define __SOUND_AC97_CODEC_H
-
-/*
+/* SPDX-License-Identifier: GPL-2.0+
+ *
  *  Copyright (c) by Jaroslav Kysela <perex@perex.cz>
  *  Universal interface for Audio Codec '97
  *
  *  For more details look to AC '97 component specification revision 2.1
  *  by Intel Corporation (http://developer.intel.com).
- *
- *
- *   This program is free software; you can redistribute it and/or modify
- *   it under the terms of the GNU General Public License as published by
- *   the Free Software Foundation; either version 2 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program; if not, write to the Free Software
- *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
- *
  */
 
+#ifndef __SOUND_AC97_CODEC_H
+#define __SOUND_AC97_CODEC_H
+
 #include <linux/bitops.h>
 #include <linux/device.h>
 #include <linux/workqueue.h>
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index 3f424f214bca..c086786e4471 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -1,20 +1,15 @@
-/*
- * soc-ac97.c  --  ALSA SoC Audio Layer AC97 support
- *
- * Copyright 2005 Wolfson Microelectronics PLC.
- * Copyright 2005 Openedhand Ltd.
- * Copyright (C) 2010 Slimlogic Ltd.
- * Copyright (C) 2010 Texas Instruments Inc.
- *
- * Author: Liam Girdwood <lrg@slimlogic.co.uk>
- *         with code, comments and ideas from :-
- *         Richard Purdie <richard@openedhand.com>
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// soc-ac97.c  --  ALSA SoC Audio Layer AC97 support
+//
+// Copyright 2005 Wolfson Microelectronics PLC.
+// Copyright 2005 Openedhand Ltd.
+// Copyright (C) 2010 Slimlogic Ltd.
+// Copyright (C) 2010 Texas Instruments Inc.
+//
+// Author: Liam Girdwood <lrg@slimlogic.co.uk>
+//         with code, comments and ideas from :-
+//         Richard Purdie <richard@openedhand.com>
 
 #include <linux/ctype.h>
 #include <linux/delay.h>
-- 
cgit v1.2.3


From 1581250119daa9426c359d059e2dc14ec04bcc0c Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Sat, 30 Jun 2018 22:24:33 +0200
Subject: ASoC: pxa: select SND_PXA2XX_LIB for drivers that depend on it

Commit d767d3ce5c48b ("ASoC: pxa: provide PCM ops for ssp, i2s and ac97
components") created a build-time dependency to SND_PXA2XX_LIB but
missed to reflect that in Kconfig.

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/pxa/Kconfig | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 95dcf97a6271..2fc02c227f69 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -24,15 +24,18 @@ config SND_PXA2XX_AC97
 config SND_PXA2XX_SOC_AC97
 	tristate
 	select AC97_BUS
+	select SND_PXA2XX_LIB
 	select SND_PXA2XX_LIB_AC97
 	select SND_SOC_AC97_BUS
 
 config SND_PXA2XX_SOC_I2S
+	select SND_PXA2XX_LIB
 	tristate
 
 config SND_PXA_SOC_SSP
 	tristate "Soc Audio via PXA2xx/PXA3xx SSP ports"
 	select PXA_SSP
+	select SND_PXA2XX_LIB
 
 config SND_MMP_SOC_SSPA
 	tristate
-- 
cgit v1.2.3


From 05739375f1c0a1048fea8b9c4cb54d9e4a891938 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Fri, 29 Jun 2018 14:59:40 +0200
Subject: ASoC: pxa-ssp: remove .set_pll() and .set_clkdiv() callbacks

The .set_pll() and .set_clkdiv() callbacks are considered legacy and should
not be used anymore. In order to support PXA boards on DT platforms, remove
them and let the code figure out the correct dividers and PLL base
frequencies itself.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/pxa2xx_ssp.h |   8 +++
 sound/soc/pxa/pxa-ssp.c    | 146 ++++++++++++++++++++++-----------------------
 2 files changed, 81 insertions(+), 73 deletions(-)

diff --git a/include/linux/pxa2xx_ssp.h b/include/linux/pxa2xx_ssp.h
index 03a7ca46735b..13b4244d44c1 100644
--- a/include/linux/pxa2xx_ssp.h
+++ b/include/linux/pxa2xx_ssp.h
@@ -171,6 +171,14 @@
 #define SSACD_SCDB		(1 << 3)	/* SSPSYSCLK Divider Bypass */
 #define SSACD_ACPS(x)		((x) << 4)	/* Audio clock PLL select */
 #define SSACD_ACDS(x)		((x) << 0)	/* Audio clock divider select */
+#define SSACD_ACDS_1		(0)
+#define SSACD_ACDS_2		(1)
+#define SSACD_ACDS_4		(2)
+#define SSACD_ACDS_8		(3)
+#define SSACD_ACDS_16		(4)
+#define SSACD_ACDS_32		(5)
+#define SSACD_SCDB_4X		(0)
+#define SSACD_SCDB_1X		(1)
 #define SSACD_SCDX8		(1 << 7)	/* SYSCLK division ratio select */
 
 /* LPSS SSP */
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index 01d54697ede4..f8339bb01251 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -41,6 +41,7 @@
  */
 struct ssp_priv {
 	struct ssp_device *ssp;
+	unsigned long ssp_clk;
 	unsigned int sysclk;
 	unsigned int dai_fmt;
 	unsigned int configured_dai_fmt;
@@ -192,21 +193,6 @@ static void pxa_ssp_set_scr(struct ssp_device *ssp, u32 div)
 	pxa_ssp_write_reg(ssp, SSCR0, sscr0);
 }
 
-/**
- * pxa_ssp_get_clkdiv - get SSP clock divider
- */
-static u32 pxa_ssp_get_scr(struct ssp_device *ssp)
-{
-	u32 sscr0 = pxa_ssp_read_reg(ssp, SSCR0);
-	u32 div;
-
-	if (ssp->type == PXA25x_SSP)
-		div = ((sscr0 >> 8) & 0xff) * 2 + 2;
-	else
-		div = ((sscr0 >> 8) & 0xfff) + 1;
-	return div;
-}
-
 /*
  * Set the SSP ports SYSCLK.
  */
@@ -262,67 +248,18 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai,
 	return 0;
 }
 
-/*
- * Set the SSP clock dividers.
- */
-static int pxa_ssp_set_dai_clkdiv(struct snd_soc_dai *cpu_dai,
-	int div_id, int div)
-{
-	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
-	struct ssp_device *ssp = priv->ssp;
-	int val;
-
-	switch (div_id) {
-	case PXA_SSP_AUDIO_DIV_ACDS:
-		val = (pxa_ssp_read_reg(ssp, SSACD) & ~0x7) | SSACD_ACDS(div);
-		pxa_ssp_write_reg(ssp, SSACD, val);
-		break;
-	case PXA_SSP_AUDIO_DIV_SCDB:
-		val = pxa_ssp_read_reg(ssp, SSACD);
-		val &= ~SSACD_SCDB;
-		if (ssp->type == PXA3xx_SSP)
-			val &= ~SSACD_SCDX8;
-		switch (div) {
-		case PXA_SSP_CLK_SCDB_1:
-			val |= SSACD_SCDB;
-			break;
-		case PXA_SSP_CLK_SCDB_4:
-			break;
-		case PXA_SSP_CLK_SCDB_8:
-			if (ssp->type == PXA3xx_SSP)
-				val |= SSACD_SCDX8;
-			else
-				return -EINVAL;
-			break;
-		default:
-			return -EINVAL;
-		}
-		pxa_ssp_write_reg(ssp, SSACD, val);
-		break;
-	case PXA_SSP_DIV_SCR:
-		pxa_ssp_set_scr(ssp, div);
-		break;
-	default:
-		return -ENODEV;
-	}
-
-	return 0;
-}
-
 /*
  * Configure the PLL frequency pxa27x and (afaik - pxa320 only)
  */
-static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id,
-	int source, unsigned int freq_in, unsigned int freq_out)
+static int pxa_ssp_set_pll(struct ssp_priv *priv, unsigned int freq)
 {
-	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
 	struct ssp_device *ssp = priv->ssp;
 	u32 ssacd = pxa_ssp_read_reg(ssp, SSACD) & ~0x70;
 
 	if (ssp->type == PXA3xx_SSP)
 		pxa_ssp_write_reg(ssp, SSACDD, 0);
 
-	switch (freq_out) {
+	switch (freq) {
 	case 5622000:
 		break;
 	case 11345000:
@@ -353,7 +290,7 @@ static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id,
 			u64 tmp = 19968;
 
 			tmp *= 1000000;
-			do_div(tmp, freq_out);
+			do_div(tmp, freq);
 			val = tmp;
 
 			val = (val << 16) | 64;
@@ -363,7 +300,7 @@ static int pxa_ssp_set_dai_pll(struct snd_soc_dai *cpu_dai, int pll_id,
 
 			dev_dbg(&ssp->pdev->dev,
 				"Using SSACDD %x to supply %uHz\n",
-				val, freq_out);
+				val, freq);
 			break;
 		}
 
@@ -568,6 +505,24 @@ static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv)
 	return 0;
 }
 
+struct pxa_ssp_clock_mode {
+	int rate;
+	int pll;
+	u8 acds;
+	u8 scdb;
+};
+
+static const struct pxa_ssp_clock_mode pxa_ssp_clock_modes[] = {
+	{ .rate =  8000, .pll = 32842000, .acds = SSACD_ACDS_32, .scdb = SSACD_SCDB_4X },
+	{ .rate = 11025, .pll =  5622000, .acds = SSACD_ACDS_4,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 16000, .pll = 32842000, .acds = SSACD_ACDS_16, .scdb = SSACD_SCDB_4X },
+	{ .rate = 22050, .pll =  5622000, .acds = SSACD_ACDS_2,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 44100, .pll = 11345000, .acds = SSACD_ACDS_2,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 48000, .pll = 12235000, .acds = SSACD_ACDS_2,  .scdb = SSACD_SCDB_4X },
+	{ .rate = 96000, .pll = 12235000, .acds = SSACD_ACDS_4,  .scdb = SSACD_SCDB_1X },
+	{}
+};
+
 /*
  * Set the SSP audio DMA parameters and sample size.
  * Can be called multiple times by oss emulation.
@@ -579,11 +534,12 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream,
 	struct ssp_priv *priv = snd_soc_dai_get_drvdata(cpu_dai);
 	struct ssp_device *ssp = priv->ssp;
 	int chn = params_channels(params);
-	u32 sscr0;
-	u32 sspsp;
+	u32 sscr0, sspsp;
 	int width = snd_pcm_format_physical_width(params_format(params));
 	int ttsa = pxa_ssp_read_reg(ssp, SSTSA) & 0xf;
 	struct snd_dmaengine_dai_dma_data *dma_data;
+	int rate = params_rate(params);
+	int bclk = rate * chn * (width / 8);
 	int ret;
 
 	dma_data = snd_soc_dai_get_dma_data(cpu_dai, substream);
@@ -623,11 +579,57 @@ static int pxa_ssp_hw_params(struct snd_pcm_substream *substream,
 	}
 	pxa_ssp_write_reg(ssp, SSCR0, sscr0);
 
+	if (sscr0 & SSCR0_ACS) {
+		ret = pxa_ssp_set_pll(priv, bclk);
+
+		/*
+		 * If we were able to generate the bclk directly,
+		 * all is fine. Otherwise, look up the closest rate
+		 * from the table and also set the dividers.
+		 */
+
+		if (ret < 0) {
+			const struct pxa_ssp_clock_mode *m;
+			int ssacd, acds;
+
+			for (m = pxa_ssp_clock_modes; m->rate; m++) {
+				if (m->rate == rate)
+					break;
+			}
+
+			if (!m->rate)
+				return -EINVAL;
+
+			acds = m->acds;
+
+			/* The values in the table are for 16 bits */
+			if (width == 32)
+				acds--;
+
+			ret = pxa_ssp_set_pll(priv, bclk);
+			if (ret < 0)
+				return ret;
+
+			ssacd = pxa_ssp_read_reg(ssp, SSACD);
+			ssacd &= ~(SSACD_ACDS(7) | SSACD_SCDB_1X);
+			ssacd |= SSACD_ACDS(m->acds);
+			ssacd |= m->scdb;
+			pxa_ssp_write_reg(ssp, SSACD, ssacd);
+		}
+	} else if (sscr0 & SSCR0_ECS) {
+		/*
+		 * For setups with external clocking, the PLL and its diviers
+		 * are not active. Instead, the SCR bits in SSCR0 can be used
+		 * to divide the clock.
+		 */
+		pxa_ssp_set_scr(ssp, bclk / rate);
+	}
+
 	switch (priv->dai_fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 	       sspsp = pxa_ssp_read_reg(ssp, SSPSP);
 
-		if ((pxa_ssp_get_scr(ssp) == 4) && (width == 16)) {
+		if (((priv->sysclk / bclk) == 64) && (width == 16)) {
 			/* This is a special case where the bitclk is 64fs
 			 * and we're not dealing with 2*32 bits of audio
 			 * samples.
@@ -812,8 +814,6 @@ static const struct snd_soc_dai_ops pxa_ssp_dai_ops = {
 	.trigger	= pxa_ssp_trigger,
 	.hw_params	= pxa_ssp_hw_params,
 	.set_sysclk	= pxa_ssp_set_dai_sysclk,
-	.set_clkdiv	= pxa_ssp_set_dai_clkdiv,
-	.set_pll	= pxa_ssp_set_dai_pll,
 	.set_fmt	= pxa_ssp_set_dai_fmt,
 	.set_tdm_slot	= pxa_ssp_set_dai_tdm_slot,
 	.set_tristate	= pxa_ssp_set_dai_tristate,
-- 
cgit v1.2.3


From d8ffee2f551a627ffb7b216e2da322cb9a037f77 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Fri, 29 Jun 2018 13:33:09 +0200
Subject: spi: spi-fsl-dspi: Fix imprecise abort on VF500 during probe

Registers of DSPI should not be accessed before enabling its clock.  On
Toradex Colibri VF50 on Iris carrier board this could be seen during
bootup as imprecise abort:

    Unhandled fault: imprecise external abort (0x1c06) at 0x00000000
    Internal error: : 1c06 [#1] ARM
    Modules linked in:
    CPU: 0 PID: 1 Comm: swapper Not tainted 4.14.39-dirty #97
    Hardware name: Freescale Vybrid VF5xx/VF6xx (Device Tree)
    Backtrace:
    [<804166a8>] (regmap_write) from [<80466b5c>] (dspi_probe+0x1f0/0x8dc)
    [<8046696c>] (dspi_probe) from [<8040107c>] (platform_drv_probe+0x54/0xb8)
    [<80401028>] (platform_drv_probe) from [<803ff53c>] (driver_probe_device+0x280/0x2f8)
    [<803ff2bc>] (driver_probe_device) from [<803ff674>] (__driver_attach+0xc0/0xc4)
    [<803ff5b4>] (__driver_attach) from [<803fd818>] (bus_for_each_dev+0x70/0xa4)
    [<803fd7a8>] (bus_for_each_dev) from [<803fee74>] (driver_attach+0x24/0x28)
    [<803fee50>] (driver_attach) from [<803fe980>] (bus_add_driver+0x1a0/0x218)
    [<803fe7e0>] (bus_add_driver) from [<803fffe8>] (driver_register+0x80/0x100)
    [<803fff68>] (driver_register) from [<80400fdc>] (__platform_driver_register+0x48/0x50)
    [<80400f94>] (__platform_driver_register) from [<8091cf7c>] (fsl_dspi_driver_init+0x1c/0x20)
    [<8091cf60>] (fsl_dspi_driver_init) from [<8010195c>] (do_one_initcall+0x4c/0x174)
    [<80101910>] (do_one_initcall) from [<80900e8c>] (kernel_init_freeable+0x144/0x1d8)
    [<80900d48>] (kernel_init_freeable) from [<805ff6a8>] (kernel_init+0x10/0x114)
    [<805ff698>] (kernel_init) from [<80107be8>] (ret_from_fork+0x14/0x2c)

Cc: <stable@vger.kernel.org>
Fixes: 5ee67b587a2b ("spi: dspi: clear SPI_SR before enable interrupt")
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index ff7456be9d6d..89a1e7a4fe5d 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1071,30 +1071,30 @@ static int dspi_probe(struct platform_device *pdev)
 		}
 	}
 
+	dspi->clk = devm_clk_get(&pdev->dev, "dspi");
+	if (IS_ERR(dspi->clk)) {
+		ret = PTR_ERR(dspi->clk);
+		dev_err(&pdev->dev, "unable to get clock\n");
+		goto out_master_put;
+	}
+	ret = clk_prepare_enable(dspi->clk);
+	if (ret)
+		goto out_master_put;
+
 	dspi_init(dspi);
 	dspi->irq = platform_get_irq(pdev, 0);
 	if (dspi->irq < 0) {
 		dev_err(&pdev->dev, "can't get platform irq\n");
 		ret = dspi->irq;
-		goto out_master_put;
+		goto out_clk_put;
 	}
 
 	ret = devm_request_irq(&pdev->dev, dspi->irq, dspi_interrupt, 0,
 			pdev->name, dspi);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "Unable to attach DSPI interrupt\n");
-		goto out_master_put;
-	}
-
-	dspi->clk = devm_clk_get(&pdev->dev, "dspi");
-	if (IS_ERR(dspi->clk)) {
-		ret = PTR_ERR(dspi->clk);
-		dev_err(&pdev->dev, "unable to get clock\n");
-		goto out_master_put;
+		goto out_clk_put;
 	}
-	ret = clk_prepare_enable(dspi->clk);
-	if (ret)
-		goto out_master_put;
 
 	if (dspi->devtype_data->trans_mode == DSPI_DMA_MODE) {
 		ret = dspi_request_dma(dspi, res->start);
-- 
cgit v1.2.3


From 5650729f9a1bbf65b57139d855dabe0a7e6cb494 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Fri, 29 Jun 2018 17:09:20 +0200
Subject: ASoC: es7134: remove 64kHz rate from the supported rates

64Khz is actually not supported by the es7134 according to the datasheet

Fixes: 9000b59d7a12 ("ASoC: es7134: add es7134 DAC driver")
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es7134.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/es7134.c b/sound/soc/codecs/es7134.c
index 58515bb1a303..2fbb49f5b278 100644
--- a/sound/soc/codecs/es7134.c
+++ b/sound/soc/codecs/es7134.c
@@ -48,7 +48,11 @@ static struct snd_soc_dai_driver es7134_dai = {
 		.stream_name = "Playback",
 		.channels_min = 2,
 		.channels_max = 2,
-		.rates = SNDRV_PCM_RATE_8000_192000,
+		.rates = (SNDRV_PCM_RATE_8000_48000 |
+			  SNDRV_PCM_RATE_88200      |
+			  SNDRV_PCM_RATE_96000      |
+			  SNDRV_PCM_RATE_176400     |
+			  SNDRV_PCM_RATE_192000),
 		.formats = (SNDRV_PCM_FMTBIT_S16_LE  |
 			    SNDRV_PCM_FMTBIT_S18_3LE |
 			    SNDRV_PCM_FMTBIT_S20_3LE |
-- 
cgit v1.2.3


From a016b11cc41df06b79c0c226e719d0d88373919c Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Fri, 29 Jun 2018 17:09:21 +0200
Subject: ASoC: es7134: check if mclk rate is valid

For each supported sample rate, the es7134 can work with several
mclk / sample rate ratio. Check if ratio we get is actually OK.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es7134.c | 119 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 117 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/es7134.c b/sound/soc/codecs/es7134.c
index 2fbb49f5b278..698289dc3e22 100644
--- a/sound/soc/codecs/es7134.c
+++ b/sound/soc/codecs/es7134.c
@@ -17,6 +17,7 @@
  * in the file called COPYING.
  */
 
+#include <linux/of_platform.h>
 #include <linux/module.h>
 #include <sound/soc.h>
 
@@ -24,6 +25,77 @@
  * The everest 7134 is a very simple DA converter with no register
  */
 
+struct es7134_clock_mode {
+	unsigned int rate_min;
+	unsigned int rate_max;
+	unsigned int *mclk_fs;
+	unsigned int mclk_fs_num;
+};
+
+struct es7134_chip {
+	const struct es7134_clock_mode *modes;
+	unsigned int mode_num;
+};
+
+struct es7134_data {
+	unsigned int mclk;
+	const struct es7134_chip *chip;
+};
+
+static int es7134_check_mclk(struct snd_soc_dai *dai,
+			     struct es7134_data *priv,
+			     unsigned int rate)
+{
+	unsigned int mfs = priv->mclk / rate;
+	int i, j;
+
+	for (i = 0; i < priv->chip->mode_num; i++) {
+		const struct es7134_clock_mode *mode = &priv->chip->modes[i];
+
+		if (rate < mode->rate_min || rate > mode->rate_max)
+			continue;
+
+		for (j = 0; j < mode->mclk_fs_num; j++) {
+			if (mode->mclk_fs[j] == mfs)
+				return 0;
+		}
+
+		dev_err(dai->dev, "unsupported mclk_fs %u for rate %u\n",
+			mfs, rate);
+		return -EINVAL;
+	}
+
+	/* should not happen */
+	dev_err(dai->dev, "unsupported rate: %u\n", rate);
+	return -EINVAL;
+}
+
+static int es7134_hw_params(struct snd_pcm_substream *substream,
+			    struct snd_pcm_hw_params *params,
+			    struct snd_soc_dai *dai)
+{
+	struct es7134_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	/* mclk has not been provided, assume it is OK */
+	if (!priv->mclk)
+		return 0;
+
+	return es7134_check_mclk(dai, priv, params_rate(params));
+}
+
+static int es7134_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+			     unsigned int freq, int dir)
+{
+	struct es7134_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	if (dir == SND_SOC_CLOCK_IN && clk_id == 0) {
+		priv->mclk = freq;
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
 static int es7134_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 {
 	fmt &= (SND_SOC_DAIFMT_FORMAT_MASK | SND_SOC_DAIFMT_INV_MASK |
@@ -40,6 +112,8 @@ static int es7134_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 
 static const struct snd_soc_dai_ops es7134_dai_ops = {
 	.set_fmt	= es7134_set_fmt,
+	.hw_params	= es7134_hw_params,
+	.set_sysclk	= es7134_set_sysclk,
 };
 
 static struct snd_soc_dai_driver es7134_dai = {
@@ -62,6 +136,33 @@ static struct snd_soc_dai_driver es7134_dai = {
 	.ops = &es7134_dai_ops,
 };
 
+static const struct es7134_clock_mode es7134_modes[] = {
+	{
+		/* Single speed mode */
+		.rate_min = 8000,
+		.rate_max = 50000,
+		.mclk_fs = (unsigned int[]) { 256, 384, 512, 768, 1024 },
+		.mclk_fs_num = 5,
+	}, {
+		/* Double speed mode */
+		.rate_min = 84000,
+		.rate_max = 100000,
+		.mclk_fs = (unsigned int[]) { 128, 192, 256, 384, 512 },
+		.mclk_fs_num = 5,
+	}, {
+		/* Quad speed mode */
+		.rate_min = 167000,
+		.rate_max = 192000,
+		.mclk_fs = (unsigned int[]) { 128, 192, 256 },
+		.mclk_fs_num = 3,
+	},
+};
+
+static const struct es7134_chip es7134_chip = {
+	.modes = es7134_modes,
+	.mode_num = ARRAY_SIZE(es7134_modes),
+};
+
 static const struct snd_soc_dapm_widget es7134_dapm_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("AOUTL"),
 	SND_SOC_DAPM_OUTPUT("AOUTR"),
@@ -86,6 +187,20 @@ static const struct snd_soc_component_driver es7134_component_driver = {
 
 static int es7134_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
+	struct es7134_data *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+
+	priv->chip = of_device_get_match_data(dev);
+	if (!priv->chip) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
 	return devm_snd_soc_register_component(&pdev->dev,
 				      &es7134_component_driver,
 				      &es7134_dai, 1);
@@ -93,8 +208,8 @@ static int es7134_probe(struct platform_device *pdev)
 
 #ifdef CONFIG_OF
 static const struct of_device_id es7134_ids[] = {
-	{ .compatible = "everest,es7134", },
-	{ .compatible = "everest,es7144", },
+	{ .compatible = "everest,es7134", .data = &es7134_chip },
+	{ .compatible = "everest,es7144", .data = &es7134_chip },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, es7134_ids);
-- 
cgit v1.2.3


From 424e2b4b3521334812d833eef27df77671428698 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Fri, 29 Jun 2018 17:09:23 +0200
Subject: ASoC: es7134: Add VDD and AVDD power supplies

Add the VDD and AVDD power supplies to the DAPM graph as some board may
need to enable a regulator to turn them on.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es7134.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/soc/codecs/es7134.c b/sound/soc/codecs/es7134.c
index 698289dc3e22..5ad59c38fed1 100644
--- a/sound/soc/codecs/es7134.c
+++ b/sound/soc/codecs/es7134.c
@@ -167,11 +167,15 @@ static const struct snd_soc_dapm_widget es7134_dapm_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("AOUTL"),
 	SND_SOC_DAPM_OUTPUT("AOUTR"),
 	SND_SOC_DAPM_DAC("DAC", "Playback", SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD", 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("AVDD", 0, 0),
 };
 
 static const struct snd_soc_dapm_route es7134_dapm_routes[] = {
 	{ "AOUTL", NULL, "DAC" },
 	{ "AOUTR", NULL, "DAC" },
+	{ "Playback", NULL, "VDD" },
+	{ "DAC", NULL, "AVDD" },
 };
 
 static const struct snd_soc_component_driver es7134_component_driver = {
-- 
cgit v1.2.3


From 9f35b818a2f90fb6cb291aa0c9f835d4f0974a9a Mon Sep 17 00:00:00 2001
From: Heiko Carstens <heiko.carstens@de.ibm.com>
Date: Mon, 2 Jul 2018 10:54:02 +0200
Subject: s390/sysinfo: add missing #ifdef CONFIG_PROC_FS

Get rid of this compile warning for !PROC_FS:

  CC      arch/s390/kernel/sysinfo.o
arch/s390/kernel/sysinfo.c:275:12: warning: 'sysinfo_show' defined but not used [-Wunused-function]
 static int sysinfo_show(struct seq_file *m, void *v)

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/sysinfo.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/s390/kernel/sysinfo.c b/arch/s390/kernel/sysinfo.c
index 54f5496913fa..12f80d1f0415 100644
--- a/arch/s390/kernel/sysinfo.c
+++ b/arch/s390/kernel/sysinfo.c
@@ -59,6 +59,8 @@ int stsi(void *sysinfo, int fc, int sel1, int sel2)
 }
 EXPORT_SYMBOL(stsi);
 
+#ifdef CONFIG_PROC_FS
+
 static bool convert_ext_name(unsigned char encoding, char *name, size_t len)
 {
 	switch (encoding) {
@@ -301,6 +303,8 @@ static int __init sysinfo_create_proc(void)
 }
 device_initcall(sysinfo_create_proc);
 
+#endif /* CONFIG_PROC_FS */
+
 /*
  * Service levels interface.
  */
-- 
cgit v1.2.3


From b887b1b106654141ab034061ef0cc8d471ebc683 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 1 Jul 2018 11:31:48 +0200
Subject: s390/decompressor: avoid constant startup.a rebuilds

Correct merging error which replaced startup.a in targets list with
non-existing setup.a. Due to missing startup.a in targets list if_changed
triggered startup.a rebuild unconditionally.

Fixes: 3e200c54438d ("s390/decompressor: avoid reusing uncompressed image objects")
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index a1ca3b805c74..e15baa7b8e0b 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -28,7 +28,7 @@ endif
 CFLAGS_sclp_early_core.o += -I$(srctree)/drivers/s390/char
 
 obj-y	:= head.o als.o ebcdic.o sclp_early_core.o mem.o
-targets	:= bzImage setup.a $(obj-y)
+targets	:= bzImage startup.a $(obj-y)
 subdir-	:= compressed
 
 OBJECTS := $(addprefix $(obj)/,$(obj-y))
-- 
cgit v1.2.3


From 7e0363b469f5d2ad00234497aad65c7b46db42c0 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:21:36 +0200
Subject: s390/decompressor: avoid packing *.o.chkbss files into startup.a

startup.a build rule packs a list of prerequisites into archive. That
didn't take into account extra prerequisites added by chkbss, so that
zero length *.o.chkbss files were also packed into the archive.

To avoid that filter only real object from prerequisites list.

Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/boot/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/boot/Makefile b/arch/s390/boot/Makefile
index e15baa7b8e0b..9e6668ee93de 100644
--- a/arch/s390/boot/Makefile
+++ b/arch/s390/boot/Makefile
@@ -40,7 +40,7 @@ $(obj)/compressed/vmlinux: $(obj)/startup.a FORCE
 	$(Q)$(MAKE) $(build)=$(obj)/compressed $@
 
 quiet_cmd_ar = AR      $@
-      cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter-out FORCE, $^)
+      cmd_ar = rm -f $@; $(AR) rcsTP$(KBUILD_ARFLAGS) $@ $(filter $(OBJECTS), $^)
 
 $(obj)/startup.a: $(OBJECTS) FORCE
 	$(call if_changed,ar)
-- 
cgit v1.2.3


From 251987a8025da049f42001bdb21250f79644ede3 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 1 Jul 2018 11:32:51 +0200
Subject: s390/build: add *.o.chkbss files to targets list

Adding *.o.chkbss files to targets list makes sure that the kbuild is
aware of them and removes them during make clean.

Also remove *.o.chkbss file before an actual check, to avoid having
stale *.o.chkbss file left even if the check is failed.

Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/scripts/Makefile.chkbss | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/s390/scripts/Makefile.chkbss b/arch/s390/scripts/Makefile.chkbss
index fb0a11bd520c..9bba2c14e0ca 100644
--- a/arch/s390/scripts/Makefile.chkbss
+++ b/arch/s390/scripts/Makefile.chkbss
@@ -2,6 +2,7 @@
 
 quiet_cmd_chkbss = CHKBSS  $<
 define cmd_chkbss
+	rm -f $@; \
 	if ! $(OBJDUMP) -j .bss -w -h $< | awk 'END { if ($$3) exit 1 }'; then \
 		echo "error: $< .bss section is not empty" >&2; exit 1; \
 	fi; \
@@ -10,10 +11,13 @@ endef
 
 chkbss-target ?= $(obj)/built-in.a
 ifneq (,$(findstring /,$(chkbss)))
-$(chkbss-target): $(patsubst %, %.chkbss, $(chkbss))
+chkbss-files := $(patsubst %, %.chkbss, $(chkbss))
 else
-$(chkbss-target): $(patsubst %, $(obj)/%.chkbss, $(chkbss))
+chkbss-files := $(patsubst %, $(obj)/%.chkbss, $(chkbss))
 endif
 
+$(chkbss-target): $(chkbss-files)
+targets += $(notdir $(chkbss-files))
+
 %.o.chkbss: %.o
 	$(call cmd,chkbss)
-- 
cgit v1.2.3


From ee6d777d3e93670af801a7288ee6281626f4ac2d Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 28 Jun 2018 19:22:21 +0200
Subject: s390/decompressor: support extra debug flags

Since decompressor cflags and aflags are made from scratch add extra
debug flags when CONFIG_DEBUG_INFO is enabled.

Also adds support for CONFIG_DEBUG_INFO_DWARF4 option.

Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Makefile | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/s390/Makefile b/arch/s390/Makefile
index d25fbc170164..eee6703093c3 100644
--- a/arch/s390/Makefile
+++ b/arch/s390/Makefile
@@ -16,12 +16,16 @@ KBUILD_AFLAGS_MODULE += -fPIC
 KBUILD_CFLAGS_MODULE += -fPIC
 KBUILD_AFLAGS	+= -m64
 KBUILD_CFLAGS	+= -m64
+aflags_dwarf	:= -Wa,-gdwarf-2
 KBUILD_AFLAGS_DECOMPRESSOR := -m64 -D__ASSEMBLY__
+KBUILD_AFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),$(aflags_dwarf))
 KBUILD_CFLAGS_DECOMPRESSOR := -m64 -O2
 KBUILD_CFLAGS_DECOMPRESSOR += -DDISABLE_BRANCH_PROFILING -D__NO_FORTIFY
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-delete-null-pointer-checks -msoft-float
 KBUILD_CFLAGS_DECOMPRESSOR += -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS_DECOMPRESSOR += $(call cc-option,-ffreestanding)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO),-g)
+KBUILD_CFLAGS_DECOMPRESSOR += $(if $(CONFIG_DEBUG_INFO_DWARF4), $(call cc-option, -gdwarf-4,))
 UTS_MACHINE	:= s390x
 STACK_SIZE	:= 16384
 CHECKFLAGS	+= -D__s390__ -D__s390x__
-- 
cgit v1.2.3


From 88763a5cf80ca59a7c3bea32681ce8f697d9995f Mon Sep 17 00:00:00 2001
From: Daniel Lezcano <daniel.lezcano@linaro.org>
Date: Tue, 26 Jun 2018 12:53:29 +0200
Subject: powercap / idle_inject: Add an idle injection framework

Initially, the cpu_cooling device for ARM was changed by adding a new
policy inserting idle cycles. The intel_powerclamp driver does a
similar action.

Instead of implementing idle injections privately in the cpu_cooling
device, move the idle injection code in a dedicated framework and give
the opportunity to other frameworks to make use of it.

The framework relies on the smpboot kthreads which handles via its
main loop the common code for hotplugging and [un]parking.

This code was previously tested with the cpu cooling device and went
through several iterations. It results now in split code and API
exported in the header file. It was tested with the cpu cooling device
with success.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Viresh Kumar <viresh.kumar@linaro.org>
[ rjw: Rewrite of all comments ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/powercap/Kconfig       |  10 ++
 drivers/powercap/Makefile      |   1 +
 drivers/powercap/idle_inject.c | 356 +++++++++++++++++++++++++++++++++++++++++
 include/linux/idle_inject.h    |  29 ++++
 4 files changed, 396 insertions(+)
 create mode 100644 drivers/powercap/idle_inject.c
 create mode 100644 include/linux/idle_inject.h

diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
index 85727ef6ce8e..6ac27e5908f5 100644
--- a/drivers/powercap/Kconfig
+++ b/drivers/powercap/Kconfig
@@ -29,4 +29,14 @@ config INTEL_RAPL
 	  controller, CPU core (Power Plance 0), graphics uncore (Power Plane
 	  1), etc.
 
+config IDLE_INJECT
+	bool "Idle injection framework"
+	depends on CPU_IDLE
+	default n
+	help
+	  This enables support for the idle injection framework. It
+	  provides a way to force idle periods on a set of specified
+	  CPUs for power capping. Idle period can be injected
+	  synchronously on a set of specified CPUs or alternatively
+	  on a per CPU basis.
 endif
diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile
index 0a21ef31372b..1b328854b36e 100644
--- a/drivers/powercap/Makefile
+++ b/drivers/powercap/Makefile
@@ -1,2 +1,3 @@
 obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
 obj-$(CONFIG_INTEL_RAPL) += intel_rapl.o
+obj-$(CONFIG_IDLE_INJECT) += idle_inject.o
diff --git a/drivers/powercap/idle_inject.c b/drivers/powercap/idle_inject.c
new file mode 100644
index 000000000000..24ff2a068978
--- /dev/null
+++ b/drivers/powercap/idle_inject.c
@@ -0,0 +1,356 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ * The idle injection framework provides a way to force CPUs to enter idle
+ * states for a specified fraction of time over a specified period.
+ *
+ * It relies on the smpboot kthreads feature providing common code for CPU
+ * hotplug and thread [un]parking.
+ *
+ * All of the kthreads used for idle injection are created at init time.
+ *
+ * Next, the users of the the idle injection framework provide a cpumask via
+ * its register function. The kthreads will be synchronized with respect to
+ * this cpumask.
+ *
+ * The idle + run duration is specified via separate helpers and that allows
+ * idle injection to be started.
+ *
+ * The idle injection kthreads will call play_idle() with the idle duration
+ * specified as per the above.
+ *
+ * After all of them have been woken up, a timer is set to start the next idle
+ * injection cycle.
+ *
+ * The timer interrupt handler will wake up the idle injection kthreads for
+ * all of the CPUs in the cpumask provided by the user.
+ *
+ * Idle injection is stopped synchronously and no leftover idle injection
+ * kthread activity after its completion is guaranteed.
+ *
+ * It is up to the user of this framework to provide a lock for higher-level
+ * synchronization to prevent race conditions like starting idle injection
+ * while unregistering from the framework.
+ */
+#define pr_fmt(fmt) "ii_dev: " fmt
+
+#include <linux/cpu.h>
+#include <linux/hrtimer.h>
+#include <linux/kthread.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/smpboot.h>
+
+#include <uapi/linux/sched/types.h>
+
+/**
+ * struct idle_inject_thread - task on/off switch structure
+ * @tsk: task injecting the idle cycles
+ * @should_run: whether or not to run the task (for the smpboot kthread API)
+ */
+struct idle_inject_thread {
+	struct task_struct *tsk;
+	int should_run;
+};
+
+/**
+ * struct idle_inject_device - idle injection data
+ * @timer: idle injection period timer
+ * @idle_duration_ms: duration of CPU idle time to inject
+ * @run_duration_ms: duration of CPU run time to allow
+ * @cpumask: mask of CPUs affected by idle injection
+ */
+struct idle_inject_device {
+	struct hrtimer timer;
+	unsigned int idle_duration_ms;
+	unsigned int run_duration_ms;
+	unsigned long int cpumask[0];
+};
+
+static DEFINE_PER_CPU(struct idle_inject_thread, idle_inject_thread);
+static DEFINE_PER_CPU(struct idle_inject_device *, idle_inject_device);
+
+/**
+ * idle_inject_wakeup - Wake up idle injection threads
+ * @ii_dev: target idle injection device
+ *
+ * Every idle injection task associated with the given idle injection device
+ * and running on an online CPU will be woken up.
+ */
+static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	for_each_cpu_and(cpu, to_cpumask(ii_dev->cpumask), cpu_online_mask) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 1;
+		wake_up_process(iit->tsk);
+	}
+}
+
+/**
+ * idle_inject_timer_fn - idle injection timer function
+ * @timer: idle injection hrtimer
+ *
+ * This function is called when the idle injection timer expires.  It wakes up
+ * idle injection tasks associated with the timer and they, in turn, invoke
+ * play_idle() to inject a specified amount of CPU idle time.
+ *
+ * Return: HRTIMER_RESTART.
+ */
+static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
+{
+	unsigned int duration_ms;
+	struct idle_inject_device *ii_dev =
+		container_of(timer, struct idle_inject_device, timer);
+
+	duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+
+	return HRTIMER_RESTART;
+}
+
+/**
+ * idle_inject_fn - idle injection work function
+ * @cpu: the CPU owning the task
+ *
+ * This function calls play_idle() to inject a specified amount of CPU idle
+ * time.
+ */
+static void idle_inject_fn(unsigned int cpu)
+{
+	struct idle_inject_device *ii_dev;
+	struct idle_inject_thread *iit;
+
+	ii_dev = per_cpu(idle_inject_device, cpu);
+	iit = per_cpu_ptr(&idle_inject_thread, cpu);
+
+	/*
+	 * Let the smpboot main loop know that the task should not run again.
+	 */
+	iit->should_run = 0;
+
+	play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+}
+
+/**
+ * idle_inject_set_duration - idle and run duration update helper
+ * @run_duration_ms: CPU run time to allow in milliseconds
+ * @idle_duration_ms: CPU idle time to inject in milliseconds
+ */
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+			      unsigned int run_duration_ms,
+			      unsigned int idle_duration_ms)
+{
+	if (run_duration_ms && idle_duration_ms) {
+		WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
+		WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+	}
+}
+
+/**
+ * idle_inject_get_duration - idle and run duration retrieval helper
+ * @run_duration_ms: memory location to store the current CPU run time
+ * @idle_duration_ms: memory location to store the current CPU idle time
+ */
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+			      unsigned int *run_duration_ms,
+			      unsigned int *idle_duration_ms)
+{
+	*run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	*idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+}
+
+/**
+ * idle_inject_start - start idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function starts idle injection by first waking up all of the idle
+ * injection kthreads associated with @ii_dev to let them inject CPU idle time
+ * sets up a timer to start the next idle injection period.
+ *
+ * Return: -EINVAL if the CPU idle or CPU run time is not set or 0 on success.
+ */
+int idle_inject_start(struct idle_inject_device *ii_dev)
+{
+	unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+
+	if (!idle_duration_ms || !run_duration_ms)
+		return -EINVAL;
+
+	pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	idle_inject_wakeup(ii_dev);
+
+	hrtimer_start(&ii_dev->timer,
+		      ms_to_ktime(idle_duration_ms + run_duration_ms),
+		      HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+/**
+ * idle_inject_stop - stops idle injections
+ * @ii_dev: idle injection control device structure
+ *
+ * The function stops idle injection and waits for the threads to finish work.
+ * If CPU idle time is being injected when this function runs, then it will
+ * wait until the end of the cycle.
+ *
+ * When it returns, there is no more idle injection kthread activity.  The
+ * kthreads are scheduled out and the periodic timer is off.
+ */
+void idle_inject_stop(struct idle_inject_device *ii_dev)
+{
+	struct idle_inject_thread *iit;
+	unsigned int cpu;
+
+	pr_debug("Stopping idle injection on CPUs '%*pbl'\n",
+		 cpumask_pr_args(to_cpumask(ii_dev->cpumask)));
+
+	hrtimer_cancel(&ii_dev->timer);
+
+	/*
+	 * Stopping idle injection requires all of the idle injection kthreads
+	 * associated with the given cpumask to be parked and stay that way, so
+	 * prevent CPUs from going online at this point.  Any CPUs going online
+	 * after the loop below will be covered by clearing the should_run flag
+	 * that will cause the smpboot main loop to schedule them out.
+	 */
+	cpu_hotplug_disable();
+
+	/*
+	 * Iterate over all (online + offline) CPUs here in case one of them
+	 * goes offline with the should_run flag set so as to prevent its idle
+	 * injection kthread from running when the CPU goes online again after
+	 * the ii_dev has been freed.
+	 */
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+		iit = per_cpu_ptr(&idle_inject_thread, cpu);
+		iit->should_run = 0;
+
+		wait_task_inactive(iit->tsk, 0);
+	}
+
+	cpu_hotplug_enable();
+}
+
+/**
+ * idle_inject_setup - prepare the current task for idle injection
+ * @cpu: not used
+ *
+ * Called once, this function is in charge of setting the current task's
+ * scheduler parameters to make it an RT task.
+ */
+static void idle_inject_setup(unsigned int cpu)
+{
+	struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 };
+
+	sched_setscheduler(current, SCHED_FIFO, &param);
+}
+
+/**
+ * idle_inject_should_run - function helper for the smpboot API
+ * @cpu: CPU the kthread is running on
+ *
+ * Return: whether or not the thread can run.
+ */
+static int idle_inject_should_run(unsigned int cpu)
+{
+	struct idle_inject_thread *iit =
+		per_cpu_ptr(&idle_inject_thread, cpu);
+
+	return iit->should_run;
+}
+
+/**
+ * idle_inject_register - initialize idle injection on a set of CPUs
+ * @cpumask: CPUs to be affected by idle injection
+ *
+ * This function creates an idle injection control device structure for the
+ * given set of CPUs and initializes the timer associated with it.  It does not
+ * start any injection cycles.
+ *
+ * Return: NULL if memory allocation fails, idle injection control device
+ * pointer on success.
+ */
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask)
+{
+	struct idle_inject_device *ii_dev;
+	int cpu, cpu_rb;
+
+	ii_dev = kzalloc(sizeof(*ii_dev) + cpumask_size(), GFP_KERNEL);
+	if (!ii_dev)
+		return NULL;
+
+	cpumask_copy(to_cpumask(ii_dev->cpumask), cpumask);
+	hrtimer_init(&ii_dev->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	ii_dev->timer.function = idle_inject_timer_fn;
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask)) {
+
+		if (per_cpu(idle_inject_device, cpu)) {
+			pr_err("cpu%d is already registered\n", cpu);
+			goto out_rollback;
+		}
+
+		per_cpu(idle_inject_device, cpu) = ii_dev;
+	}
+
+	return ii_dev;
+
+out_rollback:
+	for_each_cpu(cpu_rb, to_cpumask(ii_dev->cpumask)) {
+		if (cpu == cpu_rb)
+			break;
+		per_cpu(idle_inject_device, cpu_rb) = NULL;
+	}
+
+	kfree(ii_dev);
+
+	return NULL;
+}
+
+/**
+ * idle_inject_unregister - unregister idle injection control device
+ * @ii_dev: idle injection control device to unregister
+ *
+ * The function stops idle injection for the given control device,
+ * unregisters its kthreads and frees memory allocated when that device was
+ * created.
+ */
+void idle_inject_unregister(struct idle_inject_device *ii_dev)
+{
+	unsigned int cpu;
+
+	idle_inject_stop(ii_dev);
+
+	for_each_cpu(cpu, to_cpumask(ii_dev->cpumask))
+		per_cpu(idle_inject_device, cpu) = NULL;
+
+	kfree(ii_dev);
+}
+
+static struct smp_hotplug_thread idle_inject_threads = {
+	.store = &idle_inject_thread.tsk,
+	.setup = idle_inject_setup,
+	.thread_fn = idle_inject_fn,
+	.thread_comm = "idle_inject/%u",
+	.thread_should_run = idle_inject_should_run,
+};
+
+static int __init idle_inject_init(void)
+{
+	return smpboot_register_percpu_thread(&idle_inject_threads);
+}
+early_initcall(idle_inject_init);
diff --git a/include/linux/idle_inject.h b/include/linux/idle_inject.h
new file mode 100644
index 000000000000..bdc0293fb6cb
--- /dev/null
+++ b/include/linux/idle_inject.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Linaro Ltd
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@linaro.org>
+ *
+ */
+#ifndef __IDLE_INJECT_H__
+#define __IDLE_INJECT_H__
+
+/* private idle injection device structure */
+struct idle_inject_device;
+
+struct idle_inject_device *idle_inject_register(struct cpumask *cpumask);
+
+void idle_inject_unregister(struct idle_inject_device *ii_dev);
+
+int idle_inject_start(struct idle_inject_device *ii_dev);
+
+void idle_inject_stop(struct idle_inject_device *ii_dev);
+
+void idle_inject_set_duration(struct idle_inject_device *ii_dev,
+				 unsigned int run_duration_ms,
+				 unsigned int idle_duration_ms);
+
+void idle_inject_get_duration(struct idle_inject_device *ii_dev,
+				 unsigned int *run_duration_ms,
+				 unsigned int *idle_duration_ms);
+#endif /* __IDLE_INJECT_H__ */
-- 
cgit v1.2.3


From 7c058c7c74b3dbeb7d157c273959f87faf710350 Mon Sep 17 00:00:00 2001
From: Ravi Chandra Sadineni <ravisadineni@chromium.org>
Date: Wed, 27 Jun 2018 10:55:02 -0700
Subject: ACPI / button: increment wakeup count only when notified

Because acpi_lid_initialize_state() is called on every system
resume and it triggers acpi_lid_notify_state() which invokes
acpi_pm_wakeup_event() for the lid device, the lid's wakeup count is
incremented even if the lid was not the source of the event that woke up
the system. That behavior confuses user space deamons using
wakeup_count to identify the potential system wakeup source. To avoid
the confusion, only trigger acpi_pm_wakeup_event() in the
acpi_button_notify() path and don't do that in the
acpi_lid_initialize_state() path.

Signed-off-by: Ravi Chandra Sadineni <ravisadineni@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/button.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 2345a5ee2dbb..40ed3ec9fc94 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -235,9 +235,6 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 		button->last_time = ktime_get();
 	}
 
-	if (state)
-		acpi_pm_wakeup_event(&device->dev);
-
 	ret = blocking_notifier_call_chain(&acpi_lid_notifier, state, device);
 	if (ret == NOTIFY_DONE)
 		ret = blocking_notifier_call_chain(&acpi_lid_notifier, state,
@@ -366,7 +363,8 @@ int acpi_lid_open(void)
 }
 EXPORT_SYMBOL(acpi_lid_open);
 
-static int acpi_lid_update_state(struct acpi_device *device)
+static int acpi_lid_update_state(struct acpi_device *device,
+				 bool signal_wakeup)
 {
 	int state;
 
@@ -374,6 +372,9 @@ static int acpi_lid_update_state(struct acpi_device *device)
 	if (state < 0)
 		return state;
 
+	if (state && signal_wakeup)
+		acpi_pm_wakeup_event(&device->dev);
+
 	return acpi_lid_notify_state(device, state);
 }
 
@@ -384,7 +385,7 @@ static void acpi_lid_initialize_state(struct acpi_device *device)
 		(void)acpi_lid_notify_state(device, 1);
 		break;
 	case ACPI_BUTTON_LID_INIT_METHOD:
-		(void)acpi_lid_update_state(device);
+		(void)acpi_lid_update_state(device, false);
 		break;
 	case ACPI_BUTTON_LID_INIT_IGNORE:
 	default:
@@ -409,7 +410,7 @@ static void acpi_button_notify(struct acpi_device *device, u32 event)
 			users = button->input->users;
 			mutex_unlock(&button->input->mutex);
 			if (users)
-				acpi_lid_update_state(device);
+				acpi_lid_update_state(device, true);
 		} else {
 			int keycode;
 
-- 
cgit v1.2.3


From c02462d8a3e96d99967fb26fca7375d449328ce6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 30 Jun 2018 21:39:24 +0100
Subject: netdevsim: fix sa_idx out of bounds check

Currently if sa_idx is equal to NSIM_IPSEC_MAX_SA_COUNT then
an out-of-bounds read on ipsec->sa will occur. Fix the
incorrect bounds check by using >= rather than >.

Detected by CoverityScan, CID#1470226 ("Out-of-bounds-read")

Fixes: 7699353da875 ("netdevsim: add ipsec offload testing")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/ipsec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/ipsec.c b/drivers/net/netdevsim/ipsec.c
index ceff544510b9..2dcf6cc269d0 100644
--- a/drivers/net/netdevsim/ipsec.c
+++ b/drivers/net/netdevsim/ipsec.c
@@ -249,7 +249,7 @@ bool nsim_ipsec_tx(struct netdevsim *ns, struct sk_buff *skb)
 	}
 
 	sa_idx = xs->xso.offload_handle & ~NSIM_IPSEC_VALID;
-	if (unlikely(sa_idx > NSIM_IPSEC_MAX_SA_COUNT)) {
+	if (unlikely(sa_idx >= NSIM_IPSEC_MAX_SA_COUNT)) {
 		netdev_err(ns->netdev, "bad sa_idx=%d max=%d\n",
 			   sa_idx, NSIM_IPSEC_MAX_SA_COUNT);
 		return false;
-- 
cgit v1.2.3


From 1201a5a25cf0f7d8019d106a81c64f3a7397d17c Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 29 Jun 2018 11:45:36 -0700
Subject: perf/arm-cci: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], this
removes the VLA in favor of a maximum size and adds a sanity check
at registration time. The sizes are all explicitly enumerated already,
so this just collects them into macros.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/perf/arm-cci.c | 38 ++++++++++++++++++++++++++------------
 1 file changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 0d09d8e669cd..1bfeb160c5b1 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -53,6 +53,16 @@ enum {
 	CCI_IF_MAX,
 };
 
+#define NUM_HW_CNTRS_CII_4XX	4
+#define NUM_HW_CNTRS_CII_5XX	8
+#define NUM_HW_CNTRS_MAX	NUM_HW_CNTRS_CII_5XX
+
+#define FIXED_HW_CNTRS_CII_4XX	1
+#define FIXED_HW_CNTRS_CII_5XX	0
+#define FIXED_HW_CNTRS_MAX	FIXED_HW_CNTRS_CII_4XX
+
+#define HW_CNTRS_MAX		(NUM_HW_CNTRS_MAX + FIXED_HW_CNTRS_MAX)
+
 struct event_range {
 	u32 min;
 	u32 max;
@@ -633,8 +643,7 @@ static void cci_pmu_sync_counters(struct cci_pmu *cci_pmu)
 {
 	int i;
 	struct cci_pmu_hw_events *cci_hw = &cci_pmu->hw_events;
-
-	DECLARE_BITMAP(mask, cci_pmu->num_cntrs);
+	DECLARE_BITMAP(mask, HW_CNTRS_MAX);
 
 	bitmap_zero(mask, cci_pmu->num_cntrs);
 	for_each_set_bit(i, cci_pmu->hw_events.used_mask, cci_pmu->num_cntrs) {
@@ -940,7 +949,7 @@ static void pmu_write_counters(struct cci_pmu *cci_pmu, unsigned long *mask)
 static void cci5xx_pmu_write_counters(struct cci_pmu *cci_pmu, unsigned long *mask)
 {
 	int i;
-	DECLARE_BITMAP(saved_mask, cci_pmu->num_cntrs);
+	DECLARE_BITMAP(saved_mask, HW_CNTRS_MAX);
 
 	bitmap_zero(saved_mask, cci_pmu->num_cntrs);
 	pmu_save_counters(cci_pmu, saved_mask);
@@ -1245,7 +1254,7 @@ static int validate_group(struct perf_event *event)
 {
 	struct perf_event *sibling, *leader = event->group_leader;
 	struct cci_pmu *cci_pmu = to_cci_pmu(event->pmu);
-	unsigned long mask[BITS_TO_LONGS(cci_pmu->num_cntrs)];
+	unsigned long mask[BITS_TO_LONGS(HW_CNTRS_MAX)];
 	struct cci_pmu_hw_events fake_pmu = {
 		/*
 		 * Initialise the fake PMU. We only need to populate the
@@ -1403,6 +1412,11 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 	char *name = model->name;
 	u32 num_cntrs;
 
+	if (WARN_ON(model->num_hw_cntrs > NUM_HW_CNTRS_MAX))
+		return -EINVAL;
+	if (WARN_ON(model->fixed_hw_cntrs > FIXED_HW_CNTRS_MAX))
+		return -EINVAL;
+
 	pmu_event_attr_group.attrs = model->event_attrs;
 	pmu_format_attr_group.attrs = model->format_attrs;
 
@@ -1455,8 +1469,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI400_PMU
 	[CCI400_R0] = {
 		.name = "CCI_400",
-		.fixed_hw_cntrs = 1,	/* Cycle counter */
-		.num_hw_cntrs = 4,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_4XX, /* Cycle counter */
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_4XX,
 		.cntr_size = SZ_4K,
 		.format_attrs = cci400_pmu_format_attrs,
 		.event_attrs = cci400_r0_pmu_event_attrs,
@@ -1475,8 +1489,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 	},
 	[CCI400_R1] = {
 		.name = "CCI_400_r1",
-		.fixed_hw_cntrs = 1,	/* Cycle counter */
-		.num_hw_cntrs = 4,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_4XX, /* Cycle counter */
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_4XX,
 		.cntr_size = SZ_4K,
 		.format_attrs = cci400_pmu_format_attrs,
 		.event_attrs = cci400_r1_pmu_event_attrs,
@@ -1497,8 +1511,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 #ifdef CONFIG_ARM_CCI5xx_PMU
 	[CCI500_R0] = {
 		.name = "CCI_500",
-		.fixed_hw_cntrs = 0,
-		.num_hw_cntrs = 8,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_5XX,
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_5XX,
 		.cntr_size = SZ_64K,
 		.format_attrs = cci5xx_pmu_format_attrs,
 		.event_attrs = cci5xx_pmu_event_attrs,
@@ -1521,8 +1535,8 @@ static __maybe_unused struct cci_pmu_model cci_pmu_models[] = {
 	},
 	[CCI550_R0] = {
 		.name = "CCI_550",
-		.fixed_hw_cntrs = 0,
-		.num_hw_cntrs = 8,
+		.fixed_hw_cntrs = FIXED_HW_CNTRS_CII_5XX,
+		.num_hw_cntrs = NUM_HW_CNTRS_CII_5XX,
 		.cntr_size = SZ_64K,
 		.format_attrs = cci5xx_pmu_format_attrs,
 		.event_attrs = cci5xx_pmu_event_attrs,
-- 
cgit v1.2.3


From 1823342a1f2b47a4e6f5667f67cd28ab6bc4d6cd Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 1 Jul 2018 13:56:54 -0700
Subject: configfs: replace strncpy with memcpy

gcc 8.1.0 complains:

fs/configfs/symlink.c:67:3: warning:
	'strncpy' output truncated before terminating nul copying as many
	bytes from a string as its length
fs/configfs/symlink.c: In function 'configfs_get_link':
fs/configfs/symlink.c:63:13: note: length computed here

Using strncpy() is indeed less than perfect since the length of data to
be copied has already been determined with strlen(). Replace strncpy()
with memcpy() to address the warning and optimize the code a little.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/configfs/symlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index 78ffc2699993..a5c54af861f7 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -64,7 +64,7 @@ static void fill_item_path(struct config_item * item, char * buffer, int length)
 
 		/* back up enough to print this bus id with '/' */
 		length -= cur;
-		strncpy(buffer + length,config_item_name(p),cur);
+		memcpy(buffer + length, config_item_name(p), cur);
 		*(buffer + --length) = '/';
 	}
 }
-- 
cgit v1.2.3


From 335c997dce5c448ee06b3fd4dfe49fc7279f73ce Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 1 Jul 2018 00:25:19 +0200
Subject: r8169: remove old PHY reset hack

This hack (affecting the non-PCIe models only) was introduced in 2004
to deal with link negotiation failures in 1GBit mode. Based on a
comment in the r8169 vendor driver I assume the issue affects RTL8169sb
in combination with particular 1GBit switch models.

Resetting the PHY every 10s and hoping that one fine day we will make
it to establish the link seems to be very hacky to me. I'd say:
If 1GBit doesn't work reliably in a users environment then the user
should remove 1GBit from the advertised modes, e.g. by using
ethtool -s <if> advertise <10/100 modes>

If the issue affects one chip version only and that with most link
partners, then we could also think of removing 1GBit from the
advertised modes for this chip version in the driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 57 +-----------------------------------
 1 file changed, 1 insertion(+), 56 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index d943a00dbccf..f80ac894ef92 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -80,7 +80,6 @@ static const int multicast_filter_limit = 32;
 #define R8169_RX_RING_BYTES	(NUM_RX_DESC * sizeof(struct RxDesc))
 
 #define RTL8169_TX_TIMEOUT	(6*HZ)
-#define RTL8169_PHY_TIMEOUT	(10*HZ)
 
 /* write/read MMIO register */
 #define RTL_W8(tp, reg, val8)	writeb((val8), tp->mmio_addr + (reg))
@@ -703,7 +702,6 @@ enum rtl_flag {
 	RTL_FLAG_TASK_ENABLED,
 	RTL_FLAG_TASK_SLOW_PENDING,
 	RTL_FLAG_TASK_RESET_PENDING,
-	RTL_FLAG_TASK_PHY_PENDING,
 	RTL_FLAG_MAX
 };
 
@@ -731,7 +729,6 @@ struct rtl8169_private {
 	dma_addr_t RxPhyAddr;
 	void *Rx_databuff[NUM_RX_DESC];	/* Rx data buffers */
 	struct ring_info tx_skb[NUM_TX_DESC];	/* Tx data buffers */
-	struct timer_list timer;
 	u16 cp_cmd;
 
 	u16 event_slow;
@@ -1788,20 +1785,7 @@ out:
 static int rtl8169_set_speed(struct net_device *dev,
 			     u8 autoneg, u16 speed, u8 duplex, u32 advertising)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int ret;
-
-	ret = rtl8169_set_speed_xmii(dev, autoneg, speed, duplex, advertising);
-	if (ret < 0)
-		goto out;
-
-	if (netif_running(dev) && (autoneg == AUTONEG_ENABLE) &&
-	    (advertising & ADVERTISED_1000baseT_Full) &&
-	    !pci_is_pcie(tp->pci_dev)) {
-		mod_timer(&tp->timer, jiffies + RTL8169_PHY_TIMEOUT);
-	}
-out:
-	return ret;
+	return rtl8169_set_speed_xmii(dev, autoneg, speed, duplex, advertising);
 }
 
 static netdev_features_t rtl8169_fix_features(struct net_device *dev,
@@ -1888,8 +1872,6 @@ static int rtl8169_set_link_ksettings(struct net_device *dev,
 	    cmd->link_modes.advertising))
 		return -EINVAL;
 
-	del_timer_sync(&tp->timer);
-
 	rtl_lock_work(tp);
 	rc = rtl8169_set_speed(dev, cmd->base.autoneg, cmd->base.speed,
 			       cmd->base.duplex, advertising);
@@ -4293,44 +4275,12 @@ static void rtl_hw_phy_config(struct net_device *dev)
 	}
 }
 
-static void rtl_phy_work(struct rtl8169_private *tp)
-{
-	struct timer_list *timer = &tp->timer;
-	unsigned long timeout = RTL8169_PHY_TIMEOUT;
-
-	if (rtl8169_xmii_reset_pending(tp)) {
-		/*
-		 * A busy loop could burn quite a few cycles on nowadays CPU.
-		 * Let's delay the execution of the timer for a few ticks.
-		 */
-		timeout = HZ/10;
-		goto out_mod_timer;
-	}
-
-	if (rtl8169_xmii_link_ok(tp))
-		return;
-
-	netif_dbg(tp, link, tp->dev, "PHY reset until link up\n");
-
-	rtl8169_xmii_reset_enable(tp);
-
-out_mod_timer:
-	mod_timer(timer, jiffies + timeout);
-}
-
 static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
 {
 	if (!test_and_set_bit(flag, tp->wk.flags))
 		schedule_work(&tp->wk.work);
 }
 
-static void rtl8169_phy_timer(struct timer_list *t)
-{
-	struct rtl8169_private *tp = from_timer(tp, t, timer);
-
-	rtl_schedule_task(tp, RTL_FLAG_TASK_PHY_PENDING);
-}
-
 DECLARE_RTL_COND(rtl_phy_reset_cond)
 {
 	return rtl8169_xmii_reset_pending(tp);
@@ -6909,7 +6859,6 @@ static void rtl_task(struct work_struct *work)
 		/* XXX - keep rtl_slow_event_work() as first element. */
 		{ RTL_FLAG_TASK_SLOW_PENDING,	rtl_slow_event_work },
 		{ RTL_FLAG_TASK_RESET_PENDING,	rtl_reset_work },
-		{ RTL_FLAG_TASK_PHY_PENDING,	rtl_phy_work }
 	};
 	struct rtl8169_private *tp =
 		container_of(work, struct rtl8169_private, wk.work);
@@ -6982,8 +6931,6 @@ static void rtl8169_down(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	del_timer_sync(&tp->timer);
-
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
 
@@ -7694,8 +7641,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->event_slow = cfg->event_slow;
 	tp->coalesce_info = cfg->coalesce_info;
 
-	timer_setup(&tp->timer, rtl8169_phy_timer, 0);
-
 	tp->rtl_fw = RTL_FIRMWARE_UNKNOWN;
 
 	tp->counters = dmam_alloc_coherent (&pdev->dev, sizeof(*tp->counters),
-- 
cgit v1.2.3


From d6f19938eb031ee2158272757db33258153ae59c Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sun, 1 Jul 2018 23:31:30 +0800
Subject: net: expose sk wmem in sock_exceed_buf_limit tracepoint

Currently trace_sock_exceed_buf_limit() only show rmem info,
but wmem limit may also be hit.
So expose wmem info in this tracepoint as well.

Regarding memcg, I think it is better to introduce a new tracepoint(if
that is needed), i.e. trace_memcg_limit_hit other than show memcg info in
trace_sock_exceed_buf_limit.

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/sock.h | 30 +++++++++++++++++++++++++-----
 net/core/sock.c             |  6 ++++--
 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/include/trace/events/sock.h b/include/trace/events/sock.h
index 3176a3931107..a0c4b8a30966 100644
--- a/include/trace/events/sock.h
+++ b/include/trace/events/sock.h
@@ -35,6 +35,10 @@
 		EM(TCP_CLOSING)			\
 		EMe(TCP_NEW_SYN_RECV)
 
+#define skmem_kind_names			\
+		EM(SK_MEM_SEND)			\
+		EMe(SK_MEM_RECV)
+
 /* enums need to be exported to user space */
 #undef EM
 #undef EMe
@@ -44,6 +48,7 @@
 family_names
 inet_protocol_names
 tcp_state_names
+skmem_kind_names
 
 #undef EM
 #undef EMe
@@ -59,6 +64,9 @@ tcp_state_names
 #define show_tcp_state_name(val)        \
 	__print_symbolic(val, tcp_state_names)
 
+#define show_skmem_kind_names(val)	\
+	__print_symbolic(val, skmem_kind_names)
+
 TRACE_EVENT(sock_rcvqueue_full,
 
 	TP_PROTO(struct sock *sk, struct sk_buff *skb),
@@ -83,9 +91,9 @@ TRACE_EVENT(sock_rcvqueue_full,
 
 TRACE_EVENT(sock_exceed_buf_limit,
 
-	TP_PROTO(struct sock *sk, struct proto *prot, long allocated),
+	TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind),
 
-	TP_ARGS(sk, prot, allocated),
+	TP_ARGS(sk, prot, allocated, kind),
 
 	TP_STRUCT__entry(
 		__array(char, name, 32)
@@ -93,6 +101,10 @@ TRACE_EVENT(sock_exceed_buf_limit,
 		__field(long, allocated)
 		__field(int, sysctl_rmem)
 		__field(int, rmem_alloc)
+		__field(int, sysctl_wmem)
+		__field(int, wmem_alloc)
+		__field(int, wmem_queued)
+		__field(int, kind)
 	),
 
 	TP_fast_assign(
@@ -101,17 +113,25 @@ TRACE_EVENT(sock_exceed_buf_limit,
 		__entry->allocated = allocated;
 		__entry->sysctl_rmem = sk_get_rmem0(sk, prot);
 		__entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc);
+		__entry->sysctl_wmem = sk_get_wmem0(sk, prot);
+		__entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc);
+		__entry->wmem_queued = sk->sk_wmem_queued;
+		__entry->kind = kind;
 	),
 
-	TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld "
-		"sysctl_rmem=%d rmem_alloc=%d",
+	TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s",
 		__entry->name,
 		__entry->sysctl_mem[0],
 		__entry->sysctl_mem[1],
 		__entry->sysctl_mem[2],
 		__entry->allocated,
 		__entry->sysctl_rmem,
-		__entry->rmem_alloc)
+		__entry->rmem_alloc,
+		__entry->sysctl_wmem,
+		__entry->wmem_alloc,
+		__entry->wmem_queued,
+		show_skmem_kind_names(__entry->kind)
+	)
 );
 
 TRACE_EVENT(inet_sock_set_state,
diff --git a/net/core/sock.c b/net/core/sock.c
index dac6d785186b..8b69ac96a850 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2401,9 +2401,10 @@ int __sk_mem_raise_allocated(struct sock *sk, int size, int amt, int kind)
 {
 	struct proto *prot = sk->sk_prot;
 	long allocated = sk_memory_allocated_add(sk, amt);
+	bool charged = true;
 
 	if (mem_cgroup_sockets_enabled && sk->sk_memcg &&
-	    !mem_cgroup_charge_skmem(sk->sk_memcg, amt))
+	    !(charged = mem_cgroup_charge_skmem(sk->sk_memcg, amt)))
 		goto suppress_allocation;
 
 	/* Under limit. */
@@ -2461,7 +2462,8 @@ suppress_allocation:
 			return 1;
 	}
 
-	trace_sock_exceed_buf_limit(sk, prot, allocated);
+	if (kind == SK_MEM_SEND || (kind == SK_MEM_RECV && charged))
+		trace_sock_exceed_buf_limit(sk, prot, allocated, kind);
 
 	sk_memory_allocated_sub(sk, amt);
 
-- 
cgit v1.2.3


From 100ec4bf09679583d45316fcf13611f66a8d0f88 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 1 Jul 2018 19:14:58 +0200
Subject: net: phy: realtek: add missing entry for RTL8211 to mdio_device_id
 table

When adding support for RTL8211 I forgot to update the mdio_device_id
table.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Fixes: d241d4aac93f ("net: phy: realtek: add support for RTL8211")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 9757b16231f9..7b516e5d4f7f 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -260,6 +260,7 @@ module_phy_driver(realtek_drvs);
 
 static struct mdio_device_id __maybe_unused realtek_tbl[] = {
 	{ 0x001cc816, 0x001fffff },
+	{ 0x001cc910, 0x001fffff },
 	{ 0x001cc912, 0x001fffff },
 	{ 0x001cc914, 0x001fffff },
 	{ 0x001cc915, 0x001fffff },
-- 
cgit v1.2.3


From 414372f633e378b3ef7443ce0f0370a6a4e5808b Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Sun, 1 Jul 2018 13:57:38 -0700
Subject: TTY: isdn: Replace strncpy with memcpy

gcc 8.1.0 complains:

drivers/isdn/i4l/isdn_tty.c: In function 'isdn_tty_suspend.isra.1':
drivers/isdn/i4l/isdn_tty.c:790:3: warning:
	'strncpy' output truncated before terminating nul copying
	as many bytes from a string as its length
drivers/isdn/i4l/isdn_tty.c:778:6: note: length computed here

drivers/isdn/i4l/isdn_tty.c: In function 'isdn_tty_resume':
drivers/isdn/i4l/isdn_tty.c:880:3: warning:
	'strncpy' output truncated before terminating nul copying
	as many bytes from a string as its length
drivers/isdn/i4l/isdn_tty.c:817:6: note: length computed here

Using strncpy() is indeed less than perfect since the length of data to
be copied has already been determined with strlen(). Replace strncpy()
with memcpy() to address the warning and optimize the code a little.

Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/i4l/isdn_tty.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/isdn/i4l/isdn_tty.c b/drivers/isdn/i4l/isdn_tty.c
index 960f26348bb5..b730037a0e2d 100644
--- a/drivers/isdn/i4l/isdn_tty.c
+++ b/drivers/isdn/i4l/isdn_tty.c
@@ -787,7 +787,7 @@ isdn_tty_suspend(char *id, modem_info *info, atemu *m)
 		cmd.parm.cmsg.para[3] = 4; /* 16 bit 0x0004 Suspend */
 		cmd.parm.cmsg.para[4] = 0;
 		cmd.parm.cmsg.para[5] = l;
-		strncpy(&cmd.parm.cmsg.para[6], id, l);
+		memcpy(&cmd.parm.cmsg.para[6], id, l);
 		cmd.command = CAPI_PUT_MESSAGE;
 		cmd.driver = info->isdn_driver;
 		cmd.arg = info->isdn_channel;
@@ -877,7 +877,7 @@ isdn_tty_resume(char *id, modem_info *info, atemu *m)
 		cmd.parm.cmsg.para[3] = 5; /* 16 bit 0x0005 Resume */
 		cmd.parm.cmsg.para[4] = 0;
 		cmd.parm.cmsg.para[5] = l;
-		strncpy(&cmd.parm.cmsg.para[6], id, l);
+		memcpy(&cmd.parm.cmsg.para[6], id, l);
 		cmd.command = CAPI_PUT_MESSAGE;
 		info->dialing = 1;
 //		strcpy(dev->num[i], n);
-- 
cgit v1.2.3


From 9868c0b2eb18470a91d6f0f0df318738a50554e2 Mon Sep 17 00:00:00 2001
From: Roman Mashak <mrv@mojatatu.com>
Date: Mon, 2 Jul 2018 00:02:02 -0400
Subject: net sched actions: add extack messages in pedit action

Signed-off-by: Roman Mashak <mrv@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index ab151346d3d4..55bc96b610e8 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -144,8 +144,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	int ret = 0, err;
 	int ksize;
 
-	if (!nla)
+	if (!nla) {
+		NL_SET_ERR_MSG_MOD(extack, "Pedit requires attributes to be passed");
 		return -EINVAL;
+	}
 
 	err = nla_parse_nested(tb, TCA_PEDIT_MAX, nla, pedit_policy, NULL);
 	if (err < 0)
@@ -154,21 +156,27 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	pattr = tb[TCA_PEDIT_PARMS];
 	if (!pattr)
 		pattr = tb[TCA_PEDIT_PARMS_EX];
-	if (!pattr)
+	if (!pattr) {
+		NL_SET_ERR_MSG_MOD(extack, "Missing required TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute");
 		return -EINVAL;
+	}
 
 	parm = nla_data(pattr);
 	ksize = parm->nkeys * sizeof(struct tc_pedit_key);
-	if (nla_len(pattr) < sizeof(*parm) + ksize)
+	if (nla_len(pattr) < sizeof(*parm) + ksize) {
+		NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid");
 		return -EINVAL;
+	}
 
 	keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
 	if (IS_ERR(keys_ex))
 		return PTR_ERR(keys_ex);
 
 	if (!tcf_idr_check(tn, parm->index, a, bind)) {
-		if (!parm->nkeys)
+		if (!parm->nkeys) {
+			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
 			return -EINVAL;
+		}
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_pedit_ops, bind, false);
 		if (ret)
-- 
cgit v1.2.3


From cf87915cb9f873742135e786d12d42a35eea7538 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 2 Jul 2018 08:08:13 +0200
Subject: net: phy: realtek: add support for RTL8211C

RTL8211C has an issue when operating in Gigabit slave mode, therefore
genphy driver can't be used. See also this U-boot change.
https://lists.denx.de/pipermail/u-boot/2016-March/249712.html

Add a PHY driver for this chip with the quirk to force Gigabit master
mode. As a note: This will make it impossible to connect two network
ports directly which both are driven by a RTl8211C.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 7b516e5d4f7f..f8f127831a92 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -150,6 +150,15 @@ static int rtl8211_config_aneg(struct phy_device *phydev)
 	return 0;
 }
 
+static int rtl8211c_config_init(struct phy_device *phydev)
+{
+	/* RTL8211C has an issue when operating in Gigabit slave mode */
+	phy_set_bits(phydev, MII_CTRL1000,
+		     CTL1000_ENABLE_MASTER | CTL1000_AS_MASTER);
+
+	return genphy_config_init(phydev);
+}
+
 static int rtl8211f_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -220,6 +229,14 @@ static struct phy_driver realtek_drvs[] = {
 		.write_mmd	= &genphy_write_mmd_unsupported,
 		.suspend	= rtl8211b_suspend,
 		.resume		= rtl8211b_resume,
+	}, {
+		.phy_id		= 0x001cc913,
+		.name		= "RTL8211C Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.config_init	= rtl8211c_config_init,
+		.read_mmd	= &genphy_read_mmd_unsupported,
+		.write_mmd	= &genphy_write_mmd_unsupported,
 	}, {
 		.phy_id		= 0x001cc914,
 		.name		= "RTL8211DN Gigabit Ethernet",
-- 
cgit v1.2.3


From 50d4feb5e60e64a8c3053414483e7457be2f111d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 2 Jul 2018 08:37:21 +0100
Subject: atm: zatm: remove redundant pointer zatm_dev

Pointer zatm_dev is being assigned but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: variable 'zatm_dev' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/atm/zatm.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/atm/zatm.c b/drivers/atm/zatm.c
index a8d2eb0ceb8d..1e41cfbb3708 100644
--- a/drivers/atm/zatm.c
+++ b/drivers/atm/zatm.c
@@ -1385,14 +1385,12 @@ static void zatm_close(struct atm_vcc *vcc)
 
 static int zatm_open(struct atm_vcc *vcc)
 {
-	struct zatm_dev *zatm_dev;
 	struct zatm_vcc *zatm_vcc;
 	short vpi = vcc->vpi;
 	int vci = vcc->vci;
 	int error;
 
 	DPRINTK(">zatm_open\n");
-	zatm_dev = ZATM_DEV(vcc->dev);
 	if (!test_bit(ATM_VF_PARTIAL,&vcc->flags))
 		vcc->dev_data = NULL;
 	if (vci != ATM_VPI_UNSPEC && vpi != ATM_VCI_UNSPEC)
-- 
cgit v1.2.3


From 5411b984216824902344726f0f9c357cdb60fd89 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:18 +0800
Subject: net: hns3: remove unused hclge_ring_to_dma_dir

hclge_ring_to_dma_dir is unused anywhere.
This patch removes it.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 383ecf036e31..6a9576b1024b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -18,8 +18,7 @@
 #include "hclge_main.h"
 
 #define hclge_is_csq(ring) ((ring)->flag & HCLGE_TYPE_CSQ)
-#define hclge_ring_to_dma_dir(ring) (hclge_is_csq(ring) ? \
-	DMA_TO_DEVICE : DMA_FROM_DEVICE)
+
 #define cmq_ring_to_dev(ring)   (&(ring)->dev->pdev->dev)
 
 static int hclge_ring_space(struct hclge_cmq_ring *ring)
-- 
cgit v1.2.3


From eb55323c564dc793a21fe71eec782ffb5b4776da Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:19 +0800
Subject: net: hns3: remove useless code in hclge_cmd_send

There are some useless type cast, print in hclge_cmd_send.
This patch removes them.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 6a9576b1024b..969966c8d9ef 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -269,19 +269,17 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 			/* Get the result of hardware write back */
 			desc_to_use = &hw->cmq.csq.desc[ntc];
 			desc[handle] = *desc_to_use;
-			pr_debug("Get cmd desc:\n");
 
 			if (likely(!hclge_is_special_opcode(opcode)))
 				desc_ret = le16_to_cpu(desc[handle].retval);
 			else
 				desc_ret = le16_to_cpu(desc[0].retval);
 
-			if ((enum hclge_cmd_return_status)desc_ret ==
-			    HCLGE_CMD_EXEC_SUCCESS)
+			if (desc_ret == HCLGE_CMD_EXEC_SUCCESS)
 				retval = 0;
 			else
 				retval = -EIO;
-			hw->cmq.last_status = (enum hclge_cmd_status)desc_ret;
+			hw->cmq.last_status = desc_ret;
 			ntc++;
 			handle++;
 			if (ntc == hw->cmq.csq.desc_num)
-- 
cgit v1.2.3


From 043fa454f43dcd70e9821f392968970ce9dab7f8 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:20 +0800
Subject: net: hns3: remove some redundant assignments

Remove some redundant assignments.
desc->flag = cpu_to_le16(HCLGE_CMD_FLAG_NO_INTR | HCLGE_CMD_FLAG_IN)
has set bit HCLGE_CMD_FLAG_WR to zero, so does others.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c  | 2 --
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 8 --------
 2 files changed, 10 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 969966c8d9ef..054a9136270a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -110,8 +110,6 @@ void hclge_cmd_setup_basic_desc(struct hclge_desc *desc,
 
 	if (is_read)
 		desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_WR);
-	else
-		desc->flag &= cpu_to_le16(~HCLGE_CMD_FLAG_WR);
 }
 
 static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 14a6991375d9..b7f6960e7761 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2733,7 +2733,6 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_RST_TRIGGER, false);
-	hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_MAC_B, 0);
 	hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
 	req->fun_reset_vfid = func_id;
 
@@ -4264,16 +4263,9 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 
 	memset(&req, 0, sizeof(req));
 	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 0);
-	hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 
-	hnae_set_bit(egress_port, HCLGE_MAC_EPORT_SW_EN_B, 0);
-	hnae_set_bit(egress_port, HCLGE_MAC_EPORT_TYPE_B, 0);
 	hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
 		       HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
-	hnae_set_field(egress_port, HCLGE_MAC_EPORT_PFID_M,
-		       HCLGE_MAC_EPORT_PFID_S, 0);
 
 	req.egress_port = cpu_to_le16(egress_port);
 
-- 
cgit v1.2.3


From 1c1270da47a290cd3c880b933bb06073c0365e2c Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:21 +0800
Subject: net: hns3: simplify hclge_cmd_csq_clean

csq is used as a ring buffer, the value of the desc will be replaced
in next use. This patch removes the unnecessary memset, and just
updates the next_to_clean.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c  | 21 +++++----------------
 1 file changed, 5 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 054a9136270a..0839e8410e6d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -151,31 +151,20 @@ static int hclge_cmd_csq_clean(struct hclge_hw *hw)
 {
 	struct hclge_dev *hdev = container_of(hw, struct hclge_dev, hw);
 	struct hclge_cmq_ring *csq = &hw->cmq.csq;
-	u16 ntc = csq->next_to_clean;
-	struct hclge_desc *desc;
-	int clean = 0;
 	u32 head;
+	int clean;
 
-	desc = &csq->desc[ntc];
 	head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG);
 	rmb(); /* Make sure head is ready before touch any data */
 
 	if (!is_valid_csq_clean_head(csq, head)) {
-		dev_warn(&hdev->pdev->dev, "wrong head (%d, %d-%d)\n", head,
-			   csq->next_to_use, csq->next_to_clean);
+		dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head,
+			 csq->next_to_use, csq->next_to_clean);
 		return 0;
 	}
 
-	while (head != ntc) {
-		memset(desc, 0, sizeof(*desc));
-		ntc++;
-		if (ntc == csq->desc_num)
-			ntc = 0;
-		desc = &csq->desc[ntc];
-		clean++;
-	}
-	csq->next_to_clean = ntc;
-
+	clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num;
+	csq->next_to_clean = head;
 	return clean;
 }
 
-- 
cgit v1.2.3


From f6762f3852bbb1c43343916199713eb6c4f964f1 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:22 +0800
Subject: net: hns3: remove a redundant hclge_cmd_csq_done

Set complete in the first hclge_cmd_csq_done of hclge_cmd_send,
and check if complete later, unnecessary to do hclge_cmd_csq_done
again.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 0839e8410e6d..db80485b65ea 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -242,15 +242,18 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 	 */
 	if (HCLGE_SEND_SYNC(le16_to_cpu(desc->flag))) {
 		do {
-			if (hclge_cmd_csq_done(hw))
+			if (hclge_cmd_csq_done(hw)) {
+				complete = true;
 				break;
+			}
 			udelay(1);
 			timeout++;
 		} while (timeout < hw->cmq.tx_timeout);
 	}
 
-	if (hclge_cmd_csq_done(hw)) {
-		complete = true;
+	if (!complete) {
+		retval = -EAGAIN;
+	} else {
 		handle = 0;
 		while (handle < num) {
 			/* Get the result of hardware write back */
@@ -274,9 +277,6 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 		}
 	}
 
-	if (!complete)
-		retval = -EAGAIN;
-
 	/* Clean the command send queue */
 	handle = hclge_cmd_csq_clean(hw);
 	if (handle != num) {
-- 
cgit v1.2.3


From a9fc79b681025ce47df8a04b8aba9df4999bf167 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:23 +0800
Subject: net: hns3: remove some unused members of some structures

Some members in struct hns3_enet_tqp_vector, struct hnae3_client
and struct hnae3_ae_algo are unused.
This patch removes them.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.h               | 2 --
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h           | 1 -
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c   | 1 -
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 1 -
 4 files changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 8acb1d116a02..422c56bdd15e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -167,7 +167,6 @@ struct hnae3_client_ops {
 #define HNAE3_CLIENT_NAME_LENGTH 16
 struct hnae3_client {
 	char name[HNAE3_CLIENT_NAME_LENGTH];
-	u16 version;
 	unsigned long state;
 	enum hnae3_client_type type;
 	const struct hnae3_client_ops *ops;
@@ -436,7 +435,6 @@ struct hnae3_dcb_ops {
 struct hnae3_ae_algo {
 	const struct hnae3_ae_ops *ops;
 	struct list_head node;
-	char name[HNAE3_CLASS_NAME_SIZE];
 	const struct pci_device_id *pdev_id_table;
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 3b083d5ae9ce..8d6096c290b1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -499,7 +499,6 @@ struct hns3_enet_tqp_vector {
 
 	u16 num_tqps;	/* total number of tqps in TQP vector */
 
-	cpumask_t affinity_mask;
 	char name[HNAE3_INT_NAME_LEN];
 
 	/* when 0 should adjust interrupt coalesce parameter */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b7f6960e7761..2a0cd70255aa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -6287,7 +6287,6 @@ static const struct hnae3_ae_ops hclge_ops = {
 
 static struct hnae3_ae_algo ae_algo = {
 	.ops = &hclge_ops,
-	.name = HCLGE_NAME,
 	.pdev_id_table = ae_algo_pci_tbl,
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 1eb61c126988..1638193a63d3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1959,7 +1959,6 @@ static const struct hnae3_ae_ops hclgevf_ops = {
 
 static struct hnae3_ae_algo ae_algovf = {
 	.ops = &hclgevf_ops,
-	.name = HCLGEVF_NAME,
 	.pdev_id_table = ae_algovf_pci_tbl,
 };
 
-- 
cgit v1.2.3


From 7a7056e3dfa6636989b821d890448ae49375bd22 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:24 +0800
Subject: net: hns3: give default option while dependency HNS3 set

Give default option for HNS3_HCLGE and HNS3_ENET will be helpful,
while dependency HNS3 is set. Meanwhile, use "if HNS3" section
instead of all the "depends on HNS3".

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/Kconfig | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/Kconfig b/drivers/net/ethernet/hisilicon/Kconfig
index fb1a7251f45d..25152715396b 100644
--- a/drivers/net/ethernet/hisilicon/Kconfig
+++ b/drivers/net/ethernet/hisilicon/Kconfig
@@ -85,10 +85,12 @@ config HNS3
 	  drivers(like ODP)to register with HNAE devices and their associated
 	  operations.
 
+if HNS3
+
 config HNS3_HCLGE
 	tristate "Hisilicon HNS3 HCLGE Acceleration Engine & Compatibility Layer Support"
+	default m
 	depends on PCI_MSI
-	depends on HNS3
 	---help---
 	  This selects the HNS3_HCLGE network acceleration engine & its hardware
 	  compatibility layer. The engine would be used in Hisilicon hip08 family of
@@ -97,16 +99,15 @@ config HNS3_HCLGE
 config HNS3_DCB
 	bool "Hisilicon HNS3 Data Center Bridge Support"
 	default n
-	depends on HNS3 && HNS3_HCLGE && DCB
+	depends on HNS3_HCLGE && DCB
 	---help---
 	  Say Y here if you want to use Data Center Bridging (DCB) in the HNS3 driver.
 
 	  If unsure, say N.
 
 config HNS3_HCLGEVF
-    tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support"
-    depends on PCI_MSI
-    depends on HNS3
+	tristate "Hisilicon HNS3VF Acceleration Engine & Compatibility Layer Support"
+	depends on PCI_MSI
 	depends on HNS3_HCLGE
     ---help---
 	  This selects the HNS3 VF drivers network acceleration engine & its hardware
@@ -115,11 +116,13 @@ config HNS3_HCLGEVF
 
 config HNS3_ENET
 	tristate "Hisilicon HNS3 Ethernet Device Support"
+	default m
 	depends on 64BIT && PCI
-	depends on HNS3
 	---help---
 	  This selects the Ethernet Driver for Hisilicon Network Subsystem 3 for hip08
 	  family of SoCs. This module depends upon HNAE3 driver to access the HNAE3
 	  devices and their associated operations.
 
+endif #HNS3
+
 endif # NET_VENDOR_HISILICON
-- 
cgit v1.2.3


From 024cc792f9309f1342a2fd7bd5840e112b333687 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 2 Jul 2018 15:50:25 +0800
Subject: net: hns3: use dma_zalloc_coherent instead of kzalloc/dma_map_single

Reference to Documentation/DMA-API-HOWTO.txt,
Streaming DMA mappings which are usually mapped for one DMA transfer,
Network card DMA ring descriptors should use Consistent DMA mappings.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 26 +++++++++-------------
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 25 ++++++++-------------
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c   | 26 ++++++++--------------
 3 files changed, 28 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index beca36491025..8fce36329bb0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1780,33 +1780,27 @@ static void hns3_free_buffers(struct hns3_enet_ring *ring)
 /* free desc along with its attached buffer */
 static void hns3_free_desc(struct hns3_enet_ring *ring)
 {
+	int size = ring->desc_num * sizeof(ring->desc[0]);
+
 	hns3_free_buffers(ring);
 
-	dma_unmap_single(ring_to_dev(ring), ring->desc_dma_addr,
-			 ring->desc_num * sizeof(ring->desc[0]),
-			 DMA_BIDIRECTIONAL);
-	ring->desc_dma_addr = 0;
-	kfree(ring->desc);
-	ring->desc = NULL;
+	if (ring->desc) {
+		dma_free_coherent(ring_to_dev(ring), size,
+				  ring->desc, ring->desc_dma_addr);
+		ring->desc = NULL;
+	}
 }
 
 static int hns3_alloc_desc(struct hns3_enet_ring *ring)
 {
 	int size = ring->desc_num * sizeof(ring->desc[0]);
 
-	ring->desc = kzalloc(size, GFP_KERNEL);
+	ring->desc = dma_zalloc_coherent(ring_to_dev(ring), size,
+					 &ring->desc_dma_addr,
+					 GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
-	ring->desc_dma_addr = dma_map_single(ring_to_dev(ring), ring->desc,
-					     size, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(ring_to_dev(ring), ring->desc_dma_addr)) {
-		ring->desc_dma_addr = 0;
-		kfree(ring->desc);
-		ring->desc = NULL;
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index db80485b65ea..82cf12a07dc0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -45,31 +45,24 @@ static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring)
 {
 	int size  = ring->desc_num * sizeof(struct hclge_desc);
 
-	ring->desc = kzalloc(size, GFP_KERNEL);
+	ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
+					 size, &ring->desc_dma_addr,
+					 GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
-	ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc,
-					     size, DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) {
-		ring->desc_dma_addr = 0;
-		kfree(ring->desc);
-		ring->desc = NULL;
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
 static void hclge_free_cmd_desc(struct hclge_cmq_ring *ring)
 {
-	dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr,
-			 ring->desc_num * sizeof(ring->desc[0]),
-			 DMA_BIDIRECTIONAL);
+	int size  = ring->desc_num * sizeof(struct hclge_desc);
 
-	ring->desc_dma_addr = 0;
-	kfree(ring->desc);
-	ring->desc = NULL;
+	if (ring->desc) {
+		dma_free_coherent(cmq_ring_to_dev(ring), size,
+				  ring->desc, ring->desc_dma_addr);
+		ring->desc = NULL;
+	}
 }
 
 static int hclge_alloc_cmd_queue(struct hclge_dev *hdev, int ring_type)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
index 1bbfe131b596..fb471fe2c494 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c
@@ -76,32 +76,24 @@ static int hclgevf_alloc_cmd_desc(struct hclgevf_cmq_ring *ring)
 {
 	int size = ring->desc_num * sizeof(struct hclgevf_desc);
 
-	ring->desc = kzalloc(size, GFP_KERNEL);
+	ring->desc = dma_zalloc_coherent(cmq_ring_to_dev(ring),
+					 size, &ring->desc_dma_addr,
+					 GFP_KERNEL);
 	if (!ring->desc)
 		return -ENOMEM;
 
-	ring->desc_dma_addr = dma_map_single(cmq_ring_to_dev(ring), ring->desc,
-					     size, DMA_BIDIRECTIONAL);
-
-	if (dma_mapping_error(cmq_ring_to_dev(ring), ring->desc_dma_addr)) {
-		ring->desc_dma_addr = 0;
-		kfree(ring->desc);
-		ring->desc = NULL;
-		return -ENOMEM;
-	}
-
 	return 0;
 }
 
 static void hclgevf_free_cmd_desc(struct hclgevf_cmq_ring *ring)
 {
-	dma_unmap_single(cmq_ring_to_dev(ring), ring->desc_dma_addr,
-			 ring->desc_num * sizeof(ring->desc[0]),
-			 hclgevf_ring_to_dma_dir(ring));
+	int size  = ring->desc_num * sizeof(struct hclgevf_desc);
 
-	ring->desc_dma_addr = 0;
-	kfree(ring->desc);
-	ring->desc = NULL;
+	if (ring->desc) {
+		dma_free_coherent(cmq_ring_to_dev(ring), size,
+				  ring->desc, ring->desc_dma_addr);
+		ring->desc = NULL;
+	}
 }
 
 static int hclgevf_init_cmd_queue(struct hclgevf_dev *hdev,
-- 
cgit v1.2.3


From e4e87715aa850ab312fd3a3f3452d7390d46ba02 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Mon, 2 Jul 2018 15:50:26 +0800
Subject: net: hns3: modify hnae_ to hnae3_

For consistency, prefix hnae_ should be modified to hnae3_.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.c        |  28 +-
 drivers/net/ethernet/hisilicon/hns3/hnae3.h        |  16 +-
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    | 218 ++++++++-------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h    |   8 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 306 ++++++++++-----------
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c |  24 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c    |  38 +--
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c  |   8 +-
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h  |   7 +-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  |  24 +-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c   |   2 +-
 11 files changed, 343 insertions(+), 336 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 1a02620b281a..0762ad18fdcc 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -40,13 +40,13 @@ static void hnae3_set_client_init_flag(struct hnae3_client *client,
 {
 	switch (client->type) {
 	case HNAE3_CLIENT_KNIC:
-		hnae_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
+		hnae3_set_bit(ae_dev->flag, HNAE3_KNIC_CLIENT_INITED_B, inited);
 		break;
 	case HNAE3_CLIENT_UNIC:
-		hnae_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited);
+		hnae3_set_bit(ae_dev->flag, HNAE3_UNIC_CLIENT_INITED_B, inited);
 		break;
 	case HNAE3_CLIENT_ROCE:
-		hnae_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited);
+		hnae3_set_bit(ae_dev->flag, HNAE3_ROCE_CLIENT_INITED_B, inited);
 		break;
 	default:
 		break;
@@ -60,16 +60,16 @@ static int hnae3_get_client_init_flag(struct hnae3_client *client,
 
 	switch (client->type) {
 	case HNAE3_CLIENT_KNIC:
-		inited = hnae_get_bit(ae_dev->flag,
+		inited = hnae3_get_bit(ae_dev->flag,
 				       HNAE3_KNIC_CLIENT_INITED_B);
 		break;
 	case HNAE3_CLIENT_UNIC:
-		inited = hnae_get_bit(ae_dev->flag,
+		inited = hnae3_get_bit(ae_dev->flag,
 				       HNAE3_UNIC_CLIENT_INITED_B);
 		break;
 	case HNAE3_CLIENT_ROCE:
-		inited = hnae_get_bit(ae_dev->flag,
-				      HNAE3_ROCE_CLIENT_INITED_B);
+		inited = hnae3_get_bit(ae_dev->flag,
+				       HNAE3_ROCE_CLIENT_INITED_B);
 		break;
 	default:
 		break;
@@ -85,7 +85,7 @@ static int hnae3_match_n_instantiate(struct hnae3_client *client,
 
 	/* check if this client matches the type of ae_dev */
 	if (!(hnae3_client_match(client->type, ae_dev->dev_type) &&
-	      hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
+	      hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))) {
 		return 0;
 	}
 
@@ -190,7 +190,7 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo)
 			continue;
 		}
 
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 
 		/* check the client list for the match with this ae_dev type and
 		 * initialize the figure out client instance
@@ -220,7 +220,7 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_dev */
 	list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) {
-		if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+		if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
 			continue;
 
 		id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
@@ -234,7 +234,7 @@ void hnae3_unregister_ae_algo(struct hnae3_ae_algo *ae_algo)
 			hnae3_match_n_instantiate(client, ae_dev, false);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
 	}
 
 	list_del(&ae_algo->node);
@@ -278,7 +278,7 @@ void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev)
 			goto out_err;
 		}
 
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 1);
 		break;
 	}
 
@@ -310,7 +310,7 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
 	mutex_lock(&hnae3_common_lock);
 	/* Check if there are matched ae_algo */
 	list_for_each_entry(ae_algo, &hnae3_ae_algo_list, node) {
-		if (!hnae_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
+		if (!hnae3_get_bit(ae_dev->flag, HNAE3_DEV_INITED_B))
 			continue;
 
 		id = pci_match_id(ae_algo->pdev_id_table, ae_dev->pdev);
@@ -321,7 +321,7 @@ void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev)
 			hnae3_match_n_instantiate(client, ae_dev, false);
 
 		ae_algo->ops->uninit_ae_dev(ae_dev);
-		hnae_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
+		hnae3_set_bit(ae_dev->flag, HNAE3_DEV_INITED_B, 0);
 	}
 
 	list_del(&ae_dev->node);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index 422c56bdd15e..da806fdfbbe6 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -62,10 +62,10 @@
 		BIT(HNAE3_DEV_SUPPORT_ROCE_B))
 
 #define hnae3_dev_roce_supported(hdev) \
-	hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
+	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)
 
 #define hnae3_dev_dcb_supported(hdev) \
-	hnae_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
+	hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B)
 
 #define ring_ptr_move_fw(ring, p) \
 	((ring)->p = ((ring)->p + 1) % (ring)->desc_num)
@@ -507,17 +507,17 @@ struct hnae3_handle {
 	u32 numa_node_mask;	/* for multi-chip support */
 };
 
-#define hnae_set_field(origin, mask, shift, val) \
+#define hnae3_set_field(origin, mask, shift, val) \
 	do { \
 		(origin) &= (~(mask)); \
 		(origin) |= ((val) << (shift)) & (mask); \
 	} while (0)
-#define hnae_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift))
+#define hnae3_get_field(origin, mask, shift) (((origin) & (mask)) >> (shift))
 
-#define hnae_set_bit(origin, shift, val) \
-	hnae_set_field((origin), (0x1 << (shift)), (shift), (val))
-#define hnae_get_bit(origin, shift) \
-	hnae_get_field((origin), (0x1 << (shift)), (shift))
+#define hnae3_set_bit(origin, shift, val) \
+	hnae3_set_field((origin), (0x1 << (shift)), (shift), (val))
+#define hnae3_get_bit(origin, shift) \
+	hnae3_get_field((origin), (0x1 << (shift)), (shift))
 
 void hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev);
 void hnae3_unregister_ae_dev(struct hnae3_ae_dev *ae_dev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 8fce36329bb0..7e34d5fff3ae 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -493,8 +493,8 @@ static int hns3_set_tso(struct sk_buff *skb, u32 *paylen,
 
 	/* find the txbd field values */
 	*paylen = skb->len - hdr_len;
-	hnae_set_bit(*type_cs_vlan_tso,
-		     HNS3_TXD_TSO_B, 1);
+	hnae3_set_bit(*type_cs_vlan_tso,
+		      HNS3_TXD_TSO_B, 1);
 
 	/* get MSS for TSO */
 	*mss = skb_shinfo(skb)->gso_size;
@@ -586,21 +586,21 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 	/* compute L2 header size for normal packet, defined in 2 Bytes */
 	l2_len = l3.hdr - skb->data;
-	hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-		       HNS3_TXD_L2LEN_S, l2_len >> 1);
+	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
+			HNS3_TXD_L2LEN_S, l2_len >> 1);
 
 	/* tunnel packet*/
 	if (skb->encapsulation) {
 		/* compute OL2 header size, defined in 2 Bytes */
 		ol2_len = l2_len;
-		hnae_set_field(*ol_type_vlan_len_msec,
-			       HNS3_TXD_L2LEN_M,
-			       HNS3_TXD_L2LEN_S, ol2_len >> 1);
+		hnae3_set_field(*ol_type_vlan_len_msec,
+				HNS3_TXD_L2LEN_M,
+				HNS3_TXD_L2LEN_S, ol2_len >> 1);
 
 		/* compute OL3 header size, defined in 4 Bytes */
 		ol3_len = l4.hdr - l3.hdr;
-		hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
-			       HNS3_TXD_L3LEN_S, ol3_len >> 2);
+		hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L3LEN_M,
+				HNS3_TXD_L3LEN_S, ol3_len >> 2);
 
 		/* MAC in UDP, MAC in GRE (0x6558)*/
 		if ((ol4_proto == IPPROTO_UDP) || (ol4_proto == IPPROTO_GRE)) {
@@ -609,16 +609,17 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 			/* compute OL4 header size, defined in 4 Bytes. */
 			ol4_len = l2_hdr - l4.hdr;
-			hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_L4LEN_M,
-				       HNS3_TXD_L4LEN_S, ol4_len >> 2);
+			hnae3_set_field(*ol_type_vlan_len_msec,
+					HNS3_TXD_L4LEN_M, HNS3_TXD_L4LEN_S,
+					ol4_len >> 2);
 
 			/* switch IP header ptr from outer to inner header */
 			l3.hdr = skb_inner_network_header(skb);
 
 			/* compute inner l2 header size, defined in 2 Bytes. */
 			l2_len = l3.hdr - l2_hdr;
-			hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
-				       HNS3_TXD_L2LEN_S, l2_len >> 1);
+			hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L2LEN_M,
+					HNS3_TXD_L2LEN_S, l2_len >> 1);
 		} else {
 			/* skb packet types not supported by hardware,
 			 * txbd len fild doesn't be filled.
@@ -634,22 +635,24 @@ static void hns3_set_l2l3l4_len(struct sk_buff *skb, u8 ol4_proto,
 
 	/* compute inner(/normal) L3 header size, defined in 4 Bytes */
 	l3_len = l4.hdr - l3.hdr;
-	hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
-		       HNS3_TXD_L3LEN_S, l3_len >> 2);
+	hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3LEN_M,
+			HNS3_TXD_L3LEN_S, l3_len >> 2);
 
 	/* compute inner(/normal) L4 header size, defined in 4 Bytes */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-			       HNS3_TXD_L4LEN_S, l4.tcp->doff);
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+				HNS3_TXD_L4LEN_S, l4.tcp->doff);
 		break;
 	case IPPROTO_SCTP:
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-			       HNS3_TXD_L4LEN_S, (sizeof(struct sctphdr) >> 2));
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+				HNS3_TXD_L4LEN_S,
+				(sizeof(struct sctphdr) >> 2));
 		break;
 	case IPPROTO_UDP:
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
-			       HNS3_TXD_L4LEN_S, (sizeof(struct udphdr) >> 2));
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L4LEN_M,
+				HNS3_TXD_L4LEN_S,
+				(sizeof(struct udphdr) >> 2));
 		break;
 	default:
 		/* skb packet types not supported by hardware,
@@ -703,32 +706,34 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 		/* define outer network header type.*/
 		if (skb->protocol == htons(ETH_P_IP)) {
 			if (skb_is_gso(skb))
-				hnae_set_field(*ol_type_vlan_len_msec,
-					       HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S,
-					       HNS3_OL3T_IPV4_CSUM);
+				hnae3_set_field(*ol_type_vlan_len_msec,
+						HNS3_TXD_OL3T_M,
+						HNS3_TXD_OL3T_S,
+						HNS3_OL3T_IPV4_CSUM);
 			else
-				hnae_set_field(*ol_type_vlan_len_msec,
-					       HNS3_TXD_OL3T_M, HNS3_TXD_OL3T_S,
-					       HNS3_OL3T_IPV4_NO_CSUM);
+				hnae3_set_field(*ol_type_vlan_len_msec,
+						HNS3_TXD_OL3T_M,
+						HNS3_TXD_OL3T_S,
+						HNS3_OL3T_IPV4_NO_CSUM);
 
 		} else if (skb->protocol == htons(ETH_P_IPV6)) {
-			hnae_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
-				       HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
+			hnae3_set_field(*ol_type_vlan_len_msec, HNS3_TXD_OL3T_M,
+					HNS3_TXD_OL3T_S, HNS3_OL3T_IPV6);
 		}
 
 		/* define tunnel type(OL4).*/
 		switch (l4_proto) {
 		case IPPROTO_UDP:
-			hnae_set_field(*ol_type_vlan_len_msec,
-				       HNS3_TXD_TUNTYPE_M,
-				       HNS3_TXD_TUNTYPE_S,
-				       HNS3_TUN_MAC_IN_UDP);
+			hnae3_set_field(*ol_type_vlan_len_msec,
+					HNS3_TXD_TUNTYPE_M,
+					HNS3_TXD_TUNTYPE_S,
+					HNS3_TUN_MAC_IN_UDP);
 			break;
 		case IPPROTO_GRE:
-			hnae_set_field(*ol_type_vlan_len_msec,
-				       HNS3_TXD_TUNTYPE_M,
-				       HNS3_TXD_TUNTYPE_S,
-				       HNS3_TUN_NVGRE);
+			hnae3_set_field(*ol_type_vlan_len_msec,
+					HNS3_TXD_TUNTYPE_M,
+					HNS3_TXD_TUNTYPE_S,
+					HNS3_TUN_NVGRE);
 			break;
 		default:
 			/* drop the skb tunnel packet if hardware don't support,
@@ -749,43 +754,43 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 	}
 
 	if (l3.v4->version == 4) {
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-			       HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
+				HNS3_TXD_L3T_S, HNS3_L3T_IPV4);
 
 		/* the stack computes the IP header already, the only time we
 		 * need the hardware to recompute it is in the case of TSO.
 		 */
 		if (skb_is_gso(skb))
-			hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
+			hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
 
-		hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
 	} else if (l3.v6->version == 6) {
-		hnae_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
-			       HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
-		hnae_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
+		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
+				HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
 	}
 
 	switch (l4_proto) {
 	case IPPROTO_TCP:
-		hnae_set_field(*type_cs_vlan_tso,
-			       HNS3_TXD_L4T_M,
-			       HNS3_TXD_L4T_S,
-			       HNS3_L4T_TCP);
+		hnae3_set_field(*type_cs_vlan_tso,
+				HNS3_TXD_L4T_M,
+				HNS3_TXD_L4T_S,
+				HNS3_L4T_TCP);
 		break;
 	case IPPROTO_UDP:
 		if (hns3_tunnel_csum_bug(skb))
 			break;
 
-		hnae_set_field(*type_cs_vlan_tso,
-			       HNS3_TXD_L4T_M,
-			       HNS3_TXD_L4T_S,
-			       HNS3_L4T_UDP);
+		hnae3_set_field(*type_cs_vlan_tso,
+				HNS3_TXD_L4T_M,
+				HNS3_TXD_L4T_S,
+				HNS3_L4T_UDP);
 		break;
 	case IPPROTO_SCTP:
-		hnae_set_field(*type_cs_vlan_tso,
-			       HNS3_TXD_L4T_M,
-			       HNS3_TXD_L4T_S,
-			       HNS3_L4T_SCTP);
+		hnae3_set_field(*type_cs_vlan_tso,
+				HNS3_TXD_L4T_M,
+				HNS3_TXD_L4T_S,
+				HNS3_L4T_SCTP);
 		break;
 	default:
 		/* drop the skb tunnel packet if hardware don't support,
@@ -807,11 +812,11 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end)
 {
 	/* Config bd buffer end */
-	hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
-		       HNS3_TXD_BDTYPE_S, 0);
-	hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
-	hnae_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
-	hnae_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
+	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_BDTYPE_M,
+			HNS3_TXD_BDTYPE_S, 0);
+	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_FE_B, !!frag_end);
+	hnae3_set_bit(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1);
+	hnae3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_SC_M, HNS3_TXD_SC_S, 0);
 }
 
 static int hns3_fill_desc_vtags(struct sk_buff *skb,
@@ -844,10 +849,10 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb,
 		 * and use inner_vtag in one tag case.
 		 */
 		if (skb->protocol == htons(ETH_P_8021Q)) {
-			hnae_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
+			hnae3_set_bit(*out_vlan_flag, HNS3_TXD_OVLAN_B, 1);
 			*out_vtag = vlan_tag;
 		} else {
-			hnae_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
+			hnae3_set_bit(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1);
 			*inner_vtag = vlan_tag;
 		}
 	} else if (skb->protocol == htons(ETH_P_8021Q)) {
@@ -1135,7 +1140,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev)
 
 	wmb(); /* Commit all data before submit */
 
-	hnae_queue_xmit(ring->tqp, buf_num);
+	hnae3_queue_xmit(ring->tqp, buf_num);
 
 	return NETDEV_TX_OK;
 
@@ -1703,7 +1708,7 @@ static void hns3_set_default_feature(struct net_device *netdev)
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 			     struct hns3_desc_cb *cb)
 {
-	unsigned int order = hnae_page_order(ring);
+	unsigned int order = hnae3_page_order(ring);
 	struct page *p;
 
 	p = dev_alloc_pages(order);
@@ -1714,7 +1719,7 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
 	cb->page_offset = 0;
 	cb->reuse_flag = 0;
 	cb->buf  = page_address(p);
-	cb->length = hnae_page_size(ring);
+	cb->length = hnae3_page_size(ring);
 	cb->type = DESC_TYPE_PAGE;
 
 	return 0;
@@ -1881,7 +1886,7 @@ static void hns3_nic_reclaim_one_desc(struct hns3_enet_ring *ring, int *bytes,
 
 	(*pkts) += (desc_cb->type == DESC_TYPE_SKB);
 	(*bytes) += desc_cb->length;
-	/* desc_cb will be cleaned, after hnae_free_buffer_detach*/
+	/* desc_cb will be cleaned, after hnae3_free_buffer_detach*/
 	hns3_free_buffer_detach(ring, ring->next_to_clean);
 
 	ring_ptr_move_fw(ring, next_to_clean);
@@ -2010,15 +2015,15 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i,
 	bool twobufs;
 
 	twobufs = ((PAGE_SIZE < 8192) &&
-		hnae_buf_size(ring) == HNS3_BUFFER_SIZE_2048);
+		hnae3_buf_size(ring) == HNS3_BUFFER_SIZE_2048);
 
 	desc = &ring->desc[ring->next_to_clean];
 	size = le16_to_cpu(desc->rx.size);
 
-	truesize = hnae_buf_size(ring);
+	truesize = hnae3_buf_size(ring);
 
 	if (!twobufs)
-		last_offset = hnae_page_size(ring) - hnae_buf_size(ring);
+		last_offset = hnae3_page_size(ring) - hnae3_buf_size(ring);
 
 	skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len,
 			size - pull_len, truesize);
@@ -2070,13 +2075,13 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		return;
 
 	/* check if hardware has done checksum */
-	if (!hnae_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
+	if (!hnae3_get_bit(bd_base_info, HNS3_RXD_L3L4P_B))
 		return;
 
-	if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L3E_B) ||
-		     hnae_get_bit(l234info, HNS3_RXD_L4E_B) ||
-		     hnae_get_bit(l234info, HNS3_RXD_OL3E_B) ||
-		     hnae_get_bit(l234info, HNS3_RXD_OL4E_B))) {
+	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L3E_B) ||
+		     hnae3_get_bit(l234info, HNS3_RXD_L4E_B) ||
+		     hnae3_get_bit(l234info, HNS3_RXD_OL3E_B) ||
+		     hnae3_get_bit(l234info, HNS3_RXD_OL4E_B))) {
 		netdev_err(netdev, "L3/L4 error pkt\n");
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.l3l4_csum_err++;
@@ -2085,12 +2090,13 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 		return;
 	}
 
-	l3_type = hnae_get_field(l234info, HNS3_RXD_L3ID_M,
-				 HNS3_RXD_L3ID_S);
-	l4_type = hnae_get_field(l234info, HNS3_RXD_L4ID_M,
-				 HNS3_RXD_L4ID_S);
+	l3_type = hnae3_get_field(l234info, HNS3_RXD_L3ID_M,
+				  HNS3_RXD_L3ID_S);
+	l4_type = hnae3_get_field(l234info, HNS3_RXD_L4ID_M,
+				  HNS3_RXD_L4ID_S);
 
-	ol4_type = hnae_get_field(l234info, HNS3_RXD_OL4ID_M, HNS3_RXD_OL4ID_S);
+	ol4_type = hnae3_get_field(l234info, HNS3_RXD_OL4ID_M,
+				   HNS3_RXD_OL4ID_S);
 	switch (ol4_type) {
 	case HNS3_OL4_TYPE_MAC_IN_UDP:
 	case HNS3_OL4_TYPE_NVGRE:
@@ -2129,8 +2135,8 @@ static u16 hns3_parse_vlan_tag(struct hns3_enet_ring *ring,
 #define HNS3_STRP_OUTER_VLAN	0x1
 #define HNS3_STRP_INNER_VLAN	0x2
 
-	switch (hnae_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
-			       HNS3_RXD_STRP_TAGP_S)) {
+	switch (hnae3_get_field(l234info, HNS3_RXD_STRP_TAGP_M,
+				HNS3_RXD_STRP_TAGP_S)) {
 	case HNS3_STRP_OUTER_VLAN:
 		vlan_tag = le16_to_cpu(desc->rx.ot_vlan_tag);
 		break;
@@ -2168,7 +2174,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
 
 	/* Check valid BD */
-	if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
+	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B)))
 		return -EFAULT;
 
 	va = (unsigned char *)desc_cb->buf + desc_cb->page_offset;
@@ -2223,7 +2229,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 		hns3_nic_reuse_page(skb, 0, ring, pull_len, desc_cb);
 		ring_ptr_move_fw(ring, next_to_clean);
 
-		while (!hnae_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
+		while (!hnae3_get_bit(bd_base_info, HNS3_RXD_FE_B)) {
 			desc = &ring->desc[ring->next_to_clean];
 			desc_cb = &ring->desc_cb[ring->next_to_clean];
 			bd_base_info = le32_to_cpu(desc->rx.bd_base_info);
@@ -2251,7 +2257,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 					       vlan_tag);
 	}
 
-	if (unlikely(!hnae_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
+	if (unlikely(!hnae3_get_bit(bd_base_info, HNS3_RXD_VLD_B))) {
 		netdev_err(netdev, "no valid bd,%016llx,%016llx\n",
 			   ((u64 *)desc)[0], ((u64 *)desc)[1]);
 		u64_stats_update_begin(&ring->syncp);
@@ -2263,7 +2269,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 	}
 
 	if (unlikely((!desc->rx.pkt_len) ||
-		     hnae_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
+		     hnae3_get_bit(l234info, HNS3_RXD_TRUNCAT_B))) {
 		netdev_err(netdev, "truncated pkt\n");
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.err_pkt_len++;
@@ -2273,7 +2279,7 @@ static int hns3_handle_rx_bd(struct hns3_enet_ring *ring,
 		return -EFAULT;
 	}
 
-	if (unlikely(hnae_get_bit(l234info, HNS3_RXD_L2E_B))) {
+	if (unlikely(hnae3_get_bit(l234info, HNS3_RXD_L2E_B))) {
 		netdev_err(netdev, "L2 error pkt\n");
 		u64_stats_update_begin(&ring->syncp);
 		ring->stats.l2_err++;
@@ -2526,10 +2532,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 	tx_ring = tqp_vector->tx_group.ring;
 	if (tx_ring) {
 		cur_chain->tqp_index = tx_ring->tqp->tqp_index;
-		hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
-			     HNAE3_RING_TYPE_TX);
-		hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
-			       HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX);
+		hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
+			      HNAE3_RING_TYPE_TX);
+		hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_TX);
 
 		cur_chain->next = NULL;
 
@@ -2543,12 +2549,12 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 
 			cur_chain->next = chain;
 			chain->tqp_index = tx_ring->tqp->tqp_index;
-			hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B,
-				     HNAE3_RING_TYPE_TX);
-			hnae_set_field(chain->int_gl_idx,
-				       HNAE3_RING_GL_IDX_M,
-				       HNAE3_RING_GL_IDX_S,
-				       HNAE3_RING_GL_TX);
+			hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B,
+				      HNAE3_RING_TYPE_TX);
+			hnae3_set_field(chain->int_gl_idx,
+					HNAE3_RING_GL_IDX_M,
+					HNAE3_RING_GL_IDX_S,
+					HNAE3_RING_GL_TX);
 
 			cur_chain = chain;
 		}
@@ -2558,10 +2564,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 	if (!tx_ring && rx_ring) {
 		cur_chain->next = NULL;
 		cur_chain->tqp_index = rx_ring->tqp->tqp_index;
-		hnae_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
-			     HNAE3_RING_TYPE_RX);
-		hnae_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
-			       HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
+		hnae3_set_bit(cur_chain->flag, HNAE3_RING_TYPE_B,
+			      HNAE3_RING_TYPE_RX);
+		hnae3_set_field(cur_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
 
 		rx_ring = rx_ring->next;
 	}
@@ -2573,10 +2579,10 @@ static int hns3_get_vector_ring_chain(struct hns3_enet_tqp_vector *tqp_vector,
 
 		cur_chain->next = chain;
 		chain->tqp_index = rx_ring->tqp->tqp_index;
-		hnae_set_bit(chain->flag, HNAE3_RING_TYPE_B,
-			     HNAE3_RING_TYPE_RX);
-		hnae_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
-			       HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
+		hnae3_set_bit(chain->flag, HNAE3_RING_TYPE_B,
+			      HNAE3_RING_TYPE_RX);
+		hnae3_set_field(chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S, HNAE3_RING_GL_RX);
 
 		cur_chain = chain;
 
@@ -2799,7 +2805,7 @@ static int hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 		ring->io_base = q->io_base;
 	}
 
-	hnae_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
+	hnae3_set_bit(ring->flag, HNAE3_RING_TYPE_B, ring_type);
 
 	ring->tqp = q;
 	ring->desc = NULL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 8d6096c290b1..bf9aa02be994 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -590,7 +590,7 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 #define hns3_write_dev(a, reg, value) \
 	hns3_write_reg((a)->io_base, (reg), (value))
 
-#define hnae_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
+#define hnae3_queue_xmit(tqp, buf_num) writel_relaxed(buf_num, \
 		(tqp)->io_base + HNS3_RING_TX_RING_TAIL_REG)
 
 #define ring_to_dev(ring) (&(ring)->tqp->handle->pdev->dev)
@@ -600,9 +600,9 @@ static inline void hns3_write_reg(void __iomem *base, u32 reg, u32 value)
 
 #define tx_ring_data(priv, idx) ((priv)->ring_data[idx])
 
-#define hnae_buf_size(_ring) ((_ring)->buf_size)
-#define hnae_page_order(_ring) (get_order(hnae_buf_size(_ring)))
-#define hnae_page_size(_ring) (PAGE_SIZE << hnae_page_order(_ring))
+#define hnae3_buf_size(_ring) ((_ring)->buf_size)
+#define hnae3_page_order(_ring) (get_order(hnae3_buf_size(_ring)))
+#define hnae3_page_size(_ring) (PAGE_SIZE << hnae3_page_order(_ring))
 
 /* iterator for handling rings in ring group */
 #define hns3_for_each_ring(pos, head) \
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 2a0cd70255aa..6fffc69a7138 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -939,8 +939,8 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 
 	if (hnae3_dev_roce_supported(hdev)) {
 		hdev->num_roce_msi =
-		hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
-			       HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
 
 		/* PF should have NIC vectors and Roce vectors,
 		 * NIC vectors are queued before Roce vectors.
@@ -948,8 +948,8 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		hdev->num_msi = hdev->num_roce_msi  + HCLGE_ROCE_VECTOR_OFFSET;
 	} else {
 		hdev->num_msi =
-		hnae_get_field(__le16_to_cpu(req->pf_intr_vector_number),
-			       HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
+		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
+				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
 	}
 
 	return 0;
@@ -1038,38 +1038,38 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	req = (struct hclge_cfg_param_cmd *)desc[0].data;
 
 	/* get the configuration */
-	cfg->vmdq_vport_num = hnae_get_field(__le32_to_cpu(req->param[0]),
-					     HCLGE_CFG_VMDQ_M,
-					     HCLGE_CFG_VMDQ_S);
-	cfg->tc_num = hnae_get_field(__le32_to_cpu(req->param[0]),
-				     HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S);
-	cfg->tqp_desc_num = hnae_get_field(__le32_to_cpu(req->param[0]),
-					   HCLGE_CFG_TQP_DESC_N_M,
-					   HCLGE_CFG_TQP_DESC_N_S);
-
-	cfg->phy_addr = hnae_get_field(__le32_to_cpu(req->param[1]),
-				       HCLGE_CFG_PHY_ADDR_M,
-				       HCLGE_CFG_PHY_ADDR_S);
-	cfg->media_type = hnae_get_field(__le32_to_cpu(req->param[1]),
-					 HCLGE_CFG_MEDIA_TP_M,
-					 HCLGE_CFG_MEDIA_TP_S);
-	cfg->rx_buf_len = hnae_get_field(__le32_to_cpu(req->param[1]),
-					 HCLGE_CFG_RX_BUF_LEN_M,
-					 HCLGE_CFG_RX_BUF_LEN_S);
+	cfg->vmdq_vport_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+					      HCLGE_CFG_VMDQ_M,
+					      HCLGE_CFG_VMDQ_S);
+	cfg->tc_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+				      HCLGE_CFG_TC_NUM_M, HCLGE_CFG_TC_NUM_S);
+	cfg->tqp_desc_num = hnae3_get_field(__le32_to_cpu(req->param[0]),
+					    HCLGE_CFG_TQP_DESC_N_M,
+					    HCLGE_CFG_TQP_DESC_N_S);
+
+	cfg->phy_addr = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					HCLGE_CFG_PHY_ADDR_M,
+					HCLGE_CFG_PHY_ADDR_S);
+	cfg->media_type = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					  HCLGE_CFG_MEDIA_TP_M,
+					  HCLGE_CFG_MEDIA_TP_S);
+	cfg->rx_buf_len = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					  HCLGE_CFG_RX_BUF_LEN_M,
+					  HCLGE_CFG_RX_BUF_LEN_S);
 	/* get mac_address */
 	mac_addr_tmp = __le32_to_cpu(req->param[2]);
-	mac_addr_tmp_high = hnae_get_field(__le32_to_cpu(req->param[3]),
-					   HCLGE_CFG_MAC_ADDR_H_M,
-					   HCLGE_CFG_MAC_ADDR_H_S);
+	mac_addr_tmp_high = hnae3_get_field(__le32_to_cpu(req->param[3]),
+					    HCLGE_CFG_MAC_ADDR_H_M,
+					    HCLGE_CFG_MAC_ADDR_H_S);
 
 	mac_addr_tmp |= (mac_addr_tmp_high << 31) << 1;
 
-	cfg->default_speed = hnae_get_field(__le32_to_cpu(req->param[3]),
-					    HCLGE_CFG_DEFAULT_SPEED_M,
-					    HCLGE_CFG_DEFAULT_SPEED_S);
-	cfg->rss_size_max = hnae_get_field(__le32_to_cpu(req->param[3]),
-					   HCLGE_CFG_RSS_SIZE_M,
-					   HCLGE_CFG_RSS_SIZE_S);
+	cfg->default_speed = hnae3_get_field(__le32_to_cpu(req->param[3]),
+					     HCLGE_CFG_DEFAULT_SPEED_M,
+					     HCLGE_CFG_DEFAULT_SPEED_S);
+	cfg->rss_size_max = hnae3_get_field(__le32_to_cpu(req->param[3]),
+					    HCLGE_CFG_RSS_SIZE_M,
+					    HCLGE_CFG_RSS_SIZE_S);
 
 	for (i = 0; i < ETH_ALEN; i++)
 		cfg->mac_addr[i] = (mac_addr_tmp >> (8 * i)) & 0xff;
@@ -1077,9 +1077,9 @@ static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc)
 	req = (struct hclge_cfg_param_cmd *)desc[1].data;
 	cfg->numa_node_map = __le32_to_cpu(req->param[0]);
 
-	cfg->speed_ability = hnae_get_field(__le32_to_cpu(req->param[1]),
-					    HCLGE_CFG_SPEED_ABILITY_M,
-					    HCLGE_CFG_SPEED_ABILITY_S);
+	cfg->speed_ability = hnae3_get_field(__le32_to_cpu(req->param[1]),
+					     HCLGE_CFG_SPEED_ABILITY_M,
+					     HCLGE_CFG_SPEED_ABILITY_S);
 }
 
 /* hclge_get_cfg: query the static parameter from flash
@@ -1098,11 +1098,11 @@ static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg)
 		req = (struct hclge_cfg_param_cmd *)desc[i].data;
 		hclge_cmd_setup_basic_desc(&desc[i], HCLGE_OPC_GET_CFG_PARAM,
 					   true);
-		hnae_set_field(offset, HCLGE_CFG_OFFSET_M,
-			       HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES);
+		hnae3_set_field(offset, HCLGE_CFG_OFFSET_M,
+				HCLGE_CFG_OFFSET_S, i * HCLGE_CFG_RD_LEN_BYTES);
 		/* Len should be united by 4 bytes when send to hardware */
-		hnae_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S,
-			       HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT);
+		hnae3_set_field(offset, HCLGE_CFG_RD_LEN_M, HCLGE_CFG_RD_LEN_S,
+				HCLGE_CFG_RD_LEN_BYTES / HCLGE_CFG_RD_LEN_UNIT);
 		req->offset = cpu_to_le32(offset);
 	}
 
@@ -1189,7 +1189,7 @@ static int hclge_configure(struct hclge_dev *hdev)
 
 	/* Currently not support uncontiuous tc */
 	for (i = 0; i < hdev->tm_info.num_tc; i++)
-		hnae_set_bit(hdev->hw_tc_map, i, 1);
+		hnae3_set_bit(hdev->hw_tc_map, i, 1);
 
 	hdev->tx_sch_mode = HCLGE_FLAG_TC_BASE_SCH_MODE;
 
@@ -1208,13 +1208,13 @@ static int hclge_config_tso(struct hclge_dev *hdev, int tso_mss_min,
 	req = (struct hclge_cfg_tso_status_cmd *)desc.data;
 
 	tso_mss = 0;
-	hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
-		       HCLGE_TSO_MSS_MIN_S, tso_mss_min);
+	hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
+			HCLGE_TSO_MSS_MIN_S, tso_mss_min);
 	req->tso_mss_min = cpu_to_le16(tso_mss);
 
 	tso_mss = 0;
-	hnae_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
-		       HCLGE_TSO_MSS_MIN_S, tso_mss_max);
+	hnae3_set_field(tso_mss, HCLGE_TSO_MSS_MIN_M,
+			HCLGE_TSO_MSS_MIN_S, tso_mss_max);
 	req->tso_mss_max = cpu_to_le16(tso_mss);
 
 	return hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2118,48 +2118,48 @@ int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex)
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_SPEED_DUP, false);
 
-	hnae_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex);
+	hnae3_set_bit(req->speed_dup, HCLGE_CFG_DUPLEX_B, !!duplex);
 
 	switch (speed) {
 	case HCLGE_MAC_SPEED_10M:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 6);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 6);
 		break;
 	case HCLGE_MAC_SPEED_100M:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 7);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 7);
 		break;
 	case HCLGE_MAC_SPEED_1G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 0);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 0);
 		break;
 	case HCLGE_MAC_SPEED_10G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 1);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 1);
 		break;
 	case HCLGE_MAC_SPEED_25G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 2);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 2);
 		break;
 	case HCLGE_MAC_SPEED_40G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 3);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 3);
 		break;
 	case HCLGE_MAC_SPEED_50G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 4);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 4);
 		break;
 	case HCLGE_MAC_SPEED_100G:
-		hnae_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
-			       HCLGE_CFG_SPEED_S, 5);
+		hnae3_set_field(req->speed_dup, HCLGE_CFG_SPEED_M,
+				HCLGE_CFG_SPEED_S, 5);
 		break;
 	default:
 		dev_err(&hdev->pdev->dev, "invalid speed (%d)\n", speed);
 		return -EINVAL;
 	}
 
-	hnae_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B,
-		     1);
+	hnae3_set_bit(req->mac_change_fec_en, HCLGE_CFG_MAC_SPEED_CHANGE_EN_B,
+		      1);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -2201,9 +2201,9 @@ static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed,
 		return ret;
 	}
 
-	*duplex = hnae_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
-	speed_tmp = hnae_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
-				   HCLGE_QUERY_SPEED_S);
+	*duplex = hnae3_get_bit(req->an_syn_dup_speed, HCLGE_QUERY_DUPLEX_B);
+	speed_tmp = hnae3_get_field(req->an_syn_dup_speed, HCLGE_QUERY_SPEED_M,
+				    HCLGE_QUERY_SPEED_S);
 
 	ret = hclge_parse_speed(speed_tmp, speed);
 	if (ret) {
@@ -2225,7 +2225,7 @@ static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_AN_MODE, false);
 
 	req = (struct hclge_config_auto_neg_cmd *)desc.data;
-	hnae_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
+	hnae3_set_bit(flag, HCLGE_MAC_CFG_AN_EN_B, !!enable);
 	req->cfg_an_cmd_flag = cpu_to_le32(flag);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2269,8 +2269,8 @@ static int hclge_set_default_mac_vlan_mask(struct hclge_dev *hdev,
 	req = (struct hclge_mac_vlan_mask_entry_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_MASK_SET, false);
 
-	hnae_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B,
-		     mask_vlan ? 1 : 0);
+	hnae3_set_bit(req->vlan_mask, HCLGE_VLAN_MASK_EN_B,
+		      mask_vlan ? 1 : 0);
 	ether_addr_copy(req->mac_mask, mac_mask);
 
 	status = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2711,7 +2711,7 @@ static int hclge_reset_wait(struct hclge_dev *hdev)
 	}
 
 	val = hclge_read_dev(&hdev->hw, reg);
-	while (hnae_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
+	while (hnae3_get_bit(val, reg_bit) && cnt < HCLGE_RESET_WAIT_CNT) {
 		msleep(HCLGE_RESET_WATI_MS);
 		val = hclge_read_dev(&hdev->hw, reg);
 		cnt++;
@@ -2733,7 +2733,7 @@ int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id)
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CFG_RST_TRIGGER, false);
-	hnae_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
+	hnae3_set_bit(req->mac_func_reset, HCLGE_CFG_RESET_FUNC_B, 1);
 	req->fun_reset_vfid = func_id;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2752,13 +2752,13 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 	switch (hdev->reset_type) {
 	case HNAE3_GLOBAL_RESET:
 		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
-		hnae_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1);
+		hnae3_set_bit(val, HCLGE_GLOBAL_RESET_BIT, 1);
 		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
 		dev_info(&pdev->dev, "Global Reset requested\n");
 		break;
 	case HNAE3_CORE_RESET:
 		val = hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG);
-		hnae_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
+		hnae3_set_bit(val, HCLGE_CORE_RESET_BIT, 1);
 		hclge_write_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG, val);
 		dev_info(&pdev->dev, "Core Reset requested\n");
 		break;
@@ -3115,11 +3115,11 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid,
 	for (i = 0; i < HCLGE_MAX_TC_NUM; i++) {
 		u16 mode = 0;
 
-		hnae_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1));
-		hnae_set_field(mode, HCLGE_RSS_TC_SIZE_M,
-			       HCLGE_RSS_TC_SIZE_S, tc_size[i]);
-		hnae_set_field(mode, HCLGE_RSS_TC_OFFSET_M,
-			       HCLGE_RSS_TC_OFFSET_S, tc_offset[i]);
+		hnae3_set_bit(mode, HCLGE_RSS_TC_VALID_B, (tc_valid[i] & 0x1));
+		hnae3_set_field(mode, HCLGE_RSS_TC_SIZE_M,
+				HCLGE_RSS_TC_SIZE_S, tc_size[i]);
+		hnae3_set_field(mode, HCLGE_RSS_TC_OFFSET_M,
+				HCLGE_RSS_TC_OFFSET_S, tc_offset[i]);
 
 		req->rss_tc_mode[i] = cpu_to_le16(mode);
 	}
@@ -3496,16 +3496,16 @@ int hclge_bind_ring_with_vector(struct hclge_vport *vport,
 	i = 0;
 	for (node = ring_chain; node; node = node->next) {
 		tqp_type_and_id = le16_to_cpu(req->tqp_type_and_id[i]);
-		hnae_set_field(tqp_type_and_id,  HCLGE_INT_TYPE_M,
-			       HCLGE_INT_TYPE_S,
-			       hnae_get_bit(node->flag, HNAE3_RING_TYPE_B));
-		hnae_set_field(tqp_type_and_id, HCLGE_TQP_ID_M,
-			       HCLGE_TQP_ID_S, node->tqp_index);
-		hnae_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M,
-			       HCLGE_INT_GL_IDX_S,
-			       hnae_get_field(node->int_gl_idx,
-					      HNAE3_RING_GL_IDX_M,
-					      HNAE3_RING_GL_IDX_S));
+		hnae3_set_field(tqp_type_and_id,  HCLGE_INT_TYPE_M,
+				HCLGE_INT_TYPE_S,
+				hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B));
+		hnae3_set_field(tqp_type_and_id, HCLGE_TQP_ID_M,
+				HCLGE_TQP_ID_S, node->tqp_index);
+		hnae3_set_field(tqp_type_and_id, HCLGE_INT_GL_IDX_M,
+				HCLGE_INT_GL_IDX_S,
+				hnae3_get_field(node->int_gl_idx,
+						HNAE3_RING_GL_IDX_M,
+						HNAE3_RING_GL_IDX_S));
 		req->tqp_type_and_id[i] = cpu_to_le16(tqp_type_and_id);
 		if (++i >= HCLGE_VECTOR_ELEMENTS_PER_CMD) {
 			req->int_cause_num = HCLGE_VECTOR_ELEMENTS_PER_CMD;
@@ -3653,20 +3653,20 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable)
 	int ret;
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, false);
-	hnae_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
-	hnae_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
-	hnae_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_TX_EN_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_EN_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_PAD_TX_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_PAD_RX_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_1588_TX_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_1588_RX_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_LINE_LP_B, 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_FCS_TX_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_FCS_STRIP_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_TX_OVERSIZE_TRUNCATE_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_RX_OVERSIZE_TRUNCATE_B, enable);
+	hnae3_set_bit(loop_en, HCLGE_MAC_TX_UNDER_MIN_ERR_B, enable);
 	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -3694,7 +3694,7 @@ static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en)
 
 	/* 2 Then setup the loopback flag */
 	loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en);
-	hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
+	hnae3_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0);
 
 	req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en);
 
@@ -3958,10 +3958,10 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev,
 	req = (struct hclge_mta_filter_mode_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_MODE_CFG, false);
 
-	hnae_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B,
-		     enable);
-	hnae_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M,
-		       HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel);
+	hnae3_set_bit(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_EN_B,
+		      enable);
+	hnae3_set_field(req->dmac_sel_en, HCLGE_CFG_MTA_MAC_SEL_M,
+			HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -3985,8 +3985,8 @@ int hclge_cfg_func_mta_filter(struct hclge_dev *hdev,
 	req = (struct hclge_cfg_func_mta_filter_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_MAC_FUNC_CFG, false);
 
-	hnae_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B,
-		     enable);
+	hnae3_set_bit(req->accept, HCLGE_CFG_FUNC_MTA_ACCEPT_B,
+		      enable);
 	req->function_id = func_id;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -4012,10 +4012,10 @@ static int hclge_set_mta_table_item(struct hclge_vport *vport,
 
 	req = (struct hclge_cfg_func_mta_item_cmd *)desc.data;
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MTA_TBL_ITEM_CFG, false);
-	hnae_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable);
+	hnae3_set_bit(req->accept, HCLGE_CFG_MTA_ITEM_ACCEPT_B, enable);
 
-	hnae_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
-		       HCLGE_CFG_MTA_ITEM_IDX_S, idx);
+	hnae3_set_field(item_idx, HCLGE_CFG_MTA_ITEM_IDX_M,
+			HCLGE_CFG_MTA_ITEM_IDX_S, idx);
 	req->item_idx = cpu_to_le16(item_idx);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -4262,10 +4262,10 @@ int hclge_add_uc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
 
-	hnae_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
-		       HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
+	hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M,
+			HCLGE_MAC_EPORT_VFID_S, vport->vport_id);
 
 	req.egress_port = cpu_to_le16(egress_port);
 
@@ -4316,8 +4316,8 @@ int hclge_rm_uc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hclge_prepare_mac_addr(&req, addr);
 	ret = hclge_remove_mac_vlan_tbl(vport, &req);
 
@@ -4349,10 +4349,10 @@ int hclge_add_mc_addr_common(struct hclge_vport *vport,
 		return -EINVAL;
 	}
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hclge_prepare_mac_addr(&req, addr);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
 	if (!status) {
@@ -4416,10 +4416,10 @@ int hclge_rm_mc_addr_common(struct hclge_vport *vport,
 	}
 
 	memset(&req, 0, sizeof(req));
-	hnae_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
-	hnae_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
-	hnae_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.flags, HCLGE_MAC_VLAN_BIT0_EN_B, 1);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
+	hnae3_set_bit(req.entry_type, HCLGE_MAC_VLAN_BIT1_EN_B, 1);
+	hnae3_set_bit(req.mc_mac_en, HCLGE_MAC_VLAN_BIT0_EN_B, 0);
 	hclge_prepare_mac_addr(&req, addr);
 	status = hclge_lookup_mac_vlan_tbl(vport, &req, desc, true);
 	if (!status) {
@@ -4800,19 +4800,19 @@ static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport)
 	req = (struct hclge_vport_vtag_tx_cfg_cmd *)desc.data;
 	req->def_vlan_tag1 = cpu_to_le16(vcfg->default_tag1);
 	req->def_vlan_tag2 = cpu_to_le16(vcfg->default_tag2);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B,
-			vcfg->accept_tag1 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B,
-			vcfg->accept_untag1 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B,
-			vcfg->accept_tag2 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B,
-			vcfg->accept_untag2 ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B,
-		     vcfg->insert_tag1_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B,
-		     vcfg->insert_tag2_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG1_B,
+		      vcfg->accept_tag1 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG1_B,
+		      vcfg->accept_untag1 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_TAG2_B,
+		      vcfg->accept_tag2 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_ACCEPT_UNTAG2_B,
+		      vcfg->accept_untag2 ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG1_EN_B,
+		      vcfg->insert_tag1_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_PORT_INS_TAG2_EN_B,
+		      vcfg->insert_tag2_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0);
 
 	req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD;
 	req->vf_bitmap[req->vf_offset] =
@@ -4838,14 +4838,14 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_RX_CFG, false);
 
 	req = (struct hclge_vport_vtag_rx_cfg_cmd *)desc.data;
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B,
-		     vcfg->strip_tag1_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B,
-		     vcfg->strip_tag2_en ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B,
-		     vcfg->vlan1_vlan_prionly ? 1 : 0);
-	hnae_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B,
-		     vcfg->vlan2_vlan_prionly ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG1_EN_B,
+		      vcfg->strip_tag1_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_REM_TAG2_EN_B,
+		      vcfg->strip_tag2_en ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG1_EN_B,
+		      vcfg->vlan1_vlan_prionly ? 1 : 0);
+	hnae3_set_bit(req->vport_vlan_cfg, HCLGE_SHOW_TAG2_EN_B,
+		      vcfg->vlan2_vlan_prionly ? 1 : 0);
 
 	req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD;
 	req->vf_bitmap[req->vf_offset] =
@@ -5041,7 +5041,7 @@ static int hclge_send_reset_tqp_cmd(struct hclge_dev *hdev, u16 queue_id,
 
 	req = (struct hclge_reset_tqp_queue_cmd *)desc.data;
 	req->tqp_id = cpu_to_le16(queue_id & HCLGE_RING_ID_MASK);
-	hnae_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
+	hnae3_set_bit(req->reset_req, HCLGE_TQP_RESET_B, enable);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
@@ -5071,7 +5071,7 @@ static int hclge_get_reset_status(struct hclge_dev *hdev, u16 queue_id)
 		return ret;
 	}
 
-	return hnae_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
+	return hnae3_get_bit(req->ready_to_reset, HCLGE_TQP_RESET_B);
 }
 
 static u16 hclge_covert_handle_qid_global(struct hnae3_handle *handle,
@@ -5378,12 +5378,12 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 	phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_MDIX);
 
 	retval = phy_read(phydev, HCLGE_PHY_CSC_REG);
-	mdix_ctrl = hnae_get_field(retval, HCLGE_PHY_MDIX_CTRL_M,
-				   HCLGE_PHY_MDIX_CTRL_S);
+	mdix_ctrl = hnae3_get_field(retval, HCLGE_PHY_MDIX_CTRL_M,
+				    HCLGE_PHY_MDIX_CTRL_S);
 
 	retval = phy_read(phydev, HCLGE_PHY_CSS_REG);
-	mdix = hnae_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B);
-	is_resolved = hnae_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B);
+	mdix = hnae3_get_bit(retval, HCLGE_PHY_MDIX_STATUS_B);
+	is_resolved = hnae3_get_bit(retval, HCLGE_PHY_SPEED_DUP_RESOLVE_B);
 
 	phy_write(phydev, HCLGE_PHY_PAGE_REG, HCLGE_PHY_PAGE_COPPER);
 
@@ -6156,8 +6156,8 @@ static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status)
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_LED_STATUS_CFG, false);
 
 	req = (struct hclge_set_led_state_cmd *)desc.data;
-	hnae_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M,
-		       HCLGE_LED_LOCATE_STATE_S, locate_led_status);
+	hnae3_set_field(req->locate_led_config, HCLGE_LED_LOCATE_STATE_M,
+			HCLGE_LED_LOCATE_STATE_S, locate_led_status);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret)
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 7541cb9b71ce..50ae2f8f188d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -128,12 +128,12 @@ static int hclge_get_ring_chain_from_mbx(
 		HCLGE_MBX_RING_NODE_VARIABLE_NUM))
 		return -ENOMEM;
 
-	hnae_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]);
+	hnae3_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]);
 	ring_chain->tqp_index =
 			hclge_get_queue_id(vport->nic.kinfo.tqp[req->msg[4]]);
-	hnae_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
-		       HCLGE_INT_GL_IDX_S,
-		       req->msg[5]);
+	hnae3_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
+			HCLGE_INT_GL_IDX_S,
+			req->msg[5]);
 
 	cur_chain = ring_chain;
 
@@ -142,19 +142,19 @@ static int hclge_get_ring_chain_from_mbx(
 		if (!new_chain)
 			goto err;
 
-		hnae_set_bit(new_chain->flag, HNAE3_RING_TYPE_B,
-			     req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
-			     HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]);
+		hnae3_set_bit(new_chain->flag, HNAE3_RING_TYPE_B,
+			      req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
+			      HCLGE_MBX_RING_MAP_BASIC_MSG_NUM]);
 
 		new_chain->tqp_index =
 		hclge_get_queue_id(vport->nic.kinfo.tqp
 			[req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
 			HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 1]]);
 
-		hnae_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
-			       HCLGE_INT_GL_IDX_S,
-			       req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
-			       HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]);
+		hnae3_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
+				HCLGE_INT_GL_IDX_S,
+				req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
+				HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]);
 
 		cur_chain->next = new_chain;
 		cur_chain = new_chain;
@@ -460,7 +460,7 @@ void hclge_mbx_handler(struct hclge_dev *hdev)
 		req = (struct hclge_mbx_vf_to_pf_cmd *)desc->data;
 
 		flag = le16_to_cpu(crq->desc[crq->next_to_use].flag);
-		if (unlikely(!hnae_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) {
+		if (unlikely(!hnae3_get_bit(flag, HCLGE_CMDQ_RX_OUTVLD_B))) {
 			dev_warn(&hdev->pdev->dev,
 				 "dropped invalid mailbox message, code = %d\n",
 				 req->msg[0]);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 9f7932e423b5..b6cfe6ff988d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -67,16 +67,16 @@ static int hclge_mdio_write(struct mii_bus *bus, int phyid, int regnum,
 
 	mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
 
-	hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
-		       HCLGE_MDIO_PHYID_S, phyid);
-	hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
-		       HCLGE_MDIO_PHYREG_S, regnum);
+	hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
+			HCLGE_MDIO_PHYID_S, phyid);
+	hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
+			HCLGE_MDIO_PHYREG_S, regnum);
 
-	hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
-		       HCLGE_MDIO_CTRL_ST_S, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
-		       HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE);
+	hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
+			HCLGE_MDIO_CTRL_ST_S, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
+			HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_WRITE);
 
 	mdio_cmd->data_wr = cpu_to_le16(data);
 
@@ -105,16 +105,16 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum)
 
 	mdio_cmd = (struct hclge_mdio_cfg_cmd *)desc.data;
 
-	hnae_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
-		       HCLGE_MDIO_PHYID_S, phyid);
-	hnae_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
-		       HCLGE_MDIO_PHYREG_S, regnum);
+	hnae3_set_field(mdio_cmd->phyid, HCLGE_MDIO_PHYID_M,
+			HCLGE_MDIO_PHYID_S, phyid);
+	hnae3_set_field(mdio_cmd->phyad, HCLGE_MDIO_PHYREG_M,
+			HCLGE_MDIO_PHYREG_S, regnum);
 
-	hnae_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
-		       HCLGE_MDIO_CTRL_ST_S, 1);
-	hnae_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
-		       HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ);
+	hnae3_set_bit(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_START_B, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_ST_M,
+			HCLGE_MDIO_CTRL_ST_S, 1);
+	hnae3_set_field(mdio_cmd->ctrl_bit, HCLGE_MDIO_CTRL_OP_M,
+			HCLGE_MDIO_CTRL_OP_S, HCLGE_MDIO_C22_READ);
 
 	/* Read out phy data */
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -125,7 +125,7 @@ static int hclge_mdio_read(struct mii_bus *bus, int phyid, int regnum)
 		return ret;
 	}
 
-	if (hnae_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) {
+	if (hnae3_get_bit(le16_to_cpu(mdio_cmd->sta), HCLGE_MDIO_STA_B)) {
 		dev_err(&hdev->pdev->dev, "mdio read data error\n");
 		return -EIO;
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 262c125f8137..82bc30fdff98 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1184,10 +1184,10 @@ static int hclge_bp_setup_hw(struct hclge_dev *hdev, u8 tc)
 			u16 qs_id = vport->qs_offset + tc;
 			u8 grp, sub_grp;
 
-			grp = hnae_get_field(qs_id, HCLGE_BP_GRP_ID_M,
-					     HCLGE_BP_GRP_ID_S);
-			sub_grp = hnae_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
-						 HCLGE_BP_SUB_GRP_ID_S);
+			grp = hnae3_get_field(qs_id, HCLGE_BP_GRP_ID_M,
+					      HCLGE_BP_GRP_ID_S);
+			sub_grp = hnae3_get_field(qs_id, HCLGE_BP_SUB_GRP_ID_M,
+						  HCLGE_BP_SUB_GRP_ID_S);
 			if (i == grp)
 				qs_bitmap |= (1 << sub_grp);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index c2b6e8a6700f..c82d49ebd5bf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -123,10 +123,11 @@ struct hclge_port_shapping_cmd {
 };
 
 #define hclge_tm_set_field(dest, string, val) \
-			hnae_set_field((dest), (HCLGE_TM_SHAP_##string##_MSK), \
-				       (HCLGE_TM_SHAP_##string##_LSH), val)
+			   hnae3_set_field((dest), \
+			   (HCLGE_TM_SHAP_##string##_MSK), \
+			   (HCLGE_TM_SHAP_##string##_LSH), val)
 #define hclge_tm_get_field(src, string) \
-			hnae_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
+			hnae3_get_field((src), (HCLGE_TM_SHAP_##string##_MSK), \
 				       (HCLGE_TM_SHAP_##string##_LSH))
 
 int hclge_tm_schd_init(struct hclge_dev *hdev);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 1638193a63d3..5a8653238e3f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -450,12 +450,12 @@ static int hclgevf_set_rss_tc_mode(struct hclgevf_dev *hdev,  u16 rss_size)
 
 	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_RSS_TC_MODE, false);
 	for (i = 0; i < HCLGEVF_MAX_TC_NUM; i++) {
-		hnae_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B,
-			     (tc_valid[i] & 0x1));
-		hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M,
-			       HCLGEVF_RSS_TC_SIZE_S, tc_size[i]);
-		hnae_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M,
-			       HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]);
+		hnae3_set_bit(req->rss_tc_mode[i], HCLGEVF_RSS_TC_VALID_B,
+			      (tc_valid[i] & 0x1));
+		hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_SIZE_M,
+				HCLGEVF_RSS_TC_SIZE_S, tc_size[i]);
+		hnae3_set_field(req->rss_tc_mode[i], HCLGEVF_RSS_TC_OFFSET_M,
+				HCLGEVF_RSS_TC_OFFSET_S, tc_offset[i]);
 	}
 	status = hclgevf_cmd_send(&hdev->hw, &desc, 1);
 	if (status)
@@ -582,11 +582,11 @@ static int hclgevf_bind_ring_to_vector(struct hnae3_handle *handle, bool en,
 		}
 
 		req->msg[idx_offset] =
-				hnae_get_bit(node->flag, HNAE3_RING_TYPE_B);
+				hnae3_get_bit(node->flag, HNAE3_RING_TYPE_B);
 		req->msg[idx_offset + 1] = node->tqp_index;
-		req->msg[idx_offset + 2] = hnae_get_field(node->int_gl_idx,
-							  HNAE3_RING_GL_IDX_M,
-							  HNAE3_RING_GL_IDX_S);
+		req->msg[idx_offset + 2] = hnae3_get_field(node->int_gl_idx,
+							   HNAE3_RING_GL_IDX_M,
+							   HNAE3_RING_GL_IDX_S);
 
 		i++;
 		if ((i == (HCLGE_MBX_VF_MSG_DATA_NUM -
@@ -1000,8 +1000,8 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev)
 
 	/* wait to check the hardware reset completion status */
 	val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
-	while (hnae_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
-			    (cnt < HCLGEVF_RESET_WAIT_CNT)) {
+	while (hnae3_get_bit(val, HCLGEVF_FUN_RST_ING_B) &&
+	       (cnt < HCLGEVF_RESET_WAIT_CNT)) {
 		msleep(HCLGEVF_RESET_WAIT_MS);
 		val = hclgevf_read_dev(&hdev->hw, HCLGEVF_FUN_RST_ING);
 		cnt++;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index b598c06af8e0..173ca27957ef 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -152,7 +152,7 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 		req = (struct hclge_mbx_pf_to_vf_cmd *)desc->data;
 
 		flag = le16_to_cpu(crq->desc[crq->next_to_use].flag);
-		if (unlikely(!hnae_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) {
+		if (unlikely(!hnae3_get_bit(flag, HCLGEVF_CMDQ_RX_OUTVLD_B))) {
 			dev_warn(&hdev->pdev->dev,
 				 "dropped invalid mailbox message, code = %d\n",
 				 req->msg[0]);
-- 
cgit v1.2.3


From 9b11233d8e2ca80afc6e16200b680c5daf051333 Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Sun, 1 Jul 2018 17:28:07 +0200
Subject: ALSA: usb: caiaq: audio: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/caiaq/audio.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c
index f35d29f49ffe..15344d39a6cd 100644
--- a/sound/usb/caiaq/audio.c
+++ b/sound/usb/caiaq/audio.c
@@ -636,6 +636,7 @@ static void read_completed(struct urb *urb)
 	struct device *dev;
 	struct urb *out = NULL;
 	int i, frame, len, send_it = 0, outframe = 0;
+	unsigned long flags;
 	size_t offset = 0;
 
 	if (urb->status || !info)
@@ -672,10 +673,10 @@ static void read_completed(struct urb *urb)
 		offset += len;
 
 		if (len > 0) {
-			spin_lock(&cdev->spinlock);
+			spin_lock_irqsave(&cdev->spinlock, flags);
 			fill_out_urb(cdev, out, &out->iso_frame_desc[outframe]);
 			read_in_urb(cdev, urb, &urb->iso_frame_desc[frame]);
-			spin_unlock(&cdev->spinlock);
+			spin_unlock_irqrestore(&cdev->spinlock, flags);
 			check_for_elapsed_periods(cdev, cdev->sub_playback);
 			check_for_elapsed_periods(cdev, cdev->sub_capture);
 			send_it = 1;
-- 
cgit v1.2.3


From 875a92b3f58a117842c0f9e8d65355c6be218fa2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 29 Jun 2018 15:36:34 +0300
Subject: pinctrl: intel: Convert to use SPDX identifier

Reduce size of duplicated comments by switching to use SPDX identifier.

No functional change.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/Kconfig                |  4 ++--
 drivers/pinctrl/intel/pinctrl-baytrail.c     | 12 ++----------
 drivers/pinctrl/intel/pinctrl-broxton.c      |  5 +----
 drivers/pinctrl/intel/pinctrl-cannonlake.c   |  5 +----
 drivers/pinctrl/intel/pinctrl-cedarfork.c    |  5 +----
 drivers/pinctrl/intel/pinctrl-cherryview.c   |  5 +----
 drivers/pinctrl/intel/pinctrl-denverton.c    |  5 +----
 drivers/pinctrl/intel/pinctrl-geminilake.c   |  5 +----
 drivers/pinctrl/intel/pinctrl-intel.c        |  5 +----
 drivers/pinctrl/intel/pinctrl-intel.h        |  5 +----
 drivers/pinctrl/intel/pinctrl-lewisburg.c    |  5 +----
 drivers/pinctrl/intel/pinctrl-merrifield.c   |  5 +----
 drivers/pinctrl/intel/pinctrl-sunrisepoint.c |  5 +----
 13 files changed, 15 insertions(+), 56 deletions(-)

diff --git a/drivers/pinctrl/intel/Kconfig b/drivers/pinctrl/intel/Kconfig
index 490497896581..452a14f78707 100644
--- a/drivers/pinctrl/intel/Kconfig
+++ b/drivers/pinctrl/intel/Kconfig
@@ -1,6 +1,6 @@
-#
+# SPDX-License-Identifier: GPL-2.0
 # Intel pin control drivers
-#
+
 if (X86 || COMPILE_TEST)
 
 config PINCTRL_BAYTRAIL
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 6b52ea1440a6..153187919d02 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1,17 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Pinctrl GPIO driver for Intel Baytrail
- * Copyright (c) 2012-2013, Intel Corporation.
  *
+ * Copyright (c) 2012-2013, Intel Corporation
  * Author: Mathias Nyman <mathias.nyman@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- * This program is distributed in the hope it will be useful, but WITHOUT
- * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
- * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
- * more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/pinctrl/intel/pinctrl-broxton.c b/drivers/pinctrl/intel/pinctrl-broxton.c
index e6e6fd112585..8b1c7b59ad3e 100644
--- a/drivers/pinctrl/intel/pinctrl-broxton.c
+++ b/drivers/pinctrl/intel/pinctrl-broxton.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Broxton SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2015, 2016 Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index 6243e7d95e7e..71ad67b8fc35 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Cannon Lake PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Authors: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-cedarfork.c b/drivers/pinctrl/intel/pinctrl-cedarfork.c
index b2a2456f019e..c788e37e338e 100644
--- a/drivers/pinctrl/intel/pinctrl-cedarfork.c
+++ b/drivers/pinctrl/intel/pinctrl-cedarfork.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Cedar Fork PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 0f1019ae3993..6d31ad799987 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Cherryview/Braswell pinctrl driver
  *
@@ -7,10 +8,6 @@
  * This driver is based on the original Cherryview GPIO driver by
  *   Ning Li <ning.li@intel.com>
  *   Alan Cox <alan@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/dmi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-denverton.c b/drivers/pinctrl/intel/pinctrl-denverton.c
index 6572550cfe78..f321ab0d76e5 100644
--- a/drivers/pinctrl/intel/pinctrl-denverton.c
+++ b/drivers/pinctrl/intel/pinctrl-denverton.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Denverton SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-geminilake.c b/drivers/pinctrl/intel/pinctrl-geminilake.c
index a6b94c930007..5c4c96752fc1 100644
--- a/drivers/pinctrl/intel/pinctrl-geminilake.c
+++ b/drivers/pinctrl/intel/pinctrl-geminilake.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Gemini Lake SoC pinctrl/GPIO driver
  *
  * Copyright (C) 2017 Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 1e24a6b8a64e..3d0bd7b99725 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel pinctrl/GPIO core driver.
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/module.h>
diff --git a/drivers/pinctrl/intel/pinctrl-intel.h b/drivers/pinctrl/intel/pinctrl-intel.h
index 98fdf9adf623..1785abf157e4 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.h
+++ b/drivers/pinctrl/intel/pinctrl-intel.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Core pinctrl/GPIO driver for Intel GPIO controllers
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef PINCTRL_INTEL_H
diff --git a/drivers/pinctrl/intel/pinctrl-lewisburg.c b/drivers/pinctrl/intel/pinctrl-lewisburg.c
index 14d56ea6cfdc..99894647eddd 100644
--- a/drivers/pinctrl/intel/pinctrl-lewisburg.c
+++ b/drivers/pinctrl/intel/pinctrl-lewisburg.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Lewisburg pinctrl/GPIO driver
  *
  * Copyright (C) 2017, Intel Corporation
  * Author: Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/pinctrl/intel/pinctrl-merrifield.c b/drivers/pinctrl/intel/pinctrl-merrifield.c
index d9357054d41d..4a916be44f4f 100644
--- a/drivers/pinctrl/intel/pinctrl-merrifield.c
+++ b/drivers/pinctrl/intel/pinctrl-merrifield.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Merrifield SoC pinctrl driver
  *
  * Copyright (C) 2016, Intel Corporation
  * Author: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/bitops.h>
diff --git a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
index fee3435a6f15..7984392104fe 100644
--- a/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
+++ b/drivers/pinctrl/intel/pinctrl-sunrisepoint.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Intel Sunrisepoint PCH pinctrl/GPIO driver
  *
  * Copyright (C) 2015, Intel Corporation
  * Authors: Mathias Nyman <mathias.nyman@linux.intel.com>
  *          Mika Westerberg <mika.westerberg@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/acpi.h>
-- 
cgit v1.2.3


From 1259d239799bf9c898091d92adc4317f2c3d74ad Mon Sep 17 00:00:00 2001
From: John Ogness <john.ogness@linutronix.de>
Date: Sun, 1 Jul 2018 17:28:08 +0200
Subject: ALSA: usb-midi: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Signed-off-by: John Ogness <john.ogness@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Acked-by: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/midi.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 2c1aaa3292bf..dcfc546d81b9 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -281,15 +281,16 @@ static void snd_usbmidi_out_urb_complete(struct urb *urb)
 	struct out_urb_context *context = urb->context;
 	struct snd_usb_midi_out_endpoint *ep = context->ep;
 	unsigned int urb_index;
+	unsigned long flags;
 
-	spin_lock(&ep->buffer_lock);
+	spin_lock_irqsave(&ep->buffer_lock, flags);
 	urb_index = context - ep->urbs;
 	ep->active_urbs &= ~(1 << urb_index);
 	if (unlikely(ep->drain_urbs)) {
 		ep->drain_urbs &= ~(1 << urb_index);
 		wake_up(&ep->drain_wait);
 	}
-	spin_unlock(&ep->buffer_lock);
+	spin_unlock_irqrestore(&ep->buffer_lock, flags);
 	if (urb->status < 0) {
 		int err = snd_usbmidi_urb_error(urb);
 		if (err < 0) {
-- 
cgit v1.2.3


From 25b7256500a1738141d74da4afcd3c380141f71c Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Wed, 20 Jun 2018 15:54:02 +0300
Subject: dt-bindings: tegra186-gpio: Add information for Tegra194

The Tegra194 GPIO controller is similar to the one in Tegra186.
Add relevant information to the device tree binding documentation.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/gpio/nvidia,tegra186-gpio.txt | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/gpio/nvidia,tegra186-gpio.txt b/Documentation/devicetree/bindings/gpio/nvidia,tegra186-gpio.txt
index c82a2e221bc1..adff16c71d21 100644
--- a/Documentation/devicetree/bindings/gpio/nvidia,tegra186-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/nvidia,tegra186-gpio.txt
@@ -68,6 +68,8 @@ Required properties:
     One of:
     - "nvidia,tegra186-gpio".
     - "nvidia,tegra186-gpio-aon".
+    - "nvidia,tegra194-gpio".
+    - "nvidia,tegra194-gpio-aon".
 - reg-names
     Array of strings.
     Contains a list of names for the register spaces described by the reg
@@ -91,6 +93,8 @@ Required properties:
     depending on compatible value:
     - "nvidia,tegra186-gpio": 6 entries.
     - "nvidia,tegra186-gpio-aon": 1 entry.
+    - "nvidia,tegra194-gpio": 6 entries.
+    - "nvidia,tegra194-gpio-aon": 1 entry.
 - gpio-controller
     Boolean.
     Marks the device node as a GPIO controller/provider.
-- 
cgit v1.2.3


From bac5c3b829c3f2944d258dad1adec444b9deb338 Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Wed, 20 Jun 2018 15:54:03 +0300
Subject: gpio: tegra186: Add support for Tegra194

Add support for the Tegra194 GPIO bank configuration.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tegra186.c | 74 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)

diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c
index 7f1aa4c21e0d..9d0292c8a199 100644
--- a/drivers/gpio/gpio-tegra186.c
+++ b/drivers/gpio/gpio-tegra186.c
@@ -16,6 +16,7 @@
 #include <linux/platform_device.h>
 
 #include <dt-bindings/gpio/tegra186-gpio.h>
+#include <dt-bindings/gpio/tegra194-gpio.h>
 
 #define TEGRA186_GPIO_ENABLE_CONFIG 0x00
 #define  TEGRA186_GPIO_ENABLE_CONFIG_ENABLE BIT(0)
@@ -593,6 +594,73 @@ static const struct tegra_gpio_soc tegra186_aon_soc = {
 	.name = "tegra186-gpio-aon",
 };
 
+#define TEGRA194_MAIN_GPIO_PORT(port, base, count, controller)	\
+	[TEGRA194_MAIN_GPIO_PORT_##port] = {			\
+		.name = #port,					\
+		.offset = base,					\
+		.pins = count,					\
+		.irq = controller,				\
+	}
+
+static const struct tegra_gpio_port tegra194_main_ports[] = {
+	TEGRA194_MAIN_GPIO_PORT( A, 0x1400, 8, 1),
+	TEGRA194_MAIN_GPIO_PORT( B, 0x4e00, 2, 4),
+	TEGRA194_MAIN_GPIO_PORT( C, 0x4600, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( D, 0x4800, 4, 4),
+	TEGRA194_MAIN_GPIO_PORT( E, 0x4a00, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( F, 0x4c00, 6, 4),
+	TEGRA194_MAIN_GPIO_PORT( G, 0x4000, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( H, 0x4200, 8, 4),
+	TEGRA194_MAIN_GPIO_PORT( I, 0x4400, 5, 4),
+	TEGRA194_MAIN_GPIO_PORT( J, 0x5200, 6, 5),
+	TEGRA194_MAIN_GPIO_PORT( K, 0x3000, 8, 3),
+	TEGRA194_MAIN_GPIO_PORT( L, 0x3200, 4, 3),
+	TEGRA194_MAIN_GPIO_PORT( M, 0x2600, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( N, 0x2800, 3, 2),
+	TEGRA194_MAIN_GPIO_PORT( O, 0x5000, 6, 5),
+	TEGRA194_MAIN_GPIO_PORT( P, 0x2a00, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( Q, 0x2c00, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( R, 0x2e00, 6, 2),
+	TEGRA194_MAIN_GPIO_PORT( S, 0x3600, 8, 3),
+	TEGRA194_MAIN_GPIO_PORT( T, 0x3800, 8, 3),
+	TEGRA194_MAIN_GPIO_PORT( U, 0x3a00, 1, 3),
+	TEGRA194_MAIN_GPIO_PORT( V, 0x1000, 8, 1),
+	TEGRA194_MAIN_GPIO_PORT( W, 0x1200, 2, 1),
+	TEGRA194_MAIN_GPIO_PORT( X, 0x2000, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( Y, 0x2200, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT( Z, 0x2400, 8, 2),
+	TEGRA194_MAIN_GPIO_PORT(FF, 0x3400, 2, 3),
+	TEGRA194_MAIN_GPIO_PORT(GG, 0x0000, 2, 0)
+};
+
+static const struct tegra_gpio_soc tegra194_main_soc = {
+	.num_ports = ARRAY_SIZE(tegra194_main_ports),
+	.ports = tegra194_main_ports,
+	.name = "tegra194-gpio",
+};
+
+#define TEGRA194_AON_GPIO_PORT(port, base, count, controller)	\
+	[TEGRA194_AON_GPIO_PORT_##port] = {			\
+		.name = #port,					\
+		.offset = base,					\
+		.pins = count,					\
+		.irq = controller,				\
+	}
+
+static const struct tegra_gpio_port tegra194_aon_ports[] = {
+	TEGRA194_AON_GPIO_PORT(AA, 0x0600, 8, 0),
+	TEGRA194_AON_GPIO_PORT(BB, 0x0800, 4, 0),
+	TEGRA194_AON_GPIO_PORT(CC, 0x0200, 8, 0),
+	TEGRA194_AON_GPIO_PORT(DD, 0x0400, 3, 0),
+	TEGRA194_AON_GPIO_PORT(EE, 0x0000, 7, 0)
+};
+
+static const struct tegra_gpio_soc tegra194_aon_soc = {
+	.num_ports = ARRAY_SIZE(tegra194_aon_ports),
+	.ports = tegra194_aon_ports,
+	.name = "tegra194-gpio-aon",
+};
+
 static const struct of_device_id tegra186_gpio_of_match[] = {
 	{
 		.compatible = "nvidia,tegra186-gpio",
@@ -600,6 +668,12 @@ static const struct of_device_id tegra186_gpio_of_match[] = {
 	}, {
 		.compatible = "nvidia,tegra186-gpio-aon",
 		.data = &tegra186_aon_soc
+	}, {
+		.compatible = "nvidia,tegra194-gpio",
+		.data = &tegra194_main_soc
+	}, {
+		.compatible = "nvidia,tegra194-gpio-aon",
+		.data = &tegra194_aon_soc
 	}, {
 		/* sentinel */
 	}
-- 
cgit v1.2.3


From 5b9b2b5284f81941972105b13337c58489ea8fca Mon Sep 17 00:00:00 2001
From: Mathias Kresin <dev@kresin.me>
Date: Thu, 28 Jun 2018 21:57:40 +0200
Subject: gpio: stp-xway: Implement get callback

Add an implementation to get the current GPIO state.

The callback is used by the leds-gpio driver for example, in case the
current LED/GPIO state should be kept during driver load.

Signed-off-by: Mathias Kresin <dev@kresin.me>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-stp-xway.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c
index c07385b71403..63c708c3f3ae 100644
--- a/drivers/gpio/gpio-stp-xway.c
+++ b/drivers/gpio/gpio-stp-xway.c
@@ -90,6 +90,20 @@ struct xway_stp {
 	u8 reserved;	/* mask out the hw driven bits in gpio_request */
 };
 
+/**
+ * xway_stp_get() - gpio_chip->get - get gpios.
+ * @gc:     Pointer to gpio_chip device structure.
+ * @gpio:   GPIO signal number.
+ *
+ * Gets the shadow value.
+ */
+static int xway_stp_get(struct gpio_chip *gc, unsigned int gpio)
+{
+	struct xway_stp *chip = gpiochip_get_data(gc);
+
+	return (xway_stp_r32(chip->virt, XWAY_STP_CPU0) & BIT(gpio));
+}
+
 /**
  * xway_stp_set() - gpio_chip->set - set gpios.
  * @gc:     Pointer to gpio_chip device structure.
@@ -215,6 +229,7 @@ static int xway_stp_probe(struct platform_device *pdev)
 	chip->gc.parent = &pdev->dev;
 	chip->gc.label = "stp-xway";
 	chip->gc.direction_output = xway_stp_dir_out;
+	chip->gc.get = xway_stp_get;
 	chip->gc.set = xway_stp_set;
 	chip->gc.request = xway_stp_request;
 	chip->gc.base = -1;
-- 
cgit v1.2.3


From 98aef8e777544ccf015fd588ecd69d780d672bc8 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 31 May 2018 08:06:23 +0200
Subject: gpio: rc5t583: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-rc5t583.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-rc5t583.c b/drivers/gpio/gpio-rc5t583.c
index 3b4dc1a9a68d..a499c633a6c5 100644
--- a/drivers/gpio/gpio-rc5t583.c
+++ b/drivers/gpio/gpio-rc5t583.c
@@ -25,7 +25,7 @@
 #include <linux/slab.h>
 #include <linux/platform_device.h>
 #include <linux/device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/mfd/rc5t583.h>
 
 struct rc5t583_gpio {
-- 
cgit v1.2.3


From 4b1d8007987a85b9f4264905fdd6d76a3cc0b001 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 31 May 2018 08:08:13 +0200
Subject: gpio: rcar: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-rcar.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 350390c0b290..2c9a4fc92dc6 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
-- 
cgit v1.2.3


From 05467e54998be15a35c20e0605315fec309b6a5b Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 09:46:15 +0200
Subject: gpio: rdc321x: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-rdc321x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-rdc321x.c b/drivers/gpio/gpio-rdc321x.c
index cbf0f9e6465b..2938217566d3 100644
--- a/drivers/gpio/gpio-rdc321x.c
+++ b/drivers/gpio/gpio-rdc321x.c
@@ -25,7 +25,7 @@
 #include <linux/spinlock.h>
 #include <linux/platform_device.h>
 #include <linux/pci.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/mfd/rdc321x.h>
 #include <linux/slab.h>
 
-- 
cgit v1.2.3


From 827fb6af6664b614d70330f1ee96d0fb02da3504 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 09:48:03 +0200
Subject: gpio: sa1100: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sa1100.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index 249f433aa62d..986eb3b231ac 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -7,7 +7,7 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/io.h>
-- 
cgit v1.2.3


From 4c1abc84f482706f033113665faa062852bd97da Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 09:49:25 +0200
Subject: gpio: sch: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Cc: Denis Turischev <denis.turischev@compulab.co.il>
Cc: Daniel Krueger <daniel.krueger@systec-electronic.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sch.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index 545004445846..26e9b1cd2c78 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -26,8 +26,7 @@
 #include <linux/acpi.h>
 #include <linux/platform_device.h>
 #include <linux/pci_ids.h>
-
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 
 #define GEN	0x00
 #define GIO	0x04
-- 
cgit v1.2.3


From d8e764c2cc451452f07e4f35a3e83df9decf7f99 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 10:39:31 +0200
Subject: gpio: sch: Implement .get_direction()

It's pretty simple to implement the .get_direction() for this
chip, so let's just do it.

Cc: Denis Turischev <denis.turischev@compulab.co.il>
Cc: Daniel Krueger <daniel.krueger@systec-electronic.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sch.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index 26e9b1cd2c78..e9878f6ede67 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -137,6 +137,13 @@ static int sch_gpio_direction_out(struct gpio_chip *gc, unsigned gpio_num,
 	return 0;
 }
 
+static int sch_gpio_get_direction(struct gpio_chip *gc, unsigned gpio_num)
+{
+	struct sch_gpio *sch = gpiochip_get_data(gc);
+
+	return sch_gpio_reg_get(sch, gpio_num, GIO);
+}
+
 static const struct gpio_chip sch_gpio_chip = {
 	.label			= "sch_gpio",
 	.owner			= THIS_MODULE,
@@ -144,6 +151,7 @@ static const struct gpio_chip sch_gpio_chip = {
 	.get			= sch_gpio_get,
 	.direction_output	= sch_gpio_direction_out,
 	.set			= sch_gpio_set,
+	.get_direction		= sch_gpio_get_direction,
 };
 
 static int sch_gpio_probe(struct platform_device *pdev)
-- 
cgit v1.2.3


From 30467c19e456ac3503164248131ec0ea57852abf Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 10:42:01 +0200
Subject: gpio: sch311x: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Cc: Bruno Randolf <br1@einfach.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sch311x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index b96990c262a1..8bc2bf45e5da 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -17,7 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/bitops.h>
 #include <linux/io.h>
 
-- 
cgit v1.2.3


From f9e03b0ef10ce5040714783a09cf12df26bcb3d7 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 10:47:28 +0200
Subject: gpio: sch311x: Implement .get_direction()

It's pretty simple to implement the .get_direction() for this
chip, so let's just do it.

Cc: Bruno Randolf <br1@einfach.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sch311x.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index 8bc2bf45e5da..ed64f7fa23b1 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -221,6 +221,18 @@ static int sch311x_gpio_direction_out(struct gpio_chip *chip, unsigned offset,
 	return 0;
 }
 
+static int sch311x_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
+{
+	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	unsigned char data;
+
+	spin_lock(&block->lock);
+	data = inb(block->runtime_reg + block->config_regs[offset]);
+	spin_unlock(&block->lock);
+
+	return !!(data & SCH311X_GPIO_CONF_IN);
+}
+
 static int sch311x_gpio_probe(struct platform_device *pdev)
 {
 	struct sch311x_pdev_data *pdata = dev_get_platdata(&pdev->dev);
@@ -253,6 +265,7 @@ static int sch311x_gpio_probe(struct platform_device *pdev)
 		block->chip.free = sch311x_gpio_free;
 		block->chip.direction_input = sch311x_gpio_direction_in;
 		block->chip.direction_output = sch311x_gpio_direction_out;
+		block->chip.get_direction = sch311x_gpio_get_direction;
 		block->chip.get = sch311x_gpio_get;
 		block->chip.set = sch311x_gpio_set;
 		block->chip.ngpio = 8;
-- 
cgit v1.2.3


From 4a2398d7211f8f750b717ce4a2b0d117385f2a4a Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 10:52:07 +0200
Subject: gpio: sch311x: Use RMW to change direction

Bit 0 in the config register obviously controls the direction
of the GPIO so instead of hammering 0x0/0x1 into that register,
use read-modify-write so that we can also alter the other bits
in the register.

Cc: Bruno Randolf <br1@einfach.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sch311x.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index ed64f7fa23b1..faf44178f97b 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -23,10 +23,9 @@
 
 #define DRV_NAME			"gpio-sch311x"
 
-#define SCH311X_GPIO_CONF_OUT		0x00
-#define SCH311X_GPIO_CONF_IN		0x01
-#define SCH311X_GPIO_CONF_INVERT	0x02
-#define SCH311X_GPIO_CONF_OPEN_DRAIN	0x80
+#define SCH311X_GPIO_CONF_DIR		BIT(0)
+#define SCH311X_GPIO_CONF_INVERT	BIT(1)
+#define SCH311X_GPIO_CONF_OPEN_DRAIN	BIT(7)
 
 #define SIO_CONFIG_KEY_ENTER		0x55
 #define SIO_CONFIG_KEY_EXIT		0xaa
@@ -196,10 +195,12 @@ static void sch311x_gpio_set(struct gpio_chip *chip, unsigned offset,
 static int sch311x_gpio_direction_in(struct gpio_chip *chip, unsigned offset)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	unsigned char data;
 
 	spin_lock(&block->lock);
-	outb(SCH311X_GPIO_CONF_IN, block->runtime_reg +
-	     block->config_regs[offset]);
+	data = inb(block->runtime_reg + block->config_regs[offset]);
+	data |= SCH311X_GPIO_CONF_DIR;
+	outb(data, block->runtime_reg + block->config_regs[offset]);
 	spin_unlock(&block->lock);
 
 	return 0;
@@ -209,12 +210,13 @@ static int sch311x_gpio_direction_out(struct gpio_chip *chip, unsigned offset,
 				      int value)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	unsigned char data;
 
 	spin_lock(&block->lock);
 
-	outb(SCH311X_GPIO_CONF_OUT, block->runtime_reg +
-	     block->config_regs[offset]);
-
+	data = inb(block->runtime_reg + block->config_regs[offset]);
+	data &= ~SCH311X_GPIO_CONF_DIR;
+	outb(data, block->runtime_reg + block->config_regs[offset]);
 	__sch311x_gpio_set(block, offset, value);
 
 	spin_unlock(&block->lock);
@@ -230,7 +232,7 @@ static int sch311x_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 	data = inb(block->runtime_reg + block->config_regs[offset]);
 	spin_unlock(&block->lock);
 
-	return !!(data & SCH311X_GPIO_CONF_IN);
+	return !!(data & SCH311X_GPIO_CONF_DIR);
 }
 
 static int sch311x_gpio_probe(struct platform_device *pdev)
-- 
cgit v1.2.3


From 4455a82a400ba462db8abb642c670555d505bccc Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:00:44 +0200
Subject: gpio: sch311x: Implement open drain support

The chip has a bit for controlling open drain, and it is
easy to implement the callback to support open drain when
needed, so let's implement it.

Cc: Bruno Randolf <br1@einfach.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sch311x.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index faf44178f97b..1d2af9f97a91 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -235,6 +235,34 @@ static int sch311x_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 	return !!(data & SCH311X_GPIO_CONF_DIR);
 }
 
+static int sch311x_gpio_set_config(struct gpio_chip *chip, unsigned offset,
+				   unsigned long config)
+{
+	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
+	enum pin_config_param param = pinconf_to_config_param(config);
+	unsigned char data;
+
+	switch (param) {
+	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
+		spin_lock(&block->lock);
+		data = inb(block->runtime_reg + block->config_regs[offset]);
+		data |= SCH311X_GPIO_CONF_OPEN_DRAIN;
+		outb(data, block->runtime_reg + block->config_regs[offset]);
+		spin_unlock(&block->lock);
+		return 0;
+	case PIN_CONFIG_DRIVE_PUSH_PULL:
+		spin_lock(&block->lock);
+		data = inb(block->runtime_reg + block->config_regs[offset]);
+		data &= ~SCH311X_GPIO_CONF_OPEN_DRAIN;
+		outb(data, block->runtime_reg + block->config_regs[offset]);
+		spin_unlock(&block->lock);
+		return 0;
+	default:
+		break;
+	}
+	return -ENOTSUPP;
+}
+
 static int sch311x_gpio_probe(struct platform_device *pdev)
 {
 	struct sch311x_pdev_data *pdata = dev_get_platdata(&pdev->dev);
@@ -268,6 +296,7 @@ static int sch311x_gpio_probe(struct platform_device *pdev)
 		block->chip.direction_input = sch311x_gpio_direction_in;
 		block->chip.direction_output = sch311x_gpio_direction_out;
 		block->chip.get_direction = sch311x_gpio_get_direction;
+		block->chip.set_config = sch311x_gpio_set_config;
 		block->chip.get = sch311x_gpio_get;
 		block->chip.set = sch311x_gpio_set;
 		block->chip.ngpio = 8;
-- 
cgit v1.2.3


From eb452a84ece6b84e22c53abdd49ff018d189ae8a Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:03:22 +0200
Subject: gpio: sch311x: Replace unsigned char with u8

This purely syntactic change switches unsigned char to
u8 in the driver.

Cc: Bruno Randolf <br1@einfach.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sch311x.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index 1d2af9f97a91..5497f0a88cf0 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -162,7 +162,7 @@ static void sch311x_gpio_free(struct gpio_chip *chip, unsigned offset)
 static int sch311x_gpio_get(struct gpio_chip *chip, unsigned offset)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
-	unsigned char data;
+	u8 data;
 
 	spin_lock(&block->lock);
 	data = inb(block->runtime_reg + block->data_reg);
@@ -174,7 +174,7 @@ static int sch311x_gpio_get(struct gpio_chip *chip, unsigned offset)
 static void __sch311x_gpio_set(struct sch311x_gpio_block *block,
 			       unsigned offset, int value)
 {
-	unsigned char data = inb(block->runtime_reg + block->data_reg);
+	u8 data = inb(block->runtime_reg + block->data_reg);
 	if (value)
 		data |= BIT(offset);
 	else
@@ -195,7 +195,7 @@ static void sch311x_gpio_set(struct gpio_chip *chip, unsigned offset,
 static int sch311x_gpio_direction_in(struct gpio_chip *chip, unsigned offset)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
-	unsigned char data;
+	u8 data;
 
 	spin_lock(&block->lock);
 	data = inb(block->runtime_reg + block->config_regs[offset]);
@@ -210,7 +210,7 @@ static int sch311x_gpio_direction_out(struct gpio_chip *chip, unsigned offset,
 				      int value)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
-	unsigned char data;
+	u8 data;
 
 	spin_lock(&block->lock);
 
@@ -226,7 +226,7 @@ static int sch311x_gpio_direction_out(struct gpio_chip *chip, unsigned offset,
 static int sch311x_gpio_get_direction(struct gpio_chip *chip, unsigned offset)
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
-	unsigned char data;
+	u8 data;
 
 	spin_lock(&block->lock);
 	data = inb(block->runtime_reg + block->config_regs[offset]);
@@ -240,7 +240,7 @@ static int sch311x_gpio_set_config(struct gpio_chip *chip, unsigned offset,
 {
 	struct sch311x_gpio_block *block = gpiochip_get_data(chip);
 	enum pin_config_param param = pinconf_to_config_param(config);
-	unsigned char data;
+	u8 data;
 
 	switch (param) {
 	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
@@ -353,7 +353,7 @@ static int __init sch311x_detect(int sio_config_port, unsigned short *addr)
 {
 	int err = 0, reg;
 	unsigned short base_addr;
-	unsigned char dev_id;
+	u8 dev_id;
 
 	err = sch311x_sio_enter(sio_config_port);
 	if (err)
-- 
cgit v1.2.3


From 9fc18cc54add2e535c0e265a967f5e9075e22f73 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:07:02 +0200
Subject: gpio: spear-spics: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-spear-spics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-spear-spics.c b/drivers/gpio/gpio-spear-spics.c
index 22267479ba68..ee3039f091f4 100644
--- a/drivers/gpio/gpio-spear-spics.c
+++ b/drivers/gpio/gpio-spear-spics.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/io.h>
 #include <linux/init.h>
 #include <linux/of.h>
-- 
cgit v1.2.3


From 25fc1778b9ed29e75ef8b30c7827e61b444b8bce Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:09:55 +0200
Subject: gpio: sta2x11: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sta2x11.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c
index 407359da08f9..16e7f18f8f42 100644
--- a/drivers/gpio/gpio-sta2x11.c
+++ b/drivers/gpio/gpio-sta2x11.c
@@ -23,7 +23,7 @@
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
-- 
cgit v1.2.3


From 24dcfd8437b257a187a1295eb62f3f49c72b025f Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:13:03 +0200
Subject: gpio: sta2x11: Use BIT() macro

This removes the custom implementation of the BIT() macro
and inlines all calls to the helper.

Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sta2x11.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c
index 16e7f18f8f42..4af90968e838 100644
--- a/drivers/gpio/gpio-sta2x11.c
+++ b/drivers/gpio/gpio-sta2x11.c
@@ -24,6 +24,7 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/gpio/driver.h>
+#include <linux/bitops.h>
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/pci.h>
@@ -63,11 +64,6 @@ static inline struct gsta_regs __iomem *__regs(struct gsta_gpio *chip, int nr)
 	return chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 }
 
-static inline u32 __bit(int nr)
-{
-	return 1U << (nr % GSTA_GPIO_PER_BLOCK);
-}
-
 /*
  * gpio methods
  */
@@ -76,7 +72,7 @@ static void gsta_gpio_set(struct gpio_chip *gpio, unsigned nr, int val)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
 	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	if (val)
 		writel(bit, &regs->dats);
@@ -88,7 +84,7 @@ static int gsta_gpio_get(struct gpio_chip *gpio, unsigned nr)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
 	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	return !!(readl(&regs->dat) & bit);
 }
@@ -98,7 +94,7 @@ static int gsta_gpio_direction_output(struct gpio_chip *gpio, unsigned nr,
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
 	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	writel(bit, &regs->dirs);
 	/* Data register after direction, otherwise pullup/down is selected */
@@ -113,7 +109,7 @@ static int gsta_gpio_direction_input(struct gpio_chip *gpio, unsigned nr)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
 	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	writel(bit, &regs->dirc);
 	return 0;
@@ -167,7 +163,7 @@ static void gsta_set_config(struct gsta_gpio *chip, int nr, unsigned cfg)
 {
 	struct gsta_regs __iomem *regs = __regs(chip, nr);
 	unsigned long flags;
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	int err = 0;
 
@@ -235,7 +231,7 @@ static void gsta_irq_disable(struct irq_data *data)
 	struct gsta_gpio *chip = gc->private;
 	int nr = data->irq - chip->irq_base;
 	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	unsigned long flags;
 
@@ -258,7 +254,7 @@ static void gsta_irq_enable(struct irq_data *data)
 	struct gsta_gpio *chip = gc->private;
 	int nr = data->irq - chip->irq_base;
 	struct gsta_regs __iomem *regs = __regs(chip, nr);
-	u32 bit = __bit(nr);
+	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	int type;
 	unsigned long flags;
-- 
cgit v1.2.3


From aadf77c88d2f8f1ffcf75c1e985da1a5cb66c36a Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:27:34 +0200
Subject: gpio: sta2x11: Inline regs macro

I don't like the __namespace and this is simple enough to just
inline at all sites.

Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Acked-by: Alessandro Rubini <rubini@gnudd.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-sta2x11.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/gpio/gpio-sta2x11.c b/drivers/gpio/gpio-sta2x11.c
index 4af90968e838..2283c869ad5d 100644
--- a/drivers/gpio/gpio-sta2x11.c
+++ b/drivers/gpio/gpio-sta2x11.c
@@ -59,11 +59,6 @@ struct gsta_gpio {
 	unsigned			irq_type[GSTA_NR_GPIO];
 };
 
-static inline struct gsta_regs __iomem *__regs(struct gsta_gpio *chip, int nr)
-{
-	return chip->regs[nr / GSTA_GPIO_PER_BLOCK];
-}
-
 /*
  * gpio methods
  */
@@ -71,7 +66,7 @@ static inline struct gsta_regs __iomem *__regs(struct gsta_gpio *chip, int nr)
 static void gsta_gpio_set(struct gpio_chip *gpio, unsigned nr, int val)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	if (val)
@@ -83,7 +78,7 @@ static void gsta_gpio_set(struct gpio_chip *gpio, unsigned nr, int val)
 static int gsta_gpio_get(struct gpio_chip *gpio, unsigned nr)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	return !!(readl(&regs->dat) & bit);
@@ -93,7 +88,7 @@ static int gsta_gpio_direction_output(struct gpio_chip *gpio, unsigned nr,
 				      int val)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	writel(bit, &regs->dirs);
@@ -108,7 +103,7 @@ static int gsta_gpio_direction_output(struct gpio_chip *gpio, unsigned nr,
 static int gsta_gpio_direction_input(struct gpio_chip *gpio, unsigned nr)
 {
 	struct gsta_gpio *chip = gpiochip_get_data(gpio);
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 
 	writel(bit, &regs->dirc);
@@ -161,7 +156,7 @@ static void gsta_gpio_setup(struct gsta_gpio *chip) /* called from probe */
  */
 static void gsta_set_config(struct gsta_gpio *chip, int nr, unsigned cfg)
 {
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	unsigned long flags;
 	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
@@ -230,7 +225,7 @@ static void gsta_irq_disable(struct irq_data *data)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
 	struct gsta_gpio *chip = gc->private;
 	int nr = data->irq - chip->irq_base;
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	unsigned long flags;
@@ -253,7 +248,7 @@ static void gsta_irq_enable(struct irq_data *data)
 	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(data);
 	struct gsta_gpio *chip = gc->private;
 	int nr = data->irq - chip->irq_base;
-	struct gsta_regs __iomem *regs = __regs(chip, nr);
+	struct gsta_regs __iomem *regs = chip->regs[nr / GSTA_GPIO_PER_BLOCK];
 	u32 bit = BIT(nr % GSTA_GPIO_PER_BLOCK);
 	u32 val;
 	int type;
-- 
cgit v1.2.3


From ecac6e602ccd8ace3b5ec01ed8f8bf0350e30b92 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:30:48 +0200
Subject: gpio: stmpe: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-stmpe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 8d6a5a7e612d..65a2315f1673 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -8,7 +8,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/interrupt.h>
 #include <linux/of.h>
 #include <linux/mfd/stmpe.h>
-- 
cgit v1.2.3


From 97a48fcd628e5bf2a34dd23c08f646253c8767ec Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 27 Jun 2018 11:37:23 +0200
Subject: gpio: stp-xway: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-stp-xway.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c
index 63c708c3f3ae..19972084c45b 100644
--- a/drivers/gpio/gpio-stp-xway.c
+++ b/drivers/gpio/gpio-stp-xway.c
@@ -13,9 +13,8 @@
 #include <linux/types.h>
 #include <linux/of_platform.h>
 #include <linux/mutex.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/io.h>
-#include <linux/of_gpio.h>
 #include <linux/clk.h>
 #include <linux/err.h>
 
-- 
cgit v1.2.3


From 122d00f778b370124ec38bb59b2ac7622d0c6943 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 28 Jun 2018 08:35:46 +0200
Subject: gpio: syscon: Include the right header

This is a GPIO driver, include only <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-syscon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index 8b0a69c5ba88..d40cabd15e9e 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/err.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-- 
cgit v1.2.3


From 72b38caf7b7568ebc167fdd4ec5fa1daa113d08b Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Thu, 21 Jun 2018 16:38:46 +0300
Subject: gpio: pca953x: suppress interrupts warning when not applicable

Don't warn about missing interrupts support when the parent interrupt is
not defined. Enabling interrupts support would not make it work anyway.

Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-pca953x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index c55ad157e820..023a32cfac42 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -708,7 +708,7 @@ static int pca953x_irq_setup(struct pca953x_chip *chip,
 {
 	struct i2c_client *client = chip->client;
 
-	if (irq_base != -1 && (chip->driver_data & PCA_INT))
+	if (client->irq && irq_base != -1 && (chip->driver_data & PCA_INT))
 		dev_warn(&client->dev, "interrupt support not compiled in\n");
 
 	return 0;
-- 
cgit v1.2.3


From 23ee0f192033ac6742fc179699d91336a000aef5 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 2 Jul 2018 13:47:08 +0100
Subject: pinctrl: actions: fix unsigned less than zero comparison

The check to see if platform_get_irq failed is performed on the
unsigned value of pctrl->irq[i] and the check is never true because
an unsigned cannot be less than zero.  Fix this by assinging the
signed int ret to the return of platform_get_irq and checking ret
instead.

Detected by CoverityScan, CID#1470247 ("Unsigned comparison against 0")

Fixes: 6c5d0736e9c0 ("pinctrl: actions: Add interrupt support for OWL S900 SoC")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/actions/pinctrl-owl.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/actions/pinctrl-owl.c b/drivers/pinctrl/actions/pinctrl-owl.c
index ce032d71dad5..6b89b2b41316 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.c
+++ b/drivers/pinctrl/actions/pinctrl-owl.c
@@ -1026,11 +1026,10 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 	}
 
 	for (i = 0; i < pctrl->num_irq ; i++) {
-		pctrl->irq[i] = platform_get_irq(pdev, i);
-		if (pctrl->irq[i] < 0) {
-			ret = pctrl->irq[i];
+		ret = platform_get_irq(pdev, i);
+		if (ret < 0)
 			goto err_exit;
-		}
+		pctrl->irq[i] = ret;
 	}
 
 	ret = owl_gpio_init(pctrl);
-- 
cgit v1.2.3


From 44ddf559d5792b2bffcd44febf9b7b55b03e06b4 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 29 Jun 2018 14:11:16 +1000
Subject: gpio: aspeed: Rework register type accessors

Use a single accessor function for all register types instead
of several spread around. This will make it easier/cleaner
to introduce new registers and keep the mechanism in one
place.

The big switch/case is optimized at compile time since the
switch value is a constant.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Joel Stanley <joel@jms.id.au>
Reviewed-by: Andrew Jeffery <andrew@aj.id.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-aspeed.c | 118 ++++++++++++++++++++++++++-------------------
 1 file changed, 69 insertions(+), 49 deletions(-)

diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index b31ae16170e7..c9baeeb7f0cc 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -127,12 +127,21 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 };
 
-#define GPIO_BANK(x)	((x) >> 5)
-#define GPIO_OFFSET(x)	((x) & 0x1f)
-#define GPIO_BIT(x)	BIT(GPIO_OFFSET(x))
+enum aspeed_gpio_reg {
+	reg_val,
+	reg_dir,
+	reg_irq_enable,
+	reg_irq_type0,
+	reg_irq_type1,
+	reg_irq_type2,
+	reg_irq_status,
+	reg_debounce_sel1,
+	reg_debounce_sel2,
+	reg_tolerance,
+};
 
-#define GPIO_DATA	0x00
-#define GPIO_DIR	0x04
+#define GPIO_VAL_VALUE	0x00
+#define GPIO_VAL_DIR	0x04
 
 #define GPIO_IRQ_ENABLE	0x00
 #define GPIO_IRQ_TYPE0	0x04
@@ -143,6 +152,40 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 #define GPIO_DEBOUNCE_SEL1 0x00
 #define GPIO_DEBOUNCE_SEL2 0x04
 
+/* This will be resolved at compile time */
+static inline void __iomem *bank_reg(struct aspeed_gpio *gpio,
+				     const struct aspeed_gpio_bank *bank,
+				     const enum aspeed_gpio_reg reg)
+{
+	switch (reg) {
+	case reg_val:
+		return gpio->base + bank->val_regs + GPIO_VAL_VALUE;
+	case reg_dir:
+		return gpio->base + bank->val_regs + GPIO_VAL_DIR;
+	case reg_irq_enable:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_ENABLE;
+	case reg_irq_type0:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_TYPE0;
+	case reg_irq_type1:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_TYPE1;
+	case reg_irq_type2:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_TYPE2;
+	case reg_irq_status:
+		return gpio->base + bank->irq_regs + GPIO_IRQ_STATUS;
+	case reg_debounce_sel1:
+		return gpio->base + bank->debounce_regs + GPIO_DEBOUNCE_SEL1;
+	case reg_debounce_sel2:
+		return gpio->base + bank->debounce_regs + GPIO_DEBOUNCE_SEL2;
+	case reg_tolerance:
+		return gpio->base + bank->tolerance_regs;
+	}
+	BUG_ON(1);
+}
+
+#define GPIO_BANK(x)	((x) >> 5)
+#define GPIO_OFFSET(x)	((x) & 0x1f)
+#define GPIO_BIT(x)	BIT(GPIO_OFFSET(x))
+
 #define _GPIO_SET_DEBOUNCE(t, o, i) ((!!((t) & BIT(i))) << GPIO_OFFSET(o))
 #define GPIO_SET_DEBOUNCE1(t, o) _GPIO_SET_DEBOUNCE(t, o, 1)
 #define GPIO_SET_DEBOUNCE2(t, o) _GPIO_SET_DEBOUNCE(t, o, 0)
@@ -201,27 +244,12 @@ static inline bool have_output(struct aspeed_gpio *gpio, unsigned int offset)
 	return !props || (props->output & GPIO_BIT(offset));
 }
 
-static void __iomem *bank_val_reg(struct aspeed_gpio *gpio,
-		const struct aspeed_gpio_bank *bank,
-		unsigned int reg)
-{
-	return gpio->base + bank->val_regs + reg;
-}
-
-static void __iomem *bank_irq_reg(struct aspeed_gpio *gpio,
-		const struct aspeed_gpio_bank *bank,
-		unsigned int reg)
-{
-	return gpio->base + bank->irq_regs + reg;
-}
-
 static int aspeed_gpio_get(struct gpio_chip *gc, unsigned int offset)
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	const struct aspeed_gpio_bank *bank = to_bank(offset);
 
-	return !!(ioread32(bank_val_reg(gpio, bank, GPIO_DATA))
-			& GPIO_BIT(offset));
+	return !!(ioread32(bank_reg(gpio, bank, reg_val)) & GPIO_BIT(offset));
 }
 
 static void __aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset,
@@ -232,7 +260,7 @@ static void __aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset,
 	void __iomem *addr;
 	u32 reg;
 
-	addr = bank_val_reg(gpio, bank, GPIO_DATA);
+	addr = bank_reg(gpio, bank, reg_val);
 	reg = gpio->dcache[GPIO_BANK(offset)];
 
 	if (val)
@@ -269,8 +297,8 @@ static int aspeed_gpio_dir_in(struct gpio_chip *gc, unsigned int offset)
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
-	reg = ioread32(bank_val_reg(gpio, bank, GPIO_DIR));
-	iowrite32(reg & ~GPIO_BIT(offset), bank_val_reg(gpio, bank, GPIO_DIR));
+	reg = ioread32(bank_reg(gpio, bank, reg_dir));
+	iowrite32(reg & ~GPIO_BIT(offset), bank_reg(gpio, bank, reg_dir));
 
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
@@ -291,8 +319,8 @@ static int aspeed_gpio_dir_out(struct gpio_chip *gc,
 	spin_lock_irqsave(&gpio->lock, flags);
 
 	__aspeed_gpio_set(gc, offset, val);
-	reg = ioread32(bank_val_reg(gpio, bank, GPIO_DIR));
-	iowrite32(reg | GPIO_BIT(offset), bank_val_reg(gpio, bank, GPIO_DIR));
+	reg = ioread32(bank_reg(gpio, bank, reg_dir));
+	iowrite32(reg | GPIO_BIT(offset), bank_reg(gpio, bank, reg_dir));
 
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
@@ -314,7 +342,7 @@ static int aspeed_gpio_get_direction(struct gpio_chip *gc, unsigned int offset)
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
-	val = ioread32(bank_val_reg(gpio, bank, GPIO_DIR)) & GPIO_BIT(offset);
+	val = ioread32(bank_reg(gpio, bank, reg_dir)) & GPIO_BIT(offset);
 
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
@@ -358,7 +386,7 @@ static void aspeed_gpio_irq_ack(struct irq_data *d)
 	if (rc)
 		return;
 
-	status_addr = bank_irq_reg(gpio, bank, GPIO_IRQ_STATUS);
+	status_addr = bank_reg(gpio, bank, reg_irq_status);
 
 	spin_lock_irqsave(&gpio->lock, flags);
 	iowrite32(bit, status_addr);
@@ -378,7 +406,7 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set)
 	if (rc)
 		return;
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_ENABLE);
+	addr = bank_reg(gpio, bank, reg_irq_enable);
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
@@ -442,17 +470,17 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type)
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_TYPE0);
+	addr = bank_reg(gpio, bank, reg_irq_type0);
 	reg = ioread32(addr);
 	reg = (reg & ~bit) | type0;
 	iowrite32(reg, addr);
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_TYPE1);
+	addr = bank_reg(gpio, bank, reg_irq_type1);
 	reg = ioread32(addr);
 	reg = (reg & ~bit) | type1;
 	iowrite32(reg, addr);
 
-	addr = bank_irq_reg(gpio, bank, GPIO_IRQ_TYPE2);
+	addr = bank_reg(gpio, bank, reg_irq_type2);
 	reg = ioread32(addr);
 	reg = (reg & ~bit) | type2;
 	iowrite32(reg, addr);
@@ -477,7 +505,7 @@ static void aspeed_gpio_irq_handler(struct irq_desc *desc)
 	for (i = 0; i < ARRAY_SIZE(aspeed_gpio_banks); i++) {
 		const struct aspeed_gpio_bank *bank = &aspeed_gpio_banks[i];
 
-		reg = ioread32(bank_irq_reg(data, bank, GPIO_IRQ_STATUS));
+		reg = ioread32(bank_reg(data, bank, reg_irq_status));
 
 		for_each_set_bit(p, &reg, 32) {
 			girq = irq_find_mapping(gc->irq.domain, i * 32 + p);
@@ -549,21 +577,21 @@ static int aspeed_gpio_reset_tolerance(struct gpio_chip *chip,
 					unsigned int offset, bool enable)
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
-	const struct aspeed_gpio_bank *bank;
 	unsigned long flags;
+	void __iomem *treg;
 	u32 val;
 
-	bank = to_bank(offset);
+	treg = bank_reg(gpio, to_bank(offset), reg_tolerance);
 
 	spin_lock_irqsave(&gpio->lock, flags);
-	val = readl(gpio->base + bank->tolerance_regs);
+	val = readl(treg);
 
 	if (enable)
 		val |= GPIO_BIT(offset);
 	else
 		val &= ~GPIO_BIT(offset);
 
-	writel(val, gpio->base + bank->tolerance_regs);
+	writel(val, treg);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
 	return 0;
@@ -582,13 +610,6 @@ static void aspeed_gpio_free(struct gpio_chip *chip, unsigned int offset)
 	pinctrl_gpio_free(chip->base + offset);
 }
 
-static inline void __iomem *bank_debounce_reg(struct aspeed_gpio *gpio,
-		const struct aspeed_gpio_bank *bank,
-		unsigned int reg)
-{
-	return gpio->base + bank->debounce_regs + reg;
-}
-
 static int usecs_to_cycles(struct aspeed_gpio *gpio, unsigned long usecs,
 		u32 *cycles)
 {
@@ -666,11 +687,11 @@ static void configure_timer(struct aspeed_gpio *gpio, unsigned int offset,
 	void __iomem *addr;
 	u32 val;
 
-	addr = bank_debounce_reg(gpio, bank, GPIO_DEBOUNCE_SEL1);
+	addr = bank_reg(gpio, bank, reg_debounce_sel1);
 	val = ioread32(addr);
 	iowrite32((val & ~mask) | GPIO_SET_DEBOUNCE1(timer, offset), addr);
 
-	addr = bank_debounce_reg(gpio, bank, GPIO_DEBOUNCE_SEL2);
+	addr = bank_reg(gpio, bank, reg_debounce_sel2);
 	val = ioread32(addr);
 	iowrite32((val & ~mask) | GPIO_SET_DEBOUNCE2(timer, offset), addr);
 }
@@ -904,9 +925,8 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev)
 
 	/* Populate it with initial values read from the HW */
 	for (i = 0; i < banks; i++) {
-		const struct aspeed_gpio_bank *bank = &aspeed_gpio_banks[i];
-		gpio->dcache[i] = ioread32(gpio->base + bank->val_regs +
-					   GPIO_DATA);
+		void __iomem *addr = bank_reg(gpio, &aspeed_gpio_banks[i], reg_val);
+		gpio->dcache[i] = ioread32(addr);
 	}
 
 	rc = devm_gpiochip_add_data(&pdev->dev, &gpio->chip, gpio);
-- 
cgit v1.2.3


From c67dda88cc5da58c5a63083e0405fe93e2476bb7 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 29 Jun 2018 14:11:17 +1000
Subject: gpio: aspeed: Add "Read Data" register to read the write latch

The Aspeed GPIO hardware has a quirk: the value register, for an
output GPIO, doesn't contain the last value written (the write
latch content) but the sampled input value.

This means that when reading back shortly after writing, you can
get an incorrect value as the input value is delayed by a few
synchronizers.

The HW supports a separate read-only register "Data Read Register"
which allows you to read the write latch instead.

This adds the definition for it, and uses it for the initial
population of the GPIO value cache. It will be used more in
subsequent patches.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Joel Stanley <joel@jms.id.au>
Reviewed-by: Andrew Jeffery <andrew@aj.id.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-aspeed.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index c9baeeb7f0cc..a5ded50c6db0 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -59,18 +59,33 @@ struct aspeed_gpio {
 };
 
 struct aspeed_gpio_bank {
-	uint16_t	val_regs;
+	uint16_t	val_regs;	/* +0: Rd: read input value, Wr: set write latch
+					 * +4: Rd/Wr: Direction (0=in, 1=out)
+					 */
+	uint16_t	rdata_reg;	/*     Rd: read write latch, Wr: <none>  */
 	uint16_t	irq_regs;
 	uint16_t	debounce_regs;
 	uint16_t	tolerance_regs;
 	const char	names[4][3];
 };
 
+/*
+ * Note: The "value" register returns the input value sampled on the
+ *       line even when the GPIO is configured as an output. Since
+ *       that input goes through synchronizers, writing, then reading
+ *       back may not return the written value right away.
+ *
+ *       The "rdata" register returns the content of the write latch
+ *       and thus can be used to read back what was last written
+ *       reliably.
+ */
+
 static const int debounce_timers[4] = { 0x00, 0x50, 0x54, 0x58 };
 
 static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	{
 		.val_regs = 0x0000,
+		.rdata_reg = 0x00c0,
 		.irq_regs = 0x0008,
 		.debounce_regs = 0x0040,
 		.tolerance_regs = 0x001c,
@@ -78,6 +93,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 	{
 		.val_regs = 0x0020,
+		.rdata_reg = 0x00c4,
 		.irq_regs = 0x0028,
 		.debounce_regs = 0x0048,
 		.tolerance_regs = 0x003c,
@@ -85,6 +101,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 	{
 		.val_regs = 0x0070,
+		.rdata_reg = 0x00c8,
 		.irq_regs = 0x0098,
 		.debounce_regs = 0x00b0,
 		.tolerance_regs = 0x00ac,
@@ -92,6 +109,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 	{
 		.val_regs = 0x0078,
+		.rdata_reg = 0x00cc,
 		.irq_regs = 0x00e8,
 		.debounce_regs = 0x0100,
 		.tolerance_regs = 0x00fc,
@@ -99,6 +117,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 	{
 		.val_regs = 0x0080,
+		.rdata_reg = 0x00d0,
 		.irq_regs = 0x0118,
 		.debounce_regs = 0x0130,
 		.tolerance_regs = 0x012c,
@@ -106,6 +125,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 	{
 		.val_regs = 0x0088,
+		.rdata_reg = 0x00d4,
 		.irq_regs = 0x0148,
 		.debounce_regs = 0x0160,
 		.tolerance_regs = 0x015c,
@@ -113,6 +133,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 	{
 		.val_regs = 0x01E0,
+		.rdata_reg = 0x00d8,
 		.irq_regs = 0x0178,
 		.debounce_regs = 0x0190,
 		.tolerance_regs = 0x018c,
@@ -120,6 +141,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	},
 	{
 		.val_regs = 0x01e8,
+		.rdata_reg = 0x00dc,
 		.irq_regs = 0x01a8,
 		.debounce_regs = 0x01c0,
 		.tolerance_regs = 0x01bc,
@@ -129,6 +151,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 
 enum aspeed_gpio_reg {
 	reg_val,
+	reg_rdata,
 	reg_dir,
 	reg_irq_enable,
 	reg_irq_type0,
@@ -160,6 +183,8 @@ static inline void __iomem *bank_reg(struct aspeed_gpio *gpio,
 	switch (reg) {
 	case reg_val:
 		return gpio->base + bank->val_regs + GPIO_VAL_VALUE;
+	case reg_rdata:
+		return gpio->base + bank->rdata_reg;
 	case reg_dir:
 		return gpio->base + bank->val_regs + GPIO_VAL_DIR;
 	case reg_irq_enable:
@@ -925,7 +950,7 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev)
 
 	/* Populate it with initial values read from the HW */
 	for (i = 0; i < banks; i++) {
-		void __iomem *addr = bank_reg(gpio, &aspeed_gpio_banks[i], reg_val);
+		void __iomem *addr = bank_reg(gpio, &aspeed_gpio_banks[i], reg_rdata);
 		gpio->dcache[i] = ioread32(addr);
 	}
 
-- 
cgit v1.2.3


From 0f1e03c2b5a395e3eb38899a41c7e74afbc16ba0 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 29 Jun 2018 14:11:18 +1000
Subject: gpio: aspeed: Add command source registers

This adds the definitions for the command source registers
and a helper to set them.

Those registers allow to control which bus master on the
SoC is allowed to modify a given bank of GPIOs and will
be used by subsequent patches.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Joel Stanley <joel@jms.id.au>
Reviewed-by: Andrew Jeffery <andrew@aj.id.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-aspeed.c | 54 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index a5ded50c6db0..b3968f66b1d2 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -66,6 +66,7 @@ struct aspeed_gpio_bank {
 	uint16_t	irq_regs;
 	uint16_t	debounce_regs;
 	uint16_t	tolerance_regs;
+	uint16_t	cmdsrc_regs;
 	const char	names[4][3];
 };
 
@@ -89,6 +90,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x0008,
 		.debounce_regs = 0x0040,
 		.tolerance_regs = 0x001c,
+		.cmdsrc_regs = 0x0060,
 		.names = { "A", "B", "C", "D" },
 	},
 	{
@@ -97,6 +99,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x0028,
 		.debounce_regs = 0x0048,
 		.tolerance_regs = 0x003c,
+		.cmdsrc_regs = 0x0068,
 		.names = { "E", "F", "G", "H" },
 	},
 	{
@@ -105,6 +108,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x0098,
 		.debounce_regs = 0x00b0,
 		.tolerance_regs = 0x00ac,
+		.cmdsrc_regs = 0x0090,
 		.names = { "I", "J", "K", "L" },
 	},
 	{
@@ -113,6 +117,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x00e8,
 		.debounce_regs = 0x0100,
 		.tolerance_regs = 0x00fc,
+		.cmdsrc_regs = 0x00e0,
 		.names = { "M", "N", "O", "P" },
 	},
 	{
@@ -121,6 +126,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x0118,
 		.debounce_regs = 0x0130,
 		.tolerance_regs = 0x012c,
+		.cmdsrc_regs = 0x0110,
 		.names = { "Q", "R", "S", "T" },
 	},
 	{
@@ -129,6 +135,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x0148,
 		.debounce_regs = 0x0160,
 		.tolerance_regs = 0x015c,
+		.cmdsrc_regs = 0x0140,
 		.names = { "U", "V", "W", "X" },
 	},
 	{
@@ -137,6 +144,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x0178,
 		.debounce_regs = 0x0190,
 		.tolerance_regs = 0x018c,
+		.cmdsrc_regs = 0x0170,
 		.names = { "Y", "Z", "AA", "AB" },
 	},
 	{
@@ -145,6 +153,7 @@ static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 		.irq_regs = 0x01a8,
 		.debounce_regs = 0x01c0,
 		.tolerance_regs = 0x01bc,
+		.cmdsrc_regs = 0x01a0,
 		.names = { "AC", "", "", "" },
 	},
 };
@@ -161,6 +170,8 @@ enum aspeed_gpio_reg {
 	reg_debounce_sel1,
 	reg_debounce_sel2,
 	reg_tolerance,
+	reg_cmdsrc0,
+	reg_cmdsrc1,
 };
 
 #define GPIO_VAL_VALUE	0x00
@@ -175,6 +186,13 @@ enum aspeed_gpio_reg {
 #define GPIO_DEBOUNCE_SEL1 0x00
 #define GPIO_DEBOUNCE_SEL2 0x04
 
+#define GPIO_CMDSRC_0	0x00
+#define GPIO_CMDSRC_1	0x04
+#define  GPIO_CMDSRC_ARM		0
+#define  GPIO_CMDSRC_LPC		1
+#define  GPIO_CMDSRC_COLDFIRE		2
+#define  GPIO_CMDSRC_RESERVED		3
+
 /* This will be resolved at compile time */
 static inline void __iomem *bank_reg(struct aspeed_gpio *gpio,
 				     const struct aspeed_gpio_bank *bank,
@@ -203,6 +221,10 @@ static inline void __iomem *bank_reg(struct aspeed_gpio *gpio,
 		return gpio->base + bank->debounce_regs + GPIO_DEBOUNCE_SEL2;
 	case reg_tolerance:
 		return gpio->base + bank->tolerance_regs;
+	case reg_cmdsrc0:
+		return gpio->base + bank->cmdsrc_regs + GPIO_CMDSRC_0;
+	case reg_cmdsrc1:
+		return gpio->base + bank->cmdsrc_regs + GPIO_CMDSRC_1;
 	}
 	BUG_ON(1);
 }
@@ -269,6 +291,38 @@ static inline bool have_output(struct aspeed_gpio *gpio, unsigned int offset)
 	return !props || (props->output & GPIO_BIT(offset));
 }
 
+static void aspeed_gpio_change_cmd_source(struct aspeed_gpio *gpio,
+					  const struct aspeed_gpio_bank *bank,
+					  int bindex, int cmdsrc)
+{
+	void __iomem *c0 = bank_reg(gpio, bank, reg_cmdsrc0);
+	void __iomem *c1 = bank_reg(gpio, bank, reg_cmdsrc1);
+	u32 bit, reg;
+
+	/*
+	 * Each register controls 4 banks, so take the bottom 2
+	 * bits of the bank index, and use them to select the
+	 * right control bit (0, 8, 16 or 24).
+	 */
+	bit = BIT((bindex & 3) << 3);
+
+	/* Source 1 first to avoid illegal 11 combination */
+	reg = ioread32(c1);
+	if (cmdsrc & 2)
+		reg |= bit;
+	else
+		reg &= ~bit;
+	iowrite32(reg, c1);
+
+	/* Then Source 0 */
+	reg = ioread32(c0);
+	if (cmdsrc & 1)
+		reg |= bit;
+	else
+		reg &= ~bit;
+	iowrite32(reg, c0);
+}
+
 static int aspeed_gpio_get(struct gpio_chip *gc, unsigned int offset)
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
-- 
cgit v1.2.3


From a7ca13826e478f9b201eb2f9f20de0b978a82ad9 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Fri, 29 Jun 2018 14:11:19 +1000
Subject: gpio: aspeed: Add interfaces for co-processor to grab GPIOs

On the Aspeed chip, the GPIOs can be under control of the ARM
chip or of the ColdFire coprocessor. (There's a third command
source, the LPC bus, which we don't use or support yet).

The control of which master is allowed to modify a given
GPIO is per-bank (8 GPIOs).

Unfortunately, systems already exist for which we want to
use GPIOs of both sources in the same bank.

This provides an API exported by the gpio-aspeed driver
that an aspeed coprocessor driver can use to "grab" some
GPIOs for use by the coprocessor, and allow the coprocessor
driver to provide callbacks for arbitrating access.

Once at least one GPIO of a given bank has been "grabbed"
by the coprocessor, the entire bank is marked as being
under coprocessor control. It's command source is switched
to the coprocessor.

If the ARM then tries to write to a GPIO in such a marked bank,
the provided callbacks are used to request access from the
coprocessor driver, which is responsible to doing whatever
is necessary to "pause" the coprocessor or prevent it from
trying to use the GPIOs while the ARM is doing its accesses.

During that time, the command source for the bank is temporarily
switched back to the ARM.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: Joel Stanley <joel@jms.id.au>
Reviewed-by: Andrew Jeffery <andrew@aj.id.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-aspeed.c  | 251 ++++++++++++++++++++++++++++++++++++++++----
 include/linux/gpio/aspeed.h |  15 +++
 2 files changed, 246 insertions(+), 20 deletions(-)
 create mode 100644 include/linux/gpio/aspeed.h

diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index b3968f66b1d2..1e00f4045f9d 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -12,6 +12,7 @@
 #include <asm/div64.h>
 #include <linux/clk.h>
 #include <linux/gpio/driver.h>
+#include <linux/gpio/aspeed.h>
 #include <linux/hashtable.h>
 #include <linux/init.h>
 #include <linux/io.h>
@@ -22,6 +23,15 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 
+/*
+ * These two headers aren't meant to be used by GPIO drivers. We need
+ * them in order to access gpio_chip_hwgpio() which we need to implement
+ * the aspeed specific API which allows the coprocessor to request
+ * access to some GPIOs and to arbitrate between coprocessor and ARM.
+ */
+#include <linux/gpio/consumer.h>
+#include "gpiolib.h"
+
 struct aspeed_bank_props {
 	unsigned int bank;
 	u32 input;
@@ -56,6 +66,7 @@ struct aspeed_gpio {
 	struct clk *clk;
 
 	u32 *dcache;
+	u8 *cf_copro_bankmap;
 };
 
 struct aspeed_gpio_bank {
@@ -83,6 +94,9 @@ struct aspeed_gpio_bank {
 
 static const int debounce_timers[4] = { 0x00, 0x50, 0x54, 0x58 };
 
+static const struct aspeed_gpio_copro_ops *copro_ops;
+static void *copro_data;
+
 static const struct aspeed_gpio_bank aspeed_gpio_banks[] = {
 	{
 		.val_regs = 0x0000,
@@ -323,6 +337,50 @@ static void aspeed_gpio_change_cmd_source(struct aspeed_gpio *gpio,
 	iowrite32(reg, c0);
 }
 
+static bool aspeed_gpio_copro_request(struct aspeed_gpio *gpio,
+				      unsigned int offset)
+{
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+
+	if (!copro_ops || !gpio->cf_copro_bankmap)
+		return false;
+	if (!gpio->cf_copro_bankmap[offset >> 3])
+		return false;
+	if (!copro_ops->request_access)
+		return false;
+
+	/* Pause the coprocessor */
+	copro_ops->request_access(copro_data);
+
+	/* Change command source back to ARM */
+	aspeed_gpio_change_cmd_source(gpio, bank, offset >> 3, GPIO_CMDSRC_ARM);
+
+	/* Update cache */
+	gpio->dcache[GPIO_BANK(offset)] = ioread32(bank_reg(gpio, bank, reg_rdata));
+
+	return true;
+}
+
+static void aspeed_gpio_copro_release(struct aspeed_gpio *gpio,
+				      unsigned int offset)
+{
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+
+	if (!copro_ops || !gpio->cf_copro_bankmap)
+		return;
+	if (!gpio->cf_copro_bankmap[offset >> 3])
+		return;
+	if (!copro_ops->release_access)
+		return;
+
+	/* Change command source back to ColdFire */
+	aspeed_gpio_change_cmd_source(gpio, bank, offset >> 3,
+				      GPIO_CMDSRC_COLDFIRE);
+
+	/* Restart the coprocessor */
+	copro_ops->release_access(copro_data);
+}
+
 static int aspeed_gpio_get(struct gpio_chip *gc, unsigned int offset)
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
@@ -356,11 +414,15 @@ static void aspeed_gpio_set(struct gpio_chip *gc, unsigned int offset,
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	unsigned long flags;
+	bool copro;
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
 
 	__aspeed_gpio_set(gc, offset, val);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 }
 
@@ -368,7 +430,9 @@ static int aspeed_gpio_dir_in(struct gpio_chip *gc, unsigned int offset)
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	void __iomem *addr = bank_reg(gpio, bank, reg_dir);
 	unsigned long flags;
+	bool copro;
 	u32 reg;
 
 	if (!have_input(gpio, offset))
@@ -376,8 +440,13 @@ static int aspeed_gpio_dir_in(struct gpio_chip *gc, unsigned int offset)
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
-	reg = ioread32(bank_reg(gpio, bank, reg_dir));
-	iowrite32(reg & ~GPIO_BIT(offset), bank_reg(gpio, bank, reg_dir));
+	reg = ioread32(addr);
+	reg &= ~GPIO_BIT(offset);
+
+	copro = aspeed_gpio_copro_request(gpio, offset);
+	iowrite32(reg, addr);
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
@@ -389,7 +458,9 @@ static int aspeed_gpio_dir_out(struct gpio_chip *gc,
 {
 	struct aspeed_gpio *gpio = gpiochip_get_data(gc);
 	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	void __iomem *addr = bank_reg(gpio, bank, reg_dir);
 	unsigned long flags;
+	bool copro;
 	u32 reg;
 
 	if (!have_output(gpio, offset))
@@ -397,10 +468,15 @@ static int aspeed_gpio_dir_out(struct gpio_chip *gc,
 
 	spin_lock_irqsave(&gpio->lock, flags);
 
+	reg = ioread32(addr);
+	reg |= GPIO_BIT(offset);
+
+	copro = aspeed_gpio_copro_request(gpio, offset);
 	__aspeed_gpio_set(gc, offset, val);
-	reg = ioread32(bank_reg(gpio, bank, reg_dir));
-	iowrite32(reg | GPIO_BIT(offset), bank_reg(gpio, bank, reg_dir));
+	iowrite32(reg, addr);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
 	return 0;
@@ -430,24 +506,23 @@ static int aspeed_gpio_get_direction(struct gpio_chip *gc, unsigned int offset)
 }
 
 static inline int irqd_to_aspeed_gpio_data(struct irq_data *d,
-		struct aspeed_gpio **gpio,
-		const struct aspeed_gpio_bank **bank,
-		u32 *bit)
+					   struct aspeed_gpio **gpio,
+					   const struct aspeed_gpio_bank **bank,
+					   u32 *bit, int *offset)
 {
-	int offset;
 	struct aspeed_gpio *internal;
 
-	offset = irqd_to_hwirq(d);
+	*offset = irqd_to_hwirq(d);
 
 	internal = irq_data_get_irq_chip_data(d);
 
 	/* This might be a bit of a questionable place to check */
-	if (!have_irq(internal, offset))
+	if (!have_irq(internal, *offset))
 		return -ENOTSUPP;
 
 	*gpio = internal;
-	*bank = to_bank(offset);
-	*bit = GPIO_BIT(offset);
+	*bank = to_bank(*offset);
+	*bit = GPIO_BIT(*offset);
 
 	return 0;
 }
@@ -458,17 +533,23 @@ static void aspeed_gpio_irq_ack(struct irq_data *d)
 	struct aspeed_gpio *gpio;
 	unsigned long flags;
 	void __iomem *status_addr;
+	int rc, offset;
+	bool copro;
 	u32 bit;
-	int rc;
 
-	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit);
+	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset);
 	if (rc)
 		return;
 
 	status_addr = bank_reg(gpio, bank, reg_irq_status);
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
+
 	iowrite32(bit, status_addr);
+
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 }
 
@@ -479,15 +560,17 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set)
 	unsigned long flags;
 	u32 reg, bit;
 	void __iomem *addr;
-	int rc;
+	int rc, offset;
+	bool copro;
 
-	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit);
+	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset);
 	if (rc)
 		return;
 
 	addr = bank_reg(gpio, bank, reg_irq_enable);
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
 
 	reg = ioread32(addr);
 	if (set)
@@ -496,6 +579,8 @@ static void aspeed_gpio_irq_set_mask(struct irq_data *d, bool set)
 		reg &= ~bit;
 	iowrite32(reg, addr);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 }
 
@@ -520,9 +605,10 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type)
 	struct aspeed_gpio *gpio;
 	unsigned long flags;
 	void __iomem *addr;
-	int rc;
+	int rc, offset;
+	bool copro;
 
-	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit);
+	rc = irqd_to_aspeed_gpio_data(d, &gpio, &bank, &bit, &offset);
 	if (rc)
 		return -EINVAL;
 
@@ -548,6 +634,7 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type)
 	}
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
 
 	addr = bank_reg(gpio, bank, reg_irq_type0);
 	reg = ioread32(addr);
@@ -564,6 +651,8 @@ static int aspeed_gpio_set_type(struct irq_data *d, unsigned int type)
 	reg = (reg & ~bit) | type2;
 	iowrite32(reg, addr);
 
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
 	irq_set_handler_locked(d, handler);
@@ -658,11 +747,14 @@ static int aspeed_gpio_reset_tolerance(struct gpio_chip *chip,
 	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
 	unsigned long flags;
 	void __iomem *treg;
+	bool copro;
 	u32 val;
 
 	treg = bank_reg(gpio, to_bank(offset), reg_tolerance);
 
 	spin_lock_irqsave(&gpio->lock, flags);
+	copro = aspeed_gpio_copro_request(gpio, offset);
+
 	val = readl(treg);
 
 	if (enable)
@@ -671,6 +763,9 @@ static int aspeed_gpio_reset_tolerance(struct gpio_chip *chip,
 		val &= ~GPIO_BIT(offset);
 
 	writel(val, treg);
+
+	if (copro)
+		aspeed_gpio_copro_release(gpio, offset);
 	spin_unlock_irqrestore(&gpio->lock, flags);
 
 	return 0;
@@ -766,6 +861,9 @@ static void configure_timer(struct aspeed_gpio *gpio, unsigned int offset,
 	void __iomem *addr;
 	u32 val;
 
+	/* Note: Debounce timer isn't under control of the command
+	 * source registers, so no need to sync with the coprocessor
+	 */
 	addr = bank_reg(gpio, bank, reg_debounce_sel1);
 	val = ioread32(addr);
 	iowrite32((val & ~mask) | GPIO_SET_DEBOUNCE1(timer, offset), addr);
@@ -912,6 +1010,111 @@ static int aspeed_gpio_set_config(struct gpio_chip *chip, unsigned int offset,
 	return -ENOTSUPP;
 }
 
+/**
+ * aspeed_gpio_copro_set_ops - Sets the callbacks used for handhsaking with
+ *                             the coprocessor for shared GPIO banks
+ * @ops: The callbacks
+ * @data: Pointer passed back to the callbacks
+ */
+int aspeed_gpio_copro_set_ops(const struct aspeed_gpio_copro_ops *ops, void *data)
+{
+	copro_data = data;
+	copro_ops = ops;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(aspeed_gpio_copro_set_ops);
+
+/**
+ * aspeed_gpio_copro_grab_gpio - Mark a GPIO used by the coprocessor. The entire
+ *                               bank gets marked and any access from the ARM will
+ *                               result in handshaking via callbacks.
+ * @desc: The GPIO to be marked
+ * @vreg_offset: If non-NULL, returns the value register offset in the GPIO space
+ * @dreg_offset: If non-NULL, returns the data latch register offset in the GPIO space
+ * @bit: If non-NULL, returns the bit number of the GPIO in the registers
+ */
+int aspeed_gpio_copro_grab_gpio(struct gpio_desc *desc,
+				u16 *vreg_offset, u16 *dreg_offset, u8 *bit)
+{
+	struct gpio_chip *chip = gpiod_to_chip(desc);
+	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
+	int rc = 0, bindex, offset = gpio_chip_hwgpio(desc);
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	unsigned long flags;
+
+	if (!gpio->cf_copro_bankmap)
+		gpio->cf_copro_bankmap = kzalloc(gpio->config->nr_gpios >> 3, GFP_KERNEL);
+	if (!gpio->cf_copro_bankmap)
+		return -ENOMEM;
+	if (offset < 0 || offset > gpio->config->nr_gpios)
+		return -EINVAL;
+	bindex = offset >> 3;
+
+	spin_lock_irqsave(&gpio->lock, flags);
+
+	/* Sanity check, this shouldn't happen */
+	if (gpio->cf_copro_bankmap[bindex] == 0xff) {
+		rc = -EIO;
+		goto bail;
+	}
+	gpio->cf_copro_bankmap[bindex]++;
+
+	/* Switch command source */
+	if (gpio->cf_copro_bankmap[bindex] == 1)
+		aspeed_gpio_change_cmd_source(gpio, bank, bindex,
+					      GPIO_CMDSRC_COLDFIRE);
+
+	if (vreg_offset)
+		*vreg_offset = bank->val_regs;
+	if (dreg_offset)
+		*dreg_offset = bank->rdata_reg;
+	if (bit)
+		*bit = GPIO_OFFSET(offset);
+ bail:
+	spin_unlock_irqrestore(&gpio->lock, flags);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(aspeed_gpio_copro_grab_gpio);
+
+/**
+ * aspeed_gpio_copro_release_gpio - Unmark a GPIO used by the coprocessor.
+ * @desc: The GPIO to be marked
+ */
+int aspeed_gpio_copro_release_gpio(struct gpio_desc *desc)
+{
+	struct gpio_chip *chip = gpiod_to_chip(desc);
+	struct aspeed_gpio *gpio = gpiochip_get_data(chip);
+	int rc = 0, bindex, offset = gpio_chip_hwgpio(desc);
+	const struct aspeed_gpio_bank *bank = to_bank(offset);
+	unsigned long flags;
+
+	if (!gpio->cf_copro_bankmap)
+		return -ENXIO;
+
+	if (offset < 0 || offset > gpio->config->nr_gpios)
+		return -EINVAL;
+	bindex = offset >> 3;
+
+	spin_lock_irqsave(&gpio->lock, flags);
+
+	/* Sanity check, this shouldn't happen */
+	if (gpio->cf_copro_bankmap[bindex] == 0) {
+		rc = -EIO;
+		goto bail;
+	}
+	gpio->cf_copro_bankmap[bindex]--;
+
+	/* Switch command source */
+	if (gpio->cf_copro_bankmap[bindex] == 0)
+		aspeed_gpio_change_cmd_source(gpio, bank, bindex,
+					      GPIO_CMDSRC_ARM);
+ bail:
+	spin_unlock_irqrestore(&gpio->lock, flags);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(aspeed_gpio_copro_release_gpio);
+
 /*
  * Any banks not specified in a struct aspeed_bank_props array are assumed to
  * have the properties:
@@ -1002,10 +1205,18 @@ static int __init aspeed_gpio_probe(struct platform_device *pdev)
 	if (!gpio->dcache)
 		return -ENOMEM;
 
-	/* Populate it with initial values read from the HW */
+	/*
+	 * Populate it with initial values read from the HW and switch
+	 * all command sources to the ARM by default
+	 */
 	for (i = 0; i < banks; i++) {
-		void __iomem *addr = bank_reg(gpio, &aspeed_gpio_banks[i], reg_rdata);
+		const struct aspeed_gpio_bank *bank = &aspeed_gpio_banks[i];
+		void __iomem *addr = bank_reg(gpio, bank, reg_rdata);
 		gpio->dcache[i] = ioread32(addr);
+		aspeed_gpio_change_cmd_source(gpio, bank, 0, GPIO_CMDSRC_ARM);
+		aspeed_gpio_change_cmd_source(gpio, bank, 1, GPIO_CMDSRC_ARM);
+		aspeed_gpio_change_cmd_source(gpio, bank, 2, GPIO_CMDSRC_ARM);
+		aspeed_gpio_change_cmd_source(gpio, bank, 3, GPIO_CMDSRC_ARM);
 	}
 
 	rc = devm_gpiochip_add_data(&pdev->dev, &gpio->chip, gpio);
diff --git a/include/linux/gpio/aspeed.h b/include/linux/gpio/aspeed.h
new file mode 100644
index 000000000000..1bfb3cdc86d0
--- /dev/null
+++ b/include/linux/gpio/aspeed.h
@@ -0,0 +1,15 @@
+#ifndef __GPIO_ASPEED_H
+#define __GPIO_ASPEED_H
+
+struct aspeed_gpio_copro_ops {
+	int (*request_access)(void *data);
+	int (*release_access)(void *data);
+};
+
+int aspeed_gpio_copro_grab_gpio(struct gpio_desc *desc,
+				u16 *vreg_offset, u16 *dreg_offset, u8 *bit);
+int aspeed_gpio_copro_release_gpio(struct gpio_desc *desc);
+int aspeed_gpio_copro_set_ops(const struct aspeed_gpio_copro_ops *ops, void *data);
+
+
+#endif /* __GPIO_ASPEED_H */
-- 
cgit v1.2.3


From 679e1f07c86221b7183dd69df7068fd42d0041f6 Mon Sep 17 00:00:00 2001
From: Alagu Sankar <alagusankar@silex-india.com>
Date: Fri, 29 Jun 2018 16:27:56 +0300
Subject: ath10k: sdio: use same endpoint id for all packets in a bundle

All packets in a bundle should use the same endpoint id as the
first lookahead.

This matches how things are done is ath6kl, however,
this patch can theoretically handle several bundles
in ath10k_sdio_mbox_rx_process_packets().

Without this patch we get lots of errors about invalid endpoint id:

ath10k_sdio mmc2:0001:1: invalid endpoint in look-ahead: 224
ath10k_sdio mmc2:0001:1: failed to get pending recv messages: -12
ath10k_sdio mmc2:0001:1: failed to process pending SDIO interrupts: -12

Co-Developed-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Alagu Sankar <alagusankar@silex-india.com>
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/sdio.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 926e4c3ea256..4c018a9f3755 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -435,12 +435,14 @@ static int ath10k_sdio_mbox_rx_process_packets(struct ath10k *ar,
 	enum ath10k_htc_ep_id id;
 	int ret, i, *n_lookahead_local;
 	u32 *lookaheads_local;
+	int lookahead_idx = 0;
 
 	for (i = 0; i < ar_sdio->n_rx_pkts; i++) {
 		lookaheads_local = lookaheads;
 		n_lookahead_local = n_lookahead;
 
-		id = ((struct ath10k_htc_hdr *)&lookaheads[i])->eid;
+		id = ((struct ath10k_htc_hdr *)
+		      &lookaheads[lookahead_idx++])->eid;
 
 		if (id >= ATH10K_HTC_EP_COUNT) {
 			ath10k_warn(ar, "invalid endpoint in look-ahead: %d\n",
@@ -463,6 +465,7 @@ static int ath10k_sdio_mbox_rx_process_packets(struct ath10k *ar,
 			/* Only read lookahead's from RX trailers
 			 * for the last packet in a bundle.
 			 */
+			lookahead_idx--;
 			lookaheads_local = NULL;
 			n_lookahead_local = NULL;
 		}
-- 
cgit v1.2.3


From d1d061b1395a6eff8fd625f59ba97620f9488620 Mon Sep 17 00:00:00 2001
From: Alagu Sankar <alagusankar@silex-india.com>
Date: Fri, 29 Jun 2018 16:27:58 +0300
Subject: ath10k: sdio: allocate correct size for RECV_1MORE_BLOCK rx packets

Without this, when receiving a packet that has this flag set
from firmware, we will read invalid trailer data from the packet,
which will be shown as various errors, e.g. "sdio mbox lookahead
is zero" or "invalid rx packet" or "payload length x exceeds max
htc length".

Co-Developed-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Alagu Sankar <alagusankar@silex-india.com>
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htc.h  | 1 +
 drivers/net/wireless/ath/ath10k/sdio.c | 3 +++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/htc.h b/drivers/net/wireless/ath/ath10k/htc.h
index d69bb83049c4..51fda6c23f69 100644
--- a/drivers/net/wireless/ath/ath10k/htc.h
+++ b/drivers/net/wireless/ath/ath10k/htc.h
@@ -59,6 +59,7 @@ enum ath10k_htc_tx_flags {
 };
 
 enum ath10k_htc_rx_flags {
+	ATH10K_HTC_FLAGS_RECV_1MORE_BLOCK = 0x01,
 	ATH10K_HTC_FLAG_TRAILER_PRESENT = 0x02,
 	ATH10K_HTC_FLAG_BUNDLE_MASK     = 0xF0
 };
diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 4c018a9f3755..848f0afc21e5 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -604,6 +604,9 @@ static int ath10k_sdio_mbox_rx_alloc(struct ath10k *ar,
 		 * ATH10K_HTC_FLAG_BUNDLE_MASK flag set, all bundled
 		 * packet skb's have been allocated in the previous step.
 		 */
+		if (htc_hdr->flags & ATH10K_HTC_FLAGS_RECV_1MORE_BLOCK)
+			full_len += ATH10K_HIF_MBOX_BLOCK_SIZE;
+
 		ret = ath10k_sdio_mbox_alloc_rx_pkt(&ar_sdio->rx_pkts[i],
 						    act_len,
 						    full_len,
-- 
cgit v1.2.3


From 8530b4e7b22bc3bd8240579f3844c73947cd5f71 Mon Sep 17 00:00:00 2001
From: Alagu Sankar <alagusankar@silex-india.com>
Date: Fri, 29 Jun 2018 16:28:00 +0300
Subject: ath10k: sdio: set skb len for all rx packets

Without this, packets larger than 1500 will silently be dropped.
Easily reproduced by sending a ping packet with a size larger
than 1500.

Co-Developed-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Alagu Sankar <alagusankar@silex-india.com>
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/sdio.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index 848f0afc21e5..7f61591ce0de 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -397,6 +397,7 @@ static int ath10k_sdio_mbox_rx_process_packet(struct ath10k *ar,
 	int ret;
 
 	payload_len = le16_to_cpu(htc_hdr->len);
+	skb->len = payload_len + sizeof(struct ath10k_htc_hdr);
 
 	if (trailer_present) {
 		trailer = skb->data + sizeof(*htc_hdr) +
-- 
cgit v1.2.3


From 485790d070532e68a78d8beb4a139f276b35cbbd Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:14 +0300
Subject: wil6210: add support for Talyn-MB (Talyn ver 2.0) device

Add changes to support initialization of Talyn-MB wil6210
device:
- Add definition for Talyn-MB new JTAG id
- Define talyn_mb_fw_mapping array
- Add Talyn-MB reset sequence

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c     | 48 +++++++++++++++++++------
 drivers/net/wireless/ath/wil6210/pcie_bus.c | 11 +++++-
 drivers/net/wireless/ath/wil6210/wil6210.h  | 11 +++++-
 drivers/net/wireless/ath/wil6210/wmi.c      | 55 +++++++++++++++++++++++++++++
 4 files changed, 113 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index e7006c2428a0..1282e1a63f92 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -736,14 +736,24 @@ static void wil_bl_prepare_halt(struct wil6210_priv *wil)
 
 static inline void wil_halt_cpu(struct wil6210_priv *wil)
 {
-	wil_w(wil, RGF_USER_USER_CPU_0, BIT_USER_USER_CPU_MAN_RST);
-	wil_w(wil, RGF_USER_MAC_CPU_0,  BIT_USER_MAC_CPU_MAN_RST);
+	if (wil->hw_version >= HW_VER_TALYN_MB) {
+		wil_w(wil, RGF_USER_USER_CPU_0_TALYN_MB,
+		      BIT_USER_USER_CPU_MAN_RST);
+		wil_w(wil, RGF_USER_MAC_CPU_0_TALYN_MB,
+		      BIT_USER_MAC_CPU_MAN_RST);
+	} else {
+		wil_w(wil, RGF_USER_USER_CPU_0, BIT_USER_USER_CPU_MAN_RST);
+		wil_w(wil, RGF_USER_MAC_CPU_0,  BIT_USER_MAC_CPU_MAN_RST);
+	}
 }
 
 static inline void wil_release_cpu(struct wil6210_priv *wil)
 {
 	/* Start CPU */
-	wil_w(wil, RGF_USER_USER_CPU_0, 1);
+	if (wil->hw_version >= HW_VER_TALYN_MB)
+		wil_w(wil, RGF_USER_USER_CPU_0_TALYN_MB, 1);
+	else
+		wil_w(wil, RGF_USER_USER_CPU_0, 1);
 }
 
 static void wil_set_oob_mode(struct wil6210_priv *wil, u8 mode)
@@ -811,10 +821,17 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_0, 0x3ff81f);
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_1, 0xf);
 
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_2, 0xFE000000);
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_1, 0x0000003F);
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_3, 0x000000f0);
-	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0xFFE7FE00);
+	if (wil->hw_version >= HW_VER_TALYN_MB) {
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_2, 0x7e000000);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_1, 0x0000003f);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_3, 0xc00000f0);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0xffe7fe00);
+	} else {
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_2, 0xfe000000);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_1, 0x0000003f);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_3, 0x000000f0);
+		wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0xffe7fe00);
+	}
 
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_0, 0x0);
 	wil_w(wil, RGF_USER_CLKS_CTL_EXT_SW_RST_VEC_1, 0x0);
@@ -1042,8 +1059,14 @@ static int wil_get_otp_info(struct wil6210_priv *wil)
 	struct net_device *ndev = wil->main_ndev;
 	struct wiphy *wiphy = wil_to_wiphy(wil);
 	u8 mac[8];
+	int mac_addr;
+
+	if (wil->hw_version >= HW_VER_TALYN_MB)
+		mac_addr = RGF_OTP_MAC_TALYN_MB;
+	else
+		mac_addr = RGF_OTP_MAC;
 
-	wil_memcpy_fromio_32(mac, wil->csr + HOSTADDR(RGF_OTP_MAC),
+	wil_memcpy_fromio_32(mac, wil->csr + HOSTADDR(mac_addr),
 			     sizeof(mac));
 	if (!is_valid_ether_addr(mac)) {
 		wil_err(wil, "Invalid MAC %pM\n", mac);
@@ -1147,8 +1170,13 @@ static void wil_pre_fw_config(struct wil6210_priv *wil)
 	/* it is W1C, clear by writing back same value */
 	wil_s(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, ICR), 0);
 	wil_w(wil, RGF_CAF_ICR + offsetof(struct RGF_ICR, IMV), ~0);
-	/* clear PAL_UNIT_ICR (potential D0->D3 leftover) */
-	wil_s(wil, RGF_PAL_UNIT_ICR + offsetof(struct RGF_ICR, ICR), 0);
+	/* clear PAL_UNIT_ICR (potential D0->D3 leftover)
+	 * In Talyn-MB host cannot access this register due to
+	 * access control, hence PAL_UNIT_ICR is cleared by the FW
+	 */
+	if (wil->hw_version < HW_VER_TALYN_MB)
+		wil_s(wil, RGF_PAL_UNIT_ICR + offsetof(struct RGF_ICR, ICR),
+		      0);
 
 	if (wil->fw_calib_result > 0) {
 		__le32 val = cpu_to_le32(wil->fw_calib_result |
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 19cbc6add637..3a7e406d0311 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -85,7 +85,7 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		wil->rgf_ucode_assert_code_addr = SPARROW_RGF_UCODE_ASSERT_CODE;
 		break;
 	case JTAG_DEV_ID_TALYN:
-		wil->hw_name = "Talyn";
+		wil->hw_name = "Talyn-MA";
 		wil->hw_version = HW_VER_TALYN;
 		memcpy(fw_mapping, talyn_fw_mapping, sizeof(talyn_fw_mapping));
 		wil->rgf_fw_assert_code_addr = TALYN_RGF_FW_ASSERT_CODE;
@@ -94,6 +94,15 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		    BIT_NO_FLASH_INDICATION)
 			set_bit(hw_capa_no_flash, wil->hw_capa);
 		break;
+	case JTAG_DEV_ID_TALYN_MB:
+		wil->hw_name = "Talyn-MB";
+		wil->hw_version = HW_VER_TALYN_MB;
+		memcpy(fw_mapping, talyn_mb_fw_mapping,
+		       sizeof(talyn_mb_fw_mapping));
+		wil->rgf_fw_assert_code_addr = TALYN_RGF_FW_ASSERT_CODE;
+		wil->rgf_ucode_assert_code_addr = TALYN_RGF_UCODE_ASSERT_CODE;
+		set_bit(hw_capa_no_flash, wil->hw_capa);
+		break;
 	default:
 		wil_err(wil, "Unknown board hardware, chip_id 0x%08x, chip_revision 0x%08x\n",
 			jtag_id, chip_revision);
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index b623510c6f6c..4cd8e4030fe9 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -311,14 +311,20 @@ struct RGF_ICR {
 #define RGF_USER_JTAG_DEV_ID	(0x880b34) /* device ID */
 	#define JTAG_DEV_ID_SPARROW	(0x2632072f)
 	#define JTAG_DEV_ID_TALYN	(0x7e0e1)
+	#define JTAG_DEV_ID_TALYN_MB	(0x1007e0e1)
 
 #define RGF_USER_REVISION_ID		(0x88afe4)
 #define RGF_USER_REVISION_ID_MASK	(3)
 	#define REVISION_ID_SPARROW_B0	(0x0)
 	#define REVISION_ID_SPARROW_D0	(0x3)
 
+#define RGF_OTP_MAC_TALYN_MB		(0x8a0304)
 #define RGF_OTP_MAC			(0x8a0620)
 
+/* Talyn-MB */
+#define RGF_USER_USER_CPU_0_TALYN_MB	(0x8c0138)
+#define RGF_USER_MAC_CPU_0_TALYN_MB	(0x8c0154)
+
 /* crash codes for FW/Ucode stored here */
 
 /* ASSERT RGFs */
@@ -332,6 +338,7 @@ enum {
 	HW_VER_SPARROW_B0, /* REVISION_ID_SPARROW_B0 */
 	HW_VER_SPARROW_D0, /* REVISION_ID_SPARROW_D0 */
 	HW_VER_TALYN,	/* JTAG_DEV_ID_TALYN */
+	HW_VER_TALYN_MB	/* JTAG_DEV_ID_TALYN_MB */
 };
 
 /* popular locations */
@@ -349,7 +356,8 @@ enum {
 /* Hardware definitions end */
 #define SPARROW_FW_MAPPING_TABLE_SIZE 10
 #define TALYN_FW_MAPPING_TABLE_SIZE 13
-#define MAX_FW_MAPPING_TABLE_SIZE 13
+#define TALYN_MB_FW_MAPPING_TABLE_SIZE 19
+#define MAX_FW_MAPPING_TABLE_SIZE 19
 
 struct fw_map {
 	u32 from; /* linker address - from, inclusive */
@@ -363,6 +371,7 @@ struct fw_map {
 extern const struct fw_map sparrow_fw_mapping[SPARROW_FW_MAPPING_TABLE_SIZE];
 extern const struct fw_map sparrow_d0_mac_rgf_ext;
 extern const struct fw_map talyn_fw_mapping[TALYN_FW_MAPPING_TABLE_SIZE];
+extern const struct fw_map talyn_mb_fw_mapping[TALYN_MB_FW_MAPPING_TABLE_SIZE];
 extern struct fw_map fw_mapping[MAX_FW_MAPPING_TABLE_SIZE];
 
 /**
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 5d991243cdb5..5509f9474f9c 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -164,6 +164,61 @@ const struct fw_map talyn_fw_mapping[] = {
 	{0x800000, 0x808000, 0xa78000, "uc_data", false},
 };
 
+/**
+ * @talyn_mb_fw_mapping provides memory remapping table for Talyn-MB
+ *
+ * array size should be in sync with the declaration in the wil6210.h
+ *
+ * Talyn MB memory mapping:
+ * Linker address         PCI/Host address
+ *                        0x880000 .. 0xc80000  4Mb BAR0
+ * 0x800000 .. 0x820000   0xa00000 .. 0xa20000  128k DCCM
+ * 0x840000 .. 0x858000   0xa20000 .. 0xa38000  96k PERIPH
+ */
+const struct fw_map talyn_mb_fw_mapping[] = {
+	/* FW code RAM 768k */
+	{0x000000, 0x0c0000, 0x900000, "fw_code", true},
+	/* FW data RAM 128k */
+	{0x800000, 0x820000, 0xa00000, "fw_data", true},
+	/* periph. data RAM 96k */
+	{0x840000, 0x858000, 0xa20000, "fw_peri", true},
+	/* various RGF 40k */
+	{0x880000, 0x88a000, 0x880000, "rgf", true},
+	/* AGC table 4k */
+	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true},
+	/* Pcie_ext_rgf 4k */
+	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true},
+	/* mac_ext_rgf 2256b */
+	{0x88c000, 0x88c8d0, 0x88c000, "mac_rgf_ext", true},
+	/* ext USER RGF 4k */
+	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true},
+	/* SEC PKA 16k */
+	{0x890000, 0x894000, 0x890000, "sec_pka", true},
+	/* SEC KDF RGF 3096b */
+	{0x898000, 0x898c18, 0x898000, "sec_kdf_rgf", true},
+	/* SEC MAIN 2124b */
+	{0x89a000, 0x89a84c, 0x89a000, "sec_main", true},
+	/* OTP 4k */
+	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true},
+	/* DMA EXT RGF 64k */
+	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true},
+	/* DUM USER RGF 528b */
+	{0x8c0000, 0x8c0210, 0x8c0000, "dum_user_rgf", true},
+	/* DMA OFU 296b */
+	{0x8c2000, 0x8c2128, 0x8c2000, "dma_ofu", true},
+	/* ucode debug 4k */
+	{0x8c3000, 0x8c4000, 0x8c3000, "ucode_debug", true},
+	/* upper area 1536k */
+	{0x900000, 0xa80000, 0x900000, "upper", true},
+	/* UCODE areas - accessible by debugfs blobs but not by
+	 * wmi_addr_remap. UCODE areas MUST be added AFTER FW areas!
+	 */
+	/* ucode code RAM 256k */
+	{0x000000, 0x040000, 0xa38000, "uc_code", false},
+	/* ucode data RAM 32k */
+	{0x800000, 0x808000, 0xa78000, "uc_data", false},
+};
+
 struct fw_map fw_mapping[MAX_FW_MAPPING_TABLE_SIZE];
 
 struct blink_on_off_time led_blink_time[] = {
-- 
cgit v1.2.3


From 10590c6a07b6a84cc3224cfda481317deaf31565 Mon Sep 17 00:00:00 2001
From: Gidon Studinski <gidons@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:18 +0300
Subject: wil6210: add support for enhanced DMA structures

In enhanced DMA the vrings are handled internally by the FW
and are not exposed to the driver.
Instead, the driver handles descriptor rings, which are mapped
by the FW to vrings.
The completions of the TX and RX descriptors are notified to
the driver using status rings. Each status ring descriptor
includes information of the completed descriptors and the ring id
of their descriptor ring.

This patch changes struct vring to generic wil_ring to allow
its reuse for enhanced DMA descriptor rings and adds the descriptor
and status rings specific descriptors.

The vring debugfs entries have changed as follows:
- dbg_vring_index has changed to dbg_ring_index
- vrings has changed to rings
- vring_idle_trsh has changed to ring_idle_trsh
- vring_index has changed to ring_index

Signed-off-by: Gidon Studinski <gidons@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/cfg80211.c   |  12 +-
 drivers/net/wireless/ath/wil6210/debugfs.c    | 111 ++++----
 drivers/net/wireless/ath/wil6210/main.c       |  34 +--
 drivers/net/wireless/ath/wil6210/netdev.c     |   8 +-
 drivers/net/wireless/ath/wil6210/rx_reorder.c |   2 +-
 drivers/net/wireless/ath/wil6210/txrx.c       | 356 ++++++++++++--------------
 drivers/net/wireless/ath/wil6210/txrx.h       |  68 ++++-
 drivers/net/wireless/ath/wil6210/txrx_edma.h  | 290 +++++++++++++++++++++
 drivers/net/wireless/ath/wil6210/wil6210.h    | 110 ++++++--
 drivers/net/wireless/ath/wil6210/wmi.c        |  24 +-
 10 files changed, 696 insertions(+), 319 deletions(-)
 create mode 100644 drivers/net/wireless/ath/wil6210/txrx_edma.h

diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 78946f28d0c7..dfe64b06654f 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -1726,7 +1726,7 @@ static int wil_cfg80211_change_station(struct wiphy *wiphy,
 	struct wil6210_priv *wil = wiphy_to_wil(wiphy);
 	int authorize;
 	int cid, i;
-	struct vring_tx_data *txdata = NULL;
+	struct wil_ring_tx_data *txdata = NULL;
 
 	wil_dbg_misc(wil, "change station %pM mask 0x%x set 0x%x mid %d\n",
 		     mac, params->sta_flags_mask, params->sta_flags_set,
@@ -1746,20 +1746,20 @@ static int wil_cfg80211_change_station(struct wiphy *wiphy,
 		return -ENOLINK;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(wil->vring2cid_tid); i++)
-		if (wil->vring2cid_tid[i][0] == cid) {
-			txdata = &wil->vring_tx_data[i];
+	for (i = 0; i < ARRAY_SIZE(wil->ring2cid_tid); i++)
+		if (wil->ring2cid_tid[i][0] == cid) {
+			txdata = &wil->ring_tx_data[i];
 			break;
 		}
 
 	if (!txdata) {
-		wil_err(wil, "vring data not found\n");
+		wil_err(wil, "ring data not found\n");
 		return -ENOLINK;
 	}
 
 	authorize = params->sta_flags_set & BIT(NL80211_STA_FLAG_AUTHORIZED);
 	txdata->dot1x_open = authorize ? 1 : 0;
-	wil_dbg_misc(wil, "cid %d vring %d authorize %d\n", cid, i,
+	wil_dbg_misc(wil, "cid %d ring %d authorize %d\n", cid, i,
 		     txdata->dot1x_open);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index ebfdff4d328c..55e03e9b49eb 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -29,7 +29,7 @@
 /* Nasty hack. Better have per device instances */
 static u32 mem_addr;
 static u32 dbg_txdesc_index;
-static u32 dbg_vring_index; /* 24+ for Rx, 0..23 for Tx */
+static u32 dbg_ring_index; /* 24+ for Rx, 0..23 for Tx */
 
 enum dbg_off_type {
 	doff_u32 = 0,
@@ -47,20 +47,20 @@ struct dbg_off {
 	enum dbg_off_type type;
 };
 
-static void wil_print_vring(struct seq_file *s, struct wil6210_priv *wil,
-			    const char *name, struct vring *vring,
-			    char _s, char _h)
+static void wil_print_ring(struct seq_file *s, struct wil6210_priv *wil,
+			   const char *name, struct wil_ring *ring,
+			   char _s, char _h)
 {
-	void __iomem *x = wmi_addr(wil, vring->hwtail);
+	void __iomem *x = wmi_addr(wil, ring->hwtail);
 	u32 v;
 
-	seq_printf(s, "VRING %s = {\n", name);
-	seq_printf(s, "  pa     = %pad\n", &vring->pa);
-	seq_printf(s, "  va     = 0x%p\n", vring->va);
-	seq_printf(s, "  size   = %d\n", vring->size);
-	seq_printf(s, "  swtail = %d\n", vring->swtail);
-	seq_printf(s, "  swhead = %d\n", vring->swhead);
-	seq_printf(s, "  hwtail = [0x%08x] -> ", vring->hwtail);
+	seq_printf(s, "RING %s = {\n", name);
+	seq_printf(s, "  pa     = %pad\n", &ring->pa);
+	seq_printf(s, "  va     = 0x%p\n", ring->va);
+	seq_printf(s, "  size   = %d\n", ring->size);
+	seq_printf(s, "  swtail = %d\n", ring->swtail);
+	seq_printf(s, "  swhead = %d\n", ring->swhead);
+	seq_printf(s, "  hwtail = [0x%08x] -> ", ring->hwtail);
 	if (x) {
 		v = readl(x);
 		seq_printf(s, "0x%08x = %d\n", v, v);
@@ -68,41 +68,42 @@ static void wil_print_vring(struct seq_file *s, struct wil6210_priv *wil,
 		seq_puts(s, "???\n");
 	}
 
-	if (vring->va && (vring->size <= (1 << WIL_RING_SIZE_ORDER_MAX))) {
+	if (ring->va && (ring->size <= (1 << WIL_RING_SIZE_ORDER_MAX))) {
 		uint i;
 
-		for (i = 0; i < vring->size; i++) {
-			volatile struct vring_tx_desc *d = &vring->va[i].tx;
+		for (i = 0; i < ring->size; i++) {
+			volatile struct vring_tx_desc *d =
+				&ring->va[i].tx.legacy;
 
 			if ((i % 128) == 0 && (i != 0))
 				seq_puts(s, "\n");
 			seq_printf(s, "%c", (d->dma.status & BIT(0)) ?
-					_s : (vring->ctx[i].skb ? _h : 'h'));
+					_s : (ring->ctx[i].skb ? _h : 'h'));
 		}
 		seq_puts(s, "\n");
 	}
 	seq_puts(s, "}\n");
 }
 
-static int wil_vring_debugfs_show(struct seq_file *s, void *data)
+static int wil_ring_debugfs_show(struct seq_file *s, void *data)
 {
 	uint i;
 	struct wil6210_priv *wil = s->private;
 
-	wil_print_vring(s, wil, "rx", &wil->vring_rx, 'S', '_');
+	wil_print_ring(s, wil, "rx", &wil->ring_rx, 'S', '_');
 
-	for (i = 0; i < ARRAY_SIZE(wil->vring_tx); i++) {
-		struct vring *vring = &wil->vring_tx[i];
-		struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+	for (i = 0; i < ARRAY_SIZE(wil->ring_tx); i++) {
+		struct wil_ring *ring = &wil->ring_tx[i];
+		struct wil_ring_tx_data *txdata = &wil->ring_tx_data[i];
 
-		if (vring->va) {
-			int cid = wil->vring2cid_tid[i][0];
-			int tid = wil->vring2cid_tid[i][1];
-			u32 swhead = vring->swhead;
-			u32 swtail = vring->swtail;
-			int used = (vring->size + swhead - swtail)
-				   % vring->size;
-			int avail = vring->size - used - 1;
+		if (ring->va) {
+			int cid = wil->ring2cid_tid[i][0];
+			int tid = wil->ring2cid_tid[i][1];
+			u32 swhead = ring->swhead;
+			u32 swtail = ring->swtail;
+			int used = (ring->size + swhead - swtail)
+				   % ring->size;
+			int avail = ring->size - used - 1;
 			char name[10];
 			char sidle[10];
 			/* performance monitoring */
@@ -137,20 +138,20 @@ static int wil_vring_debugfs_show(struct seq_file *s, void *data)
 					   txdata->dot1x_open ? "+" : "-",
 					   used, avail, sidle);
 
-			wil_print_vring(s, wil, name, vring, '_', 'H');
+			wil_print_ring(s, wil, name, ring, '_', 'H');
 		}
 	}
 
 	return 0;
 }
 
-static int wil_vring_seq_open(struct inode *inode, struct file *file)
+static int wil_ring_seq_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, wil_vring_debugfs_show, inode->i_private);
+	return single_open(file, wil_ring_debugfs_show, inode->i_private);
 }
 
-static const struct file_operations fops_vring = {
-	.open		= wil_vring_seq_open,
+static const struct file_operations fops_ring = {
+	.open		= wil_ring_seq_open,
 	.release	= single_release,
 	.read		= seq_read,
 	.llseek		= seq_lseek,
@@ -162,8 +163,8 @@ static void wil_seq_hexdump(struct seq_file *s, void *p, int len,
 	seq_hex_dump(s, prefix, DUMP_PREFIX_NONE, 16, 1, p, len, false);
 }
 
-static void wil_print_ring(struct seq_file *s, const char *prefix,
-			   void __iomem *off)
+static void wil_print_mbox_ring(struct seq_file *s, const char *prefix,
+				void __iomem *off)
 {
 	struct wil6210_priv *wil = s->private;
 	struct wil6210_mbox_ring r;
@@ -249,9 +250,9 @@ static int wil_mbox_debugfs_show(struct seq_file *s, void *data)
 	if (ret < 0)
 		return ret;
 
-	wil_print_ring(s, "tx", wil->csr + HOST_MBOX +
+	wil_print_mbox_ring(s, "tx", wil->csr + HOST_MBOX +
 		       offsetof(struct wil6210_mbox_ctl, tx));
-	wil_print_ring(s, "rx", wil->csr + HOST_MBOX +
+	wil_print_mbox_ring(s, "rx", wil->csr + HOST_MBOX +
 		       offsetof(struct wil6210_mbox_ctl, rx));
 
 	wil_pm_runtime_put(wil);
@@ -719,13 +720,13 @@ static ssize_t wil_write_back(struct file *file, const char __user *buf,
 
 	if ((strcmp(cmd, "add") == 0) ||
 	    (strcmp(cmd, "del_tx") == 0)) {
-		struct vring_tx_data *txdata;
+		struct wil_ring_tx_data *txdata;
 
 		if (p1 < 0 || p1 >= WIL6210_MAX_TX_RINGS) {
 			wil_err(wil, "BACK: invalid ring id %d\n", p1);
 			return -EINVAL;
 		}
-		txdata = &wil->vring_tx_data[p1];
+		txdata = &wil->ring_tx_data[p1];
 		if (strcmp(cmd, "add") == 0) {
 			if (rc < 3) {
 				wil_err(wil, "BACK: add require at least 2 params\n");
@@ -972,30 +973,30 @@ static void wil_seq_print_skb(struct seq_file *s, struct sk_buff *skb)
 static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
-	struct vring *vring;
-	bool tx = (dbg_vring_index < WIL6210_MAX_TX_RINGS);
+	struct wil_ring *ring;
+	bool tx = (dbg_ring_index < WIL6210_MAX_TX_RINGS);
 
-	vring = tx ? &wil->vring_tx[dbg_vring_index] : &wil->vring_rx;
+	ring = tx ? &wil->ring_tx[dbg_ring_index] : &wil->ring_rx;
 
-	if (!vring->va) {
+	if (!ring->va) {
 		if (tx)
-			seq_printf(s, "No Tx[%2d] VRING\n", dbg_vring_index);
+			seq_printf(s, "No Tx[%2d] VRING\n", dbg_ring_index);
 		else
 			seq_puts(s, "No Rx VRING\n");
 		return 0;
 	}
 
-	if (dbg_txdesc_index < vring->size) {
+	if (dbg_txdesc_index < ring->size) {
 		/* use struct vring_tx_desc for Rx as well,
 		 * only field used, .dma.length, is the same
 		 */
 		volatile struct vring_tx_desc *d =
-				&vring->va[dbg_txdesc_index].tx;
+				&ring->va[dbg_txdesc_index].tx.legacy;
 		volatile u32 *u = (volatile u32 *)d;
-		struct sk_buff *skb = vring->ctx[dbg_txdesc_index].skb;
+		struct sk_buff *skb = ring->ctx[dbg_txdesc_index].skb;
 
 		if (tx)
-			seq_printf(s, "Tx[%2d][%3d] = {\n", dbg_vring_index,
+			seq_printf(s, "Tx[%2d][%3d] = {\n", dbg_ring_index,
 				   dbg_txdesc_index);
 		else
 			seq_printf(s, "Rx[%3d] = {\n", dbg_txdesc_index);
@@ -1014,11 +1015,11 @@ static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
 	} else {
 		if (tx)
 			seq_printf(s, "[%2d] TxDesc index (%d) >= size (%d)\n",
-				   dbg_vring_index, dbg_txdesc_index,
-				   vring->size);
+				   dbg_ring_index, dbg_txdesc_index,
+				   ring->size);
 		else
 			seq_printf(s, "RxDesc index (%d) >= size (%d)\n",
-				   dbg_txdesc_index, vring->size);
+				   dbg_txdesc_index, ring->size);
 	}
 
 	return 0;
@@ -1790,7 +1791,7 @@ static const struct {
 	const struct file_operations *fops;
 } dbg_files[] = {
 	{"mbox",	0444,		&fops_mbox},
-	{"vrings",	0444,		&fops_vring},
+	{"rings",	0444,		&fops_ring},
 	{"stations", 0444,		&fops_sta},
 	{"mids",	0444,		&fops_mids},
 	{"desc",	0444,		&fops_txdesc},
@@ -1858,7 +1859,7 @@ static const struct dbg_off dbg_wil_off[] = {
 	WIL_FIELD(chip_revision, 0444,	doff_u8),
 	WIL_FIELD(abft_len, 0644,		doff_u8),
 	WIL_FIELD(wakeup_trigger, 0644,		doff_u8),
-	WIL_FIELD(vring_idle_trsh, 0644,	doff_u32),
+	WIL_FIELD(ring_idle_trsh, 0644,	doff_u32),
 	{},
 };
 
@@ -1872,7 +1873,7 @@ static const struct dbg_off dbg_wil_regs[] = {
 /* static parameters */
 static const struct dbg_off dbg_statics[] = {
 	{"desc_index",	0644, (ulong)&dbg_txdesc_index, doff_u32},
-	{"vring_index",	0644, (ulong)&dbg_vring_index, doff_u32},
+	{"ring_index",	0644, (ulong)&dbg_ring_index, doff_u32},
 	{"mem_addr",	0644, (ulong)&mem_addr, doff_u32},
 	{"led_polarity", 0644, (ulong)&led_polarity, doff_u8},
 	{},
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 1282e1a63f92..bfe628481e22 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -219,9 +219,9 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	memset(sta->tid_crypto_rx, 0, sizeof(sta->tid_crypto_rx));
 	memset(&sta->group_crypto_rx, 0, sizeof(sta->group_crypto_rx));
 	/* release vrings */
-	for (i = 0; i < ARRAY_SIZE(wil->vring_tx); i++) {
-		if (wil->vring2cid_tid[i][0] == cid)
-			wil_vring_fini_tx(wil, i);
+	for (i = 0; i < ARRAY_SIZE(wil->ring_tx); i++) {
+		if (wil->ring2cid_tid[i][0] == cid)
+			wil_ring_fini_tx(wil, i);
 	}
 	/* statistics */
 	memset(&sta->stats, 0, sizeof(sta->stats));
@@ -453,12 +453,12 @@ static void wil_fw_error_worker(struct work_struct *work)
 	mutex_unlock(&wil->mutex);
 }
 
-static int wil_find_free_vring(struct wil6210_priv *wil)
+static int wil_find_free_ring(struct wil6210_priv *wil)
 {
 	int i;
 
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		if (!wil->vring_tx[i].va)
+		if (!wil->ring_tx[i].va)
 			return i;
 	}
 	return -EINVAL;
@@ -473,13 +473,13 @@ int wil_tx_init(struct wil6210_vif *vif, int cid)
 		wil_err(wil, "No connection pending\n");
 		goto out;
 	}
-	ringid = wil_find_free_vring(wil);
+	ringid = wil_find_free_ring(wil);
 	if (ringid < 0) {
 		wil_err(wil, "No free vring found\n");
 		goto out;
 	}
 
-	wil_dbg_wmi(wil, "Configure for connection CID %d MID %d vring %d\n",
+	wil_dbg_wmi(wil, "Configure for connection CID %d MID %d ring %d\n",
 		    cid, vif->mid, ringid);
 
 	rc = wil_vring_init_tx(vif, ringid, 1 << tx_ring_order, cid, 0);
@@ -494,19 +494,19 @@ out:
 int wil_bcast_init(struct wil6210_vif *vif)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
-	int ri = vif->bcast_vring, rc;
+	int ri = vif->bcast_ring, rc;
 
-	if ((ri >= 0) && wil->vring_tx[ri].va)
+	if (ri >= 0 && wil->ring_tx[ri].va)
 		return 0;
 
-	ri = wil_find_free_vring(wil);
+	ri = wil_find_free_ring(wil);
 	if (ri < 0)
 		return ri;
 
-	vif->bcast_vring = ri;
+	vif->bcast_ring = ri;
 	rc = wil_vring_init_bcast(vif, ri, 1 << bcast_ring_order);
 	if (rc)
-		vif->bcast_vring = -1;
+		vif->bcast_ring = -1;
 
 	return rc;
 }
@@ -514,13 +514,13 @@ int wil_bcast_init(struct wil6210_vif *vif)
 void wil_bcast_fini(struct wil6210_vif *vif)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
-	int ri = vif->bcast_vring;
+	int ri = vif->bcast_ring;
 
 	if (ri < 0)
 		return;
 
-	vif->bcast_vring = -1;
-	wil_vring_fini_tx(wil, ri);
+	vif->bcast_ring = -1;
+	wil_ring_fini_tx(wil, ri);
 }
 
 void wil_bcast_fini_all(struct wil6210_priv *wil)
@@ -548,7 +548,7 @@ int wil_priv_init(struct wil6210_priv *wil)
 	}
 
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++)
-		spin_lock_init(&wil->vring_tx_data[i].lock);
+		spin_lock_init(&wil->ring_tx_data[i].lock);
 
 	mutex_init(&wil->mutex);
 	mutex_init(&wil->vif_mutex);
@@ -589,7 +589,7 @@ int wil_priv_init(struct wil6210_priv *wil)
 	wil->wakeup_trigger = WMI_WAKEUP_TRIGGER_UCAST |
 			      WMI_WAKEUP_TRIGGER_BCAST;
 	memset(&wil->suspend_stats, 0, sizeof(wil->suspend_stats));
-	wil->vring_idle_trsh = 16;
+	wil->ring_idle_trsh = 16;
 
 	wil->reply_mid = U8_MAX;
 	wil->max_vifs = 1;
diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index eb6c14ed65a4..3c6a59fd08df 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -129,11 +129,11 @@ static int wil6210_netdev_poll_tx(struct napi_struct *napi, int budget)
 
 	/* always process ALL Tx complete, regardless budget - it is fast */
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		struct vring *vring = &wil->vring_tx[i];
-		struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+		struct wil_ring *ring = &wil->ring_tx[i];
+		struct wil_ring_tx_data *txdata = &wil->ring_tx_data[i];
 		struct wil6210_vif *vif;
 
-		if (!vring->va || !txdata->enabled ||
+		if (!ring->va || !txdata->enabled ||
 		    txdata->mid >= wil->max_vifs)
 			continue;
 
@@ -228,7 +228,7 @@ static void wil_p2p_discovery_timer_fn(struct timer_list *t)
 
 static void wil_vif_init(struct wil6210_vif *vif)
 {
-	vif->bcast_vring = -1;
+	vif->bcast_ring = -1;
 
 	mutex_init(&vif->probe_client_mutex);
 
diff --git a/drivers/net/wireless/ath/wil6210/rx_reorder.c b/drivers/net/wireless/ath/wil6210/rx_reorder.c
index 76f8084c1fd8..a586929f72d4 100644
--- a/drivers/net/wireless/ath/wil6210/rx_reorder.c
+++ b/drivers/net/wireless/ath/wil6210/rx_reorder.c
@@ -384,7 +384,7 @@ int wil_addba_tx_request(struct wil6210_priv *wil, u8 ringid, u16 wsize)
 {
 	u8 agg_wsize = wil_agg_size(wil, wsize);
 	u16 agg_timeout = 0;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[ringid];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ringid];
 	int rc = 0;
 
 	if (txdata->addba_in_progress) {
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index b9a9fa828961..55946dec5110 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -47,62 +47,28 @@ static inline uint wil_rx_snaplen(void)
 	return rx_align_2 ? 6 : 0;
 }
 
-static inline int wil_vring_is_empty(struct vring *vring)
+/* wil_ring_wmark_low - low watermark for available descriptor space */
+static inline int wil_ring_wmark_low(struct wil_ring *ring)
 {
-	return vring->swhead == vring->swtail;
+	return ring->size / 8;
 }
 
-static inline u32 wil_vring_next_tail(struct vring *vring)
+/* wil_ring_wmark_high - high watermark for available descriptor space */
+static inline int wil_ring_wmark_high(struct wil_ring *ring)
 {
-	return (vring->swtail + 1) % vring->size;
-}
-
-static inline void wil_vring_advance_head(struct vring *vring, int n)
-{
-	vring->swhead = (vring->swhead + n) % vring->size;
-}
-
-static inline int wil_vring_is_full(struct vring *vring)
-{
-	return wil_vring_next_tail(vring) == vring->swhead;
-}
-
-/* Used space in Tx Vring */
-static inline int wil_vring_used_tx(struct vring *vring)
-{
-	u32 swhead = vring->swhead;
-	u32 swtail = vring->swtail;
-	return (vring->size + swhead - swtail) % vring->size;
-}
-
-/* Available space in Tx Vring */
-static inline int wil_vring_avail_tx(struct vring *vring)
-{
-	return vring->size - wil_vring_used_tx(vring) - 1;
-}
-
-/* wil_vring_wmark_low - low watermark for available descriptor space */
-static inline int wil_vring_wmark_low(struct vring *vring)
-{
-	return vring->size/8;
-}
-
-/* wil_vring_wmark_high - high watermark for available descriptor space */
-static inline int wil_vring_wmark_high(struct vring *vring)
-{
-	return vring->size/4;
+	return ring->size / 4;
 }
 
 /* returns true if num avail descriptors is lower than wmark_low */
-static inline int wil_vring_avail_low(struct vring *vring)
+static inline int wil_ring_avail_low(struct wil_ring *ring)
 {
-	return wil_vring_avail_tx(vring) < wil_vring_wmark_low(vring);
+	return wil_ring_avail_tx(ring) < wil_ring_wmark_low(ring);
 }
 
 /* returns true if num avail descriptors is higher than wmark_high */
-static inline int wil_vring_avail_high(struct vring *vring)
+static inline int wil_ring_avail_high(struct wil_ring *ring)
 {
-	return wil_vring_avail_tx(vring) > wil_vring_wmark_high(vring);
+	return wil_ring_avail_tx(ring) > wil_ring_wmark_high(ring);
 }
 
 /* returns true when all tx vrings are empty */
@@ -112,9 +78,10 @@ bool wil_is_tx_idle(struct wil6210_priv *wil)
 	unsigned long data_comp_to;
 
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		struct vring *vring = &wil->vring_tx[i];
-		int vring_index = vring - wil->vring_tx;
-		struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+		struct wil_ring *vring = &wil->ring_tx[i];
+		int vring_index = vring - wil->ring_tx;
+		struct wil_ring_tx_data *txdata =
+			&wil->ring_tx_data[vring_index];
 
 		spin_lock(&txdata->lock);
 
@@ -126,7 +93,7 @@ bool wil_is_tx_idle(struct wil6210_priv *wil)
 		data_comp_to = jiffies + msecs_to_jiffies(
 					WIL_DATA_COMPLETION_TO_MS);
 		if (test_bit(wil_status_napi_en, wil->status)) {
-			while (!wil_vring_is_empty(vring)) {
+			while (!wil_ring_is_empty(vring)) {
 				if (time_after(jiffies, data_comp_to)) {
 					wil_dbg_pm(wil,
 						   "TO waiting for idle tx\n");
@@ -156,7 +123,7 @@ static inline bool wil_val_in_range(int val, int min, int max)
 	return val >= min && val < max;
 }
 
-static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
+static int wil_vring_alloc(struct wil6210_priv *wil, struct wil_ring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
 	size_t sz = vring->size * sizeof(vring->va[0]);
@@ -205,7 +172,8 @@ static int wil_vring_alloc(struct wil6210_priv *wil, struct vring *vring)
 	 * we can use any
 	 */
 	for (i = 0; i < vring->size; i++) {
-		volatile struct vring_tx_desc *_d = &vring->va[i].tx;
+		volatile struct vring_tx_desc *_d =
+			&vring->va[i].tx.legacy;
 
 		_d->dma.status = TX_DMA_STATUS_DU;
 	}
@@ -234,7 +202,7 @@ static void wil_txdesc_unmap(struct device *dev, struct vring_tx_desc *d,
 	}
 }
 
-static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
+static void wil_vring_free(struct wil6210_priv *wil, struct wil_ring *vring,
 			   int tx)
 {
 	struct device *dev = wil_to_dev(wil);
@@ -242,7 +210,7 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
 
 	lockdep_assert_held(&wil->mutex);
 	if (tx) {
-		int vring_index = vring - wil->vring_tx;
+		int vring_index = vring - wil->ring_tx;
 
 		wil_dbg_misc(wil, "free Tx vring %d [%d] 0x%p:%pad 0x%p\n",
 			     vring_index, vring->size, vring->va,
@@ -253,7 +221,7 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
 			     &vring->pa, vring->ctx);
 	}
 
-	while (!wil_vring_is_empty(vring)) {
+	while (!wil_ring_is_empty(vring)) {
 		dma_addr_t pa;
 		u16 dmalen;
 		struct wil_ctx *ctx;
@@ -261,25 +229,25 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
 		if (tx) {
 			struct vring_tx_desc dd, *d = &dd;
 			volatile struct vring_tx_desc *_d =
-					&vring->va[vring->swtail].tx;
+					&vring->va[vring->swtail].tx.legacy;
 
 			ctx = &vring->ctx[vring->swtail];
 			if (!ctx) {
 				wil_dbg_txrx(wil,
 					     "ctx(%d) was already completed\n",
 					     vring->swtail);
-				vring->swtail = wil_vring_next_tail(vring);
+				vring->swtail = wil_ring_next_tail(vring);
 				continue;
 			}
 			*d = *_d;
 			wil_txdesc_unmap(dev, d, ctx);
 			if (ctx->skb)
 				dev_kfree_skb_any(ctx->skb);
-			vring->swtail = wil_vring_next_tail(vring);
+			vring->swtail = wil_ring_next_tail(vring);
 		} else { /* rx */
 			struct vring_rx_desc dd, *d = &dd;
 			volatile struct vring_rx_desc *_d =
-					&vring->va[vring->swhead].rx;
+				&vring->va[vring->swhead].rx.legacy;
 
 			ctx = &vring->ctx[vring->swhead];
 			*d = *_d;
@@ -287,7 +255,7 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
 			dmalen = le16_to_cpu(d->dma.length);
 			dma_unmap_single(dev, pa, dmalen, DMA_FROM_DEVICE);
 			kfree_skb(ctx->skb);
-			wil_vring_advance_head(vring, 1);
+			wil_ring_advance_head(vring, 1);
 		}
 	}
 	dma_free_coherent(dev, sz, (void *)vring->va, vring->pa);
@@ -302,13 +270,13 @@ static void wil_vring_free(struct wil6210_priv *wil, struct vring *vring,
  *
  * Safe to call from IRQ
  */
-static int wil_vring_alloc_skb(struct wil6210_priv *wil, struct vring *vring,
+static int wil_vring_alloc_skb(struct wil6210_priv *wil, struct wil_ring *vring,
 			       u32 i, int headroom)
 {
 	struct device *dev = wil_to_dev(wil);
 	unsigned int sz = wil->rx_buf_len + ETH_HLEN + wil_rx_snaplen();
 	struct vring_rx_desc dd, *d = &dd;
-	volatile struct vring_rx_desc *_d = &vring->va[i].rx;
+	volatile struct vring_rx_desc *_d = &vring->va[i].rx.legacy;
 	dma_addr_t pa;
 	struct sk_buff *skb = dev_alloc_skb(sz + headroom);
 
@@ -455,9 +423,9 @@ static inline int wil_is_back_req(u8 fc)
 bool wil_is_rx_idle(struct wil6210_priv *wil)
 {
 	struct vring_rx_desc *_d;
-	struct vring *vring = &wil->vring_rx;
+	struct wil_ring *ring = &wil->ring_rx;
 
-	_d = (struct vring_rx_desc *)&vring->va[vring->swhead].rx;
+	_d = (struct vring_rx_desc *)&ring->va[ring->swhead].rx.legacy;
 	if (_d->dma.status & RX_DMA_STATUS_DU)
 		return false;
 
@@ -472,7 +440,7 @@ bool wil_is_rx_idle(struct wil6210_priv *wil)
  * Safe to call from IRQ
  */
 static struct sk_buff *wil_vring_reap_rx(struct wil6210_priv *wil,
-					 struct vring *vring)
+					 struct wil_ring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
 	struct wil6210_vif *vif;
@@ -492,11 +460,11 @@ static struct sk_buff *wil_vring_reap_rx(struct wil6210_priv *wil,
 	BUILD_BUG_ON(sizeof(struct vring_rx_desc) > sizeof(skb->cb));
 
 again:
-	if (unlikely(wil_vring_is_empty(vring)))
+	if (unlikely(wil_ring_is_empty(vring)))
 		return NULL;
 
 	i = (int)vring->swhead;
-	_d = &vring->va[i].rx;
+	_d = &vring->va[i].rx.legacy;
 	if (unlikely(!(_d->dma.status & RX_DMA_STATUS_DU))) {
 		/* it is not error, we just reached end of Rx done area */
 		return NULL;
@@ -504,7 +472,7 @@ again:
 
 	skb = vring->ctx[i].skb;
 	vring->ctx[i].skb = NULL;
-	wil_vring_advance_head(vring, 1);
+	wil_ring_advance_head(vring, 1);
 	if (!skb) {
 		wil_err(wil, "No Rx skb at [%d]\n", i);
 		goto again;
@@ -641,15 +609,15 @@ again:
 static int wil_rx_refill(struct wil6210_priv *wil, int count)
 {
 	struct net_device *ndev = wil->main_ndev;
-	struct vring *v = &wil->vring_rx;
+	struct wil_ring *v = &wil->ring_rx;
 	u32 next_tail;
 	int rc = 0;
 	int headroom = ndev->type == ARPHRD_IEEE80211_RADIOTAP ?
 			WIL6210_RTAP_SIZE : 0;
 
-	for (; next_tail = wil_vring_next_tail(v),
-			(next_tail != v->swhead) && (count-- > 0);
-			v->swtail = next_tail) {
+	for (; next_tail = wil_ring_next_tail(v),
+	     (next_tail != v->swhead) && (count-- > 0);
+	     v->swtail = next_tail) {
 		rc = wil_vring_alloc_skb(wil, v, v->swtail, headroom);
 		if (unlikely(rc)) {
 			wil_err_ratelimited(wil, "Error %d in rx refill[%d]\n",
@@ -835,7 +803,7 @@ void wil_rx_handle(struct wil6210_priv *wil, int *quota)
 {
 	struct net_device *ndev = wil->main_ndev;
 	struct wireless_dev *wdev = ndev->ieee80211_ptr;
-	struct vring *v = &wil->vring_rx;
+	struct wil_ring *v = &wil->ring_rx;
 	struct sk_buff *skb;
 
 	if (unlikely(!v->va)) {
@@ -877,7 +845,7 @@ static void wil_rx_buf_len_init(struct wil6210_priv *wil)
 
 int wil_rx_init(struct wil6210_priv *wil, u16 size)
 {
-	struct vring *vring = &wil->vring_rx;
+	struct wil_ring *vring = &wil->ring_rx;
 	int rc;
 
 	wil_dbg_misc(wil, "rx_init\n");
@@ -911,7 +879,7 @@ int wil_rx_init(struct wil6210_priv *wil, u16 size)
 
 void wil_rx_fini(struct wil6210_priv *wil)
 {
-	struct vring *vring = &wil->vring_rx;
+	struct wil_ring *vring = &wil->ring_rx;
 
 	wil_dbg_misc(wil, "rx_fini\n");
 
@@ -919,7 +887,7 @@ void wil_rx_fini(struct wil6210_priv *wil)
 		wil_vring_free(wil, vring, 0);
 }
 
-static inline void wil_tx_data_init(struct vring_tx_data *txdata)
+static inline void wil_tx_data_init(struct wil_ring_tx_data *txdata)
 {
 	spin_lock_bh(&txdata->lock);
 	txdata->dot1x_open = 0;
@@ -966,8 +934,8 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	} __packed reply = {
 		.cmd = {.status = WMI_FW_STATUS_FAILURE},
 	};
-	struct vring *vring = &wil->vring_tx[id];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[id];
+	struct wil_ring *vring = &wil->ring_tx[id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
 
 	wil_dbg_misc(wil, "vring_init_tx: max_mpdu_size %d\n",
 		     cmd.vring_cfg.tx_sw_ring.max_mpdu_size);
@@ -985,8 +953,8 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	if (rc)
 		goto out;
 
-	wil->vring2cid_tid[id][0] = cid;
-	wil->vring2cid_tid[id][1] = tid;
+	wil->ring2cid_tid[id][0] = cid;
+	wil->ring2cid_tid[id][1] = tid;
 
 	cmd.vring_cfg.tx_sw_ring.ring_mem_base = cpu_to_le64(vring->pa);
 
@@ -1020,8 +988,8 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	txdata->enabled = 0;
 	spin_unlock_bh(&txdata->lock);
 	wil_vring_free(wil, vring, 1);
-	wil->vring2cid_tid[id][0] = WIL6210_MAX_CID;
-	wil->vring2cid_tid[id][1] = 0;
+	wil->ring2cid_tid[id][0] = WIL6210_MAX_CID;
+	wil->ring2cid_tid[id][1] = 0;
 
  out:
 
@@ -1050,8 +1018,8 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	} __packed reply = {
 		.cmd = {.status = WMI_FW_STATUS_FAILURE},
 	};
-	struct vring *vring = &wil->vring_tx[id];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[id];
+	struct wil_ring *vring = &wil->ring_tx[id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
 
 	wil_dbg_misc(wil, "vring_init_bcast: max_mpdu_size %d\n",
 		     cmd.vring_cfg.tx_sw_ring.max_mpdu_size);
@@ -1069,8 +1037,8 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	if (rc)
 		goto out;
 
-	wil->vring2cid_tid[id][0] = WIL6210_MAX_CID; /* CID */
-	wil->vring2cid_tid[id][1] = 0; /* TID */
+	wil->ring2cid_tid[id][0] = WIL6210_MAX_CID; /* CID */
+	wil->ring2cid_tid[id][1] = 0; /* TID */
 
 	cmd.vring_cfg.tx_sw_ring.ring_mem_base = cpu_to_le64(vring->pa);
 
@@ -1107,10 +1075,10 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	return rc;
 }
 
-void wil_vring_fini_tx(struct wil6210_priv *wil, int id)
+void wil_ring_fini_tx(struct wil6210_priv *wil, int id)
 {
-	struct vring *vring = &wil->vring_tx[id];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[id];
+	struct wil_ring *vring = &wil->ring_tx[id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
 
 	lockdep_assert_held(&wil->mutex);
 
@@ -1138,9 +1106,9 @@ void wil_vring_fini_tx(struct wil6210_priv *wil, int id)
 	wil_vring_free(wil, vring, 1);
 }
 
-static struct vring *wil_find_tx_ucast(struct wil6210_priv *wil,
-				       struct wil6210_vif *vif,
-				       struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_ucast(struct wil6210_priv *wil,
+					  struct wil6210_vif *vif,
+					  struct sk_buff *skb)
 {
 	int i;
 	struct ethhdr *eth = (void *)skb->data;
@@ -1150,13 +1118,13 @@ static struct vring *wil_find_tx_ucast(struct wil6210_priv *wil,
 		return NULL;
 
 	/* TODO: fix for multiple TID */
-	for (i = 0; i < ARRAY_SIZE(wil->vring2cid_tid); i++) {
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+	for (i = 0; i < ARRAY_SIZE(wil->ring2cid_tid); i++) {
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
-		if (wil->vring2cid_tid[i][0] == cid) {
-			struct vring *v = &wil->vring_tx[i];
-			struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+		if (wil->ring2cid_tid[i][0] == cid) {
+			struct wil_ring *v = &wil->ring_tx[i];
+			struct wil_ring_tx_data *txdata = &wil->ring_tx_data[i];
 
 			wil_dbg_txrx(wil, "find_tx_ucast: (%pM) -> [%d]\n",
 				     eth->h_dest, i);
@@ -1175,41 +1143,41 @@ static struct vring *wil_find_tx_ucast(struct wil6210_priv *wil,
 }
 
 static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			struct vring *vring, struct sk_buff *skb);
+			struct wil_ring *vring, struct sk_buff *skb);
 
-static struct vring *wil_find_tx_vring_sta(struct wil6210_priv *wil,
-					   struct wil6210_vif *vif,
-					   struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_ring_sta(struct wil6210_priv *wil,
+					     struct wil6210_vif *vif,
+					     struct sk_buff *skb)
 {
-	struct vring *v;
+	struct wil_ring *ring;
 	int i;
 	u8 cid;
-	struct vring_tx_data *txdata;
+	struct wil_ring_tx_data  *txdata;
 
 	/* In the STA mode, it is expected to have only 1 VRING
 	 * for the AP we connected to.
 	 * find 1-st vring eligible for this skb and use it.
 	 */
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		v = &wil->vring_tx[i];
-		txdata = &wil->vring_tx_data[i];
-		if (!v->va || !txdata->enabled || txdata->mid != vif->mid)
+		ring = &wil->ring_tx[i];
+		txdata = &wil->ring_tx_data[i];
+		if (!ring->va || !txdata->enabled || txdata->mid != vif->mid)
 			continue;
 
-		cid = wil->vring2cid_tid[i][0];
+		cid = wil->ring2cid_tid[i][0];
 		if (cid >= WIL6210_MAX_CID) /* skip BCAST */
 			continue;
 
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
 
 		wil_dbg_txrx(wil, "Tx -> ring %d\n", i);
 
-		return v;
+		return ring;
 	}
 
-	wil_dbg_txrx(wil, "Tx while no vrings active?\n");
+	wil_dbg_txrx(wil, "Tx while no rings active?\n");
 
 	return NULL;
 }
@@ -1225,22 +1193,22 @@ static struct vring *wil_find_tx_vring_sta(struct wil6210_priv *wil,
  * Use old strategy when new is not supported yet:
  *  - for PBSS
  */
-static struct vring *wil_find_tx_bcast_1(struct wil6210_priv *wil,
-					 struct wil6210_vif *vif,
-					 struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_bcast_1(struct wil6210_priv *wil,
+					    struct wil6210_vif *vif,
+					    struct sk_buff *skb)
 {
-	struct vring *v;
-	struct vring_tx_data *txdata;
-	int i = vif->bcast_vring;
+	struct wil_ring *v;
+	struct wil_ring_tx_data *txdata;
+	int i = vif->bcast_ring;
 
 	if (i < 0)
 		return NULL;
-	v = &wil->vring_tx[i];
-	txdata = &wil->vring_tx_data[i];
+	v = &wil->ring_tx[i];
+	txdata = &wil->ring_tx_data[i];
 	if (!v->va || !txdata->enabled)
 		return NULL;
-	if (!wil->vring_tx_data[i].dot1x_open &&
-	    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+	if (!wil->ring_tx_data[i].dot1x_open &&
+	    skb->protocol != cpu_to_be16(ETH_P_PAE))
 		return NULL;
 
 	return v;
@@ -1250,35 +1218,35 @@ static void wil_set_da_for_vring(struct wil6210_priv *wil,
 				 struct sk_buff *skb, int vring_index)
 {
 	struct ethhdr *eth = (void *)skb->data;
-	int cid = wil->vring2cid_tid[vring_index][0];
+	int cid = wil->ring2cid_tid[vring_index][0];
 
 	ether_addr_copy(eth->h_dest, wil->sta[cid].addr);
 }
 
-static struct vring *wil_find_tx_bcast_2(struct wil6210_priv *wil,
-					 struct wil6210_vif *vif,
-					 struct sk_buff *skb)
+static struct wil_ring *wil_find_tx_bcast_2(struct wil6210_priv *wil,
+					    struct wil6210_vif *vif,
+					    struct sk_buff *skb)
 {
-	struct vring *v, *v2;
+	struct wil_ring *v, *v2;
 	struct sk_buff *skb2;
 	int i;
 	u8 cid;
 	struct ethhdr *eth = (void *)skb->data;
 	char *src = eth->h_source;
-	struct vring_tx_data *txdata, *txdata2;
+	struct wil_ring_tx_data *txdata, *txdata2;
 
 	/* find 1-st vring eligible for data */
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		v = &wil->vring_tx[i];
-		txdata = &wil->vring_tx_data[i];
+		v = &wil->ring_tx[i];
+		txdata = &wil->ring_tx_data[i];
 		if (!v->va || !txdata->enabled || txdata->mid != vif->mid)
 			continue;
 
-		cid = wil->vring2cid_tid[i][0];
+		cid = wil->ring2cid_tid[i][0];
 		if (cid >= WIL6210_MAX_CID) /* skip BCAST */
 			continue;
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
 
 		/* don't Tx back to source when re-routing Rx->Tx at the AP */
@@ -1298,15 +1266,15 @@ found:
 
 	/* find other active vrings and duplicate skb for each */
 	for (i++; i < WIL6210_MAX_TX_RINGS; i++) {
-		v2 = &wil->vring_tx[i];
-		txdata2 = &wil->vring_tx_data[i];
+		v2 = &wil->ring_tx[i];
+		txdata2 = &wil->ring_tx_data[i];
 		if (!v2->va || txdata2->mid != vif->mid)
 			continue;
-		cid = wil->vring2cid_tid[i][0];
+		cid = wil->ring2cid_tid[i][0];
 		if (cid >= WIL6210_MAX_CID) /* skip BCAST */
 			continue;
-		if (!wil->vring_tx_data[i].dot1x_open &&
-		    (skb->protocol != cpu_to_be16(ETH_P_PAE)))
+		if (!wil->ring_tx_data[i].dot1x_open &&
+		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
 
 		if (0 == memcmp(wil->sta[cid].addr, src, ETH_ALEN))
@@ -1454,7 +1422,7 @@ static inline void wil_set_tx_desc_last_tso(volatile struct vring_tx_desc *d)
 }
 
 static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			      struct vring *vring, struct sk_buff *skb)
+			      struct wil_ring *vring, struct sk_buff *skb)
 {
 	struct device *dev = wil_to_dev(wil);
 
@@ -1474,13 +1442,13 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	int sg_desc_cnt = 0; /* number of descriptors for current mss*/
 
 	u32 swhead = vring->swhead;
-	int used, avail = wil_vring_avail_tx(vring);
+	int used, avail = wil_ring_avail_tx(vring);
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 	int min_desc_required = nr_frags + 1;
 	int mss = skb_shinfo(skb)->gso_size;	/* payload size w/o headers */
 	int f, len, hdrlen, headlen;
-	int vring_index = vring - wil->vring_tx;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+	int vring_index = vring - wil->ring_tx;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[vring_index];
 	uint i = swhead;
 	dma_addr_t pa;
 	const skb_frag_t *frag = NULL;
@@ -1548,7 +1516,7 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	tcp_hdr_len = tcp_hdrlen(skb);
 	skb_net_hdr_len = skb_network_header_len(skb);
 
-	_hdr_desc = &vring->va[i].tx;
+	_hdr_desc = &vring->va[i].tx.legacy;
 
 	pa = dma_map_single(dev, skb->data, hdrlen, DMA_TO_DEVICE);
 	if (unlikely(dma_mapping_error(dev, pa))) {
@@ -1613,7 +1581,7 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 				goto mem_error;
 			}
 
-			_desc = &vring->va[i].tx;
+			_desc = &vring->va[i].tx.legacy;
 
 			if (!_first_desc) {
 				_first_desc = _desc;
@@ -1701,8 +1669,8 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	vring->ctx[i].skb = skb_get(skb);
 
 	/* performance monitoring */
-	used = wil_vring_used_tx(vring);
-	if (wil_val_in_range(wil->vring_idle_trsh,
+	used = wil_ring_used_tx(vring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
 			     used, used + descs_used)) {
 		txdata->idle += get_cycles() - txdata->last_idle;
 		wil_dbg_txrx(wil,  "Ring[%2d] not idle %d -> %d\n",
@@ -1717,7 +1685,7 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	wmb();
 
 	/* advance swhead */
-	wil_vring_advance_head(vring, descs_used);
+	wil_ring_advance_head(vring, descs_used);
 	wil_dbg_txrx(wil, "TSO: Tx swhead %d -> %d\n", swhead, vring->swhead);
 
 	/* make sure all writes to descriptors (shared memory) are done before
@@ -1733,8 +1701,8 @@ mem_error:
 		struct wil_ctx *ctx;
 
 		i = (swhead + descs_used - 1) % vring->size;
-		d = (struct vring_tx_desc *)&vring->va[i].tx;
-		_desc = &vring->va[i].tx;
+		d = (struct vring_tx_desc *)&vring->va[i].tx.legacy;
+		_desc = &vring->va[i].tx.legacy;
 		*d = *_desc;
 		_desc->dma.status = TX_DMA_STATUS_DU;
 		ctx = &vring->ctx[i];
@@ -1747,25 +1715,25 @@ err_exit:
 }
 
 static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			  struct vring *vring, struct sk_buff *skb)
+			  struct wil_ring *vring, struct sk_buff *skb)
 {
 	struct device *dev = wil_to_dev(wil);
 	struct vring_tx_desc dd, *d = &dd;
 	volatile struct vring_tx_desc *_d;
 	u32 swhead = vring->swhead;
-	int avail = wil_vring_avail_tx(vring);
+	int avail = wil_ring_avail_tx(vring);
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 	uint f = 0;
-	int vring_index = vring - wil->vring_tx;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+	int vring_index = vring - wil->ring_tx;
+	struct wil_ring_tx_data  *txdata = &wil->ring_tx_data[vring_index];
 	uint i = swhead;
 	dma_addr_t pa;
 	int used;
-	bool mcast = (vring_index == vif->bcast_vring);
+	bool mcast = (vring_index == vif->bcast_ring);
 	uint len = skb_headlen(skb);
 
-	wil_dbg_txrx(wil, "tx_vring: %d bytes to vring %d\n", skb->len,
-		     vring_index);
+	wil_dbg_txrx(wil, "tx_ring: %d bytes to ring %d, nr_frags %d\n",
+		     skb->len, vring_index, nr_frags);
 
 	if (unlikely(!txdata->enabled))
 		return -EINVAL;
@@ -1776,7 +1744,7 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 				    vring_index, 1 + nr_frags);
 		return -ENOMEM;
 	}
-	_d = &vring->va[i].tx;
+	_d = &vring->va[i].tx.legacy;
 
 	pa = dma_map_single(dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE);
 
@@ -1816,7 +1784,7 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 		wil_hex_dump_txrx("TxD ", DUMP_PREFIX_NONE, 32, 4,
 				  (const void *)d, sizeof(*d), false);
 		i = (swhead + f + 1) % vring->size;
-		_d = &vring->va[i].tx;
+		_d = &vring->va[i].tx.legacy;
 		pa = skb_frag_dma_map(dev, frag, 0, skb_frag_size(frag),
 				      DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(dev, pa))) {
@@ -1848,8 +1816,8 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	vring->ctx[i].skb = skb_get(skb);
 
 	/* performance monitoring */
-	used = wil_vring_used_tx(vring);
-	if (wil_val_in_range(wil->vring_idle_trsh,
+	used = wil_ring_used_tx(vring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
 			     used, used + nr_frags + 1)) {
 		txdata->idle += get_cycles() - txdata->last_idle;
 		wil_dbg_txrx(wil,  "Ring[%2d] not idle %d -> %d\n",
@@ -1864,7 +1832,7 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	wmb();
 
 	/* advance swhead */
-	wil_vring_advance_head(vring, nr_frags + 1);
+	wil_ring_advance_head(vring, nr_frags + 1);
 	wil_dbg_txrx(wil, "Tx[%2d] swhead %d -> %d\n", vring_index, swhead,
 		     vring->swhead);
 	trace_wil6210_tx(vring_index, swhead, skb->len, nr_frags);
@@ -1885,7 +1853,7 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 
 		i = (swhead + f) % vring->size;
 		ctx = &vring->ctx[i];
-		_d = &vring->va[i].tx;
+		_d = &vring->va[i].tx.legacy;
 		*d = *_d;
 		_d->dma.status = TX_DMA_STATUS_DU;
 		wil_txdesc_unmap(dev, d, ctx);
@@ -1897,10 +1865,10 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 }
 
 static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			struct vring *vring, struct sk_buff *skb)
+			struct wil_ring *vring, struct sk_buff *skb)
 {
-	int vring_index = vring - wil->vring_tx;
-	struct vring_tx_data *txdata = &wil->vring_tx_data[vring_index];
+	int ring_index = vring - wil->ring_tx;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_index];
 	int rc;
 
 	spin_lock(&txdata->lock);
@@ -1941,7 +1909,7 @@ static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
  */
 static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 					   struct wil6210_vif *vif,
-					   struct vring *vring,
+					   struct wil_ring *ring,
 					   bool check_stop)
 {
 	int i;
@@ -1949,9 +1917,9 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 	if (unlikely(!vif))
 		return;
 
-	if (vring)
+	if (ring)
 		wil_dbg_txrx(wil, "vring %d, mid %d, check_stop=%d, stopped=%d",
-			     (int)(vring - wil->vring_tx), vif->mid, check_stop,
+			     (int)(ring - wil->ring_tx), vif->mid, check_stop,
 			     vif->net_queue_stopped);
 	else
 		wil_dbg_txrx(wil, "check_stop=%d, mid=%d, stopped=%d",
@@ -1962,7 +1930,7 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 		return;
 
 	if (check_stop) {
-		if (!vring || unlikely(wil_vring_avail_low(vring))) {
+		if (!ring || unlikely(wil_ring_avail_low(ring))) {
 			/* not enough room in the vring */
 			netif_tx_stop_all_queues(vif_to_ndev(vif));
 			vif->net_queue_stopped = true;
@@ -1978,22 +1946,22 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 
 	/* check wake */
 	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
-		struct vring *cur_vring = &wil->vring_tx[i];
-		struct vring_tx_data *txdata = &wil->vring_tx_data[i];
+		struct wil_ring *cur_ring = &wil->ring_tx[i];
+		struct wil_ring_tx_data  *txdata = &wil->ring_tx_data[i];
 
-		if (txdata->mid != vif->mid || !cur_vring->va ||
-		    !txdata->enabled || cur_vring == vring)
+		if (txdata->mid != vif->mid || !cur_ring->va ||
+		    !txdata->enabled || cur_ring == ring)
 			continue;
 
-		if (wil_vring_avail_low(cur_vring)) {
-			wil_dbg_txrx(wil, "vring %d full, can't wake\n",
-				     (int)(cur_vring - wil->vring_tx));
+		if (wil_ring_avail_low(cur_ring)) {
+			wil_dbg_txrx(wil, "ring %d full, can't wake\n",
+				     (int)(cur_ring - wil->ring_tx));
 			return;
 		}
 	}
 
-	if (!vring || wil_vring_avail_high(vring)) {
-		/* enough room in the vring */
+	if (!ring || wil_ring_avail_high(ring)) {
+		/* enough room in the ring */
 		wil_dbg_txrx(wil, "calling netif_tx_wake\n");
 		netif_tx_wake_all_queues(vif_to_ndev(vif));
 		vif->net_queue_stopped = false;
@@ -2001,18 +1969,18 @@ static inline void __wil_update_net_queues(struct wil6210_priv *wil,
 }
 
 void wil_update_net_queues(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			   struct vring *vring, bool check_stop)
+			   struct wil_ring *ring, bool check_stop)
 {
 	spin_lock(&wil->net_queue_lock);
-	__wil_update_net_queues(wil, vif, vring, check_stop);
+	__wil_update_net_queues(wil, vif, ring, check_stop);
 	spin_unlock(&wil->net_queue_lock);
 }
 
 void wil_update_net_queues_bh(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			      struct vring *vring, bool check_stop)
+			      struct wil_ring *ring, bool check_stop)
 {
 	spin_lock_bh(&wil->net_queue_lock);
-	__wil_update_net_queues(wil, vif, vring, check_stop);
+	__wil_update_net_queues(wil, vif, ring, check_stop);
 	spin_unlock_bh(&wil->net_queue_lock);
 }
 
@@ -2022,7 +1990,7 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	struct ethhdr *eth = (void *)skb->data;
 	bool bcast = is_multicast_ether_addr(eth->h_dest);
-	struct vring *vring;
+	struct wil_ring *vring;
 	static bool pr_once_fw;
 	int rc;
 
@@ -2048,7 +2016,7 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	/* find vring */
 	if (vif->wdev.iftype == NL80211_IFTYPE_STATION && !vif->pbss) {
 		/* in STA mode (ESS), all to same VRING (to AP) */
-		vring = wil_find_tx_vring_sta(wil, vif, skb);
+		vring = wil_find_tx_ring_sta(wil, vif, skb);
 	} else if (bcast) {
 		if (vif->pbss)
 			/* in pbss, no bcast VRING - duplicate skb in
@@ -2068,7 +2036,7 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		vring = wil_find_tx_ucast(wil, vif, skb);
 	}
 	if (unlikely(!vring)) {
-		wil_dbg_txrx(wil, "No Tx VRING found for %pM\n", eth->h_dest);
+		wil_dbg_txrx(wil, "No Tx RING found for %pM\n", eth->h_dest);
 		goto drop;
 	}
 	/* set up vring entry */
@@ -2121,10 +2089,10 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	struct net_device *ndev = vif_to_ndev(vif);
 	struct device *dev = wil_to_dev(wil);
-	struct vring *vring = &wil->vring_tx[ringid];
-	struct vring_tx_data *txdata = &wil->vring_tx_data[ringid];
+	struct wil_ring *vring = &wil->ring_tx[ringid];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ringid];
 	int done = 0;
-	int cid = wil->vring2cid_tid[ringid][0];
+	int cid = wil->ring2cid_tid[ringid][0];
 	struct wil_net_stats *stats = NULL;
 	volatile struct vring_tx_desc *_d;
 	int used_before_complete;
@@ -2142,12 +2110,12 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 
 	wil_dbg_txrx(wil, "tx_complete: (%d)\n", ringid);
 
-	used_before_complete = wil_vring_used_tx(vring);
+	used_before_complete = wil_ring_used_tx(vring);
 
 	if (cid < WIL6210_MAX_CID)
 		stats = &wil->sta[cid].stats;
 
-	while (!wil_vring_is_empty(vring)) {
+	while (!wil_ring_is_empty(vring)) {
 		int new_swtail;
 		struct wil_ctx *ctx = &vring->ctx[vring->swtail];
 		/**
@@ -2158,7 +2126,7 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 		int lf = (vring->swtail + ctx->nr_frags) % vring->size;
 		/* TODO: check we are not past head */
 
-		_d = &vring->va[lf].tx;
+		_d = &vring->va[lf].tx.legacy;
 		if (unlikely(!(_d->dma.status & TX_DMA_STATUS_DU)))
 			break;
 
@@ -2170,7 +2138,7 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 
 			ctx = &vring->ctx[vring->swtail];
 			skb = ctx->skb;
-			_d = &vring->va[vring->swtail].tx;
+			_d = &vring->va[vring->swtail].tx.legacy;
 
 			*d = *_d;
 
@@ -2203,7 +2171,7 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 			}
 			memset(ctx, 0, sizeof(*ctx));
 			/* Make sure the ctx is zeroed before updating the tail
-			 * to prevent a case where wil_tx_vring will see
+			 * to prevent a case where wil_tx_ring will see
 			 * this descriptor as used and handle it before ctx zero
 			 * is completed.
 			 */
@@ -2213,14 +2181,14 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 			 *   so hardware will not try to process this desc.,
 			 * - rest of descriptor will be initialized on Tx.
 			 */
-			vring->swtail = wil_vring_next_tail(vring);
+			vring->swtail = wil_ring_next_tail(vring);
 			done++;
 		}
 	}
 
 	/* performance monitoring */
-	used_new = wil_vring_used_tx(vring);
-	if (wil_val_in_range(wil->vring_idle_trsh,
+	used_new = wil_ring_used_tx(vring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
 			     used_new, used_before_complete)) {
 		wil_dbg_txrx(wil, "Ring[%2d] idle %d -> %d\n",
 			     ringid, used_before_complete, used_new);
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 5f07717acc2c..66217f815726 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -18,6 +18,9 @@
 #ifndef WIL6210_TXRX_H
 #define WIL6210_TXRX_H
 
+#include "wil6210.h"
+#include "txrx_edma.h"
+
 #define BUF_SW_OWNED    (1)
 #define BUF_HW_OWNED    (0)
 
@@ -29,19 +32,13 @@
 
 /* Tx/Rx path */
 
-/* Common representation of physical address in Vring */
-struct vring_dma_addr {
-	__le32 addr_low;
-	__le16 addr_high;
-} __packed;
-
-static inline dma_addr_t wil_desc_addr(struct vring_dma_addr *addr)
+static inline dma_addr_t wil_desc_addr(struct wil_ring_dma_addr *addr)
 {
 	return le32_to_cpu(addr->addr_low) |
 			   ((u64)le16_to_cpu(addr->addr_high) << 32);
 }
 
-static inline void wil_desc_addr_set(struct vring_dma_addr *addr,
+static inline void wil_desc_addr_set(struct wil_ring_dma_addr *addr,
 				     dma_addr_t pa)
 {
 	addr->addr_low = cpu_to_le32(lower_32_bits(pa));
@@ -294,7 +291,7 @@ struct vring_tx_mac {
  */
 struct vring_tx_dma {
 	u32 d0;
-	struct vring_dma_addr addr;
+	struct wil_ring_dma_addr addr;
 	u8  ip_length;
 	u8  b11;       /* 0..6: mac_length; 7:ip_version */
 	u8  error;     /* 0..2: err; 3..7: reserved; */
@@ -428,7 +425,7 @@ struct vring_rx_mac {
 
 struct vring_rx_dma {
 	u32 d0;
-	struct vring_dma_addr addr;
+	struct wil_ring_dma_addr addr;
 	u8  ip_length;
 	u8  b11;
 	u8  error;
@@ -441,14 +438,24 @@ struct vring_tx_desc {
 	struct vring_tx_dma dma;
 } __packed;
 
+union wil_tx_desc {
+	struct vring_tx_desc legacy;
+	struct wil_tx_enhanced_desc enhanced;
+} __packed;
+
 struct vring_rx_desc {
 	struct vring_rx_mac mac;
 	struct vring_rx_dma dma;
 } __packed;
 
-union vring_desc {
-	struct vring_tx_desc tx;
-	struct vring_rx_desc rx;
+union wil_rx_desc {
+	struct vring_rx_desc legacy;
+	struct wil_rx_enhanced_desc enhanced;
+} __packed;
+
+union wil_ring_desc {
+	union wil_tx_desc tx;
+	union wil_rx_desc rx;
 } __packed;
 
 static inline int wil_rxdesc_tid(struct vring_rx_desc *d)
@@ -528,6 +535,41 @@ static inline struct vring_rx_desc *wil_skb_rxdesc(struct sk_buff *skb)
 	return (void *)skb->cb;
 }
 
+static inline int wil_ring_is_empty(struct wil_ring *ring)
+{
+	return ring->swhead == ring->swtail;
+}
+
+static inline u32 wil_ring_next_tail(struct wil_ring *ring)
+{
+	return (ring->swtail + 1) % ring->size;
+}
+
+static inline void wil_ring_advance_head(struct wil_ring *ring, int n)
+{
+	ring->swhead = (ring->swhead + n) % ring->size;
+}
+
+static inline int wil_ring_is_full(struct wil_ring *ring)
+{
+	return wil_ring_next_tail(ring) == ring->swhead;
+}
+
+/* Used space in Tx ring */
+static inline int wil_ring_used_tx(struct wil_ring *ring)
+{
+	u32 swhead = ring->swhead;
+	u32 swtail = ring->swtail;
+
+	return (ring->size + swhead - swtail) % ring->size;
+}
+
+/* Available space in Tx ring */
+static inline int wil_ring_avail_tx(struct wil_ring *ring)
+{
+	return ring->size - wil_ring_used_tx(ring) - 1;
+}
+
 void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev);
 void wil_rx_reorder(struct wil6210_priv *wil, struct sk_buff *skb);
 void wil_rx_bar(struct wil6210_priv *wil, struct wil6210_vif *vif,
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
new file mode 100644
index 000000000000..14e0b6ce6dc4
--- /dev/null
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -0,0 +1,290 @@
+/*
+ * Copyright (c) 2012-2016,2018, The Linux Foundation. All rights reserved.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef WIL6210_TXRX_EDMA_H
+#define WIL6210_TXRX_EDMA_H
+
+#include "wil6210.h"
+
+/* Enhanced Rx descriptor - MAC part
+ * [dword 0] : Reserved
+ * [dword 1] : Reserved
+ * [dword 2] : Reserved
+ * [dword 3]
+ *	bit  0..15 : Buffer ID
+ *	bit 16..31 : Reserved
+ */
+struct wil_ring_rx_enhanced_mac {
+	u32 d[3];
+	__le16 buff_id;
+	u16 reserved;
+} __packed;
+
+/* Enhanced Rx descriptor - DMA part
+ * [dword 0] - Reserved
+ * [dword 1]
+ *	bit  0..31 : addr_low:32 The payload buffer address, bits 0-31
+ * [dword 2]
+ *	bit  0..15 : addr_high_low:16 The payload buffer address, bits 32-47
+ *	bit 16..31 : Reserved
+ * [dword 3]
+ *	bit  0..15 : addr_high_high:16 The payload buffer address, bits 48-63
+ *	bit 16..31 : length
+ */
+struct wil_ring_rx_enhanced_dma {
+	u32 d0;
+	struct wil_ring_dma_addr addr;
+	u16 w5;
+	__le16 addr_high_high;
+	__le16 length;
+} __packed;
+
+struct wil_rx_enhanced_desc {
+	struct wil_ring_rx_enhanced_mac mac;
+	struct wil_ring_rx_enhanced_dma dma;
+} __packed;
+
+/* Enhanced Tx descriptor - DMA part
+ * [dword 0]
+ *	Same as legacy
+ * [dword 1]
+ * bit  0..31 : addr_low:32 The payload buffer address, bits 0-31
+ * [dword 2]
+ * bit  0..15 : addr_high_low:16 The payload buffer address, bits 32-47
+ * bit 16..23 : ip_length:8 The IP header length for the TX IP checksum
+ *		offload feature
+ * bit 24..30 : mac_length:7
+ * bit     31 : ip_version:1 1 - IPv4, 0 - IPv6
+ * [dword 3]
+ * bit  0..15 : addr_high_high:16 The payload buffer address, bits 48-63
+ * bit 16..31 : length
+ */
+struct wil_ring_tx_enhanced_dma {
+	u8 l4_hdr_len;
+	u8 cmd;
+	u16 w1;
+	struct wil_ring_dma_addr addr;
+	u8  ip_length;
+	u8  b11;       /* 0..6: mac_length; 7:ip_version */
+	__le16 addr_high_high;
+	__le16 length;
+} __packed;
+
+/* Enhanced Tx descriptor - MAC part
+ * [dword 0]
+ * bit  0.. 9 : lifetime_expiry_value:10
+ * bit     10 : interrupt_en:1
+ * bit     11 : status_en:1
+ * bit 12..13 : txss_override:2
+ * bit     14 : timestamp_insertion:1
+ * bit     15 : duration_preserve:1
+ * bit 16..21 : reserved0:6
+ * bit 22..26 : mcs_index:5
+ * bit     27 : mcs_en:1
+ * bit 28..30 : reserved1:3
+ * bit     31 : sn_preserved:1
+ * [dword 1]
+ * bit  0.. 3 : pkt_mode:4
+ * bit      4 : pkt_mode_en:1
+ * bit  5..14 : reserved0:10
+ * bit     15 : ack_policy_en:1
+ * bit 16..19 : dst_index:4
+ * bit     20 : dst_index_en:1
+ * bit 21..22 : ack_policy:2
+ * bit     23 : lifetime_en:1
+ * bit 24..30 : max_retry:7
+ * bit     31 : max_retry_en:1
+ * [dword 2]
+ * bit  0.. 7 : num_of_descriptors:8
+ * bit  8..17 : reserved:10
+ * bit 18..19 : l2_translation_type:2 00 - bypass, 01 - 802.3, 10 - 802.11
+ * bit     20 : snap_hdr_insertion_en:1
+ * bit     21 : vlan_removal_en:1
+ * bit 22..23 : reserved0:2
+ * bit	   24 : Dest ID extension:1
+ * bit 25..31 : reserved0:7
+ * [dword 3]
+ * bit  0..15 : tso_mss:16
+ * bit 16..31 : descriptor_scratchpad:16 - mailbox between driver and ucode
+ */
+struct wil_ring_tx_enhanced_mac {
+	u32 d[3];
+	__le16 tso_mss;
+	u16 scratchpad;
+} __packed;
+
+struct wil_tx_enhanced_desc {
+	struct wil_ring_tx_enhanced_mac mac;
+	struct wil_ring_tx_enhanced_dma dma;
+} __packed;
+
+#define TX_STATUS_DESC_READY_POS 7
+
+/* Enhanced TX status message
+ * [dword 0]
+ *	bit  0.. 7 : Number of Descriptor:8 - The number of descriptors that
+ *		     are used to form the packets. It  is needed for WB when
+ *		     releasing the packet
+ *	bit  8..15 : tx_ring_id:8 The transmission ring ID that is related to
+ *		     the message
+ *	bit 16..23 : Status:8 - The TX status Code
+ *		0x0 - A successful transmission
+ *		0x1 - Retry expired
+ *		0x2 - Lifetime Expired
+ *		0x3 - Released
+ *		0x4-0xFF - Reserved
+ *	bit 24..30 : Reserved:7
+ *	bit     31 : Descriptor Ready bit:1 - It is initiated to
+ *		zero by the driver when the ring is created. It is set by the HW
+ *		to one for each completed status message. Each wrap around,
+ *		the DR bit value is flipped.
+ * [dword 1]
+ *	bit 0..31  : timestamp:32 - Set when MPDU is transmitted.
+ * [dword 2]
+ *	bit  0.. 4 : MCS:5 - The transmitted MCS value
+ *	bit      5 : Reserved:1
+ *	bit  6.. 7 : CB mode:2 - 0-DMG 1-EDMG 2-Wide
+ *	bit  8..12 : QID:5 - The QID that was used for the transmission
+ *	bit 13..15 : Reserved:3
+ *	bit 16..20 : Num of MSDUs:5 - Number of MSDUs in the aggregation
+ *	bit 21..22 : Reserved:2
+ *	bit     23 : Retry:1 - An indication that the transmission was retried
+ *	bit 24..31 : TX-Sector:8 - the antenna sector that was used for
+ *		     transmission
+ * [dword 3]
+ *	bit  0..11 : Sequence number:12 - The Sequence Number that was used
+ *		     for the MPDU transmission
+ *	bit 12..31 : Reserved:20
+ */
+struct wil_ring_tx_status {
+	u8 num_descriptors;
+	u8 ring_id;
+	u8 status;
+	u8 desc_ready; /* Only the last bit should be set */
+	u32 timestamp;
+	u32 d2;
+	u16 seq_number; /* Only the first 12 bits */
+	u16 w7;
+} __packed;
+
+/* Enhanced Rx status message - compressed part
+ * [dword 0]
+ *	bit  0.. 2 : L2 Rx Status:3 - The L2 packet reception Status
+ *		     0-Success, 1-MIC Error, 2-Key Error, 3-Replay Error,
+ *		     4-A-MSDU Error, 5-Reserved, 6-Reserved, 7-FCS Error
+ *	bit  3.. 4 : L3 Rx Status:2 - Bit0 - L3I - L3 identified and checksum
+ *		     calculated, Bit1- L3Err - IPv4 Checksum Error
+ *	bit  5.. 6 : L4 Rx Status:2 - Bit0 - L4I - L4 identified and checksum
+ *		     calculated, Bit1- L4Err - TCP/UDP Checksum Error
+ *	bit      7 : Reserved:1
+ *	bit  8..19 : Flow ID:12 - MSDU flow ID
+ *	bit 20..21 : MID:2 - The MAC ID
+ *	bit     22 : MID_V:1 - The MAC ID field is valid
+ *	bit     23 : L3T:1 - IP types: 0-IPv6, 1-IPv4
+ *	bit     24 : L4T:1 - Layer 4 Type: 0-UDP, 1-TCP
+ *	bit     25 : BC:1 - The received MPDU is broadcast
+ *	bit     26 : MC:1 - The received MPDU is multicast
+ *	bit     27 : Raw:1 - The MPDU received with no translation
+ *	bit     28 : Sec:1 - The FC control (b14) - Frame Protected
+ *	bit     29 : Error:1 - An error is set when (L2 status != 0) ||
+ *		(L3 status == 3) || (L4 status == 3)
+ *	bit     30 : EOP:1 - End of MSDU signaling. It is set to mark the end
+ *		     of the transfer, otherwise the status indicates buffer
+ *		     only completion.
+ *	bit     31 : Descriptor Ready bit:1 - It is initiated to
+ *		     zero by the driver when the ring is created. It is set
+ *		     by the HW to one for each completed status message.
+ *		     Each wrap around, the DR bit value is flipped.
+ * [dword 1]
+ *	bit  0.. 5 : MAC Len:6 - The number of bytes that are used for L2 header
+ *	bit  6..11 : IPLEN:6 - The number of DW that are used for L3 header
+ *	bit 12..15 : I4Len:4 - The number of DW that are used for L4 header
+ *	bit 16..21 : MCS:6 - The received MCS field from the PLCP Header
+ *	bit 22..23 : CB mode:2 - The CB Mode: 0-DMG, 1-EDMG, 2-Wide
+ *	bit 24..27 : Data Offset:4 - The data offset, a code that describe the
+ *		     payload shift from the beginning of the buffer:
+ *		     0 - 0 Bytes, 1 - 2 Bytes, 2 - 6 Bytes
+ *	bit     28 : A-MSDU Present:1 - The QoS (b7) A-MSDU present field
+ *	bit     29 : A-MSDU Type:1 The QoS (b8) A-MSDU Type field
+ *	bit     30 : A-MPDU:1 - Packet is part of aggregated MPDU
+ *	bit     31 : Key ID:1 - The extracted Key ID from the encryption header
+ * [dword 2]
+ *	bit  0..15 : Buffer ID:16 - The Buffer Identifier
+ *	bit 16..31 : Length:16 - It indicates the valid bytes that are stored
+ *		     in the current descriptor buffer. For multiple buffer
+ *		     descriptor, SW need to sum the total descriptor length
+ *		     in all buffers to produce the packet length
+ * [dword 3]
+ *	bit  0..31  : timestamp:32 - The MPDU Timestamp.
+ */
+struct wil_rx_status_compressed {
+	u32 d0;
+	u32 d1;
+	__le16 buff_id;
+	__le16 length;
+	u32 timestamp;
+} __packed;
+
+/* Enhanced Rx status message - extension part
+ * [dword 0]
+ *	bit  0.. 4 : QID:5 - The Queue Identifier that the packet is received
+ *		     from
+ *	bit  5.. 7 : Reserved:3
+ *	bit  8..11 : TID:4 - The QoS (b3-0) TID Field
+ *	bit 12..15   Source index:4 - The Source index that was found
+		     during Parsing the TA. This field is used to define the
+		     source of the packet
+ *	bit 16..18 : Destination index:3 - The Destination index that
+		     was found during Parsing the RA.
+ *	bit 19..20 : DS Type:2 - The FC Control (b9-8) - From / To DS
+ *	bit 21..22 : MIC ICR:2 - this signal tells the DMA to assert an
+		     interrupt after it writes the packet
+ *	bit     23 : ESOP:1 - The QoS (b4) ESOP field
+ *	bit     24 : RDG:1
+ *	bit 25..31 : Reserved:7
+ * [dword 1]
+ *	bit  0.. 1 : Frame Type:2 - The FC Control (b3-2) - MPDU Type
+		     (management, data, control and extension)
+ *	bit  2.. 5 : Syb type:4 - The FC Control (b7-4) - Frame Subtype
+ *	bit  6..11 : Ext sub type:6 - The FC Control (b11-8) - Frame Extended
+ *                   Subtype
+ *	bit 12..13 : ACK Policy:2 - The QoS (b6-5) ACK Policy fields
+ *	bit 14     : DECRYPT_BYP:1 - The MPDU is bypass by the decryption unit
+ *	bit 15..23 : Reserved:9
+ *	bit 24..31 : RSSI/SNR:8 - The RSSI / SNR measurement for the received
+ *                   MPDU
+ * [dword 2]
+ *	bit  0..11 : SN:12 - The received Sequence number field
+ *	bit 12..15 : Reserved:4
+ *	bit 16..31 : PN bits [15:0]:16
+ * [dword 3]
+ *	bit  0..31 : PN bits [47:16]:32
+ */
+struct wil_rx_status_extension {
+	u32 d0;
+	u32 d1;
+	__le16 seq_num; /* only lower 12 bits */
+	u16 pn_15_0;
+	u32 pn_47_16;
+} __packed;
+
+struct wil_rx_status_extended {
+	struct wil_rx_status_compressed comp;
+	struct wil_rx_status_extension ext;
+};
+
+#endif /* WIL6210_TXRX_EDMA_H */
+
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 4cd8e4030fe9..810ed5b8e558 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -80,6 +80,8 @@ static inline u32 WIL_GET_BITS(u32 x, int b0, int b1)
 #define WIL6210_NAPI_BUDGET	(16) /* arbitrary */
 #define WIL_MAX_AMPDU_SIZE	(64 * 1024) /* FW/HW limit */
 #define WIL_MAX_AGG_WSIZE	(32) /* FW/HW limit */
+#define WIL6210_MAX_STATUS_RINGS	(8)
+
 /* Hardware offload block adds the following:
  * 26 bytes - 3-address QoS data header
  *  8 bytes - IV + EIV (for GCMP)
@@ -359,6 +361,12 @@ enum {
 #define TALYN_MB_FW_MAPPING_TABLE_SIZE 19
 #define MAX_FW_MAPPING_TABLE_SIZE 19
 
+/* Common representation of physical address in wil ring */
+struct wil_ring_dma_addr {
+	__le32 addr_low;
+	__le16 addr_high;
+} __packed;
+
 struct fw_map {
 	u32 from; /* linker address - from, inclusive */
 	u32 to;   /* linker address - to, exclusive */
@@ -447,7 +455,7 @@ enum { /* for wil_ctx.mapped_as */
 };
 
 /**
- * struct wil_ctx - software context for Vring descriptor
+ * struct wil_ctx - software context for ring descriptor
  */
 struct wil_ctx {
 	struct sk_buff *skb;
@@ -455,22 +463,59 @@ struct wil_ctx {
 	u8 mapped_as;
 };
 
-union vring_desc;
+struct wil_desc_ring_rx_swtail { /* relevant for enhanced DMA only */
+	u32 *va;
+	dma_addr_t pa;
+};
 
-struct vring {
+/**
+ * A general ring structure, used for RX and TX.
+ * In legacy DMA it represents the vring,
+ * In enahnced DMA it represents the descriptor ring (vrings are handled by FW)
+ */
+struct wil_ring {
 	dma_addr_t pa;
-	volatile union vring_desc *va; /* vring_desc[size], WriteBack by DMA */
-	u16 size; /* number of vring_desc elements */
+	volatile union wil_ring_desc *va;
+	u16 size; /* number of wil_ring_desc elements */
 	u32 swtail;
 	u32 swhead;
 	u32 hwtail; /* write here to inform hw */
 	struct wil_ctx *ctx; /* ctx[size] - software context */
+	struct wil_desc_ring_rx_swtail edma_rx_swtail;
+	bool is_rx;
 };
 
 /**
- * Additional data for Tx Vring
+ * Additional data for Rx ring.
+ * Used for enhanced DMA RX chaining.
  */
-struct vring_tx_data {
+struct wil_ring_rx_data {
+	/* the skb being assembled */
+	struct sk_buff *skb;
+	/* true if we are skipping a bad fragmented packet */
+	bool skipping;
+	u16 buff_size;
+};
+
+/**
+ * Status ring structure, used for enhanced DMA completions for RX and TX.
+ */
+struct wil_status_ring {
+	dma_addr_t pa;
+	void *va; /* pointer to ring_[tr]x_status elements */
+	u16 size; /* number of status elements */
+	size_t elem_size; /* status element size in bytes */
+	u32 swhead;
+	u32 hwtail; /* write here to inform hw */
+	bool is_rx;
+	u8 desc_rdy_pol; /* Expected descriptor ready bit polarity */
+	struct wil_ring_rx_data rx_data;
+};
+
+/**
+ * Additional data for Tx ring
+ */
+struct wil_ring_tx_data {
 	bool dot1x_open;
 	int enabled;
 	cycles_t idle, last_idle, begin;
@@ -573,6 +618,9 @@ struct wil_net_stats {
 	unsigned long	rx_short_frame;
 	unsigned long	rx_large_frame;
 	unsigned long	rx_replay;
+	unsigned long	rx_mic_error; /* eDMA specific */
+	unsigned long	rx_key_error; /* eDMA specific */
+	unsigned long	rx_amsdu_error; /* eDMA specific */
 	u16 last_mcs_rx;
 	u64 rx_per_mcs[WIL_MCS_MAX + 1];
 };
@@ -690,7 +738,7 @@ struct wil6210_vif {
 	u8 hidden_ssid; /* relevant in AP mode */
 	u32 ap_isolate; /* no intra-BSS communication */
 	bool pbss;
-	int bcast_vring;
+	int bcast_ring;
 	struct cfg80211_bss *bss; /* connected bss, relevant in STA mode */
 	int locally_generated_disc; /* relevant in STA mode */
 	struct timer_list connect_timer;
@@ -706,6 +754,31 @@ struct wil6210_vif {
 	int net_queue_stopped; /* netif_tx_stop_all_queues invoked */
 };
 
+/**
+ * RX buffer allocated for enhanced DMA RX descriptors
+ */
+struct wil_rx_buff {
+	struct sk_buff *skb;
+	struct list_head list;
+	int id;
+};
+
+/**
+ * During Rx completion processing, the driver extracts a buffer ID which
+ * is used as an index to the rx_buff_mgmt.buff_arr array and then the SKB
+ * is given to the network stack and the buffer is moved from the 'active'
+ * list to the 'free' list.
+ * During Rx refill, SKBs are attached to free buffers and moved to the
+ * 'active' list.
+ */
+struct wil_rx_buff_mgmt {
+	struct wil_rx_buff *buff_arr;
+	size_t size; /* number of items in buff_arr */
+	struct list_head active;
+	struct list_head free;
+	unsigned long free_list_empty_cnt; /* statistics */
+};
+
 struct wil6210_priv {
 	struct pci_dev *pdev;
 	u32 bar_size;
@@ -770,14 +843,17 @@ struct wil6210_priv {
 	struct net_device napi_ndev; /* dummy net_device serving all VIFs */
 
 	/* DMA related */
-	struct vring vring_rx;
+	struct wil_ring ring_rx;
 	unsigned int rx_buf_len;
-	struct vring vring_tx[WIL6210_MAX_TX_RINGS];
-	struct vring_tx_data vring_tx_data[WIL6210_MAX_TX_RINGS];
-	u8 vring2cid_tid[WIL6210_MAX_TX_RINGS][2]; /* [0] - CID, [1] - TID */
+	struct wil_ring ring_tx[WIL6210_MAX_TX_RINGS];
+	struct wil_ring_tx_data ring_tx_data[WIL6210_MAX_TX_RINGS];
+	struct wil_status_ring srings[WIL6210_MAX_STATUS_RINGS];
+	int num_rx_status_rings;
+	u8 ring2cid_tid[WIL6210_MAX_TX_RINGS][2]; /* [0] - CID, [1] - TID */
 	struct wil_sta_info sta[WIL6210_MAX_CID];
-	u32 vring_idle_trsh; /* HW fetches up to 16 descriptors at once  */
+	u32 ring_idle_trsh; /* HW fetches up to 16 descriptors at once  */
 	u32 dma_addr_size; /* indicates dma addr size */
+	struct wil_rx_buff_mgmt rx_buff_mgmt;
 
 	struct mutex mutex; /* for wil6210_priv access in wil_{up|down} */
 	/* statistics */
@@ -999,7 +1075,7 @@ int wmi_add_cipher_key(struct wil6210_vif *vif, u8 key_index,
 		       int key_usage);
 int wmi_echo(struct wil6210_priv *wil);
 int wmi_set_ie(struct wil6210_vif *vif, u8 type, u16 ie_len, const void *ie);
-int wmi_rx_chain_add(struct wil6210_priv *wil, struct vring *vring);
+int wmi_rx_chain_add(struct wil6210_priv *wil, struct wil_ring *vring);
 int wmi_rxon(struct wil6210_priv *wil, bool on);
 int wmi_get_temperature(struct wil6210_priv *wil, u32 *t_m, u32 *t_r);
 int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
@@ -1098,7 +1174,7 @@ void wil_rx_fini(struct wil6210_priv *wil);
 /* TX API */
 int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 		      int cid, int tid);
-void wil_vring_fini_tx(struct wil6210_priv *wil, int id);
+void wil_ring_fini_tx(struct wil6210_priv *wil, int id);
 int wil_tx_init(struct wil6210_vif *vif, int cid);
 int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size);
 int wil_bcast_init(struct wil6210_vif *vif);
@@ -1106,9 +1182,9 @@ void wil_bcast_fini(struct wil6210_vif *vif);
 void wil_bcast_fini_all(struct wil6210_priv *wil);
 
 void wil_update_net_queues(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			   struct vring *vring, bool should_stop);
+			   struct wil_ring *ring, bool should_stop);
 void wil_update_net_queues_bh(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			      struct vring *vring, bool check_stop);
+			      struct wil_ring *ring, bool check_stop);
 netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 int wil_tx_complete(struct wil6210_vif *vif, int ringid);
 void wil6210_unmask_irq_tx(struct wil6210_priv *wil);
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 5509f9474f9c..1cf802101dd9 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -1127,7 +1127,7 @@ static void wmi_evt_vring_en(struct wil6210_vif *vif, int id, void *d, int len)
 
 	wil_dbg_wmi(wil, "Enable vring %d MID %d\n", vri, vif->mid);
 
-	if (vri >= ARRAY_SIZE(wil->vring_tx)) {
+	if (vri >= ARRAY_SIZE(wil->ring_tx)) {
 		wil_err(wil, "Enable for invalid vring %d\n", vri);
 		return;
 	}
@@ -1136,8 +1136,8 @@ static void wmi_evt_vring_en(struct wil6210_vif *vif, int id, void *d, int len)
 		/* in AP mode with disable_ap_sme, this is done by
 		 * wil_cfg80211_change_station()
 		 */
-		wil->vring_tx_data[vri].dot1x_open = true;
-	if (vri == vif->bcast_vring) /* no BA for bcast */
+		wil->ring_tx_data[vri].dot1x_open = true;
+	if (vri == vif->bcast_ring) /* no BA for bcast */
 		return;
 	if (agg_wsize >= 0)
 		wil_addba_tx_request(wil, vri, agg_wsize);
@@ -1148,7 +1148,7 @@ static void wmi_evt_ba_status(struct wil6210_vif *vif, int id,
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	struct wmi_ba_status_event *evt = d;
-	struct vring_tx_data *txdata;
+	struct wil_ring_tx_data *txdata;
 
 	wil_dbg_wmi(wil, "BACK[%d] %s {%d} timeout %d AMSDU%s\n",
 		    evt->ringid,
@@ -1167,7 +1167,7 @@ static void wmi_evt_ba_status(struct wil6210_vif *vif, int id,
 		evt->amsdu = 0;
 	}
 
-	txdata = &wil->vring_tx_data[evt->ringid];
+	txdata = &wil->ring_tx_data[evt->ringid];
 
 	txdata->agg_timeout = le16_to_cpu(evt->ba_timeout);
 	txdata->agg_wsize = evt->agg_wsize;
@@ -1205,11 +1205,11 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	if (!evt->from_initiator) {
 		int i;
 		/* find Tx vring it belongs to */
-		for (i = 0; i < ARRAY_SIZE(wil->vring2cid_tid); i++) {
-			if ((wil->vring2cid_tid[i][0] == cid) &&
-			    (wil->vring2cid_tid[i][1] == tid)) {
-				struct vring_tx_data *txdata =
-					&wil->vring_tx_data[i];
+		for (i = 0; i < ARRAY_SIZE(wil->ring2cid_tid); i++) {
+			if (wil->ring2cid_tid[i][0] == cid &&
+			    wil->ring2cid_tid[i][1] == tid) {
+				struct wil_ring_tx_data *txdata =
+					&wil->ring_tx_data[i];
 
 				wil_dbg_wmi(wil, "DELBA Tx vring %d\n", i);
 				txdata->agg_timeout = 0;
@@ -1219,7 +1219,7 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 				break; /* max. 1 matching ring */
 			}
 		}
-		if (i >= ARRAY_SIZE(wil->vring2cid_tid))
+		if (i >= ARRAY_SIZE(wil->ring2cid_tid))
 			wil_err(wil, "DELBA: unable to find Tx vring\n");
 		return;
 	}
@@ -1964,7 +1964,7 @@ int wmi_rxon(struct wil6210_priv *wil, bool on)
 	return rc;
 }
 
-int wmi_rx_chain_add(struct wil6210_priv *wil, struct vring *vring)
+int wmi_rx_chain_add(struct wil6210_priv *wil, struct wil_ring *vring)
 {
 	struct net_device *ndev = wil->main_ndev;
 	struct wireless_dev *wdev = ndev->ieee80211_ptr;
-- 
cgit v1.2.3


From 96c93589e2dfd43ad16b92e6677ceaf279ae5062 Mon Sep 17 00:00:00 2001
From: Gidon Studinski <gidons@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:23 +0300
Subject: wil6210: initialize TX and RX enhanced DMA rings

Enhanced DMA design includes the following rings:
- Single RX descriptor ring is used for all VIFs
- Multiple RX status rings are supported, to allow RSS
- TX descriptor ring is allocated per connection
- A single TX status ring is used for all TX descriptor rings

This patch initializes and frees the above descriptor and
status rings.

The RX SKBs are handled by a new entity of RX buffers manager,
which handles RX buffers, each one points to an allocated SKB.
During Rx completion processing, the driver extracts a buffer
ID which is used as an index to the buffers array.
After the SKB is freed the buffer is moved from the 'active'
list to the 'free' list, indicating it can be used for another
descriptor. During Rx refill, SKBs are allocated and attached
to 'free' buffers. Those buffers are attached to new descriptors
and moved to the 'active' list.

New debugfs entries were added to allow edma configuration:

Run the following command to configure the number of status rings:
echo NUM_OF_STATUS_RINGS > num_rx_status_rings

Run the following command to use extended RX status message for
additional debug fields from HW:
echo 0 > compressed_rx_status

Run the following command to control the size of the TX status ring:
echo TX_STATUS_RING_ORDER > tx_status_ring_order
The status ring size will be 1 << tx_status_ring_order

Run the following command to control the size of the RX status ring:
echo RX_STATUS_RING_ORDER > rx_status_ring_order
Due to HW constrains RX sring order should be bigger than RX ring order
The status ring size will be 1 << rx_status_ring_order

Run the following command to change the number of RX buffer IDs:
echo RX_BUFF_ID_COUNT > rx_buff_id_count

Signed-off-by: Gidon Studinski <gidons@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/Makefile    |   1 +
 drivers/net/wireless/ath/wil6210/debugfs.c   |  59 +++
 drivers/net/wireless/ath/wil6210/ethtool.c   |   2 +-
 drivers/net/wireless/ath/wil6210/interrupt.c |  21 +
 drivers/net/wireless/ath/wil6210/main.c      |  81 ++-
 drivers/net/wireless/ath/wil6210/pcie_bus.c  |  47 +-
 drivers/net/wireless/ath/wil6210/txrx.c      |  90 ++--
 drivers/net/wireless/ath/wil6210/txrx.h      |   8 +
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 719 +++++++++++++++++++++++++++
 drivers/net/wireless/ath/wil6210/txrx_edma.h |  54 +-
 drivers/net/wireless/ath/wil6210/wil6210.h   |  62 ++-
 drivers/net/wireless/ath/wil6210/wmi.c       | 316 +++++++++++-
 drivers/net/wireless/ath/wil6210/wmi.h       | 166 ++++++-
 13 files changed, 1513 insertions(+), 113 deletions(-)
 create mode 100644 drivers/net/wireless/ath/wil6210/txrx_edma.c

diff --git a/drivers/net/wireless/ath/wil6210/Makefile b/drivers/net/wireless/ath/wil6210/Makefile
index 398edd2a7f2b..d3d61ae459e2 100644
--- a/drivers/net/wireless/ath/wil6210/Makefile
+++ b/drivers/net/wireless/ath/wil6210/Makefile
@@ -9,6 +9,7 @@ wil6210-$(CONFIG_WIL6210_DEBUGFS) += debugfs.o
 wil6210-y += wmi.o
 wil6210-y += interrupt.o
 wil6210-y += txrx.o
+wil6210-y += txrx_edma.o
 wil6210-y += debug.o
 wil6210-y += rx_reorder.o
 wil6210-y += fw.o
diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 55e03e9b49eb..212baf46393a 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1761,6 +1761,60 @@ static const struct file_operations fops_suspend_stats = {
 	.open  = simple_open,
 };
 
+/*---------compressed_rx_status---------*/
+static ssize_t wil_compressed_rx_status_write(struct file *file,
+					      const char __user *buf,
+					      size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int compressed_rx_status;
+	int rc;
+
+	rc = kstrtoint_from_user(buf, len, 0, &compressed_rx_status);
+	if (rc) {
+		wil_err(wil, "Invalid argument\n");
+		return rc;
+	}
+
+	if (wil_has_active_ifaces(wil, true, false)) {
+		wil_err(wil, "cannot change edma config after iface is up\n");
+		return -EPERM;
+	}
+
+	wil_info(wil, "%sable compressed_rx_status\n",
+		 compressed_rx_status ? "En" : "Dis");
+
+	wil->use_compressed_rx_status = compressed_rx_status;
+
+	return len;
+}
+
+static int
+wil_compressed_rx_status_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+
+	seq_printf(s, "%d\n", wil->use_compressed_rx_status);
+
+	return 0;
+}
+
+static int
+wil_compressed_rx_status_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_compressed_rx_status_show,
+			   inode->i_private);
+}
+
+static const struct file_operations fops_compressed_rx_status = {
+	.open  = wil_compressed_rx_status_seq_open,
+	.release = single_release,
+	.read = seq_read,
+	.write = wil_compressed_rx_status_write,
+	.llseek	= seq_lseek,
+};
+
 /*----------------*/
 static void wil6210_debugfs_init_blobs(struct wil6210_priv *wil,
 				       struct dentry *dbg)
@@ -1814,6 +1868,7 @@ static const struct {
 	{"fw_capabilities",	0444,	&fops_fw_capabilities},
 	{"fw_version",	0444,		&fops_fw_version},
 	{"suspend_stats",	0644,	&fops_suspend_stats},
+	{"compressed_rx_status", 0644,	&fops_compressed_rx_status},
 };
 
 static void wil6210_debugfs_init_files(struct wil6210_priv *wil,
@@ -1860,6 +1915,10 @@ static const struct dbg_off dbg_wil_off[] = {
 	WIL_FIELD(abft_len, 0644,		doff_u8),
 	WIL_FIELD(wakeup_trigger, 0644,		doff_u8),
 	WIL_FIELD(ring_idle_trsh, 0644,	doff_u32),
+	WIL_FIELD(num_rx_status_rings, 0644,	doff_u8),
+	WIL_FIELD(rx_status_ring_order, 0644,	doff_u32),
+	WIL_FIELD(tx_status_ring_order, 0644,	doff_u32),
+	WIL_FIELD(rx_buff_id_count, 0644,	doff_u32),
 	{},
 };
 
diff --git a/drivers/net/wireless/ath/wil6210/ethtool.c b/drivers/net/wireless/ath/wil6210/ethtool.c
index e7ff41e623d2..a04c87ffd37b 100644
--- a/drivers/net/wireless/ath/wil6210/ethtool.c
+++ b/drivers/net/wireless/ath/wil6210/ethtool.c
@@ -101,7 +101,7 @@ static int wil_ethtoolops_set_coalesce(struct net_device *ndev,
 	if (ret < 0)
 		return ret;
 
-	wil_configure_interrupt_moderation(wil);
+	wil->txrx_ops.configure_interrupt_moderation(wil);
 
 	wil_pm_runtime_put(wil);
 
diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index 84e9840c1752..311d48233165 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -186,6 +186,27 @@ void wil_unmask_irq(struct wil6210_priv *wil)
 	wil6210_unmask_irq_misc(wil, true);
 }
 
+void wil_configure_interrupt_moderation_edma(struct wil6210_priv *wil)
+{
+	u32 moderation;
+
+	wil_s(wil, RGF_INT_GEN_IDLE_TIME_LIMIT, WIL_EDMA_IDLE_TIME_LIMIT_USEC);
+
+	wil_s(wil, RGF_INT_GEN_TIME_UNIT_LIMIT, WIL_EDMA_TIME_UNIT_CLK_CYCLES);
+
+	/* Update RX and TX moderation */
+	moderation = wil->rx_max_burst_duration |
+		(WIL_EDMA_AGG_WATERMARK << WIL_EDMA_AGG_WATERMARK_POS);
+	wil_w(wil, RGF_INT_CTRL_INT_GEN_CFG_0, moderation);
+	wil_w(wil, RGF_INT_CTRL_INT_GEN_CFG_1, moderation);
+
+	/* Treat special events as regular
+	 * (set bit 0 to 0x1 and clear bits 1-8)
+	 */
+	wil_c(wil, RGF_INT_COUNT_ON_SPECIAL_EVT, 0x1FE);
+	wil_s(wil, RGF_INT_COUNT_ON_SPECIAL_EVT, 0x1);
+}
+
 void wil_configure_interrupt_moderation(struct wil6210_priv *wil)
 {
 	struct wireless_dev *wdev = wil->main_ndev->ieee80211_ptr;
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index bfe628481e22..c820c86918f0 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -21,11 +21,13 @@
 
 #include "wil6210.h"
 #include "txrx.h"
+#include "txrx_edma.h"
 #include "wmi.h"
 #include "boot_loader.h"
 
 #define WAIT_FOR_HALP_VOTE_MS 100
 #define WAIT_FOR_SCAN_ABORT_MS 1000
+#define WIL_DEFAULT_NUM_RX_STATUS_RINGS 1
 
 bool debug_fw; /* = false; */
 module_param(debug_fw, bool, 0444);
@@ -160,6 +162,37 @@ void wil_memcpy_toio_32(volatile void __iomem *dst, const void *src,
 	}
 }
 
+static void wil_ring_fini_tx(struct wil6210_priv *wil, int id)
+{
+	struct wil_ring *ring = &wil->ring_tx[id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
+
+	lockdep_assert_held(&wil->mutex);
+
+	if (!ring->va)
+		return;
+
+	wil_dbg_misc(wil, "vring_fini_tx: id=%d\n", id);
+
+	spin_lock_bh(&txdata->lock);
+	txdata->dot1x_open = false;
+	txdata->mid = U8_MAX;
+	txdata->enabled = 0; /* no Tx can be in progress or start anew */
+	spin_unlock_bh(&txdata->lock);
+	/* napi_synchronize waits for completion of the current NAPI but will
+	 * not prevent the next NAPI run.
+	 * Add a memory barrier to guarantee that txdata->enabled is zeroed
+	 * before napi_synchronize so that the next scheduled NAPI will not
+	 * handle this vring
+	 */
+	wmb();
+	/* make sure NAPI won't touch this vring */
+	if (test_bit(wil_status_napi_en, wil->status))
+		napi_synchronize(&wil->napi_tx);
+
+	wil->txrx_ops.ring_fini_tx(wil, ring);
+}
+
 static void wil_disconnect_cid(struct wil6210_vif *vif, int cid,
 			       u16 reason_code, bool from_event)
 __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
@@ -456,15 +489,16 @@ static void wil_fw_error_worker(struct work_struct *work)
 static int wil_find_free_ring(struct wil6210_priv *wil)
 {
 	int i;
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
-	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
+	for (i = min_ring_id; i < WIL6210_MAX_TX_RINGS; i++) {
 		if (!wil->ring_tx[i].va)
 			return i;
 	}
 	return -EINVAL;
 }
 
-int wil_tx_init(struct wil6210_vif *vif, int cid)
+int wil_ring_init_tx(struct wil6210_vif *vif, int cid)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	int rc = -EINVAL, ringid;
@@ -482,7 +516,8 @@ int wil_tx_init(struct wil6210_vif *vif, int cid)
 	wil_dbg_wmi(wil, "Configure for connection CID %d MID %d ring %d\n",
 		    cid, vif->mid, ringid);
 
-	rc = wil_vring_init_tx(vif, ringid, 1 << tx_ring_order, cid, 0);
+	rc = wil->txrx_ops.ring_init_tx(vif, ringid, 1 << tx_ring_order,
+					cid, 0);
 	if (rc)
 		wil_err(wil, "init TX for CID %d MID %d vring %d failed\n",
 			cid, vif->mid, ringid);
@@ -504,7 +539,7 @@ int wil_bcast_init(struct wil6210_vif *vif)
 		return ri;
 
 	vif->bcast_ring = ri;
-	rc = wil_vring_init_bcast(vif, ri, 1 << bcast_ring_order);
+	rc = wil->txrx_ops.ring_init_bcast(vif, ri, 1 << bcast_ring_order);
 	if (rc)
 		vif->bcast_ring = -1;
 
@@ -594,6 +629,22 @@ int wil_priv_init(struct wil6210_priv *wil)
 	wil->reply_mid = U8_MAX;
 	wil->max_vifs = 1;
 
+	/* edma configuration can be updated via debugfs before allocation */
+	wil->num_rx_status_rings = WIL_DEFAULT_NUM_RX_STATUS_RINGS;
+	wil->use_compressed_rx_status = true;
+	wil->tx_status_ring_order = WIL_TX_SRING_SIZE_ORDER_DEFAULT;
+
+	/* Rx status ring size should be bigger than the number of RX buffers
+	 * in order to prevent backpressure on the status ring, which may
+	 * cause HW freeze.
+	 */
+	wil->rx_status_ring_order = WIL_RX_SRING_SIZE_ORDER_DEFAULT;
+	/* Number of RX buffer IDs should be bigger than the RX descriptor
+	 * ring size as in HW reorder flow, the HW can consume additional
+	 * buffers before releasing the previous ones.
+	 */
+	wil->rx_buff_id_count = WIL_RX_BUFF_ARR_SIZE_DEFAULT;
+
 	return 0;
 
 out_wmi_wq:
@@ -1312,7 +1363,8 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 	rc = wil_target_reset(wil, no_flash);
 	wil6210_clear_irq(wil);
 	wil_enable_irq(wil);
-	wil_rx_fini(wil);
+	wil->txrx_ops.rx_fini(wil);
+	wil->txrx_ops.tx_fini(wil);
 	if (rc) {
 		if (!no_flash)
 			wil_bl_crash_info(wil, true);
@@ -1365,7 +1417,6 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 	clear_bit(wil_status_resetting, wil->status);
 
 	if (load_fw) {
-		wil_configure_interrupt_moderation(wil);
 		wil_unmask_irq(wil);
 
 		/* we just started MAC, wait for FW ready */
@@ -1380,6 +1431,8 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 			return rc;
 		}
 
+		wil->txrx_ops.configure_interrupt_moderation(wil);
+
 		rc = wil_restore_vifs(wil);
 		if (rc) {
 			wil_err(wil, "failed to restore vifs, rc %d\n", rc);
@@ -1434,8 +1487,12 @@ int __wil_up(struct wil6210_priv *wil)
 	if (rc)
 		return rc;
 
-	/* Rx VRING. After MAC and beacon */
-	rc = wil_rx_init(wil, 1 << rx_ring_order);
+	/* Rx RING. After MAC and beacon */
+	rc = wil->txrx_ops.rx_init(wil, 1 << rx_ring_order);
+	if (rc)
+		return rc;
+
+	rc = wil->txrx_ops.tx_init(wil);
 	if (rc)
 		return rc;
 
@@ -1596,3 +1653,11 @@ void wil_halp_unvote(struct wil6210_priv *wil)
 
 	mutex_unlock(&wil->halp.lock);
 }
+
+void wil_init_txrx_ops(struct wil6210_priv *wil)
+{
+	if (wil->use_enhanced_dma_hw)
+		wil_init_txrx_ops_edma(wil);
+	else
+		wil_init_txrx_ops_legacy_dma(wil);
+}
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 3a7e406d0311..c01c5348b7e0 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -102,6 +102,7 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		wil->rgf_fw_assert_code_addr = TALYN_RGF_FW_ASSERT_CODE;
 		wil->rgf_ucode_assert_code_addr = TALYN_RGF_UCODE_ASSERT_CODE;
 		set_bit(hw_capa_no_flash, wil->hw_capa);
+		wil->use_enhanced_dma_hw = true;
 		break;
 	default:
 		wil_err(wil, "Unknown board hardware, chip_id 0x%08x, chip_revision 0x%08x\n",
@@ -111,6 +112,8 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		return -EINVAL;
 	}
 
+	wil_init_txrx_ops(wil);
+
 	iccm_section = wil_find_fw_mapping("fw_code");
 	if (!iccm_section) {
 		wil_err(wil, "fw_code section not found in fw_mapping\n");
@@ -266,8 +269,8 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		.fw_recovery = wil_platform_rop_fw_recovery,
 	};
 	u32 bar_size = pci_resource_len(pdev, 0);
-	int dma_addr_size[] = {48, 40, 32}; /* keep descending order */
-	int i;
+	int dma_addr_size[] = {64, 48, 40, 32}; /* keep descending order */
+	int i, start_idx;
 
 	/* check HW */
 	dev_info(&pdev->dev, WIL_NAME
@@ -302,24 +305,6 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		goto if_free;
 	}
 	/* rollback to err_plat */
-
-	/* device supports >32bit addresses */
-	for (i = 0; i < ARRAY_SIZE(dma_addr_size); i++) {
-		rc = dma_set_mask_and_coherent(dev,
-					       DMA_BIT_MASK(dma_addr_size[i]));
-		if (rc) {
-			dev_err(dev, "dma_set_mask_and_coherent(%d) failed: %d\n",
-				dma_addr_size[i], rc);
-			continue;
-		}
-		dev_info(dev, "using dma mask %d", dma_addr_size[i]);
-		wil->dma_addr_size = dma_addr_size[i];
-		break;
-	}
-
-	if (wil->dma_addr_size == 0)
-		goto err_plat;
-
 	rc = pci_enable_device(pdev);
 	if (rc && pdev->msi_enabled == 0) {
 		wil_err(wil,
@@ -359,6 +344,28 @@ static int wil_pcie_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		wil_err(wil, "wil_set_capabilities failed, rc %d\n", rc);
 		goto err_iounmap;
 	}
+
+	/* device supports >32bit addresses.
+	 * for legacy DMA start from 48 bit.
+	 */
+	start_idx = wil->use_enhanced_dma_hw ? 0 : 1;
+
+	for (i = start_idx; i < ARRAY_SIZE(dma_addr_size); i++) {
+		rc = dma_set_mask_and_coherent(dev,
+					       DMA_BIT_MASK(dma_addr_size[i]));
+		if (rc) {
+			dev_err(dev, "dma_set_mask_and_coherent(%d) failed: %d\n",
+				dma_addr_size[i], rc);
+			continue;
+		}
+		dev_info(dev, "using dma mask %d", dma_addr_size[i]);
+		wil->dma_addr_size = dma_addr_size[i];
+		break;
+	}
+
+	if (wil->dma_addr_size == 0)
+		goto err_iounmap;
+
 	wil6210_clear_irq(wil);
 
 	/* FW should raise IRQ when ready */
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 55946dec5110..2a359e164e08 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -202,14 +202,13 @@ static void wil_txdesc_unmap(struct device *dev, struct vring_tx_desc *d,
 	}
 }
 
-static void wil_vring_free(struct wil6210_priv *wil, struct wil_ring *vring,
-			   int tx)
+static void wil_vring_free(struct wil6210_priv *wil, struct wil_ring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
 	size_t sz = vring->size * sizeof(vring->va[0]);
 
 	lockdep_assert_held(&wil->mutex);
-	if (tx) {
+	if (!vring->is_rx) {
 		int vring_index = vring - wil->ring_tx;
 
 		wil_dbg_misc(wil, "free Tx vring %d [%d] 0x%p:%pad 0x%p\n",
@@ -226,7 +225,7 @@ static void wil_vring_free(struct wil6210_priv *wil, struct wil_ring *vring,
 		u16 dmalen;
 		struct wil_ctx *ctx;
 
-		if (tx) {
+		if (!vring->is_rx) {
 			struct vring_tx_desc dd, *d = &dd;
 			volatile struct vring_tx_desc *_d =
 					&vring->va[vring->swtail].tx.legacy;
@@ -843,7 +842,7 @@ static void wil_rx_buf_len_init(struct wil6210_priv *wil)
 	}
 }
 
-int wil_rx_init(struct wil6210_priv *wil, u16 size)
+static int wil_rx_init(struct wil6210_priv *wil, u16 size)
 {
 	struct wil_ring *vring = &wil->ring_rx;
 	int rc;
@@ -858,6 +857,7 @@ int wil_rx_init(struct wil6210_priv *wil, u16 size)
 	wil_rx_buf_len_init(wil);
 
 	vring->size = size;
+	vring->is_rx = true;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
 		return rc;
@@ -872,22 +872,22 @@ int wil_rx_init(struct wil6210_priv *wil, u16 size)
 
 	return 0;
  err_free:
-	wil_vring_free(wil, vring, 0);
+	wil_vring_free(wil, vring);
 
 	return rc;
 }
 
-void wil_rx_fini(struct wil6210_priv *wil)
+static void wil_rx_fini(struct wil6210_priv *wil)
 {
 	struct wil_ring *vring = &wil->ring_rx;
 
 	wil_dbg_misc(wil, "rx_fini\n");
 
 	if (vring->va)
-		wil_vring_free(wil, vring, 0);
+		wil_vring_free(wil, vring);
 }
 
-static inline void wil_tx_data_init(struct wil_ring_tx_data *txdata)
+void wil_tx_data_init(struct wil_ring_tx_data *txdata)
 {
 	spin_lock_bh(&txdata->lock);
 	txdata->dot1x_open = 0;
@@ -903,8 +903,8 @@ static inline void wil_tx_data_init(struct wil_ring_tx_data *txdata)
 	spin_unlock_bh(&txdata->lock);
 }
 
-int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
-		      int cid, int tid)
+static int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
+			     int cid, int tid)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	int rc;
@@ -948,6 +948,7 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	}
 
 	wil_tx_data_init(txdata);
+	vring->is_rx = false;
 	vring->size = size;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
@@ -987,7 +988,7 @@ int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
 	txdata->dot1x_open = false;
 	txdata->enabled = 0;
 	spin_unlock_bh(&txdata->lock);
-	wil_vring_free(wil, vring, 1);
+	wil_vring_free(wil, vring);
 	wil->ring2cid_tid[id][0] = WIL6210_MAX_CID;
 	wil->ring2cid_tid[id][1] = 0;
 
@@ -1032,6 +1033,7 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	}
 
 	wil_tx_data_init(txdata);
+	vring->is_rx = false;
 	vring->size = size;
 	rc = wil_vring_alloc(wil, vring);
 	if (rc)
@@ -1069,43 +1071,12 @@ int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size)
 	txdata->enabled = 0;
 	txdata->dot1x_open = false;
 	spin_unlock_bh(&txdata->lock);
-	wil_vring_free(wil, vring, 1);
+	wil_vring_free(wil, vring);
  out:
 
 	return rc;
 }
 
-void wil_ring_fini_tx(struct wil6210_priv *wil, int id)
-{
-	struct wil_ring *vring = &wil->ring_tx[id];
-	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[id];
-
-	lockdep_assert_held(&wil->mutex);
-
-	if (!vring->va)
-		return;
-
-	wil_dbg_misc(wil, "vring_fini_tx: id=%d\n", id);
-
-	spin_lock_bh(&txdata->lock);
-	txdata->dot1x_open = false;
-	txdata->mid = U8_MAX;
-	txdata->enabled = 0; /* no Tx can be in progress or start anew */
-	spin_unlock_bh(&txdata->lock);
-	/* napi_synchronize waits for completion of the current NAPI but will
-	 * not prevent the next NAPI run.
-	 * Add a memory barrier to guarantee that txdata->enabled is zeroed
-	 * before napi_synchronize so that the next scheduled NAPI will not
-	 * handle this vring
-	 */
-	wmb();
-	/* make sure NAPI won't touch this vring */
-	if (test_bit(wil_status_napi_en, wil->status))
-		napi_synchronize(&wil->napi_tx);
-
-	wil_vring_free(wil, vring, 1);
-}
-
 static struct wil_ring *wil_find_tx_ucast(struct wil6210_priv *wil,
 					  struct wil6210_vif *vif,
 					  struct sk_buff *skb)
@@ -1113,12 +1084,13 @@ static struct wil_ring *wil_find_tx_ucast(struct wil6210_priv *wil,
 	int i;
 	struct ethhdr *eth = (void *)skb->data;
 	int cid = wil_find_cid(wil, vif->mid, eth->h_dest);
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
 	if (cid < 0)
 		return NULL;
 
 	/* TODO: fix for multiple TID */
-	for (i = 0; i < ARRAY_SIZE(wil->ring2cid_tid); i++) {
+	for (i = min_ring_id; i < ARRAY_SIZE(wil->ring2cid_tid); i++) {
 		if (!wil->ring_tx_data[i].dot1x_open &&
 		    skb->protocol != cpu_to_be16(ETH_P_PAE))
 			continue;
@@ -1153,12 +1125,13 @@ static struct wil_ring *wil_find_tx_ring_sta(struct wil6210_priv *wil,
 	int i;
 	u8 cid;
 	struct wil_ring_tx_data  *txdata;
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
 	/* In the STA mode, it is expected to have only 1 VRING
 	 * for the AP we connected to.
 	 * find 1-st vring eligible for this skb and use it.
 	 */
-	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
+	for (i = min_ring_id; i < WIL6210_MAX_TX_RINGS; i++) {
 		ring = &wil->ring_tx[i];
 		txdata = &wil->ring_tx_data[i];
 		if (!ring->va || !txdata->enabled || txdata->mid != vif->mid)
@@ -1234,9 +1207,10 @@ static struct wil_ring *wil_find_tx_bcast_2(struct wil6210_priv *wil,
 	struct ethhdr *eth = (void *)skb->data;
 	char *src = eth->h_source;
 	struct wil_ring_tx_data *txdata, *txdata2;
+	int min_ring_id = wil_get_min_tx_ring_id(wil);
 
 	/* find 1-st vring eligible for data */
-	for (i = 0; i < WIL6210_MAX_TX_RINGS; i++) {
+	for (i = min_ring_id; i < WIL6210_MAX_TX_RINGS; i++) {
 		v = &wil->ring_tx[i];
 		txdata = &wil->ring_tx_data[i];
 		if (!v->va || !txdata->enabled || txdata->mid != vif->mid)
@@ -2201,3 +2175,25 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 
 	return done;
 }
+
+static inline int wil_tx_init(struct wil6210_priv *wil)
+{
+	return 0;
+}
+
+static inline void wil_tx_fini(struct wil6210_priv *wil) {}
+
+void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil)
+{
+	wil->txrx_ops.configure_interrupt_moderation =
+		wil_configure_interrupt_moderation;
+	/* TX ops */
+	wil->txrx_ops.ring_init_tx = wil_vring_init_tx;
+	wil->txrx_ops.ring_fini_tx = wil_vring_free;
+	wil->txrx_ops.ring_init_bcast = wil_vring_init_bcast;
+	wil->txrx_ops.tx_init = wil_tx_init;
+	wil->txrx_ops.tx_fini = wil_tx_fini;
+	/* RX ops */
+	wil->txrx_ops.rx_init = wil_rx_init;
+	wil->txrx_ops.rx_fini = wil_rx_fini;
+}
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 66217f815726..4e3781d9e7ec 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -570,6 +570,12 @@ static inline int wil_ring_avail_tx(struct wil_ring *ring)
 	return ring->size - wil_ring_used_tx(ring) - 1;
 }
 
+static inline int wil_get_min_tx_ring_id(struct wil6210_priv *wil)
+{
+	/* In Enhanced DMA ring 0 is reserved for RX */
+	return wil->use_enhanced_dma_hw ? 1 : 0;
+}
+
 void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev);
 void wil_rx_reorder(struct wil6210_priv *wil, struct sk_buff *skb);
 void wil_rx_bar(struct wil6210_priv *wil, struct wil6210_vif *vif,
@@ -578,5 +584,7 @@ struct wil_tid_ampdu_rx *wil_tid_ampdu_rx_alloc(struct wil6210_priv *wil,
 						int size, u16 ssn);
 void wil_tid_ampdu_rx_free(struct wil6210_priv *wil,
 			   struct wil_tid_ampdu_rx *r);
+void wil_tx_data_init(struct wil_ring_tx_data *txdata);
+void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil);
 
 #endif /* WIL6210_TXRX_H */
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
new file mode 100644
index 000000000000..9773d400808d
--- /dev/null
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -0,0 +1,719 @@
+/*
+ * Copyright (c) 2012-2018 The Linux Foundation. All rights reserved.
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/moduleparam.h>
+#include <linux/prefetch.h>
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include "wil6210.h"
+#include "txrx_edma.h"
+#include "txrx.h"
+
+#define WIL_EDMA_MAX_DATA_OFFSET (2)
+
+static void wil_tx_desc_unmap_edma(struct device *dev,
+				   struct wil_tx_enhanced_desc *d,
+				   struct wil_ctx *ctx)
+{
+	dma_addr_t pa = wil_tx_desc_get_addr_edma(&d->dma);
+	u16 dmalen = le16_to_cpu(d->dma.length);
+
+	switch (ctx->mapped_as) {
+	case wil_mapped_as_single:
+		dma_unmap_single(dev, pa, dmalen, DMA_TO_DEVICE);
+		break;
+	case wil_mapped_as_page:
+		dma_unmap_page(dev, pa, dmalen, DMA_TO_DEVICE);
+		break;
+	default:
+		break;
+	}
+}
+
+static int wil_find_free_sring(struct wil6210_priv *wil)
+{
+	int i;
+
+	for (i = 0; i < WIL6210_MAX_STATUS_RINGS; i++) {
+		if (!wil->srings[i].va)
+			return i;
+	}
+
+	return -EINVAL;
+}
+
+static void wil_sring_free(struct wil6210_priv *wil,
+			   struct wil_status_ring *sring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz;
+
+	if (!sring || !sring->va)
+		return;
+
+	sz = sring->elem_size * sring->size;
+
+	wil_dbg_misc(wil, "status_ring_free, size(bytes)=%zu, 0x%p:%pad\n",
+		     sz, sring->va, &sring->pa);
+
+	dma_free_coherent(dev, sz, (void *)sring->va, sring->pa);
+	sring->pa = 0;
+	sring->va = NULL;
+}
+
+static int wil_sring_alloc(struct wil6210_priv *wil,
+			   struct wil_status_ring *sring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz = sring->elem_size * sring->size;
+
+	wil_dbg_misc(wil, "status_ring_alloc: size=%zu\n", sz);
+
+	if (sz == 0) {
+		wil_err(wil, "Cannot allocate a zero size status ring\n");
+		return -EINVAL;
+	}
+
+	sring->swhead = 0;
+
+	/* Status messages are allocated and initialized to 0. This is necessary
+	 * since DR bit should be initialized to 0.
+	 */
+	sring->va = dma_zalloc_coherent(dev, sz, &sring->pa, GFP_KERNEL);
+	if (!sring->va)
+		return -ENOMEM;
+
+	wil_dbg_misc(wil, "status_ring[%d] 0x%p:%pad\n", sring->size, sring->va,
+		     &sring->pa);
+
+	return 0;
+}
+
+static int wil_tx_init_edma(struct wil6210_priv *wil)
+{
+	int ring_id = wil_find_free_sring(wil);
+	struct wil_status_ring *sring;
+	int rc;
+	u16 status_ring_size;
+
+	if (wil->tx_status_ring_order < WIL_SRING_SIZE_ORDER_MIN ||
+	    wil->tx_status_ring_order > WIL_SRING_SIZE_ORDER_MAX)
+		wil->tx_status_ring_order = WIL_TX_SRING_SIZE_ORDER_DEFAULT;
+
+	status_ring_size = 1 << wil->tx_status_ring_order;
+
+	wil_dbg_misc(wil, "init TX sring: size=%u, ring_id=%u\n",
+		     status_ring_size, ring_id);
+
+	if (ring_id < 0)
+		return ring_id;
+
+	/* Allocate Tx status ring. Tx descriptor rings will be
+	 * allocated on WMI connect event
+	 */
+	sring = &wil->srings[ring_id];
+
+	sring->is_rx = false;
+	sring->size = status_ring_size;
+	sring->elem_size = sizeof(struct wil_ring_tx_status);
+	rc = wil_sring_alloc(wil, sring);
+	if (rc)
+		return rc;
+
+	rc = wil_wmi_tx_sring_cfg(wil, ring_id);
+	if (rc)
+		goto out_free;
+
+	sring->desc_rdy_pol = 1;
+	wil->tx_sring_idx = ring_id;
+
+	return 0;
+out_free:
+	wil_sring_free(wil, sring);
+	return rc;
+}
+
+/**
+ * Allocate one skb for Rx descriptor RING
+ */
+static int wil_ring_alloc_skb_edma(struct wil6210_priv *wil,
+				   struct wil_ring *ring, u32 i)
+{
+	struct device *dev = wil_to_dev(wil);
+	unsigned int sz = wil->rx_buf_len + ETH_HLEN +
+		WIL_EDMA_MAX_DATA_OFFSET;
+	dma_addr_t pa;
+	u16 buff_id;
+	struct list_head *active = &wil->rx_buff_mgmt.active;
+	struct list_head *free = &wil->rx_buff_mgmt.free;
+	struct wil_rx_buff *rx_buff;
+	struct wil_rx_buff *buff_arr = wil->rx_buff_mgmt.buff_arr;
+	struct sk_buff *skb;
+	struct wil_rx_enhanced_desc dd, *d = &dd;
+	struct wil_rx_enhanced_desc *_d = (struct wil_rx_enhanced_desc *)
+		&ring->va[i].rx.enhanced;
+
+	if (unlikely(list_empty(free))) {
+		wil->rx_buff_mgmt.free_list_empty_cnt++;
+		return -EAGAIN;
+	}
+
+	skb = dev_alloc_skb(sz);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	skb_put(skb, sz);
+
+	pa = dma_map_single(dev, skb->data, skb->len, DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(dev, pa))) {
+		kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	/* Get the buffer ID - the index of the rx buffer in the buff_arr */
+	rx_buff = list_first_entry(free, struct wil_rx_buff, list);
+	buff_id = rx_buff->id;
+
+	/* Move a buffer from the free list to the active list */
+	list_move(&rx_buff->list, active);
+
+	buff_arr[buff_id].skb = skb;
+
+	wil_desc_set_addr_edma(&d->dma.addr, &d->dma.addr_high_high, pa);
+	d->dma.length = cpu_to_le16(sz);
+	d->mac.buff_id = cpu_to_le16(buff_id);
+	*_d = *d;
+
+	/* Save the physical address in skb->cb for later use in dma_unmap */
+	memcpy(skb->cb, &pa, sizeof(pa));
+
+	return 0;
+}
+
+static int wil_rx_refill_edma(struct wil6210_priv *wil)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+	u32 next_head;
+	int rc = 0;
+	u32 swtail = *ring->edma_rx_swtail.va;
+
+	for (; next_head = wil_ring_next_head(ring), (next_head != swtail);
+	     ring->swhead = next_head) {
+		rc = wil_ring_alloc_skb_edma(wil, ring, ring->swhead);
+		if (unlikely(rc)) {
+			if (rc == -EAGAIN)
+				wil_dbg_txrx(wil, "No free buffer ID found\n");
+			else
+				wil_err_ratelimited(wil,
+						    "Error %d in refill desc[%d]\n",
+						    rc, ring->swhead);
+			break;
+		}
+	}
+
+	/* make sure all writes to descriptors (shared memory) are done before
+	 * committing them to HW
+	 */
+	wmb();
+
+	wil_w(wil, ring->hwtail, ring->swhead);
+
+	return rc;
+}
+
+static void wil_move_all_rx_buff_to_free_list(struct wil6210_priv *wil,
+					      struct wil_ring *ring)
+{
+	struct device *dev = wil_to_dev(wil);
+	u32 next_tail;
+	u32 swhead = (ring->swhead + 1) % ring->size;
+	dma_addr_t pa;
+	u16 dmalen;
+
+	for (; next_tail = wil_ring_next_tail(ring), (next_tail != swhead);
+	     ring->swtail = next_tail) {
+		struct wil_rx_enhanced_desc dd, *d = &dd;
+		struct wil_rx_enhanced_desc *_d =
+			(struct wil_rx_enhanced_desc *)
+			&ring->va[ring->swtail].rx.enhanced;
+		struct sk_buff *skb;
+		u16 buff_id;
+
+		*d = *_d;
+		pa = wil_rx_desc_get_addr_edma(&d->dma);
+		dmalen = le16_to_cpu(d->dma.length);
+		dma_unmap_single(dev, pa, dmalen, DMA_FROM_DEVICE);
+
+		/* Extract the SKB from the rx_buff management array */
+		buff_id = __le16_to_cpu(d->mac.buff_id);
+		if (buff_id >= wil->rx_buff_mgmt.size) {
+			wil_err(wil, "invalid buff_id %d\n", buff_id);
+			continue;
+		}
+		skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
+		wil->rx_buff_mgmt.buff_arr[buff_id].skb = NULL;
+		if (unlikely(!skb))
+			wil_err(wil, "No Rx skb at buff_id %d\n", buff_id);
+		else
+			kfree_skb(skb);
+
+		/* Move the buffer from the active to the free list */
+		list_move(&wil->rx_buff_mgmt.buff_arr[buff_id].list,
+			  &wil->rx_buff_mgmt.free);
+	}
+}
+
+static void wil_free_rx_buff_arr(struct wil6210_priv *wil)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+
+	if (!wil->rx_buff_mgmt.buff_arr)
+		return;
+
+	/* Move all the buffers to the free list in case active list is
+	 * not empty in order to release all SKBs before deleting the array
+	 */
+	wil_move_all_rx_buff_to_free_list(wil, ring);
+
+	kfree(wil->rx_buff_mgmt.buff_arr);
+	wil->rx_buff_mgmt.buff_arr = NULL;
+}
+
+static int wil_init_rx_buff_arr(struct wil6210_priv *wil,
+				size_t size)
+{
+	struct wil_rx_buff *buff_arr;
+	struct list_head *active = &wil->rx_buff_mgmt.active;
+	struct list_head *free = &wil->rx_buff_mgmt.free;
+	int i;
+
+	wil->rx_buff_mgmt.buff_arr = kcalloc(size, sizeof(struct wil_rx_buff),
+					     GFP_KERNEL);
+	if (!wil->rx_buff_mgmt.buff_arr)
+		return -ENOMEM;
+
+	/* Set list heads */
+	INIT_LIST_HEAD(active);
+	INIT_LIST_HEAD(free);
+
+	/* Linkify the list */
+	buff_arr = wil->rx_buff_mgmt.buff_arr;
+	for (i = 0; i < size; i++) {
+		list_add(&buff_arr[i].list, free);
+		buff_arr[i].id = i;
+	}
+
+	wil->rx_buff_mgmt.size = size;
+
+	return 0;
+}
+
+static int wil_init_rx_sring(struct wil6210_priv *wil,
+			     u16 status_ring_size,
+			     size_t elem_size,
+			     u16 ring_id)
+{
+	struct wil_status_ring *sring = &wil->srings[ring_id];
+	int rc;
+
+	wil_dbg_misc(wil, "init RX sring: size=%u, ring_id=%u\n", sring->size,
+		     ring_id);
+
+	memset(&sring->rx_data, 0, sizeof(sring->rx_data));
+
+	sring->is_rx = true;
+	sring->size = status_ring_size;
+	sring->elem_size = elem_size;
+	rc = wil_sring_alloc(wil, sring);
+	if (rc)
+		return rc;
+
+	rc = wil_wmi_rx_sring_add(wil, ring_id);
+	if (rc)
+		goto out_free;
+
+	sring->desc_rdy_pol = 1;
+
+	return 0;
+out_free:
+	wil_sring_free(wil, sring);
+	return rc;
+}
+
+static int wil_ring_alloc_desc_ring(struct wil6210_priv *wil,
+				    struct wil_ring *ring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz = ring->size * sizeof(ring->va[0]);
+
+	wil_dbg_misc(wil, "alloc_desc_ring:\n");
+
+	BUILD_BUG_ON(sizeof(ring->va[0]) != 32);
+
+	ring->swhead = 0;
+	ring->swtail = 0;
+	ring->ctx = kcalloc(ring->size, sizeof(ring->ctx[0]), GFP_KERNEL);
+	if (!ring->ctx)
+		goto err;
+
+	ring->va = dma_zalloc_coherent(dev, sz, &ring->pa, GFP_KERNEL);
+	if (!ring->va)
+		goto err_free_ctx;
+
+	if (ring->is_rx) {
+		sz = sizeof(*ring->edma_rx_swtail.va);
+		ring->edma_rx_swtail.va =
+			dma_zalloc_coherent(dev, sz, &ring->edma_rx_swtail.pa,
+					    GFP_KERNEL);
+		if (!ring->edma_rx_swtail.va)
+			goto err_free_va;
+	}
+
+	wil_dbg_misc(wil, "%s ring[%d] 0x%p:%pad 0x%p\n",
+		     ring->is_rx ? "RX" : "TX",
+		     ring->size, ring->va, &ring->pa, ring->ctx);
+
+	return 0;
+err_free_va:
+	dma_free_coherent(dev, ring->size * sizeof(ring->va[0]),
+			  (void *)ring->va, ring->pa);
+	ring->va = NULL;
+err_free_ctx:
+	kfree(ring->ctx);
+	ring->ctx = NULL;
+err:
+	return -ENOMEM;
+}
+
+static void wil_ring_free_edma(struct wil6210_priv *wil, struct wil_ring *ring)
+{
+	struct device *dev = wil_to_dev(wil);
+	size_t sz;
+	int ring_index = 0;
+
+	if (!ring->va)
+		return;
+
+	sz = ring->size * sizeof(ring->va[0]);
+
+	lockdep_assert_held(&wil->mutex);
+	if (ring->is_rx) {
+		wil_dbg_misc(wil, "free Rx ring [%d] 0x%p:%pad 0x%p\n",
+			     ring->size, ring->va,
+			     &ring->pa, ring->ctx);
+
+		wil_move_all_rx_buff_to_free_list(wil, ring);
+		goto out;
+	}
+
+	/* TX ring */
+	ring_index = ring - wil->ring_tx;
+
+	wil_dbg_misc(wil, "free Tx ring %d [%d] 0x%p:%pad 0x%p\n",
+		     ring_index, ring->size, ring->va,
+		     &ring->pa, ring->ctx);
+
+	while (!wil_ring_is_empty(ring)) {
+		struct wil_ctx *ctx;
+
+		struct wil_tx_enhanced_desc dd, *d = &dd;
+		struct wil_tx_enhanced_desc *_d =
+			(struct wil_tx_enhanced_desc *)
+			&ring->va[ring->swtail].tx.enhanced;
+
+		ctx = &ring->ctx[ring->swtail];
+		if (!ctx) {
+			wil_dbg_txrx(wil,
+				     "ctx(%d) was already completed\n",
+				     ring->swtail);
+			ring->swtail = wil_ring_next_tail(ring);
+			continue;
+		}
+		*d = *_d;
+		wil_tx_desc_unmap_edma(dev, d, ctx);
+		if (ctx->skb)
+			dev_kfree_skb_any(ctx->skb);
+		ring->swtail = wil_ring_next_tail(ring);
+	}
+
+out:
+	dma_free_coherent(dev, sz, (void *)ring->va, ring->pa);
+	kfree(ring->ctx);
+	ring->pa = 0;
+	ring->va = NULL;
+	ring->ctx = NULL;
+}
+
+static int wil_init_rx_desc_ring(struct wil6210_priv *wil, u16 desc_ring_size,
+				 int status_ring_id)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+	int rc;
+
+	wil_dbg_misc(wil, "init RX desc ring\n");
+
+	ring->size = desc_ring_size;
+	ring->is_rx = true;
+	rc = wil_ring_alloc_desc_ring(wil, ring);
+	if (rc)
+		return rc;
+
+	rc = wil_wmi_rx_desc_ring_add(wil, status_ring_id);
+	if (rc)
+		goto out_free;
+
+	return 0;
+out_free:
+	wil_ring_free_edma(wil, ring);
+	return rc;
+}
+
+static void wil_rx_buf_len_init_edma(struct wil6210_priv *wil)
+{
+	wil->rx_buf_len = rx_large_buf ?
+		WIL_MAX_ETH_MTU : TXRX_BUF_LEN_DEFAULT - WIL_MAX_MPDU_OVERHEAD;
+}
+
+static int wil_rx_init_edma(struct wil6210_priv *wil, u16 desc_ring_size)
+{
+	u16 status_ring_size;
+	struct wil_ring *ring = &wil->ring_rx;
+	int rc;
+	size_t elem_size = wil->use_compressed_rx_status ?
+		sizeof(struct wil_rx_status_compressed) :
+		sizeof(struct wil_rx_status_extended);
+	int i;
+	u16 max_rx_pl_per_desc;
+
+	if (wil->rx_status_ring_order < WIL_SRING_SIZE_ORDER_MIN ||
+	    wil->rx_status_ring_order > WIL_SRING_SIZE_ORDER_MAX)
+		wil->rx_status_ring_order = WIL_RX_SRING_SIZE_ORDER_DEFAULT;
+
+	status_ring_size = 1 << wil->rx_status_ring_order;
+
+	wil_dbg_misc(wil,
+		     "rx_init, desc_ring_size=%u, status_ring_size=%u, elem_size=%zu\n",
+		     desc_ring_size, status_ring_size, elem_size);
+
+	wil_rx_buf_len_init_edma(wil);
+
+	max_rx_pl_per_desc = wil->rx_buf_len + ETH_HLEN +
+		WIL_EDMA_MAX_DATA_OFFSET;
+
+	/* Use debugfs dbg_num_rx_srings if set, reserve one sring for TX */
+	if (wil->num_rx_status_rings > WIL6210_MAX_STATUS_RINGS - 1)
+		wil->num_rx_status_rings = WIL6210_MAX_STATUS_RINGS - 1;
+
+	wil_dbg_misc(wil, "rx_init: allocate %d status rings\n",
+		     wil->num_rx_status_rings);
+
+	rc = wil_wmi_cfg_def_rx_offload(wil, max_rx_pl_per_desc);
+	if (rc)
+		return rc;
+
+	/* Allocate status ring */
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		int sring_id = wil_find_free_sring(wil);
+
+		if (sring_id < 0) {
+			rc = -EFAULT;
+			goto err_free_status;
+		}
+		rc = wil_init_rx_sring(wil, status_ring_size, elem_size,
+				       sring_id);
+		if (rc)
+			goto err_free_status;
+	}
+
+	/* Allocate descriptor ring */
+	rc = wil_init_rx_desc_ring(wil, desc_ring_size,
+				   WIL_DEFAULT_RX_STATUS_RING_ID);
+	if (rc)
+		goto err_free_status;
+
+	if (wil->rx_buff_id_count >= status_ring_size) {
+		wil_info(wil,
+			 "rx_buff_id_count %d exceeds sring_size %d. set it to %d\n",
+			 wil->rx_buff_id_count, status_ring_size,
+			 status_ring_size - 1);
+		wil->rx_buff_id_count = status_ring_size - 1;
+	}
+
+	/* Allocate Rx buffer array */
+	rc = wil_init_rx_buff_arr(wil, wil->rx_buff_id_count);
+	if (rc)
+		goto err_free_desc;
+
+	/* Fill descriptor ring with credits */
+	rc = wil_rx_refill_edma(wil);
+	if (rc)
+		goto err_free_rx_buff_arr;
+
+	return 0;
+err_free_rx_buff_arr:
+	wil_free_rx_buff_arr(wil);
+err_free_desc:
+	wil_ring_free_edma(wil, ring);
+err_free_status:
+	for (i = 0; i < wil->num_rx_status_rings; i++)
+		wil_sring_free(wil, &wil->srings[i]);
+
+	return rc;
+}
+
+static int wil_ring_init_tx_edma(struct wil6210_vif *vif, int ring_id,
+				 int size, int cid, int tid)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	int rc;
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+
+	lockdep_assert_held(&wil->mutex);
+
+	wil_dbg_misc(wil,
+		     "init TX ring: ring_id=%u, cid=%u, tid=%u, sring_id=%u\n",
+		     ring_id, cid, tid, wil->tx_sring_idx);
+
+	wil_tx_data_init(txdata);
+	ring->size = size;
+	rc = wil_ring_alloc_desc_ring(wil, ring);
+	if (rc)
+		goto out;
+
+	wil->ring2cid_tid[ring_id][0] = cid;
+	wil->ring2cid_tid[ring_id][1] = tid;
+	if (!vif->privacy)
+		txdata->dot1x_open = true;
+
+	rc = wil_wmi_tx_desc_ring_add(vif, ring_id, cid, tid);
+	if (rc) {
+		wil_err(wil, "WMI_TX_DESC_RING_ADD_CMD failed\n");
+		goto out_free;
+	}
+
+	if (txdata->dot1x_open && agg_wsize >= 0)
+		wil_addba_tx_request(wil, ring_id, agg_wsize);
+
+	return 0;
+ out_free:
+	spin_lock_bh(&txdata->lock);
+	txdata->dot1x_open = false;
+	txdata->enabled = 0;
+	spin_unlock_bh(&txdata->lock);
+	wil_ring_free_edma(wil, ring);
+	wil->ring2cid_tid[ring_id][0] = WIL6210_MAX_CID;
+	wil->ring2cid_tid[ring_id][1] = 0;
+
+ out:
+	return rc;
+}
+
+static int wil_ring_init_bcast_edma(struct wil6210_vif *vif, int ring_id,
+				    int size)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	int rc;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+
+	wil_dbg_misc(wil, "init bcast: ring_id=%d, sring_id=%d\n",
+		     ring_id, wil->tx_sring_idx);
+
+	lockdep_assert_held(&wil->mutex);
+
+	wil_tx_data_init(txdata);
+	ring->size = size;
+	ring->is_rx = false;
+	rc = wil_ring_alloc_desc_ring(wil, ring);
+	if (rc)
+		goto out;
+
+	wil->ring2cid_tid[ring_id][0] = WIL6210_MAX_CID; /* CID */
+	wil->ring2cid_tid[ring_id][1] = 0; /* TID */
+	if (!vif->privacy)
+		txdata->dot1x_open = true;
+
+	rc = wil_wmi_bcast_desc_ring_add(vif, ring_id);
+	if (rc)
+		goto out_free;
+
+	return 0;
+
+ out_free:
+	spin_lock_bh(&txdata->lock);
+	txdata->enabled = 0;
+	txdata->dot1x_open = false;
+	spin_unlock_bh(&txdata->lock);
+	wil_ring_free_edma(wil, ring);
+
+out:
+	return rc;
+}
+
+static void wil_tx_fini_edma(struct wil6210_priv *wil)
+{
+	struct wil_status_ring *sring = &wil->srings[wil->tx_sring_idx];
+
+	wil_dbg_misc(wil, "free TX sring\n");
+
+	wil_sring_free(wil, sring);
+}
+
+static void wil_rx_data_free(struct wil_status_ring *sring)
+{
+	if (!sring)
+		return;
+
+	kfree_skb(sring->rx_data.skb);
+	sring->rx_data.skb = NULL;
+}
+
+static void wil_rx_fini_edma(struct wil6210_priv *wil)
+{
+	struct wil_ring *ring = &wil->ring_rx;
+	int i;
+
+	wil_dbg_misc(wil, "rx_fini_edma\n");
+
+	wil_ring_free_edma(wil, ring);
+
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		wil_rx_data_free(&wil->srings[i]);
+		wil_sring_free(wil, &wil->srings[i]);
+	}
+
+	wil_free_rx_buff_arr(wil);
+}
+
+void wil_init_txrx_ops_edma(struct wil6210_priv *wil)
+{
+	wil->txrx_ops.configure_interrupt_moderation =
+		wil_configure_interrupt_moderation_edma;
+	/* TX ops */
+	wil->txrx_ops.ring_init_tx = wil_ring_init_tx_edma;
+	wil->txrx_ops.ring_fini_tx = wil_ring_free_edma;
+	wil->txrx_ops.ring_init_bcast = wil_ring_init_bcast_edma;
+	wil->txrx_ops.tx_init = wil_tx_init_edma;
+	wil->txrx_ops.tx_fini = wil_tx_fini_edma;
+	/* RX ops */
+	wil->txrx_ops.rx_init = wil_rx_init_edma;
+	wil->txrx_ops.rx_fini = wil_rx_fini_edma;
+}
+
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
index 14e0b6ce6dc4..c6f500b5150f 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.h
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -19,6 +19,25 @@
 
 #include "wil6210.h"
 
+/* limit status ring size in range [ring size..max ring size] */
+#define WIL_SRING_SIZE_ORDER_MIN	(WIL_RING_SIZE_ORDER_MIN)
+#define WIL_SRING_SIZE_ORDER_MAX	(WIL_RING_SIZE_ORDER_MAX)
+/* RX sring order should be bigger than RX ring order */
+#define WIL_RX_SRING_SIZE_ORDER_DEFAULT	(11)
+#define WIL_TX_SRING_SIZE_ORDER_DEFAULT	(12)
+#define WIL_RX_BUFF_ARR_SIZE_DEFAULT (1536)
+
+#define WIL_DEFAULT_RX_STATUS_RING_ID 0
+#define WIL_RX_DESC_RING_ID 0
+#define WIL_RX_STATUS_IRQ_IDX 0
+#define WIL_TX_STATUS_IRQ_IDX 1
+
+#define WIL_EDMA_AGG_WATERMARK (0xffff)
+#define WIL_EDMA_AGG_WATERMARK_POS (16)
+
+#define WIL_EDMA_IDLE_TIME_LIMIT_USEC (50)
+#define WIL_EDMA_TIME_UNIT_CLK_CYCLES (330) /* fits 1 usec */
+
 /* Enhanced Rx descriptor - MAC part
  * [dword 0] : Reserved
  * [dword 1] : Reserved
@@ -216,7 +235,7 @@ struct wil_ring_tx_status {
  *	bit 22..23 : CB mode:2 - The CB Mode: 0-DMG, 1-EDMG, 2-Wide
  *	bit 24..27 : Data Offset:4 - The data offset, a code that describe the
  *		     payload shift from the beginning of the buffer:
- *		     0 - 0 Bytes, 1 - 2 Bytes, 2 - 6 Bytes
+ *		     0 - 0 Bytes, 3 - 2 Bytes
  *	bit     28 : A-MSDU Present:1 - The QoS (b7) A-MSDU present field
  *	bit     29 : A-MSDU Type:1 The QoS (b8) A-MSDU Type field
  *	bit     30 : A-MPDU:1 - Packet is part of aggregated MPDU
@@ -286,5 +305,38 @@ struct wil_rx_status_extended {
 	struct wil_rx_status_extension ext;
 };
 
+static inline u32 wil_ring_next_head(struct wil_ring *ring)
+{
+	return (ring->swhead + 1) % ring->size;
+}
+
+static inline void wil_desc_set_addr_edma(struct wil_ring_dma_addr *addr,
+					  __le16 *addr_high_high,
+					  dma_addr_t pa)
+{
+	addr->addr_low = cpu_to_le32(lower_32_bits(pa));
+	addr->addr_high = cpu_to_le16((u16)upper_32_bits(pa));
+	*addr_high_high = cpu_to_le16((u16)(upper_32_bits(pa) >> 16));
+}
+
+static inline
+dma_addr_t wil_tx_desc_get_addr_edma(struct wil_ring_tx_enhanced_dma *dma)
+{
+	return le32_to_cpu(dma->addr.addr_low) |
+			   ((u64)le16_to_cpu(dma->addr.addr_high) << 32) |
+			   ((u64)le16_to_cpu(dma->addr_high_high) << 48);
+}
+
+static inline
+dma_addr_t wil_rx_desc_get_addr_edma(struct wil_ring_rx_enhanced_dma *dma)
+{
+	return le32_to_cpu(dma->addr.addr_low) |
+			   ((u64)le16_to_cpu(dma->addr.addr_high) << 32) |
+			   ((u64)le16_to_cpu(dma->addr_high_high) << 48);
+}
+
+void wil_configure_interrupt_moderation_edma(struct wil6210_priv *wil);
+void wil_init_txrx_ops_edma(struct wil6210_priv *wil);
+
 #endif /* WIL6210_TXRX_EDMA_H */
 
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 810ed5b8e558..bc049b640d59 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -37,6 +37,9 @@ extern bool rx_large_buf;
 extern bool debug_fw;
 extern bool disable_ap_sme;
 
+struct wil6210_priv;
+struct wil6210_vif;
+
 #define WIL_NAME "wil6210"
 
 #define WIL_FW_NAME_DEFAULT "wil6210.fw"
@@ -307,6 +310,18 @@ struct RGF_ICR {
 #define RGF_CAF_PLL_LOCK_STATUS		(0x88afec)
 	#define BIT_CAF_OSC_DIG_XTAL_STABLE	BIT(0)
 
+/* eDMA */
+#define RGF_INT_COUNT_ON_SPECIAL_EVT	(0x8b62d8)
+
+#define RGF_INT_CTRL_INT_GEN_CFG_0	(0x8bc000)
+#define RGF_INT_CTRL_INT_GEN_CFG_1	(0x8bc004)
+#define RGF_INT_GEN_TIME_UNIT_LIMIT	(0x8bc0c8)
+
+#define RGF_INT_GEN_CTRL		(0x8bc0ec)
+	#define BIT_CONTROL_0			BIT(0)
+
+#define RGF_INT_GEN_IDLE_TIME_LIMIT	(0x8bc134)
+
 #define USER_EXT_USER_PMU_3		(0x88d00c)
 	#define BIT_PMU_DEVICE_RDY		BIT(0)
 
@@ -512,6 +527,24 @@ struct wil_status_ring {
 	struct wil_ring_rx_data rx_data;
 };
 
+/**
+ * struct tx_rx_ops - different TX/RX ops for legacy and enhanced
+ * DMA flow
+ */
+struct wil_txrx_ops {
+	void (*configure_interrupt_moderation)(struct wil6210_priv *wil);
+	/* TX ops */
+	int (*ring_init_tx)(struct wil6210_vif *vif, int ring_id,
+			    int size, int cid, int tid);
+	void (*ring_fini_tx)(struct wil6210_priv *wil, struct wil_ring *ring);
+	int (*ring_init_bcast)(struct wil6210_vif *vif, int id, int size);
+	int (*tx_init)(struct wil6210_priv *wil);
+	void (*tx_fini)(struct wil6210_priv *wil);
+	/* RX ops */
+	int (*rx_init)(struct wil6210_priv *wil, u16 ring_size);
+	void (*rx_fini)(struct wil6210_priv *wil);
+};
+
 /**
  * Additional data for Tx ring
  */
@@ -848,12 +881,15 @@ struct wil6210_priv {
 	struct wil_ring ring_tx[WIL6210_MAX_TX_RINGS];
 	struct wil_ring_tx_data ring_tx_data[WIL6210_MAX_TX_RINGS];
 	struct wil_status_ring srings[WIL6210_MAX_STATUS_RINGS];
-	int num_rx_status_rings;
+	u8 num_rx_status_rings;
+	int tx_sring_idx;
 	u8 ring2cid_tid[WIL6210_MAX_TX_RINGS][2]; /* [0] - CID, [1] - TID */
 	struct wil_sta_info sta[WIL6210_MAX_CID];
 	u32 ring_idle_trsh; /* HW fetches up to 16 descriptors at once  */
 	u32 dma_addr_size; /* indicates dma addr size */
 	struct wil_rx_buff_mgmt rx_buff_mgmt;
+	bool use_enhanced_dma_hw;
+	struct wil_txrx_ops txrx_ops;
 
 	struct mutex mutex; /* for wil6210_priv access in wil_{up|down} */
 	/* statistics */
@@ -896,6 +932,12 @@ struct wil6210_priv {
 	u32 rgf_fw_assert_code_addr;
 	u32 rgf_ucode_assert_code_addr;
 	u32 iccm_base;
+
+	/* relevant only for eDMA */
+	bool use_compressed_rx_status;
+	u32 rx_status_ring_order;
+	u32 tx_status_ring_order;
+	u32 rx_buff_id_count;
 };
 
 #define wil_to_wiphy(i) (i->wiphy)
@@ -1168,14 +1210,10 @@ void wil_probe_client_flush(struct wil6210_vif *vif);
 void wil_probe_client_worker(struct work_struct *work);
 void wil_disconnect_worker(struct work_struct *work);
 
-int wil_rx_init(struct wil6210_priv *wil, u16 size);
-void wil_rx_fini(struct wil6210_priv *wil);
+void wil_init_txrx_ops(struct wil6210_priv *wil);
 
 /* TX API */
-int wil_vring_init_tx(struct wil6210_vif *vif, int id, int size,
-		      int cid, int tid);
-void wil_ring_fini_tx(struct wil6210_priv *wil, int id);
-int wil_tx_init(struct wil6210_vif *vif, int cid);
+int wil_ring_init_tx(struct wil6210_vif *vif, int cid);
 int wil_vring_init_bcast(struct wil6210_vif *vif, int id, int size);
 int wil_bcast_init(struct wil6210_vif *vif);
 void wil_bcast_fini(struct wil6210_vif *vif);
@@ -1227,4 +1265,14 @@ int wmi_start_sched_scan(struct wil6210_priv *wil,
 int wmi_stop_sched_scan(struct wil6210_priv *wil);
 int wmi_mgmt_tx(struct wil6210_vif *vif, const u8 *buf, size_t len);
 
+/* WMI for enhanced DMA */
+int wil_wmi_tx_sring_cfg(struct wil6210_priv *wil, int ring_id);
+int wil_wmi_cfg_def_rx_offload(struct wil6210_priv *wil,
+			       u16 max_rx_pl_per_desc);
+int wil_wmi_rx_sring_add(struct wil6210_priv *wil, u16 ring_id);
+int wil_wmi_rx_desc_ring_add(struct wil6210_priv *wil, int status_ring_id);
+int wil_wmi_tx_desc_ring_add(struct wil6210_vif *vif, int ring_id, int cid,
+			     int tid);
+int wil_wmi_bcast_desc_ring_add(struct wil6210_vif *vif, int ring_id);
+
 #endif /* __WIL6210_H__ */
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 1cf802101dd9..b2e966df57f5 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -420,10 +420,10 @@ static const char *cmdid2name(u16 cmdid)
 		return "WMI_DEL_STA_CMD";
 	case WMI_DISCONNECT_STA_CMDID:
 		return "WMI_DISCONNECT_STA_CMD";
-	case WMI_VRING_BA_EN_CMDID:
-		return "WMI_VRING_BA_EN_CMD";
-	case WMI_VRING_BA_DIS_CMDID:
-		return "WMI_VRING_BA_DIS_CMD";
+	case WMI_RING_BA_EN_CMDID:
+		return "WMI_RING_BA_EN_CMD";
+	case WMI_RING_BA_DIS_CMDID:
+		return "WMI_RING_BA_DIS_CMD";
 	case WMI_RCP_DELBA_CMDID:
 		return "WMI_RCP_DELBA_CMD";
 	case WMI_RCP_ADDBA_RESP_CMDID:
@@ -450,6 +450,18 @@ static const char *cmdid2name(u16 cmdid)
 		return "WMI_START_SCHED_SCAN_CMD";
 	case WMI_STOP_SCHED_SCAN_CMDID:
 		return "WMI_STOP_SCHED_SCAN_CMD";
+	case WMI_TX_STATUS_RING_ADD_CMDID:
+		return "WMI_TX_STATUS_RING_ADD_CMD";
+	case WMI_RX_STATUS_RING_ADD_CMDID:
+		return "WMI_RX_STATUS_RING_ADD_CMD";
+	case WMI_TX_DESC_RING_ADD_CMDID:
+		return "WMI_TX_DESC_RING_ADD_CMD";
+	case WMI_RX_DESC_RING_ADD_CMDID:
+		return "WMI_RX_DESC_RING_ADD_CMD";
+	case WMI_BCAST_DESC_RING_ADD_CMDID:
+		return "WMI_BCAST_DESC_RING_ADD_CMD";
+	case WMI_CFG_DEF_RX_OFFLOAD_CMDID:
+		return "WMI_CFG_DEF_RX_OFFLOAD_CMD";
 	default:
 		return "Untracked CMD";
 	}
@@ -504,8 +516,8 @@ static const char *eventid2name(u16 eventid)
 		return "WMI_RCP_ADDBA_REQ_EVENT";
 	case WMI_DELBA_EVENTID:
 		return "WMI_DELBA_EVENT";
-	case WMI_VRING_EN_EVENTID:
-		return "WMI_VRING_EN_EVENT";
+	case WMI_RING_EN_EVENTID:
+		return "WMI_RING_EN_EVENT";
 	case WMI_DATA_PORT_OPEN_EVENTID:
 		return "WMI_DATA_PORT_OPEN_EVENT";
 	case WMI_AOA_MEAS_EVENTID:
@@ -574,6 +586,16 @@ static const char *eventid2name(u16 eventid)
 		return "WMI_STOP_SCHED_SCAN_EVENT";
 	case WMI_SCHED_SCAN_RESULT_EVENTID:
 		return "WMI_SCHED_SCAN_RESULT_EVENT";
+	case WMI_TX_STATUS_RING_CFG_DONE_EVENTID:
+		return "WMI_TX_STATUS_RING_CFG_DONE_EVENT";
+	case WMI_RX_STATUS_RING_CFG_DONE_EVENTID:
+		return "WMI_RX_STATUS_RING_CFG_DONE_EVENT";
+	case WMI_TX_DESC_RING_CFG_DONE_EVENTID:
+		return "WMI_TX_DESC_RING_CFG_DONE_EVENT";
+	case WMI_RX_DESC_RING_CFG_DONE_EVENTID:
+		return "WMI_RX_DESC_RING_CFG_DONE_EVENT";
+	case WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID:
+		return "WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENT";
 	default:
 		return "Untracked EVENT";
 	}
@@ -961,7 +983,7 @@ static void wmi_evt_connect(struct wil6210_vif *vif, int id, void *d, int len)
 	wil->sta[evt->cid].mid = vif->mid;
 	wil->sta[evt->cid].status = wil_sta_conn_pending;
 
-	rc = wil_tx_init(vif, evt->cid);
+	rc = wil_ring_init_tx(vif, evt->cid);
 	if (rc) {
 		wil_err(wil, "config tx vring failed for CID %d, rc (%d)\n",
 			evt->cid, rc);
@@ -1118,11 +1140,11 @@ static void wmi_evt_eapol_rx(struct wil6210_vif *vif, int id, void *d, int len)
 	}
 }
 
-static void wmi_evt_vring_en(struct wil6210_vif *vif, int id, void *d, int len)
+static void wmi_evt_ring_en(struct wil6210_vif *vif, int id, void *d, int len)
 {
 	struct wil6210_priv *wil = vif_to_wil(vif);
-	struct wmi_vring_en_event *evt = d;
-	u8 vri = evt->vring_index;
+	struct wmi_ring_en_event *evt = d;
+	u8 vri = evt->ring_index;
 	struct wireless_dev *wdev = vif_to_wdev(vif);
 
 	wil_dbg_wmi(wil, "Enable vring %d MID %d\n", vri, vif->mid);
@@ -1332,7 +1354,7 @@ static const struct {
 	{WMI_BA_STATUS_EVENTID,		wmi_evt_ba_status},
 	{WMI_RCP_ADDBA_REQ_EVENTID,	wmi_evt_addba_rx_req},
 	{WMI_DELBA_EVENTID,		wmi_evt_delba},
-	{WMI_VRING_EN_EVENTID,		wmi_evt_vring_en},
+	{WMI_RING_EN_EVENTID,		wmi_evt_ring_en},
 	{WMI_DATA_PORT_OPEN_EVENTID,		wmi_evt_ignore},
 	{WMI_SCHED_SCAN_RESULT_EVENTID,		wmi_evt_sched_scan_result},
 };
@@ -2118,8 +2140,8 @@ int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
 int wmi_addba(struct wil6210_priv *wil, u8 mid,
 	      u8 ringid, u8 size, u16 timeout)
 {
-	struct wmi_vring_ba_en_cmd cmd = {
-		.ringid = ringid,
+	struct wmi_ring_ba_en_cmd cmd = {
+		.ring_id = ringid,
 		.agg_max_wsize = size,
 		.ba_timeout = cpu_to_le16(timeout),
 		.amsdu = 0,
@@ -2128,19 +2150,19 @@ int wmi_addba(struct wil6210_priv *wil, u8 mid,
 	wil_dbg_wmi(wil, "addba: (ring %d size %d timeout %d)\n", ringid, size,
 		    timeout);
 
-	return wmi_send(wil, WMI_VRING_BA_EN_CMDID, mid, &cmd, sizeof(cmd));
+	return wmi_send(wil, WMI_RING_BA_EN_CMDID, mid, &cmd, sizeof(cmd));
 }
 
 int wmi_delba_tx(struct wil6210_priv *wil, u8 mid, u8 ringid, u16 reason)
 {
-	struct wmi_vring_ba_dis_cmd cmd = {
-		.ringid = ringid,
+	struct wmi_ring_ba_dis_cmd cmd = {
+		.ring_id = ringid,
 		.reason = cpu_to_le16(reason),
 	};
 
 	wil_dbg_wmi(wil, "delba_tx: (ring %d reason %d)\n", ringid, reason);
 
-	return wmi_send(wil, WMI_VRING_BA_DIS_CMDID, mid, &cmd, sizeof(cmd));
+	return wmi_send(wil, WMI_RING_BA_DIS_CMDID, mid, &cmd, sizeof(cmd));
 }
 
 int wmi_delba_rx(struct wil6210_priv *wil, u8 mid, u8 cidxtid, u16 reason)
@@ -2907,3 +2929,263 @@ int wmi_mgmt_tx(struct wil6210_vif *vif, const u8 *buf, size_t len)
 
 	return rc;
 }
+
+int wil_wmi_tx_sring_cfg(struct wil6210_priv *wil, int ring_id)
+{
+	int rc;
+	struct wil6210_vif *vif = ndev_to_vif(wil->main_ndev);
+	struct wil_status_ring *sring = &wil->srings[ring_id];
+	struct wmi_tx_status_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(sring->size),
+		},
+		.irq_index = WIL_TX_STATUS_IRQ_IDX
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_tx_status_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_id = ring_id;
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(sring->pa);
+	rc = wmi_call(wil, WMI_TX_STATUS_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_TX_STATUS_RING_CFG_DONE_EVENTID,
+		      &reply, sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "TX_STATUS_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "TX_STATUS_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	sring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+
+	return 0;
+}
+
+int wil_wmi_cfg_def_rx_offload(struct wil6210_priv *wil, u16 max_rx_pl_per_desc)
+{
+	struct net_device *ndev = wil->main_ndev;
+	struct wil6210_vif *vif = ndev_to_vif(ndev);
+	int rc;
+	struct wmi_cfg_def_rx_offload_cmd cmd = {
+		.max_msdu_size = cpu_to_le16(wil_mtu2macbuf(WIL_MAX_ETH_MTU)),
+		.max_rx_pl_per_desc = cpu_to_le16(max_rx_pl_per_desc),
+		.decap_trans_type = WMI_DECAP_TYPE_802_3,
+		.l2_802_3_offload_ctrl = 0,
+		.l3_l4_ctrl = 1 << L3_L4_CTRL_TCPIP_CHECKSUM_EN_POS,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_cfg_def_rx_offload_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	rc = wmi_call(wil, WMI_CFG_DEF_RX_OFFLOAD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_CFG_DEF_RX_OFFLOAD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "WMI_CFG_DEF_RX_OFFLOAD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int wil_wmi_rx_sring_add(struct wil6210_priv *wil, u16 ring_id)
+{
+	struct net_device *ndev = wil->main_ndev;
+	struct wil6210_vif *vif = ndev_to_vif(ndev);
+	struct wil_status_ring *sring = &wil->srings[ring_id];
+	int rc;
+	struct wmi_rx_status_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(sring->size),
+			.ring_id = ring_id,
+		},
+		.rx_msg_type = wil->use_compressed_rx_status ?
+			WMI_RX_MSG_TYPE_COMPRESSED :
+			WMI_RX_MSG_TYPE_EXTENDED,
+		.irq_index = WIL_RX_STATUS_IRQ_IDX,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_rx_status_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(sring->pa);
+	rc = wmi_call(wil, WMI_RX_STATUS_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_RX_STATUS_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "RX_STATUS_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "RX_STATUS_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	sring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+
+	return 0;
+}
+
+int wil_wmi_rx_desc_ring_add(struct wil6210_priv *wil, int status_ring_id)
+{
+	struct net_device *ndev = wil->main_ndev;
+	struct wil6210_vif *vif = ndev_to_vif(ndev);
+	struct wil_ring *ring = &wil->ring_rx;
+	int rc;
+	struct wmi_rx_desc_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(ring->size),
+			.ring_id = WIL_RX_DESC_RING_ID,
+		},
+		.status_ring_id = status_ring_id,
+		.irq_index = WIL_RX_STATUS_IRQ_IDX,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_rx_desc_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(ring->pa);
+	cmd.sw_tail_host_addr = cpu_to_le64(ring->edma_rx_swtail.pa);
+	rc = wmi_call(wil, WMI_RX_DESC_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_RX_DESC_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_RX_DESC_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "WMI_RX_DESC_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	ring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+
+	return 0;
+}
+
+int wil_wmi_tx_desc_ring_add(struct wil6210_vif *vif, int ring_id, int cid,
+			     int tid)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	int sring_id = wil->tx_sring_idx; /* there is only one TX sring */
+	int rc;
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+	struct wmi_tx_desc_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(ring->size),
+			.ring_id = ring_id,
+		},
+		.status_ring_id = sring_id,
+		.cid = cid,
+		.tid = tid,
+		.encap_trans_type = WMI_VRING_ENC_TYPE_802_3,
+		.max_msdu_size = cpu_to_le16(wil_mtu2macbuf(mtu_max)),
+		.schd_params = {
+			.priority = cpu_to_le16(0),
+			.timeslot_us = cpu_to_le16(0xfff),
+		}
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_tx_desc_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(ring->pa);
+	rc = wmi_call(wil, WMI_TX_DESC_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_TX_DESC_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_TX_DESC_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "WMI_TX_DESC_RING_ADD_CMD failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&txdata->lock);
+	ring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+	txdata->mid = vif->mid;
+	txdata->enabled = 1;
+	spin_unlock_bh(&txdata->lock);
+
+	return 0;
+}
+
+int wil_wmi_bcast_desc_ring_add(struct wil6210_vif *vif, int ring_id)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wil_ring *ring = &wil->ring_tx[ring_id];
+	int rc;
+	struct wmi_bcast_desc_ring_add_cmd cmd = {
+		.ring_cfg = {
+			.ring_size = cpu_to_le16(ring->size),
+			.ring_id = ring_id,
+		},
+		.status_ring_id = wil->tx_sring_idx,
+		.encap_trans_type = WMI_VRING_ENC_TYPE_802_3,
+	};
+	struct {
+		struct wmi_cmd_hdr hdr;
+		struct wmi_rx_desc_ring_cfg_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_id];
+
+	cmd.ring_cfg.ring_mem_base = cpu_to_le64(ring->pa);
+	rc = wmi_call(wil, WMI_BCAST_DESC_RING_ADD_CMDID, vif->mid, &cmd,
+		      sizeof(cmd), WMI_TX_DESC_RING_CFG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_BCAST_DESC_RING_ADD_CMD failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "Broadcast Tx config failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&txdata->lock);
+	ring->hwtail = le32_to_cpu(reply.evt.ring_tail_ptr);
+	txdata->mid = vif->mid;
+	txdata->enabled = 1;
+	spin_unlock_bh(&txdata->lock);
+
+	return 0;
+}
diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index dc503d903786..38e788000801 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -148,8 +148,8 @@ enum wmi_command_id {
 	WMI_CFG_RX_CHAIN_CMDID				= 0x820,
 	WMI_VRING_CFG_CMDID				= 0x821,
 	WMI_BCAST_VRING_CFG_CMDID			= 0x822,
-	WMI_VRING_BA_EN_CMDID				= 0x823,
-	WMI_VRING_BA_DIS_CMDID				= 0x824,
+	WMI_RING_BA_EN_CMDID				= 0x823,
+	WMI_RING_BA_DIS_CMDID				= 0x824,
 	WMI_RCP_ADDBA_RESP_CMDID			= 0x825,
 	WMI_RCP_DELBA_CMDID				= 0x826,
 	WMI_SET_SSID_CMDID				= 0x827,
@@ -163,6 +163,7 @@ enum wmi_command_id {
 	WMI_BF_SM_MGMT_CMDID				= 0x838,
 	WMI_BF_RXSS_MGMT_CMDID				= 0x839,
 	WMI_BF_TRIG_CMDID				= 0x83A,
+	WMI_RCP_ADDBA_RESP_EDMA_CMDID			= 0x83B,
 	WMI_LINK_MAINTAIN_CFG_WRITE_CMDID		= 0x842,
 	WMI_LINK_MAINTAIN_CFG_READ_CMDID		= 0x843,
 	WMI_SET_SECTORS_CMDID				= 0x849,
@@ -235,6 +236,12 @@ enum wmi_command_id {
 	WMI_PRIO_TX_SECTORS_NUMBER_CMDID		= 0x9A6,
 	WMI_PRIO_TX_SECTORS_SET_DEFAULT_CFG_CMDID	= 0x9A7,
 	WMI_BF_CONTROL_CMDID				= 0x9AA,
+	WMI_TX_STATUS_RING_ADD_CMDID			= 0x9C0,
+	WMI_RX_STATUS_RING_ADD_CMDID			= 0x9C1,
+	WMI_TX_DESC_RING_ADD_CMDID			= 0x9C2,
+	WMI_RX_DESC_RING_ADD_CMDID			= 0x9C3,
+	WMI_BCAST_DESC_RING_ADD_CMDID			= 0x9C4,
+	WMI_CFG_DEF_RX_OFFLOAD_CMDID			= 0x9C5,
 	WMI_SCHEDULING_SCHEME_CMDID			= 0xA01,
 	WMI_FIXED_SCHEDULING_CONFIG_CMDID		= 0xA02,
 	WMI_ENABLE_FIXED_SCHEDULING_CMDID		= 0xA03,
@@ -781,18 +788,90 @@ struct wmi_lo_power_calib_from_otp_event {
 	u8 reserved[3];
 } __packed;
 
-/* WMI_VRING_BA_EN_CMDID */
-struct wmi_vring_ba_en_cmd {
-	u8 ringid;
+struct wmi_edma_ring_cfg {
+	__le64 ring_mem_base;
+	/* size in number of items */
+	__le16 ring_size;
+	u8 ring_id;
+	u8 reserved;
+} __packed;
+
+enum wmi_rx_msg_type {
+	WMI_RX_MSG_TYPE_COMPRESSED	= 0x00,
+	WMI_RX_MSG_TYPE_EXTENDED	= 0x01,
+};
+
+struct wmi_tx_status_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	u8 irq_index;
+	u8 reserved[3];
+} __packed;
+
+struct wmi_rx_status_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	u8 irq_index;
+	/* wmi_rx_msg_type */
+	u8 rx_msg_type;
+	u8 reserved[2];
+} __packed;
+
+struct wmi_cfg_def_rx_offload_cmd {
+	__le16 max_msdu_size;
+	__le16 max_rx_pl_per_desc;
+	u8 decap_trans_type;
+	u8 l2_802_3_offload_ctrl;
+	u8 l2_nwifi_offload_ctrl;
+	u8 vlan_id;
+	u8 nwifi_ds_trans_type;
+	u8 l3_l4_ctrl;
+	u8 reserved[6];
+} __packed;
+
+struct wmi_tx_desc_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	__le16 max_msdu_size;
+	/* Correlated status ring (0-63) */
+	u8 status_ring_id;
+	u8 cid;
+	u8 tid;
+	u8 encap_trans_type;
+	u8 mac_ctrl;
+	u8 to_resolution;
+	u8 agg_max_wsize;
+	u8 reserved[3];
+	struct wmi_vring_cfg_schd schd_params;
+} __packed;
+
+struct wmi_rx_desc_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	u8 irq_index;
+	/* 0-63 status rings */
+	u8 status_ring_id;
+	u8 reserved[2];
+	__le64 sw_tail_host_addr;
+} __packed;
+
+struct wmi_bcast_desc_ring_add_cmd {
+	struct wmi_edma_ring_cfg ring_cfg;
+	__le16 max_msdu_size;
+	/* Correlated status ring (0-63) */
+	u8 status_ring_id;
+	u8 encap_trans_type;
+	u8 reserved[4];
+} __packed;
+
+/* WMI_RING_BA_EN_CMDID */
+struct wmi_ring_ba_en_cmd {
+	u8 ring_id;
 	u8 agg_max_wsize;
 	__le16 ba_timeout;
 	u8 amsdu;
 	u8 reserved[3];
 } __packed;
 
-/* WMI_VRING_BA_DIS_CMDID */
-struct wmi_vring_ba_dis_cmd {
-	u8 ringid;
+/* WMI_RING_BA_DIS_CMDID */
+struct wmi_ring_ba_dis_cmd {
+	u8 ring_id;
 	u8 reserved;
 	__le16 reason;
 } __packed;
@@ -950,6 +1029,21 @@ struct wmi_rcp_addba_resp_cmd {
 	u8 reserved[2];
 } __packed;
 
+/* WMI_RCP_ADDBA_RESP_EDMA_CMDID */
+struct wmi_rcp_addba_resp_edma_cmd {
+	u8 cid;
+	u8 tid;
+	u8 dialog_token;
+	u8 reserved;
+	__le16 status_code;
+	/* ieee80211_ba_parameterset field to send */
+	__le16 ba_param_set;
+	__le16 ba_timeout;
+	u8 status_ring_id;
+	/* wmi_cfg_rx_chain_cmd_reorder_type */
+	u8 reorder_type;
+} __packed;
+
 /* WMI_RCP_DELBA_CMDID */
 struct wmi_rcp_delba_cmd {
 	/* Used for cid less than 8. For higher cid set
@@ -1535,7 +1629,7 @@ enum wmi_event_id {
 	WMI_BF_CTRL_DONE_EVENTID			= 0x1862,
 	WMI_NOTIFY_REQ_DONE_EVENTID			= 0x1863,
 	WMI_GET_STATUS_DONE_EVENTID			= 0x1864,
-	WMI_VRING_EN_EVENTID				= 0x1865,
+	WMI_RING_EN_EVENTID				= 0x1865,
 	WMI_GET_RF_STATUS_EVENTID			= 0x1866,
 	WMI_GET_BASEBAND_TYPE_EVENTID			= 0x1867,
 	WMI_VRING_SWITCH_TIMING_CONFIG_EVENTID		= 0x1868,
@@ -1587,6 +1681,11 @@ enum wmi_event_id {
 	WMI_PRIO_TX_SECTORS_NUMBER_EVENTID		= 0x19A6,
 	WMI_PRIO_TX_SECTORS_SET_DEFAULT_CFG_EVENTID	= 0x19A7,
 	WMI_BF_CONTROL_EVENTID				= 0x19AA,
+	WMI_TX_STATUS_RING_CFG_DONE_EVENTID		= 0x19C0,
+	WMI_RX_STATUS_RING_CFG_DONE_EVENTID		= 0x19C1,
+	WMI_TX_DESC_RING_CFG_DONE_EVENTID		= 0x19C2,
+	WMI_RX_DESC_RING_CFG_DONE_EVENTID		= 0x19C3,
+	WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID		= 0x19C5,
 	WMI_SCHEDULING_SCHEME_EVENTID			= 0x1A01,
 	WMI_FIXED_SCHEDULING_CONFIG_COMPLETE_EVENTID	= 0x1A02,
 	WMI_ENABLE_FIXED_SCHEDULING_COMPLETE_EVENTID	= 0x1A03,
@@ -1997,6 +2096,49 @@ struct wmi_rcp_addba_resp_sent_event {
 	u8 reserved2[2];
 } __packed;
 
+/* WMI_TX_STATUS_RING_CFG_DONE_EVENTID */
+struct wmi_tx_status_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
+/* WMI_RX_STATUS_RING_CFG_DONE_EVENTID */
+struct wmi_rx_status_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
+/* WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID */
+struct wmi_cfg_def_rx_offload_done_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_TX_DESC_RING_CFG_DONE_EVENTID */
+struct wmi_tx_desc_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
+/* WMI_RX_DESC_RING_CFG_DONE_EVENTID */
+struct wmi_rx_desc_ring_cfg_done_event {
+	u8 ring_id;
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+	__le32 ring_tail_ptr;
+} __packed;
+
 /* WMI_RCP_ADDBA_REQ_EVENTID */
 struct wmi_rcp_addba_req_event {
 	/* Used for cid less than 8. For higher cid set
@@ -2047,9 +2189,9 @@ struct wmi_data_port_open_event {
 	u8 reserved[3];
 } __packed;
 
-/* WMI_VRING_EN_EVENTID */
-struct wmi_vring_en_event {
-	u8 vring_index;
+/* WMI_RING_EN_EVENTID */
+struct wmi_ring_en_event {
+	u8 ring_index;
 	u8 reserved[3];
 } __packed;
 
-- 
cgit v1.2.3


From 9202d7b6748098d508a3d0a7fcc221a4bcf1ecd9 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:28 +0300
Subject: wil6210: add support for enhanced DMA TX data flows

The enhanced DMA TX data path is handled using a descriptor
ring per connection and a single status ring.

The driver gets TX completions via the TX status ring. Each
status message points to the completed descriptor ring and
includes the number of completed descriptors in this ring.

Non TSO enhanced DMA TX descriptors are similar to legacy DMA
TX descriptors, hence the same transmit function can be used.

However, enhanced DMA TSO frames division is performed by the
HW, hence a new function is added to handle enhanced DMA TSO.

Signed-off-by: Gidon Studinski <gidons@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/interrupt.c | 126 ++++++--
 drivers/net/wireless/ath/wil6210/netdev.c    |  36 ++-
 drivers/net/wireless/ath/wil6210/trace.h     |  25 ++
 drivers/net/wireless/ath/wil6210/txrx.c      | 194 ++++++------
 drivers/net/wireless/ath/wil6210/txrx.h      |  22 ++
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 427 ++++++++++++++++++++++++++-
 drivers/net/wireless/ath/wil6210/txrx_edma.h |  33 ++-
 drivers/net/wireless/ath/wil6210/wil6210.h   |  15 +
 8 files changed, 750 insertions(+), 128 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index 311d48233165..1603b9f7feb9 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -44,6 +44,7 @@
 				    (~(BIT_DMA_EP_RX_ICR_RX_HTRSH)))
 #define WIL6210_IMC_TX		(BIT_DMA_EP_TX_ICR_TX_DONE | \
 				BIT_DMA_EP_TX_ICR_TX_DONE_N(0))
+#define WIL6210_IMC_TX_EDMA		BIT_TX_STATUS_IRQ
 #define WIL6210_IMC_MISC_NO_HALP	(ISR_MISC_FW_READY | \
 					 ISR_MISC_MBOX_EVT | \
 					 ISR_MISC_FW_ERROR)
@@ -87,6 +88,12 @@ static void wil6210_mask_irq_tx(struct wil6210_priv *wil)
 	      WIL6210_IRQ_DISABLE);
 }
 
+static void wil6210_mask_irq_tx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, IMS),
+	      WIL6210_IRQ_DISABLE);
+}
+
 static void wil6210_mask_irq_rx(struct wil6210_priv *wil)
 {
 	wil_w(wil, RGF_DMA_EP_RX_ICR + offsetof(struct RGF_ICR, IMS),
@@ -125,6 +132,12 @@ void wil6210_unmask_irq_tx(struct wil6210_priv *wil)
 	      WIL6210_IMC_TX);
 }
 
+void wil6210_unmask_irq_tx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, IMC),
+	      WIL6210_IMC_TX_EDMA);
+}
+
 void wil6210_unmask_irq_rx(struct wil6210_priv *wil)
 {
 	bool unmask_rx_htrsh = atomic_read(&wil->connected_vifs) > 0;
@@ -164,6 +177,7 @@ void wil_mask_irq(struct wil6210_priv *wil)
 	wil_dbg_irq(wil, "mask_irq\n");
 
 	wil6210_mask_irq_tx(wil);
+	wil6210_mask_irq_tx_edma(wil);
 	wil6210_mask_irq_rx(wil);
 	wil6210_mask_irq_misc(wil, true);
 	wil6210_mask_irq_pseudo(wil);
@@ -179,10 +193,16 @@ void wil_unmask_irq(struct wil6210_priv *wil)
 	      WIL_ICR_ICC_VALUE);
 	wil_w(wil, RGF_DMA_EP_MISC_ICR + offsetof(struct RGF_ICR, ICC),
 	      WIL_ICR_ICC_MISC_VALUE);
+	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, ICC),
+	      WIL_ICR_ICC_VALUE);
 
 	wil6210_unmask_irq_pseudo(wil);
-	wil6210_unmask_irq_tx(wil);
-	wil6210_unmask_irq_rx(wil);
+	if (wil->use_enhanced_dma_hw) {
+		wil6210_unmask_irq_tx_edma(wil);
+	} else {
+		wil6210_unmask_irq_tx(wil);
+		wil6210_unmask_irq_rx(wil);
+	}
 	wil6210_unmask_irq_misc(wil, true);
 }
 
@@ -315,6 +335,49 @@ static irqreturn_t wil6210_irq_rx(int irq, void *cookie)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t wil6210_irq_tx_edma(int irq, void *cookie)
+{
+	struct wil6210_priv *wil = cookie;
+	u32 isr = wil_ioread32_and_clear(wil->csr +
+					 HOSTADDR(RGF_INT_GEN_TX_ICR) +
+					 offsetof(struct RGF_ICR, ICR));
+	bool need_unmask = true;
+
+	trace_wil6210_irq_tx(isr);
+	wil_dbg_irq(wil, "ISR TX 0x%08x\n", isr);
+
+	if (unlikely(!isr)) {
+		wil_err(wil, "spurious IRQ: TX\n");
+		return IRQ_NONE;
+	}
+
+	wil6210_mask_irq_tx_edma(wil);
+
+	if (likely(isr & BIT_TX_STATUS_IRQ)) {
+		wil_dbg_irq(wil, "TX status ring\n");
+		isr &= ~BIT_TX_STATUS_IRQ;
+		if (likely(test_bit(wil_status_fwready, wil->status))) {
+			wil_dbg_txrx(wil, "NAPI(Tx) schedule\n");
+			need_unmask = false;
+			napi_schedule(&wil->napi_tx);
+		} else {
+			wil_err(wil, "Got Tx status ring IRQ while in reset\n");
+		}
+	}
+
+	if (unlikely(isr))
+		wil_err(wil, "un-handled TX ISR bits 0x%08x\n", isr);
+
+	/* Tx IRQ will be enabled when NAPI processing finished */
+
+	atomic_inc(&wil->isr_count_tx);
+
+	if (unlikely(need_unmask))
+		wil6210_unmask_irq_tx_edma(wil);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t wil6210_irq_tx(int irq, void *cookie)
 {
 	struct wil6210_priv *wil = cookie;
@@ -531,30 +594,45 @@ static irqreturn_t wil6210_thread_irq(int irq, void *cookie)
  */
 static int wil6210_debug_irq_mask(struct wil6210_priv *wil, u32 pseudo_cause)
 {
+	u32 icm_rx = 0, icr_rx = 0, imv_rx = 0;
+	u32 icm_tx, icr_tx, imv_tx;
+	u32 icm_misc, icr_misc, imv_misc;
+
 	if (!test_bit(wil_status_irqen, wil->status)) {
-		u32 icm_rx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_RX_ICR) +
-				offsetof(struct RGF_ICR, ICM));
-		u32 icr_rx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_RX_ICR) +
-				offsetof(struct RGF_ICR, ICR));
-		u32 imv_rx = wil_r(wil, RGF_DMA_EP_RX_ICR +
-				   offsetof(struct RGF_ICR, IMV));
-		u32 icm_tx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_TX_ICR) +
-				offsetof(struct RGF_ICR, ICM));
-		u32 icr_tx = wil_ioread32_and_clear(wil->csr +
-				HOSTADDR(RGF_DMA_EP_TX_ICR) +
-				offsetof(struct RGF_ICR, ICR));
-		u32 imv_tx = wil_r(wil, RGF_DMA_EP_TX_ICR +
+		if (wil->use_enhanced_dma_hw) {
+			icm_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_TX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_TX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_tx = wil_r(wil, RGF_INT_GEN_TX_ICR +
+					   offsetof(struct RGF_ICR, IMV));
+		} else {
+			icm_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_RX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_RX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_rx = wil_r(wil, RGF_DMA_EP_RX_ICR +
 				   offsetof(struct RGF_ICR, IMV));
-		u32 icm_misc = wil_ioread32_and_clear(wil->csr +
+			icm_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_TX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_tx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_DMA_EP_TX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_tx = wil_r(wil, RGF_DMA_EP_TX_ICR +
+					   offsetof(struct RGF_ICR, IMV));
+		}
+		icm_misc = wil_ioread32_and_clear(wil->csr +
 				HOSTADDR(RGF_DMA_EP_MISC_ICR) +
 				offsetof(struct RGF_ICR, ICM));
-		u32 icr_misc = wil_ioread32_and_clear(wil->csr +
+		icr_misc = wil_ioread32_and_clear(wil->csr +
 				HOSTADDR(RGF_DMA_EP_MISC_ICR) +
 				offsetof(struct RGF_ICR, ICR));
-		u32 imv_misc = wil_r(wil, RGF_DMA_EP_MISC_ICR +
+		imv_misc = wil_r(wil, RGF_DMA_EP_MISC_ICR +
 				     offsetof(struct RGF_ICR, IMV));
 
 		/* HALP interrupt can be unmasked when misc interrupts are
@@ -617,7 +695,7 @@ static irqreturn_t wil6210_hardirq(int irq, void *cookie)
 		rc = IRQ_WAKE_THREAD;
 
 	if ((pseudo_cause & BIT_DMA_PSEUDO_CAUSE_TX) &&
-	    (wil6210_irq_tx(irq, cookie) == IRQ_WAKE_THREAD))
+	    (wil->txrx_ops.irq_tx(irq, cookie) == IRQ_WAKE_THREAD))
 		rc = IRQ_WAKE_THREAD;
 
 	if ((pseudo_cause & BIT_DMA_PSEUDO_CAUSE_MISC) &&
@@ -645,6 +723,8 @@ void wil6210_clear_irq(struct wil6210_priv *wil)
 		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_TX_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
+	wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_TX_ICR) +
+		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_MISC_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
 	wmb(); /* make sure write completed */
@@ -673,6 +753,10 @@ int wil6210_init_irq(struct wil6210_priv *wil, int irq, bool use_msi)
 
 	wil_dbg_misc(wil, "init_irq: %s\n", use_msi ? "MSI" : "INTx");
 
+	if (wil->use_enhanced_dma_hw)
+		wil->txrx_ops.irq_tx = wil6210_irq_tx_edma;
+	else
+		wil->txrx_ops.irq_tx = wil6210_irq_tx;
 	rc = request_threaded_irq(irq, wil6210_hardirq,
 				  wil6210_thread_irq,
 				  use_msi ? 0 : IRQF_SHARED,
diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index 3c6a59fd08df..eeda2b618e6e 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -157,6 +157,30 @@ static int wil6210_netdev_poll_tx(struct napi_struct *napi, int budget)
 	return min(tx_done, budget);
 }
 
+static int wil6210_netdev_poll_tx_edma(struct napi_struct *napi, int budget)
+{
+	struct wil6210_priv *wil = container_of(napi, struct wil6210_priv,
+						napi_tx);
+	int tx_done;
+	/* There is only one status TX ring */
+	struct wil_status_ring *sring = &wil->srings[wil->tx_sring_idx];
+
+	if (!sring->va)
+		return 0;
+
+	tx_done = wil_tx_sring_handler(wil, sring);
+
+	if (tx_done < budget) {
+		napi_complete(napi);
+		wil6210_unmask_irq_tx_edma(wil);
+		wil_dbg_txrx(wil, "NAPI TX complete\n");
+	}
+
+	wil_dbg_txrx(wil, "NAPI TX poll(%d) done %d\n", budget, tx_done);
+
+	return min(tx_done, budget);
+}
+
 static void wil_dev_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -420,9 +444,15 @@ int wil_if_add(struct wil6210_priv *wil)
 	init_dummy_netdev(&wil->napi_ndev);
 	netif_napi_add(&wil->napi_ndev, &wil->napi_rx, wil6210_netdev_poll_rx,
 		       WIL6210_NAPI_BUDGET);
-	netif_tx_napi_add(&wil->napi_ndev,
-			  &wil->napi_tx, wil6210_netdev_poll_tx,
-			  WIL6210_NAPI_BUDGET);
+	if (wil->use_enhanced_dma_hw)
+		netif_tx_napi_add(&wil->napi_ndev,
+				  &wil->napi_tx, wil6210_netdev_poll_tx_edma,
+				  WIL6210_NAPI_BUDGET);
+	else
+		netif_tx_napi_add(&wil->napi_ndev,
+				  &wil->napi_tx, wil6210_netdev_poll_tx,
+				  WIL6210_NAPI_BUDGET);
+
 
 	wil_update_net_queues_bh(wil, vif, NULL, true);
 
diff --git a/drivers/net/wireless/ath/wil6210/trace.h b/drivers/net/wireless/ath/wil6210/trace.h
index c4db2a9d9f7f..6aed2461b0d4 100644
--- a/drivers/net/wireless/ath/wil6210/trace.h
+++ b/drivers/net/wireless/ath/wil6210/trace.h
@@ -226,6 +226,31 @@ TRACE_EVENT(wil6210_tx_done,
 		  __entry->err)
 );
 
+TRACE_EVENT(wil6210_tx_status,
+	    TP_PROTO(struct wil_ring_tx_status *msg, u16 index,
+		     unsigned int len),
+	    TP_ARGS(msg, index, len),
+	    TP_STRUCT__entry(__field(u16, index)
+			     __field(unsigned int, len)
+			     __field(u8, num_descs)
+			     __field(u8, ring_id)
+			     __field(u8, status)
+			     __field(u8, mcs)
+
+	    ),
+	    TP_fast_assign(__entry->index = index;
+			   __entry->len = len;
+			   __entry->num_descs = msg->num_descriptors;
+			   __entry->ring_id = msg->ring_id;
+			   __entry->status = msg->status;
+			   __entry->mcs = wil_tx_status_get_mcs(msg);
+	    ),
+	    TP_printk(
+		      "ring_id %d swtail 0x%x len %d num_descs %d status 0x%x mcs %d",
+		      __entry->ring_id, __entry->index, __entry->len,
+		      __entry->num_descs, __entry->status, __entry->mcs)
+);
+
 #endif /* WIL6210_TRACE_H || TRACE_HEADER_MULTI_READ*/
 
 #if defined(CONFIG_WIL6210_TRACING) && !defined(__CHECKER__)
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 2a359e164e08..12d509e7f29c 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -117,12 +117,6 @@ bool wil_is_tx_idle(struct wil6210_priv *wil)
 	return true;
 }
 
-/* wil_val_in_range - check if value in [min,max) */
-static inline bool wil_val_in_range(int val, int min, int max)
-{
-	return val >= min && val < max;
-}
-
 static int wil_vring_alloc(struct wil6210_priv *wil, struct wil_ring *vring)
 {
 	struct device *dev = wil_to_dev(wil);
@@ -184,9 +178,10 @@ static int wil_vring_alloc(struct wil6210_priv *wil, struct wil_ring *vring)
 	return 0;
 }
 
-static void wil_txdesc_unmap(struct device *dev, struct vring_tx_desc *d,
+static void wil_txdesc_unmap(struct device *dev, union wil_tx_desc *desc,
 			     struct wil_ctx *ctx)
 {
+	struct vring_tx_desc *d = &desc->legacy;
 	dma_addr_t pa = wil_desc_addr(&d->dma.addr);
 	u16 dmalen = le16_to_cpu(d->dma.length);
 
@@ -239,7 +234,7 @@ static void wil_vring_free(struct wil6210_priv *wil, struct wil_ring *vring)
 				continue;
 			}
 			*d = *_d;
-			wil_txdesc_unmap(dev, d, ctx);
+			wil_txdesc_unmap(dev, (union wil_tx_desc *)d, ctx);
 			if (ctx->skb)
 				dev_kfree_skb_any(ctx->skb);
 			vring->swtail = wil_ring_next_tail(vring);
@@ -887,6 +882,30 @@ static void wil_rx_fini(struct wil6210_priv *wil)
 		wil_vring_free(wil, vring);
 }
 
+static int wil_tx_desc_map(union wil_tx_desc *desc, dma_addr_t pa,
+			   u32 len, int vring_index)
+{
+	struct vring_tx_desc *d = &desc->legacy;
+
+	wil_desc_addr_set(&d->dma.addr, pa);
+	d->dma.ip_length = 0;
+	/* 0..6: mac_length; 7:ip_version 0-IP6 1-IP4*/
+	d->dma.b11 = 0/*14 | BIT(7)*/;
+	d->dma.error = 0;
+	d->dma.status = 0; /* BIT(0) should be 0 for HW_OWNED */
+	d->dma.length = cpu_to_le16((u16)len);
+	d->dma.d0 = (vring_index << DMA_CFG_DESC_TX_0_QID_POS);
+	d->mac.d[0] = 0;
+	d->mac.d[1] = 0;
+	d->mac.d[2] = 0;
+	d->mac.ucode_cmd = 0;
+	/* translation type:  0 - bypass; 1 - 802.3; 2 - native wifi */
+	d->mac.d[2] = BIT(MAC_CFG_DESC_TX_2_SNAP_HDR_INSERTION_EN_POS) |
+		      (1 << MAC_CFG_DESC_TX_2_L2_TRANSLATION_TYPE_POS);
+
+	return 0;
+}
+
 void wil_tx_data_init(struct wil_ring_tx_data *txdata)
 {
 	spin_lock_bh(&txdata->lock);
@@ -1114,8 +1133,8 @@ static struct wil_ring *wil_find_tx_ucast(struct wil6210_priv *wil,
 	return NULL;
 }
 
-static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			struct wil_ring *vring, struct sk_buff *skb);
+static int wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif,
+		       struct wil_ring *ring, struct sk_buff *skb);
 
 static struct wil_ring *wil_find_tx_ring_sta(struct wil6210_priv *wil,
 					     struct wil6210_vif *vif,
@@ -1258,7 +1277,7 @@ found:
 		if (skb2) {
 			wil_dbg_txrx(wil, "BCAST DUP -> ring %d\n", i);
 			wil_set_da_for_vring(wil, skb2, i);
-			wil_tx_vring(wil, vif, v2, skb2);
+			wil_tx_ring(wil, vif, v2, skb2);
 		} else {
 			wil_err(wil, "skb_copy failed\n");
 		}
@@ -1267,28 +1286,6 @@ found:
 	return v;
 }
 
-static int wil_tx_desc_map(struct vring_tx_desc *d, dma_addr_t pa, u32 len,
-			   int vring_index)
-{
-	wil_desc_addr_set(&d->dma.addr, pa);
-	d->dma.ip_length = 0;
-	/* 0..6: mac_length; 7:ip_version 0-IP6 1-IP4*/
-	d->dma.b11 = 0/*14 | BIT(7)*/;
-	d->dma.error = 0;
-	d->dma.status = 0; /* BIT(0) should be 0 for HW_OWNED */
-	d->dma.length = cpu_to_le16((u16)len);
-	d->dma.d0 = (vring_index << DMA_CFG_DESC_TX_0_QID_POS);
-	d->mac.d[0] = 0;
-	d->mac.d[1] = 0;
-	d->mac.d[2] = 0;
-	d->mac.ucode_cmd = 0;
-	/* translation type:  0 - bypass; 1 - 802.3; 2 - native wifi */
-	d->mac.d[2] = BIT(MAC_CFG_DESC_TX_2_SNAP_HDR_INSERTION_EN_POS) |
-		      (1 << MAC_CFG_DESC_TX_2_L2_TRANSLATION_TYPE_POS);
-
-	return 0;
-}
-
 static inline
 void wil_tx_desc_set_nr_frags(struct vring_tx_desc *d, int nr_frags)
 {
@@ -1498,7 +1495,8 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 		goto err_exit;
 	}
 
-	wil_tx_desc_map(hdr_desc, pa, hdrlen, vring_index);
+	wil->txrx_ops.tx_desc_map((union wil_tx_desc *)hdr_desc, pa,
+				  hdrlen, vring_index);
 	wil_tx_desc_offload_setup_tso(hdr_desc, skb, wil_tso_type_hdr, is_ipv4,
 				      tcp_hdr_len, skb_net_hdr_len);
 	wil_tx_last_desc(hdr_desc);
@@ -1565,7 +1563,8 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 				d = &desc_mem;
 			}
 
-			wil_tx_desc_map(d, pa, lenmss, vring_index);
+			wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d,
+						  pa, lenmss, vring_index);
 			wil_tx_desc_offload_setup_tso(d, skb, desc_tso_type,
 						      is_ipv4, tcp_hdr_len,
 						      skb_net_hdr_len);
@@ -1680,7 +1679,7 @@ mem_error:
 		*d = *_desc;
 		_desc->dma.status = TX_DMA_STATUS_DU;
 		ctx = &vring->ctx[i];
-		wil_txdesc_unmap(dev, d, ctx);
+		wil_txdesc_unmap(dev, (union wil_tx_desc *)d, ctx);
 		memset(ctx, 0, sizeof(*ctx));
 		descs_used--;
 	}
@@ -1688,26 +1687,26 @@ err_exit:
 	return rc;
 }
 
-static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			  struct wil_ring *vring, struct sk_buff *skb)
+static int __wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif,
+			 struct wil_ring *ring, struct sk_buff *skb)
 {
 	struct device *dev = wil_to_dev(wil);
 	struct vring_tx_desc dd, *d = &dd;
 	volatile struct vring_tx_desc *_d;
-	u32 swhead = vring->swhead;
-	int avail = wil_ring_avail_tx(vring);
+	u32 swhead = ring->swhead;
+	int avail = wil_ring_avail_tx(ring);
 	int nr_frags = skb_shinfo(skb)->nr_frags;
 	uint f = 0;
-	int vring_index = vring - wil->ring_tx;
-	struct wil_ring_tx_data  *txdata = &wil->ring_tx_data[vring_index];
+	int ring_index = ring - wil->ring_tx;
+	struct wil_ring_tx_data  *txdata = &wil->ring_tx_data[ring_index];
 	uint i = swhead;
 	dma_addr_t pa;
 	int used;
-	bool mcast = (vring_index == vif->bcast_ring);
+	bool mcast = (ring_index == vif->bcast_ring);
 	uint len = skb_headlen(skb);
 
 	wil_dbg_txrx(wil, "tx_ring: %d bytes to ring %d, nr_frags %d\n",
-		     skb->len, vring_index, nr_frags);
+		     skb->len, ring_index, nr_frags);
 
 	if (unlikely(!txdata->enabled))
 		return -EINVAL;
@@ -1715,23 +1714,24 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	if (unlikely(avail < 1 + nr_frags)) {
 		wil_err_ratelimited(wil,
 				    "Tx ring[%2d] full. No space for %d fragments\n",
-				    vring_index, 1 + nr_frags);
+				    ring_index, 1 + nr_frags);
 		return -ENOMEM;
 	}
-	_d = &vring->va[i].tx.legacy;
+	_d = &ring->va[i].tx.legacy;
 
 	pa = dma_map_single(dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE);
 
-	wil_dbg_txrx(wil, "Tx[%2d] skb %d bytes 0x%p -> %pad\n", vring_index,
+	wil_dbg_txrx(wil, "Tx[%2d] skb %d bytes 0x%p -> %pad\n", ring_index,
 		     skb_headlen(skb), skb->data, &pa);
 	wil_hex_dump_txrx("Tx ", DUMP_PREFIX_OFFSET, 16, 1,
 			  skb->data, skb_headlen(skb), false);
 
 	if (unlikely(dma_mapping_error(dev, pa)))
 		return -EINVAL;
-	vring->ctx[i].mapped_as = wil_mapped_as_single;
+	ring->ctx[i].mapped_as = wil_mapped_as_single;
 	/* 1-st segment */
-	wil_tx_desc_map(d, pa, len, vring_index);
+	wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d, pa, len,
+				   ring_index);
 	if (unlikely(mcast)) {
 		d->mac.d[0] |= BIT(MAC_CFG_DESC_TX_0_MCS_EN_POS); /* MCS 0 */
 		if (unlikely(len > WIL_BCAST_MCS0_LIMIT)) /* set MCS 1 */
@@ -1740,11 +1740,11 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	/* Process TCP/UDP checksum offloading */
 	if (unlikely(wil_tx_desc_offload_setup(d, skb))) {
 		wil_err(wil, "Tx[%2d] Failed to set cksum, drop packet\n",
-			vring_index);
+			ring_index);
 		goto dma_error;
 	}
 
-	vring->ctx[i].nr_frags = nr_frags;
+	ring->ctx[i].nr_frags = nr_frags;
 	wil_tx_desc_set_nr_frags(d, nr_frags + 1);
 
 	/* middle segments */
@@ -1754,20 +1754,21 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 		int len = skb_frag_size(frag);
 
 		*_d = *d;
-		wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", vring_index, i);
+		wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", ring_index, i);
 		wil_hex_dump_txrx("TxD ", DUMP_PREFIX_NONE, 32, 4,
 				  (const void *)d, sizeof(*d), false);
-		i = (swhead + f + 1) % vring->size;
-		_d = &vring->va[i].tx.legacy;
+		i = (swhead + f + 1) % ring->size;
+		_d = &ring->va[i].tx.legacy;
 		pa = skb_frag_dma_map(dev, frag, 0, skb_frag_size(frag),
 				      DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(dev, pa))) {
 			wil_err(wil, "Tx[%2d] failed to map fragment\n",
-				vring_index);
+				ring_index);
 			goto dma_error;
 		}
-		vring->ctx[i].mapped_as = wil_mapped_as_page;
-		wil_tx_desc_map(d, pa, len, vring_index);
+		ring->ctx[i].mapped_as = wil_mapped_as_page;
+		wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d,
+					   pa, len, ring_index);
 		/* no need to check return code -
 		 * if it succeeded for 1-st descriptor,
 		 * it will succeed here too
@@ -1779,7 +1780,7 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	d->dma.d0 |= BIT(DMA_CFG_DESC_TX_0_CMD_MARK_WB_POS);
 	d->dma.d0 |= BIT(DMA_CFG_DESC_TX_0_CMD_DMA_IT_POS);
 	*_d = *d;
-	wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", vring_index, i);
+	wil_dbg_txrx(wil, "Tx[%2d] desc[%4d]\n", ring_index, i);
 	wil_hex_dump_txrx("TxD ", DUMP_PREFIX_NONE, 32, 4,
 			  (const void *)d, sizeof(*d), false);
 
@@ -1787,15 +1788,15 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	 * to prevent skb release before accounting
 	 * in case of immediate "tx done"
 	 */
-	vring->ctx[i].skb = skb_get(skb);
+	ring->ctx[i].skb = skb_get(skb);
 
 	/* performance monitoring */
-	used = wil_ring_used_tx(vring);
+	used = wil_ring_used_tx(ring);
 	if (wil_val_in_range(wil->ring_idle_trsh,
 			     used, used + nr_frags + 1)) {
 		txdata->idle += get_cycles() - txdata->last_idle;
 		wil_dbg_txrx(wil,  "Ring[%2d] not idle %d -> %d\n",
-			     vring_index, used, used + nr_frags + 1);
+			     ring_index, used, used + nr_frags + 1);
 	}
 
 	/* Make sure to advance the head only after descriptor update is done.
@@ -1806,17 +1807,17 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	wmb();
 
 	/* advance swhead */
-	wil_ring_advance_head(vring, nr_frags + 1);
-	wil_dbg_txrx(wil, "Tx[%2d] swhead %d -> %d\n", vring_index, swhead,
-		     vring->swhead);
-	trace_wil6210_tx(vring_index, swhead, skb->len, nr_frags);
+	wil_ring_advance_head(ring, nr_frags + 1);
+	wil_dbg_txrx(wil, "Tx[%2d] swhead %d -> %d\n", ring_index, swhead,
+		     ring->swhead);
+	trace_wil6210_tx(ring_index, swhead, skb->len, nr_frags);
 
 	/* make sure all writes to descriptors (shared memory) are done before
 	 * committing them to HW
 	 */
 	wmb();
 
-	wil_w(wil, vring->hwtail, vring->swhead);
+	wil_w(wil, ring->hwtail, ring->swhead);
 
 	return 0;
  dma_error:
@@ -1825,12 +1826,14 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	for (f = 0; f < nr_frags; f++) {
 		struct wil_ctx *ctx;
 
-		i = (swhead + f) % vring->size;
-		ctx = &vring->ctx[i];
-		_d = &vring->va[i].tx.legacy;
+		i = (swhead + f) % ring->size;
+		ctx = &ring->ctx[i];
+		_d = &ring->va[i].tx.legacy;
 		*d = *_d;
 		_d->dma.status = TX_DMA_STATUS_DU;
-		wil_txdesc_unmap(dev, d, ctx);
+		wil->txrx_ops.tx_desc_unmap(dev,
+					    (union wil_tx_desc *)d,
+					    ctx);
 
 		memset(ctx, 0, sizeof(*ctx));
 	}
@@ -1838,10 +1841,10 @@ static int __wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	return -EINVAL;
 }
 
-static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
-			struct wil_ring *vring, struct sk_buff *skb)
+static int wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif,
+		       struct wil_ring *ring, struct sk_buff *skb)
 {
-	int ring_index = vring - wil->ring_tx;
+	int ring_index = ring - wil->ring_tx;
 	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_index];
 	int rc;
 
@@ -1856,8 +1859,8 @@ static int wil_tx_vring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 		return -EINVAL;
 	}
 
-	rc = (skb_is_gso(skb) ? __wil_tx_vring_tso : __wil_tx_vring)
-	     (wil, vif, vring, skb);
+	rc = (skb_is_gso(skb) ? wil->txrx_ops.tx_ring_tso : __wil_tx_ring)
+	     (wil, vif, ring, skb);
 
 	spin_unlock(&txdata->lock);
 
@@ -1964,7 +1967,7 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	struct wil6210_priv *wil = vif_to_wil(vif);
 	struct ethhdr *eth = (void *)skb->data;
 	bool bcast = is_multicast_ether_addr(eth->h_dest);
-	struct wil_ring *vring;
+	struct wil_ring *ring;
 	static bool pr_once_fw;
 	int rc;
 
@@ -1990,36 +1993,36 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	/* find vring */
 	if (vif->wdev.iftype == NL80211_IFTYPE_STATION && !vif->pbss) {
 		/* in STA mode (ESS), all to same VRING (to AP) */
-		vring = wil_find_tx_ring_sta(wil, vif, skb);
+		ring = wil_find_tx_ring_sta(wil, vif, skb);
 	} else if (bcast) {
 		if (vif->pbss)
 			/* in pbss, no bcast VRING - duplicate skb in
 			 * all stations VRINGs
 			 */
-			vring = wil_find_tx_bcast_2(wil, vif, skb);
+			ring = wil_find_tx_bcast_2(wil, vif, skb);
 		else if (vif->wdev.iftype == NL80211_IFTYPE_AP)
 			/* AP has a dedicated bcast VRING */
-			vring = wil_find_tx_bcast_1(wil, vif, skb);
+			ring = wil_find_tx_bcast_1(wil, vif, skb);
 		else
 			/* unexpected combination, fallback to duplicating
 			 * the skb in all stations VRINGs
 			 */
-			vring = wil_find_tx_bcast_2(wil, vif, skb);
+			ring = wil_find_tx_bcast_2(wil, vif, skb);
 	} else {
 		/* unicast, find specific VRING by dest. address */
-		vring = wil_find_tx_ucast(wil, vif, skb);
+		ring = wil_find_tx_ucast(wil, vif, skb);
 	}
-	if (unlikely(!vring)) {
+	if (unlikely(!ring)) {
 		wil_dbg_txrx(wil, "No Tx RING found for %pM\n", eth->h_dest);
 		goto drop;
 	}
 	/* set up vring entry */
-	rc = wil_tx_vring(wil, vif, vring, skb);
+	rc = wil_tx_ring(wil, vif, ring, skb);
 
 	switch (rc) {
 	case 0:
 		/* shall we stop net queues? */
-		wil_update_net_queues_bh(wil, vif, vring, true);
+		wil_update_net_queues_bh(wil, vif, ring, true);
 		/* statistics will be updated on the tx_complete */
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -2035,22 +2038,6 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	return NET_XMIT_DROP;
 }
 
-static inline bool wil_need_txstat(struct sk_buff *skb)
-{
-	struct ethhdr *eth = (void *)skb->data;
-
-	return is_unicast_ether_addr(eth->h_dest) && skb->sk &&
-	       (skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS);
-}
-
-static inline void wil_consume_skb(struct sk_buff *skb, bool acked)
-{
-	if (unlikely(wil_need_txstat(skb)))
-		skb_complete_wifi_ack(skb, acked);
-	else
-		acked ? dev_consume_skb_any(skb) : dev_kfree_skb_any(skb);
-}
-
 /**
  * Clean up transmitted skb's from the Tx VRING
  *
@@ -2126,7 +2113,9 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 			wil_hex_dump_txrx("TxCD ", DUMP_PREFIX_NONE, 32, 4,
 					  (const void *)d, sizeof(*d), false);
 
-			wil_txdesc_unmap(dev, d, ctx);
+			wil->txrx_ops.tx_desc_unmap(dev,
+						    (union wil_tx_desc *)d,
+						    ctx);
 
 			if (skb) {
 				if (likely(d->dma.error == 0)) {
@@ -2188,6 +2177,9 @@ void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil)
 	wil->txrx_ops.configure_interrupt_moderation =
 		wil_configure_interrupt_moderation;
 	/* TX ops */
+	wil->txrx_ops.tx_desc_map = wil_tx_desc_map;
+	wil->txrx_ops.tx_desc_unmap = wil_txdesc_unmap;
+	wil->txrx_ops.tx_ring_tso =  __wil_tx_vring_tso;
 	wil->txrx_ops.ring_init_tx = wil_vring_init_tx;
 	wil->txrx_ops.ring_fini_tx = wil_vring_free;
 	wil->txrx_ops.ring_init_bcast = wil_vring_init_bcast;
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 4e3781d9e7ec..62806c5bb930 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -555,6 +555,22 @@ static inline int wil_ring_is_full(struct wil_ring *ring)
 	return wil_ring_next_tail(ring) == ring->swhead;
 }
 
+static inline bool wil_need_txstat(struct sk_buff *skb)
+{
+	struct ethhdr *eth = (void *)skb->data;
+
+	return is_unicast_ether_addr(eth->h_dest) && skb->sk &&
+	       (skb_shinfo(skb)->tx_flags & SKBTX_WIFI_STATUS);
+}
+
+static inline void wil_consume_skb(struct sk_buff *skb, bool acked)
+{
+	if (unlikely(wil_need_txstat(skb)))
+		skb_complete_wifi_ack(skb, acked);
+	else
+		acked ? dev_consume_skb_any(skb) : dev_kfree_skb_any(skb);
+}
+
 /* Used space in Tx ring */
 static inline int wil_ring_used_tx(struct wil_ring *ring)
 {
@@ -576,6 +592,12 @@ static inline int wil_get_min_tx_ring_id(struct wil6210_priv *wil)
 	return wil->use_enhanced_dma_hw ? 1 : 0;
 }
 
+/* wil_val_in_range - check if value in [min,max) */
+static inline bool wil_val_in_range(int val, int min, int max)
+{
+	return val >= min && val < max;
+}
+
 void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev);
 void wil_rx_reorder(struct wil6210_priv *wil, struct sk_buff *skb);
 void wil_rx_bar(struct wil6210_priv *wil, struct wil6210_vif *vif,
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 9773d400808d..c449286823a9 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -24,13 +24,15 @@
 #include "wil6210.h"
 #include "txrx_edma.h"
 #include "txrx.h"
+#include "trace.h"
 
 #define WIL_EDMA_MAX_DATA_OFFSET (2)
 
 static void wil_tx_desc_unmap_edma(struct device *dev,
-				   struct wil_tx_enhanced_desc *d,
+				   union wil_tx_desc *desc,
 				   struct wil_ctx *ctx)
 {
+	struct wil_tx_enhanced_desc *d = (struct wil_tx_enhanced_desc *)desc;
 	dma_addr_t pa = wil_tx_desc_get_addr_edma(&d->dma);
 	u16 dmalen = le16_to_cpu(d->dma.length);
 
@@ -206,6 +208,13 @@ static int wil_ring_alloc_skb_edma(struct wil6210_priv *wil,
 	return 0;
 }
 
+static inline void wil_sring_advance_swhead(struct wil_status_ring *sring)
+{
+	sring->swhead = (sring->swhead + 1) % sring->size;
+	if (sring->swhead == 0)
+		sring->desc_rdy_pol = 1 - sring->desc_rdy_pol;
+}
+
 static int wil_rx_refill_edma(struct wil6210_priv *wil)
 {
 	struct wil_ring *ring = &wil->ring_rx;
@@ -446,7 +455,7 @@ static void wil_ring_free_edma(struct wil6210_priv *wil, struct wil_ring *ring)
 			continue;
 		}
 		*d = *_d;
-		wil_tx_desc_unmap_edma(dev, d, ctx);
+		wil_tx_desc_unmap_edma(dev, (union wil_tx_desc *)d, ctx);
 		if (ctx->skb)
 			dev_kfree_skb_any(ctx->skb);
 		ring->swtail = wil_ring_next_tail(ring);
@@ -625,6 +634,417 @@ static int wil_ring_init_tx_edma(struct wil6210_vif *vif, int ring_id,
 	return rc;
 }
 
+static int wil_tx_desc_map_edma(union wil_tx_desc *desc,
+				dma_addr_t pa,
+				u32 len,
+				int ring_index)
+{
+	struct wil_tx_enhanced_desc *d =
+		(struct wil_tx_enhanced_desc *)&desc->enhanced;
+
+	memset(d, 0, sizeof(struct wil_tx_enhanced_desc));
+
+	wil_desc_set_addr_edma(&d->dma.addr, &d->dma.addr_high_high, pa);
+
+	/* 0..6: mac_length; 7:ip_version 0-IP6 1-IP4*/
+	d->dma.length = cpu_to_le16((u16)len);
+	d->mac.d[0] = (ring_index << WIL_EDMA_DESC_TX_MAC_CFG_0_QID_POS);
+	/* translation type:  0 - bypass; 1 - 802.3; 2 - native wifi;
+	 * 3 - eth mode
+	 */
+	d->mac.d[2] = BIT(MAC_CFG_DESC_TX_2_SNAP_HDR_INSERTION_EN_POS) |
+		      (0x3 << MAC_CFG_DESC_TX_2_L2_TRANSLATION_TYPE_POS);
+
+	return 0;
+}
+
+static inline void
+wil_get_next_tx_status_msg(struct wil_status_ring *sring,
+			   struct wil_ring_tx_status *msg)
+{
+	struct wil_ring_tx_status *_msg = (struct wil_ring_tx_status *)
+		(sring->va + (sring->elem_size * sring->swhead));
+
+	*msg = *_msg;
+}
+
+/**
+ * Clean up transmitted skb's from the Tx descriptor RING.
+ * Return number of descriptors cleared.
+ */
+int wil_tx_sring_handler(struct wil6210_priv *wil,
+			 struct wil_status_ring *sring)
+{
+	struct net_device *ndev;
+	struct device *dev = wil_to_dev(wil);
+	struct wil_ring *ring = NULL;
+	struct wil_ring_tx_data *txdata;
+	/* Total number of completed descriptors in all descriptor rings */
+	int desc_cnt = 0;
+	int cid;
+	struct wil_net_stats *stats = NULL;
+	struct wil_tx_enhanced_desc *_d;
+	unsigned int ring_id;
+	unsigned int num_descs;
+	int i;
+	u8 dr_bit; /* Descriptor Ready bit */
+	struct wil_ring_tx_status msg;
+	struct wil6210_vif *vif;
+	int used_before_complete;
+	int used_new;
+
+	wil_get_next_tx_status_msg(sring, &msg);
+	dr_bit = msg.desc_ready >> TX_STATUS_DESC_READY_POS;
+
+	/* Process completion messages while DR bit has the expected polarity */
+	while (dr_bit == sring->desc_rdy_pol) {
+		num_descs = msg.num_descriptors;
+		if (!num_descs) {
+			wil_err(wil, "invalid num_descs 0\n");
+			goto again;
+		}
+
+		/* Find the corresponding descriptor ring */
+		ring_id = msg.ring_id;
+
+		if (unlikely(ring_id >= WIL6210_MAX_TX_RINGS)) {
+			wil_err(wil, "invalid ring id %d\n", ring_id);
+			goto again;
+		}
+		ring = &wil->ring_tx[ring_id];
+		if (unlikely(!ring->va)) {
+			wil_err(wil, "Tx irq[%d]: ring not initialized\n",
+				ring_id);
+			goto again;
+		}
+		txdata = &wil->ring_tx_data[ring_id];
+		if (unlikely(!txdata->enabled)) {
+			wil_info(wil, "Tx irq[%d]: ring disabled\n", ring_id);
+			goto again;
+		}
+		vif = wil->vifs[txdata->mid];
+		if (unlikely(!vif)) {
+			wil_dbg_txrx(wil, "invalid MID %d for ring %d\n",
+				     txdata->mid, ring_id);
+			goto again;
+		}
+
+		ndev = vif_to_ndev(vif);
+
+		cid = wil->ring2cid_tid[ring_id][0];
+		if (cid < WIL6210_MAX_CID)
+			stats = &wil->sta[cid].stats;
+
+		wil_dbg_txrx(wil,
+			     "tx_status: completed desc_ring (%d), num_descs (%d)\n",
+			     ring_id, num_descs);
+
+		used_before_complete = wil_ring_used_tx(ring);
+
+		for (i = 0 ; i < num_descs; ++i) {
+			struct wil_ctx *ctx = &ring->ctx[ring->swtail];
+			struct wil_tx_enhanced_desc dd, *d = &dd;
+			u16 dmalen;
+			struct sk_buff *skb = ctx->skb;
+
+			_d = (struct wil_tx_enhanced_desc *)
+				&ring->va[ring->swtail].tx.enhanced;
+			*d = *_d;
+
+			dmalen = le16_to_cpu(d->dma.length);
+			trace_wil6210_tx_status(&msg, ring->swtail, dmalen);
+			wil_dbg_txrx(wil,
+				     "TxC[%2d][%3d] : %d bytes, status 0x%02x\n",
+				     ring_id, ring->swtail, dmalen,
+				     msg.status);
+			wil_hex_dump_txrx("TxS ", DUMP_PREFIX_NONE, 32, 4,
+					  (const void *)&msg, sizeof(msg),
+					  false);
+
+			wil_tx_desc_unmap_edma(dev,
+					       (union wil_tx_desc *)d,
+					       ctx);
+
+			if (skb) {
+				if (likely(msg.status == 0)) {
+					ndev->stats.tx_packets++;
+					ndev->stats.tx_bytes += skb->len;
+					if (stats) {
+						stats->tx_packets++;
+						stats->tx_bytes += skb->len;
+					}
+				} else {
+					ndev->stats.tx_errors++;
+					if (stats)
+						stats->tx_errors++;
+				}
+				wil_consume_skb(skb, msg.status == 0);
+			}
+			memset(ctx, 0, sizeof(*ctx));
+			/* Make sure the ctx is zeroed before updating the tail
+			 * to prevent a case where wil_tx_ring will see
+			 * this descriptor as used and handle it before ctx zero
+			 * is completed.
+			 */
+			wmb();
+
+			ring->swtail = wil_ring_next_tail(ring);
+
+			desc_cnt++;
+		}
+
+		/* performance monitoring */
+		used_new = wil_ring_used_tx(ring);
+		if (wil_val_in_range(wil->ring_idle_trsh,
+				     used_new, used_before_complete)) {
+			wil_dbg_txrx(wil, "Ring[%2d] idle %d -> %d\n",
+				     ring_id, used_before_complete, used_new);
+			txdata->last_idle = get_cycles();
+		}
+
+again:
+		wil_sring_advance_swhead(sring);
+
+		wil_get_next_tx_status_msg(sring, &msg);
+		dr_bit = msg.desc_ready >> TX_STATUS_DESC_READY_POS;
+	}
+
+	/* shall we wake net queues? */
+	if (desc_cnt)
+		wil_update_net_queues(wil, vif, NULL, false);
+
+	/* Update the HW tail ptr (RD ptr) */
+	wil_w(wil, sring->hwtail, (sring->swhead - 1) % sring->size);
+
+	return desc_cnt;
+}
+
+/**
+ * Sets the descriptor @d up for csum and/or TSO offloading. The corresponding
+ * @skb is used to obtain the protocol and headers length.
+ * @tso_desc_type is a descriptor type for TSO: 0 - a header, 1 - first data,
+ * 2 - middle, 3 - last descriptor.
+ */
+static void wil_tx_desc_offload_setup_tso_edma(struct wil_tx_enhanced_desc *d,
+					       int tso_desc_type, bool is_ipv4,
+					       int tcp_hdr_len,
+					       int skb_net_hdr_len,
+					       int mss)
+{
+	/* Number of descriptors */
+	d->mac.d[2] |= 1;
+	/* Maximum Segment Size */
+	d->mac.tso_mss |= cpu_to_le16(mss >> 2);
+	/* L4 header len: TCP header length */
+	d->dma.l4_hdr_len |= tcp_hdr_len & DMA_CFG_DESC_TX_0_L4_LENGTH_MSK;
+	/* EOP, TSO desc type, Segmentation enable,
+	 * Insert IPv4 and TCP / UDP Checksum
+	 */
+	d->dma.cmd |= BIT(WIL_EDMA_DESC_TX_CFG_EOP_POS) |
+		      tso_desc_type << WIL_EDMA_DESC_TX_CFG_TSO_DESC_TYPE_POS |
+		      BIT(WIL_EDMA_DESC_TX_CFG_SEG_EN_POS) |
+		      BIT(WIL_EDMA_DESC_TX_CFG_INSERT_IP_CHKSUM_POS) |
+		      BIT(WIL_EDMA_DESC_TX_CFG_INSERT_TCP_CHKSUM_POS);
+	/* Calculate pseudo-header */
+	d->dma.w1 |= BIT(WIL_EDMA_DESC_TX_CFG_PSEUDO_HEADER_CALC_EN_POS) |
+		     BIT(WIL_EDMA_DESC_TX_CFG_L4_TYPE_POS);
+	/* IP Header Length */
+	d->dma.ip_length |= skb_net_hdr_len;
+	/* MAC header length and IP address family*/
+	d->dma.b11 |= ETH_HLEN |
+		      is_ipv4 << DMA_CFG_DESC_TX_OFFLOAD_CFG_L3T_IPV4_POS;
+}
+
+static int wil_tx_tso_gen_desc(struct wil6210_priv *wil, void *buff_addr,
+			       int len, uint i, int tso_desc_type,
+			       skb_frag_t *frag, struct wil_ring *ring,
+			       struct sk_buff *skb, bool is_ipv4,
+			       int tcp_hdr_len, int skb_net_hdr_len,
+			       int mss, int *descs_used)
+{
+	struct device *dev = wil_to_dev(wil);
+	struct wil_tx_enhanced_desc *_desc = (struct wil_tx_enhanced_desc *)
+		&ring->va[i].tx.enhanced;
+	struct wil_tx_enhanced_desc desc_mem, *d = &desc_mem;
+	int ring_index = ring - wil->ring_tx;
+	dma_addr_t pa;
+
+	if (len == 0)
+		return 0;
+
+	if (!frag) {
+		pa = dma_map_single(dev, buff_addr, len, DMA_TO_DEVICE);
+		ring->ctx[i].mapped_as = wil_mapped_as_single;
+	} else {
+		pa = skb_frag_dma_map(dev, frag, 0, len, DMA_TO_DEVICE);
+		ring->ctx[i].mapped_as = wil_mapped_as_page;
+	}
+	if (unlikely(dma_mapping_error(dev, pa))) {
+		wil_err(wil, "TSO: Skb DMA map error\n");
+		return -EINVAL;
+	}
+
+	wil->txrx_ops.tx_desc_map((union wil_tx_desc *)d, pa,
+				   len, ring_index);
+	wil_tx_desc_offload_setup_tso_edma(d, tso_desc_type, is_ipv4,
+					   tcp_hdr_len,
+					   skb_net_hdr_len, mss);
+
+	/* hold reference to skb
+	 * to prevent skb release before accounting
+	 * in case of immediate "tx done"
+	 */
+	if (tso_desc_type == wil_tso_type_lst)
+		ring->ctx[i].skb = skb_get(skb);
+
+	wil_hex_dump_txrx("TxD ", DUMP_PREFIX_NONE, 32, 4,
+			  (const void *)d, sizeof(*d), false);
+
+	*_desc = *d;
+	(*descs_used)++;
+
+	return 0;
+}
+
+static int __wil_tx_ring_tso_edma(struct wil6210_priv *wil,
+				  struct wil6210_vif *vif,
+				  struct wil_ring *ring,
+				  struct sk_buff *skb)
+{
+	int ring_index = ring - wil->ring_tx;
+	struct wil_ring_tx_data *txdata = &wil->ring_tx_data[ring_index];
+	int nr_frags = skb_shinfo(skb)->nr_frags;
+	int min_desc_required = nr_frags + 2; /* Headers, Head, Fragments */
+	int used, avail = wil_ring_avail_tx(ring);
+	int f, hdrlen, headlen;
+	int gso_type;
+	bool is_ipv4;
+	u32 swhead = ring->swhead;
+	int descs_used = 0; /* total number of used descriptors */
+	int rc = -EINVAL;
+	int tcp_hdr_len;
+	int skb_net_hdr_len;
+	int mss = skb_shinfo(skb)->gso_size;
+
+	wil_dbg_txrx(wil, "tx_ring_tso: %d bytes to ring %d\n", skb->len,
+		     ring_index);
+
+	if (unlikely(!txdata->enabled))
+		return -EINVAL;
+
+	if (unlikely(avail < min_desc_required)) {
+		wil_err_ratelimited(wil,
+				    "TSO: Tx ring[%2d] full. No space for %d fragments\n",
+				    ring_index, min_desc_required);
+		return -ENOMEM;
+	}
+
+	gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV6 | SKB_GSO_TCPV4);
+	switch (gso_type) {
+	case SKB_GSO_TCPV4:
+		is_ipv4 = true;
+		break;
+	case SKB_GSO_TCPV6:
+		is_ipv4 = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return -EINVAL;
+
+	/* tcp header length and skb network header length are fixed for all
+	 * packet's descriptors - read them once here
+	 */
+	tcp_hdr_len = tcp_hdrlen(skb);
+	skb_net_hdr_len = skb_network_header_len(skb);
+
+	/* First descriptor must contain the header only
+	 * Header Length = MAC header len + IP header len + TCP header len
+	 */
+	hdrlen = ETH_HLEN + tcp_hdr_len + skb_net_hdr_len;
+	wil_dbg_txrx(wil, "TSO: process header descriptor, hdrlen %u\n",
+		     hdrlen);
+	rc = wil_tx_tso_gen_desc(wil, skb->data, hdrlen, swhead,
+				 wil_tso_type_hdr, NULL, ring, skb,
+				 is_ipv4, tcp_hdr_len, skb_net_hdr_len,
+				 mss, &descs_used);
+	if (rc)
+		return -EINVAL;
+
+	/* Second descriptor contains the head */
+	headlen = skb_headlen(skb) - hdrlen;
+	wil_dbg_txrx(wil, "TSO: process skb head, headlen %u\n", headlen);
+	rc = wil_tx_tso_gen_desc(wil, skb->data + hdrlen, headlen,
+				 (swhead + descs_used) % ring->size,
+				 (nr_frags != 0) ? wil_tso_type_first :
+				 wil_tso_type_lst, NULL, ring, skb,
+				 is_ipv4, tcp_hdr_len, skb_net_hdr_len,
+				 mss, &descs_used);
+	if (rc)
+		goto mem_error;
+
+	/* Rest of the descriptors are from the SKB fragments */
+	for (f = 0; f < nr_frags; f++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[f];
+		int len = frag->size;
+
+		wil_dbg_txrx(wil, "TSO: frag[%d]: len %u, descs_used %d\n", f,
+			     len, descs_used);
+
+		rc = wil_tx_tso_gen_desc(wil, NULL, len,
+					 (swhead + descs_used) % ring->size,
+					 (f != nr_frags - 1) ?
+					 wil_tso_type_mid : wil_tso_type_lst,
+					 frag, ring, skb, is_ipv4,
+					 tcp_hdr_len, skb_net_hdr_len,
+					 mss, &descs_used);
+		if (rc)
+			goto mem_error;
+	}
+
+	/* performance monitoring */
+	used = wil_ring_used_tx(ring);
+	if (wil_val_in_range(wil->ring_idle_trsh,
+			     used, used + descs_used)) {
+		txdata->idle += get_cycles() - txdata->last_idle;
+		wil_dbg_txrx(wil,  "Ring[%2d] not idle %d -> %d\n",
+			     ring_index, used, used + descs_used);
+	}
+
+	/* advance swhead */
+	wil_ring_advance_head(ring, descs_used);
+	wil_dbg_txrx(wil, "TSO: Tx swhead %d -> %d\n", swhead, ring->swhead);
+
+	/* make sure all writes to descriptors (shared memory) are done before
+	 * committing them to HW
+	 */
+	wmb();
+
+	wil_w(wil, ring->hwtail, ring->swhead);
+
+	return 0;
+
+mem_error:
+	while (descs_used > 0) {
+		struct device *dev = wil_to_dev(wil);
+		struct wil_ctx *ctx;
+		int i = (swhead + descs_used - 1) % ring->size;
+		struct wil_tx_enhanced_desc dd, *d = &dd;
+		struct wil_tx_enhanced_desc *_desc =
+			(struct wil_tx_enhanced_desc *)
+			&ring->va[i].tx.enhanced;
+
+		*d = *_desc;
+		ctx = &ring->ctx[i];
+		wil_tx_desc_unmap_edma(dev, (union wil_tx_desc *)d, ctx);
+		memset(ctx, 0, sizeof(*ctx));
+		descs_used--;
+	}
+	return rc;
+}
+
 static int wil_ring_init_bcast_edma(struct wil6210_vif *vif, int ring_id,
 				    int size)
 {
@@ -712,6 +1132,9 @@ void wil_init_txrx_ops_edma(struct wil6210_priv *wil)
 	wil->txrx_ops.ring_init_bcast = wil_ring_init_bcast_edma;
 	wil->txrx_ops.tx_init = wil_tx_init_edma;
 	wil->txrx_ops.tx_fini = wil_tx_fini_edma;
+	wil->txrx_ops.tx_desc_map = wil_tx_desc_map_edma;
+	wil->txrx_ops.tx_desc_unmap = wil_tx_desc_unmap_edma;
+	wil->txrx_ops.tx_ring_tso = __wil_tx_ring_tso_edma;
 	/* RX ops */
 	wil->txrx_ops.rx_init = wil_rx_init_edma;
 	wil->txrx_ops.rx_fini = wil_rx_fini_edma;
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
index c6f500b5150f..8eae181877b9 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.h
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -38,6 +38,30 @@
 #define WIL_EDMA_IDLE_TIME_LIMIT_USEC (50)
 #define WIL_EDMA_TIME_UNIT_CLK_CYCLES (330) /* fits 1 usec */
 
+#define WIL_EDMA_DESC_TX_MAC_CFG_0_QID_POS 16
+#define WIL_EDMA_DESC_TX_MAC_CFG_0_QID_LEN 6
+
+#define WIL_EDMA_DESC_TX_CFG_EOP_POS 0
+#define WIL_EDMA_DESC_TX_CFG_EOP_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_TSO_DESC_TYPE_POS 3
+#define WIL_EDMA_DESC_TX_CFG_TSO_DESC_TYPE_LEN 2
+
+#define WIL_EDMA_DESC_TX_CFG_SEG_EN_POS 5
+#define WIL_EDMA_DESC_TX_CFG_SEG_EN_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_INSERT_IP_CHKSUM_POS 6
+#define WIL_EDMA_DESC_TX_CFG_INSERT_IP_CHKSUM_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_INSERT_TCP_CHKSUM_POS 7
+#define WIL_EDMA_DESC_TX_CFG_INSERT_TCP_CHKSUM_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_L4_TYPE_POS 15
+#define WIL_EDMA_DESC_TX_CFG_L4_TYPE_LEN 1
+
+#define WIL_EDMA_DESC_TX_CFG_PSEUDO_HEADER_CALC_EN_POS 5
+#define WIL_EDMA_DESC_TX_CFG_PSEUDO_HEADER_CALC_EN_LEN 1
+
 /* Enhanced Rx descriptor - MAC part
  * [dword 0] : Reserved
  * [dword 1] : Reserved
@@ -303,7 +327,12 @@ struct wil_rx_status_extension {
 struct wil_rx_status_extended {
 	struct wil_rx_status_compressed comp;
 	struct wil_rx_status_extension ext;
-};
+} __packed;
+
+static inline u8 wil_tx_status_get_mcs(struct wil_ring_tx_status *msg)
+{
+	return WIL_GET_BITS(msg->d2, 0, 4);
+}
 
 static inline u32 wil_ring_next_head(struct wil_ring *ring)
 {
@@ -336,6 +365,8 @@ dma_addr_t wil_rx_desc_get_addr_edma(struct wil_ring_rx_enhanced_dma *dma)
 }
 
 void wil_configure_interrupt_moderation_edma(struct wil6210_priv *wil);
+int wil_tx_sring_handler(struct wil6210_priv *wil,
+			 struct wil_status_ring *sring);
 void wil_init_txrx_ops_edma(struct wil6210_priv *wil);
 
 #endif /* WIL6210_TXRX_EDMA_H */
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index bc049b640d59..f35c64e1ca22 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -24,6 +24,7 @@
 #include <net/cfg80211.h>
 #include <linux/timex.h>
 #include <linux/types.h>
+#include <linux/irqreturn.h>
 #include "wmi.h"
 #include "wil_platform.h"
 #include "fw.h"
@@ -39,6 +40,7 @@ extern bool disable_ap_sme;
 
 struct wil6210_priv;
 struct wil6210_vif;
+union wil_tx_desc;
 
 #define WIL_NAME "wil6210"
 
@@ -320,6 +322,10 @@ struct RGF_ICR {
 #define RGF_INT_GEN_CTRL		(0x8bc0ec)
 	#define BIT_CONTROL_0			BIT(0)
 
+/* eDMA status interrupts */
+#define RGF_INT_GEN_TX_ICR		(0x8bc110)
+	#define BIT_TX_STATUS_IRQ BIT(WIL_TX_STATUS_IRQ_IDX)
+#define RGF_INT_CTRL_TX_INT_MASK	(0x8bc130)
 #define RGF_INT_GEN_IDLE_TIME_LIMIT	(0x8bc134)
 
 #define USER_EXT_USER_PMU_3		(0x88d00c)
@@ -540,6 +546,14 @@ struct wil_txrx_ops {
 	int (*ring_init_bcast)(struct wil6210_vif *vif, int id, int size);
 	int (*tx_init)(struct wil6210_priv *wil);
 	void (*tx_fini)(struct wil6210_priv *wil);
+	int (*tx_desc_map)(union wil_tx_desc *desc, dma_addr_t pa,
+			   u32 len, int ring_index);
+	void (*tx_desc_unmap)(struct device *dev,
+			      union wil_tx_desc *desc,
+			      struct wil_ctx *ctx);
+	int (*tx_ring_tso)(struct wil6210_priv *wil, struct wil6210_vif *vif,
+			   struct wil_ring *ring, struct sk_buff *skb);
+	irqreturn_t (*irq_tx)(int irq, void *cookie);
 	/* RX ops */
 	int (*rx_init)(struct wil6210_priv *wil, u16 ring_size);
 	void (*rx_fini)(struct wil6210_priv *wil);
@@ -1226,6 +1240,7 @@ void wil_update_net_queues_bh(struct wil6210_priv *wil, struct wil6210_vif *vif,
 netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 int wil_tx_complete(struct wil6210_vif *vif, int ringid);
 void wil6210_unmask_irq_tx(struct wil6210_priv *wil);
+void wil6210_unmask_irq_tx_edma(struct wil6210_priv *wil);
 
 /* RX API */
 void wil_rx_handle(struct wil6210_priv *wil, int *quota);
-- 
cgit v1.2.3


From 7be13fc3e60fb51570288d4516a15266ed500dfd Mon Sep 17 00:00:00 2001
From: Gidon Studinski <gidons@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:33 +0300
Subject: wil6210: add support for enhanced DMA RX data flows

Enhanced DMA RX data path is handled using a single
RX descriptor ring for all VIFs.
Multiple RX status rings are supported, to allow RSS
and multi MSI support.
The driver gets the RX completions via the RX status rings.
The RX status message includes the completed RX buffer ID,
which points to the allocated SKB.

The enhanced DMA RX data flow supports RX chaining, where
multiple SKBs are merged into a single packet.

Enhanced DMA HW supports RX HW reorder offload, enabled by
default for Talyn-MB.

amsdu_en debugfs entry was added to allow control MSDU aggregation.
Use the following command to disable AMSDU (enabled by default):
echo 0 > amsdu_en

Signed-off-by: Gidon Studinski <gidons@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c    |   1 +
 drivers/net/wireless/ath/wil6210/interrupt.c  |  86 ++++-
 drivers/net/wireless/ath/wil6210/main.c       |   3 +
 drivers/net/wireless/ath/wil6210/netdev.c     |  35 +-
 drivers/net/wireless/ath/wil6210/pcie_bus.c   |   1 +
 drivers/net/wireless/ath/wil6210/pm.c         |   6 +-
 drivers/net/wireless/ath/wil6210/rx_reorder.c |  24 +-
 drivers/net/wireless/ath/wil6210/trace.h      |  34 ++
 drivers/net/wireless/ath/wil6210/txrx.c       |  53 ++-
 drivers/net/wireless/ath/wil6210/txrx.h       |   7 +
 drivers/net/wireless/ath/wil6210/txrx_edma.c  | 456 ++++++++++++++++++++++++++
 drivers/net/wireless/ath/wil6210/txrx_edma.h  | 189 +++++++++++
 drivers/net/wireless/ath/wil6210/wil6210.h    |  24 +-
 drivers/net/wireless/ath/wil6210/wmi.c        |  59 +++-
 drivers/net/wireless/ath/wil6210/wmi.h        |   1 +
 15 files changed, 939 insertions(+), 40 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 212baf46393a..8232fdd6ed09 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1919,6 +1919,7 @@ static const struct dbg_off dbg_wil_off[] = {
 	WIL_FIELD(rx_status_ring_order, 0644,	doff_u32),
 	WIL_FIELD(tx_status_ring_order, 0644,	doff_u32),
 	WIL_FIELD(rx_buff_id_count, 0644,	doff_u32),
+	WIL_FIELD(amsdu_en, 0644,	doff_u8),
 	{},
 };
 
diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index 1603b9f7feb9..d7e112da6a8d 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -45,6 +45,7 @@
 #define WIL6210_IMC_TX		(BIT_DMA_EP_TX_ICR_TX_DONE | \
 				BIT_DMA_EP_TX_ICR_TX_DONE_N(0))
 #define WIL6210_IMC_TX_EDMA		BIT_TX_STATUS_IRQ
+#define WIL6210_IMC_RX_EDMA		BIT_RX_STATUS_IRQ
 #define WIL6210_IMC_MISC_NO_HALP	(ISR_MISC_FW_READY | \
 					 ISR_MISC_MBOX_EVT | \
 					 ISR_MISC_FW_ERROR)
@@ -100,6 +101,12 @@ static void wil6210_mask_irq_rx(struct wil6210_priv *wil)
 	      WIL6210_IRQ_DISABLE);
 }
 
+static void wil6210_mask_irq_rx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_RX_ICR + offsetof(struct RGF_ICR, IMS),
+	      WIL6210_IRQ_DISABLE);
+}
+
 static void wil6210_mask_irq_misc(struct wil6210_priv *wil, bool mask_halp)
 {
 	wil_dbg_irq(wil, "mask_irq_misc: mask_halp(%s)\n",
@@ -146,6 +153,12 @@ void wil6210_unmask_irq_rx(struct wil6210_priv *wil)
 	      unmask_rx_htrsh ? WIL6210_IMC_RX : WIL6210_IMC_RX_NO_RX_HTRSH);
 }
 
+void wil6210_unmask_irq_rx_edma(struct wil6210_priv *wil)
+{
+	wil_w(wil, RGF_INT_GEN_RX_ICR + offsetof(struct RGF_ICR, IMC),
+	      WIL6210_IMC_RX_EDMA);
+}
+
 static void wil6210_unmask_irq_misc(struct wil6210_priv *wil, bool unmask_halp)
 {
 	wil_dbg_irq(wil, "unmask_irq_misc: unmask_halp(%s)\n",
@@ -179,6 +192,7 @@ void wil_mask_irq(struct wil6210_priv *wil)
 	wil6210_mask_irq_tx(wil);
 	wil6210_mask_irq_tx_edma(wil);
 	wil6210_mask_irq_rx(wil);
+	wil6210_mask_irq_rx_edma(wil);
 	wil6210_mask_irq_misc(wil, true);
 	wil6210_mask_irq_pseudo(wil);
 }
@@ -195,10 +209,13 @@ void wil_unmask_irq(struct wil6210_priv *wil)
 	      WIL_ICR_ICC_MISC_VALUE);
 	wil_w(wil, RGF_INT_GEN_TX_ICR + offsetof(struct RGF_ICR, ICC),
 	      WIL_ICR_ICC_VALUE);
+	wil_w(wil, RGF_INT_GEN_RX_ICR + offsetof(struct RGF_ICR, ICC),
+	      WIL_ICR_ICC_VALUE);
 
 	wil6210_unmask_irq_pseudo(wil);
 	if (wil->use_enhanced_dma_hw) {
 		wil6210_unmask_irq_tx_edma(wil);
+		wil6210_unmask_irq_rx_edma(wil);
 	} else {
 		wil6210_unmask_irq_tx(wil);
 		wil6210_unmask_irq_rx(wil);
@@ -335,6 +352,54 @@ static irqreturn_t wil6210_irq_rx(int irq, void *cookie)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t wil6210_irq_rx_edma(int irq, void *cookie)
+{
+	struct wil6210_priv *wil = cookie;
+	u32 isr = wil_ioread32_and_clear(wil->csr +
+					 HOSTADDR(RGF_INT_GEN_RX_ICR) +
+					 offsetof(struct RGF_ICR, ICR));
+	bool need_unmask = true;
+
+	trace_wil6210_irq_rx(isr);
+	wil_dbg_irq(wil, "ISR RX 0x%08x\n", isr);
+
+	if (unlikely(!isr)) {
+		wil_err(wil, "spurious IRQ: RX\n");
+		return IRQ_NONE;
+	}
+
+	wil6210_mask_irq_rx_edma(wil);
+
+	if (likely(isr & BIT_RX_STATUS_IRQ)) {
+		wil_dbg_irq(wil, "RX status ring\n");
+		isr &= ~BIT_RX_STATUS_IRQ;
+		if (likely(test_bit(wil_status_fwready, wil->status))) {
+			if (likely(test_bit(wil_status_napi_en, wil->status))) {
+				wil_dbg_txrx(wil, "NAPI(Rx) schedule\n");
+				need_unmask = false;
+				napi_schedule(&wil->napi_rx);
+			} else {
+				wil_err(wil,
+					"Got Rx interrupt while stopping interface\n");
+			}
+		} else {
+			wil_err(wil, "Got Rx interrupt while in reset\n");
+		}
+	}
+
+	if (unlikely(isr))
+		wil_err(wil, "un-handled RX ISR bits 0x%08x\n", isr);
+
+	/* Rx IRQ will be enabled when NAPI processing finished */
+
+	atomic_inc(&wil->isr_count_rx);
+
+	if (unlikely(need_unmask))
+		wil6210_unmask_irq_rx_edma(wil);
+
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t wil6210_irq_tx_edma(int irq, void *cookie)
 {
 	struct wil6210_priv *wil = cookie;
@@ -594,12 +659,20 @@ static irqreturn_t wil6210_thread_irq(int irq, void *cookie)
  */
 static int wil6210_debug_irq_mask(struct wil6210_priv *wil, u32 pseudo_cause)
 {
-	u32 icm_rx = 0, icr_rx = 0, imv_rx = 0;
+	u32 icm_rx, icr_rx, imv_rx;
 	u32 icm_tx, icr_tx, imv_tx;
 	u32 icm_misc, icr_misc, imv_misc;
 
 	if (!test_bit(wil_status_irqen, wil->status)) {
 		if (wil->use_enhanced_dma_hw) {
+			icm_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_RX_ICR) +
+					offsetof(struct RGF_ICR, ICM));
+			icr_rx = wil_ioread32_and_clear(wil->csr +
+					HOSTADDR(RGF_INT_GEN_RX_ICR) +
+					offsetof(struct RGF_ICR, ICR));
+			imv_rx = wil_r(wil, RGF_INT_GEN_RX_ICR +
+				   offsetof(struct RGF_ICR, IMV));
 			icm_tx = wil_ioread32_and_clear(wil->csr +
 					HOSTADDR(RGF_INT_GEN_TX_ICR) +
 					offsetof(struct RGF_ICR, ICM));
@@ -691,7 +764,7 @@ static irqreturn_t wil6210_hardirq(int irq, void *cookie)
 	 * voting for wake thread - need at least 1 vote
 	 */
 	if ((pseudo_cause & BIT_DMA_PSEUDO_CAUSE_RX) &&
-	    (wil6210_irq_rx(irq, cookie) == IRQ_WAKE_THREAD))
+	    (wil->txrx_ops.irq_rx(irq, cookie) == IRQ_WAKE_THREAD))
 		rc = IRQ_WAKE_THREAD;
 
 	if ((pseudo_cause & BIT_DMA_PSEUDO_CAUSE_TX) &&
@@ -723,6 +796,8 @@ void wil6210_clear_irq(struct wil6210_priv *wil)
 		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_TX_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
+	wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_RX_ICR) +
+		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_INT_GEN_TX_ICR) +
 		    offsetof(struct RGF_ICR, ICR));
 	wil_clear32(wil->csr + HOSTADDR(RGF_DMA_EP_MISC_ICR) +
@@ -753,10 +828,13 @@ int wil6210_init_irq(struct wil6210_priv *wil, int irq, bool use_msi)
 
 	wil_dbg_misc(wil, "init_irq: %s\n", use_msi ? "MSI" : "INTx");
 
-	if (wil->use_enhanced_dma_hw)
+	if (wil->use_enhanced_dma_hw) {
 		wil->txrx_ops.irq_tx = wil6210_irq_tx_edma;
-	else
+		wil->txrx_ops.irq_rx = wil6210_irq_rx_edma;
+	} else {
 		wil->txrx_ops.irq_tx = wil6210_irq_tx;
+		wil->txrx_ops.irq_rx = wil6210_irq_rx;
+	}
 	rc = request_threaded_irq(irq, wil6210_hardirq,
 				  wil6210_thread_irq,
 				  use_msi ? 0 : IRQF_SHARED,
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index c820c86918f0..e0072b6c7a44 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -632,6 +632,7 @@ int wil_priv_init(struct wil6210_priv *wil)
 	/* edma configuration can be updated via debugfs before allocation */
 	wil->num_rx_status_rings = WIL_DEFAULT_NUM_RX_STATUS_RINGS;
 	wil->use_compressed_rx_status = true;
+	wil->use_rx_hw_reordering = true;
 	wil->tx_status_ring_order = WIL_TX_SRING_SIZE_ORDER_DEFAULT;
 
 	/* Rx status ring size should be bigger than the number of RX buffers
@@ -645,6 +646,8 @@ int wil_priv_init(struct wil6210_priv *wil)
 	 */
 	wil->rx_buff_id_count = WIL_RX_BUFF_ARR_SIZE_DEFAULT;
 
+	wil->amsdu_en = 1;
+
 	return 0;
 
 out_wmi_wq:
diff --git a/drivers/net/wireless/ath/wil6210/netdev.c b/drivers/net/wireless/ath/wil6210/netdev.c
index eeda2b618e6e..7a78a06bd356 100644
--- a/drivers/net/wireless/ath/wil6210/netdev.c
+++ b/drivers/net/wireless/ath/wil6210/netdev.c
@@ -120,6 +120,27 @@ static int wil6210_netdev_poll_rx(struct napi_struct *napi, int budget)
 	return done;
 }
 
+static int wil6210_netdev_poll_rx_edma(struct napi_struct *napi, int budget)
+{
+	struct wil6210_priv *wil = container_of(napi, struct wil6210_priv,
+						napi_rx);
+	int quota = budget;
+	int done;
+
+	wil_rx_handle_edma(wil, &quota);
+	done = budget - quota;
+
+	if (done < budget) {
+		napi_complete_done(napi, done);
+		wil6210_unmask_irq_rx_edma(wil);
+		wil_dbg_txrx(wil, "NAPI RX complete\n");
+	}
+
+	wil_dbg_txrx(wil, "NAPI RX poll(%d) done %d\n", budget, done);
+
+	return done;
+}
+
 static int wil6210_netdev_poll_tx(struct napi_struct *napi, int budget)
 {
 	struct wil6210_priv *wil = container_of(napi, struct wil6210_priv,
@@ -442,17 +463,21 @@ int wil_if_add(struct wil6210_priv *wil)
 	}
 
 	init_dummy_netdev(&wil->napi_ndev);
-	netif_napi_add(&wil->napi_ndev, &wil->napi_rx, wil6210_netdev_poll_rx,
-		       WIL6210_NAPI_BUDGET);
-	if (wil->use_enhanced_dma_hw)
+	if (wil->use_enhanced_dma_hw) {
+		netif_napi_add(&wil->napi_ndev, &wil->napi_rx,
+			       wil6210_netdev_poll_rx_edma,
+			       WIL6210_NAPI_BUDGET);
 		netif_tx_napi_add(&wil->napi_ndev,
 				  &wil->napi_tx, wil6210_netdev_poll_tx_edma,
 				  WIL6210_NAPI_BUDGET);
-	else
+	} else {
+		netif_napi_add(&wil->napi_ndev, &wil->napi_rx,
+			       wil6210_netdev_poll_rx,
+			       WIL6210_NAPI_BUDGET);
 		netif_tx_napi_add(&wil->napi_ndev,
 				  &wil->napi_tx, wil6210_netdev_poll_tx,
 				  WIL6210_NAPI_BUDGET);
-
+	}
 
 	wil_update_net_queues_bh(wil, vif, NULL, true);
 
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index c01c5348b7e0..8b148cb91372 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -103,6 +103,7 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		wil->rgf_ucode_assert_code_addr = TALYN_RGF_UCODE_ASSERT_CODE;
 		set_bit(hw_capa_no_flash, wil->hw_capa);
 		wil->use_enhanced_dma_hw = true;
+		wil->use_rx_hw_reordering = true;
 		break;
 	default:
 		wil_err(wil, "Unknown board hardware, chip_id 0x%08x, chip_revision 0x%08x\n",
diff --git a/drivers/net/wireless/ath/wil6210/pm.c b/drivers/net/wireless/ath/wil6210/pm.c
index ba81fb3ac96f..3a4194779ddf 100644
--- a/drivers/net/wireless/ath/wil6210/pm.c
+++ b/drivers/net/wireless/ath/wil6210/pm.c
@@ -211,7 +211,7 @@ static int wil_suspend_keep_radio_on(struct wil6210_priv *wil)
 		goto reject_suspend;
 	}
 
-	if (!wil_is_rx_idle(wil)) {
+	if (!wil->txrx_ops.is_rx_idle(wil)) {
 		wil_dbg_pm(wil, "Pending RX data, reject suspend\n");
 		wil->suspend_stats.rejected_by_host++;
 		goto reject_suspend;
@@ -235,9 +235,9 @@ static int wil_suspend_keep_radio_on(struct wil6210_priv *wil)
 	start = jiffies;
 	data_comp_to = jiffies + msecs_to_jiffies(WIL_DATA_COMPLETION_TO_MS);
 	if (test_bit(wil_status_napi_en, wil->status)) {
-		while (!wil_is_rx_idle(wil)) {
+		while (!wil->txrx_ops.is_rx_idle(wil)) {
 			if (time_after(jiffies, data_comp_to)) {
-				if (wil_is_rx_idle(wil))
+				if (wil->txrx_ops.is_rx_idle(wil))
 					break;
 				wil_err(wil,
 					"TO waiting for idle RX, suspend failed\n");
diff --git a/drivers/net/wireless/ath/wil6210/rx_reorder.c b/drivers/net/wireless/ath/wil6210/rx_reorder.c
index a586929f72d4..22475a1ddb7f 100644
--- a/drivers/net/wireless/ath/wil6210/rx_reorder.c
+++ b/drivers/net/wireless/ath/wil6210/rx_reorder.c
@@ -95,17 +95,17 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 {
 	struct wil6210_vif *vif;
 	struct net_device *ndev;
-	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
-	int tid = wil_rxdesc_tid(d);
-	int cid = wil_rxdesc_cid(d);
-	int mid = wil_rxdesc_mid(d);
-	u16 seq = wil_rxdesc_seq(d);
-	int mcast = wil_rxdesc_mcast(d);
-	struct wil_sta_info *sta = &wil->sta[cid];
+	int tid, cid, mid, mcast;
+	u16 seq;
+	struct wil_sta_info *sta;
 	struct wil_tid_ampdu_rx *r;
 	u16 hseq;
 	int index;
 
+	wil->txrx_ops.get_reorder_params(wil, skb, &tid, &cid, &mid, &seq,
+					 &mcast);
+	sta = &wil->sta[cid];
+
 	wil_dbg_txrx(wil, "MID %d CID %d TID %d Seq 0x%03x mcast %01x\n",
 		     mid, cid, tid, seq, mcast);
 
@@ -315,7 +315,10 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	 * bits 6..15: buffer size
 	 */
 	u16 req_agg_wsize = WIL_GET_BITS(param_set, 6, 15);
-	bool agg_amsdu = !!(param_set & BIT(0));
+	bool agg_amsdu = wil->use_enhanced_dma_hw &&
+		wil->use_rx_hw_reordering &&
+		test_bit(WMI_FW_CAPABILITY_AMSDU, wil->fw_capabilities) &&
+		wil->amsdu_en && (param_set & BIT(0));
 	int ba_policy = param_set & BIT(1);
 	u16 status = WLAN_STATUS_SUCCESS;
 	u16 ssn = seq_ctrl >> 4;
@@ -360,8 +363,9 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 		}
 	}
 
-	rc = wmi_addba_rx_resp(wil, mid, cid, tid, dialog_token, status,
-			       agg_amsdu, agg_wsize, agg_timeout);
+	rc = wil->txrx_ops.wmi_addba_rx_resp(wil, mid, cid, tid, dialog_token,
+					     status, agg_amsdu, agg_wsize,
+					     agg_timeout);
 	if (rc || (status != WLAN_STATUS_SUCCESS)) {
 		wil_err(wil, "do not apply ba, rc(%d), status(%d)\n", rc,
 			status);
diff --git a/drivers/net/wireless/ath/wil6210/trace.h b/drivers/net/wireless/ath/wil6210/trace.h
index 6aed2461b0d4..853abc3a73e4 100644
--- a/drivers/net/wireless/ath/wil6210/trace.h
+++ b/drivers/net/wireless/ath/wil6210/trace.h
@@ -187,6 +187,40 @@ TRACE_EVENT(wil6210_rx,
 		  __entry->seq, __entry->type, __entry->subtype)
 );
 
+TRACE_EVENT(wil6210_rx_status,
+	    TP_PROTO(struct wil6210_priv *wil, u8 use_compressed, u16 buff_id,
+		     void *msg),
+	    TP_ARGS(wil, use_compressed, buff_id, msg),
+	    TP_STRUCT__entry(__field(u8, use_compressed)
+			     __field(u16, buff_id)
+			     __field(unsigned int, len)
+			     __field(u8, mid)
+			     __field(u8, cid)
+			     __field(u8, tid)
+			     __field(u8, type)
+			     __field(u8, subtype)
+			     __field(u16, seq)
+			     __field(u8, mcs)
+	    ),
+	    TP_fast_assign(__entry->use_compressed = use_compressed;
+			   __entry->buff_id = buff_id;
+			   __entry->len = wil_rx_status_get_length(msg);
+			   __entry->mid = wil_rx_status_get_mid(msg);
+			   __entry->cid = wil_rx_status_get_cid(msg);
+			   __entry->tid = wil_rx_status_get_tid(msg);
+			   __entry->type = wil_rx_status_get_frame_type(wil,
+									msg);
+			   __entry->subtype = wil_rx_status_get_fc1(wil, msg);
+			   __entry->seq = wil_rx_status_get_seq(wil, msg);
+			   __entry->mcs = wil_rx_status_get_mcs(msg);
+	    ),
+	    TP_printk(
+		      "compressed %d buff_id %d len %d mid %d cid %d tid %d mcs %d seq 0x%03x type 0x%1x subtype 0x%1x",
+		      __entry->use_compressed, __entry->buff_id, __entry->len,
+		      __entry->mid, __entry->cid, __entry->tid, __entry->mcs,
+		      __entry->seq, __entry->type, __entry->subtype)
+);
+
 TRACE_EVENT(wil6210_tx,
 	TP_PROTO(u8 vring, u16 index, unsigned int len, u8 frags),
 	TP_ARGS(vring, index, len, frags),
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 12d509e7f29c..2098f3cc1cec 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -28,6 +28,7 @@
 #include "wmi.h"
 #include "txrx.h"
 #include "trace.h"
+#include "txrx_edma.h"
 
 static bool rtap_include_phy_info;
 module_param(rtap_include_phy_info, bool, 0444);
@@ -407,14 +408,7 @@ static void wil_rx_add_radiotap_header(struct wil6210_priv *wil,
 	}
 }
 
-/* similar to ieee80211_ version, but FC contain only 1-st byte */
-static inline int wil_is_back_req(u8 fc)
-{
-	return (fc & (IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
-	       (IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ);
-}
-
-bool wil_is_rx_idle(struct wil6210_priv *wil)
+static bool wil_is_rx_idle(struct wil6210_priv *wil)
 {
 	struct vring_rx_desc *_d;
 	struct wil_ring *ring = &wil->ring_rx;
@@ -639,7 +633,7 @@ static int wil_rx_refill(struct wil6210_priv *wil, int count)
  * Cut'n'paste from original memcmp (see lib/string.c)
  * with minimal modifications
  */
-static int reverse_memcmp(const void *cs, const void *ct, size_t count)
+int reverse_memcmp(const void *cs, const void *ct, size_t count)
 {
 	const unsigned char *su1, *su2;
 	int res = 0;
@@ -684,6 +678,15 @@ static int wil_rx_crypto_check(struct wil6210_priv *wil, struct sk_buff *skb)
 	return 0;
 }
 
+static void wil_get_netif_rx_params(struct sk_buff *skb, int *cid,
+				    int *security)
+{
+	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
+
+	*cid = wil_rxdesc_cid(d); /* always 0..7, no need to check */
+	*security = wil_rxdesc_security(d);
+}
+
 /*
  * Pass Rx packet to the netif. Update statistics.
  * Called in softirq context (NAPI poll).
@@ -695,15 +698,14 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 	struct wil6210_priv *wil = ndev_to_wil(ndev);
 	struct wireless_dev *wdev = vif_to_wdev(vif);
 	unsigned int len = skb->len;
-	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
-	int cid = wil_rxdesc_cid(d); /* always 0..7, no need to check */
-	int security = wil_rxdesc_security(d);
+	int cid;
+	int security;
 	struct ethhdr *eth = (void *)skb->data;
 	/* here looking for DA, not A1, thus Rxdesc's 'mcast' indication
 	 * is not suitable, need to look at data
 	 */
 	int mcast = is_multicast_ether_addr(eth->h_dest);
-	struct wil_net_stats *stats = &wil->sta[cid].stats;
+	struct wil_net_stats *stats;
 	struct sk_buff *xmit_skb = NULL;
 	static const char * const gro_res_str[] = {
 		[GRO_MERGED]		= "GRO_MERGED",
@@ -713,6 +715,10 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 		[GRO_DROP]		= "GRO_DROP",
 	};
 
+	wil->txrx_ops.get_netif_rx_params(skb, &cid, &security);
+
+	stats = &wil->sta[cid].stats;
+
 	if (ndev->features & NETIF_F_RXHASH)
 		/* fake L4 to ensure it won't be re-calculated later
 		 * set hash to any non-zero value to activate rps
@@ -723,7 +729,7 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 
 	skb_orphan(skb);
 
-	if (security && (wil_rx_crypto_check(wil, skb) != 0)) {
+	if (security && (wil->txrx_ops.rx_crypto_check(wil, skb) != 0)) {
 		rc = GRO_DROP;
 		dev_kfree_skb(skb);
 		stats->rx_replay++;
@@ -2172,6 +2178,19 @@ static inline int wil_tx_init(struct wil6210_priv *wil)
 
 static inline void wil_tx_fini(struct wil6210_priv *wil) {}
 
+static void wil_get_reorder_params(struct wil6210_priv *wil,
+				   struct sk_buff *skb, int *tid, int *cid,
+				   int *mid, u16 *seq, int *mcast)
+{
+	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
+
+	*tid = wil_rxdesc_tid(d);
+	*cid = wil_rxdesc_cid(d);
+	*mid = wil_rxdesc_mid(d);
+	*seq = wil_rxdesc_seq(d);
+	*mcast = wil_rxdesc_mcast(d);
+}
+
 void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil)
 {
 	wil->txrx_ops.configure_interrupt_moderation =
@@ -2187,5 +2206,11 @@ void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil)
 	wil->txrx_ops.tx_fini = wil_tx_fini;
 	/* RX ops */
 	wil->txrx_ops.rx_init = wil_rx_init;
+	wil->txrx_ops.wmi_addba_rx_resp = wmi_addba_rx_resp;
+	wil->txrx_ops.get_reorder_params = wil_get_reorder_params;
+	wil->txrx_ops.get_netif_rx_params =
+		wil_get_netif_rx_params;
+	wil->txrx_ops.rx_crypto_check = wil_rx_crypto_check;
+	wil->txrx_ops.is_rx_idle = wil_is_rx_idle;
 	wil->txrx_ops.rx_fini = wil_rx_fini;
 }
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 62806c5bb930..f361423628f5 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -592,6 +592,13 @@ static inline int wil_get_min_tx_ring_id(struct wil6210_priv *wil)
 	return wil->use_enhanced_dma_hw ? 1 : 0;
 }
 
+/* similar to ieee80211_ version, but FC contain only 1-st byte */
+static inline int wil_is_back_req(u8 fc)
+{
+	return (fc & (IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
+	       (IEEE80211_FTYPE_CTL | IEEE80211_STYPE_BACK_REQ);
+}
+
 /* wil_val_in_range - check if value in [min,max) */
 static inline bool wil_val_in_range(int val, int min, int max)
 {
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index c449286823a9..95f38e65d969 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -208,6 +208,13 @@ static int wil_ring_alloc_skb_edma(struct wil6210_priv *wil,
 	return 0;
 }
 
+static inline
+void wil_get_next_rx_status_msg(struct wil_status_ring *sring, void *msg)
+{
+	memcpy(msg, (void *)(sring->va + (sring->elem_size * sring->swhead)),
+	       sring->elem_size);
+}
+
 static inline void wil_sring_advance_swhead(struct wil_status_ring *sring)
 {
 	sring->swhead = (sring->swhead + 1) % sring->size;
@@ -493,6 +500,96 @@ out_free:
 	return rc;
 }
 
+static void wil_get_reorder_params_edma(struct wil6210_priv *wil,
+					struct sk_buff *skb, int *tid,
+					int *cid, int *mid, u16 *seq,
+					int *mcast)
+{
+	struct wil_rx_status_extended *s = wil_skb_rxstatus(skb);
+
+	*tid = wil_rx_status_get_tid(s);
+	*cid = wil_rx_status_get_cid(s);
+	*mid = wil_rx_status_get_mid(s);
+	*seq = le16_to_cpu(wil_rx_status_get_seq(wil, s));
+	*mcast = wil_rx_status_get_mcast(s);
+}
+
+static void wil_get_netif_rx_params_edma(struct sk_buff *skb, int *cid,
+					 int *security)
+{
+	struct wil_rx_status_extended *s = wil_skb_rxstatus(skb);
+
+	*cid = wil_rx_status_get_cid(s);
+	*security = wil_rx_status_get_security(s);
+}
+
+static int wil_rx_crypto_check_edma(struct wil6210_priv *wil,
+				    struct sk_buff *skb)
+{
+	struct wil_rx_status_extended *st;
+	int cid, tid, key_id, mc;
+	struct wil_sta_info *s;
+	struct wil_tid_crypto_rx *c;
+	struct wil_tid_crypto_rx_single *cc;
+	const u8 *pn;
+
+	/* In HW reorder, HW is responsible for crypto check */
+	if (wil->use_rx_hw_reordering)
+		return 0;
+
+	st = wil_skb_rxstatus(skb);
+
+	cid = wil_rx_status_get_cid(st);
+	tid = wil_rx_status_get_tid(st);
+	key_id = wil_rx_status_get_key_id(st);
+	mc = wil_rx_status_get_mcast(st);
+	s = &wil->sta[cid];
+	c = mc ? &s->group_crypto_rx : &s->tid_crypto_rx[tid];
+	cc = &c->key_id[key_id];
+	pn = (u8 *)&st->ext.pn_15_0;
+
+	if (!cc->key_set) {
+		wil_err_ratelimited(wil,
+				    "Key missing. CID %d TID %d MCast %d KEY_ID %d\n",
+				    cid, tid, mc, key_id);
+		return -EINVAL;
+	}
+
+	if (reverse_memcmp(pn, cc->pn, IEEE80211_GCMP_PN_LEN) <= 0) {
+		wil_err_ratelimited(wil,
+				    "Replay attack. CID %d TID %d MCast %d KEY_ID %d PN %6phN last %6phN\n",
+				    cid, tid, mc, key_id, pn, cc->pn);
+		return -EINVAL;
+	}
+	memcpy(cc->pn, pn, IEEE80211_GCMP_PN_LEN);
+
+	return 0;
+}
+
+static bool wil_is_rx_idle_edma(struct wil6210_priv *wil)
+{
+	struct wil_status_ring *sring;
+	struct wil_rx_status_extended msg1;
+	void *msg = &msg1;
+	u8 dr_bit;
+	int i;
+
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		sring = &wil->srings[i];
+		if (!sring->va)
+			continue;
+
+		wil_get_next_rx_status_msg(sring, msg);
+		dr_bit = wil_rx_status_get_desc_rdy_bit(msg);
+
+		/* Check if there are unhandled RX status messages */
+		if (dr_bit == sring->desc_rdy_pol)
+			return false;
+	}
+
+	return true;
+}
+
 static void wil_rx_buf_len_init_edma(struct wil6210_priv *wil)
 {
 	wil->rx_buf_len = rx_large_buf ?
@@ -510,6 +607,13 @@ static int wil_rx_init_edma(struct wil6210_priv *wil, u16 desc_ring_size)
 	int i;
 	u16 max_rx_pl_per_desc;
 
+	/* In SW reorder one must use extended status messages */
+	if (wil->use_compressed_rx_status && !wil->use_rx_hw_reordering) {
+		wil_err(wil,
+			"compressed RX status cannot be used with SW reorder\n");
+		return -EINVAL;
+	}
+
 	if (wil->rx_status_ring_order < WIL_SRING_SIZE_ORDER_MIN ||
 	    wil->rx_status_ring_order > WIL_SRING_SIZE_ORDER_MAX)
 		wil->rx_status_ring_order = WIL_RX_SRING_SIZE_ORDER_DEFAULT;
@@ -634,6 +738,353 @@ static int wil_ring_init_tx_edma(struct wil6210_vif *vif, int ring_id,
 	return rc;
 }
 
+/* This function is used only for RX SW reorder */
+static int wil_check_bar(struct wil6210_priv *wil, void *msg, int cid,
+			 struct sk_buff *skb, struct wil_net_stats *stats)
+{
+	u8 ftype;
+	u8 fc1;
+	int mid;
+	int tid;
+	u16 seq;
+	struct wil6210_vif *vif;
+
+	ftype = wil_rx_status_get_frame_type(wil, msg);
+	if (ftype == IEEE80211_FTYPE_DATA)
+		return 0;
+
+	fc1 = wil_rx_status_get_fc1(wil, msg);
+	mid = wil_rx_status_get_mid(msg);
+	tid = wil_rx_status_get_tid(msg);
+	seq = le16_to_cpu(wil_rx_status_get_seq(wil, msg));
+	vif = wil->vifs[mid];
+
+	if (unlikely(!vif)) {
+		wil_dbg_txrx(wil, "RX descriptor with invalid mid %d", mid);
+		return -EAGAIN;
+	}
+
+	wil_dbg_txrx(wil,
+		     "Non-data frame FC[7:0] 0x%02x MID %d CID %d TID %d Seq 0x%03x\n",
+		     fc1, mid, cid, tid, seq);
+	if (stats)
+		stats->rx_non_data_frame++;
+	if (wil_is_back_req(fc1)) {
+		wil_dbg_txrx(wil,
+			     "BAR: MID %d CID %d TID %d Seq 0x%03x\n",
+			     mid, cid, tid, seq);
+		wil_rx_bar(wil, vif, cid, tid, seq);
+	} else {
+		u32 sz = wil->use_compressed_rx_status ?
+			sizeof(struct wil_rx_status_compressed) :
+			sizeof(struct wil_rx_status_extended);
+
+		/* print again all info. One can enable only this
+		 * without overhead for printing every Rx frame
+		 */
+		wil_dbg_txrx(wil,
+			     "Unhandled non-data frame FC[7:0] 0x%02x MID %d CID %d TID %d Seq 0x%03x\n",
+			     fc1, mid, cid, tid, seq);
+		wil_hex_dump_txrx("RxS ", DUMP_PREFIX_NONE, 32, 4,
+				  (const void *)msg, sz, false);
+		wil_hex_dump_txrx("Rx ", DUMP_PREFIX_OFFSET, 16, 1,
+				  skb->data, skb_headlen(skb), false);
+	}
+
+	return -EAGAIN;
+}
+
+static int wil_rx_edma_check_errors(struct wil6210_priv *wil, void *msg,
+				    struct wil_net_stats *stats,
+				    struct sk_buff *skb)
+{
+	int error;
+	int l2_rx_status;
+	int l3_rx_status;
+	int l4_rx_status;
+
+	error = wil_rx_status_get_error(msg);
+	if (!error) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		return 0;
+	}
+
+	l2_rx_status = wil_rx_status_get_l2_rx_status(msg);
+	if (l2_rx_status != 0) {
+		wil_dbg_txrx(wil, "L2 RX error, l2_rx_status=0x%x\n",
+			     l2_rx_status);
+		/* Due to HW issue, KEY error will trigger a MIC error */
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_MIC) {
+			wil_dbg_txrx(wil,
+				     "L2 MIC/KEY error, dropping packet\n");
+			stats->rx_mic_error++;
+		}
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_KEY) {
+			wil_dbg_txrx(wil, "L2 KEY error, dropping packet\n");
+			stats->rx_key_error++;
+		}
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_REPLAY) {
+			wil_dbg_txrx(wil,
+				     "L2 REPLAY error, dropping packet\n");
+			stats->rx_replay++;
+		}
+		if (l2_rx_status & WIL_RX_EDMA_ERROR_AMSDU) {
+			wil_dbg_txrx(wil,
+				     "L2 AMSDU error, dropping packet\n");
+			stats->rx_amsdu_error++;
+		}
+		return -EFAULT;
+	}
+
+	l3_rx_status = wil_rx_status_get_l3_rx_status(msg);
+	l4_rx_status = wil_rx_status_get_l4_rx_status(msg);
+	if (!l3_rx_status && !l4_rx_status)
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	/* If HW reports bad checksum, let IP stack re-check it
+	 * For example, HW don't understand Microsoft IP stack that
+	 * mis-calculates TCP checksum - if it should be 0x0,
+	 * it writes 0xffff in violation of RFC 1624
+	 */
+
+	return 0;
+}
+
+static struct sk_buff *wil_sring_reap_rx_edma(struct wil6210_priv *wil,
+					      struct wil_status_ring *sring)
+{
+	struct device *dev = wil_to_dev(wil);
+	struct wil_rx_status_extended msg1;
+	void *msg = &msg1;
+	u16 buff_id;
+	struct sk_buff *skb;
+	dma_addr_t pa;
+	struct wil_ring_rx_data *rxdata = &sring->rx_data;
+	unsigned int sz = wil->rx_buf_len + ETH_HLEN +
+		WIL_EDMA_MAX_DATA_OFFSET;
+	struct wil_net_stats *stats = NULL;
+	u16 dmalen;
+	int cid;
+	int rc;
+	bool eop, headstolen;
+	int delta;
+	u8 dr_bit;
+	u8 data_offset;
+	struct wil_rx_status_extended *s;
+	u16 sring_idx = sring - wil->srings;
+
+	BUILD_BUG_ON(sizeof(struct wil_rx_status_extended) > sizeof(skb->cb));
+
+again:
+	wil_get_next_rx_status_msg(sring, msg);
+	dr_bit = wil_rx_status_get_desc_rdy_bit(msg);
+
+	/* Completed handling all the ready status messages */
+	if (dr_bit != sring->desc_rdy_pol)
+		return NULL;
+
+	/* Extract the buffer ID from the status message */
+	buff_id = le16_to_cpu(wil_rx_status_get_buff_id(msg));
+	if (unlikely(!wil_val_in_range(buff_id, 0, wil->rx_buff_mgmt.size))) {
+		wil_err(wil, "Corrupt buff_id=%d, sring->swhead=%d\n",
+			buff_id, sring->swhead);
+		wil_sring_advance_swhead(sring);
+		goto again;
+	}
+
+	wil_sring_advance_swhead(sring);
+
+	/* Extract the SKB from the rx_buff management array */
+	skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
+	wil->rx_buff_mgmt.buff_arr[buff_id].skb = NULL;
+	if (!skb) {
+		wil_err(wil, "No Rx skb at buff_id %d\n", buff_id);
+		goto again;
+	}
+
+	memcpy(&pa, skb->cb, sizeof(pa));
+	dma_unmap_single(dev, pa, sz, DMA_FROM_DEVICE);
+	dmalen = le16_to_cpu(wil_rx_status_get_length(msg));
+
+	trace_wil6210_rx_status(wil, wil->use_compressed_rx_status, buff_id,
+				msg);
+	wil_dbg_txrx(wil, "Rx, buff_id=%u, sring_idx=%u, dmalen=%u bytes\n",
+		     buff_id, sring_idx, dmalen);
+	wil_hex_dump_txrx("RxS ", DUMP_PREFIX_NONE, 32, 4,
+			  (const void *)msg, wil->use_compressed_rx_status ?
+			  sizeof(struct wil_rx_status_compressed) :
+			  sizeof(struct wil_rx_status_extended), false);
+
+	/* Move the buffer from the active list to the free list */
+	list_move(&wil->rx_buff_mgmt.buff_arr[buff_id].list,
+		  &wil->rx_buff_mgmt.free);
+
+	eop = wil_rx_status_get_eop(msg);
+
+	cid = wil_rx_status_get_cid(msg);
+	if (unlikely(!wil_val_in_range(cid, 0, WIL6210_MAX_CID))) {
+		wil_err(wil, "Corrupt cid=%d, sring->swhead=%d\n",
+			cid, sring->swhead);
+		rxdata->skipping = true;
+		goto skipping;
+	}
+	stats = &wil->sta[cid].stats;
+
+	if (unlikely(skb->len < ETH_HLEN)) {
+		wil_dbg_txrx(wil, "Short frame, len = %d\n", skb->len);
+		stats->rx_short_frame++;
+		rxdata->skipping = true;
+		goto skipping;
+	}
+
+	/* Check and treat errors reported by HW */
+	rc = wil_rx_edma_check_errors(wil, msg, stats, skb);
+	if (rc) {
+		rxdata->skipping = true;
+		goto skipping;
+	}
+
+	if (unlikely(dmalen > sz)) {
+		wil_err(wil, "Rx size too large: %d bytes!\n", dmalen);
+		stats->rx_large_frame++;
+		rxdata->skipping = true;
+	}
+
+skipping:
+	/* skipping indicates if a certain SKB should be dropped.
+	 * It is set in case there is an error on the current SKB or in case
+	 * of RX chaining: as long as we manage to merge the SKBs it will
+	 * be false. once we have a bad SKB or we don't manage to merge SKBs
+	 * it will be set to the !EOP value of the current SKB.
+	 * This guarantees that all the following SKBs until EOP will also
+	 * get dropped.
+	 */
+	if (unlikely(rxdata->skipping)) {
+		kfree_skb(skb);
+		if (rxdata->skb) {
+			kfree_skb(rxdata->skb);
+			rxdata->skb = NULL;
+		}
+		rxdata->skipping = !eop;
+		goto again;
+	}
+
+	skb_trim(skb, dmalen);
+
+	prefetch(skb->data);
+
+	if (!rxdata->skb) {
+		rxdata->skb = skb;
+	} else {
+		if (likely(skb_try_coalesce(rxdata->skb, skb, &headstolen,
+					    &delta))) {
+			kfree_skb_partial(skb, headstolen);
+		} else {
+			wil_err(wil, "failed to merge skbs!\n");
+			kfree_skb(skb);
+			kfree_skb(rxdata->skb);
+			rxdata->skb = NULL;
+			rxdata->skipping = !eop;
+			goto again;
+		}
+	}
+
+	if (!eop)
+		goto again;
+
+	/* reaching here rxdata->skb always contains a full packet */
+	skb = rxdata->skb;
+	rxdata->skb = NULL;
+	rxdata->skipping = false;
+
+	if (stats) {
+		stats->last_mcs_rx = wil_rx_status_get_mcs(msg);
+		if (stats->last_mcs_rx < ARRAY_SIZE(stats->rx_per_mcs))
+			stats->rx_per_mcs[stats->last_mcs_rx]++;
+	}
+
+	if (!wil->use_rx_hw_reordering && !wil->use_compressed_rx_status &&
+	    wil_check_bar(wil, msg, cid, skb, stats) == -EAGAIN) {
+		kfree_skb(skb);
+		goto again;
+	}
+
+	/* Compensate for the HW data alignment according to the status
+	 * message
+	 */
+	data_offset = wil_rx_status_get_data_offset(msg);
+	if (data_offset == 0xFF ||
+	    data_offset > WIL_EDMA_MAX_DATA_OFFSET) {
+		wil_err(wil, "Unexpected data offset %d\n", data_offset);
+		kfree_skb(skb);
+		goto again;
+	}
+
+	skb_pull(skb, data_offset);
+
+	wil_hex_dump_txrx("Rx ", DUMP_PREFIX_OFFSET, 16, 1,
+			  skb->data, skb_headlen(skb), false);
+
+	/* Has to be done after dma_unmap_single as skb->cb is also
+	 * used for holding the pa
+	 */
+	s = wil_skb_rxstatus(skb);
+	memcpy(s, msg, sring->elem_size);
+
+	return skb;
+}
+
+void wil_rx_handle_edma(struct wil6210_priv *wil, int *quota)
+{
+	struct net_device *ndev;
+	struct wil_ring *ring = &wil->ring_rx;
+	struct wil_status_ring *sring;
+	struct sk_buff *skb;
+	int i;
+
+	if (unlikely(!ring->va)) {
+		wil_err(wil, "Rx IRQ while Rx not yet initialized\n");
+		return;
+	}
+	wil_dbg_txrx(wil, "rx_handle\n");
+
+	for (i = 0; i < wil->num_rx_status_rings; i++) {
+		sring = &wil->srings[i];
+		if (unlikely(!sring->va)) {
+			wil_err(wil,
+				"Rx IRQ while Rx status ring %d not yet initialized\n",
+				i);
+			continue;
+		}
+
+		while ((*quota > 0) &&
+		       (NULL != (skb =
+			wil_sring_reap_rx_edma(wil, sring)))) {
+			(*quota)--;
+			if (wil->use_rx_hw_reordering) {
+				void *msg = wil_skb_rxstatus(skb);
+				int mid = wil_rx_status_get_mid(msg);
+				struct wil6210_vif *vif = wil->vifs[mid];
+
+				if (unlikely(!vif)) {
+					wil_dbg_txrx(wil,
+						     "RX desc invalid mid %d",
+						     mid);
+					kfree_skb(skb);
+					continue;
+				}
+				ndev = vif_to_ndev(vif);
+				wil_netif_rx_any(skb, ndev);
+			} else {
+				wil_rx_reorder(wil, skb);
+			}
+		}
+
+		wil_w(wil, sring->hwtail, (sring->swhead - 1) % sring->size);
+	}
+
+	wil_rx_refill_edma(wil);
+}
+
 static int wil_tx_desc_map_edma(union wil_tx_desc *desc,
 				dma_addr_t pa,
 				u32 len,
@@ -1137,6 +1588,11 @@ void wil_init_txrx_ops_edma(struct wil6210_priv *wil)
 	wil->txrx_ops.tx_ring_tso = __wil_tx_ring_tso_edma;
 	/* RX ops */
 	wil->txrx_ops.rx_init = wil_rx_init_edma;
+	wil->txrx_ops.wmi_addba_rx_resp = wmi_addba_rx_resp_edma;
+	wil->txrx_ops.get_reorder_params = wil_get_reorder_params_edma;
+	wil->txrx_ops.get_netif_rx_params = wil_get_netif_rx_params_edma;
+	wil->txrx_ops.rx_crypto_check = wil_rx_crypto_check_edma;
+	wil->txrx_ops.is_rx_idle = wil_is_rx_idle_edma;
 	wil->txrx_ops.rx_fini = wil_rx_fini_edma;
 }
 
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
index 8eae181877b9..e86fc2dc0ce0 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.h
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -38,6 +38,27 @@
 #define WIL_EDMA_IDLE_TIME_LIMIT_USEC (50)
 #define WIL_EDMA_TIME_UNIT_CLK_CYCLES (330) /* fits 1 usec */
 
+/* Error field */
+#define WIL_RX_EDMA_ERROR_MIC	(1)
+#define WIL_RX_EDMA_ERROR_KEY	(2) /* Key missing */
+#define WIL_RX_EDMA_ERROR_REPLAY	(3)
+#define WIL_RX_EDMA_ERROR_AMSDU	(4)
+#define WIL_RX_EDMA_ERROR_FCS	(7)
+
+#define WIL_RX_EDMA_ERROR_L3_ERR	(BIT(0) | BIT(1))
+#define WIL_RX_EDMA_ERROR_L4_ERR	(BIT(0) | BIT(1))
+
+#define WIL_RX_EDMA_DLPF_LU_MISS_BIT		BIT(11)
+#define WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK	0x7
+#define WIL_RX_EDMA_DLPF_LU_HIT_CID_TID_MASK	0xf
+
+#define WIL_RX_EDMA_DLPF_LU_MISS_CID_POS	2
+#define WIL_RX_EDMA_DLPF_LU_HIT_CID_POS		4
+
+#define WIL_RX_EDMA_DLPF_LU_MISS_TID_POS	5
+
+#define WIL_RX_EDMA_MID_VALID_BIT		BIT(22)
+
 #define WIL_EDMA_DESC_TX_MAC_CFG_0_QID_POS 16
 #define WIL_EDMA_DESC_TX_MAC_CFG_0_QID_LEN 6
 
@@ -329,6 +350,173 @@ struct wil_rx_status_extended {
 	struct wil_rx_status_extension ext;
 } __packed;
 
+static inline void *wil_skb_rxstatus(struct sk_buff *skb)
+{
+	return (void *)skb->cb;
+}
+
+static inline __le16 wil_rx_status_get_length(void *msg)
+{
+	return ((struct wil_rx_status_compressed *)msg)->length;
+}
+
+static inline u8 wil_rx_status_get_mcs(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d1,
+			    16, 21);
+}
+
+static inline u16 wil_rx_status_get_flow_id(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    8, 19);
+}
+
+static inline u8 wil_rx_status_get_mcast(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    26, 26);
+}
+
+/**
+ * In case of DLPF miss the parsing of flow Id should be as follows:
+ * dest_id:2
+ * src_id :3 - cid
+ * tid:3
+ * Otherwise:
+ * tid:4
+ * cid:4
+ */
+
+static inline u8 wil_rx_status_get_cid(void *msg)
+{
+	u16 val = wil_rx_status_get_flow_id(msg);
+
+	if (val & WIL_RX_EDMA_DLPF_LU_MISS_BIT)
+		/* CID is in bits 2..4 */
+		return (val >> WIL_RX_EDMA_DLPF_LU_MISS_CID_POS) &
+			WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK;
+	else
+		/* CID is in bits 4..7 */
+		return (val >> WIL_RX_EDMA_DLPF_LU_HIT_CID_POS) &
+			WIL_RX_EDMA_DLPF_LU_HIT_CID_TID_MASK;
+}
+
+static inline u8 wil_rx_status_get_tid(void *msg)
+{
+	u16 val = wil_rx_status_get_flow_id(msg);
+
+	if (val & WIL_RX_EDMA_DLPF_LU_MISS_BIT)
+		/* TID is in bits 5..7 */
+		return (val >> WIL_RX_EDMA_DLPF_LU_MISS_TID_POS) &
+			WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK;
+	else
+		/* TID is in bits 0..3 */
+		return val & WIL_RX_EDMA_DLPF_LU_MISS_CID_TID_MASK;
+}
+
+static inline int wil_rx_status_get_desc_rdy_bit(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    31, 31);
+}
+
+static inline int wil_rx_status_get_eop(void *msg) /* EoP = End of Packet */
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    30, 30);
+}
+
+static inline __le16 wil_rx_status_get_buff_id(void *msg)
+{
+	return ((struct wil_rx_status_compressed *)msg)->buff_id;
+}
+
+static inline u8 wil_rx_status_get_data_offset(void *msg)
+{
+	u8 val = WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d1,
+			      24, 27);
+
+	switch (val) {
+	case 0: return 0;
+	case 3: return 2;
+	default: return 0xFF;
+	}
+}
+
+static inline int wil_rx_status_get_frame_type(struct wil6210_priv *wil,
+					       void *msg)
+{
+	if (wil->use_compressed_rx_status)
+		return IEEE80211_FTYPE_DATA;
+
+	return WIL_GET_BITS(((struct wil_rx_status_extended *)msg)->ext.d1,
+			    0, 1) << 2;
+}
+
+static inline int wil_rx_status_get_fc1(struct wil6210_priv *wil, void *msg)
+{
+	if (wil->use_compressed_rx_status)
+		return 0;
+
+	return WIL_GET_BITS(((struct wil_rx_status_extended *)msg)->ext.d1,
+			    0, 5) << 2;
+}
+
+static inline __le16 wil_rx_status_get_seq(struct wil6210_priv *wil, void *msg)
+{
+	if (wil->use_compressed_rx_status)
+		return 0;
+
+	return ((struct wil_rx_status_extended *)msg)->ext.seq_num;
+}
+
+static inline int wil_rx_status_get_mid(void *msg)
+{
+	if (!(((struct wil_rx_status_compressed *)msg)->d0 &
+	    WIL_RX_EDMA_MID_VALID_BIT))
+		return 0; /* use the default MID */
+
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    20, 21);
+}
+
+static inline int wil_rx_status_get_error(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    29, 29);
+}
+
+static inline int wil_rx_status_get_l2_rx_status(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    0, 2);
+}
+
+static inline int wil_rx_status_get_l3_rx_status(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    3, 4);
+}
+
+static inline int wil_rx_status_get_l4_rx_status(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    5, 6);
+}
+
+static inline int wil_rx_status_get_security(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d0,
+			    28, 28);
+}
+
+static inline u8 wil_rx_status_get_key_id(void *msg)
+{
+	return WIL_GET_BITS(((struct wil_rx_status_compressed *)msg)->d1,
+			    31, 31);
+}
+
 static inline u8 wil_tx_status_get_mcs(struct wil_ring_tx_status *msg)
 {
 	return WIL_GET_BITS(msg->d2, 0, 4);
@@ -367,6 +555,7 @@ dma_addr_t wil_rx_desc_get_addr_edma(struct wil_ring_rx_enhanced_dma *dma)
 void wil_configure_interrupt_moderation_edma(struct wil6210_priv *wil);
 int wil_tx_sring_handler(struct wil6210_priv *wil,
 			 struct wil_status_ring *sring);
+void wil_rx_handle_edma(struct wil6210_priv *wil, int *quota);
 void wil_init_txrx_ops_edma(struct wil6210_priv *wil);
 
 #endif /* WIL6210_TXRX_EDMA_H */
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index f35c64e1ca22..f8d4a2d88d91 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -323,9 +323,13 @@ struct RGF_ICR {
 	#define BIT_CONTROL_0			BIT(0)
 
 /* eDMA status interrupts */
+#define RGF_INT_GEN_RX_ICR		(0x8bc0f4)
+	#define BIT_RX_STATUS_IRQ BIT(WIL_RX_STATUS_IRQ_IDX)
 #define RGF_INT_GEN_TX_ICR		(0x8bc110)
 	#define BIT_TX_STATUS_IRQ BIT(WIL_TX_STATUS_IRQ_IDX)
+#define RGF_INT_CTRL_RX_INT_MASK	(0x8bc12c)
 #define RGF_INT_CTRL_TX_INT_MASK	(0x8bc130)
+
 #define RGF_INT_GEN_IDLE_TIME_LIMIT	(0x8bc134)
 
 #define USER_EXT_USER_PMU_3		(0x88d00c)
@@ -557,6 +561,17 @@ struct wil_txrx_ops {
 	/* RX ops */
 	int (*rx_init)(struct wil6210_priv *wil, u16 ring_size);
 	void (*rx_fini)(struct wil6210_priv *wil);
+	int (*wmi_addba_rx_resp)(struct wil6210_priv *wil, u8 mid, u8 cid,
+				 u8 tid, u8 token, u16 status, bool amsdu,
+				 u16 agg_wsize, u16 timeout);
+	void (*get_reorder_params)(struct wil6210_priv *wil,
+				   struct sk_buff *skb, int *tid, int *cid,
+				   int *mid, u16 *seq, int *mcast);
+	void (*get_netif_rx_params)(struct sk_buff *skb,
+				    int *cid, int *security);
+	int (*rx_crypto_check)(struct wil6210_priv *wil, struct sk_buff *skb);
+	bool (*is_rx_idle)(struct wil6210_priv *wil);
+	irqreturn_t (*irq_rx)(int irq, void *cookie);
 };
 
 /**
@@ -952,6 +967,8 @@ struct wil6210_priv {
 	u32 rx_status_ring_order;
 	u32 tx_status_ring_order;
 	u32 rx_buff_id_count;
+	bool amsdu_en;
+	bool use_rx_hw_reordering;
 };
 
 #define wil_to_wiphy(i) (i->wiphy)
@@ -1245,6 +1262,7 @@ void wil6210_unmask_irq_tx_edma(struct wil6210_priv *wil);
 /* RX API */
 void wil_rx_handle(struct wil6210_priv *wil, int *quota);
 void wil6210_unmask_irq_rx(struct wil6210_priv *wil);
+void wil6210_unmask_irq_rx_edma(struct wil6210_priv *wil);
 
 int wil_iftype_nl2wmi(enum nl80211_iftype type);
 
@@ -1265,7 +1283,6 @@ bool wil_is_wmi_idle(struct wil6210_priv *wil);
 int wmi_resume(struct wil6210_priv *wil);
 int wmi_suspend(struct wil6210_priv *wil);
 bool wil_is_tx_idle(struct wil6210_priv *wil);
-bool wil_is_rx_idle(struct wil6210_priv *wil);
 
 int wil_fw_copy_crash_dump(struct wil6210_priv *wil, void *dest, u32 size);
 void wil_fw_core_dump(struct wil6210_priv *wil);
@@ -1280,6 +1297,8 @@ int wmi_start_sched_scan(struct wil6210_priv *wil,
 int wmi_stop_sched_scan(struct wil6210_priv *wil);
 int wmi_mgmt_tx(struct wil6210_vif *vif, const u8 *buf, size_t len);
 
+int reverse_memcmp(const void *cs, const void *ct, size_t count);
+
 /* WMI for enhanced DMA */
 int wil_wmi_tx_sring_cfg(struct wil6210_priv *wil, int ring_id);
 int wil_wmi_cfg_def_rx_offload(struct wil6210_priv *wil,
@@ -1289,5 +1308,8 @@ int wil_wmi_rx_desc_ring_add(struct wil6210_priv *wil, int status_ring_id);
 int wil_wmi_tx_desc_ring_add(struct wil6210_vif *vif, int ring_id, int cid,
 			     int tid);
 int wil_wmi_bcast_desc_ring_add(struct wil6210_vif *vif, int ring_id);
+int wmi_addba_rx_resp_edma(struct wil6210_priv *wil, u8 mid, u8 cid,
+			   u8 tid, u8 token, u16 status, bool amsdu,
+			   u16 agg_wsize, u16 timeout);
 
 #endif /* __WIL6210_H__ */
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index b2e966df57f5..0370b7e8dbb1 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -428,6 +428,8 @@ static const char *cmdid2name(u16 cmdid)
 		return "WMI_RCP_DELBA_CMD";
 	case WMI_RCP_ADDBA_RESP_CMDID:
 		return "WMI_RCP_ADDBA_RESP_CMD";
+	case WMI_RCP_ADDBA_RESP_EDMA_CMDID:
+		return "WMI_RCP_ADDBA_RESP_EDMA_CMD";
 	case WMI_PS_DEV_PROFILE_CFG_CMDID:
 		return "WMI_PS_DEV_PROFILE_CFG_CMD";
 	case WMI_SET_MGMT_RETRY_LIMIT_CMDID:
@@ -2140,15 +2142,18 @@ int wmi_disconnect_sta(struct wil6210_vif *vif, const u8 *mac,
 int wmi_addba(struct wil6210_priv *wil, u8 mid,
 	      u8 ringid, u8 size, u16 timeout)
 {
+	u8 amsdu = wil->use_enhanced_dma_hw && wil->use_rx_hw_reordering &&
+		test_bit(WMI_FW_CAPABILITY_AMSDU, wil->fw_capabilities) &&
+		wil->amsdu_en;
 	struct wmi_ring_ba_en_cmd cmd = {
 		.ring_id = ringid,
 		.agg_max_wsize = size,
 		.ba_timeout = cpu_to_le16(timeout),
-		.amsdu = 0,
+		.amsdu = amsdu,
 	};
 
-	wil_dbg_wmi(wil, "addba: (ring %d size %d timeout %d)\n", ringid, size,
-		    timeout);
+	wil_dbg_wmi(wil, "addba: (ring %d size %d timeout %d amsdu %d)\n",
+		    ringid, size, timeout, amsdu);
 
 	return wmi_send(wil, WMI_RING_BA_EN_CMDID, mid, &cmd, sizeof(cmd));
 }
@@ -2223,6 +2228,54 @@ int wmi_addba_rx_resp(struct wil6210_priv *wil,
 	return rc;
 }
 
+int wmi_addba_rx_resp_edma(struct wil6210_priv *wil, u8 mid, u8 cid, u8 tid,
+			   u8 token, u16 status, bool amsdu, u16 agg_wsize,
+			   u16 timeout)
+{
+	int rc;
+	struct wmi_rcp_addba_resp_edma_cmd cmd = {
+		.cid = cid,
+		.tid = tid,
+		.dialog_token = token,
+		.status_code = cpu_to_le16(status),
+		/* bit 0: A-MSDU supported
+		 * bit 1: policy (should be 0 for us)
+		 * bits 2..5: TID
+		 * bits 6..15: buffer size
+		 */
+		.ba_param_set = cpu_to_le16((amsdu ? 1 : 0) | (tid << 2) |
+					    (agg_wsize << 6)),
+		.ba_timeout = cpu_to_le16(timeout),
+		/* route all the connections to status ring 0 */
+		.status_ring_id = WIL_DEFAULT_RX_STATUS_RING_ID,
+	};
+	struct {
+		struct wmi_cmd_hdr wmi;
+		struct wmi_rcp_addba_resp_sent_event evt;
+	} __packed reply = {
+		.evt = {.status = cpu_to_le16(WMI_FW_STATUS_FAILURE)},
+	};
+
+	wil_dbg_wmi(wil,
+		    "ADDBA response for CID %d TID %d size %d timeout %d status %d AMSDU%s, sring_id %d\n",
+		    cid, tid, agg_wsize, timeout, status, amsdu ? "+" : "-",
+		    WIL_DEFAULT_RX_STATUS_RING_ID);
+
+	rc = wmi_call(wil, WMI_RCP_ADDBA_RESP_EDMA_CMDID, mid, &cmd,
+		      sizeof(cmd), WMI_RCP_ADDBA_RESP_SENT_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc)
+		return rc;
+
+	if (reply.evt.status) {
+		wil_err(wil, "ADDBA response failed with status %d\n",
+			le16_to_cpu(reply.evt.status));
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
 int wmi_ps_dev_profile_cfg(struct wil6210_priv *wil,
 			   enum wmi_ps_profile_type ps_profile)
 {
diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index 38e788000801..abf6f05c4801 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -86,6 +86,7 @@ enum wmi_fw_capability {
 	WMI_FW_CAPABILITY_PNO				= 15,
 	WMI_FW_CAPABILITY_REF_CLOCK_CONTROL		= 18,
 	WMI_FW_CAPABILITY_AP_SME_OFFLOAD_NONE		= 19,
+	WMI_FW_CAPABILITY_AMSDU				= 23,
 	WMI_FW_CAPABILITY_MAX,
 };
 
-- 
cgit v1.2.3


From d98b853934fee79b3cde2c850e03b9c367297a78 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:37 +0300
Subject: wil6210: add support for enhanced DMA debugfs

Add debugfs support for enhanced DMA TX and RX descriptor rings,
TX and RX status rings and RX buffer management.

Run the following command to print the TX and RX status rings:
cat srings

Run the following command in order to select the status ring:
echo STATUS_RING_IDX > dbg_sring_index

Run the following command in order to select the status message:
echo STATUS_MSG_IDX > dbg_status_msg_index

Run the following command in order to print the selected status
message from the selected status ring:
cat status_msg

Run the following command in order to print the RX buffer management
debug information:
cat rx_buff_mgmt

Signed-off-by: Gidon Studinski <gidons@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c | 347 +++++++++++++++++++++++++----
 1 file changed, 307 insertions(+), 40 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 8232fdd6ed09..58ce044b1130 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -30,6 +30,9 @@
 static u32 mem_addr;
 static u32 dbg_txdesc_index;
 static u32 dbg_ring_index; /* 24+ for Rx, 0..23 for Tx */
+static u32 dbg_status_msg_index;
+/* 0..wil->num_rx_status_rings-1 for Rx, wil->tx_sring_idx for Tx */
+static u32 dbg_sring_index;
 
 enum dbg_off_type {
 	doff_u32 = 0,
@@ -47,6 +50,36 @@ struct dbg_off {
 	enum dbg_off_type type;
 };
 
+static void wil_print_desc_edma(struct seq_file *s, struct wil6210_priv *wil,
+				struct wil_ring *ring,
+				char _s, char _h, int idx)
+{
+	u8 num_of_descs;
+	bool has_skb = false;
+
+	if (ring->is_rx) {
+		struct wil_rx_enhanced_desc *rx_d =
+			(struct wil_rx_enhanced_desc *)
+			&ring->va[idx].rx.enhanced;
+		u16 buff_id = le16_to_cpu(rx_d->mac.buff_id);
+
+		has_skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
+		seq_printf(s, "%c", (has_skb) ? _h : _s);
+	} else {
+		struct wil_tx_enhanced_desc *d =
+			(struct wil_tx_enhanced_desc *)
+			&ring->va[idx].tx.enhanced;
+
+		num_of_descs = (u8)d->mac.d[2];
+		has_skb = ring->ctx[idx].skb;
+		if (num_of_descs >= 1)
+			seq_printf(s, "%c", ring->ctx[idx].skb ? _h : _s);
+		else
+			/* num_of_descs == 0, it's a frag in a list of descs */
+			seq_printf(s, "%c", has_skb ? 'h' : _s);
+	}
+}
+
 static void wil_print_ring(struct seq_file *s, struct wil6210_priv *wil,
 			   const char *name, struct wil_ring *ring,
 			   char _s, char _h)
@@ -58,7 +91,10 @@ static void wil_print_ring(struct seq_file *s, struct wil6210_priv *wil,
 	seq_printf(s, "  pa     = %pad\n", &ring->pa);
 	seq_printf(s, "  va     = 0x%p\n", ring->va);
 	seq_printf(s, "  size   = %d\n", ring->size);
-	seq_printf(s, "  swtail = %d\n", ring->swtail);
+	if (wil->use_enhanced_dma_hw && ring->is_rx)
+		seq_printf(s, "  swtail = %u\n", *ring->edma_rx_swtail.va);
+	else
+		seq_printf(s, "  swtail = %d\n", ring->swtail);
 	seq_printf(s, "  swhead = %d\n", ring->swhead);
 	seq_printf(s, "  hwtail = [0x%08x] -> ", ring->hwtail);
 	if (x) {
@@ -72,13 +108,16 @@ static void wil_print_ring(struct seq_file *s, struct wil6210_priv *wil,
 		uint i;
 
 		for (i = 0; i < ring->size; i++) {
-			volatile struct vring_tx_desc *d =
-				&ring->va[i].tx.legacy;
-
-			if ((i % 128) == 0 && (i != 0))
+			if ((i % 128) == 0 && i != 0)
 				seq_puts(s, "\n");
-			seq_printf(s, "%c", (d->dma.status & BIT(0)) ?
-					_s : (ring->ctx[i].skb ? _h : 'h'));
+			if (wil->use_enhanced_dma_hw) {
+				wil_print_desc_edma(s, wil, ring, _s, _h, i);
+			} else {
+				volatile struct vring_tx_desc *d =
+					&ring->va[i].tx.legacy;
+				seq_printf(s, "%c", (d->dma.status & BIT(0)) ?
+					   _s : (ring->ctx[i].skb ? _h : 'h'));
+			}
 		}
 		seq_puts(s, "\n");
 	}
@@ -157,6 +196,74 @@ static const struct file_operations fops_ring = {
 	.llseek		= seq_lseek,
 };
 
+static void wil_print_sring(struct seq_file *s, struct wil6210_priv *wil,
+			    struct wil_status_ring *sring)
+{
+	void __iomem *x = wmi_addr(wil, sring->hwtail);
+	int sring_idx = sring - wil->srings;
+	u32 v;
+
+	seq_printf(s, "Status Ring %s [ %d ] = {\n",
+		   sring->is_rx ? "RX" : "TX", sring_idx);
+	seq_printf(s, "  pa     = %pad\n", &sring->pa);
+	seq_printf(s, "  va     = 0x%pK\n", sring->va);
+	seq_printf(s, "  size   = %d\n", sring->size);
+	seq_printf(s, "  elem_size   = %zu\n", sring->elem_size);
+	seq_printf(s, "  swhead = %d\n", sring->swhead);
+	seq_printf(s, "  hwtail = [0x%08x] -> ", sring->hwtail);
+	if (x) {
+		v = readl_relaxed(x);
+		seq_printf(s, "0x%08x = %d\n", v, v);
+	} else {
+		seq_puts(s, "???\n");
+	}
+	seq_printf(s, "  desc_rdy_pol   = %d\n", sring->desc_rdy_pol);
+
+	if (sring->va && (sring->size <= (1 << WIL_RING_SIZE_ORDER_MAX))) {
+		uint i;
+
+		for (i = 0; i < sring->size; i++) {
+			u32 *sdword_0 =
+				(u32 *)(sring->va + (sring->elem_size * i));
+
+			if ((i % 128) == 0 && i != 0)
+				seq_puts(s, "\n");
+			if (i == sring->swhead)
+				seq_printf(s, "%c", (*sdword_0 & BIT(31)) ?
+					   'X' : 'x');
+			else
+				seq_printf(s, "%c", (*sdword_0 & BIT(31)) ?
+					   '1' : '0');
+		}
+		seq_puts(s, "\n");
+	}
+	seq_puts(s, "}\n");
+}
+
+static int wil_srings_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	int i = 0;
+
+	for (i = 0; i < WIL6210_MAX_STATUS_RINGS; i++)
+		if (wil->srings[i].va)
+			wil_print_sring(s, wil, &wil->srings[i]);
+
+	return 0;
+}
+
+static int wil_srings_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_srings_debugfs_show, inode->i_private);
+}
+
+static const struct file_operations fops_srings = {
+	.open		= wil_srings_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
 static void wil_seq_hexdump(struct seq_file *s, void *p, int len,
 			    const char *prefix)
 {
@@ -974,53 +1081,92 @@ static int wil_txdesc_debugfs_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
 	struct wil_ring *ring;
-	bool tx = (dbg_ring_index < WIL6210_MAX_TX_RINGS);
+	bool tx;
+	int ring_idx = dbg_ring_index;
+	int txdesc_idx = dbg_txdesc_index;
+	volatile struct vring_tx_desc *d;
+	volatile u32 *u;
+	struct sk_buff *skb;
+
+	if (wil->use_enhanced_dma_hw) {
+		/* RX ring index == 0 */
+		if (ring_idx >= WIL6210_MAX_TX_RINGS) {
+			seq_printf(s, "invalid ring index %d\n", ring_idx);
+			return 0;
+		}
+		tx = ring_idx > 0; /* desc ring 0 is reserved for RX */
+	} else {
+		/* RX ring index == WIL6210_MAX_TX_RINGS */
+		if (ring_idx > WIL6210_MAX_TX_RINGS) {
+			seq_printf(s, "invalid ring index %d\n", ring_idx);
+			return 0;
+		}
+		tx = (ring_idx < WIL6210_MAX_TX_RINGS);
+	}
 
-	ring = tx ? &wil->ring_tx[dbg_ring_index] : &wil->ring_rx;
+	ring = tx ? &wil->ring_tx[ring_idx] : &wil->ring_rx;
 
 	if (!ring->va) {
 		if (tx)
-			seq_printf(s, "No Tx[%2d] VRING\n", dbg_ring_index);
+			seq_printf(s, "No Tx[%2d] RING\n", ring_idx);
 		else
-			seq_puts(s, "No Rx VRING\n");
+			seq_puts(s, "No Rx RING\n");
 		return 0;
 	}
 
-	if (dbg_txdesc_index < ring->size) {
-		/* use struct vring_tx_desc for Rx as well,
-		 * only field used, .dma.length, is the same
-		 */
-		volatile struct vring_tx_desc *d =
-				&ring->va[dbg_txdesc_index].tx.legacy;
-		volatile u32 *u = (volatile u32 *)d;
-		struct sk_buff *skb = ring->ctx[dbg_txdesc_index].skb;
-
+	if (txdesc_idx >= ring->size) {
 		if (tx)
-			seq_printf(s, "Tx[%2d][%3d] = {\n", dbg_ring_index,
-				   dbg_txdesc_index);
+			seq_printf(s, "[%2d] TxDesc index (%d) >= size (%d)\n",
+				   ring_idx, txdesc_idx, ring->size);
 		else
-			seq_printf(s, "Rx[%3d] = {\n", dbg_txdesc_index);
-		seq_printf(s, "  MAC = 0x%08x 0x%08x 0x%08x 0x%08x\n",
-			   u[0], u[1], u[2], u[3]);
-		seq_printf(s, "  DMA = 0x%08x 0x%08x 0x%08x 0x%08x\n",
-			   u[4], u[5], u[6], u[7]);
-		seq_printf(s, "  SKB = 0x%p\n", skb);
+			seq_printf(s, "RxDesc index (%d) >= size (%d)\n",
+				   txdesc_idx, ring->size);
+		return 0;
+	}
+
+	/* use struct vring_tx_desc for Rx as well,
+	 * only field used, .dma.length, is the same
+	 */
+	d = &ring->va[txdesc_idx].tx.legacy;
+	u = (volatile u32 *)d;
+	skb = NULL;
 
-		if (skb) {
-			skb_get(skb);
-			wil_seq_print_skb(s, skb);
-			kfree_skb(skb);
+	if (wil->use_enhanced_dma_hw) {
+		if (tx) {
+			skb = ring->ctx[txdesc_idx].skb;
+		} else {
+			struct wil_rx_enhanced_desc *rx_d =
+				(struct wil_rx_enhanced_desc *)
+				&ring->va[txdesc_idx].rx.enhanced;
+			u16 buff_id = le16_to_cpu(rx_d->mac.buff_id);
+
+			if (!wil_val_in_range(buff_id, 0,
+					      wil->rx_buff_mgmt.size)) {
+				seq_printf(s, "invalid buff_id %d\n", buff_id);
+				return 0;
+			}
+			skb = wil->rx_buff_mgmt.buff_arr[buff_id].skb;
 		}
-		seq_puts(s, "}\n");
 	} else {
-		if (tx)
-			seq_printf(s, "[%2d] TxDesc index (%d) >= size (%d)\n",
-				   dbg_ring_index, dbg_txdesc_index,
-				   ring->size);
-		else
-			seq_printf(s, "RxDesc index (%d) >= size (%d)\n",
-				   dbg_txdesc_index, ring->size);
+		skb = ring->ctx[txdesc_idx].skb;
+	}
+	if (tx)
+		seq_printf(s, "Tx[%2d][%3d] = {\n", ring_idx,
+			   txdesc_idx);
+	else
+		seq_printf(s, "Rx[%3d] = {\n", txdesc_idx);
+	seq_printf(s, "  MAC = 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   u[0], u[1], u[2], u[3]);
+	seq_printf(s, "  DMA = 0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   u[4], u[5], u[6], u[7]);
+	seq_printf(s, "  SKB = 0x%p\n", skb);
+
+	if (skb) {
+		skb_get(skb);
+		wil_seq_print_skb(s, skb);
+		kfree_skb(skb);
 	}
+	seq_puts(s, "}\n");
 
 	return 0;
 }
@@ -1037,6 +1183,115 @@ static const struct file_operations fops_txdesc = {
 	.llseek		= seq_lseek,
 };
 
+/*---------Tx/Rx status message------------*/
+static int wil_status_msg_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	int sring_idx = dbg_sring_index;
+	struct wil_status_ring *sring;
+	bool tx = sring_idx == wil->tx_sring_idx ? 1 : 0;
+	u32 status_msg_idx = dbg_status_msg_index;
+	u32 *u;
+
+	if (sring_idx >= WIL6210_MAX_STATUS_RINGS) {
+		seq_printf(s, "invalid status ring index %d\n", sring_idx);
+		return 0;
+	}
+
+	sring = &wil->srings[sring_idx];
+
+	if (!sring->va) {
+		seq_printf(s, "No %cX status ring\n", tx ? 'T' : 'R');
+		return 0;
+	}
+
+	if (status_msg_idx >= sring->size) {
+		seq_printf(s, "%cxDesc index (%d) >= size (%d)\n",
+			   tx ? 'T' : 'R', status_msg_idx, sring->size);
+		return 0;
+	}
+
+	u = sring->va + (sring->elem_size * status_msg_idx);
+
+	seq_printf(s, "%cx[%d][%3d] = {\n",
+		   tx ? 'T' : 'R', sring_idx, status_msg_idx);
+
+	seq_printf(s, "  0x%08x 0x%08x 0x%08x 0x%08x\n",
+		   u[0], u[1], u[2], u[3]);
+	if (!tx && !wil->use_compressed_rx_status)
+		seq_printf(s, "  0x%08x 0x%08x 0x%08x 0x%08x\n",
+			   u[4], u[5], u[6], u[7]);
+
+	seq_puts(s, "}\n");
+
+	return 0;
+}
+
+static int wil_status_msg_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_status_msg_debugfs_show,
+			   inode->i_private);
+}
+
+static const struct file_operations fops_status_msg = {
+	.open		= wil_status_msg_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+static int wil_print_rx_buff(struct seq_file *s, struct list_head *lh)
+{
+	struct wil_rx_buff *it;
+	int i = 0;
+
+	list_for_each_entry(it, lh, list) {
+		if ((i % 16) == 0 && i != 0)
+			seq_puts(s, "\n    ");
+		seq_printf(s, "[%4d] ", it->id);
+		i++;
+	}
+	seq_printf(s, "\nNumber of buffers: %u\n", i);
+
+	return i;
+}
+
+static int wil_rx_buff_mgmt_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	struct wil_rx_buff_mgmt *rbm = &wil->rx_buff_mgmt;
+	int num_active;
+	int num_free;
+
+	seq_printf(s, "  size = %zu\n", rbm->size);
+	seq_printf(s, "  free_list_empty_cnt = %lu\n",
+		   rbm->free_list_empty_cnt);
+
+	/* Print active list */
+	seq_puts(s, "  Active list:\n");
+	num_active = wil_print_rx_buff(s, &rbm->active);
+	seq_puts(s, "\n  Free list:\n");
+	num_free = wil_print_rx_buff(s, &rbm->free);
+
+	seq_printf(s, "  Total number of buffers: %u\n",
+		   num_active + num_free);
+
+	return 0;
+}
+
+static int wil_rx_buff_mgmt_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_rx_buff_mgmt_debugfs_show,
+			   inode->i_private);
+}
+
+static const struct file_operations fops_rx_buff_mgmt = {
+	.open		= wil_rx_buff_mgmt_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
 /*---------beamforming------------*/
 static char *wil_bfstatus_str(u32 status)
 {
@@ -1479,6 +1734,13 @@ __acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
 				   p->stats.rx_large_frame,
 				   p->stats.rx_replay);
 
+			if (wil->use_enhanced_dma_hw)
+				seq_printf(s,
+					   "mic error  %lu, key error %lu, amsdu error %lu\n",
+					   p->stats.rx_mic_error,
+					   p->stats.rx_key_error,
+					   p->stats.rx_amsdu_error);
+
 			seq_puts(s, "Rx/MCS:");
 			for (mcs = 0; mcs < ARRAY_SIZE(p->stats.rx_per_mcs);
 			     mcs++)
@@ -1869,6 +2131,9 @@ static const struct {
 	{"fw_version",	0444,		&fops_fw_version},
 	{"suspend_stats",	0644,	&fops_suspend_stats},
 	{"compressed_rx_status", 0644,	&fops_compressed_rx_status},
+	{"srings",	0444,		&fops_srings},
+	{"status_msg",	0444,		&fops_status_msg},
+	{"rx_buff_mgmt",	0444,	&fops_rx_buff_mgmt},
 };
 
 static void wil6210_debugfs_init_files(struct wil6210_priv *wil,
@@ -1936,6 +2201,8 @@ static const struct dbg_off dbg_statics[] = {
 	{"ring_index",	0644, (ulong)&dbg_ring_index, doff_u32},
 	{"mem_addr",	0644, (ulong)&mem_addr, doff_u32},
 	{"led_polarity", 0644, (ulong)&led_polarity, doff_u8},
+	{"status_index", 0644, (ulong)&dbg_status_msg_index, doff_u32},
+	{"sring_index",	0644, (ulong)&dbg_sring_index, doff_u32},
 	{},
 };
 
-- 
cgit v1.2.3


From f1dbb6c1e83394e68b082b3058aabb12ab046f25 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:42 +0300
Subject: wil6210: add support for Talyn-MB boot flow

Talyn-MB introduces various of FW download options:
FW download via PCIe, SPI or PBL for secured access.
The boot and FW download path is determined based on the
OTP HW register. Driver reads this register as part of the
SW reset flow and performs the appropriate initialization
sequence.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c    | 194 ++++++++++++++++++++++++-----
 drivers/net/wireless/ath/wil6210/wil6210.h |   9 +-
 2 files changed, 171 insertions(+), 32 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index e0072b6c7a44..4de19bd40a58 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -112,9 +112,29 @@ MODULE_PARM_DESC(tx_ring_order, " Tx ring order; size = 1 << order");
 module_param_cb(bcast_ring_order, &ring_order_ops, &bcast_ring_order, 0444);
 MODULE_PARM_DESC(bcast_ring_order, " Bcast ring order; size = 1 << order");
 
-#define RST_DELAY (20) /* msec, for loop in @wil_target_reset */
+enum {
+	WIL_BOOT_ERR,
+	WIL_BOOT_VANILLA,
+	WIL_BOOT_PRODUCTION,
+	WIL_BOOT_DEVELOPMENT,
+};
+
+enum {
+	WIL_SIG_STATUS_VANILLA = 0x0,
+	WIL_SIG_STATUS_DEVELOPMENT = 0x1,
+	WIL_SIG_STATUS_PRODUCTION = 0x2,
+	WIL_SIG_STATUS_CORRUPTED_PRODUCTION = 0x3,
+};
+
+#define RST_DELAY (20) /* msec, for loop in @wil_wait_device_ready */
 #define RST_COUNT (1 + 1000/RST_DELAY) /* round up to be above 1 sec total */
 
+#define PMU_READY_DELAY_MS (4) /* ms, for sleep in @wil_wait_device_ready */
+
+#define OTP_HW_DELAY (200) /* usec, loop in @wil_wait_device_ready_talyn_mb */
+/* round up to be above 2 ms total */
+#define OTP_HW_COUNT (1 + 2000 / OTP_HW_DELAY)
+
 /*
  * Due to a hardware issue,
  * one has to read/write to/from NIC in 32-bit chunks;
@@ -831,11 +851,146 @@ static void wil_set_oob_mode(struct wil6210_priv *wil, u8 mode)
 	}
 }
 
-static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
+static int wil_wait_device_ready(struct wil6210_priv *wil, int no_flash)
 {
 	int delay = 0;
 	u32 x, x1 = 0;
 
+	/* wait until device ready. */
+	if (no_flash) {
+		msleep(PMU_READY_DELAY_MS);
+
+		wil_dbg_misc(wil, "Reset completed\n");
+	} else {
+		do {
+			msleep(RST_DELAY);
+			x = wil_r(wil, RGF_USER_BL +
+				  offsetof(struct bl_dedicated_registers_v0,
+					   boot_loader_ready));
+			if (x1 != x) {
+				wil_dbg_misc(wil, "BL.ready 0x%08x => 0x%08x\n",
+					     x1, x);
+				x1 = x;
+			}
+			if (delay++ > RST_COUNT) {
+				wil_err(wil, "Reset not completed, bl.ready 0x%08x\n",
+					x);
+				return -ETIME;
+			}
+		} while (x != BL_READY);
+
+		wil_dbg_misc(wil, "Reset completed in %d ms\n",
+			     delay * RST_DELAY);
+	}
+
+	return 0;
+}
+
+static int wil_wait_device_ready_talyn_mb(struct wil6210_priv *wil)
+{
+	u32 otp_hw;
+	u8 signature_status;
+	bool otp_signature_err;
+	bool hw_section_done;
+	u32 otp_qc_secured;
+	int delay = 0;
+
+	/* Wait for OTP signature test to complete */
+	usleep_range(2000, 2200);
+
+	wil->boot_config = WIL_BOOT_ERR;
+
+	/* Poll until OTP signature status is valid.
+	 * In vanilla and development modes, when signature test is complete
+	 * HW sets BIT_OTP_SIGNATURE_ERR_TALYN_MB.
+	 * In production mode BIT_OTP_SIGNATURE_ERR_TALYN_MB remains 0, poll
+	 * for signature status change to 2 or 3.
+	 */
+	do {
+		otp_hw = wil_r(wil, RGF_USER_OTP_HW_RD_MACHINE_1);
+		signature_status = WIL_GET_BITS(otp_hw, 8, 9);
+		otp_signature_err = otp_hw & BIT_OTP_SIGNATURE_ERR_TALYN_MB;
+
+		if (otp_signature_err &&
+		    signature_status == WIL_SIG_STATUS_VANILLA) {
+			wil->boot_config = WIL_BOOT_VANILLA;
+			break;
+		}
+		if (otp_signature_err &&
+		    signature_status == WIL_SIG_STATUS_DEVELOPMENT) {
+			wil->boot_config = WIL_BOOT_DEVELOPMENT;
+			break;
+		}
+		if (!otp_signature_err &&
+		    signature_status == WIL_SIG_STATUS_PRODUCTION) {
+			wil->boot_config = WIL_BOOT_PRODUCTION;
+			break;
+		}
+		if  (!otp_signature_err &&
+		     signature_status ==
+		     WIL_SIG_STATUS_CORRUPTED_PRODUCTION) {
+			/* Unrecognized OTP signature found. Possibly a
+			 * corrupted production signature, access control
+			 * is applied as in production mode, therefore
+			 * do not fail
+			 */
+			wil->boot_config = WIL_BOOT_PRODUCTION;
+			break;
+		}
+		if (delay++ > OTP_HW_COUNT)
+			break;
+
+		usleep_range(OTP_HW_DELAY, OTP_HW_DELAY + 10);
+	} while (!otp_signature_err && signature_status == 0);
+
+	if (wil->boot_config == WIL_BOOT_ERR) {
+		wil_err(wil,
+			"invalid boot config, signature_status %d otp_signature_err %d\n",
+			signature_status, otp_signature_err);
+		return -ETIME;
+	}
+
+	wil_dbg_misc(wil,
+		     "signature test done in %d usec, otp_hw 0x%x, boot_config %d\n",
+		     delay * OTP_HW_DELAY, otp_hw, wil->boot_config);
+
+	if (wil->boot_config == WIL_BOOT_VANILLA)
+		/* Assuming not SPI boot (currently not supported) */
+		goto out;
+
+	hw_section_done = otp_hw & BIT_OTP_HW_SECTION_DONE_TALYN_MB;
+	delay = 0;
+
+	while (!hw_section_done) {
+		msleep(RST_DELAY);
+
+		otp_hw = wil_r(wil, RGF_USER_OTP_HW_RD_MACHINE_1);
+		hw_section_done = otp_hw & BIT_OTP_HW_SECTION_DONE_TALYN_MB;
+
+		if (delay++ > RST_COUNT) {
+			wil_err(wil, "TO waiting for hw_section_done\n");
+			return -ETIME;
+		}
+	}
+
+	wil_dbg_misc(wil, "HW section done in %d ms\n", delay * RST_DELAY);
+
+	otp_qc_secured = wil_r(wil, RGF_OTP_QC_SECURED);
+	wil->secured_boot = otp_qc_secured & BIT_BOOT_FROM_ROM ? 1 : 0;
+	wil_dbg_misc(wil, "secured boot is %sabled\n",
+		     wil->secured_boot ? "en" : "dis");
+
+out:
+	wil_dbg_misc(wil, "Reset completed\n");
+
+	return 0;
+}
+
+static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
+{
+	u32 x;
+	int rc;
+
 	wil_dbg_misc(wil, "Resetting \"%s\"...\n", wil->hw_name);
 
 	/* Clear MAC link up */
@@ -901,34 +1056,12 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 
 	wil_w(wil, RGF_USER_CLKS_CTL_SW_RST_VEC_0, 0);
 
-	/* wait until device ready. typical time is 20..80 msec */
-	if (no_flash)
-		do {
-			msleep(RST_DELAY);
-			x = wil_r(wil, USER_EXT_USER_PMU_3);
-			if (delay++ > RST_COUNT) {
-				wil_err(wil, "Reset not completed, PMU_3 0x%08x\n",
-					x);
-				return -ETIME;
-			}
-		} while ((x & BIT_PMU_DEVICE_RDY) == 0);
+	if (wil->hw_version == HW_VER_TALYN_MB)
+		rc = wil_wait_device_ready_talyn_mb(wil);
 	else
-		do {
-			msleep(RST_DELAY);
-			x = wil_r(wil, RGF_USER_BL +
-				  offsetof(struct bl_dedicated_registers_v0,
-					   boot_loader_ready));
-			if (x1 != x) {
-				wil_dbg_misc(wil, "BL.ready 0x%08x => 0x%08x\n",
-					     x1, x);
-				x1 = x;
-			}
-			if (delay++ > RST_COUNT) {
-				wil_err(wil, "Reset not completed, bl.ready 0x%08x\n",
-					x);
-				return -ETIME;
-			}
-		} while (x != BL_READY);
+		rc = wil_wait_device_ready(wil, no_flash);
+	if (rc)
+		return rc;
 
 	wil_c(wil, RGF_USER_CLKS_CTL_0, BIT_USER_CLKS_RST_PWGD);
 
@@ -936,7 +1069,7 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 	wil_s(wil, RGF_DMA_OFUL_NID_0, BIT_DMA_OFUL_NID_0_RX_EXT_TR_EN |
 	      BIT_DMA_OFUL_NID_0_RX_EXT_A3_SRC);
 
-	if (no_flash) {
+	if (wil->hw_version < HW_VER_TALYN_MB && no_flash) {
 		/* Reset OTP HW vectors to fit 40MHz */
 		wil_w(wil, RGF_USER_XPM_IFC_RD_TIME1, 0x60001);
 		wil_w(wil, RGF_USER_XPM_IFC_RD_TIME2, 0x20027);
@@ -951,7 +1084,6 @@ static int wil_target_reset(struct wil6210_priv *wil, int no_flash)
 		wil_w(wil, RGF_USER_XPM_RD_DOUT_SAMPLE_TIME, 0x57);
 	}
 
-	wil_dbg_misc(wil, "Reset completed in %d ms\n", delay * RST_DELAY);
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index f8d4a2d88d91..e639ba73c02d 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -210,7 +210,9 @@ struct RGF_ICR {
 #define RGF_USER_SPARROW_M_4			(0x880c50) /* Sparrow */
 	#define BIT_SPARROW_M_4_SEL_SLEEP_OR_REF	BIT(2)
 #define RGF_USER_OTP_HW_RD_MACHINE_1	(0x880ce0)
-	#define BIT_NO_FLASH_INDICATION		BIT(8)
+	#define BIT_OTP_SIGNATURE_ERR_TALYN_MB		BIT(0)
+	#define BIT_OTP_HW_SECTION_DONE_TALYN_MB	BIT(2)
+	#define BIT_NO_FLASH_INDICATION			BIT(8)
 #define RGF_USER_XPM_IFC_RD_TIME1	(0x880cec)
 #define RGF_USER_XPM_IFC_RD_TIME2	(0x880cf0)
 #define RGF_USER_XPM_IFC_RD_TIME3	(0x880cf4)
@@ -312,6 +314,9 @@ struct RGF_ICR {
 #define RGF_CAF_PLL_LOCK_STATUS		(0x88afec)
 	#define BIT_CAF_OSC_DIG_XTAL_STABLE	BIT(0)
 
+#define RGF_OTP_QC_SECURED		(0x8a0038)
+	#define BIT_BOOT_FROM_ROM		BIT(31)
+
 /* eDMA */
 #define RGF_INT_COUNT_ON_SPECIAL_EVT	(0x8b62d8)
 
@@ -969,6 +974,8 @@ struct wil6210_priv {
 	u32 rx_buff_id_count;
 	bool amsdu_en;
 	bool use_rx_hw_reordering;
+	bool secured_boot;
+	u8 boot_config;
 };
 
 #define wil_to_wiphy(i) (i->wiphy)
-- 
cgit v1.2.3


From 9a53d0b6f8c61b27e7071d75fb82cf707968f75a Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Fri, 29 Jun 2018 16:28:48 +0300
Subject: wil6210: remove crash dump collection from OTP section

In some cases where the device is stuck, reading from OTP
can timeout. As OTP section is known there is no need to read
it during device crash dump collection.
Adding a new field to struct fw_map to indicate if to include
this section in crash dump collection.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/wil6210.h        |  1 +
 drivers/net/wireless/ath/wil6210/wil_crash_dump.c |  5 +-
 drivers/net/wireless/ath/wil6210/wmi.c            | 86 +++++++++++------------
 3 files changed, 47 insertions(+), 45 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index e639ba73c02d..d963c76b679e 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -403,6 +403,7 @@ struct fw_map {
 	u32 host; /* PCI/Host address - BAR0 + 0x880000 */
 	const char *name; /* for debugfs */
 	bool fw; /* true if FW mapping, false if UCODE mapping */
+	bool crash_dump; /* true if should be dumped during crash dump */
 };
 
 /* array size should be in sync with actual definition in the wmi.c */
diff --git a/drivers/net/wireless/ath/wil6210/wil_crash_dump.c b/drivers/net/wireless/ath/wil6210/wil_crash_dump.c
index 1ed330674d9b..dc33a0b4c3fa 100644
--- a/drivers/net/wireless/ath/wil6210/wil_crash_dump.c
+++ b/drivers/net/wireless/ath/wil6210/wil_crash_dump.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2015,2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -36,7 +37,7 @@ static int wil_fw_get_crash_dump_bounds(struct wil6210_priv *wil,
 	for (i = 1; i < ARRAY_SIZE(fw_mapping); i++) {
 		map = &fw_mapping[i];
 
-		if (!map->fw)
+		if (!map->crash_dump)
 			continue;
 
 		if (map->host < host_min)
@@ -85,7 +86,7 @@ int wil_fw_copy_crash_dump(struct wil6210_priv *wil, void *dest, u32 size)
 	for (i = 0; i < ARRAY_SIZE(fw_mapping); i++) {
 		map = &fw_mapping[i];
 
-		if (!map->fw)
+		if (!map->crash_dump)
 			continue;
 
 		data = (void * __force)wil->csr + HOSTADDR(map->host);
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 0370b7e8dbb1..71056c834fff 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -89,28 +89,28 @@ MODULE_PARM_DESC(led_id,
  */
 const struct fw_map sparrow_fw_mapping[] = {
 	/* FW code RAM 256k */
-	{0x000000, 0x040000, 0x8c0000, "fw_code", true},
+	{0x000000, 0x040000, 0x8c0000, "fw_code", true, true},
 	/* FW data RAM 32k */
-	{0x800000, 0x808000, 0x900000, "fw_data", true},
+	{0x800000, 0x808000, 0x900000, "fw_data", true, true},
 	/* periph data 128k */
-	{0x840000, 0x860000, 0x908000, "fw_peri", true},
+	{0x840000, 0x860000, 0x908000, "fw_peri", true, true},
 	/* various RGF 40k */
-	{0x880000, 0x88a000, 0x880000, "rgf", true},
+	{0x880000, 0x88a000, 0x880000, "rgf", true, true},
 	/* AGC table   4k */
-	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true},
+	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true, true},
 	/* Pcie_ext_rgf 4k */
-	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true},
+	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true, true},
 	/* mac_ext_rgf 512b */
-	{0x88c000, 0x88c200, 0x88c000, "mac_rgf_ext", true},
+	{0x88c000, 0x88c200, 0x88c000, "mac_rgf_ext", true, true},
 	/* upper area 548k */
-	{0x8c0000, 0x949000, 0x8c0000, "upper", true},
+	{0x8c0000, 0x949000, 0x8c0000, "upper", true, true},
 	/* UCODE areas - accessible by debugfs blobs but not by
 	 * wmi_addr_remap. UCODE areas MUST be added AFTER FW areas!
 	 */
 	/* ucode code RAM 128k */
-	{0x000000, 0x020000, 0x920000, "uc_code", false},
+	{0x000000, 0x020000, 0x920000, "uc_code", false, false},
 	/* ucode data RAM 16k */
-	{0x800000, 0x804000, 0x940000, "uc_data", false},
+	{0x800000, 0x804000, 0x940000, "uc_data", false, false},
 };
 
 /**
@@ -118,7 +118,7 @@ const struct fw_map sparrow_fw_mapping[] = {
  * it is a bit larger to support extra features
  */
 const struct fw_map sparrow_d0_mac_rgf_ext = {
-	0x88c000, 0x88c500, 0x88c000, "mac_rgf_ext", true
+	0x88c000, 0x88c500, 0x88c000, "mac_rgf_ext", true, true
 };
 
 /**
@@ -134,34 +134,34 @@ const struct fw_map sparrow_d0_mac_rgf_ext = {
  */
 const struct fw_map talyn_fw_mapping[] = {
 	/* FW code RAM 1M */
-	{0x000000, 0x100000, 0x900000, "fw_code", true},
+	{0x000000, 0x100000, 0x900000, "fw_code", true, true},
 	/* FW data RAM 128k */
-	{0x800000, 0x820000, 0xa00000, "fw_data", true},
+	{0x800000, 0x820000, 0xa00000, "fw_data", true, true},
 	/* periph. data RAM 96k */
-	{0x840000, 0x858000, 0xa20000, "fw_peri", true},
+	{0x840000, 0x858000, 0xa20000, "fw_peri", true, true},
 	/* various RGF 40k */
-	{0x880000, 0x88a000, 0x880000, "rgf", true},
+	{0x880000, 0x88a000, 0x880000, "rgf", true, true},
 	/* AGC table 4k */
-	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true},
+	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true, true},
 	/* Pcie_ext_rgf 4k */
-	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true},
+	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true, true},
 	/* mac_ext_rgf 1344b */
-	{0x88c000, 0x88c540, 0x88c000, "mac_rgf_ext", true},
+	{0x88c000, 0x88c540, 0x88c000, "mac_rgf_ext", true, true},
 	/* ext USER RGF 4k */
-	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true},
+	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true, true},
 	/* OTP 4k */
-	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true},
+	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true, false},
 	/* DMA EXT RGF 64k */
-	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true},
+	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true, true},
 	/* upper area 1536k */
-	{0x900000, 0xa80000, 0x900000, "upper", true},
+	{0x900000, 0xa80000, 0x900000, "upper", true, true},
 	/* UCODE areas - accessible by debugfs blobs but not by
 	 * wmi_addr_remap. UCODE areas MUST be added AFTER FW areas!
 	 */
 	/* ucode code RAM 256k */
-	{0x000000, 0x040000, 0xa38000, "uc_code", false},
+	{0x000000, 0x040000, 0xa38000, "uc_code", false, false},
 	/* ucode data RAM 32k */
-	{0x800000, 0x808000, 0xa78000, "uc_data", false},
+	{0x800000, 0x808000, 0xa78000, "uc_data", false, false},
 };
 
 /**
@@ -177,46 +177,46 @@ const struct fw_map talyn_fw_mapping[] = {
  */
 const struct fw_map talyn_mb_fw_mapping[] = {
 	/* FW code RAM 768k */
-	{0x000000, 0x0c0000, 0x900000, "fw_code", true},
+	{0x000000, 0x0c0000, 0x900000, "fw_code", true, true},
 	/* FW data RAM 128k */
-	{0x800000, 0x820000, 0xa00000, "fw_data", true},
+	{0x800000, 0x820000, 0xa00000, "fw_data", true, true},
 	/* periph. data RAM 96k */
-	{0x840000, 0x858000, 0xa20000, "fw_peri", true},
+	{0x840000, 0x858000, 0xa20000, "fw_peri", true, true},
 	/* various RGF 40k */
-	{0x880000, 0x88a000, 0x880000, "rgf", true},
+	{0x880000, 0x88a000, 0x880000, "rgf", true, true},
 	/* AGC table 4k */
-	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true},
+	{0x88a000, 0x88b000, 0x88a000, "AGC_tbl", true, true},
 	/* Pcie_ext_rgf 4k */
-	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true},
+	{0x88b000, 0x88c000, 0x88b000, "rgf_ext", true, true},
 	/* mac_ext_rgf 2256b */
-	{0x88c000, 0x88c8d0, 0x88c000, "mac_rgf_ext", true},
+	{0x88c000, 0x88c8d0, 0x88c000, "mac_rgf_ext", true, true},
 	/* ext USER RGF 4k */
-	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true},
+	{0x88d000, 0x88e000, 0x88d000, "ext_user_rgf", true, true},
 	/* SEC PKA 16k */
-	{0x890000, 0x894000, 0x890000, "sec_pka", true},
+	{0x890000, 0x894000, 0x890000, "sec_pka", true, true},
 	/* SEC KDF RGF 3096b */
-	{0x898000, 0x898c18, 0x898000, "sec_kdf_rgf", true},
+	{0x898000, 0x898c18, 0x898000, "sec_kdf_rgf", true, true},
 	/* SEC MAIN 2124b */
-	{0x89a000, 0x89a84c, 0x89a000, "sec_main", true},
+	{0x89a000, 0x89a84c, 0x89a000, "sec_main", true, true},
 	/* OTP 4k */
-	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true},
+	{0x8a0000, 0x8a1000, 0x8a0000, "otp", true, false},
 	/* DMA EXT RGF 64k */
-	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true},
+	{0x8b0000, 0x8c0000, 0x8b0000, "dma_ext_rgf", true, true},
 	/* DUM USER RGF 528b */
-	{0x8c0000, 0x8c0210, 0x8c0000, "dum_user_rgf", true},
+	{0x8c0000, 0x8c0210, 0x8c0000, "dum_user_rgf", true, true},
 	/* DMA OFU 296b */
-	{0x8c2000, 0x8c2128, 0x8c2000, "dma_ofu", true},
+	{0x8c2000, 0x8c2128, 0x8c2000, "dma_ofu", true, true},
 	/* ucode debug 4k */
-	{0x8c3000, 0x8c4000, 0x8c3000, "ucode_debug", true},
+	{0x8c3000, 0x8c4000, 0x8c3000, "ucode_debug", true, true},
 	/* upper area 1536k */
-	{0x900000, 0xa80000, 0x900000, "upper", true},
+	{0x900000, 0xa80000, 0x900000, "upper", true, true},
 	/* UCODE areas - accessible by debugfs blobs but not by
 	 * wmi_addr_remap. UCODE areas MUST be added AFTER FW areas!
 	 */
 	/* ucode code RAM 256k */
-	{0x000000, 0x040000, 0xa38000, "uc_code", false},
+	{0x000000, 0x040000, 0xa38000, "uc_code", false, false},
 	/* ucode data RAM 32k */
-	{0x800000, 0x808000, 0xa78000, "uc_data", false},
+	{0x800000, 0x808000, 0xa78000, "uc_data", false, false},
 };
 
 struct fw_map fw_mapping[MAX_FW_MAPPING_TABLE_SIZE];
-- 
cgit v1.2.3


From f0eea2772a6baf06961c6b0812bcb3adcce307a9 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Fri, 29 Jun 2018 14:37:45 +0200
Subject: wcn36xx: drop unnecessary initialization of variables

Initialization is unneccessary when the variable is written before it is
read. There were some occasions in which the driver would initialize `ret'
during declaration without need.

Purely a cosmetic change with no functional impact.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wcn36xx/main.c |  4 +-
 drivers/net/wireless/ath/wcn36xx/smd.c  | 75 ++++++++++++++++-----------------
 2 files changed, 38 insertions(+), 41 deletions(-)

diff --git a/drivers/net/wireless/ath/wcn36xx/main.c b/drivers/net/wireless/ath/wcn36xx/main.c
index e38443ecaab4..79998a3ddb7a 100644
--- a/drivers/net/wireless/ath/wcn36xx/main.c
+++ b/drivers/net/wireless/ath/wcn36xx/main.c
@@ -1161,8 +1161,6 @@ static const struct ieee80211_ops wcn36xx_ops = {
 
 static int wcn36xx_init_ieee80211(struct wcn36xx *wcn)
 {
-	int ret = 0;
-
 	static const u32 cipher_suites[] = {
 		WLAN_CIPHER_SUITE_WEP40,
 		WLAN_CIPHER_SUITE_WEP104,
@@ -1209,7 +1207,7 @@ static int wcn36xx_init_ieee80211(struct wcn36xx *wcn)
 	wiphy_ext_feature_set(wcn->hw->wiphy,
 			      NL80211_EXT_FEATURE_CQM_RSSI_LIST);
 
-	return ret;
+	return 0;
 }
 
 static int wcn36xx_platform_get_resources(struct wcn36xx *wcn,
diff --git a/drivers/net/wireless/ath/wcn36xx/smd.c b/drivers/net/wireless/ath/wcn36xx/smd.c
index 304a86c7dcd2..00098f24116d 100644
--- a/drivers/net/wireless/ath/wcn36xx/smd.c
+++ b/drivers/net/wireless/ath/wcn36xx/smd.c
@@ -250,7 +250,7 @@ static void wcn36xx_smd_set_sta_params(struct wcn36xx *wcn,
 
 static int wcn36xx_smd_send_and_wait(struct wcn36xx *wcn, size_t len)
 {
-	int ret = 0;
+	int ret;
 	unsigned long start;
 	struct wcn36xx_hal_msg_header *hdr =
 		(struct wcn36xx_hal_msg_header *)wcn->hal_buf;
@@ -446,7 +446,7 @@ static int wcn36xx_smd_start_rsp(struct wcn36xx *wcn, void *buf, size_t len)
 int wcn36xx_smd_start(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_mac_start_req_msg msg_body, *body;
-	int ret = 0;
+	int ret;
 	int i;
 	size_t len;
 
@@ -493,7 +493,7 @@ out:
 int wcn36xx_smd_stop(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_mac_stop_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_STOP_REQ);
@@ -520,7 +520,7 @@ out:
 int wcn36xx_smd_init_scan(struct wcn36xx *wcn, enum wcn36xx_hal_sys_mode mode)
 {
 	struct wcn36xx_hal_init_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_INIT_SCAN_REQ);
@@ -549,7 +549,7 @@ out:
 int wcn36xx_smd_start_scan(struct wcn36xx *wcn, u8 scan_channel)
 {
 	struct wcn36xx_hal_start_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_START_SCAN_REQ);
@@ -579,7 +579,7 @@ out:
 int wcn36xx_smd_end_scan(struct wcn36xx *wcn, u8 scan_channel)
 {
 	struct wcn36xx_hal_end_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_END_SCAN_REQ);
@@ -610,7 +610,7 @@ int wcn36xx_smd_finish_scan(struct wcn36xx *wcn,
 			    enum wcn36xx_hal_sys_mode mode)
 {
 	struct wcn36xx_hal_finish_scan_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_FINISH_SCAN_REQ);
@@ -732,7 +732,7 @@ out:
 static int wcn36xx_smd_switch_channel_rsp(void *buf, size_t len)
 {
 	struct wcn36xx_hal_switch_channel_rsp_msg *rsp;
-	int ret = 0;
+	int ret;
 
 	ret = wcn36xx_smd_rsp_status_check(buf, len);
 	if (ret)
@@ -747,7 +747,7 @@ int wcn36xx_smd_switch_channel(struct wcn36xx *wcn,
 			       struct ieee80211_vif *vif, int ch)
 {
 	struct wcn36xx_hal_switch_channel_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_CH_SWITCH_REQ);
@@ -860,7 +860,7 @@ int wcn36xx_smd_update_scan_params(struct wcn36xx *wcn,
 				   u8 *channels, size_t channel_count)
 {
 	struct wcn36xx_hal_update_scan_params_req_ex msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_UPDATE_SCAN_PARAM_REQ);
@@ -931,7 +931,7 @@ static int wcn36xx_smd_add_sta_self_rsp(struct wcn36xx *wcn,
 int wcn36xx_smd_add_sta_self(struct wcn36xx *wcn, struct ieee80211_vif *vif)
 {
 	struct wcn36xx_hal_add_sta_self_req msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ADD_STA_SELF_REQ);
@@ -965,7 +965,7 @@ out:
 int wcn36xx_smd_delete_sta_self(struct wcn36xx *wcn, u8 *addr)
 {
 	struct wcn36xx_hal_del_sta_self_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DEL_STA_SELF_REQ);
@@ -993,7 +993,7 @@ out:
 int wcn36xx_smd_delete_sta(struct wcn36xx *wcn, u8 sta_index)
 {
 	struct wcn36xx_hal_delete_sta_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DELETE_STA_REQ);
@@ -1040,7 +1040,7 @@ static int wcn36xx_smd_join_rsp(void *buf, size_t len)
 int wcn36xx_smd_join(struct wcn36xx *wcn, const u8 *bssid, u8 *vif, u8 ch)
 {
 	struct wcn36xx_hal_join_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_JOIN_REQ);
@@ -1089,7 +1089,7 @@ int wcn36xx_smd_set_link_st(struct wcn36xx *wcn, const u8 *bssid,
 			    enum wcn36xx_hal_link_state state)
 {
 	struct wcn36xx_hal_set_link_state_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_LINK_ST_REQ);
@@ -1215,7 +1215,7 @@ int wcn36xx_smd_config_sta(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 {
 	struct wcn36xx_hal_config_sta_req_msg msg;
 	struct wcn36xx_hal_config_sta_params *sta_params;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg, WCN36XX_HAL_CONFIG_STA_REQ);
@@ -1414,7 +1414,7 @@ int wcn36xx_smd_config_bss(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 	struct wcn36xx_hal_config_bss_params *bss;
 	struct wcn36xx_hal_config_sta_params *sta_params;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg, WCN36XX_HAL_CONFIG_BSS_REQ);
@@ -1579,7 +1579,7 @@ int wcn36xx_smd_send_beacon(struct wcn36xx *wcn, struct ieee80211_vif *vif,
 			    u16 p2p_off)
 {
 	struct wcn36xx_hal_send_beacon_req_msg msg_body;
-	int ret = 0, pad, pvm_len;
+	int ret, pad, pvm_len;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SEND_BEACON_REQ);
@@ -1653,7 +1653,7 @@ int wcn36xx_smd_update_proberesp_tmpl(struct wcn36xx *wcn,
 				      struct sk_buff *skb)
 {
 	struct wcn36xx_hal_send_probe_resp_req_msg msg;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg, WCN36XX_HAL_UPDATE_PROBE_RSP_TEMPLATE_REQ);
@@ -1700,7 +1700,7 @@ int wcn36xx_smd_set_stakey(struct wcn36xx *wcn,
 			   u8 sta_index)
 {
 	struct wcn36xx_hal_set_sta_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_STAKEY_REQ);
@@ -1749,7 +1749,7 @@ int wcn36xx_smd_set_bsskey(struct wcn36xx *wcn,
 			   u8 *key)
 {
 	struct wcn36xx_hal_set_bss_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_BSSKEY_REQ);
@@ -1786,7 +1786,7 @@ int wcn36xx_smd_remove_stakey(struct wcn36xx *wcn,
 			      u8 sta_index)
 {
 	struct wcn36xx_hal_remove_sta_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_RMV_STAKEY_REQ);
@@ -1818,7 +1818,7 @@ int wcn36xx_smd_remove_bsskey(struct wcn36xx *wcn,
 			      u8 keyidx)
 {
 	struct wcn36xx_hal_remove_bss_key_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_RMV_BSSKEY_REQ);
@@ -1847,7 +1847,7 @@ int wcn36xx_smd_enter_bmps(struct wcn36xx *wcn, struct ieee80211_vif *vif)
 {
 	struct wcn36xx_hal_enter_bmps_req_msg msg_body;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ENTER_BMPS_REQ);
@@ -1877,7 +1877,7 @@ int wcn36xx_smd_exit_bmps(struct wcn36xx *wcn, struct ieee80211_vif *vif)
 {
 	struct wcn36xx_hal_exit_bmps_req_msg msg_body;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_EXIT_BMPS_REQ);
@@ -1903,7 +1903,7 @@ out:
 int wcn36xx_smd_set_power_params(struct wcn36xx *wcn, bool ignore_dtim)
 {
 	struct wcn36xx_hal_set_power_params_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_SET_POWER_PARAMS_REQ);
@@ -1938,7 +1938,7 @@ int wcn36xx_smd_keep_alive_req(struct wcn36xx *wcn,
 {
 	struct wcn36xx_hal_keep_alive_req_msg msg_body;
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_KEEP_ALIVE_REQ);
@@ -1976,7 +1976,7 @@ int wcn36xx_smd_dump_cmd_req(struct wcn36xx *wcn, u32 arg1, u32 arg2,
 			     u32 arg3, u32 arg4, u32 arg5)
 {
 	struct wcn36xx_hal_dump_cmd_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DUMP_COMMAND_REQ);
@@ -2021,7 +2021,6 @@ void set_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 int get_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 {
 	int arr_idx, bit_idx;
-	int ret = 0;
 
 	if (cap < 0 || cap > 127) {
 		wcn36xx_warn("error cap idx %d\n", cap);
@@ -2030,8 +2029,8 @@ int get_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 
 	arr_idx = cap / 32;
 	bit_idx = cap % 32;
-	ret = (bitmap[arr_idx] & (1 << bit_idx)) ? 1 : 0;
-	return ret;
+
+	return (bitmap[arr_idx] & (1 << bit_idx)) ? 1 : 0;
 }
 
 void clear_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
@@ -2051,7 +2050,7 @@ void clear_feat_caps(u32 *bitmap, enum place_holder_in_cap_bitmap cap)
 int wcn36xx_smd_feature_caps_exchange(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_feat_caps_msg msg_body, *rsp;
-	int ret = 0, i;
+	int ret, i;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_FEATURE_CAPS_EXCHANGE_REQ);
@@ -2087,7 +2086,7 @@ int wcn36xx_smd_add_ba_session(struct wcn36xx *wcn,
 		u8 sta_index)
 {
 	struct wcn36xx_hal_add_ba_session_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ADD_BA_SESSION_REQ);
@@ -2125,7 +2124,7 @@ out:
 int wcn36xx_smd_add_ba(struct wcn36xx *wcn)
 {
 	struct wcn36xx_hal_add_ba_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_ADD_BA_REQ);
@@ -2153,7 +2152,7 @@ out:
 int wcn36xx_smd_del_ba(struct wcn36xx *wcn, u16 tid, u8 sta_index)
 {
 	struct wcn36xx_hal_del_ba_req_msg msg_body;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_DEL_BA_REQ);
@@ -2193,7 +2192,7 @@ int wcn36xx_smd_trigger_ba(struct wcn36xx *wcn, u8 sta_index)
 {
 	struct wcn36xx_hal_trigger_ba_req_msg msg_body;
 	struct wcn36xx_hal_trigger_ba_req_candidate *candidate;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_TRIGGER_BA_REQ);
@@ -2372,7 +2371,7 @@ int wcn36xx_smd_update_cfg(struct wcn36xx *wcn, u32 cfg_id, u32 value)
 {
 	struct wcn36xx_hal_update_cfg_req_msg msg_body, *body;
 	size_t len;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 	INIT_HAL_MSG(msg_body, WCN36XX_HAL_UPDATE_CFG_REQ);
@@ -2407,7 +2406,7 @@ int wcn36xx_smd_set_mc_list(struct wcn36xx *wcn,
 {
 	struct wcn36xx_vif *vif_priv = wcn36xx_vif_to_priv(vif);
 	struct wcn36xx_hal_rcv_flt_pkt_set_mc_list_req_msg *msg_body = NULL;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&wcn->hal_mutex);
 
-- 
cgit v1.2.3


From e67005e59a74613c2d5879f63eef70e6267bb452 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Fri, 29 Jun 2018 13:20:39 +0300
Subject: drm/i915: abstract and document register picking macros

Try to describe what the pick variants do, and which to prefer. No
functional changes.

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180629102039.2435-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index c30cfcd90754..7dc774682922 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -139,19 +139,35 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 	return !i915_mmio_reg_equal(reg, INVALID_MMIO_REG);
 }
 
+/*
+ * Given the first two numbers __a and __b of arbitrarily many evenly spaced
+ * numbers, pick the 0-based __index'th value.
+ *
+ * Always prefer this over _PICK() if the numbers are evenly spaced.
+ */
+#define _PICK_EVEN(__index, __a, __b) ((__a) + (__index) * ((__b) - (__a)))
+
+/*
+ * Given the arbitrary numbers in varargs, pick the 0-based __index'th number.
+ *
+ * Always prefer _PICK_EVEN() over this if the numbers are evenly spaced.
+ */
 #define _PICK(__index, ...) (((const u32 []){ __VA_ARGS__ })[__index])
 
-#define _PIPE(pipe, a, b) ((a) + (pipe) * ((b) - (a)))
+/*
+ * Named helper wrappers around _PICK_EVEN() and _PICK().
+ */
+#define _PIPE(pipe, a, b) _PICK_EVEN(pipe, a, b)
 #define _MMIO_PIPE(pipe, a, b) _MMIO(_PIPE(pipe, a, b))
-#define _PLANE(plane, a, b) _PIPE(plane, a, b)
+#define _PLANE(plane, a, b) _PICK_EVEN(plane, a, b)
 #define _MMIO_PLANE(plane, a, b) _MMIO_PIPE(plane, a, b)
-#define _TRANS(tran, a, b) ((a) + (tran) * ((b) - (a)))
+#define _TRANS(tran, a, b) _PICK_EVEN(tran, a, b)
 #define _MMIO_TRANS(tran, a, b) _MMIO(_TRANS(tran, a, b))
-#define _PORT(port, a, b) ((a) + (port) * ((b) - (a)))
+#define _PORT(port, a, b) _PICK_EVEN(port, a, b)
 #define _MMIO_PORT(port, a, b) _MMIO(_PORT(port, a, b))
 #define _MMIO_PIPE3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
 #define _MMIO_PORT3(pipe, a, b, c) _MMIO(_PICK(pipe, a, b, c))
-#define _PLL(pll, a, b) ((a) + (pll) * ((b) - (a)))
+#define _PLL(pll, a, b) _PICK_EVEN(pll, a, b)
 #define _MMIO_PLL(pll, a, b) _MMIO(_PLL(pll, a, b))
 #define _PHY3(phy, ...) _PICK(phy, __VA_ARGS__)
 #define _MMIO_PHY3(phy, a, b, c) _MMIO(_PHY3(phy, a, b, c))
@@ -6874,7 +6890,7 @@ enum {
 #define _PS_ECC_STAT_2B     0x68AD0
 #define _PS_ECC_STAT_1C     0x691D0
 
-#define _ID(id, a, b) ((a) + (id) * ((b) - (a)))
+#define _ID(id, a, b) _PICK_EVEN(id, a, b)
 #define SKL_PS_CTRL(pipe, id) _MMIO_PIPE(pipe,        \
 			_ID(id, _PS_1A_CTRL, _PS_2A_CTRL),       \
 			_ID(id, _PS_1B_CTRL, _PS_2B_CTRL))
-- 
cgit v1.2.3


From d505a96a3b16f46455035dc0296bc2da6014e163 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Sun, 24 Jun 2018 10:43:49 +0100
Subject: gfs2: Further iomap cleanups

In gfs2_iomap_alloc, set the type of newly allocated extents to
IOMAP_MAPPED so that iomap_to_bh will set the bh states correctly:
otherwise, the bhs would not be marked as mapped, confusing
__mpage_writepage.  This means that we need to check for the IOMAP_F_NEW
flag in fallocate_chunk now.

Further clean up gfs2_iomap_get and implement gfs2_stuffed_iomap here
directly.  For reads beyond the end of the file, return holes instead of
failing with -ENOENT so that we can get rid of that special case in
gfs2_block_map.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/bmap.c | 74 +++++++++++++++++++++++++++++++++-------------------------
 fs/gfs2/file.c |  2 +-
 2 files changed, 43 insertions(+), 33 deletions(-)

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index ed6699705c13..33ee93344d18 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -750,6 +750,7 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 		}
 	} while (iomap->addr == IOMAP_NULL_ADDR);
 
+	iomap->type = IOMAP_MAPPED;
 	iomap->length = (u64)dblks << inode->i_blkbits;
 	ip->i_height = mp->mp_fheight;
 	gfs2_add_inode_blocks(&ip->i_inode, alloced);
@@ -759,17 +760,6 @@ out:
 	return ret;
 }
 
-static void gfs2_stuffed_iomap(struct inode *inode, struct iomap *iomap)
-{
-	struct gfs2_inode *ip = GFS2_I(inode);
-
-	iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
-		      sizeof(struct gfs2_dinode);
-	iomap->offset = 0;
-	iomap->length = i_size_read(inode);
-	iomap->type = IOMAP_INLINE;
-}
-
 #define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE
 
 /**
@@ -789,37 +779,61 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	loff_t size = i_size_read(inode);
 	__be64 *ptr;
 	sector_t lblock;
 	sector_t lblock_stop;
 	int ret;
 	int eob;
 	u64 len;
-	struct buffer_head *bh;
+	struct buffer_head *dibh = NULL, *bh;
 	u8 height;
 
 	if (!length)
 		return -EINVAL;
 
+	down_read(&ip->i_rw_mutex);
+
+	ret = gfs2_meta_inode_buffer(ip, &dibh);
+	if (ret)
+		goto unlock;
+
 	if (gfs2_is_stuffed(ip)) {
-		if (flags & IOMAP_REPORT) {
-			if (pos >= i_size_read(inode))
-				return -ENOENT;
-			gfs2_stuffed_iomap(inode, iomap);
-			return 0;
+		if (flags & IOMAP_WRITE) {
+			loff_t max_size = gfs2_max_stuffed_size(ip);
+
+			if (pos + length > max_size)
+				goto unstuff;
+			iomap->length = max_size;
+		} else {
+			if (pos >= size) {
+				if (flags & IOMAP_REPORT) {
+					ret = -ENOENT;
+					goto unlock;
+				} else {
+					/* report a hole */
+					iomap->offset = pos;
+					iomap->length = length;
+					goto do_alloc;
+				}
+			}
+			iomap->length = size;
 		}
-		BUG_ON(!(flags & IOMAP_WRITE));
+		iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
+			      sizeof(struct gfs2_dinode);
+		iomap->type = IOMAP_INLINE;
+		goto out;
 	}
+
+unstuff:
 	lblock = pos >> inode->i_blkbits;
 	iomap->offset = lblock << inode->i_blkbits;
 	lblock_stop = (pos + length - 1) >> inode->i_blkbits;
 	len = lblock_stop - lblock + 1;
+	iomap->length = len << inode->i_blkbits;
 
-	down_read(&ip->i_rw_mutex);
-
-	ret = gfs2_meta_inode_buffer(ip, &mp->mp_bh[0]);
-	if (ret)
-		goto unlock;
+	get_bh(dibh);
+	mp->mp_bh[0] = dibh;
 
 	height = ip->i_height;
 	while ((lblock + 1) * sdp->sd_sb.sb_bsize > sdp->sd_heightsize[height])
@@ -853,21 +867,23 @@ out:
 	iomap->bdev = inode->i_sb->s_bdev;
 unlock:
 	up_read(&ip->i_rw_mutex);
+	if (dibh)
+		brelse(dibh);
 	return ret;
 
 do_alloc:
 	iomap->addr = IOMAP_NULL_ADDR;
-	iomap->length = len << inode->i_blkbits;
 	iomap->type = IOMAP_HOLE;
-	iomap->flags = 0;
 	if (flags & IOMAP_REPORT) {
-		loff_t size = i_size_read(inode);
 		if (pos >= size)
 			ret = -ENOENT;
 		else if (height == ip->i_height)
 			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 		else
 			iomap->length = size - pos;
+	} else if (!(flags & IOMAP_WRITE)) {
+		if (pos < size && height == ip->i_height)
+			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 	}
 	goto out;
 }
@@ -941,12 +957,6 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
 	} else {
 		ret = gfs2_iomap_get(inode, pos, length, 0, &iomap, &mp);
 		release_metapath(&mp);
-
-		/* Return unmapped buffer beyond the end of file. */
-		if (ret == -ENOENT) {
-			ret = 0;
-			goto out;
-		}
 	}
 	if (ret)
 		goto out;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 7137db7b0119..6f6bbfbff13d 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -754,7 +754,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 		if (error)
 			goto out;
 		offset = iomap.offset + iomap.length;
-		if (iomap.type != IOMAP_HOLE)
+		if (!(iomap.flags & IOMAP_F_NEW))
 			continue;
 		error = sb_issue_zeroout(sb, iomap.addr >> inode->i_blkbits,
 					 iomap.length >> inode->i_blkbits,
-- 
cgit v1.2.3


From 64bc06bb32ee9cf458f432097113c8b495d75757 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Sun, 24 Jun 2018 15:04:04 +0100
Subject: gfs2: iomap buffered write support

With the traditional page-based writes, blocks are allocated separately
for each page written to.  With iomap writes, we can allocate a lot more
blocks at once, with a fraction of the allocation overhead for each
page.

Split calculating the number of blocks that can be allocated at a given
position (gfs2_alloc_size) off from gfs2_iomap_alloc: that size
determines the number of blocks to allocate and reserve in the journal.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/aops.c |  20 ++--
 fs/gfs2/aops.h |  19 ++++
 fs/gfs2/bmap.c | 298 +++++++++++++++++++++++++++++++++++++++++++++++++++------
 fs/gfs2/file.c |  44 +++++++--
 4 files changed, 338 insertions(+), 43 deletions(-)
 create mode 100644 fs/gfs2/aops.h

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 35f5ee23566d..ecfbca9c88ff 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -22,6 +22,7 @@
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
 #include <trace/events/writeback.h>
+#include <linux/sched/signal.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -36,10 +37,11 @@
 #include "super.h"
 #include "util.h"
 #include "glops.h"
+#include "aops.h"
 
 
-static void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
-				   unsigned int from, unsigned int len)
+void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+			    unsigned int from, unsigned int len)
 {
 	struct buffer_head *head = page_buffers(page);
 	unsigned int bsize = head->b_size;
@@ -462,7 +464,7 @@ static int gfs2_jdata_writepages(struct address_space *mapping,
  * Returns: errno
  */
 
-static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
+int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
 {
 	struct buffer_head *dibh;
 	u64 dsize = i_size_read(&ip->i_inode);
@@ -776,7 +778,7 @@ out_uninit:
  * adjust_fs_space - Adjusts the free space available due to gfs2_grow
  * @inode: the rindex inode
  */
-static void adjust_fs_space(struct inode *inode)
+void adjust_fs_space(struct inode *inode)
 {
 	struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
 	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
@@ -822,11 +824,11 @@ out:
  * This copies the data from the page into the inode block after
  * the inode data structure itself.
  *
- * Returns: errno
+ * Returns: copied bytes or errno
  */
-static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
-				  loff_t pos, unsigned copied,
-				  struct page *page)
+int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+			   loff_t pos, unsigned copied,
+			   struct page *page)
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 	u64 to = pos + copied;
@@ -865,7 +867,7 @@ static int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
  * The main write_end function for GFS2. We just put our locking around the VFS
  * provided functions.
  *
- * Returns: errno
+ * Returns: copied bytes or errno
  */
 
 static int gfs2_write_end(struct file *file, struct address_space *mapping,
diff --git a/fs/gfs2/aops.h b/fs/gfs2/aops.h
new file mode 100644
index 000000000000..fa8e5d0144dd
--- /dev/null
+++ b/fs/gfs2/aops.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Red Hat, Inc.  All rights reserved.
+ */
+
+#ifndef __AOPS_DOT_H__
+#define __AOPS_DOT_H__
+
+#include "incore.h"
+
+extern int stuffed_readpage(struct gfs2_inode *ip, struct page *page);
+extern int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
+				  loff_t pos, unsigned copied,
+				  struct page *page);
+extern void adjust_fs_space(struct inode *inode);
+extern void gfs2_page_add_databufs(struct gfs2_inode *ip, struct page *page,
+				   unsigned int from, unsigned int len);
+
+#endif /* __AOPS_DOT_H__ */
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 33ee93344d18..9a699c0a5df1 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -28,6 +28,7 @@
 #include "trans.h"
 #include "dir.h"
 #include "util.h"
+#include "aops.h"
 #include "trace_gfs2.h"
 
 /* This doesn't need to be that large as max 64 bit pointers in a 4k
@@ -41,6 +42,8 @@ struct metapath {
 	int mp_aheight; /* actual height (lookup height) */
 };
 
+static int punch_hole(struct gfs2_inode *ip, u64 offset, u64 length);
+
 /**
  * gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
  * @ip: the inode
@@ -389,7 +392,7 @@ static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h)
 	return mp->mp_aheight - x - 1;
 }
 
-static inline void release_metapath(struct metapath *mp)
+static void release_metapath(struct metapath *mp)
 {
 	int i;
 
@@ -397,6 +400,7 @@ static inline void release_metapath(struct metapath *mp)
 		if (mp->mp_bh[i] == NULL)
 			break;
 		brelse(mp->mp_bh[i]);
+		mp->mp_bh[i] = NULL;
 	}
 }
 
@@ -609,11 +613,13 @@ enum alloc_state {
  *  ii) Indirect blocks to fill in lower part of the metadata tree
  * iii) Data blocks
  *
- * The function is in two parts. The first part works out the total
- * number of blocks which we need. The second part does the actual
- * allocation asking for an extent at a time (if enough contiguous free
- * blocks are available, there will only be one request per bmap call)
- * and uses the state machine to initialise the blocks in order.
+ * This function is called after gfs2_iomap_get, which works out the
+ * total number of blocks which we need via gfs2_alloc_size.
+ *
+ * We then do the actual allocation asking for an extent at a time (if
+ * enough contiguous free blocks are available, there will only be one
+ * allocation request per call) and uses the state machine to initialise
+ * the blocks in order.
  *
  * Right now, this function will allocate at most one indirect block
  * worth of data -- with a default block size of 4K, that's slightly
@@ -633,39 +639,26 @@ static int gfs2_iomap_alloc(struct inode *inode, struct iomap *iomap,
 	struct buffer_head *dibh = mp->mp_bh[0];
 	u64 bn;
 	unsigned n, i, blks, alloced = 0, iblks = 0, branch_start = 0;
-	unsigned dblks = 0;
-	unsigned ptrs_per_blk;
+	size_t dblks = iomap->length >> inode->i_blkbits;
 	const unsigned end_of_metadata = mp->mp_fheight - 1;
 	int ret;
 	enum alloc_state state;
 	__be64 *ptr;
 	__be64 zero_bn = 0;
-	size_t maxlen = iomap->length >> inode->i_blkbits;
 
 	BUG_ON(mp->mp_aheight < 1);
 	BUG_ON(dibh == NULL);
+	BUG_ON(dblks < 1);
 
 	gfs2_trans_add_meta(ip->i_gl, dibh);
 
 	down_write(&ip->i_rw_mutex);
 
 	if (mp->mp_fheight == mp->mp_aheight) {
-		struct buffer_head *bh;
-		int eob;
-
-		/* Bottom indirect block exists, find unalloced extent size */
-		ptr = metapointer(end_of_metadata, mp);
-		bh = mp->mp_bh[end_of_metadata];
-		dblks = gfs2_extent_length(bh->b_data, bh->b_size, ptr,
-					   maxlen, &eob);
-		BUG_ON(dblks < 1);
+		/* Bottom indirect block exists */
 		state = ALLOC_DATA;
 	} else {
 		/* Need to allocate indirect blocks */
-		ptrs_per_blk = mp->mp_fheight > 1 ? sdp->sd_inptrs :
-			sdp->sd_diptrs;
-		dblks = min(maxlen, (size_t)(ptrs_per_blk -
-					     mp->mp_list[end_of_metadata]));
 		if (mp->mp_fheight == ip->i_height) {
 			/* Writing into existing tree, extend tree down */
 			iblks = mp->mp_fheight - mp->mp_aheight;
@@ -762,6 +755,50 @@ out:
 
 #define IOMAP_F_GFS2_BOUNDARY IOMAP_F_PRIVATE
 
+/**
+ * gfs2_alloc_size - Compute the maximum allocation size
+ * @inode: The inode
+ * @mp: The metapath
+ * @size: Requested size in blocks
+ *
+ * Compute the maximum size of the next allocation at @mp.
+ *
+ * Returns: size in blocks
+ */
+static u64 gfs2_alloc_size(struct inode *inode, struct metapath *mp, u64 size)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	const __be64 *first, *ptr, *end;
+
+	/*
+	 * For writes to stuffed files, this function is called twice via
+	 * gfs2_iomap_get, before and after unstuffing. The size we return the
+	 * first time needs to be large enough to get the reservation and
+	 * allocation sizes right.  The size we return the second time must
+	 * be exact or else gfs2_iomap_alloc won't do the right thing.
+	 */
+
+	if (gfs2_is_stuffed(ip) || mp->mp_fheight != mp->mp_aheight) {
+		unsigned int maxsize = mp->mp_fheight > 1 ?
+			sdp->sd_inptrs : sdp->sd_diptrs;
+		maxsize -= mp->mp_list[mp->mp_fheight - 1];
+		if (size > maxsize)
+			size = maxsize;
+		return size;
+	}
+
+	first = metapointer(ip->i_height - 1, mp);
+	end = metaend(ip->i_height - 1, mp);
+	if (end - first > size)
+		end = first + size;
+	for (ptr = first; ptr < end; ptr++) {
+		if (*ptr)
+			break;
+	}
+	return ptr - first;
+}
+
 /**
  * gfs2_iomap_get - Map blocks from an inode to disk blocks
  * @inode: The inode
@@ -797,6 +834,7 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
 	ret = gfs2_meta_inode_buffer(ip, &dibh);
 	if (ret)
 		goto unlock;
+	iomap->private = dibh;
 
 	if (gfs2_is_stuffed(ip)) {
 		if (flags & IOMAP_WRITE) {
@@ -822,6 +860,7 @@ static int gfs2_iomap_get(struct inode *inode, loff_t pos, loff_t length,
 		iomap->addr = (ip->i_no_addr << inode->i_blkbits) +
 			      sizeof(struct gfs2_dinode);
 		iomap->type = IOMAP_INLINE;
+		iomap->inline_data = dibh->b_data + sizeof(struct gfs2_dinode);
 		goto out;
 	}
 
@@ -867,7 +906,7 @@ out:
 	iomap->bdev = inode->i_sb->s_bdev;
 unlock:
 	up_read(&ip->i_rw_mutex);
-	if (dibh)
+	if (ret && dibh)
 		brelse(dibh);
 	return ret;
 
@@ -881,13 +920,168 @@ do_alloc:
 			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 		else
 			iomap->length = size - pos;
-	} else if (!(flags & IOMAP_WRITE)) {
+	} else if (flags & IOMAP_WRITE) {
+		u64 alloc_size;
+
+		len = gfs2_alloc_size(inode, mp, len);
+		alloc_size = len << inode->i_blkbits;
+		if (alloc_size < iomap->length)
+			iomap->length = alloc_size;
+	} else {
 		if (pos < size && height == ip->i_height)
 			ret = gfs2_hole_size(inode, lblock, len, mp, iomap);
 	}
 	goto out;
 }
 
+static int gfs2_write_lock(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	int error;
+
+	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
+	error = gfs2_glock_nq(&ip->i_gh);
+	if (error)
+		goto out_uninit;
+	if (&ip->i_inode == sdp->sd_rindex) {
+		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+		error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
+					   GL_NOCACHE, &m_ip->i_gh);
+		if (error)
+			goto out_unlock;
+	}
+	return 0;
+
+out_unlock:
+	gfs2_glock_dq(&ip->i_gh);
+out_uninit:
+	gfs2_holder_uninit(&ip->i_gh);
+	return error;
+}
+
+static void gfs2_write_unlock(struct inode *inode)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+
+	if (&ip->i_inode == sdp->sd_rindex) {
+		struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
+
+		gfs2_glock_dq_uninit(&m_ip->i_gh);
+	}
+	gfs2_glock_dq_uninit(&ip->i_gh);
+}
+
+static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
+				unsigned copied, struct page *page,
+				struct iomap *iomap)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+
+	gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
+}
+
+static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
+				  loff_t length, unsigned flags,
+				  struct iomap *iomap)
+{
+	struct metapath mp = { .mp_aheight = 1, };
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
+	bool unstuff, alloc_required;
+	int ret;
+
+	ret = gfs2_write_lock(inode);
+	if (ret)
+		return ret;
+
+	unstuff = gfs2_is_stuffed(ip) &&
+		  pos + length > gfs2_max_stuffed_size(ip);
+
+	ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
+	if (ret)
+		goto out_release;
+
+	alloc_required = unstuff || iomap->type == IOMAP_HOLE;
+
+	if (alloc_required || gfs2_is_jdata(ip))
+		gfs2_write_calc_reserv(ip, iomap->length, &data_blocks,
+				       &ind_blocks);
+
+	if (alloc_required) {
+		struct gfs2_alloc_parms ap = {
+			.target = data_blocks + ind_blocks
+		};
+
+		ret = gfs2_quota_lock_check(ip, &ap);
+		if (ret)
+			goto out_release;
+
+		ret = gfs2_inplace_reserve(ip, &ap);
+		if (ret)
+			goto out_qunlock;
+	}
+
+	rblocks = RES_DINODE + ind_blocks;
+	if (gfs2_is_jdata(ip))
+		rblocks += data_blocks;
+	if (ind_blocks || data_blocks)
+		rblocks += RES_STATFS + RES_QUOTA;
+	if (inode == sdp->sd_rindex)
+		rblocks += 2 * RES_STATFS;
+	if (alloc_required)
+		rblocks += gfs2_rg_blocks(ip, data_blocks + ind_blocks);
+
+	ret = gfs2_trans_begin(sdp, rblocks, iomap->length >> inode->i_blkbits);
+	if (ret)
+		goto out_trans_fail;
+
+	if (unstuff) {
+		ret = gfs2_unstuff_dinode(ip, NULL);
+		if (ret)
+			goto out_trans_end;
+		release_metapath(&mp);
+		brelse(iomap->private);
+		iomap->private = NULL;
+		ret = gfs2_iomap_get(inode, iomap->offset, iomap->length,
+				     flags, iomap, &mp);
+		if (ret)
+			goto out_trans_end;
+	}
+
+	if (iomap->type == IOMAP_HOLE) {
+		ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
+		if (ret) {
+			gfs2_trans_end(sdp);
+			gfs2_inplace_release(ip);
+			punch_hole(ip, iomap->offset, iomap->length);
+			goto out_qunlock;
+		}
+	}
+	release_metapath(&mp);
+	if (gfs2_is_jdata(ip))
+		iomap->page_done = gfs2_iomap_journaled_page_done;
+	return 0;
+
+out_trans_end:
+	gfs2_trans_end(sdp);
+out_trans_fail:
+	if (alloc_required)
+		gfs2_inplace_release(ip);
+out_qunlock:
+	if (alloc_required)
+		gfs2_quota_unlock(ip);
+out_release:
+	if (iomap->private)
+		brelse(iomap->private);
+	release_metapath(&mp);
+	gfs2_write_unlock(inode);
+	return ret;
+}
+
 static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 			    unsigned flags, struct iomap *iomap)
 {
@@ -897,10 +1091,7 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 
 	trace_gfs2_iomap_start(ip, pos, length, flags);
 	if (flags & IOMAP_WRITE) {
-		ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
-		if (!ret && iomap->type == IOMAP_HOLE)
-			ret = gfs2_iomap_alloc(inode, iomap, flags, &mp);
-		release_metapath(&mp);
+		ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap);
 	} else {
 		ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
 		release_metapath(&mp);
@@ -909,8 +1100,59 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 	return ret;
 }
 
+static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
+			  ssize_t written, unsigned flags, struct iomap *iomap)
+{
+	struct gfs2_inode *ip = GFS2_I(inode);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
+	struct gfs2_trans *tr = current->journal_info;
+	struct buffer_head *dibh = iomap->private;
+
+	if (!(flags & IOMAP_WRITE))
+		goto out;
+
+	if (iomap->type != IOMAP_INLINE) {
+		gfs2_ordered_add_inode(ip);
+
+		if (tr->tr_num_buf_new)
+			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		else
+			gfs2_trans_add_meta(ip->i_gl, dibh);
+	}
+
+	if (inode == sdp->sd_rindex) {
+		adjust_fs_space(inode);
+		sdp->sd_rindex_uptodate = 0;
+	}
+
+	gfs2_trans_end(sdp);
+	gfs2_inplace_release(ip);
+
+	if (length != written && (iomap->flags & IOMAP_F_NEW)) {
+		/* Deallocate blocks that were just allocated. */
+		loff_t blockmask = i_blocksize(inode) - 1;
+		loff_t end = (pos + length) & ~blockmask;
+
+		pos = (pos + written + blockmask) & ~blockmask;
+		if (pos < end) {
+			truncate_pagecache_range(inode, pos, end - 1);
+			punch_hole(ip, pos, end - pos);
+		}
+	}
+
+	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
+		gfs2_quota_unlock(ip);
+	gfs2_write_unlock(inode);
+
+out:
+	if (dibh)
+		brelse(dibh);
+	return 0;
+}
+
 const struct iomap_ops gfs2_iomap_ops = {
 	.iomap_begin = gfs2_iomap_begin,
+	.iomap_end = gfs2_iomap_end,
 };
 
 /**
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 6f6bbfbff13d..16dd395479a5 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -26,10 +26,12 @@
 #include <linux/dlm.h>
 #include <linux/dlm_plock.h>
 #include <linux/delay.h>
+#include <linux/backing-dev.h>
 
 #include "gfs2.h"
 #include "incore.h"
 #include "bmap.h"
+#include "aops.h"
 #include "dir.h"
 #include "glock.h"
 #include "glops.h"
@@ -691,9 +693,7 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 /**
  * gfs2_file_write_iter - Perform a write to a file
  * @iocb: The io context
- * @iov: The data to write
- * @nr_segs: Number of @iov segments
- * @pos: The file position
+ * @from: The data to write
  *
  * We have to do a lock/unlock here to refresh the inode size for
  * O_APPEND writes, otherwise we can land up writing at the wrong
@@ -705,8 +705,9 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
-	struct gfs2_inode *ip = GFS2_I(file_inode(file));
-	int ret;
+	struct inode *inode = file_inode(file);
+	struct gfs2_inode *ip = GFS2_I(inode);
+	ssize_t ret;
 
 	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
@@ -723,7 +724,38 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		gfs2_glock_dq_uninit(&gh);
 	}
 
-	return generic_file_write_iter(iocb, from);
+	if (iocb->ki_flags & IOCB_DIRECT)
+		return generic_file_write_iter(iocb, from);
+
+	inode_lock(inode);
+	ret = generic_write_checks(iocb, from);
+	if (ret <= 0)
+		goto out;
+
+	/* We can write back this queue in page reclaim */
+	current->backing_dev_info = inode_to_bdi(inode);
+
+	ret = file_remove_privs(file);
+	if (ret)
+		goto out2;
+
+	ret = file_update_time(file);
+	if (ret)
+		goto out2;
+
+	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+
+out2:
+	current->backing_dev_info = NULL;
+out:
+	inode_unlock(inode);
+	if (likely(ret > 0)) {
+		iocb->ki_pos += ret;
+
+		/* Handle various SYNC-type writes */
+		ret = generic_write_sync(iocb, ret);
+	}
+	return ret;
 }
 
 static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
-- 
cgit v1.2.3


From bcfe94139a45fae128844558d6e27a0258860a90 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 11 May 2018 17:44:19 +0100
Subject: gfs2: gfs2_extent_length cleanup

Now that gfs2_extent_length is no longer used for determining the size
of a hole and always with an upper size limit, the function can be
simplified.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/bmap.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 9a699c0a5df1..8b5876e19ecf 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -406,22 +406,17 @@ static void release_metapath(struct metapath *mp)
 
 /**
  * gfs2_extent_length - Returns length of an extent of blocks
- * @start: Start of the buffer
- * @len: Length of the buffer in bytes
- * @ptr: Current position in the buffer
- * @limit: Max extent length to return (0 = unlimited)
+ * @bh: The metadata block
+ * @ptr: Current position in @bh
+ * @limit: Max extent length to return
  * @eob: Set to 1 if we hit "end of block"
  *
- * If the first block is zero (unallocated) it will return the number of
- * unallocated blocks in the extent, otherwise it will return the number
- * of contiguous blocks in the extent.
- *
  * Returns: The length of the extent (minimum of one block)
  */
 
-static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __be64 *ptr, size_t limit, int *eob)
+static inline unsigned int gfs2_extent_length(struct buffer_head *bh, __be64 *ptr, size_t limit, int *eob)
 {
-	const __be64 *end = (start + len);
+	const __be64 *end = (__be64 *)(bh->b_data + bh->b_size);
 	const __be64 *first = ptr;
 	u64 d = be64_to_cpu(*ptr);
 
@@ -430,14 +425,11 @@ static inline unsigned int gfs2_extent_length(void *start, unsigned int len, __b
 		ptr++;
 		if (ptr >= end)
 			break;
-		if (limit && --limit == 0)
-			break;
-		if (d)
-			d++;
+		d++;
 	} while(be64_to_cpu(*ptr) == d);
 	if (ptr >= end)
 		*eob = 1;
-	return (ptr - first);
+	return ptr - first;
 }
 
 typedef const __be64 *(*gfs2_metadata_walker)(
@@ -893,7 +885,7 @@ unstuff:
 		goto do_alloc;
 
 	bh = mp->mp_bh[ip->i_height - 1];
-	len = gfs2_extent_length(bh->b_data, bh->b_size, ptr, len, &eob);
+	len = gfs2_extent_length(bh, ptr, len, &eob);
 
 	iomap->addr = be64_to_cpu(*ptr) << inode->i_blkbits;
 	iomap->length = len << inode->i_blkbits;
-- 
cgit v1.2.3


From 967bcc91b044936e85dbb5848952dc1335a846f4 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 19 Jun 2018 15:08:02 +0100
Subject: gfs2: iomap direct I/O support

The page unmapping previously done in gfs2_direct_IO is now done
generically in iomap_dio_rw.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/aops.c | 100 +------------------------------------------
 fs/gfs2/bmap.c |  14 +++++-
 fs/gfs2/file.c | 132 ++++++++++++++++++++++++++++++++++++++++++++++++++++-----
 3 files changed, 136 insertions(+), 110 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index ecfbca9c88ff..1054cc4a96db 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -84,12 +84,6 @@ static int gfs2_get_block_noalloc(struct inode *inode, sector_t lblock,
 	return 0;
 }
 
-static int gfs2_get_block_direct(struct inode *inode, sector_t lblock,
-				 struct buffer_head *bh_result, int create)
-{
-	return gfs2_block_map(inode, lblock, bh_result, 0);
-}
-
 /**
  * gfs2_writepage_common - Common bits of writepage
  * @page: The page to be written
@@ -1024,96 +1018,6 @@ out:
 		try_to_release_page(page, 0);
 }
 
-/**
- * gfs2_ok_for_dio - check that dio is valid on this file
- * @ip: The inode
- * @offset: The offset at which we are reading or writing
- *
- * Returns: 0 (to ignore the i/o request and thus fall back to buffered i/o)
- *          1 (to accept the i/o request)
- */
-static int gfs2_ok_for_dio(struct gfs2_inode *ip, loff_t offset)
-{
-	/*
-	 * Should we return an error here? I can't see that O_DIRECT for
-	 * a stuffed file makes any sense. For now we'll silently fall
-	 * back to buffered I/O
-	 */
-	if (gfs2_is_stuffed(ip))
-		return 0;
-
-	if (offset >= i_size_read(&ip->i_inode))
-		return 0;
-	return 1;
-}
-
-
-
-static ssize_t gfs2_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
-	struct file *file = iocb->ki_filp;
-	struct inode *inode = file->f_mapping->host;
-	struct address_space *mapping = inode->i_mapping;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	loff_t offset = iocb->ki_pos;
-	struct gfs2_holder gh;
-	int rv;
-
-	/*
-	 * Deferred lock, even if its a write, since we do no allocation
-	 * on this path. All we need change is atime, and this lock mode
-	 * ensures that other nodes have flushed their buffered read caches
-	 * (i.e. their page cache entries for this inode). We do not,
-	 * unfortunately have the option of only flushing a range like
-	 * the VFS does.
-	 */
-	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
-	rv = gfs2_glock_nq(&gh);
-	if (rv)
-		goto out_uninit;
-	rv = gfs2_ok_for_dio(ip, offset);
-	if (rv != 1)
-		goto out; /* dio not valid, fall back to buffered i/o */
-
-	/*
-	 * Now since we are holding a deferred (CW) lock at this point, you
-	 * might be wondering why this is ever needed. There is a case however
-	 * where we've granted a deferred local lock against a cached exclusive
-	 * glock. That is ok provided all granted local locks are deferred, but
-	 * it also means that it is possible to encounter pages which are
-	 * cached and possibly also mapped. So here we check for that and sort
-	 * them out ahead of the dio. The glock state machine will take care of
-	 * everything else.
-	 *
-	 * If in fact the cached glock state (gl->gl_state) is deferred (CW) in
-	 * the first place, mapping->nr_pages will always be zero.
-	 */
-	if (mapping->nrpages) {
-		loff_t lstart = offset & ~(PAGE_SIZE - 1);
-		loff_t len = iov_iter_count(iter);
-		loff_t end = PAGE_ALIGN(offset + len) - 1;
-
-		rv = 0;
-		if (len == 0)
-			goto out;
-		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
-			unmap_shared_mapping_range(ip->i_inode.i_mapping, offset, len);
-		rv = filemap_write_and_wait_range(mapping, lstart, end);
-		if (rv)
-			goto out;
-		if (iov_iter_rw(iter) == WRITE)
-			truncate_inode_pages_range(mapping, lstart, end);
-	}
-
-	rv = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
-				  gfs2_get_block_direct, NULL, NULL, 0);
-out:
-	gfs2_glock_dq(&gh);
-out_uninit:
-	gfs2_holder_uninit(&gh);
-	return rv;
-}
-
 /**
  * gfs2_releasepage - free the metadata associated with a page
  * @page: the page that's being released
@@ -1194,7 +1098,7 @@ static const struct address_space_operations gfs2_writeback_aops = {
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,
 	.releasepage = gfs2_releasepage,
-	.direct_IO = gfs2_direct_IO,
+	.direct_IO = noop_direct_IO,
 	.migratepage = buffer_migrate_page,
 	.is_partially_uptodate = block_is_partially_uptodate,
 	.error_remove_page = generic_error_remove_page,
@@ -1211,7 +1115,7 @@ static const struct address_space_operations gfs2_ordered_aops = {
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,
 	.releasepage = gfs2_releasepage,
-	.direct_IO = gfs2_direct_IO,
+	.direct_IO = noop_direct_IO,
 	.migratepage = buffer_migrate_page,
 	.is_partially_uptodate = block_is_partially_uptodate,
 	.error_remove_page = generic_error_remove_page,
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 8b5876e19ecf..29391090d5b7 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -915,6 +915,9 @@ do_alloc:
 	} else if (flags & IOMAP_WRITE) {
 		u64 alloc_size;
 
+		if (flags & IOMAP_DIRECT)
+			goto out;  /* (see gfs2_file_direct_write) */
+
 		len = gfs2_alloc_size(inode, mp, len);
 		alloc_size = len << inode->i_blkbits;
 		if (alloc_size < iomap->length)
@@ -1082,11 +1085,18 @@ static int gfs2_iomap_begin(struct inode *inode, loff_t pos, loff_t length,
 	int ret;
 
 	trace_gfs2_iomap_start(ip, pos, length, flags);
-	if (flags & IOMAP_WRITE) {
+	if ((flags & IOMAP_WRITE) && !(flags & IOMAP_DIRECT)) {
 		ret = gfs2_iomap_begin_write(inode, pos, length, flags, iomap);
 	} else {
 		ret = gfs2_iomap_get(inode, pos, length, flags, iomap, &mp);
 		release_metapath(&mp);
+		/*
+		 * Silently fall back to buffered I/O for stuffed files or if
+		 * we've hot a hole (see gfs2_file_direct_write).
+		 */
+		if ((flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT) &&
+		    iomap->type != IOMAP_MAPPED)
+			ret = -ENOTBLK;
 	}
 	trace_gfs2_iomap_end(ip, iomap, ret);
 	return ret;
@@ -1100,7 +1110,7 @@ static int gfs2_iomap_end(struct inode *inode, loff_t pos, loff_t length,
 	struct gfs2_trans *tr = current->journal_info;
 	struct buffer_head *dibh = iomap->private;
 
-	if (!(flags & IOMAP_WRITE))
+	if ((flags & (IOMAP_WRITE | IOMAP_DIRECT)) != IOMAP_WRITE)
 		goto out;
 
 	if (iomap->type != IOMAP_INLINE) {
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 16dd395479a5..89280515169e 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -690,6 +690,85 @@ static int gfs2_fsync(struct file *file, loff_t start, loff_t end,
 	return ret ? ret : ret1;
 }
 
+static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
+	size_t count = iov_iter_count(to);
+	struct gfs2_holder gh;
+	ssize_t ret;
+
+	if (!count)
+		return 0; /* skip atime */
+
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out_uninit;
+
+	/* fall back to buffered I/O for stuffed files */
+	ret = -ENOTBLK;
+	if (gfs2_is_stuffed(ip))
+		goto out;
+
+	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL);
+
+out:
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static ssize_t gfs2_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct inode *inode = file->f_mapping->host;
+	struct gfs2_inode *ip = GFS2_I(inode);
+	size_t len = iov_iter_count(from);
+	loff_t offset = iocb->ki_pos;
+	struct gfs2_holder gh;
+	ssize_t ret;
+
+	/*
+	 * Deferred lock, even if its a write, since we do no allocation on
+	 * this path. All we need to change is the atime, and this lock mode
+	 * ensures that other nodes have flushed their buffered read caches
+	 * (i.e. their page cache entries for this inode). We do not,
+	 * unfortunately, have the option of only flushing a range like the
+	 * VFS does.
+	 */
+	gfs2_holder_init(ip->i_gl, LM_ST_DEFERRED, 0, &gh);
+	ret = gfs2_glock_nq(&gh);
+	if (ret)
+		goto out_uninit;
+
+	/* Silently fall back to buffered I/O when writing beyond EOF */
+	if (offset + len > i_size_read(&ip->i_inode))
+		goto out;
+
+	ret = iomap_dio_rw(iocb, from, &gfs2_iomap_ops, NULL);
+
+out:
+	gfs2_glock_dq(&gh);
+out_uninit:
+	gfs2_holder_uninit(&gh);
+	return ret;
+}
+
+static ssize_t gfs2_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	ssize_t ret;
+
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		ret = gfs2_file_direct_read(iocb, to);
+		if (likely(ret != -ENOTBLK))
+			return ret;
+		iocb->ki_flags &= ~IOCB_DIRECT;
+	}
+	return generic_file_read_iter(iocb, to);
+}
+
 /**
  * gfs2_file_write_iter - Perform a write to a file
  * @iocb: The io context
@@ -707,7 +786,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct gfs2_inode *ip = GFS2_I(inode);
-	ssize_t ret;
+	ssize_t written = 0, ret;
 
 	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
@@ -724,9 +803,6 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		gfs2_glock_dq_uninit(&gh);
 	}
 
-	if (iocb->ki_flags & IOCB_DIRECT)
-		return generic_file_write_iter(iocb, from);
-
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret <= 0)
@@ -743,19 +819,55 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out2;
 
-	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+	if (iocb->ki_flags & IOCB_DIRECT) {
+		struct address_space *mapping = file->f_mapping;
+		loff_t pos, endbyte;
+		ssize_t buffered;
+
+		written = gfs2_file_direct_write(iocb, from);
+		if (written < 0 || !iov_iter_count(from))
+			goto out2;
+
+		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+		if (unlikely(ret < 0))
+			goto out2;
+		buffered = ret;
+
+		/*
+		 * We need to ensure that the page cache pages are written to
+		 * disk and invalidated to preserve the expected O_DIRECT
+		 * semantics.
+		 */
+		pos = iocb->ki_pos;
+		endbyte = pos + buffered - 1;
+		ret = filemap_write_and_wait_range(mapping, pos, endbyte);
+		if (!ret) {
+			iocb->ki_pos += buffered;
+			written += buffered;
+			invalidate_mapping_pages(mapping,
+						 pos >> PAGE_SHIFT,
+						 endbyte >> PAGE_SHIFT);
+		} else {
+			/*
+			 * We don't know how much we wrote, so just return
+			 * the number of bytes which were direct-written
+			 */
+		}
+	} else {
+		ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops);
+		if (likely(ret > 0))
+			iocb->ki_pos += ret;
+	}
 
 out2:
 	current->backing_dev_info = NULL;
 out:
 	inode_unlock(inode);
 	if (likely(ret > 0)) {
-		iocb->ki_pos += ret;
-
 		/* Handle various SYNC-type writes */
 		ret = generic_write_sync(iocb, ret);
 	}
-	return ret;
+	return written ? written : ret;
 }
 
 static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
@@ -1157,7 +1269,7 @@ static int gfs2_flock(struct file *file, int cmd, struct file_lock *fl)
 
 const struct file_operations gfs2_file_fops = {
 	.llseek		= gfs2_llseek,
-	.read_iter	= generic_file_read_iter,
+	.read_iter	= gfs2_file_read_iter,
 	.write_iter	= gfs2_file_write_iter,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
@@ -1187,7 +1299,7 @@ const struct file_operations gfs2_dir_fops = {
 
 const struct file_operations gfs2_file_fops_nolock = {
 	.llseek		= gfs2_llseek,
-	.read_iter	= generic_file_read_iter,
+	.read_iter	= gfs2_file_read_iter,
 	.write_iter	= gfs2_file_write_iter,
 	.unlocked_ioctl	= gfs2_ioctl,
 	.mmap		= gfs2_mmap,
-- 
cgit v1.2.3


From 025d0e7f73c6a9cc3ca2fe7de821792a8f3269bf Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Mon, 19 Mar 2018 23:10:52 +0000
Subject: gfs2: Remove gfs2_write_{begin,end}

Now that generic_file_write_iter is no longer used, there are no
remaining users of these address space operations.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/aops.c | 213 ---------------------------------------------------------
 1 file changed, 213 deletions(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 1054cc4a96db..cc80fd71f3dd 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -639,135 +639,6 @@ out_uninit:
 	return ret;
 }
 
-/**
- * gfs2_write_begin - Begin to write to a file
- * @file: The file to write to
- * @mapping: The mapping in which to write
- * @pos: The file offset at which to start writing
- * @len: Length of the write
- * @flags: Various flags
- * @pagep: Pointer to return the page
- * @fsdata: Pointer to return fs data (unused by GFS2)
- *
- * Returns: errno
- */
-
-static int gfs2_write_begin(struct file *file, struct address_space *mapping,
-			    loff_t pos, unsigned len, unsigned flags,
-			    struct page **pagep, void **fsdata)
-{
-	struct gfs2_inode *ip = GFS2_I(mapping->host);
-	struct gfs2_sbd *sdp = GFS2_SB(mapping->host);
-	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
-	unsigned int data_blocks = 0, ind_blocks = 0, rblocks;
-	unsigned requested = 0;
-	int alloc_required;
-	int error = 0;
-	pgoff_t index = pos >> PAGE_SHIFT;
-	unsigned from = pos & (PAGE_SIZE - 1);
-	struct page *page;
-
-	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
-	error = gfs2_glock_nq(&ip->i_gh);
-	if (unlikely(error))
-		goto out_uninit;
-	if (&ip->i_inode == sdp->sd_rindex) {
-		error = gfs2_glock_nq_init(m_ip->i_gl, LM_ST_EXCLUSIVE,
-					   GL_NOCACHE, &m_ip->i_gh);
-		if (unlikely(error)) {
-			gfs2_glock_dq(&ip->i_gh);
-			goto out_uninit;
-		}
-	}
-
-	alloc_required = gfs2_write_alloc_required(ip, pos, len);
-
-	if (alloc_required || gfs2_is_jdata(ip))
-		gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
-
-	if (alloc_required) {
-		struct gfs2_alloc_parms ap = { .aflags = 0, };
-		requested = data_blocks + ind_blocks;
-		ap.target = requested;
-		error = gfs2_quota_lock_check(ip, &ap);
-		if (error)
-			goto out_unlock;
-
-		error = gfs2_inplace_reserve(ip, &ap);
-		if (error)
-			goto out_qunlock;
-	}
-
-	rblocks = RES_DINODE + ind_blocks;
-	if (gfs2_is_jdata(ip))
-		rblocks += data_blocks ? data_blocks : 1;
-	if (ind_blocks || data_blocks)
-		rblocks += RES_STATFS + RES_QUOTA;
-	if (&ip->i_inode == sdp->sd_rindex)
-		rblocks += 2 * RES_STATFS;
-	if (alloc_required)
-		rblocks += gfs2_rg_blocks(ip, requested);
-
-	error = gfs2_trans_begin(sdp, rblocks,
-				 PAGE_SIZE/sdp->sd_sb.sb_bsize);
-	if (error)
-		goto out_trans_fail;
-
-	error = -ENOMEM;
-	flags |= AOP_FLAG_NOFS;
-	page = grab_cache_page_write_begin(mapping, index, flags);
-	*pagep = page;
-	if (unlikely(!page))
-		goto out_endtrans;
-
-	if (gfs2_is_stuffed(ip)) {
-		error = 0;
-		if (pos + len > gfs2_max_stuffed_size(ip)) {
-			error = gfs2_unstuff_dinode(ip, page);
-			if (error == 0)
-				goto prepare_write;
-		} else if (!PageUptodate(page)) {
-			error = stuffed_readpage(ip, page);
-		}
-		goto out;
-	}
-
-prepare_write:
-	error = __block_write_begin(page, from, len, gfs2_block_map);
-out:
-	if (error == 0)
-		return 0;
-
-	unlock_page(page);
-	put_page(page);
-
-	gfs2_trans_end(sdp);
-	if (alloc_required) {
-		gfs2_inplace_release(ip);
-		if (pos + len > ip->i_inode.i_size)
-			gfs2_trim_blocks(&ip->i_inode);
-	}
-	goto out_qunlock;
-
-out_endtrans:
-	gfs2_trans_end(sdp);
-out_trans_fail:
-	if (alloc_required)
-		gfs2_inplace_release(ip);
-out_qunlock:
-	if (alloc_required)
-		gfs2_quota_unlock(ip);
-out_unlock:
-	if (&ip->i_inode == sdp->sd_rindex) {
-		gfs2_glock_dq(&m_ip->i_gh);
-		gfs2_holder_uninit(&m_ip->i_gh);
-	}
-	gfs2_glock_dq(&ip->i_gh);
-out_uninit:
-	gfs2_holder_uninit(&ip->i_gh);
-	return error;
-}
-
 /**
  * adjust_fs_space - Adjusts the free space available due to gfs2_grow
  * @inode: the rindex inode
@@ -848,84 +719,6 @@ int gfs2_stuffed_write_end(struct inode *inode, struct buffer_head *dibh,
 	return copied;
 }
 
-/**
- * gfs2_write_end
- * @file: The file to write to
- * @mapping: The address space to write to
- * @pos: The file position
- * @len: The length of the data
- * @copied: How much was actually copied by the VFS
- * @page: The page that has been written
- * @fsdata: The fsdata (unused in GFS2)
- *
- * The main write_end function for GFS2. We just put our locking around the VFS
- * provided functions.
- *
- * Returns: copied bytes or errno
- */
-
-static int gfs2_write_end(struct file *file, struct address_space *mapping,
-			  loff_t pos, unsigned len, unsigned copied,
-			  struct page *page, void *fsdata)
-{
-	struct inode *inode = page->mapping->host;
-	struct gfs2_inode *ip = GFS2_I(inode);
-	struct gfs2_sbd *sdp = GFS2_SB(inode);
-	struct gfs2_inode *m_ip = GFS2_I(sdp->sd_statfs_inode);
-	struct buffer_head *dibh;
-	int ret;
-	struct gfs2_trans *tr = current->journal_info;
-	BUG_ON(!tr);
-
-	BUG_ON(gfs2_glock_is_locked_by_me(ip->i_gl) == NULL);
-
-	ret = gfs2_meta_inode_buffer(ip, &dibh);
-	if (unlikely(ret))
-		goto out;
-
-	if (gfs2_is_stuffed(ip)) {
-		ret = gfs2_stuffed_write_end(inode, dibh, pos, copied, page);
-		page = NULL;
-		goto out2;
-	}
-
-	if (gfs2_is_jdata(ip))
-		gfs2_page_add_databufs(ip, page, pos & ~PAGE_MASK, len);
-	else
-		gfs2_ordered_add_inode(ip);
-
-	ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata);
-	page = NULL;
-	if (tr->tr_num_buf_new)
-		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-	else
-		gfs2_trans_add_meta(ip->i_gl, dibh);
-
-out2:
-	if (inode == sdp->sd_rindex) {
-		adjust_fs_space(inode);
-		sdp->sd_rindex_uptodate = 0;
-	}
-
-	brelse(dibh);
-out:
-	if (page) {
-		unlock_page(page);
-		put_page(page);
-	}
-	gfs2_trans_end(sdp);
-	gfs2_inplace_release(ip);
-	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
-		gfs2_quota_unlock(ip);
-	if (inode == sdp->sd_rindex) {
-		gfs2_glock_dq(&m_ip->i_gh);
-		gfs2_holder_uninit(&m_ip->i_gh);
-	}
-	gfs2_glock_dq(&ip->i_gh);
-	gfs2_holder_uninit(&ip->i_gh);
-	return ret;
-}
-
 /**
  * jdata_set_page_dirty - Page dirtying function
  * @page: The page to dirty
@@ -1093,8 +886,6 @@ static const struct address_space_operations gfs2_writeback_aops = {
 	.writepages = gfs2_writepages,
 	.readpage = gfs2_readpage,
 	.readpages = gfs2_readpages,
-	.write_begin = gfs2_write_begin,
-	.write_end = gfs2_write_end,
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,
 	.releasepage = gfs2_releasepage,
@@ -1109,8 +900,6 @@ static const struct address_space_operations gfs2_ordered_aops = {
 	.writepages = gfs2_writepages,
 	.readpage = gfs2_readpage,
 	.readpages = gfs2_readpages,
-	.write_begin = gfs2_write_begin,
-	.write_end = gfs2_write_end,
 	.set_page_dirty = __set_page_dirty_buffers,
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,
@@ -1126,8 +915,6 @@ static const struct address_space_operations gfs2_jdata_aops = {
 	.writepages = gfs2_jdata_writepages,
 	.readpage = gfs2_readpage,
 	.readpages = gfs2_readpages,
-	.write_begin = gfs2_write_begin,
-	.write_end = gfs2_write_end,
 	.set_page_dirty = jdata_set_page_dirty,
 	.bmap = gfs2_bmap,
 	.invalidatepage = gfs2_invalidatepage,
-- 
cgit v1.2.3


From e35a2f9aee31fb9e85ebbf4820481ce3f5e94db2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 23:41:44 +0300
Subject: drm/atomic-helper: Use old/new state in
 drm_atomic_helper_commit_planes_on_crtc()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Update drm_atomic_helper_commit_planes_on_crtc() to use explicit old/new
states instead of relying on obj->state.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626204144.14769-1-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_atomic_helper.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 17baf5057132..4f487ceffe68 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2342,11 +2342,13 @@ drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_state)
 	const struct drm_crtc_helper_funcs *crtc_funcs;
 	struct drm_crtc *crtc = old_crtc_state->crtc;
 	struct drm_atomic_state *old_state = old_crtc_state->state;
+	struct drm_crtc_state *new_crtc_state =
+		drm_atomic_get_new_crtc_state(old_state, crtc);
 	struct drm_plane *plane;
 	unsigned plane_mask;
 
 	plane_mask = old_crtc_state->plane_mask;
-	plane_mask |= crtc->state->plane_mask;
+	plane_mask |= new_crtc_state->plane_mask;
 
 	crtc_funcs = crtc->helper_private;
 	if (crtc_funcs && crtc_funcs->atomic_begin)
@@ -2355,6 +2357,8 @@ drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_state)
 	drm_for_each_plane_mask(plane, crtc->dev, plane_mask) {
 		struct drm_plane_state *old_plane_state =
 			drm_atomic_get_old_plane_state(old_state, plane);
+		struct drm_plane_state *new_plane_state =
+			drm_atomic_get_new_plane_state(old_state, plane);
 		const struct drm_plane_helper_funcs *plane_funcs;
 
 		plane_funcs = plane->helper_private;
@@ -2362,13 +2366,14 @@ drm_atomic_helper_commit_planes_on_crtc(struct drm_crtc_state *old_crtc_state)
 		if (!old_plane_state || !plane_funcs)
 			continue;
 
-		WARN_ON(plane->state->crtc && plane->state->crtc != crtc);
+		WARN_ON(new_plane_state->crtc &&
+			new_plane_state->crtc != crtc);
 
-		if (drm_atomic_plane_disabling(old_plane_state, plane->state) &&
+		if (drm_atomic_plane_disabling(old_plane_state, new_plane_state) &&
 		    plane_funcs->atomic_disable)
 			plane_funcs->atomic_disable(plane, old_plane_state);
-		else if (plane->state->crtc ||
-			 drm_atomic_plane_disabling(old_plane_state, plane->state))
+		else if (new_plane_state->crtc ||
+			 drm_atomic_plane_disabling(old_plane_state, new_plane_state))
 			plane_funcs->atomic_update(plane, old_plane_state);
 	}
 
-- 
cgit v1.2.3


From 62f77ad0969594ee428043523bf28329df191b39 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:07 +0300
Subject: drm: Add drm_plane_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add drm_plane_mask() which returns the 1<<index for the plane.
We already have an identical drm_crtc_mask() for crtcs.

Mostly performed with coccinelle:
@@
@@
- (1<<drm_plane_index(
+ drm_plane_mask(
  ...)
-  )

@@
@@
- 1<<drm_plane_index(
+ drm_plane_mask(
  ...)

@@
@@
- BIT(drm_plane_index(
+ drm_plane_mask(
  ...)
- )

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-1-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/drm_atomic.c            |  4 ++--
 drivers/gpu/drm/drm_framebuffer.c       |  2 +-
 drivers/gpu/drm/drm_simple_kms_helper.c |  2 +-
 include/drm/drm_plane.h                 | 14 ++++++++++++--
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 178842380f75..684c9d3a1d6c 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1581,7 +1581,7 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state,
 		if (WARN_ON(IS_ERR(crtc_state)))
 			return PTR_ERR(crtc_state);
 
-		crtc_state->plane_mask &= ~(1 << drm_plane_index(plane));
+		crtc_state->plane_mask &= ~drm_plane_mask(plane);
 	}
 
 	plane_state->crtc = crtc;
@@ -1591,7 +1591,7 @@ drm_atomic_set_crtc_for_plane(struct drm_plane_state *plane_state,
 						       crtc);
 		if (IS_ERR(crtc_state))
 			return PTR_ERR(crtc_state);
-		crtc_state->plane_mask |= (1 << drm_plane_index(plane));
+		crtc_state->plane_mask |= drm_plane_mask(plane);
 	}
 
 	if (crtc)
diff --git a/drivers/gpu/drm/drm_framebuffer.c b/drivers/gpu/drm/drm_framebuffer.c
index ed90974a452a..781af1d42d76 100644
--- a/drivers/gpu/drm/drm_framebuffer.c
+++ b/drivers/gpu/drm/drm_framebuffer.c
@@ -847,7 +847,7 @@ retry:
 		if (ret)
 			goto unlock;
 
-		plane_mask |= BIT(drm_plane_index(plane));
+		plane_mask |= drm_plane_mask(plane);
 	}
 
 	/* This list is only filled when disable_crtcs is set. */
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index 7a00455ca568..9d87961da1db 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -52,7 +52,7 @@ static int drm_simple_kms_crtc_check(struct drm_crtc *crtc,
 				     struct drm_crtc_state *state)
 {
 	bool has_primary = state->plane_mask &
-			   BIT(drm_plane_index(crtc->primary));
+			   drm_plane_mask(crtc->primary);
 
 	/* We always want to have an active plane with an active CRTC */
 	if (has_primary != state->enable)
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 7d4d6c7f0afd..cee9dfaaa740 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -639,10 +639,20 @@ void drm_plane_cleanup(struct drm_plane *plane);
  * Given a registered plane, return the index of that plane within a DRM
  * device's list of planes.
  */
-static inline unsigned int drm_plane_index(struct drm_plane *plane)
+static inline unsigned int drm_plane_index(const struct drm_plane *plane)
 {
 	return plane->index;
 }
+
+/**
+ * drm_plane_mask - find the mask of a registered plane
+ * @plane: plane to find mask for
+ */
+static inline u32 drm_plane_mask(const struct drm_plane *plane)
+{
+	return 1 << drm_plane_index(plane);
+}
+
 struct drm_plane * drm_plane_from_index(struct drm_device *dev, int idx);
 void drm_plane_force_disable(struct drm_plane *plane);
 
@@ -678,7 +688,7 @@ static inline struct drm_plane *drm_plane_find(struct drm_device *dev,
  */
 #define drm_for_each_plane_mask(plane, dev, plane_mask) \
 	list_for_each_entry((plane), &(dev)->mode_config.plane_list, head) \
-		for_each_if ((plane_mask) & (1 << drm_plane_index(plane)))
+		for_each_if ((plane_mask) & drm_plane_mask(plane))
 
 /**
  * drm_for_each_legacy_plane - iterate over all planes for legacy userspace
-- 
cgit v1.2.3


From 6a52193bd0dd683607793bea0caf6be94b32b333 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:08 +0300
Subject: drm: Use drm_crtc_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_crtc_mask() where appropriate.

Mostly performed with coccinelle:
@@
@@
- (1<<drm_crtc_index(
+ drm_crtc_mask(
  ...)
-  )

@@
@@
- 1<<drm_crtc_index(
+ drm_crtc_mask(
  ...)

@@
@@
- BIT(drm_crtc_index(
+ drm_crtc_mask(
  ...)
- )

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-2-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/drm_crtc.c              | 4 ++--
 drivers/gpu/drm/drm_simple_kms_helper.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index f45e7a8d4acd..c762e75a2d94 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -329,9 +329,9 @@ int drm_crtc_init_with_planes(struct drm_device *dev, struct drm_crtc *crtc,
 	crtc->primary = primary;
 	crtc->cursor = cursor;
 	if (primary && !primary->possible_crtcs)
-		primary->possible_crtcs = 1 << drm_crtc_index(crtc);
+		primary->possible_crtcs = drm_crtc_mask(crtc);
 	if (cursor && !cursor->possible_crtcs)
-		cursor->possible_crtcs = 1 << drm_crtc_index(crtc);
+		cursor->possible_crtcs = drm_crtc_mask(crtc);
 
 	ret = drm_crtc_crc_init(crtc);
 	if (ret) {
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index 9d87961da1db..b72fcf1e9605 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -281,7 +281,7 @@ int drm_simple_display_pipe_init(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	encoder->possible_crtcs = 1 << drm_crtc_index(crtc);
+	encoder->possible_crtcs = drm_crtc_mask(crtc);
 	ret = drm_encoder_init(dev, encoder, &drm_simple_kms_encoder_funcs,
 			       DRM_MODE_ENCODER_NONE, NULL);
 	if (ret || !connector)
-- 
cgit v1.2.3


From 6f3be036da5cf6b192966ebea250cf9c8b1fd4a0 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:09 +0300
Subject: drm: Add drm_encoder_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add drm_encoder_mask() which returns the 1<<index for the encoder.
We already have an identical drm_crtc_mask() for crtcs.

Mostly performed with coccinelle:
@@
@@
- (1<<drm_encoder_index(
+ drm_encoder_mask(
  ...)
-  )

@@
@@
- 1<<drm_encoder_index(
+ drm_encoder_mask(
  ...)

@@
@@
- BIT(drm_encoder_index(
+ drm_encoder_mask(
  ...)
- )

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-3-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/drm_atomic_helper.c | 10 +++++-----
 include/drm/drm_encoder.h           | 16 ++++++++++++++--
 2 files changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 4f487ceffe68..8008a7de2e10 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -121,7 +121,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 			new_encoder = drm_atomic_helper_best_encoder(connector);
 
 		if (new_encoder) {
-			if (encoder_mask & (1 << drm_encoder_index(new_encoder))) {
+			if (encoder_mask & drm_encoder_mask(new_encoder)) {
 				DRM_DEBUG_ATOMIC("[ENCODER:%d:%s] on [CONNECTOR:%d:%s] already assigned\n",
 					new_encoder->base.id, new_encoder->name,
 					connector->base.id, connector->name);
@@ -129,7 +129,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 				return -EINVAL;
 			}
 
-			encoder_mask |= 1 << drm_encoder_index(new_encoder);
+			encoder_mask |= drm_encoder_mask(new_encoder);
 		}
 	}
 
@@ -155,7 +155,7 @@ static int handle_conflicting_encoders(struct drm_atomic_state *state,
 			continue;
 
 		encoder = connector->state->best_encoder;
-		if (!encoder || !(encoder_mask & (1 << drm_encoder_index(encoder))))
+		if (!encoder || !(encoder_mask & drm_encoder_mask(encoder)))
 			continue;
 
 		if (!disable_conflicting_encoders) {
@@ -223,7 +223,7 @@ set_best_encoder(struct drm_atomic_state *state,
 			crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 
 			crtc_state->encoder_mask &=
-				~(1 << drm_encoder_index(conn_state->best_encoder));
+				~drm_encoder_mask(conn_state->best_encoder);
 		}
 	}
 
@@ -234,7 +234,7 @@ set_best_encoder(struct drm_atomic_state *state,
 			crtc_state = drm_atomic_get_new_crtc_state(state, crtc);
 
 			crtc_state->encoder_mask |=
-				1 << drm_encoder_index(encoder);
+				drm_encoder_mask(encoder);
 		}
 	}
 
diff --git a/include/drm/drm_encoder.h b/include/drm/drm_encoder.h
index fb299696c7c4..4f597c0730b4 100644
--- a/include/drm/drm_encoder.h
+++ b/include/drm/drm_encoder.h
@@ -191,11 +191,23 @@ int drm_encoder_init(struct drm_device *dev,
  * Given a registered encoder, return the index of that encoder within a DRM
  * device's list of encoders.
  */
-static inline unsigned int drm_encoder_index(struct drm_encoder *encoder)
+static inline unsigned int drm_encoder_index(const struct drm_encoder *encoder)
 {
 	return encoder->index;
 }
 
+/**
+ * drm_encoder_mask - find the mask of a registered ENCODER
+ * @encoder: encoder to find mask for
+ *
+ * Given a registered encoder, return the mask bit of that encoder for an
+ * encoder's possible_clones field.
+ */
+static inline u32 drm_encoder_mask(const struct drm_encoder *encoder)
+{
+	return 1 << drm_encoder_index(encoder);
+}
+
 /**
  * drm_encoder_crtc_ok - can a given crtc drive a given encoder?
  * @encoder: encoder to test
@@ -241,7 +253,7 @@ void drm_encoder_cleanup(struct drm_encoder *encoder);
  */
 #define drm_for_each_encoder_mask(encoder, dev, encoder_mask) \
 	list_for_each_entry((encoder), &(dev)->mode_config.encoder_list, head) \
-		for_each_if ((encoder_mask) & (1 << drm_encoder_index(encoder)))
+		for_each_if ((encoder_mask) & drm_encoder_mask(encoder))
 
 /**
  * drm_for_each_encoder - iterate over all encoders
-- 
cgit v1.2.3


From 737057321f3c2d30b98fa8006b7af1869c32a68b Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:10 +0300
Subject: drm: Add drm_connector_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add drm_connector_mask() which returns the 1<<index for the connector.
We already have an identical drm_crtc_mask() for crtcs.

Mostly performed with coccinelle:
@@
@@
- (1<<drm_connector_index(
+ drm_connector_mask(
  ...)
-  )

@@
@@
- 1<<drm_connector_index(
+ drm_connector_mask(
  ...)

@@
@@
- BIT(drm_connector_index(
+ drm_connector_mask(
  ...)
- )

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-4-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/drm_atomic.c | 6 +++---
 include/drm/drm_connector.h  | 8 +++++++-
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 684c9d3a1d6c..d5cefb1cb2a2 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1700,7 +1700,7 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 							   conn_state->crtc);
 
 		crtc_state->connector_mask &=
-			~(1 << drm_connector_index(conn_state->connector));
+			~drm_connector_mask(conn_state->connector);
 
 		drm_connector_put(conn_state->connector);
 		conn_state->crtc = NULL;
@@ -1712,7 +1712,7 @@ drm_atomic_set_crtc_for_connector(struct drm_connector_state *conn_state,
 			return PTR_ERR(crtc_state);
 
 		crtc_state->connector_mask |=
-			1 << drm_connector_index(conn_state->connector);
+			drm_connector_mask(conn_state->connector);
 
 		drm_connector_get(conn_state->connector);
 		conn_state->crtc = crtc;
@@ -1839,7 +1839,7 @@ drm_atomic_add_affected_connectors(struct drm_atomic_state *state,
 	 */
 	drm_connector_list_iter_begin(state->dev, &conn_iter);
 	drm_for_each_connector_iter(connector, &conn_iter) {
-		if (!(crtc_state->connector_mask & (1 << drm_connector_index(connector))))
+		if (!(crtc_state->connector_mask & drm_connector_mask(connector)))
 			continue;
 
 		conn_state = drm_atomic_get_connector_state(state, connector);
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index 14ab58ade87f..bf0f0f0786d3 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -1030,11 +1030,17 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 				      struct drm_encoder *encoder);
 
 void drm_connector_cleanup(struct drm_connector *connector);
-static inline unsigned drm_connector_index(struct drm_connector *connector)
+
+static inline unsigned int drm_connector_index(const struct drm_connector *connector)
 {
 	return connector->index;
 }
 
+static inline u32 drm_connector_mask(const struct drm_connector *connector)
+{
+	return 1 << connector->index;
+}
+
 /**
  * drm_connector_lookup - lookup connector object
  * @dev: DRM device
-- 
cgit v1.2.3


From 40560e26dc45e53ae05cce61804a31367f36a5e6 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:11 +0300
Subject: drm/i915: Use drm_plane_mask() & co.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_{plane,crtc,encoder,connector}_mask() where appropriate.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-5-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/intel_display.c  | 14 +++++++-------
 drivers/gpu/drm/i915/intel_display.h  |  4 ++--
 drivers/gpu/drm/i915/intel_dpll_mgr.c |  6 +++---
 3 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 2c8fef3ede54..694a4703042f 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -2756,10 +2756,10 @@ intel_set_plane_visible(struct intel_crtc_state *crtc_state,
 
 	/* FIXME pre-g4x don't work like this */
 	if (visible) {
-		crtc_state->base.plane_mask |= BIT(drm_plane_index(&plane->base));
+		crtc_state->base.plane_mask |= drm_plane_mask(&plane->base);
 		crtc_state->active_planes |= BIT(plane->id);
 	} else {
-		crtc_state->base.plane_mask &= ~BIT(drm_plane_index(&plane->base));
+		crtc_state->base.plane_mask &= ~drm_plane_mask(&plane->base);
 		crtc_state->active_planes &= ~BIT(plane->id);
 	}
 
@@ -11884,7 +11884,7 @@ verify_single_dpll_state(struct drm_i915_private *dev_priv,
 			 struct drm_crtc_state *new_state)
 {
 	struct intel_dpll_hw_state dpll_hw_state;
-	unsigned crtc_mask;
+	unsigned int crtc_mask;
 	bool active;
 
 	memset(&dpll_hw_state, 0, sizeof(dpll_hw_state));
@@ -11911,7 +11911,7 @@ verify_single_dpll_state(struct drm_i915_private *dev_priv,
 		return;
 	}
 
-	crtc_mask = 1 << drm_crtc_index(crtc);
+	crtc_mask = drm_crtc_mask(crtc);
 
 	if (new_state->active)
 		I915_STATE_WARN(!(pll->active_mask & crtc_mask),
@@ -11946,7 +11946,7 @@ verify_shared_dpll_state(struct drm_device *dev, struct drm_crtc *crtc,
 
 	if (old_state->shared_dpll &&
 	    old_state->shared_dpll != new_state->shared_dpll) {
-		unsigned crtc_mask = 1 << drm_crtc_index(crtc);
+		unsigned int crtc_mask = drm_crtc_mask(crtc);
 		struct intel_shared_dpll *pll = old_state->shared_dpll;
 
 		I915_STATE_WARN(pll->active_mask & crtc_mask,
@@ -15608,9 +15608,9 @@ static void intel_modeset_readout_hw_state(struct drm_device *dev)
 				 * rely on the connector_mask being accurate.
 				 */
 				encoder->base.crtc->state->connector_mask |=
-					1 << drm_connector_index(&connector->base);
+					drm_connector_mask(&connector->base);
 				encoder->base.crtc->state->encoder_mask |=
-					1 << drm_encoder_index(&encoder->base);
+					drm_encoder_mask(&encoder->base);
 			}
 
 		} else {
diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index dfb02da73ac8..dd30cae5eb00 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -261,7 +261,7 @@ struct intel_link_m_n {
 			    &(dev)->mode_config.plane_list,		\
 			    base.head)					\
 		for_each_if((plane_mask) &				\
-			    BIT(drm_plane_index(&intel_plane->base)))
+			    drm_plane_mask(&intel_plane->base)))
 
 #define for_each_intel_plane_on_crtc(dev, intel_crtc, intel_plane)	\
 	list_for_each_entry(intel_plane,				\
@@ -278,7 +278,7 @@ struct intel_link_m_n {
 	list_for_each_entry(intel_crtc,					\
 			    &(dev)->mode_config.crtc_list,		\
 			    base.head)					\
-		for_each_if((crtc_mask) & BIT(drm_crtc_index(&intel_crtc->base)))
+		for_each_if((crtc_mask) & drm_crtc_mask(&intel_crtc->base))
 
 #define for_each_intel_encoder(dev, intel_encoder)		\
 	list_for_each_entry(intel_encoder,			\
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 132fe63e042a..156f8e4cbe4c 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -163,8 +163,8 @@ void intel_enable_shared_dpll(struct intel_crtc *crtc)
 	struct drm_device *dev = crtc->base.dev;
 	struct drm_i915_private *dev_priv = to_i915(dev);
 	struct intel_shared_dpll *pll = crtc->config->shared_dpll;
-	unsigned crtc_mask = 1 << drm_crtc_index(&crtc->base);
-	unsigned old_mask;
+	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
+	unsigned int old_mask;
 
 	if (WARN_ON(pll == NULL))
 		return;
@@ -207,7 +207,7 @@ void intel_disable_shared_dpll(struct intel_crtc *crtc)
 {
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	struct intel_shared_dpll *pll = crtc->config->shared_dpll;
-	unsigned crtc_mask = 1 << drm_crtc_index(&crtc->base);
+	unsigned int crtc_mask = drm_crtc_mask(&crtc->base);
 
 	/* PCH only available on ILK+ */
 	if (INTEL_GEN(dev_priv) < 5)
-- 
cgit v1.2.3


From 2d4569fd8d8ee13a8556ed3dd8b2cd1dc45fd8bd Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:12 +0300
Subject: drm/imx: Use drm_plane_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_plane_mask() where appropriate.

Cc: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-6-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/ipuv3-crtc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index e83af0f2be86..21d002859ae0 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -213,7 +213,7 @@ static bool ipu_crtc_mode_fixup(struct drm_crtc *crtc,
 static int ipu_crtc_atomic_check(struct drm_crtc *crtc,
 				 struct drm_crtc_state *state)
 {
-	u32 primary_plane_mask = 1 << drm_plane_index(crtc->primary);
+	u32 primary_plane_mask = drm_plane_mask(crtc->primary);
 
 	if (state->active && (primary_plane_mask & state->plane_mask) == 0)
 		return -EINVAL;
-- 
cgit v1.2.3


From dbf8f9e40e6f5fc39e2e6c4c8a392fe99189c4d2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:14 +0300
Subject: drm/sun4i: Use drm_crtc_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_crtc_mask() where appropriate.

Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-8-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Acked-by: Maxime Ripard <maxime.ripard@bootlin.com>
---
 drivers/gpu/drm/sun4i/sun4i_crtc.c | 2 +-
 drivers/gpu/drm/sun4i/sun4i_lvds.c | 2 +-
 drivers/gpu/drm/sun4i/sun4i_rgb.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_crtc.c b/drivers/gpu/drm/sun4i/sun4i_crtc.c
index 2d7c57406715..3eedf335a935 100644
--- a/drivers/gpu/drm/sun4i/sun4i_crtc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_crtc.c
@@ -242,7 +242,7 @@ struct sun4i_crtc *sun4i_crtc_init(struct drm_device *drm,
 
 	/* Set possible_crtcs to this crtc for overlay planes */
 	for (i = 0; planes[i]; i++) {
-		uint32_t possible_crtcs = BIT(drm_crtc_index(&scrtc->crtc));
+		uint32_t possible_crtcs = drm_crtc_mask(&scrtc->crtc);
 		struct drm_plane *plane = planes[i];
 
 		if (plane->type == DRM_PLANE_TYPE_OVERLAY)
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index be3f14d7746d..a69fe2e1f9d1 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -136,7 +136,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	}
 
 	/* The LVDS encoder can only work with the TCON channel 0 */
-	lvds->encoder.possible_crtcs = BIT(drm_crtc_index(&tcon->crtc->crtc));
+	lvds->encoder.possible_crtcs = drm_crtc_mask(&tcon->crtc->crtc);
 
 	if (tcon->panel) {
 		drm_connector_helper_add(&lvds->connector,
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index f2fa1f210509..96d21b07f8fc 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -202,7 +202,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 	}
 
 	/* The RGB encoder can only work with the TCON channel 0 */
-	rgb->encoder.possible_crtcs = BIT(drm_crtc_index(&tcon->crtc->crtc));
+	rgb->encoder.possible_crtcs = drm_crtc_mask(&tcon->crtc->crtc);
 
 	if (tcon->panel) {
 		drm_connector_helper_add(&rgb->connector,
-- 
cgit v1.2.3


From c0183a8eae1820173f410dada7e311295e6a8580 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:15 +0300
Subject: drm/vc4: Use drm_crtc_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_crtc_mask() where appropriate.

Cc: Eric Anholt <eric@anholt.net>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-9-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
---
 drivers/gpu/drm/vc4/vc4_crtc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index dcadf793ee80..d222358fa8a7 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -1081,7 +1081,7 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 		if (IS_ERR(plane))
 			continue;
 
-		plane->possible_crtcs = 1 << drm_crtc_index(crtc);
+		plane->possible_crtcs = drm_crtc_mask(crtc);
 	}
 
 	/* Set up the legacy cursor after overlay initialization,
@@ -1090,7 +1090,7 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 	 */
 	cursor_plane = vc4_plane_init(drm, DRM_PLANE_TYPE_CURSOR);
 	if (!IS_ERR(cursor_plane)) {
-		cursor_plane->possible_crtcs = 1 << drm_crtc_index(crtc);
+		cursor_plane->possible_crtcs = drm_crtc_mask(crtc);
 		crtc->cursor = cursor_plane;
 	}
 
@@ -1118,7 +1118,7 @@ static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 err_destroy_planes:
 	list_for_each_entry_safe(destroy_plane, temp,
 				 &drm->mode_config.plane_list, head) {
-		if (destroy_plane->possible_crtcs == 1 << drm_crtc_index(crtc))
+		if (destroy_plane->possible_crtcs == drm_crtc_mask(crtc))
 		    destroy_plane->funcs->destroy(destroy_plane);
 	}
 err:
-- 
cgit v1.2.3


From ea632725956d1dd7c4a10aa2449c672bbb22b2cb Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 26 Jun 2018 22:47:16 +0300
Subject: drm/vmwgfx: Use drm_plane_mask() & co.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_{plane,connector}_mask() where appropriate.

Cc: VMware Graphics <linux-graphics-maintainer@vmware.com>
Cc: Sinclair Yeh <syeh@vmware.com>
Cc: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626194716.12522-10-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 6317672070cd..bc5fbd39cf9a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -535,9 +535,9 @@ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc,
 			     struct drm_crtc_state *new_state)
 {
 	struct vmw_display_unit *du = vmw_crtc_to_du(new_state->crtc);
-	int connector_mask = 1 << drm_connector_index(&du->connector);
+	int connector_mask = drm_connector_mask(&du->connector);
 	bool has_primary = new_state->plane_mask &
-			   BIT(drm_plane_index(crtc->primary));
+			   drm_plane_mask(crtc->primary);
 
 	/* We always want to have an active plane with an active CRTC */
 	if (has_primary != new_state->enable)
-- 
cgit v1.2.3


From 7e7367d3bc6cf27dd7e007e7897fcebfeff1ee8b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 30 Jun 2018 10:05:09 +0100
Subject: drm/i915: Try GGTT mmapping whole object as partial

If the whole object is already pinned by HW for use as scanout, we will
fail to move it to the mappable region and so must resort to using a
partial VMA covering the whole object.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=104513
Fixes: aa136d9d72c2 ("drm/i915: Convert partial ggtt vma to full ggtt if it spans the entire object")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180630090509.469-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 28 +++++++++++++++++-----------
 drivers/gpu/drm/i915/i915_vma.c |  2 +-
 2 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 8954db6ab083..048b722cf27c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2006,7 +2006,6 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	bool write = !!(vmf->flags & FAULT_FLAG_WRITE);
 	struct i915_vma *vma;
 	pgoff_t page_offset;
-	unsigned int flags;
 	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset */
@@ -2042,27 +2041,34 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 		goto err_unlock;
 	}
 
-	/* If the object is smaller than a couple of partial vma, it is
-	 * not worth only creating a single partial vma - we may as well
-	 * clear enough space for the full object.
-	 */
-	flags = PIN_MAPPABLE;
-	if (obj->base.size > 2 * MIN_CHUNK_PAGES << PAGE_SHIFT)
-		flags |= PIN_NONBLOCK | PIN_NONFAULT;
 
 	/* Now pin it into the GTT as needed */
-	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0, flags);
+	vma = i915_gem_object_ggtt_pin(obj, NULL, 0, 0,
+				       PIN_MAPPABLE |
+				       PIN_NONBLOCK |
+				       PIN_NONFAULT);
 	if (IS_ERR(vma)) {
 		/* Use a partial view if it is bigger than available space */
 		struct i915_ggtt_view view =
 			compute_partial_view(obj, page_offset, MIN_CHUNK_PAGES);
+		unsigned int flags;
 
-		/* Userspace is now writing through an untracked VMA, abandon
+		flags = PIN_MAPPABLE;
+		if (view.type == I915_GGTT_VIEW_NORMAL)
+			flags |= PIN_NONBLOCK; /* avoid warnings for pinned */
+
+		/*
+		 * Userspace is now writing through an untracked VMA, abandon
 		 * all hope that the hardware is able to track future writes.
 		 */
 		obj->frontbuffer_ggtt_origin = ORIGIN_CPU;
 
-		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, PIN_MAPPABLE);
+		vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		if (IS_ERR(vma) && !view.type) {
+			flags = PIN_MAPPABLE;
+			view.type = I915_GGTT_VIEW_PARTIAL;
+			vma = i915_gem_object_ggtt_pin(obj, &view, 0, 0, flags);
+		}
 	}
 	if (IS_ERR(vma)) {
 		ret = PTR_ERR(vma);
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index d0e606e9b27a..de2b6d65e865 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -143,7 +143,7 @@ vma_create(struct drm_i915_gem_object *obj,
 						     obj->base.size >> PAGE_SHIFT));
 			vma->size = view->partial.size;
 			vma->size <<= PAGE_SHIFT;
-			GEM_BUG_ON(vma->size >= obj->base.size);
+			GEM_BUG_ON(vma->size > obj->base.size);
 		} else if (view->type == I915_GGTT_VIEW_ROTATED) {
 			vma->size = intel_rotation_info_size(&view->rotated);
 			vma->size <<= PAGE_SHIFT;
-- 
cgit v1.2.3


From d25c0634441ca59325f1119cbd203ecda65521b2 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:03 -0300
Subject: scripts/documentation-file-ref-check: remove some false positives

There are several false positives at tcm_mod_builder.txt:

    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000/tcm_nab5000_base.h
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../include/target/target_core_fabric_ops.h
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000/tcm_nab5000_fabric.c
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000/tcm_nab5000_fabric.h
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000/tcm_nab5000_configfs.c
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000/Kbuild
    Documentation/target/tcm_mod_builder.txt: mnt/sdb/lio-core-2.6.git/Documentation/target/../../drivers/target/tcm_nab5000/Kconfig

Ignore them.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 scripts/documentation-file-ref-check | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check
index 078999a3fdff..857eb0d7458d 100755
--- a/scripts/documentation-file-ref-check
+++ b/scripts/documentation-file-ref-check
@@ -75,6 +75,9 @@ while (<IN>) {
 		# Remove URL false-positives
 		next if ($fulref =~ m/^http/);
 
+		# Discard some build examples from Documentation/target/tcm_mod_builder.txt
+		next if ($fulref =~ m,mnt/sdb/lio-core-2.6.git/Documentation/target,);
+
 		# Check if exists, evaluating wildcards
 		next if (grep -e, glob("$ref $fulref"));
 
-- 
cgit v1.2.3


From 5d395fa63baa5cce7314ff806b81c77319432bf2 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:04 -0300
Subject: scripts/documentation-file-ref-check: ignore sched-pelt false
 positive

When Documentation/scheduler/sched-pelt.c is compiled, it generates
a file called Documentation/scheduler/sched-pelt. As this only
exists after building such tool, we need an explict check
to remove the false-positive.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 scripts/documentation-file-ref-check | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/scripts/documentation-file-ref-check b/scripts/documentation-file-ref-check
index 857eb0d7458d..ad9db6821824 100755
--- a/scripts/documentation-file-ref-check
+++ b/scripts/documentation-file-ref-check
@@ -75,6 +75,9 @@ while (<IN>) {
 		# Remove URL false-positives
 		next if ($fulref =~ m/^http/);
 
+		# Remove sched-pelt false-positive
+		next if ($fulref =~ m,^Documentation/scheduler/sched-pelt$,);
+
 		# Discard some build examples from Documentation/target/tcm_mod_builder.txt
 		next if ($fulref =~ m,mnt/sdb/lio-core-2.6.git/Documentation/target,);
 
-- 
cgit v1.2.3


From 1d1636e32e69961ed42ee043ef6b75c26d327599 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:05 -0300
Subject: docs: zh_CN: fix location of oops-tracing.txt

This file was merged with bug-hunting. Make the translation
to point for its new location.

Fixes: f226e460875d ("admin-guide: merge oops-tracing with bug-hunting")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/translations/zh_CN/oops-tracing.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/translations/zh_CN/oops-tracing.txt b/Documentation/translations/zh_CN/oops-tracing.txt
index 41ab53cc0e83..a893f04dfd5d 100644
--- a/Documentation/translations/zh_CN/oops-tracing.txt
+++ b/Documentation/translations/zh_CN/oops-tracing.txt
@@ -1,4 +1,4 @@
-Chinese translated version of Documentation/admin-guide/oops-tracing.rst
+Chinese translated version of Documentation/admin-guide/bug-hunting.rst
 
 If you have any comment or update to the content, please contact the
 original document maintainer directly.  However, if you have a problem
@@ -8,7 +8,7 @@ or if there is a problem with the translation.
 
 Chinese maintainer: Dave Young <hidave.darkstar@gmail.com>
 ---------------------------------------------------------------------
-Documentation/admin-guide/oops-tracing.rst 的中文翻译
+Documentation/admin-guide/bug-hunting.rst 的中文翻译
 
 如果想评论或更新本文的内容，请直接联系原文档的维护者。如果你使用英文
 交流有困难的话，也可以向中文版维护者求助。如果本翻译更新不及时或者翻
-- 
cgit v1.2.3


From 3fc3bbfc2083a048500a2a1b8377331af7f9175f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:06 -0300
Subject: devicectree: bindings: fix location of leds common file

The leds.txt was moved and renamed. Fix references to
it accordingly.

Fixes: f67605394f0b ("devicetree/bindings: Move gpio-leds binding into leds directory")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/devicetree/bindings/leds/common.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/leds/common.txt b/Documentation/devicetree/bindings/leds/common.txt
index 1d4afe9644b6..aa1399814a2a 100644
--- a/Documentation/devicetree/bindings/leds/common.txt
+++ b/Documentation/devicetree/bindings/leds/common.txt
@@ -31,7 +31,7 @@ Optional properties for child nodes:
      "backlight" - LED will act as a back-light, controlled by the framebuffer
 		   system
      "default-on" - LED will turn on (but for leds-gpio see "default-state"
-		    property in Documentation/devicetree/bindings/gpio/led.txt)
+		    property in Documentation/devicetree/bindings/leds/leds-gpio.txt)
      "heartbeat" - LED "double" flashes at a load average based rate
      "disk-activity" - LED indicates disk activity
      "ide-disk" - LED indicates IDE disk activity (deprecated),
-- 
cgit v1.2.3


From 2f896e1c518c7678fb059e16dd92bbac1cb68c95 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:07 -0300
Subject: MAINTAINERS: fix location of ina2xx.txt device tree file

This file got moved and merged, causing the old reference to
not exist anymore. Fix it.

Fixes: 6e24d205a8aa ("hwmon: ina209: move binding docs to proper place")
Fixes: 62bc9f15e443 ("dt-bindings: merge ina209 binding into ina2xx binding")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 0aaaff932c46..bc0d050d99fb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7033,7 +7033,7 @@ M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/hwmon/ina209
-F:	Documentation/devicetree/bindings/i2c/ina209.txt
+F:	Documentation/devicetree/bindings/hwmon/ina2xx.txt
 F:	drivers/hwmon/ina209.c
 
 INA2XX HARDWARE MONITOR DRIVER
-- 
cgit v1.2.3


From 60a866685006bae0c3db20e4bae31887eb452ff1 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:08 -0300
Subject: gpio.h: fix location of gpio legacy documentation

The location of this doc file was moved. Change its reference
accordingly.

Fixes: 7ee2c13080c9 ("Documentation: gpio: Move legacy documentation to driver-api")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/gpio.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 91ed23468530..39745b8bdd65 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -14,7 +14,7 @@
 
 #include <linux/errno.h>
 
-/* see Documentation/gpio/gpio-legacy.txt */
+/* see Documentation/driver-api/gpio/legacy.rst */
 
 /* make these flag values available regardless of GPIO kconfig options */
 #define GPIOF_DIR_OUT	(0 << 0)
-- 
cgit v1.2.3


From ea272257ccba1e57b9448444e1e3de39794ad6b4 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 26 Jun 2018 06:49:11 -0300
Subject: docs: histogram.txt: convert it to ReST file format

Despite being mentioned at Documentation/trace/ftrace.rst as a
rst file, this file was still a text one, with several issues.

Convert it to ReST and add it to the trace index:
- Mark the document title as such;
- Identify and indent the literal blocks;
- Use the proper markups for table.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/trace/events.rst    |    2 +-
 Documentation/trace/histogram.rst | 2545 +++++++++++++++++++++++++++++++++++++
 Documentation/trace/histogram.txt | 2539 ------------------------------------
 Documentation/trace/index.rst     |    1 +
 kernel/trace/Kconfig              |    2 +-
 5 files changed, 2548 insertions(+), 2541 deletions(-)
 create mode 100644 Documentation/trace/histogram.rst
 delete mode 100644 Documentation/trace/histogram.txt

diff --git a/Documentation/trace/events.rst b/Documentation/trace/events.rst
index 696dc69b8158..f7e1fcc0953c 100644
--- a/Documentation/trace/events.rst
+++ b/Documentation/trace/events.rst
@@ -524,4 +524,4 @@ The following commands are supported:
   totals derived from one or more trace event format fields and/or
   event counts (hitcount).
 
-  See Documentation/trace/histogram.txt for details and examples.
+  See Documentation/trace/histogram.rst for details and examples.
diff --git a/Documentation/trace/histogram.rst b/Documentation/trace/histogram.rst
new file mode 100644
index 000000000000..5ac724baea7d
--- /dev/null
+++ b/Documentation/trace/histogram.rst
@@ -0,0 +1,2545 @@
+================
+Event Histograms
+================
+
+Documentation written by Tom Zanussi
+
+1. Introduction
+===============
+
+  Histogram triggers are special event triggers that can be used to
+  aggregate trace event data into histograms.  For information on
+  trace events and event triggers, see Documentation/trace/events.rst.
+
+
+2. Histogram Trigger Command
+============================
+
+  A histogram trigger command is an event trigger command that
+  aggregates event hits into a hash table keyed on one or more trace
+  event format fields (or stacktrace) and a set of running totals
+  derived from one or more trace event format fields and/or event
+  counts (hitcount).
+
+  The format of a hist trigger is as follows::
+
+        hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
+          [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
+          [:clear][:name=histname1] [if <filter>]
+
+  When a matching event is hit, an entry is added to a hash table
+  using the key(s) and value(s) named.  Keys and values correspond to
+  fields in the event's format description.  Values must correspond to
+  numeric fields - on an event hit, the value(s) will be added to a
+  sum kept for that field.  The special string 'hitcount' can be used
+  in place of an explicit value field - this is simply a count of
+  event hits.  If 'values' isn't specified, an implicit 'hitcount'
+  value will be automatically created and used as the only value.
+  Keys can be any field, or the special string 'stacktrace', which
+  will use the event's kernel stacktrace as the key.  The keywords
+  'keys' or 'key' can be used to specify keys, and the keywords
+  'values', 'vals', or 'val' can be used to specify values.  Compound
+  keys consisting of up to two fields can be specified by the 'keys'
+  keyword.  Hashing a compound key produces a unique entry in the
+  table for each unique combination of component keys, and can be
+  useful for providing more fine-grained summaries of event data.
+  Additionally, sort keys consisting of up to two fields can be
+  specified by the 'sort' keyword.  If more than one field is
+  specified, the result will be a 'sort within a sort': the first key
+  is taken to be the primary sort key and the second the secondary
+  key.  If a hist trigger is given a name using the 'name' parameter,
+  its histogram data will be shared with other triggers of the same
+  name, and trigger hits will update this common data.  Only triggers
+  with 'compatible' fields can be combined in this way; triggers are
+  'compatible' if the fields named in the trigger share the same
+  number and type of fields and those fields also have the same names.
+  Note that any two events always share the compatible 'hitcount' and
+  'stacktrace' fields and can therefore be combined using those
+  fields, however pointless that may be.
+
+  'hist' triggers add a 'hist' file to each event's subdirectory.
+  Reading the 'hist' file for the event will dump the hash table in
+  its entirety to stdout.  If there are multiple hist triggers
+  attached to an event, there will be a table for each trigger in the
+  output.  The table displayed for a named trigger will be the same as
+  any other instance having the same name. Each printed hash table
+  entry is a simple list of the keys and values comprising the entry;
+  keys are printed first and are delineated by curly braces, and are
+  followed by the set of value fields for the entry.  By default,
+  numeric fields are displayed as base-10 integers.  This can be
+  modified by appending any of the following modifiers to the field
+  name:
+
+	=========== ==========================================
+        .hex        display a number as a hex value
+	.sym        display an address as a symbol
+	.sym-offset display an address as a symbol and offset
+	.syscall    display a syscall id as a system call name
+	.execname   display a common_pid as a program name
+	.log2       display log2 value rather than raw number
+	.usecs      display a common_timestamp in microseconds
+	=========== ==========================================
+
+  Note that in general the semantics of a given field aren't
+  interpreted when applying a modifier to it, but there are some
+  restrictions to be aware of in this regard:
+
+    - only the 'hex' modifier can be used for values (because values
+      are essentially sums, and the other modifiers don't make sense
+      in that context).
+    - the 'execname' modifier can only be used on a 'common_pid'.  The
+      reason for this is that the execname is simply the 'comm' value
+      saved for the 'current' process when an event was triggered,
+      which is the same as the common_pid value saved by the event
+      tracing code.  Trying to apply that comm value to other pid
+      values wouldn't be correct, and typically events that care save
+      pid-specific comm fields in the event itself.
+
+  A typical usage scenario would be the following to enable a hist
+  trigger, read its current contents, and then turn it off::
+
+    # echo 'hist:keys=skbaddr.hex:vals=len' > \
+      /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+    # echo '!hist:keys=skbaddr.hex:vals=len' > \
+      /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+  The trigger file itself can be read to show the details of the
+  currently attached hist trigger.  This information is also displayed
+  at the top of the 'hist' file when read.
+
+  By default, the size of the hash table is 2048 entries.  The 'size'
+  parameter can be used to specify more or fewer than that.  The units
+  are in terms of hashtable entries - if a run uses more entries than
+  specified, the results will show the number of 'drops', the number
+  of hits that were ignored.  The size should be a power of 2 between
+  128 and 131072 (any non- power-of-2 number specified will be rounded
+  up).
+
+  The 'sort' parameter can be used to specify a value field to sort
+  on.  The default if unspecified is 'hitcount' and the default sort
+  order is 'ascending'.  To sort in the opposite direction, append
+  .descending' to the sort key.
+
+  The 'pause' parameter can be used to pause an existing hist trigger
+  or to start a hist trigger but not log any events until told to do
+  so.  'continue' or 'cont' can be used to start or restart a paused
+  hist trigger.
+
+  The 'clear' parameter will clear the contents of a running hist
+  trigger and leave its current paused/active state.
+
+  Note that the 'pause', 'cont', and 'clear' parameters should be
+  applied using 'append' shell operator ('>>') if applied to an
+  existing trigger, rather than via the '>' operator, which will cause
+  the trigger to be removed through truncation.
+
+- enable_hist/disable_hist
+
+  The enable_hist and disable_hist triggers can be used to have one
+  event conditionally start and stop another event's already-attached
+  hist trigger.  Any number of enable_hist and disable_hist triggers
+  can be attached to a given event, allowing that event to kick off
+  and stop aggregations on a host of other events.
+
+  The format is very similar to the enable/disable_event triggers::
+
+      enable_hist:<system>:<event>[:count]
+      disable_hist:<system>:<event>[:count]
+
+  Instead of enabling or disabling the tracing of the target event
+  into the trace buffer as the enable/disable_event triggers do, the
+  enable/disable_hist triggers enable or disable the aggregation of
+  the target event into a hash table.
+
+  A typical usage scenario for the enable_hist/disable_hist triggers
+  would be to first set up a paused hist trigger on some event,
+  followed by an enable_hist/disable_hist pair that turns the hist
+  aggregation on and off when conditions of interest are hit::
+
+   # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
+      /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+    # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
+      /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+    # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
+      /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+  The above sets up an initially paused hist trigger which is unpaused
+  and starts aggregating events when a given program is executed, and
+  which stops aggregating when the process exits and the hist trigger
+  is paused again.
+
+  The examples below provide a more concrete illustration of the
+  concepts and typical usage patterns discussed above.
+
+'special' event fields
+------------------------
+
+  There are a number of 'special event fields' available for use as
+  keys or values in a hist trigger.  These look like and behave as if
+  they were actual event fields, but aren't really part of the event's
+  field definition or format file.  They are however available for any
+  event, and can be used anywhere an actual event field could be.
+  They are:
+
+    ====================== ==== =======================================
+    common_timestamp       u64  timestamp (from ring buffer) associated
+                                with the event, in nanoseconds.  May be
+			        modified by .usecs to have timestamps
+			        interpreted as microseconds.
+    cpu                    int  the cpu on which the event occurred.
+    ====================== ==== =======================================
+
+Extended error information
+--------------------------
+
+  For some error conditions encountered when invoking a hist trigger
+  command, extended error information is available via the
+  corresponding event's 'hist' file.  Reading the hist file after an
+  error will display more detailed information about what went wrong,
+  if information is available.  This extended error information will
+  be available until the next hist trigger command for that event.
+
+  If available for a given error condition, the extended error
+  information and usage takes the following form::
+
+    # echo xxx > /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
+    echo: write error: Invalid argument
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/hist
+    ERROR: Couldn't yyy: zzz
+      Last command: xxx
+
+6.2 'hist' trigger examples
+---------------------------
+
+  The first set of examples creates aggregations using the kmalloc
+  event.  The fields that can be used for the hist trigger are listed
+  in the kmalloc event's format file::
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/format
+    name: kmalloc
+    ID: 374
+    format:
+	field:unsigned short common_type;	offset:0;	size:2;	signed:0;
+	field:unsigned char common_flags;	offset:2;	size:1;	signed:0;
+	field:unsigned char common_preempt_count;		offset:3;	size:1;	signed:0;
+	field:int common_pid;					offset:4;	size:4;	signed:1;
+
+	field:unsigned long call_site;				offset:8;	size:8;	signed:0;
+	field:const void * ptr;					offset:16;	size:8;	signed:0;
+	field:size_t bytes_req;					offset:24;	size:8;	signed:0;
+	field:size_t bytes_alloc;				offset:32;	size:8;	signed:0;
+	field:gfp_t gfp_flags;					offset:40;	size:4;	signed:0;
+
+  We'll start by creating a hist trigger that generates a simple table
+  that lists the total number of bytes requested for each function in
+  the kernel that made one or more calls to kmalloc::
+
+    # echo 'hist:key=call_site:val=bytes_req' > \
+            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+  This tells the tracing system to create a 'hist' trigger using the
+  call_site field of the kmalloc event as the key for the table, which
+  just means that each unique call_site address will have an entry
+  created for it in the table.  The 'val=bytes_req' parameter tells
+  the hist trigger that for each unique entry (call_site) in the
+  table, it should keep a running total of the number of bytes
+  requested by that call_site.
+
+  We'll let it run for awhile and then dump the contents of the 'hist'
+  file in the kmalloc event's subdirectory (for readability, a number
+  of entries have been omitted)::
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+    { call_site: 18446744072106379007 } hitcount:          1  bytes_req:        176
+    { call_site: 18446744071579557049 } hitcount:          1  bytes_req:       1024
+    { call_site: 18446744071580608289 } hitcount:          1  bytes_req:      16384
+    { call_site: 18446744071581827654 } hitcount:          1  bytes_req:         24
+    { call_site: 18446744071580700980 } hitcount:          1  bytes_req:          8
+    { call_site: 18446744071579359876 } hitcount:          1  bytes_req:        152
+    { call_site: 18446744071580795365 } hitcount:          3  bytes_req:        144
+    { call_site: 18446744071581303129 } hitcount:          3  bytes_req:        144
+    { call_site: 18446744071580713234 } hitcount:          4  bytes_req:       2560
+    { call_site: 18446744071580933750 } hitcount:          4  bytes_req:        736
+    .
+    .
+    .
+    { call_site: 18446744072106047046 } hitcount:         69  bytes_req:       5576
+    { call_site: 18446744071582116407 } hitcount:         73  bytes_req:       2336
+    { call_site: 18446744072106054684 } hitcount:        136  bytes_req:     140504
+    { call_site: 18446744072106224230 } hitcount:        136  bytes_req:      19584
+    { call_site: 18446744072106078074 } hitcount:        153  bytes_req:       2448
+    { call_site: 18446744072106062406 } hitcount:        153  bytes_req:      36720
+    { call_site: 18446744071582507929 } hitcount:        153  bytes_req:      37088
+    { call_site: 18446744072102520590 } hitcount:        273  bytes_req:      10920
+    { call_site: 18446744071582143559 } hitcount:        358  bytes_req:        716
+    { call_site: 18446744072106465852 } hitcount:        417  bytes_req:      56712
+    { call_site: 18446744072102523378 } hitcount:        485  bytes_req:      27160
+    { call_site: 18446744072099568646 } hitcount:       1676  bytes_req:      33520
+
+    Totals:
+        Hits: 4610
+        Entries: 45
+        Dropped: 0
+
+  The output displays a line for each entry, beginning with the key
+  specified in the trigger, followed by the value(s) also specified in
+  the trigger.  At the beginning of the output is a line that displays
+  the trigger info, which can also be displayed by reading the
+  'trigger' file::
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+    hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+  At the end of the output are a few lines that display the overall
+  totals for the run.  The 'Hits' field shows the total number of
+  times the event trigger was hit, the 'Entries' field shows the total
+  number of used entries in the hash table, and the 'Dropped' field
+  shows the number of hits that were dropped because the number of
+  used entries for the run exceeded the maximum number of entries
+  allowed for the table (normally 0, but if not a hint that you may
+  want to increase the size of the table using the 'size' parameter).
+
+  Notice in the above output that there's an extra field, 'hitcount',
+  which wasn't specified in the trigger.  Also notice that in the
+  trigger info output, there's a parameter, 'sort=hitcount', which
+  wasn't specified in the trigger either.  The reason for that is that
+  every trigger implicitly keeps a count of the total number of hits
+  attributed to a given entry, called the 'hitcount'.  That hitcount
+  information is explicitly displayed in the output, and in the
+  absence of a user-specified sort parameter, is used as the default
+  sort field.
+
+  The value 'hitcount' can be used in place of an explicit value in
+  the 'values' parameter if you don't really need to have any
+  particular field summed and are mainly interested in hit
+  frequencies.
+
+  To turn the hist trigger off, simply call up the trigger in the
+  command history and re-execute it with a '!' prepended::
+
+    # echo '!hist:key=call_site:val=bytes_req' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+  Finally, notice that the call_site as displayed in the output above
+  isn't really very useful.  It's an address, but normally addresses
+  are displayed in hex.  To have a numeric field displayed as a hex
+  value, simply append '.hex' to the field name in the trigger::
+
+    # echo 'hist:key=call_site.hex:val=bytes_req' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.hex:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+    { call_site: ffffffffa026b291 } hitcount:          1  bytes_req:        433
+    { call_site: ffffffffa07186ff } hitcount:          1  bytes_req:        176
+    { call_site: ffffffff811ae721 } hitcount:          1  bytes_req:      16384
+    { call_site: ffffffff811c5134 } hitcount:          1  bytes_req:          8
+    { call_site: ffffffffa04a9ebb } hitcount:          1  bytes_req:        511
+    { call_site: ffffffff8122e0a6 } hitcount:          1  bytes_req:         12
+    { call_site: ffffffff8107da84 } hitcount:          1  bytes_req:        152
+    { call_site: ffffffff812d8246 } hitcount:          1  bytes_req:         24
+    { call_site: ffffffff811dc1e5 } hitcount:          3  bytes_req:        144
+    { call_site: ffffffffa02515e8 } hitcount:          3  bytes_req:        648
+    { call_site: ffffffff81258159 } hitcount:          3  bytes_req:        144
+    { call_site: ffffffff811c80f4 } hitcount:          4  bytes_req:        544
+    .
+    .
+    .
+    { call_site: ffffffffa06c7646 } hitcount:        106  bytes_req:       8024
+    { call_site: ffffffffa06cb246 } hitcount:        132  bytes_req:      31680
+    { call_site: ffffffffa06cef7a } hitcount:        132  bytes_req:       2112
+    { call_site: ffffffff8137e399 } hitcount:        132  bytes_req:      23232
+    { call_site: ffffffffa06c941c } hitcount:        185  bytes_req:     171360
+    { call_site: ffffffffa06f2a66 } hitcount:        185  bytes_req:      26640
+    { call_site: ffffffffa036a70e } hitcount:        265  bytes_req:      10600
+    { call_site: ffffffff81325447 } hitcount:        292  bytes_req:        584
+    { call_site: ffffffffa072da3c } hitcount:        446  bytes_req:      60656
+    { call_site: ffffffffa036b1f2 } hitcount:        526  bytes_req:      29456
+    { call_site: ffffffffa0099c06 } hitcount:       1780  bytes_req:      35600
+
+    Totals:
+        Hits: 4775
+        Entries: 46
+        Dropped: 0
+
+  Even that's only marginally more useful - while hex values do look
+  more like addresses, what users are typically more interested in
+  when looking at text addresses are the corresponding symbols
+  instead.  To have an address displayed as symbolic value instead,
+  simply append '.sym' or '.sym-offset' to the field name in the
+  trigger::
+
+    # echo 'hist:key=call_site.sym:val=bytes_req' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+    { call_site: [ffffffff810adcb9] syslog_print_all                              } hitcount:          1  bytes_req:       1024
+    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffff8154acbe] usb_alloc_urb                                 } hitcount:          1  bytes_req:        192
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
+    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff811febd5] fsnotify_alloc_group                          } hitcount:          2  bytes_req:        528
+    { call_site: [ffffffff81440f58] __tty_buffer_request_room                     } hitcount:          2  bytes_req:       2624
+    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          2  bytes_req:         96
+    { call_site: [ffffffffa05e19af] ieee80211_start_tx_ba_session [mac80211]      } hitcount:          2  bytes_req:        464
+    { call_site: [ffffffff81672406] tcp_get_metrics                               } hitcount:          2  bytes_req:        304
+    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff81089b05] sched_create_group                            } hitcount:          2  bytes_req:       1424
+    .
+    .
+    .
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1185  bytes_req:     123240
+    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:       1185  bytes_req:     104280
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       1402  bytes_req:     190672
+    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       1518  bytes_req:     146208
+    { call_site: [ffffffffa029070e] drm_vma_node_allow [drm]                      } hitcount:       1746  bytes_req:      69840
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       2021  bytes_req:     792312
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       2592  bytes_req:     145152
+    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2629  bytes_req:     378576
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2629  bytes_req:    3783248
+    { call_site: [ffffffff81325607] apparmor_file_alloc_security                  } hitcount:       5192  bytes_req:      10384
+    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       5529  bytes_req:     110584
+    { call_site: [ffffffff8131ebf7] aa_alloc_task_context                         } hitcount:      21943  bytes_req:     702176
+    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:      55759  bytes_req:    5074265
+
+    Totals:
+        Hits: 109928
+        Entries: 71
+        Dropped: 0
+
+  Because the default sort key above is 'hitcount', the above shows a
+  the list of call_sites by increasing hitcount, so that at the bottom
+  we see the functions that made the most kmalloc calls during the
+  run.  If instead we we wanted to see the top kmalloc callers in
+  terms of the number of bytes requested rather than the number of
+  calls, and we wanted the top caller to appear at the top, we can use
+  the 'sort' parameter, along with the 'descending' modifier::
+
+    # echo 'hist:key=call_site.sym:val=bytes_req:sort=bytes_req.descending' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
+
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2186  bytes_req:    3397464
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1790  bytes_req:     712176
+    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       8132  bytes_req:     513135
+    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        106  bytes_req:     440128
+    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2186  bytes_req:     314784
+    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       2174  bytes_req:     208992
+    { call_site: [ffffffff811ae8e1] __kmalloc                                     } hitcount:          8  bytes_req:     131072
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:        859  bytes_req:     116824
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       1834  bytes_req:     102704
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:        972  bytes_req:     101088
+    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:        972  bytes_req:      85536
+    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       3333  bytes_req:      66664
+    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        209  bytes_req:      61632
+    .
+    .
+    .
+    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffff812d8406] copy_semundo                                  } hitcount:          2  bytes_req:         48
+    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          1  bytes_req:         48
+    { call_site: [ffffffffa027121a] drm_getmagic [drm]                            } hitcount:          1  bytes_req:         48
+    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
+    { call_site: [ffffffff811c52f4] bprm_change_interp                            } hitcount:          2  bytes_req:         16
+    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
+
+    Totals:
+        Hits: 32133
+        Entries: 81
+        Dropped: 0
+
+  To display the offset and size information in addition to the symbol
+  name, just use 'sym-offset' instead::
+
+    # echo 'hist:key=call_site.sym-offset:val=bytes_req:sort=bytes_req.descending' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym-offset:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
+
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2+0x6c/0x2c0 [i915]                  } hitcount:       4569  bytes_req:    3163720
+    { call_site: [ffffffffa0489a66] intel_ring_begin+0xc6/0x1f0 [i915]                      } hitcount:       4569  bytes_req:     657936
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23+0x694/0x1020 [i915]      } hitcount:       1519  bytes_req:     472936
+    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23+0x516/0x1020 [i915]      } hitcount:       3050  bytes_req:     211832
+    { call_site: [ffffffff811e2a1b] seq_buf_alloc+0x1b/0x50                                 } hitcount:         34  bytes_req:     148384
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip+0xbc/0x870 [i915]                  } hitcount:       1385  bytes_req:     144040
+    { call_site: [ffffffff811ae8e1] __kmalloc+0x191/0x1b0                                   } hitcount:          8  bytes_req:     131072
+    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl+0x282/0x360 [drm]              } hitcount:       1385  bytes_req:     121880
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc+0x32/0x100 [drm]                  } hitcount:       1848  bytes_req:     103488
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state+0x2c/0xa0 [i915]            } hitcount:        461  bytes_req:      62696
+    { call_site: [ffffffffa029070e] drm_vma_node_allow+0x2e/0xd0 [drm]                      } hitcount:       1541  bytes_req:      61640
+    { call_site: [ffffffff815f8d7b] sk_prot_alloc+0xcb/0x1b0                                } hitcount:         57  bytes_req:      57456
+    .
+    .
+    .
+    { call_site: [ffffffff8109524a] alloc_fair_sched_group+0x5a/0x1a0                       } hitcount:          2  bytes_req:        128
+    { call_site: [ffffffffa027b921] drm_vm_open_locked+0x31/0xa0 [drm]                      } hitcount:          3  bytes_req:         96
+    { call_site: [ffffffff8122e266] proc_self_follow_link+0x76/0xb0                         } hitcount:          8  bytes_req:         96
+    { call_site: [ffffffff81213e80] load_elf_binary+0x240/0x1650                            } hitcount:          3  bytes_req:         84
+    { call_site: [ffffffff8154bc62] usb_control_msg+0x42/0x110                              } hitcount:          1  bytes_req:          8
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report+0x7e/0x1a0 [hid]                     } hitcount:          1  bytes_req:          7
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event+0x8a/0x120 [hid]                    } hitcount:          1  bytes_req:          7
+
+    Totals:
+        Hits: 26098
+        Entries: 64
+        Dropped: 0
+
+  We can also add multiple fields to the 'values' parameter.  For
+  example, we might want to see the total number of bytes allocated
+  alongside bytes requested, and display the result sorted by bytes
+  allocated in a descending order::
+
+    # echo 'hist:keys=call_site.sym:values=bytes_req,bytes_alloc:sort=bytes_alloc.descending' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=call_site.sym:vals=bytes_req,bytes_alloc:sort=bytes_alloc.descending:size=2048 [active]
+
+    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       7403  bytes_req:    4084360  bytes_alloc:    5958016
+    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        541  bytes_req:    2213968  bytes_alloc:    2228224
+    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       7404  bytes_req:    1066176  bytes_alloc:    1421568
+    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1565  bytes_req:     557368  bytes_alloc:    1037760
+    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       9557  bytes_req:     595778  bytes_alloc:     695744
+    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       5839  bytes_req:     430680  bytes_alloc:     470400
+    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       2388  bytes_req:     324768  bytes_alloc:     458496
+    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       3911  bytes_req:     219016  bytes_alloc:     250304
+    { call_site: [ffffffff815f8d7b] sk_prot_alloc                                 } hitcount:        235  bytes_req:     236880  bytes_alloc:     240640
+    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        557  bytes_req:     169024  bytes_alloc:     221760
+    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       9378  bytes_req:     187548  bytes_alloc:     206312
+    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1519  bytes_req:     157976  bytes_alloc:     194432
+    .
+    .
+    .
+    { call_site: [ffffffff8109bd3b] sched_autogroup_create_attach                 } hitcount:          2  bytes_req:        144  bytes_alloc:        192
+    { call_site: [ffffffff81097ee8] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
+    { call_site: [ffffffff81213e80] load_elf_binary                               } hitcount:          3  bytes_req:         84  bytes_alloc:         96
+    { call_site: [ffffffff81079a2e] kthread_create_on_node                        } hitcount:          1  bytes_req:         56  bytes_alloc:         64
+    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7  bytes_alloc:          8
+    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8  bytes_alloc:          8
+    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7  bytes_alloc:          8
+
+    Totals:
+        Hits: 66598
+        Entries: 65
+        Dropped: 0
+
+  Finally, to finish off our kmalloc example, instead of simply having
+  the hist trigger display symbolic call_sites, we can have the hist
+  trigger additionally display the complete set of kernel stack traces
+  that led to each call_site.  To do that, we simply use the special
+  value 'stacktrace' for the key parameter::
+
+    # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \
+           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+  The above trigger will use the kernel stack trace in effect when an
+  event is triggered as the key for the hash table.  This allows the
+  enumeration of every kernel callpath that led up to a particular
+  event, along with a running total of any of the event fields for
+  that event.  Here we tally bytes requested and bytes allocated for
+  every callpath in the system that led up to a kmalloc (in this case
+  every callpath to a kmalloc for a kernel compile)::
+
+    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+    # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active]
+
+    { stacktrace:
+         __kmalloc_track_caller+0x10b/0x1a0
+         kmemdup+0x20/0x50
+         hidraw_report_event+0x8a/0x120 [hid]
+         hid_report_raw_event+0x3ea/0x440 [hid]
+         hid_input_report+0x112/0x190 [hid]
+         hid_irq_in+0xc2/0x260 [usbhid]
+         __usb_hcd_giveback_urb+0x72/0x120
+         usb_giveback_urb_bh+0x9e/0xe0
+         tasklet_hi_action+0xf8/0x100
+         __do_softirq+0x114/0x2c0
+         irq_exit+0xa5/0xb0
+         do_IRQ+0x5a/0xf0
+         ret_from_intr+0x0/0x30
+         cpuidle_enter+0x17/0x20
+         cpu_startup_entry+0x315/0x3e0
+         rest_init+0x7c/0x80
+    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
+    { stacktrace:
+         __kmalloc_track_caller+0x10b/0x1a0
+         kmemdup+0x20/0x50
+         hidraw_report_event+0x8a/0x120 [hid]
+         hid_report_raw_event+0x3ea/0x440 [hid]
+         hid_input_report+0x112/0x190 [hid]
+         hid_irq_in+0xc2/0x260 [usbhid]
+         __usb_hcd_giveback_urb+0x72/0x120
+         usb_giveback_urb_bh+0x9e/0xe0
+         tasklet_hi_action+0xf8/0x100
+         __do_softirq+0x114/0x2c0
+         irq_exit+0xa5/0xb0
+         do_IRQ+0x5a/0xf0
+         ret_from_intr+0x0/0x30
+    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
+    { stacktrace:
+         kmem_cache_alloc_trace+0xeb/0x150
+         aa_alloc_task_context+0x27/0x40
+         apparmor_cred_prepare+0x1f/0x50
+         security_prepare_creds+0x16/0x20
+         prepare_creds+0xdf/0x1a0
+         SyS_capset+0xb5/0x200
+         system_call_fastpath+0x12/0x6a
+    } hitcount:          1  bytes_req:         32  bytes_alloc:         32
+    .
+    .
+    .
+    { stacktrace:
+         __kmalloc+0x11b/0x1b0
+         i915_gem_execbuffer2+0x6c/0x2c0 [i915]
+         drm_ioctl+0x349/0x670 [drm]
+         do_vfs_ioctl+0x2f0/0x4f0
+         SyS_ioctl+0x81/0xa0
+         system_call_fastpath+0x12/0x6a
+    } hitcount:      17726  bytes_req:   13944120  bytes_alloc:   19593808
+    { stacktrace:
+         __kmalloc+0x11b/0x1b0
+         load_elf_phdrs+0x76/0xa0
+         load_elf_binary+0x102/0x1650
+         search_binary_handler+0x97/0x1d0
+         do_execveat_common.isra.34+0x551/0x6e0
+         SyS_execve+0x3a/0x50
+         return_from_execve+0x0/0x23
+    } hitcount:      33348  bytes_req:   17152128  bytes_alloc:   20226048
+    { stacktrace:
+         kmem_cache_alloc_trace+0xeb/0x150
+         apparmor_file_alloc_security+0x27/0x40
+         security_file_alloc+0x16/0x20
+         get_empty_filp+0x93/0x1c0
+         path_openat+0x31/0x5f0
+         do_filp_open+0x3a/0x90
+         do_sys_open+0x128/0x220
+         SyS_open+0x1e/0x20
+         system_call_fastpath+0x12/0x6a
+    } hitcount:    4766422  bytes_req:    9532844  bytes_alloc:   38131376
+    { stacktrace:
+         __kmalloc+0x11b/0x1b0
+         seq_buf_alloc+0x1b/0x50
+         seq_read+0x2cc/0x370
+         proc_reg_read+0x3d/0x80
+         __vfs_read+0x28/0xe0
+         vfs_read+0x86/0x140
+         SyS_read+0x46/0xb0
+         system_call_fastpath+0x12/0x6a
+    } hitcount:      19133  bytes_req:   78368768  bytes_alloc:   78368768
+
+    Totals:
+        Hits: 6085872
+        Entries: 253
+        Dropped: 0
+
+  If you key a hist trigger on common_pid, in order for example to
+  gather and display sorted totals for each process, you can use the
+  special .execname modifier to display the executable names for the
+  processes in the table rather than raw pids.  The example below
+  keeps a per-process sum of total bytes read::
+
+    # echo 'hist:key=common_pid.execname:val=count:sort=count.descending' > \
+           /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
+
+    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/hist
+    # trigger info: hist:keys=common_pid.execname:vals=count:sort=count.descending:size=2048 [active]
+
+    { common_pid: gnome-terminal  [      3196] } hitcount:        280  count:    1093512
+    { common_pid: Xorg            [      1309] } hitcount:        525  count:     256640
+    { common_pid: compiz          [      2889] } hitcount:         59  count:     254400
+    { common_pid: bash            [      8710] } hitcount:          3  count:      66369
+    { common_pid: dbus-daemon-lau [      8703] } hitcount:         49  count:      47739
+    { common_pid: irqbalance      [      1252] } hitcount:         27  count:      27648
+    { common_pid: 01ifupdown      [      8705] } hitcount:          3  count:      17216
+    { common_pid: dbus-daemon     [       772] } hitcount:         10  count:      12396
+    { common_pid: Socket Thread   [      8342] } hitcount:         11  count:      11264
+    { common_pid: nm-dhcp-client. [      8701] } hitcount:          6  count:       7424
+    { common_pid: gmain           [      1315] } hitcount:         18  count:       6336
+    .
+    .
+    .
+    { common_pid: postgres        [      1892] } hitcount:          2  count:         32
+    { common_pid: postgres        [      1891] } hitcount:          2  count:         32
+    { common_pid: gmain           [      8704] } hitcount:          2  count:         32
+    { common_pid: upstart-dbus-br [      2740] } hitcount:         21  count:         21
+    { common_pid: nm-dispatcher.a [      8696] } hitcount:          1  count:         16
+    { common_pid: indicator-datet [      2904] } hitcount:          1  count:         16
+    { common_pid: gdbus           [      2998] } hitcount:          1  count:         16
+    { common_pid: rtkit-daemon    [      2052] } hitcount:          1  count:          8
+    { common_pid: init            [         1] } hitcount:          2  count:          2
+
+    Totals:
+        Hits: 2116
+        Entries: 51
+        Dropped: 0
+
+  Similarly, if you key a hist trigger on syscall id, for example to
+  gather and display a list of systemwide syscall hits, you can use
+  the special .syscall modifier to display the syscall names rather
+  than raw ids.  The example below keeps a running total of syscall
+  counts for the system during the run::
+
+    # echo 'hist:key=id.syscall:val=hitcount' > \
+           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+    # trigger info: hist:keys=id.syscall:vals=hitcount:sort=hitcount:size=2048 [active]
+
+    { id: sys_fsync                     [ 74] } hitcount:          1
+    { id: sys_newuname                  [ 63] } hitcount:          1
+    { id: sys_prctl                     [157] } hitcount:          1
+    { id: sys_statfs                    [137] } hitcount:          1
+    { id: sys_symlink                   [ 88] } hitcount:          1
+    { id: sys_sendmmsg                  [307] } hitcount:          1
+    { id: sys_semctl                    [ 66] } hitcount:          1
+    { id: sys_readlink                  [ 89] } hitcount:          3
+    { id: sys_bind                      [ 49] } hitcount:          3
+    { id: sys_getsockname               [ 51] } hitcount:          3
+    { id: sys_unlink                    [ 87] } hitcount:          3
+    { id: sys_rename                    [ 82] } hitcount:          4
+    { id: unknown_syscall               [ 58] } hitcount:          4
+    { id: sys_connect                   [ 42] } hitcount:          4
+    { id: sys_getpid                    [ 39] } hitcount:          4
+    .
+    .
+    .
+    { id: sys_rt_sigprocmask            [ 14] } hitcount:        952
+    { id: sys_futex                     [202] } hitcount:       1534
+    { id: sys_write                     [  1] } hitcount:       2689
+    { id: sys_setitimer                 [ 38] } hitcount:       2797
+    { id: sys_read                      [  0] } hitcount:       3202
+    { id: sys_select                    [ 23] } hitcount:       3773
+    { id: sys_writev                    [ 20] } hitcount:       4531
+    { id: sys_poll                      [  7] } hitcount:       8314
+    { id: sys_recvmsg                   [ 47] } hitcount:      13738
+    { id: sys_ioctl                     [ 16] } hitcount:      21843
+
+    Totals:
+        Hits: 67612
+        Entries: 72
+        Dropped: 0
+
+  The syscall counts above provide a rough overall picture of system
+  call activity on the system; we can see for example that the most
+  popular system call on this system was the 'sys_ioctl' system call.
+
+  We can use 'compound' keys to refine that number and provide some
+  further insight as to which processes exactly contribute to the
+  overall ioctl count.
+
+  The command below keeps a hitcount for every unique combination of
+  system call id and pid - the end result is essentially a table
+  that keeps a per-pid sum of system call hits.  The results are
+  sorted using the system call id as the primary key, and the
+  hitcount sum as the secondary key::
+
+    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount' > \
+           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 [active]
+
+    { id: sys_read                      [  0], common_pid: rtkit-daemon    [      1877] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: gdbus           [      2976] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: console-kit-dae [      3400] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: postgres        [      1865] } hitcount:          1
+    { id: sys_read                      [  0], common_pid: deja-dup-monito [      3543] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: NetworkManager  [       890] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: evolution-calen [      3048] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: postgres        [      1864] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: nm-applet       [      3022] } hitcount:          2
+    { id: sys_read                      [  0], common_pid: whoopsie        [      1212] } hitcount:          2
+    .
+    .
+    .
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      8479] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      3472] } hitcount:         12
+    { id: sys_ioctl                     [ 16], common_pid: gnome-terminal  [      3199] } hitcount:         16
+    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:       1808
+    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:       5580
+    .
+    .
+    .
+    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2690] } hitcount:          3
+    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2688] } hitcount:         16
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [       975] } hitcount:          2
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3204] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2888] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3003] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2873] } hitcount:          4
+    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3196] } hitcount:          6
+    { id: sys_openat                    [257], common_pid: java            [      2623] } hitcount:          2
+    { id: sys_eventfd2                  [290], common_pid: ibus-ui-gtk3    [      2760] } hitcount:          4
+    { id: sys_eventfd2                  [290], common_pid: compiz          [      2994] } hitcount:          6
+
+    Totals:
+        Hits: 31536
+        Entries: 323
+        Dropped: 0
+
+  The above list does give us a breakdown of the ioctl syscall by
+  pid, but it also gives us quite a bit more than that, which we
+  don't really care about at the moment.  Since we know the syscall
+  id for sys_ioctl (16, displayed next to the sys_ioctl name), we
+  can use that to filter out all the other syscalls::
+
+    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount if id == 16' > \
+           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 if id == 16 [active]
+
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2769] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: evolution-addre [      8571] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      3003] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2781] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2829] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      8726] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: bash            [      8508] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2970] } hitcount:          1
+    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2768] } hitcount:          1
+    .
+    .
+    .
+    { id: sys_ioctl                     [ 16], common_pid: pool            [      8559] } hitcount:         45
+    { id: sys_ioctl                     [ 16], common_pid: pool            [      8555] } hitcount:         48
+    { id: sys_ioctl                     [ 16], common_pid: pool            [      8551] } hitcount:         48
+    { id: sys_ioctl                     [ 16], common_pid: avahi-daemon    [       896] } hitcount:         66
+    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:      26674
+    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:      73443
+
+    Totals:
+        Hits: 101162
+        Entries: 103
+        Dropped: 0
+
+  The above output shows that 'compiz' and 'Xorg' are far and away
+  the heaviest ioctl callers (which might lead to questions about
+  whether they really need to be making all those calls and to
+  possible avenues for further investigation.)
+
+  The compound key examples used a key and a sum value (hitcount) to
+  sort the output, but we can just as easily use two keys instead.
+  Here's an example where we use a compound key composed of the the
+  common_pid and size event fields.  Sorting with pid as the primary
+  key and 'size' as the secondary key allows us to display an
+  ordered summary of the recvfrom sizes, with counts, received by
+  each process::
+
+    # echo 'hist:key=common_pid.execname,size:val=hitcount:sort=common_pid,size' > \
+           /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/trigger
+
+    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/hist
+    # trigger info: hist:keys=common_pid.execname,size:vals=hitcount:sort=common_pid.execname,size:size=2048 [active]
+
+    { common_pid: smbd            [       784], size:          4 } hitcount:          1
+    { common_pid: dnsmasq         [      1412], size:       4096 } hitcount:        672
+    { common_pid: postgres        [      1796], size:       1000 } hitcount:          6
+    { common_pid: postgres        [      1867], size:       1000 } hitcount:         10
+    { common_pid: bamfdaemon      [      2787], size:         28 } hitcount:          2
+    { common_pid: bamfdaemon      [      2787], size:      14360 } hitcount:          1
+    { common_pid: compiz          [      2994], size:          8 } hitcount:          1
+    { common_pid: compiz          [      2994], size:         20 } hitcount:         11
+    { common_pid: gnome-terminal  [      3199], size:          4 } hitcount:          2
+    { common_pid: firefox         [      8817], size:          4 } hitcount:          1
+    { common_pid: firefox         [      8817], size:          8 } hitcount:          5
+    { common_pid: firefox         [      8817], size:        588 } hitcount:          2
+    { common_pid: firefox         [      8817], size:        628 } hitcount:          1
+    { common_pid: firefox         [      8817], size:       6944 } hitcount:          1
+    { common_pid: firefox         [      8817], size:     408880 } hitcount:          2
+    { common_pid: firefox         [      8822], size:          8 } hitcount:          2
+    { common_pid: firefox         [      8822], size:        160 } hitcount:          2
+    { common_pid: firefox         [      8822], size:        320 } hitcount:          2
+    { common_pid: firefox         [      8822], size:        352 } hitcount:          1
+    .
+    .
+    .
+    { common_pid: pool            [      8923], size:       1960 } hitcount:         10
+    { common_pid: pool            [      8923], size:       2048 } hitcount:         10
+    { common_pid: pool            [      8924], size:       1960 } hitcount:         10
+    { common_pid: pool            [      8924], size:       2048 } hitcount:         10
+    { common_pid: pool            [      8928], size:       1964 } hitcount:          4
+    { common_pid: pool            [      8928], size:       1965 } hitcount:          2
+    { common_pid: pool            [      8928], size:       2048 } hitcount:          6
+    { common_pid: pool            [      8929], size:       1982 } hitcount:          1
+    { common_pid: pool            [      8929], size:       2048 } hitcount:          1
+
+    Totals:
+        Hits: 2016
+        Entries: 224
+        Dropped: 0
+
+  The above example also illustrates the fact that although a compound
+  key is treated as a single entity for hashing purposes, the sub-keys
+  it's composed of can be accessed independently.
+
+  The next example uses a string field as the hash key and
+  demonstrates how you can manually pause and continue a hist trigger.
+  In this example, we'll aggregate fork counts and don't expect a
+  large number of entries in the hash table, so we'll drop it to a
+  much smaller number, say 256::
+
+    # echo 'hist:key=child_comm:val=hitcount:size=256' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
+
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: ibus-daemon                         } hitcount:          1
+    { child_comm: whoopsie                            } hitcount:          1
+    { child_comm: smbd                                } hitcount:          1
+    { child_comm: gdbus                               } hitcount:          1
+    { child_comm: kthreadd                            } hitcount:          1
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: evolution-alarm                     } hitcount:          2
+    { child_comm: Socket Thread                       } hitcount:          2
+    { child_comm: postgres                            } hitcount:          2
+    { child_comm: bash                                } hitcount:          3
+    { child_comm: compiz                              } hitcount:          3
+    { child_comm: evolution-sourc                     } hitcount:          4
+    { child_comm: dhclient                            } hitcount:          4
+    { child_comm: pool                                } hitcount:          5
+    { child_comm: nm-dispatcher.a                     } hitcount:          8
+    { child_comm: firefox                             } hitcount:          8
+    { child_comm: dbus-daemon                         } hitcount:          8
+    { child_comm: glib-pacrunner                      } hitcount:         10
+    { child_comm: evolution                           } hitcount:         23
+
+    Totals:
+        Hits: 89
+        Entries: 20
+        Dropped: 0
+
+  If we want to pause the hist trigger, we can simply append :pause to
+  the command that started the trigger.  Notice that the trigger info
+  displays as [paused]::
+
+    # echo 'hist:key=child_comm:val=hitcount:size=256:pause' >> \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [paused]
+
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: kthreadd                            } hitcount:          1
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: gdbus                               } hitcount:          1
+    { child_comm: ibus-daemon                         } hitcount:          1
+    { child_comm: Socket Thread                       } hitcount:          2
+    { child_comm: evolution-alarm                     } hitcount:          2
+    { child_comm: smbd                                } hitcount:          2
+    { child_comm: bash                                } hitcount:          3
+    { child_comm: whoopsie                            } hitcount:          3
+    { child_comm: compiz                              } hitcount:          3
+    { child_comm: evolution-sourc                     } hitcount:          4
+    { child_comm: pool                                } hitcount:          5
+    { child_comm: postgres                            } hitcount:          6
+    { child_comm: firefox                             } hitcount:          8
+    { child_comm: dhclient                            } hitcount:         10
+    { child_comm: emacs                               } hitcount:         12
+    { child_comm: dbus-daemon                         } hitcount:         20
+    { child_comm: nm-dispatcher.a                     } hitcount:         20
+    { child_comm: evolution                           } hitcount:         35
+    { child_comm: glib-pacrunner                      } hitcount:         59
+
+    Totals:
+        Hits: 199
+        Entries: 21
+        Dropped: 0
+
+  To manually continue having the trigger aggregate events, append
+  :cont instead.  Notice that the trigger info displays as [active]
+  again, and the data has changed::
+
+    # echo 'hist:key=child_comm:val=hitcount:size=256:cont' >> \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
+
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: dconf worker                        } hitcount:          1
+    { child_comm: kthreadd                            } hitcount:          1
+    { child_comm: gdbus                               } hitcount:          1
+    { child_comm: ibus-daemon                         } hitcount:          1
+    { child_comm: Socket Thread                       } hitcount:          2
+    { child_comm: evolution-alarm                     } hitcount:          2
+    { child_comm: smbd                                } hitcount:          2
+    { child_comm: whoopsie                            } hitcount:          3
+    { child_comm: compiz                              } hitcount:          3
+    { child_comm: evolution-sourc                     } hitcount:          4
+    { child_comm: bash                                } hitcount:          5
+    { child_comm: pool                                } hitcount:          5
+    { child_comm: postgres                            } hitcount:          6
+    { child_comm: firefox                             } hitcount:          8
+    { child_comm: dhclient                            } hitcount:         11
+    { child_comm: emacs                               } hitcount:         12
+    { child_comm: dbus-daemon                         } hitcount:         22
+    { child_comm: nm-dispatcher.a                     } hitcount:         22
+    { child_comm: evolution                           } hitcount:         35
+    { child_comm: glib-pacrunner                      } hitcount:         59
+
+    Totals:
+        Hits: 206
+        Entries: 21
+        Dropped: 0
+
+  The previous example showed how to start and stop a hist trigger by
+  appending 'pause' and 'continue' to the hist trigger command.  A
+  hist trigger can also be started in a paused state by initially
+  starting the trigger with ':pause' appended.  This allows you to
+  start the trigger only when you're ready to start collecting data
+  and not before.  For example, you could start the trigger in a
+  paused state, then unpause it and do something you want to measure,
+  then pause the trigger again when done.
+
+  Of course, doing this manually can be difficult and error-prone, but
+  it is possible to automatically start and stop a hist trigger based
+  on some condition, via the enable_hist and disable_hist triggers.
+
+  For example, suppose we wanted to take a look at the relative
+  weights in terms of skb length for each callpath that leads to a
+  netif_receieve_skb event when downloading a decent-sized file using
+  wget.
+
+  First we set up an initially paused stacktrace trigger on the
+  netif_receive_skb event::
+
+    # echo 'hist:key=stacktrace:vals=len:pause' > \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+  Next, we set up an 'enable_hist' trigger on the sched_process_exec
+  event, with an 'if filename==/usr/bin/wget' filter.  The effect of
+  this new trigger is that it will 'unpause' the hist trigger we just
+  set up on netif_receive_skb if and only if it sees a
+  sched_process_exec event with a filename of '/usr/bin/wget'.  When
+  that happens, all netif_receive_skb events are aggregated into a
+  hash table keyed on stacktrace::
+
+    # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+  The aggregation continues until the netif_receive_skb is paused
+  again, which is what the following disable_hist event does by
+  creating a similar setup on the sched_process_exit event, using the
+  filter 'comm==wget'::
+
+    # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+  Whenever a process exits and the comm field of the disable_hist
+  trigger filter matches 'comm==wget', the netif_receive_skb hist
+  trigger is disabled.
+
+  The overall effect is that netif_receive_skb events are aggregated
+  into the hash table for only the duration of the wget.  Executing a
+  wget command and then listing the 'hist' file will display the
+  output generated by the wget command::
+
+    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
+
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         netif_receive_skb_internal+0x23/0x90
+         napi_gro_receive+0xc8/0x100
+         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
+         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
+         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
+         ieee80211_rx+0x31d/0x900 [mac80211]
+         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
+         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
+         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
+         irq_thread_fn+0x20/0x50
+         irq_thread+0x11f/0x150
+         kthread+0xd2/0xf0
+         ret_from_fork+0x42/0x70
+    } hitcount:         85  len:      28884
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         netif_receive_skb_internal+0x23/0x90
+         napi_gro_complete+0xa4/0xe0
+         dev_gro_receive+0x23a/0x360
+         napi_gro_receive+0x30/0x100
+         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
+         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
+         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
+         ieee80211_rx+0x31d/0x900 [mac80211]
+         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
+         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
+         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
+         irq_thread_fn+0x20/0x50
+         irq_thread+0x11f/0x150
+         kthread+0xd2/0xf0
+    } hitcount:         98  len:     664329
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         process_backlog+0xa8/0x150
+         net_rx_action+0x15d/0x340
+         __do_softirq+0x114/0x2c0
+         do_softirq_own_stack+0x1c/0x30
+         do_softirq+0x65/0x70
+         __local_bh_enable_ip+0xb5/0xc0
+         ip_finish_output+0x1f4/0x840
+         ip_output+0x6b/0xc0
+         ip_local_out_sk+0x31/0x40
+         ip_send_skb+0x1a/0x50
+         udp_send_skb+0x173/0x2a0
+         udp_sendmsg+0x2bf/0x9f0
+         inet_sendmsg+0x64/0xa0
+         sock_sendmsg+0x3d/0x50
+    } hitcount:        115  len:      13030
+    { stacktrace:
+         __netif_receive_skb_core+0x46d/0x990
+         __netif_receive_skb+0x18/0x60
+         netif_receive_skb_internal+0x23/0x90
+         napi_gro_complete+0xa4/0xe0
+         napi_gro_flush+0x6d/0x90
+         iwl_pcie_irq_handler+0x92a/0x12f0 [iwlwifi]
+         irq_thread_fn+0x20/0x50
+         irq_thread+0x11f/0x150
+         kthread+0xd2/0xf0
+         ret_from_fork+0x42/0x70
+    } hitcount:        934  len:    5512212
+
+    Totals:
+        Hits: 1232
+        Entries: 4
+        Dropped: 0
+
+  The above shows all the netif_receive_skb callpaths and their total
+  lengths for the duration of the wget command.
+
+  The 'clear' hist trigger param can be used to clear the hash table.
+  Suppose we wanted to try another run of the previous example but
+  this time also wanted to see the complete list of events that went
+  into the histogram.  In order to avoid having to set everything up
+  again, we can just clear the histogram first::
+
+    # echo 'hist:key=stacktrace:vals=len:clear' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+  Just to verify that it is in fact cleared, here's what we now see in
+  the hist file::
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
+
+    Totals:
+        Hits: 0
+        Entries: 0
+        Dropped: 0
+
+  Since we want to see the detailed list of every netif_receive_skb
+  event occurring during the new run, which are in fact the same
+  events being aggregated into the hash table, we add some additional
+  'enable_event' events to the triggering sched_process_exec and
+  sched_process_exit events as such::
+
+    # echo 'enable_event:net:netif_receive_skb if filename==/usr/bin/wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+    # echo 'disable_event:net:netif_receive_skb if comm==wget' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+  If you read the trigger files for the sched_process_exec and
+  sched_process_exit triggers, you should see two triggers for each:
+  one enabling/disabling the hist aggregation and the other
+  enabling/disabling the logging of events::
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+    enable_event:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
+    enable_hist:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+    enable_event:net:netif_receive_skb:unlimited if comm==wget
+    disable_hist:net:netif_receive_skb:unlimited if comm==wget
+
+  In other words, whenever either of the sched_process_exec or
+  sched_process_exit events is hit and matches 'wget', it enables or
+  disables both the histogram and the event log, and what you end up
+  with is a hash table and set of events just covering the specified
+  duration.  Run the wget command again::
+
+    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
+
+  Displaying the 'hist' file should show something similar to what you
+  saw in the last run, but this time you should also see the
+  individual events in the trace file::
+
+    # cat /sys/kernel/debug/tracing/trace
+
+    # tracer: nop
+    #
+    # entries-in-buffer/entries-written: 183/1426   #P:4
+    #
+    #                              _-----=> irqs-off
+    #                             / _----=> need-resched
+    #                            | / _---=> hardirq/softirq
+    #                            || / _--=> preempt-depth
+    #                            ||| /     delay
+    #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
+    #              | |       |   ||||       |         |
+                wget-15108 [000] ..s1 31769.606929: netif_receive_skb: dev=lo skbaddr=ffff88009c353100 len=60
+                wget-15108 [000] ..s1 31769.606999: netif_receive_skb: dev=lo skbaddr=ffff88009c353200 len=60
+             dnsmasq-1382  [000] ..s1 31769.677652: netif_receive_skb: dev=lo skbaddr=ffff88009c352b00 len=130
+             dnsmasq-1382  [000] ..s1 31769.685917: netif_receive_skb: dev=lo skbaddr=ffff88009c352200 len=138
+    ##### CPU 2 buffer started ####
+      irq/29-iwlwifi-559   [002] ..s. 31772.031529: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433d00 len=2948
+      irq/29-iwlwifi-559   [002] ..s. 31772.031572: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432200 len=1500
+      irq/29-iwlwifi-559   [002] ..s. 31772.032196: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433100 len=2948
+      irq/29-iwlwifi-559   [002] ..s. 31772.032761: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433000 len=2948
+      irq/29-iwlwifi-559   [002] ..s. 31772.033220: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432e00 len=1500
+    .
+    .
+    .
+
+  The following example demonstrates how multiple hist triggers can be
+  attached to a given event.  This capability can be useful for
+  creating a set of different summaries derived from the same set of
+  events, or for comparing the effects of different filters, among
+  other things::
+
+    # echo 'hist:keys=skbaddr.hex:vals=len if len < 0' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=skbaddr.hex:vals=len if len > 4096' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=skbaddr.hex:vals=len if len == 256' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=skbaddr.hex:vals=len' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:keys=len:vals=common_preempt_count' >> \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+  The above set of commands create four triggers differing only in
+  their filters, along with a completely different though fairly
+  nonsensical trigger.  Note that in order to append multiple hist
+  triggers to the same file, you should use the '>>' operator to
+  append them ('>' will also add the new hist trigger, but will remove
+  any existing hist triggers beforehand).
+
+  Displaying the contents of the 'hist' file for the event shows the
+  contents of all five histograms::
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+
+    # event histogram
+    #
+    # trigger info: hist:keys=len:vals=hitcount,common_preempt_count:sort=hitcount:size=2048 [active]
+    #
+
+    { len:        176 } hitcount:          1  common_preempt_count:          0
+    { len:        223 } hitcount:          1  common_preempt_count:          0
+    { len:       4854 } hitcount:          1  common_preempt_count:          0
+    { len:        395 } hitcount:          1  common_preempt_count:          0
+    { len:        177 } hitcount:          1  common_preempt_count:          0
+    { len:        446 } hitcount:          1  common_preempt_count:          0
+    { len:       1601 } hitcount:          1  common_preempt_count:          0
+    .
+    .
+    .
+    { len:       1280 } hitcount:         66  common_preempt_count:          0
+    { len:        116 } hitcount:         81  common_preempt_count:         40
+    { len:        708 } hitcount:        112  common_preempt_count:          0
+    { len:         46 } hitcount:        221  common_preempt_count:          0
+    { len:       1264 } hitcount:        458  common_preempt_count:          0
+
+    Totals:
+        Hits: 1428
+        Entries: 147
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+    #
+
+    { skbaddr: ffff8800baee5e00 } hitcount:          1  len:        130
+    { skbaddr: ffff88005f3d5600 } hitcount:          1  len:       1280
+    { skbaddr: ffff88005f3d4900 } hitcount:          1  len:       1280
+    { skbaddr: ffff88009fed6300 } hitcount:          1  len:        115
+    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:        115
+    { skbaddr: ffff88008cdb1900 } hitcount:          1  len:         46
+    { skbaddr: ffff880064b5ef00 } hitcount:          1  len:        118
+    { skbaddr: ffff880044e3c700 } hitcount:          1  len:         60
+    { skbaddr: ffff880100065900 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d46bd500 } hitcount:          1  len:        116
+    { skbaddr: ffff88005f3d5f00 } hitcount:          1  len:       1280
+    { skbaddr: ffff880100064700 } hitcount:          1  len:        365
+    { skbaddr: ffff8800badb6f00 } hitcount:          1  len:         60
+    .
+    .
+    .
+    { skbaddr: ffff88009fe0be00 } hitcount:         27  len:      24677
+    { skbaddr: ffff88009fe0a400 } hitcount:         27  len:      23052
+    { skbaddr: ffff88009fe0b700 } hitcount:         31  len:      25589
+    { skbaddr: ffff88009fe0b600 } hitcount:         32  len:      27326
+    { skbaddr: ffff88006a462800 } hitcount:         68  len:      71678
+    { skbaddr: ffff88006a463700 } hitcount:         70  len:      72678
+    { skbaddr: ffff88006a462b00 } hitcount:         71  len:      77589
+    { skbaddr: ffff88006a463600 } hitcount:         73  len:      71307
+    { skbaddr: ffff88006a462200 } hitcount:         81  len:      81032
+
+    Totals:
+        Hits: 1451
+        Entries: 318
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len == 256 [active]
+    #
+
+
+    Totals:
+        Hits: 0
+        Entries: 0
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len > 4096 [active]
+    #
+
+    { skbaddr: ffff88009fd2c300 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcce00 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcd700 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcda00 } hitcount:          1  len:      21492
+    { skbaddr: ffff8800ae2e2d00 } hitcount:          1  len:       7212
+    { skbaddr: ffff8800d2bcdb00 } hitcount:          1  len:       7212
+    { skbaddr: ffff88006a4df500 } hitcount:          1  len:       4854
+    { skbaddr: ffff88008ce47b00 } hitcount:          1  len:      18636
+    { skbaddr: ffff8800ae2e2200 } hitcount:          1  len:      12924
+    { skbaddr: ffff88005f3e1000 } hitcount:          1  len:       4356
+    { skbaddr: ffff8800d2bcdc00 } hitcount:          2  len:      24420
+    { skbaddr: ffff8800d2bcc200 } hitcount:          2  len:      12996
+
+    Totals:
+        Hits: 14
+        Entries: 12
+        Dropped: 0
+
+
+    # event histogram
+    #
+    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len < 0 [active]
+    #
+
+
+    Totals:
+        Hits: 0
+        Entries: 0
+        Dropped: 0
+
+  Named triggers can be used to have triggers share a common set of
+  histogram data.  This capability is mostly useful for combining the
+  output of events generated by tracepoints contained inside inline
+  functions, but names can be used in a hist trigger on any event.
+  For example, these two triggers when hit will update the same 'len'
+  field in the shared 'foo' histogram data::
+
+    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
+           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
+           /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+  You can see that they're updating common histogram data by reading
+  each event's hist files at the same time::
+
+    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist;
+      cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+    # event histogram
+    #
+    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+    #
+
+    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
+    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
+    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
+    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
+    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
+    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
+    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
+    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
+    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
+    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
+    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
+    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
+    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
+    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
+    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
+    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
+    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
+    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
+    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
+    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
+    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
+    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
+    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
+    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
+    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
+    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
+    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
+    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
+    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
+    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
+    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
+    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
+    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
+    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
+    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
+    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
+    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
+
+    Totals:
+        Hits: 81
+        Entries: 42
+        Dropped: 0
+    # event histogram
+    #
+    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+    #
+
+    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
+    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
+    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
+    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
+    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
+    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
+    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
+    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
+    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
+    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
+    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
+    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
+    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
+    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
+    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
+    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
+    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
+    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
+    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
+    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
+    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
+    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
+    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
+    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
+    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
+    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
+    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
+    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
+    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
+    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
+    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
+    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
+    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
+    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
+    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
+    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
+    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
+    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
+
+    Totals:
+        Hits: 81
+        Entries: 42
+        Dropped: 0
+
+  And here's an example that shows how to combine histogram data from
+  any two events even if they don't share any 'compatible' fields
+  other than 'hitcount' and 'stacktrace'.  These commands create a
+  couple of triggers named 'bar' using those fields::
+
+    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
+           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
+          /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+  And displaying the output of either shows some interesting if
+  somewhat confusing output::
+
+    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+    # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+    # event histogram
+    #
+    # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active]
+    #
+
+    { stacktrace:
+             _do_fork+0x18e/0x330
+             kernel_thread+0x29/0x30
+             kthreadd+0x154/0x1b0
+             ret_from_fork+0x3f/0x70
+    } hitcount:          1
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx_ni+0x20/0x70
+             dev_loopback_xmit+0xaa/0xd0
+             ip_mc_output+0x126/0x240
+             ip_local_out_sk+0x31/0x40
+             igmp_send_report+0x1e9/0x230
+             igmp_timer_expire+0xe9/0x120
+             call_timer_fn+0x39/0xf0
+             run_timer_softirq+0x1e1/0x290
+             __do_softirq+0xfd/0x290
+             irq_exit+0x98/0xb0
+             smp_apic_timer_interrupt+0x4a/0x60
+             apic_timer_interrupt+0x6d/0x80
+             cpuidle_enter+0x17/0x20
+             call_cpuidle+0x3b/0x60
+             cpu_startup_entry+0x22d/0x310
+    } hitcount:          1
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx_ni+0x20/0x70
+             dev_loopback_xmit+0xaa/0xd0
+             ip_mc_output+0x17f/0x240
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x13e/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             SYSC_sendto+0xef/0x170
+             SyS_sendto+0xe/0x10
+             entry_SYSCALL_64_fastpath+0x12/0x6a
+    } hitcount:          2
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx+0x1c/0x60
+             loopback_xmit+0x6c/0xb0
+             dev_hard_start_xmit+0x219/0x3a0
+             __dev_queue_xmit+0x415/0x4f0
+             dev_queue_xmit_sk+0x13/0x20
+             ip_finish_output2+0x237/0x340
+             ip_finish_output+0x113/0x1d0
+             ip_output+0x66/0xc0
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x16d/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             ___sys_sendmsg+0x14e/0x270
+    } hitcount:         76
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx+0x1c/0x60
+             loopback_xmit+0x6c/0xb0
+             dev_hard_start_xmit+0x219/0x3a0
+             __dev_queue_xmit+0x415/0x4f0
+             dev_queue_xmit_sk+0x13/0x20
+             ip_finish_output2+0x237/0x340
+             ip_finish_output+0x113/0x1d0
+             ip_output+0x66/0xc0
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x16d/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             ___sys_sendmsg+0x269/0x270
+    } hitcount:         77
+    { stacktrace:
+             netif_rx_internal+0xb2/0xd0
+             netif_rx+0x1c/0x60
+             loopback_xmit+0x6c/0xb0
+             dev_hard_start_xmit+0x219/0x3a0
+             __dev_queue_xmit+0x415/0x4f0
+             dev_queue_xmit_sk+0x13/0x20
+             ip_finish_output2+0x237/0x340
+             ip_finish_output+0x113/0x1d0
+             ip_output+0x66/0xc0
+             ip_local_out_sk+0x31/0x40
+             ip_send_skb+0x1a/0x50
+             udp_send_skb+0x16d/0x270
+             udp_sendmsg+0x2bf/0x980
+             inet_sendmsg+0x67/0xa0
+             sock_sendmsg+0x38/0x50
+             SYSC_sendto+0xef/0x170
+    } hitcount:         88
+    { stacktrace:
+             _do_fork+0x18e/0x330
+             SyS_clone+0x19/0x20
+             entry_SYSCALL_64_fastpath+0x12/0x6a
+    } hitcount:        244
+
+    Totals:
+        Hits: 489
+        Entries: 7
+        Dropped: 0
+
+2.2 Inter-event hist triggers
+-----------------------------
+
+Inter-event hist triggers are hist triggers that combine values from
+one or more other events and create a histogram using that data.  Data
+from an inter-event histogram can in turn become the source for
+further combined histograms, thus providing a chain of related
+histograms, which is important for some applications.
+
+The most important example of an inter-event quantity that can be used
+in this manner is latency, which is simply a difference in timestamps
+between two events.  Although latency is the most important
+inter-event quantity, note that because the support is completely
+general across the trace event subsystem, any event field can be used
+in an inter-event quantity.
+
+An example of a histogram that combines data from other histograms
+into a useful chain would be a 'wakeupswitch latency' histogram that
+combines a 'wakeup latency' histogram and a 'switch latency'
+histogram.
+
+Normally, a hist trigger specification consists of a (possibly
+compound) key along with one or more numeric values, which are
+continually updated sums associated with that key.  A histogram
+specification in this case consists of individual key and value
+specifications that refer to trace event fields associated with a
+single event type.
+
+The inter-event hist trigger extension allows fields from multiple
+events to be referenced and combined into a multi-event histogram
+specification.  In support of this overall goal, a few enabling
+features have been added to the hist trigger support:
+
+  - In order to compute an inter-event quantity, a value from one
+    event needs to saved and then referenced from another event.  This
+    requires the introduction of support for histogram 'variables'.
+
+  - The computation of inter-event quantities and their combination
+    require some minimal amount of support for applying simple
+    expressions to variables (+ and -).
+
+  - A histogram consisting of inter-event quantities isn't logically a
+    histogram on either event (so having the 'hist' file for either
+    event host the histogram output doesn't really make sense).  To
+    address the idea that the histogram is associated with a
+    combination of events, support is added allowing the creation of
+    'synthetic' events that are events derived from other events.
+    These synthetic events are full-fledged events just like any other
+    and can be used as such, as for instance to create the
+    'combination' histograms mentioned previously.
+
+  - A set of 'actions' can be associated with histogram entries -
+    these can be used to generate the previously mentioned synthetic
+    events, but can also be used for other purposes, such as for
+    example saving context when a 'max' latency has been hit.
+
+  - Trace events don't have a 'timestamp' associated with them, but
+    there is an implicit timestamp saved along with an event in the
+    underlying ftrace ring buffer.  This timestamp is now exposed as a
+    a synthetic field named 'common_timestamp' which can be used in
+    histograms as if it were any other event field; it isn't an actual
+    field in the trace format but rather is a synthesized value that
+    nonetheless can be used as if it were an actual field.  By default
+    it is in units of nanoseconds; appending '.usecs' to a
+    common_timestamp field changes the units to microseconds.
+
+A note on inter-event timestamps: If common_timestamp is used in a
+histogram, the trace buffer is automatically switched over to using
+absolute timestamps and the "global" trace clock, in order to avoid
+bogus timestamp differences with other clocks that aren't coherent
+across CPUs.  This can be overridden by specifying one of the other
+trace clocks instead, using the "clock=XXX" hist trigger attribute,
+where XXX is any of the clocks listed in the tracing/trace_clock
+pseudo-file.
+
+These features are described in more detail in the following sections.
+
+2.2.1 Histogram Variables
+-------------------------
+
+Variables are simply named locations used for saving and retrieving
+values between matching events.  A 'matching' event is defined as an
+event that has a matching key - if a variable is saved for a histogram
+entry corresponding to that key, any subsequent event with a matching
+key can access that variable.
+
+A variable's value is normally available to any subsequent event until
+it is set to something else by a subsequent event.  The one exception
+to that rule is that any variable used in an expression is essentially
+'read-once' - once it's used by an expression in a subsequent event,
+it's reset to its 'unset' state, which means it can't be used again
+unless it's set again.  This ensures not only that an event doesn't
+use an uninitialized variable in a calculation, but that that variable
+is used only once and not for any unrelated subsequent match.
+
+The basic syntax for saving a variable is to simply prefix a unique
+variable name not corresponding to any keyword along with an '=' sign
+to any event field.
+
+Either keys or values can be saved and retrieved in this way.  This
+creates a variable named 'ts0' for a histogram entry with the key
+'next_pid'::
+
+  # echo 'hist:keys=next_pid:vals=$ts0:ts0=common_timestamp ... >> \
+	event/trigger
+
+The ts0 variable can be accessed by any subsequent event having the
+same pid as 'next_pid'.
+
+Variable references are formed by prepending the variable name with
+the '$' sign.  Thus for example, the ts0 variable above would be
+referenced as '$ts0' in expressions.
+
+Because 'vals=' is used, the common_timestamp variable value above
+will also be summed as a normal histogram value would (though for a
+timestamp it makes little sense).
+
+The below shows that a key value can also be saved in the same way::
+
+  # echo 'hist:timer_pid=common_pid:key=timer_pid ...' >> event/trigger
+
+If a variable isn't a key variable or prefixed with 'vals=', the
+associated event field will be saved in a variable but won't be summed
+as a value::
+
+  # echo 'hist:keys=next_pid:ts1=common_timestamp ...' >> event/trigger
+
+Multiple variables can be assigned at the same time.  The below would
+result in both ts0 and b being created as variables, with both
+common_timestamp and field1 additionally being summed as values::
+
+  # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ...' >> \
+	event/trigger
+
+Note that variable assignments can appear either preceding or
+following their use.  The command below behaves identically to the
+command above::
+
+  # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ...' >> \
+	event/trigger
+
+Any number of variables not bound to a 'vals=' prefix can also be
+assigned by simply separating them with colons.  Below is the same
+thing but without the values being summed in the histogram::
+
+  # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ...' >> event/trigger
+
+Variables set as above can be referenced and used in expressions on
+another event.
+
+For example, here's how a latency can be calculated::
+
+  # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger
+  # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger
+
+In the first line above, the event's timetamp is saved into the
+variable ts0.  In the next line, ts0 is subtracted from the second
+event's timestamp to produce the latency, which is then assigned into
+yet another variable, 'wakeup_lat'.  The hist trigger below in turn
+makes use of the wakeup_lat variable to compute a combined latency
+using the same key and variable from yet another event::
+
+  # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ...' >> event3/trigger
+
+2.2.2 Synthetic Events
+----------------------
+
+Synthetic events are user-defined events generated from hist trigger
+variables or fields associated with one or more other events.  Their
+purpose is to provide a mechanism for displaying data spanning
+multiple events consistent with the existing and already familiar
+usage for normal events.
+
+To define a synthetic event, the user writes a simple specification
+consisting of the name of the new event along with one or more
+variables and their types, which can be any valid field type,
+separated by semicolons, to the tracing/synthetic_events file.
+
+For instance, the following creates a new event named 'wakeup_latency'
+with 3 fields: lat, pid, and prio.  Each of those fields is simply a
+variable reference to a variable on another event::
+
+  # echo 'wakeup_latency \
+          u64 lat; \
+          pid_t pid; \
+	  int prio' >> \
+	  /sys/kernel/debug/tracing/synthetic_events
+
+Reading the tracing/synthetic_events file lists all the currently
+defined synthetic events, in this case the event defined above::
+
+  # cat /sys/kernel/debug/tracing/synthetic_events
+    wakeup_latency u64 lat; pid_t pid; int prio
+
+An existing synthetic event definition can be removed by prepending
+the command that defined it with a '!'::
+
+  # echo '!wakeup_latency u64 lat pid_t pid int prio' >> \
+    /sys/kernel/debug/tracing/synthetic_events
+
+At this point, there isn't yet an actual 'wakeup_latency' event
+instantiated in the event subsytem - for this to happen, a 'hist
+trigger action' needs to be instantiated and bound to actual fields
+and variables defined on other events (see Section 2.2.3 below on
+how that is done using hist trigger 'onmatch' action). Once that is
+done, the 'wakeup_latency' synthetic event instance is created.
+
+A histogram can now be defined for the new synthetic event::
+
+  # echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
+        /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
+
+The new event is created under the tracing/events/synthetic/ directory
+and looks and behaves just like any other event::
+
+  # ls /sys/kernel/debug/tracing/events/synthetic/wakeup_latency
+        enable  filter  format  hist  id  trigger
+
+Like any other event, once a histogram is enabled for the event, the
+output can be displayed by reading the event's 'hist' file.
+
+2.2.3 Hist trigger 'actions'
+----------------------------
+
+A hist trigger 'action' is a function that's executed whenever a
+histogram entry is added or updated.
+
+The default 'action' if no special function is explicity specified is
+as it always has been, to simply update the set of values associated
+with an entry.  Some applications, however, may want to perform
+additional actions at that point, such as generate another event, or
+compare and save a maximum.
+
+The following additional actions are available.  To specify an action
+for a given event, simply specify the action between colons in the
+hist trigger specification.
+
+  - onmatch(matching.event).<synthetic_event_name>(param list)
+
+    The 'onmatch(matching.event).<synthetic_event_name>(params)' hist
+    trigger action is invoked whenever an event matches and the
+    histogram entry would be added or updated.  It causes the named
+    synthetic event to be generated with the values given in the
+    'param list'.  The result is the generation of a synthetic event
+    that consists of the values contained in those variables at the
+    time the invoking event was hit.
+
+    The 'param list' consists of one or more parameters which may be
+    either variables or fields defined on either the 'matching.event'
+    or the target event.  The variables or fields specified in the
+    param list may be either fully-qualified or unqualified.  If a
+    variable is specified as unqualified, it must be unique between
+    the two events.  A field name used as a param can be unqualified
+    if it refers to the target event, but must be fully qualified if
+    it refers to the matching event.  A fully-qualified name is of the
+    form 'system.event_name.$var_name' or 'system.event_name.field'.
+
+    The 'matching.event' specification is simply the fully qualified
+    event name of the event that matches the target event for the
+    onmatch() functionality, in the form 'system.event_name'.
+
+    Finally, the number and type of variables/fields in the 'param
+    list' must match the number and types of the fields in the
+    synthetic event being generated.
+
+    As an example the below defines a simple synthetic event and uses
+    a variable defined on the sched_wakeup_new event as a parameter
+    when invoking the synthetic event.  Here we define the synthetic
+    event::
+
+      # echo 'wakeup_new_test pid_t pid' >> \
+             /sys/kernel/debug/tracing/synthetic_events
+
+      # cat /sys/kernel/debug/tracing/synthetic_events
+            wakeup_new_test pid_t pid
+
+    The following hist trigger both defines the missing testpid
+    variable and specifies an onmatch() action that generates a
+    wakeup_new_test synthetic event whenever a sched_wakeup_new event
+    occurs, which because of the 'if comm == "cyclictest"' filter only
+    happens when the executable is cyclictest::
+
+      # echo 'hist:keys=$testpid:testpid=pid:onmatch(sched.sched_wakeup_new).\
+              wakeup_new_test($testpid) if comm=="cyclictest"' >> \
+              /sys/kernel/debug/tracing/events/sched/sched_wakeup_new/trigger
+
+    Creating and displaying a histogram based on those events is now
+    just a matter of using the fields and new synthetic event in the
+    tracing/events/synthetic directory, as usual::
+
+      # echo 'hist:keys=pid:sort=pid' >> \
+             /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/trigger
+
+    Running 'cyclictest' should cause wakeup_new events to generate
+    wakeup_new_test synthetic events which should result in histogram
+    output in the wakeup_new_test event's hist file::
+
+      # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/hist
+
+    A more typical usage would be to use two events to calculate a
+    latency.  The following example uses a set of hist triggers to
+    produce a 'wakeup_latency' histogram.
+
+    First, we define a 'wakeup_latency' synthetic event::
+
+      # echo 'wakeup_latency u64 lat; pid_t pid; int prio' >> \
+              /sys/kernel/debug/tracing/synthetic_events
+
+    Next, we specify that whenever we see a sched_waking event for a
+    cyclictest thread, save the timestamp in a 'ts0' variable::
+
+      # echo 'hist:keys=$saved_pid:saved_pid=pid:ts0=common_timestamp.usecs \
+              if comm=="cyclictest"' >> \
+	      /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+
+    Then, when the corresponding thread is actually scheduled onto the
+    CPU by a sched_switch event, calculate the latency and use that
+    along with another variable and an event field to generate a
+    wakeup_latency synthetic event::
+
+      # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:\
+              onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,\
+	              $saved_pid,next_prio) if next_comm=="cyclictest"' >> \
+	      /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+
+    We also need to create a histogram on the wakeup_latency synthetic
+    event in order to aggregate the generated synthetic event data::
+
+      # echo 'hist:keys=pid,prio,lat:sort=pid,lat' >> \
+              /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
+
+    Finally, once we've run cyclictest to actually generate some
+    events, we can see the output by looking at the wakeup_latency
+    synthetic event's hist file::
+
+      # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/hist
+
+  - onmax(var).save(field,..	.)
+
+    The 'onmax(var).save(field,...)' hist trigger action is invoked
+    whenever the value of 'var' associated with a histogram entry
+    exceeds the current maximum contained in that variable.
+
+    The end result is that the trace event fields specified as the
+    onmax.save() params will be saved if 'var' exceeds the current
+    maximum for that hist trigger entry.  This allows context from the
+    event that exhibited the new maximum to be saved for later
+    reference.  When the histogram is displayed, additional fields
+    displaying the saved values will be printed.
+
+    As an example the below defines a couple of hist triggers, one for
+    sched_waking and another for sched_switch, keyed on pid.  Whenever
+    a sched_waking occurs, the timestamp is saved in the entry
+    corresponding to the current pid, and when the scheduler switches
+    back to that pid, the timestamp difference is calculated.  If the
+    resulting latency, stored in wakeup_lat, exceeds the current
+    maximum latency, the values specified in the save() fields are
+    recorded::
+
+      # echo 'hist:keys=pid:ts0=common_timestamp.usecs \
+              if comm=="cyclictest"' >> \
+              /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+
+      # echo 'hist:keys=next_pid:\
+              wakeup_lat=common_timestamp.usecs-$ts0:\
+              onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) \
+              if next_comm=="cyclictest"' >> \
+              /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+
+    When the histogram is displayed, the max value and the saved
+    values corresponding to the max are displayed following the rest
+    of the fields::
+
+      # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist
+        { next_pid:       2255 } hitcount:        239
+          common_timestamp-ts0:          0
+          max:         27
+	  next_comm: cyclictest
+          prev_pid:          0  prev_prio:        120  prev_comm: swapper/1
+
+        { next_pid:       2256 } hitcount:       2355
+          common_timestamp-ts0: 0
+          max:         49  next_comm: cyclictest
+          prev_pid:          0  prev_prio:        120  prev_comm: swapper/0
+
+        Totals:
+            Hits: 12970
+            Entries: 2
+            Dropped: 0
+
+3. User space creating a trigger
+--------------------------------
+
+Writing into /sys/kernel/tracing/trace_marker writes into the ftrace
+ring buffer. This can also act like an event, by writing into the trigger
+file located in /sys/kernel/tracing/events/ftrace/print/
+
+Modifying cyclictest to write into the trace_marker file before it sleeps
+and after it wakes up, something like this::
+
+  static void traceputs(char *str)
+  {
+	/* tracemark_fd is the trace_marker file descriptor */
+	if (tracemark_fd < 0)
+		return;
+	/* write the tracemark message */
+	write(tracemark_fd, str, strlen(str));
+  }
+
+And later add something like::
+
+	traceputs("start");
+	clock_nanosleep(...);
+	traceputs("end");
+
+We can make a histogram from this::
+
+ # cd /sys/kernel/tracing
+ # echo 'latency u64 lat' > synthetic_events
+ # echo 'hist:keys=common_pid:ts0=common_timestamp.usecs if buf == "start"' > events/ftrace/print/trigger
+ # echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(ftrace.print).latency($lat) if buf == "end"' >> events/ftrace/print/trigger
+ # echo 'hist:keys=lat,common_pid:sort=lat' > events/synthetic/latency/trigger
+
+The above created a synthetic event called "latency" and two histograms
+against the trace_marker, one gets triggered when "start" is written into the
+trace_marker file and the other when "end" is written. If the pids match, then
+it will call the "latency" synthetic event with the calculated latency as its
+parameter. Finally, a histogram is added to the latency synthetic event to
+record the calculated latency along with the pid.
+
+Now running cyclictest with::
+
+ # ./cyclictest -p80 -d0 -i250 -n -a -t --tracemark -b 1000
+
+ -p80  : run threads at priority 80
+ -d0   : have all threads run at the same interval
+ -i250 : start the interval at 250 microseconds (all threads will do this)
+ -n    : sleep with nanosleep
+ -a    : affine all threads to a separate CPU
+ -t    : one thread per available CPU
+ --tracemark : enable trace mark writing
+ -b 1000 : stop if any latency is greater than 1000 microseconds
+
+Note, the -b 1000 is used just to make --tracemark available.
+
+Then we can see the histogram created by this with::
+
+ # cat events/synthetic/latency/hist
+ # event histogram
+ #
+ # trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
+ #
+
+ { lat:        107, common_pid:       2039 } hitcount:          1
+ { lat:        122, common_pid:       2041 } hitcount:          1
+ { lat:        166, common_pid:       2039 } hitcount:          1
+ { lat:        174, common_pid:       2039 } hitcount:          1
+ { lat:        194, common_pid:       2041 } hitcount:          1
+ { lat:        196, common_pid:       2036 } hitcount:          1
+ { lat:        197, common_pid:       2038 } hitcount:          1
+ { lat:        198, common_pid:       2039 } hitcount:          1
+ { lat:        199, common_pid:       2039 } hitcount:          1
+ { lat:        200, common_pid:       2041 } hitcount:          1
+ { lat:        201, common_pid:       2039 } hitcount:          2
+ { lat:        202, common_pid:       2038 } hitcount:          1
+ { lat:        202, common_pid:       2043 } hitcount:          1
+ { lat:        203, common_pid:       2039 } hitcount:          1
+ { lat:        203, common_pid:       2036 } hitcount:          1
+ { lat:        203, common_pid:       2041 } hitcount:          1
+ { lat:        206, common_pid:       2038 } hitcount:          2
+ { lat:        207, common_pid:       2039 } hitcount:          1
+ { lat:        207, common_pid:       2036 } hitcount:          1
+ { lat:        208, common_pid:       2040 } hitcount:          1
+ { lat:        209, common_pid:       2043 } hitcount:          1
+ { lat:        210, common_pid:       2039 } hitcount:          1
+ { lat:        211, common_pid:       2039 } hitcount:          4
+ { lat:        212, common_pid:       2043 } hitcount:          1
+ { lat:        212, common_pid:       2039 } hitcount:          2
+ { lat:        213, common_pid:       2039 } hitcount:          1
+ { lat:        214, common_pid:       2038 } hitcount:          1
+ { lat:        214, common_pid:       2039 } hitcount:          2
+ { lat:        214, common_pid:       2042 } hitcount:          1
+ { lat:        215, common_pid:       2039 } hitcount:          1
+ { lat:        217, common_pid:       2036 } hitcount:          1
+ { lat:        217, common_pid:       2040 } hitcount:          1
+ { lat:        217, common_pid:       2039 } hitcount:          1
+ { lat:        218, common_pid:       2039 } hitcount:          6
+ { lat:        219, common_pid:       2039 } hitcount:          9
+ { lat:        220, common_pid:       2039 } hitcount:         11
+ { lat:        221, common_pid:       2039 } hitcount:          5
+ { lat:        221, common_pid:       2042 } hitcount:          1
+ { lat:        222, common_pid:       2039 } hitcount:          7
+ { lat:        223, common_pid:       2036 } hitcount:          1
+ { lat:        223, common_pid:       2039 } hitcount:          3
+ { lat:        224, common_pid:       2039 } hitcount:          4
+ { lat:        224, common_pid:       2037 } hitcount:          1
+ { lat:        224, common_pid:       2036 } hitcount:          2
+ { lat:        225, common_pid:       2039 } hitcount:          5
+ { lat:        225, common_pid:       2042 } hitcount:          1
+ { lat:        226, common_pid:       2039 } hitcount:          7
+ { lat:        226, common_pid:       2036 } hitcount:          4
+ { lat:        227, common_pid:       2039 } hitcount:          6
+ { lat:        227, common_pid:       2036 } hitcount:         12
+ { lat:        227, common_pid:       2043 } hitcount:          1
+ { lat:        228, common_pid:       2039 } hitcount:          7
+ { lat:        228, common_pid:       2036 } hitcount:         14
+ { lat:        229, common_pid:       2039 } hitcount:          9
+ { lat:        229, common_pid:       2036 } hitcount:          8
+ { lat:        229, common_pid:       2038 } hitcount:          1
+ { lat:        230, common_pid:       2039 } hitcount:         11
+ { lat:        230, common_pid:       2036 } hitcount:          6
+ { lat:        230, common_pid:       2043 } hitcount:          1
+ { lat:        230, common_pid:       2042 } hitcount:          2
+ { lat:        231, common_pid:       2041 } hitcount:          1
+ { lat:        231, common_pid:       2036 } hitcount:          6
+ { lat:        231, common_pid:       2043 } hitcount:          1
+ { lat:        231, common_pid:       2039 } hitcount:          8
+ { lat:        232, common_pid:       2037 } hitcount:          1
+ { lat:        232, common_pid:       2039 } hitcount:          6
+ { lat:        232, common_pid:       2040 } hitcount:          2
+ { lat:        232, common_pid:       2036 } hitcount:          5
+ { lat:        232, common_pid:       2043 } hitcount:          1
+ { lat:        233, common_pid:       2036 } hitcount:          5
+ { lat:        233, common_pid:       2039 } hitcount:         11
+ { lat:        234, common_pid:       2039 } hitcount:          4
+ { lat:        234, common_pid:       2038 } hitcount:          2
+ { lat:        234, common_pid:       2043 } hitcount:          2
+ { lat:        234, common_pid:       2036 } hitcount:         11
+ { lat:        234, common_pid:       2040 } hitcount:          1
+ { lat:        235, common_pid:       2037 } hitcount:          2
+ { lat:        235, common_pid:       2036 } hitcount:          8
+ { lat:        235, common_pid:       2043 } hitcount:          2
+ { lat:        235, common_pid:       2039 } hitcount:          5
+ { lat:        235, common_pid:       2042 } hitcount:          2
+ { lat:        235, common_pid:       2040 } hitcount:          4
+ { lat:        235, common_pid:       2041 } hitcount:          1
+ { lat:        236, common_pid:       2036 } hitcount:          7
+ { lat:        236, common_pid:       2037 } hitcount:          1
+ { lat:        236, common_pid:       2041 } hitcount:          5
+ { lat:        236, common_pid:       2039 } hitcount:          3
+ { lat:        236, common_pid:       2043 } hitcount:          9
+ { lat:        236, common_pid:       2040 } hitcount:          7
+ { lat:        237, common_pid:       2037 } hitcount:          1
+ { lat:        237, common_pid:       2040 } hitcount:          1
+ { lat:        237, common_pid:       2036 } hitcount:          9
+ { lat:        237, common_pid:       2039 } hitcount:          3
+ { lat:        237, common_pid:       2043 } hitcount:          8
+ { lat:        237, common_pid:       2042 } hitcount:          2
+ { lat:        237, common_pid:       2041 } hitcount:          2
+ { lat:        238, common_pid:       2043 } hitcount:         10
+ { lat:        238, common_pid:       2040 } hitcount:          1
+ { lat:        238, common_pid:       2037 } hitcount:          9
+ { lat:        238, common_pid:       2038 } hitcount:          1
+ { lat:        238, common_pid:       2039 } hitcount:          1
+ { lat:        238, common_pid:       2042 } hitcount:          3
+ { lat:        238, common_pid:       2036 } hitcount:          7
+ { lat:        239, common_pid:       2041 } hitcount:          1
+ { lat:        239, common_pid:       2043 } hitcount:         11
+ { lat:        239, common_pid:       2037 } hitcount:         11
+ { lat:        239, common_pid:       2038 } hitcount:          6
+ { lat:        239, common_pid:       2036 } hitcount:          7
+ { lat:        239, common_pid:       2040 } hitcount:          1
+ { lat:        239, common_pid:       2042 } hitcount:          9
+ { lat:        240, common_pid:       2037 } hitcount:         29
+ { lat:        240, common_pid:       2043 } hitcount:         15
+ { lat:        240, common_pid:       2040 } hitcount:         44
+ { lat:        240, common_pid:       2039 } hitcount:          1
+ { lat:        240, common_pid:       2041 } hitcount:          2
+ { lat:        240, common_pid:       2038 } hitcount:          1
+ { lat:        240, common_pid:       2036 } hitcount:         10
+ { lat:        240, common_pid:       2042 } hitcount:         13
+ { lat:        241, common_pid:       2036 } hitcount:         21
+ { lat:        241, common_pid:       2041 } hitcount:         36
+ { lat:        241, common_pid:       2037 } hitcount:         34
+ { lat:        241, common_pid:       2042 } hitcount:         14
+ { lat:        241, common_pid:       2040 } hitcount:         94
+ { lat:        241, common_pid:       2039 } hitcount:         12
+ { lat:        241, common_pid:       2038 } hitcount:          2
+ { lat:        241, common_pid:       2043 } hitcount:         28
+ { lat:        242, common_pid:       2040 } hitcount:        109
+ { lat:        242, common_pid:       2041 } hitcount:        506
+ { lat:        242, common_pid:       2039 } hitcount:        155
+ { lat:        242, common_pid:       2042 } hitcount:         21
+ { lat:        242, common_pid:       2037 } hitcount:         52
+ { lat:        242, common_pid:       2043 } hitcount:         21
+ { lat:        242, common_pid:       2036 } hitcount:         16
+ { lat:        242, common_pid:       2038 } hitcount:        156
+ { lat:        243, common_pid:       2037 } hitcount:         46
+ { lat:        243, common_pid:       2039 } hitcount:         40
+ { lat:        243, common_pid:       2042 } hitcount:        119
+ { lat:        243, common_pid:       2041 } hitcount:        611
+ { lat:        243, common_pid:       2036 } hitcount:         69
+ { lat:        243, common_pid:       2038 } hitcount:        784
+ { lat:        243, common_pid:       2040 } hitcount:        323
+ { lat:        243, common_pid:       2043 } hitcount:         14
+ { lat:        244, common_pid:       2043 } hitcount:         35
+ { lat:        244, common_pid:       2042 } hitcount:        305
+ { lat:        244, common_pid:       2039 } hitcount:          8
+ { lat:        244, common_pid:       2040 } hitcount:       4515
+ { lat:        244, common_pid:       2038 } hitcount:        371
+ { lat:        244, common_pid:       2037 } hitcount:         31
+ { lat:        244, common_pid:       2036 } hitcount:        114
+ { lat:        244, common_pid:       2041 } hitcount:       3396
+ { lat:        245, common_pid:       2036 } hitcount:        700
+ { lat:        245, common_pid:       2041 } hitcount:       2772
+ { lat:        245, common_pid:       2037 } hitcount:        268
+ { lat:        245, common_pid:       2039 } hitcount:        472
+ { lat:        245, common_pid:       2038 } hitcount:       2758
+ { lat:        245, common_pid:       2042 } hitcount:       3833
+ { lat:        245, common_pid:       2040 } hitcount:       3105
+ { lat:        245, common_pid:       2043 } hitcount:        645
+ { lat:        246, common_pid:       2038 } hitcount:       3451
+ { lat:        246, common_pid:       2041 } hitcount:        142
+ { lat:        246, common_pid:       2037 } hitcount:       5101
+ { lat:        246, common_pid:       2040 } hitcount:         68
+ { lat:        246, common_pid:       2043 } hitcount:       5099
+ { lat:        246, common_pid:       2039 } hitcount:       5608
+ { lat:        246, common_pid:       2042 } hitcount:       3723
+ { lat:        246, common_pid:       2036 } hitcount:       4738
+ { lat:        247, common_pid:       2042 } hitcount:        312
+ { lat:        247, common_pid:       2043 } hitcount:       2385
+ { lat:        247, common_pid:       2041 } hitcount:        452
+ { lat:        247, common_pid:       2038 } hitcount:        792
+ { lat:        247, common_pid:       2040 } hitcount:         78
+ { lat:        247, common_pid:       2036 } hitcount:       2375
+ { lat:        247, common_pid:       2039 } hitcount:       1834
+ { lat:        247, common_pid:       2037 } hitcount:       2655
+ { lat:        248, common_pid:       2037 } hitcount:         36
+ { lat:        248, common_pid:       2042 } hitcount:         11
+ { lat:        248, common_pid:       2038 } hitcount:        122
+ { lat:        248, common_pid:       2036 } hitcount:        135
+ { lat:        248, common_pid:       2039 } hitcount:         26
+ { lat:        248, common_pid:       2041 } hitcount:        503
+ { lat:        248, common_pid:       2043 } hitcount:         66
+ { lat:        248, common_pid:       2040 } hitcount:         46
+ { lat:        249, common_pid:       2037 } hitcount:         29
+ { lat:        249, common_pid:       2038 } hitcount:          1
+ { lat:        249, common_pid:       2043 } hitcount:         29
+ { lat:        249, common_pid:       2039 } hitcount:          8
+ { lat:        249, common_pid:       2042 } hitcount:         56
+ { lat:        249, common_pid:       2040 } hitcount:         27
+ { lat:        249, common_pid:       2041 } hitcount:         11
+ { lat:        249, common_pid:       2036 } hitcount:         27
+ { lat:        250, common_pid:       2038 } hitcount:          1
+ { lat:        250, common_pid:       2036 } hitcount:         30
+ { lat:        250, common_pid:       2040 } hitcount:         19
+ { lat:        250, common_pid:       2043 } hitcount:         22
+ { lat:        250, common_pid:       2042 } hitcount:         20
+ { lat:        250, common_pid:       2041 } hitcount:          1
+ { lat:        250, common_pid:       2039 } hitcount:          6
+ { lat:        250, common_pid:       2037 } hitcount:         48
+ { lat:        251, common_pid:       2037 } hitcount:         43
+ { lat:        251, common_pid:       2039 } hitcount:          1
+ { lat:        251, common_pid:       2036 } hitcount:         12
+ { lat:        251, common_pid:       2042 } hitcount:          2
+ { lat:        251, common_pid:       2041 } hitcount:          1
+ { lat:        251, common_pid:       2043 } hitcount:         15
+ { lat:        251, common_pid:       2040 } hitcount:          3
+ { lat:        252, common_pid:       2040 } hitcount:          1
+ { lat:        252, common_pid:       2036 } hitcount:         12
+ { lat:        252, common_pid:       2037 } hitcount:         21
+ { lat:        252, common_pid:       2043 } hitcount:         14
+ { lat:        253, common_pid:       2037 } hitcount:         21
+ { lat:        253, common_pid:       2039 } hitcount:          2
+ { lat:        253, common_pid:       2036 } hitcount:          9
+ { lat:        253, common_pid:       2043 } hitcount:          6
+ { lat:        253, common_pid:       2040 } hitcount:          1
+ { lat:        254, common_pid:       2036 } hitcount:          8
+ { lat:        254, common_pid:       2043 } hitcount:          3
+ { lat:        254, common_pid:       2041 } hitcount:          1
+ { lat:        254, common_pid:       2042 } hitcount:          1
+ { lat:        254, common_pid:       2039 } hitcount:          1
+ { lat:        254, common_pid:       2037 } hitcount:         12
+ { lat:        255, common_pid:       2043 } hitcount:          1
+ { lat:        255, common_pid:       2037 } hitcount:          2
+ { lat:        255, common_pid:       2036 } hitcount:          2
+ { lat:        255, common_pid:       2039 } hitcount:          8
+ { lat:        256, common_pid:       2043 } hitcount:          1
+ { lat:        256, common_pid:       2036 } hitcount:          4
+ { lat:        256, common_pid:       2039 } hitcount:          6
+ { lat:        257, common_pid:       2039 } hitcount:          5
+ { lat:        257, common_pid:       2036 } hitcount:          4
+ { lat:        258, common_pid:       2039 } hitcount:          5
+ { lat:        258, common_pid:       2036 } hitcount:          2
+ { lat:        259, common_pid:       2036 } hitcount:          7
+ { lat:        259, common_pid:       2039 } hitcount:          7
+ { lat:        260, common_pid:       2036 } hitcount:          8
+ { lat:        260, common_pid:       2039 } hitcount:          6
+ { lat:        261, common_pid:       2036 } hitcount:          5
+ { lat:        261, common_pid:       2039 } hitcount:          7
+ { lat:        262, common_pid:       2039 } hitcount:          5
+ { lat:        262, common_pid:       2036 } hitcount:          5
+ { lat:        263, common_pid:       2039 } hitcount:          7
+ { lat:        263, common_pid:       2036 } hitcount:          7
+ { lat:        264, common_pid:       2039 } hitcount:          9
+ { lat:        264, common_pid:       2036 } hitcount:          9
+ { lat:        265, common_pid:       2036 } hitcount:          5
+ { lat:        265, common_pid:       2039 } hitcount:          1
+ { lat:        266, common_pid:       2036 } hitcount:          1
+ { lat:        266, common_pid:       2039 } hitcount:          3
+ { lat:        267, common_pid:       2036 } hitcount:          1
+ { lat:        267, common_pid:       2039 } hitcount:          3
+ { lat:        268, common_pid:       2036 } hitcount:          1
+ { lat:        268, common_pid:       2039 } hitcount:          6
+ { lat:        269, common_pid:       2036 } hitcount:          1
+ { lat:        269, common_pid:       2043 } hitcount:          1
+ { lat:        269, common_pid:       2039 } hitcount:          2
+ { lat:        270, common_pid:       2040 } hitcount:          1
+ { lat:        270, common_pid:       2039 } hitcount:          6
+ { lat:        271, common_pid:       2041 } hitcount:          1
+ { lat:        271, common_pid:       2039 } hitcount:          5
+ { lat:        272, common_pid:       2039 } hitcount:         10
+ { lat:        273, common_pid:       2039 } hitcount:          8
+ { lat:        274, common_pid:       2039 } hitcount:          2
+ { lat:        275, common_pid:       2039 } hitcount:          1
+ { lat:        276, common_pid:       2039 } hitcount:          2
+ { lat:        276, common_pid:       2037 } hitcount:          1
+ { lat:        276, common_pid:       2038 } hitcount:          1
+ { lat:        277, common_pid:       2039 } hitcount:          1
+ { lat:        277, common_pid:       2042 } hitcount:          1
+ { lat:        278, common_pid:       2039 } hitcount:          1
+ { lat:        279, common_pid:       2039 } hitcount:          4
+ { lat:        279, common_pid:       2043 } hitcount:          1
+ { lat:        280, common_pid:       2039 } hitcount:          3
+ { lat:        283, common_pid:       2036 } hitcount:          2
+ { lat:        284, common_pid:       2039 } hitcount:          1
+ { lat:        284, common_pid:       2043 } hitcount:          1
+ { lat:        288, common_pid:       2039 } hitcount:          1
+ { lat:        289, common_pid:       2039 } hitcount:          1
+ { lat:        300, common_pid:       2039 } hitcount:          1
+ { lat:        384, common_pid:       2039 } hitcount:          1
+
+ Totals:
+     Hits: 67625
+     Entries: 278
+     Dropped: 0
+
+Note, the writes are around the sleep, so ideally they will all be of 250
+microseconds. If you are wondering how there are several that are under
+250 microseconds, that is because the way cyclictest works, is if one
+iteration comes in late, the next one will set the timer to wake up less that
+250. That is, if an iteration came in 50 microseconds late, the next wake up
+will be at 200 microseconds.
+
+But this could easily be done in userspace. To make this even more
+interesting, we can mix the histogram between events that happened in the
+kernel with trace_marker::
+
+ # cd /sys/kernel/tracing
+ # echo 'latency u64 lat' > synthetic_events
+ # echo 'hist:keys=pid:ts0=common_timestamp.usecs' > events/sched/sched_waking/trigger
+ # echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).latency($lat) if buf == "end"' > events/ftrace/print/trigger
+ # echo 'hist:keys=lat,common_pid:sort=lat' > events/synthetic/latency/trigger
+
+The difference this time is that instead of using the trace_marker to start
+the latency, the sched_waking event is used, matching the common_pid for the
+trace_marker write with the pid that is being woken by sched_waking.
+
+After running cyclictest again with the same parameters, we now have::
+
+ # cat events/synthetic/latency/hist
+ # event histogram
+ #
+ # trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
+ #
+
+ { lat:          7, common_pid:       2302 } hitcount:        640
+ { lat:          7, common_pid:       2299 } hitcount:         42
+ { lat:          7, common_pid:       2303 } hitcount:         18
+ { lat:          7, common_pid:       2305 } hitcount:        166
+ { lat:          7, common_pid:       2306 } hitcount:          1
+ { lat:          7, common_pid:       2301 } hitcount:         91
+ { lat:          7, common_pid:       2300 } hitcount:         17
+ { lat:          8, common_pid:       2303 } hitcount:       8296
+ { lat:          8, common_pid:       2304 } hitcount:       6864
+ { lat:          8, common_pid:       2305 } hitcount:       9464
+ { lat:          8, common_pid:       2301 } hitcount:       9213
+ { lat:          8, common_pid:       2306 } hitcount:       6246
+ { lat:          8, common_pid:       2302 } hitcount:       8797
+ { lat:          8, common_pid:       2299 } hitcount:       8771
+ { lat:          8, common_pid:       2300 } hitcount:       8119
+ { lat:          9, common_pid:       2305 } hitcount:       1519
+ { lat:          9, common_pid:       2299 } hitcount:       2346
+ { lat:          9, common_pid:       2303 } hitcount:       2841
+ { lat:          9, common_pid:       2301 } hitcount:       1846
+ { lat:          9, common_pid:       2304 } hitcount:       3861
+ { lat:          9, common_pid:       2302 } hitcount:       1210
+ { lat:          9, common_pid:       2300 } hitcount:       2762
+ { lat:          9, common_pid:       2306 } hitcount:       4247
+ { lat:         10, common_pid:       2299 } hitcount:         16
+ { lat:         10, common_pid:       2306 } hitcount:        333
+ { lat:         10, common_pid:       2303 } hitcount:         16
+ { lat:         10, common_pid:       2304 } hitcount:        168
+ { lat:         10, common_pid:       2302 } hitcount:        240
+ { lat:         10, common_pid:       2301 } hitcount:         28
+ { lat:         10, common_pid:       2300 } hitcount:         95
+ { lat:         10, common_pid:       2305 } hitcount:         18
+ { lat:         11, common_pid:       2303 } hitcount:          5
+ { lat:         11, common_pid:       2305 } hitcount:          8
+ { lat:         11, common_pid:       2306 } hitcount:        221
+ { lat:         11, common_pid:       2302 } hitcount:         76
+ { lat:         11, common_pid:       2304 } hitcount:         26
+ { lat:         11, common_pid:       2300 } hitcount:        125
+ { lat:         11, common_pid:       2299 } hitcount:          2
+ { lat:         12, common_pid:       2305 } hitcount:          3
+ { lat:         12, common_pid:       2300 } hitcount:          6
+ { lat:         12, common_pid:       2306 } hitcount:         90
+ { lat:         12, common_pid:       2302 } hitcount:          4
+ { lat:         12, common_pid:       2303 } hitcount:          1
+ { lat:         12, common_pid:       2304 } hitcount:        122
+ { lat:         13, common_pid:       2300 } hitcount:         12
+ { lat:         13, common_pid:       2301 } hitcount:          1
+ { lat:         13, common_pid:       2306 } hitcount:         32
+ { lat:         13, common_pid:       2302 } hitcount:          5
+ { lat:         13, common_pid:       2305 } hitcount:          1
+ { lat:         13, common_pid:       2303 } hitcount:          1
+ { lat:         13, common_pid:       2304 } hitcount:         61
+ { lat:         14, common_pid:       2303 } hitcount:          4
+ { lat:         14, common_pid:       2306 } hitcount:          5
+ { lat:         14, common_pid:       2305 } hitcount:          4
+ { lat:         14, common_pid:       2304 } hitcount:         62
+ { lat:         14, common_pid:       2302 } hitcount:         19
+ { lat:         14, common_pid:       2300 } hitcount:         33
+ { lat:         14, common_pid:       2299 } hitcount:          1
+ { lat:         14, common_pid:       2301 } hitcount:          4
+ { lat:         15, common_pid:       2305 } hitcount:          1
+ { lat:         15, common_pid:       2302 } hitcount:         25
+ { lat:         15, common_pid:       2300 } hitcount:         11
+ { lat:         15, common_pid:       2299 } hitcount:          5
+ { lat:         15, common_pid:       2301 } hitcount:          1
+ { lat:         15, common_pid:       2304 } hitcount:          8
+ { lat:         15, common_pid:       2303 } hitcount:          1
+ { lat:         15, common_pid:       2306 } hitcount:          6
+ { lat:         16, common_pid:       2302 } hitcount:         31
+ { lat:         16, common_pid:       2306 } hitcount:          3
+ { lat:         16, common_pid:       2300 } hitcount:          5
+ { lat:         17, common_pid:       2302 } hitcount:          6
+ { lat:         17, common_pid:       2303 } hitcount:          1
+ { lat:         18, common_pid:       2304 } hitcount:          1
+ { lat:         18, common_pid:       2302 } hitcount:          8
+ { lat:         18, common_pid:       2299 } hitcount:          1
+ { lat:         18, common_pid:       2301 } hitcount:          1
+ { lat:         19, common_pid:       2303 } hitcount:          4
+ { lat:         19, common_pid:       2304 } hitcount:          5
+ { lat:         19, common_pid:       2302 } hitcount:          4
+ { lat:         19, common_pid:       2299 } hitcount:          3
+ { lat:         19, common_pid:       2306 } hitcount:          1
+ { lat:         19, common_pid:       2300 } hitcount:          4
+ { lat:         19, common_pid:       2305 } hitcount:          5
+ { lat:         20, common_pid:       2299 } hitcount:          2
+ { lat:         20, common_pid:       2302 } hitcount:          3
+ { lat:         20, common_pid:       2305 } hitcount:          1
+ { lat:         20, common_pid:       2300 } hitcount:          2
+ { lat:         20, common_pid:       2301 } hitcount:          2
+ { lat:         20, common_pid:       2303 } hitcount:          3
+ { lat:         21, common_pid:       2305 } hitcount:          1
+ { lat:         21, common_pid:       2299 } hitcount:          5
+ { lat:         21, common_pid:       2303 } hitcount:          4
+ { lat:         21, common_pid:       2302 } hitcount:          7
+ { lat:         21, common_pid:       2300 } hitcount:          1
+ { lat:         21, common_pid:       2301 } hitcount:          5
+ { lat:         21, common_pid:       2304 } hitcount:          2
+ { lat:         22, common_pid:       2302 } hitcount:          5
+ { lat:         22, common_pid:       2303 } hitcount:          1
+ { lat:         22, common_pid:       2306 } hitcount:          3
+ { lat:         22, common_pid:       2301 } hitcount:          2
+ { lat:         22, common_pid:       2300 } hitcount:          1
+ { lat:         22, common_pid:       2299 } hitcount:          1
+ { lat:         22, common_pid:       2305 } hitcount:          1
+ { lat:         22, common_pid:       2304 } hitcount:          1
+ { lat:         23, common_pid:       2299 } hitcount:          1
+ { lat:         23, common_pid:       2306 } hitcount:          2
+ { lat:         23, common_pid:       2302 } hitcount:          6
+ { lat:         24, common_pid:       2302 } hitcount:          3
+ { lat:         24, common_pid:       2300 } hitcount:          1
+ { lat:         24, common_pid:       2306 } hitcount:          2
+ { lat:         24, common_pid:       2305 } hitcount:          1
+ { lat:         24, common_pid:       2299 } hitcount:          1
+ { lat:         25, common_pid:       2300 } hitcount:          1
+ { lat:         25, common_pid:       2302 } hitcount:          4
+ { lat:         26, common_pid:       2302 } hitcount:          2
+ { lat:         27, common_pid:       2305 } hitcount:          1
+ { lat:         27, common_pid:       2300 } hitcount:          1
+ { lat:         27, common_pid:       2302 } hitcount:          3
+ { lat:         28, common_pid:       2306 } hitcount:          1
+ { lat:         28, common_pid:       2302 } hitcount:          4
+ { lat:         29, common_pid:       2302 } hitcount:          1
+ { lat:         29, common_pid:       2300 } hitcount:          2
+ { lat:         29, common_pid:       2306 } hitcount:          1
+ { lat:         29, common_pid:       2304 } hitcount:          1
+ { lat:         30, common_pid:       2302 } hitcount:          4
+ { lat:         31, common_pid:       2302 } hitcount:          6
+ { lat:         32, common_pid:       2302 } hitcount:          1
+ { lat:         33, common_pid:       2299 } hitcount:          1
+ { lat:         33, common_pid:       2302 } hitcount:          3
+ { lat:         34, common_pid:       2302 } hitcount:          2
+ { lat:         35, common_pid:       2302 } hitcount:          1
+ { lat:         35, common_pid:       2304 } hitcount:          1
+ { lat:         36, common_pid:       2302 } hitcount:          4
+ { lat:         37, common_pid:       2302 } hitcount:          6
+ { lat:         38, common_pid:       2302 } hitcount:          2
+ { lat:         39, common_pid:       2302 } hitcount:          2
+ { lat:         39, common_pid:       2304 } hitcount:          1
+ { lat:         40, common_pid:       2304 } hitcount:          2
+ { lat:         40, common_pid:       2302 } hitcount:          5
+ { lat:         41, common_pid:       2304 } hitcount:          1
+ { lat:         41, common_pid:       2302 } hitcount:          8
+ { lat:         42, common_pid:       2302 } hitcount:          6
+ { lat:         42, common_pid:       2304 } hitcount:          1
+ { lat:         43, common_pid:       2302 } hitcount:          3
+ { lat:         43, common_pid:       2304 } hitcount:          4
+ { lat:         44, common_pid:       2302 } hitcount:          6
+ { lat:         45, common_pid:       2302 } hitcount:          5
+ { lat:         46, common_pid:       2302 } hitcount:          5
+ { lat:         47, common_pid:       2302 } hitcount:          7
+ { lat:         48, common_pid:       2301 } hitcount:          1
+ { lat:         48, common_pid:       2302 } hitcount:          9
+ { lat:         49, common_pid:       2302 } hitcount:          3
+ { lat:         50, common_pid:       2302 } hitcount:          1
+ { lat:         50, common_pid:       2301 } hitcount:          1
+ { lat:         51, common_pid:       2302 } hitcount:          2
+ { lat:         51, common_pid:       2301 } hitcount:          1
+ { lat:         61, common_pid:       2302 } hitcount:          1
+ { lat:        110, common_pid:       2302 } hitcount:          1
+
+ Totals:
+     Hits: 89565
+     Entries: 158
+     Dropped: 0
+
+This doesn't tell us any information about how late cyclictest may have
+woken up, but it does show us a nice histogram of how long it took from
+the time that cyclictest was woken to the time it made it into user space.
diff --git a/Documentation/trace/histogram.txt b/Documentation/trace/histogram.txt
deleted file mode 100644
index 7ffea6aa22e3..000000000000
--- a/Documentation/trace/histogram.txt
+++ /dev/null
@@ -1,2539 +0,0 @@
-			     Event Histograms
-
-		    Documentation written by Tom Zanussi
-
-1. Introduction
-===============
-
-  Histogram triggers are special event triggers that can be used to
-  aggregate trace event data into histograms.  For information on
-  trace events and event triggers, see Documentation/trace/events.rst.
-
-
-2. Histogram Trigger Command
-============================
-
-  A histogram trigger command is an event trigger command that
-  aggregates event hits into a hash table keyed on one or more trace
-  event format fields (or stacktrace) and a set of running totals
-  derived from one or more trace event format fields and/or event
-  counts (hitcount).
-
-  The format of a hist trigger is as follows:
-
-        hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
-          [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
-          [:clear][:name=histname1] [if <filter>]
-
-  When a matching event is hit, an entry is added to a hash table
-  using the key(s) and value(s) named.  Keys and values correspond to
-  fields in the event's format description.  Values must correspond to
-  numeric fields - on an event hit, the value(s) will be added to a
-  sum kept for that field.  The special string 'hitcount' can be used
-  in place of an explicit value field - this is simply a count of
-  event hits.  If 'values' isn't specified, an implicit 'hitcount'
-  value will be automatically created and used as the only value.
-  Keys can be any field, or the special string 'stacktrace', which
-  will use the event's kernel stacktrace as the key.  The keywords
-  'keys' or 'key' can be used to specify keys, and the keywords
-  'values', 'vals', or 'val' can be used to specify values.  Compound
-  keys consisting of up to two fields can be specified by the 'keys'
-  keyword.  Hashing a compound key produces a unique entry in the
-  table for each unique combination of component keys, and can be
-  useful for providing more fine-grained summaries of event data.
-  Additionally, sort keys consisting of up to two fields can be
-  specified by the 'sort' keyword.  If more than one field is
-  specified, the result will be a 'sort within a sort': the first key
-  is taken to be the primary sort key and the second the secondary
-  key.  If a hist trigger is given a name using the 'name' parameter,
-  its histogram data will be shared with other triggers of the same
-  name, and trigger hits will update this common data.  Only triggers
-  with 'compatible' fields can be combined in this way; triggers are
-  'compatible' if the fields named in the trigger share the same
-  number and type of fields and those fields also have the same names.
-  Note that any two events always share the compatible 'hitcount' and
-  'stacktrace' fields and can therefore be combined using those
-  fields, however pointless that may be.
-
-  'hist' triggers add a 'hist' file to each event's subdirectory.
-  Reading the 'hist' file for the event will dump the hash table in
-  its entirety to stdout.  If there are multiple hist triggers
-  attached to an event, there will be a table for each trigger in the
-  output.  The table displayed for a named trigger will be the same as
-  any other instance having the same name. Each printed hash table
-  entry is a simple list of the keys and values comprising the entry;
-  keys are printed first and are delineated by curly braces, and are
-  followed by the set of value fields for the entry.  By default,
-  numeric fields are displayed as base-10 integers.  This can be
-  modified by appending any of the following modifiers to the field
-  name:
-
-        .hex        display a number as a hex value
-	.sym        display an address as a symbol
-	.sym-offset display an address as a symbol and offset
-	.syscall    display a syscall id as a system call name
-	.execname   display a common_pid as a program name
-	.log2       display log2 value rather than raw number
-	.usecs      display a common_timestamp in microseconds
-
-  Note that in general the semantics of a given field aren't
-  interpreted when applying a modifier to it, but there are some
-  restrictions to be aware of in this regard:
-
-    - only the 'hex' modifier can be used for values (because values
-      are essentially sums, and the other modifiers don't make sense
-      in that context).
-    - the 'execname' modifier can only be used on a 'common_pid'.  The
-      reason for this is that the execname is simply the 'comm' value
-      saved for the 'current' process when an event was triggered,
-      which is the same as the common_pid value saved by the event
-      tracing code.  Trying to apply that comm value to other pid
-      values wouldn't be correct, and typically events that care save
-      pid-specific comm fields in the event itself.
-
-  A typical usage scenario would be the following to enable a hist
-  trigger, read its current contents, and then turn it off:
-
-  # echo 'hist:keys=skbaddr.hex:vals=len' > \
-    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
-  # echo '!hist:keys=skbaddr.hex:vals=len' > \
-    /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  The trigger file itself can be read to show the details of the
-  currently attached hist trigger.  This information is also displayed
-  at the top of the 'hist' file when read.
-
-  By default, the size of the hash table is 2048 entries.  The 'size'
-  parameter can be used to specify more or fewer than that.  The units
-  are in terms of hashtable entries - if a run uses more entries than
-  specified, the results will show the number of 'drops', the number
-  of hits that were ignored.  The size should be a power of 2 between
-  128 and 131072 (any non- power-of-2 number specified will be rounded
-  up).
-
-  The 'sort' parameter can be used to specify a value field to sort
-  on.  The default if unspecified is 'hitcount' and the default sort
-  order is 'ascending'.  To sort in the opposite direction, append
-  .descending' to the sort key.
-
-  The 'pause' parameter can be used to pause an existing hist trigger
-  or to start a hist trigger but not log any events until told to do
-  so.  'continue' or 'cont' can be used to start or restart a paused
-  hist trigger.
-
-  The 'clear' parameter will clear the contents of a running hist
-  trigger and leave its current paused/active state.
-
-  Note that the 'pause', 'cont', and 'clear' parameters should be
-  applied using 'append' shell operator ('>>') if applied to an
-  existing trigger, rather than via the '>' operator, which will cause
-  the trigger to be removed through truncation.
-
-- enable_hist/disable_hist
-
-  The enable_hist and disable_hist triggers can be used to have one
-  event conditionally start and stop another event's already-attached
-  hist trigger.  Any number of enable_hist and disable_hist triggers
-  can be attached to a given event, allowing that event to kick off
-  and stop aggregations on a host of other events.
-
-  The format is very similar to the enable/disable_event triggers:
-
-      enable_hist:<system>:<event>[:count]
-      disable_hist:<system>:<event>[:count]
-
-  Instead of enabling or disabling the tracing of the target event
-  into the trace buffer as the enable/disable_event triggers do, the
-  enable/disable_hist triggers enable or disable the aggregation of
-  the target event into a hash table.
-
-  A typical usage scenario for the enable_hist/disable_hist triggers
-  would be to first set up a paused hist trigger on some event,
-  followed by an enable_hist/disable_hist pair that turns the hist
-  aggregation on and off when conditions of interest are hit:
-
-  # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
-    /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
-    /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
-  # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
-    /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
-  The above sets up an initially paused hist trigger which is unpaused
-  and starts aggregating events when a given program is executed, and
-  which stops aggregating when the process exits and the hist trigger
-  is paused again.
-
-  The examples below provide a more concrete illustration of the
-  concepts and typical usage patterns discussed above.
-
-  'special' event fields
-  ------------------------
-
-  There are a number of 'special event fields' available for use as
-  keys or values in a hist trigger.  These look like and behave as if
-  they were actual event fields, but aren't really part of the event's
-  field definition or format file.  They are however available for any
-  event, and can be used anywhere an actual event field could be.
-  They are:
-
-    common_timestamp       u64 - timestamp (from ring buffer) associated
-                                 with the event, in nanoseconds.  May be
-				 modified by .usecs to have timestamps
-				 interpreted as microseconds.
-    cpu                    int - the cpu on which the event occurred.
-
-  Extended error information
-  --------------------------
-
-  For some error conditions encountered when invoking a hist trigger
-  command, extended error information is available via the
-  corresponding event's 'hist' file.  Reading the hist file after an
-  error will display more detailed information about what went wrong,
-  if information is available.  This extended error information will
-  be available until the next hist trigger command for that event.
-
-  If available for a given error condition, the extended error
-  information and usage takes the following form:
-
-    # echo xxx > /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
-    echo: write error: Invalid argument
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/hist
-    ERROR: Couldn't yyy: zzz
-      Last command: xxx
-
-6.2 'hist' trigger examples
----------------------------
-
-  The first set of examples creates aggregations using the kmalloc
-  event.  The fields that can be used for the hist trigger are listed
-  in the kmalloc event's format file:
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/format
-    name: kmalloc
-    ID: 374
-    format:
-	field:unsigned short common_type;	offset:0;	size:2;	signed:0;
-	field:unsigned char common_flags;	offset:2;	size:1;	signed:0;
-	field:unsigned char common_preempt_count;		offset:3;	size:1;	signed:0;
-	field:int common_pid;					offset:4;	size:4;	signed:1;
-
-	field:unsigned long call_site;				offset:8;	size:8;	signed:0;
-	field:const void * ptr;					offset:16;	size:8;	signed:0;
-	field:size_t bytes_req;					offset:24;	size:8;	signed:0;
-	field:size_t bytes_alloc;				offset:32;	size:8;	signed:0;
-	field:gfp_t gfp_flags;					offset:40;	size:4;	signed:0;
-
-  We'll start by creating a hist trigger that generates a simple table
-  that lists the total number of bytes requested for each function in
-  the kernel that made one or more calls to kmalloc:
-
-    # echo 'hist:key=call_site:val=bytes_req' > \
-            /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-  This tells the tracing system to create a 'hist' trigger using the
-  call_site field of the kmalloc event as the key for the table, which
-  just means that each unique call_site address will have an entry
-  created for it in the table.  The 'val=bytes_req' parameter tells
-  the hist trigger that for each unique entry (call_site) in the
-  table, it should keep a running total of the number of bytes
-  requested by that call_site.
-
-  We'll let it run for awhile and then dump the contents of the 'hist'
-  file in the kmalloc event's subdirectory (for readability, a number
-  of entries have been omitted):
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-    { call_site: 18446744072106379007 } hitcount:          1  bytes_req:        176
-    { call_site: 18446744071579557049 } hitcount:          1  bytes_req:       1024
-    { call_site: 18446744071580608289 } hitcount:          1  bytes_req:      16384
-    { call_site: 18446744071581827654 } hitcount:          1  bytes_req:         24
-    { call_site: 18446744071580700980 } hitcount:          1  bytes_req:          8
-    { call_site: 18446744071579359876 } hitcount:          1  bytes_req:        152
-    { call_site: 18446744071580795365 } hitcount:          3  bytes_req:        144
-    { call_site: 18446744071581303129 } hitcount:          3  bytes_req:        144
-    { call_site: 18446744071580713234 } hitcount:          4  bytes_req:       2560
-    { call_site: 18446744071580933750 } hitcount:          4  bytes_req:        736
-    .
-    .
-    .
-    { call_site: 18446744072106047046 } hitcount:         69  bytes_req:       5576
-    { call_site: 18446744071582116407 } hitcount:         73  bytes_req:       2336
-    { call_site: 18446744072106054684 } hitcount:        136  bytes_req:     140504
-    { call_site: 18446744072106224230 } hitcount:        136  bytes_req:      19584
-    { call_site: 18446744072106078074 } hitcount:        153  bytes_req:       2448
-    { call_site: 18446744072106062406 } hitcount:        153  bytes_req:      36720
-    { call_site: 18446744071582507929 } hitcount:        153  bytes_req:      37088
-    { call_site: 18446744072102520590 } hitcount:        273  bytes_req:      10920
-    { call_site: 18446744071582143559 } hitcount:        358  bytes_req:        716
-    { call_site: 18446744072106465852 } hitcount:        417  bytes_req:      56712
-    { call_site: 18446744072102523378 } hitcount:        485  bytes_req:      27160
-    { call_site: 18446744072099568646 } hitcount:       1676  bytes_req:      33520
-
-    Totals:
-        Hits: 4610
-        Entries: 45
-        Dropped: 0
-
-  The output displays a line for each entry, beginning with the key
-  specified in the trigger, followed by the value(s) also specified in
-  the trigger.  At the beginning of the output is a line that displays
-  the trigger info, which can also be displayed by reading the
-  'trigger' file:
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-    hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-  At the end of the output are a few lines that display the overall
-  totals for the run.  The 'Hits' field shows the total number of
-  times the event trigger was hit, the 'Entries' field shows the total
-  number of used entries in the hash table, and the 'Dropped' field
-  shows the number of hits that were dropped because the number of
-  used entries for the run exceeded the maximum number of entries
-  allowed for the table (normally 0, but if not a hint that you may
-  want to increase the size of the table using the 'size' parameter).
-
-  Notice in the above output that there's an extra field, 'hitcount',
-  which wasn't specified in the trigger.  Also notice that in the
-  trigger info output, there's a parameter, 'sort=hitcount', which
-  wasn't specified in the trigger either.  The reason for that is that
-  every trigger implicitly keeps a count of the total number of hits
-  attributed to a given entry, called the 'hitcount'.  That hitcount
-  information is explicitly displayed in the output, and in the
-  absence of a user-specified sort parameter, is used as the default
-  sort field.
-
-  The value 'hitcount' can be used in place of an explicit value in
-  the 'values' parameter if you don't really need to have any
-  particular field summed and are mainly interested in hit
-  frequencies.
-
-  To turn the hist trigger off, simply call up the trigger in the
-  command history and re-execute it with a '!' prepended:
-
-    # echo '!hist:key=call_site:val=bytes_req' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-  Finally, notice that the call_site as displayed in the output above
-  isn't really very useful.  It's an address, but normally addresses
-  are displayed in hex.  To have a numeric field displayed as a hex
-  value, simply append '.hex' to the field name in the trigger:
-
-    # echo 'hist:key=call_site.hex:val=bytes_req' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.hex:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-    { call_site: ffffffffa026b291 } hitcount:          1  bytes_req:        433
-    { call_site: ffffffffa07186ff } hitcount:          1  bytes_req:        176
-    { call_site: ffffffff811ae721 } hitcount:          1  bytes_req:      16384
-    { call_site: ffffffff811c5134 } hitcount:          1  bytes_req:          8
-    { call_site: ffffffffa04a9ebb } hitcount:          1  bytes_req:        511
-    { call_site: ffffffff8122e0a6 } hitcount:          1  bytes_req:         12
-    { call_site: ffffffff8107da84 } hitcount:          1  bytes_req:        152
-    { call_site: ffffffff812d8246 } hitcount:          1  bytes_req:         24
-    { call_site: ffffffff811dc1e5 } hitcount:          3  bytes_req:        144
-    { call_site: ffffffffa02515e8 } hitcount:          3  bytes_req:        648
-    { call_site: ffffffff81258159 } hitcount:          3  bytes_req:        144
-    { call_site: ffffffff811c80f4 } hitcount:          4  bytes_req:        544
-    .
-    .
-    .
-    { call_site: ffffffffa06c7646 } hitcount:        106  bytes_req:       8024
-    { call_site: ffffffffa06cb246 } hitcount:        132  bytes_req:      31680
-    { call_site: ffffffffa06cef7a } hitcount:        132  bytes_req:       2112
-    { call_site: ffffffff8137e399 } hitcount:        132  bytes_req:      23232
-    { call_site: ffffffffa06c941c } hitcount:        185  bytes_req:     171360
-    { call_site: ffffffffa06f2a66 } hitcount:        185  bytes_req:      26640
-    { call_site: ffffffffa036a70e } hitcount:        265  bytes_req:      10600
-    { call_site: ffffffff81325447 } hitcount:        292  bytes_req:        584
-    { call_site: ffffffffa072da3c } hitcount:        446  bytes_req:      60656
-    { call_site: ffffffffa036b1f2 } hitcount:        526  bytes_req:      29456
-    { call_site: ffffffffa0099c06 } hitcount:       1780  bytes_req:      35600
-
-    Totals:
-        Hits: 4775
-        Entries: 46
-        Dropped: 0
-
-  Even that's only marginally more useful - while hex values do look
-  more like addresses, what users are typically more interested in
-  when looking at text addresses are the corresponding symbols
-  instead.  To have an address displayed as symbolic value instead,
-  simply append '.sym' or '.sym-offset' to the field name in the
-  trigger:
-
-    # echo 'hist:key=call_site.sym:val=bytes_req' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=hitcount:size=2048 [active]
-
-    { call_site: [ffffffff810adcb9] syslog_print_all                              } hitcount:          1  bytes_req:       1024
-    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffff8154acbe] usb_alloc_urb                                 } hitcount:          1  bytes_req:        192
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
-    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff811febd5] fsnotify_alloc_group                          } hitcount:          2  bytes_req:        528
-    { call_site: [ffffffff81440f58] __tty_buffer_request_room                     } hitcount:          2  bytes_req:       2624
-    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          2  bytes_req:         96
-    { call_site: [ffffffffa05e19af] ieee80211_start_tx_ba_session [mac80211]      } hitcount:          2  bytes_req:        464
-    { call_site: [ffffffff81672406] tcp_get_metrics                               } hitcount:          2  bytes_req:        304
-    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff81089b05] sched_create_group                            } hitcount:          2  bytes_req:       1424
-    .
-    .
-    .
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1185  bytes_req:     123240
-    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:       1185  bytes_req:     104280
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       1402  bytes_req:     190672
-    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       1518  bytes_req:     146208
-    { call_site: [ffffffffa029070e] drm_vma_node_allow [drm]                      } hitcount:       1746  bytes_req:      69840
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       2021  bytes_req:     792312
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       2592  bytes_req:     145152
-    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2629  bytes_req:     378576
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2629  bytes_req:    3783248
-    { call_site: [ffffffff81325607] apparmor_file_alloc_security                  } hitcount:       5192  bytes_req:      10384
-    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       5529  bytes_req:     110584
-    { call_site: [ffffffff8131ebf7] aa_alloc_task_context                         } hitcount:      21943  bytes_req:     702176
-    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:      55759  bytes_req:    5074265
-
-    Totals:
-        Hits: 109928
-        Entries: 71
-        Dropped: 0
-
-  Because the default sort key above is 'hitcount', the above shows a
-  the list of call_sites by increasing hitcount, so that at the bottom
-  we see the functions that made the most kmalloc calls during the
-  run.  If instead we we wanted to see the top kmalloc callers in
-  terms of the number of bytes requested rather than the number of
-  calls, and we wanted the top caller to appear at the top, we can use
-  the 'sort' parameter, along with the 'descending' modifier:
-
-    # echo 'hist:key=call_site.sym:val=bytes_req:sort=bytes_req.descending' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
-
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       2186  bytes_req:    3397464
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1790  bytes_req:     712176
-    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       8132  bytes_req:     513135
-    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        106  bytes_req:     440128
-    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       2186  bytes_req:     314784
-    { call_site: [ffffffff812891ca] ext4_find_extent                              } hitcount:       2174  bytes_req:     208992
-    { call_site: [ffffffff811ae8e1] __kmalloc                                     } hitcount:          8  bytes_req:     131072
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:        859  bytes_req:     116824
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       1834  bytes_req:     102704
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:        972  bytes_req:     101088
-    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm]                } hitcount:        972  bytes_req:      85536
-    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       3333  bytes_req:      66664
-    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        209  bytes_req:      61632
-    .
-    .
-    .
-    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffff812d8406] copy_semundo                                  } hitcount:          2  bytes_req:         48
-    { call_site: [ffffffff81200ba6] inotify_new_group                             } hitcount:          1  bytes_req:         48
-    { call_site: [ffffffffa027121a] drm_getmagic [drm]                            } hitcount:          1  bytes_req:         48
-    { call_site: [ffffffff811e3a25] __seq_open_private                            } hitcount:          1  bytes_req:         40
-    { call_site: [ffffffff811c52f4] bprm_change_interp                            } hitcount:          2  bytes_req:         16
-    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7
-
-    Totals:
-        Hits: 32133
-        Entries: 81
-        Dropped: 0
-
-  To display the offset and size information in addition to the symbol
-  name, just use 'sym-offset' instead:
-
-    # echo 'hist:key=call_site.sym-offset:val=bytes_req:sort=bytes_req.descending' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym-offset:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
-
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2+0x6c/0x2c0 [i915]                  } hitcount:       4569  bytes_req:    3163720
-    { call_site: [ffffffffa0489a66] intel_ring_begin+0xc6/0x1f0 [i915]                      } hitcount:       4569  bytes_req:     657936
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23+0x694/0x1020 [i915]      } hitcount:       1519  bytes_req:     472936
-    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23+0x516/0x1020 [i915]      } hitcount:       3050  bytes_req:     211832
-    { call_site: [ffffffff811e2a1b] seq_buf_alloc+0x1b/0x50                                 } hitcount:         34  bytes_req:     148384
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip+0xbc/0x870 [i915]                  } hitcount:       1385  bytes_req:     144040
-    { call_site: [ffffffff811ae8e1] __kmalloc+0x191/0x1b0                                   } hitcount:          8  bytes_req:     131072
-    { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl+0x282/0x360 [drm]              } hitcount:       1385  bytes_req:     121880
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc+0x32/0x100 [drm]                  } hitcount:       1848  bytes_req:     103488
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state+0x2c/0xa0 [i915]            } hitcount:        461  bytes_req:      62696
-    { call_site: [ffffffffa029070e] drm_vma_node_allow+0x2e/0xd0 [drm]                      } hitcount:       1541  bytes_req:      61640
-    { call_site: [ffffffff815f8d7b] sk_prot_alloc+0xcb/0x1b0                                } hitcount:         57  bytes_req:      57456
-    .
-    .
-    .
-    { call_site: [ffffffff8109524a] alloc_fair_sched_group+0x5a/0x1a0                       } hitcount:          2  bytes_req:        128
-    { call_site: [ffffffffa027b921] drm_vm_open_locked+0x31/0xa0 [drm]                      } hitcount:          3  bytes_req:         96
-    { call_site: [ffffffff8122e266] proc_self_follow_link+0x76/0xb0                         } hitcount:          8  bytes_req:         96
-    { call_site: [ffffffff81213e80] load_elf_binary+0x240/0x1650                            } hitcount:          3  bytes_req:         84
-    { call_site: [ffffffff8154bc62] usb_control_msg+0x42/0x110                              } hitcount:          1  bytes_req:          8
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report+0x7e/0x1a0 [hid]                     } hitcount:          1  bytes_req:          7
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event+0x8a/0x120 [hid]                    } hitcount:          1  bytes_req:          7
-
-    Totals:
-        Hits: 26098
-        Entries: 64
-        Dropped: 0
-
-  We can also add multiple fields to the 'values' parameter.  For
-  example, we might want to see the total number of bytes allocated
-  alongside bytes requested, and display the result sorted by bytes
-  allocated in a descending order:
-
-    # echo 'hist:keys=call_site.sym:values=bytes_req,bytes_alloc:sort=bytes_alloc.descending' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=call_site.sym:vals=bytes_req,bytes_alloc:sort=bytes_alloc.descending:size=2048 [active]
-
-    { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915]                   } hitcount:       7403  bytes_req:    4084360  bytes_alloc:    5958016
-    { call_site: [ffffffff811e2a1b] seq_buf_alloc                                 } hitcount:        541  bytes_req:    2213968  bytes_alloc:    2228224
-    { call_site: [ffffffffa0489a66] intel_ring_begin [i915]                       } hitcount:       7404  bytes_req:    1066176  bytes_alloc:    1421568
-    { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       1565  bytes_req:     557368  bytes_alloc:    1037760
-    { call_site: [ffffffff8125847d] ext4_htree_store_dirent                       } hitcount:       9557  bytes_req:     595778  bytes_alloc:     695744
-    { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23 [i915]         } hitcount:       5839  bytes_req:     430680  bytes_alloc:     470400
-    { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915]            } hitcount:       2388  bytes_req:     324768  bytes_alloc:     458496
-    { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm]                   } hitcount:       3911  bytes_req:     219016  bytes_alloc:     250304
-    { call_site: [ffffffff815f8d7b] sk_prot_alloc                                 } hitcount:        235  bytes_req:     236880  bytes_alloc:     240640
-    { call_site: [ffffffff8137e559] sg_kmalloc                                    } hitcount:        557  bytes_req:     169024  bytes_alloc:     221760
-    { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid]                    } hitcount:       9378  bytes_req:     187548  bytes_alloc:     206312
-    { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915]                   } hitcount:       1519  bytes_req:     157976  bytes_alloc:     194432
-    .
-    .
-    .
-    { call_site: [ffffffff8109bd3b] sched_autogroup_create_attach                 } hitcount:          2  bytes_req:        144  bytes_alloc:        192
-    { call_site: [ffffffff81097ee8] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff8109524a] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff81095225] alloc_fair_sched_group                        } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff81097ec2] alloc_rt_sched_group                          } hitcount:          2  bytes_req:        128  bytes_alloc:        128
-    { call_site: [ffffffff81213e80] load_elf_binary                               } hitcount:          3  bytes_req:         84  bytes_alloc:         96
-    { call_site: [ffffffff81079a2e] kthread_create_on_node                        } hitcount:          1  bytes_req:         56  bytes_alloc:         64
-    { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid]                      } hitcount:          1  bytes_req:          7  bytes_alloc:          8
-    { call_site: [ffffffff8154bc62] usb_control_msg                               } hitcount:          1  bytes_req:          8  bytes_alloc:          8
-    { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid]                     } hitcount:          1  bytes_req:          7  bytes_alloc:          8
-
-    Totals:
-        Hits: 66598
-        Entries: 65
-        Dropped: 0
-
-  Finally, to finish off our kmalloc example, instead of simply having
-  the hist trigger display symbolic call_sites, we can have the hist
-  trigger additionally display the complete set of kernel stack traces
-  that led to each call_site.  To do that, we simply use the special
-  value 'stacktrace' for the key parameter:
-
-    # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \
-           /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
-  The above trigger will use the kernel stack trace in effect when an
-  event is triggered as the key for the hash table.  This allows the
-  enumeration of every kernel callpath that led up to a particular
-  event, along with a running total of any of the event fields for
-  that event.  Here we tally bytes requested and bytes allocated for
-  every callpath in the system that led up to a kmalloc (in this case
-  every callpath to a kmalloc for a kernel compile):
-
-    # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
-    # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active]
-
-    { stacktrace:
-         __kmalloc_track_caller+0x10b/0x1a0
-         kmemdup+0x20/0x50
-         hidraw_report_event+0x8a/0x120 [hid]
-         hid_report_raw_event+0x3ea/0x440 [hid]
-         hid_input_report+0x112/0x190 [hid]
-         hid_irq_in+0xc2/0x260 [usbhid]
-         __usb_hcd_giveback_urb+0x72/0x120
-         usb_giveback_urb_bh+0x9e/0xe0
-         tasklet_hi_action+0xf8/0x100
-         __do_softirq+0x114/0x2c0
-         irq_exit+0xa5/0xb0
-         do_IRQ+0x5a/0xf0
-         ret_from_intr+0x0/0x30
-         cpuidle_enter+0x17/0x20
-         cpu_startup_entry+0x315/0x3e0
-         rest_init+0x7c/0x80
-    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
-    { stacktrace:
-         __kmalloc_track_caller+0x10b/0x1a0
-         kmemdup+0x20/0x50
-         hidraw_report_event+0x8a/0x120 [hid]
-         hid_report_raw_event+0x3ea/0x440 [hid]
-         hid_input_report+0x112/0x190 [hid]
-         hid_irq_in+0xc2/0x260 [usbhid]
-         __usb_hcd_giveback_urb+0x72/0x120
-         usb_giveback_urb_bh+0x9e/0xe0
-         tasklet_hi_action+0xf8/0x100
-         __do_softirq+0x114/0x2c0
-         irq_exit+0xa5/0xb0
-         do_IRQ+0x5a/0xf0
-         ret_from_intr+0x0/0x30
-    } hitcount:          3  bytes_req:         21  bytes_alloc:         24
-    { stacktrace:
-         kmem_cache_alloc_trace+0xeb/0x150
-         aa_alloc_task_context+0x27/0x40
-         apparmor_cred_prepare+0x1f/0x50
-         security_prepare_creds+0x16/0x20
-         prepare_creds+0xdf/0x1a0
-         SyS_capset+0xb5/0x200
-         system_call_fastpath+0x12/0x6a
-    } hitcount:          1  bytes_req:         32  bytes_alloc:         32
-    .
-    .
-    .
-    { stacktrace:
-         __kmalloc+0x11b/0x1b0
-         i915_gem_execbuffer2+0x6c/0x2c0 [i915]
-         drm_ioctl+0x349/0x670 [drm]
-         do_vfs_ioctl+0x2f0/0x4f0
-         SyS_ioctl+0x81/0xa0
-         system_call_fastpath+0x12/0x6a
-    } hitcount:      17726  bytes_req:   13944120  bytes_alloc:   19593808
-    { stacktrace:
-         __kmalloc+0x11b/0x1b0
-         load_elf_phdrs+0x76/0xa0
-         load_elf_binary+0x102/0x1650
-         search_binary_handler+0x97/0x1d0
-         do_execveat_common.isra.34+0x551/0x6e0
-         SyS_execve+0x3a/0x50
-         return_from_execve+0x0/0x23
-    } hitcount:      33348  bytes_req:   17152128  bytes_alloc:   20226048
-    { stacktrace:
-         kmem_cache_alloc_trace+0xeb/0x150
-         apparmor_file_alloc_security+0x27/0x40
-         security_file_alloc+0x16/0x20
-         get_empty_filp+0x93/0x1c0
-         path_openat+0x31/0x5f0
-         do_filp_open+0x3a/0x90
-         do_sys_open+0x128/0x220
-         SyS_open+0x1e/0x20
-         system_call_fastpath+0x12/0x6a
-    } hitcount:    4766422  bytes_req:    9532844  bytes_alloc:   38131376
-    { stacktrace:
-         __kmalloc+0x11b/0x1b0
-         seq_buf_alloc+0x1b/0x50
-         seq_read+0x2cc/0x370
-         proc_reg_read+0x3d/0x80
-         __vfs_read+0x28/0xe0
-         vfs_read+0x86/0x140
-         SyS_read+0x46/0xb0
-         system_call_fastpath+0x12/0x6a
-    } hitcount:      19133  bytes_req:   78368768  bytes_alloc:   78368768
-
-    Totals:
-        Hits: 6085872
-        Entries: 253
-        Dropped: 0
-
-  If you key a hist trigger on common_pid, in order for example to
-  gather and display sorted totals for each process, you can use the
-  special .execname modifier to display the executable names for the
-  processes in the table rather than raw pids.  The example below
-  keeps a per-process sum of total bytes read:
-
-    # echo 'hist:key=common_pid.execname:val=count:sort=count.descending' > \
-           /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
-
-    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/hist
-    # trigger info: hist:keys=common_pid.execname:vals=count:sort=count.descending:size=2048 [active]
-
-    { common_pid: gnome-terminal  [      3196] } hitcount:        280  count:    1093512
-    { common_pid: Xorg            [      1309] } hitcount:        525  count:     256640
-    { common_pid: compiz          [      2889] } hitcount:         59  count:     254400
-    { common_pid: bash            [      8710] } hitcount:          3  count:      66369
-    { common_pid: dbus-daemon-lau [      8703] } hitcount:         49  count:      47739
-    { common_pid: irqbalance      [      1252] } hitcount:         27  count:      27648
-    { common_pid: 01ifupdown      [      8705] } hitcount:          3  count:      17216
-    { common_pid: dbus-daemon     [       772] } hitcount:         10  count:      12396
-    { common_pid: Socket Thread   [      8342] } hitcount:         11  count:      11264
-    { common_pid: nm-dhcp-client. [      8701] } hitcount:          6  count:       7424
-    { common_pid: gmain           [      1315] } hitcount:         18  count:       6336
-    .
-    .
-    .
-    { common_pid: postgres        [      1892] } hitcount:          2  count:         32
-    { common_pid: postgres        [      1891] } hitcount:          2  count:         32
-    { common_pid: gmain           [      8704] } hitcount:          2  count:         32
-    { common_pid: upstart-dbus-br [      2740] } hitcount:         21  count:         21
-    { common_pid: nm-dispatcher.a [      8696] } hitcount:          1  count:         16
-    { common_pid: indicator-datet [      2904] } hitcount:          1  count:         16
-    { common_pid: gdbus           [      2998] } hitcount:          1  count:         16
-    { common_pid: rtkit-daemon    [      2052] } hitcount:          1  count:          8
-    { common_pid: init            [         1] } hitcount:          2  count:          2
-
-    Totals:
-        Hits: 2116
-        Entries: 51
-        Dropped: 0
-
-  Similarly, if you key a hist trigger on syscall id, for example to
-  gather and display a list of systemwide syscall hits, you can use
-  the special .syscall modifier to display the syscall names rather
-  than raw ids.  The example below keeps a running total of syscall
-  counts for the system during the run:
-
-    # echo 'hist:key=id.syscall:val=hitcount' > \
-           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
-    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
-    # trigger info: hist:keys=id.syscall:vals=hitcount:sort=hitcount:size=2048 [active]
-
-    { id: sys_fsync                     [ 74] } hitcount:          1
-    { id: sys_newuname                  [ 63] } hitcount:          1
-    { id: sys_prctl                     [157] } hitcount:          1
-    { id: sys_statfs                    [137] } hitcount:          1
-    { id: sys_symlink                   [ 88] } hitcount:          1
-    { id: sys_sendmmsg                  [307] } hitcount:          1
-    { id: sys_semctl                    [ 66] } hitcount:          1
-    { id: sys_readlink                  [ 89] } hitcount:          3
-    { id: sys_bind                      [ 49] } hitcount:          3
-    { id: sys_getsockname               [ 51] } hitcount:          3
-    { id: sys_unlink                    [ 87] } hitcount:          3
-    { id: sys_rename                    [ 82] } hitcount:          4
-    { id: unknown_syscall               [ 58] } hitcount:          4
-    { id: sys_connect                   [ 42] } hitcount:          4
-    { id: sys_getpid                    [ 39] } hitcount:          4
-    .
-    .
-    .
-    { id: sys_rt_sigprocmask            [ 14] } hitcount:        952
-    { id: sys_futex                     [202] } hitcount:       1534
-    { id: sys_write                     [  1] } hitcount:       2689
-    { id: sys_setitimer                 [ 38] } hitcount:       2797
-    { id: sys_read                      [  0] } hitcount:       3202
-    { id: sys_select                    [ 23] } hitcount:       3773
-    { id: sys_writev                    [ 20] } hitcount:       4531
-    { id: sys_poll                      [  7] } hitcount:       8314
-    { id: sys_recvmsg                   [ 47] } hitcount:      13738
-    { id: sys_ioctl                     [ 16] } hitcount:      21843
-
-    Totals:
-        Hits: 67612
-        Entries: 72
-        Dropped: 0
-
-    The syscall counts above provide a rough overall picture of system
-    call activity on the system; we can see for example that the most
-    popular system call on this system was the 'sys_ioctl' system call.
-
-    We can use 'compound' keys to refine that number and provide some
-    further insight as to which processes exactly contribute to the
-    overall ioctl count.
-
-    The command below keeps a hitcount for every unique combination of
-    system call id and pid - the end result is essentially a table
-    that keeps a per-pid sum of system call hits.  The results are
-    sorted using the system call id as the primary key, and the
-    hitcount sum as the secondary key:
-
-    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount' > \
-           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
-    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
-    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 [active]
-
-    { id: sys_read                      [  0], common_pid: rtkit-daemon    [      1877] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: gdbus           [      2976] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: console-kit-dae [      3400] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: postgres        [      1865] } hitcount:          1
-    { id: sys_read                      [  0], common_pid: deja-dup-monito [      3543] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: NetworkManager  [       890] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: evolution-calen [      3048] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: postgres        [      1864] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: nm-applet       [      3022] } hitcount:          2
-    { id: sys_read                      [  0], common_pid: whoopsie        [      1212] } hitcount:          2
-    .
-    .
-    .
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      8479] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      3472] } hitcount:         12
-    { id: sys_ioctl                     [ 16], common_pid: gnome-terminal  [      3199] } hitcount:         16
-    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:       1808
-    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:       5580
-    .
-    .
-    .
-    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2690] } hitcount:          3
-    { id: sys_waitid                    [247], common_pid: upstart-dbus-br [      2688] } hitcount:         16
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [       975] } hitcount:          2
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3204] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2888] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3003] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      2873] } hitcount:          4
-    { id: sys_inotify_add_watch         [254], common_pid: gmain           [      3196] } hitcount:          6
-    { id: sys_openat                    [257], common_pid: java            [      2623] } hitcount:          2
-    { id: sys_eventfd2                  [290], common_pid: ibus-ui-gtk3    [      2760] } hitcount:          4
-    { id: sys_eventfd2                  [290], common_pid: compiz          [      2994] } hitcount:          6
-
-    Totals:
-        Hits: 31536
-        Entries: 323
-        Dropped: 0
-
-    The above list does give us a breakdown of the ioctl syscall by
-    pid, but it also gives us quite a bit more than that, which we
-    don't really care about at the moment.  Since we know the syscall
-    id for sys_ioctl (16, displayed next to the sys_ioctl name), we
-    can use that to filter out all the other syscalls:
-
-    # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount if id == 16' > \
-           /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
-    # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
-    # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 if id == 16 [active]
-
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2769] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: evolution-addre [      8571] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      3003] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2781] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2829] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      8726] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: bash            [      8508] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2970] } hitcount:          1
-    { id: sys_ioctl                     [ 16], common_pid: gmain           [      2768] } hitcount:          1
-    .
-    .
-    .
-    { id: sys_ioctl                     [ 16], common_pid: pool            [      8559] } hitcount:         45
-    { id: sys_ioctl                     [ 16], common_pid: pool            [      8555] } hitcount:         48
-    { id: sys_ioctl                     [ 16], common_pid: pool            [      8551] } hitcount:         48
-    { id: sys_ioctl                     [ 16], common_pid: avahi-daemon    [       896] } hitcount:         66
-    { id: sys_ioctl                     [ 16], common_pid: Xorg            [      1267] } hitcount:      26674
-    { id: sys_ioctl                     [ 16], common_pid: compiz          [      2994] } hitcount:      73443
-
-    Totals:
-        Hits: 101162
-        Entries: 103
-        Dropped: 0
-
-    The above output shows that 'compiz' and 'Xorg' are far and away
-    the heaviest ioctl callers (which might lead to questions about
-    whether they really need to be making all those calls and to
-    possible avenues for further investigation.)
-
-    The compound key examples used a key and a sum value (hitcount) to
-    sort the output, but we can just as easily use two keys instead.
-    Here's an example where we use a compound key composed of the the
-    common_pid and size event fields.  Sorting with pid as the primary
-    key and 'size' as the secondary key allows us to display an
-    ordered summary of the recvfrom sizes, with counts, received by
-    each process:
-
-    # echo 'hist:key=common_pid.execname,size:val=hitcount:sort=common_pid,size' > \
-           /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/trigger
-
-    # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/hist
-    # trigger info: hist:keys=common_pid.execname,size:vals=hitcount:sort=common_pid.execname,size:size=2048 [active]
-
-    { common_pid: smbd            [       784], size:          4 } hitcount:          1
-    { common_pid: dnsmasq         [      1412], size:       4096 } hitcount:        672
-    { common_pid: postgres        [      1796], size:       1000 } hitcount:          6
-    { common_pid: postgres        [      1867], size:       1000 } hitcount:         10
-    { common_pid: bamfdaemon      [      2787], size:         28 } hitcount:          2
-    { common_pid: bamfdaemon      [      2787], size:      14360 } hitcount:          1
-    { common_pid: compiz          [      2994], size:          8 } hitcount:          1
-    { common_pid: compiz          [      2994], size:         20 } hitcount:         11
-    { common_pid: gnome-terminal  [      3199], size:          4 } hitcount:          2
-    { common_pid: firefox         [      8817], size:          4 } hitcount:          1
-    { common_pid: firefox         [      8817], size:          8 } hitcount:          5
-    { common_pid: firefox         [      8817], size:        588 } hitcount:          2
-    { common_pid: firefox         [      8817], size:        628 } hitcount:          1
-    { common_pid: firefox         [      8817], size:       6944 } hitcount:          1
-    { common_pid: firefox         [      8817], size:     408880 } hitcount:          2
-    { common_pid: firefox         [      8822], size:          8 } hitcount:          2
-    { common_pid: firefox         [      8822], size:        160 } hitcount:          2
-    { common_pid: firefox         [      8822], size:        320 } hitcount:          2
-    { common_pid: firefox         [      8822], size:        352 } hitcount:          1
-    .
-    .
-    .
-    { common_pid: pool            [      8923], size:       1960 } hitcount:         10
-    { common_pid: pool            [      8923], size:       2048 } hitcount:         10
-    { common_pid: pool            [      8924], size:       1960 } hitcount:         10
-    { common_pid: pool            [      8924], size:       2048 } hitcount:         10
-    { common_pid: pool            [      8928], size:       1964 } hitcount:          4
-    { common_pid: pool            [      8928], size:       1965 } hitcount:          2
-    { common_pid: pool            [      8928], size:       2048 } hitcount:          6
-    { common_pid: pool            [      8929], size:       1982 } hitcount:          1
-    { common_pid: pool            [      8929], size:       2048 } hitcount:          1
-
-    Totals:
-        Hits: 2016
-        Entries: 224
-        Dropped: 0
-
-  The above example also illustrates the fact that although a compound
-  key is treated as a single entity for hashing purposes, the sub-keys
-  it's composed of can be accessed independently.
-
-  The next example uses a string field as the hash key and
-  demonstrates how you can manually pause and continue a hist trigger.
-  In this example, we'll aggregate fork counts and don't expect a
-  large number of entries in the hash table, so we'll drop it to a
-  much smaller number, say 256:
-
-    # echo 'hist:key=child_comm:val=hitcount:size=256' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
-
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: ibus-daemon                         } hitcount:          1
-    { child_comm: whoopsie                            } hitcount:          1
-    { child_comm: smbd                                } hitcount:          1
-    { child_comm: gdbus                               } hitcount:          1
-    { child_comm: kthreadd                            } hitcount:          1
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: evolution-alarm                     } hitcount:          2
-    { child_comm: Socket Thread                       } hitcount:          2
-    { child_comm: postgres                            } hitcount:          2
-    { child_comm: bash                                } hitcount:          3
-    { child_comm: compiz                              } hitcount:          3
-    { child_comm: evolution-sourc                     } hitcount:          4
-    { child_comm: dhclient                            } hitcount:          4
-    { child_comm: pool                                } hitcount:          5
-    { child_comm: nm-dispatcher.a                     } hitcount:          8
-    { child_comm: firefox                             } hitcount:          8
-    { child_comm: dbus-daemon                         } hitcount:          8
-    { child_comm: glib-pacrunner                      } hitcount:         10
-    { child_comm: evolution                           } hitcount:         23
-
-    Totals:
-        Hits: 89
-        Entries: 20
-        Dropped: 0
-
-  If we want to pause the hist trigger, we can simply append :pause to
-  the command that started the trigger.  Notice that the trigger info
-  displays as [paused]:
-
-    # echo 'hist:key=child_comm:val=hitcount:size=256:pause' >> \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [paused]
-
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: kthreadd                            } hitcount:          1
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: gdbus                               } hitcount:          1
-    { child_comm: ibus-daemon                         } hitcount:          1
-    { child_comm: Socket Thread                       } hitcount:          2
-    { child_comm: evolution-alarm                     } hitcount:          2
-    { child_comm: smbd                                } hitcount:          2
-    { child_comm: bash                                } hitcount:          3
-    { child_comm: whoopsie                            } hitcount:          3
-    { child_comm: compiz                              } hitcount:          3
-    { child_comm: evolution-sourc                     } hitcount:          4
-    { child_comm: pool                                } hitcount:          5
-    { child_comm: postgres                            } hitcount:          6
-    { child_comm: firefox                             } hitcount:          8
-    { child_comm: dhclient                            } hitcount:         10
-    { child_comm: emacs                               } hitcount:         12
-    { child_comm: dbus-daemon                         } hitcount:         20
-    { child_comm: nm-dispatcher.a                     } hitcount:         20
-    { child_comm: evolution                           } hitcount:         35
-    { child_comm: glib-pacrunner                      } hitcount:         59
-
-    Totals:
-        Hits: 199
-        Entries: 21
-        Dropped: 0
-
-  To manually continue having the trigger aggregate events, append
-  :cont instead.  Notice that the trigger info displays as [active]
-  again, and the data has changed:
-
-    # echo 'hist:key=child_comm:val=hitcount:size=256:cont' >> \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
-
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: dconf worker                        } hitcount:          1
-    { child_comm: kthreadd                            } hitcount:          1
-    { child_comm: gdbus                               } hitcount:          1
-    { child_comm: ibus-daemon                         } hitcount:          1
-    { child_comm: Socket Thread                       } hitcount:          2
-    { child_comm: evolution-alarm                     } hitcount:          2
-    { child_comm: smbd                                } hitcount:          2
-    { child_comm: whoopsie                            } hitcount:          3
-    { child_comm: compiz                              } hitcount:          3
-    { child_comm: evolution-sourc                     } hitcount:          4
-    { child_comm: bash                                } hitcount:          5
-    { child_comm: pool                                } hitcount:          5
-    { child_comm: postgres                            } hitcount:          6
-    { child_comm: firefox                             } hitcount:          8
-    { child_comm: dhclient                            } hitcount:         11
-    { child_comm: emacs                               } hitcount:         12
-    { child_comm: dbus-daemon                         } hitcount:         22
-    { child_comm: nm-dispatcher.a                     } hitcount:         22
-    { child_comm: evolution                           } hitcount:         35
-    { child_comm: glib-pacrunner                      } hitcount:         59
-
-    Totals:
-        Hits: 206
-        Entries: 21
-        Dropped: 0
-
-  The previous example showed how to start and stop a hist trigger by
-  appending 'pause' and 'continue' to the hist trigger command.  A
-  hist trigger can also be started in a paused state by initially
-  starting the trigger with ':pause' appended.  This allows you to
-  start the trigger only when you're ready to start collecting data
-  and not before.  For example, you could start the trigger in a
-  paused state, then unpause it and do something you want to measure,
-  then pause the trigger again when done.
-
-  Of course, doing this manually can be difficult and error-prone, but
-  it is possible to automatically start and stop a hist trigger based
-  on some condition, via the enable_hist and disable_hist triggers.
-
-  For example, suppose we wanted to take a look at the relative
-  weights in terms of skb length for each callpath that leads to a
-  netif_receieve_skb event when downloading a decent-sized file using
-  wget.
-
-  First we set up an initially paused stacktrace trigger on the
-  netif_receive_skb event:
-
-    # echo 'hist:key=stacktrace:vals=len:pause' > \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  Next, we set up an 'enable_hist' trigger on the sched_process_exec
-  event, with an 'if filename==/usr/bin/wget' filter.  The effect of
-  this new trigger is that it will 'unpause' the hist trigger we just
-  set up on netif_receive_skb if and only if it sees a
-  sched_process_exec event with a filename of '/usr/bin/wget'.  When
-  that happens, all netif_receive_skb events are aggregated into a
-  hash table keyed on stacktrace:
-
-    # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
-  The aggregation continues until the netif_receive_skb is paused
-  again, which is what the following disable_hist event does by
-  creating a similar setup on the sched_process_exit event, using the
-  filter 'comm==wget':
-
-    # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
-  Whenever a process exits and the comm field of the disable_hist
-  trigger filter matches 'comm==wget', the netif_receive_skb hist
-  trigger is disabled.
-
-  The overall effect is that netif_receive_skb events are aggregated
-  into the hash table for only the duration of the wget.  Executing a
-  wget command and then listing the 'hist' file will display the
-  output generated by the wget command:
-
-    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
-    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
-
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         netif_receive_skb_internal+0x23/0x90
-         napi_gro_receive+0xc8/0x100
-         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
-         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
-         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
-         ieee80211_rx+0x31d/0x900 [mac80211]
-         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
-         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
-         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
-         irq_thread_fn+0x20/0x50
-         irq_thread+0x11f/0x150
-         kthread+0xd2/0xf0
-         ret_from_fork+0x42/0x70
-    } hitcount:         85  len:      28884
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         netif_receive_skb_internal+0x23/0x90
-         napi_gro_complete+0xa4/0xe0
-         dev_gro_receive+0x23a/0x360
-         napi_gro_receive+0x30/0x100
-         ieee80211_deliver_skb+0xd6/0x270 [mac80211]
-         ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
-         ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
-         ieee80211_rx+0x31d/0x900 [mac80211]
-         iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
-         iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
-         iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
-         irq_thread_fn+0x20/0x50
-         irq_thread+0x11f/0x150
-         kthread+0xd2/0xf0
-    } hitcount:         98  len:     664329
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         process_backlog+0xa8/0x150
-         net_rx_action+0x15d/0x340
-         __do_softirq+0x114/0x2c0
-         do_softirq_own_stack+0x1c/0x30
-         do_softirq+0x65/0x70
-         __local_bh_enable_ip+0xb5/0xc0
-         ip_finish_output+0x1f4/0x840
-         ip_output+0x6b/0xc0
-         ip_local_out_sk+0x31/0x40
-         ip_send_skb+0x1a/0x50
-         udp_send_skb+0x173/0x2a0
-         udp_sendmsg+0x2bf/0x9f0
-         inet_sendmsg+0x64/0xa0
-         sock_sendmsg+0x3d/0x50
-    } hitcount:        115  len:      13030
-    { stacktrace:
-         __netif_receive_skb_core+0x46d/0x990
-         __netif_receive_skb+0x18/0x60
-         netif_receive_skb_internal+0x23/0x90
-         napi_gro_complete+0xa4/0xe0
-         napi_gro_flush+0x6d/0x90
-         iwl_pcie_irq_handler+0x92a/0x12f0 [iwlwifi]
-         irq_thread_fn+0x20/0x50
-         irq_thread+0x11f/0x150
-         kthread+0xd2/0xf0
-         ret_from_fork+0x42/0x70
-    } hitcount:        934  len:    5512212
-
-    Totals:
-        Hits: 1232
-        Entries: 4
-        Dropped: 0
-
-  The above shows all the netif_receive_skb callpaths and their total
-  lengths for the duration of the wget command.
-
-  The 'clear' hist trigger param can be used to clear the hash table.
-  Suppose we wanted to try another run of the previous example but
-  this time also wanted to see the complete list of events that went
-  into the histogram.  In order to avoid having to set everything up
-  again, we can just clear the histogram first:
-
-    # echo 'hist:key=stacktrace:vals=len:clear' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  Just to verify that it is in fact cleared, here's what we now see in
-  the hist file:
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
-    # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
-
-    Totals:
-        Hits: 0
-        Entries: 0
-        Dropped: 0
-
-  Since we want to see the detailed list of every netif_receive_skb
-  event occurring during the new run, which are in fact the same
-  events being aggregated into the hash table, we add some additional
-  'enable_event' events to the triggering sched_process_exec and
-  sched_process_exit events as such:
-
-    # echo 'enable_event:net:netif_receive_skb if filename==/usr/bin/wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
-    # echo 'disable_event:net:netif_receive_skb if comm==wget' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
-  If you read the trigger files for the sched_process_exec and
-  sched_process_exit triggers, you should see two triggers for each:
-  one enabling/disabling the hist aggregation and the other
-  enabling/disabling the logging of events:
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-    enable_event:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
-    enable_hist:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-    enable_event:net:netif_receive_skb:unlimited if comm==wget
-    disable_hist:net:netif_receive_skb:unlimited if comm==wget
-
-  In other words, whenever either of the sched_process_exec or
-  sched_process_exit events is hit and matches 'wget', it enables or
-  disables both the histogram and the event log, and what you end up
-  with is a hash table and set of events just covering the specified
-  duration.  Run the wget command again:
-
-    $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
-
-  Displaying the 'hist' file should show something similar to what you
-  saw in the last run, but this time you should also see the
-  individual events in the trace file:
-
-    # cat /sys/kernel/debug/tracing/trace
-
-    # tracer: nop
-    #
-    # entries-in-buffer/entries-written: 183/1426   #P:4
-    #
-    #                              _-----=> irqs-off
-    #                             / _----=> need-resched
-    #                            | / _---=> hardirq/softirq
-    #                            || / _--=> preempt-depth
-    #                            ||| /     delay
-    #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
-    #              | |       |   ||||       |         |
-                wget-15108 [000] ..s1 31769.606929: netif_receive_skb: dev=lo skbaddr=ffff88009c353100 len=60
-                wget-15108 [000] ..s1 31769.606999: netif_receive_skb: dev=lo skbaddr=ffff88009c353200 len=60
-             dnsmasq-1382  [000] ..s1 31769.677652: netif_receive_skb: dev=lo skbaddr=ffff88009c352b00 len=130
-             dnsmasq-1382  [000] ..s1 31769.685917: netif_receive_skb: dev=lo skbaddr=ffff88009c352200 len=138
-    ##### CPU 2 buffer started ####
-      irq/29-iwlwifi-559   [002] ..s. 31772.031529: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433d00 len=2948
-      irq/29-iwlwifi-559   [002] ..s. 31772.031572: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432200 len=1500
-      irq/29-iwlwifi-559   [002] ..s. 31772.032196: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433100 len=2948
-      irq/29-iwlwifi-559   [002] ..s. 31772.032761: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433000 len=2948
-      irq/29-iwlwifi-559   [002] ..s. 31772.033220: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432e00 len=1500
-    .
-    .
-    .
-
-  The following example demonstrates how multiple hist triggers can be
-  attached to a given event.  This capability can be useful for
-  creating a set of different summaries derived from the same set of
-  events, or for comparing the effects of different filters, among
-  other things.
-
-    # echo 'hist:keys=skbaddr.hex:vals=len if len < 0' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=skbaddr.hex:vals=len if len > 4096' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=skbaddr.hex:vals=len if len == 256' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=skbaddr.hex:vals=len' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:keys=len:vals=common_preempt_count' >> \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
-  The above set of commands create four triggers differing only in
-  their filters, along with a completely different though fairly
-  nonsensical trigger.  Note that in order to append multiple hist
-  triggers to the same file, you should use the '>>' operator to
-  append them ('>' will also add the new hist trigger, but will remove
-  any existing hist triggers beforehand).
-
-  Displaying the contents of the 'hist' file for the event shows the
-  contents of all five histograms:
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
-
-    # event histogram
-    #
-    # trigger info: hist:keys=len:vals=hitcount,common_preempt_count:sort=hitcount:size=2048 [active]
-    #
-
-    { len:        176 } hitcount:          1  common_preempt_count:          0
-    { len:        223 } hitcount:          1  common_preempt_count:          0
-    { len:       4854 } hitcount:          1  common_preempt_count:          0
-    { len:        395 } hitcount:          1  common_preempt_count:          0
-    { len:        177 } hitcount:          1  common_preempt_count:          0
-    { len:        446 } hitcount:          1  common_preempt_count:          0
-    { len:       1601 } hitcount:          1  common_preempt_count:          0
-    .
-    .
-    .
-    { len:       1280 } hitcount:         66  common_preempt_count:          0
-    { len:        116 } hitcount:         81  common_preempt_count:         40
-    { len:        708 } hitcount:        112  common_preempt_count:          0
-    { len:         46 } hitcount:        221  common_preempt_count:          0
-    { len:       1264 } hitcount:        458  common_preempt_count:          0
-
-    Totals:
-        Hits: 1428
-        Entries: 147
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
-    #
-
-    { skbaddr: ffff8800baee5e00 } hitcount:          1  len:        130
-    { skbaddr: ffff88005f3d5600 } hitcount:          1  len:       1280
-    { skbaddr: ffff88005f3d4900 } hitcount:          1  len:       1280
-    { skbaddr: ffff88009fed6300 } hitcount:          1  len:        115
-    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:        115
-    { skbaddr: ffff88008cdb1900 } hitcount:          1  len:         46
-    { skbaddr: ffff880064b5ef00 } hitcount:          1  len:        118
-    { skbaddr: ffff880044e3c700 } hitcount:          1  len:         60
-    { skbaddr: ffff880100065900 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d46bd500 } hitcount:          1  len:        116
-    { skbaddr: ffff88005f3d5f00 } hitcount:          1  len:       1280
-    { skbaddr: ffff880100064700 } hitcount:          1  len:        365
-    { skbaddr: ffff8800badb6f00 } hitcount:          1  len:         60
-    .
-    .
-    .
-    { skbaddr: ffff88009fe0be00 } hitcount:         27  len:      24677
-    { skbaddr: ffff88009fe0a400 } hitcount:         27  len:      23052
-    { skbaddr: ffff88009fe0b700 } hitcount:         31  len:      25589
-    { skbaddr: ffff88009fe0b600 } hitcount:         32  len:      27326
-    { skbaddr: ffff88006a462800 } hitcount:         68  len:      71678
-    { skbaddr: ffff88006a463700 } hitcount:         70  len:      72678
-    { skbaddr: ffff88006a462b00 } hitcount:         71  len:      77589
-    { skbaddr: ffff88006a463600 } hitcount:         73  len:      71307
-    { skbaddr: ffff88006a462200 } hitcount:         81  len:      81032
-
-    Totals:
-        Hits: 1451
-        Entries: 318
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len == 256 [active]
-    #
-
-
-    Totals:
-        Hits: 0
-        Entries: 0
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len > 4096 [active]
-    #
-
-    { skbaddr: ffff88009fd2c300 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcce00 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcd700 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcda00 } hitcount:          1  len:      21492
-    { skbaddr: ffff8800ae2e2d00 } hitcount:          1  len:       7212
-    { skbaddr: ffff8800d2bcdb00 } hitcount:          1  len:       7212
-    { skbaddr: ffff88006a4df500 } hitcount:          1  len:       4854
-    { skbaddr: ffff88008ce47b00 } hitcount:          1  len:      18636
-    { skbaddr: ffff8800ae2e2200 } hitcount:          1  len:      12924
-    { skbaddr: ffff88005f3e1000 } hitcount:          1  len:       4356
-    { skbaddr: ffff8800d2bcdc00 } hitcount:          2  len:      24420
-    { skbaddr: ffff8800d2bcc200 } hitcount:          2  len:      12996
-
-    Totals:
-        Hits: 14
-        Entries: 12
-        Dropped: 0
-
-
-    # event histogram
-    #
-    # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len < 0 [active]
-    #
-
-
-    Totals:
-        Hits: 0
-        Entries: 0
-        Dropped: 0
-
-  Named triggers can be used to have triggers share a common set of
-  histogram data.  This capability is mostly useful for combining the
-  output of events generated by tracepoints contained inside inline
-  functions, but names can be used in a hist trigger on any event.
-  For example, these two triggers when hit will update the same 'len'
-  field in the shared 'foo' histogram data:
-
-    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
-           /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-    # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
-           /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  You can see that they're updating common histogram data by reading
-  each event's hist files at the same time:
-
-    # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist;
-      cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
-    # event histogram
-    #
-    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
-    #
-
-    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
-    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
-    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
-    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
-    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
-    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
-    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
-    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
-    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
-    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
-    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
-    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
-    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
-    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
-    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
-    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
-    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
-    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
-    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
-    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
-    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
-    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
-    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
-    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
-    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
-    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
-    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
-    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
-    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
-    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
-    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
-    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
-    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
-    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
-    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
-    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
-    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
-
-    Totals:
-        Hits: 81
-        Entries: 42
-        Dropped: 0
-    # event histogram
-    #
-    # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
-    #
-
-    { skbaddr: ffff88000ad53500 } hitcount:          1  len:         46
-    { skbaddr: ffff8800af5a1500 } hitcount:          1  len:         76
-    { skbaddr: ffff8800d62a1900 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bccb00 } hitcount:          1  len:        468
-    { skbaddr: ffff8800d3c69900 } hitcount:          1  len:         46
-    { skbaddr: ffff88009ff09100 } hitcount:          1  len:         52
-    { skbaddr: ffff88010f13ab00 } hitcount:          1  len:        168
-    { skbaddr: ffff88006a54f400 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcc500 } hitcount:          1  len:        260
-    { skbaddr: ffff880064505000 } hitcount:          1  len:         46
-    { skbaddr: ffff8800baf24e00 } hitcount:          1  len:         32
-    { skbaddr: ffff88009fe0ad00 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d3edff00 } hitcount:          1  len:         44
-    { skbaddr: ffff88009fe0b400 } hitcount:          1  len:        168
-    { skbaddr: ffff8800a1c55a00 } hitcount:          1  len:         40
-    { skbaddr: ffff8800d2bcd100 } hitcount:          1  len:         40
-    { skbaddr: ffff880064505f00 } hitcount:          1  len:        174
-    { skbaddr: ffff8800a8bff200 } hitcount:          1  len:        160
-    { skbaddr: ffff880044e3cc00 } hitcount:          1  len:         76
-    { skbaddr: ffff8800a8bfe700 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcdc00 } hitcount:          1  len:         32
-    { skbaddr: ffff8800a1f64800 } hitcount:          1  len:         46
-    { skbaddr: ffff8800d2bcde00 } hitcount:          1  len:        988
-    { skbaddr: ffff88006a5dea00 } hitcount:          1  len:         46
-    { skbaddr: ffff88002e37a200 } hitcount:          1  len:         44
-    { skbaddr: ffff8800a1f32c00 } hitcount:          2  len:        676
-    { skbaddr: ffff88000ad52600 } hitcount:          2  len:        107
-    { skbaddr: ffff8800a1f91e00 } hitcount:          2  len:         92
-    { skbaddr: ffff8800af5a0200 } hitcount:          2  len:        142
-    { skbaddr: ffff8800d2bcc600 } hitcount:          2  len:        220
-    { skbaddr: ffff8800ba36f500 } hitcount:          2  len:         92
-    { skbaddr: ffff8800d021f800 } hitcount:          2  len:         92
-    { skbaddr: ffff8800a1f33600 } hitcount:          2  len:        675
-    { skbaddr: ffff8800a8bfff00 } hitcount:          3  len:        138
-    { skbaddr: ffff8800d62a1300 } hitcount:          3  len:        138
-    { skbaddr: ffff88002e37a100 } hitcount:          4  len:        184
-    { skbaddr: ffff880064504400 } hitcount:          4  len:        184
-    { skbaddr: ffff8800a8bfec00 } hitcount:          4  len:        184
-    { skbaddr: ffff88000ad53700 } hitcount:          5  len:        230
-    { skbaddr: ffff8800d2bcdb00 } hitcount:          5  len:        196
-    { skbaddr: ffff8800a1f90000 } hitcount:          6  len:        276
-    { skbaddr: ffff88006a54f900 } hitcount:          6  len:        276
-
-    Totals:
-        Hits: 81
-        Entries: 42
-        Dropped: 0
-
-  And here's an example that shows how to combine histogram data from
-  any two events even if they don't share any 'compatible' fields
-  other than 'hitcount' and 'stacktrace'.  These commands create a
-  couple of triggers named 'bar' using those fields:
-
-    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
-           /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-    # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
-          /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
-  And displaying the output of either shows some interesting if
-  somewhat confusing output:
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
-    # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
-    # event histogram
-    #
-    # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active]
-    #
-
-    { stacktrace:
-             _do_fork+0x18e/0x330
-             kernel_thread+0x29/0x30
-             kthreadd+0x154/0x1b0
-             ret_from_fork+0x3f/0x70
-    } hitcount:          1
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx_ni+0x20/0x70
-             dev_loopback_xmit+0xaa/0xd0
-             ip_mc_output+0x126/0x240
-             ip_local_out_sk+0x31/0x40
-             igmp_send_report+0x1e9/0x230
-             igmp_timer_expire+0xe9/0x120
-             call_timer_fn+0x39/0xf0
-             run_timer_softirq+0x1e1/0x290
-             __do_softirq+0xfd/0x290
-             irq_exit+0x98/0xb0
-             smp_apic_timer_interrupt+0x4a/0x60
-             apic_timer_interrupt+0x6d/0x80
-             cpuidle_enter+0x17/0x20
-             call_cpuidle+0x3b/0x60
-             cpu_startup_entry+0x22d/0x310
-    } hitcount:          1
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx_ni+0x20/0x70
-             dev_loopback_xmit+0xaa/0xd0
-             ip_mc_output+0x17f/0x240
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x13e/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             SYSC_sendto+0xef/0x170
-             SyS_sendto+0xe/0x10
-             entry_SYSCALL_64_fastpath+0x12/0x6a
-    } hitcount:          2
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx+0x1c/0x60
-             loopback_xmit+0x6c/0xb0
-             dev_hard_start_xmit+0x219/0x3a0
-             __dev_queue_xmit+0x415/0x4f0
-             dev_queue_xmit_sk+0x13/0x20
-             ip_finish_output2+0x237/0x340
-             ip_finish_output+0x113/0x1d0
-             ip_output+0x66/0xc0
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x16d/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             ___sys_sendmsg+0x14e/0x270
-    } hitcount:         76
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx+0x1c/0x60
-             loopback_xmit+0x6c/0xb0
-             dev_hard_start_xmit+0x219/0x3a0
-             __dev_queue_xmit+0x415/0x4f0
-             dev_queue_xmit_sk+0x13/0x20
-             ip_finish_output2+0x237/0x340
-             ip_finish_output+0x113/0x1d0
-             ip_output+0x66/0xc0
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x16d/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             ___sys_sendmsg+0x269/0x270
-    } hitcount:         77
-    { stacktrace:
-             netif_rx_internal+0xb2/0xd0
-             netif_rx+0x1c/0x60
-             loopback_xmit+0x6c/0xb0
-             dev_hard_start_xmit+0x219/0x3a0
-             __dev_queue_xmit+0x415/0x4f0
-             dev_queue_xmit_sk+0x13/0x20
-             ip_finish_output2+0x237/0x340
-             ip_finish_output+0x113/0x1d0
-             ip_output+0x66/0xc0
-             ip_local_out_sk+0x31/0x40
-             ip_send_skb+0x1a/0x50
-             udp_send_skb+0x16d/0x270
-             udp_sendmsg+0x2bf/0x980
-             inet_sendmsg+0x67/0xa0
-             sock_sendmsg+0x38/0x50
-             SYSC_sendto+0xef/0x170
-    } hitcount:         88
-    { stacktrace:
-             _do_fork+0x18e/0x330
-             SyS_clone+0x19/0x20
-             entry_SYSCALL_64_fastpath+0x12/0x6a
-    } hitcount:        244
-
-    Totals:
-        Hits: 489
-        Entries: 7
-        Dropped: 0
-
-2.2 Inter-event hist triggers
------------------------------
-
-Inter-event hist triggers are hist triggers that combine values from
-one or more other events and create a histogram using that data.  Data
-from an inter-event histogram can in turn become the source for
-further combined histograms, thus providing a chain of related
-histograms, which is important for some applications.
-
-The most important example of an inter-event quantity that can be used
-in this manner is latency, which is simply a difference in timestamps
-between two events.  Although latency is the most important
-inter-event quantity, note that because the support is completely
-general across the trace event subsystem, any event field can be used
-in an inter-event quantity.
-
-An example of a histogram that combines data from other histograms
-into a useful chain would be a 'wakeupswitch latency' histogram that
-combines a 'wakeup latency' histogram and a 'switch latency'
-histogram.
-
-Normally, a hist trigger specification consists of a (possibly
-compound) key along with one or more numeric values, which are
-continually updated sums associated with that key.  A histogram
-specification in this case consists of individual key and value
-specifications that refer to trace event fields associated with a
-single event type.
-
-The inter-event hist trigger extension allows fields from multiple
-events to be referenced and combined into a multi-event histogram
-specification.  In support of this overall goal, a few enabling
-features have been added to the hist trigger support:
-
-  - In order to compute an inter-event quantity, a value from one
-    event needs to saved and then referenced from another event.  This
-    requires the introduction of support for histogram 'variables'.
-
-  - The computation of inter-event quantities and their combination
-    require some minimal amount of support for applying simple
-    expressions to variables (+ and -).
-
-  - A histogram consisting of inter-event quantities isn't logically a
-    histogram on either event (so having the 'hist' file for either
-    event host the histogram output doesn't really make sense).  To
-    address the idea that the histogram is associated with a
-    combination of events, support is added allowing the creation of
-    'synthetic' events that are events derived from other events.
-    These synthetic events are full-fledged events just like any other
-    and can be used as such, as for instance to create the
-    'combination' histograms mentioned previously.
-
-  - A set of 'actions' can be associated with histogram entries -
-    these can be used to generate the previously mentioned synthetic
-    events, but can also be used for other purposes, such as for
-    example saving context when a 'max' latency has been hit.
-
-  - Trace events don't have a 'timestamp' associated with them, but
-    there is an implicit timestamp saved along with an event in the
-    underlying ftrace ring buffer.  This timestamp is now exposed as a
-    a synthetic field named 'common_timestamp' which can be used in
-    histograms as if it were any other event field; it isn't an actual
-    field in the trace format but rather is a synthesized value that
-    nonetheless can be used as if it were an actual field.  By default
-    it is in units of nanoseconds; appending '.usecs' to a
-    common_timestamp field changes the units to microseconds.
-
-A note on inter-event timestamps: If common_timestamp is used in a
-histogram, the trace buffer is automatically switched over to using
-absolute timestamps and the "global" trace clock, in order to avoid
-bogus timestamp differences with other clocks that aren't coherent
-across CPUs.  This can be overridden by specifying one of the other
-trace clocks instead, using the "clock=XXX" hist trigger attribute,
-where XXX is any of the clocks listed in the tracing/trace_clock
-pseudo-file.
-
-These features are described in more detail in the following sections.
-
-2.2.1 Histogram Variables
--------------------------
-
-Variables are simply named locations used for saving and retrieving
-values between matching events.  A 'matching' event is defined as an
-event that has a matching key - if a variable is saved for a histogram
-entry corresponding to that key, any subsequent event with a matching
-key can access that variable.
-
-A variable's value is normally available to any subsequent event until
-it is set to something else by a subsequent event.  The one exception
-to that rule is that any variable used in an expression is essentially
-'read-once' - once it's used by an expression in a subsequent event,
-it's reset to its 'unset' state, which means it can't be used again
-unless it's set again.  This ensures not only that an event doesn't
-use an uninitialized variable in a calculation, but that that variable
-is used only once and not for any unrelated subsequent match.
-
-The basic syntax for saving a variable is to simply prefix a unique
-variable name not corresponding to any keyword along with an '=' sign
-to any event field.
-
-Either keys or values can be saved and retrieved in this way.  This
-creates a variable named 'ts0' for a histogram entry with the key
-'next_pid':
-
-  # echo 'hist:keys=next_pid:vals=$ts0:ts0=common_timestamp ... >> \
-	event/trigger
-
-The ts0 variable can be accessed by any subsequent event having the
-same pid as 'next_pid'.
-
-Variable references are formed by prepending the variable name with
-the '$' sign.  Thus for example, the ts0 variable above would be
-referenced as '$ts0' in expressions.
-
-Because 'vals=' is used, the common_timestamp variable value above
-will also be summed as a normal histogram value would (though for a
-timestamp it makes little sense).
-
-The below shows that a key value can also be saved in the same way:
-
-  # echo 'hist:timer_pid=common_pid:key=timer_pid ...' >> event/trigger
-
-If a variable isn't a key variable or prefixed with 'vals=', the
-associated event field will be saved in a variable but won't be summed
-as a value:
-
-  # echo 'hist:keys=next_pid:ts1=common_timestamp ...' >> event/trigger
-
-Multiple variables can be assigned at the same time.  The below would
-result in both ts0 and b being created as variables, with both
-common_timestamp and field1 additionally being summed as values:
-
-  # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ...' >> \
-	event/trigger
-
-Note that variable assignments can appear either preceding or
-following their use.  The command below behaves identically to the
-command above:
-
-  # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ...' >> \
-	event/trigger
-
-Any number of variables not bound to a 'vals=' prefix can also be
-assigned by simply separating them with colons.  Below is the same
-thing but without the values being summed in the histogram:
-
-  # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ...' >> event/trigger
-
-Variables set as above can be referenced and used in expressions on
-another event.
-
-For example, here's how a latency can be calculated:
-
-  # echo 'hist:keys=pid,prio:ts0=common_timestamp ...' >> event1/trigger
-  # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ...' >> event2/trigger
-
-In the first line above, the event's timetamp is saved into the
-variable ts0.  In the next line, ts0 is subtracted from the second
-event's timestamp to produce the latency, which is then assigned into
-yet another variable, 'wakeup_lat'.  The hist trigger below in turn
-makes use of the wakeup_lat variable to compute a combined latency
-using the same key and variable from yet another event:
-
-  # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ...' >> event3/trigger
-
-2.2.2 Synthetic Events
-----------------------
-
-Synthetic events are user-defined events generated from hist trigger
-variables or fields associated with one or more other events.  Their
-purpose is to provide a mechanism for displaying data spanning
-multiple events consistent with the existing and already familiar
-usage for normal events.
-
-To define a synthetic event, the user writes a simple specification
-consisting of the name of the new event along with one or more
-variables and their types, which can be any valid field type,
-separated by semicolons, to the tracing/synthetic_events file.
-
-For instance, the following creates a new event named 'wakeup_latency'
-with 3 fields: lat, pid, and prio.  Each of those fields is simply a
-variable reference to a variable on another event:
-
-  # echo 'wakeup_latency \
-          u64 lat; \
-          pid_t pid; \
-	  int prio' >> \
-	  /sys/kernel/debug/tracing/synthetic_events
-
-Reading the tracing/synthetic_events file lists all the currently
-defined synthetic events, in this case the event defined above:
-
-  # cat /sys/kernel/debug/tracing/synthetic_events
-    wakeup_latency u64 lat; pid_t pid; int prio
-
-An existing synthetic event definition can be removed by prepending
-the command that defined it with a '!':
-
-  # echo '!wakeup_latency u64 lat pid_t pid int prio' >> \
-    /sys/kernel/debug/tracing/synthetic_events
-
-At this point, there isn't yet an actual 'wakeup_latency' event
-instantiated in the event subsytem - for this to happen, a 'hist
-trigger action' needs to be instantiated and bound to actual fields
-and variables defined on other events (see Section 2.2.3 below on
-how that is done using hist trigger 'onmatch' action). Once that is
-done, the 'wakeup_latency' synthetic event instance is created.
-
-A histogram can now be defined for the new synthetic event:
-
-  # echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
-        /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
-
-The new event is created under the tracing/events/synthetic/ directory
-and looks and behaves just like any other event:
-
-  # ls /sys/kernel/debug/tracing/events/synthetic/wakeup_latency
-        enable  filter  format  hist  id  trigger
-
-Like any other event, once a histogram is enabled for the event, the
-output can be displayed by reading the event's 'hist' file.
-
-2.2.3 Hist trigger 'actions'
-----------------------------
-
-A hist trigger 'action' is a function that's executed whenever a
-histogram entry is added or updated.
-
-The default 'action' if no special function is explicity specified is
-as it always has been, to simply update the set of values associated
-with an entry.  Some applications, however, may want to perform
-additional actions at that point, such as generate another event, or
-compare and save a maximum.
-
-The following additional actions are available.  To specify an action
-for a given event, simply specify the action between colons in the
-hist trigger specification.
-
-  - onmatch(matching.event).<synthetic_event_name>(param list)
-
-    The 'onmatch(matching.event).<synthetic_event_name>(params)' hist
-    trigger action is invoked whenever an event matches and the
-    histogram entry would be added or updated.  It causes the named
-    synthetic event to be generated with the values given in the
-    'param list'.  The result is the generation of a synthetic event
-    that consists of the values contained in those variables at the
-    time the invoking event was hit.
-
-    The 'param list' consists of one or more parameters which may be
-    either variables or fields defined on either the 'matching.event'
-    or the target event.  The variables or fields specified in the
-    param list may be either fully-qualified or unqualified.  If a
-    variable is specified as unqualified, it must be unique between
-    the two events.  A field name used as a param can be unqualified
-    if it refers to the target event, but must be fully qualified if
-    it refers to the matching event.  A fully-qualified name is of the
-    form 'system.event_name.$var_name' or 'system.event_name.field'.
-
-    The 'matching.event' specification is simply the fully qualified
-    event name of the event that matches the target event for the
-    onmatch() functionality, in the form 'system.event_name'.
-
-    Finally, the number and type of variables/fields in the 'param
-    list' must match the number and types of the fields in the
-    synthetic event being generated.
-
-    As an example the below defines a simple synthetic event and uses
-    a variable defined on the sched_wakeup_new event as a parameter
-    when invoking the synthetic event.  Here we define the synthetic
-    event:
-
-    # echo 'wakeup_new_test pid_t pid' >> \
-           /sys/kernel/debug/tracing/synthetic_events
-
-    # cat /sys/kernel/debug/tracing/synthetic_events
-          wakeup_new_test pid_t pid
-
-    The following hist trigger both defines the missing testpid
-    variable and specifies an onmatch() action that generates a
-    wakeup_new_test synthetic event whenever a sched_wakeup_new event
-    occurs, which because of the 'if comm == "cyclictest"' filter only
-    happens when the executable is cyclictest:
-
-    # echo 'hist:keys=$testpid:testpid=pid:onmatch(sched.sched_wakeup_new).\
-            wakeup_new_test($testpid) if comm=="cyclictest"' >> \
-            /sys/kernel/debug/tracing/events/sched/sched_wakeup_new/trigger
-
-    Creating and displaying a histogram based on those events is now
-    just a matter of using the fields and new synthetic event in the
-    tracing/events/synthetic directory, as usual:
-
-    # echo 'hist:keys=pid:sort=pid' >> \
-           /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/trigger
-
-    Running 'cyclictest' should cause wakeup_new events to generate
-    wakeup_new_test synthetic events which should result in histogram
-    output in the wakeup_new_test event's hist file:
-
-    # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/hist
-
-    A more typical usage would be to use two events to calculate a
-    latency.  The following example uses a set of hist triggers to
-    produce a 'wakeup_latency' histogram:
-
-    First, we define a 'wakeup_latency' synthetic event:
-
-    # echo 'wakeup_latency u64 lat; pid_t pid; int prio' >> \
-            /sys/kernel/debug/tracing/synthetic_events
-
-    Next, we specify that whenever we see a sched_waking event for a
-    cyclictest thread, save the timestamp in a 'ts0' variable:
-
-    # echo 'hist:keys=$saved_pid:saved_pid=pid:ts0=common_timestamp.usecs \
-            if comm=="cyclictest"' >> \
-	    /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
-
-    Then, when the corresponding thread is actually scheduled onto the
-    CPU by a sched_switch event, calculate the latency and use that
-    along with another variable and an event field to generate a
-    wakeup_latency synthetic event:
-
-    # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:\
-            onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,\
-	            $saved_pid,next_prio) if next_comm=="cyclictest"' >> \
-	    /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
-
-    We also need to create a histogram on the wakeup_latency synthetic
-    event in order to aggregate the generated synthetic event data:
-
-    # echo 'hist:keys=pid,prio,lat:sort=pid,lat' >> \
-            /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
-
-    Finally, once we've run cyclictest to actually generate some
-    events, we can see the output by looking at the wakeup_latency
-    synthetic event's hist file:
-
-    # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/hist
-
-  - onmax(var).save(field,..	.)
-
-    The 'onmax(var).save(field,...)' hist trigger action is invoked
-    whenever the value of 'var' associated with a histogram entry
-    exceeds the current maximum contained in that variable.
-
-    The end result is that the trace event fields specified as the
-    onmax.save() params will be saved if 'var' exceeds the current
-    maximum for that hist trigger entry.  This allows context from the
-    event that exhibited the new maximum to be saved for later
-    reference.  When the histogram is displayed, additional fields
-    displaying the saved values will be printed.
-
-    As an example the below defines a couple of hist triggers, one for
-    sched_waking and another for sched_switch, keyed on pid.  Whenever
-    a sched_waking occurs, the timestamp is saved in the entry
-    corresponding to the current pid, and when the scheduler switches
-    back to that pid, the timestamp difference is calculated.  If the
-    resulting latency, stored in wakeup_lat, exceeds the current
-    maximum latency, the values specified in the save() fields are
-    recorded:
-
-    # echo 'hist:keys=pid:ts0=common_timestamp.usecs \
-            if comm=="cyclictest"' >> \
-            /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
-
-    # echo 'hist:keys=next_pid:\
-            wakeup_lat=common_timestamp.usecs-$ts0:\
-            onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) \
-            if next_comm=="cyclictest"' >> \
-            /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
-
-    When the histogram is displayed, the max value and the saved
-    values corresponding to the max are displayed following the rest
-    of the fields:
-
-    # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist
-      { next_pid:       2255 } hitcount:        239
-        common_timestamp-ts0:          0
-        max:         27
-	next_comm: cyclictest
-        prev_pid:          0  prev_prio:        120  prev_comm: swapper/1
-
-      { next_pid:       2256 } hitcount:       2355
-        common_timestamp-ts0: 0
-        max:         49  next_comm: cyclictest
-        prev_pid:          0  prev_prio:        120  prev_comm: swapper/0
-
-      Totals:
-          Hits: 12970
-          Entries: 2
-          Dropped: 0
-
-3. User space creating a trigger
---------------------------------
-
-Writing into /sys/kernel/tracing/trace_marker writes into the ftrace
-ring buffer. This can also act like an event, by writing into the trigger
-file located in /sys/kernel/tracing/events/ftrace/print/
-
-Modifying cyclictest to write into the trace_marker file before it sleeps
-and after it wakes up, something like this:
-
-static void traceputs(char *str)
-{
-	/* tracemark_fd is the trace_marker file descriptor */
-	if (tracemark_fd < 0)
-		return;
-	/* write the tracemark message */
-	write(tracemark_fd, str, strlen(str));
-}
-
-And later add something like:
-
-	traceputs("start");
-	clock_nanosleep(...);
-	traceputs("end");
-
-We can make a histogram from this:
-
- # cd /sys/kernel/tracing
- # echo 'latency u64 lat' > synthetic_events
- # echo 'hist:keys=common_pid:ts0=common_timestamp.usecs if buf == "start"' > events/ftrace/print/trigger
- # echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(ftrace.print).latency($lat) if buf == "end"' >> events/ftrace/print/trigger
- # echo 'hist:keys=lat,common_pid:sort=lat' > events/synthetic/latency/trigger
-
-The above created a synthetic event called "latency" and two histograms
-against the trace_marker, one gets triggered when "start" is written into the
-trace_marker file and the other when "end" is written. If the pids match, then
-it will call the "latency" synthetic event with the calculated latency as its
-parameter. Finally, a histogram is added to the latency synthetic event to
-record the calculated latency along with the pid.
-
-Now running cyclictest with:
-
- # ./cyclictest -p80 -d0 -i250 -n -a -t --tracemark -b 1000
-
- -p80  : run threads at priority 80
- -d0   : have all threads run at the same interval
- -i250 : start the interval at 250 microseconds (all threads will do this)
- -n    : sleep with nanosleep
- -a    : affine all threads to a separate CPU
- -t    : one thread per available CPU
- --tracemark : enable trace mark writing
- -b 1000 : stop if any latency is greater than 1000 microseconds
-
-Note, the -b 1000 is used just to make --tracemark available.
-
-Then we can see the histogram created by this with:
-
- # cat events/synthetic/latency/hist
-# event histogram
-#
-# trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
-#
-
-{ lat:        107, common_pid:       2039 } hitcount:          1
-{ lat:        122, common_pid:       2041 } hitcount:          1
-{ lat:        166, common_pid:       2039 } hitcount:          1
-{ lat:        174, common_pid:       2039 } hitcount:          1
-{ lat:        194, common_pid:       2041 } hitcount:          1
-{ lat:        196, common_pid:       2036 } hitcount:          1
-{ lat:        197, common_pid:       2038 } hitcount:          1
-{ lat:        198, common_pid:       2039 } hitcount:          1
-{ lat:        199, common_pid:       2039 } hitcount:          1
-{ lat:        200, common_pid:       2041 } hitcount:          1
-{ lat:        201, common_pid:       2039 } hitcount:          2
-{ lat:        202, common_pid:       2038 } hitcount:          1
-{ lat:        202, common_pid:       2043 } hitcount:          1
-{ lat:        203, common_pid:       2039 } hitcount:          1
-{ lat:        203, common_pid:       2036 } hitcount:          1
-{ lat:        203, common_pid:       2041 } hitcount:          1
-{ lat:        206, common_pid:       2038 } hitcount:          2
-{ lat:        207, common_pid:       2039 } hitcount:          1
-{ lat:        207, common_pid:       2036 } hitcount:          1
-{ lat:        208, common_pid:       2040 } hitcount:          1
-{ lat:        209, common_pid:       2043 } hitcount:          1
-{ lat:        210, common_pid:       2039 } hitcount:          1
-{ lat:        211, common_pid:       2039 } hitcount:          4
-{ lat:        212, common_pid:       2043 } hitcount:          1
-{ lat:        212, common_pid:       2039 } hitcount:          2
-{ lat:        213, common_pid:       2039 } hitcount:          1
-{ lat:        214, common_pid:       2038 } hitcount:          1
-{ lat:        214, common_pid:       2039 } hitcount:          2
-{ lat:        214, common_pid:       2042 } hitcount:          1
-{ lat:        215, common_pid:       2039 } hitcount:          1
-{ lat:        217, common_pid:       2036 } hitcount:          1
-{ lat:        217, common_pid:       2040 } hitcount:          1
-{ lat:        217, common_pid:       2039 } hitcount:          1
-{ lat:        218, common_pid:       2039 } hitcount:          6
-{ lat:        219, common_pid:       2039 } hitcount:          9
-{ lat:        220, common_pid:       2039 } hitcount:         11
-{ lat:        221, common_pid:       2039 } hitcount:          5
-{ lat:        221, common_pid:       2042 } hitcount:          1
-{ lat:        222, common_pid:       2039 } hitcount:          7
-{ lat:        223, common_pid:       2036 } hitcount:          1
-{ lat:        223, common_pid:       2039 } hitcount:          3
-{ lat:        224, common_pid:       2039 } hitcount:          4
-{ lat:        224, common_pid:       2037 } hitcount:          1
-{ lat:        224, common_pid:       2036 } hitcount:          2
-{ lat:        225, common_pid:       2039 } hitcount:          5
-{ lat:        225, common_pid:       2042 } hitcount:          1
-{ lat:        226, common_pid:       2039 } hitcount:          7
-{ lat:        226, common_pid:       2036 } hitcount:          4
-{ lat:        227, common_pid:       2039 } hitcount:          6
-{ lat:        227, common_pid:       2036 } hitcount:         12
-{ lat:        227, common_pid:       2043 } hitcount:          1
-{ lat:        228, common_pid:       2039 } hitcount:          7
-{ lat:        228, common_pid:       2036 } hitcount:         14
-{ lat:        229, common_pid:       2039 } hitcount:          9
-{ lat:        229, common_pid:       2036 } hitcount:          8
-{ lat:        229, common_pid:       2038 } hitcount:          1
-{ lat:        230, common_pid:       2039 } hitcount:         11
-{ lat:        230, common_pid:       2036 } hitcount:          6
-{ lat:        230, common_pid:       2043 } hitcount:          1
-{ lat:        230, common_pid:       2042 } hitcount:          2
-{ lat:        231, common_pid:       2041 } hitcount:          1
-{ lat:        231, common_pid:       2036 } hitcount:          6
-{ lat:        231, common_pid:       2043 } hitcount:          1
-{ lat:        231, common_pid:       2039 } hitcount:          8
-{ lat:        232, common_pid:       2037 } hitcount:          1
-{ lat:        232, common_pid:       2039 } hitcount:          6
-{ lat:        232, common_pid:       2040 } hitcount:          2
-{ lat:        232, common_pid:       2036 } hitcount:          5
-{ lat:        232, common_pid:       2043 } hitcount:          1
-{ lat:        233, common_pid:       2036 } hitcount:          5
-{ lat:        233, common_pid:       2039 } hitcount:         11
-{ lat:        234, common_pid:       2039 } hitcount:          4
-{ lat:        234, common_pid:       2038 } hitcount:          2
-{ lat:        234, common_pid:       2043 } hitcount:          2
-{ lat:        234, common_pid:       2036 } hitcount:         11
-{ lat:        234, common_pid:       2040 } hitcount:          1
-{ lat:        235, common_pid:       2037 } hitcount:          2
-{ lat:        235, common_pid:       2036 } hitcount:          8
-{ lat:        235, common_pid:       2043 } hitcount:          2
-{ lat:        235, common_pid:       2039 } hitcount:          5
-{ lat:        235, common_pid:       2042 } hitcount:          2
-{ lat:        235, common_pid:       2040 } hitcount:          4
-{ lat:        235, common_pid:       2041 } hitcount:          1
-{ lat:        236, common_pid:       2036 } hitcount:          7
-{ lat:        236, common_pid:       2037 } hitcount:          1
-{ lat:        236, common_pid:       2041 } hitcount:          5
-{ lat:        236, common_pid:       2039 } hitcount:          3
-{ lat:        236, common_pid:       2043 } hitcount:          9
-{ lat:        236, common_pid:       2040 } hitcount:          7
-{ lat:        237, common_pid:       2037 } hitcount:          1
-{ lat:        237, common_pid:       2040 } hitcount:          1
-{ lat:        237, common_pid:       2036 } hitcount:          9
-{ lat:        237, common_pid:       2039 } hitcount:          3
-{ lat:        237, common_pid:       2043 } hitcount:          8
-{ lat:        237, common_pid:       2042 } hitcount:          2
-{ lat:        237, common_pid:       2041 } hitcount:          2
-{ lat:        238, common_pid:       2043 } hitcount:         10
-{ lat:        238, common_pid:       2040 } hitcount:          1
-{ lat:        238, common_pid:       2037 } hitcount:          9
-{ lat:        238, common_pid:       2038 } hitcount:          1
-{ lat:        238, common_pid:       2039 } hitcount:          1
-{ lat:        238, common_pid:       2042 } hitcount:          3
-{ lat:        238, common_pid:       2036 } hitcount:          7
-{ lat:        239, common_pid:       2041 } hitcount:          1
-{ lat:        239, common_pid:       2043 } hitcount:         11
-{ lat:        239, common_pid:       2037 } hitcount:         11
-{ lat:        239, common_pid:       2038 } hitcount:          6
-{ lat:        239, common_pid:       2036 } hitcount:          7
-{ lat:        239, common_pid:       2040 } hitcount:          1
-{ lat:        239, common_pid:       2042 } hitcount:          9
-{ lat:        240, common_pid:       2037 } hitcount:         29
-{ lat:        240, common_pid:       2043 } hitcount:         15
-{ lat:        240, common_pid:       2040 } hitcount:         44
-{ lat:        240, common_pid:       2039 } hitcount:          1
-{ lat:        240, common_pid:       2041 } hitcount:          2
-{ lat:        240, common_pid:       2038 } hitcount:          1
-{ lat:        240, common_pid:       2036 } hitcount:         10
-{ lat:        240, common_pid:       2042 } hitcount:         13
-{ lat:        241, common_pid:       2036 } hitcount:         21
-{ lat:        241, common_pid:       2041 } hitcount:         36
-{ lat:        241, common_pid:       2037 } hitcount:         34
-{ lat:        241, common_pid:       2042 } hitcount:         14
-{ lat:        241, common_pid:       2040 } hitcount:         94
-{ lat:        241, common_pid:       2039 } hitcount:         12
-{ lat:        241, common_pid:       2038 } hitcount:          2
-{ lat:        241, common_pid:       2043 } hitcount:         28
-{ lat:        242, common_pid:       2040 } hitcount:        109
-{ lat:        242, common_pid:       2041 } hitcount:        506
-{ lat:        242, common_pid:       2039 } hitcount:        155
-{ lat:        242, common_pid:       2042 } hitcount:         21
-{ lat:        242, common_pid:       2037 } hitcount:         52
-{ lat:        242, common_pid:       2043 } hitcount:         21
-{ lat:        242, common_pid:       2036 } hitcount:         16
-{ lat:        242, common_pid:       2038 } hitcount:        156
-{ lat:        243, common_pid:       2037 } hitcount:         46
-{ lat:        243, common_pid:       2039 } hitcount:         40
-{ lat:        243, common_pid:       2042 } hitcount:        119
-{ lat:        243, common_pid:       2041 } hitcount:        611
-{ lat:        243, common_pid:       2036 } hitcount:         69
-{ lat:        243, common_pid:       2038 } hitcount:        784
-{ lat:        243, common_pid:       2040 } hitcount:        323
-{ lat:        243, common_pid:       2043 } hitcount:         14
-{ lat:        244, common_pid:       2043 } hitcount:         35
-{ lat:        244, common_pid:       2042 } hitcount:        305
-{ lat:        244, common_pid:       2039 } hitcount:          8
-{ lat:        244, common_pid:       2040 } hitcount:       4515
-{ lat:        244, common_pid:       2038 } hitcount:        371
-{ lat:        244, common_pid:       2037 } hitcount:         31
-{ lat:        244, common_pid:       2036 } hitcount:        114
-{ lat:        244, common_pid:       2041 } hitcount:       3396
-{ lat:        245, common_pid:       2036 } hitcount:        700
-{ lat:        245, common_pid:       2041 } hitcount:       2772
-{ lat:        245, common_pid:       2037 } hitcount:        268
-{ lat:        245, common_pid:       2039 } hitcount:        472
-{ lat:        245, common_pid:       2038 } hitcount:       2758
-{ lat:        245, common_pid:       2042 } hitcount:       3833
-{ lat:        245, common_pid:       2040 } hitcount:       3105
-{ lat:        245, common_pid:       2043 } hitcount:        645
-{ lat:        246, common_pid:       2038 } hitcount:       3451
-{ lat:        246, common_pid:       2041 } hitcount:        142
-{ lat:        246, common_pid:       2037 } hitcount:       5101
-{ lat:        246, common_pid:       2040 } hitcount:         68
-{ lat:        246, common_pid:       2043 } hitcount:       5099
-{ lat:        246, common_pid:       2039 } hitcount:       5608
-{ lat:        246, common_pid:       2042 } hitcount:       3723
-{ lat:        246, common_pid:       2036 } hitcount:       4738
-{ lat:        247, common_pid:       2042 } hitcount:        312
-{ lat:        247, common_pid:       2043 } hitcount:       2385
-{ lat:        247, common_pid:       2041 } hitcount:        452
-{ lat:        247, common_pid:       2038 } hitcount:        792
-{ lat:        247, common_pid:       2040 } hitcount:         78
-{ lat:        247, common_pid:       2036 } hitcount:       2375
-{ lat:        247, common_pid:       2039 } hitcount:       1834
-{ lat:        247, common_pid:       2037 } hitcount:       2655
-{ lat:        248, common_pid:       2037 } hitcount:         36
-{ lat:        248, common_pid:       2042 } hitcount:         11
-{ lat:        248, common_pid:       2038 } hitcount:        122
-{ lat:        248, common_pid:       2036 } hitcount:        135
-{ lat:        248, common_pid:       2039 } hitcount:         26
-{ lat:        248, common_pid:       2041 } hitcount:        503
-{ lat:        248, common_pid:       2043 } hitcount:         66
-{ lat:        248, common_pid:       2040 } hitcount:         46
-{ lat:        249, common_pid:       2037 } hitcount:         29
-{ lat:        249, common_pid:       2038 } hitcount:          1
-{ lat:        249, common_pid:       2043 } hitcount:         29
-{ lat:        249, common_pid:       2039 } hitcount:          8
-{ lat:        249, common_pid:       2042 } hitcount:         56
-{ lat:        249, common_pid:       2040 } hitcount:         27
-{ lat:        249, common_pid:       2041 } hitcount:         11
-{ lat:        249, common_pid:       2036 } hitcount:         27
-{ lat:        250, common_pid:       2038 } hitcount:          1
-{ lat:        250, common_pid:       2036 } hitcount:         30
-{ lat:        250, common_pid:       2040 } hitcount:         19
-{ lat:        250, common_pid:       2043 } hitcount:         22
-{ lat:        250, common_pid:       2042 } hitcount:         20
-{ lat:        250, common_pid:       2041 } hitcount:          1
-{ lat:        250, common_pid:       2039 } hitcount:          6
-{ lat:        250, common_pid:       2037 } hitcount:         48
-{ lat:        251, common_pid:       2037 } hitcount:         43
-{ lat:        251, common_pid:       2039 } hitcount:          1
-{ lat:        251, common_pid:       2036 } hitcount:         12
-{ lat:        251, common_pid:       2042 } hitcount:          2
-{ lat:        251, common_pid:       2041 } hitcount:          1
-{ lat:        251, common_pid:       2043 } hitcount:         15
-{ lat:        251, common_pid:       2040 } hitcount:          3
-{ lat:        252, common_pid:       2040 } hitcount:          1
-{ lat:        252, common_pid:       2036 } hitcount:         12
-{ lat:        252, common_pid:       2037 } hitcount:         21
-{ lat:        252, common_pid:       2043 } hitcount:         14
-{ lat:        253, common_pid:       2037 } hitcount:         21
-{ lat:        253, common_pid:       2039 } hitcount:          2
-{ lat:        253, common_pid:       2036 } hitcount:          9
-{ lat:        253, common_pid:       2043 } hitcount:          6
-{ lat:        253, common_pid:       2040 } hitcount:          1
-{ lat:        254, common_pid:       2036 } hitcount:          8
-{ lat:        254, common_pid:       2043 } hitcount:          3
-{ lat:        254, common_pid:       2041 } hitcount:          1
-{ lat:        254, common_pid:       2042 } hitcount:          1
-{ lat:        254, common_pid:       2039 } hitcount:          1
-{ lat:        254, common_pid:       2037 } hitcount:         12
-{ lat:        255, common_pid:       2043 } hitcount:          1
-{ lat:        255, common_pid:       2037 } hitcount:          2
-{ lat:        255, common_pid:       2036 } hitcount:          2
-{ lat:        255, common_pid:       2039 } hitcount:          8
-{ lat:        256, common_pid:       2043 } hitcount:          1
-{ lat:        256, common_pid:       2036 } hitcount:          4
-{ lat:        256, common_pid:       2039 } hitcount:          6
-{ lat:        257, common_pid:       2039 } hitcount:          5
-{ lat:        257, common_pid:       2036 } hitcount:          4
-{ lat:        258, common_pid:       2039 } hitcount:          5
-{ lat:        258, common_pid:       2036 } hitcount:          2
-{ lat:        259, common_pid:       2036 } hitcount:          7
-{ lat:        259, common_pid:       2039 } hitcount:          7
-{ lat:        260, common_pid:       2036 } hitcount:          8
-{ lat:        260, common_pid:       2039 } hitcount:          6
-{ lat:        261, common_pid:       2036 } hitcount:          5
-{ lat:        261, common_pid:       2039 } hitcount:          7
-{ lat:        262, common_pid:       2039 } hitcount:          5
-{ lat:        262, common_pid:       2036 } hitcount:          5
-{ lat:        263, common_pid:       2039 } hitcount:          7
-{ lat:        263, common_pid:       2036 } hitcount:          7
-{ lat:        264, common_pid:       2039 } hitcount:          9
-{ lat:        264, common_pid:       2036 } hitcount:          9
-{ lat:        265, common_pid:       2036 } hitcount:          5
-{ lat:        265, common_pid:       2039 } hitcount:          1
-{ lat:        266, common_pid:       2036 } hitcount:          1
-{ lat:        266, common_pid:       2039 } hitcount:          3
-{ lat:        267, common_pid:       2036 } hitcount:          1
-{ lat:        267, common_pid:       2039 } hitcount:          3
-{ lat:        268, common_pid:       2036 } hitcount:          1
-{ lat:        268, common_pid:       2039 } hitcount:          6
-{ lat:        269, common_pid:       2036 } hitcount:          1
-{ lat:        269, common_pid:       2043 } hitcount:          1
-{ lat:        269, common_pid:       2039 } hitcount:          2
-{ lat:        270, common_pid:       2040 } hitcount:          1
-{ lat:        270, common_pid:       2039 } hitcount:          6
-{ lat:        271, common_pid:       2041 } hitcount:          1
-{ lat:        271, common_pid:       2039 } hitcount:          5
-{ lat:        272, common_pid:       2039 } hitcount:         10
-{ lat:        273, common_pid:       2039 } hitcount:          8
-{ lat:        274, common_pid:       2039 } hitcount:          2
-{ lat:        275, common_pid:       2039 } hitcount:          1
-{ lat:        276, common_pid:       2039 } hitcount:          2
-{ lat:        276, common_pid:       2037 } hitcount:          1
-{ lat:        276, common_pid:       2038 } hitcount:          1
-{ lat:        277, common_pid:       2039 } hitcount:          1
-{ lat:        277, common_pid:       2042 } hitcount:          1
-{ lat:        278, common_pid:       2039 } hitcount:          1
-{ lat:        279, common_pid:       2039 } hitcount:          4
-{ lat:        279, common_pid:       2043 } hitcount:          1
-{ lat:        280, common_pid:       2039 } hitcount:          3
-{ lat:        283, common_pid:       2036 } hitcount:          2
-{ lat:        284, common_pid:       2039 } hitcount:          1
-{ lat:        284, common_pid:       2043 } hitcount:          1
-{ lat:        288, common_pid:       2039 } hitcount:          1
-{ lat:        289, common_pid:       2039 } hitcount:          1
-{ lat:        300, common_pid:       2039 } hitcount:          1
-{ lat:        384, common_pid:       2039 } hitcount:          1
-
-Totals:
-    Hits: 67625
-    Entries: 278
-    Dropped: 0
-
-Note, the writes are around the sleep, so ideally they will all be of 250
-microseconds. If you are wondering how there are several that are under
-250 microseconds, that is because the way cyclictest works, is if one
-iteration comes in late, the next one will set the timer to wake up less that
-250. That is, if an iteration came in 50 microseconds late, the next wake up
-will be at 200 microseconds.
-
-But this could easily be done in userspace. To make this even more
-interesting, we can mix the histogram between events that happened in the
-kernel with trace_marker.
-
- # cd /sys/kernel/tracing
- # echo 'latency u64 lat' > synthetic_events
- # echo 'hist:keys=pid:ts0=common_timestamp.usecs' > events/sched/sched_waking/trigger
- # echo 'hist:keys=common_pid:lat=common_timestamp.usecs-$ts0:onmatch(sched.sched_waking).latency($lat) if buf == "end"' > events/ftrace/print/trigger
- # echo 'hist:keys=lat,common_pid:sort=lat' > events/synthetic/latency/trigger
-
-The difference this time is that instead of using the trace_marker to start
-the latency, the sched_waking event is used, matching the common_pid for the
-trace_marker write with the pid that is being woken by sched_waking.
-
-After running cyclictest again with the same parameters, we now have:
-
- # cat events/synthetic/latency/hist
-# event histogram
-#
-# trigger info: hist:keys=lat,common_pid:vals=hitcount:sort=lat:size=2048 [active]
-#
-
-{ lat:          7, common_pid:       2302 } hitcount:        640
-{ lat:          7, common_pid:       2299 } hitcount:         42
-{ lat:          7, common_pid:       2303 } hitcount:         18
-{ lat:          7, common_pid:       2305 } hitcount:        166
-{ lat:          7, common_pid:       2306 } hitcount:          1
-{ lat:          7, common_pid:       2301 } hitcount:         91
-{ lat:          7, common_pid:       2300 } hitcount:         17
-{ lat:          8, common_pid:       2303 } hitcount:       8296
-{ lat:          8, common_pid:       2304 } hitcount:       6864
-{ lat:          8, common_pid:       2305 } hitcount:       9464
-{ lat:          8, common_pid:       2301 } hitcount:       9213
-{ lat:          8, common_pid:       2306 } hitcount:       6246
-{ lat:          8, common_pid:       2302 } hitcount:       8797
-{ lat:          8, common_pid:       2299 } hitcount:       8771
-{ lat:          8, common_pid:       2300 } hitcount:       8119
-{ lat:          9, common_pid:       2305 } hitcount:       1519
-{ lat:          9, common_pid:       2299 } hitcount:       2346
-{ lat:          9, common_pid:       2303 } hitcount:       2841
-{ lat:          9, common_pid:       2301 } hitcount:       1846
-{ lat:          9, common_pid:       2304 } hitcount:       3861
-{ lat:          9, common_pid:       2302 } hitcount:       1210
-{ lat:          9, common_pid:       2300 } hitcount:       2762
-{ lat:          9, common_pid:       2306 } hitcount:       4247
-{ lat:         10, common_pid:       2299 } hitcount:         16
-{ lat:         10, common_pid:       2306 } hitcount:        333
-{ lat:         10, common_pid:       2303 } hitcount:         16
-{ lat:         10, common_pid:       2304 } hitcount:        168
-{ lat:         10, common_pid:       2302 } hitcount:        240
-{ lat:         10, common_pid:       2301 } hitcount:         28
-{ lat:         10, common_pid:       2300 } hitcount:         95
-{ lat:         10, common_pid:       2305 } hitcount:         18
-{ lat:         11, common_pid:       2303 } hitcount:          5
-{ lat:         11, common_pid:       2305 } hitcount:          8
-{ lat:         11, common_pid:       2306 } hitcount:        221
-{ lat:         11, common_pid:       2302 } hitcount:         76
-{ lat:         11, common_pid:       2304 } hitcount:         26
-{ lat:         11, common_pid:       2300 } hitcount:        125
-{ lat:         11, common_pid:       2299 } hitcount:          2
-{ lat:         12, common_pid:       2305 } hitcount:          3
-{ lat:         12, common_pid:       2300 } hitcount:          6
-{ lat:         12, common_pid:       2306 } hitcount:         90
-{ lat:         12, common_pid:       2302 } hitcount:          4
-{ lat:         12, common_pid:       2303 } hitcount:          1
-{ lat:         12, common_pid:       2304 } hitcount:        122
-{ lat:         13, common_pid:       2300 } hitcount:         12
-{ lat:         13, common_pid:       2301 } hitcount:          1
-{ lat:         13, common_pid:       2306 } hitcount:         32
-{ lat:         13, common_pid:       2302 } hitcount:          5
-{ lat:         13, common_pid:       2305 } hitcount:          1
-{ lat:         13, common_pid:       2303 } hitcount:          1
-{ lat:         13, common_pid:       2304 } hitcount:         61
-{ lat:         14, common_pid:       2303 } hitcount:          4
-{ lat:         14, common_pid:       2306 } hitcount:          5
-{ lat:         14, common_pid:       2305 } hitcount:          4
-{ lat:         14, common_pid:       2304 } hitcount:         62
-{ lat:         14, common_pid:       2302 } hitcount:         19
-{ lat:         14, common_pid:       2300 } hitcount:         33
-{ lat:         14, common_pid:       2299 } hitcount:          1
-{ lat:         14, common_pid:       2301 } hitcount:          4
-{ lat:         15, common_pid:       2305 } hitcount:          1
-{ lat:         15, common_pid:       2302 } hitcount:         25
-{ lat:         15, common_pid:       2300 } hitcount:         11
-{ lat:         15, common_pid:       2299 } hitcount:          5
-{ lat:         15, common_pid:       2301 } hitcount:          1
-{ lat:         15, common_pid:       2304 } hitcount:          8
-{ lat:         15, common_pid:       2303 } hitcount:          1
-{ lat:         15, common_pid:       2306 } hitcount:          6
-{ lat:         16, common_pid:       2302 } hitcount:         31
-{ lat:         16, common_pid:       2306 } hitcount:          3
-{ lat:         16, common_pid:       2300 } hitcount:          5
-{ lat:         17, common_pid:       2302 } hitcount:          6
-{ lat:         17, common_pid:       2303 } hitcount:          1
-{ lat:         18, common_pid:       2304 } hitcount:          1
-{ lat:         18, common_pid:       2302 } hitcount:          8
-{ lat:         18, common_pid:       2299 } hitcount:          1
-{ lat:         18, common_pid:       2301 } hitcount:          1
-{ lat:         19, common_pid:       2303 } hitcount:          4
-{ lat:         19, common_pid:       2304 } hitcount:          5
-{ lat:         19, common_pid:       2302 } hitcount:          4
-{ lat:         19, common_pid:       2299 } hitcount:          3
-{ lat:         19, common_pid:       2306 } hitcount:          1
-{ lat:         19, common_pid:       2300 } hitcount:          4
-{ lat:         19, common_pid:       2305 } hitcount:          5
-{ lat:         20, common_pid:       2299 } hitcount:          2
-{ lat:         20, common_pid:       2302 } hitcount:          3
-{ lat:         20, common_pid:       2305 } hitcount:          1
-{ lat:         20, common_pid:       2300 } hitcount:          2
-{ lat:         20, common_pid:       2301 } hitcount:          2
-{ lat:         20, common_pid:       2303 } hitcount:          3
-{ lat:         21, common_pid:       2305 } hitcount:          1
-{ lat:         21, common_pid:       2299 } hitcount:          5
-{ lat:         21, common_pid:       2303 } hitcount:          4
-{ lat:         21, common_pid:       2302 } hitcount:          7
-{ lat:         21, common_pid:       2300 } hitcount:          1
-{ lat:         21, common_pid:       2301 } hitcount:          5
-{ lat:         21, common_pid:       2304 } hitcount:          2
-{ lat:         22, common_pid:       2302 } hitcount:          5
-{ lat:         22, common_pid:       2303 } hitcount:          1
-{ lat:         22, common_pid:       2306 } hitcount:          3
-{ lat:         22, common_pid:       2301 } hitcount:          2
-{ lat:         22, common_pid:       2300 } hitcount:          1
-{ lat:         22, common_pid:       2299 } hitcount:          1
-{ lat:         22, common_pid:       2305 } hitcount:          1
-{ lat:         22, common_pid:       2304 } hitcount:          1
-{ lat:         23, common_pid:       2299 } hitcount:          1
-{ lat:         23, common_pid:       2306 } hitcount:          2
-{ lat:         23, common_pid:       2302 } hitcount:          6
-{ lat:         24, common_pid:       2302 } hitcount:          3
-{ lat:         24, common_pid:       2300 } hitcount:          1
-{ lat:         24, common_pid:       2306 } hitcount:          2
-{ lat:         24, common_pid:       2305 } hitcount:          1
-{ lat:         24, common_pid:       2299 } hitcount:          1
-{ lat:         25, common_pid:       2300 } hitcount:          1
-{ lat:         25, common_pid:       2302 } hitcount:          4
-{ lat:         26, common_pid:       2302 } hitcount:          2
-{ lat:         27, common_pid:       2305 } hitcount:          1
-{ lat:         27, common_pid:       2300 } hitcount:          1
-{ lat:         27, common_pid:       2302 } hitcount:          3
-{ lat:         28, common_pid:       2306 } hitcount:          1
-{ lat:         28, common_pid:       2302 } hitcount:          4
-{ lat:         29, common_pid:       2302 } hitcount:          1
-{ lat:         29, common_pid:       2300 } hitcount:          2
-{ lat:         29, common_pid:       2306 } hitcount:          1
-{ lat:         29, common_pid:       2304 } hitcount:          1
-{ lat:         30, common_pid:       2302 } hitcount:          4
-{ lat:         31, common_pid:       2302 } hitcount:          6
-{ lat:         32, common_pid:       2302 } hitcount:          1
-{ lat:         33, common_pid:       2299 } hitcount:          1
-{ lat:         33, common_pid:       2302 } hitcount:          3
-{ lat:         34, common_pid:       2302 } hitcount:          2
-{ lat:         35, common_pid:       2302 } hitcount:          1
-{ lat:         35, common_pid:       2304 } hitcount:          1
-{ lat:         36, common_pid:       2302 } hitcount:          4
-{ lat:         37, common_pid:       2302 } hitcount:          6
-{ lat:         38, common_pid:       2302 } hitcount:          2
-{ lat:         39, common_pid:       2302 } hitcount:          2
-{ lat:         39, common_pid:       2304 } hitcount:          1
-{ lat:         40, common_pid:       2304 } hitcount:          2
-{ lat:         40, common_pid:       2302 } hitcount:          5
-{ lat:         41, common_pid:       2304 } hitcount:          1
-{ lat:         41, common_pid:       2302 } hitcount:          8
-{ lat:         42, common_pid:       2302 } hitcount:          6
-{ lat:         42, common_pid:       2304 } hitcount:          1
-{ lat:         43, common_pid:       2302 } hitcount:          3
-{ lat:         43, common_pid:       2304 } hitcount:          4
-{ lat:         44, common_pid:       2302 } hitcount:          6
-{ lat:         45, common_pid:       2302 } hitcount:          5
-{ lat:         46, common_pid:       2302 } hitcount:          5
-{ lat:         47, common_pid:       2302 } hitcount:          7
-{ lat:         48, common_pid:       2301 } hitcount:          1
-{ lat:         48, common_pid:       2302 } hitcount:          9
-{ lat:         49, common_pid:       2302 } hitcount:          3
-{ lat:         50, common_pid:       2302 } hitcount:          1
-{ lat:         50, common_pid:       2301 } hitcount:          1
-{ lat:         51, common_pid:       2302 } hitcount:          2
-{ lat:         51, common_pid:       2301 } hitcount:          1
-{ lat:         61, common_pid:       2302 } hitcount:          1
-{ lat:        110, common_pid:       2302 } hitcount:          1
-
-Totals:
-    Hits: 89565
-    Entries: 158
-    Dropped: 0
-
-This doesn't tell us any information about how late cyclictest may have
-woken up, but it does show us a nice histogram of how long it took from
-the time that cyclictest was woken to the time it made it into user space.
diff --git a/Documentation/trace/index.rst b/Documentation/trace/index.rst
index b58c10b04e27..306997941ba1 100644
--- a/Documentation/trace/index.rst
+++ b/Documentation/trace/index.rst
@@ -18,6 +18,7 @@ Linux Tracing Technologies
    events-nmi
    events-msr
    mmiotrace
+   histogram
    hwlat_detector
    intel_th
    stm
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index dcc0166d1997..2bd4a9181a0f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -605,7 +605,7 @@ config HIST_TRIGGERS
 	  Inter-event tracing of quantities such as latencies is also
 	  supported using hist triggers under this option.
 
-	  See Documentation/trace/histogram.txt.
+	  See Documentation/trace/histogram.rst.
 	  If in doubt, say N.
 
 config MMIOTRACE_TEST
-- 
cgit v1.2.3


From be926ceeb4efc3bf44cb9b56f5c71aac9b1f8bbe Mon Sep 17 00:00:00 2001
From: Jean-Christophe Dubois <jcd@tribudubois.net>
Date: Sun, 1 Jul 2018 00:10:50 +0200
Subject: thermal: i.MX: Allow thermal probe to fail gracefully in case of bad
 calibration.

Without this fix, the thermal probe on i.MX6 might trigger a division
by zero exception later in the probe if the calibration does fail.

Note: This linux behavior (Division by zero in kernel) has been triggered
on a Qemu i.MX6 emulation where parameters in nvmem were not set. With this
fix the division by zero is not triggeed anymore as the thermal probe does
fail early.

Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/imx_thermal.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/imx_thermal.c b/drivers/thermal/imx_thermal.c
index 334d98be03b9..b1f82d64253e 100644
--- a/drivers/thermal/imx_thermal.c
+++ b/drivers/thermal/imx_thermal.c
@@ -604,7 +604,10 @@ static int imx_init_from_nvmem_cells(struct platform_device *pdev)
 	ret = nvmem_cell_read_u32(&pdev->dev, "calib", &val);
 	if (ret)
 		return ret;
-	imx_init_calib(pdev, val);
+
+	ret = imx_init_calib(pdev, val);
+	if (ret)
+		return ret;
 
 	ret = nvmem_cell_read_u32(&pdev->dev, "temp_grade", &val);
 	if (ret)
-- 
cgit v1.2.3


From 00b062967f1524de25daf6578d9043b0bbe7c208 Mon Sep 17 00:00:00 2001
From: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Date: Wed, 27 Jun 2018 13:38:30 +0530
Subject: drm/i915/psr: Add psr1 live status

Prints live state of psr1.Extending the existing
PSR2 live state function to cover psr1.

Tested on KBL with psr2 and psr1 panel.

v2: rebase
v3: DK
    Rename psr2_live_status to psr_source_status.
v4: DK
    Move EDP_PSR_STATUS_STATE_SHIFT below EDP_PSR_STATUS_STATE_MASK.
    Pass seq to psr_source_status, handle source status prints in
    psr_source_status.
v5: Fixed CI warning messages
v6:
    Remove extra space in the title before the colon.(DK)
    Rebase. (Jani)
v7: Use tabs for indenting the values.(Jani)
v8: Addressed dk's review comments.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>

Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Vathsala Nagaraju <vathsala.nagaraju@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530086910-15914-1-git-send-email-vathsala.nagaraju@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c | 72 ++++++++++++++++++++++++-------------
 drivers/gpu/drm/i915/i915_reg.h     |  1 +
 2 files changed, 49 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 48a57c0636bf..f6142d78ede4 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2592,27 +2592,55 @@ static const struct file_operations i915_guc_log_relay_fops = {
 	.release = i915_guc_log_relay_release,
 };
 
-static const char *psr2_live_status(u32 val)
-{
-	static const char * const live_status[] = {
-		"IDLE",
-		"CAPTURE",
-		"CAPTURE_FS",
-		"SLEEP",
-		"BUFON_FW",
-		"ML_UP",
-		"SU_STANDBY",
-		"FAST_SLEEP",
-		"DEEP_SLEEP",
-		"BUF_ON",
-		"TG_ON"
-	};
+static void
+psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
+{
+	u32 val, psr_status;
 
-	val = (val & EDP_PSR2_STATUS_STATE_MASK) >> EDP_PSR2_STATUS_STATE_SHIFT;
-	if (val < ARRAY_SIZE(live_status))
-		return live_status[val];
+	if (dev_priv->psr.psr2_enabled) {
+		static const char * const live_status[] = {
+			"IDLE",
+			"CAPTURE",
+			"CAPTURE_FS",
+			"SLEEP",
+			"BUFON_FW",
+			"ML_UP",
+			"SU_STANDBY",
+			"FAST_SLEEP",
+			"DEEP_SLEEP",
+			"BUF_ON",
+			"TG_ON"
+		};
+		psr_status = I915_READ(EDP_PSR2_STATUS);
+		val = (psr_status & EDP_PSR2_STATUS_STATE_MASK) >>
+			EDP_PSR2_STATUS_STATE_SHIFT;
+		if (val < ARRAY_SIZE(live_status)) {
+			seq_printf(m, "Source PSR status: 0x%x [%s]\n",
+				   psr_status, live_status[val]);
+			return;
+		}
+	} else {
+		static const char * const live_status[] = {
+			"IDLE",
+			"SRDONACK",
+			"SRDENT",
+			"BUFOFF",
+			"BUFON",
+			"AUXACK",
+			"SRDOFFACK",
+			"SRDENT_ON",
+		};
+		psr_status = I915_READ(EDP_PSR_STATUS);
+		val = (psr_status & EDP_PSR_STATUS_STATE_MASK) >>
+			EDP_PSR_STATUS_STATE_SHIFT;
+		if (val < ARRAY_SIZE(live_status)) {
+			seq_printf(m, "Source PSR status: 0x%x [%s]\n",
+				   psr_status, live_status[val]);
+			return;
+		}
+	}
 
-	return "unknown";
+	seq_printf(m, "Source PSR status: 0x%x [%s]\n", psr_status, "unknown");
 }
 
 static const char *psr_sink_status(u8 val)
@@ -2676,12 +2704,8 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 
 		seq_printf(m, "Performance_Counter: %u\n", psrperf);
 	}
-	if (dev_priv->psr.psr2_enabled) {
-		u32 psr2 = I915_READ(EDP_PSR2_STATUS);
 
-		seq_printf(m, "EDP_PSR2_STATUS: %x [%s]\n",
-			   psr2, psr2_live_status(psr2));
-	}
+	psr_source_status(dev_priv, m);
 
 	if (dev_priv->psr.enabled) {
 		struct drm_dp_aux *aux = &dev_priv->psr.enabled->aux;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 7dc774682922..69b9978d7dda 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4133,6 +4133,7 @@ enum {
 
 #define EDP_PSR_STATUS				_MMIO(dev_priv->psr_mmio_base + 0x40)
 #define   EDP_PSR_STATUS_STATE_MASK		(7 << 29)
+#define   EDP_PSR_STATUS_STATE_SHIFT		29
 #define   EDP_PSR_STATUS_STATE_IDLE		(0 << 29)
 #define   EDP_PSR_STATUS_STATE_SRDONACK		(1 << 29)
 #define   EDP_PSR_STATUS_STATE_SRDENT		(2 << 29)
-- 
cgit v1.2.3


From abdd322f680870dbe1942425d1fa2c74de4721f4 Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Date: Wed, 27 Jun 2018 23:18:54 -0700
Subject: drm/i915: Remove unnecessary check for unsupported modifiers for NV12

There is already a check to allow only RGB8888 formats with CCS
modifiers.

Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628061854.6430-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/intel_display.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index fca72ce0b3b3..ce7646265b50 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -14478,11 +14478,6 @@ static int intel_framebuffer_init(struct intel_framebuffer *intel_fb,
 		}
 		break;
 	case DRM_FORMAT_NV12:
-		if (mode_cmd->modifier[0] == I915_FORMAT_MOD_Y_TILED_CCS ||
-		    mode_cmd->modifier[0] == I915_FORMAT_MOD_Yf_TILED_CCS) {
-			DRM_DEBUG_KMS("RC not to be enabled with NV12\n");
-			goto err;
-		}
 		if (INTEL_GEN(dev_priv) < 9 || IS_SKYLAKE(dev_priv) ||
 		    IS_BROXTON(dev_priv)) {
 			DRM_DEBUG_KMS("unsupported pixel format: %s\n",
-- 
cgit v1.2.3


From c43dbcbbcc8c515d4ececc7a996d5fc7286c28c3 Mon Sep 17 00:00:00 2001
From: Tarun Vyas <tarun.vyas@intel.com>
Date: Wed, 27 Jun 2018 13:02:49 -0700
Subject: drm/i915/psr: Lockless version of psr_wait_for_idle

This is a lockless version of the exisiting psr_wait_for_idle().
We want to wait for PSR to idle out inside intel_pipe_update_start.
At the time of a pipe update, we should never race with any psr
enable or disable code, which is a part of crtc enable/disable.
The follow up patch will use this lockless wait inside pipe_update_
start to wait for PSR to idle out before checking for vblank evasion.
We need to keep the wait in pipe_update_start to as less as it can be.
So,we can live and flourish w/o taking any psr locks at all.

Even if psr is never enabled, psr2_enabled will be false and this
function will wait for PSR1 to idle out, which should just return
immediately, so a very short (~1-2 usec) wait for cases where PSR
is disabled.

v2: Add comment to explain the 25msec timeout (DK)

v3: Rename psr_wait_for_idle to __psr_wait_for_idle_locked to avoid
    naming conflicts and propagate err (if any) to the caller (Chris)

v5: Form a series with the next patch

v7: Better explain the need for lockless wait and increase the max
    timeout to handle refresh rates < 60 Hz (Daniel Vetter)

v8: Rebase

Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Tarun Vyas <tarun.vyas@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627200250.1515-1-tarun.vyas@intel.com
---
 drivers/gpu/drm/i915/intel_drv.h |  1 +
 drivers/gpu/drm/i915/intel_psr.c | 36 ++++++++++++++++++++++++++++++++++--
 2 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 5a37db292d3a..a8073eb02ffa 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1921,6 +1921,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug);
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir);
 void intel_psr_short_pulse(struct intel_dp *intel_dp);
+int intel_psr_wait_for_idle(struct drm_i915_private *dev_priv);
 
 /* intel_runtime_pm.c */
 int intel_power_domains_init(struct drm_i915_private *);
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 45f1cb7d6c04..23acc9ac8d4d 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -717,7 +717,39 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 	cancel_work_sync(&dev_priv->psr.work);
 }
 
-static bool psr_wait_for_idle(struct drm_i915_private *dev_priv)
+int intel_psr_wait_for_idle(struct drm_i915_private *dev_priv)
+{
+	i915_reg_t reg;
+	u32 mask;
+
+	/*
+	 * The sole user right now is intel_pipe_update_start(),
+	 * which won't race with psr_enable/disable, which is
+	 * where psr2_enabled is written to. So, we don't need
+	 * to acquire the psr.lock. More importantly, we want the
+	 * latency inside intel_pipe_update_start() to be as low
+	 * as possible, so no need to acquire psr.lock when it is
+	 * not needed and will induce latencies in the atomic
+	 * update path.
+	 */
+	if (dev_priv->psr.psr2_enabled) {
+		reg = EDP_PSR2_STATUS;
+		mask = EDP_PSR2_STATUS_STATE_MASK;
+	} else {
+		reg = EDP_PSR_STATUS;
+		mask = EDP_PSR_STATUS_STATE_MASK;
+	}
+
+	/*
+	 * Max time for PSR to idle = Inverse of the refresh rate +
+	 * 6 ms of exit training time + 1.5 ms of aux channel
+	 * handshake. 50 msec is defesive enough to cover everything.
+	 */
+	return intel_wait_for_register(dev_priv, reg, mask,
+				       EDP_PSR_STATUS_STATE_IDLE, 50);
+}
+
+static bool __psr_wait_for_idle_locked(struct drm_i915_private *dev_priv)
 {
 	struct intel_dp *intel_dp;
 	i915_reg_t reg;
@@ -763,7 +795,7 @@ static void intel_psr_work(struct work_struct *work)
 	 * PSR might take some time to get fully disabled
 	 * and be ready for re-enable.
 	 */
-	if (!psr_wait_for_idle(dev_priv))
+	if (!__psr_wait_for_idle_locked(dev_priv))
 		goto unlock;
 
 	/*
-- 
cgit v1.2.3


From a608987970b929e250957e4e3fb891f1f10eff6f Mon Sep 17 00:00:00 2001
From: Tarun Vyas <tarun.vyas@intel.com>
Date: Wed, 27 Jun 2018 13:02:50 -0700
Subject: drm/i915: Wait for PSR exit before checking for vblank evasion

The PIPEDSL freezes on PSR entry and if PSR hasn't fully exited, then
the pipe_update_start call schedules itself out to check back later.

On ChromeOS-4.4 kernel, which is fairly up-to-date w.r.t drm/i915 but
lags w.r.t core kernel code, hot plugging an external display triggers
tons of "potential atomic update errors" in the dmesg, on *pipe A*. A
closer analysis reveals that we try to read the scanline 3 times and
eventually timeout, b/c PSR hasn't exited fully leading to a PIPEDSL
stuck @ 1599. This issue is not seen on upstream kernels, b/c for *some*
reason we loop inside intel_pipe_update start for ~2+ msec which in this
case is more than enough to exit PSR fully, hence an *unstuck* PIPEDSL
counter, hence no error. On the other hand, the ChromeOS kernel spends
~1.1 msec looping inside intel_pipe_update_start and hence errors out
b/c the source is still in PSR.

Regardless, we should wait for PSR exit (if PSR is disabled, we incur
a ~1-2 usec penalty) before reading the PIPEDSL, b/c if we haven't
fully exited PSR, then checking for vblank evasion isn't actually
applicable.

v4: Comment explaining psr_wait after enabling VBL interrupts (DK)

v5: CAN_PSR() to handle platforms that don't support PSR.

v6: Handle local_irq_disable on early return (Chris)

Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Tarun Vyas <tarun.vyas@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180627200250.1515-2-tarun.vyas@intel.com
---
 drivers/gpu/drm/i915/intel_sprite.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index d9e7f4fb5096..e2328d0402d8 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -107,13 +107,21 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 						      VBLANK_EVASION_TIME_US);
 	max = vblank_start - 1;
 
-	local_irq_disable();
-
 	if (min <= 0 || max <= 0)
-		return;
+		goto irq_disable;
 
 	if (WARN_ON(drm_crtc_vblank_get(&crtc->base)))
-		return;
+		goto irq_disable;
+
+	/*
+	 * Wait for psr to idle out after enabling the VBL interrupts
+	 * VBL interrupts will start the PSR exit and prevent a PSR
+	 * re-entry as well.
+	 */
+	if (CAN_PSR(dev_priv) && intel_psr_wait_for_idle(dev_priv))
+		DRM_ERROR("PSR idle timed out, atomic update may fail\n");
+
+	local_irq_disable();
 
 	crtc->debug.min_vbl = min;
 	crtc->debug.max_vbl = max;
@@ -171,6 +179,10 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 	crtc->debug.start_vbl_count = intel_crtc_get_vblank_counter(crtc);
 
 	trace_i915_pipe_update_vblank_evaded(crtc);
+	return;
+
+irq_disable:
+	local_irq_disable();
 }
 
 /**
-- 
cgit v1.2.3


From 1262dc09dc9ae7bf4ad00b6a2c5ed6a6936bcd10 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 26 Jun 2018 17:35:16 -0300
Subject: scsi: ibmvscsi: Improve strings handling

Currently an open firmware property is copied into partition_name variable
without keeping a room for \0.

Later one, this variable (partition_name), which is 97 bytes long, is
strncpyed into ibmvcsci_host_data->madapter_info->partition_name, which is
96 bytes long, possibly truncating it 'again' and removing the \0.

This patch simply decreases the partition name to 96 and just copy using
strlcpy() which guarantees that the string is \0 terminated. I think there
is no issue if this there is a truncation in this very first copy, i.e,
when the open firmware property is read and copied into the driver for the
very first time;

This issue also causes the following warning on GCC 8:

	drivers/scsi/ibmvscsi/ibmvscsi.c:281:2: warning:  strncpy  output may be truncated copying 96 bytes from a string of length 96 [-Wstringop-truncation]
	...
	inlined from  ibmvscsi_probe  at drivers/scsi/ibmvscsi/ibmvscsi.c:2221:7:
	drivers/scsi/ibmvscsi/ibmvscsi.c:265:3: warning:  strncpy  specified bound 97 equals destination size [-Wstringop-truncation]

CC: Bart Van Assche <bart.vanassche@wdc.com>
CC: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: Breno Leitao <leitao@debian.org>
Acked-by: Tyrel Datwyler <tyreld@linux.vnet.ibm.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvscsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 44916282ebd4..02689298325b 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -93,7 +93,7 @@ static int max_requests = IBMVSCSI_MAX_REQUESTS_DEFAULT;
 static int max_events = IBMVSCSI_MAX_REQUESTS_DEFAULT + 2;
 static int fast_fail = 1;
 static int client_reserve = 1;
-static char partition_name[97] = "UNKNOWN";
+static char partition_name[96] = "UNKNOWN";
 static unsigned int partition_number = -1;
 static LIST_HEAD(ibmvscsi_head);
 
@@ -262,7 +262,7 @@ static void gather_partition_info(void)
 
 	ppartition_name = of_get_property(of_root, "ibm,partition-name", NULL);
 	if (ppartition_name)
-		strncpy(partition_name, ppartition_name,
+		strlcpy(partition_name, ppartition_name,
 				sizeof(partition_name));
 	p_number_ptr = of_get_property(of_root, "ibm,partition-no", NULL);
 	if (p_number_ptr)
-- 
cgit v1.2.3


From 915d9b71422126076f1971f1a44561ae76890060 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 28 Jun 2018 12:23:10 +0300
Subject: scsi: qedi: tidy up a size calculation

The id_tbl->table pointer points to unsigned long so static checkers
complain that instead of 4 we should be allocating sizeof(long) bytes.

We're trying to allocate enough bits for the bitmap.  The size variable is
always 1024.  (1024 / 32 * 4) is the same as (1024 / 64 * 8) so this
doesn't change runtime, but this is the more idiomatic way to do it and
makes the static checker happy.

[mkp: typo]

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Manish Rangankar <Manish.Rangankar@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qedi/qedi_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qedi/qedi_main.c b/drivers/scsi/qedi/qedi_main.c
index cf274a79e77a..682f3ce31014 100644
--- a/drivers/scsi/qedi/qedi_main.c
+++ b/drivers/scsi/qedi/qedi_main.c
@@ -524,7 +524,7 @@ static int qedi_init_id_tbl(struct qedi_portid_tbl *id_tbl, u16 size,
 	id_tbl->max = size;
 	id_tbl->next = next;
 	spin_lock_init(&id_tbl->lock);
-	id_tbl->table = kcalloc(DIV_ROUND_UP(size, 32), 4, GFP_KERNEL);
+	id_tbl->table = kcalloc(BITS_TO_LONGS(size), sizeof(long), GFP_KERNEL);
 	if (!id_tbl->table)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 68c3f904ed4591797ccac22148b95c54af391f30 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 28 Jun 2018 08:31:28 -0700
Subject: scsi: sd_zbc: Remove an assignment from sd_zbc_setup_report_cmnd()

Since nr_bytes == blk_rq_bytes(rq) == rq->__data_len, the
rq->__data_len = nr_bytes assignment does not modify the value of
rq->__data_len. Hence remove that assignment. Note: the code in
sd_done() that sets the residual to zero for zone report requests
is not affected by this patch.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sd_zbc.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c
index a14fef11776e..160b79619d30 100644
--- a/drivers/scsi/sd_zbc.c
+++ b/drivers/scsi/sd_zbc.c
@@ -148,12 +148,6 @@ int sd_zbc_setup_report_cmnd(struct scsi_cmnd *cmd)
 	cmd->transfersize = sdkp->device->sector_size;
 	cmd->allowed = 0;
 
-	/*
-	 * Report may return less bytes than requested. Make sure
-	 * to report completion on the entire initial request.
-	 */
-	rq->__data_len = nr_bytes;
-
 	return BLKPREP_OK;
 }
 
-- 
cgit v1.2.3


From 624fa7790f80575a4ec28fbdb2034097dc18d051 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:54:49 -0700
Subject: scsi: klist: Make it safe to use klists in atomic context

In the scsi_transport_srp implementation it cannot be avoided to
iterate over a klist from atomic context when using the legacy block
layer instead of blk-mq. Hence this patch that makes it safe to use
klists in atomic context. This patch avoids that lockdep reports the
following:

WARNING: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected
 Possible interrupt unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&(&k->k_lock)->rlock);
                               local_irq_disable();
                               lock(&(&q->__queue_lock)->rlock);
                               lock(&(&k->k_lock)->rlock);
  <Interrupt>
    lock(&(&q->__queue_lock)->rlock);

stack backtrace:
Workqueue: kblockd blk_timeout_work
Call Trace:
 dump_stack+0xa4/0xf5
 check_usage+0x6e6/0x700
 __lock_acquire+0x185d/0x1b50
 lock_acquire+0xd2/0x260
 _raw_spin_lock+0x32/0x50
 klist_next+0x47/0x190
 device_for_each_child+0x8e/0x100
 srp_timed_out+0xaf/0x1d0 [scsi_transport_srp]
 scsi_times_out+0xd4/0x410 [scsi_mod]
 blk_rq_timed_out+0x36/0x70
 blk_timeout_work+0x1b5/0x220
 process_one_work+0x4fe/0xad0
 worker_thread+0x63/0x5a0
 kthread+0x1c1/0x1e0
 ret_from_fork+0x24/0x30

See also commit c9ddf73476ff ("scsi: scsi_transport_srp: Fix shost to
rport translation").

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: James Bottomley <jejb@linux.vnet.ibm.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 lib/klist.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/lib/klist.c b/lib/klist.c
index 0507fa5d84c5..f6b547812fe3 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -336,8 +336,9 @@ struct klist_node *klist_prev(struct klist_iter *i)
 	void (*put)(struct klist_node *) = i->i_klist->put;
 	struct klist_node *last = i->i_cur;
 	struct klist_node *prev;
+	unsigned long flags;
 
-	spin_lock(&i->i_klist->k_lock);
+	spin_lock_irqsave(&i->i_klist->k_lock, flags);
 
 	if (last) {
 		prev = to_klist_node(last->n_node.prev);
@@ -356,7 +357,7 @@ struct klist_node *klist_prev(struct klist_iter *i)
 		prev = to_klist_node(prev->n_node.prev);
 	}
 
-	spin_unlock(&i->i_klist->k_lock);
+	spin_unlock_irqrestore(&i->i_klist->k_lock, flags);
 
 	if (put && last)
 		put(last);
@@ -377,8 +378,9 @@ struct klist_node *klist_next(struct klist_iter *i)
 	void (*put)(struct klist_node *) = i->i_klist->put;
 	struct klist_node *last = i->i_cur;
 	struct klist_node *next;
+	unsigned long flags;
 
-	spin_lock(&i->i_klist->k_lock);
+	spin_lock_irqsave(&i->i_klist->k_lock, flags);
 
 	if (last) {
 		next = to_klist_node(last->n_node.next);
@@ -397,7 +399,7 @@ struct klist_node *klist_next(struct klist_iter *i)
 		next = to_klist_node(next->n_node.next);
 	}
 
-	spin_unlock(&i->i_klist->k_lock);
+	spin_unlock_irqrestore(&i->i_klist->k_lock, flags);
 
 	if (put && last)
 		put(last);
-- 
cgit v1.2.3


From 265d59aacbce7e50bdc1f5d25033c38dd70b3767 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sat, 30 Jun 2018 09:27:24 +0800
Subject: scsi: core: fix scsi_host_queue_ready

328728630d9f ("scsi: avoid to hold host-wide counter of host_busy for
scsi_mq") adds one extra check on scsi_host_busy(shost) in
scsi_host_queue_ready(), which is wrong and not necessary, can causes
booting stall on LSI53c895A.

So remove the check.

Cc: Omar Sandoval <osandov@fb.com>,
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>,
Cc: James Bottomley <james.bottomley@hansenpartnership.com>,
Cc: Christoph Hellwig <hch@lst.de>,
Cc: Don Brace <don.brace@microsemi.com>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Mike Snitzer <snitzer@redhat.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Guenter Roeck <linux@roeck-us.net>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Fixes: 328728630d9f ("scsi: avoid to hold host-wide counter of host_busy for scsi_mq")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 600c78065d62..93cf2ec2d13b 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1611,7 +1611,7 @@ static inline int scsi_host_queue_ready(struct request_queue *q,
 	else
 		busy = 0;
 	if (atomic_read(&shost->host_blocked) > 0) {
-		if (busy || scsi_host_busy(shost))
+		if (busy)
 			goto starved;
 
 		/*
-- 
cgit v1.2.3


From 6f3bf5a2fa4a53c8dbb5b7b3d3d93bf85acaa2eb Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:48 -0700
Subject: scsi: target: Use config_item_name() instead of open-coding it

Some target code uses config_item_name() while other code accesses .ci_name
directly. Make the target code consistent by switching to
config_item_name().

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_configfs.c | 4 ++--
 drivers/target/target_core_sbc.c      | 7 ++++---
 2 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 5ccef7d597fa..93d3ff34b614 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -263,8 +263,8 @@ static struct config_group *target_core_register_fabric(
 			&tf->tf_discovery_cit);
 	configfs_add_default_group(&tf->tf_disc_group, &tf->tf_group);
 
-	pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric:"
-			" %s\n", tf->tf_group.cg_item.ci_name);
+	pr_debug("Target_Core_ConfigFS: REGISTER -> Allocated Fabric: %s\n",
+		 config_item_name(&tf->tf_group.cg_item));
 	return &tf->tf_group;
 }
 
diff --git a/drivers/target/target_core_sbc.c b/drivers/target/target_core_sbc.c
index b054682e974f..ebac2b49b9c6 100644
--- a/drivers/target/target_core_sbc.c
+++ b/drivers/target/target_core_sbc.c
@@ -978,9 +978,10 @@ sbc_parse_cdb(struct se_cmd *cmd, struct sbc_ops *ops)
 	}
 	case COMPARE_AND_WRITE:
 		if (!dev->dev_attrib.emulate_caw) {
-			pr_err_ratelimited("se_device %s/%s (vpd_unit_serial %s) reject"
-				" COMPARE_AND_WRITE\n", dev->se_hba->backend->ops->name,
-				dev->dev_group.cg_item.ci_name, dev->t10_wwn.unit_serial);
+			pr_err_ratelimited("se_device %s/%s (vpd_unit_serial %s) reject COMPARE_AND_WRITE\n",
+					   dev->se_hba->backend->ops->name,
+					   config_item_name(&dev->dev_group.cg_item),
+					   dev->t10_wwn.unit_serial);
 			return TCM_UNSUPPORTED_SCSI_OPCODE;
 		}
 		sectors = cdb[13];
-- 
cgit v1.2.3


From 36d4cb460bcbe2a1323732a6e4bb9dd783284368 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 28 Jun 2018 13:48:57 -0500
Subject: scsi: target: Avoid that EXTENDED COPY commands trigger lock
 inversion

The approach for adding a device to the devices_idr data structure and for
removing it is as follows:

* &dev->dev_group.cg_item is initialized before a device is added to
  devices_idr.

* If the reference count of a device drops to zero then
  target_free_device() removes the device from devices_idr.

* All devices_idr manipulations are protected by device_mutex.

This means that increasing the reference count of a device is sufficient to
prevent removal from devices_idr and also that it is safe access
dev_group.cg_item for any device that is referenced by devices_idr. Use
this to modify target_find_device() and target_for_each_device() such that
these functions no longer introduce a dependency between device_mutex and
the configfs root inode mutex.

Note: it is safe to pass a NULL pointer to config_item_put() and also to
config_item_get_unless_zero().

This patch prevents that lockdep reports the following complaint:

======================================================
WARNING: possible circular locking dependency detected
4.12.0-rc1-dbg+ #1 Not tainted
------------------------------------------------------
rmdir/12053 is trying to acquire lock:
 (device_mutex#2){+.+.+.}, at: [<ffffffffa010afce>]
target_free_device+0xae/0xf0 [target_core_mod]

but task is already holding lock:
 (&sb->s_type->i_mutex_key#14){++++++}, at: [<ffffffff811c5c30>]
vfs_rmdir+0x50/0x140

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&sb->s_type->i_mutex_key#14){++++++}:
       lock_acquire+0x59/0x80
       down_write+0x36/0x70
       configfs_depend_item+0x3a/0xb0 [configfs]
       target_depend_item+0x13/0x20 [target_core_mod]
       target_xcopy_locate_se_dev_e4_iter+0x87/0x100 [target_core_mod]
       target_devices_idr_iter+0x16/0x20 [target_core_mod]
       idr_for_each+0x39/0xc0
       target_for_each_device+0x36/0x50 [target_core_mod]
       target_xcopy_locate_se_dev_e4+0x28/0x80 [target_core_mod]
       target_xcopy_do_work+0x2e9/0xdd0 [target_core_mod]
       process_one_work+0x1ca/0x3f0
       worker_thread+0x49/0x3b0
       kthread+0x109/0x140
       ret_from_fork+0x31/0x40

-> #0 (device_mutex#2){+.+.+.}:
       __lock_acquire+0x101f/0x11d0
       lock_acquire+0x59/0x80
       __mutex_lock+0x7e/0x950
       mutex_lock_nested+0x16/0x20
       target_free_device+0xae/0xf0 [target_core_mod]
       target_core_dev_release+0x10/0x20 [target_core_mod]
       config_item_put+0x6e/0xb0 [configfs]
       configfs_rmdir+0x1a6/0x300 [configfs]
       vfs_rmdir+0xb7/0x140
       do_rmdir+0x1f4/0x200
       SyS_rmdir+0x11/0x20
       entry_SYSCALL_64_fastpath+0x23/0xc2

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&sb->s_type->i_mutex_key#14);
                               lock(device_mutex#2);
                               lock(&sb->s_type->i_mutex_key#14);
  lock(device_mutex#2);

 *** DEADLOCK ***

3 locks held by rmdir/12053:
 #0:  (sb_writers#10){.+.+.+}, at: [<ffffffff811e223f>]
mnt_want_write+0x1f/0x50
 #1:  (&sb->s_type->i_mutex_key#14/1){+.+.+.}, at: [<ffffffff811cb97e>]
do_rmdir+0x15e/0x200
 #2:  (&sb->s_type->i_mutex_key#14){++++++}, at: [<ffffffff811c5c30>]
vfs_rmdir+0x50/0x140

stack backtrace:
CPU: 3 PID: 12053 Comm: rmdir Not tainted 4.12.0-rc1-dbg+ #1
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.0.0-prebuilt.qemu-project.org 04/01/2014
Call Trace:
 dump_stack+0x86/0xcf
 print_circular_bug+0x1c7/0x220
 __lock_acquire+0x101f/0x11d0
 lock_acquire+0x59/0x80
 __mutex_lock+0x7e/0x950
 mutex_lock_nested+0x16/0x20
 target_free_device+0xae/0xf0 [target_core_mod]
 target_core_dev_release+0x10/0x20 [target_core_mod]
 config_item_put+0x6e/0xb0 [configfs]
 configfs_rmdir+0x1a6/0x300 [configfs]
 vfs_rmdir+0xb7/0x140
 do_rmdir+0x1f4/0x200
 SyS_rmdir+0x11/0x20
 entry_SYSCALL_64_fastpath+0x23/0xc2

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
[Rebased to handle conflict withe target_find_device removal]
Signed-off-by: Mike Christie <mchristi@redhat.com>

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_device.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index a9ad6ecb1812..e5c90afb40e6 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -880,14 +880,20 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb)
 EXPORT_SYMBOL(target_to_linux_sector);
 
 struct devices_idr_iter {
+	struct config_item *prev_item;
 	int (*fn)(struct se_device *dev, void *data);
 	void *data;
 };
 
 static int target_devices_idr_iter(int id, void *p, void *data)
+	 __must_hold(&device_mutex)
 {
 	struct devices_idr_iter *iter = data;
 	struct se_device *dev = p;
+	int ret;
+
+	config_item_put(iter->prev_item);
+	iter->prev_item = NULL;
 
 	/*
 	 * We add the device early to the idr, so it can be used
@@ -898,7 +904,15 @@ static int target_devices_idr_iter(int id, void *p, void *data)
 	if (!(dev->dev_flags & DF_CONFIGURED))
 		return 0;
 
-	return iter->fn(dev, iter->data);
+	iter->prev_item = config_item_get_unless_zero(&dev->dev_group.cg_item);
+	if (!iter->prev_item)
+		return 0;
+	mutex_unlock(&device_mutex);
+
+	ret = iter->fn(dev, iter->data);
+
+	mutex_lock(&device_mutex);
+	return ret;
 }
 
 /**
@@ -912,15 +926,13 @@ static int target_devices_idr_iter(int id, void *p, void *data)
 int target_for_each_device(int (*fn)(struct se_device *dev, void *data),
 			   void *data)
 {
-	struct devices_idr_iter iter;
+	struct devices_idr_iter iter = { .fn = fn, .data = data };
 	int ret;
 
-	iter.fn = fn;
-	iter.data = data;
-
 	mutex_lock(&device_mutex);
 	ret = idr_for_each(&devices_idr, target_devices_idr_iter, &iter);
 	mutex_unlock(&device_mutex);
+	config_item_put(iter.prev_item);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 3eeff1984051e45448765e49b712c6bfee1de378 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:50 -0700
Subject: scsi: target: Move a list_del_init() statement

This patch does not change any functionality but makes the next patch
easier to read.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 89dd475d0a8f..5e8329c5ddd0 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2697,6 +2697,7 @@ static void target_release_cmd_kref(struct kref *kref)
 
 	if (se_sess) {
 		spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
+		list_del_init(&se_cmd->se_cmd_list);
 
 		spin_lock(&se_cmd->t_state_lock);
 		fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) &&
@@ -2704,13 +2705,11 @@ static void target_release_cmd_kref(struct kref *kref)
 		spin_unlock(&se_cmd->t_state_lock);
 
 		if (se_cmd->cmd_wait_set || fabric_stop) {
-			list_del_init(&se_cmd->se_cmd_list);
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 			target_free_cmd_mem(se_cmd);
 			complete(&se_cmd->cmd_wait_comp);
 			return;
 		}
-		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 	}
 
-- 
cgit v1.2.3


From 317f89712d7aa4acc2d93df27b753d4489826cc5 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:51 -0700
Subject: scsi: target: Rename transport_init_session() into
 transport_alloc_session()

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/iscsi/iscsi_target_login.c |  2 +-
 drivers/target/target_core_transport.c    | 26 ++++++++++++++++++++++----
 include/target/target_core_fabric.h       |  2 +-
 3 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 99501785cdc1..923b1a9fc3dc 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -369,7 +369,7 @@ static int iscsi_login_zero_tsih_s1(
 		return -ENOMEM;
 	}
 
-	sess->se_sess = transport_init_session(TARGET_PROT_NORMAL);
+	sess->se_sess = transport_alloc_session(TARGET_PROT_NORMAL);
 	if (IS_ERR(sess->se_sess)) {
 		iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
 				ISCSI_LOGIN_STATUS_NO_RESOURCES);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 5e8329c5ddd0..880e07f40099 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -224,7 +224,11 @@ void transport_subsystem_check_init(void)
 	sub_api_initialized = 1;
 }
 
-struct se_session *transport_init_session(enum target_prot_op sup_prot_ops)
+/**
+ * transport_alloc_session - allocate a session object and initialize it
+ * @sup_prot_ops: bitmask that defines which T10-PI modes are supported.
+ */
+struct se_session *transport_alloc_session(enum target_prot_op sup_prot_ops)
 {
 	struct se_session *se_sess;
 
@@ -243,8 +247,15 @@ struct se_session *transport_init_session(enum target_prot_op sup_prot_ops)
 
 	return se_sess;
 }
-EXPORT_SYMBOL(transport_init_session);
+EXPORT_SYMBOL(transport_alloc_session);
 
+/**
+ * transport_alloc_session_tags - allocate target driver private data
+ * @se_sess:  Session pointer.
+ * @tag_num:  Maximum number of in-flight commands between initiator and target.
+ * @tag_size: Size in bytes of the private data a target driver associates with
+ *	      each command.
+ */
 int transport_alloc_session_tags(struct se_session *se_sess,
 			         unsigned int tag_num, unsigned int tag_size)
 {
@@ -274,6 +285,13 @@ int transport_alloc_session_tags(struct se_session *se_sess,
 }
 EXPORT_SYMBOL(transport_alloc_session_tags);
 
+/**
+ * transport_init_session_tags - allocate a session and target driver private data
+ * @tag_num:  Maximum number of in-flight commands between initiator and target.
+ * @tag_size: Size in bytes of the private data a target driver associates with
+ *	      each command.
+ * @sup_prot_ops: bitmask that defines which T10-PI modes are supported.
+ */
 struct se_session *transport_init_session_tags(unsigned int tag_num,
 					       unsigned int tag_size,
 					       enum target_prot_op sup_prot_ops)
@@ -292,7 +310,7 @@ struct se_session *transport_init_session_tags(unsigned int tag_num,
 		return ERR_PTR(-EINVAL);
 	}
 
-	se_sess = transport_init_session(sup_prot_ops);
+	se_sess = transport_alloc_session(sup_prot_ops);
 	if (IS_ERR(se_sess))
 		return se_sess;
 
@@ -402,7 +420,7 @@ target_alloc_session(struct se_portal_group *tpg,
 	if (tag_num != 0)
 		sess = transport_init_session_tags(tag_num, tag_size, prot_op);
 	else
-		sess = transport_init_session(prot_op);
+		sess = transport_alloc_session(prot_op);
 
 	if (IS_ERR(sess))
 		return sess;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index b297aa0d9651..010df9d5b977 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -115,7 +115,7 @@ struct se_session *target_alloc_session(struct se_portal_group *,
 		int (*callback)(struct se_portal_group *,
 				struct se_session *, void *));
 
-struct se_session *transport_init_session(enum target_prot_op);
+struct se_session *transport_alloc_session(enum target_prot_op);
 int transport_alloc_session_tags(struct se_session *, unsigned int,
 		unsigned int);
 struct se_session *transport_init_session_tags(unsigned int, unsigned int,
-- 
cgit v1.2.3


From d1bff07f387c05cfaba1ea505fc2ee5eac6b2c21 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:52 -0700
Subject: scsi: target: Introduce transport_init_session()

Other than initializing xcopy_pt_sess.sess_wait_list, this patch does not
change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 22 +++++++++++++++++-----
 drivers/target/target_core_xcopy.c     |  5 +----
 include/target/target_core_fabric.h    |  1 +
 3 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 880e07f40099..595b2f12ca6a 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -224,6 +224,22 @@ void transport_subsystem_check_init(void)
 	sub_api_initialized = 1;
 }
 
+/**
+ * transport_init_session - initialize a session object
+ * @se_sess: Session object pointer.
+ *
+ * The caller must have zero-initialized @se_sess before calling this function.
+ */
+void transport_init_session(struct se_session *se_sess)
+{
+	INIT_LIST_HEAD(&se_sess->sess_list);
+	INIT_LIST_HEAD(&se_sess->sess_acl_list);
+	INIT_LIST_HEAD(&se_sess->sess_cmd_list);
+	INIT_LIST_HEAD(&se_sess->sess_wait_list);
+	spin_lock_init(&se_sess->sess_cmd_lock);
+}
+EXPORT_SYMBOL(transport_init_session);
+
 /**
  * transport_alloc_session - allocate a session object and initialize it
  * @sup_prot_ops: bitmask that defines which T10-PI modes are supported.
@@ -238,11 +254,7 @@ struct se_session *transport_alloc_session(enum target_prot_op sup_prot_ops)
 				" se_sess_cache\n");
 		return ERR_PTR(-ENOMEM);
 	}
-	INIT_LIST_HEAD(&se_sess->sess_list);
-	INIT_LIST_HEAD(&se_sess->sess_acl_list);
-	INIT_LIST_HEAD(&se_sess->sess_cmd_list);
-	INIT_LIST_HEAD(&se_sess->sess_wait_list);
-	spin_lock_init(&se_sess->sess_cmd_lock);
+	transport_init_session(se_sess);
 	se_sess->sup_prot_ops = sup_prot_ops;
 
 	return se_sess;
diff --git a/drivers/target/target_core_xcopy.c b/drivers/target/target_core_xcopy.c
index 9ee89e00cd77..2718a933c0c6 100644
--- a/drivers/target/target_core_xcopy.c
+++ b/drivers/target/target_core_xcopy.c
@@ -497,10 +497,7 @@ int target_xcopy_setup_pt(void)
 	INIT_LIST_HEAD(&xcopy_pt_nacl.acl_list);
 	INIT_LIST_HEAD(&xcopy_pt_nacl.acl_sess_list);
 	memset(&xcopy_pt_sess, 0, sizeof(struct se_session));
-	INIT_LIST_HEAD(&xcopy_pt_sess.sess_list);
-	INIT_LIST_HEAD(&xcopy_pt_sess.sess_acl_list);
-	INIT_LIST_HEAD(&xcopy_pt_sess.sess_cmd_list);
-	spin_lock_init(&xcopy_pt_sess.sess_cmd_lock);
+	transport_init_session(&xcopy_pt_sess);
 
 	xcopy_pt_nacl.se_tpg = &xcopy_pt_tpg;
 	xcopy_pt_nacl.nacl_sess = &xcopy_pt_sess;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 010df9d5b977..84a681b6e5ca 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -115,6 +115,7 @@ struct se_session *target_alloc_session(struct se_portal_group *,
 		int (*callback)(struct se_portal_group *,
 				struct se_session *, void *));
 
+void transport_init_session(struct se_session *);
 struct se_session *transport_alloc_session(enum target_prot_op);
 int transport_alloc_session_tags(struct se_session *, unsigned int,
 		unsigned int);
-- 
cgit v1.2.3


From 00d909a10710a3416272d4179adf3837b9a9f3c2 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:53 -0700
Subject: scsi: target: Make the session shutdown code also wait for commands
 that are being aborted

Target drivers must call target_sess_cmd_list_set_waiting() and
target_wait_for_sess_cmds() before freeing a session. Since freeing a
session is only safe after all commands that are associated with a session
have finished, make target_wait_for_sess_cmds() also wait for commands that
are being aborted. Instead of setting a flag in each pending command from
target_sess_cmd_list_set_waiting() and waiting in
target_wait_for_sess_cmds() on a per-command completion, only set a
per-session flag in the former function and wait on a per-session
completion in the latter function. This change is safe because once a SCSI
initiator system has submitted a command a target system is always allowed
to execute it to completion. See also commit 0f4a943168f3 ("target: Fix
remote-port TMR ABORT + se_cmd fabric stop").

This patch is based on the following two patches:

* Bart Van Assche, target: Simplify session shutdown code, February 19, 2015
  (https://github.com/bvanassche/linux/commit/8df5463d7d7619f2f1b70cfe5172eaef0aa52815).

* Christoph Hellwig, target: Rework session shutdown code, December 7, 2015
  (http://thread.gmane.org/gmane.linux.scsi.target.devel/10695).

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_tmr.c       |  5 +--
 drivers/target/target_core_transport.c | 77 ++++++++++------------------------
 include/target/target_core_base.h      |  3 +-
 3 files changed, 24 insertions(+), 61 deletions(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 9c7bc1ca341a..da8125dd3a4c 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -142,7 +142,7 @@ static bool __target_check_io_state(struct se_cmd *se_cmd,
 			return false;
 		}
 	}
-	if (sess->sess_tearing_down || se_cmd->cmd_wait_set) {
+	if (sess->sess_tearing_down) {
 		pr_debug("Attempted to abort io tag: %llu already shutdown,"
 			" skipping\n", se_cmd->tag);
 		spin_unlock(&se_cmd->t_state_lock);
@@ -187,7 +187,6 @@ void core_tmr_abort_task(
 		if (!__target_check_io_state(se_cmd, se_sess, 0))
 			continue;
 
-		list_del_init(&se_cmd->se_cmd_list);
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 
 		cancel_work_sync(&se_cmd->work);
@@ -259,7 +258,7 @@ static void core_tmr_drain_tmr_list(
 			spin_unlock(&sess->sess_cmd_lock);
 			continue;
 		}
-		if (sess->sess_tearing_down || cmd->cmd_wait_set) {
+		if (sess->sess_tearing_down) {
 			spin_unlock(&cmd->t_state_lock);
 			spin_unlock(&sess->sess_cmd_lock);
 			continue;
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 595b2f12ca6a..087dddfc5c35 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -235,8 +235,8 @@ void transport_init_session(struct se_session *se_sess)
 	INIT_LIST_HEAD(&se_sess->sess_list);
 	INIT_LIST_HEAD(&se_sess->sess_acl_list);
 	INIT_LIST_HEAD(&se_sess->sess_cmd_list);
-	INIT_LIST_HEAD(&se_sess->sess_wait_list);
 	spin_lock_init(&se_sess->sess_cmd_lock);
+	init_waitqueue_head(&se_sess->cmd_list_wq);
 }
 EXPORT_SYMBOL(transport_init_session);
 
@@ -2728,13 +2728,15 @@ static void target_release_cmd_kref(struct kref *kref)
 	if (se_sess) {
 		spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 		list_del_init(&se_cmd->se_cmd_list);
+		if (list_empty(&se_sess->sess_cmd_list))
+			wake_up(&se_sess->cmd_list_wq);
 
 		spin_lock(&se_cmd->t_state_lock);
 		fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) &&
 			      (se_cmd->transport_state & CMD_T_ABORTED);
 		spin_unlock(&se_cmd->t_state_lock);
 
-		if (se_cmd->cmd_wait_set || fabric_stop) {
+		if (fabric_stop) {
 			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 			target_free_cmd_mem(se_cmd);
 			complete(&se_cmd->cmd_wait_comp);
@@ -2863,78 +2865,41 @@ void target_show_cmd(const char *pfx, struct se_cmd *cmd)
 EXPORT_SYMBOL(target_show_cmd);
 
 /**
- * target_sess_cmd_list_set_waiting - Flag all commands in
- *         sess_cmd_list to complete cmd_wait_comp.  Set
- *         sess_tearing_down so no more commands are queued.
+ * target_sess_cmd_list_set_waiting - Set sess_tearing_down so no new commands are queued.
  * @se_sess:	session to flag
  */
 void target_sess_cmd_list_set_waiting(struct se_session *se_sess)
 {
-	struct se_cmd *se_cmd, *tmp_cmd;
 	unsigned long flags;
-	int rc;
 
 	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
-	if (se_sess->sess_tearing_down) {
-		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-		return;
-	}
 	se_sess->sess_tearing_down = 1;
-	list_splice_init(&se_sess->sess_cmd_list, &se_sess->sess_wait_list);
-
-	list_for_each_entry_safe(se_cmd, tmp_cmd,
-				 &se_sess->sess_wait_list, se_cmd_list) {
-		rc = kref_get_unless_zero(&se_cmd->cmd_kref);
-		if (rc) {
-			se_cmd->cmd_wait_set = 1;
-			spin_lock(&se_cmd->t_state_lock);
-			se_cmd->transport_state |= CMD_T_FABRIC_STOP;
-			spin_unlock(&se_cmd->t_state_lock);
-		} else
-			list_del_init(&se_cmd->se_cmd_list);
-	}
-
 	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 }
 EXPORT_SYMBOL(target_sess_cmd_list_set_waiting);
 
 /**
- * target_wait_for_sess_cmds - Wait for outstanding descriptors
+ * target_wait_for_sess_cmds - Wait for outstanding commands
  * @se_sess:    session to wait for active I/O
  */
 void target_wait_for_sess_cmds(struct se_session *se_sess)
 {
-	struct se_cmd *se_cmd, *tmp_cmd;
-	unsigned long flags;
-	bool tas;
-
-	list_for_each_entry_safe(se_cmd, tmp_cmd,
-				&se_sess->sess_wait_list, se_cmd_list) {
-		pr_debug("Waiting for se_cmd: %p t_state: %d, fabric state:"
-			" %d\n", se_cmd, se_cmd->t_state,
-			se_cmd->se_tfo->get_cmd_state(se_cmd));
-
-		spin_lock_irqsave(&se_cmd->t_state_lock, flags);
-		tas = (se_cmd->transport_state & CMD_T_TAS);
-		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
-
-		if (!target_put_sess_cmd(se_cmd)) {
-			if (tas)
-				target_put_sess_cmd(se_cmd);
-		}
-
-		wait_for_completion(&se_cmd->cmd_wait_comp);
-		pr_debug("After cmd_wait_comp: se_cmd: %p t_state: %d"
-			" fabric state: %d\n", se_cmd, se_cmd->t_state,
-			se_cmd->se_tfo->get_cmd_state(se_cmd));
-
-		se_cmd->se_tfo->release_cmd(se_cmd);
-	}
-
-	spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
-	WARN_ON(!list_empty(&se_sess->sess_cmd_list));
-	spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
+	struct se_cmd *cmd;
+	int ret;
 
+	WARN_ON_ONCE(!se_sess->sess_tearing_down);
+
+	spin_lock_irq(&se_sess->sess_cmd_lock);
+	do {
+		ret = wait_event_interruptible_lock_irq_timeout(
+				se_sess->cmd_list_wq,
+				list_empty(&se_sess->sess_cmd_list),
+				se_sess->sess_cmd_lock, 180 * HZ);
+		list_for_each_entry(cmd, &se_sess->sess_cmd_list, se_cmd_list)
+			target_show_cmd("session shutdown: still waiting for ",
+					cmd);
+	} while (ret <= 0);
+	spin_unlock_irq(&se_sess->sess_cmd_lock);
 }
 EXPORT_SYMBOL(target_wait_for_sess_cmds);
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 448f291125c2..906c1fc485e4 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -443,7 +443,6 @@ struct se_cmd {
 	u8			scsi_asc;
 	u8			scsi_ascq;
 	u16			scsi_sense_length;
-	unsigned		cmd_wait_set:1;
 	unsigned		unknown_data_length:1;
 	bool			state_active:1;
 	u64			tag; /* SAM command identifier aka task tag */
@@ -606,8 +605,8 @@ struct se_session {
 	struct list_head	sess_list;
 	struct list_head	sess_acl_list;
 	struct list_head	sess_cmd_list;
-	struct list_head	sess_wait_list;
 	spinlock_t		sess_cmd_lock;
+	wait_queue_head_t	cmd_list_wq;
 	void			*sess_cmd_map;
 	struct sbitmap_queue	sess_tag_pool;
 };
-- 
cgit v1.2.3


From 953bcf7ad16ac6ecee7d2f5593501aee5e5ae8b8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:54 -0700
Subject: scsi: target: Document when CMD_T_STOP and CMD_T_COMPLETE are set

Document those aspects of transport_cmd_check_stop_to_fabric() and
transport_generic_free_cmd() of which it is nontrivial to derive these from
their implementation.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 34 ++++++++++++++++++++++++++++------
 1 file changed, 28 insertions(+), 6 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 087dddfc5c35..47318f64296d 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -632,6 +632,13 @@ static void target_remove_from_state_list(struct se_cmd *cmd)
 	spin_unlock_irqrestore(&dev->execute_task_lock, flags);
 }
 
+/*
+ * This function is called by the target core after the target core has
+ * finished processing a SCSI command or SCSI TMF. Both the regular command
+ * processing code and the code for aborting commands can call this
+ * function. CMD_T_STOP is set if and only if another thread is waiting
+ * inside transport_wait_for_tasks() for t_transport_stop_comp.
+ */
 static int transport_cmd_check_stop_to_fabric(struct se_cmd *cmd)
 {
 	unsigned long flags;
@@ -2624,6 +2631,27 @@ static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas)
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 }
 
+/*
+ * This function is called by frontend drivers after processing of a command
+ * has finished.
+ *
+ * The protocol for ensuring that either the regular flow or the TMF
+ * code drops one reference is as follows:
+ * - Calling .queue_data_in(), .queue_status() or queue_tm_rsp() will cause
+ *   the frontend driver to drop one reference, synchronously or asynchronously.
+ * - During regular command processing the target core sets CMD_T_COMPLETE
+ *   before invoking one of the .queue_*() functions.
+ * - The code that aborts commands skips commands and TMFs for which
+ *   CMD_T_COMPLETE has been set.
+ * - CMD_T_ABORTED is set atomically after the CMD_T_COMPLETE check for
+ *   commands that will be aborted.
+ * - If the CMD_T_ABORTED flag is set but CMD_T_TAS has not been set
+ *   transport_generic_free_cmd() skips its call to target_put_sess_cmd().
+ * - For aborted commands for which CMD_T_TAS has been set .queue_status() will
+ *   be called and will drop a reference.
+ * - For aborted commands for which CMD_T_TAS has not been set .aborted_task()
+ *   will be called. transport_cmd_finish_abort() will drop the final reference.
+ */
 int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 {
 	int ret = 0;
@@ -2652,12 +2680,6 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 		if (!aborted || tas)
 			ret = target_put_sess_cmd(cmd);
 	}
-	/*
-	 * If the task has been internally aborted due to TMR ABORT_TASK
-	 * or LUN_RESET, target_core_tmr.c is responsible for performing
-	 * the remaining calls to target_put_sess_cmd(), and not the
-	 * callers of this function.
-	 */
 	if (aborted) {
 		pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
 		wait_for_completion(&cmd->cmd_wait_comp);
-- 
cgit v1.2.3


From 709d56512fe8ed6d5092a1d43a4343d23df2b31c Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:55 -0700
Subject: scsi: target: Simplify core_tmr_handle_tas_abort()

The code that can set CMD_T_TAS is executed by the same thread as the
thread that executes core_tmr_handle_tas_abort(). That means that no
locking is needed to check CMD_T_TAS from inside
core_tmr_handle_tas_abort(). This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_tmr.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index da8125dd3a4c..08af053e7990 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -77,21 +77,12 @@ void core_tmr_release_req(struct se_tmr_req *tmr)
 
 static int core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
 {
-	unsigned long flags;
-	bool remove = true, send_tas;
-	/*
-	 * TASK ABORTED status (TAS) bit support
-	 */
-	spin_lock_irqsave(&cmd->t_state_lock, flags);
-	send_tas = (cmd->transport_state & CMD_T_TAS);
-	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
+	bool send_tas = cmd->transport_state & CMD_T_TAS;
 
-	if (send_tas) {
-		remove = false;
+	if (send_tas)
 		transport_send_task_abort(cmd);
-	}
 
-	return transport_cmd_finish_abort(cmd, remove);
+	return transport_cmd_finish_abort(cmd, !send_tas);
 }
 
 static int target_check_cdb_and_preempt(struct list_head *list,
-- 
cgit v1.2.3


From 65422d705f1abf65897464b4e9c51ec3e1376ec4 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:56 -0700
Subject: scsi: target: Fold core_tmr_handle_tas_abort() into
 transport_cmd_finish_abort()

For the two calls to transport_cmd_finish_abort() outside
core_tmr_handle_tas_abort() it is guaranteed that CMD_T_TAS is not set. Use
this property to fold core_tmr_handle_tas_abort() into
transport_cmd_finish_abort(). This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_internal.h  |  2 +-
 drivers/target/target_core_tmr.c       | 16 +++-------------
 drivers/target/target_core_transport.c | 10 +++++++---
 3 files changed, 11 insertions(+), 17 deletions(-)

diff --git a/drivers/target/target_core_internal.h b/drivers/target/target_core_internal.h
index dead30b1d32c..0c6635587930 100644
--- a/drivers/target/target_core_internal.h
+++ b/drivers/target/target_core_internal.h
@@ -138,7 +138,7 @@ int	init_se_kmem_caches(void);
 void	release_se_kmem_caches(void);
 u32	scsi_get_new_index(scsi_index_t);
 void	transport_subsystem_check_init(void);
-int	transport_cmd_finish_abort(struct se_cmd *, int);
+int	transport_cmd_finish_abort(struct se_cmd *);
 unsigned char *transport_dump_cmd_direction(struct se_cmd *);
 void	transport_dump_dev_state(struct se_device *, char *, int *);
 void	transport_dump_dev_info(struct se_device *, struct se_lun *,
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 08af053e7990..6d1179a7f043 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -75,16 +75,6 @@ void core_tmr_release_req(struct se_tmr_req *tmr)
 	kfree(tmr);
 }
 
-static int core_tmr_handle_tas_abort(struct se_cmd *cmd, int tas)
-{
-	bool send_tas = cmd->transport_state & CMD_T_TAS;
-
-	if (send_tas)
-		transport_send_task_abort(cmd);
-
-	return transport_cmd_finish_abort(cmd, !send_tas);
-}
-
 static int target_check_cdb_and_preempt(struct list_head *list,
 		struct se_cmd *cmd)
 {
@@ -183,7 +173,7 @@ void core_tmr_abort_task(
 		cancel_work_sync(&se_cmd->work);
 		transport_wait_for_tasks(se_cmd);
 
-		if (!transport_cmd_finish_abort(se_cmd, true))
+		if (!transport_cmd_finish_abort(se_cmd))
 			target_put_sess_cmd(se_cmd);
 
 		printk("ABORT_TASK: Sending TMR_FUNCTION_COMPLETE for"
@@ -281,7 +271,7 @@ static void core_tmr_drain_tmr_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		if (!transport_cmd_finish_abort(cmd, 1))
+		if (!transport_cmd_finish_abort(cmd))
 			target_put_sess_cmd(cmd);
 	}
 }
@@ -370,7 +360,7 @@ static void core_tmr_drain_state_list(
 		cancel_work_sync(&cmd->work);
 		transport_wait_for_tasks(cmd);
 
-		if (!core_tmr_handle_tas_abort(cmd, tas))
+		if (!transport_cmd_finish_abort(cmd))
 			target_put_sess_cmd(cmd);
 	}
 }
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 47318f64296d..3f95ddea6b1c 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -688,23 +688,27 @@ static void transport_lun_remove_cmd(struct se_cmd *cmd)
 		percpu_ref_put(&lun->lun_ref);
 }
 
-int transport_cmd_finish_abort(struct se_cmd *cmd, int remove)
+int transport_cmd_finish_abort(struct se_cmd *cmd)
 {
+	bool send_tas = cmd->transport_state & CMD_T_TAS;
 	bool ack_kref = (cmd->se_cmd_flags & SCF_ACK_KREF);
 	int ret = 0;
 
+	if (send_tas)
+		transport_send_task_abort(cmd);
+
 	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD)
 		transport_lun_remove_cmd(cmd);
 	/*
 	 * Allow the fabric driver to unmap any resources before
 	 * releasing the descriptor via TFO->release_cmd()
 	 */
-	if (remove)
+	if (!send_tas)
 		cmd->se_tfo->aborted_task(cmd);
 
 	if (transport_cmd_check_stop_to_fabric(cmd))
 		return 1;
-	if (remove && ack_kref)
+	if (!send_tas && ack_kref)
 		ret = target_put_sess_cmd(cmd);
 
 	return ret;
-- 
cgit v1.2.3


From a8864d861d62feadc5f37c6651a7d7a2fc2477a8 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:57 -0700
Subject: scsi: target: Simplify transport_generic_free_cmd() (1/2)

Move identical code outside an if/else statement. This patch does not
change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 3f95ddea6b1c..65995532d02b 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2664,9 +2664,6 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
 		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
 			target_wait_free_cmd(cmd, &aborted, &tas);
-
-		if (!aborted || tas)
-			ret = target_put_sess_cmd(cmd);
 	} else {
 		if (wait_for_tasks)
 			target_wait_free_cmd(cmd, &aborted, &tas);
@@ -2680,10 +2677,9 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
-
-		if (!aborted || tas)
-			ret = target_put_sess_cmd(cmd);
 	}
+	if (!aborted || tas)
+		ret = target_put_sess_cmd(cmd);
 	if (aborted) {
 		pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
 		wait_for_completion(&cmd->cmd_wait_comp);
-- 
cgit v1.2.3


From edf46eee59c5acd829c3b6a564c26b5386362ea3 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:58 -0700
Subject: scsi: target: Simplify transport_generic_free_cmd() (2/2)

Since target_wait_free_cmd() skips TMFs with no associated LUN, it is safe
to call that function for such commands. Use this to simplify
transport_generic_free_cmd(). The only functional change in this patch is
that CMD_T_FABRIC_STOP gets set for TMFs with no associated LUN by
transport_generic_free_cmd().

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 65995532d02b..ebd54fc1f13a 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2661,12 +2661,10 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 	int ret = 0;
 	bool aborted = false, tas = false;
 
-	if (!(cmd->se_cmd_flags & SCF_SE_LUN_CMD)) {
-		if (wait_for_tasks && (cmd->se_cmd_flags & SCF_SCSI_TMR_CDB))
-			target_wait_free_cmd(cmd, &aborted, &tas);
-	} else {
-		if (wait_for_tasks)
-			target_wait_free_cmd(cmd, &aborted, &tas);
+	if (wait_for_tasks)
+		target_wait_free_cmd(cmd, &aborted, &tas);
+
+	if (cmd->se_cmd_flags & SCF_SE_LUN_CMD) {
 		/*
 		 * Handle WRITE failure case where transport_generic_new_cmd()
 		 * has already added se_cmd to state_list, but fabric has
-- 
cgit v1.2.3


From 7b2cc7dc0dbf5da9cf16ffcf1ca8e904ab574ff5 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:52:59 -0700
Subject: scsi: target: Simplify the code for waiting for command completion

Instead of embedding the completion that is used for waiting for command
completion in struct se_cmd, let the context that waits for command
completion allocate it. This makes it possible to have a single code path
for non-aborted and aborted commands in target_release_cmd_kref() and
avoids that transport_generic_free_cmd() has to call
cmd->se_tfo->release_cmd() directly. This patch does not change any
functionality. Note: transport_generic_free_cmd() only waits until the
se_cmd reference count has reached zero after it has set both
CMD_T_FABRIC_STOP and CMD_T_ABORTED.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 24 ++++++++----------------
 include/target/target_core_base.h      |  2 +-
 2 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index ebd54fc1f13a..cb48dbc2c9ba 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -1309,7 +1309,7 @@ void transport_init_se_cmd(
 	INIT_LIST_HEAD(&cmd->se_cmd_list);
 	INIT_LIST_HEAD(&cmd->state_list);
 	init_completion(&cmd->t_transport_stop_comp);
-	init_completion(&cmd->cmd_wait_comp);
+	cmd->compl = NULL;
 	spin_lock_init(&cmd->t_state_lock);
 	INIT_WORK(&cmd->work, NULL);
 	kref_init(&cmd->cmd_kref);
@@ -2658,6 +2658,7 @@ static void target_wait_free_cmd(struct se_cmd *cmd, bool *aborted, bool *tas)
  */
 int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 {
+	DECLARE_COMPLETION_ONSTACK(compl);
 	int ret = 0;
 	bool aborted = false, tas = false;
 
@@ -2676,12 +2677,13 @@ int transport_generic_free_cmd(struct se_cmd *cmd, int wait_for_tasks)
 		if (cmd->se_lun)
 			transport_lun_remove_cmd(cmd);
 	}
+	if (aborted)
+		cmd->compl = &compl;
 	if (!aborted || tas)
 		ret = target_put_sess_cmd(cmd);
 	if (aborted) {
 		pr_debug("Detected CMD_T_ABORTED for ITT: %llu\n", cmd->tag);
-		wait_for_completion(&cmd->cmd_wait_comp);
-		cmd->se_tfo->release_cmd(cmd);
+		wait_for_completion(&compl);
 		ret = 1;
 	}
 	return ret;
@@ -2742,31 +2744,21 @@ static void target_release_cmd_kref(struct kref *kref)
 {
 	struct se_cmd *se_cmd = container_of(kref, struct se_cmd, cmd_kref);
 	struct se_session *se_sess = se_cmd->se_sess;
+	struct completion *compl = se_cmd->compl;
 	unsigned long flags;
-	bool fabric_stop;
 
 	if (se_sess) {
 		spin_lock_irqsave(&se_sess->sess_cmd_lock, flags);
 		list_del_init(&se_cmd->se_cmd_list);
 		if (list_empty(&se_sess->sess_cmd_list))
 			wake_up(&se_sess->cmd_list_wq);
-
-		spin_lock(&se_cmd->t_state_lock);
-		fabric_stop = (se_cmd->transport_state & CMD_T_FABRIC_STOP) &&
-			      (se_cmd->transport_state & CMD_T_ABORTED);
-		spin_unlock(&se_cmd->t_state_lock);
-
-		if (fabric_stop) {
-			spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
-			target_free_cmd_mem(se_cmd);
-			complete(&se_cmd->cmd_wait_comp);
-			return;
-		}
 		spin_unlock_irqrestore(&se_sess->sess_cmd_lock, flags);
 	}
 
 	target_free_cmd_mem(se_cmd);
 	se_cmd->se_tfo->release_cmd(se_cmd);
+	if (compl)
+		complete(compl);
 }
 
 /**
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index 906c1fc485e4..ca59e065c1fd 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -475,7 +475,7 @@ struct se_cmd {
 	struct se_session	*se_sess;
 	struct se_tmr_req	*se_tmr_req;
 	struct list_head	se_cmd_list;
-	struct completion	cmd_wait_comp;
+	struct completion	*compl;
 	const struct target_core_fabric_ops *se_tfo;
 	sense_reason_t		(*execute_cmd)(struct se_cmd *);
 	sense_reason_t (*transport_complete_callback)(struct se_cmd *, bool, int *);
-- 
cgit v1.2.3


From ed88f055788a89598c33d183652af8a84dfc5007 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:00 -0700
Subject: scsi: target/iscsi: Reduce number of __iscsit_free_cmd() callers

Instead of calling __iscsit_free_cmd() from inside iscsit_aborted_task() if
a command has been aborted and from inside iscsit_free_cmd() if a command
has not been aborted, call __iscsit_free_cmd() from inside
lio_release_cmd(). The latter function is namely called for all commands
once the reference count has dropped to zero.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Varun Prakash <varun@chelsio.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/iscsi/iscsi_target.c          | 2 --
 drivers/target/iscsi/iscsi_target_configfs.c | 1 +
 drivers/target/iscsi/iscsi_target_util.c     | 4 +---
 3 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 8e223799347a..d547dcd625d9 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -497,8 +497,6 @@ void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 	    !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP))
 		list_del_init(&cmd->i_conn_node);
 	spin_unlock_bh(&conn->cmd_lock);
-
-	__iscsit_free_cmd(cmd, true);
 }
 EXPORT_SYMBOL(iscsit_aborted_task);
 
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 0ebc4818e132..0bc346b2c27c 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1546,6 +1546,7 @@ static void lio_release_cmd(struct se_cmd *se_cmd)
 	struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
 
 	pr_debug("Entering lio_release_cmd for se_cmd: %p\n", se_cmd);
+	__iscsit_free_cmd(cmd, true);
 	iscsit_release_cmd(cmd);
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 8cfcf9033507..5a645b5f1eb4 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -772,10 +772,8 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
 	__iscsit_free_cmd(cmd, shutdown);
 	if (se_cmd) {
 		rc = transport_generic_free_cmd(se_cmd, shutdown);
-		if (!rc && shutdown && se_cmd->se_sess) {
-			__iscsit_free_cmd(cmd, shutdown);
+		if (!rc && shutdown && se_cmd->se_sess)
 			target_put_sess_cmd(se_cmd);
-		}
 	} else {
 		iscsit_release_cmd(cmd);
 	}
-- 
cgit v1.2.3


From 35bea5c84fd13c643cce63f0b5cd4b148f8c901d Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:01 -0700
Subject: scsi: target/iscsi: Make iscsit_ta_authentication() respect the
 output buffer size

Fixes: e48354ce078c ("iscsi-target: Add iSCSI fabric support for target v4.1")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/iscsi/iscsi_target_tpg.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_tpg.c b/drivers/target/iscsi/iscsi_target_tpg.c
index 4b34f71547c6..101d62105c93 100644
--- a/drivers/target/iscsi/iscsi_target_tpg.c
+++ b/drivers/target/iscsi/iscsi_target_tpg.c
@@ -636,8 +636,7 @@ int iscsit_ta_authentication(struct iscsi_portal_group *tpg, u32 authentication)
 		none = strstr(buf1, NONE);
 		if (none)
 			goto out;
-		strncat(buf1, ",", strlen(","));
-		strncat(buf1, NONE, strlen(NONE));
+		strlcat(buf1, "," NONE, sizeof(buf1));
 		if (iscsi_update_param_value(param, buf1) < 0)
 			return -EINVAL;
 	}
-- 
cgit v1.2.3


From aa090eabcb341b0c023e802884235c29598df1e5 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:02 -0700
Subject: scsi: target: Remove second argument from fabric_make_tpg()

Since most target drivers do not use the second fabric_make_tpg() argument
("group") and since it is trivial to derive the group pointer from the wwn
pointer, do not pass the group pointer to fabric_make_tpg().

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Felipe Balbi <felipe.balbi@linux.intel.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/infiniband/ulp/srpt/ib_srpt.c        |  2 --
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c     |  1 -
 drivers/scsi/qla2xxx/tcm_qla2xxx.c           | 12 ++++--------
 drivers/target/iscsi/iscsi_target_configfs.c |  6 ++----
 drivers/target/loopback/tcm_loop.c           |  6 ++----
 drivers/target/sbp/sbp_target.c              |  6 ++----
 drivers/target/target_core_fabric_configfs.c |  2 +-
 drivers/target/tcm_fc/tfc_conf.c             |  5 +----
 drivers/usb/gadget/function/f_tcm.c          |  8 +++-----
 drivers/vhost/scsi.c                         |  4 +---
 drivers/xen/xen-scsiback.c                   |  4 +---
 include/target/target_core_fabric.h          |  2 +-
 12 files changed, 18 insertions(+), 40 deletions(-)

diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 3081c629a7f7..07b3e1c583bd 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -3597,11 +3597,9 @@ static struct configfs_attribute *srpt_tpg_attrs[] = {
 /**
  * srpt_make_tpg - configfs callback invoked for mkdir /sys/kernel/config/target/$driver/$port/$tpg
  * @wwn: Corresponds to $driver/$port.
- * @group: Not used.
  * @name: $tpg.
  */
 static struct se_portal_group *srpt_make_tpg(struct se_wwn *wwn,
-					     struct config_group *group,
 					     const char *name)
 {
 	struct srpt_port *sport = wwn->priv;
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index c3a76af9f5fa..fdda04e5cf94 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -3928,7 +3928,6 @@ static void ibmvscsis_drop_tport(struct se_wwn *wwn)
 }
 
 static struct se_portal_group *ibmvscsis_make_tpg(struct se_wwn *wwn,
-						  struct config_group *group,
 						  const char *name)
 {
 	struct ibmvscsis_tport *tport =
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index 7732e9336d43..cfb5d6067f9f 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1049,10 +1049,8 @@ static struct configfs_attribute *tcm_qla2xxx_tpg_attrs[] = {
 	NULL,
 };
 
-static struct se_portal_group *tcm_qla2xxx_make_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *tcm_qla2xxx_make_tpg(struct se_wwn *wwn,
+						    const char *name)
 {
 	struct tcm_qla2xxx_lport *lport = container_of(wwn,
 			struct tcm_qla2xxx_lport, lport_wwn);
@@ -1171,10 +1169,8 @@ static struct configfs_attribute *tcm_qla2xxx_npiv_tpg_attrs[] = {
         NULL,
 };
 
-static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *tcm_qla2xxx_npiv_make_tpg(struct se_wwn *wwn,
+							 const char *name)
 {
 	struct tcm_qla2xxx_lport *lport = container_of(wwn,
 			struct tcm_qla2xxx_lport, lport_wwn);
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 0bc346b2c27c..1fcd9bc7189d 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1090,10 +1090,8 @@ static struct configfs_attribute *lio_target_tpg_attrs[] = {
 
 /* Start items for lio_target_tiqn_cit */
 
-static struct se_portal_group *lio_target_tiqn_addtpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *lio_target_tiqn_addtpg(struct se_wwn *wwn,
+						      const char *name)
 {
 	struct iscsi_portal_group *tpg;
 	struct iscsi_tiqn *tiqn;
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 60d5b918c4ac..4c8a97711291 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -983,10 +983,8 @@ static struct configfs_attribute *tcm_loop_tpg_attrs[] = {
 
 /* Start items for tcm_loop_naa_cit */
 
-static struct se_portal_group *tcm_loop_make_naa_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *tcm_loop_make_naa_tpg(struct se_wwn *wwn,
+						     const char *name)
 {
 	struct tcm_loop_hba *tl_hba = container_of(wwn,
 			struct tcm_loop_hba, tl_hba_wwn);
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index 42b21f2ac8b0..b61b79ac98ff 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -2006,10 +2006,8 @@ static void sbp_pre_unlink_lun(
 		pr_err("unlink LUN: failed to update unit directory\n");
 }
 
-static struct se_portal_group *sbp_make_tpg(
-		struct se_wwn *wwn,
-		struct config_group *group,
-		const char *name)
+static struct se_portal_group *sbp_make_tpg(struct se_wwn *wwn,
+					    const char *name)
 {
 	struct sbp_tport *tport =
 		container_of(wwn, struct sbp_tport, tport_wwn);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index e1416b007aa4..1fa436e865f9 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -841,7 +841,7 @@ static struct config_group *target_fabric_make_tpg(
 		return ERR_PTR(-ENOSYS);
 	}
 
-	se_tpg = tf->tf_ops->fabric_make_tpg(wwn, group, name);
+	se_tpg = tf->tf_ops->fabric_make_tpg(wwn, name);
 	if (!se_tpg || IS_ERR(se_tpg))
 		return ERR_PTR(-EINVAL);
 
diff --git a/drivers/target/tcm_fc/tfc_conf.c b/drivers/target/tcm_fc/tfc_conf.c
index 42ee91123dca..e55c4d537592 100644
--- a/drivers/target/tcm_fc/tfc_conf.c
+++ b/drivers/target/tcm_fc/tfc_conf.c
@@ -223,10 +223,7 @@ static int ft_init_nodeacl(struct se_node_acl *nacl, const char *name)
 /*
  * local_port port_group (tpg) ops.
  */
-static struct se_portal_group *ft_add_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *ft_add_tpg(struct se_wwn *wwn, const char *name)
 {
 	struct ft_lport_wwn *ft_wwn;
 	struct ft_tpg *tpg;
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 5003e857dce7..4f183176b0b4 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1344,10 +1344,8 @@ static int usbg_init_nodeacl(struct se_node_acl *se_nacl, const char *name)
 	return 0;
 }
 
-static struct se_portal_group *usbg_make_tpg(
-	struct se_wwn *wwn,
-	struct config_group *group,
-	const char *name)
+static struct se_portal_group *usbg_make_tpg(struct se_wwn *wwn,
+					     const char *name)
 {
 	struct usbg_tport *tport = container_of(wwn, struct usbg_tport,
 			tport_wwn);
@@ -1380,7 +1378,7 @@ static struct se_portal_group *usbg_make_tpg(
 			goto unlock_dep;
 	} else {
 		ret = configfs_depend_item_unlocked(
-			group->cg_subsys,
+			wwn->wwn_group.cg_subsys,
 			&opts->func_inst.group.cg_item);
 		if (ret)
 			goto unlock_dep;
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index ebaf831285ea..c84a6edd4c25 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1912,9 +1912,7 @@ static struct configfs_attribute *vhost_scsi_tpg_attrs[] = {
 };
 
 static struct se_portal_group *
-vhost_scsi_make_tpg(struct se_wwn *wwn,
-		   struct config_group *group,
-		   const char *name)
+vhost_scsi_make_tpg(struct se_wwn *wwn, const char *name)
 {
 	struct vhost_scsi_tport *tport = container_of(wwn,
 			struct vhost_scsi_tport, tport_wwn);
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 764dd9aa0131..fd77ccfc7d6e 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1732,9 +1732,7 @@ static void scsiback_port_unlink(struct se_portal_group *se_tpg,
 }
 
 static struct se_portal_group *
-scsiback_make_tpg(struct se_wwn *wwn,
-		   struct config_group *group,
-		   const char *name)
+scsiback_make_tpg(struct se_wwn *wwn, const char *name)
 {
 	struct scsiback_tport *tport = container_of(wwn,
 			struct scsiback_tport, tport_wwn);
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index 84a681b6e5ca..f61aa716cfe1 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -79,7 +79,7 @@ struct target_core_fabric_ops {
 	void (*fabric_drop_wwn)(struct se_wwn *);
 	void (*add_wwn_groups)(struct se_wwn *);
 	struct se_portal_group *(*fabric_make_tpg)(struct se_wwn *,
-				struct config_group *, const char *);
+						   const char *);
 	void (*fabric_drop_tpg)(struct se_portal_group *);
 	int (*fabric_post_link)(struct se_portal_group *,
 				struct se_lun *);
-- 
cgit v1.2.3


From 799d44d0fab60a96a0f13cdb13c9cc94ce06765e Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:03 -0700
Subject: scsi: target/tcm_loop: Avoid that static checkers warn about dead
 code

The code under the "release:" label can only be reached after se_cmd has
been set to a non-NULL value. Hence remove the if (se_cmd) test.  Keep the
else-part since calling transport_generic_free_cmd() is not necessary for a
command that has not been submitted to the core.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: 4d3895d5ea43 ("target/tcm_loop: Merge struct tcm_loop_cmd and struct tcm_loop_tmr")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/loopback/tcm_loop.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 4c8a97711291..b2e7ff50ff61 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -239,10 +239,7 @@ out:
 	return ret;
 
 release:
-	if (se_cmd)
-		transport_generic_free_cmd(se_cmd, 0);
-	else
-		kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
+	kmem_cache_free(tcm_loop_cmd_cache, tl_cmd);
 	goto out;
 }
 
-- 
cgit v1.2.3


From 89a104ed4f6a6876c25fbe8de0253b89466869f0 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:04 -0700
Subject: scsi: target: Do not duplicate the code that marks that a command has
 sense data

This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index cb48dbc2c9ba..ebbc7e321cf3 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2121,9 +2121,6 @@ static void transport_complete_qf(struct se_cmd *cmd)
 		if (cmd->scsi_status)
 			goto queue_status;
 
-		cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
-		cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
-		cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
 		translate_sense_reason(cmd, TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE);
 		goto queue_status;
 	}
@@ -3199,6 +3196,9 @@ static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 		ascq = si->ascq;
 	}
 
+	cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
+	cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
+	cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
 	scsi_build_sense_buffer(desc_format, buffer, si->key, asc, ascq);
 	if (si->add_sector_info)
 		return scsi_set_sense_information(buffer,
@@ -3225,9 +3225,6 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 	if (!from_transport) {
 		int rc;
 
-		cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
-		cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
-		cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
 		rc = translate_sense_reason(cmd, reason);
 		if (rc)
 			return rc;
-- 
cgit v1.2.3


From 17e391dd09f5b257365367ce812a4332dc2c9653 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:05 -0700
Subject: scsi: target: Send unit attention condition even if the sense buffer
 is too small

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 21 +++++++--------------
 1 file changed, 7 insertions(+), 14 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index ebbc7e321cf3..a71cfae46805 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -64,7 +64,7 @@ struct kmem_cache *t10_alua_lba_map_cache;
 struct kmem_cache *t10_alua_lba_map_mem_cache;
 
 static void transport_complete_task_attr(struct se_cmd *cmd);
-static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
+static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason);
 static void transport_handle_queue_full(struct se_cmd *cmd,
 		struct se_device *dev, int err, bool write_pending);
 static void target_complete_ok_work(struct work_struct *work);
@@ -3170,7 +3170,7 @@ static const struct sense_info sense_info_table[] = {
 	},
 };
 
-static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
+static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 {
 	const struct sense_info *si;
 	u8 *buffer = cmd->sense_buffer;
@@ -3201,11 +3201,9 @@ static int translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 	cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
 	scsi_build_sense_buffer(desc_format, buffer, si->key, asc, ascq);
 	if (si->add_sector_info)
-		return scsi_set_sense_information(buffer,
-						  cmd->scsi_sense_length,
-						  cmd->bad_sector);
-
-	return 0;
+		WARN_ON_ONCE(scsi_set_sense_information(buffer,
+							cmd->scsi_sense_length,
+							cmd->bad_sector) < 0);
 }
 
 int
@@ -3222,13 +3220,8 @@ transport_send_check_condition_and_sense(struct se_cmd *cmd,
 	cmd->se_cmd_flags |= SCF_SENT_CHECK_CONDITION;
 	spin_unlock_irqrestore(&cmd->t_state_lock, flags);
 
-	if (!from_transport) {
-		int rc;
-
-		rc = translate_sense_reason(cmd, reason);
-		if (rc)
-			return rc;
-	}
+	if (!from_transport)
+		translate_sense_reason(cmd, reason);
 
 	trace_target_cmd_complete(cmd);
 	return cmd->se_tfo->queue_status(cmd);
-- 
cgit v1.2.3


From 325c1e8b248ed12a685d0a904b774abef3821e8e Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:06 -0700
Subject: scsi: target: Fix handling of removed LUNs

Send a valid ASC / ASCQ combination back to the initiator if a SCSI command
is received after a LUN has been removed. This patch fixes the following
call trace:

WARNING: CPU: 0 PID: 4 at drivers/target/target_core_transport.c:3131 translate_sense_reason+0x164/0x190 [target_core_mod]
Workqueue: ib-comp-wq ib_cq_poll_work [ib_core]
RIP: 0010:translate_sense_reason+0x164/0x190 [target_core_mod]
Call Trace:
transport_send_check_condition_and_sense+0x95/0x1c0 [target_core_mod]
transport_generic_request_failure+0x102/0x270 [target_core_mod]
transport_generic_new_cmd+0x138/0x340 [target_core_mod]
transport_handle_cdb_direct+0x2f/0x80 [target_core_mod]
target_submit_cmd_map_sgls+0x212/0x2a0 [target_core_mod]
srpt_handle_new_iu+0x244/0x680 [ib_srpt]
__ib_process_cq+0x6d/0xc0 [ib_core]
ib_cq_poll_work+0x18/0x50 [ib_core]
process_one_work+0x20b/0x6a0
worker_thread+0x35/0x380
kthread+0x117/0x130
ret_from_fork+0x24/0x30

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 23 +++++++++++++++++++----
 drivers/target/target_core_ua.c        | 31 ++++++++++++++++++-------------
 drivers/target/target_core_ua.h        |  3 ++-
 3 files changed, 39 insertions(+), 18 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index a71cfae46805..7261561e87cc 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -3170,12 +3170,23 @@ static const struct sense_info sense_info_table[] = {
 	},
 };
 
+/**
+ * translate_sense_reason - translate a sense reason into T10 key, asc and ascq
+ * @cmd: SCSI command in which the resulting sense buffer or SCSI status will
+ *   be stored.
+ * @reason: LIO sense reason code. If this argument has the value
+ *   TCM_CHECK_CONDITION_UNIT_ATTENTION, try to dequeue a unit attention. If
+ *   dequeuing a unit attention fails due to multiple commands being processed
+ *   concurrently, set the command status to BUSY.
+ *
+ * Return: 0 upon success or -EINVAL if the sense buffer is too small.
+ */
 static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 {
 	const struct sense_info *si;
 	u8 *buffer = cmd->sense_buffer;
 	int r = (__force int)reason;
-	u8 asc, ascq;
+	u8 key, asc, ascq;
 	bool desc_format = target_sense_desc_format(cmd->se_dev);
 
 	if (r < ARRAY_SIZE(sense_info_table) && sense_info_table[r].key)
@@ -3184,9 +3195,13 @@ static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 		si = &sense_info_table[(__force int)
 				       TCM_LOGICAL_UNIT_COMMUNICATION_FAILURE];
 
+	key = si->key;
 	if (reason == TCM_CHECK_CONDITION_UNIT_ATTENTION) {
-		core_scsi3_ua_for_check_condition(cmd, &asc, &ascq);
-		WARN_ON_ONCE(asc == 0);
+		if (!core_scsi3_ua_for_check_condition(cmd, &key, &asc,
+						       &ascq)) {
+			cmd->scsi_status = SAM_STAT_BUSY;
+			return;
+		}
 	} else if (si->asc == 0) {
 		WARN_ON_ONCE(cmd->scsi_asc == 0);
 		asc = cmd->scsi_asc;
@@ -3199,7 +3214,7 @@ static void translate_sense_reason(struct se_cmd *cmd, sense_reason_t reason)
 	cmd->se_cmd_flags |= SCF_EMULATED_TASK_SENSE;
 	cmd->scsi_status = SAM_STAT_CHECK_CONDITION;
 	cmd->scsi_sense_length  = TRANSPORT_SENSE_BUFFER;
-	scsi_build_sense_buffer(desc_format, buffer, si->key, asc, ascq);
+	scsi_build_sense_buffer(desc_format, buffer, key, asc, ascq);
 	if (si->add_sector_info)
 		WARN_ON_ONCE(scsi_set_sense_information(buffer,
 							cmd->scsi_sense_length,
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index be25eb807a5f..9399b38339f9 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -202,10 +202,13 @@ void core_scsi3_ua_release_all(
 	spin_unlock(&deve->ua_lock);
 }
 
-void core_scsi3_ua_for_check_condition(
-	struct se_cmd *cmd,
-	u8 *asc,
-	u8 *ascq)
+/*
+ * Dequeue a unit attention from the unit attention list. This function
+ * returns true if the dequeuing succeeded and if *@key, *@asc and *@ascq have
+ * been set.
+ */
+bool core_scsi3_ua_for_check_condition(struct se_cmd *cmd, u8 *key, u8 *asc,
+				       u8 *ascq)
 {
 	struct se_device *dev = cmd->se_dev;
 	struct se_dev_entry *deve;
@@ -214,23 +217,23 @@ void core_scsi3_ua_for_check_condition(
 	struct se_ua *ua = NULL, *ua_p;
 	int head = 1;
 
-	if (!sess)
-		return;
+	if (WARN_ON_ONCE(!sess))
+		return false;
 
 	nacl = sess->se_node_acl;
-	if (!nacl)
-		return;
+	if (WARN_ON_ONCE(!nacl))
+		return false;
 
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, cmd->orig_fe_lun);
 	if (!deve) {
 		rcu_read_unlock();
-		return;
-	}
-	if (!atomic_read(&deve->ua_count)) {
-		rcu_read_unlock();
-		return;
+		*key = ILLEGAL_REQUEST;
+		*asc = 0x25; /* LOGICAL UNIT NOT SUPPORTED */
+		*ascq = 0;
+		return true;
 	}
+	*key = UNIT_ATTENTION;
 	/*
 	 * The highest priority Unit Attentions are placed at the head of the
 	 * struct se_dev_entry->ua_list, and will be returned in CHECK_CONDITION +
@@ -273,6 +276,8 @@ void core_scsi3_ua_for_check_condition(
 		(dev->dev_attrib.emulate_ua_intlck_ctrl != 0) ? "Reporting" :
 		"Releasing", dev->dev_attrib.emulate_ua_intlck_ctrl,
 		cmd->orig_fe_lun, cmd->t_task_cdb[0], *asc, *ascq);
+
+	return head == 0;
 }
 
 int core_scsi3_ua_clear_for_request_sense(
diff --git a/drivers/target/target_core_ua.h b/drivers/target/target_core_ua.h
index b0f4205a96cd..76487c9be090 100644
--- a/drivers/target/target_core_ua.h
+++ b/drivers/target/target_core_ua.h
@@ -37,7 +37,8 @@ extern sense_reason_t target_scsi3_ua_check(struct se_cmd *);
 extern int core_scsi3_ua_allocate(struct se_dev_entry *, u8, u8);
 extern void target_ua_allocate_lun(struct se_node_acl *, u32, u8, u8);
 extern void core_scsi3_ua_release_all(struct se_dev_entry *);
-extern void core_scsi3_ua_for_check_condition(struct se_cmd *, u8 *, u8 *);
+extern bool core_scsi3_ua_for_check_condition(struct se_cmd *, u8 *, u8 *,
+					      u8 *);
 extern int core_scsi3_ua_clear_for_request_sense(struct se_cmd *,
 						u8 *, u8 *);
 
-- 
cgit v1.2.3


From e936a38ac92dd40867ac3b52cfd8f3f70fe717a5 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 22 Jun 2018 14:53:07 -0700
Subject: scsi: target: Remove se_dev_entry.ua_count

se_dev_entry.ua_count is only used to check whether or not
se_dev_entry.ua_list is empty. Use list_empty_careful() instead.  Checking
whether or not ua_list is empty without holding the lock that protects that
list is fine because the code that dequeues from that list will check again
whether or not that list is empty.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Hannes Reinecke <hare@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_device.c |  1 -
 drivers/target/target_core_ua.c     | 12 ++----------
 include/target/target_core_base.h   |  1 -
 3 files changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index e5c90afb40e6..73675eec740d 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -336,7 +336,6 @@ int core_enable_device_list_for_node(
 		return -ENOMEM;
 	}
 
-	atomic_set(&new->ua_count, 0);
 	spin_lock_init(&new->ua_lock);
 	INIT_LIST_HEAD(&new->ua_list);
 	INIT_LIST_HEAD(&new->lun_link);
diff --git a/drivers/target/target_core_ua.c b/drivers/target/target_core_ua.c
index 9399b38339f9..c8ac242ce888 100644
--- a/drivers/target/target_core_ua.c
+++ b/drivers/target/target_core_ua.c
@@ -55,7 +55,7 @@ target_scsi3_ua_check(struct se_cmd *cmd)
 		rcu_read_unlock();
 		return 0;
 	}
-	if (!atomic_read(&deve->ua_count)) {
+	if (list_empty_careful(&deve->ua_list)) {
 		rcu_read_unlock();
 		return 0;
 	}
@@ -154,7 +154,6 @@ int core_scsi3_ua_allocate(
 				&deve->ua_list);
 		spin_unlock(&deve->ua_lock);
 
-		atomic_inc_mb(&deve->ua_count);
 		return 0;
 	}
 	list_add_tail(&ua->ua_nacl_list, &deve->ua_list);
@@ -164,7 +163,6 @@ int core_scsi3_ua_allocate(
 		" 0x%02x, ASCQ: 0x%02x\n", deve->mapped_lun,
 		asc, ascq);
 
-	atomic_inc_mb(&deve->ua_count);
 	return 0;
 }
 
@@ -196,8 +194,6 @@ void core_scsi3_ua_release_all(
 	list_for_each_entry_safe(ua, ua_p, &deve->ua_list, ua_nacl_list) {
 		list_del(&ua->ua_nacl_list);
 		kmem_cache_free(se_ua_cache, ua);
-
-		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
 }
@@ -263,8 +259,6 @@ bool core_scsi3_ua_for_check_condition(struct se_cmd *cmd, u8 *key, u8 *asc,
 		}
 		list_del(&ua->ua_nacl_list);
 		kmem_cache_free(se_ua_cache, ua);
-
-		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
 	rcu_read_unlock();
@@ -304,7 +298,7 @@ int core_scsi3_ua_clear_for_request_sense(
 		rcu_read_unlock();
 		return -EINVAL;
 	}
-	if (!atomic_read(&deve->ua_count)) {
+	if (list_empty_careful(&deve->ua_list)) {
 		rcu_read_unlock();
 		return -EPERM;
 	}
@@ -327,8 +321,6 @@ int core_scsi3_ua_clear_for_request_sense(
 		}
 		list_del(&ua->ua_nacl_list);
 		kmem_cache_free(se_ua_cache, ua);
-
-		atomic_dec_mb(&deve->ua_count);
 	}
 	spin_unlock(&deve->ua_lock);
 	rcu_read_unlock();
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index ca59e065c1fd..7a4ee7852ca4 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -638,7 +638,6 @@ struct se_dev_entry {
 	atomic_long_t		total_cmds;
 	atomic_long_t		read_bytes;
 	atomic_long_t		write_bytes;
-	atomic_t		ua_count;
 	/* Used for PR SPEC_I_PT=1 and REGISTER_AND_MOVE */
 	struct kref		pr_kref;
 	struct completion	pr_comp;
-- 
cgit v1.2.3


From 6aa56f44253a6dd802e45d8ab1b48847feaf063a Mon Sep 17 00:00:00 2001
From: Kamal Mostafa <kamal@canonical.com>
Date: Fri, 29 Jun 2018 13:04:21 -0700
Subject: usercopy: Do not select BUG with HARDENED_USERCOPY

There is no need to "select BUG" when CONFIG_HARDENED_USERCOPY is enabled.
The kernel thread will always die, regardless of the CONFIG_BUG.

Signed-off-by: Kamal Mostafa <kamal@canonical.com>
[kees: tweak commit log]
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 security/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/security/Kconfig b/security/Kconfig
index c4302067a3ad..766777406ca8 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -153,7 +153,6 @@ config HAVE_HARDENED_USERCOPY_ALLOCATOR
 config HARDENED_USERCOPY
 	bool "Harden memory copies between kernel and userspace"
 	depends on HAVE_HARDENED_USERCOPY_ALLOCATOR
-	select BUG
 	imply STRICT_DEVMEM
 	help
 	  This option checks for obviously wrong memory regions when
-- 
cgit v1.2.3


From c17d6179ad5aec2a6ef85f8555454e9cefd4b9fb Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 3 Jul 2018 09:39:12 +0900
Subject: gcc-plugins: remove unused GCC_PLUGIN_SUBDIR

GCC_PLUGIN_SUBDIR has never been used.  If you really need this in
the future, please re-add it then.

For now, the code is unused. Remove.

'export HOSTLIBS' is not necessary either.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 scripts/Makefile.gcc-plugins | 3 +--
 scripts/gcc-plugins/Makefile | 5 -----
 2 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index c961b9a65d11..f9942d9ac3fc 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -19,7 +19,7 @@ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT_PERFORMANCE)	+= -fplugin-arg-ra
 
 GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y))
 
-export GCC_PLUGINS_CFLAGS GCC_PLUGIN GCC_PLUGIN_SUBDIR
+export GCC_PLUGINS_CFLAGS GCC_PLUGIN
 export DISABLE_LATENT_ENTROPY_PLUGIN
 
 # sancov_plugin.so can be only in CFLAGS_KCOV because avoid duplication.
@@ -27,7 +27,6 @@ GCC_PLUGINS_CFLAGS := $(filter-out %/sancov_plugin.so, $(GCC_PLUGINS_CFLAGS))
 
 KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS)
 GCC_PLUGIN := $(gcc-plugin-y)
-GCC_PLUGIN_SUBDIR := $(gcc-plugin-subdir-y)
 
 # Actually do the build, if requested.
 PHONY += gcc-plugins
diff --git a/scripts/gcc-plugins/Makefile b/scripts/gcc-plugins/Makefile
index 326254653bd0..aa0d0ec6936d 100644
--- a/scripts/gcc-plugins/Makefile
+++ b/scripts/gcc-plugins/Makefile
@@ -14,8 +14,6 @@ else
   export HOST_EXTRACXXFLAGS
 endif
 
-export HOSTLIBS
-
 $(obj)/randomize_layout_plugin.o: $(objtree)/$(obj)/randomize_layout_seed.h
 quiet_cmd_create_randomize_layout_seed = GENSEED $@
 cmd_create_randomize_layout_seed = \
@@ -29,7 +27,4 @@ always := $($(HOSTLIBS)-y)
 
 $(foreach p,$($(HOSTLIBS)-y:%.so=%),$(eval $(p)-objs := $(p).o))
 
-subdir-y := $(GCC_PLUGIN_SUBDIR)
-subdir-  += $(GCC_PLUGIN_SUBDIR)
-
 clean-files += *.so
-- 
cgit v1.2.3


From 42036383599e53fc4b3d9aab52d1492c561ab650 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Fri, 29 Jun 2018 10:35:45 -0500
Subject: net: phy: DP83TC811: Add INT_STAT3

Add INT_STAT3 interrupt setting and clearing
support.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83tc811.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index 49ac678eb2dc..f8653f5d8789 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -21,6 +21,7 @@
 #define MII_DP83811_SGMII_CTRL	0x09
 #define MII_DP83811_INT_STAT1	0x12
 #define MII_DP83811_INT_STAT2	0x13
+#define MII_DP83811_INT_STAT3	0x18
 #define MII_DP83811_RESET_CTRL	0x1f
 
 #define DP83811_HW_RESET	BIT(15)
@@ -44,6 +45,11 @@
 #define DP83811_OVERVOLTAGE_INT_EN	BIT(6)
 #define DP83811_UNDERVOLTAGE_INT_EN	BIT(7)
 
+/* INT_STAT3 bits */
+#define DP83811_LPS_INT_EN	BIT(0)
+#define DP83811_NO_FRAME_INT_EN	BIT(3)
+#define DP83811_POR_DONE_INT_EN	BIT(4)
+
 #define MII_DP83811_RXSOP1	0x04a5
 #define MII_DP83811_RXSOP2	0x04a6
 #define MII_DP83811_RXSOP3	0x04a7
@@ -81,6 +87,10 @@ static int dp83811_ack_interrupt(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
+	err = phy_read(phydev, MII_DP83811_INT_STAT3);
+	if (err < 0)
+		return err;
+
 	return 0;
 }
 
@@ -216,6 +226,18 @@ static int dp83811_config_intr(struct phy_device *phydev)
 				DP83811_UNDERVOLTAGE_INT_EN);
 
 		err = phy_write(phydev, MII_DP83811_INT_STAT2, misr_status);
+		if (err < 0)
+			return err;
+
+		misr_status = phy_read(phydev, MII_DP83811_INT_STAT3);
+		if (misr_status < 0)
+			return misr_status;
+
+		misr_status |= (DP83811_LPS_INT_EN |
+				DP83811_NO_FRAME_INT_EN |
+				DP83811_POR_DONE_INT_EN);
+
+		err = phy_write(phydev, MII_DP83811_INT_STAT3, misr_status);
 
 	} else {
 		err = phy_write(phydev, MII_DP83811_INT_STAT1, 0);
@@ -223,6 +245,10 @@ static int dp83811_config_intr(struct phy_device *phydev)
 			return err;
 
 		err = phy_write(phydev, MII_DP83811_INT_STAT2, 0);
+		if (err < 0)
+			return err;
+
+		err = phy_write(phydev, MII_DP83811_INT_STAT3, 0);
 	}
 
 	return err;
-- 
cgit v1.2.3


From 00f553660a7f524a3b913cb5cf6c5f33f9638f09 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Fri, 29 Jun 2018 10:35:46 -0500
Subject: net: phy: DP83TC811: Fix SGMII enable/disable

If SGMII was selected in the DT then the device should
write the SGMII enable bit.

If SGMII is not selected in the DT then the SGMII bit
should be disabled.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83tc811.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c
index f8653f5d8789..78cad134a79e 100644
--- a/drivers/net/phy/dp83tc811.c
+++ b/drivers/net/phy/dp83tc811.c
@@ -284,21 +284,19 @@ static int dp83811_config_init(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
+	value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
 	if (phydev->interface == PHY_INTERFACE_MODE_SGMII) {
-		value = phy_read(phydev, MII_DP83811_SGMII_CTRL);
-		if (!(value & DP83811_SGMII_EN)) {
-			err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+		err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
 					(DP83811_SGMII_EN | value));
-			if (err < 0)
-				return err;
-		} else {
-			err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
-					(~DP83811_SGMII_EN & value));
-			if (err < 0)
-				return err;
-		}
+	} else {
+		err = phy_write(phydev, MII_DP83811_SGMII_CTRL,
+				(~DP83811_SGMII_EN & value));
 	}
 
+	if (err < 0)
+
+		return err;
+
 	value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN;
 
 	return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG,
-- 
cgit v1.2.3


From ce730f1cc1255be152c879a2bc5f295d341d8036 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Sat, 30 Jun 2018 22:03:02 -0700
Subject: x86/intel_rdt: Move pseudo_lock_region_clear()

The pseudo_lock_region_clear() function is moved to earlier in the file in
preparation for its use in functions that currently appear before it. No
functional change.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/ef098ec2a45501e23792289bff80ae3152141e2f.1530421026.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 46 ++++++++++++++---------------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 6e83f61552a5..1860ec10302d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -246,6 +246,29 @@ out_err:
 	return ret;
 }
 
+/**
+ * pseudo_lock_region_clear - Reset pseudo-lock region data
+ * @plr: pseudo-lock region
+ *
+ * All content of the pseudo-locked region is reset - any memory allocated
+ * freed.
+ *
+ * Return: void
+ */
+static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
+{
+	plr->size = 0;
+	plr->line_size = 0;
+	kfree(plr->kmem);
+	plr->kmem = NULL;
+	plr->r = NULL;
+	if (plr->d)
+		plr->d->plr = NULL;
+	plr->d = NULL;
+	plr->cbm = 0;
+	plr->debugfs_dir = NULL;
+}
+
 /**
  * pseudo_lock_region_init - Initialize pseudo-lock region information
  * @plr: pseudo-lock region
@@ -318,29 +341,6 @@ static int pseudo_lock_init(struct rdtgroup *rdtgrp)
 	return 0;
 }
 
-/**
- * pseudo_lock_region_clear - Reset pseudo-lock region data
- * @plr: pseudo-lock region
- *
- * All content of the pseudo-locked region is reset - any memory allocated
- * freed.
- *
- * Return: void
- */
-static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
-{
-	plr->size = 0;
-	plr->line_size = 0;
-	kfree(plr->kmem);
-	plr->kmem = NULL;
-	plr->r = NULL;
-	if (plr->d)
-		plr->d->plr = NULL;
-	plr->d = NULL;
-	plr->cbm = 0;
-	plr->debugfs_dir = NULL;
-}
-
 /**
  * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
  * @plr: pseudo-lock region
-- 
cgit v1.2.3


From 546d3c74277398a3d76d059bd2db47186bb47fc8 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Sat, 30 Jun 2018 22:03:03 -0700
Subject: x86/intel_rdt: Fix cleanup of plr structure on error

When a resource group enters pseudo-locksetup mode a pseudo_lock_region is
associated with it. When the user writes to the resource group's schemata
file the CBM of the requested pseudo-locked region is entered into the
pseudo_lock_region struct. If any part of pseudo-lock region creation fails
the resource group will remain in pseudo-locksetup mode with the
pseudo_lock_region associated with it.

In case of failure during pseudo-lock region creation care needs to be
taken to ensure that the pseudo_lock_region struct associated with the
resource group is cleared from any pseudo-locking data - especially the
CBM. This is because the existence of a pseudo_lock_region struct with a
CBM is significant in other areas of the code, for example, the display of
bit_usage and initialization of a new resource group.

Fix the error path of pseudo-lock region creation to ensure that the
pseudo_lock_region struct is cleared at each error exit.

Fixes: 018961ae5579 ("x86/intel_rdt: Pseudo-lock region creation/removal core")
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/49b4782f6d204d122cee3499e642b2772a98d2b4.1530421026.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 1860ec10302d..8fd79c281ee6 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -290,6 +290,7 @@ static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
 static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 {
 	struct cpu_cacheinfo *ci;
+	int ret;
 	int i;
 
 	/* Pick the first cpu we find that is associated with the cache. */
@@ -298,7 +299,8 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 	if (!cpu_online(plr->cpu)) {
 		rdt_last_cmd_printf("cpu %u associated with cache not online\n",
 				    plr->cpu);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_region;
 	}
 
 	ci = get_cpu_cacheinfo(plr->cpu);
@@ -312,8 +314,11 @@ static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
 		}
 	}
 
+	ret = -1;
 	rdt_last_cmd_puts("unable to determine cache line size\n");
-	return -1;
+out_region:
+	pseudo_lock_region_clear(plr);
+	return ret;
 }
 
 /**
@@ -365,16 +370,23 @@ static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
 	 */
 	if (plr->size > KMALLOC_MAX_SIZE) {
 		rdt_last_cmd_puts("requested region exceeds maximum size\n");
-		return -E2BIG;
+		ret = -E2BIG;
+		goto out_region;
 	}
 
 	plr->kmem = kzalloc(plr->size, GFP_KERNEL);
 	if (!plr->kmem) {
 		rdt_last_cmd_puts("unable to allocate memory\n");
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_region;
 	}
 
-	return 0;
+	ret = 0;
+	goto out;
+out_region:
+	pseudo_lock_region_clear(plr);
+out:
+	return ret;
 }
 
 /**
-- 
cgit v1.2.3


From 392487def48e4b596526a4a8c2c2ec4cfe73bf13 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Sat, 30 Jun 2018 22:17:32 -0700
Subject: x86/intel_rdt: Support restoration of subset of permissions

As the mode of a resource group changes, the operations it can support may
also change. One way in which the supported operations are managed is to
modify the permissions of the files within the resource group's resctrl
directory.

At the moment only two possible permissions are supported: the default
permissions or no permissions in support for when the operation is "locked
down". It is possible where an operation on a resource group may have more
possibilities. For example, if by default changes can be made to the
resource group by writing to a resctrl file while the current settings can
be obtained by reading from the file, then it may be possible that in
another mode it is only possible to read the current settings, and not
change them.

Make it possible to modify some of the permissions of a resctrl file in
support of a more flexible way to manage the operations on a resource
group. In this preparation work the original behavior is maintained where
all permissions are restored.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/8773aadfade7bcb2c48a45fa294a04d2c03bb0a1.1530421961.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt.h             |  3 ++-
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 14 +++++++-------
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    |  6 ++++--
 3 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt.h b/arch/x86/kernel/cpu/intel_rdt.h
index 2d9cbb9d7a58..4e588f36228f 100644
--- a/arch/x86/kernel/cpu/intel_rdt.h
+++ b/arch/x86/kernel/cpu/intel_rdt.h
@@ -512,7 +512,8 @@ void rdt_ctrl_update(void *arg);
 struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
 void rdtgroup_kn_unlock(struct kernfs_node *kn);
 int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name);
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask);
 struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
 				   struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 8fd79c281ee6..5dfe4008c58f 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -590,11 +590,11 @@ static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
 	goto out;
 
 err_cpus_list:
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list");
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
 err_cpus:
-	rdtgroup_kn_mode_restore(rdtgrp, "cpus");
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
 err_tasks:
-	rdtgroup_kn_mode_restore(rdtgrp, "tasks");
+	rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
 out:
 	return ret;
 }
@@ -615,20 +615,20 @@ static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
 {
 	int ret;
 
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks");
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
 	if (ret)
 		return ret;
 
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus");
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
 	if (ret)
 		goto err_tasks;
 
-	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list");
+	ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
 	if (ret)
 		goto err_cpus;
 
 	if (rdt_mon_capable) {
-		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups");
+		ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
 		if (ret)
 			goto err_cpus_list;
 	}
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 7b4a09d81a30..c20b51afd62d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -1405,13 +1405,15 @@ int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
  * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
  * @r: The resource group with which the file is associated.
  * @name: Name of the file
+ * @mask: Mask of permissions that should be restored
  *
  * Restore the permissions of the named file. If @name is a directory the
  * permissions of its parent will be used.
  *
  * Return: 0 on success, <0 on failure.
  */
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name)
+int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
+			     umode_t mask)
 {
 	struct iattr iattr = {.ia_valid = ATTR_MODE,};
 	struct kernfs_node *kn, *parent;
@@ -1423,7 +1425,7 @@ int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name)
 
 	for (rft = rfts; rft < rfts + len; rft++) {
 		if (!strcmp(rft->name, name))
-			iattr.ia_mode = rft->mode;
+			iattr.ia_mode = rft->mode & mask;
 	}
 
 	kn = kernfs_find_and_get_ns(r->kn, name, NULL);
-- 
cgit v1.2.3


From 33dc3e410a0d99f394905143b26d34f1fd64c962 Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Sat, 30 Jun 2018 22:17:33 -0700
Subject: x86/intel_rdt: Make CPU information accessible for pseudo-locked
 regions

When a resource group enters pseudo-locksetup mode it reflects that the
platform supports cache pseudo-locking and the resource group is unused,
ready to be used for a pseudo-locked region. Until it is set up as a
pseudo-locked region the resource group is "locked down" such that no new
tasks or cpus can be assigned to it. This is accomplished in a user visible
way by making the cpus, cpus_list, and tasks resctrl files inaccassible
(user cannot read from or write to these files).

When the resource group changes to pseudo-locked mode it represents a cache
pseudo-locked region. While not appropriate to make any changes to the cpus
assigned to this region it is useful to make it easy for the user to see
which cpus are associated with the pseudo-locked region.

Modify the permissions of the cpus/cpus_list file when the resource group
changes to pseudo-locked mode to support reading (not writing).  The
information presented to the user when reading the file are the cpus
associated with the pseudo-locked region.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: dave.hansen@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/12756b7963b6abc1bffe8fb560b87b75da827bd1.1530421961.git.reinette.chatre@intel.com
---
 Documentation/x86/intel_rdt_ui.txt          | 3 +++
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 3 +++
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c    | 8 ++++++--
 3 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/Documentation/x86/intel_rdt_ui.txt b/Documentation/x86/intel_rdt_ui.txt
index acac30b67c62..f662d3c530e5 100644
--- a/Documentation/x86/intel_rdt_ui.txt
+++ b/Documentation/x86/intel_rdt_ui.txt
@@ -178,6 +178,9 @@ All groups contain the following files:
 	CPUs to/from this group. As with the tasks file a hierarchy is
 	maintained where MON groups may only include CPUs owned by the
 	parent CTRL_MON group.
+	When the resouce group is in pseudo-locked mode this file will
+	only be readable, reflecting the CPUs associated with the
+	pseudo-locked region.
 
 
 "cpus_list":
diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 5dfe4008c58f..751c78f9992f 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -1303,6 +1303,9 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 	rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
 	closid_free(rdtgrp->closid);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
+	rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
+
 	ret = 0;
 	goto out;
 
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index c20b51afd62d..d6d7ea7349d0 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -265,8 +265,12 @@ static int rdtgroup_cpus_show(struct kernfs_open_file *of,
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 
 	if (rdtgrp) {
-		seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
-			   cpumask_pr_args(&rdtgrp->cpu_mask));
+		if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
+			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+				   cpumask_pr_args(&rdtgrp->plr->d->cpu_mask));
+		else
+			seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
+				   cpumask_pr_args(&rdtgrp->cpu_mask));
 	} else {
 		ret = -ENOENT;
 	}
-- 
cgit v1.2.3


From ba6096311ba6aed28fec237038ec986c9bf9b8e9 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 2 Jul 2018 11:10:23 +0200
Subject: drm: Fix hdmi connector content type property docs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Apparently didn't get carefully checked.

Fixes: 50525c332b55 ("drm: content-type property for HDMI connector")
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Stanislav Lisovskiy <stanislav.lisovskiy@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702091023.695-1-daniel.vetter@ffwll.ch
---
 Documentation/gpu/drm-kms.rst   | 2 +-
 drivers/gpu/drm/drm_connector.c | 4 +---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 4f6f113a7f5d..514939433004 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -527,7 +527,7 @@ Standard Connector Properties
    :doc: standard connector properties
 
 HDMI Specific Connector Properties
------------------------------
+----------------------------------
 
 .. kernel-doc:: drivers/gpu/drm/drm_connector.c
    :doc: HDMI connector properties
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 2f9ebddd178e..b09b3a3e4024 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -1033,9 +1033,7 @@ EXPORT_SYMBOL(drm_mode_create_dvi_i_properties);
  *
  *	Drivers can set up this property by calling
  *	drm_connector_attach_content_type_property(). Decoding to
- *	infoframe values is done through
- *	drm_hdmi_get_content_type_from_property() and
- *	drm_hdmi_get_itc_bit_from_property().
+ *	infoframe values is done through drm_hdmi_avi_infoframe_content_type().
  */
 
 /**
-- 
cgit v1.2.3


From 53e52966901a5b14caa2a7c77428a693fe71f734 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 22 Jun 2018 19:06:22 +0200
Subject: x86/hyper-v: Implement hv_do_fast_hypercall16

Implement 'Fast' hypercall with two 64-bit input parameter. This is
going to be used for HvCallSendSyntheticClusterIpi hypercall.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: devel@linuxdriverproject.org
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Tianyu Lan <Tianyu.Lan@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Link: https://lkml.kernel.org/r/20180622170625.30688-2-vkuznets@redhat.com
---
 arch/x86/include/asm/mshyperv.h | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index 3cd14311edfa..da25642940d3 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -193,6 +193,40 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
 		return hv_status;
 }
 
+/* Fast hypercall with 16 bytes of input */
+static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
+{
+	u64 hv_status, control = (u64)code | HV_HYPERCALL_FAST_BIT;
+
+#ifdef CONFIG_X86_64
+	{
+		__asm__ __volatile__("mov %4, %%r8\n"
+				     CALL_NOSPEC
+				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
+				       "+c" (control), "+d" (input1)
+				     : "r" (input2),
+				       THUNK_TARGET(hv_hypercall_pg)
+				     : "cc", "r8", "r9", "r10", "r11");
+	}
+#else
+	{
+		u32 input1_hi = upper_32_bits(input1);
+		u32 input1_lo = lower_32_bits(input1);
+		u32 input2_hi = upper_32_bits(input2);
+		u32 input2_lo = lower_32_bits(input2);
+
+		__asm__ __volatile__ (CALL_NOSPEC
+				      : "=A"(hv_status),
+					"+c"(input1_lo), ASM_CALL_CONSTRAINT
+				      :	"A" (control), "b" (input1_hi),
+					"D"(input2_hi), "S"(input2_lo),
+					THUNK_TARGET(hv_hypercall_pg)
+				      : "cc");
+	}
+#endif
+		return hv_status;
+}
+
 /*
  * Rep hypercalls. Callers of this functions are supposed to ensure that
  * rep_count and varhead_size comply with Hyper-V hypercall definition.
-- 
cgit v1.2.3


From d8e6b232cfdd5d141c03e40a14c1c781480ea05e Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 22 Jun 2018 19:06:23 +0200
Subject: x86/hyper-v: Use 'fast' hypercall for HVCALL_SEND_IPI

Current Hyper-V TLFS (v5.0b) claims that HvCallSendSyntheticClusterIpi
hypercall can't be 'fast' (passing parameters through registers) but
apparently this is not true, Windows always uses 'fast' version. We can
do the same in Linux too.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: devel@linuxdriverproject.org
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Tianyu Lan <Tianyu.Lan@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Link: https://lkml.kernel.org/r/20180622170625.30688-3-vkuznets@redhat.com
---
 arch/x86/hyperv/hv_apic.c | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index f68855499391..90055f89223b 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -128,10 +128,8 @@ ipi_mask_ex_done:
 static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 {
 	int cur_cpu, vcpu;
-	struct ipi_arg_non_ex **arg;
-	struct ipi_arg_non_ex *ipi_arg;
+	struct ipi_arg_non_ex ipi_arg;
 	int ret = 1;
-	unsigned long flags;
 
 	if (cpumask_empty(mask))
 		return true;
@@ -145,16 +143,8 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
 		return __send_ipi_mask_ex(mask, vector);
 
-	local_irq_save(flags);
-	arg = (struct ipi_arg_non_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
-
-	ipi_arg = *arg;
-	if (unlikely(!ipi_arg))
-		goto ipi_mask_done;
-
-	ipi_arg->vector = vector;
-	ipi_arg->reserved = 0;
-	ipi_arg->cpu_mask = 0;
+	ipi_arg.vector = vector;
+	ipi_arg.cpu_mask = 0;
 
 	for_each_cpu(cur_cpu, mask) {
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
@@ -165,13 +155,13 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 		if (vcpu >= 64)
 			goto ipi_mask_done;
 
-		__set_bit(vcpu, (unsigned long *)&ipi_arg->cpu_mask);
+		__set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask);
 	}
 
-	ret = hv_do_hypercall(HVCALL_SEND_IPI, ipi_arg, NULL);
+	ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
+				     ipi_arg.cpu_mask);
 
 ipi_mask_done:
-	local_irq_restore(flags);
 	return ((ret == 0) ? true : false);
 }
 
-- 
cgit v1.2.3


From 4bd06060762bc7e4834ecf9daeb78834f7a29582 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 22 Jun 2018 19:06:24 +0200
Subject: x86/hyper-v: Use cheaper HVCALL_SEND_IPI hypercall when possible

When there is no need to send an IPI to a CPU with VP number > 64
we can do the job with fast HVCALL_SEND_IPI hypercall.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: devel@linuxdriverproject.org
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Tianyu Lan <Tianyu.Lan@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Link: https://lkml.kernel.org/r/20180622170625.30688-4-vkuznets@redhat.com
---
 arch/x86/hyperv/hv_apic.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 90055f89223b..ee962784d25b 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -99,6 +99,9 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector)
 	int nr_bank = 0;
 	int ret = 1;
 
+	if (!(ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
+		return false;
+
 	local_irq_save(flags);
 	arg = (struct ipi_arg_ex **)this_cpu_ptr(hyperv_pcpu_input_arg);
 
@@ -140,8 +143,18 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR))
 		return false;
 
-	if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-		return __send_ipi_mask_ex(mask, vector);
+	/*
+	 * From the supplied CPU set we need to figure out if we can get away
+	 * with cheaper HVCALL_SEND_IPI hypercall. This is possible when the
+	 * highest VP number in the set is < 64. As VP numbers are usually in
+	 * ascending order and match Linux CPU ids, here is an optimization:
+	 * we check the VP number for the highest bit in the supplied set first
+	 * so we can quickly find out if using HVCALL_SEND_IPI_EX hypercall is
+	 * a must. We will also check all VP numbers when walking the supplied
+	 * CPU set to remain correct in all cases.
+	 */
+	if (hv_cpu_number_to_vp_number(cpumask_last(mask)) >= 64)
+		goto do_ex_hypercall;
 
 	ipi_arg.vector = vector;
 	ipi_arg.cpu_mask = 0;
@@ -153,16 +166,17 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 		 * only target upto 64 CPUs.
 		 */
 		if (vcpu >= 64)
-			goto ipi_mask_done;
+			goto do_ex_hypercall;
 
 		__set_bit(vcpu, (unsigned long *)&ipi_arg.cpu_mask);
 	}
 
 	ret = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector,
 				     ipi_arg.cpu_mask);
-
-ipi_mask_done:
 	return ((ret == 0) ? true : false);
+
+do_ex_hypercall:
+	return __send_ipi_mask_ex(mask, vector);
 }
 
 static bool __send_ipi_one(int cpu, int vector)
@@ -218,10 +232,7 @@ static void hv_send_ipi_self(int vector)
 void __init hv_apic_init(void)
 {
 	if (ms_hyperv.hints & HV_X64_CLUSTER_IPI_RECOMMENDED) {
-		if ((ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED))
-			pr_info("Hyper-V: Using ext hypercalls for IPI\n");
-		else
-			pr_info("Hyper-V: Using IPI hypercalls\n");
+		pr_info("Hyper-V: Using IPI hypercalls\n");
 		/*
 		 * Set the IPI entry points.
 		 */
-- 
cgit v1.2.3


From 58ec5e9c9044bd7e1c0bcc6ad822b2e909f49732 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 22 Jun 2018 19:06:25 +0200
Subject: x86/hyper-v: Trace PV IPI send

Trace Hyper-V PV IPIs the same way we do PV TLB flush.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: devel@linuxdriverproject.org
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Tianyu Lan <Tianyu.Lan@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Link: https://lkml.kernel.org/r/20180622170625.30688-5-vkuznets@redhat.com
---
 arch/x86/hyperv/hv_apic.c           |  4 ++++
 arch/x86/include/asm/trace/hyperv.h | 15 +++++++++++++++
 2 files changed, 19 insertions(+)

diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index ee962784d25b..657a2b8c738a 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -31,6 +31,8 @@
 #include <asm/mshyperv.h>
 #include <asm/apic.h>
 
+#include <asm/trace/hyperv.h>
+
 static struct apic orig_apic;
 
 static u64 hv_apic_icr_read(void)
@@ -134,6 +136,8 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	struct ipi_arg_non_ex ipi_arg;
 	int ret = 1;
 
+	trace_hyperv_send_ipi_mask(mask, vector);
+
 	if (cpumask_empty(mask))
 		return true;
 
diff --git a/arch/x86/include/asm/trace/hyperv.h b/arch/x86/include/asm/trace/hyperv.h
index 4253bca99989..9c0d4b588e3f 100644
--- a/arch/x86/include/asm/trace/hyperv.h
+++ b/arch/x86/include/asm/trace/hyperv.h
@@ -28,6 +28,21 @@ TRACE_EVENT(hyperv_mmu_flush_tlb_others,
 		      __entry->addr, __entry->end)
 	);
 
+TRACE_EVENT(hyperv_send_ipi_mask,
+	    TP_PROTO(const struct cpumask *cpus,
+		     int vector),
+	    TP_ARGS(cpus, vector),
+	    TP_STRUCT__entry(
+		    __field(unsigned int, ncpus)
+		    __field(int, vector)
+		    ),
+	    TP_fast_assign(__entry->ncpus = cpumask_weight(cpus);
+			   __entry->vector = vector;
+		    ),
+	    TP_printk("ncpus %d vector %x",
+		      __entry->ncpus, __entry->vector)
+	);
+
 #endif /* CONFIG_HYPERV */
 
 #undef TRACE_INCLUDE_PATH
-- 
cgit v1.2.3


From b5722a457b6e5eabd97a7f39c6c2b8e9a623ab15 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 3 Jul 2018 10:50:13 +0900
Subject: x86/build/vdso: Remove unused vdso-syms.lds

This file contains symbol values, and was originally linked into
vmlinux, but I have no idea what it was actually used for.

Since the following commit:

  827880ec260b ("x86/um: thin archives build fix")

it is not even linked.  Now it is completely orphan, and no problem has
been reported.  It is a proof that this file was not needed in the
first place.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Richard Weinberger <richard@nod.at>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-um@lists.infradead.org
Link: http://lkml.kernel.org/r/1530582614-5173-2-git-send-email-yamada.masahiro@socionext.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/um/vdso/.gitignore |  1 -
 arch/x86/um/vdso/Makefile   | 16 ----------------
 2 files changed, 17 deletions(-)

diff --git a/arch/x86/um/vdso/.gitignore b/arch/x86/um/vdso/.gitignore
index 9cac6d072199..f8b69d84238e 100644
--- a/arch/x86/um/vdso/.gitignore
+++ b/arch/x86/um/vdso/.gitignore
@@ -1,2 +1 @@
-vdso-syms.lds
 vdso.lds
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
index b2d6967262b2..822ccdba93ad 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
@@ -53,22 +53,6 @@ $(vobjs): KBUILD_CFLAGS += $(CFL)
 CFLAGS_REMOVE_vdso-note.o = -pg -fprofile-arcs -ftest-coverage
 CFLAGS_REMOVE_um_vdso.o = -pg -fprofile-arcs -ftest-coverage
 
-targets += vdso-syms.lds
-extra-$(VDSO64-y)			+= vdso-syms.lds
-
-#
-# Match symbols in the DSO that look like VDSO*; produce a file of constants.
-#
-sed-vdsosym := -e 's/^00*/0/' \
-	-e 's/^\([0-9a-fA-F]*\) . \(VDSO[a-zA-Z0-9_]*\)$$/\2 = 0x\1;/p'
-quiet_cmd_vdsosym = VDSOSYM $@
-define cmd_vdsosym
-	$(NM) $< | LC_ALL=C sed -n $(sed-vdsosym) | LC_ALL=C sort > $@
-endef
-
-$(obj)/%-syms.lds: $(obj)/%.so.dbg FORCE
-	$(call if_changed,vdsosym)
-
 #
 # The DSO images are built using a special linker script.
 #
-- 
cgit v1.2.3


From c5fcdbf15523f6bbbaeb822e3be6003e60f9d3b7 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 3 Jul 2018 10:50:14 +0900
Subject: x86/build/vdso: Simplify 'cmd_vdso2c'

No reason to use 'define' directive here.  Just use the = operator.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1530582614-5173-3-git-send-email-yamada.masahiro@socionext.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/entry/vdso/Makefile | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 261802b1cc50..b9ed1aa53a26 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -58,9 +58,7 @@ HOST_EXTRACFLAGS += -I$(srctree)/tools/include -I$(srctree)/include/uapi -I$(src
 hostprogs-y			+= vdso2c
 
 quiet_cmd_vdso2c = VDSO2C  $@
-define cmd_vdso2c
-	$(obj)/vdso2c $< $(<:%.dbg=%) $@
-endef
+      cmd_vdso2c = $(obj)/vdso2c $< $(<:%.dbg=%) $@
 
 $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
 	$(call if_changed,vdso2c)
-- 
cgit v1.2.3


From 9cf57731b63e37ed995b46690adc604891a9a28f Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 7 Jun 2018 10:52:03 +0200
Subject: watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work

Oleg suggested to replace the "watchdog/%u" threads with
cpu_stop_work. That removes one thread per CPU while at the same time
fixes softlockup vs SCHED_DEADLINE.

But more importantly, it does away with the single
smpboot_update_cpumask_percpu_thread() user, which allows
cleanups/shrinkage of the smpboot interface.

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/cpuhotplug.h |   1 +
 include/linux/nmi.h        |   5 ++
 kernel/cpu.c               |   5 ++
 kernel/watchdog.c          | 137 ++++++++++++++++++++-------------------------
 4 files changed, 71 insertions(+), 77 deletions(-)

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 8796ba387152..4cf06a64bc02 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -164,6 +164,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
+	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index b8d868d23e79..80664bbeca43 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -33,10 +33,15 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
 #define sysctl_hardlockup_all_cpu_backtrace 0
 #endif /* !CONFIG_SMP */
 
+extern int lockup_detector_online_cpu(unsigned int cpu);
+extern int lockup_detector_offline_cpu(unsigned int cpu);
+
 #else /* CONFIG_LOCKUP_DETECTOR */
 static inline void lockup_detector_init(void) { }
 static inline void lockup_detector_soft_poweroff(void) { }
 static inline void lockup_detector_cleanup(void) { }
+#define lockup_detector_online_cpu	NULL
+#define lockup_detector_offline_cpu	NULL
 #endif /* !CONFIG_LOCKUP_DETECTOR */
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..191097c45fb1 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1344,6 +1344,11 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 		.startup.single		= perf_event_init_cpu,
 		.teardown.single	= perf_event_exit_cpu,
 	},
+	[CPUHP_AP_WATCHDOG_ONLINE] = {
+		.name			= "lockup_detector:online",
+		.startup.single		= lockup_detector_online_cpu,
+		.teardown.single	= lockup_detector_offline_cpu,
+	},
 	[CPUHP_AP_WORKQUEUE_ONLINE] = {
 		.name			= "workqueue:online",
 		.startup.single		= workqueue_online_cpu,
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 576d18045811..b81f777838d5 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -18,18 +18,14 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/sysctl.h>
-#include <linux/smpboot.h>
-#include <linux/sched/rt.h>
-#include <uapi/linux/sched/types.h>
 #include <linux/tick.h>
-#include <linux/workqueue.h>
 #include <linux/sched/clock.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/isolation.h>
+#include <linux/stop_machine.h>
 
 #include <asm/irq_regs.h>
 #include <linux/kvm_para.h>
-#include <linux/kthread.h>
 
 static DEFINE_MUTEX(watchdog_mutex);
 
@@ -169,11 +165,10 @@ static void lockup_detector_update_enable(void)
 unsigned int __read_mostly softlockup_panic =
 			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
-static bool softlockup_threads_initialized __read_mostly;
+static bool softlockup_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
-static DEFINE_PER_CPU(struct task_struct *, softlockup_watchdog);
 static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer);
 static DEFINE_PER_CPU(bool, softlockup_touch_sync);
 static DEFINE_PER_CPU(bool, soft_watchdog_warn);
@@ -335,6 +330,25 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
+/*
+ * The watchdog thread function - touches the timestamp.
+ *
+ * It only runs once every sample_period seconds (4 seconds by
+ * default) to reset the softlockup timestamp. If this gets delayed
+ * for more than 2*watchdog_thresh seconds then the debug-printout
+ * triggers in watchdog_timer_fn().
+ */
+static int softlockup_fn(void *data)
+{
+	__this_cpu_write(soft_lockup_hrtimer_cnt,
+			 __this_cpu_read(hrtimer_interrupts));
+	__touch_watchdog();
+
+	return 0;
+}
+
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -350,7 +364,9 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	watchdog_interrupt_count();
 
 	/* kick the softlockup detector */
-	wake_up_process(__this_cpu_read(softlockup_watchdog));
+	stop_one_cpu_nowait(smp_processor_id(),
+			softlockup_fn, NULL,
+			this_cpu_ptr(&softlockup_stop_work));
 
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
@@ -448,17 +464,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
-static void watchdog_set_prio(unsigned int policy, unsigned int prio)
-{
-	struct sched_param param = { .sched_priority = prio };
-
-	sched_setscheduler(current, policy, &param);
-}
-
 static void watchdog_enable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	/*
 	 * Start the timer first to prevent the NMI watchdog triggering
 	 * before the timer has a chance to fire.
@@ -473,15 +484,14 @@ static void watchdog_enable(unsigned int cpu)
 	/* Enable the perf event */
 	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
 		watchdog_nmi_enable(cpu);
-
-	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
 
 static void watchdog_disable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
-	watchdog_set_prio(SCHED_NORMAL, 0);
+	WARN_ON_ONCE(cpu != smp_processor_id());
+
 	/*
 	 * Disable the perf event first. That prevents that a large delay
 	 * between disabling the timer and disabling the perf event causes
@@ -491,77 +501,63 @@ static void watchdog_disable(unsigned int cpu)
 	hrtimer_cancel(hrtimer);
 }
 
-static void watchdog_cleanup(unsigned int cpu, bool online)
+static int softlockup_stop_fn(void *data)
 {
-	watchdog_disable(cpu);
+	watchdog_disable(smp_processor_id());
+	return 0;
 }
 
-static int watchdog_should_run(unsigned int cpu)
+static void softlockup_stop_all(void)
 {
-	return __this_cpu_read(hrtimer_interrupts) !=
-		__this_cpu_read(soft_lockup_hrtimer_cnt);
+	int cpu;
+
+	if (!softlockup_initialized)
+		return;
+
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false);
+
+	cpumask_clear(&watchdog_allowed_mask);
 }
 
-/*
- * The watchdog thread function - touches the timestamp.
- *
- * It only runs once every sample_period seconds (4 seconds by
- * default) to reset the softlockup timestamp. If this gets delayed
- * for more than 2*watchdog_thresh seconds then the debug-printout
- * triggers in watchdog_timer_fn().
- */
-static void watchdog(unsigned int cpu)
+static int softlockup_start_fn(void *data)
 {
-	__this_cpu_write(soft_lockup_hrtimer_cnt,
-			 __this_cpu_read(hrtimer_interrupts));
-	__touch_watchdog();
+	watchdog_enable(smp_processor_id());
+	return 0;
 }
 
-static struct smp_hotplug_thread watchdog_threads = {
-	.store			= &softlockup_watchdog,
-	.thread_should_run	= watchdog_should_run,
-	.thread_fn		= watchdog,
-	.thread_comm		= "watchdog/%u",
-	.setup			= watchdog_enable,
-	.cleanup		= watchdog_cleanup,
-	.park			= watchdog_disable,
-	.unpark			= watchdog_enable,
-};
-
-static void softlockup_update_smpboot_threads(void)
+static void softlockup_start_all(void)
 {
-	lockdep_assert_held(&watchdog_mutex);
-
-	if (!softlockup_threads_initialized)
-		return;
+	int cpu;
 
-	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
-					     &watchdog_allowed_mask);
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	for_each_cpu(cpu, &watchdog_allowed_mask)
+		smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false);
 }
 
-/* Temporarily park all watchdog threads */
-static void softlockup_park_all_threads(void)
+int lockup_detector_online_cpu(unsigned int cpu)
 {
-	cpumask_clear(&watchdog_allowed_mask);
-	softlockup_update_smpboot_threads();
+	watchdog_enable(cpu);
+	return 0;
 }
 
-/* Unpark enabled threads */
-static void softlockup_unpark_threads(void)
+int lockup_detector_offline_cpu(unsigned int cpu)
 {
-	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
-	softlockup_update_smpboot_threads();
+	watchdog_disable(cpu);
+	return 0;
 }
 
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
 	watchdog_nmi_stop();
-	softlockup_park_all_threads();
+
+	softlockup_stop_all();
 	set_sample_period();
 	lockup_detector_update_enable();
 	if (watchdog_enabled && watchdog_thresh)
-		softlockup_unpark_threads();
+		softlockup_start_all();
+
 	watchdog_nmi_start();
 	cpus_read_unlock();
 	/*
@@ -580,8 +576,6 @@ static void lockup_detector_reconfigure(void)
  */
 static __init void lockup_detector_setup(void)
 {
-	int ret;
-
 	/*
 	 * If sysctl is off and watchdog got disabled on the command line,
 	 * nothing to do here.
@@ -592,24 +586,13 @@ static __init void lockup_detector_setup(void)
 	    !(watchdog_enabled && watchdog_thresh))
 		return;
 
-	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-						     &watchdog_allowed_mask);
-	if (ret) {
-		pr_err("Failed to initialize soft lockup detector threads\n");
-		return;
-	}
-
 	mutex_lock(&watchdog_mutex);
-	softlockup_threads_initialized = true;
 	lockup_detector_reconfigure();
+	softlockup_initialized = true;
 	mutex_unlock(&watchdog_mutex);
 }
 
 #else /* CONFIG_SOFTLOCKUP_DETECTOR */
-static inline int watchdog_park_threads(void) { return 0; }
-static inline void watchdog_unpark_threads(void) { }
-static inline int watchdog_enable_all_cpus(void) { return 0; }
-static inline void watchdog_disable_all_cpus(void) { }
 static void lockup_detector_reconfigure(void)
 {
 	cpus_read_lock();
-- 
cgit v1.2.3


From 167a88677b05d6a810f23b871cfb2b5db1808e60 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 7 Jun 2018 10:53:01 +0200
Subject: smpboot: Remove cpumask from the API

Now that the sole use of the whole smpboot_*cpumask() API is gone,
remove it.

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/smpboot.h | 15 +-------------
 kernel/smpboot.c        | 54 +++++--------------------------------------------
 2 files changed, 6 insertions(+), 63 deletions(-)

diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index c174844cf663..d0884b525001 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -25,8 +25,6 @@ struct smpboot_thread_data;
  *			parked (cpu offline)
  * @unpark:		Optional unpark function, called when the thread is
  *			unparked (cpu online)
- * @cpumask:		Internal state.  To update which threads are unparked,
- *			call smpboot_update_cpumask_percpu_thread().
  * @selfparking:	Thread is not parked by the park function.
  * @thread_comm:	The base name of the thread
  */
@@ -40,23 +38,12 @@ struct smp_hotplug_thread {
 	void				(*cleanup)(unsigned int cpu, bool online);
 	void				(*park)(unsigned int cpu);
 	void				(*unpark)(unsigned int cpu);
-	cpumask_var_t			cpumask;
 	bool				selfparking;
 	const char			*thread_comm;
 };
 
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask);
-
-static inline int
-smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
-{
-	return smpboot_register_percpu_thread_cpumask(plug_thread,
-						      cpu_possible_mask);
-}
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
 
 void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *);
 
 #endif
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 5043e7433f4b..c230c2dd48e1 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -238,8 +238,7 @@ int smpboot_unpark_threads(unsigned int cpu)
 
 	mutex_lock(&smpboot_threads_lock);
 	list_for_each_entry(cur, &hotplug_threads, list)
-		if (cpumask_test_cpu(cpu, cur->cpumask))
-			smpboot_unpark_thread(cur, cpu);
+		smpboot_unpark_thread(cur, cpu);
 	mutex_unlock(&smpboot_threads_lock);
 	return 0;
 }
@@ -280,34 +279,26 @@ static void smpboot_destroy_threads(struct smp_hotplug_thread *ht)
 }
 
 /**
- * smpboot_register_percpu_thread_cpumask - Register a per_cpu thread related
+ * smpboot_register_percpu_thread - Register a per_cpu thread related
  * 					    to hotplug
  * @plug_thread:	Hotplug thread descriptor
- * @cpumask:		The cpumask where threads run
  *
  * Creates and starts the threads on all online cpus.
  */
-int smpboot_register_percpu_thread_cpumask(struct smp_hotplug_thread *plug_thread,
-					   const struct cpumask *cpumask)
+int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 {
 	unsigned int cpu;
 	int ret = 0;
 
-	if (!alloc_cpumask_var(&plug_thread->cpumask, GFP_KERNEL))
-		return -ENOMEM;
-	cpumask_copy(plug_thread->cpumask, cpumask);
-
 	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
 		ret = __smpboot_create_thread(plug_thread, cpu);
 		if (ret) {
 			smpboot_destroy_threads(plug_thread);
-			free_cpumask_var(plug_thread->cpumask);
 			goto out;
 		}
-		if (cpumask_test_cpu(cpu, cpumask))
-			smpboot_unpark_thread(plug_thread, cpu);
+		smpboot_unpark_thread(plug_thread, cpu);
 	}
 	list_add(&plug_thread->list, &hotplug_threads);
 out:
@@ -315,7 +306,7 @@ out:
 	put_online_cpus();
 	return ret;
 }
-EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread_cpumask);
+EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
 
 /**
  * smpboot_unregister_percpu_thread - Unregister a per_cpu thread related to hotplug
@@ -331,44 +322,9 @@ void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread)
 	smpboot_destroy_threads(plug_thread);
 	mutex_unlock(&smpboot_threads_lock);
 	put_online_cpus();
-	free_cpumask_var(plug_thread->cpumask);
 }
 EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
 
-/**
- * smpboot_update_cpumask_percpu_thread - Adjust which per_cpu hotplug threads stay parked
- * @plug_thread:	Hotplug thread descriptor
- * @new:		Revised mask to use
- *
- * The cpumask field in the smp_hotplug_thread must not be updated directly
- * by the client, but only by calling this function.
- * This function can only be called on a registered smp_hotplug_thread.
- */
-void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					  const struct cpumask *new)
-{
-	struct cpumask *old = plug_thread->cpumask;
-	static struct cpumask tmp;
-	unsigned int cpu;
-
-	lockdep_assert_cpus_held();
-	mutex_lock(&smpboot_threads_lock);
-
-	/* Park threads that were exclusively enabled on the old mask. */
-	cpumask_andnot(&tmp, old, new);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_park_thread(plug_thread, cpu);
-
-	/* Unpark threads that are exclusively enabled on the new mask. */
-	cpumask_andnot(&tmp, new, old);
-	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
-		smpboot_unpark_thread(plug_thread, cpu);
-
-	cpumask_copy(old, new);
-
-	mutex_unlock(&smpboot_threads_lock);
-}
-
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
 /*
-- 
cgit v1.2.3


From f83ee19be4272564ad592ef90145db7295229490 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 7 Jun 2018 10:55:56 +0200
Subject: kthread: Simplify kthread_park() completion

Oleg explains the reason we could hit park+park is that
smpboot_update_cpumask_percpu_thread()'s

  for_each_cpu_and(cpu, &tmp, cpu_online_mask)
	smpboot_park_kthread();

turns into:

  for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)and)
	smpboot_park_kthread();

on UP, ignoring the mask. But since we just completely removed that
function, this is no longer relevant.

So revert commit:

  b1f5b378e126 ("kthread: Allow kthread_park() on a parked kthread")

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/kthread.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/kthread.c b/kernel/kthread.c
index 750cb8082694..11b591ee51ab 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -190,7 +190,7 @@ static void __kthread_parkme(struct kthread *self)
 		if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
 			break;
 
-		complete_all(&self->parked);
+		complete(&self->parked);
 		schedule();
 	}
 	__set_current_state(TASK_RUNNING);
@@ -465,7 +465,6 @@ void kthread_unpark(struct task_struct *k)
 	if (test_bit(KTHREAD_IS_PER_CPU, &kthread->flags))
 		__kthread_bind(k, kthread->cpu, TASK_PARKED);
 
-	reinit_completion(&kthread->parked);
 	clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	/*
 	 * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
@@ -493,6 +492,9 @@ int kthread_park(struct task_struct *k)
 	if (WARN_ON(k->flags & PF_EXITING))
 		return -ENOSYS;
 
+	if (WARN_ON_ONCE(test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)))
+		return -EBUSY;
+
 	set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
 	if (k != current) {
 		wake_up_process(k);
-- 
cgit v1.2.3


From 070473bcf703366e9acb14e172d5b6563cc07a26 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 2 Jul 2018 17:21:23 +0100
Subject: drm: add missing ctx argument to plane transitional helpers

In commits:
34a2ab5e0689 ("drm: Add acquire ctx parameter to ->update_plane")
1931529448bc ("drm: Add acquire ctx parameter to ->plane_disable")

a pointer to a drm_modeset_acquire_ctx structure was added as an
argument to the method prototypes.  The transitional helpers are
supposed to be directly plugged in as implementations of these
methods, but doing so generates a warning.  Add the missing
argument.

A number of buggy users were added for drm_plane_helper_disable()
which need to be fixed up for this change, which we do by passing
a NULL ctx argument.

Fixes: 1931529448bc ("drm: Add acquire ctx parameter to ->plane_disable")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/E1fa1Zr-0005gT-VF@rmk-PC.armlinux.org.uk
---
 drivers/gpu/drm/arc/arcpgu_crtc.c          | 2 +-
 drivers/gpu/drm/arm/hdlcd_crtc.c           | 2 +-
 drivers/gpu/drm/drm_plane_helper.c         | 8 ++++++--
 drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c | 2 +-
 drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c | 2 +-
 drivers/gpu/drm/sti/sti_cursor.c           | 2 +-
 drivers/gpu/drm/sti/sti_gdp.c              | 2 +-
 drivers/gpu/drm/sti/sti_hqvdp.c            | 2 +-
 drivers/gpu/drm/vc4/vc4_plane.c            | 2 +-
 drivers/gpu/drm/zte/zx_plane.c             | 2 +-
 include/drm/drm_plane_helper.h             | 6 ++++--
 11 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/arc/arcpgu_crtc.c b/drivers/gpu/drm/arc/arcpgu_crtc.c
index c3349b8fb58b..965cda48dc13 100644
--- a/drivers/gpu/drm/arc/arcpgu_crtc.c
+++ b/drivers/gpu/drm/arc/arcpgu_crtc.c
@@ -186,7 +186,7 @@ static const struct drm_plane_helper_funcs arc_pgu_plane_helper_funcs = {
 
 static void arc_pgu_plane_destroy(struct drm_plane *plane)
 {
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 }
 
diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index cf5cbd63ecdf..f3f08cd6e9ef 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -282,7 +282,7 @@ static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = {
 
 static void hdlcd_plane_destroy(struct drm_plane *plane)
 {
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 }
 
diff --git a/drivers/gpu/drm/drm_plane_helper.c b/drivers/gpu/drm/drm_plane_helper.c
index 2010794943bc..621f17643bb0 100644
--- a/drivers/gpu/drm/drm_plane_helper.c
+++ b/drivers/gpu/drm/drm_plane_helper.c
@@ -440,6 +440,7 @@ out:
  * @src_y: y offset of @fb for panning
  * @src_w: width of source rectangle in @fb
  * @src_h: height of source rectangle in @fb
+ * @ctx: lock acquire context, not used here
  *
  * Provides a default plane update handler using the atomic plane update
  * functions. It is fully left to the driver to check plane constraints and
@@ -455,7 +456,8 @@ int drm_plane_helper_update(struct drm_plane *plane, struct drm_crtc *crtc,
 			    int crtc_x, int crtc_y,
 			    unsigned int crtc_w, unsigned int crtc_h,
 			    uint32_t src_x, uint32_t src_y,
-			    uint32_t src_w, uint32_t src_h)
+			    uint32_t src_w, uint32_t src_h,
+			    struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_plane_state *plane_state;
 
@@ -489,6 +491,7 @@ EXPORT_SYMBOL(drm_plane_helper_update);
 /**
  * drm_plane_helper_disable() - Transitional helper for plane disable
  * @plane: plane to disable
+ * @ctx: lock acquire context, not used here
  *
  * Provides a default plane disable handler using the atomic plane update
  * functions. It is fully left to the driver to check plane constraints and
@@ -499,7 +502,8 @@ EXPORT_SYMBOL(drm_plane_helper_update);
  * RETURNS:
  * Zero on success, error code on failure
  */
-int drm_plane_helper_disable(struct drm_plane *plane)
+int drm_plane_helper_disable(struct drm_plane *plane,
+			     struct drm_modeset_acquire_ctx *ctx)
 {
 	struct drm_plane_state *plane_state;
 	struct drm_framebuffer *old_fb;
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
index 7b641fa6dc4d..79ff653d8081 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_plane.c
@@ -68,7 +68,7 @@ static void mdp4_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp4_plane *mdp4_plane = to_mdp4_plane(plane);
 
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 
 	kfree(mdp4_plane);
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
index c4f115fe96ff..7d306c5acd09 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_plane.c
@@ -46,7 +46,7 @@ static void mdp5_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
 
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 
 	kfree(mdp5_plane);
diff --git a/drivers/gpu/drm/sti/sti_cursor.c b/drivers/gpu/drm/sti/sti_cursor.c
index df0a282b9615..57b870e1e696 100644
--- a/drivers/gpu/drm/sti/sti_cursor.c
+++ b/drivers/gpu/drm/sti/sti_cursor.c
@@ -332,7 +332,7 @@ static void sti_cursor_destroy(struct drm_plane *drm_plane)
 {
 	DRM_DEBUG_DRIVER("\n");
 
-	drm_plane_helper_disable(drm_plane);
+	drm_plane_helper_disable(drm_plane, NULL);
 	drm_plane_cleanup(drm_plane);
 }
 
diff --git a/drivers/gpu/drm/sti/sti_gdp.c b/drivers/gpu/drm/sti/sti_gdp.c
index 49813d34bdf0..c32de6cbf061 100644
--- a/drivers/gpu/drm/sti/sti_gdp.c
+++ b/drivers/gpu/drm/sti/sti_gdp.c
@@ -883,7 +883,7 @@ static void sti_gdp_destroy(struct drm_plane *drm_plane)
 {
 	DRM_DEBUG_DRIVER("\n");
 
-	drm_plane_helper_disable(drm_plane);
+	drm_plane_helper_disable(drm_plane, NULL);
 	drm_plane_cleanup(drm_plane);
 }
 
diff --git a/drivers/gpu/drm/sti/sti_hqvdp.c b/drivers/gpu/drm/sti/sti_hqvdp.c
index 106be8c4e58b..03ac3b4a4469 100644
--- a/drivers/gpu/drm/sti/sti_hqvdp.c
+++ b/drivers/gpu/drm/sti/sti_hqvdp.c
@@ -1260,7 +1260,7 @@ static void sti_hqvdp_destroy(struct drm_plane *drm_plane)
 {
 	DRM_DEBUG_DRIVER("\n");
 
-	drm_plane_helper_disable(drm_plane);
+	drm_plane_helper_disable(drm_plane, NULL);
 	drm_plane_cleanup(drm_plane);
 }
 
diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 8604fd2e7c5a..9d7a36f148cf 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -902,7 +902,7 @@ static const struct drm_plane_helper_funcs vc4_plane_helper_funcs = {
 
 static void vc4_plane_destroy(struct drm_plane *plane)
 {
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 }
 
diff --git a/drivers/gpu/drm/zte/zx_plane.c b/drivers/gpu/drm/zte/zx_plane.c
index d1931f5ea0b2..ae8c53b4b261 100644
--- a/drivers/gpu/drm/zte/zx_plane.c
+++ b/drivers/gpu/drm/zte/zx_plane.c
@@ -446,7 +446,7 @@ static const struct drm_plane_helper_funcs zx_gl_plane_helper_funcs = {
 
 static void zx_plane_destroy(struct drm_plane *plane)
 {
-	drm_plane_helper_disable(plane);
+	drm_plane_helper_disable(plane, NULL);
 	drm_plane_cleanup(plane);
 }
 
diff --git a/include/drm/drm_plane_helper.h b/include/drm/drm_plane_helper.h
index 28d7ce620729..26cee2934781 100644
--- a/include/drm/drm_plane_helper.h
+++ b/include/drm/drm_plane_helper.h
@@ -67,8 +67,10 @@ int drm_plane_helper_update(struct drm_plane *plane, struct drm_crtc *crtc,
 			    int crtc_x, int crtc_y,
 			    unsigned int crtc_w, unsigned int crtc_h,
 			    uint32_t src_x, uint32_t src_y,
-			    uint32_t src_w, uint32_t src_h);
-int drm_plane_helper_disable(struct drm_plane *plane);
+			    uint32_t src_w, uint32_t src_h,
+			    struct drm_modeset_acquire_ctx *ctx);
+int drm_plane_helper_disable(struct drm_plane *plane,
+			     struct drm_modeset_acquire_ctx *ctx);
 
 /* For use by drm_crtc_helper.c */
 int drm_plane_helper_commit(struct drm_plane *plane,
-- 
cgit v1.2.3


From 55f036ca7e74b85e34958af3d22121c656796413 Mon Sep 17 00:00:00 2001
From: Peter Ziljstra <peterz@infradead.org>
Date: Fri, 15 Jun 2018 10:07:12 +0200
Subject: locking: WW mutex cleanup

Make the WW mutex code more readable by adding comments, splitting up
functions and pointing out that we're actually using the Wait-Die
algorithm.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: David Airlie <airlied@linux.ie>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-doc@vger.kernel.org
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Co-authored-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/locking/ww-mutex-design.txt |  12 +-
 include/linux/ww_mutex.h                  |  28 ++---
 kernel/locking/mutex.c                    | 202 ++++++++++++++++++------------
 3 files changed, 145 insertions(+), 97 deletions(-)

diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt
index 34c3a1b50b9a..2fd7f2a2af21 100644
--- a/Documentation/locking/ww-mutex-design.txt
+++ b/Documentation/locking/ww-mutex-design.txt
@@ -32,10 +32,10 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the
 younger task) unlocks all of the buffers that it has already locked, and then
 tries again.
 
-In the RDBMS literature this deadlock handling approach is called wait/wound:
+In the RDBMS literature this deadlock handling approach is called wait/die:
 The older tasks waits until it can acquire the contended lock. The younger tasks
 needs to back off and drop all the locks it is currently holding, i.e. the
-younger task is wounded.
+younger task dies.
 
 Concepts
 --------
@@ -56,9 +56,9 @@ Furthermore there are three different class of w/w lock acquire functions:
 
 * Normal lock acquisition with a context, using ww_mutex_lock.
 
-* Slowpath lock acquisition on the contending lock, used by the wounded task
-  after having dropped all already acquired locks. These functions have the
-  _slow postfix.
+* Slowpath lock acquisition on the contending lock, used by the task that just
+  killed its transaction after having dropped all already acquired locks.
+  These functions have the _slow postfix.
 
   From a simple semantics point-of-view the _slow functions are not strictly
   required, since simply calling the normal ww_mutex_lock functions on the
@@ -220,7 +220,7 @@ mutexes are a natural fit for such a case for two reasons:
 
 Note that this approach differs in two important ways from the above methods:
 - Since the list of objects is dynamically constructed (and might very well be
-  different when retrying due to hitting the -EDEADLK wound condition) there's
+  different when retrying due to hitting the -EDEADLK die condition) there's
   no need to keep any object on a persistent list when it's not locked. We can
   therefore move the list_head into the object itself.
 - On the other hand the dynamic object list construction also means that the -EALREADY return
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 39fda195bf78..f82fce2229c8 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -6,7 +6,7 @@
  *
  *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  *
- * Wound/wait implementation:
+ * Wait/Die implementation:
  *  Copyright (C) 2013 Canonical Ltd.
  *
  * This file contains the main data structure and API definitions.
@@ -28,9 +28,9 @@ struct ww_class {
 struct ww_acquire_ctx {
 	struct task_struct *task;
 	unsigned long stamp;
-	unsigned acquired;
+	unsigned int acquired;
 #ifdef CONFIG_DEBUG_MUTEXES
-	unsigned done_acquire;
+	unsigned int done_acquire;
 	struct ww_class *ww_class;
 	struct ww_mutex *contending_lock;
 #endif
@@ -38,8 +38,8 @@ struct ww_acquire_ctx {
 	struct lockdep_map dep_map;
 #endif
 #ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH
-	unsigned deadlock_inject_interval;
-	unsigned deadlock_inject_countdown;
+	unsigned int deadlock_inject_interval;
+	unsigned int deadlock_inject_countdown;
 #endif
 };
 
@@ -102,7 +102,7 @@ static inline void ww_mutex_init(struct ww_mutex *lock,
  *
  * Context-based w/w mutex acquiring can be done in any order whatsoever within
  * a given lock class. Deadlocks will be detected and handled with the
- * wait/wound logic.
+ * wait/die logic.
  *
  * Mixing of context-based w/w mutex acquiring and single w/w mutex locking can
  * result in undetected deadlocks and is so forbidden. Mixing different contexts
@@ -195,13 +195,13 @@ static inline void ww_acquire_fini(struct ww_acquire_ctx *ctx)
  * Lock the w/w mutex exclusively for this task.
  *
  * Deadlocks within a given w/w class of locks are detected and handled with the
- * wait/wound algorithm. If the lock isn't immediately avaiable this function
+ * wait/die algorithm. If the lock isn't immediately available this function
  * will either sleep until it is (wait case). Or it selects the current context
- * for backing off by returning -EDEADLK (wound case). Trying to acquire the
+ * for backing off by returning -EDEADLK (die case). Trying to acquire the
  * same lock with the same context twice is also detected and signalled by
  * returning -EALREADY. Returns 0 if the mutex was successfully acquired.
  *
- * In the wound case the caller must release all currently held w/w mutexes for
+ * In the die case the caller must release all currently held w/w mutexes for
  * the given context and then wait for this contending lock to be available by
  * calling ww_mutex_lock_slow. Alternatively callers can opt to not acquire this
  * lock and proceed with trying to acquire further w/w mutexes (e.g. when
@@ -226,14 +226,14 @@ extern int /* __must_check */ ww_mutex_lock(struct ww_mutex *lock, struct ww_acq
  * Lock the w/w mutex exclusively for this task.
  *
  * Deadlocks within a given w/w class of locks are detected and handled with the
- * wait/wound algorithm. If the lock isn't immediately avaiable this function
+ * wait/die algorithm. If the lock isn't immediately available this function
  * will either sleep until it is (wait case). Or it selects the current context
- * for backing off by returning -EDEADLK (wound case). Trying to acquire the
+ * for backing off by returning -EDEADLK (die case). Trying to acquire the
  * same lock with the same context twice is also detected and signalled by
  * returning -EALREADY. Returns 0 if the mutex was successfully acquired. If a
  * signal arrives while waiting for the lock then this function returns -EINTR.
  *
- * In the wound case the caller must release all currently held w/w mutexes for
+ * In the die case the caller must release all currently held w/w mutexes for
  * the given context and then wait for this contending lock to be available by
  * calling ww_mutex_lock_slow_interruptible. Alternatively callers can opt to
  * not acquire this lock and proceed with trying to acquire further w/w mutexes
@@ -256,7 +256,7 @@ extern int __must_check ww_mutex_lock_interruptible(struct ww_mutex *lock,
  * @lock: the mutex to be acquired
  * @ctx: w/w acquire context
  *
- * Acquires a w/w mutex with the given context after a wound case. This function
+ * Acquires a w/w mutex with the given context after a die case. This function
  * will sleep until the lock becomes available.
  *
  * The caller must have released all w/w mutexes already acquired with the
@@ -290,7 +290,7 @@ ww_mutex_lock_slow(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
  * @lock: the mutex to be acquired
  * @ctx: w/w acquire context
  *
- * Acquires a w/w mutex with the given context after a wound case. This function
+ * Acquires a w/w mutex with the given context after a die case. This function
  * will sleep until the lock becomes available and returns 0 when the lock has
  * been acquired. If a signal arrives while waiting for the lock then this
  * function returns -EINTR.
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index f44f658ae629..cfe48419b7d0 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -244,6 +244,17 @@ void __sched mutex_lock(struct mutex *lock)
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
+/*
+ * Wait-Die:
+ *   The newer transactions are killed when:
+ *     It (the new transaction) makes a request for a lock being held
+ *     by an older transaction.
+ */
+
+/*
+ * Associate the ww_mutex @ww with the context @ww_ctx under which we acquired
+ * it.
+ */
 static __always_inline void
 ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
 {
@@ -282,26 +293,53 @@ ww_mutex_lock_acquired(struct ww_mutex *ww, struct ww_acquire_ctx *ww_ctx)
 	DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class);
 #endif
 	ww_ctx->acquired++;
+	ww->ctx = ww_ctx;
 }
 
+/*
+ * Determine if context @a is 'after' context @b. IOW, @a is a younger
+ * transaction than @b and depending on algorithm either needs to wait for
+ * @b or die.
+ */
 static inline bool __sched
 __ww_ctx_stamp_after(struct ww_acquire_ctx *a, struct ww_acquire_ctx *b)
 {
-	return a->stamp - b->stamp <= LONG_MAX &&
-	       (a->stamp != b->stamp || a > b);
+
+	return (signed long)(a->stamp - b->stamp) > 0;
+}
+
+/*
+ * Wait-Die; wake a younger waiter context (when locks held) such that it can
+ * die.
+ *
+ * Among waiters with context, only the first one can have other locks acquired
+ * already (ctx->acquired > 0), because __ww_mutex_add_waiter() and
+ * __ww_mutex_check_kill() wake any but the earliest context.
+ */
+static bool __sched
+__ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter,
+	       struct ww_acquire_ctx *ww_ctx)
+{
+	if (waiter->ww_ctx->acquired > 0 &&
+			__ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) {
+		debug_mutex_wake_waiter(lock, waiter);
+		wake_up_process(waiter->task);
+	}
+
+	return true;
 }
 
 /*
- * Wake up any waiters that may have to back off when the lock is held by the
- * given context.
+ * We just acquired @lock under @ww_ctx, if there are later contexts waiting
+ * behind us on the wait-list, check if they need to die.
  *
- * Due to the invariants on the wait list, this can only affect the first
- * waiter with a context.
+ * See __ww_mutex_add_waiter() for the list-order construction; basically the
+ * list is ordered by stamp, smallest (oldest) first.
  *
  * The current task must not be on the wait list.
  */
 static void __sched
-__ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
+__ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
 {
 	struct mutex_waiter *cur;
 
@@ -311,30 +349,23 @@ __ww_mutex_wakeup_for_backoff(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
 		if (!cur->ww_ctx)
 			continue;
 
-		if (cur->ww_ctx->acquired > 0 &&
-		    __ww_ctx_stamp_after(cur->ww_ctx, ww_ctx)) {
-			debug_mutex_wake_waiter(lock, cur);
-			wake_up_process(cur->task);
-		}
-
-		break;
+		if (__ww_mutex_die(lock, cur, ww_ctx))
+			break;
 	}
 }
 
 /*
- * After acquiring lock with fastpath or when we lost out in contested
- * slowpath, set ctx and wake up any waiters so they can recheck.
+ * After acquiring lock with fastpath, where we do not hold wait_lock, set ctx
+ * and wake up any waiters so they can recheck.
  */
 static __always_inline void
 ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
 	ww_mutex_lock_acquired(lock, ctx);
 
-	lock->ctx = ctx;
-
 	/*
 	 * The lock->ctx update should be visible on all cores before
-	 * the atomic read is done, otherwise contended waiters might be
+	 * the WAITERS check is done, otherwise contended waiters might be
 	 * missed. The contended waiters will either see ww_ctx == NULL
 	 * and keep spinning, or it will acquire wait_lock, add itself
 	 * to waiter list and sleep.
@@ -348,29 +379,14 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 		return;
 
 	/*
-	 * Uh oh, we raced in fastpath, wake up everyone in this case,
-	 * so they can see the new lock->ctx.
+	 * Uh oh, we raced in fastpath, check if any of the waiters need to
+	 * die.
 	 */
 	spin_lock(&lock->base.wait_lock);
-	__ww_mutex_wakeup_for_backoff(&lock->base, ctx);
+	__ww_mutex_check_waiters(&lock->base, ctx);
 	spin_unlock(&lock->base.wait_lock);
 }
 
-/*
- * After acquiring lock in the slowpath set ctx.
- *
- * Unlike for the fast path, the caller ensures that waiters are woken up where
- * necessary.
- *
- * Callers must hold the mutex wait_lock.
- */
-static __always_inline void
-ww_mutex_set_context_slowpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
-{
-	ww_mutex_lock_acquired(lock, ctx);
-	lock->ctx = ctx;
-}
-
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 
 static inline
@@ -646,37 +662,73 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
 }
 EXPORT_SYMBOL(ww_mutex_unlock);
 
+
+static __always_inline int __sched
+__ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
+{
+	if (ww_ctx->acquired > 0) {
+#ifdef CONFIG_DEBUG_MUTEXES
+		struct ww_mutex *ww;
+
+		ww = container_of(lock, struct ww_mutex, base);
+		DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
+		ww_ctx->contending_lock = ww;
+#endif
+		return -EDEADLK;
+	}
+
+	return 0;
+}
+
+
+/*
+ * Check whether we need to kill the transaction for the current lock acquire.
+ *
+ * Wait-Die: If we're trying to acquire a lock already held by an older
+ *           context, kill ourselves.
+ *
+ * Since __ww_mutex_add_waiter() orders the wait-list on stamp, we only have to
+ * look at waiters before us in the wait-list.
+ */
 static inline int __sched
-__ww_mutex_lock_check_stamp(struct mutex *lock, struct mutex_waiter *waiter,
-			    struct ww_acquire_ctx *ctx)
+__ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter,
+		      struct ww_acquire_ctx *ctx)
 {
 	struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
 	struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx);
 	struct mutex_waiter *cur;
 
+	if (ctx->acquired == 0)
+		return 0;
+
 	if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))
-		goto deadlock;
+		return __ww_mutex_kill(lock, ctx);
 
 	/*
 	 * If there is a waiter in front of us that has a context, then its
-	 * stamp is earlier than ours and we must back off.
+	 * stamp is earlier than ours and we must kill ourself.
 	 */
 	cur = waiter;
 	list_for_each_entry_continue_reverse(cur, &lock->wait_list, list) {
-		if (cur->ww_ctx)
-			goto deadlock;
+		if (!cur->ww_ctx)
+			continue;
+
+		return __ww_mutex_kill(lock, ctx);
 	}
 
 	return 0;
-
-deadlock:
-#ifdef CONFIG_DEBUG_MUTEXES
-	DEBUG_LOCKS_WARN_ON(ctx->contending_lock);
-	ctx->contending_lock = ww;
-#endif
-	return -EDEADLK;
 }
 
+/*
+ * Add @waiter to the wait-list, keep the wait-list ordered by stamp, smallest
+ * first. Such that older contexts are preferred to acquire the lock over
+ * younger contexts.
+ *
+ * Waiters without context are interspersed in FIFO order.
+ *
+ * Furthermore, for Wait-Die kill ourself immediately when possible (there are
+ * older contexts already waiting) to avoid unnecessary waiting.
+ */
 static inline int __sched
 __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 		      struct mutex *lock,
@@ -693,7 +745,7 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 	/*
 	 * Add the waiter before the first waiter with a higher stamp.
 	 * Waiters without a context are skipped to avoid starving
-	 * them.
+	 * them. Wait-Die waiters may die here.
 	 */
 	pos = &lock->wait_list;
 	list_for_each_entry_reverse(cur, &lock->wait_list, list) {
@@ -701,34 +753,27 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 			continue;
 
 		if (__ww_ctx_stamp_after(ww_ctx, cur->ww_ctx)) {
-			/* Back off immediately if necessary. */
-			if (ww_ctx->acquired > 0) {
-#ifdef CONFIG_DEBUG_MUTEXES
-				struct ww_mutex *ww;
+			/*
+			 * Wait-Die: if we find an older context waiting, there
+			 * is no point in queueing behind it, as we'd have to
+			 * die the moment it would acquire the lock.
+			 */
+			int ret = __ww_mutex_kill(lock, ww_ctx);
 
-				ww = container_of(lock, struct ww_mutex, base);
-				DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock);
-				ww_ctx->contending_lock = ww;
-#endif
-				return -EDEADLK;
-			}
+			if (ret)
+				return ret;
 
 			break;
 		}
 
 		pos = &cur->list;
 
-		/*
-		 * Wake up the waiter so that it gets a chance to back
-		 * off.
-		 */
-		if (cur->ww_ctx->acquired > 0) {
-			debug_mutex_wake_waiter(lock, cur);
-			wake_up_process(cur->task);
-		}
+		/* Wait-Die: ensure younger waiters die. */
+		__ww_mutex_die(lock, cur, ww_ctx);
 	}
 
 	list_add_tail(&waiter->list, pos);
+
 	return 0;
 }
 
@@ -772,7 +817,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 */
 	if (__mutex_trylock(lock)) {
 		if (use_ww_ctx && ww_ctx)
-			__ww_mutex_wakeup_for_backoff(lock, ww_ctx);
+			__ww_mutex_check_waiters(lock, ww_ctx);
 
 		goto skip_wait;
 	}
@@ -790,10 +835,13 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		waiter.ww_ctx = MUTEX_POISON_WW_CTX;
 #endif
 	} else {
-		/* Add in stamp order, waking up waiters that must back off. */
+		/*
+		 * Add in stamp order, waking up waiters that must kill
+		 * themselves.
+		 */
 		ret = __ww_mutex_add_waiter(&waiter, lock, ww_ctx);
 		if (ret)
-			goto err_early_backoff;
+			goto err_early_kill;
 
 		waiter.ww_ctx = ww_ctx;
 	}
@@ -815,7 +863,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			goto acquired;
 
 		/*
-		 * Check for signals and wound conditions while holding
+		 * Check for signals and kill conditions while holding
 		 * wait_lock. This ensures the lock cancellation is ordered
 		 * against mutex_unlock() and wake-ups do not go missing.
 		 */
@@ -824,8 +872,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 			goto err;
 		}
 
-		if (use_ww_ctx && ww_ctx && ww_ctx->acquired > 0) {
-			ret = __ww_mutex_lock_check_stamp(lock, &waiter, ww_ctx);
+		if (use_ww_ctx && ww_ctx) {
+			ret = __ww_mutex_check_kill(lock, &waiter, ww_ctx);
 			if (ret)
 				goto err;
 		}
@@ -870,7 +918,7 @@ skip_wait:
 	lock_acquired(&lock->dep_map, ip);
 
 	if (use_ww_ctx && ww_ctx)
-		ww_mutex_set_context_slowpath(ww, ww_ctx);
+		ww_mutex_lock_acquired(ww, ww_ctx);
 
 	spin_unlock(&lock->wait_lock);
 	preempt_enable();
@@ -879,7 +927,7 @@ skip_wait:
 err:
 	__set_current_state(TASK_RUNNING);
 	mutex_remove_waiter(lock, &waiter, current);
-err_early_backoff:
+err_early_kill:
 	spin_unlock(&lock->wait_lock);
 	debug_mutex_free_waiter(&waiter);
 	mutex_release(&lock->dep_map, 1, ip);
-- 
cgit v1.2.3


From 08295b3b5beec9aac0f7a9db86f0fc3792039da3 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Fri, 15 Jun 2018 10:17:38 +0200
Subject: locking: Implement an algorithm choice for Wound-Wait mutexes

The current Wound-Wait mutex algorithm is actually not Wound-Wait but
Wait-Die. Implement also Wound-Wait as a per-ww-class choice. Wound-Wait
is, contrary to Wait-Die a preemptive algorithm and is known to generate
fewer backoffs. Testing reveals that this is true if the
number of simultaneous contending transactions is small.
As the number of simultaneous contending threads increases, Wait-Wound
becomes inferior to Wait-Die in terms of elapsed time.
Possibly due to the larger number of held locks of sleeping transactions.

Update documentation and callers.

Timings using git://people.freedesktop.org/~thomash/ww_mutex_test
tag patch-18-06-15

Each thread runs 100000 batches of lock / unlock 800 ww mutexes randomly
chosen out of 100000. Four core Intel x86_64:

Algorithm    #threads       Rollbacks  time
Wound-Wait   4              ~100       ~17s.
Wait-Die     4              ~150000    ~19s.
Wound-Wait   16             ~360000    ~109s.
Wait-Die     16             ~450000    ~82s.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: David Airlie <airlied@linux.ie>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: linux-doc@vger.kernel.org
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Co-authored-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/locking/ww-mutex-design.txt |  57 +++++++++--
 drivers/dma-buf/reservation.c             |   2 +-
 drivers/gpu/drm/drm_modeset_lock.c        |   2 +-
 include/linux/ww_mutex.h                  |  17 ++-
 kernel/locking/locktorture.c              |   2 +-
 kernel/locking/mutex.c                    | 165 +++++++++++++++++++++++++++---
 kernel/locking/test-ww_mutex.c            |   2 +-
 lib/locking-selftest.c                    |   2 +-
 8 files changed, 213 insertions(+), 36 deletions(-)

diff --git a/Documentation/locking/ww-mutex-design.txt b/Documentation/locking/ww-mutex-design.txt
index 2fd7f2a2af21..f0ed7c30e695 100644
--- a/Documentation/locking/ww-mutex-design.txt
+++ b/Documentation/locking/ww-mutex-design.txt
@@ -1,4 +1,4 @@
-Wait/Wound Deadlock-Proof Mutex Design
+Wound/Wait Deadlock-Proof Mutex Design
 ======================================
 
 Please read mutex-design.txt first, as it applies to wait/wound mutexes too.
@@ -32,10 +32,26 @@ the oldest task) wins, and the one with the higher reservation id (i.e. the
 younger task) unlocks all of the buffers that it has already locked, and then
 tries again.
 
-In the RDBMS literature this deadlock handling approach is called wait/die:
-The older tasks waits until it can acquire the contended lock. The younger tasks
-needs to back off and drop all the locks it is currently holding, i.e. the
-younger task dies.
+In the RDBMS literature, a reservation ticket is associated with a transaction.
+and the deadlock handling approach is called Wait-Die. The name is based on
+the actions of a locking thread when it encounters an already locked mutex.
+If the transaction holding the lock is younger, the locking transaction waits.
+If the transaction holding the lock is older, the locking transaction backs off
+and dies. Hence Wait-Die.
+There is also another algorithm called Wound-Wait:
+If the transaction holding the lock is younger, the locking transaction
+wounds the transaction holding the lock, requesting it to die.
+If the transaction holding the lock is older, it waits for the other
+transaction. Hence Wound-Wait.
+The two algorithms are both fair in that a transaction will eventually succeed.
+However, the Wound-Wait algorithm is typically stated to generate fewer backoffs
+compared to Wait-Die, but is, on the other hand, associated with more work than
+Wait-Die when recovering from a backoff. Wound-Wait is also a preemptive
+algorithm in that transactions are wounded by other transactions, and that
+requires a reliable way to pick up up the wounded condition and preempt the
+running transaction. Note that this is not the same as process preemption. A
+Wound-Wait transaction is considered preempted when it dies (returning
+-EDEADLK) following a wound.
 
 Concepts
 --------
@@ -47,10 +63,12 @@ Acquire context: To ensure eventual forward progress it is important the a task
 trying to acquire locks doesn't grab a new reservation id, but keeps the one it
 acquired when starting the lock acquisition. This ticket is stored in the
 acquire context. Furthermore the acquire context keeps track of debugging state
-to catch w/w mutex interface abuse.
+to catch w/w mutex interface abuse. An acquire context is representing a
+transaction.
 
 W/w class: In contrast to normal mutexes the lock class needs to be explicit for
-w/w mutexes, since it is required to initialize the acquire context.
+w/w mutexes, since it is required to initialize the acquire context. The lock
+class also specifies what algorithm to use, Wound-Wait or Wait-Die.
 
 Furthermore there are three different class of w/w lock acquire functions:
 
@@ -90,6 +108,12 @@ provided.
 Usage
 -----
 
+The algorithm (Wait-Die vs Wound-Wait) is chosen by using either
+DEFINE_WW_CLASS() (Wound-Wait) or DEFINE_WD_CLASS() (Wait-Die)
+As a rough rule of thumb, use Wound-Wait iff you
+expect the number of simultaneous competing transactions to be typically small,
+and you want to reduce the number of rollbacks.
+
 Three different ways to acquire locks within the same w/w class. Common
 definitions for methods #1 and #2:
 
@@ -312,12 +336,23 @@ Design:
   We maintain the following invariants for the wait list:
   (1) Waiters with an acquire context are sorted by stamp order; waiters
       without an acquire context are interspersed in FIFO order.
-  (2) Among waiters with contexts, only the first one can have other locks
-      acquired already (ctx->acquired > 0). Note that this waiter may come
-      after other waiters without contexts in the list.
+  (2) For Wait-Die, among waiters with contexts, only the first one can have
+      other locks acquired already (ctx->acquired > 0). Note that this waiter
+      may come after other waiters without contexts in the list.
+
+  The Wound-Wait preemption is implemented with a lazy-preemption scheme:
+  The wounded status of the transaction is checked only when there is
+  contention for a new lock and hence a true chance of deadlock. In that
+  situation, if the transaction is wounded, it backs off, clears the
+  wounded status and retries. A great benefit of implementing preemption in
+  this way is that the wounded transaction can identify a contending lock to
+  wait for before restarting the transaction. Just blindly restarting the
+  transaction would likely make the transaction end up in a situation where
+  it would have to back off again.
 
   In general, not much contention is expected. The locks are typically used to
-  serialize access to resources for devices.
+  serialize access to resources for devices, and optimization focus should
+  therefore be directed towards the uncontended cases.
 
 Lockdep:
   Special care has been taken to warn for as many cases of api abuse
diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 314eb1071cce..20bf90f4ee63 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -46,7 +46,7 @@
  * write-side updates.
  */
 
-DEFINE_WW_CLASS(reservation_ww_class);
+DEFINE_WD_CLASS(reservation_ww_class);
 EXPORT_SYMBOL(reservation_ww_class);
 
 struct lock_class_key reservation_seqcount_class;
diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 8a5100685875..638be2eb67b4 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -70,7 +70,7 @@
  * lists and lookup data structures.
  */
 
-static DEFINE_WW_CLASS(crtc_ww_class);
+static DEFINE_WD_CLASS(crtc_ww_class);
 
 /**
  * drm_modeset_lock_all - take all modeset locks
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index f82fce2229c8..3af7c0e03be5 100644
--- a/include/linux/ww_mutex.h
+++ b/include/linux/ww_mutex.h
@@ -8,6 +8,8 @@
  *
  * Wait/Die implementation:
  *  Copyright (C) 2013 Canonical Ltd.
+ * Choice of algorithm:
+ *  Copyright (C) 2018 WMWare Inc.
  *
  * This file contains the main data structure and API definitions.
  */
@@ -23,12 +25,15 @@ struct ww_class {
 	struct lock_class_key mutex_key;
 	const char *acquire_name;
 	const char *mutex_name;
+	unsigned int is_wait_die;
 };
 
 struct ww_acquire_ctx {
 	struct task_struct *task;
 	unsigned long stamp;
 	unsigned int acquired;
+	unsigned short wounded;
+	unsigned short is_wait_die;
 #ifdef CONFIG_DEBUG_MUTEXES
 	unsigned int done_acquire;
 	struct ww_class *ww_class;
@@ -58,17 +63,21 @@ struct ww_mutex {
 # define __WW_CLASS_MUTEX_INITIALIZER(lockname, class)
 #endif
 
-#define __WW_CLASS_INITIALIZER(ww_class) \
+#define __WW_CLASS_INITIALIZER(ww_class, _is_wait_die)	    \
 		{ .stamp = ATOMIC_LONG_INIT(0) \
 		, .acquire_name = #ww_class "_acquire" \
-		, .mutex_name = #ww_class "_mutex" }
+		, .mutex_name = #ww_class "_mutex" \
+		, .is_wait_die = _is_wait_die }
 
 #define __WW_MUTEX_INITIALIZER(lockname, class) \
 		{ .base =  __MUTEX_INITIALIZER(lockname.base) \
 		__WW_CLASS_MUTEX_INITIALIZER(lockname, class) }
 
+#define DEFINE_WD_CLASS(classname) \
+	struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 1)
+
 #define DEFINE_WW_CLASS(classname) \
-	struct ww_class classname = __WW_CLASS_INITIALIZER(classname)
+	struct ww_class classname = __WW_CLASS_INITIALIZER(classname, 0)
 
 #define DEFINE_WW_MUTEX(mutexname, ww_class) \
 	struct ww_mutex mutexname = __WW_MUTEX_INITIALIZER(mutexname, ww_class)
@@ -123,6 +132,8 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
 	ctx->task = current;
 	ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp);
 	ctx->acquired = 0;
+	ctx->wounded = false;
+	ctx->is_wait_die = ww_class->is_wait_die;
 #ifdef CONFIG_DEBUG_MUTEXES
 	ctx->ww_class = ww_class;
 	ctx->done_acquire = 0;
diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c
index 8402b3349dca..c28224347d69 100644
--- a/kernel/locking/locktorture.c
+++ b/kernel/locking/locktorture.c
@@ -365,7 +365,7 @@ static struct lock_torture_ops mutex_lock_ops = {
 };
 
 #include <linux/ww_mutex.h>
-static DEFINE_WW_CLASS(torture_ww_class);
+static DEFINE_WD_CLASS(torture_ww_class);
 static DEFINE_WW_MUTEX(torture_ww_mutex_0, &torture_ww_class);
 static DEFINE_WW_MUTEX(torture_ww_mutex_1, &torture_ww_class);
 static DEFINE_WW_MUTEX(torture_ww_mutex_2, &torture_ww_class);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index cfe48419b7d0..1a81a1257b3f 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -173,6 +173,21 @@ static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_wait
 	return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter;
 }
 
+/*
+ * Add @waiter to a given location in the lock wait_list and set the
+ * FLAG_WAITERS flag if it's the first waiter.
+ */
+static void __sched
+__mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
+		   struct list_head *list)
+{
+	debug_mutex_add_waiter(lock, waiter, current);
+
+	list_add_tail(&waiter->list, list);
+	if (__mutex_waiter_is_first(lock, waiter))
+		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
+}
+
 /*
  * Give up ownership to a specific task, when @task = NULL, this is equivalent
  * to a regular unlock. Sets PICKUP on a handoff, clears HANDOF, preserves
@@ -249,6 +264,11 @@ EXPORT_SYMBOL(mutex_lock);
  *   The newer transactions are killed when:
  *     It (the new transaction) makes a request for a lock being held
  *     by an older transaction.
+ *
+ * Wound-Wait:
+ *   The newer transactions are wounded when:
+ *     An older transaction makes a request for a lock being held by
+ *     the newer transaction.
  */
 
 /*
@@ -320,6 +340,9 @@ static bool __sched
 __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter,
 	       struct ww_acquire_ctx *ww_ctx)
 {
+	if (!ww_ctx->is_wait_die)
+		return false;
+
 	if (waiter->ww_ctx->acquired > 0 &&
 			__ww_ctx_stamp_after(waiter->ww_ctx, ww_ctx)) {
 		debug_mutex_wake_waiter(lock, waiter);
@@ -329,13 +352,65 @@ __ww_mutex_die(struct mutex *lock, struct mutex_waiter *waiter,
 	return true;
 }
 
+/*
+ * Wound-Wait; wound a younger @hold_ctx if it holds the lock.
+ *
+ * Wound the lock holder if there are waiters with older transactions than
+ * the lock holders. Even if multiple waiters may wound the lock holder,
+ * it's sufficient that only one does.
+ */
+static bool __ww_mutex_wound(struct mutex *lock,
+			     struct ww_acquire_ctx *ww_ctx,
+			     struct ww_acquire_ctx *hold_ctx)
+{
+	struct task_struct *owner = __mutex_owner(lock);
+
+	lockdep_assert_held(&lock->wait_lock);
+
+	/*
+	 * Possible through __ww_mutex_add_waiter() when we race with
+	 * ww_mutex_set_context_fastpath(). In that case we'll get here again
+	 * through __ww_mutex_check_waiters().
+	 */
+	if (!hold_ctx)
+		return false;
+
+	/*
+	 * Can have !owner because of __mutex_unlock_slowpath(), but if owner,
+	 * it cannot go away because we'll have FLAG_WAITERS set and hold
+	 * wait_lock.
+	 */
+	if (!owner)
+		return false;
+
+	if (ww_ctx->acquired > 0 && __ww_ctx_stamp_after(hold_ctx, ww_ctx)) {
+		hold_ctx->wounded = 1;
+
+		/*
+		 * wake_up_process() paired with set_current_state()
+		 * inserts sufficient barriers to make sure @owner either sees
+		 * it's wounded in __ww_mutex_lock_check_stamp() or has a
+		 * wakeup pending to re-read the wounded state.
+		 */
+		if (owner != current)
+			wake_up_process(owner);
+
+		return true;
+	}
+
+	return false;
+}
+
 /*
  * We just acquired @lock under @ww_ctx, if there are later contexts waiting
- * behind us on the wait-list, check if they need to die.
+ * behind us on the wait-list, check if they need to die, or wound us.
  *
  * See __ww_mutex_add_waiter() for the list-order construction; basically the
  * list is ordered by stamp, smallest (oldest) first.
  *
+ * This relies on never mixing wait-die/wound-wait on the same wait-list;
+ * which is currently ensured by that being a ww_class property.
+ *
  * The current task must not be on the wait list.
  */
 static void __sched
@@ -349,7 +424,8 @@ __ww_mutex_check_waiters(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
 		if (!cur->ww_ctx)
 			continue;
 
-		if (__ww_mutex_die(lock, cur, ww_ctx))
+		if (__ww_mutex_die(lock, cur, ww_ctx) ||
+		    __ww_mutex_wound(lock, cur->ww_ctx, ww_ctx))
 			break;
 	}
 }
@@ -370,17 +446,23 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 	 * and keep spinning, or it will acquire wait_lock, add itself
 	 * to waiter list and sleep.
 	 */
-	smp_mb(); /* ^^^ */
+	smp_mb(); /* See comments above and below. */
 
 	/*
-	 * Check if lock is contended, if not there is nobody to wake up
+	 * [W] ww->ctx = ctx	    [W] MUTEX_FLAG_WAITERS
+	 *     MB		        MB
+	 * [R] MUTEX_FLAG_WAITERS   [R] ww->ctx
+	 *
+	 * The memory barrier above pairs with the memory barrier in
+	 * __ww_mutex_add_waiter() and makes sure we either observe ww->ctx
+	 * and/or !empty list.
 	 */
 	if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))
 		return;
 
 	/*
 	 * Uh oh, we raced in fastpath, check if any of the waiters need to
-	 * die.
+	 * die or wound us.
 	 */
 	spin_lock(&lock->base.wait_lock);
 	__ww_mutex_check_waiters(&lock->base, ctx);
@@ -682,7 +764,9 @@ __ww_mutex_kill(struct mutex *lock, struct ww_acquire_ctx *ww_ctx)
 
 
 /*
- * Check whether we need to kill the transaction for the current lock acquire.
+ * Check the wound condition for the current lock acquire.
+ *
+ * Wound-Wait: If we're wounded, kill ourself.
  *
  * Wait-Die: If we're trying to acquire a lock already held by an older
  *           context, kill ourselves.
@@ -701,6 +785,13 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter,
 	if (ctx->acquired == 0)
 		return 0;
 
+	if (!ctx->is_wait_die) {
+		if (ctx->wounded)
+			return __ww_mutex_kill(lock, ctx);
+
+		return 0;
+	}
+
 	if (hold_ctx && __ww_ctx_stamp_after(ctx, hold_ctx))
 		return __ww_mutex_kill(lock, ctx);
 
@@ -727,7 +818,8 @@ __ww_mutex_check_kill(struct mutex *lock, struct mutex_waiter *waiter,
  * Waiters without context are interspersed in FIFO order.
  *
  * Furthermore, for Wait-Die kill ourself immediately when possible (there are
- * older contexts already waiting) to avoid unnecessary waiting.
+ * older contexts already waiting) to avoid unnecessary waiting and for
+ * Wound-Wait ensure we wound the owning context when it is younger.
  */
 static inline int __sched
 __ww_mutex_add_waiter(struct mutex_waiter *waiter,
@@ -736,16 +828,21 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 {
 	struct mutex_waiter *cur;
 	struct list_head *pos;
+	bool is_wait_die;
 
 	if (!ww_ctx) {
-		list_add_tail(&waiter->list, &lock->wait_list);
+		__mutex_add_waiter(lock, waiter, &lock->wait_list);
 		return 0;
 	}
 
+	is_wait_die = ww_ctx->is_wait_die;
+
 	/*
 	 * Add the waiter before the first waiter with a higher stamp.
 	 * Waiters without a context are skipped to avoid starving
-	 * them. Wait-Die waiters may die here.
+	 * them. Wait-Die waiters may die here. Wound-Wait waiters
+	 * never die here, but they are sorted in stamp order and
+	 * may wound the lock holder.
 	 */
 	pos = &lock->wait_list;
 	list_for_each_entry_reverse(cur, &lock->wait_list, list) {
@@ -758,10 +855,12 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 			 * is no point in queueing behind it, as we'd have to
 			 * die the moment it would acquire the lock.
 			 */
-			int ret = __ww_mutex_kill(lock, ww_ctx);
+			if (is_wait_die) {
+				int ret = __ww_mutex_kill(lock, ww_ctx);
 
-			if (ret)
-				return ret;
+				if (ret)
+					return ret;
+			}
 
 			break;
 		}
@@ -772,7 +871,23 @@ __ww_mutex_add_waiter(struct mutex_waiter *waiter,
 		__ww_mutex_die(lock, cur, ww_ctx);
 	}
 
-	list_add_tail(&waiter->list, pos);
+	__mutex_add_waiter(lock, waiter, pos);
+
+	/*
+	 * Wound-Wait: if we're blocking on a mutex owned by a younger context,
+	 * wound that such that we might proceed.
+	 */
+	if (!is_wait_die) {
+		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+
+		/*
+		 * See ww_mutex_set_context_fastpath(). Orders setting
+		 * MUTEX_FLAG_WAITERS vs the ww->ctx load,
+		 * such that either we or the fastpath will wound @ww->ctx.
+		 */
+		smp_mb();
+		__ww_mutex_wound(lock, ww_ctx, ww->ctx);
+	}
 
 	return 0;
 }
@@ -796,6 +911,14 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	if (use_ww_ctx && ww_ctx) {
 		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
 			return -EALREADY;
+
+		/*
+		 * Reset the wounded flag after a kill. No other process can
+		 * race and wound us here since they can't have a valid owner
+		 * pointer if we don't have any locks held.
+		 */
+		if (ww_ctx->acquired == 0)
+			ww_ctx->wounded = 0;
 	}
 
 	preempt_disable();
@@ -829,7 +952,8 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 	if (!use_ww_ctx) {
 		/* add waiting tasks to the end of the waitqueue (FIFO): */
-		list_add_tail(&waiter.list, &lock->wait_list);
+		__mutex_add_waiter(lock, &waiter, &lock->wait_list);
+
 
 #ifdef CONFIG_DEBUG_MUTEXES
 		waiter.ww_ctx = MUTEX_POISON_WW_CTX;
@@ -848,9 +972,6 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 
 	waiter.task = current;
 
-	if (__mutex_waiter_is_first(lock, &waiter))
-		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
-
 	set_current_state(state);
 	for (;;) {
 		/*
@@ -907,6 +1028,16 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 acquired:
 	__set_current_state(TASK_RUNNING);
 
+	if (use_ww_ctx && ww_ctx) {
+		/*
+		 * Wound-Wait; we stole the lock (!first_waiter), check the
+		 * waiters as anyone might want to wound us.
+		 */
+		if (!ww_ctx->is_wait_die &&
+		    !__mutex_waiter_is_first(lock, &waiter))
+			__ww_mutex_check_waiters(lock, ww_ctx);
+	}
+
 	mutex_remove_waiter(lock, &waiter, current);
 	if (likely(list_empty(&lock->wait_list)))
 		__mutex_clear_flag(lock, MUTEX_FLAGS);
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index 0e4cd64ad2c0..5b915b370d5a 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -26,7 +26,7 @@
 #include <linux/slab.h>
 #include <linux/ww_mutex.h>
 
-static DEFINE_WW_CLASS(ww_class);
+static DEFINE_WD_CLASS(ww_class);
 struct workqueue_struct *wq;
 
 struct test_mutex {
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index b5c1293ce147..1e1bbf171eca 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -29,7 +29,7 @@
  */
 static unsigned int debug_locks_verbose;
 
-static DEFINE_WW_CLASS(ww_lockdep);
+static DEFINE_WD_CLASS(ww_lockdep);
 
 static int __init setup_debug_locks_verbose(char *str)
 {
-- 
cgit v1.2.3


From 07c13bb78c8b8a9cb6ee169659528945038d5e85 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Thu, 14 Jun 2018 09:29:22 +0200
Subject: drm: Change deadlock-avoidance algorithm for the modeset locks.

For modeset locks we don't expect a high number of contending
transactions so change algorithm from Wait-Die to Wound-Wait.

Cc: dri-devel@lists.freedesktop.org
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/gpu/drm/drm_modeset_lock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_modeset_lock.c b/drivers/gpu/drm/drm_modeset_lock.c
index 638be2eb67b4..8a5100685875 100644
--- a/drivers/gpu/drm/drm_modeset_lock.c
+++ b/drivers/gpu/drm/drm_modeset_lock.c
@@ -70,7 +70,7 @@
  * lists and lookup data structures.
  */
 
-static DEFINE_WD_CLASS(crtc_ww_class);
+static DEFINE_WW_CLASS(crtc_ww_class);
 
 /**
  * drm_modeset_lock_all - take all modeset locks
-- 
cgit v1.2.3


From a7bea8308933aaeea76dad7d42a6e51000417626 Mon Sep 17 00:00:00 2001
From: Jan Beulich <JBeulich@suse.com>
Date: Mon, 2 Jul 2018 04:31:54 -0600
Subject: x86/asm/64: Use 32-bit XOR to zero registers

Some Intel CPUs don't recognize 64-bit XORs as zeroing idioms. Zeroing
idioms don't require execution bandwidth, as they're being taken care
of in the frontend (through register renaming). Use 32-bit XORs instead.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: Alok Kataria <akataria@vmware.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: davem@davemloft.net
Cc: herbert@gondor.apana.org.au
Cc: pavel@ucw.cz
Cc: rjw@rjwysocki.net
Link: http://lkml.kernel.org/r/5B39FF1A02000078001CFB54@prv1-mh.provo.novell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/crypto/aegis128-aesni-asm.S     | 2 +-
 arch/x86/crypto/aegis128l-aesni-asm.S    | 2 +-
 arch/x86/crypto/aegis256-aesni-asm.S     | 2 +-
 arch/x86/crypto/aesni-intel_asm.S        | 8 ++++----
 arch/x86/crypto/aesni-intel_avx-x86_64.S | 4 ++--
 arch/x86/crypto/morus1280-avx2-asm.S     | 2 +-
 arch/x86/crypto/morus1280-sse2-asm.S     | 2 +-
 arch/x86/crypto/morus640-sse2-asm.S      | 2 +-
 arch/x86/crypto/sha1_ssse3_asm.S         | 2 +-
 arch/x86/kernel/head_64.S                | 2 +-
 arch/x86/kernel/paravirt_patch_64.c      | 2 +-
 arch/x86/lib/memcpy_64.S                 | 2 +-
 arch/x86/power/hibernate_asm_64.S        | 2 +-
 13 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/arch/x86/crypto/aegis128-aesni-asm.S b/arch/x86/crypto/aegis128-aesni-asm.S
index 9254e0b6cc06..d5c5e2082ae7 100644
--- a/arch/x86/crypto/aegis128-aesni-asm.S
+++ b/arch/x86/crypto/aegis128-aesni-asm.S
@@ -75,7 +75,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov LEN, %r8
diff --git a/arch/x86/crypto/aegis128l-aesni-asm.S b/arch/x86/crypto/aegis128l-aesni-asm.S
index 9263c344f2c7..0fbdf5f00bda 100644
--- a/arch/x86/crypto/aegis128l-aesni-asm.S
+++ b/arch/x86/crypto/aegis128l-aesni-asm.S
@@ -66,7 +66,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG0, MSG0
 	pxor MSG1, MSG1
 
diff --git a/arch/x86/crypto/aegis256-aesni-asm.S b/arch/x86/crypto/aegis256-aesni-asm.S
index 1d977d515bf9..a49f58e2a5dd 100644
--- a/arch/x86/crypto/aegis256-aesni-asm.S
+++ b/arch/x86/crypto/aegis256-aesni-asm.S
@@ -59,7 +59,7 @@
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov LEN, %r8
diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S
index e762ef417562..9bd139569b41 100644
--- a/arch/x86/crypto/aesni-intel_asm.S
+++ b/arch/x86/crypto/aesni-intel_asm.S
@@ -258,7 +258,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 .macro GCM_INIT Iv SUBKEY AAD AADLEN
 	mov \AADLEN, %r11
 	mov %r11, AadLen(%arg2) # ctx_data.aad_length = aad_length
-	xor %r11, %r11
+	xor %r11d, %r11d
 	mov %r11, InLen(%arg2) # ctx_data.in_length = 0
 	mov %r11, PBlockLen(%arg2) # ctx_data.partial_block_length = 0
 	mov %r11, PBlockEncKey(%arg2) # ctx_data.partial_block_enc_key = 0
@@ -286,7 +286,7 @@ ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
 	movdqu HashKey(%arg2), %xmm13
 	add %arg5, InLen(%arg2)
 
-	xor %r11, %r11 # initialise the data pointer offset as zero
+	xor %r11d, %r11d # initialise the data pointer offset as zero
 	PARTIAL_BLOCK %arg3 %arg4 %arg5 %r11 %xmm8 \operation
 
 	sub %r11, %arg5		# sub partial block data used
@@ -702,7 +702,7 @@ _no_extra_mask_1_\@:
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
-	xor	%rax,%rax
+	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
 	jmp	_dec_done_\@
@@ -737,7 +737,7 @@ _no_extra_mask_2_\@:
 
 	# GHASH computation for the last <16 Byte block
 	GHASH_MUL \AAD_HASH, %xmm13, %xmm0, %xmm10, %xmm11, %xmm5, %xmm6
-	xor	%rax,%rax
+	xor	%eax, %eax
 
 	mov	%rax, PBlockLen(%arg2)
 	jmp	_encode_done_\@
diff --git a/arch/x86/crypto/aesni-intel_avx-x86_64.S b/arch/x86/crypto/aesni-intel_avx-x86_64.S
index faecb1518bf8..1985ea0b551b 100644
--- a/arch/x86/crypto/aesni-intel_avx-x86_64.S
+++ b/arch/x86/crypto/aesni-intel_avx-x86_64.S
@@ -463,7 +463,7 @@ _get_AAD_rest_final\@:
 
 _get_AAD_done\@:
 	# initialize the data pointer offset as zero
-	xor     %r11, %r11
+	xor     %r11d, %r11d
 
 	# start AES for num_initial_blocks blocks
 	mov     arg5, %rax                     # rax = *Y0
@@ -1770,7 +1770,7 @@ _get_AAD_rest_final\@:
 
 _get_AAD_done\@:
 	# initialize the data pointer offset as zero
-	xor     %r11, %r11
+	xor     %r11d, %r11d
 
 	# start AES for num_initial_blocks blocks
 	mov     arg5, %rax                     # rax = *Y0
diff --git a/arch/x86/crypto/morus1280-avx2-asm.S b/arch/x86/crypto/morus1280-avx2-asm.S
index 37d422e77931..c3f74913476c 100644
--- a/arch/x86/crypto/morus1280-avx2-asm.S
+++ b/arch/x86/crypto/morus1280-avx2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus1280_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	vpxor MSG, MSG, MSG
 
 	mov %rcx, %r8
diff --git a/arch/x86/crypto/morus1280-sse2-asm.S b/arch/x86/crypto/morus1280-sse2-asm.S
index 1fe637c7be9d..b3f4d103ba06 100644
--- a/arch/x86/crypto/morus1280-sse2-asm.S
+++ b/arch/x86/crypto/morus1280-sse2-asm.S
@@ -235,7 +235,7 @@ ENDPROC(__morus1280_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG_LO, MSG_LO
 	pxor MSG_HI, MSG_HI
 
diff --git a/arch/x86/crypto/morus640-sse2-asm.S b/arch/x86/crypto/morus640-sse2-asm.S
index 71c72a0a0862..d2958a47fccc 100644
--- a/arch/x86/crypto/morus640-sse2-asm.S
+++ b/arch/x86/crypto/morus640-sse2-asm.S
@@ -113,7 +113,7 @@ ENDPROC(__morus640_update_zero)
  *   %r9
  */
 __load_partial:
-	xor %r9, %r9
+	xor %r9d, %r9d
 	pxor MSG, MSG
 
 	mov %rcx, %r8
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
index 6204bd53528c..613d0bfc3d84 100644
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ b/arch/x86/crypto/sha1_ssse3_asm.S
@@ -96,7 +96,7 @@
 	# cleanup workspace
 	mov	$8, %ecx
 	mov	%rsp, %rdi
-	xor	%rax, %rax
+	xor	%eax, %eax
 	rep stosq
 
 	mov	%rbp, %rsp		# deallocate workspace
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 8344dd2f310a..15ebc2fc166e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -235,7 +235,7 @@ ENTRY(secondary_startup_64)
 	 *		address given in m16:64.
 	 */
 	pushq	$.Lafter_lret	# put return address on stack for unwinder
-	xorq	%rbp, %rbp	# clear frame pointer
+	xorl	%ebp, %ebp	# clear frame pointer
 	movq	initial_code(%rip), %rax
 	pushq	$__KERNEL_CS	# set correct cs
 	pushq	%rax		# target address in negative space
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index 9edadabf04f6..9cb98f7b07c9 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/arch/x86/kernel/paravirt_patch_64.c
@@ -20,7 +20,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
-DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
 #endif
 
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 298ef1479240..3b24dc05251c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -256,7 +256,7 @@ ENTRY(__memcpy_mcsafe)
 
 	/* Copy successful. Return zero */
 .L_done_memcpy_trap:
-	xorq %rax, %rax
+	xorl %eax, %eax
 	ret
 ENDPROC(__memcpy_mcsafe)
 EXPORT_SYMBOL_GPL(__memcpy_mcsafe)
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index ce8da3a0412c..fd369a6e9ff8 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -137,7 +137,7 @@ ENTRY(restore_registers)
 	/* Saved in save_processor_state. */
 	lgdt	saved_context_gdt_desc(%rax)
 
-	xorq	%rax, %rax
+	xorl	%eax, %eax
 
 	/* tell the hibernation core that we've just restored the memory */
 	movq	%rax, in_suspend(%rip)
-- 
cgit v1.2.3


From 6709812f094d96543b443645c68daaa32d3d3e77 Mon Sep 17 00:00:00 2001
From: Jan Beulich <JBeulich@suse.com>
Date: Mon, 2 Jul 2018 04:47:57 -0600
Subject: x86/entry/64: Add two more instruction suffixes

Sadly, other than claimed in:

  a368d7fd2a ("x86/entry/64: Add instruction suffix")

... there are two more instances which want to be adjusted.

As said there, omitting suffixes from instructions in AT&T mode is bad
practice when operand size cannot be determined by the assembler from
register operands, and is likely going to be warned about by upstream
gas in the future (mine does already).

Add the other missing suffixes here as well.

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/5B3A02DD02000078001CFB78@prv1-mh.provo.novell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/entry/entry_64.S | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index c6f3677e6105..65aa16d845f6 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -92,7 +92,7 @@ END(native_usergs_sysret64)
 .endm
 
 .macro TRACE_IRQS_IRETQ_DEBUG
-	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	btl	$9, EFLAGS(%rsp)		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON_DEBUG
 1:
@@ -702,7 +702,7 @@ retint_kernel:
 #ifdef CONFIG_PREEMPT
 	/* Interrupts are off */
 	/* Check if we need preemption */
-	bt	$9, EFLAGS(%rsp)		/* were interrupts off? */
+	btl	$9, EFLAGS(%rsp)		/* were interrupts off? */
 	jnc	1f
 0:	cmpl	$0, PER_CPU_VAR(__preempt_count)
 	jnz	1f
-- 
cgit v1.2.3


From 9b912485e0e74a74e042e4f2dd87f262e46fcdf1 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Mon, 25 Jun 2018 11:16:55 +0800
Subject: x86/boot/KASLR: Add two new functions for 1GB huge pages handling

Introduce two new functions: parse_gb_huge_pages() and process_gb_huge_pages(),
which handle a conflict between KASLR and huge pages of 1GB.

These two functions will be used in the next patch:

- parse_gb_huge_pages() is used to parse kernel command-line to get
  how many 1GB huge pages have been specified. A static global
  variable 'max_gb_huge_pages' is added to store the number.

- process_gb_huge_pages() is used to skip as many 1GB huge pages
  as possible from the passed in memory region according to the
  specified number.

Signed-off-by: Baoquan He <bhe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: douly.fnst@cn.fujitsu.com
Cc: fanc.fnst@cn.fujitsu.com
Cc: indou.takao@jp.fujitsu.com
Cc: keescook@chromium.org
Cc: lcapitulino@redhat.com
Cc: yasu.isimatu@gmail.com
Link: http://lkml.kernel.org/r/20180625031656.12443-2-bhe@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/kaslr.c | 83 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)

diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index b87a7582853d..d97647b5ffb7 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -215,6 +215,35 @@ static void mem_avoid_memmap(char *str)
 		memmap_too_large = true;
 }
 
+/* Store the number of 1GB huge pages which users specified: */
+static unsigned long max_gb_huge_pages;
+
+static void parse_gb_huge_pages(char *param, char *val)
+{
+	static bool gbpage_sz;
+	char *p;
+
+	if (!strcmp(param, "hugepagesz")) {
+		p = val;
+		if (memparse(p, &p) != PUD_SIZE) {
+			gbpage_sz = false;
+			return;
+		}
+
+		if (gbpage_sz)
+			warn("Repeatedly set hugeTLB page size of 1G!\n");
+		gbpage_sz = true;
+		return;
+	}
+
+	if (!strcmp(param, "hugepages") && gbpage_sz) {
+		p = val;
+		max_gb_huge_pages = simple_strtoull(p, &p, 0);
+		return;
+	}
+}
+
+
 static int handle_mem_memmap(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
@@ -466,6 +495,60 @@ static void store_slot_info(struct mem_vector *region, unsigned long image_size)
 	}
 }
 
+/*
+ * Skip as many 1GB huge pages as possible in the passed region
+ * according to the number which users specified:
+ */
+static void
+process_gb_huge_pages(struct mem_vector *region, unsigned long image_size)
+{
+	unsigned long addr, size = 0;
+	struct mem_vector tmp;
+	int i = 0;
+
+	if (!max_gb_huge_pages) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	addr = ALIGN(region->start, PUD_SIZE);
+	/* Did we raise the address above the passed in memory entry? */
+	if (addr < region->start + region->size)
+		size = region->size - (addr - region->start);
+
+	/* Check how many 1GB huge pages can be filtered out: */
+	while (size > PUD_SIZE && max_gb_huge_pages) {
+		size -= PUD_SIZE;
+		max_gb_huge_pages--;
+		i++;
+	}
+
+	/* No good 1GB huge pages found: */
+	if (!i) {
+		store_slot_info(region, image_size);
+		return;
+	}
+
+	/*
+	 * Skip those 'i'*1GB good huge pages, and continue checking and
+	 * processing the remaining head or tail part of the passed region
+	 * if available.
+	 */
+
+	if (addr >= region->start + image_size) {
+		tmp.start = region->start;
+		tmp.size = addr - region->start;
+		store_slot_info(&tmp, image_size);
+	}
+
+	size  = region->size - (addr - region->start) - i * PUD_SIZE;
+	if (size >= image_size) {
+		tmp.start = addr + i * PUD_SIZE;
+		tmp.size = size;
+		store_slot_info(&tmp, image_size);
+	}
+}
+
 static unsigned long slots_fetch_random(void)
 {
 	unsigned long slot;
-- 
cgit v1.2.3


From 747ff6265db4c2b77e8c7384f8054916a0c1eb39 Mon Sep 17 00:00:00 2001
From: Baoquan He <bhe@redhat.com>
Date: Mon, 25 Jun 2018 11:16:56 +0800
Subject: x86/boot/KASLR: Skip specified number of 1GB huge pages when doing
 physical randomization (KASLR)

When KASLR is enabled then 1GB huge pages allocations might regress
sporadically.

To reproduce on a KVM guest with 4GB RAM:

- add the following options to the kernel command-line:

   'default_hugepagesz=1G hugepagesz=1G hugepages=1'

- boot the guest and check number of 1GB pages reserved:

    # grep HugePages_Total /proc/meminfo

- sporadically, every couple of bootups the output of this
  command shows that when booting with "nokaslr" HugePages_Total is always 1,
  while booting without "nokaslr" sometimes HugePages_Total is set as 0
  (that is, reserving the 1GB page failed).

Note that you may need to boot a few times to trigger the issue,
because it's somewhat non-deterministic.

The root cause is that kernel may be put into the only good 1GB huge page
in the [0x40000000, 0x7fffffff] physical range randomly.

Below is the dmesg output snippet from the KVM guest. We can see that only
[0x40000000, 0x7fffffff] region is good 1GB huge page,
[0x100000000, 0x13fffffff] will be touched by the memblock top-down allocation:

[...] e820: BIOS-provided physical RAM map:
[...] BIOS-e820: [mem 0x0000000000000000-0x000000000009fbff] usable
[...] BIOS-e820: [mem 0x000000000009fc00-0x000000000009ffff] reserved
[...] BIOS-e820: [mem 0x00000000000f0000-0x00000000000fffff] reserved
[...] BIOS-e820: [mem 0x0000000000100000-0x00000000bffdffff] usable
[...] BIOS-e820: [mem 0x00000000bffe0000-0x00000000bfffffff] reserved
[...] BIOS-e820: [mem 0x00000000feffc000-0x00000000feffffff] reserved
[...] BIOS-e820: [mem 0x00000000fffc0000-0x00000000ffffffff] reserved
[...] BIOS-e820: [mem 0x0000000100000000-0x000000013fffffff] usable

Besides, on bare-metal machines with larger memory, one less 1GB huge page
might be available with KASLR enabled. That too is because the kernel
image might be randomized into those "good" 1GB huge pages.

To fix this, firstly parse the kernel command-line to get how many 1GB huge
pages are specified. Then try to skip the specified number of 1GB huge
pages when decide which memory region kernel can be randomized into.

Also change the name of handle_mem_memmap() as handle_mem_options()
since it handles not only 'mem=' and 'memmap=', but also 'hugepagesxxx' now.

Signed-off-by: Baoquan He <bhe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: douly.fnst@cn.fujitsu.com
Cc: fanc.fnst@cn.fujitsu.com
Cc: indou.takao@jp.fujitsu.com
Cc: keescook@chromium.org
Cc: lcapitulino@redhat.com
Cc: yasu.isimatu@gmail.com
Link: http://lkml.kernel.org/r/20180625031656.12443-3-bhe@redhat.com
[ Rewrote the changelog, fixed style problems in the code. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/kaslr.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index d97647b5ffb7..531c9876f573 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -244,7 +244,7 @@ static void parse_gb_huge_pages(char *param, char *val)
 }
 
 
-static int handle_mem_memmap(void)
+static int handle_mem_options(void)
 {
 	char *args = (char *)get_cmd_line_ptr();
 	size_t len = strlen((char *)args);
@@ -252,7 +252,8 @@ static int handle_mem_memmap(void)
 	char *param, *val;
 	u64 mem_size;
 
-	if (!strstr(args, "memmap=") && !strstr(args, "mem="))
+	if (!strstr(args, "memmap=") && !strstr(args, "mem=") &&
+		!strstr(args, "hugepages"))
 		return 0;
 
 	tmp_cmdline = malloc(len + 1);
@@ -277,6 +278,8 @@ static int handle_mem_memmap(void)
 
 		if (!strcmp(param, "memmap")) {
 			mem_avoid_memmap(val);
+		} else if (strstr(param, "hugepages")) {
+			parse_gb_huge_pages(param, val);
 		} else if (!strcmp(param, "mem")) {
 			char *p = val;
 
@@ -416,7 +419,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	/* We don't need to set a mapping for setup_data. */
 
 	/* Mark the memmap regions we need to avoid */
-	handle_mem_memmap();
+	handle_mem_options();
 
 #ifdef CONFIG_X86_VERBOSE_BOOTUP
 	/* Make sure video RAM can be used. */
@@ -629,7 +632,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 		/* If nothing overlaps, store the region and return. */
 		if (!mem_avoid_overlap(&region, &overlap)) {
-			store_slot_info(&region, image_size);
+			process_gb_huge_pages(&region, image_size);
 			return;
 		}
 
@@ -639,7 +642,7 @@ static void process_mem_region(struct mem_vector *entry,
 
 			beginning.start = region.start;
 			beginning.size = overlap.start - region.start;
-			store_slot_info(&beginning, image_size);
+			process_gb_huge_pages(&beginning, image_size);
 		}
 
 		/* Return if overlap extends to or past end of region. */
-- 
cgit v1.2.3


From 6c0ad1df179b8d26ecd5e9954c36146fa87c1b0c Mon Sep 17 00:00:00 2001
From: Yixun Lan <yixun.lan@amlogic.com>
Date: Mon, 2 Jul 2018 21:31:17 +0000
Subject: clk: meson-axg: add pcie and mipi clock bindings

Add the pcie and mipi clock dt-bindings for the pcie driver.

Since the mipi clock isalso used by the pcie driver,
we add it together in this patch.

Tested-by: Jianxin Qin <jianxin.qin@amlogic.com>
Signed-off-by: Yixun Lan <yixun.lan@amlogic.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 include/dt-bindings/clock/axg-clkc.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/dt-bindings/clock/axg-clkc.h b/include/dt-bindings/clock/axg-clkc.h
index 555937a25504..70371228b7e0 100644
--- a/include/dt-bindings/clock/axg-clkc.h
+++ b/include/dt-bindings/clock/axg-clkc.h
@@ -68,5 +68,8 @@
 #define CLKID_SD_EMMC_B_CLK0			59
 #define CLKID_SD_EMMC_C_CLK0			60
 #define CLKID_HIFI_PLL				69
+#define CLKID_PCIE_CML_EN0			79
+#define CLKID_PCIE_CML_EN1			80
+#define CLKID_MIPI_ENABLE			81
 
 #endif /* __AXG_CLKC_H */
-- 
cgit v1.2.3


From dbd0fbc76c77daac08ddd245afdcbade0d506e19 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 29 Jun 2018 22:31:10 +0300
Subject: x86/tsc: Add missing header to tsc_msr.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a missing header otherwise compiler warns about missed prototype:

CC      arch/x86/kernel/tsc_msr.o
arch/x86/kernel/tsc_msr.c:73:15: warning: no previous prototype for ‘cpu_khz_from_msr’ [-Wmissing-prototypes]
   unsigned long cpu_khz_from_msr(void)
                 ^~~~~~~~~~~~~~~~

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Link: https://lkml.kernel.org/r/20180629193113.84425-4-andriy.shevchenko@linux.intel.com
---
 arch/x86/kernel/tsc_msr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 19afdbd7d0a7..5532d1be7687 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -12,6 +12,7 @@
 #include <asm/setup.h>
 #include <asm/apic.h>
 #include <asm/param.h>
+#include <asm/tsc.h>
 
 #define MAX_NUM_FREQS	9
 
-- 
cgit v1.2.3


From e2ce67b2b34b6e9d77da2f375dba5b525508f7df Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 29 Jun 2018 22:31:08 +0300
Subject: x86/cpu: Introduce INTEL_CPU_FAM*() helper macros

These macros are often used by drivers and there exists already a lot of
duplication as ICPU() macro across the drivers.

Provide a generic x86 macro for users.

Note, as Ingo Molnar pointed out this has a hidden issue when a driver
needs to preserve const qualifier. Though, it would be addressed
separately at some point.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Link: https://lkml.kernel.org/r/20180629193113.84425-2-andriy.shevchenko@linux.intel.com
---
 arch/x86/include/asm/intel-family.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index cf090e584202..7ed08a7c3398 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -76,4 +76,17 @@
 #define INTEL_FAM6_XEON_PHI_KNL		0x57 /* Knights Landing */
 #define INTEL_FAM6_XEON_PHI_KNM		0x85 /* Knights Mill */
 
+/* Useful macros */
+#define INTEL_CPU_FAM_ANY(_family, _model, _driver_data)	\
+{								\
+	.vendor		= X86_VENDOR_INTEL,			\
+	.family		= _family,				\
+	.model		= _model,				\
+	.feature	= X86_FEATURE_ANY,			\
+	.driver_data	= (kernel_ulong_t)&_driver_data		\
+}
+
+#define INTEL_CPU_FAM6(_model, _driver_data)			\
+	INTEL_CPU_FAM_ANY(6, INTEL_FAM6_##_model, _driver_data)
+
 #endif /* _ASM_X86_INTEL_FAMILY_H */
-- 
cgit v1.2.3


From 397d3ad18dc431456baf8bce96606fa1d18b30b0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 29 Jun 2018 22:31:09 +0300
Subject: x86/tsc: Convert to use x86_match_cpu() and INTEL_CPU_FAM6()

Move the code to use recently introduced INTEL_CPU_FAM6() macro and
drop custom version of x86_match_cpu() function.

No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Link: https://lkml.kernel.org/r/20180629193113.84425-3-andriy.shevchenko@linux.intel.com
---
 arch/x86/kernel/tsc_msr.c | 83 ++++++++++++++++++++++++-----------------------
 1 file changed, 42 insertions(+), 41 deletions(-)

diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 5532d1be7687..1465aaee543a 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -8,9 +8,11 @@
  */
 
 #include <linux/kernel.h>
-#include <asm/processor.h>
-#include <asm/setup.h>
+
 #include <asm/apic.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include <asm/msr.h>
 #include <asm/param.h>
 #include <asm/tsc.h>
 
@@ -24,44 +26,43 @@
  * field msr_plat does.
  */
 struct freq_desc {
-	u8 x86_family;	/* CPU family */
-	u8 x86_model;	/* model */
 	u8 msr_plat;	/* 1: use MSR_PLATFORM_INFO, 0: MSR_IA32_PERF_STATUS */
 	u32 freqs[MAX_NUM_FREQS];
 };
 
-static struct freq_desc freq_desc_tables[] = {
-	/* PNW */
-	{ 6, 0x27, 0, { 0, 0, 0, 0, 0, 99840, 0, 83200 } },
-	/* CLV+ */
-	{ 6, 0x35, 0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 } },
-	/* TNG - Intel Atom processor Z3400 series */
-	{ 6, 0x4a, 1, { 0, 100000, 133300, 0, 0, 0, 0, 0 } },
-	/* VLV2 - Intel Atom processor E3000, Z3600, Z3700 series */
-	{ 6, 0x37, 1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 } },
-	/* ANN - Intel Atom processor Z3500 series */
-	{ 6, 0x5a, 1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 } },
-	/* AMT - Intel Atom processor X7-Z8000 and X5-Z8000 series */
-	{ 6, 0x4c, 1, { 83300, 100000, 133300, 116700,
-			80000, 93300, 90000, 88900, 87500 } },
+static const struct freq_desc freq_desc_pnw = {
+	0, { 0, 0, 0, 0, 0, 99840, 0, 83200 }
 };
 
-static int match_cpu(u8 family, u8 model)
-{
-	int i;
+static const struct freq_desc freq_desc_clv = {
+	0, { 0, 133200, 0, 0, 0, 99840, 0, 83200 }
+};
 
-	for (i = 0; i < ARRAY_SIZE(freq_desc_tables); i++) {
-		if ((family == freq_desc_tables[i].x86_family) &&
-			(model == freq_desc_tables[i].x86_model))
-			return i;
-	}
+static const struct freq_desc freq_desc_byt = {
+	1, { 83300, 100000, 133300, 116700, 80000, 0, 0, 0 }
+};
 
-	return -1;
-}
+static const struct freq_desc freq_desc_cht = {
+	1, { 83300, 100000, 133300, 116700, 80000, 93300, 90000, 88900, 87500 }
+};
 
-/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
-#define id_to_freq(cpu_index, freq_id) \
-	(freq_desc_tables[cpu_index].freqs[freq_id])
+static const struct freq_desc freq_desc_tng = {
+	1, { 0, 100000, 133300, 0, 0, 0, 0, 0 }
+};
+
+static const struct freq_desc freq_desc_ann = {
+	1, { 83300, 100000, 133300, 100000, 0, 0, 0, 0 }
+};
+
+static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
+	INTEL_CPU_FAM6(ATOM_PENWELL,		freq_desc_pnw),
+	INTEL_CPU_FAM6(ATOM_CLOVERVIEW,		freq_desc_clv),
+	INTEL_CPU_FAM6(ATOM_SILVERMONT1,	freq_desc_byt),
+	INTEL_CPU_FAM6(ATOM_AIRMONT,		freq_desc_cht),
+	INTEL_CPU_FAM6(ATOM_MERRIFIELD,		freq_desc_tng),
+	INTEL_CPU_FAM6(ATOM_MOOREFIELD,		freq_desc_ann),
+	{}
+};
 
 /*
  * MSR-based CPU/TSC frequency discovery for certain CPUs.
@@ -71,18 +72,17 @@ static int match_cpu(u8 family, u8 model)
  */
 unsigned long cpu_khz_from_msr(void)
 {
-	u32 lo, hi, ratio, freq_id, freq;
+	u32 lo, hi, ratio, freq;
+	const struct freq_desc *freq_desc;
+	const struct x86_cpu_id *id;
 	unsigned long res;
-	int cpu_index;
 
-	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
+	id = x86_match_cpu(tsc_msr_cpu_ids);
+	if (!id)
 		return 0;
 
-	cpu_index = match_cpu(boot_cpu_data.x86, boot_cpu_data.x86_model);
-	if (cpu_index < 0)
-		return 0;
-
-	if (freq_desc_tables[cpu_index].msr_plat) {
+	freq_desc = (struct freq_desc *)id->driver_data;
+	if (freq_desc->msr_plat) {
 		rdmsr(MSR_PLATFORM_INFO, lo, hi);
 		ratio = (lo >> 8) & 0xff;
 	} else {
@@ -92,8 +92,9 @@ unsigned long cpu_khz_from_msr(void)
 
 	/* Get FSB FREQ ID */
 	rdmsr(MSR_FSB_FREQ, lo, hi);
-	freq_id = lo & 0x7;
-	freq = id_to_freq(cpu_index, freq_id);
+
+	/* Map CPU reference clock freq ID(0-7) to CPU reference clock freq(KHz) */
+	freq = freq_desc->freqs[lo & 0x7];
 
 	/* TSC frequency = maximum resolved freq * maximum resolved bus ratio */
 	res = freq * ratio;
-- 
cgit v1.2.3


From 5067b087cf5b2fa4de00443cdc6a66acb28a4953 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 29 Jun 2018 22:31:11 +0300
Subject: x86/tsc: Use SPDX identifier and update Intel copyright

Use SPDX identifier and update year in Intel copyright line.

While here, remove file name from the file itself.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Link: https://lkml.kernel.org/r/20180629193113.84425-5-andriy.shevchenko@linux.intel.com
---
 arch/x86/kernel/tsc_msr.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 1465aaee543a..f0951c2e9f28 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -1,10 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
- * tsc_msr.c - TSC frequency enumeration via MSR
+ * TSC frequency enumeration via MSR
  *
- * Copyright (C) 2013 Intel Corporation
+ * Copyright (C) 2013, 2018 Intel Corporation
  * Author: Bin Gao <bin.gao@intel.com>
- *
- * This file is released under the GPLv2.
  */
 
 #include <linux/kernel.h>
-- 
cgit v1.2.3


From d99e5da91b36db5c35ddaf3653b280ee060971da Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 29 Jun 2018 22:31:12 +0300
Subject: x86/platform/intel-mid: Remove custom TSC calibration

Since the commit

  7da7c1561366 ("x86, tsc: Add static (MSR) TSC calibration on Intel Atom SoCs")

introduced a common way for all Intel MID chips to get their TSC frequency
via MSRs, there is no need to keep a duplication in each of Intel MID
platform code.

Thus, remove the custom calibration code for good.

Note, there is slight difference in how to get frequency for (reserved?)
values in MSRs, i.e. legacy code enforces some defaults while new code just
uses 0 in that cases.

Suggested-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: Bin Gao <bin.gao@intel.com>
Link: https://lkml.kernel.org/r/20180629193113.84425-6-andriy.shevchenko@linux.intel.com
---
 arch/x86/include/asm/intel-mid.h        | 14 -------
 arch/x86/kernel/tsc_msr.c               |  5 +++
 arch/x86/platform/intel-mid/intel-mid.c |  6 ---
 arch/x86/platform/intel-mid/mfld.c      | 36 ----------------
 arch/x86/platform/intel-mid/mrfld.c     | 74 ---------------------------------
 5 files changed, 5 insertions(+), 130 deletions(-)

diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index fe04491130ae..376eb8ada62d 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -136,20 +136,6 @@ enum intel_mid_timer_options {
 
 extern enum intel_mid_timer_options intel_mid_timer_options;
 
-/*
- * Penwell uses spread spectrum clock, so the freq number is not exactly
- * the same as reported by MSR based on SDM.
- */
-#define FSB_FREQ_83SKU			83200
-#define FSB_FREQ_100SKU			99840
-#define FSB_FREQ_133SKU			133000
-
-#define FSB_FREQ_167SKU			167000
-#define FSB_FREQ_200SKU			200000
-#define FSB_FREQ_267SKU			267000
-#define FSB_FREQ_333SKU			333000
-#define FSB_FREQ_400SKU			400000
-
 /* Bus Select SoC Fuse value */
 #define BSEL_SOC_FUSE_MASK		0x7
 /* FSB 133MHz */
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index f0951c2e9f28..27ef714d886c 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -29,6 +29,11 @@ struct freq_desc {
 	u32 freqs[MAX_NUM_FREQS];
 };
 
+/*
+ * Penwell and Clovertrail use spread spectrum clock,
+ * so the freq number is not exactly the same as reported
+ * by MSR based on SDM.
+ */
 static const struct freq_desc freq_desc_pnw = {
 	0, { 0, 0, 0, 0, 0, 99840, 0, 83200 }
 };
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 2ebdf31d9996..aac15a4018d5 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -82,11 +82,6 @@ static void intel_mid_reboot(void)
 	intel_scu_ipc_simple_command(IPCMSG_COLD_RESET, 0);
 }
 
-static unsigned long __init intel_mid_calibrate_tsc(void)
-{
-	return 0;
-}
-
 static void __init intel_mid_setup_bp_timer(void)
 {
 	apbt_time_init();
@@ -191,7 +186,6 @@ void __init x86_intel_mid_early_setup(void)
 
 	x86_cpuinit.setup_percpu_clockev = apbt_setup_secondary_clock;
 
-	x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
 	x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
 
 	x86_init.pci.arch_init = intel_mid_pci_init;
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
index e42978d4deaf..e66b51f5c206 100644
--- a/arch/x86/platform/intel-mid/mfld.c
+++ b/arch/x86/platform/intel-mid/mfld.c
@@ -11,48 +11,12 @@
 
 #include <linux/init.h>
 
-#include <asm/apic.h>
 #include <asm/intel-mid.h>
-#include <asm/intel_mid_vrtc.h>
 
 #include "intel_mid_weak_decls.h"
 
-static unsigned long __init mfld_calibrate_tsc(void)
-{
-	unsigned long fast_calibrate;
-	u32 lo, hi, ratio, fsb;
-
-	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
-	pr_debug("IA32 perf status is 0x%x, 0x%0x\n", lo, hi);
-	ratio = (hi >> 8) & 0x1f;
-	pr_debug("ratio is %d\n", ratio);
-	if (!ratio) {
-		pr_err("read a zero ratio, should be incorrect!\n");
-		pr_err("force tsc ratio to 16 ...\n");
-		ratio = 16;
-	}
-	rdmsr(MSR_FSB_FREQ, lo, hi);
-	if ((lo & 0x7) == 0x7)
-		fsb = FSB_FREQ_83SKU;
-	else
-		fsb = FSB_FREQ_100SKU;
-	fast_calibrate = ratio * fsb;
-	pr_debug("read penwell tsc %lu khz\n", fast_calibrate);
-	lapic_timer_frequency = fsb * 1000 / HZ;
-
-	/*
-	 * TSC on Intel Atom SoCs is reliable and of known frequency.
-	 * See tsc_msr.c for details.
-	 */
-	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
-	return fast_calibrate;
-}
-
 static void __init penwell_arch_setup(void)
 {
-	x86_platform.calibrate_tsc = mfld_calibrate_tsc;
 }
 
 static struct intel_mid_ops penwell_ops = {
diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c
index ae7bdeb0e507..c5538ec2d62d 100644
--- a/arch/x86/platform/intel-mid/mrfld.c
+++ b/arch/x86/platform/intel-mid/mrfld.c
@@ -11,86 +11,12 @@
 
 #include <linux/init.h>
 
-#include <asm/apic.h>
 #include <asm/intel-mid.h>
 
 #include "intel_mid_weak_decls.h"
 
-static unsigned long __init tangier_calibrate_tsc(void)
-{
-	unsigned long fast_calibrate;
-	u32 lo, hi, ratio, fsb, bus_freq;
-
-	/* *********************** */
-	/* Compute TSC:Ratio * FSB */
-	/* *********************** */
-
-	/* Compute Ratio */
-	rdmsr(MSR_PLATFORM_INFO, lo, hi);
-	pr_debug("IA32 PLATFORM_INFO is 0x%x : %x\n", hi, lo);
-
-	ratio = (lo >> 8) & 0xFF;
-	pr_debug("ratio is %d\n", ratio);
-	if (!ratio) {
-		pr_err("Read a zero ratio, force tsc ratio to 4 ...\n");
-		ratio = 4;
-	}
-
-	/* Compute FSB */
-	rdmsr(MSR_FSB_FREQ, lo, hi);
-	pr_debug("Actual FSB frequency detected by SOC 0x%x : %x\n",
-			hi, lo);
-
-	bus_freq = lo & 0x7;
-	pr_debug("bus_freq = 0x%x\n", bus_freq);
-
-	if (bus_freq == 0)
-		fsb = FSB_FREQ_100SKU;
-	else if (bus_freq == 1)
-		fsb = FSB_FREQ_100SKU;
-	else if (bus_freq == 2)
-		fsb = FSB_FREQ_133SKU;
-	else if (bus_freq == 3)
-		fsb = FSB_FREQ_167SKU;
-	else if (bus_freq == 4)
-		fsb = FSB_FREQ_83SKU;
-	else if (bus_freq == 5)
-		fsb = FSB_FREQ_400SKU;
-	else if (bus_freq == 6)
-		fsb = FSB_FREQ_267SKU;
-	else if (bus_freq == 7)
-		fsb = FSB_FREQ_333SKU;
-	else {
-		BUG();
-		pr_err("Invalid bus_freq! Setting to minimal value!\n");
-		fsb = FSB_FREQ_100SKU;
-	}
-
-	/* TSC = FSB Freq * Resolved HFM Ratio */
-	fast_calibrate = ratio * fsb;
-	pr_debug("calculate tangier tsc %lu KHz\n", fast_calibrate);
-
-	/* ************************************ */
-	/* Calculate Local APIC Timer Frequency */
-	/* ************************************ */
-	lapic_timer_frequency = (fsb * 1000) / HZ;
-
-	pr_debug("Setting lapic_timer_frequency = %d\n",
-			lapic_timer_frequency);
-
-	/*
-	 * TSC on Intel Atom SoCs is reliable and of known frequency.
-	 * See tsc_msr.c for details.
-	 */
-	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
-
-	return fast_calibrate;
-}
-
 static void __init tangier_arch_setup(void)
 {
-	x86_platform.calibrate_tsc = tangier_calibrate_tsc;
 	x86_platform.legacy.rtc = 1;
 }
 
-- 
cgit v1.2.3


From 41afb1dfad4d6af0c716746f6a15f3230482955c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 29 Jun 2018 22:31:13 +0300
Subject: x86/platform/intel-mid: Remove per platform code

After custom TSC calibration gone, there is no more reason to have
custom platform code for each of Intel MID.

Thus, remove it for good.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Link: https://lkml.kernel.org/r/20180629193113.84425-7-andriy.shevchenko@linux.intel.com
---
 arch/x86/include/asm/intel-mid.h                   | 29 ------------------
 arch/x86/platform/intel-mid/Makefile               |  2 +-
 arch/x86/platform/intel-mid/intel-mid.c            | 17 +----------
 arch/x86/platform/intel-mid/intel_mid_weak_decls.h | 18 ------------
 arch/x86/platform/intel-mid/mfld.c                 | 34 ----------------------
 arch/x86/platform/intel-mid/mrfld.c                | 31 --------------------
 6 files changed, 2 insertions(+), 129 deletions(-)
 delete mode 100644 arch/x86/platform/intel-mid/intel_mid_weak_decls.h
 delete mode 100644 arch/x86/platform/intel-mid/mfld.c
 delete mode 100644 arch/x86/platform/intel-mid/mrfld.c

diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 376eb8ada62d..52f815a80539 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -80,35 +80,6 @@ enum intel_mid_cpu_type {
 
 extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
 
-/**
- * struct intel_mid_ops - Interface between intel-mid & sub archs
- * @arch_setup: arch_setup function to re-initialize platform
- *		structures (x86_init, x86_platform_init)
- *
- * This structure can be extended if any new interface is required
- * between intel-mid & its sub arch files.
- */
-struct intel_mid_ops {
-	void (*arch_setup)(void);
-};
-
-/* Helper API's for INTEL_MID_OPS_INIT */
-#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid)				\
-	[cpuid] = get_##cpuname##_ops
-
-/* Maximum number of CPU ops */
-#define MAX_CPU_OPS(a)			(sizeof(a)/sizeof(void *))
-
-/*
- * For every new cpu addition, a weak get_<cpuname>_ops() function needs be
- * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h.
- */
-#define INTEL_MID_OPS_INIT {							\
-	DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL),	\
-	DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW),	\
-	DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER)		\
-};
-
 #ifdef CONFIG_X86_INTEL_MID
 
 static inline enum intel_mid_cpu_type intel_mid_identify_cpu(void)
diff --git a/arch/x86/platform/intel-mid/Makefile b/arch/x86/platform/intel-mid/Makefile
index fa021dfab088..5cf886c867c2 100644
--- a/arch/x86/platform/intel-mid/Makefile
+++ b/arch/x86/platform/intel-mid/Makefile
@@ -1,4 +1,4 @@
-obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o mfld.o mrfld.o pwr.o
+obj-$(CONFIG_X86_INTEL_MID) += intel-mid.o intel_mid_vrtc.o pwr.o
 
 # SFI specific code
 ifdef CONFIG_X86_INTEL_MID
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index aac15a4018d5..56f66eafb94f 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -36,8 +36,6 @@
 #include <asm/apb_timer.h>
 #include <asm/reboot.h>
 
-#include "intel_mid_weak_decls.h"
-
 /*
  * the clockevent devices on Moorestown/Medfield can be APBT or LAPIC clock,
  * cmdline option x86_intel_mid_timer can be used to override the configuration
@@ -61,10 +59,6 @@
 
 enum intel_mid_timer_options intel_mid_timer_options;
 
-/* intel_mid_ops to store sub arch ops */
-static struct intel_mid_ops *intel_mid_ops;
-/* getter function for sub arch ops*/
-static void *(*get_intel_mid_ops[])(void) = INTEL_MID_OPS_INIT;
 enum intel_mid_cpu_type __intel_mid_cpu_chip;
 EXPORT_SYMBOL_GPL(__intel_mid_cpu_chip);
 
@@ -128,6 +122,7 @@ static void intel_mid_arch_setup(void)
 	case 0x3C:
 	case 0x4A:
 		__intel_mid_cpu_chip = INTEL_MID_CPU_CHIP_TANGIER;
+		x86_platform.legacy.rtc = 1;
 		break;
 	case 0x27:
 	default:
@@ -135,17 +130,7 @@ static void intel_mid_arch_setup(void)
 		break;
 	}
 
-	if (__intel_mid_cpu_chip < MAX_CPU_OPS(get_intel_mid_ops))
-		intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
-	else {
-		intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
-		pr_info("ARCH: Unknown SoC, assuming Penwell!\n");
-	}
-
 out:
-	if (intel_mid_ops->arch_setup)
-		intel_mid_ops->arch_setup();
-
 	/*
 	 * Intel MID platforms are using explicitly defined regulators.
 	 *
diff --git a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h b/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
deleted file mode 100644
index 3c1c3866d82b..000000000000
--- a/arch/x86/platform/intel-mid/intel_mid_weak_decls.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * intel_mid_weak_decls.h: Weak declarations of intel-mid.c
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-
-/* For every CPU addition a new get_<cpuname>_ops interface needs
- * to be added.
- */
-extern void *get_penwell_ops(void);
-extern void *get_cloverview_ops(void);
-extern void *get_tangier_ops(void);
diff --git a/arch/x86/platform/intel-mid/mfld.c b/arch/x86/platform/intel-mid/mfld.c
deleted file mode 100644
index e66b51f5c206..000000000000
--- a/arch/x86/platform/intel-mid/mfld.c
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- * mfld.c: Intel Medfield platform setup code
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-
-#include <asm/intel-mid.h>
-
-#include "intel_mid_weak_decls.h"
-
-static void __init penwell_arch_setup(void)
-{
-}
-
-static struct intel_mid_ops penwell_ops = {
-	.arch_setup = penwell_arch_setup,
-};
-
-void *get_penwell_ops(void)
-{
-	return &penwell_ops;
-}
-
-void *get_cloverview_ops(void)
-{
-	return &penwell_ops;
-}
diff --git a/arch/x86/platform/intel-mid/mrfld.c b/arch/x86/platform/intel-mid/mrfld.c
deleted file mode 100644
index c5538ec2d62d..000000000000
--- a/arch/x86/platform/intel-mid/mrfld.c
+++ /dev/null
@@ -1,31 +0,0 @@
-/*
- * Intel Merrifield platform specific setup code
- *
- * (C) Copyright 2013 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; version 2
- * of the License.
- */
-
-#include <linux/init.h>
-
-#include <asm/intel-mid.h>
-
-#include "intel_mid_weak_decls.h"
-
-static void __init tangier_arch_setup(void)
-{
-	x86_platform.legacy.rtc = 1;
-}
-
-/* tangier arch ops */
-static struct intel_mid_ops tangier_ops = {
-	.arch_setup = tangier_arch_setup,
-};
-
-void *get_tangier_ops(void)
-{
-	return &tangier_ops;
-}
-- 
cgit v1.2.3


From 418cc6ca06071e7b7d75c0d525d80a6f49a763d6 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:25:52 +0200
Subject: dma-fence: Make ->wait callback optional
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Almost everyone uses dma_fence_default_wait.

v2: Also remove the BUG_ON(!ops->wait) (Chris).

Reviewed-by: Christian König <christian.koenig@amd.com> (v1)
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-5-daniel.vetter@ffwll.ch
---
 drivers/dma-buf/dma-fence-array.c |  1 -
 drivers/dma-buf/dma-fence.c       |  8 +++++---
 drivers/dma-buf/sw_sync.c         |  1 -
 include/linux/dma-fence.h         | 13 ++++++++-----
 4 files changed, 13 insertions(+), 10 deletions(-)

diff --git a/drivers/dma-buf/dma-fence-array.c b/drivers/dma-buf/dma-fence-array.c
index dd1edfb27b61..a8c254497251 100644
--- a/drivers/dma-buf/dma-fence-array.c
+++ b/drivers/dma-buf/dma-fence-array.c
@@ -104,7 +104,6 @@ const struct dma_fence_ops dma_fence_array_ops = {
 	.get_timeline_name = dma_fence_array_get_timeline_name,
 	.enable_signaling = dma_fence_array_enable_signaling,
 	.signaled = dma_fence_array_signaled,
-	.wait = dma_fence_default_wait,
 	.release = dma_fence_array_release,
 };
 EXPORT_SYMBOL(dma_fence_array_ops);
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index ea343f992112..7a92f85a4cec 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -158,7 +158,10 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
 		return -EINVAL;
 
 	trace_dma_fence_wait_start(fence);
-	ret = fence->ops->wait(fence, intr, timeout);
+	if (fence->ops->wait)
+		ret = fence->ops->wait(fence, intr, timeout);
+	else
+		ret = dma_fence_default_wait(fence, intr, timeout);
 	trace_dma_fence_wait_end(fence);
 	return ret;
 }
@@ -556,8 +559,7 @@ dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
 	       spinlock_t *lock, u64 context, unsigned seqno)
 {
 	BUG_ON(!lock);
-	BUG_ON(!ops || !ops->wait ||
-	       !ops->get_driver_name || !ops->get_timeline_name);
+	BUG_ON(!ops || !ops->get_driver_name || !ops->get_timeline_name);
 
 	kref_init(&fence->refcount);
 	fence->ops = ops;
diff --git a/drivers/dma-buf/sw_sync.c b/drivers/dma-buf/sw_sync.c
index 3d78ca89a605..53c1d6d36a64 100644
--- a/drivers/dma-buf/sw_sync.c
+++ b/drivers/dma-buf/sw_sync.c
@@ -188,7 +188,6 @@ static const struct dma_fence_ops timeline_fence_ops = {
 	.get_timeline_name = timeline_fence_get_timeline_name,
 	.enable_signaling = timeline_fence_enable_signaling,
 	.signaled = timeline_fence_signaled,
-	.wait = dma_fence_default_wait,
 	.release = timeline_fence_release,
 	.fence_value_str = timeline_fence_value_str,
 	.timeline_value_str = timeline_fence_timeline_value_str,
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index c053d19e1e24..02dba8cd033d 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -191,11 +191,14 @@ struct dma_fence_ops {
 	/**
 	 * @wait:
 	 *
-	 * Custom wait implementation, or dma_fence_default_wait.
+	 * Custom wait implementation, defaults to dma_fence_default_wait() if
+	 * not set.
 	 *
-	 * Must not be NULL, set to dma_fence_default_wait for default implementation.
-	 * the dma_fence_default_wait implementation should work for any fence, as long
-	 * as enable_signaling works correctly.
+	 * The dma_fence_default_wait implementation should work for any fence, as long
+	 * as @enable_signaling works correctly. This hook allows drivers to
+	 * have an optimized version for the case where a process context is
+	 * already available, e.g. if @enable_signaling for the general case
+	 * needs to set up a worker thread.
 	 *
 	 * Must return -ERESTARTSYS if the wait is intr = true and the wait was
 	 * interrupted, and remaining jiffies if fence has signaled, or 0 if wait
@@ -203,7 +206,7 @@ struct dma_fence_ops {
 	 * which should be treated as if the fence is signaled. For example a hardware
 	 * lockup could be reported like that.
 	 *
-	 * This callback is mandatory.
+	 * This callback is optional.
 	 */
 	signed long (*wait)(struct dma_fence *fence,
 			    bool intr, signed long timeout);
-- 
cgit v1.2.3


From 95f9e2636a60424c27dc16c7674a03feef9e1303 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:25:53 +0200
Subject: drm/amdgpu: Remove unecessary dma_fence_ops
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

dma_fence_default_wait is the default now.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: Monk Liu <Monk.Liu@amd.com>
Cc: pding <Pixel.Ding@amd.com>
Cc: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Cc: Evan Quan <evan.quan@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Kees Cook <keescook@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-6-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c | 2 --
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c        | 1 -
 2 files changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
index 2c14025e5e76..574c1181ae9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_fence.c
@@ -173,7 +173,5 @@ static const struct dma_fence_ops amdkfd_fence_ops = {
 	.get_driver_name = amdkfd_fence_get_driver_name,
 	.get_timeline_name = amdkfd_fence_get_timeline_name,
 	.enable_signaling = amdkfd_fence_enable_signaling,
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
 	.release = amdkfd_fence_release,
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 39ec6b8890a1..2e9db0ebe678 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -646,7 +646,6 @@ static const struct dma_fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
 	.enable_signaling = amdgpu_fence_enable_signaling,
-	.wait = dma_fence_default_wait,
 	.release = amdgpu_fence_release,
 };
 
-- 
cgit v1.2.3


From 99e227cb03970287958d05ed41589cc82383534d Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:25:54 +0200
Subject: drm: Remove unecessary dma_fence_ops

dma_fence_default_wait is the default now, same for the trivial
enable_signaling implementation.

Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Sean Paul <seanpaul@chromium.org>
Cc: David Airlie <airlied@linux.ie>
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-7-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/drm_crtc.c              |  7 -------
 drivers/gpu/drm/drm_syncobj.c           |  1 -
 drivers/gpu/drm/scheduler/sched_fence.c | 11 -----------
 3 files changed, 19 deletions(-)

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index c762e75a2d94..a6906c4ab880 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -225,16 +225,9 @@ static const char *drm_crtc_fence_get_timeline_name(struct dma_fence *fence)
 	return crtc->timeline_name;
 }
 
-static bool drm_crtc_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 static const struct dma_fence_ops drm_crtc_fence_ops = {
 	.get_driver_name = drm_crtc_fence_get_driver_name,
 	.get_timeline_name = drm_crtc_fence_get_timeline_name,
-	.enable_signaling = drm_crtc_fence_enable_signaling,
-	.wait = dma_fence_default_wait,
 };
 
 struct dma_fence *drm_crtc_create_fence(struct drm_crtc *crtc)
diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
index d4f4ce484529..adb3cb27d31e 100644
--- a/drivers/gpu/drm/drm_syncobj.c
+++ b/drivers/gpu/drm/drm_syncobj.c
@@ -207,7 +207,6 @@ static const struct dma_fence_ops drm_syncobj_null_fence_ops = {
 	.get_driver_name = drm_syncobj_null_fence_get_name,
 	.get_timeline_name = drm_syncobj_null_fence_get_name,
 	.enable_signaling = drm_syncobj_null_fence_enable_signaling,
-	.wait = dma_fence_default_wait,
 	.release = NULL,
 };
 
diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index df4461648e3f..45d9c3affbea 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -81,11 +81,6 @@ static const char *drm_sched_fence_get_timeline_name(struct dma_fence *f)
 	return (const char *)fence->sched->name;
 }
 
-static bool drm_sched_fence_enable_signaling(struct dma_fence *f)
-{
-	return true;
-}
-
 /**
  * drm_sched_fence_free - free up the fence memory
  *
@@ -134,18 +129,12 @@ static void drm_sched_fence_release_finished(struct dma_fence *f)
 const struct dma_fence_ops drm_sched_fence_ops_scheduled = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
-	.enable_signaling = drm_sched_fence_enable_signaling,
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
 	.release = drm_sched_fence_release_scheduled,
 };
 
 const struct dma_fence_ops drm_sched_fence_ops_finished = {
 	.get_driver_name = drm_sched_fence_get_driver_name,
 	.get_timeline_name = drm_sched_fence_get_timeline_name,
-	.enable_signaling = drm_sched_fence_enable_signaling,
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
 	.release = drm_sched_fence_release_finished,
 };
 
-- 
cgit v1.2.3


From 51eebbc76b25c16e110d3a40a4f45b31e53b298e Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:25:55 +0200
Subject: drm/etnaviv: Remove unecessary dma_fence_ops

dma_fence_default_wait is the default now, same for the trivial
enable_signaling implementation.

Acked-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Lucas Stach <l.stach@pengutronix.de>
Cc: Russell King <linux+etnaviv@armlinux.org.uk>
Cc: Christian Gmeiner <christian.gmeiner@gmail.com>
Cc: etnaviv@lists.freedesktop.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-8-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 686f6552db48..19b09a59e30e 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1027,11 +1027,6 @@ static const char *etnaviv_fence_get_timeline_name(struct dma_fence *fence)
 	return dev_name(f->gpu->dev);
 }
 
-static bool etnaviv_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 static bool etnaviv_fence_signaled(struct dma_fence *fence)
 {
 	struct etnaviv_fence *f = to_etnaviv_fence(fence);
@@ -1049,9 +1044,7 @@ static void etnaviv_fence_release(struct dma_fence *fence)
 static const struct dma_fence_ops etnaviv_fence_ops = {
 	.get_driver_name = etnaviv_fence_get_driver_name,
 	.get_timeline_name = etnaviv_fence_get_timeline_name,
-	.enable_signaling = etnaviv_fence_enable_signaling,
 	.signaled = etnaviv_fence_signaled,
-	.wait = dma_fence_default_wait,
 	.release = etnaviv_fence_release,
 };
 
-- 
cgit v1.2.3


From 93f8252bcbec8b810ce5f01184c10f4a6b8b86eb Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:25:59 +0200
Subject: drm/qxl: Remove unecessary dma_fence_ops

The trivial enable_signaling implementation matches the default code.

v2: Fix up commit message to match patch better (Eric).

Cc: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dave Airlie <airlied@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-12-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/qxl/qxl_release.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/qxl/qxl_release.c b/drivers/gpu/drm/qxl/qxl_release.c
index 7cb214577275..e37f0097f744 100644
--- a/drivers/gpu/drm/qxl/qxl_release.c
+++ b/drivers/gpu/drm/qxl/qxl_release.c
@@ -50,12 +50,6 @@ static const char *qxl_get_timeline_name(struct dma_fence *fence)
 	return "release";
 }
 
-static bool qxl_nop_signaling(struct dma_fence *fence)
-{
-	/* fences are always automatically signaled, so just pretend we did this.. */
-	return true;
-}
-
 static long qxl_fence_wait(struct dma_fence *fence, bool intr,
 			   signed long timeout)
 {
@@ -119,7 +113,6 @@ signaled:
 static const struct dma_fence_ops qxl_fence_ops = {
 	.get_driver_name = qxl_get_driver_name,
 	.get_timeline_name = qxl_get_timeline_name,
-	.enable_signaling = qxl_nop_signaling,
 	.wait = qxl_fence_wait,
 };
 
-- 
cgit v1.2.3


From 144b09795528780d96491d70619ccbadac324e68 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Fri, 4 May 2018 16:09:01 +0200
Subject: drm/vc4: Remove unecessary dma_fence_ops

dma_fence_default_wait is the default now, same for the trivial
enable_signaling implementation.

v2: Also remove the relase hook, dma_fence_free is the default.

Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180504140901.27471-1-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/vc4/vc4_fence.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_fence.c b/drivers/gpu/drm/vc4/vc4_fence.c
index dbf5a5a5d5f5..580214e2158c 100644
--- a/drivers/gpu/drm/vc4/vc4_fence.c
+++ b/drivers/gpu/drm/vc4/vc4_fence.c
@@ -33,11 +33,6 @@ static const char *vc4_fence_get_timeline_name(struct dma_fence *fence)
 	return "vc4-v3d";
 }
 
-static bool vc4_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 static bool vc4_fence_signaled(struct dma_fence *fence)
 {
 	struct vc4_fence *f = to_vc4_fence(fence);
@@ -49,8 +44,5 @@ static bool vc4_fence_signaled(struct dma_fence *fence)
 const struct dma_fence_ops vc4_fence_ops = {
 	.get_driver_name = vc4_fence_get_driver_name,
 	.get_timeline_name = vc4_fence_get_timeline_name,
-	.enable_signaling = vc4_fence_enable_signaling,
 	.signaled = vc4_fence_signaled,
-	.wait = dma_fence_default_wait,
-	.release = dma_fence_free,
 };
-- 
cgit v1.2.3


From 64e625cf53539fea4fcc5410d64c619fdbf3d225 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Thu, 3 May 2018 16:26:02 +0200
Subject: drm/virtio: Remove unecessary dma_fence_ops

dma_fence_default_wait is the default now, same for the trivial
enable_signaling implementation.

Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: David Airlie <airlied@linux.ie>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: virtualization@lists.linux-foundation.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180503142603.28513-15-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/virtio/virtgpu_fence.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/virtio/virtgpu_fence.c b/drivers/gpu/drm/virtio/virtgpu_fence.c
index 23353521f903..00c742a441bf 100644
--- a/drivers/gpu/drm/virtio/virtgpu_fence.c
+++ b/drivers/gpu/drm/virtio/virtgpu_fence.c
@@ -36,11 +36,6 @@ static const char *virtio_get_timeline_name(struct dma_fence *f)
 	return "controlq";
 }
 
-static bool virtio_enable_signaling(struct dma_fence *f)
-{
-	return true;
-}
-
 static bool virtio_signaled(struct dma_fence *f)
 {
 	struct virtio_gpu_fence *fence = to_virtio_fence(f);
@@ -67,9 +62,7 @@ static void virtio_timeline_value_str(struct dma_fence *f, char *str, int size)
 static const struct dma_fence_ops virtio_fence_ops = {
 	.get_driver_name     = virtio_get_driver_name,
 	.get_timeline_name   = virtio_get_timeline_name,
-	.enable_signaling    = virtio_enable_signaling,
 	.signaled            = virtio_signaled,
-	.wait                = dma_fence_default_wait,
 	.fence_value_str     = virtio_fence_value_str,
 	.timeline_value_str  = virtio_timeline_value_str,
 };
-- 
cgit v1.2.3


From a1de8d0a7e2cc79dad6d469901b3b5d4c94c4554 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 3 Jul 2018 15:30:16 +0300
Subject: drm/i810: off by one in i810_dma_vertex()

If vertex->idx == dma->buf_count then we end up reading one element
beyond the end of the dma->buflist[] array.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703123015.kma7v7rwtdy4urce@kili.mountain
---
 drivers/gpu/drm/i810/i810_dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i810/i810_dma.c b/drivers/gpu/drm/i810/i810_dma.c
index 576a417690d4..3b378936f575 100644
--- a/drivers/gpu/drm/i810/i810_dma.c
+++ b/drivers/gpu/drm/i810/i810_dma.c
@@ -934,7 +934,7 @@ static int i810_dma_vertex(struct drm_device *dev, void *data,
 	DRM_DEBUG("idx %d used %d discard %d\n",
 		  vertex->idx, vertex->used, vertex->discard);
 
-	if (vertex->idx < 0 || vertex->idx > dma->buf_count)
+	if (vertex->idx < 0 || vertex->idx >= dma->buf_count)
 		return -EINVAL;
 
 	i810_dma_dispatch_vertex(dev,
-- 
cgit v1.2.3


From de10eba0f68a161f3176b710b6e27d291d48aac2 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 3 Jul 2018 15:29:21 +0300
Subject: drm/vgem: off by one in vgem_gem_fault()

If page_offset is == num_pages then we end up reading beyond the end of
obj->pages[].

Fixes: af33a9190d02 ("drm/vgem: Enable dmabuf import interfaces")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703122921.brlfxl4vx2ybvrd2@kili.mountain
---
 drivers/gpu/drm/vgem/vgem_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vgem/vgem_drv.c b/drivers/gpu/drm/vgem/vgem_drv.c
index c64a85950c82..0e5620f76ee0 100644
--- a/drivers/gpu/drm/vgem/vgem_drv.c
+++ b/drivers/gpu/drm/vgem/vgem_drv.c
@@ -74,7 +74,7 @@ static vm_fault_t vgem_gem_fault(struct vm_fault *vmf)
 
 	num_pages = DIV_ROUND_UP(obj->base.size, PAGE_SIZE);
 
-	if (page_offset > num_pages)
+	if (page_offset >= num_pages)
 		return VM_FAULT_SIGBUS;
 
 	mutex_lock(&obj->pages_lock);
-- 
cgit v1.2.3


From c72051d5778a9c0e5df31d6553a6fa3507b3685c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 16:58:24 +0200
Subject: audit: use ktime_get_coarse_ts64() for time access

The API got renamed for consistency with the other time accessors,
this changes the audit caller as well.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/audit.c   | 2 +-
 kernel/auditsc.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/audit.c b/kernel/audit.c
index 0f3222e4edde..e17bc697d11c 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1721,7 +1721,7 @@ static inline void audit_get_stamp(struct audit_context *ctx,
 				   struct timespec64 *t, unsigned int *serial)
 {
 	if (!ctx || !auditsc_get_stamp(ctx, t, serial)) {
-		*t = current_kernel_time64();
+		ktime_get_coarse_ts64(t);
 		*serial = audit_serial();
 	}
 }
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index d762e0b8160e..f6a0cb32d76e 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1540,10 +1540,10 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
 	context->argv[2]    = a3;
 	context->argv[3]    = a4;
 	context->serial     = 0;
-	context->ctime = current_kernel_time64();
 	context->in_syscall = 1;
 	context->current_state  = state;
 	context->ppid       = 0;
+	ktime_get_coarse_ts64(&context->ctime);
 }
 
 /**
-- 
cgit v1.2.3


From c18a9c096683dd30300686ffc755443816893968 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 2 Jul 2018 07:09:32 -0500
Subject: net: stmmac_tc: use 64-bit arithmetic instead of 32-bit

Add suffix UL to constant 1024 in order to give the compiler complete
information about the proper arithmetic to use. Notice that this
constant is used in a context that expects an expression of type
u64 (64 bits, unsigned) and  following expressions are currently
being evaluated using 32-bit arithmetic:

qopt->idleslope * 1024 * ptr
qopt->hicredit * 1024 * 8
qopt->locredit * 1024 * 8

Addresses-Coverity-ID: 1470246 ("Unintentional integer overflow")
Addresses-Coverity-ID: 1470248 ("Unintentional integer overflow")
Addresses-Coverity-ID: 1470249 ("Unintentional integer overflow")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Jose Abreu <joabreu@synopsys.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 0b0fca0200b2..8fedc288d138 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -321,7 +321,7 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 	speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000;
 
 	/* Final adjustments for HW */
-	value = qopt->idleslope * 1024 * ptr;
+	value = qopt->idleslope * 1024UL * ptr;
 	do_div(value, speed_div);
 	priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0);
 
@@ -329,10 +329,10 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 	do_div(value, speed_div);
 	priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0);
 
-	value = qopt->hicredit * 1024 * 8;
+	value = qopt->hicredit * 1024UL * 8;
 	priv->plat->tx_queues_cfg[queue].high_credit = value & GENMASK(31, 0);
 
-	value = qopt->locredit * 1024 * 8;
+	value = qopt->locredit * 1024UL * 8;
 	priv->plat->tx_queues_cfg[queue].low_credit = value & GENMASK(31, 0);
 
 	ret = stmmac_config_cbs(priv, priv->hw,
-- 
cgit v1.2.3


From c1af5427954b6a7f8c34b9778b1e1c9f1d9af302 Mon Sep 17 00:00:00 2001
From: Anton Mikaev <amikaev@aquantia.com>
Date: Mon, 2 Jul 2018 17:03:35 +0300
Subject: net: aquantia: Ethtool based ring size configuration

Implemented ring size setup, min/max validation and reconfiguration in
runtime.

Signed-off-by: Anton Mikaev <amikaev@aquantia.com>
Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    | 61 ++++++++++++++++++++++
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  9 +++-
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    |  4 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c  | 46 ++++++++--------
 .../aquantia/atlantic/hw_atl/hw_atl_a0_internal.h  |  8 +++
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  | 50 +++++++++---------
 .../aquantia/atlantic/hw_atl/hw_atl_b0_internal.h  |  8 +++
 7 files changed, 136 insertions(+), 50 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index f2d8063a2cef..06242154a002 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -11,6 +11,7 @@
 
 #include "aq_ethtool.h"
 #include "aq_nic.h"
+#include "aq_vec.h"
 
 static void aq_ethtool_get_regs(struct net_device *ndev,
 				struct ethtool_regs *regs, void *p)
@@ -284,6 +285,64 @@ static int aq_ethtool_set_coalesce(struct net_device *ndev,
 	return aq_nic_update_interrupt_moderation_settings(aq_nic);
 }
 
+static void aq_get_ringparam(struct net_device *ndev,
+			     struct ethtool_ringparam *ring)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(aq_nic);
+
+	ring->rx_pending = aq_nic_cfg->rxds;
+	ring->tx_pending = aq_nic_cfg->txds;
+
+	ring->rx_max_pending = aq_nic_cfg->aq_hw_caps->rxds_max;
+	ring->tx_max_pending = aq_nic_cfg->aq_hw_caps->txds_max;
+}
+
+static int aq_set_ringparam(struct net_device *ndev,
+			    struct ethtool_ringparam *ring)
+{
+	int err = 0;
+	bool ndev_running = false;
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	struct aq_nic_cfg_s *aq_nic_cfg = aq_nic_get_cfg(aq_nic);
+	const struct aq_hw_caps_s *hw_caps = aq_nic_cfg->aq_hw_caps;
+
+	if (ring->rx_mini_pending || ring->rx_jumbo_pending) {
+		err = -EOPNOTSUPP;
+		goto err_exit;
+	}
+
+	if (netif_running(ndev)) {
+		ndev_running = true;
+		dev_close(ndev);
+	}
+
+	aq_nic_free_vectors(aq_nic);
+
+	aq_nic_cfg->rxds = max(ring->rx_pending, hw_caps->rxds_min);
+	aq_nic_cfg->rxds = min(aq_nic_cfg->rxds, hw_caps->rxds_max);
+	aq_nic_cfg->rxds = ALIGN(aq_nic_cfg->rxds, AQ_HW_RXD_MULTIPLE);
+
+	aq_nic_cfg->txds = max(ring->tx_pending, hw_caps->txds_min);
+	aq_nic_cfg->txds = min(aq_nic_cfg->txds, hw_caps->txds_max);
+	aq_nic_cfg->txds = ALIGN(aq_nic_cfg->txds, AQ_HW_TXD_MULTIPLE);
+
+	for (aq_nic->aq_vecs = 0; aq_nic->aq_vecs < aq_nic_cfg->vecs;
+	     aq_nic->aq_vecs++) {
+		aq_nic->aq_vec[aq_nic->aq_vecs] =
+		    aq_vec_alloc(aq_nic, aq_nic->aq_vecs, aq_nic_cfg);
+		if (unlikely(!aq_nic->aq_vec[aq_nic->aq_vecs])) {
+			err = -ENOMEM;
+			goto err_exit;
+		}
+	}
+	if (ndev_running)
+		err = dev_open(ndev);
+
+err_exit:
+	return err;
+}
+
 const struct ethtool_ops aq_ethtool_ops = {
 	.get_link            = aq_ethtool_get_link,
 	.get_regs_len        = aq_ethtool_get_regs_len,
@@ -291,6 +350,8 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.get_drvinfo         = aq_ethtool_get_drvinfo,
 	.get_strings         = aq_ethtool_get_strings,
 	.get_rxfh_indir_size = aq_ethtool_get_rss_indir_size,
+	.get_ringparam       = aq_get_ringparam,
+	.set_ringparam       = aq_set_ringparam,
 	.get_rxfh_key_size   = aq_ethtool_get_rss_key_size,
 	.get_rxfh            = aq_ethtool_get_rss,
 	.get_rxnfc           = aq_ethtool_get_rxnfc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index a2d416b24ffc..904cdfd74cd7 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -24,8 +24,10 @@ struct aq_hw_caps_s {
 	u64 link_speed_msk;
 	unsigned int hw_priv_flags;
 	u32 media_type;
-	u32 rxds;
-	u32 txds;
+	u32 rxds_max;
+	u32 txds_max;
+	u32 rxds_min;
+	u32 txds_min;
 	u32 txhwb_alignment;
 	u32 irq_mask;
 	u32 vecs;
@@ -98,6 +100,9 @@ struct aq_stats_s {
 #define AQ_HW_MEDIA_TYPE_TP    1U
 #define AQ_HW_MEDIA_TYPE_FIBRE 2U
 
+#define AQ_HW_TXD_MULTIPLE 8U
+#define AQ_HW_RXD_MULTIPLE 8U
+
 struct aq_hw_s {
 	atomic_t flags;
 	u8 rbl_enabled:1;
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index 1a1a6380c128..ba6bbcfb7287 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -89,8 +89,8 @@ void aq_nic_cfg_start(struct aq_nic_s *self)
 	aq_nic_rss_init(self, cfg->num_rss_queues);
 
 	/*descriptors */
-	cfg->rxds = min(cfg->aq_hw_caps->rxds, AQ_CFG_RXDS_DEF);
-	cfg->txds = min(cfg->aq_hw_caps->txds, AQ_CFG_TXDS_DEF);
+	cfg->rxds = min(cfg->aq_hw_caps->rxds_max, AQ_CFG_RXDS_DEF);
+	cfg->txds = min(cfg->aq_hw_caps->txds_max, AQ_CFG_TXDS_DEF);
 
 	/*rss rings */
 	cfg->vecs = min(cfg->aq_hw_caps->vecs, AQ_CFG_VECS_DEF);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 67e2f9fb9402..7fd6a7e54fc6 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -19,29 +19,31 @@
 #include "hw_atl_a0_internal.h"
 
 #define DEFAULT_A0_BOARD_BASIC_CAPABILITIES \
-	.is_64_dma = true, \
-	.msix_irqs = 4U, \
-	.irq_mask = ~0U, \
-	.vecs = HW_ATL_A0_RSS_MAX, \
-	.tcs = HW_ATL_A0_TC_MAX, \
-	.rxd_alignment = 1U, \
-	.rxd_size = HW_ATL_A0_RXD_SIZE, \
-	.rxds = 248U, \
-	.txd_alignment = 1U, \
-	.txd_size = HW_ATL_A0_TXD_SIZE, \
-	.txds = 8U * 1024U, \
-	.txhwb_alignment = 4096U, \
-	.tx_rings = HW_ATL_A0_TX_RINGS, \
-	.rx_rings = HW_ATL_A0_RX_RINGS, \
-	.hw_features = NETIF_F_HW_CSUM | \
-			NETIF_F_RXHASH | \
-			NETIF_F_RXCSUM | \
-			NETIF_F_SG | \
-			NETIF_F_TSO, \
+	.is_64_dma = true,		  \
+	.msix_irqs = 4U,		  \
+	.irq_mask = ~0U,		  \
+	.vecs = HW_ATL_A0_RSS_MAX,	  \
+	.tcs = HW_ATL_A0_TC_MAX,	  \
+	.rxd_alignment = 1U,		  \
+	.rxd_size = HW_ATL_A0_RXD_SIZE,   \
+	.rxds_max = HW_ATL_A0_MAX_RXD,    \
+	.rxds_min = HW_ATL_A0_MIN_RXD,    \
+	.txd_alignment = 1U,		  \
+	.txd_size = HW_ATL_A0_TXD_SIZE,   \
+	.txds_max = HW_ATL_A0_MAX_TXD,    \
+	.txds_min = HW_ATL_A0_MIN_RXD,    \
+	.txhwb_alignment = 4096U,	  \
+	.tx_rings = HW_ATL_A0_TX_RINGS,   \
+	.rx_rings = HW_ATL_A0_RX_RINGS,   \
+	.hw_features = NETIF_F_HW_CSUM |  \
+			NETIF_F_RXHASH |  \
+			NETIF_F_RXCSUM |  \
+			NETIF_F_SG |	  \
+			NETIF_F_TSO,	  \
 	.hw_priv_flags = IFF_UNICAST_FLT, \
-	.flow_control = true, \
-	.mtu = HW_ATL_A0_MTU_JUMBO, \
-	.mac_regs_count = 88, \
+	.flow_control = true,		  \
+	.mtu = HW_ATL_A0_MTU_JUMBO,       \
+	.mac_regs_count = 88,		  \
 	.hw_alive_check_addr = 0x10U
 
 const struct aq_hw_caps_s hw_atl_a0_caps_aqc100 = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
index 1d8855558d74..3c94cff57876 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0_internal.h
@@ -88,4 +88,12 @@
 
 #define HW_ATL_A0_FW_VER_EXPECTED 0x01050006U
 
+#define HW_ATL_A0_MIN_RXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
+#define HW_ATL_A0_MIN_TXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_TXD_MULTIPLE))
+
+#define HW_ATL_A0_MAX_RXD 8184U
+#define HW_ATL_A0_MAX_TXD 8184U
+
 #endif /* HW_ATL_A0_INTERNAL_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 819f6bcf9b4e..4ea15b9a869e 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -20,30 +20,32 @@
 #include "hw_atl_llh_internal.h"
 
 #define DEFAULT_B0_BOARD_BASIC_CAPABILITIES \
-	.is_64_dma = true,	\
-	.msix_irqs = 4U,	\
-	.irq_mask = ~0U,	\
-	.vecs = HW_ATL_B0_RSS_MAX,	\
-	.tcs = HW_ATL_B0_TC_MAX,	\
-	.rxd_alignment = 1U,		\
-	.rxd_size = HW_ATL_B0_RXD_SIZE, \
-	.rxds = 4U * 1024U,		\
-	.txd_alignment = 1U,		\
-	.txd_size = HW_ATL_B0_TXD_SIZE, \
-	.txds = 8U * 1024U,		\
-	.txhwb_alignment = 4096U,	\
-	.tx_rings = HW_ATL_B0_TX_RINGS, \
-	.rx_rings = HW_ATL_B0_RX_RINGS, \
-	.hw_features = NETIF_F_HW_CSUM | \
-			NETIF_F_RXCSUM | \
-			NETIF_F_RXHASH | \
-			NETIF_F_SG |  \
-			NETIF_F_TSO | \
-			NETIF_F_LRO,  \
-	.hw_priv_flags = IFF_UNICAST_FLT,   \
-	.flow_control = true,		\
-	.mtu = HW_ATL_B0_MTU_JUMBO,	\
-	.mac_regs_count = 88,		\
+	.is_64_dma = true,		  \
+	.msix_irqs = 4U,		  \
+	.irq_mask = ~0U,		  \
+	.vecs = HW_ATL_B0_RSS_MAX,	  \
+	.tcs = HW_ATL_B0_TC_MAX,	  \
+	.rxd_alignment = 1U,		  \
+	.rxd_size = HW_ATL_B0_RXD_SIZE,   \
+	.rxds_max = HW_ATL_B0_MAX_RXD,    \
+	.rxds_min = HW_ATL_B0_MIN_RXD,    \
+	.txd_alignment = 1U,		  \
+	.txd_size = HW_ATL_B0_TXD_SIZE,   \
+	.txds_max = HW_ATL_B0_MAX_TXD,    \
+	.txds_min = HW_ATL_B0_MIN_TXD,    \
+	.txhwb_alignment = 4096U,	  \
+	.tx_rings = HW_ATL_B0_TX_RINGS,   \
+	.rx_rings = HW_ATL_B0_RX_RINGS,   \
+	.hw_features = NETIF_F_HW_CSUM |  \
+			NETIF_F_RXCSUM |  \
+			NETIF_F_RXHASH |  \
+			NETIF_F_SG |      \
+			NETIF_F_TSO |     \
+			NETIF_F_LRO,      \
+	.hw_priv_flags = IFF_UNICAST_FLT, \
+	.flow_control = true,		  \
+	.mtu = HW_ATL_B0_MTU_JUMBO,	  \
+	.mac_regs_count = 88,		  \
 	.hw_alive_check_addr = 0x10U
 
 const struct aq_hw_caps_s hw_atl_b0_caps_aqc100 = {
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
index 405d1455c222..28568f5fa74b 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0_internal.h
@@ -142,6 +142,14 @@
 #define HW_ATL_INTR_MODER_MAX  0x1FF
 #define HW_ATL_INTR_MODER_MIN  0xFF
 
+#define HW_ATL_B0_MIN_RXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_RXD_MULTIPLE))
+#define HW_ATL_B0_MIN_TXD \
+	(ALIGN(AQ_CFG_SKB_FRAGS_MAX + 1U, AQ_HW_TXD_MULTIPLE))
+
+#define HW_ATL_B0_MAX_RXD 8184U
+#define HW_ATL_B0_MAX_TXD 8184U
+
 /* HW layer capabilities */
 
 #endif /* HW_ATL_B0_INTERNAL_H */
-- 
cgit v1.2.3


From 44e00dd8eb94b894b7f60009c251acf24b8bbaf1 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Mon, 2 Jul 2018 17:03:36 +0300
Subject: net: aquantia: Improve adapter init/deinit logic

We now pass link drop status to FW on init/deinit. This is required
to inform FW that driver took/released a control on link.
FW then will manage its own state and device power profile based
on this information. To improve management we remove mpi_set
function which ambiguously took both state and speed parameters.

Deinit callback is now a part of FW ops, as it actually manages the FW.

Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  9 ++--
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    |  2 +-
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c  |  1 -
 .../ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c  |  1 -
 .../aquantia/atlantic/hw_atl/hw_atl_utils.c        | 53 ++++++++++++----------
 .../aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c   | 31 ++++++++++++-
 6 files changed, 66 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 904cdfd74cd7..3aa36d5765bc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -202,25 +202,28 @@ struct aq_hw_ops {
 
 	int (*hw_get_fw_version)(struct aq_hw_s *self, u32 *fw_version);
 
-	int (*hw_deinit)(struct aq_hw_s *self);
-
 	int (*hw_set_power)(struct aq_hw_s *self, unsigned int power_state);
 };
 
 struct aq_fw_ops {
 	int (*init)(struct aq_hw_s *self);
 
+	int (*deinit)(struct aq_hw_s *self);
+
 	int (*reset)(struct aq_hw_s *self);
 
 	int (*get_mac_permanent)(struct aq_hw_s *self, u8 *mac);
 
 	int (*set_link_speed)(struct aq_hw_s *self, u32 speed);
 
-	int (*set_state)(struct aq_hw_s *self, enum hal_atl_utils_fw_state_e state);
+	int (*set_state)(struct aq_hw_s *self,
+			 enum hal_atl_utils_fw_state_e state);
 
 	int (*update_link_status)(struct aq_hw_s *self);
 
 	int (*update_stats)(struct aq_hw_s *self);
+
+	int (*set_flow_control)(struct aq_hw_s *self);
 };
 
 #endif /* AQ_HW_H */
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index ba6bbcfb7287..e8cf93adc445 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -879,7 +879,7 @@ void aq_nic_deinit(struct aq_nic_s *self)
 		aq_vec_deinit(aq_vec);
 
 	if (self->power_state == AQ_HW_POWER_STATE_D0) {
-		(void)self->aq_hw_ops->hw_deinit(self->aq_hw);
+		(void)self->aq_fw_ops->deinit(self->aq_hw);
 	} else {
 		(void)self->aq_hw_ops->hw_set_power(self->aq_hw,
 						   self->power_state);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
index 7fd6a7e54fc6..ed7fe6f2e360 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_a0.c
@@ -877,7 +877,6 @@ static int hw_atl_a0_hw_ring_rx_stop(struct aq_hw_s *self,
 const struct aq_hw_ops hw_atl_ops_a0 = {
 	.hw_set_mac_address   = hw_atl_a0_hw_mac_addr_set,
 	.hw_init              = hw_atl_a0_hw_init,
-	.hw_deinit            = hw_atl_utils_hw_deinit,
 	.hw_set_power         = hw_atl_utils_hw_set_power,
 	.hw_reset             = hw_atl_a0_hw_reset,
 	.hw_start             = hw_atl_a0_hw_start,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
index 4ea15b9a869e..9dd4f497676c 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_b0.c
@@ -935,7 +935,6 @@ static int hw_atl_b0_hw_ring_rx_stop(struct aq_hw_s *self,
 const struct aq_hw_ops hw_atl_ops_b0 = {
 	.hw_set_mac_address   = hw_atl_b0_hw_mac_addr_set,
 	.hw_init              = hw_atl_b0_hw_init,
-	.hw_deinit            = hw_atl_utils_hw_deinit,
 	.hw_set_power         = hw_atl_utils_hw_set_power,
 	.hw_reset             = hw_atl_b0_hw_reset,
 	.hw_start             = hw_atl_b0_hw_start,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index e652d86b87d4..9d0a96dda8bc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -30,10 +30,11 @@
 #define HW_ATL_MPI_CONTROL_ADR  0x0368U
 #define HW_ATL_MPI_STATE_ADR    0x036CU
 
-#define HW_ATL_MPI_STATE_MSK    0x00FFU
-#define HW_ATL_MPI_STATE_SHIFT  0U
-#define HW_ATL_MPI_SPEED_MSK    0xFFFF0000U
-#define HW_ATL_MPI_SPEED_SHIFT  16U
+#define HW_ATL_MPI_STATE_MSK      0x00FFU
+#define HW_ATL_MPI_STATE_SHIFT    0U
+#define HW_ATL_MPI_SPEED_MSK      0x00FF0000U
+#define HW_ATL_MPI_SPEED_SHIFT    16U
+#define HW_ATL_MPI_DIRTY_WAKE_MSK 0x02000000U
 
 #define HW_ATL_MPI_DAISY_CHAIN_STATUS	0x704
 #define HW_ATL_MPI_BOOT_EXIT_CODE	0x388
@@ -521,23 +522,24 @@ void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 err_exit:;
 }
 
-static int hw_atl_utils_mpi_set_speed(struct aq_hw_s *self, u32 speed)
+int hw_atl_utils_mpi_set_speed(struct aq_hw_s *self, u32 speed)
 {
 	u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
 
-	val = (val & HW_ATL_MPI_STATE_MSK) | (speed << HW_ATL_MPI_SPEED_SHIFT);
+	val = val & ~HW_ATL_MPI_SPEED_MSK;
+	val |= speed << HW_ATL_MPI_SPEED_SHIFT;
 	aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR, val);
 
 	return 0;
 }
 
-void hw_atl_utils_mpi_set(struct aq_hw_s *self,
-			  enum hal_atl_utils_fw_state_e state,
-			  u32 speed)
+int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
+			       enum hal_atl_utils_fw_state_e state)
 {
 	int err = 0;
 	u32 transaction_id = 0;
 	struct hw_aq_atl_utils_mbox_header mbox;
+	u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
 
 	if (state == MPI_RESET) {
 		hw_atl_utils_mpi_read_mbox(self, &mbox);
@@ -551,21 +553,21 @@ void hw_atl_utils_mpi_set(struct aq_hw_s *self,
 		if (err < 0)
 			goto err_exit;
 	}
+	/* On interface DEINIT we disable DW (raise bit)
+	 * Otherwise enable DW (clear bit)
+	 */
+	if (state == MPI_DEINIT || state == MPI_POWER)
+		val |= HW_ATL_MPI_DIRTY_WAKE_MSK;
+	else
+		val &= ~HW_ATL_MPI_DIRTY_WAKE_MSK;
 
-	aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR,
-			(speed << HW_ATL_MPI_SPEED_SHIFT) | state);
+	/* Set new state bits */
+	val = val & ~HW_ATL_MPI_STATE_MSK;
+	val |= state & HW_ATL_MPI_STATE_MSK;
 
-err_exit:;
-}
-
-static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
-				      enum hal_atl_utils_fw_state_e state)
-{
-	u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
-
-	val = state | (val & HW_ATL_MPI_SPEED_MSK);
 	aq_hw_write_reg(self, HW_ATL_MPI_CONTROL_ADR, val);
-	return 0;
+err_exit:
+	return err;
 }
 
 int hw_atl_utils_mpi_get_link_status(struct aq_hw_s *self)
@@ -721,16 +723,18 @@ void hw_atl_utils_hw_chip_features_init(struct aq_hw_s *self, u32 *p)
 	*p = chip_features;
 }
 
-int hw_atl_utils_hw_deinit(struct aq_hw_s *self)
+static int hw_atl_fw1x_deinit(struct aq_hw_s *self)
 {
-	hw_atl_utils_mpi_set(self, MPI_DEINIT, 0x0U);
+	hw_atl_utils_mpi_set_speed(self, 0);
+	hw_atl_utils_mpi_set_state(self, MPI_DEINIT);
 	return 0;
 }
 
 int hw_atl_utils_hw_set_power(struct aq_hw_s *self,
 			      unsigned int power_state)
 {
-	hw_atl_utils_mpi_set(self, MPI_POWER, 0x0U);
+	hw_atl_utils_mpi_set_speed(self, 0);
+	hw_atl_utils_mpi_set_state(self, MPI_POWER);
 	return 0;
 }
 
@@ -823,6 +827,7 @@ int hw_atl_utils_get_fw_version(struct aq_hw_s *self, u32 *fw_version)
 
 const struct aq_fw_ops aq_fw_1x_ops = {
 	.init = hw_atl_utils_mpi_create,
+	.deinit = hw_atl_fw1x_deinit,
 	.reset = NULL,
 	.get_mac_permanent = hw_atl_utils_get_mac_permanent,
 	.set_link_speed = hw_atl_utils_mpi_set_speed,
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index 39cd3a27fe77..a3e95f076bf0 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -28,6 +28,10 @@
 #define HW_ATL_FW2X_MPI_STATE_ADDR	0x370
 #define HW_ATL_FW2X_MPI_STATE2_ADDR	0x374
 
+static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed);
+static int aq_fw2x_set_state(struct aq_hw_s *self,
+			     enum hal_atl_utils_fw_state_e state);
+
 static int aq_fw2x_init(struct aq_hw_s *self)
 {
 	int err = 0;
@@ -39,6 +43,16 @@ static int aq_fw2x_init(struct aq_hw_s *self)
 	return err;
 }
 
+static int aq_fw2x_deinit(struct aq_hw_s *self)
+{
+	int err = aq_fw2x_set_link_speed(self, 0);
+
+	if (!err)
+		err = aq_fw2x_set_state(self, MPI_DEINIT);
+
+	return err;
+}
+
 static enum hw_atl_fw2x_rate link_speed_mask_2fw2x_ratemask(u32 speed)
 {
 	enum hw_atl_fw2x_rate rate = 0;
@@ -76,7 +90,21 @@ static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed)
 static int aq_fw2x_set_state(struct aq_hw_s *self,
 			     enum hal_atl_utils_fw_state_e state)
 {
-	/* No explicit state in 2x fw */
+	u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+	switch (state) {
+	case MPI_INIT:
+		mpi_state &= ~BIT(CAPS_HI_LINK_DROP);
+		break;
+	case MPI_DEINIT:
+		mpi_state |= BIT(CAPS_HI_LINK_DROP);
+		break;
+	case MPI_RESET:
+	case MPI_POWER:
+		/* No actions */
+		break;
+	}
+	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_state);
 	return 0;
 }
 
@@ -175,6 +203,7 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self)
 
 const struct aq_fw_ops aq_fw_2x_ops = {
 	.init = aq_fw2x_init,
+	.deinit = aq_fw2x_deinit,
 	.reset = NULL,
 	.get_mac_permanent = aq_fw2x_get_mac_permanent,
 	.set_link_speed = aq_fw2x_set_link_speed,
-- 
cgit v1.2.3


From 288551de45aa39a751bc03e7976919aa896c5093 Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Mon, 2 Jul 2018 17:03:37 +0300
Subject: net: aquantia: Implement rx/tx flow control ethtools callback

Runtime change of pause frame configuration (rx/tx flow control)
via ethtool.

Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    | 42 ++++++++++++++++++++++
 drivers/net/ethernet/aquantia/atlantic/aq_nic.c    |  6 +++-
 .../aquantia/atlantic/hw_atl/hw_atl_utils.c        |  1 +
 .../aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c   | 26 ++++++++++++++
 4 files changed, 74 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 06242154a002..37f8460647ac 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -285,6 +285,46 @@ static int aq_ethtool_set_coalesce(struct net_device *ndev,
 	return aq_nic_update_interrupt_moderation_settings(aq_nic);
 }
 
+static void aq_ethtool_get_pauseparam(struct net_device *ndev,
+				      struct ethtool_pauseparam *pause)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	pause->autoneg = 0;
+
+	if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_RX)
+		pause->rx_pause = 1;
+	if (aq_nic->aq_hw->aq_nic_cfg->flow_control & AQ_NIC_FC_TX)
+		pause->tx_pause = 1;
+}
+
+static int aq_ethtool_set_pauseparam(struct net_device *ndev,
+				     struct ethtool_pauseparam *pause)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+	int err = 0;
+
+	if (!aq_nic->aq_fw_ops->set_flow_control)
+		return -EOPNOTSUPP;
+
+	if (pause->autoneg == AUTONEG_ENABLE)
+		return -EOPNOTSUPP;
+
+	if (pause->rx_pause)
+		aq_nic->aq_hw->aq_nic_cfg->flow_control |= AQ_NIC_FC_RX;
+	else
+		aq_nic->aq_hw->aq_nic_cfg->flow_control &= ~AQ_NIC_FC_RX;
+
+	if (pause->tx_pause)
+		aq_nic->aq_hw->aq_nic_cfg->flow_control |= AQ_NIC_FC_TX;
+	else
+		aq_nic->aq_hw->aq_nic_cfg->flow_control &= ~AQ_NIC_FC_TX;
+
+	err = aq_nic->aq_fw_ops->set_flow_control(aq_nic->aq_hw);
+
+	return err;
+}
+
 static void aq_get_ringparam(struct net_device *ndev,
 			     struct ethtool_ringparam *ring)
 {
@@ -352,6 +392,8 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.get_rxfh_indir_size = aq_ethtool_get_rss_indir_size,
 	.get_ringparam       = aq_get_ringparam,
 	.set_ringparam       = aq_set_ringparam,
+	.get_pauseparam      = aq_ethtool_get_pauseparam,
+	.set_pauseparam      = aq_ethtool_set_pauseparam,
 	.get_rxfh_key_size   = aq_ethtool_get_rss_key_size,
 	.get_rxfh            = aq_ethtool_get_rss,
 	.get_rxnfc           = aq_ethtool_get_rxnfc,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
index e8cf93adc445..21cfb327d791 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_nic.c
@@ -761,10 +761,14 @@ void aq_nic_get_link_ksettings(struct aq_nic_s *self,
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     100baseT_Full);
 
-	if (self->aq_nic_cfg.flow_control)
+	if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_RX)
 		ethtool_link_ksettings_add_link_mode(cmd, advertising,
 						     Pause);
 
+	if (self->aq_nic_cfg.flow_control & AQ_NIC_FC_TX)
+		ethtool_link_ksettings_add_link_mode(cmd, advertising,
+						     Asym_Pause);
+
 	if (self->aq_nic_cfg.aq_hw_caps->media_type == AQ_HW_MEDIA_TYPE_FIBRE)
 		ethtool_link_ksettings_add_link_mode(cmd, advertising, FIBRE);
 	else
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index 9d0a96dda8bc..e1feba5787d1 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -834,4 +834,5 @@ const struct aq_fw_ops aq_fw_1x_ops = {
 	.set_state = hw_atl_utils_mpi_set_state,
 	.update_link_status = hw_atl_utils_mpi_get_link_status,
 	.update_stats = hw_atl_utils_update_stats,
+	.set_flow_control = NULL,
 };
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index a3e95f076bf0..c1b671e604fe 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -87,6 +87,19 @@ static int aq_fw2x_set_link_speed(struct aq_hw_s *self, u32 speed)
 	return 0;
 }
 
+static void aq_fw2x_set_mpi_flow_control(struct aq_hw_s *self, u32 *mpi_state)
+{
+	if (self->aq_nic_cfg->flow_control & AQ_NIC_FC_RX)
+		*mpi_state |= BIT(CAPS_HI_PAUSE);
+	else
+		*mpi_state &= ~BIT(CAPS_HI_PAUSE);
+
+	if (self->aq_nic_cfg->flow_control & AQ_NIC_FC_TX)
+		*mpi_state |= BIT(CAPS_HI_ASYMMETRIC_PAUSE);
+	else
+		*mpi_state &= ~BIT(CAPS_HI_ASYMMETRIC_PAUSE);
+}
+
 static int aq_fw2x_set_state(struct aq_hw_s *self,
 			     enum hal_atl_utils_fw_state_e state)
 {
@@ -95,6 +108,7 @@ static int aq_fw2x_set_state(struct aq_hw_s *self,
 	switch (state) {
 	case MPI_INIT:
 		mpi_state &= ~BIT(CAPS_HI_LINK_DROP);
+		aq_fw2x_set_mpi_flow_control(self, &mpi_state);
 		break;
 	case MPI_DEINIT:
 		mpi_state |= BIT(CAPS_HI_LINK_DROP);
@@ -201,6 +215,17 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self)
 	return hw_atl_utils_update_stats(self);
 }
 
+static int aq_fw2x_set_flow_control(struct aq_hw_s *self)
+{
+	u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+	aq_fw2x_set_mpi_flow_control(self, &mpi_state);
+
+	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_state);
+
+	return 0;
+}
+
 const struct aq_fw_ops aq_fw_2x_ops = {
 	.init = aq_fw2x_init,
 	.deinit = aq_fw2x_deinit,
@@ -210,4 +235,5 @@ const struct aq_fw_ops aq_fw_2x_ops = {
 	.set_state = aq_fw2x_set_state,
 	.update_link_status = aq_fw2x_update_link_status,
 	.update_stats = aq_fw2x_update_stats,
+	.set_flow_control   = aq_fw2x_set_flow_control,
 };
-- 
cgit v1.2.3


From b8d68b62d99355c827243c62f00de70168e1661f Mon Sep 17 00:00:00 2001
From: Anton Mikaev <amikaev@aquantia.com>
Date: Mon, 2 Jul 2018 17:03:38 +0300
Subject: net: aquantia: Add renegotiate ethtool operation support

Adds ethtool -r|--negotiate operation support. It triggers special
control bit on FW interface causing FW to restart link negotiation.

Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: Anton Mikaev <amikaev@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/aquantia/atlantic/aq_ethtool.c    | 14 +++++++++
 drivers/net/ethernet/aquantia/atlantic/aq_hw.h     |  2 ++
 .../aquantia/atlantic/hw_atl/hw_atl_utils.h        | 35 ++++++++++++++++++++++
 .../aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c   | 12 ++++++++
 4 files changed, 63 insertions(+)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
index 37f8460647ac..08c9fa6ca71f 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_ethtool.c
@@ -285,6 +285,19 @@ static int aq_ethtool_set_coalesce(struct net_device *ndev,
 	return aq_nic_update_interrupt_moderation_settings(aq_nic);
 }
 
+static int aq_ethtool_nway_reset(struct net_device *ndev)
+{
+	struct aq_nic_s *aq_nic = netdev_priv(ndev);
+
+	if (unlikely(!aq_nic->aq_fw_ops->renegotiate))
+		return -EOPNOTSUPP;
+
+	if (netif_running(ndev))
+		return aq_nic->aq_fw_ops->renegotiate(aq_nic->aq_hw);
+
+	return 0;
+}
+
 static void aq_ethtool_get_pauseparam(struct net_device *ndev,
 				      struct ethtool_pauseparam *pause)
 {
@@ -390,6 +403,7 @@ const struct ethtool_ops aq_ethtool_ops = {
 	.get_drvinfo         = aq_ethtool_get_drvinfo,
 	.get_strings         = aq_ethtool_get_strings,
 	.get_rxfh_indir_size = aq_ethtool_get_rss_indir_size,
+	.nway_reset          = aq_ethtool_nway_reset,
 	.get_ringparam       = aq_get_ringparam,
 	.set_ringparam       = aq_set_ringparam,
 	.get_pauseparam      = aq_ethtool_get_pauseparam,
diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
index 3aa36d5765bc..1a51152029c3 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_hw.h
@@ -212,6 +212,8 @@ struct aq_fw_ops {
 
 	int (*reset)(struct aq_hw_s *self);
 
+	int (*renegotiate)(struct aq_hw_s *self);
+
 	int (*get_mac_permanent)(struct aq_hw_s *self, u8 *mac);
 
 	int (*set_link_speed)(struct aq_hw_s *self, u32 speed);
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index cd8f18f39c61..b875590efcbd 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -239,6 +239,41 @@ enum hw_atl_fw2x_caps_hi {
 	CAPS_HI_TRANSACTION_ID,
 };
 
+enum hw_atl_fw2x_ctrl {
+	CTRL_RESERVED1 = 0x00,
+	CTRL_RESERVED2,
+	CTRL_RESERVED3,
+	CTRL_PAUSE,
+	CTRL_ASYMMETRIC_PAUSE,
+	CTRL_RESERVED4,
+	CTRL_RESERVED5,
+	CTRL_RESERVED6,
+	CTRL_1GBASET_FD_EEE,
+	CTRL_2P5GBASET_FD_EEE,
+	CTRL_5GBASET_FD_EEE,
+	CTRL_10GBASET_FD_EEE,
+	CTRL_THERMAL_SHUTDOWN,
+	CTRL_PHY_LOGS,
+	CTRL_EEE_AUTO_DISABLE,
+	CTRL_PFC,
+	CTRL_WAKE_ON_LINK,
+	CTRL_CABLE_DIAG,
+	CTRL_TEMPERATURE,
+	CTRL_DOWNSHIFT,
+	CTRL_PTP_AVB,
+	CTRL_RESERVED7,
+	CTRL_LINK_DROP,
+	CTRL_SLEEP_PROXY,
+	CTRL_WOL,
+	CTRL_MAC_STOP,
+	CTRL_EXT_LOOPBACK,
+	CTRL_INT_LOOPBACK,
+	CTRL_RESERVED8,
+	CTRL_WOL_TIMER,
+	CTRL_STATISTICS,
+	CTRL_FORCE_RECONNECT,
+};
+
 struct aq_hw_s;
 struct aq_fw_ops;
 struct aq_hw_caps_s;
diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
index c1b671e604fe..e37943760a58 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils_fw2x.c
@@ -215,6 +215,17 @@ static int aq_fw2x_update_stats(struct aq_hw_s *self)
 	return hw_atl_utils_update_stats(self);
 }
 
+static int aq_fw2x_renegotiate(struct aq_hw_s *self)
+{
+	u32 mpi_opts = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
+
+	mpi_opts |= BIT(CTRL_FORCE_RECONNECT);
+
+	aq_hw_write_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR, mpi_opts);
+
+	return 0;
+}
+
 static int aq_fw2x_set_flow_control(struct aq_hw_s *self)
 {
 	u32 mpi_state = aq_hw_read_reg(self, HW_ATL_FW2X_MPI_CONTROL2_ADDR);
@@ -230,6 +241,7 @@ const struct aq_fw_ops aq_fw_2x_ops = {
 	.init = aq_fw2x_init,
 	.deinit = aq_fw2x_deinit,
 	.reset = NULL,
+	.renegotiate = aq_fw2x_renegotiate,
 	.get_mac_permanent = aq_fw2x_get_mac_permanent,
 	.set_link_speed = aq_fw2x_set_link_speed,
 	.set_state = aq_fw2x_set_state,
-- 
cgit v1.2.3


From 1d1c21228344f2519f14aea25d0ebb1274b43c9a Mon Sep 17 00:00:00 2001
From: Igor Russkikh <igor.russkikh@aquantia.com>
Date: Mon, 2 Jul 2018 17:03:39 +0300
Subject: net: aquantia: bump driver version

Signed-off-by: Igor Russkikh <igor.russkikh@aquantia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/ver.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/ver.h b/drivers/net/ethernet/aquantia/atlantic/ver.h
index a445de6837a6..94efc6477bdc 100644
--- a/drivers/net/ethernet/aquantia/atlantic/ver.h
+++ b/drivers/net/ethernet/aquantia/atlantic/ver.h
@@ -12,8 +12,8 @@
 
 #define NIC_MAJOR_DRIVER_VERSION           2
 #define NIC_MINOR_DRIVER_VERSION           0
-#define NIC_BUILD_DRIVER_VERSION           2
-#define NIC_REVISION_DRIVER_VERSION        1
+#define NIC_BUILD_DRIVER_VERSION           3
+#define NIC_REVISION_DRIVER_VERSION        0
 
 #define AQ_CFG_DRV_VERSION_SUFFIX "-kern"
 
-- 
cgit v1.2.3


From 2daf3d9962c5a11fb79fe17bae03125df5d60236 Mon Sep 17 00:00:00 2001
From: Bard Liao <bardliao@realtek.com>
Date: Tue, 3 Jul 2018 13:07:25 +0800
Subject: ASoC: rt5682: add button detection mode control

We are currently using power saving mode for button detection.
However, it will impact the headset recording performance.
This patch will switch button detection to normal mode in capture
and switch to power saving mode in the end of capture.

Signed-off-by: Bard Liao <bardliao@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5682.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
index baad177908ab..640d400ca013 100644
--- a/sound/soc/codecs/rt5682.c
+++ b/sound/soc/codecs/rt5682.c
@@ -857,6 +857,8 @@ static int rt5682_button_detect(struct snd_soc_component *component)
 	btn_type = val & 0xfff0;
 	snd_soc_component_write(component, RT5682_4BTN_IL_CMD_1, val);
 	pr_debug("%s btn_type=%x\n", __func__, btn_type);
+	snd_soc_component_update_bits(component,
+		RT5682_SAR_IL_CMD_2, 0x10, 0x10);
 
 	return btn_type;
 }
@@ -1645,6 +1647,8 @@ static const struct snd_soc_dapm_widget rt5682_dapm_widgets[] = {
 	SND_SOC_DAPM_MIXER("Stereo1 ADC MIXR", RT5682_STO1_ADC_DIG_VOL,
 		RT5682_R_MUTE_SFT, 1, rt5682_sto1_adc_r_mix,
 		ARRAY_SIZE(rt5682_sto1_adc_r_mix)),
+	SND_SOC_DAPM_SUPPLY("BTN Detection Mode", RT5682_SAR_IL_CMD_1,
+		14, 1, NULL, 0),
 
 	/* ADC PGA */
 	SND_SOC_DAPM_PGA("Stereo1 ADC MIX", SND_SOC_NOPM, 0, 0, NULL, 0),
@@ -1807,6 +1811,8 @@ static const struct snd_soc_dapm_route rt5682_dapm_routes[] = {
 	{"Stereo1 ADC MIXR", "ADC2 Switch", "Stereo1 ADC R2 Mux"},
 	{"Stereo1 ADC MIXR", NULL, "ADC Stereo1 Filter"},
 
+	{"ADC Stereo1 Filter", NULL, "BTN Detection Mode"},
+
 	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXL"},
 	{"Stereo1 ADC MIX", NULL, "Stereo1 ADC MIXR"},
 
-- 
cgit v1.2.3


From 1b8fc56ed514f815c4779273348c3308fb263c87 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 3 Jul 2018 15:28:44 +0200
Subject: ASoC: es7241: add dt-bindings documentation for the es7241 adc

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/everest,es7241.txt   | 28 ++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/everest,es7241.txt

diff --git a/Documentation/devicetree/bindings/sound/everest,es7241.txt b/Documentation/devicetree/bindings/sound/everest,es7241.txt
new file mode 100644
index 000000000000..28f82cf4959f
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/everest,es7241.txt
@@ -0,0 +1,28 @@
+ES7241 i2s AD converter
+
+Required properties:
+- compatible : "everest,es7241"
+- VDDP-supply: regulator phandle for the VDDA supply
+- VDDA-supply: regulator phandle for the VDDP supply
+- VDDD-supply: regulator phandle for the VDDD supply
+
+Optional properties:
+- reset-gpios: gpio connected to the reset pin
+- m0-gpios   : gpio connected to the m0 pin
+- m1-gpios   : gpio connected to the m1 pin
+- everest,sdout-pull-down:
+   Format used by the serial interface is controlled by pulling
+   the sdout. If the sdout is pulled down, leftj format is used.
+   If this property is not provided, sdout is assumed to pulled
+   up and i2s format is used
+
+Example:
+
+linein: audio-codec@2 {
+	#sound-dai-cells = <0>;
+	compatible = "everest,es7241";
+	VDDA-supply = <&vcc_3v3>;
+	VDDP-supply = <&vcc_3v3>;
+	VDDD-supply = <&vcc_3v3>;
+	reset-gpios = <&gpio GPIOH_42>;
+};
-- 
cgit v1.2.3


From 5f7bdc466c772b3af3145a71724965ecdc03e6bf Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 3 Jul 2018 15:28:45 +0200
Subject: ASoC: es7241: add es7241 codec support

Add support for the everest es7241 which is a simple 2 channels
analog to digital converter.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Kconfig  |   4 +
 sound/soc/codecs/Makefile |   2 +
 sound/soc/codecs/es7241.c | 322 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 328 insertions(+)
 create mode 100644 sound/soc/codecs/es7241.c

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index 6d1674699385..efb095dbcd71 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -79,6 +79,7 @@ config SND_SOC_ALL_CODECS
 	select SND_SOC_ES8328_SPI if SPI_MASTER
 	select SND_SOC_ES8328_I2C if I2C
 	select SND_SOC_ES7134
+	select SND_SOC_ES7241
 	select SND_SOC_GTM601
 	select SND_SOC_HDAC_HDMI
 	select SND_SOC_ICS43432
@@ -585,6 +586,9 @@ config SND_SOC_HDMI_CODEC
 config SND_SOC_ES7134
        tristate "Everest Semi ES7134 CODEC"
 
+config SND_SOC_ES7241
+       tristate "Everest Semi ES7241 CODEC"
+
 config SND_SOC_ES8316
 	tristate "Everest Semi ES8316 CODEC"
 	depends on I2C
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index f26ded89a1e5..7ae7c85e8219 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -71,6 +71,7 @@ snd-soc-da732x-objs := da732x.o
 snd-soc-da9055-objs := da9055.o
 snd-soc-dmic-objs := dmic.o
 snd-soc-es7134-objs := es7134.o
+snd-soc-es7241-objs := es7241.o
 snd-soc-es8316-objs := es8316.o
 snd-soc-es8328-objs := es8328.o
 snd-soc-es8328-i2c-objs := es8328-i2c.o
@@ -330,6 +331,7 @@ obj-$(CONFIG_SND_SOC_DA732X)	+= snd-soc-da732x.o
 obj-$(CONFIG_SND_SOC_DA9055)	+= snd-soc-da9055.o
 obj-$(CONFIG_SND_SOC_DMIC)	+= snd-soc-dmic.o
 obj-$(CONFIG_SND_SOC_ES7134)	+= snd-soc-es7134.o
+obj-$(CONFIG_SND_SOC_ES7241)	+= snd-soc-es7241.o
 obj-$(CONFIG_SND_SOC_ES8316)    += snd-soc-es8316.o
 obj-$(CONFIG_SND_SOC_ES8328)	+= snd-soc-es8328.o
 obj-$(CONFIG_SND_SOC_ES8328_I2C)+= snd-soc-es8328-i2c.o
diff --git a/sound/soc/codecs/es7241.c b/sound/soc/codecs/es7241.c
new file mode 100644
index 000000000000..87991bd4acef
--- /dev/null
+++ b/sound/soc/codecs/es7241.c
@@ -0,0 +1,322 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/gpio/consumer.h>
+#include <linux/of_platform.h>
+#include <linux/module.h>
+#include <sound/soc.h>
+
+struct es7241_clock_mode {
+	unsigned int rate_min;
+	unsigned int rate_max;
+	unsigned int *slv_mfs;
+	unsigned int slv_mfs_num;
+	unsigned int mst_mfs;
+	unsigned int mst_m0:1;
+	unsigned int mst_m1:1;
+};
+
+struct es7241_chip {
+	const struct es7241_clock_mode *modes;
+	unsigned int mode_num;
+};
+
+struct es7241_data {
+	struct gpio_desc *reset;
+	struct gpio_desc *m0;
+	struct gpio_desc *m1;
+	unsigned int fmt;
+	unsigned int mclk;
+	bool is_slave;
+	const struct es7241_chip *chip;
+};
+
+static void es7241_set_mode(struct es7241_data *priv,  int m0, int m1)
+{
+	/* put the device in reset */
+	gpiod_set_value_cansleep(priv->reset, 0);
+
+	/* set the mode */
+	gpiod_set_value_cansleep(priv->m0, m0);
+	gpiod_set_value_cansleep(priv->m1, m1);
+
+	/* take the device out of reset - datasheet does not specify a delay */
+	gpiod_set_value_cansleep(priv->reset, 1);
+}
+
+static int es7241_set_slave_mode(struct es7241_data *priv,
+				 const struct es7241_clock_mode *mode,
+				 unsigned int mfs)
+{
+	int j;
+
+	if (!mfs)
+		goto out_ok;
+
+	for (j = 0; j < mode->slv_mfs_num; j++) {
+		if (mode->slv_mfs[j] == mfs)
+			goto out_ok;
+	}
+
+	return -EINVAL;
+
+out_ok:
+	es7241_set_mode(priv, 1, 1);
+	return 0;
+}
+
+static int es7241_set_master_mode(struct es7241_data *priv,
+				  const struct es7241_clock_mode *mode,
+				  unsigned int mfs)
+{
+	/*
+	 * We can't really set clock ratio, if the mclk/lrclk is different
+	 * from what we provide, then error out
+	 */
+	if (mfs && mfs != mode->mst_mfs)
+		return -EINVAL;
+
+	es7241_set_mode(priv, mode->mst_m0, mode->mst_m1);
+
+	return 0;
+}
+
+static int es7241_hw_params(struct snd_pcm_substream *substream,
+			    struct snd_pcm_hw_params *params,
+			    struct snd_soc_dai *dai)
+{
+	struct es7241_data *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int rate = params_rate(params);
+	unsigned int mfs = priv->mclk / rate;
+	int i;
+
+	for (i = 0; i < priv->chip->mode_num; i++) {
+		const struct es7241_clock_mode *mode = &priv->chip->modes[i];
+
+		if (rate < mode->rate_min || rate >= mode->rate_max)
+			continue;
+
+		if (priv->is_slave)
+			return es7241_set_slave_mode(priv, mode, mfs);
+		else
+			return es7241_set_master_mode(priv, mode, mfs);
+	}
+
+	/* should not happen */
+	dev_err(dai->dev, "unsupported rate: %u\n", rate);
+	return -EINVAL;
+}
+
+static int es7241_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+			     unsigned int freq, int dir)
+{
+	struct es7241_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	if (dir == SND_SOC_CLOCK_IN && clk_id == 0) {
+		priv->mclk = freq;
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int es7241_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct es7241_data *priv = snd_soc_dai_get_drvdata(dai);
+
+	if ((fmt & SND_SOC_DAIFMT_INV_MASK) != SND_SOC_DAIFMT_NB_NF) {
+		dev_err(dai->dev, "Unsupported dai clock inversion\n");
+		return -EINVAL;
+	}
+
+	if ((fmt & SND_SOC_DAIFMT_FORMAT_MASK) != priv->fmt) {
+		dev_err(dai->dev, "Invalid dai format\n");
+		return -EINVAL;
+	}
+
+	switch (fmt & SND_SOC_DAIFMT_MASTER_MASK) {
+	case SND_SOC_DAIFMT_CBS_CFS:
+		priv->is_slave = true;
+		break;
+	case SND_SOC_DAIFMT_CBM_CFM:
+		priv->is_slave = false;
+		break;
+
+	default:
+		dev_err(dai->dev, "Unsupported clock configuration\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops es7241_dai_ops = {
+	.set_fmt	= es7241_set_fmt,
+	.hw_params	= es7241_hw_params,
+	.set_sysclk	= es7241_set_sysclk,
+};
+
+static struct snd_soc_dai_driver es7241_dai = {
+	.name = "es7241-hifi",
+	.capture = {
+		.stream_name = "Capture",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = SNDRV_PCM_RATE_8000_192000,
+		.formats = (SNDRV_PCM_FMTBIT_S16_LE  |
+			    SNDRV_PCM_FMTBIT_S24_3LE |
+			    SNDRV_PCM_FMTBIT_S24_LE),
+	},
+	.ops = &es7241_dai_ops,
+};
+
+static const struct es7241_clock_mode es7241_modes[] = {
+	{
+		/* Single speed mode */
+		.rate_min = 8000,
+		.rate_max = 50000,
+		.slv_mfs = (unsigned int[]) { 256, 384, 512, 768, 1024 },
+		.slv_mfs_num = 5,
+		.mst_mfs = 256,
+		.mst_m0 = 0,
+		.mst_m1 = 0,
+	}, {
+		/* Double speed mode */
+		.rate_min = 50000,
+		.rate_max = 100000,
+		.slv_mfs = (unsigned int[]) { 128, 192 },
+		.slv_mfs_num = 2,
+		.mst_mfs = 128,
+		.mst_m0 = 1,
+		.mst_m1 = 0,
+	}, {
+		/* Quad speed mode */
+		.rate_min = 100000,
+		.rate_max = 200000,
+		.slv_mfs = (unsigned int[]) { 64 },
+		.slv_mfs_num = 1,
+		.mst_mfs = 64,
+		.mst_m0 = 0,
+		.mst_m1 = 1,
+	},
+};
+
+static const struct es7241_chip es7241_chip = {
+	.modes = es7241_modes,
+	.mode_num = ARRAY_SIZE(es7241_modes),
+};
+
+static const struct snd_soc_dapm_widget es7241_dapm_widgets[] = {
+	SND_SOC_DAPM_INPUT("AINL"),
+	SND_SOC_DAPM_INPUT("AINR"),
+	SND_SOC_DAPM_DAC("ADC", "Capture", SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDDP", 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDDD", 0, 0),
+	SND_SOC_DAPM_REGULATOR_SUPPLY("VDDA", 0, 0),
+};
+
+static const struct snd_soc_dapm_route es7241_dapm_routes[] = {
+	{ "ADC", NULL, "AINL", },
+	{ "ADC", NULL, "AINR", },
+	{ "ADC", NULL, "VDDA", },
+	{ "Capture", NULL, "VDDP", },
+	{ "Capture", NULL, "VDDD", },
+};
+
+static const struct snd_soc_component_driver es7241_component_driver = {
+	.dapm_widgets		= es7241_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(es7241_dapm_widgets),
+	.dapm_routes		= es7241_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(es7241_dapm_routes),
+	.idle_bias_on		= 1,
+	.endianness		= 1,
+	.non_legacy_dai_naming	= 1,
+};
+
+static void es7241_parse_fmt(struct device *dev, struct es7241_data *priv)
+{
+	bool is_leftj;
+
+	/*
+	 * The format is given by a pull resistor on the SDOUT pin:
+	 * pull-up for i2s, pull-down for left justified.
+	 */
+	is_leftj = of_property_read_bool(dev->of_node,
+					 "everest,sdout-pull-down");
+	if (is_leftj)
+		priv->fmt = SND_SOC_DAIFMT_LEFT_J;
+	else
+		priv->fmt = SND_SOC_DAIFMT_I2S;
+}
+
+static int es7241_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct es7241_data *priv;
+	int err;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+
+	priv->chip = of_device_get_match_data(dev);
+	if (!priv->chip) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
+	es7241_parse_fmt(dev, priv);
+
+	priv->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(priv->reset)) {
+		err = PTR_ERR(priv->reset);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'reset' gpio: %d", err);
+		return err;
+	}
+
+	priv->m0 = devm_gpiod_get_optional(dev, "m0", GPIOD_OUT_LOW);
+	if (IS_ERR(priv->m0)) {
+		err = PTR_ERR(priv->m0);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'm0' gpio: %d", err);
+		return err;
+	}
+
+	priv->m1 = devm_gpiod_get_optional(dev, "m1", GPIOD_OUT_LOW);
+	if (IS_ERR(priv->m1)) {
+		err = PTR_ERR(priv->m1);
+		if (err != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get 'm1' gpio: %d", err);
+		return err;
+	}
+
+	return devm_snd_soc_register_component(&pdev->dev,
+				      &es7241_component_driver,
+				      &es7241_dai, 1);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id es7241_ids[] = {
+	{ .compatible = "everest,es7241", .data = &es7241_chip },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, es7241_ids);
+#endif
+
+static struct platform_driver es7241_driver = {
+	.driver = {
+		.name = "es7241",
+		.of_match_table = of_match_ptr(es7241_ids),
+	},
+	.probe = es7241_probe,
+};
+
+module_platform_driver(es7241_driver);
+
+MODULE_DESCRIPTION("ASoC ES7241 audio codec driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From e0431de301cbb8e3915261dfff4d0b072738de69 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 2 Jul 2018 07:17:07 -0500
Subject: ASoC: pxa-ssp: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/pxa/pxa-ssp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index f8339bb01251..ff1e0bd8d407 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -470,6 +470,7 @@ static int pxa_ssp_configure_dai_fmt(struct ssp_priv *priv)
 
 	case SND_SOC_DAIFMT_DSP_A:
 		sspsp |= SSPSP_FSRT;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_B:
 		sscr0 |= SSCR0_MOD | SSCR0_PSP;
 		sscr1 |= SSCR1_TRAIL | SSCR1_RWOT;
-- 
cgit v1.2.3


From 30896d3619bd80486a3f8a75d62ea3b58fc61ad5 Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 2 Jul 2018 15:19:50 -0600
Subject: ASoC: AMD: Always stop ch2 first

Commit 6b116dfb4633a ("ASoC: AMD: make channel 1 dma as circular") made
both channels circular, so this comment and logic no longer applies.  Always
stop ch2 (the channel closest to the output) before ch1.  This ensures
that the downstream circular DMA channel does not continue to play/capture
repeated samples after the upstream circular DMA channel has already
stopped.

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 17 ++---------------
 1 file changed, 2 insertions(+), 15 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 3c3d398d0d0b..4665ae12e74e 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -1067,21 +1067,8 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_STOP:
 	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
 	case SNDRV_PCM_TRIGGER_SUSPEND:
-		/* For playback, non circular dma should be stopped first
-		 * i.e Sysram to acp dma transfer channel(rtd->ch1) should be
-		 * stopped before stopping cirular dma which is acp sram to i2s
-		 * fifo dma transfer channel(rtd->ch2). Where as in Capture
-		 * scenario, i2s fifo to acp sram dma channel(rtd->ch2) stopped
-		 * first before stopping acp sram to sysram which is circular
-		 * dma(rtd->ch1).
-		 */
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-			acp_dma_stop(rtd->acp_mmio, rtd->ch1);
-			ret =  acp_dma_stop(rtd->acp_mmio, rtd->ch2);
-		} else {
-			acp_dma_stop(rtd->acp_mmio, rtd->ch2);
-			ret = acp_dma_stop(rtd->acp_mmio, rtd->ch1);
-		}
+		acp_dma_stop(rtd->acp_mmio, rtd->ch2);
+		ret = acp_dma_stop(rtd->acp_mmio, rtd->ch1);
 		rtd->bytescount = 0;
 		break;
 	default:
-- 
cgit v1.2.3


From 715cdce04487fb23d5c10693b3bc01309fea955a Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 2 Jul 2018 15:19:52 -0600
Subject: ASoC: AMD: Always subtract bytescount

It is always correct to subtract out the starting bytescount value.  Even
in the case of 2^64 byte rollover (292 Million Years in the future
@ 48000 Hz) the math still works out.

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 4665ae12e74e..034fac3de037 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -995,8 +995,7 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 	buffersize = frames_to_bytes(runtime, runtime->buffer_size);
 	bytescount = acp_get_byte_count(rtd);
 
-	if (bytescount > rtd->bytescount)
-		bytescount -= rtd->bytescount;
+	bytescount -= rtd->bytescount;
 	pos = do_div(bytescount, buffersize);
 	return bytes_to_frames(runtime, pos);
 }
-- 
cgit v1.2.3


From 55af49ac1b8627dfbfa2689af118d994d7a0ba1b Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 2 Jul 2018 15:19:53 -0600
Subject: ASoC: AMD: Fix Capture DMA channel names

On capture, audio data is first copied from I2S to ACP memory, and then
to SYSRAM.  For each step the channel number increases, so the names in
the driver were wrong.

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 24 ++++++++++++------------
 sound/soc/amd/acp.h         |  8 ++++----
 2 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 034fac3de037..df53412967e1 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -697,31 +697,31 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
+	if ((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) != 0) {
 		valid_irq = true;
 		snd_pcm_period_elapsed(irq_data->capture_i2ssp_stream);
-		acp_reg_write((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) << 16,
+		acp_reg_write((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) != 0) {
+	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
 		valid_irq = true;
-		acp_reg_write((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) << 16,
+		acp_reg_write((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) != 0) {
+	if ((intr_flag & BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) != 0) {
 		valid_irq = true;
 		snd_pcm_period_elapsed(irq_data->capture_i2sbt_stream);
 		acp_reg_write((intr_flag &
-			      BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) << 16,
+			      BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) != 0) {
+	if ((intr_flag & BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) != 0) {
 		valid_irq = true;
 		acp_reg_write((intr_flag &
-			      BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) << 16,
+			      BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
@@ -899,8 +899,8 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 		switch (rtd->i2s_instance) {
 		case I2S_BT_INSTANCE:
 			rtd->pte_offset = ACP_ST_BT_CAPTURE_PTE_OFFSET;
-			rtd->ch1 = ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM;
-			rtd->ch2 = I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM;
+			rtd->ch1 = I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM;
+			rtd->ch2 = ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM;
 			rtd->sram_bank = ACP_SRAM_BANK_4_ADDRESS;
 			rtd->destination = FROM_BLUETOOTH;
 			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH10;
@@ -914,8 +914,8 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 		case I2S_SP_INSTANCE:
 		default:
 			rtd->pte_offset = ACP_CAPTURE_PTE_OFFSET;
-			rtd->ch1 = ACP_TO_SYSRAM_CH_NUM;
-			rtd->ch2 = I2S_TO_ACP_DMA_CH_NUM;
+			rtd->ch1 = I2S_TO_ACP_DMA_CH_NUM;
+			rtd->ch2 = ACP_TO_SYSRAM_CH_NUM;
 			switch (adata->asic_type) {
 			case CHIP_STONEY:
 				rtd->pte_offset = ACP_ST_CAPTURE_PTE_OFFSET;
diff --git a/sound/soc/amd/acp.h b/sound/soc/amd/acp.h
index 3190fdce6307..0a2240bff62e 100644
--- a/sound/soc/amd/acp.h
+++ b/sound/soc/amd/acp.h
@@ -74,16 +74,16 @@
 #define ACP_TO_I2S_DMA_CH_NUM 13
 
 /* Capture DMA channels */
-#define ACP_TO_SYSRAM_CH_NUM 14
-#define I2S_TO_ACP_DMA_CH_NUM 15
+#define I2S_TO_ACP_DMA_CH_NUM 14
+#define ACP_TO_SYSRAM_CH_NUM 15
 
 /* Playback DMA Channels for I2S BT instance */
 #define SYSRAM_TO_ACP_BT_INSTANCE_CH_NUM  8
 #define ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM 9
 
 /* Capture DMA Channels for I2S BT Instance */
-#define ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM 10
-#define I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM 11
+#define I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM 10
+#define ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM 11
 
 #define NUM_DSCRS_PER_CHANNEL 2
 
-- 
cgit v1.2.3


From 8c6b964eddd2c39a9796899b2be099ece1b6c6ca Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 2 Jul 2018 15:19:54 -0600
Subject: ASoC: AMD: Do not generate interrups for every captured sample

On capture, audio data is first copied from I2S to ACP memory, and then
from ACP to SYSRAM.  The I2S_TO_ACP_DMA interrupt fires on every sample
transferred from I2S to ACP memory.  That is it fires ~48000 times per
second when capturing @ 48 kHz.  Since we don't do anything on this
interrupt anyway, disable it to save quite a few unnecessary interrupts.
The real "work" (calling snd_pcm_period_elapsed()) is done when transfer
from ACP to SYSRAM is complete.

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index df53412967e1..cd4d2520ac14 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -412,10 +412,8 @@ static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
 	switch (ch_num) {
 	case ACP_TO_I2S_DMA_CH_NUM:
 	case ACP_TO_SYSRAM_CH_NUM:
-	case I2S_TO_ACP_DMA_CH_NUM:
 	case ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM:
 	case ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM:
-	case I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM:
 		dma_ctrl |= ACP_DMA_CNTL_0__DMAChIOCEn_MASK;
 		break;
 	default:
@@ -704,12 +702,6 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
-		valid_irq = true;
-		acp_reg_write((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) << 16,
-			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
-	}
-
 	if ((intr_flag & BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) != 0) {
 		valid_irq = true;
 		snd_pcm_period_elapsed(irq_data->capture_i2sbt_stream);
@@ -718,13 +710,6 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) != 0) {
-		valid_irq = true;
-		acp_reg_write((intr_flag &
-			      BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) << 16,
-			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
-	}
-
 	if (valid_irq)
 		return IRQ_HANDLED;
 	else
-- 
cgit v1.2.3


From 1a337a1e7885085d224583c766614e5945bde671 Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 2 Jul 2018 15:19:51 -0600
Subject: ASoC: AMD: Reset bytescount when starting transaction

The pointer() callback gets its value by reading the I2S BYTE_COUNT
register.  This is a 64-bit runnning transaction counter. If a
transaction was aborted in the middle of a sample buffer, the counter will
stop counting on a number divisible by the buffer size.  Since we actually
use it as a pointer into an aligned buffer, however, we do want to ensure
that it always starts at a number divisible by the buffer size when
starting a transaction, hence we reset it whenever starting a transaction.

To accomplish this, it wasn't necessary to zero bytescount at the
termination of each transaction, so remove this unnecessary code.

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index cd4d2520ac14..ab60129f4f26 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -1013,7 +1013,6 @@ static int acp_dma_prepare(struct snd_pcm_substream *substream)
 static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 {
 	int ret;
-	u64 bytescount = 0;
 
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
@@ -1024,9 +1023,7 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_START:
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
-		bytescount = acp_get_byte_count(rtd);
-		if (rtd->bytescount == 0)
-			rtd->bytescount = bytescount;
+		rtd->bytescount = acp_get_byte_count(rtd);
 		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
 			acp_dma_start(rtd->acp_mmio, rtd->ch1);
 			acp_dma_start(rtd->acp_mmio, rtd->ch2);
@@ -1053,7 +1050,6 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_SUSPEND:
 		acp_dma_stop(rtd->acp_mmio, rtd->ch2);
 		ret = acp_dma_stop(rtd->acp_mmio, rtd->ch1);
-		rtd->bytescount = 0;
 		break;
 	default:
 		ret = -EINVAL;
-- 
cgit v1.2.3


From df61f9f76609456efbc60d495b3235baf7d07691 Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 2 Jul 2018 15:19:55 -0600
Subject: ASoC: AMD: Simplify trigger handler

Now that the I2S channel names are fixed, and DMA data flow order is
consistent (ch1 then ch2), we can simplify channel start order:
start the upstream channel and then the downstream channel for both
playback and capture cases.

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index ab60129f4f26..65c1033bd51c 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -1024,10 +1024,7 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
 		rtd->bytescount = acp_get_byte_count(rtd);
-		if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
-			acp_dma_start(rtd->acp_mmio, rtd->ch1);
-			acp_dma_start(rtd->acp_mmio, rtd->ch2);
-		} else {
+		if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
 			if (rtd->capture_channel == CAP_CHANNEL0) {
 				acp_dma_cap_channel_disable(rtd->acp_mmio,
 							    CAP_CHANNEL1);
@@ -1040,9 +1037,9 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 				acp_dma_cap_channel_enable(rtd->acp_mmio,
 							   CAP_CHANNEL1);
 			}
-			acp_dma_start(rtd->acp_mmio, rtd->ch2);
-			acp_dma_start(rtd->acp_mmio, rtd->ch1);
 		}
+		acp_dma_start(rtd->acp_mmio, rtd->ch1);
+		acp_dma_start(rtd->acp_mmio, rtd->ch2);
 		ret = 0;
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
-- 
cgit v1.2.3


From c9445d94d7fc60e7b0290df9e109daef85d26bd4 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 3 Jul 2018 17:05:58 +0200
Subject: ASoC: es7134: update DT binding with new compatible and supplies

Update the documentation to add support for the es7154 and
optional power supplies phandles.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/everest,es7134.txt | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/sound/everest,es7134.txt b/Documentation/devicetree/bindings/sound/everest,es7134.txt
index 5495a3cb8b7b..091666069bde 100644
--- a/Documentation/devicetree/bindings/sound/everest,es7134.txt
+++ b/Documentation/devicetree/bindings/sound/everest,es7134.txt
@@ -1,10 +1,15 @@
 ES7134 i2s DA converter
 
 Required properties:
-- compatible : "everest,es7134" or "everest,es7144"
+- compatible : "everest,es7134" or
+               "everest,es7144" or
+	       "everest,es7154"
+- VDD-supply : regulator phandle for the VDD supply
+- PVDD-supply: regulator phandle for the PVDD supply for the es7154
 
 Example:
 
 i2s_codec: external-codec {
 	compatible = "everest,es7134";
+	VDD-supply = <&vcc_5v>;
 };
-- 
cgit v1.2.3


From 30ddfffd10b73d5d960650ea70b33a8ee0562679 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 3 Jul 2018 17:05:59 +0200
Subject: ASoC: es7134: correct required power supplies

Drop AVDD in favor of PVDD to match the names used in the datasheet
and only claim PVDD on the es7154. The es7134 and es7144 don't have
a separate supply for the digital I/O.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es7134.c | 44 +++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 41 insertions(+), 3 deletions(-)

diff --git a/sound/soc/codecs/es7134.c b/sound/soc/codecs/es7134.c
index 5ad59c38fed1..80f2936cefed 100644
--- a/sound/soc/codecs/es7134.c
+++ b/sound/soc/codecs/es7134.c
@@ -35,6 +35,10 @@ struct es7134_clock_mode {
 struct es7134_chip {
 	const struct es7134_clock_mode *modes;
 	unsigned int mode_num;
+	const struct snd_soc_dapm_widget *extra_widgets;
+	unsigned int extra_widget_num;
+	const struct snd_soc_dapm_route *extra_routes;
+	unsigned int extra_route_num;
 };
 
 struct es7134_data {
@@ -110,6 +114,34 @@ static int es7134_set_fmt(struct snd_soc_dai *codec_dai, unsigned int fmt)
 	return 0;
 }
 
+static int es7134_component_probe(struct snd_soc_component *c)
+{
+	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(c);
+	struct es7134_data *priv = snd_soc_component_get_drvdata(c);
+	const struct es7134_chip *chip = priv->chip;
+	int ret;
+
+	if (chip->extra_widget_num) {
+		ret = snd_soc_dapm_new_controls(dapm, chip->extra_widgets,
+						chip->extra_widget_num);
+		if (ret) {
+			dev_err(c->dev, "failed to add extra widgets\n");
+			return ret;
+		}
+	}
+
+	if (chip->extra_route_num) {
+		ret = snd_soc_dapm_add_routes(dapm, chip->extra_routes,
+					      chip->extra_route_num);
+		if (ret) {
+			dev_err(c->dev, "failed to add extra routes\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
 static const struct snd_soc_dai_ops es7134_dai_ops = {
 	.set_fmt	= es7134_set_fmt,
 	.hw_params	= es7134_hw_params,
@@ -158,9 +190,16 @@ static const struct es7134_clock_mode es7134_modes[] = {
 	},
 };
 
+/* Digital I/O are also supplied by VDD on the es7134 */
+static const struct snd_soc_dapm_route es7134_extra_routes[] = {
+	{ "Playback", NULL, "VDD", }
+};
+
 static const struct es7134_chip es7134_chip = {
 	.modes = es7134_modes,
 	.mode_num = ARRAY_SIZE(es7134_modes),
+	.extra_routes = es7134_extra_routes,
+	.extra_route_num = ARRAY_SIZE(es7134_extra_routes),
 };
 
 static const struct snd_soc_dapm_widget es7134_dapm_widgets[] = {
@@ -168,17 +207,16 @@ static const struct snd_soc_dapm_widget es7134_dapm_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("AOUTR"),
 	SND_SOC_DAPM_DAC("DAC", "Playback", SND_SOC_NOPM, 0, 0),
 	SND_SOC_DAPM_REGULATOR_SUPPLY("VDD", 0, 0),
-	SND_SOC_DAPM_REGULATOR_SUPPLY("AVDD", 0, 0),
 };
 
 static const struct snd_soc_dapm_route es7134_dapm_routes[] = {
 	{ "AOUTL", NULL, "DAC" },
 	{ "AOUTR", NULL, "DAC" },
-	{ "Playback", NULL, "VDD" },
-	{ "DAC", NULL, "AVDD" },
+	{ "DAC", NULL, "VDD" },
 };
 
 static const struct snd_soc_component_driver es7134_component_driver = {
+	.probe			= es7134_component_probe,
 	.dapm_widgets		= es7134_dapm_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(es7134_dapm_widgets),
 	.dapm_routes		= es7134_dapm_routes,
-- 
cgit v1.2.3


From 563c263248ff37dcd743549a0c0932fe2bf83980 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 3 Jul 2018 17:06:00 +0200
Subject: ASoC: es7134: add support for the es7154

Add support for the es7154 which is basically an es7134 with an
embedded power amplifier and lower maximum sample rate

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es7134.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 59 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/es7134.c b/sound/soc/codecs/es7134.c
index 80f2936cefed..6d7bca7b78ca 100644
--- a/sound/soc/codecs/es7134.c
+++ b/sound/soc/codecs/es7134.c
@@ -33,6 +33,7 @@ struct es7134_clock_mode {
 };
 
 struct es7134_chip {
+	struct snd_soc_dai_driver *dai_drv;
 	const struct es7134_clock_mode *modes;
 	unsigned int mode_num;
 	const struct snd_soc_dapm_widget *extra_widgets;
@@ -196,6 +197,7 @@ static const struct snd_soc_dapm_route es7134_extra_routes[] = {
 };
 
 static const struct es7134_chip es7134_chip = {
+	.dai_drv = &es7134_dai,
 	.modes = es7134_modes,
 	.mode_num = ARRAY_SIZE(es7134_modes),
 	.extra_routes = es7134_extra_routes,
@@ -227,6 +229,61 @@ static const struct snd_soc_component_driver es7134_component_driver = {
 	.non_legacy_dai_naming	= 1,
 };
 
+static struct snd_soc_dai_driver es7154_dai = {
+	.name = "es7154-hifi",
+	.playback = {
+		.stream_name = "Playback",
+		.channels_min = 2,
+		.channels_max = 2,
+		.rates = (SNDRV_PCM_RATE_8000_48000 |
+			  SNDRV_PCM_RATE_88200      |
+			  SNDRV_PCM_RATE_96000),
+		.formats = (SNDRV_PCM_FMTBIT_S16_LE  |
+			    SNDRV_PCM_FMTBIT_S18_3LE |
+			    SNDRV_PCM_FMTBIT_S20_3LE |
+			    SNDRV_PCM_FMTBIT_S24_3LE |
+			    SNDRV_PCM_FMTBIT_S24_LE),
+	},
+	.ops = &es7134_dai_ops,
+};
+
+static const struct es7134_clock_mode es7154_modes[] = {
+	{
+		/* Single speed mode */
+		.rate_min = 8000,
+		.rate_max = 50000,
+		.mclk_fs = (unsigned int[]) { 32, 64, 128, 192, 256,
+					      384, 512, 768, 1024 },
+		.mclk_fs_num = 9,
+	}, {
+		/* Double speed mode */
+		.rate_min = 84000,
+		.rate_max = 100000,
+		.mclk_fs = (unsigned int[]) { 128, 192, 256, 384, 512,
+					      768, 1024},
+		.mclk_fs_num = 7,
+	}
+};
+
+/* Es7154 has a separate supply for digital I/O  */
+static const struct snd_soc_dapm_widget es7154_extra_widgets[] = {
+	SND_SOC_DAPM_REGULATOR_SUPPLY("PVDD", 0, 0),
+};
+
+static const struct snd_soc_dapm_route es7154_extra_routes[] = {
+	{ "Playback", NULL, "PVDD", }
+};
+
+static const struct es7134_chip es7154_chip = {
+	.dai_drv = &es7154_dai,
+	.modes = es7154_modes,
+	.mode_num = ARRAY_SIZE(es7154_modes),
+	.extra_routes = es7154_extra_routes,
+	.extra_route_num = ARRAY_SIZE(es7154_extra_routes),
+	.extra_widgets = es7154_extra_widgets,
+	.extra_widget_num = ARRAY_SIZE(es7154_extra_widgets),
+};
+
 static int es7134_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -245,13 +302,14 @@ static int es7134_probe(struct platform_device *pdev)
 
 	return devm_snd_soc_register_component(&pdev->dev,
 				      &es7134_component_driver,
-				      &es7134_dai, 1);
+				      priv->chip->dai_drv, 1);
 }
 
 #ifdef CONFIG_OF
 static const struct of_device_id es7134_ids[] = {
 	{ .compatible = "everest,es7134", .data = &es7134_chip },
 	{ .compatible = "everest,es7144", .data = &es7134_chip },
+	{ .compatible = "everest,es7154", .data = &es7154_chip },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, es7134_ids);
-- 
cgit v1.2.3


From 73ad0df572901e03fc703b6f114e4442291f45c2 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Tue, 3 Jul 2018 17:56:30 +0300
Subject: ASoC: atmel-i2s: Remove unnecessary audio PLL clock (aclk)

The generated clock (gclk) driver is able to set aclk as its parent and
change its rate alone, if needed. This means that our driver no longer
needs to configure aclk and we can let gclk select and configure its
clock source.

Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/atmel/atmel-i2s.c | 46 +++++++--------------------------------------
 1 file changed, 7 insertions(+), 39 deletions(-)

diff --git a/sound/soc/atmel/atmel-i2s.c b/sound/soc/atmel/atmel-i2s.c
index 5d3b5af9fd92..d88c1d995036 100644
--- a/sound/soc/atmel/atmel-i2s.c
+++ b/sound/soc/atmel/atmel-i2s.c
@@ -206,7 +206,6 @@ struct atmel_i2s_dev {
 	struct regmap				*regmap;
 	struct clk				*pclk;
 	struct clk				*gclk;
-	struct clk				*aclk;
 	struct snd_dmaengine_dai_dma_data	playback;
 	struct snd_dmaengine_dai_dma_data	capture;
 	unsigned int				fmt;
@@ -303,7 +302,7 @@ static int atmel_i2s_get_gck_param(struct atmel_i2s_dev *dev, int fs)
 {
 	int i, best;
 
-	if (!dev->gclk || !dev->aclk) {
+	if (!dev->gclk) {
 		dev_err(dev->dev, "cannot generate the I2S Master Clock\n");
 		return -EINVAL;
 	}
@@ -421,7 +420,7 @@ static int atmel_i2s_switch_mck_generator(struct atmel_i2s_dev *dev,
 					  bool enabled)
 {
 	unsigned int mr, mr_mask;
-	unsigned long aclk_rate;
+	unsigned long gclk_rate;
 	int ret;
 
 	mr = 0;
@@ -445,35 +444,18 @@ static int atmel_i2s_switch_mck_generator(struct atmel_i2s_dev *dev,
 		/* Disable/unprepare the PMC generated clock. */
 		clk_disable_unprepare(dev->gclk);
 
-		/* Disable/unprepare the PLL audio clock. */
-		clk_disable_unprepare(dev->aclk);
 		return 0;
 	}
 
 	if (!dev->gck_param)
 		return -EINVAL;
 
-	aclk_rate = dev->gck_param->mck * (dev->gck_param->imckdiv + 1);
+	gclk_rate = dev->gck_param->mck * (dev->gck_param->imckdiv + 1);
 
-	/* Fist change the PLL audio clock frequency ... */
-	ret = clk_set_rate(dev->aclk, aclk_rate);
+	ret = clk_set_rate(dev->gclk, gclk_rate);
 	if (ret)
 		return ret;
 
-	/*
-	 * ... then set the PMC generated clock rate to the very same frequency
-	 * to set the gclk parent to aclk.
-	 */
-	ret = clk_set_rate(dev->gclk, aclk_rate);
-	if (ret)
-		return ret;
-
-	/* Prepare and enable the PLL audio clock first ... */
-	ret = clk_prepare_enable(dev->aclk);
-	if (ret)
-		return ret;
-
-	/* ... then prepare and enable the PMC generated clock. */
 	ret = clk_prepare_enable(dev->gclk);
 	if (ret)
 		return ret;
@@ -668,28 +650,14 @@ static int atmel_i2s_probe(struct platform_device *pdev)
 		return err;
 	}
 
-	/* Get audio clocks to generate the I2S Master Clock (I2S_MCK) */
-	dev->aclk = devm_clk_get(&pdev->dev, "aclk");
+	/* Get audio clock to generate the I2S Master Clock (I2S_MCK) */
 	dev->gclk = devm_clk_get(&pdev->dev, "gclk");
-	if (IS_ERR(dev->aclk) && IS_ERR(dev->gclk)) {
-		if (PTR_ERR(dev->aclk) == -EPROBE_DEFER ||
-		    PTR_ERR(dev->gclk) == -EPROBE_DEFER)
+	if (IS_ERR(dev->gclk)) {
+		if (PTR_ERR(dev->gclk) == -EPROBE_DEFER)
 			return -EPROBE_DEFER;
 		/* Master Mode not supported */
-		dev->aclk = NULL;
 		dev->gclk = NULL;
-	} else if (IS_ERR(dev->gclk)) {
-		err = PTR_ERR(dev->gclk);
-		dev_err(&pdev->dev,
-			"failed to get the PMC generated clock: %d\n", err);
-		return err;
-	} else if (IS_ERR(dev->aclk)) {
-		err = PTR_ERR(dev->aclk);
-		dev_err(&pdev->dev,
-			"failed to get the PLL audio clock: %d\n", err);
-		return err;
 	}
-
 	dev->dev = &pdev->dev;
 	dev->regmap = regmap;
 	platform_set_drvdata(pdev, dev);
-- 
cgit v1.2.3


From 2bd368d7bf21028f37a123041a138922254d4840 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Tue, 3 Jul 2018 17:56:31 +0300
Subject: ASoC: atmel-i2s: dt-bindings: Remove unnecessary phandle to aclk

The optional clock phandle to aclk (Audio PLL clock) is no longer needed
by the driver.

Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/atmel-i2s.txt | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/sound/atmel-i2s.txt b/Documentation/devicetree/bindings/sound/atmel-i2s.txt
index 735368b8a73f..40549f496a81 100644
--- a/Documentation/devicetree/bindings/sound/atmel-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/atmel-i2s.txt
@@ -15,7 +15,6 @@ Required properties:
 - clock-names:    Should be one of each entry matching the clocks phandles list:
                   - "pclk" (peripheral clock) Required.
                   - "gclk" (generated clock) Optional (1).
-                  - "aclk" (Audio PLL clock) Optional (1).
                   - "muxclk" (I2S mux clock) Optional (1).
 
 Optional properties:
@@ -23,9 +22,9 @@ Optional properties:
 - princtrl-names: Should contain only one value - "default".
 
 
-(1) : Only the peripheral clock is required. The generated clock, the Audio
-      PLL clock adn the I2S mux clock are optional and should only be set
-      together, when Master Mode is required.
+(1) : Only the peripheral clock is required. The generated clock and the I2S
+      mux clock are optional and should only be set together, when Master Mode
+      is required.
 
 Example:
 
@@ -40,8 +39,8 @@ Example:
 			(AT91_XDMAC_DT_MEM_IF(0) | AT91_XDMAC_DT_PER_IF(1) |
 			 AT91_XDMAC_DT_PERID(32))>;
 		dma-names = "tx", "rx";
-		clocks = <&i2s0_clk>, <&i2s0_gclk>, <&audio_pll_pmc>, <&i2s0muxck>;
-		clock-names = "pclk", "gclk", "aclk", "muxclk";
+		clocks = <&i2s0_clk>, <&i2s0_gclk>, <&i2s0muxck>;
+		clock-names = "pclk", "gclk", "muxclk";
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_i2s0_default>;
 	};
-- 
cgit v1.2.3


From a655de808cbde6c58b3298e704d786b53f59fb5d Mon Sep 17 00:00:00 2001
From: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Date: Mon, 2 Jul 2018 16:59:54 +0100
Subject: ASoC: core: Allow topology to override machine driver FE DAI link
 config.

Machine drivers statically define a number of DAI links that currently
cannot be changed or removed by topology. This means PCMs and platform
components cannot be changed by topology at runtime AND machine drivers
are tightly coupled to topology.

This patch allows topology to override the machine driver DAI link config
in order to reuse machine drivers with different topologies and platform
components. The patch supports :-

1) create new FE PCMs with a topology defined PCM ID.
2) destroy existing static FE PCMs
3) change the platform component driver.
4) assign any new HW params fixups.
5) assign a new card name prefix to differentiate this topology to userspace.

The patch requires no changes to the machine drivers, but does add some
platform component flags that the platform component driver can assign
before loading topologies.

Signed-off-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  13 +++++++
 sound/soc/soc-core.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++++--
 sound/soc/soc-pcm.c  |  12 ++++++
 3 files changed, 123 insertions(+), 3 deletions(-)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 16f0bf10cc42..870ba6b64817 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -803,6 +803,14 @@ struct snd_soc_component_driver {
 	unsigned int use_pmdown_time:1; /* care pmdown_time at stop */
 	unsigned int endianness:1;
 	unsigned int non_legacy_dai_naming:1;
+
+	/* this component uses topology and ignore machine driver FEs */
+	const char *ignore_machine;
+	const char *topology_name_prefix;
+	int (*be_hw_params_fixup)(struct snd_soc_pcm_runtime *rtd,
+				  struct snd_pcm_hw_params *params);
+	bool use_dai_pcm_id;	/* use the DAI link PCM ID as PCM device number */
+	int be_pcm_base;	/* base device ID for all BE PCMs */
 };
 
 struct snd_soc_component {
@@ -960,6 +968,9 @@ struct snd_soc_dai_link {
 	/* pmdown_time is ignored at stop */
 	unsigned int ignore_pmdown_time:1;
 
+	/* Do not create a PCM for this DAI link (Backend link) */
+	unsigned int ignore:1;
+
 	struct list_head list; /* DAI link list of the soc card */
 	struct snd_soc_dobj dobj; /* For topology */
 };
@@ -999,6 +1010,7 @@ struct snd_soc_card {
 	const char *long_name;
 	const char *driver_name;
 	char dmi_longname[80];
+	char topology_shortname[32];
 
 	struct device *dev;
 	struct snd_card *snd_card;
@@ -1008,6 +1020,7 @@ struct snd_soc_card {
 	struct mutex dapm_mutex;
 
 	bool instantiated;
+	bool topology_shortname_created;
 
 	int (*probe)(struct snd_soc_card *card);
 	int (*late_probe)(struct snd_soc_card *card);
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 68b08781c832..00bd58d167dd 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -847,6 +847,9 @@ static int soc_bind_dai_link(struct snd_soc_card *card,
 	const char *platform_name;
 	int i;
 
+	if (dai_link->ignore)
+		return 0;
+
 	dev_dbg(card->dev, "ASoC: binding %s\n", dai_link->name);
 
 	if (soc_is_dai_link_bound(card, dai_link)) {
@@ -1456,7 +1459,9 @@ static int soc_probe_link_dais(struct snd_soc_card *card,
 {
 	struct snd_soc_dai_link *dai_link = rtd->dai_link;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	int i, ret;
+	struct snd_soc_rtdcom_list *rtdcom;
+	struct snd_soc_component *component;
+	int i, ret, num;
 
 	dev_dbg(card->dev, "ASoC: probe %s dai link %d late %d\n",
 			card->name, rtd->num, order);
@@ -1502,9 +1507,28 @@ static int soc_probe_link_dais(struct snd_soc_card *card,
 		soc_dpcm_debugfs_add(rtd);
 #endif
 
+	num = rtd->num;
+
+	/*
+	 * most drivers will register their PCMs using DAI link ordering but
+	 * topology based drivers can use the DAI link id field to set PCM
+	 * device number and then use rtd + a base offset of the BEs.
+	 */
+	for_each_rtdcom(rtd, rtdcom) {
+		component = rtdcom->component;
+
+		if (!component->driver->use_dai_pcm_id)
+			continue;
+
+		if (rtd->dai_link->no_pcm)
+			num += component->driver->be_pcm_base;
+		else
+			num = rtd->dai_link->id;
+	}
+
 	if (cpu_dai->driver->compress_new) {
 		/*create compress_device"*/
-		ret = cpu_dai->driver->compress_new(rtd, rtd->num);
+		ret = cpu_dai->driver->compress_new(rtd, num);
 		if (ret < 0) {
 			dev_err(card->dev, "ASoC: can't create compress %s\n",
 					 dai_link->stream_name);
@@ -1514,7 +1538,7 @@ static int soc_probe_link_dais(struct snd_soc_card *card,
 
 		if (!dai_link->params) {
 			/* create the pcm */
-			ret = soc_new_pcm(rtd, rtd->num);
+			ret = soc_new_pcm(rtd, num);
 			if (ret < 0) {
 				dev_err(card->dev, "ASoC: can't create pcm %s :%d\n",
 				       dai_link->stream_name, ret);
@@ -1841,6 +1865,74 @@ int snd_soc_set_dmi_name(struct snd_soc_card *card, const char *flavour)
 EXPORT_SYMBOL_GPL(snd_soc_set_dmi_name);
 #endif /* CONFIG_DMI */
 
+static void soc_check_tplg_fes(struct snd_soc_card *card)
+{
+	struct snd_soc_component *component;
+	const struct snd_soc_component_driver *comp_drv;
+	struct snd_soc_dai_link *dai_link;
+	int i;
+
+	list_for_each_entry(component, &component_list, list) {
+
+		/* does this component override FEs ? */
+		if (!component->driver->ignore_machine)
+			continue;
+
+		/* for this machine ? */
+		if (strcmp(component->driver->ignore_machine,
+			   card->dev->driver->name))
+			continue;
+
+		/* machine matches, so override the rtd data */
+		for (i = 0; i < card->num_links; i++) {
+
+			dai_link = &card->dai_link[i];
+
+			/* ignore this FE */
+			if (dai_link->dynamic) {
+				dai_link->ignore = true;
+				continue;
+			}
+
+			dev_info(card->dev, "info: override FE DAI link %s\n",
+				 card->dai_link[i].name);
+
+			/* override platform component */
+			dai_link->platform_name = component->name;
+
+			/* convert non BE into BE */
+			dai_link->no_pcm = 1;
+
+			/* override any BE fixups */
+			dai_link->be_hw_params_fixup =
+				component->driver->be_hw_params_fixup;
+
+			/* most BE links don't set stream name, so set it to
+			 * dai link name if it's NULL to help bind widgets.
+			 */
+			if (!dai_link->stream_name)
+				dai_link->stream_name = dai_link->name;
+		}
+
+		/* Inform userspace we are using alternate topology */
+		if (component->driver->topology_name_prefix) {
+
+			/* topology shortname created ? */
+			if (!card->topology_shortname_created) {
+				comp_drv = component->driver;
+
+				snprintf(card->topology_shortname, 32, "%s-%s",
+					 comp_drv->topology_name_prefix,
+					 card->name);
+				card->topology_shortname_created = true;
+			}
+
+			/* use topology shortname */
+			card->name = card->topology_shortname;
+		}
+	}
+}
+
 static int snd_soc_instantiate_card(struct snd_soc_card *card)
 {
 	struct snd_soc_pcm_runtime *rtd;
@@ -1850,6 +1942,9 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 	mutex_lock(&client_mutex);
 	mutex_lock_nested(&card->mutex, SND_SOC_CARD_CLASS_INIT);
 
+	/* check whether any platform is ignore machine FE and using topology */
+	soc_check_tplg_fes(card);
+
 	/* bind DAIs */
 	for (i = 0; i < card->num_links; i++) {
 		ret = soc_bind_dai_link(card, &card->dai_link[i]);
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index c2a31b51da4f..b7e67b871c0c 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -859,8 +859,20 @@ int soc_dai_hw_params(struct snd_pcm_substream *substream,
 		      struct snd_pcm_hw_params *params,
 		      struct snd_soc_dai *dai)
 {
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	int ret;
 
+	/* perform any topology hw_params fixups before DAI  */
+	if (rtd->dai_link->be_hw_params_fixup) {
+		ret = rtd->dai_link->be_hw_params_fixup(rtd, params);
+		if (ret < 0) {
+			dev_err(rtd->dev,
+				"ASoC: hw_params topology fixup failed %d\n",
+				ret);
+			return ret;
+		}
+	}
+
 	if (dai->driver->ops->hw_params) {
 		ret = dai->driver->ops->hw_params(substream, params, dai);
 		if (ret < 0) {
-- 
cgit v1.2.3


From 09230435dffdb13de507e5e40b524b0069fc5c7b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 3 Jul 2018 09:07:46 -0700
Subject: iomap: refactor iomap_dio_actor

Split the function up into two helpers for the bio based I/O and hole
case, and a small helper to call the two.  This separates the code a
little better in preparation for supporting I/O to inline data.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c | 88 +++++++++++++++++++++++++++++++++++++-------------------------
 1 file changed, 52 insertions(+), 36 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 2ebff76039b5..4d8ff0f5ecc9 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1327,10 +1327,9 @@ iomap_dio_zero(struct iomap_dio *dio, struct iomap *iomap, loff_t pos,
 }
 
 static loff_t
-iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
-		void *data, struct iomap *iomap)
+iomap_dio_bio_actor(struct inode *inode, loff_t pos, loff_t length,
+		struct iomap_dio *dio, struct iomap *iomap)
 {
-	struct iomap_dio *dio = data;
 	unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
 	unsigned int fs_block_size = i_blocksize(inode), pad;
 	unsigned int align = iov_iter_alignment(dio->submit.iter);
@@ -1344,41 +1343,27 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	if ((pos | length | align) & ((1 << blkbits) - 1))
 		return -EINVAL;
 
-	switch (iomap->type) {
-	case IOMAP_HOLE:
-		if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
-			return -EIO;
-		/*FALLTHRU*/
-	case IOMAP_UNWRITTEN:
-		if (!(dio->flags & IOMAP_DIO_WRITE)) {
-			length = iov_iter_zero(length, dio->submit.iter);
-			dio->size += length;
-			return length;
-		}
+	if (iomap->type == IOMAP_UNWRITTEN) {
 		dio->flags |= IOMAP_DIO_UNWRITTEN;
 		need_zeroout = true;
-		break;
-	case IOMAP_MAPPED:
-		if (iomap->flags & IOMAP_F_SHARED)
-			dio->flags |= IOMAP_DIO_COW;
-		if (iomap->flags & IOMAP_F_NEW) {
-			need_zeroout = true;
-		} else {
-			/*
-			 * Use a FUA write if we need datasync semantics, this
-			 * is a pure data IO that doesn't require any metadata
-			 * updates and the underlying device supports FUA. This
-			 * allows us to avoid cache flushes on IO completion.
-			 */
-			if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
-			    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
-			    blk_queue_fua(bdev_get_queue(iomap->bdev)))
-				use_fua = true;
-		}
-		break;
-	default:
-		WARN_ON_ONCE(1);
-		return -EIO;
+	}
+
+	if (iomap->flags & IOMAP_F_SHARED)
+		dio->flags |= IOMAP_DIO_COW;
+
+	if (iomap->flags & IOMAP_F_NEW) {
+		need_zeroout = true;
+	} else {
+		/*
+		 * Use a FUA write if we need datasync semantics, this
+		 * is a pure data IO that doesn't require any metadata
+		 * updates and the underlying device supports FUA. This
+		 * allows us to avoid cache flushes on IO completion.
+		 */
+		if (!(iomap->flags & (IOMAP_F_SHARED|IOMAP_F_DIRTY)) &&
+		    (dio->flags & IOMAP_DIO_WRITE_FUA) &&
+		    blk_queue_fua(bdev_get_queue(iomap->bdev)))
+			use_fua = true;
 	}
 
 	/*
@@ -1457,6 +1442,37 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 	return copied;
 }
 
+static loff_t
+iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio)
+{
+	length = iov_iter_zero(length, dio->submit.iter);
+	dio->size += length;
+	return length;
+}
+
+static loff_t
+iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
+		void *data, struct iomap *iomap)
+{
+	struct iomap_dio *dio = data;
+
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		if (WARN_ON_ONCE(dio->flags & IOMAP_DIO_WRITE))
+			return -EIO;
+		return iomap_dio_hole_actor(length, dio);
+	case IOMAP_UNWRITTEN:
+		if (!(dio->flags & IOMAP_DIO_WRITE))
+			return iomap_dio_hole_actor(length, dio);
+		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
+	case IOMAP_MAPPED:
+		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
+	default:
+		WARN_ON_ONCE(1);
+		return -EIO;
+	}
+}
+
 /*
  * iomap_dio_rw() always completes O_[D]SYNC writes regardless of whether the IO
  * is being issued as AIO or not.  This allows us to optimise pure data writes
-- 
cgit v1.2.3


From ec181f6782d8e8c22aa2c3462a20195cfa214ec6 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 3 Jul 2018 09:07:47 -0700
Subject: iomap: support direct I/O to inline data

Add support for reading from and writing to inline data to iomap_dio_rw.
This saves filesystems from having to implement fallback code for this
case.

The inline data is actually cached in the inode, so the I/O is only
direct in the sense that it doesn't go through the page cache.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/fs/iomap.c b/fs/iomap.c
index 4d8ff0f5ecc9..98a1fdd5c091 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -1450,6 +1450,33 @@ iomap_dio_hole_actor(loff_t length, struct iomap_dio *dio)
 	return length;
 }
 
+static loff_t
+iomap_dio_inline_actor(struct inode *inode, loff_t pos, loff_t length,
+		struct iomap_dio *dio, struct iomap *iomap)
+{
+	struct iov_iter *iter = dio->submit.iter;
+	size_t copied;
+
+	BUG_ON(pos + length > PAGE_SIZE - offset_in_page(iomap->inline_data));
+
+	if (dio->flags & IOMAP_DIO_WRITE) {
+		loff_t size = inode->i_size;
+
+		if (pos > size)
+			memset(iomap->inline_data + size, 0, pos - size);
+		copied = copy_from_iter(iomap->inline_data + pos, length, iter);
+		if (copied) {
+			if (pos + copied > size)
+				i_size_write(inode, pos + copied);
+			mark_inode_dirty(inode);
+		}
+	} else {
+		copied = copy_to_iter(iomap->inline_data + pos, length, iter);
+	}
+	dio->size += copied;
+	return copied;
+}
+
 static loff_t
 iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		void *data, struct iomap *iomap)
@@ -1467,6 +1494,8 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
 	case IOMAP_MAPPED:
 		return iomap_dio_bio_actor(inode, pos, length, dio, iomap);
+	case IOMAP_INLINE:
+		return iomap_dio_inline_actor(inode, pos, length, dio, iomap);
 	default:
 		WARN_ON_ONCE(1);
 		return -EIO;
-- 
cgit v1.2.3


From 806a1477b10a153cd01ee7ccba8ca2492df3e0b2 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Tue, 3 Jul 2018 09:07:47 -0700
Subject: iomap: add inline data support to iomap_readpage_actor

Just copy the inline data into the page using the existing helper.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/iomap.c b/fs/iomap.c
index 98a1fdd5c091..13cdcf33e6c0 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -155,6 +155,12 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	bool is_contig = false;
 	sector_t sector;
 
+	if (iomap->type == IOMAP_INLINE) {
+		WARN_ON_ONCE(poff);
+		iomap_read_inline_data(inode, page, iomap);
+		return PAGE_SIZE;
+	}
+
 	/* we don't support blocksize < PAGE_SIZE quite yet. */
 	WARN_ON_ONCE(pos != page_offset(page));
 	WARN_ON_ONCE(plen != PAGE_SIZE);
-- 
cgit v1.2.3


From cfb8282e18e292a8efc4d13ea1e4547a47dfb2d0 Mon Sep 17 00:00:00 2001
From: Amit Nischal <anischal@codeaurora.org>
Date: Mon, 11 Jun 2018 12:08:15 +0530
Subject: clk: qcom: Enable clocks which needs to be always on for SDM845

There are certain clocks which needs to be always enabled for system
operation. Add support for the same by adding 'CLK_IS_CRITICAL' flag
for such clocks.

Signed-off-by: Amit Nischal <anischal@codeaurora.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/gcc-sdm845.c               | 43 ++++++++++++++++++++++++++---
 include/dt-bindings/clock/qcom,gcc-sdm845.h |  2 ++
 2 files changed, 41 insertions(+), 4 deletions(-)

diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c
index e78e6f5b99fc..0f694ed4238a 100644
--- a/drivers/clk/qcom/gcc-sdm845.c
+++ b/drivers/clk/qcom/gcc-sdm845.c
@@ -1103,6 +1103,7 @@ static struct clk_branch gcc_camera_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_camera_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1129,6 +1130,7 @@ static struct clk_branch gcc_camera_xo_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_camera_xo_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1270,6 +1272,7 @@ static struct clk_branch gcc_disp_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_disp_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1328,6 +1331,7 @@ static struct clk_branch gcc_disp_xo_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_disp_xo_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -1397,6 +1401,7 @@ static struct clk_branch gcc_gpu_cfg_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_gpu_cfg_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -2985,6 +2990,7 @@ static struct clk_branch gcc_video_ahb_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_video_ahb_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -3011,6 +3017,7 @@ static struct clk_branch gcc_video_xo_clk = {
 		.enable_mask = BIT(0),
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_video_xo_clk",
+			.flags = CLK_IS_CRITICAL,
 			.ops = &clk_branch2_ops,
 		},
 	},
@@ -3049,6 +3056,36 @@ static struct clk_branch gcc_vs_ctrl_clk = {
 	},
 };
 
+static struct clk_branch gcc_cpuss_dvm_bus_clk = {
+	.halt_reg = 0x48190,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x48190,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cpuss_dvm_bus_clk",
+			.flags = CLK_IS_CRITICAL,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch gcc_cpuss_gnoc_clk = {
+	.halt_reg = 0x48004,
+	.halt_check = BRANCH_HALT_VOTED,
+	.hwcg_reg = 0x48004,
+	.hwcg_bit = 1,
+	.clkr = {
+		.enable_reg = 0x52004,
+		.enable_mask = BIT(22),
+		.hw.init = &(struct clk_init_data){
+			.name = "gcc_cpuss_gnoc_clk",
+			.flags = CLK_IS_CRITICAL,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
 static struct gdsc pcie_0_gdsc = {
 	.gdscr = 0x6b004,
 	.pd = {
@@ -3344,6 +3381,8 @@ static struct clk_regmap *gcc_sdm845_clocks[] = {
 	[GPLL0] = &gpll0.clkr,
 	[GPLL0_OUT_EVEN] = &gpll0_out_even.clkr,
 	[GPLL4] = &gpll4.clkr,
+	[GCC_CPUSS_DVM_BUS_CLK] = &gcc_cpuss_dvm_bus_clk.clkr,
+	[GCC_CPUSS_GNOC_CLK] = &gcc_cpuss_gnoc_clk.clkr,
 };
 
 static const struct qcom_reset_map gcc_sdm845_resets[] = {
@@ -3433,10 +3472,6 @@ static int gcc_sdm845_probe(struct platform_device *pdev)
 	regmap_update_bits(regmap, 0x09ffc, 0x3, 0x3);
 	regmap_update_bits(regmap, 0x71028, 0x3, 0x3);
 
-	/* Enable CPUSS clocks */
-	regmap_update_bits(regmap, 0x48190, BIT(0), 0x1);
-	regmap_update_bits(regmap, 0x52004, BIT(22), 0x1);
-
 	return qcom_cc_really_probe(pdev, &gcc_sdm845_desc, regmap);
 }
 
diff --git a/include/dt-bindings/clock/qcom,gcc-sdm845.h b/include/dt-bindings/clock/qcom,gcc-sdm845.h
index aca61264f12c..f96fc2dbf60e 100644
--- a/include/dt-bindings/clock/qcom,gcc-sdm845.h
+++ b/include/dt-bindings/clock/qcom,gcc-sdm845.h
@@ -192,6 +192,8 @@
 #define GCC_VS_CTRL_CLK_SRC					182
 #define GCC_VSENSOR_CLK_SRC					183
 #define GPLL4							184
+#define GCC_CPUSS_DVM_BUS_CLK					185
+#define GCC_CPUSS_GNOC_CLK					186
 
 /* GCC Resets */
 #define GCC_MMSS_BCR						0
-- 
cgit v1.2.3


From f1d34bfd70b1b4543a139ea28bad4c001c5f413d Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Tue, 19 Jun 2018 15:02:16 +0200
Subject: drm/vmwgfx: Replace vmw_dma_buffer with vmw_buffer_object

Initially vmware buffer objects were only used as DMA buffers, so the name
DMA buffer was a natural one. However, currently they are used also as
dumb buffers and MOBs backing guest backed objects so renaming them to
buffer objects is logical. Particularly since there is a dmabuf subsystem
in the kernel where a dma buffer means something completely different.

This also renames user-space api structures and IOCTL names
correspondingly, but the old names remain defined for now and the ABI
hasn't changed.

There are a couple of minor style changes to make checkpatch happy.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/Makefile            |   4 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c         | 376 ++++++++++++
 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c     | 887 -----------------------------
 drivers/gpu/drm/vmwgfx/vmwgfx_context.c    |  10 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c    |  10 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c     | 376 ------------
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c        |  18 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h        | 129 ++---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c    |  86 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_fb.c         |  16 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c      |   4 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c        | 203 ++++---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.h        |  58 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c        |  10 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c    |  24 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c   | 280 ++++-----
 drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c       | 100 ++--
 drivers/gpu/drm/vmwgfx/vmwgfx_shader.c     |  22 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c       |  64 +--
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c    |  37 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c | 887 +++++++++++++++++++++++++++++
 include/uapi/drm/vmwgfx_drm.h              |  61 +-
 22 files changed, 1822 insertions(+), 1840 deletions(-)
 create mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
 delete mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
 delete mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
 create mode 100644 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c

diff --git a/drivers/gpu/drm/vmwgfx/Makefile b/drivers/gpu/drm/vmwgfx/Makefile
index 794cc9d5c9b0..09b2aa08363e 100644
--- a/drivers/gpu/drm/vmwgfx/Makefile
+++ b/drivers/gpu/drm/vmwgfx/Makefile
@@ -1,9 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 vmwgfx-y := vmwgfx_execbuf.o vmwgfx_gmr.o vmwgfx_kms.o vmwgfx_drv.o \
-	    vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_buffer.o \
+	    vmwgfx_fb.o vmwgfx_ioctl.o vmwgfx_resource.o vmwgfx_ttm_buffer.o \
 	    vmwgfx_fifo.o vmwgfx_irq.o vmwgfx_ldu.o vmwgfx_ttm_glue.o \
 	    vmwgfx_overlay.o vmwgfx_marker.o vmwgfx_gmrid_manager.o \
-	    vmwgfx_fence.o vmwgfx_dmabuf.o vmwgfx_scrn.o vmwgfx_context.o \
+	    vmwgfx_fence.o vmwgfx_bo.o vmwgfx_scrn.o vmwgfx_context.o \
 	    vmwgfx_surface.o vmwgfx_prime.o vmwgfx_mob.o vmwgfx_shader.o \
 	    vmwgfx_cmdbuf_res.o vmwgfx_cmdbuf.o vmwgfx_stdu.o \
 	    vmwgfx_cotable.o vmwgfx_so.o vmwgfx_binding.o vmwgfx_msg.o \
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
new file mode 100644
index 000000000000..f26f658cccdb
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -0,0 +1,376 @@
+/**************************************************************************
+ *
+ * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#include <drm/ttm/ttm_placement.h>
+
+#include <drm/drmP.h>
+#include "vmwgfx_drv.h"
+
+
+/**
+ * vmw_bo_pin_in_placement - Validate a buffer to placement.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @placement:  The placement to pin it.
+ * @interruptible:  Use interruptible wait.
+ *
+ * Returns
+ *  -ERESTARTSYS if interrupted by a signal.
+ */
+int vmw_bo_pin_in_placement(struct vmw_private *dev_priv,
+			    struct vmw_buffer_object *buf,
+			    struct ttm_placement *placement,
+			    bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+	uint32_t new_flags;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, placement, &ctx);
+
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+
+err:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_bo_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @pin:  Pin buffer if true.
+ * @interruptible:  Use interruptible wait.
+ *
+ * Returns
+ * -ERESTARTSYS if interrupted by a signal.
+ */
+int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
+			      struct vmw_buffer_object *buf,
+			      bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+	uint32_t new_flags;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	if (buf->pin_count > 0) {
+		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+		goto out_unreserve;
+	}
+
+	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx);
+	if (likely(ret == 0) || ret == -ERESTARTSYS)
+		goto out_unreserve;
+
+	ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx);
+
+out_unreserve:
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_bo_pin_in_vram - Move a buffer to vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to move.
+ * @interruptible:  Use interruptible wait.
+ *
+ * Returns
+ * -ERESTARTSYS if interrupted by a signal.
+ */
+int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *buf,
+		       bool interruptible)
+{
+	return vmw_bo_pin_in_placement(dev_priv, buf, &vmw_vram_placement,
+				       interruptible);
+}
+
+/**
+ * vmw_bo_pin_in_start_of_vram - Move a buffer to start of vram.
+ *
+ * This function takes the reservation_sem in write mode.
+ * Flushes and unpins the query bo to avoid failures.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to pin.
+ * @interruptible:  Use interruptible wait.
+ *
+ * Returns
+ * -ERESTARTSYS if interrupted by a signal.
+ */
+int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv,
+				struct vmw_buffer_object *buf,
+				bool interruptible)
+{
+	struct ttm_operation_ctx ctx = {interruptible, false };
+	struct ttm_buffer_object *bo = &buf->base;
+	struct ttm_placement placement;
+	struct ttm_place place;
+	int ret = 0;
+	uint32_t new_flags;
+
+	place = vmw_vram_placement.placement[0];
+	place.lpfn = bo->num_pages;
+	placement.num_placement = 1;
+	placement.placement = &place;
+	placement.num_busy_placement = 1;
+	placement.busy_placement = &place;
+
+	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_execbuf_release_pinned_bo(dev_priv);
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err_unlock;
+
+	/*
+	 * Is this buffer already in vram but not at the start of it?
+	 * In that case, evict it first because TTM isn't good at handling
+	 * that situation.
+	 */
+	if (bo->mem.mem_type == TTM_PL_VRAM &&
+	    bo->mem.start < bo->num_pages &&
+	    bo->mem.start > 0 &&
+	    buf->pin_count == 0) {
+		ctx.interruptible = false;
+		(void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx);
+	}
+
+	if (buf->pin_count > 0)
+		ret = ttm_bo_mem_compat(&placement, &bo->mem,
+					&new_flags) == true ? 0 : -EINVAL;
+	else
+		ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	/* For some reason we didn't end up at the start of vram */
+	WARN_ON(ret == 0 && bo->offset != 0);
+	if (!ret)
+		vmw_bo_pin_reserved(buf, true);
+
+	ttm_bo_unreserve(bo);
+err_unlock:
+	ttm_write_unlock(&dev_priv->reservation_sem);
+
+	return ret;
+}
+
+/**
+ * vmw_bo_unpin - Unpin the buffer given buffer, does not move the buffer.
+ *
+ * This function takes the reservation_sem in write mode.
+ *
+ * @dev_priv:  Driver private.
+ * @buf:  DMA buffer to unpin.
+ * @interruptible:  Use interruptible wait.
+ *
+ * Returns
+ * -ERESTARTSYS if interrupted by a signal.
+ */
+int vmw_bo_unpin(struct vmw_private *dev_priv,
+		 struct vmw_buffer_object *buf,
+		 bool interruptible)
+{
+	struct ttm_buffer_object *bo = &buf->base;
+	int ret;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
+	if (unlikely(ret != 0))
+		goto err;
+
+	vmw_bo_pin_reserved(buf, false);
+
+	ttm_bo_unreserve(bo);
+
+err:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement
+ * of a buffer.
+ *
+ * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved.
+ * @ptr: SVGAGuestPtr returning the result.
+ */
+void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
+			  SVGAGuestPtr *ptr)
+{
+	if (bo->mem.mem_type == TTM_PL_VRAM) {
+		ptr->gmrId = SVGA_GMR_FRAMEBUFFER;
+		ptr->offset = bo->offset;
+	} else {
+		ptr->gmrId = bo->mem.start;
+		ptr->offset = 0;
+	}
+}
+
+
+/**
+ * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it.
+ *
+ * @vbo: The buffer object. Must be reserved.
+ * @pin: Whether to pin or unpin.
+ *
+ */
+void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin)
+{
+	struct ttm_operation_ctx ctx = { false, true };
+	struct ttm_place pl;
+	struct ttm_placement placement;
+	struct ttm_buffer_object *bo = &vbo->base;
+	uint32_t old_mem_type = bo->mem.mem_type;
+	int ret;
+
+	lockdep_assert_held(&bo->resv->lock.base);
+
+	if (pin) {
+		if (vbo->pin_count++ > 0)
+			return;
+	} else {
+		WARN_ON(vbo->pin_count <= 0);
+		if (--vbo->pin_count > 0)
+			return;
+	}
+
+	pl.fpfn = 0;
+	pl.lpfn = 0;
+	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
+		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
+	if (pin)
+		pl.flags |= TTM_PL_FLAG_NO_EVICT;
+
+	memset(&placement, 0, sizeof(placement));
+	placement.num_placement = 1;
+	placement.placement = &pl;
+
+	ret = ttm_bo_validate(bo, &placement, &ctx);
+
+	BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type);
+}
+
+
+/*
+ * vmw_buffer_object_unmap - Tear down a cached buffer object map.
+ *
+ * @vbo: The buffer object whose map we are tearing down.
+ *
+ * This function tears down a cached map set up using
+ * vmw_buffer_object_map_and_cache().
+ */
+void vmw_buffer_object_unmap(struct vmw_buffer_object *vbo)
+{
+	if (vbo->map.bo == NULL)
+		return;
+
+	ttm_bo_kunmap(&vbo->map);
+}
+
+
+/*
+ * vmw_buffer_object_map_and_cache - Map a buffer object and cache the map
+ *
+ * @vbo: The buffer object to map
+ * Return: A kernel virtual address or NULL if mapping failed.
+ *
+ * This function maps a buffer object into the kernel address space, or
+ * returns the virtual kernel address of an already existing map. The virtual
+ * address remains valid as long as the buffer object is pinned or reserved.
+ * The cached map is torn down on either
+ * 1) Buffer object move
+ * 2) Buffer object swapout
+ * 3) Buffer object destruction
+ *
+ */
+void *vmw_buffer_object_map_and_cache(struct vmw_buffer_object *vbo)
+{
+	struct ttm_buffer_object *bo = &vbo->base;
+	bool not_used;
+	void *virtual;
+	int ret;
+
+	virtual = ttm_kmap_obj_virtual(&vbo->map, &not_used);
+	if (virtual)
+		return virtual;
+
+	ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map);
+	if (ret)
+		DRM_ERROR("Buffer object map failed: %d.\n", ret);
+
+	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
deleted file mode 100644
index 21111fd091f9..000000000000
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_buffer.c
+++ /dev/null
@@ -1,887 +0,0 @@
-/**************************************************************************
- *
- * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- **************************************************************************/
-
-#include "vmwgfx_drv.h"
-#include <drm/ttm/ttm_bo_driver.h>
-#include <drm/ttm/ttm_placement.h>
-#include <drm/ttm/ttm_page_alloc.h>
-
-static const struct ttm_place vram_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
-};
-
-static const struct ttm_place vram_ne_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
-};
-
-static const struct ttm_place sys_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
-};
-
-static const struct ttm_place sys_ne_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
-};
-
-static const struct ttm_place gmr_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
-};
-
-static const struct ttm_place gmr_ne_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
-};
-
-static const struct ttm_place mob_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
-};
-
-static const struct ttm_place mob_ne_placement_flags = {
-	.fpfn = 0,
-	.lpfn = 0,
-	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
-};
-
-struct ttm_placement vmw_vram_placement = {
-	.num_placement = 1,
-	.placement = &vram_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &vram_placement_flags
-};
-
-static const struct ttm_place vram_gmr_placement_flags[] = {
-	{
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
-	}
-};
-
-static const struct ttm_place gmr_vram_placement_flags[] = {
-	{
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
-	}
-};
-
-struct ttm_placement vmw_vram_gmr_placement = {
-	.num_placement = 2,
-	.placement = vram_gmr_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &gmr_placement_flags
-};
-
-static const struct ttm_place vram_gmr_ne_placement_flags[] = {
-	{
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED |
-			 TTM_PL_FLAG_NO_EVICT
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED |
-			 TTM_PL_FLAG_NO_EVICT
-	}
-};
-
-struct ttm_placement vmw_vram_gmr_ne_placement = {
-	.num_placement = 2,
-	.placement = vram_gmr_ne_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &gmr_ne_placement_flags
-};
-
-struct ttm_placement vmw_vram_sys_placement = {
-	.num_placement = 1,
-	.placement = &vram_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &sys_placement_flags
-};
-
-struct ttm_placement vmw_vram_ne_placement = {
-	.num_placement = 1,
-	.placement = &vram_ne_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &vram_ne_placement_flags
-};
-
-struct ttm_placement vmw_sys_placement = {
-	.num_placement = 1,
-	.placement = &sys_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &sys_placement_flags
-};
-
-struct ttm_placement vmw_sys_ne_placement = {
-	.num_placement = 1,
-	.placement = &sys_ne_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &sys_ne_placement_flags
-};
-
-static const struct ttm_place evictable_placement_flags[] = {
-	{
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
-	}
-};
-
-static const struct ttm_place nonfixed_placement_flags[] = {
-	{
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
-	}, {
-		.fpfn = 0,
-		.lpfn = 0,
-		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
-	}
-};
-
-struct ttm_placement vmw_evictable_placement = {
-	.num_placement = 4,
-	.placement = evictable_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &sys_placement_flags
-};
-
-struct ttm_placement vmw_srf_placement = {
-	.num_placement = 1,
-	.num_busy_placement = 2,
-	.placement = &gmr_placement_flags,
-	.busy_placement = gmr_vram_placement_flags
-};
-
-struct ttm_placement vmw_mob_placement = {
-	.num_placement = 1,
-	.num_busy_placement = 1,
-	.placement = &mob_placement_flags,
-	.busy_placement = &mob_placement_flags
-};
-
-struct ttm_placement vmw_mob_ne_placement = {
-	.num_placement = 1,
-	.num_busy_placement = 1,
-	.placement = &mob_ne_placement_flags,
-	.busy_placement = &mob_ne_placement_flags
-};
-
-struct ttm_placement vmw_nonfixed_placement = {
-	.num_placement = 3,
-	.placement = nonfixed_placement_flags,
-	.num_busy_placement = 1,
-	.busy_placement = &sys_placement_flags
-};
-
-struct vmw_ttm_tt {
-	struct ttm_dma_tt dma_ttm;
-	struct vmw_private *dev_priv;
-	int gmr_id;
-	struct vmw_mob *mob;
-	int mem_type;
-	struct sg_table sgt;
-	struct vmw_sg_table vsgt;
-	uint64_t sg_alloc_size;
-	bool mapped;
-};
-
-const size_t vmw_tt_size = sizeof(struct vmw_ttm_tt);
-
-/**
- * Helper functions to advance a struct vmw_piter iterator.
- *
- * @viter: Pointer to the iterator.
- *
- * These functions return false if past the end of the list,
- * true otherwise. Functions are selected depending on the current
- * DMA mapping mode.
- */
-static bool __vmw_piter_non_sg_next(struct vmw_piter *viter)
-{
-	return ++(viter->i) < viter->num_pages;
-}
-
-static bool __vmw_piter_sg_next(struct vmw_piter *viter)
-{
-	return __sg_page_iter_next(&viter->iter);
-}
-
-
-/**
- * Helper functions to return a pointer to the current page.
- *
- * @viter: Pointer to the iterator
- *
- * These functions return a pointer to the page currently
- * pointed to by @viter. Functions are selected depending on the
- * current mapping mode.
- */
-static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter)
-{
-	return viter->pages[viter->i];
-}
-
-static struct page *__vmw_piter_sg_page(struct vmw_piter *viter)
-{
-	return sg_page_iter_page(&viter->iter);
-}
-
-
-/**
- * Helper functions to return the DMA address of the current page.
- *
- * @viter: Pointer to the iterator
- *
- * These functions return the DMA address of the page currently
- * pointed to by @viter. Functions are selected depending on the
- * current mapping mode.
- */
-static dma_addr_t __vmw_piter_phys_addr(struct vmw_piter *viter)
-{
-	return page_to_phys(viter->pages[viter->i]);
-}
-
-static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter)
-{
-	return viter->addrs[viter->i];
-}
-
-static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter)
-{
-	return sg_page_iter_dma_address(&viter->iter);
-}
-
-
-/**
- * vmw_piter_start - Initialize a struct vmw_piter.
- *
- * @viter: Pointer to the iterator to initialize
- * @vsgt: Pointer to a struct vmw_sg_table to initialize from
- *
- * Note that we're following the convention of __sg_page_iter_start, so that
- * the iterator doesn't point to a valid page after initialization; it has
- * to be advanced one step first.
- */
-void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt,
-		     unsigned long p_offset)
-{
-	viter->i = p_offset - 1;
-	viter->num_pages = vsgt->num_pages;
-	switch (vsgt->mode) {
-	case vmw_dma_phys:
-		viter->next = &__vmw_piter_non_sg_next;
-		viter->dma_address = &__vmw_piter_phys_addr;
-		viter->page = &__vmw_piter_non_sg_page;
-		viter->pages = vsgt->pages;
-		break;
-	case vmw_dma_alloc_coherent:
-		viter->next = &__vmw_piter_non_sg_next;
-		viter->dma_address = &__vmw_piter_dma_addr;
-		viter->page = &__vmw_piter_non_sg_page;
-		viter->addrs = vsgt->addrs;
-		viter->pages = vsgt->pages;
-		break;
-	case vmw_dma_map_populate:
-	case vmw_dma_map_bind:
-		viter->next = &__vmw_piter_sg_next;
-		viter->dma_address = &__vmw_piter_sg_addr;
-		viter->page = &__vmw_piter_sg_page;
-		__sg_page_iter_start(&viter->iter, vsgt->sgt->sgl,
-				     vsgt->sgt->orig_nents, p_offset);
-		break;
-	default:
-		BUG();
-	}
-}
-
-/**
- * vmw_ttm_unmap_from_dma - unmap  device addresses previsouly mapped for
- * TTM pages
- *
- * @vmw_tt: Pointer to a struct vmw_ttm_backend
- *
- * Used to free dma mappings previously mapped by vmw_ttm_map_for_dma.
- */
-static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt)
-{
-	struct device *dev = vmw_tt->dev_priv->dev->dev;
-
-	dma_unmap_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.nents,
-		DMA_BIDIRECTIONAL);
-	vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents;
-}
-
-/**
- * vmw_ttm_map_for_dma - map TTM pages to get device addresses
- *
- * @vmw_tt: Pointer to a struct vmw_ttm_backend
- *
- * This function is used to get device addresses from the kernel DMA layer.
- * However, it's violating the DMA API in that when this operation has been
- * performed, it's illegal for the CPU to write to the pages without first
- * unmapping the DMA mappings, or calling dma_sync_sg_for_cpu(). It is
- * therefore only legal to call this function if we know that the function
- * dma_sync_sg_for_cpu() is a NOP, and dma_sync_sg_for_device() is at most
- * a CPU write buffer flush.
- */
-static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt)
-{
-	struct device *dev = vmw_tt->dev_priv->dev->dev;
-	int ret;
-
-	ret = dma_map_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.orig_nents,
-			 DMA_BIDIRECTIONAL);
-	if (unlikely(ret == 0))
-		return -ENOMEM;
-
-	vmw_tt->sgt.nents = ret;
-
-	return 0;
-}
-
-/**
- * vmw_ttm_map_dma - Make sure TTM pages are visible to the device
- *
- * @vmw_tt: Pointer to a struct vmw_ttm_tt
- *
- * Select the correct function for and make sure the TTM pages are
- * visible to the device. Allocate storage for the device mappings.
- * If a mapping has already been performed, indicated by the storage
- * pointer being non NULL, the function returns success.
- */
-static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
-{
-	struct vmw_private *dev_priv = vmw_tt->dev_priv;
-	struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
-	struct vmw_sg_table *vsgt = &vmw_tt->vsgt;
-	struct ttm_operation_ctx ctx = {
-		.interruptible = true,
-		.no_wait_gpu = false
-	};
-	struct vmw_piter iter;
-	dma_addr_t old;
-	int ret = 0;
-	static size_t sgl_size;
-	static size_t sgt_size;
-
-	if (vmw_tt->mapped)
-		return 0;
-
-	vsgt->mode = dev_priv->map_mode;
-	vsgt->pages = vmw_tt->dma_ttm.ttm.pages;
-	vsgt->num_pages = vmw_tt->dma_ttm.ttm.num_pages;
-	vsgt->addrs = vmw_tt->dma_ttm.dma_address;
-	vsgt->sgt = &vmw_tt->sgt;
-
-	switch (dev_priv->map_mode) {
-	case vmw_dma_map_bind:
-	case vmw_dma_map_populate:
-		if (unlikely(!sgl_size)) {
-			sgl_size = ttm_round_pot(sizeof(struct scatterlist));
-			sgt_size = ttm_round_pot(sizeof(struct sg_table));
-		}
-		vmw_tt->sg_alloc_size = sgt_size + sgl_size * vsgt->num_pages;
-		ret = ttm_mem_global_alloc(glob, vmw_tt->sg_alloc_size, &ctx);
-		if (unlikely(ret != 0))
-			return ret;
-
-		ret = sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
-						vsgt->num_pages, 0,
-						(unsigned long)
-						vsgt->num_pages << PAGE_SHIFT,
-						GFP_KERNEL);
-		if (unlikely(ret != 0))
-			goto out_sg_alloc_fail;
-
-		if (vsgt->num_pages > vmw_tt->sgt.nents) {
-			uint64_t over_alloc =
-				sgl_size * (vsgt->num_pages -
-					    vmw_tt->sgt.nents);
-
-			ttm_mem_global_free(glob, over_alloc);
-			vmw_tt->sg_alloc_size -= over_alloc;
-		}
-
-		ret = vmw_ttm_map_for_dma(vmw_tt);
-		if (unlikely(ret != 0))
-			goto out_map_fail;
-
-		break;
-	default:
-		break;
-	}
-
-	old = ~((dma_addr_t) 0);
-	vmw_tt->vsgt.num_regions = 0;
-	for (vmw_piter_start(&iter, vsgt, 0); vmw_piter_next(&iter);) {
-		dma_addr_t cur = vmw_piter_dma_addr(&iter);
-
-		if (cur != old + PAGE_SIZE)
-			vmw_tt->vsgt.num_regions++;
-		old = cur;
-	}
-
-	vmw_tt->mapped = true;
-	return 0;
-
-out_map_fail:
-	sg_free_table(vmw_tt->vsgt.sgt);
-	vmw_tt->vsgt.sgt = NULL;
-out_sg_alloc_fail:
-	ttm_mem_global_free(glob, vmw_tt->sg_alloc_size);
-	return ret;
-}
-
-/**
- * vmw_ttm_unmap_dma - Tear down any TTM page device mappings
- *
- * @vmw_tt: Pointer to a struct vmw_ttm_tt
- *
- * Tear down any previously set up device DMA mappings and free
- * any storage space allocated for them. If there are no mappings set up,
- * this function is a NOP.
- */
-static void vmw_ttm_unmap_dma(struct vmw_ttm_tt *vmw_tt)
-{
-	struct vmw_private *dev_priv = vmw_tt->dev_priv;
-
-	if (!vmw_tt->vsgt.sgt)
-		return;
-
-	switch (dev_priv->map_mode) {
-	case vmw_dma_map_bind:
-	case vmw_dma_map_populate:
-		vmw_ttm_unmap_from_dma(vmw_tt);
-		sg_free_table(vmw_tt->vsgt.sgt);
-		vmw_tt->vsgt.sgt = NULL;
-		ttm_mem_global_free(vmw_mem_glob(dev_priv),
-				    vmw_tt->sg_alloc_size);
-		break;
-	default:
-		break;
-	}
-	vmw_tt->mapped = false;
-}
-
-
-/**
- * vmw_bo_map_dma - Make sure buffer object pages are visible to the device
- *
- * @bo: Pointer to a struct ttm_buffer_object
- *
- * Wrapper around vmw_ttm_map_dma, that takes a TTM buffer object pointer
- * instead of a pointer to a struct vmw_ttm_backend as argument.
- * Note that the buffer object must be either pinned or reserved before
- * calling this function.
- */
-int vmw_bo_map_dma(struct ttm_buffer_object *bo)
-{
-	struct vmw_ttm_tt *vmw_tt =
-		container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-
-	return vmw_ttm_map_dma(vmw_tt);
-}
-
-
-/**
- * vmw_bo_unmap_dma - Make sure buffer object pages are visible to the device
- *
- * @bo: Pointer to a struct ttm_buffer_object
- *
- * Wrapper around vmw_ttm_unmap_dma, that takes a TTM buffer object pointer
- * instead of a pointer to a struct vmw_ttm_backend as argument.
- */
-void vmw_bo_unmap_dma(struct ttm_buffer_object *bo)
-{
-	struct vmw_ttm_tt *vmw_tt =
-		container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-
-	vmw_ttm_unmap_dma(vmw_tt);
-}
-
-
-/**
- * vmw_bo_sg_table - Return a struct vmw_sg_table object for a
- * TTM buffer object
- *
- * @bo: Pointer to a struct ttm_buffer_object
- *
- * Returns a pointer to a struct vmw_sg_table object. The object should
- * not be freed after use.
- * Note that for the device addresses to be valid, the buffer object must
- * either be reserved or pinned.
- */
-const struct vmw_sg_table *vmw_bo_sg_table(struct ttm_buffer_object *bo)
-{
-	struct vmw_ttm_tt *vmw_tt =
-		container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-
-	return &vmw_tt->vsgt;
-}
-
-
-static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
-{
-	struct vmw_ttm_tt *vmw_be =
-		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-	int ret;
-
-	ret = vmw_ttm_map_dma(vmw_be);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_be->gmr_id = bo_mem->start;
-	vmw_be->mem_type = bo_mem->mem_type;
-
-	switch (bo_mem->mem_type) {
-	case VMW_PL_GMR:
-		return vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt,
-				    ttm->num_pages, vmw_be->gmr_id);
-	case VMW_PL_MOB:
-		if (unlikely(vmw_be->mob == NULL)) {
-			vmw_be->mob =
-				vmw_mob_create(ttm->num_pages);
-			if (unlikely(vmw_be->mob == NULL))
-				return -ENOMEM;
-		}
-
-		return vmw_mob_bind(vmw_be->dev_priv, vmw_be->mob,
-				    &vmw_be->vsgt, ttm->num_pages,
-				    vmw_be->gmr_id);
-	default:
-		BUG();
-	}
-	return 0;
-}
-
-static int vmw_ttm_unbind(struct ttm_tt *ttm)
-{
-	struct vmw_ttm_tt *vmw_be =
-		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-
-	switch (vmw_be->mem_type) {
-	case VMW_PL_GMR:
-		vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id);
-		break;
-	case VMW_PL_MOB:
-		vmw_mob_unbind(vmw_be->dev_priv, vmw_be->mob);
-		break;
-	default:
-		BUG();
-	}
-
-	if (vmw_be->dev_priv->map_mode == vmw_dma_map_bind)
-		vmw_ttm_unmap_dma(vmw_be);
-
-	return 0;
-}
-
-
-static void vmw_ttm_destroy(struct ttm_tt *ttm)
-{
-	struct vmw_ttm_tt *vmw_be =
-		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-
-	vmw_ttm_unmap_dma(vmw_be);
-	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
-		ttm_dma_tt_fini(&vmw_be->dma_ttm);
-	else
-		ttm_tt_fini(ttm);
-
-	if (vmw_be->mob)
-		vmw_mob_destroy(vmw_be->mob);
-
-	kfree(vmw_be);
-}
-
-
-static int vmw_ttm_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
-{
-	struct vmw_ttm_tt *vmw_tt =
-		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
-	struct vmw_private *dev_priv = vmw_tt->dev_priv;
-	struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
-	int ret;
-
-	if (ttm->state != tt_unpopulated)
-		return 0;
-
-	if (dev_priv->map_mode == vmw_dma_alloc_coherent) {
-		size_t size =
-			ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t));
-		ret = ttm_mem_global_alloc(glob, size, ctx);
-		if (unlikely(ret != 0))
-			return ret;
-
-		ret = ttm_dma_populate(&vmw_tt->dma_ttm, dev_priv->dev->dev,
-					ctx);
-		if (unlikely(ret != 0))
-			ttm_mem_global_free(glob, size);
-	} else
-		ret = ttm_pool_populate(ttm, ctx);
-
-	return ret;
-}
-
-static void vmw_ttm_unpopulate(struct ttm_tt *ttm)
-{
-	struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt,
-						 dma_ttm.ttm);
-	struct vmw_private *dev_priv = vmw_tt->dev_priv;
-	struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
-
-
-	if (vmw_tt->mob) {
-		vmw_mob_destroy(vmw_tt->mob);
-		vmw_tt->mob = NULL;
-	}
-
-	vmw_ttm_unmap_dma(vmw_tt);
-	if (dev_priv->map_mode == vmw_dma_alloc_coherent) {
-		size_t size =
-			ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t));
-
-		ttm_dma_unpopulate(&vmw_tt->dma_ttm, dev_priv->dev->dev);
-		ttm_mem_global_free(glob, size);
-	} else
-		ttm_pool_unpopulate(ttm);
-}
-
-static struct ttm_backend_func vmw_ttm_func = {
-	.bind = vmw_ttm_bind,
-	.unbind = vmw_ttm_unbind,
-	.destroy = vmw_ttm_destroy,
-};
-
-static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo,
-					uint32_t page_flags)
-{
-	struct vmw_ttm_tt *vmw_be;
-	int ret;
-
-	vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL);
-	if (!vmw_be)
-		return NULL;
-
-	vmw_be->dma_ttm.ttm.func = &vmw_ttm_func;
-	vmw_be->dev_priv = container_of(bo->bdev, struct vmw_private, bdev);
-	vmw_be->mob = NULL;
-
-	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
-		ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bo, page_flags);
-	else
-		ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bo, page_flags);
-	if (unlikely(ret != 0))
-		goto out_no_init;
-
-	return &vmw_be->dma_ttm.ttm;
-out_no_init:
-	kfree(vmw_be);
-	return NULL;
-}
-
-static int vmw_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
-{
-	return 0;
-}
-
-static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
-		      struct ttm_mem_type_manager *man)
-{
-	switch (type) {
-	case TTM_PL_SYSTEM:
-		/* System memory */
-
-		man->flags = TTM_MEMTYPE_FLAG_MAPPABLE;
-		man->available_caching = TTM_PL_FLAG_CACHED;
-		man->default_caching = TTM_PL_FLAG_CACHED;
-		break;
-	case TTM_PL_VRAM:
-		/* "On-card" video ram */
-		man->func = &ttm_bo_manager_func;
-		man->gpu_offset = 0;
-		man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE;
-		man->available_caching = TTM_PL_FLAG_CACHED;
-		man->default_caching = TTM_PL_FLAG_CACHED;
-		break;
-	case VMW_PL_GMR:
-	case VMW_PL_MOB:
-		/*
-		 * "Guest Memory Regions" is an aperture like feature with
-		 *  one slot per bo. There is an upper limit of the number of
-		 *  slots as well as the bo size.
-		 */
-		man->func = &vmw_gmrid_manager_func;
-		man->gpu_offset = 0;
-		man->flags = TTM_MEMTYPE_FLAG_CMA | TTM_MEMTYPE_FLAG_MAPPABLE;
-		man->available_caching = TTM_PL_FLAG_CACHED;
-		man->default_caching = TTM_PL_FLAG_CACHED;
-		break;
-	default:
-		DRM_ERROR("Unsupported memory type %u\n", (unsigned)type);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static void vmw_evict_flags(struct ttm_buffer_object *bo,
-		     struct ttm_placement *placement)
-{
-	*placement = vmw_sys_placement;
-}
-
-static int vmw_verify_access(struct ttm_buffer_object *bo, struct file *filp)
-{
-	struct ttm_object_file *tfile =
-		vmw_fpriv((struct drm_file *)filp->private_data)->tfile;
-
-	return vmw_user_dmabuf_verify_access(bo, tfile);
-}
-
-static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
-{
-	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
-	struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev);
-
-	mem->bus.addr = NULL;
-	mem->bus.is_iomem = false;
-	mem->bus.offset = 0;
-	mem->bus.size = mem->num_pages << PAGE_SHIFT;
-	mem->bus.base = 0;
-	if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE))
-		return -EINVAL;
-	switch (mem->mem_type) {
-	case TTM_PL_SYSTEM:
-	case VMW_PL_GMR:
-	case VMW_PL_MOB:
-		return 0;
-	case TTM_PL_VRAM:
-		mem->bus.offset = mem->start << PAGE_SHIFT;
-		mem->bus.base = dev_priv->vram_start;
-		mem->bus.is_iomem = true;
-		break;
-	default:
-		return -EINVAL;
-	}
-	return 0;
-}
-
-static void vmw_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
-{
-}
-
-static int vmw_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
-{
-	return 0;
-}
-
-/**
- * vmw_move_notify - TTM move_notify_callback
- *
- * @bo: The TTM buffer object about to move.
- * @mem: The struct ttm_mem_reg indicating to what memory
- *       region the move is taking place.
- *
- * Calls move_notify for all subsystems needing it.
- * (currently only resources).
- */
-static void vmw_move_notify(struct ttm_buffer_object *bo,
-			    bool evict,
-			    struct ttm_mem_reg *mem)
-{
-	vmw_resource_move_notify(bo, mem);
-	vmw_query_move_notify(bo, mem);
-}
-
-
-/**
- * vmw_swap_notify - TTM move_notify_callback
- *
- * @bo: The TTM buffer object about to be swapped out.
- */
-static void vmw_swap_notify(struct ttm_buffer_object *bo)
-{
-	vmw_resource_swap_notify(bo);
-	(void) ttm_bo_wait(bo, false, false);
-}
-
-
-struct ttm_bo_driver vmw_bo_driver = {
-	.ttm_tt_create = &vmw_ttm_tt_create,
-	.ttm_tt_populate = &vmw_ttm_populate,
-	.ttm_tt_unpopulate = &vmw_ttm_unpopulate,
-	.invalidate_caches = vmw_invalidate_caches,
-	.init_mem_type = vmw_init_mem_type,
-	.eviction_valuable = ttm_bo_eviction_valuable,
-	.evict_flags = vmw_evict_flags,
-	.move = NULL,
-	.verify_access = vmw_verify_access,
-	.move_notify = vmw_move_notify,
-	.swap_notify = vmw_swap_notify,
-	.fault_reserve_notify = &vmw_ttm_fault_reserve_notify,
-	.io_mem_reserve = &vmw_ttm_io_mem_reserve,
-	.io_mem_free = &vmw_ttm_io_mem_free,
-};
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index 3767ac335aca..ff8acc74786c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -38,7 +38,7 @@ struct vmw_user_context {
 	struct vmw_cmdbuf_res_manager *man;
 	struct vmw_resource *cotables[SVGA_COTABLE_DX10_MAX];
 	spinlock_t cotable_lock;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 };
 
 static void vmw_user_context_free(struct vmw_resource *res);
@@ -900,7 +900,7 @@ vmw_context_binding_state(struct vmw_resource *ctx)
  * specified in the parameter.  0 otherwise.
  */
 int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
-			      struct vmw_dma_buffer *mob)
+			      struct vmw_buffer_object *mob)
 {
 	struct vmw_user_context *uctx =
 		container_of(ctx_res, struct vmw_user_context, res);
@@ -908,7 +908,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
 	if (mob == NULL) {
 		if (uctx->dx_query_mob) {
 			uctx->dx_query_mob->dx_query_ctx = NULL;
-			vmw_dmabuf_unreference(&uctx->dx_query_mob);
+			vmw_bo_unreference(&uctx->dx_query_mob);
 			uctx->dx_query_mob = NULL;
 		}
 
@@ -922,7 +922,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
 	mob->dx_query_ctx  = ctx_res;
 
 	if (!uctx->dx_query_mob)
-		uctx->dx_query_mob = vmw_dmabuf_reference(mob);
+		uctx->dx_query_mob = vmw_bo_reference(mob);
 
 	return 0;
 }
@@ -932,7 +932,7 @@ int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
  *
  * @ctx_res: The context resource
  */
-struct vmw_dma_buffer *
+struct vmw_buffer_object *
 vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res)
 {
 	struct vmw_user_context *uctx =
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index cbf54ea7b4c0..1052cd3cb700 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -390,7 +390,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	struct ttm_operation_ctx ctx = { false, false };
 	struct vmw_private *dev_priv = res->dev_priv;
 	struct vmw_cotable *vcotbl = vmw_cotable(res);
-	struct vmw_dma_buffer *buf, *old_buf = res->backup;
+	struct vmw_buffer_object *buf, *old_buf = res->backup;
 	struct ttm_buffer_object *bo, *old_bo = &res->backup->base;
 	size_t old_size = res->backup_size;
 	size_t old_size_read_back = vcotbl->size_read_back;
@@ -415,8 +415,8 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	if (!buf)
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, buf, new_size, &vmw_mob_ne_placement,
-			      true, vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, buf, new_size, &vmw_mob_ne_placement,
+			  true, vmw_bo_bo_free);
 	if (ret) {
 		DRM_ERROR("Failed initializing new cotable MOB.\n");
 		return ret;
@@ -482,7 +482,7 @@ static int vmw_cotable_resize(struct vmw_resource *res, size_t new_size)
 	/* Let go of the old mob. */
 	list_del(&res->mob_head);
 	list_add_tail(&res->mob_head, &buf->res_list);
-	vmw_dmabuf_unreference(&old_buf);
+	vmw_bo_unreference(&old_buf);
 	res->id = vcotbl->type;
 
 	return 0;
@@ -491,7 +491,7 @@ out_map_new:
 	ttm_bo_kunmap(&old_map);
 out_wait:
 	ttm_bo_unreserve(bo);
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
deleted file mode 100644
index d59d9dd16ebc..000000000000
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_dmabuf.c
+++ /dev/null
@@ -1,376 +0,0 @@
-/**************************************************************************
- *
- * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA
- * All Rights Reserved.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the
- * "Software"), to deal in the Software without restriction, including
- * without limitation the rights to use, copy, modify, merge, publish,
- * distribute, sub license, and/or sell copies of the Software, and to
- * permit persons to whom the Software is furnished to do so, subject to
- * the following conditions:
- *
- * The above copyright notice and this permission notice (including the
- * next paragraph) shall be included in all copies or substantial portions
- * of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
- * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
- * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
- * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
- * USE OR OTHER DEALINGS IN THE SOFTWARE.
- *
- **************************************************************************/
-
-#include <drm/ttm/ttm_placement.h>
-
-#include <drm/drmP.h>
-#include "vmwgfx_drv.h"
-
-
-/**
- * vmw_dmabuf_pin_in_placement - Validate a buffer to placement.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @placement:  The placement to pin it.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- *  -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_placement(struct vmw_private *dev_priv,
-				struct vmw_dma_buffer *buf,
-				struct ttm_placement *placement,
-				bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-	uint32_t new_flags;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	if (buf->pin_count > 0)
-		ret = ttm_bo_mem_compat(placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-	else
-		ret = ttm_bo_validate(bo, placement, &ctx);
-
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-
-err:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dmabuf_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @pin:  Pin buffer if true.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
-				  bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-	uint32_t new_flags;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	if (buf->pin_count > 0) {
-		ret = ttm_bo_mem_compat(&vmw_vram_gmr_placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-		goto out_unreserve;
-	}
-
-	ret = ttm_bo_validate(bo, &vmw_vram_gmr_placement, &ctx);
-	if (likely(ret == 0) || ret == -ERESTARTSYS)
-		goto out_unreserve;
-
-	ret = ttm_bo_validate(bo, &vmw_vram_placement, &ctx);
-
-out_unreserve:
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-err:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dmabuf_pin_in_vram - Move a buffer to vram.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to move.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv,
-			   struct vmw_dma_buffer *buf,
-			   bool interruptible)
-{
-	return vmw_dmabuf_pin_in_placement(dev_priv, buf, &vmw_vram_placement,
-					   interruptible);
-}
-
-/**
- * vmw_dmabuf_pin_in_start_of_vram - Move a buffer to start of vram.
- *
- * This function takes the reservation_sem in write mode.
- * Flushes and unpins the query bo to avoid failures.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to pin.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *dev_priv,
-				    struct vmw_dma_buffer *buf,
-				    bool interruptible)
-{
-	struct ttm_operation_ctx ctx = {interruptible, false };
-	struct ttm_buffer_object *bo = &buf->base;
-	struct ttm_placement placement;
-	struct ttm_place place;
-	int ret = 0;
-	uint32_t new_flags;
-
-	place = vmw_vram_placement.placement[0];
-	place.lpfn = bo->num_pages;
-	placement.num_placement = 1;
-	placement.placement = &place;
-	placement.num_busy_placement = 1;
-	placement.busy_placement = &place;
-
-	ret = ttm_write_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	vmw_execbuf_release_pinned_bo(dev_priv);
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err_unlock;
-
-	/*
-	 * Is this buffer already in vram but not at the start of it?
-	 * In that case, evict it first because TTM isn't good at handling
-	 * that situation.
-	 */
-	if (bo->mem.mem_type == TTM_PL_VRAM &&
-	    bo->mem.start < bo->num_pages &&
-	    bo->mem.start > 0 &&
-	    buf->pin_count == 0) {
-		ctx.interruptible = false;
-		(void) ttm_bo_validate(bo, &vmw_sys_placement, &ctx);
-	}
-
-	if (buf->pin_count > 0)
-		ret = ttm_bo_mem_compat(&placement, &bo->mem,
-					&new_flags) == true ? 0 : -EINVAL;
-	else
-		ret = ttm_bo_validate(bo, &placement, &ctx);
-
-	/* For some reason we didn't end up at the start of vram */
-	WARN_ON(ret == 0 && bo->offset != 0);
-	if (!ret)
-		vmw_bo_pin_reserved(buf, true);
-
-	ttm_bo_unreserve(bo);
-err_unlock:
-	ttm_write_unlock(&dev_priv->reservation_sem);
-
-	return ret;
-}
-
-/**
- * vmw_dmabuf_unpin - Unpin the buffer given buffer, does not move the buffer.
- *
- * This function takes the reservation_sem in write mode.
- *
- * @dev_priv:  Driver private.
- * @buf:  DMA buffer to unpin.
- * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
- */
-int vmw_dmabuf_unpin(struct vmw_private *dev_priv,
-		     struct vmw_dma_buffer *buf,
-		     bool interruptible)
-{
-	struct ttm_buffer_object *bo = &buf->base;
-	int ret;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, interruptible);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = ttm_bo_reserve(bo, interruptible, false, NULL);
-	if (unlikely(ret != 0))
-		goto err;
-
-	vmw_bo_pin_reserved(buf, false);
-
-	ttm_bo_unreserve(bo);
-
-err:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_bo_get_guest_ptr - Get the guest ptr representing the current placement
- * of a buffer.
- *
- * @bo: Pointer to a struct ttm_buffer_object. Must be pinned or reserved.
- * @ptr: SVGAGuestPtr returning the result.
- */
-void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *bo,
-			  SVGAGuestPtr *ptr)
-{
-	if (bo->mem.mem_type == TTM_PL_VRAM) {
-		ptr->gmrId = SVGA_GMR_FRAMEBUFFER;
-		ptr->offset = bo->offset;
-	} else {
-		ptr->gmrId = bo->mem.start;
-		ptr->offset = 0;
-	}
-}
-
-
-/**
- * vmw_bo_pin_reserved - Pin or unpin a buffer object without moving it.
- *
- * @vbo: The buffer object. Must be reserved.
- * @pin: Whether to pin or unpin.
- *
- */
-void vmw_bo_pin_reserved(struct vmw_dma_buffer *vbo, bool pin)
-{
-	struct ttm_operation_ctx ctx = { false, true };
-	struct ttm_place pl;
-	struct ttm_placement placement;
-	struct ttm_buffer_object *bo = &vbo->base;
-	uint32_t old_mem_type = bo->mem.mem_type;
-	int ret;
-
-	lockdep_assert_held(&bo->resv->lock.base);
-
-	if (pin) {
-		if (vbo->pin_count++ > 0)
-			return;
-	} else {
-		WARN_ON(vbo->pin_count <= 0);
-		if (--vbo->pin_count > 0)
-			return;
-	}
-
-	pl.fpfn = 0;
-	pl.lpfn = 0;
-	pl.flags = TTM_PL_FLAG_VRAM | VMW_PL_FLAG_GMR | VMW_PL_FLAG_MOB
-		| TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED;
-	if (pin)
-		pl.flags |= TTM_PL_FLAG_NO_EVICT;
-
-	memset(&placement, 0, sizeof(placement));
-	placement.num_placement = 1;
-	placement.placement = &pl;
-
-	ret = ttm_bo_validate(bo, &placement, &ctx);
-
-	BUG_ON(ret != 0 || bo->mem.mem_type != old_mem_type);
-}
-
-
-/*
- * vmw_dma_buffer_unmap - Tear down a cached buffer object map.
- *
- * @vbo: The buffer object whose map we are tearing down.
- *
- * This function tears down a cached map set up using
- * vmw_dma_buffer_map_and_cache().
- */
-void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo)
-{
-	if (vbo->map.bo == NULL)
-		return;
-
-	ttm_bo_kunmap(&vbo->map);
-}
-
-
-/*
- * vmw_dma_buffer_map_and_cache - Map a buffer object and cache the map
- *
- * @vbo: The buffer object to map
- * Return: A kernel virtual address or NULL if mapping failed.
- *
- * This function maps a buffer object into the kernel address space, or
- * returns the virtual kernel address of an already existing map. The virtual
- * address remains valid as long as the buffer object is pinned or reserved.
- * The cached map is torn down on either
- * 1) Buffer object move
- * 2) Buffer object swapout
- * 3) Buffer object destruction
- *
- */
-void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo)
-{
-	struct ttm_buffer_object *bo = &vbo->base;
-	bool not_used;
-	void *virtual;
-	int ret;
-
-	virtual = ttm_kmap_obj_virtual(&vbo->map, &not_used);
-	if (virtual)
-		return virtual;
-
-	ret = ttm_bo_kmap(bo, 0, bo->num_pages, &vbo->map);
-	if (ret)
-		DRM_ERROR("Buffer object map failed: %d.\n", ret);
-
-	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
-}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 09cc721160c4..4f18304226bc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -153,9 +153,9 @@
 static const struct drm_ioctl_desc vmw_ioctls[] = {
 	VMW_IOCTL_DEF(VMW_GET_PARAM, vmw_getparam_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_dmabuf_alloc_ioctl,
+	VMW_IOCTL_DEF(VMW_ALLOC_DMABUF, vmw_bo_alloc_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
-	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_dmabuf_unref_ioctl,
+	VMW_IOCTL_DEF(VMW_UNREF_DMABUF, vmw_bo_unref_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CURSOR_BYPASS,
 		      vmw_kms_cursor_bypass_ioctl,
@@ -219,7 +219,7 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 		      vmw_gb_surface_reference_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_SYNCCPU,
-		      vmw_user_dmabuf_synccpu_ioctl,
+		      vmw_user_bo_synccpu_ioctl,
 		      DRM_RENDER_ALLOW),
 	VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT,
 		      vmw_extended_context_define_ioctl,
@@ -321,7 +321,7 @@ static void vmw_print_capabilities(uint32_t capabilities)
 static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 {
 	int ret;
-	struct vmw_dma_buffer *vbo;
+	struct vmw_buffer_object *vbo;
 	struct ttm_bo_kmap_obj map;
 	volatile SVGA3dQueryResult *result;
 	bool dummy;
@@ -335,9 +335,9 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 	if (!vbo)
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, vbo, PAGE_SIZE,
-			      &vmw_sys_ne_placement, false,
-			      &vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, vbo, PAGE_SIZE,
+			  &vmw_sys_ne_placement, false,
+			  &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -358,7 +358,7 @@ static int vmw_dummy_query_bo_create(struct vmw_private *dev_priv)
 
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Dummy query buffer map failed.\n");
-		vmw_dmabuf_unreference(&vbo);
+		vmw_bo_unreference(&vbo);
 	} else
 		dev_priv->dummy_query_bo = vbo;
 
@@ -460,7 +460,7 @@ static void vmw_release_device_early(struct vmw_private *dev_priv)
 
 	BUG_ON(dev_priv->pinned_bo != NULL);
 
-	vmw_dmabuf_unreference(&dev_priv->dummy_query_bo);
+	vmw_bo_unreference(&dev_priv->dummy_query_bo);
 	if (dev_priv->cman)
 		vmw_cmdbuf_remove_pool(dev_priv->cman);
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 5fcbe1620d50..25c2f668ad6c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -86,7 +86,7 @@ struct vmw_fpriv {
 	bool gb_aware;
 };
 
-struct vmw_dma_buffer {
+struct vmw_buffer_object {
 	struct ttm_buffer_object base;
 	struct list_head res_list;
 	s32 pin_count;
@@ -120,7 +120,7 @@ struct vmw_resource {
 	unsigned long backup_size;
 	bool res_dirty; /* Protected by backup buffer reserved */
 	bool backup_dirty; /* Protected by backup buffer reserved */
-	struct vmw_dma_buffer *backup;
+	struct vmw_buffer_object *backup;
 	unsigned long backup_offset;
 	unsigned long pin_count; /* Protected by resource reserved */
 	const struct vmw_res_func *func;
@@ -304,7 +304,7 @@ struct vmw_sw_context{
 	uint32_t cmd_bounce_size;
 	struct list_head resource_list;
 	struct list_head ctx_resource_list; /* For contexts and cotables */
-	struct vmw_dma_buffer *cur_query_bo;
+	struct vmw_buffer_object *cur_query_bo;
 	struct list_head res_relocations;
 	uint32_t *buf_start;
 	struct vmw_res_cache_entry res_cache[vmw_res_max];
@@ -315,7 +315,7 @@ struct vmw_sw_context{
 	bool staged_bindings_inuse;
 	struct list_head staged_cmd_res;
 	struct vmw_resource_val_node *dx_ctx_node;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct vmw_resource *dx_query_ctx;
 	struct vmw_cmdbuf_res_manager *man;
 };
@@ -513,8 +513,8 @@ struct vmw_private {
 	 * are protected by the cmdbuf mutex.
 	 */
 
-	struct vmw_dma_buffer *dummy_query_bo;
-	struct vmw_dma_buffer *pinned_bo;
+	struct vmw_buffer_object *dummy_query_bo;
+	struct vmw_buffer_object *pinned_bo;
 	uint32_t query_cid;
 	uint32_t query_cid_valid;
 	bool dummy_query_bo_pinned;
@@ -623,43 +623,43 @@ extern int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 				  struct ttm_object_file *tfile,
 				  uint32_t handle,
 				  struct vmw_surface **out_surf,
-				  struct vmw_dma_buffer **out_buf);
+				  struct vmw_buffer_object **out_buf);
 extern int vmw_user_resource_lookup_handle(
 	struct vmw_private *dev_priv,
 	struct ttm_object_file *tfile,
 	uint32_t handle,
 	const struct vmw_user_resource_conv *converter,
 	struct vmw_resource **p_res);
-extern void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo);
-extern int vmw_dmabuf_init(struct vmw_private *dev_priv,
-			   struct vmw_dma_buffer *vmw_bo,
-			   size_t size, struct ttm_placement *placement,
-			   bool interuptable,
-			   void (*bo_free) (struct ttm_buffer_object *bo));
-extern int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
-				  struct ttm_object_file *tfile);
-extern int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
-				 struct ttm_object_file *tfile,
-				 uint32_t size,
-				 bool shareable,
-				 uint32_t *handle,
-				 struct vmw_dma_buffer **p_dma_buf,
-				 struct ttm_base_object **p_base);
-extern int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
-				     struct vmw_dma_buffer *dma_buf,
-				     uint32_t *handle);
-extern int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv);
-extern int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv);
-extern int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
-					 struct drm_file *file_priv);
-extern uint32_t vmw_dmabuf_validate_node(struct ttm_buffer_object *bo,
-					 uint32_t cur_validate_node);
-extern void vmw_dmabuf_validate_clear(struct ttm_buffer_object *bo);
-extern int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-				  uint32_t id, struct vmw_dma_buffer **out,
-				  struct ttm_base_object **base);
+extern void vmw_bo_bo_free(struct ttm_buffer_object *bo);
+extern int vmw_bo_init(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *vmw_bo,
+		       size_t size, struct ttm_placement *placement,
+		       bool interuptable,
+		       void (*bo_free)(struct ttm_buffer_object *bo));
+extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
+				     struct ttm_object_file *tfile);
+extern int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+			     struct ttm_object_file *tfile,
+			     uint32_t size,
+			     bool shareable,
+			     uint32_t *handle,
+			     struct vmw_buffer_object **p_dma_buf,
+			     struct ttm_base_object **p_base);
+extern int vmw_user_bo_reference(struct ttm_object_file *tfile,
+				 struct vmw_buffer_object *dma_buf,
+				 uint32_t *handle);
+extern int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+				     struct drm_file *file_priv);
+extern uint32_t vmw_bo_validate_node(struct ttm_buffer_object *bo,
+				     uint32_t cur_validate_node);
+extern void vmw_bo_validate_clear(struct ttm_buffer_object *bo);
+extern int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+			      uint32_t id, struct vmw_buffer_object **out,
+			      struct ttm_base_object **base);
 extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
 extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
@@ -670,43 +670,43 @@ extern int vmw_user_stream_lookup(struct vmw_private *dev_priv,
 				  struct vmw_resource **out);
 extern void vmw_resource_unreserve(struct vmw_resource *res,
 				   bool switch_backup,
-				   struct vmw_dma_buffer *new_backup,
+				   struct vmw_buffer_object *new_backup,
 				   unsigned long new_backup_offset);
 extern void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 				     struct ttm_mem_reg *mem);
 extern void vmw_query_move_notify(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem);
 extern void vmw_resource_swap_notify(struct ttm_buffer_object *bo);
-extern int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob);
+extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob);
 extern void vmw_fence_single_bo(struct ttm_buffer_object *bo,
 				struct vmw_fence_obj *fence);
 extern void vmw_resource_evict_all(struct vmw_private *dev_priv);
 
 
 /**
- * DMA buffer helper routines - vmwgfx_dmabuf.c
+ * Buffer object helper functions - vmwgfx_bo.c
  */
-extern int vmw_dmabuf_pin_in_placement(struct vmw_private *vmw_priv,
-				       struct vmw_dma_buffer *bo,
-				       struct ttm_placement *placement,
+extern int vmw_bo_pin_in_placement(struct vmw_private *vmw_priv,
+				   struct vmw_buffer_object *bo,
+				   struct ttm_placement *placement,
+				   bool interruptible);
+extern int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
+			      struct vmw_buffer_object *buf,
+			      bool interruptible);
+extern int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
+				     struct vmw_buffer_object *buf,
+				     bool interruptible);
+extern int vmw_bo_pin_in_start_of_vram(struct vmw_private *vmw_priv,
+				       struct vmw_buffer_object *bo,
 				       bool interruptible);
-extern int vmw_dmabuf_pin_in_vram(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
-				  bool interruptible);
-extern int vmw_dmabuf_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
-					 struct vmw_dma_buffer *buf,
-					 bool interruptible);
-extern int vmw_dmabuf_pin_in_start_of_vram(struct vmw_private *vmw_priv,
-					   struct vmw_dma_buffer *bo,
-					   bool interruptible);
-extern int vmw_dmabuf_unpin(struct vmw_private *vmw_priv,
-			    struct vmw_dma_buffer *bo,
-			    bool interruptible);
+extern int vmw_bo_unpin(struct vmw_private *vmw_priv,
+			struct vmw_buffer_object *bo,
+			bool interruptible);
 extern void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *buf,
 				 SVGAGuestPtr *ptr);
-extern void vmw_bo_pin_reserved(struct vmw_dma_buffer *bo, bool pin);
-extern void *vmw_dma_buffer_map_and_cache(struct vmw_dma_buffer *vbo);
-extern void vmw_dma_buffer_unmap(struct vmw_dma_buffer *vbo);
+extern void vmw_bo_pin_reserved(struct vmw_buffer_object *bo, bool pin);
+extern void *vmw_buffer_object_map_and_cache(struct vmw_buffer_object *vbo);
+extern void vmw_buffer_object_unmap(struct vmw_buffer_object *vbo);
 
 /**
  * Misc Ioctl functionality - vmwgfx_ioctl.c
@@ -758,7 +758,7 @@ extern void vmw_ttm_global_release(struct vmw_private *dev_priv);
 extern int vmw_mmap(struct file *filp, struct vm_area_struct *vma);
 
 /**
- * TTM buffer object driver - vmwgfx_buffer.c
+ * TTM buffer object driver - vmwgfx_ttm_buffer.c
  */
 
 extern const size_t vmw_tt_size;
@@ -1041,8 +1041,8 @@ vmw_context_binding_state(struct vmw_resource *ctx);
 extern void vmw_dx_context_scrub_cotables(struct vmw_resource *ctx,
 					  bool readback);
 extern int vmw_context_bind_dx_query(struct vmw_resource *ctx_res,
-				     struct vmw_dma_buffer *mob);
-extern struct vmw_dma_buffer *
+				     struct vmw_buffer_object *mob);
+extern struct vmw_buffer_object *
 vmw_context_get_dx_query_mob(struct vmw_resource *ctx_res);
 
 
@@ -1243,9 +1243,9 @@ static inline struct vmw_surface *vmw_surface_reference(struct vmw_surface *srf)
 	return srf;
 }
 
-static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf)
+static inline void vmw_bo_unreference(struct vmw_buffer_object **buf)
 {
-	struct vmw_dma_buffer *tmp_buf = *buf;
+	struct vmw_buffer_object *tmp_buf = *buf;
 
 	*buf = NULL;
 	if (tmp_buf != NULL) {
@@ -1255,7 +1255,8 @@ static inline void vmw_dmabuf_unreference(struct vmw_dma_buffer **buf)
 	}
 }
 
-static inline struct vmw_dma_buffer *vmw_dmabuf_reference(struct vmw_dma_buffer *buf)
+static inline struct vmw_buffer_object *
+vmw_bo_reference(struct vmw_buffer_object *buf)
 {
 	if (ttm_bo_reference(&buf->base))
 		return buf;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index c9d5cc237124..a8b194655c40 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -92,7 +92,7 @@ struct vmw_resource_val_node {
 	struct list_head head;
 	struct drm_hash_item hash;
 	struct vmw_resource *res;
-	struct vmw_dma_buffer *new_backup;
+	struct vmw_buffer_object *new_backup;
 	struct vmw_ctx_binding_state *staged_bindings;
 	unsigned long new_backup_offset;
 	u32 first_usage : 1;
@@ -126,9 +126,9 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
 static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGAMobId *id,
-				 struct vmw_dma_buffer **vmw_bo_p);
+				 struct vmw_buffer_object **vmw_bo_p);
 static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
-				   struct vmw_dma_buffer *vbo,
+				   struct vmw_buffer_object *vbo,
 				   bool validate_as_mob,
 				   uint32_t *p_val_node);
 /**
@@ -185,7 +185,7 @@ static void vmw_resources_unreserve(struct vmw_sw_context *sw_context,
 		}
 		vmw_resource_unreserve(res, switch_backup, val->new_backup,
 				       val->new_backup_offset);
-		vmw_dmabuf_unreference(&val->new_backup);
+		vmw_bo_unreference(&val->new_backup);
 	}
 }
 
@@ -423,7 +423,7 @@ static int vmw_resource_context_res_add(struct vmw_private *dev_priv,
 	}
 
 	if (dev_priv->has_dx && vmw_res_type(ctx) == vmw_res_dx_context) {
-		struct vmw_dma_buffer *dx_query_mob;
+		struct vmw_buffer_object *dx_query_mob;
 
 		dx_query_mob = vmw_context_get_dx_query_mob(ctx);
 		if (dx_query_mob)
@@ -544,7 +544,7 @@ static int vmw_cmd_ok(struct vmw_private *dev_priv,
  * submission is reached.
  */
 static int vmw_bo_to_validate_list(struct vmw_sw_context *sw_context,
-				   struct vmw_dma_buffer *vbo,
+				   struct vmw_buffer_object *vbo,
 				   bool validate_as_mob,
 				   uint32_t *p_val_node)
 {
@@ -616,7 +616,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context)
 			return ret;
 
 		if (res->backup) {
-			struct vmw_dma_buffer *vbo = res->backup;
+			struct vmw_buffer_object *vbo = res->backup;
 
 			ret = vmw_bo_to_validate_list
 				(sw_context, vbo,
@@ -628,7 +628,7 @@ static int vmw_resources_reserve(struct vmw_sw_context *sw_context)
 	}
 
 	if (sw_context->dx_query_mob) {
-		struct vmw_dma_buffer *expected_dx_query_mob;
+		struct vmw_buffer_object *expected_dx_query_mob;
 
 		expected_dx_query_mob =
 			vmw_context_get_dx_query_mob(sw_context->dx_query_ctx);
@@ -657,7 +657,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context)
 
 	list_for_each_entry(val, &sw_context->resource_list, head) {
 		struct vmw_resource *res = val->res;
-		struct vmw_dma_buffer *backup = res->backup;
+		struct vmw_buffer_object *backup = res->backup;
 
 		ret = vmw_resource_validate(res);
 		if (unlikely(ret != 0)) {
@@ -668,7 +668,7 @@ static int vmw_resources_validate(struct vmw_sw_context *sw_context)
 
 		/* Check if the resource switched backup buffer */
 		if (backup && res->backup && (backup != res->backup)) {
-			struct vmw_dma_buffer *vbo = res->backup;
+			struct vmw_buffer_object *vbo = res->backup;
 
 			ret = vmw_bo_to_validate_list
 				(sw_context, vbo,
@@ -821,7 +821,7 @@ out_no_reloc:
 static int vmw_rebind_all_dx_query(struct vmw_resource *ctx_res)
 {
 	struct vmw_private *dev_priv = ctx_res->dev_priv;
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDXBindAllQuery body;
@@ -1152,7 +1152,7 @@ static int vmw_cmd_present_check(struct vmw_private *dev_priv,
  * command batch.
  */
 static int vmw_query_bo_switch_prepare(struct vmw_private *dev_priv,
-				       struct vmw_dma_buffer *new_query_bo,
+				       struct vmw_buffer_object *new_query_bo,
 				       struct vmw_sw_context *sw_context)
 {
 	struct vmw_res_cache_entry *ctx_entry =
@@ -1234,7 +1234,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 	if (dev_priv->pinned_bo != sw_context->cur_query_bo) {
 		if (dev_priv->pinned_bo) {
 			vmw_bo_pin_reserved(dev_priv->pinned_bo, false);
-			vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+			vmw_bo_unreference(&dev_priv->pinned_bo);
 		}
 
 		if (!sw_context->needs_post_query_barrier) {
@@ -1256,7 +1256,7 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 			dev_priv->query_cid = sw_context->last_query_ctx->id;
 			dev_priv->query_cid_valid = true;
 			dev_priv->pinned_bo =
-				vmw_dmabuf_reference(sw_context->cur_query_bo);
+				vmw_bo_reference(sw_context->cur_query_bo);
 		}
 	}
 }
@@ -1282,15 +1282,14 @@ static void vmw_query_bo_switch_commit(struct vmw_private *dev_priv,
 static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGAMobId *id,
-				 struct vmw_dma_buffer **vmw_bo_p)
+				 struct vmw_buffer_object **vmw_bo_p)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	uint32_t handle = *id;
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
-				     NULL);
+	ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use MOB buffer.\n");
 		ret = -EINVAL;
@@ -1316,7 +1315,7 @@ static int vmw_translate_mob_ptr(struct vmw_private *dev_priv,
 	return 0;
 
 out_no_reloc:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	*vmw_bo_p = NULL;
 	return ret;
 }
@@ -1343,15 +1342,14 @@ out_no_reloc:
 static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 				   struct vmw_sw_context *sw_context,
 				   SVGAGuestPtr *ptr,
-				   struct vmw_dma_buffer **vmw_bo_p)
+				   struct vmw_buffer_object **vmw_bo_p)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	uint32_t handle = ptr->gmrId;
 	struct vmw_relocation *reloc;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(sw_context->fp->tfile, handle, &vmw_bo,
-				     NULL);
+	ret = vmw_user_bo_lookup(sw_context->fp->tfile, handle, &vmw_bo, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("Could not find or use GMR region.\n");
 		ret = -EINVAL;
@@ -1376,7 +1374,7 @@ static int vmw_translate_guest_ptr(struct vmw_private *dev_priv,
 	return 0;
 
 out_no_reloc:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	*vmw_bo_p = NULL;
 	return ret;
 }
@@ -1447,7 +1445,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 		SVGA3dCmdDXBindQuery q;
 	} *cmd;
 
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int    ret;
 
 
@@ -1466,7 +1464,7 @@ static int vmw_cmd_dx_bind_query(struct vmw_private *dev_priv,
 	sw_context->dx_query_mob = vmw_bo;
 	sw_context->dx_query_ctx = sw_context->dx_ctx_node->res;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 
 	return ret;
 }
@@ -1549,7 +1547,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv,
 				struct vmw_sw_context *sw_context,
 				SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdEndGBQuery q;
@@ -1569,7 +1567,7 @@ static int vmw_cmd_end_gb_query(struct vmw_private *dev_priv,
 
 	ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context);
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1584,7 +1582,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv,
 			     struct vmw_sw_context *sw_context,
 			     SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdEndQuery q;
@@ -1623,7 +1621,7 @@ static int vmw_cmd_end_query(struct vmw_private *dev_priv,
 
 	ret = vmw_query_bo_switch_prepare(dev_priv, vmw_bo, sw_context);
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1638,7 +1636,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv,
 				 struct vmw_sw_context *sw_context,
 				 SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdWaitForGBQuery q;
@@ -1656,7 +1654,7 @@ static int vmw_cmd_wait_gb_query(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return 0;
 }
 
@@ -1671,7 +1669,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv,
 			      struct vmw_sw_context *sw_context,
 			      SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	struct vmw_query_cmd {
 		SVGA3dCmdHeader header;
 		SVGA3dCmdWaitForQuery q;
@@ -1708,7 +1706,7 @@ static int vmw_cmd_wait_query(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return 0;
 }
 
@@ -1716,7 +1714,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 		       struct vmw_sw_context *sw_context,
 		       SVGA3dCmdHeader *header)
 {
-	struct vmw_dma_buffer *vmw_bo = NULL;
+	struct vmw_buffer_object *vmw_bo = NULL;
 	struct vmw_surface *srf = NULL;
 	struct vmw_dma_cmd {
 		SVGA3dCmdHeader header;
@@ -1768,7 +1766,7 @@ static int vmw_cmd_dma(struct vmw_private *dev_priv,
 			     header);
 
 out_no_surface:
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 	return ret;
 }
 
@@ -1887,7 +1885,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv,
 				      struct vmw_sw_context *sw_context,
 				      void *buf)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int ret;
 
 	struct {
@@ -1901,7 +1899,7 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	vmw_dmabuf_unreference(&vmw_bo);
+	vmw_bo_unreference(&vmw_bo);
 
 	return ret;
 }
@@ -1928,7 +1926,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv,
 				     uint32_t *buf_id,
 				     unsigned long backup_offset)
 {
-	struct vmw_dma_buffer *dma_buf;
+	struct vmw_buffer_object *dma_buf;
 	int ret;
 
 	ret = vmw_translate_mob_ptr(dev_priv, sw_context, buf_id, &dma_buf);
@@ -1939,7 +1937,7 @@ static int vmw_cmd_res_switch_backup(struct vmw_private *dev_priv,
 	if (val_node->first_usage)
 		val_node->no_buffer_needed = true;
 
-	vmw_dmabuf_unreference(&val_node->new_backup);
+	vmw_bo_unreference(&val_node->new_backup);
 	val_node->new_backup = dma_buf;
 	val_node->new_backup_offset = backup_offset;
 
@@ -3701,8 +3699,8 @@ int vmw_validate_single_buffer(struct vmw_private *dev_priv,
 			       bool interruptible,
 			       bool validate_as_mob)
 {
-	struct vmw_dma_buffer *vbo = container_of(bo, struct vmw_dma_buffer,
-						  base);
+	struct vmw_buffer_object *vbo =
+		container_of(bo, struct vmw_buffer_object, base);
 	struct ttm_operation_ctx ctx = { interruptible, true };
 	int ret;
 
@@ -4423,7 +4421,7 @@ void __vmw_execbuf_release_pinned_bo(struct vmw_private *dev_priv,
 
 	ttm_bo_unref(&query_val.bo);
 	ttm_bo_unref(&pinned_val.bo);
-	vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+	vmw_bo_unreference(&dev_priv->pinned_bo);
 out_unlock:
 	return;
 
@@ -4432,7 +4430,7 @@ out_no_emit:
 out_no_reserve:
 	ttm_bo_unref(&query_val.bo);
 	ttm_bo_unref(&pinned_val.bo);
-	vmw_dmabuf_unreference(&dev_priv->pinned_bo);
+	vmw_bo_unreference(&dev_priv->pinned_bo);
 }
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index 9b7e0aca5f84..dcde4985c574 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -42,7 +42,7 @@ struct vmw_fb_par {
 	void *vmalloc;
 
 	struct mutex bo_mutex;
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	unsigned bo_size;
 	struct drm_framebuffer *set_fb;
 	struct drm_display_mode *set_mode;
@@ -184,7 +184,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work)
 	struct drm_clip_rect clip;
 	struct drm_framebuffer *cur_fb;
 	u8 *src_ptr, *dst_ptr;
-	struct vmw_dma_buffer *vbo = par->vmw_bo;
+	struct vmw_buffer_object *vbo = par->vmw_bo;
 	void *virtual;
 
 	if (!READ_ONCE(par->dirty.active))
@@ -197,7 +197,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work)
 
 	(void) ttm_read_lock(&vmw_priv->reservation_sem, false);
 	(void) ttm_bo_reserve(&vbo->base, false, false, NULL);
-	virtual = vmw_dma_buffer_map_and_cache(vbo);
+	virtual = vmw_buffer_object_map_and_cache(vbo);
 	if (!virtual)
 		goto out_unreserve;
 
@@ -391,9 +391,9 @@ static void vmw_fb_imageblit(struct fb_info *info, const struct fb_image *image)
  */
 
 static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
-			    size_t size, struct vmw_dma_buffer **out)
+			    size_t size, struct vmw_buffer_object **out)
 {
-	struct vmw_dma_buffer *vmw_bo;
+	struct vmw_buffer_object *vmw_bo;
 	int ret;
 
 	(void) ttm_write_lock(&vmw_priv->reservation_sem, false);
@@ -404,10 +404,10 @@ static int vmw_fb_create_bo(struct vmw_private *vmw_priv,
 		goto err_unlock;
 	}
 
-	ret = vmw_dmabuf_init(vmw_priv, vmw_bo, size,
+	ret = vmw_bo_init(vmw_priv, vmw_bo, size,
 			      &vmw_sys_placement,
 			      false,
-			      &vmw_dmabuf_bo_free);
+			      &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		goto err_unlock; /* init frees the buffer on failure */
 
@@ -491,7 +491,7 @@ static int vmw_fb_kms_detach(struct vmw_fb_par *par,
 	}
 
 	if (par->vmw_bo && detach_bo && unref_bo)
-		vmw_dmabuf_unreference(&par->vmw_bo);
+		vmw_bo_unreference(&par->vmw_bo);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index c5e8eae0dbe2..5e0c8f775c92 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -377,8 +377,8 @@ int vmw_present_readback_ioctl(struct drm_device *dev, void *data,
 	}
 
 	vfb = vmw_framebuffer_to_vfb(fb);
-	if (!vfb->dmabuf) {
-		DRM_ERROR("Framebuffer not dmabuf backed.\n");
+	if (!vfb->bo) {
+		DRM_ERROR("Framebuffer not buffer backed.\n");
 		ret = -EINVAL;
 		goto out_no_ttm_lock;
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index ef96ba7432ad..7a32be0cef14 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -85,10 +85,10 @@ static int vmw_cursor_update_image(struct vmw_private *dev_priv,
 	return 0;
 }
 
-static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
-				    struct vmw_dma_buffer *dmabuf,
-				    u32 width, u32 height,
-				    u32 hotspotX, u32 hotspotY)
+static int vmw_cursor_update_bo(struct vmw_private *dev_priv,
+				struct vmw_buffer_object *bo,
+				u32 width, u32 height,
+				u32 hotspotX, u32 hotspotY)
 {
 	struct ttm_bo_kmap_obj map;
 	unsigned long kmap_offset;
@@ -100,13 +100,13 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
 	kmap_offset = 0;
 	kmap_num = (width*height*4 + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	ret = ttm_bo_reserve(&dmabuf->base, true, false, NULL);
+	ret = ttm_bo_reserve(&bo->base, true, false, NULL);
 	if (unlikely(ret != 0)) {
 		DRM_ERROR("reserve failed\n");
 		return -EINVAL;
 	}
 
-	ret = ttm_bo_kmap(&dmabuf->base, kmap_offset, kmap_num, &map);
+	ret = ttm_bo_kmap(&bo->base, kmap_offset, kmap_num, &map);
 	if (unlikely(ret != 0))
 		goto err_unreserve;
 
@@ -116,7 +116,7 @@ static int vmw_cursor_update_dmabuf(struct vmw_private *dev_priv,
 
 	ttm_bo_kunmap(&map);
 err_unreserve:
-	ttm_bo_unreserve(&dmabuf->base);
+	ttm_bo_unreserve(&bo->base);
 
 	return ret;
 }
@@ -352,13 +352,13 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
 	if (vps->surf)
 		vmw_surface_unreference(&vps->surf);
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unreference(&vps->dmabuf);
+	if (vps->bo)
+		vmw_bo_unreference(&vps->bo);
 
 	if (fb) {
-		if (vmw_framebuffer_to_vfb(fb)->dmabuf) {
-			vps->dmabuf = vmw_framebuffer_to_vfbd(fb)->buffer;
-			vmw_dmabuf_reference(vps->dmabuf);
+		if (vmw_framebuffer_to_vfb(fb)->bo) {
+			vps->bo = vmw_framebuffer_to_vfbd(fb)->buffer;
+			vmw_bo_reference(vps->bo);
 		} else {
 			vps->surf = vmw_framebuffer_to_vfbs(fb)->surface;
 			vmw_surface_reference(vps->surf);
@@ -390,7 +390,7 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 	}
 
 	du->cursor_surface = vps->surf;
-	du->cursor_dmabuf = vps->dmabuf;
+	du->cursor_bo = vps->bo;
 
 	if (vps->surf) {
 		du->cursor_age = du->cursor_surface->snooper.age;
@@ -399,11 +399,11 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
 					      vps->surf->snooper.image,
 					      64, 64, hotspot_x,
 					      hotspot_y);
-	} else if (vps->dmabuf) {
-		ret = vmw_cursor_update_dmabuf(dev_priv, vps->dmabuf,
-					       plane->state->crtc_w,
-					       plane->state->crtc_h,
-					       hotspot_x, hotspot_y);
+	} else if (vps->bo) {
+		ret = vmw_cursor_update_bo(dev_priv, vps->bo,
+					   plane->state->crtc_w,
+					   plane->state->crtc_h,
+					   hotspot_x, hotspot_y);
 	} else {
 		vmw_cursor_update_position(dev_priv, false, 0, 0);
 		return;
@@ -519,7 +519,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane,
 		ret = -EINVAL;
 	}
 
-	if (!vmw_framebuffer_to_vfb(fb)->dmabuf)
+	if (!vmw_framebuffer_to_vfb(fb)->bo)
 		surface = vmw_framebuffer_to_vfbs(fb)->surface;
 
 	if (surface && !surface->snooper.image) {
@@ -687,8 +687,8 @@ vmw_du_plane_duplicate_state(struct drm_plane *plane)
 	if (vps->surf)
 		(void) vmw_surface_reference(vps->surf);
 
-	if (vps->dmabuf)
-		(void) vmw_dmabuf_reference(vps->dmabuf);
+	if (vps->bo)
+		(void) vmw_bo_reference(vps->bo);
 
 	state = &vps->base;
 
@@ -745,8 +745,8 @@ vmw_du_plane_destroy_state(struct drm_plane *plane,
 	if (vps->surf)
 		vmw_surface_unreference(&vps->surf);
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unreference(&vps->dmabuf);
+	if (vps->bo)
+		vmw_bo_unreference(&vps->bo);
 
 	drm_atomic_helper_plane_destroy_state(plane, state);
 }
@@ -902,12 +902,12 @@ static int vmw_framebuffer_surface_dirty(struct drm_framebuffer *framebuffer,
 
 /**
  * vmw_kms_readback - Perform a readback from the screen system to
- * a dma-buffer backed framebuffer.
+ * a buffer-object backed framebuffer.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm_file identifying the caller.
  * Must be set to NULL if @user_fence_rep is NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @user_fence_rep: User-space provided structure for fence information.
  * Must be set to non-NULL if @file_priv is non-NULL.
  * @vclips: Array of clip rects.
@@ -951,7 +951,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 					   struct vmw_framebuffer **out,
 					   const struct drm_mode_fb_cmd2
 					   *mode_cmd,
-					   bool is_dmabuf_proxy)
+					   bool is_bo_proxy)
 
 {
 	struct drm_device *dev = dev_priv->dev;
@@ -1019,7 +1019,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
 	drm_helper_mode_fill_fb_struct(dev, &vfbs->base.base, mode_cmd);
 	vfbs->surface = vmw_surface_reference(surface);
 	vfbs->base.user_handle = mode_cmd->handles[0];
-	vfbs->is_dmabuf_proxy = is_dmabuf_proxy;
+	vfbs->is_bo_proxy = is_bo_proxy;
 
 	*out = &vfbs->base;
 
@@ -1038,30 +1038,30 @@ out_err1:
 }
 
 /*
- * Dmabuf framebuffer code
+ * Buffer-object framebuffer code
  */
 
-static void vmw_framebuffer_dmabuf_destroy(struct drm_framebuffer *framebuffer)
+static void vmw_framebuffer_bo_destroy(struct drm_framebuffer *framebuffer)
 {
-	struct vmw_framebuffer_dmabuf *vfbd =
+	struct vmw_framebuffer_bo *vfbd =
 		vmw_framebuffer_to_vfbd(framebuffer);
 
 	drm_framebuffer_cleanup(framebuffer);
-	vmw_dmabuf_unreference(&vfbd->buffer);
+	vmw_bo_unreference(&vfbd->buffer);
 	if (vfbd->base.user_obj)
 		ttm_base_object_unref(&vfbd->base.user_obj);
 
 	kfree(vfbd);
 }
 
-static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
-				 struct drm_file *file_priv,
-				 unsigned flags, unsigned color,
-				 struct drm_clip_rect *clips,
-				 unsigned num_clips)
+static int vmw_framebuffer_bo_dirty(struct drm_framebuffer *framebuffer,
+				    struct drm_file *file_priv,
+				    unsigned int flags, unsigned int color,
+				    struct drm_clip_rect *clips,
+				    unsigned int num_clips)
 {
 	struct vmw_private *dev_priv = vmw_priv(framebuffer->dev);
-	struct vmw_framebuffer_dmabuf *vfbd =
+	struct vmw_framebuffer_bo *vfbd =
 		vmw_framebuffer_to_vfbd(framebuffer);
 	struct drm_clip_rect norect;
 	int ret, increment = 1;
@@ -1092,13 +1092,13 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
 				       true, true, NULL);
 		break;
 	case vmw_du_screen_object:
-		ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, &vfbd->base,
-						  clips, NULL, num_clips,
-						  increment, true, NULL, NULL);
+		ret = vmw_kms_sou_do_bo_dirty(dev_priv, &vfbd->base,
+					      clips, NULL, num_clips,
+					      increment, true, NULL, NULL);
 		break;
 	case vmw_du_legacy:
-		ret = vmw_kms_ldu_do_dmabuf_dirty(dev_priv, &vfbd->base, 0, 0,
-						  clips, num_clips, increment);
+		ret = vmw_kms_ldu_do_bo_dirty(dev_priv, &vfbd->base, 0, 0,
+					      clips, num_clips, increment);
 		break;
 	default:
 		ret = -EINVAL;
@@ -1114,23 +1114,23 @@ static int vmw_framebuffer_dmabuf_dirty(struct drm_framebuffer *framebuffer,
 	return ret;
 }
 
-static const struct drm_framebuffer_funcs vmw_framebuffer_dmabuf_funcs = {
-	.destroy = vmw_framebuffer_dmabuf_destroy,
-	.dirty = vmw_framebuffer_dmabuf_dirty,
+static const struct drm_framebuffer_funcs vmw_framebuffer_bo_funcs = {
+	.destroy = vmw_framebuffer_bo_destroy,
+	.dirty = vmw_framebuffer_bo_dirty,
 };
 
 /**
- * Pin the dmabuffer in a location suitable for access by the
+ * Pin the bofer in a location suitable for access by the
  * display system.
  */
 static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 {
 	struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct ttm_placement *placement;
 	int ret;
 
-	buf = vfb->dmabuf ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
 		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup;
 
 	if (!buf)
@@ -1139,12 +1139,12 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 	switch (dev_priv->active_display_unit) {
 	case vmw_du_legacy:
 		vmw_overlay_pause_all(dev_priv);
-		ret = vmw_dmabuf_pin_in_start_of_vram(dev_priv, buf, false);
+		ret = vmw_bo_pin_in_start_of_vram(dev_priv, buf, false);
 		vmw_overlay_resume_all(dev_priv);
 		break;
 	case vmw_du_screen_object:
 	case vmw_du_screen_target:
-		if (vfb->dmabuf) {
+		if (vfb->bo) {
 			if (dev_priv->capabilities & SVGA_CAP_3D) {
 				/*
 				 * Use surface DMA to get content to
@@ -1160,8 +1160,7 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 			placement = &vmw_mob_placement;
 		}
 
-		return vmw_dmabuf_pin_in_placement(dev_priv, buf, placement,
-						   false);
+		return vmw_bo_pin_in_placement(dev_priv, buf, placement, false);
 	default:
 		return -EINVAL;
 	}
@@ -1172,36 +1171,36 @@ static int vmw_framebuffer_pin(struct vmw_framebuffer *vfb)
 static int vmw_framebuffer_unpin(struct vmw_framebuffer *vfb)
 {
 	struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 
-	buf = vfb->dmabuf ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+	buf = vfb->bo ?  vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
 		vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.backup;
 
 	if (WARN_ON(!buf))
 		return 0;
 
-	return vmw_dmabuf_unpin(dev_priv, buf, false);
+	return vmw_bo_unpin(dev_priv, buf, false);
 }
 
 /**
- * vmw_create_dmabuf_proxy - create a proxy surface for the DMA buf
+ * vmw_create_bo_proxy - create a proxy surface for the buffer object
  *
  * @dev: DRM device
  * @mode_cmd: parameters for the new surface
- * @dmabuf_mob: MOB backing the DMA buf
+ * @bo_mob: MOB backing the buffer object
  * @srf_out: newly created surface
  *
- * When the content FB is a DMA buf, we create a surface as a proxy to the
+ * When the content FB is a buffer object, we create a surface as a proxy to the
  * same buffer.  This way we can do a surface copy rather than a surface DMA.
  * This is a more efficient approach
  *
  * RETURNS:
  * 0 on success, error code otherwise
  */
-static int vmw_create_dmabuf_proxy(struct drm_device *dev,
-				   const struct drm_mode_fb_cmd2 *mode_cmd,
-				   struct vmw_dma_buffer *dmabuf_mob,
-				   struct vmw_surface **srf_out)
+static int vmw_create_bo_proxy(struct drm_device *dev,
+			       const struct drm_mode_fb_cmd2 *mode_cmd,
+			       struct vmw_buffer_object *bo_mob,
+			       struct vmw_surface **srf_out)
 {
 	uint32_t format;
 	struct drm_vmw_size content_base_size = {0};
@@ -1258,8 +1257,8 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 	/* Reserve and switch the backing mob. */
 	mutex_lock(&res->dev_priv->cmdbuf_mutex);
 	(void) vmw_resource_reserve(res, false, true);
-	vmw_dmabuf_unreference(&res->backup);
-	res->backup = vmw_dmabuf_reference(dmabuf_mob);
+	vmw_bo_unreference(&res->backup);
+	res->backup = vmw_bo_reference(bo_mob);
 	res->backup_offset = 0;
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
@@ -1269,21 +1268,21 @@ static int vmw_create_dmabuf_proxy(struct drm_device *dev,
 
 
 
-static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv,
-					  struct vmw_dma_buffer *dmabuf,
-					  struct vmw_framebuffer **out,
-					  const struct drm_mode_fb_cmd2
-					  *mode_cmd)
+static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv,
+				      struct vmw_buffer_object *bo,
+				      struct vmw_framebuffer **out,
+				      const struct drm_mode_fb_cmd2
+				      *mode_cmd)
 
 {
 	struct drm_device *dev = dev_priv->dev;
-	struct vmw_framebuffer_dmabuf *vfbd;
+	struct vmw_framebuffer_bo *vfbd;
 	unsigned int requested_size;
 	struct drm_format_name_buf format_name;
 	int ret;
 
 	requested_size = mode_cmd->height * mode_cmd->pitches[0];
-	if (unlikely(requested_size > dmabuf->base.num_pages * PAGE_SIZE)) {
+	if (unlikely(requested_size > bo->base.num_pages * PAGE_SIZE)) {
 		DRM_ERROR("Screen buffer object size is too small "
 			  "for requested mode.\n");
 		return -EINVAL;
@@ -1312,20 +1311,20 @@ static int vmw_kms_new_framebuffer_dmabuf(struct vmw_private *dev_priv,
 	}
 
 	drm_helper_mode_fill_fb_struct(dev, &vfbd->base.base, mode_cmd);
-	vfbd->base.dmabuf = true;
-	vfbd->buffer = vmw_dmabuf_reference(dmabuf);
+	vfbd->base.bo = true;
+	vfbd->buffer = vmw_bo_reference(bo);
 	vfbd->base.user_handle = mode_cmd->handles[0];
 	*out = &vfbd->base;
 
 	ret = drm_framebuffer_init(dev, &vfbd->base.base,
-				   &vmw_framebuffer_dmabuf_funcs);
+				   &vmw_framebuffer_bo_funcs);
 	if (ret)
 		goto out_err2;
 
 	return 0;
 
 out_err2:
-	vmw_dmabuf_unreference(&dmabuf);
+	vmw_bo_unreference(&bo);
 	kfree(vfbd);
 out_err1:
 	return ret;
@@ -1354,57 +1353,57 @@ vmw_kms_srf_ok(struct vmw_private *dev_priv, uint32_t width, uint32_t height)
  * vmw_kms_new_framebuffer - Create a new framebuffer.
  *
  * @dev_priv: Pointer to device private struct.
- * @dmabuf: Pointer to dma buffer to wrap the kms framebuffer around.
- * Either @dmabuf or @surface must be NULL.
+ * @bo: Pointer to buffer object to wrap the kms framebuffer around.
+ * Either @bo or @surface must be NULL.
  * @surface: Pointer to a surface to wrap the kms framebuffer around.
- * Either @dmabuf or @surface must be NULL.
- * @only_2d: No presents will occur to this dma buffer based framebuffer. This
- * Helps the code to do some important optimizations.
+ * Either @bo or @surface must be NULL.
+ * @only_2d: No presents will occur to this buffer object based framebuffer.
+ * This helps the code to do some important optimizations.
  * @mode_cmd: Frame-buffer metadata.
  */
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_dma_buffer *dmabuf,
+			struct vmw_buffer_object *bo,
 			struct vmw_surface *surface,
 			bool only_2d,
 			const struct drm_mode_fb_cmd2 *mode_cmd)
 {
 	struct vmw_framebuffer *vfb = NULL;
-	bool is_dmabuf_proxy = false;
+	bool is_bo_proxy = false;
 	int ret;
 
 	/*
 	 * We cannot use the SurfaceDMA command in an non-accelerated VM,
-	 * therefore, wrap the DMA buf in a surface so we can use the
+	 * therefore, wrap the buffer object in a surface so we can use the
 	 * SurfaceCopy command.
 	 */
 	if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)  &&
-	    dmabuf && only_2d &&
+	    bo && only_2d &&
 	    mode_cmd->width > 64 &&  /* Don't create a proxy for cursor */
 	    dev_priv->active_display_unit == vmw_du_screen_target) {
-		ret = vmw_create_dmabuf_proxy(dev_priv->dev, mode_cmd,
-					      dmabuf, &surface);
+		ret = vmw_create_bo_proxy(dev_priv->dev, mode_cmd,
+					  bo, &surface);
 		if (ret)
 			return ERR_PTR(ret);
 
-		is_dmabuf_proxy = true;
+		is_bo_proxy = true;
 	}
 
 	/* Create the new framebuffer depending one what we have */
 	if (surface) {
 		ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb,
 						      mode_cmd,
-						      is_dmabuf_proxy);
+						      is_bo_proxy);
 
 		/*
-		 * vmw_create_dmabuf_proxy() adds a reference that is no longer
+		 * vmw_create_bo_proxy() adds a reference that is no longer
 		 * needed
 		 */
-		if (is_dmabuf_proxy)
+		if (is_bo_proxy)
 			vmw_surface_unreference(&surface);
-	} else if (dmabuf) {
-		ret = vmw_kms_new_framebuffer_dmabuf(dev_priv, dmabuf, &vfb,
-						     mode_cmd);
+	} else if (bo) {
+		ret = vmw_kms_new_framebuffer_bo(dev_priv, bo, &vfb,
+						 mode_cmd);
 	} else {
 		BUG();
 	}
@@ -1430,7 +1429,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	struct vmw_framebuffer *vfb = NULL;
 	struct vmw_surface *surface = NULL;
-	struct vmw_dma_buffer *bo = NULL;
+	struct vmw_buffer_object *bo = NULL;
 	struct ttm_base_object *user_obj;
 	int ret;
 
@@ -1466,7 +1465,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	 * End conditioned code.
 	 */
 
-	/* returns either a dmabuf or surface */
+	/* returns either a bo or surface */
 	ret = vmw_user_lookup_handle(dev_priv, tfile,
 				     mode_cmd->handles[0],
 				     &surface, &bo);
@@ -1494,7 +1493,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 err_out:
 	/* vmw_user_lookup_handle takes one ref so does new_fb */
 	if (bo)
-		vmw_dmabuf_unreference(&bo);
+		vmw_bo_unreference(&bo);
 	if (surface)
 		vmw_surface_unreference(&surface);
 
@@ -2427,7 +2426,7 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
  * interrupted by a signal.
  */
 int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  bool interruptible,
 				  bool validate_as_mob,
 				  bool for_cpu_blit)
@@ -2459,7 +2458,7 @@ int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
  * Helper to be used if an error forces the caller to undo the actions of
  * vmw_kms_helper_buffer_prepare.
  */
-void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf)
+void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf)
 {
 	if (buf)
 		ttm_bo_unreserve(&buf->base);
@@ -2482,7 +2481,7 @@ void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf)
  */
 void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 				  struct drm_file *file_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  struct vmw_fence_obj **out_fence,
 				  struct drm_vmw_fence_rep __user *
 				  user_fence_rep)
@@ -2522,7 +2521,7 @@ void vmw_kms_helper_resource_revert(struct vmw_validation_ctx *ctx)
 	struct vmw_resource *res = ctx->res;
 
 	vmw_kms_helper_buffer_revert(ctx->buf);
-	vmw_dmabuf_unreference(&ctx->buf);
+	vmw_bo_unreference(&ctx->buf);
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 }
@@ -2567,7 +2566,7 @@ int vmw_kms_helper_resource_prepare(struct vmw_resource *res,
 		if (ret)
 			goto out_unreserve;
 
-		ctx->buf = vmw_dmabuf_reference(res->backup);
+		ctx->buf = vmw_bo_reference(res->backup);
 	}
 	ret = vmw_resource_validate(res);
 	if (ret)
@@ -2600,7 +2599,7 @@ void vmw_kms_helper_resource_finish(struct vmw_validation_ctx *ctx,
 		vmw_kms_helper_buffer_finish(res->dev_priv, NULL, ctx->buf,
 					     out_fence, NULL);
 
-	vmw_dmabuf_unreference(&ctx->buf);
+	vmw_bo_unreference(&ctx->buf);
 	vmw_resource_unreserve(res, false, NULL, 0);
 	mutex_unlock(&res->dev_priv->cmdbuf_mutex);
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index 6b7c012719f1..ff1caed38f94 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -90,7 +90,7 @@ struct vmw_kms_dirty {
 #define vmw_framebuffer_to_vfbs(x) \
 	container_of(x, struct vmw_framebuffer_surface, base.base)
 #define vmw_framebuffer_to_vfbd(x) \
-	container_of(x, struct vmw_framebuffer_dmabuf, base.base)
+	container_of(x, struct vmw_framebuffer_bo, base.base)
 
 /**
  * Base class for framebuffers
@@ -102,7 +102,7 @@ struct vmw_framebuffer {
 	struct drm_framebuffer base;
 	int (*pin)(struct vmw_framebuffer *fb);
 	int (*unpin)(struct vmw_framebuffer *fb);
-	bool dmabuf;
+	bool bo;
 	struct ttm_base_object *user_obj;
 	uint32_t user_handle;
 };
@@ -117,15 +117,15 @@ struct vmw_clip_rect {
 struct vmw_framebuffer_surface {
 	struct vmw_framebuffer base;
 	struct vmw_surface *surface;
-	struct vmw_dma_buffer *buffer;
+	struct vmw_buffer_object *buffer;
 	struct list_head head;
-	bool is_dmabuf_proxy;  /* true if this is proxy surface for DMA buf */
+	bool is_bo_proxy;  /* true if this is proxy surface for DMA buf */
 };
 
 
-struct vmw_framebuffer_dmabuf {
+struct vmw_framebuffer_bo {
 	struct vmw_framebuffer base;
-	struct vmw_dma_buffer *buffer;
+	struct vmw_buffer_object *buffer;
 };
 
 
@@ -161,18 +161,18 @@ struct vmw_crtc_state {
  *
  * @base DRM plane object
  * @surf Display surface for STDU
- * @dmabuf display dmabuf for SOU
+ * @bo display bo for SOU
  * @content_fb_type Used by STDU.
- * @dmabuf_size Size of the dmabuf, used by Screen Object Display Unit
+ * @bo_size Size of the bo, used by Screen Object Display Unit
  * @pinned pin count for STDU display surface
  */
 struct vmw_plane_state {
 	struct drm_plane_state base;
 	struct vmw_surface *surf;
-	struct vmw_dma_buffer *dmabuf;
+	struct vmw_buffer_object *bo;
 
 	int content_fb_type;
-	unsigned long dmabuf_size;
+	unsigned long bo_size;
 
 	int pinned;
 
@@ -209,7 +209,7 @@ struct vmw_display_unit {
 	struct drm_plane cursor;
 
 	struct vmw_surface *cursor_surface;
-	struct vmw_dma_buffer *cursor_dmabuf;
+	struct vmw_buffer_object *cursor_bo;
 	size_t cursor_age;
 
 	int cursor_x;
@@ -243,7 +243,7 @@ struct vmw_display_unit {
 
 struct vmw_validation_ctx {
 	struct vmw_resource *res;
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 };
 
 #define vmw_crtc_to_du(x) \
@@ -291,14 +291,14 @@ int vmw_kms_helper_dirty(struct vmw_private *dev_priv,
 			 struct vmw_kms_dirty *dirty);
 
 int vmw_kms_helper_buffer_prepare(struct vmw_private *dev_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  bool interruptible,
 				  bool validate_as_mob,
 				  bool for_cpu_blit);
-void vmw_kms_helper_buffer_revert(struct vmw_dma_buffer *buf);
+void vmw_kms_helper_buffer_revert(struct vmw_buffer_object *buf);
 void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 				  struct drm_file *file_priv,
-				  struct vmw_dma_buffer *buf,
+				  struct vmw_buffer_object *buf,
 				  struct vmw_fence_obj **out_fence,
 				  struct drm_vmw_fence_rep __user *
 				  user_fence_rep);
@@ -316,7 +316,7 @@ int vmw_kms_readback(struct vmw_private *dev_priv,
 		     uint32_t num_clips);
 struct vmw_framebuffer *
 vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
-			struct vmw_dma_buffer *dmabuf,
+			struct vmw_buffer_object *bo,
 			struct vmw_surface *surface,
 			bool only_2d,
 			const struct drm_mode_fb_cmd2 *mode_cmd);
@@ -384,11 +384,11 @@ void vmw_du_connector_destroy_state(struct drm_connector *connector,
  */
 int vmw_kms_ldu_init_display(struct vmw_private *dev_priv);
 int vmw_kms_ldu_close_display(struct vmw_private *dev_priv);
-int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				unsigned flags, unsigned color,
-				struct drm_clip_rect *clips,
-				unsigned num_clips, int increment);
+int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    unsigned int flags, unsigned int color,
+			    struct drm_clip_rect *clips,
+			    unsigned int num_clips, int increment);
 int vmw_kms_update_proxy(struct vmw_resource *res,
 			 const struct drm_clip_rect *clips,
 			 unsigned num_clips,
@@ -408,14 +408,14 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
 				 unsigned num_clips, int inc,
 				 struct vmw_fence_obj **out_fence,
 				 struct drm_crtc *crtc);
-int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				struct drm_clip_rect *clips,
-				struct drm_vmw_rect *vclips,
-				unsigned num_clips, int increment,
-				bool interruptible,
-				struct vmw_fence_obj **out_fence,
-				struct drm_crtc *crtc);
+int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    struct drm_clip_rect *clips,
+			    struct drm_vmw_rect *vclips,
+			    unsigned int num_clips, int increment,
+			    bool interruptible,
+			    struct vmw_fence_obj **out_fence,
+			    struct drm_crtc *crtc);
 int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 			 struct drm_file *file_priv,
 			 struct vmw_framebuffer *vfb,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index 4a5907e3f560..a2dd9a829219 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -547,11 +547,11 @@ int vmw_kms_ldu_close_display(struct vmw_private *dev_priv)
 }
 
 
-int vmw_kms_ldu_do_dmabuf_dirty(struct vmw_private *dev_priv,
-				struct vmw_framebuffer *framebuffer,
-				unsigned flags, unsigned color,
-				struct drm_clip_rect *clips,
-				unsigned num_clips, int increment)
+int vmw_kms_ldu_do_bo_dirty(struct vmw_private *dev_priv,
+			    struct vmw_framebuffer *framebuffer,
+			    unsigned int flags, unsigned int color,
+			    struct drm_clip_rect *clips,
+			    unsigned int num_clips, int increment)
 {
 	size_t fifo_size;
 	int i;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
index 222c9c2123a1..09420ef19ecb 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -38,7 +38,7 @@
 #define VMW_OVERLAY_CAP_MASK (SVGA_FIFO_CAP_VIDEO | SVGA_FIFO_CAP_ESCAPE)
 
 struct vmw_stream {
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	bool claimed;
 	bool paused;
 	struct drm_vmw_control_stream_arg saved;
@@ -94,7 +94,7 @@ static inline void fill_flush(struct vmw_escape_video_flush *cmd,
  * -ERESTARTSYS if interrupted by a signal.
  */
 static int vmw_overlay_send_put(struct vmw_private *dev_priv,
-				struct vmw_dma_buffer *buf,
+				struct vmw_buffer_object *buf,
 				struct drm_vmw_control_stream_arg *arg,
 				bool interruptible)
 {
@@ -225,16 +225,16 @@ static int vmw_overlay_send_stop(struct vmw_private *dev_priv,
  * used with GMRs instead of being locked to vram.
  */
 static int vmw_overlay_move_buffer(struct vmw_private *dev_priv,
-				   struct vmw_dma_buffer *buf,
+				   struct vmw_buffer_object *buf,
 				   bool pin, bool inter)
 {
 	if (!pin)
-		return vmw_dmabuf_unpin(dev_priv, buf, inter);
+		return vmw_bo_unpin(dev_priv, buf, inter);
 
 	if (dev_priv->active_display_unit == vmw_du_legacy)
-		return vmw_dmabuf_pin_in_vram(dev_priv, buf, inter);
+		return vmw_bo_pin_in_vram(dev_priv, buf, inter);
 
-	return vmw_dmabuf_pin_in_vram_or_gmr(dev_priv, buf, inter);
+	return vmw_bo_pin_in_vram_or_gmr(dev_priv, buf, inter);
 }
 
 /**
@@ -278,7 +278,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv,
 	}
 
 	if (!pause) {
-		vmw_dmabuf_unreference(&stream->buf);
+		vmw_bo_unreference(&stream->buf);
 		stream->paused = false;
 	} else {
 		stream->paused = true;
@@ -297,7 +297,7 @@ static int vmw_overlay_stop(struct vmw_private *dev_priv,
  * -ERESTARTSYS if interrupted.
  */
 static int vmw_overlay_update_stream(struct vmw_private *dev_priv,
-				     struct vmw_dma_buffer *buf,
+				     struct vmw_buffer_object *buf,
 				     struct drm_vmw_control_stream_arg *arg,
 				     bool interruptible)
 {
@@ -347,7 +347,7 @@ static int vmw_overlay_update_stream(struct vmw_private *dev_priv,
 	}
 
 	if (stream->buf != buf)
-		stream->buf = vmw_dmabuf_reference(buf);
+		stream->buf = vmw_bo_reference(buf);
 	stream->saved = *arg;
 	/* stream is no longer stopped/paused */
 	stream->paused = false;
@@ -466,7 +466,7 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 	struct vmw_overlay *overlay = dev_priv->overlay_priv;
 	struct drm_vmw_control_stream_arg *arg =
 	    (struct drm_vmw_control_stream_arg *)data;
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct vmw_resource *res;
 	int ret;
 
@@ -484,13 +484,13 @@ int vmw_overlay_ioctl(struct drm_device *dev, void *data,
 		goto out_unlock;
 	}
 
-	ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &buf, NULL);
+	ret = vmw_user_bo_lookup(tfile, arg->handle, &buf, NULL);
 	if (ret)
 		goto out_unlock;
 
 	ret = vmw_overlay_update_stream(dev_priv, buf, arg, true);
 
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 
 out_unlock:
 	mutex_unlock(&overlay->mutex);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 6b3a942b18df..5aaf9ac65cba 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -35,9 +35,9 @@
 
 #define VMW_RES_EVICT_ERR_COUNT 10
 
-struct vmw_user_dma_buffer {
+struct vmw_user_buffer_object {
 	struct ttm_prime_object prime;
-	struct vmw_dma_buffer dma;
+	struct vmw_buffer_object vbo;
 };
 
 struct vmw_bo_user_rep {
@@ -45,17 +45,18 @@ struct vmw_bo_user_rep {
 	uint64_t map_handle;
 };
 
-static inline struct vmw_dma_buffer *
-vmw_dma_buffer(struct ttm_buffer_object *bo)
+static inline struct vmw_buffer_object *
+vmw_buffer_object(struct ttm_buffer_object *bo)
 {
-	return container_of(bo, struct vmw_dma_buffer, base);
+	return container_of(bo, struct vmw_buffer_object, base);
 }
 
-static inline struct vmw_user_dma_buffer *
-vmw_user_dma_buffer(struct ttm_buffer_object *bo)
+static inline struct vmw_user_buffer_object *
+vmw_user_buffer_object(struct ttm_buffer_object *bo)
 {
-	struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo);
-	return container_of(vmw_bo, struct vmw_user_dma_buffer, dma);
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	return container_of(vmw_bo, struct vmw_user_buffer_object, vbo);
 }
 
 struct vmw_resource *vmw_resource_reference(struct vmw_resource *res)
@@ -116,7 +117,7 @@ static void vmw_resource_release(struct kref *kref)
 		res->backup_dirty = false;
 		list_del_init(&res->mob_head);
 		ttm_bo_unreserve(bo);
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 	}
 
 	if (likely(res->hw_destroy != NULL)) {
@@ -287,7 +288,7 @@ out_bad_resource:
 }
 
 /**
- * Helper function that looks either a surface or dmabuf.
+ * Helper function that looks either a surface or bo.
  *
  * The pointer this pointed at by out_surf and out_buf needs to be null.
  */
@@ -295,7 +296,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 			   struct ttm_object_file *tfile,
 			   uint32_t handle,
 			   struct vmw_surface **out_surf,
-			   struct vmw_dma_buffer **out_buf)
+			   struct vmw_buffer_object **out_buf)
 {
 	struct vmw_resource *res;
 	int ret;
@@ -311,7 +312,7 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 	}
 
 	*out_surf = NULL;
-	ret = vmw_user_dmabuf_lookup(tfile, handle, out_buf, NULL);
+	ret = vmw_user_bo_lookup(tfile, handle, out_buf, NULL);
 	return ret;
 }
 
@@ -320,14 +321,14 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
  */
 
 /**
- * vmw_dmabuf_acc_size - Calculate the pinned memory usage of buffers
+ * vmw_bo_acc_size - Calculate the pinned memory usage of buffers
  *
  * @dev_priv: Pointer to a struct vmw_private identifying the device.
  * @size: The requested buffer size.
  * @user: Whether this is an ordinary dma buffer or a user dma buffer.
  */
-static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size,
-				  bool user)
+static size_t vmw_bo_acc_size(struct vmw_private *dev_priv, size_t size,
+			      bool user)
 {
 	static size_t struct_size, user_struct_size;
 	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
@@ -337,9 +338,9 @@ static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size,
 		size_t backend_size = ttm_round_pot(vmw_tt_size);
 
 		struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_dma_buffer));
+			ttm_round_pot(sizeof(struct vmw_buffer_object));
 		user_struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_user_dma_buffer));
+			ttm_round_pot(sizeof(struct vmw_user_buffer_object));
 	}
 
 	if (dev_priv->map_mode == vmw_dma_alloc_coherent)
@@ -350,36 +351,36 @@ static size_t vmw_dmabuf_acc_size(struct vmw_private *dev_priv, size_t size,
 		page_array_size;
 }
 
-void vmw_dmabuf_bo_free(struct ttm_buffer_object *bo)
+void vmw_bo_bo_free(struct ttm_buffer_object *bo)
 {
-	struct vmw_dma_buffer *vmw_bo = vmw_dma_buffer(bo);
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
 
-	vmw_dma_buffer_unmap(vmw_bo);
+	vmw_buffer_object_unmap(vmw_bo);
 	kfree(vmw_bo);
 }
 
-static void vmw_user_dmabuf_destroy(struct ttm_buffer_object *bo)
+static void vmw_user_bo_destroy(struct ttm_buffer_object *bo)
 {
-	struct vmw_user_dma_buffer *vmw_user_bo = vmw_user_dma_buffer(bo);
+	struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo);
 
-	vmw_dma_buffer_unmap(&vmw_user_bo->dma);
+	vmw_buffer_object_unmap(&vmw_user_bo->vbo);
 	ttm_prime_object_kfree(vmw_user_bo, prime);
 }
 
-int vmw_dmabuf_init(struct vmw_private *dev_priv,
-		    struct vmw_dma_buffer *vmw_bo,
-		    size_t size, struct ttm_placement *placement,
-		    bool interruptible,
-		    void (*bo_free) (struct ttm_buffer_object *bo))
+int vmw_bo_init(struct vmw_private *dev_priv,
+		struct vmw_buffer_object *vmw_bo,
+		size_t size, struct ttm_placement *placement,
+		bool interruptible,
+		void (*bo_free)(struct ttm_buffer_object *bo))
 {
 	struct ttm_bo_device *bdev = &dev_priv->bdev;
 	size_t acc_size;
 	int ret;
-	bool user = (bo_free == &vmw_user_dmabuf_destroy);
+	bool user = (bo_free == &vmw_user_bo_destroy);
 
-	BUG_ON(!bo_free && (!user && (bo_free != vmw_dmabuf_bo_free)));
+	WARN_ON_ONCE(!bo_free && (!user && (bo_free != vmw_bo_bo_free)));
 
-	acc_size = vmw_dmabuf_acc_size(dev_priv, size, user);
+	acc_size = vmw_bo_acc_size(dev_priv, size, user);
 	memset(vmw_bo, 0, sizeof(*vmw_bo));
 
 	INIT_LIST_HEAD(&vmw_bo->res_list);
@@ -391,9 +392,9 @@ int vmw_dmabuf_init(struct vmw_private *dev_priv,
 	return ret;
 }
 
-static void vmw_user_dmabuf_release(struct ttm_base_object **p_base)
+static void vmw_user_bo_release(struct ttm_base_object **p_base)
 {
-	struct vmw_user_dma_buffer *vmw_user_bo;
+	struct vmw_user_buffer_object *vmw_user_bo;
 	struct ttm_base_object *base = *p_base;
 	struct ttm_buffer_object *bo;
 
@@ -402,21 +403,22 @@ static void vmw_user_dmabuf_release(struct ttm_base_object **p_base)
 	if (unlikely(base == NULL))
 		return;
 
-	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
 				   prime.base);
-	bo = &vmw_user_bo->dma.base;
+	bo = &vmw_user_bo->vbo.base;
 	ttm_bo_unref(&bo);
 }
 
-static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base,
-					    enum ttm_ref_type ref_type)
+static void vmw_user_bo_ref_obj_release(struct ttm_base_object *base,
+					enum ttm_ref_type ref_type)
 {
-	struct vmw_user_dma_buffer *user_bo;
-	user_bo = container_of(base, struct vmw_user_dma_buffer, prime.base);
+	struct vmw_user_buffer_object *user_bo;
+
+	user_bo = container_of(base, struct vmw_user_buffer_object, prime.base);
 
 	switch (ref_type) {
 	case TTM_REF_SYNCCPU_WRITE:
-		ttm_bo_synccpu_write_release(&user_bo->dma.base);
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
 		break;
 	default:
 		BUG();
@@ -424,7 +426,7 @@ static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base,
 }
 
 /**
- * vmw_user_dmabuf_alloc - Allocate a user dma buffer
+ * vmw_user_bo_alloc - Allocate a user dma buffer
  *
  * @dev_priv: Pointer to a struct device private.
  * @tfile: Pointer to a struct ttm_object_file on which to register the user
@@ -432,18 +434,18 @@ static void vmw_user_dmabuf_ref_obj_release(struct ttm_base_object *base,
  * @size: Size of the dma buffer.
  * @shareable: Boolean whether the buffer is shareable with other open files.
  * @handle: Pointer to where the handle value should be assigned.
- * @p_dma_buf: Pointer to where the refcounted struct vmw_dma_buffer pointer
+ * @p_vbo: Pointer to where the refcounted struct vmw_buffer_object pointer
  * should be assigned.
  */
-int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
-			  struct ttm_object_file *tfile,
-			  uint32_t size,
-			  bool shareable,
-			  uint32_t *handle,
-			  struct vmw_dma_buffer **p_dma_buf,
-			  struct ttm_base_object **p_base)
+int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+		      struct ttm_object_file *tfile,
+		      uint32_t size,
+		      bool shareable,
+		      uint32_t *handle,
+		      struct vmw_buffer_object **p_vbo,
+		      struct ttm_base_object **p_base)
 {
-	struct vmw_user_dma_buffer *user_bo;
+	struct vmw_user_buffer_object *user_bo;
 	struct ttm_buffer_object *tmp;
 	int ret;
 
@@ -453,28 +455,28 @@ int vmw_user_dmabuf_alloc(struct vmw_private *dev_priv,
 		return -ENOMEM;
 	}
 
-	ret = vmw_dmabuf_init(dev_priv, &user_bo->dma, size,
-			      (dev_priv->has_mob) ?
-			      &vmw_sys_placement :
-			      &vmw_vram_sys_placement, true,
-			      &vmw_user_dmabuf_destroy);
+	ret = vmw_bo_init(dev_priv, &user_bo->vbo, size,
+			  (dev_priv->has_mob) ?
+			  &vmw_sys_placement :
+			  &vmw_vram_sys_placement, true,
+			  &vmw_user_bo_destroy);
 	if (unlikely(ret != 0))
 		return ret;
 
-	tmp = ttm_bo_reference(&user_bo->dma.base);
+	tmp = ttm_bo_reference(&user_bo->vbo.base);
 	ret = ttm_prime_object_init(tfile,
 				    size,
 				    &user_bo->prime,
 				    shareable,
 				    ttm_buffer_type,
-				    &vmw_user_dmabuf_release,
-				    &vmw_user_dmabuf_ref_obj_release);
+				    &vmw_user_bo_release,
+				    &vmw_user_bo_ref_obj_release);
 	if (unlikely(ret != 0)) {
 		ttm_bo_unref(&tmp);
 		goto out_no_base_object;
 	}
 
-	*p_dma_buf = &user_bo->dma;
+	*p_vbo = &user_bo->vbo;
 	if (p_base) {
 		*p_base = &user_bo->prime.base;
 		kref_get(&(*p_base)->refcount);
@@ -486,21 +488,21 @@ out_no_base_object:
 }
 
 /**
- * vmw_user_dmabuf_verify_access - verify access permissions on this
+ * vmw_user_bo_verify_access - verify access permissions on this
  * buffer object.
  *
  * @bo: Pointer to the buffer object being accessed
  * @tfile: Identifying the caller.
  */
-int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
+int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
 				  struct ttm_object_file *tfile)
 {
-	struct vmw_user_dma_buffer *vmw_user_bo;
+	struct vmw_user_buffer_object *vmw_user_bo;
 
-	if (unlikely(bo->destroy != vmw_user_dmabuf_destroy))
+	if (unlikely(bo->destroy != vmw_user_bo_destroy))
 		return -EPERM;
 
-	vmw_user_bo = vmw_user_dma_buffer(bo);
+	vmw_user_bo = vmw_user_buffer_object(bo);
 
 	/* Check that the caller has opened the object. */
 	if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base)))
@@ -511,7 +513,7 @@ int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
 }
 
 /**
- * vmw_user_dmabuf_synccpu_grab - Grab a struct vmw_user_dma_buffer for cpu
+ * vmw_user_bo_synccpu_grab - Grab a struct vmw_user_buffer_object for cpu
  * access, idling previous GPU operations on the buffer and optionally
  * blocking it for further command submissions.
  *
@@ -521,11 +523,11 @@ int vmw_user_dmabuf_verify_access(struct ttm_buffer_object *bo,
  *
  * A blocking grab will be automatically released when @tfile is closed.
  */
-static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
+static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo,
 					struct ttm_object_file *tfile,
 					uint32_t flags)
 {
-	struct ttm_buffer_object *bo = &user_bo->dma.base;
+	struct ttm_buffer_object *bo = &user_bo->vbo.base;
 	bool existed;
 	int ret;
 
@@ -550,20 +552,20 @@ static int vmw_user_dmabuf_synccpu_grab(struct vmw_user_dma_buffer *user_bo,
 	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
 				 TTM_REF_SYNCCPU_WRITE, &existed, false);
 	if (ret != 0 || existed)
-		ttm_bo_synccpu_write_release(&user_bo->dma.base);
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
 
 	return ret;
 }
 
 /**
- * vmw_user_dmabuf_synccpu_release - Release a previous grab for CPU access,
+ * vmw_user_bo_synccpu_release - Release a previous grab for CPU access,
  * and unblock command submission on the buffer if blocked.
  *
  * @handle: Handle identifying the buffer object.
  * @tfile: Identifying the caller.
  * @flags: Flags indicating the type of release.
  */
-static int vmw_user_dmabuf_synccpu_release(uint32_t handle,
+static int vmw_user_bo_synccpu_release(uint32_t handle,
 					   struct ttm_object_file *tfile,
 					   uint32_t flags)
 {
@@ -575,7 +577,7 @@ static int vmw_user_dmabuf_synccpu_release(uint32_t handle,
 }
 
 /**
- * vmw_user_dmabuf_synccpu_release - ioctl function implementing the synccpu
+ * vmw_user_bo_synccpu_release - ioctl function implementing the synccpu
  * functionality.
  *
  * @dev: Identifies the drm device.
@@ -585,13 +587,13 @@ static int vmw_user_dmabuf_synccpu_release(uint32_t handle,
  * This function checks the ioctl arguments for validity and calls the
  * relevant synccpu functions.
  */
-int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
+int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv)
 {
 	struct drm_vmw_synccpu_arg *arg =
 		(struct drm_vmw_synccpu_arg *) data;
-	struct vmw_dma_buffer *dma_buf;
-	struct vmw_user_dma_buffer *user_bo;
+	struct vmw_buffer_object *vbo;
+	struct vmw_user_buffer_object *user_bo;
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
 	struct ttm_base_object *buffer_base;
 	int ret;
@@ -606,15 +608,15 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 
 	switch (arg->op) {
 	case drm_vmw_synccpu_grab:
-		ret = vmw_user_dmabuf_lookup(tfile, arg->handle, &dma_buf,
+		ret = vmw_user_bo_lookup(tfile, arg->handle, &vbo,
 					     &buffer_base);
 		if (unlikely(ret != 0))
 			return ret;
 
-		user_bo = container_of(dma_buf, struct vmw_user_dma_buffer,
-				       dma);
-		ret = vmw_user_dmabuf_synccpu_grab(user_bo, tfile, arg->flags);
-		vmw_dmabuf_unreference(&dma_buf);
+		user_bo = container_of(vbo, struct vmw_user_buffer_object,
+				       vbo);
+		ret = vmw_user_bo_synccpu_grab(user_bo, tfile, arg->flags);
+		vmw_bo_unreference(&vbo);
 		ttm_base_object_unref(&buffer_base);
 		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
 			     ret != -EBUSY)) {
@@ -624,8 +626,8 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 		}
 		break;
 	case drm_vmw_synccpu_release:
-		ret = vmw_user_dmabuf_synccpu_release(arg->handle, tfile,
-						      arg->flags);
+		ret = vmw_user_bo_synccpu_release(arg->handle, tfile,
+						  arg->flags);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
 				  (unsigned int) arg->handle);
@@ -640,15 +642,15 @@ int vmw_user_dmabuf_synccpu_ioctl(struct drm_device *dev, void *data,
 	return 0;
 }
 
-int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv)
+int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	union drm_vmw_alloc_dmabuf_arg *arg =
 	    (union drm_vmw_alloc_dmabuf_arg *)data;
 	struct drm_vmw_alloc_dmabuf_req *req = &arg->req;
 	struct drm_vmw_dmabuf_rep *rep = &arg->rep;
-	struct vmw_dma_buffer *dma_buf;
+	struct vmw_buffer_object *vbo;
 	uint32_t handle;
 	int ret;
 
@@ -656,27 +658,27 @@ int vmw_dmabuf_alloc_ioctl(struct drm_device *dev, void *data,
 	if (unlikely(ret != 0))
 		return ret;
 
-	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    req->size, false, &handle, &dma_buf,
-				    NULL);
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+				req->size, false, &handle, &vbo,
+				NULL);
 	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
+		goto out_no_bo;
 
 	rep->handle = handle;
-	rep->map_handle = drm_vma_node_offset_addr(&dma_buf->base.vma_node);
+	rep->map_handle = drm_vma_node_offset_addr(&vbo->base.vma_node);
 	rep->cur_gmr_id = handle;
 	rep->cur_gmr_offset = 0;
 
-	vmw_dmabuf_unreference(&dma_buf);
+	vmw_bo_unreference(&vbo);
 
-out_no_dmabuf:
+out_no_bo:
 	ttm_read_unlock(&dev_priv->reservation_sem);
 
 	return ret;
 }
 
-int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
-			   struct drm_file *file_priv)
+int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
 {
 	struct drm_vmw_unref_dmabuf_arg *arg =
 	    (struct drm_vmw_unref_dmabuf_arg *)data;
@@ -686,11 +688,11 @@ int vmw_dmabuf_unref_ioctl(struct drm_device *dev, void *data,
 					 TTM_REF_USAGE);
 }
 
-int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
-			   uint32_t handle, struct vmw_dma_buffer **out,
+int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+			   uint32_t handle, struct vmw_buffer_object **out,
 			   struct ttm_base_object **p_base)
 {
-	struct vmw_user_dma_buffer *vmw_user_bo;
+	struct vmw_user_buffer_object *vmw_user_bo;
 	struct ttm_base_object *base;
 
 	base = ttm_base_object_lookup(tfile, handle);
@@ -707,28 +709,28 @@ int vmw_user_dmabuf_lookup(struct ttm_object_file *tfile,
 		return -EINVAL;
 	}
 
-	vmw_user_bo = container_of(base, struct vmw_user_dma_buffer,
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
 				   prime.base);
-	(void)ttm_bo_reference(&vmw_user_bo->dma.base);
+	(void)ttm_bo_reference(&vmw_user_bo->vbo.base);
 	if (p_base)
 		*p_base = base;
 	else
 		ttm_base_object_unref(&base);
-	*out = &vmw_user_bo->dma;
+	*out = &vmw_user_bo->vbo;
 
 	return 0;
 }
 
-int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
-			      struct vmw_dma_buffer *dma_buf,
+int vmw_user_bo_reference(struct ttm_object_file *tfile,
+			      struct vmw_buffer_object *vbo,
 			      uint32_t *handle)
 {
-	struct vmw_user_dma_buffer *user_bo;
+	struct vmw_user_buffer_object *user_bo;
 
-	if (dma_buf->base.destroy != vmw_user_dmabuf_destroy)
+	if (vbo->base.destroy != vmw_user_bo_destroy)
 		return -EINVAL;
 
-	user_bo = container_of(dma_buf, struct vmw_user_dma_buffer, dma);
+	user_bo = container_of(vbo, struct vmw_user_buffer_object, vbo);
 
 	*handle = user_bo->prime.base.hash.key;
 	return ttm_ref_object_add(tfile, &user_bo->prime.base,
@@ -743,7 +745,7 @@ int vmw_user_dmabuf_reference(struct ttm_object_file *tfile,
  * @args: Pointer to a struct drm_mode_create_dumb structure
  *
  * This is a driver callback for the core drm create_dumb functionality.
- * Note that this is very similar to the vmw_dmabuf_alloc ioctl, except
+ * Note that this is very similar to the vmw_bo_alloc ioctl, except
  * that the arguments have a different format.
  */
 int vmw_dumb_create(struct drm_file *file_priv,
@@ -751,7 +753,7 @@ int vmw_dumb_create(struct drm_file *file_priv,
 		    struct drm_mode_create_dumb *args)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_dma_buffer *dma_buf;
+	struct vmw_buffer_object *vbo;
 	int ret;
 
 	args->pitch = args->width * ((args->bpp + 7) / 8);
@@ -761,14 +763,14 @@ int vmw_dumb_create(struct drm_file *file_priv,
 	if (unlikely(ret != 0))
 		return ret;
 
-	ret = vmw_user_dmabuf_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
 				    args->size, false, &args->handle,
-				    &dma_buf, NULL);
+				    &vbo, NULL);
 	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
+		goto out_no_bo;
 
-	vmw_dmabuf_unreference(&dma_buf);
-out_no_dmabuf:
+	vmw_bo_unreference(&vbo);
+out_no_bo:
 	ttm_read_unlock(&dev_priv->reservation_sem);
 	return ret;
 }
@@ -788,15 +790,15 @@ int vmw_dumb_map_offset(struct drm_file *file_priv,
 			uint64_t *offset)
 {
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_dma_buffer *out_buf;
+	struct vmw_buffer_object *out_buf;
 	int ret;
 
-	ret = vmw_user_dmabuf_lookup(tfile, handle, &out_buf, NULL);
+	ret = vmw_user_bo_lookup(tfile, handle, &out_buf, NULL);
 	if (ret != 0)
 		return -EINVAL;
 
 	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
-	vmw_dmabuf_unreference(&out_buf);
+	vmw_bo_unreference(&out_buf);
 	return 0;
 }
 
@@ -829,7 +831,7 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res,
 {
 	unsigned long size =
 		(res->backup_size + PAGE_SIZE - 1) & PAGE_MASK;
-	struct vmw_dma_buffer *backup;
+	struct vmw_buffer_object *backup;
 	int ret;
 
 	if (likely(res->backup)) {
@@ -841,16 +843,16 @@ static int vmw_resource_buf_alloc(struct vmw_resource *res,
 	if (unlikely(!backup))
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(res->dev_priv, backup, res->backup_size,
+	ret = vmw_bo_init(res->dev_priv, backup, res->backup_size,
 			      res->func->backup_placement,
 			      interruptible,
-			      &vmw_dmabuf_bo_free);
+			      &vmw_bo_bo_free);
 	if (unlikely(ret != 0))
-		goto out_no_dmabuf;
+		goto out_no_bo;
 
 	res->backup = backup;
 
-out_no_dmabuf:
+out_no_bo:
 	return ret;
 }
 
@@ -919,7 +921,7 @@ out_bind_failed:
  */
 void vmw_resource_unreserve(struct vmw_resource *res,
 			    bool switch_backup,
-			    struct vmw_dma_buffer *new_backup,
+			    struct vmw_buffer_object *new_backup,
 			    unsigned long new_backup_offset)
 {
 	struct vmw_private *dev_priv = res->dev_priv;
@@ -931,11 +933,11 @@ void vmw_resource_unreserve(struct vmw_resource *res,
 		if (res->backup) {
 			lockdep_assert_held(&res->backup->base.resv->lock.base);
 			list_del_init(&res->mob_head);
-			vmw_dmabuf_unreference(&res->backup);
+			vmw_bo_unreference(&res->backup);
 		}
 
 		if (new_backup) {
-			res->backup = vmw_dmabuf_reference(new_backup);
+			res->backup = vmw_bo_reference(new_backup);
 			lockdep_assert_held(&new_backup->base.resv->lock.base);
 			list_add_tail(&res->mob_head, &new_backup->res_list);
 		} else {
@@ -1007,7 +1009,7 @@ out_no_validate:
 out_no_reserve:
 	ttm_bo_unref(&val_buf->bo);
 	if (backup_dirty)
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 
 	return ret;
 }
@@ -1171,7 +1173,7 @@ int vmw_resource_validate(struct vmw_resource *res)
 		goto out_no_validate;
 	else if (!res->func->needs_backup && res->backup) {
 		list_del_init(&res->mob_head);
-		vmw_dmabuf_unreference(&res->backup);
+		vmw_bo_unreference(&res->backup);
 	}
 
 	return 0;
@@ -1230,22 +1232,22 @@ void vmw_fence_single_bo(struct ttm_buffer_object *bo,
 void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 			      struct ttm_mem_reg *mem)
 {
-	struct vmw_dma_buffer *dma_buf;
+	struct vmw_buffer_object *vbo;
 
 	if (mem == NULL)
 		return;
 
-	if (bo->destroy != vmw_dmabuf_bo_free &&
-	    bo->destroy != vmw_user_dmabuf_destroy)
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
 		return;
 
-	dma_buf = container_of(bo, struct vmw_dma_buffer, base);
+	vbo = container_of(bo, struct vmw_buffer_object, base);
 
 	/*
 	 * Kill any cached kernel maps before move. An optimization could
 	 * be to do this iff source or destination memory type is VRAM.
 	 */
-	vmw_dma_buffer_unmap(dma_buf);
+	vmw_buffer_object_unmap(vbo);
 
 	if (mem->mem_type != VMW_PL_MOB) {
 		struct vmw_resource *res, *n;
@@ -1254,7 +1256,7 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo,
 		val_buf.bo = bo;
 		val_buf.shared = false;
 
-		list_for_each_entry_safe(res, n, &dma_buf->res_list, mob_head) {
+		list_for_each_entry_safe(res, n, &vbo->res_list, mob_head) {
 
 			if (unlikely(res->func->unbind == NULL))
 				continue;
@@ -1277,12 +1279,12 @@ void vmw_resource_move_notify(struct ttm_buffer_object *bo,
  */
 void vmw_resource_swap_notify(struct ttm_buffer_object *bo)
 {
-	if (bo->destroy != vmw_dmabuf_bo_free &&
-	    bo->destroy != vmw_user_dmabuf_destroy)
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
 		return;
 
 	/* Kill any cached kernel maps before swapout */
-	vmw_dma_buffer_unmap(vmw_dma_buffer(bo));
+	vmw_buffer_object_unmap(vmw_buffer_object(bo));
 }
 
 
@@ -1294,7 +1296,7 @@ void vmw_resource_swap_notify(struct ttm_buffer_object *bo)
  * Read back cached states from the device if they exist.  This function
  * assumings binding_mutex is held.
  */
-int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob)
+int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob)
 {
 	struct vmw_resource *dx_query_ctx;
 	struct vmw_private *dev_priv;
@@ -1344,7 +1346,7 @@ int vmw_query_readback_all(struct vmw_dma_buffer *dx_query_mob)
 void vmw_query_move_notify(struct ttm_buffer_object *bo,
 			   struct ttm_mem_reg *mem)
 {
-	struct vmw_dma_buffer *dx_query_mob;
+	struct vmw_buffer_object *dx_query_mob;
 	struct ttm_bo_device *bdev = bo->bdev;
 	struct vmw_private *dev_priv;
 
@@ -1353,7 +1355,7 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo,
 
 	mutex_lock(&dev_priv->binding_mutex);
 
-	dx_query_mob = container_of(bo, struct vmw_dma_buffer, base);
+	dx_query_mob = container_of(bo, struct vmw_buffer_object, base);
 	if (mem == NULL || !dx_query_mob || !dx_query_mob->dx_query_ctx) {
 		mutex_unlock(&dev_priv->binding_mutex);
 		return;
@@ -1481,7 +1483,7 @@ int vmw_resource_pin(struct vmw_resource *res, bool interruptible)
 		goto out_no_reserve;
 
 	if (res->pin_count == 0) {
-		struct vmw_dma_buffer *vbo = NULL;
+		struct vmw_buffer_object *vbo = NULL;
 
 		if (res->backup) {
 			vbo = res->backup;
@@ -1539,7 +1541,7 @@ void vmw_resource_unpin(struct vmw_resource *res)
 
 	WARN_ON(res->pin_count == 0);
 	if (--res->pin_count == 0 && res->backup) {
-		struct vmw_dma_buffer *vbo = res->backup;
+		struct vmw_buffer_object *vbo = res->backup;
 
 		(void) ttm_bo_reserve(&vbo->base, false, false, NULL);
 		vmw_bo_pin_reserved(vbo, false);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 9798640cbfcd..74dfd4621b7e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -66,7 +66,7 @@ struct vmw_kms_sou_readback_blit {
 	SVGAFifoCmdBlitScreenToGMRFB body;
 };
 
-struct vmw_kms_sou_dmabuf_blit {
+struct vmw_kms_sou_bo_blit {
 	uint32 header;
 	SVGAFifoCmdBlitGMRFBToScreen body;
 };
@@ -83,7 +83,7 @@ struct vmw_screen_object_unit {
 	struct vmw_display_unit base;
 
 	unsigned long buffer_size; /**< Size of allocated buffer */
-	struct vmw_dma_buffer *buffer; /**< Backing store buffer */
+	struct vmw_buffer_object *buffer; /**< Backing store buffer */
 
 	bool defined;
 };
@@ -240,8 +240,8 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	}
 
 	if (vfb) {
-		sou->buffer = vps->dmabuf;
-		sou->buffer_size = vps->dmabuf_size;
+		sou->buffer = vps->bo;
+		sou->buffer_size = vps->bo_size;
 
 		ret = vmw_sou_fifo_create(dev_priv, sou, crtc->x, crtc->y,
 					  &crtc->mode);
@@ -408,10 +408,10 @@ vmw_sou_primary_plane_cleanup_fb(struct drm_plane *plane,
 	struct drm_crtc *crtc = plane->state->crtc ?
 		plane->state->crtc : old_state->crtc;
 
-	if (vps->dmabuf)
-		vmw_dmabuf_unpin(vmw_priv(crtc->dev), vps->dmabuf, false);
-	vmw_dmabuf_unreference(&vps->dmabuf);
-	vps->dmabuf_size = 0;
+	if (vps->bo)
+		vmw_bo_unpin(vmw_priv(crtc->dev), vps->bo, false);
+	vmw_bo_unreference(&vps->bo);
+	vps->bo_size = 0;
 
 	vmw_du_plane_cleanup_fb(plane, old_state);
 }
@@ -440,8 +440,8 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 
 
 	if (!new_fb) {
-		vmw_dmabuf_unreference(&vps->dmabuf);
-		vps->dmabuf_size = 0;
+		vmw_bo_unreference(&vps->bo);
+		vps->bo_size = 0;
 
 		return 0;
 	}
@@ -449,22 +449,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	size = new_state->crtc_w * new_state->crtc_h * 4;
 	dev_priv = vmw_priv(crtc->dev);
 
-	if (vps->dmabuf) {
-		if (vps->dmabuf_size == size) {
+	if (vps->bo) {
+		if (vps->bo_size == size) {
 			/*
 			 * Note that this might temporarily up the pin-count
 			 * to 2, until cleanup_fb() is called.
 			 */
-			return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf,
+			return vmw_bo_pin_in_vram(dev_priv, vps->bo,
 						      true);
 		}
 
-		vmw_dmabuf_unreference(&vps->dmabuf);
-		vps->dmabuf_size = 0;
+		vmw_bo_unreference(&vps->bo);
+		vps->bo_size = 0;
 	}
 
-	vps->dmabuf = kzalloc(sizeof(*vps->dmabuf), GFP_KERNEL);
-	if (!vps->dmabuf)
+	vps->bo = kzalloc(sizeof(*vps->bo), GFP_KERNEL);
+	if (!vps->bo)
 		return -ENOMEM;
 
 	vmw_svga_enable(dev_priv);
@@ -473,22 +473,22 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
 	 * resume the overlays, this is preferred to failing to alloc.
 	 */
 	vmw_overlay_pause_all(dev_priv);
-	ret = vmw_dmabuf_init(dev_priv, vps->dmabuf, size,
+	ret = vmw_bo_init(dev_priv, vps->bo, size,
 			      &vmw_vram_ne_placement,
-			      false, &vmw_dmabuf_bo_free);
+			      false, &vmw_bo_bo_free);
 	vmw_overlay_resume_all(dev_priv);
 	if (ret) {
-		vps->dmabuf = NULL; /* vmw_dmabuf_init frees on error */
+		vps->bo = NULL; /* vmw_bo_init frees on error */
 		return ret;
 	}
 
-	vps->dmabuf_size = size;
+	vps->bo_size = size;
 
 	/*
 	 * TTM already thinks the buffer is pinned, but make sure the
 	 * pin_count is upped.
 	 */
-	return vmw_dmabuf_pin_in_vram(dev_priv, vps->dmabuf, true);
+	return vmw_bo_pin_in_vram(dev_priv, vps->bo, true);
 }
 
 
@@ -512,10 +512,10 @@ vmw_sou_primary_plane_atomic_update(struct drm_plane *plane,
 		vclips.w = crtc->mode.hdisplay;
 		vclips.h = crtc->mode.vdisplay;
 
-		if (vfb->dmabuf)
-			ret = vmw_kms_sou_do_dmabuf_dirty(dev_priv, vfb, NULL,
-							  &vclips, 1, 1, true,
-							  &fence, crtc);
+		if (vfb->bo)
+			ret = vmw_kms_sou_do_bo_dirty(dev_priv, vfb, NULL,
+						      &vclips, 1, 1, true,
+						      &fence, crtc);
 		else
 			ret = vmw_kms_sou_do_surface_dirty(dev_priv, vfb, NULL,
 							   &vclips, NULL, 0, 0,
@@ -775,11 +775,11 @@ int vmw_kms_sou_init_display(struct vmw_private *dev_priv)
 	return 0;
 }
 
-static int do_dmabuf_define_gmrfb(struct vmw_private *dev_priv,
+static int do_bo_define_gmrfb(struct vmw_private *dev_priv,
 				  struct vmw_framebuffer *framebuffer)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(framebuffer, struct vmw_framebuffer_dmabuf,
+	struct vmw_buffer_object *buf =
+		container_of(framebuffer, struct vmw_framebuffer_bo,
 			     base)->buffer;
 	int depth = framebuffer->base.format->depth;
 	struct {
@@ -970,13 +970,13 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
 }
 
 /**
- * vmw_sou_dmabuf_fifo_commit - Callback to submit a set of readback clips.
+ * vmw_sou_bo_fifo_commit - Callback to submit a set of readback clips.
  *
  * @dirty: The closure structure.
  *
  * Commits a previously built command buffer of readback clips.
  */
-static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
+static void vmw_sou_bo_fifo_commit(struct vmw_kms_dirty *dirty)
 {
 	if (!dirty->num_hits) {
 		vmw_fifo_commit(dirty->dev_priv, 0);
@@ -984,20 +984,20 @@ static void vmw_sou_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
 	}
 
 	vmw_fifo_commit(dirty->dev_priv,
-			sizeof(struct vmw_kms_sou_dmabuf_blit) *
+			sizeof(struct vmw_kms_sou_bo_blit) *
 			dirty->num_hits);
 }
 
 /**
- * vmw_sou_dmabuf_clip - Callback to encode a readback cliprect.
+ * vmw_sou_bo_clip - Callback to encode a readback cliprect.
  *
  * @dirty: The closure structure
  *
  * Encodes a BLIT_GMRFB_TO_SCREEN cliprect.
  */
-static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
+static void vmw_sou_bo_clip(struct vmw_kms_dirty *dirty)
 {
-	struct vmw_kms_sou_dmabuf_blit *blit = dirty->cmd;
+	struct vmw_kms_sou_bo_blit *blit = dirty->cmd;
 
 	blit += dirty->num_hits;
 	blit->header = SVGA_CMD_BLIT_GMRFB_TO_SCREEN;
@@ -1012,10 +1012,10 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
 }
 
 /**
- * vmw_kms_do_dmabuf_dirty - Dirty part of a dma-buffer backed framebuffer
+ * vmw_kms_do_bo_dirty - Dirty part of a buffer-object backed framebuffer
  *
  * @dev_priv: Pointer to the device private structure.
- * @framebuffer: Pointer to the dma-buffer backed framebuffer.
+ * @framebuffer: Pointer to the buffer-object backed framebuffer.
  * @clips: Array of clip rects.
  * @vclips: Alternate array of clip rects. Either @clips or @vclips must
  * be NULL.
@@ -1025,12 +1025,12 @@ static void vmw_sou_dmabuf_clip(struct vmw_kms_dirty *dirty)
  * @out_fence: If non-NULL, will return a ref-counted pointer to a
  * struct vmw_fence_obj. The returned fence pointer may be NULL in which
  * case the device has already synchronized.
- * @crtc: If crtc is passed, perform dmabuf dirty on that crtc only.
+ * @crtc: If crtc is passed, perform bo dirty on that crtc only.
  *
  * Returns 0 on success, negative error code on failure. -ERESTARTSYS if
  * interrupted.
  */
-int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
+int vmw_kms_sou_do_bo_dirty(struct vmw_private *dev_priv,
 				struct vmw_framebuffer *framebuffer,
 				struct drm_clip_rect *clips,
 				struct drm_vmw_rect *vclips,
@@ -1039,8 +1039,8 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
 				struct vmw_fence_obj **out_fence,
 				struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(framebuffer, struct vmw_framebuffer_dmabuf,
+	struct vmw_buffer_object *buf =
+		container_of(framebuffer, struct vmw_framebuffer_bo,
 			     base)->buffer;
 	struct vmw_kms_dirty dirty;
 	int ret;
@@ -1050,14 +1050,14 @@ int vmw_kms_sou_do_dmabuf_dirty(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	ret = do_dmabuf_define_gmrfb(dev_priv, framebuffer);
+	ret = do_bo_define_gmrfb(dev_priv, framebuffer);
 	if (unlikely(ret != 0))
 		goto out_revert;
 
 	dirty.crtc = crtc;
-	dirty.fifo_commit = vmw_sou_dmabuf_fifo_commit;
-	dirty.clip = vmw_sou_dmabuf_clip;
-	dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_dmabuf_blit) *
+	dirty.fifo_commit = vmw_sou_bo_fifo_commit;
+	dirty.clip = vmw_sou_bo_clip;
+	dirty.fifo_reserve_size = sizeof(struct vmw_kms_sou_bo_blit) *
 		num_clips;
 	ret = vmw_kms_helper_dirty(dev_priv, framebuffer, clips, vclips,
 				   0, 0, num_clips, increment, &dirty);
@@ -1116,12 +1116,12 @@ static void vmw_sou_readback_clip(struct vmw_kms_dirty *dirty)
 
 /**
  * vmw_kms_sou_readback - Perform a readback from the screen object system to
- * a dma-buffer backed framebuffer.
+ * a buffer-object backed framebuffer.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm_file identifying the caller.
  * Must be set to NULL if @user_fence_rep is NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @user_fence_rep: User-space provided structure for fence information.
  * Must be set to non-NULL if @file_priv is non-NULL.
  * @vclips: Array of clip rects.
@@ -1139,8 +1139,8 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 			 uint32_t num_clips,
 			 struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer;
+	struct vmw_buffer_object *buf =
+		container_of(vfb, struct vmw_framebuffer_bo, base)->buffer;
 	struct vmw_kms_dirty dirty;
 	int ret;
 
@@ -1149,7 +1149,7 @@ int vmw_kms_sou_readback(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	ret = do_dmabuf_define_gmrfb(dev_priv, vfb);
+	ret = do_bo_define_gmrfb(dev_priv, vfb);
 	if (unlikely(ret != 0))
 		goto out_revert;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index 73b8e9a16368..f6c939f3ff5e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -159,7 +159,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv,
 			      SVGA3dShaderType type,
 			      uint8_t num_input_sig,
 			      uint8_t num_output_sig,
-			      struct vmw_dma_buffer *byte_code,
+			      struct vmw_buffer_object *byte_code,
 			      void (*res_free) (struct vmw_resource *res))
 {
 	struct vmw_shader *shader = vmw_res_to_shader(res);
@@ -178,7 +178,7 @@ static int vmw_gb_shader_init(struct vmw_private *dev_priv,
 
 	res->backup_size = size;
 	if (byte_code) {
-		res->backup = vmw_dmabuf_reference(byte_code);
+		res->backup = vmw_bo_reference(byte_code);
 		res->backup_offset = offset;
 	}
 	shader->size = size;
@@ -723,7 +723,7 @@ int vmw_shader_destroy_ioctl(struct drm_device *dev, void *data,
 }
 
 static int vmw_user_shader_alloc(struct vmw_private *dev_priv,
-				 struct vmw_dma_buffer *buffer,
+				 struct vmw_buffer_object *buffer,
 				 size_t shader_size,
 				 size_t offset,
 				 SVGA3dShaderType shader_type,
@@ -801,7 +801,7 @@ out:
 
 
 static struct vmw_resource *vmw_shader_alloc(struct vmw_private *dev_priv,
-					     struct vmw_dma_buffer *buffer,
+					     struct vmw_buffer_object *buffer,
 					     size_t shader_size,
 					     size_t offset,
 					     SVGA3dShaderType shader_type)
@@ -862,12 +862,12 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_dma_buffer *buffer = NULL;
+	struct vmw_buffer_object *buffer = NULL;
 	SVGA3dShaderType shader_type;
 	int ret;
 
 	if (buffer_handle != SVGA3D_INVALID_ID) {
-		ret = vmw_user_dmabuf_lookup(tfile, buffer_handle,
+		ret = vmw_user_bo_lookup(tfile, buffer_handle,
 					     &buffer, NULL);
 		if (unlikely(ret != 0)) {
 			DRM_ERROR("Could not find buffer for shader "
@@ -906,7 +906,7 @@ static int vmw_shader_define(struct drm_device *dev, struct drm_file *file_priv,
 
 	ttm_read_unlock(&dev_priv->reservation_sem);
 out_bad_arg:
-	vmw_dmabuf_unreference(&buffer);
+	vmw_bo_unreference(&buffer);
 	return ret;
 }
 
@@ -983,7 +983,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 			  struct list_head *list)
 {
 	struct ttm_operation_ctx ctx = { false, true };
-	struct vmw_dma_buffer *buf;
+	struct vmw_buffer_object *buf;
 	struct ttm_bo_kmap_obj map;
 	bool is_iomem;
 	int ret;
@@ -997,8 +997,8 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 	if (unlikely(!buf))
 		return -ENOMEM;
 
-	ret = vmw_dmabuf_init(dev_priv, buf, size, &vmw_sys_ne_placement,
-			      true, vmw_dmabuf_bo_free);
+	ret = vmw_bo_init(dev_priv, buf, size, &vmw_sys_ne_placement,
+			      true, vmw_bo_bo_free);
 	if (unlikely(ret != 0))
 		goto out;
 
@@ -1031,7 +1031,7 @@ int vmw_compat_shader_add(struct vmw_private *dev_priv,
 				 res, list);
 	vmw_resource_unreference(&res);
 no_reserve:
-	vmw_dmabuf_unreference(&buf);
+	vmw_bo_unreference(&buf);
 out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 152e96cb1c01..537df9034008 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -44,7 +44,7 @@
 enum stdu_content_type {
 	SAME_AS_DISPLAY = 0,
 	SEPARATE_SURFACE,
-	SEPARATE_DMA
+	SEPARATE_BO
 };
 
 /**
@@ -58,7 +58,7 @@ enum stdu_content_type {
  * @bottom: Bottom side of bounding box.
  * @fb_left: Left side of the framebuffer/content bounding box
  * @fb_top: Top of the framebuffer/content bounding box
- * @buf: DMA buffer when DMA-ing between buffer and screen targets.
+ * @buf: buffer object when DMA-ing between buffer and screen targets.
  * @sid: Surface ID when copying between surface and screen targets.
  */
 struct vmw_stdu_dirty {
@@ -68,7 +68,7 @@ struct vmw_stdu_dirty {
 	s32 fb_left, fb_top;
 	u32 pitch;
 	union {
-		struct vmw_dma_buffer *buf;
+		struct vmw_buffer_object *buf;
 		u32 sid;
 	};
 };
@@ -508,14 +508,14 @@ static int vmw_stdu_crtc_page_flip(struct drm_crtc *crtc,
 
 
 /**
- * vmw_stdu_dmabuf_clip - Callback to encode a suface DMA command cliprect
+ * vmw_stdu_bo_clip - Callback to encode a suface DMA command cliprect
  *
  * @dirty: The closure structure.
  *
  * Encodes a surface DMA command cliprect and updates the bounding box
  * for the DMA.
  */
-static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_clip(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -543,14 +543,14 @@ static void vmw_stdu_dmabuf_clip(struct vmw_kms_dirty *dirty)
 }
 
 /**
- * vmw_stdu_dmabuf_fifo_commit - Callback to fill in and submit a DMA command.
+ * vmw_stdu_bo_fifo_commit - Callback to fill in and submit a DMA command.
  *
  * @dirty: The closure structure.
  *
  * Fills in the missing fields in a DMA command, and optionally encodes
  * a screen target update command, depending on transfer direction.
  */
-static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_fifo_commit(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -594,13 +594,13 @@ static void vmw_stdu_dmabuf_fifo_commit(struct vmw_kms_dirty *dirty)
 
 
 /**
- * vmw_stdu_dmabuf_cpu_clip - Callback to encode a CPU blit
+ * vmw_stdu_bo_cpu_clip - Callback to encode a CPU blit
  *
  * @dirty: The closure structure.
  *
  * This function calculates the bounding box for all the incoming clips.
  */
-static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_cpu_clip(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -624,14 +624,14 @@ static void vmw_stdu_dmabuf_cpu_clip(struct vmw_kms_dirty *dirty)
 
 
 /**
- * vmw_stdu_dmabuf_cpu_commit - Callback to do a CPU blit from DMAbuf
+ * vmw_stdu_bo_cpu_commit - Callback to do a CPU blit from buffer object
  *
  * @dirty: The closure structure.
  *
  * For the special case when we cannot create a proxy surface in a
  * 2D VM, we have to do a CPU blit ourselves.
  */
-static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
+static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty)
 {
 	struct vmw_stdu_dirty *ddirty =
 		container_of(dirty, struct vmw_stdu_dirty, base);
@@ -652,7 +652,7 @@ static void vmw_stdu_dmabuf_cpu_commit(struct vmw_kms_dirty *dirty)
 	if (width == 0 || height == 0)
 		return;
 
-	/* Assume we are blitting from Guest (dmabuf) to Host (display_srf) */
+	/* Assume we are blitting from Guest (bo) to Host (display_srf) */
 	dst_pitch = stdu->display_srf->base_size.width * stdu->cpp;
 	dst_bo = &stdu->display_srf->res.backup->base;
 	dst_offset = ddirty->top * dst_pitch + ddirty->left * stdu->cpp;
@@ -712,13 +712,13 @@ out_cleanup:
 }
 
 /**
- * vmw_kms_stdu_dma - Perform a DMA transfer between a dma-buffer backed
+ * vmw_kms_stdu_dma - Perform a DMA transfer between a buffer-object backed
  * framebuffer and the screen target system.
  *
  * @dev_priv: Pointer to the device private structure.
  * @file_priv: Pointer to a struct drm-file identifying the caller. May be
  * set to NULL, but then @user_fence_rep must also be set to NULL.
- * @vfb: Pointer to the dma-buffer backed framebuffer.
+ * @vfb: Pointer to the buffer-object backed framebuffer.
  * @clips: Array of clip rects. Either @clips or @vclips must be NULL.
  * @vclips: Alternate array of clip rects. Either @clips or @vclips must
  * be NULL.
@@ -747,8 +747,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 		     bool interruptible,
 		     struct drm_crtc *crtc)
 {
-	struct vmw_dma_buffer *buf =
-		container_of(vfb, struct vmw_framebuffer_dmabuf, base)->buffer;
+	struct vmw_buffer_object *buf =
+		container_of(vfb, struct vmw_framebuffer_bo, base)->buffer;
 	struct vmw_stdu_dirty ddirty;
 	int ret;
 	bool cpu_blit = !(dev_priv->capabilities & SVGA_CAP_3D);
@@ -770,8 +770,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 	ddirty.fb_left = ddirty.fb_top = S32_MAX;
 	ddirty.pitch = vfb->base.pitches[0];
 	ddirty.buf = buf;
-	ddirty.base.fifo_commit = vmw_stdu_dmabuf_fifo_commit;
-	ddirty.base.clip = vmw_stdu_dmabuf_clip;
+	ddirty.base.fifo_commit = vmw_stdu_bo_fifo_commit;
+	ddirty.base.clip = vmw_stdu_bo_clip;
 	ddirty.base.fifo_reserve_size = sizeof(struct vmw_stdu_dma) +
 		num_clips * sizeof(SVGA3dCopyBox) +
 		sizeof(SVGA3dCmdSurfaceDMASuffix);
@@ -780,8 +780,8 @@ int vmw_kms_stdu_dma(struct vmw_private *dev_priv,
 
 
 	if (cpu_blit) {
-		ddirty.base.fifo_commit = vmw_stdu_dmabuf_cpu_commit;
-		ddirty.base.clip = vmw_stdu_dmabuf_cpu_clip;
+		ddirty.base.fifo_commit = vmw_stdu_bo_cpu_commit;
+		ddirty.base.clip = vmw_stdu_bo_cpu_clip;
 		ddirty.base.fifo_reserve_size = 0;
 	}
 
@@ -927,7 +927,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
 	if (ret)
 		return ret;
 
-	if (vfbs->is_dmabuf_proxy) {
+	if (vfbs->is_bo_proxy) {
 		ret = vmw_kms_update_proxy(srf, clips, num_clips, inc);
 		if (ret)
 			goto out_finish;
@@ -1075,7 +1075,7 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane,
  * @new_state: info on the new plane state, including the FB
  *
  * This function allocates a new display surface if the content is
- * backed by a DMA.  The display surface is pinned here, and it'll
+ * backed by a buffer object.  The display surface is pinned here, and it'll
  * be unpinned in .cleanup_fb()
  *
  * Returns 0 on success
@@ -1105,13 +1105,13 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	}
 
 	vfb = vmw_framebuffer_to_vfb(new_fb);
-	new_vfbs = (vfb->dmabuf) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
+	new_vfbs = (vfb->bo) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
 
 	if (new_vfbs && new_vfbs->surface->base_size.width == hdisplay &&
 	    new_vfbs->surface->base_size.height == vdisplay)
 		new_content_type = SAME_AS_DISPLAY;
-	else if (vfb->dmabuf)
-		new_content_type = SEPARATE_DMA;
+	else if (vfb->bo)
+		new_content_type = SEPARATE_BO;
 	else
 		new_content_type = SEPARATE_SURFACE;
 
@@ -1124,10 +1124,10 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 		display_base_size.depth  = 1;
 
 		/*
-		 * If content buffer is a DMA buf, then we have to construct
-		 * surface info
+		 * If content buffer is a buffer object, then we have to
+		 * construct surface info
 		 */
-		if (new_content_type == SEPARATE_DMA) {
+		if (new_content_type == SEPARATE_BO) {
 
 			switch (new_fb->format->cpp[0]*8) {
 			case 32:
@@ -1212,12 +1212,12 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 	vps->content_fb_type = new_content_type;
 
 	/*
-	 * This should only happen if the DMA buf is too large to create a
+	 * This should only happen if the buffer object is too large to create a
 	 * proxy surface for.
-	 * If we are a 2D VM with a DMA buffer then we have to use CPU blit
+	 * If we are a 2D VM with a buffer object then we have to use CPU blit
 	 * so cache these mappings
 	 */
-	if (vps->content_fb_type == SEPARATE_DMA &&
+	if (vps->content_fb_type == SEPARATE_BO &&
 	    !(dev_priv->capabilities & SVGA_CAP_3D))
 		vps->cpp = new_fb->pitches[0] / new_fb->width;
 
@@ -1276,7 +1276,7 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
 		if (ret)
 			DRM_ERROR("Failed to bind surface to STDU.\n");
 
-		if (vfb->dmabuf)
+		if (vfb->bo)
 			ret = vmw_kms_stdu_dma(dev_priv, NULL, vfb, NULL, NULL,
 					       &vclips, 1, 1, true, false,
 					       crtc);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index b236c48bf265..2b2e8aa7114a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -842,12 +842,12 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	if (dev_priv->has_mob && req->shareable) {
 		uint32_t backup_handle;
 
-		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
-					    res->backup_size,
-					    true,
-					    &backup_handle,
-					    &res->backup,
-					    &user_srf->backup_base);
+		ret = vmw_user_bo_alloc(dev_priv, tfile,
+					res->backup_size,
+					true,
+					&backup_handle,
+					&res->backup,
+					&user_srf->backup_base);
 		if (unlikely(ret != 0)) {
 			vmw_resource_unreference(&res);
 			goto out_unlock;
@@ -1317,14 +1317,14 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 
 
 	if (req->buffer_handle != SVGA3D_INVALID_ID) {
-		ret = vmw_user_dmabuf_lookup(tfile, req->buffer_handle,
-					     &res->backup,
-					     &user_srf->backup_base);
+		ret = vmw_user_bo_lookup(tfile, req->buffer_handle,
+					 &res->backup,
+					 &user_srf->backup_base);
 		if (ret == 0) {
 			if (res->backup->base.num_pages * PAGE_SIZE <
 			    res->backup_size) {
 				DRM_ERROR("Surface backup buffer is too small.\n");
-				vmw_dmabuf_unreference(&res->backup);
+				vmw_bo_unreference(&res->backup);
 				ret = -EINVAL;
 				goto out_unlock;
 			} else {
@@ -1332,13 +1332,13 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 			}
 		}
 	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
-		ret = vmw_user_dmabuf_alloc(dev_priv, tfile,
-					    res->backup_size,
-					    req->drm_surface_flags &
-					    drm_vmw_surface_flag_shareable,
-					    &backup_handle,
-					    &res->backup,
-					    &user_srf->backup_base);
+		ret = vmw_user_bo_alloc(dev_priv, tfile,
+					res->backup_size,
+					req->drm_surface_flags &
+					drm_vmw_surface_flag_shareable,
+					&backup_handle,
+					&res->backup,
+					&user_srf->backup_base);
 
 	if (unlikely(ret != 0)) {
 		vmw_resource_unreference(&res);
@@ -1414,8 +1414,7 @@ int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data,
 	}
 
 	mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */
-	ret = vmw_user_dmabuf_reference(tfile, srf->res.backup,
-					&backup_handle);
+	ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle);
 	mutex_unlock(&dev_priv->cmdbuf_mutex);
 
 	if (unlikely(ret != 0)) {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
new file mode 100644
index 000000000000..0931f43913b1
--- /dev/null
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -0,0 +1,887 @@
+/**************************************************************************
+ *
+ * Copyright © 2009-2015 VMware, Inc., Palo Alto, CA., USA
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+
+#include "vmwgfx_drv.h"
+#include <drm/ttm/ttm_bo_driver.h>
+#include <drm/ttm/ttm_placement.h>
+#include <drm/ttm/ttm_page_alloc.h>
+
+static const struct ttm_place vram_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+};
+
+static const struct ttm_place vram_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
+
+static const struct ttm_place sys_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+};
+
+static const struct ttm_place sys_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
+
+static const struct ttm_place gmr_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+};
+
+static const struct ttm_place gmr_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
+
+static const struct ttm_place mob_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+};
+
+static const struct ttm_place mob_ne_placement_flags = {
+	.fpfn = 0,
+	.lpfn = 0,
+	.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED | TTM_PL_FLAG_NO_EVICT
+};
+
+struct ttm_placement vmw_vram_placement = {
+	.num_placement = 1,
+	.placement = &vram_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &vram_placement_flags
+};
+
+static const struct ttm_place vram_gmr_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}
+};
+
+static const struct ttm_place gmr_vram_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}
+};
+
+struct ttm_placement vmw_vram_gmr_placement = {
+	.num_placement = 2,
+	.placement = vram_gmr_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &gmr_placement_flags
+};
+
+static const struct ttm_place vram_gmr_ne_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED |
+			 TTM_PL_FLAG_NO_EVICT
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED |
+			 TTM_PL_FLAG_NO_EVICT
+	}
+};
+
+struct ttm_placement vmw_vram_gmr_ne_placement = {
+	.num_placement = 2,
+	.placement = vram_gmr_ne_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &gmr_ne_placement_flags
+};
+
+struct ttm_placement vmw_vram_sys_placement = {
+	.num_placement = 1,
+	.placement = &vram_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags
+};
+
+struct ttm_placement vmw_vram_ne_placement = {
+	.num_placement = 1,
+	.placement = &vram_ne_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &vram_ne_placement_flags
+};
+
+struct ttm_placement vmw_sys_placement = {
+	.num_placement = 1,
+	.placement = &sys_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags
+};
+
+struct ttm_placement vmw_sys_ne_placement = {
+	.num_placement = 1,
+	.placement = &sys_ne_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_ne_placement_flags
+};
+
+static const struct ttm_place evictable_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_VRAM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+	}
+};
+
+static const struct ttm_place nonfixed_placement_flags[] = {
+	{
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = TTM_PL_FLAG_SYSTEM | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_GMR | TTM_PL_FLAG_CACHED
+	}, {
+		.fpfn = 0,
+		.lpfn = 0,
+		.flags = VMW_PL_FLAG_MOB | TTM_PL_FLAG_CACHED
+	}
+};
+
+struct ttm_placement vmw_evictable_placement = {
+	.num_placement = 4,
+	.placement = evictable_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags
+};
+
+struct ttm_placement vmw_srf_placement = {
+	.num_placement = 1,
+	.num_busy_placement = 2,
+	.placement = &gmr_placement_flags,
+	.busy_placement = gmr_vram_placement_flags
+};
+
+struct ttm_placement vmw_mob_placement = {
+	.num_placement = 1,
+	.num_busy_placement = 1,
+	.placement = &mob_placement_flags,
+	.busy_placement = &mob_placement_flags
+};
+
+struct ttm_placement vmw_mob_ne_placement = {
+	.num_placement = 1,
+	.num_busy_placement = 1,
+	.placement = &mob_ne_placement_flags,
+	.busy_placement = &mob_ne_placement_flags
+};
+
+struct ttm_placement vmw_nonfixed_placement = {
+	.num_placement = 3,
+	.placement = nonfixed_placement_flags,
+	.num_busy_placement = 1,
+	.busy_placement = &sys_placement_flags
+};
+
+struct vmw_ttm_tt {
+	struct ttm_dma_tt dma_ttm;
+	struct vmw_private *dev_priv;
+	int gmr_id;
+	struct vmw_mob *mob;
+	int mem_type;
+	struct sg_table sgt;
+	struct vmw_sg_table vsgt;
+	uint64_t sg_alloc_size;
+	bool mapped;
+};
+
+const size_t vmw_tt_size = sizeof(struct vmw_ttm_tt);
+
+/**
+ * Helper functions to advance a struct vmw_piter iterator.
+ *
+ * @viter: Pointer to the iterator.
+ *
+ * These functions return false if past the end of the list,
+ * true otherwise. Functions are selected depending on the current
+ * DMA mapping mode.
+ */
+static bool __vmw_piter_non_sg_next(struct vmw_piter *viter)
+{
+	return ++(viter->i) < viter->num_pages;
+}
+
+static bool __vmw_piter_sg_next(struct vmw_piter *viter)
+{
+	return __sg_page_iter_next(&viter->iter);
+}
+
+
+/**
+ * Helper functions to return a pointer to the current page.
+ *
+ * @viter: Pointer to the iterator
+ *
+ * These functions return a pointer to the page currently
+ * pointed to by @viter. Functions are selected depending on the
+ * current mapping mode.
+ */
+static struct page *__vmw_piter_non_sg_page(struct vmw_piter *viter)
+{
+	return viter->pages[viter->i];
+}
+
+static struct page *__vmw_piter_sg_page(struct vmw_piter *viter)
+{
+	return sg_page_iter_page(&viter->iter);
+}
+
+
+/**
+ * Helper functions to return the DMA address of the current page.
+ *
+ * @viter: Pointer to the iterator
+ *
+ * These functions return the DMA address of the page currently
+ * pointed to by @viter. Functions are selected depending on the
+ * current mapping mode.
+ */
+static dma_addr_t __vmw_piter_phys_addr(struct vmw_piter *viter)
+{
+	return page_to_phys(viter->pages[viter->i]);
+}
+
+static dma_addr_t __vmw_piter_dma_addr(struct vmw_piter *viter)
+{
+	return viter->addrs[viter->i];
+}
+
+static dma_addr_t __vmw_piter_sg_addr(struct vmw_piter *viter)
+{
+	return sg_page_iter_dma_address(&viter->iter);
+}
+
+
+/**
+ * vmw_piter_start - Initialize a struct vmw_piter.
+ *
+ * @viter: Pointer to the iterator to initialize
+ * @vsgt: Pointer to a struct vmw_sg_table to initialize from
+ *
+ * Note that we're following the convention of __sg_page_iter_start, so that
+ * the iterator doesn't point to a valid page after initialization; it has
+ * to be advanced one step first.
+ */
+void vmw_piter_start(struct vmw_piter *viter, const struct vmw_sg_table *vsgt,
+		     unsigned long p_offset)
+{
+	viter->i = p_offset - 1;
+	viter->num_pages = vsgt->num_pages;
+	switch (vsgt->mode) {
+	case vmw_dma_phys:
+		viter->next = &__vmw_piter_non_sg_next;
+		viter->dma_address = &__vmw_piter_phys_addr;
+		viter->page = &__vmw_piter_non_sg_page;
+		viter->pages = vsgt->pages;
+		break;
+	case vmw_dma_alloc_coherent:
+		viter->next = &__vmw_piter_non_sg_next;
+		viter->dma_address = &__vmw_piter_dma_addr;
+		viter->page = &__vmw_piter_non_sg_page;
+		viter->addrs = vsgt->addrs;
+		viter->pages = vsgt->pages;
+		break;
+	case vmw_dma_map_populate:
+	case vmw_dma_map_bind:
+		viter->next = &__vmw_piter_sg_next;
+		viter->dma_address = &__vmw_piter_sg_addr;
+		viter->page = &__vmw_piter_sg_page;
+		__sg_page_iter_start(&viter->iter, vsgt->sgt->sgl,
+				     vsgt->sgt->orig_nents, p_offset);
+		break;
+	default:
+		BUG();
+	}
+}
+
+/**
+ * vmw_ttm_unmap_from_dma - unmap  device addresses previsouly mapped for
+ * TTM pages
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_backend
+ *
+ * Used to free dma mappings previously mapped by vmw_ttm_map_for_dma.
+ */
+static void vmw_ttm_unmap_from_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct device *dev = vmw_tt->dev_priv->dev->dev;
+
+	dma_unmap_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.nents,
+		DMA_BIDIRECTIONAL);
+	vmw_tt->sgt.nents = vmw_tt->sgt.orig_nents;
+}
+
+/**
+ * vmw_ttm_map_for_dma - map TTM pages to get device addresses
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_backend
+ *
+ * This function is used to get device addresses from the kernel DMA layer.
+ * However, it's violating the DMA API in that when this operation has been
+ * performed, it's illegal for the CPU to write to the pages without first
+ * unmapping the DMA mappings, or calling dma_sync_sg_for_cpu(). It is
+ * therefore only legal to call this function if we know that the function
+ * dma_sync_sg_for_cpu() is a NOP, and dma_sync_sg_for_device() is at most
+ * a CPU write buffer flush.
+ */
+static int vmw_ttm_map_for_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct device *dev = vmw_tt->dev_priv->dev->dev;
+	int ret;
+
+	ret = dma_map_sg(dev, vmw_tt->sgt.sgl, vmw_tt->sgt.orig_nents,
+			 DMA_BIDIRECTIONAL);
+	if (unlikely(ret == 0))
+		return -ENOMEM;
+
+	vmw_tt->sgt.nents = ret;
+
+	return 0;
+}
+
+/**
+ * vmw_ttm_map_dma - Make sure TTM pages are visible to the device
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_tt
+ *
+ * Select the correct function for and make sure the TTM pages are
+ * visible to the device. Allocate storage for the device mappings.
+ * If a mapping has already been performed, indicated by the storage
+ * pointer being non NULL, the function returns success.
+ */
+static int vmw_ttm_map_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct vmw_private *dev_priv = vmw_tt->dev_priv;
+	struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
+	struct vmw_sg_table *vsgt = &vmw_tt->vsgt;
+	struct ttm_operation_ctx ctx = {
+		.interruptible = true,
+		.no_wait_gpu = false
+	};
+	struct vmw_piter iter;
+	dma_addr_t old;
+	int ret = 0;
+	static size_t sgl_size;
+	static size_t sgt_size;
+
+	if (vmw_tt->mapped)
+		return 0;
+
+	vsgt->mode = dev_priv->map_mode;
+	vsgt->pages = vmw_tt->dma_ttm.ttm.pages;
+	vsgt->num_pages = vmw_tt->dma_ttm.ttm.num_pages;
+	vsgt->addrs = vmw_tt->dma_ttm.dma_address;
+	vsgt->sgt = &vmw_tt->sgt;
+
+	switch (dev_priv->map_mode) {
+	case vmw_dma_map_bind:
+	case vmw_dma_map_populate:
+		if (unlikely(!sgl_size)) {
+			sgl_size = ttm_round_pot(sizeof(struct scatterlist));
+			sgt_size = ttm_round_pot(sizeof(struct sg_table));
+		}
+		vmw_tt->sg_alloc_size = sgt_size + sgl_size * vsgt->num_pages;
+		ret = ttm_mem_global_alloc(glob, vmw_tt->sg_alloc_size, &ctx);
+		if (unlikely(ret != 0))
+			return ret;
+
+		ret = sg_alloc_table_from_pages(&vmw_tt->sgt, vsgt->pages,
+						vsgt->num_pages, 0,
+						(unsigned long)
+						vsgt->num_pages << PAGE_SHIFT,
+						GFP_KERNEL);
+		if (unlikely(ret != 0))
+			goto out_sg_alloc_fail;
+
+		if (vsgt->num_pages > vmw_tt->sgt.nents) {
+			uint64_t over_alloc =
+				sgl_size * (vsgt->num_pages -
+					    vmw_tt->sgt.nents);
+
+			ttm_mem_global_free(glob, over_alloc);
+			vmw_tt->sg_alloc_size -= over_alloc;
+		}
+
+		ret = vmw_ttm_map_for_dma(vmw_tt);
+		if (unlikely(ret != 0))
+			goto out_map_fail;
+
+		break;
+	default:
+		break;
+	}
+
+	old = ~((dma_addr_t) 0);
+	vmw_tt->vsgt.num_regions = 0;
+	for (vmw_piter_start(&iter, vsgt, 0); vmw_piter_next(&iter);) {
+		dma_addr_t cur = vmw_piter_dma_addr(&iter);
+
+		if (cur != old + PAGE_SIZE)
+			vmw_tt->vsgt.num_regions++;
+		old = cur;
+	}
+
+	vmw_tt->mapped = true;
+	return 0;
+
+out_map_fail:
+	sg_free_table(vmw_tt->vsgt.sgt);
+	vmw_tt->vsgt.sgt = NULL;
+out_sg_alloc_fail:
+	ttm_mem_global_free(glob, vmw_tt->sg_alloc_size);
+	return ret;
+}
+
+/**
+ * vmw_ttm_unmap_dma - Tear down any TTM page device mappings
+ *
+ * @vmw_tt: Pointer to a struct vmw_ttm_tt
+ *
+ * Tear down any previously set up device DMA mappings and free
+ * any storage space allocated for them. If there are no mappings set up,
+ * this function is a NOP.
+ */
+static void vmw_ttm_unmap_dma(struct vmw_ttm_tt *vmw_tt)
+{
+	struct vmw_private *dev_priv = vmw_tt->dev_priv;
+
+	if (!vmw_tt->vsgt.sgt)
+		return;
+
+	switch (dev_priv->map_mode) {
+	case vmw_dma_map_bind:
+	case vmw_dma_map_populate:
+		vmw_ttm_unmap_from_dma(vmw_tt);
+		sg_free_table(vmw_tt->vsgt.sgt);
+		vmw_tt->vsgt.sgt = NULL;
+		ttm_mem_global_free(vmw_mem_glob(dev_priv),
+				    vmw_tt->sg_alloc_size);
+		break;
+	default:
+		break;
+	}
+	vmw_tt->mapped = false;
+}
+
+
+/**
+ * vmw_bo_map_dma - Make sure buffer object pages are visible to the device
+ *
+ * @bo: Pointer to a struct ttm_buffer_object
+ *
+ * Wrapper around vmw_ttm_map_dma, that takes a TTM buffer object pointer
+ * instead of a pointer to a struct vmw_ttm_backend as argument.
+ * Note that the buffer object must be either pinned or reserved before
+ * calling this function.
+ */
+int vmw_bo_map_dma(struct ttm_buffer_object *bo)
+{
+	struct vmw_ttm_tt *vmw_tt =
+		container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm);
+
+	return vmw_ttm_map_dma(vmw_tt);
+}
+
+
+/**
+ * vmw_bo_unmap_dma - Make sure buffer object pages are visible to the device
+ *
+ * @bo: Pointer to a struct ttm_buffer_object
+ *
+ * Wrapper around vmw_ttm_unmap_dma, that takes a TTM buffer object pointer
+ * instead of a pointer to a struct vmw_ttm_backend as argument.
+ */
+void vmw_bo_unmap_dma(struct ttm_buffer_object *bo)
+{
+	struct vmw_ttm_tt *vmw_tt =
+		container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm);
+
+	vmw_ttm_unmap_dma(vmw_tt);
+}
+
+
+/**
+ * vmw_bo_sg_table - Return a struct vmw_sg_table object for a
+ * TTM buffer object
+ *
+ * @bo: Pointer to a struct ttm_buffer_object
+ *
+ * Returns a pointer to a struct vmw_sg_table object. The object should
+ * not be freed after use.
+ * Note that for the device addresses to be valid, the buffer object must
+ * either be reserved or pinned.
+ */
+const struct vmw_sg_table *vmw_bo_sg_table(struct ttm_buffer_object *bo)
+{
+	struct vmw_ttm_tt *vmw_tt =
+		container_of(bo->ttm, struct vmw_ttm_tt, dma_ttm.ttm);
+
+	return &vmw_tt->vsgt;
+}
+
+
+static int vmw_ttm_bind(struct ttm_tt *ttm, struct ttm_mem_reg *bo_mem)
+{
+	struct vmw_ttm_tt *vmw_be =
+		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
+	int ret;
+
+	ret = vmw_ttm_map_dma(vmw_be);
+	if (unlikely(ret != 0))
+		return ret;
+
+	vmw_be->gmr_id = bo_mem->start;
+	vmw_be->mem_type = bo_mem->mem_type;
+
+	switch (bo_mem->mem_type) {
+	case VMW_PL_GMR:
+		return vmw_gmr_bind(vmw_be->dev_priv, &vmw_be->vsgt,
+				    ttm->num_pages, vmw_be->gmr_id);
+	case VMW_PL_MOB:
+		if (unlikely(vmw_be->mob == NULL)) {
+			vmw_be->mob =
+				vmw_mob_create(ttm->num_pages);
+			if (unlikely(vmw_be->mob == NULL))
+				return -ENOMEM;
+		}
+
+		return vmw_mob_bind(vmw_be->dev_priv, vmw_be->mob,
+				    &vmw_be->vsgt, ttm->num_pages,
+				    vmw_be->gmr_id);
+	default:
+		BUG();
+	}
+	return 0;
+}
+
+static int vmw_ttm_unbind(struct ttm_tt *ttm)
+{
+	struct vmw_ttm_tt *vmw_be =
+		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
+
+	switch (vmw_be->mem_type) {
+	case VMW_PL_GMR:
+		vmw_gmr_unbind(vmw_be->dev_priv, vmw_be->gmr_id);
+		break;
+	case VMW_PL_MOB:
+		vmw_mob_unbind(vmw_be->dev_priv, vmw_be->mob);
+		break;
+	default:
+		BUG();
+	}
+
+	if (vmw_be->dev_priv->map_mode == vmw_dma_map_bind)
+		vmw_ttm_unmap_dma(vmw_be);
+
+	return 0;
+}
+
+
+static void vmw_ttm_destroy(struct ttm_tt *ttm)
+{
+	struct vmw_ttm_tt *vmw_be =
+		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
+
+	vmw_ttm_unmap_dma(vmw_be);
+	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
+		ttm_dma_tt_fini(&vmw_be->dma_ttm);
+	else
+		ttm_tt_fini(ttm);
+
+	if (vmw_be->mob)
+		vmw_mob_destroy(vmw_be->mob);
+
+	kfree(vmw_be);
+}
+
+
+static int vmw_ttm_populate(struct ttm_tt *ttm, struct ttm_operation_ctx *ctx)
+{
+	struct vmw_ttm_tt *vmw_tt =
+		container_of(ttm, struct vmw_ttm_tt, dma_ttm.ttm);
+	struct vmw_private *dev_priv = vmw_tt->dev_priv;
+	struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
+	int ret;
+
+	if (ttm->state != tt_unpopulated)
+		return 0;
+
+	if (dev_priv->map_mode == vmw_dma_alloc_coherent) {
+		size_t size =
+			ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t));
+		ret = ttm_mem_global_alloc(glob, size, ctx);
+		if (unlikely(ret != 0))
+			return ret;
+
+		ret = ttm_dma_populate(&vmw_tt->dma_ttm, dev_priv->dev->dev,
+					ctx);
+		if (unlikely(ret != 0))
+			ttm_mem_global_free(glob, size);
+	} else
+		ret = ttm_pool_populate(ttm, ctx);
+
+	return ret;
+}
+
+static void vmw_ttm_unpopulate(struct ttm_tt *ttm)
+{
+	struct vmw_ttm_tt *vmw_tt = container_of(ttm, struct vmw_ttm_tt,
+						 dma_ttm.ttm);
+	struct vmw_private *dev_priv = vmw_tt->dev_priv;
+	struct ttm_mem_global *glob = vmw_mem_glob(dev_priv);
+
+
+	if (vmw_tt->mob) {
+		vmw_mob_destroy(vmw_tt->mob);
+		vmw_tt->mob = NULL;
+	}
+
+	vmw_ttm_unmap_dma(vmw_tt);
+	if (dev_priv->map_mode == vmw_dma_alloc_coherent) {
+		size_t size =
+			ttm_round_pot(ttm->num_pages * sizeof(dma_addr_t));
+
+		ttm_dma_unpopulate(&vmw_tt->dma_ttm, dev_priv->dev->dev);
+		ttm_mem_global_free(glob, size);
+	} else
+		ttm_pool_unpopulate(ttm);
+}
+
+static struct ttm_backend_func vmw_ttm_func = {
+	.bind = vmw_ttm_bind,
+	.unbind = vmw_ttm_unbind,
+	.destroy = vmw_ttm_destroy,
+};
+
+static struct ttm_tt *vmw_ttm_tt_create(struct ttm_buffer_object *bo,
+					uint32_t page_flags)
+{
+	struct vmw_ttm_tt *vmw_be;
+	int ret;
+
+	vmw_be = kzalloc(sizeof(*vmw_be), GFP_KERNEL);
+	if (!vmw_be)
+		return NULL;
+
+	vmw_be->dma_ttm.ttm.func = &vmw_ttm_func;
+	vmw_be->dev_priv = container_of(bo->bdev, struct vmw_private, bdev);
+	vmw_be->mob = NULL;
+
+	if (vmw_be->dev_priv->map_mode == vmw_dma_alloc_coherent)
+		ret = ttm_dma_tt_init(&vmw_be->dma_ttm, bo, page_flags);
+	else
+		ret = ttm_tt_init(&vmw_be->dma_ttm.ttm, bo, page_flags);
+	if (unlikely(ret != 0))
+		goto out_no_init;
+
+	return &vmw_be->dma_ttm.ttm;
+out_no_init:
+	kfree(vmw_be);
+	return NULL;
+}
+
+static int vmw_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
+{
+	return 0;
+}
+
+static int vmw_init_mem_type(struct ttm_bo_device *bdev, uint32_t type,
+		      struct ttm_mem_type_manager *man)
+{
+	switch (type) {
+	case TTM_PL_SYSTEM:
+		/* System memory */
+
+		man->flags = TTM_MEMTYPE_FLAG_MAPPABLE;
+		man->available_caching = TTM_PL_FLAG_CACHED;
+		man->default_caching = TTM_PL_FLAG_CACHED;
+		break;
+	case TTM_PL_VRAM:
+		/* "On-card" video ram */
+		man->func = &ttm_bo_manager_func;
+		man->gpu_offset = 0;
+		man->flags = TTM_MEMTYPE_FLAG_FIXED | TTM_MEMTYPE_FLAG_MAPPABLE;
+		man->available_caching = TTM_PL_FLAG_CACHED;
+		man->default_caching = TTM_PL_FLAG_CACHED;
+		break;
+	case VMW_PL_GMR:
+	case VMW_PL_MOB:
+		/*
+		 * "Guest Memory Regions" is an aperture like feature with
+		 *  one slot per bo. There is an upper limit of the number of
+		 *  slots as well as the bo size.
+		 */
+		man->func = &vmw_gmrid_manager_func;
+		man->gpu_offset = 0;
+		man->flags = TTM_MEMTYPE_FLAG_CMA | TTM_MEMTYPE_FLAG_MAPPABLE;
+		man->available_caching = TTM_PL_FLAG_CACHED;
+		man->default_caching = TTM_PL_FLAG_CACHED;
+		break;
+	default:
+		DRM_ERROR("Unsupported memory type %u\n", (unsigned)type);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void vmw_evict_flags(struct ttm_buffer_object *bo,
+		     struct ttm_placement *placement)
+{
+	*placement = vmw_sys_placement;
+}
+
+static int vmw_verify_access(struct ttm_buffer_object *bo, struct file *filp)
+{
+	struct ttm_object_file *tfile =
+		vmw_fpriv((struct drm_file *)filp->private_data)->tfile;
+
+	return vmw_user_bo_verify_access(bo, tfile);
+}
+
+static int vmw_ttm_io_mem_reserve(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+{
+	struct ttm_mem_type_manager *man = &bdev->man[mem->mem_type];
+	struct vmw_private *dev_priv = container_of(bdev, struct vmw_private, bdev);
+
+	mem->bus.addr = NULL;
+	mem->bus.is_iomem = false;
+	mem->bus.offset = 0;
+	mem->bus.size = mem->num_pages << PAGE_SHIFT;
+	mem->bus.base = 0;
+	if (!(man->flags & TTM_MEMTYPE_FLAG_MAPPABLE))
+		return -EINVAL;
+	switch (mem->mem_type) {
+	case TTM_PL_SYSTEM:
+	case VMW_PL_GMR:
+	case VMW_PL_MOB:
+		return 0;
+	case TTM_PL_VRAM:
+		mem->bus.offset = mem->start << PAGE_SHIFT;
+		mem->bus.base = dev_priv->vram_start;
+		mem->bus.is_iomem = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static void vmw_ttm_io_mem_free(struct ttm_bo_device *bdev, struct ttm_mem_reg *mem)
+{
+}
+
+static int vmw_ttm_fault_reserve_notify(struct ttm_buffer_object *bo)
+{
+	return 0;
+}
+
+/**
+ * vmw_move_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to move.
+ * @mem: The struct ttm_mem_reg indicating to what memory
+ *       region the move is taking place.
+ *
+ * Calls move_notify for all subsystems needing it.
+ * (currently only resources).
+ */
+static void vmw_move_notify(struct ttm_buffer_object *bo,
+			    bool evict,
+			    struct ttm_mem_reg *mem)
+{
+	vmw_resource_move_notify(bo, mem);
+	vmw_query_move_notify(bo, mem);
+}
+
+
+/**
+ * vmw_swap_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to be swapped out.
+ */
+static void vmw_swap_notify(struct ttm_buffer_object *bo)
+{
+	vmw_resource_swap_notify(bo);
+	(void) ttm_bo_wait(bo, false, false);
+}
+
+
+struct ttm_bo_driver vmw_bo_driver = {
+	.ttm_tt_create = &vmw_ttm_tt_create,
+	.ttm_tt_populate = &vmw_ttm_populate,
+	.ttm_tt_unpopulate = &vmw_ttm_unpopulate,
+	.invalidate_caches = vmw_invalidate_caches,
+	.init_mem_type = vmw_init_mem_type,
+	.eviction_valuable = ttm_bo_eviction_valuable,
+	.evict_flags = vmw_evict_flags,
+	.move = NULL,
+	.verify_access = vmw_verify_access,
+	.move_notify = vmw_move_notify,
+	.swap_notify = vmw_swap_notify,
+	.fault_reserve_notify = &vmw_ttm_fault_reserve_notify,
+	.io_mem_reserve = &vmw_ttm_io_mem_reserve,
+	.io_mem_free = &vmw_ttm_io_mem_free,
+};
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 0bc784f5e0db..57115a5fe61a 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -40,6 +40,7 @@ extern "C" {
 
 #define DRM_VMW_GET_PARAM            0
 #define DRM_VMW_ALLOC_DMABUF         1
+#define DRM_VMW_ALLOC_BO             1
 #define DRM_VMW_UNREF_DMABUF         2
 #define DRM_VMW_HANDLE_CLOSE         2
 #define DRM_VMW_CURSOR_BYPASS        3
@@ -356,9 +357,9 @@ struct drm_vmw_fence_rep {
 
 /*************************************************************************/
 /**
- * DRM_VMW_ALLOC_DMABUF
+ * DRM_VMW_ALLOC_BO
  *
- * Allocate a DMA buffer that is visible also to the host.
+ * Allocate a buffer object that is visible also to the host.
  * NOTE: The buffer is
  * identified by a handle and an offset, which are private to the guest, but
  * useable in the command stream. The guest kernel may translate these
@@ -366,27 +367,28 @@ struct drm_vmw_fence_rep {
  * be zero at all times, or it may disappear from the interface before it is
  * fixed.
  *
- * The DMA buffer may stay user-space mapped in the guest at all times,
+ * The buffer object may stay user-space mapped in the guest at all times,
  * and is thus suitable for sub-allocation.
  *
- * DMA buffers are mapped using the mmap() syscall on the drm device.
+ * Buffer objects are mapped using the mmap() syscall on the drm device.
  */
 
 /**
- * struct drm_vmw_alloc_dmabuf_req
+ * struct drm_vmw_alloc_bo_req
  *
  * @size: Required minimum size of the buffer.
  *
- * Input data to the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Input data to the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-struct drm_vmw_alloc_dmabuf_req {
+struct drm_vmw_alloc_bo_req {
 	__u32 size;
 	__u32 pad64;
 };
+#define drm_vmw_alloc_dmabuf_req drm_vmw_alloc_bo_req
 
 /**
- * struct drm_vmw_dmabuf_rep
+ * struct drm_vmw_bo_rep
  *
  * @map_handle: Offset to use in the mmap() call used to map the buffer.
  * @handle: Handle unique to this buffer. Used for unreferencing.
@@ -395,50 +397,32 @@ struct drm_vmw_alloc_dmabuf_req {
  * @cur_gmr_offset: Offset to use in the command stream when this buffer is
  * referenced. See note above.
  *
- * Output data from the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Output data from the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-struct drm_vmw_dmabuf_rep {
+struct drm_vmw_bo_rep {
 	__u64 map_handle;
 	__u32 handle;
 	__u32 cur_gmr_id;
 	__u32 cur_gmr_offset;
 	__u32 pad64;
 };
+#define drm_vmw_dmabuf_rep drm_vmw_bo_rep
 
 /**
- * union drm_vmw_dmabuf_arg
+ * union drm_vmw_alloc_bo_arg
  *
  * @req: Input data as described above.
  * @rep: Output data as described above.
  *
- * Argument to the DRM_VMW_ALLOC_DMABUF Ioctl.
+ * Argument to the DRM_VMW_ALLOC_BO Ioctl.
  */
 
-union drm_vmw_alloc_dmabuf_arg {
-	struct drm_vmw_alloc_dmabuf_req req;
-	struct drm_vmw_dmabuf_rep rep;
-};
-
-/*************************************************************************/
-/**
- * DRM_VMW_UNREF_DMABUF - Free a DMA buffer.
- *
- */
-
-/**
- * struct drm_vmw_unref_dmabuf_arg
- *
- * @handle: Handle indicating what buffer to free. Obtained from the
- * DRM_VMW_ALLOC_DMABUF Ioctl.
- *
- * Argument to the DRM_VMW_UNREF_DMABUF Ioctl.
- */
-
-struct drm_vmw_unref_dmabuf_arg {
-	__u32 handle;
-	__u32 pad64;
+union drm_vmw_alloc_bo_arg {
+	struct drm_vmw_alloc_bo_req req;
+	struct drm_vmw_bo_rep rep;
 };
+#define drm_vmw_alloc_dmabuf_arg drm_vmw_alloc_bo_arg
 
 /*************************************************************************/
 /**
@@ -1103,9 +1087,8 @@ union drm_vmw_extended_context_arg {
  * DRM_VMW_HANDLE_CLOSE - Close a user-space handle and release its
  * underlying resource.
  *
- * Note that this ioctl is overlaid on the DRM_VMW_UNREF_DMABUF Ioctl.
- * The ioctl arguments therefore need to be identical in layout.
- *
+ * Note that this ioctl is overlaid on the deprecated DRM_VMW_UNREF_DMABUF
+ * Ioctl.
  */
 
 /**
@@ -1119,7 +1102,7 @@ struct drm_vmw_handle_close_arg {
 	__u32 handle;
 	__u32 pad64;
 };
-
+#define drm_vmw_unref_dmabuf_arg drm_vmw_handle_close_arg
 
 #if defined(__cplusplus)
 }
-- 
cgit v1.2.3


From e9431ea5076a913a3b350cf5f89eacf9375126b1 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Tue, 19 Jun 2018 15:33:53 +0200
Subject: drm/vmwgfx: Move buffer object related code to vmwgfx_bo.c

It makes more sense to have all the buffer object related code in
a single file rather than splitting it up between the resource code
and buffer object pinning utilities.

Place all buffer object related code in vmwgfx_bo.c. Fix up headers
and export resource functionality when needed in the buffer object
code.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c         | 816 +++++++++++++++++++++++++++--
 drivers/gpu/drm/vmwgfx/vmwgfx_context.c    |   4 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c    |   4 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h        |  73 ++-
 drivers/gpu/drm/vmwgfx/vmwgfx_fb.c         |   2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c        |   2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_mob.c        |   6 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c   | 640 +---------------------
 drivers/gpu/drm/vmwgfx/vmwgfx_shader.c     |   4 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c    |   4 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c |   4 +-
 11 files changed, 851 insertions(+), 708 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index f26f658cccdb..d950244798fe 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -1,6 +1,6 @@
 /**************************************************************************
  *
- * Copyright © 2011-2015 VMware, Inc., Palo Alto, CA., USA
+ * Copyright © 2011-2018 VMware, Inc., Palo Alto, CA., USA
  * All Rights Reserved.
  *
  * Permission is hereby granted, free of charge, to any person obtaining a
@@ -29,6 +29,51 @@
 
 #include <drm/drmP.h>
 #include "vmwgfx_drv.h"
+#include "drm/ttm/ttm_object.h"
+
+
+/**
+ * struct vmw_user_buffer_object - User-space-visible buffer object
+ *
+ * @prime: The prime object providing user visibility.
+ * @vbo: The struct vmw_buffer_object
+ */
+struct vmw_user_buffer_object {
+	struct ttm_prime_object prime;
+	struct vmw_buffer_object vbo;
+};
+
+
+/**
+ * vmw_buffer_object - Convert a struct ttm_buffer_object to a struct
+ * vmw_buffer_object.
+ *
+ * @bo: Pointer to the TTM buffer object.
+ * Return: Pointer to the struct vmw_buffer_object embedding the
+ * TTM buffer object.
+ */
+static struct vmw_buffer_object *
+vmw_buffer_object(struct ttm_buffer_object *bo)
+{
+	return container_of(bo, struct vmw_buffer_object, base);
+}
+
+
+/**
+ * vmw_user_buffer_object - Convert a struct ttm_buffer_object to a struct
+ * vmw_user_buffer_object.
+ *
+ * @bo: Pointer to the TTM buffer object.
+ * Return: Pointer to the struct vmw_buffer_object embedding the TTM buffer
+ * object.
+ */
+static struct vmw_user_buffer_object *
+vmw_user_buffer_object(struct ttm_buffer_object *bo)
+{
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	return container_of(vmw_bo, struct vmw_user_buffer_object, vbo);
+}
 
 
 /**
@@ -38,9 +83,8 @@
  * @buf:  DMA buffer to move.
  * @placement:  The placement to pin it.
  * @interruptible:  Use interruptible wait.
- *
- * Returns
- *  -ERESTARTSYS if interrupted by a signal.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
  */
 int vmw_bo_pin_in_placement(struct vmw_private *dev_priv,
 			    struct vmw_buffer_object *buf,
@@ -78,6 +122,7 @@ err:
 	return ret;
 }
 
+
 /**
  * vmw_bo_pin_in_vram_or_gmr - Move a buffer to vram or gmr.
  *
@@ -88,9 +133,8 @@ err:
  * @buf:  DMA buffer to move.
  * @pin:  Pin buffer if true.
  * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
  */
 int vmw_bo_pin_in_vram_or_gmr(struct vmw_private *dev_priv,
 			      struct vmw_buffer_object *buf,
@@ -133,6 +177,7 @@ err:
 	return ret;
 }
 
+
 /**
  * vmw_bo_pin_in_vram - Move a buffer to vram.
  *
@@ -142,9 +187,8 @@ err:
  * @dev_priv:  Driver private.
  * @buf:  DMA buffer to move.
  * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
  */
 int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
 		       struct vmw_buffer_object *buf,
@@ -154,6 +198,7 @@ int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
 				       interruptible);
 }
 
+
 /**
  * vmw_bo_pin_in_start_of_vram - Move a buffer to start of vram.
  *
@@ -163,9 +208,8 @@ int vmw_bo_pin_in_vram(struct vmw_private *dev_priv,
  * @dev_priv:  Driver private.
  * @buf:  DMA buffer to pin.
  * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
  */
 int vmw_bo_pin_in_start_of_vram(struct vmw_private *dev_priv,
 				struct vmw_buffer_object *buf,
@@ -225,6 +269,7 @@ err_unlock:
 	return ret;
 }
 
+
 /**
  * vmw_bo_unpin - Unpin the buffer given buffer, does not move the buffer.
  *
@@ -233,9 +278,8 @@ err_unlock:
  * @dev_priv:  Driver private.
  * @buf:  DMA buffer to unpin.
  * @interruptible:  Use interruptible wait.
- *
- * Returns
- * -ERESTARTSYS if interrupted by a signal.
+ * Return: Zero on success, Negative error code on failure. In particular
+ * -ERESTARTSYS if interrupted by a signal
  */
 int vmw_bo_unpin(struct vmw_private *dev_priv,
 		 struct vmw_buffer_object *buf,
@@ -325,25 +369,8 @@ void vmw_bo_pin_reserved(struct vmw_buffer_object *vbo, bool pin)
 }
 
 
-/*
- * vmw_buffer_object_unmap - Tear down a cached buffer object map.
- *
- * @vbo: The buffer object whose map we are tearing down.
- *
- * This function tears down a cached map set up using
- * vmw_buffer_object_map_and_cache().
- */
-void vmw_buffer_object_unmap(struct vmw_buffer_object *vbo)
-{
-	if (vbo->map.bo == NULL)
-		return;
-
-	ttm_bo_kunmap(&vbo->map);
-}
-
-
-/*
- * vmw_buffer_object_map_and_cache - Map a buffer object and cache the map
+/**
+ * vmw_bo_map_and_cache - Map a buffer object and cache the map
  *
  * @vbo: The buffer object to map
  * Return: A kernel virtual address or NULL if mapping failed.
@@ -357,7 +384,7 @@ void vmw_buffer_object_unmap(struct vmw_buffer_object *vbo)
  * 3) Buffer object destruction
  *
  */
-void *vmw_buffer_object_map_and_cache(struct vmw_buffer_object *vbo)
+void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo)
 {
 	struct ttm_buffer_object *bo = &vbo->base;
 	bool not_used;
@@ -374,3 +401,720 @@ void *vmw_buffer_object_map_and_cache(struct vmw_buffer_object *vbo)
 
 	return ttm_kmap_obj_virtual(&vbo->map, &not_used);
 }
+
+
+/**
+ * vmw_bo_unmap - Tear down a cached buffer object map.
+ *
+ * @vbo: The buffer object whose map we are tearing down.
+ *
+ * This function tears down a cached map set up using
+ * vmw_buffer_object_map_and_cache().
+ */
+void vmw_bo_unmap(struct vmw_buffer_object *vbo)
+{
+	if (vbo->map.bo == NULL)
+		return;
+
+	ttm_bo_kunmap(&vbo->map);
+}
+
+
+/**
+ * vmw_bo_acc_size - Calculate the pinned memory usage of buffers
+ *
+ * @dev_priv: Pointer to a struct vmw_private identifying the device.
+ * @size: The requested buffer size.
+ * @user: Whether this is an ordinary dma buffer or a user dma buffer.
+ */
+static size_t vmw_bo_acc_size(struct vmw_private *dev_priv, size_t size,
+			      bool user)
+{
+	static size_t struct_size, user_struct_size;
+	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	size_t page_array_size = ttm_round_pot(num_pages * sizeof(void *));
+
+	if (unlikely(struct_size == 0)) {
+		size_t backend_size = ttm_round_pot(vmw_tt_size);
+
+		struct_size = backend_size +
+			ttm_round_pot(sizeof(struct vmw_buffer_object));
+		user_struct_size = backend_size +
+			ttm_round_pot(sizeof(struct vmw_user_buffer_object));
+	}
+
+	if (dev_priv->map_mode == vmw_dma_alloc_coherent)
+		page_array_size +=
+			ttm_round_pot(num_pages * sizeof(dma_addr_t));
+
+	return ((user) ? user_struct_size : struct_size) +
+		page_array_size;
+}
+
+
+/**
+ * vmw_bo_bo_free - vmw buffer object destructor
+ *
+ * @bo: Pointer to the embedded struct ttm_buffer_object
+ */
+void vmw_bo_bo_free(struct ttm_buffer_object *bo)
+{
+	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
+
+	vmw_bo_unmap(vmw_bo);
+	kfree(vmw_bo);
+}
+
+
+/**
+ * vmw_user_bo_destroy - vmw buffer object destructor
+ *
+ * @bo: Pointer to the embedded struct ttm_buffer_object
+ */
+static void vmw_user_bo_destroy(struct ttm_buffer_object *bo)
+{
+	struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo);
+
+	vmw_bo_unmap(&vmw_user_bo->vbo);
+	ttm_prime_object_kfree(vmw_user_bo, prime);
+}
+
+
+/**
+ * vmw_bo_init - Initialize a vmw buffer object
+ *
+ * @dev_priv: Pointer to the device private struct
+ * @vmw_bo: Pointer to the struct vmw_buffer_object to initialize.
+ * @size: Buffer object size in bytes.
+ * @placement: Initial placement.
+ * @interruptible: Whether waits should be performed interruptible.
+ * @bo_free: The buffer object destructor.
+ * Returns: Zero on success, negative error code on error.
+ *
+ * Note that on error, the code will free the buffer object.
+ */
+int vmw_bo_init(struct vmw_private *dev_priv,
+		struct vmw_buffer_object *vmw_bo,
+		size_t size, struct ttm_placement *placement,
+		bool interruptible,
+		void (*bo_free)(struct ttm_buffer_object *bo))
+{
+	struct ttm_bo_device *bdev = &dev_priv->bdev;
+	size_t acc_size;
+	int ret;
+	bool user = (bo_free == &vmw_user_bo_destroy);
+
+	WARN_ON_ONCE(!bo_free && (!user && (bo_free != vmw_bo_bo_free)));
+
+	acc_size = vmw_bo_acc_size(dev_priv, size, user);
+	memset(vmw_bo, 0, sizeof(*vmw_bo));
+
+	INIT_LIST_HEAD(&vmw_bo->res_list);
+
+	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
+			  ttm_bo_type_device, placement,
+			  0, interruptible, acc_size,
+			  NULL, NULL, bo_free);
+	return ret;
+}
+
+
+/**
+ * vmw_user_bo_release - TTM reference base object release callback for
+ * vmw user buffer objects
+ *
+ * @p_base: The TTM base object pointer about to be unreferenced.
+ *
+ * Clears the TTM base object pointer and drops the reference the
+ * base object has on the underlying struct vmw_buffer_object.
+ */
+static void vmw_user_bo_release(struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+	struct ttm_base_object *base = *p_base;
+	struct ttm_buffer_object *bo;
+
+	*p_base = NULL;
+
+	if (unlikely(base == NULL))
+		return;
+
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
+				   prime.base);
+	bo = &vmw_user_bo->vbo.base;
+	ttm_bo_unref(&bo);
+}
+
+
+/**
+ * vmw_user_bo_ref_obj-release - TTM synccpu reference object release callback
+ * for vmw user buffer objects
+ *
+ * @base: Pointer to the TTM base object
+ * @ref_type: Reference type of the reference reaching zero.
+ *
+ * Called when user-space drops its last synccpu reference on the buffer
+ * object, Either explicitly or as part of a cleanup file close.
+ */
+static void vmw_user_bo_ref_obj_release(struct ttm_base_object *base,
+					enum ttm_ref_type ref_type)
+{
+	struct vmw_user_buffer_object *user_bo;
+
+	user_bo = container_of(base, struct vmw_user_buffer_object, prime.base);
+
+	switch (ref_type) {
+	case TTM_REF_SYNCCPU_WRITE:
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
+		break;
+	default:
+		WARN_ONCE(true, "Undefined buffer object reference release.\n");
+	}
+}
+
+
+/**
+ * vmw_user_bo_alloc - Allocate a user buffer object
+ *
+ * @dev_priv: Pointer to a struct device private.
+ * @tfile: Pointer to a struct ttm_object_file on which to register the user
+ * object.
+ * @size: Size of the buffer object.
+ * @shareable: Boolean whether the buffer is shareable with other open files.
+ * @handle: Pointer to where the handle value should be assigned.
+ * @p_vbo: Pointer to where the refcounted struct vmw_buffer_object pointer
+ * should be assigned.
+ * Return: Zero on success, negative error code on error.
+ */
+int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+		      struct ttm_object_file *tfile,
+		      uint32_t size,
+		      bool shareable,
+		      uint32_t *handle,
+		      struct vmw_buffer_object **p_vbo,
+		      struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *user_bo;
+	struct ttm_buffer_object *tmp;
+	int ret;
+
+	user_bo = kzalloc(sizeof(*user_bo), GFP_KERNEL);
+	if (unlikely(!user_bo)) {
+		DRM_ERROR("Failed to allocate a buffer.\n");
+		return -ENOMEM;
+	}
+
+	ret = vmw_bo_init(dev_priv, &user_bo->vbo, size,
+			  (dev_priv->has_mob) ?
+			  &vmw_sys_placement :
+			  &vmw_vram_sys_placement, true,
+			  &vmw_user_bo_destroy);
+	if (unlikely(ret != 0))
+		return ret;
+
+	tmp = ttm_bo_reference(&user_bo->vbo.base);
+	ret = ttm_prime_object_init(tfile,
+				    size,
+				    &user_bo->prime,
+				    shareable,
+				    ttm_buffer_type,
+				    &vmw_user_bo_release,
+				    &vmw_user_bo_ref_obj_release);
+	if (unlikely(ret != 0)) {
+		ttm_bo_unref(&tmp);
+		goto out_no_base_object;
+	}
+
+	*p_vbo = &user_bo->vbo;
+	if (p_base) {
+		*p_base = &user_bo->prime.base;
+		kref_get(&(*p_base)->refcount);
+	}
+	*handle = user_bo->prime.base.hash.key;
+
+out_no_base_object:
+	return ret;
+}
+
+
+/**
+ * vmw_user_bo_verify_access - verify access permissions on this
+ * buffer object.
+ *
+ * @bo: Pointer to the buffer object being accessed
+ * @tfile: Identifying the caller.
+ */
+int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
+			      struct ttm_object_file *tfile)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+
+	if (unlikely(bo->destroy != vmw_user_bo_destroy))
+		return -EPERM;
+
+	vmw_user_bo = vmw_user_buffer_object(bo);
+
+	/* Check that the caller has opened the object. */
+	if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base)))
+		return 0;
+
+	DRM_ERROR("Could not grant buffer access.\n");
+	return -EPERM;
+}
+
+
+/**
+ * vmw_user_bo_synccpu_grab - Grab a struct vmw_user_buffer_object for cpu
+ * access, idling previous GPU operations on the buffer and optionally
+ * blocking it for further command submissions.
+ *
+ * @user_bo: Pointer to the buffer object being grabbed for CPU access
+ * @tfile: Identifying the caller.
+ * @flags: Flags indicating how the grab should be performed.
+ * Return: Zero on success, Negative error code on error. In particular,
+ * -EBUSY will be returned if a dontblock operation is requested and the
+ * buffer object is busy, and -ERESTARTSYS will be returned if a wait is
+ * interrupted by a signal.
+ *
+ * A blocking grab will be automatically released when @tfile is closed.
+ */
+static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo,
+				    struct ttm_object_file *tfile,
+				    uint32_t flags)
+{
+	struct ttm_buffer_object *bo = &user_bo->vbo.base;
+	bool existed;
+	int ret;
+
+	if (flags & drm_vmw_synccpu_allow_cs) {
+		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
+		long lret;
+
+		lret = reservation_object_wait_timeout_rcu
+			(bo->resv, true, true,
+			 nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
+		if (!lret)
+			return -EBUSY;
+		else if (lret < 0)
+			return lret;
+		return 0;
+	}
+
+	ret = ttm_bo_synccpu_write_grab
+		(bo, !!(flags & drm_vmw_synccpu_dontblock));
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
+				 TTM_REF_SYNCCPU_WRITE, &existed, false);
+	if (ret != 0 || existed)
+		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
+
+	return ret;
+}
+
+/**
+ * vmw_user_bo_synccpu_release - Release a previous grab for CPU access,
+ * and unblock command submission on the buffer if blocked.
+ *
+ * @handle: Handle identifying the buffer object.
+ * @tfile: Identifying the caller.
+ * @flags: Flags indicating the type of release.
+ */
+static int vmw_user_bo_synccpu_release(uint32_t handle,
+					   struct ttm_object_file *tfile,
+					   uint32_t flags)
+{
+	if (!(flags & drm_vmw_synccpu_allow_cs))
+		return ttm_ref_object_base_unref(tfile, handle,
+						 TTM_REF_SYNCCPU_WRITE);
+
+	return 0;
+}
+
+
+/**
+ * vmw_user_bo_synccpu_ioctl - ioctl function implementing the synccpu
+ * functionality.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and calls the
+ * relevant synccpu functions.
+ */
+int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv)
+{
+	struct drm_vmw_synccpu_arg *arg =
+		(struct drm_vmw_synccpu_arg *) data;
+	struct vmw_buffer_object *vbo;
+	struct vmw_user_buffer_object *user_bo;
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct ttm_base_object *buffer_base;
+	int ret;
+
+	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
+	    || (arg->flags & ~(drm_vmw_synccpu_read | drm_vmw_synccpu_write |
+			       drm_vmw_synccpu_dontblock |
+			       drm_vmw_synccpu_allow_cs)) != 0) {
+		DRM_ERROR("Illegal synccpu flags.\n");
+		return -EINVAL;
+	}
+
+	switch (arg->op) {
+	case drm_vmw_synccpu_grab:
+		ret = vmw_user_bo_lookup(tfile, arg->handle, &vbo,
+					     &buffer_base);
+		if (unlikely(ret != 0))
+			return ret;
+
+		user_bo = container_of(vbo, struct vmw_user_buffer_object,
+				       vbo);
+		ret = vmw_user_bo_synccpu_grab(user_bo, tfile, arg->flags);
+		vmw_bo_unreference(&vbo);
+		ttm_base_object_unref(&buffer_base);
+		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
+			     ret != -EBUSY)) {
+			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	case drm_vmw_synccpu_release:
+		ret = vmw_user_bo_synccpu_release(arg->handle, tfile,
+						  arg->flags);
+		if (unlikely(ret != 0)) {
+			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
+				  (unsigned int) arg->handle);
+			return ret;
+		}
+		break;
+	default:
+		DRM_ERROR("Invalid synccpu operation.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+
+/**
+ * vmw_bo_alloc_ioctl - ioctl function implementing the buffer object
+ * allocation functionality.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and allocates a
+ * struct vmw_user_buffer_object bo.
+ */
+int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	union drm_vmw_alloc_dmabuf_arg *arg =
+	    (union drm_vmw_alloc_dmabuf_arg *)data;
+	struct drm_vmw_alloc_dmabuf_req *req = &arg->req;
+	struct drm_vmw_dmabuf_rep *rep = &arg->rep;
+	struct vmw_buffer_object *vbo;
+	uint32_t handle;
+	int ret;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+				req->size, false, &handle, &vbo,
+				NULL);
+	if (unlikely(ret != 0))
+		goto out_no_bo;
+
+	rep->handle = handle;
+	rep->map_handle = drm_vma_node_offset_addr(&vbo->base.vma_node);
+	rep->cur_gmr_id = handle;
+	rep->cur_gmr_offset = 0;
+
+	vmw_bo_unreference(&vbo);
+
+out_no_bo:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+
+	return ret;
+}
+
+
+/**
+ * vmw_bo_unref_ioctl - Generic handle close ioctl.
+ *
+ * @dev: Identifies the drm device.
+ * @data: Pointer to the ioctl argument.
+ * @file_priv: Identifies the caller.
+ * Return: Zero on success, negative error code on error.
+ *
+ * This function checks the ioctl arguments for validity and closes a
+ * handle to a TTM base object, optionally freeing the object.
+ */
+int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+		       struct drm_file *file_priv)
+{
+	struct drm_vmw_unref_dmabuf_arg *arg =
+	    (struct drm_vmw_unref_dmabuf_arg *)data;
+
+	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
+					 arg->handle,
+					 TTM_REF_USAGE);
+}
+
+
+/**
+ * vmw_user_bo_lookup - Look up a vmw user buffer object from a handle.
+ *
+ * @tfile: The TTM object file the handle is registered with.
+ * @handle: The user buffer object handle
+ * @out: Pointer to a where a pointer to the embedded
+ * struct vmw_buffer_object should be placed.
+ * @p_base: Pointer to where a pointer to the TTM base object should be
+ * placed, or NULL if no such pointer is required.
+ * Return: Zero on success, Negative error code on error.
+ *
+ * Both the output base object pointer and the vmw buffer object pointer
+ * will be refcounted.
+ */
+int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+		       uint32_t handle, struct vmw_buffer_object **out,
+		       struct ttm_base_object **p_base)
+{
+	struct vmw_user_buffer_object *vmw_user_bo;
+	struct ttm_base_object *base;
+
+	base = ttm_base_object_lookup(tfile, handle);
+	if (unlikely(base == NULL)) {
+		DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
+			  (unsigned long)handle);
+		return -ESRCH;
+	}
+
+	if (unlikely(ttm_base_object_type(base) != ttm_buffer_type)) {
+		ttm_base_object_unref(&base);
+		DRM_ERROR("Invalid buffer object handle 0x%08lx.\n",
+			  (unsigned long)handle);
+		return -EINVAL;
+	}
+
+	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
+				   prime.base);
+	(void)ttm_bo_reference(&vmw_user_bo->vbo.base);
+	if (p_base)
+		*p_base = base;
+	else
+		ttm_base_object_unref(&base);
+	*out = &vmw_user_bo->vbo;
+
+	return 0;
+}
+
+
+/**
+ * vmw_user_bo_reference - Open a handle to a vmw user buffer object.
+ *
+ * @tfile: The TTM object file to register the handle with.
+ * @vbo: The embedded vmw buffer object.
+ * @handle: Pointer to where the new handle should be placed.
+ * Return: Zero on success, Negative error code on error.
+ */
+int vmw_user_bo_reference(struct ttm_object_file *tfile,
+			  struct vmw_buffer_object *vbo,
+			  uint32_t *handle)
+{
+	struct vmw_user_buffer_object *user_bo;
+
+	if (vbo->base.destroy != vmw_user_bo_destroy)
+		return -EINVAL;
+
+	user_bo = container_of(vbo, struct vmw_user_buffer_object, vbo);
+
+	*handle = user_bo->prime.base.hash.key;
+	return ttm_ref_object_add(tfile, &user_bo->prime.base,
+				  TTM_REF_USAGE, NULL, false);
+}
+
+
+/**
+ * vmw_bo_fence_single - Utility function to fence a single TTM buffer
+ *                       object without unreserving it.
+ *
+ * @bo:             Pointer to the struct ttm_buffer_object to fence.
+ * @fence:          Pointer to the fence. If NULL, this function will
+ *                  insert a fence into the command stream..
+ *
+ * Contrary to the ttm_eu version of this function, it takes only
+ * a single buffer object instead of a list, and it also doesn't
+ * unreserve the buffer object, which needs to be done separately.
+ */
+void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+			 struct vmw_fence_obj *fence)
+{
+	struct ttm_bo_device *bdev = bo->bdev;
+
+	struct vmw_private *dev_priv =
+		container_of(bdev, struct vmw_private, bdev);
+
+	if (fence == NULL) {
+		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+		dma_fence_put(&fence->base);
+	} else
+		reservation_object_add_excl_fence(bo->resv, &fence->base);
+}
+
+
+/**
+ * vmw_dumb_create - Create a dumb kms buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @args: Pointer to a struct drm_mode_create_dumb structure
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm create_dumb functionality.
+ * Note that this is very similar to the vmw_bo_alloc ioctl, except
+ * that the arguments have a different format.
+ */
+int vmw_dumb_create(struct drm_file *file_priv,
+		    struct drm_device *dev,
+		    struct drm_mode_create_dumb *args)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_buffer_object *vbo;
+	int ret;
+
+	args->pitch = args->width * ((args->bpp + 7) / 8);
+	args->size = args->pitch * args->height;
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
+				    args->size, false, &args->handle,
+				    &vbo, NULL);
+	if (unlikely(ret != 0))
+		goto out_no_bo;
+
+	vmw_bo_unreference(&vbo);
+out_no_bo:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+
+/**
+ * vmw_dumb_map_offset - Return the address space offset of a dumb buffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @handle: Handle identifying the dumb buffer.
+ * @offset: The address space offset returned.
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm dumb_map_offset functionality.
+ */
+int vmw_dumb_map_offset(struct drm_file *file_priv,
+			struct drm_device *dev, uint32_t handle,
+			uint64_t *offset)
+{
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_buffer_object *out_buf;
+	int ret;
+
+	ret = vmw_user_bo_lookup(tfile, handle, &out_buf, NULL);
+	if (ret != 0)
+		return -EINVAL;
+
+	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
+	vmw_bo_unreference(&out_buf);
+	return 0;
+}
+
+
+/**
+ * vmw_dumb_destroy - Destroy a dumb boffer
+ *
+ * @file_priv: Pointer to a struct drm_file identifying the caller.
+ * @dev: Pointer to the drm device.
+ * @handle: Handle identifying the dumb buffer.
+ * Return: Zero on success, negative error code on failure.
+ *
+ * This is a driver callback for the core drm dumb_destroy functionality.
+ */
+int vmw_dumb_destroy(struct drm_file *file_priv,
+		     struct drm_device *dev,
+		     uint32_t handle)
+{
+	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
+					 handle, TTM_REF_USAGE);
+}
+
+
+/**
+ * vmw_bo_swap_notify - swapout notify callback.
+ *
+ * @bo: The buffer object to be swapped out.
+ */
+void vmw_bo_swap_notify(struct ttm_buffer_object *bo)
+{
+	/* Is @bo embedded in a struct vmw_buffer_object? */
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
+		return;
+
+	/* Kill any cached kernel maps before swapout */
+	vmw_bo_unmap(vmw_buffer_object(bo));
+}
+
+
+/**
+ * vmw_bo_move_notify - TTM move_notify_callback
+ *
+ * @bo: The TTM buffer object about to move.
+ * @mem: The struct ttm_mem_reg indicating to what memory
+ *       region the move is taking place.
+ *
+ * Detaches cached maps and device bindings that require that the
+ * buffer doesn't move.
+ */
+void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+			struct ttm_mem_reg *mem)
+{
+	struct vmw_buffer_object *vbo;
+
+	if (mem == NULL)
+		return;
+
+	/* Make sure @bo is embedded in a struct vmw_buffer_object? */
+	if (bo->destroy != vmw_bo_bo_free &&
+	    bo->destroy != vmw_user_bo_destroy)
+		return;
+
+	vbo = container_of(bo, struct vmw_buffer_object, base);
+
+	/*
+	 * Kill any cached kernel maps before move. An optimization could
+	 * be to do this iff source or destination memory type is in VRAM.
+	 */
+	vmw_bo_unmap(vbo);
+
+	/*
+	 * If we're moving a backup MOB out of MOB placement, then make sure we
+	 * read back all resource content first, and unbind the MOB from
+	 * the resource.
+	 */
+	if (mem->mem_type != VMW_PL_MOB)
+		vmw_resource_unbind_list(vbo);
+}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
index ff8acc74786c..d460a721eaee 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_context.c
@@ -424,7 +424,7 @@ static int vmw_gb_context_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -648,7 +648,7 @@ static int vmw_dx_context_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
index 1052cd3cb700..980e6e7cd592 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -324,7 +324,7 @@ static int vmw_cotable_unbind(struct vmw_resource *res,
 		vmw_dx_context_scrub_cotables(vcotbl->ctx, readback);
 	mutex_unlock(&dev_priv->binding_mutex);
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-	vmw_fence_single_bo(bo, fence);
+	vmw_bo_fence_single(bo, fence);
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
 
@@ -367,7 +367,7 @@ static int vmw_cotable_readback(struct vmw_resource *res)
 	}
 
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-	vmw_fence_single_bo(&res->backup->base, fence);
+	vmw_bo_fence_single(&res->backup->base, fence);
 	vmw_fence_obj_unreference(&fence);
 
 	return 0;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 25c2f668ad6c..769d72fabb56 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -630,36 +630,6 @@ extern int vmw_user_resource_lookup_handle(
 	uint32_t handle,
 	const struct vmw_user_resource_conv *converter,
 	struct vmw_resource **p_res);
-extern void vmw_bo_bo_free(struct ttm_buffer_object *bo);
-extern int vmw_bo_init(struct vmw_private *dev_priv,
-		       struct vmw_buffer_object *vmw_bo,
-		       size_t size, struct ttm_placement *placement,
-		       bool interuptable,
-		       void (*bo_free)(struct ttm_buffer_object *bo));
-extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
-				     struct ttm_object_file *tfile);
-extern int vmw_user_bo_alloc(struct vmw_private *dev_priv,
-			     struct ttm_object_file *tfile,
-			     uint32_t size,
-			     bool shareable,
-			     uint32_t *handle,
-			     struct vmw_buffer_object **p_dma_buf,
-			     struct ttm_base_object **p_base);
-extern int vmw_user_bo_reference(struct ttm_object_file *tfile,
-				 struct vmw_buffer_object *dma_buf,
-				 uint32_t *handle);
-extern int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv);
-extern int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
-			      struct drm_file *file_priv);
-extern int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
-				     struct drm_file *file_priv);
-extern uint32_t vmw_bo_validate_node(struct ttm_buffer_object *bo,
-				     uint32_t cur_validate_node);
-extern void vmw_bo_validate_clear(struct ttm_buffer_object *bo);
-extern int vmw_user_bo_lookup(struct ttm_object_file *tfile,
-			      uint32_t id, struct vmw_buffer_object **out,
-			      struct ttm_base_object **base);
 extern int vmw_stream_claim_ioctl(struct drm_device *dev, void *data,
 				  struct drm_file *file_priv);
 extern int vmw_stream_unref_ioctl(struct drm_device *dev, void *data,
@@ -672,16 +642,11 @@ extern void vmw_resource_unreserve(struct vmw_resource *res,
 				   bool switch_backup,
 				   struct vmw_buffer_object *new_backup,
 				   unsigned long new_backup_offset);
-extern void vmw_resource_move_notify(struct ttm_buffer_object *bo,
-				     struct ttm_mem_reg *mem);
 extern void vmw_query_move_notify(struct ttm_buffer_object *bo,
 				  struct ttm_mem_reg *mem);
-extern void vmw_resource_swap_notify(struct ttm_buffer_object *bo);
 extern int vmw_query_readback_all(struct vmw_buffer_object *dx_query_mob);
-extern void vmw_fence_single_bo(struct ttm_buffer_object *bo,
-				struct vmw_fence_obj *fence);
 extern void vmw_resource_evict_all(struct vmw_private *dev_priv);
-
+extern void vmw_resource_unbind_list(struct vmw_buffer_object *vbo);
 
 /**
  * Buffer object helper functions - vmwgfx_bo.c
@@ -705,8 +670,40 @@ extern int vmw_bo_unpin(struct vmw_private *vmw_priv,
 extern void vmw_bo_get_guest_ptr(const struct ttm_buffer_object *buf,
 				 SVGAGuestPtr *ptr);
 extern void vmw_bo_pin_reserved(struct vmw_buffer_object *bo, bool pin);
-extern void *vmw_buffer_object_map_and_cache(struct vmw_buffer_object *vbo);
-extern void vmw_buffer_object_unmap(struct vmw_buffer_object *vbo);
+extern void vmw_bo_bo_free(struct ttm_buffer_object *bo);
+extern int vmw_bo_init(struct vmw_private *dev_priv,
+		       struct vmw_buffer_object *vmw_bo,
+		       size_t size, struct ttm_placement *placement,
+		       bool interuptable,
+		       void (*bo_free)(struct ttm_buffer_object *bo));
+extern int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
+				     struct ttm_object_file *tfile);
+extern int vmw_user_bo_alloc(struct vmw_private *dev_priv,
+			     struct ttm_object_file *tfile,
+			     uint32_t size,
+			     bool shareable,
+			     uint32_t *handle,
+			     struct vmw_buffer_object **p_dma_buf,
+			     struct ttm_base_object **p_base);
+extern int vmw_user_bo_reference(struct ttm_object_file *tfile,
+				 struct vmw_buffer_object *dma_buf,
+				 uint32_t *handle);
+extern int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
+			      struct drm_file *file_priv);
+extern int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
+				     struct drm_file *file_priv);
+extern int vmw_user_bo_lookup(struct ttm_object_file *tfile,
+			      uint32_t id, struct vmw_buffer_object **out,
+			      struct ttm_base_object **base);
+extern void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+				struct vmw_fence_obj *fence);
+extern void *vmw_bo_map_and_cache(struct vmw_buffer_object *vbo);
+extern void vmw_bo_unmap(struct vmw_buffer_object *vbo);
+extern void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+			       struct ttm_mem_reg *mem);
+extern void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
 
 /**
  * Misc Ioctl functionality - vmwgfx_ioctl.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
index dcde4985c574..b913a56f3426 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fb.c
@@ -197,7 +197,7 @@ static void vmw_fb_dirty_flush(struct work_struct *work)
 
 	(void) ttm_read_lock(&vmw_priv->reservation_sem, false);
 	(void) ttm_bo_reserve(&vbo->base, false, false, NULL);
-	virtual = vmw_buffer_object_map_and_cache(vbo);
+	virtual = vmw_bo_map_and_cache(vbo);
 	if (!virtual)
 		goto out_unreserve;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 7a32be0cef14..e7a7a2e73bbf 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2493,7 +2493,7 @@ void vmw_kms_helper_buffer_finish(struct vmw_private *dev_priv,
 	ret = vmw_execbuf_fence_commands(file_priv, dev_priv, &fence,
 					 file_priv ? &handle : NULL);
 	if (buf)
-		vmw_fence_single_bo(&buf->base, fence);
+		vmw_bo_fence_single(&buf->base, fence);
 	if (file_priv)
 		vmw_execbuf_copy_fence_user(dev_priv, vmw_fpriv(file_priv),
 					    ret, user_fence_rep, fence,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
index d07c585e3c1d..e44da7bb4861 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_mob.c
@@ -225,7 +225,7 @@ static void vmw_takedown_otable_base(struct vmw_private *dev_priv,
 		ret = ttm_bo_reserve(bo, false, true, NULL);
 		BUG_ON(ret != 0);
 
-		vmw_fence_single_bo(bo, NULL);
+		vmw_bo_fence_single(bo, NULL);
 		ttm_bo_unreserve(bo);
 	}
 
@@ -362,7 +362,7 @@ static void vmw_otable_batch_takedown(struct vmw_private *dev_priv,
 	ret = ttm_bo_reserve(bo, false, true, NULL);
 	BUG_ON(ret != 0);
 
-	vmw_fence_single_bo(bo, NULL);
+	vmw_bo_fence_single(bo, NULL);
 	ttm_bo_unreserve(bo);
 
 	ttm_bo_unref(&batch->otable_bo);
@@ -620,7 +620,7 @@ void vmw_mob_unbind(struct vmw_private *dev_priv,
 		vmw_fifo_commit(dev_priv, sizeof(*cmd));
 	}
 	if (bo) {
-		vmw_fence_single_bo(bo, NULL);
+		vmw_bo_fence_single(bo, NULL);
 		ttm_bo_unreserve(bo);
 	}
 	vmw_fifo_resource_dec(dev_priv);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 5aaf9ac65cba..6d2cad744f5d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -27,7 +27,6 @@
 
 #include "vmwgfx_drv.h"
 #include <drm/vmwgfx_drm.h>
-#include <drm/ttm/ttm_object.h>
 #include <drm/ttm/ttm_placement.h>
 #include <drm/drmP.h>
 #include "vmwgfx_resource_priv.h"
@@ -35,30 +34,6 @@
 
 #define VMW_RES_EVICT_ERR_COUNT 10
 
-struct vmw_user_buffer_object {
-	struct ttm_prime_object prime;
-	struct vmw_buffer_object vbo;
-};
-
-struct vmw_bo_user_rep {
-	uint32_t handle;
-	uint64_t map_handle;
-};
-
-static inline struct vmw_buffer_object *
-vmw_buffer_object(struct ttm_buffer_object *bo)
-{
-	return container_of(bo, struct vmw_buffer_object, base);
-}
-
-static inline struct vmw_user_buffer_object *
-vmw_user_buffer_object(struct ttm_buffer_object *bo)
-{
-	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
-
-	return container_of(vmw_bo, struct vmw_user_buffer_object, vbo);
-}
-
 struct vmw_resource *vmw_resource_reference(struct vmw_resource *res)
 {
 	kref_get(&res->kref);
@@ -316,509 +291,6 @@ int vmw_user_lookup_handle(struct vmw_private *dev_priv,
 	return ret;
 }
 
-/**
- * Buffer management.
- */
-
-/**
- * vmw_bo_acc_size - Calculate the pinned memory usage of buffers
- *
- * @dev_priv: Pointer to a struct vmw_private identifying the device.
- * @size: The requested buffer size.
- * @user: Whether this is an ordinary dma buffer or a user dma buffer.
- */
-static size_t vmw_bo_acc_size(struct vmw_private *dev_priv, size_t size,
-			      bool user)
-{
-	static size_t struct_size, user_struct_size;
-	size_t num_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
-	size_t page_array_size = ttm_round_pot(num_pages * sizeof(void *));
-
-	if (unlikely(struct_size == 0)) {
-		size_t backend_size = ttm_round_pot(vmw_tt_size);
-
-		struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_buffer_object));
-		user_struct_size = backend_size +
-			ttm_round_pot(sizeof(struct vmw_user_buffer_object));
-	}
-
-	if (dev_priv->map_mode == vmw_dma_alloc_coherent)
-		page_array_size +=
-			ttm_round_pot(num_pages * sizeof(dma_addr_t));
-
-	return ((user) ? user_struct_size : struct_size) +
-		page_array_size;
-}
-
-void vmw_bo_bo_free(struct ttm_buffer_object *bo)
-{
-	struct vmw_buffer_object *vmw_bo = vmw_buffer_object(bo);
-
-	vmw_buffer_object_unmap(vmw_bo);
-	kfree(vmw_bo);
-}
-
-static void vmw_user_bo_destroy(struct ttm_buffer_object *bo)
-{
-	struct vmw_user_buffer_object *vmw_user_bo = vmw_user_buffer_object(bo);
-
-	vmw_buffer_object_unmap(&vmw_user_bo->vbo);
-	ttm_prime_object_kfree(vmw_user_bo, prime);
-}
-
-int vmw_bo_init(struct vmw_private *dev_priv,
-		struct vmw_buffer_object *vmw_bo,
-		size_t size, struct ttm_placement *placement,
-		bool interruptible,
-		void (*bo_free)(struct ttm_buffer_object *bo))
-{
-	struct ttm_bo_device *bdev = &dev_priv->bdev;
-	size_t acc_size;
-	int ret;
-	bool user = (bo_free == &vmw_user_bo_destroy);
-
-	WARN_ON_ONCE(!bo_free && (!user && (bo_free != vmw_bo_bo_free)));
-
-	acc_size = vmw_bo_acc_size(dev_priv, size, user);
-	memset(vmw_bo, 0, sizeof(*vmw_bo));
-
-	INIT_LIST_HEAD(&vmw_bo->res_list);
-
-	ret = ttm_bo_init(bdev, &vmw_bo->base, size,
-			  ttm_bo_type_device, placement,
-			  0, interruptible, acc_size,
-			  NULL, NULL, bo_free);
-	return ret;
-}
-
-static void vmw_user_bo_release(struct ttm_base_object **p_base)
-{
-	struct vmw_user_buffer_object *vmw_user_bo;
-	struct ttm_base_object *base = *p_base;
-	struct ttm_buffer_object *bo;
-
-	*p_base = NULL;
-
-	if (unlikely(base == NULL))
-		return;
-
-	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
-				   prime.base);
-	bo = &vmw_user_bo->vbo.base;
-	ttm_bo_unref(&bo);
-}
-
-static void vmw_user_bo_ref_obj_release(struct ttm_base_object *base,
-					enum ttm_ref_type ref_type)
-{
-	struct vmw_user_buffer_object *user_bo;
-
-	user_bo = container_of(base, struct vmw_user_buffer_object, prime.base);
-
-	switch (ref_type) {
-	case TTM_REF_SYNCCPU_WRITE:
-		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
-		break;
-	default:
-		BUG();
-	}
-}
-
-/**
- * vmw_user_bo_alloc - Allocate a user dma buffer
- *
- * @dev_priv: Pointer to a struct device private.
- * @tfile: Pointer to a struct ttm_object_file on which to register the user
- * object.
- * @size: Size of the dma buffer.
- * @shareable: Boolean whether the buffer is shareable with other open files.
- * @handle: Pointer to where the handle value should be assigned.
- * @p_vbo: Pointer to where the refcounted struct vmw_buffer_object pointer
- * should be assigned.
- */
-int vmw_user_bo_alloc(struct vmw_private *dev_priv,
-		      struct ttm_object_file *tfile,
-		      uint32_t size,
-		      bool shareable,
-		      uint32_t *handle,
-		      struct vmw_buffer_object **p_vbo,
-		      struct ttm_base_object **p_base)
-{
-	struct vmw_user_buffer_object *user_bo;
-	struct ttm_buffer_object *tmp;
-	int ret;
-
-	user_bo = kzalloc(sizeof(*user_bo), GFP_KERNEL);
-	if (unlikely(!user_bo)) {
-		DRM_ERROR("Failed to allocate a buffer.\n");
-		return -ENOMEM;
-	}
-
-	ret = vmw_bo_init(dev_priv, &user_bo->vbo, size,
-			  (dev_priv->has_mob) ?
-			  &vmw_sys_placement :
-			  &vmw_vram_sys_placement, true,
-			  &vmw_user_bo_destroy);
-	if (unlikely(ret != 0))
-		return ret;
-
-	tmp = ttm_bo_reference(&user_bo->vbo.base);
-	ret = ttm_prime_object_init(tfile,
-				    size,
-				    &user_bo->prime,
-				    shareable,
-				    ttm_buffer_type,
-				    &vmw_user_bo_release,
-				    &vmw_user_bo_ref_obj_release);
-	if (unlikely(ret != 0)) {
-		ttm_bo_unref(&tmp);
-		goto out_no_base_object;
-	}
-
-	*p_vbo = &user_bo->vbo;
-	if (p_base) {
-		*p_base = &user_bo->prime.base;
-		kref_get(&(*p_base)->refcount);
-	}
-	*handle = user_bo->prime.base.hash.key;
-
-out_no_base_object:
-	return ret;
-}
-
-/**
- * vmw_user_bo_verify_access - verify access permissions on this
- * buffer object.
- *
- * @bo: Pointer to the buffer object being accessed
- * @tfile: Identifying the caller.
- */
-int vmw_user_bo_verify_access(struct ttm_buffer_object *bo,
-				  struct ttm_object_file *tfile)
-{
-	struct vmw_user_buffer_object *vmw_user_bo;
-
-	if (unlikely(bo->destroy != vmw_user_bo_destroy))
-		return -EPERM;
-
-	vmw_user_bo = vmw_user_buffer_object(bo);
-
-	/* Check that the caller has opened the object. */
-	if (likely(ttm_ref_object_exists(tfile, &vmw_user_bo->prime.base)))
-		return 0;
-
-	DRM_ERROR("Could not grant buffer access.\n");
-	return -EPERM;
-}
-
-/**
- * vmw_user_bo_synccpu_grab - Grab a struct vmw_user_buffer_object for cpu
- * access, idling previous GPU operations on the buffer and optionally
- * blocking it for further command submissions.
- *
- * @user_bo: Pointer to the buffer object being grabbed for CPU access
- * @tfile: Identifying the caller.
- * @flags: Flags indicating how the grab should be performed.
- *
- * A blocking grab will be automatically released when @tfile is closed.
- */
-static int vmw_user_bo_synccpu_grab(struct vmw_user_buffer_object *user_bo,
-					struct ttm_object_file *tfile,
-					uint32_t flags)
-{
-	struct ttm_buffer_object *bo = &user_bo->vbo.base;
-	bool existed;
-	int ret;
-
-	if (flags & drm_vmw_synccpu_allow_cs) {
-		bool nonblock = !!(flags & drm_vmw_synccpu_dontblock);
-		long lret;
-
-		lret = reservation_object_wait_timeout_rcu(bo->resv, true, true,
-							   nonblock ? 0 : MAX_SCHEDULE_TIMEOUT);
-		if (!lret)
-			return -EBUSY;
-		else if (lret < 0)
-			return lret;
-		return 0;
-	}
-
-	ret = ttm_bo_synccpu_write_grab
-		(bo, !!(flags & drm_vmw_synccpu_dontblock));
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = ttm_ref_object_add(tfile, &user_bo->prime.base,
-				 TTM_REF_SYNCCPU_WRITE, &existed, false);
-	if (ret != 0 || existed)
-		ttm_bo_synccpu_write_release(&user_bo->vbo.base);
-
-	return ret;
-}
-
-/**
- * vmw_user_bo_synccpu_release - Release a previous grab for CPU access,
- * and unblock command submission on the buffer if blocked.
- *
- * @handle: Handle identifying the buffer object.
- * @tfile: Identifying the caller.
- * @flags: Flags indicating the type of release.
- */
-static int vmw_user_bo_synccpu_release(uint32_t handle,
-					   struct ttm_object_file *tfile,
-					   uint32_t flags)
-{
-	if (!(flags & drm_vmw_synccpu_allow_cs))
-		return ttm_ref_object_base_unref(tfile, handle,
-						 TTM_REF_SYNCCPU_WRITE);
-
-	return 0;
-}
-
-/**
- * vmw_user_bo_synccpu_release - ioctl function implementing the synccpu
- * functionality.
- *
- * @dev: Identifies the drm device.
- * @data: Pointer to the ioctl argument.
- * @file_priv: Identifies the caller.
- *
- * This function checks the ioctl arguments for validity and calls the
- * relevant synccpu functions.
- */
-int vmw_user_bo_synccpu_ioctl(struct drm_device *dev, void *data,
-				  struct drm_file *file_priv)
-{
-	struct drm_vmw_synccpu_arg *arg =
-		(struct drm_vmw_synccpu_arg *) data;
-	struct vmw_buffer_object *vbo;
-	struct vmw_user_buffer_object *user_bo;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct ttm_base_object *buffer_base;
-	int ret;
-
-	if ((arg->flags & (drm_vmw_synccpu_read | drm_vmw_synccpu_write)) == 0
-	    || (arg->flags & ~(drm_vmw_synccpu_read | drm_vmw_synccpu_write |
-			       drm_vmw_synccpu_dontblock |
-			       drm_vmw_synccpu_allow_cs)) != 0) {
-		DRM_ERROR("Illegal synccpu flags.\n");
-		return -EINVAL;
-	}
-
-	switch (arg->op) {
-	case drm_vmw_synccpu_grab:
-		ret = vmw_user_bo_lookup(tfile, arg->handle, &vbo,
-					     &buffer_base);
-		if (unlikely(ret != 0))
-			return ret;
-
-		user_bo = container_of(vbo, struct vmw_user_buffer_object,
-				       vbo);
-		ret = vmw_user_bo_synccpu_grab(user_bo, tfile, arg->flags);
-		vmw_bo_unreference(&vbo);
-		ttm_base_object_unref(&buffer_base);
-		if (unlikely(ret != 0 && ret != -ERESTARTSYS &&
-			     ret != -EBUSY)) {
-			DRM_ERROR("Failed synccpu grab on handle 0x%08x.\n",
-				  (unsigned int) arg->handle);
-			return ret;
-		}
-		break;
-	case drm_vmw_synccpu_release:
-		ret = vmw_user_bo_synccpu_release(arg->handle, tfile,
-						  arg->flags);
-		if (unlikely(ret != 0)) {
-			DRM_ERROR("Failed synccpu release on handle 0x%08x.\n",
-				  (unsigned int) arg->handle);
-			return ret;
-		}
-		break;
-	default:
-		DRM_ERROR("Invalid synccpu operation.\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-int vmw_bo_alloc_ioctl(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	union drm_vmw_alloc_dmabuf_arg *arg =
-	    (union drm_vmw_alloc_dmabuf_arg *)data;
-	struct drm_vmw_alloc_dmabuf_req *req = &arg->req;
-	struct drm_vmw_dmabuf_rep *rep = &arg->rep;
-	struct vmw_buffer_object *vbo;
-	uint32_t handle;
-	int ret;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				req->size, false, &handle, &vbo,
-				NULL);
-	if (unlikely(ret != 0))
-		goto out_no_bo;
-
-	rep->handle = handle;
-	rep->map_handle = drm_vma_node_offset_addr(&vbo->base.vma_node);
-	rep->cur_gmr_id = handle;
-	rep->cur_gmr_offset = 0;
-
-	vmw_bo_unreference(&vbo);
-
-out_no_bo:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-
-	return ret;
-}
-
-int vmw_bo_unref_ioctl(struct drm_device *dev, void *data,
-		       struct drm_file *file_priv)
-{
-	struct drm_vmw_unref_dmabuf_arg *arg =
-	    (struct drm_vmw_unref_dmabuf_arg *)data;
-
-	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					 arg->handle,
-					 TTM_REF_USAGE);
-}
-
-int vmw_user_bo_lookup(struct ttm_object_file *tfile,
-			   uint32_t handle, struct vmw_buffer_object **out,
-			   struct ttm_base_object **p_base)
-{
-	struct vmw_user_buffer_object *vmw_user_bo;
-	struct ttm_base_object *base;
-
-	base = ttm_base_object_lookup(tfile, handle);
-	if (unlikely(base == NULL)) {
-		pr_err("Invalid buffer object handle 0x%08lx\n",
-		       (unsigned long)handle);
-		return -ESRCH;
-	}
-
-	if (unlikely(ttm_base_object_type(base) != ttm_buffer_type)) {
-		ttm_base_object_unref(&base);
-		pr_err("Invalid buffer object handle 0x%08lx\n",
-		       (unsigned long)handle);
-		return -EINVAL;
-	}
-
-	vmw_user_bo = container_of(base, struct vmw_user_buffer_object,
-				   prime.base);
-	(void)ttm_bo_reference(&vmw_user_bo->vbo.base);
-	if (p_base)
-		*p_base = base;
-	else
-		ttm_base_object_unref(&base);
-	*out = &vmw_user_bo->vbo;
-
-	return 0;
-}
-
-int vmw_user_bo_reference(struct ttm_object_file *tfile,
-			      struct vmw_buffer_object *vbo,
-			      uint32_t *handle)
-{
-	struct vmw_user_buffer_object *user_bo;
-
-	if (vbo->base.destroy != vmw_user_bo_destroy)
-		return -EINVAL;
-
-	user_bo = container_of(vbo, struct vmw_user_buffer_object, vbo);
-
-	*handle = user_bo->prime.base.hash.key;
-	return ttm_ref_object_add(tfile, &user_bo->prime.base,
-				  TTM_REF_USAGE, NULL, false);
-}
-
-/**
- * vmw_dumb_create - Create a dumb kms buffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @args: Pointer to a struct drm_mode_create_dumb structure
- *
- * This is a driver callback for the core drm create_dumb functionality.
- * Note that this is very similar to the vmw_bo_alloc ioctl, except
- * that the arguments have a different format.
- */
-int vmw_dumb_create(struct drm_file *file_priv,
-		    struct drm_device *dev,
-		    struct drm_mode_create_dumb *args)
-{
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_buffer_object *vbo;
-	int ret;
-
-	args->pitch = args->width * ((args->bpp + 7) / 8);
-	args->size = args->pitch * args->height;
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	ret = vmw_user_bo_alloc(dev_priv, vmw_fpriv(file_priv)->tfile,
-				    args->size, false, &args->handle,
-				    &vbo, NULL);
-	if (unlikely(ret != 0))
-		goto out_no_bo;
-
-	vmw_bo_unreference(&vbo);
-out_no_bo:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
-}
-
-/**
- * vmw_dumb_map_offset - Return the address space offset of a dumb buffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @handle: Handle identifying the dumb buffer.
- * @offset: The address space offset returned.
- *
- * This is a driver callback for the core drm dumb_map_offset functionality.
- */
-int vmw_dumb_map_offset(struct drm_file *file_priv,
-			struct drm_device *dev, uint32_t handle,
-			uint64_t *offset)
-{
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_buffer_object *out_buf;
-	int ret;
-
-	ret = vmw_user_bo_lookup(tfile, handle, &out_buf, NULL);
-	if (ret != 0)
-		return -EINVAL;
-
-	*offset = drm_vma_node_offset_addr(&out_buf->base.vma_node);
-	vmw_bo_unreference(&out_buf);
-	return 0;
-}
-
-/**
- * vmw_dumb_destroy - Destroy a dumb boffer
- *
- * @file_priv: Pointer to a struct drm_file identifying the caller.
- * @dev: Pointer to the drm device.
- * @handle: Handle identifying the dumb buffer.
- *
- * This is a driver callback for the core drm dumb_destroy functionality.
- */
-int vmw_dumb_destroy(struct drm_file *file_priv,
-		     struct drm_device *dev,
-		     uint32_t handle)
-{
-	return ttm_ref_object_base_unref(vmw_fpriv(file_priv)->tfile,
-					 handle, TTM_REF_USAGE);
-}
-
 /**
  * vmw_resource_buf_alloc - Allocate a backup buffer for a resource.
  *
@@ -1182,109 +654,39 @@ out_no_validate:
 	return ret;
 }
 
-/**
- * vmw_fence_single_bo - Utility function to fence a single TTM buffer
- *                       object without unreserving it.
- *
- * @bo:             Pointer to the struct ttm_buffer_object to fence.
- * @fence:          Pointer to the fence. If NULL, this function will
- *                  insert a fence into the command stream..
- *
- * Contrary to the ttm_eu version of this function, it takes only
- * a single buffer object instead of a list, and it also doesn't
- * unreserve the buffer object, which needs to be done separately.
- */
-void vmw_fence_single_bo(struct ttm_buffer_object *bo,
-			 struct vmw_fence_obj *fence)
-{
-	struct ttm_bo_device *bdev = bo->bdev;
-
-	struct vmw_private *dev_priv =
-		container_of(bdev, struct vmw_private, bdev);
-
-	if (fence == NULL) {
-		vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-		reservation_object_add_excl_fence(bo->resv, &fence->base);
-		dma_fence_put(&fence->base);
-	} else
-		reservation_object_add_excl_fence(bo->resv, &fence->base);
-}
 
 /**
- * vmw_resource_move_notify - TTM move_notify_callback
+ * vmw_resource_unbind_list
  *
- * @bo: The TTM buffer object about to move.
- * @mem: The struct ttm_mem_reg indicating to what memory
- *       region the move is taking place.
+ * @vbo: Pointer to the current backing MOB.
  *
  * Evicts the Guest Backed hardware resource if the backup
  * buffer is being moved out of MOB memory.
- * Note that this function should not race with the resource
- * validation code as long as it accesses only members of struct
- * resource that remain static while bo::res is !NULL and
- * while we have @bo reserved. struct resource::backup is *not* a
- * static member. The resource validation code will take care
- * to set @bo::res to NULL, while having @bo reserved when the
- * buffer is no longer bound to the resource, so @bo:res can be
- * used to determine whether there is a need to unbind and whether
- * it is safe to unbind.
+ * Note that this function will not race with the resource
+ * validation code, since resource validation and eviction
+ * both require the backup buffer to be reserved.
  */
-void vmw_resource_move_notify(struct ttm_buffer_object *bo,
-			      struct ttm_mem_reg *mem)
+void vmw_resource_unbind_list(struct vmw_buffer_object *vbo)
 {
-	struct vmw_buffer_object *vbo;
-
-	if (mem == NULL)
-		return;
-
-	if (bo->destroy != vmw_bo_bo_free &&
-	    bo->destroy != vmw_user_bo_destroy)
-		return;
-
-	vbo = container_of(bo, struct vmw_buffer_object, base);
-
-	/*
-	 * Kill any cached kernel maps before move. An optimization could
-	 * be to do this iff source or destination memory type is VRAM.
-	 */
-	vmw_buffer_object_unmap(vbo);
 
-	if (mem->mem_type != VMW_PL_MOB) {
-		struct vmw_resource *res, *n;
-		struct ttm_validate_buffer val_buf;
+	struct vmw_resource *res, *next;
+	struct ttm_validate_buffer val_buf = {
+		.bo = &vbo->base,
+		.shared = false
+	};
 
-		val_buf.bo = bo;
-		val_buf.shared = false;
+	lockdep_assert_held(&vbo->base.resv->lock.base);
+	list_for_each_entry_safe(res, next, &vbo->res_list, mob_head) {
+		if (!res->func->unbind)
+			continue;
 
-		list_for_each_entry_safe(res, n, &vbo->res_list, mob_head) {
-
-			if (unlikely(res->func->unbind == NULL))
-				continue;
-
-			(void) res->func->unbind(res, true, &val_buf);
-			res->backup_dirty = true;
-			res->res_dirty = false;
-			list_del_init(&res->mob_head);
-		}
-
-		(void) ttm_bo_wait(bo, false, false);
+		(void) res->func->unbind(res, true, &val_buf);
+		res->backup_dirty = true;
+		res->res_dirty = false;
+		list_del_init(&res->mob_head);
 	}
-}
-
-
-/**
- * vmw_resource_swap_notify - swapout notify callback.
- *
- * @bo: The buffer object to be swapped out.
- */
-void vmw_resource_swap_notify(struct ttm_buffer_object *bo)
-{
-	if (bo->destroy != vmw_bo_bo_free &&
-	    bo->destroy != vmw_user_bo_destroy)
-		return;
 
-	/* Kill any cached kernel maps before swapout */
-	vmw_buffer_object_unmap(vmw_buffer_object(bo));
+	(void) ttm_bo_wait(&vbo->base, false, false);
 }
 
 
@@ -1370,7 +772,7 @@ void vmw_query_move_notify(struct ttm_buffer_object *bo,
 
 		/* Create a fence and attach the BO to it */
 		(void) vmw_execbuf_fence_commands(NULL, dev_priv, &fence, NULL);
-		vmw_fence_single_bo(bo, fence);
+		vmw_bo_fence_single(bo, fence);
 
 		if (fence != NULL)
 			vmw_fence_obj_unreference(&fence);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
index f6c939f3ff5e..4ec1a91990d9 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -306,7 +306,7 @@ static int vmw_gb_shader_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -537,7 +537,7 @@ static int vmw_dx_shader_unbind(struct vmw_resource *res,
 
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 2b2e8aa7114a..f2af53613803 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -468,7 +468,7 @@ static int vmw_legacy_srf_dma(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
@@ -1210,7 +1210,7 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
 	(void) vmw_execbuf_fence_commands(NULL, dev_priv,
 					  &fence, NULL);
 
-	vmw_fence_single_bo(val_buf->bo, fence);
+	vmw_bo_fence_single(val_buf->bo, fence);
 
 	if (likely(fence != NULL))
 		vmw_fence_obj_unreference(&fence);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
index 0931f43913b1..239e1edf0919 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_buffer.c
@@ -852,7 +852,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
 			    bool evict,
 			    struct ttm_mem_reg *mem)
 {
-	vmw_resource_move_notify(bo, mem);
+	vmw_bo_move_notify(bo, mem);
 	vmw_query_move_notify(bo, mem);
 }
 
@@ -864,7 +864,7 @@ static void vmw_move_notify(struct ttm_buffer_object *bo,
  */
 static void vmw_swap_notify(struct ttm_buffer_object *bo)
 {
-	vmw_resource_swap_notify(bo);
+	vmw_bo_swap_notify(bo);
 	(void) ttm_bo_wait(bo, false, false);
 }
 
-- 
cgit v1.2.3


From 098d7d532bf78ea218b46c1d6887cbb43197ab4e Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Tue, 19 Jun 2018 19:20:29 +0200
Subject: drm/vmwgfx: Optimize the buffer object swap_notify callback somewhat.

Only try to unmap cached maps when the buffer is moved into or out from
vram. Otherwise the underlying pages stay the same.

Also when unbinding resources from MOBs about to move, make sure we're
really moving out of MOB memory.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_bo.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
index d950244798fe..87204ff67c09 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
@@ -1105,16 +1105,18 @@ void vmw_bo_move_notify(struct ttm_buffer_object *bo,
 	vbo = container_of(bo, struct vmw_buffer_object, base);
 
 	/*
-	 * Kill any cached kernel maps before move. An optimization could
-	 * be to do this iff source or destination memory type is in VRAM.
+	 * Kill any cached kernel maps before move to or from VRAM.
+	 * With other types of moves, the underlying pages stay the same,
+	 * and the map can be kept.
 	 */
-	vmw_bo_unmap(vbo);
+	if (mem->mem_type == TTM_PL_VRAM || bo->mem.mem_type == TTM_PL_VRAM)
+		vmw_bo_unmap(vbo);
 
 	/*
 	 * If we're moving a backup MOB out of MOB placement, then make sure we
 	 * read back all resource content first, and unbind the MOB from
 	 * the resource.
 	 */
-	if (mem->mem_type != VMW_PL_MOB)
+	if (mem->mem_type != VMW_PL_MOB && bo->mem.mem_type == VMW_PL_MOB)
 		vmw_resource_unbind_list(vbo);
 }
-- 
cgit v1.2.3


From 19f976ab01a6bb1f36384dd8cc743b88a6b7ebd6 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Tue, 19 Jun 2018 19:22:16 +0200
Subject: drm/vmwgfx: Use blocking buffer object reserves when evicting
 resources

Previously when evicting resources we were unconditionally calling
ttm_eu_reserve_buffers with a NULL ww acquire context. That meant all
buffer object reserves were done using trylock semantics.
That makes sense when evicting during resource validation, because then
there already are a number of buffers reserved and using waiting locks
would cause lockdep errors.

That's not the case when unconditionally evicting all resources as part
of driver takedown or hibernation, so in that code path, make sure
we have a ww acquire context to get waiting lock buffer object reserve
semantics.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_resource.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
index 6d2cad744f5d..3b2d9b6c50fc 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -433,6 +433,7 @@ void vmw_resource_unreserve(struct vmw_resource *res,
  *                             for a resource and in that case, allocate
  *                             one, reserve and validate it.
  *
+ * @ticket:         The ww aqcquire context to use, or NULL if trylocking.
  * @res:            The resource for which to allocate a backup buffer.
  * @interruptible:  Whether any sleeps during allocation should be
  *                  performed while interruptible.
@@ -440,7 +441,8 @@ void vmw_resource_unreserve(struct vmw_resource *res,
  *                  reserved and validated backup buffer.
  */
 static int
-vmw_resource_check_buffer(struct vmw_resource *res,
+vmw_resource_check_buffer(struct ww_acquire_ctx *ticket,
+			  struct vmw_resource *res,
 			  bool interruptible,
 			  struct ttm_validate_buffer *val_buf)
 {
@@ -459,7 +461,7 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	val_buf->bo = ttm_bo_reference(&res->backup->base);
 	val_buf->shared = false;
 	list_add_tail(&val_buf->head, &val_list);
-	ret = ttm_eu_reserve_buffers(NULL, &val_list, interruptible, NULL);
+	ret = ttm_eu_reserve_buffers(ticket, &val_list, interruptible, NULL);
 	if (unlikely(ret != 0))
 		goto out_no_reserve;
 
@@ -477,7 +479,7 @@ vmw_resource_check_buffer(struct vmw_resource *res,
 	return 0;
 
 out_no_validate:
-	ttm_eu_backoff_reservation(NULL, &val_list);
+	ttm_eu_backoff_reservation(ticket, &val_list);
 out_no_reserve:
 	ttm_bo_unref(&val_buf->bo);
 	if (backup_dirty)
@@ -524,10 +526,12 @@ int vmw_resource_reserve(struct vmw_resource *res, bool interruptible,
  * vmw_resource_backoff_reservation - Unreserve and unreference a
  *                                    backup buffer
  *.
+ * @ticket:         The ww acquire ctx used for reservation.
  * @val_buf:        Backup buffer information.
  */
 static void
-vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
+vmw_resource_backoff_reservation(struct ww_acquire_ctx *ticket,
+				 struct ttm_validate_buffer *val_buf)
 {
 	struct list_head val_list;
 
@@ -536,7 +540,7 @@ vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
 
 	INIT_LIST_HEAD(&val_list);
 	list_add_tail(&val_buf->head, &val_list);
-	ttm_eu_backoff_reservation(NULL, &val_list);
+	ttm_eu_backoff_reservation(ticket, &val_list);
 	ttm_bo_unref(&val_buf->bo);
 }
 
@@ -544,10 +548,12 @@ vmw_resource_backoff_reservation(struct ttm_validate_buffer *val_buf)
  * vmw_resource_do_evict - Evict a resource, and transfer its data
  *                         to a backup buffer.
  *
+ * @ticket:         The ww acquire ticket to use, or NULL if trylocking.
  * @res:            The resource to evict.
  * @interruptible:  Whether to wait interruptible.
  */
-static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
+static int vmw_resource_do_evict(struct ww_acquire_ctx *ticket,
+				 struct vmw_resource *res, bool interruptible)
 {
 	struct ttm_validate_buffer val_buf;
 	const struct vmw_res_func *func = res->func;
@@ -557,7 +563,7 @@ static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 
 	val_buf.bo = NULL;
 	val_buf.shared = false;
-	ret = vmw_resource_check_buffer(res, interruptible, &val_buf);
+	ret = vmw_resource_check_buffer(ticket, res, interruptible, &val_buf);
 	if (unlikely(ret != 0))
 		return ret;
 
@@ -572,7 +578,7 @@ static int vmw_resource_do_evict(struct vmw_resource *res, bool interruptible)
 	res->backup_dirty = true;
 	res->res_dirty = false;
 out_no_unbind:
-	vmw_resource_backoff_reservation(&val_buf);
+	vmw_resource_backoff_reservation(ticket, &val_buf);
 
 	return ret;
 }
@@ -626,7 +632,8 @@ int vmw_resource_validate(struct vmw_resource *res)
 
 		write_unlock(&dev_priv->resource_lock);
 
-		ret = vmw_resource_do_evict(evict_res, true);
+		/* Trylock backup buffers with a NULL ticket. */
+		ret = vmw_resource_do_evict(NULL, evict_res, true);
 		if (unlikely(ret != 0)) {
 			write_lock(&dev_priv->resource_lock);
 			list_add_tail(&evict_res->lru_head, lru_list);
@@ -809,6 +816,7 @@ static void vmw_resource_evict_type(struct vmw_private *dev_priv,
 	struct vmw_resource *evict_res;
 	unsigned err_count = 0;
 	int ret;
+	struct ww_acquire_ctx ticket;
 
 	do {
 		write_lock(&dev_priv->resource_lock);
@@ -822,7 +830,8 @@ static void vmw_resource_evict_type(struct vmw_private *dev_priv,
 		list_del_init(&evict_res->lru_head);
 		write_unlock(&dev_priv->resource_lock);
 
-		ret = vmw_resource_do_evict(evict_res, false);
+		/* Wait lock backup buffers with a ticket. */
+		ret = vmw_resource_do_evict(&ticket, evict_res, false);
 		if (unlikely(ret != 0)) {
 			write_lock(&dev_priv->resource_lock);
 			list_add_tail(&evict_res->lru_head, lru_list);
-- 
cgit v1.2.3


From b249cb4f6bc45485f631803b9762e443108a4b00 Mon Sep 17 00:00:00 2001
From: Sinclair Yeh <syeh@vmware.com>
Date: Tue, 19 Jun 2018 19:46:58 +0200
Subject: drm/vmwgfx: Fix atomic mode set check

vmw_kms_atomic_check_modeset() is currently checking config using the
legacy state, which is updated after a commit has happened.

This means vmw_kms_atomic_check_modeset() will reject an invalid config
on the next update rather than the current one.

Fix this by using the new states for config checking

Signed-off-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 40 ++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index e7a7a2e73bbf..6b8541f9215d 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1526,33 +1526,45 @@ static int
 vmw_kms_atomic_check_modeset(struct drm_device *dev,
 			     struct drm_atomic_state *state)
 {
-	struct drm_crtc_state *crtc_state;
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_plane_state *new_plane_state;
+	struct drm_plane *plane;
 	struct drm_crtc *crtc;
 	struct vmw_private *dev_priv = vmw_priv(dev);
-	int i;
+	int i, ret, cpp = 0;
 
-	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
-		unsigned long requested_bb_mem = 0;
+	ret = drm_atomic_helper_check(dev, state);
 
-		if (dev_priv->active_display_unit == vmw_du_screen_target) {
-			struct drm_plane *plane = crtc->primary;
-			struct drm_plane_state *plane_state;
+	/* If this is not a STDU, then no more checking is necessary */
+	if (ret || dev_priv->active_display_unit != vmw_du_screen_target)
+		return ret;
 
-			plane_state = drm_atomic_get_new_plane_state(state, plane);
+	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
+		if (new_plane_state->fb) {
+			int current_cpp = new_plane_state->fb->pitches[0] /
+					  new_plane_state->fb->width;
 
-			if (plane_state && plane_state->fb) {
-				int cpp = plane_state->fb->format->cpp[0];
+			if (cpp == 0)
+				cpp = current_cpp;
+			else if (current_cpp != cpp)
+				return -EINVAL;
+		}
+	}
 
-				requested_bb_mem += crtc->mode.hdisplay * cpp *
-						    crtc->mode.vdisplay;
-			}
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
+		unsigned long requested_bb_mem = 0;
+
+		if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
+			requested_bb_mem += new_crtc_state->mode.hdisplay *
+					    new_crtc_state->mode.vdisplay *
+					    cpp;
 
 			if (requested_bb_mem > dev_priv->prim_bb_mem)
 				return -EINVAL;
 		}
 	}
 
-	return drm_atomic_helper_check(dev, state);
+	return ret;
 }
 
 static const struct drm_mode_config_funcs vmw_kms_funcs = {
-- 
cgit v1.2.3


From 0a80eb4c122fd6119f3a15910d7bb9e6e33c3661 Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Tue, 19 Jun 2018 19:51:15 +0200
Subject: drm/vmwgfx: Perform topology validation during atomic modeset.

This patch adds display (primary) memory validation during modeset
check. Display memory validation are applicable to both SOU and STDU,
so allow both display unit to undergo this check.

Also added check for SVGA_CAP_NO_BB_RESTRICTION capability which lifts
bounding box restriction for STDU.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/device_include/svga_reg.h |  31 +++-
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c              | 184 ++++++++++++++++++-----
 2 files changed, 177 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
index 88e72bf9a534..cdd48a3763db 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
@@ -672,8 +672,34 @@ SVGASignedPoint;
  * SVGA_CAP_GBOBJECTS --
  *    Enable guest-backed objects and surfaces.
  *
- * SVGA_CAP_CMD_BUFFERS_3 --
- *    Enable support for command buffers in a mob.
+ * SVGA_CAP_DX --
+ *    Enable support for DX commands, and command buffers in a mob.
+ *
+ * SVGA_CAP_HP_CMD_QUEUE --
+ *    Enable support for the high priority command queue, and the
+ *    ScreenCopy command.
+ *
+ * SVGA_CAP_NO_BB_RESTRICTION --
+ *    Allow ScreenTargets to be defined without regard to the 32-bpp
+ *    bounding-box memory restrictions. ie:
+ *
+ *    The summed memory usage of all screens (assuming they were defined as
+ *    32-bpp) must always be less than the value of the
+ *    SVGA_REG_MAX_PRIMARY_MEM register.
+ *
+ *    If this cap is not present, the 32-bpp bounding box around all screens
+ *    must additionally be under the value of the SVGA_REG_MAX_PRIMARY_MEM
+ *    register.
+ *
+ *    If the cap is present, the bounding box restriction is lifted (and only
+ *    the screen-sum limit applies).
+ *
+ *    (Note that this is a slight lie... there is still a sanity limit on any
+ *     dimension of the topology to be less than SVGA_SCREEN_ROOT_LIMIT, even
+ *     when SVGA_CAP_NO_BB_RESTRICTION is present, but that should be
+ *     large enough to express any possible topology without holes between
+ *     monitors.)
+ *
  */
 
 #define SVGA_CAP_NONE               0x00000000
@@ -699,6 +725,7 @@ SVGASignedPoint;
 #define SVGA_CAP_GBOBJECTS          0x08000000
 #define SVGA_CAP_DX                 0x10000000
 #define SVGA_CAP_HP_CMD_QUEUE       0x20000000
+#define SVGA_CAP_NO_BB_RESTRICTION  0x40000000
 
 #define SVGA_CAP_CMD_RESERVED       0x80000000
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 6b8541f9215d..a7c9a017fc3c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1507,66 +1507,178 @@ err_out:
 	return &vfb->base;
 }
 
+/**
+ * vmw_kms_check_display_memory - Validates display memory required for a
+ * topology
+ * @dev: DRM device
+ * @num_rects: number of drm_rect in rects
+ * @rects: array of drm_rect representing the topology to validate indexed by
+ * crtc index.
+ *
+ * Returns:
+ * 0 on success otherwise negative error code
+ */
+static int vmw_kms_check_display_memory(struct drm_device *dev,
+					uint32_t num_rects,
+					struct drm_rect *rects)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	struct drm_rect bounding_box = {0};
+	u64 total_pixels = 0, pixel_mem, bb_mem;
+	int i;
+
+	for (i = 0; i < num_rects; i++) {
+		/*
+		 * Currently this check is limiting the topology within max
+		 * texture/screentarget size. This should change in future when
+		 * user-space support multiple fb with topology.
+		 */
+		if (rects[i].x1 < 0 ||  rects[i].y1 < 0 ||
+		    rects[i].x2 > mode_config->max_width ||
+		    rects[i].y2 > mode_config->max_height) {
+			DRM_ERROR("Invalid GUI layout.\n");
+			return -EINVAL;
+		}
+
+		/* Bounding box upper left is at (0,0). */
+		if (rects[i].x2 > bounding_box.x2)
+			bounding_box.x2 = rects[i].x2;
+
+		if (rects[i].y2 > bounding_box.y2)
+			bounding_box.y2 = rects[i].y2;
+
+		total_pixels += (u64) drm_rect_width(&rects[i]) *
+			(u64) drm_rect_height(&rects[i]);
+	}
+
+	/* Virtual svga device primary limits are always in 32-bpp. */
+	pixel_mem = total_pixels * 4;
+
+	/*
+	 * For HV10 and below prim_bb_mem is vram size. When
+	 * SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM is not present vram size is
+	 * limit on primary bounding box
+	 */
+	if (pixel_mem > dev_priv->prim_bb_mem) {
+		DRM_ERROR("Combined output size too large.\n");
+		return -EINVAL;
+	}
 
+	/* SVGA_CAP_NO_BB_RESTRICTION is available for STDU only. */
+	if (dev_priv->active_display_unit != vmw_du_screen_target ||
+	    !(dev_priv->capabilities & SVGA_CAP_NO_BB_RESTRICTION)) {
+		bb_mem = (u64) bounding_box.x2 * bounding_box.y2 * 4;
+
+		if (bb_mem > dev_priv->prim_bb_mem) {
+			DRM_ERROR("Topology is beyond supported limits.\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
 
 /**
- * vmw_kms_atomic_check_modeset- validate state object for modeset changes
- *
+ * vmw_kms_check_topology - Validates topology in drm_atomic_state
  * @dev: DRM device
  * @state: the driver state object
  *
- * This is a simple wrapper around drm_atomic_helper_check_modeset() for
- * us to assign a value to mode->crtc_clock so that
- * drm_calc_timestamping_constants() won't throw an error message
- *
- * RETURNS
- * Zero for success or -errno
+ * Returns:
+ * 0 on success otherwise negative error code
  */
-static int
-vmw_kms_atomic_check_modeset(struct drm_device *dev,
-			     struct drm_atomic_state *state)
+static int vmw_kms_check_topology(struct drm_device *dev,
+				  struct drm_atomic_state *state)
 {
-	struct drm_crtc_state *new_crtc_state;
-	struct drm_plane_state *new_plane_state;
-	struct drm_plane *plane;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_rect *rects;
 	struct drm_crtc *crtc;
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	int i, ret, cpp = 0;
+	uint32_t i;
+	int ret = 0;
 
-	ret = drm_atomic_helper_check(dev, state);
+	rects = kcalloc(dev->mode_config.num_crtc, sizeof(struct drm_rect),
+			GFP_KERNEL);
+	if (!rects)
+		return -ENOMEM;
 
-	/* If this is not a STDU, then no more checking is necessary */
-	if (ret || dev_priv->active_display_unit != vmw_du_screen_target)
-		return ret;
+	drm_for_each_crtc(crtc, dev) {
+		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+		struct drm_crtc_state *crtc_state = crtc->state;
 
-	for_each_new_plane_in_state(state, plane, new_plane_state, i) {
-		if (new_plane_state->fb) {
-			int current_cpp = new_plane_state->fb->pitches[0] /
-					  new_plane_state->fb->width;
+		i = drm_crtc_index(crtc);
 
-			if (cpp == 0)
-				cpp = current_cpp;
-			else if (current_cpp != cpp)
-				return -EINVAL;
+		if (crtc_state && crtc_state->enable) {
+			/*
+			 * There could be a race condition with update of gui_x/
+			 * gui_y. Those are protected by dev->mode_config.mutex.
+			 */
+			rects[i].x1 = du->gui_x;
+			rects[i].y1 = du->gui_y;
+			rects[i].x2 = du->gui_x + crtc_state->mode.hdisplay;
+			rects[i].y2 = du->gui_y + crtc_state->mode.vdisplay;
 		}
 	}
 
-	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
-		unsigned long requested_bb_mem = 0;
+	/* Determine change to topology due to new atomic state */
+	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
+				      new_crtc_state, i) {
+		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+
+		if (!new_crtc_state->enable && old_crtc_state->enable) {
+			rects[i].x1 = 0;
+			rects[i].y1 = 0;
+			rects[i].x2 = 0;
+			rects[i].y2 = 0;
+		}
 
-		if (drm_atomic_crtc_needs_modeset(new_crtc_state)) {
-			requested_bb_mem += new_crtc_state->mode.hdisplay *
-					    new_crtc_state->mode.vdisplay *
-					    cpp;
+		if (new_crtc_state->enable) {
+			/* If display unit is not active cannot enable CRTC */
+			if (!du->pref_active) {
+				ret = -EINVAL;
+				goto clean;
+			}
 
-			if (requested_bb_mem > dev_priv->prim_bb_mem)
-				return -EINVAL;
+			rects[i].x1 = du->gui_x;
+			rects[i].y1 = du->gui_y;
+			rects[i].x2 = du->gui_x + new_crtc_state->mode.hdisplay;
+			rects[i].y2 = du->gui_y + new_crtc_state->mode.vdisplay;
 		}
 	}
 
+	ret = vmw_kms_check_display_memory(dev, dev->mode_config.num_crtc,
+					   rects);
+
+clean:
+	kfree(rects);
 	return ret;
 }
 
+/**
+ * vmw_kms_atomic_check_modeset- validate state object for modeset changes
+ *
+ * @dev: DRM device
+ * @state: the driver state object
+ *
+ * This is a simple wrapper around drm_atomic_helper_check_modeset() for
+ * us to assign a value to mode->crtc_clock so that
+ * drm_calc_timestamping_constants() won't throw an error message
+ *
+ * Returns:
+ * Zero for success or -errno
+ */
+static int
+vmw_kms_atomic_check_modeset(struct drm_device *dev,
+			     struct drm_atomic_state *state)
+{
+	int ret;
+
+	ret = drm_atomic_helper_check(dev, state);
+	if (ret)
+		return ret;
+
+	return vmw_kms_check_topology(dev, state);
+}
+
 static const struct drm_mode_config_funcs vmw_kms_funcs = {
 	.fb_create = vmw_kms_fb_create,
 	.atomic_check = vmw_kms_atomic_check_modeset,
-- 
cgit v1.2.3


From 5e24133ea3dfb89fd0cf28cd7a845b66fa680b69 Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 11:17:16 +0200
Subject: drm/vmwgfx: Use modeset display memory validation for layout ioctl

Call the same display memory validation function which is used by
modeset_check. This ensure consistency that kernel change preferred
mode/topology only if supported.

Also change the internal function to use drm_rect instead of
drm_vmw_rect.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 120 +++++++++++++++---------------------
 1 file changed, 51 insertions(+), 69 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index a7c9a017fc3c..387bb39de839 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1968,13 +1968,15 @@ void vmw_disable_vblank(struct drm_device *dev, unsigned int pipe)
 {
 }
 
-
-/*
- * Small shared kms functions.
+/**
+ * vmw_du_update_layout - Update the display unit with topology from resolution
+ * plugin and generate DRM uevent
+ * @dev_priv: device private
+ * @num_rects: number of drm_rect in rects
+ * @rects: toplogy to update
  */
-
-static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
-			 struct drm_vmw_rect *rects)
+static int vmw_du_update_layout(struct vmw_private *dev_priv,
+				unsigned int num_rects, struct drm_rect *rects)
 {
 	struct drm_device *dev = dev_priv->dev;
 	struct vmw_display_unit *du;
@@ -1982,26 +1984,14 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv, unsigned num,
 
 	mutex_lock(&dev->mode_config.mutex);
 
-#if 0
-	{
-		unsigned int i;
-
-		DRM_INFO("%s: new layout ", __func__);
-		for (i = 0; i < num; i++)
-			DRM_INFO("(%i, %i %ux%u) ", rects[i].x, rects[i].y,
-				 rects[i].w, rects[i].h);
-		DRM_INFO("\n");
-	}
-#endif
-
 	list_for_each_entry(con, &dev->mode_config.connector_list, head) {
 		du = vmw_connector_to_du(con);
-		if (num > du->unit) {
-			du->pref_width = rects[du->unit].w;
-			du->pref_height = rects[du->unit].h;
+		if (num_rects > du->unit) {
+			du->pref_width = drm_rect_width(&rects[du->unit]);
+			du->pref_height = drm_rect_height(&rects[du->unit]);
 			du->pref_active = true;
-			du->gui_x = rects[du->unit].x;
-			du->gui_y = rects[du->unit].y;
+			du->gui_x = rects[du->unit].x1;
+			du->gui_y = rects[du->unit].y1;
 			drm_object_property_set_value
 			  (&con->base, dev->mode_config.suggested_x_property,
 			   du->gui_x);
@@ -2322,7 +2312,25 @@ vmw_du_connector_atomic_get_property(struct drm_connector *connector,
 	return 0;
 }
 
-
+/**
+ * vmw_kms_update_layout_ioctl - Handler for DRM_VMW_UPDATE_LAYOUT ioctl
+ * @dev: drm device for the ioctl
+ * @data: data pointer for the ioctl
+ * @file_priv: drm file for the ioctl call
+ *
+ * Update preferred topology of display unit as per ioctl request. The topology
+ * is expressed as array of drm_vmw_rect.
+ * e.g.
+ * [0 0 640 480] [640 0 800 600] [0 480 640 480]
+ *
+ * NOTE:
+ * The x and y offset (upper left) in drm_vmw_rect cannot be less than 0. Beside
+ * device limit on topology, x + w and y + h (lower right) cannot be greater
+ * than INT_MAX. So topology beyond these limits will return with error.
+ *
+ * Returns:
+ * Zero on success, negative errno on failure.
+ */
 int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
@@ -2331,15 +2339,12 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		(struct drm_vmw_update_layout_arg *)data;
 	void __user *user_rects;
 	struct drm_vmw_rect *rects;
+	struct drm_rect *drm_rects;
 	unsigned rects_size;
-	int ret;
-	int i;
-	u64 total_pixels = 0;
-	struct drm_mode_config *mode_config = &dev->mode_config;
-	struct drm_vmw_rect bounding_box = {0};
+	int ret, i;
 
 	if (!arg->num_outputs) {
-		struct drm_vmw_rect def_rect = {0, 0, 800, 600};
+		struct drm_rect def_rect = {0, 0, 800, 600};
 		vmw_du_update_layout(dev_priv, 1, &def_rect);
 		return 0;
 	}
@@ -2358,52 +2363,29 @@ int vmw_kms_update_layout_ioctl(struct drm_device *dev, void *data,
 		goto out_free;
 	}
 
-	for (i = 0; i < arg->num_outputs; ++i) {
-		if (rects[i].x < 0 ||
-		    rects[i].y < 0 ||
-		    rects[i].x + rects[i].w > mode_config->max_width ||
-		    rects[i].y + rects[i].h > mode_config->max_height) {
-			DRM_ERROR("Invalid GUI layout.\n");
-			ret = -EINVAL;
-			goto out_free;
-		}
-
-		/*
-		 * bounding_box.w and bunding_box.h are used as
-		 * lower-right coordinates
-		 */
-		if (rects[i].x + rects[i].w > bounding_box.w)
-			bounding_box.w = rects[i].x + rects[i].w;
-
-		if (rects[i].y + rects[i].h > bounding_box.h)
-			bounding_box.h = rects[i].y + rects[i].h;
+	drm_rects = (struct drm_rect *)rects;
 
-		total_pixels += (u64) rects[i].w * (u64) rects[i].h;
-	}
+	for (i = 0; i < arg->num_outputs; i++) {
+		struct drm_vmw_rect curr_rect;
 
-	if (dev_priv->active_display_unit == vmw_du_screen_target) {
-		/*
-		 * For Screen Targets, the limits for a toplogy are:
-		 *	1. Bounding box (assuming 32bpp) must be < prim_bb_mem
-		 *      2. Total pixels (assuming 32bpp) must be < prim_bb_mem
-		 */
-		u64 bb_mem    = (u64) bounding_box.w * bounding_box.h * 4;
-		u64 pixel_mem = total_pixels * 4;
-
-		if (bb_mem > dev_priv->prim_bb_mem) {
-			DRM_ERROR("Topology is beyond supported limits.\n");
-			ret = -EINVAL;
+		/* Verify user-space for overflow as kernel use drm_rect */
+		if ((rects[i].x + rects[i].w > INT_MAX) ||
+		    (rects[i].y + rects[i].h > INT_MAX)) {
+			ret = -ERANGE;
 			goto out_free;
 		}
 
-		if (pixel_mem > dev_priv->prim_bb_mem) {
-			DRM_ERROR("Combined output size too large\n");
-			ret = -EINVAL;
-			goto out_free;
-		}
+		curr_rect = rects[i];
+		drm_rects[i].x1 = curr_rect.x;
+		drm_rects[i].y1 = curr_rect.y;
+		drm_rects[i].x2 = curr_rect.x + curr_rect.w;
+		drm_rects[i].y2 = curr_rect.y + curr_rect.h;
 	}
 
-	vmw_du_update_layout(dev_priv, arg->num_outputs, rects);
+	ret = vmw_kms_check_display_memory(dev, arg->num_outputs, drm_rects);
+
+	if (ret == 0)
+		vmw_du_update_layout(dev_priv, arg->num_outputs, drm_rects);
 
 out_free:
 	kfree(rects);
-- 
cgit v1.2.3


From 7e14eabca82ec75da5200769989d396da46033ee Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 11:23:55 +0200
Subject: drm/vmwgfx: Perform memory validations only when need full modeset.

For cases when full modeset is not requested like page-flip, skip
memory validation as the topology is not changed.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 387bb39de839..3605ac1702c2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1670,13 +1670,32 @@ static int
 vmw_kms_atomic_check_modeset(struct drm_device *dev,
 			     struct drm_atomic_state *state)
 {
-	int ret;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	bool need_modeset = false;
+	int i, ret;
 
 	ret = drm_atomic_helper_check(dev, state);
 	if (ret)
 		return ret;
 
-	return vmw_kms_check_topology(dev, state);
+	if (!state->allow_modeset)
+		return ret;
+
+	/*
+	 * Legacy path do not set allow_modeset properly like
+	 * @drm_atomic_helper_update_plane, This will result in unnecessary call
+	 * to vmw_kms_check_topology. So extra set of check.
+	 */
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		if (drm_atomic_crtc_needs_modeset(crtc_state))
+			need_modeset = true;
+	}
+
+	if (need_modeset)
+		return vmw_kms_check_topology(dev, state);
+
+	return ret;
 }
 
 static const struct drm_mode_config_funcs vmw_kms_funcs = {
-- 
cgit v1.2.3


From 018f60b26602bb41b33139da3408224e36dfe02d Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 11:26:59 +0200
Subject: drm/vmwgfx: Remove primary memory validation against mode while
 creating fb

This validation is not required because user-space will send create_fb
request once the memory is allocated. This check should be performed
during mode-setting.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 3605ac1702c2..f0ae0b2ee2e6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1433,19 +1433,6 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
 	struct ttm_base_object *user_obj;
 	int ret;
 
-	/**
-	 * This code should be conditioned on Screen Objects not being used.
-	 * If screen objects are used, we can allocate a GMR to hold the
-	 * requested framebuffer.
-	 */
-
-	if (!vmw_kms_validate_mode_vram(dev_priv,
-					mode_cmd->pitches[0],
-					mode_cmd->height)) {
-		DRM_ERROR("Requested mode exceed bounding box limit.\n");
-		return ERR_PTR(-ENOMEM);
-	}
-
 	/*
 	 * Take a reference on the user object of the resource
 	 * backing the kms fb. This ensures that user-space handle
-- 
cgit v1.2.3


From b89e5ff9eeeb8b1fe3d2d7477fb9e1c1aed5dd5b Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 11:32:29 +0200
Subject: drm/vmwgfx: Use a mutex to protect gui positioning in
 vmw_display_unit

To avoid race condition between update_layout ioctl and modeset ioctl
for access to gui_x/y positioning added a new mutex
requested_layout_mutex.

Also used drm_for_each_connector_iter to iterate over connector list.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c |  1 +
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h |  9 +++++++++
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c | 38 ++++++++++++++++++++++++++-----------
 3 files changed, 37 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 4f18304226bc..45dfff7733d6 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -644,6 +644,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	mutex_init(&dev_priv->cmdbuf_mutex);
 	mutex_init(&dev_priv->release_mutex);
 	mutex_init(&dev_priv->binding_mutex);
+	mutex_init(&dev_priv->requested_layout_mutex);
 	mutex_init(&dev_priv->global_kms_state_mutex);
 	rwlock_init(&dev_priv->resource_lock);
 	ttm_lock_init(&dev_priv->reservation_sem);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 769d72fabb56..a38318c3efe4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -411,6 +411,15 @@ struct vmw_private {
 
 	uint32_t num_displays;
 
+	/*
+	 * Currently requested_layout_mutex is used to protect the gui
+	 * positionig state in display unit. With that use case currently this
+	 * mutex is only taken during layout ioctl and atomic check_modeset.
+	 * Other display unit state can be protected with this mutex but that
+	 * needs careful consideration.
+	 */
+	struct mutex requested_layout_mutex;
+
 	/*
 	 * Framebuffer info.
 	 */
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index f0ae0b2ee2e6..a592d10e5c76 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1577,6 +1577,7 @@ static int vmw_kms_check_display_memory(struct drm_device *dev,
 static int vmw_kms_check_topology(struct drm_device *dev,
 				  struct drm_atomic_state *state)
 {
+	struct vmw_private *dev_priv = vmw_priv(dev);
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct drm_rect *rects;
 	struct drm_crtc *crtc;
@@ -1588,6 +1589,8 @@ static int vmw_kms_check_topology(struct drm_device *dev,
 	if (!rects)
 		return -ENOMEM;
 
+	mutex_lock(&dev_priv->requested_layout_mutex);
+
 	drm_for_each_crtc(crtc, dev) {
 		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
 		struct drm_crtc_state *crtc_state = crtc->state;
@@ -1595,10 +1598,6 @@ static int vmw_kms_check_topology(struct drm_device *dev,
 		i = drm_crtc_index(crtc);
 
 		if (crtc_state && crtc_state->enable) {
-			/*
-			 * There could be a race condition with update of gui_x/
-			 * gui_y. Those are protected by dev->mode_config.mutex.
-			 */
 			rects[i].x1 = du->gui_x;
 			rects[i].y1 = du->gui_y;
 			rects[i].x2 = du->gui_x + crtc_state->mode.hdisplay;
@@ -1636,6 +1635,7 @@ static int vmw_kms_check_topology(struct drm_device *dev,
 					   rects);
 
 clean:
+	mutex_unlock(&dev_priv->requested_layout_mutex);
 	kfree(rects);
 	return ret;
 }
@@ -1987,10 +1987,14 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv,
 	struct drm_device *dev = dev_priv->dev;
 	struct vmw_display_unit *du;
 	struct drm_connector *con;
+	struct drm_connector_list_iter conn_iter;
 
-	mutex_lock(&dev->mode_config.mutex);
-
-	list_for_each_entry(con, &dev->mode_config.connector_list, head) {
+	/*
+	 * Currently only gui_x/y is protected with requested_layout_mutex.
+	 */
+	mutex_lock(&dev_priv->requested_layout_mutex);
+	drm_connector_list_iter_begin(dev, &conn_iter);
+	drm_for_each_connector_iter(con, &conn_iter) {
 		du = vmw_connector_to_du(con);
 		if (num_rects > du->unit) {
 			du->pref_width = drm_rect_width(&rects[du->unit]);
@@ -1998,6 +2002,21 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv,
 			du->pref_active = true;
 			du->gui_x = rects[du->unit].x1;
 			du->gui_y = rects[du->unit].y1;
+		} else {
+			du->pref_width = 800;
+			du->pref_height = 600;
+			du->pref_active = false;
+			du->gui_x = 0;
+			du->gui_y = 0;
+		}
+	}
+	drm_connector_list_iter_end(&conn_iter);
+	mutex_unlock(&dev_priv->requested_layout_mutex);
+
+	mutex_lock(&dev->mode_config.mutex);
+	list_for_each_entry(con, &dev->mode_config.connector_list, head) {
+		du = vmw_connector_to_du(con);
+		if (num_rects > du->unit) {
 			drm_object_property_set_value
 			  (&con->base, dev->mode_config.suggested_x_property,
 			   du->gui_x);
@@ -2005,9 +2024,6 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv,
 			  (&con->base, dev->mode_config.suggested_y_property,
 			   du->gui_y);
 		} else {
-			du->pref_width = 800;
-			du->pref_height = 600;
-			du->pref_active = false;
 			drm_object_property_set_value
 			  (&con->base, dev->mode_config.suggested_x_property,
 			   0);
@@ -2017,8 +2033,8 @@ static int vmw_du_update_layout(struct vmw_private *dev_priv,
 		}
 		con->status = vmw_du_connector_detect(con, true);
 	}
-
 	mutex_unlock(&dev->mode_config.mutex);
+
 	drm_sysfs_hotplug_event(dev);
 
 	return 0;
-- 
cgit v1.2.3


From 3e79ecdad8897dad4d311576989b6856dbcb958e Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 11:34:26 +0200
Subject: drm/vmwgfx: Add gui_x/y to vmw_connector_state

As gui_x/y positioning is display unit is protected by
requested_layout_mutex adding vmw_connector_state copy of the same and
modeset commit will refer the state copy to sync with modeset_check
state.

v2: Tested with CONFIG_PROVE_LOCKING enabled.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c  | 37 +++++++++++++++++++++++++----------
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.h  | 18 +++++++++++++++++
 drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c | 38 ++++++++++++++++++++++--------------
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c | 29 ++++++++++++++++-----------
 4 files changed, 86 insertions(+), 36 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index a592d10e5c76..0fb363458ab5 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1609,26 +1609,43 @@ static int vmw_kms_check_topology(struct drm_device *dev,
 	for_each_oldnew_crtc_in_state(state, crtc, old_crtc_state,
 				      new_crtc_state, i) {
 		struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+		struct drm_connector *connector;
+		struct drm_connector_state *conn_state;
+		struct vmw_connector_state *vmw_conn_state;
 
 		if (!new_crtc_state->enable && old_crtc_state->enable) {
 			rects[i].x1 = 0;
 			rects[i].y1 = 0;
 			rects[i].x2 = 0;
 			rects[i].y2 = 0;
+			continue;
 		}
 
-		if (new_crtc_state->enable) {
-			/* If display unit is not active cannot enable CRTC */
-			if (!du->pref_active) {
-				ret = -EINVAL;
-				goto clean;
-			}
+		if (!du->pref_active) {
+			ret = -EINVAL;
+			goto clean;
+		}
 
-			rects[i].x1 = du->gui_x;
-			rects[i].y1 = du->gui_y;
-			rects[i].x2 = du->gui_x + new_crtc_state->mode.hdisplay;
-			rects[i].y2 = du->gui_y + new_crtc_state->mode.vdisplay;
+		/*
+		 * For vmwgfx each crtc has only one connector attached and it
+		 * is not changed so don't really need to check the
+		 * crtc->connector_mask and iterate over it.
+		 */
+		connector = &du->connector;
+		conn_state = drm_atomic_get_connector_state(state, connector);
+		if (IS_ERR(conn_state)) {
+			ret = PTR_ERR(conn_state);
+			goto clean;
 		}
+
+		vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
+		vmw_conn_state->gui_x = du->gui_x;
+		vmw_conn_state->gui_y = du->gui_y;
+
+		rects[i].x1 = du->gui_x;
+		rects[i].y1 = du->gui_y;
+		rects[i].x2 = du->gui_x + new_crtc_state->mode.hdisplay;
+		rects[i].y2 = du->gui_y + new_crtc_state->mode.vdisplay;
 	}
 
 	ret = vmw_kms_check_display_memory(dev, dev->mode_config.num_crtc,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
index ff1caed38f94..1f2b01862652 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
@@ -192,6 +192,24 @@ struct vmw_connector_state {
 	struct drm_connector_state base;
 
 	bool is_implicit;
+
+	/**
+	 * @gui_x:
+	 *
+	 * vmwgfx connector property representing the x position of this display
+	 * unit (connector is synonymous to display unit) in overall topology.
+	 * This is what the device expect as xRoot while creating screen.
+	 */
+	int gui_x;
+
+	/**
+	 * @gui_y:
+	 *
+	 * vmwgfx connector property representing the y position of this display
+	 * unit (connector is synonymous to display unit) in overall topology.
+	 * This is what the device expect as yRoot while creating screen.
+	 */
+	int gui_y;
 };
 
 /**
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 74dfd4621b7e..df21d5a6f84a 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -109,7 +109,7 @@ static void vmw_sou_crtc_destroy(struct drm_crtc *crtc)
  */
 static int vmw_sou_fifo_create(struct vmw_private *dev_priv,
 			       struct vmw_screen_object_unit *sou,
-			       uint32_t x, uint32_t y,
+			       int x, int y,
 			       struct drm_display_mode *mode)
 {
 	size_t fifo_size;
@@ -139,13 +139,8 @@ static int vmw_sou_fifo_create(struct vmw_private *dev_priv,
 		(sou->base.unit == 0 ? SVGA_SCREEN_IS_PRIMARY : 0);
 	cmd->obj.size.width = mode->hdisplay;
 	cmd->obj.size.height = mode->vdisplay;
-	if (sou->base.is_implicit) {
-		cmd->obj.root.x = x;
-		cmd->obj.root.y = y;
-	} else {
-		cmd->obj.root.x = sou->base.gui_x;
-		cmd->obj.root.y = sou->base.gui_y;
-	}
+	cmd->obj.root.x = x;
+	cmd->obj.root.y = y;
 	sou->base.set_gui_x = cmd->obj.root.x;
 	sou->base.set_gui_y = cmd->obj.root.y;
 
@@ -222,12 +217,11 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	struct vmw_plane_state *vps;
 	int ret;
 
-
-	sou      = vmw_crtc_to_sou(crtc);
+	sou = vmw_crtc_to_sou(crtc);
 	dev_priv = vmw_priv(crtc->dev);
-	ps       = crtc->primary->state;
-	fb       = ps->fb;
-	vps      = vmw_plane_state_to_vps(ps);
+	ps = crtc->primary->state;
+	fb = ps->fb;
+	vps = vmw_plane_state_to_vps(ps);
 
 	vfb = (fb) ? vmw_framebuffer_to_vfb(fb) : NULL;
 
@@ -240,11 +234,25 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	}
 
 	if (vfb) {
+		struct drm_connector_state *conn_state;
+		struct vmw_connector_state *vmw_conn_state;
+		int x, y;
+
 		sou->buffer = vps->bo;
 		sou->buffer_size = vps->bo_size;
 
-		ret = vmw_sou_fifo_create(dev_priv, sou, crtc->x, crtc->y,
-					  &crtc->mode);
+		if (sou->base.is_implicit) {
+			x = crtc->x;
+			y = crtc->y;
+		} else {
+			conn_state = sou->base.connector.state;
+			vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
+
+			x = vmw_conn_state->gui_x;
+			y = vmw_conn_state->gui_y;
+		}
+
+		ret = vmw_sou_fifo_create(dev_priv, sou, x, y, &crtc->mode);
 		if (ret)
 			DRM_ERROR("Failed to define Screen Object %dx%d\n",
 				  crtc->x, crtc->y);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 537df9034008..15f2cb2a151b 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -178,13 +178,9 @@ static int vmw_stdu_define_st(struct vmw_private *dev_priv,
 	cmd->body.height = mode->vdisplay;
 	cmd->body.flags  = (0 == cmd->body.stid) ? SVGA_STFLAG_PRIMARY : 0;
 	cmd->body.dpi    = 0;
-	if (stdu->base.is_implicit) {
-		cmd->body.xRoot  = crtc_x;
-		cmd->body.yRoot  = crtc_y;
-	} else {
-		cmd->body.xRoot  = stdu->base.gui_x;
-		cmd->body.yRoot  = stdu->base.gui_y;
-	}
+	cmd->body.xRoot  = crtc_x;
+	cmd->body.yRoot  = crtc_y;
+
 	stdu->base.set_gui_x = cmd->body.xRoot;
 	stdu->base.set_gui_y = cmd->body.yRoot;
 
@@ -374,11 +370,14 @@ static void vmw_stdu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
 	struct vmw_private *dev_priv;
 	struct vmw_screen_target_display_unit *stdu;
-	int ret;
-
+	struct drm_connector_state *conn_state;
+	struct vmw_connector_state *vmw_conn_state;
+	int x, y, ret;
 
-	stdu     = vmw_crtc_to_stdu(crtc);
+	stdu = vmw_crtc_to_stdu(crtc);
 	dev_priv = vmw_priv(crtc->dev);
+	conn_state = stdu->base.connector.state;
+	vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
 
 	if (stdu->defined) {
 		ret = vmw_stdu_bind_st(dev_priv, stdu, NULL);
@@ -397,8 +396,16 @@ static void vmw_stdu_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	if (!crtc->state->enable)
 		return;
 
+	if (stdu->base.is_implicit) {
+		x = crtc->x;
+		y = crtc->y;
+	} else {
+		x = vmw_conn_state->gui_x;
+		y = vmw_conn_state->gui_y;
+	}
+
 	vmw_svga_enable(dev_priv);
-	ret = vmw_stdu_define_st(dev_priv, stdu, &crtc->mode, crtc->x, crtc->y);
+	ret = vmw_stdu_define_st(dev_priv, stdu, &crtc->mode, x, y);
 
 	if (ret)
 		DRM_ERROR("Failed to define Screen Target of size %dx%d\n",
-- 
cgit v1.2.3


From 3fbeccf8ceb1651b376a14bfe1005d518a4d8fa0 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Wed, 20 Jun 2018 11:38:48 +0200
Subject: drm/vmwgfx: Improve on host message error messages

Make sure the error messages are a bit more descriptive, so that
a log reader may understand what's gone wrong.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index 21d746bdc922..a72268e97042 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -234,7 +234,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 
 		if ((HIGH_WORD(ecx) & MESSAGE_STATUS_SUCCESS) == 0 ||
 		    (HIGH_WORD(ecx) & MESSAGE_STATUS_HB) == 0) {
-			DRM_ERROR("Failed to get reply size\n");
+			DRM_ERROR("Failed to get reply size for host message.\n");
 			return -EINVAL;
 		}
 
@@ -245,7 +245,7 @@ static int vmw_recv_msg(struct rpc_channel *channel, void **msg,
 		reply_len = ebx;
 		reply     = kzalloc(reply_len + 1, GFP_KERNEL);
 		if (!reply) {
-			DRM_ERROR("Cannot allocate memory for reply\n");
+			DRM_ERROR("Cannot allocate memory for host message reply.\n");
 			return -ENOMEM;
 		}
 
@@ -338,7 +338,8 @@ int vmw_host_get_guestinfo(const char *guest_info_param,
 
 	msg = kasprintf(GFP_KERNEL, "info-get %s", guest_info_param);
 	if (!msg) {
-		DRM_ERROR("Cannot allocate memory to get %s", guest_info_param);
+		DRM_ERROR("Cannot allocate memory to get guest info \"%s\".",
+			  guest_info_param);
 		return -ENOMEM;
 	}
 
@@ -374,7 +375,7 @@ out_msg:
 out_open:
 	*length = 0;
 	kfree(msg);
-	DRM_ERROR("Failed to get %s", guest_info_param);
+	DRM_ERROR("Failed to get guest info \"%s\".", guest_info_param);
 
 	return -EINVAL;
 }
@@ -403,7 +404,7 @@ int vmw_host_log(const char *log)
 
 	msg = kasprintf(GFP_KERNEL, "log %s", log);
 	if (!msg) {
-		DRM_ERROR("Cannot allocate memory for log message\n");
+		DRM_ERROR("Cannot allocate memory for host log message.\n");
 		return -ENOMEM;
 	}
 
@@ -422,7 +423,7 @@ out_msg:
 	vmw_close_channel(&channel);
 out_open:
 	kfree(msg);
-	DRM_ERROR("Failed to send log\n");
+	DRM_ERROR("Failed to send host log message.\n");
 
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From 14dba7178491e2bc411dc2e4542295709c1fb9e6 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Wed, 20 Jun 2018 11:51:02 +0200
Subject: drm/vmwgfx: Reorganize the fence wait loop

Reorganize the fence wait loop somewhat to make it look more like the
examples in set_current_state() kerneldoc, and add some code comments.

Also if we're about to time out, make sure we check again whether the fence
is actually signaled.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_fence.c | 38 ++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
index 9ed544f8958f..ea41d74d8341 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
@@ -175,7 +175,6 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	struct vmw_private *dev_priv = fman->dev_priv;
 	struct vmwgfx_wait_cb cb;
 	long ret = timeout;
-	unsigned long irq_flags;
 
 	if (likely(vmw_fence_obj_signaled(fence)))
 		return timeout;
@@ -183,7 +182,7 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	vmw_fifo_ping_host(dev_priv, SVGA_SYNC_GENERIC);
 	vmw_seqno_waiter_add(dev_priv);
 
-	spin_lock_irqsave(f->lock, irq_flags);
+	spin_lock(f->lock);
 
 	if (intr && signal_pending(current)) {
 		ret = -ERESTARTSYS;
@@ -194,30 +193,45 @@ static long vmw_fence_wait(struct dma_fence *f, bool intr, signed long timeout)
 	cb.task = current;
 	list_add(&cb.base.node, &f->cb_list);
 
-	while (ret > 0) {
+	for (;;) {
 		__vmw_fences_update(fman);
-		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags))
-			break;
 
+		/*
+		 * We can use the barrier free __set_current_state() since
+		 * DMA_FENCE_FLAG_SIGNALED_BIT + wakeup is protected by the
+		 * fence spinlock.
+		 */
 		if (intr)
 			__set_current_state(TASK_INTERRUPTIBLE);
 		else
 			__set_current_state(TASK_UNINTERRUPTIBLE);
-		spin_unlock_irqrestore(f->lock, irq_flags);
 
-		ret = schedule_timeout(ret);
+		if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &f->flags)) {
+			if (ret == 0 && timeout > 0)
+				ret = 1;
+			break;
+		}
 
-		spin_lock_irqsave(f->lock, irq_flags);
-		if (ret > 0 && intr && signal_pending(current))
+		if (intr && signal_pending(current)) {
 			ret = -ERESTARTSYS;
-	}
+			break;
+		}
 
+		if (ret == 0)
+			break;
+
+		spin_unlock(f->lock);
+
+		ret = schedule_timeout(ret);
+
+		spin_lock(f->lock);
+	}
+	__set_current_state(TASK_RUNNING);
 	if (!list_empty(&cb.base.node))
 		list_del(&cb.base.node);
-	__set_current_state(TASK_RUNNING);
 
 out:
-	spin_unlock_irqrestore(f->lock, irq_flags);
+	spin_unlock(f->lock);
 
 	vmw_seqno_waiter_remove(dev_priv);
 
-- 
cgit v1.2.3


From 6ff67ae759a0f839efeab40424c9dc544223f900 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Thu, 21 Jun 2018 09:39:21 +0200
Subject: drm/vmwgfx: Fix host message module function declarations

Make the host message module function declarations similar to the other
declarations in vmwgfx_drv.h and include the header in vmwgfx_msg.c

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h | 11 +++++------
 drivers/gpu/drm/vmwgfx/vmwgfx_msg.c |  1 +
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index a38318c3efe4..a3a0826958a1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1230,6 +1230,11 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
 		    u32 w, u32 h,
 		    struct vmw_diff_cpy *diff);
 
+/* Host messaging -vmwgfx_msg.c: */
+int vmw_host_get_guestinfo(const char *guest_info_param,
+			   char *buffer, size_t *length);
+int vmw_host_log(const char *log);
+
 /**
  * Inline helper functions
  */
@@ -1309,10 +1314,4 @@ static inline void vmw_mmio_write(u32 value, u32 *addr)
 {
 	WRITE_ONCE(*addr, value);
 }
-
-/**
- * Add vmw_msg module function
- */
-extern int vmw_host_log(const char *log);
-
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
index a72268e97042..3549e6bd4178 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_msg.c
@@ -31,6 +31,7 @@
 #include <linux/frame.h>
 #include <asm/hypervisor.h>
 #include <drm/drmP.h>
+#include "vmwgfx_drv.h"
 #include "vmwgfx_msg.h"
 
 
-- 
cgit v1.2.3


From 812a954b787ab5a91d62e597a36351628b08d079 Mon Sep 17 00:00:00 2001
From: Thomas Hellstrom <thellstrom@vmware.com>
Date: Thu, 21 Jun 2018 09:44:42 +0200
Subject: drm/vmwgfx: Remove an obsolete __le32 conversion

We've long ago given up on enforcing the device format is always little
endian, so remove a leftover conversion.

Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Deepak Rawat <drawat@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index f2af53613803..e90f8d39de53 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1072,7 +1072,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		cmd2->header.size = cmd_len;
 		cmd2->body.sid = srf->res.id;
 		cmd2->body.surfaceFlags = srf->flags;
-		cmd2->body.format = cpu_to_le32(srf->format);
+		cmd2->body.format = srf->format;
 		cmd2->body.numMipLevels = srf->mip_levels[0];
 		cmd2->body.multisampleCount = srf->multisample_count;
 		cmd2->body.autogenFilter = srf->autogen_filter;
@@ -1085,7 +1085,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		cmd->header.size = cmd_len;
 		cmd->body.sid = srf->res.id;
 		cmd->body.surfaceFlags = srf->flags;
-		cmd->body.format = cpu_to_le32(srf->format);
+		cmd->body.format = srf->format;
 		cmd->body.numMipLevels = srf->mip_levels[0];
 		cmd->body.multisampleCount = srf->multisample_count;
 		cmd->body.autogenFilter = srf->autogen_filter;
-- 
cgit v1.2.3


From 63b8add24e1a99d7218c904f258623e7c07ce99e Mon Sep 17 00:00:00 2001
From: Elaine Zhang <zhangqing@rock-chips.com>
Date: Fri, 15 Jun 2018 10:16:49 +0800
Subject: clk: rockchip: add dt-binding header for px30

Add the dt-bindings header for the px30, that gets shared between
the clock controller and the clock references in the dts.
Add softreset ID for px30.

Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 include/dt-bindings/clock/px30-cru.h | 389 +++++++++++++++++++++++++++++++++++
 1 file changed, 389 insertions(+)
 create mode 100644 include/dt-bindings/clock/px30-cru.h

diff --git a/include/dt-bindings/clock/px30-cru.h b/include/dt-bindings/clock/px30-cru.h
new file mode 100644
index 000000000000..00101479f7c4
--- /dev/null
+++ b/include/dt-bindings/clock/px30-cru.h
@@ -0,0 +1,389 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _DT_BINDINGS_CLK_ROCKCHIP_PX30_H
+#define _DT_BINDINGS_CLK_ROCKCHIP_PX30_H
+
+/* core clocks */
+#define PLL_APLL		1
+#define PLL_DPLL		2
+#define PLL_CPLL		3
+#define PLL_NPLL		4
+#define APLL_BOOST_H		5
+#define APLL_BOOST_L		6
+#define ARMCLK			7
+
+/* sclk gates (special clocks) */
+#define USB480M			14
+#define SCLK_PDM		15
+#define SCLK_I2S0_TX		16
+#define SCLK_I2S0_TX_OUT	17
+#define SCLK_I2S0_RX		18
+#define SCLK_I2S0_RX_OUT	19
+#define SCLK_I2S1		20
+#define SCLK_I2S1_OUT		21
+#define SCLK_I2S2		22
+#define SCLK_I2S2_OUT		23
+#define SCLK_UART1		24
+#define SCLK_UART2		25
+#define SCLK_UART3		26
+#define SCLK_UART4		27
+#define SCLK_UART5		28
+#define SCLK_I2C0		29
+#define SCLK_I2C1		30
+#define SCLK_I2C2		31
+#define SCLK_I2C3		32
+#define SCLK_I2C4		33
+#define SCLK_PWM0		34
+#define SCLK_PWM1		35
+#define SCLK_SPI0		36
+#define SCLK_SPI1		37
+#define SCLK_TIMER0		38
+#define SCLK_TIMER1		39
+#define SCLK_TIMER2		40
+#define SCLK_TIMER3		41
+#define SCLK_TIMER4		42
+#define SCLK_TIMER5		43
+#define SCLK_TSADC		44
+#define SCLK_SARADC		45
+#define SCLK_OTP		46
+#define SCLK_OTP_USR		47
+#define SCLK_CRYPTO		48
+#define SCLK_CRYPTO_APK		49
+#define SCLK_DDRC		50
+#define SCLK_ISP		51
+#define SCLK_CIF_OUT		52
+#define SCLK_RGA_CORE		53
+#define SCLK_VOPB_PWM		54
+#define SCLK_NANDC		55
+#define SCLK_SDIO		56
+#define SCLK_EMMC		57
+#define SCLK_SFC		58
+#define SCLK_SDMMC		59
+#define SCLK_OTG_ADP		60
+#define SCLK_GMAC_SRC		61
+#define SCLK_GMAC		62
+#define SCLK_GMAC_RX_TX		63
+#define SCLK_MAC_REF		64
+#define SCLK_MAC_REFOUT		65
+#define SCLK_MAC_OUT		66
+#define SCLK_SDMMC_DRV		67
+#define SCLK_SDMMC_SAMPLE	68
+#define SCLK_SDIO_DRV		69
+#define SCLK_SDIO_SAMPLE	70
+#define SCLK_EMMC_DRV		71
+#define SCLK_EMMC_SAMPLE	72
+#define SCLK_GPU		73
+#define SCLK_PVTM		74
+#define SCLK_CORE_VPU		75
+#define SCLK_GMAC_RMII		76
+#define SCLK_UART2_SRC		77
+#define SCLK_NANDC_DIV		78
+#define SCLK_NANDC_DIV50	79
+#define SCLK_SDIO_DIV		80
+#define SCLK_SDIO_DIV50		81
+#define SCLK_EMMC_DIV		82
+#define SCLK_EMMC_DIV50		83
+#define SCLK_DDRCLK		84
+#define SCLK_UART1_SRC		85
+
+/* dclk gates */
+#define DCLK_VOPB		150
+#define DCLK_VOPL		151
+
+/* aclk gates */
+#define ACLK_GPU		170
+#define ACLK_BUS_PRE		171
+#define ACLK_CRYPTO		172
+#define ACLK_VI_PRE		173
+#define ACLK_VO_PRE		174
+#define ACLK_VPU		175
+#define ACLK_PERI_PRE		176
+#define ACLK_GMAC		178
+#define ACLK_CIF		179
+#define ACLK_ISP		180
+#define ACLK_VOPB		181
+#define ACLK_VOPL		182
+#define ACLK_RGA		183
+#define ACLK_GIC		184
+#define ACLK_DCF		186
+#define ACLK_DMAC		187
+#define ACLK_BUS_SRC		188
+#define ACLK_PERI_SRC		189
+
+/* hclk gates */
+#define HCLK_BUS_PRE		240
+#define HCLK_CRYPTO		241
+#define HCLK_VI_PRE		242
+#define HCLK_VO_PRE		243
+#define HCLK_VPU		244
+#define HCLK_PERI_PRE		245
+#define HCLK_MMC_NAND		246
+#define HCLK_SDMMC		247
+#define HCLK_USB		248
+#define HCLK_CIF		249
+#define HCLK_ISP		250
+#define HCLK_VOPB		251
+#define HCLK_VOPL		252
+#define HCLK_RGA		253
+#define HCLK_NANDC		254
+#define HCLK_SDIO		255
+#define HCLK_EMMC		256
+#define HCLK_SFC		257
+#define HCLK_OTG		258
+#define HCLK_HOST		259
+#define HCLK_HOST_ARB		260
+#define HCLK_PDM		261
+#define HCLK_I2S0		262
+#define HCLK_I2S1		263
+#define HCLK_I2S2		264
+
+/* pclk gates */
+#define PCLK_BUS_PRE		320
+#define PCLK_DDR		321
+#define PCLK_VO_PRE		322
+#define PCLK_GMAC		323
+#define PCLK_MIPI_DSI		324
+#define PCLK_MIPIDSIPHY		325
+#define PCLK_MIPICSIPHY		326
+#define PCLK_USB_GRF		327
+#define PCLK_DCF		328
+#define PCLK_UART1		329
+#define PCLK_UART2		330
+#define PCLK_UART3		331
+#define PCLK_UART4		332
+#define PCLK_UART5		333
+#define PCLK_I2C0		334
+#define PCLK_I2C1		335
+#define PCLK_I2C2		336
+#define PCLK_I2C3		337
+#define PCLK_I2C4		338
+#define PCLK_PWM0		339
+#define PCLK_PWM1		340
+#define PCLK_SPI0		341
+#define PCLK_SPI1		342
+#define PCLK_SARADC		343
+#define PCLK_TSADC		344
+#define PCLK_TIMER		345
+#define PCLK_OTP_NS		346
+#define PCLK_WDT_NS		347
+#define PCLK_GPIO1		348
+#define PCLK_GPIO2		349
+#define PCLK_GPIO3		350
+#define PCLK_ISP		351
+#define PCLK_CIF		352
+#define PCLK_OTP_PHY		353
+
+#define CLK_NR_CLKS		(PCLK_OTP_PHY + 1)
+
+/* pmu-clocks indices */
+
+#define PLL_GPLL		1
+
+#define SCLK_RTC32K_PMU		4
+#define SCLK_WIFI_PMU		5
+#define SCLK_UART0_PMU		6
+#define SCLK_PVTM_PMU		7
+#define PCLK_PMU_PRE		8
+#define SCLK_REF24M_PMU		9
+#define SCLK_USBPHY_REF		10
+#define SCLK_MIPIDSIPHY_REF	11
+
+#define XIN24M_DIV		12
+
+#define PCLK_GPIO0_PMU		20
+#define PCLK_UART0_PMU		21
+
+#define CLKPMU_NR_CLKS		(PCLK_UART0_PMU + 1)
+
+/* soft-reset indices */
+#define SRST_CORE0_PO		0
+#define SRST_CORE1_PO		1
+#define SRST_CORE2_PO		2
+#define SRST_CORE3_PO		3
+#define SRST_CORE0		4
+#define SRST_CORE1		5
+#define SRST_CORE2		6
+#define SRST_CORE3		7
+#define SRST_CORE0_DBG		8
+#define SRST_CORE1_DBG		9
+#define SRST_CORE2_DBG		10
+#define SRST_CORE3_DBG		11
+#define SRST_TOPDBG		12
+#define SRST_CORE_NOC		13
+#define SRST_STRC_A		14
+#define SRST_L2C		15
+
+#define SRST_DAP		16
+#define SRST_CORE_PVTM		17
+#define SRST_GPU		18
+#define SRST_GPU_NIU		19
+#define SRST_UPCTL2		20
+#define SRST_UPCTL2_A		21
+#define SRST_UPCTL2_P		22
+#define SRST_MSCH		23
+#define SRST_MSCH_P		24
+#define SRST_DDRMON_P		25
+#define SRST_DDRSTDBY_P		26
+#define SRST_DDRSTDBY		27
+#define SRST_DDRGRF_p		28
+#define SRST_AXI_SPLIT_A	29
+#define SRST_AXI_CMD_A		30
+#define SRST_AXI_CMD_P		31
+
+#define SRST_DDRPHY		32
+#define SRST_DDRPHYDIV		33
+#define SRST_DDRPHY_P		34
+#define SRST_VPU_A		36
+#define SRST_VPU_NIU_A		37
+#define SRST_VPU_H		38
+#define SRST_VPU_NIU_H		39
+#define SRST_VI_NIU_A		40
+#define SRST_VI_NIU_H		41
+#define SRST_ISP_H		42
+#define SRST_ISP		43
+#define SRST_CIF_A		44
+#define SRST_CIF_H		45
+#define SRST_CIF_PCLKIN		46
+#define SRST_MIPICSIPHY_P	47
+
+#define SRST_VO_NIU_A		48
+#define SRST_VO_NIU_H		49
+#define SRST_VO_NIU_P		50
+#define SRST_VOPB_A		51
+#define SRST_VOPB_H		52
+#define SRST_VOPB		53
+#define SRST_PWM_VOPB		54
+#define SRST_VOPL_A		55
+#define SRST_VOPL_H		56
+#define SRST_VOPL		57
+#define SRST_RGA_A		58
+#define SRST_RGA_H		59
+#define SRST_RGA		60
+#define SRST_MIPIDSI_HOST_P	61
+#define SRST_MIPIDSIPHY_P	62
+#define SRST_VPU_CORE		63
+
+#define SRST_PERI_NIU_A		64
+#define SRST_USB_NIU_H		65
+#define SRST_USB2OTG_H		66
+#define SRST_USB2OTG		67
+#define SRST_USB2OTG_ADP	68
+#define SRST_USB2HOST_H		69
+#define SRST_USB2HOST_ARB_H	70
+#define SRST_USB2HOST_AUX_H	71
+#define SRST_USB2HOST_EHCI	72
+#define SRST_USB2HOST		73
+#define SRST_USBPHYPOR		74
+#define SRST_USBPHY_OTG_PORT	75
+#define SRST_USBPHY_HOST_PORT	76
+#define SRST_USBPHY_GRF		77
+#define SRST_CPU_BOOST_P	78
+#define SRST_CPU_BOOST		79
+
+#define SRST_MMC_NAND_NIU_H	80
+#define SRST_SDIO_H		81
+#define SRST_EMMC_H		82
+#define SRST_SFC_H		83
+#define SRST_SFC		84
+#define SRST_SDCARD_NIU_H	85
+#define SRST_SDMMC_H		86
+#define SRST_NANDC_H		89
+#define SRST_NANDC		90
+#define SRST_GMAC_NIU_A		92
+#define SRST_GMAC_NIU_P		93
+#define SRST_GMAC_A		94
+
+#define SRST_PMU_NIU_P		96
+#define SRST_PMU_SGRF_P		97
+#define SRST_PMU_GRF_P		98
+#define SRST_PMU		99
+#define SRST_PMU_MEM_P		100
+#define SRST_PMU_GPIO0_P	101
+#define SRST_PMU_UART0_P	102
+#define SRST_PMU_CRU_P		103
+#define SRST_PMU_PVTM		104
+#define SRST_PMU_UART		105
+#define SRST_PMU_NIU_H		106
+#define SRST_PMU_DDR_FAIL_SAVE	107
+#define SRST_PMU_CORE_PERF_A	108
+#define SRST_PMU_CORE_GRF_P	109
+#define SRST_PMU_GPU_PERF_A	110
+#define SRST_PMU_GPU_GRF_P	111
+
+#define SRST_CRYPTO_NIU_A	112
+#define SRST_CRYPTO_NIU_H	113
+#define SRST_CRYPTO_A		114
+#define SRST_CRYPTO_H		115
+#define SRST_CRYPTO		116
+#define SRST_CRYPTO_APK		117
+#define SRST_BUS_NIU_H		120
+#define SRST_USB_NIU_P		121
+#define SRST_BUS_TOP_NIU_P	122
+#define SRST_INTMEM_A		123
+#define SRST_GIC_A		124
+#define SRST_ROM_H		126
+#define SRST_DCF_A		127
+
+#define SRST_DCF_P		128
+#define SRST_PDM_H		129
+#define SRST_PDM		130
+#define SRST_I2S0_H		131
+#define SRST_I2S0_TX		132
+#define SRST_I2S1_H		133
+#define SRST_I2S1		134
+#define SRST_I2S2_H		135
+#define SRST_I2S2		136
+#define SRST_UART1_P		137
+#define SRST_UART1		138
+#define SRST_UART2_P		139
+#define SRST_UART2		140
+#define SRST_UART3_P		141
+#define SRST_UART3		142
+#define SRST_UART4_P		143
+
+#define SRST_UART4		144
+#define SRST_UART5_P		145
+#define SRST_UART5		146
+#define SRST_I2C0_P		147
+#define SRST_I2C0		148
+#define SRST_I2C1_P		149
+#define SRST_I2C1		150
+#define SRST_I2C2_P		151
+#define SRST_I2C2		152
+#define SRST_I2C3_P		153
+#define SRST_I2C3		154
+#define SRST_PWM0_P		157
+#define SRST_PWM0		158
+#define SRST_PWM1_P		159
+
+#define SRST_PWM1		160
+#define SRST_SPI0_P		161
+#define SRST_SPI0		162
+#define SRST_SPI1_P		163
+#define SRST_SPI1		164
+#define SRST_SARADC_P		165
+#define SRST_SARADC		166
+#define SRST_TSADC_P		167
+#define SRST_TSADC		168
+#define SRST_TIMER_P		169
+#define SRST_TIMER0		170
+#define SRST_TIMER1		171
+#define SRST_TIMER2		172
+#define SRST_TIMER3		173
+#define SRST_TIMER4		174
+#define SRST_TIMER5		175
+
+#define SRST_OTP_NS_P		176
+#define SRST_OTP_NS_SBPI	177
+#define SRST_OTP_NS_USR		178
+#define SRST_OTP_PHY_P		179
+#define SRST_OTP_PHY		180
+#define SRST_WDT_NS_P		181
+#define SRST_GPIO1_P		182
+#define SRST_GPIO2_P		183
+#define SRST_GPIO3_P		184
+#define SRST_SGRF_P		185
+#define SRST_GRF_P		186
+#define SRST_I2S0_RX		191
+
+#endif
-- 
cgit v1.2.3


From 97752d2343518169db7e1fb9da7f2386cf2c3727 Mon Sep 17 00:00:00 2001
From: Elaine Zhang <zhangqing@rock-chips.com>
Date: Fri, 15 Jun 2018 10:16:48 +0800
Subject: dt-bindings: add bindings for px30 clock controller

Add devicetree bindings for Rockchip cru which found on
Rockchip SoCs.

Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 .../bindings/clock/rockchip,px30-cru.txt           | 65 ++++++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/rockchip,px30-cru.txt

diff --git a/Documentation/devicetree/bindings/clock/rockchip,px30-cru.txt b/Documentation/devicetree/bindings/clock/rockchip,px30-cru.txt
new file mode 100644
index 000000000000..39f0c1ac84ee
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/rockchip,px30-cru.txt
@@ -0,0 +1,65 @@
+* Rockchip PX30 Clock and Reset Unit
+
+The PX30 clock controller generates and supplies clock to various
+controllers within the SoC and also implements a reset controller for SoC
+peripherals.
+
+Required Properties:
+
+- compatible: PMU for CRU should be "rockchip,px30-pmu-cru"
+- compatible: CRU should be "rockchip,px30-cru"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- #clock-cells: should be 1.
+- #reset-cells: should be 1.
+
+Optional Properties:
+
+- rockchip,grf: phandle to the syscon managing the "general register files"
+  If missing, pll rates are not changeable, due to the missing pll lock status.
+
+Each clock is assigned an identifier and client nodes can use this identifier
+to specify the clock which they consume. All available clocks are defined as
+preprocessor macros in the dt-bindings/clock/px30-cru.h headers and can be
+used in device tree sources. Similar macros exist for the reset sources in
+these files.
+
+External clocks:
+
+There are several clocks that are generated outside the SoC. It is expected
+that they are defined using standard clock bindings with following
+clock-output-names:
+ - "xin24m" - crystal input - required,
+ - "xin32k" - rtc clock - optional,
+ - "i2sx_clkin" - external I2S clock - optional,
+ - "gmac_clkin" - external GMAC clock - optional
+
+Example: Clock controller node:
+
+	pmucru: clock-controller@ff2bc000 {
+		compatible = "rockchip,px30-pmucru";
+		reg = <0x0 0xff2bc000 0x0 0x1000>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+	cru: clock-controller@ff2b0000 {
+		compatible = "rockchip,px30-cru";
+		reg = <0x0 0xff2b0000 0x0 0x1000>;
+		rockchip,grf = <&grf>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+	};
+
+Example: UART controller node that consumes the clock generated by the clock
+  controller:
+
+	uart0: serial@ff030000 {
+		compatible = "rockchip,px30-uart", "snps,dw-apb-uart";
+		reg = <0x0 0xff030000 0x0 0x100>;
+		interrupts = <GIC_SPI 15 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&pmucru SCLK_UART0_PMU>, <&pmucru PCLK_UART0_PMU>;
+		clock-names = "baudclk", "apb_pclk";
+		reg-shift = <2>;
+		reg-io-width = <4>;
+	};
-- 
cgit v1.2.3


From f041f96abcf8718540e94aac6e73604c5d33d9f9 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 20:52:33 +0200
Subject: dt-bindings: leds: Add bindings for lltc,lt3593

This patch adds the bindings document for LT3593 LED drivers.
The binding is kept consistent with other LED driver bindings in that it
stores all the LED-specific properties in its own subnode. As the hardware
only supports one channel, there can consequently only be one sub-node.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 .../devicetree/bindings/leds/leds-lt3593.txt       | 32 ++++++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/leds/leds-lt3593.txt

diff --git a/Documentation/devicetree/bindings/leds/leds-lt3593.txt b/Documentation/devicetree/bindings/leds/leds-lt3593.txt
new file mode 100644
index 000000000000..6b2cabc36c0c
--- /dev/null
+++ b/Documentation/devicetree/bindings/leds/leds-lt3593.txt
@@ -0,0 +1,32 @@
+Bindings for Linear Technologies LT3593 LED controller
+
+Required properties:
+- compatible:		Should be "lltc,lt3593".
+- lltc,ctrl-gpios:	A handle to the GPIO that is connected to the 'CTRL'
+			pin of the chip.
+
+The hardware supports only one LED. The properties of this LED are
+configured in a sub-node in the device node.
+
+Optional sub-node properties:
+- label:	A label for the LED. If none is given, the LED will be
+		named "lt3595::".
+- linux,default-trigger: The default trigger for the LED.
+			See Documentation/devicetree/bindings/leds/common.txt
+- default-state:	The initial state of the LED.
+			See Documentation/devicetree/bindings/leds/common.txt
+
+If multiple chips of this type are found in a design, each one needs to
+be handled by its own device node.
+
+Example:
+
+led-controller {
+	compatible = "lltc,lt3593";
+	lltc,ctrl-gpios = <&gpio 0 GPIO_ACTIVE_HIGH>;
+
+	led {
+		label = "white:backlight";
+		default-state = "on";
+	};
+};
-- 
cgit v1.2.3


From d8be286739d6317b2c4b2a6c2cbf63d76410ff90 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 20:52:34 +0200
Subject: leds: lt3593: merge functions and clean up code

In preparation to DT probe functionality, merge create_lt3593_led() into
its only call-site. The DT based setup code will be quite different, so this
internal helper function is of no help.

This also changes the way the driver works by only handling one entry inside
'struct gpio_led_platform_data'. If multiple devices of the same type are
found in a design, there should be a platform device for each of them. The
only mainline user of this driver is not affected by this change.

Last, use devm_led_classdev_register() instead of
led_classdev_register(), so the driver's remove callback can go away.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-lt3593.c | 103 +++++++++++++++------------------------------
 1 file changed, 35 insertions(+), 68 deletions(-)

diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index 5ec730a31b65..1a3dc347db21 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -71,104 +71,71 @@ static int lt3593_led_set(struct led_classdev *led_cdev,
 	return 0;
 }
 
-static int create_lt3593_led(const struct gpio_led *template,
-	struct lt3593_led_data *led_dat, struct device *parent)
+static struct lt3593_led_data *lt3593_led_probe_pdata(struct device *dev)
 {
+	struct gpio_led_platform_data *pdata = dev_get_platdata(dev);
+	const struct gpio_led *template = &pdata->leds[0];
+	struct lt3593_led_data *led_data;
 	int ret, state;
 
-	/* skip leds on GPIOs that aren't available */
+	if (pdata->num_leds != 1)
+		return ERR_PTR(-EINVAL);
+
+	led_data = devm_kzalloc(dev, sizeof(*led_data), GFP_KERNEL);
+	if (!led_data)
+		return ERR_PTR(-ENOMEM);
+
 	if (!gpio_is_valid(template->gpio)) {
-		dev_info(parent, "%s: skipping unavailable LT3593 LED at gpio %d (%s)\n",
-				KBUILD_MODNAME, template->gpio, template->name);
-		return 0;
+		dev_info(dev, "skipping unavailable LT3593 LED at gpio "
+			 "%d (%s)\n", template->gpio, template->name);
+		return ERR_PTR(-EINVAL);
 	}
 
-	led_dat->cdev.name = template->name;
-	led_dat->cdev.default_trigger = template->default_trigger;
-	led_dat->gpio = template->gpio;
-
-	led_dat->cdev.brightness_set_blocking = lt3593_led_set;
+	led_data->cdev.name = template->name;
+	led_data->cdev.default_trigger = template->default_trigger;
+	led_data->gpio = template->gpio;
+	led_data->cdev.brightness_set_blocking = lt3593_led_set;
 
 	state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
-	led_dat->cdev.brightness = state ? LED_FULL : LED_OFF;
+	led_data->cdev.brightness = state ? LED_FULL : LED_OFF;
 
 	if (!template->retain_state_suspended)
-		led_dat->cdev.flags |= LED_CORE_SUSPENDRESUME;
+		led_data->cdev.flags |= LED_CORE_SUSPENDRESUME;
 
-	ret = devm_gpio_request_one(parent, template->gpio, state ?
+	ret = devm_gpio_request_one(dev, template->gpio, state ?
 				    GPIOF_OUT_INIT_HIGH : GPIOF_OUT_INIT_LOW,
 				    template->name);
 	if (ret < 0)
-		return ret;
+		return ERR_PTR(ret);
 
-	ret = led_classdev_register(parent, &led_dat->cdev);
+	ret = devm_led_classdev_register(dev, &led_data->cdev);
 	if (ret < 0)
-		return ret;
-
-	dev_info(parent, "%s: registered LT3593 LED '%s' at GPIO %d\n",
-		KBUILD_MODNAME, template->name, template->gpio);
+		return ERR_PTR(ret);
 
-	return 0;
-}
+	dev_info(dev, "registered LT3593 LED '%s' at GPIO %d\n",
+		 template->name, template->gpio);
 
-static void delete_lt3593_led(struct lt3593_led_data *led)
-{
-	if (!gpio_is_valid(led->gpio))
-		return;
-
-	led_classdev_unregister(&led->cdev);
+	return led_data;
 }
 
 static int lt3593_led_probe(struct platform_device *pdev)
 {
-	struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct lt3593_led_data *leds_data;
-	int i, ret = 0;
-
-	if (!pdata)
-		return -EBUSY;
-
-	leds_data = devm_kcalloc(&pdev->dev,
-			pdata->num_leds, sizeof(struct lt3593_led_data),
-			GFP_KERNEL);
-	if (!leds_data)
-		return -ENOMEM;
-
-	for (i = 0; i < pdata->num_leds; i++) {
-		ret = create_lt3593_led(&pdata->leds[i], &leds_data[i],
-				      &pdev->dev);
-		if (ret < 0)
-			goto err;
-	}
+	struct device *dev = &pdev->dev;
+	struct lt3593_led_data *led_data;
 
-	platform_set_drvdata(pdev, leds_data);
-
-	return 0;
-
-err:
-	for (i = i - 1; i >= 0; i--)
-		delete_lt3593_led(&leds_data[i]);
-
-	return ret;
-}
-
-static int lt3593_led_remove(struct platform_device *pdev)
-{
-	int i;
-	struct gpio_led_platform_data *pdata = dev_get_platdata(&pdev->dev);
-	struct lt3593_led_data *leds_data;
-
-	leds_data = platform_get_drvdata(pdev);
+	if (dev_get_platdata(dev)) {
+		led_data = lt3593_led_probe_pdata(dev);
+		if (IS_ERR(led_data))
+			return PTR_ERR(led_data);
+	}
 
-	for (i = 0; i < pdata->num_leds; i++)
-		delete_lt3593_led(&leds_data[i]);
+	platform_set_drvdata(pdev, led_data);
 
 	return 0;
 }
 
 static struct platform_driver lt3593_led_driver = {
 	.probe		= lt3593_led_probe,
-	.remove		= lt3593_led_remove,
 	.driver		= {
 		.name	= "leds-lt3593",
 	},
-- 
cgit v1.2.3


From 73f103c9528135bc896459a58e2371ce86090aea Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 20:52:35 +0200
Subject: leds: lt3593: switch to gpiod interface

Clean up the code a bit and transition over to the gpiod based interface.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-lt3593.c | 26 ++++++++++++--------------
 1 file changed, 12 insertions(+), 14 deletions(-)

diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index 1a3dc347db21..a096ee64cbbb 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -21,12 +21,13 @@
 #include <linux/leds.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 
 struct lt3593_led_data {
 	struct led_classdev cdev;
-	unsigned gpio;
+	struct gpio_desc *gpiod;
 };
 
 static int lt3593_led_set(struct led_classdev *led_cdev,
@@ -46,25 +47,25 @@ static int lt3593_led_set(struct led_classdev *led_cdev,
 	 */
 
 	if (value == 0) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		return 0;
 	}
 
 	pulses = 32 - (value * 32) / 255;
 
 	if (pulses == 0) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		mdelay(1);
-		gpio_set_value_cansleep(led_dat->gpio, 1);
+		gpiod_set_value_cansleep(led_dat->gpiod, 1);
 		return 0;
 	}
 
-	gpio_set_value_cansleep(led_dat->gpio, 1);
+	gpiod_set_value_cansleep(led_dat->gpiod, 1);
 
 	while (pulses--) {
-		gpio_set_value_cansleep(led_dat->gpio, 0);
+		gpiod_set_value_cansleep(led_dat->gpiod, 0);
 		udelay(1);
-		gpio_set_value_cansleep(led_dat->gpio, 1);
+		gpiod_set_value_cansleep(led_dat->gpiod, 1);
 		udelay(1);
 	}
 
@@ -85,15 +86,8 @@ static struct lt3593_led_data *lt3593_led_probe_pdata(struct device *dev)
 	if (!led_data)
 		return ERR_PTR(-ENOMEM);
 
-	if (!gpio_is_valid(template->gpio)) {
-		dev_info(dev, "skipping unavailable LT3593 LED at gpio "
-			 "%d (%s)\n", template->gpio, template->name);
-		return ERR_PTR(-EINVAL);
-	}
-
 	led_data->cdev.name = template->name;
 	led_data->cdev.default_trigger = template->default_trigger;
-	led_data->gpio = template->gpio;
 	led_data->cdev.brightness_set_blocking = lt3593_led_set;
 
 	state = (template->default_state == LEDS_GPIO_DEFSTATE_ON);
@@ -108,6 +102,10 @@ static struct lt3593_led_data *lt3593_led_probe_pdata(struct device *dev)
 	if (ret < 0)
 		return ERR_PTR(ret);
 
+	led_data->gpiod = gpio_to_desc(template->gpio);
+	if (!led_data->gpiod)
+		return ERR_PTR(-EPROBE_DEFER);
+
 	ret = devm_led_classdev_register(dev, &led_data->cdev);
 	if (ret < 0)
 		return ERR_PTR(ret);
-- 
cgit v1.2.3


From 8cd7d6daba9330383259686d1cc1d64caf857b11 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 20:52:36 +0200
Subject: leds: lt3593: Add device tree probing glue

The binding details are described in an earlier commit that adds the
documentation.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-lt3593.c | 70 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index a096ee64cbbb..2e35a4a4c571 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -24,8 +24,11 @@
 #include <linux/gpio/consumer.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/of.h>
+#include <uapi/linux/uleds.h>
 
 struct lt3593_led_data {
+	char name[LED_MAX_NAME_SIZE];
 	struct led_classdev cdev;
 	struct gpio_desc *gpiod;
 };
@@ -120,22 +123,89 @@ static int lt3593_led_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct lt3593_led_data *led_data;
+	struct fwnode_handle *child;
+	int ret, state = LEDS_GPIO_DEFSTATE_OFF;
+	enum gpiod_flags flags = GPIOD_OUT_LOW;
+	const char *tmp;
 
 	if (dev_get_platdata(dev)) {
 		led_data = lt3593_led_probe_pdata(dev);
 		if (IS_ERR(led_data))
 			return PTR_ERR(led_data);
+
+		goto out;
 	}
 
+	if (!dev->of_node)
+		return -ENODEV;
+
+	led_data = devm_kzalloc(dev, sizeof(*led_data), GFP_KERNEL);
+	if (!led_data)
+		return -ENOMEM;
+
+	if (device_get_child_node_count(dev) != 1) {
+		dev_err(dev, "Device must have exactly one LED sub-node.");
+		return -EINVAL;
+	}
+
+	led_data->gpiod = devm_gpiod_get(dev, "lltc,ctrl", 0);
+	if (IS_ERR(led_data->gpiod))
+		return PTR_ERR(led_data->gpiod);
+
+	child = device_get_next_child_node(dev, NULL);
+
+	ret = fwnode_property_read_string(child, "label", &tmp);
+	if (ret < 0)
+		snprintf(led_data->name, sizeof(led_data->name),
+			 "lt3593::");
+	else
+		snprintf(led_data->name, sizeof(led_data->name),
+			 "lt3593:%s", tmp);
+
+	fwnode_property_read_string(child, "linux,default-trigger",
+				    &led_data->cdev.default_trigger);
+
+	if (!fwnode_property_read_string(child, "default-state", &tmp)) {
+		if (!strcmp(tmp, "keep")) {
+			state = LEDS_GPIO_DEFSTATE_KEEP;
+			flags = GPIOD_ASIS;
+		} else if (!strcmp(tmp, "on")) {
+			state = LEDS_GPIO_DEFSTATE_ON;
+			flags = GPIOD_OUT_HIGH;
+		}
+	}
+
+	led_data->cdev.name = led_data->name;
+	led_data->cdev.brightness_set_blocking = lt3593_led_set;
+	led_data->cdev.brightness = state ? LED_FULL : LED_OFF;
+
+	ret = devm_led_classdev_register(dev, &led_data->cdev);
+	if (ret < 0) {
+		fwnode_handle_put(child);
+		return ret;
+	}
+
+	led_data->cdev.dev->of_node = dev->of_node;
+
+out:
 	platform_set_drvdata(pdev, led_data);
 
 	return 0;
 }
 
+#ifdef CONFIG_OF
+static const struct of_device_id of_lt3593_leds_match[] = {
+	{ .compatible = "lltc,lt3593", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_lt3593_leds_match);
+#endif
+
 static struct platform_driver lt3593_led_driver = {
 	.probe		= lt3593_led_probe,
 	.driver		= {
 		.name	= "leds-lt3593",
+		.of_match_table = of_match_ptr(of_lt3593_leds_match),
 	},
 };
 
-- 
cgit v1.2.3


From dd08ac2e5fbc867c5793c3fc0404ef16390b5206 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 20:52:37 +0200
Subject: leds: lt3593: update email address and switch to SPDX license header

Update the email address in the module information and in the comments
and in the module information, and drop the existing boilerplate in
favor of a SPDX header.

Also sync the module license information with the header.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-lt3593.c | 23 ++++-------------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/drivers/leds/leds-lt3593.c b/drivers/leds/leds-lt3593.c
index 2e35a4a4c571..de3623e0d094 100644
--- a/drivers/leds/leds-lt3593.c
+++ b/drivers/leds/leds-lt3593.c
@@ -1,20 +1,5 @@
-/*
- * LEDs driver for LT3593 controllers
- *
- * See the datasheet at http://cds.linear.com/docs/Datasheet/3593f.pdf
- *
- * Copyright (c) 2009 Daniel Mack <daniel@caiaq.de>
- *
- * Based on leds-gpio.c,
- *
- *   Copyright (C) 2007 8D Technologies inc.
- *   Raphael Assenat <raph@8d.com>
- *   Copyright (C) 2008 Freescale Semiconductor, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2009,2018 Daniel Mack <daniel@zonque.org>
 
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
@@ -211,7 +196,7 @@ static struct platform_driver lt3593_led_driver = {
 
 module_platform_driver(lt3593_led_driver);
 
-MODULE_AUTHOR("Daniel Mack <daniel@caiaq.de>");
+MODULE_AUTHOR("Daniel Mack <daniel@zonque.org>");
 MODULE_DESCRIPTION("LED driver for LT3593 controllers");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_ALIAS("platform:leds-lt3593");
-- 
cgit v1.2.3


From 7a5de56db902ea632a0ff0c2b47481d278db645f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 2 Jul 2018 17:50:37 +0100
Subject: leds: max8997: use mode when calling max8997_led_set_mode

Variable mode is assigned to pdata->led_pdata->mode[led->id] and yet
is not being used when calling function max8997_led_set_mode. Fix
this by using mode when calling max8997_led_set_mode.

Cleans up clang warning:
warning: variable 'mode' set but not used [-Wunused-but-set-variable]

Fixes: 8584cb82f151 ("leds: Add suuport for MAX8997-LED driver")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-max8997.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/leds/leds-max8997.c b/drivers/leds/leds-max8997.c
index 4edf74f1d6d4..8c019c28f9f5 100644
--- a/drivers/leds/leds-max8997.c
+++ b/drivers/leds/leds-max8997.c
@@ -268,7 +268,7 @@ static int max8997_led_probe(struct platform_device *pdev)
 		mode = pdata->led_pdata->mode[led->id];
 		brightness = pdata->led_pdata->brightness[led->id];
 
-		max8997_led_set_mode(led, pdata->led_pdata->mode[led->id]);
+		max8997_led_set_mode(led, mode);
 
 		if (brightness > led->cdev.max_brightness)
 			brightness = led->cdev.max_brightness;
-- 
cgit v1.2.3


From 43d20ff3633112322de38c18b4b35bbbf04438d7 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Mon, 2 Jul 2018 13:12:13 -0500
Subject: leds: lm3692x: Update license header to SPDX

Update the license header to the current
SPDX licensing format.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-lm3692x.c | 17 +++--------------
 1 file changed, 3 insertions(+), 14 deletions(-)

diff --git a/drivers/leds/leds-lm3692x.c b/drivers/leds/leds-lm3692x.c
index 437173d1712c..e518ae36f410 100644
--- a/drivers/leds/leds-lm3692x.c
+++ b/drivers/leds/leds-lm3692x.c
@@ -1,17 +1,6 @@
-/*
- * TI lm3692x LED Driver
- *
- * Copyright (C) 2017 Texas Instruments
- *
- * Author: Dan Murphy <dmurphy@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * Data sheet is located
- * http://www.ti.com/lit/ds/snvsa29/snvsa29.pdf
- */
+// SPDX-License-Identifier: GPL-2.0
+// TI LM3692x LED chip family driver
+// Copyright (C) 2017-18 Texas Instruments Incorporated - http://www.ti.com/
 
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
-- 
cgit v1.2.3


From 9a5c1c64ac0a4d01c78328283dac7a9dc33ff0f9 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Mon, 2 Jul 2018 13:12:14 -0500
Subject: leds: lm3692x: Change DT calls to fwnode calls

Update the code to use the fwnode calls as opposed
to ARM DT node api's.

This allows the device to be used with either DT
configurations or ACPI definitions.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-lm3692x.c | 38 +++++++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 17 deletions(-)

diff --git a/drivers/leds/leds-lm3692x.c b/drivers/leds/leds-lm3692x.c
index e518ae36f410..9e6432b6a3b5 100644
--- a/drivers/leds/leds-lm3692x.c
+++ b/drivers/leds/leds-lm3692x.c
@@ -267,30 +267,15 @@ out:
 static int lm3692x_probe(struct i2c_client *client,
 			const struct i2c_device_id *id)
 {
-	int ret;
+	struct fwnode_handle *child = NULL;
 	struct lm3692x_led *led;
-	struct device_node *np = client->dev.of_node;
-	struct device_node *child_node;
 	const char *name;
+	int ret;
 
 	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
 	if (!led)
 		return -ENOMEM;
 
-	for_each_available_child_of_node(np, child_node) {
-		led->led_dev.default_trigger = of_get_property(child_node,
-						    "linux,default-trigger",
-						    NULL);
-
-		ret = of_property_read_string(child_node, "label", &name);
-		if (!ret)
-			snprintf(led->label, sizeof(led->label),
-				 "%s:%s", id->name, name);
-		else
-			snprintf(led->label, sizeof(led->label),
-				 "%s::backlight_cluster", id->name);
-	};
-
 	led->enable_gpio = devm_gpiod_get_optional(&client->dev,
 						   "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(led->enable_gpio)) {
@@ -323,6 +308,25 @@ static int lm3692x_probe(struct i2c_client *client,
 	if (ret)
 		return ret;
 
+	child = device_get_next_child_node(&led->client->dev, child);
+	if (!child) {
+		dev_err(&led->client->dev, "No LED Child node\n");
+		return ret;
+	}
+
+	fwnode_property_read_string(child, "linux,default-trigger",
+				    &led->led_dev.default_trigger);
+
+	ret = fwnode_property_read_string(child, "label", &name);
+	if (ret)
+		snprintf(led->label, sizeof(led->label),
+			"%s::", led->client->name);
+	else
+		snprintf(led->label, sizeof(led->label),
+			 "%s:%s", led->client->name, name);
+
+	led->led_dev.dev->of_node = to_of_node(child);
+
 	ret = devm_led_classdev_register(&client->dev, &led->led_dev);
 	if (ret) {
 		dev_err(&client->dev, "led register err: %d\n", ret);
-- 
cgit v1.2.3


From 581e3ca38a1aa40b742baad39026f440445488d4 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Mon, 2 Jul 2018 13:12:15 -0500
Subject: dt: bindings: lm3692x: Update binding for LED sync control

Update the binding to be able to configure the LED
sync to turn on.

The LM36922 has one output but can sync current to 2 LED
strings. The user may only use one sync so the other
syncs need to be disabled.

The LM36923 has 3 LED syncs.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 Documentation/devicetree/bindings/leds/leds-lm3692x.txt | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/leds/leds-lm3692x.txt b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
index 6c9074f84a51..08b352840bd7 100644
--- a/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
+++ b/Documentation/devicetree/bindings/leds/leds-lm3692x.txt
@@ -20,7 +20,10 @@ Optional properties:
 	- vled-supply : LED supply
 
 Required child properties:
-	- reg : 0
+	- reg : 0 - Will enable all LED sync paths
+		1 - Will enable the LED1 sync
+		2 - Will enable the LED2 sync
+		3 - Will enable the LED3 sync (LM36923 only)
 
 Optional child properties:
 	- label : see Documentation/devicetree/bindings/leds/common.txt
-- 
cgit v1.2.3


From 07abd4325e7013c728bf9642fbb862aa9eb4a367 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Mon, 2 Jul 2018 13:12:16 -0500
Subject: leds: lm3692x: Support LED sync configuration

The LM36922 has one output but can sync current to 2 LED
strings. The user may only use one sync so the other
syncs need to be disabled.

The LM36923 has 3 LED syncs.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-lm3692x.c | 158 +++++++++++++++++++++++++++++++++-----------
 1 file changed, 120 insertions(+), 38 deletions(-)

diff --git a/drivers/leds/leds-lm3692x.c b/drivers/leds/leds-lm3692x.c
index 9e6432b6a3b5..4f413a7c5f05 100644
--- a/drivers/leds/leds-lm3692x.c
+++ b/drivers/leds/leds-lm3692x.c
@@ -15,6 +15,9 @@
 #include <linux/slab.h>
 #include <uapi/linux/uleds.h>
 
+#define LM36922_MODEL	0
+#define LM36923_MODEL	1
+
 #define LM3692X_REV		0x0
 #define LM3692X_RESET		0x1
 #define LM3692X_EN		0x10
@@ -33,6 +36,9 @@
 #define LM3692X_DEVICE_EN	BIT(0)
 #define LM3692X_LED1_EN		BIT(1)
 #define LM3692X_LED2_EN		BIT(2)
+#define LM36923_LED3_EN		BIT(3)
+#define LM3692X_ENABLE_MASK	(LM3692X_DEVICE_EN | LM3692X_LED1_EN | \
+				 LM3692X_LED2_EN | LM36923_LED3_EN)
 
 /* Brightness Control Bits */
 #define LM3692X_BL_ADJ_POL	BIT(0)
@@ -98,6 +104,8 @@
  * @enable_gpio - VDDIO/EN gpio to enable communication interface
  * @regulator - LED supply regulator pointer
  * @label - LED label
+ * @led_enable - LED sync to be enabled
+ * @model_id - Current device model ID enumerated
  */
 struct lm3692x_led {
 	struct mutex lock;
@@ -107,6 +115,8 @@ struct lm3692x_led {
 	struct gpio_desc *enable_gpio;
 	struct regulator *regulator;
 	char label[LED_MAX_NAME_SIZE];
+	int led_enable;
+	int model_id;
 };
 
 static const struct reg_default lm3692x_reg_defs[] = {
@@ -189,6 +199,7 @@ out:
 
 static int lm3692x_init(struct lm3692x_led *led)
 {
+	int enable_state;
 	int ret;
 
 	if (led->regulator) {
@@ -215,9 +226,25 @@ static int lm3692x_init(struct lm3692x_led *led)
 
 	/*
 	 * For glitch free operation, the following data should
-	 * only be written while device enable bit is 0
+	 * only be written while LEDx enable bits are 0 and the device enable
+	 * bit is set to 1.
 	 * per Section 7.5.14 of the data sheet
 	 */
+	ret = regmap_write(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN);
+	if (ret)
+		goto out;
+
+	/* Set the brightness to 0 so when enabled the LEDs do not come
+	 * on with full brightness.
+	 */
+	ret = regmap_write(led->regmap, LM3692X_BRT_MSB, 0);
+	if (ret)
+		goto out;
+
+	ret = regmap_write(led->regmap, LM3692X_BRT_LSB, 0);
+	if (ret)
+		goto out;
+
 	ret = regmap_write(led->regmap, LM3692X_PWM_CTRL,
 		LM3692X_PWM_FILTER_100 | LM3692X_PWM_SAMP_24MHZ);
 	if (ret)
@@ -247,6 +274,38 @@ static int lm3692x_init(struct lm3692x_led *led)
 	if (ret)
 		goto out;
 
+	switch (led->led_enable) {
+	case 0:
+	default:
+		if (led->model_id == LM36923_MODEL)
+			enable_state = LM3692X_LED1_EN | LM3692X_LED2_EN |
+			       LM36923_LED3_EN;
+		else
+			enable_state = LM3692X_LED1_EN | LM3692X_LED2_EN;
+
+		break;
+	case 1:
+		enable_state = LM3692X_LED1_EN;
+		break;
+	case 2:
+		enable_state = LM3692X_LED2_EN;
+		break;
+
+	case 3:
+		if (led->model_id == LM36923_MODEL) {
+			enable_state = LM36923_LED3_EN;
+			break;
+		}
+
+		ret = -EINVAL;
+		dev_err(&led->client->dev,
+			"LED3 sync not available on this device\n");
+		goto out;
+	}
+
+	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_ENABLE_MASK,
+				 enable_state | LM3692X_DEVICE_EN);
+
 	return ret;
 out:
 	dev_err(&led->client->dev, "Fail writing initialization values\n");
@@ -263,55 +322,29 @@ out:
 
 	return ret;
 }
-
-static int lm3692x_probe(struct i2c_client *client,
-			const struct i2c_device_id *id)
+static int lm3692x_probe_dt(struct lm3692x_led *led)
 {
 	struct fwnode_handle *child = NULL;
-	struct lm3692x_led *led;
 	const char *name;
 	int ret;
 
-	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
-	if (!led)
-		return -ENOMEM;
-
-	led->enable_gpio = devm_gpiod_get_optional(&client->dev,
+	led->enable_gpio = devm_gpiod_get_optional(&led->client->dev,
 						   "enable", GPIOD_OUT_LOW);
 	if (IS_ERR(led->enable_gpio)) {
 		ret = PTR_ERR(led->enable_gpio);
-		dev_err(&client->dev, "Failed to get enable gpio: %d\n", ret);
+		dev_err(&led->client->dev, "Failed to get enable gpio: %d\n",
+			ret);
 		return ret;
 	}
 
-	led->regulator = devm_regulator_get(&client->dev, "vled");
+	led->regulator = devm_regulator_get(&led->client->dev, "vled");
 	if (IS_ERR(led->regulator))
 		led->regulator = NULL;
 
-	led->client = client;
-	led->led_dev.name = led->label;
-	led->led_dev.brightness_set_blocking = lm3692x_brightness_set;
-
-	mutex_init(&led->lock);
-
-	i2c_set_clientdata(client, led);
-
-	led->regmap = devm_regmap_init_i2c(client, &lm3692x_regmap_config);
-	if (IS_ERR(led->regmap)) {
-		ret = PTR_ERR(led->regmap);
-		dev_err(&client->dev, "Failed to allocate register map: %d\n",
-			ret);
-		return ret;
-	}
-
-	ret = lm3692x_init(led);
-	if (ret)
-		return ret;
-
 	child = device_get_next_child_node(&led->client->dev, child);
 	if (!child) {
 		dev_err(&led->client->dev, "No LED Child node\n");
-		return ret;
+		return -ENODEV;
 	}
 
 	fwnode_property_read_string(child, "linux,default-trigger",
@@ -325,14 +358,57 @@ static int lm3692x_probe(struct i2c_client *client,
 		snprintf(led->label, sizeof(led->label),
 			 "%s:%s", led->client->name, name);
 
-	led->led_dev.dev->of_node = to_of_node(child);
+	ret = fwnode_property_read_u32(child, "reg", &led->led_enable);
+	if (ret) {
+		dev_err(&led->client->dev, "reg DT property missing\n");
+		return ret;
+	}
+
+	led->led_dev.name = led->label;
 
-	ret = devm_led_classdev_register(&client->dev, &led->led_dev);
+	ret = devm_led_classdev_register(&led->client->dev, &led->led_dev);
 	if (ret) {
-		dev_err(&client->dev, "led register err: %d\n", ret);
+		dev_err(&led->client->dev, "led register err: %d\n", ret);
+		return ret;
+	}
+
+	led->led_dev.dev->of_node = to_of_node(child);
+
+	return 0;
+}
+
+static int lm3692x_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	struct lm3692x_led *led;
+	int ret;
+
+	led = devm_kzalloc(&client->dev, sizeof(*led), GFP_KERNEL);
+	if (!led)
+		return -ENOMEM;
+
+	mutex_init(&led->lock);
+	led->client = client;
+	led->led_dev.brightness_set_blocking = lm3692x_brightness_set;
+	led->model_id = id->driver_data;
+	i2c_set_clientdata(client, led);
+
+	led->regmap = devm_regmap_init_i2c(client, &lm3692x_regmap_config);
+	if (IS_ERR(led->regmap)) {
+		ret = PTR_ERR(led->regmap);
+		dev_err(&client->dev, "Failed to allocate register map: %d\n",
+			ret);
 		return ret;
 	}
 
+	ret = lm3692x_probe_dt(led);
+	if (ret)
+		return ret;
+
+	ret = lm3692x_init(led);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -341,6 +417,12 @@ static int lm3692x_remove(struct i2c_client *client)
 	struct lm3692x_led *led = i2c_get_clientdata(client);
 	int ret;
 
+	ret = regmap_update_bits(led->regmap, LM3692X_EN, LM3692X_DEVICE_EN, 0);
+	if (ret) {
+		dev_err(&led->client->dev, "Failed to disable regulator\n");
+		return ret;
+	}
+
 	if (led->enable_gpio)
 		gpiod_direction_output(led->enable_gpio, 0);
 
@@ -357,8 +439,8 @@ static int lm3692x_remove(struct i2c_client *client)
 }
 
 static const struct i2c_device_id lm3692x_id[] = {
-	{ "lm36922", 0 },
-	{ "lm36923", 1 },
+	{ "lm36922", LM36922_MODEL },
+	{ "lm36923", LM36923_MODEL },
 	{ }
 };
 MODULE_DEVICE_TABLE(i2c, lm3692x_id);
-- 
cgit v1.2.3


From 3fae17468a96f3a397dff633be82a42d89fb1b91 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 3 Jul 2018 08:08:34 -0700
Subject: fs: Fix attr.c kernel-doc

A couple of minor warnings.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/attr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/attr.c b/fs/attr.c
index e3d53bf12240..d22e8187477f 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -120,7 +120,6 @@ EXPORT_SYMBOL(setattr_prepare);
  * inode_newsize_ok - may this inode be truncated to a given size
  * @inode:	the inode to be truncated
  * @offset:	the new size to assign to the inode
- * @Returns:	0 on success, -ve errno on failure
  *
  * inode_newsize_ok must be called with i_mutex held.
  *
@@ -130,6 +129,8 @@ EXPORT_SYMBOL(setattr_prepare);
  * returned. @inode must be a file (not directory), with appropriate
  * permissions to allow truncate (inode_newsize_ok does NOT check these
  * conditions).
+ *
+ * Return: 0 on success, -ve errno on failure
  */
 int inode_newsize_ok(const struct inode *inode, loff_t offset)
 {
@@ -205,7 +206,7 @@ EXPORT_SYMBOL(setattr_copy);
 /**
  * notify_change - modify attributes of a filesytem object
  * @dentry:	object affected
- * @iattr:	new attributes
+ * @attr:	new attributes
  * @delegated_inode: returns inode, if the inode is delegated
  *
  * The caller must hold the i_mutex on the affected object.
-- 
cgit v1.2.3


From b7d3f17fa7a93250daec8c679bf8069715dbeb25 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 3 Jul 2018 08:08:35 -0700
Subject: fs: Add more kernel-doc to the produced documentation

People have gone to all the effort of writing kernel-doc for these
functions; the least we can do is put them in the "Other functions"
part of the VFS documentation.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/index.rst | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 53b89d0edc15..46d1b1be3a51 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -71,6 +71,39 @@ Other Functions
 .. kernel-doc:: fs/block_dev.c
    :export:
 
+.. kernel-doc:: fs/anon_inodes.c
+   :export:
+
+.. kernel-doc:: fs/attr.c
+   :export:
+
+.. kernel-doc:: fs/d_path.c
+   :export:
+
+.. kernel-doc:: fs/dax.c
+   :export:
+
+.. kernel-doc:: fs/direct-io.c
+   :export:
+
+.. kernel-doc:: fs/file_table.c
+   :export:
+
+.. kernel-doc:: fs/libfs.c
+   :export:
+
+.. kernel-doc:: fs/posix_acl.c
+   :export:
+
+.. kernel-doc:: fs/stat.c
+   :export:
+
+.. kernel-doc:: fs/sync.c
+   :export:
+
+.. kernel-doc:: fs/xattr.c
+   :export:
+
 The proc filesystem
 ===================
 
-- 
cgit v1.2.3


From 38b7fb0b2ad1f2ba83bf9a8535cedb198a448ea4 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 3 Jul 2018 11:18:29 +0100
Subject: drm/i915/selftests: Release the struct_mutex to free the objects

live_gtt is a very slow test to run, simply because it tries to allocate
and use as much as the 48b address space as possibly can and in the
process will try to own all of the system memory. This leads to resource
exhaustion and CPU starvation; the latter impacts us when the NMI
watchdog declares a task hung due to a mutex contention with ourselves.
This we can prevent by releasing the struct_mutex and forcing our
i915/rcu workers to run, and in particular flushing the freed object
worker that is the cause for concern.

References: https://bugs.freedesktop.org/show_bug.cgi?id=107094
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703101829.7360-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index a28ee0cc6a63..9578652fba24 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -32,6 +32,20 @@
 #include "mock_drm.h"
 #include "mock_gem_device.h"
 
+static void cleanup_freed_objects(struct drm_i915_private *i915)
+{
+	/*
+	 * As we may hold onto the struct_mutex for inordinate lengths of
+	 * time, the NMI khungtaskd detector may fire for the free objects
+	 * worker.
+	 */
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	i915_gem_drain_freed_objects(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+}
+
 static void fake_free_pages(struct drm_i915_gem_object *obj,
 			    struct sg_table *pages)
 {
@@ -291,6 +305,8 @@ static int lowlevel_hole(struct drm_i915_private *i915,
 		i915_gem_object_put(obj);
 
 		kfree(order);
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -519,6 +535,7 @@ static int fill_hole(struct drm_i915_private *i915,
 		}
 
 		close_object_list(&objects, vm);
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -605,6 +622,8 @@ err_put:
 		i915_gem_object_put(obj);
 		if (err)
 			return err;
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -789,6 +808,8 @@ err_obj:
 		kfree(order);
 		if (err)
 			return err;
+
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
@@ -857,6 +878,7 @@ static int __shrink_hole(struct drm_i915_private *i915,
 	}
 
 	close_object_list(&objects, vm);
+	cleanup_freed_objects(i915);
 	return err;
 }
 
@@ -949,6 +971,7 @@ static int shrink_boom(struct drm_i915_private *i915,
 		i915_gem_object_put(explode);
 
 		memset(&vm->fault_attr, 0, sizeof(vm->fault_attr));
+		cleanup_freed_objects(i915);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 1f6f00238abf2bfa46f4d2c44cfc7512566f3685 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 3 Jul 2018 14:53:31 +0100
Subject: drm/i915/selftests: Drop struct_mutex around lowlevel pggtt
 allocation

For a ppgtt that we are constructing, there is no struct_mutex
dependence so skip it. In the process, also ping the scheduler
frequently to try and avoid the NMI watchdog.

v2: gen6 requires struct_mutex to clean up (currently)

Suggested-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
References: https://bugs.freedesktop.org/show_bug.cgi?id=107094
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703135331.12265-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 9578652fba24..a7956ecc3e1f 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -156,12 +156,9 @@ static int igt_ppgtt_alloc(void *arg)
 	if (!USES_PPGTT(dev_priv))
 		return 0;
 
-	mutex_lock(&dev_priv->drm.struct_mutex);
 	ppgtt = __hw_ppgtt_create(dev_priv);
-	if (IS_ERR(ppgtt)) {
-		err = PTR_ERR(ppgtt);
-		goto err_unlock;
-	}
+	if (IS_ERR(ppgtt))
+		return PTR_ERR(ppgtt);
 
 	if (!ppgtt->vm.allocate_va_range)
 		goto err_ppgtt_cleanup;
@@ -180,6 +177,8 @@ static int igt_ppgtt_alloc(void *arg)
 			goto err_ppgtt_cleanup;
 		}
 
+		cond_resched();
+
 		ppgtt->vm.clear_range(&ppgtt->vm, 0, size);
 	}
 
@@ -197,13 +196,15 @@ static int igt_ppgtt_alloc(void *arg)
 			}
 			goto err_ppgtt_cleanup;
 		}
+
+		cond_resched();
 	}
 
 err_ppgtt_cleanup:
+	mutex_lock(&dev_priv->drm.struct_mutex);
 	ppgtt->vm.cleanup(&ppgtt->vm);
-	kfree(ppgtt);
-err_unlock:
 	mutex_unlock(&dev_priv->drm.struct_mutex);
+	kfree(ppgtt);
 	return err;
 }
 
-- 
cgit v1.2.3


From 67701aea341e9e667eae816510523982137b12e6 Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <steven.hill@cavium.com>
Date: Tue, 3 Jul 2018 16:44:20 -0500
Subject: MIPS: Octeon: Remove unused CIU types.

Remove all unused data types. Verified with a 'make allyesconfig'
and Cavium platform.

[paul.burton@mips.com:
  - Also checked via convoluted grep invocation for use of all removed
    structs & unions within arch/mips/ & drivers/.]

Signed-off-by: Steven J. Hill <steven.hill@cavium.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19711/
Cc: linux-mips@linux-mips.org
Cc: Chandrakala Chavva <cchavva@caviumnetworks.com>
---
 arch/mips/include/asm/octeon/cvmx-ciu-defs.h | 9629 --------------------------
 1 file changed, 9629 deletions(-)

diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index 6e61792d9248..7c2168bdf3ab 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -209,7700 +209,6 @@ static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
 	return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 }
 
-union cvmx_ciu_bist {
-	uint64_t u64;
-	struct cvmx_ciu_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_7_63:57;
-		uint64_t bist:7;
-#else
-		uint64_t bist:7;
-		uint64_t reserved_7_63:57;
-#endif
-	} s;
-	struct cvmx_ciu_bist_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t bist:4;
-#else
-		uint64_t bist:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_bist_cn30xx cn31xx;
-	struct cvmx_ciu_bist_cn30xx cn38xx;
-	struct cvmx_ciu_bist_cn30xx cn38xxp2;
-	struct cvmx_ciu_bist_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t bist:2;
-#else
-		uint64_t bist:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_bist_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_3_63:61;
-		uint64_t bist:3;
-#else
-		uint64_t bist:3;
-		uint64_t reserved_3_63:61;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_bist_cn52xx cn52xxp1;
-	struct cvmx_ciu_bist_cn30xx cn56xx;
-	struct cvmx_ciu_bist_cn30xx cn56xxp1;
-	struct cvmx_ciu_bist_cn30xx cn58xx;
-	struct cvmx_ciu_bist_cn30xx cn58xxp1;
-	struct cvmx_ciu_bist_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t bist:6;
-#else
-		uint64_t bist:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_bist_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_5_63:59;
-		uint64_t bist:5;
-#else
-		uint64_t bist:5;
-		uint64_t reserved_5_63:59;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_bist_cn63xx cn63xxp1;
-	struct cvmx_ciu_bist_cn61xx cn66xx;
-	struct cvmx_ciu_bist_s cn68xx;
-	struct cvmx_ciu_bist_s cn68xxp1;
-	struct cvmx_ciu_bist_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_block_int {
-	uint64_t u64;
-	struct cvmx_ciu_block_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_62_63:2;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_43_59:17;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_34_39:6;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t reserved_34_39:6;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_59:17;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_63:2;
-#endif
-	} s;
-	struct cvmx_ciu_block_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t reserved_31_40:10;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_40:10;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_block_int_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_34_39:6;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t reserved_2_2:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t reserved_2_2:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t reserved_34_39:6;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_block_int_cn63xx cn63xxp1;
-	struct cvmx_ciu_block_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_62_63:2;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_43_59:17;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t dfm:1;
-		uint64_t reserved_33_39:7;
-		uint64_t srio0:1;
-		uint64_t reserved_31_31:1;
-		uint64_t iob:1;
-		uint64_t reserved_29_29:1;
-		uint64_t agl:1;
-		uint64_t reserved_27_27:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_24_24:1;
-		uint64_t asxpcs1:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_8_8:1;
-		uint64_t zip:1;
-		uint64_t dfa:1;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t gmx1:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t gmx1:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t dfa:1;
-		uint64_t zip:1;
-		uint64_t reserved_8_8:1;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t asxpcs1:1;
-		uint64_t reserved_24_24:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_27:1;
-		uint64_t agl:1;
-		uint64_t reserved_29_29:1;
-		uint64_t iob:1;
-		uint64_t reserved_31_31:1;
-		uint64_t srio0:1;
-		uint64_t reserved_33_39:7;
-		uint64_t dfm:1;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_59:17;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_63:2;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_block_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_43_63:21;
-		uint64_t ptp:1;
-		uint64_t dpi:1;
-		uint64_t reserved_31_40:10;
-		uint64_t iob:1;
-		uint64_t reserved_27_29:3;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_21_21:1;
-		uint64_t pip:1;
-		uint64_t reserved_18_19:2;
-		uint64_t lmc0:1;
-		uint64_t l2c:1;
-		uint64_t reserved_15_15:1;
-		uint64_t rad:1;
-		uint64_t usb:1;
-		uint64_t pow:1;
-		uint64_t tim:1;
-		uint64_t pko:1;
-		uint64_t ipd:1;
-		uint64_t reserved_6_8:3;
-		uint64_t fpa:1;
-		uint64_t key:1;
-		uint64_t sli:1;
-		uint64_t reserved_2_2:1;
-		uint64_t gmx0:1;
-		uint64_t mio:1;
-#else
-		uint64_t mio:1;
-		uint64_t gmx0:1;
-		uint64_t reserved_2_2:1;
-		uint64_t sli:1;
-		uint64_t key:1;
-		uint64_t fpa:1;
-		uint64_t reserved_6_8:3;
-		uint64_t ipd:1;
-		uint64_t pko:1;
-		uint64_t tim:1;
-		uint64_t pow:1;
-		uint64_t usb:1;
-		uint64_t rad:1;
-		uint64_t reserved_15_15:1;
-		uint64_t l2c:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_18_19:2;
-		uint64_t pip:1;
-		uint64_t reserved_21_21:1;
-		uint64_t asxpcs0:1;
-		uint64_t reserved_23_24:2;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_27_29:3;
-		uint64_t iob:1;
-		uint64_t reserved_31_40:10;
-		uint64_t dpi:1;
-		uint64_t ptp:1;
-		uint64_t reserved_43_63:21;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_dint {
-	uint64_t u64;
-	struct cvmx_ciu_dint_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t dint:32;
-#else
-		uint64_t dint:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_dint_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t dint:1;
-#else
-		uint64_t dint:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_dint_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t dint:2;
-#else
-		uint64_t dint:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_dint_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t dint:16;
-#else
-		uint64_t dint:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_dint_cn38xx cn38xxp2;
-	struct cvmx_ciu_dint_cn31xx cn50xx;
-	struct cvmx_ciu_dint_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t dint:4;
-#else
-		uint64_t dint:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_dint_cn52xx cn52xxp1;
-	struct cvmx_ciu_dint_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t dint:12;
-#else
-		uint64_t dint:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_dint_cn56xx cn56xxp1;
-	struct cvmx_ciu_dint_cn38xx cn58xx;
-	struct cvmx_ciu_dint_cn38xx cn58xxp1;
-	struct cvmx_ciu_dint_cn52xx cn61xx;
-	struct cvmx_ciu_dint_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t dint:6;
-#else
-		uint64_t dint:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_dint_cn63xx cn63xxp1;
-	struct cvmx_ciu_dint_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t dint:10;
-#else
-		uint64_t dint:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_dint_s cn68xx;
-	struct cvmx_ciu_dint_s cn68xxp1;
-	struct cvmx_ciu_dint_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_iox_int_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_iox_int_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_iox_int_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_iox_int_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_iox_int_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip2_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip2_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip3_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip3_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1c_s cnf71xx;
-};
-
-union cvmx_ciu_en2_ppx_ip4_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_cn61xx cn66xx;
-	struct cvmx_ciu_en2_ppx_ip4_w1s_s cnf71xx;
-};
-
-union cvmx_ciu_fuse {
-	uint64_t u64;
-	struct cvmx_ciu_fuse_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t fuse:32;
-#else
-		uint64_t fuse:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_fuse_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t fuse:1;
-#else
-		uint64_t fuse:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_fuse_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t fuse:2;
-#else
-		uint64_t fuse:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_fuse_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t fuse:16;
-#else
-		uint64_t fuse:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_fuse_cn38xx cn38xxp2;
-	struct cvmx_ciu_fuse_cn31xx cn50xx;
-	struct cvmx_ciu_fuse_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t fuse:4;
-#else
-		uint64_t fuse:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_fuse_cn52xx cn52xxp1;
-	struct cvmx_ciu_fuse_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t fuse:12;
-#else
-		uint64_t fuse:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_fuse_cn56xx cn56xxp1;
-	struct cvmx_ciu_fuse_cn38xx cn58xx;
-	struct cvmx_ciu_fuse_cn38xx cn58xxp1;
-	struct cvmx_ciu_fuse_cn52xx cn61xx;
-	struct cvmx_ciu_fuse_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t fuse:6;
-#else
-		uint64_t fuse:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_fuse_cn63xx cn63xxp1;
-	struct cvmx_ciu_fuse_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t fuse:10;
-#else
-		uint64_t fuse:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_fuse_s cn68xx;
-	struct cvmx_ciu_fuse_s cn68xxp1;
-	struct cvmx_ciu_fuse_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_gstop {
-	uint64_t u64;
-	struct cvmx_ciu_gstop_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t gstop:1;
-#else
-		uint64_t gstop:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_gstop_s cn30xx;
-	struct cvmx_ciu_gstop_s cn31xx;
-	struct cvmx_ciu_gstop_s cn38xx;
-	struct cvmx_ciu_gstop_s cn38xxp2;
-	struct cvmx_ciu_gstop_s cn50xx;
-	struct cvmx_ciu_gstop_s cn52xx;
-	struct cvmx_ciu_gstop_s cn52xxp1;
-	struct cvmx_ciu_gstop_s cn56xx;
-	struct cvmx_ciu_gstop_s cn56xxp1;
-	struct cvmx_ciu_gstop_s cn58xx;
-	struct cvmx_ciu_gstop_s cn58xxp1;
-	struct cvmx_ciu_gstop_s cn61xx;
-	struct cvmx_ciu_gstop_s cn63xx;
-	struct cvmx_ciu_gstop_s cn63xxp1;
-	struct cvmx_ciu_gstop_s cn66xx;
-	struct cvmx_ciu_gstop_s cn68xx;
-	struct cvmx_ciu_gstop_s cn68xxp1;
-	struct cvmx_ciu_gstop_s cnf71xx;
-};
-
-union cvmx_ciu_intx_en0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_en0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_en0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_en0_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_en0_cn30xx cn50xx;
-	struct cvmx_ciu_intx_en0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_en0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en0_cn38xx cn58xx;
-	struct cvmx_ciu_intx_en0_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_en0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_w1c_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en0_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en0_w1s_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t wdog:1;
-#else
-		uint64_t wdog:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_en1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_en1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_en1_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_en1_cn31xx cn50xx;
-	struct cvmx_ciu_intx_en1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_intx_en1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en1_cn38xx cn58xx;
-	struct cvmx_ciu_intx_en1_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_en1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_w1c_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en1_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en1_w1s_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_en4_0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en4_0_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_en4_0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_0_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_0_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_0_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_0_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t reserved_44_44:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t reserved_44_44:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_en4_1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_intx_en4_1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_en4_1_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_en4_1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1c {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_w1c_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_w1c_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_w1c_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_w1c_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_en4_1_w1s {
-	uint64_t u64;
-	struct cvmx_ciu_intx_en4_1_w1s_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_en4_1_w1s_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cn63xx cn63xxp1;
-	struct cvmx_ciu_intx_en4_1_w1s_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_en4_1_w1s_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_sum0 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_sum0_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_intx_sum0_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_intx_sum0_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_intx_sum0_cn38xx cn38xxp2;
-	struct cvmx_ciu_intx_sum0_cn30xx cn50xx;
-	struct cvmx_ciu_intx_sum0_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_sum0_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_sum0_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_sum0_cn38xx cn58xx;
-	struct cvmx_ciu_intx_sum0_cn38xx cn58xxp1;
-	struct cvmx_ciu_intx_sum0_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn63xx;
-	struct cvmx_ciu_intx_sum0_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_intx_sum4 {
-	uint64_t u64;
-	struct cvmx_ciu_intx_sum4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_intx_sum4_cn50xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_59_63:5;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_47_47:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t reserved_47_47:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t reserved_59_63:5;
-#endif
-	} cn50xx;
-	struct cvmx_ciu_intx_sum4_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn52xxp1;
-	struct cvmx_ciu_intx_sum4_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_intx_sum4_cn56xx cn56xxp1;
-	struct cvmx_ciu_intx_sum4_cn58xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_56_63:8;
-		uint64_t timer:4;
-		uint64_t key_zero:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t key_zero:1;
-		uint64_t timer:4;
-		uint64_t reserved_56_63:8;
-#endif
-	} cn58xx;
-	struct cvmx_ciu_intx_sum4_cn58xx cn58xxp1;
-	struct cvmx_ciu_intx_sum4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn63xx;
-	struct cvmx_ciu_intx_sum4_cn52xx cn63xxp1;
-	struct cvmx_ciu_intx_sum4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_intx_sum4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_int33_sum0 {
-	uint64_t u64;
-	struct cvmx_ciu_int33_sum0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} s;
-	struct cvmx_ciu_int33_sum0_s cn61xx;
-	struct cvmx_ciu_int33_sum0_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t reserved_57_58:2;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t reserved_51_51:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_51_51:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_58:2;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int33_sum0_cn63xx cn63xxp1;
-	struct cvmx_ciu_int33_sum0_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t mii:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t reserved_57_57:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t gmx_drp:2;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:2;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t reserved_57_57:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t mii:1;
-		uint64_t bootdma:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_int33_sum0_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t bootdma:1;
-		uint64_t reserved_62_62:1;
-		uint64_t ipdppthr:1;
-		uint64_t powiq:1;
-		uint64_t twsi2:1;
-		uint64_t mpi:1;
-		uint64_t pcm:1;
-		uint64_t usb:1;
-		uint64_t timer:4;
-		uint64_t sum2:1;
-		uint64_t ipd_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t gmx_drp:1;
-		uint64_t trace:1;
-		uint64_t rml:1;
-		uint64_t twsi:1;
-		uint64_t wdog_sum:1;
-		uint64_t pci_msi:4;
-		uint64_t pci_int:4;
-		uint64_t uart:2;
-		uint64_t mbox:2;
-		uint64_t gpio:16;
-		uint64_t workq:16;
-#else
-		uint64_t workq:16;
-		uint64_t gpio:16;
-		uint64_t mbox:2;
-		uint64_t uart:2;
-		uint64_t pci_int:4;
-		uint64_t pci_msi:4;
-		uint64_t wdog_sum:1;
-		uint64_t twsi:1;
-		uint64_t rml:1;
-		uint64_t trace:1;
-		uint64_t gmx_drp:1;
-		uint64_t reserved_49_49:1;
-		uint64_t ipd_drp:1;
-		uint64_t sum2:1;
-		uint64_t timer:4;
-		uint64_t usb:1;
-		uint64_t pcm:1;
-		uint64_t mpi:1;
-		uint64_t twsi2:1;
-		uint64_t powiq:1;
-		uint64_t ipdppthr:1;
-		uint64_t reserved_62_62:1;
-		uint64_t bootdma:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_int_dbg_sel {
-	uint64_t u64;
-	struct cvmx_ciu_int_dbg_sel_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_5_7:3;
-		uint64_t pp:5;
-#else
-		uint64_t pp:5;
-		uint64_t reserved_5_7:3;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} s;
-	struct cvmx_ciu_int_dbg_sel_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_4_7:4;
-		uint64_t pp:4;
-#else
-		uint64_t pp:4;
-		uint64_t reserved_4_7:4;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_int_dbg_sel_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t sel:3;
-		uint64_t reserved_10_15:6;
-		uint64_t irq:2;
-		uint64_t reserved_3_7:5;
-		uint64_t pp:3;
-#else
-		uint64_t pp:3;
-		uint64_t reserved_3_7:5;
-		uint64_t irq:2;
-		uint64_t reserved_10_15:6;
-		uint64_t sel:3;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int_dbg_sel_cn61xx cn66xx;
-	struct cvmx_ciu_int_dbg_sel_s cn68xx;
-	struct cvmx_ciu_int_dbg_sel_s cn68xxp1;
-	struct cvmx_ciu_int_dbg_sel_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_int_sum1 {
-	uint64_t u64;
-	struct cvmx_ciu_int_sum1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_int_sum1_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t wdog:1;
-#else
-		uint64_t wdog:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_int_sum1_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t wdog:2;
-#else
-		uint64_t wdog:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_int_sum1_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t wdog:16;
-#else
-		uint64_t wdog:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_int_sum1_cn38xx cn38xxp2;
-	struct cvmx_ciu_int_sum1_cn31xx cn50xx;
-	struct cvmx_ciu_int_sum1_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_20_63:44;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t reserved_20_63:44;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_int_sum1_cn52xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_19_63:45;
-		uint64_t mii1:1;
-		uint64_t usb1:1;
-		uint64_t uart2:1;
-		uint64_t reserved_4_15:12;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_15:12;
-		uint64_t uart2:1;
-		uint64_t usb1:1;
-		uint64_t mii1:1;
-		uint64_t reserved_19_63:45;
-#endif
-	} cn52xxp1;
-	struct cvmx_ciu_int_sum1_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t wdog:12;
-#else
-		uint64_t wdog:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_int_sum1_cn56xx cn56xxp1;
-	struct cvmx_ciu_int_sum1_cn38xx cn58xx;
-	struct cvmx_ciu_int_sum1_cn38xx cn58xxp1;
-	struct cvmx_ciu_int_sum1_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_int_sum1_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_57_62:6;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t srio1:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_6_17:12;
-		uint64_t wdog:6;
-#else
-		uint64_t wdog:6;
-		uint64_t reserved_6_17:12;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_45:9;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t srio1:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_62:6;
-		uint64_t rst:1;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_int_sum1_cn63xx cn63xxp1;
-	struct cvmx_ciu_int_sum1_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_int_sum1_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_37_46:10;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_46:10;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_mbox_clrx {
-	uint64_t u64;
-	struct cvmx_ciu_mbox_clrx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t bits:32;
-#else
-		uint64_t bits:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_mbox_clrx_s cn30xx;
-	struct cvmx_ciu_mbox_clrx_s cn31xx;
-	struct cvmx_ciu_mbox_clrx_s cn38xx;
-	struct cvmx_ciu_mbox_clrx_s cn38xxp2;
-	struct cvmx_ciu_mbox_clrx_s cn50xx;
-	struct cvmx_ciu_mbox_clrx_s cn52xx;
-	struct cvmx_ciu_mbox_clrx_s cn52xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn56xx;
-	struct cvmx_ciu_mbox_clrx_s cn56xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn58xx;
-	struct cvmx_ciu_mbox_clrx_s cn58xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn61xx;
-	struct cvmx_ciu_mbox_clrx_s cn63xx;
-	struct cvmx_ciu_mbox_clrx_s cn63xxp1;
-	struct cvmx_ciu_mbox_clrx_s cn66xx;
-	struct cvmx_ciu_mbox_clrx_s cn68xx;
-	struct cvmx_ciu_mbox_clrx_s cn68xxp1;
-	struct cvmx_ciu_mbox_clrx_s cnf71xx;
-};
-
-union cvmx_ciu_mbox_setx {
-	uint64_t u64;
-	struct cvmx_ciu_mbox_setx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t bits:32;
-#else
-		uint64_t bits:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_mbox_setx_s cn30xx;
-	struct cvmx_ciu_mbox_setx_s cn31xx;
-	struct cvmx_ciu_mbox_setx_s cn38xx;
-	struct cvmx_ciu_mbox_setx_s cn38xxp2;
-	struct cvmx_ciu_mbox_setx_s cn50xx;
-	struct cvmx_ciu_mbox_setx_s cn52xx;
-	struct cvmx_ciu_mbox_setx_s cn52xxp1;
-	struct cvmx_ciu_mbox_setx_s cn56xx;
-	struct cvmx_ciu_mbox_setx_s cn56xxp1;
-	struct cvmx_ciu_mbox_setx_s cn58xx;
-	struct cvmx_ciu_mbox_setx_s cn58xxp1;
-	struct cvmx_ciu_mbox_setx_s cn61xx;
-	struct cvmx_ciu_mbox_setx_s cn63xx;
-	struct cvmx_ciu_mbox_setx_s cn63xxp1;
-	struct cvmx_ciu_mbox_setx_s cn66xx;
-	struct cvmx_ciu_mbox_setx_s cn68xx;
-	struct cvmx_ciu_mbox_setx_s cn68xxp1;
-	struct cvmx_ciu_mbox_setx_s cnf71xx;
-};
-
-union cvmx_ciu_nmi {
-	uint64_t u64;
-	struct cvmx_ciu_nmi_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t nmi:32;
-#else
-		uint64_t nmi:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_nmi_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t nmi:1;
-#else
-		uint64_t nmi:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_nmi_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t nmi:2;
-#else
-		uint64_t nmi:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_nmi_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t nmi:16;
-#else
-		uint64_t nmi:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_nmi_cn38xx cn38xxp2;
-	struct cvmx_ciu_nmi_cn31xx cn50xx;
-	struct cvmx_ciu_nmi_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t nmi:4;
-#else
-		uint64_t nmi:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_nmi_cn52xx cn52xxp1;
-	struct cvmx_ciu_nmi_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t nmi:12;
-#else
-		uint64_t nmi:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_nmi_cn56xx cn56xxp1;
-	struct cvmx_ciu_nmi_cn38xx cn58xx;
-	struct cvmx_ciu_nmi_cn38xx cn58xxp1;
-	struct cvmx_ciu_nmi_cn52xx cn61xx;
-	struct cvmx_ciu_nmi_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t nmi:6;
-#else
-		uint64_t nmi:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_nmi_cn63xx cn63xxp1;
-	struct cvmx_ciu_nmi_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t nmi:10;
-#else
-		uint64_t nmi:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_nmi_s cn68xx;
-	struct cvmx_ciu_nmi_s cn68xxp1;
-	struct cvmx_ciu_nmi_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pci_inta {
-	uint64_t u64;
-	struct cvmx_ciu_pci_inta_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t intr:2;
-#else
-		uint64_t intr:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} s;
-	struct cvmx_ciu_pci_inta_s cn30xx;
-	struct cvmx_ciu_pci_inta_s cn31xx;
-	struct cvmx_ciu_pci_inta_s cn38xx;
-	struct cvmx_ciu_pci_inta_s cn38xxp2;
-	struct cvmx_ciu_pci_inta_s cn50xx;
-	struct cvmx_ciu_pci_inta_s cn52xx;
-	struct cvmx_ciu_pci_inta_s cn52xxp1;
-	struct cvmx_ciu_pci_inta_s cn56xx;
-	struct cvmx_ciu_pci_inta_s cn56xxp1;
-	struct cvmx_ciu_pci_inta_s cn58xx;
-	struct cvmx_ciu_pci_inta_s cn58xxp1;
-	struct cvmx_ciu_pci_inta_s cn61xx;
-	struct cvmx_ciu_pci_inta_s cn63xx;
-	struct cvmx_ciu_pci_inta_s cn63xxp1;
-	struct cvmx_ciu_pci_inta_s cn66xx;
-	struct cvmx_ciu_pci_inta_s cn68xx;
-	struct cvmx_ciu_pci_inta_s cn68xxp1;
-	struct cvmx_ciu_pci_inta_s cnf71xx;
-};
-
-union cvmx_ciu_pp_bist_stat {
-	uint64_t u64;
-	struct cvmx_ciu_pp_bist_stat_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t pp_bist:32;
-#else
-		uint64_t pp_bist:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_bist_stat_s cn68xx;
-	struct cvmx_ciu_pp_bist_stat_s cn68xxp1;
-};
-
-union cvmx_ciu_pp_dbg {
-	uint64_t u64;
-	struct cvmx_ciu_pp_dbg_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t ppdbg:32;
-#else
-		uint64_t ppdbg:32;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_dbg_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t ppdbg:1;
-#else
-		uint64_t ppdbg:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_pp_dbg_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t ppdbg:2;
-#else
-		uint64_t ppdbg:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_pp_dbg_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t ppdbg:16;
-#else
-		uint64_t ppdbg:16;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_pp_dbg_cn38xx cn38xxp2;
-	struct cvmx_ciu_pp_dbg_cn31xx cn50xx;
-	struct cvmx_ciu_pp_dbg_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t ppdbg:4;
-#else
-		uint64_t ppdbg:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_pp_dbg_cn52xx cn52xxp1;
-	struct cvmx_ciu_pp_dbg_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t ppdbg:12;
-#else
-		uint64_t ppdbg:12;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_pp_dbg_cn56xx cn56xxp1;
-	struct cvmx_ciu_pp_dbg_cn38xx cn58xx;
-	struct cvmx_ciu_pp_dbg_cn38xx cn58xxp1;
-	struct cvmx_ciu_pp_dbg_cn52xx cn61xx;
-	struct cvmx_ciu_pp_dbg_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t ppdbg:6;
-#else
-		uint64_t ppdbg:6;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_pp_dbg_cn63xx cn63xxp1;
-	struct cvmx_ciu_pp_dbg_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t ppdbg:10;
-#else
-		uint64_t ppdbg:10;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_pp_dbg_s cn68xx;
-	struct cvmx_ciu_pp_dbg_s cn68xxp1;
-	struct cvmx_ciu_pp_dbg_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_pp_pokex {
-	uint64_t u64;
-	struct cvmx_ciu_pp_pokex_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t poke:64;
-#else
-		uint64_t poke:64;
-#endif
-	} s;
-	struct cvmx_ciu_pp_pokex_s cn30xx;
-	struct cvmx_ciu_pp_pokex_s cn31xx;
-	struct cvmx_ciu_pp_pokex_s cn38xx;
-	struct cvmx_ciu_pp_pokex_s cn38xxp2;
-	struct cvmx_ciu_pp_pokex_s cn50xx;
-	struct cvmx_ciu_pp_pokex_s cn52xx;
-	struct cvmx_ciu_pp_pokex_s cn52xxp1;
-	struct cvmx_ciu_pp_pokex_s cn56xx;
-	struct cvmx_ciu_pp_pokex_s cn56xxp1;
-	struct cvmx_ciu_pp_pokex_s cn58xx;
-	struct cvmx_ciu_pp_pokex_s cn58xxp1;
-	struct cvmx_ciu_pp_pokex_s cn61xx;
-	struct cvmx_ciu_pp_pokex_s cn63xx;
-	struct cvmx_ciu_pp_pokex_s cn63xxp1;
-	struct cvmx_ciu_pp_pokex_s cn66xx;
-	struct cvmx_ciu_pp_pokex_s cn68xx;
-	struct cvmx_ciu_pp_pokex_s cn68xxp1;
-	struct cvmx_ciu_pp_pokex_s cnf71xx;
-};
-
-union cvmx_ciu_pp_rst {
-	uint64_t u64;
-	struct cvmx_ciu_pp_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t rst:31;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:31;
-		uint64_t reserved_32_63:32;
-#endif
-	} s;
-	struct cvmx_ciu_pp_rst_cn30xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn30xx;
-	struct cvmx_ciu_pp_rst_cn31xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t rst:1;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:1;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn31xx;
-	struct cvmx_ciu_pp_rst_cn38xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_16_63:48;
-		uint64_t rst:15;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:15;
-		uint64_t reserved_16_63:48;
-#endif
-	} cn38xx;
-	struct cvmx_ciu_pp_rst_cn38xx cn38xxp2;
-	struct cvmx_ciu_pp_rst_cn31xx cn50xx;
-	struct cvmx_ciu_pp_rst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t rst:3;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:3;
-		uint64_t reserved_4_63:60;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_pp_rst_cn52xx cn52xxp1;
-	struct cvmx_ciu_pp_rst_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_12_63:52;
-		uint64_t rst:11;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:11;
-		uint64_t reserved_12_63:52;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_pp_rst_cn56xx cn56xxp1;
-	struct cvmx_ciu_pp_rst_cn38xx cn58xx;
-	struct cvmx_ciu_pp_rst_cn38xx cn58xxp1;
-	struct cvmx_ciu_pp_rst_cn52xx cn61xx;
-	struct cvmx_ciu_pp_rst_cn63xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_6_63:58;
-		uint64_t rst:5;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:5;
-		uint64_t reserved_6_63:58;
-#endif
-	} cn63xx;
-	struct cvmx_ciu_pp_rst_cn63xx cn63xxp1;
-	struct cvmx_ciu_pp_rst_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t rst:9;
-		uint64_t rst0:1;
-#else
-		uint64_t rst0:1;
-		uint64_t rst:9;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_pp_rst_s cn68xx;
-	struct cvmx_ciu_pp_rst_s cn68xxp1;
-	struct cvmx_ciu_pp_rst_cn52xx cnf71xx;
-};
-
 union cvmx_ciu_qlm0 {
 	uint64_t u64;
 	struct cvmx_ciu_qlm0_s {
@@ -7936,53 +242,6 @@ union cvmx_ciu_qlm0 {
 		uint64_t g2bypass:1;
 #endif
 	} s;
-	struct cvmx_ciu_qlm0_s cn61xx;
-	struct cvmx_ciu_qlm0_s cn63xx;
-	struct cvmx_ciu_qlm0_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm0_s cn66xx;
-	struct cvmx_ciu_qlm0_cn68xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn68xx;
-	struct cvmx_ciu_qlm0_cn68xx cn68xxp1;
-	struct cvmx_ciu_qlm0_s cnf71xx;
 };
 
 union cvmx_ciu_qlm1 {
@@ -8018,214 +277,6 @@ union cvmx_ciu_qlm1 {
 		uint64_t g2bypass:1;
 #endif
 	} s;
-	struct cvmx_ciu_qlm1_s cn61xx;
-	struct cvmx_ciu_qlm1_s cn63xx;
-	struct cvmx_ciu_qlm1_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm1_s cn66xx;
-	struct cvmx_ciu_qlm1_s cn68xx;
-	struct cvmx_ciu_qlm1_s cn68xxp1;
-	struct cvmx_ciu_qlm1_s cnf71xx;
-};
-
-union cvmx_ciu_qlm2 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm2_cn61xx cn63xx;
-	struct cvmx_ciu_qlm2_cn63xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_32_63:32;
-		uint64_t txbypass:1;
-		uint64_t reserved_20_30:11;
-		uint64_t txdeemph:4;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:4;
-		uint64_t reserved_20_30:11;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_63:32;
-#endif
-	} cn63xxp1;
-	struct cvmx_ciu_qlm2_cn61xx cn66xx;
-	struct cvmx_ciu_qlm2_s cn68xx;
-	struct cvmx_ciu_qlm2_s cn68xxp1;
-	struct cvmx_ciu_qlm2_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_qlm3 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm3_s cn68xx;
-	struct cvmx_ciu_qlm3_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm4 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-	struct cvmx_ciu_qlm4_s cn68xx;
-	struct cvmx_ciu_qlm4_s cn68xxp1;
-};
-
-union cvmx_ciu_qlm_dcok {
-	uint64_t u64;
-	struct cvmx_ciu_qlm_dcok_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_4_63:60;
-		uint64_t qlm_dcok:4;
-#else
-		uint64_t qlm_dcok:4;
-		uint64_t reserved_4_63:60;
-#endif
-	} s;
-	struct cvmx_ciu_qlm_dcok_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_2_63:62;
-		uint64_t qlm_dcok:2;
-#else
-		uint64_t qlm_dcok:2;
-		uint64_t reserved_2_63:62;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_dcok_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_dcok_s cn56xx;
-	struct cvmx_ciu_qlm_dcok_s cn56xxp1;
 };
 
 union cvmx_ciu_qlm_jtgc {
@@ -8249,63 +300,6 @@ union cvmx_ciu_qlm_jtgc {
 		uint64_t reserved_17_63:47;
 #endif
 	} s;
-	struct cvmx_ciu_qlm_jtgc_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_5_7:3;
-		uint64_t mux_sel:1;
-		uint64_t reserved_2_3:2;
-		uint64_t bypass:2;
-#else
-		uint64_t bypass:2;
-		uint64_t reserved_2_3:2;
-		uint64_t mux_sel:1;
-		uint64_t reserved_5_7:3;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_jtgc_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_6_7:2;
-		uint64_t mux_sel:2;
-		uint64_t bypass:4;
-#else
-		uint64_t bypass:4;
-		uint64_t mux_sel:2;
-		uint64_t reserved_6_7:2;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_qlm_jtgc_cn56xx cn56xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_11_63:53;
-		uint64_t clk_div:3;
-		uint64_t reserved_6_7:2;
-		uint64_t mux_sel:2;
-		uint64_t reserved_3_3:1;
-		uint64_t bypass:3;
-#else
-		uint64_t bypass:3;
-		uint64_t reserved_3_3:1;
-		uint64_t mux_sel:2;
-		uint64_t reserved_6_7:2;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_63:53;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn63xx;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn63xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cn66xx;
-	struct cvmx_ciu_qlm_jtgc_s cn68xx;
-	struct cvmx_ciu_qlm_jtgc_s cn68xxp1;
-	struct cvmx_ciu_qlm_jtgc_cn61xx cnf71xx;
 };
 
 union cvmx_ciu_qlm_jtgd {
@@ -8331,124 +325,6 @@ union cvmx_ciu_qlm_jtgd {
 		uint64_t capture:1;
 #endif
 	} s;
-	struct cvmx_ciu_qlm_jtgd_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_42_60:19;
-		uint64_t select:2;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:2;
-		uint64_t reserved_42_60:19;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_qlm_jtgd_cn52xx cn52xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn56xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_44_60:17;
-		uint64_t select:4;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:4;
-		uint64_t reserved_44_60:17;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn56xx;
-	struct cvmx_ciu_qlm_jtgd_cn56xxp1 {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_37_60:24;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_60:24;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn56xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_43_60:18;
-		uint64_t select:3;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:3;
-		uint64_t reserved_43_60:18;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn63xx;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn63xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cn66xx;
-	struct cvmx_ciu_qlm_jtgd_s cn68xx;
-	struct cvmx_ciu_qlm_jtgd_s cn68xxp1;
-	struct cvmx_ciu_qlm_jtgd_cn61xx cnf71xx;
-};
-
-union cvmx_ciu_soft_bist {
-	uint64_t u64;
-	struct cvmx_ciu_soft_bist_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_bist:1;
-#else
-		uint64_t soft_bist:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_bist_s cn30xx;
-	struct cvmx_ciu_soft_bist_s cn31xx;
-	struct cvmx_ciu_soft_bist_s cn38xx;
-	struct cvmx_ciu_soft_bist_s cn38xxp2;
-	struct cvmx_ciu_soft_bist_s cn50xx;
-	struct cvmx_ciu_soft_bist_s cn52xx;
-	struct cvmx_ciu_soft_bist_s cn52xxp1;
-	struct cvmx_ciu_soft_bist_s cn56xx;
-	struct cvmx_ciu_soft_bist_s cn56xxp1;
-	struct cvmx_ciu_soft_bist_s cn58xx;
-	struct cvmx_ciu_soft_bist_s cn58xxp1;
-	struct cvmx_ciu_soft_bist_s cn61xx;
-	struct cvmx_ciu_soft_bist_s cn63xx;
-	struct cvmx_ciu_soft_bist_s cn63xxp1;
-	struct cvmx_ciu_soft_bist_s cn66xx;
-	struct cvmx_ciu_soft_bist_s cn68xx;
-	struct cvmx_ciu_soft_bist_s cn68xxp1;
-	struct cvmx_ciu_soft_bist_s cnf71xx;
 };
 
 union cvmx_ciu_soft_prst {
@@ -8466,1459 +342,6 @@ union cvmx_ciu_soft_prst {
 		uint64_t reserved_3_63:61;
 #endif
 	} s;
-	struct cvmx_ciu_soft_prst_s cn30xx;
-	struct cvmx_ciu_soft_prst_s cn31xx;
-	struct cvmx_ciu_soft_prst_s cn38xx;
-	struct cvmx_ciu_soft_prst_s cn38xxp2;
-	struct cvmx_ciu_soft_prst_s cn50xx;
-	struct cvmx_ciu_soft_prst_cn52xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} cn52xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn52xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn56xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn56xxp1;
-	struct cvmx_ciu_soft_prst_s cn58xx;
-	struct cvmx_ciu_soft_prst_s cn58xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn61xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn63xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn63xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cn66xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn68xx;
-	struct cvmx_ciu_soft_prst_cn52xx cn68xxp1;
-	struct cvmx_ciu_soft_prst_cn52xx cnf71xx;
-};
-
-union cvmx_ciu_soft_prst1 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst1_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst1_s cn52xx;
-	struct cvmx_ciu_soft_prst1_s cn52xxp1;
-	struct cvmx_ciu_soft_prst1_s cn56xx;
-	struct cvmx_ciu_soft_prst1_s cn56xxp1;
-	struct cvmx_ciu_soft_prst1_s cn61xx;
-	struct cvmx_ciu_soft_prst1_s cn63xx;
-	struct cvmx_ciu_soft_prst1_s cn63xxp1;
-	struct cvmx_ciu_soft_prst1_s cn66xx;
-	struct cvmx_ciu_soft_prst1_s cn68xx;
-	struct cvmx_ciu_soft_prst1_s cn68xxp1;
-	struct cvmx_ciu_soft_prst1_s cnf71xx;
-};
-
-union cvmx_ciu_soft_prst2 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst2_s cn66xx;
-};
-
-union cvmx_ciu_soft_prst3 {
-	uint64_t u64;
-	struct cvmx_ciu_soft_prst3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_prst3_s cn66xx;
-};
-
-union cvmx_ciu_soft_rst {
-	uint64_t u64;
-	struct cvmx_ciu_soft_rst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t soft_rst:1;
-#else
-		uint64_t soft_rst:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_soft_rst_s cn30xx;
-	struct cvmx_ciu_soft_rst_s cn31xx;
-	struct cvmx_ciu_soft_rst_s cn38xx;
-	struct cvmx_ciu_soft_rst_s cn38xxp2;
-	struct cvmx_ciu_soft_rst_s cn50xx;
-	struct cvmx_ciu_soft_rst_s cn52xx;
-	struct cvmx_ciu_soft_rst_s cn52xxp1;
-	struct cvmx_ciu_soft_rst_s cn56xx;
-	struct cvmx_ciu_soft_rst_s cn56xxp1;
-	struct cvmx_ciu_soft_rst_s cn58xx;
-	struct cvmx_ciu_soft_rst_s cn58xxp1;
-	struct cvmx_ciu_soft_rst_s cn61xx;
-	struct cvmx_ciu_soft_rst_s cn63xx;
-	struct cvmx_ciu_soft_rst_s cn63xxp1;
-	struct cvmx_ciu_soft_rst_s cn66xx;
-	struct cvmx_ciu_soft_rst_s cn68xx;
-	struct cvmx_ciu_soft_rst_s cn68xxp1;
-	struct cvmx_ciu_soft_rst_s cnf71xx;
-};
-
-union cvmx_ciu_sum1_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_iox_int_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_iox_int_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip2_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip2_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip3_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip3_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum1_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_sum1_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} s;
-	struct cvmx_ciu_sum1_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_41_45:5;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_38_39:2;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_4_17:14;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_17:14;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_39:2;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_45:5;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum1_ppx_ip4_cn66xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_62_62:1;
-		uint64_t srio3:1;
-		uint64_t srio2:1;
-		uint64_t reserved_57_59:3;
-		uint64_t dfm:1;
-		uint64_t reserved_53_55:3;
-		uint64_t lmc0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t srio0:1;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t agl:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agx1:1;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t dfa:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t zip:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t mii1:1;
-		uint64_t reserved_10_17:8;
-		uint64_t wdog:10;
-#else
-		uint64_t wdog:10;
-		uint64_t reserved_10_17:8;
-		uint64_t mii1:1;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t zip:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t dfa:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t agx1:1;
-		uint64_t reserved_38_45:8;
-		uint64_t agl:1;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t srio0:1;
-		uint64_t reserved_51_51:1;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_55:3;
-		uint64_t dfm:1;
-		uint64_t reserved_57_59:3;
-		uint64_t srio2:1;
-		uint64_t srio3:1;
-		uint64_t reserved_62_62:1;
-		uint64_t rst:1;
-#endif
-	} cn66xx;
-	struct cvmx_ciu_sum1_ppx_ip4_cnf71xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t rst:1;
-		uint64_t reserved_53_62:10;
-		uint64_t lmc0:1;
-		uint64_t reserved_50_51:2;
-		uint64_t pem1:1;
-		uint64_t pem0:1;
-		uint64_t ptp:1;
-		uint64_t reserved_41_46:6;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_37_39:3;
-		uint64_t agx0:1;
-		uint64_t dpi:1;
-		uint64_t sli:1;
-		uint64_t usb:1;
-		uint64_t reserved_32_32:1;
-		uint64_t key:1;
-		uint64_t rad:1;
-		uint64_t tim:1;
-		uint64_t reserved_28_28:1;
-		uint64_t pko:1;
-		uint64_t pip:1;
-		uint64_t ipd:1;
-		uint64_t l2c:1;
-		uint64_t pow:1;
-		uint64_t fpa:1;
-		uint64_t iob:1;
-		uint64_t mio:1;
-		uint64_t nand:1;
-		uint64_t reserved_4_18:15;
-		uint64_t wdog:4;
-#else
-		uint64_t wdog:4;
-		uint64_t reserved_4_18:15;
-		uint64_t nand:1;
-		uint64_t mio:1;
-		uint64_t iob:1;
-		uint64_t fpa:1;
-		uint64_t pow:1;
-		uint64_t l2c:1;
-		uint64_t ipd:1;
-		uint64_t pip:1;
-		uint64_t pko:1;
-		uint64_t reserved_28_28:1;
-		uint64_t tim:1;
-		uint64_t rad:1;
-		uint64_t key:1;
-		uint64_t reserved_32_32:1;
-		uint64_t usb:1;
-		uint64_t sli:1;
-		uint64_t dpi:1;
-		uint64_t agx0:1;
-		uint64_t reserved_37_39:3;
-		uint64_t dpi_dma:1;
-		uint64_t reserved_41_46:6;
-		uint64_t ptp:1;
-		uint64_t pem0:1;
-		uint64_t pem1:1;
-		uint64_t reserved_50_51:2;
-		uint64_t lmc0:1;
-		uint64_t reserved_53_62:10;
-		uint64_t rst:1;
-#endif
-	} cnf71xx;
-};
-
-union cvmx_ciu_sum2_iox_int {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_iox_int_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_iox_int_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_iox_int_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_iox_int_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip2 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip2_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip2_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip2_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip2_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip3 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip3_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip3_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip3_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip3_s cnf71xx;
-};
-
-union cvmx_ciu_sum2_ppx_ip4 {
-	uint64_t u64;
-	struct cvmx_ciu_sum2_ppx_ip4_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_15_63:49;
-		uint64_t endor:2;
-		uint64_t eoi:1;
-		uint64_t reserved_10_11:2;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_11:2;
-		uint64_t eoi:1;
-		uint64_t endor:2;
-		uint64_t reserved_15_63:49;
-#endif
-	} s;
-	struct cvmx_ciu_sum2_ppx_ip4_cn61xx {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_10_63:54;
-		uint64_t timer:6;
-		uint64_t reserved_0_3:4;
-#else
-		uint64_t reserved_0_3:4;
-		uint64_t timer:6;
-		uint64_t reserved_10_63:54;
-#endif
-	} cn61xx;
-	struct cvmx_ciu_sum2_ppx_ip4_cn61xx cn66xx;
-	struct cvmx_ciu_sum2_ppx_ip4_s cnf71xx;
 };
 
 union cvmx_ciu_timx {
@@ -9934,40 +357,6 @@ union cvmx_ciu_timx {
 		uint64_t reserved_37_63:27;
 #endif
 	} s;
-	struct cvmx_ciu_timx_s cn30xx;
-	struct cvmx_ciu_timx_s cn31xx;
-	struct cvmx_ciu_timx_s cn38xx;
-	struct cvmx_ciu_timx_s cn38xxp2;
-	struct cvmx_ciu_timx_s cn50xx;
-	struct cvmx_ciu_timx_s cn52xx;
-	struct cvmx_ciu_timx_s cn52xxp1;
-	struct cvmx_ciu_timx_s cn56xx;
-	struct cvmx_ciu_timx_s cn56xxp1;
-	struct cvmx_ciu_timx_s cn58xx;
-	struct cvmx_ciu_timx_s cn58xxp1;
-	struct cvmx_ciu_timx_s cn61xx;
-	struct cvmx_ciu_timx_s cn63xx;
-	struct cvmx_ciu_timx_s cn63xxp1;
-	struct cvmx_ciu_timx_s cn66xx;
-	struct cvmx_ciu_timx_s cn68xx;
-	struct cvmx_ciu_timx_s cn68xxp1;
-	struct cvmx_ciu_timx_s cnf71xx;
-};
-
-union cvmx_ciu_tim_multi_cast {
-	uint64_t u64;
-	struct cvmx_ciu_tim_multi_cast_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_1_63:63;
-		uint64_t en:1;
-#else
-		uint64_t en:1;
-		uint64_t reserved_1_63:63;
-#endif
-	} s;
-	struct cvmx_ciu_tim_multi_cast_s cn61xx;
-	struct cvmx_ciu_tim_multi_cast_s cn66xx;
-	struct cvmx_ciu_tim_multi_cast_s cnf71xx;
 };
 
 union cvmx_ciu_wdogx {
@@ -9991,24 +380,6 @@ union cvmx_ciu_wdogx {
 		uint64_t reserved_46_63:18;
 #endif
 	} s;
-	struct cvmx_ciu_wdogx_s cn30xx;
-	struct cvmx_ciu_wdogx_s cn31xx;
-	struct cvmx_ciu_wdogx_s cn38xx;
-	struct cvmx_ciu_wdogx_s cn38xxp2;
-	struct cvmx_ciu_wdogx_s cn50xx;
-	struct cvmx_ciu_wdogx_s cn52xx;
-	struct cvmx_ciu_wdogx_s cn52xxp1;
-	struct cvmx_ciu_wdogx_s cn56xx;
-	struct cvmx_ciu_wdogx_s cn56xxp1;
-	struct cvmx_ciu_wdogx_s cn58xx;
-	struct cvmx_ciu_wdogx_s cn58xxp1;
-	struct cvmx_ciu_wdogx_s cn61xx;
-	struct cvmx_ciu_wdogx_s cn63xx;
-	struct cvmx_ciu_wdogx_s cn63xxp1;
-	struct cvmx_ciu_wdogx_s cn66xx;
-	struct cvmx_ciu_wdogx_s cn68xx;
-	struct cvmx_ciu_wdogx_s cn68xxp1;
-	struct cvmx_ciu_wdogx_s cnf71xx;
 };
 
 #endif
-- 
cgit v1.2.3


From 769f4372b2887b7c758f67f4fae82bd5b8555b59 Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <steven.hill@cavium.com>
Date: Tue, 3 Jul 2018 16:44:21 -0500
Subject: MIPS: Octeon: Unify QLM data types in CIU header.

Data types 'cvmx_ciu_qlm0' and 'cvmx_ciu_qlm1' are identical in
their usage and structure. Combine them and update the PCIe code.

Signed-off-by: Steven J. Hill <steven.hill@cavium.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19708/
Cc: linux-mips@linux-mips.org
Cc: Chandrakala Chavva <cchavva@caviumnetworks.com>
---
 arch/mips/include/asm/octeon/cvmx-ciu-defs.h | 39 ++--------------------------
 arch/mips/pci/pcie-octeon.c                  |  4 +--
 2 files changed, 4 insertions(+), 39 deletions(-)

diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index 7c2168bdf3ab..f8ca7b7cca69 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -209,44 +209,9 @@ static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
 	return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 }
 
-union cvmx_ciu_qlm0 {
+union cvmx_ciu_qlm {
 	uint64_t u64;
-	struct cvmx_ciu_qlm0_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
-	} s;
-};
-
-union cvmx_ciu_qlm1 {
-	uint64_t u64;
-	struct cvmx_ciu_qlm1_s {
+	struct cvmx_ciu_qlm_s {
 #ifdef __BIG_ENDIAN_BITFIELD
 		uint64_t g2bypass:1;
 		uint64_t reserved_53_62:10;
diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
index 9cc5905860ef..d919a0d813a1 100644
--- a/arch/mips/pci/pcie-octeon.c
+++ b/arch/mips/pci/pcie-octeon.c
@@ -1237,14 +1237,14 @@ static int __cvmx_pcie_rc_initialize_gen2(int pcie_port)
 	/* CN63XX Pass 1.0 errata G-14395 requires the QLM De-emphasis be programmed */
 	if (OCTEON_IS_MODEL(OCTEON_CN63XX_PASS1_0)) {
 		if (pcie_port) {
-			union cvmx_ciu_qlm1 ciu_qlm;
+			union cvmx_ciu_qlm ciu_qlm;
 			ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM1);
 			ciu_qlm.s.txbypass = 1;
 			ciu_qlm.s.txdeemph = 5;
 			ciu_qlm.s.txmargin = 0x17;
 			cvmx_write_csr(CVMX_CIU_QLM1, ciu_qlm.u64);
 		} else {
-			union cvmx_ciu_qlm0 ciu_qlm;
+			union cvmx_ciu_qlm ciu_qlm;
 			ciu_qlm.u64 = cvmx_read_csr(CVMX_CIU_QLM0);
 			ciu_qlm.s.txbypass = 1;
 			ciu_qlm.s.txdeemph = 5;
-- 
cgit v1.2.3


From 9609e3e9f8de4c760f4711e3cfc7403173352c1a Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <steven.hill@cavium.com>
Date: Tue, 3 Jul 2018 16:44:22 -0500
Subject: MIPS: Octeon: Convert CIU types to use bitfields.

Convert remaining structures to use __BITFIELD_FIELD macro. Also
straighten up the description text and whitespace.

Signed-off-by: Steven J. Hill <steven.hill@cavium.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19709/
Cc: linux-mips@linux-mips.org
Cc: Chandrakala Chavva <cchavva@caviumnetworks.com>
---
 arch/mips/include/asm/octeon/cvmx-ciu-defs.h | 184 ++++++++-------------------
 1 file changed, 56 insertions(+), 128 deletions(-)

diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index f8ca7b7cca69..931e91115c5c 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -1,33 +1,14 @@
-/***********************license start***************
- * Author: Cavium Networks
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Octeon CIU definitions
  *
- * Contact: support@caviumnetworks.com
- * This file is part of the OCTEON SDK
- *
- * Copyright (c) 2003-2012 Cavium Networks
- *
- * This file is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License, Version 2, as
- * published by the Free Software Foundation.
- *
- * This file is distributed in the hope that it will be useful, but
- * AS-IS and WITHOUT ANY WARRANTY; without even the implied warranty
- * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE, TITLE, or
- * NONINFRINGEMENT.  See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this file; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
- * or visit http://www.gnu.org/licenses/.
- *
- * This file may also be available under a different license from Cavium.
- * Contact Cavium Networks for more information
- ***********************license end**************************************/
+ * Copyright (C) 2003-2018 Cavium, Inc.
+ */
 
 #ifndef __CVMX_CIU_DEFS_H__
 #define __CVMX_CIU_DEFS_H__
 
+#include <asm/bitfield.h>
+
 #define CVMX_CIU_BIST (CVMX_ADD_IO_SEG(0x0001070000000730ull))
 #define CVMX_CIU_BLOCK_INT (CVMX_ADD_IO_SEG(0x00010700000007C0ull))
 #define CVMX_CIU_DINT (CVMX_ADD_IO_SEG(0x0001070000000720ull))
@@ -209,142 +190,89 @@ static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
 	return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 }
 
+
 union cvmx_ciu_qlm {
 	uint64_t u64;
 	struct cvmx_ciu_qlm_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t g2bypass:1;
-		uint64_t reserved_53_62:10;
-		uint64_t g2deemph:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2margin:5;
-		uint64_t reserved_32_39:8;
-		uint64_t txbypass:1;
-		uint64_t reserved_21_30:10;
-		uint64_t txdeemph:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txmargin:5;
-		uint64_t reserved_4_7:4;
-		uint64_t lane_en:4;
-#else
-		uint64_t lane_en:4;
-		uint64_t reserved_4_7:4;
-		uint64_t txmargin:5;
-		uint64_t reserved_13_15:3;
-		uint64_t txdeemph:5;
-		uint64_t reserved_21_30:10;
-		uint64_t txbypass:1;
-		uint64_t reserved_32_39:8;
-		uint64_t g2margin:5;
-		uint64_t reserved_45_47:3;
-		uint64_t g2deemph:5;
-		uint64_t reserved_53_62:10;
-		uint64_t g2bypass:1;
-#endif
+		__BITFIELD_FIELD(uint64_t g2bypass:1,
+		__BITFIELD_FIELD(uint64_t reserved_53_62:10,
+		__BITFIELD_FIELD(uint64_t g2deemph:5,
+		__BITFIELD_FIELD(uint64_t reserved_45_47:3,
+		__BITFIELD_FIELD(uint64_t g2margin:5,
+		__BITFIELD_FIELD(uint64_t reserved_32_39:8,
+		__BITFIELD_FIELD(uint64_t txbypass:1,
+		__BITFIELD_FIELD(uint64_t reserved_21_30:10,
+		__BITFIELD_FIELD(uint64_t txdeemph:5,
+		__BITFIELD_FIELD(uint64_t reserved_13_15:3,
+		__BITFIELD_FIELD(uint64_t txmargin:5,
+		__BITFIELD_FIELD(uint64_t reserved_4_7:4,
+		__BITFIELD_FIELD(uint64_t lane_en:4,
+		;)))))))))))))
 	} s;
 };
 
 union cvmx_ciu_qlm_jtgc {
 	uint64_t u64;
 	struct cvmx_ciu_qlm_jtgc_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_17_63:47;
-		uint64_t bypass_ext:1;
-		uint64_t reserved_11_15:5;
-		uint64_t clk_div:3;
-		uint64_t reserved_7_7:1;
-		uint64_t mux_sel:3;
-		uint64_t bypass:4;
-#else
-		uint64_t bypass:4;
-		uint64_t mux_sel:3;
-		uint64_t reserved_7_7:1;
-		uint64_t clk_div:3;
-		uint64_t reserved_11_15:5;
-		uint64_t bypass_ext:1;
-		uint64_t reserved_17_63:47;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_17_63:47,
+		__BITFIELD_FIELD(uint64_t bypass_ext:1,
+		__BITFIELD_FIELD(uint64_t reserved_11_15:5,
+		__BITFIELD_FIELD(uint64_t clk_div:3,
+		__BITFIELD_FIELD(uint64_t reserved_7_7:1,
+		__BITFIELD_FIELD(uint64_t mux_sel:3,
+		__BITFIELD_FIELD(uint64_t bypass:4,
+		;)))))))
 	} s;
 };
 
 union cvmx_ciu_qlm_jtgd {
 	uint64_t u64;
 	struct cvmx_ciu_qlm_jtgd_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t capture:1;
-		uint64_t shift:1;
-		uint64_t update:1;
-		uint64_t reserved_45_60:16;
-		uint64_t select:5;
-		uint64_t reserved_37_39:3;
-		uint64_t shft_cnt:5;
-		uint64_t shft_reg:32;
-#else
-		uint64_t shft_reg:32;
-		uint64_t shft_cnt:5;
-		uint64_t reserved_37_39:3;
-		uint64_t select:5;
-		uint64_t reserved_45_60:16;
-		uint64_t update:1;
-		uint64_t shift:1;
-		uint64_t capture:1;
-#endif
+		__BITFIELD_FIELD(uint64_t capture:1,
+		__BITFIELD_FIELD(uint64_t shift:1,
+		__BITFIELD_FIELD(uint64_t update:1,
+		__BITFIELD_FIELD(uint64_t reserved_45_60:16,
+		__BITFIELD_FIELD(uint64_t select:5,
+		__BITFIELD_FIELD(uint64_t reserved_37_39:3,
+		__BITFIELD_FIELD(uint64_t shft_cnt:5,
+		__BITFIELD_FIELD(uint64_t shft_reg:32,
+		;))))))))
 	} s;
 };
 
 union cvmx_ciu_soft_prst {
 	uint64_t u64;
 	struct cvmx_ciu_soft_prst_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_3_63:61;
-		uint64_t host64:1;
-		uint64_t npi:1;
-		uint64_t soft_prst:1;
-#else
-		uint64_t soft_prst:1;
-		uint64_t npi:1;
-		uint64_t host64:1;
-		uint64_t reserved_3_63:61;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_3_63:61,
+		__BITFIELD_FIELD(uint64_t host64:1,
+		__BITFIELD_FIELD(uint64_t npi:1,
+		__BITFIELD_FIELD(uint64_t soft_prst:1,
+		;))))
 	} s;
 };
 
 union cvmx_ciu_timx {
 	uint64_t u64;
 	struct cvmx_ciu_timx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_37_63:27;
-		uint64_t one_shot:1;
-		uint64_t len:36;
-#else
-		uint64_t len:36;
-		uint64_t one_shot:1;
-		uint64_t reserved_37_63:27;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_37_63:27,
+		__BITFIELD_FIELD(uint64_t one_shot:1,
+		__BITFIELD_FIELD(uint64_t len:36,
+		;)))
 	} s;
 };
 
 union cvmx_ciu_wdogx {
 	uint64_t u64;
 	struct cvmx_ciu_wdogx_s {
-#ifdef __BIG_ENDIAN_BITFIELD
-		uint64_t reserved_46_63:18;
-		uint64_t gstopen:1;
-		uint64_t dstop:1;
-		uint64_t cnt:24;
-		uint64_t len:16;
-		uint64_t state:2;
-		uint64_t mode:2;
-#else
-		uint64_t mode:2;
-		uint64_t state:2;
-		uint64_t len:16;
-		uint64_t cnt:24;
-		uint64_t dstop:1;
-		uint64_t gstopen:1;
-		uint64_t reserved_46_63:18;
-#endif
+		__BITFIELD_FIELD(uint64_t reserved_46_63:18,
+		__BITFIELD_FIELD(uint64_t gstopen:1,
+		__BITFIELD_FIELD(uint64_t dstop:1,
+		__BITFIELD_FIELD(uint64_t cnt:24,
+		__BITFIELD_FIELD(uint64_t len:16,
+		__BITFIELD_FIELD(uint64_t state:2,
+		__BITFIELD_FIELD(uint64_t mode:2,
+		;)))))))
 	} s;
 };
 
-#endif
+#endif /* __CVMX_CIU_DEFS_H__ */
-- 
cgit v1.2.3


From c39f8ecff73b641067855fe27ef5761fdf61961a Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <steven.hill@cavium.com>
Date: Tue, 3 Jul 2018 16:44:23 -0500
Subject: MIPS: Octeon: Remove all unused CIU macros.

Get rid of all unused CIU macros and sort them. Verified with
'make allyesconfig' build test.

[paul.burton@mips.com:
  - Also checked via convoluted grep invocation for use of all removed
    macros within arch/mips/ & drivers/.]

Signed-off-by: Steven J. Hill <steven.hill@cavium.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19710/
Cc: linux-mips@linux-mips.org
Cc: Chandrakala Chavva <cchavva@caviumnetworks.com>
---
 arch/mips/include/asm/octeon/cvmx-ciu-defs.h | 70 +++++++---------------------
 1 file changed, 18 insertions(+), 52 deletions(-)

diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index 931e91115c5c..c9fa6b66627d 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -9,40 +9,35 @@
 
 #include <asm/bitfield.h>
 
-#define CVMX_CIU_BIST (CVMX_ADD_IO_SEG(0x0001070000000730ull))
-#define CVMX_CIU_BLOCK_INT (CVMX_ADD_IO_SEG(0x00010700000007C0ull))
-#define CVMX_CIU_DINT (CVMX_ADD_IO_SEG(0x0001070000000720ull))
-#define CVMX_CIU_EN2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x000107000000A600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_IOX_INT_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AE00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_EN2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x000107000000A000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000C800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP2_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000A800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x000107000000A200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CA00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP3_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AA00ull) + ((offset) & 15) * 8)
 #define CVMX_CIU_EN2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x000107000000A400ull) + ((offset) & 15) * 8)
 #define CVMX_CIU_EN2_PPX_IP4_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CC00ull) + ((offset) & 15) * 8)
 #define CVMX_CIU_EN2_PPX_IP4_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AC00ull) + ((offset) & 15) * 8)
 #define CVMX_CIU_FUSE (CVMX_ADD_IO_SEG(0x0001070000000728ull))
-#define CVMX_CIU_GSTOP (CVMX_ADD_IO_SEG(0x0001070000000710ull))
-#define CVMX_CIU_INT33_SUM0 (CVMX_ADD_IO_SEG(0x0001070000000110ull))
+#define CVMX_CIU_INT_SUM1 (CVMX_ADD_IO_SEG(0x0001070000000108ull))
 #define CVMX_CIU_INTX_EN0(offset) (CVMX_ADD_IO_SEG(0x0001070000000200ull) + ((offset) & 63) * 16)
 #define CVMX_CIU_INTX_EN0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002200ull) + ((offset) & 63) * 16)
 #define CVMX_CIU_INTX_EN0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006200ull) + ((offset) & 63) * 16)
 #define CVMX_CIU_INTX_EN1(offset) (CVMX_ADD_IO_SEG(0x0001070000000208ull) + ((offset) & 63) * 16)
 #define CVMX_CIU_INTX_EN1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002208ull) + ((offset) & 63) * 16)
 #define CVMX_CIU_INTX_EN1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN4_0(offset) (CVMX_ADD_IO_SEG(0x0001070000000C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C80ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1(offset) (CVMX_ADD_IO_SEG(0x0001070000000C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002C88ull) + ((offset) & 15) * 16)
-#define CVMX_CIU_INTX_EN4_1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006C88ull) + ((offset) & 15) * 16)
 #define CVMX_CIU_INTX_SUM0(offset) (CVMX_ADD_IO_SEG(0x0001070000000000ull) + ((offset) & 63) * 8)
-#define CVMX_CIU_INTX_SUM4(offset) (CVMX_ADD_IO_SEG(0x0001070000000C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_INT_DBG_SEL (CVMX_ADD_IO_SEG(0x00010700000007D0ull))
-#define CVMX_CIU_INT_SUM1 (CVMX_ADD_IO_SEG(0x0001070000000108ull))
+#define CVMX_CIU_NMI (CVMX_ADD_IO_SEG(0x0001070000000718ull))
+#define CVMX_CIU_PCI_INTA (CVMX_ADD_IO_SEG(0x0001070000000750ull))
+#define CVMX_CIU_PP_BIST_STAT (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
+#define CVMX_CIU_PP_DBG (CVMX_ADD_IO_SEG(0x0001070000000708ull))
+#define CVMX_CIU_PP_RST (CVMX_ADD_IO_SEG(0x0001070000000700ull))
+#define CVMX_CIU_QLM0 (CVMX_ADD_IO_SEG(0x0001070000000780ull))
+#define CVMX_CIU_QLM1 (CVMX_ADD_IO_SEG(0x0001070000000788ull))
+#define CVMX_CIU_QLM_JTGC (CVMX_ADD_IO_SEG(0x0001070000000768ull))
+#define CVMX_CIU_QLM_JTGD (CVMX_ADD_IO_SEG(0x0001070000000770ull))
+#define CVMX_CIU_SOFT_BIST (CVMX_ADD_IO_SEG(0x0001070000000738ull))
+#define CVMX_CIU_SOFT_PRST1 (CVMX_ADD_IO_SEG(0x0001070000000758ull))
+#define CVMX_CIU_SOFT_PRST (CVMX_ADD_IO_SEG(0x0001070000000748ull))
+#define CVMX_CIU_SOFT_RST (CVMX_ADD_IO_SEG(0x0001070000000740ull))
+#define CVMX_CIU_SUM2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008C00ull) + ((offset) & 15) * 8)
+#define CVMX_CIU_TIM_MULTI_CAST (CVMX_ADD_IO_SEG(0x000107000000C200ull))
+#define CVMX_CIU_TIMX(offset) (CVMX_ADD_IO_SEG(0x0001070000000480ull) + ((offset) & 15) * 8)
+
 static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned long offset)
 {
 	switch (cvmx_get_octeon_family()) {
@@ -97,10 +92,6 @@ static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned long offset)
 	return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
 }
 
-#define CVMX_CIU_NMI (CVMX_ADD_IO_SEG(0x0001070000000718ull))
-#define CVMX_CIU_PCI_INTA (CVMX_ADD_IO_SEG(0x0001070000000750ull))
-#define CVMX_CIU_PP_BIST_STAT (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_PP_DBG (CVMX_ADD_IO_SEG(0x0001070000000708ull))
 static inline uint64_t CVMX_CIU_PP_POKEX(unsigned long offset)
 {
 	switch (cvmx_get_octeon_family()) {
@@ -133,31 +124,6 @@ static inline uint64_t CVMX_CIU_PP_POKEX(unsigned long offset)
 	return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
 }
 
-#define CVMX_CIU_PP_RST (CVMX_ADD_IO_SEG(0x0001070000000700ull))
-#define CVMX_CIU_QLM0 (CVMX_ADD_IO_SEG(0x0001070000000780ull))
-#define CVMX_CIU_QLM1 (CVMX_ADD_IO_SEG(0x0001070000000788ull))
-#define CVMX_CIU_QLM2 (CVMX_ADD_IO_SEG(0x0001070000000790ull))
-#define CVMX_CIU_QLM3 (CVMX_ADD_IO_SEG(0x0001070000000798ull))
-#define CVMX_CIU_QLM4 (CVMX_ADD_IO_SEG(0x00010700000007A0ull))
-#define CVMX_CIU_QLM_DCOK (CVMX_ADD_IO_SEG(0x0001070000000760ull))
-#define CVMX_CIU_QLM_JTGC (CVMX_ADD_IO_SEG(0x0001070000000768ull))
-#define CVMX_CIU_QLM_JTGD (CVMX_ADD_IO_SEG(0x0001070000000770ull))
-#define CVMX_CIU_SOFT_BIST (CVMX_ADD_IO_SEG(0x0001070000000738ull))
-#define CVMX_CIU_SOFT_PRST (CVMX_ADD_IO_SEG(0x0001070000000748ull))
-#define CVMX_CIU_SOFT_PRST1 (CVMX_ADD_IO_SEG(0x0001070000000758ull))
-#define CVMX_CIU_SOFT_PRST2 (CVMX_ADD_IO_SEG(0x00010700000007D8ull))
-#define CVMX_CIU_SOFT_PRST3 (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_SOFT_RST (CVMX_ADD_IO_SEG(0x0001070000000740ull))
-#define CVMX_CIU_SUM1_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008600ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM1_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008000ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008200ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM1_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_IOX_INT(offset) (CVMX_ADD_IO_SEG(0x0001070000008E00ull) + ((offset) & 1) * 8)
-#define CVMX_CIU_SUM2_PPX_IP2(offset) (CVMX_ADD_IO_SEG(0x0001070000008800ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP3(offset) (CVMX_ADD_IO_SEG(0x0001070000008A00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_SUM2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIMX(offset) (CVMX_ADD_IO_SEG(0x0001070000000480ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIM_MULTI_CAST (CVMX_ADD_IO_SEG(0x000107000000C200ull))
 static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
 {
 	switch (cvmx_get_octeon_family()) {
-- 
cgit v1.2.3


From a730c7cd4534b3ffb62d1a692f05e313b058bc38 Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <steven.hill@cavium.com>
Date: Tue, 3 Jul 2018 16:44:24 -0500
Subject: MIPS: Octeon: Create simple macro for CIU registers.

Create new CVMX_CIU_ADDR macro to improve readability.

Signed-off-by: Steven J. Hill <steven.hill@cavium.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19712/
Cc: linux-mips@linux-mips.org
Cc: Chandrakala Chavva <cchavva@caviumnetworks.com>
---
 arch/mips/include/asm/octeon/cvmx-ciu-defs.h | 60 +++++++++++++++-------------
 1 file changed, 32 insertions(+), 28 deletions(-)

diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index c9fa6b66627d..652f1664c925 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -9,34 +9,38 @@
 
 #include <asm/bitfield.h>
 
-#define CVMX_CIU_EN2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x000107000000A400ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1C(offset) (CVMX_ADD_IO_SEG(0x000107000000CC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_EN2_PPX_IP4_W1S(offset) (CVMX_ADD_IO_SEG(0x000107000000AC00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_FUSE (CVMX_ADD_IO_SEG(0x0001070000000728ull))
-#define CVMX_CIU_INT_SUM1 (CVMX_ADD_IO_SEG(0x0001070000000108ull))
-#define CVMX_CIU_INTX_EN0(offset) (CVMX_ADD_IO_SEG(0x0001070000000200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN0_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006200ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1(offset) (CVMX_ADD_IO_SEG(0x0001070000000208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1C(offset) (CVMX_ADD_IO_SEG(0x0001070000002208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_EN1_W1S(offset) (CVMX_ADD_IO_SEG(0x0001070000006208ull) + ((offset) & 63) * 16)
-#define CVMX_CIU_INTX_SUM0(offset) (CVMX_ADD_IO_SEG(0x0001070000000000ull) + ((offset) & 63) * 8)
-#define CVMX_CIU_NMI (CVMX_ADD_IO_SEG(0x0001070000000718ull))
-#define CVMX_CIU_PCI_INTA (CVMX_ADD_IO_SEG(0x0001070000000750ull))
-#define CVMX_CIU_PP_BIST_STAT (CVMX_ADD_IO_SEG(0x00010700000007E0ull))
-#define CVMX_CIU_PP_DBG (CVMX_ADD_IO_SEG(0x0001070000000708ull))
-#define CVMX_CIU_PP_RST (CVMX_ADD_IO_SEG(0x0001070000000700ull))
-#define CVMX_CIU_QLM0 (CVMX_ADD_IO_SEG(0x0001070000000780ull))
-#define CVMX_CIU_QLM1 (CVMX_ADD_IO_SEG(0x0001070000000788ull))
-#define CVMX_CIU_QLM_JTGC (CVMX_ADD_IO_SEG(0x0001070000000768ull))
-#define CVMX_CIU_QLM_JTGD (CVMX_ADD_IO_SEG(0x0001070000000770ull))
-#define CVMX_CIU_SOFT_BIST (CVMX_ADD_IO_SEG(0x0001070000000738ull))
-#define CVMX_CIU_SOFT_PRST1 (CVMX_ADD_IO_SEG(0x0001070000000758ull))
-#define CVMX_CIU_SOFT_PRST (CVMX_ADD_IO_SEG(0x0001070000000748ull))
-#define CVMX_CIU_SOFT_RST (CVMX_ADD_IO_SEG(0x0001070000000740ull))
-#define CVMX_CIU_SUM2_PPX_IP4(offset) (CVMX_ADD_IO_SEG(0x0001070000008C00ull) + ((offset) & 15) * 8)
-#define CVMX_CIU_TIM_MULTI_CAST (CVMX_ADD_IO_SEG(0x000107000000C200ull))
-#define CVMX_CIU_TIMX(offset) (CVMX_ADD_IO_SEG(0x0001070000000480ull) + ((offset) & 15) * 8)
+#define CVMX_CIU_ADDR(addr, coreid, coremask, offset)			       \
+	(CVMX_ADD_IO_SEG(0x0001070000000000ull + addr##ull) +		       \
+	(((coreid) & (coremask)) * offset))
+
+#define CVMX_CIU_EN2_PPX_IP4(c)		CVMX_CIU_ADDR(0xA400, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1C(c)	CVMX_CIU_ADDR(0xCC00, c, 0x0F, 8)
+#define CVMX_CIU_EN2_PPX_IP4_W1S(c)	CVMX_CIU_ADDR(0xAC00, c, 0x0F, 8)
+#define CVMX_CIU_FUSE			CVMX_CIU_ADDR(0x0728, 0, 0x00, 0)
+#define CVMX_CIU_INT_SUM1		CVMX_CIU_ADDR(0x0108, 0, 0x00, 0)
+#define CVMX_CIU_INTX_EN0(c)		CVMX_CIU_ADDR(0x0200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1C(c)	CVMX_CIU_ADDR(0x2200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN0_W1S(c)	CVMX_CIU_ADDR(0x6200, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1(c)		CVMX_CIU_ADDR(0x0208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1C(c)	CVMX_CIU_ADDR(0x2208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_EN1_W1S(c)	CVMX_CIU_ADDR(0x6208, c, 0x3F, 16)
+#define CVMX_CIU_INTX_SUM0(c)		CVMX_CIU_ADDR(0x0000, c, 0x3F, 8)
+#define CVMX_CIU_NMI			CVMX_CIU_ADDR(0x0718, 0, 0x00, 0)
+#define CVMX_CIU_PCI_INTA		CVMX_CIU_ADDR(0x0750, 0, 0x00, 0)
+#define CVMX_CIU_PP_BIST_STAT		CVMX_CIU_ADDR(0x07E0, 0, 0x00, 0)
+#define CVMX_CIU_PP_DBG			CVMX_CIU_ADDR(0x0708, 0, 0x00, 0)
+#define CVMX_CIU_PP_RST			CVMX_CIU_ADDR(0x0700, 0, 0x00, 0)
+#define CVMX_CIU_QLM0			CVMX_CIU_ADDR(0x0780, 0, 0x00, 0)
+#define CVMX_CIU_QLM1			CVMX_CIU_ADDR(0x0788, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGC		CVMX_CIU_ADDR(0x0768, 0, 0x00, 0)
+#define CVMX_CIU_QLM_JTGD		CVMX_CIU_ADDR(0x0770, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_BIST		CVMX_CIU_ADDR(0x0738, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST1		CVMX_CIU_ADDR(0x0758, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_PRST		CVMX_CIU_ADDR(0x0748, 0, 0x00, 0)
+#define CVMX_CIU_SOFT_RST		CVMX_CIU_ADDR(0x0740, 0, 0x00, 0)
+#define CVMX_CIU_SUM2_PPX_IP4(c)	CVMX_CIU_ADDR(0x8C00, c, 0x0F, 8)
+#define CVMX_CIU_TIM_MULTI_CAST		CVMX_CIU_ADDR(0xC200, 0, 0x00, 0)
+#define CVMX_CIU_TIMX(c)		CVMX_CIU_ADDR(0x0480, c, 0x0F, 8)
 
 static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned long offset)
 {
-- 
cgit v1.2.3


From cfe1824411ad6bed3eb05efabbd43135592fcfd7 Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <steven.hill@cavium.com>
Date: Tue, 3 Jul 2018 16:44:25 -0500
Subject: MIPS: Octeon: Simplify CIU register functions.

Collapse and simplify switch statements in functions.

Signed-off-by: Steven J. Hill <steven.hill@cavium.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19713/
Cc: linux-mips@linux-mips.org
Cc: Chandrakala Chavva <cchavva@caviumnetworks.com>
---
 arch/mips/include/asm/octeon/cvmx-ciu-defs.h | 116 +++++----------------------
 1 file changed, 22 insertions(+), 94 deletions(-)

diff --git a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
index 652f1664c925..1d18be8cdddc 100644
--- a/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-ciu-defs.h
@@ -42,122 +42,50 @@
 #define CVMX_CIU_TIM_MULTI_CAST		CVMX_CIU_ADDR(0xC200, 0, 0x00, 0)
 #define CVMX_CIU_TIMX(c)		CVMX_CIU_ADDR(0x0480, c, 0x0F, 8)
 
-static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned long offset)
+static inline uint64_t CVMX_CIU_MBOX_CLRX(unsigned int coreid)
 {
-	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
-	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100600ull) + (offset) * 8;
-	}
-	return CVMX_ADD_IO_SEG(0x0001070000000680ull) + (offset) * 8;
+	if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+		return CVMX_CIU_ADDR(0x100100600, coreid, 0x0F, 8);
+	else
+		return CVMX_CIU_ADDR(0x000000680, coreid, 0x0F, 8);
 }
 
-static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned long offset)
+static inline uint64_t CVMX_CIU_MBOX_SETX(unsigned int coreid)
 {
-	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
-	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100400ull) + (offset) * 8;
-	}
-	return CVMX_ADD_IO_SEG(0x0001070000000600ull) + (offset) * 8;
+	if (cvmx_get_octeon_family() == (OCTEON_CN68XX & OCTEON_FAMILY_MASK))
+		return CVMX_CIU_ADDR(0x100100400, coreid, 0x0F, 8);
+	else
+		return CVMX_CIU_ADDR(0x000000600, coreid, 0x0F, 8);
 }
 
-static inline uint64_t CVMX_CIU_PP_POKEX(unsigned long offset)
+static inline uint64_t CVMX_CIU_PP_POKEX(unsigned int coreid)
 {
 	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
 	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100200ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x100100200, coreid, 0x0F, 8);
 	case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001010000030000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x000030000, coreid, 0x0F, 8) -
+			0x60000000000ull;
+	default:
+		return CVMX_CIU_ADDR(0x000000580, coreid, 0x0F, 8);
 	}
-	return CVMX_ADD_IO_SEG(0x0001070000000580ull) + (offset) * 8;
 }
 
-static inline uint64_t CVMX_CIU_WDOGX(unsigned long offset)
+static inline uint64_t CVMX_CIU_WDOGX(unsigned int coreid)
 {
 	switch (cvmx_get_octeon_family()) {
-	case OCTEON_CN30XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN52XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CNF71XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN61XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN70XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN31XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN50XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN38XX & OCTEON_FAMILY_MASK:
-	case OCTEON_CN58XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN56XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN66XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
-	case OCTEON_CN63XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 	case OCTEON_CN68XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001070100100000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x100100000, coreid, 0x0F, 8);
 	case OCTEON_CNF75XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN73XX & OCTEON_FAMILY_MASK:
 	case OCTEON_CN78XX & OCTEON_FAMILY_MASK:
-		return CVMX_ADD_IO_SEG(0x0001010000020000ull) + (offset) * 8;
+		return CVMX_CIU_ADDR(0x000020000, coreid, 0x0F, 8) -
+			0x60000000000ull;
+	default:
+		return CVMX_CIU_ADDR(0x000000500, coreid, 0x0F, 8);
 	}
-	return CVMX_ADD_IO_SEG(0x0001070000000500ull) + (offset) * 8;
 }
 
 
-- 
cgit v1.2.3


From 1decd2ec22b91fc4ea360ddc5cc21811cd64bd68 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 30 Jun 2018 13:17:29 +0200
Subject: net: dsa: Add DT bindings for Vitesse VSC73xx switches

This adds the device tree bindings for the Vitesse VSC73xx
switches. We also add the vendor name for Vitesse.

Cc: devicetree@vger.kernel.org
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../bindings/net/dsa/vitesse,vsc73xx.txt           | 81 ++++++++++++++++++++++
 .../devicetree/bindings/vendor-prefixes.txt        |  1 +
 2 files changed, 82 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt

diff --git a/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
new file mode 100644
index 000000000000..ed4710c40641
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/vitesse,vsc73xx.txt
@@ -0,0 +1,81 @@
+Vitesse VSC73xx Switches
+========================
+
+This defines device tree bindings for the Vitesse VSC73xx switch chips.
+The Vitesse company has been acquired by Microsemi and Microsemi in turn
+acquired by Microchip but retains this vendor branding.
+
+The currently supported switch chips are:
+Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+
+The device tree node is an SPI device so it must reside inside a SPI bus
+device tree node, see spi/spi-bus.txt
+
+Required properties:
+
+- compatible: must be exactly one of:
+	"vitesse,vsc7385"
+	"vitesse,vsc7388"
+	"vitesse,vsc7395"
+	"vitesse,vsc7398"
+- gpio-controller: indicates that this switch is also a GPIO controller,
+  see gpio/gpio.txt
+- #gpio-cells: this must be set to <2> and indicates that we are a twocell
+  GPIO controller, see gpio/gpio.txt
+
+Optional properties:
+
+- reset-gpios: a handle to a GPIO line that can issue reset of the chip.
+  It should be tagged as active low.
+
+Required subnodes:
+
+See net/dsa/dsa.txt for a list of additional required and optional properties
+and subnodes of DSA switches.
+
+Examples:
+
+switch@0 {
+	compatible = "vitesse,vsc7395";
+	reg = <0>;
+	/* Specified for 2.5 MHz or below */
+	spi-max-frequency = <2500000>;
+	gpio-controller;
+	#gpio-cells = <2>;
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		port@0 {
+			reg = <0>;
+			label = "lan1";
+		};
+		port@1 {
+			reg = <1>;
+			label = "lan2";
+		};
+		port@2 {
+			reg = <2>;
+			label = "lan3";
+		};
+		port@3 {
+			reg = <3>;
+			label = "lan4";
+		};
+		vsc: port@6 {
+			reg = <6>;
+			label = "cpu";
+			ethernet = <&gmac1>;
+			phy-mode = "rgmii";
+			fixed-link {
+				speed = <1000>;
+				full-duplex;
+				pause;
+			};
+		};
+	};
+};
diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 7cad066191ee..3e5398f87eac 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -395,6 +395,7 @@ v3	V3 Semiconductor
 variscite	Variscite Ltd.
 via	VIA Technologies, Inc.
 virtio	Virtual I/O Device Specification, developed by the OASIS consortium
+vitesse	Vitesse Semiconductor Corporation
 vivante	Vivante Corporation
 vocore VoCore Studio
 voipac	Voipac Technologies s.r.o.
-- 
cgit v1.2.3


From 975ae7c69d51154fccd7024d2e7f0347c34c6f72 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 30 Jun 2018 13:17:30 +0200
Subject: net: phy: vitesse: Add support for VSC73xx

The VSC7385, VSC7388, VSC7395 and VSC7398 are integrated
switch/router chips for 5+1 or 8-port switches/routers. When
managed directly by Linux using DSA we need to do a special
set-up "dance" on the PHY. Unfortunately these sequences
switches the PHY to undocumented pages named 2a30 and 52b6
and does undocumented things. It is described by these opaque
sequences also in the reference manual. This is a best
effort to integrate it anyways.

Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/vitesse.c | 175 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 175 insertions(+)

diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
index d9dd8fbfffc7..fbf9ad429593 100644
--- a/drivers/net/phy/vitesse.c
+++ b/drivers/net/phy/vitesse.c
@@ -72,6 +72,10 @@
 #define PHY_ID_VSC8572			0x000704d0
 #define PHY_ID_VSC8574			0x000704a0
 #define PHY_ID_VSC8601			0x00070420
+#define PHY_ID_VSC7385			0x00070450
+#define PHY_ID_VSC7388			0x00070480
+#define PHY_ID_VSC7395			0x00070550
+#define PHY_ID_VSC7398			0x00070580
 #define PHY_ID_VSC8662			0x00070660
 #define PHY_ID_VSC8221			0x000fc550
 #define PHY_ID_VSC8211			0x000fc4b0
@@ -116,6 +120,137 @@ static int vsc824x_config_init(struct phy_device *phydev)
 	return err;
 }
 
+#define VSC73XX_EXT_PAGE_ACCESS 0x1f
+
+static int vsc73xx_read_page(struct phy_device *phydev)
+{
+	return __phy_read(phydev, VSC73XX_EXT_PAGE_ACCESS);
+}
+
+static int vsc73xx_write_page(struct phy_device *phydev, int page)
+{
+	return __phy_write(phydev, VSC73XX_EXT_PAGE_ACCESS, page);
+}
+
+static void vsc73xx_config_init(struct phy_device *phydev)
+{
+	/* Receiver init */
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x0c, 0x0300, 0x0200);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	/* Config LEDs 0x61 */
+	phy_modify(phydev, MII_TPISTATUS, 0xff00, 0x0061);
+}
+
+static int vsc738x_config_init(struct phy_device *phydev)
+{
+	u16 rev;
+	/* This magic sequence appear in the application note
+	 * "VSC7385/7388 PHY Configuration".
+	 *
+	 * Maybe one day we will get to know what it all means.
+	 */
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0200);
+	phy_write(phydev, 0x1f, 0x52b5);
+	phy_write(phydev, 0x10, 0xb68a);
+	phy_modify(phydev, 0x12, 0xff07, 0x0003);
+	phy_modify(phydev, 0x11, 0x00ff, 0x00a2);
+	phy_write(phydev, 0x10, 0x968a);
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0000);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	/* Read revision */
+	rev = phy_read(phydev, MII_PHYSID2);
+	rev &= 0x0f;
+
+	/* Special quirk for revision 0 */
+	if (rev == 0) {
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_modify(phydev, 0x08, 0x0200, 0x0200);
+		phy_write(phydev, 0x1f, 0x52b5);
+		phy_write(phydev, 0x12, 0x0000);
+		phy_write(phydev, 0x11, 0x0689);
+		phy_write(phydev, 0x10, 0x8f92);
+		phy_write(phydev, 0x1f, 0x52b5);
+		phy_write(phydev, 0x12, 0x0000);
+		phy_write(phydev, 0x11, 0x0e35);
+		phy_write(phydev, 0x10, 0x9786);
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_modify(phydev, 0x08, 0x0200, 0x0000);
+		phy_write(phydev, 0x17, 0xff80);
+		phy_write(phydev, 0x17, 0x0000);
+	}
+
+	phy_write(phydev, 0x1f, 0x0000);
+	phy_write(phydev, 0x12, 0x0048);
+
+	if (rev == 0) {
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_write(phydev, 0x14, 0x6600);
+		phy_write(phydev, 0x1f, 0x0000);
+		phy_write(phydev, 0x18, 0xa24e);
+	} else {
+		phy_write(phydev, 0x1f, 0x2a30);
+		phy_modify(phydev, 0x16, 0x0fc0, 0x0240);
+		phy_modify(phydev, 0x14, 0x6000, 0x4000);
+		/* bits 14-15 in extended register 0x14 controls DACG amplitude
+		 * 6 = -8%, 2 is hardware default
+		 */
+		phy_write(phydev, 0x1f, 0x0001);
+		phy_modify(phydev, 0x14, 0xe000, 0x6000);
+		phy_write(phydev, 0x1f, 0x0000);
+	}
+
+	vsc73xx_config_init(phydev);
+
+	return genphy_config_init(phydev);
+}
+
+static int vsc739x_config_init(struct phy_device *phydev)
+{
+	/* This magic sequence appears in the VSC7395 SparX-G5e application
+	 * note "VSC7395/VSC7398 PHY Configuration"
+	 *
+	 * Maybe one day we will get to know what it all means.
+	 */
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0200);
+	phy_write(phydev, 0x1f, 0x52b5);
+	phy_write(phydev, 0x10, 0xb68a);
+	phy_modify(phydev, 0x12, 0xff07, 0x0003);
+	phy_modify(phydev, 0x11, 0x00ff, 0x00a2);
+	phy_write(phydev, 0x10, 0x968a);
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x08, 0x0200, 0x0000);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	phy_write(phydev, 0x1f, 0x0000);
+	phy_write(phydev, 0x12, 0x0048);
+	phy_write(phydev, 0x1f, 0x2a30);
+	phy_modify(phydev, 0x16, 0x0fc0, 0x0240);
+	phy_modify(phydev, 0x14, 0x6000, 0x4000);
+	phy_write(phydev, 0x1f, 0x0001);
+	phy_modify(phydev, 0x14, 0xe000, 0x6000);
+	phy_write(phydev, 0x1f, 0x0000);
+
+	vsc73xx_config_init(phydev);
+
+	return genphy_config_init(phydev);
+}
+
+static int vsc73xx_config_aneg(struct phy_device *phydev)
+{
+	/* The VSC73xx switches does not like to be instructed to
+	 * do autonegotiation in any way, it prefers that you just go
+	 * with the power-on/reset defaults. Writing some registers will
+	 * just make autonegotiation permanently fail.
+	 */
+	return 0;
+}
+
 /* This adds a skew for both TX and RX clocks, so the skew should only be
  * applied to "rgmii-id" interfaces. It may not work as expected
  * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces. */
@@ -318,6 +453,42 @@ static struct phy_driver vsc82xx_driver[] = {
 	.config_init    = &vsc8601_config_init,
 	.ack_interrupt  = &vsc824x_ack_interrupt,
 	.config_intr    = &vsc82xx_config_intr,
+}, {
+	.phy_id         = PHY_ID_VSC7385,
+	.name           = "Vitesse VSC7385",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc738x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
+}, {
+	.phy_id         = PHY_ID_VSC7388,
+	.name           = "Vitesse VSC7388",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc738x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
+}, {
+	.phy_id         = PHY_ID_VSC7395,
+	.name           = "Vitesse VSC7395",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc739x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
+}, {
+	.phy_id         = PHY_ID_VSC7398,
+	.name           = "Vitesse VSC7398",
+	.phy_id_mask    = 0x000ffff0,
+	.features       = PHY_GBIT_FEATURES,
+	.config_init    = vsc739x_config_init,
+	.config_aneg    = vsc73xx_config_aneg,
+	.read_page      = vsc73xx_read_page,
+	.write_page     = vsc73xx_write_page,
 }, {
 	.phy_id         = PHY_ID_VSC8662,
 	.name           = "Vitesse VSC8662",
@@ -358,6 +529,10 @@ static struct mdio_device_id __maybe_unused vitesse_tbl[] = {
 	{ PHY_ID_VSC8514, 0x000ffff0 },
 	{ PHY_ID_VSC8572, 0x000ffff0 },
 	{ PHY_ID_VSC8574, 0x000ffff0 },
+	{ PHY_ID_VSC7385, 0x000ffff0 },
+	{ PHY_ID_VSC7388, 0x000ffff0 },
+	{ PHY_ID_VSC7395, 0x000ffff0 },
+	{ PHY_ID_VSC7398, 0x000ffff0 },
 	{ PHY_ID_VSC8662, 0x000ffff0 },
 	{ PHY_ID_VSC8221, 0x000ffff0 },
 	{ PHY_ID_VSC8211, 0x000ffff0 },
-- 
cgit v1.2.3


From 05bd97fc559df4d26e33b0714b5327de8f610971 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 30 Jun 2018 13:17:31 +0200
Subject: net: dsa: Add Vitesse VSC73xx DSA router driver

This adds a DSA driver for:

Vitesse VSC7385 SparX-G5 5-port Integrated Gigabit Ethernet Switch
Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch

These switches have a built-in 8051 CPU and can download and execute
firmware in this CPU. They can also be configured to use an external
CPU handling the switch in a memory-mapped manner by connecting to
that external CPU's memory bus.

This driver (currently) only takes control of the switch chip over
SPI and configures it to route packages around when connected to a
CPU port. The chip has embedded PHYs and VLAN support so we model it
using DSA as a best fit so we can easily add VLAN support and maybe
later also exploit the internal frame header to get more direct
control over the switch.

The four built-in GPIO lines are exposed using a standard GPIO chip.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/Kconfig           |   11 +
 drivers/net/dsa/Makefile          |    1 +
 drivers/net/dsa/vitesse-vsc73xx.c | 1364 +++++++++++++++++++++++++++++++++++++
 3 files changed, 1376 insertions(+)
 create mode 100644 drivers/net/dsa/vitesse-vsc73xx.c

diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 2b81b97e994f..733653d8359a 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -76,4 +76,15 @@ config NET_DSA_SMSC_LAN9303_MDIO
 	  Enable access functions if the SMSC/Microchip LAN9303 is configured
 	  for MDIO managed mode.
 
+config NET_DSA_VITESSE_VSC73XX
+	tristate "Vitesse VSC7385/7388/7395/7398 support"
+	depends on OF && SPI
+	depends on NET_DSA
+	select FIXED_PHY
+	select VITESSE_PHY
+	select GPIOLIB
+	---help---
+	  This enables support for the Vitesse VSC7385, VSC7388,
+	  VSC7395 and VSC7398 SparX integrated ethernet switches.
+
 endmenu
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index 15c2a831edf1..d4f873ae2f6a 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_NET_DSA_QCA8K)	+= qca8k.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
+obj-$(CONFIG_NET_DSA_VITESSE_VSC73XX) += vitesse-vsc73xx.o
 obj-y				+= b53/
 obj-y				+= microchip/
 obj-y				+= mv88e6xxx/
diff --git a/drivers/net/dsa/vitesse-vsc73xx.c b/drivers/net/dsa/vitesse-vsc73xx.c
new file mode 100644
index 000000000000..a4fc260006de
--- /dev/null
+++ b/drivers/net/dsa/vitesse-vsc73xx.c
@@ -0,0 +1,1364 @@
+// SPDX-License-Identifier: GPL-2.0
+/* DSA driver for:
+ * Vitesse VSC7385 SparX-G5 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7388 SparX-G8 8-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7395 SparX-G5e 5+1-port Integrated Gigabit Ethernet Switch
+ * Vitesse VSC7398 SparX-G8e 8-port Integrated Gigabit Ethernet Switch
+ *
+ * These switches have a built-in 8051 CPU and can download and execute a
+ * firmware in this CPU. They can also be configured to use an external CPU
+ * handling the switch in a memory-mapped manner by connecting to that external
+ * CPU's memory bus.
+ *
+ * This driver (currently) only takes control of the switch chip over SPI and
+ * configures it to route packages around when connected to a CPU port. The
+ * chip has embedded PHYs and VLAN support so we model it using DSA.
+ *
+ * Copyright (C) 2018 Linus Wallej <linus.walleij@linaro.org>
+ * Includes portions of code from the firmware uploader by:
+ * Copyright (C) 2009 Gabor Juhos <juhosg@openwrt.org>
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+#include <linux/etherdevice.h>
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/driver.h>
+#include <linux/random.h>
+#include <net/dsa.h>
+
+#define VSC73XX_BLOCK_MAC	0x1 /* Subblocks 0-4, 6 (CPU port) */
+#define VSC73XX_BLOCK_ANALYZER	0x2 /* Only subblock 0 */
+#define VSC73XX_BLOCK_MII	0x3 /* Subblocks 0 and 1 */
+#define VSC73XX_BLOCK_MEMINIT	0x3 /* Only subblock 2 */
+#define VSC73XX_BLOCK_CAPTURE	0x4 /* Only subblock 2 */
+#define VSC73XX_BLOCK_ARBITER	0x5 /* Only subblock 0 */
+#define VSC73XX_BLOCK_SYSTEM	0x7 /* Only subblock 0 */
+
+#define CPU_PORT	6 /* CPU port */
+
+/* MAC Block registers */
+#define VSC73XX_MAC_CFG		0x00
+#define VSC73XX_MACHDXGAP	0x02
+#define VSC73XX_FCCONF		0x04
+#define VSC73XX_FCMACHI		0x08
+#define VSC73XX_FCMACLO		0x0c
+#define VSC73XX_MAXLEN		0x10
+#define VSC73XX_ADVPORTM	0x19
+#define VSC73XX_TXUPDCFG	0x24
+#define VSC73XX_TXQ_SELECT_CFG	0x28
+#define VSC73XX_RXOCT		0x50
+#define VSC73XX_TXOCT		0x51
+#define VSC73XX_C_RX0		0x52
+#define VSC73XX_C_RX1		0x53
+#define VSC73XX_C_RX2		0x54
+#define VSC73XX_C_TX0		0x55
+#define VSC73XX_C_TX1		0x56
+#define VSC73XX_C_TX2		0x57
+#define VSC73XX_C_CFG		0x58
+#define VSC73XX_CAT_DROP	0x6e
+#define VSC73XX_CAT_PR_MISC_L2	0x6f
+#define VSC73XX_CAT_PR_USR_PRIO	0x75
+#define VSC73XX_Q_MISC_CONF	0xdf
+
+/* MAC_CFG register bits */
+#define VSC73XX_MAC_CFG_WEXC_DIS	BIT(31)
+#define VSC73XX_MAC_CFG_PORT_RST	BIT(29)
+#define VSC73XX_MAC_CFG_TX_EN		BIT(28)
+#define VSC73XX_MAC_CFG_SEED_LOAD	BIT(27)
+#define VSC73XX_MAC_CFG_SEED_MASK	GENMASK(26, 19)
+#define VSC73XX_MAC_CFG_SEED_OFFSET	19
+#define VSC73XX_MAC_CFG_FDX		BIT(18)
+#define VSC73XX_MAC_CFG_GIGA_MODE	BIT(17)
+#define VSC73XX_MAC_CFG_RX_EN		BIT(16)
+#define VSC73XX_MAC_CFG_VLAN_DBLAWR	BIT(15)
+#define VSC73XX_MAC_CFG_VLAN_AWR	BIT(14)
+#define VSC73XX_MAC_CFG_100_BASE_T	BIT(13) /* Not in manual */
+#define VSC73XX_MAC_CFG_TX_IPG_MASK	GENMASK(10, 6)
+#define VSC73XX_MAC_CFG_TX_IPG_OFFSET	6
+#define VSC73XX_MAC_CFG_TX_IPG_1000M	(6 << VSC73XX_MAC_CFG_TX_IPG_OFFSET)
+#define VSC73XX_MAC_CFG_TX_IPG_100_10M	(17 << VSC73XX_MAC_CFG_TX_IPG_OFFSET)
+#define VSC73XX_MAC_CFG_MAC_RX_RST	BIT(5)
+#define VSC73XX_MAC_CFG_MAC_TX_RST	BIT(4)
+#define VSC73XX_MAC_CFG_CLK_SEL_MASK	GENMASK(2, 0)
+#define VSC73XX_MAC_CFG_CLK_SEL_OFFSET	0
+#define VSC73XX_MAC_CFG_CLK_SEL_1000M	1
+#define VSC73XX_MAC_CFG_CLK_SEL_100M	2
+#define VSC73XX_MAC_CFG_CLK_SEL_10M	3
+#define VSC73XX_MAC_CFG_CLK_SEL_EXT	4
+
+#define VSC73XX_MAC_CFG_1000M_F_PHY	(VSC73XX_MAC_CFG_FDX | \
+					 VSC73XX_MAC_CFG_GIGA_MODE | \
+					 VSC73XX_MAC_CFG_TX_IPG_1000M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_100_10M_F_PHY	(VSC73XX_MAC_CFG_FDX | \
+					 VSC73XX_MAC_CFG_TX_IPG_100_10M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_100_10M_H_PHY	(VSC73XX_MAC_CFG_TX_IPG_100_10M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_EXT)
+#define VSC73XX_MAC_CFG_1000M_F_RGMII	(VSC73XX_MAC_CFG_FDX | \
+					 VSC73XX_MAC_CFG_GIGA_MODE | \
+					 VSC73XX_MAC_CFG_TX_IPG_1000M | \
+					 VSC73XX_MAC_CFG_CLK_SEL_1000M)
+#define VSC73XX_MAC_CFG_RESET		(VSC73XX_MAC_CFG_PORT_RST | \
+					 VSC73XX_MAC_CFG_MAC_RX_RST | \
+					 VSC73XX_MAC_CFG_MAC_TX_RST)
+
+/* Flow control register bits */
+#define VSC73XX_FCCONF_ZERO_PAUSE_EN	BIT(17)
+#define VSC73XX_FCCONF_FLOW_CTRL_OBEY	BIT(16)
+#define VSC73XX_FCCONF_PAUSE_VAL_MASK	GENMASK(15, 0)
+
+/* ADVPORTM advanced port setup register bits */
+#define VSC73XX_ADVPORTM_IFG_PPM	BIT(7)
+#define VSC73XX_ADVPORTM_EXC_COL_CONT	BIT(6)
+#define VSC73XX_ADVPORTM_EXT_PORT	BIT(5)
+#define VSC73XX_ADVPORTM_INV_GTX	BIT(4)
+#define VSC73XX_ADVPORTM_ENA_GTX	BIT(3)
+#define VSC73XX_ADVPORTM_DDR_MODE	BIT(2)
+#define VSC73XX_ADVPORTM_IO_LOOPBACK	BIT(1)
+#define VSC73XX_ADVPORTM_HOST_LOOPBACK	BIT(0)
+
+/* CAT_DROP categorizer frame dropping register bits */
+#define VSC73XX_CAT_DROP_DROP_MC_SMAC_ENA	BIT(6)
+#define VSC73XX_CAT_DROP_FWD_CTRL_ENA		BIT(4)
+#define VSC73XX_CAT_DROP_FWD_PAUSE_ENA		BIT(3)
+#define VSC73XX_CAT_DROP_UNTAGGED_ENA		BIT(2)
+#define VSC73XX_CAT_DROP_TAGGED_ENA		BIT(1)
+#define VSC73XX_CAT_DROP_NULL_MAC_ENA		BIT(0)
+
+#define VSC73XX_Q_MISC_CONF_EXTENT_MEM		BIT(31)
+#define VSC73XX_Q_MISC_CONF_EARLY_TX_MASK	GENMASK(4, 1)
+#define VSC73XX_Q_MISC_CONF_EARLY_TX_512	(1 << 1)
+#define VSC73XX_Q_MISC_CONF_MAC_PAUSE_MODE	BIT(0)
+
+/* Frame analyzer block 2 registers */
+#define VSC73XX_STORMLIMIT	0x02
+#define VSC73XX_ADVLEARN	0x03
+#define VSC73XX_IFLODMSK	0x04
+#define VSC73XX_VLANMASK	0x05
+#define VSC73XX_MACHDATA	0x06
+#define VSC73XX_MACLDATA	0x07
+#define VSC73XX_ANMOVED		0x08
+#define VSC73XX_ANAGEFIL	0x09
+#define VSC73XX_ANEVENTS	0x0a
+#define VSC73XX_ANCNTMASK	0x0b
+#define VSC73XX_ANCNTVAL	0x0c
+#define VSC73XX_LEARNMASK	0x0d
+#define VSC73XX_UFLODMASK	0x0e
+#define VSC73XX_MFLODMASK	0x0f
+#define VSC73XX_RECVMASK	0x10
+#define VSC73XX_AGGRCTRL	0x20
+#define VSC73XX_AGGRMSKS	0x30 /* Until 0x3f */
+#define VSC73XX_DSTMASKS	0x40 /* Until 0x7f */
+#define VSC73XX_SRCMASKS	0x80 /* Until 0x87 */
+#define VSC73XX_CAPENAB		0xa0
+#define VSC73XX_MACACCESS	0xb0
+#define VSC73XX_IPMCACCESS	0xb1
+#define VSC73XX_MACTINDX	0xc0
+#define VSC73XX_VLANACCESS	0xd0
+#define VSC73XX_VLANTIDX	0xe0
+#define VSC73XX_AGENCTRL	0xf0
+#define VSC73XX_CAPRST		0xff
+
+#define VSC73XX_MACACCESS_CPU_COPY		BIT(14)
+#define VSC73XX_MACACCESS_FWD_KILL		BIT(13)
+#define VSC73XX_MACACCESS_IGNORE_VLAN		BIT(12)
+#define VSC73XX_MACACCESS_AGED_FLAG		BIT(11)
+#define VSC73XX_MACACCESS_VALID			BIT(10)
+#define VSC73XX_MACACCESS_LOCKED		BIT(9)
+#define VSC73XX_MACACCESS_DEST_IDX_MASK		GENMASK(8, 3)
+#define VSC73XX_MACACCESS_CMD_MASK		GENMASK(2, 0)
+#define VSC73XX_MACACCESS_CMD_IDLE		0
+#define VSC73XX_MACACCESS_CMD_LEARN		1
+#define VSC73XX_MACACCESS_CMD_FORGET		2
+#define VSC73XX_MACACCESS_CMD_AGE_TABLE		3
+#define VSC73XX_MACACCESS_CMD_FLUSH_TABLE	4
+#define VSC73XX_MACACCESS_CMD_CLEAR_TABLE	5
+#define VSC73XX_MACACCESS_CMD_READ_ENTRY	6
+#define VSC73XX_MACACCESS_CMD_WRITE_ENTRY	7
+
+#define VSC73XX_VLANACCESS_LEARN_DISABLED	BIT(30)
+#define VSC73XX_VLANACCESS_VLAN_MIRROR		BIT(29)
+#define VSC73XX_VLANACCESS_VLAN_SRC_CHECK	BIT(28)
+#define VSC73XX_VLANACCESS_VLAN_PORT_MASK	GENMASK(9, 2)
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_MASK	GENMASK(2, 0)
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_IDLE	0
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_READ_ENTRY	1
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_WRITE_ENTRY	2
+#define VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE	3
+
+/* MII block 3 registers */
+#define VSC73XX_MII_STAT	0x0
+#define VSC73XX_MII_CMD		0x1
+#define VSC73XX_MII_DATA	0x2
+
+/* Arbiter block 5 registers */
+#define VSC73XX_ARBEMPTY		0x0c
+#define VSC73XX_ARBDISC			0x0e
+#define VSC73XX_SBACKWDROP		0x12
+#define VSC73XX_DBACKWDROP		0x13
+#define VSC73XX_ARBBURSTPROB		0x15
+
+/* System block 7 registers */
+#define VSC73XX_ICPU_SIPAD		0x01
+#define VSC73XX_GMIIDELAY		0x05
+#define VSC73XX_ICPU_CTRL		0x10
+#define VSC73XX_ICPU_ADDR		0x11
+#define VSC73XX_ICPU_SRAM		0x12
+#define VSC73XX_HWSEM			0x13
+#define VSC73XX_GLORESET		0x14
+#define VSC73XX_ICPU_MBOX_VAL		0x15
+#define VSC73XX_ICPU_MBOX_SET		0x16
+#define VSC73XX_ICPU_MBOX_CLR		0x17
+#define VSC73XX_CHIPID			0x18
+#define VSC73XX_GPIO			0x34
+
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_NONE	0
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_4_NS	1
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_1_7_NS	2
+#define VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS	3
+
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_NONE	(0 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_4_NS	(1 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_1_7_NS	(2 << 4)
+#define VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS	(3 << 4)
+
+#define VSC73XX_ICPU_CTRL_WATCHDOG_RST	BIT(31)
+#define VSC73XX_ICPU_CTRL_CLK_DIV_MASK	GENMASK(12, 8)
+#define VSC73XX_ICPU_CTRL_SRST_HOLD	BIT(7)
+#define VSC73XX_ICPU_CTRL_ICPU_PI_EN	BIT(6)
+#define VSC73XX_ICPU_CTRL_BOOT_EN	BIT(3)
+#define VSC73XX_ICPU_CTRL_EXT_ACC_EN	BIT(2)
+#define VSC73XX_ICPU_CTRL_CLK_EN	BIT(1)
+#define VSC73XX_ICPU_CTRL_SRST		BIT(0)
+
+#define VSC73XX_CHIPID_ID_SHIFT		12
+#define VSC73XX_CHIPID_ID_MASK		0xffff
+#define VSC73XX_CHIPID_REV_SHIFT	28
+#define VSC73XX_CHIPID_REV_MASK		0xf
+#define VSC73XX_CHIPID_ID_7385		0x7385
+#define VSC73XX_CHIPID_ID_7388		0x7388
+#define VSC73XX_CHIPID_ID_7395		0x7395
+#define VSC73XX_CHIPID_ID_7398		0x7398
+
+#define VSC73XX_GLORESET_STROBE		BIT(4)
+#define VSC73XX_GLORESET_ICPU_LOCK	BIT(3)
+#define VSC73XX_GLORESET_MEM_LOCK	BIT(2)
+#define VSC73XX_GLORESET_PHY_RESET	BIT(1)
+#define VSC73XX_GLORESET_MASTER_RESET	BIT(0)
+
+#define VSC73XX_CMD_MODE_READ		0
+#define VSC73XX_CMD_MODE_WRITE		1
+#define VSC73XX_CMD_MODE_SHIFT		4
+#define VSC73XX_CMD_BLOCK_SHIFT		5
+#define VSC73XX_CMD_BLOCK_MASK		0x7
+#define VSC73XX_CMD_SUBBLOCK_MASK	0xf
+
+#define VSC7385_CLOCK_DELAY		((3 << 4) | 3)
+#define VSC7385_CLOCK_DELAY_MASK	((3 << 4) | 3)
+
+#define VSC73XX_ICPU_CTRL_STOP	(VSC73XX_ICPU_CTRL_SRST_HOLD | \
+				 VSC73XX_ICPU_CTRL_BOOT_EN | \
+				 VSC73XX_ICPU_CTRL_EXT_ACC_EN)
+
+#define VSC73XX_ICPU_CTRL_START	(VSC73XX_ICPU_CTRL_CLK_DIV | \
+				 VSC73XX_ICPU_CTRL_BOOT_EN | \
+				 VSC73XX_ICPU_CTRL_CLK_EN | \
+				 VSC73XX_ICPU_CTRL_SRST)
+
+/**
+ * struct vsc73xx - VSC73xx state container
+ */
+struct vsc73xx {
+	struct device		*dev;
+	struct gpio_desc	*reset;
+	struct spi_device	*spi;
+	struct dsa_switch	*ds;
+	struct gpio_chip	gc;
+	u16			chipid;
+	u8			addr[ETH_ALEN];
+	struct mutex		lock; /* Protects SPI traffic */
+};
+
+#define IS_7385(a) ((a)->chipid == VSC73XX_CHIPID_ID_7385)
+#define IS_7388(a) ((a)->chipid == VSC73XX_CHIPID_ID_7388)
+#define IS_7395(a) ((a)->chipid == VSC73XX_CHIPID_ID_7395)
+#define IS_7398(a) ((a)->chipid == VSC73XX_CHIPID_ID_7398)
+#define IS_739X(a) (IS_7395(a) || IS_7398(a))
+
+struct vsc73xx_counter {
+	u8 counter;
+	const char *name;
+};
+
+/* Counters are named according to the MIB standards where applicable.
+ * Some counters are custom, non-standard. The standard counters are
+ * named in accordance with RFC2819, RFC2021 and IEEE Std 802.3-2002 Annex
+ * 30A Counters.
+ */
+static const struct vsc73xx_counter vsc73xx_rx_counters[] = {
+	{ 0, "RxEtherStatsPkts" },
+	{ 1, "RxBroadcast+MulticastPkts" }, /* non-standard counter */
+	{ 2, "RxTotalErrorPackets" }, /* non-standard counter */
+	{ 3, "RxEtherStatsBroadcastPkts" },
+	{ 4, "RxEtherStatsMulticastPkts" },
+	{ 5, "RxEtherStatsPkts64Octets" },
+	{ 6, "RxEtherStatsPkts65to127Octets" },
+	{ 7, "RxEtherStatsPkts128to255Octets" },
+	{ 8, "RxEtherStatsPkts256to511Octets" },
+	{ 9, "RxEtherStatsPkts512to1023Octets" },
+	{ 10, "RxEtherStatsPkts1024to1518Octets" },
+	{ 11, "RxJumboFrames" }, /* non-standard counter */
+	{ 12, "RxaPauseMACControlFramesTransmitted" },
+	{ 13, "RxFIFODrops" }, /* non-standard counter */
+	{ 14, "RxBackwardDrops" }, /* non-standard counter */
+	{ 15, "RxClassifierDrops" }, /* non-standard counter */
+	{ 16, "RxEtherStatsCRCAlignErrors" },
+	{ 17, "RxEtherStatsUndersizePkts" },
+	{ 18, "RxEtherStatsOversizePkts" },
+	{ 19, "RxEtherStatsFragments" },
+	{ 20, "RxEtherStatsJabbers" },
+	{ 21, "RxaMACControlFramesReceived" },
+	/* 22-24 are undefined */
+	{ 25, "RxaFramesReceivedOK" },
+	{ 26, "RxQoSClass0" }, /* non-standard counter */
+	{ 27, "RxQoSClass1" }, /* non-standard counter */
+	{ 28, "RxQoSClass2" }, /* non-standard counter */
+	{ 29, "RxQoSClass3" }, /* non-standard counter */
+};
+
+static const struct vsc73xx_counter vsc73xx_tx_counters[] = {
+	{ 0, "TxEtherStatsPkts" },
+	{ 1, "TxBroadcast+MulticastPkts" }, /* non-standard counter */
+	{ 2, "TxTotalErrorPackets" }, /* non-standard counter */
+	{ 3, "TxEtherStatsBroadcastPkts" },
+	{ 4, "TxEtherStatsMulticastPkts" },
+	{ 5, "TxEtherStatsPkts64Octets" },
+	{ 6, "TxEtherStatsPkts65to127Octets" },
+	{ 7, "TxEtherStatsPkts128to255Octets" },
+	{ 8, "TxEtherStatsPkts256to511Octets" },
+	{ 9, "TxEtherStatsPkts512to1023Octets" },
+	{ 10, "TxEtherStatsPkts1024to1518Octets" },
+	{ 11, "TxJumboFrames" }, /* non-standard counter */
+	{ 12, "TxaPauseMACControlFramesTransmitted" },
+	{ 13, "TxFIFODrops" }, /* non-standard counter */
+	{ 14, "TxDrops" }, /* non-standard counter */
+	{ 15, "TxEtherStatsCollisions" },
+	{ 16, "TxEtherStatsCRCAlignErrors" },
+	{ 17, "TxEtherStatsUndersizePkts" },
+	{ 18, "TxEtherStatsOversizePkts" },
+	{ 19, "TxEtherStatsFragments" },
+	{ 20, "TxEtherStatsJabbers" },
+	/* 21-24 are undefined */
+	{ 25, "TxaFramesReceivedOK" },
+	{ 26, "TxQoSClass0" }, /* non-standard counter */
+	{ 27, "TxQoSClass1" }, /* non-standard counter */
+	{ 28, "TxQoSClass2" }, /* non-standard counter */
+	{ 29, "TxQoSClass3" }, /* non-standard counter */
+};
+
+static int vsc73xx_is_addr_valid(u8 block, u8 subblock)
+{
+	switch (block) {
+	case VSC73XX_BLOCK_MAC:
+		switch (subblock) {
+		case 0 ... 4:
+		case 6:
+			return 1;
+		}
+		break;
+
+	case VSC73XX_BLOCK_ANALYZER:
+	case VSC73XX_BLOCK_SYSTEM:
+		switch (subblock) {
+		case 0:
+			return 1;
+		}
+		break;
+
+	case VSC73XX_BLOCK_MII:
+	case VSC73XX_BLOCK_CAPTURE:
+	case VSC73XX_BLOCK_ARBITER:
+		switch (subblock) {
+		case 0 ... 1:
+			return 1;
+		}
+		break;
+	}
+
+	return 0;
+}
+
+static u8 vsc73xx_make_addr(u8 mode, u8 block, u8 subblock)
+{
+	u8 ret;
+
+	ret = (block & VSC73XX_CMD_BLOCK_MASK) << VSC73XX_CMD_BLOCK_SHIFT;
+	ret |= (mode & 1) << VSC73XX_CMD_MODE_SHIFT;
+	ret |= subblock & VSC73XX_CMD_SUBBLOCK_MASK;
+
+	return ret;
+}
+
+static int vsc73xx_read(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+			u32 *val)
+{
+	struct spi_transfer t[2];
+	struct spi_message m;
+	u8 cmd[4];
+	u8 buf[4];
+	int ret;
+
+	if (!vsc73xx_is_addr_valid(block, subblock))
+		return -EINVAL;
+
+	spi_message_init(&m);
+
+	memset(&t, 0, sizeof(t));
+
+	t[0].tx_buf = cmd;
+	t[0].len = sizeof(cmd);
+	spi_message_add_tail(&t[0], &m);
+
+	t[1].rx_buf = buf;
+	t[1].len = sizeof(buf);
+	spi_message_add_tail(&t[1], &m);
+
+	cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_READ, block, subblock);
+	cmd[1] = reg;
+	cmd[2] = 0;
+	cmd[3] = 0;
+
+	mutex_lock(&vsc->lock);
+	ret = spi_sync(vsc->spi, &m);
+	mutex_unlock(&vsc->lock);
+
+	if (ret)
+		return ret;
+
+	*val = (buf[0] << 24) | (buf[1] << 16) | (buf[2] << 8) | buf[3];
+
+	return 0;
+}
+
+static int vsc73xx_write(struct vsc73xx *vsc, u8 block, u8 subblock, u8 reg,
+			 u32 val)
+{
+	struct spi_transfer t[2];
+	struct spi_message m;
+	u8 cmd[2];
+	u8 buf[4];
+	int ret;
+
+	if (!vsc73xx_is_addr_valid(block, subblock))
+		return -EINVAL;
+
+	spi_message_init(&m);
+
+	memset(&t, 0, sizeof(t));
+
+	t[0].tx_buf = cmd;
+	t[0].len = sizeof(cmd);
+	spi_message_add_tail(&t[0], &m);
+
+	t[1].tx_buf = buf;
+	t[1].len = sizeof(buf);
+	spi_message_add_tail(&t[1], &m);
+
+	cmd[0] = vsc73xx_make_addr(VSC73XX_CMD_MODE_WRITE, block, subblock);
+	cmd[1] = reg;
+
+	buf[0] = (val >> 24) & 0xff;
+	buf[1] = (val >> 16) & 0xff;
+	buf[2] = (val >> 8) & 0xff;
+	buf[3] = val & 0xff;
+
+	mutex_lock(&vsc->lock);
+	ret = spi_sync(vsc->spi, &m);
+	mutex_unlock(&vsc->lock);
+
+	return ret;
+}
+
+static int vsc73xx_update_bits(struct vsc73xx *vsc, u8 block, u8 subblock,
+			       u8 reg, u32 mask, u32 val)
+{
+	u32 tmp, orig;
+	int ret;
+
+	/* Same read-modify-write algorithm as e.g. regmap */
+	ret = vsc73xx_read(vsc, block, subblock, reg, &orig);
+	if (ret)
+		return ret;
+	tmp = orig & ~mask;
+	tmp |= val & mask;
+	return vsc73xx_write(vsc, block, subblock, reg, tmp);
+}
+
+static int vsc73xx_detect(struct vsc73xx *vsc)
+{
+	bool icpu_si_boot_en;
+	bool icpu_pi_en;
+	u32 val;
+	u32 rev;
+	int ret;
+	u32 id;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_ICPU_MBOX_VAL, &val);
+	if (ret) {
+		dev_err(vsc->dev, "unable to read mailbox (%d)\n", ret);
+		return ret;
+	}
+
+	if (val == 0xffffffff) {
+		dev_info(vsc->dev, "chip seems dead, assert reset\n");
+		gpiod_set_value_cansleep(vsc->reset, 1);
+		/* Reset pulse should be 20ns minimum, according to datasheet
+		 * table 245, so 10us should be fine
+		 */
+		usleep_range(10, 100);
+		gpiod_set_value_cansleep(vsc->reset, 0);
+		/* Wait 20ms according to datasheet table 245 */
+		msleep(20);
+
+		ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+				   VSC73XX_ICPU_MBOX_VAL, &val);
+		if (val == 0xffffffff) {
+			dev_err(vsc->dev, "seems not to help, giving up\n");
+			return -ENODEV;
+		}
+	}
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_CHIPID, &val);
+	if (ret) {
+		dev_err(vsc->dev, "unable to read chip id (%d)\n", ret);
+		return ret;
+	}
+
+	id = (val >> VSC73XX_CHIPID_ID_SHIFT) &
+		VSC73XX_CHIPID_ID_MASK;
+	switch (id) {
+	case VSC73XX_CHIPID_ID_7385:
+	case VSC73XX_CHIPID_ID_7388:
+	case VSC73XX_CHIPID_ID_7395:
+	case VSC73XX_CHIPID_ID_7398:
+		break;
+	default:
+		dev_err(vsc->dev, "unsupported chip, id=%04x\n", id);
+		return -ENODEV;
+	}
+
+	vsc->chipid = id;
+	rev = (val >> VSC73XX_CHIPID_REV_SHIFT) &
+		VSC73XX_CHIPID_REV_MASK;
+	dev_info(vsc->dev, "VSC%04X (rev: %d) switch found\n", id, rev);
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_ICPU_CTRL, &val);
+	if (ret) {
+		dev_err(vsc->dev, "unable to read iCPU control\n");
+		return ret;
+	}
+
+	/* The iCPU can always be used but can boot in different ways.
+	 * If it is initially disabled and has no external memory,
+	 * we are in control and can do whatever we like, else we
+	 * are probably in trouble (we need some way to communicate
+	 * with the running firmware) so we bail out for now.
+	 */
+	icpu_pi_en = !!(val & VSC73XX_ICPU_CTRL_ICPU_PI_EN);
+	icpu_si_boot_en = !!(val & VSC73XX_ICPU_CTRL_BOOT_EN);
+	if (icpu_si_boot_en && icpu_pi_en) {
+		dev_err(vsc->dev,
+			"iCPU enabled boots from SI, has external memory\n");
+		dev_err(vsc->dev, "no idea how to deal with this\n");
+		return -ENODEV;
+	}
+	if (icpu_si_boot_en && !icpu_pi_en) {
+		dev_err(vsc->dev,
+			"iCPU enabled boots from SI, no external memory\n");
+		dev_err(vsc->dev, "no idea how to deal with this\n");
+		return -ENODEV;
+	}
+	if (!icpu_si_boot_en && icpu_pi_en) {
+		dev_err(vsc->dev,
+			"iCPU enabled, boots from PI external memory\n");
+		dev_err(vsc->dev, "no idea how to deal with this\n");
+		return -ENODEV;
+	}
+	/* !icpu_si_boot_en && !cpu_pi_en */
+	dev_info(vsc->dev, "iCPU disabled, no external memory\n");
+
+	return 0;
+}
+
+static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u32 cmd;
+	u32 val;
+	int ret;
+
+	/* Setting bit 26 means "read" */
+	cmd = BIT(26) | (phy << 21) | (regnum << 16);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+	if (ret)
+		return ret;
+	msleep(2);
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val);
+	if (ret)
+		return ret;
+	if (val & BIT(16)) {
+		dev_err(vsc->dev, "reading reg %02x from phy%d failed\n",
+			regnum, phy);
+		return -EIO;
+	}
+	val &= 0xFFFFU;
+
+	dev_dbg(vsc->dev, "read reg %02x from phy%d = %04x\n",
+		regnum, phy, val);
+
+	return val;
+}
+
+static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
+			     u16 val)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u32 cmd;
+	int ret;
+
+	/* It was found through tedious experiments that this router
+	 * chip really hates to have it's PHYs reset. They
+	 * never recover if that happens: autonegotiation stops
+	 * working after a reset. Just filter out this command.
+	 * (Resetting the whole chip is OK.)
+	 */
+	if (regnum == 0 && (val & BIT(15))) {
+		dev_info(vsc->dev, "reset PHY - disallowed\n");
+		return 0;
+	}
+
+	cmd = (phy << 21) | (regnum << 16);
+	ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+	if (ret)
+		return ret;
+
+	dev_dbg(vsc->dev, "write %04x to reg %02x in phy%d\n",
+		val, regnum, phy);
+	return 0;
+}
+
+static enum dsa_tag_protocol vsc73xx_get_tag_protocol(struct dsa_switch *ds,
+						      int port)
+{
+	/* The switch internally uses a 8 byte header with length,
+	 * source port, tag, LPA and priority. This is supposedly
+	 * only accessible when operating the switch using the internal
+	 * CPU or with an external CPU mapping the device in, but not
+	 * when operating the switch over SPI and putting frames in/out
+	 * on port 6 (the CPU port). So far we must assume that we
+	 * cannot access the tag. (See "Internal frame header" section
+	 * 3.9.1 in the manual.)
+	 */
+	return DSA_TAG_PROTO_NONE;
+}
+
+static int vsc73xx_setup(struct dsa_switch *ds)
+{
+	struct vsc73xx *vsc = ds->priv;
+	int i;
+
+	dev_info(vsc->dev, "set up the switch\n");
+
+	/* Issue RESET */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
+		      VSC73XX_GLORESET_MASTER_RESET);
+	usleep_range(125, 200);
+
+	/* Initialize memory, initialize RAM bank 0..15 except 6 and 7
+	 * This sequence appears in the
+	 * VSC7385 SparX-G5 datasheet section 6.6.1
+	 * VSC7395 SparX-G5e datasheet section 6.6.1
+	 * "initialization sequence".
+	 * No explanation is given to the 0x1010400 magic number.
+	 */
+	for (i = 0; i <= 15; i++) {
+		if (i != 6 && i != 7) {
+			vsc73xx_write(vsc, VSC73XX_BLOCK_MEMINIT,
+				      2,
+				      0, 0x1010400 + i);
+			mdelay(1);
+		}
+	}
+	mdelay(30);
+
+	/* Clear MAC table */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+		      VSC73XX_MACACCESS,
+		      VSC73XX_MACACCESS_CMD_CLEAR_TABLE);
+
+	/* Clear VLAN table */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+		      VSC73XX_VLANACCESS,
+		      VSC73XX_VLANACCESS_VLAN_TBL_CMD_CLEAR_TABLE);
+
+	msleep(40);
+
+	/* Use 20KiB buffers on all ports on VSC7395
+	 * The VSC7385 has 16KiB buffers and that is the
+	 * default if we don't set this up explicitly.
+	 * Port "31" is "all ports".
+	 */
+	if (IS_739X(vsc))
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, 0x1f,
+			      VSC73XX_Q_MISC_CONF,
+			      VSC73XX_Q_MISC_CONF_EXTENT_MEM);
+
+	/* Put all ports into reset until enabled */
+	for (i = 0; i < 7; i++) {
+		if (i == 5)
+			continue;
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, 4,
+			      VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET);
+	}
+
+	/* MII delay, set both GTX and RX delay to 2 ns */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GMIIDELAY,
+		      VSC73XX_GMIIDELAY_GMII0_GTXDELAY_2_0_NS |
+		      VSC73XX_GMIIDELAY_GMII0_RXDELAY_2_0_NS);
+	/* Enable reception of frames on all ports */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_RECVMASK,
+		      0x5f);
+	/* IP multicast flood mask (table 144) */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_ANALYZER, 0, VSC73XX_IFLODMSK,
+		      0xff);
+
+	mdelay(50);
+
+	/* Release reset from the internal PHYs */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_SYSTEM, 0, VSC73XX_GLORESET,
+		      VSC73XX_GLORESET_PHY_RESET);
+
+	udelay(4);
+
+	return 0;
+}
+
+static void vsc73xx_init_port(struct vsc73xx *vsc, int port)
+{
+	u32 val;
+
+	/* MAC configure, first reset the port and then write defaults */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_MAC_CFG,
+		      VSC73XX_MAC_CFG_RESET);
+
+	/* Take up the port in 1Gbit mode by default, this will be
+	 * augmented after auto-negotiation on the PHY-facing
+	 * ports.
+	 */
+	if (port == CPU_PORT)
+		val = VSC73XX_MAC_CFG_1000M_F_RGMII;
+	else
+		val = VSC73XX_MAC_CFG_1000M_F_PHY;
+
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_MAC_CFG,
+		      val |
+		      VSC73XX_MAC_CFG_TX_EN |
+		      VSC73XX_MAC_CFG_RX_EN);
+
+	/* Max length, we can do up to 9.6 KiB, so allow that.
+	 * According to application not "VSC7398 Jumbo Frames" setting
+	 * up the MTU to 9.6 KB does not affect the performance on standard
+	 * frames, so just enable it. It is clear from the application note
+	 * that "9.6 kilobytes" == 9600 bytes.
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_MAXLEN, 9600);
+
+	/* Flow control for the CPU port:
+	 * Use a zero delay pause frame when pause condition is left
+	 * Obey pause control frames
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_FCCONF,
+		      VSC73XX_FCCONF_ZERO_PAUSE_EN |
+		      VSC73XX_FCCONF_FLOW_CTRL_OBEY);
+
+	/* Issue pause control frames on PHY facing ports.
+	 * Allow early initiation of MAC transmission if the amount
+	 * of egress data is below 512 bytes on CPU port.
+	 * FIXME: enable 20KiB buffers?
+	 */
+	if (port == CPU_PORT)
+		val = VSC73XX_Q_MISC_CONF_EARLY_TX_512;
+	else
+		val = VSC73XX_Q_MISC_CONF_MAC_PAUSE_MODE;
+	val |= VSC73XX_Q_MISC_CONF_EXTENT_MEM;
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_Q_MISC_CONF,
+		      val);
+
+	/* Flow control MAC: a MAC address used in flow control frames */
+	val = (vsc->addr[5] << 16) | (vsc->addr[4] << 8) | (vsc->addr[3]);
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_FCMACHI,
+		      val);
+	val = (vsc->addr[2] << 16) | (vsc->addr[1] << 8) | (vsc->addr[0]);
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_FCMACLO,
+		      val);
+
+	/* Tell the categorizer to forward pause frames, not control
+	 * frame. Do not drop anything.
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port,
+		      VSC73XX_CAT_DROP,
+		      VSC73XX_CAT_DROP_FWD_PAUSE_ENA);
+
+	/* Clear all counters */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+		      port, VSC73XX_C_RX0, 0);
+}
+
+static void vsc73xx_adjust_enable_port(struct vsc73xx *vsc,
+				       int port, struct phy_device *phydev,
+				       u32 initval)
+{
+	u32 val = initval;
+	u8 seed;
+
+	/* Reset this port FIXME: break out subroutine */
+	val |= VSC73XX_MAC_CFG_RESET;
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);
+
+	/* Seed the port randomness with randomness */
+	get_random_bytes(&seed, 1);
+	val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET;
+	val |= VSC73XX_MAC_CFG_SEED_LOAD;
+	val |= VSC73XX_MAC_CFG_WEXC_DIS;
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);
+
+	/* Flow control for the PHY facing ports:
+	 * Use a zero delay pause frame when pause condition is left
+	 * Obey pause control frames
+	 * When generating pause frames, use 0xff as pause value
+	 */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_FCCONF,
+		      VSC73XX_FCCONF_ZERO_PAUSE_EN |
+		      VSC73XX_FCCONF_FLOW_CTRL_OBEY |
+		      0xff);
+
+	/* Disallow backward dropping of frames from this port */
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+			    VSC73XX_SBACKWDROP, BIT(port), 0);
+
+	/* Enable TX, RX, deassert reset, stop loading seed */
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_MAC, port,
+			    VSC73XX_MAC_CFG,
+			    VSC73XX_MAC_CFG_RESET | VSC73XX_MAC_CFG_SEED_LOAD |
+			    VSC73XX_MAC_CFG_TX_EN | VSC73XX_MAC_CFG_RX_EN,
+			    VSC73XX_MAC_CFG_TX_EN | VSC73XX_MAC_CFG_RX_EN);
+}
+
+static void vsc73xx_adjust_link(struct dsa_switch *ds, int port,
+				struct phy_device *phydev)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u32 val;
+
+	/* Special handling of the CPU-facing port */
+	if (port == CPU_PORT) {
+		/* Other ports are already initialized but not this one */
+		vsc73xx_init_port(vsc, CPU_PORT);
+		/* Select the external port for this interface (EXT_PORT)
+		 * Enable the GMII GTX external clock
+		 * Use double data rate (DDR mode)
+		 */
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC,
+			      CPU_PORT,
+			      VSC73XX_ADVPORTM,
+			      VSC73XX_ADVPORTM_EXT_PORT |
+			      VSC73XX_ADVPORTM_ENA_GTX |
+			      VSC73XX_ADVPORTM_DDR_MODE);
+	}
+
+	/* This is the MAC confiuration that always need to happen
+	 * after a PHY or the CPU port comes up or down.
+	 */
+	if (!phydev->link) {
+		int maxloop = 10;
+
+		dev_dbg(vsc->dev, "port %d: went down\n",
+			port);
+
+		/* Disable RX on this port */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_MAC, port,
+				    VSC73XX_MAC_CFG,
+				    VSC73XX_MAC_CFG_RX_EN, 0);
+
+		/* Discard packets */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				    VSC73XX_ARBDISC, BIT(port), BIT(port));
+
+		/* Wait until queue is empty */
+		vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0,
+			     VSC73XX_ARBEMPTY, &val);
+		while (!(val & BIT(port))) {
+			msleep(1);
+			vsc73xx_read(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				     VSC73XX_ARBEMPTY, &val);
+			if (--maxloop == 0) {
+				dev_err(vsc->dev,
+					"timeout waitting for block arbiter\n");
+				/* Continue anyway */
+				break;
+			}
+		}
+
+		/* Put this port into reset */
+		vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG,
+			      VSC73XX_MAC_CFG_RESET);
+
+		/* Accept packets again */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				    VSC73XX_ARBDISC, BIT(port), 0);
+
+		/* Allow backward dropping of frames from this port */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ARBITER, 0,
+				    VSC73XX_SBACKWDROP, BIT(port), BIT(port));
+
+		/* Receive mask (disable forwarding) */
+		vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+				    VSC73XX_RECVMASK, BIT(port), 0);
+
+		return;
+	}
+
+	/* Figure out what speed was negotiated */
+	if (phydev->speed == SPEED_1000) {
+		dev_dbg(vsc->dev, "port %d: 1000 Mbit mode full duplex\n",
+			port);
+
+		/* Set up default for internal port or external RGMII */
+		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
+			val = VSC73XX_MAC_CFG_1000M_F_RGMII;
+		else
+			val = VSC73XX_MAC_CFG_1000M_F_PHY;
+		vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+	} else if (phydev->speed == SPEED_100) {
+		if (phydev->duplex == DUPLEX_FULL) {
+			val = VSC73XX_MAC_CFG_100_10M_F_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 100 Mbit full duplex mode\n",
+				port);
+		} else {
+			val = VSC73XX_MAC_CFG_100_10M_H_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 100 Mbit half duplex mode\n",
+				port);
+		}
+		vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+	} else if (phydev->speed == SPEED_10) {
+		if (phydev->duplex == DUPLEX_FULL) {
+			val = VSC73XX_MAC_CFG_100_10M_F_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 10 Mbit full duplex mode\n",
+				port);
+		} else {
+			val = VSC73XX_MAC_CFG_100_10M_H_PHY;
+			dev_dbg(vsc->dev,
+				"port %d: 10 Mbit half duplex mode\n",
+				port);
+		}
+		vsc73xx_adjust_enable_port(vsc, port, phydev, val);
+	} else {
+		dev_err(vsc->dev,
+			"could not adjust link: unknown speed\n");
+	}
+
+	/* Enable port (forwarding) in the receieve mask */
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_ANALYZER, 0,
+			    VSC73XX_RECVMASK, BIT(port), BIT(port));
+}
+
+static int vsc73xx_port_enable(struct dsa_switch *ds, int port,
+			       struct phy_device *phy)
+{
+	struct vsc73xx *vsc = ds->priv;
+
+	dev_info(vsc->dev, "enable port %d\n", port);
+	vsc73xx_init_port(vsc, port);
+
+	return 0;
+}
+
+static void vsc73xx_port_disable(struct dsa_switch *ds, int port,
+				 struct phy_device *phy)
+{
+	struct vsc73xx *vsc = ds->priv;
+
+	/* Just put the port into reset */
+	vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port,
+		      VSC73XX_MAC_CFG, VSC73XX_MAC_CFG_RESET);
+}
+
+static const struct vsc73xx_counter *
+vsc73xx_find_counter(struct vsc73xx *vsc,
+		     u8 counter,
+		     bool tx)
+{
+	const struct vsc73xx_counter *cnts;
+	int num_cnts;
+	int i;
+
+	if (tx) {
+		cnts = vsc73xx_tx_counters;
+		num_cnts = ARRAY_SIZE(vsc73xx_tx_counters);
+	} else {
+		cnts = vsc73xx_rx_counters;
+		num_cnts = ARRAY_SIZE(vsc73xx_rx_counters);
+	}
+
+	for (i = 0; i < num_cnts; i++) {
+		const struct vsc73xx_counter *cnt;
+
+		cnt = &cnts[i];
+		if (cnt->counter == counter)
+			return cnt;
+	}
+
+	return NULL;
+}
+
+void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+			 uint8_t *data)
+{
+	const struct vsc73xx_counter *cnt;
+	struct vsc73xx *vsc = ds->priv;
+	u8 indices[6];
+	int i, j;
+	u32 val;
+	int ret;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MAC, port,
+			   VSC73XX_C_CFG, &val);
+	if (ret)
+		return;
+
+	indices[0] = (val & 0x1f); /* RX counter 0 */
+	indices[1] = ((val >> 5) & 0x1f); /* RX counter 1 */
+	indices[2] = ((val >> 10) & 0x1f); /* RX counter 2 */
+	indices[3] = ((val >> 16) & 0x1f); /* TX counter 0 */
+	indices[4] = ((val >> 21) & 0x1f); /* TX counter 1 */
+	indices[5] = ((val >> 26) & 0x1f); /* TX counter 2 */
+
+	/* The first counters is the RX octets */
+	j = 0;
+	strncpy(data + j * ETH_GSTRING_LEN,
+		"RxEtherStatsOctets", ETH_GSTRING_LEN);
+	j++;
+
+	/* Each port supports recording 3 RX counters and 3 TX counters,
+	 * figure out what counters we use in this set-up and return the
+	 * names of them. The hardware default counters will be number of
+	 * packets on RX/TX, combined broadcast+multicast packets RX/TX and
+	 * total error packets RX/TX.
+	 */
+	for (i = 0; i < 3; i++) {
+		cnt = vsc73xx_find_counter(vsc, indices[i], false);
+		if (cnt)
+			strncpy(data + j * ETH_GSTRING_LEN,
+				cnt->name, ETH_GSTRING_LEN);
+		j++;
+	}
+
+	/* TX stats begins with the number of TX octets */
+	strncpy(data + j * ETH_GSTRING_LEN,
+		"TxEtherStatsOctets", ETH_GSTRING_LEN);
+	j++;
+
+	for (i = 3; i < 6; i++) {
+		cnt = vsc73xx_find_counter(vsc, indices[i], true);
+		if (cnt)
+			strncpy(data + j * ETH_GSTRING_LEN,
+				cnt->name, ETH_GSTRING_LEN);
+		j++;
+	}
+}
+
+int vsc73xx_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+	/* We only support SS_STATS */
+	if (sset != ETH_SS_STATS)
+		return 0;
+	/* RX and TX packets, then 3 RX counters, 3 TX counters */
+	return 8;
+}
+
+void vsc73xx_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
+{
+	struct vsc73xx *vsc = ds->priv;
+	u8 regs[] = {
+		VSC73XX_RXOCT,
+		VSC73XX_C_RX0,
+		VSC73XX_C_RX1,
+		VSC73XX_C_RX2,
+		VSC73XX_TXOCT,
+		VSC73XX_C_TX0,
+		VSC73XX_C_TX1,
+		VSC73XX_C_TX2,
+	};
+	u32 val;
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(regs); i++) {
+		ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MAC, port,
+				   regs[i], &val);
+		if (ret) {
+			dev_err(vsc->dev, "error reading counter %d\n", i);
+			return;
+		}
+		data[i] = val;
+	}
+}
+
+static const struct dsa_switch_ops vsc73xx_ds_ops = {
+	.get_tag_protocol = vsc73xx_get_tag_protocol,
+	.setup = vsc73xx_setup,
+	.phy_read = vsc73xx_phy_read,
+	.phy_write = vsc73xx_phy_write,
+	.adjust_link = vsc73xx_adjust_link,
+	.get_strings = vsc73xx_get_strings,
+	.get_ethtool_stats = vsc73xx_get_ethtool_stats,
+	.get_sset_count = vsc73xx_get_sset_count,
+	.port_enable = vsc73xx_port_enable,
+	.port_disable = vsc73xx_port_disable,
+};
+
+static int vsc73xx_gpio_get(struct gpio_chip *chip, unsigned int offset)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 val;
+	int ret;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_GPIO, &val);
+	if (ret)
+		return ret;
+
+	return !!(val & BIT(offset));
+}
+
+static void vsc73xx_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			     int val)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 tmp = val ? BIT(offset) : 0;
+
+	vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			    VSC73XX_GPIO, BIT(offset), tmp);
+}
+
+static int vsc73xx_gpio_direction_output(struct gpio_chip *chip,
+					 unsigned int offset, int val)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 tmp = val ? BIT(offset) : 0;
+
+	return vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+				   VSC73XX_GPIO, BIT(offset + 4) | BIT(offset),
+				   BIT(offset + 4) | tmp);
+}
+
+static int vsc73xx_gpio_direction_input(struct gpio_chip *chip,
+					unsigned int offset)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+
+	return  vsc73xx_update_bits(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+				    VSC73XX_GPIO, BIT(offset + 4),
+				    0);
+}
+
+static int vsc73xx_gpio_get_direction(struct gpio_chip *chip,
+				      unsigned int offset)
+{
+	struct vsc73xx *vsc = gpiochip_get_data(chip);
+	u32 val;
+	int ret;
+
+	ret = vsc73xx_read(vsc, VSC73XX_BLOCK_SYSTEM, 0,
+			   VSC73XX_GPIO, &val);
+	if (ret)
+		return ret;
+
+	return !(val & BIT(offset + 4));
+}
+
+static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
+{
+	int ret;
+
+	vsc->gc.label = devm_kasprintf(vsc->dev, GFP_KERNEL, "VSC%04x",
+				       vsc->chipid);
+	vsc->gc.ngpio = 4;
+	vsc->gc.owner = THIS_MODULE;
+	vsc->gc.parent = vsc->dev;
+	vsc->gc.of_node = vsc->dev->of_node;
+	vsc->gc.base = -1;
+	vsc->gc.get = vsc73xx_gpio_get;
+	vsc->gc.set = vsc73xx_gpio_set;
+	vsc->gc.direction_input = vsc73xx_gpio_direction_input;
+	vsc->gc.direction_output = vsc73xx_gpio_direction_output;
+	vsc->gc.get_direction = vsc73xx_gpio_get_direction;
+	vsc->gc.can_sleep = true;
+	ret = devm_gpiochip_add_data(vsc->dev, &vsc->gc, vsc);
+	if (ret) {
+		dev_err(vsc->dev, "unable to register GPIO chip\n");
+		return ret;
+	}
+	return 0;
+}
+
+static int vsc73xx_probe(struct spi_device *spi)
+{
+	struct device *dev = &spi->dev;
+	struct vsc73xx *vsc;
+	int ret;
+
+	vsc = devm_kzalloc(dev, sizeof(*vsc), GFP_KERNEL);
+	if (!vsc)
+		return -ENOMEM;
+
+	spi_set_drvdata(spi, vsc);
+	vsc->spi = spi_dev_get(spi);
+	vsc->dev = dev;
+	mutex_init(&vsc->lock);
+
+	/* Release reset, if any */
+	vsc->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(vsc->reset)) {
+		dev_err(dev, "failed to get RESET GPIO\n");
+		return PTR_ERR(vsc->reset);
+	}
+	if (vsc->reset)
+		/* Wait 20ms according to datasheet table 245 */
+		msleep(20);
+
+	spi->mode = SPI_MODE_0;
+	spi->bits_per_word = 8;
+	ret = spi_setup(spi);
+	if (ret < 0) {
+		dev_err(dev, "spi setup failed.\n");
+		return ret;
+	}
+
+	ret = vsc73xx_detect(vsc);
+	if (ret) {
+		dev_err(dev, "no chip found (%d)\n", ret);
+		return -ENODEV;
+	}
+
+	eth_random_addr(vsc->addr);
+	dev_info(vsc->dev,
+		 "MAC for control frames: %02X:%02X:%02X:%02X:%02X:%02X\n",
+		 vsc->addr[0], vsc->addr[1], vsc->addr[2],
+		 vsc->addr[3], vsc->addr[4], vsc->addr[5]);
+
+	/* The VSC7395 switch chips have 5+1 ports which means 5
+	 * ordinary ports and a sixth CPU port facing the processor
+	 * with an RGMII interface. These ports are numbered 0..4
+	 * and 6, so they leave a "hole" in the port map for port 5,
+	 * which is invalid.
+	 *
+	 * The VSC7398 has 8 ports, port 7 is again the CPU port.
+	 *
+	 * We allocate 8 ports and avoid access to the nonexistant
+	 * ports.
+	 */
+	vsc->ds = dsa_switch_alloc(dev, 8);
+	if (!vsc->ds)
+		return -ENOMEM;
+	vsc->ds->priv = vsc;
+
+	vsc->ds->ops = &vsc73xx_ds_ops;
+	ret = dsa_register_switch(vsc->ds);
+	if (ret) {
+		dev_err(dev, "unable to register switch (%d)\n", ret);
+		return ret;
+	}
+
+	ret = vsc73xx_gpio_probe(vsc);
+	if (ret) {
+		dsa_unregister_switch(vsc->ds);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int vsc73xx_remove(struct spi_device *spi)
+{
+	struct vsc73xx *vsc = spi_get_drvdata(spi);
+
+	dsa_unregister_switch(vsc->ds);
+	gpiod_set_value(vsc->reset, 1);
+
+	return 0;
+}
+
+static const struct of_device_id vsc73xx_of_match[] = {
+	{
+		.compatible = "vitesse,vsc7385",
+	},
+	{
+		.compatible = "vitesse,vsc7388",
+	},
+	{
+		.compatible = "vitesse,vsc7395",
+	},
+	{
+		.compatible = "vitesse,vsc7398",
+	},
+	{ },
+};
+MODULE_DEVICE_TABLE(of, vsc73xx_of_match);
+
+static struct spi_driver vsc73xx_driver = {
+	.probe = vsc73xx_probe,
+	.remove = vsc73xx_remove,
+	.driver = {
+		.name = "vsc73xx",
+		.of_match_table = vsc73xx_of_match,
+	},
+};
+module_spi_driver(vsc73xx_driver);
+
+MODULE_AUTHOR("Linus Walleij <linus.walleij@linaro.org>");
+MODULE_DESCRIPTION("Vitesse VSC7385/7388/7395/7398 driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 69b9e1e07d98b57b972df3c44647ca8795284d39 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 2 Jul 2018 18:21:11 +0800
Subject: ipv4: add __ip_queue_xmit() that supports tos param

This patch introduces __ip_queue_xmit(), through which the callers
can pass tos param into it without having to set inet->tos. For
ipv6, ip6_xmit() already allows passing tclass parameter.

It's needed when some transport protocol doesn't use inet->tos,
like sctp's per transport dscp, which will be added in next patch.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h     | 9 ++++++++-
 net/ipv4/ip_output.c | 9 +++++----
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 0d2281b4b27a..09da79d8ceea 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -148,7 +148,8 @@ void ip_send_check(struct iphdr *ip);
 int __ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 int ip_local_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 
-int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
+int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+		    __u8 tos);
 void ip_init(void);
 int ip_append_data(struct sock *sk, struct flowi4 *fl4,
 		   int getfrag(void *from, char *to, int offset, int len,
@@ -174,6 +175,12 @@ struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4,
 			    struct ipcm_cookie *ipc, struct rtable **rtp,
 			    struct inet_cork *cork, unsigned int flags);
 
+static inline int ip_queue_xmit(struct sock *sk, struct sk_buff *skb,
+				struct flowi *fl)
+{
+	return __ip_queue_xmit(sk, skb, fl, inet_sk(sk)->tos);
+}
+
 static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4)
 {
 	return __ip_make_skb(sk, fl4, &sk->sk_write_queue, &inet_sk(sk)->cork.base);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b3308e9d9762..188cc586e7ff 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -423,7 +423,8 @@ static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4)
 }
 
 /* Note: skb->sk can be different from sk, in case of tunnels */
-int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
+int __ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
+		    __u8 tos)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct net *net = sock_net(sk);
@@ -462,7 +463,7 @@ int ip_queue_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl)
 					   inet->inet_dport,
 					   inet->inet_sport,
 					   sk->sk_protocol,
-					   RT_CONN_FLAGS(sk),
+					   RT_CONN_FLAGS_TOS(sk, tos),
 					   sk->sk_bound_dev_if);
 		if (IS_ERR(rt))
 			goto no_route;
@@ -478,7 +479,7 @@ packet_routed:
 	skb_push(skb, sizeof(struct iphdr) + (inet_opt ? inet_opt->opt.optlen : 0));
 	skb_reset_network_header(skb);
 	iph = ip_hdr(skb);
-	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
+	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (tos & 0xff));
 	if (ip_dont_fragment(sk, &rt->dst) && !skb->ignore_df)
 		iph->frag_off = htons(IP_DF);
 	else
@@ -511,7 +512,7 @@ no_route:
 	kfree_skb(skb);
 	return -EHOSTUNREACH;
 }
-EXPORT_SYMBOL(ip_queue_xmit);
+EXPORT_SYMBOL(__ip_queue_xmit);
 
 static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 {
-- 
cgit v1.2.3


From 8a9c58d28d0f66569737a3295116710ed24573cd Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 2 Jul 2018 18:21:12 +0800
Subject: sctp: add support for dscp and flowlabel per transport

Like some other per transport params, flowlabel and dscp are added
in transport, asoc and sctp_sock. By default, transport sets its
value from asoc's, and asoc does it from sctp_sock. flowlabel
only works for ipv6 transport.

Other than that they need to be passed down in sctp_xmit, flow4/6
also needs to set them before looking up route in get_dst.

Note that it uses '& 0x100000' to check if flowlabel is set and
'& 0x1' (tos 1st bit is unused) to check if dscp is set by users,
so that they could be set to 0 by sockopt in next patch.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/sctp.h       |  7 +++++++
 include/net/sctp/structs.h |  9 +++++++++
 net/sctp/associola.c       |  7 +++++++
 net/sctp/ipv6.c            | 11 +++++++++--
 net/sctp/protocol.c        | 16 ++++++++++++----
 5 files changed, 44 insertions(+), 6 deletions(-)

diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index b36c76635f18..83d94341e003 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -801,4 +801,11 @@ struct sctp_strreset_resptsn {
 	__be32 receivers_next_tsn;
 };
 
+enum {
+	SCTP_DSCP_SET_MASK = 0x1,
+	SCTP_DSCP_VAL_MASK = 0xfc,
+	SCTP_FLOWLABEL_SET_MASK = 0x100000,
+	SCTP_FLOWLABEL_VAL_MASK = 0xfffff
+};
+
 #endif /* __LINUX_SCTP_H__ */
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 701a51736fa5..ab869e0d8326 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -193,6 +193,9 @@ struct sctp_sock {
 	/* This is the max_retrans value for new associations. */
 	__u16 pathmaxrxt;
 
+	__u32 flowlabel;
+	__u8  dscp;
+
 	/* The initial Path MTU to use for new associations. */
 	__u32 pathmtu;
 
@@ -895,6 +898,9 @@ struct sctp_transport {
 	 */
 	__u16 pathmaxrxt;
 
+	__u32 flowlabel;
+	__u8  dscp;
+
 	/* This is the partially failed retrans value for the transport
 	 * and will be initialized from the assocs value.  This can be changed
 	 * using the SCTP_PEER_ADDR_THLDS socket option
@@ -1772,6 +1778,9 @@ struct sctp_association {
 	 */
 	__u16 pathmaxrxt;
 
+	__u32 flowlabel;
+	__u8  dscp;
+
 	/* Flag that path mtu update is pending */
 	__u8   pmtu_pending;
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 5d5a16204d50..16ecfbc95614 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -115,6 +115,9 @@ static struct sctp_association *sctp_association_init(
 	/* Initialize path max retrans value. */
 	asoc->pathmaxrxt = sp->pathmaxrxt;
 
+	asoc->flowlabel = sp->flowlabel;
+	asoc->dscp = sp->dscp;
+
 	/* Initialize default path MTU. */
 	asoc->pathmtu = sp->pathmtu;
 
@@ -647,6 +650,10 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	peer->sackdelay = asoc->sackdelay;
 	peer->sackfreq = asoc->sackfreq;
 
+	if (addr->sa.sa_family == AF_INET6)
+		peer->flowlabel = asoc->flowlabel;
+	peer->dscp = asoc->dscp;
+
 	/* Enable/disable heartbeat, SACK delay, and path MTU discovery
 	 * based on association setting.
 	 */
diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 0cd2e764f47f..38102bf7f13e 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -209,12 +209,17 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 	struct sock *sk = skb->sk;
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct flowi6 *fl6 = &transport->fl.u.ip6;
+	__u8 tclass = np->tclass;
 	int res;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI6 dst:%pI6\n", __func__, skb,
 		 skb->len, &fl6->saddr, &fl6->daddr);
 
-	IP6_ECN_flow_xmit(sk, fl6->flowlabel);
+	if (transport->dscp & SCTP_DSCP_SET_MASK)
+		tclass = transport->dscp & SCTP_DSCP_VAL_MASK;
+
+	if (INET_ECN_is_capable(tclass))
+		IP6_ECN_flow_xmit(sk, fl6->flowlabel);
 
 	if (!(transport->param_flags & SPP_PMTUD_ENABLE))
 		skb->ignore_df = 1;
@@ -223,7 +228,7 @@ static int sctp_v6_xmit(struct sk_buff *skb, struct sctp_transport *transport)
 
 	rcu_read_lock();
 	res = ip6_xmit(sk, skb, fl6, sk->sk_mark, rcu_dereference(np->opt),
-		       np->tclass);
+		       tclass);
 	rcu_read_unlock();
 	return res;
 }
@@ -254,6 +259,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl6->flowi6_oif = daddr->v6.sin6_scope_id;
 	else if (asoc)
 		fl6->flowi6_oif = asoc->base.sk->sk_bound_dev_if;
+	if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK)
+		fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK);
 
 	pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr);
 
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 67f73d3a1356..e948db29ab53 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -426,13 +426,16 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	struct dst_entry *dst = NULL;
 	union sctp_addr *daddr = &t->ipaddr;
 	union sctp_addr dst_saddr;
+	__u8 tos = inet_sk(sk)->tos;
 
+	if (t->dscp & SCTP_DSCP_SET_MASK)
+		tos = t->dscp & SCTP_DSCP_VAL_MASK;
 	memset(fl4, 0x0, sizeof(struct flowi4));
 	fl4->daddr  = daddr->v4.sin_addr.s_addr;
 	fl4->fl4_dport = daddr->v4.sin_port;
 	fl4->flowi4_proto = IPPROTO_SCTP;
 	if (asoc) {
-		fl4->flowi4_tos = RT_CONN_FLAGS(asoc->base.sk);
+		fl4->flowi4_tos = RT_CONN_FLAGS_TOS(asoc->base.sk, tos);
 		fl4->flowi4_oif = asoc->base.sk->sk_bound_dev_if;
 		fl4->fl4_sport = htons(asoc->base.bind_addr.port);
 	}
@@ -495,7 +498,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 		fl4->fl4_sport = laddr->a.v4.sin_port;
 		flowi4_update_output(fl4,
 				     asoc->base.sk->sk_bound_dev_if,
-				     RT_CONN_FLAGS(asoc->base.sk),
+				     RT_CONN_FLAGS_TOS(asoc->base.sk, tos),
 				     daddr->v4.sin_addr.s_addr,
 				     laddr->a.v4.sin_addr.s_addr);
 
@@ -971,16 +974,21 @@ static inline int sctp_v4_xmit(struct sk_buff *skb,
 			       struct sctp_transport *transport)
 {
 	struct inet_sock *inet = inet_sk(skb->sk);
+	__u8 dscp = inet->tos;
 
 	pr_debug("%s: skb:%p, len:%d, src:%pI4, dst:%pI4\n", __func__, skb,
-		 skb->len, &transport->fl.u.ip4.saddr, &transport->fl.u.ip4.daddr);
+		 skb->len, &transport->fl.u.ip4.saddr,
+		 &transport->fl.u.ip4.daddr);
+
+	if (transport->dscp & SCTP_DSCP_SET_MASK)
+		dscp = transport->dscp & SCTP_DSCP_VAL_MASK;
 
 	inet->pmtudisc = transport->param_flags & SPP_PMTUD_ENABLE ?
 			 IP_PMTUDISC_DO : IP_PMTUDISC_DONT;
 
 	SCTP_INC_STATS(sock_net(&inet->sk), SCTP_MIB_OUTSCTPPACKS);
 
-	return ip_queue_xmit(&inet->sk, skb, &transport->fl);
+	return __ip_queue_xmit(&inet->sk, skb, &transport->fl, dscp);
 }
 
 static struct sctp_af sctp_af_inet;
-- 
cgit v1.2.3


From 0b0dce7a36fb9f1a9dd8245ea82d3a268c6943fe Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 2 Jul 2018 18:21:13 +0800
Subject: sctp: add spp_ipv6_flowlabel and spp_dscp for sctp_paddrparams

spp_ipv6_flowlabel and spp_dscp are added in sctp_paddrparams in
this patch so that users could set sctp_sock/asoc/transport dscp
and flowlabel with spp_flags SPP_IPV6_FLOWLABEL or SPP_DSCP by
SCTP_PEER_ADDR_PARAMS , as described section 8.1.12 in RFC6458.

As said in last patch, it uses '| 0x100000' or '|0x1' to mark
flowlabel or dscp is set,  so that their values could be set
to 0.

Note that to guarantee that an old app built with old kernel
headers could work on the newer kernel, the param's check in
sctp_g/setsockopt_peer_addr_params() is also improved, which
follows the way that sctp_g/setsockopt_delayed_ack() or some
other sockopts' process that accept two types of params does.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/sctp.h |   4 ++
 net/sctp/socket.c         | 177 ++++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 175 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/sctp.h b/include/uapi/linux/sctp.h
index c02986a284db..b479db5c71d9 100644
--- a/include/uapi/linux/sctp.h
+++ b/include/uapi/linux/sctp.h
@@ -763,6 +763,8 @@ enum  sctp_spp_flags {
 	SPP_SACKDELAY_DISABLE = 1<<6,	/*Disable SACK*/
 	SPP_SACKDELAY = SPP_SACKDELAY_ENABLE | SPP_SACKDELAY_DISABLE,
 	SPP_HB_TIME_IS_ZERO = 1<<7,	/* Set HB delay to 0 */
+	SPP_IPV6_FLOWLABEL = 1<<8,
+	SPP_DSCP = 1<<9,
 };
 
 struct sctp_paddrparams {
@@ -773,6 +775,8 @@ struct sctp_paddrparams {
 	__u32			spp_pathmtu;
 	__u32			spp_sackdelay;
 	__u32			spp_flags;
+	__u32			spp_ipv6_flowlabel;
+	__u8			spp_dscp;
 } __attribute__((packed, aligned(4)));
 
 /*
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 0e4c8332771a..50b7ef975b42 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2393,6 +2393,8 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
  *     uint32_t                spp_pathmtu;
  *     uint32_t                spp_sackdelay;
  *     uint32_t                spp_flags;
+ *     uint32_t                spp_ipv6_flowlabel;
+ *     uint8_t                 spp_dscp;
  * };
  *
  *   spp_assoc_id    - (one-to-many style socket) This is filled in the
@@ -2472,6 +2474,45 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval,
  *                     also that this field is mutually exclusive to
  *                     SPP_SACKDELAY_ENABLE, setting both will have undefined
  *                     results.
+ *
+ *                     SPP_IPV6_FLOWLABEL:  Setting this flag enables the
+ *                     setting of the IPV6 flow label value.  The value is
+ *                     contained in the spp_ipv6_flowlabel field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_ipv6_flowlabel field has a valid value returned.
+ *                     If a specific destination address is set (in the
+ *                     spp_address field), then the value returned is that of
+ *                     the address.  If just an association is specified (and
+ *                     no address), then the association's default flow label
+ *                     is returned.  If neither an association nor a destination
+ *                     is specified, then the socket's default flow label is
+ *                     returned.  For non-IPv6 sockets, this flag will be left
+ *                     cleared.
+ *
+ *                     SPP_DSCP:  Setting this flag enables the setting of the
+ *                     Differentiated Services Code Point (DSCP) value
+ *                     associated with either the association or a specific
+ *                     address.  The value is obtained in the spp_dscp field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_dscp field has a valid value returned.  If a
+ *                     specific destination address is set when called (in the
+ *                     spp_address field), then that specific destination
+ *                     address's DSCP value is returned.  If just an association
+ *                     is specified, then the association's default DSCP is
+ *                     returned.  If neither an association nor a destination is
+ *                     specified, then the socket's default DSCP is returned.
+ *
+ *   spp_ipv6_flowlabel
+ *                   - This field is used in conjunction with the
+ *                     SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label.
+ *                     The 20 least significant bits are used for the flow
+ *                     label.  This setting has precedence over any IPv6-layer
+ *                     setting.
+ *
+ *   spp_dscp        - This field is used in conjunction with the SPP_DSCP flag
+ *                     and contains the DSCP.  The 6 most significant bits are
+ *                     used for the DSCP.  This setting has precedence over any
+ *                     IPv4- or IPv6- layer setting.
  */
 static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 				       struct sctp_transport   *trans,
@@ -2611,6 +2652,51 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params,
 		}
 	}
 
+	if (params->spp_flags & SPP_IPV6_FLOWLABEL) {
+		if (trans && trans->ipaddr.sa.sa_family == AF_INET6) {
+			trans->flowlabel = params->spp_ipv6_flowlabel &
+					   SCTP_FLOWLABEL_VAL_MASK;
+			trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		} else if (asoc) {
+			list_for_each_entry(trans,
+					    &asoc->peer.transport_addr_list,
+					    transports) {
+				if (trans->ipaddr.sa.sa_family != AF_INET6)
+					continue;
+				trans->flowlabel = params->spp_ipv6_flowlabel &
+						   SCTP_FLOWLABEL_VAL_MASK;
+				trans->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+			}
+			asoc->flowlabel = params->spp_ipv6_flowlabel &
+					  SCTP_FLOWLABEL_VAL_MASK;
+			asoc->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		} else if (sctp_opt2sk(sp)->sk_family == AF_INET6) {
+			sp->flowlabel = params->spp_ipv6_flowlabel &
+					SCTP_FLOWLABEL_VAL_MASK;
+			sp->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		}
+	}
+
+	if (params->spp_flags & SPP_DSCP) {
+		if (trans) {
+			trans->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+			trans->dscp |= SCTP_DSCP_SET_MASK;
+		} else if (asoc) {
+			list_for_each_entry(trans,
+					    &asoc->peer.transport_addr_list,
+					    transports) {
+				trans->dscp = params->spp_dscp &
+					      SCTP_DSCP_VAL_MASK;
+				trans->dscp |= SCTP_DSCP_SET_MASK;
+			}
+			asoc->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+			asoc->dscp |= SCTP_DSCP_SET_MASK;
+		} else {
+			sp->dscp = params->spp_dscp & SCTP_DSCP_VAL_MASK;
+			sp->dscp |= SCTP_DSCP_SET_MASK;
+		}
+	}
+
 	return 0;
 }
 
@@ -2625,11 +2711,18 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk,
 	int error;
 	int hb_change, pmtud_change, sackdelay_change;
 
-	if (optlen != sizeof(struct sctp_paddrparams))
+	if (optlen == sizeof(params)) {
+		if (copy_from_user(&params, optval, optlen))
+			return -EFAULT;
+	} else if (optlen == ALIGN(offsetof(struct sctp_paddrparams,
+					    spp_ipv6_flowlabel), 4)) {
+		if (copy_from_user(&params, optval, optlen))
+			return -EFAULT;
+		if (params.spp_flags & (SPP_DSCP | SPP_IPV6_FLOWLABEL))
+			return -EINVAL;
+	} else {
 		return -EINVAL;
-
-	if (copy_from_user(&params, optval, optlen))
-		return -EFAULT;
+	}
 
 	/* Validate flags and value parameters. */
 	hb_change        = params.spp_flags & SPP_HB;
@@ -5453,6 +5546,45 @@ out:
  *                     also that this field is mutually exclusive to
  *                     SPP_SACKDELAY_ENABLE, setting both will have undefined
  *                     results.
+ *
+ *                     SPP_IPV6_FLOWLABEL:  Setting this flag enables the
+ *                     setting of the IPV6 flow label value.  The value is
+ *                     contained in the spp_ipv6_flowlabel field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_ipv6_flowlabel field has a valid value returned.
+ *                     If a specific destination address is set (in the
+ *                     spp_address field), then the value returned is that of
+ *                     the address.  If just an association is specified (and
+ *                     no address), then the association's default flow label
+ *                     is returned.  If neither an association nor a destination
+ *                     is specified, then the socket's default flow label is
+ *                     returned.  For non-IPv6 sockets, this flag will be left
+ *                     cleared.
+ *
+ *                     SPP_DSCP:  Setting this flag enables the setting of the
+ *                     Differentiated Services Code Point (DSCP) value
+ *                     associated with either the association or a specific
+ *                     address.  The value is obtained in the spp_dscp field.
+ *                     Upon retrieval, this flag will be set to indicate that
+ *                     the spp_dscp field has a valid value returned.  If a
+ *                     specific destination address is set when called (in the
+ *                     spp_address field), then that specific destination
+ *                     address's DSCP value is returned.  If just an association
+ *                     is specified, then the association's default DSCP is
+ *                     returned.  If neither an association nor a destination is
+ *                     specified, then the socket's default DSCP is returned.
+ *
+ *   spp_ipv6_flowlabel
+ *                   - This field is used in conjunction with the
+ *                     SPP_IPV6_FLOWLABEL flag and contains the IPv6 flow label.
+ *                     The 20 least significant bits are used for the flow
+ *                     label.  This setting has precedence over any IPv6-layer
+ *                     setting.
+ *
+ *   spp_dscp        - This field is used in conjunction with the SPP_DSCP flag
+ *                     and contains the DSCP.  The 6 most significant bits are
+ *                     used for the DSCP.  This setting has precedence over any
+ *                     IPv4- or IPv6- layer setting.
  */
 static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 					    char __user *optval, int __user *optlen)
@@ -5462,9 +5594,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 	struct sctp_association *asoc = NULL;
 	struct sctp_sock        *sp = sctp_sk(sk);
 
-	if (len < sizeof(struct sctp_paddrparams))
+	if (len >= sizeof(params))
+		len = sizeof(params);
+	else if (len >= ALIGN(offsetof(struct sctp_paddrparams,
+				       spp_ipv6_flowlabel), 4))
+		len = ALIGN(offsetof(struct sctp_paddrparams,
+				     spp_ipv6_flowlabel), 4);
+	else
 		return -EINVAL;
-	len = sizeof(struct sctp_paddrparams);
+
 	if (copy_from_user(&params, optval, len))
 		return -EFAULT;
 
@@ -5499,6 +5637,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 
 		/*draft-11 doesn't say what to return in spp_flags*/
 		params.spp_flags      = trans->param_flags;
+		if (trans->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+			params.spp_ipv6_flowlabel = trans->flowlabel &
+						    SCTP_FLOWLABEL_VAL_MASK;
+			params.spp_flags |= SPP_IPV6_FLOWLABEL;
+		}
+		if (trans->dscp & SCTP_DSCP_SET_MASK) {
+			params.spp_dscp	= trans->dscp & SCTP_DSCP_VAL_MASK;
+			params.spp_flags |= SPP_DSCP;
+		}
 	} else if (asoc) {
 		/* Fetch association values. */
 		params.spp_hbinterval = jiffies_to_msecs(asoc->hbinterval);
@@ -5508,6 +5655,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 
 		/*draft-11 doesn't say what to return in spp_flags*/
 		params.spp_flags      = asoc->param_flags;
+		if (asoc->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+			params.spp_ipv6_flowlabel = asoc->flowlabel &
+						    SCTP_FLOWLABEL_VAL_MASK;
+			params.spp_flags |= SPP_IPV6_FLOWLABEL;
+		}
+		if (asoc->dscp & SCTP_DSCP_SET_MASK) {
+			params.spp_dscp	= asoc->dscp & SCTP_DSCP_VAL_MASK;
+			params.spp_flags |= SPP_DSCP;
+		}
 	} else {
 		/* Fetch socket values. */
 		params.spp_hbinterval = sp->hbinterval;
@@ -5517,6 +5673,15 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len,
 
 		/*draft-11 doesn't say what to return in spp_flags*/
 		params.spp_flags      = sp->param_flags;
+		if (sp->flowlabel & SCTP_FLOWLABEL_SET_MASK) {
+			params.spp_ipv6_flowlabel = sp->flowlabel &
+						    SCTP_FLOWLABEL_VAL_MASK;
+			params.spp_flags |= SPP_IPV6_FLOWLABEL;
+		}
+		if (sp->dscp & SCTP_DSCP_SET_MASK) {
+			params.spp_dscp	= sp->dscp & SCTP_DSCP_VAL_MASK;
+			params.spp_flags |= SPP_DSCP;
+		}
 	}
 
 	if (copy_to_user(optval, &params, len))
-- 
cgit v1.2.3


From 4be4139f7d0dc74e5a0932c7c7ddf0eb65da9e3a Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 2 Jul 2018 18:21:14 +0800
Subject: sctp: add support for setting flowlabel when adding a transport

Struct sockaddr_in6 has the member sin6_flowinfo that includes the
ipv6 flowlabel, it should also support for setting flowlabel when
adding a transport whose ipaddr is from userspace.

Note that addrinfo in sctp_sendmsg is using struct in6_addr for
the secondary addrs, which doesn't contain sin6_flowinfo, and
it needs to copy sin6_flowinfo from the primary addr.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/associola.c | 12 ++++++++++--
 net/sctp/socket.c    |  5 +++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 16ecfbc95614..297d9cf960b9 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -650,8 +650,16 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc,
 	peer->sackdelay = asoc->sackdelay;
 	peer->sackfreq = asoc->sackfreq;
 
-	if (addr->sa.sa_family == AF_INET6)
-		peer->flowlabel = asoc->flowlabel;
+	if (addr->sa.sa_family == AF_INET6) {
+		__be32 info = addr->v6.sin6_flowinfo;
+
+		if (info) {
+			peer->flowlabel = ntohl(info & IPV6_FLOWLABEL_MASK);
+			peer->flowlabel |= SCTP_FLOWLABEL_SET_MASK;
+		} else {
+			peer->flowlabel = asoc->flowlabel;
+		}
+	}
 	peer->dscp = asoc->dscp;
 
 	/* Enable/disable heartbeat, SACK delay, and path MTU discovery
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 50b7ef975b42..502c0d7cb105 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1697,6 +1697,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 	struct sctp_association *asoc;
 	enum sctp_scope scope;
 	struct cmsghdr *cmsg;
+	__be32 flowinfo = 0;
 	struct sctp_af *af;
 	int err;
 
@@ -1781,6 +1782,9 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 	if (!cmsgs->addrs_msg)
 		return 0;
 
+	if (daddr->sa.sa_family == AF_INET6)
+		flowinfo = daddr->v6.sin6_flowinfo;
+
 	/* sendv addr list parse */
 	for_each_cmsghdr(cmsg, cmsgs->addrs_msg) {
 		struct sctp_transport *transport;
@@ -1813,6 +1817,7 @@ static int sctp_sendmsg_new_asoc(struct sock *sk, __u16 sflags,
 			}
 
 			dlen = sizeof(struct in6_addr);
+			daddr->v6.sin6_flowinfo = flowinfo;
 			daddr->v6.sin6_family = AF_INET6;
 			daddr->v6.sin6_port = htons(asoc->peer.port);
 			memcpy(&daddr->v6.sin6_addr, CMSG_DATA(cmsg), dlen);
-- 
cgit v1.2.3


From 0999f021c988770a37edfb266027db9c413901fd Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Mon, 2 Jul 2018 18:21:15 +0800
Subject: sctp: check for ipv6_pinfo legal sndflow with flowlabel in
 sctp_v6_get_dst

The transport with illegal flowlabel should not be allowed to send
packets. Other transport protocols already denies this.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/ipv6.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
index 38102bf7f13e..fc6c5e4bffa5 100644
--- a/net/sctp/ipv6.c
+++ b/net/sctp/ipv6.c
@@ -262,6 +262,15 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
 	if (t->flowlabel & SCTP_FLOWLABEL_SET_MASK)
 		fl6->flowlabel = htonl(t->flowlabel & SCTP_FLOWLABEL_VAL_MASK);
 
+	if (np->sndflow && (fl6->flowlabel & IPV6_FLOWLABEL_MASK)) {
+		struct ip6_flowlabel *flowlabel;
+
+		flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
+		if (!flowlabel)
+			goto out;
+		fl6_sock_release(flowlabel);
+	}
+
 	pr_debug("%s: dst=%pI6 ", __func__, &fl6->daddr);
 
 	if (asoc)
-- 
cgit v1.2.3


From f6ad8c1bcdf014272d08c55b9469536952a0a771 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:12:45 +0100
Subject: net: core: trivial netif_receive_skb_list() entry point

Just calls netif_receive_skb() in a loop.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  1 +
 net/core/dev.c            | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 64480a0f2c16..f67258f057ca 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3477,6 +3477,7 @@ int netif_rx(struct sk_buff *skb);
 int netif_rx_ni(struct sk_buff *skb);
 int netif_receive_skb(struct sk_buff *skb);
 int netif_receive_skb_core(struct sk_buff *skb);
+void netif_receive_skb_list(struct list_head *head);
 gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
 void napi_gro_flush(struct napi_struct *napi, bool flush_old);
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
diff --git a/net/core/dev.c b/net/core/dev.c
index 08d58e0debe5..85c456a4b551 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4906,6 +4906,25 @@ int netif_receive_skb(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(netif_receive_skb);
 
+/**
+ *	netif_receive_skb_list - process many receive buffers from network
+ *	@head: list of skbs to process.
+ *
+ *	For now, just calls netif_receive_skb() in a loop, ignoring the
+ *	return value.
+ *
+ *	This function may only be called from softirq context and interrupts
+ *	should be enabled.
+ */
+void netif_receive_skb_list(struct list_head *head)
+{
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list)
+		netif_receive_skb(skb);
+}
+EXPORT_SYMBOL(netif_receive_skb_list);
+
 DEFINE_PER_CPU(struct work_struct, flush_works);
 
 /* Network device is going away, flush any packets still pending */
-- 
cgit v1.2.3


From e090bfb9f19259b958387d2bd4938d66b324cd09 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:12:53 +0100
Subject: sfc: batch up RX delivery

Improves packet rate of 1-byte UDP receives by up to 10%.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/efx.c        | 12 ++++++++++++
 drivers/net/ethernet/sfc/net_driver.h |  3 +++
 drivers/net/ethernet/sfc/rx.c         |  7 ++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 570ec72266f3..b24c2e21db8e 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -264,11 +264,17 @@ static int efx_check_disabled(struct efx_nic *efx)
 static int efx_process_channel(struct efx_channel *channel, int budget)
 {
 	struct efx_tx_queue *tx_queue;
+	struct list_head rx_list;
 	int spent;
 
 	if (unlikely(!channel->enabled))
 		return 0;
 
+	/* Prepare the batch receive list */
+	EFX_WARN_ON_PARANOID(channel->rx_list != NULL);
+	INIT_LIST_HEAD(&rx_list);
+	channel->rx_list = &rx_list;
+
 	efx_for_each_channel_tx_queue(tx_queue, channel) {
 		tx_queue->pkts_compl = 0;
 		tx_queue->bytes_compl = 0;
@@ -291,6 +297,10 @@ static int efx_process_channel(struct efx_channel *channel, int budget)
 		}
 	}
 
+	/* Receive any packets we queued up */
+	netif_receive_skb_list(channel->rx_list);
+	channel->rx_list = NULL;
+
 	return spent;
 }
 
@@ -555,6 +565,8 @@ static int efx_probe_channel(struct efx_channel *channel)
 			goto fail;
 	}
 
+	channel->rx_list = NULL;
+
 	return 0;
 
 fail:
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 65568925c3ef..961b92979640 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -448,6 +448,7 @@ enum efx_sync_events_state {
  *	__efx_rx_packet(), or zero if there is none
  * @rx_pkt_index: Ring index of first buffer for next packet to be delivered
  *	by __efx_rx_packet(), if @rx_pkt_n_frags != 0
+ * @rx_list: list of SKBs from current RX, awaiting processing
  * @rx_queue: RX queue for this channel
  * @tx_queue: TX queues for this channel
  * @sync_events_state: Current state of sync events on this channel
@@ -500,6 +501,8 @@ struct efx_channel {
 	unsigned int rx_pkt_n_frags;
 	unsigned int rx_pkt_index;
 
+	struct list_head *rx_list;
+
 	struct efx_rx_queue rx_queue;
 	struct efx_tx_queue tx_queue[EFX_TXQ_TYPES];
 
diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c
index d2e254f2f72b..396ff01298cd 100644
--- a/drivers/net/ethernet/sfc/rx.c
+++ b/drivers/net/ethernet/sfc/rx.c
@@ -634,7 +634,12 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh,
 			return;
 
 	/* Pass the packet up */
-	netif_receive_skb(skb);
+	if (channel->rx_list != NULL)
+		/* Add to list, will pass up later */
+		list_add_tail(&skb->list, channel->rx_list);
+	else
+		/* No list, so pass it up now */
+		netif_receive_skb(skb);
 }
 
 /* Handle a received packet.  Second half: Touches packet payload. */
-- 
cgit v1.2.3


From 920572b73280a29e3a9f58807a8b90051b19ee60 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:13:11 +0100
Subject: net: core: unwrap skb list receive slightly further

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/net.h | 7 +++++++
 net/core/dev.c             | 4 +++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 9c886739246a..00aa72ce0e7c 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -223,6 +223,13 @@ DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_entry,
 	TP_ARGS(skb)
 );
 
+DEFINE_EVENT(net_dev_rx_verbose_template, netif_receive_skb_list_entry,
+
+	TP_PROTO(const struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
 DEFINE_EVENT(net_dev_rx_verbose_template, netif_rx_entry,
 
 	TP_PROTO(const struct sk_buff *skb),
diff --git a/net/core/dev.c b/net/core/dev.c
index 85c456a4b551..308acfd48139 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4920,8 +4920,10 @@ void netif_receive_skb_list(struct list_head *head)
 {
 	struct sk_buff *skb, *next;
 
+	list_for_each_entry(skb, head, list)
+		trace_netif_receive_skb_list_entry(skb);
 	list_for_each_entry_safe(skb, next, head, list)
-		netif_receive_skb(skb);
+		netif_receive_skb_internal(skb);
 }
 EXPORT_SYMBOL(netif_receive_skb_list);
 
-- 
cgit v1.2.3


From 7da517a3bc529dc5399e742688b32cafa2ca5ca0 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:13:24 +0100
Subject: net: core: Another step of skb receive list processing

netif_receive_skb_list_internal() now processes a list and hands it
 on to the next function.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 61 +++++++++++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 56 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 308acfd48139..1e87361df2ab 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4843,6 +4843,14 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	return ret;
 }
 
+static void __netif_receive_skb_list(struct list_head *head)
+{
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list)
+		__netif_receive_skb(skb);
+}
+
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
@@ -4883,6 +4891,50 @@ static int netif_receive_skb_internal(struct sk_buff *skb)
 	return ret;
 }
 
+static void netif_receive_skb_list_internal(struct list_head *head)
+{
+	struct bpf_prog *xdp_prog = NULL;
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		net_timestamp_check(netdev_tstamp_prequeue, skb);
+		if (skb_defer_rx_timestamp(skb))
+			/* Handled, remove from list */
+			list_del(&skb->list);
+	}
+
+	if (static_branch_unlikely(&generic_xdp_needed_key)) {
+		preempt_disable();
+		rcu_read_lock();
+		list_for_each_entry_safe(skb, next, head, list) {
+			xdp_prog = rcu_dereference(skb->dev->xdp_prog);
+			if (do_xdp_generic(xdp_prog, skb) != XDP_PASS)
+				/* Dropped, remove from list */
+				list_del(&skb->list);
+		}
+		rcu_read_unlock();
+		preempt_enable();
+	}
+
+	rcu_read_lock();
+#ifdef CONFIG_RPS
+	if (static_key_false(&rps_needed)) {
+		list_for_each_entry_safe(skb, next, head, list) {
+			struct rps_dev_flow voidflow, *rflow = &voidflow;
+			int cpu = get_rps_cpu(skb->dev, skb, &rflow);
+
+			if (cpu >= 0) {
+				enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
+				/* Handled, remove from list */
+				list_del(&skb->list);
+			}
+		}
+	}
+#endif
+	__netif_receive_skb_list(head);
+	rcu_read_unlock();
+}
+
 /**
  *	netif_receive_skb - process receive buffer from network
  *	@skb: buffer to process
@@ -4910,20 +4962,19 @@ EXPORT_SYMBOL(netif_receive_skb);
  *	netif_receive_skb_list - process many receive buffers from network
  *	@head: list of skbs to process.
  *
- *	For now, just calls netif_receive_skb() in a loop, ignoring the
- *	return value.
+ *	Since return value of netif_receive_skb() is normally ignored, and
+ *	wouldn't be meaningful for a list, this function returns void.
  *
  *	This function may only be called from softirq context and interrupts
  *	should be enabled.
  */
 void netif_receive_skb_list(struct list_head *head)
 {
-	struct sk_buff *skb, *next;
+	struct sk_buff *skb;
 
 	list_for_each_entry(skb, head, list)
 		trace_netif_receive_skb_list_entry(skb);
-	list_for_each_entry_safe(skb, next, head, list)
-		netif_receive_skb_internal(skb);
+	netif_receive_skb_list_internal(head);
 }
 EXPORT_SYMBOL(netif_receive_skb_list);
 
-- 
cgit v1.2.3


From 4ce0017a373afaaa9ef17614d8fa4f6fde261d18 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:13:40 +0100
Subject: net: core: another layer of lists, around PF_MEMALLOC skb handling

First example of a layer splitting the list (rather than merely taking
 individual packets off it).
Involves new list.h function, list_cut_before(), like list_cut_position()
 but cuts on the other side of the given entry.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/list.h | 30 ++++++++++++++++++++++++++++++
 net/core/dev.c       | 44 ++++++++++++++++++++++++++++++++++++--------
 2 files changed, 66 insertions(+), 8 deletions(-)

diff --git a/include/linux/list.h b/include/linux/list.h
index 4b129df4d46b..de04cc5ed536 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -285,6 +285,36 @@ static inline void list_cut_position(struct list_head *list,
 		__list_cut_position(list, head, entry);
 }
 
+/**
+ * list_cut_before - cut a list into two, before given entry
+ * @list: a new list to add all removed entries
+ * @head: a list with entries
+ * @entry: an entry within head, could be the head itself
+ *
+ * This helper moves the initial part of @head, up to but
+ * excluding @entry, from @head to @list.  You should pass
+ * in @entry an element you know is on @head.  @list should
+ * be an empty list or a list you do not care about losing
+ * its data.
+ * If @entry == @head, all entries on @head are moved to
+ * @list.
+ */
+static inline void list_cut_before(struct list_head *list,
+				   struct list_head *head,
+				   struct list_head *entry)
+{
+	if (head->next == entry) {
+		INIT_LIST_HEAD(list);
+		return;
+	}
+	list->next = head->next;
+	list->next->prev = list;
+	list->prev = entry->prev;
+	list->prev->next = list;
+	head->next = entry;
+	entry->prev = head;
+}
+
 static inline void __list_splice(const struct list_head *list,
 				 struct list_head *prev,
 				 struct list_head *next)
diff --git a/net/core/dev.c b/net/core/dev.c
index 1e87361df2ab..9aadef976e8c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4784,6 +4784,14 @@ int netif_receive_skb_core(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(netif_receive_skb_core);
 
+static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
+{
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list)
+		__netif_receive_skb_core(skb, pfmemalloc);
+}
+
 static int __netif_receive_skb(struct sk_buff *skb)
 {
 	int ret;
@@ -4809,6 +4817,34 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	return ret;
 }
 
+static void __netif_receive_skb_list(struct list_head *head)
+{
+	unsigned long noreclaim_flag = 0;
+	struct sk_buff *skb, *next;
+	bool pfmemalloc = false; /* Is current sublist PF_MEMALLOC? */
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		if ((sk_memalloc_socks() && skb_pfmemalloc(skb)) != pfmemalloc) {
+			struct list_head sublist;
+
+			/* Handle the previous sublist */
+			list_cut_before(&sublist, head, &skb->list);
+			__netif_receive_skb_list_core(&sublist, pfmemalloc);
+			pfmemalloc = !pfmemalloc;
+			/* See comments in __netif_receive_skb */
+			if (pfmemalloc)
+				noreclaim_flag = memalloc_noreclaim_save();
+			else
+				memalloc_noreclaim_restore(noreclaim_flag);
+		}
+	}
+	/* Handle the remaining sublist */
+	__netif_receive_skb_list_core(head, pfmemalloc);
+	/* Restore pflags */
+	if (pfmemalloc)
+		memalloc_noreclaim_restore(noreclaim_flag);
+}
+
 static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 {
 	struct bpf_prog *old = rtnl_dereference(dev->xdp_prog);
@@ -4843,14 +4879,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 	return ret;
 }
 
-static void __netif_receive_skb_list(struct list_head *head)
-{
-	struct sk_buff *skb, *next;
-
-	list_for_each_entry_safe(skb, next, head, list)
-		__netif_receive_skb(skb);
-}
-
 static int netif_receive_skb_internal(struct sk_buff *skb)
 {
 	int ret;
-- 
cgit v1.2.3


From 88eb1944e18c1ba61da538ae9d1732832eb79b9d Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:13:56 +0100
Subject: net: core: propagate SKB lists through packet_type lookup

__netif_receive_skb_core() does a depressingly large amount of per-packet
 work that can't easily be listified, because the another_round looping
 makes it nontrivial to slice up into smaller functions.
Fortunately, most of that work disappears in the fast path:
 * Hardware devices generally don't have an rx_handler
 * Unless you're tcpdumping or something, there is usually only one ptype
 * VLAN processing comes before the protocol ptype lookup, so doesn't force
   a pt_prev deliver
 so normally, __netif_receive_skb_core() will run straight through and pass
 back the one ptype found in ptype_base[hash of skb->protocol].

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 72 +++++++++++++++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 64 insertions(+), 8 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 9aadef976e8c..1bc485bb0678 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4608,7 +4608,8 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
 	return 0;
 }
 
-static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc)
+static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc,
+				    struct packet_type **ppt_prev)
 {
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
@@ -4738,8 +4739,7 @@ skip_classify:
 	if (pt_prev) {
 		if (unlikely(skb_orphan_frags_rx(skb, GFP_ATOMIC)))
 			goto drop;
-		else
-			ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+		*ppt_prev = pt_prev;
 	} else {
 drop:
 		if (!deliver_exact)
@@ -4757,6 +4757,18 @@ out:
 	return ret;
 }
 
+static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc)
+{
+	struct net_device *orig_dev = skb->dev;
+	struct packet_type *pt_prev = NULL;
+	int ret;
+
+	ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+	if (pt_prev)
+		ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+	return ret;
+}
+
 /**
  *	netif_receive_skb_core - special purpose version of netif_receive_skb
  *	@skb: buffer to process
@@ -4777,19 +4789,63 @@ int netif_receive_skb_core(struct sk_buff *skb)
 	int ret;
 
 	rcu_read_lock();
-	ret = __netif_receive_skb_core(skb, false);
+	ret = __netif_receive_skb_one_core(skb, false);
 	rcu_read_unlock();
 
 	return ret;
 }
 EXPORT_SYMBOL(netif_receive_skb_core);
 
-static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
+static inline void __netif_receive_skb_list_ptype(struct list_head *head,
+						  struct packet_type *pt_prev,
+						  struct net_device *orig_dev)
 {
 	struct sk_buff *skb, *next;
 
+	if (!pt_prev)
+		return;
+	if (list_empty(head))
+		return;
+
 	list_for_each_entry_safe(skb, next, head, list)
-		__netif_receive_skb_core(skb, pfmemalloc);
+		pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+}
+
+static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
+{
+	/* Fast-path assumptions:
+	 * - There is no RX handler.
+	 * - Only one packet_type matches.
+	 * If either of these fails, we will end up doing some per-packet
+	 * processing in-line, then handling the 'last ptype' for the whole
+	 * sublist.  This can't cause out-of-order delivery to any single ptype,
+	 * because the 'last ptype' must be constant across the sublist, and all
+	 * other ptypes are handled per-packet.
+	 */
+	/* Current (common) ptype of sublist */
+	struct packet_type *pt_curr = NULL;
+	/* Current (common) orig_dev of sublist */
+	struct net_device *od_curr = NULL;
+	struct list_head sublist;
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *orig_dev = skb->dev;
+		struct packet_type *pt_prev = NULL;
+
+		__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+		if (pt_curr != pt_prev || od_curr != orig_dev) {
+			/* dispatch old sublist */
+			list_cut_before(&sublist, head, &skb->list);
+			__netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr);
+			/* start new sublist */
+			pt_curr = pt_prev;
+			od_curr = orig_dev;
+		}
+	}
+
+	/* dispatch final sublist */
+	__netif_receive_skb_list_ptype(head, pt_curr, od_curr);
 }
 
 static int __netif_receive_skb(struct sk_buff *skb)
@@ -4809,10 +4865,10 @@ static int __netif_receive_skb(struct sk_buff *skb)
 		 * context down to all allocation sites.
 		 */
 		noreclaim_flag = memalloc_noreclaim_save();
-		ret = __netif_receive_skb_core(skb, true);
+		ret = __netif_receive_skb_one_core(skb, true);
 		memalloc_noreclaim_restore(noreclaim_flag);
 	} else
-		ret = __netif_receive_skb_core(skb, false);
+		ret = __netif_receive_skb_one_core(skb, false);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 17266ee939849cb095ed7dd9edbec4162172226b Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:14:12 +0100
Subject: net: ipv4: listified version of ip_rcv

Also involved adding a way to run a netfilter hook over a list of packets.
 Rather than attempting to make netfilter know about lists (which would be
 a major project in itself) we just let it call the regular okfn (in this
 case ip_rcv_finish()) for any packets it steals, and have it give us back
 a list of packets it's synchronously accepted (which normally NF_HOOK
 would automatically call okfn() on, but we want to be able to potentially
 pass the list to a listified version of okfn().)
The netfilter hooks themselves are indirect calls that still happen per-
 packet (see nf_hook_entry_hookfn()), but again, changing that can be left
 for future work.

There is potential for out-of-order receives if the netfilter hook ends up
 synchronously stealing packets, as they will be processed before any
 accepts earlier in the list.  However, it was already possible for an
 asynchronous accept to cause out-of-order receives, so presumably this is
 considered OK.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  3 +++
 include/linux/netfilter.h | 22 +++++++++++++++
 include/net/ip.h          |  2 ++
 net/core/dev.c            |  8 +++---
 net/ipv4/af_inet.c        |  1 +
 net/ipv4/ip_input.c       | 68 ++++++++++++++++++++++++++++++++++++++++++-----
 6 files changed, 94 insertions(+), 10 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f67258f057ca..c1ef749b6f9f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2297,6 +2297,9 @@ struct packet_type {
 					 struct net_device *,
 					 struct packet_type *,
 					 struct net_device *);
+	void			(*list_func) (struct list_head *,
+					      struct packet_type *,
+					      struct net_device *);
 	bool			(*id_match)(struct packet_type *ptype,
 					    struct sock *sk);
 	void			*af_packet_priv;
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index dd2052f0efb7..5a5e0a2ab2a3 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -288,6 +288,20 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk, struct
 	return ret;
 }
 
+static inline void
+NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
+	     struct list_head *head, struct net_device *in, struct net_device *out,
+	     int (*okfn)(struct net *, struct sock *, struct sk_buff *))
+{
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn);
+		if (ret != 1)
+			list_del(&skb->list);
+	}
+}
+
 /* Call setsockopt() */
 int nf_setsockopt(struct sock *sk, u_int8_t pf, int optval, char __user *opt,
 		  unsigned int len);
@@ -369,6 +383,14 @@ NF_HOOK(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
 	return okfn(net, sk, skb);
 }
 
+static inline void
+NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
+	     struct list_head *head, struct net_device *in, struct net_device *out,
+	     int (*okfn)(struct net *, struct sock *, struct sk_buff *))
+{
+	/* nothing to do */
+}
+
 static inline int nf_hook(u_int8_t pf, unsigned int hook, struct net *net,
 			  struct sock *sk, struct sk_buff *skb,
 			  struct net_device *indev, struct net_device *outdev,
diff --git a/include/net/ip.h b/include/net/ip.h
index 09da79d8ceea..99d1b835d2aa 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -138,6 +138,8 @@ int ip_build_and_send_pkt(struct sk_buff *skb, const struct sock *sk,
 			  struct ip_options_rcu *opt);
 int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 	   struct net_device *orig_dev);
+void ip_list_rcv(struct list_head *head, struct packet_type *pt,
+		 struct net_device *orig_dev);
 int ip_local_deliver(struct sk_buff *skb);
 int ip_mr_input(struct sk_buff *skb);
 int ip_output(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1bc485bb0678..5e22719ce71d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4806,9 +4806,11 @@ static inline void __netif_receive_skb_list_ptype(struct list_head *head,
 		return;
 	if (list_empty(head))
 		return;
-
-	list_for_each_entry_safe(skb, next, head, list)
-		pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
+	if (pt_prev->list_func != NULL)
+		pt_prev->list_func(head, pt_prev, orig_dev);
+	else
+		list_for_each_entry_safe(skb, next, head, list)
+			pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 }
 
 static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemalloc)
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9263a2c114e0..c716be13d58c 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1882,6 +1882,7 @@ fs_initcall(ipv4_offload_init);
 static struct packet_type ip_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IP),
 	.func = ip_rcv,
+	.list_func = ip_list_rcv,
 };
 
 static int __init inet_init(void)
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 7582713dd18f..914240830bdf 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -408,10 +408,9 @@ drop_error:
 /*
  * 	Main IP Receive routine.
  */
-int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net)
 {
 	const struct iphdr *iph;
-	struct net *net;
 	u32 len;
 
 	/* When the interface is in promisc. mode, drop all the crap
@@ -421,7 +420,6 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 		goto drop;
 
 
-	net = dev_net(dev);
 	__IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len);
 
 	skb = skb_share_check(skb, GFP_ATOMIC);
@@ -489,9 +487,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 	/* Must drop socket now because of tproxy. */
 	skb_orphan(skb);
 
-	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
-		       net, NULL, skb, dev, NULL,
-		       ip_rcv_finish);
+	return skb;
 
 csum_error:
 	__IP_INC_STATS(net, IPSTATS_MIB_CSUMERRORS);
@@ -500,5 +496,63 @@ inhdr_error:
 drop:
 	kfree_skb(skb);
 out:
-	return NET_RX_DROP;
+	return NULL;
+}
+
+/*
+ * IP receive entry point
+ */
+int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
+	   struct net_device *orig_dev)
+{
+	struct net *net = dev_net(dev);
+
+	skb = ip_rcv_core(skb, net);
+	if (skb == NULL)
+		return NET_RX_DROP;
+	return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
+		       net, NULL, skb, dev, NULL,
+		       ip_rcv_finish);
+}
+
+static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
+			   struct net *net)
+{
+	struct sk_buff *skb, *next;
+
+	NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL,
+		     head, dev, NULL, ip_rcv_finish);
+	list_for_each_entry_safe(skb, next, head, list)
+		ip_rcv_finish(net, NULL, skb);
+}
+
+/* Receive a list of IP packets */
+void ip_list_rcv(struct list_head *head, struct packet_type *pt,
+		 struct net_device *orig_dev)
+{
+	struct net_device *curr_dev = NULL;
+	struct net *curr_net = NULL;
+	struct sk_buff *skb, *next;
+	struct list_head sublist;
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *dev = skb->dev;
+		struct net *net = dev_net(dev);
+
+		skb = ip_rcv_core(skb, net);
+		if (skb == NULL)
+			continue;
+
+		if (curr_dev != dev || curr_net != net) {
+			/* dispatch old sublist */
+			list_cut_before(&sublist, head, &skb->list);
+			if (!list_empty(&sublist))
+				ip_sublist_rcv(&sublist, dev, net);
+			/* start new sublist */
+			curr_dev = dev;
+			curr_net = net;
+		}
+	}
+	/* dispatch final sublist */
+	ip_sublist_rcv(head, curr_dev, curr_net);
 }
-- 
cgit v1.2.3


From 5fa12739a53d0780265ed9d44d9ec9ba5f9ad00a Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:14:34 +0100
Subject: net: ipv4: listify ip_rcv_finish

ip_rcv_finish_core(), if it does not drop, sets skb->dst by either early
 demux or route lookup.  The last step, calling dst_input(skb), is left to
 the caller; in the listified case, we split to form sublists with a common
 dst, but then ip_sublist_rcv_finish() just calls dst_input(skb) in a loop.
The next step in listification would thus be to add a list_input() method
 to struct dst_entry.

Early demux is an indirect call based on iph->protocol; this is another
 opportunity for listification which is not taken here (it would require
 slicing up ip_rcv_finish_core() to allow splitting on protocol changes).

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_input.c | 54 +++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 48 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 914240830bdf..24b9b0210aeb 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -307,7 +307,8 @@ drop:
 	return true;
 }
 
-static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static int ip_rcv_finish_core(struct net *net, struct sock *sk,
+			      struct sk_buff *skb)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	int (*edemux)(struct sk_buff *skb);
@@ -393,7 +394,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 	}
 
-	return dst_input(skb);
+	return NET_RX_SUCCESS;
 
 drop:
 	kfree_skb(skb);
@@ -405,6 +406,15 @@ drop_error:
 	goto drop;
 }
 
+static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	int ret = ip_rcv_finish_core(net, sk, skb);
+
+	if (ret != NET_RX_DROP)
+		ret = dst_input(skb);
+	return ret;
+}
+
 /*
  * 	Main IP Receive routine.
  */
@@ -515,15 +525,47 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
 		       ip_rcv_finish);
 }
 
-static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
-			   struct net *net)
+static void ip_sublist_rcv_finish(struct list_head *head)
 {
 	struct sk_buff *skb, *next;
 
+	list_for_each_entry_safe(skb, next, head, list)
+		dst_input(skb);
+}
+
+static void ip_list_rcv_finish(struct net *net, struct sock *sk,
+			       struct list_head *head)
+{
+	struct dst_entry *curr_dst = NULL;
+	struct sk_buff *skb, *next;
+	struct list_head sublist;
+
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct dst_entry *dst;
+
+		if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
+			continue;
+
+		dst = skb_dst(skb);
+		if (curr_dst != dst) {
+			/* dispatch old sublist */
+			list_cut_before(&sublist, head, &skb->list);
+			if (!list_empty(&sublist))
+				ip_sublist_rcv_finish(&sublist);
+			/* start new sublist */
+			curr_dst = dst;
+		}
+	}
+	/* dispatch final sublist */
+	ip_sublist_rcv_finish(head);
+}
+
+static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
+			   struct net *net)
+{
 	NF_HOOK_LIST(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL,
 		     head, dev, NULL, ip_rcv_finish);
-	list_for_each_entry_safe(skb, next, head, list)
-		ip_rcv_finish(net, NULL, skb);
+	ip_list_rcv_finish(net, NULL, head);
 }
 
 /* Receive a list of IP packets */
-- 
cgit v1.2.3


From b9f463d6c9849230043123a6335d59ac7fea4d5a Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 2 Jul 2018 16:14:44 +0100
Subject: net: don't bother calling list RX functions on empty lists

Generally the check should be very cheap, as the sk_buff_head is in cache.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5e22719ce71d..7e6a2f66db5c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4887,7 +4887,8 @@ static void __netif_receive_skb_list(struct list_head *head)
 
 			/* Handle the previous sublist */
 			list_cut_before(&sublist, head, &skb->list);
-			__netif_receive_skb_list_core(&sublist, pfmemalloc);
+			if (!list_empty(&sublist))
+				__netif_receive_skb_list_core(&sublist, pfmemalloc);
 			pfmemalloc = !pfmemalloc;
 			/* See comments in __netif_receive_skb */
 			if (pfmemalloc)
@@ -4897,7 +4898,8 @@ static void __netif_receive_skb_list(struct list_head *head)
 		}
 	}
 	/* Handle the remaining sublist */
-	__netif_receive_skb_list_core(head, pfmemalloc);
+	if (!list_empty(head))
+		__netif_receive_skb_list_core(head, pfmemalloc);
 	/* Restore pflags */
 	if (pfmemalloc)
 		memalloc_noreclaim_restore(noreclaim_flag);
@@ -5058,6 +5060,8 @@ void netif_receive_skb_list(struct list_head *head)
 {
 	struct sk_buff *skb;
 
+	if (list_empty(head))
+		return;
 	list_for_each_entry(skb, head, list)
 		trace_netif_receive_skb_list_entry(skb);
 	netif_receive_skb_list_internal(head);
-- 
cgit v1.2.3


From 35c31d5c323f14ddd70c3382ca0a65b0b92d02ee Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 2 Jul 2018 19:58:49 +0200
Subject: selftests: forwarding: Test mirror-to-gretap w/ UL 802.1d

Test for "tc action mirred egress mirror" that mirrors to gretap when
the underlay route points at a VLAN-unaware bridge (802.1d).

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/mirror_gre_bridge_1d.sh         | 132 +++++++++++++++++++++
 1 file changed, 132 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh
new file mode 100755
index 000000000000..c5095da7f6bf
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1d.sh
@@ -0,0 +1,132 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device without vlan filtering (802.1d).
+#
+# This test uses standard topology for testing mirror-to-gretap. See
+# mirror_gre_topo_lib.sh for more details. The full topology is as follows:
+#
+#  +---------------------+                             +---------------------+
+#  | H1                  |                             |                  H2 |
+#  |     + $h1           |                             |           $h2 +     |
+#  |     | 192.0.2.1/28  |                             |  192.0.2.2/28 |     |
+#  +-----|---------------+                             +---------------|-----+
+#        |                                                             |
+#  +-----|-------------------------------------------------------------|-----+
+#  | SW  o---> mirror                                                  |     |
+#  | +---|-------------------------------------------------------------|---+ |
+#  | |   + $swp1            + br1 (802.1q bridge)                $swp2 +   | |
+#  | +---------------------------------------------------------------------+ |
+#  |                                                                         |
+#  | +---------------------------------------------------------------------+ |
+#  | |                      + br2 (802.1d bridge)                          | |
+#  | |                        192.0.2.129/28                               | |
+#  | |   + $swp3              2001:db8:2::1/64                             | |
+#  | +---|-----------------------------------------------------------------+ |
+#  |     |                                          ^                    ^   |
+#  |     |                     + gt6 (ip6gretap)    | + gt4 (gretap)     |   |
+#  |     |                     : loc=2001:db8:2::1  | : loc=192.0.2.129  |   |
+#  |     |                     : rem=2001:db8:2::2 -+ : rem=192.0.2.130 -+   |
+#  |     |                     : ttl=100              : ttl=100              |
+#  |     |                     : tos=inherit          : tos=inherit          |
+#  +-----|---------------------:----------------------:----------------------+
+#        |                     :                      :
+#  +-----|---------------------:----------------------:----------------------+
+#  | H3  + $h3                 + h3-gt6(ip6gretap)    + h3-gt4 (gretap)      |
+#  |       192.0.2.130/28        loc=2001:db8:2::2      loc=192.0.2.130      |
+#  |       2001:db8:2::2/64      rem=2001:db8:2::1      rem=192.0.2.129      |
+#  |                             ttl=100                ttl=100              |
+#  |                             tos=inherit            tos=inherit          |
+#  +-------------------------------------------------------------------------+
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip link add name br2 type bridge vlan_filtering 0
+	ip link set dev br2 up
+
+	ip link set dev $swp3 master br2
+	ip route add 192.0.2.130/32 dev br2
+	ip -6 route add 2001:db8:2::2/128 dev br2
+
+	ip address add dev br2 192.0.2.129/28
+	ip address add dev br2 2001:db8:2::1/64
+
+	ip address add dev $h3 192.0.2.130/28
+	ip address add dev $h3 2001:db8:2::2/64
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip address del dev $h3 2001:db8:2::2/64
+	ip address del dev $h3 192.0.2.130/28
+	ip link del dev br2
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_gretap()
+{
+	full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+	full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+	full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+	full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 239e754af854137f300e7d3ea199684c3e02a888 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 2 Jul 2018 19:58:56 +0200
Subject: selftests: forwarding: Test mirror-to-gretap w/ UL 802.1q

Test for "tc action mirred egress mirror" that mirrors to gretap when
the underlay route points at a VLAN-aware bridge (802.1q).

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/mirror_gre_bridge_1q.sh         | 126 +++++++++++++++++++++
 1 file changed, 126 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh
new file mode 100755
index 000000000000..a3402cd8d5b6
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q.sh
@@ -0,0 +1,126 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device with vlan filtering (802.1q).
+#
+# This test uses standard topology for testing mirror-to-gretap. See
+# mirror_gre_topo_lib.sh for more details. The full topology is as follows:
+#
+#  +---------------------+                               +---------------------+
+#  | H1                  |                               |                  H2 |
+#  |     + $h1           |                               |           $h2 +     |
+#  |     | 192.0.2.1/28  |                               |  192.0.2.2/28 |     |
+#  +-----|---------------+                               +---------------|-----+
+#        |                                                               |
+#  +-----|---------------------------------------------------------------|-----+
+#  | SW  o---> mirror                                                    |     |
+#  | +---|---------------------------------------------------------------|---+ |
+#  | |   + $swp1                  + br1 (802.1q bridge)            $swp2 +   | |
+#  | |                              192.0.2.129/28                           | |
+#  | |   + $swp3                    2001:db8:2::1/64                         | |
+#  | |   | vid555                   vid555[pvid,untagged]                    | |
+#  | +---|-------------------------------------------------------------------+ |
+#  |     |                                          ^                      ^   |
+#  |     |                     + gt6 (ip6gretap)    |   + gt4 (gretap)     |   |
+#  |     |                     : loc=2001:db8:2::1  |   : loc=192.0.2.129  |   |
+#  |     |                     : rem=2001:db8:2::2 -+   : rem=192.0.2.130 -+   |
+#  |     |                     : ttl=100                : ttl=100              |
+#  |     |                     : tos=inherit            : tos=inherit          |
+#  +-----|---------------------:------------------------:----------------------+
+#        |                     :                        :
+#  +-----|---------------------:------------------------:----------------------+
+#  | H3  + $h3                 + h3-gt6(ip6gretap)      + h3-gt4 (gretap)      |
+#  |     |                       loc=2001:db8:2::2        loc=192.0.2.130      |
+#  |     + $h3.555               rem=2001:db8:2::1        rem=192.0.2.129      |
+#  |       192.0.2.130/28        ttl=100                  ttl=100              |
+#  |       2001:db8:2::2/64      tos=inherit              tos=inherit          |
+#  +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+	test_gretap
+	test_ip6gretap
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+source mirror_gre_topo_lib.sh
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip link set dev $swp3 master br1
+	bridge vlan add dev br1 vid 555 pvid untagged self
+	ip address add dev br1 192.0.2.129/28
+	ip address add dev br1 2001:db8:2::1/64
+
+	ip -4 route add 192.0.2.130/32 dev br1
+	ip -6 route add 2001:db8:2::2/128 dev br1
+
+	vlan_create $h3 555 v$h3 192.0.2.130/28 2001:db8:2::2/64
+	bridge vlan add dev $swp3 vid 555
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	ip link set dev $swp3 nomaster
+	vlan_destroy $h3 555
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_gretap()
+{
+	full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap"
+	full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap"
+}
+
+test_ip6gretap()
+{
+	full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap"
+	full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap"
+}
+
+tests()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+tests
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	tests
+fi
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 0ac942826b3d900b7054f71bb6a15428441458d2 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.vnet.ibm.com>
Date: Fri, 8 Apr 2016 17:55:19 +0200
Subject: s390/pci: add fmt3 fmb

Add support for format 3 function measurement blocks.

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/pci.h | 5 +++++
 arch/s390/pci/pci_debug.c   | 8 ++++++++
 2 files changed, 13 insertions(+)

diff --git a/arch/s390/include/asm/pci.h b/arch/s390/include/asm/pci.h
index 94f8db468c9b..10fe982f2b4b 100644
--- a/arch/s390/include/asm/pci.h
+++ b/arch/s390/include/asm/pci.h
@@ -51,6 +51,10 @@ struct zpci_fmb_fmt2 {
 	u64 max_work_units;
 };
 
+struct zpci_fmb_fmt3 {
+	u64 tx_bytes;
+};
+
 struct zpci_fmb {
 	u32 format	: 8;
 	u32 fmt_ind	: 24;
@@ -66,6 +70,7 @@ struct zpci_fmb {
 		struct zpci_fmb_fmt0 fmt0;
 		struct zpci_fmb_fmt1 fmt1;
 		struct zpci_fmb_fmt2 fmt2;
+		struct zpci_fmb_fmt3 fmt3;
 	};
 } __packed __aligned(128);
 
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index b482e95b6249..57f7cdac70a3 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -48,6 +48,10 @@ static char *pci_fmt2_names[] = {
 	"Maximum work units",
 };
 
+static char *pci_fmt3_names[] = {
+	"Transmitted bytes",
+};
+
 static char *pci_sw_names[] = {
 	"Allocated pages",
 	"Mapped pages",
@@ -112,6 +116,10 @@ static int pci_perf_show(struct seq_file *m, void *v)
 		pci_fmb_show(m, pci_fmt2_names, ARRAY_SIZE(pci_fmt2_names),
 			     &zdev->fmb->fmt2.consumed_work_units);
 		break;
+	case 3:
+		pci_fmb_show(m, pci_fmt3_names, ARRAY_SIZE(pci_fmt3_names),
+			     &zdev->fmb->fmt3.tx_bytes);
+		break;
 	default:
 		seq_puts(m, "Unknown format\n");
 	}
-- 
cgit v1.2.3


From d2f2df69885d0548ed5c0ba8fa2751497ba62352 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.ibm.com>
Date: Tue, 3 Jul 2018 13:06:45 +0200
Subject: s390/dasd: fix cast-function-type warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Change the tasklets parameter type to fix W=1 warnings when building
with gcc 8 like below:

drivers/s390/block/dasd.c: In function 'dasd_alloc_device':
drivers/s390/block/dasd.c:129:8: warning: cast between incompatible function types
from 'void (*)(struct dasd_device *)' to 'void (*)(long unsigned int)' [-Wcast-function-type]
        (void (*)(unsigned long)) dasd_device_tasklet,
        ^

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Acked-by: Jan Höppner <hoeppner@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/dasd.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
index 7c3dddeb781c..5645eb7cc395 100644
--- a/drivers/s390/block/dasd.c
+++ b/drivers/s390/block/dasd.c
@@ -64,8 +64,8 @@ static int  dasd_alloc_queue(struct dasd_block *);
 static void dasd_setup_queue(struct dasd_block *);
 static void dasd_free_queue(struct dasd_block *);
 static int dasd_flush_block_queue(struct dasd_block *);
-static void dasd_device_tasklet(struct dasd_device *);
-static void dasd_block_tasklet(struct dasd_block *);
+static void dasd_device_tasklet(unsigned long);
+static void dasd_block_tasklet(unsigned long);
 static void do_kick_device(struct work_struct *);
 static void do_restore_device(struct work_struct *);
 static void do_reload_device(struct work_struct *);
@@ -116,8 +116,7 @@ struct dasd_device *dasd_alloc_device(void)
 	dasd_init_chunklist(&device->erp_chunks, device->erp_mem, PAGE_SIZE);
 	spin_lock_init(&device->mem_lock);
 	atomic_set(&device->tasklet_scheduled, 0);
-	tasklet_init(&device->tasklet,
-		     (void (*)(unsigned long)) dasd_device_tasklet,
+	tasklet_init(&device->tasklet, dasd_device_tasklet,
 		     (unsigned long) device);
 	INIT_LIST_HEAD(&device->ccw_queue);
 	timer_setup(&device->timer, dasd_device_timeout, 0);
@@ -157,8 +156,7 @@ struct dasd_block *dasd_alloc_block(void)
 	atomic_set(&block->open_count, -1);
 
 	atomic_set(&block->tasklet_scheduled, 0);
-	tasklet_init(&block->tasklet,
-		     (void (*)(unsigned long)) dasd_block_tasklet,
+	tasklet_init(&block->tasklet, dasd_block_tasklet,
 		     (unsigned long) block);
 	INIT_LIST_HEAD(&block->ccw_queue);
 	spin_lock_init(&block->queue_lock);
@@ -2055,8 +2053,9 @@ EXPORT_SYMBOL_GPL(dasd_flush_device_queue);
 /*
  * Acquire the device lock and process queues for the device.
  */
-static void dasd_device_tasklet(struct dasd_device *device)
+static void dasd_device_tasklet(unsigned long data)
 {
+	struct dasd_device *device = (struct dasd_device *) data;
 	struct list_head final_queue;
 
 	atomic_set (&device->tasklet_scheduled, 0);
@@ -2774,8 +2773,9 @@ static void __dasd_block_start_head(struct dasd_block *block)
  * block layer request queue, creates ccw requests, enqueues them on
  * a dasd_device and processes ccw requests that have been returned.
  */
-static void dasd_block_tasklet(struct dasd_block *block)
+static void dasd_block_tasklet(unsigned long data)
 {
+	struct dasd_block *block = (struct dasd_block *) data;
 	struct list_head final_queue;
 	struct list_head *l, *n;
 	struct dasd_ccw_req *cqr;
-- 
cgit v1.2.3


From ad5728ce21398926a1215ebb38570113fa8edd99 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 3 Jul 2018 12:52:21 -0700
Subject: RAID/s390: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], this moves
the "$#" replacement from being an argument to being inside the function,
which avoids generating VLAs.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 lib/raid6/s390vx.uc | 34 ++++++++++++++++++----------------
 1 file changed, 18 insertions(+), 16 deletions(-)

diff --git a/lib/raid6/s390vx.uc b/lib/raid6/s390vx.uc
index 140fa8bb5c23..914ebe98fc21 100644
--- a/lib/raid6/s390vx.uc
+++ b/lib/raid6/s390vx.uc
@@ -55,22 +55,24 @@ static inline void XOR(int x, int y, int z)
 	asm volatile ("VX %0,%1,%2" : : "i" (x), "i" (y), "i" (z));
 }
 
-static inline void LOAD_DATA(int x, int n, u8 *ptr)
+static inline void LOAD_DATA(int x, u8 *ptr)
 {
-	typedef struct { u8 _[16*n]; } addrtype;
+	typedef struct { u8 _[16 * $#]; } addrtype;
 	register addrtype *__ptr asm("1") = (addrtype *) ptr;
 
 	asm volatile ("VLM %2,%3,0,%r1"
-		      : : "m" (*__ptr), "a" (__ptr), "i" (x), "i" (x + n - 1));
+		      : : "m" (*__ptr), "a" (__ptr), "i" (x),
+			  "i" (x + $# - 1));
 }
 
-static inline void STORE_DATA(int x, int n, u8 *ptr)
+static inline void STORE_DATA(int x, u8 *ptr)
 {
-	typedef struct { u8 _[16*n]; } addrtype;
+	typedef struct { u8 _[16 * $#]; } addrtype;
 	register addrtype *__ptr asm("1") = (addrtype *) ptr;
 
 	asm volatile ("VSTM %2,%3,0,1"
-		      : "=m" (*__ptr) : "a" (__ptr), "i" (x), "i" (x + n - 1));
+		      : "=m" (*__ptr) : "a" (__ptr), "i" (x),
+			"i" (x + $# - 1));
 }
 
 static inline void COPY_VEC(int x, int y)
@@ -93,19 +95,19 @@ static void raid6_s390vx$#_gen_syndrome(int disks, size_t bytes, void **ptrs)
 	q = dptr[z0 + 2];	/* RS syndrome */
 
 	for (d = 0; d < bytes; d += $#*NSIZE) {
-		LOAD_DATA(0,$#,&dptr[z0][d]);
+		LOAD_DATA(0,&dptr[z0][d]);
 		COPY_VEC(8+$$,0+$$);
 		for (z = z0 - 1; z >= 0; z--) {
 			MASK(16+$$,8+$$);
 			AND(16+$$,16+$$,25);
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
-			LOAD_DATA(16,$#,&dptr[z][d]);
+			LOAD_DATA(16,&dptr[z][d]);
 			XOR(0+$$,0+$$,16+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
-		STORE_DATA(0,$#,&p[d]);
-		STORE_DATA(8,$#,&q[d]);
+		STORE_DATA(0,&p[d]);
+		STORE_DATA(8,&q[d]);
 	}
 	kernel_fpu_end(&vxstate, KERNEL_VXR);
 }
@@ -127,14 +129,14 @@ static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 
 	for (d = 0; d < bytes; d += $#*NSIZE) {
 		/* P/Q data pages */
-		LOAD_DATA(0,$#,&dptr[z0][d]);
+		LOAD_DATA(0,&dptr[z0][d]);
 		COPY_VEC(8+$$,0+$$);
 		for (z = z0 - 1; z >= start; z--) {
 			MASK(16+$$,8+$$);
 			AND(16+$$,16+$$,25);
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
-			LOAD_DATA(16,$#,&dptr[z][d]);
+			LOAD_DATA(16,&dptr[z][d]);
 			XOR(0+$$,0+$$,16+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
@@ -145,12 +147,12 @@ static void raid6_s390vx$#_xor_syndrome(int disks, int start, int stop,
 			SHLBYTE(8+$$,8+$$);
 			XOR(8+$$,8+$$,16+$$);
 		}
-		LOAD_DATA(16,$#,&p[d]);
+		LOAD_DATA(16,&p[d]);
 		XOR(16+$$,16+$$,0+$$);
-		STORE_DATA(16,$#,&p[d]);
-		LOAD_DATA(16,$#,&q[d]);
+		STORE_DATA(16,&p[d]);
+		LOAD_DATA(16,&q[d]);
 		XOR(16+$$,16+$$,8+$$);
-		STORE_DATA(16,$#,&q[d]);
+		STORE_DATA(16,&q[d]);
 	}
 	kernel_fpu_end(&vxstate, KERNEL_VXR);
 }
-- 
cgit v1.2.3


From dc75e733308c3673d88664fe5e6b9478fa6bec4d Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 13 Jun 2018 13:53:28 -0700
Subject: drm/vmwgfx: Update the device headers

This change updates the device headers to the latest device version.
Where renaming affects the existing code, it's updated accordingly.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h |  230 +++--
 .../gpu/drm/vmwgfx/device_include/svga3d_devcaps.h |   83 +-
 drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h  |  297 ++++--
 .../gpu/drm/vmwgfx/device_include/svga3d_limits.h  |    4 +-
 .../drm/vmwgfx/device_include/svga3d_surfacedefs.h | 1070 +++++++++++---------
 .../gpu/drm/vmwgfx/device_include/svga3d_types.h   |  331 ++++--
 drivers/gpu/drm/vmwgfx/device_include/svga_reg.h   |  177 +++-
 drivers/gpu/drm/vmwgfx/device_include/svga_types.h |    3 +
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c                |    2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c            |    4 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c              |   15 +-
 11 files changed, 1438 insertions(+), 778 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
index 2dfd57c5f463..168bbf8373a5 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_cmd.h
@@ -46,10 +46,10 @@
  * the SVGA3D protocol and remain reserved; they should not be used in the
  * future.
  *
- * IDs between 1040 and 1999 (inclusive) are available for use by the
+ * IDs between 1040 and 2999 (inclusive) are available for use by the
  * current SVGA3D protocol.
  *
- * FIFO clients other than SVGA3D should stay below 1000, or at 2000
+ * FIFO clients other than SVGA3D should stay below 1000, or at 3000
  * and up.
  */
 
@@ -89,19 +89,19 @@ typedef enum {
    SVGA_3D_CMD_BLIT_SURFACE_TO_SCREEN                     = 1069,
    SVGA_3D_CMD_SURFACE_DEFINE_V2                          = 1070,
    SVGA_3D_CMD_GENERATE_MIPMAPS                           = 1071,
-   SVGA_3D_CMD_VIDEO_CREATE_DECODER                       = 1072,
-   SVGA_3D_CMD_VIDEO_DESTROY_DECODER                      = 1073,
-   SVGA_3D_CMD_VIDEO_CREATE_PROCESSOR                     = 1074,
-   SVGA_3D_CMD_VIDEO_DESTROY_PROCESSOR                    = 1075,
-   SVGA_3D_CMD_VIDEO_DECODE_START_FRAME                   = 1076,
-   SVGA_3D_CMD_VIDEO_DECODE_RENDER                        = 1077,
-   SVGA_3D_CMD_VIDEO_DECODE_END_FRAME                     = 1078,
-   SVGA_3D_CMD_VIDEO_PROCESS_FRAME                        = 1079,
+   SVGA_3D_CMD_DEAD4                                      = 1072,
+   SVGA_3D_CMD_DEAD5                                      = 1073,
+   SVGA_3D_CMD_DEAD6                                      = 1074,
+   SVGA_3D_CMD_DEAD7                                      = 1075,
+   SVGA_3D_CMD_DEAD8                                      = 1076,
+   SVGA_3D_CMD_DEAD9                                      = 1077,
+   SVGA_3D_CMD_DEAD10                                     = 1078,
+   SVGA_3D_CMD_DEAD11                                     = 1079,
    SVGA_3D_CMD_ACTIVATE_SURFACE                           = 1080,
    SVGA_3D_CMD_DEACTIVATE_SURFACE                         = 1081,
    SVGA_3D_CMD_SCREEN_DMA                                 = 1082,
-   SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE                   = 1083,
-   SVGA_3D_CMD_OPEN_CONTEXT_SURFACE                       = 1084,
+   SVGA_3D_CMD_DEAD1                                      = 1083,
+   SVGA_3D_CMD_DEAD2                                      = 1084,
 
    SVGA_3D_CMD_LOGICOPS_BITBLT                            = 1085,
    SVGA_3D_CMD_LOGICOPS_TRANSBLT                          = 1086,
@@ -217,7 +217,7 @@ typedef enum {
    SVGA_3D_CMD_DX_CLEAR_DEPTHSTENCIL_VIEW                 = 1177,
    SVGA_3D_CMD_DX_PRED_COPY_REGION                        = 1178,
    SVGA_3D_CMD_DX_PRED_COPY                               = 1179,
-   SVGA_3D_CMD_DX_STRETCHBLT                              = 1180,
+   SVGA_3D_CMD_DX_PRESENTBLT                              = 1180,
    SVGA_3D_CMD_DX_GENMIPS                                 = 1181,
    SVGA_3D_CMD_DX_UPDATE_SUBRESOURCE                      = 1182,
    SVGA_3D_CMD_DX_READBACK_SUBRESOURCE                    = 1183,
@@ -254,7 +254,7 @@ typedef enum {
    SVGA_3D_CMD_DX_READBACK_ALL_QUERY                      = 1214,
    SVGA_3D_CMD_DX_PRED_TRANSFER_FROM_BUFFER               = 1215,
    SVGA_3D_CMD_DX_MOB_FENCE_64                            = 1216,
-   SVGA_3D_CMD_DX_BIND_SHADER_ON_CONTEXT                  = 1217,
+   SVGA_3D_CMD_DX_BIND_ALL_SHADER                         = 1217,
    SVGA_3D_CMD_DX_HINT                                    = 1218,
    SVGA_3D_CMD_DX_BUFFER_UPDATE                           = 1219,
    SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET           = 1220,
@@ -262,17 +262,47 @@ typedef enum {
    SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET           = 1222,
 
    /*
-    * Reserve some IDs to be used for the DX11 shader types.
+    * Reserve some IDs to be used for the SM5 shader types.
     */
    SVGA_3D_CMD_DX_RESERVED1                               = 1223,
    SVGA_3D_CMD_DX_RESERVED2                               = 1224,
    SVGA_3D_CMD_DX_RESERVED3                               = 1225,
 
-   SVGA_3D_CMD_DX_MAX                                     = 1226,
-   SVGA_3D_CMD_MAX                                        = 1226,
+   SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER                    = 1226,
+   SVGA_3D_CMD_DX_MAX                                     = 1227,
+
+   SVGA_3D_CMD_SCREEN_COPY                                = 1227,
+
+   /*
+    * Reserve some IDs to be used for video.
+    */
+   SVGA_3D_CMD_VIDEO_RESERVED1                            = 1228,
+   SVGA_3D_CMD_VIDEO_RESERVED2                            = 1229,
+   SVGA_3D_CMD_VIDEO_RESERVED3                            = 1230,
+   SVGA_3D_CMD_VIDEO_RESERVED4                            = 1231,
+   SVGA_3D_CMD_VIDEO_RESERVED5                            = 1232,
+   SVGA_3D_CMD_VIDEO_RESERVED6                            = 1233,
+   SVGA_3D_CMD_VIDEO_RESERVED7                            = 1234,
+   SVGA_3D_CMD_VIDEO_RESERVED8                            = 1235,
+
+   SVGA_3D_CMD_GROW_OTABLE                                = 1236,
+   SVGA_3D_CMD_DX_GROW_COTABLE                            = 1237,
+   SVGA_3D_CMD_INTRA_SURFACE_COPY                         = 1238,
+
+   SVGA_3D_CMD_DEFINE_GB_SURFACE_V3                       = 1239,
+
+   SVGA_3D_CMD_DX_RESOLVE_COPY                            = 1240,
+   SVGA_3D_CMD_DX_PRED_RESOLVE_COPY                       = 1241,
+   SVGA_3D_CMD_DX_PRED_CONVERT_REGION                     = 1242,
+   SVGA_3D_CMD_DX_PRED_CONVERT                            = 1243,
+   SVGA_3D_CMD_WHOLE_SURFACE_COPY                         = 1244,
+
+   SVGA_3D_CMD_MAX                                        = 1245,
    SVGA_3D_CMD_FUTURE_MAX                                 = 3000
 } SVGAFifo3dCmdId;
 
+#define SVGA_NUM_3D_CMD (SVGA_3D_CMD_MAX - SVGA_3D_CMD_BASE)
+
 /*
  * FIFO command format definitions:
  */
@@ -301,7 +331,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    uint32                      sid;
-   SVGA3dSurfaceFlags          surfaceFlags;
+   SVGA3dSurface1Flags         surfaceFlags;
    SVGA3dSurfaceFormat         format;
    /*
     * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
@@ -327,7 +357,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    uint32                      sid;
-   SVGA3dSurfaceFlags          surfaceFlags;
+   SVGA3dSurface1Flags         surfaceFlags;
    SVGA3dSurfaceFormat         format;
    /*
     * If surfaceFlags has SVGA3D_SURFACE_CUBEMAP bit set, all SVGA3dSurfaceFace
@@ -459,6 +489,28 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdSurfaceCopy;               /* SVGA_3D_CMD_SURFACE_COPY */
 
+/*
+ * Perform a surface copy within the same image.
+ * The src/dest boxes are allowed to overlap.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceImageId  surface;
+   SVGA3dCopyBox box;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdIntraSurfaceCopy;               /* SVGA_3D_CMD_INTRA_SURFACE_COPY */
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 srcSid;
+   uint32 destSid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdWholeSurfaceCopy;               /* SVGA_3D_CMD_WHOLE_SURFACE_COPY */
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -772,6 +824,17 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dVertexElement;
 
+/*
+ * Should the vertex element respect the stream value?  The high bit of the
+ * stream should be set to indicate that the stream should be respected.  If
+ * the high bit is not set, the stream will be ignored and replaced by the index
+ * of the position of the currently considered vertex element.
+ *
+ * All guests should set this bit and correctly specify the stream going
+ * forward.
+ */
+#define SVGA3D_VERTEX_ELEMENT_RESPECT_STREAM (1 << 7)
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1102,8 +1165,6 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdGenerateMipmaps;             /* SVGA_3D_CMD_GENERATE_MIPMAPS */
 
-
-
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1146,38 +1207,6 @@ struct SVGA3dCmdScreenDMA {
 #include "vmware_pack_end.h"
 SVGA3dCmdScreenDMA;        /* SVGA_3D_CMD_SCREEN_DMA */
 
-/*
- * Set Unity Surface Cookie
- *
- * Associates the supplied cookie with the surface id for use with
- * Unity.  This cookie is a hint from guest to host, there is no way
- * for the guest to readback the cookie and the host is free to drop
- * the cookie association at will.  The default value for the cookie
- * on all surfaces is 0.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdSetUnitySurfaceCookie {
-   uint32 sid;
-   uint64 cookie;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdSetUnitySurfaceCookie;   /* SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE */
-
-/*
- * Open a context-specific surface in a non-context-specific manner.
- */
-
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdOpenContextSurface {
-   uint32 sid;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdOpenContextSurface;   /* SVGA_3D_CMD_OPEN_CONTEXT_SURFACE */
-
-
 /*
  * Logic ops
  */
@@ -1324,7 +1353,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct {
    SVGA3dSurfaceFormat format;
-   SVGA3dSurfaceFlags surfaceFlags;
+   SVGA3dSurface1Flags surface1Flags;
    uint32 numMipLevels;
    uint32 multisampleCount;
    SVGA3dTextureFilter autogenFilter;
@@ -1332,7 +1361,11 @@ struct {
    SVGAMobId mobid;
    uint32 arraySize;
    uint32 mobPitch;
-   uint32 pad[5];
+   SVGA3dSurface2Flags surface2Flags;
+   uint8 multisamplePattern;
+   uint8 qualityLevel;
+   uint8  pad0[2];
+   uint32 pad1[3];
 }
 #include "vmware_pack_end.h"
 SVGAOTableSurfaceEntry;
@@ -1360,7 +1393,8 @@ struct {
 SVGAOTableShaderEntry;
 #define SVGA3D_OTABLE_SHADER_ENTRY_SIZE (sizeof(SVGAOTableShaderEntry))
 
-#define SVGA_STFLAG_PRIMARY (1 << 0)
+#define SVGA_STFLAG_PRIMARY  (1 << 0)
+#define SVGA_STFLAG_RESERVED (1 << 1) /* Added with cap SVGA_CAP_HP_CMD_QUEUE */
 typedef uint32 SVGAScreenTargetFlags;
 
 typedef
@@ -1528,6 +1562,25 @@ struct {
 #include "vmware_pack_end.h"
 SVGA3dCmdSetOTableBase64;  /* SVGA_3D_CMD_SET_OTABLE_BASE64 */
 
+/*
+ * Guests using SVGA_3D_CMD_GROW_OTABLE are promising that
+ * the new OTable contains the same contents as the old one, except possibly
+ * for some new invalid entries at the end.
+ *
+ * (Otherwise, guests should use one of the SetOTableBase commands.)
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGAOTableType type;
+   PPN64 baseAddress;
+   uint32 sizeInBytes;
+   uint32 validSizeInBytes;
+   SVGAMobFormat ptDepth;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdGrowOTable;  /* SVGA_3D_CMD_GROW_OTABLE */
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1615,7 +1668,7 @@ typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDefineGBSurface {
    uint32 sid;
-   SVGA3dSurfaceFlags surfaceFlags;
+   SVGA3dSurface1Flags surfaceFlags;
    SVGA3dSurfaceFormat format;
    uint32 numMipLevels;
    uint32 multisampleCount;
@@ -1625,6 +1678,45 @@ struct SVGA3dCmdDefineGBSurface {
 #include "vmware_pack_end.h"
 SVGA3dCmdDefineGBSurface;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE */
 
+/*
+ * Defines a guest-backed surface, adding the arraySize field.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDefineGBSurface_v2 {
+   uint32 sid;
+   SVGA3dSurface1Flags surfaceFlags;
+   SVGA3dSurfaceFormat format;
+   uint32 numMipLevels;
+   uint32 multisampleCount;
+   SVGA3dTextureFilter autogenFilter;
+   SVGA3dSize size;
+   uint32 arraySize;
+   uint32 pad;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDefineGBSurface_v2;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */
+
+/*
+ * Defines a guest-backed surface, adding the larger flags.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDefineGBSurface_v3 {
+   uint32 sid;
+   SVGA3dSurfaceAllFlags surfaceFlags;
+   SVGA3dSurfaceFormat format;
+   uint32 numMipLevels;
+   uint32 multisampleCount;
+   SVGA3dMSPattern multisamplePattern;
+   SVGA3dMSQualityLevel qualityLevel;
+   SVGA3dTextureFilter autogenFilter;
+   SVGA3dSize size;
+   uint32 arraySize;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDefineGBSurface_v3;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V3 */
+
 /*
  * Destroy a guest-backed surface.
  */
@@ -1672,7 +1764,7 @@ SVGA3dCmdBindGBSurfaceWithPitch;   /* SVGA_3D_CMD_BIND_GB_SURFACE_WITH_PITCH */
 
 typedef
 #include "vmware_pack_begin.h"
-struct{
+struct SVGA3dCmdCondBindGBSurface {
    uint32 sid;
    SVGAMobId testMobid;
    SVGAMobId mobid;
@@ -2066,6 +2158,26 @@ struct {
    uint32 mobOffset;
 }
 #include "vmware_pack_end.h"
-SVGA3dCmdGBMobFence;  /* SVGA_3D_CMD_GB_MOB_FENCE*/
+SVGA3dCmdGBMobFence;  /* SVGA_3D_CMD_GB_MOB_FENCE */
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 stid;
+   SVGA3dSurfaceImageId dest;
+
+   uint32 statusMobId;
+   uint32 statusMobOffset;
+
+   /* Reserved fields */
+   uint32 mustBeInvalidId;
+   uint32 mustBeZero;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdScreenCopy;  /* SVGA_3D_CMD_SCREEN_COPY */
+
+#define SVGA_SCREEN_COPY_STATUS_FAILURE 0x00
+#define SVGA_SCREEN_COPY_STATUS_SUCCESS 0x01
+#define SVGA_SCREEN_COPY_STATUS_INVALID 0xFFFFFFFF
 
 #endif /* _SVGA3D_CMD_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
index c18b663f360f..e545013e65d6 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_devcaps.h
@@ -229,9 +229,9 @@ typedef enum {
    SVGA3D_DEVCAP_DEAD2                             = 94,
 
    /*
-    * Does the device support the DX commands?
+    * Does the device support DXContexts?
     */
-   SVGA3D_DEVCAP_DX                                = 95,
+   SVGA3D_DEVCAP_DXCONTEXT                         = 95,
 
    /*
     * What is the maximum size of a texture array?
@@ -241,21 +241,47 @@ typedef enum {
    SVGA3D_DEVCAP_MAX_TEXTURE_ARRAY_SIZE            = 96,
 
    /*
-    * What is the maximum number of vertex buffers that can
-    * be used in the DXContext inputAssembly?
+    * What is the maximum number of vertex buffers or vertex input registers
+    * that can be expected to work correctly with a DXContext?
+    *
+    * The guest is allowed to set up to SVGA3D_DX_MAX_VERTEXBUFFERS, but
+    * anything in excess of this cap is not guaranteed to render correctly.
+    *
+    * Similarly, the guest can set up to SVGA3D_DX_MAX_VERTEXINPUTREGISTERS
+    * input registers without the SVGA3D_DEVCAP_SM4_1 cap, or
+    * SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS with the SVGA3D_DEVCAP_SM4_1,
+    * but only the registers up to this cap value are guaranteed to render
+    * correctly.
+    *
+    * If guest-drivers are able to expose a lower-limit, it's recommended
+    * that they clamp to this value.  Otherwise, the host will make a
+    * best-effort on case-by-case basis if guests exceed this.
     */
    SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS              = 97,
 
    /*
-    * What is the maximum number of constant buffers
-    * that can be expected to work correctly with a
-    * DX context?
+    * What is the maximum number of constant buffers that can be expected to
+    * work correctly with a DX context?
+    *
+    * The guest is allowed to set up to SVGA3D_DX_MAX_CONSTBUFFERS, but
+    * anything in excess of this cap is not guaranteed to render correctly.
+    *
+    * If guest-drivers are able to expose a lower-limit, it's recommended
+    * that they clamp to this value.  Otherwise, the host will make a
+    * best-effort on case-by-case basis if guests exceed this.
     */
    SVGA3D_DEVCAP_DX_MAX_CONSTANT_BUFFERS           = 98,
 
    /*
     * Does the device support provoking vertex control?
-    * If zero, the first vertex will always be the provoking vertex.
+    *
+    * If this cap is present, the provokingVertexLast field in the
+    * rasterizer state is enabled.  (Guests can then set it to FALSE,
+    * meaning that the first vertex is the provoking vertex, or TRUE,
+    * meaning that the last verteix is the provoking vertex.)
+    *
+    * If this cap is FALSE, then guests should set the provokingVertexLast
+    * to FALSE, otherwise rendering behavior is undefined.
     */
    SVGA3D_DEVCAP_DX_PROVOKING_VERTEX               = 99,
 
@@ -281,7 +307,7 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_BUMPU8V8                    = 119,
    SVGA3D_DEVCAP_DXFMT_BUMPL6V5U5                  = 120,
    SVGA3D_DEVCAP_DXFMT_BUMPX8L8V8U8                = 121,
-   SVGA3D_DEVCAP_DXFMT_BUMPL8V8U8                  = 122,
+   SVGA3D_DEVCAP_DXFMT_FORMAT_DEAD1                = 122,
    SVGA3D_DEVCAP_DXFMT_ARGB_S10E5                  = 123,
    SVGA3D_DEVCAP_DXFMT_ARGB_S23E8                  = 124,
    SVGA3D_DEVCAP_DXFMT_A2R10G10B10                 = 125,
@@ -320,8 +346,8 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_R32G32_SINT                 = 158,
    SVGA3D_DEVCAP_DXFMT_R32G8X24_TYPELESS           = 159,
    SVGA3D_DEVCAP_DXFMT_D32_FLOAT_S8X24_UINT        = 160,
-   SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24_TYPELESS    = 161,
-   SVGA3D_DEVCAP_DXFMT_X32_TYPELESS_G8X24_UINT     = 162,
+   SVGA3D_DEVCAP_DXFMT_R32_FLOAT_X8X24             = 161,
+   SVGA3D_DEVCAP_DXFMT_X32_G8X24_UINT              = 162,
    SVGA3D_DEVCAP_DXFMT_R10G10B10A2_TYPELESS        = 163,
    SVGA3D_DEVCAP_DXFMT_R10G10B10A2_UINT            = 164,
    SVGA3D_DEVCAP_DXFMT_R11G11B10_FLOAT             = 165,
@@ -339,8 +365,8 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_R32_SINT                    = 177,
    SVGA3D_DEVCAP_DXFMT_R24G8_TYPELESS              = 178,
    SVGA3D_DEVCAP_DXFMT_D24_UNORM_S8_UINT           = 179,
-   SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8_TYPELESS       = 180,
-   SVGA3D_DEVCAP_DXFMT_X24_TYPELESS_G8_UINT        = 181,
+   SVGA3D_DEVCAP_DXFMT_R24_UNORM_X8                = 180,
+   SVGA3D_DEVCAP_DXFMT_X24_G8_UINT                 = 181,
    SVGA3D_DEVCAP_DXFMT_R8G8_TYPELESS               = 182,
    SVGA3D_DEVCAP_DXFMT_R8G8_UNORM                  = 183,
    SVGA3D_DEVCAP_DXFMT_R8G8_UINT                   = 184,
@@ -404,6 +430,17 @@ typedef enum {
    SVGA3D_DEVCAP_DXFMT_BC4_UNORM                   = 242,
    SVGA3D_DEVCAP_DXFMT_BC5_UNORM                   = 243,
 
+   /*
+    * Advertises shaderModel 4.1 support, independent blend-states,
+    * cube-map arrays, and a higher vertex input registers limit.
+    *
+    * (See documentation on SVGA3D_DEVCAP_DX_MAX_VERTEXBUFFERS.)
+    */
+   SVGA3D_DEVCAP_SM41                              = 244,
+
+   SVGA3D_DEVCAP_MULTISAMPLE_2X                    = 245,
+   SVGA3D_DEVCAP_MULTISAMPLE_4X                    = 246,
+
    SVGA3D_DEVCAP_MAX                       /* This must be the last index. */
 } SVGA3dDevCapIndex;
 
@@ -419,9 +456,7 @@ typedef enum {
  * MIPS: Does the format support mip levels?
  * ARRAY: Does the format support texture arrays?
  * VOLUME: Does the format support having volume?
- * MULTISAMPLE_2: Does the format support 2x multisample?
- * MULTISAMPLE_4: Does the format support 4x multisample?
- * MULTISAMPLE_8: Does the format support 8x multisample?
+ * MULTISAMPLE: Does the format support multisample?
  */
 #define SVGA3D_DXFMT_SUPPORTED                (1 <<  0)
 #define SVGA3D_DXFMT_SHADER_SAMPLE            (1 <<  1)
@@ -432,20 +467,8 @@ typedef enum {
 #define SVGA3D_DXFMT_ARRAY                    (1 <<  6)
 #define SVGA3D_DXFMT_VOLUME                   (1 <<  7)
 #define SVGA3D_DXFMT_DX_VERTEX_BUFFER         (1 <<  8)
-#define SVGADX_DXFMT_MULTISAMPLE_2            (1 <<  9)
-#define SVGADX_DXFMT_MULTISAMPLE_4            (1 << 10)
-#define SVGADX_DXFMT_MULTISAMPLE_8            (1 << 11)
-#define SVGADX_DXFMT_MAX                      (1 << 12)
-
-/*
- * Convenience mask for any multisample capability.
- *
- * The multisample bits imply both load and render capability.
- */
-#define SVGA3D_DXFMT_MULTISAMPLE ( \
-           SVGADX_DXFMT_MULTISAMPLE_2 | \
-           SVGADX_DXFMT_MULTISAMPLE_4 | \
-           SVGADX_DXFMT_MULTISAMPLE_8 )
+#define SVGA3D_DXFMT_MULTISAMPLE              (1 <<  9)
+#define SVGA3D_DXFMT_MAX                      (1 << 10)
 
 typedef union {
    Bool   b;
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
index 8c5ae608cfb4..a5d3b6a686af 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_dx.h
@@ -56,6 +56,16 @@ typedef uint32 SVGA3dInputClassification;
 #define SVGA3D_RESOURCE_TYPE_MAX      7
 typedef uint32 SVGA3dResourceType;
 
+#define SVGA3D_COLOR_WRITE_ENABLE_RED     (1 << 0)
+#define SVGA3D_COLOR_WRITE_ENABLE_GREEN   (1 << 1)
+#define SVGA3D_COLOR_WRITE_ENABLE_BLUE    (1 << 2)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALPHA   (1 << 3)
+#define SVGA3D_COLOR_WRITE_ENABLE_ALL     (SVGA3D_COLOR_WRITE_ENABLE_RED |   \
+                                           SVGA3D_COLOR_WRITE_ENABLE_GREEN | \
+                                           SVGA3D_COLOR_WRITE_ENABLE_BLUE |  \
+                                           SVGA3D_COLOR_WRITE_ENABLE_ALPHA)
+typedef uint8 SVGA3dColorWriteEnable;
+
 #define SVGA3D_DEPTH_WRITE_MASK_ZERO   0
 #define SVGA3D_DEPTH_WRITE_MASK_ALL    1
 typedef uint8 SVGA3dDepthWriteMask;
@@ -88,17 +98,28 @@ typedef uint8 SVGA3dCullMode;
 #define SVGA3D_COMPARISON_MAX             9
 typedef uint8 SVGA3dComparisonFunc;
 
+/*
+ * SVGA3D_MULTISAMPLE_RAST_DISABLE disables MSAA for all primitives.
+ * SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE, which is supported in SM41,
+ * disables MSAA for lines only.
+ */
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE        0
+#define SVGA3D_MULTISAMPLE_RAST_ENABLE         1
+#define SVGA3D_MULTISAMPLE_RAST_DX_MAX         1
+#define SVGA3D_MULTISAMPLE_RAST_DISABLE_LINE   2
+#define SVGA3D_MULTISAMPLE_RAST_MAX            2
+typedef uint8 SVGA3dMultisampleRastEnable;
+
 #define SVGA3D_DX_MAX_VERTEXBUFFERS 32
+#define SVGA3D_DX_MAX_VERTEXINPUTREGISTERS 16
+#define SVGA3D_DX_SM41_MAX_VERTEXINPUTREGISTERS 32
 #define SVGA3D_DX_MAX_SOTARGETS 4
 #define SVGA3D_DX_MAX_SRVIEWS 128
 #define SVGA3D_DX_MAX_CONSTBUFFERS 16
 #define SVGA3D_DX_MAX_SAMPLERS 16
 
-/* Id limits */
-static const uint32 SVGA3dBlendObjectCountPerContext = 4096;
-static const uint32 SVGA3dDepthStencilObjectCountPerContext = 4096;
+#define SVGA3D_DX_MAX_CONSTBUF_BINDING_SIZE (4096 * 4 * (uint32)sizeof(uint32))
 
-typedef uint32 SVGA3dSurfaceId;
 typedef uint32 SVGA3dShaderResourceViewId;
 typedef uint32 SVGA3dRenderTargetViewId;
 typedef uint32 SVGA3dDepthStencilViewId;
@@ -192,20 +213,6 @@ struct SVGA3dCmdDXInvalidateContext {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXInvalidateContext;   /* SVGA_3D_CMD_DX_INVALIDATE_CONTEXT */
 
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dReplyFormatData {
-   uint32 formatSupport;
-   uint32 msaa2xQualityLevels:5;
-   uint32 msaa4xQualityLevels:5;
-   uint32 msaa8xQualityLevels:5;
-   uint32 msaa16xQualityLevels:5;
-   uint32 msaa32xQualityLevels:5;
-   uint32 pad:7;
-}
-#include "vmware_pack_end.h"
-SVGA3dReplyFormatData;
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXSetSingleConstantBuffer {
@@ -622,6 +629,28 @@ struct SVGA3dCmdDXPredCopy {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXPredCopy; /* SVGA_3D_CMD_DX_PRED_COPY */
 
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXPredConvertRegion {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dBox destBox;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dBox srcBox;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredConvertRegion; /* SVGA_3D_CMD_DX_PRED_CONVERT_REGION */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXPredConvert {
+   SVGA3dSurfaceId dstSid;
+   SVGA3dSurfaceId srcSid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredConvert; /* SVGA_3D_CMD_DX_PRED_CONVERT */
+
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXBufferCopy {
@@ -635,23 +664,57 @@ struct SVGA3dCmdDXBufferCopy {
 SVGA3dCmdDXBufferCopy;
 /* SVGA_3D_CMD_DX_BUFFER_COPY */
 
-typedef uint32 SVGA3dDXStretchBltMode;
-#define SVGADX_STRETCHBLT_LINEAR         (1 << 0)
-#define SVGADX_STRETCHBLT_FORCE_SRC_SRGB (1 << 1)
+/*
+ * Perform a surface copy between a multisample, and a non-multisampled
+ * surface.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dSurfaceFormat copyFormat;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXResolveCopy;               /* SVGA_3D_CMD_DX_RESOLVE_COPY */
+
+/*
+ * Perform a predicated surface copy between a multisample, and a
+ * non-multisampled surface.
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   SVGA3dSurfaceId dstSid;
+   uint32 dstSubResource;
+   SVGA3dSurfaceId srcSid;
+   uint32 srcSubResource;
+   SVGA3dSurfaceFormat copyFormat;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXPredResolveCopy;           /* SVGA_3D_CMD_DX_PRED_RESOLVE_COPY */
+
+typedef uint32 SVGA3dDXPresentBltMode;
+#define SVGADX_PRESENTBLT_LINEAR           (1 << 0)
+#define SVGADX_PRESENTBLT_FORCE_SRC_SRGB   (1 << 1)
+#define SVGADX_PRESENTBLT_FORCE_SRC_XRBIAS (1 << 2)
+#define SVGADX_PRESENTBLT_MODE_MAX         (1 << 3)
 
 typedef
 #include "vmware_pack_begin.h"
-struct SVGA3dCmdDXStretchBlt {
+struct SVGA3dCmdDXPresentBlt {
    SVGA3dSurfaceId srcSid;
    uint32 srcSubResource;
    SVGA3dSurfaceId dstSid;
    uint32 destSubResource;
    SVGA3dBox boxSrc;
    SVGA3dBox boxDest;
-   SVGA3dDXStretchBltMode mode;
+   SVGA3dDXPresentBltMode mode;
 }
 #include "vmware_pack_end.h"
-SVGA3dCmdDXStretchBlt; /* SVGA_3D_CMD_DX_STRETCHBLT */
+SVGA3dCmdDXPresentBlt; /* SVGA_3D_CMD_DX_PRESENTBLT*/
 
 typedef
 #include "vmware_pack_begin.h"
@@ -661,26 +724,6 @@ struct SVGA3dCmdDXGenMips {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXGenMips; /* SVGA_3D_CMD_DX_GENMIPS */
 
-/*
- * Defines a resource/DX surface.  Resources share the surfaceId namespace.
- *
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dCmdDefineGBSurface_v2 {
-   uint32 sid;
-   SVGA3dSurfaceFlags surfaceFlags;
-   SVGA3dSurfaceFormat format;
-   uint32 numMipLevels;
-   uint32 multisampleCount;
-   SVGA3dTextureFilter autogenFilter;
-   SVGA3dSize size;
-   uint32 arraySize;
-   uint32 pad;
-}
-#include "vmware_pack_end.h"
-SVGA3dCmdDefineGBSurface_v2;   /* SVGA_3D_CMD_DEFINE_GB_SURFACE_V2 */
-
 /*
  * Update a sub-resource in a guest-backed resource.
  * (Inform the device that the guest-contents have been updated.)
@@ -724,7 +767,8 @@ SVGA3dCmdDXInvalidateSubResource;   /* SVGA_3D_CMD_DX_INVALIDATE_SUBRESOURCE */
 
 /*
  * Raw byte wise transfer from a buffer surface into another surface
- * of the requested box.
+ * of the requested box.  Supported if 3d is enabled and SVGA_CAP_DX
+ * is set.  This command does not take a context.
  */
 typedef
 #include "vmware_pack_begin.h"
@@ -773,6 +817,93 @@ struct SVGA3dCmdDXSurfaceCopyAndReadback {
 SVGA3dCmdDXSurfaceCopyAndReadback;
 /* SVGA_3D_CMD_DX_SURFACE_COPY_AND_READBACK */
 
+/*
+ * SVGA_DX_HINT_NONE: Does nothing.
+ *
+ * SVGA_DX_HINT_PREFETCH_OBJECT:
+ * SVGA_DX_HINT_PREEVICT_OBJECT:
+ *      Consumes a SVGAObjectRef, and hints that the host should consider
+ *      fetching/evicting the specified object.
+ *
+ *      An id of SVGA3D_INVALID_ID can be used if the guest isn't sure
+ *      what object was affected.  (For instance, if the guest knows that
+ *      it is about to evict a DXShader, but doesn't know precisely which one,
+ *      the device can still use this to help limit it's search, or track
+ *      how many page-outs have happened.)
+ *
+ * SVGA_DX_HINT_PREFETCH_COBJECT:
+ * SVGA_DX_HINT_PREEVICT_COBJECT:
+ *      Same as the above, except they consume an SVGACObjectRef.
+ */
+typedef uint32 SVGADXHintId;
+#define SVGA_DX_HINT_NONE              0
+#define SVGA_DX_HINT_PREFETCH_OBJECT   1
+#define SVGA_DX_HINT_PREEVICT_OBJECT   2
+#define SVGA_DX_HINT_PREFETCH_COBJECT  3
+#define SVGA_DX_HINT_PREEVICT_COBJECT  4
+#define SVGA_DX_HINT_MAX               5
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGAObjectRef {
+   SVGAOTableType type;
+   uint32 id;
+}
+#include "vmware_pack_end.h"
+SVGAObjectRef;
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGACObjectRef {
+   SVGACOTableType type;
+   uint32 cid;
+   uint32 id;
+}
+#include "vmware_pack_end.h"
+SVGACObjectRef;
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXHint {
+   SVGADXHintId hintId;
+
+   /*
+    * Followed by variable sized data depending on the hintId.
+    */
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXHint;
+/* SVGA_3D_CMD_DX_HINT */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXBufferUpdate {
+   SVGA3dSurfaceId sid;
+   uint32 x;
+   uint32 width;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXBufferUpdate;
+/* SVGA_3D_CMD_DX_BUFFER_UPDATE */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXSetConstantBufferOffset {
+   uint32 slot;
+   uint32 offsetInBytes;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXSetConstantBufferOffset;
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetVSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_VS_CONSTANT_BUFFER_OFFSET */
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetPSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_PS_CONSTANT_BUFFER_OFFSET */
+
+typedef SVGA3dCmdDXSetConstantBufferOffset SVGA3dCmdDXSetGSConstantBufferOffset;
+/* SVGA_3D_CMD_DX_SET_GS_CONSTANT_BUFFER_OFFSET */
+
 
 typedef
 #include "vmware_pack_begin.h"
@@ -789,7 +920,7 @@ struct {
          uint32 firstArraySlice;
          uint32 mipLevels;
          uint32 arraySize;
-      } tex;
+      } tex; /* 1d, 2d, 3d, cube */
       struct {
          uint32 firstElement;
          uint32 numElements;
@@ -844,6 +975,7 @@ struct SVGA3dRenderTargetViewDesc {
       struct {
          uint32 firstElement;
          uint32 numElements;
+         uint32 padding0;
       } buffer;
       struct {
          uint32 mipSlice;
@@ -964,9 +1096,6 @@ SVGA3dInputElementDesc;
 typedef
 #include "vmware_pack_begin.h"
 struct {
-   /*
-    * XXX: How many of these can there be?
-    */
    uint32 elid;
    uint32 numDescs;
    SVGA3dInputElementDesc desc[32];
@@ -1007,7 +1136,7 @@ struct SVGA3dDXBlendStatePerRT {
       uint8 srcBlendAlpha;
       uint8 destBlendAlpha;
       uint8 blendOpAlpha;
-      uint8 renderTargetWriteMask;
+      SVGA3dColorWriteEnable renderTargetWriteMask;
       uint8 logicOpEnable;
       uint8 logicOp;
       uint16 pad0;
@@ -1125,7 +1254,7 @@ struct {
    float slopeScaledDepthBias;
    uint8 depthClipEnable;
    uint8 scissorEnable;
-   uint8 multisampleEnable;
+   SVGA3dMultisampleRastEnable multisampleEnable;
    uint8 antialiasedLineEnable;
    float lineWidth;
    uint8 lineStippleEnable;
@@ -1152,7 +1281,7 @@ struct SVGA3dCmdDXDefineRasterizerState {
    float slopeScaledDepthBias;
    uint8 depthClipEnable;
    uint8 scissorEnable;
-   uint8 multisampleEnable;
+   SVGA3dMultisampleRastEnable multisampleEnable;
    uint8 antialiasedLineEnable;
    float lineWidth;
    uint8 lineStippleEnable;
@@ -1222,21 +1351,6 @@ struct SVGA3dCmdDXDestroySamplerState {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXDestroySamplerState; /* SVGA_3D_CMD_DX_DESTROY_SAMPLER_STATE */
 
-/*
- */
-typedef
-#include "vmware_pack_begin.h"
-struct SVGA3dSignatureEntry {
-   uint8 systemValue;
-   uint8 reg;                 /* register is a reserved word */
-   uint16 mask;
-   uint8 registerComponentType;
-   uint8 minPrecision;
-   uint16 pad0;
-}
-#include "vmware_pack_end.h"
-SVGA3dSignatureEntry;
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXDefineShader {
@@ -1254,12 +1368,7 @@ struct SVGACOTableDXShaderEntry {
    uint32 sizeInBytes;
    uint32 offsetInBytes;
    SVGAMobId mobid;
-   uint32 numInputSignatureEntries;
-   uint32 numOutputSignatureEntries;
-
-   uint32 numPatchConstantSignatureEntries;
-
-   uint32 pad;
+   uint32 pad[4];
 }
 #include "vmware_pack_end.h"
 SVGACOTableDXShaderEntry;
@@ -1283,6 +1392,25 @@ struct SVGA3dCmdDXBindShader {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXBindShader;   /* SVGA_3D_CMD_DX_BIND_SHADER */
 
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXBindAllShader {
+   uint32 cid;
+   SVGAMobId mobid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXBindAllShader;   /* SVGA_3D_CMD_DX_BIND_ALL_SHADER */
+
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXCondBindAllShader {
+   uint32 cid;
+   SVGAMobId testMobid;
+   SVGAMobId mobid;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXCondBindAllShader;   /* SVGA_3D_CMD_DX_COND_BIND_ALL_SHADER */
+
 /*
  * The maximum number of streamout decl's in each streamout entry.
  */
@@ -1356,7 +1484,6 @@ SVGA3dCmdDXMobFence64;  /* SVGA_3D_CMD_DX_MOB_FENCE_64 */
  *
  * This command allows the guest to bind a mob to a context-object table.
  */
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXSetCOTable {
@@ -1368,6 +1495,26 @@ struct SVGA3dCmdDXSetCOTable {
 #include "vmware_pack_end.h"
 SVGA3dCmdDXSetCOTable; /* SVGA_3D_CMD_DX_SET_COTABLE */
 
+/*
+ * Guests using SVGA_3D_CMD_DX_GROW_COTABLE are promising that
+ * the new COTable contains the same contents as the old one, except possibly
+ * for some new invalid entries at the end.
+ *
+ * If there is an old cotable mob bound, it also has to still be valid.
+ *
+ * (Otherwise, guests should use the DXSetCOTableBase command.)
+ */
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dCmdDXGrowCOTable {
+   uint32 cid;
+   uint32 mobid;
+   SVGACOTableType type;
+   uint32 validSizeInBytes;
+}
+#include "vmware_pack_end.h"
+SVGA3dCmdDXGrowCOTable; /* SVGA_3D_CMD_DX_GROW_COTABLE */
+
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCmdDXReadbackCOTable {
@@ -1471,7 +1618,7 @@ struct SVGADXContextMobFormat {
    SVGA3dQueryId queryID[SVGA3D_MAX_QUERY];
 
    SVGA3dCOTableData cotables[SVGA_COTABLE_MAX];
-   uint32 pad7[381];
+   uint32 pad7[380];
 }
 #include "vmware_pack_end.h"
 SVGADXContextMobFormat;
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
index a1c36877ad55..2d462ab7cccf 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_limits.h
@@ -62,7 +62,9 @@
  * Maximum size in dwords of shader text the SVGA device will allow.
  * Currently 8 MB.
  */
-#define SVGA3D_MAX_SHADER_MEMORY  (8 * 1024 * 1024 / sizeof(uint32))
+#define SVGA3D_MAX_SHADER_MEMORY_BYTES (8 * 1024 * 1024)
+#define SVGA3D_MAX_SHADER_MEMORY  (SVGA3D_MAX_SHADER_MEMORY_BYTES / \
+                                   sizeof(uint32))
 
 #define SVGA3D_MAX_CLIP_PLANES    6
 
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
index babe7cb84fc2..6422e3899cdf 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
@@ -25,189 +25,355 @@
  *
  **************************************************************************/
 
-#include <linux/kernel.h>
-
-#ifdef __KERNEL__
-
-#include <drm/vmwgfx_drm.h>
-#define surf_size_struct struct drm_vmw_size
-
-#else /* __KERNEL__ */
+/*
+ * svga3d_surfacedefs.h --
+ *
+ *      Surface definitions and inlineable utilities for SVGA3d.
+ */
 
-#ifndef ARRAY_SIZE
-#define ARRAY_SIZE(_A) (sizeof(_A) / sizeof((_A)[0]))
-#endif /* ARRAY_SIZE */
+#ifndef _SVGA3D_SURFACEDEFS_H_
+#define _SVGA3D_SURFACEDEFS_H_
 
-#define max_t(type, x, y)  ((x) > (y) ? (x) : (y))
-#define surf_size_struct SVGA3dSize
-#define u32 uint32
+#define INCLUDE_ALLOW_USERLEVEL
+#define INCLUDE_ALLOW_MODULE
+#include "includeCheck.h"
 
-#endif /* __KERNEL__ */
+#include <linux/kernel.h>
+#include <drm/vmwgfx_drm.h>
 
 #include "svga3d_reg.h"
 
+#define surf_size_struct struct drm_vmw_size
+
 /*
- * enum svga3d_block_desc describes the active data channels in a block.
- *
- * There can be at-most four active channels in a block:
- *    1. Red, bump W, luminance and depth are stored in the first channel.
- *    2. Green, bump V and stencil are stored in the second channel.
- *    3. Blue and bump U are stored in the third channel.
- *    4. Alpha and bump Q are stored in the fourth channel.
- *
- * Block channels can be used to store compressed and buffer data:
- *    1. For compressed formats, only the data channel is used and its size
- *       is equal to that of a singular block in the compression scheme.
- *    2. For buffer formats, only the data channel is used and its size is
- *       exactly one byte in length.
- *    3. In each case the bit depth represent the size of a singular block.
- *
- * Note: Compressed and IEEE formats do not use the bitMask structure.
+ * enum svga3d_block_desc - describes generic properties about formats.
  */
-
 enum svga3d_block_desc {
-	SVGA3DBLOCKDESC_NONE        = 0,         /* No channels are active */
-	SVGA3DBLOCKDESC_BLUE        = 1 << 0,    /* Block with red channel
-						    data */
-	SVGA3DBLOCKDESC_U           = 1 << 0,    /* Block with bump U channel
-						    data */
-	SVGA3DBLOCKDESC_UV_VIDEO    = 1 << 7,    /* Block with alternating video
-						    U and V */
-	SVGA3DBLOCKDESC_GREEN       = 1 << 1,    /* Block with green channel
-						    data */
-	SVGA3DBLOCKDESC_V           = 1 << 1,    /* Block with bump V channel
-						    data */
-	SVGA3DBLOCKDESC_STENCIL     = 1 << 1,    /* Block with a stencil
-						    channel */
-	SVGA3DBLOCKDESC_RED         = 1 << 2,    /* Block with blue channel
-						    data */
-	SVGA3DBLOCKDESC_W           = 1 << 2,    /* Block with bump W channel
-						    data */
-	SVGA3DBLOCKDESC_LUMINANCE   = 1 << 2,    /* Block with luminance channel
-						    data */
-	SVGA3DBLOCKDESC_Y           = 1 << 2,    /* Block with video luminance
-						    data */
-	SVGA3DBLOCKDESC_DEPTH       = 1 << 2,    /* Block with depth channel */
-	SVGA3DBLOCKDESC_ALPHA       = 1 << 3,    /* Block with an alpha
-						    channel */
-	SVGA3DBLOCKDESC_Q           = 1 << 3,    /* Block with bump Q channel
-						    data */
-	SVGA3DBLOCKDESC_BUFFER      = 1 << 4,    /* Block stores 1 byte of
-						    data */
-	SVGA3DBLOCKDESC_COMPRESSED  = 1 << 5,    /* Block stores n bytes of
-						    data depending on the
-						    compression method used */
-	SVGA3DBLOCKDESC_IEEE_FP     = 1 << 6,    /* Block stores data in an IEEE
-						    floating point
-						    representation in
-						    all channels */
-	SVGA3DBLOCKDESC_PLANAR_YUV  = 1 << 8,    /* Three separate blocks store
-						    data. */
-	SVGA3DBLOCKDESC_U_VIDEO     = 1 << 9,    /* Block with U video data */
-	SVGA3DBLOCKDESC_V_VIDEO     = 1 << 10,   /* Block with V video data */
-	SVGA3DBLOCKDESC_EXP         = 1 << 11,   /* Shared exponent */
-	SVGA3DBLOCKDESC_SRGB        = 1 << 12,   /* Data is in sRGB format */
-	SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 13,   /* 2 planes of Y, UV,
-						    e.g., NV12. */
-	SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 14,   /* 3 planes of separate
-						    Y, U, V, e.g., YV12. */
-
-	SVGA3DBLOCKDESC_RG         = SVGA3DBLOCKDESC_RED |
-	SVGA3DBLOCKDESC_GREEN,
-	SVGA3DBLOCKDESC_RGB        = SVGA3DBLOCKDESC_RG |
-	SVGA3DBLOCKDESC_BLUE,
-	SVGA3DBLOCKDESC_RGB_SRGB   = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_RGBA       = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_ALPHA,
-	SVGA3DBLOCKDESC_RGBA_SRGB  = SVGA3DBLOCKDESC_RGBA |
-	SVGA3DBLOCKDESC_SRGB,
+	/* Nothing special can be said about this format. */
+	SVGA3DBLOCKDESC_NONE        = 0,
+
+	/* Format contains Blue/U data */
+	SVGA3DBLOCKDESC_BLUE        = 1 << 0,
+	SVGA3DBLOCKDESC_W           = 1 << 0,
+	SVGA3DBLOCKDESC_BUMP_L      = 1 << 0,
+
+	/* Format contains Green/V data */
+	SVGA3DBLOCKDESC_GREEN       = 1 << 1,
+	SVGA3DBLOCKDESC_V           = 1 << 1,
+
+	/* Format contains Red/W/Luminance data */
+	SVGA3DBLOCKDESC_RED         = 1 << 2,
+	SVGA3DBLOCKDESC_U           = 1 << 2,
+	SVGA3DBLOCKDESC_LUMINANCE   = 1 << 2,
+
+	/* Format contains Alpha/Q data */
+	SVGA3DBLOCKDESC_ALPHA       = 1 << 3,
+	SVGA3DBLOCKDESC_Q           = 1 << 3,
+
+	/* Format is a buffer */
+	SVGA3DBLOCKDESC_BUFFER      = 1 << 4,
+
+	/* Format is compressed */
+	SVGA3DBLOCKDESC_COMPRESSED  = 1 << 5,
+
+	/* Format uses IEEE floating point */
+	SVGA3DBLOCKDESC_FP          = 1 << 6,
+
+	/* Three separate blocks store data. */
+	SVGA3DBLOCKDESC_PLANAR_YUV  = 1 << 7,
+
+	/* 2 planes of Y, UV, e.g., NV12. */
+	SVGA3DBLOCKDESC_2PLANAR_YUV = 1 << 8,
+
+	/* 3 planes of separate Y, U, V, e.g., YV12. */
+	SVGA3DBLOCKDESC_3PLANAR_YUV = 1 << 9,
+
+	/* Block with a stencil channel */
+	SVGA3DBLOCKDESC_STENCIL     = 1 << 11,
+
+	/* Typeless format */
+	SVGA3DBLOCKDESC_TYPELESS    = 1 << 12,
+
+	/* Channels are signed integers */
+	SVGA3DBLOCKDESC_SINT        = 1 << 13,
+
+	/* Channels are unsigned integers */
+	SVGA3DBLOCKDESC_UINT        = 1 << 14,
+
+	/* Channels are normalized (when sampling) */
+	SVGA3DBLOCKDESC_NORM        = 1 << 15,
+
+	/* Channels are in SRGB */
+	SVGA3DBLOCKDESC_SRGB        = 1 << 16,
+
+	/* Shared exponent */
+	SVGA3DBLOCKDESC_EXP         = 1 << 17,
+
+	/* Format contains color data. */
+	SVGA3DBLOCKDESC_COLOR       = 1 << 18,
+	/* Format contains depth data. */
+	SVGA3DBLOCKDESC_DEPTH       = 1 << 19,
+	/* Format contains bump data. */
+	SVGA3DBLOCKDESC_BUMP        = 1 << 20,
+
+	/* Format contains YUV video data. */
+	SVGA3DBLOCKDESC_YUV_VIDEO   = 1 << 21,
+
+	/* For mixed unsigned/signed formats. */
+	SVGA3DBLOCKDESC_MIXED       = 1 << 22,
+
+	/* For distingushing CxV8U8. */
+	SVGA3DBLOCKDESC_CX          = 1 << 23,
+
+	/* Different compressed format groups. */
+	SVGA3DBLOCKDESC_BC1         = 1 << 24,
+	SVGA3DBLOCKDESC_BC2         = 1 << 25,
+	SVGA3DBLOCKDESC_BC3         = 1 << 26,
+	SVGA3DBLOCKDESC_BC4         = 1 << 27,
+	SVGA3DBLOCKDESC_BC5         = 1 << 28,
+
+	SVGA3DBLOCKDESC_A_UINT    = SVGA3DBLOCKDESC_ALPHA |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_A_UNORM   = SVGA3DBLOCKDESC_A_UINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_UINT    = SVGA3DBLOCKDESC_RED |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_UNORM   = SVGA3DBLOCKDESC_R_UINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_R_SINT    = SVGA3DBLOCKDESC_RED |
+				    SVGA3DBLOCKDESC_SINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_R_SNORM   = SVGA3DBLOCKDESC_R_SINT |
+				    SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_G_UINT    = SVGA3DBLOCKDESC_GREEN |
+				    SVGA3DBLOCKDESC_UINT |
+				    SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UINT    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_UNORM   = SVGA3DBLOCKDESC_RG_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RG_SINT    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RG_SNORM   = SVGA3DBLOCKDESC_RG_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UINT   = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_SINT   = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_UNORM   = SVGA3DBLOCKDESC_RGB_UINT |
+				      SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGB_UNORM_SRGB = SVGA3DBLOCKDESC_RGB_UNORM |
+					 SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_UINT  = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_UNORM = SVGA3DBLOCKDESC_RGBA_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_UNORM_SRGB = SVGA3DBLOCKDESC_RGBA_UNORM |
+					  SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_RGBA_SINT  = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGBA_SNORM = SVGA3DBLOCKDESC_RGBA_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_RGBA_FP    = SVGA3DBLOCKDESC_RED |
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_FP |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_UV         = SVGA3DBLOCKDESC_U |
-	SVGA3DBLOCKDESC_V,
+				     SVGA3DBLOCKDESC_V |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVL        = SVGA3DBLOCKDESC_UV |
-	SVGA3DBLOCKDESC_LUMINANCE,
+				     SVGA3DBLOCKDESC_BUMP_L |
+				     SVGA3DBLOCKDESC_MIXED |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVW        = SVGA3DBLOCKDESC_UV |
-	SVGA3DBLOCKDESC_W,
+				     SVGA3DBLOCKDESC_W |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVWA       = SVGA3DBLOCKDESC_UVW |
-	SVGA3DBLOCKDESC_ALPHA,
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_MIXED |
+				     SVGA3DBLOCKDESC_BUMP,
 	SVGA3DBLOCKDESC_UVWQ       = SVGA3DBLOCKDESC_U |
-	SVGA3DBLOCKDESC_V |
-	SVGA3DBLOCKDESC_W |
-	SVGA3DBLOCKDESC_Q,
-	SVGA3DBLOCKDESC_LA         = SVGA3DBLOCKDESC_LUMINANCE |
-	SVGA3DBLOCKDESC_ALPHA,
+				     SVGA3DBLOCKDESC_V |
+				     SVGA3DBLOCKDESC_W |
+				     SVGA3DBLOCKDESC_Q |
+				     SVGA3DBLOCKDESC_BUMP,
+	SVGA3DBLOCKDESC_L_UNORM    = SVGA3DBLOCKDESC_LUMINANCE |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_LA_UNORM   = SVGA3DBLOCKDESC_LUMINANCE |
+				     SVGA3DBLOCKDESC_ALPHA |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_R_FP       = SVGA3DBLOCKDESC_RED |
-	SVGA3DBLOCKDESC_IEEE_FP,
+				     SVGA3DBLOCKDESC_FP |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_RG_FP      = SVGA3DBLOCKDESC_R_FP |
-	SVGA3DBLOCKDESC_GREEN,
+				     SVGA3DBLOCKDESC_GREEN |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_RGB_FP     = SVGA3DBLOCKDESC_RG_FP |
-	SVGA3DBLOCKDESC_BLUE,
-	SVGA3DBLOCKDESC_RGBA_FP    = SVGA3DBLOCKDESC_RGB_FP |
-	SVGA3DBLOCKDESC_ALPHA,
-	SVGA3DBLOCKDESC_DS         = SVGA3DBLOCKDESC_DEPTH |
-	SVGA3DBLOCKDESC_STENCIL,
-	SVGA3DBLOCKDESC_YUV        = SVGA3DBLOCKDESC_UV_VIDEO |
-	SVGA3DBLOCKDESC_Y,
+				     SVGA3DBLOCKDESC_BLUE |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YUV        = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_COLOR,
 	SVGA3DBLOCKDESC_AYUV       = SVGA3DBLOCKDESC_ALPHA |
-	SVGA3DBLOCKDESC_Y |
-	SVGA3DBLOCKDESC_U_VIDEO |
-	SVGA3DBLOCKDESC_V_VIDEO,
-	SVGA3DBLOCKDESC_RGBE       = SVGA3DBLOCKDESC_RGB |
-	SVGA3DBLOCKDESC_EXP,
-	SVGA3DBLOCKDESC_COMPRESSED_SRGB = SVGA3DBLOCKDESC_COMPRESSED |
-	SVGA3DBLOCKDESC_SRGB,
-	SVGA3DBLOCKDESC_NV12       = SVGA3DBLOCKDESC_PLANAR_YUV |
-	SVGA3DBLOCKDESC_2PLANAR_YUV,
-	SVGA3DBLOCKDESC_YV12       = SVGA3DBLOCKDESC_PLANAR_YUV |
-	SVGA3DBLOCKDESC_3PLANAR_YUV,
+				     SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_RGB_EXP       = SVGA3DBLOCKDESC_RED |
+					SVGA3DBLOCKDESC_GREEN |
+					SVGA3DBLOCKDESC_BLUE |
+					SVGA3DBLOCKDESC_EXP |
+					SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_COMP_TYPELESS = SVGA3DBLOCKDESC_COMPRESSED |
+					SVGA3DBLOCKDESC_TYPELESS,
+	SVGA3DBLOCKDESC_COMP_UNORM = SVGA3DBLOCKDESC_COMPRESSED |
+				     SVGA3DBLOCKDESC_UINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_SNORM = SVGA3DBLOCKDESC_COMPRESSED |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_COMP_UNORM |
+					  SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC1_COMP_TYPELESS = SVGA3DBLOCKDESC_BC1 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM = SVGA3DBLOCKDESC_BC1 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC1_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC2_COMP_TYPELESS = SVGA3DBLOCKDESC_BC2 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM = SVGA3DBLOCKDESC_BC2 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC2_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC3_COMP_TYPELESS = SVGA3DBLOCKDESC_BC3 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM = SVGA3DBLOCKDESC_BC3 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB = SVGA3DBLOCKDESC_BC3_COMP_UNORM |
+					      SVGA3DBLOCKDESC_SRGB,
+	SVGA3DBLOCKDESC_BC4_COMP_TYPELESS = SVGA3DBLOCKDESC_BC4 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC4_COMP_UNORM = SVGA3DBLOCKDESC_BC4 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC4_COMP_SNORM = SVGA3DBLOCKDESC_BC4 |
+					 SVGA3DBLOCKDESC_COMP_SNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_TYPELESS = SVGA3DBLOCKDESC_BC5 |
+					    SVGA3DBLOCKDESC_COMP_TYPELESS,
+	SVGA3DBLOCKDESC_BC5_COMP_UNORM = SVGA3DBLOCKDESC_BC5 |
+					 SVGA3DBLOCKDESC_COMP_UNORM,
+	SVGA3DBLOCKDESC_BC5_COMP_SNORM = SVGA3DBLOCKDESC_BC5 |
+					 SVGA3DBLOCKDESC_COMP_SNORM,
+
+	SVGA3DBLOCKDESC_NV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_PLANAR_YUV |
+				     SVGA3DBLOCKDESC_2PLANAR_YUV |
+				     SVGA3DBLOCKDESC_COLOR,
+	SVGA3DBLOCKDESC_YV12       = SVGA3DBLOCKDESC_YUV_VIDEO |
+				     SVGA3DBLOCKDESC_PLANAR_YUV |
+				     SVGA3DBLOCKDESC_3PLANAR_YUV |
+				     SVGA3DBLOCKDESC_COLOR,
+
+	SVGA3DBLOCKDESC_DEPTH_UINT = SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DEPTH_UNORM = SVGA3DBLOCKDESC_DEPTH_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DS      =    SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_STENCIL,
+	SVGA3DBLOCKDESC_DS_UINT =    SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_STENCIL |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_DS_UNORM =   SVGA3DBLOCKDESC_DS_UINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_DEPTH_FP   = SVGA3DBLOCKDESC_DEPTH |
+				     SVGA3DBLOCKDESC_FP,
+
+	SVGA3DBLOCKDESC_UV_UINT    = SVGA3DBLOCKDESC_UV |
+				     SVGA3DBLOCKDESC_UINT,
+	SVGA3DBLOCKDESC_UV_SNORM   = SVGA3DBLOCKDESC_UV |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM,
+	SVGA3DBLOCKDESC_UVCX_SNORM = SVGA3DBLOCKDESC_UV_SNORM |
+				     SVGA3DBLOCKDESC_CX,
+	SVGA3DBLOCKDESC_UVWQ_SNORM = SVGA3DBLOCKDESC_UVWQ |
+				     SVGA3DBLOCKDESC_SINT |
+				     SVGA3DBLOCKDESC_NORM,
 };
 
-/*
- * SVGA3dSurfaceDesc describes the actual pixel data.
- *
- * This structure provides the following information:
- *    1. Block description.
- *    2. Dimensions of a block in the surface.
- *    3. Size of block in bytes.
- *    4. Bit depth of the pixel data.
- *    5. Channel bit depths and masks (if applicable).
- */
 struct svga3d_channel_def {
 	union {
 		u8 blue;
-		u8 u;
+		u8 w_bump;
+		u8 l_bump;
 		u8 uv_video;
 		u8 u_video;
 	};
 	union {
 		u8 green;
-		u8 v;
 		u8 stencil;
+		u8 v_bump;
 		u8 v_video;
 	};
 	union {
 		u8 red;
-		u8 w;
+		u8 u_bump;
 		u8 luminance;
-		u8 y;
+		u8 y_video;
 		u8 depth;
 		u8 data;
 	};
 	union {
 		u8 alpha;
-		u8 q;
+		u8 q_bump;
 		u8 exp;
 	};
 };
 
+/*
+ * struct svga3d_surface_desc - describes the actual pixel data.
+ *
+ * @format: Format
+ * @block_desc: Block description
+ * @block_size: Dimensions in pixels of a block
+ * @bytes_per_block: Size of block in bytes
+ * @pitch_bytes_per_block: Size of a block in bytes for purposes of pitch
+ * @bit_depth: Channel bit depths
+ * @bit_offset: Channel bit masks (in bits offset from the start of the pointer)
+ */
 struct svga3d_surface_desc {
 	SVGA3dSurfaceFormat format;
 	enum svga3d_block_desc block_desc;
+
 	surf_size_struct block_size;
 	u32 bytes_per_block;
 	u32 pitch_bytes_per_block;
 
-	u32 total_bit_depth;
 	struct svga3d_channel_def bit_depth;
 	struct svga3d_channel_def bit_offset;
 };
@@ -215,729 +381,728 @@ struct svga3d_surface_desc {
 static const struct svga3d_surface_desc svga3d_surface_descs[] = {
    {SVGA3D_FORMAT_INVALID, SVGA3DBLOCKDESC_NONE,
       {1, 1, 1},  0, 0,
-      0, {{0}, {0}, {0}, {0}},
+      {{0}, {0}, {0}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_X8R8G8B8, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A8R8G8B8, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R5G6B5, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {6}, {5}, {0}},
+      {{5}, {6}, {5}, {0}},
       {{0}, {5}, {11}, {0}}},
 
-   {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_X1R5G5B5, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      15, {{5}, {5}, {5}, {0}},
+      {{5}, {5}, {5}, {0}},
       {{0}, {5}, {10}, {0}}},
 
-   {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A1R5G5B5, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {5}, {1}},
+      {{5}, {5}, {5}, {1}},
       {{0}, {5}, {10}, {15}}},
 
-   {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A4R4G4B4, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{4}, {4}, {4}, {4}},
+      {{4}, {4}, {4}, {4}},
       {{0}, {4}, {8}, {12}}},
 
-   {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D32, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D16, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D24S8, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {8}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D15S1, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {1}, {15}, {0}},
-      {{0}, {15}, {0}, {0}}},
+      {{0}, {1}, {15}, {0}},
+      {{0}, {0}, {1}, {0}}},
 
-   {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_LUMINANCE,
+   {SVGA3D_LUMINANCE8, SVGA3DBLOCKDESC_L_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA,
-    {1  , 1, 1},  1, 1,
-      8, {{0}, {0}, {4}, {4}},
+   {SVGA3D_LUMINANCE4_ALPHA4, SVGA3DBLOCKDESC_LA_UNORM,
+      {1, 1, 1},  1, 1,
+      {{0}, {0}, {4}, {4}},
       {{0}, {0}, {0}, {4}}},
 
-   {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_LUMINANCE,
+   {SVGA3D_LUMINANCE16, SVGA3DBLOCKDESC_L_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA,
+   {SVGA3D_LUMINANCE8_ALPHA8, SVGA3DBLOCKDESC_LA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {8}, {8}},
+      {{0}, {0}, {8}, {8}},
       {{0}, {0}, {0}, {8}}},
 
-   {SVGA3D_DXT1, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT1, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT2, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT2, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT3, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT3, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT4, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT4, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_DXT5, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_DXT5, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_BUMPU8V8, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {8}, {8}},
-      {{0}, {0}, {0}, {8}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_BUMPL6V5U5, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {6}, {0}},
-      {{11}, {6}, {0}, {0}}},
+      {{6}, {5}, {5}, {0}},
+      {{10}, {5}, {0}, {0}}},
 
    {SVGA3D_BUMPX8L8V8U8, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
-   {SVGA3D_BUMPL8V8U8, SVGA3DBLOCKDESC_UVL,
+   {SVGA3D_FORMAT_DEAD1, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  3, 3,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
    {SVGA3D_ARGB_S10E5, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_ARGB_S23E8, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A2R10G10B10, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
+      {{10}, {10}, {10}, {2}},
       {{0}, {10}, {20}, {30}}},
 
-   {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_V8U8, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_Q8W8V8U8, SVGA3DBLOCKDESC_UVWQ_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
-      {{24}, {16}, {8}, {0}}},
+      {{8}, {8}, {8}, {8}},
+      {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_CxV8U8, SVGA3DBLOCKDESC_UVCX_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_X8L8V8U8, SVGA3DBLOCKDESC_UVL,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{16}, {8}, {0}, {0}}},
 
    {SVGA3D_A2W10V10U10, SVGA3DBLOCKDESC_UVWA,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_ALPHA,
+   {SVGA3D_ALPHA8, SVGA3DBLOCKDESC_A_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {0}, {8}},
+      {{0}, {0}, {0}, {8}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R_S10E5, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R_S23E8, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_RG_S10E5, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
    {SVGA3D_RG_S23E8, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
    {SVGA3D_BUFFER, SVGA3DBLOCKDESC_BUFFER,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_D24X8, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_V16U16, SVGA3DBLOCKDESC_UV_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{16}, {16}, {0}, {0}},
-      {{16}, {0}, {0}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_G16R16, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
-      {{0}, {0}, {16}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_A16B16G16R16, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_UYVY, SVGA3DBLOCKDESC_YUV,
-      {1, 1, 1},  2, 2,
-      16, {{8}, {0}, {8}, {0}},
+      {2, 1, 1},  4, 4,
+      {{8}, {0}, {8}, {0}},
       {{0}, {0}, {8}, {0}}},
 
    {SVGA3D_YUY2, SVGA3DBLOCKDESC_YUV,
-      {1, 1, 1},  2, 2,
-      16, {{8}, {0}, {8}, {0}},
+      {2, 1, 1},  4, 4,
+      {{8}, {0}, {8}, {0}},
       {{8}, {0}, {0}, {0}}},
 
    {SVGA3D_NV12, SVGA3DBLOCKDESC_NV12,
       {2, 2, 1},  6, 2,
-      48, {{0}, {0}, {48}, {0}},
+      {{0}, {0}, {48}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_AYUV, SVGA3DBLOCKDESC_AYUV,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R32G32B32A32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R32G32B32A32_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R32G32B32A32_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
-   {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R32G32B32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
    {SVGA3D_R32G32B32_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_R32G32B32_UINT, SVGA3DBLOCKDESC_RGB_UINT,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_UVW,
+   {SVGA3D_R32G32B32_SINT, SVGA3DBLOCKDESC_RGB_SINT,
       {1, 1, 1},  12, 12,
-      96, {{32}, {32}, {32}, {0}},
+      {{32}, {32}, {32}, {0}},
       {{64}, {32}, {0}, {0}}},
 
-   {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R16G16B16A16_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_UVWQ,
+   {SVGA3D_R16G16B16A16_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G32_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R32G32_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R32G8X24_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {32}, {0}},
+      {{0}, {8}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
    {SVGA3D_D32_FLOAT_S8X24_UINT, SVGA3DBLOCKDESC_DS,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {32}, {0}},
+      {{0}, {8}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R32_FLOAT_X8X24_TYPELESS, SVGA3DBLOCKDESC_R_FP,
+   {SVGA3D_R32_FLOAT_X8X24, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X32_TYPELESS_G8X24_UINT, SVGA3DBLOCKDESC_GREEN,
+   {SVGA3D_X32_G8X24_UINT, SVGA3DBLOCKDESC_G_UINT,
       {1, 1, 1},  8, 8,
-      64, {{0}, {8}, {0}, {0}},
+      {{0}, {8}, {0}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
    {SVGA3D_R11G11B10_FLOAT, SVGA3DBLOCKDESC_RGB_FP,
       {1, 1, 1},  4, 4,
-      32, {{10}, {11}, {11}, {0}},
-      {{0}, {10}, {21}, {0}}},
+      {{10}, {11}, {11}, {0}},
+      {{22}, {11}, {0}, {0}}},
 
-   {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_SRGB,
+   {SVGA3D_R8G8B8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_UINT, SVGA3DBLOCKDESC_RGBA_UINT,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_SINT, SVGA3DBLOCKDESC_RGBA_SINT,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{16}, {8}, {0}, {24}}},
 
-   {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_FP,
+   {SVGA3D_R16G16_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R16G16_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_D32_FLOAT, SVGA3DBLOCKDESC_DEPTH_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R32_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R24G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
+      {{0}, {8}, {24}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_D24_UNORM_S8_UINT, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
+      {{0}, {8}, {24}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_R24_UNORM_X8_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R24_UNORM_X8, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {24}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_X24_TYPELESS_G8_UINT, SVGA3DBLOCKDESC_GREEN,
+   {SVGA3D_X24_G8_UINT, SVGA3DBLOCKDESC_G_UINT,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {0}, {0}},
+      {{0}, {8}, {0}, {0}},
       {{0}, {24}, {0}, {0}}},
 
-   {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_UINT, SVGA3DBLOCKDESC_RG_UINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_UV,
+   {SVGA3D_R8G8_SINT, SVGA3DBLOCKDESC_RG_SINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_UNORM, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R16_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R16_SNORM, SVGA3DBLOCKDESC_R_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R16_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_UNORM, SVGA3DBLOCKDESC_R_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_R8_UINT, SVGA3DBLOCKDESC_R_UINT,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R8_SNORM, SVGA3DBLOCKDESC_R_SNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_U,
+   {SVGA3D_R8_SINT, SVGA3DBLOCKDESC_R_SINT,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_P8, SVGA3DBLOCKDESC_RED,
+   {SVGA3D_P8, SVGA3DBLOCKDESC_NONE,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {8}, {0}},
+      {{0}, {0}, {8}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGBE,
+   {SVGA3D_R9G9B9E5_SHAREDEXP, SVGA3DBLOCKDESC_RGB_EXP,
       {1, 1, 1},  4, 4,
-      32, {{9}, {9}, {9}, {5}},
+      {{9}, {9}, {9}, {5}},
       {{18}, {9}, {0}, {27}}},
 
-   {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_RG,
-      {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
-      {{0}, {8}, {0}, {0}}},
+   {SVGA3D_R8G8_B8G8_UNORM, SVGA3DBLOCKDESC_NONE,
+      {2, 1, 1},  4, 4,
+      {{0}, {8}, {8}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_RG,
-      {1, 1, 1},  2, 2,
-      16, {{0}, {8}, {8}, {0}},
+   {SVGA3D_G8R8_G8B8_UNORM, SVGA3DBLOCKDESC_NONE,
+      {2, 1, 1},  4, 4,
+      {{0}, {8}, {8}, {0}},
       {{0}, {8}, {0}, {0}}},
 
-   {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC1_TYPELESS, SVGA3DBLOCKDESC_BC1_COMP_TYPELESS,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC1_UNORM_SRGB, SVGA3DBLOCKDESC_BC1_COMP_UNORM_SRGB,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC2_TYPELESS, SVGA3DBLOCKDESC_BC2_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC2_UNORM_SRGB, SVGA3DBLOCKDESC_BC2_COMP_UNORM_SRGB,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC3_TYPELESS, SVGA3DBLOCKDESC_BC3_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_COMPRESSED_SRGB,
+   {SVGA3D_BC3_UNORM_SRGB, SVGA3DBLOCKDESC_BC3_COMP_UNORM_SRGB,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_TYPELESS, SVGA3DBLOCKDESC_BC4_COMP_TYPELESS,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_ATI1, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_ATI1, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_SNORM, SVGA3DBLOCKDESC_BC4_COMP_SNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_TYPELESS, SVGA3DBLOCKDESC_BC5_COMP_TYPELESS,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_ATI2, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_ATI2, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_SNORM, SVGA3DBLOCKDESC_BC5_COMP_SNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10_XR_BIAS_A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+     {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B8G8R8A8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_SRGB,
+   {SVGA3D_B8G8R8A8_UNORM_SRGB, SVGA3DBLOCKDESC_RGBA_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B8G8R8X8_TYPELESS, SVGA3DBLOCKDESC_TYPELESS,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_SRGB,
+   {SVGA3D_B8G8R8X8_UNORM_SRGB, SVGA3DBLOCKDESC_RGB_UNORM_SRGB,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_DF16, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_Z_DF24, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {0}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
-   {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS,
+   {SVGA3D_Z_D24S8_INT, SVGA3DBLOCKDESC_DS_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {8}, {24}, {0}},
-      {{0}, {24}, {0}, {0}}},
+      {{0}, {8}, {24}, {0}},
+      {{0}, {0}, {8}, {0}}},
 
    {SVGA3D_YV12, SVGA3DBLOCKDESC_YV12,
       {2, 2, 1},  6, 2,
-      48, {{0}, {0}, {48}, {0}},
+      {{0}, {0}, {48}, {0}},
       {{0}, {0}, {0}, {0}}},
 
    {SVGA3D_R32G32B32A32_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  16, 16,
-      128, {{32}, {32}, {32}, {32}},
+      {{32}, {32}, {32}, {32}},
       {{64}, {32}, {0}, {96}}},
 
    {SVGA3D_R16G16B16A16_FLOAT, SVGA3DBLOCKDESC_RGBA_FP,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
-   {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R16G16B16A16_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  8, 8,
-      64, {{16}, {16}, {16}, {16}},
+      {{16}, {16}, {16}, {16}},
       {{32}, {16}, {0}, {48}}},
 
    {SVGA3D_R32G32_FLOAT, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  8, 8,
-      64, {{0}, {32}, {32}, {0}},
+      {{0}, {32}, {32}, {0}},
       {{0}, {32}, {0}, {0}}},
 
-   {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R10G10B10A2_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{10}, {10}, {10}, {2}},
-      {{0}, {10}, {20}, {30}}},
+      {{10}, {10}, {10}, {2}},
+      {{20}, {10}, {0}, {30}}},
 
-   {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_R8G8B8A8_SNORM, SVGA3DBLOCKDESC_RGBA_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
-      {{24}, {16}, {8}, {0}}},
+      {{8}, {8}, {8}, {8}},
+      {{16}, {8}, {0}, {24}}},
 
    {SVGA3D_R16G16_FLOAT, SVGA3DBLOCKDESC_RG_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {16}, {0}},
       {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_UNORM, SVGA3DBLOCKDESC_RG_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{0}, {16}, {16}, {0}},
-      {{0}, {0}, {16}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
-   {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R16G16_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
       {1, 1, 1},  4, 4,
-      32, {{16}, {16}, {0}, {0}},
-      {{16}, {0}, {0}, {0}}},
+      {{0}, {16}, {16}, {0}},
+      {{0}, {16}, {0}, {0}}},
 
    {SVGA3D_R32_FLOAT, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  4, 4,
-      32, {{0}, {0}, {32}, {0}},
+      {{0}, {0}, {32}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG,
+   {SVGA3D_R8G8_SNORM, SVGA3DBLOCKDESC_RG_SNORM,
       {1, 1, 1},  2, 2,
-      16, {{8}, {8}, {0}, {0}},
-      {{8}, {0}, {0}, {0}}},
+      {{0}, {8}, {8}, {0}},
+      {{0}, {8}, {0}, {0}}},
 
    {SVGA3D_R16_FLOAT, SVGA3DBLOCKDESC_R_FP,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH,
+   {SVGA3D_D16_UNORM, SVGA3DBLOCKDESC_DEPTH_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{0}, {0}, {16}, {0}},
+      {{0}, {0}, {16}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_ALPHA,
+   {SVGA3D_A8_UNORM, SVGA3DBLOCKDESC_A_UNORM,
       {1, 1, 1},  1, 1,
-      8, {{0}, {0}, {0}, {8}},
+      {{0}, {0}, {0}, {8}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC1_UNORM, SVGA3DBLOCKDESC_BC1_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC2_UNORM, SVGA3DBLOCKDESC_BC2_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC3_UNORM, SVGA3DBLOCKDESC_BC3_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B5G6R5_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {6}, {5}, {0}},
+      {{5}, {6}, {5}, {0}},
       {{0}, {5}, {11}, {0}}},
 
-   {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B5G5R5A1_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  2, 2,
-      16, {{5}, {5}, {5}, {1}},
+      {{5}, {5}, {5}, {1}},
       {{0}, {5}, {10}, {15}}},
 
-   {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA,
+   {SVGA3D_B8G8R8A8_UNORM, SVGA3DBLOCKDESC_RGBA_UNORM,
       {1, 1, 1},  4, 4,
-      32, {{8}, {8}, {8}, {8}},
+      {{8}, {8}, {8}, {8}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB,
+   {SVGA3D_B8G8R8X8_UNORM, SVGA3DBLOCKDESC_RGB_UNORM,
       {1, 1, 1},  4, 4,
-      24, {{8}, {8}, {8}, {0}},
+      {{8}, {8}, {8}, {0}},
       {{0}, {8}, {16}, {24}}},
 
-   {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC4_UNORM, SVGA3DBLOCKDESC_BC4_COMP_UNORM,
       {4, 4, 1},  8, 8,
-      64, {{0}, {0}, {64}, {0}},
+      {{0}, {0}, {64}, {0}},
       {{0}, {0}, {0}, {0}}},
 
-   {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_COMPRESSED,
+   {SVGA3D_BC5_UNORM, SVGA3DBLOCKDESC_BC5_COMP_UNORM,
       {4, 4, 1},  16, 16,
-      128, {{0}, {0}, {128}, {0}},
+      {{0}, {0}, {128}, {0}},
       {{0}, {0}, {0}, {0}}},
-
 };
 
 static inline u32 clamped_umul32(u32 a, u32 b)
@@ -946,6 +1111,10 @@ static inline u32 clamped_umul32(u32 a, u32 b)
 	return (tmp > (uint64_t) ((u32) -1)) ? (u32) -1 : tmp;
 }
 
+/**
+ * svga3dsurface_get_desc - Look up the appropriate SVGA3dSurfaceDesc for the
+ * given format.
+ */
 static inline const struct svga3d_surface_desc *
 svga3dsurface_get_desc(SVGA3dSurfaceFormat format)
 {
@@ -955,23 +1124,10 @@ svga3dsurface_get_desc(SVGA3dSurfaceFormat format)
 	return &svga3d_surface_descs[SVGA3D_FORMAT_INVALID];
 }
 
-/*
- *----------------------------------------------------------------------
- *
- * svga3dsurface_get_mip_size --
- *
- *      Given a base level size and the mip level, compute the size of
- *      the mip level.
- *
- * Results:
- *      See above.
- *
- * Side effects:
- *      None.
- *
- *----------------------------------------------------------------------
+/**
+ * svga3dsurface_get_mip_size -  Given a base level size and the mip level,
+ * compute the size of the mip level.
  */
-
 static inline surf_size_struct
 svga3dsurface_get_mip_size(surf_size_struct base_level, u32 mip_level)
 {
@@ -1018,28 +1174,17 @@ svga3dsurface_calculate_pitch(const struct svga3d_surface_desc *desc,
 	return pitch;
 }
 
-/*
- *-----------------------------------------------------------------------------
- *
- * svga3dsurface_get_image_buffer_size --
- *
- *      Return the number of bytes of buffer space required to store
- *      one image of a surface, optionally using the specified pitch.
- *
- *      If pitch is zero, it is assumed that rows are tightly packed.
- *
- *      This function is overflow-safe. If the result would have
- *      overflowed, instead we return MAX_UINT32.
+/**
+ * svga3dsurface_get_image_buffer_size - Calculates image buffer size.
  *
- * Results:
- *      Byte count.
+ * Return the number of bytes of buffer space required to store one image of a
+ * surface, optionally using the specified pitch.
  *
- * Side effects:
- *      None.
+ * If pitch is zero, it is assumed that rows are tightly packed.
  *
- *-----------------------------------------------------------------------------
+ * This function is overflow-safe. If the result would have overflowed, instead
+ * we return MAX_UINT32.
  */
-
 static inline u32
 svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc,
 				    const surf_size_struct *size,
@@ -1067,6 +1212,9 @@ svga3dsurface_get_image_buffer_size(const struct svga3d_surface_desc *desc,
 	return total_size;
 }
 
+/**
+ * svga3dsurface_get_serialized_size - Get the serialized size for the image.
+ */
 static inline u32
 svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format,
 				  surf_size_struct base_level_size,
@@ -1206,3 +1354,5 @@ svga3dsurface_is_screen_target_format(SVGA3dSurfaceFormat format)
 	}
 	return svga3dsurface_is_dx_screen_target_format(format);
 }
+
+#endif /* _SVGA3D_SURFACEDEFS_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
index 27b33ba88430..309904e7cfd3 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_types.h
@@ -44,9 +44,21 @@
 
 #define SVGA3D_INVALID_ID         ((uint32)-1)
 
+typedef uint8 SVGABool8;   /* 8-bit Bool definition */
 typedef uint32 SVGA3dBool; /* 32-bit Bool definition */
 typedef uint32 SVGA3dColor; /* a, r, g, b */
 
+typedef uint32 SVGA3dSurfaceId;
+
+typedef
+#include "vmware_pack_begin.h"
+struct {
+   uint32 numerator;
+   uint32 denominator;
+}
+#include "vmware_pack_end.h"
+SVGA3dFraction64;
+
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dCopyRect {
@@ -145,7 +157,7 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_BUMPU8V8                     = 20,
    SVGA3D_BUMPL6V5U5                   = 21,
    SVGA3D_BUMPX8L8V8U8                 = 22,
-   SVGA3D_BUMPL8V8U8                   = 23,
+   SVGA3D_FORMAT_DEAD1                 = 23,
 
    SVGA3D_ARGB_S10E5                   = 24,   /* 16-bit floating-point ARGB */
    SVGA3D_ARGB_S23E8                   = 25,   /* 32-bit floating-point ARGB */
@@ -204,8 +216,8 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_R32G32_SINT                  = 59,
    SVGA3D_R32G8X24_TYPELESS            = 60,
    SVGA3D_D32_FLOAT_S8X24_UINT         = 61,
-   SVGA3D_R32_FLOAT_X8X24_TYPELESS     = 62,
-   SVGA3D_X32_TYPELESS_G8X24_UINT      = 63,
+   SVGA3D_R32_FLOAT_X8X24              = 62,
+   SVGA3D_X32_G8X24_UINT               = 63,
    SVGA3D_R10G10B10A2_TYPELESS         = 64,
    SVGA3D_R10G10B10A2_UINT             = 65,
    SVGA3D_R11G11B10_FLOAT              = 66,
@@ -223,8 +235,8 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_R32_SINT                     = 78,
    SVGA3D_R24G8_TYPELESS               = 79,
    SVGA3D_D24_UNORM_S8_UINT            = 80,
-   SVGA3D_R24_UNORM_X8_TYPELESS        = 81,
-   SVGA3D_X24_TYPELESS_G8_UINT         = 82,
+   SVGA3D_R24_UNORM_X8                 = 81,
+   SVGA3D_X24_G8_UINT                  = 82,
    SVGA3D_R8G8_TYPELESS                = 83,
    SVGA3D_R8G8_UNORM                   = 84,
    SVGA3D_R8G8_UINT                    = 85,
@@ -296,92 +308,114 @@ typedef enum SVGA3dSurfaceFormat {
    SVGA3D_FORMAT_MAX
 } SVGA3dSurfaceFormat;
 
-typedef enum SVGA3dSurfaceFlags {
-   SVGA3D_SURFACE_CUBEMAP               = (1 << 0),
+/*
+ * SVGA3d Surface Flags --
+ */
+#define SVGA3D_SURFACE_CUBEMAP                (1 << 0)
 
-   /*
-    * HINT flags are not enforced by the device but are useful for
-    * performance.
-    */
-   SVGA3D_SURFACE_HINT_STATIC           = (1 << 1),
-   SVGA3D_SURFACE_HINT_DYNAMIC          = (1 << 2),
-   SVGA3D_SURFACE_HINT_INDEXBUFFER      = (1 << 3),
-   SVGA3D_SURFACE_HINT_VERTEXBUFFER     = (1 << 4),
-   SVGA3D_SURFACE_HINT_TEXTURE          = (1 << 5),
-   SVGA3D_SURFACE_HINT_RENDERTARGET     = (1 << 6),
-   SVGA3D_SURFACE_HINT_DEPTHSTENCIL     = (1 << 7),
-   SVGA3D_SURFACE_HINT_WRITEONLY        = (1 << 8),
-   SVGA3D_SURFACE_MASKABLE_ANTIALIAS    = (1 << 9),
-   SVGA3D_SURFACE_AUTOGENMIPMAPS        = (1 << 10),
-   SVGA3D_SURFACE_DECODE_RENDERTARGET   = (1 << 11),
+/*
+ * HINT flags are not enforced by the device but are useful for
+ * performance.
+ */
+#define SVGA3D_SURFACE_HINT_STATIC            (CONST64U(1) << 1)
+#define SVGA3D_SURFACE_HINT_DYNAMIC           (CONST64U(1) << 2)
+#define SVGA3D_SURFACE_HINT_INDEXBUFFER       (CONST64U(1) << 3)
+#define SVGA3D_SURFACE_HINT_VERTEXBUFFER      (CONST64U(1) << 4)
+#define SVGA3D_SURFACE_HINT_TEXTURE           (CONST64U(1) << 5)
+#define SVGA3D_SURFACE_HINT_RENDERTARGET      (CONST64U(1) << 6)
+#define SVGA3D_SURFACE_HINT_DEPTHSTENCIL      (CONST64U(1) << 7)
+#define SVGA3D_SURFACE_HINT_WRITEONLY         (CONST64U(1) << 8)
+#define SVGA3D_SURFACE_MASKABLE_ANTIALIAS     (CONST64U(1) << 9)
+#define SVGA3D_SURFACE_AUTOGENMIPMAPS         (CONST64U(1) << 10)
+
+#define SVGA3D_SURFACE_DECODE_RENDERTARGET    (CONST64U(1) << 11)
 
-   /*
-    * Is this surface using a base-level pitch for it's mob backing?
-    *
-    * This flag is not intended to be set by guest-drivers, but is instead
-    * set by the device when the surface is bound to a mob with a specified
-    * pitch.
-    */
-   SVGA3D_SURFACE_MOB_PITCH             = (1 << 12),
+/*
+ * Is this surface using a base-level pitch for it's mob backing?
+ *
+ * This flag is not intended to be set by guest-drivers, but is instead
+ * set by the device when the surface is bound to a mob with a specified
+ * pitch.
+ */
+#define SVGA3D_SURFACE_MOB_PITCH              (CONST64U(1) << 12)
 
-   SVGA3D_SURFACE_INACTIVE              = (1 << 13),
-   SVGA3D_SURFACE_HINT_RT_LOCKABLE      = (1 << 14),
-   SVGA3D_SURFACE_VOLUME                = (1 << 15),
+#define SVGA3D_SURFACE_INACTIVE               (CONST64U(1) << 13)
+#define SVGA3D_SURFACE_HINT_RT_LOCKABLE       (CONST64U(1) << 14)
+#define SVGA3D_SURFACE_VOLUME                 (CONST64U(1) << 15)
 
-   /*
-    * Required to be set on a surface to bind it to a screen target.
-    */
-   SVGA3D_SURFACE_SCREENTARGET          = (1 << 16),
+/*
+ * Required to be set on a surface to bind it to a screen target.
+ */
+#define SVGA3D_SURFACE_SCREENTARGET           (CONST64U(1) << 16)
 
-   /*
-    * Align images in the guest-backing mob to 16-bytes.
-    */
-   SVGA3D_SURFACE_ALIGN16               = (1 << 17),
+/*
+ * Align images in the guest-backing mob to 16-bytes.
+ */
+#define SVGA3D_SURFACE_ALIGN16                (CONST64U(1) << 17)
 
-   SVGA3D_SURFACE_1D                    = (1 << 18),
-   SVGA3D_SURFACE_ARRAY                 = (1 << 19),
+#define SVGA3D_SURFACE_1D                     (CONST64U(1) << 18)
+#define SVGA3D_SURFACE_ARRAY                  (CONST64U(1) << 19)
 
-   /*
-    * Bind flags.
-    * These are enforced for any surface defined with DefineGBSurface_v2.
-    */
-   SVGA3D_SURFACE_BIND_VERTEX_BUFFER    = (1 << 20),
-   SVGA3D_SURFACE_BIND_INDEX_BUFFER     = (1 << 21),
-   SVGA3D_SURFACE_BIND_CONSTANT_BUFFER  = (1 << 22),
-   SVGA3D_SURFACE_BIND_SHADER_RESOURCE  = (1 << 23),
-   SVGA3D_SURFACE_BIND_RENDER_TARGET    = (1 << 24),
-   SVGA3D_SURFACE_BIND_DEPTH_STENCIL    = (1 << 25),
-   SVGA3D_SURFACE_BIND_STREAM_OUTPUT    = (1 << 26),
+/*
+ * Bind flags.
+ * These are enforced for any surface defined with DefineGBSurface_v2.
+ */
+#define SVGA3D_SURFACE_BIND_VERTEX_BUFFER     (CONST64U(1) << 20)
+#define SVGA3D_SURFACE_BIND_INDEX_BUFFER      (CONST64U(1) << 21)
+#define SVGA3D_SURFACE_BIND_CONSTANT_BUFFER   (CONST64U(1) << 22)
+#define SVGA3D_SURFACE_BIND_SHADER_RESOURCE   (CONST64U(1) << 23)
+#define SVGA3D_SURFACE_BIND_RENDER_TARGET     (CONST64U(1) << 24)
+#define SVGA3D_SURFACE_BIND_DEPTH_STENCIL     (CONST64U(1) << 25)
+#define SVGA3D_SURFACE_BIND_STREAM_OUTPUT     (CONST64U(1) << 26)
 
-   /*
-    * A note on staging flags:
-    *
-    * The STAGING flags notes that the surface will not be used directly by the
-    * drawing pipeline, i.e. that it will not be bound to any bind point.
-    * Staging surfaces may be used by copy operations to move data in and out
-    * of other surfaces.
-    *
-    * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive
-    * updates indirectly, i.e. the surface will not be updated directly, but
-    * will receive copies from staging surfaces.
-    */
-   SVGA3D_SURFACE_STAGING_UPLOAD        = (1 << 27),
-   SVGA3D_SURFACE_STAGING_DOWNLOAD      = (1 << 28),
-   SVGA3D_SURFACE_HINT_INDIRECT_UPDATE  = (1 << 29),
+/*
+ * The STAGING flags notes that the surface will not be used directly by the
+ * drawing pipeline, i.e. that it will not be bound to any bind point.
+ * Staging surfaces may be used by copy operations to move data in and out
+ * of other surfaces.  No bind flags may be set on surfaces with this flag.
+ *
+ * The HINT_INDIRECT_UPDATE flag suggests that the surface will receive
+ * updates indirectly, i.e. the surface will not be updated directly, but
+ * will receive copies from staging surfaces.
+ */
+#define SVGA3D_SURFACE_STAGING_UPLOAD         (CONST64U(1) << 27)
+#define SVGA3D_SURFACE_STAGING_DOWNLOAD       (CONST64U(1) << 28)
+#define SVGA3D_SURFACE_HINT_INDIRECT_UPDATE   (CONST64U(1) << 29)
 
-   /*
-    * Setting this flag allow this surface to be used with the
-    * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command.  It is only valid for
-    * buffer surfaces, an no bind flags are allowed to be set on surfaces
-    * with this flag.
-    */
-   SVGA3D_SURFACE_TRANSFER_FROM_BUFFER  = (1 << 30),
+/*
+ * Setting this flag allow this surface to be used with the
+ * SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER command.  It is only valid for
+ * buffer surfaces, and no bind flags are allowed to be set on surfaces
+ * with this flag.
+ */
+#define SVGA3D_SURFACE_TRANSFER_FROM_BUFFER   (CONST64U(1) << 30)
 
-   /*
-    * Marker for the last defined bit.
-    */
-   SVGA3D_SURFACE_FLAG_MAX              = (1 << 31),
-} SVGA3dSurfaceFlags;
+/*
+ * Reserved for video operations.
+ */
+#define SVGA3D_SURFACE_RESERVED1              (CONST64U(1) << 31)
+
+/*
+ * Specifies that a surface is multisample, and therefore requires the full
+ * mob-backing to store all the samples.
+ */
+#define SVGA3D_SURFACE_MULTISAMPLE            (CONST64U(1) << 32)
+
+#define SVGA3D_SURFACE_FLAG_MAX               (CONST64U(1) << 33)
+
+/*
+ * Surface flags types:
+ *
+ * SVGA3dSurface1Flags:  Lower 32-bits of flags.
+ * SVGA3dSurface2Flags:  Upper 32-bits of flags.
+ * SVGA3dSurfaceAllFlags: Full 64-bits of flags.
+ */
+typedef uint32 SVGA3dSurface1Flags;
+typedef uint32 SVGA3dSurface2Flags;
+typedef uint64 SVGA3dSurfaceAllFlags;
+
+#define SVGA3D_SURFACE_FLAGS1_MASK ((uint64_t)MAX_UINT32)
+#define SVGA3D_SURFACE_FLAGS2_MASK (MAX_UINT64 & ~SVGA3D_SURFACE_FLAGS1_MASK)
 
 #define SVGA3D_SURFACE_HB_DISALLOWED_MASK        \
         (  SVGA3D_SURFACE_MOB_PITCH    |         \
@@ -392,29 +426,41 @@ typedef enum SVGA3dSurfaceFlags {
            SVGA3D_SURFACE_STAGING_UPLOAD |       \
            SVGA3D_SURFACE_STAGING_DOWNLOAD |     \
            SVGA3D_SURFACE_HINT_INDIRECT_UPDATE | \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER   \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER | \
+           SVGA3D_SURFACE_MULTISAMPLE            \
+        )
+
+#define SVGA3D_SURFACE_HB_PRESENT_DISALLOWED_MASK   \
+       (   SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MULTISAMPLE               \
         )
 
 #define SVGA3D_SURFACE_2D_DISALLOWED_MASK           \
         (  SVGA3D_SURFACE_CUBEMAP |                 \
            SVGA3D_SURFACE_MASKABLE_ANTIALIAS |      \
            SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_DECODE_RENDERTARGET |     \
            SVGA3D_SURFACE_VOLUME |                  \
            SVGA3D_SURFACE_1D |                      \
-           SVGA3D_SURFACE_ARRAY |                   \
            SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
            SVGA3D_SURFACE_BIND_INDEX_BUFFER |       \
            SVGA3D_SURFACE_BIND_CONSTANT_BUFFER |    \
            SVGA3D_SURFACE_BIND_DEPTH_STENCIL |      \
            SVGA3D_SURFACE_BIND_STREAM_OUTPUT |      \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER      \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
+           SVGA3D_SURFACE_MULTISAMPLE               \
+        )
+
+#define SVGA3D_SURFACE_BASICOPS_DISALLOWED_MASK     \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MULTISAMPLE               \
         )
 
 #define SVGA3D_SURFACE_SCREENTARGET_DISALLOWED_MASK \
         (  SVGA3D_SURFACE_CUBEMAP |                 \
            SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
-           SVGA3D_SURFACE_DECODE_RENDERTARGET |     \
            SVGA3D_SURFACE_VOLUME |                  \
            SVGA3D_SURFACE_1D |                      \
            SVGA3D_SURFACE_BIND_VERTEX_BUFFER |      \
@@ -426,12 +472,36 @@ typedef enum SVGA3dSurfaceFlags {
            SVGA3D_SURFACE_STAGING_UPLOAD |          \
            SVGA3D_SURFACE_STAGING_DOWNLOAD |        \
            SVGA3D_SURFACE_HINT_INDIRECT_UPDATE |    \
-           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER      \
+           SVGA3D_SURFACE_TRANSFER_FROM_BUFFER |    \
+           SVGA3D_SURFACE_MULTISAMPLE               \
+        )
+
+#define SVGA3D_SURFACE_BUFFER_DISALLOWED_MASK       \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_MASKABLE_ANTIALIAS |      \
+           SVGA3D_SURFACE_ARRAY |                   \
+           SVGA3D_SURFACE_MULTISAMPLE |             \
+           SVGA3D_SURFACE_MOB_PITCH                 \
+        )
+
+#define SVGA3D_SURFACE_MULTISAMPLE_DISALLOWED_MASK  \
+        (  SVGA3D_SURFACE_CUBEMAP |                 \
+           SVGA3D_SURFACE_AUTOGENMIPMAPS |          \
+           SVGA3D_SURFACE_VOLUME |                  \
+           SVGA3D_SURFACE_1D |                      \
+           SVGA3D_SURFACE_SCREENTARGET |            \
+           SVGA3D_SURFACE_MOB_PITCH                 \
         )
 
 #define SVGA3D_SURFACE_DX_ONLY_MASK             \
         (  SVGA3D_SURFACE_BIND_STREAM_OUTPUT |  \
+           SVGA3D_SURFACE_STAGING_UPLOAD |      \
+           SVGA3D_SURFACE_STAGING_DOWNLOAD |    \
            SVGA3D_SURFACE_TRANSFER_FROM_BUFFER  \
+        )
 
 #define SVGA3D_SURFACE_STAGING_MASK             \
         (  SVGA3D_SURFACE_STAGING_UPLOAD |      \
@@ -487,7 +557,7 @@ typedef enum {
 
 /*
  * Indicates that this format can be converted to any RGB format for which
- * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified
+ * SVGA3DFORMAT_OP_MEMBEROFGROUP_ARGB is specified.
  */
    SVGA3DFORMAT_OP_CONVERT_TO_ARGB                       = 0x00002000,
 
@@ -498,22 +568,22 @@ typedef enum {
 
 /*
  * Indicated that this format can be read as an SRGB texture (meaning that the
- * sampler will linearize the looked up data)
+ * sampler will linearize the looked up data).
  */
    SVGA3DFORMAT_OP_SRGBREAD                              = 0x00008000,
 
 /*
- * Indicates that this format can be used in the bumpmap instructions
+ * Indicates that this format can be used in the bumpmap instructions.
  */
    SVGA3DFORMAT_OP_BUMPMAP                               = 0x00010000,
 
 /*
- * Indicates that this format can be sampled by the displacement map sampler
+ * Indicates that this format can be sampled by the displacement map sampler.
  */
    SVGA3DFORMAT_OP_DMAP                                  = 0x00020000,
 
 /*
- * Indicates that this format cannot be used with texture filtering
+ * Indicates that this format cannot be used with texture filtering.
  */
    SVGA3DFORMAT_OP_NOFILTER                              = 0x00040000,
 
@@ -530,18 +600,18 @@ typedef enum {
    SVGA3DFORMAT_OP_SRGBWRITE                             = 0x00100000,
 
 /*
- * Indicates that this format cannot be used with alpha blending
+ * Indicates that this format cannot be used with alpha blending.
  */
    SVGA3DFORMAT_OP_NOALPHABLEND                          = 0x00200000,
 
 /*
  * Indicates that the device can auto-generated sublevels for resources
- * of this format
+ * of this format.
  */
    SVGA3DFORMAT_OP_AUTOGENMIPMAP                         = 0x00400000,
 
 /*
- * Indicates that this format can be used by vertex texture sampler
+ * Indicates that this format can be used by vertex texture sampler.
  */
    SVGA3DFORMAT_OP_VERTEXTEXTURE                         = 0x00800000,
 
@@ -1501,7 +1571,6 @@ union SVGADXQueryResultUnion {
 #include "vmware_pack_end.h"
 SVGADXQueryResultUnion;
 
-
 typedef enum {
    SVGA3D_QUERYSTATE_PENDING     = 0,      /* Query is not finished yet */
    SVGA3D_QUERYSTATE_SUCCEEDED   = 1,      /* Completed successfully */
@@ -1533,9 +1602,9 @@ typedef
 struct {
    union {
       struct {
-	 uint16  function;       /* SVGA3dFogFunction */
-	 uint8   type;           /* SVGA3dFogType */
-	 uint8   base;           /* SVGA3dFogBase */
+         uint16  function;       /* SVGA3dFogFunction */
+         uint8   type;           /* SVGA3dFogType */
+         uint8   base;           /* SVGA3dFogBase */
       };
       uint32     uintValue;
    };
@@ -1547,17 +1616,25 @@ SVGA3dFogMode;
  * Uniquely identify one image (a 1D/2D/3D array) from a surface. This
  * is a surface ID as well as face/mipmap indices.
  */
-
 typedef
 #include "vmware_pack_begin.h"
 struct SVGA3dSurfaceImageId {
-   uint32               sid;
-   uint32               face;
-   uint32               mipmap;
+   uint32 sid;
+   uint32 face;
+   uint32 mipmap;
 }
 #include "vmware_pack_end.h"
 SVGA3dSurfaceImageId;
 
+typedef
+#include "vmware_pack_begin.h"
+struct SVGA3dSubSurfaceId {
+   uint32 sid;
+   uint32 subResourceId;
+}
+#include "vmware_pack_end.h"
+SVGA3dSubSurfaceId;
+
 typedef
 #include "vmware_pack_begin.h"
 struct {
@@ -1582,13 +1659,18 @@ typedef enum {
    SVGA_OTABLE_DX9_MAX         = 5,
 
    SVGA_OTABLE_DXCONTEXT       = 5,
-   SVGA_OTABLE_MAX             = 6
-} SVGAOTableType;
+   SVGA_OTABLE_DX_MAX          = 6,
 
-/*
- * Deprecated.
- */
-#define SVGA_OTABLE_COUNT 4
+   SVGA_OTABLE_RESERVED1       = 6,
+   SVGA_OTABLE_RESERVED2       = 7,
+
+   /*
+    * Additions to this table need to be tied to HW-version features and
+    * checkpointed accordingly.
+    */
+   SVGA_OTABLE_DEVEL_MAX       = 8,
+   SVGA_OTABLE_MAX             = 8
+} SVGAOTableType;
 
 typedef enum {
    SVGA_COTABLE_MIN             = 0,
@@ -1605,7 +1687,7 @@ typedef enum {
    SVGA_COTABLE_DXSHADER        = 10,
    SVGA_COTABLE_DX10_MAX        = 11,
    SVGA_COTABLE_UAVIEW          = 11,
-   SVGA_COTABLE_MAX
+   SVGA_COTABLE_MAX             = 12,
 } SVGACOTableType;
 
 /*
@@ -1626,8 +1708,37 @@ typedef enum SVGAMobFormat {
    SVGA3D_MOBFMT_PREDX_MAX   = 7,
    SVGA3D_MOBFMT_EMPTY       = 7,
    SVGA3D_MOBFMT_MAX,
+
+   /*
+    * This isn't actually used by the guest, but is a mob-format used
+    * internally by the SVGA device (and is therefore not binary compatible).
+    */
+   SVGA3D_MOBFMT_HB,
 } SVGAMobFormat;
 
 #define SVGA3D_MOB_EMPTY_BASE 1
 
+/*
+ * Multisample pattern types.
+ */
+
+typedef enum SVGA3dMSPattern {
+   SVGA3D_MS_PATTERN_NONE     = 0,
+   SVGA3D_MS_PATTERN_MIN      = 0,
+   SVGA3D_MS_PATTERN_STANDARD = 1,
+   SVGA3D_MS_PATTERN_CENTER   = 2,
+   SVGA3D_MS_PATTERN_MAX      = 3,
+} SVGA3dMSPattern;
+
+/*
+ * Precision settings for each sample.
+ */
+
+typedef enum SVGA3dMSQualityLevel {
+   SVGA3D_MS_QUALITY_NONE = 0,
+   SVGA3D_MS_QUALITY_MIN  = 0,
+   SVGA3D_MS_QUALITY_FULL = 1,
+   SVGA3D_MS_QUALITY_MAX  = 2,
+} SVGA3dMSQualityLevel;
+
 #endif /* _SVGA3D_TYPES_H_ */
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
index cdd48a3763db..ab8ea6b3cdb1 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_reg.h
@@ -63,16 +63,26 @@ typedef uint32 SVGAMobId;
 #define SVGA_MAX_BITS_PER_PIXEL         32
 #define SVGA_MAX_DEPTH                  24
 #define SVGA_MAX_DISPLAYS               10
+#define SVGA_MAX_SCREEN_SIZE            8192
+#define SVGA_SCREEN_ROOT_LIMIT (SVGA_MAX_SCREEN_SIZE * SVGA_MAX_DISPLAYS)
+
 
 /*
  * Legal values for the SVGA_REG_CURSOR_ON register in old-fashioned
  * cursor bypass mode. This is still supported, but no new guest
  * drivers should use it.
  */
-#define SVGA_CURSOR_ON_HIDE            0x0   /* Must be 0 to maintain backward compatibility */
-#define SVGA_CURSOR_ON_SHOW            0x1   /* Must be 1 to maintain backward compatibility */
-#define SVGA_CURSOR_ON_REMOVE_FROM_FB  0x2   /* Remove the cursor from the framebuffer because we need to see what's under it */
-#define SVGA_CURSOR_ON_RESTORE_TO_FB   0x3   /* Put the cursor back in the framebuffer so the user can see it */
+#define SVGA_CURSOR_ON_HIDE            0x0
+#define SVGA_CURSOR_ON_SHOW            0x1
+
+/*
+ * Remove the cursor from the framebuffer
+ * because we need to see what's under it
+ */
+#define SVGA_CURSOR_ON_REMOVE_FROM_FB  0x2
+
+/* Put the cursor back in the framebuffer so the user can see it */
+#define SVGA_CURSOR_ON_RESTORE_TO_FB   0x3
 
 /*
  * The maximum framebuffer size that can traced for guests unless the
@@ -101,7 +111,10 @@ typedef uint32 SVGAMobId;
 #define SVGA_VERSION_0     0
 #define SVGA_ID_0          SVGA_MAKE_ID(SVGA_VERSION_0)
 
-/* "Invalid" value for all SVGA IDs. (Version ID, screen object ID, surface ID...) */
+/*
+ * "Invalid" value for all SVGA IDs.
+ * (Version ID, screen object ID, surface ID...)
+ */
 #define SVGA_ID_INVALID    0xFFFFFFFF
 
 /* Port offsets, relative to BAR0 */
@@ -154,7 +167,7 @@ enum {
    SVGA_REG_CONFIG_DONE = 20,         /* Set when memory area configured */
    SVGA_REG_SYNC = 21,                /* See "FIFO Synchronization Registers" */
    SVGA_REG_BUSY = 22,                /* See "FIFO Synchronization Registers" */
-   SVGA_REG_GUEST_ID = 23,            /* Set guest OS identifier */
+   SVGA_REG_GUEST_ID = 23,            /* (Deprecated) */
    SVGA_REG_CURSOR_ID = 24,           /* (Deprecated) */
    SVGA_REG_CURSOR_X = 25,            /* (Deprecated) */
    SVGA_REG_CURSOR_Y = 26,            /* (Deprecated) */
@@ -186,7 +199,14 @@ enum {
    SVGA_REG_MEMORY_SIZE = 47,       /* Total dedicated device memory excluding FIFO */
    SVGA_REG_COMMAND_LOW = 48,       /* Lower 32 bits and submits commands */
    SVGA_REG_COMMAND_HIGH = 49,      /* Upper 32 bits of command buffer PA */
-   SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,   /* Max primary memory */
+
+   /*
+    * Max primary memory.
+    * See SVGA_CAP_NO_BB_RESTRICTION.
+    */
+   SVGA_REG_MAX_PRIMARY_MEM = 50,
+   SVGA_REG_MAX_PRIMARY_BOUNDING_BOX_MEM = 50,
+
    SVGA_REG_SUGGESTED_GBOBJECT_MEM_SIZE_KB = 51, /* Sugested limit on mob mem */
    SVGA_REG_DEV_CAP = 52,           /* Write dev cap index, read value */
    SVGA_REG_CMD_PREPEND_LOW = 53,
@@ -194,7 +214,10 @@ enum {
    SVGA_REG_SCREENTARGET_MAX_WIDTH = 55,
    SVGA_REG_SCREENTARGET_MAX_HEIGHT = 56,
    SVGA_REG_MOB_MAX_SIZE = 57,
-   SVGA_REG_TOP = 58,               /* Must be 1 more than the last register */
+   SVGA_REG_BLANK_SCREEN_TARGETS = 58,
+   SVGA_REG_CAP2 = 59,
+   SVGA_REG_DEVEL_CAP = 60,
+   SVGA_REG_TOP = 61,               /* Must be 1 more than the last register */
 
    SVGA_PALETTE_BASE = 1024,        /* Base of SVGA color map */
    /* Next 768 (== 256*3) registers exist for colormap */
@@ -392,6 +415,7 @@ typedef enum {
    SVGA_CB_CONTEXT_0      = 0x0,
    SVGA_CB_CONTEXT_1      = 0x1, /* Supported with SVGA_CAP_HP_CMD_QUEUE */
    SVGA_CB_CONTEXT_MAX    = 0x2,
+   SVGA_CB_CONTEXT_HP_MAX = 0x2,
 } SVGACBContext;
 
 
@@ -448,6 +472,18 @@ typedef enum {
     * due to an error.  No IRQ is raised.
     */
    SVGA_CB_STATUS_SUBMISSION_ERROR = 6,
+
+   /*
+    * Written by the host when the host finished a
+    * SVGA_DC_CMD_ASYNC_STOP_QUEUE request for this command buffer
+    * queue.  The offset of the first byte not processed is stored in
+    * the errorOffset field of the command buffer header.  All guest
+    * visible side effects of commands till that point are guaranteed
+    * to be finished before this is written.  The
+    * SVGA_IRQFLAG_COMMAND_BUFFER IRQ is raised as long as the
+    * SVGA_CB_FLAG_NO_IRQ is not set.
+    */
+   SVGA_CB_STATUS_PARTIAL_COMPLETE = 7,
 } SVGACBStatus;
 
 typedef enum {
@@ -460,8 +496,8 @@ typedef enum {
 typedef
 #include "vmware_pack_begin.h"
 struct {
-   volatile SVGACBStatus status;
-   volatile uint32 errorOffset;
+   volatile SVGACBStatus status; /* Modified by device. */
+   volatile uint32 errorOffset;  /* Modified by device. */
    uint64 id;
    SVGACBFlags flags;
    uint32 length;
@@ -472,7 +508,9 @@ struct {
          uint32 mobOffset;
       } mob;
    } ptr;
-   uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise */
+   uint32 offset; /* Valid if CMD_BUFFERS_2 cap set, must be zero otherwise,
+                   * modified by device.
+                   */
    uint32 dxContext; /* Valid if DX_CONTEXT flag set, must be zero otherwise */
    uint32 mustBeZero[6];
 }
@@ -483,20 +521,26 @@ typedef enum {
    SVGA_DC_CMD_NOP                   = 0,
    SVGA_DC_CMD_START_STOP_CONTEXT    = 1,
    SVGA_DC_CMD_PREEMPT               = 2,
-   SVGA_DC_CMD_MAX                   = 3,
-   SVGA_DC_CMD_FORCE_UINT            = MAX_UINT32,
+   SVGA_DC_CMD_START_QUEUE           = 3, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_ASYNC_STOP_QUEUE      = 4, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE   = 5, /* Requires SVGA_CAP_HP_CMD_QUEUE */
+   SVGA_DC_CMD_MAX                   = 6,
 } SVGADeviceContextCmdId;
 
-typedef struct {
+/*
+ * Starts or stops both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1.
+ */
+
+typedef struct SVGADCCmdStartStop {
    uint32 enable;
-   SVGACBContext context;
+   SVGACBContext context; /* Must be zero */
 } SVGADCCmdStartStop;
 
 /*
  * SVGADCCmdPreempt --
  *
  * This command allows the guest to request that all command buffers
- * on the specified context be preempted that can be.  After execution
+ * on SVGA_CB_CONTEXT_0 be preempted that can be.  After execution
  * of this command all command buffers that were preempted will
  * already have SVGA_CB_STATUS_PREEMPTED written into the status
  * field.  The device might still be processing a command buffer,
@@ -506,11 +550,68 @@ typedef struct {
  * command buffer header set to zero.
  */
 
-typedef struct {
-   SVGACBContext context;
+typedef struct SVGADCCmdPreempt {
+   SVGACBContext context; /* Must be zero */
    uint32 ignoreIDZero;
 } SVGADCCmdPreempt;
 
+/*
+ * Starts the requested command buffer processing queue.  Valid only
+ * if the SVGA_CAP_HP_CMD_QUEUE cap is set.
+ *
+ * For a command queue to be considered runnable it must be enabled
+ * and any corresponding higher priority queues must also be enabled.
+ * For example in order for command buffers to be processed on
+ * SVGA_CB_CONTEXT_0 both SVGA_CB_CONTEXT_0 and SVGA_CB_CONTEXT_1 must
+ * be enabled.  But for commands to be runnable on SVGA_CB_CONTEXT_1
+ * only that queue must be enabled.
+ */
+
+typedef struct SVGADCCmdStartQueue {
+   SVGACBContext context;
+} SVGADCCmdStartQueue;
+
+/*
+ * Requests the SVGA device to stop processing the requested command
+ * buffer queue as soon as possible.  The guest knows the stop has
+ * completed when one of the following happens.
+ *
+ * 1) A command buffer status of SVGA_CB_STATUS_PARTIAL_COMPLETE is returned
+ * 2) A command buffer error is encountered with would stop the queue
+ *    regardless of the async stop request.
+ * 3) All command buffers that have been submitted complete successfully.
+ * 4) The stop completes synchronously if no command buffers are
+ *    active on the queue when it is issued.
+ *
+ * If the command queue is not in a runnable state there is no
+ * guarentee this async stop will finish.  For instance if the high
+ * priority queue is not enabled and a stop is requested on the low
+ * priority queue, the high priority queue must be reenabled to
+ * guarantee that the async stop will finish.
+ *
+ * This command along with SVGA_DC_CMD_EMPTY_CONTEXT_QUEUE can be used
+ * to implement mid command buffer preemption.
+ *
+ * Valid only if the SVGA_CAP_HP_CMD_QUEUE cap is set.
+ */
+
+typedef struct SVGADCCmdAsyncStopQueue {
+   SVGACBContext context;
+} SVGADCCmdAsyncStopQueue;
+
+/*
+ * Requests the SVGA device to throw away any full command buffers on
+ * the requested command queue that have not been started.  For a
+ * driver to know which command buffers were thrown away a driver
+ * should only issue this command when the queue is stopped, for
+ * whatever reason.
+ */
+
+typedef struct SVGADCCmdEmptyQueue {
+   SVGACBContext context;
+} SVGADCCmdEmptyQueue;
+
+
 /*
  * SVGAGMRImageFormat --
  *
@@ -536,7 +637,7 @@ typedef struct SVGAGMRImageFormat {
       struct {
          uint32 bitsPerPixel : 8;
          uint32 colorDepth   : 8;
-	 uint32 reserved     : 16;  /* Must be zero */
+         uint32 reserved     : 16;  /* Must be zero */
       };
 
       uint32 value;
@@ -700,6 +801,8 @@ SVGASignedPoint;
  *     large enough to express any possible topology without holes between
  *     monitors.)
  *
+ * SVGA_CAP_CAP2_REGISTER --
+ *    If this cap is present, the SVGA_REG_CAP2 register is supported.
  */
 
 #define SVGA_CAP_NONE               0x00000000
@@ -726,8 +829,29 @@ SVGASignedPoint;
 #define SVGA_CAP_DX                 0x10000000
 #define SVGA_CAP_HP_CMD_QUEUE       0x20000000
 #define SVGA_CAP_NO_BB_RESTRICTION  0x40000000
+#define SVGA_CAP_CAP2_REGISTER      0x80000000
 
-#define SVGA_CAP_CMD_RESERVED       0x80000000
+/*
+ * The SVGA_REG_CAP2 register is an additional set of SVGA capability bits.
+ *
+ * SVGA_CAP2_GROW_OTABLE --
+ *      Allow the GrowOTable/DXGrowCOTable commands.
+ *
+ * SVGA_CAP2_INTRA_SURFACE_COPY --
+ *      Allow the IntraSurfaceCopy command.
+ *
+ * SVGA_CAP2_DX2 --
+ *      Allow the DefineGBSurface_v3, WholeSurfaceCopy.
+ *
+ * SVGA_CAP2_RESERVED --
+ *      Reserve the last bit for extending the SVGA capabilities to some
+ *      future mechanisms.
+ */
+#define SVGA_CAP2_NONE               0x00000000
+#define SVGA_CAP2_GROW_OTABLE        0x00000001
+#define SVGA_CAP2_INTRA_SURFACE_COPY 0x00000002
+#define SVGA_CAP2_DX2                0x00000004
+#define SVGA_CAP2_RESERVED           0x80000000
 
 
 /*
@@ -749,7 +873,8 @@ typedef enum {
    SVGABackdoorCapDeviceCaps = 0,
    SVGABackdoorCapFifoCaps = 1,
    SVGABackdoorCap3dHWVersion = 2,
-   SVGABackdoorCapMax = 3,
+   SVGABackdoorCapDeviceCaps2 = 3,
+   SVGABackdoorCapMax = 4,
 } SVGABackdoorCapType;
 
 
@@ -1941,16 +2066,6 @@ SVGAFifoCmdRemapGMR2;
 
 #define SVGA_VRAM_SIZE_W2K          (64 * 1024 * 1024) /* 64 MB */
 
-/*
- * To simplify autoDetect display configuration, support a minimum of
- * two 1920x1200 monitors, 32bpp, side-by-side, optionally rotated:
- *   numDisplays = 2
- *   maxWidth = numDisplay * 1920 = 3840
- *   maxHeight = rotated width of single monitor = 1920
- *   vramSize = maxWidth * maxHeight * 4 = 29491200
- */
-#define SVGA_VRAM_SIZE_AUTODETECT   (32 * 1024 * 1024)
-
 #if defined(VMX86_SERVER)
 #define SVGA_VRAM_SIZE               (4 * 1024 * 1024)
 #define SVGA_VRAM_SIZE_3D           (64 * 1024 * 1024)
diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
index 2e8ba4df8de9..2ba15f131858 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga_types.h
@@ -40,7 +40,10 @@ typedef uint64 PPN64;
 
 typedef bool Bool;
 
+#define MAX_UINT64 U64_MAX
 #define MAX_UINT32 U32_MAX
 #define MAX_UINT16 U16_MAX
 
+#define CONST64U(x) x##ULL
+
 #endif
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 45dfff7733d6..1128420de2c0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -884,7 +884,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 
 	if (dev_priv->has_mob) {
 		spin_lock(&dev_priv->cap_lock);
-		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DX);
+		vmw_write(dev_priv, SVGA_REG_DEV_CAP, SVGA3D_DEVCAP_DXCONTEXT);
 		dev_priv->has_dx = !!vmw_read(dev_priv, SVGA_REG_DEV_CAP);
 		spin_unlock(&dev_priv->cap_lock);
 	}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index a8b194655c40..2d6efc36288f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -3230,9 +3230,9 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 		    false, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_SCREEN_DMA, &vmw_cmd_invalid,
 		    false, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_SET_UNITY_SURFACE_COOKIE, &vmw_cmd_invalid,
+	VMW_CMD_DEF(SVGA_3D_CMD_DEAD1, &vmw_cmd_invalid,
 		    false, false, false),
-	VMW_CMD_DEF(SVGA_3D_CMD_OPEN_CONTEXT_SURFACE, &vmw_cmd_invalid,
+	VMW_CMD_DEF(SVGA_3D_CMD_DEAD2, &vmw_cmd_invalid,
 		    false, false, false),
 	VMW_CMD_DEF(SVGA_3D_CMD_LOGICOPS_BITBLT, &vmw_cmd_invalid,
 		    false, false, false),
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 5e0c8f775c92..6872c7ee8a08 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -122,15 +122,12 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 
 static u32 vmw_mask_multisample(unsigned int cap, u32 fmt_value)
 {
-	/* If the header is updated, update the format test as well! */
-	BUILD_BUG_ON(SVGA3D_DEVCAP_DXFMT_BC5_UNORM + 1 != SVGA3D_DEVCAP_MAX);
-
-	if (cap >= SVGA3D_DEVCAP_DXFMT_X8R8G8B8 &&
-	    cap <= SVGA3D_DEVCAP_DXFMT_BC5_UNORM)
-		fmt_value &= ~(SVGADX_DXFMT_MULTISAMPLE_2 |
-			       SVGADX_DXFMT_MULTISAMPLE_4 |
-			       SVGADX_DXFMT_MULTISAMPLE_8);
-	else if (cap == SVGA3D_DEVCAP_MULTISAMPLE_MASKABLESAMPLES)
+	/*
+	 * A version of user-space exists which use MULTISAMPLE_MASKABLESAMPLES
+	 * to check the sample count supported by virtual device. Since there
+	 * never was support for multisample count for backing MOB return 0.
+	 */
+	if (cap == SVGA3D_DEVCAP_MULTISAMPLE_MASKABLESAMPLES)
 		return 0;
 
 	return fmt_value;
-- 
cgit v1.2.3


From 6f9db69ad93cd6ab77d5571cf748ff7cdcfb0285 Mon Sep 17 00:00:00 2001
From: Tristian Celestin <tristiancelestin@fastmail.com>
Date: Fri, 15 Jun 2018 04:50:18 -0400
Subject: ACPI / PM: Default to s2idle in all machines supporting LP S0

The Dell Venue Pro 7140 supports the Low Power S0 Idle state, but
does not support any of the _DSM functions that the current heuristic
checks for.

Since suspend-to-mem can not be safely performed on this machine,
and since the bitfield check can't cover this case, it is safer
to enable s2idle by default by checking for the presence of the
_DSM alone and removing the bitfield check.

Signed-off-by: Tristian Celestin <tristiancelestin@fastmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/sleep.c | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 5d0486f1cfcd..06ba8cc68889 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -718,9 +718,6 @@ static const struct acpi_device_id lps0_device_ids[] = {
 #define ACPI_LPS0_ENTRY		5
 #define ACPI_LPS0_EXIT		6
 
-#define ACPI_LPS0_SCREEN_MASK	((1 << ACPI_LPS0_SCREEN_OFF) | (1 << ACPI_LPS0_SCREEN_ON))
-#define ACPI_LPS0_PLATFORM_MASK	((1 << ACPI_LPS0_ENTRY) | (1 << ACPI_LPS0_EXIT))
-
 static acpi_handle lps0_device_handle;
 static guid_t lps0_dsm_guid;
 static char lps0_dsm_func_mask;
@@ -924,17 +921,14 @@ static int lps0_device_attach(struct acpi_device *adev,
 	if (out_obj && out_obj->type == ACPI_TYPE_BUFFER) {
 		char bitmask = *(char *)out_obj->buffer.pointer;
 
-		if ((bitmask & ACPI_LPS0_PLATFORM_MASK) == ACPI_LPS0_PLATFORM_MASK ||
-		    (bitmask & ACPI_LPS0_SCREEN_MASK) == ACPI_LPS0_SCREEN_MASK) {
-			lps0_dsm_func_mask = bitmask;
-			lps0_device_handle = adev->handle;
-			/*
-			 * Use suspend-to-idle by default if the default
-			 * suspend mode was not set from the command line.
-			 */
-			if (mem_sleep_default > PM_SUSPEND_MEM)
-				mem_sleep_current = PM_SUSPEND_TO_IDLE;
-		}
+		lps0_dsm_func_mask = bitmask;
+		lps0_device_handle = adev->handle;
+		/*
+		 * Use suspend-to-idle by default if the default
+		 * suspend mode was not set from the command line.
+		 */
+		if (mem_sleep_default > PM_SUSPEND_MEM)
+			mem_sleep_current = PM_SUSPEND_TO_IDLE;
 
 		acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n",
 				  bitmask);
-- 
cgit v1.2.3


From 72a361a5b91c77b33ab2533674fdcec4de3278d0 Mon Sep 17 00:00:00 2001
From: Tristian Celestin <tristiancelestin@fastmail.com>
Date: Sat, 9 Jun 2018 18:18:06 -0400
Subject: ACPI / x86: enable touchscreen on Dell Venue Pro 7139

Permanently enable the SYNA7500 touchscreen device on the Dell
Venue Pro 7139. The DSDT hides the touchscreen ACPI device on
the 7139 in the same fashion as the 7130, and needs to
be enabled in the same way.

Signed-off-by: Tristian Celestin <tristiancelestin@fastmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/x86/utils.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index ec5b0f190231..3a13b2af2bf8 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -62,14 +62,20 @@ static const struct always_present_id always_present_ids[] = {
 	 */
 	ENTRY("INT0002", "1", ICPU(INTEL_FAM6_ATOM_AIRMONT), {}),
 	/*
-	 * On the Dell Venue 11 Pro 7130 the DSDT hides the touchscreen ACPI
-	 * device until a certain time after _SB.PCI0.GFX0.LCD.LCD1._ON gets
-	 * called has passed *and* _STA has been called at least 3 times since.
+	 * On the Dell Venue 11 Pro 7130 and 7139, the DSDT hides
+	 * the touchscreen ACPI device until a certain time
+	 * after _SB.PCI0.GFX0.LCD.LCD1._ON gets called has passed
+	 * *and* _STA has been called at least 3 times since.
 	 */
 	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), {
 		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7130"),
 	      }),
+	ENTRY("SYNA7500", "1", ICPU(INTEL_FAM6_HASWELL_ULT), {
+		DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "Venue 11 Pro 7139"),
+	      }),
+
 	/*
 	 * The GPD win BIOS dated 20170221 has disabled the accelerometer, the
 	 * drivers sometimes cause crashes under Windows and this is how the
-- 
cgit v1.2.3


From ad5145164b21eb4fcb091096b1b384a3faecac64 Mon Sep 17 00:00:00 2001
From: Bingbu Cao <bingbu.cao@intel.com>
Date: Tue, 19 Jun 2018 02:01:46 -0400
Subject: media: dt-bindings: Add bindings for AKM ak7375 voice coil lens

Add device tree bindings for AKM ak7375 voice coil lens
driver. This chip is used to drive a lens in a camera module.

Signed-off-by: Tianshu Qiu <tian.shu.qiu@intel.com>
Signed-off-by: Bingbu Cao <bingbu.cao@intel.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/i2c/ak7375.txt | 8 ++++++++
 MAINTAINERS                                            | 8 ++++++++
 2 files changed, 16 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/media/i2c/ak7375.txt

diff --git a/Documentation/devicetree/bindings/media/i2c/ak7375.txt b/Documentation/devicetree/bindings/media/i2c/ak7375.txt
new file mode 100644
index 000000000000..aa3e24b41241
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/ak7375.txt
@@ -0,0 +1,8 @@
+Asahi Kasei Microdevices AK7375 voice coil lens driver
+
+AK7375 is a camera voice coil lens.
+
+Mandatory properties:
+
+- compatible: "asahi-kasei,ak7375"
+- reg: I2C slave address
diff --git a/MAINTAINERS b/MAINTAINERS
index bd147aee7f80..bbd9b9b3d74f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2272,6 +2272,14 @@ L:	linux-leds@vger.kernel.org
 S:	Maintained
 F:	drivers/leds/leds-as3645a.c
 
+ASAHI KASEI AK7375 LENS VOICE COIL DRIVER
+M:	Tianshu Qiu <tian.shu.qiu@intel.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/i2c/ak7375.c
+F:	Documentation/devicetree/bindings/media/i2c/ak7375.txt
+
 ASAHI KASEI AK8974 DRIVER
 M:	Linus Walleij <linus.walleij@linaro.org>
 L:	linux-iio@vger.kernel.org
-- 
cgit v1.2.3


From 4dd3cdb281f7a3200234ed2bcaae79af15f120d2 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Wed, 4 Jul 2018 11:29:09 +0200
Subject: dma-fence: Polish kernel-doc for dma-fence.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- Intro section that links to how this is exposed to userspace.
- Lots more hyperlinks.
- Minor clarifications and style polish

v2: Add misplaced hunk of kerneldoc from a different patch.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Gustavo Padovan <gustavo@padovan.org>
Cc: linux-media@vger.kernel.org
Cc: linaro-mm-sig@lists.linaro.org
Link: https://patchwork.freedesktop.org/patch/msgid/20180704092909.6599-6-daniel.vetter@ffwll.ch
---
 Documentation/driver-api/dma-buf.rst |   6 ++
 drivers/dma-buf/dma-fence.c          | 147 ++++++++++++++++++++++++-----------
 2 files changed, 109 insertions(+), 44 deletions(-)

diff --git a/Documentation/driver-api/dma-buf.rst b/Documentation/driver-api/dma-buf.rst
index dc384f2f7f34..b541e97c7ab1 100644
--- a/Documentation/driver-api/dma-buf.rst
+++ b/Documentation/driver-api/dma-buf.rst
@@ -130,6 +130,12 @@ Reservation Objects
 DMA Fences
 ----------
 
+.. kernel-doc:: drivers/dma-buf/dma-fence.c
+   :doc: DMA fences overview
+
+DMA Fences Functions Reference
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
 .. kernel-doc:: drivers/dma-buf/dma-fence.c
    :export:
 
diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c
index 7a92f85a4cec..1551ca7df394 100644
--- a/drivers/dma-buf/dma-fence.c
+++ b/drivers/dma-buf/dma-fence.c
@@ -38,12 +38,43 @@ EXPORT_TRACEPOINT_SYMBOL(dma_fence_enable_signal);
  */
 static atomic64_t dma_fence_context_counter = ATOMIC64_INIT(0);
 
+/**
+ * DOC: DMA fences overview
+ *
+ * DMA fences, represented by &struct dma_fence, are the kernel internal
+ * synchronization primitive for DMA operations like GPU rendering, video
+ * encoding/decoding, or displaying buffers on a screen.
+ *
+ * A fence is initialized using dma_fence_init() and completed using
+ * dma_fence_signal(). Fences are associated with a context, allocated through
+ * dma_fence_context_alloc(), and all fences on the same context are
+ * fully ordered.
+ *
+ * Since the purposes of fences is to facilitate cross-device and
+ * cross-application synchronization, there's multiple ways to use one:
+ *
+ * - Individual fences can be exposed as a &sync_file, accessed as a file
+ *   descriptor from userspace, created by calling sync_file_create(). This is
+ *   called explicit fencing, since userspace passes around explicit
+ *   synchronization points.
+ *
+ * - Some subsystems also have their own explicit fencing primitives, like
+ *   &drm_syncobj. Compared to &sync_file, a &drm_syncobj allows the underlying
+ *   fence to be updated.
+ *
+ * - Then there's also implicit fencing, where the synchronization points are
+ *   implicitly passed around as part of shared &dma_buf instances. Such
+ *   implicit fences are stored in &struct reservation_object through the
+ *   &dma_buf.resv pointer.
+ */
+
 /**
  * dma_fence_context_alloc - allocate an array of fence contexts
- * @num:	[in]	amount of contexts to allocate
+ * @num: amount of contexts to allocate
  *
- * This function will return the first index of the number of fences allocated.
- * The fence context is used for setting fence->context to a unique number.
+ * This function will return the first index of the number of fence contexts
+ * allocated.  The fence context is used for setting &dma_fence.context to a
+ * unique number by passing the context to dma_fence_init().
  */
 u64 dma_fence_context_alloc(unsigned num)
 {
@@ -59,10 +90,14 @@ EXPORT_SYMBOL(dma_fence_context_alloc);
  * Signal completion for software callbacks on a fence, this will unblock
  * dma_fence_wait() calls and run all the callbacks added with
  * dma_fence_add_callback(). Can be called multiple times, but since a fence
- * can only go from unsignaled to signaled state, it will only be effective
- * the first time.
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time.
+ *
+ * Unlike dma_fence_signal(), this function must be called with &dma_fence.lock
+ * held.
  *
- * Unlike dma_fence_signal, this function must be called with fence->lock held.
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
  */
 int dma_fence_signal_locked(struct dma_fence *fence)
 {
@@ -102,8 +137,11 @@ EXPORT_SYMBOL(dma_fence_signal_locked);
  * Signal completion for software callbacks on a fence, this will unblock
  * dma_fence_wait() calls and run all the callbacks added with
  * dma_fence_add_callback(). Can be called multiple times, but since a fence
- * can only go from unsignaled to signaled state, it will only be effective
- * the first time.
+ * can only go from the unsignaled to the signaled state and not back, it will
+ * only be effective the first time.
+ *
+ * Returns 0 on success and a negative error value when @fence has been
+ * signalled already.
  */
 int dma_fence_signal(struct dma_fence *fence)
 {
@@ -136,9 +174,9 @@ EXPORT_SYMBOL(dma_fence_signal);
 /**
  * dma_fence_wait_timeout - sleep until the fence gets signaled
  * or until timeout elapses
- * @fence:	[in]	the fence to wait on
- * @intr:	[in]	if true, do an interruptible wait
- * @timeout:	[in]	timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
+ * @fence: the fence to wait on
+ * @intr: if true, do an interruptible wait
+ * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
  *
  * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the
  * remaining timeout in jiffies on success. Other error values may be
@@ -148,6 +186,8 @@ EXPORT_SYMBOL(dma_fence_signal);
  * directly or indirectly (buf-mgr between reservation and committing)
  * holds a reference to the fence, otherwise the fence might be
  * freed before return, resulting in undefined behavior.
+ *
+ * See also dma_fence_wait() and dma_fence_wait_any_timeout().
  */
 signed long
 dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
@@ -167,6 +207,13 @@ dma_fence_wait_timeout(struct dma_fence *fence, bool intr, signed long timeout)
 }
 EXPORT_SYMBOL(dma_fence_wait_timeout);
 
+/**
+ * dma_fence_release - default relese function for fences
+ * @kref: &dma_fence.recfount
+ *
+ * This is the default release functions for &dma_fence. Drivers shouldn't call
+ * this directly, but instead call dma_fence_put().
+ */
 void dma_fence_release(struct kref *kref)
 {
 	struct dma_fence *fence =
@@ -184,6 +231,13 @@ void dma_fence_release(struct kref *kref)
 }
 EXPORT_SYMBOL(dma_fence_release);
 
+/**
+ * dma_fence_free - default release function for &dma_fence.
+ * @fence: fence to release
+ *
+ * This is the default implementation for &dma_fence_ops.release. It calls
+ * kfree_rcu() on @fence.
+ */
 void dma_fence_free(struct dma_fence *fence)
 {
 	kfree_rcu(fence, rcu);
@@ -192,10 +246,11 @@ EXPORT_SYMBOL(dma_fence_free);
 
 /**
  * dma_fence_enable_sw_signaling - enable signaling on fence
- * @fence:	[in]	the fence to enable
+ * @fence: the fence to enable
  *
- * this will request for sw signaling to be enabled, to make the fence
- * complete as soon as possible
+ * This will request for sw signaling to be enabled, to make the fence
+ * complete as soon as possible. This calls &dma_fence_ops.enable_signaling
+ * internally.
  */
 void dma_fence_enable_sw_signaling(struct dma_fence *fence)
 {
@@ -220,24 +275,24 @@ EXPORT_SYMBOL(dma_fence_enable_sw_signaling);
 /**
  * dma_fence_add_callback - add a callback to be called when the fence
  * is signaled
- * @fence:	[in]	the fence to wait on
- * @cb:		[in]	the callback to register
- * @func:	[in]	the function to call
+ * @fence: the fence to wait on
+ * @cb: the callback to register
+ * @func: the function to call
  *
- * cb will be initialized by dma_fence_add_callback, no initialization
+ * @cb will be initialized by dma_fence_add_callback(), no initialization
  * by the caller is required. Any number of callbacks can be registered
  * to a fence, but a callback can only be registered to one fence at a time.
  *
  * Note that the callback can be called from an atomic context.  If
  * fence is already signaled, this function will return -ENOENT (and
- * *not* call the callback)
+ * *not* call the callback).
  *
  * Add a software callback to the fence. Same restrictions apply to
- * refcount as it does to dma_fence_wait, however the caller doesn't need to
- * keep a refcount to fence afterwards: when software access is enabled,
- * the creator of the fence is required to keep the fence alive until
- * after it signals with dma_fence_signal. The callback itself can be called
- * from irq context.
+ * refcount as it does to dma_fence_wait(), however the caller doesn't need to
+ * keep a refcount to fence afterward dma_fence_add_callback() has returned:
+ * when software access is enabled, the creator of the fence is required to keep
+ * the fence alive until after it signals with dma_fence_signal(). The callback
+ * itself can be called from irq context.
  *
  * Returns 0 in case of success, -ENOENT if the fence is already signaled
  * and -EINVAL in case of error.
@@ -286,7 +341,7 @@ EXPORT_SYMBOL(dma_fence_add_callback);
 
 /**
  * dma_fence_get_status - returns the status upon completion
- * @fence: [in]	the dma_fence to query
+ * @fence: the dma_fence to query
  *
  * This wraps dma_fence_get_status_locked() to return the error status
  * condition on a signaled fence. See dma_fence_get_status_locked() for more
@@ -311,8 +366,8 @@ EXPORT_SYMBOL(dma_fence_get_status);
 
 /**
  * dma_fence_remove_callback - remove a callback from the signaling list
- * @fence:	[in]	the fence to wait on
- * @cb:		[in]	the callback to remove
+ * @fence: the fence to wait on
+ * @cb: the callback to remove
  *
  * Remove a previously queued callback from the fence. This function returns
  * true if the callback is successfully removed, or false if the fence has
@@ -323,6 +378,9 @@ EXPORT_SYMBOL(dma_fence_get_status);
  * doing, since deadlocks and race conditions could occur all too easily. For
  * this reason, it should only ever be done on hardware lockup recovery,
  * with a reference held to the fence.
+ *
+ * Behaviour is undefined if @cb has not been added to @fence using
+ * dma_fence_add_callback() beforehand.
  */
 bool
 dma_fence_remove_callback(struct dma_fence *fence, struct dma_fence_cb *cb)
@@ -359,9 +417,9 @@ dma_fence_default_wait_cb(struct dma_fence *fence, struct dma_fence_cb *cb)
 /**
  * dma_fence_default_wait - default sleep until the fence gets signaled
  * or until timeout elapses
- * @fence:	[in]	the fence to wait on
- * @intr:	[in]	if true, do an interruptible wait
- * @timeout:	[in]	timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
+ * @fence: the fence to wait on
+ * @intr: if true, do an interruptible wait
+ * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
  *
  * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or the
  * remaining timeout in jiffies on success. If timeout is zero the value one is
@@ -454,12 +512,12 @@ dma_fence_test_signaled_any(struct dma_fence **fences, uint32_t count,
 /**
  * dma_fence_wait_any_timeout - sleep until any fence gets signaled
  * or until timeout elapses
- * @fences:	[in]	array of fences to wait on
- * @count:	[in]	number of fences to wait on
- * @intr:	[in]	if true, do an interruptible wait
- * @timeout:	[in]	timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
- * @idx:       [out]	the first signaled fence index, meaningful only on
- *			positive return
+ * @fences: array of fences to wait on
+ * @count: number of fences to wait on
+ * @intr: if true, do an interruptible wait
+ * @timeout: timeout value in jiffies, or MAX_SCHEDULE_TIMEOUT
+ * @idx: used to store the first signaled fence index, meaningful only on
+ *	positive return
  *
  * Returns -EINVAL on custom fence wait implementation, -ERESTARTSYS if
  * interrupted, 0 if the wait timed out, or the remaining timeout in jiffies
@@ -468,6 +526,8 @@ dma_fence_test_signaled_any(struct dma_fence **fences, uint32_t count,
  * Synchronous waits for the first fence in the array to be signaled. The
  * caller needs to hold a reference to all fences in the array, otherwise a
  * fence might be freed before return, resulting in undefined behavior.
+ *
+ * See also dma_fence_wait() and dma_fence_wait_timeout().
  */
 signed long
 dma_fence_wait_any_timeout(struct dma_fence **fences, uint32_t count,
@@ -540,19 +600,18 @@ EXPORT_SYMBOL(dma_fence_wait_any_timeout);
 
 /**
  * dma_fence_init - Initialize a custom fence.
- * @fence:	[in]	the fence to initialize
- * @ops:	[in]	the dma_fence_ops for operations on this fence
- * @lock:	[in]	the irqsafe spinlock to use for locking this fence
- * @context:	[in]	the execution context this fence is run on
- * @seqno:	[in]	a linear increasing sequence number for this context
+ * @fence: the fence to initialize
+ * @ops: the dma_fence_ops for operations on this fence
+ * @lock: the irqsafe spinlock to use for locking this fence
+ * @context: the execution context this fence is run on
+ * @seqno: a linear increasing sequence number for this context
  *
  * Initializes an allocated fence, the caller doesn't have to keep its
  * refcount after committing with this fence, but it will need to hold a
- * refcount again if dma_fence_ops.enable_signaling gets called. This can
- * be used for other implementing other types of fence.
+ * refcount again if &dma_fence_ops.enable_signaling gets called.
  *
  * context and seqno are used for easy comparison between fences, allowing
- * to check which fence is later by simply using dma_fence_later.
+ * to check which fence is later by simply using dma_fence_later().
  */
 void
 dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
-- 
cgit v1.2.3


From 59b62e7ad0874681dc4f84cac90cc991dc265809 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 4 Jul 2018 11:50:50 +0100
Subject: drivers/perf: Initialise return value in armpmu_request_irqs()

If a PMU doesn't have any IRQs, we should return 0 from
armpmu_request_irqs(), rather than uninitialised stack.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/perf/arm_pmu_platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 971ff336494a..96075cecb0ae 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -160,7 +160,7 @@ static int pmu_parse_irqs(struct arm_pmu *pmu)
 static int armpmu_request_irqs(struct arm_pmu *armpmu)
 {
 	struct pmu_hw_events __percpu *hw_events = armpmu->hw_events;
-	int cpu, err;
+	int cpu, err = 0;
 
 	for_each_cpu(cpu, &armpmu->supported_cpus) {
 		int irq = per_cpu(hw_events->irq, cpu);
-- 
cgit v1.2.3


From 90ee26fb2f50e1e57f9d957a1799af1bcafd9671 Mon Sep 17 00:00:00 2001
From: Bingbu Cao <bingbu.cao@intel.com>
Date: Tue, 19 Jun 2018 02:01:47 -0400
Subject: media: ak7375: Add ak7375 lens voice coil driver

Add a v4l2 sub-device driver for the ak7375 lens voice coil.
This is a voice coil module using the i2c bus to control the
focus position.

ak7375 can write multiple bytes of data at a time. If more
data is received instead of the stop condition after receiving
one byte of data, the address inside the chip is automatically
incremented and the data is written into the next address.

The ak7375 can control the position with 12 bits value and
consists of two 8 bit registers show as below:
register 0x00(AK7375_REG_POSITION):
    +---+---+---+---+---+---+---+---+
    |D11|D10|D09|D08|D07|D06|D05|D04|
    +---+---+---+---+---+---+---+---+
register 0x01:
    +---+---+---+---+---+---+---+---+
    |D03|D02|D01|D00|---|---|---|---|
    +---+---+---+---+---+---+---+---+

This driver support :
    - set ak7375 to standby mode once suspend and
      turn it back to active if resume
    - set the position via V4L2_CID_FOCUS_ABSOLUTE ctrl

[Sakari Ailus: Rename val as ret in probe, drop redundant error message]

Signed-off-by: Tianshu Qiu <tian.shu.qiu@intel.com>
Signed-off-by: Bingbu Cao <bingbu.cao@intel.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/Kconfig  |  10 ++
 drivers/media/i2c/Makefile |   1 +
 drivers/media/i2c/ak7375.c | 292 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 303 insertions(+)
 create mode 100644 drivers/media/i2c/ak7375.c

diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 1cf91bce2613..8669853e1361 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -326,6 +326,16 @@ config VIDEO_AD5820
 	  This is a driver for the AD5820 camera lens voice coil.
 	  It is used for example in Nokia N900 (RX-51).
 
+config VIDEO_AK7375
+	tristate "AK7375 lens voice coil support"
+	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
+	depends on VIDEO_V4L2_SUBDEV_API
+	help
+	  This is a driver for the AK7375 camera lens voice coil.
+	  AK7375 is a 12 bit DAC with 120mA output current sink
+	  capability. This is designed for linear control of
+	  voice coil motors, controlled via I2C serial interface.
+
 config VIDEO_DW9714
 	tristate "DW9714 lens voice coil support"
 	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index 1d994658a9d4..837c428339df 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_VIDEO_SAA7127) += saa7127.o
 obj-$(CONFIG_VIDEO_SAA7185) += saa7185.o
 obj-$(CONFIG_VIDEO_SAA6752HS) += saa6752hs.o
 obj-$(CONFIG_VIDEO_AD5820)  += ad5820.o
+obj-$(CONFIG_VIDEO_AK7375)  += ak7375.o
 obj-$(CONFIG_VIDEO_DW9714)  += dw9714.o
 obj-$(CONFIG_VIDEO_DW9807)  += dw9807.o
 obj-$(CONFIG_VIDEO_ADV7170) += adv7170.o
diff --git a/drivers/media/i2c/ak7375.c b/drivers/media/i2c/ak7375.c
new file mode 100644
index 000000000000..7b14b11605ca
--- /dev/null
+++ b/drivers/media/i2c/ak7375.c
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Intel Corporation
+
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+
+#define AK7375_MAX_FOCUS_POS	4095
+/*
+ * This sets the minimum granularity for the focus positions.
+ * A value of 1 gives maximum accuracy for a desired focus position
+ */
+#define AK7375_FOCUS_STEPS	1
+/*
+ * This acts as the minimum granularity of lens movement.
+ * Keep this value power of 2, so the control steps can be
+ * uniformly adjusted for gradual lens movement, with desired
+ * number of control steps.
+ */
+#define AK7375_CTRL_STEPS	64
+#define AK7375_CTRL_DELAY_US	1000
+
+#define AK7375_REG_POSITION	0x0
+#define AK7375_REG_CONT		0x2
+#define AK7375_MODE_ACTIVE	0x0
+#define AK7375_MODE_STANDBY	0x40
+
+/* ak7375 device structure */
+struct ak7375_device {
+	struct v4l2_ctrl_handler ctrls_vcm;
+	struct v4l2_subdev sd;
+	struct v4l2_ctrl *focus;
+	/* active or standby mode */
+	bool active;
+};
+
+static inline struct ak7375_device *to_ak7375_vcm(struct v4l2_ctrl *ctrl)
+{
+	return container_of(ctrl->handler, struct ak7375_device, ctrls_vcm);
+}
+
+static inline struct ak7375_device *sd_to_ak7375_vcm(struct v4l2_subdev *subdev)
+{
+	return container_of(subdev, struct ak7375_device, sd);
+}
+
+static int ak7375_i2c_write(struct ak7375_device *ak7375,
+	u8 addr, u16 data, u8 size)
+{
+	struct i2c_client *client = v4l2_get_subdevdata(&ak7375->sd);
+	u8 buf[3];
+	int ret;
+
+	if (size != 1 && size != 2)
+		return -EINVAL;
+	buf[0] = addr;
+	buf[size] = data & 0xff;
+	if (size == 2)
+		buf[1] = (data >> 8) & 0xff;
+	ret = i2c_master_send(client, (const char *)buf, size + 1);
+	if (ret < 0)
+		return ret;
+	if (ret != size + 1)
+		return -EIO;
+
+	return 0;
+}
+
+static int ak7375_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct ak7375_device *dev_vcm = to_ak7375_vcm(ctrl);
+
+	if (ctrl->id == V4L2_CID_FOCUS_ABSOLUTE)
+		return ak7375_i2c_write(dev_vcm, AK7375_REG_POSITION,
+					ctrl->val << 4, 2);
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops ak7375_vcm_ctrl_ops = {
+	.s_ctrl = ak7375_set_ctrl,
+};
+
+static int ak7375_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	int ret;
+
+	ret = pm_runtime_get_sync(sd->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(sd->dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ak7375_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	pm_runtime_put(sd->dev);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_internal_ops ak7375_int_ops = {
+	.open = ak7375_open,
+	.close = ak7375_close,
+};
+
+static const struct v4l2_subdev_ops ak7375_ops = { };
+
+static void ak7375_subdev_cleanup(struct ak7375_device *ak7375_dev)
+{
+	v4l2_async_unregister_subdev(&ak7375_dev->sd);
+	v4l2_ctrl_handler_free(&ak7375_dev->ctrls_vcm);
+	media_entity_cleanup(&ak7375_dev->sd.entity);
+}
+
+static int ak7375_init_controls(struct ak7375_device *dev_vcm)
+{
+	struct v4l2_ctrl_handler *hdl = &dev_vcm->ctrls_vcm;
+	const struct v4l2_ctrl_ops *ops = &ak7375_vcm_ctrl_ops;
+
+	v4l2_ctrl_handler_init(hdl, 1);
+
+	dev_vcm->focus = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FOCUS_ABSOLUTE,
+		0, AK7375_MAX_FOCUS_POS, AK7375_FOCUS_STEPS, 0);
+
+	if (hdl->error)
+		dev_err(dev_vcm->sd.dev, "%s fail error: 0x%x\n",
+			__func__, hdl->error);
+	dev_vcm->sd.ctrl_handler = hdl;
+
+	return hdl->error;
+}
+
+static int ak7375_probe(struct i2c_client *client)
+{
+	struct ak7375_device *ak7375_dev;
+	int ret;
+
+	ak7375_dev = devm_kzalloc(&client->dev, sizeof(*ak7375_dev),
+				  GFP_KERNEL);
+	if (!ak7375_dev)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&ak7375_dev->sd, client, &ak7375_ops);
+	ak7375_dev->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	ak7375_dev->sd.internal_ops = &ak7375_int_ops;
+	ak7375_dev->sd.entity.function = MEDIA_ENT_F_LENS;
+
+	ret = ak7375_init_controls(ak7375_dev);
+	if (ret)
+		goto err_cleanup;
+
+	ret = media_entity_pads_init(&ak7375_dev->sd.entity, 0, NULL);
+	if (ret < 0)
+		goto err_cleanup;
+
+	ret = v4l2_async_register_subdev(&ak7375_dev->sd);
+	if (ret < 0)
+		goto err_cleanup;
+
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_enable(&client->dev);
+	pm_runtime_idle(&client->dev);
+
+	return 0;
+
+err_cleanup:
+	v4l2_ctrl_handler_free(&ak7375_dev->ctrls_vcm);
+	media_entity_cleanup(&ak7375_dev->sd.entity);
+
+	return ret;
+}
+
+static int ak7375_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ak7375_device *ak7375_dev = sd_to_ak7375_vcm(sd);
+
+	ak7375_subdev_cleanup(ak7375_dev);
+	pm_runtime_disable(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position, so it consumes least current
+ * The lens position is gradually moved in units of AK7375_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int __maybe_unused ak7375_vcm_suspend(struct device *dev)
+{
+
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ak7375_device *ak7375_dev = sd_to_ak7375_vcm(sd);
+	int ret, val;
+
+	if (!ak7375_dev->active)
+		return 0;
+
+	for (val = ak7375_dev->focus->val & ~(AK7375_CTRL_STEPS - 1);
+	     val >= 0; val -= AK7375_CTRL_STEPS) {
+		ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_POSITION,
+				       val << 4, 2);
+		if (ret)
+			dev_err_once(dev, "%s I2C failure: %d\n",
+				     __func__, ret);
+		usleep_range(AK7375_CTRL_DELAY_US, AK7375_CTRL_DELAY_US + 10);
+	}
+
+	ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_CONT,
+			       AK7375_MODE_STANDBY, 1);
+	if (ret)
+		dev_err(dev, "%s I2C failure: %d\n", __func__, ret);
+
+	ak7375_dev->active = false;
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position to the value set by the user
+ * through v4l2_ctrl_ops s_ctrl handler
+ * The lens position is gradually moved in units of AK7375_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int __maybe_unused ak7375_vcm_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ak7375_device *ak7375_dev = sd_to_ak7375_vcm(sd);
+	int ret, val;
+
+	if (ak7375_dev->active)
+		return 0;
+
+	ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_CONT,
+		AK7375_MODE_ACTIVE, 1);
+	if (ret) {
+		dev_err(dev, "%s I2C failure: %d\n", __func__, ret);
+		return ret;
+	}
+
+	for (val = ak7375_dev->focus->val % AK7375_CTRL_STEPS;
+	     val <= ak7375_dev->focus->val;
+	     val += AK7375_CTRL_STEPS) {
+		ret = ak7375_i2c_write(ak7375_dev, AK7375_REG_POSITION,
+				       val << 4, 2);
+		if (ret)
+			dev_err_ratelimited(dev, "%s I2C failure: %d\n",
+						__func__, ret);
+		usleep_range(AK7375_CTRL_DELAY_US, AK7375_CTRL_DELAY_US + 10);
+	}
+
+	ak7375_dev->active = true;
+
+	return 0;
+}
+
+static const struct of_device_id ak7375_of_table[] = {
+	{ .compatible = "asahi-kasei,ak7375" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, ak7375_of_table);
+
+static const struct dev_pm_ops ak7375_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ak7375_vcm_suspend, ak7375_vcm_resume)
+	SET_RUNTIME_PM_OPS(ak7375_vcm_suspend, ak7375_vcm_resume, NULL)
+};
+
+static struct i2c_driver ak7375_i2c_driver = {
+	.driver = {
+		.name = "ak7375",
+		.pm = &ak7375_pm_ops,
+		.of_match_table = ak7375_of_table,
+	},
+	.probe_new = ak7375_probe,
+	.remove = ak7375_remove,
+};
+module_i2c_driver(ak7375_i2c_driver);
+
+MODULE_AUTHOR("Tianshu Qiu <tian.shu.qiu@intel.com>");
+MODULE_AUTHOR("Bingbu Cao <bingbu.cao@intel.com>");
+MODULE_DESCRIPTION("AK7375 VCM driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 438ac1fd5e1e132782795ba474b97fffbc79bbd5 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Mon, 11 Jun 2018 07:35:32 -0400
Subject: media: imx274: initialize format before v4l2 controls

The current probe function calls v4l2_ctrl_handler_setup() before
initializing the format info. This triggers call paths such as:
imx274_probe -> v4l2_ctrl_handler_setup -> imx274_s_ctrl ->
imx274_set_exposure, where priv->mode_index is accessed before being
assigned.

This is wrong but does not trigger a visible bug because priv is
zero-initialized and 0 is the default value for priv->mode_index. But
this would become a crash in follow-up commits when mode_index is
replaced by a pointer that must always be valid.

Fix the bug before it shows up by initializing struct members early.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 63fb94e7da37..8a8a11b8d75d 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -1632,6 +1632,16 @@ static int imx274_probe(struct i2c_client *client,
 
 	mutex_init(&imx274->lock);
 
+	/* initialize format */
+	imx274->mode_index = IMX274_MODE_3840X2160;
+	imx274->format.width = imx274_formats[0].size.width;
+	imx274->format.height = imx274_formats[0].size.height;
+	imx274->format.field = V4L2_FIELD_NONE;
+	imx274->format.code = MEDIA_BUS_FMT_SRGGB10_1X10;
+	imx274->format.colorspace = V4L2_COLORSPACE_SRGB;
+	imx274->frame_interval.numerator = 1;
+	imx274->frame_interval.denominator = IMX274_DEF_FRAME_RATE;
+
 	/* initialize regmap */
 	imx274->regmap = devm_regmap_init_i2c(client, &imx274_regmap_config);
 	if (IS_ERR(imx274->regmap)) {
@@ -1720,16 +1730,6 @@ static int imx274_probe(struct i2c_client *client,
 		goto err_ctrls;
 	}
 
-	/* initialize format */
-	imx274->mode_index = IMX274_MODE_3840X2160;
-	imx274->format.width = imx274_formats[0].size.width;
-	imx274->format.height = imx274_formats[0].size.height;
-	imx274->format.field = V4L2_FIELD_NONE;
-	imx274->format.code = MEDIA_BUS_FMT_SRGGB10_1X10;
-	imx274->format.colorspace = V4L2_COLORSPACE_SRGB;
-	imx274->frame_interval.numerator = 1;
-	imx274->frame_interval.denominator = IMX274_DEF_FRAME_RATE;
-
 	/* load default control values */
 	ret = imx274_load_default(imx274);
 	if (ret) {
-- 
cgit v1.2.3


From 96a2c731a4e661470d3a0a39d5efc792a22c7bba Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Mon, 11 Jun 2018 07:35:33 -0400
Subject: media: imx274: consolidate per-mode data in imx274_frmfmt

Data about the implemented readout modes is partially stored in
imx274_formats[], the rest is scattered in several arrays. The latter
are then accessed using the mode index, e.g.:

  min_frame_len[priv->mode_index]

Consolidate all these data in imx274_formats[], and store a pointer to
the selected mode (i.e. imx274_formats[priv->mode_index]) in the main
device struct. This way code to use these data becomes more readable,
e.g.:

  priv->mode->min_frame_len

This removes lots of scaffolding code and keeps data about each mode
in a unique place.

Also remove a parameter to imx274_mode_regs() that is now unused.

While this adds the mode pointer to the device struct, it does not
remove the mode_index from it because mode_index is still used in two
dev_dbg() calls.  This will be handled in a follow-up commit.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 139 +++++++++++++++++++++------------------------
 1 file changed, 66 insertions(+), 73 deletions(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 8a8a11b8d75d..2ec31ae4e60d 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -147,10 +147,28 @@ enum imx274_mode {
 };
 
 /*
- * imx274 format related structure
+ * Parameters for each imx274 readout mode.
+ *
+ * These are the values to configure the sensor in one of the
+ * implemented modes.
+ *
+ * @size: recommended recording pixels
+ * @init_regs: registers to initialize the mode
+ * @min_frame_len: Minimum frame length for each mode (see "Frame Rate
+ *                 Adjustment (CSI-2)" in the datasheet)
+ * @min_SHR: Minimum SHR register value (see "Shutter Setting (CSI-2)" in the
+ *           datasheet)
+ * @max_fps: Maximum frames per second
+ * @nocpiop: Number of clocks per internal offset period (see "Integration Time
+ *           in Each Readout Drive Mode (CSI-2)" in the datasheet)
  */
 struct imx274_frmfmt {
 	struct v4l2_frmsize_discrete size;
+	const struct reg_8 *init_regs;
+	int min_frame_len;
+	int min_SHR;
+	int max_fps;
+	int nocpiop;
 };
 
 /*
@@ -476,58 +494,35 @@ static const struct reg_8 imx274_tp_regs[] = {
 	{IMX274_TABLE_END, 0x00}
 };
 
-static const struct reg_8 *mode_table[] = {
-	[IMX274_MODE_3840X2160]		= imx274_mode1_3840x2160_raw10,
-	[IMX274_MODE_1920X1080]		= imx274_mode3_1920x1080_raw10,
-	[IMX274_MODE_1280X720]		= imx274_mode5_1280x720_raw10,
-};
-
-/*
- * imx274 format related structure
- */
+/* nocpiop happens to be the same number for the implemented modes */
 static const struct imx274_frmfmt imx274_formats[] = {
-	{ {3840, 2160} },
-	{ {1920, 1080} },
-	{ {1280,  720} },
-};
-
-/*
- * minimal frame length for each mode
- * refer to datasheet section "Frame Rate Adjustment (CSI-2)"
- */
-static const int min_frame_len[] = {
-	4550, /* mode 1, 4K */
-	2310, /* mode 3, 1080p */
-	2310 /* mode 5, 720p */
-};
-
-/*
- * minimal numbers of SHR register
- * refer to datasheet table "Shutter Setting (CSI-2)"
- */
-static const int min_SHR[] = {
-	12, /* mode 1, 4K */
-	8, /* mode 3, 1080p */
-	8 /* mode 5, 720p */
-};
-
-static const int max_frame_rate[] = {
-	60, /* mode 1 , 4K */
-	120, /* mode 3, 1080p */
-	120 /* mode 5, 720p */
-};
-
-/*
- * Number of clocks per internal offset period
- * a constant based on mode
- * refer to section "Integration Time in Each Readout Drive Mode (CSI-2)"
- * in the datasheet
- * for the implemented 3 modes, it happens to be the same number
- */
-static const int nocpiop[] = {
-	112, /* mode 1 , 4K */
-	112, /* mode 3, 1080p */
-	112 /* mode 5, 720p */
+	{
+		/* mode 1, 4K */
+		.size = {3840, 2160},
+		.init_regs = imx274_mode1_3840x2160_raw10,
+		.min_frame_len = 4550,
+		.min_SHR = 12,
+		.max_fps = 60,
+		.nocpiop = 112,
+	},
+	{
+		/* mode 3, 1080p */
+		.size = {1920, 1080},
+		.init_regs = imx274_mode3_1920x1080_raw10,
+		.min_frame_len = 2310,
+		.min_SHR = 8,
+		.max_fps = 120,
+		.nocpiop = 112,
+	},
+	{
+		/* mode 5, 720p */
+		.size = {1280, 720},
+		.init_regs = imx274_mode5_1280x720_raw10,
+		.min_frame_len = 2310,
+		.min_SHR = 8,
+		.max_fps = 120,
+		.nocpiop = 112,
+	},
 };
 
 /*
@@ -557,6 +552,8 @@ struct imx274_ctrls {
  * @regmap: Pointer to regmap structure
  * @reset_gpio: Pointer to reset gpio
  * @lock: Mutex structure
+ * @mode: Parameters for the selected readout mode
+ *        (points to imx274_formats[mode_index])
  * @mode_index: Resolution mode index
  */
 struct stimx274 {
@@ -569,6 +566,7 @@ struct stimx274 {
 	struct regmap *regmap;
 	struct gpio_desc *reset_gpio;
 	struct mutex lock; /* mutex lock for operations */
+	const struct imx274_frmfmt *mode;
 	u32 mode_index;
 };
 
@@ -704,18 +702,12 @@ static int imx274_write_table(struct stimx274 *priv, const struct reg_8 table[])
 }
 
 /*
- * imx274_mode_regs - Function for set mode registers per mode index
+ * Set mode registers to start stream.
  * @priv: Pointer to device structure
- * @mode: Mode index value
- *
- * This is used to start steam per mode index.
- * mode = 0, start stream for sensor Mode 1: 4K/raw10
- * mode = 1, start stream for sensor Mode 3: 1080p/raw10
- * mode = 2, start stream for sensor Mode 5: 720p/raw10
  *
  * Return: 0 on success, errors otherwise
  */
-static int imx274_mode_regs(struct stimx274 *priv, int mode)
+static int imx274_mode_regs(struct stimx274 *priv)
 {
 	int err = 0;
 
@@ -727,7 +719,7 @@ static int imx274_mode_regs(struct stimx274 *priv, int mode)
 	if (err)
 		return err;
 
-	err = imx274_write_table(priv, mode_table[mode]);
+	err = imx274_write_table(priv, priv->mode->init_regs);
 
 	return err;
 }
@@ -889,6 +881,7 @@ static int imx274_set_fmt(struct v4l2_subdev *sd,
 	}
 
 	imx274->mode_index = index;
+	imx274->mode = &imx274_formats[index];
 
 	if (fmt->width > IMX274_MAX_WIDTH)
 		fmt->width = IMX274_MAX_WIDTH;
@@ -1042,7 +1035,7 @@ static int imx274_s_stream(struct v4l2_subdev *sd, int on)
 
 	if (on) {
 		/* load mode registers */
-		ret = imx274_mode_regs(imx274, imx274->mode_index);
+		ret = imx274_mode_regs(imx274);
 		if (ret)
 			goto fail;
 
@@ -1146,14 +1139,14 @@ static int imx274_clamp_coarse_time(struct stimx274 *priv, u32 *val,
 	if (err)
 		return err;
 
-	if (*frame_length < min_frame_len[priv->mode_index])
-		*frame_length = min_frame_len[priv->mode_index];
+	if (*frame_length < priv->mode->min_frame_len)
+		*frame_length =  priv->mode->min_frame_len;
 
 	*val = *frame_length - *val; /* convert to raw shr */
 	if (*val > *frame_length - IMX274_SHR_LIMIT_CONST)
 		*val = *frame_length - IMX274_SHR_LIMIT_CONST;
-	else if (*val < min_SHR[priv->mode_index])
-		*val = min_SHR[priv->mode_index];
+	else if (*val < priv->mode->min_SHR)
+		*val = priv->mode->min_SHR;
 
 	return 0;
 }
@@ -1365,7 +1358,7 @@ static int imx274_set_exposure(struct stimx274 *priv, int val)
 	}
 
 	coarse_time = (IMX274_PIXCLK_CONST1 / IMX274_PIXCLK_CONST2 * val
-			- nocpiop[priv->mode_index]) / hmax;
+			- priv->mode->nocpiop) / hmax;
 
 	/* step 2: convert exposure_time into SHR value */
 
@@ -1375,7 +1368,7 @@ static int imx274_set_exposure(struct stimx274 *priv, int val)
 		goto fail;
 
 	priv->ctrls.exposure->val =
-			(coarse_time * hmax + nocpiop[priv->mode_index])
+			(coarse_time * hmax + priv->mode->nocpiop)
 			/ (IMX274_PIXCLK_CONST1 / IMX274_PIXCLK_CONST2);
 
 	dev_dbg(&priv->client->dev,
@@ -1529,10 +1522,9 @@ static int imx274_set_frame_interval(struct stimx274 *priv,
 				/ frame_interval.numerator);
 
 	/* boundary check */
-	if (req_frame_rate > max_frame_rate[priv->mode_index]) {
+	if (req_frame_rate > priv->mode->max_fps) {
 		frame_interval.numerator = 1;
-		frame_interval.denominator =
-					max_frame_rate[priv->mode_index];
+		frame_interval.denominator = priv->mode->max_fps;
 	} else if (req_frame_rate < IMX274_MIN_FRAME_RATE) {
 		frame_interval.numerator = 1;
 		frame_interval.denominator = IMX274_MIN_FRAME_RATE;
@@ -1634,8 +1626,9 @@ static int imx274_probe(struct i2c_client *client,
 
 	/* initialize format */
 	imx274->mode_index = IMX274_MODE_3840X2160;
-	imx274->format.width = imx274_formats[0].size.width;
-	imx274->format.height = imx274_formats[0].size.height;
+	imx274->mode = &imx274_formats[imx274->mode_index];
+	imx274->format.width = imx274->mode->size.width;
+	imx274->format.height = imx274->mode->size.height;
 	imx274->format.field = V4L2_FIELD_NONE;
 	imx274->format.code = MEDIA_BUS_FMT_SRGGB10_1X10;
 	imx274->format.colorspace = V4L2_COLORSPACE_SRGB;
-- 
cgit v1.2.3


From 4317322d5a10467e75cfb5b12e13e5e6f3261b25 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Mon, 11 Jun 2018 07:35:34 -0400
Subject: media: imx274: get rid of mode_index

After restructuring struct imx274_frmfmt, the mode_index field is
still in use only for two dev_dbg() calls in imx274_s_stream(). Let's
remove it and avoid duplicated information.

Replacing the first usage requires some rather annoying but trivial
pointer math. The other one can be removed entirely since it would
print the same value anyway.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 2ec31ae4e60d..f075715ffced 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -553,8 +553,6 @@ struct imx274_ctrls {
  * @reset_gpio: Pointer to reset gpio
  * @lock: Mutex structure
  * @mode: Parameters for the selected readout mode
- *        (points to imx274_formats[mode_index])
- * @mode_index: Resolution mode index
  */
 struct stimx274 {
 	struct v4l2_subdev sd;
@@ -567,7 +565,6 @@ struct stimx274 {
 	struct gpio_desc *reset_gpio;
 	struct mutex lock; /* mutex lock for operations */
 	const struct imx274_frmfmt *mode;
-	u32 mode_index;
 };
 
 /*
@@ -880,7 +877,6 @@ static int imx274_set_fmt(struct v4l2_subdev *sd,
 		index = 0;
 	}
 
-	imx274->mode_index = index;
 	imx274->mode = &imx274_formats[index];
 
 	if (fmt->width > IMX274_MAX_WIDTH)
@@ -1028,8 +1024,9 @@ static int imx274_s_stream(struct v4l2_subdev *sd, int on)
 	struct stimx274 *imx274 = to_imx274(sd);
 	int ret = 0;
 
-	dev_dbg(&imx274->client->dev, "%s : %s, mode index = %d\n", __func__,
-		on ? "Stream Start" : "Stream Stop", imx274->mode_index);
+	dev_dbg(&imx274->client->dev, "%s : %s, mode index = %td\n", __func__,
+		on ? "Stream Start" : "Stream Stop",
+		imx274->mode - &imx274_formats[0]);
 
 	mutex_lock(&imx274->lock);
 
@@ -1068,8 +1065,7 @@ static int imx274_s_stream(struct v4l2_subdev *sd, int on)
 	}
 
 	mutex_unlock(&imx274->lock);
-	dev_dbg(&imx274->client->dev,
-		"%s : Done: mode = %d\n", __func__, imx274->mode_index);
+	dev_dbg(&imx274->client->dev, "%s : Done\n", __func__);
 	return 0;
 
 fail:
@@ -1625,8 +1621,7 @@ static int imx274_probe(struct i2c_client *client,
 	mutex_init(&imx274->lock);
 
 	/* initialize format */
-	imx274->mode_index = IMX274_MODE_3840X2160;
-	imx274->mode = &imx274_formats[imx274->mode_index];
+	imx274->mode = &imx274_formats[IMX274_MODE_3840X2160];
 	imx274->format.width = imx274->mode->size.width;
 	imx274->format.height = imx274->mode->size.height;
 	imx274->format.field = V4L2_FIELD_NONE;
-- 
cgit v1.2.3


From 0b4c9553b135a511f3c5c565ea2b48e801a5f81f Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Mon, 11 Jun 2018 07:35:35 -0400
Subject: media: imx274: actually use IMX274_DEFAULT_MODE

IMX274_DEFAULT_MODE is defined but not used. Start using it, so the
default can be more easily changed without digging into the code.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index f075715ffced..ceeec97cd330 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -1621,7 +1621,7 @@ static int imx274_probe(struct i2c_client *client,
 	mutex_init(&imx274->lock);
 
 	/* initialize format */
-	imx274->mode = &imx274_formats[IMX274_MODE_3840X2160];
+	imx274->mode = &imx274_formats[IMX274_DEFAULT_MODE];
 	imx274->format.width = imx274->mode->size.width;
 	imx274->format.height = imx274->mode->size.height;
 	imx274->format.field = V4L2_FIELD_NONE;
-- 
cgit v1.2.3


From 7ff67863c690fbe1e10c70cefbb718b36c155a32 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Mon, 11 Jun 2018 07:35:36 -0400
Subject: media: imx274: simplify imx274_write_table()

imx274_write_table() is a mere wrapper (and the only user) to
imx274_regmap_util_write_table_8(). Remove this useless indirection by
merging the two functions into one.

Also get rid of the wait_ms_addr and end_addr parameters since it does
not make any sense to give them any values other than
IMX274_TABLE_WAIT_MS and IMX274_TABLE_END.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 28 ++++++++++------------------
 1 file changed, 10 insertions(+), 18 deletions(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index ceeec97cd330..48343c2ade83 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -597,20 +597,18 @@ static inline struct stimx274 *to_imx274(struct v4l2_subdev *sd)
 }
 
 /*
- * imx274_regmap_util_write_table_8 - Function for writing register table
- * @regmap: Pointer to device reg map structure
- * @table: Table containing register values
- * @wait_ms_addr: Flag for performing delay
- * @end_addr: Flag for incating end of table
+ * Writing a register table
+ *
+ * @priv: Pointer to device
+ * @table: Table containing register values (with optional delays)
  *
  * This is used to write register table into sensor's reg map.
  *
  * Return: 0 on success, errors otherwise
  */
-static int imx274_regmap_util_write_table_8(struct regmap *regmap,
-					    const struct reg_8 table[],
-					    u16 wait_ms_addr, u16 end_addr)
+static int imx274_write_table(struct stimx274 *priv, const struct reg_8 table[])
 {
+	struct regmap *regmap = priv->regmap;
 	int err = 0;
 	const struct reg_8 *next;
 	u8 val;
@@ -622,8 +620,8 @@ static int imx274_regmap_util_write_table_8(struct regmap *regmap,
 
 	for (next = table;; next++) {
 		if ((next->addr != range_start + range_count) ||
-		    (next->addr == end_addr) ||
-		    (next->addr == wait_ms_addr) ||
+		    (next->addr == IMX274_TABLE_END) ||
+		    (next->addr == IMX274_TABLE_WAIT_MS) ||
 		    (range_count == max_range_vals)) {
 			if (range_count == 1)
 				err = regmap_write(regmap,
@@ -642,10 +640,10 @@ static int imx274_regmap_util_write_table_8(struct regmap *regmap,
 			range_count = 0;
 
 			/* Handle special address values */
-			if (next->addr == end_addr)
+			if (next->addr == IMX274_TABLE_END)
 				break;
 
-			if (next->addr == wait_ms_addr) {
+			if (next->addr == IMX274_TABLE_WAIT_MS) {
 				msleep_range(next->val);
 				continue;
 			}
@@ -692,12 +690,6 @@ static inline int imx274_write_reg(struct stimx274 *priv, u16 addr, u8 val)
 	return err;
 }
 
-static int imx274_write_table(struct stimx274 *priv, const struct reg_8 table[])
-{
-	return imx274_regmap_util_write_table_8(priv->regmap,
-		table, IMX274_TABLE_WAIT_MS, IMX274_TABLE_END);
-}
-
 /*
  * Set mode registers to start stream.
  * @priv: Pointer to device structure
-- 
cgit v1.2.3


From 19d38b235b88e0d28e40fb091b52fc10050e0d5e Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Mon, 11 Jun 2018 07:35:38 -0400
Subject: media: imx274: fix typo

pd -> pad

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 48343c2ade83..edca63eaea9b 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -544,7 +544,7 @@ struct imx274_ctrls {
 /*
  * struct stim274 - imx274 device structure
  * @sd: V4L2 subdevice structure
- * @pd: Media pad structure
+ * @pad: Media pad structure
  * @client: Pointer to I2C client
  * @ctrls: imx274 control structure
  * @format: V4L2 media bus frame format structure
-- 
cgit v1.2.3


From d862bc08ffcb45316962a4d59c6d4ffb51f9dbfa Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Fri, 15 Jun 2018 15:07:21 -0400
Subject: media: v4l2-ioctl.c: use correct vb2_queue lock for m2m devices

For m2m devices the vdev->queue lock was always taken instead of the
lock for the specific capture or output queue. Now that we pushed
the locking down into __video_do_ioctl() we can pick the correct
lock and potentially improve the performance of m2m devices.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-ioctl.c | 56 ++++++++++++++++++++++++++++++++++--
 1 file changed, 54 insertions(+), 2 deletions(-)

diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index eeed14468a17..01670567641a 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -29,6 +29,7 @@
 #include <media/v4l2-device.h>
 #include <media/videobuf2-v4l2.h>
 #include <media/v4l2-mc.h>
+#include <media/v4l2-mem2mem.h>
 
 #include <trace/events/v4l2.h>
 
@@ -2670,11 +2671,62 @@ static bool v4l2_is_known_ioctl(unsigned int cmd)
 	return v4l2_ioctls[_IOC_NR(cmd)].ioctl == cmd;
 }
 
+#if IS_ENABLED(CONFIG_V4L2_MEM2MEM_DEV)
+static bool v4l2_ioctl_m2m_queue_is_output(unsigned int cmd, void *arg)
+{
+	switch (cmd) {
+	case VIDIOC_CREATE_BUFS: {
+		struct v4l2_create_buffers *cbufs = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(cbufs->format.type);
+	}
+	case VIDIOC_REQBUFS: {
+		struct v4l2_requestbuffers *rbufs = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(rbufs->type);
+	}
+	case VIDIOC_QBUF:
+	case VIDIOC_DQBUF:
+	case VIDIOC_QUERYBUF:
+	case VIDIOC_PREPARE_BUF: {
+		struct v4l2_buffer *buf = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(buf->type);
+	}
+	case VIDIOC_EXPBUF: {
+		struct v4l2_exportbuffer *expbuf = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(expbuf->type);
+	}
+	case VIDIOC_STREAMON:
+	case VIDIOC_STREAMOFF: {
+		int *type = arg;
+
+		return V4L2_TYPE_IS_OUTPUT(*type);
+	}
+	default:
+		return false;
+	}
+}
+#endif
+
 static struct mutex *v4l2_ioctl_get_lock(struct video_device *vdev,
-					 unsigned int cmd)
+					 struct v4l2_fh *vfh, unsigned int cmd,
+					 void *arg)
 {
 	if (_IOC_NR(cmd) >= V4L2_IOCTLS)
 		return vdev->lock;
+#if IS_ENABLED(CONFIG_V4L2_MEM2MEM_DEV)
+	if (vfh && vfh->m2m_ctx &&
+	    (v4l2_ioctls[_IOC_NR(cmd)].flags & INFO_FL_QUEUE)) {
+		bool is_output = v4l2_ioctl_m2m_queue_is_output(cmd, arg);
+		struct v4l2_m2m_queue_ctx *ctx = is_output ?
+			&vfh->m2m_ctx->out_q_ctx : &vfh->m2m_ctx->cap_q_ctx;
+
+		if (ctx->q.lock)
+			return ctx->q.lock;
+	}
+#endif
 	if (vdev->queue && vdev->queue->lock &&
 			(v4l2_ioctls[_IOC_NR(cmd)].flags & INFO_FL_QUEUE))
 		return vdev->queue->lock;
@@ -2741,7 +2793,7 @@ static long __video_do_ioctl(struct file *file,
 	if (test_bit(V4L2_FL_USES_V4L2_FH, &vfd->flags))
 		vfh = file->private_data;
 
-	lock = v4l2_ioctl_get_lock(vfd, cmd);
+	lock = v4l2_ioctl_get_lock(vfd, vfh, cmd, arg);
 
 	if (lock && mutex_lock_interruptible(lock))
 		return -ERESTARTSYS;
-- 
cgit v1.2.3


From cd63c0288fd760ce7de247fba618e2bbcfc0c35c Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:22 -0400
Subject: media: sta2x11: Add video_device and vb2_queue locks

Currently, this driver does not serialize its video4linux
ioctls, which is a bug, as race conditions might appear.

In addition, video_device and vb2_queue locks are now both
mandatory. Add them, and implement wait_prepare and
wait_finish.

To stay on the safe side, this commit uses a single mutex
for both locks. Better latency can be obtained by separating
these if needed.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/sta2x11/sta2x11_vip.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c
index 069c4a853346..da2b2a2292d0 100644
--- a/drivers/media/pci/sta2x11/sta2x11_vip.c
+++ b/drivers/media/pci/sta2x11/sta2x11_vip.c
@@ -145,6 +145,7 @@ struct sta2x11_vip {
 	unsigned int sequence;
 	struct vip_buffer *active; /* current active buffer */
 	spinlock_t lock; /* Used in videobuf2 callback */
+	struct mutex v4l_lock;
 
 	/* Interrupt counters */
 	int tcount, bcount;
@@ -385,6 +386,8 @@ static const struct vb2_ops vip_video_qops = {
 	.buf_queue		= buffer_queue,
 	.start_streaming	= start_streaming,
 	.stop_streaming		= stop_streaming,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
 };
 
 
@@ -870,6 +873,7 @@ static int sta2x11_vip_init_buffer(struct sta2x11_vip *vip)
 	vip->vb_vidq.mem_ops = &vb2_dma_contig_memops;
 	vip->vb_vidq.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	vip->vb_vidq.dev = &vip->pdev->dev;
+	vip->vb_vidq.lock = &vip->v4l_lock;
 	err = vb2_queue_init(&vip->vb_vidq);
 	if (err)
 		return err;
@@ -1034,6 +1038,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev,
 	vip->std = V4L2_STD_PAL;
 	vip->format = formats_50[0];
 	vip->config = config;
+	mutex_init(&vip->v4l_lock);
 
 	ret = sta2x11_vip_init_controls(vip);
 	if (ret)
@@ -1080,6 +1085,7 @@ static int sta2x11_vip_init_one(struct pci_dev *pdev,
 	vip->video_dev = video_dev_template;
 	vip->video_dev.v4l2_dev = &vip->v4l2_dev;
 	vip->video_dev.queue = &vip->vb_vidq;
+	vip->video_dev.lock = &vip->v4l_lock;
 	video_set_drvdata(&vip->video_dev, vip);
 
 	ret = video_register_device(&vip->video_dev, VFL_TYPE_GRABBER, -1);
-- 
cgit v1.2.3


From f1db5d978d88c75cfb1bcac74fbf06f77b86b7c3 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:25 -0400
Subject: media: mtk-mdp: Add locks for capture and output vb2_queues

Use the mutex in struct mtk_mdp_ctx to protect the
capture and output  vb2_queues. This allows to replace
the ad-hoc wait_{prepare, finish} with
vb2_ops_wait_{prepare, finish}.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c | 20 ++++----------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
index 583d47724ee8..c2e2f5f1ebf1 100644
--- a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
+++ b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
@@ -394,20 +394,6 @@ static bool mtk_mdp_ctx_state_is_set(struct mtk_mdp_ctx *ctx, u32 mask)
 	return ret;
 }
 
-static void mtk_mdp_ctx_lock(struct vb2_queue *vq)
-{
-	struct mtk_mdp_ctx *ctx = vb2_get_drv_priv(vq);
-
-	mutex_lock(&ctx->mdp_dev->lock);
-}
-
-static void mtk_mdp_ctx_unlock(struct vb2_queue *vq)
-{
-	struct mtk_mdp_ctx *ctx = vb2_get_drv_priv(vq);
-
-	mutex_unlock(&ctx->mdp_dev->lock);
-}
-
 static void mtk_mdp_set_frame_size(struct mtk_mdp_frame *frame, int width,
 				   int height)
 {
@@ -625,10 +611,10 @@ static const struct vb2_ops mtk_mdp_m2m_qops = {
 	.queue_setup	 = mtk_mdp_m2m_queue_setup,
 	.buf_prepare	 = mtk_mdp_m2m_buf_prepare,
 	.buf_queue	 = mtk_mdp_m2m_buf_queue,
-	.wait_prepare	 = mtk_mdp_ctx_unlock,
-	.wait_finish	 = mtk_mdp_ctx_lock,
 	.stop_streaming	 = mtk_mdp_m2m_stop_streaming,
 	.start_streaming = mtk_mdp_m2m_start_streaming,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
 };
 
 static int mtk_mdp_m2m_querycap(struct file *file, void *fh,
@@ -996,6 +982,7 @@ static int mtk_mdp_m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->dev = &ctx->mdp_dev->pdev->dev;
+	src_vq->lock = &ctx->mdp_dev->lock;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -1010,6 +997,7 @@ static int mtk_mdp_m2m_queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->dev = &ctx->mdp_dev->pdev->dev;
+	dst_vq->lock = &ctx->mdp_dev->lock;
 
 	return vb2_queue_init(dst_vq);
 }
-- 
cgit v1.2.3


From b53e19e16153ff8a0a560151ed27c3bc8d846de2 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:26 -0400
Subject: media: s5p-g2d: Implement wait_prepare and wait_finish

This driver is currently specifying a vb2_queue lock,
which means it straightforward to implement wait_prepare
and wait_finish.

Having these callbacks releases the queue lock while blocking,
which improves latency by allowing for example streamoff
or qbuf operations while waiting in dqbuf.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/s5p-g2d/g2d.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 3735c204e9ac..6b1c23463009 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -142,6 +142,8 @@ static const struct vb2_ops g2d_qops = {
 	.queue_setup	= g2d_queue_setup,
 	.buf_prepare	= g2d_buf_prepare,
 	.buf_queue	= g2d_buf_queue,
+	.wait_prepare	= vb2_ops_wait_prepare,
+	.wait_finish	= vb2_ops_wait_finish,
 };
 
 static int queue_init(void *priv, struct vb2_queue *src_vq,
-- 
cgit v1.2.3


From e5e4c9c962742b7f8dc8efc3b67f03add20fe467 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:27 -0400
Subject: media: staging: bcm2835-camera: Provide lock for vb2_queue

Use the device mutex to protect the vb2_queue.
This allows to replace the ad-hoc wait_{prepare, finish}
with vb2_ops_wait_{prepare, finish}.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../vc04_services/bcm2835-camera/bcm2835-camera.c  | 24 +++++-----------------
 1 file changed, 5 insertions(+), 19 deletions(-)

diff --git a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
index ce26741ae9d9..6dd0c838db05 100644
--- a/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
+++ b/drivers/staging/vc04_services/bcm2835-camera/bcm2835-camera.c
@@ -628,20 +628,6 @@ static void stop_streaming(struct vb2_queue *vq)
 		v4l2_err(&dev->v4l2_dev, "Failed to disable camera\n");
 }
 
-static void bm2835_mmal_lock(struct vb2_queue *vq)
-{
-	struct bm2835_mmal_dev *dev = vb2_get_drv_priv(vq);
-
-	mutex_lock(&dev->mutex);
-}
-
-static void bm2835_mmal_unlock(struct vb2_queue *vq)
-{
-	struct bm2835_mmal_dev *dev = vb2_get_drv_priv(vq);
-
-	mutex_unlock(&dev->mutex);
-}
-
 static const struct vb2_ops bm2835_mmal_video_qops = {
 	.queue_setup = queue_setup,
 	.buf_init = buffer_init,
@@ -650,8 +636,8 @@ static const struct vb2_ops bm2835_mmal_video_qops = {
 	.buf_queue = buffer_queue,
 	.start_streaming = start_streaming,
 	.stop_streaming = stop_streaming,
-	.wait_prepare = bm2835_mmal_unlock,
-	.wait_finish = bm2835_mmal_lock,
+	.wait_prepare = vb2_ops_wait_prepare,
+	.wait_finish = vb2_ops_wait_finish,
 };
 
 /* ------------------------------------------------------------------
@@ -1864,6 +1850,8 @@ static int bcm2835_mmal_probe(struct platform_device *pdev)
 			goto cleanup_gdev;
 		}
 
+		/* v4l2 core mutex used to protect all fops and v4l2 ioctls. */
+		mutex_init(&dev->mutex);
 		dev->camera_num = camera;
 		dev->max_width = resolutions[camera][0];
 		dev->max_height = resolutions[camera][1];
@@ -1908,13 +1896,11 @@ static int bcm2835_mmal_probe(struct platform_device *pdev)
 		q->ops = &bm2835_mmal_video_qops;
 		q->mem_ops = &vb2_vmalloc_memops;
 		q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+		q->lock = &dev->mutex;
 		ret = vb2_queue_init(q);
 		if (ret < 0)
 			goto unreg_dev;
 
-		/* v4l2 core mutex used to protect all fops and v4l2 ioctls. */
-		mutex_init(&dev->mutex);
-
 		/* initialise video devices */
 		ret = bm2835_mmal_init_device(dev, &dev->vdev);
 		if (ret < 0)
-- 
cgit v1.2.3


From 4e55969f2308129b0fd1aa90438553728e21ec7d Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:29 -0400
Subject: media: davinci_vpfe: Add video_device and vb2_queue locks

Currently, this driver does not serialize its video4linux
ioctls, which is a bug, as race conditions might appear.

In addition, video_device and vb2_queue locks are now both
mandatory. Add them, and implement wait_prepare and
wait_finish.

To stay on the safe side, this commit uses a single mutex
for both locks. Better latency can be obtained by separating
these if needed.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/davinci_vpfe/vpfe_video.c | 6 +++++-
 drivers/staging/media/davinci_vpfe/vpfe_video.h | 2 +-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.c b/drivers/staging/media/davinci_vpfe/vpfe_video.c
index 390fc98d07dd..1269a983455e 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.c
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.c
@@ -1312,6 +1312,8 @@ static const struct vb2_ops video_qops = {
 	.stop_streaming		= vpfe_stop_streaming,
 	.buf_cleanup		= vpfe_buf_cleanup,
 	.buf_queue		= vpfe_buffer_queue,
+	.wait_prepare		= vb2_ops_wait_prepare,
+	.wait_finish		= vb2_ops_wait_finish,
 };
 
 /*
@@ -1357,6 +1359,7 @@ static int vpfe_reqbufs(struct file *file, void *priv,
 	q->buf_struct_size = sizeof(struct vpfe_cap_buffer);
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 	q->dev = vpfe_dev->pdev;
+	q->lock = &video->lock;
 
 	ret = vb2_queue_init(q);
 	if (ret) {
@@ -1598,17 +1601,18 @@ int vpfe_video_init(struct vpfe_video_device *video, const char *name)
 		return -EINVAL;
 	}
 	/* Initialize field of video device */
+	mutex_init(&video->lock);
 	video->video_dev.release = video_device_release;
 	video->video_dev.fops = &vpfe_fops;
 	video->video_dev.ioctl_ops = &vpfe_ioctl_ops;
 	video->video_dev.minor = -1;
 	video->video_dev.tvnorms = 0;
+	video->video_dev.lock = &video->lock;
 	snprintf(video->video_dev.name, sizeof(video->video_dev.name),
 		 "DAVINCI VIDEO %s %s", name, direction);
 
 	spin_lock_init(&video->irqlock);
 	spin_lock_init(&video->dma_queue_lock);
-	mutex_init(&video->lock);
 	ret = media_entity_pads_init(&video->video_dev.entity,
 				1, &video->pad);
 	if (ret < 0)
diff --git a/drivers/staging/media/davinci_vpfe/vpfe_video.h b/drivers/staging/media/davinci_vpfe/vpfe_video.h
index 22136d3dadcb..4bbd219e8329 100644
--- a/drivers/staging/media/davinci_vpfe/vpfe_video.h
+++ b/drivers/staging/media/davinci_vpfe/vpfe_video.h
@@ -128,7 +128,7 @@ struct vpfe_video_device {
 	spinlock_t				irqlock;
 	/* IRQ lock for DMA queue */
 	spinlock_t				dma_queue_lock;
-	/* lock used to access this structure */
+	/* lock used to serialize all video4linux ioctls */
 	struct mutex				lock;
 	/* number of users performing IO */
 	u32					io_usrs;
-- 
cgit v1.2.3


From a4273abcd3e40f7e8fe9c5347dea1e0a6b9ccadb Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:30 -0400
Subject: media: mx_emmaprp: Implement wait_prepare and wait_finish

This driver is currently specifying a video_device lock,
which means it is protecting all the ioctls (including
queue ioctls) with a single mutex.

It's therefore straightforward to implement wait_prepare
and wait_finish, by explicitly setting the vb2_queue lock.

Having these callbacks releases the queue lock while blocking,
which improves latency by allowing for example streamoff
or qbuf operations while waiting in dqbuf.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/mx2_emmaprp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/media/platform/mx2_emmaprp.c b/drivers/media/platform/mx2_emmaprp.c
index 83b9db895a64..64195c4ddeaf 100644
--- a/drivers/media/platform/mx2_emmaprp.c
+++ b/drivers/media/platform/mx2_emmaprp.c
@@ -733,6 +733,8 @@ static const struct vb2_ops emmaprp_qops = {
 	.queue_setup	 = emmaprp_queue_setup,
 	.buf_prepare	 = emmaprp_buf_prepare,
 	.buf_queue	 = emmaprp_buf_queue,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
 };
 
 static int queue_init(void *priv, struct vb2_queue *src_vq,
@@ -749,6 +751,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->dev = ctx->dev->v4l2_dev.dev;
+	src_vq->lock = &ctx->dev->dev_mutex;
 
 	ret = vb2_queue_init(src_vq);
 	if (ret)
@@ -762,6 +765,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->dev = ctx->dev->v4l2_dev.dev;
+	dst_vq->lock = &ctx->dev->dev_mutex;
 
 	return vb2_queue_init(dst_vq);
 }
-- 
cgit v1.2.3


From 1d120649a81e5fc71151cbe8d6d82c58f7777160 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:31 -0400
Subject: media: m2m-deinterlace: Implement wait_prepare and wait_finish

This driver is currently specifying a video_device lock,
which means it is protecting all the ioctls (including
queue ioctls) with a single mutex.

It's therefore straightforward to implement wait_prepare
and wait_finish, by explicitly setting the vb2_queue lock.

Having these callbacks releases the queue lock while blocking,
which improves latency by allowing for example streamoff
or qbuf operations while waiting in dqbuf.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/m2m-deinterlace.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/media/platform/m2m-deinterlace.c b/drivers/media/platform/m2m-deinterlace.c
index a566ec566cec..5f84d2aa47ab 100644
--- a/drivers/media/platform/m2m-deinterlace.c
+++ b/drivers/media/platform/m2m-deinterlace.c
@@ -842,6 +842,8 @@ static const struct vb2_ops deinterlace_qops = {
 	.queue_setup	 = deinterlace_queue_setup,
 	.buf_prepare	 = deinterlace_buf_prepare,
 	.buf_queue	 = deinterlace_buf_queue,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
 };
 
 static int queue_init(void *priv, struct vb2_queue *src_vq,
@@ -858,6 +860,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	src_vq->mem_ops = &vb2_dma_contig_memops;
 	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	src_vq->dev = ctx->dev->v4l2_dev.dev;
+	src_vq->lock = &ctx->dev->dev_mutex;
 	q_data[V4L2_M2M_SRC].fmt = &formats[0];
 	q_data[V4L2_M2M_SRC].width = 640;
 	q_data[V4L2_M2M_SRC].height = 480;
@@ -876,6 +879,7 @@ static int queue_init(void *priv, struct vb2_queue *src_vq,
 	dst_vq->mem_ops = &vb2_dma_contig_memops;
 	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
 	dst_vq->dev = ctx->dev->v4l2_dev.dev;
+	dst_vq->lock = &ctx->dev->dev_mutex;
 	q_data[V4L2_M2M_DST].fmt = &formats[0];
 	q_data[V4L2_M2M_DST].width = 640;
 	q_data[V4L2_M2M_DST].height = 480;
-- 
cgit v1.2.3


From de3e581f31626a9e5697ea1581967729fcffdd1d Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Fri, 15 Jun 2018 15:07:32 -0400
Subject: media: stk1160: Set the vb2_queue lock before calling vb2_queue_init

The vb2_queue will soon be mandatory. The videobuf2 core
will throw a verbose warning if it's not set.

The stk1160 driver is setting the queue lock, but after
the vb2_queue_init call. Avoid the warning by setting
the lock before the queue initialization.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/stk1160/stk1160-v4l.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/stk1160/stk1160-v4l.c b/drivers/media/usb/stk1160/stk1160-v4l.c
index 77b759a0bcd9..504e413edcd2 100644
--- a/drivers/media/usb/stk1160/stk1160-v4l.c
+++ b/drivers/media/usb/stk1160/stk1160-v4l.c
@@ -802,6 +802,7 @@ int stk1160_vb2_setup(struct stk1160 *dev)
 	q->buf_struct_size = sizeof(struct stk1160_buffer);
 	q->ops = &stk1160_video_qops;
 	q->mem_ops = &vb2_vmalloc_memops;
+	q->lock = &dev->vb_queue_lock;
 	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
 
 	rc = vb2_queue_init(q);
@@ -827,7 +828,6 @@ int stk1160_video_register(struct stk1160 *dev)
 	 * It will be used to protect *only* v4l2 ioctls.
 	 */
 	dev->vdev.lock = &dev->v4l_lock;
-	dev->vdev.queue->lock = &dev->vb_queue_lock;
 
 	/* This will be used to set video_device parent */
 	dev->vdev.v4l2_dev = &dev->v4l2_dev;
-- 
cgit v1.2.3


From 421860b9d47053badce4b247576fa48df9ab4c48 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 27 Jun 2018 14:39:43 -0400
Subject: media: v4l2-ctrls: Fix CID base conflict between MAX217X and IMX

When the imx-media driver was initially merged, there was a conflict
with 8d67ae25 ("media: v4l2-ctrls: Reserve controls for MAX217X") which
was not fixed up correctly, resulting in V4L2_CID_USER_MAX217X_BASE and
V4L2_CID_USER_IMX_BASE taking on the same value. Fix by assigning imx
CID base the next available range at 0x10b0.

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 include/uapi/linux/v4l2-controls.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 8d473c979b61..8a75ad7899f3 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -188,7 +188,7 @@ enum v4l2_colorfx {
 
 /* The base for the imx driver controls.
  * We reserve 16 controls for this driver. */
-#define V4L2_CID_USER_IMX_BASE			(V4L2_CID_USER_BASE + 0x1090)
+#define V4L2_CID_USER_IMX_BASE			(V4L2_CID_USER_BASE + 0x10b0)
 
 /* MPEG-class control IDs */
 /* The MPEG controls are applicable to all codec controls
-- 
cgit v1.2.3


From 18c227af2c90eee06bd90f751a4b1193ee209d56 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 28 Jun 2018 11:44:12 -0400
Subject: media: coda: fix encoder source stride

The encoder picture run command takes a picture source stride parameter.
This must be set to the output queue's bytesperline, not width.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 68ed2a564ad1..a585b80ca3ac 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1362,7 +1362,8 @@ static int coda_prepare_encode(struct coda_ctx *ctx)
 
 	if (dev->devtype->product == CODA_960) {
 		coda_write(dev, 4/*FIXME: 0*/, CODA9_CMD_ENC_PIC_SRC_INDEX);
-		coda_write(dev, q_data_src->width, CODA9_CMD_ENC_PIC_SRC_STRIDE);
+		coda_write(dev, q_data_src->bytesperline,
+			   CODA9_CMD_ENC_PIC_SRC_STRIDE);
 		coda_write(dev, 0, CODA9_CMD_ENC_PIC_SUB_FRAME_SYNC);
 
 		reg = CODA9_CMD_ENC_PIC_SRC_ADDR_Y;
-- 
cgit v1.2.3


From 42a68012e67c2613e0570d462c5a0bd9a1527048 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 28 Jun 2018 11:47:08 -0400
Subject: media: coda: add read-only h.264 decoder profile/level controls

The decoder profile/level controls initially can be used to determine
supported profiles and levels. The values are set for a given stream
once the headers are parsed.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-common.c | 115 +++++++++++++++++++++++++++++-
 drivers/media/platform/coda/coda.h        |   2 +
 2 files changed, 116 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index b86d704ae10c..f41f2035204d 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -1395,6 +1395,72 @@ static int coda_buf_prepare(struct vb2_buffer *vb)
 	return 0;
 }
 
+static void coda_update_menu_ctrl(struct v4l2_ctrl *ctrl, int value)
+{
+	if (!ctrl)
+		return;
+
+	v4l2_ctrl_lock(ctrl);
+
+	/*
+	 * Extend the control range if the parsed stream contains a known but
+	 * unsupported value or level.
+	 */
+	if (value > ctrl->maximum) {
+		__v4l2_ctrl_modify_range(ctrl, ctrl->minimum, value,
+			ctrl->menu_skip_mask & ~(1 << value),
+			ctrl->default_value);
+	} else if (value < ctrl->minimum) {
+		__v4l2_ctrl_modify_range(ctrl, value, ctrl->maximum,
+			ctrl->menu_skip_mask & ~(1 << value),
+			ctrl->default_value);
+	}
+
+	__v4l2_ctrl_s_ctrl(ctrl, value);
+
+	v4l2_ctrl_unlock(ctrl);
+}
+
+static void coda_update_h264_profile_ctrl(struct coda_ctx *ctx)
+{
+	const char * const *profile_names;
+	int profile;
+
+	profile = coda_h264_profile(ctx->params.h264_profile_idc);
+	if (profile < 0) {
+		v4l2_warn(&ctx->dev->v4l2_dev, "Invalid H264 Profile: %u\n",
+			  ctx->params.h264_profile_idc);
+		return;
+	}
+
+	coda_update_menu_ctrl(ctx->h264_profile_ctrl, profile);
+
+	profile_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_PROFILE);
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev, "Parsed H264 Profile: %s\n",
+		 profile_names[profile]);
+}
+
+static void coda_update_h264_level_ctrl(struct coda_ctx *ctx)
+{
+	const char * const *level_names;
+	int level;
+
+	level = coda_h264_level(ctx->params.h264_level_idc);
+	if (level < 0) {
+		v4l2_warn(&ctx->dev->v4l2_dev, "Invalid H264 Level: %u\n",
+			  ctx->params.h264_level_idc);
+		return;
+	}
+
+	coda_update_menu_ctrl(ctx->h264_level_ctrl, level);
+
+	level_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_LEVEL);
+
+	v4l2_dbg(1, coda_debug, &ctx->dev->v4l2_dev, "Parsed H264 Level: %s\n",
+		 level_names[level]);
+}
+
 static void coda_buf_queue(struct vb2_buffer *vb)
 {
 	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
@@ -1423,8 +1489,11 @@ static void coda_buf_queue(struct vb2_buffer *vb)
 			 * whether to enable reordering during sequence
 			 * initialization.
 			 */
-			if (!ctx->params.h264_profile_idc)
+			if (!ctx->params.h264_profile_idc) {
 				coda_sps_parse_profile(ctx, vb);
+				coda_update_h264_profile_ctrl(ctx);
+				coda_update_h264_level_ctrl(ctx);
+			}
 		}
 
 		mutex_lock(&ctx->bitstream_mutex);
@@ -1862,6 +1931,47 @@ static void coda_jpeg_encode_ctrls(struct coda_ctx *ctx)
 		V4L2_CID_JPEG_RESTART_INTERVAL, 0, 100, 1, 0);
 }
 
+static void coda_decode_ctrls(struct coda_ctx *ctx)
+{
+	u64 mask;
+	u8 max;
+
+	ctx->h264_profile_ctrl = v4l2_ctrl_new_std_menu(&ctx->ctrls,
+		&coda_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_PROFILE,
+		V4L2_MPEG_VIDEO_H264_PROFILE_HIGH,
+		~((1 << V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE) |
+		  (1 << V4L2_MPEG_VIDEO_H264_PROFILE_MAIN) |
+		  (1 << V4L2_MPEG_VIDEO_H264_PROFILE_HIGH)),
+		V4L2_MPEG_VIDEO_H264_PROFILE_HIGH);
+	if (ctx->h264_profile_ctrl)
+		ctx->h264_profile_ctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY;
+
+	if (ctx->dev->devtype->product == CODA_HX4 ||
+	    ctx->dev->devtype->product == CODA_7541) {
+		max = V4L2_MPEG_VIDEO_H264_LEVEL_4_0;
+		mask = ~((1 << V4L2_MPEG_VIDEO_H264_LEVEL_2_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_1) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_2) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_0));
+	} else if (ctx->dev->devtype->product == CODA_960) {
+		max = V4L2_MPEG_VIDEO_H264_LEVEL_4_1;
+		mask = ~((1 << V4L2_MPEG_VIDEO_H264_LEVEL_2_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_1) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_3_2) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_0) |
+			 (1 << V4L2_MPEG_VIDEO_H264_LEVEL_4_1));
+	} else {
+		return;
+	}
+	ctx->h264_level_ctrl = v4l2_ctrl_new_std_menu(&ctx->ctrls,
+		&coda_ctrl_ops, V4L2_CID_MPEG_VIDEO_H264_LEVEL, max, mask,
+		max);
+	if (ctx->h264_level_ctrl)
+		ctx->h264_level_ctrl->flags |= V4L2_CTRL_FLAG_READ_ONLY;
+}
+
 static int coda_ctrls_setup(struct coda_ctx *ctx)
 {
 	v4l2_ctrl_handler_init(&ctx->ctrls, 2);
@@ -1875,6 +1985,9 @@ static int coda_ctrls_setup(struct coda_ctx *ctx)
 			coda_jpeg_encode_ctrls(ctx);
 		else
 			coda_encode_ctrls(ctx);
+	} else {
+		if (ctx->cvd->src_formats[0] == V4L2_PIX_FMT_H264)
+			coda_decode_ctrls(ctx);
 	}
 
 	if (ctx->ctrls.error) {
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index c70cfab2433f..9f57f73161d6 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -214,6 +214,8 @@ struct coda_ctx {
 	enum v4l2_quantization		quantization;
 	struct coda_params		params;
 	struct v4l2_ctrl_handler	ctrls;
+	struct v4l2_ctrl		*h264_profile_ctrl;
+	struct v4l2_ctrl		*h264_level_ctrl;
 	struct v4l2_fh			fh;
 	int				gopcounter;
 	int				runcounter;
-- 
cgit v1.2.3


From 9f84310d88304bb2f2b154ba740ecc3a6326c175 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 28 Jun 2018 11:47:09 -0400
Subject: media: coda: fix reorder detection for unknown levels

Whether reordering should be enabled only depends on the h.264 profile.
Stop parsing the level and drop the debug message, profile and level
can now be determined via read-only decoder controls.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c | 25 ++++---------------------
 1 file changed, 4 insertions(+), 21 deletions(-)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index a585b80ca3ac..36c19983910b 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1583,10 +1583,8 @@ static int coda_decoder_reqbufs(struct coda_ctx *ctx,
 
 static bool coda_reorder_enable(struct coda_ctx *ctx)
 {
-	const char * const *profile_names;
-	const char * const *level_names;
 	struct coda_dev *dev = ctx->dev;
-	int profile, level;
+	int profile;
 
 	if (dev->devtype->product != CODA_HX4 &&
 	    dev->devtype->product != CODA_7541 &&
@@ -1600,24 +1598,9 @@ static bool coda_reorder_enable(struct coda_ctx *ctx)
 		return true;
 
 	profile = coda_h264_profile(ctx->params.h264_profile_idc);
-	if (profile < 0) {
-		v4l2_warn(&dev->v4l2_dev, "Invalid H264 Profile: %d\n",
-			 ctx->params.h264_profile_idc);
-		return false;
-	}
-
-	level = coda_h264_level(ctx->params.h264_level_idc);
-	if (level < 0) {
-		v4l2_warn(&dev->v4l2_dev, "Invalid H264 Level: %d\n",
-			 ctx->params.h264_level_idc);
-		return false;
-	}
-
-	profile_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_PROFILE);
-	level_names = v4l2_ctrl_get_menu(V4L2_CID_MPEG_VIDEO_H264_LEVEL);
-
-	v4l2_dbg(1, coda_debug, &dev->v4l2_dev, "H264 Profile/Level: %s L%s\n",
-		 profile_names[profile], level_names[level]);
+	if (profile < 0)
+		v4l2_warn(&dev->v4l2_dev, "Unknown H264 Profile: %u\n",
+			  ctx->params.h264_profile_idc);
 
 	/* Baseline profile does not support reordering */
 	return profile > V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE;
-- 
cgit v1.2.3


From 83a729530a3a8a40dd529c72e4c3fe491d9bce68 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Fri, 29 Jun 2018 05:40:41 -0400
Subject: media: vivid: fix gain when autogain is on

In the vivid driver you want gain to continuous change while autogain
is on. However, dev->jiffies_vid_cap doesn't actually change. It probably
did in the past, but changes in the code caused this to be a fixed value
that is only set when you start streaming.

Replace it by jiffies, which is always changing.

[mchehab@kernel.org: use jiffies_to_msecs() instead of dividing by HZ]

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vivid/vivid-ctrls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/vivid/vivid-ctrls.c b/drivers/media/platform/vivid/vivid-ctrls.c
index 6b0bfa091592..5429193fbb91 100644
--- a/drivers/media/platform/vivid/vivid-ctrls.c
+++ b/drivers/media/platform/vivid/vivid-ctrls.c
@@ -295,7 +295,7 @@ static int vivid_user_vid_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 
 	switch (ctrl->id) {
 	case V4L2_CID_AUTOGAIN:
-		dev->gain->val = dev->jiffies_vid_cap & 0xff;
+		dev->gain->val = (jiffies_to_msecs(jiffies) / 1000) & 0xff;
 		break;
 	}
 	return 0;
-- 
cgit v1.2.3


From 4d2096b4695623e3683cd41a96d6d0af6a5acf87 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 29 Jun 2018 08:42:08 -0400
Subject: media: coda: clear hold flag on streamoff

If new buffers are queued after streamoff, the flag will be cleared
anyway, so this is mostly for the purpose of correctness.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index f41f2035204d..42f852ccc8c0 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -1703,6 +1703,7 @@ static void coda_stop_streaming(struct vb2_queue *q)
 			ctx->bitstream.vaddr, ctx->bitstream.size);
 		ctx->runcounter = 0;
 		ctx->aborting = 0;
+		ctx->hold = false;
 	}
 
 	if (!ctx->streamon_out && !ctx->streamon_cap)
-- 
cgit v1.2.3


From 1e3e2a9ac40ad4d11699a49a1bbbf40cd8d4c8bd Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 29 Jun 2018 08:46:46 -0400
Subject: media: coda: jpeg: allow non-JPEG colorspace

The hardware codec is not colorspace aware. We should trust userspace to
set the correct colorimetry information on the OUTPUT queue and mirror
the exact same setting on the CAPTURE queue.

There is no reason to restrict colorspace to JPEG for JPEG images, if
userspace injects the correct colorspace information into the JPEG
headers after encoding.

Fixes: b14ac545688d ("[media] coda: improve colorimetry handling")

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-common.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index 42f852ccc8c0..f25f1417b4fa 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -569,8 +569,6 @@ static int coda_try_fmt(struct coda_ctx *ctx, const struct coda_codec *codec,
 					f->fmt.pix.height * 2;
 		break;
 	case V4L2_PIX_FMT_JPEG:
-		f->fmt.pix.colorspace = V4L2_COLORSPACE_JPEG;
-		/* fallthrough */
 	case V4L2_PIX_FMT_H264:
 	case V4L2_PIX_FMT_MPEG4:
 	case V4L2_PIX_FMT_MPEG2:
-- 
cgit v1.2.3


From 86b30a671b3bbe376ad7679ae3c1436c2a8f4510 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 29 Jun 2018 08:46:47 -0400
Subject: media: coda: jpeg: only queue two buffers into the bitstream for JPEG
 on CODA7541

Padding the bitstream buffer is not enough to reliably avoid prefetch
failures.  Picture runs with the next buffer's header already visible to
the CODA7541 succeed much more reliably, so always queue two JPEG frames
into the bitstream buffer.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 36c19983910b..e2994b3ddbf2 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -261,11 +261,12 @@ void coda_fill_bitstream(struct coda_ctx *ctx, struct list_head *buffer_list)
 
 	while (v4l2_m2m_num_src_bufs_ready(ctx->fh.m2m_ctx) > 0) {
 		/*
-		 * Only queue a single JPEG into the bitstream buffer, except
-		 * to increase payload over 512 bytes or if in hold state.
+		 * Only queue two JPEGs into the bitstream buffer to keep
+		 * latency low. We need at least one complete buffer and the
+		 * header of another buffer (for prescan) in the bitstream.
 		 */
 		if (ctx->codec->src_fourcc == V4L2_PIX_FMT_JPEG &&
-		    (coda_get_bitstream_payload(ctx) >= 512) && !ctx->hold)
+		    ctx->num_metas > 1)
 			break;
 
 		src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
-- 
cgit v1.2.3


From 968d72e6a5105a18fe17c0a8b4ef2951d0eb42dd Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 4 Jul 2018 12:48:10 +0300
Subject: drm/savage: off by one in savage_bci_cmdbuf()

The > should be >= here so that we don't read beyond the end of the
dma->buflist[] array.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180704094810.whrgn6jxe7uibnfv@kili.mountain
---
 drivers/gpu/drm/savage/savage_state.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/savage/savage_state.c b/drivers/gpu/drm/savage/savage_state.c
index 2db89bed52e8..7559a820bd43 100644
--- a/drivers/gpu/drm/savage/savage_state.c
+++ b/drivers/gpu/drm/savage/savage_state.c
@@ -971,7 +971,7 @@ int savage_bci_cmdbuf(struct drm_device *dev, void *data, struct drm_file *file_
 	LOCK_TEST_WITH_RETURN(dev, file_priv);
 
 	if (dma && dma->buflist) {
-		if (cmdbuf->dma_idx > dma->buf_count) {
+		if (cmdbuf->dma_idx >= dma->buf_count) {
 			DRM_ERROR
 			    ("vertex buffer index %u out of range (0-%u)\n",
 			     cmdbuf->dma_idx, dma->buf_count - 1);
-- 
cgit v1.2.3


From e7e3728bd776d1d1450212ad266832f1003f833f Mon Sep 17 00:00:00 2001
From: Qiaobin Fu <qiaobinf@bu.edu>
Date: Sun, 1 Jul 2018 15:16:27 -0400
Subject: net:sched: add action inheritdsfield to skbedit

The new action inheritdsfield copies the field DS of
IPv4 and IPv6 packets into skb->priority. This enables
later classification of packets based on the DS field.

v5:
*Update the drop counter for TC_ACT_SHOT

v4:
*Not allow setting flags other than the expected ones.

*Allow dumping the pure flags.

v3:
*Use optional flags, so that it won't break old versions of tc.

*Allow users to set both SKBEDIT_F_PRIORITY and SKBEDIT_F_INHERITDSFIELD flags.

v2:
*Fix the style issue

*Move the code from skbmod to skbedit

Original idea by Jamal Hadi Salim <jhs@mojatatu.com>

Signed-off-by: Qiaobin Fu <qiaobinf@bu.edu>
Reviewed-by: Michel Machado <michel@digirati.com.br>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tc_act/tc_skbedit.h |  2 ++
 net/sched/act_skbedit.c                | 41 ++++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/include/uapi/linux/tc_act/tc_skbedit.h b/include/uapi/linux/tc_act/tc_skbedit.h
index fbcfe27a4e6c..6de6071ebed6 100644
--- a/include/uapi/linux/tc_act/tc_skbedit.h
+++ b/include/uapi/linux/tc_act/tc_skbedit.h
@@ -30,6 +30,7 @@
 #define SKBEDIT_F_MARK			0x4
 #define SKBEDIT_F_PTYPE			0x8
 #define SKBEDIT_F_MASK			0x10
+#define SKBEDIT_F_INHERITDSFIELD	0x20
 
 struct tc_skbedit {
 	tc_gen;
@@ -45,6 +46,7 @@ enum {
 	TCA_SKBEDIT_PAD,
 	TCA_SKBEDIT_PTYPE,
 	TCA_SKBEDIT_MASK,
+	TCA_SKBEDIT_FLAGS,
 	__TCA_SKBEDIT_MAX
 };
 #define TCA_SKBEDIT_MAX (__TCA_SKBEDIT_MAX - 1)
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 6138d1d71900..dfaf5d8028dd 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -23,6 +23,9 @@
 #include <linux/rtnetlink.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/dsfield.h>
 
 #include <linux/tc_act/tc_skbedit.h>
 #include <net/tc_act/tc_skbedit.h>
@@ -41,6 +44,25 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 
 	if (d->flags & SKBEDIT_F_PRIORITY)
 		skb->priority = d->priority;
+	if (d->flags & SKBEDIT_F_INHERITDSFIELD) {
+		int wlen = skb_network_offset(skb);
+
+		switch (tc_skb_protocol(skb)) {
+		case htons(ETH_P_IP):
+			wlen += sizeof(struct iphdr);
+			if (!pskb_may_pull(skb, wlen))
+				goto err;
+			skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
+			break;
+
+		case htons(ETH_P_IPV6):
+			wlen += sizeof(struct ipv6hdr);
+			if (!pskb_may_pull(skb, wlen))
+				goto err;
+			skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
+			break;
+		}
+	}
 	if (d->flags & SKBEDIT_F_QUEUE_MAPPING &&
 	    skb->dev->real_num_tx_queues > d->queue_mapping)
 		skb_set_queue_mapping(skb, d->queue_mapping);
@@ -53,6 +75,11 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 
 	spin_unlock(&d->tcf_lock);
 	return d->tcf_action;
+
+err:
+	d->tcf_qstats.drops++;
+	spin_unlock(&d->tcf_lock);
+	return TC_ACT_SHOT;
 }
 
 static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
@@ -62,6 +89,7 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 	[TCA_SKBEDIT_MARK]		= { .len = sizeof(u32) },
 	[TCA_SKBEDIT_PTYPE]		= { .len = sizeof(u16) },
 	[TCA_SKBEDIT_MASK]		= { .len = sizeof(u32) },
+	[TCA_SKBEDIT_FLAGS]		= { .len = sizeof(u64) },
 };
 
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
@@ -114,6 +142,13 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		mask = nla_data(tb[TCA_SKBEDIT_MASK]);
 	}
 
+	if (tb[TCA_SKBEDIT_FLAGS] != NULL) {
+		u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]);
+
+		if (*pure_flags & SKBEDIT_F_INHERITDSFIELD)
+			flags |= SKBEDIT_F_INHERITDSFIELD;
+	}
+
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
 
 	exists = tcf_idr_check(tn, parm->index, a, bind);
@@ -178,6 +213,7 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 		.action  = d->tcf_action,
 	};
 	struct tcf_t t;
+	u64 pure_flags = 0;
 
 	if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
@@ -196,6 +232,11 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 	if ((d->flags & SKBEDIT_F_MASK) &&
 	    nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask))
 		goto nla_put_failure;
+	if (d->flags & SKBEDIT_F_INHERITDSFIELD)
+		pure_flags |= SKBEDIT_F_INHERITDSFIELD;
+	if (pure_flags != 0 &&
+	    nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
+		goto nla_put_failure;
 
 	tcf_tm_dump(&t, &d->tcf_tm);
 	if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD))
-- 
cgit v1.2.3


From 2b84e2a0092c74e4ccc7933a06014e850c905a55 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 29 Jun 2018 08:46:48 -0400
Subject: media: coda: jpeg: explicitly disable thumbnails in SEQ_INIT

Explicitly clear DEC_SEQ_JPG_THUMB_EN during sequence initialization.
Not clearing the register does not cause problems, since the only other
codec (MPEG-4 decode) that writes to this register happens to always
write 0 as well.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c  | 2 ++
 drivers/media/platform/coda/coda_regs.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index e2994b3ddbf2..92044b779f59 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1679,6 +1679,8 @@ static int __coda_start_decoding(struct coda_ctx *ctx)
 			coda_write(dev, 512, CODA_CMD_DEC_SEQ_SPP_CHUNK_SIZE);
 		}
 	}
+	if (src_fourcc == V4L2_PIX_FMT_JPEG)
+		coda_write(dev, 0, CODA_CMD_DEC_SEQ_JPG_THUMB_EN);
 	if (dev->devtype->product != CODA_960)
 		coda_write(dev, 0, CODA_CMD_DEC_SEQ_SRC_SIZE);
 
diff --git a/drivers/media/platform/coda/coda_regs.h b/drivers/media/platform/coda/coda_regs.h
index 3b650b8aabe9..5e7b00a97671 100644
--- a/drivers/media/platform/coda/coda_regs.h
+++ b/drivers/media/platform/coda/coda_regs.h
@@ -157,6 +157,7 @@
 #define CODA_CMD_DEC_SEQ_START_BYTE		0x190
 #define CODA_CMD_DEC_SEQ_PS_BB_START		0x194
 #define CODA_CMD_DEC_SEQ_PS_BB_SIZE		0x198
+#define CODA_CMD_DEC_SEQ_JPG_THUMB_EN		0x19c
 #define CODA_CMD_DEC_SEQ_MP4_ASP_CLASS		0x19c
 #define		CODA_MP4_CLASS_MPEG4			0
 #define CODA_CMD_DEC_SEQ_X264_MV_EN		0x19c
-- 
cgit v1.2.3


From b8f8e559c71980c527d8697d274d53809c61aa37 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 29 Jun 2018 08:47:20 -0400
Subject: media: coda: mark CODA960 firmware version 2.1.9 as supported

This patch adds the i.MX6 CODA960 firmware versions 2.1.9
(revision 32515) to the list of supported firmware versions.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 92044b779f59..26d14e6a64cc 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -722,6 +722,7 @@ static u32 coda_supported_firmwares[] = {
 	CODA_FIRMWARE_VERNUM(CODA_HX4, 1, 4, 50),
 	CODA_FIRMWARE_VERNUM(CODA_7541, 1, 4, 50),
 	CODA_FIRMWARE_VERNUM(CODA_960, 2, 1, 5),
+	CODA_FIRMWARE_VERNUM(CODA_960, 2, 1, 9),
 	CODA_FIRMWARE_VERNUM(CODA_960, 2, 3, 10),
 	CODA_FIRMWARE_VERNUM(CODA_960, 3, 1, 1),
 };
-- 
cgit v1.2.3


From 662a99e145661c2b35155cf375044deae9b79896 Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Fri, 29 Jun 2018 17:49:22 -0400
Subject: media: fsl-viu: fix error handling in viu_of_probe()

viu_of_probe() ignores fails in i2c_get_adapter(),
tries to unlock uninitialized mutex on error path.

The patch streamlining the error handling in viu_of_probe().

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/fsl-viu.c | 38 +++++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/drivers/media/platform/fsl-viu.c b/drivers/media/platform/fsl-viu.c
index e41510ce69a4..0273302aa741 100644
--- a/drivers/media/platform/fsl-viu.c
+++ b/drivers/media/platform/fsl-viu.c
@@ -1414,7 +1414,7 @@ static int viu_of_probe(struct platform_device *op)
 				     sizeof(struct viu_reg), DRV_NAME)) {
 		dev_err(&op->dev, "Error while requesting mem region\n");
 		ret = -EBUSY;
-		goto err;
+		goto err_irq;
 	}
 
 	/* remap registers */
@@ -1422,7 +1422,7 @@ static int viu_of_probe(struct platform_device *op)
 	if (!viu_regs) {
 		dev_err(&op->dev, "Can't map register set\n");
 		ret = -ENOMEM;
-		goto err;
+		goto err_irq;
 	}
 
 	/* Prepare our private structure */
@@ -1430,7 +1430,7 @@ static int viu_of_probe(struct platform_device *op)
 	if (!viu_dev) {
 		dev_err(&op->dev, "Can't allocate private structure\n");
 		ret = -ENOMEM;
-		goto err;
+		goto err_irq;
 	}
 
 	viu_dev->vr = viu_regs;
@@ -1446,16 +1446,21 @@ static int viu_of_probe(struct platform_device *op)
 	ret = v4l2_device_register(viu_dev->dev, &viu_dev->v4l2_dev);
 	if (ret < 0) {
 		dev_err(&op->dev, "v4l2_device_register() failed: %d\n", ret);
-		goto err;
+		goto err_irq;
 	}
 
 	ad = i2c_get_adapter(0);
+	if (!ad) {
+		ret = -EFAULT;
+		dev_err(&op->dev, "couldn't get i2c adapter\n");
+		goto err_v4l2;
+	}
 
 	v4l2_ctrl_handler_init(&viu_dev->hdl, 5);
 	if (viu_dev->hdl.error) {
 		ret = viu_dev->hdl.error;
 		dev_err(&op->dev, "couldn't register control\n");
-		goto err_vdev;
+		goto err_i2c;
 	}
 	/* This control handler will inherit the control(s) from the
 	   sub-device(s). */
@@ -1471,7 +1476,7 @@ static int viu_of_probe(struct platform_device *op)
 	vdev = video_device_alloc();
 	if (vdev == NULL) {
 		ret = -ENOMEM;
-		goto err_vdev;
+		goto err_hdl;
 	}
 
 	*vdev = viu_template;
@@ -1492,7 +1497,7 @@ static int viu_of_probe(struct platform_device *op)
 	ret = video_register_device(viu_dev->vdev, VFL_TYPE_GRABBER, -1);
 	if (ret < 0) {
 		video_device_release(viu_dev->vdev);
-		goto err_vdev;
+		goto err_unlock;
 	}
 
 	/* enable VIU clock */
@@ -1500,12 +1505,12 @@ static int viu_of_probe(struct platform_device *op)
 	if (IS_ERR(clk)) {
 		dev_err(&op->dev, "failed to lookup the clock!\n");
 		ret = PTR_ERR(clk);
-		goto err_clk;
+		goto err_vdev;
 	}
 	ret = clk_prepare_enable(clk);
 	if (ret) {
 		dev_err(&op->dev, "failed to enable the clock!\n");
-		goto err_clk;
+		goto err_vdev;
 	}
 	viu_dev->clk = clk;
 
@@ -1516,7 +1521,7 @@ static int viu_of_probe(struct platform_device *op)
 	if (request_irq(viu_dev->irq, viu_intr, 0, "viu", (void *)viu_dev)) {
 		dev_err(&op->dev, "Request VIU IRQ failed.\n");
 		ret = -ENODEV;
-		goto err_irq;
+		goto err_clk;
 	}
 
 	mutex_unlock(&viu_dev->lock);
@@ -1524,16 +1529,19 @@ static int viu_of_probe(struct platform_device *op)
 	dev_info(&op->dev, "Freescale VIU Video Capture Board\n");
 	return ret;
 
-err_irq:
-	clk_disable_unprepare(viu_dev->clk);
 err_clk:
-	video_unregister_device(viu_dev->vdev);
+	clk_disable_unprepare(viu_dev->clk);
 err_vdev:
-	v4l2_ctrl_handler_free(&viu_dev->hdl);
+	video_unregister_device(viu_dev->vdev);
+err_unlock:
 	mutex_unlock(&viu_dev->lock);
+err_hdl:
+	v4l2_ctrl_handler_free(&viu_dev->hdl);
+err_i2c:
 	i2c_put_adapter(ad);
+err_v4l2:
 	v4l2_device_unregister(&viu_dev->v4l2_dev);
-err:
+err_irq:
 	irq_dispose_mapping(viu_irq);
 	return ret;
 }
-- 
cgit v1.2.3


From 28b9b33b983f4de3ce9e660e3efe1e08adabf779 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 3 Jul 2018 16:31:31 +0900
Subject: vhost_net: Rename local variables in vhost_net_rx_peek_head_len

So we can easily see which variable is for which, tx or rx.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 29756d88799b..3939c50d757a 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -647,39 +647,39 @@ static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
 
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 {
-	struct vhost_net_virtqueue *rvq = &net->vqs[VHOST_NET_VQ_RX];
-	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
-	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
+	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *tvq = &tnvq->vq;
 	unsigned long uninitialized_var(endtime);
-	int len = peek_head_len(rvq, sk);
+	int len = peek_head_len(rnvq, sk);
 
-	if (!len && vq->busyloop_timeout) {
+	if (!len && tvq->busyloop_timeout) {
 		/* Flush batched heads first */
-		vhost_rx_signal_used(rvq);
+		vhost_rx_signal_used(rnvq);
 		/* Both tx vq and rx socket were polled here */
-		mutex_lock_nested(&vq->mutex, 1);
-		vhost_disable_notify(&net->dev, vq);
+		mutex_lock_nested(&tvq->mutex, 1);
+		vhost_disable_notify(&net->dev, tvq);
 
 		preempt_disable();
-		endtime = busy_clock() + vq->busyloop_timeout;
+		endtime = busy_clock() + tvq->busyloop_timeout;
 
 		while (vhost_can_busy_poll(&net->dev, endtime) &&
 		       !sk_has_rx_data(sk) &&
-		       vhost_vq_avail_empty(&net->dev, vq))
+		       vhost_vq_avail_empty(&net->dev, tvq))
 			cpu_relax();
 
 		preempt_enable();
 
-		if (!vhost_vq_avail_empty(&net->dev, vq))
-			vhost_poll_queue(&vq->poll);
-		else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
-			vhost_disable_notify(&net->dev, vq);
-			vhost_poll_queue(&vq->poll);
+		if (!vhost_vq_avail_empty(&net->dev, tvq)) {
+			vhost_poll_queue(&tvq->poll);
+		} else if (unlikely(vhost_enable_notify(&net->dev, tvq))) {
+			vhost_disable_notify(&net->dev, tvq);
+			vhost_poll_queue(&tvq->poll);
 		}
 
-		mutex_unlock(&vq->mutex);
+		mutex_unlock(&tvq->mutex);
 
-		len = peek_head_len(rvq, sk);
+		len = peek_head_len(rnvq, sk);
 	}
 
 	return len;
-- 
cgit v1.2.3


From 027b17603b030f1334ade079b7a3e986569c956b Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 3 Jul 2018 16:31:32 +0900
Subject: vhost_net: Avoid tx vring kicks during busyloop

Under heavy load vhost busypoll may run without suppressing
notification. For example tx zerocopy callback can push tx work while
handle_tx() is running, then busyloop exits due to vhost_has_work()
condition and enables notification but immediately reenters handle_tx()
because the pushed work was tx. In this case handle_tx() tries to
disable notification again, but when using event_idx it by design
cannot. Then busyloop will run without suppressing notification.
Another example is the case where handle_tx() tries to enable
notification but avail idx is advanced so disables it again. This case
also leads to the same situation with event_idx.

The problem is that once we enter this situation busyloop does not work
under heavy load for considerable amount of time, because notification
is likely to happen during busyloop and handle_tx() immediately enables
notification after notification happens. Specifically busyloop detects
notification by vhost_has_work() and then handle_tx() calls
vhost_enable_notify(). Because the detected work was the tx work, it
enters handle_tx(), and enters busyloop without suppression again.
This is likely to be repeated, so with event_idx we are almost not able
to suppress notification in this case.

To fix this, poll the work instead of enabling notification when
busypoll is interrupted by something. IMHO vhost_has_work() is kind of
interruption rather than a signal to completely cancel the busypoll, so
let's run busypoll after the necessary work is done.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 3939c50d757a..811c0e5ffc8e 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -396,13 +396,10 @@ static inline unsigned long busy_clock(void)
 	return local_clock() >> 10;
 }
 
-static bool vhost_can_busy_poll(struct vhost_dev *dev,
-				unsigned long endtime)
+static bool vhost_can_busy_poll(unsigned long endtime)
 {
-	return likely(!need_resched()) &&
-	       likely(!time_after(busy_clock(), endtime)) &&
-	       likely(!signal_pending(current)) &&
-	       !vhost_has_work(dev);
+	return likely(!need_resched() && !time_after(busy_clock(), endtime) &&
+		      !signal_pending(current));
 }
 
 static void vhost_net_disable_vq(struct vhost_net *n,
@@ -434,7 +431,8 @@ static int vhost_net_enable_vq(struct vhost_net *n,
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 				    struct vhost_virtqueue *vq,
 				    struct iovec iov[], unsigned int iov_size,
-				    unsigned int *out_num, unsigned int *in_num)
+				    unsigned int *out_num, unsigned int *in_num,
+				    bool *busyloop_intr)
 {
 	unsigned long uninitialized_var(endtime);
 	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
@@ -443,9 +441,15 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 	if (r == vq->num && vq->busyloop_timeout) {
 		preempt_disable();
 		endtime = busy_clock() + vq->busyloop_timeout;
-		while (vhost_can_busy_poll(vq->dev, endtime) &&
-		       vhost_vq_avail_empty(vq->dev, vq))
+		while (vhost_can_busy_poll(endtime)) {
+			if (vhost_has_work(vq->dev)) {
+				*busyloop_intr = true;
+				break;
+			}
+			if (!vhost_vq_avail_empty(vq->dev, vq))
+				break;
 			cpu_relax();
+		}
 		preempt_enable();
 		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
 				      out_num, in_num, NULL, NULL);
@@ -501,20 +505,24 @@ static void handle_tx(struct vhost_net *net)
 	zcopy = nvq->ubufs;
 
 	for (;;) {
+		bool busyloop_intr;
+
 		/* Release DMAs done buffers first */
 		if (zcopy)
 			vhost_zerocopy_signal_used(net, vq);
 
-
+		busyloop_intr = false;
 		head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
 						ARRAY_SIZE(vq->iov),
-						&out, &in);
+						&out, &in, &busyloop_intr);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(head < 0))
 			break;
 		/* Nothing new?  Wait for eventfd to tell us they refilled. */
 		if (head == vq->num) {
-			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			if (unlikely(busyloop_intr)) {
+				vhost_poll_queue(&vq->poll);
+			} else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				vhost_disable_notify(&net->dev, vq);
 				continue;
 			}
@@ -663,7 +671,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 		preempt_disable();
 		endtime = busy_clock() + tvq->busyloop_timeout;
 
-		while (vhost_can_busy_poll(&net->dev, endtime) &&
+		while (vhost_can_busy_poll(endtime) &&
+		       !vhost_has_work(&net->dev) &&
 		       !sk_has_rx_data(sk) &&
 		       vhost_vq_avail_empty(&net->dev, tvq))
 			cpu_relax();
-- 
cgit v1.2.3


From be294a51adfc1e1d9884e34480c34e4388f27904 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 3 Jul 2018 16:31:33 +0900
Subject: vhost_net: Avoid rx queue wake-ups during busypoll

We may run handle_rx() while rx work is queued. For example a packet can
push the rx work during the window before handle_rx calls
vhost_net_disable_vq().
In that case busypoll immediately exits due to vhost_has_work()
condition and enables vq again. This can lead to another unnecessary rx
wake-ups, so poll rx work instead of enabling the vq.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 26 +++++++++++++++++++-------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 811c0e5ffc8e..791bc8b22aac 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -653,7 +653,8 @@ static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
 	nvq->done_idx = 0;
 }
 
-static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
+static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
+				      bool *busyloop_intr)
 {
 	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
 	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
@@ -671,11 +672,16 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 		preempt_disable();
 		endtime = busy_clock() + tvq->busyloop_timeout;
 
-		while (vhost_can_busy_poll(endtime) &&
-		       !vhost_has_work(&net->dev) &&
-		       !sk_has_rx_data(sk) &&
-		       vhost_vq_avail_empty(&net->dev, tvq))
+		while (vhost_can_busy_poll(endtime)) {
+			if (vhost_has_work(&net->dev)) {
+				*busyloop_intr = true;
+				break;
+			}
+			if (sk_has_rx_data(sk) ||
+			    !vhost_vq_avail_empty(&net->dev, tvq))
+				break;
 			cpu_relax();
+		}
 
 		preempt_enable();
 
@@ -795,6 +801,7 @@ static void handle_rx(struct vhost_net *net)
 	s16 headcount;
 	size_t vhost_hlen, sock_hlen;
 	size_t vhost_len, sock_len;
+	bool busyloop_intr = false;
 	struct socket *sock;
 	struct iov_iter fixup;
 	__virtio16 num_buffers;
@@ -818,7 +825,9 @@ static void handle_rx(struct vhost_net *net)
 		vq->log : NULL;
 	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);
 
-	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
+	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
+						      &busyloop_intr))) {
+		busyloop_intr = false;
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
@@ -905,7 +914,10 @@ static void handle_rx(struct vhost_net *net)
 			goto out;
 		}
 	}
-	vhost_net_enable_vq(net, vq);
+	if (unlikely(busyloop_intr))
+		vhost_poll_queue(&vq->poll);
+	else
+		vhost_net_enable_vq(net, vq);
 out:
 	vhost_rx_signal_used(nvq);
 	mutex_unlock(&vq->mutex);
-- 
cgit v1.2.3


From 6369fec5be0aad4965bb13cc8f26a621ff39cc65 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Tue, 3 Jul 2018 16:31:34 +0900
Subject: vhost_net: Avoid rx vring kicks during busyloop

We may run out of avail rx ring descriptor under heavy load but busypoll
did not detect it so busypoll may have exited prematurely. Avoid this by
checking rx ring full during busypoll.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 791bc8b22aac..b2240361f1a1 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -658,6 +658,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 {
 	struct vhost_net_virtqueue *rnvq = &net->vqs[VHOST_NET_VQ_RX];
 	struct vhost_net_virtqueue *tnvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *rvq = &rnvq->vq;
 	struct vhost_virtqueue *tvq = &tnvq->vq;
 	unsigned long uninitialized_var(endtime);
 	int len = peek_head_len(rnvq, sk);
@@ -677,7 +678,8 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 				*busyloop_intr = true;
 				break;
 			}
-			if (sk_has_rx_data(sk) ||
+			if ((sk_has_rx_data(sk) &&
+			     !vhost_vq_avail_empty(&net->dev, rvq)) ||
 			    !vhost_vq_avail_empty(&net->dev, tvq))
 				break;
 			cpu_relax();
@@ -827,7 +829,6 @@ static void handle_rx(struct vhost_net *net)
 
 	while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk,
 						      &busyloop_intr))) {
-		busyloop_intr = false;
 		sock_len += sock_hlen;
 		vhost_len = sock_len + vhost_hlen;
 		headcount = get_rx_bufs(vq, vq->heads + nvq->done_idx,
@@ -838,7 +839,9 @@ static void handle_rx(struct vhost_net *net)
 			goto out;
 		/* OK, now we need to know about added descriptors. */
 		if (!headcount) {
-			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
+			if (unlikely(busyloop_intr)) {
+				vhost_poll_queue(&vq->poll);
+			} else if (unlikely(vhost_enable_notify(&net->dev, vq))) {
 				/* They have slipped one in as we were
 				 * doing that: check again. */
 				vhost_disable_notify(&net->dev, vq);
@@ -848,6 +851,7 @@ static void handle_rx(struct vhost_net *net)
 			 * they refilled. */
 			goto out;
 		}
+		busyloop_intr = false;
 		if (nvq->rx_ring)
 			msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
 		/* On overrun, truncate and discard */
-- 
cgit v1.2.3


From 0245abf8206fb573a3977558de2b7b2be6f3d9f8 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Fri, 29 Jun 2018 06:12:43 -0400
Subject: media: v4l2-ctrls.c: fix broken auto cluster handling

When you switch from auto to manual mode for an auto-cluster (e.g.
autogain+gain controls), then the current HW value has to be copied
to the current control value. However, has_changed was never set to
true, so new_to_cur didn't actually copy this value.

Reported-by: Hugues FRUCHET <hugues.fruchet@st.com>
Tested-by: Hugues FRUCHET <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-ctrls.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index d29e45516eb7..d1087573da34 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -3137,9 +3137,22 @@ static int try_or_set_cluster(struct v4l2_fh *fh, struct v4l2_ctrl *master,
 
 	/* If OK, then make the new values permanent. */
 	update_flag = is_cur_manual(master) != is_new_manual(master);
-	for (i = 0; i < master->ncontrols; i++)
+
+	for (i = 0; i < master->ncontrols; i++) {
+		/*
+		 * If we switch from auto to manual mode, and this cluster
+		 * contains volatile controls, then all non-master controls
+		 * have to be marked as changed. The 'new' value contains
+		 * the volatile value (obtained by update_from_auto_cluster),
+		 * which now has to become the current value.
+		 */
+		if (i && update_flag && is_new_manual(master) &&
+		    master->has_volatiles && master->cluster[i])
+			master->cluster[i]->has_changed = true;
+
 		new_to_cur(fh, master->cluster[i], ch_flags |
 			((update_flag && i > 0) ? V4L2_EVENT_CTRL_CH_FLAGS : 0));
+	}
 	return 0;
 }
 
-- 
cgit v1.2.3


From 967450c54300fd858b24e044ee960a1133c916a4 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 3 Jul 2018 15:42:43 +0300
Subject: selftests: forwarding: lib: extract ping and ping6 so they can be
 reused

Extract ping and ping6 command execution so the return value can be
checked by the caller, this is needed for port isolation tests that are
intended to fail.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index e073918bbe15..2bb9cf303c53 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -659,30 +659,40 @@ multipath_eval()
 ##############################################################################
 # Tests
 
-ping_test()
+ping_do()
 {
 	local if_name=$1
 	local dip=$2
 	local vrf_name
 
-	RET=0
-
 	vrf_name=$(master_name_get $if_name)
 	ip vrf exec $vrf_name $PING $dip -c 10 -i 0.1 -w 2 &> /dev/null
+}
+
+ping_test()
+{
+	RET=0
+
+	ping_do $1 $2
 	check_err $?
 	log_test "ping"
 }
 
-ping6_test()
+ping6_do()
 {
 	local if_name=$1
 	local dip=$2
 	local vrf_name
 
-	RET=0
-
 	vrf_name=$(master_name_get $if_name)
 	ip vrf exec $vrf_name $PING6 $dip -c 10 -i 0.1 -w 2 &> /dev/null
+}
+
+ping6_test()
+{
+	RET=0
+
+	ping6_do $1 $2
 	check_err $?
 	log_test "ping6"
 }
-- 
cgit v1.2.3


From a14e9fafaa3437a5e73e6ff521d3a351f173799b Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Tue, 3 Jul 2018 15:42:44 +0300
Subject: selftests: forwarding: test for bridge port isolation

This test checks if the bridge port isolation feature works as expected
by performing ping/ping6 tests between hosts that are isolated (should
not work) and between an isolated and non-isolated hosts (should work).
Same test is performed for flooding from and to isolated and
non-isolated ports.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/bridge_port_isolation.sh        | 151 +++++++++++++++++++++
 1 file changed, 151 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/bridge_port_isolation.sh

diff --git a/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh b/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh
new file mode 100755
index 000000000000..a43b4645c4de
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/bridge_port_isolation.sh
@@ -0,0 +1,151 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4 ping_ipv6 flooding"
+NUM_NETIFS=6
+CHECK_TC="yes"
+source lib.sh
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/24 2001:db8:1::1/64
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+h2_destroy()
+{
+	simple_if_fini $h2 192.0.2.2/24 2001:db8:1::2/64
+}
+
+h3_create()
+{
+	simple_if_init $h3 192.0.2.3/24 2001:db8:1::3/64
+}
+
+h3_destroy()
+{
+	simple_if_fini $h3 192.0.2.3/24 2001:db8:1::3/64
+}
+
+switch_create()
+{
+	ip link add dev br0 type bridge
+
+	ip link set dev $swp1 master br0
+	ip link set dev $swp2 master br0
+	ip link set dev $swp3 master br0
+
+	ip link set dev $swp1 type bridge_slave isolated on
+	check_err $? "Can't set isolation on port $swp1"
+	ip link set dev $swp2 type bridge_slave isolated on
+	check_err $? "Can't set isolation on port $swp2"
+	ip link set dev $swp3 type bridge_slave isolated off
+	check_err $? "Can't disable isolation on port $swp3"
+
+	ip link set dev br0 up
+	ip link set dev $swp1 up
+	ip link set dev $swp2 up
+	ip link set dev $swp3 up
+}
+
+switch_destroy()
+{
+	ip link set dev $swp3 down
+	ip link set dev $swp2 down
+	ip link set dev $swp1 down
+
+	ip link del dev br0
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	RET=0
+	ping_do $h1 192.0.2.2
+	check_fail $? "Ping worked when it should not have"
+
+	RET=0
+	ping_do $h3 192.0.2.2
+	check_err $? "Ping didn't work when it should have"
+
+	log_test "Isolated port ping"
+}
+
+ping_ipv6()
+{
+	RET=0
+	ping6_do $h1 2001:db8:1::2
+	check_fail $? "Ping6 worked when it should not have"
+
+	RET=0
+	ping6_do $h3 2001:db8:1::2
+	check_err $? "Ping6 didn't work when it should have"
+
+	log_test "Isolated port ping6"
+}
+
+flooding()
+{
+	local mac=de:ad:be:ef:13:37
+	local ip=192.0.2.100
+
+	RET=0
+	flood_test_do false $mac $ip $h1 $h2
+	check_err $? "Packet was flooded when it should not have been"
+
+	RET=0
+	flood_test_do true $mac $ip $h3 $h2
+	check_err $? "Packet was not flooded when it should have been"
+
+	log_test "Isolated port flooding"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 4d1e4545a65903a09f5d15d32a3fbb6131a8d11e Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Mon, 2 Jul 2018 08:43:02 -0400
Subject: media: mark entity-intf links as IMMUTABLE

Currently links between entities and an interface are just marked as
ENABLED. But (at least today) these links cannot be disabled by userspace
or the driver, so they should also be marked as IMMUTABLE.

It might become possible that drivers can disable such links (if for some
reason the device node cannot be used), so we might need to add a new link
flag at some point to mark interface links that can be changed by the driver
but not by userspace.

Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-core/dvbdev.c       | 18 ++++++++++++------
 drivers/media/v4l2-core/v4l2-dev.c    |  3 ++-
 drivers/media/v4l2-core/v4l2-device.c |  3 ++-
 3 files changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/media/dvb-core/dvbdev.c b/drivers/media/dvb-core/dvbdev.c
index 64d6793674b9..3c8778570331 100644
--- a/drivers/media/dvb-core/dvbdev.c
+++ b/drivers/media/dvb-core/dvbdev.c
@@ -440,8 +440,10 @@ static int dvb_register_media_device(struct dvb_device *dvbdev,
 	if (!dvbdev->entity)
 		return 0;
 
-	link = media_create_intf_link(dvbdev->entity, &dvbdev->intf_devnode->intf,
-				      MEDIA_LNK_FL_ENABLED);
+	link = media_create_intf_link(dvbdev->entity,
+				      &dvbdev->intf_devnode->intf,
+				      MEDIA_LNK_FL_ENABLED |
+				      MEDIA_LNK_FL_IMMUTABLE);
 	if (!link)
 		return -ENOMEM;
 #endif
@@ -599,7 +601,8 @@ static int dvb_create_io_intf_links(struct dvb_adapter *adap,
 			if (strncmp(entity->name, name, strlen(name)))
 				continue;
 			link = media_create_intf_link(entity, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
@@ -754,14 +757,16 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 	media_device_for_each_intf(intf, mdev) {
 		if (intf->type == MEDIA_INTF_T_DVB_CA && ca) {
 			link = media_create_intf_link(ca, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
 
 		if (intf->type == MEDIA_INTF_T_DVB_FE && tuner) {
 			link = media_create_intf_link(tuner, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
@@ -773,7 +778,8 @@ int dvb_create_media_graph(struct dvb_adapter *adap,
 		 */
 		if (intf->type == MEDIA_INTF_T_DVB_DVR && demux) {
 			link = media_create_intf_link(demux, intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link)
 				return -ENOMEM;
 		}
diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 4ffd7d60a901..5f43f63fa700 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -808,7 +808,8 @@ static int video_register_media_controller(struct video_device *vdev, int type)
 
 		link = media_create_intf_link(&vdev->entity,
 					      &vdev->intf_devnode->intf,
-					      MEDIA_LNK_FL_ENABLED);
+					      MEDIA_LNK_FL_ENABLED |
+					      MEDIA_LNK_FL_IMMUTABLE);
 		if (!link) {
 			media_devnode_remove(vdev->intf_devnode);
 			media_device_unregister_entity(&vdev->entity);
diff --git a/drivers/media/v4l2-core/v4l2-device.c b/drivers/media/v4l2-core/v4l2-device.c
index 937c6de85606..3940e55c72f1 100644
--- a/drivers/media/v4l2-core/v4l2-device.c
+++ b/drivers/media/v4l2-core/v4l2-device.c
@@ -267,7 +267,8 @@ int v4l2_device_register_subdev_nodes(struct v4l2_device *v4l2_dev)
 
 			link = media_create_intf_link(&sd->entity,
 						      &vdev->intf_devnode->intf,
-						      MEDIA_LNK_FL_ENABLED);
+						      MEDIA_LNK_FL_ENABLED |
+						      MEDIA_LNK_FL_IMMUTABLE);
 			if (!link) {
 				err = -ENOMEM;
 				goto clean_up;
-- 
cgit v1.2.3


From be2fff656322e82f215730839063c2c2ca73d14b Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Mon, 2 Jul 2018 11:36:05 -0400
Subject: media: add helpers for memory-to-memory media controller

A memory-to-memory pipeline device consists in three
entities: two DMA engine and one video processing entities.
The DMA engine entities are linked to a V4L interface.

This commit add a new v4l2_m2m_{un}register_media_controller
API to register this topology.

For instance, a typical mem2mem device topology would
look like this:

Device topology
- entity 1: source (1 pad, 1 link)
            type Node subtype V4L flags 0
	pad0: Source
		-> "proc":1 [ENABLED,IMMUTABLE]

- entity 3: proc (2 pads, 2 links)
            type Node subtype Unknown flags 0
	pad0: Source
		-> "sink":0 [ENABLED,IMMUTABLE]
	pad1: Sink
		<- "source":0 [ENABLED,IMMUTABLE]

- entity 6: sink (1 pad, 1 link)
            type Node subtype V4L flags 0
	pad0: Sink
		<- "proc":0 [ENABLED,IMMUTABLE]

[hans.verkuil@cisco.com: mark interface links as IMMUTABLE]

Suggested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-dev.c     |  13 ++-
 drivers/media/v4l2-core/v4l2-mem2mem.c | 190 +++++++++++++++++++++++++++++++++
 include/media/v4l2-mem2mem.h           |  19 ++++
 3 files changed, 217 insertions(+), 5 deletions(-)

diff --git a/drivers/media/v4l2-core/v4l2-dev.c b/drivers/media/v4l2-core/v4l2-dev.c
index 5f43f63fa700..69e775930fc4 100644
--- a/drivers/media/v4l2-core/v4l2-dev.c
+++ b/drivers/media/v4l2-core/v4l2-dev.c
@@ -202,7 +202,7 @@ static void v4l2_device_release(struct device *cd)
 	mutex_unlock(&videodev_lock);
 
 #if defined(CONFIG_MEDIA_CONTROLLER)
-	if (v4l2_dev->mdev) {
+	if (v4l2_dev->mdev && vdev->vfl_dir != VFL_DIR_M2M) {
 		/* Remove interfaces and interface links */
 		media_devnode_remove(vdev->intf_devnode);
 		if (vdev->entity.function != MEDIA_ENT_F_UNKNOWN)
@@ -733,19 +733,22 @@ static void determine_valid_ioctls(struct video_device *vdev)
 			BASE_VIDIOC_PRIVATE);
 }
 
-static int video_register_media_controller(struct video_device *vdev, int type)
+static int video_register_media_controller(struct video_device *vdev)
 {
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	u32 intf_type;
 	int ret;
 
-	if (!vdev->v4l2_dev->mdev)
+	/* Memory-to-memory devices are more complex and use
+	 * their own function to register its mc entities.
+	 */
+	if (!vdev->v4l2_dev->mdev || vdev->vfl_dir == VFL_DIR_M2M)
 		return 0;
 
 	vdev->entity.obj_type = MEDIA_ENTITY_TYPE_VIDEO_DEVICE;
 	vdev->entity.function = MEDIA_ENT_F_UNKNOWN;
 
-	switch (type) {
+	switch (vdev->vfl_type) {
 	case VFL_TYPE_GRABBER:
 		intf_type = MEDIA_INTF_T_V4L_VIDEO;
 		vdev->entity.function = MEDIA_ENT_F_IO_V4L;
@@ -994,7 +997,7 @@ int __video_register_device(struct video_device *vdev,
 	v4l2_device_get(vdev->v4l2_dev);
 
 	/* Part 5: Register the entity. */
-	ret = video_register_media_controller(vdev, type);
+	ret = video_register_media_controller(vdev);
 
 	/* Part 6: Activate this minor. The char device can now be used. */
 	set_bit(V4L2_FL_REGISTERED, &vdev->flags);
diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 5f9cd5b74cda..725da74d15d8 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -17,9 +17,11 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 
+#include <media/media-device.h>
 #include <media/videobuf2-v4l2.h>
 #include <media/v4l2-mem2mem.h>
 #include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
 #include <media/v4l2-fh.h>
 #include <media/v4l2-event.h>
 
@@ -50,6 +52,17 @@ module_param(debug, bool, 0644);
  * offsets but for different queues */
 #define DST_QUEUE_OFF_BASE	(1 << 30)
 
+enum v4l2_m2m_entity_type {
+	MEM2MEM_ENT_TYPE_SOURCE,
+	MEM2MEM_ENT_TYPE_SINK,
+	MEM2MEM_ENT_TYPE_PROC
+};
+
+static const char * const m2m_entity_name[] = {
+	"source",
+	"sink",
+	"proc"
+};
 
 /**
  * struct v4l2_m2m_dev - per-device context
@@ -60,6 +73,15 @@ module_param(debug, bool, 0644);
  */
 struct v4l2_m2m_dev {
 	struct v4l2_m2m_ctx	*curr_ctx;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_entity	*source;
+	struct media_pad	source_pad;
+	struct media_entity	sink;
+	struct media_pad	sink_pad;
+	struct media_entity	proc;
+	struct media_pad	proc_pads[2];
+	struct media_intf_devnode *intf_devnode;
+#endif
 
 	struct list_head	job_queue;
 	spinlock_t		job_spinlock;
@@ -594,6 +616,174 @@ int v4l2_m2m_mmap(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
 }
 EXPORT_SYMBOL(v4l2_m2m_mmap);
 
+#if defined(CONFIG_MEDIA_CONTROLLER)
+void v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev)
+{
+	media_remove_intf_links(&m2m_dev->intf_devnode->intf);
+	media_devnode_remove(m2m_dev->intf_devnode);
+
+	media_entity_remove_links(m2m_dev->source);
+	media_entity_remove_links(&m2m_dev->sink);
+	media_entity_remove_links(&m2m_dev->proc);
+	media_device_unregister_entity(m2m_dev->source);
+	media_device_unregister_entity(&m2m_dev->sink);
+	media_device_unregister_entity(&m2m_dev->proc);
+	kfree(m2m_dev->source->name);
+	kfree(m2m_dev->sink.name);
+	kfree(m2m_dev->proc.name);
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_unregister_media_controller);
+
+static int v4l2_m2m_register_entity(struct media_device *mdev,
+	struct v4l2_m2m_dev *m2m_dev, enum v4l2_m2m_entity_type type,
+	struct video_device *vdev, int function)
+{
+	struct media_entity *entity;
+	struct media_pad *pads;
+	char *name;
+	unsigned int len;
+	int num_pads;
+	int ret;
+
+	switch (type) {
+	case MEM2MEM_ENT_TYPE_SOURCE:
+		entity = m2m_dev->source;
+		pads = &m2m_dev->source_pad;
+		pads[0].flags = MEDIA_PAD_FL_SOURCE;
+		num_pads = 1;
+		break;
+	case MEM2MEM_ENT_TYPE_SINK:
+		entity = &m2m_dev->sink;
+		pads = &m2m_dev->sink_pad;
+		pads[0].flags = MEDIA_PAD_FL_SINK;
+		num_pads = 1;
+		break;
+	case MEM2MEM_ENT_TYPE_PROC:
+		entity = &m2m_dev->proc;
+		pads = m2m_dev->proc_pads;
+		pads[0].flags = MEDIA_PAD_FL_SINK;
+		pads[1].flags = MEDIA_PAD_FL_SOURCE;
+		num_pads = 2;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	entity->obj_type = MEDIA_ENTITY_TYPE_BASE;
+	if (type != MEM2MEM_ENT_TYPE_PROC) {
+		entity->info.dev.major = VIDEO_MAJOR;
+		entity->info.dev.minor = vdev->minor;
+	}
+	len = strlen(vdev->name) + 2 + strlen(m2m_entity_name[type]);
+	name = kmalloc(len, GFP_KERNEL);
+	if (!name)
+		return -ENOMEM;
+	snprintf(name, len, "%s-%s", vdev->name, m2m_entity_name[type]);
+	entity->name = name;
+	entity->function = function;
+
+	ret = media_entity_pads_init(entity, num_pads, pads);
+	if (ret)
+		return ret;
+	ret = media_device_register_entity(mdev, entity);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev,
+		struct video_device *vdev, int function)
+{
+	struct media_device *mdev = vdev->v4l2_dev->mdev;
+	struct media_link *link;
+	int ret;
+
+	if (!mdev)
+		return 0;
+
+	/* A memory-to-memory device consists in two
+	 * DMA engine and one video processing entities.
+	 * The DMA engine entities are linked to a V4L interface
+	 */
+
+	/* Create the three entities with their pads */
+	m2m_dev->source = &vdev->entity;
+	ret = v4l2_m2m_register_entity(mdev, m2m_dev,
+			MEM2MEM_ENT_TYPE_SOURCE, vdev, MEDIA_ENT_F_IO_V4L);
+	if (ret)
+		return ret;
+	ret = v4l2_m2m_register_entity(mdev, m2m_dev,
+			MEM2MEM_ENT_TYPE_PROC, vdev, function);
+	if (ret)
+		goto err_rel_entity0;
+	ret = v4l2_m2m_register_entity(mdev, m2m_dev,
+			MEM2MEM_ENT_TYPE_SINK, vdev, MEDIA_ENT_F_IO_V4L);
+	if (ret)
+		goto err_rel_entity1;
+
+	/* Connect the three entities */
+	ret = media_create_pad_link(m2m_dev->source, 0, &m2m_dev->proc, 1,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (ret)
+		goto err_rel_entity2;
+
+	ret = media_create_pad_link(&m2m_dev->proc, 0, &m2m_dev->sink, 0,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (ret)
+		goto err_rm_links0;
+
+	/* Create video interface */
+	m2m_dev->intf_devnode = media_devnode_create(mdev,
+			MEDIA_INTF_T_V4L_VIDEO, 0,
+			VIDEO_MAJOR, vdev->minor);
+	if (!m2m_dev->intf_devnode) {
+		ret = -ENOMEM;
+		goto err_rm_links1;
+	}
+
+	/* Connect the two DMA engines to the interface */
+	link = media_create_intf_link(m2m_dev->source,
+			&m2m_dev->intf_devnode->intf,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (!link) {
+		ret = -ENOMEM;
+		goto err_rm_devnode;
+	}
+
+	link = media_create_intf_link(&m2m_dev->sink,
+			&m2m_dev->intf_devnode->intf,
+			MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+	if (!link) {
+		ret = -ENOMEM;
+		goto err_rm_intf_link;
+	}
+	return 0;
+
+err_rm_intf_link:
+	media_remove_intf_links(&m2m_dev->intf_devnode->intf);
+err_rm_devnode:
+	media_devnode_remove(m2m_dev->intf_devnode);
+err_rm_links1:
+	media_entity_remove_links(&m2m_dev->sink);
+err_rm_links0:
+	media_entity_remove_links(&m2m_dev->proc);
+	media_entity_remove_links(m2m_dev->source);
+err_rel_entity2:
+	media_device_unregister_entity(&m2m_dev->proc);
+	kfree(m2m_dev->proc.name);
+err_rel_entity1:
+	media_device_unregister_entity(&m2m_dev->sink);
+	kfree(m2m_dev->sink.name);
+err_rel_entity0:
+	media_device_unregister_entity(m2m_dev->source);
+	kfree(m2m_dev->source->name);
+	return ret;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_register_media_controller);
+#endif
+
 struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops)
 {
 	struct v4l2_m2m_dev *m2m_dev;
diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index 8f4b208cfee7..af48b1eca025 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -47,6 +47,7 @@ struct v4l2_m2m_ops {
 	void (*job_abort)(void *priv);
 };
 
+struct video_device;
 struct v4l2_m2m_dev;
 
 /**
@@ -322,6 +323,24 @@ int v4l2_m2m_mmap(struct file *file, struct v4l2_m2m_ctx *m2m_ctx,
  */
 struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops);
 
+#if defined(CONFIG_MEDIA_CONTROLLER)
+void v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev);
+int v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev,
+			struct video_device *vdev, int function);
+#else
+static inline void
+v4l2_m2m_unregister_media_controller(struct v4l2_m2m_dev *m2m_dev)
+{
+}
+
+static inline int
+v4l2_m2m_register_media_controller(struct v4l2_m2m_dev *m2m_dev,
+		struct video_device *vdev, int function)
+{
+	return 0;
+}
+#endif
+
 /**
  * v4l2_m2m_release() - cleans up and frees a m2m_dev structure
  *
-- 
cgit v1.2.3


From e35f702151346b7a97979d9d78d66ab461ba366f Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 2 Jul 2018 11:36:06 -0400
Subject: media: vim2m: add media device

Request API requires a media node. Add one to the vim2m driver so we can
use requests with it.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vim2m.c | 41 +++++++++++++++++++++++++++++++++++++----
 1 file changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/vim2m.c b/drivers/media/platform/vim2m.c
index 1393aa806462..462099a141e4 100644
--- a/drivers/media/platform/vim2m.c
+++ b/drivers/media/platform/vim2m.c
@@ -140,6 +140,9 @@ static struct vim2m_fmt *find_format(struct v4l2_format *f)
 struct vim2m_dev {
 	struct v4l2_device	v4l2_dev;
 	struct video_device	vfd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device	mdev;
+#endif
 
 	atomic_t		num_inst;
 	struct mutex		dev_mutex;
@@ -1016,7 +1019,7 @@ static int vim2m_probe(struct platform_device *pdev)
 	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
 	if (ret) {
 		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
-		goto unreg_dev;
+		goto unreg_v4l2;
 	}
 
 	video_set_drvdata(vfd, dev);
@@ -1030,15 +1033,39 @@ static int vim2m_probe(struct platform_device *pdev)
 	if (IS_ERR(dev->m2m_dev)) {
 		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem device\n");
 		ret = PTR_ERR(dev->m2m_dev);
-		goto err_m2m;
+		goto unreg_dev;
+	}
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->mdev.dev = &pdev->dev;
+	strlcpy(dev->mdev.model, "vim2m", sizeof(dev->mdev.model));
+	media_device_init(&dev->mdev);
+	dev->v4l2_dev.mdev = &dev->mdev;
+
+	ret = v4l2_m2m_register_media_controller(dev->m2m_dev,
+			vfd, MEDIA_ENT_F_PROC_VIDEO_SCALER);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller\n");
+		goto unreg_m2m;
 	}
 
+	ret = media_device_register(&dev->mdev);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register mem2mem media device\n");
+		goto unreg_m2m_mc;
+	}
+#endif
 	return 0;
 
-err_m2m:
+#ifdef CONFIG_MEDIA_CONTROLLER
+unreg_m2m_mc:
+	v4l2_m2m_unregister_media_controller(dev->m2m_dev);
+unreg_m2m:
 	v4l2_m2m_release(dev->m2m_dev);
-	video_unregister_device(&dev->vfd);
+#endif
 unreg_dev:
+	video_unregister_device(&dev->vfd);
+unreg_v4l2:
 	v4l2_device_unregister(&dev->v4l2_dev);
 
 	return ret;
@@ -1049,6 +1076,12 @@ static int vim2m_remove(struct platform_device *pdev)
 	struct vim2m_dev *dev = platform_get_drvdata(pdev);
 
 	v4l2_info(&dev->v4l2_dev, "Removing " MEM2MEM_NAME);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	media_device_unregister(&dev->mdev);
+	v4l2_m2m_unregister_media_controller(dev->m2m_dev);
+	media_device_cleanup(&dev->mdev);
+#endif
 	v4l2_m2m_release(dev->m2m_dev);
 	del_timer_sync(&dev->timer);
 	video_unregister_device(&dev->vfd);
-- 
cgit v1.2.3


From d24c029ed3fb64f4b61ff38b8db4e2b35fa140a8 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:23 -0400
Subject: media: rcar-vin: Rename 'digital' to 'parallel'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As the term 'digital' is used all over the rcar-vin code in place of
'parallel', rename all the occurrencies.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 72 ++++++++++++++---------------
 drivers/media/platform/rcar-vin/rcar-dma.c  |  4 +-
 drivers/media/platform/rcar-vin/rcar-v4l2.c | 12 ++---
 drivers/media/platform/rcar-vin/rcar-vin.h  |  6 +--
 4 files changed, 47 insertions(+), 47 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index e6a010ee4ba1..2a8ad99777ec 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -376,12 +376,12 @@ static int rvin_find_pad(struct v4l2_subdev *sd, int direction)
 }
 
 /* -----------------------------------------------------------------------------
- * Digital async notifier
+ * Parallel async notifier
  */
 
 /* The vin lock should be held when calling the subdevice attach and detach */
-static int rvin_digital_subdevice_attach(struct rvin_dev *vin,
-					 struct v4l2_subdev *subdev)
+static int rvin_parallel_subdevice_attach(struct rvin_dev *vin,
+					  struct v4l2_subdev *subdev)
 {
 	struct v4l2_subdev_mbus_code_enum code = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
@@ -392,15 +392,15 @@ static int rvin_digital_subdevice_attach(struct rvin_dev *vin,
 	ret = rvin_find_pad(subdev, MEDIA_PAD_FL_SOURCE);
 	if (ret < 0)
 		return ret;
-	vin->digital->source_pad = ret;
+	vin->parallel->source_pad = ret;
 
 	ret = rvin_find_pad(subdev, MEDIA_PAD_FL_SINK);
-	vin->digital->sink_pad = ret < 0 ? 0 : ret;
+	vin->parallel->sink_pad = ret < 0 ? 0 : ret;
 
 	/* Find compatible subdevices mbus format */
 	vin->mbus_code = 0;
 	code.index = 0;
-	code.pad = vin->digital->source_pad;
+	code.pad = vin->parallel->source_pad;
 	while (!vin->mbus_code &&
 	       !v4l2_subdev_call(subdev, pad, enum_mbus_code, NULL, &code)) {
 		code.index++;
@@ -450,21 +450,21 @@ static int rvin_digital_subdevice_attach(struct rvin_dev *vin,
 
 	vin->vdev.ctrl_handler = &vin->ctrl_handler;
 
-	vin->digital->subdev = subdev;
+	vin->parallel->subdev = subdev;
 
 	return 0;
 }
 
-static void rvin_digital_subdevice_detach(struct rvin_dev *vin)
+static void rvin_parallel_subdevice_detach(struct rvin_dev *vin)
 {
 	rvin_v4l2_unregister(vin);
 	v4l2_ctrl_handler_free(&vin->ctrl_handler);
 
 	vin->vdev.ctrl_handler = NULL;
-	vin->digital->subdev = NULL;
+	vin->parallel->subdev = NULL;
 }
 
-static int rvin_digital_notify_complete(struct v4l2_async_notifier *notifier)
+static int rvin_parallel_notify_complete(struct v4l2_async_notifier *notifier)
 {
 	struct rvin_dev *vin = notifier_to_vin(notifier);
 	int ret;
@@ -478,28 +478,28 @@ static int rvin_digital_notify_complete(struct v4l2_async_notifier *notifier)
 	return rvin_v4l2_register(vin);
 }
 
-static void rvin_digital_notify_unbind(struct v4l2_async_notifier *notifier,
-				       struct v4l2_subdev *subdev,
-				       struct v4l2_async_subdev *asd)
+static void rvin_parallel_notify_unbind(struct v4l2_async_notifier *notifier,
+					struct v4l2_subdev *subdev,
+					struct v4l2_async_subdev *asd)
 {
 	struct rvin_dev *vin = notifier_to_vin(notifier);
 
-	vin_dbg(vin, "unbind digital subdev %s\n", subdev->name);
+	vin_dbg(vin, "unbind parallel subdev %s\n", subdev->name);
 
 	mutex_lock(&vin->lock);
-	rvin_digital_subdevice_detach(vin);
+	rvin_parallel_subdevice_detach(vin);
 	mutex_unlock(&vin->lock);
 }
 
-static int rvin_digital_notify_bound(struct v4l2_async_notifier *notifier,
-				     struct v4l2_subdev *subdev,
-				     struct v4l2_async_subdev *asd)
+static int rvin_parallel_notify_bound(struct v4l2_async_notifier *notifier,
+				      struct v4l2_subdev *subdev,
+				      struct v4l2_async_subdev *asd)
 {
 	struct rvin_dev *vin = notifier_to_vin(notifier);
 	int ret;
 
 	mutex_lock(&vin->lock);
-	ret = rvin_digital_subdevice_attach(vin, subdev);
+	ret = rvin_parallel_subdevice_attach(vin, subdev);
 	mutex_unlock(&vin->lock);
 	if (ret)
 		return ret;
@@ -507,21 +507,21 @@ static int rvin_digital_notify_bound(struct v4l2_async_notifier *notifier,
 	v4l2_set_subdev_hostdata(subdev, vin);
 
 	vin_dbg(vin, "bound subdev %s source pad: %u sink pad: %u\n",
-		subdev->name, vin->digital->source_pad,
-		vin->digital->sink_pad);
+		subdev->name, vin->parallel->source_pad,
+		vin->parallel->sink_pad);
 
 	return 0;
 }
 
-static const struct v4l2_async_notifier_operations rvin_digital_notify_ops = {
-	.bound = rvin_digital_notify_bound,
-	.unbind = rvin_digital_notify_unbind,
-	.complete = rvin_digital_notify_complete,
+static const struct v4l2_async_notifier_operations rvin_parallel_notify_ops = {
+	.bound = rvin_parallel_notify_bound,
+	.unbind = rvin_parallel_notify_unbind,
+	.complete = rvin_parallel_notify_complete,
 };
 
-static int rvin_digital_parse_v4l2(struct device *dev,
-				   struct v4l2_fwnode_endpoint *vep,
-				   struct v4l2_async_subdev *asd)
+static int rvin_parallel_parse_v4l2(struct device *dev,
+				    struct v4l2_fwnode_endpoint *vep,
+				    struct v4l2_async_subdev *asd)
 {
 	struct rvin_dev *vin = dev_get_drvdata(dev);
 	struct rvin_graph_entity *rvge =
@@ -546,28 +546,28 @@ static int rvin_digital_parse_v4l2(struct device *dev,
 		return -EINVAL;
 	}
 
-	vin->digital = rvge;
+	vin->parallel = rvge;
 
 	return 0;
 }
 
-static int rvin_digital_graph_init(struct rvin_dev *vin)
+static int rvin_parallel_graph_init(struct rvin_dev *vin)
 {
 	int ret;
 
 	ret = v4l2_async_notifier_parse_fwnode_endpoints(
 		vin->dev, &vin->notifier,
-		sizeof(struct rvin_graph_entity), rvin_digital_parse_v4l2);
+		sizeof(struct rvin_graph_entity), rvin_parallel_parse_v4l2);
 	if (ret)
 		return ret;
 
-	if (!vin->digital)
+	if (!vin->parallel)
 		return -ENODEV;
 
-	vin_dbg(vin, "Found digital subdevice %pOF\n",
-		to_of_node(vin->digital->asd.match.fwnode));
+	vin_dbg(vin, "Found parallel subdevice %pOF\n",
+		to_of_node(vin->parallel->asd.match.fwnode));
 
-	vin->notifier.ops = &rvin_digital_notify_ops;
+	vin->notifier.ops = &rvin_parallel_notify_ops;
 	ret = v4l2_async_notifier_register(&vin->v4l2_dev, &vin->notifier);
 	if (ret < 0) {
 		vin_err(vin, "Notifier registration failed\n");
@@ -1136,7 +1136,7 @@ static int rcar_vin_probe(struct platform_device *pdev)
 	if (vin->info->use_mc)
 		ret = rvin_mc_init(vin);
 	else
-		ret = rvin_digital_graph_init(vin);
+		ret = rvin_parallel_graph_init(vin);
 	if (ret < 0)
 		goto error;
 
diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
index cfe5d7a9d44e..ce9502f15f5b 100644
--- a/drivers/media/platform/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -733,7 +733,7 @@ static int rvin_setup(struct rvin_dev *vin)
 		vnmc |= VNMC_BPS;
 
 	if (vin->info->model == RCAR_GEN3) {
-		/* Select between CSI-2 and Digital input */
+		/* Select between CSI-2 and parallel input */
 		if (vin->mbus_cfg.type == V4L2_MBUS_CSI2)
 			vnmc &= ~VNMC_DPINE;
 		else
@@ -1088,7 +1088,7 @@ static int rvin_set_stream(struct rvin_dev *vin, int on)
 
 	/* No media controller used, simply pass operation to subdevice. */
 	if (!vin->info->use_mc) {
-		ret = v4l2_subdev_call(vin->digital->subdev, video, s_stream,
+		ret = v4l2_subdev_call(vin->parallel->subdev, video, s_stream,
 				       on);
 
 		return ret == -ENOIOCTLCMD ? 0 : ret;
diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c
index e78fba84d590..87a718b1c2e6 100644
--- a/drivers/media/platform/rcar-vin/rcar-v4l2.c
+++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c
@@ -144,7 +144,7 @@ static int rvin_reset_format(struct rvin_dev *vin)
 {
 	struct v4l2_subdev_format fmt = {
 		.which = V4L2_SUBDEV_FORMAT_ACTIVE,
-		.pad = vin->digital->source_pad,
+		.pad = vin->parallel->source_pad,
 	};
 	int ret;
 
@@ -175,7 +175,7 @@ static int rvin_try_format(struct rvin_dev *vin, u32 which,
 	struct v4l2_subdev_pad_config *pad_cfg;
 	struct v4l2_subdev_format format = {
 		.which = which,
-		.pad = vin->digital->source_pad,
+		.pad = vin->parallel->source_pad,
 	};
 	enum v4l2_field field;
 	u32 width, height;
@@ -517,7 +517,7 @@ static int rvin_enum_dv_timings(struct file *file, void *priv_fh,
 	if (timings->pad)
 		return -EINVAL;
 
-	timings->pad = vin->digital->sink_pad;
+	timings->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, enum_dv_timings, timings);
 
@@ -569,7 +569,7 @@ static int rvin_dv_timings_cap(struct file *file, void *priv_fh,
 	if (cap->pad)
 		return -EINVAL;
 
-	cap->pad = vin->digital->sink_pad;
+	cap->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, dv_timings_cap, cap);
 
@@ -587,7 +587,7 @@ static int rvin_g_edid(struct file *file, void *fh, struct v4l2_edid *edid)
 	if (edid->pad)
 		return -EINVAL;
 
-	edid->pad = vin->digital->sink_pad;
+	edid->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, get_edid, edid);
 
@@ -605,7 +605,7 @@ static int rvin_s_edid(struct file *file, void *fh, struct v4l2_edid *edid)
 	if (edid->pad)
 		return -EINVAL;
 
-	edid->pad = vin->digital->sink_pad;
+	edid->pad = vin->parallel->sink_pad;
 
 	ret = v4l2_subdev_call(sd, pad, set_edid, edid);
 
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
index ff747e22d8cf..b89f63b8ecdc 100644
--- a/drivers/media/platform/rcar-vin/rcar-vin.h
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -148,7 +148,7 @@ struct rvin_info {
  * @v4l2_dev:		V4L2 device
  * @ctrl_handler:	V4L2 control handler
  * @notifier:		V4L2 asynchronous subdevs notifier
- * @digital:		entity in the DT for local digital subdevice
+ * @parallel:		entity in the DT for local parallel subdevice
  *
  * @group:		Gen3 CSI group
  * @id:			Gen3 group id for this VIN
@@ -184,7 +184,7 @@ struct rvin_dev {
 	struct v4l2_device v4l2_dev;
 	struct v4l2_ctrl_handler ctrl_handler;
 	struct v4l2_async_notifier notifier;
-	struct rvin_graph_entity *digital;
+	struct rvin_graph_entity *parallel;
 
 	struct rvin_group *group;
 	unsigned int id;
@@ -211,7 +211,7 @@ struct rvin_dev {
 	v4l2_std_id std;
 };
 
-#define vin_to_source(vin)		((vin)->digital->subdev)
+#define vin_to_source(vin)		((vin)->parallel->subdev)
 
 /* Debug */
 #define vin_dbg(d, fmt, arg...)		dev_dbg(d->dev, fmt, ##arg)
-- 
cgit v1.2.3


From 30e99ed6dbdde68f5ad23db3a5872c3c247526b6 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Tue, 3 Jul 2018 13:45:12 +0000
Subject: net: sched: act_pedit: fix possible memory leak in tcf_pedit_init()

'keys_ex' is malloced by tcf_pedit_keys_ex_parse() in tcf_pedit_init()
but not all of the error handle path free it, this may cause memory
leak. This patch fix it.

Fixes: 71d0ed7079df ("net/act_pedit: Support using offset relative to the conventional network headers")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 25 ++++++++++++++++---------
 1 file changed, 16 insertions(+), 9 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 55bc96b610e8..e43aef28fdac 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -175,32 +175,35 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (!tcf_idr_check(tn, parm->index, a, bind)) {
 		if (!parm->nkeys) {
 			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto out_free;
 		}
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_pedit_ops, bind, false);
 		if (ret)
-			return ret;
+			goto out_free;
 		p = to_pedit(*a);
 		keys = kmalloc(ksize, GFP_KERNEL);
 		if (!keys) {
 			tcf_idr_release(*a, bind);
-			kfree(keys_ex);
-			return -ENOMEM;
+			ret = -ENOMEM;
+			goto out_free;
 		}
 		ret = ACT_P_CREATED;
 	} else {
 		if (bind)
-			return 0;
+			goto out_free;
 		tcf_idr_release(*a, bind);
-		if (!ovr)
-			return -EEXIST;
+		if (!ovr) {
+			ret = -EEXIST;
+			goto out_free;
+		}
 		p = to_pedit(*a);
 		if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
 			keys = kmalloc(ksize, GFP_KERNEL);
 			if (!keys) {
-				kfree(keys_ex);
-				return -ENOMEM;
+				ret = -ENOMEM;
+				goto out_free;
 			}
 		}
 	}
@@ -222,6 +225,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+out_free:
+	kfree(keys_ex);
+	return ret;
+
 }
 
 static void tcf_pedit_cleanup(struct tc_action *a)
-- 
cgit v1.2.3


From a561e9e0944aea3e8683c3ab17219d6942ad3ca8 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:24 -0400
Subject: media: rcar-vin: Remove two empty lines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove un-necessary empty lines.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 2a8ad99777ec..1548b409806d 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -707,11 +707,9 @@ static int rvin_mc_parse_of_endpoint(struct device *dev,
 		return -EINVAL;
 
 	if (!of_device_is_available(to_of_node(asd->match.fwnode))) {
-
 		vin_dbg(vin, "OF device %pOF disabled, ignoring\n",
 			to_of_node(asd->match.fwnode));
 		return -ENOTCONN;
-
 	}
 
 	if (vin->group->csi[vep->base.id].fwnode) {
-- 
cgit v1.2.3


From 03fc5d4ffb0da005f0dce02d7c015821681e260c Mon Sep 17 00:00:00 2001
From: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Date: Tue, 3 Jul 2018 17:06:49 +0200
Subject: net: usb: asix: allow optionally getting mac address from device tree

For Embedded use where e.g. AX88772B chips may be used without external
EEPROMs the boot loader may choose to pass the MAC address to be used
via device tree. Therefore, allow for optionally getting the MAC
address from device tree data e.g. as follows (excerpt from a T30 based
board, local-mac-address to be filled in by boot loader):

/* EHCI instance 1: USB2_DP/N -> AX88772B */
usb@7d004000 {
	status = "okay";
	#address-cells = <1>;
	#size-cells = <0>;
	asix@1 {
		reg = <1>;
		local-mac-address = [00 00 00 00 00 00];
	};
};

Signed-off-by: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/asix_devices.c | 38 +++++++++++++++++++++++---------------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 3d4f7959dabb..8f41c6bda8e5 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -691,24 +691,32 @@ static int ax88772_bind(struct usbnet *dev, struct usb_interface *intf)
 	u32 phyid;
 	struct asix_common_private *priv;
 
-	usbnet_get_endpoints(dev,intf);
+	usbnet_get_endpoints(dev, intf);
 
-	/* Get the MAC address */
-	if (dev->driver_info->data & FLAG_EEPROM_MAC) {
-		for (i = 0; i < (ETH_ALEN >> 1); i++) {
-			ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM, 0x04 + i,
-					    0, 2, buf + i * 2, 0);
-			if (ret < 0)
-				break;
-		}
+	/* Maybe the boot loader passed the MAC address via device tree */
+	if (!eth_platform_get_mac_address(&dev->udev->dev, buf)) {
+		netif_dbg(dev, ifup, dev->net,
+			  "MAC address read from device tree");
 	} else {
-		ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID,
-				0, 0, ETH_ALEN, buf, 0);
-	}
+		/* Try getting the MAC address from EEPROM */
+		if (dev->driver_info->data & FLAG_EEPROM_MAC) {
+			for (i = 0; i < (ETH_ALEN >> 1); i++) {
+				ret = asix_read_cmd(dev, AX_CMD_READ_EEPROM,
+						    0x04 + i, 0, 2, buf + i * 2,
+						    0);
+				if (ret < 0)
+					break;
+			}
+		} else {
+			ret = asix_read_cmd(dev, AX_CMD_READ_NODE_ID,
+					    0, 0, ETH_ALEN, buf, 0);
+		}
 
-	if (ret < 0) {
-		netdev_dbg(dev->net, "Failed to read MAC address: %d\n", ret);
-		return ret;
+		if (ret < 0) {
+			netdev_dbg(dev->net, "Failed to read MAC address: %d\n",
+				   ret);
+			return ret;
+		}
 	}
 
 	asix_set_netdev_dev_addr(dev, buf);
-- 
cgit v1.2.3


From 2241ea75b82c43e060d3da26fa2c286f6c872348 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:25 -0400
Subject: media: rcar-vin: Create a group notifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As CSI-2 subdevices are shared between several VIN instances, a shared
notifier to collect the CSI-2 async subdevices is required. So far, the
rcar-vin driver used the notifier of the last VIN instance to probe but
with the forth-coming introduction of parallel input subdevices support
in mc-compliant code path, each VIN may register its own notifier if any
parallel subdevice is connected there.

To avoid registering a notifier twice (once for parallel subdev and one
for the CSI-2 subdevs) create a group notifier, shared by all the VIN
instances.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 46 +++++++++++++----------------
 drivers/media/platform/rcar-vin/rcar-vin.h  |  5 ++--
 2 files changed, 23 insertions(+), 28 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 1548b409806d..735e6ac66e48 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -46,6 +46,8 @@
  */
 #define rvin_group_id_to_master(vin) ((vin) < 4 ? 0 : 4)
 
+#define v4l2_dev_to_vin(d)	container_of(d, struct rvin_dev, v4l2_dev)
+
 /* -----------------------------------------------------------------------------
  * Media Controller link notification
  */
@@ -359,8 +361,6 @@ out:
  * Async notifier
  */
 
-#define notifier_to_vin(n) container_of(n, struct rvin_dev, notifier)
-
 static int rvin_find_pad(struct v4l2_subdev *sd, int direction)
 {
 	unsigned int pad;
@@ -466,7 +466,7 @@ static void rvin_parallel_subdevice_detach(struct rvin_dev *vin)
 
 static int rvin_parallel_notify_complete(struct v4l2_async_notifier *notifier)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	int ret;
 
 	ret = v4l2_device_register_subdev_nodes(&vin->v4l2_dev);
@@ -482,7 +482,7 @@ static void rvin_parallel_notify_unbind(struct v4l2_async_notifier *notifier,
 					struct v4l2_subdev *subdev,
 					struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 
 	vin_dbg(vin, "unbind parallel subdev %s\n", subdev->name);
 
@@ -495,7 +495,7 @@ static int rvin_parallel_notify_bound(struct v4l2_async_notifier *notifier,
 				      struct v4l2_subdev *subdev,
 				      struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	int ret;
 
 	mutex_lock(&vin->lock);
@@ -583,7 +583,7 @@ static int rvin_parallel_graph_init(struct rvin_dev *vin)
 
 static int rvin_group_notify_complete(struct v4l2_async_notifier *notifier)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	const struct rvin_group_route *route;
 	unsigned int i;
 	int ret;
@@ -649,7 +649,7 @@ static void rvin_group_notify_unbind(struct v4l2_async_notifier *notifier,
 				     struct v4l2_subdev *subdev,
 				     struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	unsigned int i;
 
 	for (i = 0; i < RCAR_VIN_NUM; i++)
@@ -673,7 +673,7 @@ static int rvin_group_notify_bound(struct v4l2_async_notifier *notifier,
 				   struct v4l2_subdev *subdev,
 				   struct v4l2_async_subdev *asd)
 {
-	struct rvin_dev *vin = notifier_to_vin(notifier);
+	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
 	unsigned int i;
 
 	mutex_lock(&vin->group->lock);
@@ -734,12 +734,6 @@ static int rvin_mc_parse_of_graph(struct rvin_dev *vin)
 
 	mutex_lock(&vin->group->lock);
 
-	/* If there already is a notifier something has gone wrong, bail out. */
-	if (WARN_ON(vin->group->notifier)) {
-		mutex_unlock(&vin->group->lock);
-		return -EINVAL;
-	}
-
 	/* If not all VIN's are registered don't register the notifier. */
 	for (i = 0; i < RCAR_VIN_NUM; i++)
 		if (vin->group->vin[i])
@@ -751,19 +745,16 @@ static int rvin_mc_parse_of_graph(struct rvin_dev *vin)
 	}
 
 	/*
-	 * Have all VIN's look for subdevices. Some subdevices will overlap
-	 * but the parser function can handle it, so each subdevice will
-	 * only be registered once with the notifier.
+	 * Have all VIN's look for CSI-2 subdevices. Some subdevices will
+	 * overlap but the parser function can handle it, so each subdevice
+	 * will only be registered once with the group notifier.
 	 */
-
-	vin->group->notifier = &vin->notifier;
-
 	for (i = 0; i < RCAR_VIN_NUM; i++) {
 		if (!vin->group->vin[i])
 			continue;
 
 		ret = v4l2_async_notifier_parse_fwnode_endpoints_by_port(
-				vin->group->vin[i]->dev, vin->group->notifier,
+				vin->group->vin[i]->dev, &vin->group->notifier,
 				sizeof(struct v4l2_async_subdev), 1,
 				rvin_mc_parse_of_endpoint);
 		if (ret) {
@@ -774,9 +765,12 @@ static int rvin_mc_parse_of_graph(struct rvin_dev *vin)
 
 	mutex_unlock(&vin->group->lock);
 
-	vin->group->notifier->ops = &rvin_group_notify_ops;
+	if (!vin->group->notifier.num_subdevs)
+		return 0;
 
-	ret = v4l2_async_notifier_register(&vin->v4l2_dev, &vin->notifier);
+	vin->group->notifier.ops = &rvin_group_notify_ops;
+	ret = v4l2_async_notifier_register(&vin->v4l2_dev,
+					   &vin->group->notifier);
 	if (ret < 0) {
 		vin_err(vin, "Notifier registration failed\n");
 		return ret;
@@ -1162,8 +1156,10 @@ static int rcar_vin_remove(struct platform_device *pdev)
 
 	if (vin->info->use_mc) {
 		mutex_lock(&vin->group->lock);
-		if (vin->group->notifier == &vin->notifier)
-			vin->group->notifier = NULL;
+		if (&vin->v4l2_dev == vin->group->notifier.v4l2_dev) {
+			v4l2_async_notifier_unregister(&vin->group->notifier);
+			v4l2_async_notifier_cleanup(&vin->group->notifier);
+		}
 		mutex_unlock(&vin->group->lock);
 		rvin_group_put(vin);
 	} else {
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
index b89f63b8ecdc..17b4de4d2734 100644
--- a/drivers/media/platform/rcar-vin/rcar-vin.h
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -227,8 +227,7 @@ struct rvin_dev {
  *
  * @lock:		protects the count, notifier, vin and csi members
  * @count:		number of enabled VIN instances found in DT
- * @notifier:		pointer to the notifier of a VIN which handles the
- *			groups async sub-devices.
+ * @notifier:		group notifier for CSI-2 async subdevices
  * @vin:		VIN instances which are part of the group
  * @csi:		array of pairs of fwnode and subdev pointers
  *			to all CSI-2 subdevices.
@@ -240,7 +239,7 @@ struct rvin_group {
 
 	struct mutex lock;
 	unsigned int count;
-	struct v4l2_async_notifier *notifier;
+	struct v4l2_async_notifier notifier;
 	struct rvin_dev *vin[RCAR_VIN_NUM];
 
 	struct {
-- 
cgit v1.2.3


From d287c5024361554d746e918b20d69a37f1b6bd79 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 3 Jul 2018 16:17:31 -0500
Subject: isdn: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Warning level 2 was used: -Wimplicit-fallthrough=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/gigaset/bas-gigaset.c          | 3 +++
 drivers/isdn/hardware/mISDN/avmfritz.c      | 1 +
 drivers/isdn/hardware/mISDN/hfcpci.c        | 1 +
 drivers/isdn/hardware/mISDN/mISDNinfineon.c | 1 +
 drivers/isdn/hardware/mISDN/mISDNisar.c     | 4 ++++
 drivers/isdn/hisax/avm_pci.c                | 1 +
 drivers/isdn/hisax/callc.c                  | 1 +
 drivers/isdn/hisax/config.c                 | 1 +
 drivers/isdn/hisax/gazel.c                  | 4 ++++
 drivers/isdn/hisax/isar.c                   | 2 ++
 drivers/isdn/hisax/l3_1tr6.c                | 1 +
 drivers/isdn/hisax/l3dss1.c                 | 1 +
 drivers/isdn/hysdn/hysdn_boot.c             | 2 ++
 drivers/isdn/i4l/isdn_v110.c                | 9 +++++++++
 drivers/isdn/mISDN/stack.c                  | 1 +
 15 files changed, 33 insertions(+)

diff --git a/drivers/isdn/gigaset/bas-gigaset.c b/drivers/isdn/gigaset/bas-gigaset.c
index 40c141163f0f..ecdeb89645d0 100644
--- a/drivers/isdn/gigaset/bas-gigaset.c
+++ b/drivers/isdn/gigaset/bas-gigaset.c
@@ -739,6 +739,7 @@ static void read_int_callback(struct urb *urb)
 
 	case HD_OPEN_B2CHANNEL_ACK:
 		++channel;
+		/* fall through */
 	case HD_OPEN_B1CHANNEL_ACK:
 		bcs = cs->bcs + channel;
 		update_basstate(ucs, BS_B1OPEN << channel, 0);
@@ -752,6 +753,7 @@ static void read_int_callback(struct urb *urb)
 
 	case HD_CLOSE_B2CHANNEL_ACK:
 		++channel;
+		/* fall through */
 	case HD_CLOSE_B1CHANNEL_ACK:
 		bcs = cs->bcs + channel;
 		update_basstate(ucs, 0, BS_B1OPEN << channel);
@@ -765,6 +767,7 @@ static void read_int_callback(struct urb *urb)
 
 	case HD_B2_FLOW_CONTROL:
 		++channel;
+		/* fall through */
 	case HD_B1_FLOW_CONTROL:
 		bcs = cs->bcs + channel;
 		atomic_add((l - BAS_NORMFRAME) * BAS_CORRFRAMES,
diff --git a/drivers/isdn/hardware/mISDN/avmfritz.c b/drivers/isdn/hardware/mISDN/avmfritz.c
index ae2b2669af1b..8eb28a83832e 100644
--- a/drivers/isdn/hardware/mISDN/avmfritz.c
+++ b/drivers/isdn/hardware/mISDN/avmfritz.c
@@ -361,6 +361,7 @@ modehdlc(struct bchannel *bch, int protocol)
 	switch (protocol) {
 	case -1: /* used for init */
 		bch->state = -1;
+		/* fall through */
 	case ISDN_P_NONE:
 		if (bch->state == ISDN_P_NONE)
 			break;
diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 34c93874af23..72a271b98873 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -1296,6 +1296,7 @@ mode_hfcpci(struct bchannel *bch, int bc, int protocol)
 	case (-1): /* used for init */
 		bch->state = -1;
 		bch->nr = bc;
+		/* fall through */
 	case (ISDN_P_NONE):
 		if (bch->state == ISDN_P_NONE)
 			return 0;
diff --git a/drivers/isdn/hardware/mISDN/mISDNinfineon.c b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
index 1fc290659e94..3e01012be4ab 100644
--- a/drivers/isdn/hardware/mISDN/mISDNinfineon.c
+++ b/drivers/isdn/hardware/mISDN/mISDNinfineon.c
@@ -887,6 +887,7 @@ release_card(struct inf_hw *card) {
 				release_card(card->sc[i]);
 			card->sc[i] = NULL;
 		}
+		/* fall through */
 	default:
 		pci_disable_device(card->pdev);
 		pci_set_drvdata(card->pdev, NULL);
diff --git a/drivers/isdn/hardware/mISDN/mISDNisar.c b/drivers/isdn/hardware/mISDN/mISDNisar.c
index b791688d0228..386731ec2489 100644
--- a/drivers/isdn/hardware/mISDN/mISDNisar.c
+++ b/drivers/isdn/hardware/mISDN/mISDNisar.c
@@ -972,6 +972,7 @@ isar_pump_statev_fax(struct isar_ch *ch, u8 devt) {
 				break;
 			case PCTRL_CMD_FTM:
 				p1 = 2;
+				/* fall through */
 			case PCTRL_CMD_FTH:
 				send_mbox(ch->is, dps | ISAR_HIS_PUMPCTRL,
 					  PCTRL_CMD_SILON, 1, &p1);
@@ -1177,6 +1178,7 @@ setup_pump(struct isar_ch *ch) {
 			send_mbox(ch->is, dps | ISAR_HIS_PUMPCFG,
 				  PMOD_DTMF, 1, param);
 		}
+		/* fall through */
 	case ISDN_P_B_MODEM_ASYNC:
 		ctrl = PMOD_DATAMODEM;
 		if (test_bit(FLG_ORIGIN, &ch->bch.Flags)) {
@@ -1268,6 +1270,7 @@ setup_iom2(struct isar_ch *ch) {
 	case ISDN_P_B_MODEM_ASYNC:
 	case ISDN_P_B_T30_FAX:
 		cmsb |= IOM_CTRL_RCV;
+		/* fall through */
 	case ISDN_P_B_L2DTMF:
 		if (test_bit(FLG_DTMFSEND, &ch->bch.Flags))
 			cmsb |= IOM_CTRL_RCV;
@@ -1560,6 +1563,7 @@ isar_l2l1(struct mISDNchannel *ch, struct sk_buff *skb)
 				ich->is->name, hh->id);
 			ret = -EINVAL;
 		}
+		/* fall through */
 	default:
 		pr_info("%s: %s unknown prim(%x,%x)\n",
 			ich->is->name, __func__, hh->prim, hh->id);
diff --git a/drivers/isdn/hisax/avm_pci.c b/drivers/isdn/hisax/avm_pci.c
index a18b605fb4f2..b161456c942e 100644
--- a/drivers/isdn/hisax/avm_pci.c
+++ b/drivers/isdn/hisax/avm_pci.c
@@ -207,6 +207,7 @@ modehdlc(struct BCState *bcs, int mode, int bc)
 		bcs->mode = 1;
 		bcs->channel = bc;
 		bc = 0;
+		/* fall through */
 	case (L1_MODE_NULL):
 		if (bcs->mode == L1_MODE_NULL)
 			return;
diff --git a/drivers/isdn/hisax/callc.c b/drivers/isdn/hisax/callc.c
index ddec47a911a0..5f43783039d4 100644
--- a/drivers/isdn/hisax/callc.c
+++ b/drivers/isdn/hisax/callc.c
@@ -1369,6 +1369,7 @@ leased_l1l2(struct PStack *st, int pr, void *arg)
 	case (PH_ACTIVATE | INDICATION):
 	case (PH_ACTIVATE | CONFIRM):
 		event = EV_LEASED;
+		/* fall through */
 	case (PH_DEACTIVATE | INDICATION):
 	case (PH_DEACTIVATE | CONFIRM):
 		if (test_bit(FLG_TWO_DCHAN, &chanp->cs->HW_Flags))
diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index 7108bdb8742e..fcc9c46127b4 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -1843,6 +1843,7 @@ static void hisax_b_l2l1(struct PStack *st, int pr, void *arg)
 	case PH_DEACTIVATE | REQUEST:
 		test_and_clear_bit(BC_FLG_BUSY, &bcs->Flag);
 		skb_queue_purge(&bcs->squeue);
+		/* fall through */
 	default:
 		B_L2L1(b_if, pr, arg);
 		break;
diff --git a/drivers/isdn/hisax/gazel.c b/drivers/isdn/hisax/gazel.c
index 35c6df6534ec..a6d8af02354a 100644
--- a/drivers/isdn/hisax/gazel.c
+++ b/drivers/isdn/hisax/gazel.c
@@ -108,6 +108,7 @@ ReadISAC(struct IsdnCardState *cs, u_char offset)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		return (readreg(cs->hw.gazel.isac, off2));
 	case R753:
@@ -125,6 +126,7 @@ WriteISAC(struct IsdnCardState *cs, u_char offset, u_char value)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		writereg(cs->hw.gazel.isac, off2, value);
 		break;
@@ -203,6 +205,7 @@ ReadHSCX(struct IsdnCardState *cs, int hscx, u_char offset)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		return (readreg(cs->hw.gazel.hscx[hscx], off2));
 	case R753:
@@ -220,6 +223,7 @@ WriteHSCX(struct IsdnCardState *cs, int hscx, u_char offset, u_char value)
 	switch (cs->subtyp) {
 	case R647:
 		off2 = ((off2 << 8 & 0xf000) | (off2 & 0xf));
+		/* fall through */
 	case R685:
 		writereg(cs->hw.gazel.hscx[hscx], off2, value);
 		break;
diff --git a/drivers/isdn/hisax/isar.c b/drivers/isdn/hisax/isar.c
index d01ff116797b..82c1879f5664 100644
--- a/drivers/isdn/hisax/isar.c
+++ b/drivers/isdn/hisax/isar.c
@@ -1089,6 +1089,7 @@ isar_pump_statev_fax(struct BCState *bcs, u_char devt) {
 				break;
 			case PCTRL_CMD_FTM:
 				p1 = 2;
+				/* fall through */
 			case PCTRL_CMD_FTH:
 				sendmsg(cs, dps | ISAR_HIS_PUMPCTRL,
 					PCTRL_CMD_SILON, 1, &p1);
@@ -1097,6 +1098,7 @@ isar_pump_statev_fax(struct BCState *bcs, u_char devt) {
 			case PCTRL_CMD_FRM:
 				if (frm_extra_delay)
 					mdelay(frm_extra_delay);
+				/* fall through */
 			case PCTRL_CMD_FRH:
 				p1 = bcs->hw.isar.mod = bcs->hw.isar.newmod;
 				bcs->hw.isar.newmod = 0;
diff --git a/drivers/isdn/hisax/l3_1tr6.c b/drivers/isdn/hisax/l3_1tr6.c
index da0a1c6aa329..98f60d1523f4 100644
--- a/drivers/isdn/hisax/l3_1tr6.c
+++ b/drivers/isdn/hisax/l3_1tr6.c
@@ -88,6 +88,7 @@ l3_1tr6_setup_req(struct l3_process *pc, u_char pr, void *arg)
 			break;
 		case 'C':
 			channel = 0x08;
+			/* fall through */
 		case 'P':
 			channel |= 0x80;
 			teln++;
diff --git a/drivers/isdn/hisax/l3dss1.c b/drivers/isdn/hisax/l3dss1.c
index 18a3484b1f7e..368d152a8f1d 100644
--- a/drivers/isdn/hisax/l3dss1.c
+++ b/drivers/isdn/hisax/l3dss1.c
@@ -1282,6 +1282,7 @@ l3dss1_setup_req(struct l3_process *pc, u_char pr,
 			switch (0x5f & *teln) {
 			case 'C':
 				channel = 0x08;
+				/* fall through */
 			case 'P':
 				channel |= 0x80;
 				teln++;
diff --git a/drivers/isdn/hysdn/hysdn_boot.c b/drivers/isdn/hysdn/hysdn_boot.c
index 4a0425378f37..ba177c3a621b 100644
--- a/drivers/isdn/hysdn/hysdn_boot.c
+++ b/drivers/isdn/hysdn/hysdn_boot.c
@@ -99,6 +99,7 @@ pof_handle_data(hysdn_card *card, int datlen)
 
 	case TAG_CBOOTDTA:
 		DecryptBuf(boot, datlen);	/* we need to encrypt the buffer */
+		/* fall through */
 	case TAG_BOOTDTA:
 		if (card->debug_flags & LOG_POF_RECORD)
 			hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
@@ -137,6 +138,7 @@ pof_handle_data(hysdn_card *card, int datlen)
 
 	case TAG_CABSDATA:
 		DecryptBuf(boot, datlen);	/* we need to encrypt the buffer */
+		/* fall through */
 	case TAG_ABSDATA:
 		if (card->debug_flags & LOG_POF_RECORD)
 			hysdn_addlog(card, "POF got %s len=%d offs=0x%lx",
diff --git a/drivers/isdn/i4l/isdn_v110.c b/drivers/isdn/i4l/isdn_v110.c
index 8b74ce412524..2a5f6668756c 100644
--- a/drivers/isdn/i4l/isdn_v110.c
+++ b/drivers/isdn/i4l/isdn_v110.c
@@ -354,6 +354,7 @@ EncodeMatrix(unsigned char *buf, int len, unsigned char *m, int mlen)
 				printk(KERN_WARNING "isdn_v110 (EncodeMatrix): buffer full!\n");
 				return line;
 			}
+			/* else: fall through */
 		case 128:
 			m[line] = 128;	/* leftmost -> set byte to 1000000 */
 			mbit = 64;	/* current bit in the matrix line */
@@ -386,20 +387,28 @@ EncodeMatrix(unsigned char *buf, int len, unsigned char *m, int mlen)
 		switch (++line % 10) {
 		case 1:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 2:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 3:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 4:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 5:
 			m[line++] = 0xbf;
+			/* fall through */
 		case 6:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 7:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 8:
 			m[line++] = 0xfe;
+			/* fall through */
 		case 9:
 			m[line++] = 0xfe;
 		}
diff --git a/drivers/isdn/mISDN/stack.c b/drivers/isdn/mISDN/stack.c
index 422dced7c90a..d97c6dd52223 100644
--- a/drivers/isdn/mISDN/stack.c
+++ b/drivers/isdn/mISDN/stack.c
@@ -539,6 +539,7 @@ create_l2entity(struct mISDNdevice *dev, struct mISDNchannel *ch,
 		rq.protocol = ISDN_P_NT_S0;
 		if (dev->Dprotocols & (1 << ISDN_P_NT_E1))
 			rq.protocol = ISDN_P_NT_E1;
+		/* fall through */
 	case ISDN_P_LAPD_TE:
 		ch->recv = mISDN_queue_message;
 		ch->peer = &dev->D.st->own;
-- 
cgit v1.2.3


From 9863bc8695bc36e39aca289650e5a4f17c1bf628 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:26 -0400
Subject: media: rcar-vin: Cleanup notifier in error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During the notifier initialization, memory for the list of associated async
subdevices is reserved during the fwnode endpoint parsing from the v4l2-async
framework. If the notifier registration fails, that memory should be released
and the notifier 'cleaned up'.

Catch the notifier registration error and perform the cleanup both for the
group and the parallel notifiers.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 735e6ac66e48..87b29be2ea9e 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -571,6 +571,7 @@ static int rvin_parallel_graph_init(struct rvin_dev *vin)
 	ret = v4l2_async_notifier_register(&vin->v4l2_dev, &vin->notifier);
 	if (ret < 0) {
 		vin_err(vin, "Notifier registration failed\n");
+		v4l2_async_notifier_cleanup(&vin->group->notifier);
 		return ret;
 	}
 
@@ -773,6 +774,7 @@ static int rvin_mc_parse_of_graph(struct rvin_dev *vin)
 					   &vin->group->notifier);
 	if (ret < 0) {
 		vin_err(vin, "Notifier registration failed\n");
+		v4l2_async_notifier_cleanup(&vin->group->notifier);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From 158e2a53fc9620fac7ebbb83223ec18280bd34f0 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:27 -0400
Subject: media: rcar-vin: Cache the mbus configuration flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Media bus configuration flags and media bus type were so far a property
of each VIN instance, as the subdevice they were connected to was
immutable during the whole system life time.

With the forth-coming introduction of parallel input devices support,
a VIN instance can have the subdevice it is connected to switched at
runtime, from a CSI-2 subdevice to a parallel one and viceversa, through
the modification of links between media entities in the media controller
graph. To avoid discarding the per-subdevice configuration flags retrieved by
v4l2_fwnode parsing facilities, cache them in the 'rvin_graph_entity'
member of each VIN instance, opportunely renamed to 'rvin_parallel_entity'.

Also modify the register configuration function to take mbus flags into
account when running on a bus type that supports them.

The media bus type currently in use will be updated in a follow-up patch
to the link state change notification function.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 21 ++++++++-----------
 drivers/media/platform/rcar-vin/rcar-dma.c  | 32 +++++++++++++++++++----------
 drivers/media/platform/rcar-vin/rcar-vin.h  | 22 ++++++++++++++------
 3 files changed, 45 insertions(+), 30 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 87b29be2ea9e..7f84c7b9518a 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -524,30 +524,29 @@ static int rvin_parallel_parse_v4l2(struct device *dev,
 				    struct v4l2_async_subdev *asd)
 {
 	struct rvin_dev *vin = dev_get_drvdata(dev);
-	struct rvin_graph_entity *rvge =
-		container_of(asd, struct rvin_graph_entity, asd);
+	struct rvin_parallel_entity *rvpe =
+		container_of(asd, struct rvin_parallel_entity, asd);
 
 	if (vep->base.port || vep->base.id)
 		return -ENOTCONN;
 
-	vin->mbus_cfg.type = vep->bus_type;
+	vin->parallel = rvpe;
+	vin->parallel->mbus_type = vep->bus_type;
 
-	switch (vin->mbus_cfg.type) {
+	switch (vin->parallel->mbus_type) {
 	case V4L2_MBUS_PARALLEL:
 		vin_dbg(vin, "Found PARALLEL media bus\n");
-		vin->mbus_cfg.flags = vep->bus.parallel.flags;
+		vin->parallel->mbus_flags = vep->bus.parallel.flags;
 		break;
 	case V4L2_MBUS_BT656:
 		vin_dbg(vin, "Found BT656 media bus\n");
-		vin->mbus_cfg.flags = 0;
+		vin->parallel->mbus_flags = 0;
 		break;
 	default:
 		vin_err(vin, "Unknown media bus type\n");
 		return -EINVAL;
 	}
 
-	vin->parallel = rvge;
-
 	return 0;
 }
 
@@ -557,7 +556,7 @@ static int rvin_parallel_graph_init(struct rvin_dev *vin)
 
 	ret = v4l2_async_notifier_parse_fwnode_endpoints(
 		vin->dev, &vin->notifier,
-		sizeof(struct rvin_graph_entity), rvin_parallel_parse_v4l2);
+		sizeof(struct rvin_parallel_entity), rvin_parallel_parse_v4l2);
 	if (ret)
 		return ret;
 
@@ -785,10 +784,6 @@ static int rvin_mc_init(struct rvin_dev *vin)
 {
 	int ret;
 
-	/* All our sources are CSI-2 */
-	vin->mbus_cfg.type = V4L2_MBUS_CSI2;
-	vin->mbus_cfg.flags = 0;
-
 	vin->pad.flags = MEDIA_PAD_FL_SINK;
 	ret = media_entity_pads_init(&vin->vdev.entity, 1, &vin->pad);
 	if (ret)
diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
index ce9502f15f5b..1de598120286 100644
--- a/drivers/media/platform/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -659,8 +659,12 @@ static int rvin_setup(struct rvin_dev *vin)
 		break;
 	case MEDIA_BUS_FMT_UYVY8_2X8:
 		/* BT.656 8bit YCbCr422 or BT.601 8bit YCbCr422 */
-		vnmc |= vin->mbus_cfg.type == V4L2_MBUS_BT656 ?
-			VNMC_INF_YUV8_BT656 : VNMC_INF_YUV8_BT601;
+		if (!vin->is_csi &&
+		    vin->parallel->mbus_type == V4L2_MBUS_BT656)
+			vnmc |= VNMC_INF_YUV8_BT656;
+		else
+			vnmc |= VNMC_INF_YUV8_BT601;
+
 		input_is_yuv = true;
 		break;
 	case MEDIA_BUS_FMT_RGB888_1X24:
@@ -668,8 +672,12 @@ static int rvin_setup(struct rvin_dev *vin)
 		break;
 	case MEDIA_BUS_FMT_UYVY10_2X10:
 		/* BT.656 10bit YCbCr422 or BT.601 10bit YCbCr422 */
-		vnmc |= vin->mbus_cfg.type == V4L2_MBUS_BT656 ?
-			VNMC_INF_YUV10_BT656 : VNMC_INF_YUV10_BT601;
+		if (!vin->is_csi &&
+		    vin->parallel->mbus_type == V4L2_MBUS_BT656)
+			vnmc |= VNMC_INF_YUV10_BT656;
+		else
+			vnmc |= VNMC_INF_YUV10_BT601;
+
 		input_is_yuv = true;
 		break;
 	default:
@@ -682,13 +690,15 @@ static int rvin_setup(struct rvin_dev *vin)
 	else
 		dmr2 = VNDMR2_FTEV | VNDMR2_VLV(1);
 
-	/* Hsync Signal Polarity Select */
-	if (!(vin->mbus_cfg.flags & V4L2_MBUS_HSYNC_ACTIVE_LOW))
-		dmr2 |= VNDMR2_HPS;
+	if (!vin->is_csi) {
+		/* Hsync Signal Polarity Select */
+		if (!(vin->parallel->mbus_flags & V4L2_MBUS_HSYNC_ACTIVE_LOW))
+			dmr2 |= VNDMR2_HPS;
 
-	/* Vsync Signal Polarity Select */
-	if (!(vin->mbus_cfg.flags & V4L2_MBUS_VSYNC_ACTIVE_LOW))
-		dmr2 |= VNDMR2_VPS;
+		/* Vsync Signal Polarity Select */
+		if (!(vin->parallel->mbus_flags & V4L2_MBUS_VSYNC_ACTIVE_LOW))
+			dmr2 |= VNDMR2_VPS;
+	}
 
 	/*
 	 * Output format
@@ -734,7 +744,7 @@ static int rvin_setup(struct rvin_dev *vin)
 
 	if (vin->info->model == RCAR_GEN3) {
 		/* Select between CSI-2 and parallel input */
-		if (vin->mbus_cfg.type == V4L2_MBUS_CSI2)
+		if (vin->is_csi)
 			vnmc &= ~VNMC_DPINE;
 		else
 			vnmc |= VNMC_DPINE;
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
index 17b4de4d2734..df2a47e4be31 100644
--- a/drivers/media/platform/rcar-vin/rcar-vin.h
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -75,16 +75,22 @@ struct rvin_video_format {
 };
 
 /**
- * struct rvin_graph_entity - Video endpoint from async framework
+ * struct rvin_parallel_entity - Parallel video input endpoint descriptor
  * @asd:	sub-device descriptor for async framework
  * @subdev:	subdevice matched using async framework
+ * @mbus_type:	media bus type
+ * @mbus_flags:	media bus configuration flags
  * @source_pad:	source pad of remote subdevice
  * @sink_pad:	sink pad of remote subdevice
+ *
  */
-struct rvin_graph_entity {
+struct rvin_parallel_entity {
 	struct v4l2_async_subdev asd;
 	struct v4l2_subdev *subdev;
 
+	enum v4l2_mbus_type mbus_type;
+	unsigned int mbus_flags;
+
 	unsigned int source_pad;
 	unsigned int sink_pad;
 };
@@ -148,7 +154,8 @@ struct rvin_info {
  * @v4l2_dev:		V4L2 device
  * @ctrl_handler:	V4L2 control handler
  * @notifier:		V4L2 asynchronous subdevs notifier
- * @parallel:		entity in the DT for local parallel subdevice
+ *
+ * @parallel:		parallel input subdevice descriptor
  *
  * @group:		Gen3 CSI group
  * @id:			Gen3 group id for this VIN
@@ -166,7 +173,8 @@ struct rvin_info {
  * @sequence:		V4L2 buffers sequence number
  * @state:		keeps track of operation state
  *
- * @mbus_cfg:		media bus configuration from DT
+ * @is_csi:		flag to mark the VIN as using a CSI-2 subdevice
+ *
  * @mbus_code:		media bus format code
  * @format:		active V4L2 pixel format
  *
@@ -184,7 +192,8 @@ struct rvin_dev {
 	struct v4l2_device v4l2_dev;
 	struct v4l2_ctrl_handler ctrl_handler;
 	struct v4l2_async_notifier notifier;
-	struct rvin_graph_entity *parallel;
+
+	struct rvin_parallel_entity *parallel;
 
 	struct rvin_group *group;
 	unsigned int id;
@@ -201,7 +210,8 @@ struct rvin_dev {
 	unsigned int sequence;
 	enum rvin_dma_state state;
 
-	struct v4l2_mbus_config mbus_cfg;
+	bool is_csi;
+
 	u32 mbus_code;
 	struct v4l2_pix_format format;
 
-- 
cgit v1.2.3


From a597a772cd3f51193e1917a729db8a991615341b Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:28 -0400
Subject: media: rcar-vin: Parse parallel input on Gen3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The rcar-vin driver so far had a mutually exclusive code path for
handling parallel and CSI-2 video input subdevices, with only the CSI-2
use case supporting media-controller. As we add support for parallel
inputs to Gen3 media-controller compliant code path now parse both port@0
and port@1, handling the media-controller use case in the parallel
bound/unbind notifier operations.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 53 +++++++++++++++++++++--------
 1 file changed, 38 insertions(+), 15 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 7f84c7b9518a..e9b5b83122e6 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -397,6 +397,11 @@ static int rvin_parallel_subdevice_attach(struct rvin_dev *vin,
 	ret = rvin_find_pad(subdev, MEDIA_PAD_FL_SINK);
 	vin->parallel->sink_pad = ret < 0 ? 0 : ret;
 
+	if (vin->info->use_mc) {
+		vin->parallel->subdev = subdev;
+		return 0;
+	}
+
 	/* Find compatible subdevices mbus format */
 	vin->mbus_code = 0;
 	code.index = 0;
@@ -458,10 +463,12 @@ static int rvin_parallel_subdevice_attach(struct rvin_dev *vin,
 static void rvin_parallel_subdevice_detach(struct rvin_dev *vin)
 {
 	rvin_v4l2_unregister(vin);
-	v4l2_ctrl_handler_free(&vin->ctrl_handler);
-
-	vin->vdev.ctrl_handler = NULL;
 	vin->parallel->subdev = NULL;
+
+	if (!vin->info->use_mc) {
+		v4l2_ctrl_handler_free(&vin->ctrl_handler);
+		vin->vdev.ctrl_handler = NULL;
+	}
 }
 
 static int rvin_parallel_notify_complete(struct v4l2_async_notifier *notifier)
@@ -550,18 +557,19 @@ static int rvin_parallel_parse_v4l2(struct device *dev,
 	return 0;
 }
 
-static int rvin_parallel_graph_init(struct rvin_dev *vin)
+static int rvin_parallel_init(struct rvin_dev *vin)
 {
 	int ret;
 
-	ret = v4l2_async_notifier_parse_fwnode_endpoints(
-		vin->dev, &vin->notifier,
-		sizeof(struct rvin_parallel_entity), rvin_parallel_parse_v4l2);
+	ret = v4l2_async_notifier_parse_fwnode_endpoints_by_port(
+		vin->dev, &vin->notifier, sizeof(struct rvin_parallel_entity),
+		0, rvin_parallel_parse_v4l2);
 	if (ret)
 		return ret;
 
+	/* If using mc, it's fine not to have any input registered. */
 	if (!vin->parallel)
-		return -ENODEV;
+		return vin->info->use_mc ? 0 : -ENODEV;
 
 	vin_dbg(vin, "Found parallel subdevice %pOF\n",
 		to_of_node(vin->parallel->asd.match.fwnode));
@@ -1122,20 +1130,35 @@ static int rcar_vin_probe(struct platform_device *pdev)
 		return ret;
 
 	platform_set_drvdata(pdev, vin);
-	if (vin->info->use_mc)
+
+	if (vin->info->use_mc) {
 		ret = rvin_mc_init(vin);
-	else
-		ret = rvin_parallel_graph_init(vin);
-	if (ret < 0)
-		goto error;
+		if (ret)
+			goto error_dma_unregister;
+	}
+
+	ret = rvin_parallel_init(vin);
+	if (ret)
+		goto error_group_unregister;
 
 	pm_suspend_ignore_children(&pdev->dev, true);
 	pm_runtime_enable(&pdev->dev);
 
 	return 0;
-error:
+
+error_group_unregister:
+	if (vin->info->use_mc) {
+		mutex_lock(&vin->group->lock);
+		if (&vin->v4l2_dev == vin->group->notifier.v4l2_dev) {
+			v4l2_async_notifier_unregister(&vin->group->notifier);
+			v4l2_async_notifier_cleanup(&vin->group->notifier);
+		}
+		mutex_unlock(&vin->group->lock);
+		rvin_group_put(vin);
+	}
+
+error_dma_unregister:
 	rvin_dma_unregister(vin);
-	v4l2_async_notifier_cleanup(&vin->notifier);
 
 	return ret;
 }
-- 
cgit v1.2.3


From a962a80476b06fc6c2a4b7d77bb38b77dd73edac Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:29 -0400
Subject: media: rcar-vin: Link parallel input media entities
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When running with media-controller link the parallel input
media entities with the VIN entities at 'complete' callback time.

To create media links the v4l2_device should be registered first.
Check if the device is already registered, to avoid double registrations.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index e9b5b83122e6..bf54e23b12eb 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -474,6 +474,8 @@ static void rvin_parallel_subdevice_detach(struct rvin_dev *vin)
 static int rvin_parallel_notify_complete(struct v4l2_async_notifier *notifier)
 {
 	struct rvin_dev *vin = v4l2_dev_to_vin(notifier->v4l2_dev);
+	struct media_entity *source;
+	struct media_entity *sink;
 	int ret;
 
 	ret = v4l2_device_register_subdev_nodes(&vin->v4l2_dev);
@@ -482,7 +484,26 @@ static int rvin_parallel_notify_complete(struct v4l2_async_notifier *notifier)
 		return ret;
 	}
 
-	return rvin_v4l2_register(vin);
+	if (!video_is_registered(&vin->vdev)) {
+		ret = rvin_v4l2_register(vin);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (!vin->info->use_mc)
+		return 0;
+
+	/* If we're running with media-controller, link the subdevs. */
+	source = &vin->parallel->subdev->entity;
+	sink = &vin->vdev.entity;
+
+	ret = media_create_pad_link(source, vin->parallel->source_pad,
+				    sink, vin->parallel->sink_pad, 0);
+	if (ret)
+		vin_err(vin, "Error adding link from %s to %s: %d\n",
+			source->name, sink->name, ret);
+
+	return ret;
 }
 
 static void rvin_parallel_notify_unbind(struct v4l2_async_notifier *notifier,
@@ -604,7 +625,8 @@ static int rvin_group_notify_complete(struct v4l2_async_notifier *notifier)
 
 	/* Register all video nodes for the group. */
 	for (i = 0; i < RCAR_VIN_NUM; i++) {
-		if (vin->group->vin[i]) {
+		if (vin->group->vin[i] &&
+		    !video_is_registered(&vin->group->vin[i]->vdev)) {
 			ret = rvin_v4l2_register(vin->group->vin[i]);
 			if (ret)
 				return ret;
-- 
cgit v1.2.3


From 1284605dc821cebdc4793772487f65f56c5d0c62 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:30 -0400
Subject: media: rcar-vin: Handle parallel subdev in link_notify
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Handle parallel subdevices in link_notify callback. If the notified link
involves a parallel subdevice, do not change routing of the VIN-CSI-2
devices and mark the VIN instance as using a parallel input. If the
CSI-2 link setup succeeds instead, mark the VIN instance as using CSI-2.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 35 ++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index bf54e23b12eb..cd37657530db 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -171,9 +171,37 @@ static int rvin_group_link_notify(struct media_link *link, u32 flags,
 
 	/* Add the new link to the existing mask and check if it works. */
 	csi_id = rvin_group_entity_to_csi_id(group, link->source->entity);
+
+	if (csi_id == -ENODEV) {
+		struct v4l2_subdev *sd;
+		unsigned int i;
+
+		/*
+		 * Make sure the source entity subdevice is registered as
+		 * a parallel input of one of the enabled VINs if it is not
+		 * one of the CSI-2 subdevices.
+		 *
+		 * No hardware configuration required for parallel inputs,
+		 * we can return here.
+		 */
+		sd = media_entity_to_v4l2_subdev(link->source->entity);
+		for (i = 0; i < RCAR_VIN_NUM; i++) {
+			if (group->vin[i] && group->vin[i]->parallel &&
+			    group->vin[i]->parallel->subdev == sd) {
+				group->vin[i]->is_csi = false;
+				ret = 0;
+				goto out;
+			}
+		}
+
+		vin_err(vin, "Subdevice %s not registered to any VIN\n",
+			link->source->entity->name);
+		ret = -ENODEV;
+		goto out;
+	}
+
 	channel = rvin_group_csi_pad_to_channel(link->source->index);
 	mask_new = mask & rvin_group_get_mask(vin, csi_id, channel);
-
 	vin_dbg(vin, "Try link change mask: 0x%x new: 0x%x\n", mask, mask_new);
 
 	if (!mask_new) {
@@ -183,6 +211,11 @@ static int rvin_group_link_notify(struct media_link *link, u32 flags,
 
 	/* New valid CHSEL found, set the new value. */
 	ret = rvin_set_channel_routing(group->vin[master_id], __ffs(mask_new));
+	if (ret)
+		goto out;
+
+	vin->is_csi = true;
+
 out:
 	mutex_unlock(&group->lock);
 
-- 
cgit v1.2.3


From 5cda0fca7824605d56e4c0d9a96d464d9a93dc33 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:31 -0400
Subject: media: rcar-vin: Rename _rcar_info to rcar_info
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove leading underscore to align all rcar_group_route structure
declarations.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index cd37657530db..636784079921 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -1070,7 +1070,7 @@ static const struct rvin_info rcar_info_r8a77965 = {
 	.routes = rcar_info_r8a77965_routes,
 };
 
-static const struct rvin_group_route _rcar_info_r8a77970_routes[] = {
+static const struct rvin_group_route rcar_info_r8a77970_routes[] = {
 	{ .csi = RVIN_CSI40, .channel = 0, .vin = 0, .mask = BIT(0) | BIT(3) },
 	{ .csi = RVIN_CSI40, .channel = 0, .vin = 1, .mask = BIT(2) },
 	{ .csi = RVIN_CSI40, .channel = 1, .vin = 1, .mask = BIT(3) },
@@ -1086,7 +1086,7 @@ static const struct rvin_info rcar_info_r8a77970 = {
 	.use_mc = true,
 	.max_width = 4096,
 	.max_height = 4096,
-	.routes = _rcar_info_r8a77970_routes,
+	.routes = rcar_info_r8a77970_routes,
 };
 
 static const struct of_device_id rvin_of_id_table[] = {
-- 
cgit v1.2.3


From aa2446ef9e8b33d304bde808ea3dac416af1bd0c Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 12 Jun 2018 05:43:32 -0400
Subject: media: rcar-vin: Add support for R-Car R8A77995 SoC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add R-Car R8A77995 SoC to the rcar-vin supported ones.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-core.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 636784079921..8843367cd339 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -1089,6 +1089,18 @@ static const struct rvin_info rcar_info_r8a77970 = {
 	.routes = rcar_info_r8a77970_routes,
 };
 
+static const struct rvin_group_route rcar_info_r8a77995_routes[] = {
+	{ /* Sentinel */ }
+};
+
+static const struct rvin_info rcar_info_r8a77995 = {
+	.model = RCAR_GEN3,
+	.use_mc = true,
+	.max_width = 4096,
+	.max_height = 4096,
+	.routes = rcar_info_r8a77995_routes,
+};
+
 static const struct of_device_id rvin_of_id_table[] = {
 	{
 		.compatible = "renesas,vin-r8a7778",
@@ -1134,6 +1146,10 @@ static const struct of_device_id rvin_of_id_table[] = {
 		.compatible = "renesas,vin-r8a77970",
 		.data = &rcar_info_r8a77970,
 	},
+	{
+		.compatible = "renesas,vin-r8a77995",
+		.data = &rcar_info_r8a77995,
+	},
 	{ /* Sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, rvin_of_id_table);
-- 
cgit v1.2.3


From 8736c1038cd22fe639091349767ae89b883d1a81 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Wed, 4 Jul 2018 04:51:36 -0400
Subject: media: dt-bindings: media: rcar-vin: Add R8A77995 support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add compatible string for R-Car D3 R8A7795 to list of SoCs supported by
rcar-vin driver.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/rcar_vin.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index 638cecdde474..e25ab07ded57 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -23,6 +23,7 @@ on Gen3 platforms to a CSI-2 receiver.
    - "renesas,vin-r8a7796" for the R8A7796 device
    - "renesas,vin-r8a77965" for the R8A77965 device
    - "renesas,vin-r8a77970" for the R8A77970 device
+   - "renesas,vin-r8a77995" for the R8A77995 device
    - "renesas,rcar-gen2-vin" for a generic R-Car Gen2 or RZ/G1 compatible
      device.
 
-- 
cgit v1.2.3


From a38d4b71cb7a12b65317f4e3d59883a918957719 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 15 Mar 2018 15:13:22 -0400
Subject: media: staging/imx: fill vb2_v4l2_buffer field entry

- fixes gstreamer v4l2src warning:

  0:00:00.716640334  349  0x164f720 WARN  v4l2bufferpool gstv4l2bufferpool.c:1195:gst_v4l2_buffer_pool_dqbuf:<v4l2src0:pool:src> Driver should never set v4l2_buffer.field to ANY

- fixes v4l2-compliance test failure:

  Streaming ioctls:
          test read/write: OK (Not Supported)
              Video Capture:
                  Buffer: 0 Sequence: 0 Field: Any Timestamp: 58.383658s
                  fail: v4l2-test-buffers.cpp(297): g_field() == V4L2_FIELD_ANY

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/imx/imx-ic-prpencvf.c | 1 +
 drivers/staging/media/imx/imx-media-csi.c   | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c
index ae453fd422f0..ffeb017c73b2 100644
--- a/drivers/staging/media/imx/imx-ic-prpencvf.c
+++ b/drivers/staging/media/imx/imx-ic-prpencvf.c
@@ -210,6 +210,7 @@ static void prp_vb2_buf_done(struct prp_priv *priv, struct ipuv3_channel *ch)
 
 	done = priv->active_vb2_buf[priv->ipu_buf_num];
 	if (done) {
+		done->vbuf.field = vdev->fmt.fmt.pix.field;
 		vb = &done->vbuf.vb2_buf;
 		vb->timestamp = ktime_get_ns();
 		vb2_buffer_done(vb, priv->nfb4eof ?
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 06af76d31c0b..caf9029bd7c3 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -236,6 +236,7 @@ static void csi_vb2_buf_done(struct csi_priv *priv)
 
 	done = priv->active_vb2_buf[priv->ipu_buf_num];
 	if (done) {
+		done->vbuf.field = vdev->fmt.fmt.pix.field;
 		vb = &done->vbuf.vb2_buf;
 		vb->timestamp = ktime_get_ns();
 		vb2_buffer_done(vb, priv->nfb4eof ?
-- 
cgit v1.2.3


From 56e5faf299502d902b94cd88d6ff1c48c3865c69 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 15 Mar 2018 15:13:23 -0400
Subject: media: staging/imx: fill vb2_v4l2_buffer sequence entry

- enables gstreamer v4l2src lost frame detection, e.g:

  0:00:08.685185668  348  0x54f520 WARN  v4l2src gstv4l2src.c:970:gst_v4l2src_create:<v4l2src0> lost frames detected: count = 141 - ts: 0:00:08.330177332

- fixes v4l2-compliance test failure:

  Streaming ioctls:
          test read/write: OK (Not Supported)
              Video Capture:
                  Buffer: 0 Sequence: 0 Field: None Timestamp: 92.991450s
                  Buffer: 1 Sequence: 0 Field: None Timestamp: 93.008135s
                  fail: v4l2-test-buffers.cpp(294): (int)g_sequence() < seq.last_seq + 1
                  fail: v4l2-test-buffers.cpp(707): buf.check(q, last_seq)

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/imx/imx-ic-prpencvf.c | 4 ++++
 drivers/staging/media/imx/imx-media-csi.c   | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/staging/media/imx/imx-ic-prpencvf.c b/drivers/staging/media/imx/imx-ic-prpencvf.c
index ffeb017c73b2..28f41caba05d 100644
--- a/drivers/staging/media/imx/imx-ic-prpencvf.c
+++ b/drivers/staging/media/imx/imx-ic-prpencvf.c
@@ -103,6 +103,7 @@ struct prp_priv {
 	int nfb4eof_irq;
 
 	int stream_count;
+	u32 frame_sequence; /* frame sequence counter */
 	bool last_eof;  /* waiting for last EOF at stream off */
 	bool nfb4eof;    /* NFB4EOF encountered during streaming */
 	struct completion last_eof_comp;
@@ -211,12 +212,14 @@ static void prp_vb2_buf_done(struct prp_priv *priv, struct ipuv3_channel *ch)
 	done = priv->active_vb2_buf[priv->ipu_buf_num];
 	if (done) {
 		done->vbuf.field = vdev->fmt.fmt.pix.field;
+		done->vbuf.sequence = priv->frame_sequence;
 		vb = &done->vbuf.vb2_buf;
 		vb->timestamp = ktime_get_ns();
 		vb2_buffer_done(vb, priv->nfb4eof ?
 				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
 	}
 
+	priv->frame_sequence++;
 	priv->nfb4eof = false;
 
 	/* get next queued buffer */
@@ -638,6 +641,7 @@ static int prp_start(struct prp_priv *priv)
 
 	/* init EOF completion waitq */
 	init_completion(&priv->last_eof_comp);
+	priv->frame_sequence = 0;
 	priv->last_eof = false;
 	priv->nfb4eof = false;
 
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index caf9029bd7c3..6a892839ffbf 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -111,6 +111,7 @@ struct csi_priv {
 	struct v4l2_ctrl_handler ctrl_hdlr;
 
 	int stream_count; /* streaming counter */
+	u32 frame_sequence; /* frame sequence counter */
 	bool last_eof;   /* waiting for last EOF at stream off */
 	bool nfb4eof;    /* NFB4EOF encountered during streaming */
 	struct completion last_eof_comp;
@@ -237,12 +238,14 @@ static void csi_vb2_buf_done(struct csi_priv *priv)
 	done = priv->active_vb2_buf[priv->ipu_buf_num];
 	if (done) {
 		done->vbuf.field = vdev->fmt.fmt.pix.field;
+		done->vbuf.sequence = priv->frame_sequence;
 		vb = &done->vbuf.vb2_buf;
 		vb->timestamp = ktime_get_ns();
 		vb2_buffer_done(vb, priv->nfb4eof ?
 				VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
 	}
 
+	priv->frame_sequence++;
 	priv->nfb4eof = false;
 
 	/* get next queued buffer */
@@ -546,6 +549,7 @@ static int csi_idmac_start(struct csi_priv *priv)
 
 	/* init EOF completion waitq */
 	init_completion(&priv->last_eof_comp);
+	priv->frame_sequence = 0;
 	priv->last_eof = false;
 	priv->nfb4eof = false;
 
-- 
cgit v1.2.3


From f6aaac7fa03e36bb43401182864a74f65a211e86 Mon Sep 17 00:00:00 2001
From: Jan Luebbe <jlu@pengutronix.de>
Date: Fri, 18 May 2018 09:56:38 -0400
Subject: media: imx: capture: refactor enum_/try_fmt

By checking and handling the internal IPU formats (ARGB or AYUV) first,
we don't need to check whether it's a bayer format, as we can default to
passing the input format on in all other cases.

This simplifies handling the different configurations for RGB565 between
parallel and MIPI CSI-2, as we don't need to check the details of the
format anymore.

Signed-off-by: Jan Luebbe <jlu@pengutronix.de>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Reviewed-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/imx/imx-media-capture.c | 38 +++++++++++++--------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c
index 4e3fdf8aeef5..256039ce561e 100644
--- a/drivers/staging/media/imx/imx-media-capture.c
+++ b/drivers/staging/media/imx/imx-media-capture.c
@@ -170,23 +170,22 @@ static int capture_enum_fmt_vid_cap(struct file *file, void *fh,
 	}
 
 	cc_src = imx_media_find_ipu_format(fmt_src.format.code, CS_SEL_ANY);
-	if (!cc_src)
-		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
-						    CS_SEL_ANY, true);
-	if (!cc_src)
-		return -EINVAL;
-
-	if (cc_src->bayer) {
-		if (f->index != 0)
-			return -EINVAL;
-		fourcc = cc_src->fourcc;
-	} else {
+	if (cc_src) {
 		u32 cs_sel = (cc_src->cs == IPUV3_COLORSPACE_YUV) ?
 			CS_SEL_YUV : CS_SEL_RGB;
 
 		ret = imx_media_enum_format(&fourcc, f->index, cs_sel);
 		if (ret)
 			return ret;
+	} else {
+		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
+						    CS_SEL_ANY, true);
+		if (WARN_ON(!cc_src))
+			return -EINVAL;
+
+		if (f->index != 0)
+			return -EINVAL;
+		fourcc = cc_src->fourcc;
 	}
 
 	f->pixelformat = fourcc;
@@ -219,15 +218,7 @@ static int capture_try_fmt_vid_cap(struct file *file, void *fh,
 		return ret;
 
 	cc_src = imx_media_find_ipu_format(fmt_src.format.code, CS_SEL_ANY);
-	if (!cc_src)
-		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
-						    CS_SEL_ANY, true);
-	if (!cc_src)
-		return -EINVAL;
-
-	if (cc_src->bayer) {
-		cc = cc_src;
-	} else {
+	if (cc_src) {
 		u32 fourcc, cs_sel;
 
 		cs_sel = (cc_src->cs == IPUV3_COLORSPACE_YUV) ?
@@ -239,6 +230,13 @@ static int capture_try_fmt_vid_cap(struct file *file, void *fh,
 			imx_media_enum_format(&fourcc, 0, cs_sel);
 			cc = imx_media_find_format(fourcc, cs_sel, false);
 		}
+	} else {
+		cc_src = imx_media_find_mbus_format(fmt_src.format.code,
+						    CS_SEL_ANY, true);
+		if (WARN_ON(!cc_src))
+			return -EINVAL;
+
+		cc = cc_src;
 	}
 
 	imx_media_mbus_fmt_to_pix_fmt(&f->fmt.pix, &fmt_src.format, cc);
-- 
cgit v1.2.3


From 779680e2e793db349c37668099f26d9080801f53 Mon Sep 17 00:00:00 2001
From: Jan Luebbe <jlu@pengutronix.de>
Date: Fri, 18 May 2018 09:56:39 -0400
Subject: media: imx: add support for RGB565_2X8 on parallel bus

The IPU can only capture RGB565 with two 8-bit cycles in bayer/generic
mode on the parallel bus, compared to a specific mode on MIPI CSI-2.
To handle this, we extend imx_media_pixfmt with a cycles per pixel
field, which is used for generic formats on the parallel bus.

Based on the selected format and bus, we then update the width to
account for the multiple cycles per pixel.

Signed-off-by: Jan Luebbe <jlu@pengutronix.de>
Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/imx/imx-media-csi.c   | 101 +++++++++++++++++++---------
 drivers/staging/media/imx/imx-media-utils.c |   1 +
 drivers/staging/media/imx/imx-media.h       |   2 +
 3 files changed, 71 insertions(+), 33 deletions(-)

diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 6a892839ffbf..4647206f92ca 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -122,10 +122,32 @@ static inline struct csi_priv *sd_to_dev(struct v4l2_subdev *sdev)
 	return container_of(sdev, struct csi_priv, sd);
 }
 
+static inline bool is_parallel_bus(struct v4l2_fwnode_endpoint *ep)
+{
+	return ep->bus_type != V4L2_MBUS_CSI2;
+}
+
 static inline bool is_parallel_16bit_bus(struct v4l2_fwnode_endpoint *ep)
 {
-	return ep->bus_type != V4L2_MBUS_CSI2 &&
-		ep->bus.parallel.bus_width >= 16;
+	return is_parallel_bus(ep) && ep->bus.parallel.bus_width >= 16;
+}
+
+/*
+ * Check for conditions that require the IPU to handle the
+ * data internally as generic data, aka passthrough mode:
+ * - raw bayer media bus formats, or
+ * - the CSI is receiving from a 16-bit parallel bus, or
+ * - the CSI is receiving from an 8-bit parallel bus and the incoming
+ *   media bus format is other than UYVY8_2X8/YUYV8_2X8.
+ */
+static inline bool requires_passthrough(struct v4l2_fwnode_endpoint *ep,
+					struct v4l2_mbus_framefmt *infmt,
+					const struct imx_media_pixfmt *incc)
+{
+	return incc->bayer || is_parallel_16bit_bus(ep) ||
+		(is_parallel_bus(ep) &&
+		 infmt->code != MEDIA_BUS_FMT_UYVY8_2X8 &&
+		 infmt->code != MEDIA_BUS_FMT_YUYV8_2X8);
 }
 
 /*
@@ -371,15 +393,18 @@ static void csi_idmac_unsetup_vb2_buf(struct csi_priv *priv,
 static int csi_idmac_setup_channel(struct csi_priv *priv)
 {
 	struct imx_media_video_dev *vdev = priv->vdev;
+	const struct imx_media_pixfmt *incc;
 	struct v4l2_mbus_framefmt *infmt;
 	struct ipu_image image;
 	u32 passthrough_bits;
+	u32 passthrough_cycles;
 	dma_addr_t phys[2];
 	bool passthrough;
 	u32 burst_size;
 	int ret;
 
 	infmt = &priv->format_mbus[CSI_SINK_PAD];
+	incc = priv->cc[CSI_SINK_PAD];
 
 	ipu_cpmem_zero(priv->idmac_ch);
 
@@ -393,12 +418,9 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	image.phys0 = phys[0];
 	image.phys1 = phys[1];
 
-	/*
-	 * Check for conditions that require the IPU to handle the
-	 * data internally as generic data, aka passthrough mode:
-	 * - raw bayer formats
-	 * - the CSI is receiving from a 16-bit parallel bus
-	 */
+	passthrough = requires_passthrough(&priv->upstream_ep, infmt, incc);
+	passthrough_cycles = 1;
+
 	switch (image.pix.pixelformat) {
 	case V4L2_PIX_FMT_SBGGR8:
 	case V4L2_PIX_FMT_SGBRG8:
@@ -406,7 +428,6 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	case V4L2_PIX_FMT_SRGGB8:
 	case V4L2_PIX_FMT_GREY:
 		burst_size = 16;
-		passthrough = true;
 		passthrough_bits = 8;
 		break;
 	case V4L2_PIX_FMT_SBGGR16:
@@ -415,7 +436,6 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	case V4L2_PIX_FMT_SRGGB16:
 	case V4L2_PIX_FMT_Y16:
 		burst_size = 8;
-		passthrough = true;
 		passthrough_bits = 16;
 		break;
 	case V4L2_PIX_FMT_YUV420:
@@ -423,7 +443,6 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 		burst_size = (image.pix.width & 0x3f) ?
 			     ((image.pix.width & 0x1f) ?
 			      ((image.pix.width & 0xf) ? 8 : 16) : 32) : 64;
-		passthrough = is_parallel_16bit_bus(&priv->upstream_ep);
 		passthrough_bits = 16;
 		/* Skip writing U and V components to odd rows */
 		ipu_cpmem_skip_odd_chroma_rows(priv->idmac_ch);
@@ -432,18 +451,25 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 	case V4L2_PIX_FMT_UYVY:
 		burst_size = (image.pix.width & 0x1f) ?
 			     ((image.pix.width & 0xf) ? 8 : 16) : 32;
-		passthrough = is_parallel_16bit_bus(&priv->upstream_ep);
 		passthrough_bits = 16;
 		break;
+	case V4L2_PIX_FMT_RGB565:
+		if (passthrough) {
+			burst_size = 16;
+			passthrough_bits = 8;
+			passthrough_cycles = incc->cycles;
+			break;
+		}
+		/* fallthrough for non-passthrough RGB565 (CSI-2 bus) */
 	default:
 		burst_size = (image.pix.width & 0xf) ? 8 : 16;
-		passthrough = is_parallel_16bit_bus(&priv->upstream_ep);
 		passthrough_bits = 16;
 		break;
 	}
 
 	if (passthrough) {
-		ipu_cpmem_set_resolution(priv->idmac_ch, image.rect.width,
+		ipu_cpmem_set_resolution(priv->idmac_ch,
+					 image.rect.width * passthrough_cycles,
 					 image.rect.height);
 		ipu_cpmem_set_stride(priv->idmac_ch, image.pix.bytesperline);
 		ipu_cpmem_set_buffer(priv->idmac_ch, 0, image.phys0);
@@ -635,17 +661,20 @@ static void csi_idmac_stop(struct csi_priv *priv)
 static int csi_setup(struct csi_priv *priv)
 {
 	struct v4l2_mbus_framefmt *infmt, *outfmt;
+	const struct imx_media_pixfmt *incc;
 	struct v4l2_mbus_config mbus_cfg;
 	struct v4l2_mbus_framefmt if_fmt;
+	struct v4l2_rect crop;
 
 	infmt = &priv->format_mbus[CSI_SINK_PAD];
+	incc = priv->cc[CSI_SINK_PAD];
 	outfmt = &priv->format_mbus[priv->active_output_pad];
 
 	/* compose mbus_config from the upstream endpoint */
 	mbus_cfg.type = priv->upstream_ep.bus_type;
-	mbus_cfg.flags = (priv->upstream_ep.bus_type == V4L2_MBUS_CSI2) ?
-		priv->upstream_ep.bus.mipi_csi2.flags :
-		priv->upstream_ep.bus.parallel.flags;
+	mbus_cfg.flags = is_parallel_bus(&priv->upstream_ep) ?
+		priv->upstream_ep.bus.parallel.flags :
+		priv->upstream_ep.bus.mipi_csi2.flags;
 
 	/*
 	 * we need to pass input frame to CSI interface, but
@@ -653,8 +682,18 @@ static int csi_setup(struct csi_priv *priv)
 	 */
 	if_fmt = *infmt;
 	if_fmt.field = outfmt->field;
+	crop = priv->crop;
 
-	ipu_csi_set_window(priv->csi, &priv->crop);
+	/*
+	 * if cycles is set, we need to handle this over multiple cycles as
+	 * generic/bayer data
+	 */
+	if (is_parallel_bus(&priv->upstream_ep) && incc->cycles) {
+		if_fmt.width *= incc->cycles;
+		crop.width *= incc->cycles;
+	}
+
+	ipu_csi_set_window(priv->csi, &crop);
 
 	ipu_csi_set_downsize(priv->csi,
 			     priv->crop.width == 2 * priv->compose.width,
@@ -1012,7 +1051,6 @@ static int csi_link_validate(struct v4l2_subdev *sd,
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
 	struct v4l2_fwnode_endpoint upstream_ep = {};
-	const struct imx_media_pixfmt *incc;
 	bool is_csi2;
 	int ret;
 
@@ -1030,17 +1068,7 @@ static int csi_link_validate(struct v4l2_subdev *sd,
 	mutex_lock(&priv->lock);
 
 	priv->upstream_ep = upstream_ep;
-	is_csi2 = (upstream_ep.bus_type == V4L2_MBUS_CSI2);
-	incc = priv->cc[CSI_SINK_PAD];
-
-	if (priv->dest != IPU_CSI_DEST_IDMAC &&
-	    (incc->bayer || is_parallel_16bit_bus(&upstream_ep))) {
-		v4l2_err(&priv->sd,
-			 "bayer/16-bit parallel buses must go to IDMAC pad\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
+	is_csi2 = !is_parallel_bus(&upstream_ep);
 	if (is_csi2) {
 		int vc_num = 0;
 		/*
@@ -1064,7 +1092,7 @@ static int csi_link_validate(struct v4l2_subdev *sd,
 
 	/* select either parallel or MIPI-CSI2 as input to CSI */
 	ipu_set_csi_src_mux(priv->ipu, priv->csi_id, is_csi2);
-out:
+
 	mutex_unlock(&priv->lock);
 	return ret;
 }
@@ -1136,6 +1164,7 @@ static int csi_enum_mbus_code(struct v4l2_subdev *sd,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	struct csi_priv *priv = v4l2_get_subdevdata(sd);
+	struct v4l2_fwnode_endpoint upstream_ep;
 	const struct imx_media_pixfmt *incc;
 	struct v4l2_mbus_framefmt *infmt;
 	int ret = 0;
@@ -1152,7 +1181,13 @@ static int csi_enum_mbus_code(struct v4l2_subdev *sd,
 		break;
 	case CSI_SRC_PAD_DIRECT:
 	case CSI_SRC_PAD_IDMAC:
-		if (incc->bayer) {
+		ret = csi_get_upstream_endpoint(priv, &upstream_ep);
+		if (ret) {
+			v4l2_err(&priv->sd, "failed to find upstream endpoint\n");
+			goto out;
+		}
+
+		if (requires_passthrough(&upstream_ep, infmt, incc)) {
 			if (code->index != 0) {
 				ret = -EINVAL;
 				goto out;
@@ -1293,7 +1328,7 @@ static void csi_try_fmt(struct csi_priv *priv,
 		sdformat->format.width = compose->width;
 		sdformat->format.height = compose->height;
 
-		if (incc->bayer) {
+		if (requires_passthrough(upstream_ep, infmt, incc)) {
 			sdformat->format.code = infmt->code;
 			*cc = incc;
 		} else {
diff --git a/drivers/staging/media/imx/imx-media-utils.c b/drivers/staging/media/imx/imx-media-utils.c
index 7ec2db84451c..8aa13403b09d 100644
--- a/drivers/staging/media/imx/imx-media-utils.c
+++ b/drivers/staging/media/imx/imx-media-utils.c
@@ -78,6 +78,7 @@ static const struct imx_media_pixfmt rgb_formats[] = {
 		.codes  = {MEDIA_BUS_FMT_RGB565_2X8_LE},
 		.cs     = IPUV3_COLORSPACE_RGB,
 		.bpp    = 16,
+		.cycles = 2,
 	}, {
 		.fourcc	= V4L2_PIX_FMT_RGB24,
 		.codes  = {
diff --git a/drivers/staging/media/imx/imx-media.h b/drivers/staging/media/imx/imx-media.h
index e945e0ed6dd6..57bd094cf765 100644
--- a/drivers/staging/media/imx/imx-media.h
+++ b/drivers/staging/media/imx/imx-media.h
@@ -62,6 +62,8 @@ struct imx_media_pixfmt {
 	u32     fourcc;
 	u32     codes[4];
 	int     bpp;     /* total bpp */
+	/* cycles per pixel for generic (bayer) formats for the parallel bus */
+	int	cycles;
 	enum ipu_color_space cs;
 	bool    planar;  /* is a planar format */
 	bool    bayer;   /* is a raw bayer format */
-- 
cgit v1.2.3


From 5520b9467a39d5ec9ce9cd8a9ed01f826b817524 Mon Sep 17 00:00:00 2001
From: Keiichi Watanabe <keiichiw@chromium.org>
Date: Mon, 18 Jun 2018 03:58:52 -0400
Subject: media: v4l2-ctrl: Change control for VP8 profile to menu control

Add a menu control V4L2_CID_MPEG_VIDEO_VP8_PROFILE for VP8 profile and make
V4L2_CID_MPEG_VIDEO_VPX_PROFILE an alias of it. This new control is used to
select the desired profile for VP8 encoder and query for supported profiles by
VP8 encoder/decoder.

Though we have originally a control V4L2_CID_MPEG_VIDEO_VPX_PROFILE and its name
contains 'VPX', it works only for VP8 because supported profiles usually differ
between VP8 and VP9. In addition, this control cannot be used for querying since
it is not a menu control but an integer control, which cannot return an
arbitrary set of supported profiles.

The new control V4L2_CID_MPEG_VIDEO_VP8_PROFILE is a menu control as with
controls for other codec profiles. (e.g. H264)

In addition, this patch also fixes the use of V4L2_CID_MPEG_VIDEO_VPX_PROFILE in
drivers of Qualcomm's venus and Samsung's s5p-mfc.

Signed-off-by: Keiichi Watanabe <keiichiw@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/extended-controls.rst | 25 +++++++++++++++++++---
 drivers/media/platform/qcom/venus/vdec_ctrls.c     | 10 +++++----
 drivers/media/platform/qcom/venus/venc.c           |  4 ++--
 drivers/media/platform/qcom/venus/venc_ctrls.c     | 10 +++++----
 drivers/media/platform/s5p-mfc/s5p_mfc_enc.c       | 15 ++++++-------
 drivers/media/v4l2-core/v4l2-ctrls.c               | 12 ++++++++++-
 include/uapi/linux/v4l2-controls.h                 | 11 +++++++++-
 7 files changed, 64 insertions(+), 23 deletions(-)

diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst
index 03931f9b1285..01ef31a934b4 100644
--- a/Documentation/media/uapi/v4l/extended-controls.rst
+++ b/Documentation/media/uapi/v4l/extended-controls.rst
@@ -1955,9 +1955,28 @@ enum v4l2_vp8_golden_frame_sel -
 ``V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP (integer)``
     Quantization parameter for a P frame for VP8.
 
-``V4L2_CID_MPEG_VIDEO_VPX_PROFILE (integer)``
-    Select the desired profile for VPx encoder. Acceptable values are 0,
-    1, 2 and 3 corresponding to encoder profiles 0, 1, 2 and 3.
+.. _v4l2-mpeg-video-vp8-profile:
+
+``V4L2_CID_MPEG_VIDEO_VP8_PROFILE``
+    (enum)
+
+enum v4l2_mpeg_video_vp8_profile -
+    This control allows selecting the profile for VP8 encoder.
+    This is also used to enumerate supported profiles by VP8 encoder or decoder.
+    Possible values are:
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_0``
+      - Profile 0
+    * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_1``
+      - Profile 1
+    * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_2``
+      - Profile 2
+    * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_3``
+      - Profile 3
 
 
 High Efficiency Video Coding (HEVC/H.265) Control Reference
diff --git a/drivers/media/platform/qcom/venus/vdec_ctrls.c b/drivers/media/platform/qcom/venus/vdec_ctrls.c
index 032839bbc967..f4604b0cd57e 100644
--- a/drivers/media/platform/qcom/venus/vdec_ctrls.c
+++ b/drivers/media/platform/qcom/venus/vdec_ctrls.c
@@ -29,7 +29,7 @@ static int vdec_op_s_ctrl(struct v4l2_ctrl *ctrl)
 		break;
 	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE:
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		ctr->profile = ctrl->val;
 		break;
 	case V4L2_CID_MPEG_VIDEO_H264_LEVEL:
@@ -54,7 +54,7 @@ static int vdec_op_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
 	switch (ctrl->id) {
 	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_MPEG4_PROFILE:
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		ret = hfi_session_get_property(inst, ptype, &hprop);
 		if (!ret)
 			ctr->profile = hprop.profile_level.profile;
@@ -130,8 +130,10 @@ int vdec_ctrl_init(struct venus_inst *inst)
 	if (ctrl)
 		ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
-	ctrl = v4l2_ctrl_new_std(&inst->ctrl_handler, &vdec_ctrl_ops,
-				 V4L2_CID_MPEG_VIDEO_VPX_PROFILE, 0, 3, 1, 0);
+	ctrl = v4l2_ctrl_new_std_menu(&inst->ctrl_handler, &vdec_ctrl_ops,
+				      V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
+				      V4L2_MPEG_VIDEO_VP8_PROFILE_3,
+				      0, V4L2_MPEG_VIDEO_VP8_PROFILE_0);
 	if (ctrl)
 		ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
 
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 11dafc7848c5..f7a87a3dbb46 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -223,7 +223,7 @@ static int venc_v4l2_to_hfi(int id, int value)
 		case V4L2_MPEG_VIDEO_H264_ENTROPY_MODE_CABAC:
 			return HFI_H264_ENTROPY_CABAC;
 		}
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		switch (value) {
 		case 0:
 		default:
@@ -754,7 +754,7 @@ static int venc_set_properties(struct venus_inst *inst)
 		level = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_H264_LEVEL,
 					 ctr->level.h264);
 	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_VP8) {
-		profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_VPX_PROFILE,
+		profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
 					   ctr->profile.vpx);
 		level = 0;
 	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_MPEG4) {
diff --git a/drivers/media/platform/qcom/venus/venc_ctrls.c b/drivers/media/platform/qcom/venus/venc_ctrls.c
index 21e938a28662..459101728d26 100644
--- a/drivers/media/platform/qcom/venus/venc_ctrls.c
+++ b/drivers/media/platform/qcom/venus/venc_ctrls.c
@@ -101,7 +101,7 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
 		ctr->profile.h264 = ctrl->val;
 		break;
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		ctr->profile.vpx = ctrl->val;
 		break;
 	case V4L2_CID_MPEG_VIDEO_MPEG4_LEVEL:
@@ -248,6 +248,11 @@ int venc_ctrl_init(struct venus_inst *inst)
 		V4L2_MPEG_VIDEO_MULTI_SICE_MODE_MAX_BYTES,
 		0, V4L2_MPEG_VIDEO_MULTI_SLICE_MODE_SINGLE);
 
+	v4l2_ctrl_new_std_menu(&inst->ctrl_handler, &venc_ctrl_ops,
+		V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
+		V4L2_MPEG_VIDEO_VP8_PROFILE_3,
+		0, V4L2_MPEG_VIDEO_VP8_PROFILE_0);
+
 	v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops,
 		V4L2_CID_MPEG_VIDEO_BITRATE, BITRATE_MIN, BITRATE_MAX,
 		BITRATE_STEP, BITRATE_DEFAULT);
@@ -256,9 +261,6 @@ int venc_ctrl_init(struct venus_inst *inst)
 		V4L2_CID_MPEG_VIDEO_BITRATE_PEAK, BITRATE_MIN, BITRATE_MAX,
 		BITRATE_STEP, BITRATE_DEFAULT_PEAK);
 
-	v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops,
-		V4L2_CID_MPEG_VIDEO_VPX_PROFILE, 0, 3, 1, 0);
-
 	v4l2_ctrl_new_std(&inst->ctrl_handler, &venc_ctrl_ops,
 		V4L2_CID_MPEG_VIDEO_H264_I_FRAME_QP, 1, 51, 1, 26);
 
diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
index 570f391f2cfd..3ad4f5073002 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc_enc.c
@@ -692,12 +692,12 @@ static struct mfc_control controls[] = {
 		.default_value = 10,
 	},
 	{
-		.id = V4L2_CID_MPEG_VIDEO_VPX_PROFILE,
-		.type = V4L2_CTRL_TYPE_INTEGER,
-		.minimum = 0,
-		.maximum = 3,
-		.step = 1,
-		.default_value = 0,
+		.id = V4L2_CID_MPEG_VIDEO_VP8_PROFILE,
+		.type = V4L2_CTRL_TYPE_MENU,
+		.minimum = V4L2_MPEG_VIDEO_VP8_PROFILE_0,
+		.maximum = V4L2_MPEG_VIDEO_VP8_PROFILE_3,
+		.default_value = V4L2_MPEG_VIDEO_VP8_PROFILE_0,
+		.menu_skip_mask = 0,
 	},
 	{
 		.id = V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP,
@@ -2057,7 +2057,7 @@ static int s5p_mfc_enc_s_ctrl(struct v4l2_ctrl *ctrl)
 	case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP:
 		p->codec.vp8.rc_p_frame_qp = ctrl->val;
 		break;
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		p->codec.vp8.profile = ctrl->val;
 		break;
 	case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP:
@@ -2711,4 +2711,3 @@ void s5p_mfc_enc_init(struct s5p_mfc_ctx *ctx)
 	f.fmt.pix_mp.pixelformat = DEF_DST_FMT_ENC;
 	ctx->dst_fmt = find_format(&f, MFC_FMT_ENC);
 }
-
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index d1087573da34..4a182a70de36 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -431,6 +431,13 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		"Use Previous Specific Frame",
 		NULL,
 	};
+	static const char * const vp8_profile[] = {
+		"0",
+		"1",
+		"2",
+		"3",
+		NULL,
+	};
 
 	static const char * const flash_led_mode[] = {
 		"Off",
@@ -614,6 +621,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		return mpeg4_profile;
 	case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL:
 		return vpx_golden_frame_sel;
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
+		return vp8_profile;
 	case V4L2_CID_JPEG_CHROMA_SUBSAMPLING:
 		return jpeg_chroma_subsampling;
 	case V4L2_CID_DV_TX_MODE:
@@ -839,7 +848,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_VPX_MAX_QP:			return "VPX Maximum QP Value";
 	case V4L2_CID_MPEG_VIDEO_VPX_I_FRAME_QP:		return "VPX I-Frame QP Value";
 	case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP:		return "VPX P-Frame QP Value";
-	case V4L2_CID_MPEG_VIDEO_VPX_PROFILE:			return "VPX Profile";
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:			return "VP8 Profile";
 
 	/* HEVC controls */
 	case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP:		return "HEVC I-Frame QP Value";
@@ -1180,6 +1189,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_DEINTERLACING_MODE:
 	case V4L2_CID_TUNE_DEEMPHASIS:
 	case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL:
+	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 	case V4L2_CID_DETECT_MD_MODE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL:
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index 8a75ad7899f3..ab96795b2829 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -587,7 +587,16 @@ enum v4l2_vp8_golden_frame_sel {
 #define V4L2_CID_MPEG_VIDEO_VPX_MAX_QP			(V4L2_CID_MPEG_BASE+508)
 #define V4L2_CID_MPEG_VIDEO_VPX_I_FRAME_QP		(V4L2_CID_MPEG_BASE+509)
 #define V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP		(V4L2_CID_MPEG_BASE+510)
-#define V4L2_CID_MPEG_VIDEO_VPX_PROFILE			(V4L2_CID_MPEG_BASE+511)
+
+#define V4L2_CID_MPEG_VIDEO_VP8_PROFILE			(V4L2_CID_MPEG_BASE+511)
+enum v4l2_mpeg_video_vp8_profile {
+	V4L2_MPEG_VIDEO_VP8_PROFILE_0				= 0,
+	V4L2_MPEG_VIDEO_VP8_PROFILE_1				= 1,
+	V4L2_MPEG_VIDEO_VP8_PROFILE_2				= 2,
+	V4L2_MPEG_VIDEO_VP8_PROFILE_3				= 3,
+};
+/* Deprecated alias for compatibility reasons. */
+#define V4L2_CID_MPEG_VIDEO_VPX_PROFILE	V4L2_CID_MPEG_VIDEO_VP8_PROFILE
 
 /* CIDs for HEVC encoding. */
 
-- 
cgit v1.2.3


From c47d8c2f38f805ba541496ddd7d8c3aee59b49d5 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:47 -0700
Subject: net: Clear skb->tstamp only on the forwarding path

This is done in preparation for the upcoming time based transmission
patchset. Now that skb->tstamp will be used to hold packet's txtime,
we must ensure that it is being cleared when traversing namespaces.
Also, doing that from skb_scrub_packet() before the early return would
break our feature when tunnels are used.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 1357f36c8a5e..c4e24ac27464 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -4898,7 +4898,6 @@ EXPORT_SYMBOL(skb_try_coalesce);
  */
 void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 {
-	skb->tstamp = 0;
 	skb->pkt_type = PACKET_HOST;
 	skb->skb_iif = 0;
 	skb->ignore_df = 0;
@@ -4912,6 +4911,7 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 
 	ipvs_reset(skb);
 	skb->mark = 0;
+	skb->tstamp = 0;
 }
 EXPORT_SYMBOL_GPL(skb_scrub_packet);
 
-- 
cgit v1.2.3


From 80b14dee2bea128928537d61c333f24cb8cbb62f Mon Sep 17 00:00:00 2001
From: Richard Cochran <rcochran@linutronix.de>
Date: Tue, 3 Jul 2018 15:42:48 -0700
Subject: net: Add a new socket option for a future transmit time.

This patch introduces SO_TXTIME. User space enables this option in
order to pass a desired future transmit time in a CMSG when calling
sendmsg(2). The argument to this socket option is a 8-bytes long struct
provided by the uapi header net_tstamp.h defined as:

struct sock_txtime {
	clockid_t 	clockid;
	u32		flags;
};

Note that new fields were added to struct sock by filling a 2-bytes
hole found in the struct. For that reason, neither the struct size or
number of cachelines were altered.

Signed-off-by: Richard Cochran <rcochran@linutronix.de>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/alpha/include/uapi/asm/socket.h  |  3 +++
 arch/ia64/include/uapi/asm/socket.h   |  3 +++
 arch/mips/include/uapi/asm/socket.h   |  3 +++
 arch/parisc/include/uapi/asm/socket.h |  3 +++
 arch/s390/include/uapi/asm/socket.h   |  3 +++
 arch/sparc/include/uapi/asm/socket.h  |  3 +++
 arch/xtensa/include/uapi/asm/socket.h |  3 +++
 include/net/sock.h                    | 10 ++++++++++
 include/uapi/asm-generic/socket.h     |  3 +++
 include/uapi/linux/net_tstamp.h       | 15 +++++++++++++++
 net/core/sock.c                       | 35 +++++++++++++++++++++++++++++++++++
 11 files changed, 84 insertions(+)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index be14f16149d5..065fb372e355 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -112,4 +112,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 3efba40adc54..c872c4e6bafb 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -114,4 +114,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index 49c3d4795963..71370fb3ceef 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -123,4 +123,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index 1d0fdc3b5d22..061b9cf2a779 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -104,4 +104,7 @@
 
 #define SO_ZEROCOPY		0x4035
 
+#define SO_TXTIME		0x4036
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 3510c0fd06f4..39d901476ee5 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -111,4 +111,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index d58520c2e6ff..7ea35e5601b6 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -101,6 +101,9 @@
 
 #define SO_ZEROCOPY		0x003e
 
+#define SO_TXTIME		0x003f
+#define SCM_TXTIME		SO_TXTIME
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 75a07b8119a9..1de07a7f7680 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -116,4 +116,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index 2ed99bfa4595..68347b9821c6 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -319,6 +319,9 @@ struct sock_common {
   *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
   *	@sk_reuseport_cb: reuseport group container
   *	@sk_rcu: used during RCU grace period
+  *	@sk_clockid: clockid used by time-based scheduling (SO_TXTIME)
+  *	@sk_txtime_deadline_mode: set deadline mode for SO_TXTIME
+  *	@sk_txtime_unused: unused txtime flags
   */
 struct sock {
 	/*
@@ -475,6 +478,11 @@ struct sock {
 	u8			sk_shutdown;
 	u32			sk_tskey;
 	atomic_t		sk_zckey;
+
+	u8			sk_clockid;
+	u8			sk_txtime_deadline_mode : 1,
+				sk_txtime_unused : 7;
+
 	struct socket		*sk_socket;
 	void			*sk_user_data;
 #ifdef CONFIG_SECURITY
@@ -790,6 +798,7 @@ enum sock_flags {
 	SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
 	SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
+	SOCK_TXTIME,
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -1585,6 +1594,7 @@ void sock_kzfree_s(struct sock *sk, void *mem, int size);
 void sk_send_sigurg(struct sock *sk);
 
 struct sockcm_cookie {
+	u64 transmit_time;
 	u32 mark;
 	u16 tsflags;
 };
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 0ae758c90e54..a12692e5f7a8 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -107,4 +107,7 @@
 
 #define SO_ZEROCOPY		60
 
+#define SO_TXTIME		61
+#define SCM_TXTIME		SO_TXTIME
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 4fe104b2411f..c9a77c353b98 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -141,4 +141,19 @@ struct scm_ts_pktinfo {
 	__u32 reserved[2];
 };
 
+/*
+ * SO_TXTIME gets a struct sock_txtime with flags being an integer bit
+ * field comprised of these values.
+ */
+enum txtime_flags {
+	SOF_TXTIME_DEADLINE_MODE = (1 << 0),
+
+	SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_DEADLINE_MODE)
+};
+
+struct sock_txtime {
+	clockid_t       clockid;        /* reference clockid */
+	u32             flags;          /* flags defined by enum txtime_flags */
+};
+
 #endif /* _NET_TIMESTAMPING_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index 6429982eb976..fe64b839f1b2 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -91,6 +91,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <asm/unaligned.h>
 #include <linux/capability.h>
 #include <linux/errno.h>
 #include <linux/errqueue.h>
@@ -697,6 +698,7 @@ EXPORT_SYMBOL(sk_mc_loop);
 int sock_setsockopt(struct socket *sock, int level, int optname,
 		    char __user *optval, unsigned int optlen)
 {
+	struct sock_txtime sk_txtime;
 	struct sock *sk = sock->sk;
 	int val;
 	int valbool;
@@ -1070,6 +1072,24 @@ set_rcvbuf:
 		}
 		break;
 
+	case SO_TXTIME:
+		if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN)) {
+			ret = -EPERM;
+		} else if (optlen != sizeof(struct sock_txtime)) {
+			ret = -EINVAL;
+		} else if (copy_from_user(&sk_txtime, optval,
+			   sizeof(struct sock_txtime))) {
+			ret = -EFAULT;
+		} else if (sk_txtime.flags & ~SOF_TXTIME_FLAGS_MASK) {
+			ret = -EINVAL;
+		} else {
+			sock_valbool_flag(sk, SOCK_TXTIME, true);
+			sk->sk_clockid = sk_txtime.clockid;
+			sk->sk_txtime_deadline_mode =
+				!!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
+		}
+		break;
+
 	default:
 		ret = -ENOPROTOOPT;
 		break;
@@ -1115,6 +1135,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		u64 val64;
 		struct linger ling;
 		struct timeval tm;
+		struct sock_txtime txtime;
 	} v;
 
 	int lv = sizeof(int);
@@ -1403,6 +1424,13 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sock_flag(sk, SOCK_ZEROCOPY);
 		break;
 
+	case SO_TXTIME:
+		lv = sizeof(v.txtime);
+		v.txtime.clockid = sk->sk_clockid;
+		v.txtime.flags |= sk->sk_txtime_deadline_mode ?
+				  SOF_TXTIME_DEADLINE_MODE : 0;
+		break;
+
 	default:
 		/* We implement the SO_SNDLOWAT etc to not be settable
 		 * (1003.1g 7).
@@ -2137,6 +2165,13 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		sockc->tsflags &= ~SOF_TIMESTAMPING_TX_RECORD_MASK;
 		sockc->tsflags |= tsflags;
 		break;
+	case SCM_TXTIME:
+		if (!sock_flag(sk, SOCK_TXTIME))
+			return -EINVAL;
+		if (cmsg->cmsg_len != CMSG_LEN(sizeof(u64)))
+			return -EINVAL;
+		sockc->transmit_time = get_unaligned((u64 *)CMSG_DATA(cmsg));
+		break;
 	/* SCM_RIGHTS and SCM_CREDENTIALS are semantically in SOL_UNIX. */
 	case SCM_RIGHTS:
 	case SCM_CREDENTIALS:
-- 
cgit v1.2.3


From bc969a977880511057053642a81371196303ca01 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:49 -0700
Subject: net: ipv4: Hook into time based transmission

Add a transmit_time field to struct inet_cork, then copy the
timestamp from the CMSG cookie at ip_setup_cork() so we can
safely copy it into the skb later during __ip_make_skb().

For the raw fast path, just perform the copy at raw_send_hdrinc().

Signed-off-by: Richard Cochran <rcochran@linutronix.de>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h | 1 +
 net/ipv4/icmp.c         | 2 ++
 net/ipv4/ip_output.c    | 3 +++
 net/ipv4/ping.c         | 1 +
 net/ipv4/raw.c          | 2 ++
 net/ipv4/udp.c          | 1 +
 6 files changed, 10 insertions(+)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 83d5b3c2ac42..314be484c696 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -148,6 +148,7 @@ struct inet_cork {
 	__s16			tos;
 	char			priority;
 	__u16			gso_size;
+	u64			transmit_time;
 };
 
 struct inet_cork_full {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 1617604c9284..937239afd68d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -437,6 +437,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	if (icmp_param->replyopts.opt.opt.optlen) {
 		ipc.opt = &icmp_param->replyopts.opt;
@@ -715,6 +716,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, &icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 188cc586e7ff..570e3ebc3974 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1154,6 +1154,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->tos = ipc->tos;
 	cork->priority = ipc->priority;
 	cork->tx_flags = ipc->tx_flags;
+	cork->transmit_time = ipc->sockc.transmit_time;
 
 	return 0;
 }
@@ -1414,6 +1415,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk,
 
 	skb->priority = (cork->tos != -1) ? cork->priority: sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = cork->transmit_time;
 	/*
 	 * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec
 	 * on dst refcount
@@ -1551,6 +1553,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 2ed64bca54e3..b47492205507 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,6 +746,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index abb3c9490c55..446af7be2b55 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -381,6 +381,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4,
 
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc->transmit_time;
 	skb_dst_set(skb, &rt->dst);
 	*rtp = NULL;
 
@@ -562,6 +563,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	}
 
 	ipc.sockc.tsflags = sk->sk_tsflags;
+	ipc.sockc.transmit_time = 0;
 	ipc.addr = inet->inet_saddr;
 	ipc.opt = NULL;
 	ipc.tx_flags = 0;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 24e116ddae79..5c76ba0666ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -930,6 +930,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc.tx_flags = 0;
 	ipc.ttl = 0;
 	ipc.tos = -1;
+	ipc.sockc.transmit_time = 0;
 
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 
-- 
cgit v1.2.3


From a818f75e311c23cdac528888c60ae6e43a8958d0 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:50 -0700
Subject: net: ipv6: Hook into time based transmission

Add a struct sockcm_cookie parameter to ip6_setup_cork() so
we can easily re-use the transmit_time field from struct inet_cork
for most paths, by copying the timestamp from the CMSG cookie.
This is later copied into the skb during __ip6_make_skb().

For the raw fast path, also pass the sockcm_cookie as a parameter
so we can just perform the copy at rawv6_send_hdrinc() directly.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_output.c | 11 ++++++++---
 net/ipv6/raw.c        |  7 +++++--
 net/ipv6/udp.c        |  1 +
 3 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index a14fb4fcdf18..f48af7e62f12 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1158,7 +1158,8 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 
 static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 			  struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6,
-			  struct rt6_info *rt, struct flowi6 *fl6)
+			  struct rt6_info *rt, struct flowi6 *fl6,
+			  const struct sockcm_cookie *sockc)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	unsigned int mtu;
@@ -1226,6 +1227,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		cork->base.flags |= IPCORK_ALLFRAG;
 	cork->base.length = 0;
 
+	cork->base.transmit_time = sockc->transmit_time;
+
 	return 0;
 }
 
@@ -1575,7 +1578,7 @@ int ip6_append_data(struct sock *sk,
 		 * setup for corking
 		 */
 		err = ip6_setup_cork(sk, &inet->cork, &np->cork,
-				     ipc6, rt, fl6);
+				     ipc6, rt, fl6, sockc);
 		if (err)
 			return err;
 
@@ -1673,6 +1676,8 @@ struct sk_buff *__ip6_make_skb(struct sock *sk,
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
 
+	skb->tstamp = cork->base.transmit_time;
+
 	skb_dst_set(skb, dst_clone(&rt->dst));
 	IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len);
 	if (proto == IPPROTO_ICMPV6) {
@@ -1765,7 +1770,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	cork->base.opt = NULL;
 	cork->base.dst = NULL;
 	v6_cork.opt = NULL;
-	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
+	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6, sockc);
 	if (err) {
 		ip6_cork_release(cork, &v6_cork);
 		return ERR_PTR(err);
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index afc307c89d1a..5737c50f16eb 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -620,7 +620,7 @@ out:
 
 static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 			struct flowi6 *fl6, struct dst_entry **dstp,
-			unsigned int flags)
+			unsigned int flags, const struct sockcm_cookie *sockc)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct net *net = sock_net(sk);
@@ -650,6 +650,7 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length,
 	skb->protocol = htons(ETH_P_IPV6);
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc->transmit_time;
 	skb_dst_set(skb, &rt->dst);
 	*dstp = NULL;
 
@@ -848,6 +849,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
 	sockc.tsflags = sk->sk_tsflags;
+	sockc.transmit_time = 0;
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
@@ -921,7 +923,8 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 back_from_confirm:
 	if (inet->hdrincl)
-		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags);
+		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
+					msg->msg_flags, &sockc);
 	else {
 		ipc6.opt = opt;
 		lock_sock(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index e6645cae403e..ac6fc6728903 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1148,6 +1148,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	ipc6.dontfrag = -1;
 	ipc6.gso_size = up->gso_size;
 	sockc.tsflags = sk->sk_tsflags;
+	sockc.transmit_time = 0;
 
 	/* destination address check */
 	if (sin6) {
-- 
cgit v1.2.3


From 3d0ba8c03ca9c49ffcb79d989312f123dd1bdc7a Mon Sep 17 00:00:00 2001
From: Richard Cochran <rcochran@linutronix.de>
Date: Tue, 3 Jul 2018 15:42:51 -0700
Subject: net: packet: Hook into time based transmission.

For raw layer-2 packets, copy the desired future transmit time from
the CMSG cookie into the skb.

Signed-off-by: Richard Cochran <rcochran@linutronix.de>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 57634bc3da74..3428f7739ae9 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1951,6 +1951,7 @@ retry:
 		goto out_unlock;
 	}
 
+	sockc.transmit_time = 0;
 	sockc.tsflags = sk->sk_tsflags;
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
@@ -1962,6 +1963,7 @@ retry:
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sk->sk_mark;
+	skb->tstamp = sockc.transmit_time;
 
 	sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags);
 
@@ -2457,6 +2459,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 	skb->dev = dev;
 	skb->priority = po->sk.sk_priority;
 	skb->mark = po->sk.sk_mark;
+	skb->tstamp = sockc->transmit_time;
 	sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags);
 	skb_shinfo(skb)->destructor_arg = ph.raw;
 
@@ -2633,6 +2636,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
+	sockc.transmit_time = 0;
 	sockc.tsflags = po->sk.sk_tsflags;
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(&po->sk, msg, &sockc);
@@ -2829,6 +2833,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
+	sockc.transmit_time = 0;
 	sockc.tsflags = sk->sk_tsflags;
 	sockc.mark = sk->sk_mark;
 	if (msg->msg_controllen) {
@@ -2903,6 +2908,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	skb->dev = dev;
 	skb->priority = sk->sk_priority;
 	skb->mark = sockc.mark;
+	skb->tstamp = sockc.transmit_time;
 
 	if (has_vnet_hdr) {
 		err = virtio_net_hdr_to_skb(skb, &vnet_hdr, vio_le());
-- 
cgit v1.2.3


From 860b642b9c33ea4a6ae2f416607b0b98a9d11bb0 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Tue, 3 Jul 2018 15:42:52 -0700
Subject: net/sched: Allow creating a Qdisc watchdog with other clocks

This adds 'qdisc_watchdog_init_clockid()' that allows a clockid to be
passed, this allows other time references to be used when scheduling
the Qdisc to run.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_sched.h |  2 ++
 net/sched/sch_api.c     | 11 +++++++++--
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 815b92a23936..2466ea143d01 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -72,6 +72,8 @@ struct qdisc_watchdog {
 	struct Qdisc	*qdisc;
 };
 
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+				 clockid_t clockid);
 void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
 void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires);
 
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 54eca685420f..98541c6399db 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -596,12 +596,19 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+void qdisc_watchdog_init_clockid(struct qdisc_watchdog *wd, struct Qdisc *qdisc,
+				 clockid_t clockid)
 {
-	hrtimer_init(&wd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	hrtimer_init(&wd->timer, clockid, HRTIMER_MODE_ABS_PINNED);
 	wd->timer.function = qdisc_watchdog;
 	wd->qdisc = qdisc;
 }
+EXPORT_SYMBOL(qdisc_watchdog_init_clockid);
+
+void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc)
+{
+	qdisc_watchdog_init_clockid(wd, qdisc, CLOCK_MONOTONIC);
+}
 EXPORT_SYMBOL(qdisc_watchdog_init);
 
 void qdisc_watchdog_schedule_ns(struct qdisc_watchdog *wd, u64 expires)
-- 
cgit v1.2.3


From 25db26a91364db00f5a30da2fea8e9afe14a163c Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Tue, 3 Jul 2018 15:42:53 -0700
Subject: net/sched: Introduce the ETF Qdisc

The ETF (Earliest TxTime First) qdisc uses the information added
earlier in this series (the socket option SO_TXTIME and the new
role of sk_buff->tstamp) to schedule packets transmission based
on absolute time.

For some workloads, just bandwidth enforcement is not enough, and
precise control of the transmission of packets is necessary.

Example:

$ tc qdisc replace dev enp2s0 parent root handle 100 mqprio num_tc 3 \
           map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0

$ tc qdisc add dev enp2s0 parent 100:1 etf delta 100000 \
           clockid CLOCK_TAI

In this example, the Qdisc will provide SW best-effort for the control
of the transmission time to the network adapter, the time stamp in the
socket will be in reference to the clockid CLOCK_TAI and packets
will leave the qdisc "delta" (100000) nanoseconds before its transmission
time.

The ETF qdisc will buffer packets sorted by their txtime. It will drop
packets on enqueue() if their skbuff clockid does not match the clock
reference of the Qdisc. Moreover, on dequeue(), a packet will be dropped
if it expires while being enqueued.

The qdisc also supports the SO_TXTIME deadline mode. For this mode, it
will dequeue a packet as soon as possible and change the skb timestamp
to 'now' during etf_dequeue().

Note that both the qdisc's and the SO_TXTIME ABIs allow for a clockid
to be configured, but it's been decided that usage of CLOCK_TAI should
be enforced until we decide to allow for other clockids to be used.
The rationale here is that PTP times are usually in the TAI scale, thus
no other clocks should be necessary. For now, the qdisc will return
EINVAL if any clocks other than CLOCK_TAI are used.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h      |   1 +
 include/uapi/linux/pkt_sched.h |  17 ++
 net/sched/Kconfig              |  11 ++
 net/sched/Makefile             |   1 +
 net/sched/sch_etf.c            | 384 +++++++++++++++++++++++++++++++++++++++++
 5 files changed, 414 insertions(+)
 create mode 100644 net/sched/sch_etf.c

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c1ef749b6f9f..f06ee8f91e74 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -798,6 +798,7 @@ enum tc_setup_type {
 	TC_SETUP_QDISC_RED,
 	TC_SETUP_QDISC_PRIO,
 	TC_SETUP_QDISC_MQ,
+	TC_SETUP_QDISC_ETF,
 };
 
 /* These structures hold the attributes of bpf state that are being passed
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index bad3c03bcf43..d5e933ce1447 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -937,4 +937,21 @@ enum {
 
 #define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
 
+
+/* ETF */
+struct tc_etf_qopt {
+	__s32 delta;
+	__s32 clockid;
+	__u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON	BIT(0)
+};
+
+enum {
+	TCA_ETF_UNSPEC,
+	TCA_ETF_PARMS,
+	__TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index a01169fb5325..fcc89706745b 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -183,6 +183,17 @@ config NET_SCH_CBS
 	  To compile this code as a module, choose M here: the
 	  module will be called sch_cbs.
 
+config NET_SCH_ETF
+	tristate "Earliest TxTime First (ETF)"
+	help
+	  Say Y here if you want to use the Earliest TxTime First (ETF) packet
+	  scheduling algorithm.
+
+	  See the top of <file:net/sched/sch_etf.c> for more details.
+
+	  To compile this code as a module, choose M here: the
+	  module will be called sch_etf.
+
 config NET_SCH_GRED
 	tristate "Generic Random Early Detection (GRED)"
 	---help---
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 8811d3804878..9a5a7077d217 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -54,6 +54,7 @@ obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
 obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
 obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
 obj-$(CONFIG_NET_SCH_CBS)	+= sch_cbs.o
+obj-$(CONFIG_NET_SCH_ETF)	+= sch_etf.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
new file mode 100644
index 000000000000..4b7f4903ac17
--- /dev/null
+++ b/net/sched/sch_etf.c
@@ -0,0 +1,384 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* net/sched/sch_etf.c  Earliest TxTime First queueing discipline.
+ *
+ * Authors:	Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
+ *		Vinicius Costa Gomes <vinicius.gomes@intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/rbtree.h>
+#include <linux/skbuff.h>
+#include <linux/posix-timers.h>
+#include <net/netlink.h>
+#include <net/sch_generic.h>
+#include <net/pkt_sched.h>
+#include <net/sock.h>
+
+#define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
+
+struct etf_sched_data {
+	bool deadline_mode;
+	int clockid;
+	int queue;
+	s32 delta; /* in ns */
+	ktime_t last; /* The txtime of the last skb sent to the netdevice. */
+	struct rb_root head;
+	struct qdisc_watchdog watchdog;
+	ktime_t (*get_time)(void);
+};
+
+static const struct nla_policy etf_policy[TCA_ETF_MAX + 1] = {
+	[TCA_ETF_PARMS]	= { .len = sizeof(struct tc_etf_qopt) },
+};
+
+static inline int validate_input_params(struct tc_etf_qopt *qopt,
+					struct netlink_ext_ack *extack)
+{
+	/* Check if params comply to the following rules:
+	 *	* Clockid and delta must be valid.
+	 *
+	 *	* Dynamic clockids are not supported.
+	 *
+	 *	* Delta must be a positive integer.
+	 */
+	if (qopt->clockid < 0) {
+		NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
+		return -ENOTSUPP;
+	}
+
+	if (qopt->clockid != CLOCK_TAI) {
+		NL_SET_ERR_MSG(extack, "Invalid clockid. CLOCK_TAI must be used");
+		return -EINVAL;
+	}
+
+	if (qopt->delta < 0) {
+		NL_SET_ERR_MSG(extack, "Delta must be positive");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	ktime_t txtime = nskb->tstamp;
+	struct sock *sk = nskb->sk;
+	ktime_t now;
+
+	if (!sk)
+		return false;
+
+	if (!sock_flag(sk, SOCK_TXTIME))
+		return false;
+
+	/* We don't perform crosstimestamping.
+	 * Drop if packet's clockid differs from qdisc's.
+	 */
+	if (sk->sk_clockid != q->clockid)
+		return false;
+
+	if (sk->sk_txtime_deadline_mode != q->deadline_mode)
+		return false;
+
+	now = q->get_time();
+	if (ktime_before(txtime, now) || ktime_before(txtime, q->last))
+		return false;
+
+	return true;
+}
+
+static struct sk_buff *etf_peek_timesortedlist(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct rb_node *p;
+
+	p = rb_first(&q->head);
+	if (!p)
+		return NULL;
+
+	return rb_to_skb(p);
+}
+
+static void reset_watchdog(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb = etf_peek_timesortedlist(sch);
+	ktime_t next;
+
+	if (!skb)
+		return;
+
+	next = ktime_sub_ns(skb->tstamp, q->delta);
+	qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
+}
+
+static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
+				      struct sk_buff **to_free)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct rb_node **p = &q->head.rb_node, *parent = NULL;
+	ktime_t txtime = nskb->tstamp;
+
+	if (!is_packet_valid(sch, nskb))
+		return qdisc_drop(nskb, sch, to_free);
+
+	while (*p) {
+		struct sk_buff *skb;
+
+		parent = *p;
+		skb = rb_to_skb(parent);
+		if (ktime_after(txtime, skb->tstamp))
+			p = &parent->rb_right;
+		else
+			p = &parent->rb_left;
+	}
+	rb_link_node(&nskb->rbnode, parent, p);
+	rb_insert_color(&nskb->rbnode, &q->head);
+
+	qdisc_qstats_backlog_inc(sch, nskb);
+	sch->q.qlen++;
+
+	/* Now we may need to re-arm the qdisc watchdog for the next packet. */
+	reset_watchdog(sch);
+
+	return NET_XMIT_SUCCESS;
+}
+
+static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
+				 bool drop)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+
+	rb_erase(&skb->rbnode, &q->head);
+
+	/* The rbnode field in the skb re-uses these fields, now that
+	 * we are done with the rbnode, reset them.
+	 */
+	skb->next = NULL;
+	skb->prev = NULL;
+	skb->dev = qdisc_dev(sch);
+
+	qdisc_qstats_backlog_dec(sch, skb);
+
+	if (drop) {
+		struct sk_buff *to_free = NULL;
+
+		qdisc_drop(skb, sch, &to_free);
+		kfree_skb_list(to_free);
+		qdisc_qstats_overlimit(sch);
+	} else {
+		qdisc_bstats_update(sch, skb);
+
+		q->last = skb->tstamp;
+	}
+
+	sch->q.qlen--;
+}
+
+static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+	ktime_t now, next;
+
+	skb = etf_peek_timesortedlist(sch);
+	if (!skb)
+		return NULL;
+
+	now = q->get_time();
+
+	/* Drop if packet has expired while in queue. */
+	/* FIXME: Must return error on the socket's error queue */
+	if (ktime_before(skb->tstamp, now)) {
+		timesortedlist_erase(sch, skb, true);
+		skb = NULL;
+		goto out;
+	}
+
+	/* When in deadline mode, dequeue as soon as possible and change the
+	 * txtime from deadline to (now + delta).
+	 */
+	if (q->deadline_mode) {
+		timesortedlist_erase(sch, skb, false);
+		skb->tstamp = now;
+		goto out;
+	}
+
+	next = ktime_sub_ns(skb->tstamp, q->delta);
+
+	/* Dequeue only if now is within the [txtime - delta, txtime] range. */
+	if (ktime_after(now, next))
+		timesortedlist_erase(sch, skb, false);
+	else
+		skb = NULL;
+
+out:
+	/* Now we may need to re-arm the qdisc watchdog for the next packet. */
+	reset_watchdog(sch);
+
+	return skb;
+}
+
+static int etf_init(struct Qdisc *sch, struct nlattr *opt,
+		    struct netlink_ext_ack *extack)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	struct nlattr *tb[TCA_ETF_MAX + 1];
+	struct tc_etf_qopt *qopt;
+	int err;
+
+	if (!opt) {
+		NL_SET_ERR_MSG(extack,
+			       "Missing ETF qdisc options which are mandatory");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_ETF_MAX, opt, etf_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (!tb[TCA_ETF_PARMS]) {
+		NL_SET_ERR_MSG(extack, "Missing mandatory ETF parameters");
+		return -EINVAL;
+	}
+
+	qopt = nla_data(tb[TCA_ETF_PARMS]);
+
+	pr_debug("delta %d clockid %d deadline %s\n",
+		 qopt->delta, qopt->clockid,
+		 DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");
+
+	err = validate_input_params(qopt, extack);
+	if (err < 0)
+		return err;
+
+	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
+
+	/* Everything went OK, save the parameters used. */
+	q->delta = qopt->delta;
+	q->clockid = qopt->clockid;
+	q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);
+
+	switch (q->clockid) {
+	case CLOCK_REALTIME:
+		q->get_time = ktime_get_real;
+		break;
+	case CLOCK_MONOTONIC:
+		q->get_time = ktime_get;
+		break;
+	case CLOCK_BOOTTIME:
+		q->get_time = ktime_get_boottime;
+		break;
+	case CLOCK_TAI:
+		q->get_time = ktime_get_clocktai;
+		break;
+	default:
+		NL_SET_ERR_MSG(extack, "Clockid is not supported");
+		return -ENOTSUPP;
+	}
+
+	qdisc_watchdog_init_clockid(&q->watchdog, sch, q->clockid);
+
+	return 0;
+}
+
+static void timesortedlist_clear(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct rb_node *p = rb_first(&q->head);
+
+	while (p) {
+		struct sk_buff *skb = rb_to_skb(p);
+
+		p = rb_next(p);
+
+		rb_erase(&skb->rbnode, &q->head);
+		rtnl_kfree_skbs(skb, skb);
+		sch->q.qlen--;
+	}
+}
+
+static void etf_reset(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+
+	/* Only cancel watchdog if it's been initialized. */
+	if (q->watchdog.qdisc == sch)
+		qdisc_watchdog_cancel(&q->watchdog);
+
+	/* No matter which mode we are on, it's safe to clear both lists. */
+	timesortedlist_clear(sch);
+	__qdisc_reset_queue(&sch->q);
+
+	sch->qstats.backlog = 0;
+	sch->q.qlen = 0;
+
+	q->last = 0;
+}
+
+static void etf_destroy(struct Qdisc *sch)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+
+	/* Only cancel watchdog if it's been initialized. */
+	if (q->watchdog.qdisc == sch)
+		qdisc_watchdog_cancel(&q->watchdog);
+}
+
+static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct etf_sched_data *q = qdisc_priv(sch);
+	struct tc_etf_qopt opt = { };
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, TCA_OPTIONS);
+	if (!nest)
+		goto nla_put_failure;
+
+	opt.delta = q->delta;
+	opt.clockid = q->clockid;
+	if (q->deadline_mode)
+		opt.flags |= TC_ETF_DEADLINE_MODE_ON;
+
+	if (nla_put(skb, TCA_ETF_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, nest);
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -1;
+}
+
+static struct Qdisc_ops etf_qdisc_ops __read_mostly = {
+	.id		=	"etf",
+	.priv_size	=	sizeof(struct etf_sched_data),
+	.enqueue	=	etf_enqueue_timesortedlist,
+	.dequeue	=	etf_dequeue_timesortedlist,
+	.peek		=	etf_peek_timesortedlist,
+	.init		=	etf_init,
+	.reset		=	etf_reset,
+	.destroy	=	etf_destroy,
+	.dump		=	etf_dump,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init etf_module_init(void)
+{
+	return register_qdisc(&etf_qdisc_ops);
+}
+
+static void __exit etf_module_exit(void)
+{
+	unregister_qdisc(&etf_qdisc_ops);
+}
+module_init(etf_module_init)
+module_exit(etf_module_exit)
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 88cab77162e86e0f6a2b7e4f859c1435c4e24feb Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:54 -0700
Subject: net/sched: Add HW offloading capability to ETF

Add infra so etf qdisc supports HW offload of time-based transmission.

For hw offload, the time sorted list is still used, so packets are
dequeued always in order of txtime.

Example:

$ tc qdisc replace dev enp2s0 parent root handle 100 mqprio num_tc 3 \
           map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 0

$ tc qdisc add dev enp2s0 parent 100:1 etf offload delta 100000 \
	   clockid CLOCK_REALTIME

In this example, the Qdisc will use HW offload for the control of the
transmission time through the network adapter. The hrtimer used for
packets scheduling inside the qdisc will use the clockid CLOCK_REALTIME
as reference and packets leave the Qdisc "delta" (100000) nanoseconds
before their transmission time. Because this will be using HW offload and
since dynamic clocks are not supported by the hrtimer, the system clock
and the PHC clock must be synchronized for this mode to behave as
expected.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_sched.h        |  5 +++
 include/uapi/linux/pkt_sched.h |  1 +
 net/sched/sch_etf.c            | 71 +++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 76 insertions(+), 1 deletion(-)

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 2466ea143d01..7dc769e5452b 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -155,4 +155,9 @@ struct tc_cbs_qopt_offload {
 	s32 sendslope;
 };
 
+struct tc_etf_qopt_offload {
+	u8 enable;
+	s32 queue;
+};
+
 #endif
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index d5e933ce1447..949118461009 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -944,6 +944,7 @@ struct tc_etf_qopt {
 	__s32 clockid;
 	__u32 flags;
 #define TC_ETF_DEADLINE_MODE_ON	BIT(0)
+#define TC_ETF_OFFLOAD_ON	BIT(1)
 };
 
 enum {
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 4b7f4903ac17..932a136db568 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -20,8 +20,10 @@
 #include <net/sock.h>
 
 #define DEADLINE_MODE_IS_ON(x) ((x)->flags & TC_ETF_DEADLINE_MODE_ON)
+#define OFFLOAD_IS_ON(x) ((x)->flags & TC_ETF_OFFLOAD_ON)
 
 struct etf_sched_data {
+	bool offload;
 	bool deadline_mode;
 	int clockid;
 	int queue;
@@ -45,6 +47,9 @@ static inline int validate_input_params(struct tc_etf_qopt *qopt,
 	 *	* Dynamic clockids are not supported.
 	 *
 	 *	* Delta must be a positive integer.
+	 *
+	 * Also note that for the HW offload case, we must
+	 * expect that system clocks have been synchronized to PHC.
 	 */
 	if (qopt->clockid < 0) {
 		NL_SET_ERR_MSG(extack, "Dynamic clockids are not supported");
@@ -225,6 +230,56 @@ out:
 	return skb;
 }
 
+static void etf_disable_offload(struct net_device *dev,
+				struct etf_sched_data *q)
+{
+	struct tc_etf_qopt_offload etf = { };
+	const struct net_device_ops *ops;
+	int err;
+
+	if (!q->offload)
+		return;
+
+	ops = dev->netdev_ops;
+	if (!ops->ndo_setup_tc)
+		return;
+
+	etf.queue = q->queue;
+	etf.enable = 0;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+	if (err < 0)
+		pr_warn("Couldn't disable ETF offload for queue %d\n",
+			etf.queue);
+}
+
+static int etf_enable_offload(struct net_device *dev, struct etf_sched_data *q,
+			      struct netlink_ext_ack *extack)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	struct tc_etf_qopt_offload etf = { };
+	int err;
+
+	if (q->offload)
+		return 0;
+
+	if (!ops->ndo_setup_tc) {
+		NL_SET_ERR_MSG(extack, "Specified device does not support ETF offload");
+		return -EOPNOTSUPP;
+	}
+
+	etf.queue = q->queue;
+	etf.enable = 1;
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_ETF, &etf);
+	if (err < 0) {
+		NL_SET_ERR_MSG(extack, "Specified device failed to setup ETF hardware offload");
+		return err;
+	}
+
+	return 0;
+}
+
 static int etf_init(struct Qdisc *sch, struct nlattr *opt,
 		    struct netlink_ext_ack *extack)
 {
@@ -251,8 +306,9 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt,
 
 	qopt = nla_data(tb[TCA_ETF_PARMS]);
 
-	pr_debug("delta %d clockid %d deadline %s\n",
+	pr_debug("delta %d clockid %d offload %s deadline %s\n",
 		 qopt->delta, qopt->clockid,
+		 OFFLOAD_IS_ON(qopt) ? "on" : "off",
 		 DEADLINE_MODE_IS_ON(qopt) ? "on" : "off");
 
 	err = validate_input_params(qopt, extack);
@@ -261,9 +317,16 @@ static int etf_init(struct Qdisc *sch, struct nlattr *opt,
 
 	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
 
+	if (OFFLOAD_IS_ON(qopt)) {
+		err = etf_enable_offload(dev, q, extack);
+		if (err < 0)
+			return err;
+	}
+
 	/* Everything went OK, save the parameters used. */
 	q->delta = qopt->delta;
 	q->clockid = qopt->clockid;
+	q->offload = OFFLOAD_IS_ON(qopt);
 	q->deadline_mode = DEADLINE_MODE_IS_ON(qopt);
 
 	switch (q->clockid) {
@@ -326,10 +389,13 @@ static void etf_reset(struct Qdisc *sch)
 static void etf_destroy(struct Qdisc *sch)
 {
 	struct etf_sched_data *q = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
 
 	/* Only cancel watchdog if it's been initialized. */
 	if (q->watchdog.qdisc == sch)
 		qdisc_watchdog_cancel(&q->watchdog);
+
+	etf_disable_offload(dev, q);
 }
 
 static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -344,6 +410,9 @@ static int etf_dump(struct Qdisc *sch, struct sk_buff *skb)
 
 	opt.delta = q->delta;
 	opt.clockid = q->clockid;
+	if (q->offload)
+		opt.flags |= TC_ETF_OFFLOAD_ON;
+
 	if (q->deadline_mode)
 		opt.flags |= TC_ETF_DEADLINE_MODE_ON;
 
-- 
cgit v1.2.3


From 91db364236c8ae1af976d9794e5fec98e859dae7 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:55 -0700
Subject: igb: Refactor igb_configure_cbs()

Make this function retrieve what it needs from the Tx ring being
addressed since it already relies on what had been saved on it before.
Also, since this function will be used by the upcoming Launchtime
patches rename it to better reflect its intention. Note that
Launchtime is not part of what 802.1Qav specifies, but the i210
datasheet refers to this set of functionality as "Qav Transmission
Mode".

Here we also perform a tiny refactor at is_any_cbs_enabled(), and add
further documentation to igb_setup_tx_mode().

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 60 +++++++++++++++----------------
 1 file changed, 28 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f1e3397bd405..15f6b9c57ccf 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1655,23 +1655,17 @@ static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode)
 }
 
 /**
- *  igb_configure_cbs - Configure Credit-Based Shaper (CBS)
+ *  igb_config_tx_modes - Configure "Qav Tx mode" features on igb
  *  @adapter: pointer to adapter struct
  *  @queue: queue number
- *  @enable: true = enable CBS, false = disable CBS
- *  @idleslope: idleSlope in kbps
- *  @sendslope: sendSlope in kbps
- *  @hicredit: hiCredit in bytes
- *  @locredit: loCredit in bytes
  *
- *  Configure CBS for a given hardware queue. When disabling, idleslope,
- *  sendslope, hicredit, locredit arguments are ignored. Returns 0 if
- *  success. Negative otherwise.
+ *  Configure CBS for a given hardware queue. Parameters are retrieved
+ *  from the correct Tx ring, so igb_save_cbs_params() should be used
+ *  for setting those correctly prior to this function being called.
  **/
-static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
-			      bool enable, int idleslope, int sendslope,
-			      int hicredit, int locredit)
+static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 {
+	struct igb_ring *ring = adapter->tx_ring[queue];
 	struct net_device *netdev = adapter->netdev;
 	struct e1000_hw *hw = &adapter->hw;
 	u32 tqavcc;
@@ -1680,7 +1674,7 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 	WARN_ON(hw->mac.type != e1000_i210);
 	WARN_ON(queue < 0 || queue > 1);
 
-	if (enable || queue == 0) {
+	if (ring->cbs_enable || queue == 0) {
 		/* i210 does not allow the queue 0 to be in the Strict
 		 * Priority mode while the Qav mode is enabled, so,
 		 * instead of disabling strict priority mode, we give
@@ -1690,10 +1684,10 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 		 * Queue0 QueueMode must be set to 1b when
 		 * TransmitMode is set to Qav."
 		 */
-		if (queue == 0 && !enable) {
+		if (queue == 0 && !ring->cbs_enable) {
 			/* max "linkspeed" idleslope in kbps */
-			idleslope = 1000000;
-			hicredit = ETH_FRAME_LEN;
+			ring->idleslope = 1000000;
+			ring->hicredit = ETH_FRAME_LEN;
 		}
 
 		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
@@ -1756,14 +1750,15 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 		 *       calculated value, so the resulting bandwidth might
 		 *       be slightly higher for some configurations.
 		 */
-		value = DIV_ROUND_UP_ULL(idleslope * 61034ULL, 1000000);
+		value = DIV_ROUND_UP_ULL(ring->idleslope * 61034ULL, 1000000);
 
 		tqavcc = rd32(E1000_I210_TQAVCC(queue));
 		tqavcc &= ~E1000_TQAVCC_IDLESLOPE_MASK;
 		tqavcc |= value;
 		wr32(E1000_I210_TQAVCC(queue), tqavcc);
 
-		wr32(E1000_I210_TQAVHC(queue), 0x80000000 + hicredit * 0x7735);
+		wr32(E1000_I210_TQAVHC(queue),
+		     0x80000000 + ring->hicredit * 0x7735);
 	} else {
 		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
 		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
@@ -1783,8 +1778,9 @@ static void igb_configure_cbs(struct igb_adapter *adapter, int queue,
 	 */
 
 	netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
-		   (enable) ? "enabled" : "disabled", queue,
-		   idleslope, sendslope, hicredit, locredit);
+		   (ring->cbs_enable) ? "enabled" : "disabled", queue,
+		   ring->idleslope, ring->sendslope, ring->hicredit,
+		   ring->locredit);
 }
 
 static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
@@ -1809,19 +1805,25 @@ static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
 
 static bool is_any_cbs_enabled(struct igb_adapter *adapter)
 {
-	struct igb_ring *ring;
 	int i;
 
 	for (i = 0; i < adapter->num_tx_queues; i++) {
-		ring = adapter->tx_ring[i];
-
-		if (ring->cbs_enable)
+		if (adapter->tx_ring[i]->cbs_enable)
 			return true;
 	}
 
 	return false;
 }
 
+/**
+ *  igb_setup_tx_mode - Switch to/from Qav Tx mode when applicable
+ *  @adapter: pointer to adapter struct
+ *
+ *  Configure TQAVCTRL register switching the controller's Tx mode
+ *  if FQTSS mode is enabled or disabled. Additionally, will issue
+ *  a call to igb_config_tx_modes() per queue so any previously saved
+ *  Tx parameters are applied.
+ **/
 static void igb_setup_tx_mode(struct igb_adapter *adapter)
 {
 	struct net_device *netdev = adapter->netdev;
@@ -1881,11 +1883,7 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 			    adapter->num_tx_queues : I210_SR_QUEUES_NUM;
 
 		for (i = 0; i < max_queue; i++) {
-			struct igb_ring *ring = adapter->tx_ring[i];
-
-			igb_configure_cbs(adapter, i, ring->cbs_enable,
-					  ring->idleslope, ring->sendslope,
-					  ring->hicredit, ring->locredit);
+			igb_config_tx_modes(adapter, i);
 		}
 	} else {
 		wr32(E1000_RXPBS, I210_RXPBSIZE_DEFAULT);
@@ -2480,9 +2478,7 @@ static int igb_offload_cbs(struct igb_adapter *adapter,
 		return err;
 
 	if (is_fqtss_enabled(adapter)) {
-		igb_configure_cbs(adapter, qopt->queue, qopt->enable,
-				  qopt->idleslope, qopt->sendslope,
-				  qopt->hicredit, qopt->locredit);
+		igb_config_tx_modes(adapter, qopt->queue);
 
 		if (!is_any_cbs_enabled(adapter))
 			enable_fqtss(adapter, false);
-- 
cgit v1.2.3


From 0364a0d0e7a124e7c821cc536a95f7ef421349cb Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:56 -0700
Subject: igb: Only change Tx arbitration when CBS is on

Currently the data transmission arbitration algorithm - DataTranARB
field on TQAVCTRL reg - is always set to CBS when the Tx mode is
changed from legacy to 'Qav' mode.

Make that configuration a bit more granular in preparation for the
upcoming Launchtime enabling patches, since CBS and Launchtime can be
enabled separately. That is achieved by moving the DataTranARB setup
to igb_config_tx_modes() instead.

Similarly, when disabling CBS we must check if it has been disabled
for all queues, and clear the DataTranARB accordingly.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 49 +++++++++++++++++++++----------
 1 file changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 15f6b9c57ccf..8c90f1e51add 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1654,6 +1654,18 @@ static void set_queue_mode(struct e1000_hw *hw, int queue, enum queue_mode mode)
 	wr32(E1000_I210_TQAVCC(queue), val);
 }
 
+static bool is_any_cbs_enabled(struct igb_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		if (adapter->tx_ring[i]->cbs_enable)
+			return true;
+	}
+
+	return false;
+}
+
 /**
  *  igb_config_tx_modes - Configure "Qav Tx mode" features on igb
  *  @adapter: pointer to adapter struct
@@ -1668,7 +1680,7 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 	struct igb_ring *ring = adapter->tx_ring[queue];
 	struct net_device *netdev = adapter->netdev;
 	struct e1000_hw *hw = &adapter->hw;
-	u32 tqavcc;
+	u32 tqavcc, tqavctrl;
 	u16 value;
 
 	WARN_ON(hw->mac.type != e1000_i210);
@@ -1693,6 +1705,14 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
 		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
 
+		/* Always set data transfer arbitration to credit-based
+		 * shaper algorithm on TQAVCTRL if CBS is enabled for any of
+		 * the queues.
+		 */
+		tqavctrl = rd32(E1000_I210_TQAVCTRL);
+		tqavctrl |= E1000_TQAVCTRL_DATATRANARB;
+		wr32(E1000_I210_TQAVCTRL, tqavctrl);
+
 		/* According to i210 datasheet section 7.2.7.7, we should set
 		 * the 'idleSlope' field from TQAVCC register following the
 		 * equation:
@@ -1770,6 +1790,16 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 
 		/* Set hiCredit to zero. */
 		wr32(E1000_I210_TQAVHC(queue), 0);
+
+		/* If CBS is not enabled for any queues anymore, then return to
+		 * the default state of Data Transmission Arbitration on
+		 * TQAVCTRL.
+		 */
+		if (!is_any_cbs_enabled(adapter)) {
+			tqavctrl = rd32(E1000_I210_TQAVCTRL);
+			tqavctrl &= ~E1000_TQAVCTRL_DATATRANARB;
+			wr32(E1000_I210_TQAVCTRL, tqavctrl);
+		}
 	}
 
 	/* XXX: In i210 controller the sendSlope and loCredit parameters from
@@ -1803,18 +1833,6 @@ static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
 	return 0;
 }
 
-static bool is_any_cbs_enabled(struct igb_adapter *adapter)
-{
-	int i;
-
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		if (adapter->tx_ring[i]->cbs_enable)
-			return true;
-	}
-
-	return false;
-}
-
 /**
  *  igb_setup_tx_mode - Switch to/from Qav Tx mode when applicable
  *  @adapter: pointer to adapter struct
@@ -1838,11 +1856,10 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 		int i, max_queue;
 
 		/* Configure TQAVCTRL register: set transmit mode to 'Qav',
-		 * set data fetch arbitration to 'round robin' and set data
-		 * transfer arbitration to 'credit shaper algorithm.
+		 * set data fetch arbitration to 'round robin'.
 		 */
 		val = rd32(E1000_I210_TQAVCTRL);
-		val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_DATATRANARB;
+		val |= E1000_TQAVCTRL_XMIT_MODE;
 		val &= ~E1000_TQAVCTRL_DATAFETCHARB;
 		wr32(E1000_I210_TQAVCTRL, val);
 
-- 
cgit v1.2.3


From 8080e6ab4e99216f414c5c314264fd7cf3b6e4c1 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:57 -0700
Subject: igb: Refactor igb_offload_cbs()

Split code into a separate function (igb_offload_apply()) that will be
used by ETF offload implementation.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 23 ++++++++++++++---------
 1 file changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 8c90f1e51add..c30ab7b260cc 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -2474,6 +2474,19 @@ igb_features_check(struct sk_buff *skb, struct net_device *dev,
 	return features;
 }
 
+static void igb_offload_apply(struct igb_adapter *adapter, s32 queue)
+{
+	if (!is_fqtss_enabled(adapter)) {
+		enable_fqtss(adapter, true);
+		return;
+	}
+
+	igb_config_tx_modes(adapter, queue);
+
+	if (!is_any_cbs_enabled(adapter))
+		enable_fqtss(adapter, false);
+}
+
 static int igb_offload_cbs(struct igb_adapter *adapter,
 			   struct tc_cbs_qopt_offload *qopt)
 {
@@ -2494,15 +2507,7 @@ static int igb_offload_cbs(struct igb_adapter *adapter,
 	if (err)
 		return err;
 
-	if (is_fqtss_enabled(adapter)) {
-		igb_config_tx_modes(adapter, qopt->queue);
-
-		if (!is_any_cbs_enabled(adapter))
-			enable_fqtss(adapter, false);
-
-	} else {
-		enable_fqtss(adapter, true);
-	}
+	igb_offload_apply(adapter, qopt->queue);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 1b9231e7e148520a3ba63a604b27f11093f21bee Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:58 -0700
Subject: igb: Only call skb_tx_timestamp after descriptors are ready

Currently, skb_tx_timestamp() is being called before the Tx
descriptors are prepared in igb_xmit_frame_ring(), which happens
during either the igb_tso() or igb_tx_csum() calls.

Given that now the skb->tstamp might be used to carry the timestamp
for SO_TXTIME, we must only call skb_tx_timestamp() after the
information has been copied into the Tx descriptors.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index c30ab7b260cc..445da8285d9b 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6033,8 +6033,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 		}
 	}
 
-	skb_tx_timestamp(skb);
-
 	if (skb_vlan_tag_present(skb)) {
 		tx_flags |= IGB_TX_FLAGS_VLAN;
 		tx_flags |= (skb_vlan_tag_get(skb) << IGB_TX_FLAGS_VLAN_SHIFT);
@@ -6050,6 +6048,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	else if (!tso)
 		igb_tx_csum(tx_ring, first);
 
+	skb_tx_timestamp(skb);
+
 	if (igb_tx_map(tx_ring, first, hdr_len))
 		goto cleanup_tx_tstamp;
 
-- 
cgit v1.2.3


From 3048cf84d152344f874e993558770bba73a65c8f Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:42:59 -0700
Subject: igb: Add support for ETF offload

Implement HW offload support for SO_TXTIME through igb's Launchtime
feature. This is done by extending igb_setup_tc() so it supports
TC_SETUP_QDISC_ETF and configuring i210 so time based transmit
arbitration is enabled.

The FQTSS transmission mode added before is extended so strict
priority (SP) queues wait for stream reservation (SR) ones.
igb_config_tx_modes() is extended so it can support enabling/disabling
Launchtime following the previous approach used for the credit-based
shaper (CBS).

As the previous flow, FQTSS transmission mode is enabled automatically
by the driver once Launchtime (or CBS, as before) is enabled.
Similarly, it's automatically disabled when the feature is disabled
for the last queue that had it setup on.

The driver just consumes the transmit times from the skbuffs directly,
so no special handling is done in case an 'invalid' time is provided.
We assume this has been handled by the ETF qdisc already.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/e1000_defines.h |  16 +++
 drivers/net/ethernet/intel/igb/igb.h           |   1 +
 drivers/net/ethernet/intel/igb/igb_main.c      | 138 ++++++++++++++++++++++---
 3 files changed, 138 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h
index 252440a418dc..8a28f3388f69 100644
--- a/drivers/net/ethernet/intel/igb/e1000_defines.h
+++ b/drivers/net/ethernet/intel/igb/e1000_defines.h
@@ -1048,6 +1048,22 @@
 #define E1000_TQAVCTRL_XMIT_MODE	BIT(0)
 #define E1000_TQAVCTRL_DATAFETCHARB	BIT(4)
 #define E1000_TQAVCTRL_DATATRANARB	BIT(8)
+#define E1000_TQAVCTRL_DATATRANTIM	BIT(9)
+#define E1000_TQAVCTRL_SP_WAIT_SR	BIT(10)
+/* Fetch Time Delta - bits 31:16
+ *
+ * This field holds the value to be reduced from the launch time for
+ * fetch time decision. The FetchTimeDelta value is defined in 32 ns
+ * granularity.
+ *
+ * This field is 16 bits wide, and so the maximum value is:
+ *
+ * 65535 * 32 = 2097120 ~= 2.1 msec
+ *
+ * XXX: We are configuring the max value here since we couldn't come up
+ * with a reason for not doing so.
+ */
+#define E1000_TQAVCTRL_FETCHTIME_DELTA	(0xFFFF << 16)
 
 /* TX Qav Credit Control fields */
 #define E1000_TQAVCC_IDLESLOPE_MASK	0xFFFF
diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h
index 9643b5b3d444..ca54e268d157 100644
--- a/drivers/net/ethernet/intel/igb/igb.h
+++ b/drivers/net/ethernet/intel/igb/igb.h
@@ -262,6 +262,7 @@ struct igb_ring {
 	u16 count;			/* number of desc. in the ring */
 	u8 queue_index;			/* logical index of the ring*/
 	u8 reg_idx;			/* physical index of the ring */
+	bool launchtime_enable;		/* true if LaunchTime is enabled */
 	bool cbs_enable;		/* indicates if CBS is enabled */
 	s32 idleslope;			/* idleSlope in kbps */
 	s32 sendslope;			/* sendSlope in kbps */
diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 445da8285d9b..e3a0c02721c9 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1666,13 +1666,26 @@ static bool is_any_cbs_enabled(struct igb_adapter *adapter)
 	return false;
 }
 
+static bool is_any_txtime_enabled(struct igb_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		if (adapter->tx_ring[i]->launchtime_enable)
+			return true;
+	}
+
+	return false;
+}
+
 /**
  *  igb_config_tx_modes - Configure "Qav Tx mode" features on igb
  *  @adapter: pointer to adapter struct
  *  @queue: queue number
  *
- *  Configure CBS for a given hardware queue. Parameters are retrieved
- *  from the correct Tx ring, so igb_save_cbs_params() should be used
+ *  Configure CBS and Launchtime for a given hardware queue.
+ *  Parameters are retrieved from the correct Tx ring, so
+ *  igb_save_cbs_params() and igb_save_txtime_params() should be used
  *  for setting those correctly prior to this function being called.
  **/
 static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
@@ -1686,6 +1699,19 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 	WARN_ON(hw->mac.type != e1000_i210);
 	WARN_ON(queue < 0 || queue > 1);
 
+	/* If any of the Qav features is enabled, configure queues as SR and
+	 * with HIGH PRIO. If none is, then configure them with LOW PRIO and
+	 * as SP.
+	 */
+	if (ring->cbs_enable || ring->launchtime_enable) {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
+		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+	} else {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
+		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
+	}
+
+	/* If CBS is enabled, set DataTranARB and config its parameters. */
 	if (ring->cbs_enable || queue == 0) {
 		/* i210 does not allow the queue 0 to be in the Strict
 		 * Priority mode while the Qav mode is enabled, so,
@@ -1702,9 +1728,6 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 			ring->hicredit = ETH_FRAME_LEN;
 		}
 
-		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
-		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
-
 		/* Always set data transfer arbitration to credit-based
 		 * shaper algorithm on TQAVCTRL if CBS is enabled for any of
 		 * the queues.
@@ -1780,8 +1803,6 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 		wr32(E1000_I210_TQAVHC(queue),
 		     0x80000000 + ring->hicredit * 0x7735);
 	} else {
-		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
-		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
 
 		/* Set idleSlope to zero. */
 		tqavcc = rd32(E1000_I210_TQAVCC(queue));
@@ -1802,17 +1823,61 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 		}
 	}
 
+	/* If LaunchTime is enabled, set DataTranTIM. */
+	if (ring->launchtime_enable) {
+		/* Always set DataTranTIM on TQAVCTRL if LaunchTime is enabled
+		 * for any of the SR queues, and configure fetchtime delta.
+		 * XXX NOTE:
+		 *     - LaunchTime will be enabled for all SR queues.
+		 *     - A fixed offset can be added relative to the launch
+		 *       time of all packets if configured at reg LAUNCH_OS0.
+		 *       We are keeping it as 0 for now (default value).
+		 */
+		tqavctrl = rd32(E1000_I210_TQAVCTRL);
+		tqavctrl |= E1000_TQAVCTRL_DATATRANTIM |
+		       E1000_TQAVCTRL_FETCHTIME_DELTA;
+		wr32(E1000_I210_TQAVCTRL, tqavctrl);
+	} else {
+		/* If Launchtime is not enabled for any SR queues anymore,
+		 * then clear DataTranTIM on TQAVCTRL and clear fetchtime delta,
+		 * effectively disabling Launchtime.
+		 */
+		if (!is_any_txtime_enabled(adapter)) {
+			tqavctrl = rd32(E1000_I210_TQAVCTRL);
+			tqavctrl &= ~E1000_TQAVCTRL_DATATRANTIM;
+			tqavctrl &= ~E1000_TQAVCTRL_FETCHTIME_DELTA;
+			wr32(E1000_I210_TQAVCTRL, tqavctrl);
+		}
+	}
+
 	/* XXX: In i210 controller the sendSlope and loCredit parameters from
 	 * CBS are not configurable by software so we don't do any 'controller
 	 * configuration' in respect to these parameters.
 	 */
 
-	netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
-		   (ring->cbs_enable) ? "enabled" : "disabled", queue,
+	netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
+			    idleslope %d sendslope %d hiCredit %d \
+			    locredit %d\n",
+		   (ring->cbs_enable) ? "enabled" : "disabled",
+		   (ring->launchtime_enable) ? "enabled" : "disabled", queue,
 		   ring->idleslope, ring->sendslope, ring->hicredit,
 		   ring->locredit);
 }
 
+static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
+				  bool enable)
+{
+	struct igb_ring *ring;
+
+	if (queue < 0 || queue > adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[queue];
+	ring->launchtime_enable = enable;
+
+	return 0;
+}
+
 static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
 			       bool enable, int idleslope, int sendslope,
 			       int hicredit, int locredit)
@@ -1856,10 +1921,11 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 		int i, max_queue;
 
 		/* Configure TQAVCTRL register: set transmit mode to 'Qav',
-		 * set data fetch arbitration to 'round robin'.
+		 * set data fetch arbitration to 'round robin', set SP_WAIT_SR
+		 * so SP queues wait for SR ones.
 		 */
 		val = rd32(E1000_I210_TQAVCTRL);
-		val |= E1000_TQAVCTRL_XMIT_MODE;
+		val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_SP_WAIT_SR;
 		val &= ~E1000_TQAVCTRL_DATAFETCHARB;
 		wr32(E1000_I210_TQAVCTRL, val);
 
@@ -2483,7 +2549,7 @@ static void igb_offload_apply(struct igb_adapter *adapter, s32 queue)
 
 	igb_config_tx_modes(adapter, queue);
 
-	if (!is_any_cbs_enabled(adapter))
+	if (!is_any_cbs_enabled(adapter) && !is_any_txtime_enabled(adapter))
 		enable_fqtss(adapter, false);
 }
 
@@ -2756,6 +2822,29 @@ static int igb_setup_tc_block(struct igb_adapter *adapter,
 	}
 }
 
+static int igb_offload_txtime(struct igb_adapter *adapter,
+			      struct tc_etf_qopt_offload *qopt)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int err;
+
+	/* Launchtime offloading is only supported by i210 controller. */
+	if (hw->mac.type != e1000_i210)
+		return -EOPNOTSUPP;
+
+	/* Launchtime offloading is only supported by queues 0 and 1. */
+	if (qopt->queue < 0 || qopt->queue > 1)
+		return -EINVAL;
+
+	err = igb_save_txtime_params(adapter, qopt->queue, qopt->enable);
+	if (err)
+		return err;
+
+	igb_offload_apply(adapter, qopt->queue);
+
+	return 0;
+}
+
 static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			void *type_data)
 {
@@ -2766,6 +2855,8 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		return igb_offload_cbs(adapter, type_data);
 	case TC_SETUP_BLOCK:
 		return igb_setup_tc_block(adapter, type_data);
+	case TC_SETUP_QDISC_ETF:
+		return igb_offload_txtime(adapter, type_data);
 
 	default:
 		return -EOPNOTSUPP;
@@ -5586,11 +5677,14 @@ set_itr_now:
 	}
 }
 
-static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
-			    u32 type_tucmd, u32 mss_l4len_idx)
+static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
+			    struct igb_tx_buffer *first,
+			    u32 vlan_macip_lens, u32 type_tucmd,
+			    u32 mss_l4len_idx)
 {
 	struct e1000_adv_tx_context_desc *context_desc;
 	u16 i = tx_ring->next_to_use;
+	struct timespec64 ts;
 
 	context_desc = IGB_TX_CTXTDESC(tx_ring, i);
 
@@ -5605,9 +5699,18 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
 		mss_l4len_idx |= tx_ring->reg_idx << 4;
 
 	context_desc->vlan_macip_lens	= cpu_to_le32(vlan_macip_lens);
-	context_desc->seqnum_seed	= 0;
 	context_desc->type_tucmd_mlhl	= cpu_to_le32(type_tucmd);
 	context_desc->mss_l4len_idx	= cpu_to_le32(mss_l4len_idx);
+
+	/* We assume there is always a valid tx time available. Invalid times
+	 * should have been handled by the upper layers.
+	 */
+	if (tx_ring->launchtime_enable) {
+		ts = ns_to_timespec64(first->skb->tstamp);
+		context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
+	} else {
+		context_desc->seqnum_seed = 0;
+	}
 }
 
 static int igb_tso(struct igb_ring *tx_ring,
@@ -5690,7 +5793,8 @@ static int igb_tso(struct igb_ring *tx_ring,
 	vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
 
-	igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
+	igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens,
+			type_tucmd, mss_l4len_idx);
 
 	return 1;
 }
@@ -5745,7 +5849,7 @@ no_csum:
 	vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
 
-	igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, 0);
+	igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0);
 }
 
 #define IGB_SET_FLAG(_input, _flag, _result) \
-- 
cgit v1.2.3


From 4b15c7075352668d4467ced7594b676707d11cae Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Tue, 3 Jul 2018 15:43:00 -0700
Subject: net/sched: Make etf report drops on error_queue

Use the socket error queue for reporting dropped packets if the
socket has enabled that feature through the SO_TXTIME API.

Packets are dropped either on enqueue() if they aren't accepted by the
qdisc or on dequeue() if the system misses their deadline. Those are
reported as different errors so applications can react accordingly.

Userspace can retrieve the errors through the socket error queue and the
corresponding cmsg interfaces. A struct sock_extended_err* is used for
returning the error data, and the packet's timestamp can be retrieved by
adding both ee_data and ee_info fields as e.g.:

    ((__u64) serr->ee_data << 32) + serr->ee_info

This feature is disabled by default and must be explicitly enabled by
applications. Enabling it can bring some overhead for the Tx cycles
of the application.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h              |  3 ++-
 include/uapi/linux/errqueue.h   |  4 ++++
 include/uapi/linux/net_tstamp.h |  5 ++++-
 net/core/sock.c                 |  4 ++++
 net/sched/sch_etf.c             | 35 +++++++++++++++++++++++++++++++++--
 5 files changed, 47 insertions(+), 4 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 68347b9821c6..e0eac9ef44b5 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -481,7 +481,8 @@ struct sock {
 
 	u8			sk_clockid;
 	u8			sk_txtime_deadline_mode : 1,
-				sk_txtime_unused : 7;
+				sk_txtime_report_errors : 1,
+				sk_txtime_unused : 6;
 
 	struct socket		*sk_socket;
 	void			*sk_user_data;
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index dc64cfaf13da..c0151200f7d1 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -20,12 +20,16 @@ struct sock_extended_err {
 #define SO_EE_ORIGIN_ICMP6	3
 #define SO_EE_ORIGIN_TXSTATUS	4
 #define SO_EE_ORIGIN_ZEROCOPY	5
+#define SO_EE_ORIGIN_TXTIME	6
 #define SO_EE_ORIGIN_TIMESTAMPING SO_EE_ORIGIN_TXSTATUS
 
 #define SO_EE_OFFENDER(ee)	((struct sockaddr*)((ee)+1))
 
 #define SO_EE_CODE_ZEROCOPY_COPIED	1
 
+#define SO_EE_CODE_TXTIME_INVALID_PARAM	1
+#define SO_EE_CODE_TXTIME_MISSED	2
+
 /**
  *	struct scm_timestamping - timestamps exposed through cmsg
  *
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index c9a77c353b98..f8f4539f1135 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -147,8 +147,11 @@ struct scm_ts_pktinfo {
  */
 enum txtime_flags {
 	SOF_TXTIME_DEADLINE_MODE = (1 << 0),
+	SOF_TXTIME_REPORT_ERRORS = (1 << 1),
 
-	SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_DEADLINE_MODE)
+	SOF_TXTIME_FLAGS_LAST = SOF_TXTIME_REPORT_ERRORS,
+	SOF_TXTIME_FLAGS_MASK = (SOF_TXTIME_FLAGS_LAST - 1) |
+				 SOF_TXTIME_FLAGS_LAST
 };
 
 struct sock_txtime {
diff --git a/net/core/sock.c b/net/core/sock.c
index fe64b839f1b2..03fdea5b0f57 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1087,6 +1087,8 @@ set_rcvbuf:
 			sk->sk_clockid = sk_txtime.clockid;
 			sk->sk_txtime_deadline_mode =
 				!!(sk_txtime.flags & SOF_TXTIME_DEADLINE_MODE);
+			sk->sk_txtime_report_errors =
+				!!(sk_txtime.flags & SOF_TXTIME_REPORT_ERRORS);
 		}
 		break;
 
@@ -1429,6 +1431,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.txtime.clockid = sk->sk_clockid;
 		v.txtime.flags |= sk->sk_txtime_deadline_mode ?
 				  SOF_TXTIME_DEADLINE_MODE : 0;
+		v.txtime.flags |= sk->sk_txtime_report_errors ?
+				  SOF_TXTIME_REPORT_ERRORS : 0;
 		break;
 
 	default:
diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c
index 932a136db568..1538d6fa8165 100644
--- a/net/sched/sch_etf.c
+++ b/net/sched/sch_etf.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/errno.h>
+#include <linux/errqueue.h>
 #include <linux/rbtree.h>
 #include <linux/skbuff.h>
 #include <linux/posix-timers.h>
@@ -123,6 +124,32 @@ static void reset_watchdog(struct Qdisc *sch)
 	qdisc_watchdog_schedule_ns(&q->watchdog, ktime_to_ns(next));
 }
 
+static void report_sock_error(struct sk_buff *skb, u32 err, u8 code)
+{
+	struct sock_exterr_skb *serr;
+	struct sk_buff *clone;
+	ktime_t txtime = skb->tstamp;
+
+	if (!skb->sk || !(skb->sk->sk_txtime_report_errors))
+		return;
+
+	clone = skb_clone(skb, GFP_ATOMIC);
+	if (!clone)
+		return;
+
+	serr = SKB_EXT_ERR(clone);
+	serr->ee.ee_errno = err;
+	serr->ee.ee_origin = SO_EE_ORIGIN_TXTIME;
+	serr->ee.ee_type = 0;
+	serr->ee.ee_code = code;
+	serr->ee.ee_pad = 0;
+	serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */
+	serr->ee.ee_info = txtime; /* low part of tstamp */
+
+	if (sock_queue_err_skb(skb->sk, clone))
+		kfree_skb(clone);
+}
+
 static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 				      struct sk_buff **to_free)
 {
@@ -130,8 +157,11 @@ static int etf_enqueue_timesortedlist(struct sk_buff *nskb, struct Qdisc *sch,
 	struct rb_node **p = &q->head.rb_node, *parent = NULL;
 	ktime_t txtime = nskb->tstamp;
 
-	if (!is_packet_valid(sch, nskb))
+	if (!is_packet_valid(sch, nskb)) {
+		report_sock_error(nskb, EINVAL,
+				  SO_EE_CODE_TXTIME_INVALID_PARAM);
 		return qdisc_drop(nskb, sch, to_free);
+	}
 
 	while (*p) {
 		struct sk_buff *skb;
@@ -174,6 +204,8 @@ static void timesortedlist_erase(struct Qdisc *sch, struct sk_buff *skb,
 	if (drop) {
 		struct sk_buff *to_free = NULL;
 
+		report_sock_error(skb, ECANCELED, SO_EE_CODE_TXTIME_MISSED);
+
 		qdisc_drop(skb, sch, &to_free);
 		kfree_skb_list(to_free);
 		qdisc_qstats_overlimit(sch);
@@ -199,7 +231,6 @@ static struct sk_buff *etf_dequeue_timesortedlist(struct Qdisc *sch)
 	now = q->get_time();
 
 	/* Drop if packet has expired while in queue. */
-	/* FIXME: Must return error on the socket's error queue */
 	if (ktime_before(skb->tstamp, now)) {
 		timesortedlist_erase(sch, skb, true);
 		skb = NULL;
-- 
cgit v1.2.3


From 2a75364d09b05f257f4cd1f718e06e0247eb1dd3 Mon Sep 17 00:00:00 2001
From: Keiichi Watanabe <keiichiw@chromium.org>
Date: Mon, 18 Jun 2018 03:58:53 -0400
Subject: media: v4l2-ctrl: Add control for VP9 profile

Add a new control V4L2_CID_MPEG_VIDEO_VP9_PROFILE for VP9 profiles. This control
allows selecting the desired profile for VP9 encoder and querying for supported
profiles by VP9 encoder/decoder.

Though this control is similar to V4L2_CID_MPEG_VIDEO_VP8_PROFILE, we need to
separate this control from it because supported profiles usually differ between
VP8 and VP9.

Signed-off-by: Keiichi Watanabe <keiichiw@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/extended-controls.rst | 23 ++++++++++++++++++++++
 drivers/media/v4l2-core/v4l2-ctrls.c               | 11 +++++++++++
 include/uapi/linux/v4l2-controls.h                 |  7 +++++++
 3 files changed, 41 insertions(+)

diff --git a/Documentation/media/uapi/v4l/extended-controls.rst b/Documentation/media/uapi/v4l/extended-controls.rst
index 01ef31a934b4..9f7312bf3365 100644
--- a/Documentation/media/uapi/v4l/extended-controls.rst
+++ b/Documentation/media/uapi/v4l/extended-controls.rst
@@ -1978,6 +1978,29 @@ enum v4l2_mpeg_video_vp8_profile -
     * - ``V4L2_MPEG_VIDEO_VP8_PROFILE_3``
       - Profile 3
 
+.. _v4l2-mpeg-video-vp9-profile:
+
+``V4L2_CID_MPEG_VIDEO_VP9_PROFILE``
+    (enum)
+
+enum v4l2_mpeg_video_vp9_profile -
+    This control allows selecting the profile for VP9 encoder.
+    This is also used to enumerate supported profiles by VP9 encoder or decoder.
+    Possible values are:
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+
+    * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_0``
+      - Profile 0
+    * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_1``
+      - Profile 1
+    * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_2``
+      - Profile 2
+    * - ``V4L2_MPEG_VIDEO_VP9_PROFILE_3``
+      - Profile 3
+
 
 High Efficiency Video Coding (HEVC/H.265) Control Reference
 -----------------------------------------------------------
diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c
index 4a182a70de36..599c1cbff3b9 100644
--- a/drivers/media/v4l2-core/v4l2-ctrls.c
+++ b/drivers/media/v4l2-core/v4l2-ctrls.c
@@ -438,6 +438,13 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		"3",
 		NULL,
 	};
+	static const char * const vp9_profile[] = {
+		"0",
+		"1",
+		"2",
+		"3",
+		NULL,
+	};
 
 	static const char * const flash_led_mode[] = {
 		"Off",
@@ -623,6 +630,8 @@ const char * const *v4l2_ctrl_get_menu(u32 id)
 		return vpx_golden_frame_sel;
 	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
 		return vp8_profile;
+	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:
+		return vp9_profile;
 	case V4L2_CID_JPEG_CHROMA_SUBSAMPLING:
 		return jpeg_chroma_subsampling;
 	case V4L2_CID_DV_TX_MODE:
@@ -849,6 +858,7 @@ const char *v4l2_ctrl_get_name(u32 id)
 	case V4L2_CID_MPEG_VIDEO_VPX_I_FRAME_QP:		return "VPX I-Frame QP Value";
 	case V4L2_CID_MPEG_VIDEO_VPX_P_FRAME_QP:		return "VPX P-Frame QP Value";
 	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:			return "VP8 Profile";
+	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:			return "VP9 Profile";
 
 	/* HEVC controls */
 	case V4L2_CID_MPEG_VIDEO_HEVC_I_FRAME_QP:		return "HEVC I-Frame QP Value";
@@ -1190,6 +1200,7 @@ void v4l2_ctrl_fill(u32 id, const char **name, enum v4l2_ctrl_type *type,
 	case V4L2_CID_TUNE_DEEMPHASIS:
 	case V4L2_CID_MPEG_VIDEO_VPX_GOLDEN_FRAME_SEL:
 	case V4L2_CID_MPEG_VIDEO_VP8_PROFILE:
+	case V4L2_CID_MPEG_VIDEO_VP9_PROFILE:
 	case V4L2_CID_DETECT_MD_MODE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE:
 	case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL:
diff --git a/include/uapi/linux/v4l2-controls.h b/include/uapi/linux/v4l2-controls.h
index ab96795b2829..e4ee10ee917d 100644
--- a/include/uapi/linux/v4l2-controls.h
+++ b/include/uapi/linux/v4l2-controls.h
@@ -597,6 +597,13 @@ enum v4l2_mpeg_video_vp8_profile {
 };
 /* Deprecated alias for compatibility reasons. */
 #define V4L2_CID_MPEG_VIDEO_VPX_PROFILE	V4L2_CID_MPEG_VIDEO_VP8_PROFILE
+#define V4L2_CID_MPEG_VIDEO_VP9_PROFILE			(V4L2_CID_MPEG_BASE+512)
+enum v4l2_mpeg_video_vp9_profile {
+	V4L2_MPEG_VIDEO_VP9_PROFILE_0				= 0,
+	V4L2_MPEG_VIDEO_VP9_PROFILE_1				= 1,
+	V4L2_MPEG_VIDEO_VP9_PROFILE_2				= 2,
+	V4L2_MPEG_VIDEO_VP9_PROFILE_3				= 3,
+};
 
 /* CIDs for HEVC encoding. */
 
-- 
cgit v1.2.3


From d45c9dc0b8349d8005ed8f7bc82c4583f50dd357 Mon Sep 17 00:00:00 2001
From: Keiichi Watanabe <keiichiw@chromium.org>
Date: Mon, 18 Jun 2018 03:58:54 -0400
Subject: media: mtk-vcodec: Support VP9 profile in decoder

Add V4L2_CID_MPEG_VIDEO_VP9_PROFILE control in MediaTek decoder's
driver. MediaTek decoder only supports profile 0 for now.

Signed-off-by: Keiichi Watanabe <keiichiw@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
index 5523edadb86c..0c8a8b4c4e1c 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
@@ -1400,6 +1400,11 @@ int mtk_vcodec_dec_ctrls_setup(struct mtk_vcodec_ctx *ctx)
 				V4L2_CID_MIN_BUFFERS_FOR_CAPTURE,
 				0, 32, 1, 1);
 	ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
+	v4l2_ctrl_new_std_menu(&ctx->ctrl_hdl,
+				&mtk_vcodec_dec_ctrl_ops,
+				V4L2_CID_MPEG_VIDEO_VP9_PROFILE,
+				V4L2_MPEG_VIDEO_VP9_PROFILE_0,
+				0, V4L2_MPEG_VIDEO_VP9_PROFILE_0);
 
 	if (ctx->ctrl_hdl.error) {
 		mtk_v4l2_err("Adding control failed %d",
-- 
cgit v1.2.3


From c928d45475d7b07f1c1bdd68c327189289fcb3c2 Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name>
Date: Mon, 2 Jul 2018 17:23:21 -0400
Subject: media: ivtv: zero-initialize cx25840 platform data

We need to zero-initialize cx25840 platform data structure to make sure
that its future members do not contain random stack garbage.

Signed-off-by: Maciej S. Szmigiero <mail@maciej.szmigiero.name>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ivtv/ivtv-i2c.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/pci/ivtv/ivtv-i2c.c b/drivers/media/pci/ivtv/ivtv-i2c.c
index 522cd111e399..e9ce54dd5e01 100644
--- a/drivers/media/pci/ivtv/ivtv-i2c.c
+++ b/drivers/media/pci/ivtv/ivtv-i2c.c
@@ -293,6 +293,7 @@ int ivtv_i2c_register(struct ivtv *itv, unsigned idx)
 			.platform_data = &pdata,
 		};
 
+		memset(&pdata, 0, sizeof(pdata));
 		pdata.pvr150_workaround = itv->pvr150_workaround;
 		sd = v4l2_i2c_new_subdev_board(&itv->v4l2_dev, adap,
 				&cx25840_info, NULL);
-- 
cgit v1.2.3


From 9cd641ed31f576d08f7b784850ba93eef050f32f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 4 Jul 2018 14:46:27 +0200
Subject: ALSA: pcm: trace XRUN event at injection, too

The PCM xrun injection triggers directly snd_pcm_stop() without the
standard xrun handler, hence it's not recorded on the event buffer.
Ditto for snd_pcm_stop_xrun() call and SNDRV_PCM_IOCTL_XRUN ioctl.
They are inconvenient from the debugging POV.

Let's make them to trigger XRUN via the standard helper more
consistently.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/pcm.c        | 2 +-
 sound/core/pcm_lib.c    | 7 ++++---
 sound/core/pcm_local.h  | 2 ++
 sound/core/pcm_native.c | 8 ++++----
 4 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index c352bfb973cc..6f037a4b8b52 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -497,7 +497,7 @@ static void snd_pcm_xrun_injection_write(struct snd_info_entry *entry,
 	snd_pcm_stream_lock_irq(substream);
 	runtime = substream->runtime;
 	if (runtime && runtime->status->state == SNDRV_PCM_STATE_RUNNING)
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+		__snd_pcm_xrun(substream);
 	snd_pcm_stream_unlock_irq(substream);
 }
 
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 44b5ae833082..c1d2e8e1fc6b 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -153,7 +153,8 @@ EXPORT_SYMBOL(snd_pcm_debug_name);
 			dump_stack();				\
 	} while (0)
 
-static void xrun(struct snd_pcm_substream *substream)
+/* call with stream lock held */
+void __snd_pcm_xrun(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 
@@ -201,7 +202,7 @@ int snd_pcm_update_state(struct snd_pcm_substream *substream,
 		}
 	} else {
 		if (avail >= runtime->stop_threshold) {
-			xrun(substream);
+			__snd_pcm_xrun(substream);
 			return -EPIPE;
 		}
 	}
@@ -297,7 +298,7 @@ static int snd_pcm_update_hw_ptr0(struct snd_pcm_substream *substream,
 	}
 
 	if (pos == SNDRV_PCM_POS_XRUN) {
-		xrun(substream);
+		__snd_pcm_xrun(substream);
 		return -EPIPE;
 	}
 	if (pos >= runtime->buffer_size) {
diff --git a/sound/core/pcm_local.h b/sound/core/pcm_local.h
index 7a499d02df6c..c515612969a4 100644
--- a/sound/core/pcm_local.h
+++ b/sound/core/pcm_local.h
@@ -65,4 +65,6 @@ static inline void snd_pcm_timer_init(struct snd_pcm_substream *substream) {}
 static inline void snd_pcm_timer_done(struct snd_pcm_substream *substream) {}
 #endif
 
+void __snd_pcm_xrun(struct snd_pcm_substream *substream);
+
 #endif	/* __SOUND_CORE_PCM_LOCAL_H */
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index cecc79772c94..20174d0c0527 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1337,13 +1337,12 @@ int snd_pcm_drain_done(struct snd_pcm_substream *substream)
 int snd_pcm_stop_xrun(struct snd_pcm_substream *substream)
 {
 	unsigned long flags;
-	int ret = 0;
 
 	snd_pcm_stream_lock_irqsave(substream, flags);
 	if (snd_pcm_running(substream))
-		ret = snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+		__snd_pcm_xrun(substream);
 	snd_pcm_stream_unlock_irqrestore(substream, flags);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_pcm_stop_xrun);
 
@@ -1591,7 +1590,8 @@ static int snd_pcm_xrun(struct snd_pcm_substream *substream)
 		result = 0;	/* already there */
 		break;
 	case SNDRV_PCM_STATE_RUNNING:
-		result = snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+		__snd_pcm_xrun(substream);
+		result = 0;
 		break;
 	default:
 		result = -EBADFD;
-- 
cgit v1.2.3


From e647f5a5c5d165c87750e8c0dcbe341b5a378ffd Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 4 Jul 2018 15:08:05 +0200
Subject: ALSA: pcm: Use snd_pcm_stop_xrun() for xrun injection

Basically the xrun injection routine can simply call the standard
helper snd_pcm_stop_xrun(), but with one exception: it may be called
even when the stream is closed.

Make snd_pcm_stop_xrun() more robust and check the NULL runtime state,
and simplify xrun injection code by calling it.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/pcm.c        | 7 +------
 sound/core/pcm_native.c | 2 +-
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/sound/core/pcm.c b/sound/core/pcm.c
index 6f037a4b8b52..fdb9b92fc8d6 100644
--- a/sound/core/pcm.c
+++ b/sound/core/pcm.c
@@ -492,13 +492,8 @@ static void snd_pcm_xrun_injection_write(struct snd_info_entry *entry,
 					 struct snd_info_buffer *buffer)
 {
 	struct snd_pcm_substream *substream = entry->private_data;
-	struct snd_pcm_runtime *runtime;
 
-	snd_pcm_stream_lock_irq(substream);
-	runtime = substream->runtime;
-	if (runtime && runtime->status->state == SNDRV_PCM_STATE_RUNNING)
-		__snd_pcm_xrun(substream);
-	snd_pcm_stream_unlock_irq(substream);
+	snd_pcm_stop_xrun(substream);
 }
 
 static void snd_pcm_xrun_debug_read(struct snd_info_entry *entry,
diff --git a/sound/core/pcm_native.c b/sound/core/pcm_native.c
index 20174d0c0527..66c90f486af9 100644
--- a/sound/core/pcm_native.c
+++ b/sound/core/pcm_native.c
@@ -1339,7 +1339,7 @@ int snd_pcm_stop_xrun(struct snd_pcm_substream *substream)
 	unsigned long flags;
 
 	snd_pcm_stream_lock_irqsave(substream, flags);
-	if (snd_pcm_running(substream))
+	if (substream->runtime && snd_pcm_running(substream))
 		__snd_pcm_xrun(substream);
 	snd_pcm_stream_unlock_irqrestore(substream, flags);
 	return 0;
-- 
cgit v1.2.3


From af16d0a132af47c60494c373100ff8952d557b01 Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name>
Date: Mon, 2 Jul 2018 17:23:22 -0400
Subject: media: cx25840: add kernel-doc description of struct cx25840_state

This commit describes a device instance private data of the driver
(struct cx25840_state) in a kernel-doc style comment.

Signed-off-by: Maciej S. Szmigiero <mail@maciej.szmigiero.name>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/cx25840/cx25840-core.h | 33 ++++++++++++++++++++++++++++++--
 1 file changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/media/i2c/cx25840/cx25840-core.h b/drivers/media/i2c/cx25840/cx25840-core.h
index fb13a624d2e3..c323b1af1f83 100644
--- a/drivers/media/i2c/cx25840/cx25840-core.h
+++ b/drivers/media/i2c/cx25840/cx25840-core.h
@@ -45,6 +45,35 @@ enum cx25840_media_pads {
 	CX25840_NUM_PADS
 };
 
+/**
+ * struct cx25840_state - a device instance private data
+ * @c:			i2c_client struct representing this device
+ * @sd:		our V4L2 sub-device
+ * @hdl:		our V4L2 control handler
+ * @volume:		audio volume V4L2 control (non-cx2583x devices only)
+ * @mute:		audio mute V4L2 control (non-cx2583x devices only)
+ * @pvr150_workaround:	whether we enable workaround for Hauppauge PVR150
+ *			hardware bug (audio dropping out)
+ * @radio:		set if we are currently in the radio mode, otherwise
+ *			the current mode is non-radio (that is, video)
+ * @std:		currently set video standard
+ * @vid_input:		currently set video input
+ * @aud_input:		currently set audio input
+ * @audclk_freq:	currently set audio sample rate
+ * @audmode:		currently set audio mode (when in non-radio mode)
+ * @vbi_line_offset:	vbi line number offset
+ * @id:		exact device model
+ * @rev:		raw device id read from the chip
+ * @is_initialized:	whether we have already loaded firmware into the chip
+ *			and initialized it
+ * @vbi_regs_offset:	offset of vbi regs
+ * @fw_wait:		wait queue to wake an initalization function up when
+ *			firmware loading (on a separate workqueue) finishes
+ * @fw_work:		a work that actually loads the firmware on a separate
+ *			workqueue
+ * @ir_state:		a pointer to chip IR controller private data
+ * @pads:		array of supported chip pads (currently only a stub)
+ */
 struct cx25840_state {
 	struct i2c_client *c;
 	struct v4l2_subdev sd;
@@ -66,8 +95,8 @@ struct cx25840_state {
 	u32 rev;
 	int is_initialized;
 	unsigned vbi_regs_offset;
-	wait_queue_head_t fw_wait;    /* wake up when the fw load is finished */
-	struct work_struct fw_work;   /* work entry for fw load */
+	wait_queue_head_t fw_wait;
+	struct work_struct fw_work;
 	struct cx25840_ir_state *ir_state;
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	struct media_pad	pads[CX25840_NUM_PADS];
-- 
cgit v1.2.3


From 5c17a07cff792bc5ec2ae8a3577f1fcfd5668595 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 07:54:36 +0100
Subject: net: dsa: bcm_sf2: remove redundant variable off

Variable 'off' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'off' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index 02e8982519ce..ac96ff40d37e 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -220,7 +220,7 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 				 struct phy_device *phy)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
-	u32 off, reg;
+	u32 reg;
 
 	if (priv->wol_ports_mask & (1 << port))
 		return;
@@ -231,11 +231,6 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 	if (priv->int_phy_mask & 1 << port && priv->hw_params.num_gphy == 1)
 		bcm_sf2_gphy_enable_set(ds, false);
 
-	if (dsa_is_cpu_port(ds, port))
-		off = CORE_IMP_CTL;
-	else
-		off = CORE_G_PCTL_PORT(port);
-
 	b53_disable_port(ds, port, phy);
 
 	/* Power down the port memory */
-- 
cgit v1.2.3


From 3ff39a21640efd469c8b9d96e34d281deed0c6f6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:01:35 +0100
Subject: net: alteon: acenic: remove redundant pointer rxdesc

Pointer rxdesc is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'rxdesc' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/alteon/acenic.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 8f71b79b4949..08945baee48a 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -1933,7 +1933,7 @@ static void ace_rx_int(struct net_device *dev, u32 rxretprd, u32 rxretcsm)
 	while (idx != rxretprd) {
 		struct ring_info *rip;
 		struct sk_buff *skb;
-		struct rx_desc *rxdesc, *retdesc;
+		struct rx_desc *retdesc;
 		u32 skbidx;
 		int bd_flags, desc_type, mapsize;
 		u16 csum;
@@ -1959,19 +1959,16 @@ static void ace_rx_int(struct net_device *dev, u32 rxretprd, u32 rxretcsm)
 		case 0:
 			rip = &ap->skb->rx_std_skbuff[skbidx];
 			mapsize = ACE_STD_BUFSIZE;
-			rxdesc = &ap->rx_std_ring[skbidx];
 			std_count++;
 			break;
 		case BD_FLG_JUMBO:
 			rip = &ap->skb->rx_jumbo_skbuff[skbidx];
 			mapsize = ACE_JUMBO_BUFSIZE;
-			rxdesc = &ap->rx_jumbo_ring[skbidx];
 			atomic_dec(&ap->cur_jumbo_bufs);
 			break;
 		case BD_FLG_MINI:
 			rip = &ap->skb->rx_mini_skbuff[skbidx];
 			mapsize = ACE_MINI_BUFSIZE;
-			rxdesc = &ap->rx_mini_ring[skbidx];
 			mini_count++;
 			break;
 		default:
-- 
cgit v1.2.3


From 371b4fc33b2e32bd18fc139d2fb8b508ea66fe50 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:15:30 +0100
Subject: net: alx: remove redundant variable old_duplex

Variable old_duplex is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'old_duplex' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/atheros/alx/main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c
index 5e5022fa1d04..6d3221134927 100644
--- a/drivers/net/ethernet/atheros/alx/main.c
+++ b/drivers/net/ethernet/atheros/alx/main.c
@@ -1279,7 +1279,6 @@ static void alx_check_link(struct alx_priv *alx)
 	struct alx_hw *hw = &alx->hw;
 	unsigned long flags;
 	int old_speed;
-	u8 old_duplex;
 	int err;
 
 	/* clear PHY internal interrupt status, otherwise the main
@@ -1288,7 +1287,6 @@ static void alx_check_link(struct alx_priv *alx)
 	alx_clear_phy_intr(hw);
 
 	old_speed = hw->link_speed;
-	old_duplex = hw->duplex;
 	err = alx_read_phy_link(hw);
 	if (err < 0)
 		goto reset;
-- 
cgit v1.2.3


From 5b9f78ecdf590131aa1411b37151acda4f2ffc17 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:20:20 +0100
Subject: net: ethernet: nb8800: remove redundant pointer rxd

Pointer rxd is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'rxb' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aurora/nb8800.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c
index e94159507847..c8d1f8fa4713 100644
--- a/drivers/net/ethernet/aurora/nb8800.c
+++ b/drivers/net/ethernet/aurora/nb8800.c
@@ -304,12 +304,10 @@ static int nb8800_poll(struct napi_struct *napi, int budget)
 
 again:
 	do {
-		struct nb8800_rx_buf *rxb;
 		unsigned int len;
 
 		next = (last + 1) % RX_DESC_COUNT;
 
-		rxb = &priv->rx_bufs[next];
 		rxd = &priv->rx_descs[next];
 
 		if (!rxd->report)
-- 
cgit v1.2.3


From 15cdd5764a547caf7c9ab14306829135c616845d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:30:43 +0100
Subject: net: bgmac: remove redundant variable 'freed'

Variable 'freed' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'freed' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bgmac.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c
index e6ea8e61f96d..4c94d9218bba 100644
--- a/drivers/net/ethernet/broadcom/bgmac.c
+++ b/drivers/net/ethernet/broadcom/bgmac.c
@@ -236,7 +236,6 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 {
 	struct device *dma_dev = bgmac->dma_dev;
 	int empty_slot;
-	bool freed = false;
 	unsigned bytes_compl = 0, pkts_compl = 0;
 
 	/* The last slot that hardware didn't consume yet */
@@ -279,7 +278,6 @@ static void bgmac_dma_tx_free(struct bgmac *bgmac, struct bgmac_dma_ring *ring)
 
 		slot->dma_addr = 0;
 		ring->start++;
-		freed = true;
 	}
 
 	if (!pkts_compl)
-- 
cgit v1.2.3


From b68431ace4b60ac58fef92c0d70b61b3d2cba165 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:39:12 +0100
Subject: cnic: remove redundant pointer req and variable func

Pointer req and variable func are being assigned but are never used
hence they are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'req' set but not used [-Wunused-but-set-variable]
warning: variable 'func' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/cnic.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 4fd829b5e65d..2369b2f0d95a 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -2562,7 +2562,6 @@ static void cnic_bnx2x_delete_wait(struct cnic_dev *dev, u32 start_cid)
 
 static int cnic_bnx2x_fcoe_fw_destroy(struct cnic_dev *dev, struct kwqe *kwqe)
 {
-	struct fcoe_kwqe_destroy *req;
 	union l5cm_specific_data l5_data;
 	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
@@ -2571,7 +2570,6 @@ static int cnic_bnx2x_fcoe_fw_destroy(struct cnic_dev *dev, struct kwqe *kwqe)
 
 	cnic_bnx2x_delete_wait(dev, MAX_ISCSI_TBL_SZ);
 
-	req = (struct fcoe_kwqe_destroy *) kwqe;
 	cid = BNX2X_HW_CID(bp, cp->fcoe_init_cid);
 
 	memset(&l5_data, 0, sizeof(l5_data));
@@ -5091,13 +5089,12 @@ static int cnic_start_bnx2x_hw(struct cnic_dev *dev)
 	struct cnic_local *cp = dev->cnic_priv;
 	struct bnx2x *bp = netdev_priv(dev->netdev);
 	struct cnic_eth_dev *ethdev = cp->ethdev;
-	int func, ret;
+	int ret;
 	u32 pfid;
 
 	dev->stats_addr = ethdev->addr_drv_info_to_mcp;
 	cp->func = bp->pf_num;
 
-	func = CNIC_FUNC(cp);
 	pfid = bp->pfid;
 
 	ret = cnic_init_id_tbl(&cp->cid_tbl, MAX_ISCSI_TBL_SZ,
-- 
cgit v1.2.3


From f06bd2ed745cdca87ca398e27ef0bbbdf1089b05 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:49:43 +0100
Subject: net: fec: remove redundant variable 'inc'

Variable 'inc' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'inc' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_ptp.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 36c2d7d6ee1b..7e892b1cbd3d 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -99,7 +99,6 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 {
 	unsigned long flags;
 	u32 val, tempval;
-	int inc;
 	struct timespec64 ts;
 	u64 ns;
 	val = 0;
@@ -114,7 +113,6 @@ static int fec_ptp_enable_pps(struct fec_enet_private *fep, uint enable)
 
 	fep->pps_channel = DEFAULT_PPS_CHANNEL;
 	fep->reload_period = PPS_OUPUT_RELOAD_PERIOD;
-	inc = fep->ptp_inc;
 
 	spin_lock_irqsave(&fep->tmreg_lock, flags);
 
-- 
cgit v1.2.3


From 1d981f1dbe14ebf96fe1b2de58b72f60e897fb91 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:54:55 +0100
Subject: net: ethernet: gianfar_ethtool: remove redundant variable
 last_rule_idx

Variable last_rule_idx is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'last_rule_idx' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/gianfar_ethtool.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 8cb98cae0a6f..395a5266ea30 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -740,7 +740,6 @@ static void ethflow_to_filer_rules (struct gfar_private *priv, u64 ethflow)
 static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow,
 				       u64 class)
 {
-	unsigned int last_rule_idx = priv->cur_filer_idx;
 	unsigned int cmp_rqfpr;
 	unsigned int *local_rqfpr;
 	unsigned int *local_rqfcr;
@@ -819,7 +818,6 @@ static int gfar_ethflow_to_filer_table(struct gfar_private *priv, u64 ethflow,
 	}
 
 	priv->cur_filer_idx = l - 1;
-	last_rule_idx = l;
 
 	/* hash rules */
 	ethflow_to_filer_rules(priv, ethflow);
-- 
cgit v1.2.3


From 8c3689fcc5985c06a8d057cde82d59da8ebe29e2 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 08:59:25 +0100
Subject: net: hns3: remove redundant variable 'protocol'

Variable 'protocol' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'protocol' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 7e34d5fff3ae..f73c9dff46ff 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -885,7 +885,6 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 	u16 out_vtag = 0;
 	u32 paylen = 0;
 	u16 mss = 0;
-	__be16 protocol;
 	u8 ol4_proto;
 	u8 il4_proto;
 	int ret;
@@ -914,7 +913,6 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv,
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
 			skb_reset_mac_len(skb);
-			protocol = skb->protocol;
 
 			ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto);
 			if (ret)
-- 
cgit v1.2.3


From 541a1fecff3082664193c4615d2368186bd80dd5 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 09:06:27 +0100
Subject: net: hinic: remove redundant pointer pfhwdev

Pointer pfhwdev is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'pfhwdev' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
index 79b567447084..6b19607a4caa 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_dev.c
@@ -264,7 +264,6 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
 	struct hinic_hwif *hwif = hwdev->hwif;
 	struct pci_dev *pdev = hwif->pdev;
 	struct hinic_cmd_fw_ctxt fw_ctxt;
-	struct hinic_pfhwdev *pfhwdev;
 	u16 out_size;
 	int err;
 
@@ -276,8 +275,6 @@ static int init_fw_ctxt(struct hinic_hwdev *hwdev)
 	fw_ctxt.func_idx = HINIC_HWIF_FUNC_IDX(hwif);
 	fw_ctxt.rx_buf_sz = HINIC_RX_BUF_SZ;
 
-	pfhwdev = container_of(hwdev, struct hinic_pfhwdev, hwdev);
-
 	err = hinic_port_msg_cmd(hwdev, HINIC_PORT_CMD_FWCTXT_INIT,
 				 &fw_ctxt, sizeof(fw_ctxt),
 				 &fw_ctxt, &out_size);
-- 
cgit v1.2.3


From 5074298ab08bfc218ad8773ba270a6415a38468d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 12:20:44 +0100
Subject: ethernet: micrel: remove redundant pointer 'info'

Pointer 'info' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'info' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/micrel/ksz884x.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c
index b72d1bd11296..ebbdfb908745 100644
--- a/drivers/net/ethernet/micrel/ksz884x.c
+++ b/drivers/net/ethernet/micrel/ksz884x.c
@@ -3373,7 +3373,6 @@ static void port_get_link_speed(struct ksz_port *port)
  */
 static void port_set_link_speed(struct ksz_port *port)
 {
-	struct ksz_port_info *info;
 	struct ksz_hw *hw = port->hw;
 	u16 data;
 	u16 cfg;
@@ -3382,8 +3381,6 @@ static void port_set_link_speed(struct ksz_port *port)
 	int p;
 
 	for (i = 0, p = port->first_port; i < port->port_cnt; i++, p++) {
-		info = &hw->port_info[p];
-
 		port_r16(hw, p, KS884X_PORT_CTRL_4_OFFSET, &data);
 		port_r8(hw, p, KS884X_PORT_STATUS_OFFSET, &status);
 
-- 
cgit v1.2.3


From 9b0bb10a84ffbbbb9f589122e34ceee0194ea5ca Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 13:06:26 +0100
Subject: qed: remove redundant pointer 'name'

Pointer 'name' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'name' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index e0680ce91328..12b4c2ab5796 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -221,7 +221,6 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data,
 	struct qed_hw_info *p_info = &p_hwfn->hw_info;
 	enum qed_pci_personality personality;
 	enum dcbx_protocol_type id;
-	char *name;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(qed_dcbx_app_update); i++) {
@@ -231,7 +230,6 @@ qed_dcbx_update_app_info(struct qed_dcbx_results *p_data,
 			continue;
 
 		personality = qed_dcbx_app_update[i].personality;
-		name = qed_dcbx_app_update[i].name;
 
 		qed_dcbx_set_params(p_data, p_info, enable,
 				    prio, tc, type, personality);
-- 
cgit v1.2.3


From 2e6dde5c618f847fdb811373ad520cdb3a4425ab Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 13:13:01 +0100
Subject: sfc: remove redundant variable old_vlan

Variable old_vlan is being assigned but is never used hence it is
and can be removed.

Cleans up clang warning:
warning: variable 'old_vlan' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/ef10_sriov.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10_sriov.c b/drivers/net/ethernet/sfc/ef10_sriov.c
index 8820be83ce85..3d76fd1504c2 100644
--- a/drivers/net/ethernet/sfc/ef10_sriov.c
+++ b/drivers/net/ethernet/sfc/ef10_sriov.c
@@ -564,7 +564,7 @@ int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan,
 {
 	struct efx_ef10_nic_data *nic_data = efx->nic_data;
 	struct ef10_vf *vf;
-	u16 old_vlan, new_vlan;
+	u16 new_vlan;
 	int rc = 0, rc2 = 0;
 
 	if (vf_i >= efx->vf_count)
@@ -619,7 +619,6 @@ int efx_ef10_sriov_set_vf_vlan(struct efx_nic *efx, int vf_i, u16 vlan,
 	}
 
 	/* Do the actual vlan change */
-	old_vlan = vf->vlan;
 	vf->vlan = new_vlan;
 
 	/* Restore everything in reverse order */
-- 
cgit v1.2.3


From 211c41c8c46b5035b2a747a4d41627eef8261969 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 13:19:29 +0100
Subject: epic100: remove redundant variable 'irq'

Variable 'irq' is being assigned but is never used hence it is
and can be removed.

Cleans up clang warning:
warning: variable 'irq' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/smsc/epic100.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/smsc/epic100.c b/drivers/net/ethernet/smsc/epic100.c
index 949aaef390b6..15c62c160953 100644
--- a/drivers/net/ethernet/smsc/epic100.c
+++ b/drivers/net/ethernet/smsc/epic100.c
@@ -321,7 +321,6 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	static int card_idx = -1;
 	void __iomem *ioaddr;
 	int chip_idx = (int) ent->driver_data;
-	int irq;
 	struct net_device *dev;
 	struct epic_private *ep;
 	int i, ret, option = 0, duplex = 0;
@@ -338,7 +337,6 @@ static int epic_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	ret = pci_enable_device(pdev);
 	if (ret)
 		goto out;
-	irq = pdev->irq;
 
 	if (pci_resource_len(pdev, 0) < EPIC_TOTAL_SIZE) {
 		dev_err(&pdev->dev, "no PCI region space\n");
-- 
cgit v1.2.3


From 010b876ae9a05307c138cd591555fcd8a0a0bf14 Mon Sep 17 00:00:00 2001
From: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name>
Date: Mon, 2 Jul 2018 17:23:24 -0400
Subject: media: tuner-simple: allow setting mono radio mode

For some types of tuners (Philips FMD1216ME(X) MK3 currently) we know that
letting TDA9887 output port 1 remain high (inactive) will switch FM radio
to mono mode.
Let's make use of this functionality - nothing changes for the default
stereo radio mode.

Tested on a Medion 95700 board which has a FMD1216ME tuner.

Signed-off-by: Maciej S. Szmigiero <mail@maciej.szmigiero.name>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/tuners/tuner-simple.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/media/tuners/tuner-simple.c b/drivers/media/tuners/tuner-simple.c
index 36b88f820239..29c1473f2e9f 100644
--- a/drivers/media/tuners/tuner-simple.c
+++ b/drivers/media/tuners/tuner-simple.c
@@ -670,6 +670,7 @@ static int simple_set_radio_freq(struct dvb_frontend *fe,
 	int rc, j;
 	struct tuner_params *t_params;
 	unsigned int freq = params->frequency;
+	bool mono = params->audmode == V4L2_TUNER_MODE_MONO;
 
 	tun = priv->tun;
 
@@ -736,8 +737,8 @@ static int simple_set_radio_freq(struct dvb_frontend *fe,
 			config |= TDA9887_PORT2_ACTIVE;
 		if (t_params->intercarrier_mode)
 			config |= TDA9887_INTERCARRIER;
-/*		if (t_params->port1_set_for_fm_mono)
-			config &= ~TDA9887_PORT1_ACTIVE;*/
+		if (t_params->port1_set_for_fm_mono && mono)
+			config &= ~TDA9887_PORT1_ACTIVE;
 		if (t_params->fm_gain_normal)
 			config |= TDA9887_GAIN_NORMAL;
 		if (t_params->radio_if == 2)
-- 
cgit v1.2.3


From 110743189c863e96dc08a581d56c50b965870a3f Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 4 Jul 2018 10:49:43 +0100
Subject: ASoC: qdsp6: q6afe-dai: do not close port if its not opened

afe ports are open as part of prepare, so for use cases like
"aplay sample.wav" were sample.wav is not present. This would
call port close eventhough port was never opened. DSP would
return errors for such use cases.

Avoid doing this by checking the port state.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe-dai.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index 5002dd05bf27..a373ca5523ff 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -315,6 +315,9 @@ static void q6afe_dai_shutdown(struct snd_pcm_substream *substream,
 	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
 	int rc;
 
+	if (!dai_data->is_port_started[dai->id])
+		return;
+
 	rc = q6afe_port_stop(dai_data->port[dai->id]);
 	if (rc < 0)
 		dev_err(dai->dev, "fail to close AFE port (%d)\n", rc);
-- 
cgit v1.2.3


From 5dffc1752cabde6396fca28ff8343febfa524512 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 4 Jul 2018 10:49:44 +0100
Subject: ASoC: qdsp6: q6asm-dai: do not close port if its not opened

asm ports are open as part of prepare, so for use cases like
"aplay sample.wav" were sample.wav is not present. This would
call port close eventhough port was never opened. DSP would
return errors for such use cases.

Avoid doing this by checking the port state.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6asm-dai.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
index 349c6a883c63..360936703b3d 100644
--- a/sound/soc/qcom/qdsp6/q6asm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -390,7 +390,9 @@ static int q6asm_dai_close(struct snd_pcm_substream *substream)
 	struct q6asm_dai_rtd *prtd = runtime->private_data;
 
 	if (prtd->audio_client) {
-		q6asm_cmd(prtd->audio_client, CMD_CLOSE);
+		if (prtd->state)
+			q6asm_cmd(prtd->audio_client, CMD_CLOSE);
+
 		q6asm_unmap_memory_regions(substream->stream,
 					   prtd->audio_client);
 		q6asm_audio_client_free(prtd->audio_client);
-- 
cgit v1.2.3


From da13ed1d80fe6a4d95043aaf2e0aff292ade5708 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 09:28:28 -0500
Subject: ASoC: nau8825: use 64-bit arithmetic instead of 32-bit

Add suffix ULL to constant 256 in order to give the compiler complete
information about the proper arithmetic to use.

Notice that such constant is used in a context that expects an
expression of type u64 (64 bits, unsigned) and the following
expression is currently being evaluated using 32-bit arithmetic:

256 * fs * 2 * mclk_src_scaling[i].param

Addresses-Coverity-ID: 1339616 ("Unintentional integer overflow")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/nau8825.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/nau8825.c b/sound/soc/codecs/nau8825.c
index dc6ea4987b7d..b9fed99d8b5e 100644
--- a/sound/soc/codecs/nau8825.c
+++ b/sound/soc/codecs/nau8825.c
@@ -2016,7 +2016,7 @@ static int nau8825_calc_fll_param(unsigned int fll_in, unsigned int fs,
 	fvco_max = 0;
 	fvco_sel = ARRAY_SIZE(mclk_src_scaling);
 	for (i = 0; i < ARRAY_SIZE(mclk_src_scaling); i++) {
-		fvco = 256 * fs * 2 * mclk_src_scaling[i].param;
+		fvco = 256ULL * fs * 2 * mclk_src_scaling[i].param;
 		if (fvco > NAU_FVCO_MIN && fvco < NAU_FVCO_MAX &&
 			fvco_max < fvco) {
 			fvco_max = fvco;
-- 
cgit v1.2.3


From dae35d1f4f7dab9ccef20037df91c43e680bad0f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 4 Jul 2018 16:01:43 +0200
Subject: ASoC: davinci: Use snd_pcm_stop_xrun() helper

Replace open-codes with the standard snd_pcm_stop_xrun() helper.
It simplifies codes a lot.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/davinci/davinci-mcasp.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/sound/soc/davinci/davinci-mcasp.c b/sound/soc/davinci/davinci-mcasp.c
index 47c0c821d325..f70db8412c7c 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -320,12 +320,8 @@ static irqreturn_t davinci_mcasp_tx_irq_handler(int irq, void *data)
 		handled_mask |= XUNDRN;
 
 		substream = mcasp->substreams[SNDRV_PCM_STREAM_PLAYBACK];
-		if (substream) {
-			snd_pcm_stream_lock_irq(substream);
-			if (snd_pcm_running(substream))
-				snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-			snd_pcm_stream_unlock_irq(substream);
-		}
+		if (substream)
+			snd_pcm_stop_xrun(substream);
 	}
 
 	if (!handled_mask)
@@ -355,12 +351,8 @@ static irqreturn_t davinci_mcasp_rx_irq_handler(int irq, void *data)
 		handled_mask |= ROVRN;
 
 		substream = mcasp->substreams[SNDRV_PCM_STREAM_CAPTURE];
-		if (substream) {
-			snd_pcm_stream_lock_irq(substream);
-			if (snd_pcm_running(substream))
-				snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
-			snd_pcm_stream_unlock_irq(substream);
-		}
+		if (substream)
+			snd_pcm_stop_xrun(substream);
 	}
 
 	if (!handled_mask)
-- 
cgit v1.2.3


From 1a42e7e3aff1aa4789378020318dff7432317d25 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 4 Jul 2018 16:01:44 +0200
Subject: ASoC: qcom: Use snd_pcm_stop_xrun() helper

The XRUN trigger from the driver should be done via
snd_pcm_stop_xrun().  It fixes the missing stream locking as a gratis,
too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/lpass-platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/qcom/lpass-platform.c b/sound/soc/qcom/lpass-platform.c
index 31fe78aa207f..d07271ea4c45 100644
--- a/sound/soc/qcom/lpass-platform.c
+++ b/sound/soc/qcom/lpass-platform.c
@@ -458,7 +458,7 @@ static irqreturn_t lpass_dma_interrupt_handler(
 			return IRQ_NONE;
 		}
 		dev_warn(soc_runtime->dev, "xrun warning\n");
-		snd_pcm_stop(substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(substream);
 		ret = IRQ_HANDLED;
 	}
 
-- 
cgit v1.2.3


From dc865fb9e7c2251c9585ff6a7bf185d499db13e4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 4 Jul 2018 16:01:45 +0200
Subject: ASoC: sti: Use snd_pcm_stop_xrun() helper

The XRUN trigger from the driver should be done via
snd_pcm_stop_xrun().  It fixes the missing stream locking as a gratis,
too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sti/uniperif_player.c | 6 +++---
 sound/soc/sti/uniperif_reader.c | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
index d8b6936e544e..313dab2857ef 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -91,7 +91,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 			SET_UNIPERIF_ITM_BCLR_FIFO_ERROR(player);
 
 			/* Stop the player */
-			snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
+			snd_pcm_stop_xrun(player->substream);
 		}
 
 		ret = IRQ_HANDLED;
@@ -105,7 +105,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 		SET_UNIPERIF_ITM_BCLR_DMA_ERROR(player);
 
 		/* Stop the player */
-		snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(player->substream);
 
 		ret = IRQ_HANDLED;
 	}
@@ -138,7 +138,7 @@ static irqreturn_t uni_player_irq_handler(int irq, void *dev_id)
 		dev_err(player->dev, "Underflow recovery failed\n");
 
 		/* Stop the player */
-		snd_pcm_stop(player->substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(player->substream);
 
 		ret = IRQ_HANDLED;
 	}
diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
index ee0055e60852..7b63d35ef428 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -65,7 +65,7 @@ static irqreturn_t uni_reader_irq_handler(int irq, void *dev_id)
 	if (unlikely(status & UNIPERIF_ITS_FIFO_ERROR_MASK(reader))) {
 		dev_err(reader->dev, "FIFO error detected\n");
 
-		snd_pcm_stop(reader->substream, SNDRV_PCM_STATE_XRUN);
+		snd_pcm_stop_xrun(reader->substream);
 
 		ret = IRQ_HANDLED;
 	}
-- 
cgit v1.2.3


From b1625fbb3b87affbedf14545b65d69ff182a0611 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 4 Jul 2018 16:01:46 +0200
Subject: ASoC: stm32: Use snd_pcm_stop_xrun() helper

The XRUN trigger from the driver should be done via
snd_pcm_stop_xrun().  It simplifies the locking as well.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/stm/stm32_sai_sub.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/sound/soc/stm/stm32_sai_sub.c b/sound/soc/stm/stm32_sai_sub.c
index c4f15ea14197..06fba9650ac4 100644
--- a/sound/soc/stm/stm32_sai_sub.c
+++ b/sound/soc/stm/stm32_sai_sub.c
@@ -300,11 +300,8 @@ static irqreturn_t stm32_sai_isr(int irq, void *devid)
 		status = SNDRV_PCM_STATE_XRUN;
 	}
 
-	if (status != SNDRV_PCM_STATE_RUNNING) {
-		snd_pcm_stream_lock(sai->substream);
-		snd_pcm_stop(sai->substream, SNDRV_PCM_STATE_XRUN);
-		snd_pcm_stream_unlock(sai->substream);
-	}
+	if (status != SNDRV_PCM_STATE_RUNNING)
+		snd_pcm_stop_xrun(sai->substream);
 
 	return IRQ_HANDLED;
 }
-- 
cgit v1.2.3


From 25090bc3f36cc3c171ec020dcc89c71db6bd0a67 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 4 Jul 2018 10:49:39 +0100
Subject: ASoC: qdsp6: q6afe: Add missing slimbus capture ports

Existing code already has support for SLIMbus TX and RX, only thing
that was missing from TX side was mapping between virtual to actual
DSP port ids.

This patch adds those mappings.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6afe.c b/sound/soc/qcom/qdsp6/q6afe.c
index 671743453fbb..000775b4bba8 100644
--- a/sound/soc/qcom/qdsp6/q6afe.c
+++ b/sound/soc/qcom/qdsp6/q6afe.c
@@ -514,6 +514,20 @@ static struct afe_port_map port_maps[AFE_PORT_MAX] = {
 				SLIMBUS_5_RX, 1, 1},
 	[SLIMBUS_6_RX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_RX,
 				SLIMBUS_6_RX, 1, 1},
+	[SLIMBUS_0_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_TX,
+				SLIMBUS_0_TX, 0, 1},
+	[SLIMBUS_1_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_TX,
+				SLIMBUS_1_TX, 0, 1},
+	[SLIMBUS_2_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_TX,
+				SLIMBUS_2_TX, 0, 1},
+	[SLIMBUS_3_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_TX,
+				SLIMBUS_3_TX, 0, 1},
+	[SLIMBUS_4_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_TX,
+				SLIMBUS_4_TX, 0, 1},
+	[SLIMBUS_5_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_TX,
+				SLIMBUS_5_TX, 0, 1},
+	[SLIMBUS_6_TX] = { AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_TX,
+				SLIMBUS_6_TX, 0, 1},
 	[PRIMARY_MI2S_RX] = { AFE_PORT_ID_PRIMARY_MI2S_RX,
 				PRIMARY_MI2S_RX, 1, 1},
 	[PRIMARY_MI2S_TX] = { AFE_PORT_ID_PRIMARY_MI2S_TX,
@@ -1372,6 +1386,13 @@ struct q6afe_port *q6afe_port_get_from_id(struct device *dev, int id)
 	case AFE_PORT_ID_MULTICHAN_HDMI_RX:
 		cfg_type = AFE_PARAM_ID_HDMI_CONFIG;
 		break;
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_3_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_4_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_5_TX:
+	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_6_TX:
 	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_0_RX:
 	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_1_RX:
 	case AFE_PORT_ID_SLIMBUS_MULTI_CHAN_2_RX:
-- 
cgit v1.2.3


From f03d6b1b4d2460a749fb2826aa71e15a66104a88 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 4 Jul 2018 10:49:40 +0100
Subject: ASoC: qdsp6: q6afe-dai: add support to slim tx dais

This patch adds support to SLIMbus TX dais in AFE module.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe-dai.c | 175 +++++++++++++++++++++++++++++++++++----
 1 file changed, 161 insertions(+), 14 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index 1d2e5013c121..8dd3683eb367 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -382,23 +382,31 @@ static int q6slim_set_channel_map(struct snd_soc_dai *dai,
 	struct q6afe_port_config *pcfg = &dai_data->port_config[dai->id];
 	int i;
 
-	if (!rx_slot) {
-		pr_err("%s: rx slot not found\n", __func__);
-		return -EINVAL;
-	}
+	if (dai->id & 0x1) {
+		/* TX */
+		if (!tx_slot) {
+			pr_err("%s: tx slot not found\n", __func__);
+			return -EINVAL;
+		}
 
-	for (i = 0; i < rx_num; i++) {
-		pcfg->slim.ch_mapping[i] =   rx_slot[i];
-		pr_debug("%s: find number of channels[%d] ch[%d]\n",
-		       __func__, i, rx_slot[i]);
-	}
+		for (i = 0; i < tx_num; i++)
+			pcfg->slim.ch_mapping[i] = tx_slot[i];
+
+		pcfg->slim.num_channels = tx_num;
+
+
+	} else {
+		if (!rx_slot) {
+			pr_err("%s: rx slot not found\n", __func__);
+			return -EINVAL;
+		}
 
-	pcfg->slim.num_channels = rx_num;
+		for (i = 0; i < rx_num; i++)
+			pcfg->slim.ch_mapping[i] =   rx_slot[i];
 
-	pr_debug("%s: SLIMBUS_%d_RX cnt[%d] ch[%d %d]\n", __func__,
-		(dai->id - SLIMBUS_0_RX) / 2, rx_num,
-		pcfg->slim.ch_mapping[0],
-		pcfg->slim.ch_mapping[1]);
+		pcfg->slim.num_channels = rx_num;
+
+	}
 
 	return 0;
 }
@@ -443,6 +451,14 @@ static const struct snd_soc_dapm_route q6afe_dapm_routes[] = {
 	{"Slimbus5 Playback", NULL, "SLIMBUS_5_RX"},
 	{"Slimbus6 Playback", NULL, "SLIMBUS_6_RX"},
 
+	{"SLIMBUS_0_TX", NULL, "Slimbus Capture"},
+	{"SLIMBUS_1_TX", NULL, "Slimbus1 Capture"},
+	{"SLIMBUS_2_TX", NULL, "Slimbus2 Capture"},
+	{"SLIMBUS_3_TX", NULL, "Slimbus3 Capture"},
+	{"SLIMBUS_4_TX", NULL, "Slimbus4 Capture"},
+	{"SLIMBUS_5_TX", NULL, "Slimbus5 Capture"},
+	{"SLIMBUS_6_TX", NULL, "Slimbus6 Capture"},
+
 	{"Primary MI2S Playback", NULL, "PRI_MI2S_RX"},
 	{"Secondary MI2S Playback", NULL, "SEC_MI2S_RX"},
 	{"Tertiary MI2S Playback", NULL, "TERT_MI2S_RX"},
@@ -636,6 +652,24 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 			.rate_min = 8000,
 			.rate_max = 192000,
 		},
+	}, {
+		.name = "SLIMBUS_0_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_0_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus1 Playback",
@@ -654,6 +688,24 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_1_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+	}, {
+		.name = "SLIMBUS_1_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_1_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus1 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus2 Playback",
@@ -672,6 +724,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_2_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_2_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_2_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus2 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus3 Playback",
@@ -690,6 +761,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_3_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_3_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_3_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus3 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus4 Playback",
@@ -708,6 +798,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_4_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_4_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_4_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus4 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus5 Playback",
@@ -726,6 +835,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_5_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_5_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_5_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus5 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Slimbus6 Playback",
@@ -744,6 +872,25 @@ static struct snd_soc_dai_driver q6afe_dais[] = {
 		.id = SLIMBUS_6_RX,
 		.probe = msm_dai_q6_dai_probe,
 		.remove = msm_dai_q6_dai_remove,
+
+	}, {
+		.name = "SLIMBUS_6_TX",
+		.ops = &q6slim_ops,
+		.id = SLIMBUS_6_TX,
+		.probe = msm_dai_q6_dai_probe,
+		.remove = msm_dai_q6_dai_remove,
+		.capture = {
+			.stream_name = "Slimbus6 Capture",
+			.rates = SNDRV_PCM_RATE_48000 | SNDRV_PCM_RATE_8000 |
+				 SNDRV_PCM_RATE_16000 | SNDRV_PCM_RATE_96000 |
+				 SNDRV_PCM_RATE_192000,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE |
+				   SNDRV_PCM_FMTBIT_S24_LE,
+			.channels_min = 1,
+			.channels_max = 8,
+			.rate_min = 8000,
+			.rate_max = 192000,
+		},
 	}, {
 		.playback = {
 			.stream_name = "Primary MI2S Playback",
-- 
cgit v1.2.3


From 9191ffe2d212f64aa2ec311f4294ba7066d1f8a1 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 4 Jul 2018 10:49:41 +0100
Subject: ASoC: qdsp6: q6routing: add slim rx routings

This patch add routings mixer controls for slim rx ports.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6routing.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index c80fdbc2442e..35269b492761 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -68,6 +68,13 @@
 	{ mix_name, "SEC_MI2S_TX", "SEC_MI2S_TX" },	\
 	{ mix_name, "QUAT_MI2S_TX", "QUAT_MI2S_TX" },	\
 	{ mix_name, "TERT_MI2S_TX", "TERT_MI2S_TX" },		\
+	{ mix_name, "SLIMBUS_0_TX", "SLIMBUS_0_TX" },		\
+	{ mix_name, "SLIMBUS_1_TX", "SLIMBUS_1_TX" },		\
+	{ mix_name, "SLIMBUS_2_TX", "SLIMBUS_2_TX" },		\
+	{ mix_name, "SLIMBUS_3_TX", "SLIMBUS_3_TX" },		\
+	{ mix_name, "SLIMBUS_4_TX", "SLIMBUS_4_TX" },		\
+	{ mix_name, "SLIMBUS_5_TX", "SLIMBUS_5_TX" },		\
+	{ mix_name, "SLIMBUS_6_TX", "SLIMBUS_6_TX" },		\
 	{ mix_name, "PRIMARY_TDM_TX_0", "PRIMARY_TDM_TX_0"},	\
 	{ mix_name, "PRIMARY_TDM_TX_1", "PRIMARY_TDM_TX_1"},	\
 	{ mix_name, "PRIMARY_TDM_TX_2", "PRIMARY_TDM_TX_2"},	\
@@ -122,6 +129,27 @@
 	SOC_SINGLE_EXT("QUAT_MI2S_TX", QUATERNARY_MI2S_TX,		\
 		id, 1, 0, msm_routing_get_audio_mixer,			\
 		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_0_TX", SLIMBUS_0_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_1_TX", SLIMBUS_1_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_2_TX", SLIMBUS_2_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_3_TX", SLIMBUS_3_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_4_TX", SLIMBUS_4_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_5_TX", SLIMBUS_5_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
+	SOC_SINGLE_EXT("SLIMBUS_6_TX", SLIMBUS_6_TX,			\
+		id, 1, 0, msm_routing_get_audio_mixer,			\
+		msm_routing_put_audio_mixer),				\
 	SOC_SINGLE_EXT("PRIMARY_TDM_TX_0", PRIMARY_TDM_TX_0,		\
 		id, 1, 0, msm_routing_get_audio_mixer,			\
 		msm_routing_put_audio_mixer),				\
-- 
cgit v1.2.3


From f1478a1476d45c5d7b070c726f46a7b581d3103c Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Wed, 4 Jul 2018 10:49:42 +0100
Subject: ASoC: qdsp6: q6afe-dai: Do not overwrite slim dai num_channels

num_channels for slim dais are aready set int set_channel_map,
do not overwrite them in hw_params.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe-dai.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index 8dd3683eb367..074582afda85 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -81,7 +81,6 @@ static int q6slim_hw_params(struct snd_pcm_substream *substream,
 	struct q6afe_dai_data *dai_data = dev_get_drvdata(dai->dev);
 	struct q6afe_slim_cfg *slim = &dai_data->port_config[dai->id].slim;
 
-	slim->num_channels = params_channels(params);
 	slim->sample_rate = params_rate(params);
 
 	switch (params_format(params)) {
-- 
cgit v1.2.3


From b5cb15d9372abc9adc4e844c0c1bf594ca6a7695 Mon Sep 17 00:00:00 2001
From: Chris von Recklinghausen <crecklin@redhat.com>
Date: Tue, 3 Jul 2018 15:43:08 -0400
Subject: usercopy: Allow boot cmdline disabling of hardening

Enabling HARDENED_USERCOPY may cause measurable regressions in networking
performance: up to 8% under UDP flood.

I ran a small packet UDP flood using pktgen vs. a host b2b connected. On
the receiver side the UDP packets are processed by a simple user space
process that just reads and drops them:

https://github.com/netoptimizer/network-testing/blob/master/src/udp_sink.c

Not very useful from a functional PoV, but it helps to pin-point
bottlenecks in the networking stack.

When running a kernel with CONFIG_HARDENED_USERCOPY=y, I see a 5-8%
regression in the receive tput, compared to the same kernel without this
option enabled.

With CONFIG_HARDENED_USERCOPY=y, perf shows ~6% of CPU time spent
cumulatively in __check_object_size (~4%) and __virt_addr_valid (~2%).

The call-chain is:

__GI___libc_recvfrom
entry_SYSCALL_64_after_hwframe
do_syscall_64
__x64_sys_recvfrom
__sys_recvfrom
inet_recvmsg
udp_recvmsg
__check_object_size

udp_recvmsg() actually calls copy_to_iter() (inlined) and the latters
calls check_copy_size() (again, inlined).

A generic distro may want to enable HARDENED_USERCOPY in their default
kernel config, but at the same time, such distro may want to be able to
avoid the performance penalties in with the default configuration and
disable the stricter check on a per-boot basis.

This change adds a boot parameter that conditionally disables
HARDENED_USERCOPY via "hardened_usercopy=off".

Signed-off-by: Chris von Recklinghausen <crecklin@redhat.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 Documentation/admin-guide/kernel-parameters.txt | 11 +++++++++++
 include/linux/jump_label.h                      |  6 ++++++
 mm/usercopy.c                                   | 25 +++++++++++++++++++++++++
 3 files changed, 42 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..560d4dc66f02 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -816,6 +816,17 @@
 	disable=	[IPV6]
 			See Documentation/networking/ipv6.txt.
 
+	hardened_usercopy=
+                        [KNL] Under CONFIG_HARDENED_USERCOPY, whether
+                        hardening is enabled for this boot. Hardened
+                        usercopy checking is used to protect the kernel
+                        from reading or writing beyond known memory
+                        allocation boundaries as a proactive defense
+                        against bounds-checking flaws in the kernel's
+                        copy_to_user()/copy_from_user() interface.
+                on      Perform hardened usercopy checks (default).
+                off     Disable hardened usercopy checks.
+
 	disable_radix	[PPC]
 			Disable RADIX MMU mode on POWER9
 
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index b46b541c67c4..1a0b6f17a5d6 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -299,12 +299,18 @@ struct static_key_false {
 #define DEFINE_STATIC_KEY_TRUE(name)	\
 	struct static_key_true name = STATIC_KEY_TRUE_INIT
 
+#define DEFINE_STATIC_KEY_TRUE_RO(name)	\
+	struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT
+
 #define DECLARE_STATIC_KEY_TRUE(name)	\
 	extern struct static_key_true name
 
 #define DEFINE_STATIC_KEY_FALSE(name)	\
 	struct static_key_false name = STATIC_KEY_FALSE_INIT
 
+#define DEFINE_STATIC_KEY_FALSE_RO(name)	\
+	struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT
+
 #define DECLARE_STATIC_KEY_FALSE(name)	\
 	extern struct static_key_false name
 
diff --git a/mm/usercopy.c b/mm/usercopy.c
index e9e9325f7638..852eb4e53f06 100644
--- a/mm/usercopy.c
+++ b/mm/usercopy.c
@@ -20,6 +20,8 @@
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/thread_info.h>
+#include <linux/atomic.h>
+#include <linux/jump_label.h>
 #include <asm/sections.h>
 
 /*
@@ -240,6 +242,8 @@ static inline void check_heap_object(const void *ptr, unsigned long n,
 	}
 }
 
+static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks);
+
 /*
  * Validates that the given object is:
  * - not bogus address
@@ -248,6 +252,9 @@ static inline void check_heap_object(const void *ptr, unsigned long n,
  */
 void __check_object_size(const void *ptr, unsigned long n, bool to_user)
 {
+	if (static_branch_unlikely(&bypass_usercopy_checks))
+		return;
+
 	/* Skip all tests if size is zero. */
 	if (!n)
 		return;
@@ -279,3 +286,21 @@ void __check_object_size(const void *ptr, unsigned long n, bool to_user)
 	check_kernel_text_object((const unsigned long)ptr, n, to_user);
 }
 EXPORT_SYMBOL(__check_object_size);
+
+static bool enable_checks __initdata = true;
+
+static int __init parse_hardened_usercopy(char *str)
+{
+	return strtobool(str, &enable_checks);
+}
+
+__setup("hardened_usercopy=", parse_hardened_usercopy);
+
+static int __init set_hardened_usercopy(void)
+{
+	if (enable_checks == false)
+		static_branch_enable(&bypass_usercopy_checks);
+	return 1;
+}
+
+late_initcall(set_hardened_usercopy);
-- 
cgit v1.2.3


From 01f69dfafdbe7deff58b58053bc3a4a75c6a570c Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Sun, 24 Jun 2018 21:44:35 +0200
Subject: brcmfmac: detect firmware support for monitor interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Many/most of firmwares support creating monitor interface but only the
most recent ones explicitly /announce/ it using a "monitor" entry in the
list of capabilities.

Check for that entry and store internally info about monitor mode
support using a new feature flag. Once we sort out all details of
handling monitor interface it will be used when reporting available
interfaces to the cfg80211.

Later some fallback detecion method may be added for older firmwares.
For now just stick to the "monitor" capability which should be 100%
reliable.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c | 1 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index 800a423c7bc2..a78b9bae44e0 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -48,6 +48,7 @@ static const struct brcmf_feat_fwcap brcmf_fwcap_map[] = {
 	{ BRCMF_FEAT_MBSS, "mbss" },
 	{ BRCMF_FEAT_MCHAN, "mchan" },
 	{ BRCMF_FEAT_P2P, "p2p" },
+	{ BRCMF_FEAT_MONITOR, "monitor" },
 };
 
 #ifdef DEBUG
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
index d1193825e559..3415d5d4d6b5 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
@@ -33,6 +33,7 @@
  * MFP: 802.11w Management Frame Protection.
  * GSCAN: enhanced scan offload feature.
  * FWSUP: Firmware supplicant.
+ * MONITOR: firmware can pass monitor packets to host.
  */
 #define BRCMF_FEAT_LIST \
 	BRCMF_FEAT_DEF(MBSS) \
@@ -48,7 +49,8 @@
 	BRCMF_FEAT_DEF(WOWL_ARP_ND) \
 	BRCMF_FEAT_DEF(MFP) \
 	BRCMF_FEAT_DEF(GSCAN) \
-	BRCMF_FEAT_DEF(FWSUP)
+	BRCMF_FEAT_DEF(FWSUP) \
+	BRCMF_FEAT_DEF(MONITOR)
 
 /*
  * Quirks:
-- 
cgit v1.2.3


From e63410ac65e0ead2040bbd3927c116889edf87e4 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Sun, 24 Jun 2018 21:44:36 +0200
Subject: brcmfmac: detect firmware support for radiotap monitor frames
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Depending on used build-time options some firmwares may already include
radiotap header in passed monitor frames. Add a new feature flag to
store info about it. It's needed for proper handling of received frames
before passing them up.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c | 1 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h | 4 +++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index a78b9bae44e0..4db4d444407a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -49,6 +49,7 @@ static const struct brcmf_feat_fwcap brcmf_fwcap_map[] = {
 	{ BRCMF_FEAT_MCHAN, "mchan" },
 	{ BRCMF_FEAT_P2P, "p2p" },
 	{ BRCMF_FEAT_MONITOR, "monitor" },
+	{ BRCMF_FEAT_MONITOR_FMT_RADIOTAP, "rtap" },
 };
 
 #ifdef DEBUG
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
index 3415d5d4d6b5..0b4974df353a 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.h
@@ -34,6 +34,7 @@
  * GSCAN: enhanced scan offload feature.
  * FWSUP: Firmware supplicant.
  * MONITOR: firmware can pass monitor packets to host.
+ * MONITOR_FMT_RADIOTAP: firmware provides monitor packets with radiotap header
  */
 #define BRCMF_FEAT_LIST \
 	BRCMF_FEAT_DEF(MBSS) \
@@ -50,7 +51,8 @@
 	BRCMF_FEAT_DEF(MFP) \
 	BRCMF_FEAT_DEF(GSCAN) \
 	BRCMF_FEAT_DEF(FWSUP) \
-	BRCMF_FEAT_DEF(MONITOR)
+	BRCMF_FEAT_DEF(MONITOR) \
+	BRCMF_FEAT_DEF(MONITOR_FMT_RADIOTAP)
 
 /*
  * Quirks:
-- 
cgit v1.2.3


From a8d7631858aff156b72f807ee7cc062048e63836 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Sun, 24 Jun 2018 21:44:37 +0200
Subject: brcmfmac: handle msgbuf packets marked with monitor mode flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

New Broadcom firmwares mark monitor mode packets using a newly defined
bit in the flags field. Use it to filter them out and pass to the
monitor interface. These defines were found in bcmmsgbuf.h from SDK.

As not every firmware generates radiotap header this commit introduces
BRCMF_FEAT_MONITOR_FMT_RADIOTAP flag. It has to be has based on firmware
capabilities. If not present brcmf_netif_mon_rx() will assume packet is
a raw 802.11 frame and will prepend it with an empty radiotap header.

This new code is limited to the msgbuf protocol at this point. Adding
support for SDIO/USB devices will require some extra work (possibly a
new firmware release).

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/core.c    | 25 ++++++++++++++++++++++
 .../wireless/broadcom/brcm80211/brcmfmac/core.h    |  2 ++
 .../wireless/broadcom/brcm80211/brcmfmac/msgbuf.c  | 18 ++++++++++++++++
 3 files changed, 45 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
index 72954fd6df3b..b1f702faff4f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
@@ -21,6 +21,7 @@
 #include <net/cfg80211.h>
 #include <net/rtnetlink.h>
 #include <net/addrconf.h>
+#include <net/ieee80211_radiotap.h>
 #include <net/ipv6.h>
 #include <brcmu_utils.h>
 #include <brcmu_wifi.h>
@@ -404,6 +405,30 @@ void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb)
 		netif_rx_ni(skb);
 }
 
+void brcmf_netif_mon_rx(struct brcmf_if *ifp, struct sk_buff *skb)
+{
+	if (brcmf_feat_is_enabled(ifp, BRCMF_FEAT_MONITOR_FMT_RADIOTAP)) {
+		/* Do nothing */
+	} else {
+		struct ieee80211_radiotap_header *radiotap;
+
+		/* TODO: use RX status to fill some radiotap data */
+		radiotap = skb_push(skb, sizeof(*radiotap));
+		memset(radiotap, 0, sizeof(*radiotap));
+		radiotap->it_len = cpu_to_le16(sizeof(*radiotap));
+
+		/* TODO: 4 bytes with receive status? */
+		skb->len -= 4;
+	}
+
+	skb->dev = ifp->ndev;
+	skb_reset_mac_header(skb);
+	skb->pkt_type = PACKET_OTHERHOST;
+	skb->protocol = htons(ETH_P_802_2);
+
+	brcmf_netif_rx(ifp, skb);
+}
+
 static int brcmf_rx_hdrpull(struct brcmf_pub *drvr, struct sk_buff *skb,
 			    struct brcmf_if **ifp)
 {
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
index 401f50458686..dcf6e27cc16f 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.h
@@ -121,6 +121,7 @@ struct brcmf_pub {
 
 	struct brcmf_if *iflist[BRCMF_MAX_IFS];
 	s32 if2bss[BRCMF_MAX_IFS];
+	struct brcmf_if *mon_if;
 
 	struct mutex proto_block;
 	unsigned char proto_buf[BRCMF_DCMD_MAXLEN];
@@ -216,6 +217,7 @@ void brcmf_txflowblock_if(struct brcmf_if *ifp,
 			  enum brcmf_netif_stop_reason reason, bool state);
 void brcmf_txfinalize(struct brcmf_if *ifp, struct sk_buff *txp, bool success);
 void brcmf_netif_rx(struct brcmf_if *ifp, struct sk_buff *skb);
+void brcmf_netif_mon_rx(struct brcmf_if *ifp, struct sk_buff *skb);
 void brcmf_net_setcarrier(struct brcmf_if *ifp, bool on);
 int __init brcmf_core_init(void);
 void __exit brcmf_core_exit(void);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
index c40ba8855cd5..4e8397a0cbc8 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/msgbuf.c
@@ -69,6 +69,8 @@
 #define BRCMF_MSGBUF_MAX_EVENTBUF_POST		8
 
 #define BRCMF_MSGBUF_PKT_FLAGS_FRAME_802_3	0x01
+#define BRCMF_MSGBUF_PKT_FLAGS_FRAME_802_11	0x02
+#define BRCMF_MSGBUF_PKT_FLAGS_FRAME_MASK	0x07
 #define BRCMF_MSGBUF_PKT_FLAGS_PRIO_SHIFT	5
 
 #define BRCMF_MSGBUF_TX_FLUSH_CNT1		32
@@ -1128,6 +1130,7 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 	struct sk_buff *skb;
 	u16 data_offset;
 	u16 buflen;
+	u16 flags;
 	u32 idx;
 	struct brcmf_if *ifp;
 
@@ -1137,6 +1140,7 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 	data_offset = le16_to_cpu(rx_complete->data_offset);
 	buflen = le16_to_cpu(rx_complete->data_len);
 	idx = le32_to_cpu(rx_complete->msg.request_id);
+	flags = le16_to_cpu(rx_complete->flags);
 
 	skb = brcmf_msgbuf_get_pktid(msgbuf->drvr->bus_if->dev,
 				     msgbuf->rx_pktids, idx);
@@ -1150,6 +1154,20 @@ brcmf_msgbuf_process_rx_complete(struct brcmf_msgbuf *msgbuf, void *buf)
 
 	skb_trim(skb, buflen);
 
+	if ((flags & BRCMF_MSGBUF_PKT_FLAGS_FRAME_MASK) ==
+	    BRCMF_MSGBUF_PKT_FLAGS_FRAME_802_11) {
+		ifp = msgbuf->drvr->mon_if;
+
+		if (!ifp) {
+			brcmf_err("Received unexpected monitor pkt\n");
+			brcmu_pkt_buf_free_skb(skb);
+			return;
+		}
+
+		brcmf_netif_mon_rx(ifp, skb);
+		return;
+	}
+
 	ifp = brcmf_get_ifp(msgbuf->drvr, rx_complete->msg.ifidx);
 	if (!ifp || !ifp->ndev) {
 		brcmf_err("Received pkt for invalid ifidx %d\n",
-- 
cgit v1.2.3


From 4b4a8d808c58fc0defc32a26b2fea35d66692c45 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Thu, 28 Jun 2018 08:16:13 +0200
Subject: brcmfmac: define more bits for the flags of struct brcmf_sta_info_le
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

That struct is passed by a firmware when querying for STA info. Flags
are used to indicate what info could be obtained.

These new defines may allow passing more info to the cfg80211 in the
future. They had been obtained from Broadcom's SDK file wlioctl_defs.h
used by DD-WRT.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../broadcom/brcm80211/brcmfmac/fwil_types.h       | 29 ++++++++++++++++++----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
index 4b290705e3e6..9b3a58e89dd1 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
@@ -32,11 +32,30 @@
 #define	BRCMF_BSS_INFO_VERSION	109 /* curr ver of brcmf_bss_info_le struct */
 #define BRCMF_BSS_RSSI_ON_CHANNEL	0x0002
 
-#define BRCMF_STA_WME              0x00000002      /* WMM association */
-#define BRCMF_STA_AUTHE            0x00000008      /* Authenticated */
-#define BRCMF_STA_ASSOC            0x00000010      /* Associated */
-#define BRCMF_STA_AUTHO            0x00000020      /* Authorized */
-#define BRCMF_STA_SCBSTATS         0x00004000      /* Per STA debug stats */
+#define BRCMF_STA_BRCM			0x00000001	/* Running a Broadcom driver */
+#define BRCMF_STA_WME			0x00000002	/* WMM association */
+#define BRCMF_STA_NONERP		0x00000004	/* No ERP */
+#define BRCMF_STA_AUTHE			0x00000008	/* Authenticated */
+#define BRCMF_STA_ASSOC			0x00000010	/* Associated */
+#define BRCMF_STA_AUTHO			0x00000020	/* Authorized */
+#define BRCMF_STA_WDS			0x00000040	/* Wireless Distribution System */
+#define BRCMF_STA_WDS_LINKUP		0x00000080	/* WDS traffic/probes flowing properly */
+#define BRCMF_STA_PS			0x00000100	/* STA is in power save mode from AP's viewpoint */
+#define BRCMF_STA_APSD_BE		0x00000200	/* APSD delv/trigger for AC_BE is default enabled */
+#define BRCMF_STA_APSD_BK		0x00000400	/* APSD delv/trigger for AC_BK is default enabled */
+#define BRCMF_STA_APSD_VI		0x00000800	/* APSD delv/trigger for AC_VI is default enabled */
+#define BRCMF_STA_APSD_VO		0x00001000	/* APSD delv/trigger for AC_VO is default enabled */
+#define BRCMF_STA_N_CAP			0x00002000	/* STA 802.11n capable */
+#define BRCMF_STA_SCBSTATS		0x00004000	/* Per STA debug stats */
+#define BRCMF_STA_AMPDU_CAP		0x00008000	/* STA AMPDU capable */
+#define BRCMF_STA_AMSDU_CAP		0x00010000	/* STA AMSDU capable */
+#define BRCMF_STA_MIMO_PS		0x00020000	/* mimo ps mode is enabled */
+#define BRCMF_STA_MIMO_RTS		0x00040000	/* send rts in mimo ps mode */
+#define BRCMF_STA_RIFS_CAP		0x00080000	/* rifs enabled */
+#define BRCMF_STA_VHT_CAP		0x00100000	/* STA VHT(11ac) capable */
+#define BRCMF_STA_WPS			0x00200000	/* WPS state */
+#define BRCMF_STA_DWDS_CAP		0x01000000	/* DWDS CAP */
+#define BRCMF_STA_DWDS			0x02000000	/* DWDS active */
 
 /* size of brcmf_scan_params not including variable length array */
 #define BRCMF_SCAN_PARAMS_FIXED_SIZE	64
-- 
cgit v1.2.3


From 07b1ae46874949252625c96f309f96ca0f337020 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Thu, 28 Jun 2018 12:36:23 +0200
Subject: brcmfmac: update STA info struct to the v5
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

That struct is used when querying firmware for the STA. It seem is has
been changing during the time. Luckily its format seems to be backward
compatible starting with v2 (the only breakage was v1 -> v2).

The version that was supported by brcmfmac so far was v4. It was what
43602a1 and 4366b1 firmwares (7.35.177.56 and 10.10.69.3309 accordingly)
were using. It also seems to be used by early 4366c0 firmwares
(10.10.69.6908 and 10.10.69.69017).

The problem appears when switching to the 10.10.122.20 firmware. It uses
v5 and instead of falling back to v4 when submitted buffer isn't big
enough it fallbacks to the v3.

To receive all v4 specific info with the newest firmware we have to
submit a struct (buffer) that matches v5.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h  | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
index 9b3a58e89dd1..d5bb81e88762 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil_types.h
@@ -174,6 +174,8 @@
 #define BRCMF_MFP_CAPABLE		1
 #define BRCMF_MFP_REQUIRED		2
 
+#define BRCMF_VHT_CAP_MCS_MAP_NSS_MAX	8
+
 /* MAX_CHUNK_LEN is the maximum length for data passing to firmware in each
  * ioctl. It is relatively small because firmware has small maximum size input
  * playload restriction for ioctls.
@@ -550,6 +552,8 @@ struct brcmf_sta_info_le {
 						/* w/hi bit set if basic */
 	__le32 in;		/* seconds elapsed since associated */
 	__le32 listen_interval_inms; /* Min Listen interval in ms for STA */
+
+	/* Fields valid for ver >= 3 */
 	__le32 tx_pkts;	/* # of packets transmitted */
 	__le32 tx_failures;	/* # of packets failed */
 	__le32 rx_ucast_pkts;	/* # of unicast packets received */
@@ -558,6 +562,8 @@ struct brcmf_sta_info_le {
 	__le32 rx_rate;	/* Rate of last successful rx frame */
 	__le32 rx_decrypt_succeeds;	/* # of packet decrypted successfully */
 	__le32 rx_decrypt_failures;	/* # of packet decrypted failed */
+
+	/* Fields valid for ver >= 4 */
 	__le32 tx_tot_pkts;    /* # of tx pkts (ucast + mcast) */
 	__le32 rx_tot_pkts;    /* # of data packets recvd (uni + mcast) */
 	__le32 tx_mcast_pkts;  /* # of mcast pkts txed */
@@ -594,6 +600,14 @@ struct brcmf_sta_info_le {
 						*/
 	__le32 rx_pkts_retried;        /* # rx with retry bit set */
 	__le32 tx_rate_fallback;       /* lowest fallback TX rate */
+
+	/* Fields valid for ver >= 5 */
+	struct {
+		__le32 count;					/* # rates in this set */
+		u8 rates[BRCMF_MAXRATES_IN_SET];		/* rates in 500kbps units w/hi bit set if basic */
+		u8 mcs[BRCMF_MCSSET_LEN];			/* supported mcs index bit map */
+		__le16 vht_mcs[BRCMF_VHT_CAP_MCS_MAP_NSS_MAX];	/* supported mcs index bit map per nss */
+	} rateset_adv;
 };
 
 struct brcmf_chanspec_list {
-- 
cgit v1.2.3


From 7444a8092906ed44c09459780c56ba57043e39b1 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Wed, 27 Jun 2018 20:58:45 +0200
Subject: libertas: fix suspend and resume for SDIO connected cards

Prior to commit 573185cc7e64 ("mmc: core: Invoke sdio func driver's PM
callbacks from the sdio bus"), the MMC core used to call into the power
management functions of SDIO clients itself and removed the card if the
return code was non-zero. IOW, the mmc handled errors gracefully and didn't
upchain them to the pm core.

Since this change, the mmc core relies on generic power management
functions which treat all errors as a reason to cancel the suspend
immediately. This causes suspend attempts to fail when the libertas
driver is loaded.

To fix this, power down the card explicitly in if_sdio_suspend() when we
know we're about to lose power and return success. Also set a flag in these
cases, and power up the card again in if_sdio_resume().

Fixes: 573185cc7e64 ("mmc: core: Invoke sdio func driver's PM callbacks from the sdio bus")
Cc: <stable@vger.kernel.org>
Signed-off-by: Daniel Mack <daniel@zonque.org>
Reviewed-by: Chris Ball <chris@printf.net>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/libertas/dev.h     |  1 +
 drivers/net/wireless/marvell/libertas/if_sdio.c | 30 ++++++++++++++++++++-----
 2 files changed, 25 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/dev.h b/drivers/net/wireless/marvell/libertas/dev.h
index dd1ee1f0af48..469134930026 100644
--- a/drivers/net/wireless/marvell/libertas/dev.h
+++ b/drivers/net/wireless/marvell/libertas/dev.h
@@ -104,6 +104,7 @@ struct lbs_private {
 	u8 fw_ready;
 	u8 surpriseremoved;
 	u8 setup_fw_on_resume;
+	u8 power_up_on_resume;
 	int (*hw_host_to_card) (struct lbs_private *priv, u8 type, u8 *payload, u16 nb);
 	void (*reset_card) (struct lbs_private *priv);
 	int (*power_save) (struct lbs_private *priv);
diff --git a/drivers/net/wireless/marvell/libertas/if_sdio.c b/drivers/net/wireless/marvell/libertas/if_sdio.c
index 2300e796c6ab..43743c26c071 100644
--- a/drivers/net/wireless/marvell/libertas/if_sdio.c
+++ b/drivers/net/wireless/marvell/libertas/if_sdio.c
@@ -1290,15 +1290,23 @@ static void if_sdio_remove(struct sdio_func *func)
 static int if_sdio_suspend(struct device *dev)
 {
 	struct sdio_func *func = dev_to_sdio_func(dev);
-	int ret;
 	struct if_sdio_card *card = sdio_get_drvdata(func);
+	struct lbs_private *priv = card->priv;
+	int ret;
 
 	mmc_pm_flag_t flags = sdio_get_host_pm_caps(func);
+	priv->power_up_on_resume = false;
 
 	/* If we're powered off anyway, just let the mmc layer remove the
 	 * card. */
-	if (!lbs_iface_active(card->priv))
-		return -ENOSYS;
+	if (!lbs_iface_active(priv)) {
+		if (priv->fw_ready) {
+			priv->power_up_on_resume = true;
+			if_sdio_power_off(card);
+		}
+
+		return 0;
+	}
 
 	dev_info(dev, "%s: suspend: PM flags = 0x%x\n",
 		 sdio_func_id(func), flags);
@@ -1306,9 +1314,14 @@ static int if_sdio_suspend(struct device *dev)
 	/* If we aren't being asked to wake on anything, we should bail out
 	 * and let the SD stack power down the card.
 	 */
-	if (card->priv->wol_criteria == EHS_REMOVE_WAKEUP) {
+	if (priv->wol_criteria == EHS_REMOVE_WAKEUP) {
 		dev_info(dev, "Suspend without wake params -- powering down card\n");
-		return -ENOSYS;
+		if (priv->fw_ready) {
+			priv->power_up_on_resume = true;
+			if_sdio_power_off(card);
+		}
+
+		return 0;
 	}
 
 	if (!(flags & MMC_PM_KEEP_POWER)) {
@@ -1321,7 +1334,7 @@ static int if_sdio_suspend(struct device *dev)
 	if (ret)
 		return ret;
 
-	ret = lbs_suspend(card->priv);
+	ret = lbs_suspend(priv);
 	if (ret)
 		return ret;
 
@@ -1336,6 +1349,11 @@ static int if_sdio_resume(struct device *dev)
 
 	dev_info(dev, "%s: resume: we're back\n", sdio_func_id(func));
 
+	if (card->priv->power_up_on_resume) {
+		if_sdio_power_on(card);
+		wait_event(card->pwron_waitq, card->priv->fw_ready);
+	}
+
 	ret = lbs_resume(card->priv);
 
 	return ret;
-- 
cgit v1.2.3


From 04614fe46f315a223d96b8f5df7b52130965677b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 28 Jun 2018 08:08:09 -0500
Subject: wlcore: Fix memory leak in wlcore_cmd_wait_for_event_or_timeout

In case memory resources for *events_vector* were allocated, release
them before return.

Addresses-Coverity-ID: 1470194 ("Resource leak")
Fixes: 4ec7cece87b3 ("wlcore: Add missing PM call for wlcore_cmd_wait_for_event_or_timeout()")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/cmd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/cmd.c b/drivers/net/wireless/ti/wlcore/cmd.c
index 836c61663803..903968735a74 100644
--- a/drivers/net/wireless/ti/wlcore/cmd.c
+++ b/drivers/net/wireless/ti/wlcore/cmd.c
@@ -195,8 +195,7 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 	ret = pm_runtime_get_sync(wl->dev);
 	if (ret < 0) {
 		pm_runtime_put_noidle(wl->dev);
-
-		return ret;
+		goto free_vector;
 	}
 
 	do {
@@ -232,6 +231,7 @@ int wlcore_cmd_wait_for_event_or_timeout(struct wl1271 *wl,
 out:
 	pm_runtime_mark_last_busy(wl->dev);
 	pm_runtime_put_autosuspend(wl->dev);
+free_vector:
 	kfree(events_vector);
 	return ret;
 }
-- 
cgit v1.2.3


From f9cbaeb52930342059429f56d0b9f05c8d54c0ba Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 30 Jun 2018 14:33:41 +0800
Subject: atmel: using strlcpy() to avoid possible buffer overflows

'firmware' is a module param which may been longer than firmware_id,
so using strlcpy() to guard against overflows. Also priv is allocated
with zeroed memory,no need to set firmware_id[0] to '\0'.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/atmel/atmel.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index 0d8e0af3f74b..3ed3d9f6aae9 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -1516,10 +1516,9 @@ struct net_device *init_atmel_card(unsigned short irq, unsigned long port,
 	priv->present_callback = card_present;
 	priv->card = card;
 	priv->firmware = NULL;
-	priv->firmware_id[0] = '\0';
 	priv->firmware_type = fw_type;
 	if (firmware) /* module parameter */
-		strcpy(priv->firmware_id, firmware);
+		strlcpy(priv->firmware_id, firmware, sizeof(priv->firmware_id));
 	priv->bus_type = card_present ? BUS_TYPE_PCCARD : BUS_TYPE_PCI;
 	priv->station_state = STATION_STATE_DOWN;
 	priv->do_rx_crc = 0;
-- 
cgit v1.2.3


From ee8aa945e4ae94f2928ef1c2af340a655f16dfcc Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 29 Jun 2018 13:40:52 +0200
Subject: mt76: introduce mt76_{incr,decr} utility routines

Add mt76_{incr,decr} utility routines to increment/decrement a value
with wrap-around (they will be used by mt76x2 DFS sw detector)

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index d2166fbf50ff..96e9798bb8a0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -390,6 +390,18 @@ struct dentry *mt76_register_debugfs(struct mt76_dev *dev);
 int mt76_eeprom_init(struct mt76_dev *dev, int len);
 void mt76_eeprom_override(struct mt76_dev *dev);
 
+/* increment with wrap-around */
+static inline int mt76_incr(int val, int size)
+{
+	return (val + 1) & (size - 1);
+}
+
+/* decrement with wrap-around */
+static inline int mt76_decr(int val, int size)
+{
+	return (val - 1) & (size - 1);
+}
+
 static inline struct ieee80211_txq *
 mtxq_to_txq(struct mt76_txq *mtxq)
 {
-- 
cgit v1.2.3


From 1fc9bc9ab501cf31119e959379f158280f2a8ea1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 29 Jun 2018 13:40:53 +0200
Subject: mt76x2: dfs: add sw event ring buffer

Introduce sw event ring buffer to queue DFS pulses loaded from the hw.
Radar pulses will be used in DFS sw detector

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c | 139 +++++++++++++++++++++++-
 drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h |  27 +++++
 2 files changed, 163 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
index f936dc9a5476..606202fe1851 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
@@ -159,6 +159,21 @@ static void mt76x2_dfs_set_capture_mode_ctrl(struct mt76x2_dev *dev,
 	mt76_wr(dev, MT_BBP(DFS, 36), data);
 }
 
+static void mt76x2_dfs_detector_reset(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	int i;
+
+	/* reset hw detector */
+	mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+
+	/* reset sw detector */
+	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
+		dfs_pd->event_rb[i].h_rb = 0;
+		dfs_pd->event_rb[i].t_rb = 0;
+	}
+}
+
 static bool mt76x2_dfs_check_chirp(struct mt76x2_dev *dev)
 {
 	bool ret = false;
@@ -295,6 +310,117 @@ static bool mt76x2_dfs_check_hw_pulse(struct mt76x2_dev *dev,
 	return ret;
 }
 
+static bool mt76x2_dfs_fetch_event(struct mt76x2_dev *dev,
+				   struct mt76x2_dfs_event *event)
+{
+	u32 data;
+
+	/* 1st: DFS_R37[31]: 0 (engine 0) - 1 (engine 2)
+	 * 2nd: DFS_R37[21:0]: pulse time
+	 * 3rd: DFS_R37[11:0]: pulse width
+	 * 3rd: DFS_R37[25:16]: phase
+	 * 4th: DFS_R37[12:0]: current pwr
+	 * 4th: DFS_R37[21:16]: pwr stable counter
+	 *
+	 * 1st: DFS_R37[31:0] set to 0xffffffff means no event detected
+	 */
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	if (!MT_DFS_CHECK_EVENT(data))
+		return false;
+
+	event->engine = MT_DFS_EVENT_ENGINE(data);
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	event->ts = MT_DFS_EVENT_TIMESTAMP(data);
+	data = mt76_rr(dev, MT_BBP(DFS, 37));
+	event->width = MT_DFS_EVENT_WIDTH(data);
+
+	return true;
+}
+
+static bool mt76x2_dfs_check_event(struct mt76x2_dev *dev,
+				   struct mt76x2_dfs_event *event)
+{
+	if (event->engine == 2) {
+		struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+		struct mt76x2_dfs_event_rb *event_buff = &dfs_pd->event_rb[1];
+		u16 last_event_idx;
+		u32 delta_ts;
+
+		last_event_idx = mt76_decr(event_buff->t_rb,
+					   MT_DFS_EVENT_BUFLEN);
+		delta_ts = event->ts - event_buff->data[last_event_idx].ts;
+		if (delta_ts < MT_DFS_EVENT_TIME_MARGIN &&
+		    event_buff->data[last_event_idx].width >= 200)
+			return false;
+	}
+	return true;
+}
+
+static void mt76x2_dfs_queue_event(struct mt76x2_dev *dev,
+				   struct mt76x2_dfs_event *event)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_event_rb *event_buff;
+
+	/* add radar event to ring buffer */
+	event_buff = event->engine == 2 ? &dfs_pd->event_rb[1]
+					: &dfs_pd->event_rb[0];
+	event_buff->data[event_buff->t_rb] = *event;
+	event_buff->data[event_buff->t_rb].fetch_ts = jiffies;
+
+	event_buff->t_rb = mt76_incr(event_buff->t_rb, MT_DFS_EVENT_BUFLEN);
+	if (event_buff->t_rb == event_buff->h_rb)
+		event_buff->h_rb = mt76_incr(event_buff->h_rb,
+					     MT_DFS_EVENT_BUFLEN);
+}
+
+static void mt76x2_dfs_add_events(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_event event;
+	int i;
+
+	/* disable debug mode */
+	mt76x2_dfs_set_capture_mode_ctrl(dev, false);
+	for (i = 0; i < MT_DFS_EVENT_LOOP; i++) {
+		if (!mt76x2_dfs_fetch_event(dev, &event))
+			break;
+
+		if (dfs_pd->last_event_ts > event.ts)
+			mt76x2_dfs_detector_reset(dev);
+		dfs_pd->last_event_ts = event.ts;
+
+		if (!mt76x2_dfs_check_event(dev, &event))
+			continue;
+
+		mt76x2_dfs_queue_event(dev, &event);
+	}
+	mt76x2_dfs_set_capture_mode_ctrl(dev, true);
+}
+
+static void mt76x2_dfs_check_event_window(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_event_rb *event_buff;
+	struct mt76x2_dfs_event *event;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dfs_pd->event_rb); i++) {
+		event_buff = &dfs_pd->event_rb[i];
+
+		while (event_buff->h_rb != event_buff->t_rb) {
+			event = &event_buff->data[event_buff->h_rb];
+
+			/* sorted list */
+			if (time_is_after_jiffies(event->fetch_ts +
+						  MT_DFS_EVENT_WINDOW))
+				break;
+			event_buff->h_rb = mt76_incr(event_buff->h_rb,
+						     MT_DFS_EVENT_BUFLEN);
+		}
+	}
+}
+
 static void mt76x2_dfs_tasklet(unsigned long arg)
 {
 	struct mt76x2_dev *dev = (struct mt76x2_dev *)arg;
@@ -305,6 +431,14 @@ static void mt76x2_dfs_tasklet(unsigned long arg)
 	if (test_bit(MT76_SCANNING, &dev->mt76.state))
 		goto out;
 
+	if (time_is_before_jiffies(dfs_pd->last_sw_check +
+				   MT_DFS_SW_TIMEOUT)) {
+		dfs_pd->last_sw_check = jiffies;
+
+		mt76x2_dfs_add_events(dev);
+		mt76x2_dfs_check_event_window(dev);
+	}
+
 	engine_mask = mt76_rr(dev, MT_BBP(DFS, 1));
 	if (!(engine_mask & 0xf))
 		goto out;
@@ -326,9 +460,7 @@ static void mt76x2_dfs_tasklet(unsigned long arg)
 		/* hw detector rx radar pattern */
 		dfs_pd->stats[i].hw_pattern++;
 		ieee80211_radar_detected(dev->mt76.hw);
-
-		/* reset hw detector */
-		mt76_wr(dev, MT_BBP(DFS, 1), 0xf);
+		mt76x2_dfs_detector_reset(dev);
 
 		return;
 	}
@@ -487,6 +619,7 @@ void mt76x2_dfs_init_detector(struct mt76x2_dev *dev)
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 
 	dfs_pd->region = NL80211_DFS_UNSET;
+	dfs_pd->last_sw_check = jiffies;
 	tasklet_init(&dfs_pd->dfs_tasklet, mt76x2_dfs_tasklet,
 		     (unsigned long)dev);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
index 8dbc783cc6bc..49a49e999fed 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
@@ -33,6 +33,12 @@
 #define MT_DFS_PKT_END_MASK		0
 #define MT_DFS_CH_EN			0xf
 
+/* sw detector params */
+#define MT_DFS_EVENT_LOOP		64
+#define MT_DFS_SW_TIMEOUT		(HZ / 20)
+#define MT_DFS_EVENT_WINDOW		(HZ / 5)
+#define MT_DFS_EVENT_TIME_MARGIN	2000
+
 struct mt76x2_radar_specs {
 	u8 mode;
 	u16 avg_len;
@@ -50,6 +56,23 @@ struct mt76x2_radar_specs {
 	u16 pwr_jmp;
 };
 
+#define MT_DFS_CHECK_EVENT(x)		((x) != GENMASK(31, 0))
+#define MT_DFS_EVENT_ENGINE(x)		(((x) & BIT(31)) ? 2 : 0)
+#define MT_DFS_EVENT_TIMESTAMP(x)	((x) & GENMASK(21, 0))
+#define MT_DFS_EVENT_WIDTH(x)		((x) & GENMASK(11, 0))
+struct mt76x2_dfs_event {
+	unsigned long fetch_ts;
+	u32 ts;
+	u16 width;
+	u8 engine;
+};
+
+#define MT_DFS_EVENT_BUFLEN		256
+struct mt76x2_dfs_event_rb {
+	struct mt76x2_dfs_event data[MT_DFS_EVENT_BUFLEN];
+	int h_rb, t_rb;
+};
+
 struct mt76x2_dfs_hw_pulse {
 	u8 engine;
 	u32 period;
@@ -69,6 +92,10 @@ struct mt76x2_dfs_pattern_detector {
 	u8 chirp_pulse_cnt;
 	u32 chirp_pulse_ts;
 
+	struct mt76x2_dfs_event_rb event_rb[2];
+	unsigned long last_sw_check;
+	u32 last_event_ts;
+
 	struct mt76x2_dfs_engine_stats stats[MT_DFS_NUM_ENGINES];
 	struct tasklet_struct dfs_tasklet;
 };
-- 
cgit v1.2.3


From b7384e4e0d564a6d898b7f9b68e3ba7e619fcdc1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 29 Jun 2018 13:40:54 +0200
Subject: mt76x2: dfs: add sw pattern detector

Add sw DFS pattern detector support for mt76x2 based devices.
Dfs pattern supported:
- short pulse radar patterns
- staggered radar patterns

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c | 231 +++++++++++++++++++++++-
 drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h |  30 +++
 2 files changed, 260 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
index 606202fe1851..38c1d5dc47ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
@@ -159,9 +159,57 @@ static void mt76x2_dfs_set_capture_mode_ctrl(struct mt76x2_dev *dev,
 	mt76_wr(dev, MT_BBP(DFS, 36), data);
 }
 
+static void mt76x2_dfs_seq_pool_put(struct mt76x2_dev *dev,
+				    struct mt76x2_dfs_sequence *seq)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	list_add(&seq->head, &dfs_pd->seq_pool);
+}
+
+static
+struct mt76x2_dfs_sequence *mt76x2_dfs_seq_pool_get(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sequence *seq;
+
+	if (list_empty(&dfs_pd->seq_pool)) {
+		seq = devm_kzalloc(dev->mt76.dev, sizeof(*seq), GFP_ATOMIC);
+	} else {
+		seq = list_first_entry(&dfs_pd->seq_pool,
+				       struct mt76x2_dfs_sequence,
+				       head);
+		list_del(&seq->head);
+	}
+	return seq;
+}
+
+static int mt76x2_dfs_get_multiple(int val, int frac, int margin)
+{
+	int remainder, factor;
+
+	if (!frac)
+		return 0;
+
+	if (abs(val - frac) <= margin)
+		return 1;
+
+	factor = val / frac;
+	remainder = val % frac;
+
+	if (remainder > margin) {
+		if ((frac - remainder) <= margin)
+			factor++;
+		else
+			factor = 0;
+	}
+	return factor;
+}
+
 static void mt76x2_dfs_detector_reset(struct mt76x2_dev *dev)
 {
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sequence *seq, *tmp_seq;
 	int i;
 
 	/* reset hw detector */
@@ -172,6 +220,11 @@ static void mt76x2_dfs_detector_reset(struct mt76x2_dev *dev)
 		dfs_pd->event_rb[i].h_rb = 0;
 		dfs_pd->event_rb[i].t_rb = 0;
 	}
+
+	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
+		list_del_init(&seq->head);
+		mt76x2_dfs_seq_pool_put(dev, seq);
+	}
 }
 
 static bool mt76x2_dfs_check_chirp(struct mt76x2_dev *dev)
@@ -374,11 +427,145 @@ static void mt76x2_dfs_queue_event(struct mt76x2_dev *dev,
 					     MT_DFS_EVENT_BUFLEN);
 }
 
+static int mt76x2_dfs_create_sequence(struct mt76x2_dev *dev,
+				      struct mt76x2_dfs_event *event,
+				      u16 cur_len)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sw_detector_params *sw_params;
+	u32 width_delta, with_sum, factor, cur_pri;
+	struct mt76x2_dfs_sequence seq, *seq_p;
+	struct mt76x2_dfs_event_rb *event_rb;
+	struct mt76x2_dfs_event *cur_event;
+	int i, j, end, pri;
+
+	event_rb = event->engine == 2 ? &dfs_pd->event_rb[1]
+				      : &dfs_pd->event_rb[0];
+
+	i = mt76_decr(event_rb->t_rb, MT_DFS_EVENT_BUFLEN);
+	end = mt76_decr(event_rb->h_rb, MT_DFS_EVENT_BUFLEN);
+
+	while (i != end) {
+		cur_event = &event_rb->data[i];
+		with_sum = event->width + cur_event->width;
+
+		sw_params = &dfs_pd->sw_dpd_params;
+		switch (dev->dfs_pd.region) {
+		case NL80211_DFS_FCC:
+		case NL80211_DFS_JP:
+			if (with_sum < 600)
+				width_delta = 8;
+			else
+				width_delta = with_sum >> 3;
+			break;
+		case NL80211_DFS_ETSI:
+			if (event->engine == 2)
+				width_delta = with_sum >> 6;
+			else if (with_sum < 620)
+				width_delta = 24;
+			else
+				width_delta = 8;
+			break;
+		case NL80211_DFS_UNSET:
+		default:
+			return -EINVAL;
+		}
+
+		pri = event->ts - cur_event->ts;
+		if (abs(event->width - cur_event->width) > width_delta ||
+		    pri < sw_params->min_pri)
+			goto next;
+
+		if (pri > sw_params->max_pri)
+			break;
+
+		seq.pri = event->ts - cur_event->ts;
+		seq.first_ts = cur_event->ts;
+		seq.last_ts = event->ts;
+		seq.engine = event->engine;
+		seq.count = 2;
+
+		j = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
+		while (j != end) {
+			cur_event = &event_rb->data[j];
+			cur_pri = event->ts - cur_event->ts;
+			factor = mt76x2_dfs_get_multiple(cur_pri, seq.pri,
+						sw_params->pri_margin);
+			if (factor > 0) {
+				seq.first_ts = cur_event->ts;
+				seq.count++;
+			}
+
+			j = mt76_decr(j, MT_DFS_EVENT_BUFLEN);
+		}
+		if (seq.count <= cur_len)
+			goto next;
+
+		seq_p = mt76x2_dfs_seq_pool_get(dev);
+		if (!seq_p)
+			return -ENOMEM;
+
+		*seq_p = seq;
+		INIT_LIST_HEAD(&seq_p->head);
+		list_add(&seq_p->head, &dfs_pd->sequences);
+next:
+		i = mt76_decr(i, MT_DFS_EVENT_BUFLEN);
+	}
+	return 0;
+}
+
+static u16 mt76x2_dfs_add_event_to_sequence(struct mt76x2_dev *dev,
+					    struct mt76x2_dfs_event *event)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sw_detector_params *sw_params;
+	struct mt76x2_dfs_sequence *seq, *tmp_seq;
+	u16 max_seq_len = 0;
+	u32 factor, pri;
+
+	sw_params = &dfs_pd->sw_dpd_params;
+	list_for_each_entry_safe(seq, tmp_seq, &dfs_pd->sequences, head) {
+		if (event->ts > seq->first_ts + MT_DFS_SEQUENCE_WINDOW) {
+			list_del_init(&seq->head);
+			mt76x2_dfs_seq_pool_put(dev, seq);
+			continue;
+		}
+
+		if (event->engine != seq->engine)
+			continue;
+
+		pri = event->ts - seq->last_ts;
+		factor = mt76x2_dfs_get_multiple(pri, seq->pri,
+						 sw_params->pri_margin);
+		if (factor > 0) {
+			seq->last_ts = event->ts;
+			seq->count++;
+			max_seq_len = max_t(u16, max_seq_len, seq->count);
+		}
+	}
+	return max_seq_len;
+}
+
+static bool mt76x2_dfs_check_detection(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+	struct mt76x2_dfs_sequence *seq;
+
+	if (list_empty(&dfs_pd->sequences))
+		return false;
+
+	list_for_each_entry(seq, &dfs_pd->sequences, head) {
+		if (seq->count > MT_DFS_SEQUENCE_TH)
+			return true;
+	}
+	return false;
+}
+
 static void mt76x2_dfs_add_events(struct mt76x2_dev *dev)
 {
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 	struct mt76x2_dfs_event event;
-	int i;
+	int i, seq_len;
 
 	/* disable debug mode */
 	mt76x2_dfs_set_capture_mode_ctrl(dev, false);
@@ -393,6 +580,9 @@ static void mt76x2_dfs_add_events(struct mt76x2_dev *dev)
 		if (!mt76x2_dfs_check_event(dev, &event))
 			continue;
 
+		seq_len = mt76x2_dfs_add_event_to_sequence(dev, &event);
+		mt76x2_dfs_create_sequence(dev, &event, seq_len);
+
 		mt76x2_dfs_queue_event(dev, &event);
 	}
 	mt76x2_dfs_set_capture_mode_ctrl(dev, true);
@@ -433,9 +623,19 @@ static void mt76x2_dfs_tasklet(unsigned long arg)
 
 	if (time_is_before_jiffies(dfs_pd->last_sw_check +
 				   MT_DFS_SW_TIMEOUT)) {
+		bool radar_detected;
+
 		dfs_pd->last_sw_check = jiffies;
 
 		mt76x2_dfs_add_events(dev);
+		radar_detected = mt76x2_dfs_check_detection(dev);
+		if (radar_detected) {
+			/* sw detector rx radar pattern */
+			ieee80211_radar_detected(dev->mt76.hw);
+			mt76x2_dfs_detector_reset(dev);
+
+			return;
+		}
 		mt76x2_dfs_check_event_window(dev);
 	}
 
@@ -472,6 +672,32 @@ out:
 	mt76x2_irq_enable(dev, MT_INT_GPTIMER);
 }
 
+static void mt76x2_dfs_init_sw_detector(struct mt76x2_dev *dev)
+{
+	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
+
+	switch (dev->dfs_pd.region) {
+	case NL80211_DFS_FCC:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_FCC_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_FCC_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
+		break;
+	case NL80211_DFS_ETSI:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_ETSI_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_ETSI_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN << 2;
+		break;
+	case NL80211_DFS_JP:
+		dfs_pd->sw_dpd_params.max_pri = MT_DFS_JP_MAX_PRI;
+		dfs_pd->sw_dpd_params.min_pri = MT_DFS_JP_MIN_PRI;
+		dfs_pd->sw_dpd_params.pri_margin = MT_DFS_PRI_MARGIN;
+		break;
+	case NL80211_DFS_UNSET:
+	default:
+		break;
+	}
+}
+
 static void mt76x2_dfs_set_bbp_params(struct mt76x2_dev *dev)
 {
 	u32 data;
@@ -594,6 +820,7 @@ void mt76x2_dfs_init_params(struct mt76x2_dev *dev)
 
 	if ((chandef->chan->flags & IEEE80211_CHAN_RADAR) &&
 	    dev->dfs_pd.region != NL80211_DFS_UNSET) {
+		mt76x2_dfs_init_sw_detector(dev);
 		mt76x2_dfs_set_bbp_params(dev);
 		/* enable debug mode */
 		mt76x2_dfs_set_capture_mode_ctrl(dev, true);
@@ -618,6 +845,8 @@ void mt76x2_dfs_init_detector(struct mt76x2_dev *dev)
 {
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 
+	INIT_LIST_HEAD(&dfs_pd->sequences);
+	INIT_LIST_HEAD(&dfs_pd->seq_pool);
 	dfs_pd->region = NL80211_DFS_UNSET;
 	dfs_pd->last_sw_check = jiffies;
 	tasklet_init(&dfs_pd->dfs_tasklet, mt76x2_dfs_tasklet,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
index 49a49e999fed..83d2ff0b7e1f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
@@ -37,7 +37,17 @@
 #define MT_DFS_EVENT_LOOP		64
 #define MT_DFS_SW_TIMEOUT		(HZ / 20)
 #define MT_DFS_EVENT_WINDOW		(HZ / 5)
+#define MT_DFS_SEQUENCE_WINDOW		(200 * (1 << 20))
 #define MT_DFS_EVENT_TIME_MARGIN	2000
+#define MT_DFS_PRI_MARGIN		4
+#define MT_DFS_SEQUENCE_TH		6
+
+#define MT_DFS_FCC_MAX_PRI		((28570 << 1) + 1000)
+#define MT_DFS_FCC_MIN_PRI		(3000 - 2)
+#define MT_DFS_JP_MAX_PRI		((80000 << 1) + 1000)
+#define MT_DFS_JP_MIN_PRI		(28500 - 2)
+#define MT_DFS_ETSI_MAX_PRI		(133333 + 125000 + 117647 + 1000)
+#define MT_DFS_ETSI_MIN_PRI		(4500 - 20)
 
 struct mt76x2_radar_specs {
 	u8 mode;
@@ -73,6 +83,15 @@ struct mt76x2_dfs_event_rb {
 	int h_rb, t_rb;
 };
 
+struct mt76x2_dfs_sequence {
+	struct list_head head;
+	u32 first_ts;
+	u32 last_ts;
+	u32 pri;
+	u16 count;
+	u8 engine;
+};
+
 struct mt76x2_dfs_hw_pulse {
 	u8 engine;
 	u32 period;
@@ -81,6 +100,12 @@ struct mt76x2_dfs_hw_pulse {
 	u32 burst;
 };
 
+struct mt76x2_dfs_sw_detector_params {
+	u32 min_pri;
+	u32 max_pri;
+	u32 pri_margin;
+};
+
 struct mt76x2_dfs_engine_stats {
 	u32 hw_pattern;
 	u32 hw_pulse_discarded;
@@ -92,7 +117,12 @@ struct mt76x2_dfs_pattern_detector {
 	u8 chirp_pulse_cnt;
 	u32 chirp_pulse_ts;
 
+	struct mt76x2_dfs_sw_detector_params sw_dpd_params;
 	struct mt76x2_dfs_event_rb event_rb[2];
+
+	struct list_head sequences;
+	struct list_head seq_pool;
+
 	unsigned long last_sw_check;
 	u32 last_event_ts;
 
-- 
cgit v1.2.3


From 4a07ed51cae18765c76d9aede5b9830d42db1546 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Fri, 29 Jun 2018 13:40:55 +0200
Subject: mt76x2: debugfs: add sw pulse statistics to dfs debugfs

Add sw pattern detector statistics to mt76x2 debugfs.
Moreover track down number of allocated sequence by the detector

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c |  8 ++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c     | 11 ++++++++++-
 drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h     |  7 +++++++
 3 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
index 3f86e01049f3..74725902e6dc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
@@ -91,12 +91,20 @@ mt76x2_dfs_stat_read(struct seq_file *file, void *data)
 	struct mt76x2_dev *dev = file->private;
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 
+	seq_printf(file, "allocated sequences:\t%d\n",
+		   dfs_pd->seq_stats.seq_pool_len);
+	seq_printf(file, "used sequences:\t\t%d\n",
+		   dfs_pd->seq_stats.seq_len);
+	seq_puts(file, "\n");
+
 	for (i = 0; i < MT_DFS_NUM_ENGINES; i++) {
 		seq_printf(file, "engine: %d\n", i);
 		seq_printf(file, "  hw pattern detected:\t%d\n",
 			   dfs_pd->stats[i].hw_pattern);
 		seq_printf(file, "  hw pulse discarded:\t%d\n",
 			   dfs_pd->stats[i].hw_pulse_discarded);
+		seq_printf(file, "  sw pattern detected:\t%d\n",
+			   dfs_pd->stats[i].sw_pattern);
 	}
 
 	return 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
index 38c1d5dc47ec..374cc655c11d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.c
@@ -165,6 +165,9 @@ static void mt76x2_dfs_seq_pool_put(struct mt76x2_dev *dev,
 	struct mt76x2_dfs_pattern_detector *dfs_pd = &dev->dfs_pd;
 
 	list_add(&seq->head, &dfs_pd->seq_pool);
+
+	dfs_pd->seq_stats.seq_pool_len++;
+	dfs_pd->seq_stats.seq_len--;
 }
 
 static
@@ -180,7 +183,11 @@ struct mt76x2_dfs_sequence *mt76x2_dfs_seq_pool_get(struct mt76x2_dev *dev)
 				       struct mt76x2_dfs_sequence,
 				       head);
 		list_del(&seq->head);
+		dfs_pd->seq_stats.seq_pool_len--;
 	}
+	if (seq)
+		dfs_pd->seq_stats.seq_len++;
+
 	return seq;
 }
 
@@ -555,8 +562,10 @@ static bool mt76x2_dfs_check_detection(struct mt76x2_dev *dev)
 		return false;
 
 	list_for_each_entry(seq, &dfs_pd->sequences, head) {
-		if (seq->count > MT_DFS_SEQUENCE_TH)
+		if (seq->count > MT_DFS_SEQUENCE_TH) {
+			dfs_pd->stats[seq->engine].sw_pattern++;
 			return true;
+		}
 	}
 	return false;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
index 83d2ff0b7e1f..693f421bf096 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dfs.h
@@ -109,6 +109,12 @@ struct mt76x2_dfs_sw_detector_params {
 struct mt76x2_dfs_engine_stats {
 	u32 hw_pattern;
 	u32 hw_pulse_discarded;
+	u32 sw_pattern;
+};
+
+struct mt76x2_dfs_seq_stats {
+	u32 seq_pool_len;
+	u32 seq_len;
 };
 
 struct mt76x2_dfs_pattern_detector {
@@ -122,6 +128,7 @@ struct mt76x2_dfs_pattern_detector {
 
 	struct list_head sequences;
 	struct list_head seq_pool;
+	struct mt76x2_dfs_seq_stats seq_stats;
 
 	unsigned long last_sw_check;
 	u32 last_event_ts;
-- 
cgit v1.2.3


From 2473394343c338426689476aec42790e6d40731c Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 19 Apr 2018 10:05:56 -0400
Subject: media: platform: exynos4-is: simplify getting .drvdata

We should get drvdata from struct device directly. Going via
platform_device is an unneeded step back and forth.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/exynos4-is/media-dev.c | 6 ++----
 drivers/media/platform/exynos4-is/mipi-csis.c | 6 ++----
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/media/platform/exynos4-is/media-dev.c b/drivers/media/platform/exynos4-is/media-dev.c
index 78b48a1fa26c..deb499f76412 100644
--- a/drivers/media/platform/exynos4-is/media-dev.c
+++ b/drivers/media/platform/exynos4-is/media-dev.c
@@ -1201,8 +1201,7 @@ static const struct media_device_ops fimc_md_ops = {
 static ssize_t fimc_md_sysfs_show(struct device *dev,
 				  struct device_attribute *attr, char *buf)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct fimc_md *fmd = platform_get_drvdata(pdev);
+	struct fimc_md *fmd = dev_get_drvdata(dev);
 
 	if (fmd->user_subdev_api)
 		return strlcpy(buf, "Sub-device API (sub-dev)\n", PAGE_SIZE);
@@ -1214,8 +1213,7 @@ static ssize_t fimc_md_sysfs_store(struct device *dev,
 				   struct device_attribute *attr,
 				   const char *buf, size_t count)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct fimc_md *fmd = platform_get_drvdata(pdev);
+	struct fimc_md *fmd = dev_get_drvdata(dev);
 	bool subdev_api;
 	int i;
 
diff --git a/drivers/media/platform/exynos4-is/mipi-csis.c b/drivers/media/platform/exynos4-is/mipi-csis.c
index cba46a656338..b4e28a299e26 100644
--- a/drivers/media/platform/exynos4-is/mipi-csis.c
+++ b/drivers/media/platform/exynos4-is/mipi-csis.c
@@ -891,8 +891,7 @@ e_clkput:
 
 static int s5pcsis_pm_suspend(struct device *dev, bool runtime)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct v4l2_subdev *sd = platform_get_drvdata(pdev);
+	struct v4l2_subdev *sd = dev_get_drvdata(dev);
 	struct csis_state *state = sd_to_csis_state(sd);
 	int ret = 0;
 
@@ -921,8 +920,7 @@ static int s5pcsis_pm_suspend(struct device *dev, bool runtime)
 
 static int s5pcsis_pm_resume(struct device *dev, bool runtime)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct v4l2_subdev *sd = platform_get_drvdata(pdev);
+	struct v4l2_subdev *sd = dev_get_drvdata(dev);
 	struct csis_state *state = sd_to_csis_state(sd);
 	int ret = 0;
 
-- 
cgit v1.2.3


From c51756d56e20a12476e4e192b332fac39c1550ca Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 29 Jun 2018 11:47:40 -0700
Subject: drm/sun4i: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], this
switches to using a kmalloc allocation and moves all the size calculations
to the start to do an allocation. If an upper bounds on the mode timing
calculations could be determined, a fixed stack size could be used instead.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180629184740.GA37415@beast
---
 drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c | 107 ++++++++++++++++++++-------------
 1 file changed, 64 insertions(+), 43 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index d4e7d16a2514..da9814f94d00 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -13,6 +13,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/regmap.h>
 #include <linux/reset.h>
+#include <linux/slab.h>
 
 #include <linux/phy/phy.h>
 
@@ -247,10 +248,8 @@ static u16 sun6i_dsi_crc_compute(u8 const *buffer, size_t len)
 	return crc_ccitt(0xffff, buffer, len);
 }
 
-static u16 sun6i_dsi_crc_repeat_compute(u8 pd, size_t len)
+static u16 sun6i_dsi_crc_repeat(u8 pd, u8 *buffer, size_t len)
 {
-	u8 buffer[len];
-
 	memset(buffer, pd, len);
 
 	return sun6i_dsi_crc_compute(buffer, len);
@@ -274,11 +273,11 @@ static u32 sun6i_dsi_build_blk0_pkt(u8 vc, u16 wc)
 					wc & 0xff, wc >> 8);
 }
 
-static u32 sun6i_dsi_build_blk1_pkt(u16 pd, size_t len)
+static u32 sun6i_dsi_build_blk1_pkt(u16 pd, u8 *buffer, size_t len)
 {
 	u32 val = SUN6I_DSI_BLK_PD(pd);
 
-	return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat_compute(pd, len));
+	return val | SUN6I_DSI_BLK_PF(sun6i_dsi_crc_repeat(pd, buffer, len));
 }
 
 static void sun6i_dsi_inst_abort(struct sun6i_dsi *dsi)
@@ -452,6 +451,54 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 	struct mipi_dsi_device *device = dsi->device;
 	unsigned int Bpp = mipi_dsi_pixel_format_to_bpp(device->format) / 8;
 	u16 hbp, hfp, hsa, hblk, vblk;
+	size_t bytes;
+	u8 *buffer;
+
+	/* Do all timing calculations up front to allocate buffer space */
+
+	/*
+	 * A sync period is composed of a blanking packet (4 bytes +
+	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
+	 * minimal size is therefore 10 bytes
+	 */
+#define HSA_PACKET_OVERHEAD	10
+	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
+		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+
+	/*
+	 * The backporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HBP_PACKET_OVERHEAD	6
+	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
+		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
+
+	/*
+	 * The frontporch is set using a blanking packet (4 bytes +
+	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
+	 */
+#define HFP_PACKET_OVERHEAD	6
+	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
+		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
+
+	/*
+	 * hblk seems to be the line + porches length.
+	 */
+	hblk = mode->htotal * Bpp - hsa;
+
+	/*
+	 * And I'm not entirely sure what vblk is about. The driver in
+	 * Allwinner BSP is using a rather convoluted calculation
+	 * there only for 4 lanes. However, using 0 (the !4 lanes
+	 * case) even with a 4 lanes screen seems to work...
+	 */
+	vblk = 0;
+
+	/* How many bytes do we need to send all payloads? */
+	bytes = max_t(size_t, max(max(hfp, hblk), max(hsa, hbp)), vblk);
+	buffer = kmalloc(bytes, GFP_KERNEL);
+	if (WARN_ON(!buffer))
+		return;
 
 	regmap_write(dsi->regs, SUN6I_DSI_BASIC_CTL_REG, 0);
 
@@ -485,63 +532,37 @@ static void sun6i_dsi_setup_timings(struct sun6i_dsi *dsi,
 		     SUN6I_DSI_BASIC_SIZE1_VACT(mode->vdisplay) |
 		     SUN6I_DSI_BASIC_SIZE1_VT(mode->vtotal));
 
-	/*
-	 * A sync period is composed of a blanking packet (4 bytes +
-	 * payload + 2 bytes) and a sync event packet (4 bytes). Its
-	 * minimal size is therefore 10 bytes
-	 */
-#define HSA_PACKET_OVERHEAD	10
-	hsa = max((unsigned int)HSA_PACKET_OVERHEAD,
-		  (mode->hsync_end - mode->hsync_start) * Bpp - HSA_PACKET_OVERHEAD);
+	/* sync */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hsa));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HSA1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hsa));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hsa));
 
-	/*
-	 * The backporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
-#define HBP_PACKET_OVERHEAD	6
-	hbp = max((unsigned int)HBP_PACKET_OVERHEAD,
-		  (mode->hsync_start - mode->hdisplay) * Bpp - HBP_PACKET_OVERHEAD);
+	/* backporch */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hbp));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBP1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hbp));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hbp));
 
-	/*
-	 * The frontporch is set using a blanking packet (4 bytes +
-	 * payload + 2 bytes). Its minimal size is therefore 6 bytes
-	 */
-#define HFP_PACKET_OVERHEAD	6
-	hfp = max((unsigned int)HFP_PACKET_OVERHEAD,
-		  (mode->htotal - mode->hsync_end) * Bpp - HFP_PACKET_OVERHEAD);
+	/* frontporch */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hfp));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HFP1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hfp));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hfp));
 
-	/*
-	 * hblk seems to be the line + porches length.
-	 */
-	hblk = mode->htotal * Bpp - hsa;
+	/* hblk */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, hblk));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_HBLK1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, hblk));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, hblk));
 
-	/*
-	 * And I'm not entirely sure what vblk is about. The driver in
-	 * Allwinner BSP is using a rather convoluted calculation
-	 * there only for 4 lanes. However, using 0 (the !4 lanes
-	 * case) even with a 4 lanes screen seems to work...
-	 */
-	vblk = 0;
+	/* vblk */
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK0_REG,
 		     sun6i_dsi_build_blk0_pkt(device->channel, vblk));
 	regmap_write(dsi->regs, SUN6I_DSI_BLK_VBLK1_REG,
-		     sun6i_dsi_build_blk1_pkt(0, vblk));
+		     sun6i_dsi_build_blk1_pkt(0, buffer, vblk));
+
+	kfree(buffer);
 }
 
 static int sun6i_dsi_start(struct sun6i_dsi *dsi,
-- 
cgit v1.2.3


From 666e994aa2278e948e2492ee9d81b4df241e7222 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 19 Apr 2018 10:05:57 -0400
Subject: media: platform: s5p-mfc: simplify getting .drvdata

We should get drvdata from struct device directly. Going via
platform_device is an unneeded step back and forth.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/s5p-mfc/s5p_mfc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index a80251ed3143..9ca707cb2a42 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -1449,8 +1449,7 @@ static int s5p_mfc_remove(struct platform_device *pdev)
 
 static int s5p_mfc_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct s5p_mfc_dev *m_dev = platform_get_drvdata(pdev);
+	struct s5p_mfc_dev *m_dev = dev_get_drvdata(dev);
 	int ret;
 
 	if (m_dev->num_inst == 0)
@@ -1484,8 +1483,7 @@ static int s5p_mfc_suspend(struct device *dev)
 
 static int s5p_mfc_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct s5p_mfc_dev *m_dev = platform_get_drvdata(pdev);
+	struct s5p_mfc_dev *m_dev = dev_get_drvdata(dev);
 
 	if (m_dev->num_inst == 0)
 		return 0;
-- 
cgit v1.2.3


From 7c1b9a5aeed91bef98988ac0fcf38c8c1f4f9a3a Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <s.nawrocki@samsung.com>
Date: Tue, 15 May 2018 05:21:45 -0400
Subject: media: exynos4-is: Prevent NULL pointer dereference in
 __isp_video_try_fmt()

This patch fixes potential NULL pointer dereference as indicated
by the following static checker warning:

drivers/media/platform/exynos4-is/fimc-isp-video.c:408 isp_video_try_fmt_mplane()
error: NULL dereference inside function '__isp_video_try_fmt(isp, &f->fmt.pix_mp, (0))()'.

Fixes: 34947b8aebe3: ("[media] exynos4-is: Add the FIMC-IS ISP capture DMA driver")

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/exynos4-is/fimc-isp-video.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/exynos4-is/fimc-isp-video.c b/drivers/media/platform/exynos4-is/fimc-isp-video.c
index 55ba696b8cf4..a920164f53f1 100644
--- a/drivers/media/platform/exynos4-is/fimc-isp-video.c
+++ b/drivers/media/platform/exynos4-is/fimc-isp-video.c
@@ -384,12 +384,17 @@ static void __isp_video_try_fmt(struct fimc_isp *isp,
 				struct v4l2_pix_format_mplane *pixm,
 				const struct fimc_fmt **fmt)
 {
-	*fmt = fimc_isp_find_format(&pixm->pixelformat, NULL, 2);
+	const struct fimc_fmt *__fmt;
+
+	__fmt = fimc_isp_find_format(&pixm->pixelformat, NULL, 2);
+
+	if (fmt)
+		*fmt = __fmt;
 
 	pixm->colorspace = V4L2_COLORSPACE_SRGB;
 	pixm->field = V4L2_FIELD_NONE;
-	pixm->num_planes = (*fmt)->memplanes;
-	pixm->pixelformat = (*fmt)->fourcc;
+	pixm->num_planes = __fmt->memplanes;
+	pixm->pixelformat = __fmt->fourcc;
 	/*
 	 * TODO: double check with the docmentation these width/height
 	 * constraints are correct.
-- 
cgit v1.2.3


From 7e7df71fd57ff2894d96abb0080922bf39460a79 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Thu, 14 Jun 2018 14:58:21 -0400
Subject: arm64: fix infinite stacktrace

I've got this infinite stacktrace when debugging another problem:
[  908.795225] INFO: rcu_preempt detected stalls on CPUs/tasks:
[  908.796176]  1-...!: (1 GPs behind) idle=952/1/4611686018427387904 softirq=1462/1462 fqs=355
[  908.797692]  2-...!: (1 GPs behind) idle=f42/1/4611686018427387904 softirq=1550/1551 fqs=355
[  908.799189]  (detected by 0, t=2109 jiffies, g=130, c=129, q=235)
[  908.800284] Task dump for CPU 1:
[  908.800871] kworker/1:1     R  running task        0    32      2 0x00000022
[  908.802127] Workqueue: writecache-writeabck writecache_writeback [dm_writecache]
[  908.820285] Call trace:
[  908.824785]  __switch_to+0x68/0x90
[  908.837661]  0xfffffe00603afd90
[  908.844119]  0xfffffe00603afd90
[  908.850091]  0xfffffe00603afd90
[  908.854285]  0xfffffe00603afd90
[  908.863538]  0xfffffe00603afd90
[  908.865523]  0xfffffe00603afd90

The machine just locked up and kept on printing the same line over and
over again. This patch fixes it.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/stacktrace.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d5718a060672..e160ca123da3 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -56,6 +56,9 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
 	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
 
+	if (frame->fp <= fp)
+		return -EINVAL;
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
 			(frame->pc == (unsigned long)return_to_handler)) {
-- 
cgit v1.2.3


From 76f4e2da45b44bf70f61c28fcbc91668492463e0 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 2 Jul 2018 14:17:53 +0100
Subject: arm64: kexec: always reset to EL2 if present

Currently machine_kexec() doesn't reset to EL2 in the case of a
crashdump kernel. This leaves potentially dodgy state active at EL2, and
means that if the crashdump kernel attempts to online secondary CPUs,
these will be booted as mismatched ELs.

Let's reset to EL2, as we do in all other cases, and simplify things. If
EL2 state is corrupt, things are already sufficiently bad that kdump is
unlikely to work, and it's best-effort regardless.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/cpu-reset.h     | 9 +++++----
 arch/arm64/kernel/machine_kexec.c | 3 +--
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h
index 6c2b1b4f57c9..fad90e4935fb 100644
--- a/arch/arm64/kernel/cpu-reset.h
+++ b/arch/arm64/kernel/cpu-reset.h
@@ -16,13 +16,14 @@
 void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry,
 	unsigned long arg0, unsigned long arg1, unsigned long arg2);
 
-static inline void __noreturn cpu_soft_restart(unsigned long el2_switch,
-	unsigned long entry, unsigned long arg0, unsigned long arg1,
-	unsigned long arg2)
+static inline void __noreturn cpu_soft_restart(unsigned long entry,
+					       unsigned long arg0,
+					       unsigned long arg1,
+					       unsigned long arg2)
 {
 	typeof(__cpu_soft_restart) *restart;
 
-	el2_switch = el2_switch && !is_kernel_in_hyp_mode() &&
+	unsigned long el2_switch = !is_kernel_in_hyp_mode() &&
 		is_hyp_mode_available();
 	restart = (void *)__pa_symbol(__cpu_soft_restart);
 
diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index f76ea92dff91..f62effc6e064 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -207,8 +207,7 @@ void machine_kexec(struct kimage *kimage)
 	 * relocation is complete.
 	 */
 
-	cpu_soft_restart(kimage != kexec_crash_image,
-		reboot_code_buffer_phys, kimage->head, kimage->start, 0);
+	cpu_soft_restart(reboot_code_buffer_phys, kimage->head, kimage->start, 0);
 
 	BUG(); /* Should never get here. */
 }
-- 
cgit v1.2.3


From 26acfb666a473d960f0fd971fe68f3e3ad16c70b Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 20 Jun 2018 11:29:53 -0400
Subject: x86/KVM: Warn user if KVM is loaded SMT and L1TF CPU bug being
 present

If the L1TF CPU bug is present we allow the KVM module to be loaded as the
major of users that use Linux and KVM have trusted guests and do not want a
broken setup.

Cloud vendors are the ones that are uncomfortable with CVE 2018-3620 and as
such they are the ones that should set nosmt to one.

Setting 'nosmt' means that the system administrator also needs to disable
SMT (Hyper-threading) in the BIOS, or via the 'nosmt' command line
parameter, or via the /sys/devices/system/cpu/smt/control. See commit
05736e4ac13c ("cpu/hotplug: Provide knobs to control SMT").

Other mitigations are to use task affinity, cpu sets, interrupt binding,
etc - anything to make sure that _only_ the same guests vCPUs are running
on sibling threads.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/admin-guide/kernel-parameters.txt |  6 ++++++
 arch/x86/kvm/vmx.c                              | 13 +++++++++++++
 kernel/cpu.c                                    |  1 +
 3 files changed, 20 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 5da7b0b30432..298f1b38dc89 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1946,6 +1946,12 @@
 			[KVM,ARM] Allow use of GICv4 for direct injection of
 			LPIs.
 
+	kvm-intel.nosmt=[KVM,Intel] If the L1TF CPU bug is present (CVE-2018-3620)
+			and the system has SMT (aka Hyper-Threading) enabled then
+			don't allow guests to be created.
+
+			Default is 0 (allow guests to be created).
+
 	kvm-intel.ept=	[KVM,Intel] Disable extended page tables
 			(virtualized MMU) support on capable Intel chips.
 			Default is 1 (enabled)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 559a12b6184d..f2e7b6d016c9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -71,6 +71,9 @@ static const struct x86_cpu_id vmx_cpu_id[] = {
 };
 MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
 
+static bool __read_mostly nosmt;
+module_param(nosmt, bool, S_IRUGO);
+
 static bool __read_mostly enable_vpid = 1;
 module_param_named(vpid, enable_vpid, bool, 0444);
 
@@ -10370,10 +10373,20 @@ free_vcpu:
 	return ERR_PTR(err);
 }
 
+#define L1TF_MSG "SMT enabled with L1TF CPU bug present. Refer to CVE-2018-3620 for details.\n"
+
 static int vmx_vm_init(struct kvm *kvm)
 {
 	if (!ple_gap)
 		kvm->arch.pause_in_guest = true;
+
+	if (boot_cpu_has(X86_BUG_L1TF) && cpu_smt_control == CPU_SMT_ENABLED) {
+		if (nosmt) {
+			pr_err(L1TF_MSG);
+			return -EOPNOTSUPP;
+		}
+		pr_warn(L1TF_MSG);
+	}
 	return 0;
 }
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 6f3a3cde8b83..5a00ebdf98c6 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -345,6 +345,7 @@ EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 
 #ifdef CONFIG_HOTPLUG_SMT
 enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
+EXPORT_SYMBOL_GPL(cpu_smt_control);
 
 static int __init smt_cmdline_disable(char *str)
 {
-- 
cgit v1.2.3


From a399477e52c17e148746d3ce9a483f681c2aa9a0 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Mon, 2 Jul 2018 12:29:30 +0200
Subject: x86/KVM/VMX: Add module argument for L1TF mitigation

Add a mitigation mode parameter "vmentry_l1d_flush" for CVE-2018-3620, aka
L1 terminal fault. The valid arguments are:

 - "always" 	L1D cache flush on every VMENTER.
 - "cond"	Conditional L1D cache flush, explained below
 - "never"	Disable the L1D cache flush mitigation

"cond" is trying to avoid L1D cache flushes on VMENTER if the code executed
between VMEXIT and VMENTER is considered safe, i.e. is not bringing any
interesting information into L1D which might exploited.

[ tglx: Split out from a larger patch ]

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/admin-guide/kernel-parameters.txt | 12 +++++
 arch/x86/kvm/vmx.c                              | 59 +++++++++++++++++++++++++
 2 files changed, 71 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 298f1b38dc89..4f790566ad91 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1973,6 +1973,18 @@
 			(virtualized real and unpaged mode) on capable
 			Intel chips. Default is 1 (enabled)
 
+	kvm-intel.vmentry_l1d_flush=[KVM,Intel] Mitigation for L1 Terminal Fault
+			CVE-2018-3620.
+
+			Valid arguments: never, cond, always
+
+			always: L1D cache flush on every VMENTER.
+			cond:	Flush L1D on VMENTER only when the code between
+				VMEXIT and VMENTER can leak host memory.
+			never:	Disables the mitigation
+
+			Default is cond (do L1 cache flush in specific instances)
+
 	kvm-intel.vpid=	[KVM,Intel] Disable Virtual Processor Identification
 			feature (tagged TLBs) on capable Intel chips.
 			Default is 1 (enabled)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index f2e7b6d016c9..dd82428ec923 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -191,6 +191,54 @@ module_param(ple_window_max, uint, 0444);
 
 extern const ulong vmx_return;
 
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+
+/* These MUST be in sync with vmentry_l1d_param order. */
+enum vmx_l1d_flush_state {
+	VMENTER_L1D_FLUSH_NEVER,
+	VMENTER_L1D_FLUSH_COND,
+	VMENTER_L1D_FLUSH_ALWAYS,
+};
+
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND;
+
+static const struct {
+	const char *option;
+	enum vmx_l1d_flush_state cmd;
+} vmentry_l1d_param[] = {
+	{"never",	VMENTER_L1D_FLUSH_NEVER},
+	{"cond",	VMENTER_L1D_FLUSH_COND},
+	{"always",	VMENTER_L1D_FLUSH_ALWAYS},
+};
+
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+	unsigned int i;
+
+	if (!s)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+		if (!strcmp(s, vmentry_l1d_param[i].option)) {
+			vmentry_l1d_flush = vmentry_l1d_param[i].cmd;
+			return 0;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
+{
+	return sprintf(s, "%s\n", vmentry_l1d_param[vmentry_l1d_flush].option);
+}
+
+static const struct kernel_param_ops vmentry_l1d_flush_ops = {
+	.set = vmentry_l1d_flush_set,
+	.get = vmentry_l1d_flush_get,
+};
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, &vmentry_l1d_flush, S_IRUGO);
+
 struct kvm_vmx {
 	struct kvm kvm;
 
@@ -13062,6 +13110,15 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.enable_smi_window = enable_smi_window,
 };
 
+static void __init vmx_setup_l1d_flush(void)
+{
+	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
+	    !boot_cpu_has_bug(X86_BUG_L1TF))
+		return;
+
+	static_branch_enable(&vmx_l1d_should_flush);
+}
+
 static int __init vmx_init(void)
 {
 	int r;
@@ -13095,6 +13152,8 @@ static int __init vmx_init(void)
 	}
 #endif
 
+	vmx_setup_l1d_flush();
+
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
                      __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r)
-- 
cgit v1.2.3


From a47dd5f06714c844b33f3b5f517b6f3e81ce57b5 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 2 Jul 2018 12:47:38 +0200
Subject: x86/KVM/VMX: Add L1D flush algorithm

To mitigate the L1 Terminal Fault vulnerability it's required to flush L1D
on VMENTER to prevent rogue guests from snooping host memory.

CPUs will have a new control MSR via a microcode update to flush L1D with a
single MSR write, but in the absence of microcode a fallback to a software
based flush algorithm is required.

Add a software flush loop which is based on code from Intel.

[ tglx: Split out from combo patch ]
[ bpetkov: Polish the asm code ]

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 71 ++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 66 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index dd82428ec923..b072264eb464 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9563,6 +9563,46 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 	}
 }
 
+/*
+ * Software based L1D cache flush which is used when microcode providing
+ * the cache control MSR is not loaded.
+ *
+ * The L1D cache is 32 KiB on Nehalem and later microarchitectures, but to
+ * flush it is required to read in 64 KiB because the replacement algorithm
+ * is not exactly LRU. This could be sized at runtime via topology
+ * information but as all relevant affected CPUs have 32KiB L1D cache size
+ * there is no point in doing so.
+ */
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static void __maybe_unused vmx_l1d_flush(void)
+{
+	int size = PAGE_SIZE << L1D_CACHE_ORDER;
+
+	asm volatile(
+		/* First ensure the pages are in the TLB */
+		"xorl	%%eax, %%eax\n"
+		".Lpopulate_tlb:\n\t"
+		"movzbl	(%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$4096, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lpopulate_tlb\n\t"
+		"xorl	%%eax, %%eax\n\t"
+		"cpuid\n\t"
+		/* Now fill the cache */
+		"xorl	%%eax, %%eax\n"
+		".Lfill_cache:\n"
+		"movzbl	(%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+		"addl	$64, %%eax\n\t"
+		"cmpl	%%eax, %[size]\n\t"
+		"jne	.Lfill_cache\n\t"
+		"lfence\n"
+		:: [empty_zp] "r" (vmx_l1d_flush_pages),
+		    [size] "r" (size)
+		: "eax", "ebx", "ecx", "edx");
+}
+
 static void update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
 {
 	struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
@@ -13110,13 +13150,29 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.enable_smi_window = enable_smi_window,
 };
 
-static void __init vmx_setup_l1d_flush(void)
+static int __init vmx_setup_l1d_flush(void)
 {
+	struct page *page;
+
 	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
 	    !boot_cpu_has_bug(X86_BUG_L1TF))
-		return;
+		return 0;
+
+	page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+	if (!page)
+		return -ENOMEM;
 
+	vmx_l1d_flush_pages = page_address(page);
 	static_branch_enable(&vmx_l1d_should_flush);
+	return 0;
+}
+
+static void vmx_free_l1d_flush_pages(void)
+{
+	if (vmx_l1d_flush_pages) {
+		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
+		vmx_l1d_flush_pages = NULL;
+	}
 }
 
 static int __init vmx_init(void)
@@ -13152,12 +13208,16 @@ static int __init vmx_init(void)
 	}
 #endif
 
-	vmx_setup_l1d_flush();
+	r = vmx_setup_l1d_flush();
+	if (r)
+		return r;
 
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
-                     __alignof__(struct vcpu_vmx), THIS_MODULE);
-	if (r)
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
+	if (r) {
+		vmx_free_l1d_flush_pages();
 		return r;
+	}
 
 #ifdef CONFIG_KEXEC_CORE
 	rcu_assign_pointer(crash_vmclear_loaded_vmcss,
@@ -13199,6 +13259,7 @@ static void __exit vmx_exit(void)
 		static_branch_disable(&enable_evmcs);
 	}
 #endif
+	vmx_free_l1d_flush_pages();
 }
 
 module_init(vmx_init)
-- 
cgit v1.2.3


From 3fa045be4c720146b18a19cea7a767dc6ad5df94 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 2 Jul 2018 13:03:48 +0200
Subject: x86/KVM/VMX: Add L1D MSR based flush

336996-Speculative-Execution-Side-Channel-Mitigations.pdf defines a new MSR
(IA32_FLUSH_CMD aka 0x10B) which has similar write-only semantics to other
MSRs defined in the document.

The semantics of this MSR is to allow "finer granularity invalidation of
caching structures than existing mechanisms like WBINVD. It will writeback
and invalidate the L1 data cache, including all cachelines brought in by
preceding instructions, without invalidating all caches (eg. L2 or
LLC). Some processors may also invalidate the first level level instruction
cache on a L1D_FLUSH command. The L1 data and instruction caches may be
shared across the logical processors of a core."

Use it instead of the loop based L1 flush algorithm.

A copy of this document is available at
   https://bugzilla.kernel.org/show_bug.cgi?id=199511

[ tglx: Avoid allocating pages when the MSR is available ]

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/msr-index.h |  6 ++++++
 arch/x86/kvm/vmx.c               | 15 +++++++++++----
 2 files changed, 17 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 68b2c3150de1..0e7517089b80 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -76,6 +76,12 @@
 						    * control required.
 						    */
 
+#define MSR_IA32_FLUSH_CMD		0x0000010b
+#define L1D_FLUSH			(1 << 0)   /*
+						    * Writeback and invalidate the
+						    * L1 data cache.
+						    */
+
 #define MSR_IA32_BBL_CR_CTL		0x00000119
 #define MSR_IA32_BBL_CR_CTL3		0x0000011e
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b072264eb464..a1dbc17c7a03 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9580,6 +9580,11 @@ static void __maybe_unused vmx_l1d_flush(void)
 {
 	int size = PAGE_SIZE << L1D_CACHE_ORDER;
 
+	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+		return;
+	}
+
 	asm volatile(
 		/* First ensure the pages are in the TLB */
 		"xorl	%%eax, %%eax\n"
@@ -13158,11 +13163,13 @@ static int __init vmx_setup_l1d_flush(void)
 	    !boot_cpu_has_bug(X86_BUG_L1TF))
 		return 0;
 
-	page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
-	if (!page)
-		return -ENOMEM;
+	if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+		if (!page)
+			return -ENOMEM;
+		vmx_l1d_flush_pages = page_address(page);
+	}
 
-	vmx_l1d_flush_pages = page_address(page);
 	static_branch_enable(&vmx_l1d_should_flush);
 	return 0;
 }
-- 
cgit v1.2.3


From c595ceee45707f00f64f61c54fb64ef0cc0b4e85 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Mon, 2 Jul 2018 13:07:14 +0200
Subject: x86/KVM/VMX: Add L1D flush logic

Add the logic for flushing L1D on VMENTER. The flush depends on the static
key being enabled and the new l1tf_flush_l1d flag being set.

The flags is set:
 - Always, if the flush module parameter is 'always'

 - Conditionally at:
   - Entry to vcpu_run(), i.e. after executing user space

   - From the sched_in notifier, i.e. when switching to a vCPU thread.

   - From vmexit handlers which are considered unsafe, i.e. where
     sensitive data can be brought into L1D:

     - The emulator, which could be a good target for other speculative
       execution-based threats,

     - The MMU, which can bring host page tables in the L1 cache.

     - External interrupts

     - Nested operations that require the MMU (see above). That is
       vmptrld, vmptrst, vmclear,vmwrite,vmread.

     - When handling invept,invvpid

[ tglx: Split out from combo patch and reduced to a single flag ]

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/kvm_host.h |  4 ++++
 arch/x86/kvm/mmu.c              |  1 +
 arch/x86/kvm/vmx.c              | 22 +++++++++++++++++++++-
 arch/x86/kvm/x86.c              |  8 ++++++++
 4 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index c13cd28d9d1b..57d418061c55 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -713,6 +713,9 @@ struct kvm_vcpu_arch {
 
 	/* be preempted when it's in kernel-mode(cpl=0) */
 	bool preempted_in_kernel;
+
+	/* Flush the L1 Data cache for L1TF mitigation on VMENTER */
+	bool l1tf_flush_l1d;
 };
 
 struct kvm_lpage_info {
@@ -881,6 +884,7 @@ struct kvm_vcpu_stat {
 	u64 signal_exits;
 	u64 irq_window_exits;
 	u64 nmi_window_exits;
+	u64 l1d_flush;
 	u64 halt_exits;
 	u64 halt_successful_poll;
 	u64 halt_attempted_poll;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index d594690d8b95..9beb772b9eb6 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3840,6 +3840,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 {
 	int r = 1;
 
+	vcpu->arch.l1tf_flush_l1d = true;
 	switch (vcpu->arch.apf.host_apf_reason) {
 	default:
 		trace_kvm_page_fault(fault_address, error_code);
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index a1dbc17c7a03..882df9605e42 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9576,9 +9576,20 @@ static int vmx_handle_exit(struct kvm_vcpu *vcpu)
 #define L1D_CACHE_ORDER 4
 static void *vmx_l1d_flush_pages;
 
-static void __maybe_unused vmx_l1d_flush(void)
+static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 {
 	int size = PAGE_SIZE << L1D_CACHE_ORDER;
+	bool always;
+
+	/*
+	 * If the mitigation mode is 'flush always', keep the flush bit
+	 * set, otherwise clear it. It gets set again either from
+	 * vcpu_run() or from one of the unsafe VMEXIT handlers.
+	 */
+	always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+	vcpu->arch.l1tf_flush_l1d = always;
+
+	vcpu->stat.l1d_flush++;
 
 	if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
 		wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
@@ -9847,6 +9858,7 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 			[ss]"i"(__KERNEL_DS),
 			[cs]"i"(__KERNEL_CS)
 			);
+		vcpu->arch.l1tf_flush_l1d = true;
 	}
 }
 STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
@@ -10104,6 +10116,11 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	evmcs_rsp = static_branch_unlikely(&enable_evmcs) ?
 		(unsigned long)&current_evmcs->host_rsp : 0;
 
+	if (static_branch_unlikely(&vmx_l1d_should_flush)) {
+		if (vcpu->arch.l1tf_flush_l1d)
+			vmx_l1d_flush(vcpu);
+	}
+
 	asm(
 		/* Store host registers */
 		"push %%" _ASM_DX "; push %%" _ASM_BP ";"
@@ -11917,6 +11934,9 @@ static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch)
 		return ret;
 	}
 
+	/* Hide L1D cache contents from the nested guest.  */
+	vmx->vcpu.arch.l1tf_flush_l1d = true;
+
 	/*
 	 * If we're entering a halted L2 vcpu and the L2 vcpu won't be woken
 	 * by event injection, halt vcpu.
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 0046aa70205a..902d535dff8f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -195,6 +195,7 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 	{ "irq_injections", VCPU_STAT(irq_injections) },
 	{ "nmi_injections", VCPU_STAT(nmi_injections) },
 	{ "req_event", VCPU_STAT(req_event) },
+	{ "l1d_flush", VCPU_STAT(l1d_flush) },
 	{ "mmu_shadow_zapped", VM_STAT(mmu_shadow_zapped) },
 	{ "mmu_pte_write", VM_STAT(mmu_pte_write) },
 	{ "mmu_pte_updated", VM_STAT(mmu_pte_updated) },
@@ -4874,6 +4875,9 @@ static int emulator_write_std(struct x86_emulate_ctxt *ctxt, gva_t addr, void *v
 int kvm_write_guest_virt_system(struct kvm_vcpu *vcpu, gva_t addr, void *val,
 				unsigned int bytes, struct x86_exception *exception)
 {
+	/* kvm_write_guest_virt_system can pull in tons of pages. */
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	return kvm_write_guest_virt_helper(addr, val, bytes, vcpu,
 					   PFERR_WRITE_MASK, exception);
 }
@@ -6050,6 +6054,8 @@ int x86_emulate_instruction(struct kvm_vcpu *vcpu,
 	bool writeback = true;
 	bool write_fault_to_spt = vcpu->arch.write_fault_to_shadow_pgtable;
 
+	vcpu->arch.l1tf_flush_l1d = true;
+
 	/*
 	 * Clear write_fault_to_shadow_pgtable here to ensure it is
 	 * never reused.
@@ -7579,6 +7585,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 	struct kvm *kvm = vcpu->kvm;
 
 	vcpu->srcu_idx = srcu_read_lock(&kvm->srcu);
+	vcpu->arch.l1tf_flush_l1d = true;
 
 	for (;;) {
 		if (kvm_vcpu_running(vcpu)) {
@@ -8698,6 +8705,7 @@ void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
 
 void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
+	vcpu->arch.l1tf_flush_l1d = true;
 	kvm_x86_ops->sched_in(vcpu, cpu);
 }
 
-- 
cgit v1.2.3


From 33966dd6b2d2c352fae55412db2ea8cfff5df13a Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 20 Jun 2018 13:58:37 -0400
Subject: x86/KVM/VMX: Split the VMX MSR LOAD structures to have an host/guest
 numbers

There is no semantic change but this change allows an unbalanced amount of
MSRs to be loaded on VMEXIT and VMENTER, i.e. the number of MSRs to save or
restore on VMEXIT or VMENTER may be different.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 65 +++++++++++++++++++++++++++++-------------------------
 1 file changed, 35 insertions(+), 30 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 882df9605e42..3425238b0808 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -808,6 +808,11 @@ static inline int pi_test_sn(struct pi_desc *pi_desc)
 			(unsigned long *)&pi_desc->control);
 }
 
+struct vmx_msrs {
+	unsigned int		nr;
+	struct vmx_msr_entry	val[NR_AUTOLOAD_MSRS];
+};
+
 struct vcpu_vmx {
 	struct kvm_vcpu       vcpu;
 	unsigned long         host_rsp;
@@ -841,9 +846,8 @@ struct vcpu_vmx {
 	struct loaded_vmcs   *loaded_vmcs;
 	bool                  __launched; /* temporary, used in vmx_vcpu_run */
 	struct msr_autoload {
-		unsigned nr;
-		struct vmx_msr_entry guest[NR_AUTOLOAD_MSRS];
-		struct vmx_msr_entry host[NR_AUTOLOAD_MSRS];
+		struct vmx_msrs guest;
+		struct vmx_msrs host;
 	} msr_autoload;
 	struct {
 		int           loaded;
@@ -2440,18 +2444,18 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
-
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
+	for (i = 0; i < m->guest.nr; ++i)
+		if (m->guest.val[i].index == msr)
 			break;
 
-	if (i == m->nr)
+	if (i == m->guest.nr)
 		return;
-	--m->nr;
-	m->guest[i] = m->guest[m->nr];
-	m->host[i] = m->host[m->nr];
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+	--m->guest.nr;
+	--m->host.nr;
+	m->guest.val[i] = m->guest.val[m->guest.nr];
+	m->host.val[i] = m->host.val[m->host.nr];
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 }
 
 static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
@@ -2503,24 +2507,25 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	for (i = 0; i < m->nr; ++i)
-		if (m->guest[i].index == msr)
+	for (i = 0; i < m->guest.nr; ++i)
+		if (m->guest.val[i].index == msr)
 			break;
 
 	if (i == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
-	} else if (i == m->nr) {
-		++m->nr;
-		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->nr);
-		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->nr);
+	} else if (i == m->guest.nr) {
+		++m->guest.nr;
+		++m->host.nr;
+		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 	}
 
-	m->guest[i].index = msr;
-	m->guest[i].value = guest_val;
-	m->host[i].index = msr;
-	m->host[i].value = host_val;
+	m->guest.val[i].index = msr;
+	m->guest.val[i].value = guest_val;
+	m->host.val[i].index = msr;
+	m->host.val[i].value = host_val;
 }
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
@@ -6290,9 +6295,9 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, 0);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	if (vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_PAT)
 		vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
@@ -11350,10 +11355,10 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
 	 * Set the MSR load/store lists to match L0's settings.
 	 */
 	vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
+	vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
 
 	set_cr4_guest_host_mask(vmx);
 
@@ -12457,8 +12462,8 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
 	vmx_segment_cache_clear(vmx);
 
 	/* Update any VMCS fields that might have changed while L2 ran */
-	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
-	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
+	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
 	vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
 	if (vmx->hv_deadline_tsc == -1)
 		vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
-- 
cgit v1.2.3


From ca83b4a7f2d068da79a029d323024aa45decb250 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 20 Jun 2018 20:11:39 -0400
Subject: x86/KVM/VMX: Add find_msr() helper function

.. to help find the MSR on either the guest or host MSR list.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 31 ++++++++++++++++++-------------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 3425238b0808..e18805f8ed31 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2421,9 +2421,20 @@ static void clear_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 	vm_exit_controls_clearbit(vmx, exit);
 }
 
+static int find_msr(struct vmx_msrs *m, unsigned int msr)
+{
+	unsigned int i;
+
+	for (i = 0; i < m->nr; ++i) {
+		if (m->val[i].index == msr)
+			return i;
+	}
+	return -ENOENT;
+}
+
 static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 {
-	unsigned i;
+	int i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2444,11 +2455,8 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 		}
 		break;
 	}
-	for (i = 0; i < m->guest.nr; ++i)
-		if (m->guest.val[i].index == msr)
-			break;
-
-	if (i == m->guest.nr)
+	i = find_msr(&m->guest, msr);
+	if (i < 0)
 		return;
 	--m->guest.nr;
 	--m->host.nr;
@@ -2472,7 +2480,7 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 				  u64 guest_val, u64 host_val)
 {
-	unsigned i;
+	int i;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2507,16 +2515,13 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
 	}
 
-	for (i = 0; i < m->guest.nr; ++i)
-		if (m->guest.val[i].index == msr)
-			break;
-
+	i = find_msr(&m->guest, msr);
 	if (i == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
-	} else if (i == m->guest.nr) {
-		++m->guest.nr;
+	} else if (i < 0) {
+		i = m->guest.nr++;
 		++m->host.nr;
 		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
-- 
cgit v1.2.3


From 3190709335dd31fe1aeeebfe4ffb6c7624ef971f Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 20 Jun 2018 22:00:47 -0400
Subject: x86/KVM/VMX: Separate the VMX AUTOLOAD guest/host number accounting

This allows to load a different number of MSRs depending on the context:
VMEXIT or VMENTER.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e18805f8ed31..bde1602a94f5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2457,12 +2457,18 @@ static void clear_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr)
 	}
 	i = find_msr(&m->guest, msr);
 	if (i < 0)
-		return;
+		goto skip_guest;
 	--m->guest.nr;
-	--m->host.nr;
 	m->guest.val[i] = m->guest.val[m->guest.nr];
-	m->host.val[i] = m->host.val[m->host.nr];
 	vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+
+skip_guest:
+	i = find_msr(&m->host, msr);
+	if (i < 0)
+		return;
+
+	--m->host.nr;
+	m->host.val[i] = m->host.val[m->host.nr];
 	vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 }
 
@@ -2480,7 +2486,7 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 				  u64 guest_val, u64 host_val)
 {
-	int i;
+	int i, j;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2516,21 +2522,24 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	}
 
 	i = find_msr(&m->guest, msr);
-	if (i == NR_AUTOLOAD_MSRS) {
+	j = find_msr(&m->host, msr);
+	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
 		return;
-	} else if (i < 0) {
+	}
+	if (i < 0) {
 		i = m->guest.nr++;
-		++m->host.nr;
 		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
+	}
+	if (j < 0) {
+		j = m->host.nr++;
 		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 	}
-
 	m->guest.val[i].index = msr;
 	m->guest.val[i].value = guest_val;
-	m->host.val[i].index = msr;
-	m->host.val[i].value = host_val;
+	m->host.val[j].index = msr;
+	m->host.val[j].value = host_val;
 }
 
 static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
-- 
cgit v1.2.3


From 989e3992d2eca32c3f1404f2bc91acda3aa122d8 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Wed, 20 Jun 2018 22:01:22 -0400
Subject: x86/KVM/VMX: Extend add_atomic_switch_msr() to allow VMENTER only
 MSRs

The IA32_FLUSH_CMD MSR needs only to be written on VMENTER. Extend
add_atomic_switch_msr() with an entry_only parameter to allow storing the
MSR only in the guest (ENTRY) MSR array.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index bde1602a94f5..fd80f93ba98b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2484,9 +2484,9 @@ static void add_atomic_switch_msr_special(struct vcpu_vmx *vmx,
 }
 
 static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
-				  u64 guest_val, u64 host_val)
+				  u64 guest_val, u64 host_val, bool entry_only)
 {
-	int i, j;
+	int i, j = 0;
 	struct msr_autoload *m = &vmx->msr_autoload;
 
 	switch (msr) {
@@ -2522,7 +2522,9 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 	}
 
 	i = find_msr(&m->guest, msr);
-	j = find_msr(&m->host, msr);
+	if (!entry_only)
+		j = find_msr(&m->host, msr);
+
 	if (i == NR_AUTOLOAD_MSRS || j == NR_AUTOLOAD_MSRS) {
 		printk_once(KERN_WARNING "Not enough msr switch entries. "
 				"Can't add msr %x\n", msr);
@@ -2532,12 +2534,16 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
 		i = m->guest.nr++;
 		vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, m->guest.nr);
 	}
+	m->guest.val[i].index = msr;
+	m->guest.val[i].value = guest_val;
+
+	if (entry_only)
+		return;
+
 	if (j < 0) {
 		j = m->host.nr++;
 		vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, m->host.nr);
 	}
-	m->guest.val[i].index = msr;
-	m->guest.val[i].value = guest_val;
 	m->host.val[j].index = msr;
 	m->host.val[j].value = host_val;
 }
@@ -2583,7 +2589,7 @@ static bool update_transition_efer(struct vcpu_vmx *vmx, int efer_offset)
 			guest_efer &= ~EFER_LME;
 		if (guest_efer != host_efer)
 			add_atomic_switch_msr(vmx, MSR_EFER,
-					      guest_efer, host_efer);
+					      guest_efer, host_efer, false);
 		return false;
 	} else {
 		guest_efer &= ~ignore_bits;
@@ -4037,7 +4043,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 		vcpu->arch.ia32_xss = data;
 		if (vcpu->arch.ia32_xss != host_xss)
 			add_atomic_switch_msr(vmx, MSR_IA32_XSS,
-				vcpu->arch.ia32_xss, host_xss);
+				vcpu->arch.ia32_xss, host_xss, false);
 		else
 			clear_atomic_switch_msr(vmx, MSR_IA32_XSS);
 		break;
@@ -10040,7 +10046,7 @@ static void atomic_switch_perf_msrs(struct vcpu_vmx *vmx)
 			clear_atomic_switch_msr(vmx, msrs[i].msr);
 		else
 			add_atomic_switch_msr(vmx, msrs[i].msr, msrs[i].guest,
-					msrs[i].host);
+					msrs[i].host, false);
 }
 
 static void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
-- 
cgit v1.2.3


From 390d975e0c4e60ce70d4157e0dd91ede37824603 Mon Sep 17 00:00:00 2001
From: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Date: Thu, 28 Jun 2018 17:10:36 -0400
Subject: x86/KVM/VMX: Use MSR save list for IA32_FLUSH_CMD if required

If the L1D flush module parameter is set to 'always' and the IA32_FLUSH_CMD
MSR is available, optimize the VMENTER code with the MSR save list.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 42 +++++++++++++++++++++++++++++++++++++-----
 1 file changed, 37 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index fd80f93ba98b..eb7c207a3bc3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6237,6 +6237,16 @@ static void ept_set_mmio_spte_mask(void)
 				   VMX_EPT_MISCONFIG_WX_VALUE);
 }
 
+static bool vmx_l1d_use_msr_save_list(void)
+{
+	if (!enable_ept || !boot_cpu_has_bug(X86_BUG_L1TF) ||
+	    static_cpu_has(X86_FEATURE_HYPERVISOR) ||
+	    !static_cpu_has(X86_FEATURE_FLUSH_L1D))
+		return false;
+
+	return vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+}
+
 #define VMX_XSS_EXIT_BITMAP 0
 /*
  * Sets up the vmcs for emulated real mode.
@@ -6358,6 +6368,12 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
 		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
 	}
+	/*
+	 * If flushing the L1D cache on every VMENTER is enforced and the
+	 * MSR is available, use the MSR save list.
+	 */
+	if (vmx_l1d_use_msr_save_list())
+		add_atomic_switch_msr(vmx, MSR_IA32_FLUSH_CMD, L1D_FLUSH, 0, true);
 }
 
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9607,11 +9623,26 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	bool always;
 
 	/*
-	 * If the mitigation mode is 'flush always', keep the flush bit
-	 * set, otherwise clear it. It gets set again either from
-	 * vcpu_run() or from one of the unsafe VMEXIT handlers.
+	 * This code is only executed when:
+	 * - the flush mode is 'cond'
+	 * - the flush mode is 'always' and the flush MSR is not
+	 *   available
+	 *
+	 * If the CPU has the flush MSR then clear the flush bit because
+	 * 'always' mode is handled via the MSR save list.
+	 *
+	 * If the MSR is not avaibable then act depending on the mitigation
+	 * mode: If 'flush always', keep the flush bit set, otherwise clear
+	 * it.
+	 *
+	 * The flush bit gets set again either from vcpu_run() or from one
+	 * of the unsafe VMEXIT handlers.
 	 */
-	always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+	if (static_cpu_has(X86_FEATURE_FLUSH_L1D))
+		always = false;
+	else
+		always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+
 	vcpu->arch.l1tf_flush_l1d = always;
 
 	vcpu->stat.l1d_flush++;
@@ -13205,7 +13236,8 @@ static int __init vmx_setup_l1d_flush(void)
 	struct page *page;
 
 	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
-	    !boot_cpu_has_bug(X86_BUG_L1TF))
+	    !boot_cpu_has_bug(X86_BUG_L1TF) ||
+	    vmx_l1d_use_msr_save_list())
 		return 0;
 
 	if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
-- 
cgit v1.2.3


From f967db0b9ed44ec3057a28f3b28efc51df51b835 Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hpe.com>
Date: Wed, 27 Jun 2018 08:13:46 -0600
Subject: x86/mm: Disable ioremap free page handling on x86-PAE

ioremap() supports pmd mappings on x86-PAE.  However, kernel's pmd
tables are not shared among processes on x86-PAE.  Therefore, any
update to sync'd pmd entries need re-syncing.  Freeing a pte page
also leads to a vmalloc fault and hits the BUG_ON in vmalloc_sync_one().

Disable free page handling on x86-PAE.  pud_free_pmd_page() and
pmd_free_pte_page() simply return 0 if a given pud/pmd entry is present.
This assures that ioremap() does not update sync'd pmd entries at the
cost of falling back to pte mappings.

Fixes: 28ee90fe6048 ("x86/mm: implement free pmd/pte page interfaces")
Reported-by: Joerg Roedel <joro@8bytes.org>
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: mhocko@suse.com
Cc: akpm@linux-foundation.org
Cc: hpa@zytor.com
Cc: cpandya@codeaurora.org
Cc: linux-mm@kvack.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: stable@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20180627141348.21777-2-toshi.kani@hpe.com
---
 arch/x86/mm/pgtable.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 47b5951e592b..1aeb7a5dbce5 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -719,6 +719,7 @@ int pmd_clear_huge(pmd_t *pmd)
 	return 0;
 }
 
+#ifdef CONFIG_X86_64
 /**
  * pud_free_pmd_page - Clear pud entry and free pmd page.
  * @pud: Pointer to a PUD.
@@ -766,4 +767,22 @@ int pmd_free_pte_page(pmd_t *pmd)
 
 	return 1;
 }
+
+#else /* !CONFIG_X86_64 */
+
+int pud_free_pmd_page(pud_t *pud)
+{
+	return pud_none(*pud);
+}
+
+/*
+ * Disable free page handling on x86-PAE. This assures that ioremap()
+ * does not update sync'd pmd entries. See vmalloc_sync_one().
+ */
+int pmd_free_pte_page(pmd_t *pmd)
+{
+	return pmd_none(*pmd);
+}
+
+#endif /* CONFIG_X86_64 */
 #endif	/* CONFIG_HAVE_ARCH_HUGE_VMAP */
-- 
cgit v1.2.3


From 785a19f9d1dd8a4ab2d0633be4656653bd3de1fc Mon Sep 17 00:00:00 2001
From: Chintan Pandya <cpandya@codeaurora.org>
Date: Wed, 27 Jun 2018 08:13:47 -0600
Subject: ioremap: Update pgtable free interfaces with addr

The following kernel panic was observed on ARM64 platform due to a stale
TLB entry.

 1. ioremap with 4K size, a valid pte page table is set.
 2. iounmap it, its pte entry is set to 0.
 3. ioremap the same address with 2M size, update its pmd entry with
    a new value.
 4. CPU may hit an exception because the old pmd entry is still in TLB,
    which leads to a kernel panic.

Commit b6bdb7517c3d ("mm/vmalloc: add interfaces to free unmapped page
table") has addressed this panic by falling to pte mappings in the above
case on ARM64.

To support pmd mappings in all cases, TLB purge needs to be performed
in this case on ARM64.

Add a new arg, 'addr', to pud_free_pmd_page() and pmd_free_pte_page()
so that TLB purge can be added later in seprate patches.

[toshi.kani@hpe.com: merge changes, rewrite patch description]
Fixes: 28ee90fe6048 ("x86/mm: implement free pmd/pte page interfaces")
Signed-off-by: Chintan Pandya <cpandya@codeaurora.org>
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: mhocko@suse.com
Cc: akpm@linux-foundation.org
Cc: hpa@zytor.com
Cc: linux-mm@kvack.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: Will Deacon <will.deacon@arm.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: stable@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20180627141348.21777-3-toshi.kani@hpe.com
---
 arch/arm64/mm/mmu.c           |  4 ++--
 arch/x86/mm/pgtable.c         | 12 +++++++-----
 include/asm-generic/pgtable.h |  8 ++++----
 lib/ioremap.c                 |  4 ++--
 4 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 493ff75670ff..8ae5d7ae4af3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -977,12 +977,12 @@ int pmd_clear_huge(pmd_t *pmdp)
 	return 1;
 }
 
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return pud_none(*pud);
 }
 
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	return pmd_none(*pmd);
 }
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 1aeb7a5dbce5..fbd14e506758 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -723,11 +723,12 @@ int pmd_clear_huge(pmd_t *pmd)
 /**
  * pud_free_pmd_page - Clear pud entry and free pmd page.
  * @pud: Pointer to a PUD.
+ * @addr: Virtual address associated with pud.
  *
  * Context: The pud range has been unmaped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
  */
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	pmd_t *pmd;
 	int i;
@@ -738,7 +739,7 @@ int pud_free_pmd_page(pud_t *pud)
 	pmd = (pmd_t *)pud_page_vaddr(*pud);
 
 	for (i = 0; i < PTRS_PER_PMD; i++)
-		if (!pmd_free_pte_page(&pmd[i]))
+		if (!pmd_free_pte_page(&pmd[i], addr + (i * PMD_SIZE)))
 			return 0;
 
 	pud_clear(pud);
@@ -750,11 +751,12 @@ int pud_free_pmd_page(pud_t *pud)
 /**
  * pmd_free_pte_page - Clear pmd entry and free pte page.
  * @pmd: Pointer to a PMD.
+ * @addr: Virtual address associated with pmd.
  *
  * Context: The pmd range has been unmaped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
  */
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	pte_t *pte;
 
@@ -770,7 +772,7 @@ int pmd_free_pte_page(pmd_t *pmd)
 
 #else /* !CONFIG_X86_64 */
 
-int pud_free_pmd_page(pud_t *pud)
+int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return pud_none(*pud);
 }
@@ -779,7 +781,7 @@ int pud_free_pmd_page(pud_t *pud)
  * Disable free page handling on x86-PAE. This assures that ioremap()
  * does not update sync'd pmd entries. See vmalloc_sync_one().
  */
-int pmd_free_pte_page(pmd_t *pmd)
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	return pmd_none(*pmd);
 }
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index f59639afaa39..b081794ba135 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1019,8 +1019,8 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot);
 int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot);
 int pud_clear_huge(pud_t *pud);
 int pmd_clear_huge(pmd_t *pmd);
-int pud_free_pmd_page(pud_t *pud);
-int pmd_free_pte_page(pmd_t *pmd);
+int pud_free_pmd_page(pud_t *pud, unsigned long addr);
+int pmd_free_pte_page(pmd_t *pmd, unsigned long addr);
 #else	/* !CONFIG_HAVE_ARCH_HUGE_VMAP */
 static inline int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
 {
@@ -1046,11 +1046,11 @@ static inline int pmd_clear_huge(pmd_t *pmd)
 {
 	return 0;
 }
-static inline int pud_free_pmd_page(pud_t *pud)
+static inline int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
 	return 0;
 }
-static inline int pmd_free_pte_page(pmd_t *pmd)
+static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 {
 	return 0;
 }
diff --git a/lib/ioremap.c b/lib/ioremap.c
index 54e5bbaa3200..517f5853ffed 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -92,7 +92,7 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
 		if (ioremap_pmd_enabled() &&
 		    ((next - addr) == PMD_SIZE) &&
 		    IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
-		    pmd_free_pte_page(pmd)) {
+		    pmd_free_pte_page(pmd, addr)) {
 			if (pmd_set_huge(pmd, phys_addr + addr, prot))
 				continue;
 		}
@@ -119,7 +119,7 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
 		if (ioremap_pud_enabled() &&
 		    ((next - addr) == PUD_SIZE) &&
 		    IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
-		    pud_free_pmd_page(pud)) {
+		    pud_free_pmd_page(pud, addr)) {
 			if (pud_set_huge(pud, phys_addr + addr, prot))
 				continue;
 		}
-- 
cgit v1.2.3


From 5e0fb5df2ee871b841f96f9cb6a7f2784e96aa4e Mon Sep 17 00:00:00 2001
From: Toshi Kani <toshi.kani@hpe.com>
Date: Wed, 27 Jun 2018 08:13:48 -0600
Subject: x86/mm: Add TLB purge to free pmd/pte page interfaces

ioremap() calls pud_free_pmd_page() / pmd_free_pte_page() when it creates
a pud / pmd map.  The following preconditions are met at their entry.
 - All pte entries for a target pud/pmd address range have been cleared.
 - System-wide TLB purges have been peformed for a target pud/pmd address
   range.

The preconditions assure that there is no stale TLB entry for the range.
Speculation may not cache TLB entries since it requires all levels of page
entries, including ptes, to have P & A-bits set for an associated address.
However, speculation may cache pud/pmd entries (paging-structure caches)
when they have P-bit set.

Add a system-wide TLB purge (INVLPG) to a single page after clearing
pud/pmd entry's P-bit.

SDM 4.10.4.1, Operation that Invalidate TLBs and Paging-Structure Caches,
states that:
  INVLPG invalidates all paging-structure caches associated with the
  current PCID regardless of the liner addresses to which they correspond.

Fixes: 28ee90fe6048 ("x86/mm: implement free pmd/pte page interfaces")
Signed-off-by: Toshi Kani <toshi.kani@hpe.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: mhocko@suse.com
Cc: akpm@linux-foundation.org
Cc: hpa@zytor.com
Cc: cpandya@codeaurora.org
Cc: linux-mm@kvack.org
Cc: linux-arm-kernel@lists.infradead.org
Cc: Joerg Roedel <joro@8bytes.org>
Cc: stable@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20180627141348.21777-4-toshi.kani@hpe.com
---
 arch/x86/mm/pgtable.c | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index fbd14e506758..e3deefb891da 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -725,24 +725,44 @@ int pmd_clear_huge(pmd_t *pmd)
  * @pud: Pointer to a PUD.
  * @addr: Virtual address associated with pud.
  *
- * Context: The pud range has been unmaped and TLB purged.
+ * Context: The pud range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
+ *
+ * NOTE: Callers must allow a single page allocation.
  */
 int pud_free_pmd_page(pud_t *pud, unsigned long addr)
 {
-	pmd_t *pmd;
+	pmd_t *pmd, *pmd_sv;
+	pte_t *pte;
 	int i;
 
 	if (pud_none(*pud))
 		return 1;
 
 	pmd = (pmd_t *)pud_page_vaddr(*pud);
+	pmd_sv = (pmd_t *)__get_free_page(GFP_KERNEL);
+	if (!pmd_sv)
+		return 0;
 
-	for (i = 0; i < PTRS_PER_PMD; i++)
-		if (!pmd_free_pte_page(&pmd[i], addr + (i * PMD_SIZE)))
-			return 0;
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd_sv[i] = pmd[i];
+		if (!pmd_none(pmd[i]))
+			pmd_clear(&pmd[i]);
+	}
 
 	pud_clear(pud);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		if (!pmd_none(pmd_sv[i])) {
+			pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
+			free_page((unsigned long)pte);
+		}
+	}
+
+	free_page((unsigned long)pmd_sv);
 	free_page((unsigned long)pmd);
 
 	return 1;
@@ -753,7 +773,7 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
  * @pmd: Pointer to a PMD.
  * @addr: Virtual address associated with pmd.
  *
- * Context: The pmd range has been unmaped and TLB purged.
+ * Context: The pmd range has been unmapped and TLB purged.
  * Return: 1 if clearing the entry succeeded. 0 otherwise.
  */
 int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
@@ -765,6 +785,10 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
 
 	pte = (pte_t *)pmd_page_vaddr(*pmd);
 	pmd_clear(pmd);
+
+	/* INVLPG to clear all paging-structure caches */
+	flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
+
 	free_page((unsigned long)pte);
 
 	return 1;
-- 
cgit v1.2.3


From 0ba7c51a6fd80a89236f6ceb52e63f8a7f62bfd3 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 14 Jun 2018 20:56:25 +0300
Subject: drm/i915: Fix hotplug irq ack on i965/g4x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just like with PIPESTAT, the edge triggered IIR on i965/g4x
also causes problems for hotplug interrupts. To make sure
we don't get the IIR port interrupt bit stuck low with the
ISR bit high we must force an edge in ISR. Unfortunately
we can't borrow the PIPESTAT trick and toggle the enable
bits in PORT_HOTPLUG_EN as that act itself generates hotplug
interrupts. Instead we just have to loop until we've cleared
PORT_HOTPLUG_STAT, or we just give up and WARN.

v2: Don't frob with PORT_HOTPLUG_EN

Cc: stable@vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180614175625.1615-1-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 435a4444314c..c59aa0737079 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -2069,10 +2069,38 @@ static void valleyview_pipestat_irq_handler(struct drm_i915_private *dev_priv,
 
 static u32 i9xx_hpd_irq_ack(struct drm_i915_private *dev_priv)
 {
-	u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+	u32 hotplug_status = 0, hotplug_status_mask;
+	int i;
+
+	if (IS_G4X(dev_priv) ||
+	    IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		hotplug_status_mask = HOTPLUG_INT_STATUS_G4X |
+			DP_AUX_CHANNEL_MASK_INT_STATUS_G4X;
+	else
+		hotplug_status_mask = HOTPLUG_INT_STATUS_I915;
 
-	if (hotplug_status)
+	/*
+	 * We absolutely have to clear all the pending interrupt
+	 * bits in PORT_HOTPLUG_STAT. Otherwise the ISR port
+	 * interrupt bit won't have an edge, and the i965/g4x
+	 * edge triggered IIR will not notice that an interrupt
+	 * is still pending. We can't use PORT_HOTPLUG_EN to
+	 * guarantee the edge as the act of toggling the enable
+	 * bits can itself generate a new hotplug interrupt :(
+	 */
+	for (i = 0; i < 10; i++) {
+		u32 tmp = I915_READ(PORT_HOTPLUG_STAT) & hotplug_status_mask;
+
+		if (tmp == 0)
+			return hotplug_status;
+
+		hotplug_status |= tmp;
 		I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+	}
+
+	WARN_ONCE(1,
+		  "PORT_HOTPLUG_STAT did not clear (0x%08x)\n",
+		  I915_READ(PORT_HOTPLUG_STAT));
 
 	return hotplug_status;
 }
-- 
cgit v1.2.3


From 78c357dd3fcf51de61a0b8db3abdb8ed5aea6dd8 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 11 Jun 2018 23:02:57 +0300
Subject: drm/i915: Fix pre-ILK error interrupt ack
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adjust the EIR clearing to cope with the edge triggered IIR
on i965/g4x. To guarantee an edge in the ISR master error bit
we temporarily mask everything in EMR. As some of the EIR bits
can't even be directly cleared we also borrow a trick from
i915_clear_error_registers() and permanently mask any bit that
remains high. No real thought given to how we might unmask them
again once the cause for the error has been clered. I suppose
on pre-g4x GPU reset will reinitialize EMR from scratch.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611200258.27121-3-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 105 ++++++++++++++++++++++++++++++++++++----
 drivers/gpu/drm/i915/i915_reg.h |   1 -
 2 files changed, 96 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index c59aa0737079..7fb493b7aa74 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -3279,7 +3279,7 @@ static void i915_clear_error_registers(struct drm_i915_private *dev_priv)
 		 */
 		DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masking\n", eir);
 		I915_WRITE(EMR, I915_READ(EMR) | eir);
-		I915_WRITE(IIR, I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		I915_WRITE(IIR, I915_MASTER_ERROR_INTERRUPT);
 	}
 }
 
@@ -4406,6 +4406,81 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 	return 0;
 }
 
+static void i8xx_error_irq_ack(struct drm_i915_private *dev_priv,
+			       u16 *eir, u16 *eir_stuck)
+{
+	u16 emr;
+
+	*eir = I915_READ16(EIR);
+
+	if (*eir)
+		I915_WRITE16(EIR, *eir);
+
+	*eir_stuck = I915_READ16(EIR);
+	if (*eir_stuck == 0)
+		return;
+
+	/*
+	 * Toggle all EMR bits to make sure we get an edge
+	 * in the ISR master error bit if we don't clear
+	 * all the EIR bits. Otherwise the edge triggered
+	 * IIR on i965/g4x wouldn't notice that an interrupt
+	 * is still pending. Also some EIR bits can't be
+	 * cleared except by handling the underlying error
+	 * (or by a GPU reset) so we mask any bit that
+	 * remains set.
+	 */
+	emr = I915_READ16(EMR);
+	I915_WRITE16(EMR, 0xffff);
+	I915_WRITE16(EMR, emr | *eir_stuck);
+}
+
+static void i8xx_error_irq_handler(struct drm_i915_private *dev_priv,
+				   u16 eir, u16 eir_stuck)
+{
+	DRM_DEBUG("Master Error: EIR 0x%04x\n", eir);
+
+	if (eir_stuck)
+		DRM_DEBUG_DRIVER("EIR stuck: 0x%04x, masked\n", eir_stuck);
+}
+
+static void i9xx_error_irq_ack(struct drm_i915_private *dev_priv,
+			       u32 *eir, u32 *eir_stuck)
+{
+	u32 emr;
+
+	*eir = I915_READ(EIR);
+
+	I915_WRITE(EIR, *eir);
+
+	*eir_stuck = I915_READ(EIR);
+	if (*eir_stuck == 0)
+		return;
+
+	/*
+	 * Toggle all EMR bits to make sure we get an edge
+	 * in the ISR master error bit if we don't clear
+	 * all the EIR bits. Otherwise the edge triggered
+	 * IIR on i965/g4x wouldn't notice that an interrupt
+	 * is still pending. Also some EIR bits can't be
+	 * cleared except by handling the underlying error
+	 * (or by a GPU reset) so we mask any bit that
+	 * remains set.
+	 */
+	emr = I915_READ(EMR);
+	I915_WRITE(EMR, 0xffffffff);
+	I915_WRITE(EMR, emr | *eir_stuck);
+}
+
+static void i9xx_error_irq_handler(struct drm_i915_private *dev_priv,
+				   u32 eir, u32 eir_stuck)
+{
+	DRM_DEBUG("Master Error, EIR 0x%08x\n", eir);
+
+	if (eir_stuck)
+		DRM_DEBUG_DRIVER("EIR stuck: 0x%08x, masked\n", eir_stuck);
+}
+
 static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 {
 	struct drm_device *dev = arg;
@@ -4420,6 +4495,7 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u16 eir = 0, eir_stuck = 0;
 		u16 iir;
 
 		iir = I915_READ16(IIR);
@@ -4432,13 +4508,16 @@ static irqreturn_t i8xx_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i8xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE16(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[RCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i8xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		i8xx_pipestat_irq_handler(dev_priv, iir, pipe_stats);
 	} while (0);
@@ -4519,6 +4598,7 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u32 eir = 0, eir_stuck = 0;
 		u32 hotplug_status = 0;
 		u32 iir;
 
@@ -4536,13 +4616,16 @@ static irqreturn_t i915_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[RCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		if (hotplug_status)
 			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
@@ -4596,14 +4679,14 @@ static int i965_irq_postinstall(struct drm_device *dev)
 		  I915_DISPLAY_PORT_INTERRUPT |
 		  I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		  I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT);
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_ASLE_INTERRUPT |
 		I915_DISPLAY_PORT_INTERRUPT |
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
-		I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	if (IS_G4X(dev_priv))
@@ -4663,6 +4746,7 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 
 	do {
 		u32 pipe_stats[I915_MAX_PIPES] = {};
+		u32 eir = 0, eir_stuck = 0;
 		u32 hotplug_status = 0;
 		u32 iir;
 
@@ -4679,6 +4763,9 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		 * signalled in iir */
 		i9xx_pipestat_irq_ack(dev_priv, iir, pipe_stats);
 
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_ack(dev_priv, &eir, &eir_stuck);
+
 		I915_WRITE(IIR, iir);
 
 		if (iir & I915_USER_INTERRUPT)
@@ -4687,8 +4774,8 @@ static irqreturn_t i965_irq_handler(int irq, void *arg)
 		if (iir & I915_BSD_USER_INTERRUPT)
 			notify_ring(dev_priv->engine[VCS]);
 
-		if (iir & I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT)
-			DRM_DEBUG("Command parser error, iir 0x%08x\n", iir);
+		if (iir & I915_MASTER_ERROR_INTERRUPT)
+			i9xx_error_irq_handler(dev_priv, eir, eir_stuck);
 
 		if (hotplug_status)
 			i9xx_hpd_irq_handler(dev_priv, hotplug_status);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 69b9978d7dda..097000520a80 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2871,7 +2871,6 @@ enum i915_power_well_id {
 #define I915_DISPLAY_PORT_INTERRUPT			(1 << 17)
 #define I915_DISPLAY_PIPE_C_HBLANK_INTERRUPT		(1 << 16)
 #define I915_MASTER_ERROR_INTERRUPT			(1 << 15)
-#define I915_RENDER_COMMAND_PARSER_ERROR_INTERRUPT	(1 << 15)
 #define I915_DISPLAY_PIPE_B_HBLANK_INTERRUPT		(1 << 14)
 #define I915_GMCH_THERMAL_SENSOR_EVENT_INTERRUPT	(1 << 14) /* p-state */
 #define I915_DISPLAY_PIPE_A_HBLANK_INTERRUPT		(1 << 13)
-- 
cgit v1.2.3


From 16659bc53a027f8e4bce6393476849e2bda8b8fa Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 11 Jun 2018 23:02:58 +0300
Subject: drm/i915: Unmask and enable master error interrupt on gen2/3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For whatever reason we only unmask and enable the master error
interrut on gen4. With the EIR handling fixed let's do that
on gen2/3 as well.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180611200258.27121-4-ville.syrjala@linux.intel.com
Reviewed-by: Imre Deak <imre.deak@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 7fb493b7aa74..2fcc00b06915 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -4387,11 +4387,13 @@ static int i8xx_irq_postinstall(struct drm_device *dev)
 	/* Unmask the interrupts that we always want on. */
 	dev_priv->irq_mask =
 		~(I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	GEN2_IRQ_INIT(, dev_priv->irq_mask, enable_mask);
@@ -4555,12 +4557,14 @@ static int i915_irq_postinstall(struct drm_device *dev)
 	dev_priv->irq_mask =
 		~(I915_ASLE_INTERRUPT |
 		  I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
-		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT);
+		  I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		  I915_MASTER_ERROR_INTERRUPT);
 
 	enable_mask =
 		I915_ASLE_INTERRUPT |
 		I915_DISPLAY_PIPE_A_EVENT_INTERRUPT |
 		I915_DISPLAY_PIPE_B_EVENT_INTERRUPT |
+		I915_MASTER_ERROR_INTERRUPT |
 		I915_USER_INTERRUPT;
 
 	if (I915_HAS_HOTPLUG(dev_priv)) {
-- 
cgit v1.2.3


From 63fd659fb1a52262a37293a9a034a912a2406b26 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 4 Jul 2018 19:55:18 +0100
Subject: drm/i915/gtt: Pull global wc page stash under its own locking

Currently, the wc-stash used for providing flushed WC pages ready for
constructing the page directories is assumed to be protected by the
struct_mutex. However, we want to remove this global lock and so must
install a replacement global lock for accessing the global wc-stash (the
per-vm stash continues to be guarded by the vm).

We need to push ahead on this patch due to an oversight in hastily
removing the struct_mutex guard around the igt_ppgtt_alloc selftest. No
matter, it will prove very useful (i.e. will be required) in the near
future.

v2: Restore the onstack stash so that we can drop the vm->mutex in
future across the allocation.
v3: Restore the lost pagevec_init of the onstack allocation, and repaint
function names.
v4: Reorder init so that we don't try and use i915_address_space before
it is ininitialised.

Fixes: 1f6f00238abf ("drm/i915/selftests: Drop struct_mutex around lowlevel pggtt allocation")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180704185518.4193-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.h               |   2 +-
 drivers/gpu/drm/i915/i915_gem_context.c       |   2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c           | 210 ++++++++++++++++----------
 drivers/gpu/drm/i915/i915_gem_gtt.h           |  10 +-
 drivers/gpu/drm/i915/selftests/huge_pages.c   |   2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c |   2 +-
 drivers/gpu/drm/i915/selftests/mock_gtt.c     |   2 +-
 7 files changed, 144 insertions(+), 86 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ce7d06332884..4f9191ab3e12 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -952,7 +952,7 @@ struct i915_gem_mm {
 	/**
 	 * Small stash of WC pages
 	 */
-	struct pagevec wc_stash;
+	struct pagestash wc_stash;
 
 	/**
 	 * tmpfs instance used for shmem backed objects
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index ccf463ab6562..985ef70d9416 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -374,7 +374,7 @@ i915_gem_create_context(struct drm_i915_private *dev_priv,
 	if (USES_FULL_PPGTT(dev_priv)) {
 		struct i915_hw_ppgtt *ppgtt;
 
-		ppgtt = i915_ppgtt_create(dev_priv, file_priv, ctx->name);
+		ppgtt = i915_ppgtt_create(dev_priv, file_priv);
 		if (IS_ERR(ppgtt)) {
 			DRM_DEBUG_DRIVER("PPGTT setup failed (%ld)\n",
 					 PTR_ERR(ppgtt));
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index ba1aed07d6dc..5fb299590579 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -375,37 +375,70 @@ static gen6_pte_t iris_pte_encode(dma_addr_t addr,
 	return pte;
 }
 
+static void stash_init(struct pagestash *stash)
+{
+	pagevec_init(&stash->pvec);
+	spin_lock_init(&stash->lock);
+}
+
+static struct page *stash_pop_page(struct pagestash *stash)
+{
+	struct page *page = NULL;
+
+	spin_lock(&stash->lock);
+	if (likely(stash->pvec.nr))
+		page = stash->pvec.pages[--stash->pvec.nr];
+	spin_unlock(&stash->lock);
+
+	return page;
+}
+
+static void stash_push_pagevec(struct pagestash *stash, struct pagevec *pvec)
+{
+	int nr;
+
+	spin_lock_nested(&stash->lock, SINGLE_DEPTH_NESTING);
+
+	nr = min_t(int, pvec->nr, pagevec_space(&stash->pvec));
+	memcpy(stash->pvec.pages + stash->pvec.nr,
+	       pvec->pages + pvec->nr - nr,
+	       sizeof(pvec->pages[0]) * nr);
+	stash->pvec.nr += nr;
+
+	spin_unlock(&stash->lock);
+
+	pvec->nr -= nr;
+}
+
 static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 {
-	struct pagevec *pvec = &vm->free_pages;
-	struct pagevec stash;
+	struct pagevec stack;
+	struct page *page;
 
 	if (I915_SELFTEST_ONLY(should_fail(&vm->fault_attr, 1)))
 		i915_gem_shrink_all(vm->i915);
 
-	if (likely(pvec->nr))
-		return pvec->pages[--pvec->nr];
+	page = stash_pop_page(&vm->free_pages);
+	if (page)
+		return page;
 
 	if (!vm->pt_kmap_wc)
 		return alloc_page(gfp);
 
-	/* A placeholder for a specific mutex to guard the WC stash */
-	lockdep_assert_held(&vm->i915->drm.struct_mutex);
-
 	/* Look in our global stash of WC pages... */
-	pvec = &vm->i915->mm.wc_stash;
-	if (likely(pvec->nr))
-		return pvec->pages[--pvec->nr];
+	page = stash_pop_page(&vm->i915->mm.wc_stash);
+	if (page)
+		return page;
 
 	/*
-	 * Otherwise batch allocate pages to amoritize cost of set_pages_wc.
+	 * Otherwise batch allocate pages to amortize cost of set_pages_wc.
 	 *
 	 * We have to be careful as page allocation may trigger the shrinker
 	 * (via direct reclaim) which will fill up the WC stash underneath us.
 	 * So we add our WB pages into a temporary pvec on the stack and merge
 	 * them into the WC stash after all the allocations are complete.
 	 */
-	pagevec_init(&stash);
+	pagevec_init(&stack);
 	do {
 		struct page *page;
 
@@ -413,59 +446,67 @@ static struct page *vm_alloc_page(struct i915_address_space *vm, gfp_t gfp)
 		if (unlikely(!page))
 			break;
 
-		stash.pages[stash.nr++] = page;
-	} while (stash.nr < pagevec_space(pvec));
+		stack.pages[stack.nr++] = page;
+	} while (pagevec_space(&stack));
 
-	if (stash.nr) {
-		int nr = min_t(int, stash.nr, pagevec_space(pvec));
-		struct page **pages = stash.pages + stash.nr - nr;
+	if (stack.nr && !set_pages_array_wc(stack.pages, stack.nr)) {
+		page = stack.pages[--stack.nr];
 
-		if (nr && !set_pages_array_wc(pages, nr)) {
-			memcpy(pvec->pages + pvec->nr,
-			       pages, sizeof(pages[0]) * nr);
-			pvec->nr += nr;
-			stash.nr -= nr;
-		}
+		/* Merge spare WC pages to the global stash */
+		stash_push_pagevec(&vm->i915->mm.wc_stash, &stack);
+
+		/* Push any surplus WC pages onto the local VM stash */
+		if (stack.nr)
+			stash_push_pagevec(&vm->free_pages, &stack);
+	}
 
-		pagevec_release(&stash);
+	/* Return unwanted leftovers */
+	if (unlikely(stack.nr)) {
+		WARN_ON_ONCE(set_pages_array_wb(stack.pages, stack.nr));
+		__pagevec_release(&stack);
 	}
 
-	return likely(pvec->nr) ? pvec->pages[--pvec->nr] : NULL;
+	return page;
 }
 
 static void vm_free_pages_release(struct i915_address_space *vm,
 				  bool immediate)
 {
-	struct pagevec *pvec = &vm->free_pages;
+	struct pagevec *pvec = &vm->free_pages.pvec;
+	struct pagevec stack;
 
+	lockdep_assert_held(&vm->free_pages.lock);
 	GEM_BUG_ON(!pagevec_count(pvec));
 
 	if (vm->pt_kmap_wc) {
-		struct pagevec *stash = &vm->i915->mm.wc_stash;
-
-		/* When we use WC, first fill up the global stash and then
+		/*
+		 * When we use WC, first fill up the global stash and then
 		 * only if full immediately free the overflow.
 		 */
+		stash_push_pagevec(&vm->i915->mm.wc_stash, pvec);
 
-		lockdep_assert_held(&vm->i915->drm.struct_mutex);
-		if (pagevec_space(stash)) {
-			do {
-				stash->pages[stash->nr++] =
-					pvec->pages[--pvec->nr];
-				if (!pvec->nr)
-					return;
-			} while (pagevec_space(stash));
-
-			/* As we have made some room in the VM's free_pages,
-			 * we can wait for it to fill again. Unless we are
-			 * inside i915_address_space_fini() and must
-			 * immediately release the pages!
-			 */
-			if (!immediate)
-				return;
-		}
+		/*
+		 * As we have made some room in the VM's free_pages,
+		 * we can wait for it to fill again. Unless we are
+		 * inside i915_address_space_fini() and must
+		 * immediately release the pages!
+		 */
+		if (pvec->nr <= (immediate ? 0 : PAGEVEC_SIZE - 1))
+			return;
 
+		/*
+		 * We have to drop the lock to allow ourselves to sleep,
+		 * so take a copy of the pvec and clear the stash for
+		 * others to use it as we sleep.
+		 */
+		stack = *pvec;
+		pagevec_reinit(pvec);
+		spin_unlock(&vm->free_pages.lock);
+
+		pvec = &stack;
 		set_pages_array_wb(pvec->pages, pvec->nr);
+
+		spin_lock(&vm->free_pages.lock);
 	}
 
 	__pagevec_release(pvec);
@@ -481,8 +522,38 @@ static void vm_free_page(struct i915_address_space *vm, struct page *page)
 	 * unconditional might_sleep() for everybody.
 	 */
 	might_sleep();
-	if (!pagevec_add(&vm->free_pages, page))
+	spin_lock(&vm->free_pages.lock);
+	if (!pagevec_add(&vm->free_pages.pvec, page))
 		vm_free_pages_release(vm, false);
+	spin_unlock(&vm->free_pages.lock);
+}
+
+static void i915_address_space_init(struct i915_address_space *vm,
+				    struct drm_i915_private *dev_priv)
+{
+	GEM_BUG_ON(!vm->total);
+	drm_mm_init(&vm->mm, 0, vm->total);
+	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
+
+	stash_init(&vm->free_pages);
+
+	INIT_LIST_HEAD(&vm->active_list);
+	INIT_LIST_HEAD(&vm->inactive_list);
+	INIT_LIST_HEAD(&vm->unbound_list);
+
+	list_add_tail(&vm->global_link, &dev_priv->vm_list);
+}
+
+static void i915_address_space_fini(struct i915_address_space *vm)
+{
+	spin_lock(&vm->free_pages.lock);
+	if (pagevec_count(&vm->free_pages.pvec))
+		vm_free_pages_release(vm, true);
+	GEM_BUG_ON(pagevec_count(&vm->free_pages.pvec));
+	spin_unlock(&vm->free_pages.lock);
+
+	drm_mm_takedown(&vm->mm);
+	list_del(&vm->global_link);
 }
 
 static int __setup_page_dma(struct i915_address_space *vm,
@@ -1562,6 +1633,8 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 	if (!ppgtt)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&ppgtt->ref);
+
 	ppgtt->vm.i915 = i915;
 	ppgtt->vm.dma = &i915->drm.pdev->dev;
 
@@ -1569,6 +1642,8 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 		1ULL << 48 :
 		1ULL << 32;
 
+	i915_address_space_init(&ppgtt->vm, i915);
+
 	/* There are only few exceptions for gen >=6. chv and bxt.
 	 * And we are not sure about the latter so play safe for now.
 	 */
@@ -2068,11 +2143,15 @@ static struct i915_hw_ppgtt *gen6_ppgtt_create(struct drm_i915_private *i915)
 	if (!ppgtt)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&ppgtt->base.ref);
+
 	ppgtt->base.vm.i915 = i915;
 	ppgtt->base.vm.dma = &i915->drm.pdev->dev;
 
 	ppgtt->base.vm.total = I915_PDES * GEN6_PTES * PAGE_SIZE;
 
+	i915_address_space_init(&ppgtt->base.vm, i915);
+
 	ppgtt->base.vm.allocate_va_range = gen6_alloc_va_range;
 	ppgtt->base.vm.clear_range = gen6_ppgtt_clear_range;
 	ppgtt->base.vm.insert_entries = gen6_ppgtt_insert_entries;
@@ -2105,30 +2184,6 @@ err_free:
 	return ERR_PTR(err);
 }
 
-static void i915_address_space_init(struct i915_address_space *vm,
-				    struct drm_i915_private *dev_priv,
-				    const char *name)
-{
-	drm_mm_init(&vm->mm, 0, vm->total);
-	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
-
-	INIT_LIST_HEAD(&vm->active_list);
-	INIT_LIST_HEAD(&vm->inactive_list);
-	INIT_LIST_HEAD(&vm->unbound_list);
-
-	list_add_tail(&vm->global_link, &dev_priv->vm_list);
-	pagevec_init(&vm->free_pages);
-}
-
-static void i915_address_space_fini(struct i915_address_space *vm)
-{
-	if (pagevec_count(&vm->free_pages))
-		vm_free_pages_release(vm, true);
-
-	drm_mm_takedown(&vm->mm);
-	list_del(&vm->global_link);
-}
-
 static void gtt_write_workarounds(struct drm_i915_private *dev_priv)
 {
 	/* This function is for gtt related workarounds. This function is
@@ -2199,8 +2254,7 @@ __hw_ppgtt_create(struct drm_i915_private *i915)
 
 struct i915_hw_ppgtt *
 i915_ppgtt_create(struct drm_i915_private *i915,
-		  struct drm_i915_file_private *fpriv,
-		  const char *name)
+		  struct drm_i915_file_private *fpriv)
 {
 	struct i915_hw_ppgtt *ppgtt;
 
@@ -2208,8 +2262,6 @@ i915_ppgtt_create(struct drm_i915_private *i915,
 	if (IS_ERR(ppgtt))
 		return ppgtt;
 
-	kref_init(&ppgtt->ref);
-	i915_address_space_init(&ppgtt->vm, i915, name);
 	ppgtt->vm.file = fpriv;
 
 	trace_i915_ppgtt_create(&ppgtt->vm);
@@ -2788,7 +2840,7 @@ int i915_gem_init_aliasing_ppgtt(struct drm_i915_private *i915)
 	struct i915_hw_ppgtt *ppgtt;
 	int err;
 
-	ppgtt = i915_ppgtt_create(i915, ERR_PTR(-EPERM), "[alias]");
+	ppgtt = i915_ppgtt_create(i915, ERR_PTR(-EPERM));
 	if (IS_ERR(ppgtt))
 		return PTR_ERR(ppgtt);
 
@@ -2918,7 +2970,7 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv)
 
 	ggtt->vm.cleanup(&ggtt->vm);
 
-	pvec = &dev_priv->mm.wc_stash;
+	pvec = &dev_priv->mm.wc_stash.pvec;
 	if (pvec->nr) {
 		set_pages_array_wb(pvec->pages, pvec->nr);
 		__pagevec_release(pvec);
@@ -3518,6 +3570,8 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 	int ret;
 
+	stash_init(&dev_priv->mm.wc_stash);
+
 	INIT_LIST_HEAD(&dev_priv->vm_list);
 
 	/* Note that we use page colouring to enforce a guard page at the
@@ -3526,7 +3580,7 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	 * and beyond the end of the GTT if we do not provide a guard.
 	 */
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	i915_address_space_init(&ggtt->vm, dev_priv, "[global]");
+	i915_address_space_init(&ggtt->vm, dev_priv);
 	if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv))
 		ggtt->vm.mm.color_adjust = i915_gtt_color_adjust;
 	mutex_unlock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 9a4824cae68d..f298e72b79ca 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -270,6 +270,11 @@ struct i915_vma_ops {
 	void (*clear_pages)(struct i915_vma *vma);
 };
 
+struct pagestash {
+	spinlock_t lock;
+	struct pagevec pvec;
+};
+
 struct i915_address_space {
 	struct drm_mm mm;
 	struct drm_i915_private *i915;
@@ -324,7 +329,7 @@ struct i915_address_space {
 	 */
 	struct list_head unbound_list;
 
-	struct pagevec free_pages;
+	struct pagestash free_pages;
 	bool pt_kmap_wc;
 
 	/* FIXME: Need a more generic return type */
@@ -615,8 +620,7 @@ void i915_ggtt_cleanup_hw(struct drm_i915_private *dev_priv);
 int i915_ppgtt_init_hw(struct drm_i915_private *dev_priv);
 void i915_ppgtt_release(struct kref *kref);
 struct i915_hw_ppgtt *i915_ppgtt_create(struct drm_i915_private *dev_priv,
-					struct drm_i915_file_private *fpriv,
-					const char *name);
+					struct drm_i915_file_private *fpriv);
 void i915_ppgtt_close(struct i915_address_space *vm);
 static inline void i915_ppgtt_get(struct i915_hw_ppgtt *ppgtt)
 {
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index b5e87fcdcdae..39699939587d 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -1694,7 +1694,7 @@ int i915_gem_huge_page_mock_selftests(void)
 	dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(39));
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ppgtt = i915_ppgtt_create(dev_priv, ERR_PTR(-ENODEV), "mock");
+	ppgtt = i915_ppgtt_create(dev_priv, ERR_PTR(-ENODEV));
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index a7956ecc3e1f..4bfb0537f9be 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1004,7 +1004,7 @@ static int exercise_ppgtt(struct drm_i915_private *dev_priv,
 		return PTR_ERR(file);
 
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ppgtt = i915_ppgtt_create(dev_priv, file->driver_priv, "mock");
+	ppgtt = i915_ppgtt_create(dev_priv, file->driver_priv);
 	if (IS_ERR(ppgtt)) {
 		err = PTR_ERR(ppgtt);
 		goto out_unlock;
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 6a7f4da7b523..0da5b8c6d912 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -124,7 +124,7 @@ void mock_init_ggtt(struct drm_i915_private *i915)
 	ggtt->vm.vma_ops.set_pages   = ggtt_set_pages;
 	ggtt->vm.vma_ops.clear_pages = clear_pages;
 
-	i915_address_space_init(&ggtt->vm, i915, "global");
+	i915_address_space_init(&ggtt->vm, i915);
 }
 
 void mock_fini_ggtt(struct drm_i915_private *i915)
-- 
cgit v1.2.3


From 03f8c41c73da849ec2b73aa678ce6380e8318920 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 21 Jun 2018 07:22:12 -0500
Subject: gfs2: Stop messing with ip->i_rgd in the rlist code

In the resource group list code, keep the last resource group added in
the last position in the array.  Check against that instead of messing
with ip->i_rgd.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/rgrp.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 7a001f6e8aee..ecdc4cb5b6ad 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -2559,19 +2559,35 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
 	if (gfs2_assert_warn(sdp, !rlist->rl_ghs))
 		return;
 
-	if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, block))
-		rgd = ip->i_rgd;
-	else
+	/*
+	 * The resource group last accessed is kept in the last position.
+	 */
+
+	if (rlist->rl_rgrps) {
+		rgd = rlist->rl_rgd[rlist->rl_rgrps - 1];
+		if (rgrp_contains_block(rgd, block))
+			return;
 		rgd = gfs2_blk2rgrpd(sdp, block, 1);
+	} else {
+		rgd = ip->i_rgd;
+		if (!rgd || !rgrp_contains_block(rgd, block))
+			rgd = gfs2_blk2rgrpd(sdp, block, 1);
+	}
+
 	if (!rgd) {
-		fs_err(sdp, "rlist_add: no rgrp for block %llu\n", (unsigned long long)block);
+		fs_err(sdp, "rlist_add: no rgrp for block %llu\n",
+		       (unsigned long long)block);
 		return;
 	}
 	ip->i_rgd = rgd;
 
-	for (x = 0; x < rlist->rl_rgrps; x++)
-		if (rlist->rl_rgd[x] == rgd)
+	for (x = 0; x < rlist->rl_rgrps; x++) {
+		if (rlist->rl_rgd[x] == rgd) {
+			swap(rlist->rl_rgd[x],
+			     rlist->rl_rgd[rlist->rl_rgrps - 1]);
 			return;
+		}
+	}
 
 	if (rlist->rl_rgrps == rlist->rl_space) {
 		new_space = rlist->rl_space + 10;
-- 
cgit v1.2.3


From 0eaec62a91ed9d5694b7e2bff30a1b1ad7107be7 Mon Sep 17 00:00:00 2001
From: Casey Leedom <leedom@chelsio.com>
Date: Wed, 4 Jul 2018 15:12:56 +0530
Subject: cxgb4: Add support to read actual provisioned resources

In highly constrained resources environments (like the 124VF
T5 and 248VF T6 configurations), PF4 may not have very many
resources at all and we need to adapt to whatever we've been
allocated, this patch adds support to get the provisioned
resources.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h         |  17 +++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c |  39 ++++++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c    | 134 +++++++++++++++------
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c         |  51 ++++++++
 4 files changed, 206 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 4a8cbd864ef7..3da9299cd786 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -320,6 +320,21 @@ struct vpd_params {
 	u8 na[MACADDR_LEN + 1];
 };
 
+/* Maximum resources provisioned for a PCI PF.
+ */
+struct pf_resources {
+	unsigned int nvi;		/* N virtual interfaces */
+	unsigned int neq;		/* N egress Qs */
+	unsigned int nethctrl;		/* N egress ETH or CTRL Qs */
+	unsigned int niqflint;		/* N ingress Qs/w free list(s) & intr */
+	unsigned int niq;		/* N ingress Qs */
+	unsigned int tc;		/* PCI-E traffic class */
+	unsigned int pmask;		/* port access rights mask */
+	unsigned int nexactf;		/* N exact MPS filters */
+	unsigned int r_caps;		/* read capabilities */
+	unsigned int wx_caps;		/* write/execute capabilities */
+};
+
 struct pci_params {
 	unsigned int vpd_cap_addr;
 	unsigned char speed;
@@ -347,6 +362,7 @@ struct adapter_params {
 	struct sge_params sge;
 	struct tp_params  tp;
 	struct vpd_params vpd;
+	struct pf_resources pfres;
 	struct pci_params pci;
 	struct devlog_params devlog;
 	enum pcie_memwin drv_memwin;
@@ -1568,6 +1584,7 @@ int t4_eeprom_ptov(unsigned int phys_addr, unsigned int fn, unsigned int sz);
 int t4_seeprom_wp(struct adapter *adapter, bool enable);
 int t4_get_raw_vpd_params(struct adapter *adapter, struct vpd_params *p);
 int t4_get_vpd_params(struct adapter *adapter, struct vpd_params *p);
+int t4_get_pfres(struct adapter *adapter);
 int t4_read_flash(struct adapter *adapter, unsigned int addr,
 		  unsigned int nwords, u32 *data, int byte_oriented);
 int t4_load_fw(struct adapter *adapter, const u8 *fw_data, unsigned int size);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index c301aaf79d64..516c883e1613 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2414,6 +2414,44 @@ static const struct file_operations rss_vf_config_debugfs_fops = {
 	.release = seq_release_private
 };
 
+static int resources_show(struct seq_file *seq, void *v)
+{
+	struct adapter *adapter = seq->private;
+	struct pf_resources *pfres = &adapter->params.pfres;
+
+	#define S(desc, fmt, var) \
+		seq_printf(seq, "%-60s " fmt "\n", \
+			   desc " (" #var "):", pfres->var)
+
+	S("Virtual Interfaces", "%d", nvi);
+	S("Egress Queues", "%d", neq);
+	S("Ethernet Control", "%d", nethctrl);
+	S("Ingress Queues/w Free Lists/Interrupts", "%d", niqflint);
+	S("Ingress Queues", "%d", niq);
+	S("Traffic Class", "%d", tc);
+	S("Port Access Rights Mask", "%#x", pmask);
+	S("MAC Address Filters", "%d", nexactf);
+	S("Firmware Command Read Capabilities", "%#x", r_caps);
+	S("Firmware Command Write/Execute Capabilities", "%#x", wx_caps);
+
+	#undef S
+
+	return 0;
+}
+
+static int resources_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, resources_show, inode->i_private);
+}
+
+static const struct file_operations resources_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = resources_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
 /**
  * ethqset2pinfo - return port_info of an Ethernet Queue Set
  * @adap: the adapter
@@ -2973,6 +3011,7 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "rss_key", &rss_key_debugfs_fops, 0400, 0 },
 		{ "rss_pf_config", &rss_pf_config_debugfs_fops, 0400, 0 },
 		{ "rss_vf_config", &rss_vf_config_debugfs_fops, 0400, 0 },
+		{ "resources", &resources_debugfs_fops, 0400, 0 },
 		{ "sge_qinfo", &sge_qinfo_debugfs_fops, 0400, 0 },
 		{ "ibq_tp0",  &cim_ibq_fops, 0400, 0 },
 		{ "ibq_tp1",  &cim_ibq_fops, 0400, 1 },
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 1c0374cbb890..96fcbd1c33a3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -924,6 +924,7 @@ static int setup_sge_queues(struct adapter *adap)
 		     QUEUENUMBER_V(s->ethrxq[0].rspq.abs_id));
 	return 0;
 freeout:
+	dev_err(adap->pdev_dev, "Can't allocate queues, err=%d\n", -err);
 	t4_free_sge_resources(adap);
 	return err;
 }
@@ -3536,6 +3537,16 @@ static int adap_init1(struct adapter *adap, struct fw_caps_config_cmd *c)
 	u32 v;
 	int ret;
 
+	/* Now that we've successfully configured and initialized the adapter
+	 * can ask the Firmware what resources it has provisioned for us.
+	 */
+	ret = t4_get_pfres(adap);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Unable to retrieve resource provisioning information\n");
+		return ret;
+	}
+
 	/* get device capabilities */
 	memset(c, 0, sizeof(*c));
 	c->op_to_write = htonl(FW_CMD_OP_V(FW_CAPS_CONFIG_CMD) |
@@ -4170,32 +4181,6 @@ static int adap_init0(struct adapter *adap)
 			goto bye;
 	}
 
-	/*
-	 * Grab VPD parameters.  This should be done after we establish a
-	 * connection to the firmware since some of the VPD parameters
-	 * (notably the Core Clock frequency) are retrieved via requests to
-	 * the firmware.  On the other hand, we need these fairly early on
-	 * so we do this right after getting ahold of the firmware.
-	 */
-	ret = t4_get_vpd_params(adap, &adap->params.vpd);
-	if (ret < 0)
-		goto bye;
-
-	/*
-	 * Find out what ports are available to us.  Note that we need to do
-	 * this before calling adap_init0_no_config() since it needs nports
-	 * and portvec ...
-	 */
-	v =
-	    FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
-	    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
-	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
-	if (ret < 0)
-		goto bye;
-
-	adap->params.nports = hweight32(port_vec);
-	adap->params.portvec = port_vec;
-
 	/* If the firmware is initialized already, emit a simply note to that
 	 * effect. Otherwise, it's time to try initializing the adapter.
 	 */
@@ -4246,6 +4231,45 @@ static int adap_init0(struct adapter *adap)
 		}
 	}
 
+	/* Now that we've successfully configured and initialized the adapter
+	 * (or found it already initialized), we can ask the Firmware what
+	 * resources it has provisioned for us.
+	 */
+	ret = t4_get_pfres(adap);
+	if (ret) {
+		dev_err(adap->pdev_dev,
+			"Unable to retrieve resource provisioning information\n");
+		goto bye;
+	}
+
+	/* Grab VPD parameters.  This should be done after we establish a
+	 * connection to the firmware since some of the VPD parameters
+	 * (notably the Core Clock frequency) are retrieved via requests to
+	 * the firmware.  On the other hand, we need these fairly early on
+	 * so we do this right after getting ahold of the firmware.
+	 *
+	 * We need to do this after initializing the adapter because someone
+	 * could have FLASHed a new VPD which won't be read by the firmware
+	 * until we do the RESET ...
+	 */
+	ret = t4_get_vpd_params(adap, &adap->params.vpd);
+	if (ret < 0)
+		goto bye;
+
+	/* Find out what ports are available to us.  Note that we need to do
+	 * this before calling adap_init0_no_config() since it needs nports
+	 * and portvec ...
+	 */
+	v =
+	    FW_PARAMS_MNEM_V(FW_PARAMS_MNEM_DEV) |
+	    FW_PARAMS_PARAM_X_V(FW_PARAMS_PARAM_DEV_PORTVEC);
+	ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 1, &v, &port_vec);
+	if (ret < 0)
+		goto bye;
+
+	adap->params.nports = hweight32(port_vec);
+	adap->params.portvec = port_vec;
+
 	/* Give the SGE code a chance to pull in anything that it needs ...
 	 * Note that this must be called after we retrieve our VPD parameters
 	 * in order to know how to convert core ticks to seconds, etc.
@@ -4797,10 +4821,12 @@ static inline bool is_x_10g_port(const struct link_config *lc)
  * of ports we found and the number of available CPUs.  Most settings can be
  * modified by the admin prior to actual use.
  */
-static void cfg_queues(struct adapter *adap)
+static int cfg_queues(struct adapter *adap)
 {
 	struct sge *s = &adap->sge;
-	int i = 0, n10g = 0, qidx = 0;
+	int i, n10g = 0, qidx = 0;
+	int niqflint, neq, avail_eth_qsets;
+	int max_eth_qsets = 32;
 #ifndef CONFIG_CHELSIO_T4_DCB
 	int q10g = 0;
 #endif
@@ -4812,16 +4838,46 @@ static void cfg_queues(struct adapter *adap)
 		adap->params.crypto = 0;
 	}
 
-	n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
+	/* Calculate the number of Ethernet Queue Sets available based on
+	 * resources provisioned for us.  We always have an Asynchronous
+	 * Firmware Event Ingress Queue.  If we're operating in MSI or Legacy
+	 * IRQ Pin Interrupt mode, then we'll also have a Forwarded Interrupt
+	 * Ingress Queue.  Meanwhile, we need two Egress Queues for each
+	 * Queue Set: one for the Free List and one for the Ethernet TX Queue.
+	 *
+	 * Note that we should also take into account all of the various
+	 * Offload Queues.  But, in any situation where we're operating in
+	 * a Resource Constrained Provisioning environment, doing any Offload
+	 * at all is problematic ...
+	 */
+	niqflint = adap->params.pfres.niqflint - 1;
+	if (!(adap->flags & USING_MSIX))
+		niqflint--;
+	neq = adap->params.pfres.neq / 2;
+	avail_eth_qsets = min(niqflint, neq);
+
+	if (avail_eth_qsets > max_eth_qsets)
+		avail_eth_qsets = max_eth_qsets;
+
+	if (avail_eth_qsets < adap->params.nports) {
+		dev_err(adap->pdev_dev, "avail_eth_qsets=%d < nports=%d\n",
+			avail_eth_qsets, adap->params.nports);
+		return -ENOMEM;
+	}
+
+	/* Count the number of 10Gb/s or better ports */
+	for_each_port(adap, i)
+		n10g += is_x_10g_port(&adap2pinfo(adap, i)->link_cfg);
+
 #ifdef CONFIG_CHELSIO_T4_DCB
 	/* For Data Center Bridging support we need to be able to support up
 	 * to 8 Traffic Priorities; each of which will be assigned to its
 	 * own TX Queue in order to prevent Head-Of-Line Blocking.
 	 */
-	if (adap->params.nports * 8 > MAX_ETH_QSETS) {
-		dev_err(adap->pdev_dev, "MAX_ETH_QSETS=%d < %d!\n",
-			MAX_ETH_QSETS, adap->params.nports * 8);
-		BUG_ON(1);
+	if (adap->params.nports * 8 > avail_eth_qsets) {
+		dev_err(adap->pdev_dev, "DCB avail_eth_qsets=%d < %d!\n",
+			avail_eth_qsets, adap->params.nports * 8);
+		return -ENOMEM;
 	}
 
 	for_each_port(adap, i) {
@@ -4837,7 +4893,7 @@ static void cfg_queues(struct adapter *adap)
 	 * per 10G port.
 	 */
 	if (n10g)
-		q10g = (MAX_ETH_QSETS - (adap->params.nports - n10g)) / n10g;
+		q10g = (avail_eth_qsets - (adap->params.nports - n10g)) / n10g;
 	if (q10g > netif_get_num_default_rss_queues())
 		q10g = netif_get_num_default_rss_queues();
 
@@ -4888,6 +4944,8 @@ static void cfg_queues(struct adapter *adap)
 
 	init_rspq(adap, &s->fw_evtq, 0, 1, 1024, 64);
 	init_rspq(adap, &s->intrq, 0, 1, 512, 64);
+
+	return 0;
 }
 
 /*
@@ -5628,10 +5686,15 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		}
 	}
 
+	if (!(adapter->flags & FW_OK))
+		goto fw_attach_fail;
+
 	/* Configure queues and allocate tables now, they can be needed as
 	 * soon as the first register_netdev completes.
 	 */
-	cfg_queues(adapter);
+	err = cfg_queues(adapter);
+	if (err)
+		goto out_free_dev;
 
 	adapter->smt = t4_init_smt();
 	if (!adapter->smt) {
@@ -5738,6 +5801,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto out_free_dev;
 	}
 
+fw_attach_fail:
 	/*
 	 * The card is now ready to go.  If any errors occur during device
 	 * registration we do not fail the whole card but rather proceed only
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 974a868a4824..d266177aeef5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -2882,6 +2882,57 @@ int t4_get_vpd_params(struct adapter *adapter, struct vpd_params *p)
 	return 0;
 }
 
+/**
+ *	t4_get_pfres - retrieve VF resource limits
+ *	@adapter: the adapter
+ *
+ *	Retrieves configured resource limits and capabilities for a physical
+ *	function.  The results are stored in @adapter->pfres.
+ */
+int t4_get_pfres(struct adapter *adapter)
+{
+	struct pf_resources *pfres = &adapter->params.pfres;
+	struct fw_pfvf_cmd cmd, rpl;
+	int v;
+	u32 word;
+
+	/* Execute PFVF Read command to get VF resource limits; bail out early
+	 * with error on command failure.
+	 */
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.op_to_vfn = cpu_to_be32(FW_CMD_OP_V(FW_PFVF_CMD) |
+				    FW_CMD_REQUEST_F |
+				    FW_CMD_READ_F |
+				    FW_PFVF_CMD_PFN_V(adapter->pf) |
+				    FW_PFVF_CMD_VFN_V(0));
+	cmd.retval_len16 = cpu_to_be32(FW_LEN16(cmd));
+	v = t4_wr_mbox(adapter, adapter->mbox, &cmd, sizeof(cmd), &rpl);
+	if (v != FW_SUCCESS)
+		return v;
+
+	/* Extract PF resource limits and return success.
+	 */
+	word = be32_to_cpu(rpl.niqflint_niq);
+	pfres->niqflint = FW_PFVF_CMD_NIQFLINT_G(word);
+	pfres->niq = FW_PFVF_CMD_NIQ_G(word);
+
+	word = be32_to_cpu(rpl.type_to_neq);
+	pfres->neq = FW_PFVF_CMD_NEQ_G(word);
+	pfres->pmask = FW_PFVF_CMD_PMASK_G(word);
+
+	word = be32_to_cpu(rpl.tc_to_nexactf);
+	pfres->tc = FW_PFVF_CMD_TC_G(word);
+	pfres->nvi = FW_PFVF_CMD_NVI_G(word);
+	pfres->nexactf = FW_PFVF_CMD_NEXACTF_G(word);
+
+	word = be32_to_cpu(rpl.r_caps_to_nethctrl);
+	pfres->r_caps = FW_PFVF_CMD_R_CAPS_G(word);
+	pfres->wx_caps = FW_PFVF_CMD_WX_CAPS_G(word);
+	pfres->nethctrl = FW_PFVF_CMD_NETHCTRL_G(word);
+
+	return 0;
+}
+
 /* serial flash and firmware constants */
 enum {
 	SF_ATTEMPTS = 10,             /* max retries for SF operations */
-- 
cgit v1.2.3


From a4ca8b7df73c6d78b8b5aa8246a7d794b25c25ce Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Wed, 4 Jul 2018 19:23:50 +0100
Subject: net: ipv4: fix drop handling in ip_list_rcv() and
 ip_list_rcv_finish()

Since callees (ip_rcv_core() and ip_rcv_finish_core()) might free or steal
 the skb, we can't use the list_cut_before() method; we can't even do a
 list_del(&skb->list) in the drop case, because skb might have already been
 freed and reused.
So instead, take each skb off the source list before processing, and add it
 to the sublist afterwards if it wasn't freed or stolen.

Fixes: 5fa12739a53d net: ipv4: listify ip_rcv_finish
Fixes: 17266ee93984 net: ipv4: listified version of ip_rcv
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_input.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 24b9b0210aeb..14ba628b2761 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -540,24 +540,27 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 	struct sk_buff *skb, *next;
 	struct list_head sublist;
 
+	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct dst_entry *dst;
 
+		list_del(&skb->list);
 		if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
 			continue;
 
 		dst = skb_dst(skb);
 		if (curr_dst != dst) {
 			/* dispatch old sublist */
-			list_cut_before(&sublist, head, &skb->list);
 			if (!list_empty(&sublist))
 				ip_sublist_rcv_finish(&sublist);
 			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
 			curr_dst = dst;
 		}
+		list_add_tail(&skb->list, &sublist);
 	}
 	/* dispatch final sublist */
-	ip_sublist_rcv_finish(head);
+	ip_sublist_rcv_finish(&sublist);
 }
 
 static void ip_sublist_rcv(struct list_head *head, struct net_device *dev,
@@ -577,24 +580,27 @@ void ip_list_rcv(struct list_head *head, struct packet_type *pt,
 	struct sk_buff *skb, *next;
 	struct list_head sublist;
 
+	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct net_device *dev = skb->dev;
 		struct net *net = dev_net(dev);
 
+		list_del(&skb->list);
 		skb = ip_rcv_core(skb, net);
 		if (skb == NULL)
 			continue;
 
 		if (curr_dev != dev || curr_net != net) {
 			/* dispatch old sublist */
-			list_cut_before(&sublist, head, &skb->list);
 			if (!list_empty(&sublist))
-				ip_sublist_rcv(&sublist, dev, net);
+				ip_sublist_rcv(&sublist, curr_dev, curr_net);
 			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
 			curr_dev = dev;
 			curr_net = net;
 		}
+		list_add_tail(&skb->list, &sublist);
 	}
 	/* dispatch final sublist */
-	ip_sublist_rcv(head, curr_dev, curr_net);
+	ip_sublist_rcv(&sublist, curr_dev, curr_net);
 }
-- 
cgit v1.2.3


From 6fcf9b1d4d6cd38202247de5c0ac7d85c4483abb Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 4 Jul 2018 21:11:29 +0200
Subject: r8169: fix runtime suspend

When runtime-suspending we configure WoL w/o touching saved_wolopts.
If saved_wolopts == 0 we would power down the PHY in this case what's
wrong. Therefore we have to check the actual chip WoL settings here.

Fixes: 433f9d0ddcc6 ("r8169: improve saved_wolopts handling")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index f80ac894ef92..d598fdf0470c 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1534,12 +1534,6 @@ static void rtl8169_check_link_status(struct net_device *dev,
 
 #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
 
-/* Currently we only enable WoL if explicitly told by userspace to circumvent
- * issues on certain platforms, see commit bde135a672bf ("r8169: only enable
- * PCI wakeups when WOL is active"). Let's keep __rtl8169_get_wol() for the
- * case that we want to respect BIOS settings again.
- */
-#if 0
 static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
 {
 	u8 options;
@@ -1574,7 +1568,6 @@ static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
 
 	return wolopts;
 }
-#endif
 
 static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
@@ -4470,7 +4463,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 
 static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 {
-	if (!netif_running(tp->dev) || !tp->saved_wolopts)
+	if (!netif_running(tp->dev) || !__rtl8169_get_wol(tp))
 		return false;
 
 	rtl_speed_down(tp);
-- 
cgit v1.2.3


From 598865c5f32d6e11e99f2aac07348e5fd17cdc03 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 31 Jan 2018 15:55:24 +0000
Subject: arm64: barrier: Implement smp_cond_load_relaxed

We can provide an implementation of smp_cond_load_relaxed using READ_ONCE
and __cmpwait_relaxed.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/barrier.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index f11518af96a9..822a9192c551 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -128,6 +128,19 @@ do {									\
 	__u.__val;							\
 })
 
+#define smp_cond_load_relaxed(ptr, cond_expr)				\
+({									\
+	typeof(ptr) __PTR = (ptr);					\
+	typeof(*ptr) VAL;						\
+	for (;;) {							\
+		VAL = READ_ONCE(*__PTR);				\
+		if (cond_expr)						\
+			break;						\
+		__cmpwait_relaxed(__PTR, VAL);				\
+	}								\
+	VAL;								\
+})
+
 #define smp_cond_load_acquire(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\
-- 
cgit v1.2.3


From c11090474d70590170cf5fa6afe85864ab494b37 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 13 Mar 2018 20:45:45 +0000
Subject: arm64: locking: Replace ticket lock implementation with qspinlock

It's fair to say that our ticket lock has served us well over time, but
it's time to bite the bullet and start using the generic qspinlock code
so we can make use of explicit MCS queuing and potentially better PV
performance in future.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig                      |   1 +
 arch/arm64/include/asm/Kbuild           |   1 +
 arch/arm64/include/asm/spinlock.h       | 117 +-------------------------------
 arch/arm64/include/asm/spinlock_types.h |  17 +----
 4 files changed, 4 insertions(+), 132 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 42c090cf0292..facd19625563 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -44,6 +44,7 @@ config ARM64
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPT
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_SUPPORTS_MEMORY_FAILURE
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_INT128 if GCC_VERSION >= 50000 || CC_IS_CLANG
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 3a9b84d39d71..6cd5d77b6b44 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -16,6 +16,7 @@ generic-y += mm-arch-hooks.h
 generic-y += msi.h
 generic-y += preempt.h
 generic-y += qrwlock.h
+generic-y += qspinlock.h
 generic-y += rwsem.h
 generic-y += segment.h
 generic-y += serial.h
diff --git a/arch/arm64/include/asm/spinlock.h b/arch/arm64/include/asm/spinlock.h
index 26c5bd7d88d8..38116008d18b 100644
--- a/arch/arm64/include/asm/spinlock.h
+++ b/arch/arm64/include/asm/spinlock.h
@@ -16,123 +16,8 @@
 #ifndef __ASM_SPINLOCK_H
 #define __ASM_SPINLOCK_H
 
-#include <asm/lse.h>
-#include <asm/spinlock_types.h>
-#include <asm/processor.h>
-
-/*
- * Spinlock implementation.
- *
- * The memory barriers are implicit with the load-acquire and store-release
- * instructions.
- */
-
-static inline void arch_spin_lock(arch_spinlock_t *lock)
-{
-	unsigned int tmp;
-	arch_spinlock_t lockval, newval;
-
-	asm volatile(
-	/* Atomically increment the next ticket. */
-	ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-"	prfm	pstl1strm, %3\n"
-"1:	ldaxr	%w0, %3\n"
-"	add	%w1, %w0, %w5\n"
-"	stxr	%w2, %w1, %3\n"
-"	cbnz	%w2, 1b\n",
-	/* LSE atomics */
-"	mov	%w2, %w5\n"
-"	ldadda	%w2, %w0, %3\n"
-	__nops(3)
-	)
-
-	/* Did we get the lock? */
-"	eor	%w1, %w0, %w0, ror #16\n"
-"	cbz	%w1, 3f\n"
-	/*
-	 * No: spin on the owner. Send a local event to avoid missing an
-	 * unlock before the exclusive load.
-	 */
-"	sevl\n"
-"2:	wfe\n"
-"	ldaxrh	%w2, %4\n"
-"	eor	%w1, %w2, %w0, lsr #16\n"
-"	cbnz	%w1, 2b\n"
-	/* We got the lock. Critical section starts here. */
-"3:"
-	: "=&r" (lockval), "=&r" (newval), "=&r" (tmp), "+Q" (*lock)
-	: "Q" (lock->owner), "I" (1 << TICKET_SHIFT)
-	: "memory");
-}
-
-static inline int arch_spin_trylock(arch_spinlock_t *lock)
-{
-	unsigned int tmp;
-	arch_spinlock_t lockval;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	prfm	pstl1strm, %2\n"
-	"1:	ldaxr	%w0, %2\n"
-	"	eor	%w1, %w0, %w0, ror #16\n"
-	"	cbnz	%w1, 2f\n"
-	"	add	%w0, %w0, %3\n"
-	"	stxr	%w1, %w0, %2\n"
-	"	cbnz	%w1, 1b\n"
-	"2:",
-	/* LSE atomics */
-	"	ldr	%w0, %2\n"
-	"	eor	%w1, %w0, %w0, ror #16\n"
-	"	cbnz	%w1, 1f\n"
-	"	add	%w1, %w0, %3\n"
-	"	casa	%w0, %w1, %2\n"
-	"	sub	%w1, %w1, %3\n"
-	"	eor	%w1, %w1, %w0\n"
-	"1:")
-	: "=&r" (lockval), "=&r" (tmp), "+Q" (*lock)
-	: "I" (1 << TICKET_SHIFT)
-	: "memory");
-
-	return !tmp;
-}
-
-static inline void arch_spin_unlock(arch_spinlock_t *lock)
-{
-	unsigned long tmp;
-
-	asm volatile(ARM64_LSE_ATOMIC_INSN(
-	/* LL/SC */
-	"	ldrh	%w1, %0\n"
-	"	add	%w1, %w1, #1\n"
-	"	stlrh	%w1, %0",
-	/* LSE atomics */
-	"	mov	%w1, #1\n"
-	"	staddlh	%w1, %0\n"
-	__nops(1))
-	: "=Q" (lock->owner), "=&r" (tmp)
-	:
-	: "memory");
-}
-
-static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
-{
-	return lock.owner == lock.next;
-}
-
-static inline int arch_spin_is_locked(arch_spinlock_t *lock)
-{
-	return !arch_spin_value_unlocked(READ_ONCE(*lock));
-}
-
-static inline int arch_spin_is_contended(arch_spinlock_t *lock)
-{
-	arch_spinlock_t lockval = READ_ONCE(*lock);
-	return (lockval.next - lockval.owner) > 1;
-}
-#define arch_spin_is_contended	arch_spin_is_contended
-
 #include <asm/qrwlock.h>
+#include <asm/qspinlock.h>
 
 /* See include/linux/spinlock.h */
 #define smp_mb__after_spinlock()	smp_mb()
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 6b856012c51b..a157ff465e27 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -20,22 +20,7 @@
 # error "please don't include this file directly"
 #endif
 
-#include <linux/types.h>
-
-#define TICKET_SHIFT	16
-
-typedef struct {
-#ifdef __AARCH64EB__
-	u16 next;
-	u16 owner;
-#else
-	u16 owner;
-	u16 next;
-#endif
-} __aligned(4) arch_spinlock_t;
-
-#define __ARCH_SPIN_LOCK_UNLOCKED	{ 0 , 0 }
-
+#include <asm-generic/qspinlock_types.h>
 #include <asm-generic/qrwlock_types.h>
 
 #endif
-- 
cgit v1.2.3


From 5d168964aece0b4a41269839c613683c5d7e0fb2 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 13 Mar 2018 21:17:01 +0000
Subject: arm64: kconfig: Ensure spinlock fastpaths are inlined if !PREEMPT

When running with CONFIG_PREEMPT=n, the spinlock fastpaths fit inside
64 bytes, which typically coincides with the L1 I-cache line size.

Inline the spinlock fastpaths, like we do already for rwlocks.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index facd19625563..476de9b1d239 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -42,6 +42,16 @@ config ARM64
 	select ARCH_INLINE_WRITE_UNLOCK_BH if !PREEMPT
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ if !PREEMPT
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE if !PREEMPT
+	select ARCH_INLINE_SPIN_TRYLOCK if !PREEMPT
+	select ARCH_INLINE_SPIN_TRYLOCK_BH if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK_BH if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_SPIN_LOCK_IRQSAVE if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK_BH if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK_IRQ if !PREEMPT
+	select ARCH_INLINE_SPIN_UNLOCK_IRQRESTORE if !PREEMPT
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
 	select ARCH_USE_QUEUED_SPINLOCKS
-- 
cgit v1.2.3


From 4c4a39dd5fe2d13e2d2fa5fceb8ef95d19fc389a Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Wed, 4 Jul 2018 23:07:45 +0100
Subject: arm64: Fix mismatched cache line size detection

If there is a mismatch in the I/D min line size, we must
always use the system wide safe value both in applications
and in the kernel, while performing cache operations. However,
we have been checking more bits than just the min line sizes,
which triggers false negatives. We may need to trap the user
accesses in such cases, but not necessarily patch the kernel.

This patch fixes the check to do the right thing as advertised.
A new capability will be added to check mismatches in other
fields and ensure we trap the CTR accesses.

Fixes: be68a8aaf925 ("arm64: cpufeature: Fix CTR_EL0 field definitions")
Cc: <stable@vger.kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Reported-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/cache.h | 4 ++++
 arch/arm64/kernel/cpu_errata.c | 6 ++++--
 arch/arm64/kernel/cpufeature.c | 2 +-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h
index 5df5cfe1c143..5ee5bca8c24b 100644
--- a/arch/arm64/include/asm/cache.h
+++ b/arch/arm64/include/asm/cache.h
@@ -21,12 +21,16 @@
 #define CTR_L1IP_SHIFT		14
 #define CTR_L1IP_MASK		3
 #define CTR_DMINLINE_SHIFT	16
+#define CTR_IMINLINE_SHIFT	0
 #define CTR_ERG_SHIFT		20
 #define CTR_CWG_SHIFT		24
 #define CTR_CWG_MASK		15
 #define CTR_IDC_SHIFT		28
 #define CTR_DIC_SHIFT		29
 
+#define CTR_CACHE_MINLINE_MASK	\
+	(0xf << CTR_DMINLINE_SHIFT | 0xf << CTR_IMINLINE_SHIFT)
+
 #define CTR_L1IP(ctr)		(((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK)
 
 #define ICACHE_POLICY_VPIPT	0
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 1d2b6d768efe..5d1fa928ea4b 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -68,9 +68,11 @@ static bool
 has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
 				int scope)
 {
+	u64 mask = CTR_CACHE_MINLINE_MASK;
+
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
-	return (read_cpuid_cachetype() & arm64_ftr_reg_ctrel0.strict_mask) !=
-		(arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
+	return (read_cpuid_cachetype() & mask) !=
+	       (arm64_ftr_reg_ctrel0.sys_val & mask);
 }
 
 static void
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index f24892a40d2c..25d5cef00333 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -214,7 +214,7 @@ static const struct arm64_ftr_bits ftr_ctr[] = {
 	 * If we have differing I-cache policies, report it as the weakest - VIPT.
 	 */
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_VIPT),	/* L1Ip */
-	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, CTR_IMINLINE_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
 
-- 
cgit v1.2.3


From 314d53d297980676011e6fd83dac60db4a01dc70 Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Wed, 4 Jul 2018 23:07:46 +0100
Subject: arm64: Handle mismatched cache type

Track mismatches in the cache type register (CTR_EL0), other
than the D/I min line sizes and trap user accesses if there are any.

Fixes: be68a8aaf925 ("arm64: cpufeature: Fix CTR_EL0 field definitions")
Cc: <stable@vger.kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/cpucaps.h |  3 ++-
 arch/arm64/kernel/cpu_errata.c   | 17 ++++++++++++++---
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
index 8a699c708fc9..be3bf3d08916 100644
--- a/arch/arm64/include/asm/cpucaps.h
+++ b/arch/arm64/include/asm/cpucaps.h
@@ -49,7 +49,8 @@
 #define ARM64_HAS_CACHE_DIC			28
 #define ARM64_HW_DBM				29
 #define ARM64_SSBD				30
+#define ARM64_MISMATCHED_CACHE_TYPE		31
 
-#define ARM64_NCAPS				31
+#define ARM64_NCAPS				32
 
 #endif /* __ASM_CPUCAPS_H */
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 5d1fa928ea4b..5d59ff9a8da9 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -65,11 +65,15 @@ is_kryo_midr(const struct arm64_cpu_capabilities *entry, int scope)
 }
 
 static bool
-has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
-				int scope)
+has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
+			  int scope)
 {
 	u64 mask = CTR_CACHE_MINLINE_MASK;
 
+	/* Skip matching the min line sizes for cache type check */
+	if (entry->capability == ARM64_MISMATCHED_CACHE_TYPE)
+		mask ^= arm64_ftr_reg_ctrel0.strict_mask;
+
 	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
 	return (read_cpuid_cachetype() & mask) !=
 	       (arm64_ftr_reg_ctrel0.sys_val & mask);
@@ -615,7 +619,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "Mismatched cache line size",
 		.capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
-		.matches = has_mismatched_cache_line_size,
+		.matches = has_mismatched_cache_type,
+		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
+		.cpu_enable = cpu_enable_trap_ctr_access,
+	},
+	{
+		.desc = "Mismatched cache type",
+		.capability = ARM64_MISMATCHED_CACHE_TYPE,
+		.matches = has_mismatched_cache_type,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.cpu_enable = cpu_enable_trap_ctr_access,
 	},
-- 
cgit v1.2.3


From b999a7a9e72bd2d37b5d03772cedfc4dd45875bf Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 09:18:33 -0500
Subject: ASoC: fsl_spdif: Use 64-bit arithmetic instead of 32-bit

Add suffix ULL to constant 64 in order to give the compiler complete
information about the proper arithmetic to use.

Notice that such constant is used in a context that expects an
expression of type u64 (64 bits, unsigned) and the following
expression is currently being evaluated using 32-bit arithmetic:

rate[index] * txclk_df * 64

Addresses-Coverity-ID: 1222129 ("Unintentional integer overflow")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Nicolin Chen <nicoleotsuka@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_spdif.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/fsl/fsl_spdif.c b/sound/soc/fsl/fsl_spdif.c
index 9b59d87b61bf..740b90df44bb 100644
--- a/sound/soc/fsl/fsl_spdif.c
+++ b/sound/soc/fsl/fsl_spdif.c
@@ -1118,7 +1118,7 @@ static u32 fsl_spdif_txclk_caldiv(struct fsl_spdif_priv *spdif_priv,
 
 	for (sysclk_df = sysclk_dfmin; sysclk_df <= sysclk_dfmax; sysclk_df++) {
 		for (txclk_df = 1; txclk_df <= 128; txclk_df++) {
-			rate_ideal = rate[index] * txclk_df * 64;
+			rate_ideal = rate[index] * txclk_df * 64ULL;
 			if (round)
 				rate_actual = clk_round_rate(clk, rate_ideal);
 			else
-- 
cgit v1.2.3


From 74b37e299f038c910dc728d736e3f071ba0ead2a Mon Sep 17 00:00:00 2001
From: Andrew Gabbasov <andrew_gabbasov@mentor.com>
Date: Thu, 5 Jul 2018 11:20:04 +0900
Subject: ASoC: rsnd: cmd: Add missing newline to debug message

To comply with the style of all kernel messages, add newline
to the end of every message.

Fixes: 70fb10529f61 ("ASoC: rsnd: add MIX (Mixer) support")
Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com>
Signed-off-by: Jiada Wang <jiada_wang@mentor.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/rcar/cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/sh/rcar/cmd.c b/sound/soc/sh/rcar/cmd.c
index d8043ad33540..cc191cd5fb82 100644
--- a/sound/soc/sh/rcar/cmd.c
+++ b/sound/soc/sh/rcar/cmd.c
@@ -86,7 +86,7 @@ static int rsnd_cmd_init(struct rsnd_mod *mod,
 			cmd_case[rsnd_mod_id(src)] << 16;
 	}
 
-	dev_dbg(dev, "ctu/mix path = 0x%08x", data);
+	dev_dbg(dev, "ctu/mix path = 0x%08x\n", data);
 
 	rsnd_mod_write(mod, CMD_ROUTE_SLCT, data);
 	rsnd_mod_write(mod, CMD_BUSIF_MODE, rsnd_get_busif_shift(io, mod) | 1);
-- 
cgit v1.2.3


From 90eb6b59d311e6facd040124cb5b659a865125b8 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Mon, 2 Jul 2018 17:11:00 +0200
Subject: ASoC: pxa-ssp: add support for an external clock in devicetree

Allow setting a clock called 'extclk' in the device of the ssp-dai
device. If specified, this clock will be set to the mclk rate from the
DAI's .set_sysclk() callback. The DAI will also configure itself to
use that external clock.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/mrvl,pxa-ssp.txt     |  8 +++++++
 sound/soc/pxa/pxa-ssp.c                            | 25 ++++++++++++++++++++++
 2 files changed, 33 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt b/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
index 74c9ba6c2823..93b982e9419f 100644
--- a/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
+++ b/Documentation/devicetree/bindings/sound/mrvl,pxa-ssp.txt
@@ -5,6 +5,14 @@ Required properties:
 	compatible	Must be "mrvl,pxa-ssp-dai"
 	port		A phandle reference to a PXA ssp upstream device
 
+Optional properties:
+
+	clock-names
+	clocks		Through "clock-names" and "clocks", external clocks
+			can be configured. If a clock names "extclk" exists,
+			it will be set to the mclk rate of the audio stream
+			and be used as clock provider of the DAI.
+
 Example:
 
 	/* upstream device */
diff --git a/sound/soc/pxa/pxa-ssp.c b/sound/soc/pxa/pxa-ssp.c
index ff1e0bd8d407..69033e1a84e6 100644
--- a/sound/soc/pxa/pxa-ssp.c
+++ b/sound/soc/pxa/pxa-ssp.c
@@ -41,6 +41,7 @@
  */
 struct ssp_priv {
 	struct ssp_device *ssp;
+	struct clk *extclk;
 	unsigned long ssp_clk;
 	unsigned int sysclk;
 	unsigned int dai_fmt;
@@ -205,6 +206,21 @@ static int pxa_ssp_set_dai_sysclk(struct snd_soc_dai *cpu_dai,
 	u32 sscr0 = pxa_ssp_read_reg(ssp, SSCR0) &
 		~(SSCR0_ECS | SSCR0_NCS | SSCR0_MOD | SSCR0_ACS);
 
+	if (priv->extclk) {
+		int ret;
+
+		/*
+		 * For DT based boards, if an extclk is given, use it
+		 * here and configure PXA_SSP_CLK_EXT.
+		 */
+
+		ret = clk_set_rate(priv->extclk, freq);
+		if (ret < 0)
+			return ret;
+
+		clk_id = PXA_SSP_CLK_EXT;
+	}
+
 	dev_dbg(&ssp->pdev->dev,
 		"pxa_ssp_set_dai_sysclk id: %d, clk_id %d, freq %u\n",
 		cpu_dai->id, clk_id, freq);
@@ -774,6 +790,15 @@ static int pxa_ssp_probe(struct snd_soc_dai *dai)
 			ret = -ENODEV;
 			goto err_priv;
 		}
+
+		priv->extclk = devm_clk_get(dev, "extclk");
+		if (IS_ERR(priv->extclk)) {
+			ret = PTR_ERR(priv->extclk);
+			if (ret == -EPROBE_DEFER)
+				return ret;
+
+			priv->extclk = NULL;
+		}
 	} else {
 		priv->ssp = pxa_ssp_request(dai->id + 1, "SoC audio");
 		if (priv->ssp == NULL) {
-- 
cgit v1.2.3


From cef08fdc743c4211aeba69dd23408093d59da241 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 5 Jul 2018 07:56:51 +0100
Subject: drm/i915: Remove defunct i915->vm_list

No longer used and can be removed. One less global that currently
demands struct_mutex protection.

References: e9e7dc4144cd ("drm/i915/gtt: Make gen6 page directories evictable")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705065653.20449-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.h           | 1 -
 drivers/gpu/drm/i915/i915_gem_gtt.c       | 5 -----
 drivers/gpu/drm/i915/i915_gem_gtt.h       | 1 -
 drivers/gpu/drm/i915/selftests/mock_gtt.c | 3 ---
 4 files changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 4f9191ab3e12..e236016eef7b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1744,7 +1744,6 @@ struct drm_i915_private {
 	struct drm_atomic_state *modeset_restore_state;
 	struct drm_modeset_acquire_ctx reset_ctx;
 
-	struct list_head vm_list; /* Global list of all address spaces */
 	struct i915_ggtt ggtt; /* VM representing the global address space */
 
 	struct i915_gem_mm mm;
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 5fb299590579..a9330de886f8 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -540,8 +540,6 @@ static void i915_address_space_init(struct i915_address_space *vm,
 	INIT_LIST_HEAD(&vm->active_list);
 	INIT_LIST_HEAD(&vm->inactive_list);
 	INIT_LIST_HEAD(&vm->unbound_list);
-
-	list_add_tail(&vm->global_link, &dev_priv->vm_list);
 }
 
 static void i915_address_space_fini(struct i915_address_space *vm)
@@ -553,7 +551,6 @@ static void i915_address_space_fini(struct i915_address_space *vm)
 	spin_unlock(&vm->free_pages.lock);
 
 	drm_mm_takedown(&vm->mm);
-	list_del(&vm->global_link);
 }
 
 static int __setup_page_dma(struct i915_address_space *vm,
@@ -3572,8 +3569,6 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 
 	stash_init(&dev_priv->mm.wc_stash);
 
-	INIT_LIST_HEAD(&dev_priv->vm_list);
-
 	/* Note that we use page colouring to enforce a guard page at the
 	 * end of the address space. This is required as the CS may prefetch
 	 * beyond the end of the batch buffer, across the page boundary,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index f298e72b79ca..feda45dfd481 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -288,7 +288,6 @@ struct i915_address_space {
 	 * assign blame.
 	 */
 	struct drm_i915_file_private *file;
-	struct list_head global_link;
 	u64 total;		/* size addr space maps (ex. 2GB for ggtt) */
 	u64 reserved;		/* size addr space reserved */
 
diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 0da5b8c6d912..07df5c399ec1 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -74,7 +74,6 @@ mock_ppgtt(struct drm_i915_private *i915,
 	INIT_LIST_HEAD(&ppgtt->vm.inactive_list);
 	INIT_LIST_HEAD(&ppgtt->vm.unbound_list);
 
-	INIT_LIST_HEAD(&ppgtt->vm.global_link);
 	drm_mm_init(&ppgtt->vm.mm, 0, ppgtt->vm.total);
 
 	ppgtt->vm.clear_range = nop_clear_range;
@@ -106,8 +105,6 @@ void mock_init_ggtt(struct drm_i915_private *i915)
 {
 	struct i915_ggtt *ggtt = &i915->ggtt;
 
-	INIT_LIST_HEAD(&i915->vm_list);
-
 	ggtt->vm.i915 = i915;
 
 	ggtt->gmadr = (struct resource) DEFINE_RES_MEM(0, 2048 * PAGE_SIZE);
-- 
cgit v1.2.3


From eae4c9445354602926ff7cc4702c2516e2485a94 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 5 Jul 2018 07:56:52 +0100
Subject: drm/i915/selftests: Use full release for local ppgtt allocation

We can now use the full release mechanism (i915_ppgtt_put) for our local
ppgtt allocation in igt_ppgtt_alloc.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705065653.20449-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 4bfb0537f9be..e108fe4e0fd9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -202,9 +202,8 @@ static int igt_ppgtt_alloc(void *arg)
 
 err_ppgtt_cleanup:
 	mutex_lock(&dev_priv->drm.struct_mutex);
-	ppgtt->vm.cleanup(&ppgtt->vm);
+	i915_ppgtt_put(ppgtt);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
-	kfree(ppgtt);
 	return err;
 }
 
-- 
cgit v1.2.3


From 0f17d5dd2199555830482b638a5fc8bf915f2f10 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 5 Jul 2018 07:56:53 +0100
Subject: drm/i915/selftests: Replace open-coded i915_address_space_init()

Use i915_address_space_init() rather than open-code it inside
mock_ppgtt() as we will forget to keep it in sync.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705065653.20449-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/mock_gtt.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/mock_gtt.c b/drivers/gpu/drm/i915/selftests/mock_gtt.c
index 07df5c399ec1..a140ea5c3a7c 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gtt.c
@@ -70,11 +70,7 @@ mock_ppgtt(struct drm_i915_private *i915,
 	ppgtt->vm.total = round_down(U64_MAX, PAGE_SIZE);
 	ppgtt->vm.file = ERR_PTR(-ENODEV);
 
-	INIT_LIST_HEAD(&ppgtt->vm.active_list);
-	INIT_LIST_HEAD(&ppgtt->vm.inactive_list);
-	INIT_LIST_HEAD(&ppgtt->vm.unbound_list);
-
-	drm_mm_init(&ppgtt->vm.mm, 0, ppgtt->vm.total);
+	i915_address_space_init(&ppgtt->vm, i915);
 
 	ppgtt->vm.clear_range = nop_clear_range;
 	ppgtt->vm.insert_page = mock_insert_page;
-- 
cgit v1.2.3


From 6312fe77751f57d4fa2b28abeef84c6a95c28136 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Thu, 5 Jul 2018 14:34:32 +0800
Subject: net: limit each hash list length to MAX_GRO_SKBS

After commit 07d78363dcff ("net: Convert NAPI gro list into a small hash
table.")' there is 8 hash buckets, which allows more flows to be held for
merging.  but MAX_GRO_SKBS, the total held skb for merging, is 8 skb still,
limit the hash table performance.

keep MAX_GRO_SKBS as 8 skb, but limit each hash list length to 8 skb, not
the total 8 skb

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  7 +++++-
 net/core/dev.c            | 56 +++++++++++++++++++----------------------------
 2 files changed, 29 insertions(+), 34 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f06ee8f91e74..b683971e500d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -302,6 +302,11 @@ struct netdev_boot_setup {
 
 int __init netdev_boot_setup(char *str);
 
+struct gro_list {
+	struct list_head	list;
+	int			count;
+};
+
 /*
  * Structure for NAPI scheduling similar to tasklet but with weighting
  */
@@ -323,7 +328,7 @@ struct napi_struct {
 	int			poll_owner;
 #endif
 	struct net_device	*dev;
-	struct list_head	gro_hash[GRO_HASH_BUCKETS];
+	struct gro_list		gro_hash[GRO_HASH_BUCKETS];
 	struct sk_buff		*skb;
 	struct hrtimer		timer;
 	struct list_head	dev_list;
diff --git a/net/core/dev.c b/net/core/dev.c
index 7e6a2f66db5c..89825c1eccdc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -149,7 +149,6 @@
 
 #include "net-sysfs.h"
 
-/* Instead of increasing this, you should create a hash table. */
 #define MAX_GRO_SKBS 8
 
 /* This should be increased if a protocol with a bigger head is added. */
@@ -5151,9 +5150,10 @@ out:
 	return netif_receive_skb_internal(skb);
 }
 
-static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *head,
+static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
 				   bool flush_old)
 {
+	struct list_head *head = &napi->gro_hash[index].list;
 	struct sk_buff *skb, *p;
 
 	list_for_each_entry_safe_reverse(skb, p, head, list) {
@@ -5162,22 +5162,20 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, struct list_head *h
 		list_del_init(&skb->list);
 		napi_gro_complete(skb);
 		napi->gro_count--;
+		napi->gro_hash[index].count--;
 	}
 }
 
-/* napi->gro_hash contains packets ordered by age.
+/* napi->gro_hash[].list contains packets ordered by age.
  * youngest packets at the head of it.
  * Complete skbs in reverse order to reduce latencies.
  */
 void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
-	int i;
-
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		struct list_head *head = &napi->gro_hash[i];
+	u32 i;
 
-		__napi_gro_flush_chain(napi, head, flush_old);
-	}
+	for (i = 0; i < GRO_HASH_BUCKETS; i++)
+		__napi_gro_flush_chain(napi, i, flush_old);
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
@@ -5189,7 +5187,7 @@ static struct list_head *gro_list_prepare(struct napi_struct *napi,
 	struct list_head *head;
 	struct sk_buff *p;
 
-	head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)];
+	head = &napi->gro_hash[hash & (GRO_HASH_BUCKETS - 1)].list;
 	list_for_each_entry(p, head, list) {
 		unsigned long diffs;
 
@@ -5257,27 +5255,13 @@ static void gro_pull_from_frag0(struct sk_buff *skb, int grow)
 	}
 }
 
-static void gro_flush_oldest(struct napi_struct *napi)
+static void gro_flush_oldest(struct list_head *head)
 {
-	struct sk_buff *oldest = NULL;
-	unsigned long age = jiffies;
-	int i;
-
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		struct list_head *head = &napi->gro_hash[i];
-		struct sk_buff *skb;
-
-		if (list_empty(head))
-			continue;
+	struct sk_buff *oldest;
 
-		skb = list_last_entry(head, struct sk_buff, list);
-		if (!oldest || time_before(NAPI_GRO_CB(skb)->age, age)) {
-			oldest = skb;
-			age = NAPI_GRO_CB(skb)->age;
-		}
-	}
+	oldest = list_last_entry(head, struct sk_buff, list);
 
-	/* We are called with napi->gro_count >= MAX_GRO_SKBS, so this is
+	/* We are called with head length >= MAX_GRO_SKBS, so this is
 	 * impossible.
 	 */
 	if (WARN_ON_ONCE(!oldest))
@@ -5292,6 +5276,7 @@ static void gro_flush_oldest(struct napi_struct *napi)
 
 static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 {
+	u32 hash = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
 	struct list_head *head = &offload_base;
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
@@ -5358,6 +5343,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		list_del_init(&pp->list);
 		napi_gro_complete(pp);
 		napi->gro_count--;
+		napi->gro_hash[hash].count--;
 	}
 
 	if (same_flow)
@@ -5366,10 +5352,11 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (NAPI_GRO_CB(skb)->flush)
 		goto normal;
 
-	if (unlikely(napi->gro_count >= MAX_GRO_SKBS)) {
-		gro_flush_oldest(napi);
+	if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) {
+		gro_flush_oldest(gro_head);
 	} else {
 		napi->gro_count++;
+		napi->gro_hash[hash].count++;
 	}
 	NAPI_GRO_CB(skb)->count = 1;
 	NAPI_GRO_CB(skb)->age = jiffies;
@@ -6006,8 +5993,10 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
 	napi->gro_count = 0;
-	for (i = 0; i < GRO_HASH_BUCKETS; i++)
-		INIT_LIST_HEAD(&napi->gro_hash[i]);
+	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+		INIT_LIST_HEAD(&napi->gro_hash[i].list);
+		napi->gro_hash[i].count = 0;
+	}
 	napi->skb = NULL;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
@@ -6047,8 +6036,9 @@ static void flush_gro_hash(struct napi_struct *napi)
 	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
 		struct sk_buff *skb, *n;
 
-		list_for_each_entry_safe(skb, n, &napi->gro_hash[i], list)
+		list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list)
 			kfree_skb(skb);
+		napi->gro_hash[i].count = 0;
 	}
 }
 
-- 
cgit v1.2.3


From 896e863d6df7df70a5c4ec37800a67e1fb5ae5f0 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 5 Jul 2018 09:30:04 +0100
Subject: net: dsa: fix spelling mistake "waitting" -> "waiting"

Trivial fix to spelling mistake in dev_err error message.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/vitesse-vsc73xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/vitesse-vsc73xx.c b/drivers/net/dsa/vitesse-vsc73xx.c
index a4fc260006de..3bbd86084119 100644
--- a/drivers/net/dsa/vitesse-vsc73xx.c
+++ b/drivers/net/dsa/vitesse-vsc73xx.c
@@ -930,7 +930,7 @@ static void vsc73xx_adjust_link(struct dsa_switch *ds, int port,
 				     VSC73XX_ARBEMPTY, &val);
 			if (--maxloop == 0) {
 				dev_err(vsc->dev,
-					"timeout waitting for block arbiter\n");
+					"timeout waiting for block arbiter\n");
 				/* Continue anyway */
 				break;
 			}
-- 
cgit v1.2.3


From e7550b0be3cf1361bcadd629b8ea1c9e749725e4 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Thu, 5 Jul 2018 08:59:09 +0000
Subject: net: dsa: vsc73xx: Make some functions static

Fixes the following sparse warnings:

drivers/net/dsa/vitesse-vsc73xx.c:1054:6: warning:
 symbol 'vsc73xx_get_strings' was not declared. Should it be static?
drivers/net/dsa/vitesse-vsc73xx.c:1113:5: warning:
 symbol 'vsc73xx_get_sset_count' was not declared. Should it be static?
drivers/net/dsa/vitesse-vsc73xx.c:1122:6: warning:
 symbol 'vsc73xx_get_ethtool_stats' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/vitesse-vsc73xx.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/vitesse-vsc73xx.c b/drivers/net/dsa/vitesse-vsc73xx.c
index 3bbd86084119..9f1b5f2e8a64 100644
--- a/drivers/net/dsa/vitesse-vsc73xx.c
+++ b/drivers/net/dsa/vitesse-vsc73xx.c
@@ -1051,8 +1051,8 @@ vsc73xx_find_counter(struct vsc73xx *vsc,
 	return NULL;
 }
 
-void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
-			 uint8_t *data)
+static void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+				uint8_t *data)
 {
 	const struct vsc73xx_counter *cnt;
 	struct vsc73xx *vsc = ds->priv;
@@ -1110,7 +1110,7 @@ void vsc73xx_get_strings(struct dsa_switch *ds, int port, u32 stringset,
 	}
 }
 
-int vsc73xx_get_sset_count(struct dsa_switch *ds, int port, int sset)
+static int vsc73xx_get_sset_count(struct dsa_switch *ds, int port, int sset)
 {
 	/* We only support SS_STATS */
 	if (sset != ETH_SS_STATS)
@@ -1119,7 +1119,8 @@ int vsc73xx_get_sset_count(struct dsa_switch *ds, int port, int sset)
 	return 8;
 }
 
-void vsc73xx_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
+static void vsc73xx_get_ethtool_stats(struct dsa_switch *ds, int port,
+				      uint64_t *data)
 {
 	struct vsc73xx *vsc = ds->priv;
 	u8 regs[] = {
-- 
cgit v1.2.3


From dfbd07497860f32b847bfac0023331947d33aae6 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Thu, 5 Jul 2018 09:00:10 +0000
Subject: net: aquantia: Make some functions static

Fixes the following sparse warnings:

drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c:525:5: warning:
 symbol 'hw_atl_utils_mpi_set_speed' was not declared. Should it be static?
drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c:536:5: warning:
 symbol 'hw_atl_utils_mpi_set_state' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
index e1feba5787d1..c965e65d07db 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.c
@@ -522,7 +522,7 @@ void hw_atl_utils_mpi_read_stats(struct aq_hw_s *self,
 err_exit:;
 }
 
-int hw_atl_utils_mpi_set_speed(struct aq_hw_s *self, u32 speed)
+static int hw_atl_utils_mpi_set_speed(struct aq_hw_s *self, u32 speed)
 {
 	u32 val = aq_hw_read_reg(self, HW_ATL_MPI_CONTROL_ADR);
 
@@ -533,8 +533,8 @@ int hw_atl_utils_mpi_set_speed(struct aq_hw_s *self, u32 speed)
 	return 0;
 }
 
-int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
-			       enum hal_atl_utils_fw_state_e state)
+static int hw_atl_utils_mpi_set_state(struct aq_hw_s *self,
+				      enum hal_atl_utils_fw_state_e state)
 {
 	int err = 0;
 	u32 transaction_id = 0;
-- 
cgit v1.2.3


From e0515b0cbccc69c7fb4d6edc2f25ac1faa20ac0f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 5 Jul 2018 10:26:13 +0100
Subject: net: socionext: remove redundant pointer ndev

Pointer ndev is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'ndev' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index e080d3e7c582..01589b6982e4 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -780,11 +780,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 static int netsec_napi_poll(struct napi_struct *napi, int budget)
 {
 	struct netsec_priv *priv;
-	struct net_device *ndev;
 	int tx, rx, done, todo;
 
 	priv = container_of(napi, struct netsec_priv, napi);
-	ndev = priv->ndev;
 
 	todo = budget;
 	do {
-- 
cgit v1.2.3


From 2f9be18164add28fa231950e20ad9a978a34f13d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 5 Jul 2018 10:55:49 +0100
Subject: net: tehuti: remove redundant pointer skb

Pointer skb is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'skb' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/tehuti/tehuti.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c
index 163d8d16bc24..dc966ddb6d81 100644
--- a/drivers/net/ethernet/tehuti/tehuti.c
+++ b/drivers/net/ethernet/tehuti/tehuti.c
@@ -1151,7 +1151,6 @@ static void bdx_recycle_skb(struct bdx_priv *priv, struct rxd_desc *rxdd)
 	struct rx_map *dm;
 	struct rxf_fifo *f;
 	struct rxdb *db;
-	struct sk_buff *skb;
 	int delta;
 
 	ENTER;
@@ -1161,7 +1160,6 @@ static void bdx_recycle_skb(struct bdx_priv *priv, struct rxd_desc *rxdd)
 	DBG("db=%p f=%p\n", db, f);
 	dm = bdx_rxdb_addr_elem(db, rxdd->va_lo);
 	DBG("dm=%p\n", dm);
-	skb = dm->skb;
 	rxfd = (struct rxf_desc *)(f->m.va + f->m.wptr);
 	rxfd->info = CPU_CHIP_SWAP32(0x10003);	/* INFO=1 BC=3 */
 	rxfd->va_lo = rxdd->va_lo;
-- 
cgit v1.2.3


From b67030b139de957f1266555009f5f19feac819c4 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 5 Jul 2018 11:05:32 +0100
Subject: fjes: use currently unused variable my_epid and max_epid

Variables my_epid and max_epid are currently assigned and not being
used - however, I suspect they were intended to be used in the for-loops
to reduce the dereferencing of hw.  Replace hw->my_epid and hw->max_epid
with these variables.

Cleans up clang warnings:
warning: variable 'my_epid' set but not used [-Wunused-but-set-variable]
variable 'max_epid' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/fjes/fjes_main.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/fjes/fjes_main.c b/drivers/net/fjes/fjes_main.c
index 750954be5a74..d3eae1239045 100644
--- a/drivers/net/fjes/fjes_main.c
+++ b/drivers/net/fjes/fjes_main.c
@@ -1395,8 +1395,8 @@ static void fjes_watch_unshare_task(struct work_struct *work)
 
 	while ((unshare_watch_bitmask || hw->txrx_stop_req_bit) &&
 	       (wait_time < 3000)) {
-		for (epidx = 0; epidx < hw->max_epid; epidx++) {
-			if (epidx == hw->my_epid)
+		for (epidx = 0; epidx < max_epid; epidx++) {
+			if (epidx == my_epid)
 				continue;
 
 			is_shared = fjes_hw_epid_is_shared(hw->hw_info.share,
@@ -1453,8 +1453,8 @@ static void fjes_watch_unshare_task(struct work_struct *work)
 	}
 
 	if (hw->hw_info.buffer_unshare_reserve_bit) {
-		for (epidx = 0; epidx < hw->max_epid; epidx++) {
-			if (epidx == hw->my_epid)
+		for (epidx = 0; epidx < max_epid; epidx++) {
+			if (epidx == my_epid)
 				continue;
 
 			if (test_bit(epidx,
-- 
cgit v1.2.3


From 827ad90cfa6140f86c398a7a8d32d9f319835273 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 5 Jul 2018 11:11:07 +0100
Subject: net/hamradio/6pack: remove redundant variable channel

Variable channel is being assigned but is never used hence it is
redundant and can be removed.

Cleans up two clang warnings:
warning: variable 'channel' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hamradio/6pack.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 32f49c4ce457..d79a69dd2146 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -878,10 +878,8 @@ static void decode_data(struct sixpack *sp, unsigned char inbyte)
 
 static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
 {
-	unsigned char channel;
 	int actual;
 
-	channel = cmd & SIXP_CHN_MASK;
 	if ((cmd & SIXP_PRIO_DATA_MASK) != 0) {     /* idle ? */
 
 	/* RX and DCD flags can only be set in the same prio command,
@@ -933,10 +931,9 @@ static void decode_prio_command(struct sixpack *sp, unsigned char cmd)
 
 static void decode_std_command(struct sixpack *sp, unsigned char cmd)
 {
-	unsigned char checksum = 0, rest = 0, channel;
+	unsigned char checksum = 0, rest = 0;
 	short i;
 
-	channel = cmd & SIXP_CHN_MASK;
 	switch (cmd & SIXP_CMD_MASK) {     /* normal command */
 	case SIXP_SEOF:
 		if ((sp->rx_count == 0) && (sp->rx_count_cooked == 0)) {
-- 
cgit v1.2.3


From eabaef1896bc06319461a644e3aa139885454def Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:28 +0300
Subject: devlink: Add devlink_param register and unregister

Define configuration parameters data structure.
Add functions to register and unregister the driver supported
configuration parameters table.
For each parameter registered, the driver should fill all the parameter's
fields. In case the only supported configuration mode is "driverinit"
the parameter's get()/set() functions are not required and should be set
to NULL, for any other configuration mode, these functions are required
and should be set by the driver.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h        |  85 +++++++++++++++++++++++++
 include/uapi/linux/devlink.h |  10 +++
 net/core/devlink.c           | 148 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 243 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index e336ea9c73df..4a0687a1fb99 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -27,6 +27,7 @@ struct devlink {
 	struct list_head sb_list;
 	struct list_head dpipe_table_list;
 	struct list_head resource_list;
+	struct list_head param_list;
 	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
@@ -295,6 +296,68 @@ struct devlink_resource {
 
 #define DEVLINK_RESOURCE_ID_PARENT_TOP 0
 
+#define DEVLINK_PARAM_MAX_STRING_VALUE 32
+enum devlink_param_type {
+	DEVLINK_PARAM_TYPE_U8,
+	DEVLINK_PARAM_TYPE_U16,
+	DEVLINK_PARAM_TYPE_U32,
+	DEVLINK_PARAM_TYPE_STRING,
+	DEVLINK_PARAM_TYPE_BOOL,
+};
+
+union devlink_param_value {
+	u8 vu8;
+	u16 vu16;
+	u32 vu32;
+	const char *vstr;
+	bool vbool;
+};
+
+struct devlink_param_gset_ctx {
+	union devlink_param_value val;
+	enum devlink_param_cmode cmode;
+};
+
+/**
+ * struct devlink_param - devlink configuration parameter data
+ * @name: name of the parameter
+ * @generic: indicates if the parameter is generic or driver specific
+ * @type: parameter type
+ * @supported_cmodes: bitmap of supported configuration modes
+ * @get: get parameter value, used for runtime and permanent
+ *       configuration modes
+ * @set: set parameter value, used for runtime and permanent
+ *       configuration modes
+ *
+ * This struct should be used by the driver to fill the data for
+ * a parameter it registers.
+ */
+struct devlink_param {
+	u32 id;
+	const char *name;
+	bool generic;
+	enum devlink_param_type type;
+	unsigned long supported_cmodes;
+	int (*get)(struct devlink *devlink, u32 id,
+		   struct devlink_param_gset_ctx *ctx);
+	int (*set)(struct devlink *devlink, u32 id,
+		   struct devlink_param_gset_ctx *ctx);
+};
+
+struct devlink_param_item {
+	struct list_head list;
+	const struct devlink_param *param;
+	union devlink_param_value driverinit_value;
+	bool driverinit_value_valid;
+};
+
+enum devlink_param_generic_id {
+
+	/* add new param generic ids above here*/
+	__DEVLINK_PARAM_GENERIC_ID_MAX,
+	DEVLINK_PARAM_GENERIC_ID_MAX = __DEVLINK_PARAM_GENERIC_ID_MAX - 1,
+};
+
 struct devlink_ops {
 	int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
@@ -430,6 +493,12 @@ void devlink_resource_occ_get_register(struct devlink *devlink,
 				       void *occ_get_priv);
 void devlink_resource_occ_get_unregister(struct devlink *devlink,
 					 u64 resource_id);
+int devlink_params_register(struct devlink *devlink,
+			    const struct devlink_param *params,
+			    size_t params_count);
+void devlink_params_unregister(struct devlink *devlink,
+			       const struct devlink_param *params,
+			       size_t params_count);
 
 #else
 
@@ -622,6 +691,22 @@ devlink_resource_occ_get_unregister(struct devlink *devlink,
 {
 }
 
+static inline int
+devlink_params_register(struct devlink *devlink,
+			const struct devlink_param *params,
+			size_t params_count)
+{
+	return 0;
+}
+
+static inline void
+devlink_params_unregister(struct devlink *devlink,
+			  const struct devlink_param *params,
+			  size_t params_count)
+{
+
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 75cb5450c851..d814fa67c7b9 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -142,6 +142,16 @@ enum devlink_port_flavour {
 				   */
 };
 
+enum devlink_param_cmode {
+	DEVLINK_PARAM_CMODE_RUNTIME,
+	DEVLINK_PARAM_CMODE_DRIVERINIT,
+	DEVLINK_PARAM_CMODE_PERMANENT,
+
+	/* Add new configuration modes above */
+	__DEVLINK_PARAM_CMODE_MAX,
+	DEVLINK_PARAM_CMODE_MAX = __DEVLINK_PARAM_CMODE_MAX - 1
+};
+
 enum devlink_attr {
 	/* don't change the order or add anything between, this is ABI! */
 	DEVLINK_ATTR_UNSPEC,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 22099705cc41..41b1a5d1c992 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2604,6 +2604,82 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 	return devlink->ops->reload(devlink, info->extack);
 }
 
+static const struct devlink_param devlink_param_generic[] = {};
+
+static int devlink_param_generic_verify(const struct devlink_param *param)
+{
+	/* verify it match generic parameter by id and name */
+	if (param->id > DEVLINK_PARAM_GENERIC_ID_MAX)
+		return -EINVAL;
+	if (strcmp(param->name, devlink_param_generic[param->id].name))
+		return -ENOENT;
+
+	WARN_ON(param->type != devlink_param_generic[param->id].type);
+
+	return 0;
+}
+
+static int devlink_param_driver_verify(const struct devlink_param *param)
+{
+	int i;
+
+	if (param->id <= DEVLINK_PARAM_GENERIC_ID_MAX)
+		return -EINVAL;
+	/* verify no such name in generic params */
+	for (i = 0; i <= DEVLINK_PARAM_GENERIC_ID_MAX; i++)
+		if (!strcmp(param->name, devlink_param_generic[i].name))
+			return -EEXIST;
+
+	return 0;
+}
+
+static struct devlink_param_item *
+devlink_param_find_by_name(struct list_head *param_list,
+			   const char *param_name)
+{
+	struct devlink_param_item *param_item;
+
+	list_for_each_entry(param_item, param_list, list)
+		if (!strcmp(param_item->param->name, param_name))
+			return param_item;
+	return NULL;
+}
+
+static int devlink_param_register_one(struct devlink *devlink,
+				      const struct devlink_param *param)
+{
+	struct devlink_param_item *param_item;
+
+	if (devlink_param_find_by_name(&devlink->param_list,
+				       param->name))
+		return -EEXIST;
+
+	if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT))
+		WARN_ON(param->get || param->set);
+	else
+		WARN_ON(!param->get || !param->set);
+
+	param_item = kzalloc(sizeof(*param_item), GFP_KERNEL);
+	if (!param_item)
+		return -ENOMEM;
+	param_item->param = param;
+
+	list_add_tail(&param_item->list, &devlink->param_list);
+	return 0;
+}
+
+static void devlink_param_unregister_one(struct devlink *devlink,
+					 const struct devlink_param *param)
+{
+	struct devlink_param_item *param_item;
+
+	param_item = devlink_param_find_by_name(&devlink->param_list,
+						param->name);
+	WARN_ON(!param_item);
+	list_del(&param_item->list);
+	kfree(param_item);
+}
+
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -2845,6 +2921,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	INIT_LIST_HEAD(&devlink->sb_list);
 	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	INIT_LIST_HEAD(&devlink->resource_list);
+	INIT_LIST_HEAD(&devlink->param_list);
 	mutex_init(&devlink->lock);
 	return devlink;
 }
@@ -3434,6 +3511,77 @@ out:
 }
 EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister);
 
+/**
+ *	devlink_params_register - register configuration parameters
+ *
+ *	@devlink: devlink
+ *	@params: configuration parameters array
+ *	@params_count: number of parameters provided
+ *
+ *	Register the configuration parameters supported by the driver.
+ */
+int devlink_params_register(struct devlink *devlink,
+			    const struct devlink_param *params,
+			    size_t params_count)
+{
+	const struct devlink_param *param = params;
+	int i;
+	int err;
+
+	mutex_lock(&devlink->lock);
+	for (i = 0; i < params_count; i++, param++) {
+		if (!param || !param->name || !param->supported_cmodes) {
+			err = -EINVAL;
+			goto rollback;
+		}
+		if (param->generic) {
+			err = devlink_param_generic_verify(param);
+			if (err)
+				goto rollback;
+		} else {
+			err = devlink_param_driver_verify(param);
+			if (err)
+				goto rollback;
+		}
+		err = devlink_param_register_one(devlink, param);
+		if (err)
+			goto rollback;
+	}
+
+	mutex_unlock(&devlink->lock);
+	return 0;
+
+rollback:
+	if (!i)
+		goto unlock;
+	for (param--; i > 0; i--, param--)
+		devlink_param_unregister_one(devlink, param);
+unlock:
+	mutex_unlock(&devlink->lock);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_params_register);
+
+/**
+ *	devlink_params_unregister - unregister configuration parameters
+ *	@devlink: devlink
+ *	@params: configuration parameters to unregister
+ *	@params_count: number of parameters provided
+ */
+void devlink_params_unregister(struct devlink *devlink,
+			       const struct devlink_param *params,
+			       size_t params_count)
+{
+	const struct devlink_param *param = params;
+	int i;
+
+	mutex_lock(&devlink->lock);
+	for (i = 0; i < params_count; i++, param++)
+		devlink_param_unregister_one(devlink, param);
+	mutex_unlock(&devlink->lock);
+}
+EXPORT_SYMBOL_GPL(devlink_params_unregister);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From 45f05def5c44c806f094709f1c9b03dcecdd54f0 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:29 +0300
Subject: devlink: Add param get command

Add param get command which gets data per parameter.
Option to dump the parameters data per device.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h |  11 ++
 net/core/devlink.c           | 250 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 261 insertions(+)

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index d814fa67c7b9..2ccfe84176bf 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -78,6 +78,8 @@ enum devlink_command {
 	 */
 	DEVLINK_CMD_RELOAD,
 
+	DEVLINK_CMD_PARAM_GET,		/* can dump */
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -248,6 +250,15 @@ enum devlink_attr {
 	DEVLINK_ATTR_PORT_NUMBER,		/* u32 */
 	DEVLINK_ATTR_PORT_SPLIT_SUBPORT_NUMBER,	/* u32 */
 
+	DEVLINK_ATTR_PARAM,			/* nested */
+	DEVLINK_ATTR_PARAM_NAME,		/* string */
+	DEVLINK_ATTR_PARAM_GENERIC,		/* flag */
+	DEVLINK_ATTR_PARAM_TYPE,		/* u8 */
+	DEVLINK_ATTR_PARAM_VALUES_LIST,		/* nested */
+	DEVLINK_ATTR_PARAM_VALUE,		/* nested */
+	DEVLINK_ATTR_PARAM_VALUE_DATA,		/* dynamic */
+	DEVLINK_ATTR_PARAM_VALUE_CMODE,		/* u8 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 41b1a5d1c992..b22d41275f0b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2645,6 +2645,248 @@ devlink_param_find_by_name(struct list_head *param_list,
 	return NULL;
 }
 
+static bool
+devlink_param_cmode_is_supported(const struct devlink_param *param,
+				 enum devlink_param_cmode cmode)
+{
+	return test_bit(cmode, &param->supported_cmodes);
+}
+
+static int devlink_param_get(struct devlink *devlink,
+			     const struct devlink_param *param,
+			     struct devlink_param_gset_ctx *ctx)
+{
+	if (!param->get)
+		return -EOPNOTSUPP;
+	return param->get(devlink, param->id, ctx);
+}
+
+static int
+devlink_param_type_to_nla_type(enum devlink_param_type param_type)
+{
+	switch (param_type) {
+	case DEVLINK_PARAM_TYPE_U8:
+		return NLA_U8;
+	case DEVLINK_PARAM_TYPE_U16:
+		return NLA_U16;
+	case DEVLINK_PARAM_TYPE_U32:
+		return NLA_U32;
+	case DEVLINK_PARAM_TYPE_STRING:
+		return NLA_STRING;
+	case DEVLINK_PARAM_TYPE_BOOL:
+		return NLA_FLAG;
+	default:
+		return -EINVAL;
+	}
+}
+
+static int
+devlink_nl_param_value_fill_one(struct sk_buff *msg,
+				enum devlink_param_type type,
+				enum devlink_param_cmode cmode,
+				union devlink_param_value val)
+{
+	struct nlattr *param_value_attr;
+
+	param_value_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUE);
+	if (!param_value_attr)
+		goto nla_put_failure;
+
+	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_CMODE, cmode))
+		goto value_nest_cancel;
+
+	switch (type) {
+	case DEVLINK_PARAM_TYPE_U8:
+		if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu8))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_U16:
+		if (nla_put_u16(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu16))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_U32:
+		if (nla_put_u32(msg, DEVLINK_ATTR_PARAM_VALUE_DATA, val.vu32))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_STRING:
+		if (nla_put_string(msg, DEVLINK_ATTR_PARAM_VALUE_DATA,
+				   val.vstr))
+			goto value_nest_cancel;
+		break;
+	case DEVLINK_PARAM_TYPE_BOOL:
+		if (val.vbool &&
+		    nla_put_flag(msg, DEVLINK_ATTR_PARAM_VALUE_DATA))
+			goto value_nest_cancel;
+		break;
+	}
+
+	nla_nest_end(msg, param_value_attr);
+	return 0;
+
+value_nest_cancel:
+	nla_nest_cancel(msg, param_value_attr);
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink,
+				 struct devlink_param_item *param_item,
+				 enum devlink_command cmd,
+				 u32 portid, u32 seq, int flags)
+{
+	union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1];
+	const struct devlink_param *param = param_item->param;
+	struct devlink_param_gset_ctx ctx;
+	struct nlattr *param_values_list;
+	struct nlattr *param_attr;
+	int nla_type;
+	void *hdr;
+	int err;
+	int i;
+
+	/* Get value from driver part to driverinit configuration mode */
+	for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
+		if (!devlink_param_cmode_is_supported(param, i))
+			continue;
+		if (i == DEVLINK_PARAM_CMODE_DRIVERINIT) {
+			if (!param_item->driverinit_value_valid)
+				return -EOPNOTSUPP;
+			param_value[i] = param_item->driverinit_value;
+		} else {
+			ctx.cmode = i;
+			err = devlink_param_get(devlink, param, &ctx);
+			if (err)
+				return err;
+			param_value[i] = ctx.val;
+		}
+	}
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (devlink_nl_put_handle(msg, devlink))
+		goto genlmsg_cancel;
+	param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM);
+	if (!param_attr)
+		goto genlmsg_cancel;
+	if (nla_put_string(msg, DEVLINK_ATTR_PARAM_NAME, param->name))
+		goto param_nest_cancel;
+	if (param->generic && nla_put_flag(msg, DEVLINK_ATTR_PARAM_GENERIC))
+		goto param_nest_cancel;
+
+	nla_type = devlink_param_type_to_nla_type(param->type);
+	if (nla_type < 0)
+		goto param_nest_cancel;
+	if (nla_put_u8(msg, DEVLINK_ATTR_PARAM_TYPE, nla_type))
+		goto param_nest_cancel;
+
+	param_values_list = nla_nest_start(msg, DEVLINK_ATTR_PARAM_VALUES_LIST);
+	if (!param_values_list)
+		goto param_nest_cancel;
+
+	for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) {
+		if (!devlink_param_cmode_is_supported(param, i))
+			continue;
+		err = devlink_nl_param_value_fill_one(msg, param->type,
+						      i, param_value[i]);
+		if (err)
+			goto values_list_nest_cancel;
+	}
+
+	nla_nest_end(msg, param_values_list);
+	nla_nest_end(msg, param_attr);
+	genlmsg_end(msg, hdr);
+	return 0;
+
+values_list_nest_cancel:
+	nla_nest_end(msg, param_values_list);
+param_nest_cancel:
+	nla_nest_cancel(msg, param_attr);
+genlmsg_cancel:
+	genlmsg_cancel(msg, hdr);
+	return -EMSGSIZE;
+}
+
+static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
+					   struct netlink_callback *cb)
+{
+	struct devlink_param_item *param_item;
+	struct devlink *devlink;
+	int start = cb->args[0];
+	int idx = 0;
+	int err;
+
+	mutex_lock(&devlink_mutex);
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+			continue;
+		mutex_lock(&devlink->lock);
+		list_for_each_entry(param_item, &devlink->param_list, list) {
+			if (idx < start) {
+				idx++;
+				continue;
+			}
+			err = devlink_nl_param_fill(msg, devlink, param_item,
+						    DEVLINK_CMD_PARAM_GET,
+						    NETLINK_CB(cb->skb).portid,
+						    cb->nlh->nlmsg_seq,
+						    NLM_F_MULTI);
+			if (err) {
+				mutex_unlock(&devlink->lock);
+				goto out;
+			}
+			idx++;
+		}
+		mutex_unlock(&devlink->lock);
+	}
+out:
+	mutex_unlock(&devlink_mutex);
+
+	cb->args[0] = idx;
+	return msg->len;
+}
+
+static struct devlink_param_item *
+devlink_param_get_from_info(struct devlink *devlink,
+			    struct genl_info *info)
+{
+	char *param_name;
+
+	if (!info->attrs[DEVLINK_ATTR_PARAM_NAME])
+		return NULL;
+
+	param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]);
+	return devlink_param_find_by_name(&devlink->param_list, param_name);
+}
+
+static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
+					 struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_param_item *param_item;
+	struct sk_buff *msg;
+	int err;
+
+	param_item = devlink_param_get_from_info(devlink, info);
+	if (!param_item)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_param_fill(msg, devlink, param_item,
+				    DEVLINK_CMD_PARAM_GET,
+				    info->snd_portid, info->snd_seq, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
 static int devlink_param_register_one(struct devlink *devlink,
 				      const struct devlink_param *param)
 {
@@ -2883,6 +3125,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK |
 				  DEVLINK_NL_FLAG_NO_LOCK,
 	},
+	{
+		.cmd = DEVLINK_CMD_PARAM_GET,
+		.doit = devlink_nl_cmd_param_get_doit,
+		.dumpit = devlink_nl_cmd_param_get_dumpit,
+		.policy = devlink_nl_policy,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+		/* can be retrieved by unprivileged users */
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
-- 
cgit v1.2.3


From e3b7ca18ad7b2f47ebd3b6e6ce58a42c6ec24746 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:30 +0300
Subject: devlink: Add param set command

Add param set command to set value for a parameter.
Value can be set to any of the supported configuration modes.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h        |   4 ++
 include/uapi/linux/devlink.h |   1 +
 net/core/devlink.c           | 134 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 139 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 4a0687a1fb99..88062752dcd7 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -328,6 +328,7 @@ struct devlink_param_gset_ctx {
  *       configuration modes
  * @set: set parameter value, used for runtime and permanent
  *       configuration modes
+ * @validate: validate input value is applicable (within value range, etc.)
  *
  * This struct should be used by the driver to fill the data for
  * a parameter it registers.
@@ -342,6 +343,9 @@ struct devlink_param {
 		   struct devlink_param_gset_ctx *ctx);
 	int (*set)(struct devlink *devlink, u32 id,
 		   struct devlink_param_gset_ctx *ctx);
+	int (*validate)(struct devlink *devlink, u32 id,
+			union devlink_param_value val,
+			struct netlink_ext_ack *extack);
 };
 
 struct devlink_param_item {
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 2ccfe84176bf..ea0623e568f0 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -79,6 +79,7 @@ enum devlink_command {
 	DEVLINK_CMD_RELOAD,
 
 	DEVLINK_CMD_PARAM_GET,		/* can dump */
+	DEVLINK_CMD_PARAM_SET,
 
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index b22d41275f0b..0cd7a42dcec2 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2661,6 +2661,15 @@ static int devlink_param_get(struct devlink *devlink,
 	return param->get(devlink, param->id, ctx);
 }
 
+static int devlink_param_set(struct devlink *devlink,
+			     const struct devlink_param *param,
+			     struct devlink_param_gset_ctx *ctx)
+{
+	if (!param->set)
+		return -EOPNOTSUPP;
+	return param->set(devlink, param->id, ctx);
+}
+
 static int
 devlink_param_type_to_nla_type(enum devlink_param_type param_type)
 {
@@ -2847,6 +2856,69 @@ out:
 	return msg->len;
 }
 
+static int
+devlink_param_type_get_from_info(struct genl_info *info,
+				 enum devlink_param_type *param_type)
+{
+	if (!info->attrs[DEVLINK_ATTR_PARAM_TYPE])
+		return -EINVAL;
+
+	switch (nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_TYPE])) {
+	case NLA_U8:
+		*param_type = DEVLINK_PARAM_TYPE_U8;
+		break;
+	case NLA_U16:
+		*param_type = DEVLINK_PARAM_TYPE_U16;
+		break;
+	case NLA_U32:
+		*param_type = DEVLINK_PARAM_TYPE_U32;
+		break;
+	case NLA_STRING:
+		*param_type = DEVLINK_PARAM_TYPE_STRING;
+		break;
+	case NLA_FLAG:
+		*param_type = DEVLINK_PARAM_TYPE_BOOL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int
+devlink_param_value_get_from_info(const struct devlink_param *param,
+				  struct genl_info *info,
+				  union devlink_param_value *value)
+{
+	if (param->type != DEVLINK_PARAM_TYPE_BOOL &&
+	    !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])
+		return -EINVAL;
+
+	switch (param->type) {
+	case DEVLINK_PARAM_TYPE_U8:
+		value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		break;
+	case DEVLINK_PARAM_TYPE_U16:
+		value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		break;
+	case DEVLINK_PARAM_TYPE_U32:
+		value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		break;
+	case DEVLINK_PARAM_TYPE_STRING:
+		if (nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) >
+		    DEVLINK_PARAM_MAX_STRING_VALUE)
+			return -EINVAL;
+		value->vstr = nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]);
+		break;
+	case DEVLINK_PARAM_TYPE_BOOL:
+		value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ?
+			       true : false;
+		break;
+	}
+	return 0;
+}
+
 static struct devlink_param_item *
 devlink_param_get_from_info(struct devlink *devlink,
 			    struct genl_info *info)
@@ -2887,6 +2959,58 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb,
 	return genlmsg_reply(msg, info);
 }
 
+static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
+					 struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	enum devlink_param_type param_type;
+	struct devlink_param_gset_ctx ctx;
+	enum devlink_param_cmode cmode;
+	struct devlink_param_item *param_item;
+	const struct devlink_param *param;
+	union devlink_param_value value;
+	int err = 0;
+
+	param_item = devlink_param_get_from_info(devlink, info);
+	if (!param_item)
+		return -EINVAL;
+	param = param_item->param;
+	err = devlink_param_type_get_from_info(info, &param_type);
+	if (err)
+		return err;
+	if (param_type != param->type)
+		return -EINVAL;
+	err = devlink_param_value_get_from_info(param, info, &value);
+	if (err)
+		return err;
+	if (param->validate) {
+		err = param->validate(devlink, param->id, value, info->extack);
+		if (err)
+			return err;
+	}
+
+	if (!info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE])
+		return -EINVAL;
+	cmode = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_CMODE]);
+	if (!devlink_param_cmode_is_supported(param, cmode))
+		return -EOPNOTSUPP;
+
+	if (cmode == DEVLINK_PARAM_CMODE_DRIVERINIT) {
+		param_item->driverinit_value = value;
+		param_item->driverinit_value_valid = true;
+	} else {
+		if (!param->set)
+			return -EOPNOTSUPP;
+		ctx.val = value;
+		ctx.cmode = cmode;
+		err = devlink_param_set(devlink, param, &ctx);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int devlink_param_register_one(struct devlink *devlink,
 				      const struct devlink_param *param)
 {
@@ -2942,6 +3066,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_DPIPE_TABLE_COUNTERS_ENABLED] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_RESOURCE_ID] = { .type = NLA_U64},
 	[DEVLINK_ATTR_RESOURCE_SIZE] = { .type = NLA_U64},
+	[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -3133,6 +3260,13 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 		/* can be retrieved by unprivileged users */
 	},
+	{
+		.cmd = DEVLINK_CMD_PARAM_SET,
+		.doit = devlink_nl_cmd_param_set_doit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
-- 
cgit v1.2.3


From ec01aeb1803eaaf0d006e7b07b5ddb5e429c38a4 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:31 +0300
Subject: devlink: Add support for get/set driverinit value

"driverinit" configuration mode value is held by devlink to enable
the driver query the value after reload. Two additional functions
added to help the driver get/set the value from/to devlink:
devlink_param_driverinit_value_set() and
devlink_param_driverinit_value_get().

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 18 ++++++++++++
 net/core/devlink.c    | 77 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 95 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 88062752dcd7..3302e43b09a4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -503,6 +503,10 @@ int devlink_params_register(struct devlink *devlink,
 void devlink_params_unregister(struct devlink *devlink,
 			       const struct devlink_param *params,
 			       size_t params_count);
+int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+				       union devlink_param_value *init_val);
+int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
+				       union devlink_param_value init_val);
 
 #else
 
@@ -711,6 +715,20 @@ devlink_params_unregister(struct devlink *devlink,
 
 }
 
+static inline int
+devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+				   union devlink_param_value *init_val)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
+				   union devlink_param_value init_val)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 0cd7a42dcec2..3af08f4562b5 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2645,6 +2645,17 @@ devlink_param_find_by_name(struct list_head *param_list,
 	return NULL;
 }
 
+static struct devlink_param_item *
+devlink_param_find_by_id(struct list_head *param_list, u32 param_id)
+{
+	struct devlink_param_item *param_item;
+
+	list_for_each_entry(param_item, param_list, list)
+		if (param_item->param->id == param_id)
+			return param_item;
+	return NULL;
+}
+
 static bool
 devlink_param_cmode_is_supported(const struct devlink_param *param,
 				 enum devlink_param_cmode cmode)
@@ -3966,6 +3977,72 @@ void devlink_params_unregister(struct devlink *devlink,
 }
 EXPORT_SYMBOL_GPL(devlink_params_unregister);
 
+/**
+ *	devlink_param_driverinit_value_get - get configuration parameter
+ *					     value for driver initializing
+ *
+ *	@devlink: devlink
+ *	@param_id: parameter ID
+ *	@init_val: value of parameter in driverinit configuration mode
+ *
+ *	This function should be used by the driver to get driverinit
+ *	configuration for initialization after reload command.
+ */
+int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
+				       union devlink_param_value *init_val)
+{
+	struct devlink_param_item *param_item;
+
+	if (!devlink->ops || !devlink->ops->reload)
+		return -EOPNOTSUPP;
+
+	param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
+	if (!param_item)
+		return -EINVAL;
+
+	if (!param_item->driverinit_value_valid ||
+	    !devlink_param_cmode_is_supported(param_item->param,
+					      DEVLINK_PARAM_CMODE_DRIVERINIT))
+		return -EOPNOTSUPP;
+
+	*init_val = param_item->driverinit_value;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get);
+
+/**
+ *	devlink_param_driverinit_value_set - set value of configuration
+ *					     parameter for driverinit
+ *					     configuration mode
+ *
+ *	@devlink: devlink
+ *	@param_id: parameter ID
+ *	@init_val: value of parameter to set for driverinit configuration mode
+ *
+ *	This function should be used by the driver to set driverinit
+ *	configuration mode default value.
+ */
+int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
+				       union devlink_param_value init_val)
+{
+	struct devlink_param_item *param_item;
+
+	param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
+	if (!param_item)
+		return -EINVAL;
+
+	if (!devlink_param_cmode_is_supported(param_item->param,
+					      DEVLINK_PARAM_CMODE_DRIVERINIT))
+		return -EOPNOTSUPP;
+
+	param_item->driverinit_value = init_val;
+	param_item->driverinit_value_valid = true;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From ea601e17098856ee059f35c2a75659e57df81f25 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:32 +0300
Subject: devlink: Add devlink notifications support for params

Add devlink_param_notify() function to support devlink param notifications.
Add notification call to devlink param set, register and unregister
functions.
Add devlink_param_value_changed() function to enable the driver notify
devlink on value change. Driver should use this function after value was
changed on any configuration mode part to driverinit.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h        |  7 +++++++
 include/uapi/linux/devlink.h |  2 ++
 net/core/devlink.c           | 50 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 59 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 3302e43b09a4..792edaa996ba 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -507,6 +507,7 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
 				       union devlink_param_value *init_val);
 int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
 				       union devlink_param_value init_val);
+void devlink_param_value_changed(struct devlink *devlink, u32 param_id);
 
 #else
 
@@ -729,6 +730,12 @@ devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
 	return -EOPNOTSUPP;
 }
 
+static inline void
+devlink_param_value_changed(struct devlink *devlink, u32 param_id)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index ea0623e568f0..68641fb56654 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -80,6 +80,8 @@ enum devlink_command {
 
 	DEVLINK_CMD_PARAM_GET,		/* can dump */
 	DEVLINK_CMD_PARAM_SET,
+	DEVLINK_CMD_PARAM_NEW,
+	DEVLINK_CMD_PARAM_DEL,
 
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 3af08f4562b5..89d948fd4727 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2828,6 +2828,28 @@ genlmsg_cancel:
 	return -EMSGSIZE;
 }
 
+static void devlink_param_notify(struct devlink *devlink,
+				 struct devlink_param_item *param_item,
+				 enum devlink_command cmd)
+{
+	struct sk_buff *msg;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+	err = devlink_nl_param_fill(msg, devlink, param_item, cmd, 0, 0, 0);
+	if (err) {
+		nlmsg_free(msg);
+		return;
+	}
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+}
+
 static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg,
 					   struct netlink_callback *cb)
 {
@@ -3019,6 +3041,7 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb,
 			return err;
 	}
 
+	devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
 	return 0;
 }
 
@@ -3042,6 +3065,7 @@ static int devlink_param_register_one(struct devlink *devlink,
 	param_item->param = param;
 
 	list_add_tail(&param_item->list, &devlink->param_list);
+	devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
 	return 0;
 }
 
@@ -3053,6 +3077,7 @@ static void devlink_param_unregister_one(struct devlink *devlink,
 	param_item = devlink_param_find_by_name(&devlink->param_list,
 						param->name);
 	WARN_ON(!param_item);
+	devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL);
 	list_del(&param_item->list);
 	kfree(param_item);
 }
@@ -4039,10 +4064,35 @@ int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
 	param_item->driverinit_value = init_val;
 	param_item->driverinit_value_valid = true;
 
+	devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set);
 
+/**
+ *	devlink_param_value_changed - notify devlink on a parameter's value
+ *				      change. Should be called by the driver
+ *				      right after the change.
+ *
+ *	@devlink: devlink
+ *	@param_id: parameter ID
+ *
+ *	This function should be used by the driver to notify devlink on value
+ *	change, excluding driverinit configuration mode.
+ *	For driverinit configuration mode driver should use the function
+ *	devlink_param_driverinit_value_set() instead.
+ */
+void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
+{
+	struct devlink_param_item *param_item;
+
+	param_item = devlink_param_find_by_id(&devlink->param_list, param_id);
+	WARN_ON(!param_item);
+
+	devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW);
+}
+EXPORT_SYMBOL_GPL(devlink_param_value_changed);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From 036467c3990c75ec8ce97e517a864b52e184a1aa Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:33 +0300
Subject: devlink: Add generic parameters internal_err_reset and max_macs

Add 2 first generic parameters to devlink configuration parameters set:
internal_err_reset - When set enables reset device on internal errors.
max_macs - max number of MACs per ETH port.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 31 +++++++++++++++++++++++++++++++
 net/core/devlink.c    | 14 +++++++++++++-
 2 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 792edaa996ba..a1c230d18911 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -356,12 +356,43 @@ struct devlink_param_item {
 };
 
 enum devlink_param_generic_id {
+	DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+	DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
 	DEVLINK_PARAM_GENERIC_ID_MAX = __DEVLINK_PARAM_GENERIC_ID_MAX - 1,
 };
 
+#define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME "internal_error_reset"
+#define DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE DEVLINK_PARAM_TYPE_BOOL
+
+#define DEVLINK_PARAM_GENERIC_MAX_MACS_NAME "max_macs"
+#define DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE DEVLINK_PARAM_TYPE_U32
+
+#define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
+{									\
+	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
+	.name = DEVLINK_PARAM_GENERIC_##_id##_NAME,			\
+	.type = DEVLINK_PARAM_GENERIC_##_id##_TYPE,			\
+	.generic = true,						\
+	.supported_cmodes = _cmodes,					\
+	.get = _get,							\
+	.set = _set,							\
+	.validate = _validate,						\
+}
+
+#define DEVLINK_PARAM_DRIVER(_id, _name, _type, _cmodes, _get, _set, _validate)	\
+{									\
+	.id = _id,							\
+	.name = _name,							\
+	.type = _type,							\
+	.supported_cmodes = _cmodes,					\
+	.get = _get,							\
+	.set = _set,							\
+	.validate = _validate,						\
+}
+
 struct devlink_ops {
 	int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 89d948fd4727..5bbd0aa7571a 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2604,7 +2604,19 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info)
 	return devlink->ops->reload(devlink, info->extack);
 }
 
-static const struct devlink_param devlink_param_generic[] = {};
+static const struct devlink_param devlink_param_generic[] = {
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+		.name = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_NAME,
+		.type = DEVLINK_PARAM_GENERIC_INT_ERR_RESET_TYPE,
+	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+		.name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME,
+		.type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE,
+	},
+
+};
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
 {
-- 
cgit v1.2.3


From bd1b51dc66dfe355b67afc94d299f2916136f104 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:34 +0300
Subject: mlx4: Add mlx4 initial parameters table and register it

Create initial parameters table for mlx4.
The table consists of two generic parameters and two driver-specific
parameters.
Generic:
  internal_err_reset - Enable reset device on internal errors. This
  parameter can be configured on mlx4 either on runtime or during driver
  initialization.
  max_macs - Max number of MACs per ETH port. For mlx4 this parameter
  value range is between 1 and 128. This parameter can be configured on
  mlx4 only during driver initialization.
Driver specific:
  enable_64b_cqe_eqe - Enable 64 byte CQEs/EQEs when the FW supports it.
  This parameter can be configured on mlx4 only during driver
  initialization.
  enable_4k_uar - Enable using 4K UAR. This parameter can be configured on
  mlx4 only during driver initialization.

Register the parameters table on mlx4_init_one() and unregister on
mlx4_remove_one().

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c | 108 +++++++++++++++++++++++++++++-
 1 file changed, 106 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 872014702fc1..2445f7999629 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -177,6 +177,101 @@ struct mlx4_port_config {
 
 static atomic_t pf_loading = ATOMIC_INIT(0);
 
+static int mlx4_devlink_ierr_reset_get(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx)
+{
+	ctx->val.vbool = !!mlx4_internal_err_reset;
+	return 0;
+}
+
+static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
+				       struct devlink_param_gset_ctx *ctx)
+{
+	mlx4_internal_err_reset = ctx->val.vbool;
+	return 0;
+}
+
+static int
+mlx4_devlink_max_macs_validate(struct devlink *devlink, u32 id,
+			       union devlink_param_value val,
+			       struct netlink_ext_ack *extack)
+{
+	u32 value = val.vu32;
+
+	if (value < 1 || value > 128)
+		return -ERANGE;
+
+	if (!is_power_of_2(value)) {
+		NL_SET_ERR_MSG_MOD(extack, "max_macs supported must be power of 2");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+enum mlx4_devlink_param_id {
+	MLX4_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
+	MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+	MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+};
+
+static const struct devlink_param mlx4_devlink_params[] = {
+	DEVLINK_PARAM_GENERIC(INT_ERR_RESET,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      mlx4_devlink_ierr_reset_get,
+			      mlx4_devlink_ierr_reset_set, NULL),
+	DEVLINK_PARAM_GENERIC(MAX_MACS,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, mlx4_devlink_max_macs_validate),
+	DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+			     "enable_64b_cqe_eqe", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			     NULL, NULL, NULL),
+	DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+			     "enable_4k_uar", DEVLINK_PARAM_TYPE_BOOL,
+			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			     NULL, NULL, NULL),
+};
+
+static void mlx4_devlink_set_init_value(struct devlink *devlink, u32 param_id,
+					union devlink_param_value init_val)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	int err;
+
+	err = devlink_param_driverinit_value_set(devlink, param_id, init_val);
+	if (err)
+		mlx4_warn(dev,
+			  "devlink set parameter %u value failed (err = %d)",
+			  param_id, err);
+}
+
+static void mlx4_devlink_set_params_init_values(struct devlink *devlink)
+{
+	union devlink_param_value value;
+
+	value.vbool = !!mlx4_internal_err_reset;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+				    value);
+
+	value.vu32 = 1UL << log_num_mac;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_MAX_MACS, value);
+
+	value.vbool = enable_64b_cqe_eqe;
+	mlx4_devlink_set_init_value(devlink,
+				    MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+				    value);
+
+	value.vbool = enable_4k_uar;
+	mlx4_devlink_set_init_value(devlink,
+				    MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+				    value);
+}
+
 static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
 					      struct mlx4_dev_cap *dev_cap)
 {
@@ -3792,14 +3887,21 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ret = devlink_register(devlink, &pdev->dev);
 	if (ret)
 		goto err_persist_free;
-
-	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
+	ret = devlink_params_register(devlink, mlx4_devlink_params,
+				      ARRAY_SIZE(mlx4_devlink_params));
 	if (ret)
 		goto err_devlink_unregister;
+	mlx4_devlink_set_params_init_values(devlink);
+	ret =  __mlx4_init_one(pdev, id->driver_data, priv);
+	if (ret)
+		goto err_params_unregister;
 
 	pci_save_state(pdev);
 	return 0;
 
+err_params_unregister:
+	devlink_params_unregister(devlink, mlx4_devlink_params,
+				  ARRAY_SIZE(mlx4_devlink_params));
 err_devlink_unregister:
 	devlink_unregister(devlink);
 err_persist_free:
@@ -3936,6 +4038,8 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 
 	pci_release_regions(pdev);
 	mlx4_pci_disable_device(dev);
+	devlink_params_unregister(devlink, mlx4_devlink_params,
+				  ARRAY_SIZE(mlx4_devlink_params));
 	devlink_unregister(devlink);
 	kfree(dev->persist);
 	devlink_free(devlink);
-- 
cgit v1.2.3


From dfb3c0821a4435600879b6dc7fb5d9dbf9678475 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Wed, 4 Jul 2018 14:30:35 +0300
Subject: mlx4: Add support for devlink reload and load driverinit values

Add mlx4_devlink_reload() to support devlink reload operation.
Add mlx4_devlink_param_load_driverinit_values() to load values which
were set using driverinit configuration mode.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/catas.c |  2 +-
 drivers/net/ethernet/mellanox/mlx4/main.c  | 53 +++++++++++++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h  |  3 +-
 3 files changed, 55 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index e2b6b0cac1ac..8afe4b5fb09b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -212,7 +212,7 @@ static void mlx4_handle_error_state(struct mlx4_dev_persistent *persist)
 	mutex_lock(&persist->interface_state_mutex);
 	if (persist->interface_state & MLX4_INTERFACE_STATE_UP &&
 	    !(persist->interface_state & MLX4_INTERFACE_STATE_DELETION)) {
-		err = mlx4_restart_one(persist->pdev);
+		err = mlx4_restart_one(persist->pdev, false, NULL);
 		mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n",
 			  err);
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 2445f7999629..c42eddfcd2b5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3852,8 +3852,57 @@ static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port,
 	return __set_port_type(info, mlx4_port_type);
 }
 
+static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
+{
+	union devlink_param_value saved_value;
+	int err;
+
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
+						 &saved_value);
+	if (!err && mlx4_internal_err_reset != saved_value.vbool) {
+		mlx4_internal_err_reset = saved_value.vbool;
+		/* Notify on value changed on runtime configuration mode */
+		devlink_param_value_changed(devlink,
+					    DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET);
+	}
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+						 &saved_value);
+	if (!err)
+		log_num_mac = order_base_2(saved_value.vu32);
+	err = devlink_param_driverinit_value_get(devlink,
+						 MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
+						 &saved_value);
+	if (!err)
+		enable_64b_cqe_eqe = saved_value.vbool;
+	err = devlink_param_driverinit_value_get(devlink,
+						 MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
+						 &saved_value);
+	if (!err)
+		enable_4k_uar = saved_value.vbool;
+}
+
+static int mlx4_devlink_reload(struct devlink *devlink,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_dev_persistent *persist = dev->persist;
+	int err;
+
+	if (persist->num_vfs)
+		mlx4_warn(persist->dev, "Reload performed on PF, will cause reset on operating Virtual Functions\n");
+	err = mlx4_restart_one(persist->pdev, true, devlink);
+	if (err)
+		mlx4_err(persist->dev, "mlx4_restart_one failed, ret=%d\n", err);
+
+	return err;
+}
+
 static const struct devlink_ops mlx4_devlink_ops = {
 	.port_type_set	= mlx4_devlink_port_type_set,
+	.reload		= mlx4_devlink_reload,
 };
 
 static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
@@ -4064,7 +4113,7 @@ static int restore_current_port_types(struct mlx4_dev *dev,
 	return err;
 }
 
-int mlx4_restart_one(struct pci_dev *pdev)
+int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink)
 {
 	struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev);
 	struct mlx4_dev	 *dev  = persist->dev;
@@ -4077,6 +4126,8 @@ int mlx4_restart_one(struct pci_dev *pdev)
 	memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs));
 
 	mlx4_unload_one(pdev);
+	if (reload)
+		mlx4_devlink_param_load_driverinit_values(devlink);
 	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 1);
 	if (err) {
 		mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n",
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index cb9e923e8399..2ebaa3bee42f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1042,7 +1042,8 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev);
 void mlx4_stop_catas_poll(struct mlx4_dev *dev);
 int mlx4_catas_init(struct mlx4_dev *dev);
 void mlx4_catas_end(struct mlx4_dev *dev);
-int mlx4_restart_one(struct pci_dev *pdev);
+int mlx4_restart_one(struct pci_dev *pdev, bool reload,
+		     struct devlink *devlink);
 int mlx4_register_device(struct mlx4_dev *dev);
 void mlx4_unregister_device(struct mlx4_dev *dev);
 void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type,
-- 
cgit v1.2.3


From f567bcdae2b052bab94be7903863cb9ab47c907c Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Wed, 4 Jul 2018 14:30:36 +0300
Subject: devlink: Add enable_sriov boolean generic parameter

enable_sriov - Enables Single-Root Input/Output Virtualization(SR-IOV)
characteristic of the device.

Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 4 ++++
 net/core/devlink.c    | 6 +++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index a1c230d18911..8ed571385626 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -358,6 +358,7 @@ struct devlink_param_item {
 enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
 	DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
+	DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -370,6 +371,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_MAX_MACS_NAME "max_macs"
 #define DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE DEVLINK_PARAM_TYPE_U32
 
+#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME "enable_sriov"
+#define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE DEVLINK_PARAM_TYPE_BOOL
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 5bbd0aa7571a..470f3dbfecfe 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2615,7 +2615,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_MAX_MACS_NAME,
 		.type = DEVLINK_PARAM_GENERIC_MAX_MACS_TYPE,
 	},
-
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
+		.name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME,
+		.type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
-- 
cgit v1.2.3


From 6354b95eb871beee89b8679a1f576fccc132cf90 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Wed, 4 Jul 2018 14:30:37 +0300
Subject: bnxt_en: Add bnxt_en initial params table and register it.

Create initial devlink parameters table for bnxt_en.
Table consists of a permanent generic parameter.

enable_sriov - Enables Single-Root Input/Output Virtualization(SR-IOV)
characteristic of the device.

Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 121 ++++++++++++++++++++--
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h |  15 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h     |  13 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c     |   9 +-
 4 files changed, 147 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 402fa32f7a88..7bd96ab4f7c5 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -21,16 +21,99 @@ static const struct devlink_ops bnxt_dl_ops = {
 #endif /* CONFIG_BNXT_SRIOV */
 };
 
+static const struct bnxt_dl_nvm_param nvm_params[] = {
+	{DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV, NVM_OFF_ENABLE_SRIOV,
+	 BNXT_NVM_SHARED_CFG, 1},
+};
+
+static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
+			     int msg_len, union devlink_param_value *val)
+{
+	struct hwrm_nvm_variable_input *req = msg;
+	void *data_addr = NULL, *buf = NULL;
+	struct bnxt_dl_nvm_param nvm_param;
+	int bytesize, idx = 0, rc, i;
+	dma_addr_t data_dma_addr;
+
+	/* Get/Set NVM CFG parameter is supported only on PFs */
+	if (BNXT_VF(bp))
+		return -EPERM;
+
+	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
+		if (nvm_params[i].id == param_id) {
+			nvm_param = nvm_params[i];
+			break;
+		}
+	}
+
+	if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
+		idx = bp->pf.port_id;
+	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
+		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
+
+	bytesize = roundup(nvm_param.num_bits, BITS_PER_BYTE) / BITS_PER_BYTE;
+	if (nvm_param.num_bits == 1)
+		buf = &val->vbool;
+
+	data_addr = dma_zalloc_coherent(&bp->pdev->dev, bytesize,
+					&data_dma_addr, GFP_KERNEL);
+	if (!data_addr)
+		return -ENOMEM;
+
+	req->data_addr = cpu_to_le64(data_dma_addr);
+	req->data_len = cpu_to_le16(nvm_param.num_bits);
+	req->option_num = cpu_to_le16(nvm_param.offset);
+	req->index_0 = cpu_to_le16(idx);
+	if (idx)
+		req->dimensions = cpu_to_le16(1);
+
+	if (req->req_type == HWRM_NVM_SET_VARIABLE)
+		memcpy(data_addr, buf, bytesize);
+
+	rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+	if (!rc && req->req_type == HWRM_NVM_GET_VARIABLE)
+		memcpy(buf, data_addr, bytesize);
+
+	dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr);
+	if (rc)
+		return -EIO;
+	return 0;
+}
+
+static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
+				 struct devlink_param_gset_ctx *ctx)
+{
+	struct hwrm_nvm_get_variable_input req = {0};
+	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_GET_VARIABLE, -1, -1);
+	return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
+}
+
+static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
+				 struct devlink_param_gset_ctx *ctx)
+{
+	struct hwrm_nvm_set_variable_input req = {0};
+	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_NVM_SET_VARIABLE, -1, -1);
+	return bnxt_hwrm_nvm_req(bp, id, &req, sizeof(req), &ctx->val);
+}
+
+static const struct devlink_param bnxt_dl_params[] = {
+	DEVLINK_PARAM_GENERIC(ENABLE_SRIOV,
+			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
+			      NULL),
+};
+
 int bnxt_dl_register(struct bnxt *bp)
 {
 	struct devlink *dl;
 	int rc;
 
-	if (!pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV))
-		return 0;
-
-	if (bp->hwrm_spec_code < 0x10803) {
-		netdev_warn(bp->dev, "Firmware does not support SR-IOV E-Switch SWITCHDEV mode.\n");
+	if (bp->hwrm_spec_code < 0x10600) {
+		netdev_warn(bp->dev, "Firmware does not support NVM params");
 		return -ENOTSUPP;
 	}
 
@@ -41,16 +124,34 @@ int bnxt_dl_register(struct bnxt *bp)
 	}
 
 	bnxt_link_bp_to_dl(bp, dl);
-	bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
+	/* Add switchdev eswitch mode setting, if SRIOV supported */
+	if (pci_find_ext_capability(bp->pdev, PCI_EXT_CAP_ID_SRIOV) &&
+	    bp->hwrm_spec_code > 0x10803)
+		bp->eswitch_mode = DEVLINK_ESWITCH_MODE_LEGACY;
+
 	rc = devlink_register(dl, &bp->pdev->dev);
 	if (rc) {
-		bnxt_link_bp_to_dl(bp, NULL);
-		devlink_free(dl);
 		netdev_warn(bp->dev, "devlink_register failed. rc=%d", rc);
-		return rc;
+		goto err_dl_free;
+	}
+
+	rc = devlink_params_register(dl, bnxt_dl_params,
+				     ARRAY_SIZE(bnxt_dl_params));
+	if (rc) {
+		netdev_warn(bp->dev, "devlink_params_register failed. rc=%d",
+			    rc);
+		goto err_dl_unreg;
 	}
 
 	return 0;
+
+err_dl_unreg:
+	devlink_unregister(dl);
+err_dl_free:
+	bnxt_link_bp_to_dl(bp, NULL);
+	devlink_free(dl);
+	return rc;
 }
 
 void bnxt_dl_unregister(struct bnxt *bp)
@@ -60,6 +161,8 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
+	devlink_params_unregister(dl, bnxt_dl_params,
+				  ARRAY_SIZE(bnxt_dl_params));
 	devlink_unregister(dl);
 	devlink_free(dl);
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index e92a35d8b642..2f68dc048390 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -33,6 +33,21 @@ static inline void bnxt_link_bp_to_dl(struct bnxt *bp, struct devlink *dl)
 	}
 }
 
+#define NVM_OFF_ENABLE_SRIOV		401
+
+enum bnxt_nvm_dir_type {
+	BNXT_NVM_SHARED_CFG = 40,
+	BNXT_NVM_PORT_CFG,
+	BNXT_NVM_FUNC_CFG,
+};
+
+struct bnxt_dl_nvm_param {
+	u16 id;
+	u16 offset;
+	u16 dir_type;
+	u16 num_bits;
+};
+
 int bnxt_dl_register(struct bnxt *bp);
 void bnxt_dl_unregister(struct bnxt *bp);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 0fe0ea8dce6c..c75d7fa6dab6 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -6201,6 +6201,19 @@ struct hwrm_nvm_install_update_cmd_err {
 	u8	unused_0[7];
 };
 
+struct hwrm_nvm_variable_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	data_addr;
+	__le16	data_len;
+	__le16	option_num;
+	__le16	dimensions;
+	__le16	index_0;
+};
+
 /* hwrm_nvm_get_variable_input (size:320b/40B) */
 struct hwrm_nvm_get_variable_input {
 	__le16	req_type;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 0745f2dfc80c..e31f5d803c13 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -543,9 +543,14 @@ int bnxt_dl_eswitch_mode_set(struct devlink *devlink, u16 mode)
 		break;
 
 	case DEVLINK_ESWITCH_MODE_SWITCHDEV:
+		if (bp->hwrm_spec_code < 0x10803) {
+			netdev_warn(bp->dev, "FW does not support SRIOV E-Switch SWITCHDEV mode\n");
+			rc = -ENOTSUPP;
+			goto done;
+		}
+
 		if (pci_num_vf(bp->pdev) == 0) {
-			netdev_info(bp->dev,
-				    "Enable VFs before setting switchdev mode");
+			netdev_info(bp->dev, "Enable VFs before setting switchdev mode");
 			rc = -EPERM;
 			goto done;
 		}
-- 
cgit v1.2.3


From 8e15268e3d931944675e6a7ed69c1cda60faa718 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 12:45:53 +0100
Subject: qlogic: netxen: remove various redundant variables

Variables consumer, cmd_desc, end_cnt and no_of_desc are being assigned
but are never used hence they are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'consumer' set but not used [-Wunused-but-set-variable]
warning: variable 'cmd_desc' set but not used [-Wunused-but-set-variable]
warning: variable 'end_cnt' set but not used [-Wunused-but-set-variable]
warning: variable 'no_of_desc' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c   | 10 ++--------
 drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c |  4 +---
 2 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
index 1cd39c9a0345..52ad80621335 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_hw.c
@@ -566,9 +566,8 @@ static int
 netxen_send_cmd_descs(struct netxen_adapter *adapter,
 		struct cmd_desc_type0 *cmd_desc_arr, int nr_desc)
 {
-	u32 i, producer, consumer;
+	u32 i, producer;
 	struct netxen_cmd_buffer *pbuf;
-	struct cmd_desc_type0 *cmd_desc;
 	struct nx_host_tx_ring *tx_ring;
 
 	i = 0;
@@ -580,7 +579,6 @@ netxen_send_cmd_descs(struct netxen_adapter *adapter,
 	__netif_tx_lock_bh(tx_ring->txq);
 
 	producer = tx_ring->producer;
-	consumer = tx_ring->sw_consumer;
 
 	if (nr_desc >= netxen_tx_avail(tx_ring)) {
 		netif_tx_stop_queue(tx_ring->txq);
@@ -595,8 +593,6 @@ netxen_send_cmd_descs(struct netxen_adapter *adapter,
 	}
 
 	do {
-		cmd_desc = &cmd_desc_arr[i];
-
 		pbuf = &tx_ring->cmd_buf_arr[producer];
 		pbuf->skb = NULL;
 		pbuf->frag_count = 0;
@@ -2350,7 +2346,7 @@ static int netxen_md_entry_err_chk(struct netxen_adapter *adapter,
 static int netxen_parse_md_template(struct netxen_adapter *adapter)
 {
 	int num_of_entries, buff_level, e_cnt, esize;
-	int end_cnt = 0, rv = 0, sane_start = 0, sane_end = 0;
+	int rv = 0, sane_start = 0, sane_end = 0;
 	char *dbuff;
 	void *template_buff = adapter->mdump.md_template;
 	char *dump_buff = adapter->mdump.md_capture_buff;
@@ -2386,8 +2382,6 @@ static int netxen_parse_md_template(struct netxen_adapter *adapter)
 			break;
 		case RDEND:
 			entry->hdr.driver_flags |= NX_DUMP_SKIP;
-			if (!sane_end)
-				end_cnt = e_cnt;
 			sane_end += 1;
 			break;
 		case CNTRL:
diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
index 8259e8309320..69aa7fc392c5 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c
@@ -2073,7 +2073,7 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	struct skb_frag_struct *frag;
 
 	u32 producer;
-	int frag_count, no_of_desc;
+	int frag_count;
 	u32 num_txd = tx_ring->num_desc;
 
 	frag_count = skb_shinfo(skb)->nr_frags + 1;
@@ -2093,8 +2093,6 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 
 		frag_count = 1 + skb_shinfo(skb)->nr_frags;
 	}
-	/* 4 fragments per cmd des */
-	no_of_desc = (frag_count + 3) >> 2;
 
 	if (unlikely(netxen_tx_avail(tx_ring) <= TX_STOP_THRESH)) {
 		netif_stop_queue(netdev);
-- 
cgit v1.2.3


From 118e96906dd321ac01e02db6d5c02d5b3e92bbe7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 4 Jul 2018 13:50:11 +0200
Subject: net: ethernet: Make NET_VENDOR_AURORA default to yes

Enabling NET_VENDOR_* Kconfig options does not directly affect the
kernel build.  Hence NET_VENDOR_AURORA should default to yes, like other
NET_VENDOR_* options.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/aurora/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/aurora/Kconfig b/drivers/net/ethernet/aurora/Kconfig
index 8ba7f8ff3434..392f564d8fd4 100644
--- a/drivers/net/ethernet/aurora/Kconfig
+++ b/drivers/net/ethernet/aurora/Kconfig
@@ -1,5 +1,6 @@
 config NET_VENDOR_AURORA
 	bool "Aurora VLSI devices"
+	default y
 	help
 	  If you have a network (Ethernet) device belonging to this class,
 	  say Y.
-- 
cgit v1.2.3


From 0df5f81c481e383f37f9f97eb014c885898b1773 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 4 Jul 2018 13:50:12 +0200
Subject: net: ethernet: Add missing VENDOR to Cadence and Packet Engines
 symbols

The vendor guard Kconfig symbols for Cadence and Packet Engines use a
"NET_" prefix, while all other vendor guards use a "NET_VENDOR_"
prefix.  Hence make them consistent with the rest, and add the missing
trailing "S" for Packet Engines while at it.

As these options don't directly affect the kernel build, and default to
"y", this change has no impact on kernels built with existing
(def)configs.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/Makefile              | 4 ++--
 drivers/net/ethernet/cadence/Kconfig       | 6 +++---
 drivers/net/ethernet/packetengines/Kconfig | 6 +++---
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 8fbfe9ce2fa5..0c3ab7efff8c 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -20,7 +20,7 @@ obj-$(CONFIG_NET_VENDOR_AQUANTIA) += aquantia/
 obj-$(CONFIG_NET_VENDOR_ARC) += arc/
 obj-$(CONFIG_NET_VENDOR_ATHEROS) += atheros/
 obj-$(CONFIG_NET_VENDOR_AURORA) += aurora/
-obj-$(CONFIG_NET_CADENCE) += cadence/
+obj-$(CONFIG_NET_VENDOR_CADENCE) += cadence/
 obj-$(CONFIG_NET_VENDOR_BROADCOM) += broadcom/
 obj-$(CONFIG_NET_VENDOR_BROCADE) += brocade/
 obj-$(CONFIG_NET_CALXEDA_XGMAC) += calxeda/
@@ -68,7 +68,7 @@ obj-$(CONFIG_NET_VENDOR_NVIDIA) += nvidia/
 obj-$(CONFIG_LPC_ENET) += nxp/
 obj-$(CONFIG_NET_VENDOR_OKI) += oki-semi/
 obj-$(CONFIG_ETHOC) += ethoc.o
-obj-$(CONFIG_NET_PACKET_ENGINE) += packetengines/
+obj-$(CONFIG_NET_VENDOR_PACKET_ENGINES) += packetengines/
 obj-$(CONFIG_NET_VENDOR_PASEMI) += pasemi/
 obj-$(CONFIG_NET_VENDOR_QLOGIC) += qlogic/
 obj-$(CONFIG_NET_VENDOR_QUALCOMM) += qualcomm/
diff --git a/drivers/net/ethernet/cadence/Kconfig b/drivers/net/ethernet/cadence/Kconfig
index 427d65a1a126..b9984015ca8c 100644
--- a/drivers/net/ethernet/cadence/Kconfig
+++ b/drivers/net/ethernet/cadence/Kconfig
@@ -2,7 +2,7 @@
 # Atmel device configuration
 #
 
-config NET_CADENCE
+config NET_VENDOR_CADENCE
 	bool "Cadence devices"
 	depends on HAS_IOMEM
 	default y
@@ -16,7 +16,7 @@ config NET_CADENCE
 	  the remaining Atmel network card questions. If you say Y, you will be
 	  asked for your specific card in the following questions.
 
-if NET_CADENCE
+if NET_VENDOR_CADENCE
 
 config MACB
 	tristate "Cadence MACB/GEM support"
@@ -48,4 +48,4 @@ config MACB_PCI
 	  To compile this driver as a module, choose M here: the module
 	  will be called macb_pci.
 
-endif # NET_CADENCE
+endif # NET_VENDOR_CADENCE
diff --git a/drivers/net/ethernet/packetengines/Kconfig b/drivers/net/ethernet/packetengines/Kconfig
index b5ea2a56106e..1df28f2edd1f 100644
--- a/drivers/net/ethernet/packetengines/Kconfig
+++ b/drivers/net/ethernet/packetengines/Kconfig
@@ -2,7 +2,7 @@
 # Packet engine device configuration
 #
 
-config NET_PACKET_ENGINE
+config NET_VENDOR_PACKET_ENGINES
 	bool "Packet Engine devices"
 	default y
 	depends on PCI
@@ -14,7 +14,7 @@ config NET_PACKET_ENGINE
 	  the questions about packet engine devices. If you say Y, you will
 	  be asked for your specific card in the following questions.
 
-if NET_PACKET_ENGINE
+if NET_VENDOR_PACKET_ENGINES
 
 config HAMACHI
 	tristate "Packet Engines Hamachi GNIC-II support"
@@ -40,4 +40,4 @@ config YELLOWFIN
 	  To compile this driver as a module, choose M here: the module
 	  will be called yellowfin.  This is recommended.
 
-endif # NET_PACKET_ENGINE
+endif # NET_VENDOR_PACKET_ENGINES
-- 
cgit v1.2.3


From eec8bb138e6e8214918f30eb7bdf729236d866a8 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 4 Jul 2018 13:50:13 +0200
Subject: net: ethernet: sfc: Make subdir logic consistent with other vendors

Both SFC and SFC_FALCON depend on NET_VENDOR_SOLARFLARE, hence use the
latter to decide whether to descend into the sfc subdirectory.
Move the rule to descend into sfc/falcon to the sfc subdirectory.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Martin Habets <mhabets@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/Makefile     | 3 +--
 drivers/net/ethernet/sfc/Makefile | 2 ++
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 0c3ab7efff8c..22555e7fa752 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -80,8 +80,7 @@ obj-$(CONFIG_NET_VENDOR_SAMSUNG) += samsung/
 obj-$(CONFIG_NET_VENDOR_SEEQ) += seeq/
 obj-$(CONFIG_NET_VENDOR_SILAN) += silan/
 obj-$(CONFIG_NET_VENDOR_SIS) += sis/
-obj-$(CONFIG_SFC) += sfc/
-obj-$(CONFIG_SFC_FALCON) += sfc/falcon/
+obj-$(CONFIG_NET_VENDOR_SOLARFLARE) += sfc/
 obj-$(CONFIG_NET_VENDOR_SGI) += sgi/
 obj-$(CONFIG_NET_VENDOR_SMSC) += smsc/
 obj-$(CONFIG_NET_VENDOR_SOCIONEXT) += socionext/
diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index 3bac58d0f88b..c5c297e78d06 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -6,3 +6,5 @@ sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o siena_sriov.o ef10_sriov.o
 
 obj-$(CONFIG_SFC)	+= sfc.o
+
+obj-$(CONFIG_SFC_FALCON) += falcon/
-- 
cgit v1.2.3


From a132b5a5081ca106193a02e0835e01db7c4055ec Mon Sep 17 00:00:00 2001
From: Sjoerd Simons <sjoerd.simons@collabora.co.uk>
Date: Fri, 30 Mar 2018 15:15:53 +0200
Subject: drm/tilcdc: Defer probe if there are no connectors

During probe there may not be any connectors yet if e.g. the panel
failed or hasn't been probed yet. I hitting this in practice the panels
probing was being delayed due to using a gpio backlight.

Fix this by returning -EPROBE_DEFER so the probing will be retried.

Signed-off-by: Sjoerd Simons <sjoerd.simons@collabora.co.uk>
Signed-off-by: Jyri Sarha <jsarha@ti.com>
---
 drivers/gpu/drm/tilcdc/tilcdc_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/tilcdc/tilcdc_drv.c b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
index b8a5e4ed22e6..0fb300d41a09 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_drv.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_drv.c
@@ -378,7 +378,7 @@ static int tilcdc_init(struct drm_driver *ddrv, struct device *dev)
 	if (!priv->external_connector &&
 	    ((priv->num_encoders == 0) || (priv->num_connectors == 0))) {
 		dev_err(dev, "no encoders/connectors found\n");
-		ret = -ENXIO;
+		ret = -EPROBE_DEFER;
 		goto init_failed;
 	}
 
-- 
cgit v1.2.3


From 4ed88df766704633459d8fddce1c1c87e1acb844 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 5 Jul 2018 12:05:25 +0100
Subject: net: ethernet: sun: remove redundant variables adv and lpa and
 mii_reads

Variables adv and lpa are being assigned but are never used hence they
are redundant and can be removed.  Also remove the unncessary mii_reads
too.

Cleans up clang warnings:
warning: variable 'lpa' set but not used [-Wunused-but-set-variable]
warning: variable 'adv' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sun/niu.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 88c12474a0c3..9319d84bf49f 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -1225,25 +1225,9 @@ static int link_status_1g_rgmii(struct niu *np, int *link_up_p)
 
 	bmsr = err;
 	if (bmsr & BMSR_LSTATUS) {
-		u16 adv, lpa;
-
-		err = mii_read(np, np->phy_addr, MII_ADVERTISE);
-		if (err < 0)
-			goto out;
-		adv = err;
-
-		err = mii_read(np, np->phy_addr, MII_LPA);
-		if (err < 0)
-			goto out;
-		lpa = err;
-
-		err = mii_read(np, np->phy_addr, MII_ESTATUS);
-		if (err < 0)
-			goto out;
 		link_up = 1;
 		current_speed = SPEED_1000;
 		current_duplex = DUPLEX_FULL;
-
 	}
 	lp->active_speed = current_speed;
 	lp->active_duplex = current_duplex;
-- 
cgit v1.2.3


From dfecc759e64b0ea581468fe2359836f1998deac9 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Wed, 4 Jul 2018 17:49:33 +0530
Subject: cxgb4: Fix the condition to check if the card is T5

Use 'chip_ver' rather than 'chip' to check if the card
is T5.

Fixes: e8d452923ae6 ("cxgb4: clean up init_one")
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 96fcbd1c33a3..0d91716a2566 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -5766,7 +5766,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		if (t4_read_reg(adapter, LE_DB_CONFIG_A) & HASHEN_F) {
 			u32 hash_base, hash_reg;
 
-			if (chip <= CHELSIO_T5) {
+			if (chip_ver <= CHELSIO_T5) {
 				hash_reg = LE_DB_TID_HASHBASE_A;
 				hash_base = t4_read_reg(adapter, hash_reg);
 				adapter->tids.hash_base = hash_base / 4;
-- 
cgit v1.2.3


From c53e0c787e672b4edbf719b7c1ec5833db3af2da Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 16:13:59 -0500
Subject: tipc: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Warning level 2 was used: -Wimplicit-fallthrough=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bearer.c | 1 +
 net/tipc/link.c   | 1 +
 2 files changed, 2 insertions(+)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index 2dfb492a7c94..fd6d8f18955c 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -610,6 +610,7 @@ static int tipc_l2_device_event(struct notifier_block *nb, unsigned long evt,
 	case NETDEV_CHANGE:
 		if (netif_carrier_ok(dev))
 			break;
+		/* else: fall through */
 	case NETDEV_UP:
 		test_and_set_bit_lock(0, &b->up);
 		break;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 695acb783969..63860329dbaa 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1063,6 +1063,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb,
 			skb_queue_tail(mc_inputq, skb);
 			return true;
 		}
+		/* else: fall through */
 	case CONN_MANAGER:
 		skb_queue_tail(inputq, skb);
 		return true;
-- 
cgit v1.2.3


From 3cc87d03992fc2a2d57b8a76110463fb18a95d72 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 17:05:00 -0500
Subject: net: decnet: dn_nsp_in: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/dn_nsp_in.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index 1b2120645730..34aba55ed573 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -491,6 +491,7 @@ static void dn_nsp_disc_conf(struct sock *sk, struct sk_buff *skb)
 		break;
 	case DN_RUN:
 		sk->sk_shutdown |= SHUTDOWN_MASK;
+		/* fall through */
 	case DN_CC:
 		scp->state = DN_CN;
 	}
-- 
cgit v1.2.3


From 2cc0608e42aceb38abc9e57a017449b9efc2e4a9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 17:34:37 -0500
Subject: net: core: filter: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Warning level 2 was used: -Wimplicit-fallthrough=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 547fd34589be..b9ec916f4e3a 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4660,6 +4660,7 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 	case BPF_FUNC_trace_printk:
 		if (capable(CAP_SYS_ADMIN))
 			return bpf_get_trace_printk_proto();
+		/* else: fall through */
 	default:
 		return NULL;
 	}
-- 
cgit v1.2.3


From 1c7c5fd916a0ff66501467f1e8e79d3ff8eca112 Mon Sep 17 00:00:00 2001
From: Haneen Mohammed <hamohammed.sa@gmail.com>
Date: Mon, 14 May 2018 17:33:46 +0300
Subject: drm/vkms: Introduce basic VKMS driver

This patch introduces Virtual Kernel Mode-Setting (VKMS) driver. It
creates a very basic kms driver with 1 crtc/encoder/connector/plane.

VKMS driver would be useful for testing, or for running X (or similar)
on headless machines and be able to still use the GPU. Thus it enables
a virtual display without the need for hardware display capability.

Signed-off-by: Haneen Mohammed <hamohammed.sa@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180514143346.GA21695@haneen-vb
---
 drivers/gpu/drm/Kconfig         |   6 ++
 drivers/gpu/drm/Makefile        |   1 +
 drivers/gpu/drm/vkms/Makefile   |   3 +
 drivers/gpu/drm/vkms/vkms_drv.c | 146 ++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/vkms/vkms_drv.h |  13 ++++
 5 files changed, 169 insertions(+)
 create mode 100644 drivers/gpu/drm/vkms/Makefile
 create mode 100644 drivers/gpu/drm/vkms/vkms_drv.c
 create mode 100644 drivers/gpu/drm/vkms/vkms_drv.h

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 2a72d2feb76d..7db3d82cbb27 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -213,6 +213,12 @@ config DRM_VGEM
 	  as used by Mesa's software renderer for enhanced performance.
 	  If M is selected the module will be called vgem.
 
+config DRM_VKMS
+	tristate "Virtual KMS"
+	depends on DRM
+	help
+	  Choose this option to get a virtual kernal mode-setting driver.
+	  If M is selected the module will be called vkms.
 
 source "drivers/gpu/drm/exynos/Kconfig"
 
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 69c13517ea3a..6ae535ca0914 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -69,6 +69,7 @@ obj-$(CONFIG_DRM_SAVAGE)+= savage/
 obj-$(CONFIG_DRM_VMWGFX)+= vmwgfx/
 obj-$(CONFIG_DRM_VIA)	+=via/
 obj-$(CONFIG_DRM_VGEM)	+= vgem/
+obj-$(CONFIG_DRM_VKMS)	+= vkms/
 obj-$(CONFIG_DRM_NOUVEAU) +=nouveau/
 obj-$(CONFIG_DRM_EXYNOS) +=exynos/
 obj-$(CONFIG_DRM_ROCKCHIP) +=rockchip/
diff --git a/drivers/gpu/drm/vkms/Makefile b/drivers/gpu/drm/vkms/Makefile
new file mode 100644
index 000000000000..2aef948d3a34
--- /dev/null
+++ b/drivers/gpu/drm/vkms/Makefile
@@ -0,0 +1,3 @@
+vkms-y := vkms_drv.o
+
+obj-$(CONFIG_DRM_VKMS) += vkms.o
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
new file mode 100644
index 000000000000..b1df08ed23a0
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -0,0 +1,146 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <drm/drmP.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_crtc_helper.h>
+#include "vkms_drv.h"
+
+#define DRIVER_NAME	"vkms"
+#define DRIVER_DESC	"Virtual Kernel Mode Setting"
+#define DRIVER_DATE	"20180514"
+#define DRIVER_MAJOR	1
+#define DRIVER_MINOR	0
+
+static struct vkms_device *vkms_device;
+
+static const struct file_operations vkms_driver_fops = {
+	.owner		= THIS_MODULE,
+	.open		= drm_open,
+	.mmap		= drm_gem_mmap,
+	.unlocked_ioctl	= drm_ioctl,
+	.compat_ioctl	= drm_compat_ioctl,
+	.poll		= drm_poll,
+	.read		= drm_read,
+	.llseek		= no_llseek,
+	.release	= drm_release,
+};
+
+static void vkms_release(struct drm_device *dev)
+{
+	struct vkms_device *vkms = container_of(dev, struct vkms_device, drm);
+
+	platform_device_unregister(vkms->platform);
+	drm_mode_config_cleanup(&vkms->drm);
+	drm_dev_fini(&vkms->drm);
+}
+
+struct drm_driver vkms_driver = {
+	.driver_features	= DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_GEM,
+	.release		= vkms_release,
+	.fops			= &vkms_driver_fops,
+
+	.name			= DRIVER_NAME,
+	.desc			= DRIVER_DESC,
+	.date			= DRIVER_DATE,
+	.major			= DRIVER_MAJOR,
+	.minor			= DRIVER_MINOR,
+};
+
+static const u32 vkms_formats[] = {
+	DRM_FORMAT_XRGB8888,
+};
+
+static void vkms_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs vkms_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = vkms_connector_destroy,
+};
+
+static int __init vkms_init(void)
+{
+	int ret;
+
+	vkms_device = kzalloc(sizeof(*vkms_device), GFP_KERNEL);
+	if (!vkms_device)
+		return -ENOMEM;
+
+	ret = drm_dev_init(&vkms_device->drm, &vkms_driver, NULL);
+	if (ret)
+		goto out_free;
+
+	vkms_device->platform =
+		platform_device_register_simple(DRIVER_NAME, -1, NULL, 0);
+	if (IS_ERR(vkms_device->platform)) {
+		ret = PTR_ERR(vkms_device->platform);
+		goto out_fini;
+	}
+
+	drm_mode_config_init(&vkms_device->drm);
+
+	ret = drm_connector_init(&vkms_device->drm, &vkms_device->connector,
+				 &vkms_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret < 0) {
+		DRM_ERROR("Failed to init connector\n");
+		goto out_unregister;
+	}
+
+	ret = drm_simple_display_pipe_init(&vkms_device->drm,
+					   &vkms_device->pipe,
+					   NULL,
+					   vkms_formats,
+					   ARRAY_SIZE(vkms_formats),
+					   NULL,
+					   &vkms_device->connector);
+	if (ret < 0) {
+		DRM_ERROR("Cannot setup simple display pipe\n");
+		goto out_unregister;
+	}
+
+	ret = drm_dev_register(&vkms_device->drm, 0);
+	if (ret)
+		goto out_unregister;
+
+	drm_connector_register(&vkms_device->connector);
+
+	return 0;
+
+out_unregister:
+	platform_device_unregister(vkms_device->platform);
+out_fini:
+	drm_dev_fini(&vkms_device->drm);
+out_free:
+	kfree(vkms_device);
+
+	return ret;
+}
+
+static void __exit vkms_exit(void)
+{
+	if (!vkms_device) {
+		DRM_INFO("vkms_device is NULL.\n");
+		return;
+	}
+
+	drm_dev_unregister(&vkms_device->drm);
+	drm_dev_put(&vkms_device->drm);
+
+	kfree(vkms_device);
+}
+
+module_init(vkms_init);
+module_exit(vkms_exit);
+
+MODULE_DESCRIPTION(DRIVER_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
new file mode 100644
index 000000000000..c77c5bf5032a
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -0,0 +1,13 @@
+#ifndef _VKMS_DRV_H_
+#define _VKMS_DRV_H_
+
+#include <drm/drm_simple_kms_helper.h>
+
+struct vkms_device {
+	struct drm_device drm;
+	struct platform_device *platform;
+	struct drm_simple_display_pipe pipe;
+	struct drm_connector connector;
+};
+
+#endif /* _VKMS_DRV_H_ */
-- 
cgit v1.2.3


From 41111ce17ee7277cb7451e8a21e319220afc130d Mon Sep 17 00:00:00 2001
From: kbuild test robot <lkp@intel.com>
Date: Tue, 15 May 2018 19:30:52 +0800
Subject: drm/vkms: vkms_driver can be static

Fixes: 58d8108f080c ("drm/vkms: Introduce basic VKMS driver")
Signed-off-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Haneen Mohammed <hamohammed.sa@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180515113052.GA111532@lkp-ib04
---
 drivers/gpu/drm/vkms/vkms_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index b1df08ed23a0..35517b09538e 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -40,7 +40,7 @@ static void vkms_release(struct drm_device *dev)
 	drm_dev_fini(&vkms->drm);
 }
 
-struct drm_driver vkms_driver = {
+static struct drm_driver vkms_driver = {
 	.driver_features	= DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_GEM,
 	.release		= vkms_release,
 	.fops			= &vkms_driver_fops,
-- 
cgit v1.2.3


From c04372ea4abd83ec6c86083f2afe9322515ee293 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Wed, 16 May 2018 20:55:36 -0300
Subject: drm/vkms: Add mode_config initialization

Initialize minimum and maximum width and height of the frame buffers
with default values.

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Reviewed-by: Haneen Mohammed <hamohammed.sa@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/75c55df671f24b037f9172700b479f4bb2fa7c92.1526514457.git.rodrigosiqueiramelo@gmail.com
---
 drivers/gpu/drm/vkms/vkms_drv.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 35517b09538e..aec3f180f96d 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -9,6 +9,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_atomic_helper.h>
 #include "vkms_drv.h"
 
 #define DRIVER_NAME	"vkms"
@@ -17,6 +18,12 @@
 #define DRIVER_MAJOR	1
 #define DRIVER_MINOR	0
 
+#define XRES_MIN    32
+#define YRES_MIN    32
+
+#define XRES_MAX  8192
+#define YRES_MAX  8192
+
 static struct vkms_device *vkms_device;
 
 static const struct file_operations vkms_driver_fops = {
@@ -67,6 +74,11 @@ static const struct drm_connector_funcs vkms_connector_funcs = {
 	.destroy = vkms_connector_destroy,
 };
 
+static const struct drm_mode_config_funcs vkms_mode_funcs = {
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
+};
+
 static int __init vkms_init(void)
 {
 	int ret;
@@ -87,6 +99,11 @@ static int __init vkms_init(void)
 	}
 
 	drm_mode_config_init(&vkms_device->drm);
+	vkms_device->drm.mode_config.funcs = &vkms_mode_funcs;
+	vkms_device->drm.mode_config.min_width = XRES_MIN;
+	vkms_device->drm.mode_config.min_height = YRES_MIN;
+	vkms_device->drm.mode_config.max_width = XRES_MAX;
+	vkms_device->drm.mode_config.max_height = YRES_MAX;
 
 	ret = drm_connector_init(&vkms_device->drm, &vkms_device->connector,
 				 &vkms_connector_funcs,
-- 
cgit v1.2.3


From 854502fa0a38dc77c9e855c95d239a8fd50a9b13 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Wed, 16 May 2018 20:56:21 -0300
Subject: drm/vkms: Add basic CRTC initialization

This commit adds the essential infrastructure for around CRTCs which
is composed of: a new data struct for output data information, a
function for creating planes, and a simple encoder attached to the
connector. Finally, due to the introduction of a new initialization
function, connectors were moved from vkms_drv.c to vkms_display.c.

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Reviewed-by: Haneen Mohammed <hamohammed.sa@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/b6e27bc6a54f5cb340658fa5969f7b48fbfbf1b7.1526514457.git.rodrigosiqueiramelo@gmail.com
---
 drivers/gpu/drm/vkms/Makefile      |  2 +-
 drivers/gpu/drm/vkms/vkms_crtc.c   | 35 +++++++++++++++
 drivers/gpu/drm/vkms/vkms_drv.c    | 60 +++++++------------------
 drivers/gpu/drm/vkms/vkms_drv.h    | 24 ++++++++--
 drivers/gpu/drm/vkms/vkms_output.c | 91 ++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/vkms/vkms_plane.c  | 46 +++++++++++++++++++
 6 files changed, 211 insertions(+), 47 deletions(-)
 create mode 100644 drivers/gpu/drm/vkms/vkms_crtc.c
 create mode 100644 drivers/gpu/drm/vkms/vkms_output.c
 create mode 100644 drivers/gpu/drm/vkms/vkms_plane.c

diff --git a/drivers/gpu/drm/vkms/Makefile b/drivers/gpu/drm/vkms/Makefile
index 2aef948d3a34..3f774a6a9c58 100644
--- a/drivers/gpu/drm/vkms/Makefile
+++ b/drivers/gpu/drm/vkms/Makefile
@@ -1,3 +1,3 @@
-vkms-y := vkms_drv.o
+vkms-y := vkms_drv.o vkms_plane.o vkms_output.o vkms_crtc.o
 
 obj-$(CONFIG_DRM_VKMS) += vkms.o
diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
new file mode 100644
index 000000000000..bf76cd39ece7
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -0,0 +1,35 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc_helper.h>
+
+static const struct drm_crtc_funcs vkms_crtc_funcs = {
+	.set_config             = drm_atomic_helper_set_config,
+	.destroy                = drm_crtc_cleanup,
+	.page_flip              = drm_atomic_helper_page_flip,
+	.reset                  = drm_atomic_helper_crtc_reset,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
+};
+
+int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+		   struct drm_plane *primary, struct drm_plane *cursor)
+{
+	int ret;
+
+	ret = drm_crtc_init_with_planes(dev, crtc, primary, cursor,
+					&vkms_crtc_funcs, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init CRTC\n");
+		return ret;
+	}
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index aec3f180f96d..070613e32934 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -6,7 +6,6 @@
  */
 
 #include <linux/module.h>
-#include <drm/drmP.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
@@ -59,25 +58,24 @@ static struct drm_driver vkms_driver = {
 	.minor			= DRIVER_MINOR,
 };
 
-static const u32 vkms_formats[] = {
-	DRM_FORMAT_XRGB8888,
+static const struct drm_mode_config_funcs vkms_mode_funcs = {
+	.atomic_check = drm_atomic_helper_check,
+	.atomic_commit = drm_atomic_helper_commit,
 };
 
-static void vkms_connector_destroy(struct drm_connector *connector)
+static int vkms_modeset_init(struct vkms_device *vkmsdev)
 {
-	drm_connector_unregister(connector);
-	drm_connector_cleanup(connector);
-}
+	struct drm_device *dev = &vkmsdev->drm;
 
-static const struct drm_connector_funcs vkms_connector_funcs = {
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.destroy = vkms_connector_destroy,
-};
+	drm_mode_config_init(dev);
+	dev->mode_config.funcs = &vkms_mode_funcs;
+	dev->mode_config.min_width = XRES_MIN;
+	dev->mode_config.min_height = YRES_MIN;
+	dev->mode_config.max_width = XRES_MAX;
+	dev->mode_config.max_height = YRES_MAX;
 
-static const struct drm_mode_config_funcs vkms_mode_funcs = {
-	.atomic_check = drm_atomic_helper_check,
-	.atomic_commit = drm_atomic_helper_commit,
-};
+	return vkms_output_init(vkmsdev);
+}
 
 static int __init vkms_init(void)
 {
@@ -98,48 +96,24 @@ static int __init vkms_init(void)
 		goto out_fini;
 	}
 
-	drm_mode_config_init(&vkms_device->drm);
-	vkms_device->drm.mode_config.funcs = &vkms_mode_funcs;
-	vkms_device->drm.mode_config.min_width = XRES_MIN;
-	vkms_device->drm.mode_config.min_height = YRES_MIN;
-	vkms_device->drm.mode_config.max_width = XRES_MAX;
-	vkms_device->drm.mode_config.max_height = YRES_MAX;
-
-	ret = drm_connector_init(&vkms_device->drm, &vkms_device->connector,
-				 &vkms_connector_funcs,
-				 DRM_MODE_CONNECTOR_VIRTUAL);
-	if (ret < 0) {
-		DRM_ERROR("Failed to init connector\n");
-		goto out_unregister;
-	}
-
-	ret = drm_simple_display_pipe_init(&vkms_device->drm,
-					   &vkms_device->pipe,
-					   NULL,
-					   vkms_formats,
-					   ARRAY_SIZE(vkms_formats),
-					   NULL,
-					   &vkms_device->connector);
-	if (ret < 0) {
-		DRM_ERROR("Cannot setup simple display pipe\n");
+	ret = vkms_modeset_init(vkms_device);
+	if (ret)
 		goto out_unregister;
-	}
 
 	ret = drm_dev_register(&vkms_device->drm, 0);
 	if (ret)
 		goto out_unregister;
 
-	drm_connector_register(&vkms_device->connector);
-
 	return 0;
 
 out_unregister:
 	platform_device_unregister(vkms_device->platform);
+
 out_fini:
 	drm_dev_fini(&vkms_device->drm);
+
 out_free:
 	kfree(vkms_device);
-
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index c77c5bf5032a..b0f9d2e61a42 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -1,13 +1,31 @@
 #ifndef _VKMS_DRV_H_
 #define _VKMS_DRV_H_
 
-#include <drm/drm_simple_kms_helper.h>
+#include <drm/drmP.h>
+#include <drm/drm.h>
+#include <drm/drm_encoder.h>
+
+static const u32 vkms_formats[] = {
+	DRM_FORMAT_XRGB8888,
+};
+
+struct vkms_output {
+	struct drm_crtc crtc;
+	struct drm_encoder encoder;
+	struct drm_connector connector;
+};
 
 struct vkms_device {
 	struct drm_device drm;
 	struct platform_device *platform;
-	struct drm_simple_display_pipe pipe;
-	struct drm_connector connector;
+	struct vkms_output output;
 };
 
+int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
+		   struct drm_plane *primary, struct drm_plane *cursor);
+
+int vkms_output_init(struct vkms_device *vkmsdev);
+
+struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev);
+
 #endif /* _VKMS_DRV_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c
new file mode 100644
index 000000000000..48143eac3c12
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_output.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_crtc_helper.h>
+
+static void vkms_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs vkms_connector_funcs = {
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = vkms_connector_destroy,
+};
+
+static const struct drm_encoder_funcs vkms_encoder_funcs = {
+	.destroy = drm_encoder_cleanup,
+};
+
+int vkms_output_init(struct vkms_device *vkmsdev)
+{
+	struct vkms_output *output = &vkmsdev->output;
+	struct drm_device *dev = &vkmsdev->drm;
+	struct drm_connector *connector = &output->connector;
+	struct drm_encoder *encoder = &output->encoder;
+	struct drm_crtc *crtc = &output->crtc;
+	struct drm_plane *primary;
+	int ret;
+
+	primary = vkms_plane_init(vkmsdev);
+	if (IS_ERR(primary))
+		return PTR_ERR(primary);
+
+	ret = vkms_crtc_init(dev, crtc, primary, NULL);
+	if (ret)
+		goto err_crtc;
+
+	ret = drm_connector_init(dev, connector, &vkms_connector_funcs,
+				 DRM_MODE_CONNECTOR_VIRTUAL);
+	if (ret) {
+		DRM_ERROR("Failed to init connector\n");
+		goto err_connector;
+	}
+
+	ret = drm_connector_register(connector);
+	if (ret) {
+		DRM_ERROR("Failed to register connector\n");
+		goto err_connector_register;
+	}
+
+	ret = drm_encoder_init(dev, encoder, &vkms_encoder_funcs,
+			       DRM_MODE_ENCODER_VIRTUAL, NULL);
+	if (ret) {
+		DRM_ERROR("Failed to init encoder\n");
+		goto err_encoder;
+	}
+	encoder->possible_crtcs = 1;
+
+	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	if (ret) {
+		DRM_ERROR("Failed to attach connector to encoder\n");
+		goto err_attach;
+	}
+
+	drm_mode_config_reset(dev);
+
+	return 0;
+
+err_attach:
+	drm_encoder_cleanup(encoder);
+
+err_encoder:
+	drm_connector_unregister(connector);
+
+err_connector_register:
+	drm_connector_cleanup(connector);
+
+err_connector:
+	drm_crtc_cleanup(crtc);
+
+err_crtc:
+	drm_plane_cleanup(primary);
+	return ret;
+}
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
new file mode 100644
index 000000000000..2c25b1d6ab5b
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include "vkms_drv.h"
+#include <drm/drm_plane_helper.h>
+#include <drm/drm_atomic_helper.h>
+
+static const struct drm_plane_funcs vkms_plane_funcs = {
+	.update_plane		= drm_atomic_helper_update_plane,
+	.disable_plane		= drm_atomic_helper_disable_plane,
+	.destroy		= drm_plane_cleanup,
+	.reset			= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
+};
+
+struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev)
+{
+	struct drm_device *dev = &vkmsdev->drm;
+	struct drm_plane *plane;
+	const u32 *formats;
+	int ret, nformats;
+
+	plane = kzalloc(sizeof(*plane), GFP_KERNEL);
+	if (!plane)
+		return ERR_PTR(-ENOMEM);
+
+	formats = vkms_formats;
+	nformats = ARRAY_SIZE(vkms_formats);
+
+	ret = drm_universal_plane_init(dev, plane, 0,
+				       &vkms_plane_funcs,
+				       formats, nformats,
+				       NULL, DRM_PLANE_TYPE_PRIMARY, NULL);
+	if (ret) {
+		kfree(plane);
+		return ERR_PTR(ret);
+	}
+
+	return plane;
+}
-- 
cgit v1.2.3


From c91b007ed137c8497fa89993cc6757a8e81ff99b Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Wed, 16 May 2018 20:56:40 -0300
Subject: drm/vkms: Add extra information about vkms

Add the following additional information: authors and description in
Kconfig.

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Reviewed-by: Haneen Mohammed <hamohammed.sa@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/180770375b0537f1ba1857bdb7fdc71dd201882e.1526514457.git.rodrigosiqueiramelo@gmail.com
---
 drivers/gpu/drm/Kconfig         | 8 ++++++--
 drivers/gpu/drm/vkms/vkms_drv.c | 2 ++
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 7db3d82cbb27..10f9f01123ea 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -214,10 +214,14 @@ config DRM_VGEM
 	  If M is selected the module will be called vgem.
 
 config DRM_VKMS
-	tristate "Virtual KMS"
+	tristate "Virtual KMS (EXPERIMENTAL)"
 	depends on DRM
+	default n
 	help
-	  Choose this option to get a virtual kernal mode-setting driver.
+	  Virtual Kernel Mode-Setting (VKMS) is used for testing or for
+	  running GPU in a headless machines. Choose this option to get
+	  a VKMS.
+
 	  If M is selected the module will be called vkms.
 
 source "drivers/gpu/drm/exynos/Kconfig"
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 070613e32934..740a4cbfed91 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -133,5 +133,7 @@ static void __exit vkms_exit(void)
 module_init(vkms_init);
 module_exit(vkms_exit);
 
+MODULE_AUTHOR("Haneen Mohammed <hamohammed.sa@gmail.com>");
+MODULE_AUTHOR("Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>");
 MODULE_DESCRIPTION(DRIVER_DESC);
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From be01dc33b7b36fd974275ed91b85fcf2c6ae62aa Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Thu, 5 Jul 2018 14:42:49 +0200
Subject: batman-adv: fix checkpatch warning about misspelled "cache"

commit a2d4df9b673c ("spelling.txt: add more spellings to spelling.txt")
introduced the spellcheck of "cache" for checkpatch.pl.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c
index 4229b01ac7b5..95a94160baf8 100644
--- a/net/batman-adv/debugfs.c
+++ b/net/batman-adv/debugfs.c
@@ -117,7 +117,7 @@ static int batadv_bla_backbone_table_open(struct inode *inode,
 
 #ifdef CONFIG_BATMAN_ADV_DAT
 /**
- * batadv_dat_cache_open() - Prepare file handler for reads from dat_chache
+ * batadv_dat_cache_open() - Prepare file handler for reads from dat_cache
  * @inode: inode which was opened
  * @file: file handle to be initialized
  *
-- 
cgit v1.2.3


From 27efd2566cb89b7909366dbb88add8fb1e3d24e2 Mon Sep 17 00:00:00 2001
From: Madhav Chauhan <madhav.chauhan@intel.com>
Date: Thu, 5 Jul 2018 18:31:48 +0530
Subject: drm/i915/icl: Define register for DSI PLL

This patch adds the new registers and corresponding bit definitions
which will be used for programming/enable DSI PLL.

v2: Review comments from Jani N
    - Fix spaces while defining ICL_ESC_CLK_DIV_MASK
    - Define shift and mask for bitfields.

Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530795727-28644-2-git-send-email-madhav.chauhan@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 097000520a80..dc953ee7e3b3 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9538,6 +9538,21 @@ enum skl_power_gate {
 #define MIPIO_TXESC_CLK_DIV2			_MMIO(0x160008)
 #define  GLK_TX_ESC_CLK_DIV2_MASK			0x3FF
 
+#define _ICL_DSI_ESC_CLK_DIV0		0x6b090
+#define _ICL_DSI_ESC_CLK_DIV1		0x6b890
+#define ICL_DSI_ESC_CLK_DIV(port)	_MMIO_PORT((port),	\
+							_ICL_DSI_ESC_CLK_DIV0, \
+							_ICL_DSI_ESC_CLK_DIV1)
+#define _ICL_DPHY_ESC_CLK_DIV0		0x162190
+#define _ICL_DPHY_ESC_CLK_DIV1		0x6C190
+#define ICL_DPHY_ESC_CLK_DIV(port)	_MMIO_PORT((port),	\
+						_ICL_DPHY_ESC_CLK_DIV0, \
+						_ICL_DPHY_ESC_CLK_DIV1)
+#define  ICL_BYTE_CLK_PER_ESC_CLK_MASK		(0x1f << 16)
+#define  ICL_BYTE_CLK_PER_ESC_CLK_SHIFT	16
+#define  ICL_ESC_CLK_DIV_MASK			0x1ff
+#define  ICL_ESC_CLK_DIV_SHIFT			0
+
 /* Gen4+ Timestamp and Pipe Frame time stamp registers */
 #define GEN4_TIMESTAMP		_MMIO(0x2358)
 #define ILK_TIMESTAMP_HI	_MMIO(0x70070)
-- 
cgit v1.2.3


From f0d759f038dcced7dfb756dc54c224f09ad062a2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 28 Jun 2018 17:35:41 -0500
Subject: drm/i915: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 141432
Addresses-Coverity-ID: 141433
Addresses-Coverity-ID: 141434
Addresses-Coverity-ID: 141435
Addresses-Coverity-ID: 141436
Addresses-Coverity-ID: 1357360
Addresses-Coverity-ID: 1357403
Addresses-Coverity-ID: 1357433
Addresses-Coverity-ID: 1392622
Addresses-Coverity-ID: 1415273
Addresses-Coverity-ID: 1435752
Addresses-Coverity-ID: 1441500
Addresses-Coverity-ID: 1454596
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628223541.GA17665@embeddedor.com
---
 drivers/gpu/drm/i915/i915_gem.c         | 1 +
 drivers/gpu/drm/i915/i915_gem_stolen.c  | 1 +
 drivers/gpu/drm/i915/intel_cdclk.c      | 5 +++++
 drivers/gpu/drm/i915/intel_ddi.c        | 1 +
 drivers/gpu/drm/i915/intel_display.c    | 2 ++
 drivers/gpu/drm/i915/intel_dpll_mgr.c   | 3 +++
 drivers/gpu/drm/i915/intel_drv.h        | 1 +
 drivers/gpu/drm/i915/intel_engine_cs.c  | 1 +
 drivers/gpu/drm/i915/intel_runtime_pm.c | 1 +
 drivers/gpu/drm/i915/intel_sdvo.c       | 6 ++++++
 10 files changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 048b722cf27c..0c0a1a959d0b 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2120,6 +2120,7 @@ err:
 		 */
 		if (!i915_terminally_wedged(&dev_priv->gpu_error))
 			return VM_FAULT_SIGBUS;
+		/* else: fall through */
 	case -EAGAIN:
 		/*
 		 * EAGAIN means the gpu is hung and we'll wait for the error
diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 79a347295e00..055f8687776d 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -254,6 +254,7 @@ static void vlv_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	switch (reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK) {
 	default:
 		MISSING_CASE(reg_val & GEN7_STOLEN_RESERVED_SIZE_MASK);
+		/* fall through */
 	case GEN7_STOLEN_RESERVED_1M:
 		*size = 1024 * 1024;
 		break;
diff --git a/drivers/gpu/drm/i915/intel_cdclk.c b/drivers/gpu/drm/i915/intel_cdclk.c
index bf9433d7964d..29075c763428 100644
--- a/drivers/gpu/drm/i915/intel_cdclk.c
+++ b/drivers/gpu/drm/i915/intel_cdclk.c
@@ -316,6 +316,7 @@ static void pnv_get_cdclk(struct drm_i915_private *dev_priv,
 		break;
 	default:
 		DRM_ERROR("Unknown pnv display core clock 0x%04x\n", gcfgc);
+		/* fall through */
 	case GC_DISPLAY_CLOCK_133_MHZ_PNV:
 		cdclk_state->cdclk = 133333;
 		break;
@@ -1797,6 +1798,7 @@ static int icl_calc_cdclk(int min_cdclk, unsigned int ref)
 	switch (ref) {
 	default:
 		MISSING_CASE(ref);
+		/* fall through */
 	case 24000:
 		ranges = ranges_24;
 		break;
@@ -1824,6 +1826,7 @@ static int icl_calc_cdclk_pll_vco(struct drm_i915_private *dev_priv, int cdclk)
 	switch (cdclk) {
 	default:
 		MISSING_CASE(cdclk);
+		/* fall through */
 	case 307200:
 	case 556800:
 	case 652800:
@@ -1896,6 +1899,7 @@ static u8 icl_calc_voltage_level(int cdclk)
 		return 1;
 	default:
 		MISSING_CASE(cdclk);
+		/* fall through */
 	case 652800:
 	case 648000:
 		return 2;
@@ -1913,6 +1917,7 @@ static void icl_get_cdclk(struct drm_i915_private *dev_priv,
 	switch (val & ICL_DSSM_CDCLK_PLL_REFCLK_MASK) {
 	default:
 		MISSING_CASE(val);
+		/* fall through */
 	case ICL_DSSM_CDCLK_PLL_REFCLK_24MHz:
 		cdclk_state->ref = 24000;
 		break;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 0319825b725b..c74b01a52082 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1069,6 +1069,7 @@ static uint32_t icl_pll_to_ddi_pll_sel(struct intel_encoder *encoder,
 	switch (id) {
 	default:
 		MISSING_CASE(id);
+		/* fall through */
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return DDI_CLK_SEL_NONE;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index ce7646265b50..12102224f47a 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9360,6 +9360,7 @@ static bool hsw_get_transcoder_state(struct intel_crtc *crtc,
 		switch (tmp & TRANS_DDI_EDP_INPUT_MASK) {
 		default:
 			WARN(1, "unknown pipe linked to edp transcoder\n");
+			/* fall through */
 		case TRANS_DDI_EDP_INPUT_A_ONOFF:
 		case TRANS_DDI_EDP_INPUT_A_ON:
 			trans_edp_pipe = PIPE_A;
@@ -11024,6 +11025,7 @@ static bool check_digital_port_conflicts(struct drm_atomic_state *state)
 		case INTEL_OUTPUT_DDI:
 			if (WARN_ON(!HAS_DDI(to_i915(dev))))
 				break;
+			/* else: fall through */
 		case INTEL_OUTPUT_DP:
 		case INTEL_OUTPUT_HDMI:
 		case INTEL_OUTPUT_EDP:
diff --git a/drivers/gpu/drm/i915/intel_dpll_mgr.c b/drivers/gpu/drm/i915/intel_dpll_mgr.c
index 57342364fd30..058696b7d6c3 100644
--- a/drivers/gpu/drm/i915/intel_dpll_mgr.c
+++ b/drivers/gpu/drm/i915/intel_dpll_mgr.c
@@ -2566,6 +2566,7 @@ int icl_calc_dp_combo_pll_link(struct drm_i915_private *dev_priv,
 	switch (index) {
 	default:
 		MISSING_CASE(index);
+		/* fall through */
 	case 0:
 		link_clock = 540000;
 		break;
@@ -2639,6 +2640,7 @@ static bool icl_mg_pll_find_divisors(int clock_khz, bool is_dp, bool use_ssc,
 			switch (div1) {
 			default:
 				MISSING_CASE(div1);
+				/* fall through */
 			case 2:
 				hsdiv = 0;
 				break;
@@ -2903,6 +2905,7 @@ static i915_reg_t icl_pll_id_to_enable_reg(enum intel_dpll_id id)
 	switch (id) {
 	default:
 		MISSING_CASE(id);
+		/* fall through */
 	case DPLL_ID_ICL_DPLL0:
 	case DPLL_ID_ICL_DPLL1:
 		return CNL_DPLL_ENABLE(id);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a8073eb02ffa..cdfdebc11ef8 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1253,6 +1253,7 @@ enc_to_dig_port(struct drm_encoder *encoder)
 	switch (intel_encoder->type) {
 	case INTEL_OUTPUT_DDI:
 		WARN_ON(!HAS_DDI(to_i915(encoder->dev)));
+		/* fall through */
 	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_EDP:
 	case INTEL_OUTPUT_HDMI:
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 01862884a436..478c928912c4 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -229,6 +229,7 @@ __intel_engine_context_size(struct drm_i915_private *dev_priv, u8 class)
 		break;
 	default:
 		MISSING_CASE(class);
+		/* fall through */
 	case VIDEO_DECODE_CLASS:
 	case VIDEO_ENHANCEMENT_CLASS:
 	case COPY_ENGINE_CLASS:
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index d81b2cfe1c5e..6b5aa3b074ec 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -3212,6 +3212,7 @@ static void cnl_set_procmon_ref_values(struct drm_i915_private *dev_priv,
 	switch (val & (PROCESS_INFO_MASK | VOLTAGE_INFO_MASK)) {
 	default:
 		MISSING_CASE(val);
+		/* fall through */
 	case VOLTAGE_INFO_0_85V | PROCESS_INFO_DOT_0:
 		procmon = &cnl_procmon_values[PROCMON_0_85V_DOT_0];
 		break;
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 9d9229a1f36c..36f81a96b8f6 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1340,6 +1340,7 @@ static void intel_sdvo_pre_enable(struct intel_encoder *intel_encoder,
 	switch (crtc_state->pixel_multiplier) {
 	default:
 		WARN(1, "unknown pixel multiplier specified\n");
+		/* fall through */
 	case 1: rate = SDVO_CLOCK_RATE_MULT_1X; break;
 	case 2: rate = SDVO_CLOCK_RATE_MULT_2X; break;
 	case 4: rate = SDVO_CLOCK_RATE_MULT_4X; break;
@@ -2316,14 +2317,19 @@ intel_sdvo_guess_ddc_bus(struct intel_sdvo *sdvo)
 	switch (sdvo->controlled_output) {
 	case SDVO_OUTPUT_LVDS1:
 		mask |= SDVO_OUTPUT_LVDS1;
+		/* fall through */
 	case SDVO_OUTPUT_LVDS0:
 		mask |= SDVO_OUTPUT_LVDS0;
+		/* fall through */
 	case SDVO_OUTPUT_TMDS1:
 		mask |= SDVO_OUTPUT_TMDS1;
+		/* fall through */
 	case SDVO_OUTPUT_TMDS0:
 		mask |= SDVO_OUTPUT_TMDS0;
+		/* fall through */
 	case SDVO_OUTPUT_RGB1:
 		mask |= SDVO_OUTPUT_RGB1;
+		/* fall through */
 	case SDVO_OUTPUT_RGB0:
 		mask |= SDVO_OUTPUT_RGB0;
 		break;
-- 
cgit v1.2.3


From 0d99889109892396a8164bf6dd178e36d3fe3166 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:07 +0300
Subject: drm/fb-helper: Eliminate the .best_encoder() usage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of using the .best_encoder() hook to figure out whether a given
connector+crtc combo will work, let's instead do what userspace does and
just iterate over all the encoders for the connector, and then check
each crtc against each encoder's possible_crtcs bitmask.

v2: Avoid oopsing on NULL encoders (Daniel)
    s/connector_crtc_ok/connector_has_possible_crtc/

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-2-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/drm_fb_helper.c | 41 ++++++++++++++++++++++++-----------------
 1 file changed, 24 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index cab14f253384..b37f06317d51 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -2323,6 +2323,27 @@ retry:
 	return true;
 }
 
+static bool connector_has_possible_crtc(struct drm_connector *connector,
+					struct drm_crtc *crtc)
+{
+	int i;
+
+	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
+		struct drm_encoder *encoder;
+
+		if (connector->encoder_ids[i] == 0)
+			break;
+
+		encoder = drm_encoder_find(connector->dev, NULL,
+					   connector->encoder_ids[i]);
+
+		if (encoder->possible_crtcs & drm_crtc_mask(crtc))
+			return true;
+	}
+
+	return false;
+}
+
 static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 			  struct drm_fb_helper_crtc **best_crtcs,
 			  struct drm_display_mode **modes,
@@ -2331,7 +2352,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 	int c, o;
 	struct drm_connector *connector;
 	const struct drm_connector_helper_funcs *connector_funcs;
-	struct drm_encoder *encoder;
 	int my_score, best_score, score;
 	struct drm_fb_helper_crtc **crtcs, *crtc;
 	struct drm_fb_helper_connector *fb_helper_conn;
@@ -2362,20 +2382,6 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 
 	connector_funcs = connector->helper_private;
 
-	/*
-	 * If the DRM device implements atomic hooks and ->best_encoder() is
-	 * NULL we fallback to the default drm_atomic_helper_best_encoder()
-	 * helper.
-	 */
-	if (drm_drv_uses_atomic_modeset(fb_helper->dev) &&
-	    !connector_funcs->best_encoder)
-		encoder = drm_atomic_helper_best_encoder(connector);
-	else
-		encoder = connector_funcs->best_encoder(connector);
-
-	if (!encoder)
-		goto out;
-
 	/*
 	 * select a crtc for this connector and then attempt to configure
 	 * remaining connectors
@@ -2383,7 +2389,8 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 	for (c = 0; c < fb_helper->crtc_count; c++) {
 		crtc = &fb_helper->crtc_info[c];
 
-		if ((encoder->possible_crtcs & (1 << c)) == 0)
+		if (!connector_has_possible_crtc(connector,
+						 crtc->mode_set.crtc))
 			continue;
 
 		for (o = 0; o < n; o++)
@@ -2410,7 +2417,7 @@ static int drm_pick_crtcs(struct drm_fb_helper *fb_helper,
 			       sizeof(struct drm_fb_helper_crtc *));
 		}
 	}
-out:
+
 	kfree(crtcs);
 	return best_score;
 }
-- 
cgit v1.2.3


From 20431c05ae682ff2ad387945738fc129d9751d6e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:08 +0300
Subject: drm/i915: Nuke intel_mst_best_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With the fb-helper no longer relying on the non-atomic .best_encoder()
we can eliminate the hook from the MST encoder.

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-3-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/i915/intel_dp_mst.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 5890500a3a8b..0f012fbe34eb 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -403,20 +403,10 @@ static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *c
 	return &intel_dp->mst_encoders[crtc->pipe]->base.base;
 }
 
-static struct drm_encoder *intel_mst_best_encoder(struct drm_connector *connector)
-{
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct intel_dp *intel_dp = intel_connector->mst_port;
-	if (!intel_dp)
-		return NULL;
-	return &intel_dp->mst_encoders[0]->base.base;
-}
-
 static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_funcs = {
 	.get_modes = intel_dp_mst_get_modes,
 	.mode_valid = intel_dp_mst_mode_valid,
 	.atomic_best_encoder = intel_mst_atomic_best_encoder,
-	.best_encoder = intel_mst_best_encoder,
 	.atomic_check = intel_dp_mst_atomic_check,
 };
 
-- 
cgit v1.2.3


From 83aefbb887b59df0b3520965c3701e01deacfc52 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:09 +0300
Subject: drm: Add drm_connector_for_each_possible_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a convenience macro for iterating connector->encoder_ids[].
Isolates the users from the implementation details.

Note that we don't seem to pass the file_priv down to drm_encoder_find()
because encoders apparently don't get leased. No idea why
drm_encoder_finc() even takes the file_priv actually.

Also use ARRAY_SIZE() when populating the array to avoid spreading
knowledge about the array size all over.

v2: Hide the drm_encoder_find() in the macro, and
    rename the macro appropriately (Daniel)
v3: Fix kernel docs (Daniel)

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-4-ville.syrjala@linux.intel.com
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_connector.c    | 21 +++++++++------------
 drivers/gpu/drm/drm_fb_helper.c    | 11 ++---------
 drivers/gpu/drm/drm_probe_helper.c | 10 +++-------
 include/drm/drm_connector.h        | 13 +++++++++++++
 4 files changed, 27 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index b09b3a3e4024..7387c0377e51 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -321,7 +321,7 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 	if (WARN_ON(connector->encoder))
 		return -EINVAL;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
+	for (i = 0; i < ARRAY_SIZE(connector->encoder_ids); i++) {
 		if (connector->encoder_ids[i] == 0) {
 			connector->encoder_ids[i] = encoder->base.id;
 			return 0;
@@ -1706,22 +1706,19 @@ int drm_mode_getconnector(struct drm_device *dev, void *data,
 	if (!connector)
 		return -ENOENT;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++)
-		if (connector->encoder_ids[i] != 0)
-			encoders_count++;
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		encoders_count++;
 
 	if ((out_resp->count_encoders >= encoders_count) && encoders_count) {
 		copied = 0;
 		encoder_ptr = (uint32_t __user *)(unsigned long)(out_resp->encoders_ptr);
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] != 0) {
-				if (put_user(connector->encoder_ids[i],
-					     encoder_ptr + copied)) {
-					ret = -EFAULT;
-					goto out;
-				}
-				copied++;
+
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
+			if (put_user(encoder->base.id, encoder_ptr + copied)) {
+				ret = -EFAULT;
+				goto out;
 			}
+			copied++;
 		}
 	}
 	out_resp->count_encoders = encoders_count;
diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index b37f06317d51..d697c1c4a067 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -2326,17 +2326,10 @@ retry:
 static bool connector_has_possible_crtc(struct drm_connector *connector,
 					struct drm_crtc *crtc)
 {
+	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		struct drm_encoder *encoder;
-
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					   connector->encoder_ids[i]);
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->possible_crtcs & drm_crtc_mask(crtc))
 			return true;
 	}
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 527743394150..1a901fe9e23e 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -88,9 +88,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 			    struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
-	uint32_t *ids = connector->encoder_ids;
 	enum drm_mode_status ret = MODE_OK;
-	unsigned int i;
+	struct drm_encoder *encoder;
+	int i;
 
 	/* Step 1: Validate against connector */
 	ret = drm_connector_mode_valid(connector, mode);
@@ -98,13 +98,9 @@ drm_mode_validate_pipeline(struct drm_display_mode *mode,
 		return ret;
 
 	/* Step 2: Validate against encoders and crtcs */
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		struct drm_encoder *encoder = drm_encoder_find(dev, NULL, ids[i]);
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		struct drm_crtc *crtc;
 
-		if (!encoder)
-			continue;
-
 		ret = drm_encoder_mode_valid(encoder, mode);
 		if (ret != MODE_OK) {
 			/* No point in continuing for crtc check as this encoder
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index bf0f0f0786d3..bd6f30cf0755 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -1199,4 +1199,17 @@ void drm_connector_list_iter_end(struct drm_connector_list_iter *iter);
 #define drm_for_each_connector_iter(connector, iter) \
 	while ((connector = drm_connector_list_iter_next(iter)))
 
+/**
+ * drm_connector_for_each_possible_encoder - iterate connector's possible encoders
+ * @connector: &struct drm_connector pointer
+ * @encoder: &struct drm_encoder pointer used as cursor
+ * @__i: int iteration cursor, for macro-internal use
+ */
+#define drm_connector_for_each_possible_encoder(connector, encoder, __i) \
+	for ((__i) = 0; (__i) < ARRAY_SIZE((connector)->encoder_ids) && \
+		     (connector)->encoder_ids[(__i)] != 0; (__i)++) \
+		for_each_if((encoder) = \
+			    drm_encoder_find((connector)->dev, NULL, \
+					     (connector)->encoder_ids[(__i)])) \
+
 #endif
-- 
cgit v1.2.3


From 98c0e348c09575edccdd63e9d2938f090b0d8739 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:10 +0300
Subject: drm/amdgpu: Use drm_connector_for_each_possible_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_connector_for_each_possible_encoder() for iterating
connector->encoder_ids[]. A bit more convenient not having
to deal with the implementation details.

v2: Replace drm_for_each_connector_encoder_ids() with
    drm_connector_for_each_possible_encoder() (Daniel)

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-5-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c | 81 +++++++-------------------
 drivers/gpu/drm/amd/amdgpu/dce_virtual.c       | 15 ++---
 2 files changed, 25 insertions(+), 71 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 8e66851eb427..881f7cb7ae6e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -212,30 +212,21 @@ static void
 amdgpu_connector_update_scratch_regs(struct drm_connector *connector,
 				      enum drm_connector_status status)
 {
-	struct drm_encoder *best_encoder = NULL;
-	struct drm_encoder *encoder = NULL;
+	struct drm_encoder *best_encoder;
+	struct drm_encoder *encoder;
 	const struct drm_connector_helper_funcs *connector_funcs = connector->helper_private;
 	bool connected;
 	int i;
 
 	best_encoder = connector_funcs->best_encoder(connector);
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if ((encoder == best_encoder) && (status == connector_status_connected))
 			connected = true;
 		else
 			connected = false;
 
 		amdgpu_atombios_encoder_set_bios_scratch_regs(connector, encoder, connected);
-
 	}
 }
 
@@ -246,17 +237,11 @@ amdgpu_connector_find_encoder(struct drm_connector *connector,
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == encoder_type)
 			return encoder;
 	}
+
 	return NULL;
 }
 
@@ -360,11 +345,13 @@ static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector)
 static struct drm_encoder *
 amdgpu_connector_best_single_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
+	struct drm_encoder *encoder;
+	int i;
+
+	/* pick the first one */
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
 
-	/* pick the encoder ids */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
 	return NULL;
 }
 
@@ -985,9 +972,8 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 	struct drm_device *dev = connector->dev;
 	struct amdgpu_device *adev = dev->dev_private;
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
-	struct drm_encoder *encoder = NULL;
 	const struct drm_encoder_helper_funcs *encoder_funcs;
-	int i, r;
+	int r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
@@ -1077,14 +1063,10 @@ amdgpu_connector_dvi_detect(struct drm_connector *connector, bool force)
 
 	/* find analog encoder */
 	if (amdgpu_connector->dac_load_detect) {
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == 0)
-				break;
-
-			encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-			if (!encoder)
-				continue;
+		struct drm_encoder *encoder;
+		int i;
 
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
 			if (encoder->encoder_type != DRM_MODE_ENCODER_DAC &&
 			    encoder->encoder_type != DRM_MODE_ENCODER_TVDAC)
 				continue;
@@ -1132,18 +1114,11 @@ exit:
 static struct drm_encoder *
 amdgpu_connector_dvi_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct amdgpu_connector *amdgpu_connector = to_amdgpu_connector(connector);
 	struct drm_encoder *encoder;
 	int i;
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
 
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (amdgpu_connector->use_digital == true) {
 			if (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)
 				return encoder;
@@ -1158,8 +1133,9 @@ amdgpu_connector_dvi_encoder(struct drm_connector *connector)
 
 	/* then check use digitial */
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -1296,15 +1272,7 @@ u16 amdgpu_connector_encoder_get_dp_bridge_encoder_id(struct drm_connector *conn
 	struct amdgpu_encoder *amdgpu_encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 
 		switch (amdgpu_encoder->encoder_id) {
@@ -1326,14 +1294,7 @@ static bool amdgpu_connector_encoder_is_hbr2(struct drm_connector *connector)
 	int i;
 	bool found = false;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-		encoder = drm_encoder_find(connector->dev, NULL,
-					connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		amdgpu_encoder = to_amdgpu_encoder(encoder);
 		if (amdgpu_encoder->caps & ATOM_ENCODER_CAP_RECORD_HBR2)
 			found = true;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index dbf2ccd0c744..016f15093173 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -269,25 +269,18 @@ static int dce_virtual_early_init(void *handle)
 static struct drm_encoder *
 dce_virtual_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL)
 			return encoder;
 	}
 
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
-- 
cgit v1.2.3


From ddba766dd07e67d0ca70b632d3bbac72234b547e Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Mon, 2 Jul 2018 18:29:27 +0300
Subject: drm/nouveau: Use drm_connector_for_each_possible_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_connector_for_each_possible_encoder() for iterating
connector->encoder_ids[]. A bit more convenient not having
to deal with the implementation details.

v2: Replace drm_for_each_connector_encoder_ids() with
    drm_connector_for_each_possible_encoder() (Daniel)
v3: Initialize nv_encoder to NULL to shut up gcc/smatch

Cc: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Ben Skeggs <bskeggs@redhat.com>
Cc: nouveau@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702152927.13351-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/nouveau/nouveau_connector.c | 23 ++++-------------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 7b557c354307..bb46c1d489cf 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -363,19 +363,11 @@ module_param_named(hdmimhz, nouveau_hdmimhz, int, 0400);
 struct nouveau_encoder *
 find_encoder(struct drm_connector *connector, int type)
 {
-	struct drm_device *dev = connector->dev;
 	struct nouveau_encoder *nv_encoder;
 	struct drm_encoder *enc;
-	int i, id;
-
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		id = connector->encoder_ids[i];
-		if (!id)
-			break;
+	int i;
 
-		enc = drm_encoder_find(dev, NULL, id);
-		if (!enc)
-			continue;
+	drm_connector_for_each_possible_encoder(connector, enc, i) {
 		nv_encoder = nouveau_encoder(enc);
 
 		if (type == DCB_OUTPUT_ANY ||
@@ -420,7 +412,7 @@ nouveau_connector_ddc_detect(struct drm_connector *connector)
 	struct nouveau_connector *nv_connector = nouveau_connector(connector);
 	struct nouveau_drm *drm = nouveau_drm(dev);
 	struct nvkm_gpio *gpio = nvxx_gpio(&drm->client.device);
-	struct nouveau_encoder *nv_encoder;
+	struct nouveau_encoder *nv_encoder = NULL;
 	struct drm_encoder *encoder;
 	int i, panel = -ENODEV;
 
@@ -436,14 +428,7 @@ nouveau_connector_ddc_detect(struct drm_connector *connector)
 		}
 	}
 
-	for (i = 0; nv_encoder = NULL, i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		int id = connector->encoder_ids[i];
-		if (id == 0)
-			break;
-
-		encoder = drm_encoder_find(dev, NULL, id);
-		if (!encoder)
-			continue;
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		nv_encoder = nouveau_encoder(encoder);
 
 		if (nv_encoder->dcb->type == DCB_OUTPUT_DP) {
-- 
cgit v1.2.3


From 7b71ca249b265fe69ab3152a15bc6c305554a7da Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:12 +0300
Subject: drm/radeon: Use drm_connector_for_each_possible_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_connector_for_each_possible_encoder() for iterating
connector->encoder_ids[]. A bit more convenient not having
to deal with the implementation details.

v2: Replace drm_for_each_connector_encoder_ids() with
    drm_connector_for_each_possible_encoder() (Daniel)

Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: "Christian König" <christian.koenig@amd.com>
Cc: "David (ChunMing) Zhou" <David1.Zhou@amd.com>
Cc: Harry Wentland <harry.wentland@amd.com>
Cc: amd-gfx@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-7-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/radeon/radeon_connectors.c | 90 +++++++++---------------------
 1 file changed, 26 insertions(+), 64 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 2aea2bdff99b..0655698f2956 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -244,23 +244,15 @@ radeon_connector_update_scratch_regs(struct drm_connector *connector, enum drm_c
 {
 	struct drm_device *dev = connector->dev;
 	struct radeon_device *rdev = dev->dev_private;
-	struct drm_encoder *best_encoder = NULL;
-	struct drm_encoder *encoder = NULL;
+	struct drm_encoder *best_encoder;
+	struct drm_encoder *encoder;
 	const struct drm_connector_helper_funcs *connector_funcs = connector->helper_private;
 	bool connected;
 	int i;
 
 	best_encoder = connector_funcs->best_encoder(connector);
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL,
-					   connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if ((encoder == best_encoder) && (status == connector_status_connected))
 			connected = true;
 		else
@@ -270,7 +262,6 @@ radeon_connector_update_scratch_regs(struct drm_connector *connector, enum drm_c
 			radeon_atombios_connected_scratch_regs(connector, encoder, connected);
 		else
 			radeon_combios_connected_scratch_regs(connector, encoder, connected);
-
 	}
 }
 
@@ -279,17 +270,11 @@ static struct drm_encoder *radeon_find_encoder(struct drm_connector *connector,
 	struct drm_encoder *encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (encoder->encoder_type == encoder_type)
 			return encoder;
 	}
+
 	return NULL;
 }
 
@@ -393,10 +378,13 @@ static int radeon_ddc_get_modes(struct drm_connector *connector)
 
 static struct drm_encoder *radeon_best_single_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
-	/* pick the encoder ids */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	struct drm_encoder *encoder;
+	int i;
+
+	/* pick the first one */
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -436,19 +424,19 @@ radeon_connector_analog_encoder_conflict_solve(struct drm_connector *connector,
 	struct drm_device *dev = connector->dev;
 	struct drm_connector *conflict;
 	struct radeon_connector *radeon_conflict;
-	int i;
 
 	list_for_each_entry(conflict, &dev->mode_config.connector_list, head) {
+		struct drm_encoder *enc;
+		int i;
+
 		if (conflict == connector)
 			continue;
 
 		radeon_conflict = to_radeon_connector(conflict);
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (conflict->encoder_ids[i] == 0)
-				break;
 
+		drm_connector_for_each_possible_encoder(conflict, enc, i) {
 			/* if the IDs match */
-			if (conflict->encoder_ids[i] == encoder->base.id) {
+			if (enc == encoder) {
 				if (conflict->status != connector_status_connected)
 					continue;
 
@@ -1256,7 +1244,7 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder = NULL;
 	const struct drm_encoder_helper_funcs *encoder_funcs;
-	int i, r;
+	int r;
 	enum drm_connector_status ret = connector_status_disconnected;
 	bool dret = false, broken_edid = false;
 
@@ -1374,15 +1362,9 @@ radeon_dvi_detect(struct drm_connector *connector, bool force)
 
 	/* find analog encoder */
 	if (radeon_connector->dac_load_detect) {
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == 0)
-				break;
-
-			encoder = drm_encoder_find(connector->dev, NULL,
-						   connector->encoder_ids[i]);
-			if (!encoder)
-				continue;
+		int i;
 
+		drm_connector_for_each_possible_encoder(connector, encoder, i) {
 			if (encoder->encoder_type != DRM_MODE_ENCODER_DAC &&
 			    encoder->encoder_type != DRM_MODE_ENCODER_TVDAC)
 				continue;
@@ -1458,18 +1440,11 @@ exit:
 /* okay need to be smart in here about which encoder to pick */
 static struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
 {
-	int enc_id = connector->encoder_ids[0];
 	struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 	struct drm_encoder *encoder;
 	int i;
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
 
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		if (radeon_connector->use_digital == true) {
 			if (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)
 				return encoder;
@@ -1484,8 +1459,9 @@ static struct drm_encoder *radeon_dvi_encoder(struct drm_connector *connector)
 
 	/* then check use digitial */
 	/* pick the first one */
-	if (enc_id)
-		return drm_encoder_find(connector->dev, NULL, enc_id);
+	drm_connector_for_each_possible_encoder(connector, encoder, i)
+		return encoder;
+
 	return NULL;
 }
 
@@ -1628,14 +1604,7 @@ u16 radeon_connector_encoder_get_dp_bridge_encoder_id(struct drm_connector *conn
 	struct radeon_encoder *radeon_encoder;
 	int i;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		radeon_encoder = to_radeon_encoder(encoder);
 
 		switch (radeon_encoder->encoder_id) {
@@ -1657,14 +1626,7 @@ static bool radeon_connector_encoder_is_hbr2(struct drm_connector *connector)
 	int i;
 	bool found = false;
 
-	for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-		if (connector->encoder_ids[i] == 0)
-			break;
-
-		encoder = drm_encoder_find(connector->dev, NULL, connector->encoder_ids[i]);
-		if (!encoder)
-			continue;
-
+	drm_connector_for_each_possible_encoder(connector, encoder, i) {
 		radeon_encoder = to_radeon_encoder(encoder);
 		if (radeon_encoder->caps & ATOM_ENCODER_CAP_RECORD_HBR2)
 			found = true;
-- 
cgit v1.2.3


From 38cb8d96933eb07231073efdcd24a6ffa43b23e6 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:13 +0300
Subject: drm: Add drm_connector_has_possible_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a small helper for checking whether a connector and
encoder are associated with each other.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-8-ville.syrjala@linux.intel.com
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/drm_connector.c | 23 +++++++++++++++++++++++
 include/drm/drm_connector.h     |  3 +++
 2 files changed, 26 insertions(+)

diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 7387c0377e51..5ada0640de5a 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -331,6 +331,29 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 }
 EXPORT_SYMBOL(drm_mode_connector_attach_encoder);
 
+/**
+ * drm_connector_has_possible_encoder - check if the connector and encoder are assosicated with each other
+ * @connector: the connector
+ * @encoder: the encoder
+ *
+ * Returns:
+ * True if @encoder is one of the possible encoders for @connector.
+ */
+bool drm_connector_has_possible_encoder(struct drm_connector *connector,
+					struct drm_encoder *encoder)
+{
+	struct drm_encoder *enc;
+	int i;
+
+	drm_connector_for_each_possible_encoder(connector, enc, i) {
+		if (enc == encoder)
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(drm_connector_has_possible_encoder);
+
 static void drm_mode_remove(struct drm_connector *connector,
 			    struct drm_display_mode *mode)
 {
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index bd6f30cf0755..ad397dfc042b 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -1187,6 +1187,9 @@ struct drm_connector *
 drm_connector_list_iter_next(struct drm_connector_list_iter *iter);
 void drm_connector_list_iter_end(struct drm_connector_list_iter *iter);
 
+bool drm_connector_has_possible_encoder(struct drm_connector *connector,
+					struct drm_encoder *encoder);
+
 /**
  * drm_for_each_connector_iter - connector_list iterator macro
  * @connector: &struct drm_connector pointer used as cursor
-- 
cgit v1.2.3


From f8222409d1ac7a53de4c89db5a6dc268d523f6c7 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:14 +0300
Subject: drm/msm: Use drm_connector_has_possible_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_connector_has_possible_encoder() for checking
whether the encoder has an associated connector.

v2: Replace the drm_for_each_connector_encoder_ids() loop
    with a simple drm_connector_has_possible_encoder() call

Cc: Rob Clark <robdclark@gmail.com>
Cc: linux-arm-msm@vger.kernel.org
Cc: freedreno@lists.freedesktop.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-9-ville.syrjala@linux.intel.com
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 4cb1cb68878b..4beba3f7d067 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -751,12 +751,8 @@ struct drm_connector *msm_dsi_manager_ext_bridge_init(u8 id)
 	connector_list = &dev->mode_config.connector_list;
 
 	list_for_each_entry(connector, connector_list, head) {
-		int i;
-
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++) {
-			if (connector->encoder_ids[i] == encoder->base.id)
-				return connector;
-		}
+		if (drm_connector_has_possible_encoder(connector, encoder))
+			return connector;
 	}
 
 	return ERR_PTR(-ENODEV);
-- 
cgit v1.2.3


From 0b7510d15e14ba628ab9bacd6516e3f6a35ba21f Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:13:15 +0300
Subject: drm/tilcdc: Use drm_connector_has_possible_encoder()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_connector_has_possible_encoder() for checking
whether the encoder has an associated connector.

v2: Replace the drm_for_each_connector_encoder_ids() loop
    with a simple drm_connector_has_possible_encoder() call

Cc: Jyri Sarha <jsarha@ti.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628131315.14156-10-ville.syrjala@linux.intel.com
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Jyri Sarha <jsarha@ti.com>
---
 drivers/gpu/drm/tilcdc/tilcdc_external.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/tilcdc/tilcdc_external.c b/drivers/gpu/drm/tilcdc/tilcdc_external.c
index d651bdd6597e..b4eaf9bc87f8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_external.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_external.c
@@ -103,12 +103,11 @@ struct drm_connector *tilcdc_encoder_find_connector(struct drm_device *ddev,
 						    struct drm_encoder *encoder)
 {
 	struct drm_connector *connector;
-	int i;
 
-	list_for_each_entry(connector, &ddev->mode_config.connector_list, head)
-		for (i = 0; i < DRM_CONNECTOR_MAX_ENCODER; i++)
-			if (connector->encoder_ids[i] == encoder->base.id)
-				return connector;
+	list_for_each_entry(connector, &ddev->mode_config.connector_list, head) {
+		if (drm_connector_has_possible_encoder(connector, encoder))
+			return connector;
+	}
 
 	dev_err(ddev->dev, "No connector found for %s encoder (id %d)\n",
 		encoder->name, encoder->base.id);
-- 
cgit v1.2.3


From 846c87a068f4b72e200357b899ca4dcc92ef42c4 Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Wed, 29 Mar 2017 17:42:34 +0100
Subject: drm: mali-dp: Add support for writeback on DP550/DP650

Mali-DP display processors are able to write the composition result to a
memory buffer via the SE.

Add entry points in the HAL for enabling/disabling this feature, and
implement support for it on DP650 and DP550. DP500 acts differently and
so is omitted from this change.

Changes since v3:
 - Fix missing vsync interrupt for DP550

Signed-off-by: Liviu Dudau <Liviu.Dudau@arm.com>
Signed-off-by: Brian Starkey <brian.starkey@arm.com>
[rebased and fixed conflicts]
Signed-off-by: Mihail Atanassov <mihail.atanassov@arm.com>
---
 drivers/gpu/drm/arm/malidp_hw.c   | 55 +++++++++++++++++++++++++++++++++++++--
 drivers/gpu/drm/arm/malidp_hw.h   | 17 ++++++++++++
 drivers/gpu/drm/arm/malidp_regs.h | 15 +++++++++++
 3 files changed, 85 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 069783e715f1..461e62653a36 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -588,6 +588,49 @@ static long malidp550_se_calc_mclk(struct malidp_hw_device *hwdev,
 	return ret;
 }
 
+static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev,
+				     dma_addr_t *addrs, s32 *pitches,
+				     int num_planes, u16 w, u16 h, u32 fmt_id)
+{
+	u32 base = MALIDP550_SE_MEMWRITE_BASE;
+	u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	/* enable the scaling engine block */
+	malidp_hw_setbits(hwdev, MALIDP_SCALE_ENGINE_EN, de_base + MALIDP_DE_DISPLAY_FUNC);
+
+	malidp_hw_write(hwdev, fmt_id, base + MALIDP_MW_FORMAT);
+	switch (num_planes) {
+	case 2:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE);
+		/* fall through */
+	case 1:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[0], base + MALIDP_MW_P1_STRIDE);
+		break;
+	default:
+		WARN(1, "Invalid number of planes");
+	}
+
+	malidp_hw_write(hwdev, MALIDP_DE_H_ACTIVE(w) | MALIDP_DE_V_ACTIVE(h),
+			MALIDP550_SE_MEMWRITE_OUT_SIZE);
+	malidp_hw_setbits(hwdev, MALIDP550_SE_MEMWRITE_ONESHOT | MALIDP_SE_MEMWRITE_EN,
+			  MALIDP550_SE_CONTROL);
+
+	return 0;
+}
+
+static void malidp550_disable_memwrite(struct malidp_hw_device *hwdev)
+{
+	u32 base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	malidp_hw_clearbits(hwdev, MALIDP550_SE_MEMWRITE_ONESHOT | MALIDP_SE_MEMWRITE_EN,
+			    MALIDP550_SE_CONTROL);
+	malidp_hw_clearbits(hwdev, MALIDP_SCALE_ENGINE_EN, base + MALIDP_DE_DISPLAY_FUNC);
+}
+
 static int malidp650_query_hw(struct malidp_hw_device *hwdev)
 {
 	u32 conf = malidp_hw_read(hwdev, MALIDP550_CONFIG_ID);
@@ -674,9 +717,11 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 			.se_irq_map = {
 				.irq_mask = MALIDP550_SE_IRQ_EOW |
 					    MALIDP550_SE_IRQ_AXI_ERR,
+				.vsync_irq = MALIDP550_SE_IRQ_EOW,
 			},
 			.dc_irq_map = {
-				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID,
+				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID |
+					    MALIDP550_DC_IRQ_SE,
 				.vsync_irq = MALIDP550_DC_IRQ_CONF_VALID,
 			},
 			.pixel_formats = malidp550_de_formats,
@@ -692,6 +737,8 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 		.rotmem_required = malidp550_rotmem_required,
 		.se_set_scaling_coeffs = malidp550_se_set_scaling_coeffs,
 		.se_calc_mclk = malidp550_se_calc_mclk,
+		.enable_memwrite = malidp550_enable_memwrite,
+		.disable_memwrite = malidp550_disable_memwrite,
 		.features = 0,
 	},
 	[MALIDP_650] = {
@@ -712,9 +759,11 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 			.se_irq_map = {
 				.irq_mask = MALIDP550_SE_IRQ_EOW |
 					    MALIDP550_SE_IRQ_AXI_ERR,
+				.vsync_irq = MALIDP550_SE_IRQ_EOW,
 			},
 			.dc_irq_map = {
-				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID,
+				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID |
+					    MALIDP550_DC_IRQ_SE,
 				.vsync_irq = MALIDP550_DC_IRQ_CONF_VALID,
 			},
 			.pixel_formats = malidp550_de_formats,
@@ -730,6 +779,8 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 		.rotmem_required = malidp550_rotmem_required,
 		.se_set_scaling_coeffs = malidp550_se_set_scaling_coeffs,
 		.se_calc_mclk = malidp550_se_calc_mclk,
+		.enable_memwrite = malidp550_enable_memwrite,
+		.disable_memwrite = malidp550_disable_memwrite,
 		.features = 0,
 	},
 };
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index b5dd6c73ec9f..72cc22f82836 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -177,6 +177,23 @@ struct malidp_hw {
 	long (*se_calc_mclk)(struct malidp_hw_device *hwdev,
 			     struct malidp_se_config *se_config,
 			     struct videomode *vm);
+	/**
+	 * Enable writing to memory the content of the next frame
+	 * @param hwdev - malidp_hw_device structure containing the HW description
+	 * @param addrs - array of addresses for each plane
+	 * @param pitches - array of pitches for each plane
+	 * @param num_planes - number of planes to be written
+	 * @param w - width of the output frame
+	 * @param h - height of the output frame
+	 * @param fmt_id - internal format ID of output buffer
+	 */
+	int (*enable_memwrite)(struct malidp_hw_device *hwdev, dma_addr_t *addrs,
+			       s32 *pitches, int num_planes, u16 w, u16 h, u32 fmt_id);
+
+	/*
+	 * Disable the writing to memory of the next frame's content.
+	 */
+	void (*disable_memwrite)(struct malidp_hw_device *hwdev);
 
 	u8 features;
 };
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
index 149024fb4432..e2b2c496225e 100644
--- a/drivers/gpu/drm/arm/malidp_regs.h
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -66,6 +66,8 @@
 #define   MALIDP_DISP_FUNC_GAMMA	(1 << 0)
 #define   MALIDP_DISP_FUNC_CADJ		(1 << 4)
 #define   MALIDP_DISP_FUNC_ILACED	(1 << 8)
+#define   MALIDP_SCALE_ENGINE_EN	(1 << 16)
+#define   MALIDP_SE_MEMWRITE_EN		(2 << 5)
 
 /* register offsets for IRQ management */
 #define MALIDP_REG_STATUS		0x00000
@@ -153,6 +155,16 @@
 		(((x) & MALIDP_SE_ENH_LIMIT_MASK) << 16)
 #define   MALIDP_SE_ENH_COEFF0			0x04
 
+
+/* register offsets relative to MALIDP5x0_SE_MEMWRITE_BASE */
+#define MALIDP_MW_FORMAT		0x00000
+#define MALIDP_MW_P1_STRIDE		0x00004
+#define MALIDP_MW_P2_STRIDE		0x00008
+#define MALIDP_MW_P1_PTR_LOW		0x0000c
+#define MALIDP_MW_P1_PTR_HIGH		0x00010
+#define MALIDP_MW_P2_PTR_LOW		0x0002c
+#define MALIDP_MW_P2_PTR_HIGH		0x00030
+
 /* register offsets and bits specific to DP500 */
 #define MALIDP500_ADDR_SPACE_SIZE	0x01000
 #define MALIDP500_DC_BASE		0x00000
@@ -217,6 +229,9 @@
 #define MALIDP550_DE_PERF_BASE		0x00500
 #define MALIDP550_SE_BASE		0x08000
 #define MALIDP550_SE_CONTROL		0x08010
+#define   MALIDP550_SE_MEMWRITE_ONESHOT	(1 << 7)
+#define MALIDP550_SE_MEMWRITE_OUT_SIZE	0x08030
+#define MALIDP550_SE_MEMWRITE_BASE	0x08100
 #define MALIDP550_DC_BASE		0x0c000
 #define MALIDP550_DC_CONTROL		0x0c010
 #define   MALIDP550_DC_CONFIG_REQ	(1 << 16)
-- 
cgit v1.2.3


From a67bbbe225c281f441533d55cd9dce5c2ae207a5 Mon Sep 17 00:00:00 2001
From: Brian Starkey <brian.starkey@arm.com>
Date: Wed, 29 Mar 2017 17:42:35 +0100
Subject: drm: mali-dp: Add RGB writeback formats for DP550/DP650

Add a layer bit for the SE memory-write, and add it to the pixel format
matrix for DP550/DP650.

Signed-off-by: Brian Starkey <brian.starkey@arm.com>
[rebased and fixed conflicts]
Signed-off-by: Mihail Atanassov <mihail.atanassov@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_hw.c | 22 +++++++++++-----------
 drivers/gpu/drm/arm/malidp_hw.h |  1 +
 2 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 461e62653a36..c98b3e02dd54 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -47,27 +47,27 @@ static const struct malidp_format_id malidp500_de_formats[] = {
 
 #define MALIDP_COMMON_FORMATS \
 	/*    fourcc,   layers supporting the format,      internal id   */ \
-	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 0) }, \
-	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 1) }, \
-	{ DRM_FORMAT_RGBA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 2) }, \
-	{ DRM_FORMAT_BGRA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(0, 3) }, \
+	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 0) }, \
+	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 1) }, \
+	{ DRM_FORMAT_RGBA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 2) }, \
+	{ DRM_FORMAT_BGRA1010102, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(0, 3) }, \
 	{ DRM_FORMAT_ARGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 0) }, \
 	{ DRM_FORMAT_ABGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 1) }, \
 	{ DRM_FORMAT_RGBA8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 2) }, \
 	{ DRM_FORMAT_BGRA8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(1, 3) }, \
-	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 0) }, \
-	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 1) }, \
-	{ DRM_FORMAT_RGBX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 2) }, \
-	{ DRM_FORMAT_BGRX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART, MALIDP_ID(2, 3) }, \
-	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(3, 0) }, \
-	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(3, 1) }, \
+	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 0) }, \
+	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 1) }, \
+	{ DRM_FORMAT_RGBX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 2) }, \
+	{ DRM_FORMAT_BGRX8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | DE_SMART | SE_MEMWRITE, MALIDP_ID(2, 3) }, \
+	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(3, 0) }, \
+	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(3, 1) }, \
 	{ DRM_FORMAT_RGBA5551, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 0) }, \
 	{ DRM_FORMAT_ABGR1555, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 1) }, \
 	{ DRM_FORMAT_RGB565, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 2) }, \
 	{ DRM_FORMAT_BGR565, DE_VIDEO1 | DE_GRAPHICS1 | DE_VIDEO2, MALIDP_ID(4, 3) }, \
 	{ DRM_FORMAT_YUYV, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 2) },	\
 	{ DRM_FORMAT_UYVY, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 3) },	\
-	{ DRM_FORMAT_NV12, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 6) },	\
+	{ DRM_FORMAT_NV12, DE_VIDEO1 | DE_VIDEO2 | SE_MEMWRITE, MALIDP_ID(5, 6) },	\
 	{ DRM_FORMAT_YUV420, DE_VIDEO1 | DE_VIDEO2, MALIDP_ID(5, 7) }
 
 static const struct malidp_format_id malidp550_de_formats[] = {
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index 72cc22f82836..a242e97cf642 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -33,6 +33,7 @@ enum {
 	DE_GRAPHICS2 = BIT(2), /* used only in DP500 */
 	DE_VIDEO2 = BIT(3),
 	DE_SMART = BIT(4),
+	SE_MEMWRITE = BIT(5),
 };
 
 struct malidp_format_id {
-- 
cgit v1.2.3


From 1cb3cbe732d9bedd4046bbeb2726d1699cdfabce Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Tue, 10 Apr 2018 17:25:57 +0100
Subject: drm/mali-dp: Add writeback support for DP500.

Mali DP500 behaves differently from the rest of the Mali DP IP,
in that it does not have a one-shot mode and keeps writing the
content of the current frame to the provided memory area until
stopped. As a way of emulating the one-shot behaviour, we are
going to use the CVAL interrupt that is being raised at the
start of each frame, during prefetch phase, to act as End-of-Write
signal, but with a twist: we are going to disable the memory
write engine right after we're notified that it has been enabled,
using the knowledge that the bit controlling the enabling will
only be acted upon on the next vblank/prefetch.

CVAL interrupt will fire durint the next prefetch phase every time
the global CVAL bit gets set, so we need a state byte to track
the memory write enabling. We also need to pay attention during the
disabling of the memory write engine as that requires the CVAL bit
to be set in the control register, but we don't want to do that
during an atomic commit, as it will write into the hardware a partial
state.

Reviewed-by: Brian Starkey <brian.starkey@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c  | 16 ++++++--
 drivers/gpu/drm/arm/malidp_drv.h  |  4 ++
 drivers/gpu/drm/arm/malidp_hw.c   | 82 +++++++++++++++++++++++++++++++++++++--
 drivers/gpu/drm/arm/malidp_hw.h   |  5 ++-
 drivers/gpu/drm/arm/malidp_regs.h |  3 +-
 5 files changed, 101 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 0a788d76ed5f..ab2d27e8bdd9 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -170,14 +170,15 @@ static int malidp_set_and_wait_config_valid(struct drm_device *drm)
 	struct malidp_hw_device *hwdev = malidp->dev;
 	int ret;
 
-	atomic_set(&malidp->config_valid, 0);
 	hwdev->hw->set_config_valid(hwdev);
 	/* don't wait for config_valid flag if we are in config mode */
-	if (hwdev->hw->in_config_mode(hwdev))
+	if (hwdev->hw->in_config_mode(hwdev)) {
+		atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_DONE);
 		return 0;
+	}
 
 	ret = wait_event_interruptible_timeout(malidp->wq,
-			atomic_read(&malidp->config_valid) == 1,
+			atomic_read(&malidp->config_valid) == MALIDP_CONFIG_VALID_DONE,
 			msecs_to_jiffies(MALIDP_CONF_VALID_TIMEOUT));
 
 	return (ret > 0) ? 0 : -ETIMEDOUT;
@@ -216,12 +217,19 @@ static void malidp_atomic_commit_hw_done(struct drm_atomic_state *state)
 static void malidp_atomic_commit_tail(struct drm_atomic_state *state)
 {
 	struct drm_device *drm = state->dev;
+	struct malidp_drm *malidp = drm->dev_private;
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *old_crtc_state;
 	int i;
 
 	pm_runtime_get_sync(drm->dev);
 
+	/*
+	 * set config_valid to a special value to let IRQ handlers
+	 * know that we are updating registers
+	 */
+	atomic_set(&malidp->config_valid, MALIDP_CONFIG_START);
+
 	drm_atomic_helper_commit_modeset_disables(drm, state);
 
 	for_each_old_crtc_in_state(state, crtc, old_crtc_state, i) {
@@ -588,7 +596,7 @@ static int malidp_bind(struct device *dev)
 		out_depth = (out_depth << 8) | (output_width[i] & 0xf);
 	malidp_hw_write(hwdev, out_depth, hwdev->hw->map.out_depth_base);
 
-	atomic_set(&malidp->config_valid, 0);
+	atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_INIT);
 	init_waitqueue_head(&malidp->wq);
 
 	ret = malidp_init(drm);
diff --git a/drivers/gpu/drm/arm/malidp_drv.h b/drivers/gpu/drm/arm/malidp_drv.h
index c70989b93387..e8c41cf1b5bd 100644
--- a/drivers/gpu/drm/arm/malidp_drv.h
+++ b/drivers/gpu/drm/arm/malidp_drv.h
@@ -18,6 +18,10 @@
 #include <drm/drmP.h>
 #include "malidp_hw.h"
 
+#define MALIDP_CONFIG_VALID_INIT	0
+#define MALIDP_CONFIG_VALID_DONE	1
+#define MALIDP_CONFIG_START		0xd0
+
 struct malidp_drm {
 	struct malidp_hw_device *dev;
 	struct drm_crtc crtc;
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index c98b3e02dd54..0f6290b2f768 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -22,6 +22,13 @@
 #include "malidp_drv.h"
 #include "malidp_hw.h"
 
+enum {
+	MW_NOT_ENABLED = 0,	/* SE writeback not enabled */
+	MW_ONESHOT,		/* SE in one-shot mode for writeback */
+	MW_START,		/* SE started writeback */
+	MW_STOP,		/* SE finished writeback */
+};
+
 static const struct malidp_format_id malidp500_de_formats[] = {
 	/*    fourcc,   layers supporting the format,     internal id  */
 	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  0 },
@@ -368,6 +375,51 @@ static long malidp500_se_calc_mclk(struct malidp_hw_device *hwdev,
 	return ret;
 }
 
+static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev,
+				     dma_addr_t *addrs, s32 *pitches,
+				     int num_planes, u16 w, u16 h, u32 fmt_id)
+{
+	u32 base = MALIDP500_SE_MEMWRITE_BASE;
+	u32 de_base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	/* enable the scaling engine block */
+	malidp_hw_setbits(hwdev, MALIDP_SCALE_ENGINE_EN, de_base + MALIDP_DE_DISPLAY_FUNC);
+
+	hwdev->mw_state = MW_START;
+
+	malidp_hw_write(hwdev, fmt_id, base + MALIDP_MW_FORMAT);
+	switch (num_planes) {
+	case 2:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[1]), base + MALIDP_MW_P2_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[1], base + MALIDP_MW_P2_STRIDE);
+		/* fall through */
+	case 1:
+		malidp_hw_write(hwdev, lower_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_LOW);
+		malidp_hw_write(hwdev, upper_32_bits(addrs[0]), base + MALIDP_MW_P1_PTR_HIGH);
+		malidp_hw_write(hwdev, pitches[0], base + MALIDP_MW_P1_STRIDE);
+		break;
+	default:
+		WARN(1, "Invalid number of planes");
+	}
+
+	malidp_hw_write(hwdev, MALIDP_DE_H_ACTIVE(w) | MALIDP_DE_V_ACTIVE(h),
+			MALIDP500_SE_MEMWRITE_OUT_SIZE);
+	malidp_hw_setbits(hwdev, MALIDP_SE_MEMWRITE_EN, MALIDP500_SE_CONTROL);
+
+	return 0;
+}
+
+static void malidp500_disable_memwrite(struct malidp_hw_device *hwdev)
+{
+	u32 base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
+
+	if (hwdev->mw_state == MW_START)
+		hwdev->mw_state = MW_STOP;
+	malidp_hw_clearbits(hwdev, MALIDP_SE_MEMWRITE_EN, MALIDP500_SE_CONTROL);
+	malidp_hw_clearbits(hwdev, MALIDP_SCALE_ENGINE_EN, base + MALIDP_DE_DISPLAY_FUNC);
+}
+
 static int malidp550_query_hw(struct malidp_hw_device *hwdev)
 {
 	u32 conf = malidp_hw_read(hwdev, MALIDP550_CONFIG_ID);
@@ -598,6 +650,8 @@ static int malidp550_enable_memwrite(struct malidp_hw_device *hwdev,
 	/* enable the scaling engine block */
 	malidp_hw_setbits(hwdev, MALIDP_SCALE_ENGINE_EN, de_base + MALIDP_DE_DISPLAY_FUNC);
 
+	hwdev->mw_state = MW_ONESHOT;
+
 	malidp_hw_write(hwdev, fmt_id, base + MALIDP_MW_FORMAT);
 	switch (num_planes) {
 	case 2:
@@ -678,8 +732,9 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 			},
 			.se_irq_map = {
 				.irq_mask = MALIDP500_SE_IRQ_CONF_MODE |
+					    MALIDP500_SE_IRQ_CONF_VALID |
 					    MALIDP500_SE_IRQ_GLOBAL,
-				.vsync_irq = 0,
+				.vsync_irq = MALIDP500_SE_IRQ_CONF_VALID,
 			},
 			.dc_irq_map = {
 				.irq_mask = MALIDP500_DE_IRQ_CONF_VALID,
@@ -698,6 +753,8 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 		.rotmem_required = malidp500_rotmem_required,
 		.se_set_scaling_coeffs = malidp500_se_set_scaling_coeffs,
 		.se_calc_mclk = malidp500_se_calc_mclk,
+		.enable_memwrite = malidp500_enable_memwrite,
+		.disable_memwrite = malidp500_disable_memwrite,
 		.features = MALIDP_DEVICE_LV_HAS_3_STRIDES,
 	},
 	[MALIDP_550] = {
@@ -842,7 +899,7 @@ static irqreturn_t malidp_de_irq(int irq, void *arg)
 			malidp->event = NULL;
 			spin_unlock(&drm->event_lock);
 		}
-		atomic_set(&malidp->config_valid, 1);
+		atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_DONE);
 		ret = IRQ_WAKE_THREAD;
 	}
 
@@ -936,7 +993,25 @@ static irqreturn_t malidp_se_irq(int irq, void *arg)
 	mask = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_MASKIRQ);
 	status = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_STATUS);
 	status &= mask;
-	/* ToDo: status decoding and firing up of VSYNC and page flip events */
+
+	if (status & se->vsync_irq) {
+		switch (hwdev->mw_state) {
+		case MW_STOP:
+			/* disable writeback after stop */
+			hwdev->mw_state = MW_NOT_ENABLED;
+			break;
+		case MW_START:
+			/* writeback started, need to emulate one-shot mode */
+			hw->disable_memwrite(hwdev);
+			/*
+			 * only set config_valid HW bit if there is no
+			 * other update in progress
+			 */
+			if (atomic_read(&malidp->config_valid) != MALIDP_CONFIG_START)
+				hw->set_config_valid(hwdev);
+			break;
+		}
+	}
 
 	malidp_hw_clear_irq(hwdev, MALIDP_SE_BLOCK, status);
 
@@ -966,6 +1041,7 @@ int malidp_se_irq_init(struct drm_device *drm, int irq)
 		return ret;
 	}
 
+	hwdev->mw_state = MW_NOT_ENABLED;
 	malidp_hw_enable_irq(hwdev, MALIDP_SE_BLOCK,
 			     hwdev->hw->map.se_irq_map.irq_mask);
 
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index a242e97cf642..c479738b81af 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -178,7 +178,7 @@ struct malidp_hw {
 	long (*se_calc_mclk)(struct malidp_hw_device *hwdev,
 			     struct malidp_se_config *se_config,
 			     struct videomode *vm);
-	/**
+	/*
 	 * Enable writing to memory the content of the next frame
 	 * @param hwdev - malidp_hw_device structure containing the HW description
 	 * @param addrs - array of addresses for each plane
@@ -232,6 +232,9 @@ struct malidp_hw_device {
 	/* track the device PM state */
 	bool pm_suspended;
 
+	/* track the SE memory writeback state */
+	u8 mw_state;
+
 	/* size of memory used for rotating layers, up to two banks available */
 	u32 rotation_memory[2];
 };
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
index e2b2c496225e..93b198f3af86 100644
--- a/drivers/gpu/drm/arm/malidp_regs.h
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -198,7 +198,8 @@
 #define MALIDP500_DE_LG2_PTR_BASE	0x0031c
 #define MALIDP500_SE_BASE		0x00c00
 #define MALIDP500_SE_CONTROL		0x00c0c
-#define MALIDP500_SE_PTR_BASE		0x00e0c
+#define MALIDP500_SE_MEMWRITE_OUT_SIZE	0x00c2c
+#define MALIDP500_SE_MEMWRITE_BASE	0x00e00
 #define MALIDP500_DC_IRQ_BASE		0x00f00
 #define MALIDP500_CONFIG_VALID		0x00f00
 #define MALIDP500_CONFIG_ID		0x00fd4
-- 
cgit v1.2.3


From 09368e32a97587d4e118b800c206b4c86b4db845 Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Thu, 12 Apr 2018 18:13:26 +0100
Subject: drm/mali-dp: Add RGB writeback formats for DP500.

Annotate the pixel format matrix for DP500 with the memory-write flag
for formats that are supported by the SE memwrite engine.

Reviewed-by: Brian Starkey <brian.starkey@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_hw.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 0f6290b2f768..36c7e910069a 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -31,12 +31,12 @@ enum {
 
 static const struct malidp_format_id malidp500_de_formats[] = {
 	/*    fourcc,   layers supporting the format,     internal id  */
-	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  0 },
-	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  1 },
+	{ DRM_FORMAT_ARGB2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  0 },
+	{ DRM_FORMAT_ABGR2101010, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  1 },
 	{ DRM_FORMAT_ARGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  2 },
 	{ DRM_FORMAT_ABGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  3 },
-	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  4 },
-	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  5 },
+	{ DRM_FORMAT_XRGB8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  4 },
+	{ DRM_FORMAT_XBGR8888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2 | SE_MEMWRITE,  5 },
 	{ DRM_FORMAT_RGB888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  6 },
 	{ DRM_FORMAT_BGR888, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  7 },
 	{ DRM_FORMAT_RGBA5551, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2,  8 },
@@ -45,7 +45,7 @@ static const struct malidp_format_id malidp500_de_formats[] = {
 	{ DRM_FORMAT_BGR565, DE_VIDEO1 | DE_GRAPHICS1 | DE_GRAPHICS2, 11 },
 	{ DRM_FORMAT_UYVY, DE_VIDEO1, 12 },
 	{ DRM_FORMAT_YUYV, DE_VIDEO1, 13 },
-	{ DRM_FORMAT_NV12, DE_VIDEO1, 14 },
+	{ DRM_FORMAT_NV12, DE_VIDEO1 | SE_MEMWRITE, 14 },
 	{ DRM_FORMAT_YUV420, DE_VIDEO1, 15 },
 };
 
-- 
cgit v1.2.3


From 8cbc5caf36ef7a299b5cbedf55f27fd898d700bf Mon Sep 17 00:00:00 2001
From: Brian Starkey <brian.starkey@arm.com>
Date: Thu, 2 Nov 2017 16:49:51 +0000
Subject: drm: mali-dp: Add writeback connector

Mali-DP has a memory writeback engine which can be used to write the
composition result to a memory buffer. Expose this functionality as a
DRM writeback connector on supported hardware.

Changes since v1:
 Daniel Vetter:
 - Don't require a modeset when writeback routing changes
 - Make writeback connector always disconnected

Changes since v2:
 - Rebase onto new drm_writeback_connector
 - Add reset callback, allocating subclassed state
 Daniel Vetter:
 - Squash out-fence support into this commit
 Gustavo Padovan:
 - Don't signal fence directly from driver (and drop malidp_mw_job)

Changes since v3:
 - Modifications to fit with Mali-DP commit tail changes

Signed-off-by: Brian Starkey <brian.starkey@arm.com>
[rebased and fixed conflicts]
Signed-off-by: Mihail Atanassov <mihail.atanassov@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/Makefile      |   1 +
 drivers/gpu/drm/arm/malidp_crtc.c |  10 ++
 drivers/gpu/drm/arm/malidp_drv.c  |  19 ++-
 drivers/gpu/drm/arm/malidp_drv.h  |   3 +
 drivers/gpu/drm/arm/malidp_hw.c   |   5 +
 drivers/gpu/drm/arm/malidp_mw.c   | 250 ++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/arm/malidp_mw.h   |  14 +++
 drivers/gpu/drm/drm_atomic.c      |   4 +
 8 files changed, 301 insertions(+), 5 deletions(-)
 create mode 100644 drivers/gpu/drm/arm/malidp_mw.c
 create mode 100644 drivers/gpu/drm/arm/malidp_mw.h

diff --git a/drivers/gpu/drm/arm/Makefile b/drivers/gpu/drm/arm/Makefile
index bb8b158ff90d..3bf31d1a4722 100644
--- a/drivers/gpu/drm/arm/Makefile
+++ b/drivers/gpu/drm/arm/Makefile
@@ -1,4 +1,5 @@
 hdlcd-y := hdlcd_drv.o hdlcd_crtc.o
 obj-$(CONFIG_DRM_HDLCD)	+= hdlcd.o
 mali-dp-y := malidp_drv.o malidp_hw.o malidp_planes.o malidp_crtc.o
+mali-dp-y += malidp_mw.o
 obj-$(CONFIG_DRM_MALI_DISPLAY)	+= mali-dp.o
diff --git a/drivers/gpu/drm/arm/malidp_crtc.c b/drivers/gpu/drm/arm/malidp_crtc.c
index fcc62bc60f6a..ef44202fb43f 100644
--- a/drivers/gpu/drm/arm/malidp_crtc.c
+++ b/drivers/gpu/drm/arm/malidp_crtc.c
@@ -411,6 +411,16 @@ static int malidp_crtc_atomic_check(struct drm_crtc *crtc,
 		}
 	}
 
+	/* If only the writeback routing has changed, we don't need a modeset */
+	if (state->connectors_changed) {
+		u32 old_mask = crtc->state->connector_mask;
+		u32 new_mask = state->connector_mask;
+
+		if ((old_mask ^ new_mask) ==
+		    (1 << drm_connector_index(&malidp->mw_connector.base)))
+			state->connectors_changed = false;
+	}
+
 	ret = malidp_crtc_atomic_check_gamma(crtc, state);
 	ret = ret ? ret : malidp_crtc_atomic_check_ctm(crtc, state);
 	ret = ret ? ret : malidp_crtc_atomic_check_scaling(crtc, state);
diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index ab2d27e8bdd9..e58a759fd3be 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -31,6 +31,7 @@
 #include <drm/drm_of.h>
 
 #include "malidp_drv.h"
+#include "malidp_mw.h"
 #include "malidp_regs.h"
 #include "malidp_hw.h"
 
@@ -238,7 +239,9 @@ static void malidp_atomic_commit_tail(struct drm_atomic_state *state)
 		malidp_atomic_commit_se_config(crtc, old_crtc_state);
 	}
 
-	drm_atomic_helper_commit_planes(drm, state, 0);
+	drm_atomic_helper_commit_planes(drm, state, DRM_PLANE_COMMIT_ACTIVE_ONLY);
+
+	malidp_mw_atomic_commit(drm, state);
 
 	drm_atomic_helper_commit_modeset_enables(drm, state);
 
@@ -276,12 +279,18 @@ static int malidp_init(struct drm_device *drm)
 	drm->mode_config.helper_private = &malidp_mode_config_helpers;
 
 	ret = malidp_crtc_init(drm);
-	if (ret) {
-		drm_mode_config_cleanup(drm);
-		return ret;
-	}
+	if (ret)
+		goto crtc_fail;
+
+	ret = malidp_mw_connector_init(drm);
+	if (ret)
+		goto crtc_fail;
 
 	return 0;
+
+crtc_fail:
+	drm_mode_config_cleanup(drm);
+	return ret;
 }
 
 static void malidp_fini(struct drm_device *drm)
diff --git a/drivers/gpu/drm/arm/malidp_drv.h b/drivers/gpu/drm/arm/malidp_drv.h
index e8c41cf1b5bd..5febd4b43e05 100644
--- a/drivers/gpu/drm/arm/malidp_drv.h
+++ b/drivers/gpu/drm/arm/malidp_drv.h
@@ -13,6 +13,8 @@
 #ifndef __MALIDP_DRV_H__
 #define __MALIDP_DRV_H__
 
+#include <drm/drm_writeback.h>
+#include <drm/drm_encoder.h>
 #include <linux/mutex.h>
 #include <linux/wait.h>
 #include <drm/drmP.h>
@@ -25,6 +27,7 @@
 struct malidp_drm {
 	struct malidp_hw_device *dev;
 	struct drm_crtc crtc;
+	struct drm_writeback_connector mw_connector;
 	wait_queue_head_t wq;
 	struct drm_pending_vblank_event *event;
 	atomic_t config_valid;
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 36c7e910069a..449b7ef0a77f 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -21,6 +21,7 @@
 
 #include "malidp_drv.h"
 #include "malidp_hw.h"
+#include "malidp_mw.h"
 
 enum {
 	MW_NOT_ENABLED = 0,	/* SE writeback not enabled */
@@ -996,7 +997,11 @@ static irqreturn_t malidp_se_irq(int irq, void *arg)
 
 	if (status & se->vsync_irq) {
 		switch (hwdev->mw_state) {
+		case MW_ONESHOT:
+			drm_writeback_signal_completion(&malidp->mw_connector, 0);
+			break;
 		case MW_STOP:
+			drm_writeback_signal_completion(&malidp->mw_connector, 0);
 			/* disable writeback after stop */
 			hwdev->mw_state = MW_NOT_ENABLED;
 			break;
diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
new file mode 100644
index 000000000000..cfd718e7e97c
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -0,0 +1,250 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Brian Starkey <brian.starkey@arm.com>
+ *
+ * ARM Mali DP Writeback connector implementation
+ */
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_gem_cma_helper.h>
+#include <drm/drmP.h>
+#include <drm/drm_writeback.h>
+
+#include "malidp_drv.h"
+#include "malidp_hw.h"
+#include "malidp_mw.h"
+
+#define to_mw_state(_state) (struct malidp_mw_connector_state *)(_state)
+
+struct malidp_mw_connector_state {
+	struct drm_connector_state base;
+	dma_addr_t addrs[2];
+	s32 pitches[2];
+	u8 format;
+	u8 n_planes;
+};
+
+static int malidp_mw_connector_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+
+	return drm_add_modes_noedid(connector, dev->mode_config.max_width,
+				    dev->mode_config.max_height);
+}
+
+static enum drm_mode_status
+malidp_mw_connector_mode_valid(struct drm_connector *connector,
+			       struct drm_display_mode *mode)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	int w = mode->hdisplay, h = mode->vdisplay;
+
+	if ((w < mode_config->min_width) || (w > mode_config->max_width))
+		return MODE_BAD_HVALUE;
+
+	if ((h < mode_config->min_height) || (h > mode_config->max_height))
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
+}
+
+const struct drm_connector_helper_funcs malidp_mw_connector_helper_funcs = {
+	.get_modes = malidp_mw_connector_get_modes,
+	.mode_valid = malidp_mw_connector_mode_valid,
+};
+
+static void malidp_mw_connector_reset(struct drm_connector *connector)
+{
+	struct malidp_mw_connector_state *mw_state =
+		kzalloc(sizeof(*mw_state), GFP_KERNEL);
+
+	if (connector->state)
+		__drm_atomic_helper_connector_destroy_state(connector->state);
+
+	kfree(connector->state);
+	__drm_atomic_helper_connector_reset(connector, &mw_state->base);
+}
+
+static enum drm_connector_status
+malidp_mw_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_disconnected;
+}
+
+static void malidp_mw_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_cleanup(connector);
+}
+
+static struct drm_connector_state *
+malidp_mw_connector_duplicate_state(struct drm_connector *connector)
+{
+	struct malidp_mw_connector_state *mw_state;
+
+	if (WARN_ON(!connector->state))
+		return NULL;
+
+	mw_state = kzalloc(sizeof(*mw_state), GFP_KERNEL);
+	if (!mw_state)
+		return NULL;
+
+	/* No need to preserve any of our driver-local data */
+	__drm_atomic_helper_connector_duplicate_state(connector, &mw_state->base);
+
+	return &mw_state->base;
+}
+
+static const struct drm_connector_funcs malidp_mw_connector_funcs = {
+	.reset = malidp_mw_connector_reset,
+	.detect = malidp_mw_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = malidp_mw_connector_destroy,
+	.atomic_duplicate_state = malidp_mw_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static int
+malidp_mw_encoder_atomic_check(struct drm_encoder *encoder,
+			       struct drm_crtc_state *crtc_state,
+			       struct drm_connector_state *conn_state)
+{
+	struct malidp_mw_connector_state *mw_state = to_mw_state(conn_state);
+	struct malidp_drm *malidp = encoder->dev->dev_private;
+	struct drm_framebuffer *fb;
+	int i, n_planes;
+
+	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+		return 0;
+
+	fb = conn_state->writeback_job->fb;
+	if ((fb->width != crtc_state->mode.hdisplay) ||
+	    (fb->height != crtc_state->mode.vdisplay)) {
+		DRM_DEBUG_KMS("Invalid framebuffer size %ux%u\n",
+				fb->width, fb->height);
+		return -EINVAL;
+	}
+
+	mw_state->format =
+		malidp_hw_get_format_id(&malidp->dev->hw->map, SE_MEMWRITE,
+					fb->format->format);
+	if (mw_state->format == MALIDP_INVALID_FORMAT_ID) {
+		struct drm_format_name_buf format_name;
+
+		DRM_DEBUG_KMS("Invalid pixel format %s\n",
+			      drm_get_format_name(fb->format->format,
+						  &format_name));
+		return -EINVAL;
+	}
+
+	n_planes = drm_format_num_planes(fb->format->format);
+	for (i = 0; i < n_planes; i++) {
+		struct drm_gem_cma_object *obj = drm_fb_cma_get_gem_obj(fb, i);
+		/* memory write buffers are never rotated */
+		u8 alignment = malidp_hw_get_pitch_align(malidp->dev, 0);
+
+		if (fb->pitches[i] & (alignment - 1)) {
+			DRM_DEBUG_KMS("Invalid pitch %u for plane %d\n",
+				      fb->pitches[i], i);
+			return -EINVAL;
+		}
+		mw_state->pitches[i] = fb->pitches[i];
+		mw_state->addrs[i] = obj->paddr + fb->offsets[i];
+	}
+	mw_state->n_planes = n_planes;
+
+	return 0;
+}
+
+static const struct drm_encoder_helper_funcs malidp_mw_encoder_helper_funcs = {
+	.atomic_check = malidp_mw_encoder_atomic_check,
+};
+
+static u32 *get_writeback_formats(struct malidp_drm *malidp, int *n_formats)
+{
+	const struct malidp_hw_regmap *map = &malidp->dev->hw->map;
+	u32 *formats;
+	int n, i;
+
+	formats = kcalloc(map->n_pixel_formats, sizeof(*formats),
+			  GFP_KERNEL);
+	if (!formats)
+		return NULL;
+
+	for (n = 0, i = 0;  i < map->n_pixel_formats; i++) {
+		if (map->pixel_formats[i].layer & SE_MEMWRITE)
+			formats[n++] = map->pixel_formats[i].format;
+	}
+
+	*n_formats = n;
+
+	return formats;
+}
+
+int malidp_mw_connector_init(struct drm_device *drm)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	u32 *formats;
+	int ret, n_formats;
+
+	if (!malidp->dev->hw->enable_memwrite)
+		return 0;
+
+	malidp->mw_connector.encoder.possible_crtcs = 1 << drm_crtc_index(&malidp->crtc);
+	drm_connector_helper_add(&malidp->mw_connector.base,
+				 &malidp_mw_connector_helper_funcs);
+
+	formats = get_writeback_formats(malidp, &n_formats);
+	if (!formats)
+		return -ENOMEM;
+
+	ret = drm_writeback_connector_init(drm, &malidp->mw_connector,
+					   &malidp_mw_connector_funcs,
+					   &malidp_mw_encoder_helper_funcs,
+					   formats, n_formats);
+	kfree(formats);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+void malidp_mw_atomic_commit(struct drm_device *drm,
+			     struct drm_atomic_state *old_state)
+{
+	struct malidp_drm *malidp = drm->dev_private;
+	struct drm_writeback_connector *mw_conn = &malidp->mw_connector;
+	struct drm_connector_state *conn_state = mw_conn->base.state;
+	struct malidp_hw_device *hwdev = malidp->dev;
+	struct malidp_mw_connector_state *mw_state;
+
+	if (!conn_state)
+		return;
+
+	mw_state = to_mw_state(conn_state);
+
+	if (conn_state->writeback_job && conn_state->writeback_job->fb) {
+		struct drm_framebuffer *fb = conn_state->writeback_job->fb;
+
+		DRM_DEV_DEBUG_DRIVER(drm->dev,
+				     "Enable memwrite %ux%u:%d %pad fmt: %u\n",
+				     fb->width, fb->height,
+				     mw_state->pitches[0],
+				     &mw_state->addrs[0],
+				     mw_state->format);
+
+		drm_writeback_queue_job(mw_conn, conn_state->writeback_job);
+		conn_state->writeback_job = NULL;
+
+		hwdev->hw->enable_memwrite(hwdev, mw_state->addrs,
+					   mw_state->pitches, mw_state->n_planes,
+					   fb->width, fb->height, mw_state->format);
+	} else {
+		DRM_DEV_DEBUG_DRIVER(drm->dev, "Disable memwrite\n");
+		hwdev->hw->disable_memwrite(hwdev);
+	}
+}
diff --git a/drivers/gpu/drm/arm/malidp_mw.h b/drivers/gpu/drm/arm/malidp_mw.h
new file mode 100644
index 000000000000..19a007676a1d
--- /dev/null
+++ b/drivers/gpu/drm/arm/malidp_mw.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * (C) COPYRIGHT 2016 ARM Limited. All rights reserved.
+ * Author: Brian Starkey <brian.starkey@arm.com>
+ *
+ */
+
+#ifndef __MALIDP_MW_H__
+#define __MALIDP_MW_H__
+
+int malidp_mw_connector_init(struct drm_device *drm);
+void malidp_mw_atomic_commit(struct drm_device *drm,
+			     struct drm_atomic_state *old_state);
+#endif
diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index 178842380f75..965be21b8280 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1436,6 +1436,10 @@ static void drm_atomic_connector_print_state(struct drm_printer *p,
 	drm_printf(p, "connector[%u]: %s\n", connector->base.id, connector->name);
 	drm_printf(p, "\tcrtc=%s\n", state->crtc ? state->crtc->name : "(null)");
 
+	if (connector->connector_type == DRM_MODE_CONNECTOR_WRITEBACK)
+		if (state->writeback_job && state->writeback_job->fb)
+			drm_printf(p, "\tfb=%d\n", state->writeback_job->fb->base.id);
+
 	if (connector->funcs->atomic_print_state)
 		connector->funcs->atomic_print_state(p, state);
 }
-- 
cgit v1.2.3


From 0735cfdf0af4d4ffc3743fb75b9ad929dfd37206 Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Fri, 15 Jun 2018 16:56:09 +0100
Subject: drm/mali-dp: Improve writeback handling for DP500.

Mali DP500 operates in continuous writeback mode (writes frame content
until stopped) and it needs special handling in order to behave like
a one-shot writeback engine. The original state machine added for DP500
was a bit fragile, as it did not handle correctly cases where a new
atomic commit was in progress when the SE IRQ happens and it would
commit some partial updates.

Improve the handling by adding a parameter to the set_config_valid()
function to clear the config valid bit in hardware before starting a
new commit and by introducing a MW_RESTART state in the writeback
state machine to cater for the case where a new writeback commit
gets submitted while the last one is still being active.

Reported-by: Brian Starkey <brian.starkey@arm.com>
Reviewed-by: Brian Starkey <brian.starkey@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c |  3 ++-
 drivers/gpu/drm/arm/malidp_hw.c  | 39 ++++++++++++++++++++++++++++-----------
 drivers/gpu/drm/arm/malidp_hw.h  | 11 ++++++-----
 3 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index e58a759fd3be..078b232c91ab 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -171,7 +171,7 @@ static int malidp_set_and_wait_config_valid(struct drm_device *drm)
 	struct malidp_hw_device *hwdev = malidp->dev;
 	int ret;
 
-	hwdev->hw->set_config_valid(hwdev);
+	hwdev->hw->set_config_valid(hwdev, 1);
 	/* don't wait for config_valid flag if we are in config mode */
 	if (hwdev->hw->in_config_mode(hwdev)) {
 		atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_DONE);
@@ -230,6 +230,7 @@ static void malidp_atomic_commit_tail(struct drm_atomic_state *state)
 	 * know that we are updating registers
 	 */
 	atomic_set(&malidp->config_valid, MALIDP_CONFIG_START);
+	malidp->dev->hw->set_config_valid(malidp->dev, 0);
 
 	drm_atomic_helper_commit_modeset_disables(drm, state);
 
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 449b7ef0a77f..b5c645cf4d1c 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -27,7 +27,8 @@ enum {
 	MW_NOT_ENABLED = 0,	/* SE writeback not enabled */
 	MW_ONESHOT,		/* SE in one-shot mode for writeback */
 	MW_START,		/* SE started writeback */
-	MW_STOP,		/* SE finished writeback */
+	MW_RESTART,		/* SE will start another writeback after this one */
+	MW_STOP,		/* SE needs to stop after this writeback */
 };
 
 static const struct malidp_format_id malidp500_de_formats[] = {
@@ -231,9 +232,12 @@ static bool malidp500_in_config_mode(struct malidp_hw_device *hwdev)
 	return false;
 }
 
-static void malidp500_set_config_valid(struct malidp_hw_device *hwdev)
+static void malidp500_set_config_valid(struct malidp_hw_device *hwdev, u8 value)
 {
-	malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
+	if (value)
+		malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
+	else
+		malidp_hw_clearbits(hwdev, MALIDP_CFG_VALID, MALIDP500_CONFIG_VALID);
 }
 
 static void malidp500_modeset(struct malidp_hw_device *hwdev, struct videomode *mode)
@@ -386,7 +390,11 @@ static int malidp500_enable_memwrite(struct malidp_hw_device *hwdev,
 	/* enable the scaling engine block */
 	malidp_hw_setbits(hwdev, MALIDP_SCALE_ENGINE_EN, de_base + MALIDP_DE_DISPLAY_FUNC);
 
-	hwdev->mw_state = MW_START;
+	/* restart the writeback if already enabled */
+	if (hwdev->mw_state != MW_NOT_ENABLED)
+		hwdev->mw_state = MW_RESTART;
+	else
+		hwdev->mw_state = MW_START;
 
 	malidp_hw_write(hwdev, fmt_id, base + MALIDP_MW_FORMAT);
 	switch (num_planes) {
@@ -415,7 +423,7 @@ static void malidp500_disable_memwrite(struct malidp_hw_device *hwdev)
 {
 	u32 base = malidp_get_block_base(hwdev, MALIDP_DE_BLOCK);
 
-	if (hwdev->mw_state == MW_START)
+	if (hwdev->mw_state == MW_START || hwdev->mw_state == MW_RESTART)
 		hwdev->mw_state = MW_STOP;
 	malidp_hw_clearbits(hwdev, MALIDP_SE_MEMWRITE_EN, MALIDP500_SE_CONTROL);
 	malidp_hw_clearbits(hwdev, MALIDP_SCALE_ENGINE_EN, base + MALIDP_DE_DISPLAY_FUNC);
@@ -500,9 +508,12 @@ static bool malidp550_in_config_mode(struct malidp_hw_device *hwdev)
 	return false;
 }
 
-static void malidp550_set_config_valid(struct malidp_hw_device *hwdev)
+static void malidp550_set_config_valid(struct malidp_hw_device *hwdev, u8 value)
 {
-	malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
+	if (value)
+		malidp_hw_setbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
+	else
+		malidp_hw_clearbits(hwdev, MALIDP_CFG_VALID, MALIDP550_CONFIG_VALID);
 }
 
 static void malidp550_modeset(struct malidp_hw_device *hwdev, struct videomode *mode)
@@ -1005,15 +1016,21 @@ static irqreturn_t malidp_se_irq(int irq, void *arg)
 			/* disable writeback after stop */
 			hwdev->mw_state = MW_NOT_ENABLED;
 			break;
+		case MW_RESTART:
+			drm_writeback_signal_completion(&malidp->mw_connector, 0);
+			/* fall through to a new start */
 		case MW_START:
 			/* writeback started, need to emulate one-shot mode */
 			hw->disable_memwrite(hwdev);
 			/*
-			 * only set config_valid HW bit if there is no
-			 * other update in progress
+			 * only set config_valid HW bit if there is no other update
+			 * in progress or if we raced ahead of the DE IRQ handler
+			 * and config_valid flag will not be update until later
 			 */
-			if (atomic_read(&malidp->config_valid) != MALIDP_CONFIG_START)
-				hw->set_config_valid(hwdev);
+			status = malidp_hw_read(hwdev, hw->map.dc_base + MALIDP_REG_STATUS);
+			if ((atomic_read(&malidp->config_valid) != MALIDP_CONFIG_START) ||
+			    (status & hw->map.dc_irq_map.vsync_irq))
+				hw->set_config_valid(hwdev, 1);
 			break;
 		}
 	}
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index c479738b81af..bd41aa6974a0 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -152,12 +152,13 @@ struct malidp_hw {
 	bool (*in_config_mode)(struct malidp_hw_device *hwdev);
 
 	/*
-	 * Set configuration valid flag for hardware parameters that can
-	 * be changed outside the configuration mode. Hardware will use
-	 * the new settings when config valid is set after the end of the
-	 * current buffer scanout
+	 * Set/clear configuration valid flag for hardware parameters that can
+	 * be changed outside the configuration mode to the given value.
+	 * Hardware will use the new settings when config valid is set,
+	 * after the end of the current buffer scanout, and will ignore
+	 * any new values for those parameters if config valid flag is cleared
 	 */
-	void (*set_config_valid)(struct malidp_hw_device *hwdev);
+	void (*set_config_valid)(struct malidp_hw_device *hwdev, u8 value);
 
 	/*
 	 * Set a new mode in hardware. Requires the hardware to be in
-- 
cgit v1.2.3


From 613c5c7fc8152866a798c52a5944e4b437b526f5 Mon Sep 17 00:00:00 2001
From: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Date: Tue, 15 May 2018 11:18:50 +0100
Subject: drm: mali-dp: Add debugfs file for reporting internal errors

Status register contains a lot of bits for reporting internal errors
inside Mali DP. Currently, we just silently ignore all of the errors,
that doesn't help when we are investigating different bugs, especially
on the FPGA models which have a lot of constraints, so we could easily
end up in AXI or underrun errors.

Add a new file called debug that contains an aggregate of the
errors reported by the Mali DP hardware.

E.g:
[root@alarm ~]# cat /sys/kernel/debug/dri/1/debug
[DE] num_errors : 167
[DE] last_error_status  : 0x00000001
[DE] last_error_vblank : 385
[SE] num_errors : 3
[SE] last_error_status  : 0x00e23001
[SE] last_error_vblank : 201

Changes since v2:
- Add lock to protect the errors stats.
- Add possibility to reset the error stats by writing anything to the
  debug file.

Signed-off-by: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c  | 104 ++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/arm/malidp_drv.h  |  19 +++++++
 drivers/gpu/drm/arm/malidp_hw.c   |  46 ++++++++++++++---
 drivers/gpu/drm/arm/malidp_hw.h   |   1 +
 drivers/gpu/drm/arm/malidp_regs.h |   6 +++
 5 files changed, 169 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 078b232c91ab..9b710f6999ed 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -17,6 +17,7 @@
 #include <linux/of_graph.h>
 #include <linux/of_reserved_mem.h>
 #include <linux/pm_runtime.h>
+#include <linux/debugfs.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
@@ -344,6 +345,106 @@ static int malidp_dumb_create(struct drm_file *file_priv,
 	return drm_gem_cma_dumb_create_internal(file_priv, drm, args);
 }
 
+#ifdef CONFIG_DEBUG_FS
+
+static void malidp_error_stats_init(struct malidp_error_stats *error_stats)
+{
+	error_stats->num_errors = 0;
+	error_stats->last_error_status = 0;
+	error_stats->last_error_vblank = -1;
+}
+
+void malidp_error(struct malidp_drm *malidp,
+		  struct malidp_error_stats *error_stats, u32 status,
+		  u64 vblank)
+{
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&malidp->errors_lock, irqflags);
+	error_stats->last_error_status = status;
+	error_stats->last_error_vblank = vblank;
+	error_stats->num_errors++;
+	spin_unlock_irqrestore(&malidp->errors_lock, irqflags);
+}
+
+void malidp_error_stats_dump(const char *prefix,
+			     struct malidp_error_stats error_stats,
+			     struct seq_file *m)
+{
+	seq_printf(m, "[%s] num_errors : %d\n", prefix,
+		   error_stats.num_errors);
+	seq_printf(m, "[%s] last_error_status  : 0x%08x\n", prefix,
+		   error_stats.last_error_status);
+	seq_printf(m, "[%s] last_error_vblank : %lld\n", prefix,
+		   error_stats.last_error_vblank);
+}
+
+static int malidp_show_stats(struct seq_file *m, void *arg)
+{
+	struct drm_device *drm = m->private;
+	struct malidp_drm *malidp = drm->dev_private;
+	unsigned long irqflags;
+	struct malidp_error_stats de_errors, se_errors;
+
+	spin_lock_irqsave(&malidp->errors_lock, irqflags);
+	de_errors = malidp->de_errors;
+	se_errors = malidp->se_errors;
+	spin_unlock_irqrestore(&malidp->errors_lock, irqflags);
+	malidp_error_stats_dump("DE", de_errors, m);
+	malidp_error_stats_dump("SE", se_errors, m);
+	return 0;
+}
+
+static int malidp_debugfs_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, malidp_show_stats, inode->i_private);
+}
+
+static ssize_t malidp_debugfs_write(struct file *file, const char __user *ubuf,
+				    size_t len, loff_t *offp)
+{
+	struct seq_file *m = file->private_data;
+	struct drm_device *drm = m->private;
+	struct malidp_drm *malidp = drm->dev_private;
+	unsigned long irqflags;
+
+	spin_lock_irqsave(&malidp->errors_lock, irqflags);
+	malidp_error_stats_init(&malidp->de_errors);
+	malidp_error_stats_init(&malidp->se_errors);
+	spin_unlock_irqrestore(&malidp->errors_lock, irqflags);
+	return len;
+}
+
+static const struct file_operations malidp_debugfs_fops = {
+	.owner = THIS_MODULE,
+	.open = malidp_debugfs_open,
+	.read = seq_read,
+	.write = malidp_debugfs_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int malidp_debugfs_init(struct drm_minor *minor)
+{
+	struct malidp_drm *malidp = minor->dev->dev_private;
+	struct dentry *dentry = NULL;
+
+	malidp_error_stats_init(&malidp->de_errors);
+	malidp_error_stats_init(&malidp->se_errors);
+	spin_lock_init(&malidp->errors_lock);
+	dentry = debugfs_create_file("debug",
+				     S_IRUGO | S_IWUSR,
+				     minor->debugfs_root, minor->dev,
+				     &malidp_debugfs_fops);
+	if (!dentry) {
+		DRM_ERROR("Cannot create debug file\n");
+		return -ENOMEM;
+	}
+	return 0;
+}
+
+#endif //CONFIG_DEBUG_FS
+
 static struct drm_driver malidp_driver = {
 	.driver_features = DRIVER_GEM | DRIVER_MODESET | DRIVER_ATOMIC |
 			   DRIVER_PRIME,
@@ -360,6 +461,9 @@ static struct drm_driver malidp_driver = {
 	.gem_prime_vmap = drm_gem_cma_prime_vmap,
 	.gem_prime_vunmap = drm_gem_cma_prime_vunmap,
 	.gem_prime_mmap = drm_gem_cma_prime_mmap,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init = malidp_debugfs_init,
+#endif
 	.fops = &fops,
 	.name = "mali-dp",
 	.desc = "ARM Mali Display Processor driver",
diff --git a/drivers/gpu/drm/arm/malidp_drv.h b/drivers/gpu/drm/arm/malidp_drv.h
index 5febd4b43e05..e3eb0cb1f385 100644
--- a/drivers/gpu/drm/arm/malidp_drv.h
+++ b/drivers/gpu/drm/arm/malidp_drv.h
@@ -17,6 +17,7 @@
 #include <drm/drm_encoder.h>
 #include <linux/mutex.h>
 #include <linux/wait.h>
+#include <linux/spinlock.h>
 #include <drm/drmP.h>
 #include "malidp_hw.h"
 
@@ -24,6 +25,12 @@
 #define MALIDP_CONFIG_VALID_DONE	1
 #define MALIDP_CONFIG_START		0xd0
 
+struct malidp_error_stats {
+	s32 num_errors;
+	u32 last_error_status;
+	s64 last_error_vblank;
+};
+
 struct malidp_drm {
 	struct malidp_hw_device *dev;
 	struct drm_crtc crtc;
@@ -32,6 +39,12 @@ struct malidp_drm {
 	struct drm_pending_vblank_event *event;
 	atomic_t config_valid;
 	u32 core_id;
+#ifdef CONFIG_DEBUG_FS
+	struct malidp_error_stats de_errors;
+	struct malidp_error_stats se_errors;
+	/* Protects errors stats */
+	spinlock_t errors_lock;
+#endif
 };
 
 #define crtc_to_malidp_device(x) container_of(x, struct malidp_drm, crtc)
@@ -69,6 +82,12 @@ struct malidp_crtc_state {
 int malidp_de_planes_init(struct drm_device *drm);
 int malidp_crtc_init(struct drm_device *drm);
 
+#ifdef CONFIG_DEBUG_FS
+void malidp_error(struct malidp_drm *malidp,
+		  struct malidp_error_stats *error_stats, u32 status,
+		  u64 vblank);
+#endif
+
 /* often used combination of rotational bits */
 #define MALIDP_ROTATED_MASK	(DRM_MODE_ROTATE_90 | DRM_MODE_ROTATE_270)
 
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index b5c645cf4d1c..3dfad2f97c2a 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -741,12 +741,18 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 					    MALIDP500_DE_IRQ_VSYNC |
 					    MALIDP500_DE_IRQ_GLOBAL,
 				.vsync_irq = MALIDP500_DE_IRQ_VSYNC,
+				.err_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP500_DE_IRQ_AXI_ERR |
+					    MALIDP500_DE_IRQ_SATURATION,
 			},
 			.se_irq_map = {
 				.irq_mask = MALIDP500_SE_IRQ_CONF_MODE |
 					    MALIDP500_SE_IRQ_CONF_VALID |
 					    MALIDP500_SE_IRQ_GLOBAL,
 				.vsync_irq = MALIDP500_SE_IRQ_CONF_VALID,
+				.err_mask = MALIDP500_SE_IRQ_INIT_BUSY |
+					    MALIDP500_SE_IRQ_AXI_ERROR |
+					    MALIDP500_SE_IRQ_OVERRUN,
 			},
 			.dc_irq_map = {
 				.irq_mask = MALIDP500_DE_IRQ_CONF_VALID,
@@ -782,11 +788,16 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 				.irq_mask = MALIDP_DE_IRQ_UNDERRUN |
 					    MALIDP550_DE_IRQ_VSYNC,
 				.vsync_irq = MALIDP550_DE_IRQ_VSYNC,
+				.err_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP550_DE_IRQ_SATURATION |
+					    MALIDP550_DE_IRQ_AXI_ERR,
 			},
 			.se_irq_map = {
-				.irq_mask = MALIDP550_SE_IRQ_EOW |
-					    MALIDP550_SE_IRQ_AXI_ERR,
+				.irq_mask = MALIDP550_SE_IRQ_EOW,
 				.vsync_irq = MALIDP550_SE_IRQ_EOW,
+				.err_mask  = MALIDP550_SE_IRQ_AXI_ERR |
+					     MALIDP550_SE_IRQ_OVR |
+					     MALIDP550_SE_IRQ_IBSY,
 			},
 			.dc_irq_map = {
 				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID |
@@ -824,11 +835,21 @@ const struct malidp_hw malidp_device[MALIDP_MAX_DEVICES] = {
 					    MALIDP650_DE_IRQ_DRIFT |
 					    MALIDP550_DE_IRQ_VSYNC,
 				.vsync_irq = MALIDP550_DE_IRQ_VSYNC,
+				.err_mask = MALIDP_DE_IRQ_UNDERRUN |
+					    MALIDP650_DE_IRQ_DRIFT |
+					    MALIDP550_DE_IRQ_SATURATION |
+					    MALIDP550_DE_IRQ_AXI_ERR |
+					    MALIDP650_DE_IRQ_ACEV1 |
+					    MALIDP650_DE_IRQ_ACEV2 |
+					    MALIDP650_DE_IRQ_ACEG |
+					    MALIDP650_DE_IRQ_AXIEP,
 			},
 			.se_irq_map = {
-				.irq_mask = MALIDP550_SE_IRQ_EOW |
-					    MALIDP550_SE_IRQ_AXI_ERR,
+				.irq_mask = MALIDP550_SE_IRQ_EOW,
 				.vsync_irq = MALIDP550_SE_IRQ_EOW,
+				.err_mask = MALIDP550_SE_IRQ_AXI_ERR |
+					    MALIDP550_SE_IRQ_OVR |
+					    MALIDP550_SE_IRQ_IBSY,
 			},
 			.dc_irq_map = {
 				.irq_mask = MALIDP550_DC_IRQ_CONF_VALID |
@@ -920,10 +941,17 @@ static irqreturn_t malidp_de_irq(int irq, void *arg)
 		return ret;
 
 	mask = malidp_hw_read(hwdev, MALIDP_REG_MASKIRQ);
-	status &= mask;
+	/* keep the status of the enabled interrupts, plus the error bits */
+	status &= (mask | de->err_mask);
 	if ((status & de->vsync_irq) && malidp->crtc.enabled)
 		drm_crtc_handle_vblank(&malidp->crtc);
 
+#ifdef CONFIG_DEBUG_FS
+	if (status & de->err_mask) {
+		malidp_error(malidp, &malidp->de_errors, status,
+			     drm_crtc_vblank_count(&malidp->crtc));
+	}
+#endif
 	malidp_hw_clear_irq(hwdev, MALIDP_DE_BLOCK, status);
 
 	return (ret == IRQ_NONE) ? IRQ_HANDLED : ret;
@@ -999,11 +1027,15 @@ static irqreturn_t malidp_se_irq(int irq, void *arg)
 		return IRQ_NONE;
 
 	status = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_STATUS);
-	if (!(status & se->irq_mask))
+	if (!(status & (se->irq_mask | se->err_mask)))
 		return IRQ_NONE;
 
+#ifdef CONFIG_DEBUG_FS
+	if (status & se->err_mask)
+		malidp_error(malidp, &malidp->se_errors, status,
+			     drm_crtc_vblank_count(&malidp->crtc));
+#endif
 	mask = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_MASKIRQ);
-	status = malidp_hw_read(hwdev, hw->map.se_base + MALIDP_REG_STATUS);
 	status &= mask;
 
 	if (status & se->vsync_irq) {
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index bd41aa6974a0..5b99445433a2 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -53,6 +53,7 @@ struct malidp_format_id {
 struct malidp_irq_map {
 	u32 irq_mask;		/* mask of IRQs that can be enabled in the block */
 	u32 vsync_irq;		/* IRQ bit used for signaling during VSYNC */
+	u32 err_mask;		/* mask of bits that represent errors */
 };
 
 struct malidp_layer {
diff --git a/drivers/gpu/drm/arm/malidp_regs.h b/drivers/gpu/drm/arm/malidp_regs.h
index 93b198f3af86..3579d36b2a71 100644
--- a/drivers/gpu/drm/arm/malidp_regs.h
+++ b/drivers/gpu/drm/arm/malidp_regs.h
@@ -53,6 +53,8 @@
 #define MALIDP550_DE_IRQ_AXI_ERR		(1 << 16)
 #define MALIDP550_SE_IRQ_EOW			(1 << 0)
 #define MALIDP550_SE_IRQ_AXI_ERR		(1 << 16)
+#define MALIDP550_SE_IRQ_OVR			(1 << 17)
+#define MALIDP550_SE_IRQ_IBSY			(1 << 18)
 #define MALIDP550_DC_IRQ_CONF_VALID		(1 << 0)
 #define MALIDP550_DC_IRQ_CONF_MODE		(1 << 4)
 #define MALIDP550_DC_IRQ_CONF_ACTIVE		(1 << 16)
@@ -60,6 +62,10 @@
 #define MALIDP550_DC_IRQ_SE			(1 << 24)
 
 #define MALIDP650_DE_IRQ_DRIFT			(1 << 4)
+#define MALIDP650_DE_IRQ_ACEV1			(1 << 17)
+#define MALIDP650_DE_IRQ_ACEV2			(1 << 18)
+#define MALIDP650_DE_IRQ_ACEG			(1 << 19)
+#define MALIDP650_DE_IRQ_AXIEP			(1 << 28)
 
 /* bit masks that are common between products */
 #define   MALIDP_CFG_VALID		(1 << 0)
-- 
cgit v1.2.3


From 62862cfbb18d10c5f8409f4c8e49c4bbaaf18d3a Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 15 May 2018 17:04:15 +0100
Subject: drm/arm/malidp: Modified the prototype of malidp irq de-initializers

Malidp uses two interrupts ie 1. se_irq - used for memory writeback.
 and 2. de_irq - used for display output.
'struct drm_device' is being replaced with 'struct malidp_hw_device'
as the function argument. The reason being the dependency of
malidp_de_irq_fini on 'struct drm_device' needs to be removed so as to
enable it to call from functions which receives 'struct malidp_hw_device'
as argument. Furthermore, there is no way to retrieve 'struct drm_device'
from 'struct malidp_hw_device'.

Signed-off-by: Ayan Kumar Halder <ayan.halder@arm.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c | 13 ++++++++-----
 drivers/gpu/drm/arm/malidp_hw.c  | 10 ++--------
 drivers/gpu/drm/arm/malidp_hw.h  |  4 ++--
 3 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 9b710f6999ed..16fa089fa8be 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -304,6 +304,8 @@ static int malidp_irq_init(struct platform_device *pdev)
 {
 	int irq_de, irq_se, ret = 0;
 	struct drm_device *drm = dev_get_drvdata(&pdev->dev);
+	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
 
 	/* fetch the interrupts from DT */
 	irq_de = platform_get_irq_byname(pdev, "DE");
@@ -323,7 +325,7 @@ static int malidp_irq_init(struct platform_device *pdev)
 
 	ret = malidp_se_irq_init(drm, irq_se);
 	if (ret) {
-		malidp_de_irq_fini(drm);
+		malidp_de_irq_fini(hwdev);
 		return ret;
 	}
 
@@ -763,8 +765,8 @@ register_fail:
 fbdev_fail:
 	pm_runtime_get_sync(dev);
 vblank_fail:
-	malidp_se_irq_fini(drm);
-	malidp_de_irq_fini(drm);
+	malidp_se_irq_fini(hwdev);
+	malidp_de_irq_fini(hwdev);
 	drm->irq_enabled = false;
 irq_init_fail:
 	drm_atomic_helper_shutdown(drm);
@@ -794,14 +796,15 @@ static void malidp_unbind(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
 	struct malidp_drm *malidp = drm->dev_private;
+	struct malidp_hw_device *hwdev = malidp->dev;
 
 	drm_dev_unregister(drm);
 	drm_fb_cma_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 	pm_runtime_get_sync(dev);
 	drm_crtc_vblank_off(&malidp->crtc);
-	malidp_se_irq_fini(drm);
-	malidp_de_irq_fini(drm);
+	malidp_se_irq_fini(hwdev);
+	malidp_de_irq_fini(hwdev);
 	drm->irq_enabled = false;
 	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 3dfad2f97c2a..e30a25ceea2c 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -998,11 +998,8 @@ int malidp_de_irq_init(struct drm_device *drm, int irq)
 	return 0;
 }
 
-void malidp_de_irq_fini(struct drm_device *drm)
+void malidp_de_irq_fini(struct malidp_hw_device *hwdev)
 {
-	struct malidp_drm *malidp = drm->dev_private;
-	struct malidp_hw_device *hwdev = malidp->dev;
-
 	malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK,
 			      hwdev->hw->map.de_irq_map.irq_mask);
 	malidp_hw_disable_irq(hwdev, MALIDP_DC_BLOCK,
@@ -1102,11 +1099,8 @@ int malidp_se_irq_init(struct drm_device *drm, int irq)
 	return 0;
 }
 
-void malidp_se_irq_fini(struct drm_device *drm)
+void malidp_se_irq_fini(struct malidp_hw_device *hwdev)
 {
-	struct malidp_drm *malidp = drm->dev_private;
-	struct malidp_hw_device *hwdev = malidp->dev;
-
 	malidp_hw_disable_irq(hwdev, MALIDP_SE_BLOCK,
 			      hwdev->hw->map.se_irq_map.irq_mask);
 }
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index 5b99445433a2..8304d7763b8d 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -302,9 +302,9 @@ static inline void malidp_hw_enable_irq(struct malidp_hw_device *hwdev,
 }
 
 int malidp_de_irq_init(struct drm_device *drm, int irq);
-void malidp_de_irq_fini(struct drm_device *drm);
+void malidp_de_irq_fini(struct malidp_hw_device *hwdev);
 int malidp_se_irq_init(struct drm_device *drm, int irq);
-void malidp_se_irq_fini(struct drm_device *drm);
+void malidp_se_irq_fini(struct malidp_hw_device *hwdev);
 
 u8 malidp_hw_get_format_id(const struct malidp_hw_regmap *map,
 			   u8 layer_id, u32 format);
-- 
cgit v1.2.3


From ff8fc26a764acdf5e0a2f86430bcb96c7b4eebec Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 15 May 2018 17:04:16 +0100
Subject: drm/arm/malidp: Split malidp interrupt initialization functions.

Malidp uses two interrupts ie 1. se_irq - used for memory writeback.
 and 2. de_irq - used for display output.
Extract the hardware initialization part from malidp interrupt registration
ie (malidp_de_irq_init()/ malidp_se_irq_init()) into a separate function
(ie malidp_de_irq_hw_init()/malidp_se_irq_hw_init())
which will be later invoked from runtime_pm_resume function when it needs
to re-enable the interrupts.

Signed-off-by: Ayan Kumar Halder <ayan.halder@arm.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_hw.c | 38 +++++++++++++++++++++++++++++---------
 drivers/gpu/drm/arm/malidp_hw.h |  2 ++
 2 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index e30a25ceea2c..47fc112ee32e 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -967,6 +967,23 @@ static irqreturn_t malidp_de_irq_thread_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
+void malidp_de_irq_hw_init(struct malidp_hw_device *hwdev)
+{
+	/* ensure interrupts are disabled */
+	malidp_hw_disable_irq(hwdev, MALIDP_DE_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_DE_BLOCK, 0xffffffff);
+	malidp_hw_disable_irq(hwdev, MALIDP_DC_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_DC_BLOCK, 0xffffffff);
+
+	/* first enable the DC block IRQs */
+	malidp_hw_enable_irq(hwdev, MALIDP_DC_BLOCK,
+			     hwdev->hw->map.dc_irq_map.irq_mask);
+
+	/* now enable the DE block IRQs */
+	malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
+			     hwdev->hw->map.de_irq_map.irq_mask);
+}
+
 int malidp_de_irq_init(struct drm_device *drm, int irq)
 {
 	struct malidp_drm *malidp = drm->dev_private;
@@ -987,13 +1004,7 @@ int malidp_de_irq_init(struct drm_device *drm, int irq)
 		return ret;
 	}
 
-	/* first enable the DC block IRQs */
-	malidp_hw_enable_irq(hwdev, MALIDP_DC_BLOCK,
-			     hwdev->hw->map.dc_irq_map.irq_mask);
-
-	/* now enable the DE block IRQs */
-	malidp_hw_enable_irq(hwdev, MALIDP_DE_BLOCK,
-			     hwdev->hw->map.de_irq_map.irq_mask);
+	malidp_de_irq_hw_init(hwdev);
 
 	return 0;
 }
@@ -1069,6 +1080,16 @@ static irqreturn_t malidp_se_irq(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
+void malidp_se_irq_hw_init(struct malidp_hw_device *hwdev)
+{
+	/* ensure interrupts are disabled */
+	malidp_hw_disable_irq(hwdev, MALIDP_SE_BLOCK, 0xffffffff);
+	malidp_hw_clear_irq(hwdev, MALIDP_SE_BLOCK, 0xffffffff);
+
+	malidp_hw_enable_irq(hwdev, MALIDP_SE_BLOCK,
+			     hwdev->hw->map.se_irq_map.irq_mask);
+}
+
 static irqreturn_t malidp_se_irq_thread_handler(int irq, void *arg)
 {
 	return IRQ_HANDLED;
@@ -1093,8 +1114,7 @@ int malidp_se_irq_init(struct drm_device *drm, int irq)
 	}
 
 	hwdev->mw_state = MW_NOT_ENABLED;
-	malidp_hw_enable_irq(hwdev, MALIDP_SE_BLOCK,
-			     hwdev->hw->map.se_irq_map.irq_mask);
+	malidp_se_irq_hw_init(hwdev);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index 8304d7763b8d..f5b3eab8398b 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -302,6 +302,8 @@ static inline void malidp_hw_enable_irq(struct malidp_hw_device *hwdev,
 }
 
 int malidp_de_irq_init(struct drm_device *drm, int irq);
+void malidp_se_irq_hw_init(struct malidp_hw_device *hwdev);
+void malidp_de_irq_hw_init(struct malidp_hw_device *hwdev);
 void malidp_de_irq_fini(struct malidp_hw_device *hwdev);
 int malidp_se_irq_init(struct drm_device *drm, int irq);
 void malidp_se_irq_fini(struct malidp_hw_device *hwdev);
-- 
cgit v1.2.3


From fbcc454e8a350b929cb04fbcfdfa72fab37acf38 Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 15 May 2018 17:04:17 +0100
Subject: drm/arm/malidp: Enable/disable interrupts in runtime pm

Display and scaling engine interrupts need to be disabled when the
runtime pm invokes malidp_runtime_pm_suspend(). Conversely, they
need to be enabled in malidp_runtime_pm_resume().

This patch depends on:
https://lkml.org/lkml/2017/5/15/695

Reported-by: Alexandru-Cosmin Gheorghe <Alexandru-Cosmin.Gheorghe@arm.com>
Signed-off-by: Alexandru-Cosmin Gheorghe <Alexandru-Cosmin.Gheorghe@arm.com>
Signed-off-by: Ayan Kumar Halder <ayan.halder@arm.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 16fa089fa8be..125be226bf6c 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -582,6 +582,8 @@ static int malidp_runtime_pm_suspend(struct device *dev)
 	/* we can only suspend if the hardware is in config mode */
 	WARN_ON(!hwdev->hw->in_config_mode(hwdev));
 
+	malidp_se_irq_fini(hwdev);
+	malidp_de_irq_fini(hwdev);
 	hwdev->pm_suspended = true;
 	clk_disable_unprepare(hwdev->mclk);
 	clk_disable_unprepare(hwdev->aclk);
@@ -600,6 +602,8 @@ static int malidp_runtime_pm_resume(struct device *dev)
 	clk_prepare_enable(hwdev->aclk);
 	clk_prepare_enable(hwdev->mclk);
 	hwdev->pm_suspended = false;
+	malidp_de_irq_hw_init(hwdev);
+	malidp_se_irq_hw_init(hwdev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From f877006d5db49f3615fcee4bd5eb1a56c053d419 Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 15 May 2018 17:04:18 +0100
Subject: drm/arm/malidp: Set the output_depth register in modeset

One needs to store the value of the OUTPUT_DEPTH that one has parsed from
device tree, so that it can be restored on system resume. This value is
set in the modeset function as this gets reset when the system suspends.

Signed-off-by: Ayan Kumar Halder <ayan.halder@arm.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c | 1 +
 drivers/gpu/drm/arm/malidp_hw.c  | 4 ++++
 drivers/gpu/drm/arm/malidp_hw.h  | 1 +
 3 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 125be226bf6c..7237b98be5eb 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -715,6 +715,7 @@ static int malidp_bind(struct device *dev)
 	for (i = 0; i < MAX_OUTPUT_CHANNELS; i++)
 		out_depth = (out_depth << 8) | (output_width[i] & 0xf);
 	malidp_hw_write(hwdev, out_depth, hwdev->hw->map.out_depth_base);
+	hwdev->output_color_depth = out_depth;
 
 	atomic_set(&malidp->config_valid, MALIDP_CONFIG_VALID_INIT);
 	init_waitqueue_head(&malidp->wq);
diff --git a/drivers/gpu/drm/arm/malidp_hw.c b/drivers/gpu/drm/arm/malidp_hw.c
index 47fc112ee32e..c94a4422e0e9 100644
--- a/drivers/gpu/drm/arm/malidp_hw.c
+++ b/drivers/gpu/drm/arm/malidp_hw.c
@@ -244,6 +244,8 @@ static void malidp500_modeset(struct malidp_hw_device *hwdev, struct videomode *
 {
 	u32 val = 0;
 
+	malidp_hw_write(hwdev, hwdev->output_color_depth,
+		hwdev->hw->map.out_depth_base);
 	malidp_hw_clearbits(hwdev, MALIDP500_DC_CLEAR_MASK, MALIDP500_DC_CONTROL);
 	if (mode->flags & DISPLAY_FLAGS_HSYNC_HIGH)
 		val |= MALIDP500_HSYNCPOL;
@@ -520,6 +522,8 @@ static void malidp550_modeset(struct malidp_hw_device *hwdev, struct videomode *
 {
 	u32 val = MALIDP_DE_DEFAULT_PREFETCH_START;
 
+	malidp_hw_write(hwdev, hwdev->output_color_depth,
+		hwdev->hw->map.out_depth_base);
 	malidp_hw_write(hwdev, val, MALIDP550_DE_CONTROL);
 	/*
 	 * Mali-DP550 and Mali-DP650 encode the background color like this:
diff --git a/drivers/gpu/drm/arm/malidp_hw.h b/drivers/gpu/drm/arm/malidp_hw.h
index f5b3eab8398b..ad2e96915d44 100644
--- a/drivers/gpu/drm/arm/malidp_hw.h
+++ b/drivers/gpu/drm/arm/malidp_hw.h
@@ -230,6 +230,7 @@ struct malidp_hw_device {
 
 	u8 min_line_size;
 	u16 max_line_size;
+	u32 output_color_depth;
 
 	/* track the device PM state */
 	bool pm_suspended;
-- 
cgit v1.2.3


From e368fc75c190a4ad5853e4ec5a0c8acf86bd5119 Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 15 May 2018 17:04:19 +0100
Subject: drm/arm/malidp: Added the late system pm functions

malidp_pm_suspend_late checks if the runtime status is not suspended
and if so, invokes malidp_runtime_pm_suspend which disables the
display engine/core interrupts and the clocks. It sets the runtime status
as suspended.

The difference between suspend() and suspend_late() is as follows:-
1. suspend() makes the device quiescent. In our case, we invoke the DRM
helper which disables the CRTC. This would have invoked runtime pm
suspend but the system suspend process disables runtime pm.
2. suspend_late() It continues the suspend operations of the drm device
which was started by suspend(). In our case, it performs the same functionality
as runtime_suspend().

The complimentary functions are resume() and resume_early(). In the case of
resume_early(), we invoke malidp_runtime_pm_resume() which enables the clocks
and the interrupts. It sets the runtime status as active. If the device was
in runtime suspend mode before system suspend was called, pm_runtime_work()
will put the device back in runtime suspended mode( after the complete system
has been resumed).

Signed-off-by: Ayan Kumar Halder <ayan.halder@arm.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 7237b98be5eb..5b7260557391 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -882,8 +882,25 @@ static int __maybe_unused malidp_pm_resume(struct device *dev)
 	return 0;
 }
 
+static int __maybe_unused malidp_pm_suspend_late(struct device *dev)
+{
+	if (!pm_runtime_status_suspended(dev)) {
+		malidp_runtime_pm_suspend(dev);
+		pm_runtime_set_suspended(dev);
+	}
+	return 0;
+}
+
+static int __maybe_unused malidp_pm_resume_early(struct device *dev)
+{
+	malidp_runtime_pm_resume(dev);
+	pm_runtime_set_active(dev);
+	return 0;
+}
+
 static const struct dev_pm_ops malidp_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(malidp_pm_suspend, malidp_pm_resume) \
+	SET_LATE_SYSTEM_SLEEP_PM_OPS(malidp_pm_suspend_late, malidp_pm_resume_early) \
 	SET_RUNTIME_PM_OPS(malidp_runtime_pm_suspend, malidp_runtime_pm_resume, NULL)
 };
 
-- 
cgit v1.2.3


From f7ddff54d0a0f068442414b48bec7f22aa777de7 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 5 Jul 2018 08:06:17 -0500
Subject: ASoC: nau8824: use 64-bit arithmetic instead of 32-bit

Add suffix ULL to constant 256 in order to give the compiler complete
information about the proper arithmetic to use.

Notice that such constant is used in a context that expects an
expression of type u64 (64 bits, unsigned) and the following
expression is currently being evaluated using 32-bit arithmetic:

256 * fs * 2 * mclk_src_scaling[i].param

Addresses-Coverity-ID: 1432039 ("Unintentional integer overflow")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/nau8824.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/nau8824.c b/sound/soc/codecs/nau8824.c
index 6bd14453f06e..468d5143e2c4 100644
--- a/sound/soc/codecs/nau8824.c
+++ b/sound/soc/codecs/nau8824.c
@@ -1274,7 +1274,7 @@ static int nau8824_calc_fll_param(unsigned int fll_in,
 	fvco_max = 0;
 	fvco_sel = ARRAY_SIZE(mclk_src_scaling);
 	for (i = 0; i < ARRAY_SIZE(mclk_src_scaling); i++) {
-		fvco = 256 * fs * 2 * mclk_src_scaling[i].param;
+		fvco = 256ULL * fs * 2 * mclk_src_scaling[i].param;
 		if (fvco > NAU_FVCO_MIN && fvco < NAU_FVCO_MAX &&
 			fvco_max < fvco) {
 			fvco_max = fvco;
-- 
cgit v1.2.3


From b7eba890a228f591fea2889b901267ba5de7839b Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Thu, 21 Jun 2018 07:42:37 -0500
Subject: gfs2: Eliminate redundant ip->i_rgd

GFS2 remembers the last rgrp used for allocations in ip->i_rgd.
However, block allocations are made by way of a reservations structure,
ip->i_res, which keeps the last rgrp in ip->i_res.rs_rgd, and ip->i_res
is kept in sync with ip->i_res.rs_rgd, so it's redundant.  Get rid of
ip->i_rgd and just use ip->i_res.rs_rgd in its place.

Based on patches by Robert Peterson.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Signed-off-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/incore.h |  1 -
 fs/gfs2/rgrp.c   | 13 ++++++-------
 fs/gfs2/super.c  |  1 -
 fs/gfs2/trans.h  |  6 ++++--
 4 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index e9cd2cc292d3..b50908211b69 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -397,7 +397,6 @@ struct gfs2_inode {
 	struct gfs2_holder i_gh; /* for prepare/commit_write only */
 	struct gfs2_qadata *i_qadata; /* quota allocation data */
 	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */
-	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
 	struct list_head i_ordered;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ecdc4cb5b6ad..60c86532782e 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1992,8 +1992,9 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 		return -EINVAL;
 	if (gfs2_rs_active(rs)) {
 		begin = rs->rs_rbm.rgd;
-	} else if (ip->i_rgd && rgrp_contains_block(ip->i_rgd, ip->i_goal)) {
-		rs->rs_rbm.rgd = begin = ip->i_rgd;
+	} else if (rs->rs_rbm.rgd &&
+		   rgrp_contains_block(rs->rs_rbm.rgd, ip->i_goal)) {
+		begin = rs->rs_rbm.rgd;
 	} else {
 		check_and_update_goal(ip);
 		rs->rs_rbm.rgd = begin = gfs2_blk2rgrpd(sdp, ip->i_goal, 1);
@@ -2057,8 +2058,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 		if (rs->rs_rbm.rgd->rd_free_clone >= ap->target ||
 		    (loops == 2 && ap->min_target &&
 		     rs->rs_rbm.rgd->rd_free_clone >= ap->min_target)) {
-			ip->i_rgd = rs->rs_rbm.rgd;
-			ap->allowed = ip->i_rgd->rd_free_clone;
+			ap->allowed = rs->rs_rbm.rgd->rd_free_clone;
 			return 0;
 		}
 check_rgrp:
@@ -2336,7 +2336,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct buffer_head *dibh;
-	struct gfs2_rbm rbm = { .rgd = ip->i_rgd, };
+	struct gfs2_rbm rbm = { .rgd = ip->i_res.rs_rbm.rgd, };
 	unsigned int ndata;
 	u64 block; /* block, within the file system scope */
 	int error;
@@ -2569,7 +2569,7 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
 			return;
 		rgd = gfs2_blk2rgrpd(sdp, block, 1);
 	} else {
-		rgd = ip->i_rgd;
+		rgd = ip->i_res.rs_rbm.rgd;
 		if (!rgd || !rgrp_contains_block(rgd, block))
 			rgd = gfs2_blk2rgrpd(sdp, block, 1);
 	}
@@ -2579,7 +2579,6 @@ void gfs2_rlist_add(struct gfs2_inode *ip, struct gfs2_rgrp_list *rlist,
 		       (unsigned long long)block);
 		return;
 	}
-	ip->i_rgd = rgd;
 
 	for (x = 0; x < rlist->rl_rgrps; x++) {
 		if (rlist->rl_rgd[x] == rgd) {
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index cf5c7f3080d2..685dc6fff5ed 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -1729,7 +1729,6 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 	if (ip) {
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
-		ip->i_rgd = NULL;
 		memset(&ip->i_res, 0, sizeof(ip->i_res));
 		RB_CLEAR_NODE(&ip->i_res.rs_node);
 		ip->i_rahead = 0;
diff --git a/fs/gfs2/trans.h b/fs/gfs2/trans.h
index 1e6e7da25a17..ad70087d0597 100644
--- a/fs/gfs2/trans.h
+++ b/fs/gfs2/trans.h
@@ -30,9 +30,11 @@ struct gfs2_glock;
  * block, or all of the blocks in the rg, whichever is smaller */
 static inline unsigned int gfs2_rg_blocks(const struct gfs2_inode *ip, unsigned requested)
 {
-	if (requested < ip->i_rgd->rd_length)
+	struct gfs2_rgrpd *rgd = ip->i_res.rs_rbm.rgd;
+
+	if (requested < rgd->rd_length)
 		return requested + 1;
-	return ip->i_rgd->rd_length;
+	return rgd->rd_length;
 }
 
 extern int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
-- 
cgit v1.2.3


From 25086263425641c74123f9387426c23072b299ea Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 5 Jul 2018 15:16:48 +0100
Subject: arm64: add PSR_AA32_* definitions

The AArch32 CPSR/SPSR format is *almost* identical to the AArch64
SPSR_ELx format for exceptions taken from AArch32, but the two have
diverged with the addition of DIT, and we need to treat the two as
logically distinct.

This patch adds new definitions for the SPSR_ELx format for exceptions
taken from AArch32, with a consistent PSR_AA32_ prefix. The existing
COMPAT_PSR_ definitions will be used for the PSR format as seen from
AArch32.

Definitions of DIT are provided for both, and inline functions are
provided to map between the two formats. Note that for SPSR_ELx, the
(RES0) J bit has been re-allocated as the DIT bit.

Once users of the COMPAT_PSR definitions have been migrated over to the
PSR_AA32 definitions, the (majority of) the former will be removed, so
no efforts is made to avoid duplication until then.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christoffer Dall <christoffer.dall@arm.com>
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Suzuki Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/ptrace.h | 57 ++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 56 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 6069d66e0bc2..1b2a253de6a1 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -35,7 +35,37 @@
 #define COMPAT_PTRACE_GETHBPREGS	29
 #define COMPAT_PTRACE_SETHBPREGS	30
 
-/* AArch32 CPSR bits */
+/* SPSR_ELx bits for exceptions taken from AArch32 */
+#define PSR_AA32_MODE_MASK	0x0000001f
+#define PSR_AA32_MODE_USR	0x00000010
+#define PSR_AA32_MODE_FIQ	0x00000011
+#define PSR_AA32_MODE_IRQ	0x00000012
+#define PSR_AA32_MODE_SVC	0x00000013
+#define PSR_AA32_MODE_ABT	0x00000017
+#define PSR_AA32_MODE_HYP	0x0000001a
+#define PSR_AA32_MODE_UND	0x0000001b
+#define PSR_AA32_MODE_SYS	0x0000001f
+#define PSR_AA32_T_BIT		0x00000020
+#define PSR_AA32_F_BIT		0x00000040
+#define PSR_AA32_I_BIT		0x00000080
+#define PSR_AA32_A_BIT		0x00000100
+#define PSR_AA32_E_BIT		0x00000200
+#define PSR_AA32_DIT_BIT	0x01000000
+#define PSR_AA32_Q_BIT		0x08000000
+#define PSR_AA32_V_BIT		0x10000000
+#define PSR_AA32_C_BIT		0x20000000
+#define PSR_AA32_Z_BIT		0x40000000
+#define PSR_AA32_N_BIT		0x80000000
+#define PSR_AA32_IT_MASK	0x0600fc00	/* If-Then execution state mask */
+#define PSR_AA32_GE_MASK	0x000f0000
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define PSR_AA32_ENDSTATE	PSR_AA32_E_BIT
+#else
+#define PSR_AA32_ENDSTATE	0
+#endif
+
+/* AArch32 CPSR bits, as seen in AArch32 */
 #define COMPAT_PSR_MODE_MASK	0x0000001f
 #define COMPAT_PSR_MODE_USR	0x00000010
 #define COMPAT_PSR_MODE_FIQ	0x00000011
@@ -50,6 +80,7 @@
 #define COMPAT_PSR_I_BIT	0x00000080
 #define COMPAT_PSR_A_BIT	0x00000100
 #define COMPAT_PSR_E_BIT	0x00000200
+#define COMPAT_PSR_DIT_BIT	0x00200000
 #define COMPAT_PSR_J_BIT	0x01000000
 #define COMPAT_PSR_Q_BIT	0x08000000
 #define COMPAT_PSR_V_BIT	0x10000000
@@ -111,6 +142,30 @@
 #define compat_sp_fiq	regs[29]
 #define compat_lr_fiq	regs[30]
 
+static inline unsigned long compat_psr_to_pstate(const unsigned long psr)
+{
+	unsigned long pstate;
+
+	pstate = psr & ~COMPAT_PSR_DIT_BIT;
+
+	if (psr & COMPAT_PSR_DIT_BIT)
+		pstate |= PSR_AA32_DIT_BIT;
+
+	return pstate;
+}
+
+static inline unsigned long pstate_to_compat_psr(const unsigned long pstate)
+{
+	unsigned long psr;
+
+	psr = pstate & ~PSR_AA32_DIT_BIT;
+
+	if (pstate & PSR_AA32_DIT_BIT)
+		psr |= COMPAT_PSR_DIT_BIT;
+
+	return psr;
+}
+
 /*
  * This struct defines the way the registers are stored on the stack during an
  * exception. Note that sizeof(struct pt_regs) has to be a multiple of 16 (for
-- 
cgit v1.2.3


From 1265132127b63502d34e0f58c8bdef3a4dc927c2 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 5 Jul 2018 15:16:49 +0100
Subject: arm64: don't zero DIT on signal return

Currently valid_user_regs() treats SPSR_ELx.DIT as a RES0 bit, causing
it to be zeroed upon exception return, rather than preserved. Thus, code
relying on DIT will not function as expected, and may expose an
unexpected timing sidechannel.

Let's remove DIT from the set of RES0 bits, such that it is preserved.
At the same time, the related comment is updated to better describe the
situation, and to take into account the most recent documentation of
SPSR_ELx, in ARM DDI 0487C.a.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 7206dc93a58fb764 ("arm64: Expose Arm v8.4 features")
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Suzuki K Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/ptrace.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 5c338ce5a7fa..5df75ab6a3c8 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1659,15 +1659,19 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs)
 }
 
 /*
- * Bits which are always architecturally RES0 per ARM DDI 0487A.h
+ * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487C.a
+ * We also take into account DIT (bit 24), which is not yet documented, and
+ * treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may be
+ * allocated an EL0 meaning in future.
  * Userspace cannot use these until they have an architectural meaning.
+ * Note that this follows the SPSR_ELx format, not the AArch32 PSR format.
  * We also reserve IL for the kernel; SS is handled dynamically.
  */
 #define SPSR_EL1_AARCH64_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 22) | GENMASK_ULL(20, 10) | \
-	 GENMASK_ULL(5, 5))
+	(GENMASK_ULL(63,32) | GENMASK_ULL(27, 25) | GENMASK_ULL(23, 22) | \
+	 GENMASK_ULL(20, 10) | GENMASK_ULL(5, 5))
 #define SPSR_EL1_AARCH32_RES0_BITS \
-	(GENMASK_ULL(63,32) | GENMASK_ULL(24, 22) | GENMASK_ULL(20,20))
+	(GENMASK_ULL(63,32) | GENMASK_ULL(23, 22) | GENMASK_ULL(20,20))
 
 static int valid_compat_regs(struct user_pt_regs *regs)
 {
-- 
cgit v1.2.3


From 25dc2c80cfa33153057aa94984855acd57adf92a Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 5 Jul 2018 15:16:50 +0100
Subject: arm64: compat: map SPSR_ELx<->PSR for signals

The SPSR_ELx format for exceptions taken from AArch32 differs from the
AArch32 PSR format. Thus, we must translate between the two when setting
up a compat sigframe, or restoring context from a compat sigframe.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 7206dc93a58fb764 ("arm64: Expose Arm v8.4 features")
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Suzuki Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/signal32.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 77b91f478995..12aec0a66376 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -243,6 +243,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	int err;
 	sigset_t set;
 	struct compat_aux_sigframe __user *aux;
+	unsigned long psr;
 
 	err = get_sigset_t(&set, &sf->uc.uc_sigmask);
 	if (err == 0) {
@@ -266,7 +267,9 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	__get_user_error(regs->compat_sp, &sf->uc.uc_mcontext.arm_sp, err);
 	__get_user_error(regs->compat_lr, &sf->uc.uc_mcontext.arm_lr, err);
 	__get_user_error(regs->pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__get_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err);
+	__get_user_error(psr, &sf->uc.uc_mcontext.arm_cpsr, err);
+
+	regs->pstate = compat_psr_to_pstate(psr);
 
 	/*
 	 * Avoid compat_sys_sigreturn() restarting.
@@ -414,6 +417,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf,
 				 struct pt_regs *regs, sigset_t *set)
 {
 	struct compat_aux_sigframe __user *aux;
+	unsigned long psr = pstate_to_compat_psr(regs->pstate);
 	int err = 0;
 
 	__put_user_error(regs->regs[0], &sf->uc.uc_mcontext.arm_r0, err);
@@ -432,7 +436,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf,
 	__put_user_error(regs->compat_sp, &sf->uc.uc_mcontext.arm_sp, err);
 	__put_user_error(regs->compat_lr, &sf->uc.uc_mcontext.arm_lr, err);
 	__put_user_error(regs->pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__put_user_error(regs->pstate, &sf->uc.uc_mcontext.arm_cpsr, err);
+	__put_user_error(psr, &sf->uc.uc_mcontext.arm_cpsr, err);
 
 	__put_user_error((compat_ulong_t)0, &sf->uc.uc_mcontext.trap_no, err);
 	/* set the compat FSR WnR */
-- 
cgit v1.2.3


From 76fc52bd07d3e9cb708f1a50b60c825c96acd606 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 5 Jul 2018 15:16:51 +0100
Subject: arm64: ptrace: map SPSR_ELx<->PSR for compat tasks

The SPSR_ELx format for exceptions taken from AArch32 is slightly
different to the AArch32 PSR format.

Map between the two in the compat ptrace code.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 7206dc93a58fb764 ("arm64: Expose Arm v8.4 features")
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Suzuki Poulose <suzuki.poulose@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/ptrace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 5df75ab6a3c8..2c4b09f84dd0 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1076,6 +1076,7 @@ static int compat_gpr_get(struct task_struct *target,
 			break;
 		case 16:
 			reg = task_pt_regs(target)->pstate;
+			reg = pstate_to_compat_psr(reg);
 			break;
 		case 17:
 			reg = task_pt_regs(target)->orig_x0;
@@ -1143,6 +1144,7 @@ static int compat_gpr_set(struct task_struct *target,
 			newregs.pc = reg;
 			break;
 		case 16:
+			reg = compat_psr_to_pstate(reg);
 			newregs.pstate = reg;
 			break;
 		case 17:
-- 
cgit v1.2.3


From d64567f67835736d65086e9bfc41a19b2863c32e Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 5 Jul 2018 15:16:52 +0100
Subject: arm64: use PSR_AA32 definitions

Some code cares about the SPSR_ELx format for exceptions taken from
AArch32 to inspect or manipulate the SPSR_ELx value, which is already in
the SPSR_ELx format, and not in the AArch32 PSR format.

To separate these from cases where we care about the AArch32 PSR format,
migrate these cases to use the PSR_AA32_* definitions rather than
COMPAT_PSR_*.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/processor.h   |  6 +++---
 arch/arm64/include/asm/ptrace.h      |  2 +-
 arch/arm64/kernel/armv8_deprecated.c | 24 ++++++++++++------------
 arch/arm64/kernel/cpufeature.c       |  2 +-
 arch/arm64/kernel/process.c          | 20 ++++++++++----------
 arch/arm64/kernel/ptrace.c           | 20 ++++++++++----------
 arch/arm64/kernel/signal32.c         | 10 +++++-----
 7 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index a73ae1e49200..e02612105d78 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -182,12 +182,12 @@ static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc,
 				       unsigned long sp)
 {
 	start_thread_common(regs, pc);
-	regs->pstate = COMPAT_PSR_MODE_USR;
+	regs->pstate = PSR_AA32_MODE_USR;
 	if (pc & 1)
-		regs->pstate |= COMPAT_PSR_T_BIT;
+		regs->pstate |= PSR_AA32_T_BIT;
 
 #ifdef __AARCH64EB__
-	regs->pstate |= COMPAT_PSR_E_BIT;
+	regs->pstate |= PSR_AA32_E_BIT;
 #endif
 
 	regs->compat_sp = sp;
diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index 1b2a253de6a1..d55237eb89bb 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -211,7 +211,7 @@ static inline void forget_syscall(struct pt_regs *regs)
 
 #ifdef CONFIG_COMPAT
 #define compat_thumb_mode(regs) \
-	(((regs)->pstate & COMPAT_PSR_T_BIT))
+	(((regs)->pstate & PSR_AA32_T_BIT))
 #else
 #define compat_thumb_mode(regs) (0)
 #endif
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index d4707abb2f16..d2c0938ccaec 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -441,8 +441,8 @@ static struct undef_hook swp_hooks[] = {
 	{
 		.instr_mask	= 0x0fb00ff0,
 		.instr_val	= 0x01000090,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= swp_handler
 	},
 	{ }
@@ -521,15 +521,15 @@ static struct undef_hook cp15_barrier_hooks[] = {
 	{
 		.instr_mask	= 0x0fff0fdf,
 		.instr_val	= 0x0e070f9a,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= cp15barrier_handler,
 	},
 	{
 		.instr_mask	= 0x0fff0fff,
 		.instr_val	= 0x0e070f95,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= cp15barrier_handler,
 	},
 	{ }
@@ -562,10 +562,10 @@ static int compat_setend_handler(struct pt_regs *regs, u32 big_endian)
 
 	if (big_endian) {
 		insn = "setend be";
-		regs->pstate |= COMPAT_PSR_E_BIT;
+		regs->pstate |= PSR_AA32_E_BIT;
 	} else {
 		insn = "setend le";
-		regs->pstate &= ~COMPAT_PSR_E_BIT;
+		regs->pstate &= ~PSR_AA32_E_BIT;
 	}
 
 	trace_instruction_emulation(insn, regs->pc);
@@ -593,16 +593,16 @@ static struct undef_hook setend_hooks[] = {
 	{
 		.instr_mask	= 0xfffffdff,
 		.instr_val	= 0xf1010000,
-		.pstate_mask	= COMPAT_PSR_MODE_MASK,
-		.pstate_val	= COMPAT_PSR_MODE_USR,
+		.pstate_mask	= PSR_AA32_MODE_MASK,
+		.pstate_val	= PSR_AA32_MODE_USR,
 		.fn		= a32_setend_handler,
 	},
 	{
 		/* Thumb mode */
 		.instr_mask	= 0x0000fff7,
 		.instr_val	= 0x0000b650,
-		.pstate_mask	= (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_MASK),
-		.pstate_val	= (COMPAT_PSR_T_BIT | COMPAT_PSR_MODE_USR),
+		.pstate_mask	= (PSR_AA32_T_BIT | PSR_AA32_MODE_MASK),
+		.pstate_val	= (PSR_AA32_T_BIT | PSR_AA32_MODE_USR),
 		.fn		= t16_setend_handler,
 	},
 	{}
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 25d5cef00333..4b3dc9fc9c68 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1723,7 +1723,7 @@ static int emulate_mrs(struct pt_regs *regs, u32 insn)
 static struct undef_hook mrs_hook = {
 	.instr_mask = 0xfff00000,
 	.instr_val  = 0xd5300000,
-	.pstate_mask = COMPAT_PSR_MODE_MASK,
+	.pstate_mask = PSR_AA32_MODE_MASK,
 	.pstate_val = PSR_MODE_EL0t,
 	.fn = emulate_mrs,
 };
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index e10bc363f533..740b31f77ade 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -177,16 +177,16 @@ static void print_pstate(struct pt_regs *regs)
 	if (compat_user_mode(regs)) {
 		printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c)\n",
 			pstate,
-			pstate & COMPAT_PSR_N_BIT ? 'N' : 'n',
-			pstate & COMPAT_PSR_Z_BIT ? 'Z' : 'z',
-			pstate & COMPAT_PSR_C_BIT ? 'C' : 'c',
-			pstate & COMPAT_PSR_V_BIT ? 'V' : 'v',
-			pstate & COMPAT_PSR_Q_BIT ? 'Q' : 'q',
-			pstate & COMPAT_PSR_T_BIT ? "T32" : "A32",
-			pstate & COMPAT_PSR_E_BIT ? "BE" : "LE",
-			pstate & COMPAT_PSR_A_BIT ? 'A' : 'a',
-			pstate & COMPAT_PSR_I_BIT ? 'I' : 'i',
-			pstate & COMPAT_PSR_F_BIT ? 'F' : 'f');
+			pstate & PSR_AA32_N_BIT ? 'N' : 'n',
+			pstate & PSR_AA32_Z_BIT ? 'Z' : 'z',
+			pstate & PSR_AA32_C_BIT ? 'C' : 'c',
+			pstate & PSR_AA32_V_BIT ? 'V' : 'v',
+			pstate & PSR_AA32_Q_BIT ? 'Q' : 'q',
+			pstate & PSR_AA32_T_BIT ? "T32" : "A32",
+			pstate & PSR_AA32_E_BIT ? "BE" : "LE",
+			pstate & PSR_AA32_A_BIT ? 'A' : 'a',
+			pstate & PSR_AA32_I_BIT ? 'I' : 'i',
+			pstate & PSR_AA32_F_BIT ? 'F' : 'f');
 	} else {
 		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO)\n",
 			pstate,
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 2c4b09f84dd0..42ff28aa5a00 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1681,15 +1681,15 @@ static int valid_compat_regs(struct user_pt_regs *regs)
 
 	if (!system_supports_mixed_endian_el0()) {
 		if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN))
-			regs->pstate |= COMPAT_PSR_E_BIT;
+			regs->pstate |= PSR_AA32_E_BIT;
 		else
-			regs->pstate &= ~COMPAT_PSR_E_BIT;
+			regs->pstate &= ~PSR_AA32_E_BIT;
 	}
 
 	if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) &&
-	    (regs->pstate & COMPAT_PSR_A_BIT) == 0 &&
-	    (regs->pstate & COMPAT_PSR_I_BIT) == 0 &&
-	    (regs->pstate & COMPAT_PSR_F_BIT) == 0) {
+	    (regs->pstate & PSR_AA32_A_BIT) == 0 &&
+	    (regs->pstate & PSR_AA32_I_BIT) == 0 &&
+	    (regs->pstate & PSR_AA32_F_BIT) == 0) {
 		return 1;
 	}
 
@@ -1697,11 +1697,11 @@ static int valid_compat_regs(struct user_pt_regs *regs)
 	 * Force PSR to a valid 32-bit EL0t, preserving the same bits as
 	 * arch/arm.
 	 */
-	regs->pstate &= COMPAT_PSR_N_BIT | COMPAT_PSR_Z_BIT |
-			COMPAT_PSR_C_BIT | COMPAT_PSR_V_BIT |
-			COMPAT_PSR_Q_BIT | COMPAT_PSR_IT_MASK |
-			COMPAT_PSR_GE_MASK | COMPAT_PSR_E_BIT |
-			COMPAT_PSR_T_BIT;
+	regs->pstate &= PSR_AA32_N_BIT | PSR_AA32_Z_BIT |
+			PSR_AA32_C_BIT | PSR_AA32_V_BIT |
+			PSR_AA32_Q_BIT | PSR_AA32_IT_MASK |
+			PSR_AA32_GE_MASK | PSR_AA32_E_BIT |
+			PSR_AA32_T_BIT;
 	regs->pstate |= PSR_MODE32_BIT;
 
 	return 0;
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 12aec0a66376..fca761be18c8 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -375,22 +375,22 @@ static void compat_setup_return(struct pt_regs *regs, struct k_sigaction *ka,
 {
 	compat_ulong_t handler = ptr_to_compat(ka->sa.sa_handler);
 	compat_ulong_t retcode;
-	compat_ulong_t spsr = regs->pstate & ~(PSR_f | COMPAT_PSR_E_BIT);
+	compat_ulong_t spsr = regs->pstate & ~(PSR_f | PSR_AA32_E_BIT);
 	int thumb;
 
 	/* Check if the handler is written for ARM or Thumb */
 	thumb = handler & 1;
 
 	if (thumb)
-		spsr |= COMPAT_PSR_T_BIT;
+		spsr |= PSR_AA32_T_BIT;
 	else
-		spsr &= ~COMPAT_PSR_T_BIT;
+		spsr &= ~PSR_AA32_T_BIT;
 
 	/* The IT state must be cleared for both ARM and Thumb-2 */
-	spsr &= ~COMPAT_PSR_IT_MASK;
+	spsr &= ~PSR_AA32_IT_MASK;
 
 	/* Restore the original endianness */
-	spsr |= COMPAT_PSR_ENDSTATE;
+	spsr |= PSR_AA32_ENDSTATE;
 
 	if (ka->sa.sa_flags & SA_RESTORER) {
 		retcode = ptr_to_compat(ka->sa.sa_restorer);
-- 
cgit v1.2.3


From 256c0960b7b6453dc90a4e879da52ab76b4037f9 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 5 Jul 2018 15:16:53 +0100
Subject: kvm/arm: use PSR_AA32 definitions

Some code cares about the SPSR_ELx format for exceptions taken from
AArch32 to inspect or manipulate the SPSR_ELx value, which is already in
the SPSR_ELx format, and not in the AArch32 PSR format.

To separate these from cases where we care about the AArch32 PSR format,
migrate these cases to use the PSR_AA32_* definitions rather than
COMPAT_PSR_*.

There should be no functional change as a result of this patch.

Note that arm64 KVM does not support a compat KVM API, and always uses
the SPSR_ELx format, even for AArch32 guests.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Christoffer Dall <christoffer.dall@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/include/asm/kvm_emulate.h       | 14 +++++++-------
 arch/arm64/include/asm/kvm_emulate.h     | 10 +++++-----
 arch/arm64/kvm/guest.c                   | 14 +++++++-------
 arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c |  2 +-
 arch/arm64/kvm/regmap.c                  | 22 +++++++++++-----------
 arch/arm64/kvm/reset.c                   |  4 ++--
 virt/kvm/arm/aarch32.c                   | 20 ++++++++++----------
 7 files changed, 43 insertions(+), 43 deletions(-)

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 6493bd479ddc..fe2fb1ddd771 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -26,13 +26,13 @@
 #include <asm/cputype.h>
 
 /* arm64 compatibility macros */
-#define COMPAT_PSR_MODE_ABT	ABT_MODE
-#define COMPAT_PSR_MODE_UND	UND_MODE
-#define COMPAT_PSR_T_BIT	PSR_T_BIT
-#define COMPAT_PSR_I_BIT	PSR_I_BIT
-#define COMPAT_PSR_A_BIT	PSR_A_BIT
-#define COMPAT_PSR_E_BIT	PSR_E_BIT
-#define COMPAT_PSR_IT_MASK	PSR_IT_MASK
+#define PSR_AA32_MODE_ABT	ABT_MODE
+#define PSR_AA32_MODE_UND	UND_MODE
+#define PSR_AA32_T_BIT		PSR_T_BIT
+#define PSR_AA32_I_BIT		PSR_I_BIT
+#define PSR_AA32_A_BIT		PSR_A_BIT
+#define PSR_AA32_E_BIT		PSR_E_BIT
+#define PSR_AA32_IT_MASK	PSR_IT_MASK
 
 unsigned long *vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num);
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index 1dab3a984608..0c97e45d1dc3 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -140,7 +140,7 @@ static inline void kvm_skip_instr(struct kvm_vcpu *vcpu, bool is_wide_instr)
 
 static inline void vcpu_set_thumb(struct kvm_vcpu *vcpu)
 {
-	*vcpu_cpsr(vcpu) |= COMPAT_PSR_T_BIT;
+	*vcpu_cpsr(vcpu) |= PSR_AA32_T_BIT;
 }
 
 /*
@@ -190,8 +190,8 @@ static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu)
 	u32 mode;
 
 	if (vcpu_mode_is_32bit(vcpu)) {
-		mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
-		return mode > COMPAT_PSR_MODE_USR;
+		mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
+		return mode > PSR_AA32_MODE_USR;
 	}
 
 	mode = *vcpu_cpsr(vcpu) & PSR_MODE_MASK;
@@ -329,7 +329,7 @@ static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu)
 static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu)) {
-		*vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT;
+		*vcpu_cpsr(vcpu) |= PSR_AA32_E_BIT;
 	} else {
 		u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1);
 		sctlr |= (1 << 25);
@@ -340,7 +340,7 @@ static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu)
 static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
-		return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT);
+		return !!(*vcpu_cpsr(vcpu) & PSR_AA32_E_BIT);
 
 	return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & (1 << 25));
 }
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 56a0260ceb11..cdd4d9d6d575 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -107,14 +107,14 @@ static int set_core_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 	}
 
 	if (off == KVM_REG_ARM_CORE_REG(regs.pstate)) {
-		u32 mode = (*(u32 *)valp) & COMPAT_PSR_MODE_MASK;
+		u32 mode = (*(u32 *)valp) & PSR_AA32_MODE_MASK;
 		switch (mode) {
-		case COMPAT_PSR_MODE_USR:
-		case COMPAT_PSR_MODE_FIQ:
-		case COMPAT_PSR_MODE_IRQ:
-		case COMPAT_PSR_MODE_SVC:
-		case COMPAT_PSR_MODE_ABT:
-		case COMPAT_PSR_MODE_UND:
+		case PSR_AA32_MODE_USR:
+		case PSR_AA32_MODE_FIQ:
+		case PSR_AA32_MODE_IRQ:
+		case PSR_AA32_MODE_SVC:
+		case PSR_AA32_MODE_ABT:
+		case PSR_AA32_MODE_UND:
 		case PSR_MODE_EL0t:
 		case PSR_MODE_EL1t:
 		case PSR_MODE_EL1h:
diff --git a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
index 39be799d0417..215c7c0eb3b0 100644
--- a/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
+++ b/arch/arm64/kvm/hyp/vgic-v2-cpuif-proxy.c
@@ -27,7 +27,7 @@
 static bool __hyp_text __is_be(struct kvm_vcpu *vcpu)
 {
 	if (vcpu_mode_is_32bit(vcpu))
-		return !!(read_sysreg_el2(spsr) & COMPAT_PSR_E_BIT);
+		return !!(read_sysreg_el2(spsr) & PSR_AA32_E_BIT);
 
 	return !!(read_sysreg(SCTLR_EL1) & SCTLR_ELx_EE);
 }
diff --git a/arch/arm64/kvm/regmap.c b/arch/arm64/kvm/regmap.c
index eefe403a2e63..7a5173ea2276 100644
--- a/arch/arm64/kvm/regmap.c
+++ b/arch/arm64/kvm/regmap.c
@@ -112,22 +112,22 @@ static const unsigned long vcpu_reg_offsets[VCPU_NR_MODES][16] = {
 unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
 {
 	unsigned long *reg_array = (unsigned long *)&vcpu->arch.ctxt.gp_regs.regs;
-	unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
 
 	switch (mode) {
-	case COMPAT_PSR_MODE_USR ... COMPAT_PSR_MODE_SVC:
+	case PSR_AA32_MODE_USR ... PSR_AA32_MODE_SVC:
 		mode &= ~PSR_MODE32_BIT; /* 0 ... 3 */
 		break;
 
-	case COMPAT_PSR_MODE_ABT:
+	case PSR_AA32_MODE_ABT:
 		mode = 4;
 		break;
 
-	case COMPAT_PSR_MODE_UND:
+	case PSR_AA32_MODE_UND:
 		mode = 5;
 		break;
 
-	case COMPAT_PSR_MODE_SYS:
+	case PSR_AA32_MODE_SYS:
 		mode = 0;	/* SYS maps to USR */
 		break;
 
@@ -143,13 +143,13 @@ unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num)
  */
 static int vcpu_spsr32_mode(const struct kvm_vcpu *vcpu)
 {
-	unsigned long mode = *vcpu_cpsr(vcpu) & COMPAT_PSR_MODE_MASK;
+	unsigned long mode = *vcpu_cpsr(vcpu) & PSR_AA32_MODE_MASK;
 	switch (mode) {
-	case COMPAT_PSR_MODE_SVC: return KVM_SPSR_SVC;
-	case COMPAT_PSR_MODE_ABT: return KVM_SPSR_ABT;
-	case COMPAT_PSR_MODE_UND: return KVM_SPSR_UND;
-	case COMPAT_PSR_MODE_IRQ: return KVM_SPSR_IRQ;
-	case COMPAT_PSR_MODE_FIQ: return KVM_SPSR_FIQ;
+	case PSR_AA32_MODE_SVC: return KVM_SPSR_SVC;
+	case PSR_AA32_MODE_ABT: return KVM_SPSR_ABT;
+	case PSR_AA32_MODE_UND: return KVM_SPSR_UND;
+	case PSR_AA32_MODE_IRQ: return KVM_SPSR_IRQ;
+	case PSR_AA32_MODE_FIQ: return KVM_SPSR_FIQ;
 	default: BUG();
 	}
 }
diff --git a/arch/arm64/kvm/reset.c b/arch/arm64/kvm/reset.c
index a74311beda35..4e4aedaf7ab7 100644
--- a/arch/arm64/kvm/reset.c
+++ b/arch/arm64/kvm/reset.c
@@ -42,8 +42,8 @@ static const struct kvm_regs default_regs_reset = {
 };
 
 static const struct kvm_regs default_regs_reset32 = {
-	.regs.pstate = (COMPAT_PSR_MODE_SVC | COMPAT_PSR_A_BIT |
-			COMPAT_PSR_I_BIT | COMPAT_PSR_F_BIT),
+	.regs.pstate = (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT |
+			PSR_AA32_I_BIT | PSR_AA32_F_BIT),
 };
 
 static bool cpu_has_32bit_el1(void)
diff --git a/virt/kvm/arm/aarch32.c b/virt/kvm/arm/aarch32.c
index efc84cbe8277..5abbe9b3c652 100644
--- a/virt/kvm/arm/aarch32.c
+++ b/virt/kvm/arm/aarch32.c
@@ -108,9 +108,9 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 {
 	unsigned long itbits, cond;
 	unsigned long cpsr = *vcpu_cpsr(vcpu);
-	bool is_arm = !(cpsr & COMPAT_PSR_T_BIT);
+	bool is_arm = !(cpsr & PSR_AA32_T_BIT);
 
-	if (is_arm || !(cpsr & COMPAT_PSR_IT_MASK))
+	if (is_arm || !(cpsr & PSR_AA32_IT_MASK))
 		return;
 
 	cond = (cpsr & 0xe000) >> 13;
@@ -123,7 +123,7 @@ static void __hyp_text kvm_adjust_itstate(struct kvm_vcpu *vcpu)
 	else
 		itbits = (itbits << 1) & 0x1f;
 
-	cpsr &= ~COMPAT_PSR_IT_MASK;
+	cpsr &= ~PSR_AA32_IT_MASK;
 	cpsr |= cond << 13;
 	cpsr |= (itbits & 0x1c) << (10 - 2);
 	cpsr |= (itbits & 0x3) << 25;
@@ -138,7 +138,7 @@ void __hyp_text kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr)
 {
 	bool is_thumb;
 
-	is_thumb = !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_T_BIT);
+	is_thumb = !!(*vcpu_cpsr(vcpu) & PSR_AA32_T_BIT);
 	if (is_thumb && !is_wide_instr)
 		*vcpu_pc(vcpu) += 2;
 	else
@@ -164,16 +164,16 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 {
 	unsigned long cpsr;
 	unsigned long new_spsr_value = *vcpu_cpsr(vcpu);
-	bool is_thumb = (new_spsr_value & COMPAT_PSR_T_BIT);
+	bool is_thumb = (new_spsr_value & PSR_AA32_T_BIT);
 	u32 return_offset = return_offsets[vect_offset >> 2][is_thumb];
 	u32 sctlr = vcpu_cp15(vcpu, c1_SCTLR);
 
-	cpsr = mode | COMPAT_PSR_I_BIT;
+	cpsr = mode | PSR_AA32_I_BIT;
 
 	if (sctlr & (1 << 30))
-		cpsr |= COMPAT_PSR_T_BIT;
+		cpsr |= PSR_AA32_T_BIT;
 	if (sctlr & (1 << 25))
-		cpsr |= COMPAT_PSR_E_BIT;
+		cpsr |= PSR_AA32_E_BIT;
 
 	*vcpu_cpsr(vcpu) = cpsr;
 
@@ -192,7 +192,7 @@ static void prepare_fault32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset)
 
 void kvm_inject_undef32(struct kvm_vcpu *vcpu)
 {
-	prepare_fault32(vcpu, COMPAT_PSR_MODE_UND, 4);
+	prepare_fault32(vcpu, PSR_AA32_MODE_UND, 4);
 }
 
 /*
@@ -216,7 +216,7 @@ static void inject_abt32(struct kvm_vcpu *vcpu, bool is_pabt,
 		fsr = &vcpu_cp15(vcpu, c5_DFSR);
 	}
 
-	prepare_fault32(vcpu, COMPAT_PSR_MODE_ABT | COMPAT_PSR_A_BIT, vect_offset);
+	prepare_fault32(vcpu, PSR_AA32_MODE_ABT | PSR_AA32_A_BIT, vect_offset);
 
 	*far = addr;
 
-- 
cgit v1.2.3


From 7373fed2f258e640031387616a2275a6fc0d7231 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 5 Jul 2018 15:16:54 +0100
Subject: arm64: remove unused COMPAT_PSR definitions

Now that users have been migrated to PSR_AA32, kill the unused
COMPAT_PSR definitions.

The only difference we need a definition for is COMPAT_PSR_DIT_BIT,
which differs from PSR_AA32_DIT_BIT.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/ptrace.h | 28 ----------------------------
 1 file changed, 28 deletions(-)

diff --git a/arch/arm64/include/asm/ptrace.h b/arch/arm64/include/asm/ptrace.h
index d55237eb89bb..177b851ca6d9 100644
--- a/arch/arm64/include/asm/ptrace.h
+++ b/arch/arm64/include/asm/ptrace.h
@@ -66,35 +66,7 @@
 #endif
 
 /* AArch32 CPSR bits, as seen in AArch32 */
-#define COMPAT_PSR_MODE_MASK	0x0000001f
-#define COMPAT_PSR_MODE_USR	0x00000010
-#define COMPAT_PSR_MODE_FIQ	0x00000011
-#define COMPAT_PSR_MODE_IRQ	0x00000012
-#define COMPAT_PSR_MODE_SVC	0x00000013
-#define COMPAT_PSR_MODE_ABT	0x00000017
-#define COMPAT_PSR_MODE_HYP	0x0000001a
-#define COMPAT_PSR_MODE_UND	0x0000001b
-#define COMPAT_PSR_MODE_SYS	0x0000001f
-#define COMPAT_PSR_T_BIT	0x00000020
-#define COMPAT_PSR_F_BIT	0x00000040
-#define COMPAT_PSR_I_BIT	0x00000080
-#define COMPAT_PSR_A_BIT	0x00000100
-#define COMPAT_PSR_E_BIT	0x00000200
 #define COMPAT_PSR_DIT_BIT	0x00200000
-#define COMPAT_PSR_J_BIT	0x01000000
-#define COMPAT_PSR_Q_BIT	0x08000000
-#define COMPAT_PSR_V_BIT	0x10000000
-#define COMPAT_PSR_C_BIT	0x20000000
-#define COMPAT_PSR_Z_BIT	0x40000000
-#define COMPAT_PSR_N_BIT	0x80000000
-#define COMPAT_PSR_IT_MASK	0x0600fc00	/* If-Then execution state mask */
-#define COMPAT_PSR_GE_MASK	0x000f0000
-
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define COMPAT_PSR_ENDSTATE	COMPAT_PSR_E_BIT
-#else
-#define COMPAT_PSR_ENDSTATE	0
-#endif
 
 /*
  * These are 'magic' values for PTRACE_PEEKUSR that return info about where a
-- 
cgit v1.2.3


From 3b8c9f1cdfc506e94e992ae66b68bbe416f89610 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 11 Jun 2018 14:22:09 +0100
Subject: arm64: IPI each CPU after invalidating the I-cache for kernel
 mappings

When invalidating the instruction cache for a kernel mapping via
flush_icache_range(), it is also necessary to flush the pipeline for
other CPUs so that instructions fetched into the pipeline before the
I-cache invalidation are discarded. For example, if module 'foo' is
unloaded and then module 'bar' is loaded into the same area of memory,
a CPU could end up executing instructions from 'foo' when branching into
'bar' if these instructions were fetched into the pipeline before 'foo'
was unloaded.

Whilst this is highly unlikely to occur in practice, particularly as
any exception acts as a context-synchronizing operation, following the
letter of the architecture requires us to execute an ISB on each CPU
in order for the new instruction stream to be visible.

Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/cacheflush.h | 27 ++++++++++++++++++++++++++-
 arch/arm64/kernel/cpu_errata.c      |  2 +-
 arch/arm64/kernel/insn.c            | 18 ++++--------------
 arch/arm64/mm/cache.S               |  4 ++--
 4 files changed, 33 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d264a7274811..19844211a4e6 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -19,6 +19,7 @@
 #ifndef __ASM_CACHEFLUSH_H
 #define __ASM_CACHEFLUSH_H
 
+#include <linux/kgdb.h>
 #include <linux/mm.h>
 
 /*
@@ -71,7 +72,7 @@
  *		- kaddr  - page address
  *		- size   - region size
  */
-extern void flush_icache_range(unsigned long start, unsigned long end);
+extern void __flush_icache_range(unsigned long start, unsigned long end);
 extern int  invalidate_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
 extern void __inval_dcache_area(void *addr, size_t len);
@@ -81,6 +82,30 @@ extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 extern void sync_icache_aliases(void *kaddr, unsigned long len);
 
+static inline void flush_icache_range(unsigned long start, unsigned long end)
+{
+	__flush_icache_range(start, end);
+
+	/*
+	 * IPI all online CPUs so that they undergo a context synchronization
+	 * event and are forced to refetch the new instructions.
+	 */
+#ifdef CONFIG_KGDB
+	/*
+	 * KGDB performs cache maintenance with interrupts disabled, so we
+	 * will deadlock trying to IPI the secondary CPUs. In theory, we can
+	 * set CACHE_FLUSH_IS_SAFE to 0 to avoid this known issue, but that
+	 * just means that KGDB will elide the maintenance altogether! As it
+	 * turns out, KGDB uses IPIs to round-up the secondary CPUs during
+	 * the patching operation, so we don't need extra IPIs here anyway.
+	 * In which case, add a KGDB-specific bodge and return early.
+	 */
+	if (kgdb_connected && irqs_disabled())
+		return;
+#endif
+	kick_all_cpus_sync();
+}
+
 static inline void flush_cache_mm(struct mm_struct *mm)
 {
 }
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 5d59ff9a8da9..459129712dfa 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -107,7 +107,7 @@ static void __copy_hyp_vect_bpi(int slot, const char *hyp_vecs_start,
 	for (i = 0; i < SZ_2K; i += 0x80)
 		memcpy(dst + i, hyp_vecs_start, hyp_vecs_end - hyp_vecs_start);
 
-	flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
+	__flush_icache_range((uintptr_t)dst, (uintptr_t)dst + SZ_2K);
 }
 
 static void __install_bp_hardening_cb(bp_hardening_cb_t fn,
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 816d03c4c913..0f6a2e0cfde0 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -216,8 +216,8 @@ int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
 
 	ret = aarch64_insn_write(tp, insn);
 	if (ret == 0)
-		flush_icache_range((uintptr_t)tp,
-				   (uintptr_t)tp + AARCH64_INSN_SIZE);
+		__flush_icache_range((uintptr_t)tp,
+				     (uintptr_t)tp + AARCH64_INSN_SIZE);
 
 	return ret;
 }
@@ -283,18 +283,8 @@ int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
 		if (ret)
 			return ret;
 
-		if (aarch64_insn_hotpatch_safe(insn, insns[0])) {
-			/*
-			 * ARMv8 architecture doesn't guarantee all CPUs see
-			 * the new instruction after returning from function
-			 * aarch64_insn_patch_text_nosync(). So send IPIs to
-			 * all other CPUs to achieve instruction
-			 * synchronization.
-			 */
-			ret = aarch64_insn_patch_text_nosync(addrs[0], insns[0]);
-			kick_all_cpus_sync();
-			return ret;
-		}
+		if (aarch64_insn_hotpatch_safe(insn, insns[0]))
+			return aarch64_insn_patch_text_nosync(addrs[0], insns[0]);
 	}
 
 	return aarch64_insn_patch_text_sync(addrs, insns, cnt);
diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 30334d81b021..0c22ede52f90 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -35,7 +35,7 @@
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-ENTRY(flush_icache_range)
+ENTRY(__flush_icache_range)
 	/* FALLTHROUGH */
 
 /*
@@ -77,7 +77,7 @@ alternative_else_nop_endif
 9:
 	mov	x0, #-EFAULT
 	b	1b
-ENDPROC(flush_icache_range)
+ENDPROC(__flush_icache_range)
 ENDPROC(__flush_cache_user_range)
 
 /*
-- 
cgit v1.2.3


From 693350a7998018391852c48f68956cf0f855b2b9 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 19 Jun 2018 17:55:28 +0100
Subject: arm64: insn: Don't fallback on nosync path for general insn patching

Patching kernel instructions at runtime requires other CPUs to undergo
a context synchronisation event via an explicit ISB or an IPI in order
to ensure that the new instructions are visible. This is required even
for "hotpatch" instructions such as NOP and BL, so avoid optimising in
this case and always go via stop_machine() when performing general
patching.

ftrace isn't quite as strict, so it can continue to call the nosync
code directly.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/insn.h |  2 --
 arch/arm64/kernel/insn.c      | 56 +------------------------------------------
 2 files changed, 1 insertion(+), 57 deletions(-)

diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index f62c56b1793f..c6802dea6cab 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -446,8 +446,6 @@ u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base,
 s32 aarch64_get_branch_offset(u32 insn);
 u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 
-bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
-
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index 0f6a2e0cfde0..2b3413549734 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -149,20 +149,6 @@ int __kprobes aarch64_insn_write(void *addr, u32 insn)
 	return __aarch64_insn_write(addr, cpu_to_le32(insn));
 }
 
-static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn)
-{
-	if (aarch64_get_insn_class(insn) != AARCH64_INSN_CLS_BR_SYS)
-		return false;
-
-	return	aarch64_insn_is_b(insn) ||
-		aarch64_insn_is_bl(insn) ||
-		aarch64_insn_is_svc(insn) ||
-		aarch64_insn_is_hvc(insn) ||
-		aarch64_insn_is_smc(insn) ||
-		aarch64_insn_is_brk(insn) ||
-		aarch64_insn_is_nop(insn);
-}
-
 bool __kprobes aarch64_insn_uses_literal(u32 insn)
 {
 	/* ldr/ldrsw (literal), prfm */
@@ -189,22 +175,6 @@ bool __kprobes aarch64_insn_is_branch(u32 insn)
 		aarch64_insn_is_bcond(insn);
 }
 
-/*
- * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a
- * Section B2.6.5 "Concurrent modification and execution of instructions":
- * Concurrent modification and execution of instructions can lead to the
- * resulting instruction performing any behavior that can be achieved by
- * executing any sequence of instructions that can be executed from the
- * same Exception level, except where the instruction before modification
- * and the instruction after modification is a B, BL, NOP, BKPT, SVC, HVC,
- * or SMC instruction.
- */
-bool __kprobes aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn)
-{
-	return __aarch64_insn_hotpatch_safe(old_insn) &&
-	       __aarch64_insn_hotpatch_safe(new_insn);
-}
-
 int __kprobes aarch64_insn_patch_text_nosync(void *addr, u32 insn)
 {
 	u32 *tp = addr;
@@ -239,11 +209,6 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 		for (i = 0; ret == 0 && i < pp->insn_cnt; i++)
 			ret = aarch64_insn_patch_text_nosync(pp->text_addrs[i],
 							     pp->new_insns[i]);
-		/*
-		 * aarch64_insn_patch_text_nosync() calls flush_icache_range(),
-		 * which ends with "dsb; isb" pair guaranteeing global
-		 * visibility.
-		 */
 		/* Notify other processors with an additional increment. */
 		atomic_inc(&pp->cpu_count);
 	} else {
@@ -255,8 +220,7 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 	return ret;
 }
 
-static
-int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
+int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
 {
 	struct aarch64_insn_patch patch = {
 		.text_addrs = addrs,
@@ -272,24 +236,6 @@ int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 				       cpu_online_mask);
 }
 
-int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
-{
-	int ret;
-	u32 insn;
-
-	/* Unsafe to patch multiple instructions without synchronizaiton */
-	if (cnt == 1) {
-		ret = aarch64_insn_read(addrs[0], &insn);
-		if (ret)
-			return ret;
-
-		if (aarch64_insn_hotpatch_safe(insn, insns[0]))
-			return aarch64_insn_patch_text_nosync(addrs[0], insns[0]);
-	}
-
-	return aarch64_insn_patch_text_sync(addrs, insns, cnt);
-}
-
 static int __kprobes aarch64_get_imm_shift_mask(enum aarch64_insn_imm_type type,
 						u32 *maskp, int *shiftp)
 {
-- 
cgit v1.2.3


From bb9e8755a4259a306cd1691b4e17c4c485d81c9e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 5 Jul 2018 16:47:56 +0100
Subject: drm/i915/selftests: Fixup recursive MI_BB_START for gen3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There's no magic bit0 in MI_BB_START for gen3, it's the same dword length
parameter as elsewhere and needs to be zero.

v2: Same bug in both live_requests and live_hanghcheck.

References: https://bugs.freedesktop.org/show_bug.cgi?id=107132
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705154756.5533-1-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/selftests/i915_request.c    | 5 +----
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 2 +-
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 521ae4a90ddf..e44aa3335d9e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -594,11 +594,8 @@ static struct i915_vma *recursive_batch(struct drm_i915_private *i915)
 	} else if (gen >= 6) {
 		*cmd++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*cmd++ = lower_32_bits(vma->node.start);
-	} else if (gen >= 4) {
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
-		*cmd++ = lower_32_bits(vma->node.start);
 	} else {
-		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT | 1;
+		*cmd++ = MI_BATCH_BUFFER_START | MI_BATCH_GTT;
 		*cmd++ = lower_32_bits(vma->node.start);
 	}
 	*cmd++ = MI_BATCH_BUFFER_END; /* terminate early in case of error */
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index fe7d3190ebfe..72547aa24538 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -193,7 +193,7 @@ static int emit_recurse_batch(struct hang *h,
 		batch += 1024 / sizeof(*batch);
 
 		*batch++ = MI_ARB_CHECK;
-		*batch++ = MI_BATCH_BUFFER_START | 2 << 6 | 1;
+		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
 		*batch++ = lower_32_bits(vma->node.start);
 	}
 	*batch++ = MI_BATCH_BUFFER_END; /* not reached */
-- 
cgit v1.2.3


From 0380cf7dbaca75c524e34b30979f0806124fa8e6 Mon Sep 17 00:00:00 2001
From: pascal paillet <p.paillet@st.com>
Date: Thu, 5 Jul 2018 14:25:57 +0000
Subject: regulator: core: Change suspend_late to suspend

Change suspend_late ops to suspend normal ops. The goal is to avoid
requesting all the regulator drivers to be operational in suspend late
phase.

Signed-off-by: pascal paillet <p.paillet@st.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c         | 26 +++++++++++++-------------
 include/linux/regulator/driver.h |  2 +-
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index 6ed568b96c0e..da9b0fed8330 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -4441,7 +4441,7 @@ void regulator_unregister(struct regulator_dev *rdev)
 EXPORT_SYMBOL_GPL(regulator_unregister);
 
 #ifdef CONFIG_SUSPEND
-static int _regulator_suspend_late(struct device *dev, void *data)
+static int _regulator_suspend(struct device *dev, void *data)
 {
 	struct regulator_dev *rdev = dev_to_rdev(dev);
 	suspend_state_t *state = data;
@@ -4455,20 +4455,20 @@ static int _regulator_suspend_late(struct device *dev, void *data)
 }
 
 /**
- * regulator_suspend_late - prepare regulators for system wide suspend
+ * regulator_suspend - prepare regulators for system wide suspend
  * @state: system suspend state
  *
  * Configure each regulator with it's suspend operating parameters for state.
  */
-static int regulator_suspend_late(struct device *dev)
+static int regulator_suspend(struct device *dev)
 {
 	suspend_state_t state = pm_suspend_target_state;
 
 	return class_for_each_device(&regulator_class, NULL, &state,
-				     _regulator_suspend_late);
+				     _regulator_suspend);
 }
 
-static int _regulator_resume_early(struct device *dev, void *data)
+static int _regulator_resume(struct device *dev, void *data)
 {
 	int ret = 0;
 	struct regulator_dev *rdev = dev_to_rdev(dev);
@@ -4481,35 +4481,35 @@ static int _regulator_resume_early(struct device *dev, void *data)
 
 	regulator_lock(rdev);
 
-	if (rdev->desc->ops->resume_early &&
+	if (rdev->desc->ops->resume &&
 	    (rstate->enabled == ENABLE_IN_SUSPEND ||
 	     rstate->enabled == DISABLE_IN_SUSPEND))
-		ret = rdev->desc->ops->resume_early(rdev);
+		ret = rdev->desc->ops->resume(rdev);
 
 	regulator_unlock(rdev);
 
 	return ret;
 }
 
-static int regulator_resume_early(struct device *dev)
+static int regulator_resume(struct device *dev)
 {
 	suspend_state_t state = pm_suspend_target_state;
 
 	return class_for_each_device(&regulator_class, NULL, &state,
-				     _regulator_resume_early);
+				     _regulator_resume);
 }
 
 #else /* !CONFIG_SUSPEND */
 
-#define regulator_suspend_late	NULL
-#define regulator_resume_early	NULL
+#define regulator_suspend	NULL
+#define regulator_resume	NULL
 
 #endif /* !CONFIG_SUSPEND */
 
 #ifdef CONFIG_PM
 static const struct dev_pm_ops __maybe_unused regulator_pm_ops = {
-	.suspend_late	= regulator_suspend_late,
-	.resume_early	= regulator_resume_early,
+	.suspend	= regulator_suspend,
+	.resume		= regulator_resume,
 };
 #endif
 
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index dea96ee39fdc..0fd8fbb74763 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -220,7 +220,7 @@ struct regulator_ops {
 	/* set regulator suspend operating mode (defined in consumer.h) */
 	int (*set_suspend_mode) (struct regulator_dev *, unsigned int mode);
 
-	int (*resume_early)(struct regulator_dev *rdev);
+	int (*resume)(struct regulator_dev *rdev);
 
 	int (*set_pull_down) (struct regulator_dev *);
 };
-- 
cgit v1.2.3


From d8842211b6f63d3f069df973d137de0a85964965 Mon Sep 17 00:00:00 2001
From: pascal paillet <p.paillet@st.com>
Date: Thu, 5 Jul 2018 14:25:56 +0000
Subject: driver core: Add device_link_remove function

Device_link_remove uses the same arguments than device_link_add. The Goal
is to avoid storing the link pointer.

Signed-off-by: pascal paillet <p.paillet@st.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/core.c    | 30 ++++++++++++++++++++++++++++++
 include/linux/device.h |  1 +
 2 files changed, 31 insertions(+)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 36622b52e419..3b380b1f2768 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -365,6 +365,36 @@ void device_link_del(struct device_link *link)
 }
 EXPORT_SYMBOL_GPL(device_link_del);
 
+/**
+ * device_link_remove - remove a link between two devices.
+ * @consumer: Consumer end of the link.
+ * @supplier: Supplier end of the link.
+ *
+ * The caller must ensure proper synchronization of this function with runtime
+ * PM.
+ */
+void device_link_remove(void *consumer, struct device *supplier)
+{
+	struct device_link *link;
+
+	if (WARN_ON(consumer == supplier))
+		return;
+
+	device_links_write_lock();
+	device_pm_lock();
+
+	list_for_each_entry(link, &supplier->links.consumers, s_node) {
+		if (link->consumer == consumer) {
+			kref_put(&link->kref, __device_link_del);
+			break;
+		}
+	}
+
+	device_pm_unlock();
+	device_links_write_unlock();
+}
+EXPORT_SYMBOL_GPL(device_link_remove);
+
 static void device_links_missing_supplier(struct device *dev)
 {
 	struct device_link *link;
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69dbcd18..9c1c3b1d5e11 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1316,6 +1316,7 @@ extern const char *dev_driver_string(const struct device *dev);
 struct device_link *device_link_add(struct device *consumer,
 				    struct device *supplier, u32 flags);
 void device_link_del(struct device_link *link);
+void device_link_remove(void *consumer, struct device *supplier);
 
 #ifdef CONFIG_PRINTK
 
-- 
cgit v1.2.3


From ed1ae2dd9f242c7a36e8e39100f6a7f6bcdfdd89 Mon Sep 17 00:00:00 2001
From: pascal paillet <p.paillet@st.com>
Date: Thu, 5 Jul 2018 14:25:56 +0000
Subject: regulator: core: Link consumer with regulator driver

Add a device link between the consumer and the driver so that
the consumer is not suspended before the driver. The goal is to avoid
implementing suspend_late ops in regulator drivers.

Signed-off-by: pascal paillet <p.paillet@st.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/core.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index da9b0fed8330..bb1324f93143 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1740,6 +1740,8 @@ struct regulator *_regulator_get(struct device *dev, const char *id,
 			rdev->use_count = 0;
 	}
 
+	device_link_add(dev, &rdev->dev, DL_FLAG_STATELESS);
+
 	return regulator;
 }
 
@@ -1829,9 +1831,21 @@ static void _regulator_put(struct regulator *regulator)
 
 	debugfs_remove_recursive(regulator->debugfs);
 
-	/* remove any sysfs entries */
-	if (regulator->dev)
+	if (regulator->dev) {
+		int count = 0;
+		struct regulator *r;
+
+		list_for_each_entry(r, &rdev->consumer_list, list)
+			if (r->dev == regulator->dev)
+				count++;
+
+		if (count == 1)
+			device_link_remove(regulator->dev, &rdev->dev);
+
+		/* remove any sysfs entries */
 		sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name);
+	}
+
 	regulator_lock(rdev);
 	list_del(&regulator->list);
 
-- 
cgit v1.2.3


From 010228e4a932ca1e8365e3b58c8e1e44c16ff793 Mon Sep 17 00:00:00 2001
From: Guoqing Jiang <gqjiang@suse.com>
Date: Mon, 2 Jul 2018 16:26:24 +0800
Subject: md-cluster: clear another node's suspend_area after the copy is
 finished

When one node leaves cluster or stops the resyncing
(resync or recovery) array, then other nodes need to
call recover_bitmaps to continue the unfinished task.

But we need to clear suspend_area later after other
nodes copy the resync information to their bitmap
(by call bitmap_copy_from_slot). Otherwise, all nodes
could write to the suspend_area even the suspend_area
is not handled by any node, because area_resyncing
returns 0 at the beginning of raid1_write_request.
Which means one node could write suspend_area while
another node is resyncing the same area, then data
could be inconsistent.

So let's clear suspend_area later to avoid above issue
with the protection of bm lock. Also it is straightforward
to clear suspend_area after nodes have copied the resync
info to bitmap.

Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/md-cluster.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 021cbf9ef1bf..1ac945f7a3c2 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -304,15 +304,6 @@ static void recover_bitmaps(struct md_thread *thread)
 	while (cinfo->recovery_map) {
 		slot = fls64((u64)cinfo->recovery_map) - 1;
 
-		/* Clear suspend_area associated with the bitmap */
-		spin_lock_irq(&cinfo->suspend_lock);
-		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
-			if (slot == s->slot) {
-				list_del(&s->list);
-				kfree(s);
-			}
-		spin_unlock_irq(&cinfo->suspend_lock);
-
 		snprintf(str, 64, "bitmap%04d", slot);
 		bm_lockres = lockres_init(mddev, str, NULL, 1);
 		if (!bm_lockres) {
@@ -331,6 +322,16 @@ static void recover_bitmaps(struct md_thread *thread)
 			pr_err("md-cluster: Could not copy data from bitmap %d\n", slot);
 			goto clear_bit;
 		}
+
+		/* Clear suspend_area associated with the bitmap */
+		spin_lock_irq(&cinfo->suspend_lock);
+		list_for_each_entry_safe(s, tmp, &cinfo->suspend_list, list)
+			if (slot == s->slot) {
+				list_del(&s->list);
+				kfree(s);
+			}
+		spin_unlock_irq(&cinfo->suspend_lock);
+
 		if (hi > 0) {
 			if (lo < mddev->recovery_cp)
 				mddev->recovery_cp = lo;
-- 
cgit v1.2.3


From 0357ba27bd611ff496390fdb172fdb31ca475398 Mon Sep 17 00:00:00 2001
From: Guoqing Jiang <gqjiang@suse.com>
Date: Mon, 2 Jul 2018 16:26:25 +0800
Subject: md-cluster: show array's status more accurate

When resync or recovery is happening in one node,
other nodes don't show the appropriate info now.

For example, when create an array in master node
without "--assume-clean", then assemble the array
in slave nodes, you can see "resync=PENDING" when
read /proc/mdstat in slave nodes. However, the info
is confusing since "PENDING" status is introduced
for start array in read-only mode.

We introduce RESYNCING_REMOTE flag to indicate that
resync thread is running in remote node. The flags
is set when node receive RESYNCING msg. And we clear
the REMOTE flag in following cases:

1. resync or recover is finished in master node,
   which means slaves receive msg with both lo
   and hi are set to 0.
2. node continues resync/recovery in recover_bitmaps.
3. when resync_finish is called.

Then we show accurate information in status_resync
by check REMOTE flags and with other conditions.

Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/md-cluster.c | 18 ++++++++++++++++--
 drivers/md/md.c         | 17 +++++++++++++++++
 drivers/md/md.h         |  1 +
 3 files changed, 34 insertions(+), 2 deletions(-)

diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 1ac945f7a3c2..5ed13c4fe72d 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -338,8 +338,14 @@ static void recover_bitmaps(struct md_thread *thread)
 			/* wake up thread to continue resync in case resync
 			 * is not finished */
 			if (mddev->recovery_cp != MaxSector) {
-			    set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
-			    md_wakeup_thread(mddev->thread);
+				/*
+				 * clear the REMOTE flag since we will launch
+				 * resync thread in current node.
+				 */
+				clear_bit(MD_RESYNCING_REMOTE,
+					  &mddev->recovery);
+				set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+				md_wakeup_thread(mddev->thread);
 			}
 		}
 clear_bit:
@@ -458,6 +464,11 @@ static void process_suspend_info(struct mddev *mddev,
 	struct suspend_info *s;
 
 	if (!hi) {
+		/*
+		 * clear the REMOTE flag since resync or recovery is finished
+		 * in remote node.
+		 */
+		clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		remove_suspend_info(mddev, slot);
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 		md_wakeup_thread(mddev->thread);
@@ -586,6 +597,7 @@ static int process_recvd_msg(struct mddev *mddev, struct cluster_msg *msg)
 		revalidate_disk(mddev->gendisk);
 		break;
 	case RESYNCING:
+		set_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 		process_suspend_info(mddev, le32_to_cpu(msg->slot),
 				     le64_to_cpu(msg->low),
 				     le64_to_cpu(msg->high));
@@ -1266,6 +1278,8 @@ static int resync_info_update(struct mddev *mddev, sector_t lo, sector_t hi)
 static int resync_finish(struct mddev *mddev)
 {
 	struct md_cluster_info *cinfo = mddev->cluster_info;
+
+	clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 	dlm_unlock_sync(cinfo->resync_lockres);
 	return resync_info_update(mddev, 0, 0);
 }
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 994aed2f9dff..da83d8710579 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -7680,6 +7680,23 @@ static int status_resync(struct seq_file *seq, struct mddev *mddev)
 		resync -= atomic_read(&mddev->recovery_active);
 
 	if (resync == 0) {
+		if (test_bit(MD_RESYNCING_REMOTE, &mddev->recovery)) {
+			struct md_rdev *rdev;
+
+			rdev_for_each(rdev, mddev)
+				if (rdev->raid_disk >= 0 &&
+				    !test_bit(Faulty, &rdev->flags) &&
+				    rdev->recovery_offset != MaxSector &&
+				    rdev->recovery_offset) {
+					seq_printf(seq, "\trecover=REMOTE");
+					return 1;
+				}
+			if (mddev->reshape_position != MaxSector)
+				seq_printf(seq, "\treshape=REMOTE");
+			else
+				seq_printf(seq, "\tresync=REMOTE");
+			return 1;
+		}
 		if (mddev->recovery_cp < MaxSector) {
 			seq_printf(seq, "\tresync=PENDING");
 			return 1;
diff --git a/drivers/md/md.h b/drivers/md/md.h
index 2d148bdaba74..8afd6bfdbfb9 100644
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -496,6 +496,7 @@ enum recovery_flags {
 	MD_RECOVERY_FROZEN,	/* User request to abort, and not restart, any action */
 	MD_RECOVERY_ERROR,	/* sync-action interrupted because io-error */
 	MD_RECOVERY_WAIT,	/* waiting for pers->start() to finish */
+	MD_RESYNCING_REMOTE,	/* remote node is running resync thread */
 };
 
 static inline int __must_check mddev_lock(struct mddev *mddev)
-- 
cgit v1.2.3


From df8c676418e1eb6f7bbafc1e01983f3538584894 Mon Sep 17 00:00:00 2001
From: Guoqing Jiang <gqjiang@suse.com>
Date: Mon, 2 Jul 2018 16:26:26 +0800
Subject: md-cluster: don't send msg if array is closing

If we close an array which resync thread is running,
then we don't need the node to send msg since another
node would launch the resync thread to continue the
rest works. Also send a message is time consuming,
we should avoid it.

Signed-off-by: Guoqing Jiang <gqjiang@suse.com>
Reviewed-by: NeilBrown <neilb@suse.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/md-cluster.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
index 5ed13c4fe72d..e8a74e92be30 100644
--- a/drivers/md/md-cluster.c
+++ b/drivers/md/md-cluster.c
@@ -1281,7 +1281,15 @@ static int resync_finish(struct mddev *mddev)
 
 	clear_bit(MD_RESYNCING_REMOTE, &mddev->recovery);
 	dlm_unlock_sync(cinfo->resync_lockres);
-	return resync_info_update(mddev, 0, 0);
+
+	/*
+	 * If resync thread is interrupted so we can't say resync is finished,
+	 * another node will launch resync thread to continue.
+	 */
+	if (test_bit(MD_CLOSING, &mddev->flags))
+		return 0;
+	else
+		return resync_info_update(mddev, 0, 0);
 }
 
 static int area_resyncing(struct mddev *mddev, int direction,
-- 
cgit v1.2.3


From ebc7709f65001911f275e13dd5f29b02803c0688 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 3 Jul 2018 07:51:09 +0100
Subject: md/r5cache: remove redundant pointer bio

Pointer bio is being assigned but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: variable 'bio' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5-cache.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/md/raid5-cache.c b/drivers/md/raid5-cache.c
index 2b775abf377b..7416db70c6cc 100644
--- a/drivers/md/raid5-cache.c
+++ b/drivers/md/raid5-cache.c
@@ -717,7 +717,6 @@ static void r5c_disable_writeback_async(struct work_struct *work)
 static void r5l_submit_current_io(struct r5l_log *log)
 {
 	struct r5l_io_unit *io = log->current_io;
-	struct bio *bio;
 	struct r5l_meta_block *block;
 	unsigned long flags;
 	u32 crc;
@@ -730,7 +729,6 @@ static void r5l_submit_current_io(struct r5l_log *log)
 	block->meta_size = cpu_to_le32(io->meta_offset);
 	crc = crc32c_le(log->uuid_checksum, block, PAGE_SIZE);
 	block->checksum = cpu_to_le32(crc);
-	bio = io->current_bio;
 
 	log->current_io = NULL;
 	spin_lock_irqsave(&log->io_list_lock, flags);
-- 
cgit v1.2.3


From 408633d2e740221204100efb9c3eed71f39aacd0 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Wed, 4 Jul 2018 20:25:57 +0530
Subject: drm/v3d: use new return type vm_fault_t in v3d_gem_fault

Instead of converting an errno into a vm_fault_t ourselves, use
vmf_insert_mixed() which returns a vm_fault_t directly.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180704145556.GA11036@jordon-HP-15-Notebook-PC
Reviewed-by: Matthew Wilcox <willy@infradead.org>
---
 drivers/gpu/drm/v3d/v3d_bo.c  | 28 +++++-----------------------
 drivers/gpu/drm/v3d/v3d_drv.h |  3 ++-
 2 files changed, 7 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index 7b1e2a549a71..54d96518a131 100644
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -227,37 +227,19 @@ v3d_set_mmap_vma_flags(struct vm_area_struct *vma)
 	vma->vm_page_prot = pgprot_writecombine(vm_get_page_prot(vma->vm_flags));
 }
 
-int v3d_gem_fault(struct vm_fault *vmf)
+vm_fault_t v3d_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct v3d_bo *bo = to_v3d_bo(obj);
-	unsigned long pfn;
+	pfn_t pfn;
 	pgoff_t pgoff;
-	int ret;
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
 	pgoff = (vmf->address - vma->vm_start) >> PAGE_SHIFT;
-	pfn = page_to_pfn(bo->pages[pgoff]);
-
-	ret = vm_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, PFN_DEV));
-
-	switch (ret) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	pfn = __pfn_to_pfn_t(page_to_pfn(bo->pages[pgoff]), PFN_DEV);
+
+	return vmf_insert_mixed(vma, vmf->address, pfn);
 }
 
 int v3d_mmap(struct file *filp, struct vm_area_struct *vma)
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index f32ac8c98f37..282763c9c7f6 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -2,6 +2,7 @@
 /* Copyright (C) 2015-2018 Broadcom */
 
 #include <linux/reservation.h>
+#include <linux/mm_types.h>
 #include <drm/drmP.h>
 #include <drm/drm_encoder.h>
 #include <drm/drm_gem.h>
@@ -252,7 +253,7 @@ int v3d_mmap_bo_ioctl(struct drm_device *dev, void *data,
 		      struct drm_file *file_priv);
 int v3d_get_bo_offset_ioctl(struct drm_device *dev, void *data,
 			    struct drm_file *file_priv);
-int v3d_gem_fault(struct vm_fault *vmf);
+vm_fault_t v3d_gem_fault(struct vm_fault *vmf);
 int v3d_mmap(struct file *filp, struct vm_area_struct *vma);
 struct reservation_object *v3d_prime_res_obj(struct drm_gem_object *obj);
 int v3d_prime_mmap(struct drm_gem_object *obj, struct vm_area_struct *vma);
-- 
cgit v1.2.3


From 624bb0c08b8298cbc6a16f9c68edc93f767716ec Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Tue, 3 Jul 2018 10:05:12 -0700
Subject: drm/v3d: Delay the scheduler timeout if we're still making progress.

GTF-GLES2.gtf.GL.acos.acos_float_vert_xvary submits jobs that take 4
seconds at maximum resolution, but we still want to reset quickly if a
job is really hung.  Sample the CL's current address and the return
address (since we call into tile lists repeatedly) and if either has
changed then assume we've made progress.

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Lucas Stach <l.stach@pengutronix.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703170515.6298-1-eric@anholt.net
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
---
 drivers/gpu/drm/v3d/v3d_drv.h   |  2 ++
 drivers/gpu/drm/v3d/v3d_regs.h  |  1 +
 drivers/gpu/drm/v3d/v3d_sched.c | 18 ++++++++++++++++++
 3 files changed, 21 insertions(+)

diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 282763c9c7f6..e6fed696ad86 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -184,6 +184,8 @@ struct v3d_job {
 
 	/* GPU virtual addresses of the start/end of the CL job. */
 	u32 start, end;
+
+	u32 timedout_ctca, timedout_ctra;
 };
 
 struct v3d_exec_info {
diff --git a/drivers/gpu/drm/v3d/v3d_regs.h b/drivers/gpu/drm/v3d/v3d_regs.h
index fc13282dfc2f..854046565989 100644
--- a/drivers/gpu/drm/v3d/v3d_regs.h
+++ b/drivers/gpu/drm/v3d/v3d_regs.h
@@ -222,6 +222,7 @@
 #define V3D_CLE_CTNCA(n) (V3D_CLE_CT0CA + 4 * n)
 #define V3D_CLE_CT0RA                                  0x00118
 #define V3D_CLE_CT1RA                                  0x0011c
+#define V3D_CLE_CTNRA(n) (V3D_CLE_CT0RA + 4 * n)
 #define V3D_CLE_CT0LC                                  0x00120
 #define V3D_CLE_CT1LC                                  0x00124
 #define V3D_CLE_CT0PC                                  0x00128
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 808bc901f567..00667c733dca 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -153,7 +153,25 @@ v3d_job_timedout(struct drm_sched_job *sched_job)
 	struct v3d_job *job = to_v3d_job(sched_job);
 	struct v3d_exec_info *exec = job->exec;
 	struct v3d_dev *v3d = exec->v3d;
+	enum v3d_queue job_q = job == &exec->bin ? V3D_BIN : V3D_RENDER;
 	enum v3d_queue q;
+	u32 ctca = V3D_CORE_READ(0, V3D_CLE_CTNCA(job_q));
+	u32 ctra = V3D_CORE_READ(0, V3D_CLE_CTNRA(job_q));
+
+	/* If the current address or return address have changed, then
+	 * the GPU has probably made progress and we should delay the
+	 * reset.  This could fail if the GPU got in an infinite loop
+	 * in the CL, but that is pretty unlikely outside of an i-g-t
+	 * testcase.
+	 */
+	if (job->timedout_ctca != ctca || job->timedout_ctra != ctra) {
+		job->timedout_ctca = ctca;
+		job->timedout_ctra = ctra;
+
+		schedule_delayed_work(&job->base.work_tdr,
+				      job->base.sched->timeout);
+		return;
+	}
 
 	mutex_lock(&v3d->reset_lock);
 
-- 
cgit v1.2.3


From e0d018119ae82cbde32c1d4f8e9b8d8f43a3c88a Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Tue, 3 Jul 2018 10:05:13 -0700
Subject: drm/v3d: Remove unnecessary dma_fence_ops.

The dma-fence core as of commit 418cc6ca0607 ("dma-fence: Make ->wait
callback optional") provides appropriate defaults for these methods.

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703170515.6298-2-eric@anholt.net
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
---
 drivers/gpu/drm/v3d/v3d_fence.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_fence.c b/drivers/gpu/drm/v3d/v3d_fence.c
index bfe31a89668b..50bfcf9a8a1a 100644
--- a/drivers/gpu/drm/v3d/v3d_fence.c
+++ b/drivers/gpu/drm/v3d/v3d_fence.c
@@ -35,19 +35,7 @@ static const char *v3d_fence_get_timeline_name(struct dma_fence *fence)
 		return "v3d-render";
 }
 
-static bool v3d_fence_enable_signaling(struct dma_fence *fence)
-{
-	return true;
-}
-
 const struct dma_fence_ops v3d_fence_ops = {
 	.get_driver_name = v3d_fence_get_driver_name,
 	.get_timeline_name = v3d_fence_get_timeline_name,
-	.enable_signaling = v3d_fence_enable_signaling,
-	/* Each of our fences gets signaled as complete by the IRQ
-	 * handler, so we rely on the core's tracking of signaling.
-	 */
-	.signaled = NULL,
-	.wait = dma_fence_default_wait,
-	.release = dma_fence_free,
 };
-- 
cgit v1.2.3


From 2dd4f211e70728af386684d912b964b62d5fa15f Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Tue, 3 Jul 2018 10:05:14 -0700
Subject: drm/v3d: Add missing v3d documentation structure.

This was a failure of "git add" on my part -- we already referenced
the doc from drivers.rst.

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703170515.6298-3-eric@anholt.net
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
---
 Documentation/gpu/v3d.rst | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 Documentation/gpu/v3d.rst

diff --git a/Documentation/gpu/v3d.rst b/Documentation/gpu/v3d.rst
new file mode 100644
index 000000000000..543f7fbf526e
--- /dev/null
+++ b/Documentation/gpu/v3d.rst
@@ -0,0 +1,28 @@
+=====================================
+ drm/v3d Broadcom V3D Graphics Driver
+=====================================
+
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_drv.c
+   :doc: Broadcom V3D Graphics Driver
+
+GPU buffer object (BO) management
+---------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_bo.c
+   :doc: V3D GEM BO management support
+
+Address space management
+===========================================
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_mmu.c
+   :doc: Broadcom V3D MMU
+
+GPU Scheduling
+===========================================
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_sched.c
+   :doc: Broadcom V3D scheduling
+
+Interrupts
+--------------
+
+.. kernel-doc:: drivers/gpu/drm/v3d/v3d_irq.c
+   :doc: Interrupt management for the V3D engine
-- 
cgit v1.2.3


From a65020d0a65da69f504b5ee4d43d255d0875999e Mon Sep 17 00:00:00 2001
From: Eric Anholt <eric@anholt.net>
Date: Tue, 3 Jul 2018 10:05:15 -0700
Subject: drm/v3d: Fix a grammar nit in the scheduler docs.

Signed-off-by: Eric Anholt <eric@anholt.net>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703170515.6298-4-eric@anholt.net
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Daniel Vetter <daniel@ffwll.ch>
---
 drivers/gpu/drm/v3d/v3d_sched.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 00667c733dca..a5501581d96b 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -14,8 +14,8 @@
  * to the HW only when it has completed the last one, instead of
  * filling up the CT[01]Q FIFOs with jobs.  Similarly, we use
  * v3d_job_dependency() to manage the dependency between bin and
- * render, instead of having the clients submit jobs with using the
- * HW's semaphores to interlock between them.
+ * render, instead of having the clients submit jobs using the HW's
+ * semaphores to interlock between them.
  */
 
 #include <linux/kthread.h>
-- 
cgit v1.2.3


From 9757973f41b52cd8fa7850100b8b0ae85261bcc5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 21 Jun 2018 20:46:58 +0300
Subject: drm/i915: Remove pointless if-else from sdvo code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The return value is a bool so we can just return the result of
the biwise AND. The compiler will take care of the rest.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180621174658.18823-1-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_sdvo.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 36f81a96b8f6..5417c54f67da 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1401,10 +1401,7 @@ static bool intel_sdvo_connector_get_hw_state(struct intel_connector *connector)
 
 	intel_sdvo_get_active_outputs(intel_sdvo, &active_outputs);
 
-	if (active_outputs & intel_sdvo_connector->output_flag)
-		return true;
-	else
-		return false;
+	return active_outputs & intel_sdvo_connector->output_flag;
 }
 
 bool intel_sdvo_port_enabled(struct drm_i915_private *dev_priv,
-- 
cgit v1.2.3


From ca52bea9fa8007f837ab4685b98979bbffc33416 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Fri, 15 Jun 2018 20:07:34 +0300
Subject: drm/atomic-helper: Use bitwise or for filling a bitmask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Using += to set the bits in a mask looks funny. It works in this case
because we never set the same bit twice. But let's switch to |= to
make this look more regular.

Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180615170734.2774-1-ville.syrjala@linux.intel.com
Reviewed-by: Eric Anholt <eric@anholt.net>
---
 drivers/gpu/drm/drm_atomic_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 8008a7de2e10..7787e0e6bbc6 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -645,7 +645,7 @@ drm_atomic_helper_check_modeset(struct drm_device *dev,
 		if (ret)
 			return ret;
 
-		connectors_mask += BIT(i);
+		connectors_mask |= BIT(i);
 	}
 
 	/*
-- 
cgit v1.2.3


From 73d8e5fba54f400cd5fe48517dbe6776fb16c2ad Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 5 Jul 2018 18:15:23 +0100
Subject: drm/i915/selftests: Detect unknown swizzling correctly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

i915_gem_detect_bit_6_swizzle() tries to hide unknown swizzling from
userspace (and ourselves) leaving us with the only clue inside
i915->quirks & QUIRK_PIN_SWIZZLED_PAGES. If we see this bit set, it
means that we really have no clue as to what the swizzle pattern is
being used in any one page and so cannot compute what the reference
value should be in our tiling selftests. We have to skip the test.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107133
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705171523.18462-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_object.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 77dd7a510ea6..885153268968 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -347,6 +347,14 @@ static int igt_partial_tiling(void *arg)
 		unsigned int pitch;
 		struct tile tile;
 
+		if (i915->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+			/*
+			 * The swizzling pattern is actually unknown as it
+			 * varies based on physical address of each page.
+			 * See i915_gem_detect_bit_6_swizzle().
+			 */
+			break;
+
 		tile.tiling = tiling;
 		switch (tiling) {
 		case I915_TILING_X:
@@ -357,8 +365,8 @@ static int igt_partial_tiling(void *arg)
 			break;
 		}
 
-		if (tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN ||
-		    tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
+		GEM_BUG_ON(tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN);
+		if (tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
 			continue;
 
 		if (INTEL_GEN(i915) <= 2) {
-- 
cgit v1.2.3


From 033692eb3ec8305f6e9998b297aaec6899680637 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:20 +0200
Subject: leds: triggers: make the MODULE_LICENSE string match the actual
 license
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These files are licensed under GPL version 2 only. So use "GPL v2"
instead of "GPL" (which means v2 or later).

Also remove an empty (but commented) line at the end of the license
header which nicely proves in the context that the drivers are really v2
only :-)

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-activity.c   | 4 ++--
 drivers/leds/trigger/ledtrig-camera.c     | 3 +--
 drivers/leds/trigger/ledtrig-default-on.c | 3 +--
 drivers/leds/trigger/ledtrig-gpio.c       | 3 +--
 drivers/leds/trigger/ledtrig-heartbeat.c  | 4 ++--
 drivers/leds/trigger/ledtrig-timer.c      | 3 +--
 6 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c
index 6c6f8a9b8d9a..b39e1bb9a9ec 100644
--- a/drivers/leds/trigger/ledtrig-activity.c
+++ b/drivers/leds/trigger/ledtrig-activity.c
@@ -7,8 +7,8 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
+
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/kernel_stat.h>
@@ -269,4 +269,4 @@ module_exit(activity_exit);
 
 MODULE_AUTHOR("Willy Tarreau <w@1wt.eu>");
 MODULE_DESCRIPTION("Activity LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-camera.c b/drivers/leds/trigger/ledtrig-camera.c
index 9bd73a8bad5c..091a09a20c58 100644
--- a/drivers/leds/trigger/ledtrig-camera.c
+++ b/drivers/leds/trigger/ledtrig-camera.c
@@ -10,7 +10,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -54,4 +53,4 @@ module_exit(ledtrig_camera_exit);
 
 MODULE_DESCRIPTION("LED Trigger for Camera Flash/Torch Control");
 MODULE_AUTHOR("Milo Kim");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c
index ff455cb46680..4ccea04b7a6b 100644
--- a/drivers/leds/trigger/ledtrig-default-on.c
+++ b/drivers/leds/trigger/ledtrig-default-on.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -42,4 +41,4 @@ module_exit(defon_trig_exit);
 
 MODULE_AUTHOR("Nick Forbes <nick.forbes@incepta.com>");
 MODULE_DESCRIPTION("Default-ON LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 8891e88d54dd..93906a17a4b6 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -6,7 +6,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -235,4 +234,4 @@ module_exit(gpio_trig_exit);
 
 MODULE_AUTHOR("Felipe Balbi <me@felipebalbi.com>");
 MODULE_DESCRIPTION("GPIO LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index f0896de410b8..304b929edb8e 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -9,8 +9,8 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
+
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -213,4 +213,4 @@ module_exit(heartbeat_trig_exit);
 
 MODULE_AUTHOR("Atsushi Nemoto <anemo@mba.ocn.ne.jp>");
 MODULE_DESCRIPTION("Heartbeat LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c
index 8d09327b5719..10fc0966b0e3 100644
--- a/drivers/leds/trigger/ledtrig-timer.c
+++ b/drivers/leds/trigger/ledtrig-timer.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -127,4 +126,4 @@ module_exit(timer_trig_exit);
 
 MODULE_AUTHOR("Richard Purdie <rpurdie@openedhand.com>");
 MODULE_DESCRIPTION("Timer LED trigger");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 2282e125a406e09331c5a785e3df29035c99a607 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:21 +0200
Subject: leds: triggers: let struct led_trigger::activate() return an error
 code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Given that activating a trigger can fail, let the callback return an
indication. This prevents to have a trigger active according to the
"trigger" sysfs attribute but not functional.

All users are changed accordingly to return 0 for now. There is no intended
change in behaviour.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/led-triggers.c               | 24 +++++++++++++++++++++---
 drivers/leds/trigger/ledtrig-activity.c   |  8 +++++---
 drivers/leds/trigger/ledtrig-backlight.c  |  8 +++++---
 drivers/leds/trigger/ledtrig-default-on.c |  3 ++-
 drivers/leds/trigger/ledtrig-gpio.c       |  8 +++++---
 drivers/leds/trigger/ledtrig-heartbeat.c  |  8 +++++---
 drivers/leds/trigger/ledtrig-netdev.c     |  8 +++++---
 drivers/leds/trigger/ledtrig-oneshot.c    |  8 +++++---
 drivers/leds/trigger/ledtrig-timer.c      |  8 +++++---
 drivers/leds/trigger/ledtrig-transient.c  |  8 +++++---
 drivers/tty/vt/keyboard.c                 |  4 +++-
 drivers/usb/core/ledtrig-usbport.c        |  7 ++++---
 include/linux/leds.h                      | 14 +++++++++-----
 net/bluetooth/leds.c                      |  6 ++++--
 net/mac80211/led.c                        | 20 +++++++++++++++-----
 net/rfkill/core.c                         |  4 +++-
 16 files changed, 101 insertions(+), 45 deletions(-)

diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 431123b048a2..a8786f4b3453 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -103,15 +103,16 @@ ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr,
 EXPORT_SYMBOL_GPL(led_trigger_show);
 
 /* Caller must ensure led_cdev->trigger_lock held */
-void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
+int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 {
 	unsigned long flags;
 	char *event = NULL;
 	char *envp[2];
 	const char *name;
+	int ret;
 
 	if (!led_cdev->trigger && !trig)
-		return;
+		return 0;
 
 	name = trig ? trig->name : "none";
 	event = kasprintf(GFP_KERNEL, "TRIGGER=%s", name);
@@ -134,8 +135,14 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 		list_add_tail(&led_cdev->trig_list, &trig->led_cdevs);
 		write_unlock_irqrestore(&trig->leddev_list_lock, flags);
 		led_cdev->trigger = trig;
+
 		if (trig->activate)
-			trig->activate(led_cdev);
+			ret = trig->activate(led_cdev);
+		else
+			ret = 0;
+
+		if (ret)
+			goto err_activate;
 	}
 
 	if (event) {
@@ -146,6 +153,17 @@ void led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 				"%s: Error sending uevent\n", __func__);
 		kfree(event);
 	}
+
+	return 0;
+
+err_activate:
+	led_cdev->trigger = NULL;
+	write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags);
+	list_del(&led_cdev->trig_list);
+	write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, flags);
+	led_set_brightness(led_cdev, LED_OFF);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(led_trigger_set);
 
diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c
index b39e1bb9a9ec..2fc065fb1754 100644
--- a/drivers/leds/trigger/ledtrig-activity.c
+++ b/drivers/leds/trigger/ledtrig-activity.c
@@ -178,20 +178,20 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
-static void activity_activate(struct led_classdev *led_cdev)
+static int activity_activate(struct led_classdev *led_cdev)
 {
 	struct activity_data *activity_data;
 	int rc;
 
 	activity_data = kzalloc(sizeof(*activity_data), GFP_KERNEL);
 	if (!activity_data)
-		return;
+		return 0;
 
 	led_cdev->trigger_data = activity_data;
 	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
 	if (rc) {
 		kfree(led_cdev->trigger_data);
-		return;
+		return 0;
 	}
 
 	activity_data->led_cdev = led_cdev;
@@ -201,6 +201,8 @@ static void activity_activate(struct led_classdev *led_cdev)
 	led_activity_function(&activity_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
 	led_cdev->activated = true;
+
+	return 0;
 }
 
 static void activity_deactivate(struct led_classdev *led_cdev)
diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 1ca1f1608f76..84512960d630 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -97,7 +97,7 @@ static ssize_t bl_trig_invert_store(struct device *dev,
 }
 static DEVICE_ATTR(inverted, 0644, bl_trig_invert_show, bl_trig_invert_store);
 
-static void bl_trig_activate(struct led_classdev *led)
+static int bl_trig_activate(struct led_classdev *led)
 {
 	int ret;
 
@@ -107,7 +107,7 @@ static void bl_trig_activate(struct led_classdev *led)
 	led->trigger_data = n;
 	if (!n) {
 		dev_err(led->dev, "unable to allocate backlight trigger\n");
-		return;
+		return 0;
 	}
 
 	ret = device_create_file(led->dev, &dev_attr_inverted);
@@ -124,11 +124,13 @@ static void bl_trig_activate(struct led_classdev *led)
 		dev_err(led->dev, "unable to register backlight trigger\n");
 	led->activated = true;
 
-	return;
+	return 0;
 
 err_invert:
 	led->trigger_data = NULL;
 	kfree(n);
+
+	return 0;
 }
 
 static void bl_trig_deactivate(struct led_classdev *led)
diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c
index 4ccea04b7a6b..2996fe672198 100644
--- a/drivers/leds/trigger/ledtrig-default-on.c
+++ b/drivers/leds/trigger/ledtrig-default-on.c
@@ -16,9 +16,10 @@
 #include <linux/leds.h>
 #include "../leds.h"
 
-static void defon_trig_activate(struct led_classdev *led_cdev)
+static int defon_trig_activate(struct led_classdev *led_cdev)
 {
 	led_set_brightness_nosleep(led_cdev, led_cdev->max_brightness);
+	return 0;
 }
 
 static struct led_trigger defon_led_trigger = {
diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index 93906a17a4b6..f5358c40d03f 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -162,14 +162,14 @@ static ssize_t gpio_trig_gpio_store(struct device *dev,
 }
 static DEVICE_ATTR(gpio, 0644, gpio_trig_gpio_show, gpio_trig_gpio_store);
 
-static void gpio_trig_activate(struct led_classdev *led)
+static int gpio_trig_activate(struct led_classdev *led)
 {
 	struct gpio_trig_data *gpio_data;
 	int ret;
 
 	gpio_data = kzalloc(sizeof(*gpio_data), GFP_KERNEL);
 	if (!gpio_data)
-		return;
+		return 0;
 
 	ret = device_create_file(led->dev, &dev_attr_gpio);
 	if (ret)
@@ -187,7 +187,7 @@ static void gpio_trig_activate(struct led_classdev *led)
 	led->trigger_data = gpio_data;
 	led->activated = true;
 
-	return;
+	return 0;
 
 err_brightness:
 	device_remove_file(led->dev, &dev_attr_inverted);
@@ -197,6 +197,8 @@ err_inverted:
 
 err_gpio:
 	kfree(gpio_data);
+
+	return 0;
 }
 
 static void gpio_trig_deactivate(struct led_classdev *led)
diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index 304b929edb8e..03a8dfce8fb9 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -121,21 +121,21 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
-static void heartbeat_trig_activate(struct led_classdev *led_cdev)
+static int heartbeat_trig_activate(struct led_classdev *led_cdev)
 {
 	struct heartbeat_trig_data *heartbeat_data;
 	int rc;
 
 	heartbeat_data = kzalloc(sizeof(*heartbeat_data), GFP_KERNEL);
 	if (!heartbeat_data)
-		return;
+		return 0;
 
 	led_cdev->trigger_data = heartbeat_data;
 	heartbeat_data->led_cdev = led_cdev;
 	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
 	if (rc) {
 		kfree(led_cdev->trigger_data);
-		return;
+		return 0;
 	}
 
 	timer_setup(&heartbeat_data->timer, led_heartbeat_function, 0);
@@ -145,6 +145,8 @@ static void heartbeat_trig_activate(struct led_classdev *led_cdev)
 	led_heartbeat_function(&heartbeat_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
 	led_cdev->activated = true;
+
+	return 0;
 }
 
 static void heartbeat_trig_deactivate(struct led_classdev *led_cdev)
diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index 6df4781a6308..bb05937255de 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -388,14 +388,14 @@ static void netdev_trig_work(struct work_struct *work)
 			(atomic_read(&trigger_data->interval)*2));
 }
 
-static void netdev_trig_activate(struct led_classdev *led_cdev)
+static int netdev_trig_activate(struct led_classdev *led_cdev)
 {
 	struct led_netdev_data *trigger_data;
 	int rc;
 
 	trigger_data = kzalloc(sizeof(struct led_netdev_data), GFP_KERNEL);
 	if (!trigger_data)
-		return;
+		return 0;
 
 	spin_lock_init(&trigger_data->lock);
 
@@ -432,7 +432,7 @@ static void netdev_trig_activate(struct led_classdev *led_cdev)
 	rc = register_netdevice_notifier(&trigger_data->notifier);
 	if (rc)
 		goto err_out_interval;
-	return;
+	return 0;
 
 err_out_interval:
 	device_remove_file(led_cdev->dev, &dev_attr_interval);
@@ -447,6 +447,8 @@ err_out_device_name:
 err_out:
 	led_cdev->trigger_data = NULL;
 	kfree(trigger_data);
+
+	return 0;
 }
 
 static void netdev_trig_deactivate(struct led_classdev *led_cdev)
diff --git a/drivers/leds/trigger/ledtrig-oneshot.c b/drivers/leds/trigger/ledtrig-oneshot.c
index b8ea9f0f1e19..7bbf92bd7f80 100644
--- a/drivers/leds/trigger/ledtrig-oneshot.c
+++ b/drivers/leds/trigger/ledtrig-oneshot.c
@@ -122,14 +122,14 @@ static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 static DEVICE_ATTR(shot, 0200, NULL, led_shot);
 
-static void oneshot_trig_activate(struct led_classdev *led_cdev)
+static int oneshot_trig_activate(struct led_classdev *led_cdev)
 {
 	struct oneshot_trig_data *oneshot_data;
 	int rc;
 
 	oneshot_data = kzalloc(sizeof(*oneshot_data), GFP_KERNEL);
 	if (!oneshot_data)
-		return;
+		return 0;
 
 	led_cdev->trigger_data = oneshot_data;
 
@@ -151,7 +151,7 @@ static void oneshot_trig_activate(struct led_classdev *led_cdev)
 
 	led_cdev->activated = true;
 
-	return;
+	return 0;
 
 err_out_invert:
 	device_remove_file(led_cdev->dev, &dev_attr_invert);
@@ -161,6 +161,8 @@ err_out_delayon:
 	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
 err_out_trig_data:
 	kfree(led_cdev->trigger_data);
+
+	return 0;
 }
 
 static void oneshot_trig_deactivate(struct led_classdev *led_cdev)
diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c
index 10fc0966b0e3..527055d815ad 100644
--- a/drivers/leds/trigger/ledtrig-timer.c
+++ b/drivers/leds/trigger/ledtrig-timer.c
@@ -70,7 +70,7 @@ static ssize_t led_delay_off_store(struct device *dev,
 static DEVICE_ATTR(delay_on, 0644, led_delay_on_show, led_delay_on_store);
 static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 
-static void timer_trig_activate(struct led_classdev *led_cdev)
+static int timer_trig_activate(struct led_classdev *led_cdev)
 {
 	int rc;
 
@@ -78,7 +78,7 @@ static void timer_trig_activate(struct led_classdev *led_cdev)
 
 	rc = device_create_file(led_cdev->dev, &dev_attr_delay_on);
 	if (rc)
-		return;
+		return 0;
 	rc = device_create_file(led_cdev->dev, &dev_attr_delay_off);
 	if (rc)
 		goto err_out_delayon;
@@ -87,10 +87,12 @@ static void timer_trig_activate(struct led_classdev *led_cdev)
 		      &led_cdev->blink_delay_off);
 	led_cdev->activated = true;
 
-	return;
+	return 0;
 
 err_out_delayon:
 	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
+
+	return 0;
 }
 
 static void timer_trig_deactivate(struct led_classdev *led_cdev)
diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c
index 9d1769073562..a55fc58179a9 100644
--- a/drivers/leds/trigger/ledtrig-transient.c
+++ b/drivers/leds/trigger/ledtrig-transient.c
@@ -152,7 +152,7 @@ static DEVICE_ATTR(duration, 0644, transient_duration_show,
 		   transient_duration_store);
 static DEVICE_ATTR(state, 0644, transient_state_show, transient_state_store);
 
-static void transient_trig_activate(struct led_classdev *led_cdev)
+static int transient_trig_activate(struct led_classdev *led_cdev)
 {
 	int rc;
 	struct transient_trig_data *tdata;
@@ -161,7 +161,7 @@ static void transient_trig_activate(struct led_classdev *led_cdev)
 	if (!tdata) {
 		dev_err(led_cdev->dev,
 			"unable to allocate transient trigger\n");
-		return;
+		return 0;
 	}
 	led_cdev->trigger_data = tdata;
 	tdata->led_cdev = led_cdev;
@@ -181,7 +181,7 @@ static void transient_trig_activate(struct led_classdev *led_cdev)
 	timer_setup(&tdata->timer, transient_timer_function, 0);
 	led_cdev->activated = true;
 
-	return;
+	return 0;
 
 err_out_state:
 	device_remove_file(led_cdev->dev, &dev_attr_duration);
@@ -191,6 +191,8 @@ err_out:
 	dev_err(led_cdev->dev, "unable to register transient trigger\n");
 	led_cdev->trigger_data = NULL;
 	kfree(tdata);
+
+	return 0;
 }
 
 static void transient_trig_deactivate(struct led_classdev *led_cdev)
diff --git a/drivers/tty/vt/keyboard.c b/drivers/tty/vt/keyboard.c
index d5b4a2b44ab8..de310621b8e7 100644
--- a/drivers/tty/vt/keyboard.c
+++ b/drivers/tty/vt/keyboard.c
@@ -959,7 +959,7 @@ struct kbd_led_trigger {
 	unsigned int mask;
 };
 
-static void kbd_led_trigger_activate(struct led_classdev *cdev)
+static int kbd_led_trigger_activate(struct led_classdev *cdev)
 {
 	struct kbd_led_trigger *trigger =
 		container_of(cdev->trigger, struct kbd_led_trigger, trigger);
@@ -970,6 +970,8 @@ static void kbd_led_trigger_activate(struct led_classdev *cdev)
 				  ledstate & trigger->mask ?
 					LED_FULL : LED_OFF);
 	tasklet_enable(&keyboard_tasklet);
+
+	return 0;
 }
 
 #define KBD_LED_TRIGGER(_led_bit, _name) {			\
diff --git a/drivers/usb/core/ledtrig-usbport.c b/drivers/usb/core/ledtrig-usbport.c
index d775ffea20c3..aa1d51458da7 100644
--- a/drivers/usb/core/ledtrig-usbport.c
+++ b/drivers/usb/core/ledtrig-usbport.c
@@ -298,14 +298,14 @@ static int usbport_trig_notify(struct notifier_block *nb, unsigned long action,
 	return NOTIFY_DONE;
 }
 
-static void usbport_trig_activate(struct led_classdev *led_cdev)
+static int usbport_trig_activate(struct led_classdev *led_cdev)
 {
 	struct usbport_trig_data *usbport_data;
 	int err;
 
 	usbport_data = kzalloc(sizeof(*usbport_data), GFP_KERNEL);
 	if (!usbport_data)
-		return;
+		return 0;
 	usbport_data->led_cdev = led_cdev;
 
 	/* List of ports */
@@ -322,10 +322,11 @@ static void usbport_trig_activate(struct led_classdev *led_cdev)
 	usb_register_notify(&usbport_data->nb);
 
 	led_cdev->activated = true;
-	return;
+	return 0;
 
 err_free:
 	kfree(usbport_data);
+	return 0;
 }
 
 static void usbport_trig_deactivate(struct led_classdev *led_cdev)
diff --git a/include/linux/leds.h b/include/linux/leds.h
index b7e82550e655..ba5baaaa43bf 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -253,7 +253,7 @@ static inline bool led_sysfs_is_disabled(struct led_classdev *led_cdev)
 struct led_trigger {
 	/* Trigger Properties */
 	const char	 *name;
-	void		(*activate)(struct led_classdev *led_cdev);
+	int		(*activate)(struct led_classdev *led_cdev);
 	void		(*deactivate)(struct led_classdev *led_cdev);
 
 	/* LEDs under control by this trigger (for simple triggers) */
@@ -288,8 +288,8 @@ extern void led_trigger_blink_oneshot(struct led_trigger *trigger,
 				      unsigned long *delay_off,
 				      int invert);
 extern void led_trigger_set_default(struct led_classdev *led_cdev);
-extern void led_trigger_set(struct led_classdev *led_cdev,
-			struct led_trigger *trigger);
+extern int led_trigger_set(struct led_classdev *led_cdev,
+			   struct led_trigger *trigger);
 extern void led_trigger_remove(struct led_classdev *led_cdev);
 
 static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
@@ -334,8 +334,12 @@ static inline void led_trigger_blink_oneshot(struct led_trigger *trigger,
 				      unsigned long *delay_off,
 				      int invert) {}
 static inline void led_trigger_set_default(struct led_classdev *led_cdev) {}
-static inline void led_trigger_set(struct led_classdev *led_cdev,
-				struct led_trigger *trigger) {}
+static inline int led_trigger_set(struct led_classdev *led_cdev,
+				  struct led_trigger *trigger)
+{
+	return 0;
+}
+
 static inline void led_trigger_remove(struct led_classdev *led_cdev) {}
 static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 {
diff --git a/net/bluetooth/leds.c b/net/bluetooth/leds.c
index cb670b5594eb..6d59a5023231 100644
--- a/net/bluetooth/leds.c
+++ b/net/bluetooth/leds.c
@@ -43,7 +43,7 @@ void hci_leds_update_powered(struct hci_dev *hdev, bool enabled)
 	led_trigger_event(bt_power_led_trigger, enabled ? LED_FULL : LED_OFF);
 }
 
-static void power_activate(struct led_classdev *led_cdev)
+static int power_activate(struct led_classdev *led_cdev)
 {
 	struct hci_basic_led_trigger *htrig;
 	bool powered;
@@ -52,10 +52,12 @@ static void power_activate(struct led_classdev *led_cdev)
 	powered = test_bit(HCI_UP, &htrig->hdev->flags);
 
 	led_trigger_event(led_cdev->trigger, powered ? LED_FULL : LED_OFF);
+
+	return 0;
 }
 
 static struct led_trigger *led_allocate_basic(struct hci_dev *hdev,
-			void (*activate)(struct led_classdev *led_cdev),
+			int (*activate)(struct led_classdev *led_cdev),
 			const char *name)
 {
 	struct hci_basic_led_trigger *htrig;
diff --git a/net/mac80211/led.c b/net/mac80211/led.c
index ba0b507ea691..d6c66fc19716 100644
--- a/net/mac80211/led.c
+++ b/net/mac80211/led.c
@@ -52,13 +52,15 @@ void ieee80211_free_led_names(struct ieee80211_local *local)
 	kfree(local->radio_led.name);
 }
 
-static void ieee80211_tx_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_tx_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     tx_led);
 
 	atomic_inc(&local->tx_led_active);
+
+	return 0;
 }
 
 static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev)
@@ -70,13 +72,15 @@ static void ieee80211_tx_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->tx_led_active);
 }
 
-static void ieee80211_rx_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_rx_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     rx_led);
 
 	atomic_inc(&local->rx_led_active);
+
+	return 0;
 }
 
 static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev)
@@ -88,13 +92,15 @@ static void ieee80211_rx_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->rx_led_active);
 }
 
-static void ieee80211_assoc_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_assoc_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     assoc_led);
 
 	atomic_inc(&local->assoc_led_active);
+
+	return 0;
 }
 
 static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev)
@@ -106,13 +112,15 @@ static void ieee80211_assoc_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->assoc_led_active);
 }
 
-static void ieee80211_radio_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_radio_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     radio_led);
 
 	atomic_inc(&local->radio_led_active);
+
+	return 0;
 }
 
 static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev)
@@ -124,13 +132,15 @@ static void ieee80211_radio_led_deactivate(struct led_classdev *led_cdev)
 	atomic_dec(&local->radio_led_active);
 }
 
-static void ieee80211_tpt_led_activate(struct led_classdev *led_cdev)
+static int ieee80211_tpt_led_activate(struct led_classdev *led_cdev)
 {
 	struct ieee80211_local *local = container_of(led_cdev->trigger,
 						     struct ieee80211_local,
 						     tpt_led);
 
 	atomic_inc(&local->tpt_led_active);
+
+	return 0;
 }
 
 static void ieee80211_tpt_led_deactivate(struct led_classdev *led_cdev)
diff --git a/net/rfkill/core.c b/net/rfkill/core.c
index a7a4e6ff9be2..1355f5ca8d22 100644
--- a/net/rfkill/core.c
+++ b/net/rfkill/core.c
@@ -141,13 +141,15 @@ static void rfkill_led_trigger_event(struct rfkill *rfkill)
 		led_trigger_event(trigger, LED_FULL);
 }
 
-static void rfkill_led_trigger_activate(struct led_classdev *led)
+static int rfkill_led_trigger_activate(struct led_classdev *led)
 {
 	struct rfkill *rfkill;
 
 	rfkill = container_of(led->trigger, struct rfkill, led_trigger);
 
 	rfkill_led_trigger_event(rfkill);
+
+	return 0;
 }
 
 const char *rfkill_get_led_trigger_name(struct rfkill *rfkill)
-- 
cgit v1.2.3


From a7e7a3156300a7e1982b03cc9cb8fb0c86434c49 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:22 +0200
Subject: leds: triggers: add device attribute support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As many triggers use device attributes, add support for these in
led_trigger_set which allows simplifying the drivers accordingly.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/led-triggers.c | 12 ++++++++++++
 include/linux/leds.h        | 11 +++++++++++
 2 files changed, 23 insertions(+)

diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index a8786f4b3453..3f3e8728d82c 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -127,6 +127,7 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 		led_stop_software_blink(led_cdev);
 		if (led_cdev->trigger->deactivate)
 			led_cdev->trigger->deactivate(led_cdev);
+		device_remove_groups(led_cdev->dev, led_cdev->trigger->groups);
 		led_cdev->trigger = NULL;
 		led_set_brightness(led_cdev, LED_OFF);
 	}
@@ -143,6 +144,12 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 
 		if (ret)
 			goto err_activate;
+
+		ret = device_add_groups(led_cdev->dev, trig->groups);
+		if (ret) {
+			dev_err(led_cdev->dev, "Failed to add trigger attributes\n");
+			goto err_add_groups;
+		}
 	}
 
 	if (event) {
@@ -156,7 +163,12 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 
 	return 0;
 
+err_add_groups:
+
+	if (trig->deactivate)
+		trig->deactivate(led_cdev);
 err_activate:
+
 	led_cdev->trigger = NULL;
 	write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags);
 	list_del(&led_cdev->trig_list);
diff --git a/include/linux/leds.h b/include/linux/leds.h
index ba5baaaa43bf..33484a5c7478 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -262,8 +262,19 @@ struct led_trigger {
 
 	/* Link to next registered trigger */
 	struct list_head  next_trig;
+
+	const struct attribute_group **groups;
 };
 
+/*
+ * Currently the attributes in struct led_trigger::groups are added directly to
+ * the LED device. As this might change in the future, the following
+ * macros abstract getting the LED device and its trigger_data from the dev
+ * parameter passed to the attribute accessor functions.
+ */
+#define led_trigger_get_led(dev)	((struct led_classdev *)dev_get_drvdata((dev)))
+#define led_trigger_get_drvdata(dev)	(led_get_trigger_data(led_trigger_get_led(dev)))
+
 ssize_t led_trigger_store(struct device *dev, struct device_attribute *attr,
 			const char *buf, size_t count);
 ssize_t led_trigger_show(struct device *dev, struct device_attribute *attr,
-- 
cgit v1.2.3


From a7d5904a6f44e0da05d62197521ec7d96cebb6aa Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:23 +0200
Subject: leds: triggers: handle .trigger_data and .activated() in the core
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This helps keeping these two fields consistent and drivers don't need to
care for this themselves any more.

Note that .activated isn't set to true automatically because that might
confuse some triggers when deactivating (e.g. ledtrig-gpio).

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/led-triggers.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
index 3f3e8728d82c..17d73db1456e 100644
--- a/drivers/leds/led-triggers.c
+++ b/drivers/leds/led-triggers.c
@@ -129,6 +129,8 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
 			led_cdev->trigger->deactivate(led_cdev);
 		device_remove_groups(led_cdev->dev, led_cdev->trigger->groups);
 		led_cdev->trigger = NULL;
+		led_cdev->trigger_data = NULL;
+		led_cdev->activated = false;
 		led_set_brightness(led_cdev, LED_OFF);
 	}
 	if (trig) {
@@ -170,6 +172,7 @@ err_add_groups:
 err_activate:
 
 	led_cdev->trigger = NULL;
+	led_cdev->trigger_data = NULL;
 	write_lock_irqsave(&led_cdev->trigger->leddev_list_lock, flags);
 	list_del(&led_cdev->trig_list);
 	write_unlock_irqrestore(&led_cdev->trigger->leddev_list_lock, flags);
-- 
cgit v1.2.3


From a0b750768371e410d77b60bcf49c18bd45078d55 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:24 +0200
Subject: leds: triggers: define module_led_trigger helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This helps to simplify modules that provide a simple led_trigger. It's
inspired by module_platform_driver, module_i2c_driver et al.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 include/linux/leds.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/leds.h b/include/linux/leds.h
index 33484a5c7478..a3ee10846a4b 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -326,6 +326,10 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 extern void led_trigger_rename_static(const char *name,
 				      struct led_trigger *trig);
 
+#define module_led_trigger(__led_trigger) \
+	module_driver(__led_trigger, led_trigger_register, \
+		      led_trigger_unregister)
+
 #else
 
 /* Trigger has no members */
-- 
cgit v1.2.3


From 9acc560de2aac73ef99c54f0fdfb86b4684296b5 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:25 +0200
Subject: leds: triggers: new function led_set_trigger_data()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is the natural counter part to the already existing
led_get_trigger_data().

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 include/linux/leds.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/leds.h b/include/linux/leds.h
index a3ee10846a4b..834683d603f9 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -303,6 +303,12 @@ extern int led_trigger_set(struct led_classdev *led_cdev,
 			   struct led_trigger *trigger);
 extern void led_trigger_remove(struct led_classdev *led_cdev);
 
+static inline void led_set_trigger_data(struct led_classdev *led_cdev,
+					void *trigger_data)
+{
+	led_cdev->trigger_data = trigger_data;
+}
+
 static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 {
 	return led_cdev->trigger_data;
@@ -356,6 +362,7 @@ static inline int led_trigger_set(struct led_classdev *led_cdev,
 }
 
 static inline void led_trigger_remove(struct led_classdev *led_cdev) {}
+static inline void led_set_trigger_data(struct led_classdev *led_cdev) {}
 static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 {
 	return NULL;
-- 
cgit v1.2.3


From f8112a1de1a728ffef0dd9f6c3005490c5f79ab1 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:26 +0200
Subject: leds: netdev trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The trigger core learned error handling for the activate callback and
can handle device attributes now. This allows simplifying the driver
considerably. Note that .deactivate() is only called when .activate()
succeeded, so the check for trigger_data being non-NULL can go away.
(It was broken before because the core didn't clear .trigger_data, so it
might have been non-NULL even if .activate() failed before.)

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-netdev.c | 99 +++++++++++------------------------
 1 file changed, 31 insertions(+), 68 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-netdev.c b/drivers/leds/trigger/ledtrig-netdev.c
index bb05937255de..3dd3ed46d473 100644
--- a/drivers/leds/trigger/ledtrig-netdev.c
+++ b/drivers/leds/trigger/ledtrig-netdev.c
@@ -94,8 +94,7 @@ static void set_baseline_state(struct led_netdev_data *trigger_data)
 static ssize_t device_name_show(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	ssize_t len;
 
 	spin_lock_bh(&trigger_data->lock);
@@ -109,8 +108,7 @@ static ssize_t device_name_store(struct device *dev,
 				 struct device_attribute *attr, const char *buf,
 				 size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 
 	if (size >= IFNAMSIZ)
 		return -EINVAL;
@@ -150,8 +148,7 @@ static DEVICE_ATTR_RW(device_name);
 static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 	enum netdev_led_attr attr)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	int bit;
 
 	switch (attr) {
@@ -174,8 +171,7 @@ static ssize_t netdev_led_attr_show(struct device *dev, char *buf,
 static ssize_t netdev_led_attr_store(struct device *dev, const char *buf,
 	size_t size, enum netdev_led_attr attr)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 	int bit;
@@ -255,8 +251,7 @@ static DEVICE_ATTR_RW(rx);
 static ssize_t interval_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n",
 		       jiffies_to_msecs(atomic_read(&trigger_data->interval)));
@@ -266,8 +261,7 @@ static ssize_t interval_store(struct device *dev,
 			      struct device_attribute *attr, const char *buf,
 			      size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_trigger_get_drvdata(dev);
 	unsigned long value;
 	int ret;
 
@@ -288,15 +282,23 @@ static ssize_t interval_store(struct device *dev,
 
 static DEVICE_ATTR_RW(interval);
 
+static struct attribute *netdev_trig_attrs[] = {
+	&dev_attr_device_name.attr,
+	&dev_attr_link.attr,
+	&dev_attr_rx.attr,
+	&dev_attr_tx.attr,
+	&dev_attr_interval.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(netdev_trig);
+
 static int netdev_trig_notify(struct notifier_block *nb,
 			      unsigned long evt, void *dv)
 {
 	struct net_device *dev =
 		netdev_notifier_info_to_dev((struct netdev_notifier_info *)dv);
-	struct led_netdev_data *trigger_data = container_of(nb,
-							    struct
-							    led_netdev_data,
-							    notifier);
+	struct led_netdev_data *trigger_data =
+		container_of(nb, struct led_netdev_data, notifier);
 
 	if (evt != NETDEV_UP && evt != NETDEV_DOWN && evt != NETDEV_CHANGE
 	    && evt != NETDEV_REGISTER && evt != NETDEV_UNREGISTER
@@ -342,10 +344,8 @@ static int netdev_trig_notify(struct notifier_block *nb,
 /* here's the real work! */
 static void netdev_trig_work(struct work_struct *work)
 {
-	struct led_netdev_data *trigger_data = container_of(work,
-							    struct
-							    led_netdev_data,
-							    work.work);
+	struct led_netdev_data *trigger_data =
+		container_of(work, struct led_netdev_data, work.work);
 	struct rtnl_link_stats64 *dev_stats;
 	unsigned int new_activity;
 	struct rtnl_link_stats64 temp;
@@ -395,7 +395,7 @@ static int netdev_trig_activate(struct led_classdev *led_cdev)
 
 	trigger_data = kzalloc(sizeof(struct led_netdev_data), GFP_KERNEL);
 	if (!trigger_data)
-		return 0;
+		return -ENOMEM;
 
 	spin_lock_init(&trigger_data->lock);
 
@@ -412,71 +412,34 @@ static int netdev_trig_activate(struct led_classdev *led_cdev)
 	atomic_set(&trigger_data->interval, msecs_to_jiffies(50));
 	trigger_data->last_activity = 0;
 
-	led_cdev->trigger_data = trigger_data;
+	led_set_trigger_data(led_cdev, trigger_data);
 
-	rc = device_create_file(led_cdev->dev, &dev_attr_device_name);
-	if (rc)
-		goto err_out;
-	rc = device_create_file(led_cdev->dev, &dev_attr_link);
-	if (rc)
-		goto err_out_device_name;
-	rc = device_create_file(led_cdev->dev, &dev_attr_rx);
-	if (rc)
-		goto err_out_link;
-	rc = device_create_file(led_cdev->dev, &dev_attr_tx);
-	if (rc)
-		goto err_out_rx;
-	rc = device_create_file(led_cdev->dev, &dev_attr_interval);
-	if (rc)
-		goto err_out_tx;
 	rc = register_netdevice_notifier(&trigger_data->notifier);
 	if (rc)
-		goto err_out_interval;
-	return 0;
-
-err_out_interval:
-	device_remove_file(led_cdev->dev, &dev_attr_interval);
-err_out_tx:
-	device_remove_file(led_cdev->dev, &dev_attr_tx);
-err_out_rx:
-	device_remove_file(led_cdev->dev, &dev_attr_rx);
-err_out_link:
-	device_remove_file(led_cdev->dev, &dev_attr_link);
-err_out_device_name:
-	device_remove_file(led_cdev->dev, &dev_attr_device_name);
-err_out:
-	led_cdev->trigger_data = NULL;
-	kfree(trigger_data);
+		kfree(trigger_data);
 
-	return 0;
+	return rc;
 }
 
 static void netdev_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct led_netdev_data *trigger_data = led_cdev->trigger_data;
+	struct led_netdev_data *trigger_data = led_get_trigger_data(led_cdev);
 
-	if (trigger_data) {
-		unregister_netdevice_notifier(&trigger_data->notifier);
+	unregister_netdevice_notifier(&trigger_data->notifier);
 
-		device_remove_file(led_cdev->dev, &dev_attr_device_name);
-		device_remove_file(led_cdev->dev, &dev_attr_link);
-		device_remove_file(led_cdev->dev, &dev_attr_rx);
-		device_remove_file(led_cdev->dev, &dev_attr_tx);
-		device_remove_file(led_cdev->dev, &dev_attr_interval);
-
-		cancel_delayed_work_sync(&trigger_data->work);
+	cancel_delayed_work_sync(&trigger_data->work);
 
-		if (trigger_data->net_dev)
-			dev_put(trigger_data->net_dev);
+	if (trigger_data->net_dev)
+		dev_put(trigger_data->net_dev);
 
-		kfree(trigger_data);
-	}
+	kfree(trigger_data);
 }
 
 static struct led_trigger netdev_led_trigger = {
 	.name = "netdev",
 	.activate = netdev_trig_activate,
 	.deactivate = netdev_trig_deactivate,
+	.groups = netdev_trig_groups,
 };
 
 static int __init netdev_trig_init(void)
-- 
cgit v1.2.3


From 2b7b6d44e29160eb12abd950c374babf21ed83d4 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:27 +0200
Subject: leds: timer trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The trigger core learned error handling for the activate callback and
can handle device attributes now. This allows simplifying the driver
considerably. Note that .deactivate() is only called when .activate()
succeeded, so the check for .trigger_data being non-NULL can go away.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-timer.c | 53 +++++++++---------------------------
 1 file changed, 13 insertions(+), 40 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c
index 527055d815ad..7c14983781ee 100644
--- a/drivers/leds/trigger/ledtrig-timer.c
+++ b/drivers/leds/trigger/ledtrig-timer.c
@@ -20,7 +20,7 @@
 static ssize_t led_delay_on_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_on);
 }
@@ -28,7 +28,7 @@ static ssize_t led_delay_on_show(struct device *dev,
 static ssize_t led_delay_on_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	ssize_t ret = -EINVAL;
 
@@ -45,7 +45,7 @@ static ssize_t led_delay_on_store(struct device *dev,
 static ssize_t led_delay_off_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_off);
 }
@@ -53,7 +53,7 @@ static ssize_t led_delay_off_show(struct device *dev,
 static ssize_t led_delay_off_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	ssize_t ret = -EINVAL;
 
@@ -70,39 +70,23 @@ static ssize_t led_delay_off_store(struct device *dev,
 static DEVICE_ATTR(delay_on, 0644, led_delay_on_show, led_delay_on_store);
 static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 
+static struct attribute *timer_trig_attrs[] = {
+	&dev_attr_delay_on.attr,
+	&dev_attr_delay_off.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(timer_trig);
+
 static int timer_trig_activate(struct led_classdev *led_cdev)
 {
-	int rc;
-
-	led_cdev->trigger_data = NULL;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_on);
-	if (rc)
-		return 0;
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_off);
-	if (rc)
-		goto err_out_delayon;
-
 	led_blink_set(led_cdev, &led_cdev->blink_delay_on,
 		      &led_cdev->blink_delay_off);
-	led_cdev->activated = true;
-
-	return 0;
-
-err_out_delayon:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
 
 	return 0;
 }
 
 static void timer_trig_deactivate(struct led_classdev *led_cdev)
 {
-	if (led_cdev->activated) {
-		device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-		device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-		led_cdev->activated = false;
-	}
-
 	/* Stop blinking */
 	led_set_brightness(led_cdev, LED_OFF);
 }
@@ -111,20 +95,9 @@ static struct led_trigger timer_led_trigger = {
 	.name     = "timer",
 	.activate = timer_trig_activate,
 	.deactivate = timer_trig_deactivate,
+	.groups = timer_trig_groups,
 };
-
-static int __init timer_trig_init(void)
-{
-	return led_trigger_register(&timer_led_trigger);
-}
-
-static void __exit timer_trig_exit(void)
-{
-	led_trigger_unregister(&timer_led_trigger);
-}
-
-module_init(timer_trig_init);
-module_exit(timer_trig_exit);
+module_led_trigger(timer_led_trigger);
 
 MODULE_AUTHOR("Richard Purdie <rpurdie@openedhand.com>");
 MODULE_DESCRIPTION("Timer LED trigger");
-- 
cgit v1.2.3


From 823f786ac7615f1bf822227fc4cbeafe11fb6bf8 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:28 +0200
Subject: leds: transient trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The trigger core learned error handling for the activate callback and
can handle device attributes now. This allows simplifying the driver
considerably. Note that .deactivate() is only called when .activate()
succeeded, so the check for .activated can go away.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-transient.c | 98 ++++++++++----------------------
 1 file changed, 30 insertions(+), 68 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-transient.c b/drivers/leds/trigger/ledtrig-transient.c
index a55fc58179a9..a80bb82aacc2 100644
--- a/drivers/leds/trigger/ledtrig-transient.c
+++ b/drivers/leds/trigger/ledtrig-transient.c
@@ -42,8 +42,8 @@ static void transient_timer_function(struct timer_list *t)
 static ssize_t transient_activate_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%d\n", transient_data->activate);
 }
@@ -51,8 +51,9 @@ static ssize_t transient_activate_show(struct device *dev,
 static ssize_t transient_activate_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -94,8 +95,7 @@ static ssize_t transient_activate_store(struct device *dev,
 static ssize_t transient_duration_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%lu\n", transient_data->duration);
 }
@@ -103,8 +103,8 @@ static ssize_t transient_duration_show(struct device *dev,
 static ssize_t transient_duration_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -119,8 +119,8 @@ static ssize_t transient_duration_store(struct device *dev,
 static ssize_t transient_state_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	int state;
 
 	state = (transient_data->state == LED_FULL) ? 1 : 0;
@@ -130,8 +130,8 @@ static ssize_t transient_state_show(struct device *dev,
 static ssize_t transient_state_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	ssize_t ret;
 
@@ -152,84 +152,46 @@ static DEVICE_ATTR(duration, 0644, transient_duration_show,
 		   transient_duration_store);
 static DEVICE_ATTR(state, 0644, transient_state_show, transient_state_store);
 
+static struct attribute *transient_trig_attrs[] = {
+	&dev_attr_activate.attr,
+	&dev_attr_duration.attr,
+	&dev_attr_state.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(transient_trig);
+
 static int transient_trig_activate(struct led_classdev *led_cdev)
 {
-	int rc;
 	struct transient_trig_data *tdata;
 
 	tdata = kzalloc(sizeof(struct transient_trig_data), GFP_KERNEL);
-	if (!tdata) {
-		dev_err(led_cdev->dev,
-			"unable to allocate transient trigger\n");
-		return 0;
-	}
-	led_cdev->trigger_data = tdata;
-	tdata->led_cdev = led_cdev;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_activate);
-	if (rc)
-		goto err_out;
+	if (!tdata)
+		return -ENOMEM;
 
-	rc = device_create_file(led_cdev->dev, &dev_attr_duration);
-	if (rc)
-		goto err_out_duration;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_state);
-	if (rc)
-		goto err_out_state;
+	led_set_trigger_data(led_cdev, tdata);
+	tdata->led_cdev = led_cdev;
 
 	timer_setup(&tdata->timer, transient_timer_function, 0);
-	led_cdev->activated = true;
-
-	return 0;
-
-err_out_state:
-	device_remove_file(led_cdev->dev, &dev_attr_duration);
-err_out_duration:
-	device_remove_file(led_cdev->dev, &dev_attr_activate);
-err_out:
-	dev_err(led_cdev->dev, "unable to register transient trigger\n");
-	led_cdev->trigger_data = NULL;
-	kfree(tdata);
 
 	return 0;
 }
 
 static void transient_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct transient_trig_data *transient_data = led_cdev->trigger_data;
+	struct transient_trig_data *transient_data = led_get_trigger_data(led_cdev);
 
-	if (led_cdev->activated) {
-		del_timer_sync(&transient_data->timer);
-		led_set_brightness_nosleep(led_cdev,
-					transient_data->restore_state);
-		device_remove_file(led_cdev->dev, &dev_attr_activate);
-		device_remove_file(led_cdev->dev, &dev_attr_duration);
-		device_remove_file(led_cdev->dev, &dev_attr_state);
-		led_cdev->trigger_data = NULL;
-		led_cdev->activated = false;
-		kfree(transient_data);
-	}
+	del_timer_sync(&transient_data->timer);
+	led_set_brightness_nosleep(led_cdev, transient_data->restore_state);
+	kfree(transient_data);
 }
 
 static struct led_trigger transient_trigger = {
 	.name     = "transient",
 	.activate = transient_trig_activate,
 	.deactivate = transient_trig_deactivate,
+	.groups = transient_trig_groups,
 };
-
-static int __init transient_trig_init(void)
-{
-	return led_trigger_register(&transient_trigger);
-}
-
-static void __exit transient_trig_exit(void)
-{
-	led_trigger_unregister(&transient_trigger);
-}
-
-module_init(transient_trig_init);
-module_exit(transient_trig_exit);
+module_led_trigger(transient_trigger);
 
 MODULE_AUTHOR("Shuah Khan <shuahkhan@gmail.com>");
 MODULE_DESCRIPTION("Transient LED trigger");
-- 
cgit v1.2.3


From 81d5533297fb672012bb298c1f7545f9c168ccb0 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:29 +0200
Subject: leds: oneshot trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The trigger core learned error handling for the activate callback and
can handle device attributes now. This allows simplifying the driver
considerably. Note that .deactivate() is only called when .activate()
succeeded, so the check for .activated can go away in .deactivate().

Also make use of module_led_trigger() and do some minor coding style
improvements.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-oneshot.c | 89 ++++++++++------------------------
 1 file changed, 26 insertions(+), 63 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-oneshot.c b/drivers/leds/trigger/ledtrig-oneshot.c
index 7bbf92bd7f80..95c9be4b6e7e 100644
--- a/drivers/leds/trigger/ledtrig-oneshot.c
+++ b/drivers/leds/trigger/ledtrig-oneshot.c
@@ -8,7 +8,6 @@
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
- *
  */
 
 #include <linux/module.h>
@@ -29,8 +28,8 @@ struct oneshot_trig_data {
 static ssize_t led_shot(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 
 	led_blink_set_oneshot(led_cdev,
 			&led_cdev->blink_delay_on, &led_cdev->blink_delay_off,
@@ -42,8 +41,7 @@ static ssize_t led_shot(struct device *dev,
 static ssize_t led_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", oneshot_data->invert);
 }
@@ -51,8 +49,8 @@ static ssize_t led_invert_show(struct device *dev,
 static ssize_t led_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
+	struct oneshot_trig_data *oneshot_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -73,7 +71,7 @@ static ssize_t led_invert_store(struct device *dev,
 static ssize_t led_delay_on_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_on);
 }
@@ -81,7 +79,7 @@ static ssize_t led_delay_on_show(struct device *dev,
 static ssize_t led_delay_on_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	int ret;
 
@@ -93,10 +91,11 @@ static ssize_t led_delay_on_store(struct device *dev,
 
 	return size;
 }
+
 static ssize_t led_delay_off_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 
 	return sprintf(buf, "%lu\n", led_cdev->blink_delay_off);
 }
@@ -104,7 +103,7 @@ static ssize_t led_delay_off_show(struct device *dev,
 static ssize_t led_delay_off_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
+	struct led_classdev *led_cdev = led_trigger_get_led(dev);
 	unsigned long state;
 	int ret;
 
@@ -122,61 +121,36 @@ static DEVICE_ATTR(delay_off, 0644, led_delay_off_show, led_delay_off_store);
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 static DEVICE_ATTR(shot, 0200, NULL, led_shot);
 
+static struct attribute *oneshot_trig_attrs[] = {
+	&dev_attr_delay_on.attr,
+	&dev_attr_delay_off.attr,
+	&dev_attr_invert.attr,
+	&dev_attr_shot.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(oneshot_trig);
+
 static int oneshot_trig_activate(struct led_classdev *led_cdev)
 {
 	struct oneshot_trig_data *oneshot_data;
-	int rc;
 
 	oneshot_data = kzalloc(sizeof(*oneshot_data), GFP_KERNEL);
 	if (!oneshot_data)
-		return 0;
-
-	led_cdev->trigger_data = oneshot_data;
-
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_on);
-	if (rc)
-		goto err_out_trig_data;
-	rc = device_create_file(led_cdev->dev, &dev_attr_delay_off);
-	if (rc)
-		goto err_out_delayon;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc)
-		goto err_out_delayoff;
-	rc = device_create_file(led_cdev->dev, &dev_attr_shot);
-	if (rc)
-		goto err_out_invert;
+		return -ENOMEM;
+
+	led_set_trigger_data(led_cdev, oneshot_data);
 
 	led_cdev->blink_delay_on = DEFAULT_DELAY;
 	led_cdev->blink_delay_off = DEFAULT_DELAY;
 
-	led_cdev->activated = true;
-
-	return 0;
-
-err_out_invert:
-	device_remove_file(led_cdev->dev, &dev_attr_invert);
-err_out_delayoff:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-err_out_delayon:
-	device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-err_out_trig_data:
-	kfree(led_cdev->trigger_data);
-
 	return 0;
 }
 
 static void oneshot_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct oneshot_trig_data *oneshot_data = led_cdev->trigger_data;
+	struct oneshot_trig_data *oneshot_data = led_get_trigger_data(led_cdev);
 
-	if (led_cdev->activated) {
-		device_remove_file(led_cdev->dev, &dev_attr_delay_on);
-		device_remove_file(led_cdev->dev, &dev_attr_delay_off);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		device_remove_file(led_cdev->dev, &dev_attr_shot);
-		kfree(oneshot_data);
-		led_cdev->activated = false;
-	}
+	kfree(oneshot_data);
 
 	/* Stop blinking */
 	led_set_brightness(led_cdev, LED_OFF);
@@ -186,20 +160,9 @@ static struct led_trigger oneshot_led_trigger = {
 	.name     = "oneshot",
 	.activate = oneshot_trig_activate,
 	.deactivate = oneshot_trig_deactivate,
+	.groups = oneshot_trig_groups,
 };
-
-static int __init oneshot_trig_init(void)
-{
-	return led_trigger_register(&oneshot_led_trigger);
-}
-
-static void __exit oneshot_trig_exit(void)
-{
-	led_trigger_unregister(&oneshot_led_trigger);
-}
-
-module_init(oneshot_trig_init);
-module_exit(oneshot_trig_exit);
+module_led_trigger(oneshot_led_trigger);
 
 MODULE_AUTHOR("Fabio Baltieri <fabio.baltieri@gmail.com>");
 MODULE_DESCRIPTION("One-shot LED trigger");
-- 
cgit v1.2.3


From 71c4af71e597f429d37c89f5db2e44c59c8ba88c Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:30 +0200
Subject: leds: heartbeat trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The trigger core learned error handling for the activate callback and
can handle device attributes now. This allows simplifying the driver
considerably. Note that .deactivate() is only called when .activate()
succeeded, so the check for .activated can go away in .deactivate().

Also make use of module_led_trigger() and the accessor function to get
and set trigger_data.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-heartbeat.c | 41 +++++++++++++++-----------------
 1 file changed, 19 insertions(+), 22 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-heartbeat.c b/drivers/leds/trigger/ledtrig-heartbeat.c
index 03a8dfce8fb9..7a2b12e19329 100644
--- a/drivers/leds/trigger/ledtrig-heartbeat.c
+++ b/drivers/leds/trigger/ledtrig-heartbeat.c
@@ -96,8 +96,8 @@ static void led_heartbeat_function(struct timer_list *t)
 static ssize_t led_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
+	struct heartbeat_trig_data *heartbeat_data =
+		led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", heartbeat_data->invert);
 }
@@ -105,8 +105,8 @@ static ssize_t led_invert_show(struct device *dev,
 static ssize_t led_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
+	struct heartbeat_trig_data *heartbeat_data =
+		led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -121,22 +121,22 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
+static struct attribute *heartbeat_trig_attrs[] = {
+	&dev_attr_invert.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(heartbeat_trig);
+
 static int heartbeat_trig_activate(struct led_classdev *led_cdev)
 {
 	struct heartbeat_trig_data *heartbeat_data;
-	int rc;
 
 	heartbeat_data = kzalloc(sizeof(*heartbeat_data), GFP_KERNEL);
 	if (!heartbeat_data)
-		return 0;
+		return -ENOMEM;
 
-	led_cdev->trigger_data = heartbeat_data;
+	led_set_trigger_data(led_cdev, heartbeat_data);
 	heartbeat_data->led_cdev = led_cdev;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc) {
-		kfree(led_cdev->trigger_data);
-		return 0;
-	}
 
 	timer_setup(&heartbeat_data->timer, led_heartbeat_function, 0);
 	heartbeat_data->phase = 0;
@@ -144,28 +144,25 @@ static int heartbeat_trig_activate(struct led_classdev *led_cdev)
 		led_cdev->blink_brightness = led_cdev->max_brightness;
 	led_heartbeat_function(&heartbeat_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
-	led_cdev->activated = true;
 
 	return 0;
 }
 
 static void heartbeat_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct heartbeat_trig_data *heartbeat_data = led_cdev->trigger_data;
-
-	if (led_cdev->activated) {
-		del_timer_sync(&heartbeat_data->timer);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		kfree(heartbeat_data);
-		clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
-		led_cdev->activated = false;
-	}
+	struct heartbeat_trig_data *heartbeat_data =
+		led_get_trigger_data(led_cdev);
+
+	del_timer_sync(&heartbeat_data->timer);
+	kfree(heartbeat_data);
+	clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
 }
 
 static struct led_trigger heartbeat_led_trigger = {
 	.name     = "heartbeat",
 	.activate = heartbeat_trig_activate,
 	.deactivate = heartbeat_trig_deactivate,
+	.groups = heartbeat_trig_groups,
 };
 
 static int heartbeat_reboot_notifier(struct notifier_block *nb,
-- 
cgit v1.2.3


From 5cccc555108b602f92101a939143925095ff9b1d Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:31 +0200
Subject: leds: default-on trigger: make use of module_led_trigger()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This removes some boilerplate from the driver.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-default-on.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-default-on.c b/drivers/leds/trigger/ledtrig-default-on.c
index 2996fe672198..7f6d9219711e 100644
--- a/drivers/leds/trigger/ledtrig-default-on.c
+++ b/drivers/leds/trigger/ledtrig-default-on.c
@@ -26,19 +26,7 @@ static struct led_trigger defon_led_trigger = {
 	.name     = "default-on",
 	.activate = defon_trig_activate,
 };
-
-static int __init defon_trig_init(void)
-{
-	return led_trigger_register(&defon_led_trigger);
-}
-
-static void __exit defon_trig_exit(void)
-{
-	led_trigger_unregister(&defon_led_trigger);
-}
-
-module_init(defon_trig_init);
-module_exit(defon_trig_exit);
+module_led_trigger(defon_led_trigger);
 
 MODULE_AUTHOR("Nick Forbes <nick.forbes@incepta.com>");
 MODULE_DESCRIPTION("Default-ON LED trigger");
-- 
cgit v1.2.3


From 13d698cbd99ce90f1d6b4fb0ff11ab90eb55f55e Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:32 +0200
Subject: leds: activity trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The trigger core learned error handling for the activate callback and
can handle device attributes now. This allows simplifying the driver
considerably. Note that .deactivate() is only called when .activate()
succeeded, so the check for .activated can go away in .deactivate().

Also make use of module_led_trigger() and the accessor function to get
and set trigger_data.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-activity.c | 38 ++++++++++++++-------------------
 1 file changed, 16 insertions(+), 22 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-activity.c b/drivers/leds/trigger/ledtrig-activity.c
index 2fc065fb1754..bcbf41c90c30 100644
--- a/drivers/leds/trigger/ledtrig-activity.c
+++ b/drivers/leds/trigger/ledtrig-activity.c
@@ -152,8 +152,7 @@ static void led_activity_function(struct timer_list *t)
 static ssize_t led_invert_show(struct device *dev,
                                struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct activity_data *activity_data = led_cdev->trigger_data;
+	struct activity_data *activity_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", activity_data->invert);
 }
@@ -162,8 +161,7 @@ static ssize_t led_invert_store(struct device *dev,
                                 struct device_attribute *attr,
                                 const char *buf, size_t size)
 {
-	struct led_classdev *led_cdev = dev_get_drvdata(dev);
-	struct activity_data *activity_data = led_cdev->trigger_data;
+	struct activity_data *activity_data = led_trigger_get_drvdata(dev);
 	unsigned long state;
 	int ret;
 
@@ -178,21 +176,21 @@ static ssize_t led_invert_store(struct device *dev,
 
 static DEVICE_ATTR(invert, 0644, led_invert_show, led_invert_store);
 
+static struct attribute *activity_led_attrs[] = {
+	&dev_attr_invert.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(activity_led);
+
 static int activity_activate(struct led_classdev *led_cdev)
 {
 	struct activity_data *activity_data;
-	int rc;
 
 	activity_data = kzalloc(sizeof(*activity_data), GFP_KERNEL);
 	if (!activity_data)
-		return 0;
+		return -ENOMEM;
 
-	led_cdev->trigger_data = activity_data;
-	rc = device_create_file(led_cdev->dev, &dev_attr_invert);
-	if (rc) {
-		kfree(led_cdev->trigger_data);
-		return 0;
-	}
+	led_set_trigger_data(led_cdev, activity_data);
 
 	activity_data->led_cdev = led_cdev;
 	timer_setup(&activity_data->timer, led_activity_function, 0);
@@ -200,28 +198,24 @@ static int activity_activate(struct led_classdev *led_cdev)
 		led_cdev->blink_brightness = led_cdev->max_brightness;
 	led_activity_function(&activity_data->timer);
 	set_bit(LED_BLINK_SW, &led_cdev->work_flags);
-	led_cdev->activated = true;
 
 	return 0;
 }
 
 static void activity_deactivate(struct led_classdev *led_cdev)
 {
-	struct activity_data *activity_data = led_cdev->trigger_data;
-
-	if (led_cdev->activated) {
-		del_timer_sync(&activity_data->timer);
-		device_remove_file(led_cdev->dev, &dev_attr_invert);
-		kfree(activity_data);
-		clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
-		led_cdev->activated = false;
-	}
+	struct activity_data *activity_data = led_get_trigger_data(led_cdev);
+
+	del_timer_sync(&activity_data->timer);
+	kfree(activity_data);
+	clear_bit(LED_BLINK_SW, &led_cdev->work_flags);
 }
 
 static struct led_trigger activity_led_trigger = {
 	.name       = "activity",
 	.activate   = activity_activate,
 	.deactivate = activity_deactivate,
+	.groups     = activity_led_groups,
 };
 
 static int activity_reboot_notifier(struct notifier_block *nb,
-- 
cgit v1.2.3


From e4786ba0db7b1163403c29c429f5ef61906a84c0 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:33 +0200
Subject: leds: backlight trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the new module_led_trigger() helper. Also use
attribute support from the trigger core. Drop error message on
allocation failure as kzalloc() already screams loudly when failing. Use
wrappers to get and set trigger data.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-backlight.c | 62 ++++++++++----------------------
 1 file changed, 19 insertions(+), 43 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-backlight.c b/drivers/leds/trigger/ledtrig-backlight.c
index 84512960d630..c2b57beef718 100644
--- a/drivers/leds/trigger/ledtrig-backlight.c
+++ b/drivers/leds/trigger/ledtrig-backlight.c
@@ -64,8 +64,7 @@ static int fb_notifier_callback(struct notifier_block *p,
 static ssize_t bl_trig_invert_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct bl_trig_notifier *n = led->trigger_data;
+	struct bl_trig_notifier *n = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", n->invert);
 }
@@ -73,8 +72,8 @@ static ssize_t bl_trig_invert_show(struct device *dev,
 static ssize_t bl_trig_invert_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t num)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct bl_trig_notifier *n = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct bl_trig_notifier *n = led_trigger_get_drvdata(dev);
 	unsigned long invert;
 	int ret;
 
@@ -97,6 +96,12 @@ static ssize_t bl_trig_invert_store(struct device *dev,
 }
 static DEVICE_ATTR(inverted, 0644, bl_trig_invert_show, bl_trig_invert_store);
 
+static struct attribute *bl_trig_attrs[] = {
+	&dev_attr_inverted.attr,
+	NULL,
+};
+ATTRIBUTE_GROUPS(bl_trig);
+
 static int bl_trig_activate(struct led_classdev *led)
 {
 	int ret;
@@ -104,15 +109,9 @@ static int bl_trig_activate(struct led_classdev *led)
 	struct bl_trig_notifier *n;
 
 	n = kzalloc(sizeof(struct bl_trig_notifier), GFP_KERNEL);
-	led->trigger_data = n;
-	if (!n) {
-		dev_err(led->dev, "unable to allocate backlight trigger\n");
-		return 0;
-	}
-
-	ret = device_create_file(led->dev, &dev_attr_inverted);
-	if (ret)
-		goto err_invert;
+	if (!n)
+		return -ENOMEM;
+	led_set_trigger_data(led, n);
 
 	n->led = led;
 	n->brightness = led->brightness;
@@ -122,48 +121,25 @@ static int bl_trig_activate(struct led_classdev *led)
 	ret = fb_register_client(&n->notifier);
 	if (ret)
 		dev_err(led->dev, "unable to register backlight trigger\n");
-	led->activated = true;
-
-	return 0;
-
-err_invert:
-	led->trigger_data = NULL;
-	kfree(n);
 
 	return 0;
 }
 
 static void bl_trig_deactivate(struct led_classdev *led)
 {
-	struct bl_trig_notifier *n =
-		(struct bl_trig_notifier *) led->trigger_data;
-
-	if (led->activated) {
-		device_remove_file(led->dev, &dev_attr_inverted);
-		fb_unregister_client(&n->notifier);
-		kfree(n);
-		led->activated = false;
-	}
+	struct bl_trig_notifier *n = led_get_trigger_data(led);
+
+	fb_unregister_client(&n->notifier);
+	kfree(n);
 }
 
 static struct led_trigger bl_led_trigger = {
 	.name		= "backlight",
 	.activate	= bl_trig_activate,
-	.deactivate	= bl_trig_deactivate
+	.deactivate	= bl_trig_deactivate,
+	.groups		= bl_trig_groups,
 };
-
-static int __init bl_trig_init(void)
-{
-	return led_trigger_register(&bl_led_trigger);
-}
-
-static void __exit bl_trig_exit(void)
-{
-	led_trigger_unregister(&bl_led_trigger);
-}
-
-module_init(bl_trig_init);
-module_exit(bl_trig_exit);
+module_led_trigger(bl_led_trigger);
 
 MODULE_AUTHOR("Rodolfo Giometti <giometti@linux.it>");
 MODULE_DESCRIPTION("Backlight emulation LED trigger");
-- 
cgit v1.2.3


From 9bfd7d9e5d63532da2d2d55a6bec5bb377761d37 Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:34 +0200
Subject: leds: gpio trigger: simplifications from core changes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The trigger core learned error handling for the activate callback and
to handle device attributes. Also make use of the module_led_trigger()
helper to simplify trigger registration.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/trigger/ledtrig-gpio.c | 87 +++++++++++--------------------------
 1 file changed, 25 insertions(+), 62 deletions(-)

diff --git a/drivers/leds/trigger/ledtrig-gpio.c b/drivers/leds/trigger/ledtrig-gpio.c
index f5358c40d03f..ed0db8ed825f 100644
--- a/drivers/leds/trigger/ledtrig-gpio.c
+++ b/drivers/leds/trigger/ledtrig-gpio.c
@@ -28,7 +28,7 @@ struct gpio_trig_data {
 static irqreturn_t gpio_trig_irq(int irq, void *_led)
 {
 	struct led_classdev *led = _led;
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_get_trigger_data(led);
 	int tmp;
 
 	tmp = gpio_get_value_cansleep(gpio_data->gpio);
@@ -51,8 +51,7 @@ static irqreturn_t gpio_trig_irq(int irq, void *_led)
 static ssize_t gpio_trig_brightness_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->desired_brightness);
 }
@@ -60,8 +59,7 @@ static ssize_t gpio_trig_brightness_show(struct device *dev,
 static ssize_t gpio_trig_brightness_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned desired_brightness;
 	int ret;
 
@@ -81,8 +79,7 @@ static DEVICE_ATTR(desired_brightness, 0644, gpio_trig_brightness_show,
 static ssize_t gpio_trig_inverted_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->inverted);
 }
@@ -90,8 +87,8 @@ static ssize_t gpio_trig_inverted_show(struct device *dev,
 static ssize_t gpio_trig_inverted_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned long inverted;
 	int ret;
 
@@ -115,8 +112,7 @@ static DEVICE_ATTR(inverted, 0644, gpio_trig_inverted_show,
 static ssize_t gpio_trig_gpio_show(struct device *dev,
 		struct device_attribute *attr, char *buf)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 
 	return sprintf(buf, "%u\n", gpio_data->gpio);
 }
@@ -124,8 +120,8 @@ static ssize_t gpio_trig_gpio_show(struct device *dev,
 static ssize_t gpio_trig_gpio_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t n)
 {
-	struct led_classdev *led = dev_get_drvdata(dev);
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct led_classdev *led = led_trigger_get_led(dev);
+	struct gpio_trig_data *gpio_data = led_trigger_get_drvdata(dev);
 	unsigned gpio;
 	int ret;
 
@@ -162,77 +158,44 @@ static ssize_t gpio_trig_gpio_store(struct device *dev,
 }
 static DEVICE_ATTR(gpio, 0644, gpio_trig_gpio_show, gpio_trig_gpio_store);
 
+static struct attribute *gpio_trig_attrs[] = {
+	&dev_attr_desired_brightness.attr,
+	&dev_attr_inverted.attr,
+	&dev_attr_gpio.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(gpio_trig);
+
 static int gpio_trig_activate(struct led_classdev *led)
 {
 	struct gpio_trig_data *gpio_data;
-	int ret;
 
 	gpio_data = kzalloc(sizeof(*gpio_data), GFP_KERNEL);
 	if (!gpio_data)
-		return 0;
-
-	ret = device_create_file(led->dev, &dev_attr_gpio);
-	if (ret)
-		goto err_gpio;
-
-	ret = device_create_file(led->dev, &dev_attr_inverted);
-	if (ret)
-		goto err_inverted;
-
-	ret = device_create_file(led->dev, &dev_attr_desired_brightness);
-	if (ret)
-		goto err_brightness;
+		return -ENOMEM;
 
 	gpio_data->led = led;
-	led->trigger_data = gpio_data;
-	led->activated = true;
-
-	return 0;
-
-err_brightness:
-	device_remove_file(led->dev, &dev_attr_inverted);
-
-err_inverted:
-	device_remove_file(led->dev, &dev_attr_gpio);
-
-err_gpio:
-	kfree(gpio_data);
+	led_set_trigger_data(led, gpio_data);
 
 	return 0;
 }
 
 static void gpio_trig_deactivate(struct led_classdev *led)
 {
-	struct gpio_trig_data *gpio_data = led->trigger_data;
+	struct gpio_trig_data *gpio_data = led_get_trigger_data(led);
 
-	if (led->activated) {
-		device_remove_file(led->dev, &dev_attr_gpio);
-		device_remove_file(led->dev, &dev_attr_inverted);
-		device_remove_file(led->dev, &dev_attr_desired_brightness);
-		if (gpio_data->gpio != 0)
-			free_irq(gpio_to_irq(gpio_data->gpio), led);
-		kfree(gpio_data);
-		led->activated = false;
-	}
+	if (gpio_data->gpio != 0)
+		free_irq(gpio_to_irq(gpio_data->gpio), led);
+	kfree(gpio_data);
 }
 
 static struct led_trigger gpio_led_trigger = {
 	.name		= "gpio",
 	.activate	= gpio_trig_activate,
 	.deactivate	= gpio_trig_deactivate,
+	.groups		= gpio_trig_groups,
 };
-
-static int __init gpio_trig_init(void)
-{
-	return led_trigger_register(&gpio_led_trigger);
-}
-module_init(gpio_trig_init);
-
-static void __exit gpio_trig_exit(void)
-{
-	led_trigger_unregister(&gpio_led_trigger);
-}
-module_exit(gpio_trig_exit);
+module_led_trigger(gpio_led_trigger);
 
 MODULE_AUTHOR("Felipe Balbi <me@felipebalbi.com>");
 MODULE_DESCRIPTION("GPIO LED trigger");
-- 
cgit v1.2.3


From 6f7b0bad88397ad5d7901ce63696163ac8b481ce Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Date: Mon, 2 Jul 2018 22:05:35 +0200
Subject: usb: simplify usbport trigger
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The led trigger core learned a few things that allow to simplify the
trigger drivers.  Make use of automated trigger attributes and error
checking of the activate callback. Also use the wrappers to set and get
trigger_data.

Acked-by: Pavel Machek <pavel@ucw.cz>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Uwe Kleine-König <u.kleine-koenig@pengutronix.de>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/usb/core/ledtrig-usbport.c | 31 +++++++++++--------------------
 1 file changed, 11 insertions(+), 20 deletions(-)

diff --git a/drivers/usb/core/ledtrig-usbport.c b/drivers/usb/core/ledtrig-usbport.c
index aa1d51458da7..dc7f7fd71684 100644
--- a/drivers/usb/core/ledtrig-usbport.c
+++ b/drivers/usb/core/ledtrig-usbport.c
@@ -113,11 +113,17 @@ static ssize_t usbport_trig_port_store(struct device *dev,
 static struct attribute *ports_attrs[] = {
 	NULL,
 };
+
 static const struct attribute_group ports_group = {
 	.name = "ports",
 	.attrs = ports_attrs,
 };
 
+static const struct attribute_group *ports_groups[] = {
+	&ports_group,
+	NULL
+};
+
 /***************************************
  * Adding & removing ports
  ***************************************/
@@ -301,59 +307,44 @@ static int usbport_trig_notify(struct notifier_block *nb, unsigned long action,
 static int usbport_trig_activate(struct led_classdev *led_cdev)
 {
 	struct usbport_trig_data *usbport_data;
-	int err;
 
 	usbport_data = kzalloc(sizeof(*usbport_data), GFP_KERNEL);
 	if (!usbport_data)
-		return 0;
+		return -ENOMEM;
 	usbport_data->led_cdev = led_cdev;
 
 	/* List of ports */
 	INIT_LIST_HEAD(&usbport_data->ports);
-	err = sysfs_create_group(&led_cdev->dev->kobj, &ports_group);
-	if (err)
-		goto err_free;
 	usb_for_each_dev(usbport_data, usbport_trig_add_usb_dev_ports);
 	usbport_trig_update_count(usbport_data);
 
 	/* Notifications */
-	usbport_data->nb.notifier_call = usbport_trig_notify,
-	led_cdev->trigger_data = usbport_data;
+	usbport_data->nb.notifier_call = usbport_trig_notify;
+	led_set_trigger_data(led_cdev, usbport_data);
 	usb_register_notify(&usbport_data->nb);
 
-	led_cdev->activated = true;
-	return 0;
-
-err_free:
-	kfree(usbport_data);
 	return 0;
 }
 
 static void usbport_trig_deactivate(struct led_classdev *led_cdev)
 {
-	struct usbport_trig_data *usbport_data = led_cdev->trigger_data;
+	struct usbport_trig_data *usbport_data = led_get_trigger_data(led_cdev);
 	struct usbport_trig_port *port, *tmp;
 
-	if (!led_cdev->activated)
-		return;
-
 	list_for_each_entry_safe(port, tmp, &usbport_data->ports, list) {
 		usbport_trig_remove_port(usbport_data, port);
 	}
 
 	usb_unregister_notify(&usbport_data->nb);
 
-	sysfs_remove_group(&led_cdev->dev->kobj, &ports_group);
-
 	kfree(usbport_data);
-
-	led_cdev->activated = false;
 }
 
 static struct led_trigger usbport_led_trigger = {
 	.name     = "usbport",
 	.activate = usbport_trig_activate,
 	.deactivate = usbport_trig_deactivate,
+	.groups = ports_groups,
 };
 
 static int __init usbport_trig_init(void)
-- 
cgit v1.2.3


From a315f232f44e685397639649fe559325424d32d4 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Tue, 19 Jun 2018 10:45:03 +0200
Subject: drm/amdgpu: band aid validating VM PTs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Always validating the VM PTs takes to much time. Only always validate
the per VM BOs for now.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 422d1a434db4..590db78b8c72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1082,7 +1082,7 @@ restart:
 					   struct amdgpu_vm_bo_base,
 					   vm_status);
 		bo_base->moved = false;
-		list_move(&bo_base->vm_status, &vm->idle);
+		list_del_init(&bo_base->vm_status);
 
 		bo = bo_base->bo->parent;
 		if (!bo)
-- 
cgit v1.2.3


From b374d82dca4721c534eb940b599dd4d45ba3a18f Mon Sep 17 00:00:00 2001
From: Tom St Denis <tom.stdenis@amd.com>
Date: Wed, 20 Jun 2018 07:55:39 -0400
Subject: drm/amd/amdgpu: Add a GPU_LOAD entry to sysfs (v3)

This adds what should be a stable interface to read GPU
load from userspace.

(v2): Fix comments and name of file per recommendations.
(v3): Add chapter to amdgpu.rst as well.

Signed-off-by: Tom St Denis <tom.stdenis@amd.com>
Acked-by: Slava Abramov <slava.abramov@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst           |  5 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 40 ++++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index e52d0ce186fe..765c2a32938f 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -115,3 +115,8 @@ pp_power_profile_mode
 .. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
    :doc: pp_power_profile_mode
 
+busy_percent
+~~~~~~~~~~~~
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+   :doc: busy_percent
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 113edffb5960..fdb399821915 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -918,6 +918,36 @@ fail:
 	return -EINVAL;
 }
 
+/**
+ * DOC: busy_percent
+ *
+ * The amdgpu driver provides a sysfs API for reading how busy the GPU
+ * is as a percentage.  The file gpu_busy_percent is used for this.
+ * The SMU firmware computes a percentage of load based on the
+ * aggregate activity level in the IP cores.
+ */
+static ssize_t amdgpu_get_busy_percent(struct device *dev,
+		struct device_attribute *attr,
+		char *buf)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int r, value, size = sizeof(value);
+
+	/* sanity check PP is enabled */
+	if (!(adev->powerplay.pp_funcs &&
+	      adev->powerplay.pp_funcs->read_sensor))
+		return -EINVAL;
+
+	/* read the IP busy sensor */
+	r = amdgpu_dpm_read_sensor(adev, AMDGPU_PP_SENSOR_GPU_LOAD,
+				   (void *)&value, &size);
+	if (r)
+		return r;
+
+	return snprintf(buf, PAGE_SIZE, "%d\n", value);
+}
+
 static DEVICE_ATTR(power_dpm_state, S_IRUGO | S_IWUSR, amdgpu_get_dpm_state, amdgpu_set_dpm_state);
 static DEVICE_ATTR(power_dpm_force_performance_level, S_IRUGO | S_IWUSR,
 		   amdgpu_get_dpm_forced_performance_level,
@@ -951,6 +981,8 @@ static DEVICE_ATTR(pp_power_profile_mode, S_IRUGO | S_IWUSR,
 static DEVICE_ATTR(pp_od_clk_voltage, S_IRUGO | S_IWUSR,
 		amdgpu_get_pp_od_clk_voltage,
 		amdgpu_set_pp_od_clk_voltage);
+static DEVICE_ATTR(gpu_busy_percent, S_IRUGO,
+		amdgpu_get_busy_percent, NULL);
 
 static ssize_t amdgpu_hwmon_show_temp(struct device *dev,
 				      struct device_attribute *attr,
@@ -1854,6 +1886,13 @@ int amdgpu_pm_sysfs_init(struct amdgpu_device *adev)
 				"pp_od_clk_voltage\n");
 		return ret;
 	}
+	ret = device_create_file(adev->dev,
+			&dev_attr_gpu_busy_percent);
+	if (ret) {
+		DRM_ERROR("failed to create device file	"
+				"gpu_busy_level\n");
+		return ret;
+	}
 	ret = amdgpu_debugfs_pm_init(adev);
 	if (ret) {
 		DRM_ERROR("Failed to register debugfs file for dpm!\n");
@@ -1889,6 +1928,7 @@ void amdgpu_pm_sysfs_fini(struct amdgpu_device *adev)
 			&dev_attr_pp_power_profile_mode);
 	device_remove_file(adev->dev,
 			&dev_attr_pp_od_clk_voltage);
+	device_remove_file(adev->dev, &dev_attr_gpu_busy_percent);
 }
 
 void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
-- 
cgit v1.2.3


From d9e222b460b195a47b30fd9057fbb131fcbd7bac Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Mon, 18 Jun 2018 11:15:10 -0400
Subject: drm/amdgpu: Polish SQ IH.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Switch to using reg fields defines istead of magic values.
Add SH_ID and PRIV fields reading for instr. and err cases.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 36 +++++++++++++++++++----------------
 1 file changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 807ee0dd623c..1d99a4205958 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -6961,10 +6961,11 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 {
 	u8 enc, se_id;
 	char type[20];
+	unsigned ih_data = entry->src_data[0];
 
-	/* Parse all fields according to SQ_INTERRUPT* registers */
-	enc = (entry->src_data[0] >> 26) & 0x3;
-	se_id = (entry->src_data[0] >> 24) & 0x3;
+
+	enc = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, ENCODING);
+	se_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, SE_ID);
 
 	switch (enc) {
 		case 0:
@@ -6974,14 +6975,14 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 					"reg_timestamp %d, thread_trace_buff_full %d,"
 					"wlt %d, thread_trace %d.\n",
 					se_id,
-					(entry->src_data[0] >> 7) & 0x1,
-					(entry->src_data[0] >> 6) & 0x1,
-					(entry->src_data[0] >> 5) & 0x1,
-					(entry->src_data[0] >> 4) & 0x1,
-					(entry->src_data[0] >> 3) & 0x1,
-					(entry->src_data[0] >> 2) & 0x1,
-					(entry->src_data[0] >> 1) & 0x1,
-					entry->src_data[0] & 0x1
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, IMMED_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, HOST_REG_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, HOST_CMD_OVERFLOW),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, CMD_TIMESTAMP),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, REG_TIMESTAMP),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, THREAD_TRACE_BUF_FULL),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, WLT),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_AUTO, THREAD_TRACE)
 					);
 			break;
 		case 1:
@@ -6994,12 +6995,15 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 
 			DRM_INFO(
 				"SQ %s detected: "
-					"se_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d\n",
+					"se_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d\n"
+					"trap %s, sh_id %d. ",
 					type, se_id,
-					(entry->src_data[0] >> 20) & 0xf,
-					(entry->src_data[0] >> 18) & 0x3,
-					(entry->src_data[0] >> 14) & 0xf,
-					(entry->src_data[0] >> 10) & 0xf
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, CU_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SIMD_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, WAVE_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, VM_ID),
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, PRIV) ? "true" : "false",
+					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SH_ID)
 					);
 			break;
 		default:
-- 
cgit v1.2.3


From 9bdc2092b488bc81aa5409b4d6fc931c5bea1094 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Tue, 19 Jun 2018 10:27:53 -0400
Subject: drm/amdgpu: Add parsing SQ_EDC_INFO to SQ IH v3.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Access to SQ_EDC_INFO requires selecting register instance and
hence mutex lock when accessing GRBM_GFX_INDEX for which a work
is schedueled from IH. But SQ interrupt can be raised on many instances
at once which means queuing work will usually succeed for the first one
but fail for the rest since the work takes time to process. To avoid
losing info about other interrupt instances call the parsing function
directly from high IRQ when current work hasn't finished and avoid
accessing SQ_EDC_INFO in that case.

v2:
Simplify high IRQ and BH handlers synchronization using work_pending.
Remove {READ,WRITE}_ONCE notations since smp_{r,w}mb are implicit
compiler barriers.

v3:
Remove exlicit memory barriers as scedule_work has r/w barriers.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h   |  7 +++
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c | 82 +++++++++++++++++++++++++++++------
 2 files changed, 76 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 71b9b861f60e..fb17838114c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -930,6 +930,11 @@ struct amdgpu_ngg {
 	bool			init;
 };
 
+struct sq_work {
+	struct work_struct	work;
+	unsigned ih_data;
+};
+
 struct amdgpu_gfx {
 	struct mutex			gpu_clock_mutex;
 	struct amdgpu_gfx_config	config;
@@ -970,6 +975,8 @@ struct amdgpu_gfx {
 	struct amdgpu_irq_src		priv_inst_irq;
 	struct amdgpu_irq_src		cp_ecc_error_irq;
 	struct amdgpu_irq_src		sq_irq;
+	struct sq_work			sq_work;
+
 	/* gfx status */
 	uint32_t			gfx_current_status;
 	/* ce ram size*/
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 1d99a4205958..4201f3dfaece 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -704,6 +704,17 @@ static const u32 stoney_mgcg_cgcg_init[] =
 	mmCGTS_SM_CTRL_REG, 0xffffffff, 0x96940200,
 };
 
+
+static const char * const sq_edc_source_names[] = {
+	"SQ_EDC_INFO_SOURCE_INVALID: No EDC error has occurred",
+	"SQ_EDC_INFO_SOURCE_INST: EDC source is Instruction Fetch",
+	"SQ_EDC_INFO_SOURCE_SGPR: EDC source is SGPR or SQC data return",
+	"SQ_EDC_INFO_SOURCE_VGPR: EDC source is VGPR",
+	"SQ_EDC_INFO_SOURCE_LDS: EDC source is LDS",
+	"SQ_EDC_INFO_SOURCE_GDS: EDC source is GDS",
+	"SQ_EDC_INFO_SOURCE_TA: EDC source is TA",
+};
+
 static void gfx_v8_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v8_0_set_gds_init(struct amdgpu_device *adev);
@@ -2006,6 +2017,8 @@ static int gfx_v8_0_compute_ring_init(struct amdgpu_device *adev, int ring_id,
 	return 0;
 }
 
+static void gfx_v8_0_sq_irq_work_func(struct work_struct *work);
+
 static int gfx_v8_0_sw_init(void *handle)
 {
 	int i, j, k, r, ring_id;
@@ -2069,6 +2082,8 @@ static int gfx_v8_0_sw_init(void *handle)
 		return r;
 	}
 
+	INIT_WORK(&adev->gfx.sq_work.work, gfx_v8_0_sq_irq_work_func);
+
 	adev->gfx.gfx_current_status = AMDGPU_GFX_NORMAL_MODE;
 
 	gfx_v8_0_scratch_init(adev);
@@ -6955,14 +6970,11 @@ static int gfx_v8_0_cp_ecc_error_irq(struct amdgpu_device *adev,
 	return 0;
 }
 
-static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
-			   struct amdgpu_irq_src *source,
-			   struct amdgpu_iv_entry *entry)
+static void gfx_v8_0_parse_sq_irq(struct amdgpu_device *adev, unsigned ih_data)
 {
-	u8 enc, se_id;
+	u32 enc, se_id, sh_id, cu_id;
 	char type[20];
-	unsigned ih_data = entry->src_data[0];
-
+	int sq_edc_source = -1;
 
 	enc = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, ENCODING);
 	se_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_CMN, SE_ID);
@@ -6988,6 +7000,24 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 		case 1:
 		case 2:
 
+			cu_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, CU_ID);
+			sh_id = REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SH_ID);
+
+			/*
+			 * This function can be called either directly from ISR
+			 * or from BH in which case we can access SQ_EDC_INFO
+			 * instance
+			 */
+			if (in_task()) {
+				mutex_lock(&adev->grbm_idx_mutex);
+				gfx_v8_0_select_se_sh(adev, se_id, sh_id, cu_id);
+
+				sq_edc_source = REG_GET_FIELD(RREG32(mmSQ_EDC_INFO), SQ_EDC_INFO, SOURCE);
+
+				gfx_v8_0_select_se_sh(adev, 0xffffffff, 0xffffffff, 0xffffffff);
+				mutex_unlock(&adev->grbm_idx_mutex);
+			}
+
 			if (enc == 1)
 				sprintf(type, "instruction intr");
 			else
@@ -6995,20 +7025,46 @@ static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
 
 			DRM_INFO(
 				"SQ %s detected: "
-					"se_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d\n"
-					"trap %s, sh_id %d. ",
-					type, se_id,
-					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, CU_ID),
+					"se_id %d, sh_id %d, cu_id %d, simd_id %d, wave_id %d, vm_id %d "
+					"trap %s, sq_ed_info.source %s.\n",
+					type, se_id, sh_id, cu_id,
 					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SIMD_ID),
 					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, WAVE_ID),
 					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, VM_ID),
 					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, PRIV) ? "true" : "false",
-					REG_GET_FIELD(ih_data, SQ_INTERRUPT_WORD_WAVE, SH_ID)
-					);
+					(sq_edc_source != -1) ? sq_edc_source_names[sq_edc_source] : "unavailable"
+				);
 			break;
 		default:
 			DRM_ERROR("SQ invalid encoding type\n.");
-			return -EINVAL;
+	}
+}
+
+static void gfx_v8_0_sq_irq_work_func(struct work_struct *work)
+{
+
+	struct amdgpu_device *adev = container_of(work, struct amdgpu_device, gfx.sq_work.work);
+	struct sq_work *sq_work = container_of(work, struct sq_work, work);
+
+	gfx_v8_0_parse_sq_irq(adev, sq_work->ih_data);
+}
+
+static int gfx_v8_0_sq_irq(struct amdgpu_device *adev,
+			   struct amdgpu_irq_src *source,
+			   struct amdgpu_iv_entry *entry)
+{
+	unsigned ih_data = entry->src_data[0];
+
+	/*
+	 * Try to submit work so SQ_EDC_INFO can be accessed from
+	 * BH. If previous work submission hasn't finished yet
+	 * just print whatever info is possible directly from the ISR.
+	 */
+	if (work_pending(&adev->gfx.sq_work.work)) {
+		gfx_v8_0_parse_sq_irq(adev, ih_data);
+	} else {
+		adev->gfx.sq_work.ih_data = ih_data;
+		schedule_work(&adev->gfx.sq_work.work);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From a25ca1625dd4ecc89c20bb9082b325490f3f78f2 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 22 Jun 2018 15:00:26 -0500
Subject: Revert "drm/amdgpu: avoid sleep while executing atombios table (V2)"

This reverts commit 8f4805a265fd710a2827b2c0e10c08ef2b526870.

This change was mistakenly committed and should have been dropped
with the rest of the series.

Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/atom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c
index b18c31a701e2..e9934de1b9cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/atom.c
+++ b/drivers/gpu/drm/amd/amdgpu/atom.c
@@ -1221,7 +1221,7 @@ static int amdgpu_atom_execute_table_locked(struct atom_context *ctx, int index,
 	ectx.abort = false;
 	ectx.last_jump = 0;
 	if (ws)
-		ectx.ws = kcalloc(4, ws, GFP_ATOMIC);
+		ectx.ws = kcalloc(4, ws, GFP_KERNEL);
 	else
 		ectx.ws = NULL;
 
-- 
cgit v1.2.3


From 765b26836430e9d9ebef95fced42dd167b4ccad6 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 23 May 2018 13:16:50 -0400
Subject: drm/amd/display: replace clocks_value struct with dc_clocks

This will avoid structs with duplicate information. Also
removes pixel clock voltage request. This has no effect since
pixel clock does not affect dcn voltage and this function only
matters for dcn.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c   | 34 ++++++++--------
 drivers/gpu/drm/amd/display/dc/core/dc_link.c      |  8 ++--
 drivers/gpu/drm/amd/display/dc/dc.h                |  5 +++
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c    | 46 ++++++++--------------
 .../amd/display/dc/dce110/dce110_hw_sequencer.c    | 18 +--------
 drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h     |  2 +-
 .../gpu/drm/amd/display/dc/inc/hw/display_clock.h  | 22 ++---------
 7 files changed, 49 insertions(+), 86 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 49a4ea45466d..d8a31650e856 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1145,10 +1145,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 
 	switch (clocks_type) {
 	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		if (clocks_in_khz > dc->dcn_soc->max_dispclk_vmax0p9*1000) {
+		/*if (clocks_in_khz > dc->dcn_soc->max_dispclk_vmax0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
-			BREAK_TO_DEBUGGER();
-		} else if (clocks_in_khz > dc->dcn_soc->max_dispclk_vnom0p8*1000) {
+			//BREAK_TO_DEBUGGER();
+		} else*/ if (clocks_in_khz > dc->dcn_soc->max_dispclk_vnom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->max_dispclk_vmid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
@@ -1158,10 +1158,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 			vdd_level = dcn_bw_v_min0p65;
 		break;
 	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-		if (clocks_in_khz > dc->dcn_soc->phyclkv_max0p9*1000) {
+		/*if (clocks_in_khz > dc->dcn_soc->phyclkv_max0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
 			BREAK_TO_DEBUGGER();
-		} else if (clocks_in_khz > dc->dcn_soc->phyclkv_nom0p8*1000) {
+		} else*/ if (clocks_in_khz > dc->dcn_soc->phyclkv_nom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->phyclkv_mid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
@@ -1172,10 +1172,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 		break;
 
 	case DM_PP_CLOCK_TYPE_DPPCLK:
-		if (clocks_in_khz > dc->dcn_soc->max_dppclk_vmax0p9*1000) {
+		/*if (clocks_in_khz > dc->dcn_soc->max_dppclk_vmax0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
 			BREAK_TO_DEBUGGER();
-		} else if (clocks_in_khz > dc->dcn_soc->max_dppclk_vnom0p8*1000) {
+		} else*/ if (clocks_in_khz > dc->dcn_soc->max_dppclk_vnom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->max_dppclk_vmid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
@@ -1189,10 +1189,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 		{
 			unsigned factor = (ddr4_dram_factor_single_Channel * dc->dcn_soc->number_of_channels);
 
-			if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9*1000000/factor) {
+			/*if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9*1000000/factor) {
 				vdd_level = dcn_bw_v_max0p91;
 				BREAK_TO_DEBUGGER();
-			} else if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8*1000000/factor) {
+			} else */if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8*1000000/factor) {
 				vdd_level = dcn_bw_v_max0p9;
 			} else if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72*1000000/factor) {
 				vdd_level = dcn_bw_v_nom0p8;
@@ -1204,10 +1204,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 		break;
 
 	case DM_PP_CLOCK_TYPE_DCFCLK:
-		if (clocks_in_khz > dc->dcn_soc->dcfclkv_max0p9*1000) {
+		/*if (clocks_in_khz > dc->dcn_soc->dcfclkv_max0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
 			BREAK_TO_DEBUGGER();
-		} else if (clocks_in_khz > dc->dcn_soc->dcfclkv_nom0p8*1000) {
+		} else */if (clocks_in_khz > dc->dcn_soc->dcfclkv_nom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->dcfclkv_mid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
@@ -1225,27 +1225,27 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 
 unsigned int dcn_find_dcfclk_suits_all(
 	const struct dc *dc,
-	struct clocks_value *clocks)
+	struct dc_clocks *clocks)
 {
 	unsigned vdd_level, vdd_level_temp;
 	unsigned dcf_clk;
 
 	/*find a common supported voltage level*/
 	vdd_level = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DISPLAY_CLK, clocks->dispclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DISPLAY_CLK, clocks->dispclk_khz);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DISPLAYPHYCLK, clocks->phyclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DISPLAYPHYCLK, clocks->phyclk_khz);
 
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DPPCLK, clocks->dppclk_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DPPCLK, clocks->dppclk_khz);
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_MEMORY_CLK, clocks->dcfclock_in_khz);
+		dc, DM_PP_CLOCK_TYPE_MEMORY_CLK, clocks->fclk_khz);
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
 	vdd_level_temp = dcn_find_normalized_clock_vdd_Level(
-		dc, DM_PP_CLOCK_TYPE_DCFCLK, clocks->dcfclock_in_khz);
+		dc, DM_PP_CLOCK_TYPE_DCFCLK, clocks->dcfclk_khz);
 
 	/*find that level conresponding dcfclk*/
 	vdd_level = dcn_bw_max(vdd_level, vdd_level_temp);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 08b7ee526f0f..6155a5c7bd36 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1290,15 +1290,13 @@ static enum dc_status enable_link_dp(
 					state->dis_clk, DM_PP_CLOCKS_STATE_NOMINAL);
 		} else {
 			uint32_t dp_phyclk_in_khz;
-			const struct clocks_value clocks_value =
-					state->dis_clk->cur_clocks_value;
+			const struct dc_clocks clocks_value =
+					state->dis_clk->clks;
 
 			/* 27mhz = 27000000hz= 27000khz */
 			dp_phyclk_in_khz = link_settings.link_rate * 27000;
 
-			if (((clocks_value.max_non_dp_phyclk_in_khz != 0) &&
-				(dp_phyclk_in_khz > clocks_value.max_non_dp_phyclk_in_khz)) ||
-				(dp_phyclk_in_khz > clocks_value.max_dp_phyclk_in_khz)) {
+			if (dp_phyclk_in_khz > clocks_value.phyclk_khz) {
 				state->dis_clk->funcs->apply_clock_voltage_request(
 						state->dis_clk,
 						DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 7ebce7669eea..8ba90a75d128 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -186,6 +186,10 @@ enum wm_report_mode {
 	WM_REPORT_OVERRIDE = 1,
 };
 
+/*
+ * For any clocks that may differ per pipe
+ * only the max is stored in this structure
+ */
 struct dc_clocks {
 	int dispclk_khz;
 	int max_supported_dppclk_khz;
@@ -194,6 +198,7 @@ struct dc_clocks {
 	int socclk_khz;
 	int dcfclk_deep_sleep_khz;
 	int fclk_khz;
+	int phyclk_khz;
 };
 
 struct dc_debug {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 8a581c67bf2d..b749a20a0c3d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -560,11 +560,9 @@ static bool dce_apply_clock_voltage_request(
 
 	switch (clocks_type) {
 	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-	case DM_PP_CLOCK_TYPE_PIXELCLK:
 	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
 		break;
 	default:
-		BREAK_TO_DEBUGGER();
 		return false;
 	}
 
@@ -575,31 +573,22 @@ static bool dce_apply_clock_voltage_request(
 	if (pre_mode_set) {
 		switch (clocks_type) {
 		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (clocks_in_khz > clk->cur_clocks_value.dispclk_in_khz) {
-				clk->cur_clocks_value.dispclk_notify_pplib_done = true;
+			if (clocks_in_khz > clk->clks.dispclk_khz) {
+				clk->dispclk_notify_pplib_done = true;
 				send_request = true;
 			} else
-				clk->cur_clocks_value.dispclk_notify_pplib_done = false;
+				clk->dispclk_notify_pplib_done = false;
 			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.dispclk_in_khz = clocks_in_khz;
-			break;
-		case DM_PP_CLOCK_TYPE_PIXELCLK:
-			if (clocks_in_khz > clk->cur_clocks_value.max_pixelclk_in_khz) {
-				clk->cur_clocks_value.pixelclk_notify_pplib_done = true;
-				send_request = true;
-			} else
-				clk->cur_clocks_value.pixelclk_notify_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.max_pixelclk_in_khz = clocks_in_khz;
+			clk->clks.dispclk_khz = clocks_in_khz;
 			break;
 		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (clocks_in_khz > clk->cur_clocks_value.max_non_dp_phyclk_in_khz) {
-				clk->cur_clocks_value.phyclk_notigy_pplib_done = true;
+			if (clocks_in_khz > clk->clks.phyclk_khz) {
+				clk->phyclk_notify_pplib_done = true;
 				send_request = true;
 			} else
-				clk->cur_clocks_value.phyclk_notigy_pplib_done = false;
+				clk->phyclk_notify_pplib_done = false;
 			/* no matter incrase or decrase clock, update current clock value */
-			clk->cur_clocks_value.max_non_dp_phyclk_in_khz = clocks_in_khz;
+			clk->clks.phyclk_khz = clocks_in_khz;
 			break;
 		default:
 			ASSERT(0);
@@ -609,16 +598,14 @@ static bool dce_apply_clock_voltage_request(
 	} else {
 		switch (clocks_type) {
 		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (!clk->cur_clocks_value.dispclk_notify_pplib_done)
-				send_request = true;
-			break;
-		case DM_PP_CLOCK_TYPE_PIXELCLK:
-			if (!clk->cur_clocks_value.pixelclk_notify_pplib_done)
+			if (!clk->dispclk_notify_pplib_done)
 				send_request = true;
+			clk->dispclk_notify_pplib_done = true;
 			break;
 		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (!clk->cur_clocks_value.phyclk_notigy_pplib_done)
+			if (!clk->phyclk_notify_pplib_done)
 				send_request = true;
+			clk->phyclk_notify_pplib_done = true;
 			break;
 		default:
 			ASSERT(0);
@@ -627,20 +614,21 @@ static bool dce_apply_clock_voltage_request(
 	}
 	if (send_request) {
 #if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-		if (clk->ctx->dce_version >= DCN_VERSION_1_0) {
+		if (clk->ctx->dce_version >= DCN_VERSION_1_0
+		) {
 			struct dc *core_dc = clk->ctx->dc;
 			/*use dcfclk request voltage*/
 			clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
 			clock_voltage_req.clocks_in_khz =
-				dcn_find_dcfclk_suits_all(core_dc, &clk->cur_clocks_value);
+				dcn_find_dcfclk_suits_all(core_dc, &clk->clks);
 		}
 #endif
 		dm_pp_apply_clock_for_voltage_request(
 			clk->ctx, &clock_voltage_req);
 	}
 	if (update_dp_phyclk && (clocks_in_khz >
-	clk->cur_clocks_value.max_dp_phyclk_in_khz))
-		clk->cur_clocks_value.max_dp_phyclk_in_khz = clocks_in_khz;
+	clk->clks.phyclk_khz))
+		clk->clks.phyclk_khz = clocks_in_khz;
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 353ffcbdf5ba..ddc8ffda9067 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1818,21 +1818,14 @@ static void apply_min_clocks(
 		context->dis_clk->funcs->apply_clock_voltage_request(
 				context->dis_clk,
 				DM_PP_CLOCK_TYPE_DISPLAY_CLK,
-				context->dis_clk->cur_clocks_value.dispclk_in_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_PIXELCLK,
-				context->dis_clk->cur_clocks_value.max_pixelclk_in_khz,
+				context->dis_clk->clks.dispclk_khz,
 				pre_mode_set,
 				false);
 
 		context->dis_clk->funcs->apply_clock_voltage_request(
 				context->dis_clk,
 				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-				context->dis_clk->cur_clocks_value.max_non_dp_phyclk_in_khz,
+				context->dis_clk->clks.phyclk_khz,
 				pre_mode_set,
 				false);
 		return;
@@ -1859,13 +1852,6 @@ static void apply_min_clocks(
 				pre_mode_set,
 				false);
 
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_PIXELCLK,
-				req_clocks.pixel_clk_khz,
-				pre_mode_set,
-				false);
-
 		context->dis_clk->funcs->apply_clock_voltage_request(
 				context->dis_clk,
 				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
index 132d18d4b293..ddbb673caa08 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dcn_calcs.h
@@ -625,7 +625,7 @@ bool dcn_validate_bandwidth(
 
 unsigned int dcn_find_dcfclk_suits_all(
 	const struct dc *dc,
-	struct clocks_value *clocks);
+	struct dc_clocks *clocks);
 
 void dcn_bw_update_from_pplib(struct dc *dc);
 void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
index f5f69cd81f6f..6b9ca5562de9 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
@@ -27,23 +27,7 @@
 #define __DISPLAY_CLOCK_H__
 
 #include "dm_services_types.h"
-
-
-struct clocks_value {
-	int dispclk_in_khz;
-	int max_pixelclk_in_khz;
-	int max_non_dp_phyclk_in_khz;
-	int max_dp_phyclk_in_khz;
-	bool dispclk_notify_pplib_done;
-	bool pixelclk_notify_pplib_done;
-	bool phyclk_notigy_pplib_done;
-	int dcfclock_in_khz;
-	int dppclk_in_khz;
-	int mclk_in_khz;
-	int phyclk_in_khz;
-	int common_vdd_level;
-};
-
+#include "dc.h"
 
 /* Structure containing all state-dependent clocks
  * (dependent on "enum clocks_state") */
@@ -56,9 +40,11 @@ struct display_clock {
 	struct dc_context *ctx;
 	const struct display_clock_funcs *funcs;
 
+	bool dispclk_notify_pplib_done;
+	bool phyclk_notify_pplib_done;
 	enum dm_pp_clocks_state max_clks_state;
 	enum dm_pp_clocks_state cur_min_clks_state;
-	struct clocks_value cur_clocks_value;
+	struct dc_clocks clks;
 };
 
 struct display_clock_funcs {
-- 
cgit v1.2.3


From fab55d61b9f04693abc6fdbc92e3fdf3872915b1 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 23 May 2018 16:21:54 -0400
Subject: drm/amd/display: redesign dce/dcn clock voltage update request

The goal of this change is to move clock programming and voltage
requests to a single function. As of this change only dce is affected.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c   |  22 +-
 drivers/gpu/drm/amd/display/dc/core/dc_link.c      |  30 +--
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c    | 279 +++++++++++----------
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h    |   6 +-
 .../amd/display/dc/dce100/dce100_hw_sequencer.c    |  49 +++-
 .../amd/display/dc/dce110/dce110_hw_sequencer.c    | 150 ++---------
 .../amd/display/dc/dce110/dce110_hw_sequencer.h    |   4 +
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  |   9 +-
 .../gpu/drm/amd/display/dc/dcn10/dcn10_resource.c  |   2 +-
 .../gpu/drm/amd/display/dc/inc/hw/display_clock.h  |  21 +-
 10 files changed, 250 insertions(+), 322 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index d8a31650e856..2b70ac67e6c2 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1145,10 +1145,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 
 	switch (clocks_type) {
 	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		/*if (clocks_in_khz > dc->dcn_soc->max_dispclk_vmax0p9*1000) {
+		if (clocks_in_khz > dc->dcn_soc->max_dispclk_vmax0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
-			//BREAK_TO_DEBUGGER();
-		} else*/ if (clocks_in_khz > dc->dcn_soc->max_dispclk_vnom0p8*1000) {
+			BREAK_TO_DEBUGGER();
+		} else if (clocks_in_khz > dc->dcn_soc->max_dispclk_vnom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->max_dispclk_vmid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
@@ -1158,10 +1158,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 			vdd_level = dcn_bw_v_min0p65;
 		break;
 	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-		/*if (clocks_in_khz > dc->dcn_soc->phyclkv_max0p9*1000) {
+		if (clocks_in_khz > dc->dcn_soc->phyclkv_max0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
 			BREAK_TO_DEBUGGER();
-		} else*/ if (clocks_in_khz > dc->dcn_soc->phyclkv_nom0p8*1000) {
+		} else if (clocks_in_khz > dc->dcn_soc->phyclkv_nom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->phyclkv_mid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
@@ -1172,10 +1172,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 		break;
 
 	case DM_PP_CLOCK_TYPE_DPPCLK:
-		/*if (clocks_in_khz > dc->dcn_soc->max_dppclk_vmax0p9*1000) {
+		if (clocks_in_khz > dc->dcn_soc->max_dppclk_vmax0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
 			BREAK_TO_DEBUGGER();
-		} else*/ if (clocks_in_khz > dc->dcn_soc->max_dppclk_vnom0p8*1000) {
+		} else if (clocks_in_khz > dc->dcn_soc->max_dppclk_vnom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->max_dppclk_vmid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
@@ -1189,10 +1189,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 		{
 			unsigned factor = (ddr4_dram_factor_single_Channel * dc->dcn_soc->number_of_channels);
 
-			/*if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9*1000000/factor) {
+			if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9*1000000/factor) {
 				vdd_level = dcn_bw_v_max0p91;
 				BREAK_TO_DEBUGGER();
-			} else */if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8*1000000/factor) {
+			} else if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8*1000000/factor) {
 				vdd_level = dcn_bw_v_max0p9;
 			} else if (clocks_in_khz > dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72*1000000/factor) {
 				vdd_level = dcn_bw_v_nom0p8;
@@ -1204,10 +1204,10 @@ static unsigned int dcn_find_normalized_clock_vdd_Level(
 		break;
 
 	case DM_PP_CLOCK_TYPE_DCFCLK:
-		/*if (clocks_in_khz > dc->dcn_soc->dcfclkv_max0p9*1000) {
+		if (clocks_in_khz > dc->dcn_soc->dcfclkv_max0p9*1000) {
 			vdd_level = dcn_bw_v_max0p91;
 			BREAK_TO_DEBUGGER();
-		} else */if (clocks_in_khz > dc->dcn_soc->dcfclkv_nom0p8*1000) {
+		} else if (clocks_in_khz > dc->dcn_soc->dcfclkv_nom0p8*1000) {
 			vdd_level = dcn_bw_v_max0p9;
 		} else if (clocks_in_khz > dc->dcn_soc->dcfclkv_mid0p72*1000) {
 			vdd_level = dcn_bw_v_nom0p8;
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 6155a5c7bd36..779d1926a756 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1284,27 +1284,15 @@ static enum dc_status enable_link_dp(
 		max_link_rate = LINK_RATE_HIGH3;
 
 	if (link_settings.link_rate == max_link_rate) {
-		if (state->dis_clk->funcs->set_min_clocks_state) {
-			if (state->dis_clk->cur_min_clks_state < DM_PP_CLOCKS_STATE_NOMINAL)
-				state->dis_clk->funcs->set_min_clocks_state(
-					state->dis_clk, DM_PP_CLOCKS_STATE_NOMINAL);
-		} else {
-			uint32_t dp_phyclk_in_khz;
-			const struct dc_clocks clocks_value =
-					state->dis_clk->clks;
-
-			/* 27mhz = 27000000hz= 27000khz */
-			dp_phyclk_in_khz = link_settings.link_rate * 27000;
-
-			if (dp_phyclk_in_khz > clocks_value.phyclk_khz) {
-				state->dis_clk->funcs->apply_clock_voltage_request(
-						state->dis_clk,
-						DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-						dp_phyclk_in_khz,
-						false,
-						true);
-			}
-		}
+		struct dc_clocks clocks = state->bw.dcn.calc_clk;
+
+		/* dce/dcn compat, do not update dispclk */
+		clocks.dispclk_khz = 0;
+		/* 27mhz = 27000000hz= 27000khz */
+		clocks.phyclk_khz = link_settings.link_rate * 27000;
+
+		state->dis_clk->funcs->update_clocks(
+				state->dis_clk, &clocks, false);
 	}
 
 	dp_enable_link_phy(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index b749a20a0c3d..d3bbac85dff1 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -275,7 +275,7 @@ static int dce_clocks_get_dp_ref_freq_wrkaround(struct display_clock *clk)
 }
 static enum dm_pp_clocks_state dce_get_required_clocks_state(
 	struct display_clock *clk,
-	struct state_dependent_clocks *req_clocks)
+	struct dc_clocks *req_clocks)
 {
 	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
 	int i;
@@ -286,48 +286,25 @@ static enum dm_pp_clocks_state dce_get_required_clocks_state(
 	 * all required clocks
 	 */
 	for (i = clk->max_clks_state; i >= DM_PP_CLOCKS_STATE_ULTRA_LOW; i--)
-		if (req_clocks->display_clk_khz >
+		if (req_clocks->dispclk_khz >
 				clk_dce->max_clks_by_state[i].display_clk_khz
-			|| req_clocks->pixel_clk_khz >
+			|| req_clocks->phyclk_khz >
 				clk_dce->max_clks_by_state[i].pixel_clk_khz)
 			break;
 
 	low_req_clk = i + 1;
 	if (low_req_clk > clk->max_clks_state) {
-		DC_LOG_WARNING("%s: clocks unsupported disp_clk %d pix_clk %d",
-				__func__,
-				req_clocks->display_clk_khz,
-				req_clocks->pixel_clk_khz);
-		low_req_clk = DM_PP_CLOCKS_STATE_INVALID;
+		/* set max clock state for high phyclock, invalid on exceeding display clock */
+		if (clk_dce->max_clks_by_state[clk->max_clks_state].display_clk_khz
+				< req_clocks->dispclk_khz)
+			low_req_clk = DM_PP_CLOCKS_STATE_INVALID;
+		else
+			low_req_clk = clk->max_clks_state;
 	}
 
 	return low_req_clk;
 }
 
-static bool dce_clock_set_min_clocks_state(
-	struct display_clock *clk,
-	enum dm_pp_clocks_state clocks_state)
-{
-	struct dm_pp_power_level_change_request level_change_req = {
-			clocks_state };
-
-	if (clocks_state > clk->max_clks_state) {
-		/*Requested state exceeds max supported state.*/
-		DC_LOG_WARNING("Requested state exceeds max supported state");
-		return false;
-	} else if (clocks_state == clk->cur_min_clks_state) {
-		/*if we're trying to set the same state, we can just return
-		 * since nothing needs to be done*/
-		return true;
-	}
-
-	/* get max clock state from PPLIB */
-	if (dm_pp_apply_power_level_change_request(clk->ctx, &level_change_req))
-		clk->cur_min_clks_state = clocks_state;
-
-	return true;
-}
-
 static int dce_set_clock(
 	struct display_clock *clk,
 	int requested_clk_khz)
@@ -488,8 +465,6 @@ static void dce_clock_read_integrated_info(struct dce_disp_clk *clk_dce)
 	if (!debug->disable_dfs_bypass && bp->integrated_info)
 		if (bp->integrated_info->gpu_cap_info & DFS_BYPASS_ENABLE)
 			clk_dce->dfs_bypass_enabled = true;
-
-	clk_dce->use_max_disp_clk = debug->max_disp_clk;
 }
 
 static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
@@ -548,117 +523,160 @@ static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
 	}
 }
 
-static bool dce_apply_clock_voltage_request(
-	struct display_clock *clk,
-	enum dm_pp_clock_type clocks_type,
-	int clocks_in_khz,
-	bool pre_mode_set,
-	bool update_dp_phyclk)
+static void dce12_update_clocks(struct display_clock *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
 {
-	bool send_request = false;
 	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
 
-	switch (clocks_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-		break;
-	default:
-		return false;
+	if ((new_clocks->dispclk_khz < dccg->clks.dispclk_khz && safe_to_lower)
+			|| new_clocks->dispclk_khz > dccg->clks.dispclk_khz) {
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
+		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
 
-	clock_voltage_req.clk_type = clocks_type;
-	clock_voltage_req.clocks_in_khz = clocks_in_khz;
-
-	/* to pplib */
-	if (pre_mode_set) {
-		switch (clocks_type) {
-		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (clocks_in_khz > clk->clks.dispclk_khz) {
-				clk->dispclk_notify_pplib_done = true;
-				send_request = true;
-			} else
-				clk->dispclk_notify_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->clks.dispclk_khz = clocks_in_khz;
-			break;
-		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (clocks_in_khz > clk->clks.phyclk_khz) {
-				clk->phyclk_notify_pplib_done = true;
-				send_request = true;
-			} else
-				clk->phyclk_notify_pplib_done = false;
-			/* no matter incrase or decrase clock, update current clock value */
-			clk->clks.phyclk_khz = clocks_in_khz;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
+	if ((new_clocks->phyclk_khz < dccg->clks.phyclk_khz && safe_to_lower)
+			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz) {
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAYPHYCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
+		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
 
-	} else {
-		switch (clocks_type) {
-		case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-			if (!clk->dispclk_notify_pplib_done)
-				send_request = true;
-			clk->dispclk_notify_pplib_done = true;
-			break;
-		case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-			if (!clk->phyclk_notify_pplib_done)
-				send_request = true;
-			clk->phyclk_notify_pplib_done = true;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
-	if (send_request) {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-		if (clk->ctx->dce_version >= DCN_VERSION_1_0
+}
+
+static void dcn_update_clocks(struct display_clock *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
+{
+	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
+	bool send_request_to_increase = false;
+	bool send_request_to_lower = false;
+
+	if (new_clocks->dispclk_khz > dccg->clks.dispclk_khz
+			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz
+			|| new_clocks->fclk_khz > dccg->clks.fclk_khz
+			|| new_clocks->dcfclk_khz > dccg->clks.dcfclk_khz)
+		send_request_to_increase = true;
+
+#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+	if (send_request_to_increase
 		) {
-			struct dc *core_dc = clk->ctx->dc;
-			/*use dcfclk request voltage*/
-			clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-			clock_voltage_req.clocks_in_khz =
-				dcn_find_dcfclk_suits_all(core_dc, &clk->clks);
-		}
+		struct dc *core_dc = dccg->ctx->dc;
+
+		/*use dcfclk to request voltage*/
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(core_dc, new_clocks);
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+	}
 #endif
-		dm_pp_apply_clock_for_voltage_request(
-			clk->ctx, &clock_voltage_req);
+
+	if ((new_clocks->dispclk_khz < dccg->clks.dispclk_khz && safe_to_lower)
+			|| new_clocks->dispclk_khz > dccg->clks.dispclk_khz) {
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
+		/* TODO: ramp up - dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);*/
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		send_request_to_lower = true;
 	}
-	if (update_dp_phyclk && (clocks_in_khz >
-	clk->clks.phyclk_khz))
-		clk->clks.phyclk_khz = clocks_in_khz;
 
-	return true;
+	if ((new_clocks->phyclk_khz < dccg->clks.phyclk_khz && safe_to_lower)
+			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz) {
+		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAYPHYCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		send_request_to_lower = true;
+	}
+
+	if ((new_clocks->fclk_khz < dccg->clks.fclk_khz && safe_to_lower)
+			|| new_clocks->fclk_khz > dccg->clks.fclk_khz) {
+		dccg->clks.phyclk_khz = new_clocks->fclk_khz;
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_FCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->fclk_khz;
+
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		send_request_to_lower = true;
+	}
+
+	if ((new_clocks->dcfclk_khz < dccg->clks.dcfclk_khz && safe_to_lower)
+			|| new_clocks->dcfclk_khz > dccg->clks.dcfclk_khz) {
+		dccg->clks.phyclk_khz = new_clocks->dcfclk_khz;
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = new_clocks->dcfclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+	if (!send_request_to_increase && send_request_to_lower
+		) {
+		struct dc *core_dc = dccg->ctx->dc;
+
+		/*use dcfclk to request voltage*/
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(core_dc, new_clocks);
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+	}
+#endif
+}
+
+static void dce_update_clocks(struct display_clock *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower)
+{
+	struct dm_pp_power_level_change_request level_change_req;
+
+	level_change_req.power_level = dce_get_required_clocks_state(dccg, new_clocks);
+	/* get max clock state from PPLIB */
+	if ((level_change_req.power_level < dccg->cur_min_clks_state && safe_to_lower)
+			|| level_change_req.power_level > dccg->cur_min_clks_state) {
+		if (dm_pp_apply_power_level_change_request(dccg->ctx, &level_change_req))
+			dccg->cur_min_clks_state = level_change_req.power_level;
+	}
+
+	if ((new_clocks->dispclk_khz < dccg->clks.dispclk_khz && safe_to_lower)
+			|| new_clocks->dispclk_khz > dccg->clks.dispclk_khz) {
+		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+	}
 }
 
+static const struct display_clock_funcs dcn_funcs = {
+	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq_wrkaround,
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dcn_update_clocks
+};
 
 static const struct display_clock_funcs dce120_funcs = {
 	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq_wrkaround,
-	.apply_clock_voltage_request = dce_apply_clock_voltage_request,
-	.set_clock = dce112_set_clock
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dce12_update_clocks
 };
 
 static const struct display_clock_funcs dce112_funcs = {
 	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce112_set_clock
+	.set_dispclk = dce112_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce110_funcs = {
 	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce_psr_set_clock
+	.set_dispclk = dce_psr_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce_funcs = {
 	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
-	.get_required_clocks_state = dce_get_required_clocks_state,
-	.set_min_clocks_state = dce_clock_set_min_clocks_state,
-	.set_clock = dce_set_clock
+	.set_dispclk = dce_set_clock,
+	.update_clocks = dce_update_clocks
 };
 
 static void dce_disp_clk_construct(
@@ -785,7 +803,6 @@ struct display_clock *dce112_disp_clk_create(
 struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
 {
 	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
-	struct dm_pp_clock_levels_with_voltage clk_level_info = {0};
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -801,15 +818,23 @@ struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
 
 	clk_dce->base.funcs = &dce120_funcs;
 
-	/* new in dce120 */
-	if (!ctx->dc->debug.disable_pplib_clock_request  &&
-			dm_pp_get_clock_levels_by_type_with_voltage(
-			ctx, DM_PP_CLOCK_TYPE_DISPLAY_CLK, &clk_level_info)
-						&& clk_level_info.num_levels)
-		clk_dce->max_displ_clk_in_khz =
-			clk_level_info.data[clk_level_info.num_levels - 1].clocks_in_khz;
-	else
-		clk_dce->max_displ_clk_in_khz = 1133000;
+	return &clk_dce->base;
+}
+
+struct display_clock *dcn_disp_clk_create(struct dc_context *ctx)
+{
+	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+
+	if (clk_dce == NULL) {
+		BREAK_TO_DEBUGGER();
+		return NULL;
+	}
+
+	/* TODO strip out useful stuff out of dce constructor */
+	dce_disp_clk_construct(
+		clk_dce, ctx, NULL, NULL, NULL);
+
+	clk_dce->base.funcs = &dcn_funcs;
 
 	return &clk_dce->base;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 0e717e0dc8f0..f9b002015255 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -91,7 +91,6 @@ struct dce_disp_clk {
 	struct state_dependent_clocks max_clks_by_state[DM_PP_CLOCKS_MAX_STATES];
 	struct dce_divider_range divider_ranges[DIVIDER_RANGE_MAX];
 
-	bool use_max_disp_clk;
 	int dentist_vco_freq_khz;
 
 	/* Cache the status of DFS-bypass feature*/
@@ -106,9 +105,6 @@ struct dce_disp_clk {
 	int dprefclk_ss_percentage;
 	/* DPREFCLK SS percentage Divider (100 or 1000) */
 	int dprefclk_ss_divider;
-
-	/* max disp_clk from PPLIB for max validation display clock*/
-	int max_displ_clk_in_khz;
 };
 
 
@@ -132,6 +128,8 @@ struct display_clock *dce112_disp_clk_create(
 
 struct display_clock *dce120_disp_clk_create(struct dc_context *ctx);
 
+struct display_clock *dcn_disp_clk_create(struct dc_context *ctx);
+
 void dce_disp_clk_destroy(struct display_clock **disp_clk);
 
 #endif /* _DCE_CLOCKS_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
index 41f83ecd7469..aabf7ca9b241 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
@@ -125,17 +125,54 @@ static void dce100_pplib_apply_display_requirements(
 	dc->prev_display_config = *pp_display_cfg;
 }
 
+/* unit: in_khz before mode set, get pixel clock from context. ASIC register
+ * may not be programmed yet
+ */
+static uint32_t get_max_pixel_clock_for_all_paths(
+	struct dc *dc,
+	struct dc_state *context)
+{
+	uint32_t max_pix_clk = 0;
+	int i;
+
+	for (i = 0; i < MAX_PIPES; i++) {
+		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+		if (pipe_ctx->stream == NULL)
+			continue;
+
+		/* do not check under lay */
+		if (pipe_ctx->top_pipe)
+			continue;
+
+		if (pipe_ctx->stream_res.pix_clk_params.requested_pix_clk > max_pix_clk)
+			max_pix_clk =
+				pipe_ctx->stream_res.pix_clk_params.requested_pix_clk;
+	}
+
+	if (max_pix_clk == 0)
+		ASSERT(0);
+
+	return max_pix_clk;
+}
+
 void dce100_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	if (decrease_allowed || context->bw.dce.dispclk_khz > dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-		dc->current_state->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz;
-	}
+	struct dc_clocks req_clks;
+
+	req_clks.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100;
+	req_clks.phyclk_khz = get_max_pixel_clock_for_all_paths(dc, context);
+
+	dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
+
+	dc->res_pool->display_clock->funcs->update_clocks(
+			dc->res_pool->display_clock,
+			&req_clks,
+			decrease_allowed);
+
 	dce100_pplib_apply_display_requirements(dc, context);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index ddc8ffda9067..02aa0a2ec875 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1663,7 +1663,7 @@ static void dce110_set_displaymarks(
 	}
 }
 
-static void set_safe_displaymarks(
+void dce110_set_safe_displaymarks(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool)
 {
@@ -1755,23 +1755,15 @@ static void set_static_screen_control(struct pipe_ctx **pipe_ctx,
 }
 
 /* unit: in_khz before mode set, get pixel clock from context. ASIC register
- * may not be programmed yet.
- * TODO: after mode set, pre_mode_set = false,
- * may read PLL register to get pixel clock
+ * may not be programmed yet
  */
 static uint32_t get_max_pixel_clock_for_all_paths(
 	struct dc *dc,
-	struct dc_state *context,
-	bool pre_mode_set)
+	struct dc_state *context)
 {
 	uint32_t max_pix_clk = 0;
 	int i;
 
-	if (!pre_mode_set) {
-		/* TODO: read ASIC register to get pixel clock */
-		ASSERT(0);
-	}
-
 	for (i = 0; i < MAX_PIPES; i++) {
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 
@@ -1793,74 +1785,6 @@ static uint32_t get_max_pixel_clock_for_all_paths(
 	return max_pix_clk;
 }
 
-/*
- * Find clock state based on clock requested. if clock value is 0, simply
- * set clock state as requested without finding clock state by clock value
- */
-
-static void apply_min_clocks(
-	struct dc *dc,
-	struct dc_state *context,
-	enum dm_pp_clocks_state *clocks_state,
-	bool pre_mode_set)
-{
-	struct state_dependent_clocks req_clocks = {0};
-
-	if (!pre_mode_set) {
-		/* set clock_state without verification */
-		if (context->dis_clk->funcs->set_min_clocks_state) {
-			context->dis_clk->funcs->set_min_clocks_state(
-						context->dis_clk, *clocks_state);
-			return;
-		}
-
-		/* TODO: This is incorrect. Figure out how to fix. */
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAY_CLK,
-				context->dis_clk->clks.dispclk_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-				context->dis_clk->clks.phyclk_khz,
-				pre_mode_set,
-				false);
-		return;
-	}
-
-	/* get the required state based on state dependent clocks:
-	 * display clock and pixel clock
-	 */
-	req_clocks.display_clk_khz = context->bw.dce.dispclk_khz;
-
-	req_clocks.pixel_clk_khz = get_max_pixel_clock_for_all_paths(
-			dc, context, true);
-
-	if (context->dis_clk->funcs->get_required_clocks_state) {
-		*clocks_state = context->dis_clk->funcs->get_required_clocks_state(
-				context->dis_clk, &req_clocks);
-		context->dis_clk->funcs->set_min_clocks_state(
-			context->dis_clk, *clocks_state);
-	} else {
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAY_CLK,
-				req_clocks.display_clk_khz,
-				pre_mode_set,
-				false);
-
-		context->dis_clk->funcs->apply_clock_voltage_request(
-				context->dis_clk,
-				DM_PP_CLOCK_TYPE_DISPLAYPHYCLK,
-				req_clocks.pixel_clk_khz,
-				pre_mode_set,
-				false);
-	}
-}
-
 /*
  *  Check if FBC can be enabled
  */
@@ -2079,7 +2003,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 	struct dc_bios *dcb = dc->ctx->dc_bios;
 	enum dc_status status;
 	int i;
-	enum dm_pp_clocks_state clocks_state = DM_PP_CLOCKS_STATE_INVALID;
 
 	/* Reset old context */
 	/* look up the targets that have been removed since last commit */
@@ -2113,54 +2036,10 @@ enum dc_status dce110_apply_ctx_to_hw(
 				PIPE_GATING_CONTROL_DISABLE);
 	}
 
-	set_safe_displaymarks(&context->res_ctx, dc->res_pool);
-
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
 
-	/*TODO: when pplib works*/
-	apply_min_clocks(dc, context, &clocks_state, true);
-
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	if (dc->ctx->dce_version >= DCN_VERSION_1_0) {
-		if (context->bw.dcn.calc_clk.fclk_khz
-				> dc->current_state->bw.dcn.cur_clk.fclk_khz) {
-			struct dm_pp_clock_for_voltage_req clock;
-
-			clock.clk_type = DM_PP_CLOCK_TYPE_FCLK;
-			clock.clocks_in_khz = context->bw.dcn.calc_clk.fclk_khz;
-			dm_pp_apply_clock_for_voltage_request(dc->ctx, &clock);
-			dc->current_state->bw.dcn.cur_clk.fclk_khz = clock.clocks_in_khz;
-			context->bw.dcn.cur_clk.fclk_khz = clock.clocks_in_khz;
-		}
-		if (context->bw.dcn.calc_clk.dcfclk_khz
-				> dc->current_state->bw.dcn.cur_clk.dcfclk_khz) {
-			struct dm_pp_clock_for_voltage_req clock;
-
-			clock.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-			clock.clocks_in_khz = context->bw.dcn.calc_clk.dcfclk_khz;
-			dm_pp_apply_clock_for_voltage_request(dc->ctx, &clock);
-			dc->current_state->bw.dcn.cur_clk.dcfclk_khz = clock.clocks_in_khz;
-			context->bw.dcn.cur_clk.dcfclk_khz = clock.clocks_in_khz;
-		}
-		if (context->bw.dcn.calc_clk.dispclk_khz
-				> dc->current_state->bw.dcn.cur_clk.dispclk_khz) {
-			dc->res_pool->display_clock->funcs->set_clock(
-					dc->res_pool->display_clock,
-					context->bw.dcn.calc_clk.dispclk_khz);
-			dc->current_state->bw.dcn.cur_clk.dispclk_khz =
-					context->bw.dcn.calc_clk.dispclk_khz;
-			context->bw.dcn.cur_clk.dispclk_khz =
-					context->bw.dcn.calc_clk.dispclk_khz;
-		}
-	} else
-#endif
-	if (context->bw.dce.dispclk_khz
-			> dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-	}
+	dc->hwss.set_bandwidth(dc, context, false);
 
 	dce110_setup_audio_dto(dc, context);
 
@@ -2191,7 +2070,7 @@ enum dc_status dce110_apply_ctx_to_hw(
 	}
 
 	/* to save power */
-	apply_min_clocks(dc, context, &clocks_state, false);
+	dc->hwss.set_bandwidth(dc, context, true);
 
 	dcb->funcs->set_scratch_critical_state(dcb, false);
 
@@ -2680,15 +2559,20 @@ static void dce110_set_bandwidth(
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	dce110_set_displaymarks(dc, context);
+	struct dc_clocks req_clks;
 
-	if (decrease_allowed || context->bw.dce.dispclk_khz > dc->current_state->bw.dce.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
-				dc->res_pool->display_clock,
-				context->bw.dce.dispclk_khz * 115 / 100);
-		dc->current_state->bw.dce.dispclk_khz = context->bw.dce.dispclk_khz;
-	}
+	req_clks.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100;
+	req_clks.phyclk_khz = get_max_pixel_clock_for_all_paths(dc, context);
+
+	if (decrease_allowed)
+		dce110_set_displaymarks(dc, context);
+	else
+		dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
 
+	dc->res_pool->display_clock->funcs->update_clocks(
+			dc->res_pool->display_clock,
+			&req_clks,
+			decrease_allowed);
 	pplib_apply_display_requirements(dc, context);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
index f48d5a68d238..d6db3dbd9015 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
@@ -60,6 +60,10 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context);
 
 void dce110_power_down(struct dc *dc);
 
+void dce110_set_safe_displaymarks(
+		struct resource_context *res_ctx,
+		const struct resource_pool *pool);
+
 void dce110_fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 03eb736a312f..7f1a7ec9ff5f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2424,7 +2424,7 @@ static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
 	int dispclk_to_dpp_threshold = determine_dppclk_threshold(dc, context);
 
 	/* set disp clk to dpp clk threshold */
-	dc->res_pool->display_clock->funcs->set_clock(
+	dc->res_pool->display_clock->funcs->set_dispclk(
 			dc->res_pool->display_clock,
 			dispclk_to_dpp_threshold);
 
@@ -2443,7 +2443,7 @@ static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
 
 	/* If target clk not same as dppclk threshold, set to target clock */
 	if (dispclk_to_dpp_threshold != context->bw.dcn.calc_clk.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_clock(
+		dc->res_pool->display_clock->funcs->set_dispclk(
 				dc->res_pool->display_clock,
 				context->bw.dcn.calc_clk.dispclk_khz);
 	}
@@ -2473,6 +2473,11 @@ static void dcn10_set_bandwidth(
 	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		return;
 
+	dc->res_pool->display_clock->funcs->update_clocks(
+			dc->res_pool->display_clock,
+			&context->bw.dcn.calc_clk,
+			decrease_allowed);
+
 	if (should_set_clock(
 			decrease_allowed,
 			context->bw.dcn.calc_clk.dcfclk_khz,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 2da325ce781b..870eb0aabcc9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1072,7 +1072,7 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce120_disp_clk_create(ctx);
+	pool->base.display_clock = dcn_disp_clk_create(ctx);
 	if (pool->base.display_clock == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
index 6b9ca5562de9..8ce106f15647 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
@@ -40,32 +40,19 @@ struct display_clock {
 	struct dc_context *ctx;
 	const struct display_clock_funcs *funcs;
 
-	bool dispclk_notify_pplib_done;
-	bool phyclk_notify_pplib_done;
 	enum dm_pp_clocks_state max_clks_state;
 	enum dm_pp_clocks_state cur_min_clks_state;
 	struct dc_clocks clks;
 };
 
 struct display_clock_funcs {
-	int (*set_clock)(struct display_clock *disp_clk,
+	void (*update_clocks)(struct display_clock *dccg,
+			struct dc_clocks *new_clocks,
+			bool safe_to_lower);
+	int (*set_dispclk)(struct display_clock *disp_clk,
 		int requested_clock_khz);
 
-	enum dm_pp_clocks_state (*get_required_clocks_state)(
-		struct display_clock *disp_clk,
-		struct state_dependent_clocks *req_clocks);
-
-	bool (*set_min_clocks_state)(struct display_clock *disp_clk,
-		enum dm_pp_clocks_state dm_pp_clocks_state);
-
 	int (*get_dp_ref_clk_frequency)(struct display_clock *disp_clk);
-
-	bool (*apply_clock_voltage_request)(
-		struct display_clock *disp_clk,
-		enum dm_pp_clock_type clocks_type,
-		int clocks_in_khz,
-		bool pre_mode_set,
-		bool update_dp_phyclk);
 };
 
 #endif /* __DISPLAY_CLOCK_H__ */
-- 
cgit v1.2.3


From 6ca11246180a6e5e6b5b668545c2575b304c9f7f Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 23 May 2018 16:44:26 -0400
Subject: drm/amd/display: rename display clock block to dccg

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c  |  2 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c    | 78 +++++++++++-----------
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h    | 16 ++---
 .../amd/display/dc/dce100/dce100_hw_sequencer.c    |  4 +-
 .../drm/amd/display/dc/dce100/dce100_resource.c    | 10 +--
 .../amd/display/dc/dce110/dce110_hw_sequencer.c    |  4 +-
 .../drm/amd/display/dc/dce110/dce110_resource.c    | 10 +--
 .../drm/amd/display/dc/dce112/dce112_resource.c    | 10 +--
 .../drm/amd/display/dc/dce120/dce120_resource.c    | 12 ++--
 .../gpu/drm/amd/display/dc/dce80/dce80_resource.c  | 22 +++---
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 12 ++--
 .../gpu/drm/amd/display/dc/dcn10/dcn10_resource.c  |  8 +--
 drivers/gpu/drm/amd/display/dc/inc/core_types.h    |  4 +-
 .../gpu/drm/amd/display/dc/inc/hw/display_clock.h  |  8 +--
 14 files changed, 100 insertions(+), 100 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index fca22550417a..c5fc5250e2bf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1948,7 +1948,7 @@ void dc_resource_state_construct(
 		const struct dc *dc,
 		struct dc_state *dst_ctx)
 {
-	dst_ctx->dis_clk = dc->res_pool->display_clock;
+	dst_ctx->dis_clk = dc->res_pool->dccg;
 }
 
 enum dc_status dc_validate_global_state(
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index d3bbac85dff1..890a3ec68d49 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -38,7 +38,7 @@
 #include "dal_asic_id.h"
 
 #define TO_DCE_CLOCKS(clocks)\
-	container_of(clocks, struct dce_disp_clk, base)
+	container_of(clocks, struct dce_dccg, base)
 
 #define REG(reg) \
 	(clk_dce->regs->reg)
@@ -187,9 +187,9 @@ static int dce_divider_range_get_divider(
 	return div;
 }
 
-static int dce_clocks_get_dp_ref_freq(struct display_clock *clk)
+static int dce_clocks_get_dp_ref_freq(struct dccg *clk)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int dprefclk_wdivider;
 	int dprefclk_src_sel;
 	int dp_ref_clk_khz = 600000;
@@ -250,9 +250,9 @@ static int dce_clocks_get_dp_ref_freq(struct display_clock *clk)
  * or CLK0_CLK11 by SMU. For DCE120, it is wlays 600Mhz. Will re-visit
  * clock implementation
  */
-static int dce_clocks_get_dp_ref_freq_wrkaround(struct display_clock *clk)
+static int dce_clocks_get_dp_ref_freq_wrkaround(struct dccg *clk)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int dp_ref_clk_khz = 600000;
 
 	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
@@ -274,10 +274,10 @@ static int dce_clocks_get_dp_ref_freq_wrkaround(struct display_clock *clk)
 	return dp_ref_clk_khz;
 }
 static enum dm_pp_clocks_state dce_get_required_clocks_state(
-	struct display_clock *clk,
+	struct dccg *clk,
 	struct dc_clocks *req_clocks)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int i;
 	enum dm_pp_clocks_state low_req_clk;
 
@@ -306,10 +306,10 @@ static enum dm_pp_clocks_state dce_get_required_clocks_state(
 }
 
 static int dce_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct bp_pixel_clock_parameters pxl_clk_params = { 0 };
 	struct dc_bios *bp = clk->ctx->dc_bios;
 	int actual_clock = requested_clk_khz;
@@ -341,10 +341,10 @@ static int dce_set_clock(
 }
 
 static int dce_psr_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct dc_context *ctx = clk_dce->base.ctx;
 	struct dc *core_dc = ctx->dc;
 	struct dmcu *dmcu = core_dc->res_pool->dmcu;
@@ -357,10 +357,10 @@ static int dce_psr_set_clock(
 }
 
 static int dce112_set_clock(
-	struct display_clock *clk,
+	struct dccg *clk,
 	int requested_clk_khz)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	struct bp_set_dce_clock_parameters dce_clk_params;
 	struct dc_bios *bp = clk->ctx->dc_bios;
 	struct dc *core_dc = clk->ctx->dc;
@@ -409,7 +409,7 @@ static int dce112_set_clock(
 	return actual_clock;
 }
 
-static void dce_clock_read_integrated_info(struct dce_disp_clk *clk_dce)
+static void dce_clock_read_integrated_info(struct dce_dccg *clk_dce)
 {
 	struct dc_debug *debug = &clk_dce->base.ctx->dc->debug;
 	struct dc_bios *bp = clk_dce->base.ctx->dc_bios;
@@ -467,7 +467,7 @@ static void dce_clock_read_integrated_info(struct dce_disp_clk *clk_dce)
 			clk_dce->dfs_bypass_enabled = true;
 }
 
-static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
+static void dce_clock_read_ss_info(struct dce_dccg *clk_dce)
 {
 	struct dc_bios *bp = clk_dce->base.ctx->dc_bios;
 	int ss_info_num = bp->funcs->get_ss_entry_number(
@@ -523,7 +523,7 @@ static void dce_clock_read_ss_info(struct dce_disp_clk *clk_dce)
 	}
 }
 
-static void dce12_update_clocks(struct display_clock *dccg,
+static void dce12_update_clocks(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
 			bool safe_to_lower)
 {
@@ -549,7 +549,7 @@ static void dce12_update_clocks(struct display_clock *dccg,
 	}
 }
 
-static void dcn_update_clocks(struct display_clock *dccg,
+static void dcn_update_clocks(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
 			bool safe_to_lower)
 {
@@ -628,7 +628,7 @@ static void dcn_update_clocks(struct display_clock *dccg,
 #endif
 }
 
-static void dce_update_clocks(struct display_clock *dccg,
+static void dce_update_clocks(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
 			bool safe_to_lower)
 {
@@ -679,14 +679,14 @@ static const struct display_clock_funcs dce_funcs = {
 	.update_clocks = dce_update_clocks
 };
 
-static void dce_disp_clk_construct(
-	struct dce_disp_clk *clk_dce,
+static void dce_dccg_construct(
+	struct dce_dccg *clk_dce,
 	struct dc_context *ctx,
 	const struct dce_disp_clk_registers *regs,
 	const struct dce_disp_clk_shift *clk_shift,
 	const struct dce_disp_clk_mask *clk_mask)
 {
-	struct display_clock *base = &clk_dce->base;
+	struct dccg *base = &clk_dce->base;
 
 	base->ctx = ctx;
 	base->funcs = &dce_funcs;
@@ -727,13 +727,13 @@ static void dce_disp_clk_construct(
 		DIVIDER_RANGE_MAX_DIVIDER_ID);
 }
 
-struct display_clock *dce_disp_clk_create(
+struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
 	const struct dce_disp_clk_registers *regs,
 	const struct dce_disp_clk_shift *clk_shift,
 	const struct dce_disp_clk_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -744,19 +744,19 @@ struct display_clock *dce_disp_clk_create(
 		dce80_max_clks_by_state,
 		sizeof(dce80_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	return &clk_dce->base;
 }
 
-struct display_clock *dce110_disp_clk_create(
+struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
 	const struct dce_disp_clk_registers *regs,
 	const struct dce_disp_clk_shift *clk_shift,
 	const struct dce_disp_clk_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -767,7 +767,7 @@ struct display_clock *dce110_disp_clk_create(
 		dce110_max_clks_by_state,
 		sizeof(dce110_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	clk_dce->base.funcs = &dce110_funcs;
@@ -775,13 +775,13 @@ struct display_clock *dce110_disp_clk_create(
 	return &clk_dce->base;
 }
 
-struct display_clock *dce112_disp_clk_create(
+struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
 	const struct dce_disp_clk_registers *regs,
 	const struct dce_disp_clk_shift *clk_shift,
 	const struct dce_disp_clk_mask *clk_mask)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -792,7 +792,7 @@ struct display_clock *dce112_disp_clk_create(
 		dce112_max_clks_by_state,
 		sizeof(dce112_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, regs, clk_shift, clk_mask);
 
 	clk_dce->base.funcs = &dce112_funcs;
@@ -800,9 +800,9 @@ struct display_clock *dce112_disp_clk_create(
 	return &clk_dce->base;
 }
 
-struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
+struct dccg *dce120_dccg_create(struct dc_context *ctx)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -813,7 +813,7 @@ struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
 		dce120_max_clks_by_state,
 		sizeof(dce120_max_clks_by_state));
 
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, NULL, NULL, NULL);
 
 	clk_dce->base.funcs = &dce120_funcs;
@@ -821,9 +821,9 @@ struct display_clock *dce120_disp_clk_create(struct dc_context *ctx)
 	return &clk_dce->base;
 }
 
-struct display_clock *dcn_disp_clk_create(struct dc_context *ctx)
+struct dccg *dcn_dccg_create(struct dc_context *ctx)
 {
-	struct dce_disp_clk *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
+	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
 		BREAK_TO_DEBUGGER();
@@ -831,7 +831,7 @@ struct display_clock *dcn_disp_clk_create(struct dc_context *ctx)
 	}
 
 	/* TODO strip out useful stuff out of dce constructor */
-	dce_disp_clk_construct(
+	dce_dccg_construct(
 		clk_dce, ctx, NULL, NULL, NULL);
 
 	clk_dce->base.funcs = &dcn_funcs;
@@ -839,10 +839,10 @@ struct display_clock *dcn_disp_clk_create(struct dc_context *ctx)
 	return &clk_dce->base;
 }
 
-void dce_disp_clk_destroy(struct display_clock **disp_clk)
+void dce_dccg_destroy(struct dccg **dccg)
 {
-	struct dce_disp_clk *clk_dce = TO_DCE_CLOCKS(*disp_clk);
+	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(*dccg);
 
 	kfree(clk_dce);
-	*disp_clk = NULL;
+	*dccg = NULL;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index f9b002015255..c695b9c9bcb5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -82,8 +82,8 @@ struct dce_divider_range {
 	int did_max;
 };
 
-struct dce_disp_clk {
-	struct display_clock base;
+struct dce_dccg {
+	struct dccg base;
 	const struct dce_disp_clk_registers *regs;
 	const struct dce_disp_clk_shift *clk_shift;
 	const struct dce_disp_clk_mask *clk_mask;
@@ -108,28 +108,28 @@ struct dce_disp_clk {
 };
 
 
-struct display_clock *dce_disp_clk_create(
+struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
 	const struct dce_disp_clk_registers *regs,
 	const struct dce_disp_clk_shift *clk_shift,
 	const struct dce_disp_clk_mask *clk_mask);
 
-struct display_clock *dce110_disp_clk_create(
+struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
 	const struct dce_disp_clk_registers *regs,
 	const struct dce_disp_clk_shift *clk_shift,
 	const struct dce_disp_clk_mask *clk_mask);
 
-struct display_clock *dce112_disp_clk_create(
+struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
 	const struct dce_disp_clk_registers *regs,
 	const struct dce_disp_clk_shift *clk_shift,
 	const struct dce_disp_clk_mask *clk_mask);
 
-struct display_clock *dce120_disp_clk_create(struct dc_context *ctx);
+struct dccg *dce120_dccg_create(struct dc_context *ctx);
 
-struct display_clock *dcn_disp_clk_create(struct dc_context *ctx);
+struct dccg *dcn_dccg_create(struct dc_context *ctx);
 
-void dce_disp_clk_destroy(struct display_clock **disp_clk);
+void dce_dccg_destroy(struct dccg **dccg);
 
 #endif /* _DCE_CLOCKS_H_ */
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
index aabf7ca9b241..ec3221333011 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
@@ -168,8 +168,8 @@ void dce100_set_bandwidth(
 
 	dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
 
-	dc->res_pool->display_clock->funcs->update_clocks(
-			dc->res_pool->display_clock,
+	dc->res_pool->dccg->funcs->update_clocks(
+			dc->res_pool->dccg,
 			&req_clks,
 			decrease_allowed);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 38ec0d609297..856d3fe8e6a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -644,8 +644,8 @@ static void destruct(struct dce110_resource_pool *pool)
 			dce_aud_destroy(&pool->base.audios[i]);
 	}
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.abm != NULL)
 				dce_abm_destroy(&pool->base.abm);
@@ -817,11 +817,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -851,7 +851,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 	{
 		struct irq_service_init_data init_data;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 02aa0a2ec875..34eb7a33851b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2569,8 +2569,8 @@ static void dce110_set_bandwidth(
 	else
 		dce110_set_safe_displaymarks(&context->res_ctx, dc->res_pool);
 
-	dc->res_pool->display_clock->funcs->update_clocks(
-			dc->res_pool->display_clock,
+	dc->res_pool->dccg->funcs->update_clocks(
+			dc->res_pool->dccg,
 			&req_clks,
 			decrease_allowed);
 	pplib_apply_display_requirements(dc, context);
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 20c029089551..71a401f73a58 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -679,8 +679,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -1179,11 +1179,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce110_disp_clk_create(ctx,
+	pool->base.dccg = dce110_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1213,7 +1213,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 				static_clk_info.max_clocks_state;
 
 	{
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 00c0a1ef15eb..ae5b19de559c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -668,8 +668,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -1124,11 +1124,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce112_disp_clk_create(ctx,
+	pool->base.dccg = dce112_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1158,7 +1158,7 @@ static bool construct(
 	 * max_clock_state
 	 */
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 				static_clk_info.max_clocks_state;
 
 	{
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 2d58daccc005..13c388a608c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -494,8 +494,8 @@ static void destruct(struct dce110_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 }
 
 static void read_dce_straps(
@@ -894,11 +894,11 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dce120_disp_clk_create(ctx);
-	if (pool->base.display_clock == NULL) {
+	pool->base.dccg = dce120_dccg_create(ctx);
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
-		goto disp_clk_create_fail;
+		goto dccg_create_fail;
 	}
 
 	pool->base.dmcu = dce_dmcu_create(ctx,
@@ -1011,7 +1011,7 @@ static bool construct(
 
 irqs_create_fail:
 controller_create_fail:
-disp_clk_create_fail:
+dccg_create_fail:
 clk_src_create_fail:
 res_create_fail:
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 48a068964722..70700530aec2 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -683,8 +683,8 @@ static void destruct(struct dce110_resource_pool *pool)
 		}
 	}
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	if (pool->base.irqs != NULL) {
 		dal_irq_service_destroy(&pool->base.irqs);
@@ -822,11 +822,11 @@ static bool dce80_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -852,7 +852,7 @@ static bool dce80_construct(
 		goto res_create_fail;
 	}
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
@@ -1006,11 +1006,11 @@ static bool dce81_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1037,7 +1037,7 @@ static bool dce81_construct(
 	}
 
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
@@ -1187,11 +1187,11 @@ static bool dce83_construct(
 		}
 	}
 
-	pool->base.display_clock = dce_disp_clk_create(ctx,
+	pool->base.dccg = dce_dccg_create(ctx,
 			&disp_clk_regs,
 			&disp_clk_shift,
 			&disp_clk_mask);
-	if (pool->base.display_clock == NULL) {
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto res_create_fail;
@@ -1218,7 +1218,7 @@ static bool dce83_construct(
 	}
 
 	if (dm_pp_get_static_clocks(ctx, &static_clk_info))
-		pool->base.display_clock->max_clks_state =
+		pool->base.dccg->max_clks_state =
 					static_clk_info.max_clocks_state;
 
 	{
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 7f1a7ec9ff5f..f519b98f4b23 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2424,8 +2424,8 @@ static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
 	int dispclk_to_dpp_threshold = determine_dppclk_threshold(dc, context);
 
 	/* set disp clk to dpp clk threshold */
-	dc->res_pool->display_clock->funcs->set_dispclk(
-			dc->res_pool->display_clock,
+	dc->res_pool->dccg->funcs->set_dispclk(
+			dc->res_pool->dccg,
 			dispclk_to_dpp_threshold);
 
 	/* update request dpp clk division option */
@@ -2443,8 +2443,8 @@ static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
 
 	/* If target clk not same as dppclk threshold, set to target clock */
 	if (dispclk_to_dpp_threshold != context->bw.dcn.calc_clk.dispclk_khz) {
-		dc->res_pool->display_clock->funcs->set_dispclk(
-				dc->res_pool->display_clock,
+		dc->res_pool->dccg->funcs->set_dispclk(
+				dc->res_pool->dccg,
 				context->bw.dcn.calc_clk.dispclk_khz);
 	}
 
@@ -2473,8 +2473,8 @@ static void dcn10_set_bandwidth(
 	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		return;
 
-	dc->res_pool->display_clock->funcs->update_clocks(
-			dc->res_pool->display_clock,
+	dc->res_pool->dccg->funcs->update_clocks(
+			dc->res_pool->dccg,
 			&context->bw.dcn.calc_clk,
 			decrease_allowed);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 870eb0aabcc9..8f1ceffa809b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -791,8 +791,8 @@ static void destruct(struct dcn10_resource_pool *pool)
 	if (pool->base.dmcu != NULL)
 		dce_dmcu_destroy(&pool->base.dmcu);
 
-	if (pool->base.display_clock != NULL)
-		dce_disp_clk_destroy(&pool->base.display_clock);
+	if (pool->base.dccg != NULL)
+		dce_dccg_destroy(&pool->base.dccg);
 
 	kfree(pool->base.pp_smu);
 }
@@ -1072,8 +1072,8 @@ static bool construct(
 		}
 	}
 
-	pool->base.display_clock = dcn_disp_clk_create(ctx);
-	if (pool->base.display_clock == NULL) {
+	pool->base.dccg = dcn_dccg_create(ctx);
+	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
 		goto fail;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 4beddca0180c..44c48f3d0a1d 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -163,7 +163,7 @@ struct resource_pool {
 	unsigned int audio_count;
 	struct audio_support audio_support;
 
-	struct display_clock *display_clock;
+	struct dccg *dccg;
 	struct irq_service *irqs;
 
 	struct abm *abm;
@@ -282,7 +282,7 @@ struct dc_state {
 	struct dcn_bw_internal_vars dcn_bw_vars;
 #endif
 
-	struct display_clock *dis_clk;
+	struct dccg *dis_clk;
 
 	struct kref refcount;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
index 8ce106f15647..3c7ccb68ecdb 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/display_clock.h
@@ -36,7 +36,7 @@ struct state_dependent_clocks {
 	int pixel_clk_khz;
 };
 
-struct display_clock {
+struct dccg {
 	struct dc_context *ctx;
 	const struct display_clock_funcs *funcs;
 
@@ -46,13 +46,13 @@ struct display_clock {
 };
 
 struct display_clock_funcs {
-	void (*update_clocks)(struct display_clock *dccg,
+	void (*update_clocks)(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
 			bool safe_to_lower);
-	int (*set_dispclk)(struct display_clock *disp_clk,
+	int (*set_dispclk)(struct dccg *dccg,
 		int requested_clock_khz);
 
-	int (*get_dp_ref_clk_frequency)(struct display_clock *disp_clk);
+	int (*get_dp_ref_clk_frequency)(struct dccg *dccg);
 };
 
 #endif /* __DISPLAY_CLOCK_H__ */
-- 
cgit v1.2.3


From e2e0a1dcd3229eec32ded439f69438a25ec817d6 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 23 May 2018 17:52:04 -0400
Subject: drm/amd/display: move clock programming from set_bandwidth to dccg

This change moves dcn clock programming(with exception of dispclk)
into dccg. This should have no functional effect.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c   |  2 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c    | 57 +++++++++++++-------
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 62 +++++-----------------
 3 files changed, 51 insertions(+), 70 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 2b70ac67e6c2..9acdd9da740e 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -997,7 +997,7 @@ bool dcn_validate_bandwidth(
 		}
 
 		context->bw.dcn.calc_clk.dppclk_khz = context->bw.dcn.calc_clk.dispclk_khz / v->dispclk_dppclk_ratio;
-
+		context->bw.dcn.calc_clk.phyclk_khz = v->phyclk_per_state[v->voltage_level];
 		switch (v->voltage_level) {
 		case 0:
 			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 890a3ec68d49..93e6063c4b97 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -523,14 +523,18 @@ static void dce_clock_read_ss_info(struct dce_dccg *clk_dce)
 	}
 }
 
+static inline bool should_set_clock(bool safe_to_lower, int calc_clk, int cur_clk)
+{
+	return ((safe_to_lower && calc_clk < cur_clk) || calc_clk > cur_clk);
+}
+
 static void dce12_update_clocks(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
 			bool safe_to_lower)
 {
 	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
 
-	if ((new_clocks->dispclk_khz < dccg->clks.dispclk_khz && safe_to_lower)
-			|| new_clocks->dispclk_khz > dccg->clks.dispclk_khz) {
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
 		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
@@ -539,8 +543,7 @@ static void dce12_update_clocks(struct dccg *dccg,
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
 
-	if ((new_clocks->phyclk_khz < dccg->clks.phyclk_khz && safe_to_lower)
-			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz) {
+	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAYPHYCLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
 		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
@@ -553,6 +556,11 @@ static void dcn_update_clocks(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
 			bool safe_to_lower)
 {
+	struct dc *dc = dccg->ctx->dc;
+	struct pp_smu_display_requirement_rv *smu_req_cur =
+			&dc->res_pool->pp_smu_req;
+	struct pp_smu_display_requirement_rv smu_req = *smu_req_cur;
+	struct pp_smu_funcs_rv *pp_smu = dc->res_pool->pp_smu;
 	struct dm_pp_clock_for_voltage_req clock_voltage_req = {0};
 	bool send_request_to_increase = false;
 	bool send_request_to_lower = false;
@@ -566,17 +574,14 @@ static void dcn_update_clocks(struct dccg *dccg,
 #ifdef CONFIG_DRM_AMD_DC_DCN1_0
 	if (send_request_to_increase
 		) {
-		struct dc *core_dc = dccg->ctx->dc;
-
 		/*use dcfclk to request voltage*/
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(core_dc, new_clocks);
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
 #endif
 
-	if ((new_clocks->dispclk_khz < dccg->clks.dispclk_khz && safe_to_lower)
-			|| new_clocks->dispclk_khz > dccg->clks.dispclk_khz) {
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
 		/* TODO: ramp up - dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);*/
@@ -586,8 +591,7 @@ static void dcn_update_clocks(struct dccg *dccg,
 		send_request_to_lower = true;
 	}
 
-	if ((new_clocks->phyclk_khz < dccg->clks.phyclk_khz && safe_to_lower)
-			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz) {
+	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
 		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAYPHYCLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
@@ -596,36 +600,50 @@ static void dcn_update_clocks(struct dccg *dccg,
 		send_request_to_lower = true;
 	}
 
-	if ((new_clocks->fclk_khz < dccg->clks.fclk_khz && safe_to_lower)
-			|| new_clocks->fclk_khz > dccg->clks.fclk_khz) {
+	if (should_set_clock(safe_to_lower, new_clocks->fclk_khz, dccg->clks.fclk_khz)) {
 		dccg->clks.phyclk_khz = new_clocks->fclk_khz;
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_FCLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->fclk_khz;
+		smu_req.hard_min_fclk_khz = new_clocks->fclk_khz;
 
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 		send_request_to_lower = true;
 	}
 
-	if ((new_clocks->dcfclk_khz < dccg->clks.dcfclk_khz && safe_to_lower)
-			|| new_clocks->dcfclk_khz > dccg->clks.dcfclk_khz) {
+	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, dccg->clks.dcfclk_khz)) {
 		dccg->clks.phyclk_khz = new_clocks->dcfclk_khz;
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->dcfclk_khz;
+		smu_req.hard_min_dcefclk_khz = new_clocks->dcfclk_khz;
 
 		send_request_to_lower = true;
 	}
 
+	if (should_set_clock(safe_to_lower,
+			new_clocks->dcfclk_deep_sleep_khz, dccg->clks.dcfclk_deep_sleep_khz)) {
+		dccg->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz;
+		smu_req.min_deep_sleep_dcefclk_mhz = new_clocks->dcfclk_deep_sleep_khz;
+	}
+
 #ifdef CONFIG_DRM_AMD_DC_DCN1_0
 	if (!send_request_to_increase && send_request_to_lower
 		) {
-		struct dc *core_dc = dccg->ctx->dc;
-
 		/*use dcfclk to request voltage*/
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(core_dc, new_clocks);
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
 #endif
+
+	if (new_clocks->phyclk_khz)
+		smu_req.display_count = 1;
+	else
+		smu_req.display_count = 0;
+
+	if (pp_smu->set_display_requirement)
+		pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
+
+	*smu_req_cur = smu_req;
 }
 
 static void dce_update_clocks(struct dccg *dccg,
@@ -642,8 +660,7 @@ static void dce_update_clocks(struct dccg *dccg,
 			dccg->cur_min_clks_state = level_change_req.power_level;
 	}
 
-	if ((new_clocks->dispclk_khz < dccg->clks.dispclk_khz && safe_to_lower)
-			|| new_clocks->dispclk_khz > dccg->clks.dispclk_khz) {
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
 		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
 		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index f519b98f4b23..09c7007868e8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2153,11 +2153,11 @@ static void dcn10_pplib_apply_display_requirements(
 {
 	struct dm_pp_display_configuration *pp_display_cfg = &context->pp_display_cfg;
 
-	pp_display_cfg->min_engine_clock_khz = context->bw.dcn.cur_clk.dcfclk_khz;
-	pp_display_cfg->min_memory_clock_khz = context->bw.dcn.cur_clk.fclk_khz;
-	pp_display_cfg->min_engine_clock_deep_sleep_khz = context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz;
-	pp_display_cfg->min_dcfc_deep_sleep_clock_khz = context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz;
-	pp_display_cfg->min_dcfclock_khz = context->bw.dcn.cur_clk.dcfclk_khz;
+	pp_display_cfg->min_engine_clock_khz = dc->res_pool->dccg->clks.dcfclk_khz;
+	pp_display_cfg->min_memory_clock_khz = dc->res_pool->dccg->clks.fclk_khz;
+	pp_display_cfg->min_engine_clock_deep_sleep_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
+	pp_display_cfg->min_dcfc_deep_sleep_clock_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
+	pp_display_cfg->min_dcfclock_khz = dc->res_pool->dccg->clks.dcfclk_khz;
 	pp_display_cfg->disp_clk_khz = context->bw.dcn.cur_clk.dispclk_khz;
 	dce110_fill_display_configs(context, pp_display_cfg);
 
@@ -2361,11 +2361,6 @@ static void dcn10_apply_ctx_for_surface(
 */
 }
 
-static inline bool should_set_clock(bool decrease_allowed, int calc_clk, int cur_clk)
-{
-	return ((decrease_allowed && calc_clk < cur_clk) || calc_clk > cur_clk);
-}
-
 static int determine_dppclk_threshold(struct dc *dc, struct dc_state *context)
 {
 	bool request_dpp_div = context->bw.dcn.calc_clk.dispclk_khz >
@@ -2456,16 +2451,16 @@ static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
 			context->bw.dcn.calc_clk.max_supported_dppclk_khz;
 }
 
+static inline bool should_set_clock(bool safe_to_lower, int calc_clk, int cur_clk)
+{
+	return ((safe_to_lower && calc_clk < cur_clk) || calc_clk > cur_clk);
+}
+
 static void dcn10_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	struct pp_smu_display_requirement_rv *smu_req_cur =
-			&dc->res_pool->pp_smu_req;
-	struct pp_smu_display_requirement_rv smu_req = *smu_req_cur;
-	struct pp_smu_funcs_rv *pp_smu = dc->res_pool->pp_smu;
-
 	if (dc->debug.sanity_checks) {
 		dcn10_verify_allow_pstate_change_high(dc);
 	}
@@ -2473,45 +2468,14 @@ static void dcn10_set_bandwidth(
 	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		return;
 
+	if (context->stream_count == 0)
+		context->bw.dcn.calc_clk.phyclk_khz = 0;
+
 	dc->res_pool->dccg->funcs->update_clocks(
 			dc->res_pool->dccg,
 			&context->bw.dcn.calc_clk,
 			decrease_allowed);
 
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			dc->current_state->bw.dcn.cur_clk.dcfclk_khz)) {
-		context->bw.dcn.cur_clk.dcfclk_khz =
-				context->bw.dcn.calc_clk.dcfclk_khz;
-		smu_req.hard_min_dcefclk_khz =
-				context->bw.dcn.calc_clk.dcfclk_khz;
-	}
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			dc->current_state->bw.dcn.cur_clk.dcfclk_deep_sleep_khz)) {
-		context->bw.dcn.cur_clk.dcfclk_deep_sleep_khz =
-				context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz;
-	}
-
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.calc_clk.fclk_khz,
-			dc->current_state->bw.dcn.cur_clk.fclk_khz)) {
-		context->bw.dcn.cur_clk.fclk_khz =
-				context->bw.dcn.calc_clk.fclk_khz;
-		smu_req.hard_min_fclk_khz = context->bw.dcn.calc_clk.fclk_khz;
-	}
-
-	smu_req.display_count = context->stream_count;
-
-	if (pp_smu->set_display_requirement)
-		pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
-
-	*smu_req_cur = smu_req;
-
 	/* make sure dcf clk is before dpp clk to
 	 * make sure we have enough voltage to run dpp clk
 	 */
-- 
cgit v1.2.3


From 734b096096ac860b5a72c52e8a6a8b81fa9e016c Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Mon, 9 Apr 2018 09:48:15 -0400
Subject: drm/amd/display: Adding dm-pp clocks getting by voltage

Function to get clock levels by voltage from PPLib

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 43 +++++++++++++++++++++-
 1 file changed, 41 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index e861929dd981..bc15ee692d37 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -253,6 +253,34 @@ static void pp_to_dc_clock_levels_with_latency(
 	}
 }
 
+static void pp_to_dc_clock_levels_with_voltage(
+		const struct pp_clock_levels_with_voltage *pp_clks,
+		struct dm_pp_clock_levels_with_voltage *clk_level_info,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->num_levels,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		clk_level_info->num_levels = pp_clks->num_levels;
+
+	DRM_INFO("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < clk_level_info->num_levels; i++) {
+		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->data[i].clocks_in_khz);
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		clk_level_info->data[i].voltage_in_mv = pp_clks->data[i].voltage_in_mv;
+	}
+}
+
+
 bool dm_pp_get_clock_levels_by_type(
 		const struct dc_context *ctx,
 		enum dm_pp_clock_type clk_type,
@@ -353,8 +381,19 @@ bool dm_pp_get_clock_levels_by_type_with_voltage(
 	enum dm_pp_clock_type clk_type,
 	struct dm_pp_clock_levels_with_voltage *clk_level_info)
 {
-	/* TODO: to be implemented */
-	return false;
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct pp_clock_levels_with_voltage pp_clk_info = {0};
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs->get_clock_by_type_with_voltage(pp_handle,
+						     dc_to_pp_clock_type(clk_type),
+						     &pp_clk_info))
+		return false;
+
+	pp_to_dc_clock_levels_with_voltage(&pp_clk_info, clk_level_info, clk_type);
+
+	return true;
 }
 
 bool dm_pp_notify_wm_clock_changes(
-- 
cgit v1.2.3


From 28825c841bfd993bbe5c9466533baca8520f08c3 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Mon, 9 Apr 2018 13:40:00 -0400
Subject: drm/amd/display: Apply clock for voltage request

Translate dm_pp tructure to pp type
Call PP lib to apply clock voltage request for display

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 31 ++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index bc15ee692d37..2eef154accf9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -416,8 +416,35 @@ bool dm_pp_apply_clock_for_voltage_request(
 	const struct dc_context *ctx,
 	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
 {
-	/* TODO: to be implemented */
-	return false;
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct pp_display_clock_request *pp_clock_request = {0};
+	int ret = 0;
+	switch (clock_for_voltage_req->clk_type) {
+	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
+		pp_clock_request->clock_type = amd_pp_disp_clock;
+		break;
+
+	case DM_PP_CLOCK_TYPE_DCEFCLK:
+		pp_clock_request->clock_type = amd_pp_dcef_clock;
+		break;
+
+	case DM_PP_CLOCK_TYPE_PIXELCLK:
+		pp_clock_request->clock_type = amd_pp_pixel_clock;
+		break;
+
+	default:
+		return false;
+	}
+
+	pp_clock_request->clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
+
+	if (adev->powerplay.pp_funcs->display_clock_voltage_request)
+		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
+			adev->powerplay.pp_handle,
+			pp_clock_request);
+	if (ret)
+		return false;
+	return true;
 }
 
 bool dm_pp_get_static_clocks(
-- 
cgit v1.2.3


From db4e525304ddf272e45542cbfd820840cf6ac874 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Wed, 18 Apr 2018 17:19:23 -0400
Subject: drm/amd/display: Adding Get static clocks for dm_pp interface

Adding a call to powerplay to get system clocks and translate to dm structure

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 2eef154accf9..dbd714d0936e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -451,8 +451,22 @@ bool dm_pp_get_static_clocks(
 	const struct dc_context *ctx,
 	struct dm_pp_static_clock_info *static_clk_info)
 {
-	/* TODO: to be implemented */
-	return false;
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct amd_pp_clock_info *pp_clk_info = {0};
+	int ret = 0;
+
+	if (adev->powerplay.pp_funcs->get_current_clocks)
+		ret = adev->powerplay.pp_funcs->get_current_clocks(
+			adev->powerplay.pp_handle,
+			pp_clk_info);
+	if (ret)
+		return false;
+
+	static_clk_info->max_clocks_state = pp_clk_info->max_clocks_state;
+	static_clk_info->max_mclk_khz = pp_clk_info->max_memory_clock;
+	static_clk_info->max_sclk_khz = pp_clk_info->max_engine_clock;
+
+	return true;
 }
 
 void dm_pp_get_funcs_rv(
-- 
cgit v1.2.3


From 30f0ea6d0901c1ff9e7a4d986959e3e4008ee8e1 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 8 May 2018 12:25:15 -0400
Subject: drm/amd/display: dal 3.1.48

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 8ba90a75d128..82e0f55bc3e4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.47"
+#define DC_VER "3.1.48"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 92276a06f9c3d29183c7bdf46a6dbbc9c00f7acf Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Wed, 11 Apr 2018 14:52:41 -0400
Subject: drm/amd/display: Introduce pp-smu raven functions

DM powerplay calls for DCN10 allowing to bypass PPLib
and call directly to the SMU functions.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 88 +++++++++++++++++++++-
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c   |  4 +-
 drivers/gpu/drm/amd/display/dc/dm_pp_smu.h         |  6 +-
 3 files changed, 92 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index dbd714d0936e..e3a9bad4b404 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -34,6 +34,11 @@
 #include "amdgpu_dm.h"
 #include "amdgpu_dm_irq.h"
 #include "amdgpu_pm.h"
+#include "dm_pp_smu.h"
+#include "../../powerplay/inc/hwmgr.h"
+#include "../../powerplay/hwmgr/smu10_hwmgr.h"
+
+
 
 unsigned long long dm_get_elapse_time_in_ns(struct dc_context *ctx,
 		unsigned long long current_time_stamp,
@@ -469,9 +474,90 @@ bool dm_pp_get_static_clocks(
 	return true;
 }
 
+void pp_rv_set_display_requirement(struct pp_smu *pp,
+		struct pp_smu_display_requirement_rv *req)
+{
+	struct amdgpu_device *adev = pp->ctx->driver_context;
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+	int ret = 0;
+	if (hwmgr->hwmgr_func->set_deep_sleep_dcefclk)
+		ret = hwmgr->hwmgr_func->set_deep_sleep_dcefclk(hwmgr, req->hard_min_dcefclk_khz/10);
+	if (hwmgr->hwmgr_func->set_active_display_count)
+		ret = hwmgr->hwmgr_func->set_active_display_count(hwmgr, req->display_count);
+
+	//store_cc6 is not yet implemented in SMU level
+}
+
+void pp_rv_set_wm_ranges(struct pp_smu *pp,
+		struct pp_smu_wm_range_sets *ranges)
+{
+	struct amdgpu_device *adev = pp->ctx->driver_context;
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+	struct pp_wm_sets_with_clock_ranges_soc15 ranges_soc15 = {0};
+	int i = 0;
+
+	if (!hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges ||
+			!pp || !ranges)
+		return;
+
+	//not entirely sure if thats a correct assignment
+	ranges_soc15.num_wm_sets_dmif = ranges->num_reader_wm_sets;
+	ranges_soc15.num_wm_sets_mcif = ranges->num_writer_wm_sets;
+
+	for (i = 0; i < ranges_soc15.num_wm_sets_dmif; i++) {
+		if (ranges->reader_wm_sets[i].wm_inst > 3)
+			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
+		else
+			ranges_soc15.wm_sets_dmif[i].wm_set_id =
+					ranges->reader_wm_sets[i].wm_inst;
+		ranges_soc15.wm_sets_dmif[i].wm_max_dcefclk_in_khz =
+				ranges->reader_wm_sets[i].max_drain_clk_khz;
+		ranges_soc15.wm_sets_dmif[i].wm_min_dcefclk_in_khz =
+				ranges->reader_wm_sets[i].min_drain_clk_khz;
+		ranges_soc15.wm_sets_dmif[i].wm_max_memclk_in_khz =
+				ranges->reader_wm_sets[i].max_fill_clk_khz;
+		ranges_soc15.wm_sets_dmif[i].wm_min_memclk_in_khz =
+				ranges->reader_wm_sets[i].min_fill_clk_khz;
+	}
+
+	for (i = 0; i < ranges_soc15.num_wm_sets_mcif; i++) {
+		if (ranges->writer_wm_sets[i].wm_inst > 3)
+			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
+		else
+			ranges_soc15.wm_sets_mcif[i].wm_set_id =
+					ranges->writer_wm_sets[i].wm_inst;
+		ranges_soc15.wm_sets_mcif[i].wm_max_socclk_in_khz =
+				ranges->writer_wm_sets[i].max_fill_clk_khz;
+		ranges_soc15.wm_sets_mcif[i].wm_min_socclk_in_khz =
+				ranges->writer_wm_sets[i].min_fill_clk_khz;
+		ranges_soc15.wm_sets_mcif[i].wm_max_memclk_in_khz =
+				ranges->writer_wm_sets[i].max_fill_clk_khz;
+		ranges_soc15.wm_sets_mcif[i].wm_min_memclk_in_khz =
+				ranges->writer_wm_sets[i].min_fill_clk_khz;
+	}
+
+	hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges(hwmgr, &ranges_soc15);
+
+}
+
+void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
+{
+	struct amdgpu_device *adev = pp->ctx->driver_context;
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+
+	if (hwmgr->hwmgr_func->smus_notify_pwe)
+		hwmgr->hwmgr_func->smus_notify_pwe(hwmgr);
+}
+
 void dm_pp_get_funcs_rv(
 		struct dc_context *ctx,
 		struct pp_smu_funcs_rv *funcs)
-{}
+{
+	funcs->pp_smu.ctx = ctx;
+	funcs->set_display_requirement = pp_rv_set_display_requirement;
+	funcs->set_wm_ranges = pp_rv_set_wm_ranges;
+	funcs->set_pme_wa_enable = pp_rv_set_pme_wa_enable;
+}
+
 
 /**** end of power component interfaces ****/
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 9acdd9da740e..9ce329e8f287 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1358,8 +1358,8 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 	/* SOCCLK does not affect anytihng but writeback for DCN so for now we dont
 	 * care what the value is, hence min to overdrive level
 	 */
-	ranges.num_reader_wm_sets = WM_COUNT;
-	ranges.num_writer_wm_sets = WM_COUNT;
+	ranges.num_reader_wm_sets = WM_SET_COUNT;
+	ranges.num_writer_wm_sets = WM_SET_COUNT;
 	ranges.reader_wm_sets[0].wm_inst = WM_A;
 	ranges.reader_wm_sets[0].min_drain_clk_khz = min_dcfclk_khz;
 	ranges.reader_wm_sets[0].max_drain_clk_khz = max_dcfclk_khz;
diff --git a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
index eac4bfe12257..58ed2055ef9f 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_pp_smu.h
@@ -40,7 +40,7 @@ enum wm_set_id {
 	WM_B,
 	WM_C,
 	WM_D,
-	WM_COUNT,
+	WM_SET_COUNT,
 };
 
 struct pp_smu_wm_set_range {
@@ -53,10 +53,10 @@ struct pp_smu_wm_set_range {
 
 struct pp_smu_wm_range_sets {
 	uint32_t num_reader_wm_sets;
-	struct pp_smu_wm_set_range reader_wm_sets[WM_COUNT];
+	struct pp_smu_wm_set_range reader_wm_sets[WM_SET_COUNT];
 
 	uint32_t num_writer_wm_sets;
-	struct pp_smu_wm_set_range writer_wm_sets[WM_COUNT];
+	struct pp_smu_wm_set_range writer_wm_sets[WM_SET_COUNT];
 };
 
 struct pp_smu_display_requirement_rv {
-- 
cgit v1.2.3


From 2dfa76d328630de3dd4fc09b296ee9771ba13e39 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Mon, 28 May 2018 18:09:52 -0400
Subject: drm/amd/display: remove invalid assert when no max_pixel_clk is found

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 34eb7a33851b..4cdf86690d19 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1779,9 +1779,6 @@ static uint32_t get_max_pixel_clock_for_all_paths(
 				pipe_ctx->stream_res.pix_clk_params.requested_pix_clk;
 	}
 
-	if (max_pix_clk == 0)
-		ASSERT(0);
-
 	return max_pix_clk;
 }
 
-- 
cgit v1.2.3


From 0d8be24134eddaf5acc937f59d58e62d869f0a6f Mon Sep 17 00:00:00 2001
From: Yongqiang Sun <yongqiang.sun@amd.com>
Date: Tue, 29 May 2018 07:18:27 -0700
Subject: drm/amd/display: Use tg count for opp init.

In case of tg count not equal to FE pipe count, if use pipe count to iterate
the tgs, it will cause BSOD.

Signed-off-by: Yongqiang Sun <yongqiang.sun@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 09c7007868e8..64ca503cab42 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1010,7 +1010,7 @@ static void dcn10_init_hw(struct dc *dc)
 	/* Reset all MPCC muxes */
 	dc->res_pool->mpc->funcs->mpc_init(dc->res_pool->mpc);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		struct timing_generator *tg = dc->res_pool->timing_generators[i];
 		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
 		struct hubp *hubp = dc->res_pool->hubps[i];
-- 
cgit v1.2.3


From 9654a28b3ac075f2454d5867d490b0c2f7cde9fd Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Tue, 29 May 2018 16:15:12 -0400
Subject: drm/amd/display: Use local structs instead of struct pointers

Change struct pointers to creating structs on a stack.
Thats fixing a mistake in a previous patch introducing dm_pplib functions

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index e3a9bad4b404..f5d626e8bf51 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -422,31 +422,31 @@ bool dm_pp_apply_clock_for_voltage_request(
 	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
 {
 	struct amdgpu_device *adev = ctx->driver_context;
-	struct pp_display_clock_request *pp_clock_request = {0};
+	struct pp_display_clock_request pp_clock_request = {0};
 	int ret = 0;
 	switch (clock_for_voltage_req->clk_type) {
 	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		pp_clock_request->clock_type = amd_pp_disp_clock;
+		pp_clock_request.clock_type = amd_pp_disp_clock;
 		break;
 
 	case DM_PP_CLOCK_TYPE_DCEFCLK:
-		pp_clock_request->clock_type = amd_pp_dcef_clock;
+		pp_clock_request.clock_type = amd_pp_dcef_clock;
 		break;
 
 	case DM_PP_CLOCK_TYPE_PIXELCLK:
-		pp_clock_request->clock_type = amd_pp_pixel_clock;
+		pp_clock_request.clock_type = amd_pp_pixel_clock;
 		break;
 
 	default:
 		return false;
 	}
 
-	pp_clock_request->clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
+	pp_clock_request.clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
 
 	if (adev->powerplay.pp_funcs->display_clock_voltage_request)
 		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
 			adev->powerplay.pp_handle,
-			pp_clock_request);
+			&pp_clock_request);
 	if (ret)
 		return false;
 	return true;
@@ -457,19 +457,19 @@ bool dm_pp_get_static_clocks(
 	struct dm_pp_static_clock_info *static_clk_info)
 {
 	struct amdgpu_device *adev = ctx->driver_context;
-	struct amd_pp_clock_info *pp_clk_info = {0};
+	struct amd_pp_clock_info pp_clk_info = {0};
 	int ret = 0;
 
 	if (adev->powerplay.pp_funcs->get_current_clocks)
 		ret = adev->powerplay.pp_funcs->get_current_clocks(
 			adev->powerplay.pp_handle,
-			pp_clk_info);
+			&pp_clk_info);
 	if (ret)
 		return false;
 
-	static_clk_info->max_clocks_state = pp_clk_info->max_clocks_state;
-	static_clk_info->max_mclk_khz = pp_clk_info->max_memory_clock;
-	static_clk_info->max_sclk_khz = pp_clk_info->max_engine_clock;
+	static_clk_info->max_clocks_state = pp_clk_info.max_clocks_state;
+	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock;
+	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock;
 
 	return true;
 }
-- 
cgit v1.2.3


From 25684c59aff5147d48cc7ce04d4d75a15c5a3a71 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Tue, 29 May 2018 16:20:37 -0400
Subject: drm/amd/display: Add clock types to applying clk for voltage

Add DCF and FCLK clock case statements for changing raven's
clocks for voltage request.
Also maintain DCEF clock for DCE120 calls.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index f5d626e8bf51..0ac428299f5f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -433,10 +433,18 @@ bool dm_pp_apply_clock_for_voltage_request(
 		pp_clock_request.clock_type = amd_pp_dcef_clock;
 		break;
 
+	case DM_PP_CLOCK_TYPE_DCFCLK:
+		pp_clock_request.clock_type = amd_pp_dcf_clock;
+		break;
+
 	case DM_PP_CLOCK_TYPE_PIXELCLK:
 		pp_clock_request.clock_type = amd_pp_pixel_clock;
 		break;
 
+	case DM_PP_CLOCK_TYPE_FCLK:
+		pp_clock_request.clock_type = amd_pp_f_clock;
+		break;
+
 	default:
 		return false;
 	}
-- 
cgit v1.2.3


From d578839ca014e5f4e6d540caadc0b84d50a8977f Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 23 May 2018 18:02:27 -0400
Subject: drm/amd/display: get rid of cur_clks from dcn_bw_output

Cleans up dcn_bw_output to only contain calculated info,
actual programmed values will now be stored in respective blocks.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c   | 28 +++----
 drivers/gpu/drm/amd/display/dc/core/dc_debug.c     | 24 +++---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c      |  2 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c    |  4 +-
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 85 +++++++++++-----------
 drivers/gpu/drm/amd/display/dc/inc/core_types.h    |  3 +-
 6 files changed, 72 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 9ce329e8f287..b8195e5a0676 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -977,42 +977,42 @@ bool dcn_validate_bandwidth(
 
 		display_pipe_configuration(v);
 		calc_wm_sets_and_perf_params(context, v);
-		context->bw.dcn.calc_clk.fclk_khz = (int)(bw_consumed * 1000000 /
+		context->bw.dcn.clk.fclk_khz = (int)(bw_consumed * 1000000 /
 				(ddr4_dram_factor_single_Channel * v->number_of_channels));
 		if (bw_consumed == v->fabric_and_dram_bandwidth_vmin0p65) {
-			context->bw.dcn.calc_clk.fclk_khz = (int)(bw_consumed * 1000000 / 32);
+			context->bw.dcn.clk.fclk_khz = (int)(bw_consumed * 1000000 / 32);
 		}
 
-		context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz = (int)(v->dcf_clk_deep_sleep * 1000);
-		context->bw.dcn.calc_clk.dcfclk_khz = (int)(v->dcfclk * 1000);
+		context->bw.dcn.clk.dcfclk_deep_sleep_khz = (int)(v->dcf_clk_deep_sleep * 1000);
+		context->bw.dcn.clk.dcfclk_khz = (int)(v->dcfclk * 1000);
 
-		context->bw.dcn.calc_clk.dispclk_khz = (int)(v->dispclk * 1000);
+		context->bw.dcn.clk.dispclk_khz = (int)(v->dispclk * 1000);
 		if (dc->debug.max_disp_clk == true)
-			context->bw.dcn.calc_clk.dispclk_khz = (int)(dc->dcn_soc->max_dispclk_vmax0p9 * 1000);
+			context->bw.dcn.clk.dispclk_khz = (int)(dc->dcn_soc->max_dispclk_vmax0p9 * 1000);
 
-		if (context->bw.dcn.calc_clk.dispclk_khz <
+		if (context->bw.dcn.clk.dispclk_khz <
 				dc->debug.min_disp_clk_khz) {
-			context->bw.dcn.calc_clk.dispclk_khz =
+			context->bw.dcn.clk.dispclk_khz =
 					dc->debug.min_disp_clk_khz;
 		}
 
-		context->bw.dcn.calc_clk.dppclk_khz = context->bw.dcn.calc_clk.dispclk_khz / v->dispclk_dppclk_ratio;
-		context->bw.dcn.calc_clk.phyclk_khz = v->phyclk_per_state[v->voltage_level];
+		context->bw.dcn.clk.dppclk_khz = context->bw.dcn.clk.dispclk_khz / v->dispclk_dppclk_ratio;
+		context->bw.dcn.clk.phyclk_khz = v->phyclk_per_state[v->voltage_level];
 		switch (v->voltage_level) {
 		case 0:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmin0p65 * 1000);
 			break;
 		case 1:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmid0p72 * 1000);
 			break;
 		case 2:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vnom0p8 * 1000);
 			break;
 		default:
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz =
 					(int)(dc->dcn_soc->max_dppclk_vmax0p9 * 1000);
 			break;
 		}
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
index 267c76766dea..e1ebdf7b5eaf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -352,19 +352,19 @@ void context_clock_trace(
 	DC_LOGGER_INIT(dc->ctx->logger);
 	CLOCK_TRACE("Current: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
-			context->bw.dcn.calc_clk.dispclk_khz,
-			context->bw.dcn.calc_clk.dppclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			context->bw.dcn.calc_clk.fclk_khz,
-			context->bw.dcn.calc_clk.socclk_khz);
+			context->bw.dcn.clk.dispclk_khz,
+			context->bw.dcn.clk.dppclk_khz,
+			context->bw.dcn.clk.dcfclk_khz,
+			context->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			context->bw.dcn.clk.fclk_khz,
+			context->bw.dcn.clk.socclk_khz);
 	CLOCK_TRACE("Calculated: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
-			context->bw.dcn.calc_clk.dispclk_khz,
-			context->bw.dcn.calc_clk.dppclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_khz,
-			context->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			context->bw.dcn.calc_clk.fclk_khz,
-			context->bw.dcn.calc_clk.socclk_khz);
+			context->bw.dcn.clk.dispclk_khz,
+			context->bw.dcn.clk.dppclk_khz,
+			context->bw.dcn.clk.dcfclk_khz,
+			context->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			context->bw.dcn.clk.fclk_khz,
+			context->bw.dcn.clk.socclk_khz);
 #endif
 }
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 779d1926a756..8eb8b8768465 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1284,7 +1284,7 @@ static enum dc_status enable_link_dp(
 		max_link_rate = LINK_RATE_HIGH3;
 
 	if (link_settings.link_rate == max_link_rate) {
-		struct dc_clocks clocks = state->bw.dcn.calc_clk;
+		struct dc_clocks clocks = state->bw.dcn.clk;
 
 		/* dce/dcn compat, do not update dispclk */
 		clocks.dispclk_khz = 0;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 93e6063c4b97..6b6570ea998d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -584,8 +584,8 @@ static void dcn_update_clocks(struct dccg *dccg,
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
-		/* TODO: ramp up - dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);*/
-		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+		/* TODO: ramp up - dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;*/
 
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 		send_request_to_lower = true;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 64ca503cab42..6ab00615c4c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -337,13 +337,13 @@ void dcn10_log_hw_state(struct dc *dc)
 
 	DTN_INFO("\nCALCULATED Clocks: dcfclk_khz:%d  dcfclk_deep_sleep_khz:%d  dispclk_khz:%d\n"
 		"dppclk_khz:%d  max_supported_dppclk_khz:%d  fclk_khz:%d  socclk_khz:%d\n\n",
-			dc->current_state->bw.dcn.calc_clk.dcfclk_khz,
-			dc->current_state->bw.dcn.calc_clk.dcfclk_deep_sleep_khz,
-			dc->current_state->bw.dcn.calc_clk.dispclk_khz,
-			dc->current_state->bw.dcn.calc_clk.dppclk_khz,
-			dc->current_state->bw.dcn.calc_clk.max_supported_dppclk_khz,
-			dc->current_state->bw.dcn.calc_clk.fclk_khz,
-			dc->current_state->bw.dcn.calc_clk.socclk_khz);
+			dc->current_state->bw.dcn.clk.dcfclk_khz,
+			dc->current_state->bw.dcn.clk.dcfclk_deep_sleep_khz,
+			dc->current_state->bw.dcn.clk.dispclk_khz,
+			dc->current_state->bw.dcn.clk.dppclk_khz,
+			dc->current_state->bw.dcn.clk.max_supported_dppclk_khz,
+			dc->current_state->bw.dcn.clk.fclk_khz,
+			dc->current_state->bw.dcn.clk.socclk_khz);
 
 	log_mpc_crc(dc);
 
@@ -1952,18 +1952,17 @@ static void update_dchubp_dpp(
 	 * divided by 2
 	 */
 	if (plane_state->update_flags.bits.full_update) {
-		bool should_divided_by_2 = context->bw.dcn.calc_clk.dppclk_khz <=
-				context->bw.dcn.cur_clk.dispclk_khz / 2;
+		bool should_divided_by_2 = context->bw.dcn.clk.dppclk_khz <=
+				dc->res_pool->dccg->clks.dispclk_khz / 2;
 
 		dpp->funcs->dpp_dppclk_control(
 				dpp,
 				should_divided_by_2,
 				true);
 
-		dc->current_state->bw.dcn.cur_clk.dppclk_khz =
-				should_divided_by_2 ?
-				context->bw.dcn.cur_clk.dispclk_khz / 2 :
-				context->bw.dcn.cur_clk.dispclk_khz;
+		dc->res_pool->dccg->clks.dppclk_khz = should_divided_by_2 ?
+						dc->res_pool->dccg->clks.dispclk_khz / 2 :
+							dc->res_pool->dccg->clks.dispclk_khz;
 	}
 
 	/* TODO: Need input parameter to tell current DCHUB pipe tie to which OTG
@@ -2158,7 +2157,7 @@ static void dcn10_pplib_apply_display_requirements(
 	pp_display_cfg->min_engine_clock_deep_sleep_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
 	pp_display_cfg->min_dcfc_deep_sleep_clock_khz = dc->res_pool->dccg->clks.dcfclk_deep_sleep_khz;
 	pp_display_cfg->min_dcfclock_khz = dc->res_pool->dccg->clks.dcfclk_khz;
-	pp_display_cfg->disp_clk_khz = context->bw.dcn.cur_clk.dispclk_khz;
+	pp_display_cfg->disp_clk_khz = dc->res_pool->dccg->clks.dispclk_khz;
 	dce110_fill_display_configs(context, pp_display_cfg);
 
 	if (memcmp(&dc->prev_display_config, pp_display_cfg, sizeof(
@@ -2363,29 +2362,29 @@ static void dcn10_apply_ctx_for_surface(
 
 static int determine_dppclk_threshold(struct dc *dc, struct dc_state *context)
 {
-	bool request_dpp_div = context->bw.dcn.calc_clk.dispclk_khz >
-			context->bw.dcn.calc_clk.dppclk_khz;
-	bool dispclk_increase = context->bw.dcn.calc_clk.dispclk_khz >
-			context->bw.dcn.cur_clk.dispclk_khz;
-	int disp_clk_threshold = context->bw.dcn.calc_clk.max_supported_dppclk_khz;
-	bool cur_dpp_div = context->bw.dcn.cur_clk.dispclk_khz >
-			context->bw.dcn.cur_clk.dppclk_khz;
+	bool request_dpp_div = context->bw.dcn.clk.dispclk_khz >
+			context->bw.dcn.clk.dppclk_khz;
+	bool dispclk_increase = context->bw.dcn.clk.dispclk_khz >
+			dc->res_pool->dccg->clks.dispclk_khz;
+	int disp_clk_threshold = context->bw.dcn.clk.max_supported_dppclk_khz;
+	bool cur_dpp_div = dc->res_pool->dccg->clks.dispclk_khz >
+			dc->res_pool->dccg->clks.dppclk_khz;
 
 	/* increase clock, looking for div is 0 for current, request div is 1*/
 	if (dispclk_increase) {
 		/* already divided by 2, no need to reach target clk with 2 steps*/
 		if (cur_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
+			return context->bw.dcn.clk.dispclk_khz;
 
 		/* request disp clk is lower than maximum supported dpp clk,
 		 * no need to reach target clk with two steps.
 		 */
-		if (context->bw.dcn.calc_clk.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.calc_clk.dispclk_khz;
+		if (context->bw.dcn.clk.dispclk_khz <= disp_clk_threshold)
+			return context->bw.dcn.clk.dispclk_khz;
 
 		/* target dpp clk not request divided by 2, still within threshold */
 		if (!request_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
+			return context->bw.dcn.clk.dispclk_khz;
 
 	} else {
 		/* decrease clock, looking for current dppclk divided by 2,
@@ -2394,17 +2393,17 @@ static int determine_dppclk_threshold(struct dc *dc, struct dc_state *context)
 
 		/* current dpp clk not divided by 2, no need to ramp*/
 		if (!cur_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
+			return context->bw.dcn.clk.dispclk_khz;
 
 		/* current disp clk is lower than current maximum dpp clk,
 		 * no need to ramp
 		 */
-		if (context->bw.dcn.cur_clk.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.calc_clk.dispclk_khz;
+		if (dc->res_pool->dccg->clks.dispclk_khz <= disp_clk_threshold)
+			return context->bw.dcn.clk.dispclk_khz;
 
 		/* request dpp clk need to be divided by 2 */
 		if (request_dpp_div)
-			return context->bw.dcn.calc_clk.dispclk_khz;
+			return context->bw.dcn.clk.dispclk_khz;
 	}
 
 	return disp_clk_threshold;
@@ -2413,8 +2412,8 @@ static int determine_dppclk_threshold(struct dc *dc, struct dc_state *context)
 static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
 {
 	int i;
-	bool request_dpp_div = context->bw.dcn.calc_clk.dispclk_khz >
-				context->bw.dcn.calc_clk.dppclk_khz;
+	bool request_dpp_div = context->bw.dcn.clk.dispclk_khz >
+				context->bw.dcn.clk.dppclk_khz;
 
 	int dispclk_to_dpp_threshold = determine_dppclk_threshold(dc, context);
 
@@ -2437,18 +2436,18 @@ static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
 	}
 
 	/* If target clk not same as dppclk threshold, set to target clock */
-	if (dispclk_to_dpp_threshold != context->bw.dcn.calc_clk.dispclk_khz) {
+	if (dispclk_to_dpp_threshold != context->bw.dcn.clk.dispclk_khz) {
 		dc->res_pool->dccg->funcs->set_dispclk(
 				dc->res_pool->dccg,
-				context->bw.dcn.calc_clk.dispclk_khz);
+				context->bw.dcn.clk.dispclk_khz);
 	}
 
-	context->bw.dcn.cur_clk.dispclk_khz =
-			context->bw.dcn.calc_clk.dispclk_khz;
-	context->bw.dcn.cur_clk.dppclk_khz =
-			context->bw.dcn.calc_clk.dppclk_khz;
-	context->bw.dcn.cur_clk.max_supported_dppclk_khz =
-			context->bw.dcn.calc_clk.max_supported_dppclk_khz;
+	dc->res_pool->dccg->clks.dispclk_khz =
+			context->bw.dcn.clk.dispclk_khz;
+	dc->res_pool->dccg->clks.dppclk_khz =
+			context->bw.dcn.clk.dppclk_khz;
+	dc->res_pool->dccg->clks.max_supported_dppclk_khz =
+			context->bw.dcn.clk.max_supported_dppclk_khz;
 }
 
 static inline bool should_set_clock(bool safe_to_lower, int calc_clk, int cur_clk)
@@ -2469,11 +2468,11 @@ static void dcn10_set_bandwidth(
 		return;
 
 	if (context->stream_count == 0)
-		context->bw.dcn.calc_clk.phyclk_khz = 0;
+		context->bw.dcn.clk.phyclk_khz = 0;
 
 	dc->res_pool->dccg->funcs->update_clocks(
 			dc->res_pool->dccg,
-			&context->bw.dcn.calc_clk,
+			&context->bw.dcn.clk,
 			decrease_allowed);
 
 	/* make sure dcf clk is before dpp clk to
@@ -2481,8 +2480,8 @@ static void dcn10_set_bandwidth(
 	 */
 	if (should_set_clock(
 			decrease_allowed,
-			context->bw.dcn.calc_clk.dispclk_khz,
-			dc->current_state->bw.dcn.cur_clk.dispclk_khz)) {
+			context->bw.dcn.clk.dispclk_khz,
+			dc->res_pool->dccg->clks.dispclk_khz)) {
 
 		ramp_up_dispclk_with_dpp(dc, context);
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 44c48f3d0a1d..00d728e629fa 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -256,8 +256,7 @@ struct dce_bw_output {
 };
 
 struct dcn_bw_output {
-	struct dc_clocks cur_clk;
-	struct dc_clocks calc_clk;
+	struct dc_clocks clk;
 	struct dcn_watermark_set watermarks;
 };
 
-- 
cgit v1.2.3


From 12c3130dd6f391437a60c765912a30b4cbb77247 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 23 May 2018 18:18:50 -0400
Subject: drm/amd/display: move dcn1 dispclk programming to dccg

No functional change.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c    |  95 ++++++++++++++++--
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h    |   2 +-
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 106 ---------------------
 .../gpu/drm/amd/display/dc/dcn10/dcn10_resource.c  |   2 +-
 4 files changed, 90 insertions(+), 115 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 6b6570ea998d..55f533cf55ba 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -552,7 +552,85 @@ static void dce12_update_clocks(struct dccg *dccg,
 	}
 }
 
-static void dcn_update_clocks(struct dccg *dccg,
+static int dcn1_determine_dppclk_threshold(struct dccg *dccg, struct dc_clocks *new_clocks)
+{
+	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
+	bool dispclk_increase = new_clocks->dispclk_khz > dccg->clks.dispclk_khz;
+	int disp_clk_threshold = new_clocks->max_supported_dppclk_khz;
+	bool cur_dpp_div = dccg->clks.dispclk_khz > dccg->clks.dppclk_khz;
+
+	/* increase clock, looking for div is 0 for current, request div is 1*/
+	if (dispclk_increase) {
+		/* already divided by 2, no need to reach target clk with 2 steps*/
+		if (cur_dpp_div)
+			return new_clocks->dispclk_khz;
+
+		/* request disp clk is lower than maximum supported dpp clk,
+		 * no need to reach target clk with two steps.
+		 */
+		if (new_clocks->dispclk_khz <= disp_clk_threshold)
+			return new_clocks->dispclk_khz;
+
+		/* target dpp clk not request divided by 2, still within threshold */
+		if (!request_dpp_div)
+			return new_clocks->dispclk_khz;
+
+	} else {
+		/* decrease clock, looking for current dppclk divided by 2,
+		 * request dppclk not divided by 2.
+		 */
+
+		/* current dpp clk not divided by 2, no need to ramp*/
+		if (!cur_dpp_div)
+			return new_clocks->dispclk_khz;
+
+		/* current disp clk is lower than current maximum dpp clk,
+		 * no need to ramp
+		 */
+		if (dccg->clks.dispclk_khz <= disp_clk_threshold)
+			return new_clocks->dispclk_khz;
+
+		/* request dpp clk need to be divided by 2 */
+		if (request_dpp_div)
+			return new_clocks->dispclk_khz;
+	}
+
+	return disp_clk_threshold;
+}
+
+static void dcn1_ramp_up_dispclk_with_dpp(struct dccg *dccg, struct dc_clocks *new_clocks)
+{
+	struct dc *dc = dccg->ctx->dc;
+	int dispclk_to_dpp_threshold = dcn1_determine_dppclk_threshold(dccg, new_clocks);
+	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
+	int i;
+
+	/* set disp clk to dpp clk threshold */
+	dccg->funcs->set_dispclk(dccg, dispclk_to_dpp_threshold);
+
+	/* update request dpp clk division option */
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
+
+		if (!pipe_ctx->plane_state)
+			continue;
+
+		pipe_ctx->plane_res.dpp->funcs->dpp_dppclk_control(
+				pipe_ctx->plane_res.dpp,
+				request_dpp_div,
+				true);
+	}
+
+	/* If target clk not same as dppclk threshold, set to target clock */
+	if (dispclk_to_dpp_threshold != new_clocks->dispclk_khz)
+		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+
+	dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+	dccg->clks.dppclk_khz = new_clocks->dppclk_khz;
+	dccg->clks.max_supported_dppclk_khz = new_clocks->max_supported_dppclk_khz;
+}
+
+static void dcn1_update_clocks(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
 			bool safe_to_lower)
 {
@@ -572,6 +650,9 @@ static void dcn_update_clocks(struct dccg *dccg,
 		send_request_to_increase = true;
 
 #ifdef CONFIG_DRM_AMD_DC_DCN1_0
+	/* make sure dcf clk is before dpp clk to
+	 * make sure we have enough voltage to run dpp clk
+	 */
 	if (send_request_to_increase
 		) {
 		/*use dcfclk to request voltage*/
@@ -584,8 +665,8 @@ static void dcn_update_clocks(struct dccg *dccg,
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
-		/* TODO: ramp up - dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
-		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;*/
+		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
 
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 		send_request_to_lower = true;
@@ -666,10 +747,10 @@ static void dce_update_clocks(struct dccg *dccg,
 	}
 }
 
-static const struct display_clock_funcs dcn_funcs = {
+static const struct display_clock_funcs dcn1_funcs = {
 	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq_wrkaround,
 	.set_dispclk = dce112_set_clock,
-	.update_clocks = dcn_update_clocks
+	.update_clocks = dcn1_update_clocks
 };
 
 static const struct display_clock_funcs dce120_funcs = {
@@ -838,7 +919,7 @@ struct dccg *dce120_dccg_create(struct dc_context *ctx)
 	return &clk_dce->base;
 }
 
-struct dccg *dcn_dccg_create(struct dc_context *ctx)
+struct dccg *dcn1_dccg_create(struct dc_context *ctx)
 {
 	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
@@ -851,7 +932,7 @@ struct dccg *dcn_dccg_create(struct dc_context *ctx)
 	dce_dccg_construct(
 		clk_dce, ctx, NULL, NULL, NULL);
 
-	clk_dce->base.funcs = &dcn_funcs;
+	clk_dce->base.funcs = &dcn1_funcs;
 
 	return &clk_dce->base;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index c695b9c9bcb5..7907c3c4b1c1 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -128,7 +128,7 @@ struct dccg *dce112_dccg_create(
 
 struct dccg *dce120_dccg_create(struct dc_context *ctx);
 
-struct dccg *dcn_dccg_create(struct dc_context *ctx);
+struct dccg *dcn1_dccg_create(struct dc_context *ctx);
 
 void dce_dccg_destroy(struct dccg **dccg);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 6ab00615c4c5..60e99477930b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2360,101 +2360,6 @@ static void dcn10_apply_ctx_for_surface(
 */
 }
 
-static int determine_dppclk_threshold(struct dc *dc, struct dc_state *context)
-{
-	bool request_dpp_div = context->bw.dcn.clk.dispclk_khz >
-			context->bw.dcn.clk.dppclk_khz;
-	bool dispclk_increase = context->bw.dcn.clk.dispclk_khz >
-			dc->res_pool->dccg->clks.dispclk_khz;
-	int disp_clk_threshold = context->bw.dcn.clk.max_supported_dppclk_khz;
-	bool cur_dpp_div = dc->res_pool->dccg->clks.dispclk_khz >
-			dc->res_pool->dccg->clks.dppclk_khz;
-
-	/* increase clock, looking for div is 0 for current, request div is 1*/
-	if (dispclk_increase) {
-		/* already divided by 2, no need to reach target clk with 2 steps*/
-		if (cur_dpp_div)
-			return context->bw.dcn.clk.dispclk_khz;
-
-		/* request disp clk is lower than maximum supported dpp clk,
-		 * no need to reach target clk with two steps.
-		 */
-		if (context->bw.dcn.clk.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.clk.dispclk_khz;
-
-		/* target dpp clk not request divided by 2, still within threshold */
-		if (!request_dpp_div)
-			return context->bw.dcn.clk.dispclk_khz;
-
-	} else {
-		/* decrease clock, looking for current dppclk divided by 2,
-		 * request dppclk not divided by 2.
-		 */
-
-		/* current dpp clk not divided by 2, no need to ramp*/
-		if (!cur_dpp_div)
-			return context->bw.dcn.clk.dispclk_khz;
-
-		/* current disp clk is lower than current maximum dpp clk,
-		 * no need to ramp
-		 */
-		if (dc->res_pool->dccg->clks.dispclk_khz <= disp_clk_threshold)
-			return context->bw.dcn.clk.dispclk_khz;
-
-		/* request dpp clk need to be divided by 2 */
-		if (request_dpp_div)
-			return context->bw.dcn.clk.dispclk_khz;
-	}
-
-	return disp_clk_threshold;
-}
-
-static void ramp_up_dispclk_with_dpp(struct dc *dc, struct dc_state *context)
-{
-	int i;
-	bool request_dpp_div = context->bw.dcn.clk.dispclk_khz >
-				context->bw.dcn.clk.dppclk_khz;
-
-	int dispclk_to_dpp_threshold = determine_dppclk_threshold(dc, context);
-
-	/* set disp clk to dpp clk threshold */
-	dc->res_pool->dccg->funcs->set_dispclk(
-			dc->res_pool->dccg,
-			dispclk_to_dpp_threshold);
-
-	/* update request dpp clk division option */
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *pipe_ctx = &dc->current_state->res_ctx.pipe_ctx[i];
-
-		if (!pipe_ctx->plane_state)
-			continue;
-
-		pipe_ctx->plane_res.dpp->funcs->dpp_dppclk_control(
-				pipe_ctx->plane_res.dpp,
-				request_dpp_div,
-				true);
-	}
-
-	/* If target clk not same as dppclk threshold, set to target clock */
-	if (dispclk_to_dpp_threshold != context->bw.dcn.clk.dispclk_khz) {
-		dc->res_pool->dccg->funcs->set_dispclk(
-				dc->res_pool->dccg,
-				context->bw.dcn.clk.dispclk_khz);
-	}
-
-	dc->res_pool->dccg->clks.dispclk_khz =
-			context->bw.dcn.clk.dispclk_khz;
-	dc->res_pool->dccg->clks.dppclk_khz =
-			context->bw.dcn.clk.dppclk_khz;
-	dc->res_pool->dccg->clks.max_supported_dppclk_khz =
-			context->bw.dcn.clk.max_supported_dppclk_khz;
-}
-
-static inline bool should_set_clock(bool safe_to_lower, int calc_clk, int cur_clk)
-{
-	return ((safe_to_lower && calc_clk < cur_clk) || calc_clk > cur_clk);
-}
-
 static void dcn10_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
@@ -2475,17 +2380,6 @@ static void dcn10_set_bandwidth(
 			&context->bw.dcn.clk,
 			decrease_allowed);
 
-	/* make sure dcf clk is before dpp clk to
-	 * make sure we have enough voltage to run dpp clk
-	 */
-	if (should_set_clock(
-			decrease_allowed,
-			context->bw.dcn.clk.dispclk_khz,
-			dc->res_pool->dccg->clks.dispclk_khz)) {
-
-		ramp_up_dispclk_with_dpp(dc, context);
-	}
-
 	dcn10_pplib_apply_display_requirements(dc, context);
 
 	if (dc->debug.sanity_checks) {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 8f1ceffa809b..b5a727f7e880 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1072,7 +1072,7 @@ static bool construct(
 		}
 	}
 
-	pool->base.dccg = dcn_dccg_create(ctx);
+	pool->base.dccg = dcn1_dccg_create(ctx);
 	if (pool->base.dccg == NULL) {
 		dm_error("DC: failed to create display clock!\n");
 		BREAK_TO_DEBUGGER();
-- 
cgit v1.2.3


From 472800a0a0c84e224a7d4d5a4cfcd8dd6a4dd2b1 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 24 May 2018 15:50:18 -0400
Subject: drm/amd/display: clean up dccg divider calc and dcn constructor

No functional change.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c | 197 ++++++++----------------
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h |  26 ----
 2 files changed, 68 insertions(+), 155 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 55f533cf55ba..6e3bfdf8a9e7 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -101,90 +101,42 @@ static const struct state_dependent_clocks dce120_max_clks_by_state[] = {
 /*ClocksStatePerformance*/
 { .display_clk_khz = 1133000, .pixel_clk_khz = 600000 } };
 
-/* Starting point for each divider range.*/
-enum dce_divider_range_start {
-	DIVIDER_RANGE_01_START = 200, /* 2.00*/
-	DIVIDER_RANGE_02_START = 1600, /* 16.00*/
-	DIVIDER_RANGE_03_START = 3200, /* 32.00*/
-	DIVIDER_RANGE_SCALE_FACTOR = 100 /* Results are scaled up by 100.*/
+/* Starting DID for each range */
+enum dentist_base_divider_id {
+	dentist_base_divider_id_1 = 0x08,
+	dentist_base_divider_id_2 = 0x40,
+	dentist_base_divider_id_3 = 0x60,
+	dentist_max_divider_id    = 0x80
 };
 
-/* Ranges for divider identifiers (Divider ID or DID)
- mmDENTIST_DISPCLK_CNTL.DENTIST_DISPCLK_WDIVIDER*/
-enum dce_divider_id_register_setting {
-	DIVIDER_RANGE_01_BASE_DIVIDER_ID = 0X08,
-	DIVIDER_RANGE_02_BASE_DIVIDER_ID = 0X40,
-	DIVIDER_RANGE_03_BASE_DIVIDER_ID = 0X60,
-	DIVIDER_RANGE_MAX_DIVIDER_ID = 0X80
+/* Starting point and step size for each divider range.*/
+enum dentist_divider_range {
+	dentist_divider_range_1_start = 8,   /* 2.00  */
+	dentist_divider_range_1_step  = 1,   /* 0.25  */
+	dentist_divider_range_2_start = 64,  /* 16.00 */
+	dentist_divider_range_2_step  = 2,   /* 0.50  */
+	dentist_divider_range_3_start = 128, /* 32.00 */
+	dentist_divider_range_3_step  = 4,   /* 1.00  */
+	dentist_divider_range_scale_factor = 4
 };
 
-/* Step size between each divider within a range.
- Incrementing the DENTIST_DISPCLK_WDIVIDER by one
- will increment the divider by this much.*/
-enum dce_divider_range_step_size {
-	DIVIDER_RANGE_01_STEP_SIZE = 25, /* 0.25*/
-	DIVIDER_RANGE_02_STEP_SIZE = 50, /* 0.50*/
-	DIVIDER_RANGE_03_STEP_SIZE = 100 /* 1.00 */
-};
-
-static bool dce_divider_range_construct(
-	struct dce_divider_range *div_range,
-	int range_start,
-	int range_step,
-	int did_min,
-	int did_max)
-{
-	div_range->div_range_start = range_start;
-	div_range->div_range_step = range_step;
-	div_range->did_min = did_min;
-	div_range->did_max = did_max;
-
-	if (div_range->div_range_step == 0) {
-		div_range->div_range_step = 1;
-		/*div_range_step cannot be zero*/
-		BREAK_TO_DEBUGGER();
-	}
-	/* Calculate this based on the other inputs.*/
-	/* See DividerRange.h for explanation of */
-	/* the relationship between divider id (DID) and a divider.*/
-	/* Number of Divider IDs = (Maximum Divider ID - Minimum Divider ID)*/
-	/* Maximum divider identified in this range =
-	 * (Number of Divider IDs)*Step size between dividers
-	 *  + The start of this range.*/
-	div_range->div_range_end = (did_max - did_min) * range_step
-		+ range_start;
-	return true;
-}
-
-static int dce_divider_range_calc_divider(
-	struct dce_divider_range *div_range,
-	int did)
-{
-	/* Is this DID within our range?*/
-	if ((did < div_range->did_min) || (did >= div_range->did_max))
-		return INVALID_DIVIDER;
-
-	return ((did - div_range->did_min) * div_range->div_range_step)
-			+ div_range->div_range_start;
-
-}
-
-static int dce_divider_range_get_divider(
-	struct dce_divider_range *div_range,
-	int ranges_num,
-	int did)
+static int dentist_get_divider_from_did(int did)
 {
-	int div = INVALID_DIVIDER;
-	int i;
-
-	for (i = 0; i < ranges_num; i++) {
-		/* Calculate divider with given divider ID*/
-		div = dce_divider_range_calc_divider(&div_range[i], did);
-		/* Found a valid return divider*/
-		if (div != INVALID_DIVIDER)
-			break;
+	if (did < dentist_base_divider_id_1)
+		did = dentist_base_divider_id_1;
+	if (did > dentist_max_divider_id)
+		did = dentist_max_divider_id;
+
+	if (did < dentist_base_divider_id_2) {
+		return dentist_divider_range_1_start + dentist_divider_range_1_step
+							* (did - dentist_base_divider_id_1);
+	} else if (did < dentist_base_divider_id_3) {
+		return dentist_divider_range_2_start + dentist_divider_range_2_step
+							* (did - dentist_base_divider_id_2);
+	} else {
+		return dentist_divider_range_3_start + dentist_divider_range_3_step
+							* (did - dentist_base_divider_id_3);
 	}
-	return div;
 }
 
 static int dce_clocks_get_dp_ref_freq(struct dccg *clk)
@@ -193,7 +145,7 @@ static int dce_clocks_get_dp_ref_freq(struct dccg *clk)
 	int dprefclk_wdivider;
 	int dprefclk_src_sel;
 	int dp_ref_clk_khz = 600000;
-	int target_div = INVALID_DIVIDER;
+	int target_div;
 
 	/* ASSERT DP Reference Clock source is from DFS*/
 	REG_GET(DPREFCLK_CNTL, DPREFCLK_SRC_SEL, &dprefclk_src_sel);
@@ -204,16 +156,11 @@ static int dce_clocks_get_dp_ref_freq(struct dccg *clk)
 	REG_GET(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, &dprefclk_wdivider);
 
 	/* Convert DENTIST_DPREFCLK_WDIVIDERto actual divider*/
-	target_div = dce_divider_range_get_divider(
-			clk_dce->divider_ranges,
-			DIVIDER_RANGE_MAX,
-			dprefclk_wdivider);
-
-	if (target_div != INVALID_DIVIDER) {
-		/* Calculate the current DFS clock, in kHz.*/
-		dp_ref_clk_khz = (DIVIDER_RANGE_SCALE_FACTOR
-			* clk_dce->dentist_vco_freq_khz) / target_div;
-	}
+	target_div = dentist_get_divider_from_did(dprefclk_wdivider);
+
+	/* Calculate the current DFS clock, in kHz.*/
+	dp_ref_clk_khz = (dentist_divider_range_scale_factor
+		* clk_dce->dentist_vco_freq_khz) / target_div;
 
 	/* SW will adjust DP REF Clock average value for all purposes
 	 * (DP DTO / DP Audio DTO and DP GTC)
@@ -229,17 +176,12 @@ static int dce_clocks_get_dp_ref_freq(struct dccg *clk)
 	  */
 	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
 		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(
-						clk_dce->dprefclk_ss_percentage,
-						clk_dce->dprefclk_ss_divider), 200);
+				dc_fixpt_from_fraction(clk_dce->dprefclk_ss_percentage,
+							clk_dce->dprefclk_ss_divider), 200);
 		struct fixed31_32 adj_dp_ref_clk_khz;
 
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
-								ss_percentage);
-		adj_dp_ref_clk_khz =
-			dc_fixpt_mul_int(
-				ss_percentage,
-				dp_ref_clk_khz);
+		ss_percentage = dc_fixpt_sub(dc_fixpt_one, ss_percentage);
+		adj_dp_ref_clk_khz = dc_fixpt_mul_int(ss_percentage, dp_ref_clk_khz);
 		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
 	}
 
@@ -257,17 +199,12 @@ static int dce_clocks_get_dp_ref_freq_wrkaround(struct dccg *clk)
 
 	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
 		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(
-						clk_dce->dprefclk_ss_percentage,
+				dc_fixpt_from_fraction(clk_dce->dprefclk_ss_percentage,
 						clk_dce->dprefclk_ss_divider), 200);
 		struct fixed31_32 adj_dp_ref_clk_khz;
 
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one,
-								ss_percentage);
-		adj_dp_ref_clk_khz =
-			dc_fixpt_mul_int(
-				ss_percentage,
-				dp_ref_clk_khz);
+		ss_percentage = dc_fixpt_sub(dc_fixpt_one, ss_percentage);
+		adj_dp_ref_clk_khz = dc_fixpt_mul_int(ss_percentage, dp_ref_clk_khz);
 		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
 	}
 
@@ -804,25 +741,6 @@ static void dce_dccg_construct(
 
 	dce_clock_read_integrated_info(clk_dce);
 	dce_clock_read_ss_info(clk_dce);
-
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_01],
-		DIVIDER_RANGE_01_START,
-		DIVIDER_RANGE_01_STEP_SIZE,
-		DIVIDER_RANGE_01_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_02_BASE_DIVIDER_ID);
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_02],
-		DIVIDER_RANGE_02_START,
-		DIVIDER_RANGE_02_STEP_SIZE,
-		DIVIDER_RANGE_02_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_03_BASE_DIVIDER_ID);
-	dce_divider_range_construct(
-		&clk_dce->divider_ranges[DIVIDER_RANGE_03],
-		DIVIDER_RANGE_03_START,
-		DIVIDER_RANGE_03_STEP_SIZE,
-		DIVIDER_RANGE_03_BASE_DIVIDER_ID,
-		DIVIDER_RANGE_MAX_DIVIDER_ID);
 }
 
 struct dccg *dce_dccg_create(
@@ -921,6 +839,9 @@ struct dccg *dce120_dccg_create(struct dc_context *ctx)
 
 struct dccg *dcn1_dccg_create(struct dc_context *ctx)
 {
+	struct dc_debug *debug = &ctx->dc->debug;
+	struct dc_bios *bp = ctx->dc_bios;
+	struct dc_firmware_info fw_info = { { 0 } };
 	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
 	if (clk_dce == NULL) {
@@ -928,12 +849,30 @@ struct dccg *dcn1_dccg_create(struct dc_context *ctx)
 		return NULL;
 	}
 
-	/* TODO strip out useful stuff out of dce constructor */
-	dce_dccg_construct(
-		clk_dce, ctx, NULL, NULL, NULL);
-
+	clk_dce->base.ctx = ctx;
 	clk_dce->base.funcs = &dcn1_funcs;
 
+	clk_dce->dfs_bypass_disp_clk = 0;
+
+	clk_dce->dprefclk_ss_percentage = 0;
+	clk_dce->dprefclk_ss_divider = 1000;
+	clk_dce->ss_on_dprefclk = false;
+
+	if (bp->integrated_info)
+		clk_dce->dentist_vco_freq_khz = bp->integrated_info->dentist_vco_freq;
+	if (clk_dce->dentist_vco_freq_khz == 0) {
+		bp->funcs->get_firmware_info(bp, &fw_info);
+		clk_dce->dentist_vco_freq_khz = fw_info.smu_gpu_pll_output_freq;
+		if (clk_dce->dentist_vco_freq_khz == 0)
+			clk_dce->dentist_vco_freq_khz = 3600000;
+	}
+
+	if (!debug->disable_dfs_bypass && bp->integrated_info)
+		if (bp->integrated_info->gpu_cap_info & DFS_BYPASS_ENABLE)
+			clk_dce->dfs_bypass_enabled = true;
+
+	dce_clock_read_ss_info(clk_dce);
+
 	return &clk_dce->base;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 7907c3c4b1c1..04a9e3c04aa7 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -57,31 +57,6 @@ struct dce_disp_clk_registers {
 	uint32_t DENTIST_DISPCLK_CNTL;
 };
 
-/* Array identifiers and count for the divider ranges.*/
-enum dce_divider_range_count {
-	DIVIDER_RANGE_01 = 0,
-	DIVIDER_RANGE_02,
-	DIVIDER_RANGE_03,
-	DIVIDER_RANGE_MAX /* == 3*/
-};
-
-enum dce_divider_error_types {
-	INVALID_DID = 0,
-	INVALID_DIVIDER = 1
-};
-
-struct dce_divider_range {
-	int div_range_start;
-	/* The end of this range of dividers.*/
-	int div_range_end;
-	/* The distance between each divider in this range.*/
-	int div_range_step;
-	/* The divider id for the lowest divider.*/
-	int did_min;
-	/* The divider id for the highest divider.*/
-	int did_max;
-};
-
 struct dce_dccg {
 	struct dccg base;
 	const struct dce_disp_clk_registers *regs;
@@ -89,7 +64,6 @@ struct dce_dccg {
 	const struct dce_disp_clk_mask *clk_mask;
 
 	struct state_dependent_clocks max_clks_by_state[DM_PP_CLOCKS_MAX_STATES];
-	struct dce_divider_range divider_ranges[DIVIDER_RANGE_MAX];
 
 	int dentist_vco_freq_khz;
 
-- 
cgit v1.2.3


From 3cdecd4513d57993aaddc03ccdf4539add772aa4 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 24 May 2018 16:48:38 -0400
Subject: drm/amd/display: rename dce_disp_clk to dccg

No functional change.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c    | 115 +++++++++------------
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h    |  41 +++++---
 drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h     |   3 -
 .../drm/amd/display/dc/dce100/dce100_resource.c    |   6 +-
 .../drm/amd/display/dc/dce110/dce110_resource.c    |   6 +-
 .../drm/amd/display/dc/dce112/dce112_resource.c    |   6 +-
 .../gpu/drm/amd/display/dc/dce80/dce80_resource.c  |   6 +-
 7 files changed, 88 insertions(+), 95 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 6e3bfdf8a9e7..242e8ae56025 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -139,7 +139,34 @@ static int dentist_get_divider_from_did(int did)
 	}
 }
 
-static int dce_clocks_get_dp_ref_freq(struct dccg *clk)
+/* SW will adjust DP REF Clock average value for all purposes
+ * (DP DTO / DP Audio DTO and DP GTC)
+ if clock is spread for all cases:
+ -if SS enabled on DP Ref clock and HW de-spreading enabled with SW
+ calculations for DS_INCR/DS_MODULO (this is planned to be default case)
+ -if SS enabled on DP Ref clock and HW de-spreading enabled with HW
+ calculations (not planned to be used, but average clock should still
+ be valid)
+ -if SS enabled on DP Ref clock and HW de-spreading disabled
+ (should not be case with CIK) then SW should program all rates
+ generated according to average value (case as with previous ASICs)
+  */
+static int dccg_adjust_dp_ref_freq_for_ss(struct dce_dccg *clk_dce, int dp_ref_clk_khz)
+{
+	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
+		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
+				dc_fixpt_from_fraction(clk_dce->dprefclk_ss_percentage,
+							clk_dce->dprefclk_ss_divider), 200);
+		struct fixed31_32 adj_dp_ref_clk_khz;
+
+		ss_percentage = dc_fixpt_sub(dc_fixpt_one, ss_percentage);
+		adj_dp_ref_clk_khz = dc_fixpt_mul_int(ss_percentage, dp_ref_clk_khz);
+		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
+	}
+	return dp_ref_clk_khz;
+}
+
+static int dce_get_dp_ref_freq_khz(struct dccg *clk)
 {
 	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
 	int dprefclk_wdivider;
@@ -162,54 +189,16 @@ static int dce_clocks_get_dp_ref_freq(struct dccg *clk)
 	dp_ref_clk_khz = (dentist_divider_range_scale_factor
 		* clk_dce->dentist_vco_freq_khz) / target_div;
 
-	/* SW will adjust DP REF Clock average value for all purposes
-	 * (DP DTO / DP Audio DTO and DP GTC)
-	 if clock is spread for all cases:
-	 -if SS enabled on DP Ref clock and HW de-spreading enabled with SW
-	 calculations for DS_INCR/DS_MODULO (this is planned to be default case)
-	 -if SS enabled on DP Ref clock and HW de-spreading enabled with HW
-	 calculations (not planned to be used, but average clock should still
-	 be valid)
-	 -if SS enabled on DP Ref clock and HW de-spreading disabled
-	 (should not be case with CIK) then SW should program all rates
-	 generated according to average value (case as with previous ASICs)
-	  */
-	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(clk_dce->dprefclk_ss_percentage,
-							clk_dce->dprefclk_ss_divider), 200);
-		struct fixed31_32 adj_dp_ref_clk_khz;
-
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one, ss_percentage);
-		adj_dp_ref_clk_khz = dc_fixpt_mul_int(ss_percentage, dp_ref_clk_khz);
-		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
-	}
-
-	return dp_ref_clk_khz;
+	return dccg_adjust_dp_ref_freq_for_ss(clk_dce, dp_ref_clk_khz);
 }
 
-/* TODO: This is DCN DPREFCLK: it could be program by DENTIST by VBIOS
- * or CLK0_CLK11 by SMU. For DCE120, it is wlays 600Mhz. Will re-visit
- * clock implementation
- */
-static int dce_clocks_get_dp_ref_freq_wrkaround(struct dccg *clk)
+static int dce12_get_dp_ref_freq_khz(struct dccg *clk)
 {
 	struct dce_dccg *clk_dce = TO_DCE_CLOCKS(clk);
-	int dp_ref_clk_khz = 600000;
-
-	if (clk_dce->ss_on_dprefclk && clk_dce->dprefclk_ss_divider != 0) {
-		struct fixed31_32 ss_percentage = dc_fixpt_div_int(
-				dc_fixpt_from_fraction(clk_dce->dprefclk_ss_percentage,
-						clk_dce->dprefclk_ss_divider), 200);
-		struct fixed31_32 adj_dp_ref_clk_khz;
-
-		ss_percentage = dc_fixpt_sub(dc_fixpt_one, ss_percentage);
-		adj_dp_ref_clk_khz = dc_fixpt_mul_int(ss_percentage, dp_ref_clk_khz);
-		dp_ref_clk_khz = dc_fixpt_floor(adj_dp_ref_clk_khz);
-	}
 
-	return dp_ref_clk_khz;
+	return dccg_adjust_dp_ref_freq_for_ss(clk_dce, 600000);
 }
+
 static enum dm_pp_clocks_state dce_get_required_clocks_state(
 	struct dccg *clk,
 	struct dc_clocks *req_clocks)
@@ -590,8 +579,7 @@ static void dcn1_update_clocks(struct dccg *dccg,
 	/* make sure dcf clk is before dpp clk to
 	 * make sure we have enough voltage to run dpp clk
 	 */
-	if (send_request_to_increase
-		) {
+	if (send_request_to_increase) {
 		/*use dcfclk to request voltage*/
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
 		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
@@ -644,8 +632,7 @@ static void dcn1_update_clocks(struct dccg *dccg,
 	}
 
 #ifdef CONFIG_DRM_AMD_DC_DCN1_0
-	if (!send_request_to_increase && send_request_to_lower
-		) {
+	if (!send_request_to_increase && send_request_to_lower) {
 		/*use dcfclk to request voltage*/
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
 		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
@@ -685,31 +672,31 @@ static void dce_update_clocks(struct dccg *dccg,
 }
 
 static const struct display_clock_funcs dcn1_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq_wrkaround,
+	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.set_dispclk = dce112_set_clock,
 	.update_clocks = dcn1_update_clocks
 };
 
 static const struct display_clock_funcs dce120_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq_wrkaround,
+	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.set_dispclk = dce112_set_clock,
 	.update_clocks = dce12_update_clocks
 };
 
 static const struct display_clock_funcs dce112_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
 	.set_dispclk = dce112_set_clock,
 	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce110_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
 	.set_dispclk = dce_psr_set_clock,
 	.update_clocks = dce_update_clocks
 };
 
 static const struct display_clock_funcs dce_funcs = {
-	.get_dp_ref_clk_frequency = dce_clocks_get_dp_ref_freq,
+	.get_dp_ref_clk_frequency = dce_get_dp_ref_freq_khz,
 	.set_dispclk = dce_set_clock,
 	.update_clocks = dce_update_clocks
 };
@@ -717,9 +704,9 @@ static const struct display_clock_funcs dce_funcs = {
 static void dce_dccg_construct(
 	struct dce_dccg *clk_dce,
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
 	struct dccg *base = &clk_dce->base;
 
@@ -745,9 +732,9 @@ static void dce_dccg_construct(
 
 struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
 	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
@@ -768,9 +755,9 @@ struct dccg *dce_dccg_create(
 
 struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
 	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
@@ -793,9 +780,9 @@ struct dccg *dce110_dccg_create(
 
 struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask)
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask)
 {
 	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 04a9e3c04aa7..be5b68d7c3c0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -33,6 +33,9 @@
 	.DPREFCLK_CNTL = mmDPREFCLK_CNTL, \
 	.DENTIST_DISPCLK_CNTL = mmDENTIST_DISPCLK_CNTL
 
+#define CLK_COMMON_REG_LIST_DCN_BASE() \
+	SR(DENTIST_DISPCLK_CNTL)
+
 #define CLK_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
 
@@ -40,28 +43,34 @@
 	CLK_SF(DPREFCLK_CNTL, DPREFCLK_SRC_SEL, mask_sh), \
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, mask_sh)
 
+#define CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh) \
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, mask_sh),\
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh)
+
 #define CLK_REG_FIELD_LIST(type) \
 	type DPREFCLK_SRC_SEL; \
-	type DENTIST_DPREFCLK_WDIVIDER;
+	type DENTIST_DPREFCLK_WDIVIDER; \
+	type DENTIST_DISPCLK_WDIVIDER; \
+	type DENTIST_DPPCLK_WDIVIDER;
 
-struct dce_disp_clk_shift {
+struct dccg_shift {
 	CLK_REG_FIELD_LIST(uint8_t)
 };
 
-struct dce_disp_clk_mask {
+struct dccg_mask {
 	CLK_REG_FIELD_LIST(uint32_t)
 };
 
-struct dce_disp_clk_registers {
+struct dccg_registers {
 	uint32_t DPREFCLK_CNTL;
 	uint32_t DENTIST_DISPCLK_CNTL;
 };
 
 struct dce_dccg {
 	struct dccg base;
-	const struct dce_disp_clk_registers *regs;
-	const struct dce_disp_clk_shift *clk_shift;
-	const struct dce_disp_clk_mask *clk_mask;
+	const struct dccg_registers *regs;
+	const struct dccg_shift *clk_shift;
+	const struct dccg_mask *clk_mask;
 
 	struct state_dependent_clocks max_clks_by_state[DM_PP_CLOCKS_MAX_STATES];
 
@@ -84,21 +93,21 @@ struct dce_dccg {
 
 struct dccg *dce_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
 
 struct dccg *dce110_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
 
 struct dccg *dce112_dccg_create(
 	struct dc_context *ctx,
-	const struct dce_disp_clk_registers *regs,
-	const struct dce_disp_clk_shift *clk_shift,
-	const struct dce_disp_clk_mask *clk_mask);
+	const struct dccg_registers *regs,
+	const struct dccg_shift *clk_shift,
+	const struct dccg_mask *clk_mask);
 
 struct dccg *dce120_dccg_create(struct dc_context *ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 057b8afd74bc..057407892618 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -249,7 +249,6 @@ struct dce_hwseq_registers {
 	uint32_t DISPCLK_FREQ_CHANGE_CNTL;
 	uint32_t RBBMIF_TIMEOUT_DIS;
 	uint32_t RBBMIF_TIMEOUT_DIS_2;
-	uint32_t DENTIST_DISPCLK_CNTL;
 	uint32_t DCHUBBUB_CRC_CTRL;
 	uint32_t DPP_TOP0_DPP_CRC_CTRL;
 	uint32_t DPP_TOP0_DPP_CRC_VAL_R_G;
@@ -496,8 +495,6 @@ struct dce_hwseq_registers {
 	type DOMAIN7_PGFSM_PWR_STATUS; \
 	type DCFCLK_GATE_DIS; \
 	type DCHUBBUB_GLOBAL_TIMER_REFDIV; \
-	type DENTIST_DPPCLK_WDIVIDER; \
-	type DENTIST_DISPCLK_WDIVIDER; \
 	type VGA_TEST_ENABLE; \
 	type VGA_TEST_RENDER_START; \
 	type D1VGA_MODE_ENABLE; \
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 856d3fe8e6a0..8ed8eace42be 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -135,15 +135,15 @@ static const struct dce110_timing_generator_offsets dce100_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 71a401f73a58..3edaa006bd57 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -146,15 +146,15 @@ static const struct dce110_timing_generator_offsets dce110_tg_offsets[] = {
 #define SRI(reg_name, block, id)\
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index ae5b19de559c..752910035e81 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -146,15 +146,15 @@ static const struct dce110_timing_generator_offsets dce112_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 70700530aec2..2ac95ec2bf96 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -153,15 +153,15 @@ static const struct dce110_timing_generator_offsets dce80_tg_offsets[] = {
 	.reg_name = mm ## block ## id ## _ ## reg_name
 
 
-static const struct dce_disp_clk_registers disp_clk_regs = {
+static const struct dccg_registers disp_clk_regs = {
 		CLK_COMMON_REG_LIST_DCE_BASE()
 };
 
-static const struct dce_disp_clk_shift disp_clk_shift = {
+static const struct dccg_shift disp_clk_shift = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(__SHIFT)
 };
 
-static const struct dce_disp_clk_mask disp_clk_mask = {
+static const struct dccg_mask disp_clk_mask = {
 		CLK_COMMON_MASK_SH_LIST_DCE_COMMON_BASE(_MASK)
 };
 
-- 
cgit v1.2.3


From c910a717dac6540a636a57c1a34261c6d84fc0eb Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 23 May 2018 18:39:21 -0400
Subject: drm/amd/display: clean up set_bandwidth usage

This removes redundant set_bandwidth calls as well
as fixes a bug in post_set_address_update where dcn1
would never get to lower clocks.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c                    |  5 -----
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c |  5 -----
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c   | 11 +++--------
 3 files changed, 3 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 53ce7fa864b4..2a785bbf2b8f 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -944,12 +944,7 @@ bool dc_post_update_surfaces_to_stream(struct dc *dc)
 
 	dc->optimized_required = false;
 
-	/* 3rd param should be true, temp w/a for RV*/
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
-	dc->hwss.set_bandwidth(dc, context, dc->ctx->dce_version < DCN_VERSION_1_0);
-#else
 	dc->hwss.set_bandwidth(dc, context, true);
-#endif
 	return true;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 4cdf86690d19..3b983b3f3423 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2036,8 +2036,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 	if (dc->fbc_compressor)
 		dc->fbc_compressor->funcs->disable_fbc(dc->fbc_compressor);
 
-	dc->hwss.set_bandwidth(dc, context, false);
-
 	dce110_setup_audio_dto(dc, context);
 
 	for (i = 0; i < dc->res_pool->pipe_count; i++) {
@@ -2066,9 +2064,6 @@ enum dc_status dce110_apply_ctx_to_hw(
 			return status;
 	}
 
-	/* to save power */
-	dc->hwss.set_bandwidth(dc, context, true);
-
 	dcb->funcs->set_scratch_critical_state(dcb, false);
 
 	if (dc->fbc_compressor)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 60e99477930b..08809b0ff6bf 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2268,8 +2268,7 @@ static void dcn10_apply_ctx_for_surface(
 			hwss1_plane_atomic_disconnect(dc, old_pipe_ctx);
 			removed_pipe[i] = true;
 
-			DC_LOG_DC(
-					"Reset mpcc for pipe %d\n",
+			DC_LOG_DC("Reset mpcc for pipe %d\n",
 					old_pipe_ctx->pipe_idx);
 		}
 	}
@@ -2365,9 +2364,8 @@ static void dcn10_set_bandwidth(
 		struct dc_state *context,
 		bool decrease_allowed)
 {
-	if (dc->debug.sanity_checks) {
+	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
-	}
 
 	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
 		return;
@@ -2382,11 +2380,8 @@ static void dcn10_set_bandwidth(
 
 	dcn10_pplib_apply_display_requirements(dc, context);
 
-	if (dc->debug.sanity_checks) {
+	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
-	}
-
-	/* need to fix this function.  not doing the right thing here */
 }
 
 static void set_drr(struct pipe_ctx **pipe_ctx,
-- 
cgit v1.2.3


From aa162e2727254262a79509ec3e99ace33b3232b6 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 31 May 2018 13:28:00 -0400
Subject: drm/amd/display: remove unnecessary pplib volage requests that are
 asserting

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 242e8ae56025..df6a37b7b769 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -588,21 +588,15 @@ static void dcn1_update_clocks(struct dccg *dccg,
 #endif
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
-		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
-		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
 		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
 		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
 
-		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 		send_request_to_lower = true;
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
-		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
-		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAYPHYCLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
 
-		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 		send_request_to_lower = true;
 	}
 
@@ -618,8 +612,6 @@ static void dcn1_update_clocks(struct dccg *dccg,
 
 	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, dccg->clks.dcfclk_khz)) {
 		dccg->clks.phyclk_khz = new_clocks->dcfclk_khz;
-		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-		clock_voltage_req.clocks_in_khz = new_clocks->dcfclk_khz;
 		smu_req.hard_min_dcefclk_khz = new_clocks->dcfclk_khz;
 
 		send_request_to_lower = true;
-- 
cgit v1.2.3


From 0eebf8ca18b647024fc9a3ccc88c0184d02db534 Mon Sep 17 00:00:00 2001
From: Wesley Chalmers <Wesley.Chalmers@amd.com>
Date: Fri, 1 Jun 2018 10:54:53 -0400
Subject: drm/amd/display: Temporarily remove Chroma logs

To ensure tests continue to pass

Signed-off-by: Wesley Chalmers <Wesley.Chalmers@amd.com>
Reviewed-by: Shahin Khayyer <Shahin.Khayyer@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 08809b0ff6bf..5b40c1c4d9e6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -151,23 +151,19 @@ static void dcn10_log_hubp_states(struct dc *dc)
 
 	DTN_INFO("\n=========RQ========\n");
 	DTN_INFO("HUBP:  drq_exp_m  prq_exp_m  mrq_exp_m  crq_exp_m  plane1_ba  L:chunk_s  min_chu_s  meta_ch_s"
-		"  min_m_c_s  dpte_gr_s  mpte_gr_s  swath_hei  pte_row_h  C:chunk_s  min_chu_s  meta_ch_s"
 		"  min_m_c_s  dpte_gr_s  mpte_gr_s  swath_hei  pte_row_h\n");
 	for (i = 0; i < pool->pipe_count; i++) {
 		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(pool->hubps[i])->state);
 		struct _vcs_dpi_display_rq_regs_st *rq_regs = &s->rq_regs;
 
 		if (!s->blank_en)
-			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
+			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
 				pool->hubps[i]->inst, rq_regs->drq_expansion_mode, rq_regs->prq_expansion_mode, rq_regs->mrq_expansion_mode,
 				rq_regs->crq_expansion_mode, rq_regs->plane1_base_address, rq_regs->rq_regs_l.chunk_size,
 				rq_regs->rq_regs_l.min_chunk_size, rq_regs->rq_regs_l.meta_chunk_size,
 				rq_regs->rq_regs_l.min_meta_chunk_size, rq_regs->rq_regs_l.dpte_group_size,
 				rq_regs->rq_regs_l.mpte_group_size, rq_regs->rq_regs_l.swath_height,
-				rq_regs->rq_regs_l.pte_row_height_linear, rq_regs->rq_regs_c.chunk_size, rq_regs->rq_regs_c.min_chunk_size,
-				rq_regs->rq_regs_c.meta_chunk_size, rq_regs->rq_regs_c.min_meta_chunk_size,
-				rq_regs->rq_regs_c.dpte_group_size, rq_regs->rq_regs_c.mpte_group_size,
-				rq_regs->rq_regs_c.swath_height, rq_regs->rq_regs_c.pte_row_height_linear);
+				rq_regs->rq_regs_l.pte_row_height_linear);
 	}
 
 	DTN_INFO("========DLG========\n");
-- 
cgit v1.2.3


From 7e17cb4ba90cf2ab51e65427092fdc878cc956bc Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Wed, 30 May 2018 15:58:08 -0400
Subject: drm/amd/display: Define dp_alt_mode

Also cleanup command_table2.c. No need for a lot of forward
declarations.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/bios/command_table2.c   | 46 ++++++++--------------
 .../drm/amd/display/dc/dcn10/dcn10_link_encoder.c  |  2 +
 .../gpu/drm/amd/display/include/grph_object_id.h   |  5 +++
 3 files changed, 24 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
index 752b08a42d3e..2b5dc499a35e 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c
@@ -59,36 +59,7 @@
 	bios_cmd_table_para_revision(bp->base.ctx->driver_context, \
 			GET_INDEX_INTO_MASTER_TABLE(command, fname))
 
-static void init_dig_encoder_control(struct bios_parser *bp);
-static void init_transmitter_control(struct bios_parser *bp);
-static void init_set_pixel_clock(struct bios_parser *bp);
 
-static void init_set_crtc_timing(struct bios_parser *bp);
-
-static void init_select_crtc_source(struct bios_parser *bp);
-static void init_enable_crtc(struct bios_parser *bp);
-
-static void init_external_encoder_control(struct bios_parser *bp);
-static void init_enable_disp_power_gating(struct bios_parser *bp);
-static void init_set_dce_clock(struct bios_parser *bp);
-static void init_get_smu_clock_info(struct bios_parser *bp);
-
-void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
-{
-	init_dig_encoder_control(bp);
-	init_transmitter_control(bp);
-	init_set_pixel_clock(bp);
-
-	init_set_crtc_timing(bp);
-
-	init_select_crtc_source(bp);
-	init_enable_crtc(bp);
-
-	init_external_encoder_control(bp);
-	init_enable_disp_power_gating(bp);
-	init_set_dce_clock(bp);
-	init_get_smu_clock_info(bp);
-}
 
 static uint32_t bios_cmd_table_para_revision(void *dev,
 					     uint32_t index)
@@ -829,3 +800,20 @@ static unsigned int get_smu_clock_info_v3_1(struct bios_parser *bp, uint8_t id)
 	return 0;
 }
 
+void dal_firmware_parser_init_cmd_tbl(struct bios_parser *bp)
+{
+	init_dig_encoder_control(bp);
+	init_transmitter_control(bp);
+	init_set_pixel_clock(bp);
+
+	init_set_crtc_timing(bp);
+
+	init_select_crtc_source(bp);
+	init_enable_crtc(bp);
+
+	init_external_encoder_control(bp);
+	init_enable_disp_power_gating(bp);
+	init_set_dce_clock(bp);
+	init_get_smu_clock_info(bp);
+
+}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index 21fa40ac0786..fd9dc70190a8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -995,6 +995,8 @@ void dcn10_link_encoder_disable_output(
 
 	if (!dcn10_is_dig_enabled(enc)) {
 		/* OF_SKIP_POWER_DOWN_INACTIVE_ENCODER */
+	/*in DP_Alt_No_Connect case, we turn off the dig already,
+	after excuation the PHY w/a sequence, not allow touch PHY any more*/
 		return;
 	}
 	/* Power-down RX and disable GPU PHY should be paired.
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_id.h b/drivers/gpu/drm/amd/display/include/grph_object_id.h
index c4197432eb7c..92cc6c112ea6 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_id.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_id.h
@@ -197,6 +197,11 @@ enum transmitter_color_depth {
 	TRANSMITTER_COLOR_DEPTH_48       /* 16 bits */
 };
 
+enum dp_alt_mode {
+	DP_Alt_mode__Unknown = 0,
+	DP_Alt_mode__Connect,
+	DP_Alt_mode__NoConnect,
+};
 /*
  *****************************************************************************
  * graphics_object_id struct
-- 
cgit v1.2.3


From 89af301e21b53317f1d0c5ed6f8e935f65e877d0 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Fri, 1 Jun 2018 14:13:40 -0400
Subject: drm/amd/display: fix dccg dcn1 ifdef

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c | 10 ++++++----
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h |  2 ++
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index df6a37b7b769..e62a21f55064 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -478,6 +478,7 @@ static void dce12_update_clocks(struct dccg *dccg,
 	}
 }
 
+#ifdef CONFIG_DRM_AMD_DC_DCN1_0
 static int dcn1_determine_dppclk_threshold(struct dccg *dccg, struct dc_clocks *new_clocks)
 {
 	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
@@ -575,7 +576,6 @@ static void dcn1_update_clocks(struct dccg *dccg,
 			|| new_clocks->dcfclk_khz > dccg->clks.dcfclk_khz)
 		send_request_to_increase = true;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
 	/* make sure dcf clk is before dpp clk to
 	 * make sure we have enough voltage to run dpp clk
 	 */
@@ -585,7 +585,6 @@ static void dcn1_update_clocks(struct dccg *dccg,
 		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
-#endif
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
 		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
@@ -623,14 +622,12 @@ static void dcn1_update_clocks(struct dccg *dccg,
 		smu_req.min_deep_sleep_dcefclk_mhz = new_clocks->dcfclk_deep_sleep_khz;
 	}
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
 	if (!send_request_to_increase && send_request_to_lower) {
 		/*use dcfclk to request voltage*/
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
 		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
 	}
-#endif
 
 	if (new_clocks->phyclk_khz)
 		smu_req.display_count = 1;
@@ -642,6 +639,7 @@ static void dcn1_update_clocks(struct dccg *dccg,
 
 	*smu_req_cur = smu_req;
 }
+#endif
 
 static void dce_update_clocks(struct dccg *dccg,
 			struct dc_clocks *new_clocks,
@@ -663,11 +661,13 @@ static void dce_update_clocks(struct dccg *dccg,
 	}
 }
 
+#ifdef CONFIG_DRM_AMD_DC_DCN1_0
 static const struct display_clock_funcs dcn1_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.set_dispclk = dce112_set_clock,
 	.update_clocks = dcn1_update_clocks
 };
+#endif
 
 static const struct display_clock_funcs dce120_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
@@ -816,6 +816,7 @@ struct dccg *dce120_dccg_create(struct dc_context *ctx)
 	return &clk_dce->base;
 }
 
+#ifdef CONFIG_DRM_AMD_DC_DCN1_0
 struct dccg *dcn1_dccg_create(struct dc_context *ctx)
 {
 	struct dc_debug *debug = &ctx->dc->debug;
@@ -854,6 +855,7 @@ struct dccg *dcn1_dccg_create(struct dc_context *ctx)
 
 	return &clk_dce->base;
 }
+#endif
 
 void dce_dccg_destroy(struct dccg **dccg)
 {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index be5b68d7c3c0..1f1899ef773a 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -111,7 +111,9 @@ struct dccg *dce112_dccg_create(
 
 struct dccg *dce120_dccg_create(struct dc_context *ctx);
 
+#ifdef CONFIG_DRM_AMD_DC_DCN1_0
 struct dccg *dcn1_dccg_create(struct dc_context *ctx);
+#endif
 
 void dce_dccg_destroy(struct dccg **dccg);
 
-- 
cgit v1.2.3


From 5b0ec710dadd4569c1ed76dc175b94abb594b977 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Fri, 1 Jun 2018 15:01:32 -0400
Subject: drm/amd/display: fix pplib voltage request

This fixes incorrect clock caching and by extension fixes
the clock reporting.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Yang <eric.yang2@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c | 59 ++++++++++++++-----------
 1 file changed, 32 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index e62a21f55064..0a4ae0f49f99 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -570,37 +570,25 @@ static void dcn1_update_clocks(struct dccg *dccg,
 	bool send_request_to_increase = false;
 	bool send_request_to_lower = false;
 
+	if (new_clocks->phyclk_khz)
+		smu_req.display_count = 1;
+	else
+		smu_req.display_count = 0;
+
 	if (new_clocks->dispclk_khz > dccg->clks.dispclk_khz
 			|| new_clocks->phyclk_khz > dccg->clks.phyclk_khz
 			|| new_clocks->fclk_khz > dccg->clks.fclk_khz
 			|| new_clocks->dcfclk_khz > dccg->clks.dcfclk_khz)
 		send_request_to_increase = true;
 
-	/* make sure dcf clk is before dpp clk to
-	 * make sure we have enough voltage to run dpp clk
-	 */
-	if (send_request_to_increase) {
-		/*use dcfclk to request voltage*/
-		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
-		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
-		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
-	}
-
-	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
-		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
-		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
-
-		send_request_to_lower = true;
-	}
-
 	if (should_set_clock(safe_to_lower, new_clocks->phyclk_khz, dccg->clks.phyclk_khz)) {
-		clock_voltage_req.clocks_in_khz = new_clocks->phyclk_khz;
+		dccg->clks.phyclk_khz = new_clocks->phyclk_khz;
 
 		send_request_to_lower = true;
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->fclk_khz, dccg->clks.fclk_khz)) {
-		dccg->clks.phyclk_khz = new_clocks->fclk_khz;
+		dccg->clks.fclk_khz = new_clocks->fclk_khz;
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_FCLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->fclk_khz;
 		smu_req.hard_min_fclk_khz = new_clocks->fclk_khz;
@@ -610,7 +598,7 @@ static void dcn1_update_clocks(struct dccg *dccg,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dcfclk_khz, dccg->clks.dcfclk_khz)) {
-		dccg->clks.phyclk_khz = new_clocks->dcfclk_khz;
+		dccg->clks.dcfclk_khz = new_clocks->dcfclk_khz;
 		smu_req.hard_min_dcefclk_khz = new_clocks->dcfclk_khz;
 
 		send_request_to_lower = true;
@@ -620,22 +608,39 @@ static void dcn1_update_clocks(struct dccg *dccg,
 			new_clocks->dcfclk_deep_sleep_khz, dccg->clks.dcfclk_deep_sleep_khz)) {
 		dccg->clks.dcfclk_deep_sleep_khz = new_clocks->dcfclk_deep_sleep_khz;
 		smu_req.min_deep_sleep_dcefclk_mhz = new_clocks->dcfclk_deep_sleep_khz;
+
+		send_request_to_lower = true;
 	}
 
-	if (!send_request_to_increase && send_request_to_lower) {
+	/* make sure dcf clk is before dpp clk to
+	 * make sure we have enough voltage to run dpp clk
+	 */
+	if (send_request_to_increase) {
 		/*use dcfclk to request voltage*/
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
 		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		if (pp_smu->set_display_requirement)
+			pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
 	}
 
-	if (new_clocks->phyclk_khz)
-		smu_req.display_count = 1;
-	else
-		smu_req.display_count = 0;
+	/* dcn1 dppclk is tied to dispclk */
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
+		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
+		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
+
+		send_request_to_lower = true;
+	}
+
+	if (!send_request_to_increase && send_request_to_lower) {
+		/*use dcfclk to request voltage*/
+		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DCFCLK;
+		clock_voltage_req.clocks_in_khz = dcn_find_dcfclk_suits_all(dc, new_clocks);
+		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
+		if (pp_smu->set_display_requirement)
+			pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
+	}
 
-	if (pp_smu->set_display_requirement)
-		pp_smu->set_display_requirement(&pp_smu->pp_smu, &smu_req);
 
 	*smu_req_cur = smu_req;
 }
-- 
cgit v1.2.3


From 5f8d084939d0a94d21c32adf2a4e9249e6ce5654 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 30 May 2018 17:12:16 -0400
Subject: drm/amd/display: add CHG_DONE mash/sh defines for dentist

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 1f1899ef773a..7ce0a54e548f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -45,13 +45,17 @@
 
 #define CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh) \
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, mask_sh),\
-	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh)
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh),\
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh),\
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, mask_sh)
 
 #define CLK_REG_FIELD_LIST(type) \
 	type DPREFCLK_SRC_SEL; \
 	type DENTIST_DPREFCLK_WDIVIDER; \
 	type DENTIST_DISPCLK_WDIVIDER; \
-	type DENTIST_DPPCLK_WDIVIDER;
+	type DENTIST_DPPCLK_WDIVIDER; \
+	type DENTIST_DISPCLK_CHG_DONE; \
+	type DENTIST_DPPCLK_CHG_DONE;
 
 struct dccg_shift {
 	CLK_REG_FIELD_LIST(uint8_t)
-- 
cgit v1.2.3


From 294c7e7347d400b2f2d9f09898e8c462f752f500 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 30 May 2018 17:17:27 -0400
Subject: drm/amd/display: change dentist DID enum values to uppercase

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c | 50 ++++++++++++-------------
 1 file changed, 25 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 0a4ae0f49f99..6882dc953a2c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -103,39 +103,39 @@ static const struct state_dependent_clocks dce120_max_clks_by_state[] = {
 
 /* Starting DID for each range */
 enum dentist_base_divider_id {
-	dentist_base_divider_id_1 = 0x08,
-	dentist_base_divider_id_2 = 0x40,
-	dentist_base_divider_id_3 = 0x60,
-	dentist_max_divider_id    = 0x80
+	DENTIST_BASE_DID_1 = 0x08,
+	DENTIST_BASE_DID_2 = 0x40,
+	DENTIST_BASE_DID_3 = 0x60,
+	DENTIST_MAX_DID    = 0x80
 };
 
 /* Starting point and step size for each divider range.*/
 enum dentist_divider_range {
-	dentist_divider_range_1_start = 8,   /* 2.00  */
-	dentist_divider_range_1_step  = 1,   /* 0.25  */
-	dentist_divider_range_2_start = 64,  /* 16.00 */
-	dentist_divider_range_2_step  = 2,   /* 0.50  */
-	dentist_divider_range_3_start = 128, /* 32.00 */
-	dentist_divider_range_3_step  = 4,   /* 1.00  */
-	dentist_divider_range_scale_factor = 4
+	DENTIST_DIVIDER_RANGE_1_START = 8,   /* 2.00  */
+	DENTIST_DIVIDER_RANGE_1_STEP  = 1,   /* 0.25  */
+	DENTIST_DIVIDER_RANGE_2_START = 64,  /* 16.00 */
+	DENTIST_DIVIDER_RANGE_2_STEP  = 2,   /* 0.50  */
+	DENTIST_DIVIDER_RANGE_3_START = 128, /* 32.00 */
+	DENTIST_DIVIDER_RANGE_3_STEP  = 4,   /* 1.00  */
+	DENTIST_DIVIDER_RANGE_SCALE_FACTOR = 4
 };
 
 static int dentist_get_divider_from_did(int did)
 {
-	if (did < dentist_base_divider_id_1)
-		did = dentist_base_divider_id_1;
-	if (did > dentist_max_divider_id)
-		did = dentist_max_divider_id;
-
-	if (did < dentist_base_divider_id_2) {
-		return dentist_divider_range_1_start + dentist_divider_range_1_step
-							* (did - dentist_base_divider_id_1);
-	} else if (did < dentist_base_divider_id_3) {
-		return dentist_divider_range_2_start + dentist_divider_range_2_step
-							* (did - dentist_base_divider_id_2);
+	if (did < DENTIST_BASE_DID_1)
+		did = DENTIST_BASE_DID_1;
+	if (did > DENTIST_MAX_DID)
+		did = DENTIST_MAX_DID;
+
+	if (did < DENTIST_BASE_DID_2) {
+		return DENTIST_DIVIDER_RANGE_1_START + DENTIST_DIVIDER_RANGE_1_STEP
+							* (did - DENTIST_BASE_DID_1);
+	} else if (did < DENTIST_BASE_DID_3) {
+		return DENTIST_DIVIDER_RANGE_2_START + DENTIST_DIVIDER_RANGE_2_STEP
+							* (did - DENTIST_BASE_DID_2);
 	} else {
-		return dentist_divider_range_3_start + dentist_divider_range_3_step
-							* (did - dentist_base_divider_id_3);
+		return DENTIST_DIVIDER_RANGE_3_START + DENTIST_DIVIDER_RANGE_3_STEP
+							* (did - DENTIST_BASE_DID_3);
 	}
 }
 
@@ -186,7 +186,7 @@ static int dce_get_dp_ref_freq_khz(struct dccg *clk)
 	target_div = dentist_get_divider_from_did(dprefclk_wdivider);
 
 	/* Calculate the current DFS clock, in kHz.*/
-	dp_ref_clk_khz = (dentist_divider_range_scale_factor
+	dp_ref_clk_khz = (DENTIST_DIVIDER_RANGE_SCALE_FACTOR
 		* clk_dce->dentist_vco_freq_khz) / target_div;
 
 	return dccg_adjust_dp_ref_freq_for_ss(clk_dce, dp_ref_clk_khz);
-- 
cgit v1.2.3


From d7b539d34acea44ee555a4fe35e77c23b8dc4bc4 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 24 May 2018 15:09:40 -0400
Subject: drm/amd/display: add safe_to_lower support to dcn wm programming

This will prevent watermarks from lowering when unsafe to do so.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c    | 346 +++++++++++++--------
 .../gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h    |   4 +-
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  |   2 +-
 3 files changed, 214 insertions(+), 138 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index 943143efbb82..63b75ac4a1d5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -193,7 +193,8 @@ static uint32_t convert_and_clamp(
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
-		unsigned int refclk_mhz)
+		unsigned int refclk_mhz,
+		bool safe_to_lower)
 {
 	uint32_t force_en = hubbub->ctx->dc->debug.disable_stutter ? 1 : 0;
 	/*
@@ -207,184 +208,257 @@ void hubbub1_program_watermarks(
 
 	/* Repeat for water mark set A, B, C and D. */
 	/* clock state A */
-	prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
-
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->a.urgent_ns > hubbub->watermarks.a.urgent_ns) {
+		hubbub->watermarks.a.urgent_ns = watermarks->a.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->a.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_A, prog_wm_value);
 
-	prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->a.pte_meta_urgent_ns, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->a.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->a.pte_meta_urgent_ns > hubbub->watermarks.a.pte_meta_urgent_ns) {
+		hubbub->watermarks.a.pte_meta_urgent_ns = watermarks->a.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->a.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_A, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_A calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->a.pte_meta_urgent_ns, prog_wm_value);
+	}
 
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A)) {
+		if (safe_to_lower || watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_A, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_A calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->a.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
+
+		if (safe_to_lower || watermarks->a.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.a.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.a.cstate_pstate.cstate_exit_ns =
+					watermarks->a.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->a.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_A calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->a.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.a.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.a.cstate_pstate.pstate_change_ns =
+				watermarks->a.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->a.cstate_pstate.cstate_exit_ns,
+				watermarks->a.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_A, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_A calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->a.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->a.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_A, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_A calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->a.cstate_pstate.pstate_change_ns, prog_wm_value);
-
-
 	/* clock state B */
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.pte_meta_urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->b.urgent_ns > hubbub->watermarks.b.urgent_ns) {
+		hubbub->watermarks.b.urgent_ns = watermarks->b.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->b.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_B, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->b.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->b.pte_meta_urgent_ns > hubbub->watermarks.b.pte_meta_urgent_ns) {
+		hubbub->watermarks.b.pte_meta_urgent_ns = watermarks->b.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->b.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_B calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_B, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_B calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->b.pte_meta_urgent_ns, prog_wm_value);
+	}
 
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B)) {
+		if (safe_to_lower || watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_B, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_B calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->b.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
+		if (safe_to_lower || watermarks->b.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.b.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.b.cstate_pstate.cstate_exit_ns =
+					watermarks->b.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->b.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_B calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
+
+	if (safe_to_lower || watermarks->b.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.b.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.b.cstate_pstate.pstate_change_ns =
+				watermarks->b.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->b.cstate_pstate.cstate_exit_ns,
+				watermarks->b.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_B, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_B calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->b.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->b.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_B, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_B calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->b.cstate_pstate.pstate_change_ns, prog_wm_value);
-
 	/* clock state C */
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.urgent_ns, prog_wm_value);
-
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.pte_meta_urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->c.urgent_ns > hubbub->watermarks.c.urgent_ns) {
+		hubbub->watermarks.c.urgent_ns = watermarks->c.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->c.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_C, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->c.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->c.pte_meta_urgent_ns > hubbub->watermarks.c.pte_meta_urgent_ns) {
+		hubbub->watermarks.c.pte_meta_urgent_ns = watermarks->c.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->c.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_C calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_C, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_C calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->c.pte_meta_urgent_ns, prog_wm_value);
+	}
 
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C)) {
+		if (safe_to_lower || watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_C, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_C calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->c.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
+		if (safe_to_lower || watermarks->c.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.c.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.c.cstate_pstate.cstate_exit_ns =
+					watermarks->c.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->c.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_C calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
+
+	if (safe_to_lower || watermarks->c.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.c.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.c.cstate_pstate.pstate_change_ns =
+				watermarks->c.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->c.cstate_pstate.cstate_exit_ns,
+				watermarks->c.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_C, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_C calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->c.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	prog_wm_value = convert_and_clamp(
-			watermarks->c.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_C, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_C calculated =%d\n\n"
-		"HW register value = 0x%x\n",
-		watermarks->c.cstate_pstate.pstate_change_ns, prog_wm_value);
-
 	/* clock state D */
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.urgent_ns, refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.urgent_ns, prog_wm_value);
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.pte_meta_urgent_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n",
-		watermarks->d.pte_meta_urgent_ns, prog_wm_value);
+	if (safe_to_lower || watermarks->d.urgent_ns > hubbub->watermarks.d.urgent_ns) {
+		hubbub->watermarks.d.urgent_ns = watermarks->d.urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->d.urgent_ns,
+				refclk_mhz, 0x1fffff);
+		REG_WRITE(DCHUBBUB_ARB_DATA_URGENCY_WATERMARK_D, prog_wm_value);
 
+		DC_LOG_BANDWIDTH_CALCS("URGENCY_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n",
+			watermarks->d.urgent_ns, prog_wm_value);
+	}
 
-	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
-		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
+	if (safe_to_lower || watermarks->d.pte_meta_urgent_ns > hubbub->watermarks.d.pte_meta_urgent_ns) {
+		hubbub->watermarks.d.pte_meta_urgent_ns = watermarks->d.pte_meta_urgent_ns;
+		prog_wm_value = convert_and_clamp(watermarks->d.pte_meta_urgent_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_ENTER_WATERMARK_D calculated =%d\n"
+		REG_WRITE(DCHUBBUB_ARB_PTE_META_URGENCY_WATERMARK_D, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("PTE_META_URGENCY_WATERMARK_D calculated =%d\n"
 			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+			watermarks->d.pte_meta_urgent_ns, prog_wm_value);
+	}
+
+	if (REG(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D)) {
+		if (safe_to_lower || watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns
+				> hubbub->watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns) {
+			hubbub->watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns =
+					watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_ENTER_WATERMARK_D, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_ENTER_EXIT_WATERMARK_D calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->d.cstate_pstate.cstate_enter_plus_exit_ns, prog_wm_value);
+		}
 
+		if (safe_to_lower || watermarks->d.cstate_pstate.cstate_exit_ns
+				> hubbub->watermarks.d.cstate_pstate.cstate_exit_ns) {
+			hubbub->watermarks.d.cstate_pstate.cstate_exit_ns =
+					watermarks->d.cstate_pstate.cstate_exit_ns;
+			prog_wm_value = convert_and_clamp(
+					watermarks->d.cstate_pstate.cstate_exit_ns,
+					refclk_mhz, 0x1fffff);
+			REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
+			DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_D calculated =%d\n"
+				"HW register value = 0x%x\n",
+				watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		}
+	}
 
+	if (safe_to_lower || watermarks->d.cstate_pstate.pstate_change_ns
+			> hubbub->watermarks.d.cstate_pstate.pstate_change_ns) {
+		hubbub->watermarks.d.cstate_pstate.pstate_change_ns =
+				watermarks->d.cstate_pstate.pstate_change_ns;
 		prog_wm_value = convert_and_clamp(
-				watermarks->d.cstate_pstate.cstate_exit_ns,
+				watermarks->d.cstate_pstate.pstate_change_ns,
 				refclk_mhz, 0x1fffff);
-		REG_WRITE(DCHUBBUB_ARB_ALLOW_SR_EXIT_WATERMARK_D, prog_wm_value);
-		DC_LOG_BANDWIDTH_CALCS("SR_EXIT_WATERMARK_D calculated =%d\n"
-			"HW register value = 0x%x\n",
-			watermarks->d.cstate_pstate.cstate_exit_ns, prog_wm_value);
+		REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
+		DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
+			"HW register value = 0x%x\n\n",
+			watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-
-	prog_wm_value = convert_and_clamp(
-			watermarks->d.cstate_pstate.pstate_change_ns,
-			refclk_mhz, 0x1fffff);
-	REG_WRITE(DCHUBBUB_ARB_ALLOW_DRAM_CLK_CHANGE_WATERMARK_D, prog_wm_value);
-	DC_LOG_BANDWIDTH_CALCS("DRAM_CLK_CHANGE_WATERMARK_D calculated =%d\n"
-		"HW register value = 0x%x\n\n",
-		watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
-
 	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
 			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index 6315a0e6b0d6..0ca39cb71968 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -185,6 +185,7 @@ struct hubbub {
 	const struct dcn_hubbub_shift *shifts;
 	const struct dcn_hubbub_mask *masks;
 	unsigned int debug_test_index_pstate;
+	struct dcn_watermark_set watermarks;
 };
 
 void hubbub1_update_dchub(
@@ -197,7 +198,8 @@ bool hubbub1_verify_allow_pstate_change_high(
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
-		unsigned int refclk_mhz);
+		unsigned int refclk_mhz,
+		bool safe_to_lower);
 
 void hubbub1_toggle_watermark_change_req(
 		struct hubbub *hubbub);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 5b40c1c4d9e6..7d9c10b6d99b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2299,7 +2299,7 @@ static void dcn10_apply_ctx_for_surface(
 
 		/* watermark is for all pipes */
 		hubbub1_program_watermarks(dc->res_pool->hubbub,
-				&context->bw.dcn.watermarks, ref_clk_mhz);
+				&context->bw.dcn.watermarks, ref_clk_mhz, true);
 
 		if (dc->debug.sanity_checks) {
 			/* pstate stuck check after watermark update */
-- 
cgit v1.2.3


From 836758ffe78a7bc45af9484e34cba2b685f2a0b2 Mon Sep 17 00:00:00 2001
From: "Zheng, XueLai(Eric)" <XueLai.Zheng@amd.com>
Date: Tue, 8 May 2018 12:25:15 -0400
Subject: drm/amd/display: support ACrYCb2101010

Signed-off-by: XueLai(Eric), Zheng <XueLai.Zheng@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h      | 1 +
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index d31023d57b58..14afbc5c0a62 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -199,6 +199,7 @@ enum surface_pixel_format {
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCrCb,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCbCr,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_10bpc_YCrCb,
+		SURFACE_PIXEL_FORMAT_SUBSAMPLE_END,
 	SURFACE_PIXEL_FORMAT_INVALID
 
 	/*grow 444 video here if necessary */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index c28085be39ff..93f52c58bc69 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -166,7 +166,7 @@ void hubp1_program_size_and_rotation(
 	/* Program data and meta surface pitch (calculation from addrlib)
 	 * 444 or 420 luma
 	 */
-	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN) {
+	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN && format < SURFACE_PIXEL_FORMAT_SUBSAMPLE_END) {
 		ASSERT(plane_size->video.chroma_pitch != 0);
 		/* Chroma pitch zero can cause system hang! */
 
-- 
cgit v1.2.3


From f3e077d95ca0a016fdf3d6b1e97a9910dfdaff17 Mon Sep 17 00:00:00 2001
From: Wesley Chalmers <Wesley.Chalmers@amd.com>
Date: Tue, 29 May 2018 17:45:05 -0400
Subject: drm/amd/display: fix use of uninitialized memory

DML does not calculate chroma values for RQ when surface is not YUV, but DC
will unconditionally use the uninitialized values for HW programming.
This does not cause visual corruption since HW will ignore garbage chroma
values when surface is not YUV, but causes presubmission tests to fail
golden value comparison.

Signed-off-by: Wesley Chalmers <Wesley.Chalmers@amd.com>
Signed-off-by: Eryk Brol <eryk.brol@amd.com>
Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
index c2037daa8e66..0efbf411667a 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
@@ -239,6 +239,8 @@ void dml1_extract_rq_regs(
 	extract_rq_sizing_regs(mode_lib, &(rq_regs->rq_regs_l), rq_param.sizing.rq_l);
 	if (rq_param.yuv420)
 		extract_rq_sizing_regs(mode_lib, &(rq_regs->rq_regs_c), rq_param.sizing.rq_c);
+	else
+		memset(&(rq_regs->rq_regs_c), 0, sizeof(rq_regs->rq_regs_c));
 
 	rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height);
 	rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height);
-- 
cgit v1.2.3


From 0176e8c4c0f35555f7554ec3097283187b33ccbd Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 8 May 2018 12:25:29 -0400
Subject: drm/amd/display: dal 3.1.49

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 82e0f55bc3e4..d1ac9676a539 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.48"
+#define DC_VER "3.1.49"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From dc38fd9dac3e15538c7c238c4dfb98ceb408fa19 Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Fri, 1 Jun 2018 09:49:06 -0400
Subject: drm/amd/display: Add front end for dp debugfs files

As part of hardware certification, read-write access to
the link rate, lane count, voltage swing, pre-emphasis,
and PHY test pattern of DP connectors is required.  This commit
adds debugfs files that will correspond to these values.
The file operations are not yet implemented: currently
writing or reading them does nothing.

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/Makefile     |   2 +-
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c  |  10 ++
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c  | 170 +++++++++++++++++++++
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h  |  34 +++++
 4 files changed, 215 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
 create mode 100644 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index af16973f2c41..589c60ec59bd 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -32,7 +32,7 @@ AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o
 endif
 
 ifneq ($(CONFIG_DEBUG_FS),)
-AMDGPUDM += amdgpu_dm_crc.o
+AMDGPUDM += amdgpu_dm_crc.o amdgpu_dm_debugfs.o
 endif
 
 subdir-ccflags-y += -I$(FULL_AMD_DISPLAY_PATH)/dc
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 66bd3cc3e387..356ac27d0180 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -39,6 +39,9 @@
 #include "dm_helpers.h"
 #include "dm_services_types.h"
 #include "amdgpu_dm_mst_types.h"
+#if defined(CONFIG_DEBUG_FS)
+#include "amdgpu_dm_debugfs.h"
+#endif
 
 #include "ivsrcid/ivsrcid_vislands30.h"
 
@@ -3619,6 +3622,13 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm,
 		&aconnector->base, &aencoder->base);
 
 	drm_connector_register(&aconnector->base);
+#if defined(CONFIG_DEBUG_FS)
+	res = connector_debugfs_init(aconnector);
+	if (res) {
+		DRM_ERROR("Failed to create debugfs for connector");
+		goto out_free;
+	}
+#endif
 
 	if (connector_type == DRM_MODE_CONNECTOR_DisplayPort
 		|| connector_type == DRM_MODE_CONNECTOR_eDP)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
new file mode 100644
index 000000000000..cf5ea69e46ad
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -0,0 +1,170 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include <linux/debugfs.h>
+
+#include "dc.h"
+#include "dc_link.h"
+
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+#include "amdgpu_dm_debugfs.h"
+
+static ssize_t dp_link_rate_debugfs_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to read link rate */
+	return 1;
+}
+
+static ssize_t dp_link_rate_debugfs_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to write link rate */
+	return 1;
+}
+
+static ssize_t dp_lane_count_debugfs_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to read lane count */
+	return 1;
+}
+
+static ssize_t dp_lane_count_debugfs_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to write lane count */
+	return 1;
+}
+
+static ssize_t dp_voltage_swing_debugfs_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to read voltage swing */
+	return 1;
+}
+
+static ssize_t dp_voltage_swing_debugfs_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to write voltage swing */
+	return 1;
+}
+
+static ssize_t dp_pre_emphasis_debugfs_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to read pre-emphasis */
+	return 1;
+}
+
+static ssize_t dp_pre_emphasis_debugfs_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to write pre-emphasis */
+	return 1;
+}
+
+static ssize_t dp_phy_test_pattern_debugfs_read(struct file *f, char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to read PHY test pattern */
+	return 1;
+}
+
+static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __user *buf,
+				 size_t size, loff_t *pos)
+{
+	/* TODO: create method to write PHY test pattern */
+	return 1;
+}
+
+static const struct file_operations dp_link_rate_fops = {
+	.owner = THIS_MODULE,
+	.read = dp_link_rate_debugfs_read,
+	.write = dp_link_rate_debugfs_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_lane_count_fops = {
+	.owner = THIS_MODULE,
+	.read = dp_lane_count_debugfs_read,
+	.write = dp_lane_count_debugfs_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_voltage_swing_fops = {
+	.owner = THIS_MODULE,
+	.read = dp_voltage_swing_debugfs_read,
+	.write = dp_voltage_swing_debugfs_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_pre_emphasis_fops = {
+	.owner = THIS_MODULE,
+	.read = dp_pre_emphasis_debugfs_read,
+	.write = dp_pre_emphasis_debugfs_write,
+	.llseek = default_llseek
+};
+
+static const struct file_operations dp_phy_test_pattern_fops = {
+	.owner = THIS_MODULE,
+	.read = dp_phy_test_pattern_debugfs_read,
+	.write = dp_phy_test_pattern_debugfs_write,
+	.llseek = default_llseek
+};
+
+static const struct {
+	char *name;
+	const struct file_operations *fops;
+} dp_debugfs_entries[] = {
+		{"link_rate", &dp_link_rate_fops},
+		{"lane_count", &dp_lane_count_fops},
+		{"voltage_swing", &dp_voltage_swing_fops},
+		{"pre_emphasis", &dp_pre_emphasis_fops},
+		{"phy_test_pattern", &dp_phy_test_pattern_fops}
+};
+
+int connector_debugfs_init(struct amdgpu_dm_connector *connector)
+{
+	int i;
+	struct dentry *ent, *dir = connector->base.debugfs_entry;
+
+	if (connector->base.connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
+		for (i = 0; i < ARRAY_SIZE(dp_debugfs_entries); i++) {
+			ent = debugfs_create_file(dp_debugfs_entries[i].name,
+						  0644,
+						  dir,
+						  connector,
+						  dp_debugfs_entries[i].fops);
+			if (IS_ERR(ent))
+				return PTR_ERR(ent);
+		}
+	}
+
+	return 0;
+}
+
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
new file mode 100644
index 000000000000..d9ed1b2aa811
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __AMDGPU_DM_DEBUGFS_H__
+#define __AMDGPU_DM_DEBUGFS_H__
+
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+
+int connector_debugfs_init(struct amdgpu_dm_connector *connector);
+
+#endif
-- 
cgit v1.2.3


From 9f6e2842d0681a9a6579618a301c8ae06e20a6cd Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 5 Jun 2018 09:13:56 -0400
Subject: drm/amd/display: dal 3.1.50

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index d1ac9676a539..cdab7b0453c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.49"
+#define DC_VER "3.1.50"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From b9c1c67aeb8805015f02efb0a6a6ddf68ea8a4b4 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Tue, 5 Jun 2018 12:54:38 -0400
Subject: drm/amd/display: clean rq/dlg/ttu reg structs before calculations

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c              | 4 ++++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c     | 8 ++++++--
 drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c | 2 --
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index b8195e5a0676..ac4451adeec9 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -423,6 +423,10 @@ static void dcn_bw_calc_rq_dlg_ttu(
 	int total_flip_bytes = 0;
 	int i;
 
+	memset(dlg_regs, 0, sizeof(*dlg_regs));
+	memset(ttu_regs, 0, sizeof(*ttu_regs));
+	memset(rq_regs, 0, sizeof(*rq_regs));
+
 	for (i = 0; i < number_of_planes; i++) {
 		total_active_bw += v->read_bandwidth[i];
 		total_prefetch_bw += v->prefetch_bandwidth[i];
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 7d9c10b6d99b..cc12c4757f8b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -151,19 +151,23 @@ static void dcn10_log_hubp_states(struct dc *dc)
 
 	DTN_INFO("\n=========RQ========\n");
 	DTN_INFO("HUBP:  drq_exp_m  prq_exp_m  mrq_exp_m  crq_exp_m  plane1_ba  L:chunk_s  min_chu_s  meta_ch_s"
+		"  min_m_c_s  dpte_gr_s  mpte_gr_s  swath_hei  pte_row_h  C:chunk_s  min_chu_s  meta_ch_s"
 		"  min_m_c_s  dpte_gr_s  mpte_gr_s  swath_hei  pte_row_h\n");
 	for (i = 0; i < pool->pipe_count; i++) {
 		struct dcn_hubp_state *s = &(TO_DCN10_HUBP(pool->hubps[i])->state);
 		struct _vcs_dpi_display_rq_regs_st *rq_regs = &s->rq_regs;
 
 		if (!s->blank_en)
-			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
+			DTN_INFO("[%2d]:  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh  %8xh\n",
 				pool->hubps[i]->inst, rq_regs->drq_expansion_mode, rq_regs->prq_expansion_mode, rq_regs->mrq_expansion_mode,
 				rq_regs->crq_expansion_mode, rq_regs->plane1_base_address, rq_regs->rq_regs_l.chunk_size,
 				rq_regs->rq_regs_l.min_chunk_size, rq_regs->rq_regs_l.meta_chunk_size,
 				rq_regs->rq_regs_l.min_meta_chunk_size, rq_regs->rq_regs_l.dpte_group_size,
 				rq_regs->rq_regs_l.mpte_group_size, rq_regs->rq_regs_l.swath_height,
-				rq_regs->rq_regs_l.pte_row_height_linear);
+				rq_regs->rq_regs_l.pte_row_height_linear, rq_regs->rq_regs_c.chunk_size, rq_regs->rq_regs_c.min_chunk_size,
+				rq_regs->rq_regs_c.meta_chunk_size, rq_regs->rq_regs_c.min_meta_chunk_size,
+				rq_regs->rq_regs_c.dpte_group_size, rq_regs->rq_regs_c.mpte_group_size,
+				rq_regs->rq_regs_c.swath_height, rq_regs->rq_regs_c.pte_row_height_linear);
 	}
 
 	DTN_INFO("========DLG========\n");
diff --git a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
index 0efbf411667a..c2037daa8e66 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/dml1_display_rq_dlg_calc.c
@@ -239,8 +239,6 @@ void dml1_extract_rq_regs(
 	extract_rq_sizing_regs(mode_lib, &(rq_regs->rq_regs_l), rq_param.sizing.rq_l);
 	if (rq_param.yuv420)
 		extract_rq_sizing_regs(mode_lib, &(rq_regs->rq_regs_c), rq_param.sizing.rq_c);
-	else
-		memset(&(rq_regs->rq_regs_c), 0, sizeof(rq_regs->rq_regs_c));
 
 	rq_regs->rq_regs_l.swath_height = dml_log2(rq_param.dlg.rq_l.swath_height);
 	rq_regs->rq_regs_c.swath_height = dml_log2(rq_param.dlg.rq_c.swath_height);
-- 
cgit v1.2.3


From d4fa93e03839c3e4e9d16020f1a3c78ae36c646a Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 5 Jun 2018 09:14:22 -0400
Subject: drm/amd/display: dal 3.1.51

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index cdab7b0453c5..cbcdbd9b9910 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.50"
+#define DC_VER "3.1.51"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 6f66ccf0aa8f6d430d161a1ac2bc43e665d2fc59 Mon Sep 17 00:00:00 2001
From: Roman Li <Roman.Li@amd.com>
Date: Tue, 5 Jun 2018 14:24:53 -0400
Subject: drm/amd/display: fix potential infinite loop in fbc path

- Fixing integer overflow bug in wait_for_fbc_state_changed()
- Correct the max value of retries for the corresponding warning

Signed-off-by: Roman Li <Roman.Li@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
index df027013e50c..1f7f25013217 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_compressor.c
@@ -143,7 +143,7 @@ static void wait_for_fbc_state_changed(
 	struct dce110_compressor *cp110,
 	bool enabled)
 {
-	uint16_t counter = 0;
+	uint32_t counter = 0;
 	uint32_t addr = mmFBC_STATUS;
 	uint32_t value;
 
@@ -158,7 +158,7 @@ static void wait_for_fbc_state_changed(
 		counter++;
 	}
 
-	if (counter == 10) {
+	if (counter == 1000) {
 		DC_LOG_WARNING("%s: wait counter exceeded, changes to HW not applied",
 			__func__);
 	} else {
-- 
cgit v1.2.3


From 5094ffac6bd265130f735dd500532cef39f0d72f Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Thu, 31 May 2018 14:49:00 -0400
Subject: drm/amd/display: Enable PPLib calls from DC on linux

Set the powerplay debug flag to false for both Windows and Linux
to allow the calls to pplib. So we can retrieve the clock values
from powerplay instead of using default hardcoded values.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index b5a727f7e880..1761e1a40dad 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -437,7 +437,7 @@ static const struct dc_debug debug_defaults_drv = {
 		 */
 		.min_disp_clk_khz = 100000,
 
-		.disable_pplib_clock_request = true,
+		.disable_pplib_clock_request = false,
 		.disable_pplib_wm_range = false,
 		.pplib_wm_report_mode = WM_REPORT_DEFAULT,
 		.pipe_split_policy = MPC_SPLIT_AVOID_MULT_DISP,
-- 
cgit v1.2.3


From 015ec75918698e63f770c9bee0752ce802ed55e2 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Thu, 31 May 2018 17:31:14 -0400
Subject: drm/amd/display: Add dmpp clks types for conversion

Add more cases for dm_pp clks translator into pp clks so
we can pass the right structures to the powerplay.
Use clks translator instead of massive switch statement.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 41 ++++++++++------------
 1 file changed, 18 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index 0ac428299f5f..a87a5946798c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -195,6 +195,21 @@ static enum amd_pp_clock_type dc_to_pp_clock_type(
 	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
 		amd_pp_clk_type = amd_pp_mem_clock;
 		break;
+	case DM_PP_CLOCK_TYPE_DCEFCLK:
+		amd_pp_clk_type  = amd_pp_dcef_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DCFCLK:
+		amd_pp_clk_type = amd_pp_dcf_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_PIXELCLK:
+		amd_pp_clk_type = amd_pp_pixel_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_FCLK:
+		amd_pp_clk_type = amd_pp_f_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
+		amd_pp_clk_type = amd_pp_dpp_clock;
+		break;
 	default:
 		DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n",
 				dm_pp_clk_type);
@@ -424,32 +439,12 @@ bool dm_pp_apply_clock_for_voltage_request(
 	struct amdgpu_device *adev = ctx->driver_context;
 	struct pp_display_clock_request pp_clock_request = {0};
 	int ret = 0;
-	switch (clock_for_voltage_req->clk_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		pp_clock_request.clock_type = amd_pp_disp_clock;
-		break;
-
-	case DM_PP_CLOCK_TYPE_DCEFCLK:
-		pp_clock_request.clock_type = amd_pp_dcef_clock;
-		break;
 
-	case DM_PP_CLOCK_TYPE_DCFCLK:
-		pp_clock_request.clock_type = amd_pp_dcf_clock;
-		break;
-
-	case DM_PP_CLOCK_TYPE_PIXELCLK:
-		pp_clock_request.clock_type = amd_pp_pixel_clock;
-		break;
-
-	case DM_PP_CLOCK_TYPE_FCLK:
-		pp_clock_request.clock_type = amd_pp_f_clock;
-		break;
+	pp_clock_request.clock_type = dc_to_pp_clock_type(clock_for_voltage_req->clk_type);
+	pp_clock_request.clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
 
-	default:
+	if (!pp_clock_request.clock_type)
 		return false;
-	}
-
-	pp_clock_request.clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
 
 	if (adev->powerplay.pp_funcs->display_clock_voltage_request)
 		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
-- 
cgit v1.2.3


From 724a75524b1c77ea8abb96c21cdba05385b22b39 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Thu, 31 May 2018 14:44:18 -0400
Subject: drm/amd/display: Convert 10kHz clks from PPLib into kHz

The driver is expecting clock frequency in kHz, while SMU returns
the values in 10kHz, which causes the bandwidth validation to fail

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c    | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index a87a5946798c..a19df20b557b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -267,8 +267,9 @@ static void pp_to_dc_clock_levels_with_latency(
 			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
 
 	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_DEBUG("DM_PPLIB:\t %d\n", pp_clks->data[i].clocks_in_khz);
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
+		/* translate 10kHz to kHz */
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
 		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
 	}
 }
@@ -294,8 +295,9 @@ static void pp_to_dc_clock_levels_with_voltage(
 			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
 
 	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->data[i].clocks_in_khz);
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
+		DRM_INFO("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
+		/* translate 10kHz to kHz */
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
 		clk_level_info->data[i].voltage_in_mv = pp_clks->data[i].voltage_in_mv;
 	}
 }
@@ -471,8 +473,9 @@ bool dm_pp_get_static_clocks(
 		return false;
 
 	static_clk_info->max_clocks_state = pp_clk_info.max_clocks_state;
-	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock;
-	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock;
+	/* translate 10kHz to kHz */
+	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock * 10;
+	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock * 10;
 
 	return true;
 }
-- 
cgit v1.2.3


From 746c58ed225b9439a8272f755a1c60f795de9a3c Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Tue, 5 Jun 2018 07:40:04 -0400
Subject: drm/amd/display: move dml defaults to respective dcn resource files

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dcn10/dcn10_resource.c  | 62 +++++++++++++++++++++
 .../gpu/drm/amd/display/dc/dml/display_mode_lib.c  | 63 +---------------------
 2 files changed, 64 insertions(+), 61 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 1761e1a40dad..2db08b99db56 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -65,6 +65,68 @@
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
 
+const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
+	.rob_buffer_size_kbytes = 64,
+	.det_buffer_size_kbytes = 164,
+	.dpte_buffer_size_in_pte_reqs = 42,
+	.dpp_output_buffer_pixels = 2560,
+	.opp_output_buffer_lines = 1,
+	.pixel_chunk_size_kbytes = 8,
+	.pte_enable = 1,
+	.pte_chunk_size_kbytes = 2,
+	.meta_chunk_size_kbytes = 2,
+	.writeback_chunk_size_kbytes = 2,
+	.line_buffer_size_bits = 589824,
+	.max_line_buffer_lines = 12,
+	.IsLineBufferBppFixed = 0,
+	.LineBufferFixedBpp = -1,
+	.writeback_luma_buffer_size_kbytes = 12,
+	.writeback_chroma_buffer_size_kbytes = 8,
+	.max_num_dpp = 4,
+	.max_num_wb = 2,
+	.max_dchub_pscl_bw_pix_per_clk = 4,
+	.max_pscl_lb_bw_pix_per_clk = 2,
+	.max_lb_vscl_bw_pix_per_clk = 4,
+	.max_vscl_hscl_bw_pix_per_clk = 4,
+	.max_hscl_ratio = 4,
+	.max_vscl_ratio = 4,
+	.hscl_mults = 4,
+	.vscl_mults = 4,
+	.max_hscl_taps = 8,
+	.max_vscl_taps = 8,
+	.dispclk_ramp_margin_percent = 1,
+	.underscan_factor = 1.10,
+	.min_vblank_lines = 14,
+	.dppclk_delay_subtotal = 90,
+	.dispclk_delay_subtotal = 42,
+	.dcfclk_cstate_latency = 10,
+	.max_inter_dcn_tile_repeaters = 8,
+	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
+	.bug_forcing_LC_req_same_size_fixed = 0,
+};
+
+const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
+	.sr_exit_time_us = 9.0,
+	.sr_enter_plus_exit_time_us = 11.0,
+	.urgent_latency_us = 4.0,
+	.writeback_latency_us = 12.0,
+	.ideal_dram_bw_after_urgent_percent = 80.0,
+	.max_request_size_bytes = 256,
+	.downspread_percent = 0.5,
+	.dram_page_open_time_ns = 50.0,
+	.dram_rw_turnaround_time_ns = 17.5,
+	.dram_return_buffer_per_channel_bytes = 8192,
+	.round_trip_ping_latency_dcfclk_cycles = 128,
+	.urgent_out_of_order_return_per_channel_bytes = 256,
+	.channel_interleave_bytes = 256,
+	.num_banks = 8,
+	.num_chans = 2,
+	.vmm_page_size_bytes = 4096,
+	.dram_clock_change_latency_us = 17.0,
+	.writeback_dram_clock_change_latency_us = 23.0,
+	.return_bus_width_bytes = 64,
+};
+
 #ifndef mmDP0_DP_DPHY_INTERNAL_CTRL
 	#define mmDP0_DP_DPHY_INTERNAL_CTRL		0x210f
 	#define mmDP0_DP_DPHY_INTERNAL_CTRL_BASE_IDX	2
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
index fd9d97aab071..dddeb0d4db8f 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.c
@@ -26,67 +26,8 @@
 #include "display_mode_lib.h"
 #include "dc_features.h"
 
-static const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
-	.rob_buffer_size_kbytes = 64,
-	.det_buffer_size_kbytes = 164,
-	.dpte_buffer_size_in_pte_reqs = 42,
-	.dpp_output_buffer_pixels = 2560,
-	.opp_output_buffer_lines = 1,
-	.pixel_chunk_size_kbytes = 8,
-	.pte_enable = 1,
-	.pte_chunk_size_kbytes = 2,
-	.meta_chunk_size_kbytes = 2,
-	.writeback_chunk_size_kbytes = 2,
-	.line_buffer_size_bits = 589824,
-	.max_line_buffer_lines = 12,
-	.IsLineBufferBppFixed = 0,
-	.LineBufferFixedBpp = -1,
-	.writeback_luma_buffer_size_kbytes = 12,
-	.writeback_chroma_buffer_size_kbytes = 8,
-	.max_num_dpp = 4,
-	.max_num_wb = 2,
-	.max_dchub_pscl_bw_pix_per_clk = 4,
-	.max_pscl_lb_bw_pix_per_clk = 2,
-	.max_lb_vscl_bw_pix_per_clk = 4,
-	.max_vscl_hscl_bw_pix_per_clk = 4,
-	.max_hscl_ratio = 4,
-	.max_vscl_ratio = 4,
-	.hscl_mults = 4,
-	.vscl_mults = 4,
-	.max_hscl_taps = 8,
-	.max_vscl_taps = 8,
-	.dispclk_ramp_margin_percent = 1,
-	.underscan_factor = 1.10,
-	.min_vblank_lines = 14,
-	.dppclk_delay_subtotal = 90,
-	.dispclk_delay_subtotal = 42,
-	.dcfclk_cstate_latency = 10,
-	.max_inter_dcn_tile_repeaters = 8,
-	.can_vstartup_lines_exceed_vsync_plus_back_porch_lines_minus_one = 0,
-	.bug_forcing_LC_req_same_size_fixed = 0,
-};
-
-static const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc = {
-	.sr_exit_time_us = 9.0,
-	.sr_enter_plus_exit_time_us = 11.0,
-	.urgent_latency_us = 4.0,
-	.writeback_latency_us = 12.0,
-	.ideal_dram_bw_after_urgent_percent = 80.0,
-	.max_request_size_bytes = 256,
-	.downspread_percent = 0.5,
-	.dram_page_open_time_ns = 50.0,
-	.dram_rw_turnaround_time_ns = 17.5,
-	.dram_return_buffer_per_channel_bytes = 8192,
-	.round_trip_ping_latency_dcfclk_cycles = 128,
-	.urgent_out_of_order_return_per_channel_bytes = 256,
-	.channel_interleave_bytes = 256,
-	.num_banks = 8,
-	.num_chans = 2,
-	.vmm_page_size_bytes = 4096,
-	.dram_clock_change_latency_us = 17.0,
-	.writeback_dram_clock_change_latency_us = 23.0,
-	.return_bus_width_bytes = 64,
-};
+extern const struct _vcs_dpi_ip_params_st dcn1_0_ip;
+extern const struct _vcs_dpi_soc_bounding_box_st dcn1_0_soc;
 
 static void set_soc_bounding_box(struct _vcs_dpi_soc_bounding_box_st *soc, enum dml_project project)
 {
-- 
cgit v1.2.3


From f7c1ed341ae0807e55fc583fbd5582ff4ef35a98 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Fri, 1 Jun 2018 15:02:55 -0400
Subject: drm/amd/display: Moving powerplay functions to a separate class

Moving powerplay functions to a new amdgpu_dm_pp_smu class
and cleaning dm_services class from unused headers.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/Makefile     |   2 +-
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c   | 525 +++++++++++++++++++++
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_services.c | 492 -------------------
 3 files changed, 526 insertions(+), 493 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
index 589c60ec59bd..94911871eb9b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/Makefile
@@ -28,7 +28,7 @@
 AMDGPUDM = amdgpu_dm.o amdgpu_dm_irq.o amdgpu_dm_mst_types.o amdgpu_dm_color.o
 
 ifneq ($(CONFIG_DRM_AMD_DC),)
-AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o
+AMDGPUDM += amdgpu_dm_services.o amdgpu_dm_helpers.o amdgpu_dm_pp_smu.o
 endif
 
 ifneq ($(CONFIG_DEBUG_FS),)
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
new file mode 100644
index 000000000000..ad96e2a2b3cf
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -0,0 +1,525 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ */
+#include <linux/string.h>
+#include <linux/acpi.h>
+
+#include <drm/drmP.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/amdgpu_drm.h>
+#include "dm_services.h"
+#include "amdgpu.h"
+#include "amdgpu_dm.h"
+#include "amdgpu_dm_irq.h"
+#include "amdgpu_pm.h"
+#include "dm_pp_smu.h"
+#include "../../powerplay/inc/hwmgr.h"
+#include "../../powerplay/hwmgr/smu10_hwmgr.h"
+
+
+bool dm_pp_apply_display_requirements(
+		const struct dc_context *ctx,
+		const struct dm_pp_display_configuration *pp_display_cfg)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+
+	if (adev->pm.dpm_enabled) {
+
+		memset(&adev->pm.pm_display_cfg, 0,
+				sizeof(adev->pm.pm_display_cfg));
+
+		adev->pm.pm_display_cfg.cpu_cc6_disable =
+			pp_display_cfg->cpu_cc6_disable;
+
+		adev->pm.pm_display_cfg.cpu_pstate_disable =
+			pp_display_cfg->cpu_pstate_disable;
+
+		adev->pm.pm_display_cfg.cpu_pstate_separation_time =
+			pp_display_cfg->cpu_pstate_separation_time;
+
+		adev->pm.pm_display_cfg.nb_pstate_switch_disable =
+			pp_display_cfg->nb_pstate_switch_disable;
+
+		adev->pm.pm_display_cfg.num_display =
+				pp_display_cfg->display_count;
+		adev->pm.pm_display_cfg.num_path_including_non_display =
+				pp_display_cfg->display_count;
+
+		adev->pm.pm_display_cfg.min_core_set_clock =
+				pp_display_cfg->min_engine_clock_khz/10;
+		adev->pm.pm_display_cfg.min_core_set_clock_in_sr =
+				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
+		adev->pm.pm_display_cfg.min_mem_set_clock =
+				pp_display_cfg->min_memory_clock_khz/10;
+
+		adev->pm.pm_display_cfg.multi_monitor_in_sync =
+				pp_display_cfg->all_displays_in_sync;
+		adev->pm.pm_display_cfg.min_vblank_time =
+				pp_display_cfg->avail_mclk_switch_time_us;
+
+		adev->pm.pm_display_cfg.display_clk =
+				pp_display_cfg->disp_clk_khz/10;
+
+		adev->pm.pm_display_cfg.dce_tolerable_mclk_in_active_latency =
+				pp_display_cfg->avail_mclk_switch_time_in_disp_active_us;
+
+		adev->pm.pm_display_cfg.crtc_index = pp_display_cfg->crtc_index;
+		adev->pm.pm_display_cfg.line_time_in_us =
+				pp_display_cfg->line_time_in_us;
+
+		adev->pm.pm_display_cfg.vrefresh = pp_display_cfg->disp_configs[0].v_refresh;
+		adev->pm.pm_display_cfg.crossfire_display_index = -1;
+		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
+
+		/* TODO: complete implementation of
+		 * pp_display_configuration_change().
+		 * Follow example of:
+		 * PHM_StoreDALConfigurationData - powerplay\hwmgr\hardwaremanager.c
+		 * PP_IRI_DisplayConfigurationChange - powerplay\eventmgr\iri.c */
+		if (adev->powerplay.pp_funcs->display_configuration_change)
+			adev->powerplay.pp_funcs->display_configuration_change(
+				adev->powerplay.pp_handle,
+				&adev->pm.pm_display_cfg);
+
+		/* TODO: replace by a separate call to 'apply display cfg'? */
+		amdgpu_pm_compute_clocks(adev);
+	}
+
+	return true;
+}
+
+static void get_default_clock_levels(
+		enum dm_pp_clock_type clk_type,
+		struct dm_pp_clock_levels *clks)
+{
+	uint32_t disp_clks_in_khz[6] = {
+			300000, 400000, 496560, 626090, 685720, 757900 };
+	uint32_t sclks_in_khz[6] = {
+			300000, 360000, 423530, 514290, 626090, 720000 };
+	uint32_t mclks_in_khz[2] = { 333000, 800000 };
+
+	switch (clk_type) {
+	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
+		clks->num_levels = 6;
+		memmove(clks->clocks_in_khz, disp_clks_in_khz,
+				sizeof(disp_clks_in_khz));
+		break;
+	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
+		clks->num_levels = 6;
+		memmove(clks->clocks_in_khz, sclks_in_khz,
+				sizeof(sclks_in_khz));
+		break;
+	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
+		clks->num_levels = 2;
+		memmove(clks->clocks_in_khz, mclks_in_khz,
+				sizeof(mclks_in_khz));
+		break;
+	default:
+		clks->num_levels = 0;
+		break;
+	}
+}
+
+static enum amd_pp_clock_type dc_to_pp_clock_type(
+		enum dm_pp_clock_type dm_pp_clk_type)
+{
+	enum amd_pp_clock_type amd_pp_clk_type = 0;
+
+	switch (dm_pp_clk_type) {
+	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
+		amd_pp_clk_type = amd_pp_disp_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
+		amd_pp_clk_type = amd_pp_sys_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
+		amd_pp_clk_type = amd_pp_mem_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DCEFCLK:
+		amd_pp_clk_type  = amd_pp_dcef_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DCFCLK:
+		amd_pp_clk_type = amd_pp_dcf_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_PIXELCLK:
+		amd_pp_clk_type = amd_pp_pixel_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_FCLK:
+		amd_pp_clk_type = amd_pp_f_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
+		amd_pp_clk_type = amd_pp_dpp_clock;
+		break;
+	default:
+		DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n",
+				dm_pp_clk_type);
+		break;
+	}
+
+	return amd_pp_clk_type;
+}
+
+static void pp_to_dc_clock_levels(
+		const struct amd_pp_clocks *pp_clks,
+		struct dm_pp_clock_levels *dc_clks,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->count > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->count,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		dc_clks->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		dc_clks->num_levels = pp_clks->count;
+
+	DRM_INFO("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < dc_clks->num_levels; i++) {
+		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->clock[i]);
+		/* translate 10kHz to kHz */
+		dc_clks->clocks_in_khz[i] = pp_clks->clock[i] * 10;
+	}
+}
+
+static void pp_to_dc_clock_levels_with_latency(
+		const struct pp_clock_levels_with_latency *pp_clks,
+		struct dm_pp_clock_levels_with_latency *clk_level_info,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->num_levels,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		clk_level_info->num_levels = pp_clks->num_levels;
+
+	DRM_DEBUG("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < clk_level_info->num_levels; i++) {
+		DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
+		/* translate 10kHz to kHz */
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
+		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
+	}
+}
+
+static void pp_to_dc_clock_levels_with_voltage(
+		const struct pp_clock_levels_with_voltage *pp_clks,
+		struct dm_pp_clock_levels_with_voltage *clk_level_info,
+		enum dm_pp_clock_type dc_clk_type)
+{
+	uint32_t i;
+
+	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
+		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
+				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
+				pp_clks->num_levels,
+				DM_PP_MAX_CLOCK_LEVELS);
+
+		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
+	} else
+		clk_level_info->num_levels = pp_clks->num_levels;
+
+	DRM_INFO("DM_PPLIB: values for %s clock\n",
+			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
+
+	for (i = 0; i < clk_level_info->num_levels; i++) {
+		DRM_INFO("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
+		/* translate 10kHz to kHz */
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
+		clk_level_info->data[i].voltage_in_mv = pp_clks->data[i].voltage_in_mv;
+	}
+}
+
+bool dm_pp_get_clock_levels_by_type(
+		const struct dc_context *ctx,
+		enum dm_pp_clock_type clk_type,
+		struct dm_pp_clock_levels *dc_clks)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct amd_pp_clocks pp_clks = { 0 };
+	struct amd_pp_simple_clock_info validation_clks = { 0 };
+	uint32_t i;
+
+	if (adev->powerplay.pp_funcs->get_clock_by_type) {
+		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
+			dc_to_pp_clock_type(clk_type), &pp_clks)) {
+		/* Error in pplib. Provide default values. */
+			get_default_clock_levels(clk_type, dc_clks);
+			return true;
+		}
+	}
+
+	pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type);
+
+	if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) {
+		if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks(
+						pp_handle, &validation_clks)) {
+			/* Error in pplib. Provide default values. */
+			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
+			validation_clks.engine_max_clock = 72000;
+			validation_clks.memory_max_clock = 80000;
+			validation_clks.level = 0;
+		}
+	}
+
+	DRM_INFO("DM_PPLIB: Validation clocks:\n");
+	DRM_INFO("DM_PPLIB:    engine_max_clock: %d\n",
+			validation_clks.engine_max_clock);
+	DRM_INFO("DM_PPLIB:    memory_max_clock: %d\n",
+			validation_clks.memory_max_clock);
+	DRM_INFO("DM_PPLIB:    level           : %d\n",
+			validation_clks.level);
+
+	/* Translate 10 kHz to kHz. */
+	validation_clks.engine_max_clock *= 10;
+	validation_clks.memory_max_clock *= 10;
+
+	/* Determine the highest non-boosted level from the Validation Clocks */
+	if (clk_type == DM_PP_CLOCK_TYPE_ENGINE_CLK) {
+		for (i = 0; i < dc_clks->num_levels; i++) {
+			if (dc_clks->clocks_in_khz[i] > validation_clks.engine_max_clock) {
+				/* This clock is higher the validation clock.
+				 * Than means the previous one is the highest
+				 * non-boosted one. */
+				DRM_INFO("DM_PPLIB: reducing engine clock level from %d to %d\n",
+						dc_clks->num_levels, i);
+				dc_clks->num_levels = i > 0 ? i : 1;
+				break;
+			}
+		}
+	} else if (clk_type == DM_PP_CLOCK_TYPE_MEMORY_CLK) {
+		for (i = 0; i < dc_clks->num_levels; i++) {
+			if (dc_clks->clocks_in_khz[i] > validation_clks.memory_max_clock) {
+				DRM_INFO("DM_PPLIB: reducing memory clock level from %d to %d\n",
+						dc_clks->num_levels, i);
+				dc_clks->num_levels = i > 0 ? i : 1;
+				break;
+			}
+		}
+	}
+
+	return true;
+}
+
+bool dm_pp_get_clock_levels_by_type_with_latency(
+	const struct dc_context *ctx,
+	enum dm_pp_clock_type clk_type,
+	struct dm_pp_clock_levels_with_latency *clk_level_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct pp_clock_levels_with_latency pp_clks = { 0 };
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->get_clock_by_type_with_latency)
+		return false;
+
+	if (pp_funcs->get_clock_by_type_with_latency(pp_handle,
+						     dc_to_pp_clock_type(clk_type),
+						     &pp_clks))
+		return false;
+
+	pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type);
+
+	return true;
+}
+
+bool dm_pp_get_clock_levels_by_type_with_voltage(
+	const struct dc_context *ctx,
+	enum dm_pp_clock_type clk_type,
+	struct dm_pp_clock_levels_with_voltage *clk_level_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	struct pp_clock_levels_with_voltage pp_clk_info = {0};
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (pp_funcs->get_clock_by_type_with_voltage(pp_handle,
+						     dc_to_pp_clock_type(clk_type),
+						     &pp_clk_info))
+		return false;
+
+	pp_to_dc_clock_levels_with_voltage(&pp_clk_info, clk_level_info, clk_type);
+
+	return true;
+}
+
+bool dm_pp_notify_wm_clock_changes(
+	const struct dc_context *ctx,
+	struct dm_pp_wm_sets_with_clock_ranges *wm_with_clock_ranges)
+{
+	/* TODO: to be implemented */
+	return false;
+}
+
+bool dm_pp_apply_power_level_change_request(
+	const struct dc_context *ctx,
+	struct dm_pp_power_level_change_request *level_change_req)
+{
+	/* TODO: to be implemented */
+	return false;
+}
+
+bool dm_pp_apply_clock_for_voltage_request(
+	const struct dc_context *ctx,
+	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct pp_display_clock_request pp_clock_request = {0};
+	int ret = 0;
+
+	pp_clock_request.clock_type = dc_to_pp_clock_type(clock_for_voltage_req->clk_type);
+	pp_clock_request.clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
+
+	if (!pp_clock_request.clock_type)
+		return false;
+
+	if (adev->powerplay.pp_funcs->display_clock_voltage_request)
+		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
+			adev->powerplay.pp_handle,
+			&pp_clock_request);
+	if (ret)
+		return false;
+	return true;
+}
+
+bool dm_pp_get_static_clocks(
+	const struct dc_context *ctx,
+	struct dm_pp_static_clock_info *static_clk_info)
+{
+	struct amdgpu_device *adev = ctx->driver_context;
+	struct amd_pp_clock_info pp_clk_info = {0};
+	int ret = 0;
+
+	if (adev->powerplay.pp_funcs->get_current_clocks)
+		ret = adev->powerplay.pp_funcs->get_current_clocks(
+			adev->powerplay.pp_handle,
+			&pp_clk_info);
+	if (ret)
+		return false;
+
+	static_clk_info->max_clocks_state = pp_clk_info.max_clocks_state;
+	/* translate 10kHz to kHz */
+	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock * 10;
+	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock * 10;
+
+	return true;
+}
+
+void pp_rv_set_display_requirement(struct pp_smu *pp,
+		struct pp_smu_display_requirement_rv *req)
+{
+	struct amdgpu_device *adev = pp->ctx->driver_context;
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+	int ret = 0;
+	if (hwmgr->hwmgr_func->set_deep_sleep_dcefclk)
+		ret = hwmgr->hwmgr_func->set_deep_sleep_dcefclk(hwmgr, req->hard_min_dcefclk_khz/10);
+	if (hwmgr->hwmgr_func->set_active_display_count)
+		ret = hwmgr->hwmgr_func->set_active_display_count(hwmgr, req->display_count);
+
+	//store_cc6 is not yet implemented in SMU level
+}
+
+void pp_rv_set_wm_ranges(struct pp_smu *pp,
+		struct pp_smu_wm_range_sets *ranges)
+{
+	struct amdgpu_device *adev = pp->ctx->driver_context;
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+	struct pp_wm_sets_with_clock_ranges_soc15 ranges_soc15 = {0};
+	int i = 0;
+
+	if (!hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges ||
+			!pp || !ranges)
+		return;
+
+	//not entirely sure if thats a correct assignment
+	ranges_soc15.num_wm_sets_dmif = ranges->num_reader_wm_sets;
+	ranges_soc15.num_wm_sets_mcif = ranges->num_writer_wm_sets;
+
+	for (i = 0; i < ranges_soc15.num_wm_sets_dmif; i++) {
+		if (ranges->reader_wm_sets[i].wm_inst > 3)
+			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
+		else
+			ranges_soc15.wm_sets_dmif[i].wm_set_id =
+					ranges->reader_wm_sets[i].wm_inst;
+		ranges_soc15.wm_sets_dmif[i].wm_max_dcefclk_in_khz =
+				ranges->reader_wm_sets[i].max_drain_clk_khz;
+		ranges_soc15.wm_sets_dmif[i].wm_min_dcefclk_in_khz =
+				ranges->reader_wm_sets[i].min_drain_clk_khz;
+		ranges_soc15.wm_sets_dmif[i].wm_max_memclk_in_khz =
+				ranges->reader_wm_sets[i].max_fill_clk_khz;
+		ranges_soc15.wm_sets_dmif[i].wm_min_memclk_in_khz =
+				ranges->reader_wm_sets[i].min_fill_clk_khz;
+	}
+
+	for (i = 0; i < ranges_soc15.num_wm_sets_mcif; i++) {
+		if (ranges->writer_wm_sets[i].wm_inst > 3)
+			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
+		else
+			ranges_soc15.wm_sets_mcif[i].wm_set_id =
+					ranges->writer_wm_sets[i].wm_inst;
+		ranges_soc15.wm_sets_mcif[i].wm_max_socclk_in_khz =
+				ranges->writer_wm_sets[i].max_fill_clk_khz;
+		ranges_soc15.wm_sets_mcif[i].wm_min_socclk_in_khz =
+				ranges->writer_wm_sets[i].min_fill_clk_khz;
+		ranges_soc15.wm_sets_mcif[i].wm_max_memclk_in_khz =
+				ranges->writer_wm_sets[i].max_fill_clk_khz;
+		ranges_soc15.wm_sets_mcif[i].wm_min_memclk_in_khz =
+				ranges->writer_wm_sets[i].min_fill_clk_khz;
+	}
+
+	hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges(hwmgr, &ranges_soc15);
+
+}
+
+void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
+{
+	struct amdgpu_device *adev = pp->ctx->driver_context;
+	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+
+	if (hwmgr->hwmgr_func->smus_notify_pwe)
+		hwmgr->hwmgr_func->smus_notify_pwe(hwmgr);
+}
+
+void dm_pp_get_funcs_rv(
+		struct dc_context *ctx,
+		struct pp_smu_funcs_rv *funcs)
+{
+	funcs->pp_smu.ctx = ctx;
+	funcs->set_display_requirement = pp_rv_set_display_requirement;
+	funcs->set_wm_ranges = pp_rv_set_wm_ranges;
+	funcs->set_pme_wa_enable = pp_rv_set_pme_wa_enable;
+}
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
index a19df20b557b..9f0a217603ad 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_services.c
@@ -34,9 +34,6 @@
 #include "amdgpu_dm.h"
 #include "amdgpu_dm_irq.h"
 #include "amdgpu_pm.h"
-#include "dm_pp_smu.h"
-#include "../../powerplay/inc/hwmgr.h"
-#include "../../powerplay/hwmgr/smu10_hwmgr.h"
 
 
 
@@ -77,493 +74,4 @@ bool dm_read_persistent_data(struct dc_context *ctx,
 
 /**** power component interfaces ****/
 
-bool dm_pp_apply_display_requirements(
-		const struct dc_context *ctx,
-		const struct dm_pp_display_configuration *pp_display_cfg)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-
-	if (adev->pm.dpm_enabled) {
-
-		memset(&adev->pm.pm_display_cfg, 0,
-				sizeof(adev->pm.pm_display_cfg));
-
-		adev->pm.pm_display_cfg.cpu_cc6_disable =
-			pp_display_cfg->cpu_cc6_disable;
-
-		adev->pm.pm_display_cfg.cpu_pstate_disable =
-			pp_display_cfg->cpu_pstate_disable;
-
-		adev->pm.pm_display_cfg.cpu_pstate_separation_time =
-			pp_display_cfg->cpu_pstate_separation_time;
-
-		adev->pm.pm_display_cfg.nb_pstate_switch_disable =
-			pp_display_cfg->nb_pstate_switch_disable;
-
-		adev->pm.pm_display_cfg.num_display =
-				pp_display_cfg->display_count;
-		adev->pm.pm_display_cfg.num_path_including_non_display =
-				pp_display_cfg->display_count;
-
-		adev->pm.pm_display_cfg.min_core_set_clock =
-				pp_display_cfg->min_engine_clock_khz/10;
-		adev->pm.pm_display_cfg.min_core_set_clock_in_sr =
-				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
-		adev->pm.pm_display_cfg.min_mem_set_clock =
-				pp_display_cfg->min_memory_clock_khz/10;
-
-		adev->pm.pm_display_cfg.multi_monitor_in_sync =
-				pp_display_cfg->all_displays_in_sync;
-		adev->pm.pm_display_cfg.min_vblank_time =
-				pp_display_cfg->avail_mclk_switch_time_us;
-
-		adev->pm.pm_display_cfg.display_clk =
-				pp_display_cfg->disp_clk_khz/10;
-
-		adev->pm.pm_display_cfg.dce_tolerable_mclk_in_active_latency =
-				pp_display_cfg->avail_mclk_switch_time_in_disp_active_us;
-
-		adev->pm.pm_display_cfg.crtc_index = pp_display_cfg->crtc_index;
-		adev->pm.pm_display_cfg.line_time_in_us =
-				pp_display_cfg->line_time_in_us;
-
-		adev->pm.pm_display_cfg.vrefresh = pp_display_cfg->disp_configs[0].v_refresh;
-		adev->pm.pm_display_cfg.crossfire_display_index = -1;
-		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
-
-		/* TODO: complete implementation of
-		 * pp_display_configuration_change().
-		 * Follow example of:
-		 * PHM_StoreDALConfigurationData - powerplay\hwmgr\hardwaremanager.c
-		 * PP_IRI_DisplayConfigurationChange - powerplay\eventmgr\iri.c */
-		if (adev->powerplay.pp_funcs->display_configuration_change)
-			adev->powerplay.pp_funcs->display_configuration_change(
-				adev->powerplay.pp_handle,
-				&adev->pm.pm_display_cfg);
-
-		/* TODO: replace by a separate call to 'apply display cfg'? */
-		amdgpu_pm_compute_clocks(adev);
-	}
-
-	return true;
-}
-
-static void get_default_clock_levels(
-		enum dm_pp_clock_type clk_type,
-		struct dm_pp_clock_levels *clks)
-{
-	uint32_t disp_clks_in_khz[6] = {
-			300000, 400000, 496560, 626090, 685720, 757900 };
-	uint32_t sclks_in_khz[6] = {
-			300000, 360000, 423530, 514290, 626090, 720000 };
-	uint32_t mclks_in_khz[2] = { 333000, 800000 };
-
-	switch (clk_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		clks->num_levels = 6;
-		memmove(clks->clocks_in_khz, disp_clks_in_khz,
-				sizeof(disp_clks_in_khz));
-		break;
-	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
-		clks->num_levels = 6;
-		memmove(clks->clocks_in_khz, sclks_in_khz,
-				sizeof(sclks_in_khz));
-		break;
-	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
-		clks->num_levels = 2;
-		memmove(clks->clocks_in_khz, mclks_in_khz,
-				sizeof(mclks_in_khz));
-		break;
-	default:
-		clks->num_levels = 0;
-		break;
-	}
-}
-
-static enum amd_pp_clock_type dc_to_pp_clock_type(
-		enum dm_pp_clock_type dm_pp_clk_type)
-{
-	enum amd_pp_clock_type amd_pp_clk_type = 0;
-
-	switch (dm_pp_clk_type) {
-	case DM_PP_CLOCK_TYPE_DISPLAY_CLK:
-		amd_pp_clk_type = amd_pp_disp_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_ENGINE_CLK:
-		amd_pp_clk_type = amd_pp_sys_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_MEMORY_CLK:
-		amd_pp_clk_type = amd_pp_mem_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_DCEFCLK:
-		amd_pp_clk_type  = amd_pp_dcef_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_DCFCLK:
-		amd_pp_clk_type = amd_pp_dcf_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_PIXELCLK:
-		amd_pp_clk_type = amd_pp_pixel_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_FCLK:
-		amd_pp_clk_type = amd_pp_f_clock;
-		break;
-	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
-		amd_pp_clk_type = amd_pp_dpp_clock;
-		break;
-	default:
-		DRM_ERROR("DM_PPLIB: invalid clock type: %d!\n",
-				dm_pp_clk_type);
-		break;
-	}
-
-	return amd_pp_clk_type;
-}
-
-static void pp_to_dc_clock_levels(
-		const struct amd_pp_clocks *pp_clks,
-		struct dm_pp_clock_levels *dc_clks,
-		enum dm_pp_clock_type dc_clk_type)
-{
-	uint32_t i;
-
-	if (pp_clks->count > DM_PP_MAX_CLOCK_LEVELS) {
-		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
-				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
-				pp_clks->count,
-				DM_PP_MAX_CLOCK_LEVELS);
-
-		dc_clks->num_levels = DM_PP_MAX_CLOCK_LEVELS;
-	} else
-		dc_clks->num_levels = pp_clks->count;
-
-	DRM_INFO("DM_PPLIB: values for %s clock\n",
-			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
-
-	for (i = 0; i < dc_clks->num_levels; i++) {
-		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->clock[i]);
-		/* translate 10kHz to kHz */
-		dc_clks->clocks_in_khz[i] = pp_clks->clock[i] * 10;
-	}
-}
-
-static void pp_to_dc_clock_levels_with_latency(
-		const struct pp_clock_levels_with_latency *pp_clks,
-		struct dm_pp_clock_levels_with_latency *clk_level_info,
-		enum dm_pp_clock_type dc_clk_type)
-{
-	uint32_t i;
-
-	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
-		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
-				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
-				pp_clks->num_levels,
-				DM_PP_MAX_CLOCK_LEVELS);
-
-		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
-	} else
-		clk_level_info->num_levels = pp_clks->num_levels;
-
-	DRM_DEBUG("DM_PPLIB: values for %s clock\n",
-			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
-
-	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
-		/* translate 10kHz to kHz */
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
-		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
-	}
-}
-
-static void pp_to_dc_clock_levels_with_voltage(
-		const struct pp_clock_levels_with_voltage *pp_clks,
-		struct dm_pp_clock_levels_with_voltage *clk_level_info,
-		enum dm_pp_clock_type dc_clk_type)
-{
-	uint32_t i;
-
-	if (pp_clks->num_levels > DM_PP_MAX_CLOCK_LEVELS) {
-		DRM_INFO("DM_PPLIB: Warning: %s clock: number of levels %d exceeds maximum of %d!\n",
-				DC_DECODE_PP_CLOCK_TYPE(dc_clk_type),
-				pp_clks->num_levels,
-				DM_PP_MAX_CLOCK_LEVELS);
-
-		clk_level_info->num_levels = DM_PP_MAX_CLOCK_LEVELS;
-	} else
-		clk_level_info->num_levels = pp_clks->num_levels;
-
-	DRM_INFO("DM_PPLIB: values for %s clock\n",
-			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
-
-	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_INFO("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
-		/* translate 10kHz to kHz */
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
-		clk_level_info->data[i].voltage_in_mv = pp_clks->data[i].voltage_in_mv;
-	}
-}
-
-
-bool dm_pp_get_clock_levels_by_type(
-		const struct dc_context *ctx,
-		enum dm_pp_clock_type clk_type,
-		struct dm_pp_clock_levels *dc_clks)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	void *pp_handle = adev->powerplay.pp_handle;
-	struct amd_pp_clocks pp_clks = { 0 };
-	struct amd_pp_simple_clock_info validation_clks = { 0 };
-	uint32_t i;
-
-	if (adev->powerplay.pp_funcs->get_clock_by_type) {
-		if (adev->powerplay.pp_funcs->get_clock_by_type(pp_handle,
-			dc_to_pp_clock_type(clk_type), &pp_clks)) {
-		/* Error in pplib. Provide default values. */
-			get_default_clock_levels(clk_type, dc_clks);
-			return true;
-		}
-	}
-
-	pp_to_dc_clock_levels(&pp_clks, dc_clks, clk_type);
-
-	if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks) {
-		if (adev->powerplay.pp_funcs->get_display_mode_validation_clocks(
-						pp_handle, &validation_clks)) {
-			/* Error in pplib. Provide default values. */
-			DRM_INFO("DM_PPLIB: Warning: using default validation clocks!\n");
-			validation_clks.engine_max_clock = 72000;
-			validation_clks.memory_max_clock = 80000;
-			validation_clks.level = 0;
-		}
-	}
-
-	DRM_INFO("DM_PPLIB: Validation clocks:\n");
-	DRM_INFO("DM_PPLIB:    engine_max_clock: %d\n",
-			validation_clks.engine_max_clock);
-	DRM_INFO("DM_PPLIB:    memory_max_clock: %d\n",
-			validation_clks.memory_max_clock);
-	DRM_INFO("DM_PPLIB:    level           : %d\n",
-			validation_clks.level);
-
-	/* Translate 10 kHz to kHz. */
-	validation_clks.engine_max_clock *= 10;
-	validation_clks.memory_max_clock *= 10;
-
-	/* Determine the highest non-boosted level from the Validation Clocks */
-	if (clk_type == DM_PP_CLOCK_TYPE_ENGINE_CLK) {
-		for (i = 0; i < dc_clks->num_levels; i++) {
-			if (dc_clks->clocks_in_khz[i] > validation_clks.engine_max_clock) {
-				/* This clock is higher the validation clock.
-				 * Than means the previous one is the highest
-				 * non-boosted one. */
-				DRM_INFO("DM_PPLIB: reducing engine clock level from %d to %d\n",
-						dc_clks->num_levels, i);
-				dc_clks->num_levels = i > 0 ? i : 1;
-				break;
-			}
-		}
-	} else if (clk_type == DM_PP_CLOCK_TYPE_MEMORY_CLK) {
-		for (i = 0; i < dc_clks->num_levels; i++) {
-			if (dc_clks->clocks_in_khz[i] > validation_clks.memory_max_clock) {
-				DRM_INFO("DM_PPLIB: reducing memory clock level from %d to %d\n",
-						dc_clks->num_levels, i);
-				dc_clks->num_levels = i > 0 ? i : 1;
-				break;
-			}
-		}
-	}
-
-	return true;
-}
-
-bool dm_pp_get_clock_levels_by_type_with_latency(
-	const struct dc_context *ctx,
-	enum dm_pp_clock_type clk_type,
-	struct dm_pp_clock_levels_with_latency *clk_level_info)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	void *pp_handle = adev->powerplay.pp_handle;
-	struct pp_clock_levels_with_latency pp_clks = { 0 };
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (!pp_funcs || !pp_funcs->get_clock_by_type_with_latency)
-		return false;
-
-	if (pp_funcs->get_clock_by_type_with_latency(pp_handle,
-						     dc_to_pp_clock_type(clk_type),
-						     &pp_clks))
-		return false;
-
-	pp_to_dc_clock_levels_with_latency(&pp_clks, clk_level_info, clk_type);
-
-	return true;
-}
-
-bool dm_pp_get_clock_levels_by_type_with_voltage(
-	const struct dc_context *ctx,
-	enum dm_pp_clock_type clk_type,
-	struct dm_pp_clock_levels_with_voltage *clk_level_info)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	void *pp_handle = adev->powerplay.pp_handle;
-	struct pp_clock_levels_with_voltage pp_clk_info = {0};
-	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
-
-	if (pp_funcs->get_clock_by_type_with_voltage(pp_handle,
-						     dc_to_pp_clock_type(clk_type),
-						     &pp_clk_info))
-		return false;
-
-	pp_to_dc_clock_levels_with_voltage(&pp_clk_info, clk_level_info, clk_type);
-
-	return true;
-}
-
-bool dm_pp_notify_wm_clock_changes(
-	const struct dc_context *ctx,
-	struct dm_pp_wm_sets_with_clock_ranges *wm_with_clock_ranges)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_apply_power_level_change_request(
-	const struct dc_context *ctx,
-	struct dm_pp_power_level_change_request *level_change_req)
-{
-	/* TODO: to be implemented */
-	return false;
-}
-
-bool dm_pp_apply_clock_for_voltage_request(
-	const struct dc_context *ctx,
-	struct dm_pp_clock_for_voltage_req *clock_for_voltage_req)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	struct pp_display_clock_request pp_clock_request = {0};
-	int ret = 0;
-
-	pp_clock_request.clock_type = dc_to_pp_clock_type(clock_for_voltage_req->clk_type);
-	pp_clock_request.clock_freq_in_khz = clock_for_voltage_req->clocks_in_khz;
-
-	if (!pp_clock_request.clock_type)
-		return false;
-
-	if (adev->powerplay.pp_funcs->display_clock_voltage_request)
-		ret = adev->powerplay.pp_funcs->display_clock_voltage_request(
-			adev->powerplay.pp_handle,
-			&pp_clock_request);
-	if (ret)
-		return false;
-	return true;
-}
-
-bool dm_pp_get_static_clocks(
-	const struct dc_context *ctx,
-	struct dm_pp_static_clock_info *static_clk_info)
-{
-	struct amdgpu_device *adev = ctx->driver_context;
-	struct amd_pp_clock_info pp_clk_info = {0};
-	int ret = 0;
-
-	if (adev->powerplay.pp_funcs->get_current_clocks)
-		ret = adev->powerplay.pp_funcs->get_current_clocks(
-			adev->powerplay.pp_handle,
-			&pp_clk_info);
-	if (ret)
-		return false;
-
-	static_clk_info->max_clocks_state = pp_clk_info.max_clocks_state;
-	/* translate 10kHz to kHz */
-	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock * 10;
-	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock * 10;
-
-	return true;
-}
-
-void pp_rv_set_display_requirement(struct pp_smu *pp,
-		struct pp_smu_display_requirement_rv *req)
-{
-	struct amdgpu_device *adev = pp->ctx->driver_context;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret = 0;
-	if (hwmgr->hwmgr_func->set_deep_sleep_dcefclk)
-		ret = hwmgr->hwmgr_func->set_deep_sleep_dcefclk(hwmgr, req->hard_min_dcefclk_khz/10);
-	if (hwmgr->hwmgr_func->set_active_display_count)
-		ret = hwmgr->hwmgr_func->set_active_display_count(hwmgr, req->display_count);
-
-	//store_cc6 is not yet implemented in SMU level
-}
-
-void pp_rv_set_wm_ranges(struct pp_smu *pp,
-		struct pp_smu_wm_range_sets *ranges)
-{
-	struct amdgpu_device *adev = pp->ctx->driver_context;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	struct pp_wm_sets_with_clock_ranges_soc15 ranges_soc15 = {0};
-	int i = 0;
-
-	if (!hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges ||
-			!pp || !ranges)
-		return;
-
-	//not entirely sure if thats a correct assignment
-	ranges_soc15.num_wm_sets_dmif = ranges->num_reader_wm_sets;
-	ranges_soc15.num_wm_sets_mcif = ranges->num_writer_wm_sets;
-
-	for (i = 0; i < ranges_soc15.num_wm_sets_dmif; i++) {
-		if (ranges->reader_wm_sets[i].wm_inst > 3)
-			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
-		else
-			ranges_soc15.wm_sets_dmif[i].wm_set_id =
-					ranges->reader_wm_sets[i].wm_inst;
-		ranges_soc15.wm_sets_dmif[i].wm_max_dcefclk_in_khz =
-				ranges->reader_wm_sets[i].max_drain_clk_khz;
-		ranges_soc15.wm_sets_dmif[i].wm_min_dcefclk_in_khz =
-				ranges->reader_wm_sets[i].min_drain_clk_khz;
-		ranges_soc15.wm_sets_dmif[i].wm_max_memclk_in_khz =
-				ranges->reader_wm_sets[i].max_fill_clk_khz;
-		ranges_soc15.wm_sets_dmif[i].wm_min_memclk_in_khz =
-				ranges->reader_wm_sets[i].min_fill_clk_khz;
-	}
-
-	for (i = 0; i < ranges_soc15.num_wm_sets_mcif; i++) {
-		if (ranges->writer_wm_sets[i].wm_inst > 3)
-			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
-		else
-			ranges_soc15.wm_sets_mcif[i].wm_set_id =
-					ranges->writer_wm_sets[i].wm_inst;
-		ranges_soc15.wm_sets_mcif[i].wm_max_socclk_in_khz =
-				ranges->writer_wm_sets[i].max_fill_clk_khz;
-		ranges_soc15.wm_sets_mcif[i].wm_min_socclk_in_khz =
-				ranges->writer_wm_sets[i].min_fill_clk_khz;
-		ranges_soc15.wm_sets_mcif[i].wm_max_memclk_in_khz =
-				ranges->writer_wm_sets[i].max_fill_clk_khz;
-		ranges_soc15.wm_sets_mcif[i].wm_min_memclk_in_khz =
-				ranges->writer_wm_sets[i].min_fill_clk_khz;
-	}
-
-	hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges(hwmgr, &ranges_soc15);
-
-}
-
-void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
-{
-	struct amdgpu_device *adev = pp->ctx->driver_context;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-
-	if (hwmgr->hwmgr_func->smus_notify_pwe)
-		hwmgr->hwmgr_func->smus_notify_pwe(hwmgr);
-}
-
-void dm_pp_get_funcs_rv(
-		struct dc_context *ctx,
-		struct pp_smu_funcs_rv *funcs)
-{
-	funcs->pp_smu.ctx = ctx;
-	funcs->set_display_requirement = pp_rv_set_display_requirement;
-	funcs->set_wm_ranges = pp_rv_set_wm_ranges;
-	funcs->set_pme_wa_enable = pp_rv_set_pme_wa_enable;
-}
-
 
-/**** end of power component interfaces ****/
-- 
cgit v1.2.3


From 33a6a7eb8014cb7089570534ef4d502efe4372ed Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 6 Jun 2018 13:19:39 -0400
Subject: drm/amd/display: fix dcn1 watermark range reporting

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c | 102 ++++-------------------
 1 file changed, 18 insertions(+), 84 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index ac4451adeec9..8dc0773b285e 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -1335,21 +1335,14 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 {
 	struct pp_smu_funcs_rv *pp = dc->res_pool->pp_smu;
 	struct pp_smu_wm_range_sets ranges = {0};
-	int max_fclk_khz, nom_fclk_khz, mid_fclk_khz, min_fclk_khz;
-	int max_dcfclk_khz, min_dcfclk_khz;
-	int socclk_khz;
+	int min_fclk_khz, min_dcfclk_khz, socclk_khz;
 	const int overdrive = 5000000; /* 5 GHz to cover Overdrive */
-	unsigned factor = (ddr4_dram_factor_single_Channel * dc->dcn_soc->number_of_channels);
 
 	if (!pp->set_wm_ranges)
 		return;
 
 	kernel_fpu_begin();
-	max_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmax0p9 * 1000000 / factor;
-	nom_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vnom0p8 * 1000000 / factor;
-	mid_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmid0p72 * 1000000 / factor;
 	min_fclk_khz = dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 * 1000000 / 32;
-	max_dcfclk_khz = dc->dcn_soc->dcfclkv_max0p9 * 1000;
 	min_dcfclk_khz = dc->dcn_soc->dcfclkv_min0p65 * 1000;
 	socclk_khz = dc->dcn_soc->socclk * 1000;
 	kernel_fpu_end();
@@ -1357,7 +1350,7 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 	/* Now notify PPLib/SMU about which Watermarks sets they should select
 	 * depending on DPM state they are in. And update BW MGR GFX Engine and
 	 * Memory clock member variables for Watermarks calculations for each
-	 * Watermark Set
+	 * Watermark Set. Only one watermark set for dcn1 due to hw bug DEGVIDCN10-254.
 	 */
 	/* SOCCLK does not affect anytihng but writeback for DCN so for now we dont
 	 * care what the value is, hence min to overdrive level
@@ -1366,96 +1359,37 @@ void dcn_bw_notify_pplib_of_wm_ranges(struct dc *dc)
 	ranges.num_writer_wm_sets = WM_SET_COUNT;
 	ranges.reader_wm_sets[0].wm_inst = WM_A;
 	ranges.reader_wm_sets[0].min_drain_clk_khz = min_dcfclk_khz;
-	ranges.reader_wm_sets[0].max_drain_clk_khz = max_dcfclk_khz;
+	ranges.reader_wm_sets[0].max_drain_clk_khz = overdrive;
 	ranges.reader_wm_sets[0].min_fill_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[0].max_fill_clk_khz = min_fclk_khz;
+	ranges.reader_wm_sets[0].max_fill_clk_khz = overdrive;
 	ranges.writer_wm_sets[0].wm_inst = WM_A;
 	ranges.writer_wm_sets[0].min_fill_clk_khz = socclk_khz;
 	ranges.writer_wm_sets[0].max_fill_clk_khz = overdrive;
 	ranges.writer_wm_sets[0].min_drain_clk_khz = min_fclk_khz;
-	ranges.writer_wm_sets[0].max_drain_clk_khz = min_fclk_khz;
-
-	ranges.reader_wm_sets[1].wm_inst = WM_B;
-	ranges.reader_wm_sets[1].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[1].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[1].min_fill_clk_khz = mid_fclk_khz;
-	ranges.reader_wm_sets[1].max_fill_clk_khz = mid_fclk_khz;
-	ranges.writer_wm_sets[1].wm_inst = WM_B;
-	ranges.writer_wm_sets[1].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[1].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[1].min_drain_clk_khz = mid_fclk_khz;
-	ranges.writer_wm_sets[1].max_drain_clk_khz = mid_fclk_khz;
-
-
-	ranges.reader_wm_sets[2].wm_inst = WM_C;
-	ranges.reader_wm_sets[2].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[2].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[2].min_fill_clk_khz = nom_fclk_khz;
-	ranges.reader_wm_sets[2].max_fill_clk_khz = nom_fclk_khz;
-	ranges.writer_wm_sets[2].wm_inst = WM_C;
-	ranges.writer_wm_sets[2].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[2].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[2].min_drain_clk_khz = nom_fclk_khz;
-	ranges.writer_wm_sets[2].max_drain_clk_khz = nom_fclk_khz;
-
-	ranges.reader_wm_sets[3].wm_inst = WM_D;
-	ranges.reader_wm_sets[3].min_drain_clk_khz = min_fclk_khz;
-	ranges.reader_wm_sets[3].max_drain_clk_khz = max_dcfclk_khz;
-	ranges.reader_wm_sets[3].min_fill_clk_khz = max_fclk_khz;
-	ranges.reader_wm_sets[3].max_fill_clk_khz = max_fclk_khz;
-	ranges.writer_wm_sets[3].wm_inst = WM_D;
-	ranges.writer_wm_sets[3].min_fill_clk_khz = socclk_khz;
-	ranges.writer_wm_sets[3].max_fill_clk_khz = overdrive;
-	ranges.writer_wm_sets[3].min_drain_clk_khz = max_fclk_khz;
-	ranges.writer_wm_sets[3].max_drain_clk_khz = max_fclk_khz;
+	ranges.writer_wm_sets[0].max_drain_clk_khz = overdrive;
 
 	if (dc->debug.pplib_wm_report_mode == WM_REPORT_OVERRIDE) {
 		ranges.reader_wm_sets[0].wm_inst = WM_A;
 		ranges.reader_wm_sets[0].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[0].max_drain_clk_khz = 654000;
+		ranges.reader_wm_sets[0].max_drain_clk_khz = 5000000;
 		ranges.reader_wm_sets[0].min_fill_clk_khz = 800000;
-		ranges.reader_wm_sets[0].max_fill_clk_khz = 800000;
+		ranges.reader_wm_sets[0].max_fill_clk_khz = 5000000;
 		ranges.writer_wm_sets[0].wm_inst = WM_A;
 		ranges.writer_wm_sets[0].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[0].max_fill_clk_khz = 757000;
+		ranges.writer_wm_sets[0].max_fill_clk_khz = 5000000;
 		ranges.writer_wm_sets[0].min_drain_clk_khz = 800000;
-		ranges.writer_wm_sets[0].max_drain_clk_khz = 800000;
-
-		ranges.reader_wm_sets[1].wm_inst = WM_B;
-		ranges.reader_wm_sets[1].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[1].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[1].min_fill_clk_khz = 933000;
-		ranges.reader_wm_sets[1].max_fill_clk_khz = 933000;
-		ranges.writer_wm_sets[1].wm_inst = WM_B;
-		ranges.writer_wm_sets[1].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[1].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[1].min_drain_clk_khz = 933000;
-		ranges.writer_wm_sets[1].max_drain_clk_khz = 933000;
-
-
-		ranges.reader_wm_sets[2].wm_inst = WM_C;
-		ranges.reader_wm_sets[2].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[2].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[2].min_fill_clk_khz = 1067000;
-		ranges.reader_wm_sets[2].max_fill_clk_khz = 1067000;
-		ranges.writer_wm_sets[2].wm_inst = WM_C;
-		ranges.writer_wm_sets[2].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[2].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[2].min_drain_clk_khz = 1067000;
-		ranges.writer_wm_sets[2].max_drain_clk_khz = 1067000;
-
-		ranges.reader_wm_sets[3].wm_inst = WM_D;
-		ranges.reader_wm_sets[3].min_drain_clk_khz = 300000;
-		ranges.reader_wm_sets[3].max_drain_clk_khz = 654000;
-		ranges.reader_wm_sets[3].min_fill_clk_khz = 1200000;
-		ranges.reader_wm_sets[3].max_fill_clk_khz = 1200000;
-		ranges.writer_wm_sets[3].wm_inst = WM_D;
-		ranges.writer_wm_sets[3].min_fill_clk_khz = 200000;
-		ranges.writer_wm_sets[3].max_fill_clk_khz = 757000;
-		ranges.writer_wm_sets[3].min_drain_clk_khz = 1200000;
-		ranges.writer_wm_sets[3].max_drain_clk_khz = 1200000;
+		ranges.writer_wm_sets[0].max_drain_clk_khz = 5000000;
 	}
 
+	ranges.reader_wm_sets[1] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[1].wm_inst = WM_B;
+
+	ranges.reader_wm_sets[2] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[2].wm_inst = WM_C;
+
+	ranges.reader_wm_sets[3] = ranges.writer_wm_sets[0];
+	ranges.reader_wm_sets[3].wm_inst = WM_D;
+
 	/* Notify PP Lib/SMU which Watermarks to use for which clock ranges */
 	pp->set_wm_ranges(&pp->pp_smu, &ranges);
 }
-- 
cgit v1.2.3


From 69d6bb171fe15f564adfbc485e77dd8c5ca953d5 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Tue, 5 Jun 2018 07:19:08 -0400
Subject: drm/amd/display: remove dcn1 watermark sets b, c and d

Currently dcn1 will not switch between watermark sets so we can
save time by not calculating 3 extra sets.

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 8dc0773b285e..12261fbc25e0 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -505,6 +505,7 @@ static void split_stream_across_pipes(
 	resource_build_scaling_params(secondary_pipe);
 }
 
+#if 0
 static void calc_wm_sets_and_perf_params(
 		struct dc_state *context,
 		struct dcn_bw_internal_vars *v)
@@ -586,6 +587,7 @@ static void calc_wm_sets_and_perf_params(
 	if (v->voltage_level >= 3)
 		context->bw.dcn.watermarks.d = context->bw.dcn.watermarks.a;
 }
+#endif
 
 static bool dcn_bw_apply_registry_override(struct dc *dc)
 {
@@ -980,7 +982,24 @@ bool dcn_validate_bandwidth(
 				bw_consumed = v->fabric_and_dram_bandwidth;
 
 		display_pipe_configuration(v);
-		calc_wm_sets_and_perf_params(context, v);
+		/*calc_wm_sets_and_perf_params(context, v);*/
+		/* Only 1 set is used by dcn since no noticeable
+		 * performance improvement was measured and due to hw bug DEGVIDCN10-254
+		 */
+		dispclkdppclkdcfclk_deep_sleep_prefetch_parameters_watermarks_and_performance_calculation(v);
+
+		context->bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns =
+			v->stutter_exit_watermark * 1000;
+		context->bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns =
+				v->stutter_enter_plus_exit_watermark * 1000;
+		context->bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns =
+				v->dram_clock_change_watermark * 1000;
+		context->bw.dcn.watermarks.a.pte_meta_urgent_ns = v->ptemeta_urgent_watermark * 1000;
+		context->bw.dcn.watermarks.a.urgent_ns = v->urgent_watermark * 1000;
+		context->bw.dcn.watermarks.b = context->bw.dcn.watermarks.a;
+		context->bw.dcn.watermarks.c = context->bw.dcn.watermarks.a;
+		context->bw.dcn.watermarks.d = context->bw.dcn.watermarks.a;
+
 		context->bw.dcn.clk.fclk_khz = (int)(bw_consumed * 1000000 /
 				(ddr4_dram_factor_single_Channel * v->number_of_channels));
 		if (bw_consumed == v->fabric_and_dram_bandwidth_vmin0p65) {
-- 
cgit v1.2.3


From 7144d3cfff7d8b0d98d9d25ee42c674491e31bc9 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Tue, 5 Jun 2018 13:14:13 -0400
Subject: drm/amd/display: separate out wm change request dcn workaround

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c       | 11 ++++++-----
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h       |  2 ++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c |  3 +++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c     |  1 +
 drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h         |  1 +
 5 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index 63b75ac4a1d5..623db09389b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -190,6 +190,12 @@ static uint32_t convert_and_clamp(
 }
 
 
+void hubbub1_wm_change_req_wa(struct hubbub *hubbub)
+{
+	REG_UPDATE_SEQ(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
+			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0, 1);
+}
+
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
@@ -203,8 +209,6 @@ void hubbub1_program_watermarks(
 	 */
 	uint32_t prog_wm_value;
 
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 0);
 
 	/* Repeat for water mark set A, B, C and D. */
 	/* clock state A */
@@ -459,9 +463,6 @@ void hubbub1_program_watermarks(
 			watermarks->d.cstate_pstate.pstate_change_ns, prog_wm_value);
 	}
 
-	REG_UPDATE(DCHUBBUB_ARB_WATERMARK_CHANGE_CNTL,
-			DCHUBBUB_ARB_WATERMARK_CHANGE_REQUEST, 1);
-
 	REG_UPDATE(DCHUBBUB_ARB_SAT_LEVEL,
 			DCHUBBUB_ARB_SAT_LEVEL, 60 * refclk_mhz);
 	REG_UPDATE(DCHUBBUB_ARB_DF_REQ_OUTSTAND,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
index 0ca39cb71968..d6e596eef4c5 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.h
@@ -195,6 +195,8 @@ void hubbub1_update_dchub(
 bool hubbub1_verify_allow_pstate_change_high(
 	struct hubbub *hubbub);
 
+void hubbub1_wm_change_req_wa(struct hubbub *hubbub);
+
 void hubbub1_program_watermarks(
 		struct hubbub *hubbub,
 		struct dcn_watermark_set *watermarks,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index cc12c4757f8b..378bb19b98de 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2305,6 +2305,9 @@ static void dcn10_apply_ctx_for_surface(
 		hubbub1_program_watermarks(dc->res_pool->hubbub,
 				&context->bw.dcn.watermarks, ref_clk_mhz, true);
 
+		if (dc->hwseq->wa.DEGVIDCN10_254)
+			hubbub1_wm_change_req_wa(dc->res_pool->hubbub);
+
 		if (dc->debug.sanity_checks) {
 			/* pstate stuck check after watermark update */
 			dcn10_verify_allow_pstate_change_high(dc);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 2db08b99db56..68be66eabc40 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -743,6 +743,7 @@ static struct dce_hwseq *dcn10_hwseq_create(
 		hws->masks = &hwseq_mask;
 		hws->wa.DEGVIDCN10_253 = true;
 		hws->wa.false_optc_underflow = true;
+		hws->wa.DEGVIDCN10_254 = true;
 	}
 	return hws;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index a71770ed4b9f..1c94dae6bbde 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -44,6 +44,7 @@ struct dce_hwseq_wa {
 	bool blnd_crtc_trigger;
 	bool DEGVIDCN10_253;
 	bool false_optc_underflow;
+	bool DEGVIDCN10_254;
 };
 
 struct hwseq_wa_state {
-- 
cgit v1.2.3


From e21db6dbdf4327f620c5a203f7801b59dad9942e Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 24 May 2018 14:39:01 -0400
Subject: drm/amd/display: move dcn watermark programming to set_bandwidth

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 107 ++++-----------------
 drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h  |   2 +-
 2 files changed, 19 insertions(+), 90 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 378bb19b98de..21b45e8d49f7 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2219,8 +2219,6 @@ static void dcn10_apply_ctx_for_surface(
 	int i;
 	struct timing_generator *tg;
 	bool removed_pipe[4] = { false };
-	unsigned int ref_clk_mhz = dc->res_pool->ref_clock_inKhz/1000;
-	bool program_water_mark = false;
 	struct pipe_ctx *top_pipe_to_program =
 			find_top_pipe_for_stream(dc, context, stream);
 	DC_LOGGER_INIT(dc->ctx->logger);
@@ -2281,107 +2279,38 @@ static void dcn10_apply_ctx_for_surface(
 	if (num_planes == 0)
 		false_optc_underflow_wa(dc, stream, tg);
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
-		struct pipe_ctx *old_pipe_ctx =
-				&dc->current_state->res_ctx.pipe_ctx[i];
-		struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
-
-		if (pipe_ctx->stream == stream &&
-				pipe_ctx->plane_state &&
-			pipe_ctx->plane_state->update_flags.bits.full_update)
-			program_water_mark = true;
-
+	for (i = 0; i < dc->res_pool->pipe_count; i++)
 		if (removed_pipe[i])
-			dcn10_disable_plane(dc, old_pipe_ctx);
-	}
-
-	if (program_water_mark) {
-		if (dc->debug.sanity_checks) {
-			/* pstate stuck check after watermark update */
-			dcn10_verify_allow_pstate_change_high(dc);
-		}
-
-		/* watermark is for all pipes */
-		hubbub1_program_watermarks(dc->res_pool->hubbub,
-				&context->bw.dcn.watermarks, ref_clk_mhz, true);
-
-		if (dc->hwseq->wa.DEGVIDCN10_254)
-			hubbub1_wm_change_req_wa(dc->res_pool->hubbub);
+			dcn10_disable_plane(dc, &dc->current_state->res_ctx.pipe_ctx[i]);
 
-		if (dc->debug.sanity_checks) {
-			/* pstate stuck check after watermark update */
-			dcn10_verify_allow_pstate_change_high(dc);
-		}
-	}
-/*	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
-			"\n============== Watermark parameters ==============\n"
-			"a.urgent_ns: %d \n"
-			"a.cstate_enter_plus_exit: %d \n"
-			"a.cstate_exit: %d \n"
-			"a.pstate_change: %d \n"
-			"a.pte_meta_urgent: %d \n"
-			"b.urgent_ns: %d \n"
-			"b.cstate_enter_plus_exit: %d \n"
-			"b.cstate_exit: %d \n"
-			"b.pstate_change: %d \n"
-			"b.pte_meta_urgent: %d \n",
-			context->bw.dcn.watermarks.a.urgent_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.a.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.a.pte_meta_urgent_ns,
-			context->bw.dcn.watermarks.b.urgent_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.b.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.b.pte_meta_urgent_ns
-			);
-	DC_LOG_BANDWIDTH_CALCS(dc->ctx->logger,
-			"\nc.urgent_ns: %d \n"
-			"c.cstate_enter_plus_exit: %d \n"
-			"c.cstate_exit: %d \n"
-			"c.pstate_change: %d \n"
-			"c.pte_meta_urgent: %d \n"
-			"d.urgent_ns: %d \n"
-			"d.cstate_enter_plus_exit: %d \n"
-			"d.cstate_exit: %d \n"
-			"d.pstate_change: %d \n"
-			"d.pte_meta_urgent: %d \n"
-			"========================================================\n",
-			context->bw.dcn.watermarks.c.urgent_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.c.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.c.pte_meta_urgent_ns,
-			context->bw.dcn.watermarks.d.urgent_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.cstate_enter_plus_exit_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.cstate_exit_ns,
-			context->bw.dcn.watermarks.d.cstate_pstate.pstate_change_ns,
-			context->bw.dcn.watermarks.d.pte_meta_urgent_ns
-			);
-*/
+	if (dc->hwseq->wa.DEGVIDCN10_254)
+		hubbub1_wm_change_req_wa(dc->res_pool->hubbub);
 }
 
 static void dcn10_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
-		bool decrease_allowed)
+		bool safe_to_lower)
 {
 	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
 
-	if (IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment))
-		return;
+	if (!IS_FPGA_MAXIMUS_DC(dc->ctx->dce_environment)) {
+		if (context->stream_count == 0)
+			context->bw.dcn.clk.phyclk_khz = 0;
 
-	if (context->stream_count == 0)
-		context->bw.dcn.clk.phyclk_khz = 0;
+		dc->res_pool->dccg->funcs->update_clocks(
+				dc->res_pool->dccg,
+				&context->bw.dcn.clk,
+				safe_to_lower);
 
-	dc->res_pool->dccg->funcs->update_clocks(
-			dc->res_pool->dccg,
-			&context->bw.dcn.clk,
-			decrease_allowed);
+		dcn10_pplib_apply_display_requirements(dc, context);
+	}
 
-	dcn10_pplib_apply_display_requirements(dc, context);
+	hubbub1_program_watermarks(dc->res_pool->hubbub,
+			&context->bw.dcn.watermarks,
+			dc->res_pool->ref_clock_inKhz / 1000,
+			true);
 
 	if (dc->debug.sanity_checks)
 		dcn10_verify_allow_pstate_change_high(dc);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 1c94dae6bbde..2506601120af 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -172,7 +172,7 @@ struct hw_sequencer_funcs {
 	void (*set_bandwidth)(
 			struct dc *dc,
 			struct dc_state *context,
-			bool decrease_allowed);
+			bool safe_to_lower);
 
 	void (*set_drr)(struct pipe_ctx **pipe_ctx, int num_pipes,
 			int vmin, int vmax);
-- 
cgit v1.2.3


From bf28c2e205b1c37e412cb6785a34f10de944bae1 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Tue, 5 Jun 2018 07:33:10 -0400
Subject: drm/amd/display: remove soc_bounding_box.c

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/Makefile        |  3 +-
 .../gpu/drm/amd/display/dc/dml/display_mode_lib.h  |  1 -
 .../drm/amd/display/dc/dml/display_mode_structs.h  |  3 +-
 .../gpu/drm/amd/display/dc/dml/soc_bounding_box.c  | 79 ----------------------
 .../gpu/drm/amd/display/dc/dml/soc_bounding_box.h  | 35 ----------
 5 files changed, 2 insertions(+), 119 deletions(-)
 delete mode 100644 drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
 delete mode 100644 drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h

diff --git a/drivers/gpu/drm/amd/display/dc/dml/Makefile b/drivers/gpu/drm/amd/display/dc/dml/Makefile
index f83a608f93e9..d97ca6528f9d 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dml/Makefile
@@ -36,11 +36,10 @@ CFLAGS_display_mode_lib.o := $(dml_ccflags)
 CFLAGS_display_pipe_clocks.o := $(dml_ccflags)
 CFLAGS_dml1_display_rq_dlg_calc.o := $(dml_ccflags)
 CFLAGS_display_rq_dlg_helpers.o := $(dml_ccflags)
-CFLAGS_soc_bounding_box.o := $(dml_ccflags)
 CFLAGS_dml_common_defs.o := $(dml_ccflags)
 
 DML = display_mode_lib.o display_rq_dlg_helpers.o dml1_display_rq_dlg_calc.o \
-	  soc_bounding_box.o dml_common_defs.o
+	dml_common_defs.o
 
 AMD_DAL_DML = $(addprefix $(AMDDALPATH)/dc/dml/,$(DML))
 
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
index 3c2abcb8a1b0..635206248889 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_lib.h
@@ -27,7 +27,6 @@
 
 
 #include "dml_common_defs.h"
-#include "soc_bounding_box.h"
 #include "dml1_display_rq_dlg_calc.h"
 
 enum dml_project {
diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index 7fa0375939ae..6943801c5fd3 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -64,10 +64,9 @@ struct _vcs_dpi_voltage_scaling_st {
 	double dscclk_mhz;
 	double dcfclk_mhz;
 	double socclk_mhz;
-	double dram_speed_mhz;
+	double dram_speed_mts;
 	double fabricclk_mhz;
 	double dispclk_mhz;
-	double dram_bw_per_chan_gbps;
 	double phyclk_mhz;
 	double dppclk_mhz;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c b/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
deleted file mode 100644
index 324239c77958..000000000000
--- a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.c
+++ /dev/null
@@ -1,79 +0,0 @@
-/*
- * Copyright 2017 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-#include "soc_bounding_box.h"
-#include "display_mode_lib.h"
-#include "dc_features.h"
-
-#include "dml_inline_defs.h"
-
-/*
- * NOTE:
- *   This file is gcc-parseable HW gospel, coming straight from HW engineers.
- *
- * It doesn't adhere to Linux kernel style and sometimes will do things in odd
- * ways. Unless there is something clearly wrong with it the code should
- * remain as-is as it provides us with a guarantee from HW that it is correct.
- */
-
-void dml_socbb_set_latencies(soc_bounding_box_st *to_box, soc_bounding_box_st *from_box)
-{
-	to_box->dram_clock_change_latency_us = from_box->dram_clock_change_latency_us;
-	to_box->sr_exit_time_us = from_box->sr_exit_time_us;
-	to_box->sr_enter_plus_exit_time_us = from_box->sr_enter_plus_exit_time_us;
-	to_box->urgent_latency_us = from_box->urgent_latency_us;
-	to_box->writeback_latency_us = from_box->writeback_latency_us;
-}
-
-voltage_scaling_st dml_socbb_voltage_scaling(
-		const soc_bounding_box_st *soc,
-		enum voltage_state voltage)
-{
-	const voltage_scaling_st *voltage_state;
-	const voltage_scaling_st * const voltage_end = soc->clock_limits + DC__VOLTAGE_STATES;
-
-	for (voltage_state = soc->clock_limits;
-			voltage_state < voltage_end && voltage_state->state != voltage;
-			voltage_state++) {
-	}
-
-	if (voltage_state < voltage_end)
-		return *voltage_state;
-	return soc->clock_limits[DC__VOLTAGE_STATES - 1];
-}
-
-double dml_socbb_return_bw_mhz(soc_bounding_box_st *box, enum voltage_state voltage)
-{
-	double return_bw;
-
-	voltage_scaling_st state = dml_socbb_voltage_scaling(box, voltage);
-
-	return_bw = dml_min((double) box->return_bus_width_bytes * state.dcfclk_mhz,
-			state.dram_bw_per_chan_gbps * 1000.0 * (double) box->num_chans
-					* box->ideal_dram_bw_after_urgent_percent / 100.0);
-
-	return_bw = dml_min((double) box->return_bus_width_bytes * state.fabricclk_mhz, return_bw);
-
-	return return_bw;
-}
diff --git a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h b/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h
deleted file mode 100644
index 7a65206a6d21..000000000000
--- a/drivers/gpu/drm/amd/display/dc/dml/soc_bounding_box.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright 2017 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-
-#ifndef __SOC_BOUNDING_BOX_H__
-#define __SOC_BOUNDING_BOX_H__
-
-#include "dml_common_defs.h"
-
-void dml_socbb_set_latencies(soc_bounding_box_st *to_box, soc_bounding_box_st *from_box);
-voltage_scaling_st dml_socbb_voltage_scaling(const soc_bounding_box_st *box, enum voltage_state voltage);
-double dml_socbb_return_bw_mhz(soc_bounding_box_st *box, enum voltage_state voltage);
-
-#endif
-- 
cgit v1.2.3


From b6c3053a8f431a032a1473dc0e0069ca7fd0b0e5 Mon Sep 17 00:00:00 2001
From: Yongqiang Sun <yongqiang.sun@amd.com>
Date: Fri, 8 Jun 2018 13:07:53 -0500
Subject: drm/amd/display: Check scaling ration not viewports params.

In case of roation, width and height in viewport is difference
between viewport and h_active and v_active, while this is not scaling.
The right way is check ratios in scaling data,
to determine it is a scaling case or not.

Signed-off-by: Yongqiang Sun <yongqiang.sun@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index c69fa4bfab0a..742fd497ed00 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -145,10 +145,10 @@ static bool dpp_get_optimal_number_of_taps(
 		pixel_width = scl_data->viewport.width;
 
 	/* Some ASICs does not support  FP16 scaling, so we reject modes require this*/
-	if (scl_data->viewport.width  != scl_data->h_active &&
-		scl_data->viewport.height != scl_data->v_active &&
+	if (scl_data->format == PIXEL_FORMAT_FP16 &&
 		dpp->caps->dscl_data_proc_format == DSCL_DATA_PRCESSING_FIXED_FORMAT &&
-		scl_data->format == PIXEL_FORMAT_FP16)
+		scl_data->ratios.horz.value != dc_fixpt_one.value &&
+		scl_data->ratios.vert.value != dc_fixpt_one.value)
 		return false;
 
 	if (scl_data->viewport.width > scl_data->h_active &&
-- 
cgit v1.2.3


From c1aaea99a43e39c7c8dc6c71b84589c89d5bcbf2 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 5 Jun 2018 09:14:36 -0400
Subject: drm/amd/display: dal 3.1.52

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index cbcdbd9b9910..74e6653b9852 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.51"
+#define DC_VER "3.1.52"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 7f93c1de64693dc18afe55559f14cee6b5403c6c Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Sat, 9 Jun 2018 19:33:14 -0400
Subject: drm/amd/display: add valid regoffset and NULL pointer check

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c      |  8 ++++---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c   |  9 ++++----
 .../amd/display/dc/dce110/dce110_hw_sequencer.c    |  7 +++---
 .../gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c    |  5 +++++
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 26 ++++++++++++++++------
 5 files changed, 38 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 8eb8b8768465..fa56c0fc02bf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -33,6 +33,7 @@
 #include "dc_link_dp.h"
 #include "dc_link_ddc.h"
 #include "link_hwss.h"
+#include "opp.h"
 
 #include "link_encoder.h"
 #include "hw_sequencer.h"
@@ -2382,9 +2383,10 @@ void core_link_enable_stream(
 	core_dc->hwss.enable_audio_stream(pipe_ctx);
 
 	/* turn off otg test pattern if enable */
-	pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
-			CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
-			COLOR_DEPTH_UNDEFINED);
+	if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
+		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
+				COLOR_DEPTH_UNDEFINED);
 
 	core_dc->hwss.enable_stream(pipe_ctx);
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 509f265663d2..049fc5cce1d2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -3,6 +3,7 @@
 #include "dc.h"
 #include "dc_link_dp.h"
 #include "dm_helpers.h"
+#include "opp.h"
 
 #include "inc/core_types.h"
 #include "link_hwss.h"
@@ -2511,8 +2512,8 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		pipe_ctx->stream->bit_depth_params = params;
 		pipe_ctx->stream_res.opp->funcs->
 			opp_program_bit_depth_reduction(pipe_ctx->stream_res.opp, &params);
-
-		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
+			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				controller_test_pattern, color_depth);
 	}
 	break;
@@ -2524,8 +2525,8 @@ static void set_crtc_test_pattern(struct dc_link *link,
 		pipe_ctx->stream->bit_depth_params = params;
 		pipe_ctx->stream_res.opp->funcs->
 			opp_program_bit_depth_reduction(pipe_ctx->stream_res.opp, &params);
-
-		pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
+		if (pipe_ctx->stream_res.tg->funcs->set_test_pattern)
+			pipe_ctx->stream_res.tg->funcs->set_test_pattern(pipe_ctx->stream_res.tg,
 				CONTROLLER_DP_TEST_PATTERN_VIDEOMODE,
 				color_depth);
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 3b983b3f3423..9cbd5036db07 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1475,7 +1475,7 @@ static void power_down_controllers(struct dc *dc)
 {
 	int i;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		dc->res_pool->timing_generators[i]->funcs->disable_crtc(
 				dc->res_pool->timing_generators[i]);
 	}
@@ -1515,12 +1515,13 @@ static void disable_vga_and_power_gate_all_controllers(
 	struct timing_generator *tg;
 	struct dc_context *ctx = dc->ctx;
 
-	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+	for (i = 0; i < dc->res_pool->timing_generator_count; i++) {
 		tg = dc->res_pool->timing_generators[i];
 
 		if (tg->funcs->disable_vga)
 			tg->funcs->disable_vga(tg);
-
+	}
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
 		/* Enable CLOCK gating for each pipe BEFORE controller
 		 * powergating. */
 		enable_display_pipe_clock_gating(ctx,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
index 623db09389b5..1ea91e153d3a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubbub.c
@@ -483,6 +483,11 @@ void hubbub1_update_dchub(
 	struct hubbub *hubbub,
 	struct dchub_init_data *dh_data)
 {
+	if (REG(DCHUBBUB_SDPIF_FB_TOP) == 0) {
+		ASSERT(false);
+		/*should not come here*/
+		return;
+	}
 	/* TODO: port code from dal2 */
 	switch (dh_data->fb_mode) {
 	case FRAME_BUFFER_MODE_ZFB_ONLY:
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 21b45e8d49f7..3b2cb2d3b8a6 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -415,6 +415,8 @@ static void dpp_pg_control(
 
 	if (hws->ctx->dc->debug.disable_dpp_power_gate)
 		return;
+	if (REG(DOMAIN1_PG_CONFIG) == 0)
+		return;
 
 	switch (dpp_inst) {
 	case 0: /* DPP0 */
@@ -465,6 +467,8 @@ static void hubp_pg_control(
 
 	if (hws->ctx->dc->debug.disable_hubp_power_gate)
 		return;
+	if (REG(DOMAIN0_PG_CONFIG) == 0)
+		return;
 
 	switch (hubp_inst) {
 	case 0: /* DCHUBP0 */
@@ -865,7 +869,8 @@ void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx)
 		return;
 
 	mpc->funcs->remove_mpcc(mpc, mpc_tree_params, mpcc_to_remove);
-	opp->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
+	if (opp != NULL)
+		opp->mpcc_disconnect_pending[pipe_ctx->plane_res.mpcc_inst] = true;
 
 	dc->optimized_required = true;
 
@@ -1343,10 +1348,11 @@ static void dcn10_enable_per_frame_crtc_position_reset(
 
 	DC_SYNC_INFO("Setting up\n");
 	for (i = 0; i < group_size; i++)
-		grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
-				grouped_pipes[i]->stream_res.tg,
-				grouped_pipes[i]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst,
-				&grouped_pipes[i]->stream->triggered_crtc_reset);
+		if (grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset)
+			grouped_pipes[i]->stream_res.tg->funcs->enable_crtc_reset(
+					grouped_pipes[i]->stream_res.tg,
+					grouped_pipes[i]->stream->triggered_crtc_reset.event_source->status.primary_otg_inst,
+					&grouped_pipes[i]->stream->triggered_crtc_reset);
 
 	DC_SYNC_INFO("Waiting for trigger\n");
 
@@ -2496,8 +2502,14 @@ static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 
 static void dcn10_update_dchub(struct dce_hwseq *hws, struct dchub_init_data *dh_data)
 {
-	if (hws->ctx->dc->res_pool->hubbub != NULL)
-		hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data);
+	if (hws->ctx->dc->res_pool->hubbub != NULL) {
+		struct hubp *hubp = hws->ctx->dc->res_pool->hubps[0];
+
+		if (hubp->funcs->hubp_update_dchub)
+			hubp->funcs->hubp_update_dchub(hubp, dh_data);
+		else
+			hubbub1_update_dchub(hws->ctx->dc->res_pool->hubbub, dh_data);
+	}
 }
 
 static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
-- 
cgit v1.2.3


From 1eeedbcc20d64ff2ef7eb9823f85bbb1c2545064 Mon Sep 17 00:00:00 2001
From: Samson Tam <Samson.Tam@amd.com>
Date: Wed, 30 May 2018 15:44:50 -0400
Subject: drm/amd/display: get board layout for edid emulation

Signed-off-by: Samson Tam <Samson.Tam@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/bios/bios_parser.c  | 196 ++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c | 218 ++++++++++++++++++++-
 drivers/gpu/drm/amd/display/dc/dc_bios_types.h     |   4 +
 .../gpu/drm/amd/display/include/grph_object_defs.h |  46 +++++
 .../gpu/drm/amd/display/include/grph_object_id.h   |  11 ++
 5 files changed, 474 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
index c7f0b27e457e..be8a2494355a 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
@@ -3762,6 +3762,200 @@ static struct integrated_info *bios_parser_create_integrated_info(
 	return NULL;
 }
 
+enum bp_result update_slot_layout_info(
+	struct dc_bios *dcb,
+	unsigned int i,
+	struct slot_layout_info *slot_layout_info,
+	unsigned int record_offset)
+{
+	unsigned int j;
+	struct bios_parser *bp;
+	ATOM_BRACKET_LAYOUT_RECORD *record;
+	ATOM_COMMON_RECORD_HEADER *record_header;
+	enum bp_result result = BP_RESULT_NORECORD;
+
+	bp = BP_FROM_DCB(dcb);
+	record = NULL;
+	record_header = NULL;
+
+	for (;;) {
+
+		record_header = (ATOM_COMMON_RECORD_HEADER *)
+			GET_IMAGE(ATOM_COMMON_RECORD_HEADER, record_offset);
+		if (record_header == NULL) {
+			result = BP_RESULT_BADBIOSTABLE;
+			break;
+		}
+
+		/* the end of the list */
+		if (record_header->ucRecordType == 0xff ||
+			record_header->ucRecordSize == 0)	{
+			break;
+		}
+
+		if (record_header->ucRecordType ==
+			ATOM_BRACKET_LAYOUT_RECORD_TYPE &&
+			sizeof(ATOM_BRACKET_LAYOUT_RECORD)
+			<= record_header->ucRecordSize) {
+			record = (ATOM_BRACKET_LAYOUT_RECORD *)
+				(record_header);
+			result = BP_RESULT_OK;
+			break;
+		}
+
+		record_offset += record_header->ucRecordSize;
+	}
+
+	/* return if the record not found */
+	if (result != BP_RESULT_OK)
+		return result;
+
+	/* get slot sizes */
+	slot_layout_info->length = record->ucLength;
+	slot_layout_info->width = record->ucWidth;
+
+	/* get info for each connector in the slot */
+	slot_layout_info->num_of_connectors = record->ucConnNum;
+	for (j = 0; j < slot_layout_info->num_of_connectors; ++j) {
+		slot_layout_info->connectors[j].connector_type =
+			(enum connector_layout_type)
+			(record->asConnInfo[j].ucConnectorType);
+		switch (record->asConnInfo[j].ucConnectorType) {
+		case CONNECTOR_TYPE_DVI_D:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DVI_D;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DVI;
+			break;
+
+		case CONNECTOR_TYPE_HDMI:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_HDMI;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_HDMI;
+			break;
+
+		case CONNECTOR_TYPE_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DP;
+			break;
+
+		case CONNECTOR_TYPE_MINI_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_MINI_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_MINI_DP;
+			break;
+
+		default:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_UNKNOWN;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_UNKNOWN;
+		}
+
+		slot_layout_info->connectors[j].position =
+			record->asConnInfo[j].ucPosition;
+		slot_layout_info->connectors[j].connector_id =
+			object_id_from_bios_object_id(
+				record->asConnInfo[j].usConnectorObjectId);
+	}
+	return result;
+}
+
+
+enum bp_result get_bracket_layout_record(
+	struct dc_bios *dcb,
+	unsigned int bracket_layout_id,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int i;
+	unsigned int record_offset;
+	struct bios_parser *bp;
+	enum bp_result result;
+	ATOM_OBJECT *object;
+	ATOM_OBJECT_TABLE *object_table;
+	unsigned int genericTableOffset;
+
+	bp = BP_FROM_DCB(dcb);
+	object = NULL;
+	if (slot_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid slot_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+
+
+	genericTableOffset = bp->object_info_tbl_offset +
+		bp->object_info_tbl.v1_3->usMiscObjectTableOffset;
+	object_table = (ATOM_OBJECT_TABLE *)
+		GET_IMAGE(ATOM_OBJECT_TABLE, genericTableOffset);
+	if (!object_table)
+		return BP_RESULT_FAILURE;
+
+	result = BP_RESULT_NORECORD;
+	for (i = 0; i < object_table->ucNumberOfObjects; ++i) {
+
+		if (bracket_layout_id ==
+			object_table->asObjects[i].usObjectID) {
+
+			object = &object_table->asObjects[i];
+			record_offset = object->usRecordOffset +
+				bp->object_info_tbl_offset;
+
+			result = update_slot_layout_info(dcb, i,
+				slot_layout_info, record_offset);
+			break;
+		}
+	}
+	return result;
+}
+
+static enum bp_result bios_get_board_layout_info(
+	struct dc_bios *dcb,
+	struct board_layout_info *board_layout_info)
+{
+	unsigned int i;
+	struct bios_parser *bp;
+	enum bp_result record_result;
+
+	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1,
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2,
+		0, 0
+	};
+
+	bp = BP_FROM_DCB(dcb);
+	if (board_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+
+	board_layout_info->num_of_slots = 0;
+
+	for (i = 0; i < MAX_BOARD_SLOTS; ++i) {
+		record_result = get_bracket_layout_record(dcb,
+			slot_index_to_vbios_id[i],
+			&board_layout_info->slots[i]);
+
+		if (record_result == BP_RESULT_NORECORD && i > 0)
+			break; /* no more slots present in bios */
+		else if (record_result != BP_RESULT_OK)
+			return record_result;  /* fail */
+
+		++board_layout_info->num_of_slots;
+	}
+
+	/* all data is valid */
+	board_layout_info->is_number_of_slots_valid = 1;
+	board_layout_info->is_slots_size_valid = 1;
+	board_layout_info->is_connector_offsets_valid = 1;
+	board_layout_info->is_connector_lengths_valid = 1;
+
+	return BP_RESULT_OK;
+}
+
 /******************************************************************************/
 
 static const struct dc_vbios_funcs vbios_funcs = {
@@ -3836,6 +4030,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.post_init = bios_parser_post_init,  /* patch vbios table for mxm module by reading i2c */
 
 	.bios_parser_destroy = bios_parser_destroy,
+
+	.get_board_layout_info = bios_get_board_layout_info,
 };
 
 static bool bios_parser_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index b8cef7af3c4a..aeb56e402ccc 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -43,6 +43,29 @@
 #include "bios_parser_interface.h"
 
 #include "bios_parser_common.h"
+
+/* Temporarily add in defines until ObjectID.h patch is updated in a few days */
+#ifndef GENERIC_OBJECT_ID_BRACKET_LAYOUT
+#define GENERIC_OBJECT_ID_BRACKET_LAYOUT          0x05
+#endif /* GENERIC_OBJECT_ID_BRACKET_LAYOUT */
+
+#ifndef GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1	\
+	(GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+	GRAPH_OBJECT_ENUM_ID1 << ENUM_ID_SHIFT |\
+	GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+#endif /* GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1 */
+
+#ifndef GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2
+#define GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2	\
+	(GRAPH_OBJECT_TYPE_GENERIC << OBJECT_TYPE_SHIFT |\
+	GRAPH_OBJECT_ENUM_ID2 << ENUM_ID_SHIFT |\
+	GENERIC_OBJECT_ID_BRACKET_LAYOUT << OBJECT_ID_SHIFT)
+#endif /* GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2 */
+
+#define DC_LOGGER \
+	bp->base.ctx->logger
+
 #define LAST_RECORD_TYPE 0xff
 #define SMU9_SYSPLL0_ID  0
 
@@ -86,7 +109,6 @@ static struct atom_encoder_caps_record *get_encoder_cap_record(
 
 #define DATA_TABLES(table) (bp->master_data_tbl->listOfdatatables.table)
 
-
 static void destruct(struct bios_parser *bp)
 {
 	kfree(bp->base.bios_local_image);
@@ -1854,6 +1876,198 @@ static struct integrated_info *bios_parser_create_integrated_info(
 	return NULL;
 }
 
+static enum bp_result update_slot_layout_info(
+	struct dc_bios *dcb,
+	unsigned int i,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int record_offset;
+	unsigned int j;
+	struct atom_display_object_path_v2 *object;
+	struct atom_bracket_layout_record *record;
+	struct atom_common_record_header *record_header;
+	enum bp_result result;
+	struct bios_parser *bp;
+	struct object_info_table *tbl;
+	struct display_object_info_table_v1_4 *v1_4;
+
+	record = NULL;
+	record_header = NULL;
+	result = BP_RESULT_NORECORD;
+
+	bp = BP_FROM_DCB(dcb);
+	tbl = &bp->object_info_tbl;
+	v1_4 = tbl->v1_4;
+
+	object = &v1_4->display_path[i];
+	record_offset = (unsigned int)
+		(object->disp_recordoffset) +
+		(unsigned int)(bp->object_info_tbl_offset);
+
+	for (;;) {
+
+		record_header = (struct atom_common_record_header *)
+			GET_IMAGE(struct atom_common_record_header,
+			record_offset);
+		if (record_header == NULL) {
+			result = BP_RESULT_BADBIOSTABLE;
+			break;
+		}
+
+		/* the end of the list */
+		if (record_header->record_type == 0xff ||
+			record_header->record_size == 0)	{
+			break;
+		}
+
+		if (record_header->record_type ==
+			ATOM_BRACKET_LAYOUT_RECORD_TYPE &&
+			sizeof(struct atom_bracket_layout_record)
+			<= record_header->record_size) {
+			record = (struct atom_bracket_layout_record *)
+				(record_header);
+			result = BP_RESULT_OK;
+			break;
+		}
+
+		record_offset += record_header->record_size;
+	}
+
+	/* return if the record not found */
+	if (result != BP_RESULT_OK)
+		return result;
+
+	/* get slot sizes */
+	slot_layout_info->length = record->bracketlen;
+	slot_layout_info->width = record->bracketwidth;
+
+	/* get info for each connector in the slot */
+	slot_layout_info->num_of_connectors = record->conn_num;
+	for (j = 0; j < slot_layout_info->num_of_connectors; ++j) {
+		slot_layout_info->connectors[j].connector_type =
+			(enum connector_layout_type)
+			(record->conn_info[j].connector_type);
+		switch (record->conn_info[j].connector_type) {
+		case CONNECTOR_TYPE_DVI_D:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DVI_D;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DVI;
+			break;
+
+		case CONNECTOR_TYPE_HDMI:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_HDMI;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_HDMI;
+			break;
+
+		case CONNECTOR_TYPE_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_DP;
+			break;
+
+		case CONNECTOR_TYPE_MINI_DISPLAY_PORT:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_MINI_DP;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_MINI_DP;
+			break;
+
+		default:
+			slot_layout_info->connectors[j].connector_type =
+				CONNECTOR_LAYOUT_TYPE_UNKNOWN;
+			slot_layout_info->connectors[j].length =
+				CONNECTOR_SIZE_UNKNOWN;
+		}
+
+		slot_layout_info->connectors[j].position =
+			record->conn_info[j].position;
+		slot_layout_info->connectors[j].connector_id =
+			object_id_from_bios_object_id(
+				record->conn_info[j].connectorobjid);
+	}
+	return result;
+}
+
+
+static enum bp_result get_bracket_layout_record(
+	struct dc_bios *dcb,
+	unsigned int bracket_layout_id,
+	struct slot_layout_info *slot_layout_info)
+{
+	unsigned int i;
+	struct bios_parser *bp = BP_FROM_DCB(dcb);
+	enum bp_result result;
+	struct object_info_table *tbl;
+	struct display_object_info_table_v1_4 *v1_4;
+
+	if (slot_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid slot_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+	tbl = &bp->object_info_tbl;
+	v1_4 = tbl->v1_4;
+
+	result = BP_RESULT_NORECORD;
+	for (i = 0; i < v1_4->number_of_path; ++i)	{
+
+		if (bracket_layout_id ==
+			v1_4->display_path[i].display_objid) {
+			result = update_slot_layout_info(dcb, i,
+				slot_layout_info);
+			break;
+		}
+	}
+	return result;
+}
+
+static enum bp_result bios_get_board_layout_info(
+	struct dc_bios *dcb,
+	struct board_layout_info *board_layout_info)
+{
+	unsigned int i;
+	struct bios_parser *bp;
+	enum bp_result record_result;
+
+	const unsigned int slot_index_to_vbios_id[MAX_BOARD_SLOTS] = {
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID1,
+		GENERICOBJECT_BRACKET_LAYOUT_ENUM_ID2,
+		0, 0
+	};
+
+	bp = BP_FROM_DCB(dcb);
+	if (board_layout_info == NULL) {
+		DC_LOG_DETECTION_EDID_PARSER("Invalid board_layout_info\n");
+		return BP_RESULT_BADINPUT;
+	}
+
+	board_layout_info->num_of_slots = 0;
+
+	for (i = 0; i < MAX_BOARD_SLOTS; ++i) {
+		record_result = get_bracket_layout_record(dcb,
+			slot_index_to_vbios_id[i],
+			&board_layout_info->slots[i]);
+
+		if (record_result == BP_RESULT_NORECORD && i > 0)
+			break; /* no more slots present in bios */
+		else if (record_result != BP_RESULT_OK)
+			return record_result;  /* fail */
+
+		++board_layout_info->num_of_slots;
+	}
+
+	/* all data is valid */
+	board_layout_info->is_number_of_slots_valid = 1;
+	board_layout_info->is_slots_size_valid = 1;
+	board_layout_info->is_connector_offsets_valid = 1;
+	board_layout_info->is_connector_lengths_valid = 1;
+
+	return BP_RESULT_OK;
+}
+
 static const struct dc_vbios_funcs vbios_funcs = {
 	.get_connectors_number = bios_parser_get_connectors_number,
 
@@ -1925,6 +2139,8 @@ static const struct dc_vbios_funcs vbios_funcs = {
 	.bios_parser_destroy = firmware_parser_destroy,
 
 	.get_smu_clock_info = bios_parser_get_smu_clock_info,
+
+	.get_board_layout_info = bios_get_board_layout_info,
 };
 
 static bool bios_parser_construct(
diff --git a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
index d9b84ec7954c..90082bab71f0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_bios_types.h
@@ -198,6 +198,10 @@ struct dc_vbios_funcs {
 	void (*post_init)(struct dc_bios *bios);
 
 	void (*bios_parser_destroy)(struct dc_bios **dcb);
+
+	enum bp_result (*get_board_layout_info)(
+		struct dc_bios *dcb,
+		struct board_layout_info *board_layout_info);
 };
 
 struct bios_registers {
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_defs.h
index 2941b882b0b6..58bb42ed85ca 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_defs.h
@@ -37,6 +37,10 @@
  * ********************************************************************
  */
 
+#define MAX_CONNECTOR_NUMBER_PER_SLOT	(16)
+#define MAX_BOARD_SLOTS					(4)
+#define INVALID_CONNECTOR_INDEX			((unsigned int)(-1))
+
 /* HPD unit id - HW direct translation */
 enum hpd_source_id {
 	HPD_SOURCEID1 = 0,
@@ -136,5 +140,47 @@ enum sync_source {
 	SYNC_SOURCE_DUAL_GPU_PIN
 };
 
+/* connector sizes in millimeters - from BiosParserTypes.hpp */
+#define CONNECTOR_SIZE_DVI			40
+#define CONNECTOR_SIZE_VGA			32
+#define CONNECTOR_SIZE_HDMI			16
+#define CONNECTOR_SIZE_DP			16
+#define CONNECTOR_SIZE_MINI_DP			9
+#define CONNECTOR_SIZE_UNKNOWN			30
+
+enum connector_layout_type {
+	CONNECTOR_LAYOUT_TYPE_UNKNOWN,
+	CONNECTOR_LAYOUT_TYPE_DVI_D,
+	CONNECTOR_LAYOUT_TYPE_DVI_I,
+	CONNECTOR_LAYOUT_TYPE_VGA,
+	CONNECTOR_LAYOUT_TYPE_HDMI,
+	CONNECTOR_LAYOUT_TYPE_DP,
+	CONNECTOR_LAYOUT_TYPE_MINI_DP,
+};
+struct connector_layout_info {
+	struct graphics_object_id connector_id;
+	enum connector_layout_type connector_type;
+	unsigned int length;
+	unsigned int position;  /* offset in mm from right side of the board */
+};
+
+/* length and width in mm */
+struct slot_layout_info {
+	unsigned int length;
+	unsigned int width;
+	unsigned int num_of_connectors;
+	struct connector_layout_info connectors[MAX_CONNECTOR_NUMBER_PER_SLOT];
+};
+
+struct board_layout_info {
+	unsigned int num_of_slots;
 
+	/* indicates valid information in bracket layout structure. */
+	unsigned int is_number_of_slots_valid : 1;
+	unsigned int is_slots_size_valid : 1;
+	unsigned int is_connector_offsets_valid : 1;
+	unsigned int is_connector_lengths_valid : 1;
+
+	struct slot_layout_info slots[MAX_BOARD_SLOTS];
+};
 #endif
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_id.h b/drivers/gpu/drm/amd/display/include/grph_object_id.h
index 92cc6c112ea6..33b3d755fe65 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_id.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_id.h
@@ -292,4 +292,15 @@ static inline enum engine_id dal_graphics_object_id_get_engine_id(
 		return (enum engine_id) id.id;
 	return ENGINE_ID_UNKNOWN;
 }
+
+static inline bool dal_graphics_object_id_equal(
+	struct graphics_object_id id_1,
+	struct graphics_object_id id_2)
+{
+	if ((id_1.id == id_2.id) && (id_1.enum_id == id_2.enum_id) &&
+		(id_1.type == id_2.type)) {
+		return true;
+	}
+	return false;
+}
 #endif
-- 
cgit v1.2.3


From f3efec54ed6ac05ba63be1bd93bd741d41b6eb37 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Fri, 8 Jun 2018 17:36:26 -0400
Subject: drm/amd/display: Allow option to use worst-case watermark

use worse case watermark (consider both DCC and VM)
to keep golden consistent regardless of DCC

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c | 23 ++++++++++++++++++++++-
 drivers/gpu/drm/amd/display/dc/dc.h              |  1 +
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 12261fbc25e0..e44b8d3d6891 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -31,6 +31,8 @@
 
 #include "resource.h"
 #include "dcn10/dcn10_resource.h"
+#include "dcn10/dcn10_hubbub.h"
+
 #include "dcn_calc_math.h"
 
 #define DC_LOGGER \
@@ -889,7 +891,26 @@ bool dcn_validate_bandwidth(
 				ASSERT(pipe->plane_res.scl_data.ratios.vert.value != dc_fixpt_one.value
 					|| v->scaler_rec_out_width[input_idx] == v->viewport_height[input_idx]);
 			}
-			v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
+
+			if (dc->debug.optimized_watermark) {
+				/*
+				 * this method requires us to always re-calculate watermark when dcc change
+				 * between flip.
+				 */
+				v->dcc_enable[input_idx] = pipe->plane_state->dcc.enable ? dcn_bw_yes : dcn_bw_no;
+			} else {
+				/*
+				 * allow us to disable dcc on the fly without re-calculating WM
+				 *
+				 * extra overhead for DCC is quite small.  for 1080p WM without
+				 * DCC is only 0.417us lower (urgent goes from 6.979us to 6.562us)
+				 */
+				unsigned int bpe;
+
+				v->dcc_enable[input_idx] = dc->res_pool->hubbub->funcs->dcc_support_pixel_format(
+						pipe->plane_state->format, &bpe) ? dcn_bw_yes : dcn_bw_no;
+			}
+
 			v->source_pixel_format[input_idx] = tl_pixel_format_to_bw_defs(
 					pipe->plane_state->format);
 			v->source_surface_mode[input_idx] = tl_sw_mode_to_bw_defs(
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 74e6653b9852..0cb7e10d2505 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -233,6 +233,7 @@ struct dc_debug {
 	int urgent_latency_ns;
 	int percent_of_ideal_drambw;
 	int dram_clock_change_latency_ns;
+	bool optimized_watermark;
 	int always_scale;
 	bool disable_pplib_clock_request;
 	bool disable_clock_gate;
-- 
cgit v1.2.3


From 180fc134d712a93a2bbc3d11ed657b5208e6f90f Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Tue, 5 Jun 2018 12:43:23 -0400
Subject: drm/scheduler: Rename cleanup functions v2.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Everything in the flush code path (i.e. waiting for SW queue
to become empty) names with *_flush()
and everything in the release code path names *_fini()

This patch also effect the amdgpu and etnaviv drivers which
use those functions.

v2:
Also pplay the change to vd3.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Acked-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c   |  8 ++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c   |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c   |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c   |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c    |  4 ++--
 drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c     |  2 +-
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c     |  2 +-
 drivers/gpu/drm/etnaviv/etnaviv_drv.c     |  4 ++--
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 18 +++++++++---------
 drivers/gpu/drm/v3d/v3d_drv.c             |  2 +-
 include/drm/gpu_scheduler.h               |  6 +++---
 11 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 64b3a1ed04dc..c0f06c02f2de 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -104,7 +104,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 
 failed:
 	for (j = 0; j < i; j++)
-		drm_sched_entity_fini(&adev->rings[j]->sched,
+		drm_sched_entity_destroy(&adev->rings[j]->sched,
 				      &ctx->rings[j].entity);
 	kfree(ctx->fences);
 	ctx->fences = NULL;
@@ -178,7 +178,7 @@ static void amdgpu_ctx_do_release(struct kref *ref)
 		if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 			continue;
 
-		drm_sched_entity_fini(&ctx->adev->rings[i]->sched,
+		drm_sched_entity_destroy(&ctx->adev->rings[i]->sched,
 			&ctx->rings[i].entity);
 	}
 
@@ -466,7 +466,7 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 			if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 				continue;
 
-			max_wait = drm_sched_entity_do_release(&ctx->adev->rings[i]->sched,
+			max_wait = drm_sched_entity_flush(&ctx->adev->rings[i]->sched,
 					  &ctx->rings[i].entity, max_wait);
 		}
 	}
@@ -492,7 +492,7 @@ void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
 				continue;
 
 			if (kref_read(&ctx->refcount) == 1)
-				drm_sched_entity_cleanup(&ctx->adev->rings[i]->sched,
+				drm_sched_entity_fini(&ctx->adev->rings[i]->sched,
 					&ctx->rings[i].entity);
 			else
 				DRM_ERROR("ctx %p is still alive\n", ctx);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 0c084d3d0865..0246cb87d9e4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -162,7 +162,7 @@ error_mem:
 static void amdgpu_ttm_global_fini(struct amdgpu_device *adev)
 {
 	if (adev->mman.mem_global_referenced) {
-		drm_sched_entity_fini(adev->mman.entity.sched,
+		drm_sched_entity_destroy(adev->mman.entity.sched,
 				      &adev->mman.entity);
 		mutex_destroy(&adev->mman.gtt_window_lock);
 		drm_global_item_unref(&adev->mman.bo_global_ref.ref);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index cc15d3230402..0b46ea1c6290 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -309,7 +309,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
 		kfree(adev->uvd.inst[j].saved_bo);
 
-		drm_sched_entity_fini(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity);
+		drm_sched_entity_destroy(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity);
 
 		amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo,
 				      &adev->uvd.inst[j].gpu_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 23d960ec1cf2..b0dcdfd85f5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -222,7 +222,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
-	drm_sched_entity_fini(&adev->vce.ring[0].sched, &adev->vce.entity);
+	drm_sched_entity_destroy(&adev->vce.ring[0].sched, &adev->vce.entity);
 
 	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
 		(void **)&adev->vce.cpu_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 590db78b8c72..837066076ccf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2643,7 +2643,7 @@ error_free_root:
 	vm->root.base.bo = NULL;
 
 error_free_sched_entity:
-	drm_sched_entity_fini(&ring->sched, &vm->entity);
+	drm_sched_entity_destroy(&ring->sched, &vm->entity);
 
 	return r;
 }
@@ -2780,7 +2780,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 
-	drm_sched_entity_fini(vm->entity.sched, &vm->entity);
+	drm_sched_entity_destroy(vm->entity.sched, &vm->entity);
 
 	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(adev->dev, "still active bo inside vm\n");
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index bfddf97dd13e..1df1c6115341 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -470,7 +470,7 @@ static int uvd_v6_0_sw_fini(void *handle)
 		return r;
 
 	if (uvd_v6_0_enc_support(adev)) {
-		drm_sched_entity_fini(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc);
+		drm_sched_entity_destroy(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc);
 
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst->ring_enc[i]);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 57d32f21b3a6..ba244d3b74db 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -491,7 +491,7 @@ static int uvd_v7_0_sw_fini(void *handle)
 		return r;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
-		drm_sched_entity_fini(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc);
+		drm_sched_entity_destroy(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc);
 
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index e5013a999147..45bfdf4cc107 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -78,8 +78,8 @@ static void etnaviv_postclose(struct drm_device *dev, struct drm_file *file)
 				gpu->lastctx = NULL;
 			mutex_unlock(&gpu->lock);
 
-			drm_sched_entity_fini(&gpu->sched,
-					      &ctx->sched_entity[i]);
+			drm_sched_entity_destroy(&gpu->sched,
+						&ctx->sched_entity[i]);
 		}
 	}
 
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 6a316701da73..7d2560699b84 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -256,7 +256,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 
 
 /**
- * drm_sched_entity_do_release - Destroy a context entity
+ * drm_sched_entity_flush - Flush a context entity
  *
  * @sched: scheduler instance
  * @entity: scheduler entity
@@ -267,7 +267,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
  *
  * Returns the remaining time in jiffies left from the input timeout
  */
-long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
+long drm_sched_entity_flush(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity, long timeout)
 {
 	long ret = timeout;
@@ -294,7 +294,7 @@ long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
 
 	return ret;
 }
-EXPORT_SYMBOL(drm_sched_entity_do_release);
+EXPORT_SYMBOL(drm_sched_entity_flush);
 
 /**
  * drm_sched_entity_cleanup - Destroy a context entity
@@ -306,7 +306,7 @@ EXPORT_SYMBOL(drm_sched_entity_do_release);
  * entity and signals all jobs with an error code if the process was killed.
  *
  */
-void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
+void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity)
 {
 
@@ -357,7 +357,7 @@ void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
 	dma_fence_put(entity->last_scheduled);
 	entity->last_scheduled = NULL;
 }
-EXPORT_SYMBOL(drm_sched_entity_cleanup);
+EXPORT_SYMBOL(drm_sched_entity_fini);
 
 /**
  * drm_sched_entity_fini - Destroy a context entity
@@ -367,13 +367,13 @@ EXPORT_SYMBOL(drm_sched_entity_cleanup);
  *
  * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup()
  */
-void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
+void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched,
 				struct drm_sched_entity *entity)
 {
-	drm_sched_entity_do_release(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
-	drm_sched_entity_cleanup(sched, entity);
+	drm_sched_entity_flush(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
+	drm_sched_entity_fini(sched, entity);
 }
-EXPORT_SYMBOL(drm_sched_entity_fini);
+EXPORT_SYMBOL(drm_sched_entity_destroy);
 
 static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb)
 {
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index cdb582043b4f..567f7d46d912 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -151,7 +151,7 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file)
 	enum v3d_queue q;
 
 	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		drm_sched_entity_fini(&v3d->queue[q].sched,
+		drm_sched_entity_destroy(&v3d->queue[q].sched,
 				      &v3d_priv->sched_entity[q]);
 	}
 
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 7c2dfd6cc1af..4214ceb71c05 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -284,12 +284,12 @@ int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
 			  struct drm_sched_entity *entity,
 			  struct drm_sched_rq *rq,
 			  atomic_t *guilty);
-long drm_sched_entity_do_release(struct drm_gpu_scheduler *sched,
+long drm_sched_entity_flush(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity, long timeout);
-void drm_sched_entity_cleanup(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity);
 void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity);
+void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched,
+			   struct drm_sched_entity *entity);
 void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 			       struct drm_sched_entity *entity);
 void drm_sched_entity_set_rq(struct drm_sched_entity *entity,
-- 
cgit v1.2.3


From c49d82800bbf04a6d7d6843c6f2c2ea5746eb26e Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Tue, 5 Jun 2018 12:56:26 -0400
Subject: drm/amdgpu: Rename entity cleanup finctions.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Everything in the flush code path (i.e. waiting for SW queue
to become empty) names with *_flush()
and everything in the release code path names *_fini()

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c | 6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index fb17838114c3..86e4d8bd52a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -683,8 +683,8 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
 int amdgpu_ctx_wait_prev_fence(struct amdgpu_ctx *ctx, unsigned ring_id);
 
 void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr);
-void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr);
+void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr);
 void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr);
 
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index c0f06c02f2de..0120b24fae1b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -444,7 +444,7 @@ void amdgpu_ctx_mgr_init(struct amdgpu_ctx_mgr *mgr)
 	idr_init(&mgr->ctx_handles);
 }
 
-void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
+void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr)
 {
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
@@ -473,7 +473,7 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 	mutex_unlock(&mgr->lock);
 }
 
-void amdgpu_ctx_mgr_entity_cleanup(struct amdgpu_ctx_mgr *mgr)
+void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 {
 	struct amdgpu_ctx *ctx;
 	struct idr *idp;
@@ -506,7 +506,7 @@ void amdgpu_ctx_mgr_fini(struct amdgpu_ctx_mgr *mgr)
 	struct idr *idp;
 	uint32_t id;
 
-	amdgpu_ctx_mgr_entity_cleanup(mgr);
+	amdgpu_ctx_mgr_entity_fini(mgr);
 
 	idp = &mgr->ctx_handles;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index a549483032b0..684149741427 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -860,7 +860,7 @@ static int amdgpu_flush(struct file *f, fl_owner_t id)
 	struct drm_file *file_priv = f->private_data;
 	struct amdgpu_fpriv *fpriv = file_priv->driver_priv;
 
-	amdgpu_ctx_mgr_entity_fini(&fpriv->ctx_mgr);
+	amdgpu_ctx_mgr_entity_flush(&fpriv->ctx_mgr);
 
 	return 0;
 }
-- 
cgit v1.2.3


From d6258eaa41fc531277d44fbbee670c866025bfdc Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sun, 17 Jun 2018 10:53:38 +0200
Subject: drm/amd/display: don't initialize result

The wrong enum type is used to initialize the result, leading to a
warning when using clang:
drivers/gpu/drm/amd/amdgpu/../display/dc/core/dc_link_dp.c:1998:26: warning:
      implicit conversion from enumeration type 'enum ddc_result' to different
      enumeration type 'enum dc_status' [-Wenum-conversion]
        enum dc_status result = DDC_RESULT_UNKNOWN;
                       ~~~~~~   ^~~~~~~~~~~~~~~~~~
1 warning generated.

Initialization of result is unnecessary anyway, just drop the
initialization.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 049fc5cce1d2..84586b679d73 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2000,7 +2000,7 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 {
 	union hpd_irq_data hpd_irq_dpcd_data = {{{{0}}}};
 	union device_service_irq device_service_clear = { { 0 } };
-	enum dc_status result = DDC_RESULT_UNKNOWN;
+	enum dc_status result;
 	bool status = false;
 	/* For use cases related to down stream connection status change,
 	 * PSR and device auto test, refer to function handle_sst_hpd_irq
-- 
cgit v1.2.3


From cc450654291bb40c2d67a04d7e2fb42bff7e162a Mon Sep 17 00:00:00 2001
From: Flora Cui <Flora.Cui@amd.com>
Date: Wed, 27 Jun 2018 13:53:53 +0800
Subject: drm/amdgpu: remove duplicated codes

the fence_context and seqno is init in amdgpu_vm_manager_init() &
amdgpu_vmid_mgr_init(). remove the amdgpu_vmid_mgr_init() copy.

Signed-off-by: Flora Cui <Flora.Cui@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
index a1c78f90eadf..3a072a7a39f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
@@ -578,11 +578,6 @@ void amdgpu_vmid_mgr_init(struct amdgpu_device *adev)
 			list_add_tail(&id_mgr->ids[j].list, &id_mgr->ids_lru);
 		}
 	}
-
-	adev->vm_manager.fence_context =
-		dma_fence_context_alloc(AMDGPU_MAX_RINGS);
-	for (i = 0; i < AMDGPU_MAX_RINGS; ++i)
-		adev->vm_manager.seqno[i] = 0;
 }
 
 /**
-- 
cgit v1.2.3


From f0626896bb2f09e8ce6438f380ac7f6511b72f84 Mon Sep 17 00:00:00 2001
From: rex zhu <rex.zhu@amd.com>
Date: Wed, 27 Jun 2018 17:35:40 +0800
Subject: drm/amd/display: Drop unnecessary header file

powerplay implement hwmgr_function table for all supported asics in
order to conceal the asic's detail infomation. so no need to include
the smu10_hwmgr.h.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index ad96e2a2b3cf..2acbcc7a9412 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -34,7 +34,6 @@
 #include "amdgpu_pm.h"
 #include "dm_pp_smu.h"
 #include "../../powerplay/inc/hwmgr.h"
-#include "../../powerplay/hwmgr/smu10_hwmgr.h"
 
 
 bool dm_pp_apply_display_requirements(
-- 
cgit v1.2.3


From 66917e56dcfe8d2ba00f2d86c7dfbf953e0604ae Mon Sep 17 00:00:00 2001
From: rex zhu <rex.zhu@amd.com>
Date: Wed, 27 Jun 2018 17:34:37 +0800
Subject: drm/amd/display: Fix dm-pp clks type convert error

fix a typo when convert displayphyclk type.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 2acbcc7a9412..cf92d7a24f33 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -167,6 +167,9 @@ static enum amd_pp_clock_type dc_to_pp_clock_type(
 		amd_pp_clk_type = amd_pp_f_clock;
 		break;
 	case DM_PP_CLOCK_TYPE_DISPLAYPHYCLK:
+		amd_pp_clk_type = amd_pp_phy_clock;
+		break;
+	case DM_PP_CLOCK_TYPE_DPPCLK:
 		amd_pp_clk_type = amd_pp_dpp_clock;
 		break;
 	default:
-- 
cgit v1.2.3


From a8da8ff3332b1f92588d22a8a643965409d1892d Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Tue, 5 Jun 2018 10:07:53 +0800
Subject: drm/amdgpu: Rename set_mmhub_powergating_by_smu to powergate_mmhub

In order to keep consistent with powergate_uvd/vce.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h           | 4 ++--
 drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c           | 4 ++--
 drivers/gpu/drm/amd/include/kgd_pp_interface.h    | 2 +-
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c     | 8 ++++----
 drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c | 4 ++--
 drivers/gpu/drm/amd/powerplay/inc/hwmgr.h         | 2 +-
 6 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index 9acfbee91c40..c6d692625687 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -359,8 +359,8 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\
 			(adev)->powerplay.pp_handle, type, parameter, size))
 
-#define amdgpu_dpm_set_mmhub_powergating_by_smu(adev) \
-		((adev)->powerplay.pp_funcs->set_mmhub_powergating_by_smu( \
+#define amdgpu_dpm_powergate_mmhub(adev) \
+		((adev)->powerplay.pp_funcs->powergate_mmhub( \
 		(adev)->powerplay.pp_handle))
 
 struct amdgpu_dpm {
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 3d53c4413f13..377f5362a3df 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -471,8 +471,8 @@ void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
 						RENG_EXECUTE_ON_REG_UPDATE, 1);
 		WREG32_SOC15(MMHUB, 0, mmPCTL1_RENG_EXECUTE, pctl1_reng_execute);
 
-		if (adev->powerplay.pp_funcs->set_mmhub_powergating_by_smu)
-			amdgpu_dpm_set_mmhub_powergating_by_smu(adev);
+		if (adev->powerplay.pp_funcs->powergate_mmhub)
+			amdgpu_dpm_powergate_mmhub(adev);
 
 	} else {
 		pctl0_reng_execute = REG_SET_FIELD(pctl0_reng_execute,
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 06f08f34a110..0f9886298a84 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -269,7 +269,7 @@ struct amd_pm_funcs {
 	int (*get_power_profile_mode)(void *handle, char *buf);
 	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
 	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
-	int (*set_mmhub_powergating_by_smu)(void *handle);
+	int (*powergate_mmhub)(void *handle);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index d567be49c31b..da98208cd130 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -1168,19 +1168,19 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 	return ret;
 }
 
-static int pp_set_mmhub_powergating_by_smu(void *handle)
+static int pp_dpm_powergate_mmhub(void *handle)
 {
 	struct pp_hwmgr *hwmgr = handle;
 
 	if (!hwmgr || !hwmgr->pm_en)
 		return -EINVAL;
 
-	if (hwmgr->hwmgr_func->set_mmhub_powergating_by_smu == NULL) {
+	if (hwmgr->hwmgr_func->powergate_mmhub == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
 		return 0;
 	}
 
-	return hwmgr->hwmgr_func->set_mmhub_powergating_by_smu(hwmgr);
+	return hwmgr->hwmgr_func->powergate_mmhub(hwmgr);
 }
 
 static const struct amd_pm_funcs pp_dpm_funcs = {
@@ -1227,5 +1227,5 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_watermarks_for_clocks_ranges = pp_set_watermarks_for_clocks_ranges,
 	.display_clock_voltage_request = pp_display_clock_voltage_request,
 	.get_display_mode_validation_clocks = pp_get_display_mode_validation_clocks,
-	.set_mmhub_powergating_by_smu = pp_set_mmhub_powergating_by_smu,
+	.powergate_mmhub = pp_dpm_powergate_mmhub,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index d4bc83e81389..0f8352cf6567 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1126,7 +1126,7 @@ static int smu10_smus_notify_pwe(struct pp_hwmgr *hwmgr)
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_SetRccPfcPmeRestoreRegister);
 }
 
-static int smu10_set_mmhub_powergating_by_smu(struct pp_hwmgr *hwmgr)
+static int smu10_powergate_mmhub(struct pp_hwmgr *hwmgr)
 {
 	return smum_send_msg_to_smc(hwmgr, PPSMC_MSG_PowerGateMmHub);
 }
@@ -1182,7 +1182,7 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.asic_setup = smu10_setup_asic_task,
 	.power_state_set = smu10_set_power_state_tasks,
 	.dynamic_state_management_disable = smu10_disable_dpm_tasks,
-	.set_mmhub_powergating_by_smu = smu10_set_mmhub_powergating_by_smu,
+	.powergate_mmhub = smu10_powergate_mmhub,
 	.smus_notify_pwe = smu10_smus_notify_pwe,
 	.gfx_off_control = smu10_gfx_off_control,
 	.display_clock_voltage_request = smu10_display_clock_voltage_request,
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 40c98ca5feb7..9b07d6e14ec6 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -327,7 +327,7 @@ struct pp_hwmgr_func {
 					enum PP_OD_DPM_TABLE_COMMAND type,
 					long *input, uint32_t size);
 	int (*set_power_limit)(struct pp_hwmgr *hwmgr, uint32_t n);
-	int (*set_mmhub_powergating_by_smu)(struct pp_hwmgr *hwmgr);
+	int (*powergate_mmhub)(struct pp_hwmgr *hwmgr);
 	int (*smus_notify_pwe)(struct pp_hwmgr *hwmgr);
 };
 
-- 
cgit v1.2.3


From 3eb6e4795de3171d5c59f9368f48bb770087de77 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Tue, 5 Jun 2018 11:28:03 +0800
Subject: drm/amd/pp: Rename enable_per_cu_power_gating to powergate_gfx

keep consistent with powergate_uvd/vce/mmhub

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c               | 6 +++---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c | 2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h | 2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c            | 2 +-
 drivers/gpu/drm/amd/powerplay/inc/hwmgr.h                   | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index da98208cd130..b69da116b30c 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -236,13 +236,13 @@ static int pp_set_powergating_state(void *handle,
 			pr_err("gfx off control failed!\n");
 	}
 
-	if (hwmgr->hwmgr_func->enable_per_cu_power_gating == NULL) {
-		pr_debug("%s was not implemented.\n", __func__);
+	if (hwmgr->hwmgr_func->powergate_gfx == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
 		return 0;
 	}
 
 	/* Enable/disable GFX per cu powergating through SMU */
-	return hwmgr->hwmgr_func->enable_per_cu_power_gating(hwmgr,
+	return hwmgr->hwmgr_func->powergate_gfx(hwmgr,
 			state == AMD_PG_STATE_GATE);
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
index 41495621d94a..683b29a99366 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.c
@@ -416,7 +416,7 @@ int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
  * Powerplay will only control the static per CU Power Gating.
  * Dynamic per CU Power Gating will be done in gfx.
  */
-int smu7_enable_per_cu_power_gating(struct pp_hwmgr *hwmgr, bool enable)
+int smu7_powergate_gfx(struct pp_hwmgr *hwmgr, bool enable)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
index be7f66d2b234..fc8f8a6acc72 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_clockpowergating.h
@@ -33,6 +33,6 @@ int smu7_powergate_acp(struct pp_hwmgr *hwmgr, bool bgate);
 int smu7_disable_clock_power_gating(struct pp_hwmgr *hwmgr);
 int smu7_update_clock_gatings(struct pp_hwmgr *hwmgr,
 					const uint32_t *msg_id);
-int smu7_enable_per_cu_power_gating(struct pp_hwmgr *hwmgr, bool enable);
+int smu7_powergate_gfx(struct pp_hwmgr *hwmgr, bool enable);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index b89d6fb8559b..de295b7442b7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -5044,7 +5044,7 @@ static const struct pp_hwmgr_func smu7_hwmgr_funcs = {
 	.get_fan_control_mode = smu7_get_fan_control_mode,
 	.force_clock_level = smu7_force_clock_level,
 	.print_clock_levels = smu7_print_clock_levels,
-	.enable_per_cu_power_gating = smu7_enable_per_cu_power_gating,
+	.powergate_gfx = smu7_powergate_gfx,
 	.get_sclk_od = smu7_get_sclk_od,
 	.set_sclk_od = smu7_set_sclk_od,
 	.get_mclk_od = smu7_get_mclk_od,
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 9b07d6e14ec6..95e29a22e445 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -302,7 +302,7 @@ struct pp_hwmgr_func {
 	int (*power_off_asic)(struct pp_hwmgr *hwmgr);
 	int (*force_clock_level)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, uint32_t mask);
 	int (*print_clock_levels)(struct pp_hwmgr *hwmgr, enum pp_clock_type type, char *buf);
-	int (*enable_per_cu_power_gating)(struct pp_hwmgr *hwmgr, bool enable);
+	int (*powergate_gfx)(struct pp_hwmgr *hwmgr, bool enable);
 	int (*get_sclk_od)(struct pp_hwmgr *hwmgr);
 	int (*set_sclk_od)(struct pp_hwmgr *hwmgr, uint32_t value);
 	int (*get_mclk_od)(struct pp_hwmgr *hwmgr);
-- 
cgit v1.2.3


From b92c628712ed3a1cf5d4a144290e8ffc170bf51e Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Tue, 5 Jun 2018 13:06:11 +0800
Subject: drm/amd/pp: Unify powergate_uvd/vce/mmhub to set_powergating_by_smu

Some HW ip blocks need call SMU to enter/leave power gate state.
So export common set_powergating_by_smu interface.

1. keep consistent with set_clockgating_by_smu
2. scales easily to powergate other ip(gfx) if necessary

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h        | 14 ++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c         |  8 +++----
 drivers/gpu/drm/amd/amdgpu/ci_dpm.c            | 15 ++++++++++++-
 drivers/gpu/drm/amd/amdgpu/kv_dpm.c            | 15 ++++++++++++-
 drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c        |  4 ++--
 drivers/gpu/drm/amd/include/kgd_pp_interface.h |  5 ++---
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c  | 29 +++++++++++++++++++++++---
 7 files changed, 66 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
index c6d692625687..ff24e1cc5b65 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.h
@@ -287,12 +287,6 @@ enum amdgpu_pcie_gen {
 #define amdgpu_dpm_force_performance_level(adev, l) \
 		((adev)->powerplay.pp_funcs->force_performance_level((adev)->powerplay.pp_handle, (l)))
 
-#define amdgpu_dpm_powergate_uvd(adev, g) \
-		((adev)->powerplay.pp_funcs->powergate_uvd((adev)->powerplay.pp_handle, (g)))
-
-#define amdgpu_dpm_powergate_vce(adev, g) \
-		((adev)->powerplay.pp_funcs->powergate_vce((adev)->powerplay.pp_handle, (g)))
-
 #define amdgpu_dpm_get_current_power_state(adev) \
 		((adev)->powerplay.pp_funcs->get_current_power_state((adev)->powerplay.pp_handle))
 
@@ -347,6 +341,10 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->set_clockgating_by_smu(\
 			(adev)->powerplay.pp_handle, msg_id))
 
+#define amdgpu_dpm_set_powergating_by_smu(adev, block_type, gate) \
+		((adev)->powerplay.pp_funcs->set_powergating_by_smu(\
+			(adev)->powerplay.pp_handle, block_type, gate))
+
 #define amdgpu_dpm_get_power_profile_mode(adev, buf) \
 		((adev)->powerplay.pp_funcs->get_power_profile_mode(\
 			(adev)->powerplay.pp_handle, buf))
@@ -359,10 +357,6 @@ enum amdgpu_pcie_gen {
 		((adev)->powerplay.pp_funcs->odn_edit_dpm_table(\
 			(adev)->powerplay.pp_handle, type, parameter, size))
 
-#define amdgpu_dpm_powergate_mmhub(adev) \
-		((adev)->powerplay.pp_funcs->powergate_mmhub( \
-		(adev)->powerplay.pp_handle))
-
 struct amdgpu_dpm {
 	struct amdgpu_ps        *ps;
 	/* number of valid power states */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index fdb399821915..a003fd881a89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1729,10 +1729,10 @@ static void amdgpu_dpm_change_power_state_locked(struct amdgpu_device *adev)
 
 void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 {
-	if (adev->powerplay.pp_funcs->powergate_uvd) {
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
 		/* enable/disable UVD */
 		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_powergate_uvd(adev, !enable);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_UVD, !enable);
 		mutex_unlock(&adev->pm.mutex);
 	} else {
 		if (enable) {
@@ -1751,10 +1751,10 @@ void amdgpu_dpm_enable_uvd(struct amdgpu_device *adev, bool enable)
 
 void amdgpu_dpm_enable_vce(struct amdgpu_device *adev, bool enable)
 {
-	if (adev->powerplay.pp_funcs->powergate_vce) {
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu) {
 		/* enable/disable VCE */
 		mutex_lock(&adev->pm.mutex);
-		amdgpu_dpm_powergate_vce(adev, !enable);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_VCE, !enable);
 		mutex_unlock(&adev->pm.mutex);
 	} else {
 		if (enable) {
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index c9d45cffca56..7c4ff71e7476 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -6767,6 +6767,19 @@ static int ci_dpm_read_sensor(void *handle, int idx,
 	}
 }
 
+static int ci_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+		ci_dpm_powergate_uvd(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 static const struct amd_ip_funcs ci_dpm_ip_funcs = {
 	.name = "ci_dpm",
 	.early_init = ci_dpm_early_init,
@@ -6804,7 +6817,7 @@ static const struct amd_pm_funcs ci_dpm_funcs = {
 	.debugfs_print_current_performance_level = &ci_dpm_debugfs_print_current_performance_level,
 	.force_performance_level = &ci_dpm_force_performance_level,
 	.vblank_too_short = &ci_dpm_vblank_too_short,
-	.powergate_uvd = &ci_dpm_powergate_uvd,
+	.set_powergating_by_smu = &ci_set_powergating_by_smu,
 	.set_fan_control_mode = &ci_dpm_set_fan_control_mode,
 	.get_fan_control_mode = &ci_dpm_get_fan_control_mode,
 	.set_fan_speed_percent = &ci_dpm_set_fan_speed_percent,
diff --git a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
index 46de1fd18a7b..3f57f6463dc8 100644
--- a/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/kv_dpm.c
@@ -3306,6 +3306,19 @@ static int kv_dpm_read_sensor(void *handle, int idx,
 	}
 }
 
+static int kv_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+		kv_dpm_powergate_uvd(handle, gate);
+		break;
+	default:
+		break;
+	}
+	return 0;
+}
+
 static const struct amd_ip_funcs kv_dpm_ip_funcs = {
 	.name = "kv_dpm",
 	.early_init = kv_dpm_early_init,
@@ -3342,7 +3355,7 @@ static const struct amd_pm_funcs kv_dpm_funcs = {
 	.print_power_state = &kv_dpm_print_power_state,
 	.debugfs_print_current_performance_level = &kv_dpm_debugfs_print_current_performance_level,
 	.force_performance_level = &kv_dpm_force_performance_level,
-	.powergate_uvd = &kv_dpm_powergate_uvd,
+	.set_powergating_by_smu = kv_set_powergating_by_smu,
 	.enable_bapm = &kv_dpm_enable_bapm,
 	.get_vce_clock_state = amdgpu_get_vce_clock_state,
 	.check_state_equal = kv_check_state_equal,
diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
index 377f5362a3df..e70a0d4d6db4 100644
--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_0.c
@@ -471,8 +471,8 @@ void mmhub_v1_0_update_power_gating(struct amdgpu_device *adev,
 						RENG_EXECUTE_ON_REG_UPDATE, 1);
 		WREG32_SOC15(MMHUB, 0, mmPCTL1_RENG_EXECUTE, pctl1_reng_execute);
 
-		if (adev->powerplay.pp_funcs->powergate_mmhub)
-			amdgpu_dpm_powergate_mmhub(adev);
+		if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GMC, true);
 
 	} else {
 		pctl0_reng_execute = REG_SET_FIELD(pctl0_reng_execute,
diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 0f9886298a84..4535756428f9 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -232,13 +232,13 @@ struct amd_pm_funcs {
 	void (*debugfs_print_current_performance_level)(void *handle, struct seq_file *m);
 	int (*switch_power_profile)(void *handle, enum PP_SMC_POWER_PROFILE type, bool en);
 /* export to amdgpu */
-	void (*powergate_uvd)(void *handle, bool gate);
-	void (*powergate_vce)(void *handle, bool gate);
 	struct amd_vce_state *(*get_vce_clock_state)(void *handle, u32 idx);
 	int (*dispatch_tasks)(void *handle, enum amd_pp_task task_id,
 			enum amd_pm_state_type *user_state);
 	int (*load_firmware)(void *handle);
 	int (*wait_for_fw_loading_complete)(void *handle);
+	int (*set_powergating_by_smu)(void *handle,
+				uint32_t block_type, bool gate);
 	int (*set_clockgating_by_smu)(void *handle, uint32_t msg_id);
 	int (*set_power_limit)(void *handle, uint32_t n);
 	int (*get_power_limit)(void *handle, uint32_t *limit, bool default_limit);
@@ -269,7 +269,6 @@ struct amd_pm_funcs {
 	int (*get_power_profile_mode)(void *handle, char *buf);
 	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
 	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
-	int (*powergate_mmhub)(void *handle);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index b69da116b30c..f68551ffb1e2 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -244,6 +244,7 @@ static int pp_set_powergating_state(void *handle,
 	/* Enable/disable GFX per cu powergating through SMU */
 	return hwmgr->hwmgr_func->powergate_gfx(hwmgr,
 			state == AMD_PG_STATE_GATE);
+
 }
 
 static int pp_suspend(void *handle)
@@ -1183,14 +1184,36 @@ static int pp_dpm_powergate_mmhub(void *handle)
 	return hwmgr->hwmgr_func->powergate_mmhub(hwmgr);
 }
 
+static int pp_set_powergating_by_smu(void *handle,
+				uint32_t block_type, bool gate)
+{
+	int ret = 0;
+
+	switch (block_type) {
+	case AMD_IP_BLOCK_TYPE_UVD:
+	case AMD_IP_BLOCK_TYPE_VCN:
+		pp_dpm_powergate_uvd(handle, gate);
+		break;
+	case AMD_IP_BLOCK_TYPE_VCE:
+		pp_dpm_powergate_vce(handle, gate);
+		break;
+	case AMD_IP_BLOCK_TYPE_GMC:
+		pp_dpm_powergate_mmhub(handle);
+		break;
+	case AMD_IP_BLOCK_TYPE_GFX:
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
 static const struct amd_pm_funcs pp_dpm_funcs = {
 	.load_firmware = pp_dpm_load_fw,
 	.wait_for_fw_loading_complete = pp_dpm_fw_loading_complete,
 	.force_performance_level = pp_dpm_force_performance_level,
 	.get_performance_level = pp_dpm_get_performance_level,
 	.get_current_power_state = pp_dpm_get_current_power_state,
-	.powergate_vce = pp_dpm_powergate_vce,
-	.powergate_uvd = pp_dpm_powergate_uvd,
 	.dispatch_tasks = pp_dpm_dispatch_tasks,
 	.set_fan_control_mode = pp_dpm_set_fan_control_mode,
 	.get_fan_control_mode = pp_dpm_get_fan_control_mode,
@@ -1210,6 +1233,7 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.get_vce_clock_state = pp_dpm_get_vce_clock_state,
 	.switch_power_profile = pp_dpm_switch_power_profile,
 	.set_clockgating_by_smu = pp_set_clockgating_by_smu,
+	.set_powergating_by_smu = pp_set_powergating_by_smu,
 	.get_power_profile_mode = pp_get_power_profile_mode,
 	.set_power_profile_mode = pp_set_power_profile_mode,
 	.odn_edit_dpm_table = pp_odn_edit_dpm_table,
@@ -1227,5 +1251,4 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_watermarks_for_clocks_ranges = pp_set_watermarks_for_clocks_ranges,
 	.display_clock_voltage_request = pp_display_clock_voltage_request,
 	.get_display_mode_validation_clocks = pp_get_display_mode_validation_clocks,
-	.powergate_mmhub = pp_dpm_powergate_mmhub,
 };
-- 
cgit v1.2.3


From 85f80cb3af10f5daf79eee28300c3bbc55a70666 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Thu, 14 Jun 2018 13:07:19 +0800
Subject: drm/amd/pp: Add gfx pg support in smu through set_powergating_by_smu

gfx ip block can call set_powergating_by_smu to set gfx pg state if
necessary.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c         | 10 ++++------
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 25 +++++++++++++++++--------
 2 files changed, 21 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 4201f3dfaece..e69fbc944956 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5606,14 +5606,12 @@ static int gfx_v8_0_late_init(void *handle)
 static void gfx_v8_0_enable_gfx_static_mg_power_gating(struct amdgpu_device *adev,
 						       bool enable)
 {
-	if ((adev->asic_type == CHIP_POLARIS11) ||
+	if (((adev->asic_type == CHIP_POLARIS11) ||
 	    (adev->asic_type == CHIP_POLARIS12) ||
-	    (adev->asic_type == CHIP_VEGAM))
+	    (adev->asic_type == CHIP_VEGAM)) &&
+	    adev->powerplay.pp_funcs->set_powergating_by_smu)
 		/* Send msg to SMU via Powerplay */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       enable ?
-						       AMD_PG_STATE_GATE : AMD_PG_STATE_UNGATE);
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, enable);
 
 	WREG32_FIELD(RLC_PG_CNTL, STATIC_PER_CU_PG_ENABLE, enable ? 1 : 0);
 }
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index f68551ffb1e2..ef4884b0ddff 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -236,14 +236,7 @@ static int pp_set_powergating_state(void *handle,
 			pr_err("gfx off control failed!\n");
 	}
 
-	if (hwmgr->hwmgr_func->powergate_gfx == NULL) {
-		pr_info("%s was not implemented.\n", __func__);
-		return 0;
-	}
-
-	/* Enable/disable GFX per cu powergating through SMU */
-	return hwmgr->hwmgr_func->powergate_gfx(hwmgr,
-			state == AMD_PG_STATE_GATE);
+	return 0;
 
 }
 
@@ -1184,6 +1177,21 @@ static int pp_dpm_powergate_mmhub(void *handle)
 	return hwmgr->hwmgr_func->powergate_mmhub(hwmgr);
 }
 
+static int pp_dpm_powergate_gfx(void *handle, bool gate)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return 0;
+
+	if (hwmgr->hwmgr_func->powergate_gfx == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return 0;
+	}
+
+	return hwmgr->hwmgr_func->powergate_gfx(hwmgr, gate);
+}
+
 static int pp_set_powergating_by_smu(void *handle,
 				uint32_t block_type, bool gate)
 {
@@ -1201,6 +1209,7 @@ static int pp_set_powergating_by_smu(void *handle,
 		pp_dpm_powergate_mmhub(handle);
 		break;
 	case AMD_IP_BLOCK_TYPE_GFX:
+		ret = pp_dpm_powergate_gfx(handle, gate);
 		break;
 	default:
 		break;
-- 
cgit v1.2.3


From a214e1c415e70f5cbc7835180cb9ed5c8e4aa35e Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Tue, 5 Jun 2018 13:55:04 +0800
Subject: drm/amd/pp: Add powergate_gfx backend function on Raven

Raven support gfx off feature instand of gfx powergate,
so use smu10_gfx_off_control as the powergate_gfx backend function.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 0f8352cf6567..0bbf11d464dd 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1186,6 +1186,7 @@ static const struct pp_hwmgr_func smu10_hwmgr_funcs = {
 	.smus_notify_pwe = smu10_smus_notify_pwe,
 	.gfx_off_control = smu10_gfx_off_control,
 	.display_clock_voltage_request = smu10_display_clock_voltage_request,
+	.powergate_gfx = smu10_gfx_off_control,
 };
 
 int smu10_init_function_pointers(struct pp_hwmgr *hwmgr)
-- 
cgit v1.2.3


From 9134c6d7f288f902d932e7cf57fab2f49e8ad70b Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Tue, 5 Jun 2018 11:46:35 +0800
Subject: drm/amdgpu: Add gfx_off support in smu through
 pp_set_powergating_by_smu

we can take gfx off feature as gfx power gate. gfx off feature is also
controled by smu. so add gfx_off support in pp_set_powergating_by_smu.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c    | 19 +++++++------------
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c         |  4 ++++
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 16 ----------------
 3 files changed, 11 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d82d0d314285..c33a41ace028 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1730,16 +1730,11 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 		}
 	}
 
-	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK) {
+	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
 		/* enable gfx powergating */
 		amdgpu_device_ip_set_powergating_state(adev,
 						       AMD_IP_BLOCK_TYPE_GFX,
 						       AMD_PG_STATE_GATE);
-		/* enable gfxoff */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       AMD_PG_STATE_GATE);
-	}
 
 	return 0;
 }
@@ -1812,6 +1807,8 @@ static int amdgpu_device_ip_fini(struct amdgpu_device *adev)
 					  adev->ip_blocks[i].version->funcs->name, r);
 				return r;
 			}
+			if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+				amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false);
 			r = adev->ip_blocks[i].version->funcs->hw_fini((void *)adev);
 			/* XXX handle errors */
 			if (r) {
@@ -1921,12 +1918,6 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		amdgpu_virt_request_full_gpu(adev, false);
 
-	/* ungate SMC block powergating */
-	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_SMC,
-						       AMD_PG_STATE_UNGATE);
-
 	/* ungate SMC block first */
 	r = amdgpu_device_ip_set_clockgating_state(adev, AMD_IP_BLOCK_TYPE_SMC,
 						   AMD_CG_STATE_UNGATE);
@@ -1934,6 +1925,10 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 		DRM_ERROR("set_clockgating_state(ungate) SMC failed %d\n", r);
 	}
 
+	/* call smu to disable gfx off feature first when suspend */
+	if (adev->powerplay.pp_funcs->set_powergating_by_smu)
+		amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, false);
+
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index a69153435ea7..ac46eabe3bcd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3714,6 +3714,10 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 
 		/* update mgcg state */
 		gfx_v9_0_update_gfx_mg_power_gating(adev, enable);
+
+		/* set gfx off through smu */
+		if (enable && adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true);
 		break;
 	default:
 		break;
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index ef4884b0ddff..387a1eb6678d 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -221,23 +221,7 @@ static int pp_sw_reset(void *handle)
 static int pp_set_powergating_state(void *handle,
 				    enum amd_powergating_state state)
 {
-	struct amdgpu_device *adev = handle;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret;
-
-	if (!hwmgr || !hwmgr->pm_en)
-		return 0;
-
-	if (hwmgr->hwmgr_func->gfx_off_control) {
-		/* Enable/disable GFX off through SMU */
-		ret = hwmgr->hwmgr_func->gfx_off_control(hwmgr,
-							 state == AMD_PG_STATE_GATE);
-		if (ret)
-			pr_err("gfx off control failed!\n");
-	}
-
 	return 0;
-
 }
 
 static int pp_suspend(void *handle)
-- 
cgit v1.2.3


From c9f96fd5063150dce7e71ecc508989f5ff055039 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Wed, 13 Jun 2018 19:30:40 +0800
Subject: drm/amdgpu: Split set_pg_state into separate function

1. add amdgpu_device_ip_late_set_pg_state function for
   set pg state.
2. delete duplicate pg state setting on gfx_v8_0's late_init.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 33 +++++++++++++++++++++++++-----
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c      |  4 ----
 2 files changed, 28 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c33a41ace028..e38564e7c5ec 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1730,12 +1730,34 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 		}
 	}
 
-	if (adev->powerplay.pp_feature & PP_GFXOFF_MASK)
-		/* enable gfx powergating */
-		amdgpu_device_ip_set_powergating_state(adev,
-						       AMD_IP_BLOCK_TYPE_GFX,
-						       AMD_PG_STATE_GATE);
+	return 0;
+}
+
+static int amdgpu_device_ip_late_set_pg_state(struct amdgpu_device *adev)
+{
+	int i = 0, r;
 
+	if (amdgpu_emu_mode == 1)
+		return 0;
+
+	for (i = 0; i < adev->num_ip_blocks; i++) {
+		if (!adev->ip_blocks[i].status.valid)
+			continue;
+		/* skip CG for VCE/UVD, it's handled specially */
+		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_UVD &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCE &&
+		    adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_VCN &&
+		    adev->ip_blocks[i].version->funcs->set_powergating_state) {
+			/* enable powergating to save power */
+			r = adev->ip_blocks[i].version->funcs->set_powergating_state((void *)adev,
+										     AMD_PG_STATE_GATE);
+			if (r) {
+				DRM_ERROR("set_powergating_state(gate) of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+				return r;
+			}
+		}
+	}
 	return 0;
 }
 
@@ -1898,6 +1920,7 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, late_init_work.work);
 	amdgpu_device_ip_late_set_cg_state(adev);
+	amdgpu_device_ip_late_set_pg_state(adev);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index e69fbc944956..551f21bad6d3 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -5596,10 +5596,6 @@ static int gfx_v8_0_late_init(void *handle)
 		return r;
 	}
 
-	amdgpu_device_ip_set_powergating_state(adev,
-					       AMD_IP_BLOCK_TYPE_GFX,
-					       AMD_PG_STATE_GATE);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 916ac57ffbe952c02fcd883dee28970e39366eca Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Wed, 6 Jun 2018 13:42:42 +0800
Subject: drm/amdgpu: Move CG/PG setting out of delay worker thread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Partially revert commit 2dc80b00652f
("drm/amdgpu: optimize amdgpu driver load & resume time")'

1. CG/PG enablement are part of gpu hw ip initialize, we should
wait for them complete. otherwise, there are some potential conflicts,
for example, Suspend and CG enablement concurrently.
2. better run ib test after hw initialize completely. That is to say,
   ib test should be after CG/PG enablement. otherwise, the test will
   not cover the cg/pg/poweroff enable case.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e38564e7c5ec..c35db859f050 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1707,10 +1707,6 @@ static int amdgpu_device_ip_late_set_cg_state(struct amdgpu_device *adev)
 	if (amdgpu_emu_mode == 1)
 		return 0;
 
-	r = amdgpu_ib_ring_tests(adev);
-	if (r)
-		DRM_ERROR("ib ring test failed (%d).\n", r);
-
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
@@ -1791,6 +1787,9 @@ static int amdgpu_device_ip_late_init(struct amdgpu_device *adev)
 		}
 	}
 
+	amdgpu_device_ip_late_set_cg_state(adev);
+	amdgpu_device_ip_late_set_pg_state(adev);
+
 	queue_delayed_work(system_wq, &adev->late_init_work,
 			   msecs_to_jiffies(AMDGPU_RESUME_MS));
 
@@ -1919,8 +1918,11 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 {
 	struct amdgpu_device *adev =
 		container_of(work, struct amdgpu_device, late_init_work.work);
-	amdgpu_device_ip_late_set_cg_state(adev);
-	amdgpu_device_ip_late_set_pg_state(adev);
+	int r;
+
+	r = amdgpu_ib_ring_tests(adev);
+	if (r)
+		DRM_ERROR("ib ring test failed (%d).\n", r);
 }
 
 /**
-- 
cgit v1.2.3


From 22994e16dd025aefd7f97a863f13ae23d8853601 Mon Sep 17 00:00:00 2001
From: rex zhu <rex.zhu@amd.com>
Date: Wed, 27 Jun 2018 18:08:43 +0800
Subject: drm/amdgpu: Add stutter mode ctrl in module parameter

Enable stutter mode can save power in low DRAM use cases
including but not limited to productivity application use,
web browsing, and video playback.

Currently this feature is disabled by default.

Make bit 17 in module parameter amdgpu_pp_feature_mask
as stutter mode mask, so user can enable/disable this feature easily.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c  | 3 ++-
 drivers/gpu/drm/amd/include/amd_shared.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 684149741427..dcdc97d6dc44 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -122,7 +122,8 @@ uint amdgpu_pg_mask = 0xffffffff;
 uint amdgpu_sdma_phase_quantum = 32;
 char *amdgpu_disable_cu = NULL;
 char *amdgpu_virtual_display = NULL;
-uint amdgpu_pp_feature_mask = 0xffff3fff; /* gfxoff (bit 15) disabled by default */
+/* OverDrive(bit 14),gfxoff(bit 15),stutter mode(bit 17) disabled by default*/
+uint amdgpu_pp_feature_mask = 0xfffd3fff;
 int amdgpu_ngg = 0;
 int amdgpu_prim_buf_per_se = 0;
 int amdgpu_pos_buf_per_se = 0;
diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index b178176b72ac..d6f487497397 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -128,6 +128,7 @@ enum PP_FEATURE_MASK {
 	PP_OVERDRIVE_MASK = 0x4000,
 	PP_GFXOFF_MASK = 0x8000,
 	PP_ACG_MASK = 0x10000,
+	PP_STUTTER_MODE = 0x20000,
 };
 
 struct amd_ip_funcs {
-- 
cgit v1.2.3


From e856ec3c292ecd6c15e38f2c6c22b350dc0daa17 Mon Sep 17 00:00:00 2001
From: rex zhu <rex.zhu@amd.com>
Date: Wed, 27 Jun 2018 18:19:08 +0800
Subject: drm/amd/display: Ctrl stutter mode through module parameter

use ppfeaturemask to enable/disable stutter mode.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 356ac27d0180..74683071fa81 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1535,7 +1535,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		/*
 		 * Temporary disable until pplib/smu interaction is implemented
 		 */
-		dm->dc->debug.disable_stutter = true;
+		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
 		break;
 #endif
 	default:
-- 
cgit v1.2.3


From b1c6fddb583f70892f2dd6de8c63af3aa4600a7b Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Wed, 20 Jun 2018 12:52:43 +0800
Subject: drm/amd/display: Fix a typo in wm_min_memg_clk_in_khz

change wm_min_memg_clk_in_khz -> wm_min_mem_clk_in_khz

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c | 8 ++++----
 drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c | 8 ++++----
 drivers/gpu/drm/amd/display/dc/dm_services_types.h      | 6 +++---
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 752910035e81..9e1afb11e6ad 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -1000,7 +1000,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[0].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[0].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -1010,7 +1010,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[1].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[1].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[1].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[1].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -1020,7 +1020,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[2].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[2].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[2].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[2].wm_max_mem_clk_in_khz = 5000000;
@@ -1030,7 +1030,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[3].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[3].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_mem_clk_in_khz = 5000000;
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 13c388a608c4..8381f27a2361 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -775,7 +775,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[0].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[0].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[0].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -785,7 +785,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[1].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[1].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[1].wm_min_mem_clk_in_khz =
 			mem_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[1].wm_max_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz - 1;
@@ -795,7 +795,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[0].clocks_in_khz;
 	clk_ranges.wm_clk_ranges[2].wm_max_eng_clk_in_khz =
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz - 1;
-	clk_ranges.wm_clk_ranges[2].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[2].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[2].wm_max_mem_clk_in_khz = 5000000;
@@ -805,7 +805,7 @@ static void bw_calcs_data_update_from_pplib(struct dc *dc)
 			eng_clks.data[eng_clks.num_levels*3/8].clocks_in_khz;
 	/* 5 GHz instead of data[7].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_eng_clk_in_khz = 5000000;
-	clk_ranges.wm_clk_ranges[3].wm_min_memg_clk_in_khz =
+	clk_ranges.wm_clk_ranges[3].wm_min_mem_clk_in_khz =
 			mem_clks.data[mem_clks.num_levels>>1].clocks_in_khz;
 	/* 5 GHz instead of data[2].clockInKHz to cover Overdrive */
 	clk_ranges.wm_clk_ranges[3].wm_max_mem_clk_in_khz = 5000000;
diff --git a/drivers/gpu/drm/amd/display/dc/dm_services_types.h b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
index ab8c77d4e6df..2b83f922ac02 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_services_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_services_types.h
@@ -137,7 +137,7 @@ struct dm_pp_clock_range_for_wm_set {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_eng_clk_in_khz;
 	uint32_t wm_max_eng_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
@@ -150,7 +150,7 @@ struct dm_pp_clock_range_for_dmif_wm_set_soc15 {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_dcfclk_clk_in_khz;
 	uint32_t wm_max_dcfclk_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
@@ -158,7 +158,7 @@ struct dm_pp_clock_range_for_mcif_wm_set_soc15 {
 	enum dm_pp_wm_set_id wm_set_id;
 	uint32_t wm_min_socclk_clk_in_khz;
 	uint32_t wm_max_socclk_clk_in_khz;
-	uint32_t wm_min_memg_clk_in_khz;
+	uint32_t wm_min_mem_clk_in_khz;
 	uint32_t wm_max_mem_clk_in_khz;
 };
 
-- 
cgit v1.2.3


From acee16f4deab484b9b78876b8b292174e95ccf88 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 28 May 2018 08:59:16 +0800
Subject: drm/amd/powerplay: correct vega12 bootup values settings

The vbios firmware structure changed between v3_1 and v3_2. So,
the code to setup bootup values needs different paths based
on header version.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c | 94 +++++++++++++++++++---
 drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h |  3 +
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c |  3 +
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h |  3 +
 4 files changed, 91 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
index 5325661fedff..aa2faffef034 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
@@ -512,14 +512,82 @@ int pp_atomfwctrl_get_clk_information_by_clkid(struct pp_hwmgr *hwmgr, BIOS_CLKI
 	return 0;
 }
 
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_2(struct pp_hwmgr *hwmgr,
+			struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+			struct atom_firmware_info_v3_2 *fw_info)
+{
+	uint32_t frequency = 0;
+
+	boot_values->ulRevision = fw_info->firmware_revision;
+	boot_values->ulGfxClk   = fw_info->bootup_sclk_in10khz;
+	boot_values->ulUClk     = fw_info->bootup_mclk_in10khz;
+	boot_values->usVddc     = fw_info->bootup_vddc_mv;
+	boot_values->usVddci    = fw_info->bootup_vddci_mv;
+	boot_values->usMvddc    = fw_info->bootup_mvddc_mv;
+	boot_values->usVddGfx   = fw_info->bootup_vddgfx_mv;
+	boot_values->ucCoolingID = fw_info->coolingsolution_id;
+	boot_values->ulSocClk   = 0;
+	boot_values->ulDCEFClk   = 0;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_SOCCLK_ID, &frequency))
+		boot_values->ulSocClk   = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCEFCLK_ID, &frequency))
+		boot_values->ulDCEFClk  = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_ECLK_ID, &frequency))
+		boot_values->ulEClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_VCLK_ID, &frequency))
+		boot_values->ulVClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU11_SYSPLL0_DCLK_ID, &frequency))
+		boot_values->ulDClk     = frequency;
+}
+
+static void pp_atomfwctrl_copy_vbios_bootup_values_3_1(struct pp_hwmgr *hwmgr,
+			struct pp_atomfwctrl_bios_boot_up_values *boot_values,
+			struct atom_firmware_info_v3_1 *fw_info)
+{
+	uint32_t frequency = 0;
+
+	boot_values->ulRevision = fw_info->firmware_revision;
+	boot_values->ulGfxClk   = fw_info->bootup_sclk_in10khz;
+	boot_values->ulUClk     = fw_info->bootup_mclk_in10khz;
+	boot_values->usVddc     = fw_info->bootup_vddc_mv;
+	boot_values->usVddci    = fw_info->bootup_vddci_mv;
+	boot_values->usMvddc    = fw_info->bootup_mvddc_mv;
+	boot_values->usVddGfx   = fw_info->bootup_vddgfx_mv;
+	boot_values->ucCoolingID = fw_info->coolingsolution_id;
+	boot_values->ulSocClk   = 0;
+	boot_values->ulDCEFClk   = 0;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_SOCCLK_ID, &frequency))
+		boot_values->ulSocClk   = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCEFCLK_ID, &frequency))
+		boot_values->ulDCEFClk  = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_ECLK_ID, &frequency))
+		boot_values->ulEClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_VCLK_ID, &frequency))
+		boot_values->ulVClk     = frequency;
+
+	if (!pp_atomfwctrl_get_clk_information_by_clkid(hwmgr, SMU9_SYSPLL0_DCLK_ID, &frequency))
+		boot_values->ulDClk     = frequency;
+}
+
 int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 			struct pp_atomfwctrl_bios_boot_up_values *boot_values)
 {
-	struct atom_firmware_info_v3_1 *info = NULL;
+	struct atom_firmware_info_v3_2 *fwinfo_3_2;
+	struct atom_firmware_info_v3_1 *fwinfo_3_1;
+	struct atom_common_table_header *info = NULL;
 	uint16_t ix;
 
 	ix = GetIndexIntoMasterDataTable(firmwareinfo);
-	info = (struct atom_firmware_info_v3_1 *)
+	info = (struct atom_common_table_header *)
 		smu_atom_get_data_table(hwmgr->adev,
 				ix, NULL, NULL, NULL);
 
@@ -528,16 +596,18 @@ int pp_atomfwctrl_get_vbios_bootup_values(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 	}
 
-	boot_values->ulRevision = info->firmware_revision;
-	boot_values->ulGfxClk   = info->bootup_sclk_in10khz;
-	boot_values->ulUClk     = info->bootup_mclk_in10khz;
-	boot_values->usVddc     = info->bootup_vddc_mv;
-	boot_values->usVddci    = info->bootup_vddci_mv;
-	boot_values->usMvddc    = info->bootup_mvddc_mv;
-	boot_values->usVddGfx   = info->bootup_vddgfx_mv;
-	boot_values->ucCoolingID = info->coolingsolution_id;
-	boot_values->ulSocClk   = 0;
-	boot_values->ulDCEFClk   = 0;
+	if ((info->format_revision == 3) && (info->content_revision == 2)) {
+		fwinfo_3_2 = (struct atom_firmware_info_v3_2 *)info;
+		pp_atomfwctrl_copy_vbios_bootup_values_3_2(hwmgr,
+				boot_values, fwinfo_3_2);
+	} else if ((info->format_revision == 3) && (info->content_revision == 1)) {
+		fwinfo_3_1 = (struct atom_firmware_info_v3_1 *)info;
+		pp_atomfwctrl_copy_vbios_bootup_values_3_1(hwmgr,
+				boot_values, fwinfo_3_1);
+	} else {
+		pr_info("Fw info table revision does not match!");
+		return -EINVAL;
+	}
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
index fe10aa4db5e6..745bd3809549 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
@@ -136,6 +136,9 @@ struct pp_atomfwctrl_bios_boot_up_values {
 	uint32_t   ulUClk;
 	uint32_t   ulSocClk;
 	uint32_t   ulDCEFClk;
+	uint32_t   ulEClk;
+	uint32_t   ulVClk;
+	uint32_t   ulDClk;
 	uint16_t   usVddc;
 	uint16_t   usVddci;
 	uint16_t   usMvddc;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 782e2098824d..e81661cc9bae 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -803,6 +803,9 @@ static int vega12_init_smc_table(struct pp_hwmgr *hwmgr)
 		data->vbios_boot_state.soc_clock = boot_up_values.ulSocClk;
 		data->vbios_boot_state.dcef_clock = boot_up_values.ulDCEFClk;
 		data->vbios_boot_state.uc_cooling_id = boot_up_values.ucCoolingID;
+		data->vbios_boot_state.eclock = boot_up_values.ulEClk;
+		data->vbios_boot_state.dclock = boot_up_values.ulDClk;
+		data->vbios_boot_state.vclock = boot_up_values.ulVClk;
 		smum_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetMinDeepSleepDcefclk,
 			(uint32_t)(data->vbios_boot_state.dcef_clock / 100));
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index e81ded1ec198..49b38df8c7f2 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -167,6 +167,9 @@ struct vega12_vbios_boot_state {
 	uint32_t    mem_clock;
 	uint32_t    soc_clock;
 	uint32_t    dcef_clock;
+	uint32_t    eclock;
+	uint32_t    dclock;
+	uint32_t    vclock;
 };
 
 #define DPMTABLE_OD_UPDATE_SCLK     0x00000001
-- 
cgit v1.2.3


From 77564c9dff26f2a90d089dfb282906ec7be7c144 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 15:20:39 +0800
Subject: drm/amd/powerplay: smc_dpm_info structure change

A new member Vr2_I2C_address is added.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/atomfirmware.h                   | 5 ++++-
 drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c           | 2 ++
 drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h           | 2 ++
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c | 2 ++
 drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h    | 5 ++++-
 5 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 092d800b703a..33b4de4ad66e 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -1433,7 +1433,10 @@ struct atom_smc_dpm_info_v4_1
 	uint8_t  acggfxclkspreadpercent;
 	uint16_t acggfxclkspreadfreq;
 
-	uint32_t boardreserved[10];
+	uint8_t Vr2_I2C_address;
+	uint8_t padding_vr2[3];
+
+	uint32_t boardreserved[9];
 };
 
 /* 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
index aa2faffef034..d27c1c9df286 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.c
@@ -699,5 +699,7 @@ int pp_atomfwctrl_get_smc_dpm_information(struct pp_hwmgr *hwmgr,
 	param->acggfxclkspreadpercent = info->acggfxclkspreadpercent;
 	param->acggfxclkspreadfreq = info->acggfxclkspreadfreq;
 
+	param->Vr2_I2C_address = info->Vr2_I2C_address;
+
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
index 745bd3809549..22e21668c93a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomfwctrl.h
@@ -210,6 +210,8 @@ struct pp_atomfwctrl_smc_dpm_parameters
 	uint8_t  acggfxclkspreadenabled;
 	uint8_t  acggfxclkspreadpercent;
 	uint16_t acggfxclkspreadfreq;
+
+	uint8_t Vr2_I2C_address;
 };
 
 int pp_atomfwctrl_get_gpu_pll_dividers_vega10(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
index 888ddca902d8..29914700ee82 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
@@ -230,6 +230,8 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable
 		ppsmc_pptable->AcgThresholdFreqLow = 0xFFFF;
 	}
 
+	ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
index 2f8a3b983cce..b08526fd1619 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
@@ -499,7 +499,10 @@ typedef struct {
 	uint8_t      AcgGfxclkSpreadPercent;
 	uint16_t     AcgGfxclkSpreadFreq;
 
-	uint32_t     BoardReserved[10];
+  uint8_t      Vr2_I2C_address;
+  uint8_t      padding_vr2[3];
+
+  uint32_t     BoardReserved[9];
 
 
   uint32_t     MmHubPadding[7];
-- 
cgit v1.2.3


From 9bf40d787924f45d6a0fa49d3e69d772c2aa5b19 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 17:38:54 +0800
Subject: drm/amd/powerplay: drop the acg fix

This workaround is not needed any more.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
index 29914700ee82..f4f366b26fd1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_processpptables.c
@@ -224,12 +224,6 @@ static int append_vbios_pptable(struct pp_hwmgr *hwmgr, PPTable_t *ppsmc_pptable
 	ppsmc_pptable->AcgGfxclkSpreadPercent = smc_dpm_table.acggfxclkspreadpercent;
 	ppsmc_pptable->AcgGfxclkSpreadFreq = smc_dpm_table.acggfxclkspreadfreq;
 
-	/* 0xFFFF will disable the ACG feature */
-	if (!(hwmgr->feature_mask & PP_ACG_MASK)) {
-		ppsmc_pptable->AcgThresholdFreqHigh = 0xFFFF;
-		ppsmc_pptable->AcgThresholdFreqLow = 0xFFFF;
-	}
-
 	ppsmc_pptable->Vr2_I2C_address = smc_dpm_table.Vr2_I2C_address;
 
 	return 0;
-- 
cgit v1.2.3


From 3b579c5483286fba6e13bc4b2f1d8a6627410371 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 15:25:37 +0800
Subject: drm/amd/powerplay: revise default dpm tables setup

Initialize the soft/hard min/max level correctly and
handle the dpm disabled situation.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 334 ++++++++-------------
 1 file changed, 132 insertions(+), 202 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index e81661cc9bae..bc976e1d22c5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -453,37 +453,30 @@ static int vega12_setup_asic_task(struct pp_hwmgr *hwmgr)
  */
 static void vega12_init_dpm_state(struct vega12_dpm_state *dpm_state)
 {
-	dpm_state->soft_min_level = 0xff;
-	dpm_state->soft_max_level = 0xff;
-	dpm_state->hard_min_level = 0xff;
-	dpm_state->hard_max_level = 0xff;
+	dpm_state->soft_min_level = 0x0;
+	dpm_state->soft_max_level = 0xffff;
+	dpm_state->hard_min_level = 0x0;
+	dpm_state->hard_max_level = 0xffff;
 }
 
-static int vega12_get_number_dpm_level(struct pp_hwmgr *hwmgr,
-		PPCLK_e clkID, uint32_t *num_dpm_level)
+static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
+		PPCLK_e clk_id, uint32_t *num_of_levels)
 {
-	int result;
-	/*
-	 * SMU expects the Clock ID to be in the top 16 bits.
-	 * Lower 16 bits specify the level however 0xFF is a
-	 * special argument the returns the total number of levels
-	 */
-	PP_ASSERT_WITH_CODE(smum_send_msg_to_smc_with_parameter(hwmgr,
-		PPSMC_MSG_GetDpmFreqByIndex, (clkID << 16 | 0xFF)) == 0,
-		"[GetNumberDpmLevel] Failed to get DPM levels from SMU for CLKID!",
-		return -EINVAL);
-
-	result = vega12_read_arg_from_smc(hwmgr, num_dpm_level);
+	int ret = 0;
 
-	PP_ASSERT_WITH_CODE(*num_dpm_level < MAX_REGULAR_DPM_NUMBER,
-		"[GetNumberDPMLevel] Number of DPM levels is greater than limit",
-		return -EINVAL);
+	ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_GetDpmFreqByIndex,
+			(clk_id << 16 | 0xFF));
+	PP_ASSERT_WITH_CODE(!ret,
+			"[GetNumOfDpmLevel] failed to get dpm levels!",
+			return ret);
 
-	PP_ASSERT_WITH_CODE(*num_dpm_level != 0,
-		"[GetNumberDPMLevel] Number of CLK Levels is zero!",
-		return -EINVAL);
+	vega12_read_arg_from_smc(hwmgr, num_of_levels);
+	PP_ASSERT_WITH_CODE(*num_of_levels > 0,
+			"[GetNumOfDpmLevel] number of clk levels is invalid!",
+			return -EINVAL);
 
-	return result;
+	return ret;
 }
 
 static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
@@ -509,6 +502,31 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 	return result;
 }
 
+static int vega12_setup_single_dpm_table(struct pp_hwmgr *hwmgr,
+		struct vega12_single_dpm_table *dpm_table, PPCLK_e clk_id)
+{
+	int ret = 0;
+	uint32_t i, num_of_levels, clk;
+
+	ret = vega12_get_number_of_dpm_level(hwmgr, clk_id, &num_of_levels);
+	PP_ASSERT_WITH_CODE(!ret,
+			"[SetupSingleDpmTable] failed to get clk levels!",
+			return ret);
+
+	dpm_table->count = num_of_levels;
+
+	for (i = 0; i < num_of_levels; i++) {
+		ret = vega12_get_dpm_frequency_by_index(hwmgr, clk_id, i, &clk);
+		PP_ASSERT_WITH_CODE(!ret,
+			"[SetupSingleDpmTable] failed to get clk of specific level!",
+			return ret);
+		dpm_table->dpm_levels[i].value = clk;
+		dpm_table->dpm_levels[i].enabled = true;
+	}
+
+	return ret;
+}
+
 /*
  * This function is to initialize all DPM state tables
  * for SMU based on the dependency table.
@@ -519,224 +537,136 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
  */
 static int vega12_setup_default_dpm_tables(struct pp_hwmgr *hwmgr)
 {
-	uint32_t num_levels, i, clock;
 
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
-
 	struct vega12_single_dpm_table *dpm_table;
+	int ret = 0;
 
 	memset(&data->dpm_table, 0, sizeof(data->dpm_table));
 
-	/* Initialize Sclk DPM and SOC DPM table based on allow Sclk values */
+	/* socclk */
 	dpm_table = &(data->dpm_table.soc_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_SOCCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for SOCCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_SOCCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for SOCCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_SOCCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get socclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.soc_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* gfxclk */
 	dpm_table = &(data->dpm_table.gfx_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_GFXCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for GFXCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_GFXCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for GFXCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_GFXCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get gfxclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.gfx_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
-	/* Initialize Mclk DPM table based on allow Mclk values */
-	dpm_table = &(data->dpm_table.mem_table);
 
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_UCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for UCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_UCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for UCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	/* memclk */
+	dpm_table = &(data->dpm_table.mem_table);
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_UCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get memclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.mem_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* eclk */
 	dpm_table = &(data->dpm_table.eclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_ECLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for ECLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-		PPCLK_ECLK, i, &clock) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for ECLK!",
-		return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_ECLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get eclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.eclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* vclk */
 	dpm_table = &(data->dpm_table.vclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_VCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for VCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_VCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for VCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_VCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get vclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.vclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* dclk */
 	dpm_table = &(data->dpm_table.dclk_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr, PPCLK_DCLK,
-		&num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DCLK, i, &clock) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCLK!",
-		return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.dclock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
-	/* Assume there is no headless Vega12 for now */
+	/* dcefclk */
 	dpm_table = &(data->dpm_table.dcef_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_DCEFCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCEFCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DCEFCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DCEFCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DCEFCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dcefclk dpm levels!",
+				return ret);
+	} else {
+		dpm_table->count = 1;
+		dpm_table->dpm_levels[0].value = data->vbios_boot_state.dcef_clock / 100;
 	}
-
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* pixclk */
 	dpm_table = &(data->dpm_table.pixel_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_PIXCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PIXCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_PIXCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PIXCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_PIXCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get pixclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* dispclk */
 	dpm_table = &(data->dpm_table.display_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_DISPCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DISPCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_DISPCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for DISPCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_DISPCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get dispclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
+	/* phyclk */
 	dpm_table = &(data->dpm_table.phy_table);
-
-	PP_ASSERT_WITH_CODE(vega12_get_number_dpm_level(hwmgr,
-		PPCLK_PHYCLK, &num_levels) == 0,
-		"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PHYCLK!",
-		return -EINVAL);
-
-	dpm_table->count = num_levels;
-
-	for (i = 0; i < num_levels; i++) {
-		PP_ASSERT_WITH_CODE(vega12_get_dpm_frequency_by_index(hwmgr,
-			PPCLK_PHYCLK, i, &clock) == 0,
-			"[SetupDefaultDPMTables] Failed to get DPM levels from SMU for PHYCLK!",
-			return -EINVAL);
-
-		dpm_table->dpm_levels[i].value = clock;
-		dpm_table->dpm_levels[i].enabled = true;
-	}
-
+	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
+		ret = vega12_setup_single_dpm_table(hwmgr, dpm_table, PPCLK_PHYCLK);
+		PP_ASSERT_WITH_CODE(!ret,
+				"[SetupDefaultDpmTable] failed to get phyclk dpm levels!",
+				return ret);
+	} else
+		dpm_table->count = 0;
 	vega12_init_dpm_state(&(dpm_table->dpm_state));
 
 	/* save a copy of the default DPM table */
-- 
cgit v1.2.3


From 70fef5741c6b82ad293a225f116006565646fb72 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 15:41:44 +0800
Subject: drm/amd/powerplay: retrieve all clock ranges on startup

So that we do not need to use PPSMC_MSG_GetMin/MaxDpmFreq to
get the clock ranges on runtime. Since that causes some problems.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 69 +++++++++++++++++-----
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h |  8 +++
 2 files changed, 61 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index bc976e1d22c5..d3e898306ced 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -856,6 +856,48 @@ static int vega12_power_control_set_level(struct pp_hwmgr *hwmgr)
 	return result;
 }
 
+static int vega12_get_all_clock_ranges_helper(struct pp_hwmgr *hwmgr,
+		PPCLK_e clkid, struct vega12_clock_range *clock)
+{
+	/* AC Max */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMaxDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get max ac clock from SMC!",
+		return -EINVAL);
+	vega12_read_arg_from_smc(hwmgr, &(clock->ACMax));
+
+	/* AC Min */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMinDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get min ac clock from SMC!",
+		return -EINVAL);
+	vega12_read_arg_from_smc(hwmgr, &(clock->ACMin));
+
+	/* DC Max */
+	PP_ASSERT_WITH_CODE(
+		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDcModeMaxDpmFreq, (clkid << 16)) == 0,
+		"[GetClockRanges] Failed to get max dc clock from SMC!",
+		return -EINVAL);
+	vega12_read_arg_from_smc(hwmgr, &(clock->DCMax));
+
+	return 0;
+}
+
+static int vega12_get_all_clock_ranges(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	uint32_t i;
+
+	for (i = 0; i < PPCLK_COUNT; i++)
+		PP_ASSERT_WITH_CODE(!vega12_get_all_clock_ranges_helper(hwmgr,
+					i, &(data->clk_range[i])),
+				"Failed to get clk range from SMC!",
+				return -EINVAL);
+
+	return 0;
+}
+
 static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 {
 	int tmp_result, result = 0;
@@ -883,6 +925,11 @@ static int vega12_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 			"Failed to power control set level!",
 			result = tmp_result);
 
+	result = vega12_get_all_clock_ranges(hwmgr);
+	PP_ASSERT_WITH_CODE(!result,
+			"Failed to get all clock ranges!",
+			return result);
+
 	result = vega12_odn_initialize_default_settings(hwmgr);
 	PP_ASSERT_WITH_CODE(!result,
 			"Failed to power control set level!",
@@ -1472,24 +1519,14 @@ static int vega12_get_clock_ranges(struct pp_hwmgr *hwmgr,
 		PPCLK_e clock_select,
 		bool max)
 {
-	int result;
-	*clock = 0;
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
-	if (max) {
-		 PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMaxDpmFreq, (clock_select << 16)) == 0,
-			"[GetClockRanges] Failed to get max clock from SMC!",
-			return -1);
-		result = vega12_read_arg_from_smc(hwmgr, clock);
-	} else {
-		PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMinDpmFreq, (clock_select << 16)) == 0,
-			"[GetClockRanges] Failed to get min clock from SMC!",
-			return -1);
-		result = vega12_read_arg_from_smc(hwmgr, clock);
-	}
+	if (max)
+		*clock = data->clk_range[clock_select].ACMax;
+	else
+		*clock = data->clk_range[clock_select].ACMin;
 
-	return result;
+	return 0;
 }
 
 static int vega12_get_sclks(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index 49b38df8c7f2..e18c08308602 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -304,6 +304,12 @@ struct vega12_odn_fan_table {
 	bool		force_fan_pwm;
 };
 
+struct vega12_clock_range {
+	uint32_t	ACMax;
+	uint32_t	ACMin;
+	uint32_t	DCMax;
+};
+
 struct vega12_hwmgr {
 	struct vega12_dpm_table          dpm_table;
 	struct vega12_dpm_table          golden_dpm_table;
@@ -385,6 +391,8 @@ struct vega12_hwmgr {
 	uint32_t                       smu_version;
 	struct smu_features            smu_features[GNLD_FEATURES_MAX];
 	struct vega12_smc_state_table  smc_state_table;
+
+	struct vega12_clock_range      clk_range[PPCLK_COUNT];
 };
 
 #define VEGA12_DPM2_NEAR_TDP_DEC                      10
-- 
cgit v1.2.3


From 8fd26361701187e6fbb56c7c8bf22b4ab763b082 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 16:04:17 +0800
Subject: drm/amd/powerplay: revise clock level setup

Make sure the clock level set only on dpm enabled. Also uvd/vce/soc
clock also changed correspondingly.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 318 ++++++++++++++-------
 1 file changed, 211 insertions(+), 107 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index d3e898306ced..45c8f2ddaa95 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -958,76 +958,172 @@ static uint32_t vega12_find_lowest_dpm_level(
 			break;
 	}
 
+	if (i >= table->count) {
+		i = 0;
+		table->dpm_levels[i].enabled = true;
+	}
+
 	return i;
 }
 
 static uint32_t vega12_find_highest_dpm_level(
 		struct vega12_single_dpm_table *table)
 {
-	uint32_t i = 0;
+	int32_t i = 0;
+	PP_ASSERT_WITH_CODE(table->count <= MAX_REGULAR_DPM_NUMBER,
+			"[FindHighestDPMLevel] DPM Table has too many entries!",
+			return MAX_REGULAR_DPM_NUMBER - 1);
 
-	if (table->count <= MAX_REGULAR_DPM_NUMBER) {
-		for (i = table->count; i > 0; i--) {
-			if (table->dpm_levels[i - 1].enabled)
-				return i - 1;
-		}
-	} else {
-		pr_info("DPM Table Has Too Many Entries!");
-		return MAX_REGULAR_DPM_NUMBER - 1;
+	for (i = table->count - 1; i >= 0; i--) {
+		if (table->dpm_levels[i].enabled)
+			break;
 	}
 
-	return i;
+	if (i < 0) {
+		i = 0;
+		table->dpm_levels[i].enabled = true;
+	}
+
+	return (uint32_t)i;
 }
 
 static int vega12_upload_dpm_min_level(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = hwmgr->backend;
-	if (data->smc_state_table.gfx_boot_level !=
-			data->dpm_table.gfx_table.dpm_state.soft_min_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMinByFreq,
-			PPCLK_GFXCLK<<16 | data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_boot_level].value);
-		data->dpm_table.gfx_table.dpm_state.soft_min_level =
-				data->smc_state_table.gfx_boot_level;
+	uint32_t min_freq;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		min_freq = data->dpm_table.gfx_table.dpm_state.soft_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_GFXCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min gfxclk !",
+					return ret);
 	}
 
-	if (data->smc_state_table.mem_boot_level !=
-			data->dpm_table.mem_table.dpm_state.soft_min_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMinByFreq,
-			PPCLK_UCLK<<16 | data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_boot_level].value);
-		data->dpm_table.mem_table.dpm_state.soft_min_level =
-				data->smc_state_table.mem_boot_level;
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		min_freq = data->dpm_table.mem_table.dpm_state.soft_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_UCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min memclk !",
+					return ret);
+
+		min_freq = data->dpm_table.mem_table.dpm_state.hard_min_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetHardMinByFreq,
+					(PPCLK_UCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set hard min memclk !",
+					return ret);
 	}
 
-	return 0;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		min_freq = data->dpm_table.vclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_VCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min vclk!",
+					return ret);
+
+		min_freq = data->dpm_table.dclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_DCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min dclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		min_freq = data->dpm_table.eclk_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_ECLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min eclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		min_freq = data->dpm_table.soc_table.dpm_state.soft_min_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMinByFreq,
+					(PPCLK_SOCCLK << 16) | (min_freq & 0xffff))),
+					"Failed to set soft min socclk!",
+					return ret);
+	}
+
+	return ret;
 
 }
 
 static int vega12_upload_dpm_max_level(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = hwmgr->backend;
-	if (data->smc_state_table.gfx_max_level !=
-		data->dpm_table.gfx_table.dpm_state.soft_max_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMaxByFreq,
-			/* plus the vale by 1 to align the resolution */
-			PPCLK_GFXCLK<<16 | (data->dpm_table.gfx_table.dpm_levels[data->smc_state_table.gfx_max_level].value + 1));
-		data->dpm_table.gfx_table.dpm_state.soft_max_level =
-				data->smc_state_table.gfx_max_level;
+	uint32_t max_freq;
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_GFXCLK].enabled) {
+		max_freq = data->dpm_table.gfx_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_GFXCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max gfxclk!",
+					return ret);
 	}
 
-	if (data->smc_state_table.mem_max_level !=
-		data->dpm_table.mem_table.dpm_state.soft_max_level) {
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-			PPSMC_MSG_SetSoftMaxByFreq,
-			/* plus the vale by 1 to align the resolution */
-			PPCLK_UCLK<<16 | (data->dpm_table.mem_table.dpm_levels[data->smc_state_table.mem_max_level].value + 1));
-		data->dpm_table.mem_table.dpm_state.soft_max_level =
-				data->smc_state_table.mem_max_level;
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		max_freq = data->dpm_table.mem_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_UCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max memclk!",
+					return ret);
 	}
 
-	return 0;
+	if (data->smu_features[GNLD_DPM_UVD].enabled) {
+		max_freq = data->dpm_table.vclk_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_VCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max vclk!",
+					return ret);
+
+		max_freq = data->dpm_table.dclk_table.dpm_state.soft_max_level;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_DCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max dclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled) {
+		max_freq = data->dpm_table.eclk_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_ECLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max eclk!",
+					return ret);
+	}
+
+	if (data->smu_features[GNLD_DPM_SOCCLK].enabled) {
+		max_freq = data->dpm_table.soc_table.dpm_state.soft_max_level;
+
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(
+					hwmgr, PPSMC_MSG_SetSoftMaxByFreq,
+					(PPCLK_SOCCLK << 16) | (max_freq & 0xffff))),
+					"Failed to set soft max socclk!",
+					return ret);
+	}
+
+	return ret;
 }
 
 int vega12_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable)
@@ -1330,12 +1426,19 @@ static int vega12_force_dpm_highest(struct pp_hwmgr *hwmgr)
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
 
-	data->smc_state_table.gfx_boot_level =
-	data->smc_state_table.gfx_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-	data->smc_state_table.mem_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
+	uint32_t soft_level;
+
+	soft_level = vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
+
+	data->dpm_table.gfx_table.dpm_state.soft_min_level =
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+		data->dpm_table.gfx_table.dpm_levels[soft_level].value;
+
+	soft_level = vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
+
+	data->dpm_table.mem_table.dpm_state.soft_min_level =
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+		data->dpm_table.mem_table.dpm_levels[soft_level].value;
 
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload boot level to highest!",
@@ -1352,13 +1455,19 @@ static int vega12_force_dpm_lowest(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data =
 			(struct vega12_hwmgr *)(hwmgr->backend);
+	uint32_t soft_level;
+
+	soft_level = vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
+
+	data->dpm_table.gfx_table.dpm_state.soft_min_level =
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+		data->dpm_table.gfx_table.dpm_levels[soft_level].value;
 
-	data->smc_state_table.gfx_boot_level =
-	data->smc_state_table.gfx_max_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-	data->smc_state_table.mem_max_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
+	soft_level = vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
+
+	data->dpm_table.mem_table.dpm_state.soft_min_level =
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+		data->dpm_table.mem_table.dpm_levels[soft_level].value;
 
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload boot level to highest!",
@@ -1374,17 +1483,6 @@ static int vega12_force_dpm_lowest(struct pp_hwmgr *hwmgr)
 
 static int vega12_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
 {
-	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
-
-	data->smc_state_table.gfx_boot_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.gfx_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.gfx_table));
-	data->smc_state_table.mem_boot_level =
-			vega12_find_lowest_dpm_level(&(data->dpm_table.mem_table));
-	data->smc_state_table.mem_max_level =
-			vega12_find_highest_dpm_level(&(data->dpm_table.mem_table));
-
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
 			"Failed to upload DPM Bootup Levels!",
 			return -1);
@@ -1392,22 +1490,28 @@ static int vega12_unforce_dpm_levels(struct pp_hwmgr *hwmgr)
 	PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
 			"Failed to upload DPM Max Levels!",
 			return -1);
+
 	return 0;
 }
 
-#if 0
 static int vega12_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_forced_level level,
 				uint32_t *sclk_mask, uint32_t *mclk_mask, uint32_t *soc_mask)
 {
-	struct phm_ppt_v2_information *table_info =
-			(struct phm_ppt_v2_information *)(hwmgr->pptable);
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	struct vega12_single_dpm_table *gfx_dpm_table = &(data->dpm_table.gfx_table);
+	struct vega12_single_dpm_table *mem_dpm_table = &(data->dpm_table.mem_table);
+	struct vega12_single_dpm_table *soc_dpm_table = &(data->dpm_table.soc_table);
+
+	*sclk_mask = 0;
+	*mclk_mask = 0;
+	*soc_mask  = 0;
 
-	if (table_info->vdd_dep_on_sclk->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL &&
-		table_info->vdd_dep_on_socclk->count > VEGA12_UMD_PSTATE_SOCCLK_LEVEL &&
-		table_info->vdd_dep_on_mclk->count > VEGA12_UMD_PSTATE_MCLK_LEVEL) {
+	if (gfx_dpm_table->count > VEGA12_UMD_PSTATE_GFXCLK_LEVEL &&
+	    mem_dpm_table->count > VEGA12_UMD_PSTATE_MCLK_LEVEL &&
+	    soc_dpm_table->count > VEGA12_UMD_PSTATE_SOCCLK_LEVEL) {
 		*sclk_mask = VEGA12_UMD_PSTATE_GFXCLK_LEVEL;
-		*soc_mask = VEGA12_UMD_PSTATE_SOCCLK_LEVEL;
 		*mclk_mask = VEGA12_UMD_PSTATE_MCLK_LEVEL;
+		*soc_mask  = VEGA12_UMD_PSTATE_SOCCLK_LEVEL;
 	}
 
 	if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
@@ -1415,13 +1519,13 @@ static int vega12_get_profiling_clk_mask(struct pp_hwmgr *hwmgr, enum amd_dpm_fo
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
 		*mclk_mask = 0;
 	} else if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
-		*sclk_mask = table_info->vdd_dep_on_sclk->count - 1;
-		*soc_mask = table_info->vdd_dep_on_socclk->count - 1;
-		*mclk_mask = table_info->vdd_dep_on_mclk->count - 1;
+		*sclk_mask = gfx_dpm_table->count - 1;
+		*mclk_mask = mem_dpm_table->count - 1;
+		*soc_mask  = soc_dpm_table->count - 1;
 	}
+
 	return 0;
 }
-#endif
 
 static void vega12_set_fan_control_mode(struct pp_hwmgr *hwmgr, uint32_t mode)
 {
@@ -1445,11 +1549,9 @@ static int vega12_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 				enum amd_dpm_forced_level level)
 {
 	int ret = 0;
-#if 0
 	uint32_t sclk_mask = 0;
 	uint32_t mclk_mask = 0;
 	uint32_t soc_mask = 0;
-#endif
 
 	switch (level) {
 	case AMD_DPM_FORCED_LEVEL_HIGH:
@@ -1465,27 +1567,18 @@ static int vega12_dpm_force_dpm_level(struct pp_hwmgr *hwmgr,
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_PEAK:
-#if 0
 		ret = vega12_get_profiling_clk_mask(hwmgr, level, &sclk_mask, &mclk_mask, &soc_mask);
 		if (ret)
 			return ret;
-		vega12_force_clock_level(hwmgr, PP_SCLK, 1<<sclk_mask);
-		vega12_force_clock_level(hwmgr, PP_MCLK, 1<<mclk_mask);
-#endif
+		vega12_force_clock_level(hwmgr, PP_SCLK, 1 << sclk_mask);
+		vega12_force_clock_level(hwmgr, PP_MCLK, 1 << mclk_mask);
 		break;
 	case AMD_DPM_FORCED_LEVEL_MANUAL:
 	case AMD_DPM_FORCED_LEVEL_PROFILE_EXIT:
 	default:
 		break;
 	}
-#if 0
-	if (!ret) {
-		if (level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
-			vega12_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_NONE);
-		else if (level != AMD_DPM_FORCED_LEVEL_PROFILE_PEAK && hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK)
-			vega12_set_fan_control_mode(hwmgr, AMD_FAN_CTRL_AUTO);
-	}
-#endif
+
 	return ret;
 }
 
@@ -1745,37 +1838,48 @@ static int vega12_force_clock_level(struct pp_hwmgr *hwmgr,
 		enum pp_clock_type type, uint32_t mask)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
-
-	if (hwmgr->request_dpm_level & (AMD_DPM_FORCED_LEVEL_AUTO |
-				AMD_DPM_FORCED_LEVEL_LOW |
-				AMD_DPM_FORCED_LEVEL_HIGH))
-		return -EINVAL;
+	uint32_t soft_min_level, soft_max_level;
+	int ret = 0;
 
 	switch (type) {
 	case PP_SCLK:
-		data->smc_state_table.gfx_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.gfx_max_level = mask ? (fls(mask) - 1) : 0;
+		soft_min_level = mask ? (ffs(mask) - 1) : 0;
+		soft_max_level = mask ? (fls(mask) - 1) : 0;
+
+		data->dpm_table.gfx_table.dpm_state.soft_min_level =
+			data->dpm_table.gfx_table.dpm_levels[soft_min_level].value;
+		data->dpm_table.gfx_table.dpm_state.soft_max_level =
+			data->dpm_table.gfx_table.dpm_levels[soft_max_level].value;
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
+		ret = vega12_upload_dpm_min_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload boot level to lowest!",
-			return -EINVAL);
+			return ret);
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
+		ret = vega12_upload_dpm_max_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
+			return ret);
 		break;
 
 	case PP_MCLK:
-		data->smc_state_table.mem_boot_level = mask ? (ffs(mask) - 1) : 0;
-		data->smc_state_table.mem_max_level = mask ? (fls(mask) - 1) : 0;
+		soft_min_level = mask ? (ffs(mask) - 1) : 0;
+		soft_max_level = mask ? (fls(mask) - 1) : 0;
+
+		data->dpm_table.mem_table.dpm_state.soft_min_level =
+			data->dpm_table.mem_table.dpm_levels[soft_min_level].value;
+		data->dpm_table.mem_table.dpm_state.soft_max_level =
+			data->dpm_table.mem_table.dpm_levels[soft_max_level].value;
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_min_level(hwmgr),
+		ret = vega12_upload_dpm_min_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload boot level to lowest!",
-			return -EINVAL);
+			return ret);
 
-		PP_ASSERT_WITH_CODE(!vega12_upload_dpm_max_level(hwmgr),
+		ret = vega12_upload_dpm_max_level(hwmgr);
+		PP_ASSERT_WITH_CODE(!ret,
 			"Failed to upload dpm max level to highest!",
-			return -EINVAL);
+			return ret);
 
 		break;
 
-- 
cgit v1.2.3


From f74aa69d0aed89b5ea283f4a6f86f0505407021e Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 16:25:14 +0800
Subject: drm/amd/powerplay: initialize uvd/vce powergate status v4

On UVD/VCE dpm enabled/disabled, the powergate status will be
set as false/true. So that we will not try to ungate/gate them(
enable/disable their dpm) again.

v2: added check for uvd/vce powergate status before gating
v3: fix typo in description
v4: warning fix (Alex)

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 23 ++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 45c8f2ddaa95..8176b231c38b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -777,6 +777,21 @@ static int vega12_set_allowed_featuresmask(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static void vega12_init_powergate_state(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+
+	data->uvd_power_gated = true;
+	data->vce_power_gated = true;
+
+	if (data->smu_features[GNLD_DPM_UVD].enabled)
+		data->uvd_power_gated = false;
+
+	if (data->smu_features[GNLD_DPM_VCE].enabled)
+		data->vce_power_gated = false;
+}
+
 static int vega12_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data =
@@ -801,6 +816,8 @@ static int vega12_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 		}
 	}
 
+	vega12_init_powergate_state(hwmgr);
+
 	return 0;
 }
 
@@ -1985,6 +2002,9 @@ static void vega12_power_gate_vce(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
+	if (data->vce_power_gated == bgate)
+		return;
+
 	data->vce_power_gated = bgate;
 	vega12_enable_disable_vce_dpm(hwmgr, !bgate);
 }
@@ -1993,6 +2013,9 @@ static void vega12_power_gate_uvd(struct pp_hwmgr *hwmgr, bool bgate)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 
+	if (data->uvd_power_gated == bgate)
+		return;
+
 	data->uvd_power_gated = bgate;
 	vega12_enable_disable_uvd_dpm(hwmgr, !bgate);
 }
-- 
cgit v1.2.3


From ac32b06acee88ab4c9f3336be5aea4a050b0d4e5 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Wed, 20 Jun 2018 12:24:29 +0800
Subject: drm/amd/powerplay: correct smc display config for multi monitor

Need to take into account multi-head with synced displays.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 8176b231c38b..824d9e15d712 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1401,7 +1401,8 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 	struct pp_display_clock_request clock_req;
 	uint32_t clk_request;
 
-	if (hwmgr->display_config->num_display > 1)
+	if ((hwmgr->display_config->num_display > 1) &&
+		!hwmgr->display_config->multi_monitor_in_sync)
 		vega12_notify_smc_display_change(hwmgr, false);
 	else
 		vega12_notify_smc_display_change(hwmgr, true);
-- 
cgit v1.2.3


From 30222561808f8fdf6d56c22ccfe3d9140fd0a169 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Wed, 20 Jun 2018 12:28:10 +0800
Subject: drm/amd/powerplay: drop unnecessary uclk hard min setting

We don't need to set uclk hard min here because this will
be set with other clocks on power state change.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 824d9e15d712..8222383009da 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1399,7 +1399,6 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 			(struct vega12_hwmgr *)(hwmgr->backend);
 	struct PP_Clocks min_clocks = {0};
 	struct pp_display_clock_request clock_req;
-	uint32_t clk_request;
 
 	if ((hwmgr->display_config->num_display > 1) &&
 		!hwmgr->display_config->multi_monitor_in_sync)
@@ -1427,15 +1426,6 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 		}
 	}
 
-	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
-		clk_request = (PPCLK_UCLK << 16) | (min_clocks.memoryClock) / 100;
-		PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_SetHardMinByFreq, clk_request) == 0,
-			"[PhwVega12_NotifySMCDisplayConfigAfterPowerStateAdjustment] Attempt to set UCLK HardMin Failed!",
-			return -1);
-		data->dpm_table.mem_table.dpm_state.hard_min_level = min_clocks.memoryClock;
-	}
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From a0a59c8fc7af37287228a0c89b0a71a1ffadc29b Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 16:33:40 +0800
Subject: drm/amd/powerplay: correct vega12 max num of dpm level

Use MAX_NUM_CLOCKS instead of VG12_PSUEDO* macros for
the max number of dpm levels.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 8222383009da..d1bab9845b08 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1642,8 +1642,8 @@ static int vega12_get_sclks(struct pp_hwmgr *hwmgr,
 		return -1;
 
 	dpm_table = &(data->dpm_table.gfx_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_GFXCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
@@ -1674,11 +1674,12 @@ static int vega12_get_memclocks(struct pp_hwmgr *hwmgr,
 		return -1;
 
 	dpm_table = &(data->dpm_table.mem_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_UCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_UCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
+			data->mclk_latency_table.entries[i].frequency =
 			dpm_table->dpm_levels[i].value * 100;
 
 		clocks->data[i].latency_in_us =
@@ -1704,8 +1705,8 @@ static int vega12_get_dcefclocks(struct pp_hwmgr *hwmgr,
 
 
 	dpm_table = &(data->dpm_table.dcef_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_DCEFCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_DCEFCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
@@ -1732,8 +1733,8 @@ static int vega12_get_socclocks(struct pp_hwmgr *hwmgr,
 
 
 	dpm_table = &(data->dpm_table.soc_table);
-	ucount = (dpm_table->count > VG12_PSUEDO_NUM_SOCCLK_DPM_LEVELS) ?
-		VG12_PSUEDO_NUM_SOCCLK_DPM_LEVELS : dpm_table->count;
+	ucount = (dpm_table->count > MAX_NUM_CLOCKS) ?
+		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-- 
cgit v1.2.3


From e17c7f92b2b7c2f14934c305a8d72bbb0bf6f362 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 16:40:57 +0800
Subject: drm/amd/powerplay: apply clocks adjust rules on power state change

This add the apply_clocks_adjust_rules callback which is used
to validate the clock settings on a power state change.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 162 +++++++++++++++++++++
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h |   2 +
 2 files changed, 164 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index d1bab9845b08..d28227efe906 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1950,6 +1950,166 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 	return size;
 }
 
+static int vega12_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	struct vega12_single_dpm_table *dpm_table;
+	bool vblank_too_short = false;
+	bool disable_mclk_switching;
+	uint32_t i, latency;
+
+	disable_mclk_switching = ((1 < hwmgr->display_config->num_display) &&
+			          !hwmgr->display_config->multi_monitor_in_sync) ||
+			          vblank_too_short;
+	latency = hwmgr->display_config->dce_tolerable_mclk_in_active_latency;
+
+	/* gfxclk */
+	dpm_table = &(data->dpm_table.gfx_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_GFXCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_GFXCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_SCLK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[0].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* memclk */
+	dpm_table = &(data->dpm_table.mem_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_MCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_MCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[0].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* honour DAL's UCLK Hardmin */
+	if (dpm_table->dpm_state.hard_min_level < (hwmgr->display_config->min_mem_set_clock / 100))
+		dpm_table->dpm_state.hard_min_level = hwmgr->display_config->min_mem_set_clock / 100;
+
+	/* Hardmin is dependent on displayconfig */
+	if (disable_mclk_switching) {
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		for (i = 0; i < data->mclk_latency_table.count - 1; i++) {
+			if (data->mclk_latency_table.entries[i].latency <= latency) {
+				if (dpm_table->dpm_levels[i].value >= (hwmgr->display_config->min_mem_set_clock / 100)) {
+					dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[i].value;
+					break;
+				}
+			}
+		}
+	}
+
+	if (hwmgr->display_config->nb_pstate_switch_disable)
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	/* vclk */
+	dpm_table = &(data->dpm_table.vclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_UVDCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* dclk */
+	dpm_table = &(data->dpm_table.dclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_UVDCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_UVDCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* socclk */
+	dpm_table = &(data->dpm_table.soc_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_SOCCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_SOCCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_SOCCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	/* eclk */
+	dpm_table = &(data->dpm_table.eclk_table);
+	dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+	dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[0].value;
+	dpm_table->dpm_state.hard_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+
+	if (PP_CAP(PHM_PlatformCaps_UMDPState)) {
+		if (VEGA12_UMD_PSTATE_VCEMCLK_LEVEL < dpm_table->count) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_VCEMCLK_LEVEL].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[VEGA12_UMD_PSTATE_VCEMCLK_LEVEL].value;
+		}
+
+		if (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK) {
+			dpm_table->dpm_state.soft_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+			dpm_table->dpm_state.soft_max_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		}
+	}
+
+	return 0;
+}
+
 static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
@@ -2202,6 +2362,8 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.display_clock_voltage_request = vega12_display_clock_voltage_request,
 	.force_clock_level = vega12_force_clock_level,
 	.print_clock_levels = vega12_print_clock_levels,
+	.apply_clocks_adjust_rules =
+		vega12_apply_clocks_adjust_rules,
 	.display_config_changed = vega12_display_configuration_changed_task,
 	.powergate_uvd = vega12_power_gate_uvd,
 	.powergate_vce = vega12_power_gate_vce,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index e18c08308602..e17237c90eea 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -443,6 +443,8 @@ struct vega12_hwmgr {
 #define VEGA12_UMD_PSTATE_GFXCLK_LEVEL         0x3
 #define VEGA12_UMD_PSTATE_SOCCLK_LEVEL         0x3
 #define VEGA12_UMD_PSTATE_MCLK_LEVEL           0x2
+#define VEGA12_UMD_PSTATE_UVDCLK_LEVEL         0x3
+#define VEGA12_UMD_PSTATE_VCEMCLK_LEVEL        0x3
 
 int vega12_enable_disable_vce_dpm(struct pp_hwmgr *hwmgr, bool enable);
 
-- 
cgit v1.2.3


From 28a7b4f4498546c0d4d41c084abd0496f9922bf3 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 17:22:33 +0800
Subject: drm/amd/powerplay: set vega12 pre display configurations

Set num_displays to 0 and force uclk high as part of the mode
set sequence.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 41 ++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index d28227efe906..e899a0cdbb0d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -2110,6 +2110,45 @@ static int vega12_apply_clocks_adjust_rules(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+static int vega12_set_uclk_to_highest_dpm_level(struct pp_hwmgr *hwmgr,
+		struct vega12_single_dpm_table *dpm_table)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->smu_features[GNLD_DPM_UCLK].enabled) {
+		PP_ASSERT_WITH_CODE(dpm_table->count > 0,
+				"[SetUclkToHightestDpmLevel] Dpm table has no entry!",
+				return -EINVAL);
+		PP_ASSERT_WITH_CODE(dpm_table->count <= NUM_UCLK_DPM_LEVELS,
+				"[SetUclkToHightestDpmLevel] Dpm table has too many entries!",
+				return -EINVAL);
+
+		dpm_table->dpm_state.hard_min_level = dpm_table->dpm_levels[dpm_table->count - 1].value;
+		PP_ASSERT_WITH_CODE(!(ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+				PPSMC_MSG_SetHardMinByFreq,
+				(PPCLK_UCLK << 16 ) | dpm_table->dpm_state.hard_min_level)),
+				"[SetUclkToHightestDpmLevel] Set hard min uclk failed!",
+				return ret);
+	}
+
+	return ret;
+}
+
+static int vega12_pre_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_NumOfDisplays, 0);
+
+	ret = vega12_set_uclk_to_highest_dpm_level(hwmgr,
+			&data->dpm_table.mem_table);
+
+	return ret;
+}
+
 static int vega12_display_configuration_changed_task(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
@@ -2364,6 +2403,8 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.print_clock_levels = vega12_print_clock_levels,
 	.apply_clocks_adjust_rules =
 		vega12_apply_clocks_adjust_rules,
+	.pre_display_config_changed =
+		vega12_pre_display_configuration_changed_task,
 	.display_config_changed = vega12_display_configuration_changed_task,
 	.powergate_uvd = vega12_power_gate_uvd,
 	.powergate_vce = vega12_power_gate_vce,
-- 
cgit v1.2.3


From 6ad87101f3a34ea2b955a09dde085e4e9901bab9 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 16:46:40 +0800
Subject: drm/amd/powerplay: correct vega12 thermal support as true

Thermal support is enabled on vega12.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index e899a0cdbb0d..6bc5f253ce8d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -81,6 +81,7 @@ static void vega12_set_default_registry_data(struct pp_hwmgr *hwmgr)
 
 	data->registry_data.disallowed_features = 0x0;
 	data->registry_data.od_state_in_dc_support = 0;
+	data->registry_data.thermal_support = 1;
 	data->registry_data.skip_baco_hardware = 0;
 
 	data->registry_data.log_avfs_param = 0;
-- 
cgit v1.2.3


From 0c3d01744511f053c5f67737cb7a6a99c0216a84 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 11 Jun 2018 16:48:43 +0800
Subject: drm/amd/powerplay: cosmetic fix

Fix coding style and drop unused variable.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c     | 10 +++-------
 .../gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h  | 18 +++++++++---------
 2 files changed, 12 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 6bc5f253ce8d..a86777954ea7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -811,9 +811,6 @@ static int vega12_enable_all_smu_features(struct pp_hwmgr *hwmgr)
 			enabled = (features_enabled & data->smu_features[i].smu_feature_bitmap) ? true : false;
 			data->smu_features[i].enabled = enabled;
 			data->smu_features[i].supported = enabled;
-			PP_ASSERT(
-				!data->smu_features[i].allowed || enabled,
-				"[EnableAllSMUFeatures] Enabled feature is different from allowed, expected disabled!");
 		}
 	}
 
@@ -1230,8 +1227,8 @@ static int vega12_get_current_gfx_clk_freq(struct pp_hwmgr *hwmgr, uint32_t *gfx
 
 	*gfx_freq = 0;
 
-	PP_ASSERT_WITH_CODE(
-			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16)) == 0,
+	PP_ASSERT_WITH_CODE(smum_send_msg_to_smc_with_parameter(hwmgr,
+			PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16)) == 0,
 			"[GetCurrentGfxClkFreq] Attempt to get Current GFXCLK Frequency Failed!",
 			return -1);
 	PP_ASSERT_WITH_CODE(
@@ -1790,7 +1787,6 @@ static int vega12_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
-	int result = 0;
 	uint32_t i;
 
 	if (!data->registry_data.disable_water_mark &&
@@ -1841,7 +1837,7 @@ static int vega12_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 		data->water_marks_bitmap &= ~WaterMarksLoaded;
 	}
 
-	return result;
+	return 0;
 }
 
 static int vega12_force_clock_level(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
index b08526fd1619..b6ffd08784e7 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/vega12/smu9_driver_if.h
@@ -412,10 +412,10 @@ typedef struct {
   QuadraticInt_t    ReservedEquation2;
   QuadraticInt_t    ReservedEquation3;
 
-	uint16_t     MinVoltageUlvGfx;
-	uint16_t     MinVoltageUlvSoc;
+  uint16_t     MinVoltageUlvGfx;
+  uint16_t     MinVoltageUlvSoc;
 
-	uint32_t     Reserved[14];
+  uint32_t     Reserved[14];
 
 
 
@@ -483,9 +483,9 @@ typedef struct {
   uint8_t      padding8_4;
 
 
-	uint8_t      PllGfxclkSpreadEnabled;
-	uint8_t      PllGfxclkSpreadPercent;
-	uint16_t     PllGfxclkSpreadFreq;
+  uint8_t      PllGfxclkSpreadEnabled;
+  uint8_t      PllGfxclkSpreadPercent;
+  uint16_t     PllGfxclkSpreadFreq;
 
   uint8_t      UclkSpreadEnabled;
   uint8_t      UclkSpreadPercent;
@@ -495,9 +495,9 @@ typedef struct {
   uint8_t      SocclkSpreadPercent;
   uint16_t     SocclkSpreadFreq;
 
-	uint8_t      AcgGfxclkSpreadEnabled;
-	uint8_t      AcgGfxclkSpreadPercent;
-	uint16_t     AcgGfxclkSpreadFreq;
+  uint8_t      AcgGfxclkSpreadEnabled;
+  uint8_t      AcgGfxclkSpreadPercent;
+  uint16_t     AcgGfxclkSpreadFreq;
 
   uint8_t      Vr2_I2C_address;
   uint8_t      padding_vr2[3];
-- 
cgit v1.2.3


From 102c16a0246d77043e555e1e5b5de316bc068cbc Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Mon, 25 Jun 2018 21:09:04 -0400
Subject: drm/amdgpu: Make struct amdgpu_atif private to amdgpu_acpi.c

Currently, there is nothing in amdgpu that actually uses these structs
other than amdgpu_acpi.c. Additionally, since we're about to start
saving the correct ACPI handle to use for calling ATIF in this struct
this saves us from having to handle making sure that the acpi_handle
(and by proxy, the type definition for acpi_handle and all of the other
acpi headers) doesn't need to be included within the amdgpu_drv struct
itself. This follows the example set by amdgpu_atpx_handler.c.

Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h      | 40 ++---------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 54 ++++++++++++++++++++++++++++++--
 2 files changed, 53 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 86e4d8bd52a6..219fea72beeb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -190,6 +190,7 @@ struct amdgpu_job;
 struct amdgpu_irq_src;
 struct amdgpu_fpriv;
 struct amdgpu_bo_va_mapping;
+struct amdgpu_atif;
 
 enum amdgpu_cp_irq {
 	AMDGPU_CP_IRQ_GFX_EOP = 0,
@@ -1278,43 +1279,6 @@ struct amdgpu_vram_scratch {
 /*
  * ACPI
  */
-struct amdgpu_atif_notification_cfg {
-	bool enabled;
-	int command_code;
-};
-
-struct amdgpu_atif_notifications {
-	bool display_switch;
-	bool expansion_mode_change;
-	bool thermal_state;
-	bool forced_power_state;
-	bool system_power_state;
-	bool display_conf_change;
-	bool px_gfx_switch;
-	bool brightness_change;
-	bool dgpu_display_event;
-};
-
-struct amdgpu_atif_functions {
-	bool system_params;
-	bool sbios_requests;
-	bool select_active_disp;
-	bool lid_state;
-	bool get_tv_standard;
-	bool set_tv_standard;
-	bool get_panel_expansion_mode;
-	bool set_panel_expansion_mode;
-	bool temperature_change;
-	bool graphics_device_types;
-};
-
-struct amdgpu_atif {
-	struct amdgpu_atif_notifications notifications;
-	struct amdgpu_atif_functions functions;
-	struct amdgpu_atif_notification_cfg notification_cfg;
-	struct amdgpu_encoder *encoder_for_bl;
-};
-
 struct amdgpu_atcs_functions {
 	bool get_ext_state;
 	bool pcie_perf_req;
@@ -1475,7 +1439,7 @@ struct amdgpu_device {
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_regs[AMDGPU_DEBUGFS_MAX_COMPONENTS];
 #endif
-	struct amdgpu_atif		atif;
+	struct amdgpu_atif		*atif;
 	struct amdgpu_atcs		atcs;
 	struct mutex			srbm_mutex;
 	/* GRBM index mutex. Protects concurrent access to GRBM index */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 8fa850a070e0..22c7e8ec0b9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -34,6 +34,43 @@
 #include "amd_acpi.h"
 #include "atom.h"
 
+struct amdgpu_atif_notification_cfg {
+	bool enabled;
+	int command_code;
+};
+
+struct amdgpu_atif_notifications {
+	bool display_switch;
+	bool expansion_mode_change;
+	bool thermal_state;
+	bool forced_power_state;
+	bool system_power_state;
+	bool display_conf_change;
+	bool px_gfx_switch;
+	bool brightness_change;
+	bool dgpu_display_event;
+};
+
+struct amdgpu_atif_functions {
+	bool system_params;
+	bool sbios_requests;
+	bool select_active_disp;
+	bool lid_state;
+	bool get_tv_standard;
+	bool set_tv_standard;
+	bool get_panel_expansion_mode;
+	bool set_panel_expansion_mode;
+	bool temperature_change;
+	bool graphics_device_types;
+};
+
+struct amdgpu_atif {
+	struct amdgpu_atif_notifications notifications;
+	struct amdgpu_atif_functions functions;
+	struct amdgpu_atif_notification_cfg notification_cfg;
+	struct amdgpu_encoder *encoder_for_bl;
+};
+
 /* Call the ATIF method
  */
 /**
@@ -292,7 +329,7 @@ out:
 static int amdgpu_atif_handler(struct amdgpu_device *adev,
 			struct acpi_bus_event *event)
 {
-	struct amdgpu_atif *atif = &adev->atif;
+	struct amdgpu_atif *atif = adev->atif;
 	struct atif_sbios_requests req;
 	acpi_handle handle;
 	int count;
@@ -303,7 +340,8 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 	if (strcmp(event->device_class, ACPI_VIDEO_CLASS) != 0)
 		return NOTIFY_DONE;
 
-	if (!atif->notification_cfg.enabled ||
+	if (!atif ||
+	    !atif->notification_cfg.enabled ||
 	    event->type != atif->notification_cfg.command_code)
 		/* Not our event */
 		return NOTIFY_DONE;
@@ -642,7 +680,7 @@ static int amdgpu_acpi_event(struct notifier_block *nb,
 int amdgpu_acpi_init(struct amdgpu_device *adev)
 {
 	acpi_handle handle;
-	struct amdgpu_atif *atif = &adev->atif;
+	struct amdgpu_atif *atif;
 	struct amdgpu_atcs *atcs = &adev->atcs;
 	int ret;
 
@@ -659,11 +697,19 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 	}
 
 	/* Call the ATIF method */
+	atif = kzalloc(sizeof(*atif), GFP_KERNEL);
+	if (!atif) {
+		DRM_WARN("Not enough memory to initialize ATIF\n");
+		goto out;
+	}
+
 	ret = amdgpu_atif_verify_interface(handle, atif);
 	if (ret) {
 		DRM_DEBUG_DRIVER("Call to ATIF verify_interface failed: %d\n", ret);
+		kfree(atif);
 		goto out;
 	}
+	adev->atif = atif;
 
 	if (atif->notifications.brightness_change) {
 		struct drm_encoder *tmp;
@@ -720,4 +766,6 @@ out:
 void amdgpu_acpi_fini(struct amdgpu_device *adev)
 {
 	unregister_acpi_notifier(&adev->acpi_nb);
+	if (adev->atif)
+		kfree(adev->atif);
 }
-- 
cgit v1.2.3


From aa03c075d02f89ae5acae10df1c8a3b095a440e7 Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Mon, 25 Jun 2018 21:09:05 -0400
Subject: drm/amdgpu: s/disp_detetion_ports/disp_detection_ports/

Fix typo.

Reviewed-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index daa06e7c5bb7..a3896412a019 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -32,7 +32,7 @@ struct amdgpu_atpx_functions {
 	bool switch_start;
 	bool switch_end;
 	bool disp_connectors_mapping;
-	bool disp_detetion_ports;
+	bool disp_detection_ports;
 };
 
 struct amdgpu_atpx {
@@ -156,7 +156,7 @@ static void amdgpu_atpx_parse_functions(struct amdgpu_atpx_functions *f, u32 mas
 	f->switch_start = mask & ATPX_GRAPHICS_DEVICE_SWITCH_START_NOTIFICATION_SUPPORTED;
 	f->switch_end = mask & ATPX_GRAPHICS_DEVICE_SWITCH_END_NOTIFICATION_SUPPORTED;
 	f->disp_connectors_mapping = mask & ATPX_GET_DISPLAY_CONNECTORS_MAPPING_SUPPORTED;
-	f->disp_detetion_ports = mask & ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED;
+	f->disp_detection_ports = mask & ATPX_GET_DISPLAY_DETECTION_PORTS_SUPPORTED;
 }
 
 /**
-- 
cgit v1.2.3


From 24aeefcdee255d21cc43bb511d5fdb760062199d Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Mon, 25 Jun 2018 21:09:06 -0400
Subject: drm/amdgpu: Add amdgpu_atpx_get_dhandle()

Since it seems that some vendors are storing the ATIF ACPI methods under
the same handle that ATPX lives under instead of the device's own
handle, we're going to need to be able to retrieve this handle later so
we can probe for ATIF there.

Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h              | 6 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c | 6 ++++++
 2 files changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 219fea72beeb..8a440b9fa0fd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1867,6 +1867,12 @@ static inline bool amdgpu_atpx_dgpu_req_power_for_displays(void) { return false;
 static inline bool amdgpu_has_atpx(void) { return false; }
 #endif
 
+#if defined(CONFIG_VGA_SWITCHEROO) && defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void);
+#else
+static inline void *amdgpu_atpx_get_dhandle(void) { return NULL; }
+#endif
+
 /*
  * KMS
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
index a3896412a019..b33f1680c9a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atpx_handler.c
@@ -90,6 +90,12 @@ bool amdgpu_atpx_dgpu_req_power_for_displays(void) {
 	return amdgpu_atpx_priv.atpx.dgpu_req_power_for_displays;
 }
 
+#if defined(CONFIG_ACPI)
+void *amdgpu_atpx_get_dhandle(void) {
+	return amdgpu_atpx_priv.dhandle;
+}
+#endif
+
 /**
  * amdgpu_atpx_call - call an ATPX method
  *
-- 
cgit v1.2.3


From 280cf1a94b822dfa2b505afcd24979dae643d6bf Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Mon, 25 Jun 2018 21:09:07 -0400
Subject: drm/amdgpu: Dynamically probe for ATIF handle (v2)

The other day I was testing one of the HP laptops at my office with an
i915/amdgpu hybrid setup and noticed that hotplugging was non-functional
on almost all of the display outputs. I eventually discovered that all
of the external outputs were connected to the amdgpu device instead of
i915, and that the hotplugs weren't being detected so long as the GPU
was in runtime suspend. After some talking with folks at AMD, I learned
that amdgpu is actually supposed to support hotplug detection in runtime
suspend so long as the OEM has implemented it properly in the firmware.

On this HP ZBook 15 G4 (the machine in question), amdgpu wasn't managing
to find the ATIF handle at all despite the fact that I could see acpi
events being sent in response to any hotplugging. After going through
dumps of the firmware, I discovered that this machine did in fact
support ATIF, but that it's ATIF method lived in an entirely different
namespace than this device's handle (the device handle was
\_SB_.PCI0.PEG0.PEGP, but ATIF lives in ATPX's handle at
\_SB_.PCI0.GFX0).

So, fix this by probing ATPX's ACPI parent's namespace if we can't find
ATIF elsewhere, along with storing a pointer to the proper handle to use
for ATIF and using that instead of the device's handle.

This fixes HPD detection while in runtime suspend for this ZBook!

v2: Update the comment to reflect how the namespaces are arranged
based on the system configuration. (Alex)

Signed-off-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 79 +++++++++++++++++++++++---------
 1 file changed, 58 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 22c7e8ec0b9a..0d8c3fc6eace 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -65,6 +65,8 @@ struct amdgpu_atif_functions {
 };
 
 struct amdgpu_atif {
+	acpi_handle handle;
+
 	struct amdgpu_atif_notifications notifications;
 	struct amdgpu_atif_functions functions;
 	struct amdgpu_atif_notification_cfg notification_cfg;
@@ -83,8 +85,9 @@ struct amdgpu_atif {
  * Executes the requested ATIF function (all asics).
  * Returns a pointer to the acpi output buffer.
  */
-static union acpi_object *amdgpu_atif_call(acpi_handle handle, int function,
-		struct acpi_buffer *params)
+static union acpi_object *amdgpu_atif_call(struct amdgpu_atif *atif,
+					   int function,
+					   struct acpi_buffer *params)
 {
 	acpi_status status;
 	union acpi_object atif_arg_elements[2];
@@ -107,7 +110,8 @@ static union acpi_object *amdgpu_atif_call(acpi_handle handle, int function,
 		atif_arg_elements[1].integer.value = 0;
 	}
 
-	status = acpi_evaluate_object(handle, "ATIF", &atif_arg, &buffer);
+	status = acpi_evaluate_object(atif->handle, NULL, &atif_arg,
+				      &buffer);
 
 	/* Fail only if calling the method fails and ATIF is supported */
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
@@ -178,15 +182,14 @@ static void amdgpu_atif_parse_functions(struct amdgpu_atif_functions *f, u32 mas
  * (all asics).
  * returns 0 on success, error on failure.
  */
-static int amdgpu_atif_verify_interface(acpi_handle handle,
-		struct amdgpu_atif *atif)
+static int amdgpu_atif_verify_interface(struct amdgpu_atif *atif)
 {
 	union acpi_object *info;
 	struct atif_verify_interface output;
 	size_t size;
 	int err = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_VERIFY_INTERFACE, NULL);
 	if (!info)
 		return -EIO;
 
@@ -213,6 +216,35 @@ out:
 	return err;
 }
 
+static acpi_handle amdgpu_atif_probe_handle(acpi_handle dhandle)
+{
+	acpi_handle handle = NULL;
+	char acpi_method_name[255] = { 0 };
+	struct acpi_buffer buffer = { sizeof(acpi_method_name), acpi_method_name };
+	acpi_status status;
+
+	/* For PX/HG systems, ATIF and ATPX are in the iGPU's namespace, on dGPU only
+	 * systems, ATIF is in the dGPU's namespace.
+	 */
+	status = acpi_get_handle(dhandle, "ATIF", &handle);
+	if (ACPI_SUCCESS(status))
+		goto out;
+
+	if (amdgpu_has_atpx()) {
+		status = acpi_get_handle(amdgpu_atpx_get_dhandle(), "ATIF",
+					 &handle);
+		if (ACPI_SUCCESS(status))
+			goto out;
+	}
+
+	DRM_DEBUG_DRIVER("No ATIF handle found\n");
+	return NULL;
+out:
+	acpi_get_name(handle, ACPI_FULL_PATHNAME, &buffer);
+	DRM_DEBUG_DRIVER("Found ATIF handle %s\n", acpi_method_name);
+	return handle;
+}
+
 /**
  * amdgpu_atif_get_notification_params - determine notify configuration
  *
@@ -225,15 +257,16 @@ out:
  * where n is specified in the result if a notifier is used.
  * Returns 0 on success, error on failure.
  */
-static int amdgpu_atif_get_notification_params(acpi_handle handle,
-		struct amdgpu_atif_notification_cfg *n)
+static int amdgpu_atif_get_notification_params(struct amdgpu_atif *atif)
 {
 	union acpi_object *info;
+	struct amdgpu_atif_notification_cfg *n = &atif->notification_cfg;
 	struct atif_system_params params;
 	size_t size;
 	int err = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_PARAMETERS,
+				NULL);
 	if (!info) {
 		err = -EIO;
 		goto out;
@@ -287,14 +320,15 @@ out:
  * (all asics).
  * Returns 0 on success, error on failure.
  */
-static int amdgpu_atif_get_sbios_requests(acpi_handle handle,
-		struct atif_sbios_requests *req)
+static int amdgpu_atif_get_sbios_requests(struct amdgpu_atif *atif,
+					  struct atif_sbios_requests *req)
 {
 	union acpi_object *info;
 	size_t size;
 	int count = 0;
 
-	info = amdgpu_atif_call(handle, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS, NULL);
+	info = amdgpu_atif_call(atif, ATIF_FUNCTION_GET_SYSTEM_BIOS_REQUESTS,
+				NULL);
 	if (!info)
 		return -EIO;
 
@@ -327,11 +361,10 @@ out:
  * Returns NOTIFY code
  */
 static int amdgpu_atif_handler(struct amdgpu_device *adev,
-			struct acpi_bus_event *event)
+			       struct acpi_bus_event *event)
 {
 	struct amdgpu_atif *atif = adev->atif;
 	struct atif_sbios_requests req;
-	acpi_handle handle;
 	int count;
 
 	DRM_DEBUG_DRIVER("event, device_class = %s, type = %#x\n",
@@ -347,8 +380,7 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 		return NOTIFY_DONE;
 
 	/* Check pending SBIOS requests */
-	handle = ACPI_HANDLE(&adev->pdev->dev);
-	count = amdgpu_atif_get_sbios_requests(handle, &req);
+	count = amdgpu_atif_get_sbios_requests(atif, &req);
 
 	if (count <= 0)
 		return NOTIFY_DONE;
@@ -679,7 +711,7 @@ static int amdgpu_acpi_event(struct notifier_block *nb,
  */
 int amdgpu_acpi_init(struct amdgpu_device *adev)
 {
-	acpi_handle handle;
+	acpi_handle handle, atif_handle;
 	struct amdgpu_atif *atif;
 	struct amdgpu_atcs *atcs = &adev->atcs;
 	int ret;
@@ -696,14 +728,20 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 		DRM_DEBUG_DRIVER("Call to ATCS verify_interface failed: %d\n", ret);
 	}
 
-	/* Call the ATIF method */
+	/* Probe for ATIF, and initialize it if found */
+	atif_handle = amdgpu_atif_probe_handle(handle);
+	if (!atif_handle)
+		goto out;
+
 	atif = kzalloc(sizeof(*atif), GFP_KERNEL);
 	if (!atif) {
 		DRM_WARN("Not enough memory to initialize ATIF\n");
 		goto out;
 	}
+	atif->handle = atif_handle;
 
-	ret = amdgpu_atif_verify_interface(handle, atif);
+	/* Call the ATIF method */
+	ret = amdgpu_atif_verify_interface(atif);
 	if (ret) {
 		DRM_DEBUG_DRIVER("Call to ATIF verify_interface failed: %d\n", ret);
 		kfree(atif);
@@ -739,8 +777,7 @@ int amdgpu_acpi_init(struct amdgpu_device *adev)
 	}
 
 	if (atif->functions.system_params) {
-		ret = amdgpu_atif_get_notification_params(handle,
-				&atif->notification_cfg);
+		ret = amdgpu_atif_get_notification_params(atif);
 		if (ret) {
 			DRM_DEBUG_DRIVER("Call to GET_SYSTEM_PARAMS failed: %d\n",
 					ret);
-- 
cgit v1.2.3


From 9735bf1930e658b074d72ea46bb317ad12483692 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Fri, 15 Jun 2018 16:37:03 +0200
Subject: drm/amdgpu: Use gmc_vram_full_visible in vram_mgr_bo_invisible_size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index b6333f92ba45..f7a4bd5885a3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -112,7 +112,7 @@ u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo)
 	unsigned pages = mem->num_pages;
 	u64 usage = 0;
 
-	if (adev->gmc.visible_vram_size == adev->gmc.real_vram_size)
+	if (amdgpu_gmc_vram_full_visible(&adev->gmc))
 		return 0;
 
 	if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
-- 
cgit v1.2.3


From 463d2fe85b0eacb3760febe100994d4eb8fedde9 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Fri, 22 Jun 2018 18:54:03 +0200
Subject: drm/amdgpu: Add AMDGPU_GPU_PAGES_IN_CPU_PAGE define
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To hopefully make the code dealing with GPU vs CPU pages a little
clearer.

Suggested-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c | 8 ++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h | 2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c   | 8 ++++----
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index dd11b7313ca0..36113cb60ca2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -234,7 +234,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 	}
 
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
-	p = t / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+	p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 	for (i = 0; i < pages; i++, p++) {
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 		adev->gart.pages[p] = NULL;
@@ -243,7 +243,7 @@ int amdgpu_gart_unbind(struct amdgpu_device *adev, uint64_t offset,
 		if (!adev->gart.ptr)
 			continue;
 
-		for (j = 0; j < (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE); j++, t++) {
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
 			amdgpu_gmc_set_pte_pde(adev, adev->gart.ptr,
 					       t, page_base, flags);
 			page_base += AMDGPU_GPU_PAGE_SIZE;
@@ -282,7 +282,7 @@ int amdgpu_gart_map(struct amdgpu_device *adev, uint64_t offset,
 
 	for (i = 0; i < pages; i++) {
 		page_base = dma_addr[i];
-		for (j = 0; j < (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE); j++, t++) {
+		for (j = 0; j < AMDGPU_GPU_PAGES_IN_CPU_PAGE; j++, t++) {
 			amdgpu_gmc_set_pte_pde(adev, dst, t, page_base, flags);
 			page_base += AMDGPU_GPU_PAGE_SIZE;
 		}
@@ -319,7 +319,7 @@ int amdgpu_gart_bind(struct amdgpu_device *adev, uint64_t offset,
 
 #ifdef CONFIG_DRM_AMDGPU_GART_DEBUGFS
 	t = offset / AMDGPU_GPU_PAGE_SIZE;
-	p = t / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+	p = t / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 	for (i = 0; i < pages; i++, p++)
 		adev->gart.pages[p] = pagelist ? pagelist[i] : NULL;
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
index 456295c00291..9f9e9dc87da1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.h
@@ -37,6 +37,8 @@ struct amdgpu_bo;
 #define AMDGPU_GPU_PAGE_SHIFT 12
 #define AMDGPU_GPU_PAGE_ALIGN(a) (((a) + AMDGPU_GPU_PAGE_MASK) & ~AMDGPU_GPU_PAGE_MASK)
 
+#define AMDGPU_GPU_PAGES_IN_CPU_PAGE (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE)
+
 struct amdgpu_gart {
 	u64				table_addr;
 	struct amdgpu_bo		*robj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 837066076ccf..712af5c1a5d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1567,7 +1567,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		if (nodes) {
 			addr = nodes->start << PAGE_SHIFT;
 			max_entries = (nodes->size - pfn) *
-				(PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+				AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 		} else {
 			addr = 0;
 			max_entries = S64_MAX;
@@ -1578,7 +1578,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 
 			max_entries = min(max_entries, 16ull * 1024ull);
 			for (count = 1;
-			     count < max_entries / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+			     count < max_entries / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 			     ++count) {
 				uint64_t idx = pfn + count;
 
@@ -1592,7 +1592,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 				dma_addr = pages_addr;
 			} else {
 				addr = pages_addr[pfn];
-				max_entries = count * (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+				max_entries = count * AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 			}
 
 		} else if (flags & AMDGPU_PTE_VALID) {
@@ -1607,7 +1607,7 @@ static int amdgpu_vm_bo_split_mapping(struct amdgpu_device *adev,
 		if (r)
 			return r;
 
-		pfn += (last - start + 1) / (PAGE_SIZE / AMDGPU_GPU_PAGE_SIZE);
+		pfn += (last - start + 1) / AMDGPU_GPU_PAGES_IN_CPU_PAGE;
 		if (nodes && nodes->size == pfn) {
 			pfn = 0;
 			++nodes;
-- 
cgit v1.2.3


From 3f37e29626b0b5dbfcdf964ef2858b36a4c2cd67 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Fri, 29 Jun 2018 11:27:11 +0200
Subject: drm/amdgpu: Remove amdgpu_gem_map_attach target_dev documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The parameter was removed.

Fixes: a19741e5e5a9 "dma_buf: remove device parameter from attach
                     callback v2"
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index b2286bc41aec..df7226ad64b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -191,7 +191,6 @@ error:
 /**
  * amdgpu_gem_map_attach - &dma_buf_ops.attach implementation
  * @dma_buf: shared DMA buffer
- * @target_dev: target device
  * @attach: DMA-buf attachment
  *
  * Makes sure that the shared DMA buffer can be accessed by the target device.
-- 
cgit v1.2.3


From 3413accb3eac9182ee0fc0b350a5f18247d8ac9d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Jun 2018 12:38:53 -0500
Subject: drm/amdgpu: fix swapped emit_ib_size in vce3

The phys and vm versions had the values swapped.

Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 0999c843f623..a71b97519cc0 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -900,7 +900,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_phys_funcs = {
 	.emit_frame_size =
 		4 + /* vce_v3_0_emit_pipeline_sync */
 		6, /* amdgpu_vce_ring_emit_fence x1 no user fence */
-	.emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
+	.emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
 	.emit_ib = amdgpu_vce_ring_emit_ib,
 	.emit_fence = amdgpu_vce_ring_emit_fence,
 	.test_ring = amdgpu_vce_ring_test_ring,
@@ -924,7 +924,7 @@ static const struct amdgpu_ring_funcs vce_v3_0_ring_vm_funcs = {
 		6 + /* vce_v3_0_emit_vm_flush */
 		4 + /* vce_v3_0_emit_pipeline_sync */
 		6 + 6, /* amdgpu_vce_ring_emit_fence x2 vm fence */
-	.emit_ib_size = 4, /* amdgpu_vce_ring_emit_ib */
+	.emit_ib_size = 5, /* vce_v3_0_ring_emit_ib */
 	.emit_ib = vce_v3_0_ring_emit_ib,
 	.emit_vm_flush = vce_v3_0_emit_vm_flush,
 	.emit_pipeline_sync = vce_v3_0_emit_pipeline_sync,
-- 
cgit v1.2.3


From 70eb46db101b55acdf432187800915f72962a564 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Jun 2018 12:44:25 -0500
Subject: drm/amdgpu/pm: fix display count in non-DC path

new_active_crtcs is a bitmask, new_active_crtc_count is the
actual count.

Reviewed-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index a003fd881a89..f1404adc3a90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1959,7 +1959,7 @@ void amdgpu_pm_compute_clocks(struct amdgpu_device *adev)
 		if (!amdgpu_device_has_dc_support(adev)) {
 			mutex_lock(&adev->pm.mutex);
 			amdgpu_dpm_get_active_displays(adev);
-			adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtcs;
+			adev->pm.pm_display_cfg.num_display = adev->pm.dpm.new_active_crtc_count;
 			adev->pm.pm_display_cfg.vrefresh = amdgpu_dpm_get_vrefresh(adev);
 			adev->pm.pm_display_cfg.min_vblank_time = amdgpu_dpm_get_vblank_time(adev);
 			/* we have issues with mclk switching with refresh rates over 120 hz on the non-DC code. */
-- 
cgit v1.2.3


From c9037d44390cc1ef7ec490c63ec8a4ee92a57925 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Jun 2018 12:48:10 -0500
Subject: drm/amdgpu/pp: add missing byte swapping in process_pptables_v1_0.c

Values need to be swapped on big endian.

Reviewed-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
index 35bd9870ab10..4e1fd5393845 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/process_pptables_v1_0.c
@@ -183,10 +183,10 @@ static int get_vddc_lookup_table(
 					ATOM_Tonga_Voltage_Lookup_Record,
 					entries, vddc_lookup_pp_tables, i);
 		record->us_calculated = 0;
-		record->us_vdd = atom_record->usVdd;
-		record->us_cac_low = atom_record->usCACLow;
-		record->us_cac_mid = atom_record->usCACMid;
-		record->us_cac_high = atom_record->usCACHigh;
+		record->us_vdd = le16_to_cpu(atom_record->usVdd);
+		record->us_cac_low = le16_to_cpu(atom_record->usCACLow);
+		record->us_cac_mid = le16_to_cpu(atom_record->usCACMid);
+		record->us_cac_high = le16_to_cpu(atom_record->usCACHigh);
 	}
 
 	*lookup_table = table;
-- 
cgit v1.2.3


From 594c34cc6f31807f23aae5c9cec6dea31d782f90 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Jun 2018 12:51:06 -0500
Subject: drm/amdgpu/pp: fix endian swapping in atomctrl_get_voltage_range

Need to swap before doing arthimetic on the values.

Reviewed-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
index 7047e29755c3..01dc46dc9c8a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/ppatomctrl.c
@@ -1544,14 +1544,14 @@ void atomctrl_get_voltage_range(struct pp_hwmgr *hwmgr, uint32_t *max_vddc,
 		switch (hwmgr->chip_id) {
 		case CHIP_TONGA:
 		case CHIP_FIJI:
-			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMaxVddc/4);
-			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMinVddc/4);
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMaxVddc) / 4;
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_3 *)profile)->ulMinVddc) / 4;
 			return;
 		case CHIP_POLARIS11:
 		case CHIP_POLARIS10:
 		case CHIP_POLARIS12:
-			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMaxVddc/100);
-			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMinVddc/100);
+			*max_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMaxVddc) / 100;
+			*min_vddc = le32_to_cpu(((ATOM_ASIC_PROFILING_INFO_V3_6 *)profile)->ulMinVddc) / 100;
 			return;
 		default:
 			break;
-- 
cgit v1.2.3


From 9861023c29dbc069e49dc85fb21f01da9f75ff06 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Jun 2018 12:52:43 -0500
Subject: drm/amdgpu/pp: fix copy paste typo in smu7_init_dpm_defaults

Should be mclk rather than sclk.

Reviewed-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index de295b7442b7..e5c27d12aa49 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -1578,7 +1578,7 @@ static void smu7_init_dpm_defaults(struct pp_hwmgr *hwmgr)
 	data->current_profile_setting.sclk_up_hyst = 0;
 	data->current_profile_setting.sclk_down_hyst = 100;
 	data->current_profile_setting.sclk_activity = SMU7_SCLK_TARGETACTIVITY_DFLT;
-	data->current_profile_setting.bupdate_sclk = 1;
+	data->current_profile_setting.bupdate_mclk = 1;
 	data->current_profile_setting.mclk_up_hyst = 0;
 	data->current_profile_setting.mclk_down_hyst = 100;
 	data->current_profile_setting.mclk_activity = SMU7_MCLK_TARGETACTIVITY_DFLT;
-- 
cgit v1.2.3


From ed54d954e5c1d8bad453fb86109075b3577152b7 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Jun 2018 13:21:12 -0500
Subject: drm/amdgpu/pp: fix copy paste typo in
 smu7_get_pp_table_entry_callback_func_v1

Should be using PCIELaneLow for the low clock level.

Reviewed-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index e5c27d12aa49..077b79938528 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -3183,7 +3183,7 @@ static int smu7_get_pp_table_entry_callback_func_v1(struct pp_hwmgr *hwmgr,
 	performance_level->pcie_gen = get_pcie_gen_support(data->pcie_gen_cap,
 			state_entry->ucPCIEGenLow);
 	performance_level->pcie_lane = get_pcie_lane_support(data->pcie_lane_cap,
-			state_entry->ucPCIELaneHigh);
+			state_entry->ucPCIELaneLow);
 
 	performance_level = &(smu7_power_state->performance_levels
 			[smu7_power_state->performance_level_count++]);
-- 
cgit v1.2.3


From 1cf0abb6c983d90ec541ebba79934a9c4786df1d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Jun 2018 12:24:10 -0500
Subject: drm/amdgpu/sdma: simplify sdma instance setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the me instance in early init and use that rather than
calculating the instance based on the ring pointer.

Reviewed-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/cik_sdma.c  | 12 ++++++------
 drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c | 12 ++++++------
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c | 14 ++++++--------
 drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 23 +++++++++++------------
 4 files changed, 29 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index a7576255cc30..dbd553a8d584 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -177,9 +177,8 @@ static uint64_t cik_sdma_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-	return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) & 0x3fffc) >> 2;
+	return (RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) & 0x3fffc) >> 2;
 }
 
 /**
@@ -192,9 +191,8 @@ static uint64_t cik_sdma_ring_get_wptr(struct amdgpu_ring *ring)
 static void cik_sdma_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	u32 me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me],
+	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me],
 		       	(lower_32_bits(ring->wptr) << 2) & 0x3fffc);
 }
 
@@ -248,7 +246,7 @@ static void cik_sdma_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 			  SDMA_POLL_REG_MEM_EXTRA_FUNC(3)); /* == */
 	u32 ref_and_mask;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA0_MASK;
 	else
 		ref_and_mask = GPU_HDP_FLUSH_DONE__SDMA1_MASK;
@@ -1290,8 +1288,10 @@ static void cik_sdma_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &cik_sdma_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs cik_sdma_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index c7190c39c4f5..cee4fae76d20 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -202,8 +202,7 @@ static uint64_t sdma_v2_4_ring_get_rptr(struct amdgpu_ring *ring)
 static uint64_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-	u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
+	u32 wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) >> 2;
 
 	return wptr;
 }
@@ -218,9 +217,8 @@ static uint64_t sdma_v2_4_ring_get_wptr(struct amdgpu_ring *ring)
 static void sdma_v2_4_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
-	int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
 
-	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
+	WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me], lower_32_bits(ring->wptr) << 2);
 }
 
 static void sdma_v2_4_ring_insert_nop(struct amdgpu_ring *ring, uint32_t count)
@@ -273,7 +271,7 @@ static void sdma_v2_4_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	u32 ref_and_mask = 0;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
 	else
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@@ -1213,8 +1211,10 @@ static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v2_4_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v2_4_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index aa9ab299fd32..99616dd9594f 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -365,9 +365,7 @@ static uint64_t sdma_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 		/* XXX check if swapping is necessary on BE */
 		wptr = ring->adev->wb.wb[ring->wptr_offs] >> 2;
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
-		wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me]) >> 2;
+		wptr = RREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me]) >> 2;
 	}
 
 	return wptr;
@@ -394,9 +392,7 @@ static void sdma_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 
 		WRITE_ONCE(*wb, (lower_32_bits(ring->wptr) << 2));
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
-		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[me], lower_32_bits(ring->wptr) << 2);
+		WREG32(mmSDMA0_GFX_RB_WPTR + sdma_offsets[ring->me], lower_32_bits(ring->wptr) << 2);
 	}
 }
 
@@ -450,7 +446,7 @@ static void sdma_v3_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 {
 	u32 ref_and_mask = 0;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA0, 1);
 	else
 		ref_and_mask = REG_SET_FIELD(ref_and_mask, GPU_HDP_FLUSH_DONE, SDMA1, 1);
@@ -1655,8 +1651,10 @@ static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v3_0_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v3_0_trap_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index ca53b3fba422..572ca63cf676 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -296,13 +296,12 @@ static uint64_t sdma_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 		DRM_DEBUG("wptr/doorbell before shift == 0x%016llx\n", wptr);
 	} else {
 		u32 lowbit, highbit;
-		int me = (ring == &adev->sdma.instance[0].ring) ? 0 : 1;
 
-		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR)) >> 2;
-		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
+		lowbit = RREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR)) >> 2;
+		highbit = RREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI)) >> 2;
 
 		DRM_DEBUG("wptr [%i]high== 0x%08x low==0x%08x\n",
-				me, highbit, lowbit);
+				ring->me, highbit, lowbit);
 		wptr = highbit;
 		wptr = wptr << 32;
 		wptr |= lowbit;
@@ -339,17 +338,15 @@ static void sdma_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 				ring->doorbell_index, ring->wptr << 2);
 		WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
 	} else {
-		int me = (ring == &ring->adev->sdma.instance[0].ring) ? 0 : 1;
-
 		DRM_DEBUG("Not using doorbell -- "
 				"mmSDMA%i_GFX_RB_WPTR == 0x%08x "
 				"mmSDMA%i_GFX_RB_WPTR_HI == 0x%08x\n",
-				me,
+				ring->me,
 				lower_32_bits(ring->wptr << 2),
-				me,
+				ring->me,
 				upper_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
-		WREG32(sdma_v4_0_get_reg_offset(adev, me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR), lower_32_bits(ring->wptr << 2));
+		WREG32(sdma_v4_0_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI), upper_32_bits(ring->wptr << 2));
 	}
 }
 
@@ -430,7 +427,7 @@ static void sdma_v4_0_ring_emit_hdp_flush(struct amdgpu_ring *ring)
 	u32 ref_and_mask = 0;
 	const struct nbio_hdp_flush_reg *nbio_hf_reg = adev->nbio_funcs->hdp_flush_reg;
 
-	if (ring == &ring->adev->sdma.instance[0].ring)
+	if (ring->me == 0)
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma0;
 	else
 		ref_and_mask = nbio_hf_reg->ref_and_mask_sdma1;
@@ -1651,8 +1648,10 @@ static void sdma_v4_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->sdma.num_instances; i++)
+	for (i = 0; i < adev->sdma.num_instances; i++) {
 		adev->sdma.instance[i].ring.funcs = &sdma_v4_0_ring_funcs;
+		adev->sdma.instance[i].ring.me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs sdma_v4_0_trap_irq_funcs = {
-- 
cgit v1.2.3


From 5d4af988f39052b77f8fdd9ed5cb61ca1645a3a6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Jun 2018 12:41:21 -0500
Subject: drm/amdgpu/vce: simplify vce instance setup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Set the me instance in early init and use that rather than
calculating the instance based on the ring pointer.

Reviewed-by: James Zhu <James.Zhu@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vce_v2_0.c | 10 ++++++----
 drivers/gpu/drm/amd/amdgpu/vce_v3_0.c | 20 ++++++++++++--------
 drivers/gpu/drm/amd/amdgpu/vce_v4_0.c | 16 +++++++++-------
 3 files changed, 27 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index 47f70827195b..d48e877b682e 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -56,7 +56,7 @@ static uint64_t vce_v2_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(mmVCE_RB_RPTR);
 	else
 		return RREG32(mmVCE_RB_RPTR2);
@@ -73,7 +73,7 @@ static uint64_t vce_v2_0_ring_get_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(mmVCE_RB_WPTR);
 	else
 		return RREG32(mmVCE_RB_WPTR2);
@@ -90,7 +90,7 @@ static void vce_v2_0_ring_set_wptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
 	else
 		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
@@ -627,8 +627,10 @@ static void vce_v2_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vce.num_rings; i++)
+	for (i = 0; i < adev->vce.num_rings; i++) {
 		adev->vce.ring[i].funcs = &vce_v2_0_ring_funcs;
+		adev->vce.ring[i].me = i;
+	}
 }
 
 static const struct amdgpu_irq_src_funcs vce_v2_0_irq_funcs = {
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index a71b97519cc0..99604d0262ad 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -86,9 +86,9 @@ static uint64_t vce_v3_0_ring_get_rptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		v = RREG32(mmVCE_RB_RPTR);
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		v = RREG32(mmVCE_RB_RPTR2);
 	else
 		v = RREG32(mmVCE_RB_RPTR3);
@@ -118,9 +118,9 @@ static uint64_t vce_v3_0_ring_get_wptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		v = RREG32(mmVCE_RB_WPTR);
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		v = RREG32(mmVCE_RB_WPTR2);
 	else
 		v = RREG32(mmVCE_RB_WPTR3);
@@ -149,9 +149,9 @@ static void vce_v3_0_ring_set_wptr(struct amdgpu_ring *ring)
 	else if (adev->vce.harvest_config == AMDGPU_VCE_HARVEST_VCE0)
 		WREG32(mmGRBM_GFX_INDEX, GET_VCE_INSTANCE(1));
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(mmVCE_RB_WPTR, lower_32_bits(ring->wptr));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		WREG32(mmVCE_RB_WPTR2, lower_32_bits(ring->wptr));
 	else
 		WREG32(mmVCE_RB_WPTR3, lower_32_bits(ring->wptr));
@@ -942,12 +942,16 @@ static void vce_v3_0_set_ring_funcs(struct amdgpu_device *adev)
 	int i;
 
 	if (adev->asic_type >= CHIP_STONEY) {
-		for (i = 0; i < adev->vce.num_rings; i++)
+		for (i = 0; i < adev->vce.num_rings; i++) {
 			adev->vce.ring[i].funcs = &vce_v3_0_ring_vm_funcs;
+			adev->vce.ring[i].me = i;
+		}
 		DRM_INFO("VCE enabled in VM mode\n");
 	} else {
-		for (i = 0; i < adev->vce.num_rings; i++)
+		for (i = 0; i < adev->vce.num_rings; i++) {
 			adev->vce.ring[i].funcs = &vce_v3_0_ring_phys_funcs;
+			adev->vce.ring[i].me = i;
+		}
 		DRM_INFO("VCE enabled in physical mode\n");
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 8fd1b742985a..575bf9709389 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -60,9 +60,9 @@ static uint64_t vce_v4_0_ring_get_rptr(struct amdgpu_ring *ring)
 {
 	struct amdgpu_device *adev = ring->adev;
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR2));
 	else
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_RPTR3));
@@ -82,9 +82,9 @@ static uint64_t vce_v4_0_ring_get_wptr(struct amdgpu_ring *ring)
 	if (ring->use_doorbell)
 		return adev->wb.wb[ring->wptr_offs];
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR2));
 	else
 		return RREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR3));
@@ -108,10 +108,10 @@ static void vce_v4_0_ring_set_wptr(struct amdgpu_ring *ring)
 		return;
 	}
 
-	if (ring == &adev->vce.ring[0])
+	if (ring->me == 0)
 		WREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR),
 			lower_32_bits(ring->wptr));
-	else if (ring == &adev->vce.ring[1])
+	else if (ring->me == 1)
 		WREG32(SOC15_REG_OFFSET(VCE, 0, mmVCE_RB_WPTR2),
 			lower_32_bits(ring->wptr));
 	else
@@ -1088,8 +1088,10 @@ static void vce_v4_0_set_ring_funcs(struct amdgpu_device *adev)
 {
 	int i;
 
-	for (i = 0; i < adev->vce.num_rings; i++)
+	for (i = 0; i < adev->vce.num_rings; i++) {
 		adev->vce.ring[i].funcs = &vce_v4_0_ring_vm_funcs;
+		adev->vce.ring[i].me = i;
+	}
 	DRM_INFO("VCE enabled in VM mode\n");
 }
 
-- 
cgit v1.2.3


From c3c18309c8319ab4600830bc010d916cb4e529de Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <contact@tzimmermann.org>
Date: Thu, 28 Jun 2018 16:10:25 +0200
Subject: drm/amd: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <contact@tzimmermann.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index dcdc97d6dc44..963578c34c47 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -665,7 +665,7 @@ retry_init:
 err_pci:
 	pci_disable_device(pdev);
 err_free:
-	drm_dev_unref(dev);
+	drm_dev_put(dev);
 	return ret;
 }
 
@@ -675,7 +675,7 @@ amdgpu_pci_remove(struct pci_dev *pdev)
 	struct drm_device *dev = pci_get_drvdata(pdev);
 
 	drm_dev_unregister(dev);
-	drm_dev_unref(dev);
+	drm_dev_put(dev);
 	pci_disable_device(pdev);
 	pci_set_drvdata(pdev, NULL);
 }
-- 
cgit v1.2.3


From 9f87830f61e79d5e2ae2529cd225cb123f7742b2 Mon Sep 17 00:00:00 2001
From: "Dirk Hohndel (VMware)" <dirk@hohndel.org>
Date: Mon, 7 May 2018 01:16:20 +0200
Subject: drm/amd: add SPDX identifier and clarify license

This is dual licensed under GPL-2.0 or MIT.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dirk Hohndel (VMware) <dirk@hohndel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index e3878256743a..57b14dccd8e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright 2009 VMware, Inc.
  *
-- 
cgit v1.2.3


From da5fd66c0eb79e01501578bfc69352cc5e2e979d Mon Sep 17 00:00:00 2001
From: "Dirk Hohndel (VMware)" <dirk@hohndel.org>
Date: Mon, 7 May 2018 01:16:23 +0200
Subject: drm/radeon: add SPDX identifier and clarify license

This is dual licensed under GPL-2.0 or MIT.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Dirk Hohndel (VMware) <dirk@hohndel.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_test.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 48f4b273e316..0c7f228db6e3 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0 OR MIT
 /*
  * Copyright 2009 VMware, Inc.
  *
-- 
cgit v1.2.3


From f8ddb39a15100076884a625e97c91f3578c686f5 Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Thu, 28 Jun 2018 14:38:21 +0800
Subject: drm/amdgpu: fix the wrong type of gem object creation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We still use legacy type of gem_object_create, it should update to ttm_bo_type
now.

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c  | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index bc5fd8ebab5d..811c62927c38 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -146,7 +146,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 				       AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED |
 				       AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS |
 				       AMDGPU_GEM_CREATE_VRAM_CLEARED,
-				       true, NULL, &gobj);
+				       ttm_bo_type_kernel, NULL, &gobj);
 	if (ret) {
 		pr_err("failed to allocate framebuffer (%d)\n", aligned_size);
 		return -ENOMEM;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index 89743cdc1c2c..bcbdcf997d20 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -265,7 +265,7 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
 
 	r = amdgpu_gem_object_create(adev, size, args->in.alignment,
 				     (u32)(0xffffffff & args->in.domains),
-				     flags, false, resv, &gobj);
+				     flags, ttm_bo_type_device, resv, &gobj);
 	if (flags & AMDGPU_GEM_CREATE_VM_ALWAYS_VALID) {
 		if (!r) {
 			struct amdgpu_bo *abo = gem_to_amdgpu_bo(gobj);
@@ -317,7 +317,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 
 	/* create a gem object to contain this object in */
 	r = amdgpu_gem_object_create(adev, args->size, 0, AMDGPU_GEM_DOMAIN_CPU,
-				     0, 0, NULL, &gobj);
+				     0, ttm_bo_type_device, NULL, &gobj);
 	if (r)
 		return r;
 
@@ -766,7 +766,7 @@ int amdgpu_mode_dumb_create(struct drm_file *file_priv,
 				amdgpu_display_supported_domains(adev));
 	r = amdgpu_gem_object_create(adev, args->size, 0, domain,
 				     AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED,
-				     false, NULL, &gobj);
+				     ttm_bo_type_device, NULL, &gobj);
 	if (r)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From afb1436c7b44ab928e6369a4d48e3abb8215241e Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 28 Jun 2018 12:32:27 -0500
Subject: drm/amdgpu: update uvd_v6_0_ring_vm_funcs to use new nop packet

Was missed when updating the uvd 6 module.

Fixes: 1aac3c9180 (drm/amdgpu: fix insert nop for UVD6 ring)
Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 1df1c6115341..8ee1c2eaaa14 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -1569,7 +1569,6 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_phys_funcs = {
 static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.type = AMDGPU_RING_TYPE_UVD,
 	.align_mask = 0xf,
-	.nop = PACKET0(mmUVD_NO_OP, 0),
 	.support_64bit_ptrs = false,
 	.get_rptr = uvd_v6_0_ring_get_rptr,
 	.get_wptr = uvd_v6_0_ring_get_wptr,
@@ -1587,7 +1586,7 @@ static const struct amdgpu_ring_funcs uvd_v6_0_ring_vm_funcs = {
 	.emit_hdp_flush = uvd_v6_0_ring_emit_hdp_flush,
 	.test_ring = uvd_v6_0_ring_test_ring,
 	.test_ib = amdgpu_uvd_ring_test_ib,
-	.insert_nop = amdgpu_ring_insert_nop,
+	.insert_nop = uvd_v6_0_ring_insert_nop,
 	.pad_ib = amdgpu_ring_generic_pad_ib,
 	.begin_use = amdgpu_uvd_ring_begin_use,
 	.end_use = amdgpu_uvd_ring_end_use,
-- 
cgit v1.2.3


From 23ec3d1479fd79658cd52c47618d8ddd2f32550b Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Mon, 18 Jun 2018 18:15:15 +0800
Subject: drm/amd/pp: Convert clock unit to KHz as defined

Convert clock unit 10KHz to KHz as the data sturct defined.
e.g.
struct pp_clock_with_latency {
	uint32_t clocks_in_khz;
	uint32_t latency_in_us;
};
Meanwhile revert the same conversion in display side.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c   | 18 +++++-------
 drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c  |  4 +--
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 34 ++++++++++------------
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 20 ++++++-------
 4 files changed, 34 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index cf92d7a24f33..596d49d7f919 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -203,8 +203,7 @@ static void pp_to_dc_clock_levels(
 
 	for (i = 0; i < dc_clks->num_levels; i++) {
 		DRM_INFO("DM_PPLIB:\t %d\n", pp_clks->clock[i]);
-		/* translate 10kHz to kHz */
-		dc_clks->clocks_in_khz[i] = pp_clks->clock[i] * 10;
+		dc_clks->clocks_in_khz[i] = pp_clks->clock[i];
 	}
 }
 
@@ -229,9 +228,8 @@ static void pp_to_dc_clock_levels_with_latency(
 			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
 
 	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_DEBUG("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
-		/* translate 10kHz to kHz */
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
+		DRM_DEBUG("DM_PPLIB:\t %d in kHz\n", pp_clks->data[i].clocks_in_khz);
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
 		clk_level_info->data[i].latency_in_us = pp_clks->data[i].latency_in_us;
 	}
 }
@@ -257,9 +255,8 @@ static void pp_to_dc_clock_levels_with_voltage(
 			DC_DECODE_PP_CLOCK_TYPE(dc_clk_type));
 
 	for (i = 0; i < clk_level_info->num_levels; i++) {
-		DRM_INFO("DM_PPLIB:\t %d in 10kHz\n", pp_clks->data[i].clocks_in_khz);
-		/* translate 10kHz to kHz */
-		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz * 10;
+		DRM_INFO("DM_PPLIB:\t %d in kHz\n", pp_clks->data[i].clocks_in_khz);
+		clk_level_info->data[i].clocks_in_khz = pp_clks->data[i].clocks_in_khz;
 		clk_level_info->data[i].voltage_in_mv = pp_clks->data[i].voltage_in_mv;
 	}
 }
@@ -434,9 +431,8 @@ bool dm_pp_get_static_clocks(
 		return false;
 
 	static_clk_info->max_clocks_state = pp_clk_info.max_clocks_state;
-	/* translate 10kHz to kHz */
-	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock * 10;
-	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock * 10;
+	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock;
+	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock;
 
 	return true;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 0bbf11d464dd..07cc98c69c7d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -993,7 +993,7 @@ static int smu10_get_clock_by_type_with_latency(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = latency_required ?
 						smu10_get_mem_latency(hwmgr,
 						pclk_vol_table->entries[i].clk) :
@@ -1044,7 +1044,7 @@ static int smu10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 
 	clocks->num_levels = 0;
 	for (i = 0; i < pclk_vol_table->count; i++) {
-		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = pclk_vol_table->entries[i].clk  * 10;
 		clocks->data[i].voltage_in_mv = pclk_vol_table->entries[i].vol;
 		clocks->num_levels++;
 	}
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 3b8d36df52e9..37c2e5c15d62 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -4064,10 +4064,11 @@ static void vega10_get_sclks(struct pp_hwmgr *hwmgr,
 			table_info->vdd_dep_on_sclk;
 	uint32_t i;
 
+	clocks->num_levels = 0;
 	for (i = 0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].clk) {
 			clocks->data[clocks->num_levels].clocks_in_khz =
-					dep_table->entries[i].clk;
+					dep_table->entries[i].clk * 10;
 			clocks->num_levels++;
 		}
 	}
@@ -4094,26 +4095,23 @@ static void vega10_get_memclocks(struct pp_hwmgr *hwmgr,
 	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table =
 			table_info->vdd_dep_on_mclk;
 	struct vega10_hwmgr *data = hwmgr->backend;
+	uint32_t j = 0;
 	uint32_t i;
 
-	clocks->num_levels = 0;
-	data->mclk_latency_table.count = 0;
-
 	for (i = 0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].clk) {
-			clocks->data[clocks->num_levels].clocks_in_khz =
-			data->mclk_latency_table.entries
-			[data->mclk_latency_table.count].frequency =
-					dep_table->entries[i].clk;
-			clocks->data[clocks->num_levels].latency_in_us =
-			data->mclk_latency_table.entries
-			[data->mclk_latency_table.count].latency =
-					vega10_get_mem_latency(hwmgr,
-						dep_table->entries[i].clk);
-			clocks->num_levels++;
-			data->mclk_latency_table.count++;
+			clocks->data[j].clocks_in_khz =
+						dep_table->entries[i].clk * 10;
+			data->mclk_latency_table.entries[j].frequency =
+							dep_table->entries[i].clk;
+			clocks->data[j].latency_in_us =
+				data->mclk_latency_table.entries[j].latency =
+						vega10_get_mem_latency(hwmgr,
+							dep_table->entries[i].clk);
+			j++;
 		}
 	}
+	clocks->num_levels = data->mclk_latency_table.count = j;
 }
 
 static void vega10_get_dcefclocks(struct pp_hwmgr *hwmgr,
@@ -4126,7 +4124,7 @@ static void vega10_get_dcefclocks(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = 0;
 		clocks->num_levels++;
 	}
@@ -4142,7 +4140,7 @@ static void vega10_get_socclocks(struct pp_hwmgr *hwmgr,
 	uint32_t i;
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk * 10;
 		clocks->data[i].latency_in_us = 0;
 		clocks->num_levels++;
 	}
@@ -4202,7 +4200,7 @@ static int vega10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 	}
 
 	for (i = 0; i < dep_table->count; i++) {
-		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk;
+		clocks->data[i].clocks_in_khz = dep_table->entries[i].clk  * 10;
 		clocks->data[i].voltage_in_mv = (uint32_t)(table_info->vddc_lookup_table->
 				entries[dep_table->entries[i].vddInd].us_vdd);
 		clocks->num_levels++;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index a86777954ea7..4cf257043a2c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1645,7 +1645,7 @@ static int vega12_get_sclks(struct pp_hwmgr *hwmgr,
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1676,10 +1676,8 @@ static int vega12_get_memclocks(struct pp_hwmgr *hwmgr,
 		MAX_NUM_CLOCKS : dpm_table->count;
 
 	for (i = 0; i < ucount; i++) {
-		clocks->data[i].clocks_in_khz =
-			data->mclk_latency_table.entries[i].frequency =
-			dpm_table->dpm_levels[i].value * 100;
-
+		clocks->data[i].clocks_in_khz = dpm_table->dpm_levels[i].value * 1000;
+		data->mclk_latency_table.entries[i].frequency = dpm_table->dpm_levels[i].value * 100;
 		clocks->data[i].latency_in_us =
 			data->mclk_latency_table.entries[i].latency =
 			vega12_get_mem_latency(hwmgr, dpm_table->dpm_levels[i].value);
@@ -1708,7 +1706,7 @@ static int vega12_get_dcefclocks(struct pp_hwmgr *hwmgr,
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1736,7 +1734,7 @@ static int vega12_get_socclocks(struct pp_hwmgr *hwmgr,
 
 	for (i = 0; i < ucount; i++) {
 		clocks->data[i].clocks_in_khz =
-			dpm_table->dpm_levels[i].value * 100;
+			dpm_table->dpm_levels[i].value * 1000;
 
 		clocks->data[i].latency_in_us = 0;
 	}
@@ -1918,8 +1916,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
-				i, clocks.data[i].clocks_in_khz / 100,
-				(clocks.data[i].clocks_in_khz == now) ? "*" : "");
+				i, clocks.data[i].clocks_in_khz / 1000,
+				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
 		break;
 
 	case PP_MCLK:
@@ -1934,8 +1932,8 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 				return -1);
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
-				i, clocks.data[i].clocks_in_khz / 100,
-				(clocks.data[i].clocks_in_khz == now) ? "*" : "");
+				i, clocks.data[i].clocks_in_khz / 1000,
+				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
 		break;
 
 	case PP_PCIE:
-- 
cgit v1.2.3


From 6eb9d6030479c5e079a1374941b77ac205b10912 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Mon, 18 Jun 2018 18:49:07 +0800
Subject: drm/amd/pp: Memory Latency is always 25us on Vega10

For HBM, 25us latency is enough for memory clock switch.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 23 ++--------------------
 1 file changed, 2 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 37c2e5c15d62..7fdd9ede96c7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -55,12 +55,6 @@
 
 static const uint32_t channel_number[] = {1, 2, 0, 4, 0, 8, 0, 16, 2};
 
-#define MEM_FREQ_LOW_LATENCY        25000
-#define MEM_FREQ_HIGH_LATENCY       80000
-#define MEM_LATENCY_HIGH            245
-#define MEM_LATENCY_LOW             35
-#define MEM_LATENCY_ERR             0xFFFF
-
 #define mmDF_CS_AON0_DramBaseAddress0                                                                  0x0044
 #define mmDF_CS_AON0_DramBaseAddress0_BASE_IDX                                                         0
 
@@ -4075,18 +4069,6 @@ static void vega10_get_sclks(struct pp_hwmgr *hwmgr,
 
 }
 
-static uint32_t vega10_get_mem_latency(struct pp_hwmgr *hwmgr,
-		uint32_t clock)
-{
-	if (clock >= MEM_FREQ_LOW_LATENCY &&
-			clock < MEM_FREQ_HIGH_LATENCY)
-		return MEM_LATENCY_HIGH;
-	else if (clock >= MEM_FREQ_HIGH_LATENCY)
-		return MEM_LATENCY_LOW;
-	else
-		return MEM_LATENCY_ERR;
-}
-
 static void vega10_get_memclocks(struct pp_hwmgr *hwmgr,
 		struct pp_clock_levels_with_latency *clocks)
 {
@@ -4100,14 +4082,13 @@ static void vega10_get_memclocks(struct pp_hwmgr *hwmgr,
 
 	for (i = 0; i < dep_table->count; i++) {
 		if (dep_table->entries[i].clk) {
+
 			clocks->data[j].clocks_in_khz =
 						dep_table->entries[i].clk * 10;
 			data->mclk_latency_table.entries[j].frequency =
 							dep_table->entries[i].clk;
 			clocks->data[j].latency_in_us =
-				data->mclk_latency_table.entries[j].latency =
-						vega10_get_mem_latency(hwmgr,
-							dep_table->entries[i].clk);
+				data->mclk_latency_table.entries[j].latency = 25;
 			j++;
 		}
 	}
-- 
cgit v1.2.3


From 7d8d968dac88a98bd1d4503a020e8b114672611e Mon Sep 17 00:00:00 2001
From: rex zhu <rex.zhu@amd.com>
Date: Thu, 28 Jun 2018 13:55:46 +0800
Subject: drm/amd/pp: Switch the tolerable latency for display

Select the lowest MCLK frequency that is within
the tolerable latency defined in DISPALY

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 7fdd9ede96c7..e5b3abffefb6 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3217,7 +3217,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
 		/* Find the lowest MCLK frequency that is within
 		 * the tolerable latency defined in DAL
 		 */
-		latency = 0;
+		latency = hwmgr->display_config->dce_tolerable_mclk_in_active_latency;
 		for (i = 0; i < data->mclk_latency_table.count; i++) {
 			if ((data->mclk_latency_table.entries[i].latency <= latency) &&
 				(data->mclk_latency_table.entries[i].frequency >=
-- 
cgit v1.2.3


From 3180fb676d7fd38a7c1effa2e5d9265779473c23 Mon Sep 17 00:00:00 2001
From: rex zhu <rex.zhu@amd.com>
Date: Mon, 2 Jul 2018 14:55:43 +0800
Subject: drm/amd/display: Notify powerplay the min_dcef clock

powerplay can notify smu to recalculates the maximum deep-sleep
divider display allowed.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 596d49d7f919..2e801bab5a78 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -71,6 +71,11 @@ bool dm_pp_apply_display_requirements(
 		adev->pm.pm_display_cfg.min_mem_set_clock =
 				pp_display_cfg->min_memory_clock_khz/10;
 
+		adev->pm.pm_display_cfg.min_dcef_deep_sleep_set_clk =
+				pp_display_cfg->min_engine_clock_deep_sleep_khz/10;
+		adev->pm.pm_display_cfg.min_dcef_set_clk =
+				pp_display_cfg->min_dcfclock_khz/10;
+
 		adev->pm.pm_display_cfg.multi_monitor_in_sync =
 				pp_display_cfg->all_displays_in_sync;
 		adev->pm.pm_display_cfg.min_vblank_time =
-- 
cgit v1.2.3


From d4d5eace210d3676202153c19e473aeb51a81909 Mon Sep 17 00:00:00 2001
From: rex zhu <rex.zhu@amd.com>
Date: Mon, 2 Jul 2018 16:20:56 +0800
Subject: drm/amd/display: Notify powerplay the display controller id

powerplay can recalculate the number of active display

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 2e801bab5a78..81845116cdcc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -41,6 +41,7 @@ bool dm_pp_apply_display_requirements(
 		const struct dm_pp_display_configuration *pp_display_cfg)
 {
 	struct amdgpu_device *adev = ctx->driver_context;
+	int i;
 
 	if (adev->pm.dpm_enabled) {
 
@@ -95,6 +96,12 @@ bool dm_pp_apply_display_requirements(
 		adev->pm.pm_display_cfg.crossfire_display_index = -1;
 		adev->pm.pm_display_cfg.min_bus_bandwidth = 0;
 
+		for (i = 0; i < pp_display_cfg->display_count; i++) {
+			const struct dm_pp_single_disp_config *dc_cfg =
+						&pp_display_cfg->disp_configs[i];
+			adev->pm.pm_display_cfg.displays[i].controller_id = dc_cfg->pipe_idx + 1;
+		}
+
 		/* TODO: complete implementation of
 		 * pp_display_configuration_change().
 		 * Follow example of:
-- 
cgit v1.2.3


From 99c5e27d3368eb92476f47530355a6f25bf486e8 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Fri, 22 Jun 2018 18:26:52 +0800
Subject: drm/amd/pp: Refine the interface exported to display

use void * as function parameter type in order for extension.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/kgd_pp_interface.h        | 3 +--
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c         | 6 +++---
 drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c | 4 ++--
 drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c     | 3 ++-
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c    | 3 ++-
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c    | 3 ++-
 drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h   | 2 +-
 drivers/gpu/drm/amd/powerplay/inc/hwmgr.h             | 3 +--
 8 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 4535756428f9..99ee3edd1609 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -192,7 +192,6 @@ struct amd_pp_simple_clock_info;
 struct amd_pp_display_configuration;
 struct amd_pp_clock_info;
 struct pp_display_clock_request;
-struct pp_wm_sets_with_clock_ranges_soc15;
 struct pp_clock_levels_with_voltage;
 struct pp_clock_levels_with_latency;
 struct amd_pp_clocks;
@@ -261,7 +260,7 @@ struct amd_pm_funcs {
 		enum amd_pp_clock_type type,
 		struct pp_clock_levels_with_voltage *clocks);
 	int (*set_watermarks_for_clocks_ranges)(void *handle,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+						void *clock_ranges);
 	int (*display_clock_voltage_request)(void *handle,
 				struct pp_display_clock_request *clock);
 	int (*get_display_mode_validation_clocks)(void *handle,
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 387a1eb6678d..b72cc644d4e7 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -1096,17 +1096,17 @@ static int pp_get_clock_by_type_with_voltage(void *handle,
 }
 
 static int pp_set_watermarks_for_clocks_ranges(void *handle,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		void *clock_ranges)
 {
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
 
-	if (!hwmgr || !hwmgr->pm_en ||!wm_with_clock_ranges)
+	if (!hwmgr || !hwmgr->pm_en || !clock_ranges)
 		return -EINVAL;
 
 	mutex_lock(&hwmgr->smu_lock);
 	ret = phm_set_watermarks_for_clocks_ranges(hwmgr,
-			wm_with_clock_ranges);
+			clock_ranges);
 	mutex_unlock(&hwmgr->smu_lock);
 
 	return ret;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
index a0bb921fac22..53207e76b0f3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hardwaremanager.c
@@ -435,7 +435,7 @@ int phm_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+					void *clock_ranges)
 {
 	PHM_FUNC_CHECK(hwmgr);
 
@@ -443,7 +443,7 @@ int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 		return -EINVAL;
 
 	return hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges(hwmgr,
-			wm_with_clock_ranges);
+								clock_ranges);
 }
 
 int phm_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 07cc98c69c7d..02fc0bc41e0a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1108,9 +1108,10 @@ static int smu10_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 }
 
 static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		void *clock_ranges)
 {
 	struct smu10_hwmgr *data = hwmgr->backend;
+	struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 	Watermarks_t *table = &(data->water_marks_table);
 	int result = 0;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index e5b3abffefb6..d515eb4fac9f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -4194,9 +4194,10 @@ static int vega10_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 static int vega10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+							void *clock_range)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
+	struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_range;
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
 	int result = 0;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 4cf257043a2c..448014b173d5 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1781,10 +1781,11 @@ static int vega12_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 }
 
 static int vega12_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+							void *clock_ranges)
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
+	struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 	uint32_t i;
 
 	if (!data->registry_data.disable_water_mark &&
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
index a202247c9894..429c9c4322da 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hardwaremanager.h
@@ -455,7 +455,7 @@ extern int phm_get_clock_by_type_with_voltage(struct pp_hwmgr *hwmgr,
 		enum amd_pp_clock_type type,
 		struct pp_clock_levels_with_voltage *clocks);
 extern int phm_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+						void *clock_ranges);
 extern int phm_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
 		struct pp_display_clock_request *clock);
 
diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index 95e29a22e445..b3363f26039a 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -293,8 +293,7 @@ struct pp_hwmgr_func {
 	int (*get_clock_by_type_with_voltage)(struct pp_hwmgr *hwmgr,
 			enum amd_pp_clock_type type,
 			struct pp_clock_levels_with_voltage *clocks);
-	int (*set_watermarks_for_clocks_ranges)(struct pp_hwmgr *hwmgr,
-			struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+	int (*set_watermarks_for_clocks_ranges)(struct pp_hwmgr *hwmgr, void *clock_ranges);
 	int (*display_clock_voltage_request)(struct pp_hwmgr *hwmgr,
 			struct pp_display_clock_request *clock);
 	int (*get_max_high_clocks)(struct pp_hwmgr *hwmgr, struct amd_pp_simple_clock_info *clocks);
-- 
cgit v1.2.3


From 860c15e903327f9af269d2ee7011454624dfcb90 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Wed, 20 Jun 2018 13:36:58 +0800
Subject: drm/amd/pp: Remove duplicate code in vega12_hwmgr.c

use smu_helper function smu_set_watermarks_for_clocks_ranges
in vega12_set_watermarks_for_clocks_ranges.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 43 +---------------------
 1 file changed, 1 insertion(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 448014b173d5..0a090755545d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1786,52 +1786,11 @@ static int vega12_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
 	struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
-	uint32_t i;
 
 	if (!data->registry_data.disable_water_mark &&
 			data->smu_features[GNLD_DPM_DCEFCLK].supported &&
 			data->smu_features[GNLD_DPM_SOCCLK].supported) {
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
-			table->WatermarkRow[WM_DCEFCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_DCEFCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
-		}
-
-		for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
-			table->WatermarkRow[WM_SOCCLK][i].MinClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxClock =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MinUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].MaxUclk =
-				cpu_to_le16((uint16_t)
-				(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
-				100);
-			table->WatermarkRow[WM_SOCCLK][i].WmSetting = (uint8_t)
-					wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
-		}
+		smu_set_watermarks_for_clocks_ranges(table, wm_with_clock_ranges);
 		data->water_marks_bitmap |= WaterMarksExist;
 		data->water_marks_bitmap &= ~WaterMarksLoaded;
 	}
-- 
cgit v1.2.3


From 9fc15f5fc836712b173f04e143b8d77fdded1a37 Mon Sep 17 00:00:00 2001
From: Nicolai Hähnle <nicolai.haehnle@amd.com>
Date: Fri, 29 Jun 2018 13:23:25 +0200
Subject: drm/amdgpu: fix user fence write race condition
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The buffer object backing the user fence is reserved using the non-user
fence, i.e., as soon as the non-user fence is signaled, the user fence
buffer object can be moved or even destroyed.

Therefore, emit the user fence first.

Both fences have the same cache invalidation behavior, so this should
have no user-visible effect.

Signed-off-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 31f8170313b4..ce7739832d29 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -231,6 +231,12 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (ib->flags & AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE)
 		fence_flags |= AMDGPU_FENCE_FLAG_TC_WB_ONLY;
 
+	/* wrap the last IB with fence */
+	if (job && job->uf_addr) {
+		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
+				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
+	}
+
 	r = amdgpu_fence_emit(ring, f, fence_flags);
 	if (r) {
 		dev_err(adev->dev, "failed to emit fence (%d)\n", r);
@@ -243,12 +249,6 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	if (ring->funcs->insert_end)
 		ring->funcs->insert_end(ring);
 
-	/* wrap the last IB with fence */
-	if (job && job->uf_addr) {
-		amdgpu_ring_emit_fence(ring, job->uf_addr, job->uf_sequence,
-				       fence_flags | AMDGPU_FENCE_FLAG_64BIT);
-	}
-
 	if (patch_offset != ~0 && ring->funcs->patch_cond_exec)
 		amdgpu_ring_patch_cond_exec(ring, patch_offset);
 
-- 
cgit v1.2.3


From ce206464e3c7a0936468f0190599d2e6070850f4 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 2 Jul 2018 14:32:28 -0500
Subject: drm/amdgpu: switch firmware path for CIK parts (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use separate firmware path for amdgpu to avoid conflicts
with radeon on CIK parts.

v2: squash in logic simplification (Alex)

Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c |  8 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 10 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 10 ++---
 drivers/gpu/drm/amd/amdgpu/ci_dpm.c     | 10 ++---
 drivers/gpu/drm/amd/amdgpu/cik_sdma.c   | 24 +++++------
 drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c   | 72 ++++++++++++++++-----------------
 drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c   |  9 ++---
 7 files changed, 70 insertions(+), 73 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
index e950730f1933..693ec5ea4950 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -314,17 +314,17 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
 					(adev->pdev->revision == 0x81) ||
 					(adev->pdev->device == 0x665f)) {
 					info->is_kicker = true;
-					strcpy(fw_name, "radeon/bonaire_k_smc.bin");
+					strcpy(fw_name, "amdgpu/bonaire_k_smc.bin");
 				} else {
-					strcpy(fw_name, "radeon/bonaire_smc.bin");
+					strcpy(fw_name, "amdgpu/bonaire_smc.bin");
 				}
 				break;
 			case CHIP_HAWAII:
 				if (adev->pdev->revision == 0x80) {
 					info->is_kicker = true;
-					strcpy(fw_name, "radeon/hawaii_k_smc.bin");
+					strcpy(fw_name, "amdgpu/hawaii_k_smc.bin");
 				} else {
-					strcpy(fw_name, "radeon/hawaii_smc.bin");
+					strcpy(fw_name, "amdgpu/hawaii_smc.bin");
 				}
 				break;
 			case CHIP_TOPAZ:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 0b46ea1c6290..3e70eb61a960 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -53,11 +53,11 @@
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
-#define FIRMWARE_BONAIRE	"radeon/bonaire_uvd.bin"
-#define FIRMWARE_KABINI	"radeon/kabini_uvd.bin"
-#define FIRMWARE_KAVERI	"radeon/kaveri_uvd.bin"
-#define FIRMWARE_HAWAII	"radeon/hawaii_uvd.bin"
-#define FIRMWARE_MULLINS	"radeon/mullins_uvd.bin"
+#define FIRMWARE_BONAIRE	"amdgpu/bonaire_uvd.bin"
+#define FIRMWARE_KABINI	"amdgpu/kabini_uvd.bin"
+#define FIRMWARE_KAVERI	"amdgpu/kaveri_uvd.bin"
+#define FIRMWARE_HAWAII	"amdgpu/hawaii_uvd.bin"
+#define FIRMWARE_MULLINS	"amdgpu/mullins_uvd.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_uvd.bin"
 #define FIRMWARE_CARRIZO	"amdgpu/carrizo_uvd.bin"
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index b0dcdfd85f5b..6ae1ad7e83b3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -40,11 +40,11 @@
 
 /* Firmware Names */
 #ifdef CONFIG_DRM_AMDGPU_CIK
-#define FIRMWARE_BONAIRE	"radeon/bonaire_vce.bin"
-#define FIRMWARE_KABINI	"radeon/kabini_vce.bin"
-#define FIRMWARE_KAVERI	"radeon/kaveri_vce.bin"
-#define FIRMWARE_HAWAII	"radeon/hawaii_vce.bin"
-#define FIRMWARE_MULLINS	"radeon/mullins_vce.bin"
+#define FIRMWARE_BONAIRE	"amdgpu/bonaire_vce.bin"
+#define FIRMWARE_KABINI	"amdgpu/kabini_vce.bin"
+#define FIRMWARE_KAVERI	"amdgpu/kaveri_vce.bin"
+#define FIRMWARE_HAWAII	"amdgpu/hawaii_vce.bin"
+#define FIRMWARE_MULLINS	"amdgpu/mullins_vce.bin"
 #endif
 #define FIRMWARE_TONGA		"amdgpu/tonga_vce.bin"
 #define FIRMWARE_CARRIZO	"amdgpu/carrizo_vce.bin"
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index 7c4ff71e7476..d79ad93b01c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -49,10 +49,10 @@
 #include "gmc/gmc_7_1_d.h"
 #include "gmc/gmc_7_1_sh_mask.h"
 
-MODULE_FIRMWARE("radeon/bonaire_smc.bin");
-MODULE_FIRMWARE("radeon/bonaire_k_smc.bin");
-MODULE_FIRMWARE("radeon/hawaii_smc.bin");
-MODULE_FIRMWARE("radeon/hawaii_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_smc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_smc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_k_smc.bin");
 
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
@@ -5815,7 +5815,7 @@ static int ci_dpm_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
 	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index dbd553a8d584..d0fa2aac2388 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -54,16 +54,16 @@ static void cik_sdma_set_buffer_funcs(struct amdgpu_device *adev);
 static void cik_sdma_set_vm_pte_funcs(struct amdgpu_device *adev);
 static int cik_sdma_soft_reset(void *handle);
 
-MODULE_FIRMWARE("radeon/bonaire_sdma.bin");
-MODULE_FIRMWARE("radeon/bonaire_sdma1.bin");
-MODULE_FIRMWARE("radeon/hawaii_sdma.bin");
-MODULE_FIRMWARE("radeon/hawaii_sdma1.bin");
-MODULE_FIRMWARE("radeon/kaveri_sdma.bin");
-MODULE_FIRMWARE("radeon/kaveri_sdma1.bin");
-MODULE_FIRMWARE("radeon/kabini_sdma.bin");
-MODULE_FIRMWARE("radeon/kabini_sdma1.bin");
-MODULE_FIRMWARE("radeon/mullins_sdma.bin");
-MODULE_FIRMWARE("radeon/mullins_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_sdma.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_sdma.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_sdma.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/kabini_sdma.bin");
+MODULE_FIRMWARE("amdgpu/kabini_sdma1.bin");
+MODULE_FIRMWARE("amdgpu/mullins_sdma.bin");
+MODULE_FIRMWARE("amdgpu/mullins_sdma1.bin");
 
 u32 amdgpu_cik_gpu_check_soft_reset(struct amdgpu_device *adev);
 
@@ -132,9 +132,9 @@ static int cik_sdma_init_microcode(struct amdgpu_device *adev)
 
 	for (i = 0; i < adev->sdma.num_instances; i++) {
 		if (i == 0)
-			snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma.bin", chip_name);
+			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma.bin", chip_name);
 		else
-			snprintf(fw_name, sizeof(fw_name), "radeon/%s_sdma1.bin", chip_name);
+			snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_sdma1.bin", chip_name);
 		err = request_firmware(&adev->sdma.instance[i].fw, fw_name, adev->dev);
 		if (err)
 			goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 42b6144c1fd5..95452c5a9df6 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -57,36 +57,36 @@ static void gfx_v7_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v7_0_set_gds_init(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/bonaire_pfp.bin");
-MODULE_FIRMWARE("radeon/bonaire_me.bin");
-MODULE_FIRMWARE("radeon/bonaire_ce.bin");
-MODULE_FIRMWARE("radeon/bonaire_rlc.bin");
-MODULE_FIRMWARE("radeon/bonaire_mec.bin");
-
-MODULE_FIRMWARE("radeon/hawaii_pfp.bin");
-MODULE_FIRMWARE("radeon/hawaii_me.bin");
-MODULE_FIRMWARE("radeon/hawaii_ce.bin");
-MODULE_FIRMWARE("radeon/hawaii_rlc.bin");
-MODULE_FIRMWARE("radeon/hawaii_mec.bin");
-
-MODULE_FIRMWARE("radeon/kaveri_pfp.bin");
-MODULE_FIRMWARE("radeon/kaveri_me.bin");
-MODULE_FIRMWARE("radeon/kaveri_ce.bin");
-MODULE_FIRMWARE("radeon/kaveri_rlc.bin");
-MODULE_FIRMWARE("radeon/kaveri_mec.bin");
-MODULE_FIRMWARE("radeon/kaveri_mec2.bin");
-
-MODULE_FIRMWARE("radeon/kabini_pfp.bin");
-MODULE_FIRMWARE("radeon/kabini_me.bin");
-MODULE_FIRMWARE("radeon/kabini_ce.bin");
-MODULE_FIRMWARE("radeon/kabini_rlc.bin");
-MODULE_FIRMWARE("radeon/kabini_mec.bin");
-
-MODULE_FIRMWARE("radeon/mullins_pfp.bin");
-MODULE_FIRMWARE("radeon/mullins_me.bin");
-MODULE_FIRMWARE("radeon/mullins_ce.bin");
-MODULE_FIRMWARE("radeon/mullins_rlc.bin");
-MODULE_FIRMWARE("radeon/mullins_mec.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_pfp.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_me.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_ce.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_rlc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/hawaii_pfp.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_me.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_ce.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_rlc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/kaveri_pfp.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_me.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_ce.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_rlc.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_mec.bin");
+MODULE_FIRMWARE("amdgpu/kaveri_mec2.bin");
+
+MODULE_FIRMWARE("amdgpu/kabini_pfp.bin");
+MODULE_FIRMWARE("amdgpu/kabini_me.bin");
+MODULE_FIRMWARE("amdgpu/kabini_ce.bin");
+MODULE_FIRMWARE("amdgpu/kabini_rlc.bin");
+MODULE_FIRMWARE("amdgpu/kabini_mec.bin");
+
+MODULE_FIRMWARE("amdgpu/mullins_pfp.bin");
+MODULE_FIRMWARE("amdgpu/mullins_me.bin");
+MODULE_FIRMWARE("amdgpu/mullins_ce.bin");
+MODULE_FIRMWARE("amdgpu/mullins_rlc.bin");
+MODULE_FIRMWARE("amdgpu/mullins_mec.bin");
 
 static const struct amdgpu_gds_reg_offset amdgpu_gds_reg_offset[] =
 {
@@ -925,7 +925,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -933,7 +933,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -941,7 +941,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -949,7 +949,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 	if (err)
 		goto out;
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_mec.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -958,7 +958,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 		goto out;
 
 	if (adev->asic_type == CHIP_KAVERI) {
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mec2.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
 		err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
 		if (err)
 			goto out;
@@ -967,7 +967,7 @@ static int gfx_v7_0_init_microcode(struct amdgpu_device *adev)
 			goto out;
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 7147bfe25a23..78339309a00c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -47,8 +47,8 @@ static void gmc_v7_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v7_0_wait_for_idle(void *handle);
 
-MODULE_FIRMWARE("radeon/bonaire_mc.bin");
-MODULE_FIRMWARE("radeon/hawaii_mc.bin");
+MODULE_FIRMWARE("amdgpu/bonaire_mc.bin");
+MODULE_FIRMWARE("amdgpu/hawaii_mc.bin");
 MODULE_FIRMWARE("amdgpu/topaz_mc.bin");
 
 static const u32 golden_settings_iceland_a11[] =
@@ -147,10 +147,7 @@ static int gmc_v7_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	if (adev->asic_type == CHIP_TOPAZ)
-		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
-	else
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
 
 	err = request_firmware(&adev->gmc.fw, fw_name, adev->dev);
 	if (err)
-- 
cgit v1.2.3


From 8eaf2b1faaf4358c6337785f2192055c6ef41e0d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 2 Jul 2018 14:35:36 -0500
Subject: drm/amdgpu: switch firmware path for SI parts
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use separate firmware path for amdgpu to avoid conflicts
with radeon on SI parts.

Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c | 56 +++++++++++++++++------------------
 drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c | 14 ++++-----
 drivers/gpu/drm/amd/amdgpu/si_dpm.c   | 22 +++++++-------
 3 files changed, 46 insertions(+), 46 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
index cd6bf291a853..de184a886057 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v6_0.c
@@ -44,30 +44,30 @@ static void gfx_v6_0_set_ring_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_set_irq_funcs(struct amdgpu_device *adev);
 static void gfx_v6_0_get_cu_info(struct amdgpu_device *adev);
 
-MODULE_FIRMWARE("radeon/tahiti_pfp.bin");
-MODULE_FIRMWARE("radeon/tahiti_me.bin");
-MODULE_FIRMWARE("radeon/tahiti_ce.bin");
-MODULE_FIRMWARE("radeon/tahiti_rlc.bin");
-
-MODULE_FIRMWARE("radeon/pitcairn_pfp.bin");
-MODULE_FIRMWARE("radeon/pitcairn_me.bin");
-MODULE_FIRMWARE("radeon/pitcairn_ce.bin");
-MODULE_FIRMWARE("radeon/pitcairn_rlc.bin");
-
-MODULE_FIRMWARE("radeon/verde_pfp.bin");
-MODULE_FIRMWARE("radeon/verde_me.bin");
-MODULE_FIRMWARE("radeon/verde_ce.bin");
-MODULE_FIRMWARE("radeon/verde_rlc.bin");
-
-MODULE_FIRMWARE("radeon/oland_pfp.bin");
-MODULE_FIRMWARE("radeon/oland_me.bin");
-MODULE_FIRMWARE("radeon/oland_ce.bin");
-MODULE_FIRMWARE("radeon/oland_rlc.bin");
-
-MODULE_FIRMWARE("radeon/hainan_pfp.bin");
-MODULE_FIRMWARE("radeon/hainan_me.bin");
-MODULE_FIRMWARE("radeon/hainan_ce.bin");
-MODULE_FIRMWARE("radeon/hainan_rlc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_pfp.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_me.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_ce.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/pitcairn_pfp.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_me.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_ce.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/verde_pfp.bin");
+MODULE_FIRMWARE("amdgpu/verde_me.bin");
+MODULE_FIRMWARE("amdgpu/verde_ce.bin");
+MODULE_FIRMWARE("amdgpu/verde_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/oland_pfp.bin");
+MODULE_FIRMWARE("amdgpu/oland_me.bin");
+MODULE_FIRMWARE("amdgpu/oland_ce.bin");
+MODULE_FIRMWARE("amdgpu/oland_rlc.bin");
+
+MODULE_FIRMWARE("amdgpu/hainan_pfp.bin");
+MODULE_FIRMWARE("amdgpu/hainan_me.bin");
+MODULE_FIRMWARE("amdgpu/hainan_ce.bin");
+MODULE_FIRMWARE("amdgpu/hainan_rlc.bin");
 
 static u32 gfx_v6_0_get_csb_size(struct amdgpu_device *adev);
 static void gfx_v6_0_get_csb_buffer(struct amdgpu_device *adev, volatile u32 *buffer);
@@ -335,7 +335,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_pfp.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_pfp.bin", chip_name);
 	err = request_firmware(&adev->gfx.pfp_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -346,7 +346,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_me.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -357,7 +357,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_ce.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
@@ -368,7 +368,7 @@ static int gfx_v6_0_init_microcode(struct amdgpu_device *adev)
 	adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
 	adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_rlc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
index 79f9ac29019b..75317f283c69 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v6_0.c
@@ -41,11 +41,11 @@ static void gmc_v6_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v6_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v6_0_wait_for_idle(void *handle);
 
-MODULE_FIRMWARE("radeon/tahiti_mc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_mc.bin");
-MODULE_FIRMWARE("radeon/verde_mc.bin");
-MODULE_FIRMWARE("radeon/oland_mc.bin");
-MODULE_FIRMWARE("radeon/si58_mc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_mc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_mc.bin");
+MODULE_FIRMWARE("amdgpu/verde_mc.bin");
+MODULE_FIRMWARE("amdgpu/oland_mc.bin");
+MODULE_FIRMWARE("amdgpu/si58_mc.bin");
 
 #define MC_SEQ_MISC0__MT__MASK   0xf0000000
 #define MC_SEQ_MISC0__MT__GDDR1  0x10000000
@@ -134,9 +134,9 @@ static int gmc_v6_0_init_microcode(struct amdgpu_device *adev)
 		is_58_fw = true;
 
 	if (is_58_fw)
-		snprintf(fw_name, sizeof(fw_name), "radeon/si58_mc.bin");
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/si58_mc.bin");
 	else
-		snprintf(fw_name, sizeof(fw_name), "radeon/%s_mc.bin", chip_name);
+		snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mc.bin", chip_name);
 	err = request_firmware(&adev->gmc.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index d51318c695e6..3560b7dc1798 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -56,16 +56,16 @@
 
 #define BIOS_SCRATCH_4                                    0x5cd
 
-MODULE_FIRMWARE("radeon/tahiti_smc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_smc.bin");
-MODULE_FIRMWARE("radeon/pitcairn_k_smc.bin");
-MODULE_FIRMWARE("radeon/verde_smc.bin");
-MODULE_FIRMWARE("radeon/verde_k_smc.bin");
-MODULE_FIRMWARE("radeon/oland_smc.bin");
-MODULE_FIRMWARE("radeon/oland_k_smc.bin");
-MODULE_FIRMWARE("radeon/hainan_smc.bin");
-MODULE_FIRMWARE("radeon/hainan_k_smc.bin");
-MODULE_FIRMWARE("radeon/banks_k_2_smc.bin");
+MODULE_FIRMWARE("amdgpu/tahiti_smc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_smc.bin");
+MODULE_FIRMWARE("amdgpu/pitcairn_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/verde_smc.bin");
+MODULE_FIRMWARE("amdgpu/verde_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/oland_smc.bin");
+MODULE_FIRMWARE("amdgpu/oland_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/hainan_smc.bin");
+MODULE_FIRMWARE("amdgpu/hainan_k_smc.bin");
+MODULE_FIRMWARE("amdgpu/banks_k_2_smc.bin");
 
 static const struct amd_pm_funcs si_dpm_funcs;
 
@@ -7667,7 +7667,7 @@ static int si_dpm_init_microcode(struct amdgpu_device *adev)
 	default: BUG();
 	}
 
-	snprintf(fw_name, sizeof(fw_name), "radeon/%s_smc.bin", chip_name);
+	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_smc.bin", chip_name);
 	err = request_firmware(&adev->pm.fw, fw_name, adev->dev);
 	if (err)
 		goto out;
-- 
cgit v1.2.3


From 576c7218a1546e0153480b208b125509cec71470 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Jun 2018 13:17:41 -0500
Subject: PCI: Export pcie_get_speed_cap and pcie_get_width_cap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

So drivers can use them.  This can be used to replace
duplicate code in the drm subsystem.

Acked-by: Christian König <christian.koenig@amd.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/pci/pci.c   | 2 ++
 include/linux/pci.h | 3 +++
 2 files changed, 5 insertions(+)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..22adaf35b136 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5222,6 +5222,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
 
 	return PCI_SPEED_UNKNOWN;
 }
+EXPORT_SYMBOL(pcie_get_speed_cap);
 
 /**
  * pcie_get_width_cap - query for the PCI device's link width capability
@@ -5240,6 +5241,7 @@ enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev)
 
 	return PCIE_LNK_WIDTH_UNKNOWN;
 }
+EXPORT_SYMBOL(pcie_get_width_cap);
 
 /**
  * pcie_bandwidth_capable - calculate a PCI device's link bandwidth capability
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..6e0c0803b241 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -261,6 +261,9 @@ enum pci_bus_speed {
 	PCI_SPEED_UNKNOWN		= 0xff,
 };
 
+enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
+enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
+
 struct pci_cap_saved_data {
 	u16		cap_nr;
 	bool		cap_extended;
-- 
cgit v1.2.3


From 4976f1c8ccff0d682176851692976e3bf03267d6 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Jun 2018 13:03:51 -0500
Subject: drm/amdgpu: update amd_pcie.h to include gen4 speeds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Internal header used by the driver to specify pcie gen
speeds of the asic and chipset.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/amd_pcie.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/amd_pcie.h b/drivers/gpu/drm/amd/include/amd_pcie.h
index 5eb895fd98bf..9cb9ceb4d74d 100644
--- a/drivers/gpu/drm/amd/include/amd_pcie.h
+++ b/drivers/gpu/drm/amd/include/amd_pcie.h
@@ -27,6 +27,7 @@
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1        0x00010000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2        0x00020000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3        0x00040000
+#define CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4        0x00080000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_MASK        0xFFFF0000
 #define CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT       16
 
@@ -34,6 +35,7 @@
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1   0x00000001
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2   0x00000002
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3   0x00000004
+#define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4   0x00000008
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_MASK   0x0000FFFF
 #define CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_SHIFT  0
 
-- 
cgit v1.2.3


From 5d9a6330403271fbb1244f14380a7cc44662796f Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Jun 2018 13:07:50 -0500
Subject: drm/amdgpu: use pcie functions for link width and speed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the newly exported pci functions to get the link width
and speed rather than using the drm duplicated versions.

Also query the GPU link caps directly rather than hardcoding
them.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 83 +++++++++++++++++++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c    |  7 ++-
 drivers/gpu/drm/amd/amdgpu/ci_dpm.c        |  3 +-
 drivers/gpu/drm/amd/amdgpu/si_dpm.c        |  3 +-
 4 files changed, 65 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index c35db859f050..d43abbd2a3cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3311,8 +3311,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
  */
 static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 {
-	u32 mask;
-	int ret;
+	struct pci_dev *pdev;
+	enum pci_bus_speed speed_cap;
+	enum pcie_link_width link_width;
 
 	if (amdgpu_pcie_gen_cap)
 		adev->pm.pcie_gen_mask = amdgpu_pcie_gen_cap;
@@ -3330,27 +3331,61 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 	}
 
 	if (adev->pm.pcie_gen_mask == 0) {
-		ret = drm_pcie_get_speed_cap_mask(adev->ddev, &mask);
-		if (!ret) {
-			adev->pm.pcie_gen_mask = (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+		/* asic caps */
+		pdev = adev->pdev;
+		speed_cap = pcie_get_speed_cap(pdev);
+		if (speed_cap == PCI_SPEED_UNKNOWN) {
+			adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
 						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
 						  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
-
-			if (mask & DRM_PCIE_SPEED_25)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
-			if (mask & DRM_PCIE_SPEED_50)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2;
-			if (mask & DRM_PCIE_SPEED_80)
-				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3;
 		} else {
-			adev->pm.pcie_gen_mask = AMDGPU_DEFAULT_PCIE_GEN_MASK;
+			if (speed_cap == PCIE_SPEED_16_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN4);
+			else if (speed_cap == PCIE_SPEED_8_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN3);
+			else if (speed_cap == PCIE_SPEED_5_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							  CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN2);
+			else
+				adev->pm.pcie_gen_mask |= CAIL_ASIC_PCIE_LINK_SPEED_SUPPORT_GEN1;
+		}
+		/* platform caps */
+		pdev = adev->ddev->pdev->bus->self;
+		speed_cap = pcie_get_speed_cap(pdev);
+		if (speed_cap == PCI_SPEED_UNKNOWN) {
+			adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+						   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2);
+		} else {
+			if (speed_cap == PCIE_SPEED_16_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN4);
+			else if (speed_cap == PCIE_SPEED_8_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3);
+			else if (speed_cap == PCIE_SPEED_5_0GT)
+				adev->pm.pcie_gen_mask |= (CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1 |
+							   CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2);
+			else
+				adev->pm.pcie_gen_mask |= CAIL_PCIE_LINK_SPEED_SUPPORT_GEN1;
+
 		}
 	}
 	if (adev->pm.pcie_mlw_mask == 0) {
-		ret = drm_pcie_get_max_link_width(adev->ddev, &mask);
-		if (!ret) {
-			switch (mask) {
-			case 32:
+		pdev = adev->ddev->pdev->bus->self;
+		link_width = pcie_get_width_cap(pdev);
+		if (link_width == PCIE_LNK_WIDTH_UNKNOWN) {
+			adev->pm.pcie_mlw_mask |= AMDGPU_DEFAULT_PCIE_MLW_MASK;
+		} else {
+			switch (link_width) {
+			case PCIE_LNK_X32:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X32 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
@@ -3359,7 +3394,7 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 16:
+			case PCIE_LNK_X16:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X16 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
@@ -3367,36 +3402,34 @@ static void amdgpu_device_get_pcie_info(struct amdgpu_device *adev)
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 12:
+			case PCIE_LNK_X12:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X12 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 8:
+			case PCIE_LNK_X8:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X8 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 4:
+			case PCIE_LNK_X4:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X4 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 2:
+			case PCIE_LNK_X2:
 				adev->pm.pcie_mlw_mask = (CAIL_PCIE_LINK_WIDTH_SUPPORT_X2 |
 							  CAIL_PCIE_LINK_WIDTH_SUPPORT_X1);
 				break;
-			case 1:
+			case PCIE_LNK_X1:
 				adev->pm.pcie_mlw_mask = CAIL_PCIE_LINK_WIDTH_SUPPORT_X1;
 				break;
 			default:
 				break;
 			}
-		} else {
-			adev->pm.pcie_mlw_mask = AMDGPU_DEFAULT_PCIE_MLW_MASK;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
index 77ad59ade85c..1c4595562f8f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_dpm.c
@@ -28,6 +28,7 @@
 #include "amdgpu_i2c.h"
 #include "amdgpu_dpm.h"
 #include "atom.h"
+#include "amd_pcie.h"
 
 void amdgpu_dpm_print_class_info(u32 class, u32 class2)
 {
@@ -936,9 +937,11 @@ enum amdgpu_pcie_gen amdgpu_get_pcie_gen_support(struct amdgpu_device *adev,
 	case AMDGPU_PCIE_GEN3:
 		return AMDGPU_PCIE_GEN3;
 	default:
-		if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == AMDGPU_PCIE_GEN3))
+		if ((sys_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3) &&
+		    (default_gen == AMDGPU_PCIE_GEN3))
 			return AMDGPU_PCIE_GEN3;
-		else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == AMDGPU_PCIE_GEN2))
+		else if ((sys_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN2) &&
+			 (default_gen == AMDGPU_PCIE_GEN2))
 			return AMDGPU_PCIE_GEN2;
 		else
 			return AMDGPU_PCIE_GEN1;
diff --git a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
index d79ad93b01c3..d2469453dca2 100644
--- a/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/ci_dpm.c
@@ -5846,8 +5846,7 @@ static int ci_dpm_init(struct amdgpu_device *adev)
 	adev->pm.dpm.priv = pi;
 
 	pi->sys_pcie_mask =
-		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
-		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+		adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK;
 
 	pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/si_dpm.c b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
index 3560b7dc1798..db327b412562 100644
--- a/drivers/gpu/drm/amd/amdgpu/si_dpm.c
+++ b/drivers/gpu/drm/amd/amdgpu/si_dpm.c
@@ -7318,8 +7318,7 @@ static int si_dpm_init(struct amdgpu_device *adev)
 	pi = &eg_pi->rv7xx;
 
 	si_pi->sys_pcie_mask =
-		(adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK) >>
-		CAIL_PCIE_LINK_SPEED_SUPPORT_SHIFT;
+		adev->pm.pcie_gen_mask & CAIL_PCIE_LINK_SPEED_SUPPORT_MASK;
 	si_pi->force_pcie_gen = AMDGPU_PCIE_GEN_INVALID;
 	si_pi->boot_pcie_gen = si_get_current_pcie_speed(adev);
 
-- 
cgit v1.2.3


From 5f152a572c10cae4b08c2c5f2932a51684f454ba Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Jun 2018 14:37:45 -0500
Subject: drm/radeon: use pcie functions for link width
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is the last user of drm_pcie_get_speed_cap_mask.  Use the pci
version so we can drop drm_pcie_get_speed_cap_mask.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/ci_dpm.c   | 20 +++++++++++++++-----
 drivers/gpu/drm/radeon/cik.c      | 22 ++++++++++++----------
 drivers/gpu/drm/radeon/r600_dpm.c |  4 ++--
 drivers/gpu/drm/radeon/radeon.h   |  4 ++++
 drivers/gpu/drm/radeon/si.c       | 22 ++++++++++++----------
 drivers/gpu/drm/radeon/si_dpm.c   | 20 +++++++++++++++-----
 6 files changed, 60 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/radeon/ci_dpm.c b/drivers/gpu/drm/radeon/ci_dpm.c
index b9302c918271..d587779a80b4 100644
--- a/drivers/gpu/drm/radeon/ci_dpm.c
+++ b/drivers/gpu/drm/radeon/ci_dpm.c
@@ -5676,19 +5676,29 @@ int ci_dpm_init(struct radeon_device *rdev)
 	u16 data_offset, size;
 	u8 frev, crev;
 	struct ci_power_info *pi;
+	enum pci_bus_speed speed_cap;
+	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
-	u32 mask;
 
 	pi = kzalloc(sizeof(struct ci_power_info), GFP_KERNEL);
 	if (pi == NULL)
 		return -ENOMEM;
 	rdev->pm.dpm.priv = pi;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		pi->sys_pcie_mask = 0;
-	else
-		pi->sys_pcie_mask = mask;
+	} else {
+		if (speed_cap == PCIE_SPEED_8_0GT)
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50 |
+				RADEON_PCIE_SPEED_80;
+		else if (speed_cap == PCIE_SPEED_5_0GT)
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50;
+		else
+			pi->sys_pcie_mask = RADEON_PCIE_SPEED_25;
+	}
 	pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
 
 	pi->pcie_gen_performance.max = RADEON_PCIE_GEN1;
diff --git a/drivers/gpu/drm/radeon/cik.c b/drivers/gpu/drm/radeon/cik.c
index 7c73bc7e2f85..ebce4601a305 100644
--- a/drivers/gpu/drm/radeon/cik.c
+++ b/drivers/gpu/drm/radeon/cik.c
@@ -9499,9 +9499,10 @@ int cik_set_vce_clocks(struct radeon_device *rdev, u32 evclk, u32 ecclk)
 static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 {
 	struct pci_dev *root = rdev->pdev->bus->self;
+	enum pci_bus_speed speed_cap;
 	int bridge_pos, gpu_pos;
-	u32 speed_cntl, mask, current_data_rate;
-	int ret, i;
+	u32 speed_cntl, current_data_rate;
+	int i;
 	u16 tmp16;
 
 	if (pci_is_root_bus(rdev->pdev->bus))
@@ -9516,23 +9517,24 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret != 0)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN)
 		return;
 
-	if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80)))
+	if ((speed_cap != PCIE_SPEED_8_0GT) &&
+	    (speed_cap != PCIE_SPEED_5_0GT))
 		return;
 
 	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
 	current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >>
 		LC_CURRENT_DATA_RATE_SHIFT;
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		if (current_data_rate == 2) {
 			DRM_INFO("PCIE gen 3 link speeds already enabled\n");
 			return;
 		}
 		DRM_INFO("enabling PCIE gen 3 link speeds, disable with radeon.pcie_gen2=0\n");
-	} else if (mask & DRM_PCIE_SPEED_50) {
+	} else if (speed_cap == PCIE_SPEED_5_0GT) {
 		if (current_data_rate == 1) {
 			DRM_INFO("PCIE gen 2 link speeds already enabled\n");
 			return;
@@ -9548,7 +9550,7 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!gpu_pos)
 		return;
 
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		/* re-try equalization if gen3 is not already enabled */
 		if (current_data_rate != 2) {
 			u16 bridge_cfg, gpu_cfg;
@@ -9636,9 +9638,9 @@ static void cik_pcie_gen3_enable(struct radeon_device *rdev)
 
 	pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
 	tmp16 &= ~0xf;
-	if (mask & DRM_PCIE_SPEED_80)
+	if (speed_cap == PCIE_SPEED_8_0GT)
 		tmp16 |= 3; /* gen3 */
-	else if (mask & DRM_PCIE_SPEED_50)
+	else if (speed_cap == PCIE_SPEED_5_0GT)
 		tmp16 |= 2; /* gen2 */
 	else
 		tmp16 |= 1; /* gen1 */
diff --git a/drivers/gpu/drm/radeon/r600_dpm.c b/drivers/gpu/drm/radeon/r600_dpm.c
index 73d4c5348116..5e044c98fca2 100644
--- a/drivers/gpu/drm/radeon/r600_dpm.c
+++ b/drivers/gpu/drm/radeon/r600_dpm.c
@@ -1327,9 +1327,9 @@ enum radeon_pcie_gen r600_get_pcie_gen_support(struct radeon_device *rdev,
 	case RADEON_PCIE_GEN3:
 		return RADEON_PCIE_GEN3;
 	default:
-		if ((sys_mask & DRM_PCIE_SPEED_80) && (default_gen == RADEON_PCIE_GEN3))
+		if ((sys_mask & RADEON_PCIE_SPEED_80) && (default_gen == RADEON_PCIE_GEN3))
 			return RADEON_PCIE_GEN3;
-		else if ((sys_mask & DRM_PCIE_SPEED_50) && (default_gen == RADEON_PCIE_GEN2))
+		else if ((sys_mask & RADEON_PCIE_SPEED_50) && (default_gen == RADEON_PCIE_GEN2))
 			return RADEON_PCIE_GEN2;
 		else
 			return RADEON_PCIE_GEN1;
diff --git a/drivers/gpu/drm/radeon/radeon.h b/drivers/gpu/drm/radeon/radeon.h
index 4a2eb409aacc..1a6f6edb3515 100644
--- a/drivers/gpu/drm/radeon/radeon.h
+++ b/drivers/gpu/drm/radeon/radeon.h
@@ -1653,6 +1653,10 @@ struct radeon_pm {
 	struct radeon_dpm       dpm;
 };
 
+#define RADEON_PCIE_SPEED_25 1
+#define RADEON_PCIE_SPEED_50 2
+#define RADEON_PCIE_SPEED_80 4
+
 int radeon_pm_get_type_index(struct radeon_device *rdev,
 			     enum radeon_pm_state_type ps_type,
 			     int instance);
diff --git a/drivers/gpu/drm/radeon/si.c b/drivers/gpu/drm/radeon/si.c
index 1907c950d76f..85c604d29235 100644
--- a/drivers/gpu/drm/radeon/si.c
+++ b/drivers/gpu/drm/radeon/si.c
@@ -7082,9 +7082,10 @@ int si_set_uvd_clocks(struct radeon_device *rdev, u32 vclk, u32 dclk)
 static void si_pcie_gen3_enable(struct radeon_device *rdev)
 {
 	struct pci_dev *root = rdev->pdev->bus->self;
+	enum pci_bus_speed speed_cap;
 	int bridge_pos, gpu_pos;
-	u32 speed_cntl, mask, current_data_rate;
-	int ret, i;
+	u32 speed_cntl, current_data_rate;
+	int i;
 	u16 tmp16;
 
 	if (pci_is_root_bus(rdev->pdev->bus))
@@ -7099,23 +7100,24 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!(rdev->flags & RADEON_IS_PCIE))
 		return;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret != 0)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN)
 		return;
 
-	if (!(mask & (DRM_PCIE_SPEED_50 | DRM_PCIE_SPEED_80)))
+	if ((speed_cap != PCIE_SPEED_8_0GT) &&
+	    (speed_cap != PCIE_SPEED_5_0GT))
 		return;
 
 	speed_cntl = RREG32_PCIE_PORT(PCIE_LC_SPEED_CNTL);
 	current_data_rate = (speed_cntl & LC_CURRENT_DATA_RATE_MASK) >>
 		LC_CURRENT_DATA_RATE_SHIFT;
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		if (current_data_rate == 2) {
 			DRM_INFO("PCIE gen 3 link speeds already enabled\n");
 			return;
 		}
 		DRM_INFO("enabling PCIE gen 3 link speeds, disable with radeon.pcie_gen2=0\n");
-	} else if (mask & DRM_PCIE_SPEED_50) {
+	} else if (speed_cap == PCIE_SPEED_5_0GT) {
 		if (current_data_rate == 1) {
 			DRM_INFO("PCIE gen 2 link speeds already enabled\n");
 			return;
@@ -7131,7 +7133,7 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 	if (!gpu_pos)
 		return;
 
-	if (mask & DRM_PCIE_SPEED_80) {
+	if (speed_cap == PCIE_SPEED_8_0GT) {
 		/* re-try equalization if gen3 is not already enabled */
 		if (current_data_rate != 2) {
 			u16 bridge_cfg, gpu_cfg;
@@ -7219,9 +7221,9 @@ static void si_pcie_gen3_enable(struct radeon_device *rdev)
 
 	pci_read_config_word(rdev->pdev, gpu_pos + PCI_EXP_LNKCTL2, &tmp16);
 	tmp16 &= ~0xf;
-	if (mask & DRM_PCIE_SPEED_80)
+	if (speed_cap == PCIE_SPEED_8_0GT)
 		tmp16 |= 3; /* gen3 */
-	else if (mask & DRM_PCIE_SPEED_50)
+	else if (speed_cap == PCIE_SPEED_5_0GT)
 		tmp16 |= 2; /* gen2 */
 	else
 		tmp16 |= 1; /* gen1 */
diff --git a/drivers/gpu/drm/radeon/si_dpm.c b/drivers/gpu/drm/radeon/si_dpm.c
index fea88078cf8e..8fb60b3af015 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -6899,8 +6899,9 @@ int si_dpm_init(struct radeon_device *rdev)
 	struct ni_power_info *ni_pi;
 	struct si_power_info *si_pi;
 	struct atom_clock_dividers dividers;
+	enum pci_bus_speed speed_cap;
+	struct pci_dev *root = rdev->pdev->bus->self;
 	int ret;
-	u32 mask;
 
 	si_pi = kzalloc(sizeof(struct si_power_info), GFP_KERNEL);
 	if (si_pi == NULL)
@@ -6910,11 +6911,20 @@ int si_dpm_init(struct radeon_device *rdev)
 	eg_pi = &ni_pi->eg;
 	pi = &eg_pi->rv7xx;
 
-	ret = drm_pcie_get_speed_cap_mask(rdev->ddev, &mask);
-	if (ret)
+	speed_cap = pcie_get_speed_cap(root);
+	if (speed_cap == PCI_SPEED_UNKNOWN) {
 		si_pi->sys_pcie_mask = 0;
-	else
-		si_pi->sys_pcie_mask = mask;
+	} else {
+		if (speed_cap == PCIE_SPEED_8_0GT)
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50 |
+				RADEON_PCIE_SPEED_80;
+		else if (speed_cap == PCIE_SPEED_5_0GT)
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25 |
+				RADEON_PCIE_SPEED_50;
+		else
+			si_pi->sys_pcie_mask = RADEON_PCIE_SPEED_25;
+	}
 	si_pi->force_pcie_gen = RADEON_PCIE_GEN_INVALID;
 	si_pi->boot_pcie_gen = si_get_current_pcie_speed(rdev);
 
-- 
cgit v1.2.3


From 289278cb7d32685ee75baf599857d7049c4b8030 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 25 Jun 2018 15:14:46 -0500
Subject: drm: drop drm_pcie_get_speed_cap_mask and drm_pcie_get_max_link_width
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These functions duplicated functionality which was ultimately added
to the pci core.

All users of these functions have been ported to using the newly
exposed pci functionality.  These functions are no longer used,
so drop them.

Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/drm_pci.c | 58 -----------------------------------------------
 include/drm/drm_pci.h     |  7 ------
 2 files changed, 65 deletions(-)

diff --git a/drivers/gpu/drm/drm_pci.c b/drivers/gpu/drm/drm_pci.c
index 4db9c515b74f..896e42a34895 100644
--- a/drivers/gpu/drm/drm_pci.c
+++ b/drivers/gpu/drm/drm_pci.c
@@ -326,64 +326,6 @@ int drm_legacy_pci_init(struct drm_driver *driver, struct pci_driver *pdriver)
 }
 EXPORT_SYMBOL(drm_legacy_pci_init);
 
-int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *mask)
-{
-	struct pci_dev *root;
-	u32 lnkcap, lnkcap2;
-
-	*mask = 0;
-	if (!dev->pdev)
-		return -EINVAL;
-
-	root = dev->pdev->bus->self;
-
-	/* we've been informed via and serverworks don't make the cut */
-	if (root->vendor == PCI_VENDOR_ID_VIA ||
-	    root->vendor == PCI_VENDOR_ID_SERVERWORKS)
-		return -EINVAL;
-
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap);
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP2, &lnkcap2);
-
-	if (lnkcap2) {	/* PCIe r3.0-compliant */
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_2_5GB)
-			*mask |= DRM_PCIE_SPEED_25;
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_5_0GB)
-			*mask |= DRM_PCIE_SPEED_50;
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
-			*mask |= DRM_PCIE_SPEED_80;
-	} else {	/* pre-r3.0 */
-		if (lnkcap & PCI_EXP_LNKCAP_SLS_2_5GB)
-			*mask |= DRM_PCIE_SPEED_25;
-		if (lnkcap & PCI_EXP_LNKCAP_SLS_5_0GB)
-			*mask |= (DRM_PCIE_SPEED_25 | DRM_PCIE_SPEED_50);
-	}
-
-	DRM_INFO("probing gen 2 caps for device %x:%x = %x/%x\n", root->vendor, root->device, lnkcap, lnkcap2);
-	return 0;
-}
-EXPORT_SYMBOL(drm_pcie_get_speed_cap_mask);
-
-int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw)
-{
-	struct pci_dev *root;
-	u32 lnkcap;
-
-	*mlw = 0;
-	if (!dev->pdev)
-		return -EINVAL;
-
-	root = dev->pdev->bus->self;
-
-	pcie_capability_read_dword(root, PCI_EXP_LNKCAP, &lnkcap);
-
-	*mlw = (lnkcap & PCI_EXP_LNKCAP_MLW) >> 4;
-
-	DRM_INFO("probing mlw for device %x:%x = %x\n", root->vendor, root->device, lnkcap);
-	return 0;
-}
-EXPORT_SYMBOL(drm_pcie_get_max_link_width);
-
 #else
 
 void drm_pci_agp_destroy(struct drm_device *dev) {}
diff --git a/include/drm/drm_pci.h b/include/drm/drm_pci.h
index 674599025d7d..8181e9e7cf1d 100644
--- a/include/drm/drm_pci.h
+++ b/include/drm/drm_pci.h
@@ -58,11 +58,4 @@ static inline int drm_get_pci_dev(struct pci_dev *pdev,
 }
 #endif
 
-#define DRM_PCIE_SPEED_25 1
-#define DRM_PCIE_SPEED_50 2
-#define DRM_PCIE_SPEED_80 4
-
-int drm_pcie_get_speed_cap_mask(struct drm_device *dev, u32 *speed_mask);
-int drm_pcie_get_max_link_width(struct drm_device *dev, u32 *mlw);
-
 #endif /* _DRM_PCI_H_ */
-- 
cgit v1.2.3


From ea870e44415a5f5ed09b6e002e38d3e0de7f390e Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Fri, 22 Jun 2018 14:12:59 +0800
Subject: drm/amd/pp: Export notify_smu_enable_pwe to display

Display can notify smu to enable pwe after gpu suspend.
It is used in case when display resumes from S3 and wants to start
audio driver by enabling pwe

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/kgd_pp_interface.h |  7 ++++---
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c  | 20 ++++++++++++++++++++
 2 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/kgd_pp_interface.h b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
index 99ee3edd1609..6a41b81c7325 100644
--- a/drivers/gpu/drm/amd/include/kgd_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_pp_interface.h
@@ -241,6 +241,9 @@ struct amd_pm_funcs {
 	int (*set_clockgating_by_smu)(void *handle, uint32_t msg_id);
 	int (*set_power_limit)(void *handle, uint32_t n);
 	int (*get_power_limit)(void *handle, uint32_t *limit, bool default_limit);
+	int (*get_power_profile_mode)(void *handle, char *buf);
+	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
+	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
 /* export to DC */
 	u32 (*get_sclk)(void *handle, bool low);
 	u32 (*get_mclk)(void *handle, bool low);
@@ -265,9 +268,7 @@ struct amd_pm_funcs {
 				struct pp_display_clock_request *clock);
 	int (*get_display_mode_validation_clocks)(void *handle,
 		struct amd_pp_simple_clock_info *clocks);
-	int (*get_power_profile_mode)(void *handle, char *buf);
-	int (*set_power_profile_mode)(void *handle, long *input, uint32_t size);
-	int (*odn_edit_dpm_table)(void *handle, uint32_t type, long *input, uint32_t size);
+	int (*notify_smu_enable_pwe)(void *handle);
 };
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index b72cc644d4e7..145e5c403bea 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -1201,6 +1201,25 @@ static int pp_set_powergating_by_smu(void *handle,
 	return ret;
 }
 
+static int pp_notify_smu_enable_pwe(void *handle)
+{
+	struct pp_hwmgr *hwmgr = handle;
+
+	if (!hwmgr || !hwmgr->pm_en)
+		return -EINVAL;;
+
+	if (hwmgr->hwmgr_func->smus_notify_pwe == NULL) {
+		pr_info("%s was not implemented.\n", __func__);
+		return -EINVAL;;
+	}
+
+	mutex_lock(&hwmgr->smu_lock);
+	hwmgr->hwmgr_func->smus_notify_pwe(hwmgr);
+	mutex_unlock(&hwmgr->smu_lock);
+
+	return 0;
+}
+
 static const struct amd_pm_funcs pp_dpm_funcs = {
 	.load_firmware = pp_dpm_load_fw,
 	.wait_for_fw_loading_complete = pp_dpm_fw_loading_complete,
@@ -1244,4 +1263,5 @@ static const struct amd_pm_funcs pp_dpm_funcs = {
 	.set_watermarks_for_clocks_ranges = pp_set_watermarks_for_clocks_ranges,
 	.display_clock_voltage_request = pp_display_clock_voltage_request,
 	.get_display_mode_validation_clocks = pp_get_display_mode_validation_clocks,
+	.notify_smu_enable_pwe = pp_notify_smu_enable_pwe,
 };
-- 
cgit v1.2.3


From b0a634ac68337b263e01d83359a023676e370cce Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Tue, 3 Jul 2018 16:31:35 +0800
Subject: drm/amd/display: Refine the implementation of dm_pp_get_funcs_rv

powerplay/dpm export all interfaces in struct amd_pm_funcs.
so call common exported interfaces instead of powerplay inner interfaces

Also not include header file hwmgr.h

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c   | 80 +++++++++++-----------
 1 file changed, 40 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 81845116cdcc..9c105c07eb25 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -33,7 +33,6 @@
 #include "amdgpu_dm_irq.h"
 #include "amdgpu_pm.h"
 #include "dm_pp_smu.h"
-#include "../../powerplay/inc/hwmgr.h"
 
 
 bool dm_pp_apply_display_requirements(
@@ -452,76 +451,77 @@ bool dm_pp_get_static_clocks(
 void pp_rv_set_display_requirement(struct pp_smu *pp,
 		struct pp_smu_display_requirement_rv *req)
 {
-	struct amdgpu_device *adev = pp->ctx->driver_context;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	int ret = 0;
-	if (hwmgr->hwmgr_func->set_deep_sleep_dcefclk)
-		ret = hwmgr->hwmgr_func->set_deep_sleep_dcefclk(hwmgr, req->hard_min_dcefclk_khz/10);
-	if (hwmgr->hwmgr_func->set_active_display_count)
-		ret = hwmgr->hwmgr_func->set_active_display_count(hwmgr, req->display_count);
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->display_configuration_changed)
+		return;
 
-	//store_cc6 is not yet implemented in SMU level
+	amdgpu_dpm_display_configuration_changed(adev);
 }
 
 void pp_rv_set_wm_ranges(struct pp_smu *pp,
 		struct pp_smu_wm_range_sets *ranges)
 {
-	struct amdgpu_device *adev = pp->ctx->driver_context;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
-	struct pp_wm_sets_with_clock_ranges_soc15 ranges_soc15 = {0};
-	int i = 0;
-
-	if (!hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges ||
-			!pp || !ranges)
-		return;
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 wm_with_clock_ranges;
+	struct dm_pp_clock_range_for_dmif_wm_set_soc15 *wm_dce_clocks = wm_with_clock_ranges.wm_dmif_clocks_ranges;
+	struct dm_pp_clock_range_for_mcif_wm_set_soc15 *wm_soc_clocks = wm_with_clock_ranges.wm_mcif_clocks_ranges;
+	int32_t i;
 
-	//not entirely sure if thats a correct assignment
-	ranges_soc15.num_wm_sets_dmif = ranges->num_reader_wm_sets;
-	ranges_soc15.num_wm_sets_mcif = ranges->num_writer_wm_sets;
+	wm_with_clock_ranges.num_wm_dmif_sets = ranges->num_reader_wm_sets;
+	wm_with_clock_ranges.num_wm_mcif_sets = ranges->num_writer_wm_sets;
 
-	for (i = 0; i < ranges_soc15.num_wm_sets_dmif; i++) {
+	for (i = 0; i < wm_with_clock_ranges.num_wm_dmif_sets; i++) {
 		if (ranges->reader_wm_sets[i].wm_inst > 3)
-			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
+			wm_dce_clocks[i].wm_set_id = WM_SET_A;
 		else
-			ranges_soc15.wm_sets_dmif[i].wm_set_id =
+			wm_dce_clocks[i].wm_set_id =
 					ranges->reader_wm_sets[i].wm_inst;
-		ranges_soc15.wm_sets_dmif[i].wm_max_dcefclk_in_khz =
+		wm_dce_clocks[i].wm_max_dcfclk_clk_in_khz =
 				ranges->reader_wm_sets[i].max_drain_clk_khz;
-		ranges_soc15.wm_sets_dmif[i].wm_min_dcefclk_in_khz =
+		wm_dce_clocks[i].wm_min_dcfclk_clk_in_khz =
 				ranges->reader_wm_sets[i].min_drain_clk_khz;
-		ranges_soc15.wm_sets_dmif[i].wm_max_memclk_in_khz =
+		wm_dce_clocks[i].wm_max_mem_clk_in_khz =
 				ranges->reader_wm_sets[i].max_fill_clk_khz;
-		ranges_soc15.wm_sets_dmif[i].wm_min_memclk_in_khz =
+		wm_dce_clocks[i].wm_min_mem_clk_in_khz =
 				ranges->reader_wm_sets[i].min_fill_clk_khz;
 	}
 
-	for (i = 0; i < ranges_soc15.num_wm_sets_mcif; i++) {
+	for (i = 0; i < wm_with_clock_ranges.num_wm_mcif_sets; i++) {
 		if (ranges->writer_wm_sets[i].wm_inst > 3)
-			ranges_soc15.wm_sets_dmif[i].wm_set_id = DC_WM_SET_A;
+			wm_soc_clocks[i].wm_set_id = WM_SET_A;
 		else
-			ranges_soc15.wm_sets_mcif[i].wm_set_id =
+			wm_soc_clocks[i].wm_set_id =
 					ranges->writer_wm_sets[i].wm_inst;
-		ranges_soc15.wm_sets_mcif[i].wm_max_socclk_in_khz =
+		wm_soc_clocks[i].wm_max_socclk_clk_in_khz =
 				ranges->writer_wm_sets[i].max_fill_clk_khz;
-		ranges_soc15.wm_sets_mcif[i].wm_min_socclk_in_khz =
+		wm_soc_clocks[i].wm_min_socclk_clk_in_khz =
 				ranges->writer_wm_sets[i].min_fill_clk_khz;
-		ranges_soc15.wm_sets_mcif[i].wm_max_memclk_in_khz =
+		wm_soc_clocks[i].wm_max_mem_clk_in_khz =
 				ranges->writer_wm_sets[i].max_fill_clk_khz;
-		ranges_soc15.wm_sets_mcif[i].wm_min_memclk_in_khz =
+		wm_soc_clocks[i].wm_min_mem_clk_in_khz =
 				ranges->writer_wm_sets[i].min_fill_clk_khz;
 	}
 
-	hwmgr->hwmgr_func->set_watermarks_for_clocks_ranges(hwmgr, &ranges_soc15);
-
+	pp_funcs->set_watermarks_for_clocks_ranges(pp_handle, &wm_with_clock_ranges);
 }
 
 void pp_rv_set_pme_wa_enable(struct pp_smu *pp)
 {
-	struct amdgpu_device *adev = pp->ctx->driver_context;
-	struct pp_hwmgr *hwmgr = adev->powerplay.pp_handle;
+	struct dc_context *ctx = pp->ctx;
+	struct amdgpu_device *adev = ctx->driver_context;
+	void *pp_handle = adev->powerplay.pp_handle;
+	const struct amd_pm_funcs *pp_funcs = adev->powerplay.pp_funcs;
+
+	if (!pp_funcs || !pp_funcs->notify_smu_enable_pwe)
+		return;
 
-	if (hwmgr->hwmgr_func->smus_notify_pwe)
-		hwmgr->hwmgr_func->smus_notify_pwe(hwmgr);
+	pp_funcs->notify_smu_enable_pwe(pp_handle);
 }
 
 void dm_pp_get_funcs_rv(
-- 
cgit v1.2.3


From 70b63170c3effc1d9a66fbfe4a5702c8cbbd31c3 Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Tue, 3 Jul 2018 17:17:21 +0800
Subject: drm/amd/display: Fix copy error when set memory clocks

Set memory clocks same as soc clocks

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 9c105c07eb25..50e863024f58 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -503,9 +503,9 @@ void pp_rv_set_wm_ranges(struct pp_smu *pp,
 		wm_soc_clocks[i].wm_min_socclk_clk_in_khz =
 				ranges->writer_wm_sets[i].min_fill_clk_khz;
 		wm_soc_clocks[i].wm_max_mem_clk_in_khz =
-				ranges->writer_wm_sets[i].max_fill_clk_khz;
+				ranges->writer_wm_sets[i].max_drain_clk_khz;
 		wm_soc_clocks[i].wm_min_mem_clk_in_khz =
-				ranges->writer_wm_sets[i].min_fill_clk_khz;
+				ranges->writer_wm_sets[i].min_drain_clk_khz;
 	}
 
 	pp_funcs->set_watermarks_for_clocks_ranges(pp_handle, &wm_with_clock_ranges);
-- 
cgit v1.2.3


From 20582319bce482e65ee1f417b9867f028d058c12 Mon Sep 17 00:00:00 2001
From: Rex Zhu <Rex.Zhu@amd.com>
Date: Wed, 20 Jun 2018 15:05:04 +0800
Subject: drm/amd/pp: Remove the same struct define in powerplay

delete the same struct define in powerplay, share the struct
with display.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/dm_pp_interface.h      | 37 ++-----------------
 drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c  |  2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c   | 42 +++++++++++-----------
 drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h   |  2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c |  2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c |  2 +-
 6 files changed, 27 insertions(+), 60 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/dm_pp_interface.h b/drivers/gpu/drm/amd/include/dm_pp_interface.h
index 7852952d1fde..1d93a0c574c9 100644
--- a/drivers/gpu/drm/amd/include/dm_pp_interface.h
+++ b/drivers/gpu/drm/amd/include/dm_pp_interface.h
@@ -23,6 +23,8 @@
 #ifndef _DM_PP_INTERFACE_
 #define _DM_PP_INTERFACE_
 
+#include "dm_services_types.h"
+
 #define PP_MAX_CLOCK_LEVELS 16
 
 enum amd_pp_display_config_type{
@@ -189,39 +191,4 @@ struct pp_display_clock_request {
 	uint32_t clock_freq_in_khz;
 };
 
-#define PP_MAX_WM_SETS 4
-
-enum pp_wm_set_id {
-	DC_WM_SET_A = 0,
-	DC_WM_SET_B,
-	DC_WM_SET_C,
-	DC_WM_SET_D,
-	DC_WM_SET_INVALID = 0xffff,
-};
-
-struct pp_wm_set_with_dmif_clock_range_soc15 {
-	enum pp_wm_set_id wm_set_id;
-	uint32_t wm_min_dcefclk_in_khz;
-	uint32_t wm_max_dcefclk_in_khz;
-	uint32_t wm_min_memclk_in_khz;
-	uint32_t wm_max_memclk_in_khz;
-};
-
-struct pp_wm_set_with_mcif_clock_range_soc15 {
-	enum pp_wm_set_id wm_set_id;
-	uint32_t wm_min_socclk_in_khz;
-	uint32_t wm_max_socclk_in_khz;
-	uint32_t wm_min_memclk_in_khz;
-	uint32_t wm_max_memclk_in_khz;
-};
-
-struct pp_wm_sets_with_clock_ranges_soc15 {
-	uint32_t num_wm_sets_dmif;
-	uint32_t num_wm_sets_mcif;
-	struct pp_wm_set_with_dmif_clock_range_soc15
-		wm_sets_dmif[PP_MAX_WM_SETS];
-	struct pp_wm_set_with_mcif_clock_range_soc15
-		wm_sets_mcif[PP_MAX_WM_SETS];
-};
-
 #endif /* _DM_PP_INTERFACE_ */
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
index 02fc0bc41e0a..a63e00653324 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu10_hwmgr.c
@@ -1111,7 +1111,7 @@ static int smu10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 		void *clock_ranges)
 {
 	struct smu10_hwmgr *data = hwmgr->backend;
-	struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 	Watermarks_t *table = &(data->water_marks_table);
 	int result = 0;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 93a3d022ba47..3effb5583d1f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -652,7 +652,7 @@ int smu_get_voltage_dependency_table_ppt_v1(
 }
 
 int smu_set_watermarks_for_clocks_ranges(void *wt_table,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges)
 {
 	uint32_t i;
 	struct watermarks *table = wt_table;
@@ -660,49 +660,49 @@ int smu_set_watermarks_for_clocks_ranges(void *wt_table,
 	if (!table || !wm_with_clock_ranges)
 		return -EINVAL;
 
-	if (wm_with_clock_ranges->num_wm_sets_dmif > 4 || wm_with_clock_ranges->num_wm_sets_mcif > 4)
+	if (wm_with_clock_ranges->num_wm_dmif_sets > 4 || wm_with_clock_ranges->num_wm_mcif_sets > 4)
 		return -EINVAL;
 
-	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_dmif; i++) {
+	for (i = 0; i < wm_with_clock_ranges->num_wm_dmif_sets; i++) {
 		table->WatermarkRow[1][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_dcefclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_dcfclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_dcefclk_in_khz) /
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_dcfclk_clk_in_khz) /
 			100);
 		table->WatermarkRow[1][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_min_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_dmif[i].wm_max_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[1][i].WmSetting = (uint8_t)
-				wm_with_clock_ranges->wm_sets_dmif[i].wm_set_id;
+				wm_with_clock_ranges->wm_dmif_clocks_ranges[i].wm_set_id;
 	}
 
-	for (i = 0; i < wm_with_clock_ranges->num_wm_sets_mcif; i++) {
+	for (i = 0; i < wm_with_clock_ranges->num_wm_mcif_sets; i++) {
 		table->WatermarkRow[0][i].MinClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_socclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_socclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MaxClock =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_socclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_socclk_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MinUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_min_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_min_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].MaxUclk =
 			cpu_to_le16((uint16_t)
-			(wm_with_clock_ranges->wm_sets_mcif[i].wm_max_memclk_in_khz) /
-			100);
+			(wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_max_mem_clk_in_khz) /
+			1000);
 		table->WatermarkRow[0][i].WmSetting = (uint8_t)
-				wm_with_clock_ranges->wm_sets_mcif[i].wm_set_id;
+				wm_with_clock_ranges->wm_mcif_clocks_ranges[i].wm_set_id;
 	}
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
index 916cc01e7652..5454289d5226 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.h
@@ -107,7 +107,7 @@ int smu_get_voltage_dependency_table_ppt_v1(
 		struct phm_ppt_v1_clock_voltage_dependency_table *dep_table);
 
 int smu_set_watermarks_for_clocks_ranges(void *wt_table,
-		struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
+		struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges);
 
 #define PHM_FIELD_SHIFT(reg, field) reg##__##field##__SHIFT
 #define PHM_FIELD_MASK(reg, field) reg##__##field##_MASK
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index d515eb4fac9f..5e771bc119d6 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -4197,7 +4197,7 @@ static int vega10_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 							void *clock_range)
 {
 	struct vega10_hwmgr *data = hwmgr->backend;
-	struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_range;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_range;
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
 	int result = 0;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 0a090755545d..57492878874f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1785,7 +1785,7 @@ static int vega12_set_watermarks_for_clocks_ranges(struct pp_hwmgr *hwmgr,
 {
 	struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
 	Watermarks_t *table = &(data->smc_state_table.water_marks_table);
-	struct pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
+	struct dm_pp_wm_sets_with_clock_ranges_soc15 *wm_with_clock_ranges = clock_ranges;
 
 	if (!data->registry_data.disable_water_mark &&
 			data->smu_features[GNLD_DPM_DCEFCLK].supported &&
-- 
cgit v1.2.3


From 5d908944c5ba4fc8d301e1332635c64c1b77d843 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 4 Jul 2018 12:46:15 +0300
Subject: drm/amd/display: off by one in find_irq_source_info()

The ->info[] array has DAL_IRQ_SOURCES_NUMBER elements so this condition
should be >= instead of > or we could read one element beyond the end of
the array.

Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/irq/irq_service.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index dcdfa0f01551..604bea01fc13 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -78,7 +78,7 @@ const struct irq_source_info *find_irq_source_info(
 	struct irq_service *irq_service,
 	enum dc_irq_source source)
 {
-	if (source > DAL_IRQ_SOURCES_NUMBER || source < DC_IRQ_SOURCE_INVALID)
+	if (source >= DAL_IRQ_SOURCES_NUMBER || source < DC_IRQ_SOURCE_INVALID)
 		return NULL;
 
 	return &irq_service->info[source];
-- 
cgit v1.2.3


From 25177e7f94a3deeda410edaf9313d0f1a2bb68e0 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Wed, 4 Jul 2018 13:47:07 -0400
Subject: Revert "drm/amd/display: Fix indentation in dcn10 resource
 constructor"

That change was a merge gone bad.

This reverts commit cb1d7eacb58f7d1b7d0e57b26dc02d45eada4a3c.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 68be66eabc40..771e0cf29bba 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1068,8 +1068,7 @@ static bool construct(
 
 	ctx->dc_bios->regs = &bios_regs;
 
-		pool->base.res_cap = &res_cap;
-
+	pool->base.res_cap = &res_cap;
 	pool->base.funcs = &dcn10_res_pool_funcs;
 
 	/*
-- 
cgit v1.2.3


From 4c1ac53eb867670883f1518f620b19c2fed7e516 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 4 Jul 2018 10:27:30 -0700
Subject: drm/amd/display: Use 2-factor allocator calls

As already done treewide, switch from open-coded multiplication to
2-factor allocation helper.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/modules/color/color_gamma.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index 98edaefa2b47..ee69c949bfbf 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -1723,8 +1723,8 @@ bool  mod_color_calculate_curve(enum dc_transfer_func_predefined trans,
 		kvfree(rgb_regamma);
 	} else if (trans == TRANSFER_FUNCTION_HLG ||
 		trans == TRANSFER_FUNCTION_HLG12) {
-		rgb_regamma = kvzalloc(sizeof(*rgb_regamma) *
-				       (MAX_HW_POINTS + _EXTRA_POINTS),
+		rgb_regamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS,
+				       sizeof(*rgb_regamma),
 				       GFP_KERNEL);
 		if (!rgb_regamma)
 			goto rgb_regamma_alloc_fail;
@@ -1802,8 +1802,8 @@ bool  mod_color_calculate_degamma_curve(enum dc_transfer_func_predefined trans,
 		kvfree(rgb_degamma);
 	} else if (trans == TRANSFER_FUNCTION_HLG ||
 		trans == TRANSFER_FUNCTION_HLG12) {
-		rgb_degamma = kvzalloc(sizeof(*rgb_degamma) *
-				       (MAX_HW_POINTS + _EXTRA_POINTS),
+		rgb_degamma = kvcalloc(MAX_HW_POINTS + _EXTRA_POINTS,
+				       sizeof(*rgb_degamma),
 				       GFP_KERNEL);
 		if (!rgb_degamma)
 			goto rgb_degamma_alloc_fail;
-- 
cgit v1.2.3


From 6f3472a993e7cb63cde5d818dcabc8e42fc03744 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 08:22:11 -0500
Subject: drm/amd/display/dc/dce: Fix multiple potential integer overflows

Add suffix ULL to constant 5 and cast variables target_pix_clk_khz and
feedback_divider to uint64_t in order to avoid multiple potential integer
overflows and give the compiler complete information about the proper
arithmetic to use.

Notice that such constant and variables are used in contexts that
expect expressions of type uint64_t (64 bits, unsigned). The current
casts to uint64_t effectively apply to each expression as a whole,
but they do not prevent them from being evaluated using 32-bit
arithmetic instead of 64-bit arithmetic.

Also, once the expressions are properly evaluated using 64-bit
arithmentic, there is no need for the parentheses that enclose
them.

Addresses-Coverity-ID: 1460245 ("Unintentional integer overflow")
Addresses-Coverity-ID: 1460286 ("Unintentional integer overflow")
Addresses-Coverity-ID: 1460401 ("Unintentional integer overflow")
Fixes: 4562236b3bc0 ("drm/amd/dc: Add dc display driver (v2)")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index 88b09dd758ba..ca137757a69e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -133,7 +133,7 @@ static bool calculate_fb_and_fractional_fb_divider(
 	uint64_t feedback_divider;
 
 	feedback_divider =
-		(uint64_t)(target_pix_clk_khz * ref_divider * post_divider);
+		(uint64_t)target_pix_clk_khz * ref_divider * post_divider;
 	feedback_divider *= 10;
 	/* additional factor, since we divide by 10 afterwards */
 	feedback_divider *= (uint64_t)(calc_pll_cs->fract_fb_divider_factor);
@@ -145,8 +145,8 @@ static bool calculate_fb_and_fractional_fb_divider(
  * of fractional feedback decimal point and the fractional FB Divider precision
  * is 2 then the equation becomes (ullfeedbackDivider + 5*100) / (10*100))*/
 
-	feedback_divider += (uint64_t)
-			(5 * calc_pll_cs->fract_fb_divider_precision_factor);
+	feedback_divider += 5ULL *
+			    calc_pll_cs->fract_fb_divider_precision_factor;
 	feedback_divider =
 		div_u64(feedback_divider,
 			calc_pll_cs->fract_fb_divider_precision_factor * 10);
@@ -203,8 +203,8 @@ static bool calc_fb_divider_checking_tolerance(
 			&fract_feedback_divider);
 
 	/*Actual calculated value*/
-	actual_calc_clk_khz = (uint64_t)(feedback_divider *
-					calc_pll_cs->fract_fb_divider_factor) +
+	actual_calc_clk_khz = (uint64_t)feedback_divider *
+					calc_pll_cs->fract_fb_divider_factor +
 							fract_feedback_divider;
 	actual_calc_clk_khz *= calc_pll_cs->ref_freq_khz;
 	actual_calc_clk_khz =
-- 
cgit v1.2.3


From 87e3f1366eaa82c78b826b38008987406470b03d Mon Sep 17 00:00:00 2001
From: Darren Powell <darren.powell@amd.com>
Date: Mon, 25 Jun 2018 19:04:03 -0400
Subject: drm/amd: Remove errors from sphinx documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Eliminating the warnings produced by sphinx when processing the sphinx comments in
 amdgpu_device.c & amdgpu_mn.c

Signed-off-by: Darren Powell <darren.powell@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 20 ++++++++++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c     |  5 +++--
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d43abbd2a3cc..9883fa9bb41b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1076,7 +1076,7 @@ static const struct vga_switcheroo_client_ops amdgpu_switcheroo_ops = {
 /**
  * amdgpu_device_ip_set_clockgating_state - set the CG state
  *
- * @adev: amdgpu_device pointer
+ * @dev: amdgpu_device pointer
  * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
  * @state: clockgating state (gate or ungate)
  *
@@ -1110,7 +1110,7 @@ int amdgpu_device_ip_set_clockgating_state(void *dev,
 /**
  * amdgpu_device_ip_set_powergating_state - set the PG state
  *
- * @adev: amdgpu_device pointer
+ * @dev: amdgpu_device pointer
  * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
  * @state: powergating state (gate or ungate)
  *
@@ -1221,7 +1221,7 @@ bool amdgpu_device_ip_is_idle(struct amdgpu_device *adev,
  * amdgpu_device_ip_get_ip_block - get a hw IP pointer
  *
  * @adev: amdgpu_device pointer
- * @block_type: Type of hardware IP (SMU, GFX, UVD, etc.)
+ * @type: Type of hardware IP (SMU, GFX, UVD, etc.)
  *
  * Returns a pointer to the hardware IP block structure
  * if it exists for the asic, otherwise NULL.
@@ -2229,7 +2229,7 @@ bool amdgpu_device_has_dc_support(struct amdgpu_device *adev)
  * amdgpu_device_init - initialize the driver
  *
  * @adev: amdgpu_device pointer
- * @pdev: drm dev pointer
+ * @ddev: drm dev pointer
  * @pdev: pci dev pointer
  * @flags: driver flags
  *
@@ -2602,8 +2602,9 @@ void amdgpu_device_fini(struct amdgpu_device *adev)
 /**
  * amdgpu_device_suspend - initiate device suspend
  *
- * @pdev: drm dev pointer
- * @state: suspend state
+ * @dev: drm dev pointer
+ * @suspend: suspend state
+ * @fbcon : notify the fbdev of suspend
  *
  * Puts the hw in the suspend state (all asics).
  * Returns 0 for success or an error on failure.
@@ -2701,7 +2702,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 /**
  * amdgpu_device_resume - initiate device resume
  *
- * @pdev: drm dev pointer
+ * @dev: drm dev pointer
+ * @resume: resume state
+ * @fbcon : notify the fbdev of resume
  *
  * Bring the hw back to operating state (all asics).
  * Returns 0 for success or an error on failure.
@@ -3164,6 +3167,7 @@ out:
  * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
  *
  * @adev: amdgpu device pointer
+ * @from_hypervisor: request from hypervisor
  *
  * do VF FLR and reinitialize Asic
  * return 0 means successed otherwise failed
@@ -3211,7 +3215,7 @@ error:
  *
  * @adev: amdgpu device pointer
  * @job: which job trigger hang
- * @force forces reset regardless of amdgpu_gpu_recovery
+ * @force: forces reset regardless of amdgpu_gpu_recovery
  *
  * Attempt to reset the GPU if it has hung (all asics).
  * Returns 0 for success or an error on failure.
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index 72a3e8c68876..a365ea2383d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -58,7 +58,8 @@
  *
  * @adev: amdgpu device pointer
  * @mm: process address space
- * @mn: MMU notifier structur
+ * @mn: MMU notifier structure
+ * @type: type of MMU notifier
  * @work: destruction work item
  * @node: hash table node to find structure by adev and mn
  * @lock: rw semaphore protecting the notifier nodes
@@ -266,7 +267,7 @@ static void amdgpu_mn_invalidate_range_start_gfx(struct mmu_notifier *mn,
  * amdgpu_mn_invalidate_range_start_hsa - callback to notify about mm change
  *
  * @mn: our notifier
- * @mn: the mm this callback is about
+ * @mm: the mm this callback is about
  * @start: start of updated range
  * @end: end of updated range
  *
-- 
cgit v1.2.3


From fe61a2f1a57fea5d7b3d27d019fa67e1bc5b7079 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Wed, 4 Jul 2018 09:27:02 -0400
Subject: drm/amd/display: adding ycbcr420 pixel encoding for hdmi

[why]
HDMI EDID's VSDB contains spectial timings for specifically
YCbCr 4:2:0 colour space. In those cases we need to verify
if the mode provided is one of the special ones has to use
YCbCr 4:2:0 pixel encoding for display info.
[how]
Verify if the mode is using specific ycbcr420 colour space with
the help of DRM helper function and assign the mode to use
ycbcr420 pixel encoding.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 74683071fa81..1386c857546d 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2184,6 +2184,7 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 					     const struct drm_connector *connector)
 {
 	struct dc_crtc_timing *timing_out = &stream->timing;
+	const struct drm_display_info *info = &connector->display_info;
 
 	memset(timing_out, 0, sizeof(struct dc_crtc_timing));
 
@@ -2192,8 +2193,10 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 	timing_out->v_border_top = 0;
 	timing_out->v_border_bottom = 0;
 	/* TODO: un-hardcode */
-
-	if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
+	if (drm_mode_is_420_only(info, mode_in)
+			&& stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR420;
+	else if ((connector->display_info.color_formats & DRM_COLOR_FORMAT_YCRCB444)
 			&& stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
 		timing_out->pixel_encoding = PIXEL_ENCODING_YCBCR444;
 	else
-- 
cgit v1.2.3


From 400443e894c5a7f63f3ace3664640ec3ea4e1585 Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Tue, 3 Jul 2018 09:42:51 -0400
Subject: drm/amd/display: add a check for display depth validity

[why]
HDMI 2.0 fails to validate 4K@60 timing with 10 bpc
[how]
Adding a helper function that would verify if the display depth
assigned would pass a bandwidth validation.
Drop the display depth by one level till calculated pixel clk
is lower than maximum TMDS clk.

Bugzilla: https://bugs.freedesktop.org/106959

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 42 +++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 1386c857546d..ca017c1dd4da 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2176,6 +2176,46 @@ get_output_color_space(const struct dc_crtc_timing *dc_crtc_timing)
 	return color_space;
 }
 
+static void reduce_mode_colour_depth(struct dc_crtc_timing *timing_out)
+{
+	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+		return;
+
+	timing_out->display_color_depth--;
+}
+
+static void adjust_colour_depth_from_display_info(struct dc_crtc_timing *timing_out,
+						const struct drm_display_info *info)
+{
+	int normalized_clk;
+	if (timing_out->display_color_depth <= COLOR_DEPTH_888)
+		return;
+	do {
+		normalized_clk = timing_out->pix_clk_khz;
+		/* YCbCr 4:2:0 requires additional adjustment of 1/2 */
+		if (timing_out->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+			normalized_clk /= 2;
+		/* Adjusting pix clock following on HDMI spec based on colour depth */
+		switch (timing_out->display_color_depth) {
+		case COLOR_DEPTH_101010:
+			normalized_clk = (normalized_clk * 30) / 24;
+			break;
+		case COLOR_DEPTH_121212:
+			normalized_clk = (normalized_clk * 36) / 24;
+			break;
+		case COLOR_DEPTH_161616:
+			normalized_clk = (normalized_clk * 48) / 24;
+			break;
+		default:
+			return;
+		}
+		if (normalized_clk <= info->max_tmds_clock)
+			return;
+		reduce_mode_colour_depth(timing_out);
+
+	} while (timing_out->display_color_depth > COLOR_DEPTH_888);
+
+}
 /*****************************************************************************/
 
 static void
@@ -2232,6 +2272,8 @@ fill_stream_properties_from_drm_display_mode(struct dc_stream_state *stream,
 
 	stream->out_transfer_func->type = TF_TYPE_PREDEFINED;
 	stream->out_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
+	if (stream->sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A)
+		adjust_colour_depth_from_display_info(timing_out, info);
 }
 
 static void fill_audio_info(struct audio_info *audio_info,
-- 
cgit v1.2.3


From 8405cf39e8bd034be29971342fca49b01e772da2 Mon Sep 17 00:00:00 2001
From: Sonny Jiang <sonny.jiang@amd.com>
Date: Tue, 26 Jun 2018 15:48:34 -0400
Subject: drm/amdgpu: update documentation for amdgpu_drv.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Acked-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 Documentation/gpu/amdgpu.rst            |   7 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 232 +++++++++++++++++++++++++++++++-
 2 files changed, 232 insertions(+), 7 deletions(-)

diff --git a/Documentation/gpu/amdgpu.rst b/Documentation/gpu/amdgpu.rst
index 765c2a32938f..a740e491dfcc 100644
--- a/Documentation/gpu/amdgpu.rst
+++ b/Documentation/gpu/amdgpu.rst
@@ -5,6 +5,13 @@
 The drm/amdgpu driver supports all AMD Radeon GPUs based on the Graphics Core
 Next (GCN) architecture.
 
+Module Parameters
+=================
+
+The amdgpu driver supports the following module parameters:
+
+.. kernel-doc:: drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+
 Core Driver Infrastructure
 ==========================
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 963578c34c47..06aede194bf8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -1,10 +1,3 @@
-/**
- * \file amdgpu_drv.c
- * AMD Amdgpu driver
- *
- * \author Gareth Hughes <gareth@valinux.com>
- */
-
 /*
  * Copyright 2000 VA Linux Systems, Inc., Sunnyvale, California.
  * All Rights Reserved.
@@ -136,102 +129,239 @@ int amdgpu_gpu_recovery = -1; /* auto */
 int amdgpu_emu_mode = 0;
 uint amdgpu_smu_memory_pool_size = 0;
 
+/**
+ * DOC: vramlimit (int)
+ * Restrict the total amount of VRAM in MiB for testing.  The default is 0 (Use full VRAM).
+ */
 MODULE_PARM_DESC(vramlimit, "Restrict VRAM for testing, in megabytes");
 module_param_named(vramlimit, amdgpu_vram_limit, int, 0600);
 
+/**
+ * DOC: vis_vramlimit (int)
+ * Restrict the amount of CPU visible VRAM in MiB for testing.  The default is 0 (Use full CPU visible VRAM).
+ */
 MODULE_PARM_DESC(vis_vramlimit, "Restrict visible VRAM for testing, in megabytes");
 module_param_named(vis_vramlimit, amdgpu_vis_vram_limit, int, 0444);
 
+/**
+ * DOC: gartsize (uint)
+ * Restrict the size of GART in Mib (32, 64, etc.) for testing. The default is -1 (The size depends on asic).
+ */
 MODULE_PARM_DESC(gartsize, "Size of GART to setup in megabytes (32, 64, etc., -1=auto)");
 module_param_named(gartsize, amdgpu_gart_size, uint, 0600);
 
+/**
+ * DOC: gttsize (int)
+ * Restrict the size of GTT domain in MiB for testing. The default is -1 (It's VRAM size if 3GB < VRAM < 3/4 RAM,
+ * otherwise 3/4 RAM size).
+ */
 MODULE_PARM_DESC(gttsize, "Size of the GTT domain in megabytes (-1 = auto)");
 module_param_named(gttsize, amdgpu_gtt_size, int, 0600);
 
+/**
+ * DOC: moverate (int)
+ * Set maximum buffer migration rate in MB/s. The default is -1 (8 MB/s).
+ */
 MODULE_PARM_DESC(moverate, "Maximum buffer migration rate in MB/s. (32, 64, etc., -1=auto, 0=1=disabled)");
 module_param_named(moverate, amdgpu_moverate, int, 0600);
 
+/**
+ * DOC: benchmark (int)
+ * Run benchmarks. The default is 0 (Skip benchmarks).
+ */
 MODULE_PARM_DESC(benchmark, "Run benchmark");
 module_param_named(benchmark, amdgpu_benchmarking, int, 0444);
 
+/**
+ * DOC: test (int)
+ * Test BO GTT->VRAM and VRAM->GTT GPU copies. The default is 0 (Skip test, only set 1 to run test).
+ */
 MODULE_PARM_DESC(test, "Run tests");
 module_param_named(test, amdgpu_testing, int, 0444);
 
+/**
+ * DOC: audio (int)
+ * Set HDMI/DPAudio. Only affects non-DC display handling. The default is -1 (Enabled), set 0 to disabled it.
+ */
 MODULE_PARM_DESC(audio, "Audio enable (-1 = auto, 0 = disable, 1 = enable)");
 module_param_named(audio, amdgpu_audio, int, 0444);
 
+/**
+ * DOC: disp_priority (int)
+ * Set display Priority (1 = normal, 2 = high). Only affects non-DC display handling. The default is 0 (auto).
+ */
 MODULE_PARM_DESC(disp_priority, "Display Priority (0 = auto, 1 = normal, 2 = high)");
 module_param_named(disp_priority, amdgpu_disp_priority, int, 0444);
 
+/**
+ * DOC: hw_i2c (int)
+ * To enable hw i2c engine. Only affects non-DC display handling. The default is 0 (Disabled).
+ */
 MODULE_PARM_DESC(hw_i2c, "hw i2c engine enable (0 = disable)");
 module_param_named(hw_i2c, amdgpu_hw_i2c, int, 0444);
 
+/**
+ * DOC: pcie_gen2 (int)
+ * To disable PCIE Gen2/3 mode (0 = disable, 1 = enable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(pcie_gen2, "PCIE Gen2 mode (-1 = auto, 0 = disable, 1 = enable)");
 module_param_named(pcie_gen2, amdgpu_pcie_gen2, int, 0444);
 
+/**
+ * DOC: msi (int)
+ * To disable Message Signaled Interrupts (MSI) functionality (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(msi, "MSI support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(msi, amdgpu_msi, int, 0444);
 
+/**
+ * DOC: lockup_timeout (int)
+ * Set GPU scheduler timeout value in ms. Value 0 is invalidated, will be adjusted to 10000.
+ * Negative values mean 'infinite timeout' (MAX_JIFFY_OFFSET). The default is 10000.
+ */
 MODULE_PARM_DESC(lockup_timeout, "GPU lockup timeout in ms > 0 (default 10000)");
 module_param_named(lockup_timeout, amdgpu_lockup_timeout, int, 0444);
 
+/**
+ * DOC: dpm (int)
+ * Override for dynamic power management setting (1 = enable, 0 = disable). The default is -1 (auto).
+ */
 MODULE_PARM_DESC(dpm, "DPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(dpm, amdgpu_dpm, int, 0444);
 
+/**
+ * DOC: fw_load_type (int)
+ * Set different firmware loading type for debugging (0 = direct, 1 = SMU, 2 = PSP). The default is -1 (auto).
+ */
 MODULE_PARM_DESC(fw_load_type, "firmware loading type (0 = direct, 1 = SMU, 2 = PSP, -1 = auto)");
 module_param_named(fw_load_type, amdgpu_fw_load_type, int, 0444);
 
+/**
+ * DOC: aspm (int)
+ * To disable ASPM (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(aspm, "ASPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(aspm, amdgpu_aspm, int, 0444);
 
+/**
+ * DOC: runpm (int)
+ * Override for runtime power management control for dGPUs in PX/HG laptops. The amdgpu driver can dynamically power down
+ * the dGPU on PX/HG laptops when it is idle. The default is -1 (auto enable). Setting the value to 0 disables this functionality.
+ */
 MODULE_PARM_DESC(runpm, "PX runtime pm (1 = force enable, 0 = disable, -1 = PX only default)");
 module_param_named(runpm, amdgpu_runtime_pm, int, 0444);
 
+/**
+ * DOC: ip_block_mask (uint)
+ * Override what IP blocks are enabled on the GPU. Each GPU is a collection of IP blocks (gfx, display, video, etc.).
+ * Use this parameter to disable specific blocks. Note that the IP blocks do not have a fixed index. Some asics may not have
+ * some IPs or may include multiple instances of an IP so the ordering various from asic to asic. See the driver output in
+ * the kernel log for the list of IPs on the asic. The default is 0xffffffff (enable all blocks on a device).
+ */
 MODULE_PARM_DESC(ip_block_mask, "IP Block Mask (all blocks enabled (default))");
 module_param_named(ip_block_mask, amdgpu_ip_block_mask, uint, 0444);
 
+/**
+ * DOC: bapm (int)
+ * Bidirectional Application Power Management (BAPM) used to dynamically share TDP between CPU and GPU. Set value 0 to disable it.
+ * The default -1 (auto, enabled)
+ */
 MODULE_PARM_DESC(bapm, "BAPM support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(bapm, amdgpu_bapm, int, 0444);
 
+/**
+ * DOC: deep_color (int)
+ * Set 1 to enable Deep Color support. Only affects non-DC display handling. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(deep_color, "Deep Color support (1 = enable, 0 = disable (default))");
 module_param_named(deep_color, amdgpu_deep_color, int, 0444);
 
+/**
+ * DOC: vm_size (int)
+ * Override the size of the GPU's per client virtual address space in GiB.  The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_size, "VM address space size in gigabytes (default 64GB)");
 module_param_named(vm_size, amdgpu_vm_size, int, 0444);
 
+/**
+ * DOC: vm_fragment_size (int)
+ * Override VM fragment size in bits (4, 5, etc. 4 = 64K, 9 = 2M). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_fragment_size, "VM fragment size in bits (4, 5, etc. 4 = 64K (default), Max 9 = 2M)");
 module_param_named(vm_fragment_size, amdgpu_vm_fragment_size, int, 0444);
 
+/**
+ * DOC: vm_block_size (int)
+ * Override VM page table size in bits (default depending on vm_size and hw setup). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(vm_block_size, "VM page table size in bits (default depending on vm_size)");
 module_param_named(vm_block_size, amdgpu_vm_block_size, int, 0444);
 
+/**
+ * DOC: vm_fault_stop (int)
+ * Stop on VM fault for debugging (0 = never, 1 = print first, 2 = always). The default is 0 (No stop).
+ */
 MODULE_PARM_DESC(vm_fault_stop, "Stop on VM fault (0 = never (default), 1 = print first, 2 = always)");
 module_param_named(vm_fault_stop, amdgpu_vm_fault_stop, int, 0444);
 
+/**
+ * DOC: vm_debug (int)
+ * Debug VM handling (0 = disabled, 1 = enabled). The default is 0 (Disabled).
+ */
 MODULE_PARM_DESC(vm_debug, "Debug VM handling (0 = disabled (default), 1 = enabled)");
 module_param_named(vm_debug, amdgpu_vm_debug, int, 0644);
 
+/**
+ * DOC: vm_update_mode (int)
+ * Override VM update mode. VM updated by using CPU (0 = never, 1 = Graphics only, 2 = Compute only, 3 = Both). The default
+ * is -1 (Only in large BAR(LB) systems Compute VM tables will be updated by CPU, otherwise 0, never).
+ */
 MODULE_PARM_DESC(vm_update_mode, "VM update using CPU (0 = never (default except for large BAR(LB)), 1 = Graphics only, 2 = Compute only (default for LB), 3 = Both");
 module_param_named(vm_update_mode, amdgpu_vm_update_mode, int, 0444);
 
+/**
+ * DOC: vram_page_split (int)
+ * Override the number of pages after we split VRAM allocations (default 512, -1 = disable). The default is 512.
+ */
 MODULE_PARM_DESC(vram_page_split, "Number of pages after we split VRAM allocations (default 512, -1 = disable)");
 module_param_named(vram_page_split, amdgpu_vram_page_split, int, 0444);
 
+/**
+ * DOC: exp_hw_support (int)
+ * Enable experimental hw support (1 = enable). The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(exp_hw_support, "experimental hw support (1 = enable, 0 = disable (default))");
 module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
 
+/**
+ * DOC: dc (int)
+ * Disable/Enable Display Core driver for debugging (1 = enable, 0 = disable). The default is -1 (automatic for each asic).
+ */
 MODULE_PARM_DESC(dc, "Display Core driver (1 = enable, 0 = disable, -1 = auto (default))");
 module_param_named(dc, amdgpu_dc, int, 0444);
 
 MODULE_PARM_DESC(dc_log, "Display Core Log Level (0 = minimal (default), 1 = chatty");
 module_param_named(dc_log, amdgpu_dc_log, int, 0444);
 
+/**
+ * DOC: sched_jobs (int)
+ * Override the max number of jobs supported in the sw queue. The default is 32.
+ */
 MODULE_PARM_DESC(sched_jobs, "the max number of jobs supported in the sw queue (default 32)");
 module_param_named(sched_jobs, amdgpu_sched_jobs, int, 0444);
 
+/**
+ * DOC: sched_hw_submission (int)
+ * Override the max number of HW submissions. The default is 2.
+ */
 MODULE_PARM_DESC(sched_hw_submission, "the max number of HW submissions (default 2)");
 module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 
+/**
+ * DOC: ppfeaturemask (uint)
+ * Override power features enabled. See enum PP_FEATURE_MASK in drivers/gpu/drm/amd/include/amd_shared.h.
+ * The default is the current set of stable power features.
+ */
 MODULE_PARM_DESC(ppfeaturemask, "all power features enabled (default))");
 module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, uint, 0444);
 
@@ -241,58 +371,135 @@ module_param_named(no_evict, amdgpu_no_evict, int, 0444);
 MODULE_PARM_DESC(direct_gma_size, "Direct GMA size in megabytes (max 96MB)");
 module_param_named(direct_gma_size, amdgpu_direct_gma_size, int, 0444);
 
+/**
+ * DOC: pcie_gen_cap (uint)
+ * Override PCIE gen speed capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
+ * The default is 0 (automatic for each asic).
+ */
 MODULE_PARM_DESC(pcie_gen_cap, "PCIE Gen Caps (0: autodetect (default))");
 module_param_named(pcie_gen_cap, amdgpu_pcie_gen_cap, uint, 0444);
 
+/**
+ * DOC: pcie_lane_cap (uint)
+ * Override PCIE lanes capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
+ * The default is 0 (automatic for each asic).
+ */
 MODULE_PARM_DESC(pcie_lane_cap, "PCIE Lane Caps (0: autodetect (default))");
 module_param_named(pcie_lane_cap, amdgpu_pcie_lane_cap, uint, 0444);
 
+/**
+ * DOC: cg_mask (uint)
+ * Override Clockgating features enabled on GPU (0 = disable clock gating). See the AMD_CG_SUPPORT flags in
+ * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffff (all enabled).
+ */
 MODULE_PARM_DESC(cg_mask, "Clockgating flags mask (0 = disable clock gating)");
 module_param_named(cg_mask, amdgpu_cg_mask, uint, 0444);
 
+/**
+ * DOC: pg_mask (uint)
+ * Override Powergating features enabled on GPU (0 = disable power gating). See the AMD_PG_SUPPORT flags in
+ * drivers/gpu/drm/amd/include/amd_shared.h. The default is 0xffffffff (all enabled).
+ */
 MODULE_PARM_DESC(pg_mask, "Powergating flags mask (0 = disable power gating)");
 module_param_named(pg_mask, amdgpu_pg_mask, uint, 0444);
 
+/**
+ * DOC: sdma_phase_quantum (uint)
+ * Override SDMA context switch phase quantum (x 1K GPU clock cycles, 0 = no change). The default is 32.
+ */
 MODULE_PARM_DESC(sdma_phase_quantum, "SDMA context switch phase quantum (x 1K GPU clock cycles, 0 = no change (default 32))");
 module_param_named(sdma_phase_quantum, amdgpu_sdma_phase_quantum, uint, 0444);
 
+/**
+ * DOC: disable_cu (charp)
+ * Set to disable CUs (It's set like se.sh.cu,...). The default is NULL.
+ */
 MODULE_PARM_DESC(disable_cu, "Disable CUs (se.sh.cu,...)");
 module_param_named(disable_cu, amdgpu_disable_cu, charp, 0444);
 
+/**
+ * DOC: virtual_display (charp)
+ * Set to enable virtual display feature. This feature provides a virtual display hardware on headless boards
+ * or in virtualized environments. It will be set like xxxx:xx:xx.x,x;xxxx:xx:xx.x,x. It's the pci address of
+ * the device, plus the number of crtcs to expose. E.g., 0000:26:00.0,4 would enable 4 virtual crtcs on the pci
+ * device at 26:00.0. The default is NULL.
+ */
 MODULE_PARM_DESC(virtual_display,
 		 "Enable virtual display feature (the virtual_display will be set like xxxx:xx:xx.x,x;xxxx:xx:xx.x,x)");
 module_param_named(virtual_display, amdgpu_virtual_display, charp, 0444);
 
+/**
+ * DOC: ngg (int)
+ * Set to enable Next Generation Graphics (1 = enable). The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(ngg, "Next Generation Graphics (1 = enable, 0 = disable(default depending on gfx))");
 module_param_named(ngg, amdgpu_ngg, int, 0444);
 
+/**
+ * DOC: prim_buf_per_se (int)
+ * Override the size of Primitive Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(prim_buf_per_se, "the size of Primitive Buffer per Shader Engine (default depending on gfx)");
 module_param_named(prim_buf_per_se, amdgpu_prim_buf_per_se, int, 0444);
 
+/**
+ * DOC: pos_buf_per_se (int)
+ * Override the size of Position Buffer per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(pos_buf_per_se, "the size of Position Buffer per Shader Engine (default depending on gfx)");
 module_param_named(pos_buf_per_se, amdgpu_pos_buf_per_se, int, 0444);
 
+/**
+ * DOC: cntl_sb_buf_per_se (int)
+ * Override the size of Control Sideband per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(cntl_sb_buf_per_se, "the size of Control Sideband per Shader Engine (default depending on gfx)");
 module_param_named(cntl_sb_buf_per_se, amdgpu_cntl_sb_buf_per_se, int, 0444);
 
+/**
+ * DOC: param_buf_per_se (int)
+ * Override the size of Off-Chip Pramater Cache per Shader Engine in Byte. The default is 0 (depending on gfx).
+ */
 MODULE_PARM_DESC(param_buf_per_se, "the size of Off-Chip Pramater Cache per Shader Engine (default depending on gfx)");
 module_param_named(param_buf_per_se, amdgpu_param_buf_per_se, int, 0444);
 
+/**
+ * DOC: job_hang_limit (int)
+ * Set how much time allow a job hang and not drop it. The default is 0.
+ */
 MODULE_PARM_DESC(job_hang_limit, "how much time allow a job hang and not drop it (default 0)");
 module_param_named(job_hang_limit, amdgpu_job_hang_limit, int ,0444);
 
+/**
+ * DOC: lbpw (int)
+ * Override Load Balancing Per Watt (LBPW) support (1 = enable, 0 = disable). The default is -1 (auto, enabled).
+ */
 MODULE_PARM_DESC(lbpw, "Load Balancing Per Watt (LBPW) support (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(lbpw, amdgpu_lbpw, int, 0444);
 
 MODULE_PARM_DESC(compute_multipipe, "Force compute queues to be spread across pipes (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(compute_multipipe, amdgpu_compute_multipipe, int, 0444);
 
+/**
+ * DOC: gpu_recovery (int)
+ * Set to enable GPU recovery mechanism (1 = enable, 0 = disable). The default is -1 (auto, disabled except SRIOV).
+ */
 MODULE_PARM_DESC(gpu_recovery, "Enable GPU recovery mechanism, (1 = enable, 0 = disable, -1 = auto)");
 module_param_named(gpu_recovery, amdgpu_gpu_recovery, int, 0444);
 
+/**
+ * DOC: emu_mode (int)
+ * Set value 1 to enable emulation mode. This is only needed when running on an emulator. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(emu_mode, "Emulation mode, (1 = enable, 0 = disable)");
 module_param_named(emu_mode, amdgpu_emu_mode, int, 0444);
 
+/**
+ * DOC: si_support (int)
+ * Set SI support driver. This parameter works after set config CONFIG_DRM_AMDGPU_SI. For SI asic, when radeon driver is enabled,
+ * set value 0 to use radeon driver, while set value 1 to use amdgpu driver. The default is using radeon driver when it available,
+ * otherwise using amdgpu driver.
+ */
 #ifdef CONFIG_DRM_AMDGPU_SI
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
@@ -306,6 +513,12 @@ MODULE_PARM_DESC(si_support, "SI support (1 = enabled (default), 0 = disabled)")
 module_param_named(si_support, amdgpu_si_support, int, 0444);
 #endif
 
+/**
+ * DOC: cik_support (int)
+ * Set CIK support driver. This parameter works after set config CONFIG_DRM_AMDGPU_CIK. For CIK asic, when radeon driver is enabled,
+ * set value 0 to use radeon driver, while set value 1 to use amdgpu driver. The default is using radeon driver when it available,
+ * otherwise using amdgpu driver.
+ */
 #ifdef CONFIG_DRM_AMDGPU_CIK
 
 #if defined(CONFIG_DRM_RADEON) || defined(CONFIG_DRM_RADEON_MODULE)
@@ -319,6 +532,11 @@ MODULE_PARM_DESC(cik_support, "CIK support (1 = enabled (default), 0 = disabled)
 module_param_named(cik_support, amdgpu_cik_support, int, 0444);
 #endif
 
+/**
+ * DOC: smu_memory_pool_size (uint)
+ * It is used to reserve gtt for smu debug usage, setting value 0 to disable it. The actual size is value * 256MiB.
+ * E.g. 0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte. The default is 0 (disabled).
+ */
 MODULE_PARM_DESC(smu_memory_pool_size,
 	"reserve gtt for smu debug usage, 0 = disable,"
 		"0x1 = 256Mbyte, 0x2 = 512Mbyte, 0x4 = 1 Gbyte, 0x8 = 2GByte");
-- 
cgit v1.2.3


From 43911fb68b19f7c37ab69eff8e6a3c1370bc0cb5 Mon Sep 17 00:00:00 2001
From: Darren Powell <darren.powell@amd.com>
Date: Wed, 27 Jun 2018 17:05:20 -0400
Subject: drm/amd: Add sphinx documentation for amd_ip_funcs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Darren Powell <darren.powell@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/amd_shared.h | 45 +++++++++++++++++++-------------
 1 file changed, 27 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/amd_shared.h b/drivers/gpu/drm/amd/include/amd_shared.h
index d6f487497397..265621d8945c 100644
--- a/drivers/gpu/drm/amd/include/amd_shared.h
+++ b/drivers/gpu/drm/amd/include/amd_shared.h
@@ -131,45 +131,54 @@ enum PP_FEATURE_MASK {
 	PP_STUTTER_MODE = 0x20000,
 };
 
+/**
+ * struct amd_ip_funcs - general hooks for managing amdgpu IP Blocks
+ */
 struct amd_ip_funcs {
-	/* Name of IP block */
+	/** @name: Name of IP block */
 	char *name;
-	/* sets up early driver state (pre sw_init), does not configure hw - Optional */
+	/**
+	 * @early_init:
+	 *
+	 * sets up early driver state (pre sw_init),
+	 * does not configure hw - Optional
+	 */
 	int (*early_init)(void *handle);
-	/* sets up late driver/hw state (post hw_init) - Optional */
+	/** @late_init: sets up late driver/hw state (post hw_init) - Optional */
 	int (*late_init)(void *handle);
-	/* sets up driver state, does not configure hw */
+	/** @sw_init: sets up driver state, does not configure hw */
 	int (*sw_init)(void *handle);
-	/* tears down driver state, does not configure hw */
+	/** @sw_fini: tears down driver state, does not configure hw */
 	int (*sw_fini)(void *handle);
-	/* sets up the hw state */
+	/** @hw_init: sets up the hw state */
 	int (*hw_init)(void *handle);
-	/* tears down the hw state */
+	/** @hw_fini: tears down the hw state */
 	int (*hw_fini)(void *handle);
+	/** @late_fini: final cleanup */
 	void (*late_fini)(void *handle);
-	/* handles IP specific hw/sw changes for suspend */
+	/** @suspend: handles IP specific hw/sw changes for suspend */
 	int (*suspend)(void *handle);
-	/* handles IP specific hw/sw changes for resume */
+	/** @resume: handles IP specific hw/sw changes for resume */
 	int (*resume)(void *handle);
-	/* returns current IP block idle status */
+	/** @is_idle: returns current IP block idle status */
 	bool (*is_idle)(void *handle);
-	/* poll for idle */
+	/** @wait_for_idle: poll for idle */
 	int (*wait_for_idle)(void *handle);
-	/* check soft reset the IP block */
+	/** @check_soft_reset: check soft reset the IP block */
 	bool (*check_soft_reset)(void *handle);
-	/* pre soft reset the IP block */
+	/** @pre_soft_reset: pre soft reset the IP block */
 	int (*pre_soft_reset)(void *handle);
-	/* soft reset the IP block */
+	/** @soft_reset: soft reset the IP block */
 	int (*soft_reset)(void *handle);
-	/* post soft reset the IP block */
+	/** @post_soft_reset: post soft reset the IP block */
 	int (*post_soft_reset)(void *handle);
-	/* enable/disable cg for the IP block */
+	/** @set_clockgating_state: enable/disable cg for the IP block */
 	int (*set_clockgating_state)(void *handle,
 				     enum amd_clockgating_state state);
-	/* enable/disable pg for the IP block */
+	/** @set_powergating_state: enable/disable pg for the IP block */
 	int (*set_powergating_state)(void *handle,
 				     enum amd_powergating_state state);
-	/* get current clockgating status */
+	/** @get_clockgating_state: get current clockgating status */
 	void (*get_clockgating_state)(void *handle, u32 *flags);
 };
 
-- 
cgit v1.2.3


From efe6aaca67a0229a195f493d142102c864b41dde Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Thu, 5 Jul 2018 15:47:39 +0100
Subject: net: ipv4: fix list processing on L3 slave devices

If we have an L3 master device, l3mdev_ip_rcv() will steal the skb, but
 we were returning NET_RX_SUCCESS from ip_rcv_finish_core() which meant
 that ip_list_rcv_finish() would keep it on the list.  Instead let's
 move the l3mdev_ip_rcv() call into the caller, so that our response to
 a steal can be different in the single packet path (return
 NET_RX_SUCCESS) and the list path (forget this packet and continue).

Fixes: 5fa12739a53d ("net: ipv4: listify ip_rcv_finish")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_input.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 14ba628b2761..1a3b6f32b1c9 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -316,13 +316,6 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 	struct rtable *rt;
 	int err;
 
-	/* if ingress device is enslaved to an L3 master device pass the
-	 * skb to its handler for processing
-	 */
-	skb = l3mdev_ip_rcv(skb);
-	if (!skb)
-		return NET_RX_SUCCESS;
-
 	if (net->ipv4.sysctl_ip_early_demux &&
 	    !skb_dst(skb) &&
 	    !skb->sk &&
@@ -408,8 +401,16 @@ drop_error:
 
 static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	int ret = ip_rcv_finish_core(net, sk, skb);
+	int ret;
+
+	/* if ingress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip_rcv(skb);
+	if (!skb)
+		return NET_RX_SUCCESS;
 
+	ret = ip_rcv_finish_core(net, sk, skb);
 	if (ret != NET_RX_DROP)
 		ret = dst_input(skb);
 	return ret;
@@ -545,6 +546,12 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 		struct dst_entry *dst;
 
 		list_del(&skb->list);
+		/* if ingress device is enslaved to an L3 master device pass the
+		 * skb to its handler for processing
+		 */
+		skb = l3mdev_ip_rcv(skb);
+		if (!skb)
+			continue;
 		if (ip_rcv_finish_core(net, sk, skb) == NET_RX_DROP)
 			continue;
 
-- 
cgit v1.2.3


From d8269e2cbf908f9d26aa5d3217236227dffd1d89 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Thu, 5 Jul 2018 15:49:42 +0100
Subject: net: ipv6: listify ipv6_rcv() and ip6_rcv_finish()

Essentially the same as the ipv4 equivalents.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h   |   2 +
 net/ipv6/af_inet6.c  |   1 +
 net/ipv6/ip6_input.c | 131 ++++++++++++++++++++++++++++++++++++++++++++-------
 3 files changed, 118 insertions(+), 16 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 16475c269749..b7843e0b16ee 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -922,6 +922,8 @@ static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6)
 
 int ipv6_rcv(struct sk_buff *skb, struct net_device *dev,
 	     struct packet_type *pt, struct net_device *orig_dev);
+void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
+		   struct net_device *orig_dev);
 
 int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 9ed0eae91758..c9535354149f 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -764,6 +764,7 @@ EXPORT_SYMBOL_GPL(ipv6_opt_accepted);
 static struct packet_type ipv6_packet_type __read_mostly = {
 	.type = cpu_to_be16(ETH_P_IPV6),
 	.func = ipv6_rcv,
+	.list_func = ipv6_list_rcv,
 };
 
 static int __init ipv6_packet_init(void)
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index f08d34491ece..6242682be876 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -47,17 +47,11 @@
 #include <net/inet_ecn.h>
 #include <net/dst_metadata.h>
 
-int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
+				struct sk_buff *skb)
 {
 	void (*edemux)(struct sk_buff *skb);
 
-	/* if ingress device is enslaved to an L3 master device pass the
-	 * skb to its handler for processing
-	 */
-	skb = l3mdev_ip6_rcv(skb);
-	if (!skb)
-		return NET_RX_SUCCESS;
-
 	if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) {
 		const struct inet6_protocol *ipprot;
 
@@ -67,20 +61,73 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	}
 	if (!skb_valid_dst(skb))
 		ip6_route_input(skb);
+}
+
+int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	/* if ingress device is enslaved to an L3 master device pass the
+	 * skb to its handler for processing
+	 */
+	skb = l3mdev_ip6_rcv(skb);
+	if (!skb)
+		return NET_RX_SUCCESS;
+	ip6_rcv_finish_core(net, sk, skb);
 
 	return dst_input(skb);
 }
 
-int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+static void ip6_sublist_rcv_finish(struct list_head *head)
+{
+	struct sk_buff *skb, *next;
+
+	list_for_each_entry_safe(skb, next, head, list)
+		dst_input(skb);
+}
+
+static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
+				struct list_head *head)
+{
+	struct dst_entry *curr_dst = NULL;
+	struct sk_buff *skb, *next;
+	struct list_head sublist;
+
+	INIT_LIST_HEAD(&sublist);
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct dst_entry *dst;
+
+		list_del(&skb->list);
+		/* if ingress device is enslaved to an L3 master device pass the
+		 * skb to its handler for processing
+		 */
+		skb = l3mdev_ip6_rcv(skb);
+		if (!skb)
+			continue;
+		ip6_rcv_finish_core(net, sk, skb);
+		dst = skb_dst(skb);
+		if (curr_dst != dst) {
+			/* dispatch old sublist */
+			if (!list_empty(&sublist))
+				ip6_sublist_rcv_finish(&sublist);
+			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
+			curr_dst = dst;
+		}
+		list_add_tail(&skb->list, &sublist);
+	}
+	/* dispatch final sublist */
+	ip6_sublist_rcv_finish(&sublist);
+}
+
+static struct sk_buff *ip6_rcv_core(struct sk_buff *skb, struct net_device *dev,
+				    struct net *net)
 {
 	const struct ipv6hdr *hdr;
 	u32 pkt_len;
 	struct inet6_dev *idev;
-	struct net *net = dev_net(skb->dev);
 
 	if (skb->pkt_type == PACKET_OTHERHOST) {
 		kfree_skb(skb);
-		return NET_RX_DROP;
+		return NULL;
 	}
 
 	rcu_read_lock();
@@ -196,7 +243,7 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 		if (ipv6_parse_hopopts(skb) < 0) {
 			__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 			rcu_read_unlock();
-			return NET_RX_DROP;
+			return NULL;
 		}
 	}
 
@@ -205,15 +252,67 @@ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
 	/* Must drop socket now because of tproxy. */
 	skb_orphan(skb);
 
-	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
-		       net, NULL, skb, dev, NULL,
-		       ip6_rcv_finish);
+	return skb;
 err:
 	__IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS);
 drop:
 	rcu_read_unlock();
 	kfree_skb(skb);
-	return NET_RX_DROP;
+	return NULL;
+}
+
+int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct net *net = dev_net(skb->dev);
+
+	skb = ip6_rcv_core(skb, dev, net);
+	if (skb == NULL)
+		return NET_RX_DROP;
+	return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
+		       net, NULL, skb, dev, NULL,
+		       ip6_rcv_finish);
+}
+
+static void ip6_sublist_rcv(struct list_head *head, struct net_device *dev,
+			    struct net *net)
+{
+	NF_HOOK_LIST(NFPROTO_IPV6, NF_INET_PRE_ROUTING, net, NULL,
+		     head, dev, NULL, ip6_rcv_finish);
+	ip6_list_rcv_finish(net, NULL, head);
+}
+
+/* Receive a list of IPv6 packets */
+void ipv6_list_rcv(struct list_head *head, struct packet_type *pt,
+		   struct net_device *orig_dev)
+{
+	struct net_device *curr_dev = NULL;
+	struct net *curr_net = NULL;
+	struct sk_buff *skb, *next;
+	struct list_head sublist;
+
+	INIT_LIST_HEAD(&sublist);
+	list_for_each_entry_safe(skb, next, head, list) {
+		struct net_device *dev = skb->dev;
+		struct net *net = dev_net(dev);
+
+		list_del(&skb->list);
+		skb = ip6_rcv_core(skb, dev, net);
+		if (skb == NULL)
+			continue;
+
+		if (curr_dev != dev || curr_net != net) {
+			/* dispatch old sublist */
+			if (!list_empty(&sublist))
+				ip6_sublist_rcv(&sublist, curr_dev, curr_net);
+			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
+			curr_dev = dev;
+			curr_net = net;
+		}
+		list_add_tail(&skb->list, &sublist);
+	}
+	/* dispatch final sublist */
+	ip6_sublist_rcv(&sublist, curr_dev, curr_net);
 }
 
 /*
-- 
cgit v1.2.3


From c4e4f4545bdc3939ae9fff1da55ed1e28776dafe Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 5 Jul 2018 16:02:14 +0100
Subject: drm/i915/selftests: Fail hangcheck testing if the GPU is wedged

If the GPU is irrecoverably wedged on startup, it means that it failed
on initialisation and we have already tried to reset it but failed. We
can ignore all further testing, as it is already dead. Failing early,
prevents us from slowly failing in our endeavours later and timing out.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705150214.28316-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 72547aa24538..5cb808dc5b50 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -1243,6 +1243,9 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 	if (!intel_has_gpu_reset(i915))
 		return 0;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return -EIO; /* we're long past hope of a successful reset */
+
 	intel_runtime_pm_get(i915);
 	saved_hangcheck = fetch_and_zero(&i915_modparams.enable_hangcheck);
 
-- 
cgit v1.2.3


From ad03b821fbc30395b72af438f5bb41676a5f891d Mon Sep 17 00:00:00 2001
From: Philipp Rudo <prudo@linux.ibm.com>
Date: Tue, 26 Jun 2018 12:24:30 +0200
Subject: s390/purgatory: Fix crash with expoline enabled

When the kernel is built with CONFIG_EXPOLINE=y and a compiler with
indirect branch mitigation enabled the purgatory crashes. The reason for
that is that the macros defined for expoline are used in mem.S. These
macros define new sections (.text.__s390x_indirect_*) which are marked
executable. Due to the missing linker script those sections are linked to
address 0, just as the .text section. In combination with the entry point
also being at address 0 this causes the purgatory load code
(kernel/kexec_file.c: kexec_purgatory_setup_sechdrs) to update the entry
point twice. Thus the old kernel jumps to some 'random' address causing the
crash.

To fix this turn off expolines for the purgatory. There is no problem with
this in this case due to the fact that the purgatory only runs once and the
tlb is purged (diag 308) in the end.

Fixes: 840798a1f5299 ("s390/kexec_file: Add purgatory")
Cc: <stable@vger.kernel.org> # 4.17
Signed-off-by: Philipp Rudo <prudo@linux.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/purgatory/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 1ace023cbdce..704e0f3c244a 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -23,6 +23,7 @@ KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
+KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
 
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
-- 
cgit v1.2.3


From c315e69308c739a43c4ebc539bedbc1ac8d79854 Mon Sep 17 00:00:00 2001
From: Philipp Rudo <prudo@linux.ibm.com>
Date: Tue, 26 Jun 2018 18:24:52 +0200
Subject: s390/purgatory: Add missing FORCE to Makefile targets

Without FORCE make does not detect changes only made to the command line
options. So object files might not be re-built even when they should be.
Fix this by adding FORCE where it is missing.

Fixes: 840798a1f5299 ("s390/kexec_file: Add purgatory")
Cc: <stable@vger.kernel.org> # 4.17
Signed-off-by: Philipp Rudo <prudo@linux.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/purgatory/Makefile | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 704e0f3c244a..abfa8c7a6d9a 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -7,13 +7,13 @@ purgatory-y := head.o purgatory.o string.o sha256.o mem.o
 targets += $(purgatory-y) purgatory.ro kexec-purgatory.c
 PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 
-$(obj)/sha256.o: $(srctree)/lib/sha256.c
+$(obj)/sha256.o: $(srctree)/lib/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S
+$(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
 
-$(obj)/string.o: $(srctree)/arch/s390/lib/string.c
+$(obj)/string.o: $(srctree)/arch/s390/lib/string.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
 LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined -nostdlib
-- 
cgit v1.2.3


From 287d6070acbb2529e24462faffca46663885dddc Mon Sep 17 00:00:00 2001
From: Philipp Rudo <prudo@linux.ibm.com>
Date: Wed, 27 Jun 2018 12:03:43 +0200
Subject: s390/purgatory: Remove duplicate variable definitions

Currently there are some variables in the purgatory (e.g. kernel_entry)
which are defined twice, once in assembler- and once in c-code. The reason
for this is that these variables are set during purgatory load, where
sanity checks on the corresponding Elf_Sym's are made, while they are used
in assembler-code. Thus adding a second definition in c-code is a handy
workaround to guarantee correct Elf_Sym's are created.

When the purgatory is compiled with -fcommon (default for gcc on s390) this
is no problem because both symbols are merged by the linker. However this
is not required by ISO C and when the purgatory is built with -fno-common
the linker fails with errors like

arch/s390/purgatory/purgatory.o:(.bss+0x18): multiple definition of `kernel_entry'
arch/s390/purgatory/head.o:/.../arch/s390/purgatory/head.S:230: first defined here

Thus remove the duplicate definitions and add the required size and type
information to the assembler definition. Also add -fno-common to the
command line options to prevent similar hacks in the future.

Signed-off-by: Philipp Rudo <prudo@linux.ibm.com>
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/purgatory.h |  6 ------
 arch/s390/purgatory/Makefile      |  2 +-
 arch/s390/purgatory/head.S        | 45 +++++++++++++++++----------------------
 arch/s390/purgatory/purgatory.c   |  9 --------
 4 files changed, 20 insertions(+), 42 deletions(-)

diff --git a/arch/s390/include/asm/purgatory.h b/arch/s390/include/asm/purgatory.h
index 6090670df51f..e297bcfc476f 100644
--- a/arch/s390/include/asm/purgatory.h
+++ b/arch/s390/include/asm/purgatory.h
@@ -13,11 +13,5 @@
 
 int verify_sha256_digest(void);
 
-extern u64 kernel_entry;
-extern u64 kernel_type;
-
-extern u64 crash_start;
-extern u64 crash_size;
-
 #endif	/* __ASSEMBLY__ */
 #endif /* _S390_PURGATORY_H_ */
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index abfa8c7a6d9a..8d61218a71aa 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -21,7 +21,7 @@ LDFLAGS_purgatory.ro += -z nodefaultlib
 KBUILD_CFLAGS := -fno-strict-aliasing -Wall -Wstrict-prototypes
 KBUILD_CFLAGS += -Wno-pointer-sign -Wno-sign-compare
 KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
-KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float
+KBUILD_CFLAGS += -c -MD -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
 
diff --git a/arch/s390/purgatory/head.S b/arch/s390/purgatory/head.S
index 660c96a05a9b..2e3707b12edd 100644
--- a/arch/s390/purgatory/head.S
+++ b/arch/s390/purgatory/head.S
@@ -243,33 +243,26 @@ gprregs:
 	.quad	0
 	.endr
 
-purgatory_sha256_digest:
-	.global purgatory_sha256_digest
-	.rept	32	/* SHA256_DIGEST_SIZE */
-	.byte	0
-	.endr
-
-purgatory_sha_regions:
-	.global purgatory_sha_regions
-	.rept	16 * __KEXEC_SHA_REGION_SIZE	/* KEXEC_SEGMENTS_MAX */
-	.byte	0
-	.endr
-
-kernel_entry:
-	.global kernel_entry
-	.quad	0
-
-kernel_type:
-	.global kernel_type
-	.quad	0
-
-crash_start:
-	.global crash_start
-	.quad	0
+/* Macro to define a global variable with name and size (in bytes) to be
+ * shared with C code.
+ *
+ * Add the .size and .type attribute to satisfy checks on the Elf_Sym during
+ * purgatory load.
+ */
+.macro GLOBAL_VARIABLE name,size
+\name:
+	.global \name
+	.size	\name,\size
+	.type	\name,object
+	.skip	\size,0
+.endm
 
-crash_size:
-	.global crash_size
-	.quad	0
+GLOBAL_VARIABLE purgatory_sha256_digest,32
+GLOBAL_VARIABLE purgatory_sha_regions,16*__KEXEC_SHA_REGION_SIZE
+GLOBAL_VARIABLE kernel_entry,8
+GLOBAL_VARIABLE kernel_type,8
+GLOBAL_VARIABLE crash_start,8
+GLOBAL_VARIABLE crash_size,8
 
 	.align	PAGE_SIZE
 stack:
diff --git a/arch/s390/purgatory/purgatory.c b/arch/s390/purgatory/purgatory.c
index 4e2beb3c29b7..3528e6da4e87 100644
--- a/arch/s390/purgatory/purgatory.c
+++ b/arch/s390/purgatory/purgatory.c
@@ -12,15 +12,6 @@
 #include <linux/string.h>
 #include <asm/purgatory.h>
 
-struct kexec_sha_region purgatory_sha_regions[KEXEC_SEGMENT_MAX];
-u8 purgatory_sha256_digest[SHA256_DIGEST_SIZE];
-
-u64 kernel_entry;
-u64 kernel_type;
-
-u64 crash_start;
-u64 crash_size;
-
 int verify_sha256_digest(void)
 {
 	struct kexec_sha_region *ptr, *end;
-- 
cgit v1.2.3


From 5bedf8aa03c28cb8dc98bdd32a41b66d8f7d3eaa Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 24 Jun 2018 12:17:43 +0200
Subject: s390/mm: correct allocate_pgste proc_handler callback

Since proc_dointvec does not perform value range control,
proc_dointvec_minmax should be used to limit value range, which is
clearly intended here, as the internal representation of the value:

unsigned int alloc_pgste:1;

In fact it currently works, since we have

      mm->context.alloc_pgste = page_table_allocate_pgste || ...

... since commit 23fefe119ceb5 ("s390/kvm: avoid global config of vm.alloc_pgste=1")

Before that it was

       mm->context.alloc_pgste = page_table_allocate_pgste;

which was broken. That was introduced with commit 0b46e0a3ec0d7 ("s390/kvm:
remove delayed reallocation of page tables for KVM").

Fixes: 0b46e0a3ec0d7 ("s390/kvm: remove delayed reallocation of page tables for KVM")
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/pgalloc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 84bd6329a88d..6cf9c9ff2bff 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -28,7 +28,7 @@ static struct ctl_table page_table_sysctl[] = {
 		.data		= &page_table_allocate_pgste,
 		.maxlen		= sizeof(int),
 		.mode		= S_IRUGO | S_IWUSR,
-		.proc_handler	= proc_dointvec,
+		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= &page_table_allocate_pgste_min,
 		.extra2		= &page_table_allocate_pgste_max,
 	},
-- 
cgit v1.2.3


From f149371e9e02d23495fc796c09075adeb376a375 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 24 Jun 2018 23:28:12 +0200
Subject: s390/sclp_async: replace callhome proc handler with generic one

Reuse generic proc_dointvec_minmax proc handler instead of
proc_handler_callhome.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/char/sclp_async.c | 38 +++++++-------------------------------
 1 file changed, 7 insertions(+), 31 deletions(-)

diff --git a/drivers/s390/char/sclp_async.c b/drivers/s390/char/sclp_async.c
index ee6f3b563728..e69b12a40636 100644
--- a/drivers/s390/char/sclp_async.c
+++ b/drivers/s390/char/sclp_async.c
@@ -64,42 +64,18 @@ static struct notifier_block call_home_panic_nb = {
 	.priority = INT_MAX,
 };
 
-static int proc_handler_callhome(struct ctl_table *ctl, int write,
-				 void __user *buffer, size_t *count,
-				 loff_t *ppos)
-{
-	unsigned long val;
-	int len, rc;
-	char buf[3];
-
-	if (!*count || (*ppos && !write)) {
-		*count = 0;
-		return 0;
-	}
-	if (!write) {
-		len = snprintf(buf, sizeof(buf), "%d\n", callhome_enabled);
-		rc = copy_to_user(buffer, buf, sizeof(buf));
-		if (rc != 0)
-			return -EFAULT;
-	} else {
-		len = *count;
-		rc = kstrtoul_from_user(buffer, len, 0, &val);
-		if (rc)
-			return rc;
-		if (val != 0 && val != 1)
-			return -EINVAL;
-		callhome_enabled = val;
-	}
-	*count = len;
-	*ppos += len;
-	return 0;
-}
+static int zero;
+static int one = 1;
 
 static struct ctl_table callhome_table[] = {
 	{
 		.procname	= "callhome",
+		.data		= &callhome_enabled,
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_handler_callhome,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
 	},
 	{}
 };
-- 
cgit v1.2.3


From 196851bed5221a7670024e3ad39704c6d92b2014 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 24 Jun 2018 12:28:46 +0200
Subject: s390/topology: correct topology mode proc handler

Reuse proc_douintvec_minmax to simplify topology mode proc handler.
This also enforces correct range of 0-1 on proc writes and correctly
handles numbers starting with 0 or spaces.

Before:
$ echo 01 > /proc/sys/s390/topology
$ cat /proc/sys/s390/topology
0
$ echo ' 1' > /proc/sys/s390/topology
-bash: echo: write error: Invalid argument
$ echo 2 > /proc/sys/s390/topology
-bash: echo: write error: Invalid argument
$ echo 12 > /proc/sys/s390/topology
$ cat /proc/sys/s390/topology
1

After:
$ echo 01 > /proc/sys/s390/topology
$ cat /proc/sys/s390/topology
1
$ echo ' 1' > /proc/sys/s390/topology
$ cat /proc/sys/s390/topology
1
$ echo 2 > /proc/sys/s390/topology
-bash: echo: write error: Invalid argument
$ echo 12 > /proc/sys/s390/topology
-bash: echo: write error: Invalid argument
$ echo '   0' > /proc/sys/s390/topology
$ cat /proc/sys/s390/topology
0

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/topology.c | 43 ++++++++++++++++++-------------------------
 1 file changed, 18 insertions(+), 25 deletions(-)

diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 33ebb423c613..e8184a15578a 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -579,40 +579,33 @@ early_param("topology", topology_setup);
 static int topology_ctl_handler(struct ctl_table *ctl, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
+	int enabled = topology_is_enabled();
 	int new_mode;
-	char buf[2];
+	int zero = 0;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &enabled,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
+
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		memcpy(buf, topology_is_enabled() ? "1\n" : "0\n", ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
-	if (buf[0] != '0' && buf[0] != '1')
-		return -EINVAL;
 	mutex_lock(&smp_cpu_state_mutex);
-	new_mode = topology_get_mode(buf[0] == '1');
+	new_mode = topology_get_mode(enabled);
 	if (topology_mode != new_mode) {
 		topology_mode = new_mode;
 		topology_schedule_update();
 	}
 	mutex_unlock(&smp_cpu_state_mutex);
 	topology_flush_work();
-out:
-	*lenp = len;
-	*ppos += len;
-	return 0;
+
+	return rc;
 }
 
 static struct ctl_table topology_ctl_table[] = {
-- 
cgit v1.2.3


From 71e33a1dd712dc6f68de733218d4506bea26bda6 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 1 Jul 2018 15:56:28 +0200
Subject: s390/cmm: split and simplify cmm pages proc handler

Split cmm_pages_handler into cmm_pages_handler and
cmm_timed_pages_handler, each handling separate proc entry.  And reuse
proc_doulongvec_minmax to simplify proc handlers. Min/max values are
optional and are omitted here.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/cmm.c | 67 ++++++++++++++++++++++++++----------------------------
 1 file changed, 32 insertions(+), 35 deletions(-)

diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 6cf024eb2085..50d8d1c887a4 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -251,45 +251,42 @@ static int cmm_skip_blanks(char *cp, char **endp)
 	return str != cp;
 }
 
-static struct ctl_table cmm_table[];
-
 static int cmm_pages_handler(struct ctl_table *ctl, int write,
 			     void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	char buf[16], *p;
-	unsigned int len;
-	long nr;
+	long nr = cmm_get_pages();
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &nr,
+		.maxlen		= sizeof(long),
+	};
+	int rc;
 
-	if (!*lenp || (*ppos && !write)) {
-		*lenp = 0;
-		return 0;
-	}
+	rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (write) {
-		len = *lenp;
-		if (copy_from_user(buf, buffer,
-				   len > sizeof(buf) ? sizeof(buf) : len))
-			return -EFAULT;
-		buf[sizeof(buf) - 1] = '\0';
-		cmm_skip_blanks(buf, &p);
-		nr = simple_strtoul(p, &p, 0);
-		if (ctl == &cmm_table[0])
-			cmm_set_pages(nr);
-		else
-			cmm_add_timed_pages(nr);
-	} else {
-		if (ctl == &cmm_table[0])
-			nr = cmm_get_pages();
-		else
-			nr = cmm_get_timed_pages();
-		len = sprintf(buf, "%ld\n", nr);
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-	}
-	*lenp = len;
-	*ppos += len;
+	cmm_set_pages(nr);
+	return 0;
+}
+
+static int cmm_timed_pages_handler(struct ctl_table *ctl, int write,
+				   void __user *buffer, size_t *lenp,
+				   loff_t *ppos)
+{
+	long nr = cmm_get_timed_pages();
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &nr,
+		.maxlen		= sizeof(long),
+	};
+	int rc;
+
+	rc = proc_doulongvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
+
+	cmm_add_timed_pages(nr);
 	return 0;
 }
 
@@ -338,7 +335,7 @@ static struct ctl_table cmm_table[] = {
 	{
 		.procname	= "cmm_timed_pages",
 		.mode		= 0644,
-		.proc_handler	= cmm_pages_handler,
+		.proc_handler	= cmm_timed_pages_handler,
 	},
 	{
 		.procname	= "cmm_timeout",
-- 
cgit v1.2.3


From 6c8021503f728b4b3eda69876c20e1ff30767a22 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Sun, 1 Jul 2018 16:59:44 +0200
Subject: s390/appldata: reuse generic proc handler functions

Simplify appldata proc handlers by reusing generic proc handler functions.

Tested-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Reviewed-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/appldata/appldata_base.c | 121 ++++++++++++++-----------------------
 1 file changed, 45 insertions(+), 76 deletions(-)

diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index 25c1399b0787..9bf8489df6e6 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -206,34 +206,28 @@ static int
 appldata_timer_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
-	char buf[2];
+	int timer_active = appldata_timer_active;
+	int zero = 0;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &timer_active,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
+
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		memcpy(buf, appldata_timer_active ? "1\n" : "0\n", ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
 	spin_lock(&appldata_timer_lock);
-	if (buf[0] == '1')
+	if (timer_active)
 		__appldata_vtimer_setup(APPLDATA_ADD_TIMER);
-	else if (buf[0] == '0')
+	else
 		__appldata_vtimer_setup(APPLDATA_DEL_TIMER);
 	spin_unlock(&appldata_timer_lock);
-out:
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
@@ -247,37 +241,24 @@ static int
 appldata_interval_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	unsigned int len;
-	int interval;
-	char buf[16];
+	int interval = appldata_interval;
+	int one = 1;
+	int rc;
+	struct ctl_table ctl_entry = {
+		.procname	= ctl->procname,
+		.data		= &interval,
+		.maxlen		= sizeof(int),
+		.extra1		= &one,
+	};
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
-		return 0;
-	}
-	if (!write) {
-		len = sprintf(buf, "%i\n", appldata_interval);
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len))
-			return -EFAULT;
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer, len > sizeof(buf) ? sizeof(buf) : len))
-		return -EFAULT;
-	interval = 0;
-	sscanf(buf, "%i", &interval);
-	if (interval <= 0)
-		return -EINVAL;
+	rc = proc_dointvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write)
+		return rc;
 
 	spin_lock(&appldata_timer_lock);
 	appldata_interval = interval;
 	__appldata_vtimer_setup(APPLDATA_MOD_TIMER);
 	spin_unlock(&appldata_timer_lock);
-out:
-	*lenp = len;
-	*ppos += len;
 	return 0;
 }
 
@@ -292,10 +273,17 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 			   void __user *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct appldata_ops *ops = NULL, *tmp_ops;
-	unsigned int len;
-	int rc, found;
-	char buf[2];
 	struct list_head *lh;
+	int rc, found;
+	int active;
+	int zero = 0;
+	int one = 1;
+	struct ctl_table ctl_entry = {
+		.data		= &active,
+		.maxlen		= sizeof(int),
+		.extra1		= &zero,
+		.extra2		= &one,
+	};
 
 	found = 0;
 	mutex_lock(&appldata_ops_mutex);
@@ -316,31 +304,15 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 	}
 	mutex_unlock(&appldata_ops_mutex);
 
-	if (!*lenp || *ppos) {
-		*lenp = 0;
+	active = ops->active;
+	rc = proc_douintvec_minmax(&ctl_entry, write, buffer, lenp, ppos);
+	if (rc < 0 || !write) {
 		module_put(ops->owner);
-		return 0;
-	}
-	if (!write) {
-		memcpy(buf, ops->active ? "1\n" : "0\n", ARRAY_SIZE(buf));
-		len = strnlen(buf, ARRAY_SIZE(buf));
-		if (len > *lenp)
-			len = *lenp;
-		if (copy_to_user(buffer, buf, len)) {
-			module_put(ops->owner);
-			return -EFAULT;
-		}
-		goto out;
-	}
-	len = *lenp;
-	if (copy_from_user(buf, buffer,
-			   len > sizeof(buf) ? sizeof(buf) : len)) {
-		module_put(ops->owner);
-		return -EFAULT;
+		return rc;
 	}
 
 	mutex_lock(&appldata_ops_mutex);
-	if ((buf[0] == '1') && (ops->active == 0)) {
+	if (active && (ops->active == 0)) {
 		// protect work queue callback
 		if (!try_module_get(ops->owner)) {
 			mutex_unlock(&appldata_ops_mutex);
@@ -358,7 +330,7 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 			module_put(ops->owner);
 		} else
 			ops->active = 1;
-	} else if ((buf[0] == '0') && (ops->active == 1)) {
+	} else if (!active && (ops->active == 1)) {
 		ops->active = 0;
 		rc = appldata_diag(ops->record_nr, APPLDATA_STOP_REC,
 				(unsigned long) ops->data, ops->size,
@@ -369,9 +341,6 @@ appldata_generic_handler(struct ctl_table *ctl, int write,
 		module_put(ops->owner);
 	}
 	mutex_unlock(&appldata_ops_mutex);
-out:
-	*lenp = len;
-	*ppos += len;
 	module_put(ops->owner);
 	return 0;
 }
-- 
cgit v1.2.3


From ca3589c11815cb1587a908c46e8f04a05a193254 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 5 Jul 2018 16:25:07 +0300
Subject: drm/i915/dsi: rename the current DSI files based on first platform
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Starting from ICL or gen 11 we have a new DSI block which requires
completely different programming from the current implementation. Having
them in the same file would be confusing. Rename the current DSI and DSI
PLL implementation files as vlv_dsi.c and vlv_dsi_pll.c.

No functional changes.

v2: use "gen7" prefix.

v3: use "vlv" prefix.

References: https://patchwork.freedesktop.org/series/44823/
Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705132509.12881-1-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/Makefile        |    6 +-
 drivers/gpu/drm/i915/intel_drv.h     |    2 +-
 drivers/gpu/drm/i915/intel_dsi.c     | 1866 ----------------------------------
 drivers/gpu/drm/i915/intel_dsi.h     |    4 +-
 drivers/gpu/drm/i915/intel_dsi_pll.c |  650 ------------
 drivers/gpu/drm/i915/vlv_dsi.c       | 1866 ++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/vlv_dsi_pll.c   |  650 ++++++++++++
 7 files changed, 2522 insertions(+), 2522 deletions(-)
 delete mode 100644 drivers/gpu/drm/i915/intel_dsi.c
 delete mode 100644 drivers/gpu/drm/i915/intel_dsi_pll.c
 create mode 100644 drivers/gpu/drm/i915/vlv_dsi.c
 create mode 100644 drivers/gpu/drm/i915/vlv_dsi_pll.c

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index 4c6adae23e18..e7fedb83aafc 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -141,9 +141,7 @@ i915-y += dvo_ch7017.o \
 	  intel_dp_link_training.o \
 	  intel_dp_mst.o \
 	  intel_dp.o \
-	  intel_dsi.o \
 	  intel_dsi_dcs_backlight.o \
-	  intel_dsi_pll.o \
 	  intel_dsi_vbt.o \
 	  intel_dvo.o \
 	  intel_hdmi.o \
@@ -152,7 +150,9 @@ i915-y += dvo_ch7017.o \
 	  intel_lvds.o \
 	  intel_panel.o \
 	  intel_sdvo.o \
-	  intel_tv.o
+	  intel_tv.o \
+	  vlv_dsi.o \
+	  vlv_dsi_pll.o
 
 # Post-mortem debug and GPU hang state capture
 i915-$(CONFIG_DRM_I915_CAPTURE_ERROR) += i915_gpu_error.o
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index cdfdebc11ef8..88d3581124e8 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1730,7 +1730,7 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector);
 /* intel_dp_mst.c */
 int intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_id);
 void intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port);
-/* intel_dsi.c */
+/* vlv_dsi.c */
 void intel_dsi_init(struct drm_i915_private *dev_priv);
 
 /* intel_dsi_dcs_backlight.c */
diff --git a/drivers/gpu/drm/i915/intel_dsi.c b/drivers/gpu/drm/i915/intel_dsi.c
deleted file mode 100644
index 3b7acb5a70b3..000000000000
--- a/drivers/gpu/drm/i915/intel_dsi.c
+++ /dev/null
@@ -1,1866 +0,0 @@
-/*
- * Copyright © 2013 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Author: Jani Nikula <jani.nikula@intel.com>
- */
-
-#include <drm/drmP.h>
-#include <drm/drm_atomic_helper.h>
-#include <drm/drm_crtc.h>
-#include <drm/drm_edid.h>
-#include <drm/i915_drm.h>
-#include <drm/drm_mipi_dsi.h>
-#include <linux/slab.h>
-#include <linux/gpio/consumer.h>
-#include "i915_drv.h"
-#include "intel_drv.h"
-#include "intel_dsi.h"
-
-/* return pixels in terms of txbyteclkhs */
-static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count,
-		       u16 burst_mode_ratio)
-{
-	return DIV_ROUND_UP(DIV_ROUND_UP(pixels * bpp * burst_mode_ratio,
-					 8 * 100), lane_count);
-}
-
-/* return pixels equvalent to txbyteclkhs */
-static u16 pixels_from_txbyteclkhs(u16 clk_hs, int bpp, int lane_count,
-			u16 burst_mode_ratio)
-{
-	return DIV_ROUND_UP((clk_hs * lane_count * 8 * 100),
-						(bpp * burst_mode_ratio));
-}
-
-enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt)
-{
-	/* It just so happens the VBT matches register contents. */
-	switch (fmt) {
-	case VID_MODE_FORMAT_RGB888:
-		return MIPI_DSI_FMT_RGB888;
-	case VID_MODE_FORMAT_RGB666:
-		return MIPI_DSI_FMT_RGB666;
-	case VID_MODE_FORMAT_RGB666_PACKED:
-		return MIPI_DSI_FMT_RGB666_PACKED;
-	case VID_MODE_FORMAT_RGB565:
-		return MIPI_DSI_FMT_RGB565;
-	default:
-		MISSING_CASE(fmt);
-		return MIPI_DSI_FMT_RGB666;
-	}
-}
-
-void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
-{
-	struct drm_encoder *encoder = &intel_dsi->base.base;
-	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	u32 mask;
-
-	mask = LP_CTRL_FIFO_EMPTY | HS_CTRL_FIFO_EMPTY |
-		LP_DATA_FIFO_EMPTY | HS_DATA_FIFO_EMPTY;
-
-	if (intel_wait_for_register(dev_priv,
-				    MIPI_GEN_FIFO_STAT(port), mask, mask,
-				    100))
-		DRM_ERROR("DPI FIFOs are not empty\n");
-}
-
-static void write_data(struct drm_i915_private *dev_priv,
-		       i915_reg_t reg,
-		       const u8 *data, u32 len)
-{
-	u32 i, j;
-
-	for (i = 0; i < len; i += 4) {
-		u32 val = 0;
-
-		for (j = 0; j < min_t(u32, len - i, 4); j++)
-			val |= *data++ << 8 * j;
-
-		I915_WRITE(reg, val);
-	}
-}
-
-static void read_data(struct drm_i915_private *dev_priv,
-		      i915_reg_t reg,
-		      u8 *data, u32 len)
-{
-	u32 i, j;
-
-	for (i = 0; i < len; i += 4) {
-		u32 val = I915_READ(reg);
-
-		for (j = 0; j < min_t(u32, len - i, 4); j++)
-			*data++ = val >> 8 * j;
-	}
-}
-
-static ssize_t intel_dsi_host_transfer(struct mipi_dsi_host *host,
-				       const struct mipi_dsi_msg *msg)
-{
-	struct intel_dsi_host *intel_dsi_host = to_intel_dsi_host(host);
-	struct drm_device *dev = intel_dsi_host->intel_dsi->base.base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	enum port port = intel_dsi_host->port;
-	struct mipi_dsi_packet packet;
-	ssize_t ret;
-	const u8 *header, *data;
-	i915_reg_t data_reg, ctrl_reg;
-	u32 data_mask, ctrl_mask;
-
-	ret = mipi_dsi_create_packet(&packet, msg);
-	if (ret < 0)
-		return ret;
-
-	header = packet.header;
-	data = packet.payload;
-
-	if (msg->flags & MIPI_DSI_MSG_USE_LPM) {
-		data_reg = MIPI_LP_GEN_DATA(port);
-		data_mask = LP_DATA_FIFO_FULL;
-		ctrl_reg = MIPI_LP_GEN_CTRL(port);
-		ctrl_mask = LP_CTRL_FIFO_FULL;
-	} else {
-		data_reg = MIPI_HS_GEN_DATA(port);
-		data_mask = HS_DATA_FIFO_FULL;
-		ctrl_reg = MIPI_HS_GEN_CTRL(port);
-		ctrl_mask = HS_CTRL_FIFO_FULL;
-	}
-
-	/* note: this is never true for reads */
-	if (packet.payload_length) {
-		if (intel_wait_for_register(dev_priv,
-					    MIPI_GEN_FIFO_STAT(port),
-					    data_mask, 0,
-					    50))
-			DRM_ERROR("Timeout waiting for HS/LP DATA FIFO !full\n");
-
-		write_data(dev_priv, data_reg, packet.payload,
-			   packet.payload_length);
-	}
-
-	if (msg->rx_len) {
-		I915_WRITE(MIPI_INTR_STAT(port), GEN_READ_DATA_AVAIL);
-	}
-
-	if (intel_wait_for_register(dev_priv,
-				    MIPI_GEN_FIFO_STAT(port),
-				    ctrl_mask, 0,
-				    50)) {
-		DRM_ERROR("Timeout waiting for HS/LP CTRL FIFO !full\n");
-	}
-
-	I915_WRITE(ctrl_reg, header[2] << 16 | header[1] << 8 | header[0]);
-
-	/* ->rx_len is set only for reads */
-	if (msg->rx_len) {
-		data_mask = GEN_READ_DATA_AVAIL;
-		if (intel_wait_for_register(dev_priv,
-					    MIPI_INTR_STAT(port),
-					    data_mask, data_mask,
-					    50))
-			DRM_ERROR("Timeout waiting for read data.\n");
-
-		read_data(dev_priv, data_reg, msg->rx_buf, msg->rx_len);
-	}
-
-	/* XXX: fix for reads and writes */
-	return 4 + packet.payload_length;
-}
-
-static int intel_dsi_host_attach(struct mipi_dsi_host *host,
-				 struct mipi_dsi_device *dsi)
-{
-	return 0;
-}
-
-static int intel_dsi_host_detach(struct mipi_dsi_host *host,
-				 struct mipi_dsi_device *dsi)
-{
-	return 0;
-}
-
-static const struct mipi_dsi_host_ops intel_dsi_host_ops = {
-	.attach = intel_dsi_host_attach,
-	.detach = intel_dsi_host_detach,
-	.transfer = intel_dsi_host_transfer,
-};
-
-static struct intel_dsi_host *intel_dsi_host_init(struct intel_dsi *intel_dsi,
-						  enum port port)
-{
-	struct intel_dsi_host *host;
-	struct mipi_dsi_device *device;
-
-	host = kzalloc(sizeof(*host), GFP_KERNEL);
-	if (!host)
-		return NULL;
-
-	host->base.ops = &intel_dsi_host_ops;
-	host->intel_dsi = intel_dsi;
-	host->port = port;
-
-	/*
-	 * We should call mipi_dsi_host_register(&host->base) here, but we don't
-	 * have a host->dev, and we don't have OF stuff either. So just use the
-	 * dsi framework as a library and hope for the best. Create the dsi
-	 * devices by ourselves here too. Need to be careful though, because we
-	 * don't initialize any of the driver model devices here.
-	 */
-	device = kzalloc(sizeof(*device), GFP_KERNEL);
-	if (!device) {
-		kfree(host);
-		return NULL;
-	}
-
-	device->host = &host->base;
-	host->device = device;
-
-	return host;
-}
-
-/*
- * send a video mode command
- *
- * XXX: commands with data in MIPI_DPI_DATA?
- */
-static int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs,
-			enum port port)
-{
-	struct drm_encoder *encoder = &intel_dsi->base.base;
-	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	u32 mask;
-
-	/* XXX: pipe, hs */
-	if (hs)
-		cmd &= ~DPI_LP_MODE;
-	else
-		cmd |= DPI_LP_MODE;
-
-	/* clear bit */
-	I915_WRITE(MIPI_INTR_STAT(port), SPL_PKT_SENT_INTERRUPT);
-
-	/* XXX: old code skips write if control unchanged */
-	if (cmd == I915_READ(MIPI_DPI_CONTROL(port)))
-		DRM_DEBUG_KMS("Same special packet %02x twice in a row.\n", cmd);
-
-	I915_WRITE(MIPI_DPI_CONTROL(port), cmd);
-
-	mask = SPL_PKT_SENT_INTERRUPT;
-	if (intel_wait_for_register(dev_priv,
-				    MIPI_INTR_STAT(port), mask, mask,
-				    100))
-		DRM_ERROR("Video mode command 0x%08x send failed.\n", cmd);
-
-	return 0;
-}
-
-static void band_gap_reset(struct drm_i915_private *dev_priv)
-{
-	mutex_lock(&dev_priv->sb_lock);
-
-	vlv_flisdsi_write(dev_priv, 0x08, 0x0001);
-	vlv_flisdsi_write(dev_priv, 0x0F, 0x0005);
-	vlv_flisdsi_write(dev_priv, 0x0F, 0x0025);
-	udelay(150);
-	vlv_flisdsi_write(dev_priv, 0x0F, 0x0000);
-	vlv_flisdsi_write(dev_priv, 0x08, 0x0000);
-
-	mutex_unlock(&dev_priv->sb_lock);
-}
-
-static inline bool is_vid_mode(struct intel_dsi *intel_dsi)
-{
-	return intel_dsi->operation_mode == INTEL_DSI_VIDEO_MODE;
-}
-
-static inline bool is_cmd_mode(struct intel_dsi *intel_dsi)
-{
-	return intel_dsi->operation_mode == INTEL_DSI_COMMAND_MODE;
-}
-
-static bool intel_dsi_compute_config(struct intel_encoder *encoder,
-				     struct intel_crtc_state *pipe_config,
-				     struct drm_connector_state *conn_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
-						   base);
-	struct intel_connector *intel_connector = intel_dsi->attached_connector;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
-	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	int ret;
-
-	DRM_DEBUG_KMS("\n");
-
-	if (fixed_mode) {
-		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
-
-		if (HAS_GMCH_DISPLAY(dev_priv))
-			intel_gmch_panel_fitting(crtc, pipe_config,
-						 conn_state->scaling_mode);
-		else
-			intel_pch_panel_fitting(crtc, pipe_config,
-						conn_state->scaling_mode);
-	}
-
-	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return false;
-
-	/* DSI uses short packets for sync events, so clear mode flags for DSI */
-	adjusted_mode->flags = 0;
-
-	if (IS_GEN9_LP(dev_priv)) {
-		/* Enable Frame time stamp based scanline reporting */
-		adjusted_mode->private_flags |=
-			I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP;
-
-		/* Dual link goes to DSI transcoder A. */
-		if (intel_dsi->ports == BIT(PORT_C))
-			pipe_config->cpu_transcoder = TRANSCODER_DSI_C;
-		else
-			pipe_config->cpu_transcoder = TRANSCODER_DSI_A;
-	}
-
-	ret = intel_compute_dsi_pll(encoder, pipe_config);
-	if (ret)
-		return false;
-
-	pipe_config->clock_set = true;
-
-	return true;
-}
-
-static bool glk_dsi_enable_io(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 tmp;
-	bool cold_boot = false;
-
-	/* Set the MIPI mode
-	 * If MIPI_Mode is off, then writing to LP_Wake bit is not reflecting.
-	 * Power ON MIPI IO first and then write into IO reset and LP wake bits
-	 */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		tmp = I915_READ(MIPI_CTRL(port));
-		I915_WRITE(MIPI_CTRL(port), tmp | GLK_MIPIIO_ENABLE);
-	}
-
-	/* Put the IO into reset */
-	tmp = I915_READ(MIPI_CTRL(PORT_A));
-	tmp &= ~GLK_MIPIIO_RESET_RELEASED;
-	I915_WRITE(MIPI_CTRL(PORT_A), tmp);
-
-	/* Program LP Wake */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		tmp = I915_READ(MIPI_CTRL(port));
-		if (!(I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY))
-			tmp &= ~GLK_LP_WAKE;
-		else
-			tmp |= GLK_LP_WAKE;
-		I915_WRITE(MIPI_CTRL(port), tmp);
-	}
-
-	/* Wait for Pwr ACK */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (intel_wait_for_register(dev_priv,
-				MIPI_CTRL(port), GLK_MIPIIO_PORT_POWERED,
-				GLK_MIPIIO_PORT_POWERED, 20))
-			DRM_ERROR("MIPIO port is powergated\n");
-	}
-
-	/* Check for cold boot scenario */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		cold_boot |= !(I915_READ(MIPI_DEVICE_READY(port)) &
-							DEVICE_READY);
-	}
-
-	return cold_boot;
-}
-
-static void glk_dsi_device_ready(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 val;
-
-	/* Wait for MIPI PHY status bit to set */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (intel_wait_for_register(dev_priv,
-				MIPI_CTRL(port), GLK_PHY_STATUS_PORT_READY,
-				GLK_PHY_STATUS_PORT_READY, 20))
-			DRM_ERROR("PHY is not ON\n");
-	}
-
-	/* Get IO out of reset */
-	val = I915_READ(MIPI_CTRL(PORT_A));
-	I915_WRITE(MIPI_CTRL(PORT_A), val | GLK_MIPIIO_RESET_RELEASED);
-
-	/* Get IO out of Low power state*/
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (!(I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY)) {
-			val = I915_READ(MIPI_DEVICE_READY(port));
-			val &= ~ULPS_STATE_MASK;
-			val |= DEVICE_READY;
-			I915_WRITE(MIPI_DEVICE_READY(port), val);
-			usleep_range(10, 15);
-		} else {
-			/* Enter ULPS */
-			val = I915_READ(MIPI_DEVICE_READY(port));
-			val &= ~ULPS_STATE_MASK;
-			val |= (ULPS_STATE_ENTER | DEVICE_READY);
-			I915_WRITE(MIPI_DEVICE_READY(port), val);
-
-			/* Wait for ULPS active */
-			if (intel_wait_for_register(dev_priv,
-				MIPI_CTRL(port), GLK_ULPS_NOT_ACTIVE, 0, 20))
-				DRM_ERROR("ULPS not active\n");
-
-			/* Exit ULPS */
-			val = I915_READ(MIPI_DEVICE_READY(port));
-			val &= ~ULPS_STATE_MASK;
-			val |= (ULPS_STATE_EXIT | DEVICE_READY);
-			I915_WRITE(MIPI_DEVICE_READY(port), val);
-
-			/* Enter Normal Mode */
-			val = I915_READ(MIPI_DEVICE_READY(port));
-			val &= ~ULPS_STATE_MASK;
-			val |= (ULPS_STATE_NORMAL_OPERATION | DEVICE_READY);
-			I915_WRITE(MIPI_DEVICE_READY(port), val);
-
-			val = I915_READ(MIPI_CTRL(port));
-			val &= ~GLK_LP_WAKE;
-			I915_WRITE(MIPI_CTRL(port), val);
-		}
-	}
-
-	/* Wait for Stop state */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (intel_wait_for_register(dev_priv,
-				MIPI_CTRL(port), GLK_DATA_LANE_STOP_STATE,
-				GLK_DATA_LANE_STOP_STATE, 20))
-			DRM_ERROR("Date lane not in STOP state\n");
-	}
-
-	/* Wait for AFE LATCH */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (intel_wait_for_register(dev_priv,
-				BXT_MIPI_PORT_CTRL(port), AFE_LATCHOUT,
-				AFE_LATCHOUT, 20))
-			DRM_ERROR("D-PHY not entering LP-11 state\n");
-	}
-}
-
-static void bxt_dsi_device_ready(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 val;
-
-	DRM_DEBUG_KMS("\n");
-
-	/* Enable MIPI PHY transparent latch */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		val = I915_READ(BXT_MIPI_PORT_CTRL(port));
-		I915_WRITE(BXT_MIPI_PORT_CTRL(port), val | LP_OUTPUT_HOLD);
-		usleep_range(2000, 2500);
-	}
-
-	/* Clear ULPS and set device ready */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		val = I915_READ(MIPI_DEVICE_READY(port));
-		val &= ~ULPS_STATE_MASK;
-		I915_WRITE(MIPI_DEVICE_READY(port), val);
-		usleep_range(2000, 2500);
-		val |= DEVICE_READY;
-		I915_WRITE(MIPI_DEVICE_READY(port), val);
-	}
-}
-
-static void vlv_dsi_device_ready(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 val;
-
-	DRM_DEBUG_KMS("\n");
-
-	mutex_lock(&dev_priv->sb_lock);
-	/* program rcomp for compliance, reduce from 50 ohms to 45 ohms
-	 * needed everytime after power gate */
-	vlv_flisdsi_write(dev_priv, 0x04, 0x0004);
-	mutex_unlock(&dev_priv->sb_lock);
-
-	/* bandgap reset is needed after everytime we do power gate */
-	band_gap_reset(dev_priv);
-
-	for_each_dsi_port(port, intel_dsi->ports) {
-
-		I915_WRITE(MIPI_DEVICE_READY(port), ULPS_STATE_ENTER);
-		usleep_range(2500, 3000);
-
-		/* Enable MIPI PHY transparent latch
-		 * Common bit for both MIPI Port A & MIPI Port C
-		 * No similar bit in MIPI Port C reg
-		 */
-		val = I915_READ(MIPI_PORT_CTRL(PORT_A));
-		I915_WRITE(MIPI_PORT_CTRL(PORT_A), val | LP_OUTPUT_HOLD);
-		usleep_range(1000, 1500);
-
-		I915_WRITE(MIPI_DEVICE_READY(port), ULPS_STATE_EXIT);
-		usleep_range(2500, 3000);
-
-		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY);
-		usleep_range(2500, 3000);
-	}
-}
-
-static void intel_dsi_device_ready(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_device_ready(encoder);
-	else if (IS_BROXTON(dev_priv))
-		bxt_dsi_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
-		glk_dsi_device_ready(encoder);
-}
-
-static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 val;
-
-	/* Enter ULPS */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		val = I915_READ(MIPI_DEVICE_READY(port));
-		val &= ~ULPS_STATE_MASK;
-		val |= (ULPS_STATE_ENTER | DEVICE_READY);
-		I915_WRITE(MIPI_DEVICE_READY(port), val);
-	}
-
-	/* Wait for MIPI PHY status bit to unset */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (intel_wait_for_register(dev_priv,
-					    MIPI_CTRL(port),
-					    GLK_PHY_STATUS_PORT_READY, 0, 20))
-			DRM_ERROR("PHY is not turning OFF\n");
-	}
-
-	/* Wait for Pwr ACK bit to unset */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (intel_wait_for_register(dev_priv,
-					    MIPI_CTRL(port),
-					    GLK_MIPIIO_PORT_POWERED, 0, 20))
-			DRM_ERROR("MIPI IO Port is not powergated\n");
-	}
-}
-
-static void glk_dsi_disable_mipi_io(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 tmp;
-
-	/* Put the IO into reset */
-	tmp = I915_READ(MIPI_CTRL(PORT_A));
-	tmp &= ~GLK_MIPIIO_RESET_RELEASED;
-	I915_WRITE(MIPI_CTRL(PORT_A), tmp);
-
-	/* Wait for MIPI PHY status bit to unset */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (intel_wait_for_register(dev_priv,
-					    MIPI_CTRL(port),
-					    GLK_PHY_STATUS_PORT_READY, 0, 20))
-			DRM_ERROR("PHY is not turning OFF\n");
-	}
-
-	/* Clear MIPI mode */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		tmp = I915_READ(MIPI_CTRL(port));
-		tmp &= ~GLK_MIPIIO_ENABLE;
-		I915_WRITE(MIPI_CTRL(port), tmp);
-	}
-}
-
-static void glk_dsi_clear_device_ready(struct intel_encoder *encoder)
-{
-	glk_dsi_enter_low_power_mode(encoder);
-	glk_dsi_disable_mipi_io(encoder);
-}
-
-static void vlv_dsi_clear_device_ready(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-
-	DRM_DEBUG_KMS("\n");
-	for_each_dsi_port(port, intel_dsi->ports) {
-		/* Common bit for both MIPI Port A & MIPI Port C on VLV/CHV */
-		i915_reg_t port_ctrl = IS_GEN9_LP(dev_priv) ?
-			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(PORT_A);
-		u32 val;
-
-		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY |
-							ULPS_STATE_ENTER);
-		usleep_range(2000, 2500);
-
-		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY |
-							ULPS_STATE_EXIT);
-		usleep_range(2000, 2500);
-
-		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY |
-							ULPS_STATE_ENTER);
-		usleep_range(2000, 2500);
-
-		/*
-		 * On VLV/CHV, wait till Clock lanes are in LP-00 state for MIPI
-		 * Port A only. MIPI Port C has no similar bit for checking.
-		 */
-		if ((IS_GEN9_LP(dev_priv) || port == PORT_A) &&
-		    intel_wait_for_register(dev_priv,
-					    port_ctrl, AFE_LATCHOUT, 0,
-					    30))
-			DRM_ERROR("DSI LP not going Low\n");
-
-		/* Disable MIPI PHY transparent latch */
-		val = I915_READ(port_ctrl);
-		I915_WRITE(port_ctrl, val & ~LP_OUTPUT_HOLD);
-		usleep_range(1000, 1500);
-
-		I915_WRITE(MIPI_DEVICE_READY(port), 0x00);
-		usleep_range(2000, 2500);
-	}
-}
-
-static void intel_dsi_port_enable(struct intel_encoder *encoder,
-				  const struct intel_crtc_state *crtc_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-
-	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
-		u32 temp;
-		if (IS_GEN9_LP(dev_priv)) {
-			for_each_dsi_port(port, intel_dsi->ports) {
-				temp = I915_READ(MIPI_CTRL(port));
-				temp &= ~BXT_PIXEL_OVERLAP_CNT_MASK |
-					intel_dsi->pixel_overlap <<
-					BXT_PIXEL_OVERLAP_CNT_SHIFT;
-				I915_WRITE(MIPI_CTRL(port), temp);
-			}
-		} else {
-			temp = I915_READ(VLV_CHICKEN_3);
-			temp &= ~PIXEL_OVERLAP_CNT_MASK |
-					intel_dsi->pixel_overlap <<
-					PIXEL_OVERLAP_CNT_SHIFT;
-			I915_WRITE(VLV_CHICKEN_3, temp);
-		}
-	}
-
-	for_each_dsi_port(port, intel_dsi->ports) {
-		i915_reg_t port_ctrl = IS_GEN9_LP(dev_priv) ?
-			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
-		u32 temp;
-
-		temp = I915_READ(port_ctrl);
-
-		temp &= ~LANE_CONFIGURATION_MASK;
-		temp &= ~DUAL_LINK_MODE_MASK;
-
-		if (intel_dsi->ports == (BIT(PORT_A) | BIT(PORT_C))) {
-			temp |= (intel_dsi->dual_link - 1)
-						<< DUAL_LINK_MODE_SHIFT;
-			if (IS_BROXTON(dev_priv))
-				temp |= LANE_CONFIGURATION_DUAL_LINK_A;
-			else
-				temp |= crtc->pipe ?
-					LANE_CONFIGURATION_DUAL_LINK_B :
-					LANE_CONFIGURATION_DUAL_LINK_A;
-		}
-		/* assert ip_tg_enable signal */
-		I915_WRITE(port_ctrl, temp | DPI_ENABLE);
-		POSTING_READ(port_ctrl);
-	}
-}
-
-static void intel_dsi_port_disable(struct intel_encoder *encoder)
-{
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-
-	for_each_dsi_port(port, intel_dsi->ports) {
-		i915_reg_t port_ctrl = IS_GEN9_LP(dev_priv) ?
-			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
-		u32 temp;
-
-		/* de-assert ip_tg_enable signal */
-		temp = I915_READ(port_ctrl);
-		I915_WRITE(port_ctrl, temp & ~DPI_ENABLE);
-		POSTING_READ(port_ctrl);
-	}
-}
-
-static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
-			      const struct intel_crtc_state *pipe_config);
-static void intel_dsi_unprepare(struct intel_encoder *encoder);
-
-static void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec)
-{
-	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
-
-	/* For v3 VBTs in vid-mode the delays are part of the VBT sequences */
-	if (is_vid_mode(intel_dsi) && dev_priv->vbt.dsi.seq_version >= 3)
-		return;
-
-	msleep(msec);
-}
-
-/*
- * Panel enable/disable sequences from the VBT spec.
- *
- * Note the spec has AssertReset / DeassertReset swapped from their
- * usual naming. We use the normal names to avoid confusion (so below
- * they are swapped compared to the spec).
- *
- * Steps starting with MIPI refer to VBT sequences, note that for v2
- * VBTs several steps which have a VBT in v2 are expected to be handled
- * directly by the driver, by directly driving gpios for example.
- *
- * v2 video mode seq         v3 video mode seq         command mode seq
- * - power on                - MIPIPanelPowerOn        - power on
- * - wait t1+t2                                        - wait t1+t2
- * - MIPIDeassertResetPin    - MIPIDeassertResetPin    - MIPIDeassertResetPin
- * - io lines to lp-11       - io lines to lp-11       - io lines to lp-11
- * - MIPISendInitialDcsCmds  - MIPISendInitialDcsCmds  - MIPISendInitialDcsCmds
- *                                                     - MIPITearOn
- *                                                     - MIPIDisplayOn
- * - turn on DPI             - turn on DPI             - set pipe to dsr mode
- * - MIPIDisplayOn           - MIPIDisplayOn
- * - wait t5                                           - wait t5
- * - backlight on            - MIPIBacklightOn         - backlight on
- * ...                       ...                       ... issue mem cmds ...
- * - backlight off           - MIPIBacklightOff        - backlight off
- * - wait t6                                           - wait t6
- * - MIPIDisplayOff
- * - turn off DPI            - turn off DPI            - disable pipe dsr mode
- *                                                     - MIPITearOff
- *                           - MIPIDisplayOff          - MIPIDisplayOff
- * - io lines to lp-00       - io lines to lp-00       - io lines to lp-00
- * - MIPIAssertResetPin      - MIPIAssertResetPin      - MIPIAssertResetPin
- * - wait t3                                           - wait t3
- * - power off               - MIPIPanelPowerOff       - power off
- * - wait t4                                           - wait t4
- */
-
-static void intel_dsi_pre_enable(struct intel_encoder *encoder,
-				 const struct intel_crtc_state *pipe_config,
-				 const struct drm_connector_state *conn_state)
-{
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	struct drm_crtc *crtc = pipe_config->base.crtc;
-	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
-	int pipe = intel_crtc->pipe;
-	enum port port;
-	u32 val;
-	bool glk_cold_boot = false;
-
-	DRM_DEBUG_KMS("\n");
-
-	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
-
-	/*
-	 * The BIOS may leave the PLL in a wonky state where it doesn't
-	 * lock. It needs to be fully powered down to fix it.
-	 */
-	intel_disable_dsi_pll(encoder);
-	intel_enable_dsi_pll(encoder, pipe_config);
-
-	if (IS_BROXTON(dev_priv)) {
-		/* Add MIPI IO reset programming for modeset */
-		val = I915_READ(BXT_P_CR_GT_DISP_PWRON);
-		I915_WRITE(BXT_P_CR_GT_DISP_PWRON,
-					val | MIPIO_RST_CTRL);
-
-		/* Power up DSI regulator */
-		I915_WRITE(BXT_P_DSI_REGULATOR_CFG, STAP_SELECT);
-		I915_WRITE(BXT_P_DSI_REGULATOR_TX_CTRL, 0);
-	}
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		u32 val;
-
-		/* Disable DPOunit clock gating, can stall pipe */
-		val = I915_READ(DSPCLK_GATE_D);
-		val |= DPOUNIT_CLOCK_GATE_DISABLE;
-		I915_WRITE(DSPCLK_GATE_D, val);
-	}
-
-	if (!IS_GEMINILAKE(dev_priv))
-		intel_dsi_prepare(encoder, pipe_config);
-
-	/* Power on, try both CRC pmic gpio and VBT */
-	if (intel_dsi->gpio_panel)
-		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 1);
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
-
-	/* Deassert reset */
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
-
-	if (IS_GEMINILAKE(dev_priv)) {
-		glk_cold_boot = glk_dsi_enable_io(encoder);
-
-		/* Prepare port in cold boot(s3/s4) scenario */
-		if (glk_cold_boot)
-			intel_dsi_prepare(encoder, pipe_config);
-	}
-
-	/* Put device in ready state (LP-11) */
-	intel_dsi_device_ready(encoder);
-
-	/* Prepare port in normal boot scenario */
-	if (IS_GEMINILAKE(dev_priv) && !glk_cold_boot)
-		intel_dsi_prepare(encoder, pipe_config);
-
-	/* Send initialization commands in LP mode */
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP);
-
-	/* Enable port in pre-enable phase itself because as per hw team
-	 * recommendation, port should be enabled befor plane & pipe */
-	if (is_cmd_mode(intel_dsi)) {
-		for_each_dsi_port(port, intel_dsi->ports)
-			I915_WRITE(MIPI_MAX_RETURN_PKT_SIZE(port), 8 * 4);
-		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_TEAR_ON);
-		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
-	} else {
-		msleep(20); /* XXX */
-		for_each_dsi_port(port, intel_dsi->ports)
-			dpi_send_cmd(intel_dsi, TURN_ON, false, port);
-		intel_dsi_msleep(intel_dsi, 100);
-
-		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
-
-		intel_dsi_port_enable(encoder, pipe_config);
-	}
-
-	intel_panel_enable_backlight(pipe_config, conn_state);
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON);
-}
-
-/*
- * DSI port enable has to be done before pipe and plane enable, so we do it in
- * the pre_enable hook.
- */
-static void intel_dsi_enable_nop(struct intel_encoder *encoder,
-				 const struct intel_crtc_state *pipe_config,
-				 const struct drm_connector_state *conn_state)
-{
-	DRM_DEBUG_KMS("\n");
-}
-
-/*
- * DSI port disable has to be done after pipe and plane disable, so we do it in
- * the post_disable hook.
- */
-static void intel_dsi_disable(struct intel_encoder *encoder,
-			      const struct intel_crtc_state *old_crtc_state,
-			      const struct drm_connector_state *old_conn_state)
-{
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-
-	DRM_DEBUG_KMS("\n");
-
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF);
-	intel_panel_disable_backlight(old_conn_state);
-
-	/*
-	 * According to the spec we should send SHUTDOWN before
-	 * MIPI_SEQ_DISPLAY_OFF only for v3+ VBTs, but field testing
-	 * has shown that the v3 sequence works for v2 VBTs too
-	 */
-	if (is_vid_mode(intel_dsi)) {
-		/* Send Shutdown command to the panel in LP mode */
-		for_each_dsi_port(port, intel_dsi->ports)
-			dpi_send_cmd(intel_dsi, SHUTDOWN, false, port);
-		msleep(10);
-	}
-}
-
-static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv) ||
-	    IS_BROXTON(dev_priv))
-		vlv_dsi_clear_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
-		glk_dsi_clear_device_ready(encoder);
-}
-
-static void intel_dsi_post_disable(struct intel_encoder *encoder,
-				   const struct intel_crtc_state *pipe_config,
-				   const struct drm_connector_state *conn_state)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 val;
-
-	DRM_DEBUG_KMS("\n");
-
-	if (is_vid_mode(intel_dsi)) {
-		for_each_dsi_port(port, intel_dsi->ports)
-			wait_for_dsi_fifo_empty(intel_dsi, port);
-
-		intel_dsi_port_disable(encoder);
-		usleep_range(2000, 5000);
-	}
-
-	intel_dsi_unprepare(encoder);
-
-	/*
-	 * if disable packets are sent before sending shutdown packet then in
-	 * some next enable sequence send turn on packet error is observed
-	 */
-	if (is_cmd_mode(intel_dsi))
-		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_TEAR_OFF);
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_OFF);
-
-	/* Transition to LP-00 */
-	intel_dsi_clear_device_ready(encoder);
-
-	if (IS_BROXTON(dev_priv)) {
-		/* Power down DSI regulator to save power */
-		I915_WRITE(BXT_P_DSI_REGULATOR_CFG, STAP_SELECT);
-		I915_WRITE(BXT_P_DSI_REGULATOR_TX_CTRL, HS_IO_CTRL_SELECT);
-
-		/* Add MIPI IO reset programming for modeset */
-		val = I915_READ(BXT_P_CR_GT_DISP_PWRON);
-		I915_WRITE(BXT_P_CR_GT_DISP_PWRON,
-				val & ~MIPIO_RST_CTRL);
-	}
-
-	intel_disable_dsi_pll(encoder);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		u32 val;
-
-		val = I915_READ(DSPCLK_GATE_D);
-		val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
-		I915_WRITE(DSPCLK_GATE_D, val);
-	}
-
-	/* Assert reset */
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET);
-
-	/* Power off, try both CRC pmic gpio and VBT */
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_off_delay);
-	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_OFF);
-	if (intel_dsi->gpio_panel)
-		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 0);
-
-	/*
-	 * FIXME As we do with eDP, just make a note of the time here
-	 * and perform the wait before the next panel power on.
-	 */
-	intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay);
-}
-
-static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
-				   enum pipe *pipe)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	bool active = false;
-
-	DRM_DEBUG_KMS("\n");
-
-	if (!intel_display_power_get_if_enabled(dev_priv,
-						encoder->power_domain))
-		return false;
-
-	/*
-	 * On Broxton the PLL needs to be enabled with a valid divider
-	 * configuration, otherwise accessing DSI registers will hang the
-	 * machine. See BSpec North Display Engine registers/MIPI[BXT].
-	 */
-	if (IS_GEN9_LP(dev_priv) && !intel_dsi_pll_is_enabled(dev_priv))
-		goto out_put_power;
-
-	/* XXX: this only works for one DSI output */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		i915_reg_t ctrl_reg = IS_GEN9_LP(dev_priv) ?
-			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
-		bool enabled = I915_READ(ctrl_reg) & DPI_ENABLE;
-
-		/*
-		 * Due to some hardware limitations on VLV/CHV, the DPI enable
-		 * bit in port C control register does not get set. As a
-		 * workaround, check pipe B conf instead.
-		 */
-		if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
-		    port == PORT_C)
-			enabled = I915_READ(PIPECONF(PIPE_B)) & PIPECONF_ENABLE;
-
-		/* Try command mode if video mode not enabled */
-		if (!enabled) {
-			u32 tmp = I915_READ(MIPI_DSI_FUNC_PRG(port));
-			enabled = tmp & CMD_MODE_DATA_WIDTH_MASK;
-		}
-
-		if (!enabled)
-			continue;
-
-		if (!(I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY))
-			continue;
-
-		if (IS_GEN9_LP(dev_priv)) {
-			u32 tmp = I915_READ(MIPI_CTRL(port));
-			tmp &= BXT_PIPE_SELECT_MASK;
-			tmp >>= BXT_PIPE_SELECT_SHIFT;
-
-			if (WARN_ON(tmp > PIPE_C))
-				continue;
-
-			*pipe = tmp;
-		} else {
-			*pipe = port == PORT_A ? PIPE_A : PIPE_B;
-		}
-
-		active = true;
-		break;
-	}
-
-out_put_power:
-	intel_display_power_put(dev_priv, encoder->power_domain);
-
-	return active;
-}
-
-static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
-				    struct intel_crtc_state *pipe_config)
-{
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct drm_display_mode *adjusted_mode =
-					&pipe_config->base.adjusted_mode;
-	struct drm_display_mode *adjusted_mode_sw;
-	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	unsigned int lane_count = intel_dsi->lane_count;
-	unsigned int bpp, fmt;
-	enum port port;
-	u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp;
-	u16 hfp_sw, hsync_sw, hbp_sw;
-	u16 crtc_htotal_sw, crtc_hsync_start_sw, crtc_hsync_end_sw,
-				crtc_hblank_start_sw, crtc_hblank_end_sw;
-
-	/* FIXME: hw readout should not depend on SW state */
-	adjusted_mode_sw = &crtc->config->base.adjusted_mode;
-
-	/*
-	 * Atleast one port is active as encoder->get_config called only if
-	 * encoder->get_hw_state() returns true.
-	 */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (I915_READ(BXT_MIPI_PORT_CTRL(port)) & DPI_ENABLE)
-			break;
-	}
-
-	fmt = I915_READ(MIPI_DSI_FUNC_PRG(port)) & VID_MODE_FORMAT_MASK;
-	pipe_config->pipe_bpp =
-			mipi_dsi_pixel_format_to_bpp(
-				pixel_format_from_register_bits(fmt));
-	bpp = pipe_config->pipe_bpp;
-
-	/* Enable Frame time stamo based scanline reporting */
-	adjusted_mode->private_flags |=
-			I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP;
-
-	/* In terms of pixels */
-	adjusted_mode->crtc_hdisplay =
-				I915_READ(BXT_MIPI_TRANS_HACTIVE(port));
-	adjusted_mode->crtc_vdisplay =
-				I915_READ(BXT_MIPI_TRANS_VACTIVE(port));
-	adjusted_mode->crtc_vtotal =
-				I915_READ(BXT_MIPI_TRANS_VTOTAL(port));
-
-	hactive = adjusted_mode->crtc_hdisplay;
-	hfp = I915_READ(MIPI_HFP_COUNT(port));
-
-	/*
-	 * Meaningful for video mode non-burst sync pulse mode only,
-	 * can be zero for non-burst sync events and burst modes
-	 */
-	hsync = I915_READ(MIPI_HSYNC_PADDING_COUNT(port));
-	hbp = I915_READ(MIPI_HBP_COUNT(port));
-
-	/* harizontal values are in terms of high speed byte clock */
-	hfp = pixels_from_txbyteclkhs(hfp, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-	hsync = pixels_from_txbyteclkhs(hsync, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-	hbp = pixels_from_txbyteclkhs(hbp, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-
-	if (intel_dsi->dual_link) {
-		hfp *= 2;
-		hsync *= 2;
-		hbp *= 2;
-	}
-
-	/* vertical values are in terms of lines */
-	vfp = I915_READ(MIPI_VFP_COUNT(port));
-	vsync = I915_READ(MIPI_VSYNC_PADDING_COUNT(port));
-	vbp = I915_READ(MIPI_VBP_COUNT(port));
-
-	adjusted_mode->crtc_htotal = hactive + hfp + hsync + hbp;
-	adjusted_mode->crtc_hsync_start = hfp + adjusted_mode->crtc_hdisplay;
-	adjusted_mode->crtc_hsync_end = hsync + adjusted_mode->crtc_hsync_start;
-	adjusted_mode->crtc_hblank_start = adjusted_mode->crtc_hdisplay;
-	adjusted_mode->crtc_hblank_end = adjusted_mode->crtc_htotal;
-
-	adjusted_mode->crtc_vsync_start = vfp + adjusted_mode->crtc_vdisplay;
-	adjusted_mode->crtc_vsync_end = vsync + adjusted_mode->crtc_vsync_start;
-	adjusted_mode->crtc_vblank_start = adjusted_mode->crtc_vdisplay;
-	adjusted_mode->crtc_vblank_end = adjusted_mode->crtc_vtotal;
-
-	/*
-	 * In BXT DSI there is no regs programmed with few horizontal timings
-	 * in Pixels but txbyteclkhs.. So retrieval process adds some
-	 * ROUND_UP ERRORS in the process of PIXELS<==>txbyteclkhs.
-	 * Actually here for the given adjusted_mode, we are calculating the
-	 * value programmed to the port and then back to the horizontal timing
-	 * param in pixels. This is the expected value, including roundup errors
-	 * And if that is same as retrieved value from port, then
-	 * (HW state) adjusted_mode's horizontal timings are corrected to
-	 * match with SW state to nullify the errors.
-	 */
-	/* Calculating the value programmed to the Port register */
-	hfp_sw = adjusted_mode_sw->crtc_hsync_start -
-					adjusted_mode_sw->crtc_hdisplay;
-	hsync_sw = adjusted_mode_sw->crtc_hsync_end -
-					adjusted_mode_sw->crtc_hsync_start;
-	hbp_sw = adjusted_mode_sw->crtc_htotal -
-					adjusted_mode_sw->crtc_hsync_end;
-
-	if (intel_dsi->dual_link) {
-		hfp_sw /= 2;
-		hsync_sw /= 2;
-		hbp_sw /= 2;
-	}
-
-	hfp_sw = txbyteclkhs(hfp_sw, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-	hsync_sw = txbyteclkhs(hsync_sw, bpp, lane_count,
-			    intel_dsi->burst_mode_ratio);
-	hbp_sw = txbyteclkhs(hbp_sw, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-
-	/* Reverse calculating the adjusted mode parameters from port reg vals*/
-	hfp_sw = pixels_from_txbyteclkhs(hfp_sw, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-	hsync_sw = pixels_from_txbyteclkhs(hsync_sw, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-	hbp_sw = pixels_from_txbyteclkhs(hbp_sw, bpp, lane_count,
-						intel_dsi->burst_mode_ratio);
-
-	if (intel_dsi->dual_link) {
-		hfp_sw *= 2;
-		hsync_sw *= 2;
-		hbp_sw *= 2;
-	}
-
-	crtc_htotal_sw = adjusted_mode_sw->crtc_hdisplay + hfp_sw +
-							hsync_sw + hbp_sw;
-	crtc_hsync_start_sw = hfp_sw + adjusted_mode_sw->crtc_hdisplay;
-	crtc_hsync_end_sw = hsync_sw + crtc_hsync_start_sw;
-	crtc_hblank_start_sw = adjusted_mode_sw->crtc_hdisplay;
-	crtc_hblank_end_sw = crtc_htotal_sw;
-
-	if (adjusted_mode->crtc_htotal == crtc_htotal_sw)
-		adjusted_mode->crtc_htotal = adjusted_mode_sw->crtc_htotal;
-
-	if (adjusted_mode->crtc_hsync_start == crtc_hsync_start_sw)
-		adjusted_mode->crtc_hsync_start =
-					adjusted_mode_sw->crtc_hsync_start;
-
-	if (adjusted_mode->crtc_hsync_end == crtc_hsync_end_sw)
-		adjusted_mode->crtc_hsync_end =
-					adjusted_mode_sw->crtc_hsync_end;
-
-	if (adjusted_mode->crtc_hblank_start == crtc_hblank_start_sw)
-		adjusted_mode->crtc_hblank_start =
-					adjusted_mode_sw->crtc_hblank_start;
-
-	if (adjusted_mode->crtc_hblank_end == crtc_hblank_end_sw)
-		adjusted_mode->crtc_hblank_end =
-					adjusted_mode_sw->crtc_hblank_end;
-}
-
-static void intel_dsi_get_config(struct intel_encoder *encoder,
-				 struct intel_crtc_state *pipe_config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 pclk;
-	DRM_DEBUG_KMS("\n");
-
-	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
-
-	if (IS_GEN9_LP(dev_priv))
-		bxt_dsi_get_pipe_config(encoder, pipe_config);
-
-	pclk = intel_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
-				  pipe_config);
-	if (!pclk)
-		return;
-
-	pipe_config->base.adjusted_mode.crtc_clock = pclk;
-	pipe_config->port_clock = pclk;
-}
-
-static enum drm_mode_status
-intel_dsi_mode_valid(struct drm_connector *connector,
-		     struct drm_display_mode *mode)
-{
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
-	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
-
-	DRM_DEBUG_KMS("\n");
-
-	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
-		return MODE_NO_DBLESCAN;
-
-	if (fixed_mode) {
-		if (mode->hdisplay > fixed_mode->hdisplay)
-			return MODE_PANEL;
-		if (mode->vdisplay > fixed_mode->vdisplay)
-			return MODE_PANEL;
-		if (fixed_mode->clock > max_dotclk)
-			return MODE_CLOCK_HIGH;
-	}
-
-	return MODE_OK;
-}
-
-/* return txclkesc cycles in terms of divider and duration in us */
-static u16 txclkesc(u32 divider, unsigned int us)
-{
-	switch (divider) {
-	case ESCAPE_CLOCK_DIVIDER_1:
-	default:
-		return 20 * us;
-	case ESCAPE_CLOCK_DIVIDER_2:
-		return 10 * us;
-	case ESCAPE_CLOCK_DIVIDER_4:
-		return 5 * us;
-	}
-}
-
-static void set_dsi_timings(struct drm_encoder *encoder,
-			    const struct drm_display_mode *adjusted_mode)
-{
-	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-	enum port port;
-	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
-	unsigned int lane_count = intel_dsi->lane_count;
-
-	u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp;
-
-	hactive = adjusted_mode->crtc_hdisplay;
-	hfp = adjusted_mode->crtc_hsync_start - adjusted_mode->crtc_hdisplay;
-	hsync = adjusted_mode->crtc_hsync_end - adjusted_mode->crtc_hsync_start;
-	hbp = adjusted_mode->crtc_htotal - adjusted_mode->crtc_hsync_end;
-
-	if (intel_dsi->dual_link) {
-		hactive /= 2;
-		if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK)
-			hactive += intel_dsi->pixel_overlap;
-		hfp /= 2;
-		hsync /= 2;
-		hbp /= 2;
-	}
-
-	vfp = adjusted_mode->crtc_vsync_start - adjusted_mode->crtc_vdisplay;
-	vsync = adjusted_mode->crtc_vsync_end - adjusted_mode->crtc_vsync_start;
-	vbp = adjusted_mode->crtc_vtotal - adjusted_mode->crtc_vsync_end;
-
-	/* horizontal values are in terms of high speed byte clock */
-	hactive = txbyteclkhs(hactive, bpp, lane_count,
-			      intel_dsi->burst_mode_ratio);
-	hfp = txbyteclkhs(hfp, bpp, lane_count, intel_dsi->burst_mode_ratio);
-	hsync = txbyteclkhs(hsync, bpp, lane_count,
-			    intel_dsi->burst_mode_ratio);
-	hbp = txbyteclkhs(hbp, bpp, lane_count, intel_dsi->burst_mode_ratio);
-
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (IS_GEN9_LP(dev_priv)) {
-			/*
-			 * Program hdisplay and vdisplay on MIPI transcoder.
-			 * This is different from calculated hactive and
-			 * vactive, as they are calculated per channel basis,
-			 * whereas these values should be based on resolution.
-			 */
-			I915_WRITE(BXT_MIPI_TRANS_HACTIVE(port),
-				   adjusted_mode->crtc_hdisplay);
-			I915_WRITE(BXT_MIPI_TRANS_VACTIVE(port),
-				   adjusted_mode->crtc_vdisplay);
-			I915_WRITE(BXT_MIPI_TRANS_VTOTAL(port),
-				   adjusted_mode->crtc_vtotal);
-		}
-
-		I915_WRITE(MIPI_HACTIVE_AREA_COUNT(port), hactive);
-		I915_WRITE(MIPI_HFP_COUNT(port), hfp);
-
-		/* meaningful for video mode non-burst sync pulse mode only,
-		 * can be zero for non-burst sync events and burst modes */
-		I915_WRITE(MIPI_HSYNC_PADDING_COUNT(port), hsync);
-		I915_WRITE(MIPI_HBP_COUNT(port), hbp);
-
-		/* vertical values are in terms of lines */
-		I915_WRITE(MIPI_VFP_COUNT(port), vfp);
-		I915_WRITE(MIPI_VSYNC_PADDING_COUNT(port), vsync);
-		I915_WRITE(MIPI_VBP_COUNT(port), vbp);
-	}
-}
-
-static u32 pixel_format_to_reg(enum mipi_dsi_pixel_format fmt)
-{
-	switch (fmt) {
-	case MIPI_DSI_FMT_RGB888:
-		return VID_MODE_FORMAT_RGB888;
-	case MIPI_DSI_FMT_RGB666:
-		return VID_MODE_FORMAT_RGB666;
-	case MIPI_DSI_FMT_RGB666_PACKED:
-		return VID_MODE_FORMAT_RGB666_PACKED;
-	case MIPI_DSI_FMT_RGB565:
-		return VID_MODE_FORMAT_RGB565;
-	default:
-		MISSING_CASE(fmt);
-		return VID_MODE_FORMAT_RGB666;
-	}
-}
-
-static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
-			      const struct intel_crtc_state *pipe_config)
-{
-	struct drm_encoder *encoder = &intel_encoder->base;
-	struct drm_device *dev = encoder->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
-	enum port port;
-	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
-	u32 val, tmp;
-	u16 mode_hdisplay;
-
-	DRM_DEBUG_KMS("pipe %c\n", pipe_name(intel_crtc->pipe));
-
-	mode_hdisplay = adjusted_mode->crtc_hdisplay;
-
-	if (intel_dsi->dual_link) {
-		mode_hdisplay /= 2;
-		if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK)
-			mode_hdisplay += intel_dsi->pixel_overlap;
-	}
-
-	for_each_dsi_port(port, intel_dsi->ports) {
-		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-			/*
-			 * escape clock divider, 20MHz, shared for A and C.
-			 * device ready must be off when doing this! txclkesc?
-			 */
-			tmp = I915_READ(MIPI_CTRL(PORT_A));
-			tmp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
-			I915_WRITE(MIPI_CTRL(PORT_A), tmp |
-					ESCAPE_CLOCK_DIVIDER_1);
-
-			/* read request priority is per pipe */
-			tmp = I915_READ(MIPI_CTRL(port));
-			tmp &= ~READ_REQUEST_PRIORITY_MASK;
-			I915_WRITE(MIPI_CTRL(port), tmp |
-					READ_REQUEST_PRIORITY_HIGH);
-		} else if (IS_GEN9_LP(dev_priv)) {
-			enum pipe pipe = intel_crtc->pipe;
-
-			tmp = I915_READ(MIPI_CTRL(port));
-			tmp &= ~BXT_PIPE_SELECT_MASK;
-
-			tmp |= BXT_PIPE_SELECT(pipe);
-			I915_WRITE(MIPI_CTRL(port), tmp);
-		}
-
-		/* XXX: why here, why like this? handling in irq handler?! */
-		I915_WRITE(MIPI_INTR_STAT(port), 0xffffffff);
-		I915_WRITE(MIPI_INTR_EN(port), 0xffffffff);
-
-		I915_WRITE(MIPI_DPHY_PARAM(port), intel_dsi->dphy_reg);
-
-		I915_WRITE(MIPI_DPI_RESOLUTION(port),
-			adjusted_mode->crtc_vdisplay << VERTICAL_ADDRESS_SHIFT |
-			mode_hdisplay << HORIZONTAL_ADDRESS_SHIFT);
-	}
-
-	set_dsi_timings(encoder, adjusted_mode);
-
-	val = intel_dsi->lane_count << DATA_LANES_PRG_REG_SHIFT;
-	if (is_cmd_mode(intel_dsi)) {
-		val |= intel_dsi->channel << CMD_MODE_CHANNEL_NUMBER_SHIFT;
-		val |= CMD_MODE_DATA_WIDTH_8_BIT; /* XXX */
-	} else {
-		val |= intel_dsi->channel << VID_MODE_CHANNEL_NUMBER_SHIFT;
-		val |= pixel_format_to_reg(intel_dsi->pixel_format);
-	}
-
-	tmp = 0;
-	if (intel_dsi->eotp_pkt == 0)
-		tmp |= EOT_DISABLE;
-	if (intel_dsi->clock_stop)
-		tmp |= CLOCKSTOP;
-
-	if (IS_GEN9_LP(dev_priv)) {
-		tmp |= BXT_DPHY_DEFEATURE_EN;
-		if (!is_cmd_mode(intel_dsi))
-			tmp |= BXT_DEFEATURE_DPI_FIFO_CTR;
-	}
-
-	for_each_dsi_port(port, intel_dsi->ports) {
-		I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
-
-		/* timeouts for recovery. one frame IIUC. if counter expires,
-		 * EOT and stop state. */
-
-		/*
-		 * In burst mode, value greater than one DPI line Time in byte
-		 * clock (txbyteclkhs) To timeout this timer 1+ of the above
-		 * said value is recommended.
-		 *
-		 * In non-burst mode, Value greater than one DPI frame time in
-		 * byte clock(txbyteclkhs) To timeout this timer 1+ of the above
-		 * said value is recommended.
-		 *
-		 * In DBI only mode, value greater than one DBI frame time in
-		 * byte clock(txbyteclkhs) To timeout this timer 1+ of the above
-		 * said value is recommended.
-		 */
-
-		if (is_vid_mode(intel_dsi) &&
-			intel_dsi->video_mode_format == VIDEO_MODE_BURST) {
-			I915_WRITE(MIPI_HS_TX_TIMEOUT(port),
-				txbyteclkhs(adjusted_mode->crtc_htotal, bpp,
-					    intel_dsi->lane_count,
-					    intel_dsi->burst_mode_ratio) + 1);
-		} else {
-			I915_WRITE(MIPI_HS_TX_TIMEOUT(port),
-				txbyteclkhs(adjusted_mode->crtc_vtotal *
-					    adjusted_mode->crtc_htotal,
-					    bpp, intel_dsi->lane_count,
-					    intel_dsi->burst_mode_ratio) + 1);
-		}
-		I915_WRITE(MIPI_LP_RX_TIMEOUT(port), intel_dsi->lp_rx_timeout);
-		I915_WRITE(MIPI_TURN_AROUND_TIMEOUT(port),
-						intel_dsi->turn_arnd_val);
-		I915_WRITE(MIPI_DEVICE_RESET_TIMER(port),
-						intel_dsi->rst_timer_val);
-
-		/* dphy stuff */
-
-		/* in terms of low power clock */
-		I915_WRITE(MIPI_INIT_COUNT(port),
-				txclkesc(intel_dsi->escape_clk_div, 100));
-
-		if (IS_GEN9_LP(dev_priv) && (!intel_dsi->dual_link)) {
-			/*
-			 * BXT spec says write MIPI_INIT_COUNT for
-			 * both the ports, even if only one is
-			 * getting used. So write the other port
-			 * if not in dual link mode.
-			 */
-			I915_WRITE(MIPI_INIT_COUNT(port ==
-						PORT_A ? PORT_C : PORT_A),
-					intel_dsi->init_count);
-		}
-
-		/* recovery disables */
-		I915_WRITE(MIPI_EOT_DISABLE(port), tmp);
-
-		/* in terms of low power clock */
-		I915_WRITE(MIPI_INIT_COUNT(port), intel_dsi->init_count);
-
-		/* in terms of txbyteclkhs. actual high to low switch +
-		 * MIPI_STOP_STATE_STALL * MIPI_LP_BYTECLK.
-		 *
-		 * XXX: write MIPI_STOP_STATE_STALL?
-		 */
-		I915_WRITE(MIPI_HIGH_LOW_SWITCH_COUNT(port),
-						intel_dsi->hs_to_lp_count);
-
-		/* XXX: low power clock equivalence in terms of byte clock.
-		 * the number of byte clocks occupied in one low power clock.
-		 * based on txbyteclkhs and txclkesc.
-		 * txclkesc time / txbyteclk time * (105 + MIPI_STOP_STATE_STALL
-		 * ) / 105.???
-		 */
-		I915_WRITE(MIPI_LP_BYTECLK(port), intel_dsi->lp_byte_clk);
-
-		if (IS_GEMINILAKE(dev_priv)) {
-			I915_WRITE(MIPI_TLPX_TIME_COUNT(port),
-					intel_dsi->lp_byte_clk);
-			/* Shadow of DPHY reg */
-			I915_WRITE(MIPI_CLK_LANE_TIMING(port),
-					intel_dsi->dphy_reg);
-		}
-
-		/* the bw essential for transmitting 16 long packets containing
-		 * 252 bytes meant for dcs write memory command is programmed in
-		 * this register in terms of byte clocks. based on dsi transfer
-		 * rate and the number of lanes configured the time taken to
-		 * transmit 16 long packets in a dsi stream varies. */
-		I915_WRITE(MIPI_DBI_BW_CTRL(port), intel_dsi->bw_timer);
-
-		I915_WRITE(MIPI_CLK_LANE_SWITCH_TIME_CNT(port),
-		intel_dsi->clk_lp_to_hs_count << LP_HS_SSW_CNT_SHIFT |
-		intel_dsi->clk_hs_to_lp_count << HS_LP_PWR_SW_CNT_SHIFT);
-
-		if (is_vid_mode(intel_dsi))
-			/* Some panels might have resolution which is not a
-			 * multiple of 64 like 1366 x 768. Enable RANDOM
-			 * resolution support for such panels by default */
-			I915_WRITE(MIPI_VIDEO_MODE_FORMAT(port),
-				intel_dsi->video_frmt_cfg_bits |
-				intel_dsi->video_mode_format |
-				IP_TG_CONFIG |
-				RANDOM_DPI_DISPLAY_RESOLUTION);
-	}
-}
-
-static void intel_dsi_unprepare(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 val;
-
-	if (!IS_GEMINILAKE(dev_priv)) {
-		for_each_dsi_port(port, intel_dsi->ports) {
-			/* Panel commands can be sent when clock is in LP11 */
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
-
-			intel_dsi_reset_clocks(encoder, port);
-			I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
-
-			val = I915_READ(MIPI_DSI_FUNC_PRG(port));
-			val &= ~VID_MODE_FORMAT_MASK;
-			I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
-
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
-		}
-	}
-}
-
-static int intel_dsi_get_modes(struct drm_connector *connector)
-{
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-	struct drm_display_mode *mode;
-
-	DRM_DEBUG_KMS("\n");
-
-	if (!intel_connector->panel.fixed_mode) {
-		DRM_DEBUG_KMS("no fixed mode\n");
-		return 0;
-	}
-
-	mode = drm_mode_duplicate(connector->dev,
-				  intel_connector->panel.fixed_mode);
-	if (!mode) {
-		DRM_DEBUG_KMS("drm_mode_duplicate failed\n");
-		return 0;
-	}
-
-	drm_mode_probed_add(connector, mode);
-	return 1;
-}
-
-static void intel_dsi_connector_destroy(struct drm_connector *connector)
-{
-	struct intel_connector *intel_connector = to_intel_connector(connector);
-
-	DRM_DEBUG_KMS("\n");
-	intel_panel_fini(&intel_connector->panel);
-	drm_connector_cleanup(connector);
-	kfree(connector);
-}
-
-static void intel_dsi_encoder_destroy(struct drm_encoder *encoder)
-{
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
-
-	/* dispose of the gpios */
-	if (intel_dsi->gpio_panel)
-		gpiod_put(intel_dsi->gpio_panel);
-
-	intel_encoder_destroy(encoder);
-}
-
-static const struct drm_encoder_funcs intel_dsi_funcs = {
-	.destroy = intel_dsi_encoder_destroy,
-};
-
-static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = {
-	.get_modes = intel_dsi_get_modes,
-	.mode_valid = intel_dsi_mode_valid,
-	.atomic_check = intel_digital_connector_atomic_check,
-};
-
-static const struct drm_connector_funcs intel_dsi_connector_funcs = {
-	.late_register = intel_connector_register,
-	.early_unregister = intel_connector_unregister,
-	.destroy = intel_dsi_connector_destroy,
-	.fill_modes = drm_helper_probe_single_connector_modes,
-	.atomic_get_property = intel_digital_connector_atomic_get_property,
-	.atomic_set_property = intel_digital_connector_atomic_set_property,
-	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
-	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
-};
-
-static int intel_dsi_get_panel_orientation(struct intel_connector *connector)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-	int orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
-	enum i9xx_plane_id i9xx_plane;
-	u32 val;
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		if (connector->encoder->crtc_mask == BIT(PIPE_B))
-			i9xx_plane = PLANE_B;
-		else
-			i9xx_plane = PLANE_A;
-
-		val = I915_READ(DSPCNTR(i9xx_plane));
-		if (val & DISPPLANE_ROTATE_180)
-			orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP;
-	}
-
-	return orientation;
-}
-
-static void intel_dsi_add_properties(struct intel_connector *connector)
-{
-	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
-
-	if (connector->panel.fixed_mode) {
-		u32 allowed_scalers;
-
-		allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN);
-		if (!HAS_GMCH_DISPLAY(dev_priv))
-			allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER);
-
-		drm_connector_attach_scaling_mode_property(&connector->base,
-								allowed_scalers);
-
-		connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT;
-
-		connector->base.display_info.panel_orientation =
-			intel_dsi_get_panel_orientation(connector);
-		drm_connector_init_panel_orientation_property(
-				&connector->base,
-				connector->panel.fixed_mode->hdisplay,
-				connector->panel.fixed_mode->vdisplay);
-	}
-}
-
-void intel_dsi_init(struct drm_i915_private *dev_priv)
-{
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_dsi *intel_dsi;
-	struct intel_encoder *intel_encoder;
-	struct drm_encoder *encoder;
-	struct intel_connector *intel_connector;
-	struct drm_connector *connector;
-	struct drm_display_mode *scan, *fixed_mode = NULL;
-	enum port port;
-
-	DRM_DEBUG_KMS("\n");
-
-	/* There is no detection method for MIPI so rely on VBT */
-	if (!intel_bios_is_dsi_present(dev_priv, &port))
-		return;
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
-	} else if (IS_GEN9_LP(dev_priv)) {
-		dev_priv->mipi_mmio_base = BXT_MIPI_BASE;
-	} else {
-		DRM_ERROR("Unsupported Mipi device to reg base");
-		return;
-	}
-
-	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
-	if (!intel_dsi)
-		return;
-
-	intel_connector = intel_connector_alloc();
-	if (!intel_connector) {
-		kfree(intel_dsi);
-		return;
-	}
-
-	intel_encoder = &intel_dsi->base;
-	encoder = &intel_encoder->base;
-	intel_dsi->attached_connector = intel_connector;
-
-	connector = &intel_connector->base;
-
-	drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI,
-			 "DSI %c", port_name(port));
-
-	intel_encoder->compute_config = intel_dsi_compute_config;
-	intel_encoder->pre_enable = intel_dsi_pre_enable;
-	intel_encoder->enable = intel_dsi_enable_nop;
-	intel_encoder->disable = intel_dsi_disable;
-	intel_encoder->post_disable = intel_dsi_post_disable;
-	intel_encoder->get_hw_state = intel_dsi_get_hw_state;
-	intel_encoder->get_config = intel_dsi_get_config;
-
-	intel_connector->get_hw_state = intel_connector_get_hw_state;
-
-	intel_encoder->port = port;
-
-	/*
-	 * On BYT/CHV, pipe A maps to MIPI DSI port A, pipe B maps to MIPI DSI
-	 * port C. BXT isn't limited like this.
-	 */
-	if (IS_GEN9_LP(dev_priv))
-		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
-	else if (port == PORT_A)
-		intel_encoder->crtc_mask = BIT(PIPE_A);
-	else
-		intel_encoder->crtc_mask = BIT(PIPE_B);
-
-	if (dev_priv->vbt.dsi.config->dual_link)
-		intel_dsi->ports = BIT(PORT_A) | BIT(PORT_C);
-	else
-		intel_dsi->ports = BIT(port);
-
-	intel_dsi->dcs_backlight_ports = dev_priv->vbt.dsi.bl_ports;
-	intel_dsi->dcs_cabc_ports = dev_priv->vbt.dsi.cabc_ports;
-
-	/* Create a DSI host (and a device) for each port. */
-	for_each_dsi_port(port, intel_dsi->ports) {
-		struct intel_dsi_host *host;
-
-		host = intel_dsi_host_init(intel_dsi, port);
-		if (!host)
-			goto err;
-
-		intel_dsi->dsi_hosts[port] = host;
-	}
-
-	if (!intel_dsi_vbt_init(intel_dsi, MIPI_DSI_GENERIC_PANEL_ID)) {
-		DRM_DEBUG_KMS("no device found\n");
-		goto err;
-	}
-
-	/*
-	 * In case of BYT with CRC PMIC, we need to use GPIO for
-	 * Panel control.
-	 */
-	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
-	    (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC)) {
-		intel_dsi->gpio_panel =
-			gpiod_get(dev->dev, "panel", GPIOD_OUT_HIGH);
-
-		if (IS_ERR(intel_dsi->gpio_panel)) {
-			DRM_ERROR("Failed to own gpio for panel control\n");
-			intel_dsi->gpio_panel = NULL;
-		}
-	}
-
-	intel_encoder->type = INTEL_OUTPUT_DSI;
-	intel_encoder->power_domain = POWER_DOMAIN_PORT_DSI;
-	intel_encoder->cloneable = 0;
-	drm_connector_init(dev, connector, &intel_dsi_connector_funcs,
-			   DRM_MODE_CONNECTOR_DSI);
-
-	drm_connector_helper_add(connector, &intel_dsi_connector_helper_funcs);
-
-	connector->display_info.subpixel_order = SubPixelHorizontalRGB; /*XXX*/
-	connector->interlace_allowed = false;
-	connector->doublescan_allowed = false;
-
-	intel_connector_attach_encoder(intel_connector, intel_encoder);
-
-	mutex_lock(&dev->mode_config.mutex);
-	intel_dsi_vbt_get_modes(intel_dsi);
-	list_for_each_entry(scan, &connector->probed_modes, head) {
-		if ((scan->type & DRM_MODE_TYPE_PREFERRED)) {
-			fixed_mode = drm_mode_duplicate(dev, scan);
-			break;
-		}
-	}
-	mutex_unlock(&dev->mode_config.mutex);
-
-	if (!fixed_mode) {
-		DRM_DEBUG_KMS("no fixed mode\n");
-		goto err;
-	}
-
-	connector->display_info.width_mm = fixed_mode->width_mm;
-	connector->display_info.height_mm = fixed_mode->height_mm;
-
-	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
-	intel_panel_setup_backlight(connector, INVALID_PIPE);
-
-	intel_dsi_add_properties(intel_connector);
-
-	return;
-
-err:
-	drm_encoder_cleanup(&intel_encoder->base);
-	kfree(intel_dsi);
-	kfree(intel_connector);
-}
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index 7afeb9580f41..dce9bcc2de53 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -129,11 +129,11 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
 	return container_of(encoder, struct intel_dsi, base.base);
 }
 
-/* intel_dsi.c */
+/* vlv_dsi.c */
 void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port);
 enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt);
 
-/* intel_dsi_pll.c */
+/* vlv_dsi_pll.c */
 bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv);
 int intel_compute_dsi_pll(struct intel_encoder *encoder,
 			  struct intel_crtc_state *config);
diff --git a/drivers/gpu/drm/i915/intel_dsi_pll.c b/drivers/gpu/drm/i915/intel_dsi_pll.c
deleted file mode 100644
index 2ff2ee7f3b78..000000000000
--- a/drivers/gpu/drm/i915/intel_dsi_pll.c
+++ /dev/null
@@ -1,650 +0,0 @@
-/*
- * Copyright © 2013 Intel Corporation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- *
- * Authors:
- *	Shobhit Kumar <shobhit.kumar@intel.com>
- *	Yogesh Mohan Marimuthu <yogesh.mohan.marimuthu@intel.com>
- */
-
-#include <linux/kernel.h>
-#include "intel_drv.h"
-#include "i915_drv.h"
-#include "intel_dsi.h"
-
-static const u16 lfsr_converts[] = {
-	426, 469, 234, 373, 442, 221, 110, 311, 411,		/* 62 - 70 */
-	461, 486, 243, 377, 188, 350, 175, 343, 427, 213,	/* 71 - 80 */
-	106, 53, 282, 397, 454, 227, 113, 56, 284, 142,		/* 81 - 90 */
-	71, 35, 273, 136, 324, 418, 465, 488, 500, 506		/* 91 - 100 */
-};
-
-/* Get DSI clock from pixel clock */
-static u32 dsi_clk_from_pclk(u32 pclk, enum mipi_dsi_pixel_format fmt,
-			     int lane_count)
-{
-	u32 dsi_clk_khz;
-	u32 bpp = mipi_dsi_pixel_format_to_bpp(fmt);
-
-	/* DSI data rate = pixel clock * bits per pixel / lane count
-	   pixel clock is converted from KHz to Hz */
-	dsi_clk_khz = DIV_ROUND_CLOSEST(pclk * bpp, lane_count);
-
-	return dsi_clk_khz;
-}
-
-static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
-			struct intel_crtc_state *config,
-			int target_dsi_clk)
-{
-	unsigned int m_min, m_max, p_min = 2, p_max = 6;
-	unsigned int m, n, p;
-	unsigned int calc_m, calc_p;
-	int delta, ref_clk;
-
-	/* target_dsi_clk is expected in kHz */
-	if (target_dsi_clk < 300000 || target_dsi_clk > 1150000) {
-		DRM_ERROR("DSI CLK Out of Range\n");
-		return -ECHRNG;
-	}
-
-	if (IS_CHERRYVIEW(dev_priv)) {
-		ref_clk = 100000;
-		n = 4;
-		m_min = 70;
-		m_max = 96;
-	} else {
-		ref_clk = 25000;
-		n = 1;
-		m_min = 62;
-		m_max = 92;
-	}
-
-	calc_p = p_min;
-	calc_m = m_min;
-	delta = abs(target_dsi_clk - (m_min * ref_clk) / (p_min * n));
-
-	for (m = m_min; m <= m_max && delta; m++) {
-		for (p = p_min; p <= p_max && delta; p++) {
-			/*
-			 * Find the optimal m and p divisors with minimal delta
-			 * +/- the required clock
-			 */
-			int calc_dsi_clk = (m * ref_clk) / (p * n);
-			int d = abs(target_dsi_clk - calc_dsi_clk);
-			if (d < delta) {
-				delta = d;
-				calc_m = m;
-				calc_p = p;
-			}
-		}
-	}
-
-	/* register has log2(N1), this works fine for powers of two */
-	config->dsi_pll.ctrl = 1 << (DSI_PLL_P1_POST_DIV_SHIFT + calc_p - 2);
-	config->dsi_pll.div =
-		(ffs(n) - 1) << DSI_PLL_N1_DIV_SHIFT |
-		(u32)lfsr_converts[calc_m - 62] << DSI_PLL_M1_DIV_SHIFT;
-
-	return 0;
-}
-
-/*
- * XXX: The muxing and gating is hard coded for now. Need to add support for
- * sharing PLLs with two DSI outputs.
- */
-static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	int ret;
-	u32 dsi_clk;
-
-	dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format,
-				    intel_dsi->lane_count);
-
-	ret = dsi_calc_mnp(dev_priv, config, dsi_clk);
-	if (ret) {
-		DRM_DEBUG_KMS("dsi_calc_mnp failed\n");
-		return ret;
-	}
-
-	if (intel_dsi->ports & (1 << PORT_A))
-		config->dsi_pll.ctrl |= DSI_PLL_CLK_GATE_DSI0_DSIPLL;
-
-	if (intel_dsi->ports & (1 << PORT_C))
-		config->dsi_pll.ctrl |= DSI_PLL_CLK_GATE_DSI1_DSIPLL;
-
-	config->dsi_pll.ctrl |= DSI_PLL_VCO_EN;
-
-	DRM_DEBUG_KMS("dsi pll div %08x, ctrl %08x\n",
-		      config->dsi_pll.div, config->dsi_pll.ctrl);
-
-	return 0;
-}
-
-static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	DRM_DEBUG_KMS("\n");
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, 0);
-	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_DIVIDER, config->dsi_pll.div);
-	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL,
-		      config->dsi_pll.ctrl & ~DSI_PLL_VCO_EN);
-
-	/* wait at least 0.5 us after ungating before enabling VCO,
-	 * allow hrtimer subsystem optimization by relaxing timing
-	 */
-	usleep_range(10, 50);
-
-	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, config->dsi_pll.ctrl);
-
-	if (wait_for(vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_CONTROL) &
-						DSI_PLL_LOCK, 20)) {
-
-		mutex_unlock(&dev_priv->sb_lock);
-		DRM_ERROR("DSI PLL lock failed\n");
-		return;
-	}
-	mutex_unlock(&dev_priv->sb_lock);
-
-	DRM_DEBUG_KMS("DSI PLL locked\n");
-}
-
-static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 tmp;
-
-	DRM_DEBUG_KMS("\n");
-
-	mutex_lock(&dev_priv->sb_lock);
-
-	tmp = vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_CONTROL);
-	tmp &= ~DSI_PLL_VCO_EN;
-	tmp |= DSI_PLL_LDO_GATE;
-	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, tmp);
-
-	mutex_unlock(&dev_priv->sb_lock);
-}
-
-static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
-{
-	bool enabled;
-	u32 val;
-	u32 mask;
-
-	mask = BXT_DSI_PLL_DO_ENABLE | BXT_DSI_PLL_LOCKED;
-	val = I915_READ(BXT_DSI_PLL_ENABLE);
-	enabled = (val & mask) == mask;
-
-	if (!enabled)
-		return false;
-
-	/*
-	 * Dividers must be programmed with valid values. As per BSEPC, for
-	 * GEMINLAKE only PORT A divider values are checked while for BXT
-	 * both divider values are validated. Check this here for
-	 * paranoia, since BIOS is known to misconfigure PLLs in this way at
-	 * times, and since accessing DSI registers with invalid dividers
-	 * causes a system hang.
-	 */
-	val = I915_READ(BXT_DSI_PLL_CTL);
-	if (IS_GEMINILAKE(dev_priv)) {
-		if (!(val & BXT_DSIA_16X_MASK)) {
-			DRM_DEBUG_DRIVER("Invalid PLL divider (%08x)\n", val);
-			enabled = false;
-		}
-	} else {
-		if (!(val & BXT_DSIA_16X_MASK) || !(val & BXT_DSIC_16X_MASK)) {
-			DRM_DEBUG_DRIVER("Invalid PLL divider (%08x)\n", val);
-			enabled = false;
-		}
-	}
-
-	return enabled;
-}
-
-static void bxt_disable_dsi_pll(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	u32 val;
-
-	DRM_DEBUG_KMS("\n");
-
-	val = I915_READ(BXT_DSI_PLL_ENABLE);
-	val &= ~BXT_DSI_PLL_DO_ENABLE;
-	I915_WRITE(BXT_DSI_PLL_ENABLE, val);
-
-	/*
-	 * PLL lock should deassert within 200us.
-	 * Wait up to 1ms before timing out.
-	 */
-	if (intel_wait_for_register(dev_priv,
-				    BXT_DSI_PLL_ENABLE,
-				    BXT_DSI_PLL_LOCKED,
-				    0,
-				    1))
-		DRM_ERROR("Timeout waiting for PLL lock deassertion\n");
-}
-
-static void assert_bpp_mismatch(enum mipi_dsi_pixel_format fmt, int pipe_bpp)
-{
-	int bpp = mipi_dsi_pixel_format_to_bpp(fmt);
-
-	WARN(bpp != pipe_bpp,
-	     "bpp match assertion failure (expected %d, current %d)\n",
-	     bpp, pipe_bpp);
-}
-
-static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	u32 dsi_clock, pclk;
-	u32 pll_ctl, pll_div;
-	u32 m = 0, p = 0, n;
-	int refclk = IS_CHERRYVIEW(dev_priv) ? 100000 : 25000;
-	int i;
-
-	DRM_DEBUG_KMS("\n");
-
-	mutex_lock(&dev_priv->sb_lock);
-	pll_ctl = vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_CONTROL);
-	pll_div = vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_DIVIDER);
-	mutex_unlock(&dev_priv->sb_lock);
-
-	config->dsi_pll.ctrl = pll_ctl & ~DSI_PLL_LOCK;
-	config->dsi_pll.div = pll_div;
-
-	/* mask out other bits and extract the P1 divisor */
-	pll_ctl &= DSI_PLL_P1_POST_DIV_MASK;
-	pll_ctl = pll_ctl >> (DSI_PLL_P1_POST_DIV_SHIFT - 2);
-
-	/* N1 divisor */
-	n = (pll_div & DSI_PLL_N1_DIV_MASK) >> DSI_PLL_N1_DIV_SHIFT;
-	n = 1 << n; /* register has log2(N1) */
-
-	/* mask out the other bits and extract the M1 divisor */
-	pll_div &= DSI_PLL_M1_DIV_MASK;
-	pll_div = pll_div >> DSI_PLL_M1_DIV_SHIFT;
-
-	while (pll_ctl) {
-		pll_ctl = pll_ctl >> 1;
-		p++;
-	}
-	p--;
-
-	if (!p) {
-		DRM_ERROR("wrong P1 divisor\n");
-		return 0;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(lfsr_converts); i++) {
-		if (lfsr_converts[i] == pll_div)
-			break;
-	}
-
-	if (i == ARRAY_SIZE(lfsr_converts)) {
-		DRM_ERROR("wrong m_seed programmed\n");
-		return 0;
-	}
-
-	m = i + 62;
-
-	dsi_clock = (m * refclk) / (p * n);
-
-	/* pixel_format and pipe_bpp should agree */
-	assert_bpp_mismatch(intel_dsi->pixel_format, pipe_bpp);
-
-	pclk = DIV_ROUND_CLOSEST(dsi_clock * intel_dsi->lane_count, pipe_bpp);
-
-	return pclk;
-}
-
-static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
-{
-	u32 pclk;
-	u32 dsi_clk;
-	u32 dsi_ratio;
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	/* Divide by zero */
-	if (!pipe_bpp) {
-		DRM_ERROR("Invalid BPP(0)\n");
-		return 0;
-	}
-
-	config->dsi_pll.ctrl = I915_READ(BXT_DSI_PLL_CTL);
-
-	dsi_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK;
-
-	dsi_clk = (dsi_ratio * BXT_REF_CLOCK_KHZ) / 2;
-
-	/* pixel_format and pipe_bpp should agree */
-	assert_bpp_mismatch(intel_dsi->pixel_format, pipe_bpp);
-
-	pclk = DIV_ROUND_CLOSEST(dsi_clk * intel_dsi->lane_count, pipe_bpp);
-
-	DRM_DEBUG_DRIVER("Calculated pclk=%u\n", pclk);
-	return pclk;
-}
-
-u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-		       struct intel_crtc_state *config)
-{
-	if (IS_GEN9_LP(to_i915(encoder->base.dev)))
-		return bxt_dsi_get_pclk(encoder, pipe_bpp, config);
-	else
-		return vlv_dsi_get_pclk(encoder, pipe_bpp, config);
-}
-
-static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
-{
-	u32 temp;
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-
-	temp = I915_READ(MIPI_CTRL(port));
-	temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
-	I915_WRITE(MIPI_CTRL(port), temp |
-			intel_dsi->escape_clk_div <<
-			ESCAPE_CLOCK_DIVIDER_SHIFT);
-}
-
-static void glk_dsi_program_esc_clock(struct drm_device *dev,
-				   const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	u32 dsi_rate = 0;
-	u32 pll_ratio = 0;
-	u32 ddr_clk = 0;
-	u32 div1_value = 0;
-	u32 div2_value = 0;
-	u32 txesc1_div = 0;
-	u32 txesc2_div = 0;
-
-	pll_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK;
-
-	dsi_rate = (BXT_REF_CLOCK_KHZ * pll_ratio) / 2;
-
-	ddr_clk = dsi_rate / 2;
-
-	/* Variable divider value */
-	div1_value = DIV_ROUND_CLOSEST(ddr_clk, 20000);
-
-	/* Calculate TXESC1 divider */
-	if (div1_value <= 10)
-		txesc1_div = div1_value;
-	else if ((div1_value > 10) && (div1_value <= 20))
-		txesc1_div = DIV_ROUND_UP(div1_value, 2);
-	else if ((div1_value > 20) && (div1_value <= 30))
-		txesc1_div = DIV_ROUND_UP(div1_value, 4);
-	else if ((div1_value > 30) && (div1_value <= 40))
-		txesc1_div = DIV_ROUND_UP(div1_value, 6);
-	else if ((div1_value > 40) && (div1_value <= 50))
-		txesc1_div = DIV_ROUND_UP(div1_value, 8);
-	else
-		txesc1_div = 10;
-
-	/* Calculate TXESC2 divider */
-	div2_value = DIV_ROUND_UP(div1_value, txesc1_div);
-
-	if (div2_value < 10)
-		txesc2_div = div2_value;
-	else
-		txesc2_div = 10;
-
-	I915_WRITE(MIPIO_TXESC_CLK_DIV1, txesc1_div & GLK_TX_ESC_CLK_DIV1_MASK);
-	I915_WRITE(MIPIO_TXESC_CLK_DIV2, txesc2_div & GLK_TX_ESC_CLK_DIV2_MASK);
-}
-
-/* Program BXT Mipi clocks and dividers */
-static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port,
-				   const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	u32 tmp;
-	u32 dsi_rate = 0;
-	u32 pll_ratio = 0;
-	u32 rx_div;
-	u32 tx_div;
-	u32 rx_div_upper;
-	u32 rx_div_lower;
-	u32 mipi_8by3_divider;
-
-	/* Clear old configurations */
-	tmp = I915_READ(BXT_MIPI_CLOCK_CTL);
-	tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port));
-	tmp &= ~(BXT_MIPI_RX_ESCLK_UPPER_FIXDIV_MASK(port));
-	tmp &= ~(BXT_MIPI_8X_BY3_DIVIDER_MASK(port));
-	tmp &= ~(BXT_MIPI_RX_ESCLK_LOWER_FIXDIV_MASK(port));
-
-	/* Get the current DSI rate(actual) */
-	pll_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK;
-	dsi_rate = (BXT_REF_CLOCK_KHZ * pll_ratio) / 2;
-
-	/*
-	 * tx clock should be <= 20MHz and the div value must be
-	 * subtracted by 1 as per bspec
-	 */
-	tx_div = DIV_ROUND_UP(dsi_rate, 20000) - 1;
-	/*
-	 * rx clock should be <= 150MHz and the div value must be
-	 * subtracted by 1 as per bspec
-	 */
-	rx_div = DIV_ROUND_UP(dsi_rate, 150000) - 1;
-
-	/*
-	 * rx divider value needs to be updated in the
-	 * two differnt bit fields in the register hence splitting the
-	 * rx divider value accordingly
-	 */
-	rx_div_lower = rx_div & RX_DIVIDER_BIT_1_2;
-	rx_div_upper = (rx_div & RX_DIVIDER_BIT_3_4) >> 2;
-
-	mipi_8by3_divider = 0x2;
-
-	tmp |= BXT_MIPI_8X_BY3_DIVIDER(port, mipi_8by3_divider);
-	tmp |= BXT_MIPI_TX_ESCLK_DIVIDER(port, tx_div);
-	tmp |= BXT_MIPI_RX_ESCLK_LOWER_DIVIDER(port, rx_div_lower);
-	tmp |= BXT_MIPI_RX_ESCLK_UPPER_DIVIDER(port, rx_div_upper);
-
-	I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
-}
-
-static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	u8 dsi_ratio, dsi_ratio_min, dsi_ratio_max;
-	u32 dsi_clk;
-
-	dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format,
-				    intel_dsi->lane_count);
-
-	/*
-	 * From clock diagram, to get PLL ratio divider, divide double of DSI
-	 * link rate (i.e., 2*8x=16x frequency value) by ref clock. Make sure to
-	 * round 'up' the result
-	 */
-	dsi_ratio = DIV_ROUND_UP(dsi_clk * 2, BXT_REF_CLOCK_KHZ);
-
-	if (IS_BROXTON(dev_priv)) {
-		dsi_ratio_min = BXT_DSI_PLL_RATIO_MIN;
-		dsi_ratio_max = BXT_DSI_PLL_RATIO_MAX;
-	} else {
-		dsi_ratio_min = GLK_DSI_PLL_RATIO_MIN;
-		dsi_ratio_max = GLK_DSI_PLL_RATIO_MAX;
-	}
-
-	if (dsi_ratio < dsi_ratio_min || dsi_ratio > dsi_ratio_max) {
-		DRM_ERROR("Cant get a suitable ratio from DSI PLL ratios\n");
-		return -ECHRNG;
-	} else
-		DRM_DEBUG_KMS("DSI PLL calculation is Done!!\n");
-
-	/*
-	 * Program DSI ratio and Select MIPIC and MIPIA PLL output as 8x
-	 * Spec says both have to be programmed, even if one is not getting
-	 * used. Configure MIPI_CLOCK_CTL dividers in modeset
-	 */
-	config->dsi_pll.ctrl = dsi_ratio | BXT_DSIA_16X_BY2 | BXT_DSIC_16X_BY2;
-
-	/* As per recommendation from hardware team,
-	 * Prog PVD ratio =1 if dsi ratio <= 50
-	 */
-	if (IS_BROXTON(dev_priv) && dsi_ratio <= 50)
-		config->dsi_pll.ctrl |= BXT_DSI_PLL_PVD_RATIO_1;
-
-	return 0;
-}
-
-static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
-	enum port port;
-	u32 val;
-
-	DRM_DEBUG_KMS("\n");
-
-	/* Configure PLL vales */
-	I915_WRITE(BXT_DSI_PLL_CTL, config->dsi_pll.ctrl);
-	POSTING_READ(BXT_DSI_PLL_CTL);
-
-	/* Program TX, RX, Dphy clocks */
-	if (IS_BROXTON(dev_priv)) {
-		for_each_dsi_port(port, intel_dsi->ports)
-			bxt_dsi_program_clocks(encoder->base.dev, port, config);
-	} else {
-		glk_dsi_program_esc_clock(encoder->base.dev, config);
-	}
-
-	/* Enable DSI PLL */
-	val = I915_READ(BXT_DSI_PLL_ENABLE);
-	val |= BXT_DSI_PLL_DO_ENABLE;
-	I915_WRITE(BXT_DSI_PLL_ENABLE, val);
-
-	/* Timeout and fail if PLL not locked */
-	if (intel_wait_for_register(dev_priv,
-				    BXT_DSI_PLL_ENABLE,
-				    BXT_DSI_PLL_LOCKED,
-				    BXT_DSI_PLL_LOCKED,
-				    1)) {
-		DRM_ERROR("Timed out waiting for DSI PLL to lock\n");
-		return;
-	}
-
-	DRM_DEBUG_KMS("DSI PLL locked\n");
-}
-
-bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
-{
-	if (IS_GEN9_LP(dev_priv))
-		return bxt_dsi_pll_is_enabled(dev_priv);
-
-	MISSING_CASE(INTEL_DEVID(dev_priv));
-
-	return false;
-}
-
-int intel_compute_dsi_pll(struct intel_encoder *encoder,
-			  struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_compute_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		return gen9lp_compute_dsi_pll(encoder, config);
-
-	return -ENODEV;
-}
-
-void intel_enable_dsi_pll(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_enable_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		gen9lp_enable_dsi_pll(encoder, config);
-}
-
-void intel_disable_dsi_pll(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_disable_dsi_pll(encoder);
-	else if (IS_GEN9_LP(dev_priv))
-		bxt_disable_dsi_pll(encoder);
-}
-
-static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
-				    enum port port)
-{
-	u32 tmp;
-	struct drm_device *dev = encoder->base.dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	/* Clear old configurations */
-	if (IS_BROXTON(dev_priv)) {
-		tmp = I915_READ(BXT_MIPI_CLOCK_CTL);
-		tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port));
-		tmp &= ~(BXT_MIPI_RX_ESCLK_UPPER_FIXDIV_MASK(port));
-		tmp &= ~(BXT_MIPI_8X_BY3_DIVIDER_MASK(port));
-		tmp &= ~(BXT_MIPI_RX_ESCLK_LOWER_FIXDIV_MASK(port));
-		I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
-	} else {
-		tmp = I915_READ(MIPIO_TXESC_CLK_DIV1);
-		tmp &= ~GLK_TX_ESC_CLK_DIV1_MASK;
-		I915_WRITE(MIPIO_TXESC_CLK_DIV1, tmp);
-
-		tmp = I915_READ(MIPIO_TXESC_CLK_DIV2);
-		tmp &= ~GLK_TX_ESC_CLK_DIV2_MASK;
-		I915_WRITE(MIPIO_TXESC_CLK_DIV2, tmp);
-	}
-	I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
-}
-
-void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_GEN9_LP(dev_priv))
-		gen9lp_dsi_reset_clocks(encoder, port);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_reset_clocks(encoder, port);
-}
diff --git a/drivers/gpu/drm/i915/vlv_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
new file mode 100644
index 000000000000..3b7acb5a70b3
--- /dev/null
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -0,0 +1,1866 @@
+/*
+ * Copyright © 2013 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Author: Jani Nikula <jani.nikula@intel.com>
+ */
+
+#include <drm/drmP.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_edid.h>
+#include <drm/i915_drm.h>
+#include <drm/drm_mipi_dsi.h>
+#include <linux/slab.h>
+#include <linux/gpio/consumer.h>
+#include "i915_drv.h"
+#include "intel_drv.h"
+#include "intel_dsi.h"
+
+/* return pixels in terms of txbyteclkhs */
+static u16 txbyteclkhs(u16 pixels, int bpp, int lane_count,
+		       u16 burst_mode_ratio)
+{
+	return DIV_ROUND_UP(DIV_ROUND_UP(pixels * bpp * burst_mode_ratio,
+					 8 * 100), lane_count);
+}
+
+/* return pixels equvalent to txbyteclkhs */
+static u16 pixels_from_txbyteclkhs(u16 clk_hs, int bpp, int lane_count,
+			u16 burst_mode_ratio)
+{
+	return DIV_ROUND_UP((clk_hs * lane_count * 8 * 100),
+						(bpp * burst_mode_ratio));
+}
+
+enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt)
+{
+	/* It just so happens the VBT matches register contents. */
+	switch (fmt) {
+	case VID_MODE_FORMAT_RGB888:
+		return MIPI_DSI_FMT_RGB888;
+	case VID_MODE_FORMAT_RGB666:
+		return MIPI_DSI_FMT_RGB666;
+	case VID_MODE_FORMAT_RGB666_PACKED:
+		return MIPI_DSI_FMT_RGB666_PACKED;
+	case VID_MODE_FORMAT_RGB565:
+		return MIPI_DSI_FMT_RGB565;
+	default:
+		MISSING_CASE(fmt);
+		return MIPI_DSI_FMT_RGB666;
+	}
+}
+
+void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
+{
+	struct drm_encoder *encoder = &intel_dsi->base.base;
+	struct drm_device *dev = encoder->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 mask;
+
+	mask = LP_CTRL_FIFO_EMPTY | HS_CTRL_FIFO_EMPTY |
+		LP_DATA_FIFO_EMPTY | HS_DATA_FIFO_EMPTY;
+
+	if (intel_wait_for_register(dev_priv,
+				    MIPI_GEN_FIFO_STAT(port), mask, mask,
+				    100))
+		DRM_ERROR("DPI FIFOs are not empty\n");
+}
+
+static void write_data(struct drm_i915_private *dev_priv,
+		       i915_reg_t reg,
+		       const u8 *data, u32 len)
+{
+	u32 i, j;
+
+	for (i = 0; i < len; i += 4) {
+		u32 val = 0;
+
+		for (j = 0; j < min_t(u32, len - i, 4); j++)
+			val |= *data++ << 8 * j;
+
+		I915_WRITE(reg, val);
+	}
+}
+
+static void read_data(struct drm_i915_private *dev_priv,
+		      i915_reg_t reg,
+		      u8 *data, u32 len)
+{
+	u32 i, j;
+
+	for (i = 0; i < len; i += 4) {
+		u32 val = I915_READ(reg);
+
+		for (j = 0; j < min_t(u32, len - i, 4); j++)
+			*data++ = val >> 8 * j;
+	}
+}
+
+static ssize_t intel_dsi_host_transfer(struct mipi_dsi_host *host,
+				       const struct mipi_dsi_msg *msg)
+{
+	struct intel_dsi_host *intel_dsi_host = to_intel_dsi_host(host);
+	struct drm_device *dev = intel_dsi_host->intel_dsi->base.base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	enum port port = intel_dsi_host->port;
+	struct mipi_dsi_packet packet;
+	ssize_t ret;
+	const u8 *header, *data;
+	i915_reg_t data_reg, ctrl_reg;
+	u32 data_mask, ctrl_mask;
+
+	ret = mipi_dsi_create_packet(&packet, msg);
+	if (ret < 0)
+		return ret;
+
+	header = packet.header;
+	data = packet.payload;
+
+	if (msg->flags & MIPI_DSI_MSG_USE_LPM) {
+		data_reg = MIPI_LP_GEN_DATA(port);
+		data_mask = LP_DATA_FIFO_FULL;
+		ctrl_reg = MIPI_LP_GEN_CTRL(port);
+		ctrl_mask = LP_CTRL_FIFO_FULL;
+	} else {
+		data_reg = MIPI_HS_GEN_DATA(port);
+		data_mask = HS_DATA_FIFO_FULL;
+		ctrl_reg = MIPI_HS_GEN_CTRL(port);
+		ctrl_mask = HS_CTRL_FIFO_FULL;
+	}
+
+	/* note: this is never true for reads */
+	if (packet.payload_length) {
+		if (intel_wait_for_register(dev_priv,
+					    MIPI_GEN_FIFO_STAT(port),
+					    data_mask, 0,
+					    50))
+			DRM_ERROR("Timeout waiting for HS/LP DATA FIFO !full\n");
+
+		write_data(dev_priv, data_reg, packet.payload,
+			   packet.payload_length);
+	}
+
+	if (msg->rx_len) {
+		I915_WRITE(MIPI_INTR_STAT(port), GEN_READ_DATA_AVAIL);
+	}
+
+	if (intel_wait_for_register(dev_priv,
+				    MIPI_GEN_FIFO_STAT(port),
+				    ctrl_mask, 0,
+				    50)) {
+		DRM_ERROR("Timeout waiting for HS/LP CTRL FIFO !full\n");
+	}
+
+	I915_WRITE(ctrl_reg, header[2] << 16 | header[1] << 8 | header[0]);
+
+	/* ->rx_len is set only for reads */
+	if (msg->rx_len) {
+		data_mask = GEN_READ_DATA_AVAIL;
+		if (intel_wait_for_register(dev_priv,
+					    MIPI_INTR_STAT(port),
+					    data_mask, data_mask,
+					    50))
+			DRM_ERROR("Timeout waiting for read data.\n");
+
+		read_data(dev_priv, data_reg, msg->rx_buf, msg->rx_len);
+	}
+
+	/* XXX: fix for reads and writes */
+	return 4 + packet.payload_length;
+}
+
+static int intel_dsi_host_attach(struct mipi_dsi_host *host,
+				 struct mipi_dsi_device *dsi)
+{
+	return 0;
+}
+
+static int intel_dsi_host_detach(struct mipi_dsi_host *host,
+				 struct mipi_dsi_device *dsi)
+{
+	return 0;
+}
+
+static const struct mipi_dsi_host_ops intel_dsi_host_ops = {
+	.attach = intel_dsi_host_attach,
+	.detach = intel_dsi_host_detach,
+	.transfer = intel_dsi_host_transfer,
+};
+
+static struct intel_dsi_host *intel_dsi_host_init(struct intel_dsi *intel_dsi,
+						  enum port port)
+{
+	struct intel_dsi_host *host;
+	struct mipi_dsi_device *device;
+
+	host = kzalloc(sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return NULL;
+
+	host->base.ops = &intel_dsi_host_ops;
+	host->intel_dsi = intel_dsi;
+	host->port = port;
+
+	/*
+	 * We should call mipi_dsi_host_register(&host->base) here, but we don't
+	 * have a host->dev, and we don't have OF stuff either. So just use the
+	 * dsi framework as a library and hope for the best. Create the dsi
+	 * devices by ourselves here too. Need to be careful though, because we
+	 * don't initialize any of the driver model devices here.
+	 */
+	device = kzalloc(sizeof(*device), GFP_KERNEL);
+	if (!device) {
+		kfree(host);
+		return NULL;
+	}
+
+	device->host = &host->base;
+	host->device = device;
+
+	return host;
+}
+
+/*
+ * send a video mode command
+ *
+ * XXX: commands with data in MIPI_DPI_DATA?
+ */
+static int dpi_send_cmd(struct intel_dsi *intel_dsi, u32 cmd, bool hs,
+			enum port port)
+{
+	struct drm_encoder *encoder = &intel_dsi->base.base;
+	struct drm_device *dev = encoder->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 mask;
+
+	/* XXX: pipe, hs */
+	if (hs)
+		cmd &= ~DPI_LP_MODE;
+	else
+		cmd |= DPI_LP_MODE;
+
+	/* clear bit */
+	I915_WRITE(MIPI_INTR_STAT(port), SPL_PKT_SENT_INTERRUPT);
+
+	/* XXX: old code skips write if control unchanged */
+	if (cmd == I915_READ(MIPI_DPI_CONTROL(port)))
+		DRM_DEBUG_KMS("Same special packet %02x twice in a row.\n", cmd);
+
+	I915_WRITE(MIPI_DPI_CONTROL(port), cmd);
+
+	mask = SPL_PKT_SENT_INTERRUPT;
+	if (intel_wait_for_register(dev_priv,
+				    MIPI_INTR_STAT(port), mask, mask,
+				    100))
+		DRM_ERROR("Video mode command 0x%08x send failed.\n", cmd);
+
+	return 0;
+}
+
+static void band_gap_reset(struct drm_i915_private *dev_priv)
+{
+	mutex_lock(&dev_priv->sb_lock);
+
+	vlv_flisdsi_write(dev_priv, 0x08, 0x0001);
+	vlv_flisdsi_write(dev_priv, 0x0F, 0x0005);
+	vlv_flisdsi_write(dev_priv, 0x0F, 0x0025);
+	udelay(150);
+	vlv_flisdsi_write(dev_priv, 0x0F, 0x0000);
+	vlv_flisdsi_write(dev_priv, 0x08, 0x0000);
+
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
+static inline bool is_vid_mode(struct intel_dsi *intel_dsi)
+{
+	return intel_dsi->operation_mode == INTEL_DSI_VIDEO_MODE;
+}
+
+static inline bool is_cmd_mode(struct intel_dsi *intel_dsi)
+{
+	return intel_dsi->operation_mode == INTEL_DSI_COMMAND_MODE;
+}
+
+static bool intel_dsi_compute_config(struct intel_encoder *encoder,
+				     struct intel_crtc_state *pipe_config,
+				     struct drm_connector_state *conn_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = container_of(encoder, struct intel_dsi,
+						   base);
+	struct intel_connector *intel_connector = intel_dsi->attached_connector;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
+	struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	int ret;
+
+	DRM_DEBUG_KMS("\n");
+
+	if (fixed_mode) {
+		intel_fixed_panel_mode(fixed_mode, adjusted_mode);
+
+		if (HAS_GMCH_DISPLAY(dev_priv))
+			intel_gmch_panel_fitting(crtc, pipe_config,
+						 conn_state->scaling_mode);
+		else
+			intel_pch_panel_fitting(crtc, pipe_config,
+						conn_state->scaling_mode);
+	}
+
+	if (adjusted_mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return false;
+
+	/* DSI uses short packets for sync events, so clear mode flags for DSI */
+	adjusted_mode->flags = 0;
+
+	if (IS_GEN9_LP(dev_priv)) {
+		/* Enable Frame time stamp based scanline reporting */
+		adjusted_mode->private_flags |=
+			I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP;
+
+		/* Dual link goes to DSI transcoder A. */
+		if (intel_dsi->ports == BIT(PORT_C))
+			pipe_config->cpu_transcoder = TRANSCODER_DSI_C;
+		else
+			pipe_config->cpu_transcoder = TRANSCODER_DSI_A;
+	}
+
+	ret = intel_compute_dsi_pll(encoder, pipe_config);
+	if (ret)
+		return false;
+
+	pipe_config->clock_set = true;
+
+	return true;
+}
+
+static bool glk_dsi_enable_io(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 tmp;
+	bool cold_boot = false;
+
+	/* Set the MIPI mode
+	 * If MIPI_Mode is off, then writing to LP_Wake bit is not reflecting.
+	 * Power ON MIPI IO first and then write into IO reset and LP wake bits
+	 */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(MIPI_CTRL(port));
+		I915_WRITE(MIPI_CTRL(port), tmp | GLK_MIPIIO_ENABLE);
+	}
+
+	/* Put the IO into reset */
+	tmp = I915_READ(MIPI_CTRL(PORT_A));
+	tmp &= ~GLK_MIPIIO_RESET_RELEASED;
+	I915_WRITE(MIPI_CTRL(PORT_A), tmp);
+
+	/* Program LP Wake */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(MIPI_CTRL(port));
+		if (!(I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY))
+			tmp &= ~GLK_LP_WAKE;
+		else
+			tmp |= GLK_LP_WAKE;
+		I915_WRITE(MIPI_CTRL(port), tmp);
+	}
+
+	/* Wait for Pwr ACK */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (intel_wait_for_register(dev_priv,
+				MIPI_CTRL(port), GLK_MIPIIO_PORT_POWERED,
+				GLK_MIPIIO_PORT_POWERED, 20))
+			DRM_ERROR("MIPIO port is powergated\n");
+	}
+
+	/* Check for cold boot scenario */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		cold_boot |= !(I915_READ(MIPI_DEVICE_READY(port)) &
+							DEVICE_READY);
+	}
+
+	return cold_boot;
+}
+
+static void glk_dsi_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 val;
+
+	/* Wait for MIPI PHY status bit to set */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (intel_wait_for_register(dev_priv,
+				MIPI_CTRL(port), GLK_PHY_STATUS_PORT_READY,
+				GLK_PHY_STATUS_PORT_READY, 20))
+			DRM_ERROR("PHY is not ON\n");
+	}
+
+	/* Get IO out of reset */
+	val = I915_READ(MIPI_CTRL(PORT_A));
+	I915_WRITE(MIPI_CTRL(PORT_A), val | GLK_MIPIIO_RESET_RELEASED);
+
+	/* Get IO out of Low power state*/
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (!(I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY)) {
+			val = I915_READ(MIPI_DEVICE_READY(port));
+			val &= ~ULPS_STATE_MASK;
+			val |= DEVICE_READY;
+			I915_WRITE(MIPI_DEVICE_READY(port), val);
+			usleep_range(10, 15);
+		} else {
+			/* Enter ULPS */
+			val = I915_READ(MIPI_DEVICE_READY(port));
+			val &= ~ULPS_STATE_MASK;
+			val |= (ULPS_STATE_ENTER | DEVICE_READY);
+			I915_WRITE(MIPI_DEVICE_READY(port), val);
+
+			/* Wait for ULPS active */
+			if (intel_wait_for_register(dev_priv,
+				MIPI_CTRL(port), GLK_ULPS_NOT_ACTIVE, 0, 20))
+				DRM_ERROR("ULPS not active\n");
+
+			/* Exit ULPS */
+			val = I915_READ(MIPI_DEVICE_READY(port));
+			val &= ~ULPS_STATE_MASK;
+			val |= (ULPS_STATE_EXIT | DEVICE_READY);
+			I915_WRITE(MIPI_DEVICE_READY(port), val);
+
+			/* Enter Normal Mode */
+			val = I915_READ(MIPI_DEVICE_READY(port));
+			val &= ~ULPS_STATE_MASK;
+			val |= (ULPS_STATE_NORMAL_OPERATION | DEVICE_READY);
+			I915_WRITE(MIPI_DEVICE_READY(port), val);
+
+			val = I915_READ(MIPI_CTRL(port));
+			val &= ~GLK_LP_WAKE;
+			I915_WRITE(MIPI_CTRL(port), val);
+		}
+	}
+
+	/* Wait for Stop state */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (intel_wait_for_register(dev_priv,
+				MIPI_CTRL(port), GLK_DATA_LANE_STOP_STATE,
+				GLK_DATA_LANE_STOP_STATE, 20))
+			DRM_ERROR("Date lane not in STOP state\n");
+	}
+
+	/* Wait for AFE LATCH */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (intel_wait_for_register(dev_priv,
+				BXT_MIPI_PORT_CTRL(port), AFE_LATCHOUT,
+				AFE_LATCHOUT, 20))
+			DRM_ERROR("D-PHY not entering LP-11 state\n");
+	}
+}
+
+static void bxt_dsi_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 val;
+
+	DRM_DEBUG_KMS("\n");
+
+	/* Enable MIPI PHY transparent latch */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		val = I915_READ(BXT_MIPI_PORT_CTRL(port));
+		I915_WRITE(BXT_MIPI_PORT_CTRL(port), val | LP_OUTPUT_HOLD);
+		usleep_range(2000, 2500);
+	}
+
+	/* Clear ULPS and set device ready */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		val = I915_READ(MIPI_DEVICE_READY(port));
+		val &= ~ULPS_STATE_MASK;
+		I915_WRITE(MIPI_DEVICE_READY(port), val);
+		usleep_range(2000, 2500);
+		val |= DEVICE_READY;
+		I915_WRITE(MIPI_DEVICE_READY(port), val);
+	}
+}
+
+static void vlv_dsi_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 val;
+
+	DRM_DEBUG_KMS("\n");
+
+	mutex_lock(&dev_priv->sb_lock);
+	/* program rcomp for compliance, reduce from 50 ohms to 45 ohms
+	 * needed everytime after power gate */
+	vlv_flisdsi_write(dev_priv, 0x04, 0x0004);
+	mutex_unlock(&dev_priv->sb_lock);
+
+	/* bandgap reset is needed after everytime we do power gate */
+	band_gap_reset(dev_priv);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+
+		I915_WRITE(MIPI_DEVICE_READY(port), ULPS_STATE_ENTER);
+		usleep_range(2500, 3000);
+
+		/* Enable MIPI PHY transparent latch
+		 * Common bit for both MIPI Port A & MIPI Port C
+		 * No similar bit in MIPI Port C reg
+		 */
+		val = I915_READ(MIPI_PORT_CTRL(PORT_A));
+		I915_WRITE(MIPI_PORT_CTRL(PORT_A), val | LP_OUTPUT_HOLD);
+		usleep_range(1000, 1500);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), ULPS_STATE_EXIT);
+		usleep_range(2500, 3000);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY);
+		usleep_range(2500, 3000);
+	}
+}
+
+static void intel_dsi_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		vlv_dsi_device_ready(encoder);
+	else if (IS_BROXTON(dev_priv))
+		bxt_dsi_device_ready(encoder);
+	else if (IS_GEMINILAKE(dev_priv))
+		glk_dsi_device_ready(encoder);
+}
+
+static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 val;
+
+	/* Enter ULPS */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		val = I915_READ(MIPI_DEVICE_READY(port));
+		val &= ~ULPS_STATE_MASK;
+		val |= (ULPS_STATE_ENTER | DEVICE_READY);
+		I915_WRITE(MIPI_DEVICE_READY(port), val);
+	}
+
+	/* Wait for MIPI PHY status bit to unset */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (intel_wait_for_register(dev_priv,
+					    MIPI_CTRL(port),
+					    GLK_PHY_STATUS_PORT_READY, 0, 20))
+			DRM_ERROR("PHY is not turning OFF\n");
+	}
+
+	/* Wait for Pwr ACK bit to unset */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (intel_wait_for_register(dev_priv,
+					    MIPI_CTRL(port),
+					    GLK_MIPIIO_PORT_POWERED, 0, 20))
+			DRM_ERROR("MIPI IO Port is not powergated\n");
+	}
+}
+
+static void glk_dsi_disable_mipi_io(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 tmp;
+
+	/* Put the IO into reset */
+	tmp = I915_READ(MIPI_CTRL(PORT_A));
+	tmp &= ~GLK_MIPIIO_RESET_RELEASED;
+	I915_WRITE(MIPI_CTRL(PORT_A), tmp);
+
+	/* Wait for MIPI PHY status bit to unset */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (intel_wait_for_register(dev_priv,
+					    MIPI_CTRL(port),
+					    GLK_PHY_STATUS_PORT_READY, 0, 20))
+			DRM_ERROR("PHY is not turning OFF\n");
+	}
+
+	/* Clear MIPI mode */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(MIPI_CTRL(port));
+		tmp &= ~GLK_MIPIIO_ENABLE;
+		I915_WRITE(MIPI_CTRL(port), tmp);
+	}
+}
+
+static void glk_dsi_clear_device_ready(struct intel_encoder *encoder)
+{
+	glk_dsi_enter_low_power_mode(encoder);
+	glk_dsi_disable_mipi_io(encoder);
+}
+
+static void vlv_dsi_clear_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+
+	DRM_DEBUG_KMS("\n");
+	for_each_dsi_port(port, intel_dsi->ports) {
+		/* Common bit for both MIPI Port A & MIPI Port C on VLV/CHV */
+		i915_reg_t port_ctrl = IS_GEN9_LP(dev_priv) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(PORT_A);
+		u32 val;
+
+		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY |
+							ULPS_STATE_ENTER);
+		usleep_range(2000, 2500);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY |
+							ULPS_STATE_EXIT);
+		usleep_range(2000, 2500);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), DEVICE_READY |
+							ULPS_STATE_ENTER);
+		usleep_range(2000, 2500);
+
+		/*
+		 * On VLV/CHV, wait till Clock lanes are in LP-00 state for MIPI
+		 * Port A only. MIPI Port C has no similar bit for checking.
+		 */
+		if ((IS_GEN9_LP(dev_priv) || port == PORT_A) &&
+		    intel_wait_for_register(dev_priv,
+					    port_ctrl, AFE_LATCHOUT, 0,
+					    30))
+			DRM_ERROR("DSI LP not going Low\n");
+
+		/* Disable MIPI PHY transparent latch */
+		val = I915_READ(port_ctrl);
+		I915_WRITE(port_ctrl, val & ~LP_OUTPUT_HOLD);
+		usleep_range(1000, 1500);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), 0x00);
+		usleep_range(2000, 2500);
+	}
+}
+
+static void intel_dsi_port_enable(struct intel_encoder *encoder,
+				  const struct intel_crtc_state *crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+
+	if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK) {
+		u32 temp;
+		if (IS_GEN9_LP(dev_priv)) {
+			for_each_dsi_port(port, intel_dsi->ports) {
+				temp = I915_READ(MIPI_CTRL(port));
+				temp &= ~BXT_PIXEL_OVERLAP_CNT_MASK |
+					intel_dsi->pixel_overlap <<
+					BXT_PIXEL_OVERLAP_CNT_SHIFT;
+				I915_WRITE(MIPI_CTRL(port), temp);
+			}
+		} else {
+			temp = I915_READ(VLV_CHICKEN_3);
+			temp &= ~PIXEL_OVERLAP_CNT_MASK |
+					intel_dsi->pixel_overlap <<
+					PIXEL_OVERLAP_CNT_SHIFT;
+			I915_WRITE(VLV_CHICKEN_3, temp);
+		}
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		i915_reg_t port_ctrl = IS_GEN9_LP(dev_priv) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
+		u32 temp;
+
+		temp = I915_READ(port_ctrl);
+
+		temp &= ~LANE_CONFIGURATION_MASK;
+		temp &= ~DUAL_LINK_MODE_MASK;
+
+		if (intel_dsi->ports == (BIT(PORT_A) | BIT(PORT_C))) {
+			temp |= (intel_dsi->dual_link - 1)
+						<< DUAL_LINK_MODE_SHIFT;
+			if (IS_BROXTON(dev_priv))
+				temp |= LANE_CONFIGURATION_DUAL_LINK_A;
+			else
+				temp |= crtc->pipe ?
+					LANE_CONFIGURATION_DUAL_LINK_B :
+					LANE_CONFIGURATION_DUAL_LINK_A;
+		}
+		/* assert ip_tg_enable signal */
+		I915_WRITE(port_ctrl, temp | DPI_ENABLE);
+		POSTING_READ(port_ctrl);
+	}
+}
+
+static void intel_dsi_port_disable(struct intel_encoder *encoder)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		i915_reg_t port_ctrl = IS_GEN9_LP(dev_priv) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
+		u32 temp;
+
+		/* de-assert ip_tg_enable signal */
+		temp = I915_READ(port_ctrl);
+		I915_WRITE(port_ctrl, temp & ~DPI_ENABLE);
+		POSTING_READ(port_ctrl);
+	}
+}
+
+static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
+			      const struct intel_crtc_state *pipe_config);
+static void intel_dsi_unprepare(struct intel_encoder *encoder);
+
+static void intel_dsi_msleep(struct intel_dsi *intel_dsi, int msec)
+{
+	struct drm_i915_private *dev_priv = to_i915(intel_dsi->base.base.dev);
+
+	/* For v3 VBTs in vid-mode the delays are part of the VBT sequences */
+	if (is_vid_mode(intel_dsi) && dev_priv->vbt.dsi.seq_version >= 3)
+		return;
+
+	msleep(msec);
+}
+
+/*
+ * Panel enable/disable sequences from the VBT spec.
+ *
+ * Note the spec has AssertReset / DeassertReset swapped from their
+ * usual naming. We use the normal names to avoid confusion (so below
+ * they are swapped compared to the spec).
+ *
+ * Steps starting with MIPI refer to VBT sequences, note that for v2
+ * VBTs several steps which have a VBT in v2 are expected to be handled
+ * directly by the driver, by directly driving gpios for example.
+ *
+ * v2 video mode seq         v3 video mode seq         command mode seq
+ * - power on                - MIPIPanelPowerOn        - power on
+ * - wait t1+t2                                        - wait t1+t2
+ * - MIPIDeassertResetPin    - MIPIDeassertResetPin    - MIPIDeassertResetPin
+ * - io lines to lp-11       - io lines to lp-11       - io lines to lp-11
+ * - MIPISendInitialDcsCmds  - MIPISendInitialDcsCmds  - MIPISendInitialDcsCmds
+ *                                                     - MIPITearOn
+ *                                                     - MIPIDisplayOn
+ * - turn on DPI             - turn on DPI             - set pipe to dsr mode
+ * - MIPIDisplayOn           - MIPIDisplayOn
+ * - wait t5                                           - wait t5
+ * - backlight on            - MIPIBacklightOn         - backlight on
+ * ...                       ...                       ... issue mem cmds ...
+ * - backlight off           - MIPIBacklightOff        - backlight off
+ * - wait t6                                           - wait t6
+ * - MIPIDisplayOff
+ * - turn off DPI            - turn off DPI            - disable pipe dsr mode
+ *                                                     - MIPITearOff
+ *                           - MIPIDisplayOff          - MIPIDisplayOff
+ * - io lines to lp-00       - io lines to lp-00       - io lines to lp-00
+ * - MIPIAssertResetPin      - MIPIAssertResetPin      - MIPIAssertResetPin
+ * - wait t3                                           - wait t3
+ * - power off               - MIPIPanelPowerOff       - power off
+ * - wait t4                                           - wait t4
+ */
+
+static void intel_dsi_pre_enable(struct intel_encoder *encoder,
+				 const struct intel_crtc_state *pipe_config,
+				 const struct drm_connector_state *conn_state)
+{
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct drm_crtc *crtc = pipe_config->base.crtc;
+	struct drm_i915_private *dev_priv = to_i915(crtc->dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
+	int pipe = intel_crtc->pipe;
+	enum port port;
+	u32 val;
+	bool glk_cold_boot = false;
+
+	DRM_DEBUG_KMS("\n");
+
+	intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, true);
+
+	/*
+	 * The BIOS may leave the PLL in a wonky state where it doesn't
+	 * lock. It needs to be fully powered down to fix it.
+	 */
+	intel_disable_dsi_pll(encoder);
+	intel_enable_dsi_pll(encoder, pipe_config);
+
+	if (IS_BROXTON(dev_priv)) {
+		/* Add MIPI IO reset programming for modeset */
+		val = I915_READ(BXT_P_CR_GT_DISP_PWRON);
+		I915_WRITE(BXT_P_CR_GT_DISP_PWRON,
+					val | MIPIO_RST_CTRL);
+
+		/* Power up DSI regulator */
+		I915_WRITE(BXT_P_DSI_REGULATOR_CFG, STAP_SELECT);
+		I915_WRITE(BXT_P_DSI_REGULATOR_TX_CTRL, 0);
+	}
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		u32 val;
+
+		/* Disable DPOunit clock gating, can stall pipe */
+		val = I915_READ(DSPCLK_GATE_D);
+		val |= DPOUNIT_CLOCK_GATE_DISABLE;
+		I915_WRITE(DSPCLK_GATE_D, val);
+	}
+
+	if (!IS_GEMINILAKE(dev_priv))
+		intel_dsi_prepare(encoder, pipe_config);
+
+	/* Power on, try both CRC pmic gpio and VBT */
+	if (intel_dsi->gpio_panel)
+		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 1);
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_ON);
+	intel_dsi_msleep(intel_dsi, intel_dsi->panel_on_delay);
+
+	/* Deassert reset */
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DEASSERT_RESET);
+
+	if (IS_GEMINILAKE(dev_priv)) {
+		glk_cold_boot = glk_dsi_enable_io(encoder);
+
+		/* Prepare port in cold boot(s3/s4) scenario */
+		if (glk_cold_boot)
+			intel_dsi_prepare(encoder, pipe_config);
+	}
+
+	/* Put device in ready state (LP-11) */
+	intel_dsi_device_ready(encoder);
+
+	/* Prepare port in normal boot scenario */
+	if (IS_GEMINILAKE(dev_priv) && !glk_cold_boot)
+		intel_dsi_prepare(encoder, pipe_config);
+
+	/* Send initialization commands in LP mode */
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_INIT_OTP);
+
+	/* Enable port in pre-enable phase itself because as per hw team
+	 * recommendation, port should be enabled befor plane & pipe */
+	if (is_cmd_mode(intel_dsi)) {
+		for_each_dsi_port(port, intel_dsi->ports)
+			I915_WRITE(MIPI_MAX_RETURN_PKT_SIZE(port), 8 * 4);
+		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_TEAR_ON);
+		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
+	} else {
+		msleep(20); /* XXX */
+		for_each_dsi_port(port, intel_dsi->ports)
+			dpi_send_cmd(intel_dsi, TURN_ON, false, port);
+		intel_dsi_msleep(intel_dsi, 100);
+
+		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_ON);
+
+		intel_dsi_port_enable(encoder, pipe_config);
+	}
+
+	intel_panel_enable_backlight(pipe_config, conn_state);
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_ON);
+}
+
+/*
+ * DSI port enable has to be done before pipe and plane enable, so we do it in
+ * the pre_enable hook.
+ */
+static void intel_dsi_enable_nop(struct intel_encoder *encoder,
+				 const struct intel_crtc_state *pipe_config,
+				 const struct drm_connector_state *conn_state)
+{
+	DRM_DEBUG_KMS("\n");
+}
+
+/*
+ * DSI port disable has to be done after pipe and plane disable, so we do it in
+ * the post_disable hook.
+ */
+static void intel_dsi_disable(struct intel_encoder *encoder,
+			      const struct intel_crtc_state *old_crtc_state,
+			      const struct drm_connector_state *old_conn_state)
+{
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+
+	DRM_DEBUG_KMS("\n");
+
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_BACKLIGHT_OFF);
+	intel_panel_disable_backlight(old_conn_state);
+
+	/*
+	 * According to the spec we should send SHUTDOWN before
+	 * MIPI_SEQ_DISPLAY_OFF only for v3+ VBTs, but field testing
+	 * has shown that the v3 sequence works for v2 VBTs too
+	 */
+	if (is_vid_mode(intel_dsi)) {
+		/* Send Shutdown command to the panel in LP mode */
+		for_each_dsi_port(port, intel_dsi->ports)
+			dpi_send_cmd(intel_dsi, SHUTDOWN, false, port);
+		msleep(10);
+	}
+}
+
+static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv) ||
+	    IS_BROXTON(dev_priv))
+		vlv_dsi_clear_device_ready(encoder);
+	else if (IS_GEMINILAKE(dev_priv))
+		glk_dsi_clear_device_ready(encoder);
+}
+
+static void intel_dsi_post_disable(struct intel_encoder *encoder,
+				   const struct intel_crtc_state *pipe_config,
+				   const struct drm_connector_state *conn_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 val;
+
+	DRM_DEBUG_KMS("\n");
+
+	if (is_vid_mode(intel_dsi)) {
+		for_each_dsi_port(port, intel_dsi->ports)
+			wait_for_dsi_fifo_empty(intel_dsi, port);
+
+		intel_dsi_port_disable(encoder);
+		usleep_range(2000, 5000);
+	}
+
+	intel_dsi_unprepare(encoder);
+
+	/*
+	 * if disable packets are sent before sending shutdown packet then in
+	 * some next enable sequence send turn on packet error is observed
+	 */
+	if (is_cmd_mode(intel_dsi))
+		intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_TEAR_OFF);
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_DISPLAY_OFF);
+
+	/* Transition to LP-00 */
+	intel_dsi_clear_device_ready(encoder);
+
+	if (IS_BROXTON(dev_priv)) {
+		/* Power down DSI regulator to save power */
+		I915_WRITE(BXT_P_DSI_REGULATOR_CFG, STAP_SELECT);
+		I915_WRITE(BXT_P_DSI_REGULATOR_TX_CTRL, HS_IO_CTRL_SELECT);
+
+		/* Add MIPI IO reset programming for modeset */
+		val = I915_READ(BXT_P_CR_GT_DISP_PWRON);
+		I915_WRITE(BXT_P_CR_GT_DISP_PWRON,
+				val & ~MIPIO_RST_CTRL);
+	}
+
+	intel_disable_dsi_pll(encoder);
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		u32 val;
+
+		val = I915_READ(DSPCLK_GATE_D);
+		val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
+		I915_WRITE(DSPCLK_GATE_D, val);
+	}
+
+	/* Assert reset */
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_ASSERT_RESET);
+
+	/* Power off, try both CRC pmic gpio and VBT */
+	intel_dsi_msleep(intel_dsi, intel_dsi->panel_off_delay);
+	intel_dsi_vbt_exec_sequence(intel_dsi, MIPI_SEQ_POWER_OFF);
+	if (intel_dsi->gpio_panel)
+		gpiod_set_value_cansleep(intel_dsi->gpio_panel, 0);
+
+	/*
+	 * FIXME As we do with eDP, just make a note of the time here
+	 * and perform the wait before the next panel power on.
+	 */
+	intel_dsi_msleep(intel_dsi, intel_dsi->panel_pwr_cycle_delay);
+}
+
+static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
+				   enum pipe *pipe)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	bool active = false;
+
+	DRM_DEBUG_KMS("\n");
+
+	if (!intel_display_power_get_if_enabled(dev_priv,
+						encoder->power_domain))
+		return false;
+
+	/*
+	 * On Broxton the PLL needs to be enabled with a valid divider
+	 * configuration, otherwise accessing DSI registers will hang the
+	 * machine. See BSpec North Display Engine registers/MIPI[BXT].
+	 */
+	if (IS_GEN9_LP(dev_priv) && !intel_dsi_pll_is_enabled(dev_priv))
+		goto out_put_power;
+
+	/* XXX: this only works for one DSI output */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		i915_reg_t ctrl_reg = IS_GEN9_LP(dev_priv) ?
+			BXT_MIPI_PORT_CTRL(port) : MIPI_PORT_CTRL(port);
+		bool enabled = I915_READ(ctrl_reg) & DPI_ENABLE;
+
+		/*
+		 * Due to some hardware limitations on VLV/CHV, the DPI enable
+		 * bit in port C control register does not get set. As a
+		 * workaround, check pipe B conf instead.
+		 */
+		if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+		    port == PORT_C)
+			enabled = I915_READ(PIPECONF(PIPE_B)) & PIPECONF_ENABLE;
+
+		/* Try command mode if video mode not enabled */
+		if (!enabled) {
+			u32 tmp = I915_READ(MIPI_DSI_FUNC_PRG(port));
+			enabled = tmp & CMD_MODE_DATA_WIDTH_MASK;
+		}
+
+		if (!enabled)
+			continue;
+
+		if (!(I915_READ(MIPI_DEVICE_READY(port)) & DEVICE_READY))
+			continue;
+
+		if (IS_GEN9_LP(dev_priv)) {
+			u32 tmp = I915_READ(MIPI_CTRL(port));
+			tmp &= BXT_PIPE_SELECT_MASK;
+			tmp >>= BXT_PIPE_SELECT_SHIFT;
+
+			if (WARN_ON(tmp > PIPE_C))
+				continue;
+
+			*pipe = tmp;
+		} else {
+			*pipe = port == PORT_A ? PIPE_A : PIPE_B;
+		}
+
+		active = true;
+		break;
+	}
+
+out_put_power:
+	intel_display_power_put(dev_priv, encoder->power_domain);
+
+	return active;
+}
+
+static void bxt_dsi_get_pipe_config(struct intel_encoder *encoder,
+				    struct intel_crtc_state *pipe_config)
+{
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct drm_display_mode *adjusted_mode =
+					&pipe_config->base.adjusted_mode;
+	struct drm_display_mode *adjusted_mode_sw;
+	struct intel_crtc *crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	unsigned int lane_count = intel_dsi->lane_count;
+	unsigned int bpp, fmt;
+	enum port port;
+	u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp;
+	u16 hfp_sw, hsync_sw, hbp_sw;
+	u16 crtc_htotal_sw, crtc_hsync_start_sw, crtc_hsync_end_sw,
+				crtc_hblank_start_sw, crtc_hblank_end_sw;
+
+	/* FIXME: hw readout should not depend on SW state */
+	adjusted_mode_sw = &crtc->config->base.adjusted_mode;
+
+	/*
+	 * Atleast one port is active as encoder->get_config called only if
+	 * encoder->get_hw_state() returns true.
+	 */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (I915_READ(BXT_MIPI_PORT_CTRL(port)) & DPI_ENABLE)
+			break;
+	}
+
+	fmt = I915_READ(MIPI_DSI_FUNC_PRG(port)) & VID_MODE_FORMAT_MASK;
+	pipe_config->pipe_bpp =
+			mipi_dsi_pixel_format_to_bpp(
+				pixel_format_from_register_bits(fmt));
+	bpp = pipe_config->pipe_bpp;
+
+	/* Enable Frame time stamo based scanline reporting */
+	adjusted_mode->private_flags |=
+			I915_MODE_FLAG_GET_SCANLINE_FROM_TIMESTAMP;
+
+	/* In terms of pixels */
+	adjusted_mode->crtc_hdisplay =
+				I915_READ(BXT_MIPI_TRANS_HACTIVE(port));
+	adjusted_mode->crtc_vdisplay =
+				I915_READ(BXT_MIPI_TRANS_VACTIVE(port));
+	adjusted_mode->crtc_vtotal =
+				I915_READ(BXT_MIPI_TRANS_VTOTAL(port));
+
+	hactive = adjusted_mode->crtc_hdisplay;
+	hfp = I915_READ(MIPI_HFP_COUNT(port));
+
+	/*
+	 * Meaningful for video mode non-burst sync pulse mode only,
+	 * can be zero for non-burst sync events and burst modes
+	 */
+	hsync = I915_READ(MIPI_HSYNC_PADDING_COUNT(port));
+	hbp = I915_READ(MIPI_HBP_COUNT(port));
+
+	/* harizontal values are in terms of high speed byte clock */
+	hfp = pixels_from_txbyteclkhs(hfp, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+	hsync = pixels_from_txbyteclkhs(hsync, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+	hbp = pixels_from_txbyteclkhs(hbp, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+
+	if (intel_dsi->dual_link) {
+		hfp *= 2;
+		hsync *= 2;
+		hbp *= 2;
+	}
+
+	/* vertical values are in terms of lines */
+	vfp = I915_READ(MIPI_VFP_COUNT(port));
+	vsync = I915_READ(MIPI_VSYNC_PADDING_COUNT(port));
+	vbp = I915_READ(MIPI_VBP_COUNT(port));
+
+	adjusted_mode->crtc_htotal = hactive + hfp + hsync + hbp;
+	adjusted_mode->crtc_hsync_start = hfp + adjusted_mode->crtc_hdisplay;
+	adjusted_mode->crtc_hsync_end = hsync + adjusted_mode->crtc_hsync_start;
+	adjusted_mode->crtc_hblank_start = adjusted_mode->crtc_hdisplay;
+	adjusted_mode->crtc_hblank_end = adjusted_mode->crtc_htotal;
+
+	adjusted_mode->crtc_vsync_start = vfp + adjusted_mode->crtc_vdisplay;
+	adjusted_mode->crtc_vsync_end = vsync + adjusted_mode->crtc_vsync_start;
+	adjusted_mode->crtc_vblank_start = adjusted_mode->crtc_vdisplay;
+	adjusted_mode->crtc_vblank_end = adjusted_mode->crtc_vtotal;
+
+	/*
+	 * In BXT DSI there is no regs programmed with few horizontal timings
+	 * in Pixels but txbyteclkhs.. So retrieval process adds some
+	 * ROUND_UP ERRORS in the process of PIXELS<==>txbyteclkhs.
+	 * Actually here for the given adjusted_mode, we are calculating the
+	 * value programmed to the port and then back to the horizontal timing
+	 * param in pixels. This is the expected value, including roundup errors
+	 * And if that is same as retrieved value from port, then
+	 * (HW state) adjusted_mode's horizontal timings are corrected to
+	 * match with SW state to nullify the errors.
+	 */
+	/* Calculating the value programmed to the Port register */
+	hfp_sw = adjusted_mode_sw->crtc_hsync_start -
+					adjusted_mode_sw->crtc_hdisplay;
+	hsync_sw = adjusted_mode_sw->crtc_hsync_end -
+					adjusted_mode_sw->crtc_hsync_start;
+	hbp_sw = adjusted_mode_sw->crtc_htotal -
+					adjusted_mode_sw->crtc_hsync_end;
+
+	if (intel_dsi->dual_link) {
+		hfp_sw /= 2;
+		hsync_sw /= 2;
+		hbp_sw /= 2;
+	}
+
+	hfp_sw = txbyteclkhs(hfp_sw, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+	hsync_sw = txbyteclkhs(hsync_sw, bpp, lane_count,
+			    intel_dsi->burst_mode_ratio);
+	hbp_sw = txbyteclkhs(hbp_sw, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+
+	/* Reverse calculating the adjusted mode parameters from port reg vals*/
+	hfp_sw = pixels_from_txbyteclkhs(hfp_sw, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+	hsync_sw = pixels_from_txbyteclkhs(hsync_sw, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+	hbp_sw = pixels_from_txbyteclkhs(hbp_sw, bpp, lane_count,
+						intel_dsi->burst_mode_ratio);
+
+	if (intel_dsi->dual_link) {
+		hfp_sw *= 2;
+		hsync_sw *= 2;
+		hbp_sw *= 2;
+	}
+
+	crtc_htotal_sw = adjusted_mode_sw->crtc_hdisplay + hfp_sw +
+							hsync_sw + hbp_sw;
+	crtc_hsync_start_sw = hfp_sw + adjusted_mode_sw->crtc_hdisplay;
+	crtc_hsync_end_sw = hsync_sw + crtc_hsync_start_sw;
+	crtc_hblank_start_sw = adjusted_mode_sw->crtc_hdisplay;
+	crtc_hblank_end_sw = crtc_htotal_sw;
+
+	if (adjusted_mode->crtc_htotal == crtc_htotal_sw)
+		adjusted_mode->crtc_htotal = adjusted_mode_sw->crtc_htotal;
+
+	if (adjusted_mode->crtc_hsync_start == crtc_hsync_start_sw)
+		adjusted_mode->crtc_hsync_start =
+					adjusted_mode_sw->crtc_hsync_start;
+
+	if (adjusted_mode->crtc_hsync_end == crtc_hsync_end_sw)
+		adjusted_mode->crtc_hsync_end =
+					adjusted_mode_sw->crtc_hsync_end;
+
+	if (adjusted_mode->crtc_hblank_start == crtc_hblank_start_sw)
+		adjusted_mode->crtc_hblank_start =
+					adjusted_mode_sw->crtc_hblank_start;
+
+	if (adjusted_mode->crtc_hblank_end == crtc_hblank_end_sw)
+		adjusted_mode->crtc_hblank_end =
+					adjusted_mode_sw->crtc_hblank_end;
+}
+
+static void intel_dsi_get_config(struct intel_encoder *encoder,
+				 struct intel_crtc_state *pipe_config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	u32 pclk;
+	DRM_DEBUG_KMS("\n");
+
+	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
+
+	if (IS_GEN9_LP(dev_priv))
+		bxt_dsi_get_pipe_config(encoder, pipe_config);
+
+	pclk = intel_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
+				  pipe_config);
+	if (!pclk)
+		return;
+
+	pipe_config->base.adjusted_mode.crtc_clock = pclk;
+	pipe_config->port_clock = pclk;
+}
+
+static enum drm_mode_status
+intel_dsi_mode_valid(struct drm_connector *connector,
+		     struct drm_display_mode *mode)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	const struct drm_display_mode *fixed_mode = intel_connector->panel.fixed_mode;
+	int max_dotclk = to_i915(connector->dev)->max_dotclk_freq;
+
+	DRM_DEBUG_KMS("\n");
+
+	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
+		return MODE_NO_DBLESCAN;
+
+	if (fixed_mode) {
+		if (mode->hdisplay > fixed_mode->hdisplay)
+			return MODE_PANEL;
+		if (mode->vdisplay > fixed_mode->vdisplay)
+			return MODE_PANEL;
+		if (fixed_mode->clock > max_dotclk)
+			return MODE_CLOCK_HIGH;
+	}
+
+	return MODE_OK;
+}
+
+/* return txclkesc cycles in terms of divider and duration in us */
+static u16 txclkesc(u32 divider, unsigned int us)
+{
+	switch (divider) {
+	case ESCAPE_CLOCK_DIVIDER_1:
+	default:
+		return 20 * us;
+	case ESCAPE_CLOCK_DIVIDER_2:
+		return 10 * us;
+	case ESCAPE_CLOCK_DIVIDER_4:
+		return 5 * us;
+	}
+}
+
+static void set_dsi_timings(struct drm_encoder *encoder,
+			    const struct drm_display_mode *adjusted_mode)
+{
+	struct drm_device *dev = encoder->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	enum port port;
+	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+	unsigned int lane_count = intel_dsi->lane_count;
+
+	u16 hactive, hfp, hsync, hbp, vfp, vsync, vbp;
+
+	hactive = adjusted_mode->crtc_hdisplay;
+	hfp = adjusted_mode->crtc_hsync_start - adjusted_mode->crtc_hdisplay;
+	hsync = adjusted_mode->crtc_hsync_end - adjusted_mode->crtc_hsync_start;
+	hbp = adjusted_mode->crtc_htotal - adjusted_mode->crtc_hsync_end;
+
+	if (intel_dsi->dual_link) {
+		hactive /= 2;
+		if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK)
+			hactive += intel_dsi->pixel_overlap;
+		hfp /= 2;
+		hsync /= 2;
+		hbp /= 2;
+	}
+
+	vfp = adjusted_mode->crtc_vsync_start - adjusted_mode->crtc_vdisplay;
+	vsync = adjusted_mode->crtc_vsync_end - adjusted_mode->crtc_vsync_start;
+	vbp = adjusted_mode->crtc_vtotal - adjusted_mode->crtc_vsync_end;
+
+	/* horizontal values are in terms of high speed byte clock */
+	hactive = txbyteclkhs(hactive, bpp, lane_count,
+			      intel_dsi->burst_mode_ratio);
+	hfp = txbyteclkhs(hfp, bpp, lane_count, intel_dsi->burst_mode_ratio);
+	hsync = txbyteclkhs(hsync, bpp, lane_count,
+			    intel_dsi->burst_mode_ratio);
+	hbp = txbyteclkhs(hbp, bpp, lane_count, intel_dsi->burst_mode_ratio);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (IS_GEN9_LP(dev_priv)) {
+			/*
+			 * Program hdisplay and vdisplay on MIPI transcoder.
+			 * This is different from calculated hactive and
+			 * vactive, as they are calculated per channel basis,
+			 * whereas these values should be based on resolution.
+			 */
+			I915_WRITE(BXT_MIPI_TRANS_HACTIVE(port),
+				   adjusted_mode->crtc_hdisplay);
+			I915_WRITE(BXT_MIPI_TRANS_VACTIVE(port),
+				   adjusted_mode->crtc_vdisplay);
+			I915_WRITE(BXT_MIPI_TRANS_VTOTAL(port),
+				   adjusted_mode->crtc_vtotal);
+		}
+
+		I915_WRITE(MIPI_HACTIVE_AREA_COUNT(port), hactive);
+		I915_WRITE(MIPI_HFP_COUNT(port), hfp);
+
+		/* meaningful for video mode non-burst sync pulse mode only,
+		 * can be zero for non-burst sync events and burst modes */
+		I915_WRITE(MIPI_HSYNC_PADDING_COUNT(port), hsync);
+		I915_WRITE(MIPI_HBP_COUNT(port), hbp);
+
+		/* vertical values are in terms of lines */
+		I915_WRITE(MIPI_VFP_COUNT(port), vfp);
+		I915_WRITE(MIPI_VSYNC_PADDING_COUNT(port), vsync);
+		I915_WRITE(MIPI_VBP_COUNT(port), vbp);
+	}
+}
+
+static u32 pixel_format_to_reg(enum mipi_dsi_pixel_format fmt)
+{
+	switch (fmt) {
+	case MIPI_DSI_FMT_RGB888:
+		return VID_MODE_FORMAT_RGB888;
+	case MIPI_DSI_FMT_RGB666:
+		return VID_MODE_FORMAT_RGB666;
+	case MIPI_DSI_FMT_RGB666_PACKED:
+		return VID_MODE_FORMAT_RGB666_PACKED;
+	case MIPI_DSI_FMT_RGB565:
+		return VID_MODE_FORMAT_RGB565;
+	default:
+		MISSING_CASE(fmt);
+		return VID_MODE_FORMAT_RGB666;
+	}
+}
+
+static void intel_dsi_prepare(struct intel_encoder *intel_encoder,
+			      const struct intel_crtc_state *pipe_config)
+{
+	struct drm_encoder *encoder = &intel_encoder->base;
+	struct drm_device *dev = encoder->dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	struct intel_crtc *intel_crtc = to_intel_crtc(pipe_config->base.crtc);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+	const struct drm_display_mode *adjusted_mode = &pipe_config->base.adjusted_mode;
+	enum port port;
+	unsigned int bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+	u32 val, tmp;
+	u16 mode_hdisplay;
+
+	DRM_DEBUG_KMS("pipe %c\n", pipe_name(intel_crtc->pipe));
+
+	mode_hdisplay = adjusted_mode->crtc_hdisplay;
+
+	if (intel_dsi->dual_link) {
+		mode_hdisplay /= 2;
+		if (intel_dsi->dual_link == DSI_DUAL_LINK_FRONT_BACK)
+			mode_hdisplay += intel_dsi->pixel_overlap;
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+			/*
+			 * escape clock divider, 20MHz, shared for A and C.
+			 * device ready must be off when doing this! txclkesc?
+			 */
+			tmp = I915_READ(MIPI_CTRL(PORT_A));
+			tmp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
+			I915_WRITE(MIPI_CTRL(PORT_A), tmp |
+					ESCAPE_CLOCK_DIVIDER_1);
+
+			/* read request priority is per pipe */
+			tmp = I915_READ(MIPI_CTRL(port));
+			tmp &= ~READ_REQUEST_PRIORITY_MASK;
+			I915_WRITE(MIPI_CTRL(port), tmp |
+					READ_REQUEST_PRIORITY_HIGH);
+		} else if (IS_GEN9_LP(dev_priv)) {
+			enum pipe pipe = intel_crtc->pipe;
+
+			tmp = I915_READ(MIPI_CTRL(port));
+			tmp &= ~BXT_PIPE_SELECT_MASK;
+
+			tmp |= BXT_PIPE_SELECT(pipe);
+			I915_WRITE(MIPI_CTRL(port), tmp);
+		}
+
+		/* XXX: why here, why like this? handling in irq handler?! */
+		I915_WRITE(MIPI_INTR_STAT(port), 0xffffffff);
+		I915_WRITE(MIPI_INTR_EN(port), 0xffffffff);
+
+		I915_WRITE(MIPI_DPHY_PARAM(port), intel_dsi->dphy_reg);
+
+		I915_WRITE(MIPI_DPI_RESOLUTION(port),
+			adjusted_mode->crtc_vdisplay << VERTICAL_ADDRESS_SHIFT |
+			mode_hdisplay << HORIZONTAL_ADDRESS_SHIFT);
+	}
+
+	set_dsi_timings(encoder, adjusted_mode);
+
+	val = intel_dsi->lane_count << DATA_LANES_PRG_REG_SHIFT;
+	if (is_cmd_mode(intel_dsi)) {
+		val |= intel_dsi->channel << CMD_MODE_CHANNEL_NUMBER_SHIFT;
+		val |= CMD_MODE_DATA_WIDTH_8_BIT; /* XXX */
+	} else {
+		val |= intel_dsi->channel << VID_MODE_CHANNEL_NUMBER_SHIFT;
+		val |= pixel_format_to_reg(intel_dsi->pixel_format);
+	}
+
+	tmp = 0;
+	if (intel_dsi->eotp_pkt == 0)
+		tmp |= EOT_DISABLE;
+	if (intel_dsi->clock_stop)
+		tmp |= CLOCKSTOP;
+
+	if (IS_GEN9_LP(dev_priv)) {
+		tmp |= BXT_DPHY_DEFEATURE_EN;
+		if (!is_cmd_mode(intel_dsi))
+			tmp |= BXT_DEFEATURE_DPI_FIFO_CTR;
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+
+		/* timeouts for recovery. one frame IIUC. if counter expires,
+		 * EOT and stop state. */
+
+		/*
+		 * In burst mode, value greater than one DPI line Time in byte
+		 * clock (txbyteclkhs) To timeout this timer 1+ of the above
+		 * said value is recommended.
+		 *
+		 * In non-burst mode, Value greater than one DPI frame time in
+		 * byte clock(txbyteclkhs) To timeout this timer 1+ of the above
+		 * said value is recommended.
+		 *
+		 * In DBI only mode, value greater than one DBI frame time in
+		 * byte clock(txbyteclkhs) To timeout this timer 1+ of the above
+		 * said value is recommended.
+		 */
+
+		if (is_vid_mode(intel_dsi) &&
+			intel_dsi->video_mode_format == VIDEO_MODE_BURST) {
+			I915_WRITE(MIPI_HS_TX_TIMEOUT(port),
+				txbyteclkhs(adjusted_mode->crtc_htotal, bpp,
+					    intel_dsi->lane_count,
+					    intel_dsi->burst_mode_ratio) + 1);
+		} else {
+			I915_WRITE(MIPI_HS_TX_TIMEOUT(port),
+				txbyteclkhs(adjusted_mode->crtc_vtotal *
+					    adjusted_mode->crtc_htotal,
+					    bpp, intel_dsi->lane_count,
+					    intel_dsi->burst_mode_ratio) + 1);
+		}
+		I915_WRITE(MIPI_LP_RX_TIMEOUT(port), intel_dsi->lp_rx_timeout);
+		I915_WRITE(MIPI_TURN_AROUND_TIMEOUT(port),
+						intel_dsi->turn_arnd_val);
+		I915_WRITE(MIPI_DEVICE_RESET_TIMER(port),
+						intel_dsi->rst_timer_val);
+
+		/* dphy stuff */
+
+		/* in terms of low power clock */
+		I915_WRITE(MIPI_INIT_COUNT(port),
+				txclkesc(intel_dsi->escape_clk_div, 100));
+
+		if (IS_GEN9_LP(dev_priv) && (!intel_dsi->dual_link)) {
+			/*
+			 * BXT spec says write MIPI_INIT_COUNT for
+			 * both the ports, even if only one is
+			 * getting used. So write the other port
+			 * if not in dual link mode.
+			 */
+			I915_WRITE(MIPI_INIT_COUNT(port ==
+						PORT_A ? PORT_C : PORT_A),
+					intel_dsi->init_count);
+		}
+
+		/* recovery disables */
+		I915_WRITE(MIPI_EOT_DISABLE(port), tmp);
+
+		/* in terms of low power clock */
+		I915_WRITE(MIPI_INIT_COUNT(port), intel_dsi->init_count);
+
+		/* in terms of txbyteclkhs. actual high to low switch +
+		 * MIPI_STOP_STATE_STALL * MIPI_LP_BYTECLK.
+		 *
+		 * XXX: write MIPI_STOP_STATE_STALL?
+		 */
+		I915_WRITE(MIPI_HIGH_LOW_SWITCH_COUNT(port),
+						intel_dsi->hs_to_lp_count);
+
+		/* XXX: low power clock equivalence in terms of byte clock.
+		 * the number of byte clocks occupied in one low power clock.
+		 * based on txbyteclkhs and txclkesc.
+		 * txclkesc time / txbyteclk time * (105 + MIPI_STOP_STATE_STALL
+		 * ) / 105.???
+		 */
+		I915_WRITE(MIPI_LP_BYTECLK(port), intel_dsi->lp_byte_clk);
+
+		if (IS_GEMINILAKE(dev_priv)) {
+			I915_WRITE(MIPI_TLPX_TIME_COUNT(port),
+					intel_dsi->lp_byte_clk);
+			/* Shadow of DPHY reg */
+			I915_WRITE(MIPI_CLK_LANE_TIMING(port),
+					intel_dsi->dphy_reg);
+		}
+
+		/* the bw essential for transmitting 16 long packets containing
+		 * 252 bytes meant for dcs write memory command is programmed in
+		 * this register in terms of byte clocks. based on dsi transfer
+		 * rate and the number of lanes configured the time taken to
+		 * transmit 16 long packets in a dsi stream varies. */
+		I915_WRITE(MIPI_DBI_BW_CTRL(port), intel_dsi->bw_timer);
+
+		I915_WRITE(MIPI_CLK_LANE_SWITCH_TIME_CNT(port),
+		intel_dsi->clk_lp_to_hs_count << LP_HS_SSW_CNT_SHIFT |
+		intel_dsi->clk_hs_to_lp_count << HS_LP_PWR_SW_CNT_SHIFT);
+
+		if (is_vid_mode(intel_dsi))
+			/* Some panels might have resolution which is not a
+			 * multiple of 64 like 1366 x 768. Enable RANDOM
+			 * resolution support for such panels by default */
+			I915_WRITE(MIPI_VIDEO_MODE_FORMAT(port),
+				intel_dsi->video_frmt_cfg_bits |
+				intel_dsi->video_mode_format |
+				IP_TG_CONFIG |
+				RANDOM_DPI_DISPLAY_RESOLUTION);
+	}
+}
+
+static void intel_dsi_unprepare(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 val;
+
+	if (!IS_GEMINILAKE(dev_priv)) {
+		for_each_dsi_port(port, intel_dsi->ports) {
+			/* Panel commands can be sent when clock is in LP11 */
+			I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
+
+			intel_dsi_reset_clocks(encoder, port);
+			I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
+
+			val = I915_READ(MIPI_DSI_FUNC_PRG(port));
+			val &= ~VID_MODE_FORMAT_MASK;
+			I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+
+			I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
+		}
+	}
+}
+
+static int intel_dsi_get_modes(struct drm_connector *connector)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct drm_display_mode *mode;
+
+	DRM_DEBUG_KMS("\n");
+
+	if (!intel_connector->panel.fixed_mode) {
+		DRM_DEBUG_KMS("no fixed mode\n");
+		return 0;
+	}
+
+	mode = drm_mode_duplicate(connector->dev,
+				  intel_connector->panel.fixed_mode);
+	if (!mode) {
+		DRM_DEBUG_KMS("drm_mode_duplicate failed\n");
+		return 0;
+	}
+
+	drm_mode_probed_add(connector, mode);
+	return 1;
+}
+
+static void intel_dsi_connector_destroy(struct drm_connector *connector)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+
+	DRM_DEBUG_KMS("\n");
+	intel_panel_fini(&intel_connector->panel);
+	drm_connector_cleanup(connector);
+	kfree(connector);
+}
+
+static void intel_dsi_encoder_destroy(struct drm_encoder *encoder)
+{
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(encoder);
+
+	/* dispose of the gpios */
+	if (intel_dsi->gpio_panel)
+		gpiod_put(intel_dsi->gpio_panel);
+
+	intel_encoder_destroy(encoder);
+}
+
+static const struct drm_encoder_funcs intel_dsi_funcs = {
+	.destroy = intel_dsi_encoder_destroy,
+};
+
+static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = {
+	.get_modes = intel_dsi_get_modes,
+	.mode_valid = intel_dsi_mode_valid,
+	.atomic_check = intel_digital_connector_atomic_check,
+};
+
+static const struct drm_connector_funcs intel_dsi_connector_funcs = {
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
+	.destroy = intel_dsi_connector_destroy,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.atomic_get_property = intel_digital_connector_atomic_get_property,
+	.atomic_set_property = intel_digital_connector_atomic_set_property,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
+};
+
+static int intel_dsi_get_panel_orientation(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+	int orientation = DRM_MODE_PANEL_ORIENTATION_NORMAL;
+	enum i9xx_plane_id i9xx_plane;
+	u32 val;
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		if (connector->encoder->crtc_mask == BIT(PIPE_B))
+			i9xx_plane = PLANE_B;
+		else
+			i9xx_plane = PLANE_A;
+
+		val = I915_READ(DSPCNTR(i9xx_plane));
+		if (val & DISPPLANE_ROTATE_180)
+			orientation = DRM_MODE_PANEL_ORIENTATION_BOTTOM_UP;
+	}
+
+	return orientation;
+}
+
+static void intel_dsi_add_properties(struct intel_connector *connector)
+{
+	struct drm_i915_private *dev_priv = to_i915(connector->base.dev);
+
+	if (connector->panel.fixed_mode) {
+		u32 allowed_scalers;
+
+		allowed_scalers = BIT(DRM_MODE_SCALE_ASPECT) | BIT(DRM_MODE_SCALE_FULLSCREEN);
+		if (!HAS_GMCH_DISPLAY(dev_priv))
+			allowed_scalers |= BIT(DRM_MODE_SCALE_CENTER);
+
+		drm_connector_attach_scaling_mode_property(&connector->base,
+								allowed_scalers);
+
+		connector->base.state->scaling_mode = DRM_MODE_SCALE_ASPECT;
+
+		connector->base.display_info.panel_orientation =
+			intel_dsi_get_panel_orientation(connector);
+		drm_connector_init_panel_orientation_property(
+				&connector->base,
+				connector->panel.fixed_mode->hdisplay,
+				connector->panel.fixed_mode->vdisplay);
+	}
+}
+
+void intel_dsi_init(struct drm_i915_private *dev_priv)
+{
+	struct drm_device *dev = &dev_priv->drm;
+	struct intel_dsi *intel_dsi;
+	struct intel_encoder *intel_encoder;
+	struct drm_encoder *encoder;
+	struct intel_connector *intel_connector;
+	struct drm_connector *connector;
+	struct drm_display_mode *scan, *fixed_mode = NULL;
+	enum port port;
+
+	DRM_DEBUG_KMS("\n");
+
+	/* There is no detection method for MIPI so rely on VBT */
+	if (!intel_bios_is_dsi_present(dev_priv, &port))
+		return;
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
+	} else if (IS_GEN9_LP(dev_priv)) {
+		dev_priv->mipi_mmio_base = BXT_MIPI_BASE;
+	} else {
+		DRM_ERROR("Unsupported Mipi device to reg base");
+		return;
+	}
+
+	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
+	if (!intel_dsi)
+		return;
+
+	intel_connector = intel_connector_alloc();
+	if (!intel_connector) {
+		kfree(intel_dsi);
+		return;
+	}
+
+	intel_encoder = &intel_dsi->base;
+	encoder = &intel_encoder->base;
+	intel_dsi->attached_connector = intel_connector;
+
+	connector = &intel_connector->base;
+
+	drm_encoder_init(dev, encoder, &intel_dsi_funcs, DRM_MODE_ENCODER_DSI,
+			 "DSI %c", port_name(port));
+
+	intel_encoder->compute_config = intel_dsi_compute_config;
+	intel_encoder->pre_enable = intel_dsi_pre_enable;
+	intel_encoder->enable = intel_dsi_enable_nop;
+	intel_encoder->disable = intel_dsi_disable;
+	intel_encoder->post_disable = intel_dsi_post_disable;
+	intel_encoder->get_hw_state = intel_dsi_get_hw_state;
+	intel_encoder->get_config = intel_dsi_get_config;
+
+	intel_connector->get_hw_state = intel_connector_get_hw_state;
+
+	intel_encoder->port = port;
+
+	/*
+	 * On BYT/CHV, pipe A maps to MIPI DSI port A, pipe B maps to MIPI DSI
+	 * port C. BXT isn't limited like this.
+	 */
+	if (IS_GEN9_LP(dev_priv))
+		intel_encoder->crtc_mask = BIT(PIPE_A) | BIT(PIPE_B) | BIT(PIPE_C);
+	else if (port == PORT_A)
+		intel_encoder->crtc_mask = BIT(PIPE_A);
+	else
+		intel_encoder->crtc_mask = BIT(PIPE_B);
+
+	if (dev_priv->vbt.dsi.config->dual_link)
+		intel_dsi->ports = BIT(PORT_A) | BIT(PORT_C);
+	else
+		intel_dsi->ports = BIT(port);
+
+	intel_dsi->dcs_backlight_ports = dev_priv->vbt.dsi.bl_ports;
+	intel_dsi->dcs_cabc_ports = dev_priv->vbt.dsi.cabc_ports;
+
+	/* Create a DSI host (and a device) for each port. */
+	for_each_dsi_port(port, intel_dsi->ports) {
+		struct intel_dsi_host *host;
+
+		host = intel_dsi_host_init(intel_dsi, port);
+		if (!host)
+			goto err;
+
+		intel_dsi->dsi_hosts[port] = host;
+	}
+
+	if (!intel_dsi_vbt_init(intel_dsi, MIPI_DSI_GENERIC_PANEL_ID)) {
+		DRM_DEBUG_KMS("no device found\n");
+		goto err;
+	}
+
+	/*
+	 * In case of BYT with CRC PMIC, we need to use GPIO for
+	 * Panel control.
+	 */
+	if ((IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) &&
+	    (dev_priv->vbt.dsi.config->pwm_blc == PPS_BLC_PMIC)) {
+		intel_dsi->gpio_panel =
+			gpiod_get(dev->dev, "panel", GPIOD_OUT_HIGH);
+
+		if (IS_ERR(intel_dsi->gpio_panel)) {
+			DRM_ERROR("Failed to own gpio for panel control\n");
+			intel_dsi->gpio_panel = NULL;
+		}
+	}
+
+	intel_encoder->type = INTEL_OUTPUT_DSI;
+	intel_encoder->power_domain = POWER_DOMAIN_PORT_DSI;
+	intel_encoder->cloneable = 0;
+	drm_connector_init(dev, connector, &intel_dsi_connector_funcs,
+			   DRM_MODE_CONNECTOR_DSI);
+
+	drm_connector_helper_add(connector, &intel_dsi_connector_helper_funcs);
+
+	connector->display_info.subpixel_order = SubPixelHorizontalRGB; /*XXX*/
+	connector->interlace_allowed = false;
+	connector->doublescan_allowed = false;
+
+	intel_connector_attach_encoder(intel_connector, intel_encoder);
+
+	mutex_lock(&dev->mode_config.mutex);
+	intel_dsi_vbt_get_modes(intel_dsi);
+	list_for_each_entry(scan, &connector->probed_modes, head) {
+		if ((scan->type & DRM_MODE_TYPE_PREFERRED)) {
+			fixed_mode = drm_mode_duplicate(dev, scan);
+			break;
+		}
+	}
+	mutex_unlock(&dev->mode_config.mutex);
+
+	if (!fixed_mode) {
+		DRM_DEBUG_KMS("no fixed mode\n");
+		goto err;
+	}
+
+	connector->display_info.width_mm = fixed_mode->width_mm;
+	connector->display_info.height_mm = fixed_mode->height_mm;
+
+	intel_panel_init(&intel_connector->panel, fixed_mode, NULL);
+	intel_panel_setup_backlight(connector, INVALID_PIPE);
+
+	intel_dsi_add_properties(intel_connector);
+
+	return;
+
+err:
+	drm_encoder_cleanup(&intel_encoder->base);
+	kfree(intel_dsi);
+	kfree(intel_connector);
+}
diff --git a/drivers/gpu/drm/i915/vlv_dsi_pll.c b/drivers/gpu/drm/i915/vlv_dsi_pll.c
new file mode 100644
index 000000000000..2ff2ee7f3b78
--- /dev/null
+++ b/drivers/gpu/drm/i915/vlv_dsi_pll.c
@@ -0,0 +1,650 @@
+/*
+ * Copyright © 2013 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Authors:
+ *	Shobhit Kumar <shobhit.kumar@intel.com>
+ *	Yogesh Mohan Marimuthu <yogesh.mohan.marimuthu@intel.com>
+ */
+
+#include <linux/kernel.h>
+#include "intel_drv.h"
+#include "i915_drv.h"
+#include "intel_dsi.h"
+
+static const u16 lfsr_converts[] = {
+	426, 469, 234, 373, 442, 221, 110, 311, 411,		/* 62 - 70 */
+	461, 486, 243, 377, 188, 350, 175, 343, 427, 213,	/* 71 - 80 */
+	106, 53, 282, 397, 454, 227, 113, 56, 284, 142,		/* 81 - 90 */
+	71, 35, 273, 136, 324, 418, 465, 488, 500, 506		/* 91 - 100 */
+};
+
+/* Get DSI clock from pixel clock */
+static u32 dsi_clk_from_pclk(u32 pclk, enum mipi_dsi_pixel_format fmt,
+			     int lane_count)
+{
+	u32 dsi_clk_khz;
+	u32 bpp = mipi_dsi_pixel_format_to_bpp(fmt);
+
+	/* DSI data rate = pixel clock * bits per pixel / lane count
+	   pixel clock is converted from KHz to Hz */
+	dsi_clk_khz = DIV_ROUND_CLOSEST(pclk * bpp, lane_count);
+
+	return dsi_clk_khz;
+}
+
+static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
+			struct intel_crtc_state *config,
+			int target_dsi_clk)
+{
+	unsigned int m_min, m_max, p_min = 2, p_max = 6;
+	unsigned int m, n, p;
+	unsigned int calc_m, calc_p;
+	int delta, ref_clk;
+
+	/* target_dsi_clk is expected in kHz */
+	if (target_dsi_clk < 300000 || target_dsi_clk > 1150000) {
+		DRM_ERROR("DSI CLK Out of Range\n");
+		return -ECHRNG;
+	}
+
+	if (IS_CHERRYVIEW(dev_priv)) {
+		ref_clk = 100000;
+		n = 4;
+		m_min = 70;
+		m_max = 96;
+	} else {
+		ref_clk = 25000;
+		n = 1;
+		m_min = 62;
+		m_max = 92;
+	}
+
+	calc_p = p_min;
+	calc_m = m_min;
+	delta = abs(target_dsi_clk - (m_min * ref_clk) / (p_min * n));
+
+	for (m = m_min; m <= m_max && delta; m++) {
+		for (p = p_min; p <= p_max && delta; p++) {
+			/*
+			 * Find the optimal m and p divisors with minimal delta
+			 * +/- the required clock
+			 */
+			int calc_dsi_clk = (m * ref_clk) / (p * n);
+			int d = abs(target_dsi_clk - calc_dsi_clk);
+			if (d < delta) {
+				delta = d;
+				calc_m = m;
+				calc_p = p;
+			}
+		}
+	}
+
+	/* register has log2(N1), this works fine for powers of two */
+	config->dsi_pll.ctrl = 1 << (DSI_PLL_P1_POST_DIV_SHIFT + calc_p - 2);
+	config->dsi_pll.div =
+		(ffs(n) - 1) << DSI_PLL_N1_DIV_SHIFT |
+		(u32)lfsr_converts[calc_m - 62] << DSI_PLL_M1_DIV_SHIFT;
+
+	return 0;
+}
+
+/*
+ * XXX: The muxing and gating is hard coded for now. Need to add support for
+ * sharing PLLs with two DSI outputs.
+ */
+static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
+			       struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	int ret;
+	u32 dsi_clk;
+
+	dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format,
+				    intel_dsi->lane_count);
+
+	ret = dsi_calc_mnp(dev_priv, config, dsi_clk);
+	if (ret) {
+		DRM_DEBUG_KMS("dsi_calc_mnp failed\n");
+		return ret;
+	}
+
+	if (intel_dsi->ports & (1 << PORT_A))
+		config->dsi_pll.ctrl |= DSI_PLL_CLK_GATE_DSI0_DSIPLL;
+
+	if (intel_dsi->ports & (1 << PORT_C))
+		config->dsi_pll.ctrl |= DSI_PLL_CLK_GATE_DSI1_DSIPLL;
+
+	config->dsi_pll.ctrl |= DSI_PLL_VCO_EN;
+
+	DRM_DEBUG_KMS("dsi pll div %08x, ctrl %08x\n",
+		      config->dsi_pll.div, config->dsi_pll.ctrl);
+
+	return 0;
+}
+
+static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
+			       const struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	DRM_DEBUG_KMS("\n");
+
+	mutex_lock(&dev_priv->sb_lock);
+
+	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, 0);
+	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_DIVIDER, config->dsi_pll.div);
+	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL,
+		      config->dsi_pll.ctrl & ~DSI_PLL_VCO_EN);
+
+	/* wait at least 0.5 us after ungating before enabling VCO,
+	 * allow hrtimer subsystem optimization by relaxing timing
+	 */
+	usleep_range(10, 50);
+
+	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, config->dsi_pll.ctrl);
+
+	if (wait_for(vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_CONTROL) &
+						DSI_PLL_LOCK, 20)) {
+
+		mutex_unlock(&dev_priv->sb_lock);
+		DRM_ERROR("DSI PLL lock failed\n");
+		return;
+	}
+	mutex_unlock(&dev_priv->sb_lock);
+
+	DRM_DEBUG_KMS("DSI PLL locked\n");
+}
+
+static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	u32 tmp;
+
+	DRM_DEBUG_KMS("\n");
+
+	mutex_lock(&dev_priv->sb_lock);
+
+	tmp = vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_CONTROL);
+	tmp &= ~DSI_PLL_VCO_EN;
+	tmp |= DSI_PLL_LDO_GATE;
+	vlv_cck_write(dev_priv, CCK_REG_DSI_PLL_CONTROL, tmp);
+
+	mutex_unlock(&dev_priv->sb_lock);
+}
+
+static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
+{
+	bool enabled;
+	u32 val;
+	u32 mask;
+
+	mask = BXT_DSI_PLL_DO_ENABLE | BXT_DSI_PLL_LOCKED;
+	val = I915_READ(BXT_DSI_PLL_ENABLE);
+	enabled = (val & mask) == mask;
+
+	if (!enabled)
+		return false;
+
+	/*
+	 * Dividers must be programmed with valid values. As per BSEPC, for
+	 * GEMINLAKE only PORT A divider values are checked while for BXT
+	 * both divider values are validated. Check this here for
+	 * paranoia, since BIOS is known to misconfigure PLLs in this way at
+	 * times, and since accessing DSI registers with invalid dividers
+	 * causes a system hang.
+	 */
+	val = I915_READ(BXT_DSI_PLL_CTL);
+	if (IS_GEMINILAKE(dev_priv)) {
+		if (!(val & BXT_DSIA_16X_MASK)) {
+			DRM_DEBUG_DRIVER("Invalid PLL divider (%08x)\n", val);
+			enabled = false;
+		}
+	} else {
+		if (!(val & BXT_DSIA_16X_MASK) || !(val & BXT_DSIC_16X_MASK)) {
+			DRM_DEBUG_DRIVER("Invalid PLL divider (%08x)\n", val);
+			enabled = false;
+		}
+	}
+
+	return enabled;
+}
+
+static void bxt_disable_dsi_pll(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	u32 val;
+
+	DRM_DEBUG_KMS("\n");
+
+	val = I915_READ(BXT_DSI_PLL_ENABLE);
+	val &= ~BXT_DSI_PLL_DO_ENABLE;
+	I915_WRITE(BXT_DSI_PLL_ENABLE, val);
+
+	/*
+	 * PLL lock should deassert within 200us.
+	 * Wait up to 1ms before timing out.
+	 */
+	if (intel_wait_for_register(dev_priv,
+				    BXT_DSI_PLL_ENABLE,
+				    BXT_DSI_PLL_LOCKED,
+				    0,
+				    1))
+		DRM_ERROR("Timeout waiting for PLL lock deassertion\n");
+}
+
+static void assert_bpp_mismatch(enum mipi_dsi_pixel_format fmt, int pipe_bpp)
+{
+	int bpp = mipi_dsi_pixel_format_to_bpp(fmt);
+
+	WARN(bpp != pipe_bpp,
+	     "bpp match assertion failure (expected %d, current %d)\n",
+	     bpp, pipe_bpp);
+}
+
+static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+			    struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	u32 dsi_clock, pclk;
+	u32 pll_ctl, pll_div;
+	u32 m = 0, p = 0, n;
+	int refclk = IS_CHERRYVIEW(dev_priv) ? 100000 : 25000;
+	int i;
+
+	DRM_DEBUG_KMS("\n");
+
+	mutex_lock(&dev_priv->sb_lock);
+	pll_ctl = vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_CONTROL);
+	pll_div = vlv_cck_read(dev_priv, CCK_REG_DSI_PLL_DIVIDER);
+	mutex_unlock(&dev_priv->sb_lock);
+
+	config->dsi_pll.ctrl = pll_ctl & ~DSI_PLL_LOCK;
+	config->dsi_pll.div = pll_div;
+
+	/* mask out other bits and extract the P1 divisor */
+	pll_ctl &= DSI_PLL_P1_POST_DIV_MASK;
+	pll_ctl = pll_ctl >> (DSI_PLL_P1_POST_DIV_SHIFT - 2);
+
+	/* N1 divisor */
+	n = (pll_div & DSI_PLL_N1_DIV_MASK) >> DSI_PLL_N1_DIV_SHIFT;
+	n = 1 << n; /* register has log2(N1) */
+
+	/* mask out the other bits and extract the M1 divisor */
+	pll_div &= DSI_PLL_M1_DIV_MASK;
+	pll_div = pll_div >> DSI_PLL_M1_DIV_SHIFT;
+
+	while (pll_ctl) {
+		pll_ctl = pll_ctl >> 1;
+		p++;
+	}
+	p--;
+
+	if (!p) {
+		DRM_ERROR("wrong P1 divisor\n");
+		return 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(lfsr_converts); i++) {
+		if (lfsr_converts[i] == pll_div)
+			break;
+	}
+
+	if (i == ARRAY_SIZE(lfsr_converts)) {
+		DRM_ERROR("wrong m_seed programmed\n");
+		return 0;
+	}
+
+	m = i + 62;
+
+	dsi_clock = (m * refclk) / (p * n);
+
+	/* pixel_format and pipe_bpp should agree */
+	assert_bpp_mismatch(intel_dsi->pixel_format, pipe_bpp);
+
+	pclk = DIV_ROUND_CLOSEST(dsi_clock * intel_dsi->lane_count, pipe_bpp);
+
+	return pclk;
+}
+
+static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+			    struct intel_crtc_state *config)
+{
+	u32 pclk;
+	u32 dsi_clk;
+	u32 dsi_ratio;
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	/* Divide by zero */
+	if (!pipe_bpp) {
+		DRM_ERROR("Invalid BPP(0)\n");
+		return 0;
+	}
+
+	config->dsi_pll.ctrl = I915_READ(BXT_DSI_PLL_CTL);
+
+	dsi_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK;
+
+	dsi_clk = (dsi_ratio * BXT_REF_CLOCK_KHZ) / 2;
+
+	/* pixel_format and pipe_bpp should agree */
+	assert_bpp_mismatch(intel_dsi->pixel_format, pipe_bpp);
+
+	pclk = DIV_ROUND_CLOSEST(dsi_clk * intel_dsi->lane_count, pipe_bpp);
+
+	DRM_DEBUG_DRIVER("Calculated pclk=%u\n", pclk);
+	return pclk;
+}
+
+u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		       struct intel_crtc_state *config)
+{
+	if (IS_GEN9_LP(to_i915(encoder->base.dev)))
+		return bxt_dsi_get_pclk(encoder, pipe_bpp, config);
+	else
+		return vlv_dsi_get_pclk(encoder, pipe_bpp, config);
+}
+
+static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+{
+	u32 temp;
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+
+	temp = I915_READ(MIPI_CTRL(port));
+	temp &= ~ESCAPE_CLOCK_DIVIDER_MASK;
+	I915_WRITE(MIPI_CTRL(port), temp |
+			intel_dsi->escape_clk_div <<
+			ESCAPE_CLOCK_DIVIDER_SHIFT);
+}
+
+static void glk_dsi_program_esc_clock(struct drm_device *dev,
+				   const struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 dsi_rate = 0;
+	u32 pll_ratio = 0;
+	u32 ddr_clk = 0;
+	u32 div1_value = 0;
+	u32 div2_value = 0;
+	u32 txesc1_div = 0;
+	u32 txesc2_div = 0;
+
+	pll_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK;
+
+	dsi_rate = (BXT_REF_CLOCK_KHZ * pll_ratio) / 2;
+
+	ddr_clk = dsi_rate / 2;
+
+	/* Variable divider value */
+	div1_value = DIV_ROUND_CLOSEST(ddr_clk, 20000);
+
+	/* Calculate TXESC1 divider */
+	if (div1_value <= 10)
+		txesc1_div = div1_value;
+	else if ((div1_value > 10) && (div1_value <= 20))
+		txesc1_div = DIV_ROUND_UP(div1_value, 2);
+	else if ((div1_value > 20) && (div1_value <= 30))
+		txesc1_div = DIV_ROUND_UP(div1_value, 4);
+	else if ((div1_value > 30) && (div1_value <= 40))
+		txesc1_div = DIV_ROUND_UP(div1_value, 6);
+	else if ((div1_value > 40) && (div1_value <= 50))
+		txesc1_div = DIV_ROUND_UP(div1_value, 8);
+	else
+		txesc1_div = 10;
+
+	/* Calculate TXESC2 divider */
+	div2_value = DIV_ROUND_UP(div1_value, txesc1_div);
+
+	if (div2_value < 10)
+		txesc2_div = div2_value;
+	else
+		txesc2_div = 10;
+
+	I915_WRITE(MIPIO_TXESC_CLK_DIV1, txesc1_div & GLK_TX_ESC_CLK_DIV1_MASK);
+	I915_WRITE(MIPIO_TXESC_CLK_DIV2, txesc2_div & GLK_TX_ESC_CLK_DIV2_MASK);
+}
+
+/* Program BXT Mipi clocks and dividers */
+static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port,
+				   const struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+	u32 tmp;
+	u32 dsi_rate = 0;
+	u32 pll_ratio = 0;
+	u32 rx_div;
+	u32 tx_div;
+	u32 rx_div_upper;
+	u32 rx_div_lower;
+	u32 mipi_8by3_divider;
+
+	/* Clear old configurations */
+	tmp = I915_READ(BXT_MIPI_CLOCK_CTL);
+	tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port));
+	tmp &= ~(BXT_MIPI_RX_ESCLK_UPPER_FIXDIV_MASK(port));
+	tmp &= ~(BXT_MIPI_8X_BY3_DIVIDER_MASK(port));
+	tmp &= ~(BXT_MIPI_RX_ESCLK_LOWER_FIXDIV_MASK(port));
+
+	/* Get the current DSI rate(actual) */
+	pll_ratio = config->dsi_pll.ctrl & BXT_DSI_PLL_RATIO_MASK;
+	dsi_rate = (BXT_REF_CLOCK_KHZ * pll_ratio) / 2;
+
+	/*
+	 * tx clock should be <= 20MHz and the div value must be
+	 * subtracted by 1 as per bspec
+	 */
+	tx_div = DIV_ROUND_UP(dsi_rate, 20000) - 1;
+	/*
+	 * rx clock should be <= 150MHz and the div value must be
+	 * subtracted by 1 as per bspec
+	 */
+	rx_div = DIV_ROUND_UP(dsi_rate, 150000) - 1;
+
+	/*
+	 * rx divider value needs to be updated in the
+	 * two differnt bit fields in the register hence splitting the
+	 * rx divider value accordingly
+	 */
+	rx_div_lower = rx_div & RX_DIVIDER_BIT_1_2;
+	rx_div_upper = (rx_div & RX_DIVIDER_BIT_3_4) >> 2;
+
+	mipi_8by3_divider = 0x2;
+
+	tmp |= BXT_MIPI_8X_BY3_DIVIDER(port, mipi_8by3_divider);
+	tmp |= BXT_MIPI_TX_ESCLK_DIVIDER(port, tx_div);
+	tmp |= BXT_MIPI_RX_ESCLK_LOWER_DIVIDER(port, rx_div_lower);
+	tmp |= BXT_MIPI_RX_ESCLK_UPPER_DIVIDER(port, rx_div_upper);
+
+	I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
+}
+
+static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
+			       struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	u8 dsi_ratio, dsi_ratio_min, dsi_ratio_max;
+	u32 dsi_clk;
+
+	dsi_clk = dsi_clk_from_pclk(intel_dsi->pclk, intel_dsi->pixel_format,
+				    intel_dsi->lane_count);
+
+	/*
+	 * From clock diagram, to get PLL ratio divider, divide double of DSI
+	 * link rate (i.e., 2*8x=16x frequency value) by ref clock. Make sure to
+	 * round 'up' the result
+	 */
+	dsi_ratio = DIV_ROUND_UP(dsi_clk * 2, BXT_REF_CLOCK_KHZ);
+
+	if (IS_BROXTON(dev_priv)) {
+		dsi_ratio_min = BXT_DSI_PLL_RATIO_MIN;
+		dsi_ratio_max = BXT_DSI_PLL_RATIO_MAX;
+	} else {
+		dsi_ratio_min = GLK_DSI_PLL_RATIO_MIN;
+		dsi_ratio_max = GLK_DSI_PLL_RATIO_MAX;
+	}
+
+	if (dsi_ratio < dsi_ratio_min || dsi_ratio > dsi_ratio_max) {
+		DRM_ERROR("Cant get a suitable ratio from DSI PLL ratios\n");
+		return -ECHRNG;
+	} else
+		DRM_DEBUG_KMS("DSI PLL calculation is Done!!\n");
+
+	/*
+	 * Program DSI ratio and Select MIPIC and MIPIA PLL output as 8x
+	 * Spec says both have to be programmed, even if one is not getting
+	 * used. Configure MIPI_CLOCK_CTL dividers in modeset
+	 */
+	config->dsi_pll.ctrl = dsi_ratio | BXT_DSIA_16X_BY2 | BXT_DSIC_16X_BY2;
+
+	/* As per recommendation from hardware team,
+	 * Prog PVD ratio =1 if dsi ratio <= 50
+	 */
+	if (IS_BROXTON(dev_priv) && dsi_ratio <= 50)
+		config->dsi_pll.ctrl |= BXT_DSI_PLL_PVD_RATIO_1;
+
+	return 0;
+}
+
+static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
+			       const struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 val;
+
+	DRM_DEBUG_KMS("\n");
+
+	/* Configure PLL vales */
+	I915_WRITE(BXT_DSI_PLL_CTL, config->dsi_pll.ctrl);
+	POSTING_READ(BXT_DSI_PLL_CTL);
+
+	/* Program TX, RX, Dphy clocks */
+	if (IS_BROXTON(dev_priv)) {
+		for_each_dsi_port(port, intel_dsi->ports)
+			bxt_dsi_program_clocks(encoder->base.dev, port, config);
+	} else {
+		glk_dsi_program_esc_clock(encoder->base.dev, config);
+	}
+
+	/* Enable DSI PLL */
+	val = I915_READ(BXT_DSI_PLL_ENABLE);
+	val |= BXT_DSI_PLL_DO_ENABLE;
+	I915_WRITE(BXT_DSI_PLL_ENABLE, val);
+
+	/* Timeout and fail if PLL not locked */
+	if (intel_wait_for_register(dev_priv,
+				    BXT_DSI_PLL_ENABLE,
+				    BXT_DSI_PLL_LOCKED,
+				    BXT_DSI_PLL_LOCKED,
+				    1)) {
+		DRM_ERROR("Timed out waiting for DSI PLL to lock\n");
+		return;
+	}
+
+	DRM_DEBUG_KMS("DSI PLL locked\n");
+}
+
+bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
+{
+	if (IS_GEN9_LP(dev_priv))
+		return bxt_dsi_pll_is_enabled(dev_priv);
+
+	MISSING_CASE(INTEL_DEVID(dev_priv));
+
+	return false;
+}
+
+int intel_compute_dsi_pll(struct intel_encoder *encoder,
+			  struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		return vlv_compute_dsi_pll(encoder, config);
+	else if (IS_GEN9_LP(dev_priv))
+		return gen9lp_compute_dsi_pll(encoder, config);
+
+	return -ENODEV;
+}
+
+void intel_enable_dsi_pll(struct intel_encoder *encoder,
+			  const struct intel_crtc_state *config)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		vlv_enable_dsi_pll(encoder, config);
+	else if (IS_GEN9_LP(dev_priv))
+		gen9lp_enable_dsi_pll(encoder, config);
+}
+
+void intel_disable_dsi_pll(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		vlv_disable_dsi_pll(encoder);
+	else if (IS_GEN9_LP(dev_priv))
+		bxt_disable_dsi_pll(encoder);
+}
+
+static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
+				    enum port port)
+{
+	u32 tmp;
+	struct drm_device *dev = encoder->base.dev;
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	/* Clear old configurations */
+	if (IS_BROXTON(dev_priv)) {
+		tmp = I915_READ(BXT_MIPI_CLOCK_CTL);
+		tmp &= ~(BXT_MIPI_TX_ESCLK_FIXDIV_MASK(port));
+		tmp &= ~(BXT_MIPI_RX_ESCLK_UPPER_FIXDIV_MASK(port));
+		tmp &= ~(BXT_MIPI_8X_BY3_DIVIDER_MASK(port));
+		tmp &= ~(BXT_MIPI_RX_ESCLK_LOWER_FIXDIV_MASK(port));
+		I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
+	} else {
+		tmp = I915_READ(MIPIO_TXESC_CLK_DIV1);
+		tmp &= ~GLK_TX_ESC_CLK_DIV1_MASK;
+		I915_WRITE(MIPIO_TXESC_CLK_DIV1, tmp);
+
+		tmp = I915_READ(MIPIO_TXESC_CLK_DIV2);
+		tmp &= ~GLK_TX_ESC_CLK_DIV2_MASK;
+		I915_WRITE(MIPIO_TXESC_CLK_DIV2, tmp);
+	}
+	I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
+}
+
+void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+
+	if (IS_GEN9_LP(dev_priv))
+		gen9lp_dsi_reset_clocks(encoder, port);
+	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
+		vlv_dsi_reset_clocks(encoder, port);
+}
-- 
cgit v1.2.3


From e518634b4366d2fe874d36e6394693b1be0a9f44 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 5 Jul 2018 16:25:08 +0300
Subject: drm/i915/dsi: use vlv and bxt prefixes for the global DSI functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoid confusion with the functions to be added for the new ICL or gen 11
DSI implementation by renaming the current DSI functions. While at it,
permutate the words in the function names to make them all start with
"vlv_dsi" or "vlv_dsi_pll" etc.

Reduce the platform abstractions in the PLL file while at it, moving the
checks to vlv_dsi.c instead, where we typically already have the
necessary if ladders.

Leave the static functions as-is for now; they could be renamed later if
needed.

No functional changes.

v2: use "gen7" prefix.

v3: use "vlv" and "bxt" prefixes, reduce the abstractions.

References: https://patchwork.freedesktop.org/series/44823/
Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705132509.12881-2-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/intel_display.c |  6 +--
 drivers/gpu/drm/i915/intel_drv.h     |  2 +-
 drivers/gpu/drm/i915/intel_dsi.h     | 30 +++++++----
 drivers/gpu/drm/i915/intel_dsi_vbt.c |  2 +-
 drivers/gpu/drm/i915/vlv_dsi.c       | 61 ++++++++++++++--------
 drivers/gpu/drm/i915/vlv_dsi_pll.c   | 98 +++++++-----------------------------
 6 files changed, 80 insertions(+), 119 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 12102224f47a..d33033abbf18 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -9416,7 +9416,7 @@ static bool bxt_get_dsi_transcoder_state(struct intel_crtc *crtc,
 		 * registers/MIPI[BXT]. We can break out here early, since we
 		 * need the same DSI PLL to be enabled for both DSI ports.
 		 */
-		if (!intel_dsi_pll_is_enabled(dev_priv))
+		if (!bxt_dsi_pll_is_enabled(dev_priv))
 			break;
 
 		/* XXX: this works for video mode only */
@@ -14092,7 +14092,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 		intel_ddi_init(dev_priv, PORT_B);
 		intel_ddi_init(dev_priv, PORT_C);
 
-		intel_dsi_init(dev_priv);
+		vlv_dsi_init(dev_priv);
 	} else if (HAS_DDI(dev_priv)) {
 		int found;
 
@@ -14198,7 +14198,7 @@ static void intel_setup_outputs(struct drm_i915_private *dev_priv)
 				intel_hdmi_init(dev_priv, CHV_HDMID, PORT_D);
 		}
 
-		intel_dsi_init(dev_priv);
+		vlv_dsi_init(dev_priv);
 	} else if (!IS_GEN2(dev_priv) && !IS_PINEVIEW(dev_priv)) {
 		bool found = false;
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 88d3581124e8..3034477b79ff 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1731,7 +1731,7 @@ int intel_dp_aux_init_backlight_funcs(struct intel_connector *intel_connector);
 int intel_dp_mst_encoder_init(struct intel_digital_port *intel_dig_port, int conn_id);
 void intel_dp_mst_encoder_cleanup(struct intel_digital_port *intel_dig_port);
 /* vlv_dsi.c */
-void intel_dsi_init(struct drm_i915_private *dev_priv);
+void vlv_dsi_init(struct drm_i915_private *dev_priv);
 
 /* intel_dsi_dcs_backlight.c */
 int intel_dsi_dcs_init_backlight_funcs(struct intel_connector *intel_connector);
diff --git a/drivers/gpu/drm/i915/intel_dsi.h b/drivers/gpu/drm/i915/intel_dsi.h
index dce9bcc2de53..ad7c1cb32983 100644
--- a/drivers/gpu/drm/i915/intel_dsi.h
+++ b/drivers/gpu/drm/i915/intel_dsi.h
@@ -130,20 +130,28 @@ static inline struct intel_dsi *enc_to_intel_dsi(struct drm_encoder *encoder)
 }
 
 /* vlv_dsi.c */
-void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port);
+void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port);
 enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt);
 
 /* vlv_dsi_pll.c */
-bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv);
-int intel_compute_dsi_pll(struct intel_encoder *encoder,
-			  struct intel_crtc_state *config);
-void intel_enable_dsi_pll(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *config);
-void intel_disable_dsi_pll(struct intel_encoder *encoder);
-u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-		       struct intel_crtc_state *config);
-void intel_dsi_reset_clocks(struct intel_encoder *encoder,
-			    enum port port);
+int vlv_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config);
+void vlv_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config);
+void vlv_dsi_pll_disable(struct intel_encoder *encoder);
+u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config);
+void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port);
+
+bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv);
+int bxt_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config);
+void bxt_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config);
+void bxt_dsi_pll_disable(struct intel_encoder *encoder);
+u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config);
+void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port);
 
 /* intel_dsi_vbt.c */
 bool intel_dsi_vbt_init(struct intel_dsi *intel_dsi, u16 panel_id);
diff --git a/drivers/gpu/drm/i915/intel_dsi_vbt.c b/drivers/gpu/drm/i915/intel_dsi_vbt.c
index 4d6ffa7b3e7b..ac83d6b89ae0 100644
--- a/drivers/gpu/drm/i915/intel_dsi_vbt.c
+++ b/drivers/gpu/drm/i915/intel_dsi_vbt.c
@@ -181,7 +181,7 @@ static const u8 *mipi_exec_send_packet(struct intel_dsi *intel_dsi,
 		break;
 	}
 
-	wait_for_dsi_fifo_empty(intel_dsi, port);
+	vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
 
 out:
 	data += len;
diff --git a/drivers/gpu/drm/i915/vlv_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
index 3b7acb5a70b3..0aa99eeae271 100644
--- a/drivers/gpu/drm/i915/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -69,7 +69,7 @@ enum mipi_dsi_pixel_format pixel_format_from_register_bits(u32 fmt)
 	}
 }
 
-void wait_for_dsi_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
+void vlv_dsi_wait_for_fifo_empty(struct intel_dsi *intel_dsi, enum port port)
 {
 	struct drm_encoder *encoder = &intel_dsi->base.base;
 	struct drm_device *dev = encoder->dev;
@@ -342,11 +342,15 @@ static bool intel_dsi_compute_config(struct intel_encoder *encoder,
 			pipe_config->cpu_transcoder = TRANSCODER_DSI_C;
 		else
 			pipe_config->cpu_transcoder = TRANSCODER_DSI_A;
-	}
 
-	ret = intel_compute_dsi_pll(encoder, pipe_config);
-	if (ret)
-		return false;
+		ret = bxt_dsi_pll_compute(encoder, pipe_config);
+		if (ret)
+			return false;
+	} else {
+		ret = vlv_dsi_pll_compute(encoder, pipe_config);
+		if (ret)
+			return false;
+	}
 
 	pipe_config->clock_set = true;
 
@@ -810,8 +814,13 @@ static void intel_dsi_pre_enable(struct intel_encoder *encoder,
 	 * The BIOS may leave the PLL in a wonky state where it doesn't
 	 * lock. It needs to be fully powered down to fix it.
 	 */
-	intel_disable_dsi_pll(encoder);
-	intel_enable_dsi_pll(encoder, pipe_config);
+	if (IS_GEN9_LP(dev_priv)) {
+		bxt_dsi_pll_disable(encoder);
+		bxt_dsi_pll_enable(encoder, pipe_config);
+	} else {
+		vlv_dsi_pll_disable(encoder);
+		vlv_dsi_pll_enable(encoder, pipe_config);
+	}
 
 	if (IS_BROXTON(dev_priv)) {
 		/* Add MIPI IO reset programming for modeset */
@@ -949,7 +958,7 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 
 	if (is_vid_mode(intel_dsi)) {
 		for_each_dsi_port(port, intel_dsi->ports)
-			wait_for_dsi_fifo_empty(intel_dsi, port);
+			vlv_dsi_wait_for_fifo_empty(intel_dsi, port);
 
 		intel_dsi_port_disable(encoder);
 		usleep_range(2000, 5000);
@@ -979,11 +988,13 @@ static void intel_dsi_post_disable(struct intel_encoder *encoder,
 				val & ~MIPIO_RST_CTRL);
 	}
 
-	intel_disable_dsi_pll(encoder);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv)) {
+		bxt_dsi_pll_disable(encoder);
+	} else {
 		u32 val;
 
+		vlv_dsi_pll_disable(encoder);
+
 		val = I915_READ(DSPCLK_GATE_D);
 		val &= ~DPOUNIT_CLOCK_GATE_DISABLE;
 		I915_WRITE(DSPCLK_GATE_D, val);
@@ -1024,7 +1035,7 @@ static bool intel_dsi_get_hw_state(struct intel_encoder *encoder,
 	 * configuration, otherwise accessing DSI registers will hang the
 	 * machine. See BSpec North Display Engine registers/MIPI[BXT].
 	 */
-	if (IS_GEN9_LP(dev_priv) && !intel_dsi_pll_is_enabled(dev_priv))
+	if (IS_GEN9_LP(dev_priv) && !bxt_dsi_pll_is_enabled(dev_priv))
 		goto out_put_power;
 
 	/* XXX: this only works for one DSI output */
@@ -1247,16 +1258,19 @@ static void intel_dsi_get_config(struct intel_encoder *encoder,
 
 	pipe_config->output_types |= BIT(INTEL_OUTPUT_DSI);
 
-	if (IS_GEN9_LP(dev_priv))
+	if (IS_GEN9_LP(dev_priv)) {
 		bxt_dsi_get_pipe_config(encoder, pipe_config);
+		pclk = bxt_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
+					pipe_config);
+	} else {
+		pclk = vlv_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
+					pipe_config);
+	}
 
-	pclk = intel_dsi_get_pclk(encoder, pipe_config->pipe_bpp,
-				  pipe_config);
-	if (!pclk)
-		return;
-
-	pipe_config->base.adjusted_mode.crtc_clock = pclk;
-	pipe_config->port_clock = pclk;
+	if (pclk) {
+		pipe_config->base.adjusted_mode.crtc_clock = pclk;
+		pipe_config->port_clock = pclk;
+	}
 }
 
 static enum drm_mode_status
@@ -1590,7 +1604,10 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder)
 			/* Panel commands can be sent when clock is in LP11 */
 			I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
 
-			intel_dsi_reset_clocks(encoder, port);
+			if (IS_GEN9_LP(dev_priv))
+				bxt_dsi_reset_clocks(encoder, port);
+			else
+				vlv_dsi_reset_clocks(encoder, port);
 			I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 
 			val = I915_READ(MIPI_DSI_FUNC_PRG(port));
@@ -1713,7 +1730,7 @@ static void intel_dsi_add_properties(struct intel_connector *connector)
 	}
 }
 
-void intel_dsi_init(struct drm_i915_private *dev_priv)
+void vlv_dsi_init(struct drm_i915_private *dev_priv)
 {
 	struct drm_device *dev = &dev_priv->drm;
 	struct intel_dsi *intel_dsi;
diff --git a/drivers/gpu/drm/i915/vlv_dsi_pll.c b/drivers/gpu/drm/i915/vlv_dsi_pll.c
index 2ff2ee7f3b78..a132a8037ecc 100644
--- a/drivers/gpu/drm/i915/vlv_dsi_pll.c
+++ b/drivers/gpu/drm/i915/vlv_dsi_pll.c
@@ -111,8 +111,8 @@ static int dsi_calc_mnp(struct drm_i915_private *dev_priv,
  * XXX: The muxing and gating is hard coded for now. Need to add support for
  * sharing PLLs with two DSI outputs.
  */
-static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
+int vlv_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -142,8 +142,8 @@ static int vlv_compute_dsi_pll(struct intel_encoder *encoder,
 	return 0;
 }
 
-static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
+void vlv_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
@@ -175,7 +175,7 @@ static void vlv_enable_dsi_pll(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("DSI PLL locked\n");
 }
 
-static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
+void vlv_dsi_pll_disable(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 tmp;
@@ -192,7 +192,7 @@ static void vlv_disable_dsi_pll(struct intel_encoder *encoder)
 	mutex_unlock(&dev_priv->sb_lock);
 }
 
-static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
+bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
 {
 	bool enabled;
 	u32 val;
@@ -229,7 +229,7 @@ static bool bxt_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
 	return enabled;
 }
 
-static void bxt_disable_dsi_pll(struct intel_encoder *encoder)
+void bxt_dsi_pll_disable(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	u32 val;
@@ -261,8 +261,8 @@ static void assert_bpp_mismatch(enum mipi_dsi_pixel_format fmt, int pipe_bpp)
 	     bpp, pipe_bpp);
 }
 
-static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
+u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -327,8 +327,8 @@ static u32 vlv_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 	return pclk;
 }
 
-static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-			    struct intel_crtc_state *config)
+u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
+		     struct intel_crtc_state *config)
 {
 	u32 pclk;
 	u32 dsi_clk;
@@ -357,16 +357,7 @@ static u32 bxt_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
 	return pclk;
 }
 
-u32 intel_dsi_get_pclk(struct intel_encoder *encoder, int pipe_bpp,
-		       struct intel_crtc_state *config)
-{
-	if (IS_GEN9_LP(to_i915(encoder->base.dev)))
-		return bxt_dsi_get_pclk(encoder, pipe_bpp, config);
-	else
-		return vlv_dsi_get_pclk(encoder, pipe_bpp, config);
-}
-
-static void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
+void vlv_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 temp;
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
@@ -480,8 +471,8 @@ static void bxt_dsi_program_clocks(struct drm_device *dev, enum port port,
 	I915_WRITE(BXT_MIPI_CLOCK_CTL, tmp);
 }
 
-static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
-			       struct intel_crtc_state *config)
+int bxt_dsi_pll_compute(struct intel_encoder *encoder,
+			struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -528,8 +519,8 @@ static int gen9lp_compute_dsi_pll(struct intel_encoder *encoder,
 	return 0;
 }
 
-static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
-			       const struct intel_crtc_state *config)
+void bxt_dsi_pll_enable(struct intel_encoder *encoder,
+			const struct intel_crtc_state *config)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
@@ -568,52 +559,7 @@ static void gen9lp_enable_dsi_pll(struct intel_encoder *encoder,
 	DRM_DEBUG_KMS("DSI PLL locked\n");
 }
 
-bool intel_dsi_pll_is_enabled(struct drm_i915_private *dev_priv)
-{
-	if (IS_GEN9_LP(dev_priv))
-		return bxt_dsi_pll_is_enabled(dev_priv);
-
-	MISSING_CASE(INTEL_DEVID(dev_priv));
-
-	return false;
-}
-
-int intel_compute_dsi_pll(struct intel_encoder *encoder,
-			  struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		return vlv_compute_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		return gen9lp_compute_dsi_pll(encoder, config);
-
-	return -ENODEV;
-}
-
-void intel_enable_dsi_pll(struct intel_encoder *encoder,
-			  const struct intel_crtc_state *config)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_enable_dsi_pll(encoder, config);
-	else if (IS_GEN9_LP(dev_priv))
-		gen9lp_enable_dsi_pll(encoder, config);
-}
-
-void intel_disable_dsi_pll(struct intel_encoder *encoder)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_disable_dsi_pll(encoder);
-	else if (IS_GEN9_LP(dev_priv))
-		bxt_disable_dsi_pll(encoder);
-}
-
-static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
-				    enum port port)
+void bxt_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
 {
 	u32 tmp;
 	struct drm_device *dev = encoder->base.dev;
@@ -638,13 +584,3 @@ static void gen9lp_dsi_reset_clocks(struct intel_encoder *encoder,
 	}
 	I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 }
-
-void intel_dsi_reset_clocks(struct intel_encoder *encoder, enum port port)
-{
-	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
-
-	if (IS_GEN9_LP(dev_priv))
-		gen9lp_dsi_reset_clocks(encoder, port);
-	else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_reset_clocks(encoder, port);
-}
-- 
cgit v1.2.3


From 012bf847d1396e4cf2503e298ca49b3dc4591755 Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Thu, 5 Jul 2018 16:25:09 +0300
Subject: drm/i915/dsi: update some of the platform based checks
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the more customary order of latest platform first, and don't bother
with an if in the last branch.

Cc: Madhav Chauhan <madhav.chauhan@intel.com>
Cc: Daniel Vetter <daniel@ffwll.ch>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705132509.12881-3-jani.nikula@intel.com
---
 drivers/gpu/drm/i915/vlv_dsi.c | 56 ++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/i915/vlv_dsi.c b/drivers/gpu/drm/i915/vlv_dsi.c
index 0aa99eeae271..435a2c35ee8c 100644
--- a/drivers/gpu/drm/i915/vlv_dsi.c
+++ b/drivers/gpu/drm/i915/vlv_dsi.c
@@ -550,12 +550,12 @@ static void intel_dsi_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-		vlv_dsi_device_ready(encoder);
-	else if (IS_BROXTON(dev_priv))
-		bxt_dsi_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
+	if (IS_GEMINILAKE(dev_priv))
 		glk_dsi_device_ready(encoder);
+	else if (IS_GEN9_LP(dev_priv))
+		bxt_dsi_device_ready(encoder);
+	else
+		vlv_dsi_device_ready(encoder);
 }
 
 static void glk_dsi_enter_low_power_mode(struct intel_encoder *encoder)
@@ -938,11 +938,10 @@ static void intel_dsi_clear_device_ready(struct intel_encoder *encoder)
 {
 	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv) ||
-	    IS_BROXTON(dev_priv))
-		vlv_dsi_clear_device_ready(encoder);
-	else if (IS_GEMINILAKE(dev_priv))
+	if (IS_GEMINILAKE(dev_priv))
 		glk_dsi_clear_device_ready(encoder);
+	else
+		vlv_dsi_clear_device_ready(encoder);
 }
 
 static void intel_dsi_post_disable(struct intel_encoder *encoder,
@@ -1599,23 +1598,24 @@ static void intel_dsi_unprepare(struct intel_encoder *encoder)
 	enum port port;
 	u32 val;
 
-	if (!IS_GEMINILAKE(dev_priv)) {
-		for_each_dsi_port(port, intel_dsi->ports) {
-			/* Panel commands can be sent when clock is in LP11 */
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
+	if (IS_GEMINILAKE(dev_priv))
+		return;
 
-			if (IS_GEN9_LP(dev_priv))
-				bxt_dsi_reset_clocks(encoder, port);
-			else
-				vlv_dsi_reset_clocks(encoder, port);
-			I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
+	for_each_dsi_port(port, intel_dsi->ports) {
+		/* Panel commands can be sent when clock is in LP11 */
+		I915_WRITE(MIPI_DEVICE_READY(port), 0x0);
 
-			val = I915_READ(MIPI_DSI_FUNC_PRG(port));
-			val &= ~VID_MODE_FORMAT_MASK;
-			I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+		if (IS_GEN9_LP(dev_priv))
+			bxt_dsi_reset_clocks(encoder, port);
+		else
+			vlv_dsi_reset_clocks(encoder, port);
+		I915_WRITE(MIPI_EOT_DISABLE(port), CLOCKSTOP);
 
-			I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
-		}
+		val = I915_READ(MIPI_DSI_FUNC_PRG(port));
+		val &= ~VID_MODE_FORMAT_MASK;
+		I915_WRITE(MIPI_DSI_FUNC_PRG(port), val);
+
+		I915_WRITE(MIPI_DEVICE_READY(port), 0x1);
 	}
 }
 
@@ -1747,14 +1747,10 @@ void vlv_dsi_init(struct drm_i915_private *dev_priv)
 	if (!intel_bios_is_dsi_present(dev_priv, &port))
 		return;
 
-	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
-	} else if (IS_GEN9_LP(dev_priv)) {
+	if (IS_GEN9_LP(dev_priv))
 		dev_priv->mipi_mmio_base = BXT_MIPI_BASE;
-	} else {
-		DRM_ERROR("Unsupported Mipi device to reg base");
-		return;
-	}
+	else
+		dev_priv->mipi_mmio_base = VLV_MIPI_BASE;
 
 	intel_dsi = kzalloc(sizeof(*intel_dsi), GFP_KERNEL);
 	if (!intel_dsi)
-- 
cgit v1.2.3


From f8878bb2f8675e3c7716906b9b41bddc9b3bc039 Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Date: Tue, 5 Jun 2018 15:54:01 +0200
Subject: drm: print plane state normalized zpos value

When dumping plane state print normalized zpos value as done for
the other plane state fields.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Reviewed-by: Philippe Cornu <philippe.cornu@st.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180605135407.20214-2-benjamin.gaignard@linaro.org
---
 drivers/gpu/drm/drm_atomic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index d5cefb1cb2a2..7c55991170cc 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -1111,6 +1111,7 @@ static void drm_atomic_plane_print_state(struct drm_printer *p,
 	drm_printf(p, "\tcrtc-pos=" DRM_RECT_FMT "\n", DRM_RECT_ARG(&dest));
 	drm_printf(p, "\tsrc-pos=" DRM_RECT_FP_FMT "\n", DRM_RECT_FP_ARG(&src));
 	drm_printf(p, "\trotation=%x\n", state->rotation);
+	drm_printf(p, "\tnormalized-zpos=%x\n", state->normalized_zpos);
 	drm_printf(p, "\tcolor-encoding=%s\n",
 		   drm_get_color_encoding_name(state->color_encoding));
 	drm_printf(p, "\tcolor-range=%s\n",
-- 
cgit v1.2.3


From 7868e5079228b4c07cf61b5ad5d35af5c29f7375 Mon Sep 17 00:00:00 2001
From: Yannick Fertre <yannick.fertre@st.com>
Date: Fri, 29 Jun 2018 13:22:22 +0200
Subject: drm/stm: ltdc: filter mode pixel clock vs pad constraint

Filter the requested mode pixel clock frequency according
to the pad maximum supported frequency.

Signed-off-by: Yannick Fertre <yannick.fertre@st.com>
Reviewed-by: Philippe Cornu <philippe.cornu@st.com>
Tested-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/1530271342-5532-1-git-send-email-yannick.fertre@st.com
---
 drivers/gpu/drm/stm/ltdc.c | 16 ++++++++++++----
 drivers/gpu/drm/stm/ltdc.h |  1 +
 2 files changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index d997a6014d6c..f1f37336a57a 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -457,6 +457,14 @@ ltdc_crtc_mode_valid(struct drm_crtc *crtc,
 	int target_max = target + CLK_TOLERANCE_HZ;
 	int result;
 
+	result = clk_round_rate(ldev->pixel_clk, target);
+
+	DRM_DEBUG_DRIVER("clk rate target %d, available %d\n", target, result);
+
+	/* Filter modes according to the max frequency supported by the pads */
+	if (result > ldev->caps.pad_max_freq_hz)
+		return MODE_CLOCK_HIGH;
+
 	/*
 	 * Accept all "preferred" modes:
 	 * - this is important for panels because panel clock tolerances are
@@ -468,10 +476,6 @@ ltdc_crtc_mode_valid(struct drm_crtc *crtc,
 	if (mode->type & DRM_MODE_TYPE_PREFERRED)
 		return MODE_OK;
 
-	result = clk_round_rate(ldev->pixel_clk, target);
-
-	DRM_DEBUG_DRIVER("clk rate target %d, available %d\n", target, result);
-
 	/*
 	 * Filter modes according to the clock value, particularly useful for
 	 * hdmi modes that require precise pixel clocks.
@@ -991,11 +995,15 @@ static int ltdc_get_caps(struct drm_device *ddev)
 		 * does not work on 2nd layer.
 		 */
 		ldev->caps.non_alpha_only_l1 = true;
+		ldev->caps.pad_max_freq_hz = 90000000;
+		if (ldev->caps.hw_version == HWVER_10200)
+			ldev->caps.pad_max_freq_hz = 65000000;
 		break;
 	case HWVER_20101:
 		ldev->caps.reg_ofs = REG_OFS_4;
 		ldev->caps.pix_fmt_hw = ltdc_pix_fmt_a1;
 		ldev->caps.non_alpha_only_l1 = false;
+		ldev->caps.pad_max_freq_hz = 150000000;
 		break;
 	default:
 		return -ENODEV;
diff --git a/drivers/gpu/drm/stm/ltdc.h b/drivers/gpu/drm/stm/ltdc.h
index 1e16d6afb0d2..d5afb8960867 100644
--- a/drivers/gpu/drm/stm/ltdc.h
+++ b/drivers/gpu/drm/stm/ltdc.h
@@ -18,6 +18,7 @@ struct ltdc_caps {
 	u32 bus_width;		/* bus width (32 or 64 bits) */
 	const u32 *pix_fmt_hw;	/* supported pixel formats */
 	bool non_alpha_only_l1; /* non-native no-alpha formats on layer 1 */
+	int pad_max_freq_hz;	/* max frequency supported by pad */
 };
 
 #define LTDC_MAX_LAYER	4
-- 
cgit v1.2.3


From 8adbbb2e7871e76d53ea91e6159864ee534fdac8 Mon Sep 17 00:00:00 2001
From: Yannick Fertre <yannick.fertre@st.com>
Date: Fri, 29 Jun 2018 13:22:35 +0200
Subject: drm/stm: ltdc: rework reset sequence

Reset must be properly assert before deassert.
This is important if there is an early boot splash screen
before the kernel start up.

Signed-off-by: Yannick Fertre <yannick.fertre@st.com>
Reviewed-by: Philippe Cornu <philippe.cornu@st.com>
Tested-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/1530271355-5608-1-git-send-email-yannick.fertre@st.com
---
 drivers/gpu/drm/stm/ltdc.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
index f1f37336a57a..808d9fb627e9 100644
--- a/drivers/gpu/drm/stm/ltdc.c
+++ b/drivers/gpu/drm/stm/ltdc.c
@@ -1082,8 +1082,11 @@ int ltdc_load(struct drm_device *ddev)
 		}
 	}
 
-	if (!IS_ERR(rstc))
+	if (!IS_ERR(rstc)) {
+		reset_control_assert(rstc);
+		usleep_range(10, 20);
 		reset_control_deassert(rstc);
+	}
 
 	/* Disable interrupts */
 	reg_clear(ldev->regs, LTDC_IER,
-- 
cgit v1.2.3


From fcfe0bdcb1911a4ff6ab6b6264e3323745178025 Mon Sep 17 00:00:00 2001
From: Madhav Chauhan <madhav.chauhan@intel.com>
Date: Thu, 5 Jul 2018 19:19:33 +0530
Subject: drm/i915/icl: Program DSI Escape clock Divider

Escape Clock is used for LP communication across the DSI
Link. To achieve the constant frequency of the escape clock
from the variable DPLL frequency output, a variable divider(M)
is needed. This patch programs the same.

v2: (Jani N) Don't end line with "(".

Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1530798591-2077-3-git-send-email-madhav.chauhan@intel.com
---
 drivers/gpu/drm/i915/Makefile   |  1 +
 drivers/gpu/drm/i915/i915_reg.h |  1 +
 drivers/gpu/drm/i915/icl_dsi.c  | 64 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 66 insertions(+)
 create mode 100644 drivers/gpu/drm/i915/icl_dsi.c

diff --git a/drivers/gpu/drm/i915/Makefile b/drivers/gpu/drm/i915/Makefile
index e7fedb83aafc..5794f102f9b8 100644
--- a/drivers/gpu/drm/i915/Makefile
+++ b/drivers/gpu/drm/i915/Makefile
@@ -135,6 +135,7 @@ i915-y += dvo_ch7017.o \
 	  dvo_ns2501.o \
 	  dvo_sil164.o \
 	  dvo_tfp410.o \
+	  icl_dsi.o \
 	  intel_crt.o \
 	  intel_ddi.o \
 	  intel_dp_aux_backlight.o \
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index dc953ee7e3b3..a35f4142cced 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9552,6 +9552,7 @@ enum skl_power_gate {
 #define  ICL_BYTE_CLK_PER_ESC_CLK_SHIFT	16
 #define  ICL_ESC_CLK_DIV_MASK			0x1ff
 #define  ICL_ESC_CLK_DIV_SHIFT			0
+#define DSI_MAX_ESC_CLK			20000		/* in KHz */
 
 /* Gen4+ Timestamp and Pipe Frame time stamp registers */
 #define GEN4_TIMESTAMP		_MMIO(0x2358)
diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c
new file mode 100644
index 000000000000..1eb4ac30e400
--- /dev/null
+++ b/drivers/gpu/drm/i915/icl_dsi.c
@@ -0,0 +1,64 @@
+/*
+ * Copyright © 2018 Intel Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Authors:
+ *   Madhav Chauhan <madhav.chauhan@intel.com>
+ *   Jani Nikula <jani.nikula@intel.com>
+ */
+
+#include "intel_dsi.h"
+
+static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 bpp = mipi_dsi_pixel_format_to_bpp(intel_dsi->pixel_format);
+	u32 afe_clk_khz; /* 8X Clock */
+	u32 esc_clk_div_m;
+
+	afe_clk_khz = DIV_ROUND_CLOSEST(intel_dsi->pclk * bpp,
+					intel_dsi->lane_count);
+
+	esc_clk_div_m = DIV_ROUND_UP(afe_clk_khz, DSI_MAX_ESC_CLK);
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		I915_WRITE(ICL_DSI_ESC_CLK_DIV(port),
+			   esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
+		POSTING_READ(ICL_DSI_ESC_CLK_DIV(port));
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		I915_WRITE(ICL_DPHY_ESC_CLK_DIV(port),
+			   esc_clk_div_m & ICL_ESC_CLK_DIV_MASK);
+		POSTING_READ(ICL_DPHY_ESC_CLK_DIV(port));
+	}
+}
+
+static void __attribute__((unused))
+gen11_dsi_pre_enable(struct intel_encoder *encoder,
+		     const struct intel_crtc_state *pipe_config,
+		     const struct drm_connector_state *conn_state)
+{
+	/* step3: enable DSI PLL */
+	gen11_dsi_program_esc_clk_div(encoder);
+}
-- 
cgit v1.2.3


From 21652f3b0d48749e3ba0d332d2b39cc18eacb1c0 Mon Sep 17 00:00:00 2001
From: Madhav Chauhan <madhav.chauhan@intel.com>
Date: Thu, 5 Jul 2018 19:19:34 +0530
Subject: drm/i915/icl: Define DSI mode ctl register

This patch defines DSI IO mode control register and it's bits
used while enabling IO power for DSI.

Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-4-git-send-email-madhav.chauhan@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index a35f4142cced..eb3b7544a875 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -9688,6 +9688,14 @@ enum skl_power_gate {
 #define _BXT_MIPIC_PORT_CTRL				0x6B8C0
 #define BXT_MIPI_PORT_CTRL(tc)	_MMIO_MIPI(tc, _BXT_MIPIA_PORT_CTRL, _BXT_MIPIC_PORT_CTRL)
 
+/* ICL DSI MODE control */
+#define _ICL_DSI_IO_MODECTL_0				0x6B094
+#define _ICL_DSI_IO_MODECTL_1				0x6B894
+#define ICL_DSI_IO_MODECTL(port)	_MMIO_PORT(port,	\
+						    _ICL_DSI_IO_MODECTL_0, \
+						    _ICL_DSI_IO_MODECTL_1)
+#define  COMBO_PHY_MODE_DSI				(1 << 0)
+
 #define BXT_P_DSI_REGULATOR_CFG			_MMIO(0x160020)
 #define  STAP_SELECT					(1 << 0)
 
-- 
cgit v1.2.3


From b1cb21a5f1c668534b25464717c806e141ba500f Mon Sep 17 00:00:00 2001
From: Madhav Chauhan <madhav.chauhan@intel.com>
Date: Thu, 5 Jul 2018 19:19:35 +0530
Subject: drm/i915/icl: Enable DSI IO power

This patch configures mode of operation for DSI
and enable DDI IO power by configuring power well.

v2: Use for_each_dsi_port() for power get (Jani N)

Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-5-git-send-email-madhav.chauhan@intel.com
---
 drivers/gpu/drm/i915/icl_dsi.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c
index 1eb4ac30e400..774ab262c8f3 100644
--- a/drivers/gpu/drm/i915/icl_dsi.c
+++ b/drivers/gpu/drm/i915/icl_dsi.c
@@ -54,11 +54,34 @@ static void gen11_dsi_program_esc_clk_div(struct intel_encoder *encoder)
 	}
 }
 
+static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 tmp;
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(ICL_DSI_IO_MODECTL(port));
+		tmp |= COMBO_PHY_MODE_DSI;
+		I915_WRITE(ICL_DSI_IO_MODECTL(port), tmp);
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		intel_display_power_get(dev_priv, port == PORT_A ?
+					POWER_DOMAIN_PORT_DDI_A_IO :
+					POWER_DOMAIN_PORT_DDI_B_IO);
+	}
+}
+
 static void __attribute__((unused))
 gen11_dsi_pre_enable(struct intel_encoder *encoder,
 		     const struct intel_crtc_state *pipe_config,
 		     const struct drm_connector_state *conn_state)
 {
+	/* step2: enable IO power */
+	gen11_dsi_enable_io_power(encoder);
+
 	/* step3: enable DSI PLL */
 	gen11_dsi_program_esc_clk_div(encoder);
 }
-- 
cgit v1.2.3


From 166869b390b6fe763544fe4ae1e01acd28db331a Mon Sep 17 00:00:00 2001
From: Madhav Chauhan <madhav.chauhan@intel.com>
Date: Thu, 5 Jul 2018 19:19:36 +0530
Subject: drm/i915/icl: Define PORT_CL_DW_10 register

This register used to power down individual lanes for
DDI/DSI ports. Bitfields to power up/down various
combinations of lanes are also added in this patch.

v2: Review comments from Jani N
    - Use override instead of "override" for bitfields
    - Define mask for override bitfield
    - Define PWR_DOWN_LN* macros shifted in place
v3: Correct PWR_DOWN_LN_MASK value (Jani N)

Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-6-git-send-email-madhav.chauhan@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index eb3b7544a875..3ad5dcb21a7a 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1720,6 +1720,26 @@ enum i915_power_well_id {
 #define ICL_PORT_CL_DW5(port)	_MMIO_PORT(port, _ICL_PORT_CL_DW5_A, \
 						 _ICL_PORT_CL_DW5_B)
 
+#define _CNL_PORT_CL_DW10_A		0x162028
+#define _ICL_PORT_CL_DW10_B		0x6c028
+#define ICL_PORT_CL_DW10(port)		_MMIO_PORT(port,	\
+						   _CNL_PORT_CL_DW10_A, \
+						   _ICL_PORT_CL_DW10_B)
+#define  PG_SEQ_DELAY_OVERRIDE_MASK	(3 << 25)
+#define  PG_SEQ_DELAY_OVERRIDE_SHIFT	25
+#define  PG_SEQ_DELAY_OVERRIDE_ENABLE	(1 << 24)
+#define  PWR_UP_ALL_LANES		(0x0 << 4)
+#define  PWR_DOWN_LN_3_2_1		(0xe << 4)
+#define  PWR_DOWN_LN_3_2		(0xc << 4)
+#define  PWR_DOWN_LN_3			(0x8 << 4)
+#define  PWR_DOWN_LN_2_1_0		(0x7 << 4)
+#define  PWR_DOWN_LN_1_0		(0x3 << 4)
+#define  PWR_DOWN_LN_1			(0x2 << 4)
+#define  PWR_DOWN_LN_3_1		(0xa << 4)
+#define  PWR_DOWN_LN_3_1_0		(0xb << 4)
+#define  PWR_DOWN_LN_MASK		(0xf << 4)
+#define  PWR_DOWN_LN_SHIFT		4
+
 #define _PORT_CL1CM_DW9_A		0x162024
 #define _PORT_CL1CM_DW9_BC		0x6C024
 #define   IREF0RC_OFFSET_SHIFT		8
-- 
cgit v1.2.3


From 45f09f7adc8a10138b158c5805a4d3b20aac611a Mon Sep 17 00:00:00 2001
From: Madhav Chauhan <madhav.chauhan@intel.com>
Date: Thu, 5 Jul 2018 19:19:37 +0530
Subject: drm/i915/icl: Power down unused DSI lanes

To save power, unused lanes should be powered
down using the bitfield of PORT_CL_DW10.

v2: Review comments from Jani N
    - Put default label next to case 4
    - Include the shifts in the macros

Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-7-git-send-email-madhav.chauhan@intel.com
---
 drivers/gpu/drm/i915/icl_dsi.c | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/drivers/gpu/drm/i915/icl_dsi.c b/drivers/gpu/drm/i915/icl_dsi.c
index 774ab262c8f3..13830e43a4d1 100644
--- a/drivers/gpu/drm/i915/icl_dsi.c
+++ b/drivers/gpu/drm/i915/icl_dsi.c
@@ -74,6 +74,43 @@ static void gen11_dsi_enable_io_power(struct intel_encoder *encoder)
 	}
 }
 
+static void gen11_dsi_power_up_lanes(struct intel_encoder *encoder)
+{
+	struct drm_i915_private *dev_priv = to_i915(encoder->base.dev);
+	struct intel_dsi *intel_dsi = enc_to_intel_dsi(&encoder->base);
+	enum port port;
+	u32 tmp;
+	u32 lane_mask;
+
+	switch (intel_dsi->lane_count) {
+	case 1:
+		lane_mask = PWR_DOWN_LN_3_1_0;
+		break;
+	case 2:
+		lane_mask = PWR_DOWN_LN_3_1;
+		break;
+	case 3:
+		lane_mask = PWR_DOWN_LN_3;
+		break;
+	case 4:
+	default:
+		lane_mask = PWR_UP_ALL_LANES;
+		break;
+	}
+
+	for_each_dsi_port(port, intel_dsi->ports) {
+		tmp = I915_READ(ICL_PORT_CL_DW10(port));
+		tmp &= ~PWR_DOWN_LN_MASK;
+		I915_WRITE(ICL_PORT_CL_DW10(port), tmp | lane_mask);
+	}
+}
+
+static void gen11_dsi_enable_port_and_phy(struct intel_encoder *encoder)
+{
+	/* step 4a: power up all lanes of the DDI used by DSI */
+	gen11_dsi_power_up_lanes(encoder);
+}
+
 static void __attribute__((unused))
 gen11_dsi_pre_enable(struct intel_encoder *encoder,
 		     const struct intel_crtc_state *pipe_config,
@@ -84,4 +121,7 @@ gen11_dsi_pre_enable(struct intel_encoder *encoder,
 
 	/* step3: enable DSI PLL */
 	gen11_dsi_program_esc_clk_div(encoder);
+
+	/* step4: enable DSI port and DPHY */
+	gen11_dsi_enable_port_and_phy(encoder);
 }
-- 
cgit v1.2.3


From d61d1b3bbba1054a7a326c18a3c66f822f9fa338 Mon Sep 17 00:00:00 2001
From: Madhav Chauhan <madhav.chauhan@intel.com>
Date: Thu, 5 Jul 2018 19:19:38 +0530
Subject: drm/i915/icl: Define AUX lane registers for Port A/B

This patch defines AUX lane registers for PORT_PCS_DW1,
PORT_TX_DW2, PORT_TX_DW4, PORT_TX_DW5 used during
dsi enabling.

v2: Review comments from Jani N:
    - Define _ICL_PORT_PCS_DW1_AUX_A for consistency
    - Three spaces for bitfield definition.

Signed-off-by: Madhav Chauhan <madhav.chauhan@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1530798591-2077-8-git-send-email-madhav.chauhan@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 3ad5dcb21a7a..0424e45f88db 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -1796,16 +1796,22 @@ enum i915_power_well_id {
 						    _CNL_PORT_PCS_DW1_LN0_D, \
 						    _CNL_PORT_PCS_DW1_LN0_AE, \
 						    _CNL_PORT_PCS_DW1_LN0_F))
+
 #define _ICL_PORT_PCS_DW1_GRP_A		0x162604
 #define _ICL_PORT_PCS_DW1_GRP_B		0x6C604
 #define _ICL_PORT_PCS_DW1_LN0_A		0x162804
 #define _ICL_PORT_PCS_DW1_LN0_B		0x6C804
+#define _ICL_PORT_PCS_DW1_AUX_A		0x162304
+#define _ICL_PORT_PCS_DW1_AUX_B		0x6c304
 #define ICL_PORT_PCS_DW1_GRP(port)	_MMIO_PORT(port,\
 						   _ICL_PORT_PCS_DW1_GRP_A, \
 						   _ICL_PORT_PCS_DW1_GRP_B)
 #define ICL_PORT_PCS_DW1_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_PCS_DW1_LN0_A, \
 						   _ICL_PORT_PCS_DW1_LN0_B)
+#define ICL_PORT_PCS_DW1_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_PCS_DW1_AUX_A, \
+						   _ICL_PORT_PCS_DW1_AUX_B)
 #define   COMMON_KEEPER_EN		(1 << 26)
 
 /* CNL Port TX registers */
@@ -1842,16 +1848,23 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW2_GRP_B		0x6C688
 #define _ICL_PORT_TX_DW2_LN0_A		0x162888
 #define _ICL_PORT_TX_DW2_LN0_B		0x6C888
+#define _ICL_PORT_TX_DW2_AUX_A		0x162388
+#define _ICL_PORT_TX_DW2_AUX_B		0x6c388
 #define ICL_PORT_TX_DW2_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW2_GRP_A, \
 						   _ICL_PORT_TX_DW2_GRP_B)
 #define ICL_PORT_TX_DW2_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW2_LN0_A, \
 						   _ICL_PORT_TX_DW2_LN0_B)
+#define ICL_PORT_TX_DW2_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW2_AUX_A, \
+						   _ICL_PORT_TX_DW2_AUX_B)
 #define   SWING_SEL_UPPER(x)		(((x) >> 3) << 15)
 #define   SWING_SEL_UPPER_MASK		(1 << 15)
 #define   SWING_SEL_LOWER(x)		(((x) & 0x7) << 11)
 #define   SWING_SEL_LOWER_MASK		(0x7 << 11)
+#define   FRC_LATENCY_OPTIM_MASK	(0x7 << 8)
+#define   FRC_LATENCY_OPTIM_VAL(x)	((x) << 8)
 #define   RCOMP_SCALAR(x)		((x) << 0)
 #define   RCOMP_SCALAR_MASK		(0xFF << 0)
 
@@ -1867,6 +1880,8 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW4_LN0_A		0x162890
 #define _ICL_PORT_TX_DW4_LN1_A		0x162990
 #define _ICL_PORT_TX_DW4_LN0_B		0x6C890
+#define _ICL_PORT_TX_DW4_AUX_A		0x162390
+#define _ICL_PORT_TX_DW4_AUX_B		0x6c390
 #define ICL_PORT_TX_DW4_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW4_GRP_A, \
 						   _ICL_PORT_TX_DW4_GRP_B)
@@ -1875,6 +1890,9 @@ enum i915_power_well_id {
 						   _ICL_PORT_TX_DW4_LN0_B) + \
 					     ((ln) * (_ICL_PORT_TX_DW4_LN1_A - \
 						      _ICL_PORT_TX_DW4_LN0_A)))
+#define ICL_PORT_TX_DW4_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW4_AUX_A, \
+						   _ICL_PORT_TX_DW4_AUX_B)
 #define   LOADGEN_SELECT		(1 << 31)
 #define   POST_CURSOR_1(x)		((x) << 12)
 #define   POST_CURSOR_1_MASK		(0x3F << 12)
@@ -1889,12 +1907,17 @@ enum i915_power_well_id {
 #define _ICL_PORT_TX_DW5_GRP_B		0x6C694
 #define _ICL_PORT_TX_DW5_LN0_A		0x162894
 #define _ICL_PORT_TX_DW5_LN0_B		0x6C894
+#define _ICL_PORT_TX_DW5_AUX_A		0x162394
+#define _ICL_PORT_TX_DW5_AUX_B		0x6c394
 #define ICL_PORT_TX_DW5_GRP(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW5_GRP_A, \
 						   _ICL_PORT_TX_DW5_GRP_B)
 #define ICL_PORT_TX_DW5_LN0(port)	_MMIO_PORT(port, \
 						   _ICL_PORT_TX_DW5_LN0_A, \
 						   _ICL_PORT_TX_DW5_LN0_B)
+#define ICL_PORT_TX_DW5_AUX(port)	_MMIO_PORT(port, \
+						   _ICL_PORT_TX_DW5_AUX_A, \
+						   _ICL_PORT_TX_DW5_AUX_B)
 #define   TX_TRAINING_EN		(1 << 31)
 #define   TAP2_DISABLE			(1 << 30)
 #define   TAP3_DISABLE			(1 << 29)
-- 
cgit v1.2.3


From 1eca65d922d7543b60610624afd345b4f3d71ae2 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:06 +0100
Subject: drm/i915: Squelch very verbose error logging

Having found the error causing the IGT test to fail, downgrade the
verbose logging so that we stop flooding the syslogs as we deliberately
provoke it many thousands of time during selftests.

References: 10195b1e4411 ("drm/i915: Show vma allocator stack when in doubt")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/Kconfig.debug | 12 ++++++++++++
 drivers/gpu/drm/i915/i915_vma.c    |  2 +-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 80efee1ff7f3..96b577f62752 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -51,6 +51,18 @@ config DRM_I915_DEBUG_GEM
 
           If in doubt, say "N".
 
+config DRM_I915_ERRLOG_GEM
+	bool "Insert extra logging (very verbose) for common GEM errors"
+	default n
+	depends on DRM_I915_DEBUG_GEM
+	help
+	  Enable additional logging that may help track down the cause of
+	  principally userspace errors.
+
+	  Recommended for driver developers only.
+
+	  If in doubt, say "N".
+
 config DRM_I915_TRACE_GEM
 	bool "Insert extra ftrace output from the GEM internals"
 	depends on DRM_I915_DEBUG_GEM
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index de2b6d65e865..518de47111ff 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -30,7 +30,7 @@
 
 #include <drm/drm_gem.h>
 
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GEM) && IS_ENABLED(CONFIG_DRM_DEBUG_MM)
+#if IS_ENABLED(CONFIG_DRM_I915_ERRLOG_GEM) && IS_ENABLED(CONFIG_DRM_DEBUG_MM)
 
 #include <linux/stackdepot.h>
 
-- 
cgit v1.2.3


From e5d2435bfaeee3f4045e03441d3902c63254b618 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:07 +0100
Subject: drm/i915/selftests: Destroy partial tiling vma after use

As we keep VMA around until the object is destroyed, when testing
partial tiling we instantiate many, many VMA (as the object is huge
allowing for many different partial regions). We test elsewhere our
handling of populating large objects with a full set of VMA and checking
we can retrieve them afterwards, but in this test we incur the cost of
flushing all VMA after every GTT write, dramatically slowing down the
test.

References: https://bugs.freedesktop.org/show_bug.cgi?id=107130
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_object.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 885153268968..232e5ccf1852 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -288,6 +288,8 @@ static int check_partial_mapping(struct drm_i915_gem_object *obj,
 		kunmap(p);
 		if (err)
 			return err;
+
+		i915_vma_destroy(vma);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From b5f6e53d4cd58043e2c4e1b60fd446924cf56cbe Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:08 +0100
Subject: drm/i915/selftests: Skip using the GPU if wedged

If the GPU is irrecoverably broken, we can not use it to dirty memory
and check for cache coherency with the CPU. All we can do is simply skip
over the GPU subtests and focus on the CPU domains (WC, WB) cache
management.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107127
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_coherency.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index a4900091ae3d..cb9eef1635e1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -239,8 +239,16 @@ static bool always_valid(struct drm_i915_private *i915)
 	return true;
 }
 
+static bool needs_fence_registers(struct drm_i915_private *i915)
+{
+	return !i915_terminally_wedged(&i915->gpu_error);
+}
+
 static bool needs_mi_store_dword(struct drm_i915_private *i915)
 {
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return false;
+
 	return intel_engine_can_store_dword(i915->engine[RCS]);
 }
 
@@ -251,7 +259,7 @@ static const struct igt_coherency_mode {
 	bool (*valid)(struct drm_i915_private *i915);
 } igt_coherency_mode[] = {
 	{ "cpu", cpu_set, cpu_get, always_valid },
-	{ "gtt", gtt_set, gtt_get, always_valid },
+	{ "gtt", gtt_set, gtt_get, needs_fence_registers },
 	{ "wc", wc_set, wc_get, always_valid },
 	{ "gpu", gpu_set, NULL, needs_mi_store_dword },
 	{ },
-- 
cgit v1.2.3


From e16f4c36cb9bf61fcd70a2ea978cee2a23ebf71d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:09 +0100
Subject: drm/i915/selftests: Skip making an object busy if the GPU is wedged

If the GPU is wedged, we cannot make the object busy as trying to
submit a request will generate -EIO. Skip to the end of the test.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_object.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 232e5ccf1852..6fe71865b710 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -553,6 +553,9 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 	/* Now fill with busy dead objects that we expect to reap */
 	for (loop = 0; loop < 3; loop++) {
+		if (i915_terminally_wedged(&i915->gpu_error))
+			break;
+
 		obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
 		if (IS_ERR(obj)) {
 			err = PTR_ERR(obj);
-- 
cgit v1.2.3


From a9450e15ad9e921fd2d76b038a8b252b1afc7bb6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:10 +0100
Subject: drm/i915/selftests: Skip all request selftests when wedged

If the GPU is irrecoverably wedge, we cannot submit any request and so
all of the request selftests will expectedly fail. Skip over them.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_request.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index e44aa3335d9e..cc27edc40356 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -859,5 +859,9 @@ int i915_request_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(live_sequential_engines),
 		SUBTEST(live_empty_request),
 	};
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
-- 
cgit v1.2.3


From 47e61a79806d5d222261250dc573a68c53e99c22 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:11 +0100
Subject: drm/i915/selftests: Skip workaround tests when wedged

If the GPU is irrecoverably wedged, we cannot submit any request and
therefore cannot query the register state of the context (which is done
using the GPU command stream). So skip over the test as it expectedly
fails.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-6-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/intel_workarounds.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index e1ea2d2bedd2..3d86b90ab722 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -283,6 +283,9 @@ int intel_workarounds_live_selftests(struct drm_i915_private *i915)
 	};
 	int err;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	mutex_lock(&i915->drm.struct_mutex);
 	err = i915_subtests(tests, i915);
 	mutex_unlock(&i915->drm.struct_mutex);
-- 
cgit v1.2.3


From 7783decff5be6811a1a31df91b47fd2541b993d0 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:12 +0100
Subject: drm/i915/selftests: Skip live eviction tests when wedged

If the GPU is irrecoverably wedged, we cannot submit any requests and so
cannot make the GTT busy in order to test evicting active objects. As
this expectedly fails, skip over the test.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-7-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_evict.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
index 8059268800fa..128ad1cf0647 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_evict.c
@@ -500,5 +500,8 @@ int i915_gem_evict_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_evict_contexts),
 	};
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
-- 
cgit v1.2.3


From 921d07d73ebf6d87064883d69fedd3d7e9e99538 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:13 +0100
Subject: drm/i915/selftests: Skip huge pages live tests if wedged

We test the GPU handling of huge pages by submitting requests that write
into a huge page, but if the GPU is irrecoverably wedged we cannot
submit any requests. As the test expectedly fails, skip over it.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-8-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/huge_pages.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 39699939587d..1193dd36913a 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -1748,6 +1748,9 @@ int i915_gem_huge_page_live_selftests(struct drm_i915_private *dev_priv)
 		return 0;
 	}
 
+	if (i915_terminally_wedged(&dev_priv->gpu_error))
+		return 0;
+
 	file = mock_file(dev_priv);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
-- 
cgit v1.2.3


From 31c9bd78018cc36e62525fe3edc0009c1da6347f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 07:53:14 +0100
Subject: drm/i915/selftests: Skip over live context testing when wedged

If the GPU is terminally wedged we cannot submit any requests into a
context, completely unfulfilling our purpose of doing so. As this
expectedly fails, skip over the test.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706065332.15214-9-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_context.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index cc848ceeb3c3..0b36265a0f96 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -599,6 +599,9 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
 	bool fake_alias = false;
 	int err;
 
+	if (i915_terminally_wedged(&dev_priv->gpu_error))
+		return 0;
+
 	/* Install a fake aliasing gtt for exercise */
 	if (USES_PPGTT(dev_priv) && !dev_priv->mm.aliasing_ppgtt) {
 		mutex_lock(&dev_priv->drm.struct_mutex);
-- 
cgit v1.2.3


From 03bc05e1a4972f73b4eb8907aa373369e825c252 Mon Sep 17 00:00:00 2001
From: Michael Scott <michael@opensourcefoundries.com>
Date: Tue, 19 Jun 2018 16:44:06 -0700
Subject: 6lowpan: iphc: reset mac_header after decompress to fix panic

After decompression of 6lowpan socket data, an IPv6 header is inserted
before the existing socket payload.  After this, we reset the
network_header value of the skb to account for the difference in payload
size from prior to decompression + the addition of the IPv6 header.

However, we fail to reset the mac_header value.

Leaving the mac_header value untouched here, can cause a calculation
error in net/packet/af_packet.c packet_rcv() function when an
AF_PACKET socket is opened in SOCK_RAW mode for use on a 6lowpan
interface.

On line 2088, the data pointer is moved backward by the value returned
from skb_mac_header().  If skb->data is adjusted so that it is before
the skb->head pointer (which can happen when an old value of mac_header
is left in place) the kernel generates a panic in net/core/skbuff.c
line 1717.

This panic can be generated by BLE 6lowpan interfaces (such as bt0) and
802.15.4 interfaces (such as lowpan0) as they both use the same 6lowpan
sources for compression and decompression.

Signed-off-by: Michael Scott <michael@opensourcefoundries.com>
Acked-by: Alexander Aring <aring@mojatatu.com>
Acked-by: Jukka Rissanen <jukka.rissanen@linux.intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/6lowpan/iphc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/6lowpan/iphc.c b/net/6lowpan/iphc.c
index 6b1042e21656..52fad5dad9f7 100644
--- a/net/6lowpan/iphc.c
+++ b/net/6lowpan/iphc.c
@@ -770,6 +770,7 @@ int lowpan_header_decompress(struct sk_buff *skb, const struct net_device *dev,
 		hdr.hop_limit, &hdr.daddr);
 
 	skb_push(skb, sizeof(hdr));
+	skb_reset_mac_header(skb);
 	skb_reset_network_header(skb);
 	skb_copy_to_linear_data(skb, &hdr, sizeof(hdr));
 
-- 
cgit v1.2.3


From 45ae68b8cfc25bdbffc11248001c47ab1b76ff6e Mon Sep 17 00:00:00 2001
From: Jian-Hong Pan <jian-hong@endlessm.com>
Date: Fri, 25 May 2018 17:54:52 +0800
Subject: Bluetooth: Add a new Realtek 8723DE ID 0bda:b009

Without this patch we cannot turn on the Bluethooth adapter on HP
14-bs007la.

T:  Bus=01 Lev=02 Prnt=03 Port=00 Cnt=01 Dev#=  4 Spd=12   MxCh= 0
D:  Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0bda ProdID=b009 Rev= 2.00
S:  Manufacturer=Realtek
S:  Product=802.11n WLAN Adapter
S:  SerialNumber=00e04c000001
C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=500mA
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=1ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms

Signed-off-by: Jian-Hong Pan <jian-hong@endlessm.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btusb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index f73a27ea28cc..75947f04fc75 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -374,6 +374,7 @@ static const struct usb_device_id blacklist_table[] = {
 	{ USB_DEVICE(0x7392, 0xa611), .driver_info = BTUSB_REALTEK },
 
 	/* Additional Realtek 8723DE Bluetooth devices */
+	{ USB_DEVICE(0x0bda, 0xb009), .driver_info = BTUSB_REALTEK },
 	{ USB_DEVICE(0x2ff8, 0xb011), .driver_info = BTUSB_REALTEK },
 
 	/* Additional Realtek 8821AE Bluetooth devices */
-- 
cgit v1.2.3


From a5e50d5b127562f3eef5438f84b1066eeda4d7c6 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 19 Jun 2018 23:56:57 +0200
Subject: Bluetooth: btusb: use irqsave() in URB's complete callback

The USB completion callback does not disable interrupts while acquiring
the ->lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave variant of the locking primitives.

Cc: Marcel Holtmann <marcel@holtmann.org>
Cc: Johan Hedberg <johan.hedberg@gmail.com>
Cc: linux-bluetooth@vger.kernel.org
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btusb.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 75947f04fc75..fc39c2d343d7 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -510,9 +510,10 @@ static inline void btusb_free_frags(struct btusb_data *data)
 static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count)
 {
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock(&data->rxlock);
+	spin_lock_irqsave(&data->rxlock, flags);
 	skb = data->evt_skb;
 
 	while (count) {
@@ -557,7 +558,7 @@ static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count)
 	}
 
 	data->evt_skb = skb;
-	spin_unlock(&data->rxlock);
+	spin_unlock_irqrestore(&data->rxlock, flags);
 
 	return err;
 }
@@ -565,9 +566,10 @@ static int btusb_recv_intr(struct btusb_data *data, void *buffer, int count)
 static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count)
 {
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock(&data->rxlock);
+	spin_lock_irqsave(&data->rxlock, flags);
 	skb = data->acl_skb;
 
 	while (count) {
@@ -614,7 +616,7 @@ static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count)
 	}
 
 	data->acl_skb = skb;
-	spin_unlock(&data->rxlock);
+	spin_unlock_irqrestore(&data->rxlock, flags);
 
 	return err;
 }
@@ -622,9 +624,10 @@ static int btusb_recv_bulk(struct btusb_data *data, void *buffer, int count)
 static int btusb_recv_isoc(struct btusb_data *data, void *buffer, int count)
 {
 	struct sk_buff *skb;
+	unsigned long flags;
 	int err = 0;
 
-	spin_lock(&data->rxlock);
+	spin_lock_irqsave(&data->rxlock, flags);
 	skb = data->sco_skb;
 
 	while (count) {
@@ -669,7 +672,7 @@ static int btusb_recv_isoc(struct btusb_data *data, void *buffer, int count)
 	}
 
 	data->sco_skb = skb;
-	spin_unlock(&data->rxlock);
+	spin_unlock_irqrestore(&data->rxlock, flags);
 
 	return err;
 }
@@ -1067,6 +1070,7 @@ static void btusb_tx_complete(struct urb *urb)
 	struct sk_buff *skb = urb->context;
 	struct hci_dev *hdev = (struct hci_dev *)skb->dev;
 	struct btusb_data *data = hci_get_drvdata(hdev);
+	unsigned long flags;
 
 	BT_DBG("%s urb %p status %d count %d", hdev->name, urb, urb->status,
 	       urb->actual_length);
@@ -1080,9 +1084,9 @@ static void btusb_tx_complete(struct urb *urb)
 		hdev->stat.err_tx++;
 
 done:
-	spin_lock(&data->txlock);
+	spin_lock_irqsave(&data->txlock, flags);
 	data->tx_in_flight--;
-	spin_unlock(&data->txlock);
+	spin_unlock_irqrestore(&data->txlock, flags);
 
 	kfree(urb->setup_packet);
 
-- 
cgit v1.2.3


From cfdb0c2d095ac5d7f09cac1317b7d0a9e8178134 Mon Sep 17 00:00:00 2001
From: Ankit Navik <ankit.p.navik@intel.com>
Date: Fri, 29 Jun 2018 12:12:50 +0530
Subject: Bluetooth: Store Resolv list size

When the controller supports the Read LE Resolv List size feature, the
maximum list size are read and now stored.

Before patch:
< HCI Command: LE Read White List... (0x08|0x000f) plen 0  #55 [hci0] 17.979791
> HCI Event: Command Complete (0x0e) plen 5                #56 [hci0] 17.980629
      LE Read White List Size (0x08|0x000f) ncmd 1
        Status: Success (0x00)
        Size: 25
< HCI Command: LE Clear White List (0x08|0x0010) plen 0    #57 [hci0] 17.980786
> HCI Event: Command Complete (0x0e) plen 4                #58 [hci0] 17.981627
      LE Clear White List (0x08|0x0010) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0  #59 [hci0] 17.981786
> HCI Event: Command Complete (0x0e) plen 12               #60 [hci0] 17.982636
      LE Read Maximum Data Length (0x08|0x002f) ncmd 1
        Status: Success (0x00)
        Max TX octets: 251
        Max TX time: 17040
        Max RX octets: 251
        Max RX time: 17040

After patch:
< HCI Command: LE Read White List... (0x08|0x000f) plen 0  #55 [hci0] 13.338168
> HCI Event: Command Complete (0x0e) plen 5                #56 [hci0] 13.338842
      LE Read White List Size (0x08|0x000f) ncmd 1
        Status: Success (0x00)
        Size: 25
< HCI Command: LE Clear White List (0x08|0x0010) plen 0    #57 [hci0] 13.339029
> HCI Event: Command Complete (0x0e) plen 4                #58 [hci0] 13.339939
      LE Clear White List (0x08|0x0010) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Read Resolving L.. (0x08|0x002a) plen 0  #59 [hci0] 13.340152
> HCI Event: Command Complete (0x0e) plen 5                #60 [hci0] 13.340952
      LE Read Resolving List Size (0x08|0x002a) ncmd 1
        Status: Success (0x00)
        Size: 25
< HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0  #61 [hci0] 13.341180
> HCI Event: Command Complete (0x0e) plen 12               #62 [hci0] 13.341898
      LE Read Maximum Data Length (0x08|0x002f) ncmd 1
        Status: Success (0x00)
        Max TX octets: 251
        Max TX time: 17040
        Max RX octets: 251
        Max RX time: 17040

Signed-off-by: Ankit Navik <ankit.p.navik@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      |  6 ++++++
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_core.c         |  8 ++++++++
 net/bluetooth/hci_debugfs.c      | 19 +++++++++++++++++++
 net/bluetooth/hci_event.c        | 18 ++++++++++++++++++
 5 files changed, 53 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 1668211297a9..484f24c7a415 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1490,6 +1490,12 @@ struct hci_cp_le_write_def_data_len {
 	__le16	tx_time;
 } __packed;
 
+#define HCI_OP_LE_READ_RESOLV_LIST_SIZE	0x202a
+struct hci_rp_le_read_resolv_list_size {
+	__u8	status;
+	__u8	size;
+} __packed;
+
 #define HCI_OP_LE_READ_MAX_DATA_LEN	0x202f
 struct hci_rp_le_read_max_data_len {
 	__u8	status;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 893bbbb5d2fa..409f49bd8338 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -221,6 +221,7 @@ struct hci_dev {
 	__u8		features[HCI_MAX_PAGES][8];
 	__u8		le_features[8];
 	__u8		le_white_list_size;
+	__u8		le_resolv_list_size;
 	__u8		le_states[8];
 	__u8		commands[64];
 	__u8		hci_ver;
@@ -367,6 +368,7 @@ struct hci_dev {
 	struct list_head	identity_resolving_keys;
 	struct list_head	remote_oob_data;
 	struct list_head	le_white_list;
+	struct list_head	le_resolv_list;
 	struct list_head	le_conn_params;
 	struct list_head	pend_le_conns;
 	struct list_head	pend_le_reports;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ee8ef1228263..036e14267d0a 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -714,6 +714,12 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 			hci_req_add(req, HCI_OP_LE_CLEAR_WHITE_LIST, 0, NULL);
 		}
 
+		if (hdev->commands[34] & 0x40) {
+			/* Read LE Resolving List Size */
+			hci_req_add(req, HCI_OP_LE_READ_RESOLV_LIST_SIZE,
+				    0, NULL);
+		}
+
 		if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) {
 			/* Read LE Maximum Data Length */
 			hci_req_add(req, HCI_OP_LE_READ_MAX_DATA_LEN, 0, NULL);
@@ -3017,6 +3023,7 @@ struct hci_dev *hci_alloc_dev(void)
 	INIT_LIST_HEAD(&hdev->identity_resolving_keys);
 	INIT_LIST_HEAD(&hdev->remote_oob_data);
 	INIT_LIST_HEAD(&hdev->le_white_list);
+	INIT_LIST_HEAD(&hdev->le_resolv_list);
 	INIT_LIST_HEAD(&hdev->le_conn_params);
 	INIT_LIST_HEAD(&hdev->pend_le_conns);
 	INIT_LIST_HEAD(&hdev->pend_le_reports);
@@ -3218,6 +3225,7 @@ void hci_unregister_dev(struct hci_dev *hdev)
 	hci_remote_oob_data_clear(hdev);
 	hci_adv_instances_clear(hdev);
 	hci_bdaddr_list_clear(&hdev->le_white_list);
+	hci_bdaddr_list_clear(&hdev->le_resolv_list);
 	hci_conn_params_clear_all(hdev);
 	hci_discovery_filter_clear(hdev);
 	hci_dev_unlock(hdev);
diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c
index 0d8ab5b3c177..51f5b1efc3a5 100644
--- a/net/bluetooth/hci_debugfs.c
+++ b/net/bluetooth/hci_debugfs.c
@@ -694,6 +694,21 @@ static int white_list_show(struct seq_file *f, void *ptr)
 
 DEFINE_SHOW_ATTRIBUTE(white_list);
 
+static int resolv_list_show(struct seq_file *f, void *ptr)
+{
+	struct hci_dev *hdev = f->private;
+	struct bdaddr_list *b;
+
+	hci_dev_lock(hdev);
+	list_for_each_entry(b, &hdev->le_resolv_list, list)
+		seq_printf(f, "%pMR (type %u)\n", &b->bdaddr, b->bdaddr_type);
+	hci_dev_unlock(hdev);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(resolv_list);
+
 static int identity_resolving_keys_show(struct seq_file *f, void *ptr)
 {
 	struct hci_dev *hdev = f->private;
@@ -955,6 +970,10 @@ void hci_debugfs_create_le(struct hci_dev *hdev)
 			  &hdev->le_white_list_size);
 	debugfs_create_file("white_list", 0444, hdev->debugfs, hdev,
 			    &white_list_fops);
+	debugfs_create_u8("resolv_list_size", 0444, hdev->debugfs,
+			  &hdev->le_resolv_list_size);
+	debugfs_create_file("resolv_list", 0444, hdev->debugfs, hdev,
+			    &resolv_list_fops);
 	debugfs_create_file("identity_resolving_keys", 0400, hdev->debugfs,
 			    hdev, &identity_resolving_keys_fops);
 	debugfs_create_file("long_term_keys", 0400, hdev->debugfs, hdev,
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 235b5aaab23d..6ee69a79258f 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -221,6 +221,7 @@ static void hci_cc_reset(struct hci_dev *hdev, struct sk_buff *skb)
 	hdev->ssp_debug_mode = 0;
 
 	hci_bdaddr_list_clear(&hdev->le_white_list);
+	hci_bdaddr_list_clear(&hdev->le_resolv_list);
 }
 
 static void hci_cc_read_stored_link_key(struct hci_dev *hdev,
@@ -1306,6 +1307,19 @@ static void hci_cc_le_write_def_data_len(struct hci_dev *hdev,
 	hdev->le_def_tx_time = le16_to_cpu(sent->tx_time);
 }
 
+static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev,
+					   struct sk_buff *skb)
+{
+	struct hci_rp_le_read_resolv_list_size *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x size %u", hdev->name, rp->status, rp->size);
+
+	if (rp->status)
+		return;
+
+	hdev->le_resolv_list_size = rp->size;
+}
+
 static void hci_cc_le_read_max_data_len(struct hci_dev *hdev,
 					struct sk_buff *skb)
 {
@@ -3015,6 +3029,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_write_def_data_len(hdev, skb);
 		break;
 
+	case HCI_OP_LE_READ_RESOLV_LIST_SIZE:
+		hci_cc_le_read_resolv_list_size(hdev, skb);
+		break;
+
 	case HCI_OP_LE_READ_MAX_DATA_LEN:
 		hci_cc_le_read_max_data_len(hdev, skb);
 		break;
-- 
cgit v1.2.3


From 545f2596b907f0747170c7cb71edc74cecf68c5c Mon Sep 17 00:00:00 2001
From: Ankit Navik <ankit.p.navik@intel.com>
Date: Fri, 29 Jun 2018 12:13:20 +0530
Subject: Bluetooth: Add HCI command for clear Resolv list

Check for Resolv list supported by controller. So check the supported
commmand first before issuing this command i.e.,HCI_OP_LE_CLEAR_RESOLV_LIST

Before patch:
< HCI Command: LE Read White List... (0x08|0x000f) plen 0  #55 [hci0] 13.338168
> HCI Event: Command Complete (0x0e) plen 5                #56 [hci0] 13.338842
      LE Read White List Size (0x08|0x000f) ncmd 1
        Status: Success (0x00)
        Size: 25
< HCI Command: LE Clear White List (0x08|0x0010) plen 0    #57 [hci0] 13.339029
> HCI Event: Command Complete (0x0e) plen 4                #58 [hci0] 13.339939
      LE Clear White List (0x08|0x0010) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Read Resolving L.. (0x08|0x002a) plen 0  #59 [hci0] 13.340152
> HCI Event: Command Complete (0x0e) plen 5                #60 [hci0] 13.340952
      LE Read Resolving List Size (0x08|0x002a) ncmd 1
        Status: Success (0x00)
        Size: 25
< HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0  #61 [hci0] 13.341180
> HCI Event: Command Complete (0x0e) plen 12               #62 [hci0] 13.341898
      LE Read Maximum Data Length (0x08|0x002f) ncmd 1
        Status: Success (0x00)
        Max TX octets: 251
        Max TX time: 17040
        Max RX octets: 251
        Max RX time: 17040

After patch:
< HCI Command: LE Read White List... (0x08|0x000f) plen 0  #55 [hci0] 28.919131
> HCI Event: Command Complete (0x0e) plen 5                #56 [hci0] 28.920016
      LE Read White List Size (0x08|0x000f) ncmd 1
        Status: Success (0x00)
        Size: 25
< HCI Command: LE Clear White List (0x08|0x0010) plen 0    #57 [hci0] 28.920164
> HCI Event: Command Complete (0x0e) plen 4                #58 [hci0] 28.920873
      LE Clear White List (0x08|0x0010) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Read Resolving L.. (0x08|0x002a) plen 0  #59 [hci0] 28.921109
> HCI Event: Command Complete (0x0e) plen 5                #60 [hci0] 28.922016
      LE Read Resolving List Size (0x08|0x002a) ncmd 1
        Status: Success (0x00)
        Size: 25
< HCI Command: LE Clear Resolving... (0x08|0x0029) plen 0  #61 [hci0] 28.922166
> HCI Event: Command Complete (0x0e) plen 4                #62 [hci0] 28.922872
      LE Clear Resolving List (0x08|0x0029) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Read Maximum Dat.. (0x08|0x002f) plen 0  #63 [hci0] 28.923117
> HCI Event: Command Complete (0x0e) plen 12               #64 [hci0] 28.924030
      LE Read Maximum Data Length (0x08|0x002f) ncmd 1
        Status: Success (0x00)
        Max TX octets: 251
        Max TX time: 17040
        Max RX octets: 251
        Max RX time: 17040

Signed-off-by: Ankit Navik <ankit.p.navik@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  2 ++
 net/bluetooth/hci_core.c    |  5 +++++
 net/bluetooth/hci_event.c   | 17 +++++++++++++++++
 3 files changed, 24 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 484f24c7a415..4af1a3a4d9b1 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1490,6 +1490,8 @@ struct hci_cp_le_write_def_data_len {
 	__le16	tx_time;
 } __packed;
 
+#define HCI_OP_LE_CLEAR_RESOLV_LIST	0x2029
+
 #define HCI_OP_LE_READ_RESOLV_LIST_SIZE	0x202a
 struct hci_rp_le_read_resolv_list_size {
 	__u8	status;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 036e14267d0a..ce2447d89ce1 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -720,6 +720,11 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 				    0, NULL);
 		}
 
+		if (hdev->commands[34] & 0x20) {
+			/* Clear LE Resolving List */
+			hci_req_add(req, HCI_OP_LE_CLEAR_RESOLV_LIST, 0, NULL);
+		}
+
 		if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) {
 			/* Read LE Maximum Data Length */
 			hci_req_add(req, HCI_OP_LE_READ_MAX_DATA_LEN, 0, NULL);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6ee69a79258f..562e7a854ed6 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1307,6 +1307,19 @@ static void hci_cc_le_write_def_data_len(struct hci_dev *hdev,
 	hdev->le_def_tx_time = le16_to_cpu(sent->tx_time);
 }
 
+static void hci_cc_le_clear_resolv_list(struct hci_dev *hdev,
+				       struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	hci_bdaddr_list_clear(&hdev->le_resolv_list);
+}
+
 static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev,
 					   struct sk_buff *skb)
 {
@@ -3029,6 +3042,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_write_def_data_len(hdev, skb);
 		break;
 
+	case HCI_OP_LE_CLEAR_RESOLV_LIST:
+		hci_cc_le_clear_resolv_list(hdev, skb);
+		break;
+
 	case HCI_OP_LE_READ_RESOLV_LIST_SIZE:
 		hci_cc_le_read_resolv_list_size(hdev, skb);
 		break;
-- 
cgit v1.2.3


From 1b0707a781eeaeeaacb464e18bb3f049b99b496b Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Thu, 7 Jun 2018 19:50:38 +0000
Subject: Bluetooth: remove unused bt-nokia-h4p.h header

Nothing in tree use this header which seems a remains of a staging
driver.
This patch remove it.

Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/linux/platform_data/bt-nokia-h4p.h | 38 ------------------------------
 1 file changed, 38 deletions(-)
 delete mode 100644 include/linux/platform_data/bt-nokia-h4p.h

diff --git a/include/linux/platform_data/bt-nokia-h4p.h b/include/linux/platform_data/bt-nokia-h4p.h
deleted file mode 100644
index 30d169dfadf3..000000000000
--- a/include/linux/platform_data/bt-nokia-h4p.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/*
- * This file is part of Nokia H4P bluetooth driver
- *
- * Copyright (C) 2010 Nokia Corporation.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
- * 02110-1301 USA
- *
- */
-
-
-/**
- * struct hci_h4p_platform data - hci_h4p Platform data structure
- */
-struct hci_h4p_platform_data {
-	int chip_type;
-	int bt_sysclk;
-	unsigned int bt_wakeup_gpio;
-	unsigned int host_wakeup_gpio;
-	unsigned int reset_gpio;
-	int reset_gpio_shared;
-	unsigned int uart_irq;
-	phys_addr_t uart_base;
-	const char *uart_iclk;
-	const char *uart_fclk;
-	void (*set_pm_limits)(struct device *dev, bool set);
-};
-- 
cgit v1.2.3


From 91a2968e245d6ba616db37001fa1a043078b1a65 Mon Sep 17 00:00:00 2001
From: Zachary Zhang <zhangzg@marvell.com>
Date: Fri, 29 Jun 2018 11:16:19 +0200
Subject: PCI: aardvark: Size bridges before resources allocation

The PCIE I/O and MEM resource allocation mechanism is that root bus
goes through the following steps:

1. Check PCI bridges' range and computes I/O and Mem base/limits.

2. Sort all subordinate devices I/O and MEM resource requirements and
   allocate the resources and writes/updates subordinate devices'
   requirements to PCI bridges I/O and Mem MEM/limits registers.

Currently, PCI Aardvark driver only handles the second step and lacks
the first step, so there is an I/O and MEM resource allocation failure
when using a PCI switch. This commit fixes that by sizing bridges
before doing the resource allocation.

Fixes: 8c39d710363c1 ("PCI: aardvark: Add Aardvark PCI host controller
driver")
Signed-off-by: Zachary Zhang <zhangzg@marvell.com>
[Thomas: edit commit log.]
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: <stable@vger.kernel.org>
---
 drivers/pci/controller/pci-aardvark.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index c9c72595bd20..10543ed7b500 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -906,6 +906,7 @@ static int advk_pcie_probe(struct platform_device *pdev)
 
 	bus = bridge->bus;
 
+	pci_bus_size_bridges(bus);
 	pci_bus_assign_resources(bus);
 
 	list_for_each_entry(child, &bus->children, node)
-- 
cgit v1.2.3


From c8e144f8ab00e6c4a070a932ef9c57db09aa41cf Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 29 Jun 2018 11:16:20 +0200
Subject: PCI: aardvark: Convert to use pci_host_probe()

Part of advk_pcie_probe() is exactly an open-coded version of
pci_host_probe(). So instead of duplicating this code, use
pci_host_probe() directly.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
[lorenzo.pieralisi@arm.com: updated commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-aardvark.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 10543ed7b500..d5030cd06197 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -843,7 +843,6 @@ static int advk_pcie_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct advk_pcie *pcie;
 	struct resource *res;
-	struct pci_bus *bus, *child;
 	struct pci_host_bridge *bridge;
 	int ret, irq;
 
@@ -897,22 +896,13 @@ static int advk_pcie_probe(struct platform_device *pdev)
 	bridge->map_irq = of_irq_parse_and_map_pci;
 	bridge->swizzle_irq = pci_common_swizzle;
 
-	ret = pci_scan_root_bus_bridge(bridge);
+	ret = pci_host_probe(bridge);
 	if (ret < 0) {
 		advk_pcie_remove_msi_irq_domain(pcie);
 		advk_pcie_remove_irq_domain(pcie);
 		return ret;
 	}
 
-	bus = bridge->bus;
-
-	pci_bus_size_bridges(bus);
-	pci_bus_assign_resources(bus);
-
-	list_for_each_entry(child, &bus->children, node)
-		pcie_bus_configure_settings(child);
-
-	pci_bus_add_devices(bus);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 05f2d2f83b5a02a15b6538017f29ee53a73088fb Mon Sep 17 00:00:00 2001
From: Chintan Pandya <cpandya@codeaurora.org>
Date: Wed, 6 Jun 2018 12:31:20 +0530
Subject: arm64: tlbflush: Introduce __flush_tlb_kernel_pgtable

Add an interface to invalidate intermediate page tables
from TLB for kernel.

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Chintan Pandya <cpandya@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/tlbflush.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index dfc61d73f740..a4a1901140ee 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -218,6 +218,13 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 	dsb(ish);
 }
 
+static inline void __flush_tlb_kernel_pgtable(unsigned long kaddr)
+{
+	unsigned long addr = __TLBI_VADDR(kaddr, 0);
+
+	__tlbi(vaae1is, addr);
+	dsb(ish);
+}
 #endif
 
 #endif
-- 
cgit v1.2.3


From ec28bb9c9b0826d7bd36f44cccfa5295c291cadd Mon Sep 17 00:00:00 2001
From: Chintan Pandya <cpandya@codeaurora.org>
Date: Wed, 6 Jun 2018 12:31:21 +0530
Subject: arm64: Implement page table free interfaces

arm64 requires break-before-make. Originally, before
setting up new pmd/pud entry for huge mapping, in few
cases, the modifying pmd/pud entry was still valid
and pointing to next level page table as we only
clear off leaf PTE in unmap leg.

 a) This was resulting into stale entry in TLBs (as few
    TLBs also cache intermediate mapping for performance
    reasons)
 b) Also, modifying pmd/pud was the only reference to
    next level page table and it was getting lost without
    freeing it. So, page leaks were happening.

Implement pud_free_pmd_page() and pmd_free_pte_page() to
enforce BBM and also free the leaking page tables.

Implementation requires,
 1) Clearing off the current pud/pmd entry
 2) Invalidation of TLB
 3) Freeing of the un-used next level page tables

Reviewed-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Chintan Pandya <cpandya@codeaurora.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/mm/mmu.c | 48 ++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 8ae5d7ae4af3..65f86271f02b 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -45,6 +45,7 @@
 #include <asm/memblock.h>
 #include <asm/mmu_context.h>
 #include <asm/ptdump.h>
+#include <asm/tlbflush.h>
 
 #define NO_BLOCK_MAPPINGS	BIT(0)
 #define NO_CONT_MAPPINGS	BIT(1)
@@ -977,12 +978,51 @@ int pmd_clear_huge(pmd_t *pmdp)
 	return 1;
 }
 
-int pud_free_pmd_page(pud_t *pud, unsigned long addr)
+int pmd_free_pte_page(pmd_t *pmdp, unsigned long addr)
 {
-	return pud_none(*pud);
+	pte_t *table;
+	pmd_t pmd;
+
+	pmd = READ_ONCE(*pmdp);
+
+	/* No-op for empty entry and WARN_ON for valid entry */
+	if (!pmd_present(pmd) || !pmd_table(pmd)) {
+		VM_WARN_ON(!pmd_table(pmd));
+		return 1;
+	}
+
+	table = pte_offset_kernel(pmdp, addr);
+	pmd_clear(pmdp);
+	__flush_tlb_kernel_pgtable(addr);
+	pte_free_kernel(NULL, table);
+	return 1;
 }
 
-int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
+int pud_free_pmd_page(pud_t *pudp, unsigned long addr)
 {
-	return pmd_none(*pmd);
+	pmd_t *table;
+	pmd_t *pmdp;
+	pud_t pud;
+	unsigned long next, end;
+
+	pud = READ_ONCE(*pudp);
+
+	/* No-op for empty entry and WARN_ON for valid entry */
+	if (!pud_present(pud) || !pud_table(pud)) {
+		VM_WARN_ON(!pud_table(pud));
+		return 1;
+	}
+
+	table = pmd_offset(pudp, addr);
+	pmdp = table;
+	next = addr;
+	end = addr + PUD_SIZE;
+	do {
+		pmd_free_pte_page(pmdp, next);
+	} while (pmdp++, next += PMD_SIZE, next != end);
+
+	pud_clear(pudp);
+	__flush_tlb_kernel_pgtable(addr);
+	pmd_free(NULL, table);
+	return 1;
 }
-- 
cgit v1.2.3


From 178909a669584b97e9154375df2126fd93b6306c Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Fri, 6 Jul 2018 09:57:45 +0100
Subject: arm64: errata: Don't define type field twice for arm64_errata[]
 entries

The ERRATA_MIDR_REV_RANGE macro assigns ARM64_CPUCAP_LOCAL_CPU_ERRATUM
to the '.type' field of the 'struct arm64_cpu_capabilities', so there's
no need to assign it explicitly as well.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/cpu_errata.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 459129712dfa..94876ab071c7 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -662,7 +662,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_HARDEN_BRANCH_PREDICTOR
 	{
 		.capability = ARM64_HARDEN_BRANCH_PREDICTOR,
-		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.cpu_enable = enable_smccc_arch_workaround_1,
 		ERRATA_MIDR_RANGE_LIST(arm64_bp_harden_smccc_cpus),
 	},
@@ -671,7 +670,6 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 	{
 		.desc = "EL2 vector hardening",
 		.capability = ARM64_HARDEN_EL2_VECTORS,
-		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		ERRATA_MIDR_RANGE_LIST(arm64_harden_el2_vectors),
 	},
 #endif
-- 
cgit v1.2.3


From 31b46035576d405ca9a98be95945986c91986368 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 6 Jul 2018 12:02:42 +0100
Subject: arm64: topology: refactor reset_cpu_topology to add support for
 removing topology

Currently reset_cpu_topology clears all the CPU topology information
and resets to default values. However we may need to just clear the
information when we hotplug out the CPU. In preparation to add the
support the same, let's refactor reset_cpu_topology to just reset
the information and move clearing out the topology information to
clear_cpu_topology.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/topology.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index f845a8617812..b64733c5ea28 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -293,6 +293,19 @@ topology_populated:
 	update_siblings_masks(cpuid);
 }
 
+static void clear_cpu_topology(int cpu)
+{
+	struct cpu_topology *cpu_topo = &cpu_topology[cpu];
+
+	cpumask_clear(&cpu_topo->llc_siblings);
+	cpumask_set_cpu(cpu, &cpu_topo->llc_siblings);
+
+	cpumask_clear(&cpu_topo->core_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
+	cpumask_clear(&cpu_topo->thread_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+}
+
 static void __init reset_cpu_topology(void)
 {
 	unsigned int cpu;
@@ -303,15 +316,9 @@ static void __init reset_cpu_topology(void)
 		cpu_topo->thread_id = -1;
 		cpu_topo->core_id = 0;
 		cpu_topo->package_id = -1;
-
 		cpu_topo->llc_id = -1;
-		cpumask_clear(&cpu_topo->llc_siblings);
-		cpumask_set_cpu(cpu, &cpu_topo->llc_siblings);
 
-		cpumask_clear(&cpu_topo->core_sibling);
-		cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
-		cpumask_clear(&cpu_topo->thread_sibling);
-		cpumask_set_cpu(cpu, &cpu_topo->thread_sibling);
+		clear_cpu_topology(cpu);
 	}
 }
 
-- 
cgit v1.2.3


From 97fd6016a7b3df00901b4cfdd883eac01e89fa8a Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 6 Jul 2018 12:02:43 +0100
Subject: arm64: numa: separate out updates to percpu nodeid and NUMA node
 cpumap

Currently numa_clear_node removes both cpu information from the NUMA
node cpumap as well as the NUMA node id from the cpu. Similarly
numa_store_cpu_info updates both percpu nodeid and NUMA cpumap.

However we need to retain the numa node id for the cpu and only remove
the cpu information from the numa node cpumap during CPU hotplug out.
The same can be extended for hotplugging in the CPU.

This patch separates out numa_{add,remove}_cpu from numa_clear_node and
numa_store_cpu_info.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Reviewed-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/numa.h |  4 ++++
 arch/arm64/kernel/smp.c       |  2 ++
 arch/arm64/mm/numa.c          | 29 +++++++++++++++++++++--------
 3 files changed, 27 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/numa.h b/arch/arm64/include/asm/numa.h
index 01bc46d5b43a..626ad01e83bf 100644
--- a/arch/arm64/include/asm/numa.h
+++ b/arch/arm64/include/asm/numa.h
@@ -35,10 +35,14 @@ void __init numa_set_distance(int from, int to, int distance);
 void __init numa_free_distance(void);
 void __init early_map_cpu_to_node(unsigned int cpu, int nid);
 void numa_store_cpu_info(unsigned int cpu);
+void numa_add_cpu(unsigned int cpu);
+void numa_remove_cpu(unsigned int cpu);
 
 #else	/* CONFIG_NUMA */
 
 static inline void numa_store_cpu_info(unsigned int cpu) { }
+static inline void numa_add_cpu(unsigned int cpu) { }
+static inline void numa_remove_cpu(unsigned int cpu) { }
 static inline void arm64_numa_init(void) { }
 static inline void early_map_cpu_to_node(unsigned int cpu, int nid) { }
 
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2faa9863d2e5..2a315f32fad3 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -225,6 +225,7 @@ asmlinkage notrace void secondary_start_kernel(void)
 	notify_cpu_starting(cpu);
 
 	store_cpu_topology(cpu);
+	numa_add_cpu(cpu);
 
 	/*
 	 * OK, now it's safe to let the boot CPU continue.  Wait for
@@ -679,6 +680,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	this_cpu = smp_processor_id();
 	store_cpu_topology(this_cpu);
 	numa_store_cpu_info(this_cpu);
+	numa_add_cpu(this_cpu);
 
 	/*
 	 * If UP is mandated by "nosmp" (which implies "maxcpus=0"), don't set
diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c
index dad128ba98bf..146c04ceaa51 100644
--- a/arch/arm64/mm/numa.c
+++ b/arch/arm64/mm/numa.c
@@ -70,19 +70,32 @@ EXPORT_SYMBOL(cpumask_of_node);
 
 #endif
 
-static void map_cpu_to_node(unsigned int cpu, int nid)
+static void numa_update_cpu(unsigned int cpu, bool remove)
 {
-	set_cpu_numa_node(cpu, nid);
-	if (nid >= 0)
+	int nid = cpu_to_node(cpu);
+
+	if (nid == NUMA_NO_NODE)
+		return;
+
+	if (remove)
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+	else
 		cpumask_set_cpu(cpu, node_to_cpumask_map[nid]);
 }
 
-void numa_clear_node(unsigned int cpu)
+void numa_add_cpu(unsigned int cpu)
 {
-	int nid = cpu_to_node(cpu);
+	numa_update_cpu(cpu, false);
+}
 
-	if (nid >= 0)
-		cpumask_clear_cpu(cpu, node_to_cpumask_map[nid]);
+void numa_remove_cpu(unsigned int cpu)
+{
+	numa_update_cpu(cpu, true);
+}
+
+void numa_clear_node(unsigned int cpu)
+{
+	numa_remove_cpu(cpu);
 	set_cpu_numa_node(cpu, NUMA_NO_NODE);
 }
 
@@ -116,7 +129,7 @@ static void __init setup_node_to_cpumask_map(void)
  */
 void numa_store_cpu_info(unsigned int cpu)
 {
-	map_cpu_to_node(cpu, cpu_to_node_map[cpu]);
+	set_cpu_numa_node(cpu, cpu_to_node_map[cpu]);
 }
 
 void __init early_map_cpu_to_node(unsigned int cpu, int nid)
-- 
cgit v1.2.3


From 5bdd2b3f0f8830f281bb568e65df6eabf655dd0d Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 6 Jul 2018 12:02:44 +0100
Subject: arm64: topology: add support to remove cpu topology sibling masks

This patch adds support to remove all the CPU topology information using
clear_cpu_topology and also resetting the sibling information on other
sibling CPUs. This will be used in cpu_disable so that all the topology
sibling information is removed on CPU hotplug out.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/topology.h |  2 ++
 arch/arm64/kernel/topology.c      | 14 ++++++++++++++
 2 files changed, 16 insertions(+)

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index df48212f767b..4c073d28f9e4 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -20,9 +20,11 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
+#define topology_llc_cpumask(cpu)	(&cpu_topology[cpu].llc_siblings)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
+void remove_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef CONFIG_NUMA
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index b64733c5ea28..cb81df545359 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -322,6 +322,20 @@ static void __init reset_cpu_topology(void)
 	}
 }
 
+void remove_cpu_topology(unsigned int cpu)
+{
+	int sibling;
+
+	for_each_cpu(sibling, topology_core_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_core_cpumask(sibling));
+	for_each_cpu(sibling, topology_sibling_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_sibling_cpumask(sibling));
+	for_each_cpu(sibling, topology_llc_cpumask(cpu))
+		cpumask_clear_cpu(cpu, topology_llc_cpumask(sibling));
+
+	clear_cpu_topology(cpu);
+}
+
 #ifdef CONFIG_ACPI
 /*
  * Propagate the topology information of the processor_topology_node tree to the
-- 
cgit v1.2.3


From 5ec8b59172b4e8d26a12952ce3a2914b30128538 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 6 Jul 2018 12:02:45 +0100
Subject: arm64: topology: restrict updating siblings_masks to online cpus only

It's incorrect to iterate over all the possible CPUs to update the
sibling masks when any CPU is hotplugged in. In case the topology
siblings masks of the CPU is removed when is it hotplugged out, we
end up updating those masks when one of it's sibling is powered up
again. This will provide inconsistent view.

Further, since the CPU calling update_sibling_masks is yet to be set
online, there's no need to compare itself with each online CPU when
updating the siblings masks.

This patch restricts updation of sibling masks only for CPUs that are
already online. It also the drops the unnecessary cpuid check.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/topology.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index cb81df545359..1a3f8ab455d0 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -231,7 +231,7 @@ static void update_siblings_masks(unsigned int cpuid)
 	int cpu;
 
 	/* update core and thread sibling masks */
-	for_each_possible_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		cpu_topo = &cpu_topology[cpu];
 
 		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
@@ -243,15 +243,13 @@ static void update_siblings_masks(unsigned int cpuid)
 			continue;
 
 		cpumask_set_cpu(cpuid, &cpu_topo->core_sibling);
-		if (cpu != cpuid)
-			cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->core_sibling);
 
 		if (cpuid_topo->core_id != cpu_topo->core_id)
 			continue;
 
 		cpumask_set_cpu(cpuid, &cpu_topo->thread_sibling);
-		if (cpu != cpuid)
-			cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
+		cpumask_set_cpu(cpu, &cpuid_topo->thread_sibling);
 	}
 }
 
-- 
cgit v1.2.3


From 7f9545aa1a91a9a4dc8c3e1476dbbfa98dd38b81 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 6 Jul 2018 12:02:46 +0100
Subject: arm64: smp: remove cpu and numa topology information when hotplugging
 out CPU

We already repopulate the information on CPU hotplug-in, so we can safely
remove the CPU topology and NUMA cpumap information during CPU hotplug
out operation. This will help to provide the correct cpumask for
scheduler domains.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/smp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2a315f32fad3..a44cc09059b5 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -279,6 +279,9 @@ int __cpu_disable(void)
 	if (ret)
 		return ret;
 
+	remove_cpu_topology(cpu);
+	numa_remove_cpu(cpu);
+
 	/*
 	 * Take this CPU offline.  Once we clear this, we can't return,
 	 * and we must not schedule until we're ready to give up the cpu.
-- 
cgit v1.2.3


From f70ff1271378b12570aa3c4ebe2ad07f35a4ec51 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 6 Jul 2018 12:02:47 +0100
Subject: arm64: topology: rename llc_siblings to align with other struct
 members

Similar to core_sibling and thread_sibling, it's better to align and
rename llc_siblings to llc_sibling.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/topology.h |  4 ++--
 arch/arm64/kernel/topology.c      | 12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h
index 4c073d28f9e4..49a0fee4f89b 100644
--- a/arch/arm64/include/asm/topology.h
+++ b/arch/arm64/include/asm/topology.h
@@ -11,7 +11,7 @@ struct cpu_topology {
 	int llc_id;
 	cpumask_t thread_sibling;
 	cpumask_t core_sibling;
-	cpumask_t llc_siblings;
+	cpumask_t llc_sibling;
 };
 
 extern struct cpu_topology cpu_topology[NR_CPUS];
@@ -20,7 +20,7 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_core_id(cpu)		(cpu_topology[cpu].core_id)
 #define topology_core_cpumask(cpu)	(&cpu_topology[cpu].core_sibling)
 #define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
-#define topology_llc_cpumask(cpu)	(&cpu_topology[cpu].llc_siblings)
+#define topology_llc_cpumask(cpu)	(&cpu_topology[cpu].llc_sibling)
 
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 1a3f8ab455d0..03b0ed2480aa 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -218,8 +218,8 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	const cpumask_t *core_mask = &cpu_topology[cpu].core_sibling;
 
 	if (cpu_topology[cpu].llc_id != -1) {
-		if (cpumask_subset(&cpu_topology[cpu].llc_siblings, core_mask))
-			core_mask = &cpu_topology[cpu].llc_siblings;
+		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
+			core_mask = &cpu_topology[cpu].llc_sibling;
 	}
 
 	return core_mask;
@@ -235,8 +235,8 @@ static void update_siblings_masks(unsigned int cpuid)
 		cpu_topo = &cpu_topology[cpu];
 
 		if (cpuid_topo->llc_id == cpu_topo->llc_id) {
-			cpumask_set_cpu(cpu, &cpuid_topo->llc_siblings);
-			cpumask_set_cpu(cpuid, &cpu_topo->llc_siblings);
+			cpumask_set_cpu(cpu, &cpuid_topo->llc_sibling);
+			cpumask_set_cpu(cpuid, &cpu_topo->llc_sibling);
 		}
 
 		if (cpuid_topo->package_id != cpu_topo->package_id)
@@ -295,8 +295,8 @@ static void clear_cpu_topology(int cpu)
 {
 	struct cpu_topology *cpu_topo = &cpu_topology[cpu];
 
-	cpumask_clear(&cpu_topo->llc_siblings);
-	cpumask_set_cpu(cpu, &cpu_topo->llc_siblings);
+	cpumask_clear(&cpu_topo->llc_sibling);
+	cpumask_set_cpu(cpu, &cpu_topo->llc_sibling);
 
 	cpumask_clear(&cpu_topo->core_sibling);
 	cpumask_set_cpu(cpu, &cpu_topo->core_sibling);
-- 
cgit v1.2.3


From e67ecf647020d31342d37e73c3766ae02434ed24 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Fri, 6 Jul 2018 12:02:48 +0100
Subject: arm64: topology: re-introduce numa mask check for scheduler MC
 selection

Commit 37c3ec2d810f ("arm64: topology: divorce MC scheduling domain from
core_siblings") selected the smallest of LLC, socket siblings, and NUMA
node siblings to ensure that the sched domain we build for the MC layer
isn't larger than the DIE above it or it's shrunk to the socket or NUMA
node if LLC exist acrosis NUMA node/chiplets.

Commit acd32e52e4e0 ("arm64: topology: Avoid checking numa mask for
scheduler MC selection") reverted the NUMA siblings checks since the
CPU topology masks weren't updated on hotplug at that time.

This patch re-introduces numa mask check as the CPU and NUMA topology
is now updated in hotplug paths. Effectively, this patch does the
partial revert of commit acd32e52e4e0.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Tested-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Tested-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/topology.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 03b0ed2480aa..0825c4a856e3 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -215,8 +215,13 @@ EXPORT_SYMBOL_GPL(cpu_topology);
 
 const struct cpumask *cpu_coregroup_mask(int cpu)
 {
-	const cpumask_t *core_mask = &cpu_topology[cpu].core_sibling;
+	const cpumask_t *core_mask = cpumask_of_node(cpu_to_node(cpu));
 
+	/* Find the smaller of NUMA, core or LLC siblings */
+	if (cpumask_subset(&cpu_topology[cpu].core_sibling, core_mask)) {
+		/* not numa in package, lets use the package siblings */
+		core_mask = &cpu_topology[cpu].core_sibling;
+	}
 	if (cpu_topology[cpu].llc_id != -1) {
 		if (cpumask_subset(&cpu_topology[cpu].llc_sibling, core_mask))
 			core_mask = &cpu_topology[cpu].llc_sibling;
-- 
cgit v1.2.3


From 6cc42152b02b3f73969934b63332d47e2dac55e4 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Thu, 28 Jun 2018 09:23:02 +0200
Subject: drm/i915: Remove support for legacy debugfs crc interface
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This interface is deprecated, and has been replaced by the upstream
drm crc interface.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: Tomi Sarvela <tomi.p.sarvela@intel.com>
Cc: Petri Latvala <petri.latvala@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628072303.14175-1-maarten.lankhorst@linux.intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c   |   7 +-
 drivers/gpu/drm/i915/i915_drv.h       |  11 +-
 drivers/gpu/drm/i915/i915_irq.c       |  79 ++----
 drivers/gpu/drm/i915/intel_drv.h      |   2 -
 drivers/gpu/drm/i915/intel_pipe_crc.c | 445 ----------------------------------
 5 files changed, 24 insertions(+), 520 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index f6142d78ede4..544e5e7f011f 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4818,7 +4818,6 @@ static const struct i915_debugfs_files {
 #endif
 	{"i915_fifo_underrun_reset", &i915_fifo_underrun_reset_ops},
 	{"i915_next_seqno", &i915_next_seqno_fops},
-	{"i915_display_crc_ctl", &i915_display_crc_ctl_fops},
 	{"i915_pri_wm_latency", &i915_pri_wm_latency_fops},
 	{"i915_spr_wm_latency", &i915_spr_wm_latency_fops},
 	{"i915_cur_wm_latency", &i915_cur_wm_latency_fops},
@@ -4838,7 +4837,7 @@ int i915_debugfs_register(struct drm_i915_private *dev_priv)
 {
 	struct drm_minor *minor = dev_priv->drm.primary;
 	struct dentry *ent;
-	int ret, i;
+	int i;
 
 	ent = debugfs_create_file("i915_forcewake_user", S_IRUSR,
 				  minor->debugfs_root, to_i915(minor->dev),
@@ -4846,10 +4845,6 @@ int i915_debugfs_register(struct drm_i915_private *dev_priv)
 	if (!ent)
 		return -ENOMEM;
 
-	ret = intel_pipe_crc_create(minor);
-	if (ret)
-		return ret;
-
 	for (i = 0; i < ARRAY_SIZE(i915_debugfs_files); i++) {
 		ent = debugfs_create_file(i915_debugfs_files[i].name,
 					  S_IRUGO | S_IWUSR,
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e236016eef7b..8a2196e4262b 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1271,20 +1271,11 @@ enum intel_pipe_crc_source {
 	INTEL_PIPE_CRC_SOURCE_MAX,
 };
 
-struct intel_pipe_crc_entry {
-	uint32_t frame;
-	uint32_t crc[5];
-};
-
 #define INTEL_PIPE_CRC_ENTRIES_NR	128
 struct intel_pipe_crc {
 	spinlock_t lock;
-	bool opened;		/* exclusive access to the result file */
-	struct intel_pipe_crc_entry *entries;
-	enum intel_pipe_crc_source source;
-	int head, tail;
-	wait_queue_head_t wq;
 	int skipped;
+	enum intel_pipe_crc_source source;
 };
 
 struct i915_frontbuffer_tracking {
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 2fcc00b06915..495b9d27990e 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1751,69 +1751,34 @@ static void display_pipe_crc_irq_handler(struct drm_i915_private *dev_priv,
 					 uint32_t crc4)
 {
 	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
-	struct intel_pipe_crc_entry *entry;
 	struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv, pipe);
-	struct drm_driver *driver = dev_priv->drm.driver;
 	uint32_t crcs[5];
-	int head, tail;
 
 	spin_lock(&pipe_crc->lock);
-	if (pipe_crc->source && !crtc->base.crc.opened) {
-		if (!pipe_crc->entries) {
-			spin_unlock(&pipe_crc->lock);
-			DRM_DEBUG_KMS("spurious interrupt\n");
-			return;
-		}
-
-		head = pipe_crc->head;
-		tail = pipe_crc->tail;
-
-		if (CIRC_SPACE(head, tail, INTEL_PIPE_CRC_ENTRIES_NR) < 1) {
-			spin_unlock(&pipe_crc->lock);
-			DRM_ERROR("CRC buffer overflowing\n");
-			return;
-		}
-
-		entry = &pipe_crc->entries[head];
-
-		entry->frame = driver->get_vblank_counter(&dev_priv->drm, pipe);
-		entry->crc[0] = crc0;
-		entry->crc[1] = crc1;
-		entry->crc[2] = crc2;
-		entry->crc[3] = crc3;
-		entry->crc[4] = crc4;
-
-		head = (head + 1) & (INTEL_PIPE_CRC_ENTRIES_NR - 1);
-		pipe_crc->head = head;
-
-		spin_unlock(&pipe_crc->lock);
-
-		wake_up_interruptible(&pipe_crc->wq);
-	} else {
-		/*
-		 * For some not yet identified reason, the first CRC is
-		 * bonkers. So let's just wait for the next vblank and read
-		 * out the buggy result.
-		 *
-		 * On GEN8+ sometimes the second CRC is bonkers as well, so
-		 * don't trust that one either.
-		 */
-		if (pipe_crc->skipped <= 0 ||
-		    (INTEL_GEN(dev_priv) >= 8 && pipe_crc->skipped == 1)) {
-			pipe_crc->skipped++;
-			spin_unlock(&pipe_crc->lock);
-			return;
-		}
+	/*
+	 * For some not yet identified reason, the first CRC is
+	 * bonkers. So let's just wait for the next vblank and read
+	 * out the buggy result.
+	 *
+	 * On GEN8+ sometimes the second CRC is bonkers as well, so
+	 * don't trust that one either.
+	 */
+	if (pipe_crc->skipped <= 0 ||
+	    (INTEL_GEN(dev_priv) >= 8 && pipe_crc->skipped == 1)) {
+		pipe_crc->skipped++;
 		spin_unlock(&pipe_crc->lock);
-		crcs[0] = crc0;
-		crcs[1] = crc1;
-		crcs[2] = crc2;
-		crcs[3] = crc3;
-		crcs[4] = crc4;
-		drm_crtc_add_crc_entry(&crtc->base, true,
-				       drm_crtc_accurate_vblank_count(&crtc->base),
-				       crcs);
+		return;
 	}
+	spin_unlock(&pipe_crc->lock);
+
+	crcs[0] = crc0;
+	crcs[1] = crc1;
+	crcs[2] = crc2;
+	crcs[3] = crc3;
+	crcs[4] = crc4;
+	drm_crtc_add_crc_entry(&crtc->base, true,
+				drm_crtc_accurate_vblank_count(&crtc->base),
+				crcs);
 }
 #else
 static inline void
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 3034477b79ff..e283e9e901c2 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -2153,7 +2153,6 @@ void lspcon_resume(struct intel_lspcon *lspcon);
 void lspcon_wait_pcon_mode(struct intel_lspcon *lspcon);
 
 /* intel_pipe_crc.c */
-int intel_pipe_crc_create(struct drm_minor *minor);
 #ifdef CONFIG_DEBUG_FS
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
 			      size_t *values_cnt);
@@ -2169,5 +2168,4 @@ static inline void intel_crtc_enable_pipe_crc(struct intel_crtc *crtc)
 {
 }
 #endif
-extern const struct file_operations i915_display_crc_ctl_fops;
 #endif /* __INTEL_DRV_H__ */
diff --git a/drivers/gpu/drm/i915/intel_pipe_crc.c b/drivers/gpu/drm/i915/intel_pipe_crc.c
index 39a4e4edda07..849e1b69ba73 100644
--- a/drivers/gpu/drm/i915/intel_pipe_crc.c
+++ b/drivers/gpu/drm/i915/intel_pipe_crc.c
@@ -30,160 +30,6 @@
 #include <linux/debugfs.h>
 #include "intel_drv.h"
 
-struct pipe_crc_info {
-	const char *name;
-	struct drm_i915_private *dev_priv;
-	enum pipe pipe;
-};
-
-static int i915_pipe_crc_open(struct inode *inode, struct file *filep)
-{
-	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-
-	if (info->pipe >= INTEL_INFO(dev_priv)->num_pipes)
-		return -ENODEV;
-
-	spin_lock_irq(&pipe_crc->lock);
-
-	if (pipe_crc->opened) {
-		spin_unlock_irq(&pipe_crc->lock);
-		return -EBUSY; /* already open */
-	}
-
-	pipe_crc->opened = true;
-	filep->private_data = inode->i_private;
-
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return 0;
-}
-
-static int i915_pipe_crc_release(struct inode *inode, struct file *filep)
-{
-	struct pipe_crc_info *info = inode->i_private;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-
-	spin_lock_irq(&pipe_crc->lock);
-	pipe_crc->opened = false;
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return 0;
-}
-
-/* (6 fields, 8 chars each, space separated (5) + '\n') */
-#define PIPE_CRC_LINE_LEN	(6 * 8 + 5 + 1)
-/* account for \'0' */
-#define PIPE_CRC_BUFFER_LEN	(PIPE_CRC_LINE_LEN + 1)
-
-static int pipe_crc_data_count(struct intel_pipe_crc *pipe_crc)
-{
-	lockdep_assert_held(&pipe_crc->lock);
-	return CIRC_CNT(pipe_crc->head, pipe_crc->tail,
-			INTEL_PIPE_CRC_ENTRIES_NR);
-}
-
-static ssize_t
-i915_pipe_crc_read(struct file *filep, char __user *user_buf, size_t count,
-		   loff_t *pos)
-{
-	struct pipe_crc_info *info = filep->private_data;
-	struct drm_i915_private *dev_priv = info->dev_priv;
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[info->pipe];
-	char buf[PIPE_CRC_BUFFER_LEN];
-	int n_entries;
-	ssize_t bytes_read;
-
-	/*
-	 * Don't allow user space to provide buffers not big enough to hold
-	 * a line of data.
-	 */
-	if (count < PIPE_CRC_LINE_LEN)
-		return -EINVAL;
-
-	if (pipe_crc->source == INTEL_PIPE_CRC_SOURCE_NONE)
-		return 0;
-
-	/* nothing to read */
-	spin_lock_irq(&pipe_crc->lock);
-	while (pipe_crc_data_count(pipe_crc) == 0) {
-		int ret;
-
-		if (filep->f_flags & O_NONBLOCK) {
-			spin_unlock_irq(&pipe_crc->lock);
-			return -EAGAIN;
-		}
-
-		ret = wait_event_interruptible_lock_irq(pipe_crc->wq,
-				pipe_crc_data_count(pipe_crc), pipe_crc->lock);
-		if (ret) {
-			spin_unlock_irq(&pipe_crc->lock);
-			return ret;
-		}
-	}
-
-	/* We now have one or more entries to read */
-	n_entries = count / PIPE_CRC_LINE_LEN;
-
-	bytes_read = 0;
-	while (n_entries > 0) {
-		struct intel_pipe_crc_entry *entry =
-			&pipe_crc->entries[pipe_crc->tail];
-
-		if (CIRC_CNT(pipe_crc->head, pipe_crc->tail,
-			     INTEL_PIPE_CRC_ENTRIES_NR) < 1)
-			break;
-
-		BUILD_BUG_ON_NOT_POWER_OF_2(INTEL_PIPE_CRC_ENTRIES_NR);
-		pipe_crc->tail = (pipe_crc->tail + 1) &
-				 (INTEL_PIPE_CRC_ENTRIES_NR - 1);
-
-		bytes_read += snprintf(buf, PIPE_CRC_BUFFER_LEN,
-				       "%8u %8x %8x %8x %8x %8x\n",
-				       entry->frame, entry->crc[0],
-				       entry->crc[1], entry->crc[2],
-				       entry->crc[3], entry->crc[4]);
-
-		spin_unlock_irq(&pipe_crc->lock);
-
-		if (copy_to_user(user_buf, buf, PIPE_CRC_LINE_LEN))
-			return -EFAULT;
-
-		user_buf += PIPE_CRC_LINE_LEN;
-		n_entries--;
-
-		spin_lock_irq(&pipe_crc->lock);
-	}
-
-	spin_unlock_irq(&pipe_crc->lock);
-
-	return bytes_read;
-}
-
-static const struct file_operations i915_pipe_crc_fops = {
-	.owner = THIS_MODULE,
-	.open = i915_pipe_crc_open,
-	.read = i915_pipe_crc_read,
-	.release = i915_pipe_crc_release,
-};
-
-static struct pipe_crc_info i915_pipe_crc_data[I915_MAX_PIPES] = {
-	{
-		.name = "i915_pipe_A_crc",
-		.pipe = PIPE_A,
-	},
-	{
-		.name = "i915_pipe_B_crc",
-		.pipe = PIPE_B,
-	},
-	{
-		.name = "i915_pipe_C_crc",
-		.pipe = PIPE_C,
-	},
-};
-
 static const char * const pipe_crc_sources[] = {
 	"none",
 	"plane1",
@@ -197,29 +43,6 @@ static const char * const pipe_crc_sources[] = {
 	"auto",
 };
 
-static const char *pipe_crc_source_name(enum intel_pipe_crc_source source)
-{
-	BUILD_BUG_ON(ARRAY_SIZE(pipe_crc_sources) != INTEL_PIPE_CRC_SOURCE_MAX);
-	return pipe_crc_sources[source];
-}
-
-static int display_crc_ctl_show(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = m->private;
-	enum pipe pipe;
-
-	for_each_pipe(dev_priv, pipe)
-		seq_printf(m, "%c %s\n", pipe_name(pipe),
-			   pipe_crc_source_name(dev_priv->pipe_crc[pipe].source));
-
-	return 0;
-}
-
-static int display_crc_ctl_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, display_crc_ctl_show, inode->i_private);
-}
-
 static int i8xx_pipe_crc_ctl_reg(enum intel_pipe_crc_source *source,
 				 uint32_t *val)
 {
@@ -616,177 +439,6 @@ static int get_new_crc_ctl_reg(struct drm_i915_private *dev_priv,
 		return ivb_pipe_crc_ctl_reg(dev_priv, pipe, source, val, set_wa);
 }
 
-static int pipe_crc_set_source(struct drm_i915_private *dev_priv,
-			       enum pipe pipe,
-			       enum intel_pipe_crc_source source)
-{
-	struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
-	enum intel_display_power_domain power_domain;
-	u32 val = 0; /* shut up gcc */
-	int ret;
-
-	if (pipe_crc->source == source)
-		return 0;
-
-	/* forbid changing the source without going back to 'none' */
-	if (pipe_crc->source && source)
-		return -EINVAL;
-
-	power_domain = POWER_DOMAIN_PIPE(pipe);
-	if (!intel_display_power_get_if_enabled(dev_priv, power_domain)) {
-		DRM_DEBUG_KMS("Trying to capture CRC while pipe is off\n");
-		return -EIO;
-	}
-
-	ret = get_new_crc_ctl_reg(dev_priv, pipe, &source, &val, true);
-	if (ret != 0)
-		goto out;
-
-	/* none -> real source transition */
-	if (source) {
-		struct intel_pipe_crc_entry *entries;
-
-		DRM_DEBUG_DRIVER("collecting CRCs for pipe %c, %s\n",
-				 pipe_name(pipe), pipe_crc_source_name(source));
-
-		entries = kcalloc(INTEL_PIPE_CRC_ENTRIES_NR,
-				  sizeof(pipe_crc->entries[0]),
-				  GFP_KERNEL);
-		if (!entries) {
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		spin_lock_irq(&pipe_crc->lock);
-		kfree(pipe_crc->entries);
-		pipe_crc->entries = entries;
-		pipe_crc->head = 0;
-		pipe_crc->tail = 0;
-		spin_unlock_irq(&pipe_crc->lock);
-	}
-
-	pipe_crc->source = source;
-
-	I915_WRITE(PIPE_CRC_CTL(pipe), val);
-	POSTING_READ(PIPE_CRC_CTL(pipe));
-
-	/* real source -> none transition */
-	if (!source) {
-		struct intel_pipe_crc_entry *entries;
-		struct intel_crtc *crtc = intel_get_crtc_for_pipe(dev_priv,
-								  pipe);
-
-		DRM_DEBUG_DRIVER("stopping CRCs for pipe %c\n",
-				 pipe_name(pipe));
-
-		drm_modeset_lock(&crtc->base.mutex, NULL);
-		if (crtc->base.state->active)
-			intel_wait_for_vblank(dev_priv, pipe);
-		drm_modeset_unlock(&crtc->base.mutex);
-
-		spin_lock_irq(&pipe_crc->lock);
-		entries = pipe_crc->entries;
-		pipe_crc->entries = NULL;
-		pipe_crc->head = 0;
-		pipe_crc->tail = 0;
-		spin_unlock_irq(&pipe_crc->lock);
-
-		kfree(entries);
-
-		if (IS_G4X(dev_priv))
-			g4x_undo_pipe_scramble_reset(dev_priv, pipe);
-		else if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv))
-			vlv_undo_pipe_scramble_reset(dev_priv, pipe);
-		else if ((IS_HASWELL(dev_priv) ||
-			  IS_BROADWELL(dev_priv)) && pipe == PIPE_A)
-			hsw_pipe_A_crc_wa(dev_priv, false);
-	}
-
-	ret = 0;
-
-out:
-	intel_display_power_put(dev_priv, power_domain);
-
-	return ret;
-}
-
-/*
- * Parse pipe CRC command strings:
- *   command: wsp* object wsp+ name wsp+ source wsp*
- *   object: 'pipe'
- *   name: (A | B | C)
- *   source: (none | plane1 | plane2 | pf)
- *   wsp: (#0x20 | #0x9 | #0xA)+
- *
- * eg.:
- *  "pipe A plane1"  ->  Start CRC computations on plane1 of pipe A
- *  "pipe A none"    ->  Stop CRC
- */
-static int display_crc_ctl_tokenize(char *buf, char *words[], int max_words)
-{
-	int n_words = 0;
-
-	while (*buf) {
-		char *end;
-
-		/* skip leading white space */
-		buf = skip_spaces(buf);
-		if (!*buf)
-			break;	/* end of buffer */
-
-		/* find end of word */
-		for (end = buf; *end && !isspace(*end); end++)
-			;
-
-		if (n_words == max_words) {
-			DRM_DEBUG_DRIVER("too many words, allowed <= %d\n",
-					 max_words);
-			return -EINVAL;	/* ran out of words[] before bytes */
-		}
-
-		if (*end)
-			*end++ = '\0';
-		words[n_words++] = buf;
-		buf = end;
-	}
-
-	return n_words;
-}
-
-enum intel_pipe_crc_object {
-	PIPE_CRC_OBJECT_PIPE,
-};
-
-static const char * const pipe_crc_objects[] = {
-	"pipe",
-};
-
-static int
-display_crc_ctl_parse_object(const char *buf, enum intel_pipe_crc_object *o)
-{
-	int i;
-
-	i = match_string(pipe_crc_objects, ARRAY_SIZE(pipe_crc_objects), buf);
-	if (i < 0)
-		return i;
-
-	*o = i;
-	return 0;
-}
-
-static int display_crc_ctl_parse_pipe(struct drm_i915_private *dev_priv,
-				      const char *buf, enum pipe *pipe)
-{
-	const char name = buf[0];
-
-	if (name < 'A' || name >= pipe_name(INTEL_INFO(dev_priv)->num_pipes))
-		return -EINVAL;
-
-	*pipe = name - 'A';
-
-	return 0;
-}
-
 static int
 display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s)
 {
@@ -805,81 +457,6 @@ display_crc_ctl_parse_source(const char *buf, enum intel_pipe_crc_source *s)
 	return 0;
 }
 
-static int display_crc_ctl_parse(struct drm_i915_private *dev_priv,
-				 char *buf, size_t len)
-{
-#define N_WORDS 3
-	int n_words;
-	char *words[N_WORDS];
-	enum pipe pipe;
-	enum intel_pipe_crc_object object;
-	enum intel_pipe_crc_source source;
-
-	n_words = display_crc_ctl_tokenize(buf, words, N_WORDS);
-	if (n_words != N_WORDS) {
-		DRM_DEBUG_DRIVER("tokenize failed, a command is %d words\n",
-				 N_WORDS);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_object(words[0], &object) < 0) {
-		DRM_DEBUG_DRIVER("unknown object %s\n", words[0]);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_pipe(dev_priv, words[1], &pipe) < 0) {
-		DRM_DEBUG_DRIVER("unknown pipe %s\n", words[1]);
-		return -EINVAL;
-	}
-
-	if (display_crc_ctl_parse_source(words[2], &source) < 0) {
-		DRM_DEBUG_DRIVER("unknown source %s\n", words[2]);
-		return -EINVAL;
-	}
-
-	return pipe_crc_set_source(dev_priv, pipe, source);
-}
-
-static ssize_t display_crc_ctl_write(struct file *file, const char __user *ubuf,
-				     size_t len, loff_t *offp)
-{
-	struct seq_file *m = file->private_data;
-	struct drm_i915_private *dev_priv = m->private;
-	char *tmpbuf;
-	int ret;
-
-	if (len == 0)
-		return 0;
-
-	if (len > PAGE_SIZE - 1) {
-		DRM_DEBUG_DRIVER("expected <%lu bytes into pipe crc control\n",
-				 PAGE_SIZE);
-		return -E2BIG;
-	}
-
-	tmpbuf = memdup_user_nul(ubuf, len);
-	if (IS_ERR(tmpbuf))
-		return PTR_ERR(tmpbuf);
-
-	ret = display_crc_ctl_parse(dev_priv, tmpbuf, len);
-
-	kfree(tmpbuf);
-	if (ret < 0)
-		return ret;
-
-	*offp += len;
-	return len;
-}
-
-const struct file_operations i915_display_crc_ctl_fops = {
-	.owner = THIS_MODULE,
-	.open = display_crc_ctl_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
-	.write = display_crc_ctl_write
-};
-
 void intel_display_crc_init(struct drm_i915_private *dev_priv)
 {
 	enum pipe pipe;
@@ -887,30 +464,8 @@ void intel_display_crc_init(struct drm_i915_private *dev_priv)
 	for_each_pipe(dev_priv, pipe) {
 		struct intel_pipe_crc *pipe_crc = &dev_priv->pipe_crc[pipe];
 
-		pipe_crc->opened = false;
 		spin_lock_init(&pipe_crc->lock);
-		init_waitqueue_head(&pipe_crc->wq);
-	}
-}
-
-int intel_pipe_crc_create(struct drm_minor *minor)
-{
-	struct drm_i915_private *dev_priv = to_i915(minor->dev);
-	struct dentry *ent;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(i915_pipe_crc_data); i++) {
-		struct pipe_crc_info *info = &i915_pipe_crc_data[i];
-
-		info->dev_priv = dev_priv;
-		ent = debugfs_create_file(info->name, S_IRUGO,
-					  minor->debugfs_root, info,
-					  &i915_pipe_crc_fops);
-		if (!ent)
-			return -ENOMEM;
 	}
-
-	return 0;
 }
 
 int intel_crtc_set_crc_source(struct drm_crtc *crtc, const char *source_name,
-- 
cgit v1.2.3


From b79ebe74e1c4219e91940b637d40939b0c80c0f2 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Thu, 5 Jul 2018 15:26:54 +0300
Subject: drm/i915/ddi: Simplify get_encoder_power_domains()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can simplify the encoder's get_power_domains() hook by calling it
only if the encoder is active. That way the hook can return its power
domains unconditionally without checking the active state by calling
encoder::get_hw_state(). This get_hw_state() query is in fact
redundant since it's already done by intel_modeset_readout_hw_state()
setting the encoder's crtc or leaving it NULL accordingly. Let's use
this fact to decide if the encoder is active.

While at it clarify the comment in intel_ddi_get_power_domains() about
primary vs. fake MST encoders and make sure we never do an incorrect
encoder->dig_port cast for fake MST encoders.

Suggested-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705122654.17072-1-imre.deak@intel.com
---
 drivers/gpu/drm/i915/intel_ddi.c     | 19 +++++++------------
 drivers/gpu/drm/i915/intel_display.c | 11 +++++------
 2 files changed, 12 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index c74b01a52082..32838ed89ee7 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -2006,24 +2006,19 @@ intel_ddi_main_link_aux_domain(struct intel_dp *intel_dp)
 static u64 intel_ddi_get_power_domains(struct intel_encoder *encoder,
 				       struct intel_crtc_state *crtc_state)
 {
-	struct intel_digital_port *dig_port = enc_to_dig_port(&encoder->base);
-	enum pipe pipe;
+	struct intel_digital_port *dig_port;
 	u64 domains;
 
-	if (!intel_ddi_get_hw_state(encoder, &pipe))
-		return 0;
-
-	domains = BIT_ULL(dig_port->ddi_io_power_domain);
-	if (!crtc_state)
-		return domains;
-
 	/*
 	 * TODO: Add support for MST encoders. Atm, the following should never
-	 * happen since this function will be called only for the primary
-	 * encoder which doesn't have its own pipe/crtc_state.
+	 * happen since fake-MST encoders don't set their get_power_domains()
+	 * hook.
 	 */
 	if (WARN_ON(intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST)))
-		return domains;
+		return 0;
+
+	dig_port = enc_to_dig_port(&encoder->base);
+	domains = BIT_ULL(dig_port->ddi_io_power_domain);
 
 	/* AUX power is only needed for (e)DP mode, not for HDMI. */
 	if (intel_crtc_has_dp_encoder(crtc_state)) {
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d33033abbf18..19f756d571ae 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15664,14 +15664,13 @@ get_encoder_power_domains(struct drm_i915_private *dev_priv)
 			continue;
 
 		/*
-		 * For MST and inactive encoders we don't have a crtc state.
-		 * FIXME: no need to call get_power_domains in such cases, it
-		 * will always return 0.
+		 * MST-primary and inactive encoders don't have a crtc state
+		 * and neither of these require any power domain references.
 		 */
-		crtc_state = encoder->base.crtc ?
-			     to_intel_crtc_state(encoder->base.crtc->state) :
-			     NULL;
+		if (!encoder->base.crtc)
+			continue;
 
+		crtc_state = to_intel_crtc_state(encoder->base.crtc->state);
 		get_domains = encoder->get_power_domains(encoder, crtc_state);
 		for_each_power_domain(domain, get_domains)
 			intel_display_power_get(dev_priv, domain);
-- 
cgit v1.2.3


From a012024571d98e2e4bf29a9168fb7ddc44b7ab86 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Date: Wed, 18 Apr 2018 14:51:21 +0200
Subject: drm/crc: Only report a single overflow when a CRC fd is opened
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reduces the amount of spam when you debug a CRC reading
program.

Signed-off-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
[mlankhorst: Change bool overflow to was_overflow (Ville)]
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180418125121.72081-1-maarten.lankhorst@linux.intel.com
---
 drivers/gpu/drm/drm_debugfs_crc.c | 9 ++++++++-
 include/drm/drm_debugfs_crc.h     | 3 ++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_debugfs_crc.c b/drivers/gpu/drm/drm_debugfs_crc.c
index 9f8312137cad..99961192bf03 100644
--- a/drivers/gpu/drm/drm_debugfs_crc.c
+++ b/drivers/gpu/drm/drm_debugfs_crc.c
@@ -139,6 +139,7 @@ static int crtc_crc_data_count(struct drm_crtc_crc *crc)
 static void crtc_crc_cleanup(struct drm_crtc_crc *crc)
 {
 	kfree(crc->entries);
+	crc->overflow = false;
 	crc->entries = NULL;
 	crc->head = 0;
 	crc->tail = 0;
@@ -391,8 +392,14 @@ int drm_crtc_add_crc_entry(struct drm_crtc *crtc, bool has_frame,
 	tail = crc->tail;
 
 	if (CIRC_SPACE(head, tail, DRM_CRC_ENTRIES_NR) < 1) {
+		bool was_overflow = crc->overflow;
+
+		crc->overflow = true;
 		spin_unlock(&crc->lock);
-		DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n");
+
+		if (!was_overflow)
+			DRM_ERROR("Overflow of CRC buffer, userspace reads too slow.\n");
+
 		return -ENOBUFS;
 	}
 
diff --git a/include/drm/drm_debugfs_crc.h b/include/drm/drm_debugfs_crc.h
index 7d63b1d4adb9..b225eeb30d05 100644
--- a/include/drm/drm_debugfs_crc.h
+++ b/include/drm/drm_debugfs_crc.h
@@ -43,6 +43,7 @@ struct drm_crtc_crc_entry {
  * @lock: protects the fields in this struct
  * @source: name of the currently configured source of CRCs
  * @opened: whether userspace has opened the data file for reading
+ * @overflow: whether an overflow occured.
  * @entries: array of entries, with size of %DRM_CRC_ENTRIES_NR
  * @head: head of circular queue
  * @tail: tail of circular queue
@@ -52,7 +53,7 @@ struct drm_crtc_crc_entry {
 struct drm_crtc_crc {
 	spinlock_t lock;
 	const char *source;
-	bool opened;
+	bool opened, overflow;
 	struct drm_crtc_crc_entry *entries;
 	int head, tail;
 	size_t values_cnt;
-- 
cgit v1.2.3


From d64c5cf8e89d124355924c513a42b16f0d7d3a03 Mon Sep 17 00:00:00 2001
From: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Date: Fri, 6 Jul 2018 13:50:36 +0100
Subject: ALSA: pcm: Allow drivers to set R/W wait time.

Currently ALSA core blocks userspace for about 10 seconds for PCM R/W IO.
This needs to be configurable for modern hardware like DSPs where no
pointer update in milliseconds can indicate terminal DSP errors.

Add a substream variable to set the wait time in ms. This allows userspace
and drivers to recover more quickly from terminal DSP errors.

Signed-off-by: Liam Girdwood <liam.r.girdwood@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h  |  1 +
 sound/core/pcm_lib.c | 17 ++++++++++++-----
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index e054c583d3b3..fcdf358a25f0 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -462,6 +462,7 @@ struct snd_pcm_substream {
         /* -- timer section -- */
 	struct snd_timer *timer;		/* timer */
 	unsigned timer_running: 1;	/* time is running */
+	long wait_time;	/* time in ms for R/W to wait for avail */
 	/* -- next substream -- */
 	struct snd_pcm_substream *next;
 	/* -- linked substreams -- */
diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index c1d2e8e1fc6b..5736860f325b 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -1833,12 +1833,19 @@ static int wait_for_avail(struct snd_pcm_substream *substream,
 	if (runtime->no_period_wakeup)
 		wait_time = MAX_SCHEDULE_TIMEOUT;
 	else {
-		wait_time = 10;
-		if (runtime->rate) {
-			long t = runtime->period_size * 2 / runtime->rate;
-			wait_time = max(t, wait_time);
+		/* use wait time from substream if available */
+		if (substream->wait_time) {
+			wait_time = substream->wait_time;
+		} else {
+			wait_time = 10;
+
+			if (runtime->rate) {
+				long t = runtime->period_size * 2 /
+					 runtime->rate;
+				wait_time = max(t, wait_time);
+			}
+			wait_time = msecs_to_jiffies(wait_time * 1000);
 		}
-		wait_time = msecs_to_jiffies(wait_time * 1000);
 	}
 
 	for (;;) {
-- 
cgit v1.2.3


From 481827b441674b7f1d030c223decdb56266ff398 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 11:14:41 +0100
Subject: drm/i915: Record logical context support in driver caps

Avoid looking at the magical engines[RCS] to decide if the HW and driver
supports logical contexts, and instead record that knowledge during
initialisation.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706101442.21279-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.h          | 1 +
 drivers/gpu/drm/i915/i915_gem_context.c  | 6 +++---
 drivers/gpu/drm/i915/intel_device_info.c | 2 ++
 drivers/gpu/drm/i915/intel_device_info.h | 1 +
 drivers/gpu/drm/i915/intel_engine_cs.c   | 2 ++
 5 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 8a2196e4262b..c1c637e47bf5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2306,6 +2306,7 @@ intel_info(const struct drm_i915_private *dev_priv)
 }
 
 #define INTEL_INFO(dev_priv)	intel_info((dev_priv))
+#define DRIVER_CAPS(dev_priv)	(&(dev_priv)->caps)
 
 #define INTEL_GEN(dev_priv)	((dev_priv)->info.gen)
 #define INTEL_DEVID(dev_priv)	((dev_priv)->info.device_id)
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 985ef70d9416..b10770cfccd2 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -512,8 +512,8 @@ int i915_gem_contexts_init(struct drm_i915_private *dev_priv)
 	}
 
 	DRM_DEBUG_DRIVER("%s context support initialized\n",
-			 dev_priv->engine[RCS]->context_size ? "logical" :
-			 "fake");
+			 DRIVER_CAPS(dev_priv)->has_logical_contexts ?
+			 "logical" : "fake");
 	return 0;
 }
 
@@ -720,7 +720,7 @@ int i915_gem_context_create_ioctl(struct drm_device *dev, void *data,
 	struct i915_gem_context *ctx;
 	int ret;
 
-	if (!dev_priv->engine[RCS]->context_size)
+	if (!DRIVER_CAPS(dev_priv)->has_logical_contexts)
 		return -ENODEV;
 
 	if (args->pad != 0)
diff --git a/drivers/gpu/drm/i915/intel_device_info.c b/drivers/gpu/drm/i915/intel_device_info.c
index 0fd13df424cf..0ef0c6448d53 100644
--- a/drivers/gpu/drm/i915/intel_device_info.c
+++ b/drivers/gpu/drm/i915/intel_device_info.c
@@ -858,6 +858,8 @@ void intel_device_info_runtime_init(struct intel_device_info *info)
 void intel_driver_caps_print(const struct intel_driver_caps *caps,
 			     struct drm_printer *p)
 {
+	drm_printf(p, "Has logical contexts? %s\n",
+		   yesno(caps->has_logical_contexts));
 	drm_printf(p, "scheduler: %x\n", caps->scheduler);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_device_info.h b/drivers/gpu/drm/i915/intel_device_info.h
index 933e31669557..633f9fbf72ea 100644
--- a/drivers/gpu/drm/i915/intel_device_info.h
+++ b/drivers/gpu/drm/i915/intel_device_info.h
@@ -186,6 +186,7 @@ struct intel_device_info {
 
 struct intel_driver_caps {
 	unsigned int scheduler;
+	bool has_logical_contexts:1;
 };
 
 static inline unsigned int sseu_subslice_total(const struct sseu_dev_info *sseu)
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 478c928912c4..e2f562853aee 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -302,6 +302,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 							   engine->class);
 	if (WARN_ON(engine->context_size > BIT(20)))
 		engine->context_size = 0;
+	if (engine->context_size)
+		DRIVER_CAPS(dev_priv)->has_logical_contexts = true;
 
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
-- 
cgit v1.2.3


From 0fdbe58c4a0f8c2fa67e38a740ce6ff3cffa8c86 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 11:19:23 +0100
Subject: drm/i915/selftests: Skip live context execution test without logical
 contexts

If the HW (or driver) doesn't support logical contexts, don't pretend we
gain anything from trying to execute GPU commands with them. At best it
reports -ENODEV, which is an unhelpful failure that we should just skip.

v2: Be more specific and check the driver/engine caps for logical (HW)
context support.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706101923.28548-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_context.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 0b36265a0f96..0d8e719802fa 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -336,11 +336,15 @@ static int igt_ctx_exec(void *arg)
 	bool first_shared_gtt = true;
 	int err = -ENODEV;
 
-	/* Create a few different contexts (with different mm) and write
+	/*
+	 * Create a few different contexts (with different mm) and write
 	 * through each ctx/mm using the GPU making sure those writes end
 	 * up in the expected pages of our obj.
 	 */
 
+	if (!DRIVER_CAPS(i915)->has_logical_contexts)
+		return 0;
+
 	file = mock_file(i915);
 	if (IS_ERR(file))
 		return PTR_ERR(file);
@@ -367,6 +371,9 @@ static int igt_ctx_exec(void *arg)
 		}
 
 		for_each_engine(engine, i915, id) {
+			if (!engine->context_size)
+				continue; /* No logical context support in HW */
+
 			if (!intel_engine_can_store_dword(engine))
 				continue;
 
-- 
cgit v1.2.3


From 03bbc508a312d9f4833f1cb0f7b2da7517787b61 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 12:45:10 +0100
Subject: drm/i915/selftests: Skip live_execlists if the GPU is terminally
 wedged

If the GPU is irrecoverably wedged, we can not execute any requests
making testing execlists (request execution) pointless. Skip!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706114510.18467-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/intel_lrc.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index ea27c7cfbf96..730a02d39058 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -455,5 +455,8 @@ int intel_execlists_live_selftests(struct drm_i915_private *i915)
 	if (!HAS_EXECLISTS(i915))
 		return 0;
 
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return 0;
+
 	return i915_subtests(tests, i915);
 }
-- 
cgit v1.2.3


From add00e6d896fab882e6115ed4908b2456f1b3a85 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 12:54:02 +0100
Subject: drm/i915: Flush the WCB following a WC write

If we have just completed a WC write, we must ensure that the WCB (Write
Combining Buffer) is flushed out to main memory before we can expect to
see the results. This is especially important when mixing WC with GTT as
the physical paths are different and cachelines are not naturally flushed.

Testcase: igt/drv_selftests/live_coherency #gdg
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706115402.18547-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0c0a1a959d0b..be63e8bbb6d2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -837,6 +837,10 @@ flush_write_domain(struct drm_i915_gem_object *obj, unsigned int flush_domains)
 		}
 		break;
 
+	case I915_GEM_DOMAIN_WC:
+		wmb();
+		break;
+
 	case I915_GEM_DOMAIN_CPU:
 		i915_gem_clflush_object(obj, I915_CLFLUSH_SYNC);
 		break;
-- 
cgit v1.2.3


From 58174eac1593f104c03a15330e0fea1b1ec01434 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 13:26:10 +0100
Subject: drm/i915/gtt: Suppress warnings for dma_map_page

As we propagate back the error to the caller for them to handle, we do
not need the lowest level spitting out a redundant warning upon an
allocation failure inside dma_map_page().

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706122611.4142-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index a9330de886f8..92a06042e0bf 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -561,8 +561,10 @@ static int __setup_page_dma(struct i915_address_space *vm,
 	if (unlikely(!p->page))
 		return -ENOMEM;
 
-	p->daddr = dma_map_page(vm->dma, p->page, 0, PAGE_SIZE,
-				PCI_DMA_BIDIRECTIONAL);
+	p->daddr = dma_map_page_attrs(vm->dma,
+				      p->page, 0, PAGE_SIZE,
+				      PCI_DMA_BIDIRECTIONAL,
+				      DMA_ATTR_NO_WARN);
 	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
 		vm_free_page(vm, p->page);
 		return -ENOMEM;
@@ -643,8 +645,10 @@ setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 		if (unlikely(!page))
 			goto skip;
 
-		addr = dma_map_page(vm->dma, page, 0, size,
-				    PCI_DMA_BIDIRECTIONAL);
+		addr = dma_map_page_attrs(vm->dma,
+					  page, 0, size,
+					  PCI_DMA_BIDIRECTIONAL,
+					  DMA_ATTR_NO_WARN);
 		if (unlikely(dma_mapping_error(vm->dma, addr)))
 			goto free_page;
 
-- 
cgit v1.2.3


From 66daec6b21840ea09af4c41f706867df7d81c820 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 13:26:11 +0100
Subject: drm/i915/gtt: Control cache domain of dma_map_page() directly

We already maually control the CPU cache for our page table directories,
so we can tell the dma mapper to skip doing it as well.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706122611.4142-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 92a06042e0bf..e2793231ef49 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -564,6 +564,7 @@ static int __setup_page_dma(struct i915_address_space *vm,
 	p->daddr = dma_map_page_attrs(vm->dma,
 				      p->page, 0, PAGE_SIZE,
 				      PCI_DMA_BIDIRECTIONAL,
+				      DMA_ATTR_SKIP_CPU_SYNC |
 				      DMA_ATTR_NO_WARN);
 	if (unlikely(dma_mapping_error(vm->dma, p->daddr))) {
 		vm_free_page(vm, p->page);
@@ -648,6 +649,7 @@ setup_scratch_page(struct i915_address_space *vm, gfp_t gfp)
 		addr = dma_map_page_attrs(vm->dma,
 					  page, 0, size,
 					  PCI_DMA_BIDIRECTIONAL,
+					  DMA_ATTR_SKIP_CPU_SYNC |
 					  DMA_ATTR_NO_WARN);
 		if (unlikely(dma_mapping_error(vm->dma, addr)))
 			goto free_page;
-- 
cgit v1.2.3


From bedbeec65c6cdec25aab609d557b630c97f81866 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Fri, 6 Jul 2018 16:21:17 +0100
Subject: arm64: mm: Export __flush_icache_range() to modules

lkdtm calls flush_icache_range(), which results in an out-of-line call
to __flush_icache_range(), which is not exported to modules.

Export the symbol to modules to fix this build breakage.

Fixes: 3b8c9f1cdfc5 ("arm64: IPI each CPU after invalidating the I-cache for kernel mappings")
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/mm/flush.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 1059884f9a6f..9786f9d5d3dc 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -82,7 +82,7 @@ EXPORT_SYMBOL(flush_dcache_page);
 /*
  * Additional functions defined in assembly.
  */
-EXPORT_SYMBOL(flush_icache_range);
+EXPORT_SYMBOL(__flush_icache_range);
 
 #ifdef CONFIG_ARCH_HAS_PMEM_API
 void arch_wb_cache_pmem(void *addr, size_t size)
-- 
cgit v1.2.3


From 207b700050b8d323d0c23b457c200b22c7ed3737 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 13:53:38 +0100
Subject: drm/i915/selftests: Limit live_gtt allocation test to fit within RAM

Limit the GTT size we try and allocate to ensure that it fits within RAM
and does not trigger the oomkiller indiscriminately.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706125338.24432-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index e108fe4e0fd9..600a3bcbd3d6 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -148,7 +148,7 @@ static int igt_ppgtt_alloc(void *arg)
 {
 	struct drm_i915_private *dev_priv = arg;
 	struct i915_hw_ppgtt *ppgtt;
-	u64 size, last;
+	u64 size, last, limit;
 	int err = 0;
 
 	/* Allocate a ppggt and try to fill the entire range */
@@ -163,10 +163,18 @@ static int igt_ppgtt_alloc(void *arg)
 	if (!ppgtt->vm.allocate_va_range)
 		goto err_ppgtt_cleanup;
 
+	/*
+	 * While we only allocate the page tables here and so we could
+	 * address a much larger GTT than we could actually fit into
+	 * RAM, a practical limit is the amount of physical pages in the system.
+	 * This should ensure that we do not run into the oomkiller during
+	 * the test and take down the machine wilfully.
+	 */
+	limit = totalram_pages << PAGE_SHIFT;
+	limit = min(ppgtt->vm.total, limit);
+
 	/* Check we can allocate the entire range */
-	for (size = 4096;
-	     size <= ppgtt->vm.total;
-	     size <<= 2) {
+	for (size = 4096; size <= limit; size <<= 2) {
 		err = ppgtt->vm.allocate_va_range(&ppgtt->vm, 0, size);
 		if (err) {
 			if (err == -ENOMEM) {
@@ -183,9 +191,7 @@ static int igt_ppgtt_alloc(void *arg)
 	}
 
 	/* Check we can incrementally allocate the entire range */
-	for (last = 0, size = 4096;
-	     size <= ppgtt->vm.total;
-	     last = size, size <<= 2) {
+	for (last = 0, size = 4096; size <= limit; last = size, size <<= 2) {
 		err = ppgtt->vm.allocate_va_range(&ppgtt->vm,
 						  last, size - last);
 		if (err) {
-- 
cgit v1.2.3


From 5b544337109081ac4de23e7ded1c31f7457e5f5e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 15:23:22 +0100
Subject: drm/i915/selftests: Replace magic 1<<22 with
 MI_USE_GGTT/MI_MEM_VIRTUAL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace the magic bit with the proper symbolic name for instructing
MI_STORE_DWORD_IMM to use a virtual address (on gen3) or the global GTT
address (still virtual!) on gen4+.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706142323.25699-1-chris@chris-wilson.co.uk
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
---
 drivers/gpu/drm/i915/selftests/huge_pages.c         | 4 ++--
 drivers/gpu/drm/i915/selftests/i915_gem_coherency.c | 4 ++--
 drivers/gpu/drm/i915/selftests/i915_gem_context.c   | 4 ++--
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c    | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 1193dd36913a..ab662dabcff7 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -919,12 +919,12 @@ gpu_write_dw(struct i915_vma *vma, u64 offset, u32 val)
 			*cmd++ = val;
 		} else if (gen >= 4) {
 			*cmd++ = MI_STORE_DWORD_IMM_GEN4 |
-				(gen < 6 ? 1 << 22 : 0);
+				(gen < 6 ? MI_USE_GGTT : 0);
 			*cmd++ = 0;
 			*cmd++ = offset;
 			*cmd++ = val;
 		} else {
-			*cmd++ = MI_STORE_DWORD_IMM | 1 << 22;
+			*cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*cmd++ = offset;
 			*cmd++ = val;
 		}
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index cb9eef1635e1..294c58aba2c1 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -210,12 +210,12 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 		*cs++ = upper_32_bits(i915_ggtt_offset(vma) + offset);
 		*cs++ = v;
 	} else if (INTEL_GEN(i915) >= 4) {
-		*cs++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
+		*cs++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*cs++ = 0;
 		*cs++ = i915_ggtt_offset(vma) + offset;
 		*cs++ = v;
 	} else {
-		*cs++ = MI_STORE_DWORD_IMM | 1 << 22;
+		*cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 		*cs++ = i915_ggtt_offset(vma) + offset;
 		*cs++ = v;
 		*cs++ = MI_NOOP;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 0d8e719802fa..65100d3e31cf 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -63,12 +63,12 @@ gpu_fill_dw(struct i915_vma *vma, u64 offset, unsigned long count, u32 value)
 			*cmd++ = value;
 		} else if (gen >= 4) {
 			*cmd++ = MI_STORE_DWORD_IMM_GEN4 |
-				(gen < 6 ? 1 << 22 : 0);
+				(gen < 6 ? MI_USE_GGTT : 0);
 			*cmd++ = 0;
 			*cmd++ = offset;
 			*cmd++ = value;
 		} else {
-			*cmd++ = MI_STORE_DWORD_IMM | 1 << 22;
+			*cmd++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 			*cmd++ = offset;
 			*cmd++ = value;
 		}
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 5cb808dc5b50..0fc6da81f86e 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -171,7 +171,7 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = MI_BATCH_BUFFER_START | 1 << 8;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else if (INTEL_GEN(i915) >= 4) {
-		*batch++ = MI_STORE_DWORD_IMM_GEN4 | 1 << 22;
+		*batch++ = MI_STORE_DWORD_IMM_GEN4 | MI_USE_GGTT;
 		*batch++ = 0;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
-- 
cgit v1.2.3


From 8fdbfd8686329e286465bcef11a7ef20be84d6b6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 15:23:23 +0100
Subject: drm/i915/selftests: Fixup missing MI_MEM_VIRTUAL for live_hangcheck
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We always want to use a virtual address (i.e. use the GTT) for
MI_STORE_DWORD_IMM, but forgot the ever so important flag in
live_hangcheck for gen3.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706142323.25699-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 0fc6da81f86e..c838f7d08cb9 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -184,7 +184,7 @@ static int emit_recurse_batch(struct hang *h,
 		*batch++ = MI_BATCH_BUFFER_START | 2 << 6;
 		*batch++ = lower_32_bits(vma->node.start);
 	} else {
-		*batch++ = MI_STORE_DWORD_IMM;
+		*batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL;
 		*batch++ = lower_32_bits(hws_address(hws, rq));
 		*batch++ = rq->fence.seqno;
 		*batch++ = MI_ARB_CHECK;
-- 
cgit v1.2.3


From 3b6c62f363a19ce82bf378187ab97c9dc01e3927 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 6 Jul 2018 09:08:01 -0700
Subject: x86/numa_emulation: Fix emulated-to-physical node mapping

Without this change the distance table calculation for emulated nodes
may use the wrong numa node and report an incorrect distance.

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/153089328103.27680.14778434392225818887.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/mm/numa_emulation.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 34a2a3bfde9c..22cbad56acab 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -61,7 +61,7 @@ static int __init emu_setup_memblk(struct numa_meminfo *ei,
 	eb->nid = nid;
 
 	if (emu_nid_to_phys[nid] == NUMA_NO_NODE)
-		emu_nid_to_phys[nid] = nid;
+		emu_nid_to_phys[nid] = pb->nid;
 
 	pb->start += size;
 	if (pb->start >= pb->end) {
-- 
cgit v1.2.3


From cc9aec03e58fea4dbab04c05d1e15852f801ca53 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 6 Jul 2018 09:08:06 -0700
Subject: x86/numa_emulation: Introduce uniform split capability

The current NUMA emulation capabilities for splitting System RAM by a
fixed size or by a set number of nodes may result in some nodes being
larger than others. The implementation prioritizes establishing a
minimum usable memory size over satisfying the requested number of NUMA
nodes.

Introduce a uniform split capability that evenly partitions each
physical NUMA node into N emulated nodes. For example numa=fake=3U
creates 6 emulated nodes total on a system that has 2 physical nodes.

This capability is useful for debugging and evaluating platform
memory-side-cache capabilities as described by the ACPI HMAT (see
5.2.27.5 Memory Side Cache Information Structure in ACPI 6.2a)

Compare numa=fake=6 that results in only 5 nodes being created against
numa=fake=3U which takes the 2 physical nodes and evenly divides them.

numa=fake=6
available: 5 nodes (0-4)
node 0 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38
node 0 size: 2648 MB
node 0 free: 2443 MB
node 1 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39
node 1 size: 2672 MB
node 1 free: 2442 MB
node 2 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38
node 2 size: 5291 MB
node 2 free: 5278 MB
node 3 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39
node 3 size: 2677 MB
node 3 free: 2665 MB
node 4 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39
node 4 size: 2676 MB
node 4 free: 2663 MB
node distances:
node   0   1   2   3   4
  0:  10  20  10  20  20
  1:  20  10  20  10  10
  2:  10  20  10  20  20
  3:  20  10  20  10  10
  4:  20  10  20  10  10

numa=fake=3U
available: 6 nodes (0-5)
node 0 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38
node 0 size: 2900 MB
node 0 free: 2637 MB
node 1 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38
node 1 size: 3023 MB
node 1 free: 3012 MB
node 2 cpus: 0 2 4 6 8 10 12 14 16 18 20 22 24 26 28 30 32 34 36 38
node 2 size: 2015 MB
node 2 free: 2004 MB
node 3 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39
node 3 size: 2704 MB
node 3 free: 2522 MB
node 4 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39
node 4 size: 2709 MB
node 4 free: 2698 MB
node 5 cpus: 1 3 5 7 9 11 13 15 17 19 21 23 25 27 29 31 33 35 37 39
node 5 size: 2612 MB
node 5 free: 2601 MB
node distances:
node   0   1   2   3   4   5
  0:  10  10  10  20  20  20
  1:  10  10  10  20  20  20
  2:  10  10  10  20  20  20
  3:  20  20  20  10  10  10
  4:  20  20  20  10  10  10
  5:  20  20  20  10  10  10

Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wei Yang <richard.weiyang@gmail.com>
Cc: linux-mm@kvack.org
Link: http://lkml.kernel.org/r/153089328617.27680.14930758266174305832.stgit@dwillia2-desk3.amr.corp.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/x86/x86_64/boot-options.txt |   4 ++
 arch/x86/mm/numa_emulation.c              | 105 ++++++++++++++++++++++++------
 2 files changed, 90 insertions(+), 19 deletions(-)

diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 8d109ef67ab6..3a2ba436721a 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -156,6 +156,10 @@ NUMA
 		If given as an integer, fills all system RAM with N fake nodes
 		interleaved over physical nodes.
 
+  numa=fake=<N>U
+		If given as an integer followed by 'U', it will divide each
+		physical node into N emulated nodes.
+
 ACPI
 
   acpi=off	Don't enable ACPI
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 22cbad56acab..b54d52a2d00a 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -198,40 +198,73 @@ static u64 __init find_end_of_node(u64 start, u64 max_addr, u64 size)
 	return end;
 }
 
+static u64 uniform_size(u64 max_addr, u64 base, u64 hole, int nr_nodes)
+{
+	unsigned long max_pfn = PHYS_PFN(max_addr);
+	unsigned long base_pfn = PHYS_PFN(base);
+	unsigned long hole_pfns = PHYS_PFN(hole);
+
+	return PFN_PHYS((max_pfn - base_pfn - hole_pfns) / nr_nodes);
+}
+
 /*
  * Sets up fake nodes of `size' interleaved over physical nodes ranging from
  * `addr' to `max_addr'.
  *
  * Returns zero on success or negative on error.
  */
-static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+static int __init split_nodes_size_interleave_uniform(struct numa_meminfo *ei,
 					      struct numa_meminfo *pi,
-					      u64 addr, u64 max_addr, u64 size)
+					      u64 addr, u64 max_addr, u64 size,
+					      int nr_nodes, struct numa_memblk *pblk,
+					      int nid)
 {
 	nodemask_t physnode_mask = numa_nodes_parsed;
+	int i, ret, uniform = 0;
 	u64 min_size;
-	int nid = 0;
-	int i, ret;
 
-	if (!size)
+	if ((!size && !nr_nodes) || (nr_nodes && !pblk))
 		return -1;
+
 	/*
-	 * The limit on emulated nodes is MAX_NUMNODES, so the size per node is
-	 * increased accordingly if the requested size is too small.  This
-	 * creates a uniform distribution of node sizes across the entire
-	 * machine (but not necessarily over physical nodes).
+	 * In the 'uniform' case split the passed in physical node by
+	 * nr_nodes, in the non-uniform case, ignore the passed in
+	 * physical block and try to create nodes of at least size
+	 * @size.
+	 *
+	 * In the uniform case, split the nodes strictly by physical
+	 * capacity, i.e. ignore holes. In the non-uniform case account
+	 * for holes and treat @size as a minimum floor.
 	 */
-	min_size = (max_addr - addr - mem_hole_size(addr, max_addr)) / MAX_NUMNODES;
-	min_size = max(min_size, FAKE_NODE_MIN_SIZE);
-	if ((min_size & FAKE_NODE_MIN_HASH_MASK) < min_size)
-		min_size = (min_size + FAKE_NODE_MIN_SIZE) &
-						FAKE_NODE_MIN_HASH_MASK;
+	if (!nr_nodes)
+		nr_nodes = MAX_NUMNODES;
+	else {
+		nodes_clear(physnode_mask);
+		node_set(pblk->nid, physnode_mask);
+		uniform = 1;
+	}
+
+	if (uniform) {
+		min_size = uniform_size(max_addr, addr, 0, nr_nodes);
+		size = min_size;
+	} else {
+		/*
+		 * The limit on emulated nodes is MAX_NUMNODES, so the
+		 * size per node is increased accordingly if the
+		 * requested size is too small.  This creates a uniform
+		 * distribution of node sizes across the entire machine
+		 * (but not necessarily over physical nodes).
+		 */
+		min_size = uniform_size(max_addr, addr,
+				mem_hole_size(addr, max_addr), nr_nodes);
+	}
+	min_size = ALIGN(max(min_size, FAKE_NODE_MIN_SIZE), FAKE_NODE_MIN_SIZE);
 	if (size < min_size) {
 		pr_err("Fake node size %LuMB too small, increasing to %LuMB\n",
 			size >> 20, min_size >> 20);
 		size = min_size;
 	}
-	size &= FAKE_NODE_MIN_HASH_MASK;
+	size = ALIGN_DOWN(size, FAKE_NODE_MIN_SIZE);
 
 	/*
 	 * Fill physical nodes with fake nodes of size until there is no memory
@@ -248,10 +281,14 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 				node_clear(i, physnode_mask);
 				continue;
 			}
+
 			start = pi->blk[phys_blk].start;
 			limit = pi->blk[phys_blk].end;
 
-			end = find_end_of_node(start, limit, size);
+			if (uniform)
+				end = start + size;
+			else
+				end = find_end_of_node(start, limit, size);
 			/*
 			 * If there won't be at least FAKE_NODE_MIN_SIZE of
 			 * non-reserved memory in ZONE_DMA32 for the next node,
@@ -266,7 +303,8 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 			 * next node, this one must extend to the end of the
 			 * physical node.
 			 */
-			if (limit - end - mem_hole_size(end, limit) < size)
+			if ((limit - end - mem_hole_size(end, limit) < size)
+					&& !uniform)
 				end = limit;
 
 			ret = emu_setup_memblk(ei, pi, nid++ % MAX_NUMNODES,
@@ -276,7 +314,15 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
 				return ret;
 		}
 	}
-	return 0;
+	return nid;
+}
+
+static int __init split_nodes_size_interleave(struct numa_meminfo *ei,
+					      struct numa_meminfo *pi,
+					      u64 addr, u64 max_addr, u64 size)
+{
+	return split_nodes_size_interleave_uniform(ei, pi, addr, max_addr, size,
+			0, NULL, NUMA_NO_NODE);
 }
 
 int __init setup_emu2phys_nid(int *dfl_phys_nid)
@@ -346,7 +392,28 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	 * the fixed node size.  Otherwise, if it is just a single number N,
 	 * split the system RAM into N fake nodes.
 	 */
-	if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
+	if (strchr(emu_cmdline, 'U')) {
+		nodemask_t physnode_mask = numa_nodes_parsed;
+		unsigned long n;
+		int nid = 0;
+
+		n = simple_strtoul(emu_cmdline, &emu_cmdline, 0);
+		ret = -1;
+		for_each_node_mask(i, physnode_mask) {
+			ret = split_nodes_size_interleave_uniform(&ei, &pi,
+					pi.blk[i].start, pi.blk[i].end, 0,
+					n, &pi.blk[i], nid);
+			if (ret < 0)
+				break;
+			if (ret < n) {
+				pr_info("%s: phys: %d only got %d of %ld nodes, failing\n",
+						__func__, i, ret, n);
+				ret = -1;
+				break;
+			}
+			nid = ret;
+		}
+	} else if (strchr(emu_cmdline, 'M') || strchr(emu_cmdline, 'G')) {
 		u64 size;
 
 		size = memparse(emu_cmdline, &emu_cmdline);
-- 
cgit v1.2.3


From 956060a52795a060833e8de2d1bb89209e61bed2 Mon Sep 17 00:00:00 2001
From: Elaine Zhang <zhangqing@rock-chips.com>
Date: Fri, 15 Jun 2018 10:16:50 +0800
Subject: clk: rockchip: add support for half divider

The new Rockchip socs have optional half divider:
The formula is shown as:
	freq_out = 2*freq_in / (2*div + 3)
Is this the same for all of new SoCs.

So we use "branch_half_divider" + "COMPOSITE_NOMUX_HALFDIV \
DIV_HALF \ COMPOSITE_HALFDIV \ CMPOSITE_NOGATE_HALFDIV"
to hook that special divider clock-type into our clock-tree.

Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/Makefile           |   1 +
 drivers/clk/rockchip/clk-half-divider.c | 227 ++++++++++++++++++++++++++++++++
 drivers/clk/rockchip/clk.c              |  10 ++
 drivers/clk/rockchip/clk.h              |  85 ++++++++++++
 4 files changed, 323 insertions(+)
 create mode 100644 drivers/clk/rockchip/clk-half-divider.c

diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile
index 98e7b9429b83..4d4b7dee1675 100644
--- a/drivers/clk/rockchip/Makefile
+++ b/drivers/clk/rockchip/Makefile
@@ -6,6 +6,7 @@
 obj-y	+= clk.o
 obj-y	+= clk-pll.o
 obj-y	+= clk-cpu.o
+obj-y	+= clk-half-divider.o
 obj-y	+= clk-inverter.o
 obj-y	+= clk-mmc-phase.o
 obj-y	+= clk-muxgrf.o
diff --git a/drivers/clk/rockchip/clk-half-divider.c b/drivers/clk/rockchip/clk-half-divider.c
new file mode 100644
index 000000000000..b8da6e799423
--- /dev/null
+++ b/drivers/clk/rockchip/clk-half-divider.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Fuzhou Rockchip Electronics Co., Ltd
+ */
+
+#include <linux/slab.h>
+#include <linux/clk-provider.h>
+#include "clk.h"
+
+#define div_mask(width)	((1 << (width)) - 1)
+
+static bool _is_best_half_div(unsigned long rate, unsigned long now,
+			      unsigned long best, unsigned long flags)
+{
+	if (flags & CLK_DIVIDER_ROUND_CLOSEST)
+		return abs(rate - now) < abs(rate - best);
+
+	return now <= rate && now > best;
+}
+
+static unsigned long clk_half_divider_recalc_rate(struct clk_hw *hw,
+						  unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	unsigned int val;
+
+	val = clk_readl(divider->reg) >> divider->shift;
+	val &= div_mask(divider->width);
+	val = val * 2 + 3;
+
+	return DIV_ROUND_UP_ULL(((u64)parent_rate * 2), val);
+}
+
+static int clk_half_divider_bestdiv(struct clk_hw *hw, unsigned long rate,
+				    unsigned long *best_parent_rate, u8 width,
+				    unsigned long flags)
+{
+	unsigned int i, bestdiv = 0;
+	unsigned long parent_rate, best = 0, now, maxdiv;
+	unsigned long parent_rate_saved = *best_parent_rate;
+
+	if (!rate)
+		rate = 1;
+
+	maxdiv = div_mask(width);
+
+	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
+		parent_rate = *best_parent_rate;
+		bestdiv = DIV_ROUND_UP_ULL(((u64)parent_rate * 2), rate);
+		if (bestdiv < 3)
+			bestdiv = 0;
+		else
+			bestdiv = (bestdiv - 3) / 2;
+		bestdiv = bestdiv > maxdiv ? maxdiv : bestdiv;
+		return bestdiv;
+	}
+
+	/*
+	 * The maximum divider we can use without overflowing
+	 * unsigned long in rate * i below
+	 */
+	maxdiv = min(ULONG_MAX / rate, maxdiv);
+
+	for (i = 0; i <= maxdiv; i++) {
+		if (((u64)rate * (i * 2 + 3)) == ((u64)parent_rate_saved * 2)) {
+			/*
+			 * It's the most ideal case if the requested rate can be
+			 * divided from parent clock without needing to change
+			 * parent rate, so return the divider immediately.
+			 */
+			*best_parent_rate = parent_rate_saved;
+			return i;
+		}
+		parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw),
+						((u64)rate * (i * 2 + 3)) / 2);
+		now = DIV_ROUND_UP_ULL(((u64)parent_rate * 2),
+				       (i * 2 + 3));
+
+		if (_is_best_half_div(rate, now, best, flags)) {
+			bestdiv = i;
+			best = now;
+			*best_parent_rate = parent_rate;
+		}
+	}
+
+	if (!bestdiv) {
+		bestdiv = div_mask(width);
+		*best_parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw), 1);
+	}
+
+	return bestdiv;
+}
+
+static long clk_half_divider_round_rate(struct clk_hw *hw, unsigned long rate,
+					unsigned long *prate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	int div;
+
+	div = clk_half_divider_bestdiv(hw, rate, prate,
+				       divider->width,
+				       divider->flags);
+
+	return DIV_ROUND_UP_ULL(((u64)*prate * 2), div * 2 + 3);
+}
+
+static int clk_half_divider_set_rate(struct clk_hw *hw, unsigned long rate,
+				     unsigned long parent_rate)
+{
+	struct clk_divider *divider = to_clk_divider(hw);
+	unsigned int value;
+	unsigned long flags = 0;
+	u32 val;
+
+	value = DIV_ROUND_UP_ULL(((u64)parent_rate * 2), rate);
+	value = (value - 3) / 2;
+	value =  min_t(unsigned int, value, div_mask(divider->width));
+
+	if (divider->lock)
+		spin_lock_irqsave(divider->lock, flags);
+	else
+		__acquire(divider->lock);
+
+	if (divider->flags & CLK_DIVIDER_HIWORD_MASK) {
+		val = div_mask(divider->width) << (divider->shift + 16);
+	} else {
+		val = clk_readl(divider->reg);
+		val &= ~(div_mask(divider->width) << divider->shift);
+	}
+	val |= value << divider->shift;
+	clk_writel(val, divider->reg);
+
+	if (divider->lock)
+		spin_unlock_irqrestore(divider->lock, flags);
+	else
+		__release(divider->lock);
+
+	return 0;
+}
+
+const struct clk_ops clk_half_divider_ops = {
+	.recalc_rate = clk_half_divider_recalc_rate,
+	.round_rate = clk_half_divider_round_rate,
+	.set_rate = clk_half_divider_set_rate,
+};
+EXPORT_SYMBOL_GPL(clk_half_divider_ops);
+
+/**
+ * Register a clock branch.
+ * Most clock branches have a form like
+ *
+ * src1 --|--\
+ *        |M |--[GATE]-[DIV]-
+ * src2 --|--/
+ *
+ * sometimes without one of those components.
+ */
+struct clk *rockchip_clk_register_halfdiv(const char *name,
+					  const char *const *parent_names,
+					  u8 num_parents, void __iomem *base,
+					  int muxdiv_offset, u8 mux_shift,
+					  u8 mux_width, u8 mux_flags,
+					  u8 div_shift, u8 div_width,
+					  u8 div_flags, int gate_offset,
+					  u8 gate_shift, u8 gate_flags,
+					  unsigned long flags,
+					  spinlock_t *lock)
+{
+	struct clk *clk;
+	struct clk_mux *mux = NULL;
+	struct clk_gate *gate = NULL;
+	struct clk_divider *div = NULL;
+	const struct clk_ops *mux_ops = NULL, *div_ops = NULL,
+			     *gate_ops = NULL;
+
+	if (num_parents > 1) {
+		mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+		if (!mux)
+			return ERR_PTR(-ENOMEM);
+
+		mux->reg = base + muxdiv_offset;
+		mux->shift = mux_shift;
+		mux->mask = BIT(mux_width) - 1;
+		mux->flags = mux_flags;
+		mux->lock = lock;
+		mux_ops = (mux_flags & CLK_MUX_READ_ONLY) ? &clk_mux_ro_ops
+							: &clk_mux_ops;
+	}
+
+	if (gate_offset >= 0) {
+		gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+		if (!gate)
+			goto err_gate;
+
+		gate->flags = gate_flags;
+		gate->reg = base + gate_offset;
+		gate->bit_idx = gate_shift;
+		gate->lock = lock;
+		gate_ops = &clk_gate_ops;
+	}
+
+	if (div_width > 0) {
+		div = kzalloc(sizeof(*div), GFP_KERNEL);
+		if (!div)
+			goto err_div;
+
+		div->flags = div_flags;
+		div->reg = base + muxdiv_offset;
+		div->shift = div_shift;
+		div->width = div_width;
+		div->lock = lock;
+		div_ops = &clk_half_divider_ops;
+	}
+
+	clk = clk_register_composite(NULL, name, parent_names, num_parents,
+				     mux ? &mux->hw : NULL, mux_ops,
+				     div ? &div->hw : NULL, div_ops,
+				     gate ? &gate->hw : NULL, gate_ops,
+				     flags);
+
+	return clk;
+err_div:
+	kfree(gate);
+err_gate:
+	kfree(mux);
+	return ERR_PTR(-ENOMEM);
+}
diff --git a/drivers/clk/rockchip/clk.c b/drivers/clk/rockchip/clk.c
index 326b3fa44f5d..c3ad92965823 100644
--- a/drivers/clk/rockchip/clk.c
+++ b/drivers/clk/rockchip/clk.c
@@ -492,6 +492,16 @@ void __init rockchip_clk_register_branches(
 				list->gate_flags, flags, list->child,
 				&ctx->lock);
 			break;
+		case branch_half_divider:
+			clk = rockchip_clk_register_halfdiv(list->name,
+				list->parent_names, list->num_parents,
+				ctx->reg_base, list->muxdiv_offset,
+				list->mux_shift, list->mux_width,
+				list->mux_flags, list->div_shift,
+				list->div_width, list->div_flags,
+				list->gate_offset, list->gate_shift,
+				list->gate_flags, flags, &ctx->lock);
+			break;
 		case branch_gate:
 			flags |= CLK_SET_RATE_PARENT;
 
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index ef601dded32c..23c569a875d4 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h
@@ -354,6 +354,7 @@ enum rockchip_clk_branch_type {
 	branch_inverter,
 	branch_factor,
 	branch_ddrclk,
+	branch_half_divider,
 };
 
 struct rockchip_clk_branch {
@@ -684,6 +685,79 @@ struct rockchip_clk_branch {
 		.gate_flags	= gf,				\
 	}
 
+#define COMPOSITE_HALFDIV(_id, cname, pnames, f, mo, ms, mw, mf, ds, dw,\
+			  df, go, gs, gf)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define COMPOSITE_NOGATE_HALFDIV(_id, cname, pnames, f, mo, ms, mw, mf,	\
+				 ds, dw, df)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= pnames,			\
+		.num_parents	= ARRAY_SIZE(pnames),		\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.mux_shift	= ms,				\
+		.mux_width	= mw,				\
+		.mux_flags	= mf,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= -1,				\
+	}
+
+#define COMPOSITE_NOMUX_HALFDIV(_id, cname, pname, f, mo, ds, dw, df,	\
+			go, gs, gf)				\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= mo,				\
+		.div_shift	= ds,				\
+		.div_width	= dw,				\
+		.div_flags	= df,				\
+		.gate_offset	= go,				\
+		.gate_shift	= gs,				\
+		.gate_flags	= gf,				\
+	}
+
+#define DIV_HALF(_id, cname, pname, f, o, s, w, df)			\
+	{							\
+		.id		= _id,				\
+		.branch_type	= branch_half_divider,		\
+		.name		= cname,			\
+		.parent_names	= (const char *[]){ pname },	\
+		.num_parents	= 1,				\
+		.flags		= f,				\
+		.muxdiv_offset	= o,				\
+		.div_shift	= s,				\
+		.div_width	= w,				\
+		.div_flags	= df,				\
+		.gate_offset	= -1,				\
+	}
+
 struct rockchip_clk_provider *rockchip_clk_init(struct device_node *np,
 			void __iomem *base, unsigned long nr_clks);
 void rockchip_clk_of_add_provider(struct device_node *np,
@@ -708,6 +782,17 @@ void rockchip_register_restart_notifier(struct rockchip_clk_provider *ctx,
 
 #define ROCKCHIP_SOFTRST_HIWORD_MASK	BIT(0)
 
+struct clk *rockchip_clk_register_halfdiv(const char *name,
+					  const char *const *parent_names,
+					  u8 num_parents, void __iomem *base,
+					  int muxdiv_offset, u8 mux_shift,
+					  u8 mux_width, u8 mux_flags,
+					  u8 div_shift, u8 div_width,
+					  u8 div_flags, int gate_offset,
+					  u8 gate_shift, u8 gate_flags,
+					  unsigned long flags,
+					  spinlock_t *lock);
+
 #ifdef CONFIG_RESET_CONTROLLER
 void rockchip_register_softrst(struct device_node *np,
 			       unsigned int num_regs,
-- 
cgit v1.2.3


From 243229b11121fbc90d9ee875292dfc75ecf53040 Mon Sep 17 00:00:00 2001
From: Elaine Zhang <zhangqing@rock-chips.com>
Date: Fri, 15 Jun 2018 10:16:51 +0800
Subject: clk: rockchip: add clock controller for px30

Add the clock tree definition for the new px30 SoC.

Signed-off-by: Elaine Zhang <zhangqing@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/Makefile   |    1 +
 drivers/clk/rockchip/clk-px30.c | 1039 +++++++++++++++++++++++++++++++++++++++
 drivers/clk/rockchip/clk.h      |   41 +-
 3 files changed, 1080 insertions(+), 1 deletion(-)
 create mode 100644 drivers/clk/rockchip/clk-px30.c

diff --git a/drivers/clk/rockchip/Makefile b/drivers/clk/rockchip/Makefile
index 4d4b7dee1675..ff35ab463a6f 100644
--- a/drivers/clk/rockchip/Makefile
+++ b/drivers/clk/rockchip/Makefile
@@ -13,6 +13,7 @@ obj-y	+= clk-muxgrf.o
 obj-y	+= clk-ddr.o
 obj-$(CONFIG_RESET_CONTROLLER)	+= softrst.o
 
+obj-y	+= clk-px30.o
 obj-y	+= clk-rv1108.o
 obj-y	+= clk-rk3036.o
 obj-y	+= clk-rk3128.o
diff --git a/drivers/clk/rockchip/clk-px30.c b/drivers/clk/rockchip/clk-px30.c
new file mode 100644
index 000000000000..601a77f1af78
--- /dev/null
+++ b/drivers/clk/rockchip/clk-px30.c
@@ -0,0 +1,1039 @@
+/*
+ * Copyright (c) 2018 Rockchip Electronics Co. Ltd.
+ * Author: Elaine Zhang<zhangqing@rock-chips.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/syscore_ops.h>
+#include <dt-bindings/clock/px30-cru.h>
+#include "clk.h"
+
+#define PX30_GRF_SOC_STATUS0		0x480
+
+enum px30_plls {
+	apll, dpll, cpll, npll, apll_b_h, apll_b_l,
+};
+
+enum px30_pmu_plls {
+	gpll,
+};
+
+static struct rockchip_pll_rate_table px30_pll_rates[] = {
+	/* _mhz, _refdiv, _fbdiv, _postdiv1, _postdiv2, _dsmpd, _frac */
+	RK3036_PLL_RATE(1608000000, 1, 67, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1584000000, 1, 66, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1560000000, 1, 65, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1536000000, 1, 64, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1512000000, 1, 63, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1488000000, 1, 62, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1464000000, 1, 61, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1440000000, 1, 60, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1416000000, 1, 59, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1392000000, 1, 58, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1368000000, 1, 57, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1344000000, 1, 56, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1320000000, 1, 55, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1296000000, 1, 54, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1272000000, 1, 53, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1248000000, 1, 52, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1200000000, 1, 50, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1188000000, 2, 99, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1104000000, 1, 46, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1100000000, 12, 550, 1, 1, 1, 0),
+	RK3036_PLL_RATE(1008000000, 1, 84, 2, 1, 1, 0),
+	RK3036_PLL_RATE(1000000000, 6, 500, 2, 1, 1, 0),
+	RK3036_PLL_RATE(984000000, 1, 82, 2, 1, 1, 0),
+	RK3036_PLL_RATE(960000000, 1, 80, 2, 1, 1, 0),
+	RK3036_PLL_RATE(936000000, 1, 78, 2, 1, 1, 0),
+	RK3036_PLL_RATE(912000000, 1, 76, 2, 1, 1, 0),
+	RK3036_PLL_RATE(900000000, 4, 300, 2, 1, 1, 0),
+	RK3036_PLL_RATE(888000000, 1, 74, 2, 1, 1, 0),
+	RK3036_PLL_RATE(864000000, 1, 72, 2, 1, 1, 0),
+	RK3036_PLL_RATE(840000000, 1, 70, 2, 1, 1, 0),
+	RK3036_PLL_RATE(816000000, 1, 68, 2, 1, 1, 0),
+	RK3036_PLL_RATE(800000000, 6, 400, 2, 1, 1, 0),
+	RK3036_PLL_RATE(700000000, 6, 350, 2, 1, 1, 0),
+	RK3036_PLL_RATE(696000000, 1, 58, 2, 1, 1, 0),
+	RK3036_PLL_RATE(624000000, 1, 52, 2, 1, 1, 0),
+	RK3036_PLL_RATE(600000000, 1, 75, 3, 1, 1, 0),
+	RK3036_PLL_RATE(594000000, 2, 99, 2, 1, 1, 0),
+	RK3036_PLL_RATE(504000000, 1, 63, 3, 1, 1, 0),
+	RK3036_PLL_RATE(500000000, 6, 250, 2, 1, 1, 0),
+	RK3036_PLL_RATE(408000000, 1, 68, 2, 2, 1, 0),
+	RK3036_PLL_RATE(312000000, 1, 52, 2, 2, 1, 0),
+	RK3036_PLL_RATE(216000000, 1, 72, 4, 2, 1, 0),
+	RK3036_PLL_RATE(96000000, 1, 64, 4, 4, 1, 0),
+	{ /* sentinel */ },
+};
+
+#define PX30_DIV_ACLKM_MASK		0x7
+#define PX30_DIV_ACLKM_SHIFT		12
+#define PX30_DIV_PCLK_DBG_MASK	0xf
+#define PX30_DIV_PCLK_DBG_SHIFT	8
+
+#define PX30_CLKSEL0(_aclk_core, _pclk_dbg)				\
+{									\
+	.reg = PX30_CLKSEL_CON(0),					\
+	.val = HIWORD_UPDATE(_aclk_core, PX30_DIV_ACLKM_MASK,		\
+			     PX30_DIV_ACLKM_SHIFT) |			\
+	       HIWORD_UPDATE(_pclk_dbg, PX30_DIV_PCLK_DBG_MASK,	\
+			     PX30_DIV_PCLK_DBG_SHIFT),		\
+}
+
+#define PX30_CPUCLK_RATE(_prate, _aclk_core, _pclk_dbg)		\
+{									\
+	.prate = _prate,						\
+	.divs = {							\
+		PX30_CLKSEL0(_aclk_core, _pclk_dbg),			\
+	},								\
+}
+
+static struct rockchip_cpuclk_rate_table px30_cpuclk_rates[] __initdata = {
+	PX30_CPUCLK_RATE(1608000000, 1, 7),
+	PX30_CPUCLK_RATE(1584000000, 1, 7),
+	PX30_CPUCLK_RATE(1560000000, 1, 7),
+	PX30_CPUCLK_RATE(1536000000, 1, 7),
+	PX30_CPUCLK_RATE(1512000000, 1, 7),
+	PX30_CPUCLK_RATE(1488000000, 1, 5),
+	PX30_CPUCLK_RATE(1464000000, 1, 5),
+	PX30_CPUCLK_RATE(1440000000, 1, 5),
+	PX30_CPUCLK_RATE(1416000000, 1, 5),
+	PX30_CPUCLK_RATE(1392000000, 1, 5),
+	PX30_CPUCLK_RATE(1368000000, 1, 5),
+	PX30_CPUCLK_RATE(1344000000, 1, 5),
+	PX30_CPUCLK_RATE(1320000000, 1, 5),
+	PX30_CPUCLK_RATE(1296000000, 1, 5),
+	PX30_CPUCLK_RATE(1272000000, 1, 5),
+	PX30_CPUCLK_RATE(1248000000, 1, 5),
+	PX30_CPUCLK_RATE(1224000000, 1, 5),
+	PX30_CPUCLK_RATE(1200000000, 1, 5),
+	PX30_CPUCLK_RATE(1104000000, 1, 5),
+	PX30_CPUCLK_RATE(1008000000, 1, 5),
+	PX30_CPUCLK_RATE(912000000, 1, 5),
+	PX30_CPUCLK_RATE(816000000, 1, 3),
+	PX30_CPUCLK_RATE(696000000, 1, 3),
+	PX30_CPUCLK_RATE(600000000, 1, 3),
+	PX30_CPUCLK_RATE(408000000, 1, 1),
+	PX30_CPUCLK_RATE(312000000, 1, 1),
+	PX30_CPUCLK_RATE(216000000,  1, 1),
+	PX30_CPUCLK_RATE(96000000, 1, 1),
+};
+
+static const struct rockchip_cpuclk_reg_data px30_cpuclk_data = {
+	.core_reg = PX30_CLKSEL_CON(0),
+	.div_core_shift = 0,
+	.div_core_mask = 0xf,
+	.mux_core_alt = 1,
+	.mux_core_main = 0,
+	.mux_core_shift = 7,
+	.mux_core_mask = 0x1,
+};
+
+PNAME(mux_pll_p)		= { "xin24m"};
+PNAME(mux_usb480m_p)		= { "xin24m", "usb480m_phy", "clk_rtc32k_pmu" };
+PNAME(mux_armclk_p)		= { "apll_core", "gpll_core" };
+PNAME(mux_ddrphy_p)		= { "dpll_ddr", "gpll_ddr" };
+PNAME(mux_ddrstdby_p)		= { "clk_ddrphy1x", "clk_stdby_2wrap" };
+PNAME(mux_4plls_p)		= { "gpll", "dummy_cpll", "usb480m", "npll" };
+PNAME(mux_cpll_npll_p)		= { "cpll", "npll" };
+PNAME(mux_npll_cpll_p)		= { "npll", "cpll" };
+PNAME(mux_gpll_cpll_p)		= { "gpll", "dummy_cpll" };
+PNAME(mux_gpll_npll_p)		= { "gpll", "npll" };
+PNAME(mux_gpll_xin24m_p)		= { "gpll", "xin24m"};
+PNAME(mux_gpll_cpll_npll_p)		= { "gpll", "dummy_cpll", "npll" };
+PNAME(mux_gpll_cpll_npll_xin24m_p)	= { "gpll", "dummy_cpll", "npll", "xin24m" };
+PNAME(mux_gpll_xin24m_npll_p)		= { "gpll", "xin24m", "npll"};
+PNAME(mux_pdm_p)		= { "clk_pdm_src", "clk_pdm_frac" };
+PNAME(mux_i2s0_tx_p)		= { "clk_i2s0_tx_src", "clk_i2s0_tx_frac", "mclk_i2s0_tx_in", "xin12m"};
+PNAME(mux_i2s0_rx_p)		= { "clk_i2s0_rx_src", "clk_i2s0_rx_frac", "mclk_i2s0_rx_in", "xin12m"};
+PNAME(mux_i2s1_p)		= { "clk_i2s1_src", "clk_i2s1_frac", "i2s1_clkin", "xin12m"};
+PNAME(mux_i2s2_p)		= { "clk_i2s2_src", "clk_i2s2_frac", "i2s2_clkin", "xin12m"};
+PNAME(mux_i2s0_tx_out_p)	= { "clk_i2s0_tx", "xin12m", "clk_i2s0_rx"};
+PNAME(mux_i2s0_rx_out_p)	= { "clk_i2s0_rx", "xin12m", "clk_i2s0_tx"};
+PNAME(mux_i2s1_out_p)		= { "clk_i2s1", "xin12m"};
+PNAME(mux_i2s2_out_p)		= { "clk_i2s2", "xin12m"};
+PNAME(mux_i2s0_tx_rx_p)		= { "clk_i2s0_tx_mux", "clk_i2s0_rx_mux"};
+PNAME(mux_i2s0_rx_tx_p)		= { "clk_i2s0_rx_mux", "clk_i2s0_tx_mux"};
+PNAME(mux_uart_src_p)		= { "gpll", "xin24m", "usb480m", "npll" };
+PNAME(mux_uart1_p)		= { "clk_uart1_src", "clk_uart1_np5", "clk_uart1_frac" };
+PNAME(mux_uart2_p)		= { "clk_uart2_src", "clk_uart2_np5", "clk_uart2_frac" };
+PNAME(mux_uart3_p)		= { "clk_uart3_src", "clk_uart3_np5", "clk_uart3_frac" };
+PNAME(mux_uart4_p)		= { "clk_uart4_src", "clk_uart4_np5", "clk_uart4_frac" };
+PNAME(mux_uart5_p)		= { "clk_uart5_src", "clk_uart5_np5", "clk_uart5_frac" };
+PNAME(mux_cif_out_p)		= { "xin24m", "dummy_cpll", "npll", "usb480m" };
+PNAME(mux_dclk_vopb_p)		= { "dclk_vopb_src", "dclk_vopb_frac", "xin24m" };
+PNAME(mux_dclk_vopl_p)		= { "dclk_vopl_src", "dclk_vopl_frac", "xin24m" };
+PNAME(mux_gmac_p)		= { "clk_gmac_src", "gmac_clkin" };
+PNAME(mux_gmac_rmii_sel_p)	= { "clk_gmac_rx_tx_div20", "clk_gmac_rx_tx_div2" };
+PNAME(mux_rtc32k_pmu_p)		= { "xin32k", "pmu_pvtm_32k", "clk_rtc32k_frac", };
+PNAME(mux_wifi_pmu_p)		= { "xin24m", "clk_wifi_pmu_src" };
+PNAME(mux_uart0_pmu_p)		= { "clk_uart0_pmu_src", "clk_uart0_np5", "clk_uart0_frac" };
+PNAME(mux_usbphy_ref_p)		= { "xin24m", "clk_ref24m_pmu" };
+PNAME(mux_mipidsiphy_ref_p)	= { "xin24m", "clk_ref24m_pmu" };
+PNAME(mux_gpu_p)		= { "clk_gpu_div", "clk_gpu_np5" };
+
+static struct rockchip_pll_clock px30_pll_clks[] __initdata = {
+	[apll] = PLL(pll_rk3328, PLL_APLL, "apll", mux_pll_p,
+		     0, PX30_PLL_CON(0),
+		     PX30_MODE_CON, 0, 0, 0, px30_pll_rates),
+	[dpll] = PLL(pll_rk3328, PLL_DPLL, "dpll", mux_pll_p,
+		     0, PX30_PLL_CON(8),
+		     PX30_MODE_CON, 4, 1, 0, NULL),
+	[cpll] = PLL(pll_rk3328, PLL_CPLL, "cpll", mux_pll_p,
+		     0, PX30_PLL_CON(16),
+		     PX30_MODE_CON, 2, 2, 0, px30_pll_rates),
+	[npll] = PLL(pll_rk3328, PLL_NPLL, "npll", mux_pll_p,
+		     0, PX30_PLL_CON(24),
+		     PX30_MODE_CON, 6, 4, 0, px30_pll_rates),
+};
+
+static struct rockchip_pll_clock px30_pmu_pll_clks[] __initdata = {
+	[gpll] = PLL(pll_rk3328, PLL_GPLL, "gpll",  mux_pll_p, 0, PX30_PMU_PLL_CON(0),
+		     PX30_PMU_MODE, 0, 3, 0, px30_pll_rates),
+};
+
+#define MFLAGS CLK_MUX_HIWORD_MASK
+#define DFLAGS CLK_DIVIDER_HIWORD_MASK
+#define GFLAGS (CLK_GATE_HIWORD_MASK | CLK_GATE_SET_TO_DISABLE)
+
+static struct rockchip_clk_branch px30_pdm_fracmux __initdata =
+	MUX(0, "clk_pdm_mux", mux_pdm_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(26), 15, 1, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s0_tx_fracmux __initdata =
+	MUX(0, "clk_i2s0_tx_mux", mux_i2s0_tx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(28), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s0_rx_fracmux __initdata =
+	MUX(0, "clk_i2s0_rx_mux", mux_i2s0_rx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(58), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s1_fracmux __initdata =
+	MUX(0, "clk_i2s1_mux", mux_i2s1_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(30), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_i2s2_fracmux __initdata =
+	MUX(0, "clk_i2s2_mux", mux_i2s2_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(32), 10, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart1_fracmux __initdata =
+	MUX(0, "clk_uart1_mux", mux_uart1_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(35), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart2_fracmux __initdata =
+	MUX(0, "clk_uart2_mux", mux_uart2_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(38), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart3_fracmux __initdata =
+	MUX(0, "clk_uart3_mux", mux_uart3_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(41), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart4_fracmux __initdata =
+	MUX(0, "clk_uart4_mux", mux_uart4_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(44), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart5_fracmux __initdata =
+	MUX(0, "clk_uart5_mux", mux_uart5_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(47), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_dclk_vopb_fracmux __initdata =
+	MUX(0, "dclk_vopb_mux", mux_dclk_vopb_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(5), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_dclk_vopl_fracmux __initdata =
+	MUX(0, "dclk_vopl_mux", mux_dclk_vopl_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(8), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_rtc32k_pmu_fracmux __initdata =
+	MUX(SCLK_RTC32K_PMU, "clk_rtc32k_pmu", mux_rtc32k_pmu_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(0), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_uart0_pmu_fracmux __initdata =
+	MUX(0, "clk_uart0_pmu_mux", mux_uart0_pmu_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(4), 14, 2, MFLAGS);
+
+static struct rockchip_clk_branch px30_clk_branches[] __initdata = {
+	/*
+	 * Clock-Architecture Diagram 1
+	 */
+
+	MUX(USB480M, "usb480m", mux_usb480m_p, CLK_SET_RATE_PARENT,
+			PX30_MODE_CON, 8, 2, MFLAGS),
+	FACTOR(0, "xin12m", "xin24m", 0, 1, 2),
+
+	/*
+	 * Clock-Architecture Diagram 3
+	 */
+
+	/* PD_CORE */
+	GATE(0, "apll_core", "apll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 0, GFLAGS),
+	GATE(0, "gpll_core", "gpll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 0, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_dbg", "armclk", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(0), 8, 4, DFLAGS | CLK_DIVIDER_READ_ONLY,
+			PX30_CLKGATE_CON(0), 2, GFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_core", "armclk", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(0), 12, 3, DFLAGS | CLK_DIVIDER_READ_ONLY,
+			PX30_CLKGATE_CON(0), 1, GFLAGS),
+	GATE(0, "aclk_core_niu", "aclk_core", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 4, GFLAGS),
+	GATE(0, "aclk_core_prf", "aclk_core", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 5, GFLAGS),
+	GATE(0, "pclk_dbg_niu", "pclk_dbg", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 5, GFLAGS),
+	GATE(0, "pclk_core_dbg", "pclk_dbg", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 6, GFLAGS),
+	GATE(0, "pclk_core_grf", "pclk_dbg", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 6, GFLAGS),
+
+	GATE(0, "clk_jtag", "jtag_clkin", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 3, GFLAGS),
+	GATE(SCLK_PVTM, "clk_pvtm", "xin24m", 0,
+			PX30_CLKGATE_CON(17), 4, GFLAGS),
+
+	/* PD_GPU */
+	COMPOSITE_NODIV(0, "clk_gpu_src", mux_4plls_p, 0,
+			PX30_CLKSEL_CON(1), 6, 2, MFLAGS,
+			PX30_CLKGATE_CON(0), 8, GFLAGS),
+	COMPOSITE_NOMUX(0, "clk_gpu_div", "clk_gpu_src", 0,
+			PX30_CLKSEL_CON(1), 0, 4, DFLAGS,
+			PX30_CLKGATE_CON(0), 12, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_gpu_np5", "clk_gpu_src", 0,
+			PX30_CLKSEL_CON(1), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(0), 9, GFLAGS),
+	COMPOSITE_NODIV(SCLK_GPU, "clk_gpu", mux_gpu_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(1), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(0), 10, GFLAGS),
+	COMPOSITE_NOMUX(0, "aclk_gpu", "clk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(1), 13, 2, DFLAGS,
+			PX30_CLKGATE_CON(17), 10, GFLAGS),
+	GATE(0, "aclk_gpu_niu", "aclk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 11, GFLAGS),
+	GATE(0, "aclk_gpu_prf", "aclk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 8, GFLAGS),
+	GATE(0, "pclk_gpu_grf", "aclk_gpu", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(17), 9, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 4
+	 */
+
+	/* PD_DDR */
+	GATE(0, "dpll_ddr", "dpll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 7, GFLAGS),
+	GATE(0, "gpll_ddr", "gpll", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 13, GFLAGS),
+	COMPOSITE_NOGATE(SCLK_DDRCLK, "sclk_ddrc", mux_ddrphy_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 7, 1, MFLAGS, 0, 3, DFLAGS | CLK_DIVIDER_POWER_OF_TWO),
+	COMPOSITE_NOGATE(0, "clk_ddrphy4x", mux_ddrphy_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 7, 1, MFLAGS, 0, 3, DFLAGS),
+	FACTOR_GATE(0, "clk_ddrphy1x", "clk_ddrphy4x", CLK_IGNORE_UNUSED, 1, 4,
+			PX30_CLKGATE_CON(0), 14, GFLAGS),
+	FACTOR_GATE(0, "clk_stdby_2wrap", "clk_ddrphy4x", CLK_IGNORE_UNUSED, 1, 4,
+			PX30_CLKGATE_CON(1), 0, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_ddrstdby", mux_ddrstdby_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 4, 1, MFLAGS,
+			PX30_CLKGATE_CON(1), 13, GFLAGS),
+	GATE(0, "aclk_split", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 15, GFLAGS),
+	GATE(0, "clk_msch", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 8, GFLAGS),
+	GATE(0, "aclk_ddrc", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 5, GFLAGS),
+	GATE(0, "clk_core_ddrc", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 6, GFLAGS),
+	GATE(0, "aclk_cmd_buff", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 6, GFLAGS),
+	GATE(0, "clk_ddrmon", "clk_ddrphy1x", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 11, GFLAGS),
+
+	GATE(0, "clk_ddrmon_timer", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(0), 15, GFLAGS),
+
+	COMPOSITE_NOMUX(PCLK_DDR, "pclk_ddr", "gpll", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(2), 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(1), 1, GFLAGS),
+	GATE(0, "pclk_ddrmon", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 10, GFLAGS),
+	GATE(0, "pclk_ddrc", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 7, GFLAGS),
+	GATE(0, "pclk_msch", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 9, GFLAGS),
+	GATE(0, "pclk_stdby", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 12, GFLAGS),
+	GATE(0, "pclk_ddr_grf", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 14, GFLAGS),
+	GATE(0, "pclk_cmdbuff", "pclk_ddr", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(1), 3, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 5
+	 */
+
+	/* PD_VI */
+	COMPOSITE(ACLK_VI_PRE, "aclk_vi_pre", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 8, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_VI_PRE, "hclk_vi_pre", "aclk_vi_pre", 0,
+			PX30_CLKSEL_CON(11), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(4), 12, GFLAGS),
+	COMPOSITE(SCLK_ISP, "clk_isp", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(12), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 9, GFLAGS),
+	COMPOSITE(SCLK_CIF_OUT, "clk_cif_out", mux_cif_out_p, 0,
+			PX30_CLKSEL_CON(13), 6, 2, MFLAGS, 0, 6, DFLAGS,
+			PX30_CLKGATE_CON(4), 11, GFLAGS),
+	GATE(PCLK_ISP, "pclkin_isp", "ext_pclkin", 0,
+			PX30_CLKGATE_CON(4), 13, GFLAGS),
+	GATE(PCLK_CIF, "pclkin_cif", "ext_pclkin", 0,
+			PX30_CLKGATE_CON(4), 14, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 6
+	 */
+
+	/* PD_VO */
+	COMPOSITE(ACLK_VO_PRE, "aclk_vo_pre", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(3), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(2), 0, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_VO_PRE, "hclk_vo_pre", "aclk_vo_pre", 0,
+			PX30_CLKSEL_CON(3), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(2), 12, GFLAGS),
+	COMPOSITE_NOMUX(PCLK_VO_PRE, "pclk_vo_pre", "aclk_vo_pre", 0,
+			PX30_CLKSEL_CON(3), 12, 4, DFLAGS,
+			PX30_CLKGATE_CON(2), 13, GFLAGS),
+	COMPOSITE(SCLK_RGA_CORE, "clk_rga_core", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(4), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(2), 1, GFLAGS),
+
+	COMPOSITE(SCLK_VOPB_PWM, "clk_vopb_pwm", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(7), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(2), 5, GFLAGS),
+	COMPOSITE(0, "dclk_vopb_src", mux_cpll_npll_p, CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+			PX30_CLKSEL_CON(5), 11, 1, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(2), 2, GFLAGS),
+	COMPOSITE_FRACMUX(0, "dclk_vopb_frac", "dclk_vopb_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(6), 0,
+			PX30_CLKGATE_CON(2), 3, GFLAGS,
+			&px30_dclk_vopb_fracmux),
+	GATE(DCLK_VOPB, "dclk_vopb", "dclk_vopb_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(2), 4, GFLAGS),
+	COMPOSITE(0, "dclk_vopl_src", mux_npll_cpll_p, 0,
+			PX30_CLKSEL_CON(8), 11, 1, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(2), 6, GFLAGS),
+	COMPOSITE_FRACMUX(0, "dclk_vopl_frac", "dclk_vopl_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(9), 0,
+			PX30_CLKGATE_CON(2), 7, GFLAGS,
+			&px30_dclk_vopl_fracmux),
+	GATE(DCLK_VOPL, "dclk_vopl", "dclk_vopl_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(2), 8, GFLAGS),
+
+	/* PD_VPU */
+	COMPOSITE(0, "aclk_vpu_pre", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(10), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 0, GFLAGS),
+	COMPOSITE_NOMUX(0, "hclk_vpu_pre", "aclk_vpu_pre", 0,
+			PX30_CLKSEL_CON(10), 8, 4, DFLAGS,
+			PX30_CLKGATE_CON(4), 2, GFLAGS),
+	COMPOSITE(SCLK_CORE_VPU, "sclk_core_vpu", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(13), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(4), 1, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 7
+	 */
+
+	COMPOSITE_NODIV(ACLK_PERI_SRC, "aclk_peri_src", mux_gpll_cpll_p, 0,
+			PX30_CLKSEL_CON(14), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(5), 7, GFLAGS),
+	COMPOSITE_NOMUX(ACLK_PERI_PRE, "aclk_peri_pre", "aclk_peri_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(14), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(5), 8, GFLAGS),
+	DIV(HCLK_PERI_PRE, "hclk_peri_pre", "aclk_peri_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(14), 8, 5, DFLAGS),
+
+	/* PD_MMC_NAND */
+	GATE(HCLK_MMC_NAND, "hclk_mmc_nand", "hclk_peri_pre", 0,
+			PX30_CLKGATE_CON(6), 0, GFLAGS),
+	COMPOSITE(SCLK_NANDC, "clk_nandc", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(15), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(5), 13, GFLAGS),
+
+	COMPOSITE(SCLK_SDIO, "clk_sdio", mux_gpll_cpll_npll_xin24m_p, 0,
+			PX30_CLKSEL_CON(18), 14, 2, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(6), 3, GFLAGS),
+
+	COMPOSITE(SCLK_EMMC, "clk_emmc", mux_gpll_cpll_npll_xin24m_p, 0,
+			PX30_CLKSEL_CON(20), 14, 2, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(6), 6, GFLAGS),
+
+	COMPOSITE(SCLK_SFC, "clk_sfc", mux_gpll_cpll_p, 0,
+			PX30_CLKSEL_CON(22), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(6), 7, GFLAGS),
+
+	MMC(SCLK_SDMMC_DRV, "sdmmc_drv", "clk_sdmmc",
+	    PX30_SDMMC_CON0, 1),
+	MMC(SCLK_SDMMC_SAMPLE, "sdmmc_sample", "clk_sdmmc",
+	    PX30_SDMMC_CON1, 1),
+
+	MMC(SCLK_SDIO_DRV, "sdio_drv", "clk_sdio",
+	    PX30_SDIO_CON0, 1),
+	MMC(SCLK_SDIO_SAMPLE, "sdio_sample", "clk_sdio",
+	    PX30_SDIO_CON1, 1),
+
+	MMC(SCLK_EMMC_DRV, "emmc_drv", "clk_emmc",
+	    PX30_EMMC_CON0, 1),
+	MMC(SCLK_EMMC_SAMPLE, "emmc_sample", "clk_emmc",
+	    PX30_EMMC_CON1, 1),
+
+	/* PD_SDCARD */
+	GATE(0, "hclk_sdmmc_pre", "hclk_peri_pre", 0,
+			PX30_CLKGATE_CON(6), 12, GFLAGS),
+	COMPOSITE(SCLK_SDMMC, "clk_sdmmc", mux_gpll_cpll_npll_xin24m_p, 0,
+			PX30_CLKSEL_CON(16), 14, 2, MFLAGS, 0, 8, DFLAGS,
+			PX30_CLKGATE_CON(6), 15, GFLAGS),
+
+	/* PD_USB */
+	GATE(HCLK_USB, "hclk_usb", "hclk_peri_pre", 0,
+			PX30_CLKGATE_CON(7), 2, GFLAGS),
+	GATE(SCLK_OTG_ADP, "clk_otg_adp", "clk_rtc32k_pmu", 0,
+			PX30_CLKGATE_CON(7), 3, GFLAGS),
+
+	/* PD_GMAC */
+	COMPOSITE(SCLK_GMAC_SRC, "clk_gmac_src", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(22), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(7), 11, GFLAGS),
+	MUX(SCLK_GMAC, "clk_gmac", mux_gmac_p,  CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(23), 6, 1, MFLAGS),
+	GATE(SCLK_MAC_REF, "clk_mac_ref", "clk_gmac", 0,
+			PX30_CLKGATE_CON(7), 15, GFLAGS),
+	GATE(SCLK_GMAC_RX_TX, "clk_gmac_rx_tx", "clk_gmac", 0,
+			PX30_CLKGATE_CON(7), 13, GFLAGS),
+	FACTOR(0, "clk_gmac_rx_tx_div2", "clk_gmac_rx_tx", 0, 1, 2),
+	FACTOR(0, "clk_gmac_rx_tx_div20", "clk_gmac_rx_tx", 0, 1, 20),
+	MUX(SCLK_GMAC_RMII, "clk_gmac_rmii_sel", mux_gmac_rmii_sel_p,  CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(23), 7, 1, MFLAGS),
+
+	GATE(0, "aclk_gmac_pre", "aclk_peri_pre", 0,
+			PX30_CLKGATE_CON(7), 10, GFLAGS),
+	COMPOSITE_NOMUX(0, "pclk_gmac_pre", "aclk_gmac_pre", 0,
+			PX30_CLKSEL_CON(23), 0, 4, DFLAGS,
+			PX30_CLKGATE_CON(7), 12, GFLAGS),
+
+	COMPOSITE(SCLK_MAC_OUT, "clk_mac_out", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(12), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 5, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 8
+	 */
+
+	/* PD_BUS */
+	COMPOSITE_NODIV(ACLK_BUS_SRC, "aclk_bus_src", mux_gpll_cpll_p, CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(23), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(8), 6, GFLAGS),
+	COMPOSITE_NOMUX(HCLK_BUS_PRE, "hclk_bus_pre", "aclk_bus_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(24), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 8, GFLAGS),
+	COMPOSITE_NOMUX(ACLK_BUS_PRE, "aclk_bus_pre", "aclk_bus_src", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(23), 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 7, GFLAGS),
+	COMPOSITE_NOMUX(PCLK_BUS_PRE, "pclk_bus_pre", "aclk_bus_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKSEL_CON(24), 8, 2, DFLAGS,
+			PX30_CLKGATE_CON(8), 9, GFLAGS),
+	GATE(0, "pclk_top_pre", "pclk_bus_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(8), 10, GFLAGS),
+
+	COMPOSITE(0, "clk_pdm_src", mux_gpll_xin24m_npll_p, 0,
+			PX30_CLKSEL_CON(26), 8, 2, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(9), 9, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_pdm_frac", "clk_pdm_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(27), 0,
+			PX30_CLKGATE_CON(9), 10, GFLAGS,
+			&px30_pdm_fracmux),
+	GATE(SCLK_PDM, "clk_pdm", "clk_pdm_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(9), 11, GFLAGS),
+
+	COMPOSITE(0, "clk_i2s0_tx_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(28), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(9), 12, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s0_tx_frac", "clk_i2s0_tx_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(29), 0,
+			PX30_CLKGATE_CON(9), 13, GFLAGS,
+			&px30_i2s0_tx_fracmux),
+	COMPOSITE_NODIV(SCLK_I2S0_TX, "clk_i2s0_tx", mux_i2s0_tx_rx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(28), 12, 1, MFLAGS,
+			PX30_CLKGATE_CON(9), 14, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s0_tx_out_pre", mux_i2s0_tx_out_p, 0,
+			PX30_CLKSEL_CON(28), 14, 2, MFLAGS,
+			PX30_CLKGATE_CON(9), 15, GFLAGS),
+	GATE(SCLK_I2S0_TX_OUT, "clk_i2s0_tx_out", "clk_i2s0_tx_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 8, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(0, "clk_i2s0_rx_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(58), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(17), 0, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s0_rx_frac", "clk_i2s0_rx_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(59), 0,
+			PX30_CLKGATE_CON(17), 1, GFLAGS,
+			&px30_i2s0_rx_fracmux),
+	COMPOSITE_NODIV(SCLK_I2S0_RX, "clk_i2s0_rx", mux_i2s0_rx_tx_p, CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(58), 12, 1, MFLAGS,
+			PX30_CLKGATE_CON(17), 2, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s0_rx_out_pre", mux_i2s0_rx_out_p, 0,
+			PX30_CLKSEL_CON(58), 14, 2, MFLAGS,
+			PX30_CLKGATE_CON(17), 3, GFLAGS),
+	GATE(SCLK_I2S0_RX_OUT, "clk_i2s0_rx_out", "clk_i2s0_rx_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 11, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(0, "clk_i2s1_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(30), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(10), 0, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s1_frac", "clk_i2s1_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(31), 0,
+			PX30_CLKGATE_CON(10), 1, GFLAGS,
+			&px30_i2s1_fracmux),
+	GATE(SCLK_I2S1, "clk_i2s1", "clk_i2s1_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 2, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s1_out_pre", mux_i2s1_out_p, 0,
+			PX30_CLKSEL_CON(30), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(10), 3, GFLAGS),
+	GATE(SCLK_I2S1_OUT, "clk_i2s1_out", "clk_i2s1_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 9, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(0, "clk_i2s2_src", mux_gpll_npll_p, 0,
+			PX30_CLKSEL_CON(32), 8, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(10), 4, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_i2s2_frac", "clk_i2s2_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(33), 0,
+			PX30_CLKGATE_CON(10), 5, GFLAGS,
+			&px30_i2s2_fracmux),
+	GATE(SCLK_I2S2, "clk_i2s2", "clk_i2s2_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 6, GFLAGS),
+	COMPOSITE_NODIV(0, "clk_i2s2_out_pre", mux_i2s2_out_p, 0,
+			PX30_CLKSEL_CON(32), 15, 1, MFLAGS,
+			PX30_CLKGATE_CON(10), 7, GFLAGS),
+	GATE(SCLK_I2S2_OUT, "clk_i2s2_out", "clk_i2s2_out_pre", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 10, CLK_GATE_HIWORD_MASK),
+
+	COMPOSITE(SCLK_UART1_SRC, "clk_uart1_src", mux_uart_src_p, CLK_SET_RATE_NO_REPARENT,
+			PX30_CLKSEL_CON(34), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(10), 12, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart1_np5", "clk_uart1_src", 0,
+			PX30_CLKSEL_CON(35), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(10), 13, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart1_frac", "clk_uart1_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(36), 0,
+			PX30_CLKGATE_CON(10), 14, GFLAGS,
+			&px30_uart1_fracmux),
+	GATE(SCLK_UART1, "clk_uart1", "clk_uart1_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(10), 15, GFLAGS),
+
+	COMPOSITE(SCLK_UART2_SRC, "clk_uart2_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(37), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 0, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart2_np5", "clk_uart2_src", 0,
+			PX30_CLKSEL_CON(38), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 1, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart2_frac", "clk_uart2_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(39), 0,
+			PX30_CLKGATE_CON(11), 2, GFLAGS,
+			&px30_uart2_fracmux),
+	GATE(SCLK_UART2, "clk_uart2", "clk_uart2_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 3, GFLAGS),
+
+	COMPOSITE(0, "clk_uart3_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(40), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 4, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart3_np5", "clk_uart3_src", 0,
+			PX30_CLKSEL_CON(41), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 5, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart3_frac", "clk_uart3_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(42), 0,
+			PX30_CLKGATE_CON(11), 6, GFLAGS,
+			&px30_uart3_fracmux),
+	GATE(SCLK_UART3, "clk_uart3", "clk_uart3_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 7, GFLAGS),
+
+	COMPOSITE(0, "clk_uart4_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(43), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 8, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart4_np5", "clk_uart4_src", 0,
+			PX30_CLKSEL_CON(44), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 9, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart4_frac", "clk_uart4_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(45), 0,
+			PX30_CLKGATE_CON(11), 10, GFLAGS,
+			&px30_uart4_fracmux),
+	GATE(SCLK_UART4, "clk_uart4", "clk_uart4_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 11, GFLAGS),
+
+	COMPOSITE(0, "clk_uart5_src", mux_uart_src_p, 0,
+			PX30_CLKSEL_CON(46), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 12, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart5_np5", "clk_uart5_src", 0,
+			PX30_CLKSEL_CON(47), 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(11), 13, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart5_frac", "clk_uart5_src", CLK_SET_RATE_PARENT,
+			PX30_CLKSEL_CON(48), 0,
+			PX30_CLKGATE_CON(11), 14, GFLAGS,
+			&px30_uart5_fracmux),
+	GATE(SCLK_UART5, "clk_uart5", "clk_uart5_mux", CLK_SET_RATE_PARENT,
+			PX30_CLKGATE_CON(11), 15, GFLAGS),
+
+	COMPOSITE(SCLK_I2C0, "clk_i2c0", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(49), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 0, GFLAGS),
+	COMPOSITE(SCLK_I2C1, "clk_i2c1", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(49), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 1, GFLAGS),
+	COMPOSITE(SCLK_I2C2, "clk_i2c2", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(50), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 2, GFLAGS),
+	COMPOSITE(SCLK_I2C3, "clk_i2c3", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(50), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 3, GFLAGS),
+	COMPOSITE(SCLK_PWM0, "clk_pwm0", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(52), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 5, GFLAGS),
+	COMPOSITE(SCLK_PWM1, "clk_pwm1", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(52), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 6, GFLAGS),
+	COMPOSITE(SCLK_SPI0, "clk_spi0", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(53), 7, 1, MFLAGS, 0, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 7, GFLAGS),
+	COMPOSITE(SCLK_SPI1, "clk_spi1", mux_gpll_xin24m_p, 0,
+			PX30_CLKSEL_CON(53), 15, 1, MFLAGS, 8, 7, DFLAGS,
+			PX30_CLKGATE_CON(12), 8, GFLAGS),
+
+	GATE(SCLK_TIMER0, "sclk_timer0", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 0, GFLAGS),
+	GATE(SCLK_TIMER1, "sclk_timer1", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 1, GFLAGS),
+	GATE(SCLK_TIMER2, "sclk_timer2", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 2, GFLAGS),
+	GATE(SCLK_TIMER3, "sclk_timer3", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 3, GFLAGS),
+	GATE(SCLK_TIMER4, "sclk_timer4", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 4, GFLAGS),
+	GATE(SCLK_TIMER5, "sclk_timer5", "xin24m", 0,
+			PX30_CLKGATE_CON(13), 5, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_TSADC, "clk_tsadc", "xin24m", 0,
+			PX30_CLKSEL_CON(54), 0, 11, DFLAGS,
+			PX30_CLKGATE_CON(12), 9, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_SARADC, "clk_saradc", "xin24m", 0,
+			PX30_CLKSEL_CON(55), 0, 11, DFLAGS,
+			PX30_CLKGATE_CON(12), 10, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_OTP, "clk_otp", "xin24m", 0,
+			PX30_CLKSEL_CON(56), 0, 3, DFLAGS,
+			PX30_CLKGATE_CON(12), 11, GFLAGS),
+	COMPOSITE_NOMUX(SCLK_OTP_USR, "clk_otp_usr", "clk_otp", 0,
+			PX30_CLKSEL_CON(56), 4, 2, DFLAGS,
+			PX30_CLKGATE_CON(13), 6, GFLAGS),
+
+	GATE(0, "clk_cpu_boost", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(12), 12, GFLAGS),
+
+	/* PD_CRYPTO */
+	GATE(0, "aclk_crypto_pre", "aclk_bus_pre", 0,
+			PX30_CLKGATE_CON(8), 12, GFLAGS),
+	GATE(0, "hclk_crypto_pre", "hclk_bus_pre", 0,
+			PX30_CLKGATE_CON(8), 13, GFLAGS),
+	COMPOSITE(SCLK_CRYPTO, "clk_crypto", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(25), 6, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 14, GFLAGS),
+	COMPOSITE(SCLK_CRYPTO_APK, "clk_crypto_apk", mux_gpll_cpll_npll_p, 0,
+			PX30_CLKSEL_CON(25), 14, 2, MFLAGS, 8, 5, DFLAGS,
+			PX30_CLKGATE_CON(8), 15, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 9
+	 */
+
+	/* PD_BUS_TOP */
+	GATE(0, "pclk_top_niu", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 0, GFLAGS),
+	GATE(0, "pclk_top_cru", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 1, GFLAGS),
+	GATE(PCLK_OTP_PHY, "pclk_otp_phy", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 2, GFLAGS),
+	GATE(0, "pclk_ddrphy", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 3, GFLAGS),
+	GATE(PCLK_MIPIDSIPHY, "pclk_mipidsiphy", "pclk_top_pre", 0, PX30_CLKGATE_CON(16), 4, GFLAGS),
+	GATE(PCLK_MIPICSIPHY, "pclk_mipicsiphy", "pclk_top_pre", 0, PX30_CLKGATE_CON(16), 5, GFLAGS),
+	GATE(PCLK_USB_GRF, "pclk_usb_grf", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 6, GFLAGS),
+	GATE(0, "pclk_cpu_hoost", "pclk_top_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(16), 7, GFLAGS),
+
+	/* PD_VI */
+	GATE(0, "aclk_vi_niu", "aclk_vi_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(4), 15, GFLAGS),
+	GATE(ACLK_CIF, "aclk_cif", "aclk_vi_pre", 0, PX30_CLKGATE_CON(5), 1, GFLAGS),
+	GATE(ACLK_ISP, "aclk_isp", "aclk_vi_pre", 0, PX30_CLKGATE_CON(5), 3, GFLAGS),
+	GATE(0, "hclk_vi_niu", "hclk_vi_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(5), 0, GFLAGS),
+	GATE(HCLK_CIF, "hclk_cif", "hclk_vi_pre", 0, PX30_CLKGATE_CON(5), 2, GFLAGS),
+	GATE(HCLK_ISP, "hclk_isp", "hclk_vi_pre", 0, PX30_CLKGATE_CON(5), 4, GFLAGS),
+
+	/* PD_VO */
+	GATE(0, "aclk_vo_niu", "aclk_vo_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(3), 0, GFLAGS),
+	GATE(ACLK_VOPB, "aclk_vopb", "aclk_vo_pre", 0, PX30_CLKGATE_CON(3), 3, GFLAGS),
+	GATE(ACLK_RGA, "aclk_rga", "aclk_vo_pre", 0, PX30_CLKGATE_CON(3), 7, GFLAGS),
+	GATE(ACLK_VOPL, "aclk_vopl", "aclk_vo_pre", 0, PX30_CLKGATE_CON(3), 5, GFLAGS),
+
+	GATE(0, "hclk_vo_niu", "hclk_vo_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(3), 1, GFLAGS),
+	GATE(HCLK_VOPB, "hclk_vopb", "hclk_vo_pre", 0, PX30_CLKGATE_CON(3), 4, GFLAGS),
+	GATE(HCLK_RGA, "hclk_rga", "hclk_vo_pre", 0, PX30_CLKGATE_CON(3), 8, GFLAGS),
+	GATE(HCLK_VOPL, "hclk_vopl", "hclk_vo_pre", 0, PX30_CLKGATE_CON(3), 6, GFLAGS),
+
+	GATE(0, "pclk_vo_niu", "pclk_vo_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(3), 2, GFLAGS),
+	GATE(PCLK_MIPI_DSI, "pclk_mipi_dsi", "pclk_vo_pre", 0, PX30_CLKGATE_CON(3), 9, GFLAGS),
+
+	/* PD_BUS */
+	GATE(0, "aclk_bus_niu", "aclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 8, GFLAGS),
+	GATE(0, "aclk_intmem", "aclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 11, GFLAGS),
+	GATE(ACLK_GIC, "aclk_gic", "aclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 12, GFLAGS),
+	GATE(ACLK_DCF, "aclk_dcf", "aclk_bus_pre", 0, PX30_CLKGATE_CON(13), 15, GFLAGS),
+
+	GATE(0, "hclk_bus_niu", "hclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 9, GFLAGS),
+	GATE(0, "hclk_rom", "hclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 14, GFLAGS),
+	GATE(HCLK_PDM, "hclk_pdm", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 1, GFLAGS),
+	GATE(HCLK_I2S0, "hclk_i2s0", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 2, GFLAGS),
+	GATE(HCLK_I2S1, "hclk_i2s1", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 3, GFLAGS),
+	GATE(HCLK_I2S2, "hclk_i2s2", "hclk_bus_pre", 0, PX30_CLKGATE_CON(14), 4, GFLAGS),
+
+	GATE(0, "pclk_bus_niu", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(13), 10, GFLAGS),
+	GATE(PCLK_DCF, "pclk_dcf", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 0, GFLAGS),
+	GATE(PCLK_UART1, "pclk_uart1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 5, GFLAGS),
+	GATE(PCLK_UART2, "pclk_uart2", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 6, GFLAGS),
+	GATE(PCLK_UART3, "pclk_uart3", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 7, GFLAGS),
+	GATE(PCLK_UART4, "pclk_uart4", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 8, GFLAGS),
+	GATE(PCLK_UART5, "pclk_uart5", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 9, GFLAGS),
+	GATE(PCLK_I2C0, "pclk_i2c0", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 10, GFLAGS),
+	GATE(PCLK_I2C1, "pclk_i2c1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 11, GFLAGS),
+	GATE(PCLK_I2C2, "pclk_i2c2", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 12, GFLAGS),
+	GATE(PCLK_I2C3, "pclk_i2c3", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 13, GFLAGS),
+	GATE(PCLK_I2C4, "pclk_i2c4", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 14, GFLAGS),
+	GATE(PCLK_PWM0, "pclk_pwm0", "pclk_bus_pre", 0, PX30_CLKGATE_CON(14), 15, GFLAGS),
+	GATE(PCLK_PWM1, "pclk_pwm1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 0, GFLAGS),
+	GATE(PCLK_SPI0, "pclk_spi0", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 1, GFLAGS),
+	GATE(PCLK_SPI1, "pclk_spi1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 2, GFLAGS),
+	GATE(PCLK_SARADC, "pclk_saradc", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 3, GFLAGS),
+	GATE(PCLK_TSADC, "pclk_tsadc", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 4, GFLAGS),
+	GATE(PCLK_TIMER, "pclk_timer", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 5, GFLAGS),
+	GATE(PCLK_OTP_NS, "pclk_otp_ns", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 6, GFLAGS),
+	GATE(PCLK_WDT_NS, "pclk_wdt_ns", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 7, GFLAGS),
+	GATE(PCLK_GPIO1, "pclk_gpio1", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 8, GFLAGS),
+	GATE(PCLK_GPIO2, "pclk_gpio2", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 9, GFLAGS),
+	GATE(PCLK_GPIO3, "pclk_gpio3", "pclk_bus_pre", 0, PX30_CLKGATE_CON(15), 10, GFLAGS),
+	GATE(0, "pclk_grf", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 11, GFLAGS),
+	GATE(0, "pclk_sgrf", "pclk_bus_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(15), 12, GFLAGS),
+
+	/* PD_VPU */
+	GATE(0, "hclk_vpu_niu", "hclk_vpu_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(4), 7, GFLAGS),
+	GATE(HCLK_VPU, "hclk_vpu", "hclk_vpu_pre", 0, PX30_CLKGATE_CON(4), 6, GFLAGS),
+	GATE(0, "aclk_vpu_niu", "aclk_vpu_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(4), 5, GFLAGS),
+	GATE(ACLK_VPU, "aclk_vpu", "aclk_vpu_pre", 0, PX30_CLKGATE_CON(4), 4, GFLAGS),
+
+	/* PD_CRYPTO */
+	GATE(0, "hclk_crypto_niu", "hclk_crypto_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(9), 3, GFLAGS),
+	GATE(HCLK_CRYPTO, "hclk_crypto", "hclk_crypto_pre", 0, PX30_CLKGATE_CON(9), 5, GFLAGS),
+	GATE(0, "aclk_crypto_niu", "aclk_crypto_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(9), 2, GFLAGS),
+	GATE(ACLK_CRYPTO, "aclk_crypto", "aclk_crypto_pre", 0, PX30_CLKGATE_CON(9), 4, GFLAGS),
+
+	/* PD_SDCARD */
+	GATE(0, "hclk_sdmmc_niu", "hclk_sdmmc_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(7), 0, GFLAGS),
+	GATE(HCLK_SDMMC, "hclk_sdmmc", "hclk_sdmmc_pre", 0, PX30_CLKGATE_CON(7), 1, GFLAGS),
+
+	/* PD_PERI */
+	GATE(0, "aclk_peri_niu", "aclk_peri_pre", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(5), 9, GFLAGS),
+
+	/* PD_MMC_NAND */
+	GATE(HCLK_NANDC, "hclk_nandc", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(5), 15, GFLAGS),
+	GATE(0, "hclk_mmc_nand_niu", "hclk_mmc_nand", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(6), 8, GFLAGS),
+	GATE(HCLK_SDIO, "hclk_sdio", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(6), 9, GFLAGS),
+	GATE(HCLK_EMMC, "hclk_emmc", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(6), 10, GFLAGS),
+	GATE(HCLK_SFC, "hclk_sfc", "hclk_mmc_nand", 0, PX30_CLKGATE_CON(6), 11, GFLAGS),
+
+	/* PD_USB */
+	GATE(0, "hclk_usb_niu", "hclk_usb", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(7), 4, GFLAGS),
+	GATE(HCLK_OTG, "hclk_otg", "hclk_usb", 0, PX30_CLKGATE_CON(7), 5, GFLAGS),
+	GATE(HCLK_HOST, "hclk_host", "hclk_usb", 0, PX30_CLKGATE_CON(7), 6, GFLAGS),
+	GATE(HCLK_HOST_ARB, "hclk_host_arb", "hclk_usb", CLK_IGNORE_UNUSED, PX30_CLKGATE_CON(7), 8, GFLAGS),
+
+	/* PD_GMAC */
+	GATE(0, "aclk_gmac_niu", "aclk_gmac_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(8), 0, GFLAGS),
+	GATE(ACLK_GMAC, "aclk_gmac", "aclk_gmac_pre", 0,
+			PX30_CLKGATE_CON(8), 2, GFLAGS),
+	GATE(0, "pclk_gmac_niu", "pclk_gmac_pre", CLK_IGNORE_UNUSED,
+			PX30_CLKGATE_CON(8), 1, GFLAGS),
+	GATE(PCLK_GMAC, "pclk_gmac", "pclk_gmac_pre", 0,
+			PX30_CLKGATE_CON(8), 3, GFLAGS),
+};
+
+static struct rockchip_clk_branch px30_clk_pmu_branches[] __initdata = {
+	/*
+	 * Clock-Architecture Diagram 2
+	 */
+
+	COMPOSITE_FRACMUX(0, "clk_rtc32k_frac", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_PMU_CLKSEL_CON(1), 0,
+			PX30_PMU_CLKGATE_CON(0), 13, GFLAGS,
+			&px30_rtc32k_pmu_fracmux),
+
+	COMPOSITE_NOMUX(XIN24M_DIV, "xin24m_div", "xin24m", CLK_IGNORE_UNUSED,
+			PX30_PMU_CLKSEL_CON(0), 8, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 12, GFLAGS),
+
+	COMPOSITE_NOMUX(0, "clk_wifi_pmu_src", "gpll", 0,
+			PX30_PMU_CLKSEL_CON(2), 8, 6, DFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 14, GFLAGS),
+	COMPOSITE_NODIV(SCLK_WIFI_PMU, "clk_wifi_pmu", mux_wifi_pmu_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(2), 15, 1, MFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 15, GFLAGS),
+
+	COMPOSITE(0, "clk_uart0_pmu_src", mux_uart_src_p, 0,
+			PX30_PMU_CLKSEL_CON(3), 14, 2, MFLAGS, 0, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 0, GFLAGS),
+	COMPOSITE_NOMUX_HALFDIV(0, "clk_uart0_np5", "clk_uart0_pmu_src", 0,
+			PX30_PMU_CLKSEL_CON(4), 0, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 1, GFLAGS),
+	COMPOSITE_FRACMUX(0, "clk_uart0_frac", "clk_uart0_pmu_src", CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(5), 0,
+			PX30_PMU_CLKGATE_CON(1), 2, GFLAGS,
+			&px30_uart0_pmu_fracmux),
+	GATE(SCLK_UART0_PMU, "clk_uart0_pmu", "clk_uart0_pmu_mux", CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKGATE_CON(1), 3, GFLAGS),
+
+	GATE(SCLK_PVTM_PMU, "clk_pvtm_pmu", "xin24m", 0,
+			PX30_PMU_CLKGATE_CON(1), 4, GFLAGS),
+
+	COMPOSITE_NOMUX(PCLK_PMU_PRE, "pclk_pmu_pre", "gpll", 0,
+			PX30_PMU_CLKSEL_CON(0), 0, 5, DFLAGS,
+			PX30_PMU_CLKGATE_CON(0), 0, GFLAGS),
+
+	COMPOSITE_NOMUX(SCLK_REF24M_PMU, "clk_ref24m_pmu", "gpll", 0,
+			PX30_PMU_CLKSEL_CON(2), 0, 6, DFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 8, GFLAGS),
+	COMPOSITE_NODIV(SCLK_USBPHY_REF, "clk_usbphy_ref", mux_usbphy_ref_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(2), 6, 1, MFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 9, GFLAGS),
+	COMPOSITE_NODIV(SCLK_MIPIDSIPHY_REF, "clk_mipidsiphy_ref", mux_mipidsiphy_ref_p, CLK_SET_RATE_PARENT,
+			PX30_PMU_CLKSEL_CON(2), 7, 1, MFLAGS,
+			PX30_PMU_CLKGATE_CON(1), 10, GFLAGS),
+
+	/*
+	 * Clock-Architecture Diagram 9
+	 */
+
+	/* PD_PMU */
+	GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 1, GFLAGS),
+	GATE(0, "pclk_pmu_sgrf", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 2, GFLAGS),
+	GATE(0, "pclk_pmu_grf", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 3, GFLAGS),
+	GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 4, GFLAGS),
+	GATE(0, "pclk_pmu_mem", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 5, GFLAGS),
+	GATE(PCLK_GPIO0_PMU, "pclk_gpio0_pmu", "pclk_pmu_pre", 0, PX30_PMU_CLKGATE_CON(0), 6, GFLAGS),
+	GATE(PCLK_UART0_PMU, "pclk_uart0_pmu", "pclk_pmu_pre", 0, PX30_PMU_CLKGATE_CON(0), 7, GFLAGS),
+	GATE(0, "pclk_cru_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, PX30_PMU_CLKGATE_CON(0), 8, GFLAGS),
+};
+
+static const char *const px30_pmucru_critical_clocks[] __initconst = {
+	"aclk_bus_pre",
+	"pclk_bus_pre",
+	"hclk_bus_pre",
+	"aclk_peri_pre",
+	"hclk_peri_pre",
+	"aclk_gpu_niu",
+	"pclk_top_pre",
+	"pclk_pmu_pre",
+	"hclk_usb_niu",
+	"pll_npll",
+	"usb480m",
+	"clk_uart2",
+	"pclk_uart2",
+};
+
+static void __init px30_clk_init(struct device_node *np)
+{
+	struct rockchip_clk_provider *ctx;
+	void __iomem *reg_base;
+	struct clk *clk;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_err("%s: could not map cru region\n", __func__);
+		return;
+	}
+
+	ctx = rockchip_clk_init(np, reg_base, CLK_NR_CLKS);
+	if (IS_ERR(ctx)) {
+		pr_err("%s: rockchip clk init failed\n", __func__);
+		iounmap(reg_base);
+		return;
+	}
+
+	/* aclk_dmac is controlled by sgrf_soc_con1[11]. */
+	clk = clk_register_fixed_factor(NULL, "aclk_dmac", "aclk_bus_pre", 0, 1, 1);
+	if (IS_ERR(clk))
+		pr_warn("%s: could not register clock aclk_dmac: %ld\n",
+			__func__, PTR_ERR(clk));
+	else
+		rockchip_clk_add_lookup(ctx, clk, ACLK_DMAC);
+
+	rockchip_clk_register_plls(ctx, px30_pll_clks,
+				   ARRAY_SIZE(px30_pll_clks),
+				   PX30_GRF_SOC_STATUS0);
+	rockchip_clk_register_branches(ctx, px30_clk_branches,
+				       ARRAY_SIZE(px30_clk_branches));
+
+	rockchip_clk_register_armclk(ctx, ARMCLK, "armclk",
+				     mux_armclk_p, ARRAY_SIZE(mux_armclk_p),
+				     &px30_cpuclk_data, px30_cpuclk_rates,
+				     ARRAY_SIZE(px30_cpuclk_rates));
+
+	rockchip_register_softrst(np, 12, reg_base + PX30_SOFTRST_CON(0),
+				  ROCKCHIP_SOFTRST_HIWORD_MASK);
+
+	rockchip_register_restart_notifier(ctx, PX30_GLB_SRST_FST, NULL);
+
+	rockchip_clk_of_add_provider(np, ctx);
+}
+CLK_OF_DECLARE(px30_cru, "rockchip,px30-cru", px30_clk_init);
+
+static void __init px30_pmu_clk_init(struct device_node *np)
+{
+	struct rockchip_clk_provider *ctx;
+	void __iomem *reg_base;
+
+	reg_base = of_iomap(np, 0);
+	if (!reg_base) {
+		pr_err("%s: could not map cru pmu region\n", __func__);
+		return;
+	}
+
+	ctx = rockchip_clk_init(np, reg_base, CLKPMU_NR_CLKS);
+	if (IS_ERR(ctx)) {
+		pr_err("%s: rockchip pmu clk init failed\n", __func__);
+		return;
+	}
+
+	rockchip_clk_register_plls(ctx, px30_pmu_pll_clks,
+				   ARRAY_SIZE(px30_pmu_pll_clks), PX30_GRF_SOC_STATUS0);
+
+	rockchip_clk_register_branches(ctx, px30_clk_pmu_branches,
+				       ARRAY_SIZE(px30_clk_pmu_branches));
+
+	rockchip_clk_protect_critical(px30_pmucru_critical_clocks,
+				      ARRAY_SIZE(px30_pmucru_critical_clocks));
+
+	rockchip_clk_of_add_provider(np, ctx);
+}
+CLK_OF_DECLARE(px30_cru_pmu, "rockchip,px30-pmucru", px30_pmu_clk_init);
diff --git a/drivers/clk/rockchip/clk.h b/drivers/clk/rockchip/clk.h
index 23c569a875d4..6b53fff4cc96 100644
--- a/drivers/clk/rockchip/clk.h
+++ b/drivers/clk/rockchip/clk.h
@@ -34,7 +34,46 @@ struct clk;
 #define HIWORD_UPDATE(val, mask, shift) \
 		((val) << (shift) | (mask) << ((shift) + 16))
 
-/* register positions shared by RV1108, RK2928, RK3036, RK3066, RK3188 and RK3228 */
+/* register positions shared by PX30, RV1108, RK2928, RK3036, RK3066, RK3188 and RK3228 */
+#define BOOST_PLL_H_CON(x)		((x) * 0x4)
+#define BOOST_CLK_CON			0x0008
+#define BOOST_BOOST_CON			0x000c
+#define BOOST_SWITCH_CNT		0x0010
+#define BOOST_HIGH_PERF_CNT0		0x0014
+#define BOOST_HIGH_PERF_CNT1		0x0018
+#define BOOST_STATIS_THRESHOLD		0x001c
+#define BOOST_SHORT_SWITCH_CNT		0x0020
+#define BOOST_SWITCH_THRESHOLD		0x0024
+#define BOOST_FSM_STATUS		0x0028
+#define BOOST_PLL_L_CON(x)		((x) * 0x4 + 0x2c)
+#define BOOST_RECOVERY_MASK		0x1
+#define BOOST_RECOVERY_SHIFT		1
+#define BOOST_SW_CTRL_MASK		0x1
+#define BOOST_SW_CTRL_SHIFT		2
+#define BOOST_LOW_FREQ_EN_MASK		0x1
+#define BOOST_LOW_FREQ_EN_SHIFT		3
+#define BOOST_BUSY_STATE		BIT(8)
+
+#define PX30_PLL_CON(x)			((x) * 0x4)
+#define PX30_CLKSEL_CON(x)		((x) * 0x4 + 0x100)
+#define PX30_CLKGATE_CON(x)		((x) * 0x4 + 0x200)
+#define PX30_GLB_SRST_FST		0xb8
+#define PX30_GLB_SRST_SND		0xbc
+#define PX30_SOFTRST_CON(x)		((x) * 0x4 + 0x300)
+#define PX30_MODE_CON			0xa0
+#define PX30_MISC_CON			0xa4
+#define PX30_SDMMC_CON0			0x380
+#define PX30_SDMMC_CON1			0x384
+#define PX30_SDIO_CON0			0x388
+#define PX30_SDIO_CON1			0x38c
+#define PX30_EMMC_CON0			0x390
+#define PX30_EMMC_CON1			0x394
+
+#define PX30_PMU_PLL_CON(x)		((x) * 0x4)
+#define PX30_PMU_CLKSEL_CON(x)		((x) * 0x4 + 0x40)
+#define PX30_PMU_CLKGATE_CON(x)		((x) * 0x4 + 0x80)
+#define PX30_PMU_MODE			0x0020
+
 #define RV1108_PLL_CON(x)		((x) * 0x4)
 #define RV1108_CLKSEL_CON(x)		((x) * 0x4 + 0x60)
 #define RV1108_CLKGATE_CON(x)		((x) * 0x4 + 0x120)
-- 
cgit v1.2.3


From da99fe5f858525b0eac5a5296bba5d6bedb81abd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 11:39:42 +0100
Subject: drm/i915: Refactor export_fence() after i915_vma_move_to_active()

Currently all callers are responsible for adding the vma to the active
timeline and then exporting its fence. Combine the two operations into
i915_vma_move_to_active() to move all the extra handling from the
callers to the single site.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706103947.15919-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c         | 47 ++++++++++------------
 drivers/gpu/drm/i915/selftests/huge_pages.c        |  4 --
 .../gpu/drm/i915/selftests/i915_gem_coherency.c    |  4 --
 drivers/gpu/drm/i915/selftests/i915_gem_context.c  |  4 --
 drivers/gpu/drm/i915/selftests/i915_gem_object.c   |  4 --
 drivers/gpu/drm/i915/selftests/intel_workarounds.c |  3 --
 6 files changed, 21 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index c2dd9b4cdace..91f20445147f 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1166,15 +1166,9 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 
 	GEM_BUG_ON(!reservation_object_test_signaled_rcu(batch->resv, true));
 	i915_vma_move_to_active(batch, rq, 0);
-	reservation_object_lock(batch->resv, NULL);
-	reservation_object_add_excl_fence(batch->resv, &rq->fence);
-	reservation_object_unlock(batch->resv);
 	i915_vma_unpin(batch);
 
 	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
 
 	rq->batch = batch;
 
@@ -1771,25 +1765,6 @@ slow:
 	return eb_relocate_slow(eb);
 }
 
-static void eb_export_fence(struct i915_vma *vma,
-			    struct i915_request *rq,
-			    unsigned int flags)
-{
-	struct reservation_object *resv = vma->resv;
-
-	/*
-	 * Ignore errors from failing to allocate the new fence, we can't
-	 * handle an error right now. Worst case should be missed
-	 * synchronisation leading to rendering corruption.
-	 */
-	reservation_object_lock(resv, NULL);
-	if (flags & EXEC_OBJECT_WRITE)
-		reservation_object_add_excl_fence(resv, &rq->fence);
-	else if (reservation_object_reserve_shared(resv) == 0)
-		reservation_object_add_shared_fence(resv, &rq->fence);
-	reservation_object_unlock(resv);
-}
-
 static int eb_move_to_gpu(struct i915_execbuffer *eb)
 {
 	const unsigned int count = eb->buffer_count;
@@ -1844,7 +1819,6 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 		struct i915_vma *vma = eb->vma[i];
 
 		i915_vma_move_to_active(vma, eb->request, flags);
-		eb_export_fence(vma, eb->request, flags);
 
 		__eb_unreserve_vma(vma, flags);
 		vma->exec_flags = NULL;
@@ -1884,6 +1858,25 @@ static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 	return true;
 }
 
+static void export_fence(struct i915_vma *vma,
+			 struct i915_request *rq,
+			 unsigned int flags)
+{
+	struct reservation_object *resv = vma->resv;
+
+	/*
+	 * Ignore errors from failing to allocate the new fence, we can't
+	 * handle an error right now. Worst case should be missed
+	 * synchronisation leading to rendering corruption.
+	 */
+	reservation_object_lock(resv, NULL);
+	if (flags & EXEC_OBJECT_WRITE)
+		reservation_object_add_excl_fence(resv, &rq->fence);
+	else if (reservation_object_reserve_shared(resv) == 0)
+		reservation_object_add_shared_fence(resv, &rq->fence);
+	reservation_object_unlock(resv);
+}
+
 void i915_vma_move_to_active(struct i915_vma *vma,
 			     struct i915_request *rq,
 			     unsigned int flags)
@@ -1921,6 +1914,8 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 
 	if (flags & EXEC_OBJECT_NEEDS_FENCE)
 		i915_gem_active_set(&vma->last_fence, rq);
+
+	export_fence(vma, rq, flags);
 }
 
 static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index ab662dabcff7..84bed69f30cc 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -998,10 +998,6 @@ static int gpu_write(struct i915_vma *vma,
 
 	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
-
 err_request:
 	i915_request_add(rq);
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index 294c58aba2c1..97a16311f083 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -225,10 +225,6 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 	i915_vma_unpin(vma);
 
-	reservation_object_lock(obj->resv, NULL);
-	reservation_object_add_excl_fence(obj->resv, &rq->fence);
-	reservation_object_unlock(obj->resv);
-
 	i915_request_add(rq);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 65100d3e31cf..c642ab97698e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -178,10 +178,6 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 	i915_vma_unpin(vma);
 
-	reservation_object_lock(obj->resv, NULL);
-	reservation_object_add_excl_fence(obj->resv, &rq->fence);
-	reservation_object_unlock(obj->resv);
-
 	i915_request_add(rq);
 
 	return 0;
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 6fe71865b710..b2ccbc5e2bbe 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -466,10 +466,6 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 
 	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
-
 	i915_request_add(rq);
 
 	i915_gem_object_set_active_reference(obj);
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index 3d86b90ab722..4a9dc01a364a 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -68,9 +68,6 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	intel_ring_advance(rq, cs);
 
 	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-	reservation_object_lock(vma->resv, NULL);
-	reservation_object_add_excl_fence(vma->resv, &rq->fence);
-	reservation_object_unlock(vma->resv);
 
 	i915_gem_object_get(result);
 	i915_gem_object_set_active_reference(result);
-- 
cgit v1.2.3


From 6dd7526f6f6c73961eecec8a4b9b717d414010f8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 11:39:43 +0100
Subject: drm/i915: Export i915_request_skip()

In the next patch, we will want to start skipping requests on failing to
complete their payloads. So export the utility function current used to
make requests inoperable following a failed gpu reset.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706103947.15919-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c     | 25 +++----------------------
 drivers/gpu/drm/i915/i915_request.c | 21 +++++++++++++++++++++
 drivers/gpu/drm/i915/i915_request.h |  2 ++
 3 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index be63e8bbb6d2..2e05cf114083 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3085,25 +3085,6 @@ int i915_gem_reset_prepare(struct drm_i915_private *dev_priv)
 	return err;
 }
 
-static void skip_request(struct i915_request *request)
-{
-	void *vaddr = request->ring->vaddr;
-	u32 head;
-
-	/* As this request likely depends on state from the lost
-	 * context, clear out all the user operations leaving the
-	 * breadcrumb at the end (so we get the fence notifications).
-	 */
-	head = request->head;
-	if (request->postfix < head) {
-		memset(vaddr + head, 0, request->ring->size - head);
-		head = 0;
-	}
-	memset(vaddr + head, 0, request->postfix - head);
-
-	dma_fence_set_error(&request->fence, -EIO);
-}
-
 static void engine_skip_context(struct i915_request *request)
 {
 	struct intel_engine_cs *engine = request->engine;
@@ -3118,10 +3099,10 @@ static void engine_skip_context(struct i915_request *request)
 
 	list_for_each_entry_continue(request, &engine->timeline.requests, link)
 		if (request->gem_context == hung_ctx)
-			skip_request(request);
+			i915_request_skip(request, -EIO);
 
 	list_for_each_entry(request, &timeline->requests, link)
-		skip_request(request);
+		i915_request_skip(request, -EIO);
 
 	spin_unlock(&timeline->lock);
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
@@ -3164,7 +3145,7 @@ i915_gem_reset_request(struct intel_engine_cs *engine,
 
 	if (stalled) {
 		i915_gem_context_mark_guilty(request->gem_context);
-		skip_request(request);
+		i915_request_skip(request, -EIO);
 
 		/* If this context is now banned, skip all pending requests. */
 		if (i915_gem_context_is_banned(request->gem_context))
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index a2f7e9358450..7ae08b68121e 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -1013,6 +1013,27 @@ i915_request_await_object(struct i915_request *to,
 	return ret;
 }
 
+void i915_request_skip(struct i915_request *rq, int error)
+{
+	void *vaddr = rq->ring->vaddr;
+	u32 head;
+
+	GEM_BUG_ON(!IS_ERR_VALUE((long)error));
+	dma_fence_set_error(&rq->fence, error);
+
+	/*
+	 * As this request likely depends on state from the lost
+	 * context, clear out all the user operations leaving the
+	 * breadcrumb at the end (so we get the fence notifications).
+	 */
+	head = rq->infix;
+	if (rq->postfix < head) {
+		memset(vaddr + head, 0, rq->ring->size - head);
+		head = 0;
+	}
+	memset(vaddr + head, 0, rq->postfix - head);
+}
+
 /*
  * NB: This function is not allowed to fail. Doing so would mean the the
  * request is not being tracked for completion but the work itself is
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index 7ee220ded9c9..a355a081485f 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -258,6 +258,8 @@ void i915_request_add(struct i915_request *rq);
 void __i915_request_submit(struct i915_request *request);
 void i915_request_submit(struct i915_request *request);
 
+void i915_request_skip(struct i915_request *request, int error);
+
 void __i915_request_unsubmit(struct i915_request *request);
 void i915_request_unsubmit(struct i915_request *request);
 
-- 
cgit v1.2.3


From a523697857cdfb6a548f6caf38f42f4fe0f7d757 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 11:39:44 +0100
Subject: drm/i915: Start returning an error from i915_vma_move_to_active()

Handling such a late error in request construction is tricky, but to
accommodate future patches which may allocate here, we potentially could
err. To handle the error after already adjusting global state to track
the new request, we must finish and submit the request. But we don't
want to use the request as not everything is being tracked by it, so we
opt to cancel the commands inside the request.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706103947.15919-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/gvt/scheduler.c               |  6 +++++-
 drivers/gpu/drm/i915/i915_drv.h                    |  6 +++---
 drivers/gpu/drm/i915/i915_gem_execbuffer.c         | 25 ++++++++++++++++------
 drivers/gpu/drm/i915/i915_gem_render_state.c       |  2 +-
 drivers/gpu/drm/i915/selftests/huge_pages.c        |  9 ++++++--
 .../gpu/drm/i915/selftests/i915_gem_coherency.c    |  4 ++--
 drivers/gpu/drm/i915/selftests/i915_gem_context.c  | 12 +++++++++--
 drivers/gpu/drm/i915/selftests/i915_gem_object.c   |  7 +++---
 drivers/gpu/drm/i915/selftests/i915_request.c      |  8 +++++--
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c   | 11 ++++++++--
 drivers/gpu/drm/i915/selftests/intel_lrc.c         | 11 ++++++++--
 drivers/gpu/drm/i915/selftests/intel_workarounds.c |  6 ++++--
 12 files changed, 78 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/scheduler.c b/drivers/gpu/drm/i915/gvt/scheduler.c
index 928818f218f7..b0e566956b8d 100644
--- a/drivers/gpu/drm/i915/gvt/scheduler.c
+++ b/drivers/gpu/drm/i915/gvt/scheduler.c
@@ -476,7 +476,11 @@ static int prepare_shadow_batch_buffer(struct intel_vgpu_workload *workload)
 			i915_gem_obj_finish_shmem_access(bb->obj);
 			bb->accessing = false;
 
-			i915_vma_move_to_active(bb->vma, workload->req, 0);
+			ret = i915_vma_move_to_active(bb->vma,
+						      workload->req,
+						      0);
+			if (ret)
+				goto err;
 		}
 	}
 	return 0;
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c1c637e47bf5..07846e63671d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3090,9 +3090,9 @@ i915_gem_obj_finish_shmem_access(struct drm_i915_gem_object *obj)
 }
 
 int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
-void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct i915_request *rq,
-			     unsigned int flags);
+int __must_check i915_vma_move_to_active(struct i915_vma *vma,
+					 struct i915_request *rq,
+					 unsigned int flags);
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 91f20445147f..97136e4ce91d 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1165,12 +1165,16 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 		goto err_request;
 
 	GEM_BUG_ON(!reservation_object_test_signaled_rcu(batch->resv, true));
-	i915_vma_move_to_active(batch, rq, 0);
-	i915_vma_unpin(batch);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto skip_request;
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto skip_request;
 
 	rq->batch = batch;
+	i915_vma_unpin(batch);
 
 	cache->rq = rq;
 	cache->rq_cmd = cmd;
@@ -1179,6 +1183,8 @@ static int __reloc_gpu_alloc(struct i915_execbuffer *eb,
 	/* Return with batch mapping (cmd) still pinned */
 	return 0;
 
+skip_request:
+	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_unpin:
@@ -1818,7 +1824,11 @@ static int eb_move_to_gpu(struct i915_execbuffer *eb)
 		unsigned int flags = eb->flags[i];
 		struct i915_vma *vma = eb->vma[i];
 
-		i915_vma_move_to_active(vma, eb->request, flags);
+		err = i915_vma_move_to_active(vma, eb->request, flags);
+		if (unlikely(err)) {
+			i915_request_skip(eb->request, err);
+			return err;
+		}
 
 		__eb_unreserve_vma(vma, flags);
 		vma->exec_flags = NULL;
@@ -1877,9 +1887,9 @@ static void export_fence(struct i915_vma *vma,
 	reservation_object_unlock(resv);
 }
 
-void i915_vma_move_to_active(struct i915_vma *vma,
-			     struct i915_request *rq,
-			     unsigned int flags)
+int i915_vma_move_to_active(struct i915_vma *vma,
+			    struct i915_request *rq,
+			    unsigned int flags)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
 	const unsigned int idx = rq->engine->id;
@@ -1916,6 +1926,7 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 		i915_gem_active_set(&vma->last_fence, rq);
 
 	export_fence(vma, rq, flags);
+	return 0;
 }
 
 static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
diff --git a/drivers/gpu/drm/i915/i915_gem_render_state.c b/drivers/gpu/drm/i915/i915_gem_render_state.c
index 3210cedfa46c..90baf9086d0a 100644
--- a/drivers/gpu/drm/i915/i915_gem_render_state.c
+++ b/drivers/gpu/drm/i915/i915_gem_render_state.c
@@ -222,7 +222,7 @@ int i915_gem_render_state_emit(struct i915_request *rq)
 			goto err_unpin;
 	}
 
-	i915_vma_move_to_active(so.vma, rq, 0);
+	err = i915_vma_move_to_active(so.vma, rq, 0);
 err_unpin:
 	i915_vma_unpin(so.vma);
 err_vma:
diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index 84bed69f30cc..d9f439f6219f 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -985,7 +985,10 @@ static int gpu_write(struct i915_vma *vma,
 		goto err_request;
 	}
 
-	i915_vma_move_to_active(batch, rq, 0);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto err_request;
+
 	i915_gem_object_set_active_reference(batch->obj);
 	i915_vma_unpin(batch);
 	i915_vma_close(batch);
@@ -996,7 +999,9 @@ static int gpu_write(struct i915_vma *vma,
 	if (err)
 		goto err_request;
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		i915_request_skip(rq, err);
 
 err_request:
 	i915_request_add(rq);
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index 97a16311f083..1de7c1402fd5 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -222,12 +222,12 @@ static int gpu_set(struct drm_i915_gem_object *obj,
 	}
 	intel_ring_advance(rq, cs);
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 	i915_vma_unpin(vma);
 
 	i915_request_add(rq);
 
-	return 0;
+	return err;
 }
 
 static bool always_valid(struct drm_i915_private *i915)
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index c642ab97698e..5fbe15f4effd 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -170,18 +170,26 @@ static int gpu_fill(struct drm_i915_gem_object *obj,
 	if (err)
 		goto err_request;
 
-	i915_vma_move_to_active(batch, rq, 0);
+	err = i915_vma_move_to_active(batch, rq, 0);
+	if (err)
+		goto skip_request;
+
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto skip_request;
+
 	i915_gem_object_set_active_reference(batch->obj);
 	i915_vma_unpin(batch);
 	i915_vma_close(batch);
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 	i915_vma_unpin(vma);
 
 	i915_request_add(rq);
 
 	return 0;
 
+skip_request:
+	i915_request_skip(rq, err);
 err_request:
 	i915_request_add(rq);
 err_batch:
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index b2ccbc5e2bbe..25c2b2d433bd 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -464,13 +464,14 @@ static int make_obj_busy(struct drm_i915_gem_object *obj)
 		return PTR_ERR(rq);
 	}
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
 
 	i915_request_add(rq);
 
-	i915_gem_object_set_active_reference(obj);
+	__i915_gem_object_release_unless_active(obj);
 	i915_vma_unpin(vma);
-	return 0;
+
+	return err;
 }
 
 static bool assert_mmap_offset(struct drm_i915_private *i915,
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index cc27edc40356..43995fc3534d 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -675,7 +675,9 @@ static int live_all_engines(void *arg)
 			i915_gem_object_set_active_reference(batch->obj);
 		}
 
-		i915_vma_move_to_active(batch, request[id], 0);
+		err = i915_vma_move_to_active(batch, request[id], 0);
+		GEM_BUG_ON(err);
+
 		i915_request_get(request[id]);
 		i915_request_add(request[id]);
 	}
@@ -785,7 +787,9 @@ static int live_sequential_engines(void *arg)
 		GEM_BUG_ON(err);
 		request[id]->batch = batch;
 
-		i915_vma_move_to_active(batch, request[id], 0);
+		err = i915_vma_move_to_active(batch, request[id], 0);
+		GEM_BUG_ON(err);
+
 		i915_gem_object_set_active_reference(batch->obj);
 		i915_vma_get(batch);
 
diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index c838f7d08cb9..73462a65a330 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -130,13 +130,19 @@ static int emit_recurse_batch(struct hang *h,
 	if (err)
 		goto unpin_vma;
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(vma->obj)) {
 		i915_gem_object_get(vma->obj);
 		i915_gem_object_set_active_reference(vma->obj);
 	}
 
-	i915_vma_move_to_active(hws, rq, 0);
+	err = i915_vma_move_to_active(hws, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(hws->obj)) {
 		i915_gem_object_get(hws->obj);
 		i915_gem_object_set_active_reference(hws->obj);
@@ -205,6 +211,7 @@ static int emit_recurse_batch(struct hang *h,
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, flags);
 
+unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index 730a02d39058..636cb68191e3 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -104,13 +104,19 @@ static int emit_recurse_batch(struct spinner *spin,
 	if (err)
 		goto unpin_vma;
 
-	i915_vma_move_to_active(vma, rq, 0);
+	err = i915_vma_move_to_active(vma, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(vma->obj)) {
 		i915_gem_object_get(vma->obj);
 		i915_gem_object_set_active_reference(vma->obj);
 	}
 
-	i915_vma_move_to_active(hws, rq, 0);
+	err = i915_vma_move_to_active(hws, rq, 0);
+	if (err)
+		goto unpin_hws;
+
 	if (!i915_gem_object_has_active_reference(hws->obj)) {
 		i915_gem_object_get(hws->obj);
 		i915_gem_object_set_active_reference(hws->obj);
@@ -134,6 +140,7 @@ static int emit_recurse_batch(struct spinner *spin,
 
 	err = rq->engine->emit_bb_start(rq, vma->node.start, PAGE_SIZE, 0);
 
+unpin_hws:
 	i915_vma_unpin(hws);
 unpin_vma:
 	i915_vma_unpin(vma);
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index 4a9dc01a364a..fafdec3fe83e 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -49,6 +49,10 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 		goto err_pin;
 	}
 
+	err = i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
+	if (err)
+		goto err_req;
+
 	srm = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT;
 	if (INTEL_GEN(ctx->i915) >= 8)
 		srm++;
@@ -67,8 +71,6 @@ read_nonprivs(struct i915_gem_context *ctx, struct intel_engine_cs *engine)
 	}
 	intel_ring_advance(rq, cs);
 
-	i915_vma_move_to_active(vma, rq, EXEC_OBJECT_WRITE);
-
 	i915_gem_object_get(result);
 	i915_gem_object_set_active_reference(result);
 
-- 
cgit v1.2.3


From e6bb1d7f1adfcd24ac7d82ab157a8b8809a0d2c8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 11:39:45 +0100
Subject: drm/i915: Move i915_vma_move_to_active() to i915_vma.c

i915_vma_move_to_active() has grown beyond its execbuf origins, and
should take its rightful place in i915_vma.c as a method for i915_vma!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706103947.15919-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.h            |  3 --
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 61 ------------------------------
 drivers/gpu/drm/i915/i915_vma.c            | 61 ++++++++++++++++++++++++++++++
 drivers/gpu/drm/i915/i915_vma.h            |  4 ++
 4 files changed, 65 insertions(+), 64 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 07846e63671d..c79008177708 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3090,9 +3090,6 @@ i915_gem_obj_finish_shmem_access(struct drm_i915_gem_object *obj)
 }
 
 int __must_check i915_mutex_lock_interruptible(struct drm_device *dev);
-int __must_check i915_vma_move_to_active(struct i915_vma *vma,
-					 struct i915_request *rq,
-					 unsigned int flags);
 int i915_gem_dumb_create(struct drm_file *file_priv,
 			 struct drm_device *dev,
 			 struct drm_mode_create_dumb *args);
diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
index 97136e4ce91d..3f0c612d42e7 100644
--- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c
@@ -1868,67 +1868,6 @@ static bool i915_gem_check_execbuffer(struct drm_i915_gem_execbuffer2 *exec)
 	return true;
 }
 
-static void export_fence(struct i915_vma *vma,
-			 struct i915_request *rq,
-			 unsigned int flags)
-{
-	struct reservation_object *resv = vma->resv;
-
-	/*
-	 * Ignore errors from failing to allocate the new fence, we can't
-	 * handle an error right now. Worst case should be missed
-	 * synchronisation leading to rendering corruption.
-	 */
-	reservation_object_lock(resv, NULL);
-	if (flags & EXEC_OBJECT_WRITE)
-		reservation_object_add_excl_fence(resv, &rq->fence);
-	else if (reservation_object_reserve_shared(resv) == 0)
-		reservation_object_add_shared_fence(resv, &rq->fence);
-	reservation_object_unlock(resv);
-}
-
-int i915_vma_move_to_active(struct i915_vma *vma,
-			    struct i915_request *rq,
-			    unsigned int flags)
-{
-	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned int idx = rq->engine->id;
-
-	lockdep_assert_held(&rq->i915->drm.struct_mutex);
-	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
-
-	/*
-	 * Add a reference if we're newly entering the active list.
-	 * The order in which we add operations to the retirement queue is
-	 * vital here: mark_active adds to the start of the callback list,
-	 * such that subsequent callbacks are called first. Therefore we
-	 * add the active reference first and queue for it to be dropped
-	 * *last*.
-	 */
-	if (!i915_vma_is_active(vma))
-		obj->active_count++;
-	i915_vma_set_active(vma, idx);
-	i915_gem_active_set(&vma->last_read[idx], rq);
-	list_move_tail(&vma->vm_link, &vma->vm->active_list);
-
-	obj->write_domain = 0;
-	if (flags & EXEC_OBJECT_WRITE) {
-		obj->write_domain = I915_GEM_DOMAIN_RENDER;
-
-		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
-			i915_gem_active_set(&obj->frontbuffer_write, rq);
-
-		obj->read_domains = 0;
-	}
-	obj->read_domains |= I915_GEM_GPU_DOMAINS;
-
-	if (flags & EXEC_OBJECT_NEEDS_FENCE)
-		i915_gem_active_set(&vma->last_fence, rq);
-
-	export_fence(vma, rq, flags);
-	return 0;
-}
-
 static int i915_reset_gen7_sol_offsets(struct i915_request *rq)
 {
 	u32 *cs;
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 518de47111ff..6f3a0f2296c2 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -859,6 +859,67 @@ void i915_vma_revoke_mmap(struct i915_vma *vma)
 		list_del(&vma->obj->userfault_link);
 }
 
+static void export_fence(struct i915_vma *vma,
+			 struct i915_request *rq,
+			 unsigned int flags)
+{
+	struct reservation_object *resv = vma->resv;
+
+	/*
+	 * Ignore errors from failing to allocate the new fence, we can't
+	 * handle an error right now. Worst case should be missed
+	 * synchronisation leading to rendering corruption.
+	 */
+	reservation_object_lock(resv, NULL);
+	if (flags & EXEC_OBJECT_WRITE)
+		reservation_object_add_excl_fence(resv, &rq->fence);
+	else if (reservation_object_reserve_shared(resv) == 0)
+		reservation_object_add_shared_fence(resv, &rq->fence);
+	reservation_object_unlock(resv);
+}
+
+int i915_vma_move_to_active(struct i915_vma *vma,
+			    struct i915_request *rq,
+			    unsigned int flags)
+{
+	struct drm_i915_gem_object *obj = vma->obj;
+	const unsigned int idx = rq->engine->id;
+
+	lockdep_assert_held(&rq->i915->drm.struct_mutex);
+	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
+
+	/*
+	 * Add a reference if we're newly entering the active list.
+	 * The order in which we add operations to the retirement queue is
+	 * vital here: mark_active adds to the start of the callback list,
+	 * such that subsequent callbacks are called first. Therefore we
+	 * add the active reference first and queue for it to be dropped
+	 * *last*.
+	 */
+	if (!i915_vma_is_active(vma))
+		obj->active_count++;
+	i915_vma_set_active(vma, idx);
+	i915_gem_active_set(&vma->last_read[idx], rq);
+	list_move_tail(&vma->vm_link, &vma->vm->active_list);
+
+	obj->write_domain = 0;
+	if (flags & EXEC_OBJECT_WRITE) {
+		obj->write_domain = I915_GEM_DOMAIN_RENDER;
+
+		if (intel_fb_obj_invalidate(obj, ORIGIN_CS))
+			i915_gem_active_set(&obj->frontbuffer_write, rq);
+
+		obj->read_domains = 0;
+	}
+	obj->read_domains |= I915_GEM_GPU_DOMAINS;
+
+	if (flags & EXEC_OBJECT_NEEDS_FENCE)
+		i915_gem_active_set(&vma->last_fence, rq);
+
+	export_fence(vma, rq, flags);
+	return 0;
+}
+
 int i915_vma_unbind(struct i915_vma *vma)
 {
 	unsigned long active;
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index 66a228931517..a218b689e418 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -215,6 +215,10 @@ static inline bool i915_vma_has_active_engine(const struct i915_vma *vma,
 	return vma->active & BIT(engine);
 }
 
+int __must_check i915_vma_move_to_active(struct i915_vma *vma,
+					 struct i915_request *rq,
+					 unsigned int flags);
+
 static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
 {
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
-- 
cgit v1.2.3


From 5c3f8c221c77ccdce3c2a8b96d196e5f4e2dac0c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 11:39:46 +0100
Subject: drm/i915: Track vma activity per fence.context, not per engine

In the next patch, we will want to be able to use more flexible request
timelines that can hop between engines. From the vma pov, we can then
not rely on the binding of this request to an engine and so can not
ensure that different requests are ordered through a per-engine
timeline, and so we must track activity of all timelines. (We track
activity on the vma itself to prevent unbinding from HW before the HW
has finished accessing it.)

v2: Switch to a rbtree for 32b safety (since using u64 as a radixtree
index is fraught with aliasing of unsigned longs).
v3: s/lookup_active/active_instance/ because we can never agree on names

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706103947.15919-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c   |   5 +-
 drivers/gpu/drm/i915/i915_gpu_error.c |  14 +----
 drivers/gpu/drm/i915/i915_gpu_error.h |   2 +-
 drivers/gpu/drm/i915/i915_request.h   |   1 +
 drivers/gpu/drm/i915/i915_vma.c       | 112 ++++++++++++++++++++++++----------
 drivers/gpu/drm/i915/i915_vma.h       |  46 ++++----------
 6 files changed, 100 insertions(+), 80 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index e2793231ef49..4db31aaaa9d3 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2074,7 +2074,6 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	struct drm_i915_private *i915 = ppgtt->base.vm.i915;
 	struct i915_ggtt *ggtt = &i915->ggtt;
 	struct i915_vma *vma;
-	int i;
 
 	GEM_BUG_ON(!IS_ALIGNED(size, I915_GTT_PAGE_SIZE));
 	GEM_BUG_ON(size > ggtt->vm.total);
@@ -2083,14 +2082,14 @@ static struct i915_vma *pd_vma_create(struct gen6_hw_ppgtt *ppgtt, int size)
 	if (!vma)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		init_request_active(&vma->last_read[i], NULL);
 	init_request_active(&vma->last_fence, NULL);
 
 	vma->vm = &ggtt->vm;
 	vma->ops = &pd_vma_ops;
 	vma->private = ppgtt;
 
+	vma->active = RB_ROOT;
+
 	vma->size = size;
 	vma->fence_size = size;
 	vma->flags = I915_VMA_GGTT;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index df524c9cad40..8c81cf3aa182 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -335,21 +335,16 @@ static void print_error_buffers(struct drm_i915_error_state_buf *m,
 				struct drm_i915_error_buffer *err,
 				int count)
 {
-	int i;
-
 	err_printf(m, "%s [%d]:\n", name, count);
 
 	while (count--) {
-		err_printf(m, "    %08x_%08x %8u %02x %02x [ ",
+		err_printf(m, "    %08x_%08x %8u %02x %02x %02x",
 			   upper_32_bits(err->gtt_offset),
 			   lower_32_bits(err->gtt_offset),
 			   err->size,
 			   err->read_domains,
-			   err->write_domain);
-		for (i = 0; i < I915_NUM_ENGINES; i++)
-			err_printf(m, "%02x ", err->rseqno[i]);
-
-		err_printf(m, "] %02x", err->wseqno);
+			   err->write_domain,
+			   err->wseqno);
 		err_puts(m, tiling_flag(err->tiling));
 		err_puts(m, dirty_flag(err->dirty));
 		err_puts(m, purgeable_flag(err->purgeable));
@@ -1021,13 +1016,10 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 		       struct i915_vma *vma)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
-	int i;
 
 	err->size = obj->base.size;
 	err->name = obj->base.name;
 
-	for (i = 0; i < I915_NUM_ENGINES; i++)
-		err->rseqno[i] = __active_get_seqno(&vma->last_read[i]);
 	err->wseqno = __active_get_seqno(&obj->frontbuffer_write);
 	err->engine = __active_get_engine_id(&obj->frontbuffer_write);
 
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.h b/drivers/gpu/drm/i915/i915_gpu_error.h
index 58910f1dc67c..f893a4e8b783 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.h
+++ b/drivers/gpu/drm/i915/i915_gpu_error.h
@@ -177,7 +177,7 @@ struct i915_gpu_state {
 	struct drm_i915_error_buffer {
 		u32 size;
 		u32 name;
-		u32 rseqno[I915_NUM_ENGINES], wseqno;
+		u32 wseqno;
 		u64 gtt_offset;
 		u32 read_domains;
 		u32 write_domain;
diff --git a/drivers/gpu/drm/i915/i915_request.h b/drivers/gpu/drm/i915/i915_request.h
index a355a081485f..e1c9365dfefb 100644
--- a/drivers/gpu/drm/i915/i915_request.h
+++ b/drivers/gpu/drm/i915/i915_request.h
@@ -380,6 +380,7 @@ static inline void
 init_request_active(struct i915_gem_active *active,
 		    i915_gem_retire_fn retire)
 {
+	RCU_INIT_POINTER(active->request, NULL);
 	INIT_LIST_HEAD(&active->link);
 	active->retire = retire ?: i915_gem_retire_noop;
 }
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 6f3a0f2296c2..b4cc98330225 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -63,18 +63,20 @@ static void vma_print_allocator(struct i915_vma *vma, const char *reason)
 
 #endif
 
+struct i915_vma_active {
+	struct i915_gem_active base;
+	struct i915_vma *vma;
+	struct rb_node node;
+	u64 timeline;
+};
+
 static void
-i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
+__i915_vma_retire(struct i915_vma *vma, struct i915_request *rq)
 {
-	const unsigned int idx = rq->engine->id;
-	struct i915_vma *vma =
-		container_of(active, struct i915_vma, last_read[idx]);
 	struct drm_i915_gem_object *obj = vma->obj;
 
-	GEM_BUG_ON(!i915_vma_has_active_engine(vma, idx));
-
-	i915_vma_clear_active(vma, idx);
-	if (i915_vma_is_active(vma))
+	GEM_BUG_ON(!i915_vma_is_active(vma));
+	if (--vma->active_count)
 		return;
 
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
@@ -108,6 +110,15 @@ i915_vma_retire(struct i915_gem_active *active, struct i915_request *rq)
 	}
 }
 
+static void
+i915_vma_retire(struct i915_gem_active *base, struct i915_request *rq)
+{
+	struct i915_vma_active *active =
+		container_of(base, typeof(*active), base);
+
+	__i915_vma_retire(active->vma, rq);
+}
+
 static struct i915_vma *
 vma_create(struct drm_i915_gem_object *obj,
 	   struct i915_address_space *vm,
@@ -115,7 +126,6 @@ vma_create(struct drm_i915_gem_object *obj,
 {
 	struct i915_vma *vma;
 	struct rb_node *rb, **p;
-	int i;
 
 	/* The aliasing_ppgtt should never be used directly! */
 	GEM_BUG_ON(vm == &vm->i915->mm.aliasing_ppgtt->vm);
@@ -124,8 +134,8 @@ vma_create(struct drm_i915_gem_object *obj,
 	if (vma == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		init_request_active(&vma->last_read[i], i915_vma_retire);
+	vma->active = RB_ROOT;
+
 	init_request_active(&vma->last_fence, NULL);
 	vma->vm = vm;
 	vma->ops = &vm->vma_ops;
@@ -778,13 +788,11 @@ void i915_vma_reopen(struct i915_vma *vma)
 static void __i915_vma_destroy(struct i915_vma *vma)
 {
 	struct drm_i915_private *i915 = vma->vm->i915;
-	int i;
+	struct i915_vma_active *iter, *n;
 
 	GEM_BUG_ON(vma->node.allocated);
 	GEM_BUG_ON(vma->fence);
 
-	for (i = 0; i < ARRAY_SIZE(vma->last_read); i++)
-		GEM_BUG_ON(i915_gem_active_isset(&vma->last_read[i]));
 	GEM_BUG_ON(i915_gem_active_isset(&vma->last_fence));
 
 	list_del(&vma->obj_link);
@@ -795,6 +803,11 @@ static void __i915_vma_destroy(struct i915_vma *vma)
 	if (!i915_vma_is_ggtt(vma))
 		i915_ppgtt_put(i915_vm_to_ppgtt(vma->vm));
 
+	rbtree_postorder_for_each_entry_safe(iter, n, &vma->active, node) {
+		GEM_BUG_ON(i915_gem_active_isset(&iter->base));
+		kfree(iter);
+	}
+
 	kmem_cache_free(i915->vmas, vma);
 }
 
@@ -878,16 +891,54 @@ static void export_fence(struct i915_vma *vma,
 	reservation_object_unlock(resv);
 }
 
+static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
+{
+	struct i915_vma_active *active;
+	struct rb_node **p, *parent;
+
+	parent = NULL;
+	p = &vma->active.rb_node;
+	while (*p) {
+		parent = *p;
+
+		active = rb_entry(parent, struct i915_vma_active, node);
+		if (active->timeline == idx)
+			return &active->base;
+
+		if (active->timeline < idx)
+			p = &parent->rb_right;
+		else
+			p = &parent->rb_left;
+	}
+
+	active = kmalloc(sizeof(*active), GFP_KERNEL);
+	if (unlikely(!active))
+		return ERR_PTR(-ENOMEM);
+
+	init_request_active(&active->base, i915_vma_retire);
+	active->vma = vma;
+	active->timeline = idx;
+
+	rb_link_node(&active->node, parent, p);
+	rb_insert_color(&active->node, &vma->active);
+
+	return &active->base;
+}
+
 int i915_vma_move_to_active(struct i915_vma *vma,
 			    struct i915_request *rq,
 			    unsigned int flags)
 {
 	struct drm_i915_gem_object *obj = vma->obj;
-	const unsigned int idx = rq->engine->id;
+	struct i915_gem_active *active;
 
 	lockdep_assert_held(&rq->i915->drm.struct_mutex);
 	GEM_BUG_ON(!drm_mm_node_allocated(&vma->node));
 
+	active = active_instance(vma, rq->fence.context);
+	if (IS_ERR(active))
+		return PTR_ERR(active);
+
 	/*
 	 * Add a reference if we're newly entering the active list.
 	 * The order in which we add operations to the retirement queue is
@@ -896,11 +947,13 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 	 * add the active reference first and queue for it to be dropped
 	 * *last*.
 	 */
-	if (!i915_vma_is_active(vma))
+	if (!i915_gem_active_isset(active) && !vma->active_count++) {
+		list_move_tail(&vma->vm_link, &vma->vm->active_list);
 		obj->active_count++;
-	i915_vma_set_active(vma, idx);
-	i915_gem_active_set(&vma->last_read[idx], rq);
-	list_move_tail(&vma->vm_link, &vma->vm->active_list);
+	}
+	i915_gem_active_set(active, rq);
+	GEM_BUG_ON(!i915_vma_is_active(vma));
+	GEM_BUG_ON(!obj->active_count);
 
 	obj->write_domain = 0;
 	if (flags & EXEC_OBJECT_WRITE) {
@@ -922,7 +975,6 @@ int i915_vma_move_to_active(struct i915_vma *vma,
 
 int i915_vma_unbind(struct i915_vma *vma)
 {
-	unsigned long active;
 	int ret;
 
 	lockdep_assert_held(&vma->vm->i915->drm.struct_mutex);
@@ -932,9 +984,8 @@ int i915_vma_unbind(struct i915_vma *vma)
 	 * have side-effects such as unpinning or even unbinding this vma.
 	 */
 	might_sleep();
-	active = i915_vma_get_active(vma);
-	if (active) {
-		int idx;
+	if (i915_vma_is_active(vma)) {
+		struct i915_vma_active *active, *n;
 
 		/*
 		 * When a closed VMA is retired, it is unbound - eek.
@@ -951,18 +1002,17 @@ int i915_vma_unbind(struct i915_vma *vma)
 		 */
 		__i915_vma_pin(vma);
 
-		for_each_active(active, idx) {
-			ret = i915_gem_active_retire(&vma->last_read[idx],
+		rbtree_postorder_for_each_entry_safe(active, n,
+						     &vma->active, node) {
+			ret = i915_gem_active_retire(&active->base,
 						     &vma->vm->i915->drm.struct_mutex);
 			if (ret)
-				break;
-		}
-
-		if (!ret) {
-			ret = i915_gem_active_retire(&vma->last_fence,
-						     &vma->vm->i915->drm.struct_mutex);
+				goto unpin;
 		}
 
+		ret = i915_gem_active_retire(&vma->last_fence,
+					     &vma->vm->i915->drm.struct_mutex);
+unpin:
 		__i915_vma_unpin(vma);
 		if (ret)
 			return ret;
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index a218b689e418..c297b0a0dc47 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -26,6 +26,7 @@
 #define __I915_VMA_H__
 
 #include <linux/io-mapping.h>
+#include <linux/rbtree.h>
 
 #include <drm/drm_mm.h>
 
@@ -94,8 +95,8 @@ struct i915_vma {
 #define I915_VMA_USERFAULT	BIT(I915_VMA_USERFAULT_BIT)
 #define I915_VMA_GGTT_WRITE	BIT(12)
 
-	unsigned int active;
-	struct i915_gem_active last_read[I915_NUM_ENGINES];
+	unsigned int active_count;
+	struct rb_root active;
 	struct i915_gem_active last_fence;
 
 	/**
@@ -138,6 +139,15 @@ i915_vma_instance(struct drm_i915_gem_object *obj,
 
 void i915_vma_unpin_and_release(struct i915_vma **p_vma);
 
+static inline bool i915_vma_is_active(struct i915_vma *vma)
+{
+	return vma->active_count;
+}
+
+int __must_check i915_vma_move_to_active(struct i915_vma *vma,
+					 struct i915_request *rq,
+					 unsigned int flags);
+
 static inline bool i915_vma_is_ggtt(const struct i915_vma *vma)
 {
 	return vma->flags & I915_VMA_GGTT;
@@ -187,38 +197,6 @@ static inline bool i915_vma_has_userfault(const struct i915_vma *vma)
 	return test_bit(I915_VMA_USERFAULT_BIT, &vma->flags);
 }
 
-static inline unsigned int i915_vma_get_active(const struct i915_vma *vma)
-{
-	return vma->active;
-}
-
-static inline bool i915_vma_is_active(const struct i915_vma *vma)
-{
-	return i915_vma_get_active(vma);
-}
-
-static inline void i915_vma_set_active(struct i915_vma *vma,
-				       unsigned int engine)
-{
-	vma->active |= BIT(engine);
-}
-
-static inline void i915_vma_clear_active(struct i915_vma *vma,
-					 unsigned int engine)
-{
-	vma->active &= ~BIT(engine);
-}
-
-static inline bool i915_vma_has_active_engine(const struct i915_vma *vma,
-					      unsigned int engine)
-{
-	return vma->active & BIT(engine);
-}
-
-int __must_check i915_vma_move_to_active(struct i915_vma *vma,
-					 struct i915_request *rq,
-					 unsigned int flags);
-
 static inline u32 i915_ggtt_offset(const struct i915_vma *vma)
 {
 	GEM_BUG_ON(!i915_vma_is_ggtt(vma));
-- 
cgit v1.2.3


From 8b293eb53a7d7605f762351918083a4e402dc784 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 13:31:57 +0100
Subject: drm/i915: Track the last-active inside the i915_vma

Using a VMA on more than one timeline concurrently is the exception
rather than the rule (using it concurrently on multiple engines). As we
expect to only use one active tracker, store the most recently used
tracker inside the i915_vma itself and only fallback to the rbtree if
we need a second or more concurrent active trackers.

v2: Comments on how we overwrite any existing last_active cache.
v3: __list_del_entry() before list_replace_init() is confusing and, much
more important, entirely redundant.
v4: Note that both last_active and the rbtree may be simultaneously
tracking this timeline, albeit with different requests, and so the vma
may be retired twice for the same timeline.
v5: No, that list_del is required!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706123157.9645-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_vma.c | 58 +++++++++++++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/i915_vma.h |  1 +
 2 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index b4cc98330225..ed4e0fb558f7 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -119,6 +119,12 @@ i915_vma_retire(struct i915_gem_active *base, struct i915_request *rq)
 	__i915_vma_retire(active->vma, rq);
 }
 
+static void
+i915_vma_last_retire(struct i915_gem_active *base, struct i915_request *rq)
+{
+	__i915_vma_retire(container_of(base, struct i915_vma, last_active), rq);
+}
+
 static struct i915_vma *
 vma_create(struct drm_i915_gem_object *obj,
 	   struct i915_address_space *vm,
@@ -136,6 +142,7 @@ vma_create(struct drm_i915_gem_object *obj,
 
 	vma->active = RB_ROOT;
 
+	init_request_active(&vma->last_active, i915_vma_last_retire);
 	init_request_active(&vma->last_fence, NULL);
 	vma->vm = vm;
 	vma->ops = &vm->vma_ops;
@@ -895,6 +902,29 @@ static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
 {
 	struct i915_vma_active *active;
 	struct rb_node **p, *parent;
+	struct i915_request *old;
+
+	/*
+	 * We track the most recently used timeline to skip a rbtree search
+	 * for the common case, under typical loads we never need the rbtree
+	 * at all. We can reuse the last_active slot if it is empty, that is
+	 * after the previous activity has been retired, or if the active
+	 * matches the current timeline.
+	 *
+	 * Note that we allow the timeline to be active simultaneously in
+	 * the rbtree and the last_active cache. We do this to avoid having
+	 * to search and replace the rbtree element for a new timeline, with
+	 * the cost being that we must be aware that the vma may be retired
+	 * twice for the same timeline (as the older rbtree element will be
+	 * retired before the new request added to last_active).
+	 */
+	old = i915_gem_active_raw(&vma->last_active,
+				  &vma->vm->i915->drm.struct_mutex);
+	if (!old || old->fence.context == idx)
+		goto out;
+
+	/* Move the currently active fence into the rbtree */
+	idx = old->fence.context;
 
 	parent = NULL;
 	p = &vma->active.rb_node;
@@ -903,7 +933,7 @@ static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
 
 		active = rb_entry(parent, struct i915_vma_active, node);
 		if (active->timeline == idx)
-			return &active->base;
+			goto replace;
 
 		if (active->timeline < idx)
 			p = &parent->rb_right;
@@ -922,7 +952,26 @@ static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
 	rb_link_node(&active->node, parent, p);
 	rb_insert_color(&active->node, &vma->active);
 
-	return &active->base;
+replace:
+	/*
+	 * Overwrite the previous active slot in the rbtree with last_active,
+	 * leaving last_active zeroed. If the previous slot is still active,
+	 * we must be careful as we now only expect to receive one retire
+	 * callback not two, and so much undo the active counting for the
+	 * overwritten slot.
+	 */
+	if (i915_gem_active_isset(&active->base)) {
+		/* Retire ourselves from the old rq->active_list */
+		__list_del_entry(&active->base.link);
+		vma->active_count--;
+		GEM_BUG_ON(!vma->active_count);
+	}
+	GEM_BUG_ON(list_empty(&vma->last_active.link));
+	list_replace_init(&vma->last_active.link, &active->base.link);
+	active->base.request = fetch_and_zero(&vma->last_active.request);
+
+out:
+	return &vma->last_active;
 }
 
 int i915_vma_move_to_active(struct i915_vma *vma,
@@ -1002,6 +1051,11 @@ int i915_vma_unbind(struct i915_vma *vma)
 		 */
 		__i915_vma_pin(vma);
 
+		ret = i915_gem_active_retire(&vma->last_active,
+					     &vma->vm->i915->drm.struct_mutex);
+		if (ret)
+			goto unpin;
+
 		rbtree_postorder_for_each_entry_safe(active, n,
 						     &vma->active, node) {
 			ret = i915_gem_active_retire(&active->base,
diff --git a/drivers/gpu/drm/i915/i915_vma.h b/drivers/gpu/drm/i915/i915_vma.h
index c297b0a0dc47..f06d66377107 100644
--- a/drivers/gpu/drm/i915/i915_vma.h
+++ b/drivers/gpu/drm/i915/i915_vma.h
@@ -97,6 +97,7 @@ struct i915_vma {
 
 	unsigned int active_count;
 	struct rb_root active;
+	struct i915_gem_active last_active;
 	struct i915_gem_active last_fence;
 
 	/**
-- 
cgit v1.2.3


From 2772ffd979baa1893c1fa75041c59b507716dcc7 Mon Sep 17 00:00:00 2001
From: Dinh Nguyen <dinguyen@kernel.org>
Date: Tue, 26 Jun 2018 08:28:09 -0500
Subject: clk: socfpga: stratix10: fix the parents of mpu_free_clk

Add a clock mux that is used as a parent for the mpu_free_clk.

Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/socfpga/clk-s10.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/socfpga/clk-s10.c b/drivers/clk/socfpga/clk-s10.c
index 72714633e39c..a15769f9985b 100644
--- a/drivers/clk/socfpga/clk-s10.c
+++ b/drivers/clk/socfpga/clk-s10.c
@@ -37,6 +37,11 @@ static const char * const s2f_usr0_mux[] = {"f2s_free_clk", "boot_clk"};
 static const char * const emac_mux[] = {"emaca_free_clk", "emacb_free_clk"};
 static const char * const noc_mux[] = {"noc_free_clk", "boot_clk"};
 
+static const char * const mpu_free_mux[] = {"main_mpu_base_clk",
+					    "peri_mpu_base_clk",
+					    "osc1", "cb_intosc_hs_div2_clk",
+					    "f2s_free_clk"};
+
 /* clocks in AO (always on) controller */
 static const struct stratix10_pll_clock s10_pll_clks[] = {
 	{ STRATIX10_BOOT_CLK, "boot_clk", boot_mux, ARRAY_SIZE(boot_mux), 0,
@@ -57,7 +62,7 @@ static const struct stratix10_perip_c_clock s10_main_perip_c_clks[] = {
 };
 
 static const struct stratix10_perip_cnt_clock s10_main_perip_cnt_clks[] = {
-	{ STRATIX10_MPU_FREE_CLK, "mpu_free_clk", NULL, cntr_mux, ARRAY_SIZE(cntr_mux),
+	{ STRATIX10_MPU_FREE_CLK, "mpu_free_clk", NULL, mpu_free_mux, ARRAY_SIZE(mpu_free_mux),
 	   0, 0x48, 0, 0, 0},
 	{ STRATIX10_NOC_FREE_CLK, "noc_free_clk", NULL, noc_free_mux, ARRAY_SIZE(noc_free_mux),
 	  0, 0x4C, 0, 0, 0},
-- 
cgit v1.2.3


From 51b9a379a843c288b07b501784a5cc52b2c5aa69 Mon Sep 17 00:00:00 2001
From: Dinh Nguyen <dinguyen@kernel.org>
Date: Tue, 26 Jun 2018 08:28:10 -0500
Subject: clk: socfpga: stratix10: fix the sdmmc_free_clk mux

The first parent of the sdmmc_free_clk should be the main_sdmmc_clk.

Signed-off-by: Dinh Nguyen <dinguyen@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/socfpga/clk-s10.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/socfpga/clk-s10.c b/drivers/clk/socfpga/clk-s10.c
index a15769f9985b..5b238fc314ac 100644
--- a/drivers/clk/socfpga/clk-s10.c
+++ b/drivers/clk/socfpga/clk-s10.c
@@ -28,7 +28,7 @@ static const char * const emaca_free_mux[] = {"peri_emaca_clk", "boot_clk"};
 static const char * const emacb_free_mux[] = {"peri_emacb_clk", "boot_clk"};
 static const char * const emac_ptp_free_mux[] = {"peri_emac_ptp_clk", "boot_clk"};
 static const char * const gpio_db_free_mux[] = {"peri_gpio_db_clk", "boot_clk"};
-static const char * const sdmmc_free_mux[] = {"peri_sdmmc_clk", "boot_clk"};
+static const char * const sdmmc_free_mux[] = {"main_sdmmc_clk", "boot_clk"};
 static const char * const s2f_usr1_free_mux[] = {"peri_s2f_usr1_clk", "boot_clk"};
 static const char * const psi_ref_free_mux[] = {"peri_psi_ref_clk", "boot_clk"};
 static const char * const mpu_mux[] = { "mpu_free_clk", "boot_clk",};
-- 
cgit v1.2.3


From 5f273c0d9facfea124f6dea9de41775085056cc2 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Mon, 18 Jun 2018 17:12:35 +0300
Subject: dt-bindings: clk: at91: add an I2S mux clock

The I2S mux clock can be used to select the I2S input clock. The
available parents are the peripheral and the generated clocks.

Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/at91-clock.txt       | 35 ++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/Documentation/devicetree/bindings/clock/at91-clock.txt b/Documentation/devicetree/bindings/clock/at91-clock.txt
index 51c259a92d02..d0adbf5ae144 100644
--- a/Documentation/devicetree/bindings/clock/at91-clock.txt
+++ b/Documentation/devicetree/bindings/clock/at91-clock.txt
@@ -91,6 +91,9 @@ Required properties:
 		at91 audio pll output on AUDIOPLLCLK that feeds the PMC
 		and can be used by peripheral clock or generic clock
 
+	"atmel,sama5d2-clk-i2s-mux" (under pmc node):
+		at91 I2S clock source selection
+
 Required properties for SCKC node:
 - reg : defines the IO memory reserved for the SCKC.
 - #size-cells : shall be 0 (reg is used to encode clk id).
@@ -507,3 +510,35 @@ For example:
 			atmel,clk-output-range = <0 83000000>;
 		};
 	};
+
+Required properties for I2S mux clocks:
+- #size-cells : shall be 0 (reg is used to encode I2S bus id).
+- #address-cells : shall be 1 (reg is used to encode I2S bus id).
+- name: device tree node describing a specific mux clock.
+	* #clock-cells : from common clock binding; shall be set to 0.
+	* clocks : shall be the mux clock parent phandles; shall be 2 phandles:
+	  peripheral and generated clock; the first phandle shall belong to the
+	  peripheral clock and the second one shall belong to the generated
+	  clock; "clock-indices" property can be user to specify
+	  the correct order.
+	* reg: I2S bus id of the corresponding mux clock.
+	  e.g. reg = <0>; for i2s0, reg = <1>; for i2s1
+
+For example:
+	i2s_clkmux {
+		compatible = "atmel,sama5d2-clk-i2s-mux";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		i2s0muxck: i2s0_muxclk {
+			clocks = <&i2s0_clk>, <&i2s0_gclk>;
+			#clock-cells = <0>;
+			reg = <0>;
+		};
+
+		i2s1muxck: i2s1_muxclk {
+			clocks = <&i2s1_clk>, <&i2s1_gclk>;
+			#clock-cells = <0>;
+			reg = <1>;
+		};
+	};
-- 
cgit v1.2.3


From 96e4ea8c253d12079db4d7174990455b4bbf0c87 Mon Sep 17 00:00:00 2001
From: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
Date: Mon, 18 Jun 2018 17:12:36 +0300
Subject: clk: at91: add I2S clock mux driver

This driver is a simple muxing driver that controls the
I2S's clock input by using syscon/regmap to change the parent.
The available inputs can be peripheral clock and generated clock.

Signed-off-by: Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
[sboyd@kernel.org: Fix SPDX tag comment style]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 arch/arm/mach-at91/Kconfig     |   4 ++
 drivers/clk/at91/Makefile      |   1 +
 drivers/clk/at91/clk-i2s-mux.c | 116 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 121 insertions(+)
 create mode 100644 drivers/clk/at91/clk-i2s-mux.c

diff --git a/arch/arm/mach-at91/Kconfig b/arch/arm/mach-at91/Kconfig
index 1254bf9d91b4..903f23c309df 100644
--- a/arch/arm/mach-at91/Kconfig
+++ b/arch/arm/mach-at91/Kconfig
@@ -27,6 +27,7 @@ config SOC_SAMA5D2
 	select HAVE_AT91_H32MX
 	select HAVE_AT91_GENERATED_CLK
 	select HAVE_AT91_AUDIO_PLL
+	select HAVE_AT91_I2S_MUX_CLK
 	select PINCTRL_AT91PIO4
 	help
 	  Select this if ou are using one of Microchip's SAMA5D2 family SoC.
@@ -129,6 +130,9 @@ config HAVE_AT91_GENERATED_CLK
 config HAVE_AT91_AUDIO_PLL
 	bool
 
+config HAVE_AT91_I2S_MUX_CLK
+	bool
+
 config SOC_SAM_V4_V5
 	bool
 
diff --git a/drivers/clk/at91/Makefile b/drivers/clk/at91/Makefile
index 082596f37c1d..facc169ebb68 100644
--- a/drivers/clk/at91/Makefile
+++ b/drivers/clk/at91/Makefile
@@ -13,3 +13,4 @@ obj-$(CONFIG_HAVE_AT91_USB_CLK)		+= clk-usb.o
 obj-$(CONFIG_HAVE_AT91_SMD)		+= clk-smd.o
 obj-$(CONFIG_HAVE_AT91_H32MX)		+= clk-h32mx.o
 obj-$(CONFIG_HAVE_AT91_GENERATED_CLK)	+= clk-generated.o
+obj-$(CONFIG_HAVE_AT91_I2S_MUX_CLK)	+= clk-i2s-mux.o
diff --git a/drivers/clk/at91/clk-i2s-mux.c b/drivers/clk/at91/clk-i2s-mux.c
new file mode 100644
index 000000000000..f0c3c3079f04
--- /dev/null
+++ b/drivers/clk/at91/clk-i2s-mux.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  Copyright (C) 2018 Microchip Technology Inc,
+ *                     Codrin Ciubotariu <codrin.ciubotariu@microchip.com>
+ *
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/of.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+
+#include <soc/at91/atmel-sfr.h>
+
+#define	I2S_BUS_NR	2
+
+struct clk_i2s_mux {
+	struct clk_hw hw;
+	struct regmap *regmap;
+	u8 bus_id;
+};
+
+#define to_clk_i2s_mux(hw) container_of(hw, struct clk_i2s_mux, hw)
+
+static u8 clk_i2s_mux_get_parent(struct clk_hw *hw)
+{
+	struct clk_i2s_mux *mux = to_clk_i2s_mux(hw);
+	u32 val;
+
+	regmap_read(mux->regmap, AT91_SFR_I2SCLKSEL, &val);
+
+	return (val & BIT(mux->bus_id)) >> mux->bus_id;
+}
+
+static int clk_i2s_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct clk_i2s_mux *mux = to_clk_i2s_mux(hw);
+
+	return regmap_update_bits(mux->regmap, AT91_SFR_I2SCLKSEL,
+				  BIT(mux->bus_id), index << mux->bus_id);
+}
+
+static const struct clk_ops clk_i2s_mux_ops = {
+	.get_parent = clk_i2s_mux_get_parent,
+	.set_parent = clk_i2s_mux_set_parent,
+	.determine_rate = __clk_mux_determine_rate,
+};
+
+static struct clk_hw * __init
+at91_clk_i2s_mux_register(struct regmap *regmap, const char *name,
+			  const char * const *parent_names,
+			  unsigned int num_parents, u8 bus_id)
+{
+	struct clk_init_data init = {};
+	struct clk_i2s_mux *i2s_ck;
+	int ret;
+
+	i2s_ck = kzalloc(sizeof(*i2s_ck), GFP_KERNEL);
+	if (!i2s_ck)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = name;
+	init.ops = &clk_i2s_mux_ops;
+	init.parent_names = parent_names;
+	init.num_parents = num_parents;
+
+	i2s_ck->hw.init = &init;
+	i2s_ck->bus_id = bus_id;
+	i2s_ck->regmap = regmap;
+
+	ret = clk_hw_register(NULL, &i2s_ck->hw);
+	if (ret) {
+		kfree(i2s_ck);
+		return ERR_PTR(ret);
+	}
+
+	return &i2s_ck->hw;
+}
+
+static void __init of_sama5d2_clk_i2s_mux_setup(struct device_node *np)
+{
+	struct regmap *regmap_sfr;
+	u8 bus_id;
+	const char *parent_names[2];
+	struct device_node *i2s_mux_np;
+	struct clk_hw *hw;
+	int ret;
+
+	regmap_sfr = syscon_regmap_lookup_by_compatible("atmel,sama5d2-sfr");
+	if (IS_ERR(regmap_sfr))
+		return;
+
+	for_each_child_of_node(np, i2s_mux_np) {
+		if (of_property_read_u8(i2s_mux_np, "reg", &bus_id))
+			continue;
+
+		if (bus_id > I2S_BUS_NR)
+			continue;
+
+		ret = of_clk_parent_fill(i2s_mux_np, parent_names, 2);
+		if (ret != 2)
+			continue;
+
+		hw = at91_clk_i2s_mux_register(regmap_sfr, i2s_mux_np->name,
+					       parent_names, 2, bus_id);
+		if (IS_ERR(hw))
+			continue;
+
+		of_clk_add_hw_provider(i2s_mux_np, of_clk_hw_simple_get, hw);
+	}
+}
+
+CLK_OF_DECLARE(sama5d2_clk_i2s_mux, "atmel,sama5d2-clk-i2s-mux",
+	       of_sama5d2_clk_i2s_mux_setup);
-- 
cgit v1.2.3


From 3b4c2511c004521efa89875512b5039a04d5e2e0 Mon Sep 17 00:00:00 2001
From: Neha Bhende <bhenden@vmware.com>
Date: Mon, 18 Jun 2018 16:44:48 -0700
Subject: drm/vmwgfx: Add CAP2 support in vmwgfx

The device exposes a new capability register. Add support for it.

Signed-off-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c   | 17 +++++++++++++++++
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h   |  1 +
 drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c |  3 +++
 include/uapi/drm/vmwgfx_drm.h         |  1 +
 4 files changed, 22 insertions(+)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 1128420de2c0..f2fad88e4c54 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -258,6 +258,15 @@ MODULE_PARM_DESC(assume_16bpp, "Assume 16-bpp when filtering modes");
 module_param_named(assume_16bpp, vmw_assume_16bpp, int, 0600);
 
 
+static void vmw_print_capabilities2(uint32_t capabilities2)
+{
+	DRM_INFO("Capabilities2:\n");
+	if (capabilities2 & SVGA_CAP2_GROW_OTABLE)
+		DRM_INFO("  Grow oTable.\n");
+	if (capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY)
+		DRM_INFO("  IntraSurface copy.\n");
+}
+
 static void vmw_print_capabilities(uint32_t capabilities)
 {
 	DRM_INFO("Capabilities:\n");
@@ -684,6 +693,12 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	dev_priv->capabilities = vmw_read(dev_priv, SVGA_REG_CAPABILITIES);
+
+	if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER) {
+		dev_priv->capabilities2 = vmw_read(dev_priv, SVGA_REG_CAP2);
+	}
+
+
 	ret = vmw_dma_select_mode(dev_priv);
 	if (unlikely(ret != 0)) {
 		DRM_INFO("Restricting capabilities due to IOMMU setup.\n");
@@ -752,6 +767,8 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	}
 
 	vmw_print_capabilities(dev_priv->capabilities);
+	if (dev_priv->capabilities & SVGA_CAP_CAP2_REGISTER)
+		vmw_print_capabilities2(dev_priv->capabilities2);
 
 	ret = vmw_dma_masks(dev_priv);
 	if (unlikely(ret != 0))
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index a3a0826958a1..920365c0e9ab 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -386,6 +386,7 @@ struct vmw_private {
 	uint32_t initial_height;
 	u32 *mmio_virt;
 	uint32_t capabilities;
+	uint32_t capabilities2;
 	uint32_t max_gmr_ids;
 	uint32_t max_gmr_pages;
 	uint32_t max_mob_pages;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index 6872c7ee8a08..ac6da0da2824 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -56,6 +56,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 	case DRM_VMW_PARAM_HW_CAPS:
 		param->value = dev_priv->capabilities;
 		break;
+	case DRM_VMW_PARAM_HW_CAPS2:
+		param->value = dev_priv->capabilities2;
+		break;
 	case DRM_VMW_PARAM_FIFO_CAPS:
 		param->value = dev_priv->fifo.capabilities;
 		break;
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 57115a5fe61a..84e81b38ca18 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -95,6 +95,7 @@ extern "C" {
 #define DRM_VMW_PARAM_MAX_MOB_SIZE     10
 #define DRM_VMW_PARAM_SCREEN_TARGET    11
 #define DRM_VMW_PARAM_DX               12
+#define DRM_VMW_PARAM_HW_CAPS2         13
 
 /**
  * enum drm_vmw_handle_type - handle type for ref ioctls
-- 
cgit v1.2.3


From 0d81d346a6281c59595a34a035c470e54f403cab Mon Sep 17 00:00:00 2001
From: Neha Bhende <bhenden@vmware.com>
Date: Mon, 18 Jun 2018 17:14:56 -0700
Subject: drm/vmwgfx: Add support for SVGA3dCmdIntraSurfaceCopy command

A new command to support Intra-Surface-Copy.

Signed-off-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
index 2d6efc36288f..8b8386cb9893 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -3116,6 +3116,32 @@ static int vmw_cmd_dx_transfer_from_buffer(struct vmw_private *dev_priv,
 				 &cmd->body.destSid, NULL);
 }
 
+/**
+ * vmw_cmd_intra_surface_copy -
+ * Validate an SVGA_3D_CMD_INTRA_SURFACE_COPY command
+ *
+ * @dev_priv: Pointer to a device private struct.
+ * @sw_context: The software context being used for this batch.
+ * @header: Pointer to the command header in the command stream.
+ */
+static int vmw_cmd_intra_surface_copy(struct vmw_private *dev_priv,
+					   struct vmw_sw_context *sw_context,
+					   SVGA3dCmdHeader *header)
+{
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdIntraSurfaceCopy body;
+	} *cmd = container_of(header, typeof(*cmd), header);
+
+	if (!(dev_priv->capabilities2 & SVGA_CAP2_INTRA_SURFACE_COPY))
+		return -EINVAL;
+
+	return vmw_cmd_res_check(dev_priv, sw_context, vmw_res_surface,
+				user_surface_converter,
+				&cmd->body.surface.sid, NULL);
+}
+
+
 static int vmw_cmd_check_not_3d(struct vmw_private *dev_priv,
 				struct vmw_sw_context *sw_context,
 				void *buf, uint32_t *size)
@@ -3471,6 +3497,8 @@ static const struct vmw_cmd_entry vmw_cmd_entries[SVGA_3D_CMD_MAX] = {
 	VMW_CMD_DEF(SVGA_3D_CMD_DX_TRANSFER_FROM_BUFFER,
 		    &vmw_cmd_dx_transfer_from_buffer,
 		    true, false, true),
+	VMW_CMD_DEF(SVGA_3D_CMD_INTRA_SURFACE_COPY, &vmw_cmd_intra_surface_copy,
+		    true, false, true),
 };
 
 bool vmw_cmd_describe(const void *buf, u32 *size, char const **cmd)
-- 
cgit v1.2.3


From 30aeee6728abf29b29d625061782519a15be88db Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 13:52:32 -0700
Subject: drm/vmwgfx: Add SM4_1 flag

A boolean flag in device private structure to specify if the device
support SM4_1.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c | 18 ++++++++++++++++--
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h |  1 +
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index f2fad88e4c54..6cf81e19182f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -916,9 +916,23 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset)
 	if (ret)
 		goto out_no_fifo;
 
+	if (dev_priv->has_dx) {
+		/*
+		 * SVGA_CAP2_DX2 (DefineGBSurface_v3) is needed for SM4_1
+		 * support
+		 */
+		if ((dev_priv->capabilities2 & SVGA_CAP2_DX2) != 0) {
+			vmw_write(dev_priv, SVGA_REG_DEV_CAP,
+					SVGA3D_DEVCAP_SM41);
+			dev_priv->has_sm4_1 = vmw_read(dev_priv,
+							SVGA_REG_DEV_CAP);
+		}
+	}
+
 	DRM_INFO("DX: %s\n", dev_priv->has_dx ? "yes." : "no.");
-	DRM_INFO("Atomic: %s\n",
-		 (dev->driver->driver_features & DRIVER_ATOMIC) ? "yes" : "no");
+	DRM_INFO("Atomic: %s\n", (dev->driver->driver_features & DRIVER_ATOMIC)
+		 ? "yes." : "no.");
+	DRM_INFO("SM4_1: %s\n", dev_priv->has_sm4_1 ? "yes." : "no.");
 
 	snprintf(host_log, sizeof(host_log), "vmwgfx: %s-%s",
 		VMWGFX_REPO, VMWGFX_GIT_VERSION);
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 920365c0e9ab..7bb08bac728e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -398,6 +398,7 @@ struct vmw_private {
 	spinlock_t cap_lock;
 	bool has_dx;
 	bool assume_16bpp;
+	bool has_sm4_1;
 
 	/*
 	 * VGA registers.
-- 
cgit v1.2.3


From cdff8e73006c05ee342dd588b5ba90b5def56184 Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 14:20:23 -0700
Subject: drm/vmwgfx: Add support for SVGA3dCmdDefineGBSurface_v3

SVGA device added new command SVGA3dCmdDefineGBSurface_v3 which allows
64-bit SVGA3dSurfaceAllFlags. This commit adds support for
SVGA3dCmdDefineGBSurface_v3 command in vmwgfx.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h     |  2 ++
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c    |  3 +++
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 32 ++++++++++++++++++++++++++++++--
 3 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 7bb08bac728e..06cce72b7b9e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -180,6 +180,8 @@ struct vmw_surface {
 	SVGA3dTextureFilter autogen_filter;
 	uint32_t multisample_count;
 	struct list_head view_list;
+	SVGA3dMSPattern multisample_pattern;
+	SVGA3dMSQualityLevel quality_level;
 };
 
 struct vmw_marker_queue {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 15f2cb2a151b..6630abf3a95c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1157,6 +1157,9 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 			content_srf.flags             = 0;
 			content_srf.mip_levels[0]     = 1;
 			content_srf.multisample_count = 0;
+			content_srf.multisample_pattern =
+				SVGA3D_MS_PATTERN_NONE;
+			content_srf.quality_level = SVGA3D_MS_QUALITY_NONE;
 		} else {
 			content_srf = *new_vfbs->surface;
 		}
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index e90f8d39de53..2abf9a895605 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -785,6 +785,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	srf->base_size = *srf->sizes;
 	srf->autogen_filter = SVGA3D_TEX_FILTER_NONE;
 	srf->multisample_count = 0;
+	srf->multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	srf->quality_level = SVGA3D_MS_QUALITY_NONE;
 
 	cur_bo_offset = 0;
 	cur_offset = srf->offsets;
@@ -1031,6 +1033,10 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		SVGA3dCmdHeader header;
 		SVGA3dCmdDefineGBSurface_v2 body;
 	} *cmd2;
+	struct {
+		SVGA3dCmdHeader header;
+		SVGA3dCmdDefineGBSurface_v3 body;
+	} *cmd3;
 
 	if (likely(res->id != -1))
 		return 0;
@@ -1047,7 +1053,11 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		goto out_no_fifo;
 	}
 
-	if (srf->array_size > 0) {
+	if (dev_priv->has_sm4_1 && srf->array_size > 0) {
+		cmd_id = SVGA_3D_CMD_DEFINE_GB_SURFACE_V3;
+		cmd_len = sizeof(cmd3->body);
+		submit_len = sizeof(*cmd3);
+	} else if (srf->array_size > 0) {
 		/* has_dx checked on creation time. */
 		cmd_id = SVGA_3D_CMD_DEFINE_GB_SURFACE_V2;
 		cmd_len = sizeof(cmd2->body);
@@ -1060,6 +1070,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 
 	cmd = vmw_fifo_reserve(dev_priv, submit_len);
 	cmd2 = (typeof(cmd2))cmd;
+	cmd3 = (typeof(cmd3))cmd;
 	if (unlikely(!cmd)) {
 		DRM_ERROR("Failed reserving FIFO space for surface "
 			  "creation.\n");
@@ -1067,7 +1078,22 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		goto out_no_fifo;
 	}
 
-	if (srf->array_size > 0) {
+	if (dev_priv->has_sm4_1 && srf->array_size > 0) {
+		cmd3->header.id = cmd_id;
+		cmd3->header.size = cmd_len;
+		cmd3->body.sid = srf->res.id;
+		cmd3->body.surfaceFlags = (SVGA3dSurfaceAllFlags)srf->flags;
+		cmd3->body.format = srf->format;
+		cmd3->body.numMipLevels = srf->mip_levels[0];
+		cmd3->body.multisampleCount = srf->multisample_count;
+		cmd3->body.multisamplePattern = srf->multisample_pattern;
+		cmd3->body.qualityLevel = srf->quality_level;
+		cmd3->body.autogenFilter = srf->autogen_filter;
+		cmd3->body.size.width = srf->base_size.width;
+		cmd3->body.size.height = srf->base_size.height;
+		cmd3->body.size.depth = srf->base_size.depth;
+		cmd3->body.arraySize = srf->array_size;
+	} else if (srf->array_size > 0) {
 		cmd2->header.id = cmd_id;
 		cmd2->header.size = cmd_len;
 		cmd2->body.sid = srf->res.id;
@@ -1561,6 +1587,8 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	srf->autogen_filter    = SVGA3D_TEX_FILTER_NONE;
 	srf->array_size        = array_size;
 	srf->multisample_count = multisample_count;
+	srf->multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	srf->quality_level = SVGA3D_MS_QUALITY_NONE;
 
 	if (array_size)
 		num_layers = array_size;
-- 
cgit v1.2.3


From 397a11175f830e1ceb82b608a1c7adbacfbe39b0 Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 14:25:07 -0700
Subject: drm/vmwgfx: Support for SVGA3dSurfaceAllFlags in vmwgfx

Since svga device introduced new 64bit SVGA3dSurfaceAllFlags, vmwgfx
now stores the surface flags internally as SVGA3dSurfaceAllFlags.
For legacy surface define commands, only lower 32-bit is used.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h     |  4 ++--
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 21 ++++++++++++++-------
 2 files changed, 16 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 06cce72b7b9e..7e5c93083036 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -166,7 +166,7 @@ struct vmw_surface_offset;
 
 struct vmw_surface {
 	struct vmw_resource res;
-	uint32_t flags;
+	SVGA3dSurfaceAllFlags flags;
 	uint32_t format;
 	uint32_t mip_levels[DRM_VMW_MAX_SURFACE_FACES];
 	struct drm_vmw_size base_size;
@@ -1080,7 +1080,7 @@ extern int vmw_surface_validate(struct vmw_private *dev_priv,
 				struct vmw_surface *srf);
 int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t user_accounting_size,
-			       uint32_t svga3d_flags,
+			       SVGA3dSurfaceAllFlags svga3d_flags,
 			       SVGA3dSurfaceFormat format,
 			       bool for_scanout,
 			       uint32_t num_mip_levels,
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 2abf9a895605..a5f93f62c7fa 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -224,7 +224,12 @@ static void vmw_surface_define_encode(const struct vmw_surface *srf,
 	cmd->header.id = SVGA_3D_CMD_SURFACE_DEFINE;
 	cmd->header.size = cmd_len;
 	cmd->body.sid = srf->res.id;
-	cmd->body.surfaceFlags = srf->flags;
+	/*
+	 * Downcast of surfaceFlags, was upcasted when received from user-space,
+	 * since driver internally stores as 64 bit.
+	 * For legacy surface define only 32 bit flag is supported.
+	 */
+	cmd->body.surfaceFlags = (SVGA3dSurface1Flags)srf->flags;
 	cmd->body.format = srf->format;
 	for (i = 0; i < DRM_VMW_MAX_SURFACE_FACES; ++i)
 		cmd->body.face[i].numMipLevels = srf->mip_levels[i];
@@ -760,7 +765,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
 	srf = &user_srf->srf;
 	res = &srf->res;
 
-	srf->flags = req->flags;
+	/* Driver internally stores as 64-bit flags */
+	srf->flags = (SVGA3dSurfaceAllFlags)req->flags;
 	srf->format = req->format;
 	srf->scanout = req->scanout;
 
@@ -992,7 +998,8 @@ int vmw_surface_reference_ioctl(struct drm_device *dev, void *data,
 	user_srf = container_of(base, struct vmw_user_surface, prime.base);
 	srf = &user_srf->srf;
 
-	rep->flags = srf->flags;
+	/* Downcast of flags when sending back to user space */
+	rep->flags = (uint32_t)srf->flags;
 	rep->format = srf->format;
 	memcpy(rep->mip_levels, srf->mip_levels, sizeof(srf->mip_levels));
 	user_sizes = (struct drm_vmw_size __user *)(unsigned long)
@@ -1082,7 +1089,7 @@ static int vmw_gb_surface_create(struct vmw_resource *res)
 		cmd3->header.id = cmd_id;
 		cmd3->header.size = cmd_len;
 		cmd3->body.sid = srf->res.id;
-		cmd3->body.surfaceFlags = (SVGA3dSurfaceAllFlags)srf->flags;
+		cmd3->body.surfaceFlags = srf->flags;
 		cmd3->body.format = srf->format;
 		cmd3->body.numMipLevels = srf->mip_levels[0];
 		cmd3->body.multisampleCount = srf->multisample_count;
@@ -1320,7 +1327,7 @@ int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 	/* Define a surface based on the parameters. */
 	ret = vmw_surface_gb_priv_define(dev,
 			size,
-			req->svga3d_flags,
+			(SVGA3dSurfaceAllFlags)req->svga3d_flags,
 			req->format,
 			req->drm_surface_flags & drm_vmw_surface_flag_scanout,
 			req->mip_levels,
@@ -1451,7 +1458,7 @@ int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data,
 		goto out_bad_resource;
 	}
 
-	rep->creq.svga3d_flags = srf->flags;
+	rep->creq.svga3d_flags = (uint32_t)srf->flags;
 	rep->creq.format = srf->format;
 	rep->creq.mip_levels = srf->mip_levels[0];
 	rep->creq.drm_surface_flags = 0;
@@ -1495,7 +1502,7 @@ out_bad_resource:
  */
 int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t user_accounting_size,
-			       uint32_t svga3d_flags,
+			       SVGA3dSurfaceAllFlags svga3d_flags,
 			       SVGA3dSurfaceFormat format,
 			       bool for_scanout,
 			       uint32_t num_mip_levels,
-- 
cgit v1.2.3


From 14b1c33e84295693c3b1a1d7c6ac82b3f384cd17 Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 14:48:35 -0700
Subject: drm/vmwgfx: Add new ioctl for GB surface create and reference

New ioctls DRM_VMW_GB_SURFACE_CREATE_EXT and DRM_VMW_GB_SURFACE_REF_EXT
are added which support 64-bit wide svga device surface flags, quality
level and multisample pattern.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.c     |  12 +
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h     |   8 +
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c     |  20 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c    |   2 +
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c | 468 +++++++++++++++++++++-----------
 include/uapi/drm/vmwgfx_drm.h           | 102 +++++++
 6 files changed, 437 insertions(+), 175 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
index 6cf81e19182f..59229111f303 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -137,6 +137,12 @@
 #define DRM_IOCTL_VMW_CREATE_EXTENDED_CONTEXT			\
 	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_CREATE_EXTENDED_CONTEXT,	\
 		struct drm_vmw_context_arg)
+#define DRM_IOCTL_VMW_GB_SURFACE_CREATE_EXT				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_CREATE_EXT,	\
+		union drm_vmw_gb_surface_create_ext_arg)
+#define DRM_IOCTL_VMW_GB_SURFACE_REF_EXT				\
+	DRM_IOWR(DRM_COMMAND_BASE + DRM_VMW_GB_SURFACE_REF_EXT,		\
+		union drm_vmw_gb_surface_reference_ext_arg)
 
 /**
  * The core DRM version of this macro doesn't account for
@@ -224,6 +230,12 @@ static const struct drm_ioctl_desc vmw_ioctls[] = {
 	VMW_IOCTL_DEF(VMW_CREATE_EXTENDED_CONTEXT,
 		      vmw_extended_context_define_ioctl,
 		      DRM_AUTH | DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_GB_SURFACE_CREATE_EXT,
+		      vmw_gb_surface_define_ext_ioctl,
+		      DRM_AUTH | DRM_RENDER_ALLOW),
+	VMW_IOCTL_DEF(VMW_GB_SURFACE_REF_EXT,
+		      vmw_gb_surface_reference_ext_ioctl,
+		      DRM_AUTH | DRM_RENDER_ALLOW),
 };
 
 static const struct pci_device_id vmw_pci_id_list[] = {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 7e5c93083036..59af14714797 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -1087,7 +1087,15 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t multisample_count,
 			       uint32_t array_size,
 			       struct drm_vmw_size size,
+			       SVGA3dMSPattern multisample_pattern,
+			       SVGA3dMSQualityLevel quality_level,
 			       struct vmw_surface **srf_out);
+extern int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev,
+					   void *data,
+					   struct drm_file *file_priv);
+extern int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev,
+					      void *data,
+					      struct drm_file *file_priv);
 
 /*
  * Shader management - vmwgfx_shader.c
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index 0fb363458ab5..3201b0a51d10 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1238,15 +1238,17 @@ static int vmw_create_bo_proxy(struct drm_device *dev,
 	content_base_size.depth  = 1;
 
 	ret = vmw_surface_gb_priv_define(dev,
-			0, /* kernel visible only */
-			0, /* flags */
-			format,
-			true, /* can be a scanout buffer */
-			1, /* num of mip levels */
-			0,
-			0,
-			content_base_size,
-			srf_out);
+					 0, /* kernel visible only */
+					 0, /* flags */
+					 format,
+					 true, /* can be a scanout buffer */
+					 1, /* num of mip levels */
+					 0,
+					 0,
+					 content_base_size,
+					 SVGA3D_MS_PATTERN_NONE,
+					 SVGA3D_MS_QUALITY_NONE,
+					 srf_out);
 	if (ret) {
 		DRM_ERROR("Failed to allocate proxy content buffer\n");
 		return ret;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index 6630abf3a95c..f9872c9e60c4 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1188,6 +1188,8 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
 				 content_srf.multisample_count,
 				 0,
 				 display_base_size,
+				 content_srf.multisample_pattern,
+				 content_srf.quality_level,
 				 &vps->surf);
 			if (ret != 0) {
 				DRM_ERROR("Couldn't allocate STDU surface.\n");
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index a5f93f62c7fa..1d4c010a0e48 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -33,6 +33,10 @@
 #include "vmwgfx_binding.h"
 #include "device_include/svga3d_surfacedefs.h"
 
+#define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32)
+#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) (svga3d_flags >> 32)
+#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \
+	(svga3d_flags & ((uint64_t)U32_MAX))
 
 /**
  * struct vmw_user_surface - User-space visible surface resource
@@ -81,7 +85,16 @@ static int vmw_gb_surface_unbind(struct vmw_resource *res,
 				 bool readback,
 				 struct ttm_validate_buffer *val_buf);
 static int vmw_gb_surface_destroy(struct vmw_resource *res);
-
+static int
+vmw_gb_surface_define_internal(struct drm_device *dev,
+			       struct drm_vmw_gb_surface_create_ext_req *req,
+			       struct drm_vmw_gb_surface_create_rep *rep,
+			       struct drm_file *file_priv);
+static int
+vmw_gb_surface_reference_internal(struct drm_device *dev,
+				  struct drm_vmw_surface_arg *req,
+				  struct drm_vmw_gb_surface_ref_ext_rep *rep,
+				  struct drm_file *file_priv);
 
 static const struct vmw_user_resource_conv user_surface_conv = {
 	.object_type = VMW_RES_SURFACE,
@@ -1289,193 +1302,55 @@ static int vmw_gb_surface_destroy(struct vmw_resource *res)
 
 /**
  * vmw_gb_surface_define_ioctl - Ioctl function implementing
- *                               the user surface define functionality.
+ * the user surface define functionality.
  *
- * @dev:            Pointer to a struct drm_device.
- * @data:           Pointer to data copied from / to user-space.
- * @file_priv:      Pointer to a drm file private structure.
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
  */
 int vmw_gb_surface_define_ioctl(struct drm_device *dev, void *data,
 				struct drm_file *file_priv)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
-	struct vmw_user_surface *user_srf;
-	struct vmw_surface *srf;
-	struct vmw_resource *res;
-	struct vmw_resource *tmp;
 	union drm_vmw_gb_surface_create_arg *arg =
 	    (union drm_vmw_gb_surface_create_arg *)data;
-	struct drm_vmw_gb_surface_create_req *req = &arg->req;
 	struct drm_vmw_gb_surface_create_rep *rep = &arg->rep;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	int ret;
-	uint32_t size;
-	uint32_t backup_handle = 0;
-
-	if (req->multisample_count != 0)
-		return -EINVAL;
-
-	if (req->mip_levels > DRM_VMW_MAX_MIP_LEVELS)
-		return -EINVAL;
-
-	if (unlikely(vmw_user_surface_size == 0))
-		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
-			128;
-
-	size = vmw_user_surface_size + 128;
-
-	/* Define a surface based on the parameters. */
-	ret = vmw_surface_gb_priv_define(dev,
-			size,
-			(SVGA3dSurfaceAllFlags)req->svga3d_flags,
-			req->format,
-			req->drm_surface_flags & drm_vmw_surface_flag_scanout,
-			req->mip_levels,
-			req->multisample_count,
-			req->array_size,
-			req->base_size,
-			&srf);
-	if (unlikely(ret != 0))
-		return ret;
-
-	user_srf = container_of(srf, struct vmw_user_surface, srf);
-	if (drm_is_primary_client(file_priv))
-		user_srf->master = drm_master_get(file_priv->master);
-
-	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
-	if (unlikely(ret != 0))
-		return ret;
-
-	res = &user_srf->srf.res;
-
-
-	if (req->buffer_handle != SVGA3D_INVALID_ID) {
-		ret = vmw_user_bo_lookup(tfile, req->buffer_handle,
-					 &res->backup,
-					 &user_srf->backup_base);
-		if (ret == 0) {
-			if (res->backup->base.num_pages * PAGE_SIZE <
-			    res->backup_size) {
-				DRM_ERROR("Surface backup buffer is too small.\n");
-				vmw_bo_unreference(&res->backup);
-				ret = -EINVAL;
-				goto out_unlock;
-			} else {
-				backup_handle = req->buffer_handle;
-			}
-		}
-	} else if (req->drm_surface_flags & drm_vmw_surface_flag_create_buffer)
-		ret = vmw_user_bo_alloc(dev_priv, tfile,
-					res->backup_size,
-					req->drm_surface_flags &
-					drm_vmw_surface_flag_shareable,
-					&backup_handle,
-					&res->backup,
-					&user_srf->backup_base);
-
-	if (unlikely(ret != 0)) {
-		vmw_resource_unreference(&res);
-		goto out_unlock;
-	}
-
-	tmp = vmw_resource_reference(res);
-	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
-				    req->drm_surface_flags &
-				    drm_vmw_surface_flag_shareable,
-				    VMW_RES_SURFACE,
-				    &vmw_user_surface_base_release, NULL);
-
-	if (unlikely(ret != 0)) {
-		vmw_resource_unreference(&tmp);
-		vmw_resource_unreference(&res);
-		goto out_unlock;
-	}
-
-	rep->handle      = user_srf->prime.base.hash.key;
-	rep->backup_size = res->backup_size;
-	if (res->backup) {
-		rep->buffer_map_handle =
-			drm_vma_node_offset_addr(&res->backup->base.vma_node);
-		rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE;
-		rep->buffer_handle = backup_handle;
-	} else {
-		rep->buffer_map_handle = 0;
-		rep->buffer_size = 0;
-		rep->buffer_handle = SVGA3D_INVALID_ID;
-	}
+	struct drm_vmw_gb_surface_create_ext_req req_ext;
 
-	vmw_resource_unreference(&res);
+	req_ext.base = arg->req;
+	req_ext.version = drm_vmw_gb_surface_v1;
+	req_ext.svga3d_flags_upper_32_bits = 0;
+	req_ext.multisample_pattern = SVGA3D_MS_PATTERN_NONE;
+	req_ext.quality_level = SVGA3D_MS_QUALITY_NONE;
+	req_ext.must_be_zero = 0;
 
-out_unlock:
-	ttm_read_unlock(&dev_priv->reservation_sem);
-	return ret;
+	return vmw_gb_surface_define_internal(dev, &req_ext, rep, file_priv);
 }
 
 /**
  * vmw_gb_surface_reference_ioctl - Ioctl function implementing
- *                                  the user surface reference functionality.
+ * the user surface reference functionality.
  *
- * @dev:            Pointer to a struct drm_device.
- * @data:           Pointer to data copied from / to user-space.
- * @file_priv:      Pointer to a drm file private structure.
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
  */
 int vmw_gb_surface_reference_ioctl(struct drm_device *dev, void *data,
 				   struct drm_file *file_priv)
 {
-	struct vmw_private *dev_priv = vmw_priv(dev);
 	union drm_vmw_gb_surface_reference_arg *arg =
 	    (union drm_vmw_gb_surface_reference_arg *)data;
 	struct drm_vmw_surface_arg *req = &arg->req;
 	struct drm_vmw_gb_surface_ref_rep *rep = &arg->rep;
-	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
-	struct vmw_surface *srf;
-	struct vmw_user_surface *user_srf;
-	struct ttm_base_object *base;
-	uint32_t backup_handle;
-	int ret = -EINVAL;
+	struct drm_vmw_gb_surface_ref_ext_rep rep_ext;
+	int ret;
+
+	ret = vmw_gb_surface_reference_internal(dev, req, &rep_ext, file_priv);
 
-	ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid,
-					   req->handle_type, &base);
 	if (unlikely(ret != 0))
 		return ret;
 
-	user_srf = container_of(base, struct vmw_user_surface, prime.base);
-	srf = &user_srf->srf;
-	if (!srf->res.backup) {
-		DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
-		goto out_bad_resource;
-	}
-
-	mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */
-	ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle);
-	mutex_unlock(&dev_priv->cmdbuf_mutex);
-
-	if (unlikely(ret != 0)) {
-		DRM_ERROR("Could not add a reference to a GB surface "
-			  "backup buffer.\n");
-		(void) ttm_ref_object_base_unref(tfile, base->hash.key,
-						 TTM_REF_USAGE);
-		goto out_bad_resource;
-	}
-
-	rep->creq.svga3d_flags = (uint32_t)srf->flags;
-	rep->creq.format = srf->format;
-	rep->creq.mip_levels = srf->mip_levels[0];
-	rep->creq.drm_surface_flags = 0;
-	rep->creq.multisample_count = srf->multisample_count;
-	rep->creq.autogen_filter = srf->autogen_filter;
-	rep->creq.array_size = srf->array_size;
-	rep->creq.buffer_handle = backup_handle;
-	rep->creq.base_size = srf->base_size;
-	rep->crep.handle = user_srf->prime.base.hash.key;
-	rep->crep.backup_size = srf->res.backup_size;
-	rep->crep.buffer_handle = backup_handle;
-	rep->crep.buffer_map_handle =
-		drm_vma_node_offset_addr(&srf->res.backup->base.vma_node);
-	rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE;
-
-out_bad_resource:
-	ttm_base_object_unref(&base);
+	rep->creq = rep_ext.creq.base;
+	rep->crep = rep_ext.crep;
 
 	return ret;
 }
@@ -1493,6 +1368,8 @@ out_bad_resource:
  * @multisample_count:
  * @array_size: Surface array size.
  * @size: width, heigh, depth of the surface requested
+ * @multisample_pattern: Multisampling pattern when msaa is supported
+ * @quality_level: Precision settings
  * @user_srf_out: allocated user_srf.  Set to NULL on failure.
  *
  * GB surfaces allocated by this function will not have a user mode handle, and
@@ -1509,6 +1386,8 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 			       uint32_t multisample_count,
 			       uint32_t array_size,
 			       struct drm_vmw_size size,
+			       SVGA3dMSPattern multisample_pattern,
+			       SVGA3dMSQualityLevel quality_level,
 			       struct vmw_surface **srf_out)
 {
 	struct vmw_private *dev_priv = vmw_priv(dev);
@@ -1519,7 +1398,7 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	};
 	struct vmw_surface *srf;
 	int ret;
-	u32 num_layers;
+	u32 num_layers = 1;
 
 	*srf_out = NULL;
 
@@ -1594,15 +1473,13 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	srf->autogen_filter    = SVGA3D_TEX_FILTER_NONE;
 	srf->array_size        = array_size;
 	srf->multisample_count = multisample_count;
-	srf->multisample_pattern = SVGA3D_MS_PATTERN_NONE;
-	srf->quality_level = SVGA3D_MS_QUALITY_NONE;
+	srf->multisample_pattern = multisample_pattern;
+	srf->quality_level = quality_level;
 
 	if (array_size)
 		num_layers = array_size;
 	else if (svga3d_flags & SVGA3D_SURFACE_CUBEMAP)
 		num_layers = SVGA3D_MAX_SURFACE_FACES;
-	else
-		num_layers = 1;
 
 	srf->res.backup_size   =
 		svga3dsurface_get_serialized_size(srf->format,
@@ -1633,3 +1510,262 @@ out_unlock:
 	ttm_read_unlock(&dev_priv->reservation_sem);
 	return ret;
 }
+
+/**
+ * vmw_gb_surface_define_ext_ioctl - Ioctl function implementing
+ * the user surface define functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+int vmw_gb_surface_define_ext_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *file_priv)
+{
+	union drm_vmw_gb_surface_create_ext_arg *arg =
+	    (union drm_vmw_gb_surface_create_ext_arg *)data;
+	struct drm_vmw_gb_surface_create_ext_req *req = &arg->req;
+	struct drm_vmw_gb_surface_create_rep *rep = &arg->rep;
+
+	return vmw_gb_surface_define_internal(dev, req, rep, file_priv);
+}
+
+/**
+ * vmw_gb_surface_reference_ext_ioctl - Ioctl function implementing
+ * the user surface reference functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @data: Pointer to data copied from / to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev, void *data,
+				   struct drm_file *file_priv)
+{
+	union drm_vmw_gb_surface_reference_ext_arg *arg =
+	    (union drm_vmw_gb_surface_reference_ext_arg *)data;
+	struct drm_vmw_surface_arg *req = &arg->req;
+	struct drm_vmw_gb_surface_ref_ext_rep *rep = &arg->rep;
+
+	return vmw_gb_surface_reference_internal(dev, req, rep, file_priv);
+}
+
+/**
+ * vmw_gb_surface_define_internal - Ioctl function implementing
+ * the user surface define functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @req: Request argument from user-space.
+ * @rep: Response argument to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+static int
+vmw_gb_surface_define_internal(struct drm_device *dev,
+			       struct drm_vmw_gb_surface_create_ext_req *req,
+			       struct drm_vmw_gb_surface_create_rep *rep,
+			       struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct vmw_user_surface *user_srf;
+	struct vmw_surface *srf;
+	struct vmw_resource *res;
+	struct vmw_resource *tmp;
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	int ret;
+	uint32_t size;
+	uint32_t backup_handle = 0;
+	SVGA3dSurfaceAllFlags svga3d_flags_64 =
+		SVGA3D_FLAGS_64(req->svga3d_flags_upper_32_bits,
+				req->base.svga3d_flags);
+
+	if (!dev_priv->has_sm4_1) {
+		/*
+		 * If SM4_1 is not support then cannot send 64-bit flag to
+		 * device.
+		 */
+		if (req->svga3d_flags_upper_32_bits != 0)
+			return -EINVAL;
+
+		if (req->base.multisample_count != 0)
+			return -EINVAL;
+
+		if (req->multisample_pattern != SVGA3D_MS_PATTERN_NONE)
+			return -EINVAL;
+
+		if (req->quality_level != SVGA3D_MS_QUALITY_NONE)
+			return -EINVAL;
+	}
+
+	if (req->base.mip_levels > DRM_VMW_MAX_MIP_LEVELS)
+		return -EINVAL;
+
+	if (unlikely(vmw_user_surface_size == 0))
+		vmw_user_surface_size = ttm_round_pot(sizeof(*user_srf)) +
+			128;
+
+	size = vmw_user_surface_size + 128;
+
+	/* Define a surface based on the parameters. */
+	ret = vmw_surface_gb_priv_define(dev,
+					 size,
+					 svga3d_flags_64,
+					 req->base.format,
+					 req->base.drm_surface_flags &
+					 drm_vmw_surface_flag_scanout,
+					 req->base.mip_levels,
+					 req->base.multisample_count,
+					 req->base.array_size,
+					 req->base.base_size,
+					 req->multisample_pattern,
+					 req->quality_level,
+					 &srf);
+	if (unlikely(ret != 0))
+		return ret;
+
+	user_srf = container_of(srf, struct vmw_user_surface, srf);
+	if (drm_is_primary_client(file_priv))
+		user_srf->master = drm_master_get(file_priv->master);
+
+	ret = ttm_read_lock(&dev_priv->reservation_sem, true);
+	if (unlikely(ret != 0))
+		return ret;
+
+	res = &user_srf->srf.res;
+
+	if (req->base.buffer_handle != SVGA3D_INVALID_ID) {
+		ret = vmw_user_bo_lookup(tfile, req->base.buffer_handle,
+					 &res->backup,
+					 &user_srf->backup_base);
+		if (ret == 0) {
+			if (res->backup->base.num_pages * PAGE_SIZE <
+			    res->backup_size) {
+				DRM_ERROR("Surface backup buffer too small.\n");
+				vmw_bo_unreference(&res->backup);
+				ret = -EINVAL;
+				goto out_unlock;
+			} else {
+				backup_handle = req->base.buffer_handle;
+			}
+		}
+	} else if (req->base.drm_surface_flags &
+		   drm_vmw_surface_flag_create_buffer)
+		ret = vmw_user_bo_alloc(dev_priv, tfile,
+					res->backup_size,
+					req->base.drm_surface_flags &
+					drm_vmw_surface_flag_shareable,
+					&backup_handle,
+					&res->backup,
+					&user_srf->backup_base);
+
+	if (unlikely(ret != 0)) {
+		vmw_resource_unreference(&res);
+		goto out_unlock;
+	}
+
+	tmp = vmw_resource_reference(res);
+	ret = ttm_prime_object_init(tfile, res->backup_size, &user_srf->prime,
+				    req->base.drm_surface_flags &
+				    drm_vmw_surface_flag_shareable,
+				    VMW_RES_SURFACE,
+				    &vmw_user_surface_base_release, NULL);
+
+	if (unlikely(ret != 0)) {
+		vmw_resource_unreference(&tmp);
+		vmw_resource_unreference(&res);
+		goto out_unlock;
+	}
+
+	rep->handle      = user_srf->prime.base.hash.key;
+	rep->backup_size = res->backup_size;
+	if (res->backup) {
+		rep->buffer_map_handle =
+			drm_vma_node_offset_addr(&res->backup->base.vma_node);
+		rep->buffer_size = res->backup->base.num_pages * PAGE_SIZE;
+		rep->buffer_handle = backup_handle;
+	} else {
+		rep->buffer_map_handle = 0;
+		rep->buffer_size = 0;
+		rep->buffer_handle = SVGA3D_INVALID_ID;
+	}
+
+	vmw_resource_unreference(&res);
+
+out_unlock:
+	ttm_read_unlock(&dev_priv->reservation_sem);
+	return ret;
+}
+
+/**
+ * vmw_gb_surface_reference_internal - Ioctl function implementing
+ * the user surface reference functionality.
+ *
+ * @dev: Pointer to a struct drm_device.
+ * @req: Pointer to user-space request surface arg.
+ * @rep: Pointer to response to user-space.
+ * @file_priv: Pointer to a drm file private structure.
+ */
+static int
+vmw_gb_surface_reference_internal(struct drm_device *dev,
+				  struct drm_vmw_surface_arg *req,
+				  struct drm_vmw_gb_surface_ref_ext_rep *rep,
+				  struct drm_file *file_priv)
+{
+	struct vmw_private *dev_priv = vmw_priv(dev);
+	struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+	struct vmw_surface *srf;
+	struct vmw_user_surface *user_srf;
+	struct ttm_base_object *base;
+	uint32_t backup_handle;
+	int ret = -EINVAL;
+
+	ret = vmw_surface_handle_reference(dev_priv, file_priv, req->sid,
+					   req->handle_type, &base);
+	if (unlikely(ret != 0))
+		return ret;
+
+	user_srf = container_of(base, struct vmw_user_surface, prime.base);
+	srf = &user_srf->srf;
+	if (!srf->res.backup) {
+		DRM_ERROR("Shared GB surface is missing a backup buffer.\n");
+		goto out_bad_resource;
+	}
+
+	mutex_lock(&dev_priv->cmdbuf_mutex); /* Protect res->backup */
+	ret = vmw_user_bo_reference(tfile, srf->res.backup, &backup_handle);
+	mutex_unlock(&dev_priv->cmdbuf_mutex);
+
+	if (unlikely(ret != 0)) {
+		DRM_ERROR("Could not add a reference to a GB surface "
+			  "backup buffer.\n");
+		(void) ttm_ref_object_base_unref(tfile, base->hash.key,
+						 TTM_REF_USAGE);
+		goto out_bad_resource;
+	}
+
+	rep->creq.base.svga3d_flags = SVGA3D_FLAGS_LOWER_32(srf->flags);
+	rep->creq.base.format = srf->format;
+	rep->creq.base.mip_levels = srf->mip_levels[0];
+	rep->creq.base.drm_surface_flags = 0;
+	rep->creq.base.multisample_count = srf->multisample_count;
+	rep->creq.base.autogen_filter = srf->autogen_filter;
+	rep->creq.base.array_size = srf->array_size;
+	rep->creq.base.buffer_handle = backup_handle;
+	rep->creq.base.base_size = srf->base_size;
+	rep->crep.handle = user_srf->prime.base.hash.key;
+	rep->crep.backup_size = srf->res.backup_size;
+	rep->crep.buffer_handle = backup_handle;
+	rep->crep.buffer_map_handle =
+		drm_vma_node_offset_addr(&srf->res.backup->base.vma_node);
+	rep->crep.buffer_size = srf->res.backup->base.num_pages * PAGE_SIZE;
+
+	rep->creq.version = drm_vmw_gb_surface_v1;
+	rep->creq.svga3d_flags_upper_32_bits =
+		SVGA3D_FLAGS_UPPER_32(srf->flags);
+	rep->creq.multisample_pattern = srf->multisample_pattern;
+	rep->creq.quality_level = srf->quality_level;
+	rep->creq.must_be_zero = 0;
+
+out_bad_resource:
+	ttm_base_object_unref(&base);
+
+	return ret;
+}
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 84e81b38ca18..68ff37d4c035 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -69,6 +69,8 @@ extern "C" {
 #define DRM_VMW_GB_SURFACE_REF       24
 #define DRM_VMW_SYNCCPU              25
 #define DRM_VMW_CREATE_EXTENDED_CONTEXT 26
+#define DRM_VMW_GB_SURFACE_CREATE_EXT   27
+#define DRM_VMW_GB_SURFACE_REF_EXT      28
 
 /*************************************************************************/
 /**
@@ -1105,6 +1107,106 @@ struct drm_vmw_handle_close_arg {
 };
 #define drm_vmw_unref_dmabuf_arg drm_vmw_handle_close_arg
 
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_CREATE_EXT - Create a host guest-backed surface.
+ *
+ * Allocates a surface handle and queues a create surface command
+ * for the host on the first use of the surface. The surface ID can
+ * be used as the surface ID in commands referencing the surface.
+ *
+ * This new command extends DRM_VMW_GB_SURFACE_CREATE by adding version
+ * parameter and 64 bit svga flag.
+ */
+
+/**
+ * enum drm_vmw_surface_version
+ *
+ * @drm_vmw_surface_gb_v1: Corresponds to current gb surface format with
+ * svga3d surface flags split into 2, upper half and lower half.
+ */
+enum drm_vmw_surface_version {
+	drm_vmw_gb_surface_v1
+};
+
+/**
+ * struct drm_vmw_gb_surface_create_ext_req
+ *
+ * @base: Surface create parameters.
+ * @version: Version of surface create ioctl.
+ * @svga3d_flags_upper_32_bits: Upper 32 bits of svga3d flags.
+ * @multisample_pattern: Multisampling pattern when msaa is supported.
+ * @quality_level: Precision settings for each sample.
+ * @must_be_zero: Reserved for future usage.
+ *
+ * Input argument to the  DRM_VMW_GB_SURFACE_CREATE_EXT Ioctl.
+ * Part of output argument for the DRM_VMW_GB_SURFACE_REF_EXT Ioctl.
+ */
+struct drm_vmw_gb_surface_create_ext_req {
+	struct drm_vmw_gb_surface_create_req base;
+	enum drm_vmw_surface_version version;
+	uint32_t svga3d_flags_upper_32_bits;
+	SVGA3dMSPattern multisample_pattern;
+	SVGA3dMSQualityLevel quality_level;
+	uint64_t must_be_zero;
+};
+
+/**
+ * union drm_vmw_gb_surface_create_ext_arg
+ *
+ * @req: Input argument as described above.
+ * @rep: Output argument as described above.
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
+union drm_vmw_gb_surface_create_ext_arg {
+	struct drm_vmw_gb_surface_create_rep rep;
+	struct drm_vmw_gb_surface_create_ext_req req;
+};
+
+/*************************************************************************/
+/**
+ * DRM_VMW_GB_SURFACE_REF_EXT - Reference a host surface.
+ *
+ * Puts a reference on a host surface with a given handle, as previously
+ * returned by the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ * A reference will make sure the surface isn't destroyed while we hold
+ * it and will allow the calling client to use the surface handle in
+ * the command stream.
+ *
+ * On successful return, the Ioctl returns the surface information given
+ * to and returned from the DRM_VMW_GB_SURFACE_CREATE_EXT ioctl.
+ */
+
+/**
+ * struct drm_vmw_gb_surface_ref_ext_rep
+ *
+ * @creq: The data used as input when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_ext_req"
+ * @crep: Additional data output when the surface was created, as described
+ *        above at "struct drm_vmw_gb_surface_create_rep"
+ *
+ * Output Argument to the DRM_VMW_GB_SURFACE_REF_EXT ioctl.
+ */
+struct drm_vmw_gb_surface_ref_ext_rep {
+	struct drm_vmw_gb_surface_create_ext_req creq;
+	struct drm_vmw_gb_surface_create_rep crep;
+};
+
+/**
+ * union drm_vmw_gb_surface_reference_ext_arg
+ *
+ * @req: Input data as described above at "struct drm_vmw_surface_arg"
+ * @rep: Output data as described above at
+ *       "struct drm_vmw_gb_surface_ref_ext_rep"
+ *
+ * Argument to the DRM_VMW_GB_SURFACE_REF Ioctl.
+ */
+union drm_vmw_gb_surface_reference_ext_arg {
+	struct drm_vmw_gb_surface_ref_ext_rep rep;
+	struct drm_vmw_surface_arg req;
+};
+
 #if defined(__cplusplus)
 }
 #endif
-- 
cgit v1.2.3


From f9261b30d92f3835891648041ce8699b1fb9a694 Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 15:24:05 -0700
Subject: drm/vmwgfx: Add support for multisampling

Support for SVGA3D_SURFACE_MULTISAMPLE and surface mob size according
to sample count.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 .../drm/vmwgfx/device_include/svga3d_surfacedefs.h   | 20 ++++++++++++++++++++
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h                  |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_surface.c              | 17 +++++++++++++----
 3 files changed, 34 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
index 6422e3899cdf..809a4ec68e89 100644
--- a/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
+++ b/drivers/gpu/drm/vmwgfx/device_include/svga3d_surfacedefs.h
@@ -1235,6 +1235,26 @@ svga3dsurface_get_serialized_size(SVGA3dSurfaceFormat format,
 	return total_size * num_layers;
 }
 
+/**
+ * svga3dsurface_get_serialized_size_extended - Returns the number of bytes
+ * required for a surface with given parameters. Support for sample count.
+ */
+static inline u32
+svga3dsurface_get_serialized_size_extended(SVGA3dSurfaceFormat format,
+					   surf_size_struct base_level_size,
+					   u32 num_mip_levels,
+					   u32 num_layers,
+					   u32 num_samples)
+{
+	uint64_t total_size =
+		svga3dsurface_get_serialized_size(format,
+						  base_level_size,
+						  num_mip_levels,
+						  num_layers);
+	total_size *= max_t(u32, 1, num_samples);
+
+	return min_t(uint64_t, total_size, (uint64_t)U32_MAX);
+}
 
 /**
  * svga3dsurface_get_pixel_offset - Compute the offset (in bytes) to a pixel
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index 59af14714797..a67b54e4fd50 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -83,7 +83,7 @@
 struct vmw_fpriv {
 	struct drm_master *locked_master;
 	struct ttm_object_file *tfile;
-	bool gb_aware;
+	bool gb_aware; /* user-space is guest-backed aware */
 };
 
 struct vmw_buffer_object {
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
index 1d4c010a0e48..7636bf2db17e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -1399,6 +1399,7 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	struct vmw_surface *srf;
 	int ret;
 	u32 num_layers = 1;
+	u32 sample_count = 1;
 
 	*srf_out = NULL;
 
@@ -1481,11 +1482,15 @@ int vmw_surface_gb_priv_define(struct drm_device *dev,
 	else if (svga3d_flags & SVGA3D_SURFACE_CUBEMAP)
 		num_layers = SVGA3D_MAX_SURFACE_FACES;
 
+	if (srf->flags & SVGA3D_SURFACE_MULTISAMPLE)
+		sample_count = srf->multisample_count;
+
 	srf->res.backup_size   =
-		svga3dsurface_get_serialized_size(srf->format,
-						  srf->base_size,
-						  srf->mip_levels[0],
-						  num_layers);
+		svga3dsurface_get_serialized_size_extended(srf->format,
+							   srf->base_size,
+							   srf->mip_levels[0],
+							   num_layers,
+							   sample_count);
 
 	if (srf->flags & SVGA3D_SURFACE_BIND_STREAM_OUTPUT)
 		srf->res.backup_size += sizeof(SVGA3dDXSOState);
@@ -1595,6 +1600,10 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
 			return -EINVAL;
 	}
 
+	if ((svga3d_flags_64 & SVGA3D_SURFACE_MULTISAMPLE) &&
+	    req->base.multisample_count == 0)
+		return -EINVAL;
+
 	if (req->base.mip_levels > DRM_VMW_MAX_MIP_LEVELS)
 		return -EINVAL;
 
-- 
cgit v1.2.3


From 9b07b287aa3ef49695bfad59c1870cd942f579a8 Mon Sep 17 00:00:00 2001
From: Deepak Rawat <drawat@vmware.com>
Date: Wed, 20 Jun 2018 15:09:43 -0700
Subject: drm/vmwgfx: Expose SM4_1 param to user space

A new param DRM_VMW_PARAM_SM4_1, is added for user space to determine
availability of SM4.1.

Minor version bump for SM4.1.

Signed-off-by: Deepak Rawat <drawat@vmware.com>
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Thomas Hellstrom <thellstrom@vmware.com>
Signed-off-by: Thomas Hellstrom <thellstrom@vmware.com>
---
 drivers/gpu/drm/vmwgfx/vmwgfx_drv.h   | 6 +++---
 drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c | 3 +++
 include/uapi/drm/vmwgfx_drm.h         | 4 ++++
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
index a67b54e4fd50..f1b803d34c59 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -43,10 +43,10 @@
 #include <linux/sync_file.h>
 
 #define VMWGFX_DRIVER_NAME "vmwgfx"
-#define VMWGFX_DRIVER_DATE "20180322"
+#define VMWGFX_DRIVER_DATE "20180704"
 #define VMWGFX_DRIVER_MAJOR 2
-#define VMWGFX_DRIVER_MINOR 14
-#define VMWGFX_DRIVER_PATCHLEVEL 1
+#define VMWGFX_DRIVER_MINOR 15
+#define VMWGFX_DRIVER_PATCHLEVEL 0
 #define VMWGFX_FILE_PAGE_OFFSET 0x00100000
 #define VMWGFX_FIFO_STATIC_SIZE (1024*1024)
 #define VMWGFX_MAX_RELOCATIONS 2048
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
index ac6da0da2824..e825192ca30e 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ioctl.c
@@ -116,6 +116,9 @@ int vmw_getparam_ioctl(struct drm_device *dev, void *data,
 	case DRM_VMW_PARAM_DX:
 		param->value = dev_priv->has_dx;
 		break;
+	case DRM_VMW_PARAM_SM4_1:
+		param->value = dev_priv->has_sm4_1;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/include/uapi/drm/vmwgfx_drm.h b/include/uapi/drm/vmwgfx_drm.h
index 68ff37d4c035..399f58317cff 100644
--- a/include/uapi/drm/vmwgfx_drm.h
+++ b/include/uapi/drm/vmwgfx_drm.h
@@ -82,6 +82,9 @@ extern "C" {
  *
  * DRM_VMW_PARAM_OVERLAY_IOCTL:
  * Does the driver support the overlay ioctl.
+ *
+ * DRM_VMW_PARAM_SM4_1
+ * SM4_1 support is enabled.
  */
 
 #define DRM_VMW_PARAM_NUM_STREAMS      0
@@ -98,6 +101,7 @@ extern "C" {
 #define DRM_VMW_PARAM_SCREEN_TARGET    11
 #define DRM_VMW_PARAM_DX               12
 #define DRM_VMW_PARAM_HW_CAPS2         13
+#define DRM_VMW_PARAM_SM4_1            14
 
 /**
  * enum drm_vmw_handle_type - handle type for ref ioctls
-- 
cgit v1.2.3


From 18df02fb79cb20ba4de1e02e1df41ba83f8b9bec Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Sun, 17 Jun 2018 14:05:34 +0200
Subject: dts: clk: add devicetree bindings for MAX9485

This patch adds the devicetree bindings for MAX9485, a programmable audio
clock generator.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/maxim,max9485.txt    | 59 ++++++++++++++++++++++
 include/dt-bindings/clock/maxim,max9485.h          | 18 +++++++
 2 files changed, 77 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/maxim,max9485.txt
 create mode 100644 include/dt-bindings/clock/maxim,max9485.h

diff --git a/Documentation/devicetree/bindings/clock/maxim,max9485.txt b/Documentation/devicetree/bindings/clock/maxim,max9485.txt
new file mode 100644
index 000000000000..61bec1100a94
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/maxim,max9485.txt
@@ -0,0 +1,59 @@
+Devicetree bindings for Maxim MAX9485 Programmable Audio Clock Generator
+
+This device exposes 4 clocks in total:
+
+- MAX9485_MCLKOUT: 	A gated, buffered output of the input clock of 27 MHz
+- MAX9485_CLKOUT:	A PLL that can be configured to 16 different discrete
+			frequencies
+- MAX9485_CLKOUT[1,2]:	Two gated outputs for MAX9485_CLKOUT
+
+MAX9485_CLKOUT[1,2] are children of MAX9485_CLKOUT which upchain all rate set
+requests.
+
+Required properties:
+- compatible:	"maxim,max9485"
+- clocks:	Input clock, must provice 27.000 MHz
+- clock-names:	Must be set to "xclk"
+- #clock-cells: From common clock binding; shall be set to 1
+
+Optional properties:
+- reset-gpios:		GPIO descriptor connected to the #RESET input pin
+- vdd-supply:		A regulator node for Vdd
+- clock-output-names:	Name of output clocks, as defined in common clock
+			bindings
+
+If not explicitly set, the output names are "mclkout", "clkout", "clkout1"
+and "clkout2".
+
+Clocks are defined as preprocessor macros in the dt-binding header.
+
+Example:
+
+	#include <dt-bindings/clock/maxim,max9485.h>
+
+	xo-27mhz: xo-27mhz {
+		compatible = "fixed-clock";
+		#clock-cells = <0>;
+		clock-frequency = <27000000>;
+	};
+
+	&i2c0 {
+		max9485: audio-clock@63 {
+			reg = <0x63>;
+			compatible = "maxim,max9485";
+			clock-names = "xclk";
+			clocks = <&xo-27mhz>;
+			reset-gpios = <&gpio 1 GPIO_ACTIVE_HIGH>;
+			vdd-supply = <&3v3-reg>;
+			#clock-cells = <1>;
+		};
+	};
+
+	// Clock consumer node
+
+	foo@0 {
+		compatible = "bar,foo";
+		/* ... */
+		clock-names = "foo-input-clk";
+		clocks = <&max9485 MAX9485_CLKOUT1>;
+	};
diff --git a/include/dt-bindings/clock/maxim,max9485.h b/include/dt-bindings/clock/maxim,max9485.h
new file mode 100644
index 000000000000..185b09ce1869
--- /dev/null
+++ b/include/dt-bindings/clock/maxim,max9485.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright (C) 2018 Daniel Mack
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ */
+
+#ifndef __DT_BINDINGS_MAX9485_CLK_H
+#define __DT_BINDINGS_MAX9485_CLK_H
+
+#define MAX9485_MCLKOUT	0
+#define MAX9485_CLKOUT	1
+#define MAX9485_CLKOUT1	2
+#define MAX9485_CLKOUT2	3
+
+#endif /* __DT_BINDINGS_MAX9485_CLK_H */
-- 
cgit v1.2.3


From 574f4e80d59e5c669c0729718525df8bac5e4d78 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Wed, 27 Jun 2018 14:14:58 +0200
Subject: clk: ingenic: Fix incorrect data for the i2s clock

The register field for configuring the divider for the i2s clock
occupies the bits [8-0], which means 9 bits and not 8.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/ingenic/jz4740-cgu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/ingenic/jz4740-cgu.c b/drivers/clk/ingenic/jz4740-cgu.c
index 32fcc75f6f77..bc073dd4470d 100644
--- a/drivers/clk/ingenic/jz4740-cgu.c
+++ b/drivers/clk/ingenic/jz4740-cgu.c
@@ -134,7 +134,7 @@ static const struct ingenic_cgu_clk_info jz4740_cgu_clocks[] = {
 		"i2s", CGU_CLK_MUX | CGU_CLK_DIV | CGU_CLK_GATE,
 		.parents = { JZ4740_CLK_EXT, JZ4740_CLK_PLL_HALF, -1, -1 },
 		.mux = { CGU_REG_CPCCR, 31, 1 },
-		.div = { CGU_REG_I2SCDR, 0, 1, 8, -1, -1, -1 },
+		.div = { CGU_REG_I2SCDR, 0, 1, 9, -1, -1, -1 },
 		.gate = { CGU_REG_CLKGR, 6 },
 	},
 
-- 
cgit v1.2.3


From 2b555a4b9caecfcab1b2aade176df795ceceaefa Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Wed, 27 Jun 2018 14:14:59 +0200
Subject: clk: ingenic: Add missing flag for UDC clock

The UDC clock of the JZ4740 SoC can be gated, but the data structure
representing it was missing the CGU_CLK_GATE flag to make it work.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/ingenic/jz4740-cgu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/ingenic/jz4740-cgu.c b/drivers/clk/ingenic/jz4740-cgu.c
index bc073dd4470d..4479c102e899 100644
--- a/drivers/clk/ingenic/jz4740-cgu.c
+++ b/drivers/clk/ingenic/jz4740-cgu.c
@@ -161,7 +161,7 @@ static const struct ingenic_cgu_clk_info jz4740_cgu_clocks[] = {
 	},
 
 	[JZ4740_CLK_UDC] = {
-		"udc", CGU_CLK_MUX | CGU_CLK_DIV,
+		"udc", CGU_CLK_MUX | CGU_CLK_DIV | CGU_CLK_GATE,
 		.parents = { JZ4740_CLK_EXT, JZ4740_CLK_PLL_HALF, -1, -1 },
 		.mux = { CGU_REG_CPCCR, 29, 1 },
 		.div = { CGU_REG_CPCCR, 23, 1, 6, -1, -1, -1 },
-- 
cgit v1.2.3


From 3a32497f0dbe170794e1506deb41dc44c4fea8d9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 18:49:26 +0100
Subject: drm/i915/selftests: Provide full mb() around clflush

clflush is an unserialised instruction and the IA manual strongly advises
you to serialise it with a mb. To be cautious, apply one before and one
after, so that it is serialised with both writes and reads without
worrying too much about the required direction.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706174926.4712-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_coherency.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
index 1de7c1402fd5..3a095c37c120 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_coherency.c
@@ -42,11 +42,21 @@ static int cpu_set(struct drm_i915_gem_object *obj,
 
 	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
-	if (needs_clflush & CLFLUSH_BEFORE)
+
+	if (needs_clflush & CLFLUSH_BEFORE) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	map[offset_in_page(offset) / sizeof(*map)] = v;
-	if (needs_clflush & CLFLUSH_AFTER)
+
+	if (needs_clflush & CLFLUSH_AFTER) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	kunmap_atomic(map);
 
 	i915_gem_obj_finish_shmem_access(obj);
@@ -68,8 +78,13 @@ static int cpu_get(struct drm_i915_gem_object *obj,
 
 	page = i915_gem_object_get_page(obj, offset >> PAGE_SHIFT);
 	map = kmap_atomic(page);
-	if (needs_clflush & CLFLUSH_BEFORE)
+
+	if (needs_clflush & CLFLUSH_BEFORE) {
+		mb();
 		clflush(map+offset_in_page(offset) / sizeof(*map));
+		mb();
+	}
+
 	*v = map[offset_in_page(offset) / sizeof(*map)];
 	kunmap_atomic(map);
 
-- 
cgit v1.2.3


From 3baef810462746cd5a085c1e1416829d2af2622d Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Fri, 6 Jul 2018 17:05:27 +0530
Subject: Bluetooth: Introduce helpers for LE set scan start and complete

Introduce a helper hci_req_start_scan() which starts an LE
scan and call it from passive_Scan() and active_scan().
There is not functionality change in this patch.

This is basically done to enable extended scanning if the
controller supports which will be done in the subsequent
patch

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/hci_event.c   | 37 ++++++++++++++++-------------
 net/bluetooth/hci_request.c | 58 +++++++++++++++++++--------------------------
 2 files changed, 46 insertions(+), 49 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 562e7a854ed6..9ec07cd4ab13 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1127,24 +1127,11 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr,
 	d->last_adv_data_len = len;
 }
 
-static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
-				      struct sk_buff *skb)
+static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable)
 {
-	struct hci_cp_le_set_scan_enable *cp;
-	__u8 status = *((__u8 *) skb->data);
-
-	BT_DBG("%s status 0x%2.2x", hdev->name, status);
-
-	if (status)
-		return;
-
-	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE);
-	if (!cp)
-		return;
-
 	hci_dev_lock(hdev);
 
-	switch (cp->enable) {
+	switch (enable) {
 	case LE_SCAN_ENABLE:
 		hci_dev_set_flag(hdev, HCI_LE_SCAN);
 		if (hdev->le_scan_type == LE_SCAN_ACTIVE)
@@ -1190,13 +1177,31 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 
 	default:
 		bt_dev_err(hdev, "use of reserved LE_Scan_Enable param %d",
-			   cp->enable);
+			   enable);
 		break;
 	}
 
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
+				      struct sk_buff *skb)
+{
+	struct hci_cp_le_set_scan_enable *cp;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_SCAN_ENABLE);
+	if (!cp)
+		return;
+
+	le_set_scan_enable_complete(hdev, cp->enable);
+}
+
 static void hci_cc_le_read_white_list_size(struct hci_dev *hdev,
 					   struct sk_buff *skb)
 {
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index e44d34734834..76dcc3f14cea 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -767,10 +767,30 @@ static bool scan_use_rpa(struct hci_dev *hdev)
 	return hci_dev_test_flag(hdev, HCI_PRIVACY);
 }
 
-void hci_req_add_le_passive_scan(struct hci_request *req)
+static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval,
+			       u16 window, u8 own_addr_type, u8 filter_policy)
 {
 	struct hci_cp_le_set_scan_param param_cp;
 	struct hci_cp_le_set_scan_enable enable_cp;
+
+	memset(&param_cp, 0, sizeof(param_cp));
+	param_cp.type = type;
+	param_cp.interval = cpu_to_le16(interval);
+	param_cp.window = cpu_to_le16(window);
+	param_cp.own_address_type = own_addr_type;
+	param_cp.filter_policy = filter_policy;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
+		    &param_cp);
+
+	memset(&enable_cp, 0, sizeof(enable_cp));
+	enable_cp.enable = LE_SCAN_ENABLE;
+	enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
+		    &enable_cp);
+}
+
+void hci_req_add_le_passive_scan(struct hci_request *req)
+{
 	struct hci_dev *hdev = req->hdev;
 	u8 own_addr_type;
 	u8 filter_policy;
@@ -804,20 +824,8 @@ void hci_req_add_le_passive_scan(struct hci_request *req)
 	    (hdev->le_features[0] & HCI_LE_EXT_SCAN_POLICY))
 		filter_policy |= 0x02;
 
-	memset(&param_cp, 0, sizeof(param_cp));
-	param_cp.type = LE_SCAN_PASSIVE;
-	param_cp.interval = cpu_to_le16(hdev->le_scan_interval);
-	param_cp.window = cpu_to_le16(hdev->le_scan_window);
-	param_cp.own_address_type = own_addr_type;
-	param_cp.filter_policy = filter_policy;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
-		    &param_cp);
-
-	memset(&enable_cp, 0, sizeof(enable_cp));
-	enable_cp.enable = LE_SCAN_ENABLE;
-	enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
-		    &enable_cp);
+	hci_req_start_scan(req, LE_SCAN_PASSIVE, hdev->le_scan_interval,
+			   hdev->le_scan_window, own_addr_type, filter_policy);
 }
 
 static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev)
@@ -2010,8 +2018,6 @@ static int active_scan(struct hci_request *req, unsigned long opt)
 {
 	uint16_t interval = opt;
 	struct hci_dev *hdev = req->hdev;
-	struct hci_cp_le_set_scan_param param_cp;
-	struct hci_cp_le_set_scan_enable enable_cp;
 	u8 own_addr_type;
 	int err;
 
@@ -2050,22 +2056,8 @@ static int active_scan(struct hci_request *req, unsigned long opt)
 	if (err < 0)
 		own_addr_type = ADDR_LE_DEV_PUBLIC;
 
-	memset(&param_cp, 0, sizeof(param_cp));
-	param_cp.type = LE_SCAN_ACTIVE;
-	param_cp.interval = cpu_to_le16(interval);
-	param_cp.window = cpu_to_le16(DISCOV_LE_SCAN_WIN);
-	param_cp.own_address_type = own_addr_type;
-
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
-		    &param_cp);
-
-	memset(&enable_cp, 0, sizeof(enable_cp));
-	enable_cp.enable = LE_SCAN_ENABLE;
-	enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
-
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
-		    &enable_cp);
-
+	hci_req_start_scan(req, LE_SCAN_ACTIVE, interval, DISCOV_LE_SCAN_WIN,
+			   own_addr_type, 0);
 	return 0;
 }
 
-- 
cgit v1.2.3


From a2344b9e3a8c5c2064306b0d99b0e9a6c4813c08 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Fri, 6 Jul 2018 17:05:28 +0530
Subject: Bluetooth: Use extended scanning if controller supports

This implements Set extended scan param and set extended scan enable
commands and use it for start LE scan based on controller support.

The new features added in these commands are setting of new PHY for
scanning and setting of scan duration. Both features are disabled
for now, meaning only 1M PHY is set and scan duration is set to 0
which means that scanning will be done untill scan disable is called.

< HCI Command: LE Set Extended Scan Parameters (0x08|0x0041) plen 8
        Own address type: Random (0x01)
        Filter policy: Accept all advertisement (0x00)
        PHYs: 0x01
        Entry 0: LE 1M
          Type: Active (0x01)
          Interval: 11.250 msec (0x0012)
          Window: 11.250 msec (0x0012)
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Scan Parameters (0x08|0x0041) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Extended Scan Enable (0x08|0x0042) plen 6
        Extended scan: Enabled (0x01)
        Filter duplicates: Enabled (0x01)
        Duration: 0 msec (0x0000)
        Period: 0.00 sec (0x0000)
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Scan Enable (0x08|0x0042) ncmd 2
        Status: Success (0x00)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      |  24 +++++++++
 include/net/bluetooth/hci_core.h |   4 ++
 net/bluetooth/hci_event.c        |  51 ++++++++++++++++++
 net/bluetooth/hci_request.c      | 110 ++++++++++++++++++++++++++++++---------
 4 files changed, 164 insertions(+), 25 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4af1a3a4d9b1..8c2868f439e7 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1514,6 +1514,30 @@ struct hci_cp_le_set_default_phy {
 	__u8    rx_phys;
 } __packed;
 
+#define HCI_OP_LE_SET_EXT_SCAN_PARAMS   0x2041
+struct hci_cp_le_set_ext_scan_params {
+	__u8    own_addr_type;
+	__u8    filter_policy;
+	__u8    scanning_phys;
+	__u8    data[0];
+} __packed;
+
+#define LE_SCAN_PHY_1M 0x01
+
+struct hci_cp_le_scan_phy_params {
+	__u8    type;
+	__le16  interval;
+	__le16  window;
+} __packed;
+
+#define HCI_OP_LE_SET_EXT_SCAN_ENABLE   0x2042
+struct hci_cp_le_set_ext_scan_enable {
+	__u8    enable;
+	__u8    filter_dup;
+	__le16  duration;
+	__le16  period;
+} __packed;
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 409f49bd8338..cc0bde74dd45 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1158,6 +1158,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define bredr_sc_enabled(dev)  (lmp_sc_capable(dev) && \
 				hci_dev_test_flag(dev, HCI_SC_ENABLED))
 
+/* Use ext scanning if set ext scan param and ext scan enable is supported */
+#define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \
+			   ((dev)->commands[37] & 0x40))
+
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 9ec07cd4ab13..15afad005d72 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1098,6 +1098,31 @@ static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_set_ext_scan_param(struct hci_dev *hdev,
+					 struct sk_buff *skb)
+{
+	struct hci_cp_le_set_ext_scan_params *cp;
+	__u8 status = *((__u8 *) skb->data);
+	struct hci_cp_le_scan_phy_params *phy_param;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_PARAMS);
+	if (!cp)
+		return;
+
+	phy_param = (void *)cp->data;
+
+	hci_dev_lock(hdev);
+
+	hdev->le_scan_type = phy_param->type;
+
+	hci_dev_unlock(hdev);
+}
+
 static bool has_pending_adv_report(struct hci_dev *hdev)
 {
 	struct discovery_state *d = &hdev->discovery;
@@ -1202,6 +1227,24 @@ static void hci_cc_le_set_scan_enable(struct hci_dev *hdev,
 	le_set_scan_enable_complete(hdev, cp->enable);
 }
 
+static void hci_cc_le_set_ext_scan_enable(struct hci_dev *hdev,
+				      struct sk_buff *skb)
+{
+	struct hci_cp_le_set_ext_scan_enable *cp;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_SCAN_ENABLE);
+	if (!cp)
+		return;
+
+	le_set_scan_enable_complete(hdev, cp->enable);
+}
+
 static void hci_cc_le_read_white_list_size(struct hci_dev *hdev,
 					   struct sk_buff *skb)
 {
@@ -3079,6 +3122,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_write_ssp_debug_mode(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_EXT_SCAN_PARAMS:
+		hci_cc_le_set_ext_scan_param(hdev, skb);
+		break;
+
+	case HCI_OP_LE_SET_EXT_SCAN_ENABLE:
+		hci_cc_le_set_ext_scan_enable(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 76dcc3f14cea..faf7c711234c 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -647,11 +647,22 @@ void __hci_req_update_eir(struct hci_request *req)
 
 void hci_req_add_le_scan_disable(struct hci_request *req)
 {
-	struct hci_cp_le_set_scan_enable cp;
+	struct hci_dev *hdev = req->hdev;
 
-	memset(&cp, 0, sizeof(cp));
-	cp.enable = LE_SCAN_DISABLE;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+	if (use_ext_scan(hdev)) {
+		struct hci_cp_le_set_ext_scan_enable cp;
+
+		memset(&cp, 0, sizeof(cp));
+		cp.enable = LE_SCAN_DISABLE;
+		hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE, sizeof(cp),
+			    &cp);
+	} else {
+		struct hci_cp_le_set_scan_enable cp;
+
+		memset(&cp, 0, sizeof(cp));
+		cp.enable = LE_SCAN_DISABLE;
+		hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+	}
 }
 
 static void add_to_white_list(struct hci_request *req,
@@ -770,23 +781,60 @@ static bool scan_use_rpa(struct hci_dev *hdev)
 static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval,
 			       u16 window, u8 own_addr_type, u8 filter_policy)
 {
-	struct hci_cp_le_set_scan_param param_cp;
-	struct hci_cp_le_set_scan_enable enable_cp;
-
-	memset(&param_cp, 0, sizeof(param_cp));
-	param_cp.type = type;
-	param_cp.interval = cpu_to_le16(interval);
-	param_cp.window = cpu_to_le16(window);
-	param_cp.own_address_type = own_addr_type;
-	param_cp.filter_policy = filter_policy;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
-		    &param_cp);
+	struct hci_dev *hdev = req->hdev;
 
-	memset(&enable_cp, 0, sizeof(enable_cp));
-	enable_cp.enable = LE_SCAN_ENABLE;
-	enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
-		    &enable_cp);
+	/* Use ext scanning if set ext scan param and ext scan enable is
+	 * supported
+	 */
+	if (use_ext_scan(hdev)) {
+		struct hci_cp_le_set_ext_scan_params *ext_param_cp;
+		struct hci_cp_le_set_ext_scan_enable ext_enable_cp;
+		struct hci_cp_le_scan_phy_params *phy_params;
+		/* Ony single PHY (1M) is supported as of now */
+		u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 1];
+
+		ext_param_cp = (void *)data;
+		phy_params = (void *)ext_param_cp->data;
+
+		memset(ext_param_cp, 0, sizeof(*ext_param_cp));
+		ext_param_cp->own_addr_type = own_addr_type;
+		ext_param_cp->filter_policy = filter_policy;
+		ext_param_cp->scanning_phys = LE_SCAN_PHY_1M;
+
+		memset(phy_params, 0, sizeof(*phy_params));
+		phy_params->type = type;
+		phy_params->interval = cpu_to_le16(interval);
+		phy_params->window = cpu_to_le16(window);
+
+		hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_PARAMS,
+			    sizeof(*ext_param_cp) + sizeof(*phy_params),
+			    ext_param_cp);
+
+		memset(&ext_enable_cp, 0, sizeof(ext_enable_cp));
+		ext_enable_cp.enable = LE_SCAN_ENABLE;
+		ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+
+		hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE,
+			    sizeof(ext_enable_cp), &ext_enable_cp);
+	} else {
+		struct hci_cp_le_set_scan_param param_cp;
+		struct hci_cp_le_set_scan_enable enable_cp;
+
+		memset(&param_cp, 0, sizeof(param_cp));
+		param_cp.type = type;
+		param_cp.interval = cpu_to_le16(interval);
+		param_cp.window = cpu_to_le16(window);
+		param_cp.own_address_type = own_addr_type;
+		param_cp.filter_policy = filter_policy;
+		hci_req_add(req, HCI_OP_LE_SET_SCAN_PARAM, sizeof(param_cp),
+			    &param_cp);
+
+		memset(&enable_cp, 0, sizeof(enable_cp));
+		enable_cp.enable = LE_SCAN_ENABLE;
+		enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+		hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(enable_cp),
+			    &enable_cp);
+	}
 }
 
 void hci_req_add_le_passive_scan(struct hci_request *req)
@@ -1948,7 +1996,6 @@ discov_stopped:
 static int le_scan_restart(struct hci_request *req, unsigned long opt)
 {
 	struct hci_dev *hdev = req->hdev;
-	struct hci_cp_le_set_scan_enable cp;
 
 	/* If controller is not scanning we are done. */
 	if (!hci_dev_test_flag(hdev, HCI_LE_SCAN))
@@ -1956,10 +2003,23 @@ static int le_scan_restart(struct hci_request *req, unsigned long opt)
 
 	hci_req_add_le_scan_disable(req);
 
-	memset(&cp, 0, sizeof(cp));
-	cp.enable = LE_SCAN_ENABLE;
-	cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+	if (use_ext_scan(hdev)) {
+		struct hci_cp_le_set_ext_scan_enable ext_enable_cp;
+
+		memset(&ext_enable_cp, 0, sizeof(ext_enable_cp));
+		ext_enable_cp.enable = LE_SCAN_ENABLE;
+		ext_enable_cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+
+		hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_ENABLE,
+			    sizeof(ext_enable_cp), &ext_enable_cp);
+	} else {
+		struct hci_cp_le_set_scan_enable cp;
+
+		memset(&cp, 0, sizeof(cp));
+		cp.enable = LE_SCAN_ENABLE;
+		cp.filter_dup = LE_SCAN_FILTER_DUP_ENABLE;
+		hci_req_add(req, HCI_OP_LE_SET_SCAN_ENABLE, sizeof(cp), &cp);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From c215e9397b00b3045a668120ed7dbd89f2866e74 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Fri, 6 Jul 2018 17:05:29 +0530
Subject: Bluetooth: Process extended ADV report event

This patch enables Extended ADV report event if extended scanning
is supported in the controller and process the same.

The new features are not handled and for now its as good as
legacy ADV report.

> HCI Event: LE Meta Event (0x3e) plen 53
      LE Extended Advertising Report (0x0d)
        Num reports: 1
        Entry 0
          Event type: 0x0013
            Props: 0x0013
              Connectable
              Scannable
              Use legacy advertising PDUs
            Data status: Complete
          Legacy PDU Type: ADV_IND (0x0013)
          Address type: Random (0x01)
          Address: DB:7E:2E:1A:85:E8 (Static)
          Primary PHY: LE 1M
          Secondary PHY: LE 1M
          SID: 0x00
          TX power: 0 dBm
          RSSI: -90 dBm (0xa6)
          Periodic advertising invteral: 0.00 msec (0x0000)
          Direct address type: Public (0x00)
          Direct address: 00:00:00:00:00:00 (OUI 00-00-00)
          Data length: 0x1b
        0f 09 44 65 73 69 67 6e 65 72 20 4d 6f 75 73 65  ..Designer Mouse
        03 19 c2 03 02 01 05 03 03 12 18                 ...........

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 26 +++++++++++++++++++++++
 net/bluetooth/hci_core.c    |  9 ++++++++
 net/bluetooth/hci_event.c   | 52 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 87 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 8c2868f439e7..0ec51eb14810 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1925,6 +1925,15 @@ struct hci_ev_le_conn_complete {
 #define LE_ADV_SCAN_IND		0x02
 #define LE_ADV_NONCONN_IND	0x03
 #define LE_ADV_SCAN_RSP		0x04
+#define LE_ADV_INVALID		0x05
+
+/* Legacy event types in extended adv report */
+#define LE_LEGACY_ADV_IND		0x0013
+#define LE_LEGACY_ADV_DIRECT_IND 	0x0015
+#define LE_LEGACY_ADV_SCAN_IND		0x0012
+#define LE_LEGACY_NONCONN_IND		0x0010
+#define LE_LEGACY_SCAN_RSP_ADV		0x001b
+#define LE_LEGACY_SCAN_RSP_ADV_SCAN	0x001a
 
 #define ADDR_LE_DEV_PUBLIC	0x00
 #define ADDR_LE_DEV_RANDOM	0x01
@@ -1989,6 +1998,23 @@ struct hci_ev_le_direct_adv_info {
 	__s8	 rssi;
 } __packed;
 
+#define HCI_EV_LE_EXT_ADV_REPORT    0x0d
+struct hci_ev_le_ext_adv_report {
+	__le16 	 evt_type;
+	__u8	 bdaddr_type;
+	bdaddr_t bdaddr;
+	__u8	 primary_phy;
+	__u8	 secondary_phy;
+	__u8	 sid;
+	__u8	 tx_power;
+	__s8	 rssi;
+	__le16 	 interval;
+	__u8  	 direct_addr_type;
+	bdaddr_t direct_addr;
+	__u8  	 length;
+	__u8	 data[0];
+} __packed;
+
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL	0xfd
 struct hci_ev_stack_internal {
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index ce2447d89ce1..e3ec2d782762 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -695,6 +695,15 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 		if (hdev->commands[35] & (0x20 | 0x40))
 			events[1] |= 0x08;        /* LE PHY Update Complete */
 
+		/* If the controller supports LE Set Extended Scan Parameters
+		 * and LE Set Extended Scan Enable commands, enable the
+		 * corresponding event.
+		 */
+		if (use_ext_scan(hdev))
+			events[1] |= 0x10;	/* LE Extended Advertising
+						 * Report
+						 */
+
 		hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events),
 			    events);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 15afad005d72..6c6fd4f55f23 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5048,6 +5048,54 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static u8 convert_legacy_evt_type(u16 evt_type)
+{
+	switch (evt_type) {
+	case LE_LEGACY_ADV_IND:
+		return LE_ADV_IND;
+	case LE_LEGACY_ADV_DIRECT_IND:
+		return LE_ADV_DIRECT_IND;
+	case LE_LEGACY_ADV_SCAN_IND:
+		return LE_ADV_SCAN_IND;
+	case LE_LEGACY_NONCONN_IND:
+		return LE_ADV_NONCONN_IND;
+	case LE_LEGACY_SCAN_RSP_ADV:
+	case LE_LEGACY_SCAN_RSP_ADV_SCAN:
+		return LE_ADV_SCAN_RSP;
+	}
+
+	BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x",
+				   evt_type);
+
+	return LE_ADV_INVALID;
+}
+
+static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	u8 num_reports = skb->data[0];
+	void *ptr = &skb->data[1];
+
+	hci_dev_lock(hdev);
+
+	while (num_reports--) {
+		struct hci_ev_le_ext_adv_report *ev = ptr;
+		u8 legacy_evt_type;
+		u16 evt_type;
+
+		evt_type = __le16_to_cpu(ev->evt_type);
+		legacy_evt_type = convert_legacy_evt_type(evt_type);
+		if (legacy_evt_type != LE_ADV_INVALID) {
+			process_adv_report(hdev, legacy_evt_type, &ev->bdaddr,
+					   ev->bdaddr_type, NULL, 0, ev->rssi,
+					   ev->data, ev->length);
+		}
+
+		ptr += sizeof(*ev) + ev->length + 1;
+	}
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_le_remote_feat_complete_evt(struct hci_dev *hdev,
 					    struct sk_buff *skb)
 {
@@ -5280,6 +5328,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_le_direct_adv_report_evt(hdev, skb);
 		break;
 
+	case HCI_EV_LE_EXT_ADV_REPORT:
+		hci_le_ext_adv_report_evt(hdev, skb);
+		break;
+
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From 33f5104624b96c6514621e63909b5703276b4dac Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Fri, 6 Jul 2018 20:53:03 +0200
Subject: clk: Add driver for MAX9485

This patch adds a driver for MAX9485, a programmable audio clock generator.

The device requires a 27.000 MHz clock input. It can provide a gated
buffered output of its input clock and two gated outputs of a PLL that can
generate one out of 16 discrete frequencies. There is only one PLL however,
so the two gated outputs will always have the same frequency but they can
be switched individually.

The driver for this device exposes 4 clocks in total:

- MAX9485_MCLKOUT:      A gated, buffered output of the input clock
- MAX9485_CLKOUT:       A PLL that can be configured to 16 different
			discrete frequencies
- MAX9485_CLKOUT[1,2]:  Two gated outputs for MAX9485_CLKOUT

Some PLL output frequencies can be achieved with different register
settings. The driver will select the one with lowest jitter in such cases.

Signed-off-by: Daniel Mack <daniel@zonque.org>
[sboyd@kernel.org: Use local variable for val in max9485_clkout_recalc_rate()
and shorten line of max9485_of_clk_get()]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/Kconfig       |   6 +
 drivers/clk/Makefile      |   1 +
 drivers/clk/clk-max9485.c | 387 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 394 insertions(+)
 create mode 100644 drivers/clk/clk-max9485.c

diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index 721572a8c429..292056bbb30e 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -45,6 +45,12 @@ config COMMON_CLK_MAX77686
 	  This driver supports Maxim 77620/77686/77802 crystal oscillator
 	  clock.
 
+config COMMON_CLK_MAX9485
+	tristate "Maxim 9485 Programmable Clock Generator"
+	depends on I2C
+	help
+	  This driver supports Maxim 9485 Programmable Audio Clock Generator
+
 config COMMON_CLK_RK808
 	tristate "Clock driver for RK805/RK808/RK818"
 	depends on MFD_RK808
diff --git a/drivers/clk/Makefile b/drivers/clk/Makefile
index ae40cbe770f0..24fc2b634362 100644
--- a/drivers/clk/Makefile
+++ b/drivers/clk/Makefile
@@ -31,6 +31,7 @@ obj-$(CONFIG_COMMON_CLK_ASPEED)		+= clk-aspeed.o
 obj-$(CONFIG_ARCH_HIGHBANK)		+= clk-highbank.o
 obj-$(CONFIG_CLK_HSDK)			+= clk-hsdk-pll.o
 obj-$(CONFIG_COMMON_CLK_MAX77686)	+= clk-max77686.o
+obj-$(CONFIG_COMMON_CLK_MAX9485)	+= clk-max9485.o
 obj-$(CONFIG_ARCH_MOXART)		+= clk-moxart.o
 obj-$(CONFIG_ARCH_NOMADIK)		+= clk-nomadik.o
 obj-$(CONFIG_ARCH_NPCM7XX)	    	+= clk-npcm7xx.o
diff --git a/drivers/clk/clk-max9485.c b/drivers/clk/clk-max9485.c
new file mode 100644
index 000000000000..5e80f3d090f3
--- /dev/null
+++ b/drivers/clk/clk-max9485.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/regulator/consumer.h>
+
+#include <dt-bindings/clock/maxim,max9485.h>
+
+#define MAX9485_NUM_CLKS 4
+
+/* This chip has only one register of 8 bit width. */
+
+#define MAX9485_FS_12KHZ	(0 << 0)
+#define MAX9485_FS_32KHZ	(1 << 0)
+#define MAX9485_FS_44_1KHZ	(2 << 0)
+#define MAX9485_FS_48KHZ	(3 << 0)
+
+#define MAX9485_SCALE_256	(0 << 2)
+#define MAX9485_SCALE_384	(1 << 2)
+#define MAX9485_SCALE_768	(2 << 2)
+
+#define MAX9485_DOUBLE		BIT(4)
+#define MAX9485_CLKOUT1_ENABLE	BIT(5)
+#define MAX9485_CLKOUT2_ENABLE	BIT(6)
+#define MAX9485_MCLK_ENABLE	BIT(7)
+#define MAX9485_FREQ_MASK	0x1f
+
+struct max9485_rate {
+	unsigned long out;
+	u8 reg_value;
+};
+
+/*
+ * Ordered by frequency. For frequency the hardware can generate with
+ * multiple settings, the one with lowest jitter is listed first.
+ */
+static const struct max9485_rate max9485_rates[] = {
+	{  3072000, MAX9485_FS_12KHZ   | MAX9485_SCALE_256 },
+	{  4608000, MAX9485_FS_12KHZ   | MAX9485_SCALE_384 },
+	{  8192000, MAX9485_FS_32KHZ   | MAX9485_SCALE_256 },
+	{  9126000, MAX9485_FS_12KHZ   | MAX9485_SCALE_768 },
+	{ 11289600, MAX9485_FS_44_1KHZ | MAX9485_SCALE_256 },
+	{ 12288000, MAX9485_FS_48KHZ   | MAX9485_SCALE_256 },
+	{ 12288000, MAX9485_FS_32KHZ   | MAX9485_SCALE_384 },
+	{ 16384000, MAX9485_FS_32KHZ   | MAX9485_SCALE_256 | MAX9485_DOUBLE },
+	{ 16934400, MAX9485_FS_44_1KHZ | MAX9485_SCALE_384 },
+	{ 18384000, MAX9485_FS_48KHZ   | MAX9485_SCALE_384 },
+	{ 22579200, MAX9485_FS_44_1KHZ | MAX9485_SCALE_256 | MAX9485_DOUBLE },
+	{ 24576000, MAX9485_FS_48KHZ   | MAX9485_SCALE_256 | MAX9485_DOUBLE },
+	{ 24576000, MAX9485_FS_32KHZ   | MAX9485_SCALE_384 | MAX9485_DOUBLE },
+	{ 24576000, MAX9485_FS_32KHZ   | MAX9485_SCALE_768 },
+	{ 33868800, MAX9485_FS_44_1KHZ | MAX9485_SCALE_384 | MAX9485_DOUBLE },
+	{ 33868800, MAX9485_FS_44_1KHZ | MAX9485_SCALE_768 },
+	{ 36864000, MAX9485_FS_48KHZ   | MAX9485_SCALE_384 | MAX9485_DOUBLE },
+	{ 36864000, MAX9485_FS_48KHZ   | MAX9485_SCALE_768 },
+	{ 49152000, MAX9485_FS_32KHZ   | MAX9485_SCALE_768 | MAX9485_DOUBLE },
+	{ 67737600, MAX9485_FS_44_1KHZ | MAX9485_SCALE_768 | MAX9485_DOUBLE },
+	{ 73728000, MAX9485_FS_48KHZ   | MAX9485_SCALE_768 | MAX9485_DOUBLE },
+	{ } /* sentinel */
+};
+
+struct max9485_driver_data;
+
+struct max9485_clk_hw {
+	struct clk_hw hw;
+	struct clk_init_data init;
+	u8 enable_bit;
+	struct max9485_driver_data *drvdata;
+};
+
+struct max9485_driver_data {
+	struct clk *xclk;
+	struct i2c_client *client;
+	u8 reg_value;
+	struct regulator *supply;
+	struct gpio_desc *reset_gpio;
+	struct max9485_clk_hw hw[MAX9485_NUM_CLKS];
+};
+
+static inline struct max9485_clk_hw *to_max9485_clk(struct clk_hw *hw)
+{
+	return container_of(hw, struct max9485_clk_hw, hw);
+}
+
+static int max9485_update_bits(struct max9485_driver_data *drvdata,
+			       u8 mask, u8 value)
+{
+	int ret;
+
+	drvdata->reg_value &= ~mask;
+	drvdata->reg_value |= value;
+
+	dev_dbg(&drvdata->client->dev,
+		"updating mask 0x%02x value 0x%02x -> 0x%02x\n",
+		mask, value, drvdata->reg_value);
+
+	ret = i2c_master_send(drvdata->client,
+			      &drvdata->reg_value,
+			      sizeof(drvdata->reg_value));
+
+	return ret < 0 ? ret : 0;
+}
+
+static int max9485_clk_prepare(struct clk_hw *hw)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+
+	return max9485_update_bits(clk_hw->drvdata,
+				   clk_hw->enable_bit,
+				   clk_hw->enable_bit);
+}
+
+static void max9485_clk_unprepare(struct clk_hw *hw)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+
+	max9485_update_bits(clk_hw->drvdata, clk_hw->enable_bit, 0);
+}
+
+/*
+ * CLKOUT - configurable clock output
+ */
+static int max9485_clkout_set_rate(struct clk_hw *hw, unsigned long rate,
+				   unsigned long parent_rate)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+	const struct max9485_rate *entry;
+
+	for (entry = max9485_rates; entry->out != 0; entry++)
+		if (entry->out == rate)
+			break;
+
+	if (entry->out == 0)
+		return -EINVAL;
+
+	return max9485_update_bits(clk_hw->drvdata,
+				   MAX9485_FREQ_MASK,
+				   entry->reg_value);
+}
+
+static unsigned long max9485_clkout_recalc_rate(struct clk_hw *hw,
+						unsigned long parent_rate)
+{
+	struct max9485_clk_hw *clk_hw = to_max9485_clk(hw);
+	struct max9485_driver_data *drvdata = clk_hw->drvdata;
+	u8 val = drvdata->reg_value & MAX9485_FREQ_MASK;
+	const struct max9485_rate *entry;
+
+	for (entry = max9485_rates; entry->out != 0; entry++)
+		if (val == entry->reg_value)
+			return entry->out;
+
+	return 0;
+}
+
+static long max9485_clkout_round_rate(struct clk_hw *hw, unsigned long rate,
+				      unsigned long *parent_rate)
+{
+	const struct max9485_rate *curr, *prev = NULL;
+
+	for (curr = max9485_rates; curr->out != 0; curr++) {
+		/* Exact matches */
+		if (curr->out == rate)
+			return rate;
+
+		/*
+		 * Find the first entry that has a frequency higher than the
+		 * requested one.
+		 */
+		if (curr->out > rate) {
+			unsigned int mid;
+
+			/*
+			 * If this is the first entry, clamp the value to the
+			 * lowest possible frequency.
+			 */
+			if (!prev)
+				return curr->out;
+
+			/*
+			 * Otherwise, determine whether the previous entry or
+			 * current one is closer.
+			 */
+			mid = prev->out + ((curr->out - prev->out) / 2);
+
+			return (mid > rate) ? prev->out : curr->out;
+		}
+
+		prev = curr;
+	}
+
+	/* If the last entry was still too high, clamp the value */
+	return prev->out;
+}
+
+struct max9485_clk {
+	const char *name;
+	int parent_index;
+	const struct clk_ops ops;
+	u8 enable_bit;
+};
+
+static const struct max9485_clk max9485_clks[MAX9485_NUM_CLKS] = {
+	[MAX9485_MCLKOUT] = {
+		.name = "mclkout",
+		.parent_index = -1,
+		.enable_bit = MAX9485_MCLK_ENABLE,
+		.ops = {
+			.prepare	= max9485_clk_prepare,
+			.unprepare	= max9485_clk_unprepare,
+		},
+	},
+	[MAX9485_CLKOUT] = {
+		.name = "clkout",
+		.parent_index = -1,
+		.ops = {
+			.set_rate	= max9485_clkout_set_rate,
+			.round_rate	= max9485_clkout_round_rate,
+			.recalc_rate	= max9485_clkout_recalc_rate,
+		},
+	},
+	[MAX9485_CLKOUT1] = {
+		.name = "clkout1",
+		.parent_index = MAX9485_CLKOUT,
+		.enable_bit = MAX9485_CLKOUT1_ENABLE,
+		.ops = {
+			.prepare	= max9485_clk_prepare,
+			.unprepare	= max9485_clk_unprepare,
+		},
+	},
+	[MAX9485_CLKOUT2] = {
+		.name = "clkout2",
+		.parent_index = MAX9485_CLKOUT,
+		.enable_bit = MAX9485_CLKOUT2_ENABLE,
+		.ops = {
+			.prepare	= max9485_clk_prepare,
+			.unprepare	= max9485_clk_unprepare,
+		},
+	},
+};
+
+static struct clk_hw *
+max9485_of_clk_get(struct of_phandle_args *clkspec, void *data)
+{
+	struct max9485_driver_data *drvdata = data;
+	unsigned int idx = clkspec->args[0];
+
+	return &drvdata->hw[idx].hw;
+}
+
+static int max9485_i2c_probe(struct i2c_client *client,
+			     const struct i2c_device_id *id)
+{
+	struct max9485_driver_data *drvdata;
+	struct device *dev = &client->dev;
+	const char *xclk_name;
+	int i, ret;
+
+	drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!drvdata)
+		return -ENOMEM;
+
+	drvdata->xclk = devm_clk_get(dev, "xclk");
+	if (IS_ERR(drvdata->xclk))
+		return PTR_ERR(drvdata->xclk);
+
+	xclk_name = __clk_get_name(drvdata->xclk);
+
+	drvdata->supply = devm_regulator_get(dev, "vdd");
+	if (IS_ERR(drvdata->supply))
+		return PTR_ERR(drvdata->supply);
+
+	ret = regulator_enable(drvdata->supply);
+	if (ret < 0)
+		return ret;
+
+	drvdata->reset_gpio =
+		devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(drvdata->reset_gpio))
+		return PTR_ERR(drvdata->reset_gpio);
+
+	i2c_set_clientdata(client, drvdata);
+	drvdata->client = client;
+
+	ret = i2c_master_recv(drvdata->client, &drvdata->reg_value,
+			      sizeof(drvdata->reg_value));
+	if (ret < 0) {
+		dev_warn(dev, "Unable to read device register: %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < MAX9485_NUM_CLKS; i++) {
+		int parent_index = max9485_clks[i].parent_index;
+		const char *name;
+
+		if (of_property_read_string_index(dev->of_node,
+						  "clock-output-names",
+						  i, &name) == 0) {
+			drvdata->hw[i].init.name = name;
+		} else {
+			drvdata->hw[i].init.name = max9485_clks[i].name;
+		}
+
+		drvdata->hw[i].init.ops = &max9485_clks[i].ops;
+		drvdata->hw[i].init.num_parents = 1;
+		drvdata->hw[i].init.flags = 0;
+
+		if (parent_index > 0) {
+			drvdata->hw[i].init.parent_names =
+				&drvdata->hw[parent_index].init.name;
+			drvdata->hw[i].init.flags |= CLK_SET_RATE_PARENT;
+		} else {
+			drvdata->hw[i].init.parent_names = &xclk_name;
+		}
+
+		drvdata->hw[i].enable_bit = max9485_clks[i].enable_bit;
+		drvdata->hw[i].hw.init = &drvdata->hw[i].init;
+		drvdata->hw[i].drvdata = drvdata;
+
+		ret = devm_clk_hw_register(dev, &drvdata->hw[i].hw);
+		if (ret < 0)
+			return ret;
+	}
+
+	return devm_of_clk_add_hw_provider(dev, max9485_of_clk_get, drvdata);
+}
+
+static int __maybe_unused max9485_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct max9485_driver_data *drvdata = i2c_get_clientdata(client);
+
+	gpiod_set_value_cansleep(drvdata->reset_gpio, 0);
+
+	return 0;
+}
+
+static int __maybe_unused max9485_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct max9485_driver_data *drvdata = i2c_get_clientdata(client);
+	int ret;
+
+	gpiod_set_value_cansleep(drvdata->reset_gpio, 1);
+
+	ret = i2c_master_send(client, &drvdata->reg_value,
+			      sizeof(drvdata->reg_value));
+
+	return ret < 0 ? ret : 0;
+}
+
+static const struct dev_pm_ops max9485_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(max9485_suspend, max9485_resume)
+};
+
+static const struct of_device_id max9485_dt_ids[] = {
+	{ .compatible = "maxim,max9485", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, max9485_dt_ids);
+
+static const struct i2c_device_id max9485_i2c_ids[] = {
+	{ .name = "max9485", },
+	{ }
+};
+MODULE_DEVICE_TABLE(i2c, max9485_i2c_ids);
+
+static struct i2c_driver max9485_driver = {
+	.driver = {
+		.name		= "max9485",
+		.pm		= &max9485_pm_ops,
+		.of_match_table	= max9485_dt_ids,
+	},
+	.probe = max9485_i2c_probe,
+	.id_table = max9485_i2c_ids,
+};
+module_i2c_driver(max9485_driver);
+
+MODULE_AUTHOR("Daniel Mack <daniel@zonque.org>");
+MODULE_DESCRIPTION("MAX9485 Programmable Audio Clock Generator");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From d12fb05643f9b48134c7650f5a03f9729aacfde4 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Fri, 6 Jul 2018 17:05:30 +0530
Subject: Bluetooth: Introduce helpers for le conn status and complete

This is done so that the helpers can be used for extended conn
implementation which will be done in subsequent patch.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/hci_event.c | 110 +++++++++++++++++++++++++++-------------------
 1 file changed, 65 insertions(+), 45 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6c6fd4f55f23..14e42e157de9 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1971,55 +1971,63 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status)
 	hci_dev_unlock(hdev);
 }
 
-static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status)
+static void cs_le_create_conn(struct hci_dev *hdev, bdaddr_t *peer_addr,
+			      u8 peer_addr_type, u8 own_address_type,
+			      u8 filter_policy)
 {
-	struct hci_cp_le_create_conn *cp;
 	struct hci_conn *conn;
 
-	BT_DBG("%s status 0x%2.2x", hdev->name, status);
-
-	/* All connection failure handling is taken care of by the
-	 * hci_le_conn_failed function which is triggered by the HCI
-	 * request completion callbacks used for connecting.
-	 */
-	if (status)
-		return;
-
-	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN);
-	if (!cp)
-		return;
-
-	hci_dev_lock(hdev);
-
-	conn = hci_conn_hash_lookup_le(hdev, &cp->peer_addr,
-				       cp->peer_addr_type);
+	conn = hci_conn_hash_lookup_le(hdev, peer_addr,
+				       peer_addr_type);
 	if (!conn)
-		goto unlock;
+		return;
 
 	/* Store the initiator and responder address information which
 	 * is needed for SMP. These values will not change during the
 	 * lifetime of the connection.
 	 */
-	conn->init_addr_type = cp->own_address_type;
-	if (cp->own_address_type == ADDR_LE_DEV_RANDOM)
+	conn->init_addr_type = own_address_type;
+	if (own_address_type == ADDR_LE_DEV_RANDOM)
 		bacpy(&conn->init_addr, &hdev->random_addr);
 	else
 		bacpy(&conn->init_addr, &hdev->bdaddr);
 
-	conn->resp_addr_type = cp->peer_addr_type;
-	bacpy(&conn->resp_addr, &cp->peer_addr);
+	conn->resp_addr_type = peer_addr_type;
+	bacpy(&conn->resp_addr, peer_addr);
 
 	/* We don't want the connection attempt to stick around
 	 * indefinitely since LE doesn't have a page timeout concept
 	 * like BR/EDR. Set a timer for any connection that doesn't use
 	 * the white list for connecting.
 	 */
-	if (cp->filter_policy == HCI_LE_USE_PEER_ADDR)
+	if (filter_policy == HCI_LE_USE_PEER_ADDR)
 		queue_delayed_work(conn->hdev->workqueue,
 				   &conn->le_conn_timeout,
 				   conn->conn_timeout);
+}
+
+static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_le_create_conn *cp;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	/* All connection failure handling is taken care of by the
+	 * hci_le_conn_failed function which is triggered by the HCI
+	 * request completion callbacks used for connecting.
+	 */
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_CREATE_CONN);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	cs_le_create_conn(hdev, &cp->peer_addr, cp->peer_addr_type,
+			  cp->own_address_type, cp->filter_policy);
 
-unlock:
 	hci_dev_unlock(hdev);
 }
 
@@ -4551,16 +4559,15 @@ static void hci_disconn_phylink_complete_evt(struct hci_dev *hdev,
 }
 #endif
 
-static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
+static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
+			bdaddr_t *bdaddr, u8 bdaddr_type, u8 role, u16 handle,
+			u16 interval, u16 latency, u16 supervision_timeout)
 {
-	struct hci_ev_le_conn_complete *ev = (void *) skb->data;
 	struct hci_conn_params *params;
 	struct hci_conn *conn;
 	struct smp_irk *irk;
 	u8 addr_type;
 
-	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
-
 	hci_dev_lock(hdev);
 
 	/* All controllers implicitly stop advertising in the event of a
@@ -4570,13 +4577,13 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 
 	conn = hci_lookup_le_connect(hdev);
 	if (!conn) {
-		conn = hci_conn_add(hdev, LE_LINK, &ev->bdaddr, ev->role);
+		conn = hci_conn_add(hdev, LE_LINK, bdaddr, role);
 		if (!conn) {
 			bt_dev_err(hdev, "no memory for new connection");
 			goto unlock;
 		}
 
-		conn->dst_type = ev->bdaddr_type;
+		conn->dst_type = bdaddr_type;
 
 		/* If we didn't have a hci_conn object previously
 		 * but we're in master role this must be something
@@ -4587,8 +4594,8 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		 * initiator address based on the HCI_PRIVACY flag.
 		 */
 		if (conn->out) {
-			conn->resp_addr_type = ev->bdaddr_type;
-			bacpy(&conn->resp_addr, &ev->bdaddr);
+			conn->resp_addr_type = bdaddr_type;
+			bacpy(&conn->resp_addr, bdaddr);
 			if (hci_dev_test_flag(hdev, HCI_PRIVACY)) {
 				conn->init_addr_type = ADDR_LE_DEV_RANDOM;
 				bacpy(&conn->init_addr, &hdev->rpa);
@@ -4612,8 +4619,8 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		else
 			bacpy(&conn->resp_addr, &hdev->bdaddr);
 
-		conn->init_addr_type = ev->bdaddr_type;
-		bacpy(&conn->init_addr, &ev->bdaddr);
+		conn->init_addr_type = bdaddr_type;
+		bacpy(&conn->init_addr, bdaddr);
 
 		/* For incoming connections, set the default minimum
 		 * and maximum connection interval. They will be used
@@ -4639,8 +4646,8 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		conn->dst_type = irk->addr_type;
 	}
 
-	if (ev->status) {
-		hci_le_conn_failed(conn, ev->status);
+	if (status) {
+		hci_le_conn_failed(conn, status);
 		goto unlock;
 	}
 
@@ -4659,17 +4666,17 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		mgmt_device_connected(hdev, conn, 0, NULL, 0);
 
 	conn->sec_level = BT_SECURITY_LOW;
-	conn->handle = __le16_to_cpu(ev->handle);
+	conn->handle = handle;
 	conn->state = BT_CONFIG;
 
-	conn->le_conn_interval = le16_to_cpu(ev->interval);
-	conn->le_conn_latency = le16_to_cpu(ev->latency);
-	conn->le_supv_timeout = le16_to_cpu(ev->supervision_timeout);
+	conn->le_conn_interval = interval;
+	conn->le_conn_latency = latency;
+	conn->le_supv_timeout = supervision_timeout;
 
 	hci_debugfs_create_conn(conn);
 	hci_conn_add_sysfs(conn);
 
-	if (!ev->status) {
+	if (!status) {
 		/* The remote features procedure is defined for master
 		 * role only. So only in case of an initiated connection
 		 * request the remote features.
@@ -4691,10 +4698,10 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			hci_conn_hold(conn);
 		} else {
 			conn->state = BT_CONNECTED;
-			hci_connect_cfm(conn, ev->status);
+			hci_connect_cfm(conn, status);
 		}
 	} else {
-		hci_connect_cfm(conn, ev->status);
+		hci_connect_cfm(conn, status);
 	}
 
 	params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst,
@@ -4713,6 +4720,19 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_ev_le_conn_complete *ev = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
+
+	le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type,
+			     ev->role, le16_to_cpu(ev->handle),
+			     le16_to_cpu(ev->interval),
+			     le16_to_cpu(ev->latency),
+			     le16_to_cpu(ev->supervision_timeout));
+}
+
 static void hci_le_conn_update_complete_evt(struct hci_dev *hdev,
 					    struct sk_buff *skb)
 {
-- 
cgit v1.2.3


From fc20654389364a55eeab837244b24f8da75009f6 Mon Sep 17 00:00:00 2001
From: Robert Jarzmik <robert.jarzmik@free.fr>
Date: Wed, 27 Jun 2018 21:41:23 +0200
Subject: clk: pxa: export 32kHz PLL

This clock is especially used by the RTC driver, so export it so that
devicetree users can use it.

Signed-off-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/pxa/clk-pxa25x.c          | 6 ++++--
 drivers/clk/pxa/clk-pxa27x.c          | 7 ++++---
 drivers/clk/pxa/clk-pxa3xx.c          | 7 ++++---
 include/dt-bindings/clock/pxa-clock.h | 3 ++-
 4 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/clk/pxa/clk-pxa25x.c b/drivers/clk/pxa/clk-pxa25x.c
index 6416c1f8e632..e88f8e01fe3a 100644
--- a/drivers/clk/pxa/clk-pxa25x.c
+++ b/drivers/clk/pxa/clk-pxa25x.c
@@ -292,8 +292,10 @@ static void __init pxa25x_register_plls(void)
 {
 	clk_register_fixed_rate(NULL, "osc_3_6864mhz", NULL,
 				CLK_GET_RATE_NOCACHE, 3686400);
-	clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
-				CLK_GET_RATE_NOCACHE, 32768);
+	clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL,
+			    clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
+						    CLK_GET_RATE_NOCACHE,
+						    32768));
 	clk_register_fixed_rate(NULL, "clk_dummy", NULL, 0, 0);
 	clk_register_fixed_factor(NULL, "ppll_95_85mhz", "osc_3_6864mhz",
 				  0, 26, 1);
diff --git a/drivers/clk/pxa/clk-pxa27x.c b/drivers/clk/pxa/clk-pxa27x.c
index 25a30194d27a..d40b63e7bbce 100644
--- a/drivers/clk/pxa/clk-pxa27x.c
+++ b/drivers/clk/pxa/clk-pxa27x.c
@@ -314,9 +314,10 @@ static void __init pxa27x_register_plls(void)
 	clk_register_fixed_rate(NULL, "osc_13mhz", NULL,
 				CLK_GET_RATE_NOCACHE,
 				13 * MHz);
-	clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
-				CLK_GET_RATE_NOCACHE,
-				32768 * KHz);
+	clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL,
+			    clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
+						    CLK_GET_RATE_NOCACHE,
+						    32768 * KHz));
 	clk_register_fixed_rate(NULL, "clk_dummy", NULL, 0, 0);
 	clk_register_fixed_factor(NULL, "ppll_312mhz", "osc_13mhz", 0, 24, 1);
 }
diff --git a/drivers/clk/pxa/clk-pxa3xx.c b/drivers/clk/pxa/clk-pxa3xx.c
index 2d126df2bccd..7aa120c3bd08 100644
--- a/drivers/clk/pxa/clk-pxa3xx.c
+++ b/drivers/clk/pxa/clk-pxa3xx.c
@@ -286,9 +286,10 @@ static void __init pxa3xx_register_plls(void)
 	clk_register_fixed_rate(NULL, "osc_13mhz", NULL,
 				CLK_GET_RATE_NOCACHE,
 				13 * MHz);
-	clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
-				CLK_GET_RATE_NOCACHE,
-				32768);
+	clkdev_pxa_register(CLK_OSC32k768, "osc_32_768khz", NULL,
+			    clk_register_fixed_rate(NULL, "osc_32_768khz", NULL,
+						    CLK_GET_RATE_NOCACHE,
+						    32768));
 	clk_register_fixed_rate(NULL, "ring_osc_120mhz", NULL,
 				CLK_GET_RATE_NOCACHE,
 				120 * MHz);
diff --git a/include/dt-bindings/clock/pxa-clock.h b/include/dt-bindings/clock/pxa-clock.h
index e65803b1dc7e..0b0fd2b01538 100644
--- a/include/dt-bindings/clock/pxa-clock.h
+++ b/include/dt-bindings/clock/pxa-clock.h
@@ -72,6 +72,7 @@
 #define CLK_USIM 58
 #define CLK_USIM1 59
 #define CLK_USMI0 60
-#define CLK_MAX 61
+#define CLK_OSC32k768 61
+#define CLK_MAX 62
 
 #endif
-- 
cgit v1.2.3


From 4d94f95d30c8fbfe86068e9abed110974d697cf5 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Fri, 6 Jul 2018 22:50:32 +0200
Subject: Bluetooth: Use extended LE Connection if supported

This implements extended LE craete connection and enhanced
LE conn complete event if the controller supports.

For now it is as good as legacy LE connection and event as
no new features in the extended connection is handled.

< HCI Command: LE Extended Create Connection (0x08|0x0043) plen 26
        Filter policy: White list is not used (0x00)
        Own address type: Public (0x00)
        Peer address type: Random (0x01)
        Peer address: DB:7E:2E:1D:85:E8 (Static)
        Initiating PHYs: 0x01
        Entry 0: LE 1M
          Scan interval: 60.000 msec (0x0060)
          Scan window: 60.000 msec (0x0060)
          Min connection interval: 50.00 msec (0x0028)
          Max connection interval: 70.00 msec (0x0038)
          Connection latency: 0 (0x0000)
          Supervision timeout: 420 msec (0x002a)
          Min connection length: 0.000 msec (0x0000)
          Max connection length: 0.000 msec (0x0000)
> HCI Event: Command Status (0x0f) plen 4
      LE Extended Create Connection (0x08|0x0043) ncmd 2
        Status: Success (0x00)
> HCI Event: LE Meta Event (0x3e) plen 31
      LE Enhanced Connection Complete (0x0a)
        Status: Success (0x00)
        Handle: 3585
        Role: Master (0x00)
        Peer address type: Random (0x01)
        Peer address: DB:7E:2E:1D:85:E8 (Static)
        Local resolvable private address: 00:00:00:00:00:00 (Non-Resolvable)
        Peer resolvable private address: 00:00:00:00:00:00 (Non-Resolvable)
        Connection interval: 67.50 msec (0x0036)
        Connection latency: 0 (0x0000)
        Supervision timeout: 420 msec (0x002a)
        Master clock accuracy: 0x00
@ MGMT Event: Device Connected (0x000b) plen 40
        LE Address: DB:7E:2E:1D:85:E8 (Static)
        Flags: 0x00000000
        Data length: 27
        Name (complete): Designer Mouse
        Appearance: Mouse (0x03c2)
        Flags: 0x05
          LE Limited Discoverable Mode
          BR/EDR Not Supported
        16-bit Service UUIDs (complete): 1 entry
          Human Interface Device (0x1812)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      | 36 ++++++++++++++++++++
 include/net/bluetooth/hci_core.h |  2 ++
 net/bluetooth/hci_conn.c         | 72 ++++++++++++++++++++++++++++++----------
 net/bluetooth/hci_core.c         |  8 +++++
 net/bluetooth/hci_event.c        | 47 ++++++++++++++++++++++++++
 5 files changed, 147 insertions(+), 18 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 0ec51eb14810..73e48be5bbb3 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1538,6 +1538,27 @@ struct hci_cp_le_set_ext_scan_enable {
 	__le16  period;
 } __packed;
 
+#define HCI_OP_LE_EXT_CREATE_CONN    0x2043
+struct hci_cp_le_ext_create_conn {
+	__u8      filter_policy;
+	__u8      own_addr_type;
+	__u8      peer_addr_type;
+	bdaddr_t  peer_addr;
+	__u8      phys;
+	__u8      data[0];
+} __packed;
+
+struct hci_cp_le_ext_conn_param {
+	__le16 scan_interval;
+	__le16 scan_window;
+	__le16 conn_interval_min;
+	__le16 conn_interval_max;
+	__le16 conn_latency;
+	__le16 supervision_timeout;
+	__le16 min_ce_len;
+	__le16 max_ce_len;
+} __packed;
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
@@ -2015,6 +2036,21 @@ struct hci_ev_le_ext_adv_report {
 	__u8	 data[0];
 } __packed;
 
+#define HCI_EV_LE_ENHANCED_CONN_COMPLETE    0x0a
+struct hci_ev_le_enh_conn_complete {
+	__u8      status;
+	__le16    handle;
+	__u8      role;
+	__u8      bdaddr_type;
+	bdaddr_t  bdaddr;
+	bdaddr_t  local_rpa;
+	bdaddr_t  peer_rpa;
+	__le16    interval;
+	__le16    latency;
+	__le16    supervision_timeout;
+	__u8      clk_accurancy;
+} __packed;
+
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL	0xfd
 struct hci_ev_stack_internal {
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index cc0bde74dd45..a74453571264 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1161,6 +1161,8 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 /* Use ext scanning if set ext scan param and ext scan enable is supported */
 #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \
 			   ((dev)->commands[37] & 0x40))
+/* Use ext create connection if command is supported */
+#define use_ext_conn(dev) ((dev)->commands[37] & 0x80)
 
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 45ff5dc124cc..cc967ca67962 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -752,7 +752,6 @@ static void hci_req_add_le_create_conn(struct hci_request *req,
 				       struct hci_conn *conn,
 				       bdaddr_t *direct_rpa)
 {
-	struct hci_cp_le_create_conn cp;
 	struct hci_dev *hdev = conn->hdev;
 	u8 own_addr_type;
 
@@ -775,25 +774,62 @@ static void hci_req_add_le_create_conn(struct hci_request *req,
 			return;
 	}
 
-	memset(&cp, 0, sizeof(cp));
+	if (use_ext_conn(hdev)) {
+		struct hci_cp_le_ext_create_conn *cp;
+		struct hci_cp_le_ext_conn_param *p;
+		/* As of now only LE 1M is supported */
+		u8 data[sizeof(*cp) + sizeof(*p) * 1];
 
-	/* Set window to be the same value as the interval to enable
-	 * continuous scanning.
-	 */
-	cp.scan_interval = cpu_to_le16(hdev->le_scan_interval);
-	cp.scan_window = cp.scan_interval;
+		cp = (void *) data;
+		p = (void *) cp->data;
 
-	bacpy(&cp.peer_addr, &conn->dst);
-	cp.peer_addr_type = conn->dst_type;
-	cp.own_address_type = own_addr_type;
-	cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval);
-	cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval);
-	cp.conn_latency = cpu_to_le16(conn->le_conn_latency);
-	cp.supervision_timeout = cpu_to_le16(conn->le_supv_timeout);
-	cp.min_ce_len = cpu_to_le16(0x0000);
-	cp.max_ce_len = cpu_to_le16(0x0000);
-
-	hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp);
+		memset(cp, 0, sizeof(*cp));
+
+		bacpy(&cp->peer_addr, &conn->dst);
+		cp->peer_addr_type = conn->dst_type;
+		cp->own_addr_type = own_addr_type;
+		cp->phys = LE_SCAN_PHY_1M;
+
+		memset(p, 0, sizeof(*p));
+
+		/* Set window to be the same value as the interval to enable
+		 * continuous scanning.
+		 */
+
+		p->scan_interval = cpu_to_le16(hdev->le_scan_interval);
+		p->scan_window = p->scan_interval;
+		p->conn_interval_min = cpu_to_le16(conn->le_conn_min_interval);
+		p->conn_interval_max = cpu_to_le16(conn->le_conn_max_interval);
+		p->conn_latency = cpu_to_le16(conn->le_conn_latency);
+		p->supervision_timeout = cpu_to_le16(conn->le_supv_timeout);
+		p->min_ce_len = cpu_to_le16(0x0000);
+		p->max_ce_len = cpu_to_le16(0x0000);
+
+		hci_req_add(req, HCI_OP_LE_EXT_CREATE_CONN, sizeof(data), data);
+
+	} else {
+		struct hci_cp_le_create_conn cp;
+
+		memset(&cp, 0, sizeof(cp));
+
+		/* Set window to be the same value as the interval to enable
+		 * continuous scanning.
+		 */
+		cp.scan_interval = cpu_to_le16(hdev->le_scan_interval);
+		cp.scan_window = cp.scan_interval;
+
+		bacpy(&cp.peer_addr, &conn->dst);
+		cp.peer_addr_type = conn->dst_type;
+		cp.own_address_type = own_addr_type;
+		cp.conn_interval_min = cpu_to_le16(conn->le_conn_min_interval);
+		cp.conn_interval_max = cpu_to_le16(conn->le_conn_max_interval);
+		cp.conn_latency = cpu_to_le16(conn->le_conn_latency);
+		cp.supervision_timeout = cpu_to_le16(conn->le_supv_timeout);
+		cp.min_ce_len = cpu_to_le16(0x0000);
+		cp.max_ce_len = cpu_to_le16(0x0000);
+
+		hci_req_add(req, HCI_OP_LE_CREATE_CONN, sizeof(cp), &cp);
+	}
 
 	conn->state = BT_CONNECT;
 	clear_bit(HCI_CONN_SCANNING, &conn->flags);
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index e3ec2d782762..f5c21004186c 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -704,6 +704,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 						 * Report
 						 */
 
+		/* If the controller supports the LE Extended Create Connection
+		 * command, enable the corresponding event.
+		 */
+		if (use_ext_conn(hdev))
+			events[1] |= 0x02;      /* LE Enhanced Connection
+						 * Complete
+						 */
+
 		hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events),
 			    events);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 14e42e157de9..68192152c23b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -2031,6 +2031,31 @@ static void hci_cs_le_create_conn(struct hci_dev *hdev, u8 status)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cs_le_ext_create_conn(struct hci_dev *hdev, u8 status)
+{
+	struct hci_cp_le_ext_create_conn *cp;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	/* All connection failure handling is taken care of by the
+	 * hci_le_conn_failed function which is triggered by the HCI
+	 * request completion callbacks used for connecting.
+	 */
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_EXT_CREATE_CONN);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	cs_le_create_conn(hdev, &cp->peer_addr, cp->peer_addr_type,
+			  cp->own_addr_type, cp->filter_policy);
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cs_le_read_remote_features(struct hci_dev *hdev, u8 status)
 {
 	struct hci_cp_le_read_remote_features *cp;
@@ -3233,6 +3258,10 @@ static void hci_cmd_status_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cs_le_start_enc(hdev, ev->status);
 		break;
 
+	case HCI_OP_LE_EXT_CREATE_CONN:
+		hci_cs_le_ext_create_conn(hdev, ev->status);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
@@ -4733,6 +4762,20 @@ static void hci_le_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb)
 			     le16_to_cpu(ev->supervision_timeout));
 }
 
+static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev,
+					 struct sk_buff *skb)
+{
+	struct hci_ev_le_enh_conn_complete *ev = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
+
+	le_conn_complete_evt(hdev, ev->status, &ev->bdaddr, ev->bdaddr_type,
+			     ev->role, le16_to_cpu(ev->handle),
+			     le16_to_cpu(ev->interval),
+			     le16_to_cpu(ev->latency),
+			     le16_to_cpu(ev->supervision_timeout));
+}
+
 static void hci_le_conn_update_complete_evt(struct hci_dev *hdev,
 					    struct sk_buff *skb)
 {
@@ -5352,6 +5395,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_le_ext_adv_report_evt(hdev, skb);
 		break;
 
+	case HCI_EV_LE_ENHANCED_CONN_COMPLETE:
+		hci_le_enh_conn_complete_evt(hdev, skb);
+		break;
+
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From cd88259a7215e0737f8ef2c2842f41922ae87d8d Mon Sep 17 00:00:00 2001
From: Lei YU <mine260309@gmail.com>
Date: Tue, 26 Jun 2018 09:55:25 +0800
Subject: clk: aspeed: Fix SDCLK name

The SDCLK was named SDCLKCLK, and no one has used this yet.
Fix it.

Signed-off-by: Lei YU <mine260309@gmail.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-aspeed.c                 | 2 +-
 include/dt-bindings/clock/aspeed-clock.h | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/clk-aspeed.c b/drivers/clk/clk-aspeed.c
index 38b366b00c57..f49c6842c604 100644
--- a/drivers/clk/clk-aspeed.c
+++ b/drivers/clk/clk-aspeed.c
@@ -109,7 +109,7 @@ static const struct aspeed_gate_data aspeed_gates[] = {
 	[ASPEED_CLK_GATE_RSACLK] =	{ 24, -1, "rsaclk-gate",	NULL,	0 }, /* RSA */
 	[ASPEED_CLK_GATE_UART3CLK] =	{ 25, -1, "uart3clk-gate",	"uart",	0 }, /* UART3 */
 	[ASPEED_CLK_GATE_UART4CLK] =	{ 26, -1, "uart4clk-gate",	"uart",	0 }, /* UART4 */
-	[ASPEED_CLK_GATE_SDCLKCLK] =	{ 27, 16, "sdclk-gate",		NULL,	0 }, /* SDIO/SD */
+	[ASPEED_CLK_GATE_SDCLK] =	{ 27, 16, "sdclk-gate",		NULL,	0 }, /* SDIO/SD */
 	[ASPEED_CLK_GATE_LHCCLK] =	{ 28, -1, "lhclk-gate",		"lhclk", 0 }, /* LPC master/LPC+ */
 };
 
diff --git a/include/dt-bindings/clock/aspeed-clock.h b/include/dt-bindings/clock/aspeed-clock.h
index 44761849fcbe..f43738607d77 100644
--- a/include/dt-bindings/clock/aspeed-clock.h
+++ b/include/dt-bindings/clock/aspeed-clock.h
@@ -25,7 +25,7 @@
 #define ASPEED_CLK_GATE_RSACLK		19
 #define ASPEED_CLK_GATE_UART3CLK	20
 #define ASPEED_CLK_GATE_UART4CLK	21
-#define ASPEED_CLK_GATE_SDCLKCLK	22
+#define ASPEED_CLK_GATE_SDCLK		22
 #define ASPEED_CLK_GATE_LHCCLK		23
 #define ASPEED_CLK_HPLL			24
 #define ASPEED_CLK_AHB			25
-- 
cgit v1.2.3


From 9d8108f9f3cb996a9677223fcd1feeb1f3e05566 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Fri, 22 Jun 2018 14:32:33 +0800
Subject: clk: imx6sll: add GPIO LPCGs

According to Reference Manual Rev.0, 06/2017, there are GPIO LPCGs
defined in CCM CCGRs, add them into clock tree.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6sll.c             | 6 ++++++
 include/dt-bindings/clock/imx6sll-clock.h | 9 ++++++++-
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/imx/clk-imx6sll.c b/drivers/clk/imx/clk-imx6sll.c
index 3651c77fbabe..627064597af9 100644
--- a/drivers/clk/imx/clk-imx6sll.c
+++ b/drivers/clk/imx/clk-imx6sll.c
@@ -253,6 +253,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SLL_CLK_DCP]		= imx_clk_gate2("dcp", "ahb", base + 0x68, 10);
 	clks[IMX6SLL_CLK_UART2_IPG]	= imx_clk_gate2("uart2_ipg", "ipg", base + 0x68, 28);
 	clks[IMX6SLL_CLK_UART2_SERIAL]	= imx_clk_gate2("uart2_serial",	"uart_podf", base + 0x68, 28);
+	clks[IMX6SLL_CLK_GPIO2]		= imx_clk_gate2("gpio2", "ipg", base + 0x68, 30);
 
 	/* CCGR1 */
 	clks[IMX6SLL_CLK_ECSPI1]	= imx_clk_gate2("ecspi1",	"ecspi_podf", base + 0x6c, 0);
@@ -267,13 +268,17 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SLL_CLK_GPT_SERIAL]	= imx_clk_gate2("gpt1_serial",	"perclk", base + 0x6c, 22);
 	clks[IMX6SLL_CLK_UART4_IPG]	= imx_clk_gate2("uart4_ipg",	"ipg", base + 0x6c, 24);
 	clks[IMX6SLL_CLK_UART4_SERIAL]	= imx_clk_gate2("uart4_serail",	"uart_podf", base + 0x6c, 24);
+	clks[IMX6SLL_CLK_GPIO1]		= imx_clk_gate2("gpio1",	"ipg", base + 0x6c, 26);
+	clks[IMX6SLL_CLK_GPIO5]		= imx_clk_gate2("gpio5",	"ipg", base + 0x6c, 30);
 
 	/* CCGR2 */
+	clks[IMX6SLL_CLK_GPIO6]		= imx_clk_gate2("gpio6",	"ipg",    base + 0x70, 0);
 	clks[IMX6SLL_CLK_CSI]		= imx_clk_gate2("csi",		"axi",    base + 0x70,	2);
 	clks[IMX6SLL_CLK_I2C1]		= imx_clk_gate2("i2c1",		"perclk", base + 0x70,	6);
 	clks[IMX6SLL_CLK_I2C2]		= imx_clk_gate2("i2c2",		"perclk", base + 0x70,	8);
 	clks[IMX6SLL_CLK_I2C3]		= imx_clk_gate2("i2c3",		"perclk", base + 0x70,	10);
 	clks[IMX6SLL_CLK_OCOTP]		= imx_clk_gate2("ocotp",	"ipg",    base + 0x70,	12);
+	clks[IMX6SLL_CLK_GPIO3]		= imx_clk_gate2("gpio3",	"ipg",    base + 0x70,	26);
 	clks[IMX6SLL_CLK_LCDIF_APB]	= imx_clk_gate2("lcdif_apb",	"axi",    base + 0x70,	28);
 	clks[IMX6SLL_CLK_PXP]		= imx_clk_gate2("pxp",		"axi",    base + 0x70,	30);
 
@@ -283,6 +288,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SLL_CLK_EPDC_AXI]	= imx_clk_gate2("epdc_aclk",	"axi",		base + 0x74, 4);
 	clks[IMX6SLL_CLK_EPDC_PIX]	= imx_clk_gate2("epdc_pix",	"epdc_podf",	base + 0x74, 4);
 	clks[IMX6SLL_CLK_LCDIF_PIX]	= imx_clk_gate2("lcdif_pix",	"lcdif_podf",	base + 0x74, 10);
+	clks[IMX6SLL_CLK_GPIO4]		= imx_clk_gate2("gpio4",	"ipg",		base + 0x74, 12);
 	clks[IMX6SLL_CLK_WDOG1]		= imx_clk_gate2("wdog1",	"ipg",		base + 0x74, 16);
 	clks[IMX6SLL_CLK_MMDC_P0_FAST]	= imx_clk_gate_flags("mmdc_p0_fast", "mmdc_podf",  base + 0x74,	20, CLK_IS_CRITICAL);
 	clks[IMX6SLL_CLK_MMDC_P0_IPG]	= imx_clk_gate2_flags("mmdc_p0_ipg", "ipg",	   base + 0x74,	24, CLK_IS_CRITICAL);
diff --git a/include/dt-bindings/clock/imx6sll-clock.h b/include/dt-bindings/clock/imx6sll-clock.h
index 151111e68f4f..1036475f997d 100644
--- a/include/dt-bindings/clock/imx6sll-clock.h
+++ b/include/dt-bindings/clock/imx6sll-clock.h
@@ -197,6 +197,13 @@
 #define IMX6SLL_CLK_EXTERN_AUDIO_PODF   171
 #define IMX6SLL_CLK_EXTERN_AUDIO        172
 
-#define IMX6SLL_CLK_END			173
+#define IMX6SLL_CLK_GPIO1               173
+#define IMX6SLL_CLK_GPIO2               174
+#define IMX6SLL_CLK_GPIO3               175
+#define IMX6SLL_CLK_GPIO4               176
+#define IMX6SLL_CLK_GPIO5               177
+#define IMX6SLL_CLK_GPIO6               178
+
+#define IMX6SLL_CLK_END			179
 
 #endif /* __DT_BINDINGS_CLOCK_IMX6SLL_H */
-- 
cgit v1.2.3


From ed235d556945f46dbac84227f6f1467d397e39a3 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Wed, 4 Jul 2018 10:49:23 -0300
Subject: clk: imx51-imx53: Annotate critical clocks as CLK_IS_CRITICAL

Instead of explicitly enabling critical clocks via clk_prepare_enable(),
let's use the standard CLK_IS_CRITICAL flag instead, which makes the code
a bit shorter.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx51-imx53.c | 43 +++++++++++++--------------------------
 1 file changed, 14 insertions(+), 29 deletions(-)

diff --git a/drivers/clk/imx/clk-imx51-imx53.c b/drivers/clk/imx/clk-imx51-imx53.c
index caa8bd40692c..346a53b48f9c 100644
--- a/drivers/clk/imx/clk-imx51-imx53.c
+++ b/drivers/clk/imx/clk-imx51-imx53.c
@@ -175,13 +175,13 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_PER_ROOT]		= imx_clk_mux("per_root", MXC_CCM_CBCMR, 0, 1,
 						per_root_sel, ARRAY_SIZE(per_root_sel));
 	clk[IMX5_CLK_AHB]		= imx_clk_divider("ahb", "main_bus", MXC_CCM_CBCDR, 10, 3);
-	clk[IMX5_CLK_AHB_MAX]		= imx_clk_gate2("ahb_max", "ahb", MXC_CCM_CCGR0, 28);
-	clk[IMX5_CLK_AIPS_TZ1]		= imx_clk_gate2("aips_tz1", "ahb", MXC_CCM_CCGR0, 24);
-	clk[IMX5_CLK_AIPS_TZ2]		= imx_clk_gate2("aips_tz2", "ahb", MXC_CCM_CCGR0, 26);
-	clk[IMX5_CLK_TMAX1]		= imx_clk_gate2("tmax1", "ahb", MXC_CCM_CCGR1, 0);
-	clk[IMX5_CLK_TMAX2]		= imx_clk_gate2("tmax2", "ahb", MXC_CCM_CCGR1, 2);
-	clk[IMX5_CLK_TMAX3]		= imx_clk_gate2("tmax3", "ahb", MXC_CCM_CCGR1, 4);
-	clk[IMX5_CLK_SPBA]		= imx_clk_gate2("spba", "ipg", MXC_CCM_CCGR5, 0);
+	clk[IMX5_CLK_AHB_MAX]		= imx_clk_gate2_flags("ahb_max", "ahb", MXC_CCM_CCGR0, 28, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_AIPS_TZ1]		= imx_clk_gate2_flags("aips_tz1", "ahb", MXC_CCM_CCGR0, 24, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_AIPS_TZ2]		= imx_clk_gate2_flags("aips_tz2", "ahb", MXC_CCM_CCGR0, 26, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_TMAX1]		= imx_clk_gate2_flags("tmax1", "ahb", MXC_CCM_CCGR1, 0, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_TMAX2]		= imx_clk_gate2_flags("tmax2", "ahb", MXC_CCM_CCGR1, 2, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_TMAX3]		= imx_clk_gate2_flags("tmax3", "ahb", MXC_CCM_CCGR1, 4, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_SPBA]		= imx_clk_gate2_flags("spba", "ipg", MXC_CCM_CCGR5, 0, CLK_IS_CRITICAL);
 	clk[IMX5_CLK_IPG]		= imx_clk_divider("ipg", "ahb", MXC_CCM_CBCDR, 8, 2);
 	clk[IMX5_CLK_AXI_A]		= imx_clk_divider("axi_a", "main_bus", MXC_CCM_CBCDR, 16, 3);
 	clk[IMX5_CLK_AXI_B]		= imx_clk_divider("axi_b", "main_bus", MXC_CCM_CBCDR, 19, 3);
@@ -252,8 +252,8 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_ECSPI2_PER_GATE]	= imx_clk_gate2("ecspi2_per_gate", "ecspi_podf", MXC_CCM_CCGR4, 24);
 	clk[IMX5_CLK_CSPI_IPG_GATE]	= imx_clk_gate2("cspi_ipg_gate", "ipg", MXC_CCM_CCGR4, 26);
 	clk[IMX5_CLK_SDMA_GATE]		= imx_clk_gate2("sdma_gate", "ipg", MXC_CCM_CCGR4, 30);
-	clk[IMX5_CLK_EMI_FAST_GATE]	= imx_clk_gate2("emi_fast_gate", "dummy", MXC_CCM_CCGR5, 14);
-	clk[IMX5_CLK_EMI_SLOW_GATE]	= imx_clk_gate2("emi_slow_gate", "emi_slow_podf", MXC_CCM_CCGR5, 16);
+	clk[IMX5_CLK_EMI_FAST_GATE]	= imx_clk_gate2_flags("emi_fast_gate", "dummy", MXC_CCM_CCGR5, 14, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_EMI_SLOW_GATE]	= imx_clk_gate2_flags("emi_slow_gate", "emi_slow_podf", MXC_CCM_CCGR5, 16, CLK_IS_CRITICAL);
 	clk[IMX5_CLK_IPU_SEL]		= imx_clk_mux("ipu_sel", MXC_CCM_CBCMR, 6, 2, ipu_sel, ARRAY_SIZE(ipu_sel));
 	clk[IMX5_CLK_IPU_GATE]		= imx_clk_gate2("ipu_gate", "ipu_sel", MXC_CCM_CCGR5, 10);
 	clk[IMX5_CLK_NFC_GATE]		= imx_clk_gate2("nfc_gate", "nfc_podf", MXC_CCM_CCGR5, 20);
@@ -267,7 +267,7 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 	clk[IMX5_CLK_VPU_SEL]		= imx_clk_mux("vpu_sel", MXC_CCM_CBCMR, 14, 2, vpu_sel, ARRAY_SIZE(vpu_sel));
 	clk[IMX5_CLK_VPU_GATE]		= imx_clk_gate2("vpu_gate", "vpu_sel", MXC_CCM_CCGR5, 6);
 	clk[IMX5_CLK_VPU_REFERENCE_GATE] = imx_clk_gate2("vpu_reference_gate", "osc", MXC_CCM_CCGR5, 8);
-	clk[IMX5_CLK_GPC_DVFS]		= imx_clk_gate2("gpc_dvfs", "dummy", MXC_CCM_CCGR5, 24);
+	clk[IMX5_CLK_GPC_DVFS]		= imx_clk_gate2_flags("gpc_dvfs", "dummy", MXC_CCM_CCGR5, 24, CLK_IS_CRITICAL);
 
 	clk[IMX5_CLK_SSI_APM]		= imx_clk_mux("ssi_apm", MXC_CCM_CSCMR1, 8, 2, ssi_apm_sels, ARRAY_SIZE(ssi_apm_sels));
 	clk[IMX5_CLK_SSI1_ROOT_SEL]	= imx_clk_mux("ssi1_root_sel", MXC_CCM_CSCMR1, 14, 2, ssi_clk_sels, ARRAY_SIZE(ssi_clk_sels));
@@ -316,21 +316,6 @@ static void __init mx5_clocks_common_init(void __iomem *ccm_base)
 
 	/* move usb phy clk to 24MHz */
 	clk_set_parent(clk[IMX5_CLK_USB_PHY_SEL], clk[IMX5_CLK_OSC]);
-
-	clk_prepare_enable(clk[IMX5_CLK_GPC_DVFS]);
-	clk_prepare_enable(clk[IMX5_CLK_AHB_MAX]); /* esdhc3 */
-	clk_prepare_enable(clk[IMX5_CLK_AIPS_TZ1]);
-	clk_prepare_enable(clk[IMX5_CLK_AIPS_TZ2]); /* fec */
-	clk_prepare_enable(clk[IMX5_CLK_SPBA]);
-	clk_prepare_enable(clk[IMX5_CLK_EMI_FAST_GATE]); /* fec */
-	clk_prepare_enable(clk[IMX5_CLK_EMI_SLOW_GATE]); /* eim */
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_HSC1_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_HSC2_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_ESC_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_MIPI_HSP_GATE]);
-	clk_prepare_enable(clk[IMX5_CLK_TMAX1]);
-	clk_prepare_enable(clk[IMX5_CLK_TMAX2]); /* esdhc2, fec */
-	clk_prepare_enable(clk[IMX5_CLK_TMAX3]); /* esdhc1, esdhc4 */
 }
 
 static void __init mx50_clocks_init(struct device_node *np)
@@ -442,10 +427,10 @@ static void __init mx51_clocks_init(struct device_node *np)
 	clk[IMX5_CLK_ESDHC4_PER_GATE]	= imx_clk_gate2("esdhc4_per_gate", "esdhc_d_sel", MXC_CCM_CCGR3, 14);
 	clk[IMX5_CLK_USB_PHY_GATE]	= imx_clk_gate2("usb_phy_gate", "usb_phy_sel", MXC_CCM_CCGR2, 0);
 	clk[IMX5_CLK_HSI2C_GATE]	= imx_clk_gate2("hsi2c_gate", "ipg", MXC_CCM_CCGR1, 22);
-	clk[IMX5_CLK_MIPI_HSC1_GATE]	= imx_clk_gate2("mipi_hsc1_gate", "ipg", MXC_CCM_CCGR4, 6);
-	clk[IMX5_CLK_MIPI_HSC2_GATE]	= imx_clk_gate2("mipi_hsc2_gate", "ipg", MXC_CCM_CCGR4, 8);
-	clk[IMX5_CLK_MIPI_ESC_GATE]	= imx_clk_gate2("mipi_esc_gate", "ipg", MXC_CCM_CCGR4, 10);
-	clk[IMX5_CLK_MIPI_HSP_GATE]	= imx_clk_gate2("mipi_hsp_gate", "ipg", MXC_CCM_CCGR4, 12);
+	clk[IMX5_CLK_MIPI_HSC1_GATE]	= imx_clk_gate2_flags("mipi_hsc1_gate", "ipg", MXC_CCM_CCGR4, 6, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_MIPI_HSC2_GATE]	= imx_clk_gate2_flags("mipi_hsc2_gate", "ipg", MXC_CCM_CCGR4, 8, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_MIPI_ESC_GATE]	= imx_clk_gate2_flags("mipi_esc_gate", "ipg", MXC_CCM_CCGR4, 10, CLK_IS_CRITICAL);
+	clk[IMX5_CLK_MIPI_HSP_GATE]	= imx_clk_gate2_flags("mipi_hsp_gate", "ipg", MXC_CCM_CCGR4, 12, CLK_IS_CRITICAL);
 	clk[IMX5_CLK_SPDIF_XTAL_SEL]	= imx_clk_mux("spdif_xtal_sel", MXC_CCM_CSCMR1, 2, 2,
 						mx51_spdif_xtal_sel, ARRAY_SIZE(mx51_spdif_xtal_sel));
 	clk[IMX5_CLK_SPDIF1_SEL]	= imx_clk_mux("spdif1_sel", MXC_CCM_CSCMR2, 2, 2,
-- 
cgit v1.2.3


From d0897bc85ca89d5ddc6c2fcf2f99e04d4a577b63 Mon Sep 17 00:00:00 2001
From: Stephen Boyd <sboyd@kernel.org>
Date: Fri, 6 Jul 2018 14:08:04 -0700
Subject: clk: imx51-imx53: Include sizes.h to silence compile errors

This driver uses sizes.h, but relies on it being implicitly included
somewhere else breaking random direct compilation of the file. Include
sizes.h so we can build it those configurations too for better compile
coverage.

Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx51-imx53.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/imx/clk-imx51-imx53.c b/drivers/clk/imx/clk-imx51-imx53.c
index 346a53b48f9c..fc8e782d817b 100644
--- a/drivers/clk/imx/clk-imx51-imx53.c
+++ b/drivers/clk/imx/clk-imx51-imx53.c
@@ -16,6 +16,7 @@
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
+#include <linux/sizes.h>
 #include <soc/imx/revision.h>
 #include <dt-bindings/clock/imx5-clock.h>
 
-- 
cgit v1.2.3


From 07e070e1e3b24e4b66a3b5e55e6486d7fe9769dd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 21:59:47 +0100
Subject: drm/i915/selftests: Avoid warning if runtime pm is disabled

Inside the mock GEM device, we try to grab the runtime pm for the fake
device to prevent it from ever suspending. However, if CONFIG_PM is not
set, trying to obtain the wakref returns an error which we WARN about.
Suppress the expected warning.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706205947.11209-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/mock_gem_device.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index c97075c5ccaf..43ed8b28aeaa 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -157,7 +157,8 @@ struct drm_i915_private *mock_gem_device(void)
 	dev_pm_domain_set(&pdev->dev, &pm_domain);
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
-	WARN_ON(pm_runtime_get_sync(&pdev->dev));
+	if (pm_runtime_enabled(&pdev->dev))
+		WARN_ON(pm_runtime_get_sync(&pdev->dev));
 
 	i915 = (struct drm_i915_private *)(pdev + 1);
 	pci_set_drvdata(pdev, i915);
-- 
cgit v1.2.3


From 2058b38371d0dbd84831a085db64b996d623f81a Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 6 Jul 2018 14:28:14 -0700
Subject: bpftool: introduce cgroup tree command

This commit introduces a new bpftool command: cgroup tree.
The idea is to iterate over the whole cgroup tree and print
all attached programs.

I was debugging a bpf/systemd issue, and found, that there is
no simple way to listen all bpf programs attached to cgroups.
I did master something in bash, but after some time got tired of it,
and decided, that adding a dedicated bpftool command could be
a better idea.

So, here it is:
  $ sudo ./bpftool cgroup tree
  CgroupPath
  ID       AttachType      AttachFlags     Name
  /sys/fs/cgroup/system.slice/systemd-machined.service
      18       ingress
      17       egress
  /sys/fs/cgroup/system.slice/systemd-logind.service
      20       ingress
      19       egress
  /sys/fs/cgroup/system.slice/systemd-udevd.service
      16       ingress
      15       egress
  /sys/fs/cgroup/system.slice/systemd-journald.service
      14       ingress
      13       egress

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Quentin Monnet <quentin.monnet@netronome.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/cgroup.c | 170 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 165 insertions(+), 5 deletions(-)

diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c
index 16bee011e16c..ee7a9765c6b3 100644
--- a/tools/bpf/bpftool/cgroup.c
+++ b/tools/bpf/bpftool/cgroup.c
@@ -2,7 +2,12 @@
 // Copyright (C) 2017 Facebook
 // Author: Roman Gushchin <guro@fb.com>
 
+#define _XOPEN_SOURCE 500
+#include <errno.h>
 #include <fcntl.h>
+#include <ftw.h>
+#include <mntent.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/stat.h>
@@ -53,7 +58,8 @@ static enum bpf_attach_type parse_attach_type(const char *str)
 }
 
 static int show_bpf_prog(int id, const char *attach_type_str,
-			 const char *attach_flags_str)
+			 const char *attach_flags_str,
+			 int level)
 {
 	struct bpf_prog_info info = {};
 	__u32 info_len = sizeof(info);
@@ -78,7 +84,8 @@ static int show_bpf_prog(int id, const char *attach_type_str,
 		jsonw_string_field(json_wtr, "name", info.name);
 		jsonw_end_object(json_wtr);
 	} else {
-		printf("%-8u %-15s %-15s %-15s\n", info.id,
+		printf("%s%-8u %-15s %-15s %-15s\n", level ? "    " : "",
+		       info.id,
 		       attach_type_str,
 		       attach_flags_str,
 		       info.name);
@@ -88,7 +95,20 @@ static int show_bpf_prog(int id, const char *attach_type_str,
 	return 0;
 }
 
-static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+static int count_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
+{
+	__u32 prog_cnt = 0;
+	int ret;
+
+	ret = bpf_prog_query(cgroup_fd, type, 0, NULL, NULL, &prog_cnt);
+	if (ret)
+		return -1;
+
+	return prog_cnt;
+}
+
+static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type,
+				   int level)
 {
 	__u32 prog_ids[1024] = {0};
 	char *attach_flags_str;
@@ -123,7 +143,7 @@ static int show_attached_bpf_progs(int cgroup_fd, enum bpf_attach_type type)
 
 	for (iter = 0; iter < prog_cnt; iter++)
 		show_bpf_prog(prog_ids[iter], attach_type_strings[type],
-			      attach_flags_str);
+			      attach_flags_str, level);
 
 	return 0;
 }
@@ -161,7 +181,7 @@ static int do_show(int argc, char **argv)
 		 * If we were able to get the show for at least one
 		 * attach type, let's return 0.
 		 */
-		if (show_attached_bpf_progs(cgroup_fd, type) == 0)
+		if (show_attached_bpf_progs(cgroup_fd, type, 0) == 0)
 			ret = 0;
 	}
 
@@ -173,6 +193,143 @@ exit:
 	return ret;
 }
 
+/*
+ * To distinguish nftw() errors and do_show_tree_fn() errors
+ * and avoid duplicating error messages, let's return -2
+ * from do_show_tree_fn() in case of error.
+ */
+#define NFTW_ERR		-1
+#define SHOW_TREE_FN_ERR	-2
+static int do_show_tree_fn(const char *fpath, const struct stat *sb,
+			   int typeflag, struct FTW *ftw)
+{
+	enum bpf_attach_type type;
+	bool skip = true;
+	int cgroup_fd;
+
+	if (typeflag != FTW_D)
+		return 0;
+
+	cgroup_fd = open(fpath, O_RDONLY);
+	if (cgroup_fd < 0) {
+		p_err("can't open cgroup %s: %s", fpath, strerror(errno));
+		return SHOW_TREE_FN_ERR;
+	}
+
+	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++) {
+		int count = count_attached_bpf_progs(cgroup_fd, type);
+
+		if (count < 0 && errno != EINVAL) {
+			p_err("can't query bpf programs attached to %s: %s",
+			      fpath, strerror(errno));
+			close(cgroup_fd);
+			return SHOW_TREE_FN_ERR;
+		}
+		if (count > 0) {
+			skip = false;
+			break;
+		}
+	}
+
+	if (skip) {
+		close(cgroup_fd);
+		return 0;
+	}
+
+	if (json_output) {
+		jsonw_start_object(json_wtr);
+		jsonw_string_field(json_wtr, "cgroup", fpath);
+		jsonw_name(json_wtr, "programs");
+		jsonw_start_array(json_wtr);
+	} else {
+		printf("%s\n", fpath);
+	}
+
+	for (type = 0; type < __MAX_BPF_ATTACH_TYPE; type++)
+		show_attached_bpf_progs(cgroup_fd, type, ftw->level);
+
+	if (json_output) {
+		jsonw_end_array(json_wtr);
+		jsonw_end_object(json_wtr);
+	}
+
+	close(cgroup_fd);
+
+	return 0;
+}
+
+static char *find_cgroup_root(void)
+{
+	struct mntent *mnt;
+	FILE *f;
+
+	f = fopen("/proc/mounts", "r");
+	if (f == NULL)
+		return NULL;
+
+	while ((mnt = getmntent(f))) {
+		if (strcmp(mnt->mnt_type, "cgroup2") == 0) {
+			fclose(f);
+			return strdup(mnt->mnt_dir);
+		}
+	}
+
+	fclose(f);
+	return NULL;
+}
+
+static int do_show_tree(int argc, char **argv)
+{
+	char *cgroup_root;
+	int ret;
+
+	switch (argc) {
+	case 0:
+		cgroup_root = find_cgroup_root();
+		if (!cgroup_root) {
+			p_err("cgroup v2 isn't mounted");
+			return -1;
+		}
+		break;
+	case 1:
+		cgroup_root = argv[0];
+		break;
+	default:
+		p_err("too many parameters for cgroup tree");
+		return -1;
+	}
+
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	else
+		printf("%s\n"
+		       "%-8s %-15s %-15s %-15s\n",
+		       "CgroupPath",
+		       "ID", "AttachType", "AttachFlags", "Name");
+
+	switch (nftw(cgroup_root, do_show_tree_fn, 1024, FTW_MOUNT)) {
+	case NFTW_ERR:
+		p_err("can't iterate over %s: %s", cgroup_root,
+		      strerror(errno));
+		ret = -1;
+		break;
+	case SHOW_TREE_FN_ERR:
+		ret = -1;
+		break;
+	default:
+		ret = 0;
+	}
+
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	if (argc == 0)
+		free(cgroup_root);
+
+	return ret;
+}
+
 static int do_attach(int argc, char **argv)
 {
 	enum bpf_attach_type attach_type;
@@ -289,6 +446,7 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %s %s { show | list } CGROUP\n"
+		"       %s %s tree [CGROUP_ROOT]\n"
 		"       %s %s attach CGROUP ATTACH_TYPE PROG [ATTACH_FLAGS]\n"
 		"       %s %s detach CGROUP ATTACH_TYPE PROG\n"
 		"       %s %s help\n"
@@ -298,6 +456,7 @@ static int do_help(int argc, char **argv)
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
+		bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2],
 		bin_name, argv[-2], bin_name, argv[-2]);
 
@@ -307,6 +466,7 @@ static int do_help(int argc, char **argv)
 static const struct cmd cmds[] = {
 	{ "show",	do_show },
 	{ "list",	do_show },
+	{ "tree",       do_show_tree },
 	{ "attach",	do_attach },
 	{ "detach",	do_detach },
 	{ "help",	do_help },
-- 
cgit v1.2.3


From 7d31a0a168979e671e25073c492c29c42610e7e2 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 6 Jul 2018 14:28:15 -0700
Subject: bpftool: document cgroup tree command

Describe cgroup tree command in the corresponding bpftool man page.

Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Quentin Monnet <quentin.monnet@netronome.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-cgroup.rst | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
index 7b0e6d453e92..edbe81534c6d 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst
@@ -15,12 +15,13 @@ SYNOPSIS
 	*OPTIONS* := { { **-j** | **--json** } [{ **-p** | **--pretty** }] | { **-f** | **--bpffs** } }
 
 	*COMMANDS* :=
-	{ **show** | **list** | **attach** | **detach** | **help** }
+	{ **show** | **list** | **tree** | **attach** | **detach** | **help** }
 
 MAP COMMANDS
 =============
 
 |	**bpftool** **cgroup { show | list }** *CGROUP*
+|	**bpftool** **cgroup tree** [*CGROUP_ROOT*]
 |	**bpftool** **cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
 |	**bpftool** **cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG*
 |	**bpftool** **cgroup help**
@@ -39,6 +40,15 @@ DESCRIPTION
 		  Output will start with program ID followed by attach type,
 		  attach flags and program name.
 
+	**bpftool cgroup tree** [*CGROUP_ROOT*]
+		  Iterate over all cgroups in *CGROUP_ROOT* and list all
+		  attached programs. If *CGROUP_ROOT* is not specified,
+		  bpftool uses cgroup v2 mountpoint.
+
+		  The output is similar to the output of cgroup show/list
+		  commands: it starts with absolute cgroup path, followed by
+		  program ID, attach type, attach flags and program name.
+
 	**bpftool cgroup attach** *CGROUP* *ATTACH_TYPE* *PROG* [*ATTACH_FLAGS*]
 		  Attach program *PROG* to the cgroup *CGROUP* with attach type
 		  *ATTACH_TYPE* and optional *ATTACH_FLAGS*.
-- 
cgit v1.2.3


From 02000b55850deeadffe433e4b4930a8831f477de Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 6 Jul 2018 14:28:16 -0700
Subject: bpftool: add bash completion for cgroup tree command

This commit adds a bash completion to the bpftool cgroup tree
command.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Jakub Kicinski <jakub.kicinski@netronome.com>
Cc: Quentin Monnet <quentin.monnet@netronome.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/bash-completion/bpftool | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index fffd76f4998b..ce0bc0cda361 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -414,6 +414,10 @@ _bpftool()
                     _filedir
                     return 0
                     ;;
+		tree)
+		    _filedir
+		    return 0
+		    ;;
                 attach|detach)
                     local ATTACH_TYPES='ingress egress sock_create sock_ops \
                         device bind4 bind6 post_bind4 post_bind6 connect4 \
@@ -455,7 +459,7 @@ _bpftool()
                 *)
                     [[ $prev == $object ]] && \
                         COMPREPLY=( $( compgen -W 'help attach detach \
-                            show list' -- "$cur" ) )
+                            show list tree' -- "$cur" ) )
                     ;;
             esac
             ;;
-- 
cgit v1.2.3


From 06ae48269d1e0324d806fca30fe77112f4a4a14a Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Fri, 6 Jul 2018 15:13:18 -0700
Subject: lib: reciprocal_div: implement the improved algorithm on the paper
 mentioned

The new added "reciprocal_value_adv" implements the advanced version of the
algorithm described in Figure 4.2 of the paper except when
"divisor > (1U << 31)" whose ceil(log2(d)) result will be 32 which then
requires u128 divide on host. The exception case could be easily handled
before calling "reciprocal_value_adv".

The advanced version requires more complex calculation to get the
reciprocal multiplier and other control variables, but then could reduce
the required emulation operations.

It makes no sense to use this advanced version for host divide emulation,
those extra complexities for calculating multiplier etc could completely
waive our saving on emulation operations.

However, it makes sense to use it for JIT divide code generation (for
example eBPF JIT backends) for which we are willing to trade performance of
JITed code with that of host. As shown by the following pseudo code, the
required emulation operations could go down from 6 (the basic version) to 3
or 4.

To use the result of "reciprocal_value_adv", suppose we want to calculate
n/d, the C-style pseudo code will be the following, it could be easily
changed to real code generation for other JIT targets.

  struct reciprocal_value_adv rvalue;
  u8 pre_shift, exp;

  // handle exception case.
  if (d >= (1U << 31)) {
    result = n >= d;
    return;
  }
  rvalue = reciprocal_value_adv(d, 32)
  exp = rvalue.exp;
  if (rvalue.is_wide_m && !(d & 1)) {
    // floor(log2(d & (2^32 -d)))
    pre_shift = fls(d & -d) - 1;
    rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift);
  } else {
    pre_shift = 0;
  }

  // code generation starts.
  if (imm == 1U << exp) {
    result = n >> exp;
  } else if (rvalue.is_wide_m) {
    // pre_shift must be zero when reached here.
    t = (n * rvalue.m) >> 32;
    result = n - t;
    result >>= 1;
    result += t;
    result >>= rvalue.sh - 1;
  } else {
    if (pre_shift)
      result = n >> pre_shift;
    result = ((u64)result * rvalue.m) >> 32;
    result >>= rvalue.sh;
  }

Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/reciprocal_div.h | 68 ++++++++++++++++++++++++++++++++++++++++++
 lib/reciprocal_div.c           | 41 +++++++++++++++++++++++++
 2 files changed, 109 insertions(+)

diff --git a/include/linux/reciprocal_div.h b/include/linux/reciprocal_div.h
index e031e9f2f9d8..585ce89c0f33 100644
--- a/include/linux/reciprocal_div.h
+++ b/include/linux/reciprocal_div.h
@@ -25,6 +25,9 @@ struct reciprocal_value {
 	u8 sh1, sh2;
 };
 
+/* "reciprocal_value" and "reciprocal_divide" together implement the basic
+ * version of the algorithm described in Figure 4.1 of the paper.
+ */
 struct reciprocal_value reciprocal_value(u32 d);
 
 static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R)
@@ -33,4 +36,69 @@ static inline u32 reciprocal_divide(u32 a, struct reciprocal_value R)
 	return (t + ((a - t) >> R.sh1)) >> R.sh2;
 }
 
+struct reciprocal_value_adv {
+	u32 m;
+	u8 sh, exp;
+	bool is_wide_m;
+};
+
+/* "reciprocal_value_adv" implements the advanced version of the algorithm
+ * described in Figure 4.2 of the paper except when "divisor > (1U << 31)" whose
+ * ceil(log2(d)) result will be 32 which then requires u128 divide on host. The
+ * exception case could be easily handled before calling "reciprocal_value_adv".
+ *
+ * The advanced version requires more complex calculation to get the reciprocal
+ * multiplier and other control variables, but then could reduce the required
+ * emulation operations.
+ *
+ * It makes no sense to use this advanced version for host divide emulation,
+ * those extra complexities for calculating multiplier etc could completely
+ * waive our saving on emulation operations.
+ *
+ * However, it makes sense to use it for JIT divide code generation for which
+ * we are willing to trade performance of JITed code with that of host. As shown
+ * by the following pseudo code, the required emulation operations could go down
+ * from 6 (the basic version) to 3 or 4.
+ *
+ * To use the result of "reciprocal_value_adv", suppose we want to calculate
+ * n/d, the pseudo C code will be:
+ *
+ *   struct reciprocal_value_adv rvalue;
+ *   u8 pre_shift, exp;
+ *
+ *   // handle exception case.
+ *   if (d >= (1U << 31)) {
+ *     result = n >= d;
+ *     return;
+ *   }
+ *
+ *   rvalue = reciprocal_value_adv(d, 32)
+ *   exp = rvalue.exp;
+ *   if (rvalue.is_wide_m && !(d & 1)) {
+ *     // floor(log2(d & (2^32 -d)))
+ *     pre_shift = fls(d & -d) - 1;
+ *     rvalue = reciprocal_value_adv(d >> pre_shift, 32 - pre_shift);
+ *   } else {
+ *     pre_shift = 0;
+ *   }
+ *
+ *   // code generation starts.
+ *   if (imm == 1U << exp) {
+ *     result = n >> exp;
+ *   } else if (rvalue.is_wide_m) {
+ *     // pre_shift must be zero when reached here.
+ *     t = (n * rvalue.m) >> 32;
+ *     result = n - t;
+ *     result >>= 1;
+ *     result += t;
+ *     result >>= rvalue.sh - 1;
+ *   } else {
+ *     if (pre_shift)
+ *       result = n >> pre_shift;
+ *     result = ((u64)result * rvalue.m) >> 32;
+ *     result >>= rvalue.sh;
+ *   }
+ */
+struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec);
+
 #endif /* _LINUX_RECIPROCAL_DIV_H */
diff --git a/lib/reciprocal_div.c b/lib/reciprocal_div.c
index fcb4ce682c6f..bf043258fa00 100644
--- a/lib/reciprocal_div.c
+++ b/lib/reciprocal_div.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <asm/div64.h>
 #include <linux/reciprocal_div.h>
@@ -26,3 +27,43 @@ struct reciprocal_value reciprocal_value(u32 d)
 	return R;
 }
 EXPORT_SYMBOL(reciprocal_value);
+
+struct reciprocal_value_adv reciprocal_value_adv(u32 d, u8 prec)
+{
+	struct reciprocal_value_adv R;
+	u32 l, post_shift;
+	u64 mhigh, mlow;
+
+	/* ceil(log2(d)) */
+	l = fls(d - 1);
+	/* NOTE: mlow/mhigh could overflow u64 when l == 32. This case needs to
+	 * be handled before calling "reciprocal_value_adv", please see the
+	 * comment at include/linux/reciprocal_div.h.
+	 */
+	WARN(l == 32,
+	     "ceil(log2(0x%08x)) == 32, %s doesn't support such divisor",
+	     d, __func__);
+	post_shift = l;
+	mlow = 1ULL << (32 + l);
+	do_div(mlow, d);
+	mhigh = (1ULL << (32 + l)) + (1ULL << (32 + l - prec));
+	do_div(mhigh, d);
+
+	for (; post_shift > 0; post_shift--) {
+		u64 lo = mlow >> 1, hi = mhigh >> 1;
+
+		if (lo >= hi)
+			break;
+
+		mlow = lo;
+		mhigh = hi;
+	}
+
+	R.m = (u32)mhigh;
+	R.sh = post_shift;
+	R.exp = l;
+	R.is_wide_m = mhigh > U32_MAX;
+
+	return R;
+}
+EXPORT_SYMBOL(reciprocal_value_adv);
-- 
cgit v1.2.3


From 662c54721d3a1e8950029cb6b0ed264d59847711 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Fri, 6 Jul 2018 15:13:19 -0700
Subject: nfp: bpf: rename umin/umax to umin_src/umax_src

The two fields are a copy of umin and umax info of bpf_insn->src_reg
generated by verifier.

Rename to make their meaning clear.

Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c      | 12 ++++++------
 drivers/net/ethernet/netronome/nfp/bpf/main.h     | 10 +++++-----
 drivers/net/ethernet/netronome/nfp/bpf/offload.c  |  2 +-
 drivers/net/ethernet/netronome/nfp/bpf/verifier.c |  4 ++--
 4 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 33111739b210..4a629e9b5c0f 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1772,8 +1772,8 @@ static int shl_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shl_imm64(nfp_prog, dst, umin);
 
@@ -1881,8 +1881,8 @@ static int shr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __shr_imm64(nfp_prog, dst, umin);
 
@@ -1995,8 +1995,8 @@ static int ashr_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	u8 dst, src;
 
 	dst = insn->dst_reg * 2;
-	umin = meta->umin;
-	umax = meta->umax;
+	umin = meta->umin_src;
+	umax = meta->umax_src;
 	if (umin == umax)
 		return __ashr_imm64(nfp_prog, dst, umin);
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 654fe7823e5e..5975a19c28cb 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -263,8 +263,8 @@ struct nfp_bpf_reg_state {
  * @func_id: function id for call instructions
  * @arg1: arg1 for call instructions
  * @arg2: arg2 for call instructions
- * @umin: copy of core verifier umin_value.
- * @umax: copy of core verifier umax_value.
+ * @umin_src: copy of core verifier umin_value for src opearnd.
+ * @umax_src: copy of core verifier umax_value for src operand.
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
@@ -301,11 +301,11 @@ struct nfp_insn_meta {
 			struct nfp_bpf_reg_state arg2;
 		};
 		/* We are interested in range info for some operands,
-		 * for example, the shift amount.
+		 * for example, the shift amount which is kept in src operand.
 		 */
 		struct {
-			u64 umin;
-			u64 umax;
+			u64 umin_src;
+			u64 umax_src;
 		};
 	};
 	unsigned int off;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 7eae4c0266f8..856a0003bb75 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -191,7 +191,7 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 		meta->insn = prog[i];
 		meta->n = i;
 		if (is_mbpf_indir_shift(meta))
-			meta->umin = U64_MAX;
+			meta->umin_src = U64_MAX;
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 4bfeba7b21b2..e862b739441f 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -555,8 +555,8 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 		const struct bpf_reg_state *sreg =
 			cur_regs(env) + meta->insn.src_reg;
 
-		meta->umin = min(meta->umin, sreg->umin_value);
-		meta->umax = max(meta->umax, sreg->umax_value);
+		meta->umin_src = min(meta->umin_src, sreg->umin_value);
+		meta->umax_src = max(meta->umax_src, sreg->umax_value);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 33b94310586b761fd04de0ef951d2f5d764b9b2a Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Fri, 6 Jul 2018 15:13:20 -0700
Subject: nfp: bpf: copy range info for all operands of all ALU operations

NFP verifier hook is coping range information of the shift amount for
indirect shift operation so optimized shift sequences could be generated.

We want to use range info to do more things. For example, to decide whether
multiplication and divide are supported on the given range.

This patch simply let NFP verifier hook to copy range info for all operands
of all ALU operands.

Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.h     | 33 +++++++++--------------
 drivers/net/ethernet/netronome/nfp/bpf/offload.c  |  4 ++-
 drivers/net/ethernet/netronome/nfp/bpf/verifier.c |  6 ++++-
 3 files changed, 20 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 5975a19c28cb..c985d0ac61a3 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -265,6 +265,8 @@ struct nfp_bpf_reg_state {
  * @arg2: arg2 for call instructions
  * @umin_src: copy of core verifier umin_value for src opearnd.
  * @umax_src: copy of core verifier umax_value for src operand.
+ * @umin_dst: copy of core verifier umin_value for dst opearnd.
+ * @umax_dst: copy of core verifier umax_value for dst operand.
  * @off: index of first generated machine instruction (in nfp_prog.prog)
  * @n: eBPF instruction number
  * @flags: eBPF instruction extra optimization flags
@@ -300,12 +302,15 @@ struct nfp_insn_meta {
 			struct bpf_reg_state arg1;
 			struct nfp_bpf_reg_state arg2;
 		};
-		/* We are interested in range info for some operands,
-		 * for example, the shift amount which is kept in src operand.
+		/* We are interested in range info for operands of ALU
+		 * operations. For example, shift amount, multiplicand and
+		 * multiplier etc.
 		 */
 		struct {
 			u64 umin_src;
 			u64 umax_src;
+			u64 umin_dst;
+			u64 umax_dst;
 		};
 	};
 	unsigned int off;
@@ -339,6 +344,11 @@ static inline u8 mbpf_mode(const struct nfp_insn_meta *meta)
 	return BPF_MODE(meta->insn.code);
 }
 
+static inline bool is_mbpf_alu(const struct nfp_insn_meta *meta)
+{
+	return mbpf_class(meta) == BPF_ALU64 || mbpf_class(meta) == BPF_ALU;
+}
+
 static inline bool is_mbpf_load(const struct nfp_insn_meta *meta)
 {
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_LDX | BPF_MEM);
@@ -384,25 +394,6 @@ static inline bool is_mbpf_xadd(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_XADD);
 }
 
-static inline bool is_mbpf_indir_shift(const struct nfp_insn_meta *meta)
-{
-	u8 code = meta->insn.code;
-	bool is_alu, is_shift;
-	u8 opclass, opcode;
-
-	opclass = BPF_CLASS(code);
-	is_alu = opclass == BPF_ALU64 || opclass == BPF_ALU;
-	if (!is_alu)
-		return false;
-
-	opcode = BPF_OP(code);
-	is_shift = opcode == BPF_LSH || opcode == BPF_RSH || opcode == BPF_ARSH;
-	if (!is_shift)
-		return false;
-
-	return BPF_SRC(code) == BPF_X;
-}
-
 /**
  * struct nfp_prog - nfp BPF program
  * @bpf: backpointer to the bpf app priv structure
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 856a0003bb75..78f44c4d95b4 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -190,8 +190,10 @@ nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog,
 
 		meta->insn = prog[i];
 		meta->n = i;
-		if (is_mbpf_indir_shift(meta))
+		if (is_mbpf_alu(meta)) {
 			meta->umin_src = U64_MAX;
+			meta->umin_dst = U64_MAX;
+		}
 
 		list_add_tail(&meta->l, &nfp_prog->insns);
 	}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index e862b739441f..7bd9666bd8ff 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -551,12 +551,16 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 	if (is_mbpf_xadd(meta))
 		return nfp_bpf_check_xadd(nfp_prog, meta, env);
 
-	if (is_mbpf_indir_shift(meta)) {
+	if (is_mbpf_alu(meta)) {
 		const struct bpf_reg_state *sreg =
 			cur_regs(env) + meta->insn.src_reg;
+		const struct bpf_reg_state *dreg =
+			cur_regs(env) + meta->insn.dst_reg;
 
 		meta->umin_src = min(meta->umin_src, sreg->umin_value);
 		meta->umax_src = max(meta->umax_src, sreg->umax_value);
+		meta->umin_dst = min(meta->umin_dst, dreg->umin_value);
+		meta->umax_dst = max(meta->umax_dst, dreg->umax_value);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From d3d23fdb4688de4421e94227c95b1d54b233f432 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Fri, 6 Jul 2018 15:13:21 -0700
Subject: nfp: bpf: support u16 and u32 multiplications

NFP supports u16 and u32 multiplication. Multiplication is done 8-bits per
step, therefore we need 2 steps for u16 and 4 steps for u32.

We also need one start instruction to initialize the sequence and one or
two instructions to fetch the result depending on either you need the high
halve of u32 multiplication.

For ALU64, if either operand is beyond u32's value range, we reject it. One
thing to note, if the source operand is BPF_K, then we need to check "imm"
field directly, and we'd reject it if it is negative.  Because for ALU64,
"imm" (with s32 type) is expected to be sign extended to s64 which NFP mul
doesn't support. For ALU32, it is fine for "imm" be negative though,
because the result is 32-bits and here is no difference on the low halve
of result for signed/unsigned mul, so we will get correct result.

Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c      | 137 ++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/bpf/main.h     |   5 +
 drivers/net/ethernet/netronome/nfp/bpf/verifier.c |  58 +++++++--
 drivers/net/ethernet/netronome/nfp/nfp_asm.h      |  28 +++++
 4 files changed, 217 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 4a629e9b5c0f..f1b27c3a4347 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -415,6 +415,60 @@ emit_alu(struct nfp_prog *nfp_prog, swreg dst,
 		   reg.dst_lmextn, reg.src_lmextn);
 }
 
+static void
+__emit_mul(struct nfp_prog *nfp_prog, enum alu_dst_ab dst_ab, u16 areg,
+	   enum mul_type type, enum mul_step step, u16 breg, bool swap,
+	   bool wr_both, bool dst_lmextn, bool src_lmextn)
+{
+	u64 insn;
+
+	insn = OP_MUL_BASE |
+		FIELD_PREP(OP_MUL_A_SRC, areg) |
+		FIELD_PREP(OP_MUL_B_SRC, breg) |
+		FIELD_PREP(OP_MUL_STEP, step) |
+		FIELD_PREP(OP_MUL_DST_AB, dst_ab) |
+		FIELD_PREP(OP_MUL_SW, swap) |
+		FIELD_PREP(OP_MUL_TYPE, type) |
+		FIELD_PREP(OP_MUL_WR_AB, wr_both) |
+		FIELD_PREP(OP_MUL_SRC_LMEXTN, src_lmextn) |
+		FIELD_PREP(OP_MUL_DST_LMEXTN, dst_lmextn);
+
+	nfp_prog_push(nfp_prog, insn);
+}
+
+static void
+emit_mul(struct nfp_prog *nfp_prog, swreg lreg, enum mul_type type,
+	 enum mul_step step, swreg rreg)
+{
+	struct nfp_insn_ur_regs reg;
+	u16 areg;
+	int err;
+
+	if (type == MUL_TYPE_START && step != MUL_STEP_NONE) {
+		nfp_prog->error = -EINVAL;
+		return;
+	}
+
+	if (step == MUL_LAST || step == MUL_LAST_2) {
+		/* When type is step and step Number is LAST or LAST2, left
+		 * source is used as destination.
+		 */
+		err = swreg_to_unrestricted(lreg, reg_none(), rreg, &reg);
+		areg = reg.dst;
+	} else {
+		err = swreg_to_unrestricted(reg_none(), lreg, rreg, &reg);
+		areg = reg.areg;
+	}
+
+	if (err) {
+		nfp_prog->error = err;
+		return;
+	}
+
+	__emit_mul(nfp_prog, reg.dst_ab, areg, type, step, reg.breg, reg.swap,
+		   reg.wr_both, reg.dst_lmextn, reg.src_lmextn);
+}
+
 static void
 __emit_ld_field(struct nfp_prog *nfp_prog, enum shf_sc sc,
 		u8 areg, u8 bmask, u8 breg, u8 shift, bool imm8,
@@ -1380,6 +1434,65 @@ static void wrp_end32(struct nfp_prog *nfp_prog, swreg reg_in, u8 gpr_out)
 		      SHF_SC_R_ROT, 16);
 }
 
+static void
+wrp_mul_u32(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg, bool gen_high_half)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_3, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_32x32, MUL_STEP_4, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_32x32, MUL_LAST, reg_none());
+	if (gen_high_half)
+		emit_mul(nfp_prog, dst_hi, MUL_TYPE_STEP_32x32, MUL_LAST_2,
+			 reg_none());
+	else
+		wrp_immed(nfp_prog, dst_hi, 0);
+}
+
+static void
+wrp_mul_u16(struct nfp_prog *nfp_prog, swreg dst_hi, swreg dst_lo, swreg lreg,
+	    swreg rreg)
+{
+	emit_mul(nfp_prog, lreg, MUL_TYPE_START, MUL_STEP_NONE, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_1, rreg);
+	emit_mul(nfp_prog, lreg, MUL_TYPE_STEP_16x16, MUL_STEP_2, rreg);
+	emit_mul(nfp_prog, dst_lo, MUL_TYPE_STEP_16x16, MUL_LAST, reg_none());
+}
+
+static int
+wrp_mul(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+	bool gen_high_half, bool ropnd_from_reg)
+{
+	swreg multiplier, multiplicand, dst_hi, dst_lo;
+	const struct bpf_insn *insn = &meta->insn;
+	u32 lopnd_max, ropnd_max;
+	u8 dst_reg;
+
+	dst_reg = insn->dst_reg;
+	multiplicand = reg_a(dst_reg * 2);
+	dst_hi = reg_both(dst_reg * 2 + 1);
+	dst_lo = reg_both(dst_reg * 2);
+	lopnd_max = meta->umax_dst;
+	if (ropnd_from_reg) {
+		multiplier = reg_b(insn->src_reg * 2);
+		ropnd_max = meta->umax_src;
+	} else {
+		u32 imm = insn->imm;
+
+		multiplier = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+		ropnd_max = imm;
+	}
+	if (lopnd_max > U16_MAX || ropnd_max > U16_MAX)
+		wrp_mul_u32(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier,
+			    gen_high_half);
+	else
+		wrp_mul_u16(nfp_prog, dst_hi, dst_lo, multiplicand, multiplier);
+
+	return 0;
+}
+
 static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	swreg tmp = imm_a(nfp_prog), tmp_len = imm_b(nfp_prog);
@@ -1684,6 +1797,16 @@ static int sub_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int mul_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, true);
+}
+
+static int mul_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, true, false);
+}
+
 static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -2097,6 +2220,16 @@ static int sub_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_alu32_imm(nfp_prog, meta, ALU_OP_SUB, !meta->insn.imm);
 }
 
+static int mul_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, true);
+}
+
+static int mul_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return wrp_mul(nfp_prog, meta, false, false);
+}
+
 static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	u8 dst = meta->insn.dst_reg * 2;
@@ -2848,6 +2981,8 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_ADD | BPF_K] =	add_imm64,
 	[BPF_ALU64 | BPF_SUB | BPF_X] =	sub_reg64,
 	[BPF_ALU64 | BPF_SUB | BPF_K] =	sub_imm64,
+	[BPF_ALU64 | BPF_MUL | BPF_X] =	mul_reg64,
+	[BPF_ALU64 | BPF_MUL | BPF_K] =	mul_imm64,
 	[BPF_ALU64 | BPF_NEG] =		neg_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_X] =	shl_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_K] =	shl_imm64,
@@ -2867,6 +3002,8 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_ADD | BPF_K] =	add_imm,
 	[BPF_ALU | BPF_SUB | BPF_X] =	sub_reg,
 	[BPF_ALU | BPF_SUB | BPF_K] =	sub_imm,
+	[BPF_ALU | BPF_MUL | BPF_X] =	mul_reg,
+	[BPF_ALU | BPF_MUL | BPF_K] =	mul_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index c985d0ac61a3..c10079b1a312 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -394,6 +394,11 @@ static inline bool is_mbpf_xadd(const struct nfp_insn_meta *meta)
 	return (meta->insn.code & ~BPF_SIZE_MASK) == (BPF_STX | BPF_XADD);
 }
 
+static inline bool is_mbpf_mul(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_MUL;
+}
+
 /**
  * struct nfp_prog - nfp BPF program
  * @bpf: backpointer to the bpf app priv structure
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 7bd9666bd8ff..30d4f1580693 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -516,6 +516,51 @@ nfp_bpf_check_xadd(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	return nfp_bpf_check_ptr(nfp_prog, meta, env, meta->insn.dst_reg);
 }
 
+static int
+nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
+		  struct bpf_verifier_env *env)
+{
+	const struct bpf_reg_state *sreg =
+		cur_regs(env) + meta->insn.src_reg;
+	const struct bpf_reg_state *dreg =
+		cur_regs(env) + meta->insn.dst_reg;
+
+	meta->umin_src = min(meta->umin_src, sreg->umin_value);
+	meta->umax_src = max(meta->umax_src, sreg->umax_value);
+	meta->umin_dst = min(meta->umin_dst, dreg->umin_value);
+	meta->umax_dst = max(meta->umax_dst, dreg->umax_value);
+
+	/* NFP supports u16 and u32 multiplication.
+	 *
+	 * For ALU64, if either operand is beyond u32's value range, we reject
+	 * it. One thing to note, if the source operand is BPF_K, then we need
+	 * to check "imm" field directly, and we'd reject it if it is negative.
+	 * Because for ALU64, "imm" (with s32 type) is expected to be sign
+	 * extended to s64 which NFP mul doesn't support.
+	 *
+	 * For ALU32, it is fine for "imm" be negative though, because the
+	 * result is 32-bits and there is no difference on the low halve of
+	 * the result for signed/unsigned mul, so we will get correct result.
+	 */
+	if (is_mbpf_mul(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "multiplier is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X && meta->umax_src > U32_MAX) {
+			pr_vlog(env, "multiplicand is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_class(meta) == BPF_ALU64 &&
+		    mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "sign extended multiplicand won't be within u32 value range\n");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int
 nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 {
@@ -551,17 +596,8 @@ nfp_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn_idx)
 	if (is_mbpf_xadd(meta))
 		return nfp_bpf_check_xadd(nfp_prog, meta, env);
 
-	if (is_mbpf_alu(meta)) {
-		const struct bpf_reg_state *sreg =
-			cur_regs(env) + meta->insn.src_reg;
-		const struct bpf_reg_state *dreg =
-			cur_regs(env) + meta->insn.dst_reg;
-
-		meta->umin_src = min(meta->umin_src, sreg->umin_value);
-		meta->umax_src = max(meta->umax_src, sreg->umax_value);
-		meta->umin_dst = min(meta->umin_dst, dreg->umin_value);
-		meta->umax_dst = max(meta->umax_dst, dreg->umax_value);
-	}
+	if (is_mbpf_alu(meta))
+		return nfp_bpf_check_alu(nfp_prog, meta, env);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index f6677bc9875a..cdc4e065f6f5 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -426,4 +426,32 @@ static inline u32 nfp_get_ind_csr_ctx_ptr_offs(u32 read_offset)
 	return (read_offset & ~NFP_IND_ME_CTX_PTR_BASE_MASK) | NFP_CSR_CTX_PTR;
 }
 
+enum mul_type {
+	MUL_TYPE_START		= 0x00,
+	MUL_TYPE_STEP_24x8	= 0x01,
+	MUL_TYPE_STEP_16x16	= 0x02,
+	MUL_TYPE_STEP_32x32	= 0x03,
+};
+
+enum mul_step {
+	MUL_STEP_1		= 0x00,
+	MUL_STEP_NONE		= MUL_STEP_1,
+	MUL_STEP_2		= 0x01,
+	MUL_STEP_3		= 0x02,
+	MUL_STEP_4		= 0x03,
+	MUL_LAST		= 0x04,
+	MUL_LAST_2		= 0x05,
+};
+
+#define OP_MUL_BASE		0x0f800000000ULL
+#define OP_MUL_A_SRC		0x000000003ffULL
+#define OP_MUL_B_SRC		0x000000ffc00ULL
+#define OP_MUL_STEP		0x00000700000ULL
+#define OP_MUL_DST_AB		0x00000800000ULL
+#define OP_MUL_SW		0x00040000000ULL
+#define OP_MUL_TYPE		0x00180000000ULL
+#define OP_MUL_WR_AB		0x20000000000ULL
+#define OP_MUL_SRC_LMEXTN	0x40000000000ULL
+#define OP_MUL_DST_LMEXTN	0x80000000000ULL
+
 #endif
-- 
cgit v1.2.3


From 2a952b03d1a011e2e7ddc9ca59cbb21df7dc3525 Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Fri, 6 Jul 2018 15:13:22 -0700
Subject: nfp: bpf: support u32 divide using reciprocal_div.h

NFP doesn't have integer divide instruction, this patch use reciprocal
algorithm (the basic one, reciprocal_div) to emulate it.

For each u32 divide, we would need 11 instructions to finish the operation.

  7 (for multiplication) + 4 (various ALUs) = 11

Given NFP only supports multiplication no bigger than u32, we'd require
divisor and dividend no bigger than that as well.

Also eBPF doesn't support signed divide and has enforced this on C language
level by failing compilation. However LLVM assembler hasn't enforced this,
so it is possible for negative constant to leak in as a BPF_K operand
through assembly code, we reject such cases as well.

Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c      | 58 ++++++++++++++++++++++-
 drivers/net/ethernet/netronome/nfp/bpf/main.h     |  5 ++
 drivers/net/ethernet/netronome/nfp/bpf/verifier.c | 31 ++++++++++++
 3 files changed, 93 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index f1b27c3a4347..7c9ee3d85907 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -34,10 +34,11 @@
 #define pr_fmt(fmt)	"NFP net bpf: " fmt
 
 #include <linux/bug.h>
-#include <linux/kernel.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
+#include <linux/kernel.h>
 #include <linux/pkt_cls.h>
+#include <linux/reciprocal_div.h>
 #include <linux/unistd.h>
 
 #include "main.h"
@@ -1493,6 +1494,32 @@ wrp_mul(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 	return 0;
 }
 
+static int wrp_div_imm(struct nfp_prog *nfp_prog, u8 dst, u64 imm)
+{
+	swreg dst_both = reg_both(dst), dst_a = reg_a(dst), dst_b = reg_a(dst);
+	struct reciprocal_value rvalue;
+	swreg tmp_b = imm_b(nfp_prog);
+	swreg magic;
+
+	if (imm > U32_MAX) {
+		wrp_immed(nfp_prog, dst_both, 0);
+		return 0;
+	}
+
+	rvalue = reciprocal_value(imm);
+	magic = ur_load_imm_any(nfp_prog, rvalue.m, imm_b(nfp_prog));
+	wrp_mul_u32(nfp_prog, imm_both(nfp_prog), reg_none(), dst_a, magic,
+		    true);
+	emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_SUB, tmp_b);
+	emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+		 SHF_SC_R_SHF, rvalue.sh1);
+	emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_ADD, tmp_b);
+	emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+		 SHF_SC_R_SHF, rvalue.sh2);
+
+	return 0;
+}
+
 static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	swreg tmp = imm_a(nfp_prog), tmp_len = imm_b(nfp_prog);
@@ -1807,6 +1834,21 @@ static int mul_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_mul(nfp_prog, meta, true, false);
 }
 
+static int div_imm64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	const struct bpf_insn *insn = &meta->insn;
+
+	return wrp_div_imm(nfp_prog, insn->dst_reg * 2, insn->imm);
+}
+
+static int div_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	/* NOTE: verifier hook has rejected cases for which verifier doesn't
+	 * know whether the source operand is constant or not.
+	 */
+	return wrp_div_imm(nfp_prog, meta->insn.dst_reg * 2, meta->umin_src);
+}
+
 static int neg_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	const struct bpf_insn *insn = &meta->insn;
@@ -2230,6 +2272,16 @@ static int mul_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return wrp_mul(nfp_prog, meta, false, false);
 }
 
+static int div_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_reg64(nfp_prog, meta);
+}
+
+static int div_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	return div_imm64(nfp_prog, meta);
+}
+
 static int neg_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
 	u8 dst = meta->insn.dst_reg * 2;
@@ -2983,6 +3035,8 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU64 | BPF_SUB | BPF_K] =	sub_imm64,
 	[BPF_ALU64 | BPF_MUL | BPF_X] =	mul_reg64,
 	[BPF_ALU64 | BPF_MUL | BPF_K] =	mul_imm64,
+	[BPF_ALU64 | BPF_DIV | BPF_X] =	div_reg64,
+	[BPF_ALU64 | BPF_DIV | BPF_K] =	div_imm64,
 	[BPF_ALU64 | BPF_NEG] =		neg_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_X] =	shl_reg64,
 	[BPF_ALU64 | BPF_LSH | BPF_K] =	shl_imm64,
@@ -3004,6 +3058,8 @@ static const instr_cb_t instr_cb[256] = {
 	[BPF_ALU | BPF_SUB | BPF_K] =	sub_imm,
 	[BPF_ALU | BPF_MUL | BPF_X] =	mul_reg,
 	[BPF_ALU | BPF_MUL | BPF_K] =	mul_imm,
+	[BPF_ALU | BPF_DIV | BPF_X] =	div_reg,
+	[BPF_ALU | BPF_DIV | BPF_K] =	div_imm,
 	[BPF_ALU | BPF_NEG] =		neg_reg,
 	[BPF_ALU | BPF_LSH | BPF_K] =	shl_imm,
 	[BPF_ALU | BPF_END | BPF_X] =	end_reg32,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index c10079b1a312..9845c1a2d4c2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -399,6 +399,11 @@ static inline bool is_mbpf_mul(const struct nfp_insn_meta *meta)
 	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_MUL;
 }
 
+static inline bool is_mbpf_div(const struct nfp_insn_meta *meta)
+{
+	return is_mbpf_alu(meta) && mbpf_op(meta) == BPF_DIV;
+}
+
 /**
  * struct nfp_prog - nfp BPF program
  * @bpf: backpointer to the bpf app priv structure
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 30d4f1580693..49ba0d645d36 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -558,6 +558,37 @@ nfp_bpf_check_alu(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 		}
 	}
 
+	/* NFP doesn't have divide instructions, we support divide by constant
+	 * through reciprocal multiplication. Given NFP support multiplication
+	 * no bigger than u32, we'd require divisor and dividend no bigger than
+	 * that as well.
+	 *
+	 * Also eBPF doesn't support signed divide and has enforced this on C
+	 * language level by failing compilation. However LLVM assembler hasn't
+	 * enforced this, so it is possible for negative constant to leak in as
+	 * a BPF_K operand through assembly code, we reject such cases as well.
+	 */
+	if (is_mbpf_div(meta)) {
+		if (meta->umax_dst > U32_MAX) {
+			pr_vlog(env, "dividend is not within u32 value range\n");
+			return -EINVAL;
+		}
+		if (mbpf_src(meta) == BPF_X) {
+			if (meta->umin_src != meta->umax_src) {
+				pr_vlog(env, "divisor is not constant\n");
+				return -EINVAL;
+			}
+			if (meta->umax_src > U32_MAX) {
+				pr_vlog(env, "divisor is not within u32 value range\n");
+				return -EINVAL;
+			}
+		}
+		if (mbpf_src(meta) == BPF_K && meta->insn.imm < 0) {
+			pr_vlog(env, "divide by negative constant is not supported\n");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 9fb410a89e8fa92f8ebc7aa95563442a14da21eb Mon Sep 17 00:00:00 2001
From: Jiong Wang <jiong.wang@netronome.com>
Date: Fri, 6 Jul 2018 15:13:23 -0700
Subject: nfp: bpf: migrate to advanced reciprocal divide in reciprocal_div.h

As we are doing JIT, we would want to use the advanced version of the
reciprocal divide (reciprocal_value_adv) to trade performance with host.

We could reduce the required ALU instructions from 4 to 2 or 1.

Signed-off-by: Jiong Wang <jiong.wang@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/jit.c | 64 +++++++++++++++++++++++-----
 1 file changed, 53 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 7c9ee3d85907..1d9e36835404 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1497,8 +1497,8 @@ wrp_mul(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta,
 static int wrp_div_imm(struct nfp_prog *nfp_prog, u8 dst, u64 imm)
 {
 	swreg dst_both = reg_both(dst), dst_a = reg_a(dst), dst_b = reg_a(dst);
-	struct reciprocal_value rvalue;
-	swreg tmp_b = imm_b(nfp_prog);
+	struct reciprocal_value_adv rvalue;
+	u8 pre_shift, exp;
 	swreg magic;
 
 	if (imm > U32_MAX) {
@@ -1506,16 +1506,58 @@ static int wrp_div_imm(struct nfp_prog *nfp_prog, u8 dst, u64 imm)
 		return 0;
 	}
 
-	rvalue = reciprocal_value(imm);
+	/* NOTE: because we are using "reciprocal_value_adv" which doesn't
+	 * support "divisor > (1u << 31)", we need to JIT separate NFP sequence
+	 * to handle such case which actually equals to the result of unsigned
+	 * comparison "dst >= imm" which could be calculated using the following
+	 * NFP sequence:
+	 *
+	 *  alu[--, dst, -, imm]
+	 *  immed[imm, 0]
+	 *  alu[dst, imm, +carry, 0]
+	 *
+	 */
+	if (imm > 1U << 31) {
+		swreg tmp_b = ur_load_imm_any(nfp_prog, imm, imm_b(nfp_prog));
+
+		emit_alu(nfp_prog, reg_none(), dst_a, ALU_OP_SUB, tmp_b);
+		wrp_immed(nfp_prog, imm_a(nfp_prog), 0);
+		emit_alu(nfp_prog, dst_both, imm_a(nfp_prog), ALU_OP_ADD_C,
+			 reg_imm(0));
+		return 0;
+	}
+
+	rvalue = reciprocal_value_adv(imm, 32);
+	exp = rvalue.exp;
+	if (rvalue.is_wide_m && !(imm & 1)) {
+		pre_shift = fls(imm & -imm) - 1;
+		rvalue = reciprocal_value_adv(imm >> pre_shift, 32 - pre_shift);
+	} else {
+		pre_shift = 0;
+	}
 	magic = ur_load_imm_any(nfp_prog, rvalue.m, imm_b(nfp_prog));
-	wrp_mul_u32(nfp_prog, imm_both(nfp_prog), reg_none(), dst_a, magic,
-		    true);
-	emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_SUB, tmp_b);
-	emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
-		 SHF_SC_R_SHF, rvalue.sh1);
-	emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_ADD, tmp_b);
-	emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
-		 SHF_SC_R_SHF, rvalue.sh2);
+	if (imm == 1U << exp) {
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, exp);
+	} else if (rvalue.is_wide_m) {
+		wrp_mul_u32(nfp_prog, imm_both(nfp_prog), reg_none(), dst_a,
+			    magic, true);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_SUB,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, 1);
+		emit_alu(nfp_prog, dst_both, dst_a, ALU_OP_ADD,
+			 imm_b(nfp_prog));
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE, dst_b,
+			 SHF_SC_R_SHF, rvalue.sh - 1);
+	} else {
+		if (pre_shift)
+			emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+				 dst_b, SHF_SC_R_SHF, pre_shift);
+		wrp_mul_u32(nfp_prog, dst_both, reg_none(), dst_a, magic, true);
+		emit_shf(nfp_prog, dst_both, reg_none(), SHF_OP_NONE,
+			 dst_b, SHF_SC_R_SHF, rvalue.sh);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From da172d2b6ba8c98101b9c18a986758662a91adbb Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Sat, 23 Jun 2018 19:49:25 +0530
Subject: clk: qcom: Move frequency table macro to common file

Frequency table macro is used by multiple clock drivers, move frequency
table macro to common header file.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/clk-rcg.h        | 2 ++
 drivers/clk/qcom/gcc-apq8084.c    | 2 --
 drivers/clk/qcom/gcc-ipq4019.c    | 2 --
 drivers/clk/qcom/gcc-ipq8074.c    | 2 --
 drivers/clk/qcom/gcc-msm8916.c    | 2 --
 drivers/clk/qcom/gcc-msm8974.c    | 2 --
 drivers/clk/qcom/gcc-msm8994.c    | 2 --
 drivers/clk/qcom/gcc-msm8996.c    | 2 --
 drivers/clk/qcom/gcc-msm8998.c    | 2 --
 drivers/clk/qcom/gcc-sdm845.c     | 2 --
 drivers/clk/qcom/mmcc-apq8084.c   | 2 --
 drivers/clk/qcom/mmcc-msm8974.c   | 2 --
 drivers/clk/qcom/mmcc-msm8996.c   | 2 --
 drivers/clk/qcom/videocc-sdm845.c | 2 --
 14 files changed, 2 insertions(+), 26 deletions(-)

diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
index b209a2fe86b9..dbd5a9e83554 100644
--- a/drivers/clk/qcom/clk-rcg.h
+++ b/drivers/clk/qcom/clk-rcg.h
@@ -7,6 +7,8 @@
 #include <linux/clk-provider.h>
 #include "clk-regmap.h"
 
+#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
+
 struct freq_tbl {
 	unsigned long freq;
 	u8 src;
diff --git a/drivers/clk/qcom/gcc-apq8084.c b/drivers/clk/qcom/gcc-apq8084.c
index 486d9610355c..9c99a71ea71e 100644
--- a/drivers/clk/qcom/gcc-apq8084.c
+++ b/drivers/clk/qcom/gcc-apq8084.c
@@ -106,8 +106,6 @@ static const char * const gcc_xo_pcie_sleep[] = {
 	"sleep_clk_src",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll gpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/gcc-ipq4019.c b/drivers/clk/qcom/gcc-ipq4019.c
index 46cb256b4aa2..8902ad42ba87 100644
--- a/drivers/clk/qcom/gcc-ipq4019.c
+++ b/drivers/clk/qcom/gcc-ipq4019.c
@@ -179,8 +179,6 @@ static const char * const gcc_xo_ddr_500_200[] = {
 	"ddrpllapss",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static const struct freq_tbl ftbl_gcc_audio_pwm_clk[] = {
 	F(48000000, P_XO, 1, 0, 0),
 	F(200000000, P_FEPLL200, 1, 0, 0),
diff --git a/drivers/clk/qcom/gcc-ipq8074.c b/drivers/clk/qcom/gcc-ipq8074.c
index 0462f4a8c932..505c6263141d 100644
--- a/drivers/clk/qcom/gcc-ipq8074.c
+++ b/drivers/clk/qcom/gcc-ipq8074.c
@@ -32,8 +32,6 @@
 #include "clk-regmap-mux.h"
 #include "reset.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_XO,
 	P_GPLL0,
diff --git a/drivers/clk/qcom/gcc-msm8916.c b/drivers/clk/qcom/gcc-msm8916.c
index d6c7f50ba86a..ac2b0aa1e8b5 100644
--- a/drivers/clk/qcom/gcc-msm8916.c
+++ b/drivers/clk/qcom/gcc-msm8916.c
@@ -264,8 +264,6 @@ static const char * const gcc_xo_gpll1_emclk_sleep[] = {
 	"sleep_clk",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll gpll0 = {
 	.l_reg = 0x21004,
 	.m_reg = 0x21008,
diff --git a/drivers/clk/qcom/gcc-msm8974.c b/drivers/clk/qcom/gcc-msm8974.c
index 348e30da4f18..08e2900d172c 100644
--- a/drivers/clk/qcom/gcc-msm8974.c
+++ b/drivers/clk/qcom/gcc-msm8974.c
@@ -62,8 +62,6 @@ static const char * const gcc_xo_gpll0_gpll4[] = {
 	"gpll4_vote",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll gpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/gcc-msm8994.c b/drivers/clk/qcom/gcc-msm8994.c
index 1e38efc37180..53f0f369a33e 100644
--- a/drivers/clk/qcom/gcc-msm8994.c
+++ b/drivers/clk/qcom/gcc-msm8994.c
@@ -57,8 +57,6 @@ static const char * const gcc_xo_gpll0_gpll4[] = {
 	"gpll4",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_fixed_factor xo = {
 	.mult = 1,
 	.div = 1,
diff --git a/drivers/clk/qcom/gcc-msm8996.c b/drivers/clk/qcom/gcc-msm8996.c
index 9f35b3fe1d97..9d3756cb93bc 100644
--- a/drivers/clk/qcom/gcc-msm8996.c
+++ b/drivers/clk/qcom/gcc-msm8996.c
@@ -32,8 +32,6 @@
 #include "reset.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_XO,
 	P_GPLL0,
diff --git a/drivers/clk/qcom/gcc-msm8998.c b/drivers/clk/qcom/gcc-msm8998.c
index 78d87f5c7098..9f0ae403d5f5 100644
--- a/drivers/clk/qcom/gcc-msm8998.c
+++ b/drivers/clk/qcom/gcc-msm8998.c
@@ -25,8 +25,6 @@
 #include "reset.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_AUD_REF_CLK,
 	P_CORE_BI_PLL_TEST_SE,
diff --git a/drivers/clk/qcom/gcc-sdm845.c b/drivers/clk/qcom/gcc-sdm845.c
index e78e6f5b99fc..19b470fd7b52 100644
--- a/drivers/clk/qcom/gcc-sdm845.c
+++ b/drivers/clk/qcom/gcc-sdm845.c
@@ -25,8 +25,6 @@
 #include "gdsc.h"
 #include "reset.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_BI_TCXO,
 	P_AUD_REF_CLK,
diff --git a/drivers/clk/qcom/mmcc-apq8084.c b/drivers/clk/qcom/mmcc-apq8084.c
index 30777f9f1a43..4ce1d7c88377 100644
--- a/drivers/clk/qcom/mmcc-apq8084.c
+++ b/drivers/clk/qcom/mmcc-apq8084.c
@@ -219,8 +219,6 @@ static const char * const mmcc_xo_mmpll0_1_4_gpll1_0_sleep[] = {
 	"sleep_clk_src",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll mmpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/mmcc-msm8974.c b/drivers/clk/qcom/mmcc-msm8974.c
index 715e7cd94125..91818516c3e0 100644
--- a/drivers/clk/qcom/mmcc-msm8974.c
+++ b/drivers/clk/qcom/mmcc-msm8974.c
@@ -184,8 +184,6 @@ static const char * const mmcc_xo_dsibyte_hdmi_edp_gpll0[] = {
 	"dsi1pllbyte",
 };
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 static struct clk_pll mmpll0 = {
 	.l_reg = 0x0004,
 	.m_reg = 0x0008,
diff --git a/drivers/clk/qcom/mmcc-msm8996.c b/drivers/clk/qcom/mmcc-msm8996.c
index 1a25ee4f3658..60f08b378291 100644
--- a/drivers/clk/qcom/mmcc-msm8996.c
+++ b/drivers/clk/qcom/mmcc-msm8996.c
@@ -34,8 +34,6 @@
 #include "reset.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_XO,
 	P_MMPLL0,
diff --git a/drivers/clk/qcom/videocc-sdm845.c b/drivers/clk/qcom/videocc-sdm845.c
index 9073b7a710ac..5d6a7724a194 100644
--- a/drivers/clk/qcom/videocc-sdm845.c
+++ b/drivers/clk/qcom/videocc-sdm845.c
@@ -18,8 +18,6 @@
 #include "clk-pll.h"
 #include "gdsc.h"
 
-#define F(f, s, h, m, n) { (f), (s), (2 * (h) - 1), (m), (n) }
-
 enum {
 	P_BI_TCXO,
 	P_CORE_BI_PLL_TEST_SE,
-- 
cgit v1.2.3


From 6c79d12e945e85556674a04cde13657a5d7943da Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Sat, 23 Jun 2018 19:49:26 +0530
Subject: dt-bindings: clock: Introduce QCOM Display clock bindings

Add device tree bindings for display clock controller for Qualcomm
Technology Inc's SDM845 SoCs.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/qcom,dispcc.txt      | 19 +++++++++
 include/dt-bindings/clock/qcom,dispcc-sdm845.h     | 45 ++++++++++++++++++++++
 2 files changed, 64 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/clock/qcom,dispcc.txt
 create mode 100644 include/dt-bindings/clock/qcom,dispcc-sdm845.h

diff --git a/Documentation/devicetree/bindings/clock/qcom,dispcc.txt b/Documentation/devicetree/bindings/clock/qcom,dispcc.txt
new file mode 100644
index 000000000000..d639e18d0b85
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/qcom,dispcc.txt
@@ -0,0 +1,19 @@
+Qualcomm Technologies, Inc. Display Clock Controller Binding
+------------------------------------------------------------
+
+Required properties :
+
+- compatible : shall contain "qcom,sdm845-dispcc"
+- reg : shall contain base register location and length.
+- #clock-cells : from common clock binding, shall contain 1.
+- #reset-cells : from common reset binding, shall contain 1.
+- #power-domain-cells : from generic power domain binding, shall contain 1.
+
+Example:
+	dispcc: clock-controller@af00000 {
+		compatible = "qcom,sdm845-dispcc";
+		reg = <0xaf00000 0x100000>;
+		#clock-cells = <1>;
+		#reset-cells = <1>;
+		#power-domain-cells = <1>;
+	};
diff --git a/include/dt-bindings/clock/qcom,dispcc-sdm845.h b/include/dt-bindings/clock/qcom,dispcc-sdm845.h
new file mode 100644
index 000000000000..11eed4bc9646
--- /dev/null
+++ b/include/dt-bindings/clock/qcom,dispcc-sdm845.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _DT_BINDINGS_CLK_SDM_DISP_CC_SDM845_H
+#define _DT_BINDINGS_CLK_SDM_DISP_CC_SDM845_H
+
+/* DISP_CC clock registers */
+#define DISP_CC_MDSS_AHB_CLK					0
+#define DISP_CC_MDSS_AXI_CLK					1
+#define DISP_CC_MDSS_BYTE0_CLK					2
+#define DISP_CC_MDSS_BYTE0_CLK_SRC				3
+#define DISP_CC_MDSS_BYTE0_INTF_CLK				4
+#define DISP_CC_MDSS_BYTE1_CLK					5
+#define DISP_CC_MDSS_BYTE1_CLK_SRC				6
+#define DISP_CC_MDSS_BYTE1_INTF_CLK				7
+#define DISP_CC_MDSS_ESC0_CLK					8
+#define DISP_CC_MDSS_ESC0_CLK_SRC				9
+#define DISP_CC_MDSS_ESC1_CLK					10
+#define DISP_CC_MDSS_ESC1_CLK_SRC				11
+#define DISP_CC_MDSS_MDP_CLK					12
+#define DISP_CC_MDSS_MDP_CLK_SRC				13
+#define DISP_CC_MDSS_MDP_LUT_CLK				14
+#define DISP_CC_MDSS_PCLK0_CLK					15
+#define DISP_CC_MDSS_PCLK0_CLK_SRC				16
+#define DISP_CC_MDSS_PCLK1_CLK					17
+#define DISP_CC_MDSS_PCLK1_CLK_SRC				18
+#define DISP_CC_MDSS_ROT_CLK					19
+#define DISP_CC_MDSS_ROT_CLK_SRC				20
+#define DISP_CC_MDSS_RSCC_AHB_CLK				21
+#define DISP_CC_MDSS_RSCC_VSYNC_CLK				22
+#define DISP_CC_MDSS_VSYNC_CLK					23
+#define DISP_CC_MDSS_VSYNC_CLK_SRC				24
+#define DISP_CC_PLL0						25
+#define DISP_CC_MDSS_BYTE0_DIV_CLK_SRC				26
+#define DISP_CC_MDSS_BYTE1_DIV_CLK_SRC				27
+
+/* DISP_CC Reset */
+#define DISP_CC_MDSS_RSCC_BCR					0
+
+/* DISP_CC GDSCR */
+#define MDSS_GDSC						0
+
+#endif
-- 
cgit v1.2.3


From 351782067b6be81879b0af0daf7bd3acbb32d986 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 6 Jul 2018 10:12:54 -0400
Subject: ipv4: ipcm_cookie initializers

Initialize the cookie in one location to reduce code duplication and
avoid bugs from inconsistent initialization, such as that fixed in
commit 9887cba19978 ("ip: limit use of gso_size to udp").

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h     | 15 +++++++++++++++
 net/ipv4/icmp.c      | 11 ++---------
 net/ipv4/ip_output.c |  6 +-----
 net/ipv4/ping.c      |  9 +--------
 net/ipv4/raw.c       |  9 +--------
 net/ipv4/udp.c       | 10 +---------
 6 files changed, 21 insertions(+), 39 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 99d1b835d2aa..6db23bf1e5eb 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -79,6 +79,21 @@ struct ipcm_cookie {
 	__u16			gso_size;
 };
 
+static inline void ipcm_init(struct ipcm_cookie *ipcm)
+{
+	*ipcm = (struct ipcm_cookie) { .tos = -1 };
+}
+
+static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
+				const struct inet_sock *inet)
+{
+	ipcm_init(ipcm);
+
+	ipcm->sockc.tsflags = inet->sk.sk_tsflags;
+	ipcm->oif = inet->sk.sk_bound_dev_if;
+	ipcm->addr = inet->inet_saddr;
+}
+
 #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb))
 #define PKTINFO_SKB_CB(skb) ((struct in_pktinfo *)((skb)->cb))
 
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 937239afd68d..695979b7ef6d 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -429,15 +429,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 
 	icmp_param->data.icmph.checksum = 0;
 
+	ipcm_init(&ipc);
 	inet->tos = ip_hdr(skb)->tos;
 	sk->sk_mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
-	ipc.opt = NULL;
-	ipc.tx_flags = 0;
-	ipc.ttl = 0;
-	ipc.tos = -1;
-	ipc.sockc.transmit_time = 0;
 
 	if (icmp_param->replyopts.opt.opt.optlen) {
 		ipc.opt = &icmp_param->replyopts.opt;
@@ -711,12 +707,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
 	icmp_param.offset = skb_network_offset(skb_in);
 	inet_sk(sk)->tos = tos;
 	sk->sk_mark = mark;
+	ipcm_init(&ipc);
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param.replyopts.opt;
-	ipc.tx_flags = 0;
-	ipc.ttl = 0;
-	ipc.tos = -1;
-	ipc.sockc.transmit_time = 0;
 
 	rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
 			       type, code, &icmp_param);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 570e3ebc3974..81d0e4a77ec5 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1548,12 +1548,8 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 	if (__ip_options_echo(net, &replyopts.opt.opt, skb, sopt))
 		return;
 
+	ipcm_init(&ipc);
 	ipc.addr = daddr;
-	ipc.opt = NULL;
-	ipc.tx_flags = 0;
-	ipc.ttl = 0;
-	ipc.tos = -1;
-	ipc.sockc.transmit_time = 0;
 
 	if (replyopts.opt.opt.optlen) {
 		ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index b47492205507..6f17fc8ebbdb 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -739,14 +739,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		/* no remote port */
 	}
 
-	ipc.sockc.tsflags = sk->sk_tsflags;
-	ipc.addr = inet->inet_saddr;
-	ipc.opt = NULL;
-	ipc.oif = sk->sk_bound_dev_if;
-	ipc.tx_flags = 0;
-	ipc.ttl = 0;
-	ipc.tos = -1;
-	ipc.sockc.transmit_time = 0;
+	ipcm_init_sk(&ipc, inet);
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 446af7be2b55..cf142909389c 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -562,14 +562,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		daddr = inet->inet_daddr;
 	}
 
-	ipc.sockc.tsflags = sk->sk_tsflags;
-	ipc.sockc.transmit_time = 0;
-	ipc.addr = inet->inet_saddr;
-	ipc.opt = NULL;
-	ipc.tx_flags = 0;
-	ipc.ttl = 0;
-	ipc.tos = -1;
-	ipc.oif = sk->sk_bound_dev_if;
+	ipcm_init_sk(&ipc, inet);
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sk, msg, &ipc, false);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5c76ba0666ec..87f3a0b77864 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -926,12 +926,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */
 		return -EOPNOTSUPP;
 
-	ipc.opt = NULL;
-	ipc.tx_flags = 0;
-	ipc.ttl = 0;
-	ipc.tos = -1;
-	ipc.sockc.transmit_time = 0;
-
 	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;
 
 	fl4 = &inet->cork.fl.u.ip4;
@@ -978,9 +972,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		connected = 1;
 	}
 
-	ipc.sockc.tsflags = sk->sk_tsflags;
-	ipc.addr = inet->inet_saddr;
-	ipc.oif = sk->sk_bound_dev_if;
+	ipcm_init_sk(&ipc, inet);
 	ipc.gso_size = up->gso_size;
 
 	if (msg->msg_controllen) {
-- 
cgit v1.2.3


From b515430ac9c25d5192cf498af3c6be6c4f51caad Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 6 Jul 2018 10:12:55 -0400
Subject: ipv6: ipcm6_cookie initializer

Initialize the cookie in one location to reduce code duplication and
avoid bugs from inconsistent initialization, such as that fixed in
commit 9887cba19978 ("ip: limit use of gso_size to udp").

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h  | 19 +++++++++++++++++++
 net/ipv6/icmp.c     |  7 ++-----
 net/ipv6/ping.c     |  4 +---
 net/ipv6/raw.c      |  5 +----
 net/ipv6/udp.c      |  4 +---
 net/l2tp/l2tp_ip6.c |  4 +---
 6 files changed, 25 insertions(+), 18 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index b7843e0b16ee..6cb247f54d4c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -301,6 +301,25 @@ struct ipcm6_cookie {
 	__u16 gso_size;
 };
 
+static inline void ipcm6_init(struct ipcm6_cookie *ipc6)
+{
+	*ipc6 = (struct ipcm6_cookie) {
+		.hlimit = -1,
+		.tclass = -1,
+		.dontfrag = -1,
+	};
+}
+
+static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6,
+				 const struct ipv6_pinfo *np)
+{
+	*ipc6 = (struct ipcm6_cookie) {
+		.hlimit = -1,
+		.tclass = np->tclass,
+		.dontfrag = np->dontfrag,
+	};
+}
+
 static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
 {
 	struct ipv6_txoptions *opt;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index be491bf6ab6e..d99fed67cd10 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -545,7 +545,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	else if (!fl6.flowi6_oif)
 		fl6.flowi6_oif = np->ucast_oif;
 
-	ipc6.tclass = np->tclass;
+	ipcm6_init_sk(&ipc6, np);
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
 	dst = icmpv6_route_lookup(net, skb, sk, &fl6);
@@ -553,8 +553,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 		goto out;
 
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
-	ipc6.dontfrag = np->dontfrag;
-	ipc6.opt = NULL;
 
 	msg.skb = skb;
 	msg.offset = skb_network_offset(skb);
@@ -726,10 +724,9 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	msg.offset = 0;
 	msg.type = ICMPV6_ECHO_REPLY;
 
+	ipcm6_init_sk(&ipc6, np);
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 	ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
-	ipc6.dontfrag = np->dontfrag;
-	ipc6.opt = NULL;
 
 	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
 			    skb->len + sizeof(struct icmp6hdr),
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 96f56bf49a30..717e7c1fba29 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -119,7 +119,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.fl6_icmp_code = user_icmph.icmp6_code;
 	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));
 
-	ipc6.tclass = np->tclass;
+	ipcm6_init_sk(&ipc6, np);
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
 	dst = ip6_sk_dst_lookup_flow(sk, &fl6, daddr, false);
@@ -142,8 +142,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	pfh.family = AF_INET6;
 
 	ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
-	ipc6.dontfrag = np->dontfrag;
-	ipc6.opt = NULL;
 
 	lock_sock(sk);
 	err = ip6_append_data(sk, ping_getfrag, &pfh, len,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5737c50f16eb..5f40670271ee 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -791,10 +791,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.flowi6_uid = sk->sk_uid;
 
-	ipc6.hlimit = -1;
-	ipc6.tclass = -1;
-	ipc6.dontfrag = -1;
-	ipc6.opt = NULL;
+	ipcm6_init(&ipc6);
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index ac6fc6728903..940115da9843 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1143,9 +1143,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
 	struct sockcm_cookie sockc;
 
-	ipc6.hlimit = -1;
-	ipc6.tclass = -1;
-	ipc6.dontfrag = -1;
+	ipcm6_init(&ipc6);
 	ipc6.gso_size = up->gso_size;
 	sockc.tsflags = sk->sk_tsflags;
 	sockc.transmit_time = 0;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 957369192ca1..38f80691f4ab 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -525,9 +525,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_mark = sk->sk_mark;
 	fl6.flowi6_uid = sk->sk_uid;
 
-	ipc6.hlimit = -1;
-	ipc6.tclass = -1;
-	ipc6.dontfrag = -1;
+	ipcm6_init(&ipc6);
 
 	if (lsa) {
 		if (addr_len < SIN6_LEN_RFC2133)
-- 
cgit v1.2.3


From 657a0667025e77cc17f8a38b93e60a2bc24d830c Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 6 Jul 2018 10:12:56 -0400
Subject: sock: sockc cookie initializer

Initialize the cookie in one location to reduce code duplication and
avoid bugs from inconsistent initialization, such as that fixed in
commit 9887cba19978 ("ip: limit use of gso_size to udp").

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h     | 6 ++++++
 net/ipv4/tcp.c         | 2 +-
 net/packet/af_packet.c | 9 +++------
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index e0eac9ef44b5..83b747538bd0 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1600,6 +1600,12 @@ struct sockcm_cookie {
 	u16 tsflags;
 };
 
+static inline void sockcm_init(struct sockcm_cookie *sockc,
+			       const struct sock *sk)
+{
+	*sockc = (struct sockcm_cookie) { .tsflags = sk->sk_tsflags };
+}
+
 int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
 		     struct sockcm_cookie *sockc);
 int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bf461fa77ed6..850dc8f15afc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1241,7 +1241,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		/* 'common' sending to sendq */
 	}
 
-	sockc.tsflags = sk->sk_tsflags;
+	sockcm_init(&sockc, sk);
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
 		if (unlikely(err)) {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 3428f7739ae9..47931ebfaef3 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1951,8 +1951,7 @@ retry:
 		goto out_unlock;
 	}
 
-	sockc.transmit_time = 0;
-	sockc.tsflags = sk->sk_tsflags;
+	sockcm_init(&sockc, sk);
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
 		if (unlikely(err))
@@ -2636,8 +2635,7 @@ static int tpacket_snd(struct packet_sock *po, struct msghdr *msg)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_put;
 
-	sockc.transmit_time = 0;
-	sockc.tsflags = po->sk.sk_tsflags;
+	sockcm_init(&sockc, &po->sk);
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(&po->sk, msg, &sockc);
 		if (unlikely(err))
@@ -2833,8 +2831,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 	if (unlikely(!(dev->flags & IFF_UP)))
 		goto out_unlock;
 
-	sockc.transmit_time = 0;
-	sockc.tsflags = sk->sk_tsflags;
+	sockcm_init(&sockc, sk);
 	sockc.mark = sk->sk_mark;
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
-- 
cgit v1.2.3


From 5fdaa88dfefa87ee1ea92750e99950dca182ea41 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 6 Jul 2018 10:12:57 -0400
Subject: ipv6: fold sockcm_cookie into ipcm6_cookie

ipcm_cookie includes sockcm_cookie. Do the same for ipcm6_cookie.

This reduces the number of arguments that need to be passed around,
applies ipcm6_init to all cookie fields at once and reduces code
differentiation between ipv4 and ipv6.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h       |  7 +++----
 include/net/transp_v6.h  |  3 +--
 net/ipv6/datagram.c      |  4 ++--
 net/ipv6/icmp.c          |  7 ++-----
 net/ipv6/ip6_flowlabel.c |  3 +--
 net/ipv6/ip6_output.c    | 24 ++++++++++--------------
 net/ipv6/ipv6_sockglue.c |  3 +--
 net/ipv6/ping.c          |  3 +--
 net/ipv6/raw.c           | 10 ++++------
 net/ipv6/udp.c           | 10 ++++------
 net/l2tp/l2tp_ip6.c      |  6 ++----
 11 files changed, 31 insertions(+), 49 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 6cb247f54d4c..aa6fd11a887c 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -294,6 +294,7 @@ struct ipv6_fl_socklist {
 };
 
 struct ipcm6_cookie {
+	struct sockcm_cookie sockc;
 	__s16 hlimit;
 	__s16 tclass;
 	__s8  dontfrag;
@@ -959,8 +960,7 @@ int ip6_append_data(struct sock *sk,
 				int odd, struct sk_buff *skb),
 		    void *from, int length, int transhdrlen,
 		    struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
-		    struct rt6_info *rt, unsigned int flags,
-		    const struct sockcm_cookie *sockc);
+		    struct rt6_info *rt, unsigned int flags);
 
 int ip6_push_pending_frames(struct sock *sk);
 
@@ -977,8 +977,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 			     void *from, int length, int transhdrlen,
 			     struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
 			     struct rt6_info *rt, unsigned int flags,
-			     struct inet_cork_full *cork,
-			     const struct sockcm_cookie *sockc);
+			     struct inet_cork_full *cork);
 
 static inline struct sk_buff *ip6_finish_skb(struct sock *sk)
 {
diff --git a/include/net/transp_v6.h b/include/net/transp_v6.h
index f6a3543e5247..a8f6020f1196 100644
--- a/include/net/transp_v6.h
+++ b/include/net/transp_v6.h
@@ -42,8 +42,7 @@ void ip6_datagram_recv_specific_ctl(struct sock *sk, struct msghdr *msg,
 				    struct sk_buff *skb);
 
 int ip6_datagram_send_ctl(struct net *net, struct sock *sk, struct msghdr *msg,
-			  struct flowi6 *fl6, struct ipcm6_cookie *ipc6,
-			  struct sockcm_cookie *sockc);
+			  struct flowi6 *fl6, struct ipcm6_cookie *ipc6);
 
 void __ip6_dgram_sock_seq_show(struct seq_file *seq, struct sock *sp,
 			       __u16 srcp, __u16 destp, int rqueue, int bucket);
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 2ee08b6a86a4..201306b9b5ea 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -736,7 +736,7 @@ EXPORT_SYMBOL_GPL(ip6_datagram_recv_ctl);
 
 int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 			  struct msghdr *msg, struct flowi6 *fl6,
-			  struct ipcm6_cookie *ipc6, struct sockcm_cookie *sockc)
+			  struct ipcm6_cookie *ipc6)
 {
 	struct in6_pktinfo *src_info;
 	struct cmsghdr *cmsg;
@@ -755,7 +755,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 		}
 
 		if (cmsg->cmsg_level == SOL_SOCKET) {
-			err = __sock_cmsg_send(sk, msg, cmsg, sockc);
+			err = __sock_cmsg_send(sk, msg, cmsg, &ipc6->sockc);
 			if (err)
 				return err;
 			continue;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index d99fed67cd10..24611c8b0562 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -430,7 +430,6 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 	struct icmp6hdr tmp_hdr;
 	struct flowi6 fl6;
 	struct icmpv6_msg msg;
-	struct sockcm_cookie sockc_unused = {0};
 	struct ipcm6_cookie ipc6;
 	int iif = 0;
 	int addr_type = 0;
@@ -573,7 +572,7 @@ static void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
 			    len + sizeof(struct icmp6hdr),
 			    sizeof(struct icmp6hdr),
 			    &ipc6, &fl6, (struct rt6_info *)dst,
-			    MSG_DONTWAIT, &sockc_unused)) {
+			    MSG_DONTWAIT)) {
 		ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
@@ -677,7 +676,6 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	struct dst_entry *dst;
 	struct ipcm6_cookie ipc6;
 	u32 mark = IP6_REPLY_MARK(net, skb->mark);
-	struct sockcm_cookie sockc_unused = {0};
 
 	saddr = &ipv6_hdr(skb)->daddr;
 
@@ -731,8 +729,7 @@ static void icmpv6_echo_reply(struct sk_buff *skb)
 	if (ip6_append_data(sk, icmpv6_getfrag, &msg,
 			    skb->len + sizeof(struct icmp6hdr),
 			    sizeof(struct icmp6hdr), &ipc6, &fl6,
-			    (struct rt6_info *)dst, MSG_DONTWAIT,
-			    &sockc_unused)) {
+			    (struct rt6_info *)dst, MSG_DONTWAIT)) {
 		__ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
 		ip6_flush_pending_frames(sk);
 	} else {
diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c
index 3eee7637bdfe..cb54a8a3c273 100644
--- a/net/ipv6/ip6_flowlabel.c
+++ b/net/ipv6/ip6_flowlabel.c
@@ -373,7 +373,6 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 	if (olen > 0) {
 		struct msghdr msg;
 		struct flowi6 flowi6;
-		struct sockcm_cookie sockc_junk;
 		struct ipcm6_cookie ipc6;
 
 		err = -ENOMEM;
@@ -392,7 +391,7 @@ fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq,
 		memset(&flowi6, 0, sizeof(flowi6));
 
 		ipc6.opt = fl->opt;
-		err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6, &sockc_junk);
+		err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6);
 		if (err)
 			goto done;
 		err = -EINVAL;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f48af7e62f12..1a3bf6437cb9 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1158,8 +1158,7 @@ static void ip6_append_data_mtu(unsigned int *mtu,
 
 static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 			  struct inet6_cork *v6_cork, struct ipcm6_cookie *ipc6,
-			  struct rt6_info *rt, struct flowi6 *fl6,
-			  const struct sockcm_cookie *sockc)
+			  struct rt6_info *rt, struct flowi6 *fl6)
 {
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	unsigned int mtu;
@@ -1227,7 +1226,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 		cork->base.flags |= IPCORK_ALLFRAG;
 	cork->base.length = 0;
 
-	cork->base.transmit_time = sockc->transmit_time;
+	cork->base.transmit_time = ipc6->sockc.transmit_time;
 
 	return 0;
 }
@@ -1241,8 +1240,7 @@ static int __ip6_append_data(struct sock *sk,
 			     int getfrag(void *from, char *to, int offset,
 					 int len, int odd, struct sk_buff *skb),
 			     void *from, int length, int transhdrlen,
-			     unsigned int flags, struct ipcm6_cookie *ipc6,
-			     const struct sockcm_cookie *sockc)
+			     unsigned int flags, struct ipcm6_cookie *ipc6)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
 	unsigned int maxfraglen, fragheaderlen, mtu, orig_mtu, pmtu;
@@ -1321,7 +1319,7 @@ emsgsize:
 		csummode = CHECKSUM_PARTIAL;
 
 	if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
-		sock_tx_timestamp(sk, sockc->tsflags, &tx_flags);
+		sock_tx_timestamp(sk, ipc6->sockc.tsflags, &tx_flags);
 		if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
 		    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
 			tskey = sk->sk_tskey++;
@@ -1563,8 +1561,7 @@ int ip6_append_data(struct sock *sk,
 				int odd, struct sk_buff *skb),
 		    void *from, int length, int transhdrlen,
 		    struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
-		    struct rt6_info *rt, unsigned int flags,
-		    const struct sockcm_cookie *sockc)
+		    struct rt6_info *rt, unsigned int flags)
 {
 	struct inet_sock *inet = inet_sk(sk);
 	struct ipv6_pinfo *np = inet6_sk(sk);
@@ -1578,7 +1575,7 @@ int ip6_append_data(struct sock *sk,
 		 * setup for corking
 		 */
 		err = ip6_setup_cork(sk, &inet->cork, &np->cork,
-				     ipc6, rt, fl6, sockc);
+				     ipc6, rt, fl6);
 		if (err)
 			return err;
 
@@ -1592,7 +1589,7 @@ int ip6_append_data(struct sock *sk,
 
 	return __ip6_append_data(sk, fl6, &sk->sk_write_queue, &inet->cork.base,
 				 &np->cork, sk_page_frag(sk), getfrag,
-				 from, length, transhdrlen, flags, ipc6, sockc);
+				 from, length, transhdrlen, flags, ipc6);
 }
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
@@ -1752,8 +1749,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 			     void *from, int length, int transhdrlen,
 			     struct ipcm6_cookie *ipc6, struct flowi6 *fl6,
 			     struct rt6_info *rt, unsigned int flags,
-			     struct inet_cork_full *cork,
-			     const struct sockcm_cookie *sockc)
+			     struct inet_cork_full *cork)
 {
 	struct inet6_cork v6_cork;
 	struct sk_buff_head queue;
@@ -1770,7 +1766,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	cork->base.opt = NULL;
 	cork->base.dst = NULL;
 	v6_cork.opt = NULL;
-	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6, sockc);
+	err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6);
 	if (err) {
 		ip6_cork_release(cork, &v6_cork);
 		return ERR_PTR(err);
@@ -1781,7 +1777,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork,
 				&current->task_frag, getfrag, from,
 				length + exthdrlen, transhdrlen + exthdrlen,
-				flags, ipc6, sockc);
+				flags, ipc6);
 	if (err) {
 		__ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
 		return ERR_PTR(err);
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 4d780c7f0130..fabe3ba1bddc 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -489,7 +489,6 @@ sticky_done:
 		struct ipv6_txoptions *opt = NULL;
 		struct msghdr msg;
 		struct flowi6 fl6;
-		struct sockcm_cookie sockc_junk;
 		struct ipcm6_cookie ipc6;
 
 		memset(&fl6, 0, sizeof(fl6));
@@ -522,7 +521,7 @@ sticky_done:
 		msg.msg_control = (void *)(opt+1);
 		ipc6.opt = opt;
 
-		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6, &sockc_junk);
+		retv = ip6_datagram_send_ctl(net, sk, &msg, &fl6, &ipc6);
 		if (retv)
 			goto done;
 update:
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 717e7c1fba29..4c04bccc7417 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -62,7 +62,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct dst_entry *dst;
 	struct rt6_info *rt;
 	struct pingfakehdr pfh;
-	struct sockcm_cookie junk = {0};
 	struct ipcm6_cookie ipc6;
 
 	pr_debug("ping_v6_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
@@ -146,7 +145,7 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	lock_sock(sk);
 	err = ip6_append_data(sk, ping_getfrag, &pfh, len,
 			      0, &ipc6, &fl6, rt,
-			      MSG_DONTWAIT, &junk);
+			      MSG_DONTWAIT);
 
 	if (err) {
 		ICMP6_INC_STATS(sock_net(sk), rt->rt6i_idev,
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index 5f40670271ee..413d98bf24f4 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -767,7 +767,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct dst_entry *dst = NULL;
 	struct raw6_frag_vec rfv;
 	struct flowi6 fl6;
-	struct sockcm_cookie sockc;
 	struct ipcm6_cookie ipc6;
 	int addr_len = msg->msg_namelen;
 	u16 proto;
@@ -792,6 +791,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_uid = sk->sk_uid;
 
 	ipcm6_init(&ipc6);
+	ipc6.sockc.tsflags = sk->sk_tsflags;
 
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
@@ -845,15 +845,13 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (fl6.flowi6_oif == 0)
 		fl6.flowi6_oif = sk->sk_bound_dev_if;
 
-	sockc.tsflags = sk->sk_tsflags;
-	sockc.transmit_time = 0;
 	if (msg->msg_controllen) {
 		opt = &opt_space;
 		memset(opt, 0, sizeof(struct ipv6_txoptions));
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 		ipc6.opt = opt;
 
-		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -921,13 +919,13 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 back_from_confirm:
 	if (inet->hdrincl)
 		err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst,
-					msg->msg_flags, &sockc);
+					msg->msg_flags, &ipc6.sockc);
 	else {
 		ipc6.opt = opt;
 		lock_sock(sk);
 		err = ip6_append_data(sk, raw6_getfrag, &rfv,
 			len, 0, &ipc6, &fl6, (struct rt6_info *)dst,
-			msg->msg_flags, &sockc);
+			msg->msg_flags);
 
 		if (err)
 			ip6_flush_pending_frames(sk);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 940115da9843..f6b96956a8ed 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1141,12 +1141,10 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
-	struct sockcm_cookie sockc;
 
 	ipcm6_init(&ipc6);
 	ipc6.gso_size = up->gso_size;
-	sockc.tsflags = sk->sk_tsflags;
-	sockc.transmit_time = 0;
+	ipc6.sockc.tsflags = sk->sk_tsflags;
 
 	/* destination address check */
 	if (sin6) {
@@ -1281,7 +1279,7 @@ do_udp_sendmsg:
 		err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
 		if (err > 0)
 			err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6,
-						    &ipc6, &sockc);
+						    &ipc6);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -1375,7 +1373,7 @@ back_from_confirm:
 		skb = ip6_make_skb(sk, getfrag, msg, ulen,
 				   sizeof(struct udphdr), &ipc6,
 				   &fl6, (struct rt6_info *)dst,
-				   msg->msg_flags, &cork, &sockc);
+				   msg->msg_flags, &cork);
 		err = PTR_ERR(skb);
 		if (!IS_ERR_OR_NULL(skb))
 			err = udp_v6_send_skb(skb, &fl6, &cork.base);
@@ -1401,7 +1399,7 @@ do_append_data:
 	up->len += ulen;
 	err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
 			      &ipc6, &fl6, (struct rt6_info *)dst,
-			      corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags, &sockc);
+			      corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
 	if (err)
 		udp_v6_flush_pending_frames(sk);
 	else if (!corkreq)
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 38f80691f4ab..672e5b753738 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -500,7 +500,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct ip6_flowlabel *flowlabel = NULL;
 	struct dst_entry *dst = NULL;
 	struct flowi6 fl6;
-	struct sockcm_cookie sockc_unused = {0};
 	struct ipcm6_cookie ipc6;
 	int addr_len = msg->msg_namelen;
 	int transhdrlen = 4; /* zero session-id */
@@ -573,8 +572,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		opt->tot_len = sizeof(struct ipv6_txoptions);
 		ipc6.opt = opt;
 
-		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6,
-					    &sockc_unused);
+		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6);
 		if (err < 0) {
 			fl6_sock_release(flowlabel);
 			return err;
@@ -639,7 +637,7 @@ back_from_confirm:
 	err = ip6_append_data(sk, ip_generic_getfrag, msg,
 			      ulen, transhdrlen, &ipc6,
 			      &fl6, (struct rt6_info *)dst,
-			      msg->msg_flags, &sockc_unused);
+			      msg->msg_flags);
 	if (err)
 		ip6_flush_pending_frames(sk);
 	else if (!(msg->msg_flags & MSG_MORE))
-- 
cgit v1.2.3


From 678ca42d688534adfc780b150abefaaac7c86687 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 6 Jul 2018 10:12:58 -0400
Subject: ip: remove tx_flags from ipcm_cookie and use same logic for v4 and v6

skb_shinfo(skb)->tx_flags is derived from sk->sk_tsflags, possibly
after modification by __sock_cmsg_send, by calling sock_tx_timestamp.

The IPv4 and IPv6 paths do this conversion differently. In IPv4, the
individual protocols that support tx timestamps call this function
and store the result in ipc.tx_flags. In IPv6, sock_tx_timestamp is
called in __ip6_append_data.

There is no need to store both tx_flags and ts_flags in the cookie
as one is derived from the other. Convert when setting up the cork
and remove the redundant field. This is similar to IPv6, only have
the conversion happen only once per datagram, in ip(6)_setup_cork.

Also change __ip6_append_data to match __ip_append_data. Only update
tskey if timestamping is enabled with OPT_ID. The SOCK_.. test is
redundant: only valid protocols can have non-zero cork->tx_flags.

After this change the IPv4 and IPv6 logic is the same.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ip.h      |  1 -
 net/ipv4/ip_output.c  |  3 ++-
 net/ipv4/ping.c       |  2 --
 net/ipv4/raw.c        |  2 --
 net/ipv4/udp.c        |  2 --
 net/ipv6/ip6_output.c | 18 ++++++++----------
 6 files changed, 10 insertions(+), 18 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 6db23bf1e5eb..e44b1a44f67a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -72,7 +72,6 @@ struct ipcm_cookie {
 	__be32			addr;
 	int			oif;
 	struct ip_options_rcu	*opt;
-	__u8			tx_flags;
 	__u8			ttl;
 	__s16			tos;
 	char			priority;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 81d0e4a77ec5..e14c774cc092 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1153,8 +1153,9 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->ttl = ipc->ttl;
 	cork->tos = ipc->tos;
 	cork->priority = ipc->priority;
-	cork->tx_flags = ipc->tx_flags;
 	cork->transmit_time = ipc->sockc.transmit_time;
+	cork->tx_flags = 0;
+	sock_tx_timestamp(sk, ipc->sockc.tsflags, &cork->tx_flags);
 
 	return 0;
 }
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 6f17fc8ebbdb..b54c964ad925 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -763,8 +763,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		rcu_read_unlock();
 	}
 
-	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
-
 	saddr = ipc.addr;
 	ipc.addr = faddr = daddr;
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index cf142909389c..33df4d76db2d 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -665,8 +665,6 @@ back_from_confirm:
 				      &rt, msg->msg_flags, &ipc.sockc);
 
 	 else {
-		sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
-
 		if (!ipc.addr)
 			ipc.addr = fl4.daddr;
 		lock_sock(sk);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 87f3a0b77864..060e841dde40 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1020,8 +1020,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	saddr = ipc.addr;
 	ipc.addr = faddr = daddr;
 
-	sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags);
-
 	if (ipc.opt && ipc.opt->opt.srr) {
 		if (!daddr) {
 			err = -EINVAL;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1a3bf6437cb9..ff4b28a600ab 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1221,6 +1221,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	cork->base.fragsize = mtu;
 	cork->base.gso_size = sk->sk_type == SOCK_DGRAM &&
 			      sk->sk_protocol == IPPROTO_UDP ? ipc6->gso_size : 0;
+	cork->base.tx_flags = 0;
+	sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
 
 	if (dst_allfrag(xfrm_dst_path(&rt->dst)))
 		cork->base.flags |= IPCORK_ALLFRAG;
@@ -1250,7 +1252,6 @@ static int __ip6_append_data(struct sock *sk,
 	int copy;
 	int err;
 	int offset = 0;
-	__u8 tx_flags = 0;
 	u32 tskey = 0;
 	struct rt6_info *rt = (struct rt6_info *)cork->dst;
 	struct ipv6_txoptions *opt = v6_cork->opt;
@@ -1269,6 +1270,10 @@ static int __ip6_append_data(struct sock *sk,
 	mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize;
 	orig_mtu = mtu;
 
+	if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP &&
+	    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
+		tskey = sk->sk_tskey++;
+
 	hh_len = LL_RESERVED_SPACE(rt->dst.dev);
 
 	fragheaderlen = sizeof(struct ipv6hdr) + rt->rt6i_nfheader_len +
@@ -1318,13 +1323,6 @@ emsgsize:
 	    rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))
 		csummode = CHECKSUM_PARTIAL;
 
-	if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) {
-		sock_tx_timestamp(sk, ipc6->sockc.tsflags, &tx_flags);
-		if (tx_flags & SKBTX_ANY_SW_TSTAMP &&
-		    sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID)
-			tskey = sk->sk_tskey++;
-	}
-
 	/*
 	 * Let's try using as much space as possible.
 	 * Use MTU if total length of the message fits into the MTU.
@@ -1443,8 +1441,8 @@ alloc_new_skb:
 				    dst_exthdrlen);
 
 			/* Only the initial fragment is time stamped */
-			skb_shinfo(skb)->tx_flags = tx_flags;
-			tx_flags = 0;
+			skb_shinfo(skb)->tx_flags = cork->tx_flags;
+			cork->tx_flags = 0;
 			skb_shinfo(skb)->tskey = tskey;
 			tskey = 0;
 
-- 
cgit v1.2.3


From fbf47813607ba8c4e5c5b81da3c47fc66ac314b1 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 6 Jul 2018 10:12:59 -0400
Subject: ip: unconditionally set cork gso_size

Now that ipc(6)->gso_size is correctly initialized in all callers of
ip(6)_setup_cork, it is safe to unconditionally pass it to the cork.

Link: http://lkml.kernel.org/r/20180619164752.143249-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_output.c  | 3 +--
 net/ipv6/ip6_output.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e14c774cc092..e2b6bd478afb 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1146,8 +1146,7 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	cork->fragsize = ip_sk_use_pmtu(sk) ?
 			 dst_mtu(&rt->dst) : rt->dst.dev->mtu;
 
-	cork->gso_size = sk->sk_type == SOCK_DGRAM &&
-			 sk->sk_protocol == IPPROTO_UDP ? ipc->gso_size : 0;
+	cork->gso_size = ipc->gso_size;
 	cork->dst = &rt->dst;
 	cork->length = 0;
 	cork->ttl = ipc->ttl;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ff4b28a600ab..8047fd41ba88 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1219,8 +1219,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	if (mtu < IPV6_MIN_MTU)
 		return -EINVAL;
 	cork->base.fragsize = mtu;
-	cork->base.gso_size = sk->sk_type == SOCK_DGRAM &&
-			      sk->sk_protocol == IPPROTO_UDP ? ipc6->gso_size : 0;
+	cork->base.gso_size = ipc6->gso_size;
 	cork->base.tx_flags = 0;
 	sock_tx_timestamp(sk, ipc6->sockc.tsflags, &cork->base.tx_flags);
 
-- 
cgit v1.2.3


From 4fed38cf26278e6597b506e62a9156e45cbcec49 Mon Sep 17 00:00:00 2001
From: Rick Farrington <ricardo.farrington@cavium.com>
Date: Fri, 6 Jul 2018 11:27:07 -0700
Subject: liquidio: fix kernel panic when NIC firmware is older than 1.7.2

Pre-1.7.2 NIC firmware does not support (and does not respond to) the "get
speed" command which is sent by the 1.7.2 driver (for CN23XX-225 cards
only) during modprobe.  Due to a bug in older firmware (with respect to
unknown commands), this unsupported command causes a cascade of errors that
ends in a kernel panic.

Fix it by making the sending of the "get speed" command conditional on the
firmware version.

Signed-off-by: Rick Farrington <ricardo.farrington@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/lio_main.c    | 26 ++++++++++++++++++++--
 .../net/ethernet/cavium/liquidio/octeon_device.h   |  9 ++++++++
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 7cb4e753829b..ebda6efc3290 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -3299,7 +3299,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 {
 	struct lio *lio = NULL;
 	struct net_device *netdev;
-	u8 mac[6], i, j, *fw_ver;
+	u8 mac[6], i, j, *fw_ver, *micro_ver;
+	unsigned long micro;
+	u32 cur_ver;
 	struct octeon_soft_command *sc;
 	struct liquidio_if_cfg_context *ctx;
 	struct liquidio_if_cfg_resp *resp;
@@ -3429,6 +3431,14 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 				 fw_ver);
 		}
 
+		/* extract micro version field; point past '<maj>.<min>.' */
+		micro_ver = fw_ver + strlen(LIQUIDIO_BASE_VERSION) + 1;
+		if (kstrtoul(micro_ver, 10, &micro) != 0)
+			micro = 0;
+		octeon_dev->fw_info.ver.maj = LIQUIDIO_BASE_MAJOR_VERSION;
+		octeon_dev->fw_info.ver.min = LIQUIDIO_BASE_MINOR_VERSION;
+		octeon_dev->fw_info.ver.rev = micro;
+
 		octeon_swap_8B_data((u64 *)(&resp->cfg_info),
 				    (sizeof(struct liquidio_if_cfg_info)) >> 3);
 
@@ -3671,7 +3681,19 @@ static int setup_nic_devices(struct octeon_device *octeon_dev)
 			OCTEON_CN2350_25GB_SUBSYS_ID ||
 		    octeon_dev->subsystem_id ==
 			OCTEON_CN2360_25GB_SUBSYS_ID) {
-			liquidio_get_speed(lio);
+			cur_ver = OCT_FW_VER(octeon_dev->fw_info.ver.maj,
+					     octeon_dev->fw_info.ver.min,
+					     octeon_dev->fw_info.ver.rev);
+
+			/* speed control unsupported in f/w older than 1.7.2 */
+			if (cur_ver < OCT_FW_VER(1, 7, 2)) {
+				dev_info(&octeon_dev->pci_dev->dev,
+					 "speed setting not supported by f/w.");
+				octeon_dev->speed_setting = 25;
+				octeon_dev->no_speed_setting = 1;
+			} else {
+				liquidio_get_speed(lio);
+			}
 
 			if (octeon_dev->speed_setting == 0) {
 				octeon_dev->speed_setting = 25;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index 94a4ed88d618..d99ca6ba23a4 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -288,8 +288,17 @@ struct oct_fw_info {
 	 */
 	u32 app_mode;
 	char   liquidio_firmware_version[32];
+	/* Fields extracted from legacy string 'liquidio_firmware_version' */
+	struct {
+		u8  maj;
+		u8  min;
+		u8  rev;
+	} ver;
 };
 
+#define OCT_FW_VER(maj, min, rev) \
+	(((u32)(maj) << 16) | ((u32)(min) << 8) | ((u32)(rev)))
+
 /* wrappers around work structs */
 struct cavium_wk {
 	struct delayed_work work;
-- 
cgit v1.2.3


From a75a8efa00c59d6987e9372583017baf63a2c27d Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 6 Jul 2018 11:27:55 +0100
Subject: net: hns3: Fix tc setup when netdev is first up

Currently, tc related configuration is not setup when the
netdev is first up, which cause the stack only using tc 0
problem.

This patch fixes it by setting the tc related configuration
using the info from NCL_CONFIG when netdev is first up.

Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 78 ++++++++++---------------
 1 file changed, 31 insertions(+), 47 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index f73c9dff46ff..e5e51e801c38 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -239,7 +239,28 @@ static int hns3_nic_set_real_num_queue(struct net_device *netdev)
 	struct hnae3_handle *h = hns3_get_handle(netdev);
 	struct hnae3_knic_private_info *kinfo = &h->kinfo;
 	unsigned int queue_size = kinfo->rss_size * kinfo->num_tc;
-	int ret;
+	int i, ret;
+
+	if (kinfo->num_tc <= 1) {
+		netdev_reset_tc(netdev);
+	} else {
+		ret = netdev_set_num_tc(netdev, kinfo->num_tc);
+		if (ret) {
+			netdev_err(netdev,
+				   "netdev_set_num_tc fail, ret=%d!\n", ret);
+			return ret;
+		}
+
+		for (i = 0; i < HNAE3_MAX_TC; i++) {
+			if (!kinfo->tc_info[i].enable)
+				continue;
+
+			netdev_set_tc_queue(netdev,
+					    kinfo->tc_info[i].tc,
+					    kinfo->tc_info[i].tqp_count,
+					    kinfo->tc_info[i].tqp_offset);
+		}
+	}
 
 	ret = netif_set_real_num_tx_queues(netdev, queue_size);
 	if (ret) {
@@ -312,7 +333,9 @@ out_start_err:
 static int hns3_nic_net_open(struct net_device *netdev)
 {
 	struct hns3_nic_priv *priv = netdev_priv(netdev);
-	int ret;
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	struct hnae3_knic_private_info *kinfo;
+	int i, ret;
 
 	netif_carrier_off(netdev);
 
@@ -327,6 +350,12 @@ static int hns3_nic_net_open(struct net_device *netdev)
 		return ret;
 	}
 
+	kinfo = &h->kinfo;
+	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
+		netdev_set_prio_tc_map(netdev, i,
+				       kinfo->prio_tc[i]);
+	}
+
 	priv->ae_handle->last_reset_time = jiffies;
 	return 0;
 }
@@ -1307,7 +1336,6 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	u16 mode = mqprio_qopt->mode;
 	u8 hw = mqprio_qopt->qopt.hw;
 	bool if_running;
-	unsigned int i;
 	int ret;
 
 	if (!((hw == TC_MQPRIO_HW_OFFLOAD_TCS &&
@@ -1331,24 +1359,6 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data)
 	if (ret)
 		goto out;
 
-	if (tc <= 1) {
-		netdev_reset_tc(netdev);
-	} else {
-		ret = netdev_set_num_tc(netdev, tc);
-		if (ret)
-			goto out;
-
-		for (i = 0; i < HNAE3_MAX_TC; i++) {
-			if (!kinfo->tc_info[i].enable)
-				continue;
-
-			netdev_set_tc_queue(netdev,
-					    kinfo->tc_info[i].tc,
-					    kinfo->tc_info[i].tqp_count,
-					    kinfo->tc_info[i].tqp_offset);
-		}
-	}
-
 	ret = hns3_nic_set_real_num_queue(netdev);
 
 out:
@@ -3202,7 +3212,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 	struct net_device *ndev = kinfo->netdev;
 	bool if_running;
 	int ret;
-	u8 i;
 
 	if (tc > HNAE3_MAX_TC)
 		return -EINVAL;
@@ -3212,10 +3221,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 
 	if_running = netif_running(ndev);
 
-	ret = netdev_set_num_tc(ndev, tc);
-	if (ret)
-		return ret;
-
 	if (if_running) {
 		(void)hns3_nic_net_stop(ndev);
 		msleep(100);
@@ -3226,27 +3231,6 @@ static int hns3_client_setup_tc(struct hnae3_handle *handle, u8 tc)
 	if (ret)
 		goto err_out;
 
-	if (tc <= 1) {
-		netdev_reset_tc(ndev);
-		goto out;
-	}
-
-	for (i = 0; i < HNAE3_MAX_TC; i++) {
-		struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
-
-		if (tc_info->enable)
-			netdev_set_tc_queue(ndev,
-					    tc_info->tc,
-					    tc_info->tqp_count,
-					    tc_info->tqp_offset);
-	}
-
-	for (i = 0; i < HNAE3_MAX_USER_PRIO; i++) {
-		netdev_set_prio_tc_map(ndev, i,
-				       kinfo->prio_tc[i]);
-	}
-
-out:
 	ret = hns3_nic_set_real_num_queue(ndev);
 
 err_out:
-- 
cgit v1.2.3


From 6d0ec65cb5810f9bf08671be008785bb8c84d39f Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 6 Jul 2018 11:27:56 +0100
Subject: net: hns3: Fix for mac pause not disable in pfc mode

When pfc pause mode is enable, the mac pause mode need to be
disabled, otherwise the pfc pause packet will not be sent when
congestion happens.

This patch fixes by disabling the mac pause when pfc pause is
enabled.

Fixes: 848440544b41 ("net: hns3: Add support of TX Scheduler & Shaper to HNS3 driver")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index 82bc30fdff98..e2acf3bd6ba3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1223,6 +1223,10 @@ static int hclge_mac_pause_setup_hw(struct hclge_dev *hdev)
 		tx_en = true;
 		rx_en = true;
 		break;
+	case HCLGE_FC_PFC:
+		tx_en = false;
+		rx_en = false;
+		break;
 	default:
 		tx_en = true;
 		rx_en = true;
@@ -1240,8 +1244,9 @@ int hclge_pause_setup_hw(struct hclge_dev *hdev)
 	if (ret)
 		return ret;
 
-	if (hdev->tm_info.fc_mode != HCLGE_FC_PFC)
-		return hclge_mac_pause_setup_hw(hdev);
+	ret = hclge_mac_pause_setup_hw(hdev);
+	if (ret)
+		return ret;
 
 	/* Only DCB-supported dev supports qset back pressure and pfc cmd */
 	if (!hnae3_dev_dcb_supported(hdev))
-- 
cgit v1.2.3


From 3738287c7a54c7b3d7421cc92c22aa5ad9096fd8 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 6 Jul 2018 11:27:57 +0100
Subject: net: hns3: Fix for waterline not setting correctly

The HCLGE_RX_PRIV_EN_B is used to tell the firmware whether
to update the specific waterline value, if the is not set,
the firmware will ignore the value.

This patch fixes by setting the HCLGE_RX_PRIV_EN_B even if
the updated value is zero.

Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 6fffc69a7138..dae1aa5c55fb 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1834,8 +1834,6 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev,
 	return 0;
 }
 
-#define HCLGE_PRIV_ENABLE(a) ((a) > 0 ? 1 : 0)
-
 static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
 				   struct hclge_pkt_buf_alloc *buf_alloc)
 {
@@ -1863,13 +1861,11 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
 			req->tc_wl[j].high =
 				cpu_to_le16(priv->wl.high >> HCLGE_BUF_UNIT_S);
 			req->tc_wl[j].high |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.high) <<
-					    HCLGE_RX_PRIV_EN_B);
+				cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 			req->tc_wl[j].low =
 				cpu_to_le16(priv->wl.low >> HCLGE_BUF_UNIT_S);
 			req->tc_wl[j].low |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(priv->wl.low) <<
-					    HCLGE_RX_PRIV_EN_B);
+				 cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 		}
 	}
 
@@ -1911,13 +1907,11 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev,
 			req->com_thrd[j].high =
 				cpu_to_le16(tc->high >> HCLGE_BUF_UNIT_S);
 			req->com_thrd[j].high |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(tc->high) <<
-					    HCLGE_RX_PRIV_EN_B);
+				 cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 			req->com_thrd[j].low =
 				cpu_to_le16(tc->low >> HCLGE_BUF_UNIT_S);
 			req->com_thrd[j].low |=
-				cpu_to_le16(HCLGE_PRIV_ENABLE(tc->low) <<
-					    HCLGE_RX_PRIV_EN_B);
+				 cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 		}
 	}
 
@@ -1943,14 +1937,10 @@ static int hclge_common_wl_config(struct hclge_dev *hdev,
 
 	req = (struct hclge_rx_com_wl *)desc.data;
 	req->com_wl.high = cpu_to_le16(buf->self.high >> HCLGE_BUF_UNIT_S);
-	req->com_wl.high |=
-		cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.high) <<
-			    HCLGE_RX_PRIV_EN_B);
+	req->com_wl.high |=  cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 
 	req->com_wl.low = cpu_to_le16(buf->self.low >> HCLGE_BUF_UNIT_S);
-	req->com_wl.low |=
-		cpu_to_le16(HCLGE_PRIV_ENABLE(buf->self.low) <<
-			    HCLGE_RX_PRIV_EN_B);
+	req->com_wl.low |=  cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-- 
cgit v1.2.3


From 5c8971979a10783150e1011ece685333bbec5759 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 6 Jul 2018 11:27:58 +0100
Subject: net: hns3: Fix for l4 checksum offload bug

Hardware only support tcp/udp/sctp l4 checksum offload, but
the driver currently tell hardware to do l4 checksum offlad when
l3 is IPv4 or IPv6, which may cause checksumm error.

This patch fixes it by only enabling the l4 offload when l4 is
tcp/udp/sctp.

Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index e5e51e801c38..c211450bfd78 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -791,16 +791,14 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 		 */
 		if (skb_is_gso(skb))
 			hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L3CS_B, 1);
-
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
 	} else if (l3.v6->version == 6) {
 		hnae3_set_field(*type_cs_vlan_tso, HNS3_TXD_L3T_M,
 				HNS3_TXD_L3T_S, HNS3_L3T_IPV6);
-		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
 	}
 
 	switch (l4_proto) {
 	case IPPROTO_TCP:
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
 		hnae3_set_field(*type_cs_vlan_tso,
 				HNS3_TXD_L4T_M,
 				HNS3_TXD_L4T_S,
@@ -810,12 +808,14 @@ static int hns3_set_l3l4_type_csum(struct sk_buff *skb, u8 ol4_proto,
 		if (hns3_tunnel_csum_bug(skb))
 			break;
 
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
 		hnae3_set_field(*type_cs_vlan_tso,
 				HNS3_TXD_L4T_M,
 				HNS3_TXD_L4T_S,
 				HNS3_L4T_UDP);
 		break;
 	case IPPROTO_SCTP:
+		hnae3_set_bit(*type_cs_vlan_tso, HNS3_TXD_L4CS_B, 1);
 		hnae3_set_field(*type_cs_vlan_tso,
 				HNS3_TXD_L4T_M,
 				HNS3_TXD_L4T_S,
-- 
cgit v1.2.3


From ead5bd4d35c0a14d5ce1474177718c678dff5205 Mon Sep 17 00:00:00 2001
From: Fuyun Liang <liangfuyun1@huawei.com>
Date: Fri, 6 Jul 2018 11:27:59 +0100
Subject: net: hns3: Fix for mailbox message truncated problem

The payload of mailbox message is 16 byte and the value of
HCLGE_MBX_MAX_ARQ_MSG_SIZE is 8. A message truncated problem will
happen when mailbox message is converted to ARQ message. This patch
replaces HCLGE_MBX_MAX_ARQ_MSG_SIZE with the size of ARQ message in
hclgevf_mbx_handler to fix this problem.

Fixes: b11a0bb231f3 ("net: hns3: Add mailbox support to VF driver")
Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
index 173ca27957ef..e9d5a4f96304 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c
@@ -208,7 +208,8 @@ void hclgevf_mbx_handler(struct hclgevf_dev *hdev)
 
 			/* tail the async message in arq */
 			msg_q = hdev->arq.msg_q[hdev->arq.tail];
-			memcpy(&msg_q[0], req->msg, HCLGE_MBX_MAX_ARQ_MSG_SIZE);
+			memcpy(&msg_q[0], req->msg,
+			       HCLGE_MBX_MAX_ARQ_MSG_SIZE * sizeof(u16));
 			hclge_mbx_tail_ptr_move_arq(hdev->arq);
 			hdev->arq.count++;
 
-- 
cgit v1.2.3


From 8fc7346c84a4471d21389a9ead1bbc2420d65ea0 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 6 Jul 2018 11:28:00 +0100
Subject: net: hns3: Add configure for mac minimal frame size

When change the mtu, the minimal frame size of mac will be set
to zero, it is incorrect. This patch fixes it by set it to the
default value.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 3 ++-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index d9aaa76c76eb..656c3e622ec8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -571,7 +571,8 @@ struct hclge_config_auto_neg_cmd {
 
 struct hclge_config_max_frm_size_cmd {
 	__le16  max_frm_size;
-	u8      rsv[22];
+	u8      min_frm_size;
+	u8      rsv[21];
 };
 
 enum hclge_mac_vlan_tbl_opcode {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index dae1aa5c55fb..df6a7a10bb83 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4987,6 +4987,7 @@ static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mtu)
 
 	req = (struct hclge_config_max_frm_size_cmd *)desc.data;
 	req->max_frm_size = cpu_to_le16(max_frm_size);
+	req->min_frm_size = HCLGE_MAC_MIN_FRAME;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
 	if (ret) {
-- 
cgit v1.2.3


From d7099d15478e89edb9bc6c6e3ab4cd341884a367 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 6 Jul 2018 11:28:01 +0100
Subject: net: hns3: Fix warning bug when doing lp selftest

The napi_alloc_skb is excepted to be called under the
non-preemptible code path when it is called by hns3_clean_rx_ring
during loopback selftest, otherwise the below warning will be
logged:

[   92.420780] BUG: using smp_processor_id() in preemptible
[00000000] code: ethtool/1873
<SNIP>
[   92.463202]  check_preemption_disabled+0xf8/0x100
[   92.467893]  debug_smp_processor_id+0x1c/0x28
[   92.472239]  __napi_alloc_skb+0x30/0x130
[   92.476158]  hns3_clean_rx_ring+0x118/0x5f0 [hns3]
[   92.480941]  hns3_self_test+0x32c/0x4d0 [hns3]
[   92.485375]  ethtool_self_test+0xdc/0x1e8
[   92.489372]  dev_ethtool+0x1020/0x1da8
[   92.493109]  dev_ioctl+0x188/0x3a0
[   92.496499]  sock_do_ioctl+0xf4/0x208
[   92.500148]  sock_ioctl+0x228/0x3e8
[   92.503626]  do_vfs_ioctl+0xc4/0x880
[   92.507189]  SyS_ioctl+0x94/0xa8
[   92.510404]  el0_svc_naked+0x30/0x34

This patch fix it by disabling preemption when calling
hns3_clean_rx_ring during loopback selftest.

Fixes: c39c4d98dc65 ("net: hns3: Add mac loopback selftest support in hns3 driver")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 40c0425b4023..11620e003a8e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -201,7 +201,9 @@ static u32 hns3_lb_check_rx_ring(struct hns3_nic_priv *priv, u32 budget)
 		rx_group = &ring->tqp_vector->rx_group;
 		pre_rx_pkt = rx_group->total_packets;
 
+		preempt_disable();
 		hns3_clean_rx_ring(ring, budget, hns3_lb_check_skb_data);
+		preempt_enable();
 
 		rcv_good_pkt_total += (rx_group->total_packets - pre_rx_pkt);
 		rx_group->total_packets = pre_rx_pkt;
-- 
cgit v1.2.3


From 03718db97bfb57535f3aa8110f0cbe0c616a67c0 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Fri, 6 Jul 2018 11:28:02 +0100
Subject: net: hns3: Fix get_vector ops in hclgevf_main module

The hclgevf_free_vector function expects the caller to pass
the vector_id to it, and hclgevf_put_vector pass vector to
it now, which will cause vector allocation problem.

This patch fixes it by converting vector into vector_id before
calling hclgevf_free_vector.

Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index 5a8653238e3f..d1f16f0c1646 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -658,8 +658,17 @@ static int hclgevf_unmap_ring_from_vector(
 static int hclgevf_put_vector(struct hnae3_handle *handle, int vector)
 {
 	struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle);
+	int vector_id;
+
+	vector_id = hclgevf_get_vector_index(hdev, vector);
+	if (vector_id < 0) {
+		dev_err(&handle->pdev->dev,
+			"hclgevf_put_vector get vector index fail. ret =%d\n",
+			vector_id);
+		return vector_id;
+	}
 
-	hclgevf_free_vector(hdev, vector);
+	hclgevf_free_vector(hdev, vector_id);
 
 	return 0;
 }
-- 
cgit v1.2.3


From a754e5c4ed0627c3d5695ebbbc7ca53b38c6103a Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Fri, 6 Jul 2018 11:28:03 +0100
Subject: net: hns3: Remove the warning when clear reset cause

Only the core/global/IMP reset need clear cause, other type does not
need do it. The warning may be treated as error as it is normal. This
patch removes the warning.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index df6a7a10bb83..4ca3e6b42f4f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2805,8 +2805,6 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 		clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
 		break;
 	default:
-		dev_warn(&hdev->pdev->dev, "Unsupported reset event to clear:%d",
-			 hdev->reset_type);
 		break;
 	}
 
-- 
cgit v1.2.3


From 8d40854fc180b7d39bf08cc76fbb9a60bcd65f14 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Fri, 6 Jul 2018 11:28:04 +0100
Subject: net: hns3: Prevent sending command during global or core reset

According to hardware's description, driver should not send command to
IMP while hardware doing global or core reset.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c  | 4 +++-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 ++
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 +
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 82cf12a07dc0..eca4b23fd0a8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -206,7 +206,8 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 
 	spin_lock_bh(&hw->cmq.csq.lock);
 
-	if (num > hclge_ring_space(&hw->cmq.csq)) {
+	if (num > hclge_ring_space(&hw->cmq.csq) ||
+	    test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state)) {
 		spin_unlock_bh(&hw->cmq.csq.lock);
 		return -EBUSY;
 	}
@@ -346,6 +347,7 @@ int hclge_cmd_init(struct hclge_dev *hdev)
 	spin_lock_init(&hdev->hw.cmq.crq.lock);
 
 	hclge_cmd_init_regs(&hdev->hw);
+	clear_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 
 	ret = hclge_cmd_query_firmware_version(&hdev->hw, &version);
 	if (ret) {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 4ca3e6b42f4f..8bbf4e5c0032 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2507,12 +2507,14 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 
 	/* check for vector0 reset event sources */
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & rst_src_reg) {
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
 		return HCLGE_VECTOR0_EVENT_RST;
 	}
 
 	if (BIT(HCLGE_VECTOR0_CORERESET_INT_B) & rst_src_reg) {
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
 		set_bit(HNAE3_CORE_RESET, &hdev->reset_pending);
 		*clearval = BIT(HCLGE_VECTOR0_CORERESET_INT_B);
 		return HCLGE_VECTOR0_EVENT_RST;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 71d38b852c56..20abe828e30b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -128,6 +128,7 @@ enum HCLGE_DEV_STATE {
 	HCLGE_STATE_MBX_SERVICE_SCHED,
 	HCLGE_STATE_MBX_HANDLING,
 	HCLGE_STATE_STATISTICS_UPDATING,
+	HCLGE_STATE_CMD_DISABLE,
 	HCLGE_STATE_MAX
 };
 
-- 
cgit v1.2.3


From 73915b2b1f2581cbce5a511550c2cac2e2b42595 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 19:40:46 +0200
Subject: drm/writeback: Fix the "overview" section of the doc

Fix the bullet list declaration in the overview section.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reported-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Fixes: 935774cd71fe ("drm: Add writeback connector type")
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703174046.22396-1-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_writeback.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index 827395071f0b..69e7a63cfcc3 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -22,10 +22,13 @@
  * Writeback connectors are used to expose hardware which can write the output
  * from a CRTC to a memory buffer. They are used and act similarly to other
  * types of connectors, with some important differences:
- *  - Writeback connectors don't provide a way to output visually to the user.
- *  - Writeback connectors should always report as "disconnected" (so that
- *    clients which don't understand them will ignore them).
- *  - Writeback connectors don't have EDID.
+ *
+ * * Writeback connectors don't provide a way to output visually to the user.
+ *
+ * * Writeback connectors should always report as "disconnected" (so that
+ *   clients which don't understand them will ignore them).
+ *
+ * * Writeback connectors don't have EDID.
  *
  * A framebuffer may only be attached to a writeback connector when the
  * connector is attached to a CRTC. The WRITEBACK_FB_ID property which sets the
-- 
cgit v1.2.3


From b82c1f8f78b4d273d1bcefe3e805eff61e879a68 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 09:50:15 +0200
Subject: drm/atomic: Avoid connector to writeback_connector casts

Use container_of() instead of type casting so that it keeps working
even if base is moved inside the drm_writeback_connector struct.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-2-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_atomic.c | 4 +++-
 include/drm/drm_writeback.h  | 6 ++++++
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_atomic.c b/drivers/gpu/drm/drm_atomic.c
index e6062c779aaf..3eb061e11e2e 100644
--- a/drivers/gpu/drm/drm_atomic.c
+++ b/drivers/gpu/drm/drm_atomic.c
@@ -2428,6 +2428,7 @@ static int prepare_signaling(struct drm_device *dev,
 	}
 
 	for_each_new_connector_in_state(state, conn, conn_state, i) {
+		struct drm_writeback_connector *wb_conn;
 		struct drm_writeback_job *job;
 		struct drm_out_fence_state *f;
 		struct dma_fence *fence;
@@ -2451,7 +2452,8 @@ static int prepare_signaling(struct drm_device *dev,
 		f[*num_fences].out_fence_ptr = fence_ptr;
 		*fence_state = f;
 
-		fence = drm_writeback_get_out_fence((struct drm_writeback_connector *)conn);
+		wb_conn = drm_connector_to_writeback(conn);
+		fence = drm_writeback_get_out_fence(wb_conn);
 		if (!fence)
 			return -ENOMEM;
 
diff --git a/include/drm/drm_writeback.h b/include/drm/drm_writeback.h
index a10fe556dfd4..23df9d463003 100644
--- a/include/drm/drm_writeback.h
+++ b/include/drm/drm_writeback.h
@@ -110,6 +110,12 @@ struct drm_writeback_job {
 	struct dma_fence *out_fence;
 };
 
+static inline struct drm_writeback_connector *
+drm_connector_to_writeback(struct drm_connector *connector)
+{
+	return container_of(connector, struct drm_writeback_connector, base);
+}
+
 int drm_writeback_connector_init(struct drm_device *dev,
 				 struct drm_writeback_connector *wb_connector,
 				 const struct drm_connector_funcs *con_funcs,
-- 
cgit v1.2.3


From 425132fdb169c2a2772190ff56e0e8eea37ff716 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 09:50:16 +0200
Subject: drm/connector: Pass a drm_connector_state to ->atomic_commit()

Other atomic hooks are passed state objects, let's change this one to
be consistent.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-3-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_atomic_helper.c      | 2 +-
 include/drm/drm_modeset_helper_vtables.h | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 7787e0e6bbc6..47e84aa7b6e2 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1187,7 +1187,7 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev,
 
 		if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) {
 			WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
-			funcs->atomic_commit(connector, new_conn_state->writeback_job);
+			funcs->atomic_commit(connector, new_conn_state);
 		}
 	}
 }
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index 3b289773297c..fb841f44949c 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -980,11 +980,13 @@ struct drm_connector_helper_funcs {
 	 *
 	 * This hook is to be used by drivers implementing writeback connectors
 	 * that need a point when to commit the writeback job to the hardware.
+	 * The writeback_job to commit is available in
+	 * &drm_connector_state.writeback_job.
 	 *
 	 * This callback is used by the atomic modeset helpers.
 	 */
 	void (*atomic_commit)(struct drm_connector *connector,
-			      struct drm_writeback_job *writeback_job);
+			      struct drm_connector_state *state);
 };
 
 /**
-- 
cgit v1.2.3


From 814bde99ee809c172a409829889d1bafc3e4bcf7 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 09:50:17 +0200
Subject: drm/connector: Make ->atomic_commit() optional

Not all writeback connector implementations might want to commit things
from the connector driver. Some, like the malidp driver, commit things
from their main commit_tail() function, and would rather not have to
implement a dummy hook for drm_connector_helper_funcs.atomic_commit().

Make this function optional and reflect this fact in the doc.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-4-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_atomic_helper.c      | 2 ++
 include/drm/drm_modeset_helper_vtables.h | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 47e84aa7b6e2..bab8051690bb 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1184,6 +1184,8 @@ static void drm_atomic_helper_commit_writebacks(struct drm_device *dev,
 		const struct drm_connector_helper_funcs *funcs;
 
 		funcs = connector->helper_private;
+		if (!funcs->atomic_commit)
+			continue;
 
 		if (new_conn_state->writeback_job && new_conn_state->writeback_job->fb) {
 			WARN_ON(connector->connector_type != DRM_MODE_CONNECTOR_WRITEBACK);
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index fb841f44949c..d0eb76c4b309 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -983,6 +983,8 @@ struct drm_connector_helper_funcs {
 	 * The writeback_job to commit is available in
 	 * &drm_connector_state.writeback_job.
 	 *
+	 * This hook is optional.
+	 *
 	 * This callback is used by the atomic modeset helpers.
 	 */
 	void (*atomic_commit)(struct drm_connector *connector,
-- 
cgit v1.2.3


From 184d3cf4f73896267340cf06acfa751fad4f8dd2 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 09:50:18 +0200
Subject: drm/vc4: Use wait_for_flip_done() instead of wait_for_vblanks()

drm_atomic_helper_wait_for_vblanks() assumes the CRTC will continuously
generate VBLANK events and the vblank counter will keep increasing.
While this work for a regular pipeline, it doesn't when you have the
CRTC is feeding the transposer block, because this block works in
oneshot mode, and, by the time we reach
drm_atomic_helper_wait_for_vblanks() the only VBLANK event might have
already been sent and the VBLANK counter will stay unchanged, thus
triggering a timeout.

Luckily, we can replace the drm_atomic_helper_wait_for_vblanks() call
by drm_atomic_helper_wait_for_flip_done() because the only thing we
want to check when calling drm_atomic_helper_wait_for_vblanks() from
vc4_atomic_complete_commit() is that new FBs are in use and the old
ones can be safely released.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-5-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/vc4/vc4_kms.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 8a411e5f8776..91239b0a4fa0 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -153,18 +153,9 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
-	/* Make sure that drm_atomic_helper_wait_for_vblanks()
-	 * actually waits for vblank.  If we're doing a full atomic
-	 * modeset (as opposed to a vc4_update_plane() short circuit),
-	 * then we need to wait for scanout to be done with our
-	 * display lists before we free it and potentially reallocate
-	 * and overwrite the dlist memory with a new modeset.
-	 */
-	state->legacy_cursor_update = false;
-
 	drm_atomic_helper_commit_hw_done(state);
 
-	drm_atomic_helper_wait_for_vblanks(dev, state);
+	drm_atomic_helper_wait_for_flip_done(dev, state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
 
-- 
cgit v1.2.3


From b25c60af7a8773694a505cdb0d2e67807243217d Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 09:50:19 +0200
Subject: drm/crtc: Add a generic infrastructure to fake VBLANK events

In some cases CRTCs are active but are not able to generating events, at
least not at every frame at it's expected to.
This is typically the case when the CRTC is feeding a writeback connector
that has no job queued. In this situation the CRTC is usually stopped
until a new job is queued, and this can lead to timeouts when part of
the pipeline is updated but no new jobs are queued to the active
writeback connector.

In order to solve that, we add a ->no_vblank flag to drm_crtc_state
and ask the CRTC drivers to set it to true when they know they're not
able to generate VBLANK events. The core drm_atomic_helper_fake_vblank()
helper can then be used to fake VBLANKs at commit time.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-6-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_atomic_helper.c | 39 +++++++++++++++++++++++++++++++++++++
 include/drm/drm_atomic_helper.h     |  1 +
 include/drm/drm_crtc.h              | 23 ++++++++++++++++++++++
 3 files changed, 63 insertions(+)

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index bab8051690bb..c31f670b1283 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2053,6 +2053,45 @@ void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *old_state)
 }
 EXPORT_SYMBOL(drm_atomic_helper_wait_for_dependencies);
 
+/**
+ * drm_atomic_helper_fake_vblank - fake VBLANK events if needed
+ * @old_state: atomic state object with old state structures
+ *
+ * This function walks all CRTCs and fake VBLANK events on those with
+ * &drm_crtc_state.no_vblank set to true and &drm_crtc_state.event != NULL.
+ * The primary use of this function is writeback connectors working in oneshot
+ * mode and faking VBLANK events. In this case they only fake the VBLANK event
+ * when a job is queued, and any change to the pipeline that does not touch the
+ * connector is leading to timeouts when calling
+ * drm_atomic_helper_wait_for_vblanks() or
+ * drm_atomic_helper_wait_for_flip_done().
+ *
+ * This is part of the atomic helper support for nonblocking commits, see
+ * drm_atomic_helper_setup_commit() for an overview.
+ */
+void drm_atomic_helper_fake_vblank(struct drm_atomic_state *old_state)
+{
+	struct drm_crtc_state *new_crtc_state;
+	struct drm_crtc *crtc;
+	int i;
+
+	for_each_new_crtc_in_state(old_state, crtc, new_crtc_state, i) {
+		unsigned long flags;
+
+		if (!new_crtc_state->no_vblank)
+			continue;
+
+		spin_lock_irqsave(&old_state->dev->event_lock, flags);
+		if (new_crtc_state->event) {
+			drm_crtc_send_vblank_event(crtc,
+						   new_crtc_state->event);
+			new_crtc_state->event = NULL;
+		}
+		spin_unlock_irqrestore(&old_state->dev->event_lock, flags);
+	}
+}
+EXPORT_SYMBOL(drm_atomic_helper_fake_vblank);
+
 /**
  * drm_atomic_helper_commit_hw_done - setup possible nonblocking commit
  * @old_state: atomic state object with old state structures
diff --git a/include/drm/drm_atomic_helper.h b/include/drm/drm_atomic_helper.h
index 26aaba58d6ce..99e2a5297c69 100644
--- a/include/drm/drm_atomic_helper.h
+++ b/include/drm/drm_atomic_helper.h
@@ -100,6 +100,7 @@ int __must_check drm_atomic_helper_swap_state(struct drm_atomic_state *state,
 int drm_atomic_helper_setup_commit(struct drm_atomic_state *state,
 				   bool nonblock);
 void drm_atomic_helper_wait_for_dependencies(struct drm_atomic_state *state);
+void drm_atomic_helper_fake_vblank(struct drm_atomic_state *state);
 void drm_atomic_helper_commit_hw_done(struct drm_atomic_state *state);
 void drm_atomic_helper_commit_cleanup_done(struct drm_atomic_state *state);
 
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 23eddbccab10..17f4f93340b8 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -119,6 +119,29 @@ struct drm_crtc_state {
 	bool zpos_changed : 1;
 	bool color_mgmt_changed : 1;
 
+	/**
+	 * @no_vblank:
+	 *
+	 * Reflects the ability of a CRTC to send VBLANK events. This state
+	 * usually depends on the pipeline configuration, and the main usuage
+	 * is CRTCs feeding a writeback connector operating in oneshot mode.
+	 * In this case the VBLANK event is only generated when a job is queued
+	 * to the writeback connector, and we want the core to fake VBLANK
+	 * events when this part of the pipeline hasn't changed but others had
+	 * or when the CRTC and connectors are being disabled.
+	 *
+	 * __drm_atomic_helper_crtc_duplicate_state() will not reset the value
+	 * from the current state, the CRTC driver is then responsible for
+	 * updating this field when needed.
+	 *
+	 * Note that the combination of &drm_crtc_state.event == NULL and
+	 * &drm_crtc_state.no_blank == true is valid and usually used when the
+	 * writeback connector attached to the CRTC has a new job queued. In
+	 * this case the driver will send the VBLANK event on its own when the
+	 * writeback job is complete.
+	 */
+	bool no_vblank : 1;
+
 	/* attached planes bitmask:
 	 * WARNING: transitional helpers do not maintain plane_mask so
 	 * drivers not converted over to atomic helpers should not rely
-- 
cgit v1.2.3


From 6fb42b6682f0d3c6ca9dc0e338c294fb92448e1d Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 09:50:20 +0200
Subject: drm/atomic: Call fake_vblank() from the generic commit_tail() helpers

Now that we have a way to fake VBLANK events when requested by the CRTC
hook it up to the generic commit_tail() helpers.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-7-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_atomic_helper.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index c31f670b1283..91fda6b8926e 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -1450,6 +1450,8 @@ void drm_atomic_helper_commit_tail(struct drm_atomic_state *old_state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, old_state);
 
+	drm_atomic_helper_fake_vblank(old_state);
+
 	drm_atomic_helper_commit_hw_done(old_state);
 
 	drm_atomic_helper_wait_for_vblanks(dev, old_state);
@@ -1479,6 +1481,8 @@ void drm_atomic_helper_commit_tail_rpm(struct drm_atomic_state *old_state)
 	drm_atomic_helper_commit_planes(dev, old_state,
 					DRM_PLANE_COMMIT_ACTIVE_ONLY);
 
+	drm_atomic_helper_fake_vblank(old_state);
+
 	drm_atomic_helper_commit_hw_done(old_state);
 
 	drm_atomic_helper_wait_for_vblanks(dev, old_state);
-- 
cgit v1.2.3


From 1ebe99a75eeda1067c39c1c039ca9bb7e3c9c342 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Tue, 3 Jul 2018 09:50:21 +0200
Subject: drm/vc4: Call drm_atomic_helper_fake_vblank() in the commit path

Mimic what is done in drm_atomic_commit_tail() and call
drm_atomic_helper_fake_vblank() so that VBLANK events are faked
when the drm_crtc_state.no_vblank is true. Will be needed when we'll
add support for the transposer block.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-8-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/vc4/vc4_kms.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index 91239b0a4fa0..ca5aa7fba769 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -153,6 +153,8 @@ vc4_atomic_complete_commit(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
+	drm_atomic_helper_fake_vblank(state);
+
 	drm_atomic_helper_commit_hw_done(state);
 
 	drm_atomic_helper_wait_for_flip_done(dev, state);
-- 
cgit v1.2.3


From 008095e065a85a13ffb41b9c98149456267c30b8 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@free-electrons.com>
Date: Tue, 3 Jul 2018 09:50:22 +0200
Subject: drm/vc4: Add support for the transposer block

The transposer block is providing support for mem-to-mem composition,
which is exposed as a drm_writeback connector in DRM.

Add a driver to support this feature.

Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703075022.15138-9-boris.brezillon@bootlin.com
---
 .../devicetree/bindings/display/brcm,bcm-vc4.txt   |   6 +
 drivers/gpu/drm/vc4/Makefile                       |   1 +
 drivers/gpu/drm/vc4/vc4_crtc.c                     | 138 ++++--
 drivers/gpu/drm/vc4/vc4_debugfs.c                  |   1 +
 drivers/gpu/drm/vc4/vc4_drv.c                      |   1 +
 drivers/gpu/drm/vc4/vc4_drv.h                      |   7 +
 drivers/gpu/drm/vc4/vc4_txp.c                      | 477 +++++++++++++++++++++
 7 files changed, 607 insertions(+), 24 deletions(-)
 create mode 100644 drivers/gpu/drm/vc4/vc4_txp.c

diff --git a/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt b/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt
index 284e2b14cfbe..26649b4c4dd8 100644
--- a/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt
+++ b/Documentation/devicetree/bindings/display/brcm,bcm-vc4.txt
@@ -74,6 +74,12 @@ Required properties for DSI:
 		The 3 clocks output from the DSI analog PHY: dsi[01]_byte,
 		dsi[01]_ddr2, and dsi[01]_ddr
 
+Required properties for the TXP (writeback) block:
+- compatible:	Should be "brcm,bcm2835-txp"
+- reg:		Physical base address and length of the TXP block's registers
+- interrupts:	The interrupt number
+		  See bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
+
 [1] Documentation/devicetree/bindings/media/video-interfaces.txt
 
 Example:
diff --git a/drivers/gpu/drm/vc4/Makefile b/drivers/gpu/drm/vc4/Makefile
index 4a3a868235f8..b303703bc7f3 100644
--- a/drivers/gpu/drm/vc4/Makefile
+++ b/drivers/gpu/drm/vc4/Makefile
@@ -19,6 +19,7 @@ vc4-y := \
 	vc4_plane.o \
 	vc4_render_cl.o \
 	vc4_trace_points.o \
+	vc4_txp.o \
 	vc4_v3d.o \
 	vc4_validate.o \
 	vc4_validate_shaders.o
diff --git a/drivers/gpu/drm/vc4/vc4_crtc.c b/drivers/gpu/drm/vc4/vc4_crtc.c
index d222358fa8a7..0e6a121858d1 100644
--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -46,6 +46,8 @@ struct vc4_crtc_state {
 	struct drm_crtc_state base;
 	/* Dlist area for this CRTC configuration. */
 	struct drm_mm_node mm;
+	bool feed_txp;
+	bool txp_armed;
 };
 
 static inline struct vc4_crtc_state *
@@ -324,10 +326,8 @@ static struct drm_encoder *vc4_get_crtc_encoder(struct drm_crtc *crtc)
 	return NULL;
 }
 
-static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
+static void vc4_crtc_config_pv(struct drm_crtc *crtc)
 {
-	struct drm_device *dev = crtc->dev;
-	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct drm_encoder *encoder = vc4_get_crtc_encoder(crtc);
 	struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
@@ -338,12 +338,6 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	bool is_dsi = (vc4_encoder->type == VC4_ENCODER_TYPE_DSI0 ||
 		       vc4_encoder->type == VC4_ENCODER_TYPE_DSI1);
 	u32 format = is_dsi ? PV_CONTROL_FORMAT_DSIV_24 : PV_CONTROL_FORMAT_24;
-	bool debug_dump_regs = false;
-
-	if (debug_dump_regs) {
-		DRM_INFO("CRTC %d regs before:\n", drm_crtc_index(crtc));
-		vc4_crtc_dump_regs(vc4_crtc);
-	}
 
 	/* Reset the PV fifo. */
 	CRTC_WRITE(PV_CONTROL, 0);
@@ -419,6 +413,49 @@ static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
 				 PV_CONTROL_CLK_SELECT) |
 		   PV_CONTROL_FIFO_CLR |
 		   PV_CONTROL_EN);
+}
+
+static void vc4_crtc_mode_set_nofb(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
+	bool interlace = mode->flags & DRM_MODE_FLAG_INTERLACE;
+	bool debug_dump_regs = false;
+
+	if (debug_dump_regs) {
+		DRM_INFO("CRTC %d regs before:\n", drm_crtc_index(crtc));
+		vc4_crtc_dump_regs(vc4_crtc);
+	}
+
+	if (vc4_crtc->channel == 2) {
+		u32 dispctrl;
+		u32 dsp3_mux;
+
+		/*
+		 * SCALER_DISPCTRL_DSP3 = X, where X < 2 means 'connect DSP3 to
+		 * FIFO X'.
+		 * SCALER_DISPCTRL_DSP3 = 3 means 'disable DSP 3'.
+		 *
+		 * DSP3 is connected to FIFO2 unless the transposer is
+		 * enabled. In this case, FIFO 2 is directly accessed by the
+		 * TXP IP, and we need to disable the FIFO2 -> pixelvalve1
+		 * route.
+		 */
+		if (vc4_state->feed_txp)
+			dsp3_mux = VC4_SET_FIELD(3, SCALER_DISPCTRL_DSP3_MUX);
+		else
+			dsp3_mux = VC4_SET_FIELD(2, SCALER_DISPCTRL_DSP3_MUX);
+
+		dispctrl = HVS_READ(SCALER_DISPCTRL) &
+			   ~SCALER_DISPCTRL_DSP3_MUX_MASK;
+		HVS_WRITE(SCALER_DISPCTRL, dispctrl | dsp3_mux);
+	}
+
+	if (!vc4_state->feed_txp)
+		vc4_crtc_config_pv(crtc);
 
 	HVS_WRITE(SCALER_DISPBKGNDX(vc4_crtc->channel),
 		  SCALER_DISPBKGND_AUTOHS |
@@ -499,6 +536,13 @@ static void vc4_crtc_atomic_disable(struct drm_crtc *crtc,
 	}
 }
 
+void vc4_crtc_txp_armed(struct drm_crtc_state *state)
+{
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(state);
+
+	vc4_state->txp_armed = true;
+}
+
 static void vc4_crtc_update_dlist(struct drm_crtc *crtc)
 {
 	struct drm_device *dev = crtc->dev;
@@ -514,8 +558,11 @@ static void vc4_crtc_update_dlist(struct drm_crtc *crtc)
 		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
 
 		spin_lock_irqsave(&dev->event_lock, flags);
-		vc4_crtc->event = crtc->state->event;
-		crtc->state->event = NULL;
+
+		if (!vc4_state->feed_txp || vc4_state->txp_armed) {
+			vc4_crtc->event = crtc->state->event;
+			crtc->state->event = NULL;
+		}
 
 		HVS_WRITE(SCALER_DISPLISTX(vc4_crtc->channel),
 			  vc4_state->mm.start);
@@ -533,8 +580,8 @@ static void vc4_crtc_atomic_enable(struct drm_crtc *crtc,
 	struct drm_device *dev = crtc->dev;
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_crtc *vc4_crtc = to_vc4_crtc(crtc);
-	struct drm_crtc_state *state = crtc->state;
-	struct drm_display_mode *mode = &state->adjusted_mode;
+	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc->state);
+	struct drm_display_mode *mode = &crtc->state->adjusted_mode;
 
 	require_hvs_enabled(dev);
 
@@ -546,15 +593,21 @@ static void vc4_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	/* Turn on the scaler, which will wait for vstart to start
 	 * compositing.
+	 * When feeding the transposer, we should operate in oneshot
+	 * mode.
 	 */
 	HVS_WRITE(SCALER_DISPCTRLX(vc4_crtc->channel),
 		  VC4_SET_FIELD(mode->hdisplay, SCALER_DISPCTRLX_WIDTH) |
 		  VC4_SET_FIELD(mode->vdisplay, SCALER_DISPCTRLX_HEIGHT) |
-		  SCALER_DISPCTRLX_ENABLE);
+		  SCALER_DISPCTRLX_ENABLE |
+		  (vc4_state->feed_txp ? SCALER_DISPCTRLX_ONESHOT : 0));
 
-	/* Turn on the pixel valve, which will emit the vstart signal. */
-	CRTC_WRITE(PV_V_CONTROL,
-		   CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN);
+	/* When feeding the transposer block the pixelvalve is unneeded and
+	 * should not be enabled.
+	 */
+	if (!vc4_state->feed_txp)
+		CRTC_WRITE(PV_V_CONTROL,
+			   CRTC_READ(PV_V_CONTROL) | PV_VCONTROL_VIDEN);
 }
 
 static enum drm_mode_status vc4_crtc_mode_valid(struct drm_crtc *crtc,
@@ -579,8 +632,10 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	struct drm_plane *plane;
 	unsigned long flags;
 	const struct drm_plane_state *plane_state;
+	struct drm_connector *conn;
+	struct drm_connector_state *conn_state;
 	u32 dlist_count = 0;
-	int ret;
+	int ret, i;
 
 	/* The pixelvalve can only feed one encoder (and encoders are
 	 * 1:1 with connectors.)
@@ -600,6 +655,24 @@ static int vc4_crtc_atomic_check(struct drm_crtc *crtc,
 	if (ret)
 		return ret;
 
+	for_each_new_connector_in_state(state->state, conn, conn_state, i) {
+		if (conn_state->crtc != crtc)
+			continue;
+
+		/* The writeback connector is implemented using the transposer
+		 * block which is directly taking its data from the HVS FIFO.
+		 */
+		if (conn->connector_type == DRM_MODE_CONNECTOR_WRITEBACK) {
+			state->no_vblank = true;
+			vc4_state->feed_txp = true;
+		} else {
+			state->no_vblank = false;
+			vc4_state->feed_txp = false;
+		}
+
+		break;
+	}
+
 	return 0;
 }
 
@@ -713,7 +786,8 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (vc4_crtc->event &&
-	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)))) {
+	    (vc4_state->mm.start == HVS_READ(SCALER_DISPLACTX(chan)) ||
+	     vc4_state->feed_txp)) {
 		drm_crtc_send_vblank_event(crtc, vc4_crtc->event);
 		vc4_crtc->event = NULL;
 		drm_crtc_vblank_put(crtc);
@@ -721,6 +795,13 @@ static void vc4_crtc_handle_page_flip(struct vc4_crtc *vc4_crtc)
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 }
 
+void vc4_crtc_handle_vblank(struct vc4_crtc *crtc)
+{
+	crtc->t_vblank = ktime_get();
+	drm_crtc_handle_vblank(&crtc->base);
+	vc4_crtc_handle_page_flip(crtc);
+}
+
 static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 {
 	struct vc4_crtc *vc4_crtc = data;
@@ -728,10 +809,8 @@ static irqreturn_t vc4_crtc_irq_handler(int irq, void *data)
 	irqreturn_t ret = IRQ_NONE;
 
 	if (stat & PV_INT_VFP_START) {
-		vc4_crtc->t_vblank = ktime_get();
 		CRTC_WRITE(PV_INTSTAT, PV_INT_VFP_START);
-		drm_crtc_handle_vblank(&vc4_crtc->base);
-		vc4_crtc_handle_page_flip(vc4_crtc);
+		vc4_crtc_handle_vblank(vc4_crtc);
 		ret = IRQ_HANDLED;
 	}
 
@@ -884,12 +963,15 @@ static int vc4_page_flip(struct drm_crtc *crtc,
 
 static struct drm_crtc_state *vc4_crtc_duplicate_state(struct drm_crtc *crtc)
 {
-	struct vc4_crtc_state *vc4_state;
+	struct vc4_crtc_state *vc4_state, *old_vc4_state;
 
 	vc4_state = kzalloc(sizeof(*vc4_state), GFP_KERNEL);
 	if (!vc4_state)
 		return NULL;
 
+	old_vc4_state = to_vc4_crtc_state(crtc->state);
+	vc4_state->feed_txp = old_vc4_state->feed_txp;
+
 	__drm_atomic_helper_crtc_duplicate_state(crtc, &vc4_state->base);
 	return &vc4_state->base;
 }
@@ -987,9 +1069,17 @@ static void vc4_set_crtc_possible_masks(struct drm_device *drm,
 	struct drm_encoder *encoder;
 
 	drm_for_each_encoder(encoder, drm) {
-		struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
+		struct vc4_encoder *vc4_encoder;
 		int i;
 
+		/* HVS FIFO2 can feed the TXP IP. */
+		if (crtc_data->hvs_channel == 2 &&
+		    encoder->encoder_type == DRM_MODE_ENCODER_VIRTUAL) {
+			encoder->possible_crtcs |= drm_crtc_mask(crtc);
+			continue;
+		}
+
+		vc4_encoder = to_vc4_encoder(encoder);
 		for (i = 0; i < ARRAY_SIZE(crtc_data->encoder_types); i++) {
 			if (vc4_encoder->type == encoder_types[i]) {
 				vc4_encoder->clock_select = i;
diff --git a/drivers/gpu/drm/vc4/vc4_debugfs.c b/drivers/gpu/drm/vc4/vc4_debugfs.c
index 5db06bdb5f27..7a0003de71ab 100644
--- a/drivers/gpu/drm/vc4/vc4_debugfs.c
+++ b/drivers/gpu/drm/vc4/vc4_debugfs.c
@@ -21,6 +21,7 @@ static const struct drm_info_list vc4_debugfs_list[] = {
 	{"dsi1_regs", vc4_dsi_debugfs_regs, 0, (void *)(uintptr_t)1},
 	{"hdmi_regs", vc4_hdmi_debugfs_regs, 0},
 	{"vec_regs", vc4_vec_debugfs_regs, 0},
+	{"txp_regs", vc4_txp_debugfs_regs, 0},
 	{"hvs_regs", vc4_hvs_debugfs_regs, 0},
 	{"crtc0_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)0},
 	{"crtc1_regs", vc4_crtc_debugfs_regs, 0, (void *)(uintptr_t)1},
diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index 466d0a27b415..e42fd5ec41cc 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -344,6 +344,7 @@ static struct platform_driver *const component_drivers[] = {
 	&vc4_vec_driver,
 	&vc4_dpi_driver,
 	&vc4_dsi_driver,
+	&vc4_txp_driver,
 	&vc4_hvs_driver,
 	&vc4_crtc_driver,
 	&vc4_v3d_driver,
diff --git a/drivers/gpu/drm/vc4/vc4_drv.h b/drivers/gpu/drm/vc4/vc4_drv.h
index eace76c621a1..bd6ef1f31822 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -73,6 +73,7 @@ struct vc4_dev {
 	struct vc4_dpi *dpi;
 	struct vc4_dsi *dsi1;
 	struct vc4_vec *vec;
+	struct vc4_txp *txp;
 
 	struct vc4_hang_state *hang_state;
 
@@ -698,6 +699,8 @@ bool vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
 			     bool in_vblank_irq, int *vpos, int *hpos,
 			     ktime_t *stime, ktime_t *etime,
 			     const struct drm_display_mode *mode);
+void vc4_crtc_handle_vblank(struct vc4_crtc *crtc);
+void vc4_crtc_txp_armed(struct drm_crtc_state *state);
 
 /* vc4_debugfs.c */
 int vc4_debugfs_init(struct drm_minor *minor);
@@ -745,6 +748,10 @@ int vc4_hdmi_debugfs_regs(struct seq_file *m, void *unused);
 extern struct platform_driver vc4_vec_driver;
 int vc4_vec_debugfs_regs(struct seq_file *m, void *unused);
 
+/* vc4_txp.c */
+extern struct platform_driver vc4_txp_driver;
+int vc4_txp_debugfs_regs(struct seq_file *m, void *unused);
+
 /* vc4_irq.c */
 irqreturn_t vc4_irq(int irq, void *arg);
 void vc4_irq_preinstall(struct drm_device *dev);
diff --git a/drivers/gpu/drm/vc4/vc4_txp.c b/drivers/gpu/drm/vc4/vc4_txp.c
new file mode 100644
index 000000000000..6e23c50168f9
--- /dev/null
+++ b/drivers/gpu/drm/vc4/vc4_txp.c
@@ -0,0 +1,477 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright © 2018 Broadcom
+ *
+ * Authors:
+ *	Eric Anholt <eric@anholt.net>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_fb_cma_helper.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_edid.h>
+#include <drm/drm_panel.h>
+#include <drm/drm_writeback.h>
+#include <linux/clk.h>
+#include <linux/component.h>
+#include <linux/of_graph.h>
+#include <linux/of_platform.h>
+#include <linux/pm_runtime.h>
+
+#include "vc4_drv.h"
+#include "vc4_regs.h"
+
+/* Base address of the output.  Raster formats must be 4-byte aligned,
+ * T and LT must be 16-byte aligned or maybe utile-aligned (docs are
+ * inconsistent, but probably utile).
+ */
+#define TXP_DST_PTR		0x00
+
+/* Pitch in bytes for raster images, 16-byte aligned.  For tiled, it's
+ * the width in tiles.
+ */
+#define TXP_DST_PITCH		0x04
+/* For T-tiled imgaes, DST_PITCH should be the number of tiles wide,
+ * shifted up.
+ */
+# define TXP_T_TILE_WIDTH_SHIFT		7
+/* For LT-tiled images, DST_PITCH should be the number of utiles wide,
+ * shifted up.
+ */
+# define TXP_LT_TILE_WIDTH_SHIFT	4
+
+/* Pre-rotation width/height of the image.  Must match HVS config.
+ *
+ * If TFORMAT and 32-bit, limit is 1920 for 32-bit and 3840 to 16-bit
+ * and width/height must be tile or utile-aligned as appropriate.  If
+ * transposing (rotating), width is limited to 1920.
+ *
+ * Height is limited to various numbers between 4088 and 4095.  I'd
+ * just use 4088 to be safe.
+ */
+#define TXP_DIM			0x08
+# define TXP_HEIGHT_SHIFT		16
+# define TXP_HEIGHT_MASK		GENMASK(31, 16)
+# define TXP_WIDTH_SHIFT		0
+# define TXP_WIDTH_MASK			GENMASK(15, 0)
+
+#define TXP_DST_CTRL		0x0c
+/* These bits are set to 0x54 */
+#define TXP_PILOT_SHIFT			24
+#define TXP_PILOT_MASK			GENMASK(31, 24)
+/* Bits 22-23 are set to 0x01 */
+#define TXP_VERSION_SHIFT		22
+#define TXP_VERSION_MASK		GENMASK(23, 22)
+
+/* Powers down the internal memory. */
+# define TXP_POWERDOWN			BIT(21)
+
+/* Enables storing the alpha component in 8888/4444, instead of
+ * filling with ~ALPHA_INVERT.
+ */
+# define TXP_ALPHA_ENABLE		BIT(20)
+
+/* 4 bits, each enables stores for a channel in each set of 4 bytes.
+ * Set to 0xf for normal operation.
+ */
+# define TXP_BYTE_ENABLE_SHIFT		16
+# define TXP_BYTE_ENABLE_MASK		GENMASK(19, 16)
+
+/* Debug: Generate VSTART again at EOF. */
+# define TXP_VSTART_AT_EOF		BIT(15)
+
+/* Debug: Terminate the current frame immediately.  Stops AXI
+ * writes.
+ */
+# define TXP_ABORT			BIT(14)
+
+# define TXP_DITHER			BIT(13)
+
+/* Inverts alpha if TXP_ALPHA_ENABLE, chooses fill value for
+ * !TXP_ALPHA_ENABLE.
+ */
+# define TXP_ALPHA_INVERT		BIT(12)
+
+/* Note: I've listed the channels here in high bit (in byte 3/2/1) to
+ * low bit (in byte 0) order.
+ */
+# define TXP_FORMAT_SHIFT		8
+# define TXP_FORMAT_MASK		GENMASK(11, 8)
+# define TXP_FORMAT_ABGR4444		0
+# define TXP_FORMAT_ARGB4444		1
+# define TXP_FORMAT_BGRA4444		2
+# define TXP_FORMAT_RGBA4444		3
+# define TXP_FORMAT_BGR565		6
+# define TXP_FORMAT_RGB565		7
+/* 888s are non-rotated, raster-only */
+# define TXP_FORMAT_BGR888		8
+# define TXP_FORMAT_RGB888		9
+# define TXP_FORMAT_ABGR8888		12
+# define TXP_FORMAT_ARGB8888		13
+# define TXP_FORMAT_BGRA8888		14
+# define TXP_FORMAT_RGBA8888		15
+
+/* If TFORMAT is set, generates LT instead of T format. */
+# define TXP_LINEAR_UTILE		BIT(7)
+
+/* Rotate output by 90 degrees. */
+# define TXP_TRANSPOSE			BIT(6)
+
+/* Generate a tiled format for V3D. */
+# define TXP_TFORMAT			BIT(5)
+
+/* Generates some undefined test mode output. */
+# define TXP_TEST_MODE			BIT(4)
+
+/* Request odd field from HVS. */
+# define TXP_FIELD			BIT(3)
+
+/* Raise interrupt when idle. */
+# define TXP_EI				BIT(2)
+
+/* Set when generating a frame, clears when idle. */
+# define TXP_BUSY			BIT(1)
+
+/* Starts a frame.  Self-clearing. */
+# define TXP_GO				BIT(0)
+
+/* Number of lines received and committed to memory. */
+#define TXP_PROGRESS		0x10
+
+#define TXP_READ(offset) readl(txp->regs + (offset))
+#define TXP_WRITE(offset, val) writel(val, txp->regs + (offset))
+
+struct vc4_txp {
+	struct platform_device *pdev;
+
+	struct drm_writeback_connector connector;
+
+	void __iomem *regs;
+};
+
+static inline struct vc4_txp *encoder_to_vc4_txp(struct drm_encoder *encoder)
+{
+	return container_of(encoder, struct vc4_txp, connector.encoder);
+}
+
+static inline struct vc4_txp *connector_to_vc4_txp(struct drm_connector *conn)
+{
+	return container_of(conn, struct vc4_txp, connector.base);
+}
+
+#define TXP_REG(reg) { reg, #reg }
+static const struct {
+	u32 reg;
+	const char *name;
+} txp_regs[] = {
+	TXP_REG(TXP_DST_PTR),
+	TXP_REG(TXP_DST_PITCH),
+	TXP_REG(TXP_DIM),
+	TXP_REG(TXP_DST_CTRL),
+	TXP_REG(TXP_PROGRESS),
+};
+
+#ifdef CONFIG_DEBUG_FS
+int vc4_txp_debugfs_regs(struct seq_file *m, void *unused)
+{
+	struct drm_info_node *node = (struct drm_info_node *)m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_txp *txp = vc4->txp;
+	int i;
+
+	if (!txp)
+		return 0;
+
+	for (i = 0; i < ARRAY_SIZE(txp_regs); i++) {
+		seq_printf(m, "%s (0x%04x): 0x%08x\n",
+			   txp_regs[i].name, txp_regs[i].reg,
+			   TXP_READ(txp_regs[i].reg));
+	}
+
+	return 0;
+}
+#endif
+
+static int vc4_txp_connector_get_modes(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+
+	return drm_add_modes_noedid(connector, dev->mode_config.max_width,
+				    dev->mode_config.max_height);
+}
+
+static enum drm_mode_status
+vc4_txp_connector_mode_valid(struct drm_connector *connector,
+			     struct drm_display_mode *mode)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_mode_config *mode_config = &dev->mode_config;
+	int w = mode->hdisplay, h = mode->vdisplay;
+
+	if (w < mode_config->min_width || w > mode_config->max_width)
+		return MODE_BAD_HVALUE;
+
+	if (h < mode_config->min_height || h > mode_config->max_height)
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
+}
+
+static const u32 drm_fmts[] = {
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_RGBX8888,
+	DRM_FORMAT_BGRX8888,
+	DRM_FORMAT_RGBA8888,
+	DRM_FORMAT_BGRA8888,
+};
+
+static const u32 txp_fmts[] = {
+	TXP_FORMAT_RGB888,
+	TXP_FORMAT_BGR888,
+	TXP_FORMAT_ARGB8888,
+	TXP_FORMAT_ABGR8888,
+	TXP_FORMAT_ARGB8888,
+	TXP_FORMAT_ABGR8888,
+	TXP_FORMAT_RGBA8888,
+	TXP_FORMAT_BGRA8888,
+	TXP_FORMAT_RGBA8888,
+	TXP_FORMAT_BGRA8888,
+};
+
+static int vc4_txp_connector_atomic_check(struct drm_connector *conn,
+					struct drm_connector_state *conn_state)
+{
+	struct drm_crtc_state *crtc_state;
+	struct drm_gem_cma_object *gem;
+	struct drm_framebuffer *fb;
+	int i;
+
+	if (!conn_state->writeback_job || !conn_state->writeback_job->fb)
+		return 0;
+
+	crtc_state = drm_atomic_get_new_crtc_state(conn_state->state,
+						   conn_state->crtc);
+
+	fb = conn_state->writeback_job->fb;
+	if (fb->width != crtc_state->mode.hdisplay ||
+	    fb->height != crtc_state->mode.vdisplay) {
+		DRM_DEBUG_KMS("Invalid framebuffer size %ux%u\n",
+			      fb->width, fb->height);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(drm_fmts); i++) {
+		if (fb->format->format == drm_fmts[i])
+			break;
+	}
+
+	if (i == ARRAY_SIZE(drm_fmts))
+		return -EINVAL;
+
+	gem = drm_fb_cma_get_gem_obj(fb, 0);
+
+	/* Pitch must be aligned on 16 bytes. */
+	if (fb->pitches[0] & GENMASK(3, 0))
+		return -EINVAL;
+
+	vc4_crtc_txp_armed(crtc_state);
+
+	return 0;
+}
+
+static void vc4_txp_connector_atomic_commit(struct drm_connector *conn,
+					struct drm_connector_state *conn_state)
+{
+	struct vc4_txp *txp = connector_to_vc4_txp(conn);
+	struct drm_gem_cma_object *gem;
+	struct drm_display_mode *mode;
+	struct drm_framebuffer *fb;
+	u32 ctrl;
+	int i;
+
+	if (WARN_ON(!conn_state->writeback_job ||
+		    !conn_state->writeback_job->fb))
+		return;
+
+	mode = &conn_state->crtc->state->adjusted_mode;
+	fb = conn_state->writeback_job->fb;
+
+	for (i = 0; i < ARRAY_SIZE(drm_fmts); i++) {
+		if (fb->format->format == drm_fmts[i])
+			break;
+	}
+
+	if (WARN_ON(i == ARRAY_SIZE(drm_fmts)))
+		return;
+
+	ctrl = TXP_GO | TXP_VSTART_AT_EOF | TXP_EI |
+	       VC4_SET_FIELD(0xf, TXP_BYTE_ENABLE) |
+	       VC4_SET_FIELD(txp_fmts[i], TXP_FORMAT);
+
+	if (fb->format->has_alpha)
+		ctrl |= TXP_ALPHA_ENABLE;
+
+	gem = drm_fb_cma_get_gem_obj(fb, 0);
+	TXP_WRITE(TXP_DST_PTR, gem->paddr + fb->offsets[0]);
+	TXP_WRITE(TXP_DST_PITCH, fb->pitches[0]);
+	TXP_WRITE(TXP_DIM,
+		  VC4_SET_FIELD(mode->hdisplay, TXP_WIDTH) |
+		  VC4_SET_FIELD(mode->vdisplay, TXP_HEIGHT));
+
+	TXP_WRITE(TXP_DST_CTRL, ctrl);
+
+	drm_writeback_queue_job(&txp->connector, conn_state->writeback_job);
+}
+
+static const struct drm_connector_helper_funcs vc4_txp_connector_helper_funcs = {
+	.get_modes = vc4_txp_connector_get_modes,
+	.mode_valid = vc4_txp_connector_mode_valid,
+	.atomic_check = vc4_txp_connector_atomic_check,
+	.atomic_commit = vc4_txp_connector_atomic_commit,
+};
+
+static enum drm_connector_status
+vc4_txp_connector_detect(struct drm_connector *connector, bool force)
+{
+	return connector_status_connected;
+}
+
+static void vc4_txp_connector_destroy(struct drm_connector *connector)
+{
+	drm_connector_unregister(connector);
+	drm_connector_cleanup(connector);
+}
+
+static const struct drm_connector_funcs vc4_txp_connector_funcs = {
+	.detect = vc4_txp_connector_detect,
+	.fill_modes = drm_helper_probe_single_connector_modes,
+	.destroy = vc4_txp_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+};
+
+static void vc4_txp_encoder_disable(struct drm_encoder *encoder)
+{
+	struct vc4_txp *txp = encoder_to_vc4_txp(encoder);
+
+	if (TXP_READ(TXP_DST_CTRL) & TXP_BUSY) {
+		unsigned long timeout = jiffies + msecs_to_jiffies(1000);
+
+		TXP_WRITE(TXP_DST_CTRL, TXP_ABORT);
+
+		while (TXP_READ(TXP_DST_CTRL) & TXP_BUSY &&
+		       time_before(jiffies, timeout))
+			;
+
+		WARN_ON(TXP_READ(TXP_DST_CTRL) & TXP_BUSY);
+	}
+
+	TXP_WRITE(TXP_DST_CTRL, TXP_POWERDOWN);
+}
+
+static const struct drm_encoder_helper_funcs vc4_txp_encoder_helper_funcs = {
+	.disable = vc4_txp_encoder_disable,
+};
+
+static irqreturn_t vc4_txp_interrupt(int irq, void *data)
+{
+	struct vc4_txp *txp = data;
+
+	TXP_WRITE(TXP_DST_CTRL, TXP_READ(TXP_DST_CTRL) & ~TXP_EI);
+	vc4_crtc_handle_vblank(to_vc4_crtc(txp->connector.base.state->crtc));
+	drm_writeback_signal_completion(&txp->connector, 0);
+
+	return IRQ_HANDLED;
+}
+
+static int vc4_txp_bind(struct device *dev, struct device *master, void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct drm_device *drm = dev_get_drvdata(master);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_txp *txp;
+	int ret, irq;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	txp = devm_kzalloc(dev, sizeof(*txp), GFP_KERNEL);
+	if (!txp)
+		return -ENOMEM;
+
+	txp->pdev = pdev;
+
+	txp->regs = vc4_ioremap_regs(pdev, 0);
+	if (IS_ERR(txp->regs))
+		return PTR_ERR(txp->regs);
+
+	drm_connector_helper_add(&txp->connector.base,
+				 &vc4_txp_connector_helper_funcs);
+	ret = drm_writeback_connector_init(drm, &txp->connector,
+					   &vc4_txp_connector_funcs,
+					   &vc4_txp_encoder_helper_funcs,
+					   drm_fmts, ARRAY_SIZE(drm_fmts));
+	if (ret)
+		return ret;
+
+	ret = devm_request_irq(dev, irq, vc4_txp_interrupt, 0,
+			       dev_name(dev), txp);
+	if (ret)
+		return ret;
+
+	dev_set_drvdata(dev, txp);
+	vc4->txp = txp;
+
+	return 0;
+}
+
+static void vc4_txp_unbind(struct device *dev, struct device *master,
+			   void *data)
+{
+	struct drm_device *drm = dev_get_drvdata(master);
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	struct vc4_txp *txp = dev_get_drvdata(dev);
+
+	vc4_txp_connector_destroy(&txp->connector.base);
+
+	vc4->txp = NULL;
+}
+
+static const struct component_ops vc4_txp_ops = {
+	.bind   = vc4_txp_bind,
+	.unbind = vc4_txp_unbind,
+};
+
+static int vc4_txp_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &vc4_txp_ops);
+}
+
+static int vc4_txp_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &vc4_txp_ops);
+	return 0;
+}
+
+static const struct of_device_id vc4_txp_dt_match[] = {
+	{ .compatible = "brcm,bcm2835-txp" },
+	{ /* sentinel */ },
+};
+
+struct platform_driver vc4_txp_driver = {
+	.probe = vc4_txp_probe,
+	.remove = vc4_txp_remove,
+	.driver = {
+		.name = "vc4_txp",
+		.of_match_table = vc4_txp_dt_match,
+	},
+};
-- 
cgit v1.2.3


From 890fd185d53037d05d10a0825950c4b038e39d4a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 6 Jul 2018 22:07:10 +0100
Subject: drm/i915: Replace nested subclassing with explicit subclasses

In the next patch, we will want a third distinct class of timeline that
may overlap with the current pair of client and engine timeline classes.
Rather than use the ad hoc markup of SINGLE_DEPTH_NESTING, initialise
the different timeline classes with an explicit subclass.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706210710.16251-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c              | 2 +-
 drivers/gpu/drm/i915/i915_request.c          | 2 +-
 drivers/gpu/drm/i915/i915_timeline.h         | 2 ++
 drivers/gpu/drm/i915/intel_engine_cs.c       | 1 +
 drivers/gpu/drm/i915/selftests/mock_engine.c | 2 ++
 5 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 2e05cf114083..1a9dab302433 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -3095,7 +3095,7 @@ static void engine_skip_context(struct i915_request *request)
 	GEM_BUG_ON(timeline == &engine->timeline);
 
 	spin_lock_irqsave(&engine->timeline.lock, flags);
-	spin_lock_nested(&timeline->lock, SINGLE_DEPTH_NESTING);
+	spin_lock(&timeline->lock);
 
 	list_for_each_entry_continue(request, &engine->timeline.requests, link)
 		if (request->gem_context == hung_ctx)
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 7ae08b68121e..3248369dbcfb 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -503,7 +503,7 @@ static void move_to_timeline(struct i915_request *request,
 	GEM_BUG_ON(request->timeline == &request->engine->timeline);
 	lockdep_assert_held(&request->engine->timeline.lock);
 
-	spin_lock_nested(&request->timeline->lock, SINGLE_DEPTH_NESTING);
+	spin_lock(&request->timeline->lock);
 	list_move_tail(&request->link, &timeline->requests);
 	spin_unlock(&request->timeline->lock);
 }
diff --git a/drivers/gpu/drm/i915/i915_timeline.h b/drivers/gpu/drm/i915/i915_timeline.h
index dc2a4632faa7..a2c2c3ab5fb0 100644
--- a/drivers/gpu/drm/i915/i915_timeline.h
+++ b/drivers/gpu/drm/i915/i915_timeline.h
@@ -37,6 +37,8 @@ struct i915_timeline {
 	u32 seqno;
 
 	spinlock_t lock;
+#define TIMELINE_CLIENT 0 /* default subclass */
+#define TIMELINE_ENGINE 1
 
 	/**
 	 * List of breadcrumbs associated with GPU requests currently
diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index e2f562853aee..0ac497275a51 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -483,6 +483,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 void intel_engine_setup_common(struct intel_engine_cs *engine)
 {
 	i915_timeline_init(engine->i915, &engine->timeline, engine->name);
+	lockdep_set_subclass(&engine->timeline.lock, TIMELINE_ENGINE);
 
 	intel_engine_init_execlist(engine);
 	intel_engine_init_hangcheck(engine);
diff --git a/drivers/gpu/drm/i915/selftests/mock_engine.c b/drivers/gpu/drm/i915/selftests/mock_engine.c
index c2a0451336cf..22a73da45ad5 100644
--- a/drivers/gpu/drm/i915/selftests/mock_engine.c
+++ b/drivers/gpu/drm/i915/selftests/mock_engine.c
@@ -200,6 +200,8 @@ struct intel_engine_cs *mock_engine(struct drm_i915_private *i915,
 	engine->base.submit_request = mock_submit_request;
 
 	i915_timeline_init(i915, &engine->base.timeline, engine->base.name);
+	lockdep_set_subclass(&engine->base.timeline.lock, TIMELINE_ENGINE);
+
 	intel_engine_init_breadcrumbs(&engine->base);
 	engine->base.breadcrumbs.mock = true; /* prevent touching HW for irqs */
 
-- 
cgit v1.2.3


From c31106b7af32d845e56acb705f07e187f9b519e6 Mon Sep 17 00:00:00 2001
From: Zhouyang Jia <jiazhouyang09@gmail.com>
Date: Fri, 22 Jun 2018 09:52:20 +0800
Subject: mtd: maps: gpio-addr-flash: add error handling for ioremap_nocache

When ioremap_nocache fails, the lack of error-handling code may
cause unexpected results.

This patch adds error-handling code after calling ioremap_nocache.

Signed-off-by: Zhouyang Jia <jiazhouyang09@gmail.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/maps/gpio-addr-flash.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/mtd/maps/gpio-addr-flash.c b/drivers/mtd/maps/gpio-addr-flash.c
index 385305e66fd1..9d9723693217 100644
--- a/drivers/mtd/maps/gpio-addr-flash.c
+++ b/drivers/mtd/maps/gpio-addr-flash.c
@@ -239,6 +239,9 @@ static int gpio_flash_probe(struct platform_device *pdev)
 	state->map.bankwidth  = pdata->width;
 	state->map.size       = state->win_size * (1 << state->gpio_count);
 	state->map.virt       = ioremap_nocache(memory->start, state->map.size);
+	if (!state->map.virt)
+		return -ENOMEM;
+
 	state->map.phys       = NO_XIP;
 	state->map.map_priv_1 = (unsigned long)state;
 
-- 
cgit v1.2.3


From d1001b060621d2119a81ee00b652a84595b03abe Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Tue, 26 Jun 2018 00:05:07 +0200
Subject: dt-bindings: mtd: document Broadcom's TRX firmware format binding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Broadcom based home router devices use TRX firmware format. It's a
container that can hold few partitions. If operating system is expected
to access them it has to understand that format and parse flash data
accordingly.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 .../bindings/mtd/partitions/brcm,trx.txt           | 37 ++++++++++++++++++++++
 1 file changed, 37 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt

diff --git a/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt b/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt
new file mode 100644
index 000000000000..b677147ca4e1
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/partitions/brcm,trx.txt
@@ -0,0 +1,37 @@
+Broadcom TRX Container Partition
+================================
+
+TRX is Broadcom's official firmware format for the BCM947xx boards. It's used by
+most of the vendors building devices based on Broadcom's BCM47xx SoCs and is
+supported by the CFE bootloader.
+
+Design of the TRX format is very minimalistic. Its header contains
+identification fields, CRC32 checksum and the locations of embedded partitions.
+Its purpose is to store a few partitions in a format that can be distributed as
+a standalone file and written in a flash memory.
+
+Container can hold up to 4 partitions. The first partition has to contain a
+device executable binary (e.g. a kernel) as it's what the CFE bootloader starts
+executing. Other partitions can be used for operating system purposes. This is
+useful for systems that keep kernel and rootfs separated.
+
+TRX doesn't enforce any strict partition boundaries or size limits. All
+partitions have to be less than the 4GiB max size limit.
+
+There are two existing/known TRX variants:
+1) v1 which contains 3 partitions
+2) v2 which contains 4 partitions
+
+There aren't separated compatible bindings for them as version can be trivialy
+detected by a software parsing TRX header.
+
+Required properties:
+- compatible : (required) must be "brcm,trx"
+
+Example:
+
+flash@0 {
+	partitions {
+		compatible = "brcm,trx";
+	};
+};
-- 
cgit v1.2.3


From 98534a58c8a40cdc9e3bcb04d74719fbcedfeb52 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Tue, 26 Jun 2018 00:05:08 +0200
Subject: mtd: parsers: trx: add of_match_table with the new DT binding
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows using TRX parser to find TRX partitions on flash device
described in DT using a proper binding. It's useful for devices storing
firmware on a separated flash and having rootfs partition in it.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/parsers/parser_trx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/mtd/parsers/parser_trx.c b/drivers/mtd/parsers/parser_trx.c
index 17ac33599783..4a89a68622fe 100644
--- a/drivers/mtd/parsers/parser_trx.c
+++ b/drivers/mtd/parsers/parser_trx.c
@@ -116,9 +116,16 @@ static int parser_trx_parse(struct mtd_info *mtd,
 	return i;
 };
 
+static const struct of_device_id mtd_parser_trx_of_match_table[] = {
+	{ .compatible = "brcm,trx" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mtd_parser_trx_of_match_table);
+
 static struct mtd_part_parser mtd_parser_trx = {
 	.parse_fn = parser_trx_parse,
 	.name = "trx",
+	.of_match_table = mtd_parser_trx_of_match_table,
 };
 module_mtd_part_parser(mtd_parser_trx);
 
-- 
cgit v1.2.3


From 48360246162b50e84a6e63ed572fdda5e038518b Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 28 Jun 2018 10:20:11 +0200
Subject: mtd: Use kasprintf() instead of fixed buffer formatting

Using "%4.4X" in the calculation of the buffer size is misleading, as
the format string literal has no relation to the actual size needed.
Hence this is fragile w.r.t. future modification.

As this is not a hot path, fix this by replacing the formatting in a
fixed buffer by kasprintf().

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/chips/gen_probe.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/chips/gen_probe.c b/drivers/mtd/chips/gen_probe.c
index 879bebf9d8b1..837b04ab96a9 100644
--- a/drivers/mtd/chips/gen_probe.c
+++ b/drivers/mtd/chips/gen_probe.c
@@ -202,16 +202,19 @@ static inline struct mtd_info *cfi_cmdset_unknown(struct map_info *map,
 	struct cfi_private *cfi = map->fldrv_priv;
 	__u16 type = primary?cfi->cfiq->P_ID:cfi->cfiq->A_ID;
 #ifdef CONFIG_MODULES
-	char probename[sizeof("cfi_cmdset_%4.4X")];
 	cfi_cmdset_fn_t *probe_function;
+	char *probename;
 
-	sprintf(probename, "cfi_cmdset_%4.4X", type);
+	probename = kasprintf(GFP_KERNEL, "cfi_cmdset_%4.4X", type);
+	if (!probename)
+		return NULL;
 
 	probe_function = __symbol_get(probename);
 	if (!probe_function) {
 		request_module("cfi_cmdset_%4.4X", type);
 		probe_function = __symbol_get(probename);
 	}
+	kfree(probename);
 
 	if (probe_function) {
 		struct mtd_info *mtd;
-- 
cgit v1.2.3


From 0219ef1ce577b85a859559c43458c52ca7f29586 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 3 Jul 2018 08:43:39 +0100
Subject: mtd: cfi: cmdset_0002: remove redundant variable timeo

Variable is_local is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'timeo' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/chips/cfi_cmdset_0002.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/mtd/chips/cfi_cmdset_0002.c b/drivers/mtd/chips/cfi_cmdset_0002.c
index a0c655628d6d..cf6cd7623e8f 100644
--- a/drivers/mtd/chips/cfi_cmdset_0002.c
+++ b/drivers/mtd/chips/cfi_cmdset_0002.c
@@ -1216,7 +1216,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 					size_t grouplen)
 {
 	DECLARE_WAITQUEUE(wait, current);
-	unsigned long timeo = jiffies + HZ;
 
  retry:
 	mutex_lock(&chip->mutex);
@@ -1229,7 +1228,6 @@ static inline int do_read_secsi_onechip(struct map_info *map,
 
 		schedule();
 		remove_wait_queue(&chip->wq, &wait);
-		timeo = jiffies + HZ;
 
 		goto retry;
 	}
-- 
cgit v1.2.3


From fb60e87dc4aa415f9d797c5df522eb9578366359 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 4 Jul 2018 07:46:09 +0100
Subject: mtd: nftl: remove redundant variable nb_erases

Variable nb_erases is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'nb_erases' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nftlmount.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/mtd/nftlmount.c b/drivers/mtd/nftlmount.c
index 27184e3874db..91b7fb326f9a 100644
--- a/drivers/mtd/nftlmount.c
+++ b/drivers/mtd/nftlmount.c
@@ -577,7 +577,7 @@ static int get_fold_mark(struct NFTLrecord *nftl, unsigned int block)
 int NFTL_mount(struct NFTLrecord *s)
 {
 	int i;
-	unsigned int first_logical_block, logical_block, rep_block, nb_erases, erase_mark;
+	unsigned int first_logical_block, logical_block, rep_block, erase_mark;
 	unsigned int block, first_block, is_first_block;
 	int chain_length, do_format_chain;
 	struct nftl_uci0 h0;
@@ -621,7 +621,6 @@ int NFTL_mount(struct NFTLrecord *s)
 
 				logical_block = le16_to_cpu ((h0.VirtUnitNum | h0.SpareVirtUnitNum));
 				rep_block = le16_to_cpu ((h0.ReplUnitNum | h0.SpareReplUnitNum));
-				nb_erases = le32_to_cpu (h1.WearInfo);
 				erase_mark = le16_to_cpu ((h1.EraseMark | h1.EraseMark1));
 
 				is_first_block = !(logical_block >> 15);
-- 
cgit v1.2.3


From be9c64b19b8131459dd7107dc0ae209eeeaa9ce8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Jul 2018 14:44:45 +0200
Subject: mlxsw: spectrum_router: avoid uninitialized variable access

When CONFIG_BRIDGE_VLAN_FILTERING is disabled, gcc correctly points out
that the 'vid' variable is uninitialized whenever br_vlan_get_pvid
returns an error:

drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c: In function 'mlxsw_sp_rif_vlan_fid_get':
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c:6881:6: error: 'vid' may be used uninitialized in this function [-Werror=maybe-uninitialized]

This changes the condition check to always return -EINVAL here,
which I guess is what the author intended here.

Fixes: e6f1960ae6c7 ("mlxsw: spectrum_router: Allocate FID according to PVID")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 88bd27ace8d9..79dcadb40857 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6878,11 +6878,9 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 		vid = vlan_dev_vlan_id(rif->dev);
 	} else {
 		err = br_vlan_get_pvid(rif->dev, &vid);
-		if (!vid)
-			err = -EINVAL;
-		if (err) {
+		if (err < 0 || !vid) {
 			NL_SET_ERR_MSG_MOD(extack, "Couldn't determine bridge PVID");
-			return ERR_PTR(err);
+			return ERR_PTR(-EINVAL);
 		}
 	}
 
-- 
cgit v1.2.3


From 22dd149167359981ea6f4afde04026fb78747ddc Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Jul 2018 14:58:51 +0200
Subject: devlink: fix incorrect return statement

A newly added dummy helper function tries to return a failure from a "void"
function:

In file included from include/net/dsa.h:24,
                 from arch/arm/plat-orion/common.c:21:
include/net/devlink.h: In function 'devlink_param_value_changed':
include/net/devlink.h:771:9: error: 'return' with a value, in function returning void [-Werror]
  return -EOPNOTSUPP;

This fixes it by removing the bogus statement.

Fixes: ea601e170988 ("devlink: Add devlink notifications support for params")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 8ed571385626..f67c29cede15 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -768,7 +768,6 @@ devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
 static inline void
 devlink_param_value_changed(struct devlink *devlink, u32 param_id)
 {
-	return -EOPNOTSUPP;
 }
 
 #endif
-- 
cgit v1.2.3


From 8d356b89f36d234a56434a110ae779e8ac389ca2 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 4 Jul 2018 16:46:29 -0700
Subject: rtnetlink: add rtnl_link_state check in rtnl_configure_link

rtnl_configure_link sets dev->rtnl_link_state to
RTNL_LINK_INITIALIZED and unconditionally calls
__dev_notify_flags to notify user-space of dev flags.

current call sequence for rtnl_configure_link
rtnetlink_newlink
    rtnl_link_ops->newlink
    rtnl_configure_link (unconditionally notifies userspace of
                         default and new dev flags)

If a newlink handler wants to call rtnl_configure_link
early, we will end up with duplicate notifications to
user-space.

This patch fixes rtnl_configure_link to check rtnl_link_state
and call __dev_notify_flags with gchanges = 0 if already
RTNL_LINK_INITIALIZED.

Later in the series, this patch will help the following sequence
where a driver implementing newlink can call rtnl_configure_link
to initialize the link early.

makes the following call sequence work:
rtnetlink_newlink
    rtnl_link_ops->newlink (vxlan) -> rtnl_configure_link (initializes
                                                link and notifies
                                                user-space of default
                                                dev flags)
    rtnl_configure_link (updates dev flags if requested by user ifm
                         and notifies user-space of new dev flags)

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ef61222fdef..e3f743c141b3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2759,9 +2759,12 @@ int rtnl_configure_link(struct net_device *dev, const struct ifinfomsg *ifm)
 			return err;
 	}
 
-	dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
-
-	__dev_notify_flags(dev, old_flags, ~0U);
+	if (dev->rtnl_link_state == RTNL_LINK_INITIALIZED) {
+		__dev_notify_flags(dev, old_flags, 0U);
+	} else {
+		dev->rtnl_link_state = RTNL_LINK_INITIALIZED;
+		__dev_notify_flags(dev, old_flags, ~0U);
+	}
 	return 0;
 }
 EXPORT_SYMBOL(rtnl_configure_link);
-- 
cgit v1.2.3


From 25e20e730d56471cffa25419bf2a66078bd55330 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 4 Jul 2018 16:46:30 -0700
Subject: vxlan: add new fdb alloc and create helpers

- Add new vxlan_fdb_alloc helper
- rename existing vxlan_fdb_create into vxlan_fdb_update:
        because it really creates or updates an existing
        fdb entry
- move new fdb creation into a separate vxlan_fdb_create

Main motivation for this change is to introduce the ability
to decouple vxlan fdb creation and notify, used in a later patch.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 91 ++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 62 insertions(+), 29 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 601ae176808d..aa88bebd9d69 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -637,8 +637,61 @@ static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
 	return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
 }
 
-/* Add new entry to forwarding table -- assumes lock held */
+static struct vxlan_fdb *vxlan_fdb_alloc(struct vxlan_dev *vxlan,
+					 const u8 *mac, __u16 state,
+					 __be32 src_vni, __u8 ndm_flags)
+{
+	struct vxlan_fdb *f;
+
+	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	if (!f)
+		return NULL;
+	f->state = state;
+	f->flags = ndm_flags;
+	f->updated = f->used = jiffies;
+	f->vni = src_vni;
+	INIT_LIST_HEAD(&f->remotes);
+	memcpy(f->eth_addr, mac, ETH_ALEN);
+
+	return f;
+}
+
 static int vxlan_fdb_create(struct vxlan_dev *vxlan,
+			    const u8 *mac, union vxlan_addr *ip,
+			    __u16 state, __be16 port, __be32 src_vni,
+			    __be32 vni, __u32 ifindex, __u8 ndm_flags,
+			    struct vxlan_fdb **fdb)
+{
+	struct vxlan_rdst *rd = NULL;
+	struct vxlan_fdb *f;
+	int rc;
+
+	if (vxlan->cfg.addrmax &&
+	    vxlan->addrcnt >= vxlan->cfg.addrmax)
+		return -ENOSPC;
+
+	netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
+	f = vxlan_fdb_alloc(vxlan, mac, state, src_vni, ndm_flags);
+	if (!f)
+		return -ENOMEM;
+
+	rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
+	if (rc < 0) {
+		kfree(f);
+		return rc;
+	}
+
+	++vxlan->addrcnt;
+	hlist_add_head_rcu(&f->hlist,
+			   vxlan_fdb_head(vxlan, mac, src_vni));
+
+	*fdb = f;
+
+	return 0;
+}
+
+/* Add new entry to forwarding table -- assumes lock held */
+static int vxlan_fdb_update(struct vxlan_dev *vxlan,
 			    const u8 *mac, union vxlan_addr *ip,
 			    __u16 state, __u16 flags,
 			    __be16 port, __be32 src_vni, __be32 vni,
@@ -688,37 +741,17 @@ static int vxlan_fdb_create(struct vxlan_dev *vxlan,
 		if (!(flags & NLM_F_CREATE))
 			return -ENOENT;
 
-		if (vxlan->cfg.addrmax &&
-		    vxlan->addrcnt >= vxlan->cfg.addrmax)
-			return -ENOSPC;
-
 		/* Disallow replace to add a multicast entry */
 		if ((flags & NLM_F_REPLACE) &&
 		    (is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
 			return -EOPNOTSUPP;
 
 		netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
-		f = kmalloc(sizeof(*f), GFP_ATOMIC);
-		if (!f)
-			return -ENOMEM;
-
-		notify = 1;
-		f->state = state;
-		f->flags = ndm_flags;
-		f->updated = f->used = jiffies;
-		f->vni = src_vni;
-		INIT_LIST_HEAD(&f->remotes);
-		memcpy(f->eth_addr, mac, ETH_ALEN);
-
-		rc = vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
-		if (rc < 0) {
-			kfree(f);
+		rc = vxlan_fdb_create(vxlan, mac, ip, state, port, src_vni,
+				      vni, ifindex, ndm_flags, &f);
+		if (rc < 0)
 			return rc;
-		}
-
-		++vxlan->addrcnt;
-		hlist_add_head_rcu(&f->hlist,
-				   vxlan_fdb_head(vxlan, mac, src_vni));
+		notify = 1;
 	}
 
 	if (notify) {
@@ -864,7 +897,7 @@ static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
 		return -EAFNOSUPPORT;
 
 	spin_lock_bh(&vxlan->hash_lock);
-	err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
+	err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags,
 			       port, src_vni, vni, ifindex, ndm->ndm_flags);
 	spin_unlock_bh(&vxlan->hash_lock);
 
@@ -1007,7 +1040,7 @@ static bool vxlan_snoop(struct net_device *dev,
 
 		/* close off race between vxlan_flush and incoming packets */
 		if (netif_running(dev))
-			vxlan_fdb_create(vxlan, src_mac, src_ip,
+			vxlan_fdb_update(vxlan, src_mac, src_ip,
 					 NUD_REACHABLE,
 					 NLM_F_EXCL|NLM_F_CREATE,
 					 vxlan->cfg.dst_port,
@@ -3172,7 +3205,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	/* create an fdb entry for a valid default destination */
 	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_create(vxlan, all_zeros_mac,
+		err = vxlan_fdb_update(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
 				       NLM_F_EXCL | NLM_F_CREATE,
@@ -3452,7 +3485,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   old_dst.remote_ifindex, 0);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
-			err = vxlan_fdb_create(vxlan, all_zeros_mac,
+			err = vxlan_fdb_update(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
 					       NLM_F_CREATE | NLM_F_APPEND,
-- 
cgit v1.2.3


From 4c2438ba85cad3be282e19147782ef3a99717a1a Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 4 Jul 2018 16:46:31 -0700
Subject: vxlan: make netlink notify in vxlan_fdb_destroy optional

Add a new option do_notify to vxlan_fdb_destroy to make
sending netlink notify optional. Used by a later patch.

Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index aa88bebd9d69..794a9a7b235f 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -775,13 +775,15 @@ static void vxlan_fdb_free(struct rcu_head *head)
 	kfree(f);
 }
 
-static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
+static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f,
+			      bool do_notify)
 {
 	netdev_dbg(vxlan->dev,
 		    "delete %pM\n", f->eth_addr);
 
 	--vxlan->addrcnt;
-	vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
+	if (do_notify)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
 
 	hlist_del_rcu(&f->hlist);
 	call_rcu(&f->rcu, vxlan_fdb_free);
@@ -931,7 +933,7 @@ static int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 		goto out;
 	}
 
-	vxlan_fdb_destroy(vxlan, f);
+	vxlan_fdb_destroy(vxlan, f, true);
 
 out:
 	return 0;
@@ -2399,7 +2401,7 @@ static void vxlan_cleanup(struct timer_list *t)
 					   "garbage collect %pM\n",
 					   f->eth_addr);
 				f->state = NUD_STALE;
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 			} else if (time_before(timeout, next_timer))
 				next_timer = timeout;
 		}
@@ -2450,7 +2452,7 @@ static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni)
 	spin_lock_bh(&vxlan->hash_lock);
 	f = __vxlan_find_mac(vxlan, all_zeros_mac, vni);
 	if (f)
-		vxlan_fdb_destroy(vxlan, f);
+		vxlan_fdb_destroy(vxlan, f, true);
 	spin_unlock_bh(&vxlan->hash_lock);
 }
 
@@ -2504,7 +2506,7 @@ static void vxlan_flush(struct vxlan_dev *vxlan, bool do_all)
 				continue;
 			/* the all_zeros_mac entry is deleted at vxlan_uninit */
 			if (!is_zero_ether_addr(f->eth_addr))
-				vxlan_fdb_destroy(vxlan, f);
+				vxlan_fdb_destroy(vxlan, f, true);
 		}
 	}
 	spin_unlock_bh(&vxlan->hash_lock);
-- 
cgit v1.2.3


From 0241b836732f5f43c3f0fd9e9073c1fb24ea6757 Mon Sep 17 00:00:00 2001
From: Roopa Prabhu <roopa@cumulusnetworks.com>
Date: Wed, 4 Jul 2018 16:46:32 -0700
Subject: vxlan: fix default fdb entry netlink notify ordering during netdev
 create

Problem:
In vxlan_newlink, a default fdb entry is added before register_netdev.
The default fdb creation function also notifies user-space of the
fdb entry on the vxlan device which user-space does not know about yet.
(RTM_NEWNEIGH goes before RTM_NEWLINK for the same ifindex).

This patch fixes the user-space netlink notification ordering issue
with the following changes:
- decouple fdb notify from fdb create.
- Move fdb notify after register_netdev.
- Call rtnl_configure_link in vxlan newlink handler to notify
userspace about the newlink before fdb notify and
hence avoiding the user-space race.

Fixes: afbd8bae9c79 ("vxlan: add implicit fdb entry for default destination")
Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/vxlan.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 794a9a7b235f..ababba37d735 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -3197,6 +3197,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 {
 	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_dev_configure(net, dev, conf, false, extack);
@@ -3207,27 +3208,38 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 
 	/* create an fdb entry for a valid default destination */
 	if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) {
-		err = vxlan_fdb_update(vxlan, all_zeros_mac,
+		err = vxlan_fdb_create(vxlan, all_zeros_mac,
 				       &vxlan->default_dst.remote_ip,
 				       NUD_REACHABLE | NUD_PERMANENT,
-				       NLM_F_EXCL | NLM_F_CREATE,
 				       vxlan->cfg.dst_port,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_vni,
 				       vxlan->default_dst.remote_ifindex,
-				       NTF_SELF);
+				       NTF_SELF, &f);
 		if (err)
 			return err;
 	}
 
 	err = register_netdevice(dev);
+	if (err)
+		goto errout;
+
+	err = rtnl_configure_link(dev, NULL);
 	if (err) {
-		vxlan_fdb_delete_default(vxlan, vxlan->default_dst.remote_vni);
-		return err;
+		unregister_netdevice(dev);
+		goto errout;
 	}
 
+	/* notify default fdb entry */
+	if (f)
+		vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
+
 	list_add(&vxlan->next, &vn->vxlan_list);
 	return 0;
+errout:
+	if (f)
+		vxlan_fdb_destroy(vxlan, f, false);
+	return err;
 }
 
 static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
@@ -3462,6 +3474,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	struct vxlan_rdst old_dst;
 	struct vxlan_config conf;
+	struct vxlan_fdb *f = NULL;
 	int err;
 
 	err = vxlan_nl2conf(tb, data,
@@ -3487,19 +3500,19 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 					   old_dst.remote_ifindex, 0);
 
 		if (!vxlan_addr_any(&dst->remote_ip)) {
-			err = vxlan_fdb_update(vxlan, all_zeros_mac,
+			err = vxlan_fdb_create(vxlan, all_zeros_mac,
 					       &dst->remote_ip,
 					       NUD_REACHABLE | NUD_PERMANENT,
-					       NLM_F_CREATE | NLM_F_APPEND,
 					       vxlan->cfg.dst_port,
 					       dst->remote_vni,
 					       dst->remote_vni,
 					       dst->remote_ifindex,
-					       NTF_SELF);
+					       NTF_SELF, &f);
 			if (err) {
 				spin_unlock_bh(&vxlan->hash_lock);
 				return err;
 			}
+			vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH);
 		}
 		spin_unlock_bh(&vxlan->hash_lock);
 	}
-- 
cgit v1.2.3


From e88bc0f25b99294b039b965e92a68213d594ba5b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 5 Jul 2018 21:10:59 +0200
Subject: selftests: forwarding: Allow importing dependent libraries

The next patch introduces a new mlxsw-specific test that uses
mirror_gre_lib.sh and mirror_gre_topo_lib.sh.

However when sourcing their own deps, these libraries assume that the
test that's running is in the same directory. That's not the case for
driver-specific tests.

So change the libraries to source their deps through $relative_path.
That variable is set up by lib.sh, which should be imported by the test
in question in any case.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/mirror_gre_lib.sh      | 2 +-
 tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
index 1c18e332cd4f..fac486178ef7 100644
--- a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
-source mirror_lib.sh
+source "$relative_path/mirror_lib.sh"
 
 quick_test_span_gre_dir_ips()
 {
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
index 253419564708..39c03e2867f4 100644
--- a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh
@@ -33,7 +33,7 @@
 #   |                                                                         |
 #   +-------------------------------------------------------------------------+
 
-source mirror_topo_lib.sh
+source "$relative_path/mirror_topo_lib.sh"
 
 mirror_gre_topo_h3_create()
 {
-- 
cgit v1.2.3


From 1ba97e6725a91f2f005699565a12267445a74f1f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 5 Jul 2018 21:09:04 +0200
Subject: selftests: mlxsw: Add mlxsw-specific test for mirror to gretap

Test several aspects of offloading mirror to gretap and ip6gretap
netdevices that are specific to mlxsw, such as requirements for TTL and
TOS values.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/mirror_gre.sh      | 217 +++++++++++++++++++++
 1 file changed, 217 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
new file mode 100755
index 000000000000..76f1ab4898d9
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/mirror_gre.sh
@@ -0,0 +1,217 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test uses standard topology for testing gretap. See
+# ../../../net/forwarding/mirror_gre_topo_lib.sh for more details.
+#
+# Test offloading various features of offloading gretap mirrors specific to
+# mlxsw.
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=6
+source $lib_dir/lib.sh
+source $lib_dir/mirror_lib.sh
+source $lib_dir/mirror_gre_lib.sh
+source $lib_dir/mirror_gre_topo_lib.sh
+
+setup_keyful()
+{
+	tunnel_create gt6-key ip6gretap 2001:db8:3::1 2001:db8:3::2 \
+		      ttl 100 tos inherit allow-localremote \
+		      key 1234
+
+	tunnel_create h3-gt6-key ip6gretap 2001:db8:3::2 2001:db8:3::1 \
+		      key 1234
+	ip link set h3-gt6-key vrf v$h3
+	matchall_sink_create h3-gt6-key
+
+	ip address add dev $swp3 2001:db8:3::1/64
+	ip address add dev $h3 2001:db8:3::2/64
+}
+
+cleanup_keyful()
+{
+	ip address del dev $h3 2001:db8:3::2/64
+	ip address del dev $swp3 2001:db8:3::1/64
+
+	tunnel_destroy h3-gt6-key
+	tunnel_destroy gt6-key
+}
+
+setup_soft()
+{
+	# Set up a topology for testing underlay routes that point at an
+	# unsupported soft device.
+
+	tunnel_create gt6-soft ip6gretap 2001:db8:4::1 2001:db8:4::2 \
+		      ttl 100 tos inherit allow-localremote
+
+	tunnel_create h3-gt6-soft ip6gretap 2001:db8:4::2 2001:db8:4::1
+	ip link set h3-gt6-soft vrf v$h3
+	matchall_sink_create h3-gt6-soft
+
+	ip link add name v1 type veth peer name v2
+	ip link set dev v1 up
+	ip address add dev v1 2001:db8:4::1/64
+
+	ip link set dev v2 vrf v$h3
+	ip link set dev v2 up
+	ip address add dev v2 2001:db8:4::2/64
+}
+
+cleanup_soft()
+{
+	ip link del dev v1
+
+	tunnel_destroy h3-gt6-soft
+	tunnel_destroy gt6-soft
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	swp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+	mirror_gre_topo_create
+
+	ip address add dev $swp3 2001:db8:2::1/64
+	ip address add dev $h3 2001:db8:2::2/64
+
+	ip address add dev $swp3 192.0.2.129/28
+	ip address add dev $h3 192.0.2.130/28
+
+	setup_keyful
+	setup_soft
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	cleanup_soft
+	cleanup_keyful
+
+	ip address del dev $h3 2001:db8:2::2/64
+	ip address del dev $swp3 2001:db8:2::1/64
+
+	ip address del dev $h3 192.0.2.130/28
+	ip address del dev $swp3 192.0.2.129/28
+
+	mirror_gre_topo_destroy
+	vrf_cleanup
+}
+
+test_span_gre_ttl_inherit()
+{
+	local tundev=$1; shift
+	local type=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	ip link set dev $tundev type $type ttl inherit
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	fail_test_span_gre_dir $tundev ingress
+
+	ip link set dev $tundev type $type ttl 100
+
+	quick_test_span_gre_dir $tundev ingress
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: no offload on TTL of inherit ($tcflags)"
+}
+
+test_span_gre_tos_fixed()
+{
+	local tundev=$1; shift
+	local type=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	ip link set dev $tundev type $type tos 0x10
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	fail_test_span_gre_dir $tundev ingress
+
+	ip link set dev $tundev type $type tos inherit
+	quick_test_span_gre_dir $tundev ingress
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: no offload on a fixed TOS ($tcflags)"
+}
+
+test_span_failable()
+{
+	local should_fail=$1; shift
+	local tundev=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress $tundev "matchall $tcflags"
+	if ((should_fail)); then
+	    fail_test_span_gre_dir  $tundev ingress
+	else
+	    quick_test_span_gre_dir $tundev ingress
+	fi
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what: should_fail=$should_fail ($tcflags)"
+}
+
+test_failable()
+{
+	local should_fail=$1; shift
+
+	test_span_failable $should_fail gt6-key "mirror to keyful gretap"
+	test_span_failable $should_fail gt6-soft "mirror to gretap w/ soft underlay"
+}
+
+test_sw()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	test_failable 0
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+test_hw()
+{
+	test_failable 1
+
+	test_span_gre_tos_fixed gt4 gretap "mirror to gretap"
+	test_span_gre_tos_fixed gt6 ip6gretap "mirror to ip6gretap"
+
+	test_span_gre_ttl_inherit gt4 gretap "mirror to gretap"
+	test_span_gre_ttl_inherit gt6 ip6gretap "mirror to ip6gretap"
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+if ! tc_offload_check; then
+    check_err 1 "Could not test offloaded functionality"
+    log_test "mlxsw-specific tests for mirror to gretap"
+    exit
+fi
+
+tcflags="skip_hw"
+test_sw
+
+tcflags="skip_sw"
+test_hw
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 94c763513452b466d1e5c86b9d883ba13c9a031a Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 7 Jul 2018 12:27:30 +0100
Subject: farsync: remove redundant variable txq_length

Variable txq_length is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'txq_length' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/farsync.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index bd46b2552980..2a3f0f1a2b0a 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -2134,7 +2134,6 @@ static void
 fst_openport(struct fst_port_info *port)
 {
 	int signals;
-	int txq_length;
 
 	/* Only init things if card is actually running. This allows open to
 	 * succeed for downloads etc.
@@ -2161,7 +2160,6 @@ fst_openport(struct fst_port_info *port)
 		else
 			netif_carrier_off(port_to_dev(port));
 
-		txq_length = port->txqe - port->txqs;
 		port->txqe = 0;
 		port->txqs = 0;
 	}
-- 
cgit v1.2.3


From 2064c3d4c02026572d4975177f28a58052f0a8b7 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Fri, 6 Jul 2018 05:38:12 +0000
Subject: net/flow_dissector: Save vlan ethertype from headers

Change vlan dissector key to save vlan tpid to support both 802.1Q
and 802.1AD ethertype.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h | 2 +-
 net/core/flow_dissector.c    | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index adc24df56b90..8f899688a965 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -47,7 +47,7 @@ struct flow_dissector_key_tags {
 struct flow_dissector_key_vlan {
 	u16	vlan_id:12,
 		vlan_priority:3;
-	u16	padding;
+	__be16	vlan_tpid;
 };
 
 struct flow_dissector_key_mpls {
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 53f96e4f7bf5..18cb99b50cba 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -751,6 +751,7 @@ proto_again:
 		const struct vlan_hdr *vlan;
 		struct vlan_hdr _vlan;
 		bool vlan_tag_present = skb && skb_vlan_tag_present(skb);
+		__be16 saved_vlan_tpid = proto;
 
 		if (vlan_tag_present)
 			proto = skb->protocol;
@@ -789,6 +790,7 @@ proto_again:
 					(ntohs(vlan->h_vlan_TCI) &
 					 VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 			}
+			key_vlan->vlan_tpid = saved_vlan_tpid;
 		}
 
 		fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
-- 
cgit v1.2.3


From aaab08344d2670e5c119b7b497d5063d7ddb8364 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Fri, 6 Jul 2018 05:38:13 +0000
Subject: net/sched: flower: Add support for matching on vlan ethertype

As flow dissector stores vlan ethertype, tc flower now can match on that.
It is to make preparation for supporting QinQ.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 352876bb901b..da9ec30763fe 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -500,6 +500,7 @@ static int fl_set_key_mpls(struct nlattr **tb,
 }
 
 static void fl_set_key_vlan(struct nlattr **tb,
+			    __be16 ethertype,
 			    struct flow_dissector_key_vlan *key_val,
 			    struct flow_dissector_key_vlan *key_mask)
 {
@@ -516,6 +517,8 @@ static void fl_set_key_vlan(struct nlattr **tb,
 			VLAN_PRIORITY_MASK;
 		key_mask->vlan_priority = VLAN_PRIORITY_MASK;
 	}
+	key_val->vlan_tpid = ethertype;
+	key_mask->vlan_tpid = cpu_to_be16(~0);
 }
 
 static void fl_set_key_flag(u32 flower_key, u32 flower_mask,
@@ -592,8 +595,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 	if (tb[TCA_FLOWER_KEY_ETH_TYPE]) {
 		ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]);
 
-		if (ethertype == htons(ETH_P_8021Q)) {
-			fl_set_key_vlan(tb, &key->vlan, &mask->vlan);
+		if (eth_type_vlan(ethertype)) {
+			fl_set_key_vlan(tb, ethertype, &key->vlan, &mask->vlan);
 			fl_set_key_val(tb, &key->basic.n_proto,
 				       TCA_FLOWER_KEY_VLAN_ETH_TYPE,
 				       &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
-- 
cgit v1.2.3


From 24c590e3b0f9eebe603ebe3d516990306d385f46 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Fri, 6 Jul 2018 05:38:14 +0000
Subject: net/flow_dissector: Add support for QinQ dissection

Dissect the QinQ packets to get both outer and inner vlan information,
then store to the extended flow keys.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h |  2 ++
 net/core/flow_dissector.c    | 32 +++++++++++++++++---------------
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 8f899688a965..c64406717eee 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -206,6 +206,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_MPLS, /* struct flow_dissector_key_mpls */
 	FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */
 	FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */
+	FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */
 
 	FLOW_DISSECTOR_KEY_MAX,
 };
@@ -237,6 +238,7 @@ struct flow_keys {
 	struct flow_dissector_key_basic basic;
 	struct flow_dissector_key_tags tags;
 	struct flow_dissector_key_vlan vlan;
+	struct flow_dissector_key_vlan cvlan;
 	struct flow_dissector_key_keyid keyid;
 	struct flow_dissector_key_ports ports;
 	struct flow_dissector_key_addrs addrs;
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 18cb99b50cba..b555fc229e96 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -589,7 +589,7 @@ bool __skb_flow_dissect(const struct sk_buff *skb,
 	struct flow_dissector_key_tags *key_tags;
 	struct flow_dissector_key_vlan *key_vlan;
 	enum flow_dissect_ret fdret;
-	bool skip_vlan = false;
+	enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX;
 	int num_hdrs = 0;
 	u8 ip_proto = 0;
 	bool ret;
@@ -748,15 +748,14 @@ proto_again:
 	}
 	case htons(ETH_P_8021AD):
 	case htons(ETH_P_8021Q): {
-		const struct vlan_hdr *vlan;
+		const struct vlan_hdr *vlan = NULL;
 		struct vlan_hdr _vlan;
-		bool vlan_tag_present = skb && skb_vlan_tag_present(skb);
 		__be16 saved_vlan_tpid = proto;
 
-		if (vlan_tag_present)
+		if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX &&
+		    skb && skb_vlan_tag_present(skb)) {
 			proto = skb->protocol;
-
-		if (!vlan_tag_present || eth_type_vlan(skb->protocol)) {
+		} else {
 			vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan),
 						    data, hlen, &_vlan);
 			if (!vlan) {
@@ -766,20 +765,23 @@ proto_again:
 
 			proto = vlan->h_vlan_encapsulated_proto;
 			nhoff += sizeof(*vlan);
-			if (skip_vlan) {
-				fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
-				break;
-			}
 		}
 
-		skip_vlan = true;
-		if (dissector_uses_key(flow_dissector,
-				       FLOW_DISSECTOR_KEY_VLAN)) {
+		if (dissector_vlan == FLOW_DISSECTOR_KEY_MAX) {
+			dissector_vlan = FLOW_DISSECTOR_KEY_VLAN;
+		} else if (dissector_vlan == FLOW_DISSECTOR_KEY_VLAN) {
+			dissector_vlan = FLOW_DISSECTOR_KEY_CVLAN;
+		} else {
+			fdret = FLOW_DISSECT_RET_PROTO_AGAIN;
+			break;
+		}
+
+		if (dissector_uses_key(flow_dissector, dissector_vlan)) {
 			key_vlan = skb_flow_dissector_target(flow_dissector,
-							     FLOW_DISSECTOR_KEY_VLAN,
+							     dissector_vlan,
 							     target_container);
 
-			if (vlan_tag_present) {
+			if (!vlan) {
 				key_vlan->vlan_id = skb_vlan_tag_get_id(skb);
 				key_vlan->vlan_priority =
 					(skb_vlan_tag_get_prio(skb) >> VLAN_PRIO_SHIFT);
-- 
cgit v1.2.3


From d30695126f0ac5bca85d09c7946ad9a1deab5d25 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Fri, 6 Jul 2018 05:38:15 +0000
Subject: net/sched: flower: Dump the ethertype encapsulated in vlan

Currently the encapsulated ethertype is not dumped as it's the same as
TCA_FLOWER_KEY_ETH_TYPE keyvalue. But the dumping result is inconsistent
with input, we add dumping it with TCA_FLOWER_KEY_VLAN_ETH_TYPE.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index da9ec30763fe..e93b13d2cb81 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1313,6 +1313,10 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan))
 		goto nla_put_failure;
 
+	if (mask->vlan.vlan_tpid &&
+	    nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, key->basic.n_proto))
+		goto nla_put_failure;
+
 	if ((key->basic.n_proto == htons(ETH_P_IP) ||
 	     key->basic.n_proto == htons(ETH_P_IPV6)) &&
 	    (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
-- 
cgit v1.2.3


From d64efd0926ba4f32e657e615a4f4a6170d5cc0fa Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Fri, 6 Jul 2018 05:38:16 +0000
Subject: net/sched: flower: Add supprt for matching on QinQ vlan headers

As support dissecting of QinQ inner and outer vlan headers, user can
add rules to match on QinQ vlan headers.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h |  4 +++
 net/sched/cls_flower.c       | 65 ++++++++++++++++++++++++++++++++++----------
 2 files changed, 55 insertions(+), 14 deletions(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 84e4c1d0f874..c4262d911596 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -469,6 +469,10 @@ enum {
 	TCA_FLOWER_KEY_IP_TTL,		/* u8 */
 	TCA_FLOWER_KEY_IP_TTL_MASK,	/* u8 */
 
+	TCA_FLOWER_KEY_CVLAN_ID,	/* be16 */
+	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
+
 	__TCA_FLOWER_MAX,
 };
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index e93b13d2cb81..487a152a852c 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -35,6 +35,7 @@ struct fl_flow_key {
 	struct flow_dissector_key_basic basic;
 	struct flow_dissector_key_eth_addrs eth;
 	struct flow_dissector_key_vlan vlan;
+	struct flow_dissector_key_vlan cvlan;
 	union {
 		struct flow_dissector_key_ipv4_addrs ipv4;
 		struct flow_dissector_key_ipv6_addrs ipv6;
@@ -449,6 +450,9 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_IP_TOS_MASK]	= { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_IP_TTL]		= { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_IP_TTL_MASK]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_CVLAN_ID]	= { .type = NLA_U16 },
+	[TCA_FLOWER_KEY_CVLAN_PRIO]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_CVLAN_ETH_TYPE]	= { .type = NLA_U16 },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
@@ -501,19 +505,20 @@ static int fl_set_key_mpls(struct nlattr **tb,
 
 static void fl_set_key_vlan(struct nlattr **tb,
 			    __be16 ethertype,
+			    int vlan_id_key, int vlan_prio_key,
 			    struct flow_dissector_key_vlan *key_val,
 			    struct flow_dissector_key_vlan *key_mask)
 {
 #define VLAN_PRIORITY_MASK	0x7
 
-	if (tb[TCA_FLOWER_KEY_VLAN_ID]) {
+	if (tb[vlan_id_key]) {
 		key_val->vlan_id =
-			nla_get_u16(tb[TCA_FLOWER_KEY_VLAN_ID]) & VLAN_VID_MASK;
+			nla_get_u16(tb[vlan_id_key]) & VLAN_VID_MASK;
 		key_mask->vlan_id = VLAN_VID_MASK;
 	}
-	if (tb[TCA_FLOWER_KEY_VLAN_PRIO]) {
+	if (tb[vlan_prio_key]) {
 		key_val->vlan_priority =
-			nla_get_u8(tb[TCA_FLOWER_KEY_VLAN_PRIO]) &
+			nla_get_u8(tb[vlan_prio_key]) &
 			VLAN_PRIORITY_MASK;
 		key_mask->vlan_priority = VLAN_PRIORITY_MASK;
 	}
@@ -596,11 +601,25 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 		ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_ETH_TYPE]);
 
 		if (eth_type_vlan(ethertype)) {
-			fl_set_key_vlan(tb, ethertype, &key->vlan, &mask->vlan);
-			fl_set_key_val(tb, &key->basic.n_proto,
-				       TCA_FLOWER_KEY_VLAN_ETH_TYPE,
-				       &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
-				       sizeof(key->basic.n_proto));
+			fl_set_key_vlan(tb, ethertype, TCA_FLOWER_KEY_VLAN_ID,
+					TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan,
+					&mask->vlan);
+
+			ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
+			if (eth_type_vlan(ethertype)) {
+				fl_set_key_vlan(tb, ethertype,
+						TCA_FLOWER_KEY_CVLAN_ID,
+						TCA_FLOWER_KEY_CVLAN_PRIO,
+						&key->cvlan, &mask->cvlan);
+				fl_set_key_val(tb, &key->basic.n_proto,
+					       TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
+					       &mask->basic.n_proto,
+					       TCA_FLOWER_UNSPEC,
+					       sizeof(key->basic.n_proto));
+			} else {
+				key->basic.n_proto = ethertype;
+				mask->basic.n_proto = cpu_to_be16(~0);
+			}
 		} else {
 			key->basic.n_proto = ethertype;
 			mask->basic.n_proto = cpu_to_be16(~0);
@@ -825,6 +844,8 @@ static void fl_init_dissector(struct fl_flow_mask *mask)
 			     FLOW_DISSECTOR_KEY_MPLS, mpls);
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_VLAN, vlan);
+	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+			     FLOW_DISSECTOR_KEY_CVLAN, cvlan);
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
@@ -1201,6 +1222,7 @@ static int fl_dump_key_ip(struct sk_buff *skb,
 }
 
 static int fl_dump_key_vlan(struct sk_buff *skb,
+			    int vlan_id_key, int vlan_prio_key,
 			    struct flow_dissector_key_vlan *vlan_key,
 			    struct flow_dissector_key_vlan *vlan_mask)
 {
@@ -1209,13 +1231,13 @@ static int fl_dump_key_vlan(struct sk_buff *skb,
 	if (!memchr_inv(vlan_mask, 0, sizeof(*vlan_mask)))
 		return 0;
 	if (vlan_mask->vlan_id) {
-		err = nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ID,
+		err = nla_put_u16(skb, vlan_id_key,
 				  vlan_key->vlan_id);
 		if (err)
 			return err;
 	}
 	if (vlan_mask->vlan_priority) {
-		err = nla_put_u8(skb, TCA_FLOWER_KEY_VLAN_PRIO,
+		err = nla_put_u8(skb, vlan_prio_key,
 				 vlan_key->vlan_priority);
 		if (err)
 			return err;
@@ -1310,13 +1332,28 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	if (fl_dump_key_mpls(skb, &key->mpls, &mask->mpls))
 		goto nla_put_failure;
 
-	if (fl_dump_key_vlan(skb, &key->vlan, &mask->vlan))
+	if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_VLAN_ID,
+			     TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan, &mask->vlan))
 		goto nla_put_failure;
 
-	if (mask->vlan.vlan_tpid &&
-	    nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE, key->basic.n_proto))
+	if (fl_dump_key_vlan(skb, TCA_FLOWER_KEY_CVLAN_ID,
+			     TCA_FLOWER_KEY_CVLAN_PRIO,
+			     &key->cvlan, &mask->cvlan) ||
+	    (mask->cvlan.vlan_tpid &&
+	     nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+			 key->cvlan.vlan_tpid)))
 		goto nla_put_failure;
 
+	if (mask->cvlan.vlan_tpid) {
+		if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
+				 key->basic.n_proto))
+			goto nla_put_failure;
+	} else if (mask->vlan.vlan_tpid) {
+		if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+				 key->basic.n_proto))
+			goto nla_put_failure;
+	}
+
 	if ((key->basic.n_proto == htons(ETH_P_IP) ||
 	     key->basic.n_proto == htons(ETH_P_IPV6)) &&
 	    (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
-- 
cgit v1.2.3


From a4dc70d46cf1a05b244a06d3d8c0c09908ea13b9 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Fri, 6 Jul 2018 15:22:36 +0200
Subject: tipc: extend link reset criteria for stale packet retransmission

Currently a link is declared stale and reset if there has been 100
repeated attempts to retransmit the same packet. However, in certain
infrastructures we see that packet (NACK) duplicates and delays may
cause such retransmit attempts to occur at a high rate, so that the
peer doesn't have a reasonable chance to acknowledge the reception
before the 100-limit is hit. This may take much less than the
stipulated link tolerance time, and despite that probe/probe replies
otherwise go through as normal.

We now extend the criteria for link reset to also being time based.
I.e., we don't reset the link until the link tolerance time is passed
AND we have made 100 retransmissions attempts.

Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 43 ++++++++++++++++++++++++-------------------
 1 file changed, 24 insertions(+), 19 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 63860329dbaa..ec4d28328652 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -106,7 +106,8 @@ struct tipc_stats {
  * @backlogq: queue for messages waiting to be sent
  * @snt_nxt: next sequence number to use for outbound messages
  * @last_retransmitted: sequence number of most recently retransmitted message
- * @stale_count: # of identical retransmit requests made by peer
+ * @stale_cnt: counter for number of identical retransmit attempts
+ * @stale_limit: time when repeated identical retransmits must force link reset
  * @ackers: # of peers that needs to ack each packet before it can be released
  * @acked: # last packet acked by a certain peer. Used for broadcast.
  * @rcv_nxt: next sequence number to expect for inbound messages
@@ -161,7 +162,8 @@ struct tipc_link {
 	u16 snd_nxt;
 	u16 last_retransm;
 	u16 window;
-	u32 stale_count;
+	u16 stale_cnt;
+	unsigned long stale_limit;
 
 	/* Reception */
 	u16 rcv_nxt;
@@ -860,7 +862,7 @@ void tipc_link_reset(struct tipc_link *l)
 	l->acked = 0;
 	l->silent_intv_cnt = 0;
 	l->rst_cnt = 0;
-	l->stale_count = 0;
+	l->stale_cnt = 0;
 	l->bc_peer_is_up = false;
 	memset(&l->mon_state, 0, sizeof(l->mon_state));
 	tipc_link_reset_stats(l);
@@ -997,39 +999,41 @@ static void link_retransmit_failure(struct tipc_link *l, struct sk_buff *skb)
 		msg_seqno(hdr), msg_prevnode(hdr), msg_orignode(hdr));
 }
 
-int tipc_link_retrans(struct tipc_link *l, struct tipc_link *nacker,
+/* tipc_link_retrans() - retransmit one or more packets
+ * @l: the link to transmit on
+ * @r: the receiving link ordering the retransmit. Same as l if unicast
+ * @from: retransmit from (inclusive) this sequence number
+ * @to: retransmit to (inclusive) this sequence number
+ * xmitq: queue for accumulating the retransmitted packets
+ */
+int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
 		      u16 from, u16 to, struct sk_buff_head *xmitq)
 {
 	struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
-	struct tipc_msg *hdr;
-	u16 ack = l->rcv_nxt - 1;
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
+	u16 ack = l->rcv_nxt - 1;
+	struct tipc_msg *hdr;
 
 	if (!skb)
 		return 0;
 
 	/* Detect repeated retransmit failures on same packet */
-	if (nacker->last_retransm != buf_seqno(skb)) {
-		nacker->last_retransm = buf_seqno(skb);
-		nacker->stale_count = 1;
-	} else if (++nacker->stale_count > 100) {
+	if (r->last_retransm != buf_seqno(skb)) {
+		r->last_retransm = buf_seqno(skb);
+		r->stale_limit = jiffies + msecs_to_jiffies(l->tolerance);
+	} else if (++r->stale_cnt > 99 && time_after(jiffies, r->stale_limit)) {
 		link_retransmit_failure(l, skb);
-		nacker->stale_count = 0;
 		if (link_is_bc_sndlink(l))
 			return TIPC_LINK_DOWN_EVT;
 		return tipc_link_fsm_evt(l, LINK_FAILURE_EVT);
 	}
 
-	/* Move forward to where retransmission should start */
 	skb_queue_walk(&l->transmq, skb) {
-		if (!less(buf_seqno(skb), from))
-			break;
-	}
-
-	skb_queue_walk_from(&l->transmq, skb) {
-		if (more(buf_seqno(skb), to))
-			break;
 		hdr = buf_msg(skb);
+		if (less(msg_seqno(hdr), from))
+			continue;
+		if (more(msg_seqno(hdr), to))
+			break;
 		_skb = __pskb_copy(skb, MIN_H_SIZE, GFP_ATOMIC);
 		if (!_skb)
 			return 0;
@@ -1272,6 +1276,7 @@ int tipc_link_rcv(struct tipc_link *l, struct sk_buff *skb,
 
 		/* Forward queues and wake up waiting users */
 		if (likely(tipc_link_release_pkts(l, msg_ack(hdr)))) {
+			l->stale_cnt = 0;
 			tipc_link_advance_backlog(l, xmitq);
 			if (unlikely(!skb_queue_empty(&l->wakeupq)))
 				link_prepare_wakeup(l);
-- 
cgit v1.2.3


From 8f704ef666406fc5e42032308a2b366ea7bca846 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Jul 2018 15:36:07 +0200
Subject: stmmac: fix signed 64-bit division

I link error on 32-bit ARM points to yet another arithmetic bug:

drivers/net/ethernet/stmicro/stmmac/stmmac_tc.o: In function `tc_setup_cbs':
stmmac_tc.c:(.text+0x148): undefined reference to `__aeabi_uldivmod'
stmmac_tc.c:(.text+0x1fc): undefined reference to `__aeabi_uldivmod'
stmmac_tc.c:(.text+0x308): undefined reference to `__aeabi_uldivmod'
stmmac_tc.c:(.text+0x320): undefined reference to `__aeabi_uldivmod'
stmmac_tc.c:(.text+0x33c): undefined reference to `__aeabi_uldivmod'
drivers/net/ethernet/stmicro/stmmac/stmmac_tc.o:stmmac_tc.c:(.text+0x3a4): more undefined references to `__aeabi_uldivmod' follow

I observe that the last change to add the 'ul' prefix was incorrect,
as it did not turn the result of the multiplication into a 64-bit
expression on 32-bit architectures. Further, it seems that the
do_div() macro gets confused by the fact that we pass a signed
variable rather than unsigned into it.

This changes the code to instead use the div_s64() helper that is
meant for signed division, along with changing the constant suffix
to 'll' to actually make it a 64-bit argument everywhere, fixing
both of the issues I pointed out.

I'm not completely convinced that this makes the code correct, but
I'm fairly sure that we have two problems less than before.

Fixes: 1f705bc61aee ("net: stmmac: Add support for CBS QDISC")
Fixes: c18a9c096683 ("net: stmmac_tc: use 64-bit arithmetic instead of 32-bit")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
index 8fedc288d138..1a96dd9c1091 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c
@@ -321,18 +321,16 @@ static int tc_setup_cbs(struct stmmac_priv *priv,
 	speed_div = (priv->speed == SPEED_100) ? 100000 : 1000000;
 
 	/* Final adjustments for HW */
-	value = qopt->idleslope * 1024UL * ptr;
-	do_div(value, speed_div);
+	value = div_s64(qopt->idleslope * 1024ll * ptr, speed_div);
 	priv->plat->tx_queues_cfg[queue].idle_slope = value & GENMASK(31, 0);
 
-	value = -qopt->sendslope * 1024UL * ptr;
-	do_div(value, speed_div);
+	value = div_s64(-qopt->sendslope * 1024ll * ptr, speed_div);
 	priv->plat->tx_queues_cfg[queue].send_slope = value & GENMASK(31, 0);
 
-	value = qopt->hicredit * 1024UL * 8;
+	value = qopt->hicredit * 1024ll * 8;
 	priv->plat->tx_queues_cfg[queue].high_credit = value & GENMASK(31, 0);
 
-	value = qopt->locredit * 1024UL * 8;
+	value = qopt->locredit * 1024ll * 8;
 	priv->plat->tx_queues_cfg[queue].low_credit = value & GENMASK(31, 0);
 
 	ret = stmmac_config_cbs(priv, priv->hw,
-- 
cgit v1.2.3


From 1239a96a8fcbdaa5e4171db12ccc694027a20ee7 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Fri, 6 Jul 2018 21:44:44 +0300
Subject: net: ethernet: ti: cpsw: use BIT macro

It's needed to avoid checkpatch warnings for farther changes.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 093998124149..f355e65323f3 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -253,23 +253,23 @@ struct cpsw_ss_regs {
 #define RX_DSCP_PRI_MAP7    0x4c /* Rx DSCP Priority to Rx Packet Mapping */
 
 /* Bit definitions for the CPSW2_CONTROL register */
-#define PASS_PRI_TAGGED     (1<<24) /* Pass Priority Tagged */
-#define VLAN_LTYPE2_EN      (1<<21) /* VLAN LTYPE 2 enable */
-#define VLAN_LTYPE1_EN      (1<<20) /* VLAN LTYPE 1 enable */
-#define DSCP_PRI_EN         (1<<16) /* DSCP Priority Enable */
-#define TS_320              (1<<14) /* Time Sync Dest Port 320 enable */
-#define TS_319              (1<<13) /* Time Sync Dest Port 319 enable */
-#define TS_132              (1<<12) /* Time Sync Dest IP Addr 132 enable */
-#define TS_131              (1<<11) /* Time Sync Dest IP Addr 131 enable */
-#define TS_130              (1<<10) /* Time Sync Dest IP Addr 130 enable */
-#define TS_129              (1<<9)  /* Time Sync Dest IP Addr 129 enable */
-#define TS_TTL_NONZERO      (1<<8)  /* Time Sync Time To Live Non-zero enable */
-#define TS_ANNEX_F_EN       (1<<6)  /* Time Sync Annex F enable */
-#define TS_ANNEX_D_EN       (1<<4)  /* Time Sync Annex D enable */
-#define TS_LTYPE2_EN        (1<<3)  /* Time Sync LTYPE 2 enable */
-#define TS_LTYPE1_EN        (1<<2)  /* Time Sync LTYPE 1 enable */
-#define TS_TX_EN            (1<<1)  /* Time Sync Transmit Enable */
-#define TS_RX_EN            (1<<0)  /* Time Sync Receive Enable */
+#define PASS_PRI_TAGGED     BIT(24) /* Pass Priority Tagged */
+#define VLAN_LTYPE2_EN      BIT(21) /* VLAN LTYPE 2 enable */
+#define VLAN_LTYPE1_EN      BIT(20) /* VLAN LTYPE 1 enable */
+#define DSCP_PRI_EN         BIT(16) /* DSCP Priority Enable */
+#define TS_320              BIT(14) /* Time Sync Dest Port 320 enable */
+#define TS_319              BIT(13) /* Time Sync Dest Port 319 enable */
+#define TS_132              BIT(12) /* Time Sync Dest IP Addr 132 enable */
+#define TS_131              BIT(11) /* Time Sync Dest IP Addr 131 enable */
+#define TS_130              BIT(10) /* Time Sync Dest IP Addr 130 enable */
+#define TS_129              BIT(9)  /* Time Sync Dest IP Addr 129 enable */
+#define TS_TTL_NONZERO      BIT(8)  /* Time Sync Time To Live Non-zero enable */
+#define TS_ANNEX_F_EN       BIT(6)  /* Time Sync Annex F enable */
+#define TS_ANNEX_D_EN       BIT(4)  /* Time Sync Annex D enable */
+#define TS_LTYPE2_EN        BIT(3)  /* Time Sync LTYPE 2 enable */
+#define TS_LTYPE1_EN        BIT(2)  /* Time Sync LTYPE 1 enable */
+#define TS_TX_EN            BIT(1)  /* Time Sync Transmit Enable */
+#define TS_RX_EN            BIT(0)  /* Time Sync Receive Enable */
 
 #define CTRL_V2_TS_BITS \
 	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
-- 
cgit v1.2.3


From 1c0e8123e32a048a6c79435704c77d9e04ec5a1b Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Fri, 6 Jul 2018 21:44:45 +0300
Subject: net: ethernet: ti: cpsw: allow PTP 224.0.0.107 to be timestamped

Tested on AM572x with cpsw v1.15 for PTP sync and delay_req messages.
It doesn't work on cpsw v1.12, so added only for cpsw v > 1.15.

Command for testing:
ptp4l -P -4 -H -i eth0 -l 6 -m -q -p /dev/ptp0 -f ptp.cfg
where ptp.cfg:

[global]
tx_timestamp_timeout     20

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index f355e65323f3..00761fe59848 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -257,6 +257,7 @@ struct cpsw_ss_regs {
 #define VLAN_LTYPE2_EN      BIT(21) /* VLAN LTYPE 2 enable */
 #define VLAN_LTYPE1_EN      BIT(20) /* VLAN LTYPE 1 enable */
 #define DSCP_PRI_EN         BIT(16) /* DSCP Priority Enable */
+#define TS_107              BIT(15) /* Tyme Sync Dest IP Address 107 */
 #define TS_320              BIT(14) /* Time Sync Dest Port 320 enable */
 #define TS_319              BIT(13) /* Time Sync Dest Port 319 enable */
 #define TS_132              BIT(12) /* Time Sync Dest IP Addr 132 enable */
@@ -281,7 +282,7 @@ struct cpsw_ss_regs {
 
 
 #define CTRL_V3_TS_BITS \
-	(TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
+	(TS_107 | TS_320 | TS_319 | TS_132 | TS_131 | TS_130 | TS_129 |\
 	 TS_TTL_NONZERO | TS_ANNEX_F_EN | TS_ANNEX_D_EN |\
 	 TS_LTYPE1_EN)
 
-- 
cgit v1.2.3


From 005c1c0eac82d76214581e9698ee183c2df9f3c6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 7 Jul 2018 13:47:06 +0100
Subject: drivers: net: lmc: remove redundant variable next_rx

Variable next_rx is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'next_rx' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/lmc/lmc_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wan/lmc/lmc_main.c b/drivers/net/wan/lmc/lmc_main.c
index 90a4ad9a2d08..093bd21f574d 100644
--- a/drivers/net/wan/lmc/lmc_main.c
+++ b/drivers/net/wan/lmc/lmc_main.c
@@ -1491,7 +1491,6 @@ static int lmc_rx(struct net_device *dev)
     lmc_softc_t *sc = dev_to_sc(dev);
     int i;
     int rx_work_limit = LMC_RXDESCS;
-    unsigned int next_rx;
     int rxIntLoopCnt;		/* debug -baz */
     int localLengthErrCnt = 0;
     long stat;
@@ -1505,7 +1504,6 @@ static int lmc_rx(struct net_device *dev)
     rxIntLoopCnt = 0;		/* debug -baz */
 
     i = sc->lmc_next_rx % LMC_RXDESCS;
-    next_rx = sc->lmc_next_rx;
 
     while (((stat = sc->lmc_rxring[i].status) & LMC_RDES_OWN_BIT) != DESC_OWNED_BY_DC21X4)
     {
-- 
cgit v1.2.3


From 94f01eed49b569a14f02fcfecfd6401a95008049 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sat, 7 Jul 2018 21:36:24 +0200
Subject: batman-adv: Unify include guards style

All other include guards in batman-adv use the style:

* _NET_BATMAN_ADV_$(FILENAME)_
* uppercase only
* "." & "-" replaced with "_"

Use this also in the B.A.T.M.A.N. IV/V OGM implementation headers.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.h | 6 +++---
 net/batman-adv/bat_v_ogm.h  | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h
index 317cafd302cf..3dc6a7a43eb7 100644
--- a/net/batman-adv/bat_iv_ogm.h
+++ b/net/batman-adv/bat_iv_ogm.h
@@ -16,11 +16,11 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifndef _BATMAN_ADV_BATADV_IV_OGM_H_
-#define _BATMAN_ADV_BATADV_IV_OGM_H_
+#ifndef _NET_BATMAN_ADV_BAT_IV_OGM_H_
+#define _NET_BATMAN_ADV_BAT_IV_OGM_H_
 
 #include "main.h"
 
 int batadv_iv_init(void);
 
-#endif /* _BATMAN_ADV_BATADV_IV_OGM_H_ */
+#endif /* _NET_BATMAN_ADV_BAT_IV_OGM_H_ */
diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h
index ed36c5e79fde..e5be14c908c6 100644
--- a/net/batman-adv/bat_v_ogm.h
+++ b/net/batman-adv/bat_v_ogm.h
@@ -16,8 +16,8 @@
  * along with this program; if not, see <http://www.gnu.org/licenses/>.
  */
 
-#ifndef _BATMAN_ADV_BATADV_V_OGM_H_
-#define _BATMAN_ADV_BATADV_V_OGM_H_
+#ifndef _NET_BATMAN_ADV_BAT_V_OGM_H_
+#define _NET_BATMAN_ADV_BAT_V_OGM_H_
 
 #include "main.h"
 
@@ -34,4 +34,4 @@ void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface);
 int batadv_v_ogm_packet_recv(struct sk_buff *skb,
 			     struct batadv_hard_iface *if_incoming);
 
-#endif /* _BATMAN_ADV_BATADV_V_OGM_H_ */
+#endif /* _NET_BATMAN_ADV_BAT_V_OGM_H_ */
-- 
cgit v1.2.3


From 3b1709de64bcc54284812fa43808da07089008ca Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sat, 7 Jul 2018 21:46:11 +0200
Subject: batman-adv: Join batadv_purge_orig_ref and _batadv_purge_orig

The single line function batadv_purge_orig_ref has no function beside
providing the name used by other source files. This can also be done
simpler by just renaming _batadv_purge_orig to batadv_purge_orig_ref.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/originator.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index 716e5b43acfa..1d295da3e342 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -1339,7 +1339,11 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 	return false;
 }
 
-static void _batadv_purge_orig(struct batadv_priv *bat_priv)
+/**
+ * batadv_purge_orig_ref() - Purge all outdated originators
+ * @bat_priv: the bat priv with all the soft interface information
+ */
+void batadv_purge_orig_ref(struct batadv_priv *bat_priv)
 {
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
 	struct hlist_node *node_tmp;
@@ -1385,21 +1389,12 @@ static void batadv_purge_orig(struct work_struct *work)
 
 	delayed_work = to_delayed_work(work);
 	bat_priv = container_of(delayed_work, struct batadv_priv, orig_work);
-	_batadv_purge_orig(bat_priv);
+	batadv_purge_orig_ref(bat_priv);
 	queue_delayed_work(batadv_event_workqueue,
 			   &bat_priv->orig_work,
 			   msecs_to_jiffies(BATADV_ORIG_WORK_PERIOD));
 }
 
-/**
- * batadv_purge_orig_ref() - Purge all outdated originators
- * @bat_priv: the bat priv with all the soft interface information
- */
-void batadv_purge_orig_ref(struct batadv_priv *bat_priv)
-{
-	_batadv_purge_orig(bat_priv);
-}
-
 #ifdef CONFIG_BATMAN_ADV_DEBUGFS
 
 /**
-- 
cgit v1.2.3


From a64ad008980c65d38e6cf6858429c78e6b740c41 Mon Sep 17 00:00:00 2001
From: Alberto Panizzo <alberto@amarulasolutions.com>
Date: Fri, 6 Jul 2018 15:18:51 +0200
Subject: clk: rockchip: fix clk_i2sout parent selection bits on rk3399

Register, shift and mask were wrong according to datasheet.

Fixes: 115510053e5e ("clk: rockchip: add clock controller for the RK3399")
Cc: stable@vger.kernel.org
Signed-off-by: Alberto Panizzo <alberto@amarulasolutions.com>
Signed-off-by: Anthony Brandon <anthony@amarulasolutions.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/clk-rk3399.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index bca10d618f0a..2a8634a52856 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -631,7 +631,7 @@ static struct rockchip_clk_branch rk3399_clk_branches[] __initdata = {
 	MUX(0, "clk_i2sout_src", mux_i2sch_p, CLK_SET_RATE_PARENT,
 			RK3399_CLKSEL_CON(31), 0, 2, MFLAGS),
 	COMPOSITE_NODIV(SCLK_I2S_8CH_OUT, "clk_i2sout", mux_i2sout_p, CLK_SET_RATE_PARENT,
-			RK3399_CLKSEL_CON(30), 8, 2, MFLAGS,
+			RK3399_CLKSEL_CON(31), 2, 1, MFLAGS,
 			RK3399_CLKGATE_CON(8), 12, GFLAGS),
 
 	/* uart */
-- 
cgit v1.2.3


From d2af686c2df82659673c2a795c06dcd37730a3b9 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 7 Jul 2018 08:27:53 -0700
Subject: connector: fix defined but not used warning

Fix a build warning in connector.c when CONFIG_PROC_FS is not enabled
by marking the unused function as __maybe_unused.

../drivers/connector/connector.c:242:12: warning: 'cn_proc_show' defined but not used [-Wunused-function]

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Evgeniy Polyakov <zbr@ioremap.net>
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/connector/connector.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/connector/connector.c b/drivers/connector/connector.c
index e718b8c69a56..eeb7d31cbda5 100644
--- a/drivers/connector/connector.c
+++ b/drivers/connector/connector.c
@@ -19,6 +19,7 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/list.h>
@@ -239,7 +240,7 @@ void cn_del_callback(struct cb_id *id)
 }
 EXPORT_SYMBOL_GPL(cn_del_callback);
 
-static int cn_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused cn_proc_show(struct seq_file *m, void *v)
 {
 	struct cn_queue_dev *dev = cdev.cbdev;
 	struct cn_callback_entry *cbq;
-- 
cgit v1.2.3


From 20fbdc35723f0b3e1a0d2948960244f9721d1646 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 7 Jul 2018 08:31:15 -0700
Subject: isdn/capi: fix defined but not used warnings

Fix build warnings in drivers/isdn/capi/ when CONFIG_PROC_FS is not
enabled by marking the unused functions as __maybe_unused.

../drivers/isdn/capi/capi.c:1324:12: warning: 'capi20_proc_show' defined but not used [-Wunused-function]
../drivers/isdn/capi/capi.c:1347:12: warning: 'capi20ncci_proc_show' defined but not used [-Wunused-function]
../drivers/isdn/capi/capidrv.c:2454:12: warning: 'capidrv_proc_show' defined but not used [-Wunused-function]

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: isdn4linux@listserv.isdn4linux.de (subscribers-only)
Cc: netdev@vger.kernel.org
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/capi/capi.c    | 5 +++--
 drivers/isdn/capi/capidrv.c | 3 ++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 6e0c2814d032..ef5560b848ab 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -9,6 +9,7 @@
  *
  */
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -1321,7 +1322,7 @@ static inline void capinc_tty_exit(void) { }
  * /proc/capi/capi20:
  *  minor applid nrecvctlpkt nrecvdatapkt nsendctlpkt nsenddatapkt
  */
-static int capi20_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capi20_proc_show(struct seq_file *m, void *v)
 {
 	struct capidev *cdev;
 	struct list_head *l;
@@ -1344,7 +1345,7 @@ static int capi20_proc_show(struct seq_file *m, void *v)
  * /proc/capi/capi20ncci:
  *  applid ncci
  */
-static int capi20ncci_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capi20ncci_proc_show(struct seq_file *m, void *v)
 {
 	struct capidev *cdev;
 	struct capincci *np;
diff --git a/drivers/isdn/capi/capidrv.c b/drivers/isdn/capi/capidrv.c
index ee510f901720..e8949f3dcae1 100644
--- a/drivers/isdn/capi/capidrv.c
+++ b/drivers/isdn/capi/capidrv.c
@@ -9,6 +9,7 @@
  *
  */
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/kernel.h>
@@ -2451,7 +2452,7 @@ lower_callback(struct notifier_block *nb, unsigned long val, void *v)
  * /proc/capi/capidrv:
  * nrecvctlpkt nrecvdatapkt nsendctlpkt nsenddatapkt
  */
-static int capidrv_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused capidrv_proc_show(struct seq_file *m, void *v)
 {
 	seq_printf(m, "%lu %lu %lu %lu\n",
 		   global.ap.nrecvctlpkt,
-- 
cgit v1.2.3


From b233504033dbd65740e59681820ccfd0a2a8ec53 Mon Sep 17 00:00:00 2001
From: Yifeng Sun <pkusunyifeng@gmail.com>
Date: Mon, 2 Jul 2018 08:18:03 -0700
Subject: openvswitch: kernel datapath clone action

Add 'clone' action to kernel datapath by using existing functions.
When actions within clone don't modify the current flow, the flow
key is not cloned before executing clone actions.

This is a follow up patch for this incomplete work:
https://patchwork.ozlabs.org/patch/722096/

v1 -> v2:
Refactor as advised by reviewer.

Signed-off-by: Yifeng Sun <pkusunyifeng@gmail.com>
Signed-off-by: Andy Zhou <azhou@ovn.org>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/openvswitch.h      |  5 +++
 include/uapi/linux/openvswitch.h |  3 ++
 net/openvswitch/actions.c        | 33 ++++++++++++++++++
 net/openvswitch/flow_netlink.c   | 73 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 114 insertions(+)

diff --git a/include/linux/openvswitch.h b/include/linux/openvswitch.h
index e6b240b6196c..379affc63e24 100644
--- a/include/linux/openvswitch.h
+++ b/include/linux/openvswitch.h
@@ -21,4 +21,9 @@
 
 #include <uapi/linux/openvswitch.h>
 
+#define OVS_CLONE_ATTR_EXEC      0   /* Specify an u32 value. When nonzero,
+				      * actions in clone will not change flow
+				      * keys. False otherwise.
+				      */
+
 #endif /* _LINUX_OPENVSWITCH_H */
diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h
index 863aabaa5cc9..dbe0cbe4f1b7 100644
--- a/include/uapi/linux/openvswitch.h
+++ b/include/uapi/linux/openvswitch.h
@@ -840,6 +840,8 @@ struct ovs_action_push_eth {
  * @OVS_ACTION_ATTR_POP_NSH: pop the outermost NSH header off the packet.
  * @OVS_ACTION_ATTR_METER: Run packet through a meter, which may drop the
  * packet, or modify the packet (e.g., change the DSCP field).
+ * @OVS_ACTION_ATTR_CLONE: make a copy of the packet and execute a list of
+ * actions without affecting the original packet and key.
  *
  * Only a single header can be set with a single %OVS_ACTION_ATTR_SET.  Not all
  * fields within a header are modifiable, e.g. the IPv4 protocol and fragment
@@ -873,6 +875,7 @@ enum ovs_action_attr {
 	OVS_ACTION_ATTR_PUSH_NSH,     /* Nested OVS_NSH_KEY_ATTR_*. */
 	OVS_ACTION_ATTR_POP_NSH,      /* No argument. */
 	OVS_ACTION_ATTR_METER,        /* u32 meter ID. */
+	OVS_ACTION_ATTR_CLONE,        /* Nested OVS_CLONE_ATTR_*.  */
 
 	__OVS_ACTION_ATTR_MAX,	      /* Nothing past this will be accepted
 				       * from userspace. */
diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c
index 30a5df27116e..85ae53d8fd09 100644
--- a/net/openvswitch/actions.c
+++ b/net/openvswitch/actions.c
@@ -1057,6 +1057,28 @@ static int sample(struct datapath *dp, struct sk_buff *skb,
 			     clone_flow_key);
 }
 
+/* When 'last' is true, clone() should always consume the 'skb'.
+ * Otherwise, clone() should keep 'skb' intact regardless what
+ * actions are executed within clone().
+ */
+static int clone(struct datapath *dp, struct sk_buff *skb,
+		 struct sw_flow_key *key, const struct nlattr *attr,
+		 bool last)
+{
+	struct nlattr *actions;
+	struct nlattr *clone_arg;
+	int rem = nla_len(attr);
+	bool dont_clone_flow_key;
+
+	/* The first action is always 'OVS_CLONE_ATTR_ARG'. */
+	clone_arg = nla_data(attr);
+	dont_clone_flow_key = nla_get_u32(clone_arg);
+	actions = nla_next(clone_arg, &rem);
+
+	return clone_execute(dp, skb, key, 0, actions, rem, last,
+			     !dont_clone_flow_key);
+}
+
 static void execute_hash(struct sk_buff *skb, struct sw_flow_key *key,
 			 const struct nlattr *attr)
 {
@@ -1336,6 +1358,17 @@ static int do_execute_actions(struct datapath *dp, struct sk_buff *skb,
 				consume_skb(skb);
 				return 0;
 			}
+			break;
+
+		case OVS_ACTION_ATTR_CLONE: {
+			bool last = nla_is_last(a, rem);
+
+			err = clone(dp, skb, key, a, last);
+			if (last)
+				return err;
+
+			break;
+		}
 		}
 
 		if (unlikely(err)) {
diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 391c4073a6dc..a70097ecf33c 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2460,6 +2460,40 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr,
 	return 0;
 }
 
+static int validate_and_copy_clone(struct net *net,
+				   const struct nlattr *attr,
+				   const struct sw_flow_key *key,
+				   struct sw_flow_actions **sfa,
+				   __be16 eth_type, __be16 vlan_tci,
+				   bool log, bool last)
+{
+	int start, err;
+	u32 exec;
+
+	if (nla_len(attr) && nla_len(attr) < NLA_HDRLEN)
+		return -EINVAL;
+
+	start = add_nested_action_start(sfa, OVS_ACTION_ATTR_CLONE, log);
+	if (start < 0)
+		return start;
+
+	exec = last || !actions_may_change_flow(attr);
+
+	err = ovs_nla_add_action(sfa, OVS_CLONE_ATTR_EXEC, &exec,
+				 sizeof(exec), log);
+	if (err)
+		return err;
+
+	err = __ovs_nla_copy_actions(net, attr, key, sfa,
+				     eth_type, vlan_tci, log);
+	if (err)
+		return err;
+
+	add_nested_action_end(*sfa, start);
+
+	return 0;
+}
+
 void ovs_match_init(struct sw_flow_match *match,
 		    struct sw_flow_key *key,
 		    bool reset_key,
@@ -2849,6 +2883,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			[OVS_ACTION_ATTR_PUSH_NSH] = (u32)-1,
 			[OVS_ACTION_ATTR_POP_NSH] = 0,
 			[OVS_ACTION_ATTR_METER] = sizeof(u32),
+			[OVS_ACTION_ATTR_CLONE] = (u32)-1,
 		};
 		const struct ovs_action_push_vlan *vlan;
 		int type = nla_type(a);
@@ -3038,6 +3073,18 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 			/* Non-existent meters are simply ignored.  */
 			break;
 
+		case OVS_ACTION_ATTR_CLONE: {
+			bool last = nla_is_last(a, rem);
+
+			err = validate_and_copy_clone(net, a, key, sfa,
+						      eth_type, vlan_tci,
+						      log, last);
+			if (err)
+				return err;
+			skip_copy = true;
+			break;
+		}
+
 		default:
 			OVS_NLERR(log, "Unknown Action type %d", type);
 			return -EINVAL;
@@ -3116,6 +3163,26 @@ out:
 	return err;
 }
 
+static int clone_action_to_attr(const struct nlattr *attr,
+				struct sk_buff *skb)
+{
+	struct nlattr *start;
+	int err = 0, rem = nla_len(attr);
+
+	start = nla_nest_start(skb, OVS_ACTION_ATTR_CLONE);
+	if (!start)
+		return -EMSGSIZE;
+
+	err = ovs_nla_put_actions(nla_data(attr), rem, skb);
+
+	if (err)
+		nla_nest_cancel(skb, start);
+	else
+		nla_nest_end(skb, start);
+
+	return err;
+}
+
 static int set_action_to_attr(const struct nlattr *a, struct sk_buff *skb)
 {
 	const struct nlattr *ovs_key = nla_data(a);
@@ -3204,6 +3271,12 @@ int ovs_nla_put_actions(const struct nlattr *attr, int len, struct sk_buff *skb)
 				return err;
 			break;
 
+		case OVS_ACTION_ATTR_CLONE:
+			err = clone_action_to_attr(a, skb);
+			if (err)
+				return err;
+			break;
+
 		default:
 			if (nla_put(skb, type, nla_len(a), nla_data(a)))
 				return -EMSGSIZE;
-- 
cgit v1.2.3


From eec94fdb04806790c7b7e6ea347820064cc6d467 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:23 +0300
Subject: net: sched: use rcu for action cookie update

Implement functions to atomically update and free action cookie
using rcu mechanism.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  2 +-
 include/net/pkt_cls.h |  1 +
 net/sched/act_api.c   | 44 ++++++++++++++++++++++++++++++--------------
 3 files changed, 32 insertions(+), 15 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 5ff11adbe2a6..ffc3ef321776 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -37,7 +37,7 @@ struct tc_action {
 	spinlock_t			tcfa_lock;
 	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
 	struct gnet_stats_queue __percpu *cpu_qstats;
-	struct tc_cookie	*act_cookie;
+	struct tc_cookie	__rcu *act_cookie;
 	struct tcf_chain	*goto_chain;
 };
 #define tcf_index	common.tcfa_index
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 6641584b27f1..2081e4219f81 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -781,6 +781,7 @@ struct tc_mqprio_qopt_offload {
 struct tc_cookie {
 	u8  *data;
 	u32 len;
+	struct rcu_head rcu;
 };
 
 struct tc_qopt_offload_stats {
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 3f4cf930f809..02670c7489e3 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -55,6 +55,24 @@ static void tcf_action_goto_chain_exec(const struct tc_action *a,
 	res->goto_tp = rcu_dereference_bh(chain->filter_chain);
 }
 
+static void tcf_free_cookie_rcu(struct rcu_head *p)
+{
+	struct tc_cookie *cookie = container_of(p, struct tc_cookie, rcu);
+
+	kfree(cookie->data);
+	kfree(cookie);
+}
+
+static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
+				  struct tc_cookie *new_cookie)
+{
+	struct tc_cookie *old;
+
+	old = xchg(old_cookie, new_cookie);
+	if (old)
+		call_rcu(&old->rcu, tcf_free_cookie_rcu);
+}
+
 /* XXX: For standalone actions, we don't need a RCU grace period either, because
  * actions are always connected to filters and filters are already destroyed in
  * RCU callbacks, so after a RCU grace period actions are already disconnected
@@ -65,10 +83,7 @@ static void free_tcf(struct tc_action *p)
 	free_percpu(p->cpu_bstats);
 	free_percpu(p->cpu_qstats);
 
-	if (p->act_cookie) {
-		kfree(p->act_cookie->data);
-		kfree(p->act_cookie);
-	}
+	tcf_set_action_cookie(&p->act_cookie, NULL);
 	if (p->goto_chain)
 		tcf_action_goto_chain_fini(p);
 
@@ -567,16 +582,22 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 	int err = -EINVAL;
 	unsigned char *b = skb_tail_pointer(skb);
 	struct nlattr *nest;
+	struct tc_cookie *cookie;
 
 	if (nla_put_string(skb, TCA_KIND, a->ops->kind))
 		goto nla_put_failure;
 	if (tcf_action_copy_stats(skb, a, 0))
 		goto nla_put_failure;
-	if (a->act_cookie) {
-		if (nla_put(skb, TCA_ACT_COOKIE, a->act_cookie->len,
-			    a->act_cookie->data))
+
+	rcu_read_lock();
+	cookie = rcu_dereference(a->act_cookie);
+	if (cookie) {
+		if (nla_put(skb, TCA_ACT_COOKIE, cookie->len, cookie->data)) {
+			rcu_read_unlock();
 			goto nla_put_failure;
+		}
 	}
+	rcu_read_unlock();
 
 	nest = nla_nest_start(skb, TCA_OPTIONS);
 	if (nest == NULL)
@@ -719,13 +740,8 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	if (err < 0)
 		goto err_mod;
 
-	if (name == NULL && tb[TCA_ACT_COOKIE]) {
-		if (a->act_cookie) {
-			kfree(a->act_cookie->data);
-			kfree(a->act_cookie);
-		}
-		a->act_cookie = cookie;
-	}
+	if (!name && tb[TCA_ACT_COOKIE])
+		tcf_set_action_cookie(&a->act_cookie, cookie);
 
 	/* module count goes up only when brand new policy is created
 	 * if it exists and is only bound to in a_o->init() then
-- 
cgit v1.2.3


From 036bb44327f50273e85ee4a2c9b56eebce1c0838 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:24 +0300
Subject: net: sched: change type of reference and bind counters

Change type of action reference counter to refcount_t.

Change type of action bind counter to atomic_t.
This type is used to allow decrementing bind counter without testing
for 0 result.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      |  5 +++--
 net/sched/act_api.c        | 32 ++++++++++++++++++++++----------
 net/sched/act_bpf.c        |  4 ++--
 net/sched/act_connmark.c   |  4 ++--
 net/sched/act_csum.c       |  4 ++--
 net/sched/act_gact.c       |  4 ++--
 net/sched/act_ife.c        |  4 ++--
 net/sched/act_ipt.c        |  4 ++--
 net/sched/act_mirred.c     |  4 ++--
 net/sched/act_nat.c        |  4 ++--
 net/sched/act_pedit.c      |  4 ++--
 net/sched/act_police.c     |  4 ++--
 net/sched/act_sample.c     |  4 ++--
 net/sched/act_simple.c     |  4 ++--
 net/sched/act_skbedit.c    |  4 ++--
 net/sched/act_skbmod.c     |  4 ++--
 net/sched/act_tunnel_key.c |  4 ++--
 net/sched/act_vlan.c       |  4 ++--
 18 files changed, 57 insertions(+), 44 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index ffc3ef321776..2759226527a2 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -6,6 +6,7 @@
  * Public action API for classifiers/qdiscs
 */
 
+#include <linux/refcount.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
 #include <net/net_namespace.h>
@@ -26,8 +27,8 @@ struct tc_action {
 	struct tcf_idrinfo		*idrinfo;
 
 	u32				tcfa_index;
-	int				tcfa_refcnt;
-	int				tcfa_bindcnt;
+	refcount_t			tcfa_refcnt;
+	atomic_t			tcfa_bindcnt;
 	u32				tcfa_capab;
 	int				tcfa_action;
 	struct tcf_t			tcfa_tm;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 02670c7489e3..4f064ecab882 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -105,14 +105,26 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
 
 	ASSERT_RTNL();
 
+	/* Release with strict==1 and bind==0 is only called through act API
+	 * interface (classifiers always bind). Only case when action with
+	 * positive reference count and zero bind count can exist is when it was
+	 * also created with act API (unbinding last classifier will destroy the
+	 * action if it was created by classifier). So only case when bind count
+	 * can be changed after initial check is when unbound action is
+	 * destroyed by act API while classifier binds to action with same id
+	 * concurrently. This result either creation of new action(same behavior
+	 * as before), or reusing existing action if concurrent process
+	 * increments reference count before action is deleted. Both scenarios
+	 * are acceptable.
+	 */
 	if (p) {
 		if (bind)
-			p->tcfa_bindcnt--;
-		else if (strict && p->tcfa_bindcnt > 0)
+			atomic_dec(&p->tcfa_bindcnt);
+		else if (strict && atomic_read(&p->tcfa_bindcnt) > 0)
 			return -EPERM;
 
-		p->tcfa_refcnt--;
-		if (p->tcfa_bindcnt <= 0 && p->tcfa_refcnt <= 0) {
+		if (atomic_read(&p->tcfa_bindcnt) <= 0 &&
+		    refcount_dec_and_test(&p->tcfa_refcnt)) {
 			if (p->ops->cleanup)
 				p->ops->cleanup(p);
 			tcf_idr_remove(p->idrinfo, p);
@@ -304,8 +316,8 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
 
 	if (index && p) {
 		if (bind)
-			p->tcfa_bindcnt++;
-		p->tcfa_refcnt++;
+			atomic_inc(&p->tcfa_bindcnt);
+		refcount_inc(&p->tcfa_refcnt);
 		*a = p;
 		return true;
 	}
@@ -324,9 +336,9 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 
 	if (unlikely(!p))
 		return -ENOMEM;
-	p->tcfa_refcnt = 1;
+	refcount_set(&p->tcfa_refcnt, 1);
 	if (bind)
-		p->tcfa_bindcnt = 1;
+		atomic_set(&p->tcfa_bindcnt, 1);
 
 	if (cpustats) {
 		p->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_cpu);
@@ -782,7 +794,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
 		return;
 
 	list_for_each_entry(a, actions, list)
-		a->tcfa_refcnt--;
+		refcount_dec(&a->tcfa_refcnt);
 }
 
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
@@ -810,7 +822,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		act->order = i;
 		sz += tcf_action_fill_size(act);
 		if (ovr)
-			act->tcfa_refcnt++;
+			refcount_inc(&act->tcfa_refcnt);
 		list_add_tail(&act->list, actions);
 	}
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 18089c02e557..15a2a53cbde1 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -141,8 +141,8 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
 	struct tcf_bpf *prog = to_bpf(act);
 	struct tc_act_bpf opt = {
 		.index   = prog->tcf_index,
-		.refcnt  = prog->tcf_refcnt - ref,
-		.bindcnt = prog->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&prog->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
 		.action  = prog->tcf_action,
 	};
 	struct tcf_t tm;
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index e4b880fa51fe..188865034f9a 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -154,8 +154,8 @@ static inline int tcf_connmark_dump(struct sk_buff *skb, struct tc_action *a,
 
 	struct tc_connmark opt = {
 		.index   = ci->tcf_index,
-		.refcnt  = ci->tcf_refcnt - ref,
-		.bindcnt = ci->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&ci->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&ci->tcf_bindcnt) - bind,
 		.action  = ci->tcf_action,
 		.zone   = ci->zone,
 	};
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 526a8e491626..da865f7b390a 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -597,8 +597,8 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	struct tcf_csum_params *params;
 	struct tc_csum opt = {
 		.index   = p->tcf_index,
-		.refcnt  = p->tcf_refcnt - ref,
-		.bindcnt = p->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&p->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
 	};
 	struct tcf_t t;
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 4dc4f153cad8..ca83debd5a70 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -169,8 +169,8 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_gact *gact = to_gact(a);
 	struct tc_gact opt = {
 		.index   = gact->tcf_index,
-		.refcnt  = gact->tcf_refcnt - ref,
-		.bindcnt = gact->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&gact->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&gact->tcf_bindcnt) - bind,
 		.action  = gact->tcf_action,
 	};
 	struct tcf_t t;
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 20d7d36b2fc9..3536a23f46b5 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -596,8 +596,8 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	struct tcf_ife_params *p = rtnl_dereference(ife->params);
 	struct tc_ife opt = {
 		.index = ife->tcf_index,
-		.refcnt = ife->tcf_refcnt - ref,
-		.bindcnt = ife->tcf_bindcnt - bind,
+		.refcnt = refcount_read(&ife->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind,
 		.action = ife->tcf_action,
 		.flags = p->flags,
 	};
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 14c312d7908f..7bce88dc11c9 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -280,8 +280,8 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (unlikely(!t))
 		goto nla_put_failure;
 
-	c.bindcnt = ipt->tcf_bindcnt - bind;
-	c.refcnt = ipt->tcf_refcnt - ref;
+	c.bindcnt = atomic_read(&ipt->tcf_bindcnt) - bind;
+	c.refcnt = refcount_read(&ipt->tcf_refcnt) - ref;
 	strcpy(t->u.user.name, ipt->tcfi_t->u.kernel.target->name);
 
 	if (nla_put(skb, TCA_IPT_TARG, ipt->tcfi_t->u.user.target_size, t) ||
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index fd34015331ab..82a8bdd67c47 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -250,8 +250,8 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	struct tc_mirred opt = {
 		.index   = m->tcf_index,
 		.action  = m->tcf_action,
-		.refcnt  = m->tcf_refcnt - ref,
-		.bindcnt = m->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&m->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&m->tcf_bindcnt) - bind,
 		.eaction = m->tcfm_eaction,
 		.ifindex = dev ? dev->ifindex : 0,
 	};
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 4b5848b6c252..457c2ae3de46 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -257,8 +257,8 @@ static int tcf_nat_dump(struct sk_buff *skb, struct tc_action *a,
 
 		.index    = p->tcf_index,
 		.action   = p->tcf_action,
-		.refcnt   = p->tcf_refcnt - ref,
-		.bindcnt  = p->tcf_bindcnt - bind,
+		.refcnt   = refcount_read(&p->tcf_refcnt) - ref,
+		.bindcnt  = atomic_read(&p->tcf_bindcnt) - bind,
 	};
 	struct tcf_t t;
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index e43aef28fdac..889690e0ec39 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -409,8 +409,8 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 	opt->nkeys = p->tcfp_nkeys;
 	opt->flags = p->tcfp_flags;
 	opt->action = p->tcf_action;
-	opt->refcnt = p->tcf_refcnt - ref;
-	opt->bindcnt = p->tcf_bindcnt - bind;
+	opt->refcnt = refcount_read(&p->tcf_refcnt) - ref;
+	opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind;
 
 	if (p->tcfp_keys_ex) {
 		tcf_pedit_key_ex_dump(skb, p->tcfp_keys_ex, p->tcfp_nkeys);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 4e72bc2a0dfb..a789b8060968 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -274,8 +274,8 @@ static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a,
 		.action = police->tcf_action,
 		.mtu = police->tcfp_mtu,
 		.burst = PSCHED_NS2TICKS(police->tcfp_burst),
-		.refcnt = police->tcf_refcnt - ref,
-		.bindcnt = police->tcf_bindcnt - bind,
+		.refcnt = refcount_read(&police->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&police->tcf_bindcnt) - bind,
 	};
 	struct tcf_t t;
 
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 5db358497c9e..4a46978db092 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -173,8 +173,8 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tc_sample opt = {
 		.index      = s->tcf_index,
 		.action     = s->tcf_action,
-		.refcnt     = s->tcf_refcnt - ref,
-		.bindcnt    = s->tcf_bindcnt - bind,
+		.refcnt     = refcount_read(&s->tcf_refcnt) - ref,
+		.bindcnt    = atomic_read(&s->tcf_bindcnt) - bind,
 	};
 	struct tcf_t t;
 
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 98c4afe7c15b..c3a761097b01 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -145,8 +145,8 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_defact *d = to_defact(a);
 	struct tc_defact opt = {
 		.index   = d->tcf_index,
-		.refcnt  = d->tcf_refcnt - ref,
-		.bindcnt = d->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
 		.action  = d->tcf_action,
 	};
 	struct tcf_t t;
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index dfaf5d8028dd..cfd20d3d2ca9 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -208,8 +208,8 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_skbedit *d = to_skbedit(a);
 	struct tc_skbedit opt = {
 		.index   = d->tcf_index,
-		.refcnt  = d->tcf_refcnt - ref,
-		.bindcnt = d->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
 		.action  = d->tcf_action,
 	};
 	struct tcf_t t;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index ad050d7d4b46..ff90d720eda3 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -205,8 +205,8 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_skbmod_params  *p = rtnl_dereference(d->skbmod_p);
 	struct tc_skbmod opt = {
 		.index   = d->tcf_index,
-		.refcnt  = d->tcf_refcnt - ref,
-		.bindcnt = d->tcf_bindcnt - bind,
+		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
+		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
 		.action  = d->tcf_action,
 	};
 	struct tcf_t t;
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index ea203e386a92..2354f07eba15 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -474,8 +474,8 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_tunnel_key_params *params;
 	struct tc_tunnel_key opt = {
 		.index    = t->tcf_index,
-		.refcnt   = t->tcf_refcnt - ref,
-		.bindcnt  = t->tcf_bindcnt - bind,
+		.refcnt   = refcount_read(&t->tcf_refcnt) - ref,
+		.bindcnt  = atomic_read(&t->tcf_bindcnt) - bind,
 	};
 	struct tcf_t tm;
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 1fb39e1f9d07..799e3deb44ac 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -239,8 +239,8 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p);
 	struct tc_vlan opt = {
 		.index    = v->tcf_index,
-		.refcnt   = v->tcf_refcnt - ref,
-		.bindcnt  = v->tcf_bindcnt - bind,
+		.refcnt   = refcount_read(&v->tcf_refcnt) - ref,
+		.bindcnt  = atomic_read(&v->tcf_bindcnt) - bind,
 		.action   = v->tcf_action,
 		.v_action = p->tcfv_action,
 	};
-- 
cgit v1.2.3


From 789871bb2a0381425b106d2a995bde1460d35a34 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:25 +0300
Subject: net: sched: implement unlocked action init API

Add additional 'rtnl_held' argument to act API init functions. It is
required to implement actions that need to release rtnl lock before loading
kernel module and reacquire if afterwards.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      |  6 ++++--
 net/sched/act_api.c        | 18 +++++++++++-------
 net/sched/act_bpf.c        |  3 ++-
 net/sched/act_connmark.c   |  2 +-
 net/sched/act_csum.c       |  3 ++-
 net/sched/act_gact.c       |  3 ++-
 net/sched/act_ife.c        |  3 ++-
 net/sched/act_ipt.c        |  6 ++++--
 net/sched/act_mirred.c     |  5 +++--
 net/sched/act_nat.c        |  2 +-
 net/sched/act_pedit.c      |  3 ++-
 net/sched/act_police.c     |  2 +-
 net/sched/act_sample.c     |  3 ++-
 net/sched/act_simple.c     |  3 ++-
 net/sched/act_skbedit.c    |  3 ++-
 net/sched/act_skbmod.c     |  3 ++-
 net/sched/act_tunnel_key.c |  3 ++-
 net/sched/act_vlan.c       |  3 ++-
 net/sched/cls_api.c        |  5 +++--
 19 files changed, 50 insertions(+), 29 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 2759226527a2..27823f4e24c4 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -92,7 +92,8 @@ struct tc_action_ops {
 			  struct netlink_ext_ack *extack);
 	int     (*init)(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act, int ovr,
-			int bind, struct netlink_ext_ack *extack);
+			int bind, bool rtnl_held,
+			struct netlink_ext_ack *extack);
 	int     (*walk)(struct net *, struct sk_buff *,
 			struct netlink_callback *, int,
 			const struct tc_action_ops *,
@@ -168,10 +169,11 @@ int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
 		    struct list_head *actions, size_t *attr_size,
-		    struct netlink_ext_ack *extack);
+		    bool rtnl_held, struct netlink_ext_ack *extack);
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
+				    bool rtnl_held,
 				    struct netlink_ext_ack *extack);
 int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 4f064ecab882..256b0c93916c 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -671,6 +671,7 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
+				    bool rtnl_held,
 				    struct netlink_ext_ack *extack)
 {
 	struct tc_action *a;
@@ -721,9 +722,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	a_o = tc_lookup_action_n(act_name);
 	if (a_o == NULL) {
 #ifdef CONFIG_MODULES
-		rtnl_unlock();
+		if (rtnl_held)
+			rtnl_unlock();
 		request_module("act_%s", act_name);
-		rtnl_lock();
+		if (rtnl_held)
+			rtnl_lock();
 
 		a_o = tc_lookup_action_n(act_name);
 
@@ -746,9 +749,10 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	/* backward compatibility for policer */
 	if (name == NULL)
 		err = a_o->init(net, tb[TCA_ACT_OPTIONS], est, &a, ovr, bind,
-				extack);
+				rtnl_held, extack);
 	else
-		err = a_o->init(net, nla, est, &a, ovr, bind, extack);
+		err = a_o->init(net, nla, est, &a, ovr, bind, rtnl_held,
+				extack);
 	if (err < 0)
 		goto err_mod;
 
@@ -800,7 +804,7 @@ static void cleanup_a(struct list_head *actions, int ovr)
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
 		    struct list_head *actions, size_t *attr_size,
-		    struct netlink_ext_ack *extack)
+		    bool rtnl_held, struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
@@ -814,7 +818,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 
 	for (i = 1; i <= TCA_ACT_MAX_PRIO && tb[i]; i++) {
 		act = tcf_action_init_1(net, tp, tb[i], est, name, ovr, bind,
-					extack);
+					rtnl_held, extack);
 		if (IS_ERR(act)) {
 			err = PTR_ERR(act);
 			goto err;
@@ -1173,7 +1177,7 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 	LIST_HEAD(actions);
 
 	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
-			      &attr_size, extack);
+			      &attr_size, true, extack);
 	if (ret)
 		return ret;
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 15a2a53cbde1..8ebf40a3506c 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -276,7 +276,8 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
 
 static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **act,
-			int replace, int bind, struct netlink_ext_ack *extack)
+			int replace, int bind, bool rtnl_held,
+			struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, bpf_net_id);
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 188865034f9a..e3787aa0025a 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -96,7 +96,7 @@ static const struct nla_policy connmark_policy[TCA_CONNMARK_MAX + 1] = {
 
 static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 			     struct nlattr *est, struct tc_action **a,
-			     int ovr, int bind,
+			     int ovr, int bind, bool rtnl_held,
 			     struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, connmark_net_id);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index da865f7b390a..334261943f9f 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -46,7 +46,8 @@ static struct tc_action_ops act_csum_ops;
 
 static int tcf_csum_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a, int ovr,
-			 int bind, struct netlink_ext_ack *extack)
+			 int bind, bool rtnl_held,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
 	struct tcf_csum_params *params_old, *params_new;
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index ca83debd5a70..b4dfb2b4addc 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -56,7 +56,8 @@ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = {
 
 static int tcf_gact_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
-			 int ovr, int bind, struct netlink_ext_ack *extack)
+			 int ovr, int bind, bool rtnl_held,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, gact_net_id);
 	struct nlattr *tb[TCA_GACT_MAX + 1];
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3536a23f46b5..576ffbba61c3 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -448,7 +448,8 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 
 static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a,
-			int ovr, int bind, struct netlink_ext_ack *extack)
+			int ovr, int bind, bool rtnl_held,
+			struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 	struct nlattr *tb[TCA_IFE_MAX + 1];
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 7bce88dc11c9..9c21663a86a6 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -196,7 +196,8 @@ err1:
 
 static int tcf_ipt_init(struct net *net, struct nlattr *nla,
 			struct nlattr *est, struct tc_action **a, int ovr,
-			int bind, struct netlink_ext_ack *extack)
+			int bind, bool rtnl_held,
+			struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, ipt_net_id, nla, est, a, &act_ipt_ops, ovr,
 			      bind);
@@ -204,7 +205,8 @@ static int tcf_ipt_init(struct net *net, struct nlattr *nla,
 
 static int tcf_xt_init(struct net *net, struct nlattr *nla,
 		       struct nlattr *est, struct tc_action **a, int ovr,
-		       int bind, struct netlink_ext_ack *extack)
+		       int bind, bool unlocked,
+		       struct netlink_ext_ack *extack)
 {
 	return __tcf_ipt_init(net, xt_net_id, nla, est, a, &act_xt_ops, ovr,
 			      bind);
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 82a8bdd67c47..5434f08f2eb7 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -68,8 +68,9 @@ static unsigned int mirred_net_id;
 static struct tc_action_ops act_mirred_ops;
 
 static int tcf_mirred_init(struct net *net, struct nlattr *nla,
-			   struct nlattr *est, struct tc_action **a, int ovr,
-			   int bind, struct netlink_ext_ack *extack)
+			   struct nlattr *est, struct tc_action **a,
+			   int ovr, int bind, bool rtnl_held,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, mirred_net_id);
 	struct nlattr *tb[TCA_MIRRED_MAX + 1];
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 457c2ae3de46..e6487ad1e4a8 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -38,7 +38,7 @@ static const struct nla_policy nat_policy[TCA_NAT_MAX + 1] = {
 
 static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 			struct tc_action **a, int ovr, int bind,
-			struct netlink_ext_ack *extack)
+			bool rtnl_held, struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, nat_net_id);
 	struct nlattr *tb[TCA_NAT_MAX + 1];
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 889690e0ec39..f7965f35585b 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -132,7 +132,8 @@ static int tcf_pedit_key_ex_dump(struct sk_buff *skb,
 
 static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
-			  int ovr, int bind, struct netlink_ext_ack *extack)
+			  int ovr, int bind, bool rtnl_held,
+			  struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, pedit_net_id);
 	struct nlattr *tb[TCA_PEDIT_MAX + 1];
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index a789b8060968..0e1c2fb0ebea 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -75,7 +75,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 
 static int tcf_act_police_init(struct net *net, struct nlattr *nla,
 			       struct nlattr *est, struct tc_action **a,
-			       int ovr, int bind,
+			       int ovr, int bind, bool rtnl_held,
 			       struct netlink_ext_ack *extack)
 {
 	int ret = 0, err;
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 4a46978db092..316fc645595d 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -37,7 +37,8 @@ static const struct nla_policy sample_policy[TCA_SAMPLE_MAX + 1] = {
 
 static int tcf_sample_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a, int ovr,
-			   int bind, struct netlink_ext_ack *extack)
+			   int bind, bool rtnl_held,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, sample_net_id);
 	struct nlattr *tb[TCA_SAMPLE_MAX + 1];
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index c3a761097b01..dc591cc87f4a 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -79,7 +79,8 @@ static const struct nla_policy simple_policy[TCA_DEF_MAX + 1] = {
 
 static int tcf_simp_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
-			 int ovr, int bind, struct netlink_ext_ack *extack)
+			 int ovr, int bind, bool rtnl_held,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, simp_net_id);
 	struct nlattr *tb[TCA_DEF_MAX + 1];
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index cfd20d3d2ca9..c4ae4bd830aa 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -94,7 +94,8 @@ static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
 
 static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 			    struct nlattr *est, struct tc_action **a,
-			    int ovr, int bind, struct netlink_ext_ack *extack)
+			    int ovr, int bind, bool rtnl_held,
+			    struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
 	struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index ff90d720eda3..026d6f58eda1 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -84,7 +84,8 @@ static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
 
 static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
-			   int ovr, int bind, struct netlink_ext_ack *extack)
+			   int ovr, int bind, bool rtnl_held,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
 	struct nlattr *tb[TCA_SKBMOD_MAX + 1];
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 2354f07eba15..15ea5ce0f9ed 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -201,7 +201,8 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			   struct nlattr *est, struct tc_action **a,
-			   int ovr, int bind, struct netlink_ext_ack *extack)
+			   int ovr, int bind, bool rtnl_held,
+			   struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 	struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 799e3deb44ac..c61775250722 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -109,7 +109,8 @@ static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
 
 static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			 struct nlattr *est, struct tc_action **a,
-			 int ovr, int bind, struct netlink_ext_ack *extack)
+			 int ovr, int bind, bool rtnl_held,
+			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index bbf8dda96b0e..ebc2b9dd783f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1632,7 +1632,7 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 		if (exts->police && tb[exts->police]) {
 			act = tcf_action_init_1(net, tp, tb[exts->police],
 						rate_tlv, "police", ovr,
-						TCA_ACT_BIND, extack);
+						TCA_ACT_BIND, true, extack);
 			if (IS_ERR(act))
 				return PTR_ERR(act);
 
@@ -1645,7 +1645,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 
 			err = tcf_action_init(net, tp, tb[exts->action],
 					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
-					      &actions, &attr_size, extack);
+					      &actions, &attr_size, true,
+					      extack);
 			if (err)
 				return err;
 			list_for_each_entry(act, &actions, list)
-- 
cgit v1.2.3


From 3f7c72bc4227b169ba2c924a7987324e24bbc4b2 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:26 +0300
Subject: net: sched: always take reference to action

Without rtnl lock protection it is no longer safe to use pointer to tc
action without holding reference to it. (it can be destroyed concurrently)

Remove unsafe action idr lookup function. Instead of it, implement safe tcf
idr check function that atomically looks up action in idr and increments
its reference and bind counters. Implement both action search and check
using new safe function

Reference taken by idr check is temporal and should not be accounted by
userspace clients (both logically and to preserver current API behavior).
Subtract temporal reference when dumping action to userspace using existing
tca_get_fill function arguments.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 46 ++++++++++++++++++++--------------------------
 1 file changed, 20 insertions(+), 26 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 256b0c93916c..aa304d36fee0 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -284,44 +284,38 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(tcf_generic_walker);
 
-static struct tc_action *tcf_idr_lookup(u32 index, struct tcf_idrinfo *idrinfo)
+static bool __tcf_idr_check(struct tc_action_net *tn, u32 index,
+			    struct tc_action **a, int bind)
 {
-	struct tc_action *p = NULL;
+	struct tcf_idrinfo *idrinfo = tn->idrinfo;
+	struct tc_action *p;
 
 	spin_lock(&idrinfo->lock);
 	p = idr_find(&idrinfo->action_idr, index);
+	if (p) {
+		refcount_inc(&p->tcfa_refcnt);
+		if (bind)
+			atomic_inc(&p->tcfa_bindcnt);
+	}
 	spin_unlock(&idrinfo->lock);
 
-	return p;
+	if (p) {
+		*a = p;
+		return true;
+	}
+	return false;
 }
 
 int tcf_idr_search(struct tc_action_net *tn, struct tc_action **a, u32 index)
 {
-	struct tcf_idrinfo *idrinfo = tn->idrinfo;
-	struct tc_action *p = tcf_idr_lookup(index, idrinfo);
-
-	if (p) {
-		*a = p;
-		return 1;
-	}
-	return 0;
+	return __tcf_idr_check(tn, index, a, 0);
 }
 EXPORT_SYMBOL(tcf_idr_search);
 
 bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
 		   int bind)
 {
-	struct tcf_idrinfo *idrinfo = tn->idrinfo;
-	struct tc_action *p = tcf_idr_lookup(index, idrinfo);
-
-	if (index && p) {
-		if (bind)
-			atomic_inc(&p->tcfa_bindcnt);
-		refcount_inc(&p->tcfa_refcnt);
-		*a = p;
-		return true;
-	}
-	return false;
+	return __tcf_idr_check(tn, index, a, bind);
 }
 EXPORT_SYMBOL(tcf_idr_check);
 
@@ -932,7 +926,7 @@ tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
 	if (!skb)
 		return -ENOBUFS;
 	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, event,
-			 0, 0) <= 0) {
+			 0, 1) <= 0) {
 		NL_SET_ERR_MSG(extack, "Failed to fill netlink attributes while adding TC action");
 		kfree_skb(skb);
 		return -EINVAL;
@@ -1072,7 +1066,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
 		return -ENOBUFS;
 
 	if (tca_get_fill(skb, actions, portid, n->nlmsg_seq, 0, RTM_DELACTION,
-			 0, 1) <= 0) {
+			 0, 2) <= 0) {
 		NL_SET_ERR_MSG(extack, "Failed to fill netlink TC action attributes");
 		kfree_skb(skb);
 		return -EINVAL;
@@ -1131,14 +1125,14 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	if (event == RTM_GETACTION)
 		ret = tcf_get_notify(net, portid, n, &actions, event, extack);
 	else { /* delete */
+		cleanup_a(&actions, 1); /* lookup took reference */
 		ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
 		if (ret)
 			goto err;
 		return ret;
 	}
 err:
-	if (event != RTM_GETACTION)
-		tcf_action_destroy(&actions, 0);
+	tcf_action_destroy(&actions, 0);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 2a2ea349704fffade9526d5122299edbbfd122ca Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:27 +0300
Subject: net: sched: implement action API that deletes action by index

Implement new action API function that atomically finds and deletes action
from idr by index. Intended to be used by lockless actions that do not rely
on rtnl lock.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  1 +
 net/sched/act_api.c   | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 27823f4e24c4..a8eaae67c264 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -153,6 +153,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		   int bind, bool cpustats);
 void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
 
+int tcf_idr_delete_index(struct tc_action_net *tn, u32 index);
 int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
 
 static inline int tcf_idr_release(struct tc_action *a, bool bind)
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index aa304d36fee0..0f31f09946ab 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -319,6 +319,45 @@ bool tcf_idr_check(struct tc_action_net *tn, u32 index, struct tc_action **a,
 }
 EXPORT_SYMBOL(tcf_idr_check);
 
+int tcf_idr_delete_index(struct tc_action_net *tn, u32 index)
+{
+	struct tcf_idrinfo *idrinfo = tn->idrinfo;
+	struct tc_action *p;
+	int ret = 0;
+
+	spin_lock(&idrinfo->lock);
+	p = idr_find(&idrinfo->action_idr, index);
+	if (!p) {
+		spin_unlock(&idrinfo->lock);
+		return -ENOENT;
+	}
+
+	if (!atomic_read(&p->tcfa_bindcnt)) {
+		if (refcount_dec_and_test(&p->tcfa_refcnt)) {
+			struct module *owner = p->ops->owner;
+
+			WARN_ON(p != idr_remove(&idrinfo->action_idr,
+						p->tcfa_index));
+			spin_unlock(&idrinfo->lock);
+
+			if (p->ops->cleanup)
+				p->ops->cleanup(p);
+
+			gen_kill_estimator(&p->tcfa_rate_est);
+			free_tcf(p);
+			module_put(owner);
+			return 0;
+		}
+		ret = 0;
+	} else {
+		ret = -EPERM;
+	}
+
+	spin_unlock(&idrinfo->lock);
+	return ret;
+}
+EXPORT_SYMBOL(tcf_idr_delete_index);
+
 int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		   struct tc_action **a, const struct tc_action_ops *ops,
 		   int bind, bool cpustats)
-- 
cgit v1.2.3


From b409074e6693bcdaa7abbee2a035f22a9eabda53 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:28 +0300
Subject: net: sched: add 'delete' function to action ops

Extend action ops with 'delete' function. Each action type to implements
its own delete function that doesn't depend on rtnl lock.

Implement delete function that is required to delete actions without
holding rtnl lock. Use action API function that atomically deletes action
only if it is still in action idr. This implementation prevents concurrent
threads from deleting same action twice.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      |  1 +
 net/sched/act_bpf.c        |  8 ++++++++
 net/sched/act_connmark.c   |  8 ++++++++
 net/sched/act_csum.c       |  8 ++++++++
 net/sched/act_gact.c       |  8 ++++++++
 net/sched/act_ife.c        |  8 ++++++++
 net/sched/act_ipt.c        | 16 ++++++++++++++++
 net/sched/act_mirred.c     |  8 ++++++++
 net/sched/act_nat.c        |  8 ++++++++
 net/sched/act_pedit.c      |  8 ++++++++
 net/sched/act_police.c     |  8 ++++++++
 net/sched/act_sample.c     |  8 ++++++++
 net/sched/act_simple.c     |  8 ++++++++
 net/sched/act_skbedit.c    |  8 ++++++++
 net/sched/act_skbmod.c     |  8 ++++++++
 net/sched/act_tunnel_key.c |  8 ++++++++
 net/sched/act_vlan.c       |  8 ++++++++
 17 files changed, 137 insertions(+)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index a8eaae67c264..b9ed2b8256a5 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -101,6 +101,7 @@ struct tc_action_ops {
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
 	size_t  (*get_fill_size)(const struct tc_action *act);
 	struct net_device *(*get_dev)(const struct tc_action *a);
+	int     (*delete)(struct net *net, u32 index);
 };
 
 struct tc_action_net {
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 8ebf40a3506c..7941dd66ff83 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -388,6 +388,13 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_bpf_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, bpf_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_bpf_ops __read_mostly = {
 	.kind		=	"bpf",
 	.type		=	TCA_ACT_BPF,
@@ -398,6 +405,7 @@ static struct tc_action_ops act_bpf_ops __read_mostly = {
 	.init		=	tcf_bpf_init,
 	.walk		=	tcf_bpf_walker,
 	.lookup		=	tcf_bpf_search,
+	.delete		=	tcf_bpf_delete,
 	.size		=	sizeof(struct tcf_bpf),
 };
 
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index e3787aa0025a..143c2d3de723 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -193,6 +193,13 @@ static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_connmark_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, connmark_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_connmark_ops = {
 	.kind		=	"connmark",
 	.type		=	TCA_ACT_CONNMARK,
@@ -202,6 +209,7 @@ static struct tc_action_ops act_connmark_ops = {
 	.init		=	tcf_connmark_init,
 	.walk		=	tcf_connmark_walker,
 	.lookup		=	tcf_connmark_search,
+	.delete		=	tcf_connmark_delete,
 	.size		=	sizeof(struct tcf_connmark_info),
 };
 
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 334261943f9f..3768539340e0 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -654,6 +654,13 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act)
 	return nla_total_size(sizeof(struct tc_csum));
 }
 
+static int tcf_csum_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, csum_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_csum_ops = {
 	.kind		= "csum",
 	.type		= TCA_ACT_CSUM,
@@ -665,6 +672,7 @@ static struct tc_action_ops act_csum_ops = {
 	.walk		= tcf_csum_walker,
 	.lookup		= tcf_csum_search,
 	.get_fill_size  = tcf_csum_get_fill_size,
+	.delete		= tcf_csum_delete,
 	.size		= sizeof(struct tcf_csum),
 };
 
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index b4dfb2b4addc..a431a711f0dd 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -231,6 +231,13 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act)
 	return sz;
 }
 
+static int tcf_gact_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, gact_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_gact_ops = {
 	.kind		=	"gact",
 	.type		=	TCA_ACT_GACT,
@@ -242,6 +249,7 @@ static struct tc_action_ops act_gact_ops = {
 	.walk		=	tcf_gact_walker,
 	.lookup		=	tcf_gact_search,
 	.get_fill_size	=	tcf_gact_get_fill_size,
+	.delete		=	tcf_gact_delete,
 	.size		=	sizeof(struct tcf_gact),
 };
 
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 576ffbba61c3..89a761395c94 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -844,6 +844,13 @@ static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_ife_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, ife_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_ife_ops = {
 	.kind = "ife",
 	.type = TCA_ACT_IFE,
@@ -854,6 +861,7 @@ static struct tc_action_ops act_ife_ops = {
 	.init = tcf_ife_init,
 	.walk = tcf_ife_walker,
 	.lookup = tcf_ife_search,
+	.delete = tcf_ife_delete,
 	.size =	sizeof(struct tcf_ife_info),
 };
 
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 9c21663a86a6..6c234411c771 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -324,6 +324,13 @@ static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_ipt_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, ipt_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_ipt_ops = {
 	.kind		=	"ipt",
 	.type		=	TCA_ACT_IPT,
@@ -334,6 +341,7 @@ static struct tc_action_ops act_ipt_ops = {
 	.init		=	tcf_ipt_init,
 	.walk		=	tcf_ipt_walker,
 	.lookup		=	tcf_ipt_search,
+	.delete		=	tcf_ipt_delete,
 	.size		=	sizeof(struct tcf_ipt),
 };
 
@@ -374,6 +382,13 @@ static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_xt_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, xt_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_xt_ops = {
 	.kind		=	"xt",
 	.type		=	TCA_ACT_XT,
@@ -384,6 +399,7 @@ static struct tc_action_ops act_xt_ops = {
 	.init		=	tcf_xt_init,
 	.walk		=	tcf_xt_walker,
 	.lookup		=	tcf_xt_search,
+	.delete		=	tcf_xt_delete,
 	.size		=	sizeof(struct tcf_ipt),
 };
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 5434f08f2eb7..3d8300bce7e4 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -322,6 +322,13 @@ static struct net_device *tcf_mirred_get_dev(const struct tc_action *a)
 	return rtnl_dereference(m->tcfm_dev);
 }
 
+static int tcf_mirred_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, mirred_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_mirred_ops = {
 	.kind		=	"mirred",
 	.type		=	TCA_ACT_MIRRED,
@@ -335,6 +342,7 @@ static struct tc_action_ops act_mirred_ops = {
 	.lookup		=	tcf_mirred_search,
 	.size		=	sizeof(struct tcf_mirred),
 	.get_dev	=	tcf_mirred_get_dev,
+	.delete		=	tcf_mirred_delete,
 };
 
 static __net_init int mirred_init_net(struct net *net)
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index e6487ad1e4a8..9eb27c89dc46 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -294,6 +294,13 @@ static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_nat_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, nat_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_nat_ops = {
 	.kind		=	"nat",
 	.type		=	TCA_ACT_NAT,
@@ -303,6 +310,7 @@ static struct tc_action_ops act_nat_ops = {
 	.init		=	tcf_nat_init,
 	.walk		=	tcf_nat_walker,
 	.lookup		=	tcf_nat_search,
+	.delete		=	tcf_nat_delete,
 	.size		=	sizeof(struct tcf_nat),
 };
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index f7965f35585b..45871052840f 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -454,6 +454,13 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_pedit_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, pedit_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_pedit_ops = {
 	.kind		=	"pedit",
 	.type		=	TCA_ACT_PEDIT,
@@ -464,6 +471,7 @@ static struct tc_action_ops act_pedit_ops = {
 	.init		=	tcf_pedit_init,
 	.walk		=	tcf_pedit_walker,
 	.lookup		=	tcf_pedit_search,
+	.delete		=	tcf_pedit_delete,
 	.size		=	sizeof(struct tcf_pedit),
 };
 
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 0e1c2fb0ebea..c955fb0d4f3f 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -314,6 +314,13 @@ static int tcf_police_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_police_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, police_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 MODULE_AUTHOR("Alexey Kuznetsov");
 MODULE_DESCRIPTION("Policing actions");
 MODULE_LICENSE("GPL");
@@ -327,6 +334,7 @@ static struct tc_action_ops act_police_ops = {
 	.init		=	tcf_act_police_init,
 	.walk		=	tcf_act_police_walker,
 	.lookup		=	tcf_police_search,
+	.delete		=	tcf_police_delete,
 	.size		=	sizeof(struct tcf_police),
 };
 
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 316fc645595d..6f79d2afcba2 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -220,6 +220,13 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_sample_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, sample_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_sample_ops = {
 	.kind	  = "sample",
 	.type	  = TCA_ACT_SAMPLE,
@@ -230,6 +237,7 @@ static struct tc_action_ops act_sample_ops = {
 	.cleanup  = tcf_sample_cleanup,
 	.walk	  = tcf_sample_walker,
 	.lookup	  = tcf_sample_search,
+	.delete	  = tcf_sample_delete,
 	.size	  = sizeof(struct tcf_sample),
 };
 
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index dc591cc87f4a..446c750f3d3c 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -184,6 +184,13 @@ static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_simp_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, simp_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_simp_ops = {
 	.kind		=	"simple",
 	.type		=	TCA_ACT_SIMP,
@@ -194,6 +201,7 @@ static struct tc_action_ops act_simp_ops = {
 	.init		=	tcf_simp_init,
 	.walk		=	tcf_simp_walker,
 	.lookup		=	tcf_simp_search,
+	.delete		=	tcf_simp_delete,
 	.size		=	sizeof(struct tcf_defact),
 };
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index c4ae4bd830aa..b3eaa120c7f4 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -267,6 +267,13 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_skbedit_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_skbedit_ops = {
 	.kind		=	"skbedit",
 	.type		=	TCA_ACT_SKBEDIT,
@@ -276,6 +283,7 @@ static struct tc_action_ops act_skbedit_ops = {
 	.init		=	tcf_skbedit_init,
 	.walk		=	tcf_skbedit_walker,
 	.lookup		=	tcf_skbedit_search,
+	.delete		=	tcf_skbedit_delete,
 	.size		=	sizeof(struct tcf_skbedit),
 };
 
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 026d6f58eda1..30be3f767495 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -253,6 +253,13 @@ static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_skbmod_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, skbmod_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_skbmod_ops = {
 	.kind		=	"skbmod",
 	.type		=	TCA_ACT_SKBMOD,
@@ -263,6 +270,7 @@ static struct tc_action_ops act_skbmod_ops = {
 	.cleanup	=	tcf_skbmod_cleanup,
 	.walk		=	tcf_skbmod_walker,
 	.lookup		=	tcf_skbmod_search,
+	.delete		=	tcf_skbmod_delete,
 	.size		=	sizeof(struct tcf_skbmod),
 };
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 15ea5ce0f9ed..655ed0b3fc67 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -534,6 +534,13 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tunnel_key_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_tunnel_key_ops = {
 	.kind		=	"tunnel_key",
 	.type		=	TCA_ACT_TUNNEL_KEY,
@@ -544,6 +551,7 @@ static struct tc_action_ops act_tunnel_key_ops = {
 	.cleanup	=	tunnel_key_release,
 	.walk		=	tunnel_key_walker,
 	.lookup		=	tunnel_key_search,
+	.delete		=	tunnel_key_delete,
 	.size		=	sizeof(struct tcf_tunnel_key),
 };
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index c61775250722..e334d2751784 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -287,6 +287,13 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index,
 	return tcf_idr_search(tn, a, index);
 }
 
+static int tcf_vlan_delete(struct net *net, u32 index)
+{
+	struct tc_action_net *tn = net_generic(net, vlan_net_id);
+
+	return tcf_idr_delete_index(tn, index);
+}
+
 static struct tc_action_ops act_vlan_ops = {
 	.kind		=	"vlan",
 	.type		=	TCA_ACT_VLAN,
@@ -297,6 +304,7 @@ static struct tc_action_ops act_vlan_ops = {
 	.cleanup	=	tcf_vlan_cleanup,
 	.walk		=	tcf_vlan_walker,
 	.lookup		=	tcf_vlan_search,
+	.delete		=	tcf_vlan_delete,
 	.size		=	sizeof(struct tcf_vlan),
 };
 
-- 
cgit v1.2.3


From 16af6067392c40e454e49eec834843ab03643d96 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:29 +0300
Subject: net: sched: implement reference counted action release

Implement helper delete function that uses new action ops 'delete', instead
of destroying action directly. This is required so act API could delete
actions by index, without holding any references to action that is being
deleted.

Implement function __tcf_action_put() that releases reference to action and
frees it, if necessary. Refactor action deletion code to use new put
function and not to rely on rtnl lock. Remove rtnl lock assertions that are
no longer needed.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 84 +++++++++++++++++++++++++++++++++++++++--------------
 net/sched/cls_api.c |  1 -
 2 files changed, 62 insertions(+), 23 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 0f31f09946ab..a023873db713 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -90,21 +90,39 @@ static void free_tcf(struct tc_action *p)
 	kfree(p);
 }
 
-static void tcf_idr_remove(struct tcf_idrinfo *idrinfo, struct tc_action *p)
+static void tcf_action_cleanup(struct tc_action *p)
 {
-	spin_lock(&idrinfo->lock);
-	idr_remove(&idrinfo->action_idr, p->tcfa_index);
-	spin_unlock(&idrinfo->lock);
+	if (p->ops->cleanup)
+		p->ops->cleanup(p);
+
 	gen_kill_estimator(&p->tcfa_rate_est);
 	free_tcf(p);
 }
 
+static int __tcf_action_put(struct tc_action *p, bool bind)
+{
+	struct tcf_idrinfo *idrinfo = p->idrinfo;
+
+	if (refcount_dec_and_lock(&p->tcfa_refcnt, &idrinfo->lock)) {
+		if (bind)
+			atomic_dec(&p->tcfa_bindcnt);
+		idr_remove(&idrinfo->action_idr, p->tcfa_index);
+		spin_unlock(&idrinfo->lock);
+
+		tcf_action_cleanup(p);
+		return 1;
+	}
+
+	if (bind)
+		atomic_dec(&p->tcfa_bindcnt);
+
+	return 0;
+}
+
 int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
 {
 	int ret = 0;
 
-	ASSERT_RTNL();
-
 	/* Release with strict==1 and bind==0 is only called through act API
 	 * interface (classifiers always bind). Only case when action with
 	 * positive reference count and zero bind count can exist is when it was
@@ -118,18 +136,11 @@ int __tcf_idr_release(struct tc_action *p, bool bind, bool strict)
 	 * are acceptable.
 	 */
 	if (p) {
-		if (bind)
-			atomic_dec(&p->tcfa_bindcnt);
-		else if (strict && atomic_read(&p->tcfa_bindcnt) > 0)
+		if (!bind && strict && atomic_read(&p->tcfa_bindcnt) > 0)
 			return -EPERM;
 
-		if (atomic_read(&p->tcfa_bindcnt) <= 0 &&
-		    refcount_dec_and_test(&p->tcfa_refcnt)) {
-			if (p->ops->cleanup)
-				p->ops->cleanup(p);
-			tcf_idr_remove(p->idrinfo, p);
+		if (__tcf_action_put(p, bind))
 			ret = ACT_P_DELETED;
-		}
 	}
 
 	return ret;
@@ -340,11 +351,7 @@ int tcf_idr_delete_index(struct tc_action_net *tn, u32 index)
 						p->tcfa_index));
 			spin_unlock(&idrinfo->lock);
 
-			if (p->ops->cleanup)
-				p->ops->cleanup(p);
-
-			gen_kill_estimator(&p->tcfa_rate_est);
-			free_tcf(p);
+			tcf_action_cleanup(p);
 			module_put(owner);
 			return 0;
 		}
@@ -615,6 +622,11 @@ int tcf_action_destroy(struct list_head *actions, int bind)
 	return ret;
 }
 
+static int tcf_action_put(struct tc_action *p)
+{
+	return __tcf_action_put(p, false);
+}
+
 int
 tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 {
@@ -1092,6 +1104,35 @@ err_out:
 	return err;
 }
 
+static int tcf_action_delete(struct net *net, struct list_head *actions,
+			     struct netlink_ext_ack *extack)
+{
+	struct tc_action *a, *tmp;
+	u32 act_index;
+	int ret;
+
+	list_for_each_entry_safe(a, tmp, actions, list) {
+		const struct tc_action_ops *ops = a->ops;
+
+		/* Actions can be deleted concurrently so we must save their
+		 * type and id to search again after reference is released.
+		 */
+		act_index = a->tcfa_index;
+
+		list_del(&a->list);
+		if (tcf_action_put(a)) {
+			/* last reference, action was deleted concurrently */
+			module_put(ops->owner);
+		} else  {
+			/* now do the delete */
+			ret = ops->delete(net, act_index);
+			if (ret < 0)
+				return ret;
+		}
+	}
+	return 0;
+}
+
 static int
 tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
 	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
@@ -1112,7 +1153,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
 	}
 
 	/* now do the delete */
-	ret = tcf_action_destroy(actions, 0);
+	ret = tcf_action_delete(net, actions, extack);
 	if (ret < 0) {
 		NL_SET_ERR_MSG(extack, "Failed to delete TC action");
 		kfree_skb(skb);
@@ -1164,7 +1205,6 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	if (event == RTM_GETACTION)
 		ret = tcf_get_notify(net, portid, n, &actions, event, extack);
 	else { /* delete */
-		cleanup_a(&actions, 1); /* lookup took reference */
 		ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
 		if (ret)
 			goto err;
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index ebc2b9dd783f..9041f0e43e9a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1611,7 +1611,6 @@ void tcf_exts_destroy(struct tcf_exts *exts)
 #ifdef CONFIG_NET_CLS_ACT
 	LIST_HEAD(actions);
 
-	ASSERT_RTNL();
 	tcf_exts_to_list(exts, &actions);
 	tcf_action_destroy(&actions, TCA_ACT_UNBIND);
 	kfree(exts->actions);
-- 
cgit v1.2.3


From 4e8ddd7f1758ca4ddd0c1f7cf3e66fce736241d2 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:30 +0300
Subject: net: sched: don't release reference on action overwrite

Return from action init function with reference to action taken,
even when overwriting existing action.

Action init API initializes its fourth argument (pointer to pointer to tc
action) to either existing action with same index or newly created action.
In case of existing index(and bind argument is zero), init function returns
without incrementing action reference counter. Caller of action init then
proceeds working with action, without actually holding reference to it.
This means that action could be deleted concurrently.

Change action init behavior to always take reference to action before
returning successfully, in order to protect from concurrent deletion.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c        |  2 --
 net/sched/act_bpf.c        |  8 ++++----
 net/sched/act_connmark.c   |  5 +++--
 net/sched/act_csum.c       |  8 ++++----
 net/sched/act_gact.c       |  5 +++--
 net/sched/act_ife.c        | 10 +++++-----
 net/sched/act_ipt.c        |  5 +++--
 net/sched/act_mirred.c     |  5 ++---
 net/sched/act_nat.c        |  5 +++--
 net/sched/act_pedit.c      |  2 +-
 net/sched/act_police.c     |  8 +++-----
 net/sched/act_sample.c     |  8 +++-----
 net/sched/act_simple.c     |  5 +++--
 net/sched/act_skbedit.c    |  5 +++--
 net/sched/act_skbmod.c     |  8 +++-----
 net/sched/act_tunnel_key.c | 11 ++++-------
 net/sched/act_vlan.c       |  8 +++-----
 17 files changed, 50 insertions(+), 58 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index a023873db713..f019f0464cec 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -870,8 +870,6 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		}
 		act->order = i;
 		sz += tcf_action_fill_size(act);
-		if (ovr)
-			refcount_inc(&act->tcfa_refcnt);
 		list_add_tail(&act->list, actions);
 	}
 
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 7941dd66ff83..d3f4ac6f2c4b 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -311,9 +311,10 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 		if (bind)
 			return 0;
 
-		tcf_idr_release(*act, bind);
-		if (!replace)
+		if (!replace) {
+			tcf_idr_release(*act, bind);
 			return -EEXIST;
+		}
 	}
 
 	is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
@@ -356,8 +357,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	return res;
 out:
-	if (res == ACT_P_CREATED)
-		tcf_idr_release(*act, bind);
+	tcf_idr_release(*act, bind);
 
 	return ret;
 }
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 143c2d3de723..701e90244eff 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -135,9 +135,10 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 		ci = to_connmark(*a);
 		if (bind)
 			return 0;
-		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 		/* replacing action and zone */
 		ci->tcf_action = parm->action;
 		ci->zone = parm->zone;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 3768539340e0..5dbee136b0a1 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -76,9 +76,10 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	} else {
 		if (bind)/* dont override defaults */
 			return 0;
-		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 	}
 
 	p = to_tcf_csum(*a);
@@ -86,8 +87,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
 	if (unlikely(!params_new)) {
-		if (ret == ACT_P_CREATED)
-			tcf_idr_release(*a, bind);
+		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
 	params_old = rtnl_dereference(p->params);
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index a431a711f0dd..11c4de3f344e 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -100,9 +100,10 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	} else {
 		if (bind)/* dont override defaults */
 			return 0;
-		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 	}
 
 	gact = to_gact(*a);
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 89a761395c94..acea3feae762 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -498,12 +498,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 			return ret;
 		}
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr) {
-			kfree(p);
-			return -EEXIST;
-		}
+		kfree(p);
+		return -EEXIST;
 	}
 
 	ife = to_ife(*a);
@@ -548,6 +546,8 @@ metadata_parse_err:
 
 			if (exists)
 				spin_unlock_bh(&ife->tcf_lock);
+			tcf_idr_release(*a, bind);
+
 			kfree(p);
 			return err;
 		}
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 6c234411c771..85e85dfba401 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -145,10 +145,11 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 	} else {
 		if (bind)/* dont override defaults */
 			return 0;
-		tcf_idr_release(*a, bind);
 
-		if (!ovr)
+		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 	}
 	hook = nla_get_u32(tb[TCA_IPT_HOOK]);
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 3d8300bce7e4..e08aed06d7f8 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -132,10 +132,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
-			return -EEXIST;
+		return -EEXIST;
 	}
 	m = to_mirred(*a);
 
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 9eb27c89dc46..1f91e8e66c0f 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -66,9 +66,10 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	} else {
 		if (bind)
 			return 0;
-		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 	}
 	p = to_tcf_nat(*a);
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 45871052840f..3a0e2f762f4e 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -194,8 +194,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	} else {
 		if (bind)
 			goto out_free;
-		tcf_idr_release(*a, bind);
 		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			ret = -EEXIST;
 			goto out_free;
 		}
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index c955fb0d4f3f..99335cca739e 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -111,10 +111,9 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
-			return -EEXIST;
+		return -EEXIST;
 	}
 
 	police = to_police(*a);
@@ -195,8 +194,7 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
 failure:
 	qdisc_put_rtab(P_tab);
 	qdisc_put_rtab(R_tab);
-	if (ret == ACT_P_CREATED)
-		tcf_idr_release(*a, bind);
+	tcf_idr_release(*a, bind);
 	return err;
 }
 
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 6f79d2afcba2..a8582e1347db 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -69,10 +69,9 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		if (ret)
 			return ret;
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
-			return -EEXIST;
+		return -EEXIST;
 	}
 	s = to_sample(*a);
 
@@ -81,8 +80,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
 	psample_group = psample_group_get(net, s->psample_group_num);
 	if (!psample_group) {
-		if (ret == ACT_P_CREATED)
-			tcf_idr_release(*a, bind);
+		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
 	RCU_INIT_POINTER(s->psample_group, psample_group);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 446c750f3d3c..2da47c682a30 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -127,9 +127,10 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 	} else {
 		d = to_defact(*a);
 
-		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 
 		reset_policy(d, tb[TCA_DEF_DATA], parm);
 	}
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index b3eaa120c7f4..4616a2c1821f 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -172,9 +172,10 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		ret = ACT_P_CREATED;
 	} else {
 		d = to_skbedit(*a);
-		tcf_idr_release(*a, bind);
-		if (!ovr)
+		if (!ovr) {
+			tcf_idr_release(*a, bind);
 			return -EEXIST;
+		}
 	}
 
 	spin_lock_bh(&d->tcf_lock);
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index 30be3f767495..e844381af066 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -145,10 +145,9 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 			return ret;
 
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
-			return -EEXIST;
+		return -EEXIST;
 	}
 
 	d = to_skbmod(*a);
@@ -156,8 +155,7 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	ASSERT_RTNL();
 	p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
 	if (unlikely(!p)) {
-		if (ret == ACT_P_CREATED)
-			tcf_idr_release(*a, bind);
+		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 655ed0b3fc67..ab5bf5c13f87 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -329,12 +329,10 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 		}
 
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr) {
-			NL_SET_ERR_MSG(extack, "TC IDR already exists");
-			return -EEXIST;
-		}
+		NL_SET_ERR_MSG(extack, "TC IDR already exists");
+		return -EEXIST;
 	}
 
 	t = to_tunnel_key(*a);
@@ -342,8 +340,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	ASSERT_RTNL();
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
 	if (unlikely(!params_new)) {
-		if (ret == ACT_P_CREATED)
-			tcf_idr_release(*a, bind);
+		tcf_idr_release(*a, bind);
 		NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters");
 		return -ENOMEM;
 	}
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index e334d2751784..9b600faaccbb 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -187,10 +187,9 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			return ret;
 
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
-		if (!ovr)
-			return -EEXIST;
+		return -EEXIST;
 	}
 
 	v = to_vlan(*a);
@@ -198,8 +197,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	ASSERT_RTNL();
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p) {
-		if (ret == ACT_P_CREATED)
-			tcf_idr_release(*a, bind);
+		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
 
-- 
cgit v1.2.3


From cae422f379f37fe9105d2a113259788f989e7df5 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:31 +0300
Subject: net: sched: use reference counting action init

Change action API to assume that action init function always takes
reference to action, even when overwriting existing action. This is
necessary because action API continues to use action pointer after init
function is done. At this point action becomes accessible for concurrent
modifications, so user must always hold reference to it.

Implement helper put list function to atomically release list of actions
after action API init code is done using them.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index f019f0464cec..eefe8c2fe667 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -627,6 +627,18 @@ static int tcf_action_put(struct tc_action *p)
 	return __tcf_action_put(p, false);
 }
 
+static void tcf_action_put_lst(struct list_head *actions)
+{
+	struct tc_action *a, *tmp;
+
+	list_for_each_entry_safe(a, tmp, actions, list) {
+		const struct tc_action_ops *ops = a->ops;
+
+		if (tcf_action_put(a))
+			module_put(ops->owner);
+	}
+}
+
 int
 tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int bind, int ref)
 {
@@ -835,17 +847,6 @@ err_out:
 	return ERR_PTR(err);
 }
 
-static void cleanup_a(struct list_head *actions, int ovr)
-{
-	struct tc_action *a;
-
-	if (!ovr)
-		return;
-
-	list_for_each_entry(a, actions, list)
-		refcount_dec(&a->tcfa_refcnt);
-}
-
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
 		    struct list_head *actions, size_t *attr_size,
@@ -874,11 +875,6 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	}
 
 	*attr_size = tcf_action_full_attrs_size(sz);
-
-	/* Remove the temp refcnt which was necessary to protect against
-	 * destroying an existing action which was being replaced
-	 */
-	cleanup_a(actions, ovr);
 	return 0;
 
 err:
@@ -1209,7 +1205,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 		return ret;
 	}
 err:
-	tcf_action_destroy(&actions, 0);
+	tcf_action_put_lst(&actions);
 	return ret;
 }
 
@@ -1251,8 +1247,11 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 			      &attr_size, true, extack);
 	if (ret)
 		return ret;
+	ret = tcf_add_notify(net, n, &actions, portid, attr_size, extack);
+	if (ovr)
+		tcf_action_put_lst(&actions);
 
-	return tcf_add_notify(net, n, &actions, portid, attr_size, extack);
+	return ret;
 }
 
 static u32 tcaa_root_flags_allowed = TCA_FLAG_LARGE_DUMP_ON;
-- 
cgit v1.2.3


From 0190c1d452a91c38a3462abdd81752be1b9006a8 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:32 +0300
Subject: net: sched: atomically check-allocate action

Implement function that atomically checks if action exists and either takes
reference to it, or allocates idr slot for action index to prevent
concurrent allocations of actions with same index. Use EBUSY error pointer
to indicate that idr slot is reserved.

Implement cleanup helper function that removes temporary error pointer from
idr. (in case of error between idr allocation and insertion of newly
created action to specified index)

Refactor all action init functions to insert new action to idr using this
API.

Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      |  3 ++
 net/sched/act_api.c        | 92 ++++++++++++++++++++++++++++++++++++----------
 net/sched/act_bpf.c        | 11 ++++--
 net/sched/act_connmark.c   | 10 +++--
 net/sched/act_csum.c       | 11 ++++--
 net/sched/act_gact.c       | 11 ++++--
 net/sched/act_ife.c        |  6 ++-
 net/sched/act_ipt.c        | 13 ++++++-
 net/sched/act_mirred.c     | 16 ++++++--
 net/sched/act_nat.c        | 11 ++++--
 net/sched/act_pedit.c      | 12 ++++--
 net/sched/act_police.c     |  9 ++++-
 net/sched/act_sample.c     | 11 ++++--
 net/sched/act_simple.c     | 11 +++++-
 net/sched/act_skbedit.c    | 11 +++++-
 net/sched/act_skbmod.c     | 11 +++++-
 net/sched/act_tunnel_key.c |  9 ++++-
 net/sched/act_vlan.c       | 17 ++++++++-
 18 files changed, 216 insertions(+), 59 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index b9ed2b8256a5..8090de2edab7 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -154,6 +154,9 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 		   int bind, bool cpustats);
 void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a);
 
+void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
+int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
+			struct tc_action **a, int bind);
 int tcf_idr_delete_index(struct tc_action_net *tn, u32 index);
 int __tcf_idr_release(struct tc_action *a, bool bind, bool strict);
 
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index eefe8c2fe667..9511502e1cbb 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -303,7 +303,9 @@ static bool __tcf_idr_check(struct tc_action_net *tn, u32 index,
 
 	spin_lock(&idrinfo->lock);
 	p = idr_find(&idrinfo->action_idr, index);
-	if (p) {
+	if (IS_ERR(p)) {
+		p = NULL;
+	} else if (p) {
 		refcount_inc(&p->tcfa_refcnt);
 		if (bind)
 			atomic_inc(&p->tcfa_bindcnt);
@@ -371,7 +373,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 {
 	struct tc_action *p = kzalloc(ops->size, GFP_KERNEL);
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
-	struct idr *idr = &idrinfo->action_idr;
 	int err = -ENOMEM;
 
 	if (unlikely(!p))
@@ -389,20 +390,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 			goto err2;
 	}
 	spin_lock_init(&p->tcfa_lock);
-	idr_preload(GFP_KERNEL);
-	spin_lock(&idrinfo->lock);
-	/* user doesn't specify an index */
-	if (!index) {
-		index = 1;
-		err = idr_alloc_u32(idr, NULL, &index, UINT_MAX, GFP_ATOMIC);
-	} else {
-		err = idr_alloc_u32(idr, NULL, &index, index, GFP_ATOMIC);
-	}
-	spin_unlock(&idrinfo->lock);
-	idr_preload_end();
-	if (err)
-		goto err3;
-
 	p->tcfa_index = index;
 	p->tcfa_tm.install = jiffies;
 	p->tcfa_tm.lastuse = jiffies;
@@ -412,7 +399,7 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 					&p->tcfa_rate_est,
 					&p->tcfa_lock, NULL, est);
 		if (err)
-			goto err4;
+			goto err3;
 	}
 
 	p->idrinfo = idrinfo;
@@ -420,8 +407,6 @@ int tcf_idr_create(struct tc_action_net *tn, u32 index, struct nlattr *est,
 	INIT_LIST_HEAD(&p->list);
 	*a = p;
 	return 0;
-err4:
-	idr_remove(idr, index);
 err3:
 	free_percpu(p->cpu_qstats);
 err2:
@@ -437,11 +422,78 @@ void tcf_idr_insert(struct tc_action_net *tn, struct tc_action *a)
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
 
 	spin_lock(&idrinfo->lock);
-	idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
+	/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
+	WARN_ON(!IS_ERR(idr_replace(&idrinfo->action_idr, a, a->tcfa_index)));
 	spin_unlock(&idrinfo->lock);
 }
 EXPORT_SYMBOL(tcf_idr_insert);
 
+/* Cleanup idr index that was allocated but not initialized. */
+
+void tcf_idr_cleanup(struct tc_action_net *tn, u32 index)
+{
+	struct tcf_idrinfo *idrinfo = tn->idrinfo;
+
+	spin_lock(&idrinfo->lock);
+	/* Remove ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
+	WARN_ON(!IS_ERR(idr_remove(&idrinfo->action_idr, index)));
+	spin_unlock(&idrinfo->lock);
+}
+EXPORT_SYMBOL(tcf_idr_cleanup);
+
+/* Check if action with specified index exists. If actions is found, increments
+ * its reference and bind counters, and return 1. Otherwise insert temporary
+ * error pointer (to prevent concurrent users from inserting actions with same
+ * index) and return 0.
+ */
+
+int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
+			struct tc_action **a, int bind)
+{
+	struct tcf_idrinfo *idrinfo = tn->idrinfo;
+	struct tc_action *p;
+	int ret;
+
+again:
+	spin_lock(&idrinfo->lock);
+	if (*index) {
+		p = idr_find(&idrinfo->action_idr, *index);
+		if (IS_ERR(p)) {
+			/* This means that another process allocated
+			 * index but did not assign the pointer yet.
+			 */
+			spin_unlock(&idrinfo->lock);
+			goto again;
+		}
+
+		if (p) {
+			refcount_inc(&p->tcfa_refcnt);
+			if (bind)
+				atomic_inc(&p->tcfa_bindcnt);
+			*a = p;
+			ret = 1;
+		} else {
+			*a = NULL;
+			ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
+					    *index, GFP_ATOMIC);
+			if (!ret)
+				idr_replace(&idrinfo->action_idr,
+					    ERR_PTR(-EBUSY), *index);
+		}
+	} else {
+		*index = 1;
+		*a = NULL;
+		ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
+				    UINT_MAX, GFP_ATOMIC);
+		if (!ret)
+			idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY),
+				    *index);
+	}
+	spin_unlock(&idrinfo->lock);
+	return ret;
+}
+EXPORT_SYMBOL(tcf_idr_check_alloc);
+
 void tcf_idrinfo_destroy(const struct tc_action_ops *ops,
 			 struct tcf_idrinfo *idrinfo)
 {
diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index d3f4ac6f2c4b..06f743d8ed41 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -299,14 +299,17 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_ACT_BPF_PARMS]);
 
-	if (!tcf_idr_check(tn, parm->index, act, bind)) {
+	ret = tcf_idr_check_alloc(tn, &parm->index, act, bind);
+	if (!ret) {
 		ret = tcf_idr_create(tn, parm->index, est, act,
 				     &act_bpf_ops, bind, true);
-		if (ret < 0)
+		if (ret < 0) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 
 		res = ACT_P_CREATED;
-	} else {
+	} else if (ret > 0) {
 		/* Don't override defaults. */
 		if (bind)
 			return 0;
@@ -315,6 +318,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 			tcf_idr_release(*act, bind);
 			return -EEXIST;
 		}
+	} else {
+		return ret;
 	}
 
 	is_bpf = tb[TCA_ACT_BPF_OPS_LEN] && tb[TCA_ACT_BPF_OPS];
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 701e90244eff..1e31f0e448e2 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -118,11 +118,14 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_CONNMARK_PARMS]);
 
-	if (!tcf_idr_check(tn, parm->index, a, bind)) {
+	ret = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (!ret) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_connmark_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 
 		ci = to_connmark(*a);
 		ci->tcf_action = parm->action;
@@ -131,7 +134,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 
 		tcf_idr_insert(tn, *a);
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (ret > 0) {
 		ci = to_connmark(*a);
 		if (bind)
 			return 0;
@@ -142,6 +145,7 @@ static int tcf_connmark_init(struct net *net, struct nlattr *nla,
 		/* replacing action and zone */
 		ci->tcf_action = parm->action;
 		ci->zone = parm->zone;
+		ret = 0;
 	}
 
 	return ret;
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 5dbee136b0a1..bd232d3bd022 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -67,19 +67,24 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	parm = nla_data(tb[TCA_CSUM_PARMS]);
 
-	if (!tcf_idr_check(tn, parm->index, a, bind)) {
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (!err) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_csum_ops, bind, true);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (err > 0) {
 		if (bind)/* dont override defaults */
 			return 0;
 		if (!ovr) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
 		}
+	} else {
+		return err;
 	}
 
 	p = to_tcf_csum(*a);
diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 11c4de3f344e..661b72b9147d 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -91,19 +91,24 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	}
 #endif
 
-	if (!tcf_idr_check(tn, parm->index, a, bind)) {
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (!err) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_gact_ops, bind, true);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (err > 0) {
 		if (bind)/* dont override defaults */
 			return 0;
 		if (!ovr) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
 		}
+	} else {
+		return err;
 	}
 
 	gact = to_gact(*a);
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index acea3feae762..a3eef00cd711 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -484,7 +484,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	if (!p)
 		return -ENOMEM;
 
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind) {
 		kfree(p);
 		return 0;
@@ -494,6 +497,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		ret = tcf_idr_create(tn, parm->index, est, a, &act_ife_ops,
 				     bind, true);
 		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			kfree(p);
 			return ret;
 		}
diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 85e85dfba401..0dc787a57798 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -119,13 +119,18 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 	if (tb[TCA_IPT_INDEX] != NULL)
 		index = nla_get_u32(tb[TCA_IPT_INDEX]);
 
-	exists = tcf_idr_check(tn, index, a, bind);
+	err = tcf_idr_check_alloc(tn, &index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
 	if (tb[TCA_IPT_HOOK] == NULL || tb[TCA_IPT_TARG] == NULL) {
 		if (exists)
 			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
@@ -133,14 +138,18 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla,
 	if (nla_len(tb[TCA_IPT_TARG]) < td->u.target_size) {
 		if (exists)
 			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, index, est, a, ops, bind,
 				     false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
 	} else {
 		if (bind)/* dont override defaults */
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index e08aed06d7f8..6afd89a36c69 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -79,7 +79,7 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	struct tcf_mirred *m;
 	struct net_device *dev;
 	bool exists = false;
-	int ret;
+	int ret, err;
 
 	if (!nla) {
 		NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed");
@@ -94,7 +94,10 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 	parm = nla_data(tb[TCA_MIRRED_PARMS]);
 
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
@@ -107,6 +110,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	default:
 		if (exists)
 			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, parm->index);
 		NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
 		return -EINVAL;
 	}
@@ -115,6 +120,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		if (dev == NULL) {
 			if (exists)
 				tcf_idr_release(*a, bind);
+			else
+				tcf_idr_cleanup(tn, parm->index);
 			return -ENODEV;
 		}
 		mac_header_xmit = dev_is_mac_header_xmit(dev);
@@ -124,13 +131,16 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		if (!dev) {
+			tcf_idr_cleanup(tn, parm->index);
 			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
 			return -EINVAL;
 		}
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_mirred_ops, bind, true);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
 	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 1f91e8e66c0f..4dd9188a72fd 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -57,19 +57,24 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 		return -EINVAL;
 	parm = nla_data(tb[TCA_NAT_PARMS]);
 
-	if (!tcf_idr_check(tn, parm->index, a, bind)) {
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (!err) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_nat_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (err > 0) {
 		if (bind)
 			return 0;
 		if (!ovr) {
 			tcf_idr_release(*a, bind);
 			return -EEXIST;
 		}
+	} else {
+		return err;
 	}
 	p = to_tcf_nat(*a);
 
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 3a0e2f762f4e..cc8ffcd1ddb5 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -173,16 +173,20 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (IS_ERR(keys_ex))
 		return PTR_ERR(keys_ex);
 
-	if (!tcf_idr_check(tn, parm->index, a, bind)) {
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (!err) {
 		if (!parm->nkeys) {
+			tcf_idr_cleanup(tn, parm->index);
 			NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed");
 			ret = -EINVAL;
 			goto out_free;
 		}
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_pedit_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			goto out_free;
+		}
 		p = to_pedit(*a);
 		keys = kmalloc(ksize, GFP_KERNEL);
 		if (!keys) {
@@ -191,7 +195,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			goto out_free;
 		}
 		ret = ACT_P_CREATED;
-	} else {
+	} else if (err > 0) {
 		if (bind)
 			goto out_free;
 		if (!ovr) {
@@ -207,6 +211,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 				goto out_free;
 			}
 		}
+	} else {
+		return err;
 	}
 
 	spin_lock_bh(&p->tcf_lock);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 99335cca739e..1f3192ea8df7 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -101,15 +101,20 @@ static int tcf_act_police_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_POLICE_TBF]);
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, NULL, a,
 				     &act_police_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
 	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index a8582e1347db..3079e7be5bde 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -46,7 +46,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	struct tc_sample *parm;
 	struct tcf_sample *s;
 	bool exists = false;
-	int ret;
+	int ret, err;
 
 	if (!nla)
 		return -EINVAL;
@@ -59,15 +59,20 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_SAMPLE_PARMS]);
 
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_sample_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 		ret = ACT_P_CREATED;
 	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 2da47c682a30..aa51152e0066 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -100,21 +100,28 @@ static int tcf_simp_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 
 	parm = nla_data(tb[TCA_DEF_PARMS]);
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
 	if (tb[TCA_DEF_DATA] == NULL) {
 		if (exists)
 			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, parm->index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_simp_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 
 		d = to_defact(*a);
 		ret = alloc_defdata(d, tb[TCA_DEF_DATA]);
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 4616a2c1821f..86521a74ecdd 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -152,21 +152,28 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 	parm = nla_data(tb[TCA_SKBEDIT_PARMS]);
 
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
 	if (!flags) {
 		if (exists)
 			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, parm->index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_skbedit_ops, bind, false);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 
 		d = to_skbedit(*a);
 		ret = ACT_P_CREATED;
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index e844381af066..cdc6bacfb190 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -128,21 +128,28 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	if (parm->flags & SKBMOD_F_SWAPMAC)
 		lflags = SKBMOD_F_SWAPMAC;
 
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
 	if (!lflags) {
 		if (exists)
 			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, parm->index);
 		return -EINVAL;
 	}
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_skbmod_ops, bind, true);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 
 		ret = ACT_P_CREATED;
 	} else if (!ovr) {
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index ab5bf5c13f87..3ec585d58762 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -237,7 +237,10 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	}
 
 	parm = nla_data(tb[TCA_TUNNEL_KEY_PARMS]);
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
@@ -325,7 +328,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 				     &act_tunnel_key_ops, bind, true);
 		if (ret) {
 			NL_SET_ERR_MSG(extack, "Cannot create TC IDR");
-			return ret;
+			goto err_out;
 		}
 
 		ret = ACT_P_CREATED;
@@ -364,6 +367,8 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 err_out:
 	if (exists)
 		tcf_idr_release(*a, bind);
+	else
+		tcf_idr_cleanup(tn, parm->index);
 	return ret;
 }
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 9b600faaccbb..ad37f308175a 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -134,7 +134,10 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	if (!tb[TCA_VLAN_PARMS])
 		return -EINVAL;
 	parm = nla_data(tb[TCA_VLAN_PARMS]);
-	exists = tcf_idr_check(tn, parm->index, a, bind);
+	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
+	if (err < 0)
+		return err;
+	exists = err;
 	if (exists && bind)
 		return 0;
 
@@ -146,12 +149,16 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 		if (!tb[TCA_VLAN_PUSH_VLAN_ID]) {
 			if (exists)
 				tcf_idr_release(*a, bind);
+			else
+				tcf_idr_cleanup(tn, parm->index);
 			return -EINVAL;
 		}
 		push_vid = nla_get_u16(tb[TCA_VLAN_PUSH_VLAN_ID]);
 		if (push_vid >= VLAN_VID_MASK) {
 			if (exists)
 				tcf_idr_release(*a, bind);
+			else
+				tcf_idr_cleanup(tn, parm->index);
 			return -ERANGE;
 		}
 
@@ -164,6 +171,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 			default:
 				if (exists)
 					tcf_idr_release(*a, bind);
+				else
+					tcf_idr_cleanup(tn, parm->index);
 				return -EPROTONOSUPPORT;
 			}
 		} else {
@@ -176,6 +185,8 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	default:
 		if (exists)
 			tcf_idr_release(*a, bind);
+		else
+			tcf_idr_cleanup(tn, parm->index);
 		return -EINVAL;
 	}
 	action = parm->v_action;
@@ -183,8 +194,10 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
 				     &act_vlan_ops, bind, true);
-		if (ret)
+		if (ret) {
+			tcf_idr_cleanup(tn, parm->index);
 			return ret;
+		}
 
 		ret = ACT_P_CREATED;
 	} else if (!ovr) {
-- 
cgit v1.2.3


From 90b73b77d08ec395311411b545c756ca710aae59 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Thu, 5 Jul 2018 17:24:33 +0300
Subject: net: sched: change action API to use array of pointers to actions

Act API used linked list to pass set of actions to functions. It is
intrusive data structure that stores list nodes inside action structure
itself, which means it is not safe to modify such list concurrently.
However, action API doesn't use any linked list specific operations on this
set of actions, so it can be safely refactored into plain pointer array.

Refactor action API to use array of pointers to tc_actions instead of
linked list. Change argument 'actions' type of exported action init,
destroy and dump functions.

Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h |  7 ++--
 net/sched/act_api.c   | 89 +++++++++++++++++++++++++++++----------------------
 net/sched/cls_api.c   | 21 ++++--------
 3 files changed, 60 insertions(+), 57 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 8090de2edab7..683ce41053d9 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -168,19 +168,20 @@ static inline int tcf_idr_release(struct tc_action *a, bool bind)
 int tcf_register_action(struct tc_action_ops *a, struct pernet_operations *ops);
 int tcf_unregister_action(struct tc_action_ops *a,
 			  struct pernet_operations *ops);
-int tcf_action_destroy(struct list_head *actions, int bind);
+int tcf_action_destroy(struct tc_action *actions[], int bind);
 int tcf_action_exec(struct sk_buff *skb, struct tc_action **actions,
 		    int nr_actions, struct tcf_result *res);
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct list_head *actions, size_t *attr_size,
+		    struct tc_action *actions[], size_t *attr_size,
 		    bool rtnl_held, struct netlink_ext_ack *extack);
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
 				    bool rtnl_held,
 				    struct netlink_ext_ack *extack);
-int tcf_action_dump(struct sk_buff *skb, struct list_head *, int, int);
+int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[], int bind,
+		    int ref);
 int tcf_action_dump_old(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int, int);
 int tcf_action_copy_stats(struct sk_buff *, struct tc_action *, int);
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 9511502e1cbb..bf1c35f3deb6 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -657,13 +657,15 @@ repeat:
 }
 EXPORT_SYMBOL(tcf_action_exec);
 
-int tcf_action_destroy(struct list_head *actions, int bind)
+int tcf_action_destroy(struct tc_action *actions[], int bind)
 {
 	const struct tc_action_ops *ops;
-	struct tc_action *a, *tmp;
-	int ret = 0;
+	struct tc_action *a;
+	int ret = 0, i;
 
-	list_for_each_entry_safe(a, tmp, actions, list) {
+	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+		a = actions[i];
+		actions[i] = NULL;
 		ops = a->ops;
 		ret = __tcf_idr_release(a, bind, true);
 		if (ret == ACT_P_DELETED)
@@ -679,11 +681,12 @@ static int tcf_action_put(struct tc_action *p)
 	return __tcf_action_put(p, false);
 }
 
-static void tcf_action_put_lst(struct list_head *actions)
+static void tcf_action_put_many(struct tc_action *actions[])
 {
-	struct tc_action *a, *tmp;
+	int i;
 
-	list_for_each_entry_safe(a, tmp, actions, list) {
+	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+		struct tc_action *a = actions[i];
 		const struct tc_action_ops *ops = a->ops;
 
 		if (tcf_action_put(a))
@@ -735,14 +738,15 @@ nla_put_failure:
 }
 EXPORT_SYMBOL(tcf_action_dump_1);
 
-int tcf_action_dump(struct sk_buff *skb, struct list_head *actions,
+int tcf_action_dump(struct sk_buff *skb, struct tc_action *actions[],
 		    int bind, int ref)
 {
 	struct tc_action *a;
-	int err = -EINVAL;
+	int err = -EINVAL, i;
 	struct nlattr *nest;
 
-	list_for_each_entry(a, actions, list) {
+	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+		a = actions[i];
 		nest = nla_nest_start(skb, a->order);
 		if (nest == NULL)
 			goto nla_put_failure;
@@ -878,10 +882,9 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 	if (TC_ACT_EXT_CMP(a->tcfa_action, TC_ACT_GOTO_CHAIN)) {
 		err = tcf_action_goto_chain_init(a, tp);
 		if (err) {
-			LIST_HEAD(actions);
+			struct tc_action *actions[] = { a, NULL };
 
-			list_add_tail(&a->list, &actions);
-			tcf_action_destroy(&actions, bind);
+			tcf_action_destroy(actions, bind);
 			NL_SET_ERR_MSG(extack, "Failed to init TC action chain");
 			return ERR_PTR(err);
 		}
@@ -899,9 +902,11 @@ err_out:
 	return ERR_PTR(err);
 }
 
+/* Returns numbers of initialized actions or negative error. */
+
 int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		    struct nlattr *est, char *name, int ovr, int bind,
-		    struct list_head *actions, size_t *attr_size,
+		    struct tc_action *actions[], size_t *attr_size,
 		    bool rtnl_held, struct netlink_ext_ack *extack)
 {
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
@@ -923,11 +928,12 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 		}
 		act->order = i;
 		sz += tcf_action_fill_size(act);
-		list_add_tail(&act->list, actions);
+		/* Start from index 0 */
+		actions[i - 1] = act;
 	}
 
 	*attr_size = tcf_action_full_attrs_size(sz);
-	return 0;
+	return i - 1;
 
 err:
 	tcf_action_destroy(actions, bind);
@@ -978,7 +984,7 @@ errout:
 	return -1;
 }
 
-static int tca_get_fill(struct sk_buff *skb, struct list_head *actions,
+static int tca_get_fill(struct sk_buff *skb, struct tc_action *actions[],
 			u32 portid, u32 seq, u16 flags, int event, int bind,
 			int ref)
 {
@@ -1014,7 +1020,7 @@ out_nlmsg_trim:
 
 static int
 tcf_get_notify(struct net *net, u32 portid, struct nlmsghdr *n,
-	       struct list_head *actions, int event,
+	       struct tc_action *actions[], int event,
 	       struct netlink_ext_ack *extack)
 {
 	struct sk_buff *skb;
@@ -1150,14 +1156,14 @@ err_out:
 	return err;
 }
 
-static int tcf_action_delete(struct net *net, struct list_head *actions,
-			     struct netlink_ext_ack *extack)
+static int tcf_action_delete(struct net *net, struct tc_action *actions[],
+			     int *acts_deleted, struct netlink_ext_ack *extack)
 {
-	struct tc_action *a, *tmp;
 	u32 act_index;
-	int ret;
+	int ret, i;
 
-	list_for_each_entry_safe(a, tmp, actions, list) {
+	for (i = 0; i < TCA_ACT_MAX_PRIO && actions[i]; i++) {
+		struct tc_action *a = actions[i];
 		const struct tc_action_ops *ops = a->ops;
 
 		/* Actions can be deleted concurrently so we must save their
@@ -1165,23 +1171,26 @@ static int tcf_action_delete(struct net *net, struct list_head *actions,
 		 */
 		act_index = a->tcfa_index;
 
-		list_del(&a->list);
 		if (tcf_action_put(a)) {
 			/* last reference, action was deleted concurrently */
 			module_put(ops->owner);
 		} else  {
 			/* now do the delete */
 			ret = ops->delete(net, act_index);
-			if (ret < 0)
+			if (ret < 0) {
+				*acts_deleted = i + 1;
 				return ret;
+			}
 		}
 	}
+	*acts_deleted = i;
 	return 0;
 }
 
 static int
-tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
-	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
+tcf_del_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
+	       int *acts_deleted, u32 portid, size_t attr_size,
+	       struct netlink_ext_ack *extack)
 {
 	int ret;
 	struct sk_buff *skb;
@@ -1199,7 +1208,7 @@ tcf_del_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
 	}
 
 	/* now do the delete */
-	ret = tcf_action_delete(net, actions, extack);
+	ret = tcf_action_delete(net, actions, acts_deleted, extack);
 	if (ret < 0) {
 		NL_SET_ERR_MSG(extack, "Failed to delete TC action");
 		kfree_skb(skb);
@@ -1221,7 +1230,8 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
 	struct tc_action *act;
 	size_t attr_size = 0;
-	LIST_HEAD(actions);
+	struct tc_action *actions[TCA_ACT_MAX_PRIO + 1] = {};
+	int acts_deleted = 0;
 
 	ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL, extack);
 	if (ret < 0)
@@ -1243,26 +1253,27 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n,
 		}
 		act->order = i;
 		attr_size += tcf_action_fill_size(act);
-		list_add_tail(&act->list, &actions);
+		actions[i - 1] = act;
 	}
 
 	attr_size = tcf_action_full_attrs_size(attr_size);
 
 	if (event == RTM_GETACTION)
-		ret = tcf_get_notify(net, portid, n, &actions, event, extack);
+		ret = tcf_get_notify(net, portid, n, actions, event, extack);
 	else { /* delete */
-		ret = tcf_del_notify(net, n, &actions, portid, attr_size, extack);
+		ret = tcf_del_notify(net, n, actions, &acts_deleted, portid,
+				     attr_size, extack);
 		if (ret)
 			goto err;
 		return ret;
 	}
 err:
-	tcf_action_put_lst(&actions);
+	tcf_action_put_many(&actions[acts_deleted]);
 	return ret;
 }
 
 static int
-tcf_add_notify(struct net *net, struct nlmsghdr *n, struct list_head *actions,
+tcf_add_notify(struct net *net, struct nlmsghdr *n, struct tc_action *actions[],
 	       u32 portid, size_t attr_size, struct netlink_ext_ack *extack)
 {
 	struct sk_buff *skb;
@@ -1293,15 +1304,15 @@ static int tcf_action_add(struct net *net, struct nlattr *nla,
 {
 	size_t attr_size = 0;
 	int ret = 0;
-	LIST_HEAD(actions);
+	struct tc_action *actions[TCA_ACT_MAX_PRIO] = {};
 
-	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, &actions,
+	ret = tcf_action_init(net, NULL, nla, NULL, NULL, ovr, 0, actions,
 			      &attr_size, true, extack);
-	if (ret)
+	if (ret < 0)
 		return ret;
-	ret = tcf_add_notify(net, n, &actions, portid, attr_size, extack);
+	ret = tcf_add_notify(net, n, actions, portid, attr_size, extack);
 	if (ovr)
-		tcf_action_put_lst(&actions);
+		tcf_action_put_many(actions);
 
 	return ret;
 }
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 9041f0e43e9a..73d9967c3739 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1609,10 +1609,7 @@ out:
 void tcf_exts_destroy(struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	LIST_HEAD(actions);
-
-	tcf_exts_to_list(exts, &actions);
-	tcf_action_destroy(&actions, TCA_ACT_UNBIND);
+	tcf_action_destroy(exts->actions, TCA_ACT_UNBIND);
 	kfree(exts->actions);
 	exts->nr_actions = 0;
 #endif
@@ -1639,18 +1636,15 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb,
 			exts->actions[0] = act;
 			exts->nr_actions = 1;
 		} else if (exts->action && tb[exts->action]) {
-			LIST_HEAD(actions);
-			int err, i = 0;
+			int err;
 
 			err = tcf_action_init(net, tp, tb[exts->action],
 					      rate_tlv, NULL, ovr, TCA_ACT_BIND,
-					      &actions, &attr_size, true,
+					      exts->actions, &attr_size, true,
 					      extack);
-			if (err)
+			if (err < 0)
 				return err;
-			list_for_each_entry(act, &actions, list)
-				exts->actions[i++] = act;
-			exts->nr_actions = i;
+			exts->nr_actions = err;
 		}
 		exts->net = net;
 	}
@@ -1699,14 +1693,11 @@ int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 		 * tc data even if iproute2  was newer - jhs
 		 */
 		if (exts->type != TCA_OLD_COMPAT) {
-			LIST_HEAD(actions);
-
 			nest = nla_nest_start(skb, exts->action);
 			if (nest == NULL)
 				goto nla_put_failure;
 
-			tcf_exts_to_list(exts, &actions);
-			if (tcf_action_dump(skb, &actions, 0, 0) < 0)
+			if (tcf_action_dump(skb, exts->actions, 0, 0) < 0)
 				goto nla_put_failure;
 			nla_nest_end(skb, nest);
 		} else if (exts->police) {
-- 
cgit v1.2.3


From 0dbc81eab4d13f6d295da69c00e6efee2427b55c Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Sun, 8 Jul 2018 17:02:59 +0900
Subject: net: sched: Fix warnings from xchg() on RCU'd cookie pointer.

The kbuild test robot reports:

>> net/sched/act_api.c:71:15: sparse: incorrect type in initializer (different address spaces) @@    expected struct tc_cookie [noderef] <asn:4>*__ret @@    got [noderef] <asn:4>*__ret @@
   net/sched/act_api.c:71:15:    expected struct tc_cookie [noderef] <asn:4>*__ret
   net/sched/act_api.c:71:15:    got struct tc_cookie *new_cookie
>> net/sched/act_api.c:71:13: sparse: incorrect type in assignment (different address spaces) @@    expected struct tc_cookie *old @@    got struct tc_cookie [noderef] <struct tc_cookie *old @@
   net/sched/act_api.c:71:13:    expected struct tc_cookie *old
   net/sched/act_api.c:71:13:    got struct tc_cookie [noderef] <asn:4>*[assigned] __ret
>> net/sched/act_api.c:132:48: sparse: dereference of noderef expression

Handle this in the usual way by force casting away the __rcu annotation
when we are using xchg() on it.

Fixes: eec94fdb0480 ("net: sched: use rcu for action cookie update")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index bf1c35f3deb6..66dc19746c63 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -68,7 +68,7 @@ static void tcf_set_action_cookie(struct tc_cookie __rcu **old_cookie,
 {
 	struct tc_cookie *old;
 
-	old = xchg(old_cookie, new_cookie);
+	old = xchg((__force struct tc_cookie **)old_cookie, new_cookie);
 	if (old)
 		call_rcu(&old->rcu, tcf_free_cookie_rcu);
 }
-- 
cgit v1.2.3


From d4b0d20fec47c95a2bbd2c7d82dc72e59364faae Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:14 +0300
Subject: mlxsw: spectrum: Change name of mlxsw_sp_afk_blocks to
 mlxsw_sp1_afk_blocks

This is specific for Spectrum as Spectrum-2 has completely different key
blocks.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c           | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 79b1fa27a9a4..da93b7fbb836 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -837,8 +837,8 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	acl->mlxsw_sp = mlxsw_sp;
 	acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						       ACL_FLEX_KEYS),
-				    mlxsw_sp_afk_blocks,
-				    MLXSW_SP_AFK_BLOCKS_COUNT);
+				    mlxsw_sp1_afk_blocks,
+				    MLXSW_SP1_AFK_BLOCKS_COUNT);
 	if (!acl->afk) {
 		err = -ENOMEM;
 		goto err_afk_create;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
index fb8031828454..f2924ef98083 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
@@ -104,7 +104,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_packet_type[] = {
 	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x00, 0, 16),
 };
 
-static const struct mlxsw_afk_block mlxsw_sp_afk_blocks[] = {
+static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_l2_dmac),
 	MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_l2_smac),
 	MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_l2_smac_ex),
@@ -119,6 +119,6 @@ static const struct mlxsw_afk_block mlxsw_sp_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
 };
 
-#define MLXSW_SP_AFK_BLOCKS_COUNT ARRAY_SIZE(mlxsw_sp_afk_blocks)
+#define MLXSW_SP1_AFK_BLOCKS_COUNT ARRAY_SIZE(mlxsw_sp1_afk_blocks)
 
 #endif
-- 
cgit v1.2.3


From 45e0620d5eb15daa102e9212b92180adf2f4f0aa Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:15 +0300
Subject: mlxsw: reg: Introduce Flex2 key type for PTAR register

Introduce Flex2 key type for PTAR register which is used in Spectrum-2.
Also, extend mlxsw_reg_ptar_pack() to set the value according to the
caller.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h               | 11 ++++++++---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c |  9 +++++++--
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 1877d9f8a11a..29c51ae91241 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2132,14 +2132,18 @@ MLXSW_ITEM32(reg, ptar, op, 0x00, 28, 4);
 
 /* reg_ptar_action_set_type
  * Type of action set to be used on this region.
- * For Spectrum, this is always type 2 - "flexible"
+ * For Spectrum and Spectrum-2, this is always type 2 - "flexible"
  * Access: WO
  */
 MLXSW_ITEM32(reg, ptar, action_set_type, 0x00, 16, 8);
 
+enum mlxsw_reg_ptar_key_type {
+	MLXSW_REG_PTAR_KEY_TYPE_FLEX = 0x50, /* Spetrum */
+	MLXSW_REG_PTAR_KEY_TYPE_FLEX2 = 0x51, /* Spectrum-2 */
+};
+
 /* reg_ptar_key_type
  * TCAM key type for the region.
- * For Spectrum, this is always type 0x50 - "FLEX_KEY"
  * Access: WO
  */
 MLXSW_ITEM32(reg, ptar, key_type, 0x00, 0, 8);
@@ -2182,13 +2186,14 @@ MLXSW_ITEM8_INDEXED(reg, ptar, flexible_key_id, 0x20, 0, 8,
 		    MLXSW_REG_PTAR_KEY_ID_LEN, 0x00, false);
 
 static inline void mlxsw_reg_ptar_pack(char *payload, enum mlxsw_reg_ptar_op op,
+				       enum mlxsw_reg_ptar_key_type key_type,
 				       u16 region_size, u16 region_id,
 				       const char *tcam_region_info)
 {
 	MLXSW_REG_ZERO(ptar, payload);
 	mlxsw_reg_ptar_op_set(payload, op);
 	mlxsw_reg_ptar_action_set_type_set(payload, 2); /* "flexible" */
-	mlxsw_reg_ptar_key_type_set(payload, 0x50); /* "FLEX_KEY" */
+	mlxsw_reg_ptar_key_type_set(payload, key_type);
 	mlxsw_reg_ptar_region_size_set(payload, region_size);
 	mlxsw_reg_ptar_region_id_set(payload, region_id);
 	mlxsw_reg_ptar_tcam_region_info_memcpy_to(payload, tcam_region_info);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index ad1b548e3cac..87fde93cec0c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -165,6 +165,7 @@ struct mlxsw_sp_acl_tcam_region {
 	struct parman *parman;
 	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_sp_acl_tcam_group *group;
+	enum mlxsw_reg_ptar_key_type key_type;
 	u16 id; /* ACL ID and region ID - they are same */
 	char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
 	struct mlxsw_afk_key_info *key_info;
@@ -455,6 +456,7 @@ mlxsw_sp_acl_tcam_region_alloc(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_ALLOC,
+			    region->key_type,
 			    MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
 			    region->id, region->tcam_region_info);
 	encodings_count = mlxsw_afk_key_info_blocks_count_get(key_info);
@@ -477,7 +479,8 @@ mlxsw_sp_acl_tcam_region_free(struct mlxsw_sp *mlxsw_sp,
 {
 	char ptar_pl[MLXSW_REG_PTAR_LEN];
 
-	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_FREE, 0, region->id,
+	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_FREE,
+			    region->key_type, 0, region->id,
 			    region->tcam_region_info);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
 }
@@ -490,7 +493,8 @@ mlxsw_sp_acl_tcam_region_resize(struct mlxsw_sp *mlxsw_sp,
 	char ptar_pl[MLXSW_REG_PTAR_LEN];
 
 	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_RESIZE,
-			    new_size, region->id, region->tcam_region_info);
+			    region->key_type, new_size, region->id,
+			    region->tcam_region_info);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
 }
 
@@ -713,6 +717,7 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_region_id_get;
 
+	region->key_type = MLXSW_REG_PTAR_KEY_TYPE_FLEX;
 	err = mlxsw_sp_acl_tcam_region_alloc(mlxsw_sp, region);
 	if (err)
 		goto err_tcam_region_alloc;
-- 
cgit v1.2.3


From 2139469b0461ac750b616d110756e374d298e228 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:16 +0300
Subject: mlxsw: spectrum_acl: Ignore always-zeroed bits in tp->prio

The lowest 16 bits of tp->prio are always zero, so ignore them with a
shift.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index da93b7fbb836..b40569c67ddf 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -487,7 +487,7 @@ int mlxsw_sp_acl_rulei_commit(struct mlxsw_sp_acl_rule_info *rulei)
 void mlxsw_sp_acl_rulei_priority(struct mlxsw_sp_acl_rule_info *rulei,
 				 unsigned int priority)
 {
-	rulei->priority = priority;
+	rulei->priority = priority >> 16;
 }
 
 void mlxsw_sp_acl_rulei_keymask_u32(struct mlxsw_sp_acl_rule_info *rulei,
-- 
cgit v1.2.3


From c43ea06dbd8c3daa2c6e3fa6ce3713b454c375f9 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:17 +0300
Subject: mlxsw: core_acl_flex_keys: Split MAC and IP address flex key elements

Since in Spectrum-2, MACs are split and IP addresses are split as well,
in order to use the same elements for Spectrum and Spectrum-2 split them
now.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.h   | 40 ++++++++-----
 .../mellanox/mlxsw/spectrum_acl_flex_keys.h        | 27 +++++----
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 22 ++++---
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c  | 69 +++++++++++++---------
 4 files changed, 96 insertions(+), 62 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 122506daa586..4c7c8eb97b9b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -42,16 +42,20 @@
 
 enum mlxsw_afk_element {
 	MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
-	MLXSW_AFK_ELEMENT_DMAC,
-	MLXSW_AFK_ELEMENT_SMAC,
+	MLXSW_AFK_ELEMENT_DMAC_32_47,
+	MLXSW_AFK_ELEMENT_DMAC_0_31,
+	MLXSW_AFK_ELEMENT_SMAC_32_47,
+	MLXSW_AFK_ELEMENT_SMAC_0_31,
 	MLXSW_AFK_ELEMENT_ETHERTYPE,
 	MLXSW_AFK_ELEMENT_IP_PROTO,
-	MLXSW_AFK_ELEMENT_SRC_IP4,
-	MLXSW_AFK_ELEMENT_DST_IP4,
-	MLXSW_AFK_ELEMENT_SRC_IP6_HI,
-	MLXSW_AFK_ELEMENT_SRC_IP6_LO,
-	MLXSW_AFK_ELEMENT_DST_IP6_HI,
-	MLXSW_AFK_ELEMENT_DST_IP6_LO,
+	MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+	MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+	MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+	MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+	MLXSW_AFK_ELEMENT_DST_IP_96_127,
+	MLXSW_AFK_ELEMENT_DST_IP_64_95,
+	MLXSW_AFK_ELEMENT_DST_IP_32_63,
+	MLXSW_AFK_ELEMENT_DST_IP_0_31,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
 	MLXSW_AFK_ELEMENT_VID,
@@ -100,8 +104,10 @@ struct mlxsw_afk_element_info {
  */
 static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 16),
-	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC, 0x04, 6),
-	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC, 0x0A, 6),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_32_47, 0x04, 2),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_0_31, 0x06, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_32_47, 0x0A, 2),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_0_31, 0x0C, 4),
 	MLXSW_AFK_ELEMENT_INFO_U32(ETHERTYPE, 0x00, 0, 16),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_PROTO, 0x10, 0, 8),
 	MLXSW_AFK_ELEMENT_INFO_U32(VID, 0x10, 8, 12),
@@ -112,12 +118,14 @@ static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_TTL_, 0x18, 0, 8),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_ECN, 0x18, 9, 2),
 	MLXSW_AFK_ELEMENT_INFO_U32(IP_DSCP, 0x18, 11, 6),
-	MLXSW_AFK_ELEMENT_INFO_U32(SRC_IP4, 0x20, 0, 32),
-	MLXSW_AFK_ELEMENT_INFO_U32(DST_IP4, 0x24, 0, 32),
-	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_HI, 0x20, 8),
-	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP6_LO, 0x28, 8),
-	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_HI, 0x30, 8),
-	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP6_LO, 0x38, 8),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_96_127, 0x20, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_64_95, 0x24, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_32_63, 0x28, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(SRC_IP_0_31, 0x2C, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_96_127, 0x30, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_64_95, 0x34, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_32_63, 0x38, 4),
+	MLXSW_AFK_ELEMENT_INFO_BUF(DST_IP_0_31, 0x3C, 4),
 };
 
 #define MLXSW_AFK_ELEMENT_STORAGE_SIZE 0x40
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
index f2924ef98083..800285b2b14a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
@@ -38,38 +38,41 @@
 #include "core_acl_flex_keys.h"
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DMAC, 0x00, 6),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x00, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x02, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x00, 6),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x00, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x02, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC, 0x02, 6),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x02, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_IP4, 0x00, 0, 32),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(DST_IP4, 0x00, 0, 32),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
 	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_IP4, 0x00, 0, 32),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 4, 2),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 24, 8),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x08, 0, 6),
@@ -84,20 +87,24 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_dip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP6_LO, 0x00, 8),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x04, 4),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_ex1[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP6_HI, 0x00, 8),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_96_127, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_64_95, 0x04, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP6_LO, 0x00, 8),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_32_63, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP6_HI, 0x00, 8),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_96_127, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_64_95, 0x04, 4),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_packet_type[] = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 87fde93cec0c..efbd2062b6ec 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -973,12 +973,14 @@ mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 	MLXSW_AFK_ELEMENT_SRC_SYS_PORT,
-	MLXSW_AFK_ELEMENT_DMAC,
-	MLXSW_AFK_ELEMENT_SMAC,
+	MLXSW_AFK_ELEMENT_DMAC_32_47,
+	MLXSW_AFK_ELEMENT_DMAC_0_31,
+	MLXSW_AFK_ELEMENT_SMAC_32_47,
+	MLXSW_AFK_ELEMENT_SMAC_0_31,
 	MLXSW_AFK_ELEMENT_ETHERTYPE,
 	MLXSW_AFK_ELEMENT_IP_PROTO,
-	MLXSW_AFK_ELEMENT_SRC_IP4,
-	MLXSW_AFK_ELEMENT_DST_IP4,
+	MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+	MLXSW_AFK_ELEMENT_DST_IP_0_31,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
 	MLXSW_AFK_ELEMENT_VID,
@@ -992,10 +994,14 @@ static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv6[] = {
 	MLXSW_AFK_ELEMENT_ETHERTYPE,
 	MLXSW_AFK_ELEMENT_IP_PROTO,
-	MLXSW_AFK_ELEMENT_SRC_IP6_HI,
-	MLXSW_AFK_ELEMENT_SRC_IP6_LO,
-	MLXSW_AFK_ELEMENT_DST_IP6_HI,
-	MLXSW_AFK_ELEMENT_DST_IP6_LO,
+	MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+	MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+	MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+	MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+	MLXSW_AFK_ELEMENT_DST_IP_96_127,
+	MLXSW_AFK_ELEMENT_DST_IP_64_95,
+	MLXSW_AFK_ELEMENT_DST_IP_32_63,
+	MLXSW_AFK_ELEMENT_DST_IP_0_31,
 	MLXSW_AFK_ELEMENT_DST_L4_PORT,
 	MLXSW_AFK_ELEMENT_SRC_L4_PORT,
 };
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 89dbf569dff5..201761a3539e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -144,10 +144,12 @@ static void mlxsw_sp_flower_parse_ipv4(struct mlxsw_sp_acl_rule_info *rulei,
 					  FLOW_DISSECTOR_KEY_IPV4_ADDRS,
 					  f->mask);
 
-	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_SRC_IP4,
-				       ntohl(key->src), ntohl(mask->src));
-	mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_DST_IP4,
-				       ntohl(key->dst), ntohl(mask->dst));
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       (char *) &key->src,
+				       (char *) &mask->src, 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       (char *) &key->dst,
+				       (char *) &mask->dst, 4);
 }
 
 static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
@@ -161,24 +163,31 @@ static void mlxsw_sp_flower_parse_ipv6(struct mlxsw_sp_acl_rule_info *rulei,
 		skb_flow_dissector_target(f->dissector,
 					  FLOW_DISSECTOR_KEY_IPV6_ADDRS,
 					  f->mask);
-	size_t addr_half_size = sizeof(key->src) / 2;
-
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP6_HI,
-				       &key->src.s6_addr[0],
-				       &mask->src.s6_addr[0],
-				       addr_half_size);
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP6_LO,
-				       &key->src.s6_addr[addr_half_size],
-				       &mask->src.s6_addr[addr_half_size],
-				       addr_half_size);
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP6_HI,
-				       &key->dst.s6_addr[0],
-				       &mask->dst.s6_addr[0],
-				       addr_half_size);
-	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP6_LO,
-				       &key->dst.s6_addr[addr_half_size],
-				       &mask->dst.s6_addr[addr_half_size],
-				       addr_half_size);
+
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_96_127,
+				       &key->src.s6_addr[0x0],
+				       &mask->src.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_64_95,
+				       &key->src.s6_addr[0x4],
+				       &mask->src.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_32_63,
+				       &key->src.s6_addr[0x8],
+				       &mask->src.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_SRC_IP_0_31,
+				       &key->src.s6_addr[0xC],
+				       &mask->src.s6_addr[0xC], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_96_127,
+				       &key->dst.s6_addr[0x0],
+				       &mask->dst.s6_addr[0x0], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_64_95,
+				       &key->dst.s6_addr[0x4],
+				       &mask->dst.s6_addr[0x4], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_32_63,
+				       &key->dst.s6_addr[0x8],
+				       &mask->dst.s6_addr[0x8], 4);
+	mlxsw_sp_acl_rulei_keymask_buf(rulei, MLXSW_AFK_ELEMENT_DST_IP_0_31,
+				       &key->dst.s6_addr[0xC],
+				       &mask->dst.s6_addr[0xC], 4);
 }
 
 static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
@@ -340,13 +349,17 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 						  f->mask);
 
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
-					       MLXSW_AFK_ELEMENT_DMAC,
-					       key->dst, mask->dst,
-					       sizeof(key->dst));
+					       MLXSW_AFK_ELEMENT_DMAC_32_47,
+					       key->dst, mask->dst, 2);
+		mlxsw_sp_acl_rulei_keymask_buf(rulei,
+					       MLXSW_AFK_ELEMENT_DMAC_0_31,
+					       key->dst + 2, mask->dst + 2, 4);
+		mlxsw_sp_acl_rulei_keymask_buf(rulei,
+					       MLXSW_AFK_ELEMENT_SMAC_32_47,
+					       key->src, mask->src, 2);
 		mlxsw_sp_acl_rulei_keymask_buf(rulei,
-					       MLXSW_AFK_ELEMENT_SMAC,
-					       key->src, mask->src,
-					       sizeof(key->src));
+					       MLXSW_AFK_ELEMENT_SMAC_0_31,
+					       key->src + 2, mask->src + 2, 4);
 	}
 
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) {
-- 
cgit v1.2.3


From 82b63bcf8c2414d6f445830f2076da5ef4a1ba25 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:18 +0300
Subject: mlxsw: core_acl_flex_keys: Change SRC_SYS_PORT flex key element size

The SRC_SYS_PORT is passed as 8 bit value down to hw anyway, so cap it
in the driver as well. Also, in Spectrum-2 the FW iface for SRC_SYS_PORT
is only 8 bits, so prepare for it.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h     | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 4c7c8eb97b9b..154eccd64019 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -103,7 +103,7 @@ struct mlxsw_afk_element_info {
  * define an internal storage geometry.
  */
 static const struct mlxsw_afk_element_info mlxsw_afk_element_infos[] = {
-	MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 16),
+	MLXSW_AFK_ELEMENT_INFO_U32(SRC_SYS_PORT, 0x00, 16, 8),
 	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_32_47, 0x04, 2),
 	MLXSW_AFK_ELEMENT_INFO_BUF(DMAC_0_31, 0x06, 4),
 	MLXSW_AFK_ELEMENT_INFO_BUF(SMAC_32_47, 0x0A, 2),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
index 800285b2b14a..a120c0dccd78 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
@@ -42,7 +42,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x02, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
@@ -50,7 +50,7 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x02, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
 	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
@@ -62,13 +62,13 @@ static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
 	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
 	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
-- 
cgit v1.2.3


From 9dbab6f588ebc9b6f741f926dc06878cba4f6c77 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:19 +0300
Subject: mlxsw: spectrum: Put pointer to flex action ops to mlxsw_sp

Spectrum-2 need a slightly different handling of flexible actions. So
put an ops pointer in mlxsw_sp struct and rename it.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c                  | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h                  | 4 ++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c | 4 ++--
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 52437363766a..cba0e9ba7dea 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3621,6 +3621,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
+	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
+
 	mlxsw_sp->core = mlxsw_core;
 	mlxsw_sp->bus_info = mlxsw_bus_info;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 4a519d8edec8..f5294c9a4c92 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -168,6 +168,7 @@ struct mlxsw_sp {
 		struct mlxsw_sp_span_entry *entries;
 		int entries_count;
 	} span;
+	const struct mlxsw_afa_ops *afa_ops;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -584,6 +585,9 @@ void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
 /* spectrum_acl_tcam.c */
 extern const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops;
 
+/* spectrum_acl_flex_actions.c */
+extern const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops;
+
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index 510ce48d87f7..5ab070916949 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -154,7 +154,7 @@ mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, int span_id, bool ingress)
 	mlxsw_sp_span_mirror_del(in_port, span_id, type, false);
 }
 
-static const struct mlxsw_afa_ops mlxsw_sp_act_afa_ops = {
+const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
 	.kvdl_set_add		= mlxsw_sp_act_kvdl_set_add,
 	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
 	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
@@ -169,7 +169,7 @@ int mlxsw_sp_afa_init(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
 							    ACL_ACTIONS_PER_SET),
-					 &mlxsw_sp_act_afa_ops, mlxsw_sp);
+					 mlxsw_sp->afa_ops, mlxsw_sp);
 	return PTR_ERR_OR_ZERO(mlxsw_sp->afa);
 }
 
-- 
cgit v1.2.3


From 5b9488fd5f1e007d22543e68cc95eb41c91f8018 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:20 +0300
Subject: mlxsw: core_acl_flex_actions: Allow the first set to be dummy

In Spectrum-2, the real action sets are always in KVD linear. The first
set is always empty and contains only pointer to the first real set in
KVD linear. So provide possibility to specify the first set is the dummy
one.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c | 17 ++++++++++++++++-
 .../net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h |  1 +
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 3c0d882ba183..9395bf385fa9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -351,9 +351,24 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa)
 	block->first_set = mlxsw_afa_set_create(true);
 	if (!block->first_set)
 		goto err_first_set_create;
-	block->cur_set = block->first_set;
+
+	/* In case user instructs to have dummy first set, we leave it
+	 * empty here and create another, real, set right away.
+	 */
+	if (mlxsw_afa->ops->dummy_first_set) {
+		block->cur_set = mlxsw_afa_set_create(false);
+		if (!block->cur_set)
+			goto err_second_set_create;
+		block->cur_set->prev = block->first_set;
+		block->first_set->next = block->cur_set;
+	} else {
+		block->cur_set = block->first_set;
+	}
+
 	return block;
 
+err_second_set_create:
+	mlxsw_afa_set_destroy(block->first_set);
 err_first_set_create:
 	kfree(block);
 	return NULL;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index 3a155d104384..f9c77bf48e24 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -54,6 +54,7 @@ struct mlxsw_afa_ops {
 			  bool ingress, int *p_span_id);
 	void (*mirror_del)(void *priv, u8 local_in_port, int span_id,
 			   bool ingress);
+	bool dummy_first_set;
 };
 
 struct mlxsw_afa *mlxsw_afa_create(unsigned int max_acts_per_set,
-- 
cgit v1.2.3


From 0317a6f4eb42a7a8cc9c920183d340312d2e8c87 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 10:00:21 +0300
Subject: mlxsw: core_acl_flex_actions: Fix helper to get the first KVD linear
 index

The helper should return always KVD linear index of the second set.
It is unused now, but going to be used soon.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c | 11 ++++++++---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h |  2 +-
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 9395bf385fa9..72a6a8a2131e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -430,11 +430,16 @@ char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block)
 }
 EXPORT_SYMBOL(mlxsw_afa_block_first_set);
 
-u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block)
+u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block)
 {
-	return block->first_set->kvdl_index;
+	/* First set is never in KVD linear. So the first set
+	 * with valid KVD linear index is always the second one.
+	 */
+	if (WARN_ON(!block->first_set->next))
+		return 0;
+	return block->first_set->next->kvdl_index;
 }
-EXPORT_SYMBOL(mlxsw_afa_block_first_set_kvdl_index);
+EXPORT_SYMBOL(mlxsw_afa_block_first_kvdl_index);
 
 int mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index f9c77bf48e24..c18249ac28f7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -65,7 +65,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa);
 void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_commit(struct mlxsw_afa_block *block);
 char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block);
-u32 mlxsw_afa_block_first_set_kvdl_index(struct mlxsw_afa_block *block);
+u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
 int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block);
-- 
cgit v1.2.3


From c47078d6a33fd78d882200cdaacbcfcd63318234 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 7 Jul 2018 23:15:56 -0700
Subject: tcp: remove redundant SOCK_DONE checks

In both tcp_splice_read() and tcp_recvmsg(), we already test
sock_flag(sk, SOCK_DONE) right before evaluating sk->sk_state,
so "!sock_flag(sk, SOCK_DONE)" is always true.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 850dc8f15afc..c4082cd50257 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -817,8 +817,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 				 * This occurs when user tries to read
 				 * from never connected socket.
 				 */
-				if (!sock_flag(sk, SOCK_DONE))
-					ret = -ENOTCONN;
+				ret = -ENOTCONN;
 				break;
 			}
 			if (!timeo) {
@@ -2042,13 +2041,10 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 				break;
 
 			if (sk->sk_state == TCP_CLOSE) {
-				if (!sock_flag(sk, SOCK_DONE)) {
-					/* This occurs when user tries to read
-					 * from never connected socket.
-					 */
-					copied = -ENOTCONN;
-					break;
-				}
+				/* This occurs when user tries to read
+				 * from never connected socket.
+				 */
+				copied = -ENOTCONN;
 				break;
 			}
 
-- 
cgit v1.2.3


From 993a4a5f7cd3aef53be3953d11f86b2d3630ebb8 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sat, 7 Jul 2018 21:50:18 +0200
Subject: batman-adv: Convert batadv_dat_addr_t to proper type

The #define for batadv_dat_addr_t is doing nothing else than giving u16 a
new typename. But C already has the special keyword "typedef" which is also
better supported by kernel-doc.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Acked-by: Antonio Quartulli <a@unstable.cc>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/types.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 360357f83f20..343d304851a5 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -43,12 +43,13 @@ struct seq_file;
 #ifdef CONFIG_BATMAN_ADV_DAT
 
 /**
- * batadv_dat_addr_t - it is the type used for all DHT addresses. If it is
- *  changed, BATADV_DAT_ADDR_MAX is changed as well.
+ * typedef batadv_dat_addr_t - type used for all DHT addresses
+ *
+ * If it is changed, BATADV_DAT_ADDR_MAX is changed as well.
  *
  * *Please be careful: batadv_dat_addr_t must be UNSIGNED*
  */
-#define batadv_dat_addr_t u16
+typedef u16 batadv_dat_addr_t;
 
 #endif /* CONFIG_BATMAN_ADV_DAT */
 
-- 
cgit v1.2.3


From ea169a30a6bf6782a05a51d2b9cf73db151eab8b Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Mon, 25 Jun 2018 12:00:18 +0200
Subject: crypto: ecdh - add public key verification test

According to SP800-56A section 5.6.2.1, the public key to be processed
for the ECDH operation shall be checked for appropriateness. When the
public key is considered to be an ephemeral key, the partial validation
test as defined in SP800-56A section 5.6.2.3.4 can be applied.

The partial verification test requires the presence of the field
elements of a and b. For the implemented NIST curves, b is defined in
FIPS 186-4 appendix D.1.2. The element a is implicitly given with the
Weierstrass equation given in D.1.2 where a = p - 3.

Without the test, the NIST ACVP testing fails. After adding this check,
the NIST ACVP testing passes.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ecc.c            | 42 ++++++++++++++++++++++++++++++++++++++----
 crypto/ecc_curve_defs.h | 22 ++++++++++++++++++----
 2 files changed, 56 insertions(+), 8 deletions(-)

diff --git a/crypto/ecc.c b/crypto/ecc.c
index 815541309a95..8facafd67802 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -1019,6 +1019,36 @@ out:
 	return ret;
 }
 
+/* SP800-56A section 5.6.2.3.4 partial verification: ephemeral keys only */
+static int ecc_is_pubkey_valid_partial(const struct ecc_curve *curve,
+				       struct ecc_point *pk)
+{
+	u64 yy[ECC_MAX_DIGITS], xxx[ECC_MAX_DIGITS], w[ECC_MAX_DIGITS];
+
+	/* Check 1: Verify key is not the zero point. */
+	if (ecc_point_is_zero(pk))
+		return -EINVAL;
+
+	/* Check 2: Verify key is in the range [1, p-1]. */
+	if (vli_cmp(curve->p, pk->x, pk->ndigits) != 1)
+		return -EINVAL;
+	if (vli_cmp(curve->p, pk->y, pk->ndigits) != 1)
+		return -EINVAL;
+
+	/* Check 3: Verify that y^2 == (x^3 + a·x + b) mod p */
+	vli_mod_square_fast(yy, pk->y, curve->p, pk->ndigits); /* y^2 */
+	vli_mod_square_fast(xxx, pk->x, curve->p, pk->ndigits); /* x^2 */
+	vli_mod_mult_fast(xxx, xxx, pk->x, curve->p, pk->ndigits); /* x^3 */
+	vli_mod_mult_fast(w, curve->a, pk->x, curve->p, pk->ndigits); /* a·x */
+	vli_mod_add(w, w, curve->b, curve->p, pk->ndigits); /* a·x + b */
+	vli_mod_add(w, w, xxx, curve->p, pk->ndigits); /* x^3 + a·x + b */
+	if (vli_cmp(yy, w, pk->ndigits) != 0) /* Equation */
+		return -EINVAL;
+
+	return 0;
+
+}
+
 int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 			      const u64 *private_key, const u64 *public_key,
 			      u64 *secret)
@@ -1046,16 +1076,20 @@ int crypto_ecdh_shared_secret(unsigned int curve_id, unsigned int ndigits,
 		goto out;
 	}
 
+	ecc_swap_digits(public_key, pk->x, ndigits);
+	ecc_swap_digits(&public_key[ndigits], pk->y, ndigits);
+	ret = ecc_is_pubkey_valid_partial(curve, pk);
+	if (ret)
+		goto err_alloc_product;
+
+	ecc_swap_digits(private_key, priv, ndigits);
+
 	product = ecc_alloc_point(ndigits);
 	if (!product) {
 		ret = -ENOMEM;
 		goto err_alloc_product;
 	}
 
-	ecc_swap_digits(public_key, pk->x, ndigits);
-	ecc_swap_digits(&public_key[ndigits], pk->y, ndigits);
-	ecc_swap_digits(private_key, priv, ndigits);
-
 	ecc_point_mult(product, pk, priv, rand_z, curve->p, ndigits);
 
 	ecc_swap_digits(product->x, secret, ndigits);
diff --git a/crypto/ecc_curve_defs.h b/crypto/ecc_curve_defs.h
index b80f45da829c..94e883a9403f 100644
--- a/crypto/ecc_curve_defs.h
+++ b/crypto/ecc_curve_defs.h
@@ -13,9 +13,11 @@ struct ecc_curve {
 	struct ecc_point g;
 	u64 *p;
 	u64 *n;
+	u64 *a;
+	u64 *b;
 };
 
-/* NIST P-192 */
+/* NIST P-192: a = p - 3 */
 static u64 nist_p192_g_x[] = { 0xF4FF0AFD82FF1012ull, 0x7CBF20EB43A18800ull,
 				0x188DA80EB03090F6ull };
 static u64 nist_p192_g_y[] = { 0x73F977A11E794811ull, 0x631011ED6B24CDD5ull,
@@ -24,6 +26,10 @@ static u64 nist_p192_p[] = { 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFEull,
 				0xFFFFFFFFFFFFFFFFull };
 static u64 nist_p192_n[] = { 0x146BC9B1B4D22831ull, 0xFFFFFFFF99DEF836ull,
 				0xFFFFFFFFFFFFFFFFull };
+static u64 nist_p192_a[] = { 0xFFFFFFFFFFFFFFFCull, 0xFFFFFFFFFFFFFFFEull,
+				0xFFFFFFFFFFFFFFFEull };
+static u64 nist_p192_b[] = { 0xFEB8DEECC146B9B1ull, 0x0FA7E9AB72243049ull,
+				0x64210519E59C80E7ull };
 static struct ecc_curve nist_p192 = {
 	.name = "nist_192",
 	.g = {
@@ -32,10 +38,12 @@ static struct ecc_curve nist_p192 = {
 		.ndigits = 3,
 	},
 	.p = nist_p192_p,
-	.n = nist_p192_n
+	.n = nist_p192_n,
+	.a = nist_p192_a,
+	.b = nist_p192_b
 };
 
-/* NIST P-256 */
+/* NIST P-256: a = p - 3 */
 static u64 nist_p256_g_x[] = { 0xF4A13945D898C296ull, 0x77037D812DEB33A0ull,
 				0xF8BCE6E563A440F2ull, 0x6B17D1F2E12C4247ull };
 static u64 nist_p256_g_y[] = { 0xCBB6406837BF51F5ull, 0x2BCE33576B315ECEull,
@@ -44,6 +52,10 @@ static u64 nist_p256_p[] = { 0xFFFFFFFFFFFFFFFFull, 0x00000000FFFFFFFFull,
 				0x0000000000000000ull, 0xFFFFFFFF00000001ull };
 static u64 nist_p256_n[] = { 0xF3B9CAC2FC632551ull, 0xBCE6FAADA7179E84ull,
 				0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFF00000000ull };
+static u64 nist_p256_a[] = { 0xFFFFFFFFFFFFFFFCull, 0x00000000FFFFFFFFull,
+				0x0000000000000000ull, 0xFFFFFFFF00000001ull };
+static u64 nist_p256_b[] = { 0x3BCE3C3E27D2604Bull, 0x651D06B0CC53B0F6ull,
+				0xB3EBBD55769886BCull, 0x5AC635D8AA3A93E7ull };
 static struct ecc_curve nist_p256 = {
 	.name = "nist_256",
 	.g = {
@@ -52,7 +64,9 @@ static struct ecc_curve nist_p256 = {
 		.ndigits = 4,
 	},
 	.p = nist_p256_p,
-	.n = nist_p256_n
+	.n = nist_p256_n,
+	.a = nist_p256_a,
+	.b = nist_p256_b
 };
 
 #endif
-- 
cgit v1.2.3


From cefd769fd0192c84d638f66da202459ed8ad63ba Mon Sep 17 00:00:00 2001
From: Stafford Horne <shorne@gmail.com>
Date: Mon, 25 Jun 2018 21:45:37 +0900
Subject: crypto: skcipher - Fix -Wstringop-truncation warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As of GCC 9.0.0 the build is reporting warnings like:

    crypto/ablkcipher.c: In function ‘crypto_ablkcipher_report’:
    crypto/ablkcipher.c:374:2: warning: ‘strncpy’ specified bound 64 equals destination size [-Wstringop-truncation]
      strncpy(rblkcipher.geniv, alg->cra_ablkcipher.geniv ?: "<default>",
      ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
       sizeof(rblkcipher.geniv));
       ~~~~~~~~~~~~~~~~~~~~~~~~~

This means the strnycpy might create a non null terminated string.  Fix this by
explicitly performing '\0' termination.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Max Filippov <jcmvbkbc@gmail.com>
Cc: Eric Biggers <ebiggers3@gmail.com>
Cc: Nick Desaulniers <nick.desaulniers@gmail.com>
Signed-off-by: Stafford Horne <shorne@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ablkcipher.c | 2 ++
 crypto/blkcipher.c  | 1 +
 2 files changed, 3 insertions(+)

diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index d880a4897159..1edb5000d783 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -373,6 +373,7 @@ static int crypto_ablkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
 	strncpy(rblkcipher.type, "ablkcipher", sizeof(rblkcipher.type));
 	strncpy(rblkcipher.geniv, alg->cra_ablkcipher.geniv ?: "<default>",
 		sizeof(rblkcipher.geniv));
+	rblkcipher.geniv[sizeof(rblkcipher.geniv) - 1] = '\0';
 
 	rblkcipher.blocksize = alg->cra_blocksize;
 	rblkcipher.min_keysize = alg->cra_ablkcipher.min_keysize;
@@ -447,6 +448,7 @@ static int crypto_givcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
 	strncpy(rblkcipher.type, "givcipher", sizeof(rblkcipher.type));
 	strncpy(rblkcipher.geniv, alg->cra_ablkcipher.geniv ?: "<built-in>",
 		sizeof(rblkcipher.geniv));
+	rblkcipher.geniv[sizeof(rblkcipher.geniv) - 1] = '\0';
 
 	rblkcipher.blocksize = alg->cra_blocksize;
 	rblkcipher.min_keysize = alg->cra_ablkcipher.min_keysize;
diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index 01c0d4aa2563..dd4dcab3766a 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -512,6 +512,7 @@ static int crypto_blkcipher_report(struct sk_buff *skb, struct crypto_alg *alg)
 	strncpy(rblkcipher.type, "blkcipher", sizeof(rblkcipher.type));
 	strncpy(rblkcipher.geniv, alg->cra_blkcipher.geniv ?: "<default>",
 		sizeof(rblkcipher.geniv));
+	rblkcipher.geniv[sizeof(rblkcipher.geniv) - 1] = '\0';
 
 	rblkcipher.blocksize = alg->cra_blocksize;
 	rblkcipher.min_keysize = alg->cra_blkcipher.min_keysize;
-- 
cgit v1.2.3


From 65f9aa36ee47a2d6bf4c246c29c98d5f2842b4a6 Mon Sep 17 00:00:00 2001
From: "lionel.debieve@st.com" <lionel.debieve@st.com>
Date: Tue, 26 Jun 2018 14:52:44 +0200
Subject: crypto: stm32/cryp - Add power management support

Adding pm and pm_runtime support to STM32 CRYP.

Signed-off-by: Lionel Debieve <lionel.debieve@st.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/stm32/stm32-cryp.c | 62 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
index c5d3efc54a4f..23b0b7bd64c7 100644
--- a/drivers/crypto/stm32/stm32-cryp.c
+++ b/drivers/crypto/stm32/stm32-cryp.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
 #include <crypto/aes.h>
@@ -105,6 +106,7 @@
 #define GCM_CTR_INIT            2
 #define _walked_in              (cryp->in_walk.offset - cryp->in_sg->offset)
 #define _walked_out             (cryp->out_walk.offset - cryp->out_sg->offset)
+#define CRYP_AUTOSUSPEND_DELAY	50
 
 struct stm32_cryp_caps {
 	bool                    swap_final;
@@ -519,6 +521,8 @@ static int stm32_cryp_hw_init(struct stm32_cryp *cryp)
 	int ret;
 	u32 cfg, hw_mode;
 
+	pm_runtime_get_sync(cryp->dev);
+
 	/* Disable interrupt */
 	stm32_cryp_write(cryp, CRYP_IMSCR, 0);
 
@@ -638,6 +642,9 @@ static void stm32_cryp_finish_req(struct stm32_cryp *cryp, int err)
 		free_pages((unsigned long)buf_out, pages);
 	}
 
+	pm_runtime_mark_last_busy(cryp->dev);
+	pm_runtime_put_autosuspend(cryp->dev);
+
 	if (is_gcm(cryp) || is_ccm(cryp)) {
 		crypto_finalize_aead_request(cryp->engine, cryp->areq, err);
 		cryp->areq = NULL;
@@ -1969,6 +1976,13 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	pm_runtime_set_autosuspend_delay(dev, CRYP_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	rst = devm_reset_control_get(dev, NULL);
 	if (!IS_ERR(rst)) {
 		reset_control_assert(rst);
@@ -2008,6 +2022,8 @@ static int stm32_cryp_probe(struct platform_device *pdev)
 
 	dev_info(dev, "Initialized\n");
 
+	pm_runtime_put_sync(dev);
+
 	return 0;
 
 err_aead_algs:
@@ -2020,6 +2036,11 @@ err_engine1:
 	list_del(&cryp->list);
 	spin_unlock(&cryp_list.lock);
 
+	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+
 	clk_disable_unprepare(cryp->clk);
 
 	return ret;
@@ -2028,10 +2049,15 @@ err_engine1:
 static int stm32_cryp_remove(struct platform_device *pdev)
 {
 	struct stm32_cryp *cryp = platform_get_drvdata(pdev);
+	int ret;
 
 	if (!cryp)
 		return -ENODEV;
 
+	ret = pm_runtime_get_sync(cryp->dev);
+	if (ret < 0)
+		return ret;
+
 	crypto_unregister_aeads(aead_algs, ARRAY_SIZE(aead_algs));
 	crypto_unregister_algs(crypto_algs, ARRAY_SIZE(crypto_algs));
 
@@ -2041,16 +2067,52 @@ static int stm32_cryp_remove(struct platform_device *pdev)
 	list_del(&cryp->list);
 	spin_unlock(&cryp_list.lock);
 
+	pm_runtime_disable(cryp->dev);
+	pm_runtime_put_noidle(cryp->dev);
+
+	clk_disable_unprepare(cryp->clk);
+
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int stm32_cryp_runtime_suspend(struct device *dev)
+{
+	struct stm32_cryp *cryp = dev_get_drvdata(dev);
+
 	clk_disable_unprepare(cryp->clk);
 
 	return 0;
 }
 
+static int stm32_cryp_runtime_resume(struct device *dev)
+{
+	struct stm32_cryp *cryp = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(cryp->clk);
+	if (ret) {
+		dev_err(cryp->dev, "Failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_cryp_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(stm32_cryp_runtime_suspend,
+			   stm32_cryp_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_cryp_driver = {
 	.probe  = stm32_cryp_probe,
 	.remove = stm32_cryp_remove,
 	.driver = {
 		.name           = DRIVER_NAME,
+		.pm		= &stm32_cryp_pm_ops,
 		.of_match_table = stm32_dt_ids,
 	},
 };
-- 
cgit v1.2.3


From 8b4d566de6a5ecb332a7fe8d79731d4d6fc06d6b Mon Sep 17 00:00:00 2001
From: "lionel.debieve@st.com" <lionel.debieve@st.com>
Date: Tue, 26 Jun 2018 14:52:45 +0200
Subject: crypto: stm32/hash - Add power management support

Adding pm and pm_runtime support to STM32 HASH.

Signed-off-by: Lionel Debieve <lionel.debieve@st.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/stm32/stm32-hash.c | 71 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index cdc96f1bb917..d1d7233d7dd6 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -31,6 +31,7 @@
 #include <linux/module.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
 #include <crypto/engine.h>
@@ -121,6 +122,8 @@ enum stm32_hash_data_format {
 #define HASH_QUEUE_LENGTH		16
 #define HASH_DMA_THRESHOLD		50
 
+#define HASH_AUTOSUSPEND_DELAY		50
+
 struct stm32_hash_ctx {
 	struct crypto_engine_ctx enginectx;
 	struct stm32_hash_dev	*hdev;
@@ -814,12 +817,17 @@ static void stm32_hash_finish_req(struct ahash_request *req, int err)
 		rctx->flags |= HASH_FLAGS_ERRORS;
 	}
 
+	pm_runtime_mark_last_busy(hdev->dev);
+	pm_runtime_put_autosuspend(hdev->dev);
+
 	crypto_finalize_hash_request(hdev->engine, req, err);
 }
 
 static int stm32_hash_hw_init(struct stm32_hash_dev *hdev,
 			      struct stm32_hash_request_ctx *rctx)
 {
+	pm_runtime_get_sync(hdev->dev);
+
 	if (!(HASH_FLAGS_INIT & hdev->flags)) {
 		stm32_hash_write(hdev, HASH_CR, HASH_CR_INIT);
 		stm32_hash_write(hdev, HASH_STR, 0);
@@ -967,6 +975,8 @@ static int stm32_hash_export(struct ahash_request *req, void *out)
 	u32 *preg;
 	unsigned int i;
 
+	pm_runtime_get_sync(hdev->dev);
+
 	while (!(stm32_hash_read(hdev, HASH_SR) & HASH_SR_DATA_INPUT_READY))
 		cpu_relax();
 
@@ -982,6 +992,9 @@ static int stm32_hash_export(struct ahash_request *req, void *out)
 	for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
 		*preg++ = stm32_hash_read(hdev, HASH_CSR(i));
 
+	pm_runtime_mark_last_busy(hdev->dev);
+	pm_runtime_put_autosuspend(hdev->dev);
+
 	memcpy(out, rctx, sizeof(*rctx));
 
 	return 0;
@@ -1000,6 +1013,8 @@ static int stm32_hash_import(struct ahash_request *req, const void *in)
 
 	preg = rctx->hw_context;
 
+	pm_runtime_get_sync(hdev->dev);
+
 	stm32_hash_write(hdev, HASH_IMR, *preg++);
 	stm32_hash_write(hdev, HASH_STR, *preg++);
 	stm32_hash_write(hdev, HASH_CR, *preg);
@@ -1009,6 +1024,9 @@ static int stm32_hash_import(struct ahash_request *req, const void *in)
 	for (i = 0; i < HASH_CSR_REGISTER_NUMBER; i++)
 		stm32_hash_write(hdev, HASH_CSR(i), *preg++);
 
+	pm_runtime_mark_last_busy(hdev->dev);
+	pm_runtime_put_autosuspend(hdev->dev);
+
 	kfree(rctx->hw_context);
 
 	return 0;
@@ -1482,6 +1500,13 @@ static int stm32_hash_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	pm_runtime_set_autosuspend_delay(dev, HASH_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	hdev->rst = devm_reset_control_get(&pdev->dev, NULL);
 	if (!IS_ERR(hdev->rst)) {
 		reset_control_assert(hdev->rst);
@@ -1522,6 +1547,8 @@ static int stm32_hash_probe(struct platform_device *pdev)
 	dev_info(dev, "Init HASH done HW ver %x DMA mode %u\n",
 		 stm32_hash_read(hdev, HASH_VER), hdev->dma_mode);
 
+	pm_runtime_put_sync(dev);
+
 	return 0;
 
 err_algs:
@@ -1535,6 +1562,9 @@ err_engine:
 	if (hdev->dma_lch)
 		dma_release_channel(hdev->dma_lch);
 
+	pm_runtime_disable(dev);
+	pm_runtime_put_noidle(dev);
+
 	clk_disable_unprepare(hdev->clk);
 
 	return ret;
@@ -1543,11 +1573,16 @@ err_engine:
 static int stm32_hash_remove(struct platform_device *pdev)
 {
 	static struct stm32_hash_dev *hdev;
+	int ret;
 
 	hdev = platform_get_drvdata(pdev);
 	if (!hdev)
 		return -ENODEV;
 
+	ret = pm_runtime_get_sync(hdev->dev);
+	if (ret < 0)
+		return ret;
+
 	stm32_hash_unregister_algs(hdev);
 
 	crypto_engine_exit(hdev->engine);
@@ -1559,16 +1594,52 @@ static int stm32_hash_remove(struct platform_device *pdev)
 	if (hdev->dma_lch)
 		dma_release_channel(hdev->dma_lch);
 
+	pm_runtime_disable(hdev->dev);
+	pm_runtime_put_noidle(hdev->dev);
+
 	clk_disable_unprepare(hdev->clk);
 
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int stm32_hash_runtime_suspend(struct device *dev)
+{
+	struct stm32_hash_dev *hdev = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(hdev->clk);
+
+	return 0;
+}
+
+static int stm32_hash_runtime_resume(struct device *dev)
+{
+	struct stm32_hash_dev *hdev = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(hdev->clk);
+	if (ret) {
+		dev_err(hdev->dev, "Failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_hash_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(stm32_hash_runtime_suspend,
+			   stm32_hash_runtime_resume, NULL)
+};
+
 static struct platform_driver stm32_hash_driver = {
 	.probe		= stm32_hash_probe,
 	.remove		= stm32_hash_remove,
 	.driver		= {
 		.name	= "stm32-hash",
+		.pm = &stm32_hash_pm_ops,
 		.of_match_table	= stm32_hash_of_match,
 	}
 };
-- 
cgit v1.2.3


From 73463ade0a57d2c7f23e1dfad25d32f18c79db95 Mon Sep 17 00:00:00 2001
From: "lionel.debieve@st.com" <lionel.debieve@st.com>
Date: Tue, 26 Jun 2018 14:52:46 +0200
Subject: crypto: stm32/crc - Add power management support

Adding pm and pm_runtime support to STM32 CRC.

Signed-off-by: Lionel Debieve <lionel.debieve@st.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/stm32/stm32_crc32.c | 62 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/drivers/crypto/stm32/stm32_crc32.c b/drivers/crypto/stm32/stm32_crc32.c
index 8f09b8430893..04ba5e1399e5 100644
--- a/drivers/crypto/stm32/stm32_crc32.c
+++ b/drivers/crypto/stm32/stm32_crc32.c
@@ -8,6 +8,7 @@
 #include <linux/clk.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 
 #include <crypto/internal/hash.h>
 
@@ -32,6 +33,8 @@
 #define POLY_CRC32              0xEDB88320
 #define POLY_CRC32C             0x82F63B78
 
+#define CRC_AUTOSUSPEND_DELAY	50
+
 struct stm32_crc {
 	struct list_head list;
 	struct device    *dev;
@@ -106,6 +109,8 @@ static int stm32_crc_init(struct shash_desc *desc)
 	}
 	spin_unlock_bh(&crc_list.lock);
 
+	pm_runtime_get_sync(ctx->crc->dev);
+
 	/* Reset, set key, poly and configure in bit reverse mode */
 	writel_relaxed(bitrev32(mctx->key), ctx->crc->regs + CRC_INIT);
 	writel_relaxed(bitrev32(mctx->poly), ctx->crc->regs + CRC_POL);
@@ -115,6 +120,9 @@ static int stm32_crc_init(struct shash_desc *desc)
 	ctx->partial = readl_relaxed(ctx->crc->regs + CRC_DR);
 	ctx->crc->nb_pending_bytes = 0;
 
+	pm_runtime_mark_last_busy(ctx->crc->dev);
+	pm_runtime_put_autosuspend(ctx->crc->dev);
+
 	return 0;
 }
 
@@ -126,6 +134,8 @@ static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
 	u32 *d32;
 	unsigned int i;
 
+	pm_runtime_get_sync(crc->dev);
+
 	if (unlikely(crc->nb_pending_bytes)) {
 		while (crc->nb_pending_bytes != sizeof(u32) && length) {
 			/* Fill in pending data */
@@ -149,6 +159,9 @@ static int stm32_crc_update(struct shash_desc *desc, const u8 *d8,
 	/* Store partial result */
 	ctx->partial = readl_relaxed(crc->regs + CRC_DR);
 
+	pm_runtime_mark_last_busy(crc->dev);
+	pm_runtime_put_autosuspend(crc->dev);
+
 	/* Check for pending data (non 32 bits) */
 	length &= 3;
 	if (likely(!length))
@@ -272,6 +285,13 @@ static int stm32_crc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	pm_runtime_set_autosuspend_delay(dev, CRC_AUTOSUSPEND_DELAY);
+	pm_runtime_use_autosuspend(dev);
+
+	pm_runtime_get_noresume(dev);
+	pm_runtime_set_active(dev);
+	pm_runtime_enable(dev);
+
 	platform_set_drvdata(pdev, crc);
 
 	spin_lock(&crc_list.lock);
@@ -287,12 +307,18 @@ static int stm32_crc_probe(struct platform_device *pdev)
 
 	dev_info(dev, "Initialized\n");
 
+	pm_runtime_put_sync(dev);
+
 	return 0;
 }
 
 static int stm32_crc_remove(struct platform_device *pdev)
 {
 	struct stm32_crc *crc = platform_get_drvdata(pdev);
+	int ret = pm_runtime_get_sync(crc->dev);
+
+	if (ret < 0)
+		return ret;
 
 	spin_lock(&crc_list.lock);
 	list_del(&crc->list);
@@ -300,11 +326,46 @@ static int stm32_crc_remove(struct platform_device *pdev)
 
 	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
 
+	pm_runtime_disable(crc->dev);
+	pm_runtime_put_noidle(crc->dev);
+
 	clk_disable_unprepare(crc->clk);
 
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int stm32_crc_runtime_suspend(struct device *dev)
+{
+	struct stm32_crc *crc = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(crc->clk);
+
+	return 0;
+}
+
+static int stm32_crc_runtime_resume(struct device *dev)
+{
+	struct stm32_crc *crc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(crc->clk);
+	if (ret) {
+		dev_err(crc->dev, "Failed to prepare_enable clock\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops stm32_crc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(stm32_crc_runtime_suspend,
+			   stm32_crc_runtime_resume, NULL)
+};
+
 static const struct of_device_id stm32_dt_ids[] = {
 	{ .compatible = "st,stm32f7-crc", },
 	{},
@@ -316,6 +377,7 @@ static struct platform_driver stm32_crc_driver = {
 	.remove = stm32_crc_remove,
 	.driver = {
 		.name           = DRIVER_NAME,
+		.pm		= &stm32_crc_pm_ops,
 		.of_match_table = stm32_dt_ids,
 	},
 };
-- 
cgit v1.2.3


From e3fe0ae129622b78e710e75ecbf7aca7af5dda47 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 27 Jun 2018 08:15:31 +0200
Subject: crypto: dh - add public key verification test

According to SP800-56A section 5.6.2.1, the public key to be processed
for the DH operation shall be checked for appropriateness. The check
shall covers the full verification test in case the domain parameter Q
is provided as defined in SP800-56A section 5.6.2.3.1. If Q is not
provided, the partial check according to SP800-56A section 5.6.2.3.2 is
performed.

The full verification test requires the presence of the domain parameter
Q. Thus, the patch adds the support to handle Q. It is permissible to
not provide the Q value as part of the domain parameters. This implies
that the interface is still backwards-compatible where so far only P and
G are to be provided. However, if Q is provided, it is imported.

Without the test, the NIST ACVP testing fails. After adding this check,
the NIST ACVP testing passes. Testing without providing the Q domain
parameter has been performed to verify the interface has not changed.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/dh.c         | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++---
 crypto/dh_helper.c  | 15 +++++++++---
 include/crypto/dh.h |  4 ++++
 3 files changed, 79 insertions(+), 6 deletions(-)

diff --git a/crypto/dh.c b/crypto/dh.c
index 5659fe7f446d..8f79269db2b7 100644
--- a/crypto/dh.c
+++ b/crypto/dh.c
@@ -16,14 +16,16 @@
 #include <linux/mpi.h>
 
 struct dh_ctx {
-	MPI p;
-	MPI g;
-	MPI xa;
+	MPI p;	/* Value is guaranteed to be set. */
+	MPI q;	/* Value is optional. */
+	MPI g;	/* Value is guaranteed to be set. */
+	MPI xa;	/* Value is guaranteed to be set. */
 };
 
 static void dh_clear_ctx(struct dh_ctx *ctx)
 {
 	mpi_free(ctx->p);
+	mpi_free(ctx->q);
 	mpi_free(ctx->g);
 	mpi_free(ctx->xa);
 	memset(ctx, 0, sizeof(*ctx));
@@ -60,6 +62,12 @@ static int dh_set_params(struct dh_ctx *ctx, struct dh *params)
 	if (!ctx->p)
 		return -EINVAL;
 
+	if (params->q && params->q_size) {
+		ctx->q = mpi_read_raw_data(params->q, params->q_size);
+		if (!ctx->q)
+			return -EINVAL;
+	}
+
 	ctx->g = mpi_read_raw_data(params->g, params->g_size);
 	if (!ctx->g)
 		return -EINVAL;
@@ -93,6 +101,55 @@ err_clear_ctx:
 	return -EINVAL;
 }
 
+/*
+ * SP800-56A public key verification:
+ *
+ * * If Q is provided as part of the domain paramenters, a full validation
+ *   according to SP800-56A section 5.6.2.3.1 is performed.
+ *
+ * * If Q is not provided, a partial validation according to SP800-56A section
+ *   5.6.2.3.2 is performed.
+ */
+static int dh_is_pubkey_valid(struct dh_ctx *ctx, MPI y)
+{
+	if (unlikely(!ctx->p))
+		return -EINVAL;
+
+	/*
+	 * Step 1: Verify that 2 <= y <= p - 2.
+	 *
+	 * The upper limit check is actually y < p instead of y < p - 1
+	 * as the mpi_sub_ui function is yet missing.
+	 */
+	if (mpi_cmp_ui(y, 1) < 1 || mpi_cmp(y, ctx->p) >= 0)
+		return -EINVAL;
+
+	/* Step 2: Verify that 1 = y^q mod p */
+	if (ctx->q) {
+		MPI val = mpi_alloc(0);
+		int ret;
+
+		if (!val)
+			return -ENOMEM;
+
+		ret = mpi_powm(val, y, ctx->q, ctx->p);
+
+		if (ret) {
+			mpi_free(val);
+			return ret;
+		}
+
+		ret = mpi_cmp_ui(val, 1);
+
+		mpi_free(val);
+
+		if (ret != 0)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int dh_compute_value(struct kpp_request *req)
 {
 	struct crypto_kpp *tfm = crypto_kpp_reqtfm(req);
@@ -115,6 +172,9 @@ static int dh_compute_value(struct kpp_request *req)
 			ret = -EINVAL;
 			goto err_free_val;
 		}
+		ret = dh_is_pubkey_valid(ctx, base);
+		if (ret)
+			goto err_free_val;
 	} else {
 		base = ctx->g;
 	}
diff --git a/crypto/dh_helper.c b/crypto/dh_helper.c
index 24fdb2ecaa85..a7de3d9ce5ac 100644
--- a/crypto/dh_helper.c
+++ b/crypto/dh_helper.c
@@ -30,7 +30,7 @@ static inline const u8 *dh_unpack_data(void *dst, const void *src, size_t size)
 
 static inline unsigned int dh_data_size(const struct dh *p)
 {
-	return p->key_size + p->p_size + p->g_size;
+	return p->key_size + p->p_size + p->q_size + p->g_size;
 }
 
 unsigned int crypto_dh_key_len(const struct dh *p)
@@ -56,9 +56,11 @@ int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params)
 	ptr = dh_pack_data(ptr, &secret, sizeof(secret));
 	ptr = dh_pack_data(ptr, &params->key_size, sizeof(params->key_size));
 	ptr = dh_pack_data(ptr, &params->p_size, sizeof(params->p_size));
+	ptr = dh_pack_data(ptr, &params->q_size, sizeof(params->q_size));
 	ptr = dh_pack_data(ptr, &params->g_size, sizeof(params->g_size));
 	ptr = dh_pack_data(ptr, params->key, params->key_size);
 	ptr = dh_pack_data(ptr, params->p, params->p_size);
+	ptr = dh_pack_data(ptr, params->q, params->q_size);
 	dh_pack_data(ptr, params->g, params->g_size);
 
 	return 0;
@@ -79,6 +81,7 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params)
 
 	ptr = dh_unpack_data(&params->key_size, ptr, sizeof(params->key_size));
 	ptr = dh_unpack_data(&params->p_size, ptr, sizeof(params->p_size));
+	ptr = dh_unpack_data(&params->q_size, ptr, sizeof(params->q_size));
 	ptr = dh_unpack_data(&params->g_size, ptr, sizeof(params->g_size));
 	if (secret.len != crypto_dh_key_len(params))
 		return -EINVAL;
@@ -88,7 +91,7 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params)
 	 * some drivers assume otherwise.
 	 */
 	if (params->key_size > params->p_size ||
-	    params->g_size > params->p_size)
+	    params->g_size > params->p_size || params->q_size > params->p_size)
 		return -EINVAL;
 
 	/* Don't allocate memory. Set pointers to data within
@@ -96,7 +99,9 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params)
 	 */
 	params->key = (void *)ptr;
 	params->p = (void *)(ptr + params->key_size);
-	params->g = (void *)(ptr + params->key_size + params->p_size);
+	params->q = (void *)(ptr + params->key_size + params->p_size);
+	params->g = (void *)(ptr + params->key_size + params->p_size +
+			     params->q_size);
 
 	/*
 	 * Don't permit 'p' to be 0.  It's not a prime number, and it's subject
@@ -106,6 +111,10 @@ int crypto_dh_decode_key(const char *buf, unsigned int len, struct dh *params)
 	if (memchr_inv(params->p, 0, params->p_size) == NULL)
 		return -EINVAL;
 
+	/* It is permissible to not provide Q. */
+	if (params->q_size == 0)
+		params->q = NULL;
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_dh_decode_key);
diff --git a/include/crypto/dh.h b/include/crypto/dh.h
index 71e1bb24d79f..7e0dad94cb2b 100644
--- a/include/crypto/dh.h
+++ b/include/crypto/dh.h
@@ -29,17 +29,21 @@
  *
  * @key:	Private DH key
  * @p:		Diffie-Hellman parameter P
+ * @q:		Diffie-Hellman parameter Q
  * @g:		Diffie-Hellman generator G
  * @key_size:	Size of the private DH key
  * @p_size:	Size of DH parameter P
+ * @q_size:	Size of DH parameter Q
  * @g_size:	Size of DH generator G
  */
 struct dh {
 	void *key;
 	void *p;
+	void *q;
 	void *g;
 	unsigned int key_size;
 	unsigned int p_size;
+	unsigned int q_size;
 	unsigned int g_size;
 };
 
-- 
cgit v1.2.3


From 043ecc635f70c38d9fed1fe1ea20009cf45b12d6 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 28 Jun 2018 17:15:31 +0200
Subject: crypto: inside-secure - move the firmware to a better location

This patch moves the firmware loaded by the Inside Secure SafeXcel
driver from /lib/firmware/ to /lib/firmware/inside-secure/eip197b/. This
prepares the driver for future patches which will support other
revisions of the EIP197 crypto engine as they'll have their own
firmwares.

To keep the compatibility of what was done, the old path is still
supported as a fallback for the EIP197b (currently the only one
supported by the driver that loads a firmware).

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index c39d2d7c9917..a04d39231aaf 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -132,18 +132,24 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
 {
 	const char *fw_name[] = {"ifpp.bin", "ipue.bin"};
 	const struct firmware *fw[FW_NB];
+	char fw_path[31];
 	int i, j, ret = 0;
 	u32 val;
 
 	for (i = 0; i < FW_NB; i++) {
-		ret = request_firmware(&fw[i], fw_name[i], priv->dev);
+		snprintf(fw_path, 31, "inside-secure/eip197b/%s", fw_name[i]);
+		ret = request_firmware(&fw[i], fw_path, priv->dev);
 		if (ret) {
-			dev_err(priv->dev,
-				"Failed to request firmware %s (%d)\n",
-				fw_name[i], ret);
-			goto release_fw;
+			/* Fallback to the old firmware location. */
+			ret = request_firmware(&fw[i], fw_name[i], priv->dev);
+			if (ret) {
+				dev_err(priv->dev,
+					"Failed to request firmware %s (%d)\n",
+					fw_name[i], ret);
+				goto release_fw;
+			}
 		}
-	 }
+	}
 
 	/* Clear the scratchpad memory */
 	val = readl(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
-- 
cgit v1.2.3


From 7d8f52a30d5a70673415a58b6766e1ae505dd321 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 28 Jun 2018 17:15:32 +0200
Subject: crypto: inside-secure - use precise compatibles

At first we used two compatibles in the SafeXcel driver, named after the
engine revision: eip97 and eip197. However this family of engines has
more precise versions and in fact we're supporting the eip97ies and
eip197b. More versions will be supported in the future, such as the
eip197d, and we'll need to differentiate them.

This patch fixes the compatibles used in the driver, to now use precise
ones. The two historical compatibles are kept for backward
compatibility.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        | 24 +++++++++++++++++-------
 drivers/crypto/inside-secure/safexcel.h        |  4 ++--
 drivers/crypto/inside-secure/safexcel_cipher.c | 16 ++++++++--------
 drivers/crypto/inside-secure/safexcel_hash.c   |  8 ++++----
 4 files changed, 31 insertions(+), 21 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index a04d39231aaf..c28ab137d721 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -294,7 +294,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	writel(EIP197_DxE_THR_CTRL_RESET_PE,
 	       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B) {
 		/* Reset HIA input interface arbiter */
 		writel(EIP197_HIA_RA_PE_CTRL_RESET,
 		       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL);
@@ -317,7 +317,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	writel(EIP197_PE_IN_xBUF_THRES_MIN(6) | EIP197_PE_IN_xBUF_THRES_MAX(7),
 	       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES);
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B) {
 		/* enable HIA input interface arbiter and rings */
 		writel(EIP197_HIA_RA_PE_CTRL_EN |
 		       GENMASK(priv->config.rings - 1, 0),
@@ -343,7 +343,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	/* FIXME: instability issues can occur for EIP97 but disabling it impact
 	 * performances.
 	 */
-	if (priv->version == EIP197)
+	if (priv->version == EIP197B)
 		val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
 	writel(val, EIP197_HIA_DSE(priv) + EIP197_HIA_DSE_CFG);
 
@@ -425,7 +425,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	/* Clear any HIA interrupt */
 	writel(GENMASK(30, 20), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B) {
 		eip197_trc_cache_init(priv);
 
 		ret = eip197_load_firmwares(priv);
@@ -879,7 +879,7 @@ static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
 {
 	struct safexcel_register_offsets *offsets = &priv->offsets;
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B) {
 		offsets->hia_aic	= EIP197_HIA_AIC_BASE;
 		offsets->hia_aic_g	= EIP197_HIA_AIC_G_BASE;
 		offsets->hia_aic_r	= EIP197_HIA_AIC_R_BASE;
@@ -1063,12 +1063,22 @@ static int safexcel_remove(struct platform_device *pdev)
 
 static const struct of_device_id safexcel_of_match_table[] = {
 	{
+		.compatible = "inside-secure,safexcel-eip97ies",
+		.data = (void *)EIP97IES,
+	},
+	{
+		.compatible = "inside-secure,safexcel-eip197b",
+		.data = (void *)EIP197B,
+	},
+	{
+		/* Deprecated. Kept for backward compatibility. */
 		.compatible = "inside-secure,safexcel-eip97",
-		.data = (void *)EIP97,
+		.data = (void *)EIP97IES,
 	},
 	{
+		/* Deprecated. Kept for backward compatibility. */
 		.compatible = "inside-secure,safexcel-eip197",
-		.data = (void *)EIP197,
+		.data = (void *)EIP197B,
 	},
 	{},
 };
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 5d6b3b705d0c..6e6bdad6a6f5 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -529,8 +529,8 @@ struct safexcel_work_data {
 };
 
 enum safexcel_eip_version {
-	EIP97,
-	EIP197,
+	EIP97IES,
+	EIP197B,
 };
 
 struct safexcel_register_offsets {
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index ca4bc2d28d2a..845546129d09 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -145,7 +145,7 @@ static int safexcel_skcipher_aes_setkey(struct crypto_skcipher *ctfm,
 		return ret;
 	}
 
-	if (priv->version == EIP197 && ctx->base.ctxr_dma) {
+	if (priv->version == EIP197B && ctx->base.ctxr_dma) {
 		for (i = 0; i < len / sizeof(u32); i++) {
 			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
 				ctx->base.needs_inv = true;
@@ -179,7 +179,7 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 		goto badkey;
 
 	/* Encryption key */
-	if (priv->version == EIP197 && ctx->base.ctxr_dma &&
+	if (priv->version == EIP197B && ctx->base.ctxr_dma &&
 	    memcmp(ctx->key, keys.enckey, keys.enckeylen))
 		ctx->base.needs_inv = true;
 
@@ -218,7 +218,7 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 	crypto_aead_set_flags(ctfm, crypto_aead_get_flags(ctfm) &
 				    CRYPTO_TFM_RES_MASK);
 
-	if (priv->version == EIP197 && ctx->base.ctxr_dma &&
+	if (priv->version == EIP197B && ctx->base.ctxr_dma &&
 	    (memcmp(ctx->ipad, istate.state, ctx->state_sz) ||
 	     memcmp(ctx->opad, ostate.state, ctx->state_sz)))
 		ctx->base.needs_inv = true;
@@ -612,7 +612,7 @@ static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	BUG_ON(priv->version == EIP97 && sreq->needs_inv);
+	BUG_ON(priv->version == EIP97IES && sreq->needs_inv);
 
 	if (sreq->needs_inv)
 		ret = safexcel_cipher_send_inv(async, ring, request, commands,
@@ -635,7 +635,7 @@ static int safexcel_aead_send(struct crypto_async_request *async, int ring,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	BUG_ON(priv->version == EIP97 && sreq->needs_inv);
+	BUG_ON(priv->version == EIP97IES && sreq->needs_inv);
 
 	if (sreq->needs_inv)
 		ret = safexcel_cipher_send_inv(async, ring, request, commands,
@@ -725,7 +725,7 @@ static int safexcel_aes(struct crypto_async_request *base,
 	ctx->mode = mode;
 
 	if (ctx->base.ctxr) {
-		if (priv->version == EIP197 && ctx->base.needs_inv) {
+		if (priv->version == EIP197B && ctx->base.needs_inv) {
 			sreq->needs_inv = true;
 			ctx->base.needs_inv = false;
 		}
@@ -802,7 +802,7 @@ static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
 	if (safexcel_cipher_cra_exit(tfm))
 		return;
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B) {
 		ret = safexcel_skcipher_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "skcipher: invalidation error %d\n",
@@ -822,7 +822,7 @@ static void safexcel_aead_cra_exit(struct crypto_tfm *tfm)
 	if (safexcel_cipher_cra_exit(tfm))
 		return;
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B) {
 		ret = safexcel_aead_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "aead: invalidation error %d\n",
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 188ba0734337..dc7239945dc0 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -442,7 +442,7 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	int err;
 
-	BUG_ON(priv->version == EIP97 && req->needs_inv);
+	BUG_ON(priv->version == EIP97IES && req->needs_inv);
 
 	if (req->needs_inv) {
 		req->needs_inv = false;
@@ -575,7 +575,7 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 	req->needs_inv = false;
 
 	if (ctx->base.ctxr) {
-		if (priv->version == EIP197 && !ctx->base.needs_inv &&
+		if (priv->version == EIP197B && !ctx->base.needs_inv &&
 		    (req->processed[0] || req->processed[1]) &&
 		    req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
 			/* We're still setting needs_inv here, even though it is
@@ -784,7 +784,7 @@ static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
 	if (!ctx->base.ctxr)
 		return;
 
-	if (priv->version == EIP197) {
+	if (priv->version == EIP197B) {
 		ret = safexcel_ahash_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "hash: invalidation error %d\n", ret);
@@ -1004,7 +1004,7 @@ static int safexcel_hmac_alg_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (ret)
 		return ret;
 
-	if (priv->version == EIP197 && ctx->base.ctxr) {
+	if (priv->version == EIP197B && ctx->base.ctxr) {
 		for (i = 0; i < state_sz / sizeof(u32); i++) {
 			if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
 			    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
-- 
cgit v1.2.3


From bfda74ad6f507e19923c8870695b25d4247b2727 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 28 Jun 2018 17:15:33 +0200
Subject: Documentation/bindings: crypto: inside-secure: update the compatibles

The compatibles were updated in the Inside Secure SafeXcel cryptographic
driver, as the ones previously used were not specific enough. The old
compatibles are still supported by the driver for backward
compatibility.

This patch updates the documentation accordingly.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 .../devicetree/bindings/crypto/inside-secure-safexcel.txt  | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
index 5dba55cdfa63..dc8678db52fa 100644
--- a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
+++ b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
@@ -1,8 +1,8 @@
 Inside Secure SafeXcel cryptographic engine
 
 Required properties:
-- compatible: Should be "inside-secure,safexcel-eip197" or
-              "inside-secure,safexcel-eip97".
+- compatible: Should be "inside-secure,safexcel-eip197b" or
+              "inside-secure,safexcel-eip97ies".
 - reg: Base physical address of the engine and length of memory mapped region.
 - interrupts: Interrupt numbers for the rings and engine.
 - interrupt-names: Should be "ring0", "ring1", "ring2", "ring3", "eip", "mem".
@@ -14,10 +14,18 @@ Optional properties:
                name must be "core" for the first clock and "reg" for
                the second one.
 
+Backward compatibility:
+Two compatibles are kept for backward compatibility, but shouldn't be used for
+new submissions:
+- "inside-secure,safexcel-eip197" is equivalent to
+  "inside-secure,safexcel-eip197b".
+- "inside-secure,safexcel-eip97" is equivalent to
+  "inside-secure,safexcel-eip97ies".
+
 Example:
 
 	crypto: crypto@800000 {
-		compatible = "inside-secure,safexcel-eip197";
+		compatible = "inside-secure,safexcel-eip197b";
 		reg = <0x800000 0x200000>;
 		interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>,
 			     <GIC_SPI 54 IRQ_TYPE_LEVEL_HIGH>,
-- 
cgit v1.2.3


From 998d2abb0cb343c419c63898a414084ac6c17100 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 28 Jun 2018 17:15:34 +0200
Subject: crypto: inside-secure - filter out the algorithms by engine

EIP engines do not support the same set of algorithms. So far the
supported engines in the Inside Secure SafeXcel driver support the same
set of algorithms, but that won't be true for all engines. This patch
adds an 'engines' field in the algorithm definitions so that they only
are registered when using a compatible cryptographic engine.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        |  9 +++++++++
 drivers/crypto/inside-secure/safexcel.h        |  5 +++--
 drivers/crypto/inside-secure/safexcel_cipher.c |  7 +++++++
 drivers/crypto/inside-secure/safexcel_hash.c   | 10 ++++++++++
 4 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index c28ab137d721..b2749ff933c8 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -817,6 +817,9 @@ static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
 	for (i = 0; i < ARRAY_SIZE(safexcel_algs); i++) {
 		safexcel_algs[i]->priv = priv;
 
+		if (!(safexcel_algs[i]->engines & priv->version))
+			continue;
+
 		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			ret = crypto_register_skcipher(&safexcel_algs[i]->alg.skcipher);
 		else if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_AEAD)
@@ -832,6 +835,9 @@ static int safexcel_register_algorithms(struct safexcel_crypto_priv *priv)
 
 fail:
 	for (j = 0; j < i; j++) {
+		if (!(safexcel_algs[j]->engines & priv->version))
+			continue;
+
 		if (safexcel_algs[j]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			crypto_unregister_skcipher(&safexcel_algs[j]->alg.skcipher);
 		else if (safexcel_algs[j]->type == SAFEXCEL_ALG_TYPE_AEAD)
@@ -848,6 +854,9 @@ static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(safexcel_algs); i++) {
+		if (!(safexcel_algs[i]->engines & priv->version))
+			continue;
+
 		if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_SKCIPHER)
 			crypto_unregister_skcipher(&safexcel_algs[i]->alg.skcipher);
 		else if (safexcel_algs[i]->type == SAFEXCEL_ALG_TYPE_AEAD)
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 6e6bdad6a6f5..b79cb36b3772 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -529,8 +529,8 @@ struct safexcel_work_data {
 };
 
 enum safexcel_eip_version {
-	EIP97IES,
-	EIP197B,
+	EIP97IES = BIT(0),
+	EIP197B  = BIT(1),
 };
 
 struct safexcel_register_offsets {
@@ -624,6 +624,7 @@ struct safexcel_ahash_export_state {
 struct safexcel_alg_template {
 	struct safexcel_crypto_priv *priv;
 	enum safexcel_alg_type type;
+	u32 engines;
 	union {
 		struct skcipher_alg skcipher;
 		struct aead_alg aead;
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 845546129d09..bf3de334c580 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -835,6 +835,7 @@ static void safexcel_aead_cra_exit(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_ecb_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B,
 	.alg.skcipher = {
 		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_ecb_aes_encrypt,
@@ -871,6 +872,7 @@ static int safexcel_cbc_aes_decrypt(struct skcipher_request *req)
 
 struct safexcel_alg_template safexcel_alg_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B,
 	.alg.skcipher = {
 		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_cbc_aes_encrypt,
@@ -940,6 +942,7 @@ static int safexcel_aead_sha1_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -974,6 +977,7 @@ static int safexcel_aead_sha256_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -1008,6 +1012,7 @@ static int safexcel_aead_sha224_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -1042,6 +1047,7 @@ static int safexcel_aead_sha512_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -1076,6 +1082,7 @@ static int safexcel_aead_sha384_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
+	.engines = EIP97IES | EIP197B,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index dc7239945dc0..66edc1f388f1 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -796,6 +796,7 @@ static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_sha1 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_sha1_init,
 		.update = safexcel_ahash_update,
@@ -1029,6 +1030,7 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 struct safexcel_alg_template safexcel_alg_hmac_sha1 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha1_init,
 		.update = safexcel_ahash_update,
@@ -1092,6 +1094,7 @@ static int safexcel_sha256_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha256 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_sha256_init,
 		.update = safexcel_ahash_update,
@@ -1154,6 +1157,7 @@ static int safexcel_sha224_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha224 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_sha224_init,
 		.update = safexcel_ahash_update,
@@ -1209,6 +1213,7 @@ static int safexcel_hmac_sha224_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha224 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha224_init,
 		.update = safexcel_ahash_update,
@@ -1265,6 +1270,7 @@ static int safexcel_hmac_sha256_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha256 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha256_init,
 		.update = safexcel_ahash_update,
@@ -1336,6 +1342,7 @@ static int safexcel_sha512_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha512 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_sha512_init,
 		.update = safexcel_ahash_update,
@@ -1406,6 +1413,7 @@ static int safexcel_sha384_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha384 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_sha384_init,
 		.update = safexcel_ahash_update,
@@ -1461,6 +1469,7 @@ static int safexcel_hmac_sha512_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha512 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha512_init,
 		.update = safexcel_ahash_update,
@@ -1517,6 +1526,7 @@ static int safexcel_hmac_sha384_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha384 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha384_init,
 		.update = safexcel_ahash_update,
-- 
cgit v1.2.3


From 53c83e915ce8b2fdd7c4e143966a105c96454647 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 28 Jun 2018 17:15:35 +0200
Subject: crypto: inside-secure - add an invalidation flag

Add a flags field in the private structure, and a first flag for engines
needing context invalidation (currently only the eip197b). The
invalidation is needed when the engine includes a TRC cache, which will
also be true for the upcoming addition of the eip197d engine.

Suggested-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        |  3 +++
 drivers/crypto/inside-secure/safexcel.h        |  5 +++++
 drivers/crypto/inside-secure/safexcel_cipher.c | 16 ++++++++--------
 drivers/crypto/inside-secure/safexcel_hash.c   |  8 ++++----
 4 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index b2749ff933c8..579e7ae2cb14 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -927,6 +927,9 @@ static int safexcel_probe(struct platform_device *pdev)
 	priv->dev = dev;
 	priv->version = (enum safexcel_eip_version)of_device_get_match_data(dev);
 
+	if (priv->version == EIP197B)
+		priv->flags |= EIP197_TRC_CACHE;
+
 	safexcel_init_register_offsets(priv);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index b79cb36b3772..f62111eba30d 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -546,6 +546,10 @@ struct safexcel_register_offsets {
 	u32 pe;
 };
 
+enum safexcel_flags {
+	EIP197_TRC_CACHE = BIT(0),
+};
+
 struct safexcel_crypto_priv {
 	void __iomem *base;
 	struct device *dev;
@@ -555,6 +559,7 @@ struct safexcel_crypto_priv {
 
 	enum safexcel_eip_version version;
 	struct safexcel_register_offsets offsets;
+	u32 flags;
 
 	/* context DMA pool */
 	struct dma_pool *context_pool;
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index bf3de334c580..566c97223d67 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -145,7 +145,7 @@ static int safexcel_skcipher_aes_setkey(struct crypto_skcipher *ctfm,
 		return ret;
 	}
 
-	if (priv->version == EIP197B && ctx->base.ctxr_dma) {
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma) {
 		for (i = 0; i < len / sizeof(u32); i++) {
 			if (ctx->key[i] != cpu_to_le32(aes.key_enc[i])) {
 				ctx->base.needs_inv = true;
@@ -179,7 +179,7 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 		goto badkey;
 
 	/* Encryption key */
-	if (priv->version == EIP197B && ctx->base.ctxr_dma &&
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma &&
 	    memcmp(ctx->key, keys.enckey, keys.enckeylen))
 		ctx->base.needs_inv = true;
 
@@ -218,7 +218,7 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 	crypto_aead_set_flags(ctfm, crypto_aead_get_flags(ctfm) &
 				    CRYPTO_TFM_RES_MASK);
 
-	if (priv->version == EIP197B && ctx->base.ctxr_dma &&
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr_dma &&
 	    (memcmp(ctx->ipad, istate.state, ctx->state_sz) ||
 	     memcmp(ctx->opad, ostate.state, ctx->state_sz)))
 		ctx->base.needs_inv = true;
@@ -612,7 +612,7 @@ static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	BUG_ON(priv->version == EIP97IES && sreq->needs_inv);
+	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && sreq->needs_inv);
 
 	if (sreq->needs_inv)
 		ret = safexcel_cipher_send_inv(async, ring, request, commands,
@@ -635,7 +635,7 @@ static int safexcel_aead_send(struct crypto_async_request *async, int ring,
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	BUG_ON(priv->version == EIP97IES && sreq->needs_inv);
+	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && sreq->needs_inv);
 
 	if (sreq->needs_inv)
 		ret = safexcel_cipher_send_inv(async, ring, request, commands,
@@ -725,7 +725,7 @@ static int safexcel_aes(struct crypto_async_request *base,
 	ctx->mode = mode;
 
 	if (ctx->base.ctxr) {
-		if (priv->version == EIP197B && ctx->base.needs_inv) {
+		if (priv->flags & EIP197_TRC_CACHE && ctx->base.needs_inv) {
 			sreq->needs_inv = true;
 			ctx->base.needs_inv = false;
 		}
@@ -802,7 +802,7 @@ static void safexcel_skcipher_cra_exit(struct crypto_tfm *tfm)
 	if (safexcel_cipher_cra_exit(tfm))
 		return;
 
-	if (priv->version == EIP197B) {
+	if (priv->flags & EIP197_TRC_CACHE) {
 		ret = safexcel_skcipher_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "skcipher: invalidation error %d\n",
@@ -822,7 +822,7 @@ static void safexcel_aead_cra_exit(struct crypto_tfm *tfm)
 	if (safexcel_cipher_cra_exit(tfm))
 		return;
 
-	if (priv->version == EIP197B) {
+	if (priv->flags & EIP197_TRC_CACHE) {
 		ret = safexcel_aead_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "aead: invalidation error %d\n",
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 66edc1f388f1..94841df4b6bd 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -442,7 +442,7 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	int err;
 
-	BUG_ON(priv->version == EIP97IES && req->needs_inv);
+	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && req->needs_inv);
 
 	if (req->needs_inv) {
 		req->needs_inv = false;
@@ -575,7 +575,7 @@ static int safexcel_ahash_enqueue(struct ahash_request *areq)
 	req->needs_inv = false;
 
 	if (ctx->base.ctxr) {
-		if (priv->version == EIP197B && !ctx->base.needs_inv &&
+		if (priv->flags & EIP197_TRC_CACHE && !ctx->base.needs_inv &&
 		    (req->processed[0] || req->processed[1]) &&
 		    req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED)
 			/* We're still setting needs_inv here, even though it is
@@ -784,7 +784,7 @@ static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
 	if (!ctx->base.ctxr)
 		return;
 
-	if (priv->version == EIP197B) {
+	if (priv->flags & EIP197_TRC_CACHE) {
 		ret = safexcel_ahash_exit_inv(tfm);
 		if (ret)
 			dev_warn(priv->dev, "hash: invalidation error %d\n", ret);
@@ -1005,7 +1005,7 @@ static int safexcel_hmac_alg_setkey(struct crypto_ahash *tfm, const u8 *key,
 	if (ret)
 		return ret;
 
-	if (priv->version == EIP197B && ctx->base.ctxr) {
+	if (priv->flags & EIP197_TRC_CACHE && ctx->base.ctxr) {
 		for (i = 0; i < state_sz / sizeof(u32); i++) {
 			if (ctx->ipad[i] != le32_to_cpu(istate.state[i]) ||
 			    ctx->opad[i] != le32_to_cpu(ostate.state[i])) {
-- 
cgit v1.2.3


From 18e0e95b82e4440eaf4179c36aa5164b9bd8323d Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:15:36 +0200
Subject: crypto: inside-secure - dynamic ring configuration allocation

The Inside Secure SafeXcel driver currently uses 4 rings, but the
eip197d engines has 8 of them. This patch updates the driver so that
rings are allocated dynamically based on the number of available rings
supported by a given engine.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c      |  7 +++
 drivers/crypto/inside-secure/safexcel.h      | 68 ++++++++++++++--------------
 drivers/crypto/inside-secure/safexcel_ring.c | 10 ++--
 3 files changed, 47 insertions(+), 38 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 579e7ae2cb14..baf8320d9c84 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -981,6 +981,13 @@ static int safexcel_probe(struct platform_device *pdev)
 
 	safexcel_configure(priv);
 
+	priv->ring = devm_kzalloc(dev, priv->config.rings * sizeof(*priv->ring),
+				  GFP_KERNEL);
+	if (!priv->ring) {
+		ret = -ENOMEM;
+		goto err_reg_clk;
+	}
+
 	for (i = 0; i < priv->config.rings; i++) {
 		char irq_name[6] = {0}; /* "ringX\0" */
 		char wq_name[9] = {0}; /* "wq_ringX\0" */
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index f62111eba30d..f370f055fd80 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -487,7 +487,7 @@ enum eip197_fw {
 	FW_NB
 };
 
-struct safexcel_ring {
+struct safexcel_desc_ring {
 	void *base;
 	void *base_end;
 	dma_addr_t base_dma;
@@ -528,6 +528,35 @@ struct safexcel_work_data {
 	int ring;
 };
 
+struct safexcel_ring {
+	spinlock_t lock;
+	spinlock_t egress_lock;
+
+	struct list_head list;
+	struct workqueue_struct *workqueue;
+	struct safexcel_work_data work_data;
+
+	/* command/result rings */
+	struct safexcel_desc_ring cdr;
+	struct safexcel_desc_ring rdr;
+
+	/* queue */
+	struct crypto_queue queue;
+	spinlock_t queue_lock;
+
+	/* Number of requests in the engine. */
+	int requests;
+
+	/* The ring is currently handling at least one request */
+	bool busy;
+
+	/* Store for current requests when bailing out of the dequeueing
+	 * function when no enough resources are available.
+	 */
+	struct crypto_async_request *req;
+	struct crypto_async_request *backlog;
+};
+
 enum safexcel_eip_version {
 	EIP97IES = BIT(0),
 	EIP197B  = BIT(1),
@@ -566,34 +595,7 @@ struct safexcel_crypto_priv {
 
 	atomic_t ring_used;
 
-	struct {
-		spinlock_t lock;
-		spinlock_t egress_lock;
-
-		struct list_head list;
-		struct workqueue_struct *workqueue;
-		struct safexcel_work_data work_data;
-
-		/* command/result rings */
-		struct safexcel_ring cdr;
-		struct safexcel_ring rdr;
-
-		/* queue */
-		struct crypto_queue queue;
-		spinlock_t queue_lock;
-
-		/* Number of requests in the engine. */
-		int requests;
-
-		/* The ring is currently handling at least one request */
-		bool busy;
-
-		/* Store for current requests when bailing out of the dequeueing
-		 * function when no enough resources are available.
-		 */
-		struct crypto_async_request *req;
-		struct crypto_async_request *backlog;
-	} ring[EIP197_MAX_RINGS];
+	struct safexcel_ring *ring;
 };
 
 struct safexcel_context {
@@ -651,13 +653,13 @@ int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      dma_addr_t ctxr_dma, int ring,
 			      struct safexcel_request *request);
 int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
-				   struct safexcel_ring *cdr,
-				   struct safexcel_ring *rdr);
+				   struct safexcel_desc_ring *cdr,
+				   struct safexcel_desc_ring *rdr);
 int safexcel_select_ring(struct safexcel_crypto_priv *priv);
 void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
-			      struct safexcel_ring *ring);
+			      struct safexcel_desc_ring *ring);
 void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
-				 struct safexcel_ring *ring);
+				 struct safexcel_desc_ring *ring);
 struct safexcel_command_desc *safexcel_add_cdesc(struct safexcel_crypto_priv *priv,
 						 int ring_id,
 						 bool first, bool last,
diff --git a/drivers/crypto/inside-secure/safexcel_ring.c b/drivers/crypto/inside-secure/safexcel_ring.c
index c9d2a8716b5b..cfd843b834f1 100644
--- a/drivers/crypto/inside-secure/safexcel_ring.c
+++ b/drivers/crypto/inside-secure/safexcel_ring.c
@@ -14,8 +14,8 @@
 #include "safexcel.h"
 
 int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
-				   struct safexcel_ring *cdr,
-				   struct safexcel_ring *rdr)
+				   struct safexcel_desc_ring *cdr,
+				   struct safexcel_desc_ring *rdr)
 {
 	cdr->offset = sizeof(u32) * priv->config.cd_offset;
 	cdr->base = dmam_alloc_coherent(priv->dev,
@@ -46,7 +46,7 @@ inline int safexcel_select_ring(struct safexcel_crypto_priv *priv)
 }
 
 static void *safexcel_ring_next_wptr(struct safexcel_crypto_priv *priv,
-				     struct safexcel_ring *ring)
+				     struct safexcel_desc_ring *ring)
 {
 	void *ptr = ring->write;
 
@@ -62,7 +62,7 @@ static void *safexcel_ring_next_wptr(struct safexcel_crypto_priv *priv,
 }
 
 void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
-			      struct safexcel_ring *ring)
+			      struct safexcel_desc_ring *ring)
 {
 	void *ptr = ring->read;
 
@@ -78,7 +78,7 @@ void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
 }
 
 void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
-				 struct safexcel_ring *ring)
+				 struct safexcel_desc_ring *ring)
 {
 	if (!ring->nr)
 		return;
-- 
cgit v1.2.3


From 367571e43cfee4a8a6de11a53bba147f46221f84 Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:15:37 +0200
Subject: crypto: inside-secure - add multiple processing engine support

So far a single processing engine (PE) was configured and used in the
Inside Secure SafeXcel cryptographic engine driver. Some versions have
more than a single PE. This patch rework the driver's initialization to
take this into account and to allow configuring more than one PE.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
[Antoine: some reworks and commit message.]
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c | 224 ++++++++++++++++++--------------
 drivers/crypto/inside-secure/safexcel.h |  44 ++++---
 2 files changed, 150 insertions(+), 118 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index baf8320d9c84..eefa6221533b 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -98,7 +98,7 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 }
 
 static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
-				  const struct firmware *fw, u32 ctrl,
+				  const struct firmware *fw, int pe, u32 ctrl,
 				  u32 prog_en)
 {
 	const u32 *data = (const u32 *)fw->data;
@@ -112,7 +112,7 @@ static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
 	       EIP197_PE(priv) + ctrl);
 
 	/* Enable access to the program memory */
-	writel(prog_en, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL);
+	writel(prog_en, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL(pe));
 
 	/* Write the firmware */
 	for (i = 0; i < fw->size / sizeof(u32); i++)
@@ -120,7 +120,7 @@ static void eip197_write_firmware(struct safexcel_crypto_priv *priv,
 		       priv->base + EIP197_CLASSIFICATION_RAMS + i * sizeof(u32));
 
 	/* Disable access to the program memory */
-	writel(0, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL);
+	writel(0, EIP197_PE(priv) + EIP197_PE_ICE_RAM_CTRL(pe));
 
 	/* Release engine from reset */
 	val = readl(EIP197_PE(priv) + ctrl);
@@ -133,7 +133,7 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
 	const char *fw_name[] = {"ifpp.bin", "ipue.bin"};
 	const struct firmware *fw[FW_NB];
 	char fw_path[31];
-	int i, j, ret = 0;
+	int i, j, ret = 0, pe;
 	u32 val;
 
 	for (i = 0; i < FW_NB; i++) {
@@ -151,22 +151,26 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
 		}
 	}
 
-	/* Clear the scratchpad memory */
-	val = readl(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
-	val |= EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_TIMER |
-	       EIP197_PE_ICE_SCRATCH_CTRL_TIMER_EN |
-	       EIP197_PE_ICE_SCRATCH_CTRL_SCRATCH_ACCESS |
-	       EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
-	writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL);
-
-	memset_io(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM, 0,
-		  EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
-
-	eip197_write_firmware(priv, fw[FW_IFPP], EIP197_PE_ICE_FPP_CTRL,
-			      EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
-
-	eip197_write_firmware(priv, fw[FW_IPUE], EIP197_PE_ICE_PUE_CTRL,
-			      EIP197_PE_ICE_RAM_CTRL_PUE_PROG_EN);
+	for (pe = 0; pe < priv->config.pes; pe++) {
+		/* Clear the scratchpad memory */
+		val = readl(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL(pe));
+		val |= EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_TIMER |
+		       EIP197_PE_ICE_SCRATCH_CTRL_TIMER_EN |
+		       EIP197_PE_ICE_SCRATCH_CTRL_SCRATCH_ACCESS |
+		       EIP197_PE_ICE_SCRATCH_CTRL_CHANGE_ACCESS;
+		writel(val, EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_CTRL(pe));
+
+		memset_io(EIP197_PE(priv) + EIP197_PE_ICE_SCRATCH_RAM(pe), 0,
+			  EIP197_NUM_OF_SCRATCH_BLOCKS * sizeof(u32));
+
+		eip197_write_firmware(priv, fw[FW_IFPP], pe,
+				      EIP197_PE_ICE_FPP_CTRL(pe),
+				      EIP197_PE_ICE_RAM_CTRL_FPP_PROG_EN);
+
+		eip197_write_firmware(priv, fw[FW_IPUE], pe,
+				      EIP197_PE_ICE_PUE_CTRL(pe),
+				      EIP197_PE_ICE_RAM_CTRL_PUE_PROG_EN);
+	}
 
 release_fw:
 	for (j = 0; j < i; j++)
@@ -262,7 +266,7 @@ static int safexcel_hw_setup_rdesc_rings(struct safexcel_crypto_priv *priv)
 static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 {
 	u32 version, val;
-	int i, ret;
+	int i, ret, pe;
 
 	/* Determine endianess and configure byte swap */
 	version = readl(EIP197_HIA_AIC(priv) + EIP197_HIA_VERSION);
@@ -288,83 +292,92 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	/* Clear any pending interrupt */
 	writel(GENMASK(31, 0), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
-	/* Data Fetch Engine configuration */
-
-	/* Reset all DFE threads */
-	writel(EIP197_DxE_THR_CTRL_RESET_PE,
-	       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
-
-	if (priv->version == EIP197B) {
-		/* Reset HIA input interface arbiter */
-		writel(EIP197_HIA_RA_PE_CTRL_RESET,
-		       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL);
-	}
+	/* Processing Engine configuration */
+	for (pe = 0; pe < priv->config.pes; pe++) {
+		/* Data Fetch Engine configuration */
 
-	/* DMA transfer size to use */
-	val = EIP197_HIA_DFE_CFG_DIS_DEBUG;
-	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(6) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(9);
-	val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(6) | EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
-	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
-	val |= EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(RD_CACHE_3BITS);
-	writel(val, EIP197_HIA_DFE(priv) + EIP197_HIA_DFE_CFG);
+		/* Reset all DFE threads */
+		writel(EIP197_DxE_THR_CTRL_RESET_PE,
+		       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
 
-	/* Leave the DFE threads reset state */
-	writel(0, EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
+		if (priv->version == EIP197B) {
+			/* Reset HIA input interface arbiter */
+			writel(EIP197_HIA_RA_PE_CTRL_RESET,
+			       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL(pe));
+		}
 
-	/* Configure the procesing engine thresholds */
-	writel(EIP197_PE_IN_xBUF_THRES_MIN(6) | EIP197_PE_IN_xBUF_THRES_MAX(9),
-	       EIP197_PE(priv) + EIP197_PE_IN_DBUF_THRES);
-	writel(EIP197_PE_IN_xBUF_THRES_MIN(6) | EIP197_PE_IN_xBUF_THRES_MAX(7),
-	       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES);
+		/* DMA transfer size to use */
+		val = EIP197_HIA_DFE_CFG_DIS_DEBUG;
+		val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(6) |
+		       EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(9);
+		val |= EIP197_HIA_DxE_CFG_MIN_CTRL_SIZE(6) |
+		       EIP197_HIA_DxE_CFG_MAX_CTRL_SIZE(7);
+		val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(RD_CACHE_3BITS);
+		val |= EIP197_HIA_DxE_CFG_CTRL_CACHE_CTRL(RD_CACHE_3BITS);
+		writel(val, EIP197_HIA_DFE(priv) + EIP197_HIA_DFE_CFG(pe));
+
+		/* Leave the DFE threads reset state */
+		writel(0, EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
+
+		/* Configure the processing engine thresholds */
+		writel(EIP197_PE_IN_xBUF_THRES_MIN(6) |
+		       EIP197_PE_IN_xBUF_THRES_MAX(9),
+		       EIP197_PE(priv) + EIP197_PE_IN_DBUF_THRES(pe));
+		writel(EIP197_PE_IN_xBUF_THRES_MIN(6) |
+		       EIP197_PE_IN_xBUF_THRES_MAX(7),
+		       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES(pe));
+
+		if (priv->version == EIP197B) {
+			/* enable HIA input interface arbiter and rings */
+			writel(EIP197_HIA_RA_PE_CTRL_EN |
+			       GENMASK(priv->config.rings - 1, 0),
+			       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL(pe));
+		}
 
-	if (priv->version == EIP197B) {
-		/* enable HIA input interface arbiter and rings */
-		writel(EIP197_HIA_RA_PE_CTRL_EN |
-		       GENMASK(priv->config.rings - 1, 0),
-		       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL);
+		/* Data Store Engine configuration */
+
+		/* Reset all DSE threads */
+		writel(EIP197_DxE_THR_CTRL_RESET_PE,
+		       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
+
+		/* Wait for all DSE threads to complete */
+		while ((readl(EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_STAT(pe)) &
+			GENMASK(15, 12)) != GENMASK(15, 12))
+			;
+
+		/* DMA transfer size to use */
+		val = EIP197_HIA_DSE_CFG_DIS_DEBUG;
+		val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) |
+		       EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
+		val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(WR_CACHE_3BITS);
+		val |= EIP197_HIA_DSE_CFG_ALWAYS_BUFFERABLE;
+		/* FIXME: instability issues can occur for EIP97 but disabling it impact
+		 * performances.
+		 */
+		if (priv->version == EIP197B)
+			val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
+		writel(val, EIP197_HIA_DSE(priv) + EIP197_HIA_DSE_CFG(pe));
+
+		/* Leave the DSE threads reset state */
+		writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
+
+		/* Configure the procesing engine thresholds */
+		writel(EIP197_PE_OUT_DBUF_THRES_MIN(7) |
+		       EIP197_PE_OUT_DBUF_THRES_MAX(8),
+		       EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES(pe));
+
+		/* Processing Engine configuration */
+
+		/* H/W capabilities selection */
+		val = EIP197_FUNCTION_RSVD;
+		val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
+		val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
+		val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
+		val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
+		val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
+		writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN(pe));
 	}
 
-	/* Data Store Engine configuration */
-
-	/* Reset all DSE threads */
-	writel(EIP197_DxE_THR_CTRL_RESET_PE,
-	       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
-
-	/* Wait for all DSE threads to complete */
-	while ((readl(EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_STAT) &
-		GENMASK(15, 12)) != GENMASK(15, 12))
-		;
-
-	/* DMA transfer size to use */
-	val = EIP197_HIA_DSE_CFG_DIS_DEBUG;
-	val |= EIP197_HIA_DxE_CFG_MIN_DATA_SIZE(7) | EIP197_HIA_DxE_CFG_MAX_DATA_SIZE(8);
-	val |= EIP197_HIA_DxE_CFG_DATA_CACHE_CTRL(WR_CACHE_3BITS);
-	val |= EIP197_HIA_DSE_CFG_ALWAYS_BUFFERABLE;
-	/* FIXME: instability issues can occur for EIP97 but disabling it impact
-	 * performances.
-	 */
-	if (priv->version == EIP197B)
-		val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
-	writel(val, EIP197_HIA_DSE(priv) + EIP197_HIA_DSE_CFG);
-
-	/* Leave the DSE threads reset state */
-	writel(0, EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
-
-	/* Configure the procesing engine thresholds */
-	writel(EIP197_PE_OUT_DBUF_THRES_MIN(7) | EIP197_PE_OUT_DBUF_THRES_MAX(8),
-	       EIP197_PE(priv) + EIP197_PE_OUT_DBUF_THRES);
-
-	/* Processing Engine configuration */
-
-	/* H/W capabilities selection */
-	val = EIP197_FUNCTION_RSVD;
-	val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
-	val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
-	val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
-	val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
-	val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
-	writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN);
-
 	/* Command Descriptor Rings prepare */
 	for (i = 0; i < priv->config.rings; i++) {
 		/* Clear interrupts for this ring */
@@ -414,13 +427,15 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		       EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_SIZE);
 	}
 
-	/* Enable command descriptor rings */
-	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
-	       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL);
+	for (pe = 0; pe < priv->config.pes; pe++) {
+		/* Enable command descriptor rings */
+		writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
+		       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
 
-	/* Enable result descriptor rings */
-	writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
-	       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL);
+		/* Enable result descriptor rings */
+		writel(EIP197_DxE_THR_CTRL_EN | GENMASK(priv->config.rings - 1, 0),
+		       EIP197_HIA_DSE_THR(priv) + EIP197_HIA_DSE_THR_CTRL(pe));
+	}
 
 	/* Clear any HIA interrupt */
 	writel(GENMASK(30, 20), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
@@ -868,9 +883,20 @@ static void safexcel_unregister_algorithms(struct safexcel_crypto_priv *priv)
 
 static void safexcel_configure(struct safexcel_crypto_priv *priv)
 {
-	u32 val, mask;
+	u32 val, mask = 0;
 
 	val = readl(EIP197_HIA_AIC_G(priv) + EIP197_HIA_OPTIONS);
+
+	/* Read number of PEs from the engine */
+	switch (priv->version) {
+	case EIP197B:
+		mask = EIP197_N_PES_MASK;
+		break;
+	default:
+		mask = EIP97_N_PES_MASK;
+	}
+	priv->config.pes = (val >> EIP197_N_PES_OFFSET) & mask;
+
 	val = (val & GENMASK(27, 25)) >> 25;
 	mask = BIT(val) - 1;
 
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index f370f055fd80..4b7445b1af22 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -95,13 +95,13 @@
 #define EIP197_HIA_xDR_STAT			0x003c
 
 /* register offsets */
-#define EIP197_HIA_DFE_CFG			0x0000
-#define EIP197_HIA_DFE_THR_CTRL			0x0000
-#define EIP197_HIA_DFE_THR_STAT			0x0004
-#define EIP197_HIA_DSE_CFG			0x0000
-#define EIP197_HIA_DSE_THR_CTRL			0x0000
-#define EIP197_HIA_DSE_THR_STAT			0x0004
-#define EIP197_HIA_RA_PE_CTRL			0x0010
+#define EIP197_HIA_DFE_CFG(n)			(0x0000 + (128 * (n)))
+#define EIP197_HIA_DFE_THR_CTRL(n)		(0x0000 + (128 * (n)))
+#define EIP197_HIA_DFE_THR_STAT(n)		(0x0004 + (128 * (n)))
+#define EIP197_HIA_DSE_CFG(n)			(0x0000 + (128 * (n)))
+#define EIP197_HIA_DSE_THR_CTRL(n)		(0x0000 + (128 * (n)))
+#define EIP197_HIA_DSE_THR_STAT(n)		(0x0004 + (128 * (n)))
+#define EIP197_HIA_RA_PE_CTRL(n)		(0x0010 + (8   * (n)))
 #define EIP197_HIA_RA_PE_STAT			0x0014
 #define EIP197_HIA_AIC_R_OFF(r)			((r) * 0x1000)
 #define EIP197_HIA_AIC_R_ENABLE_CTRL(r)		(0xe008 - EIP197_HIA_AIC_R_OFF(r))
@@ -114,18 +114,18 @@
 #define EIP197_HIA_MST_CTRL			0xfff4
 #define EIP197_HIA_OPTIONS			0xfff8
 #define EIP197_HIA_VERSION			0xfffc
-#define EIP197_PE_IN_DBUF_THRES			0x0000
-#define EIP197_PE_IN_TBUF_THRES			0x0100
-#define EIP197_PE_ICE_SCRATCH_RAM		0x0800
-#define EIP197_PE_ICE_PUE_CTRL			0x0c80
-#define EIP197_PE_ICE_SCRATCH_CTRL		0x0d04
-#define EIP197_PE_ICE_FPP_CTRL			0x0d80
-#define EIP197_PE_ICE_RAM_CTRL			0x0ff0
-#define EIP197_PE_EIP96_FUNCTION_EN		0x1004
-#define EIP197_PE_EIP96_CONTEXT_CTRL		0x1008
-#define EIP197_PE_EIP96_CONTEXT_STAT		0x100c
-#define EIP197_PE_OUT_DBUF_THRES		0x1c00
-#define EIP197_PE_OUT_TBUF_THRES		0x1d00
+#define EIP197_PE_IN_DBUF_THRES(n)		(0x0000 + (0x2000 * (n)))
+#define EIP197_PE_IN_TBUF_THRES(n)		(0x0100 + (0x2000 * (n)))
+#define EIP197_PE_ICE_SCRATCH_RAM(n)		(0x0800 + (0x2000 * (n)))
+#define EIP197_PE_ICE_PUE_CTRL(n)		(0x0c80 + (0x2000 * (n)))
+#define EIP197_PE_ICE_SCRATCH_CTRL(n)		(0x0d04 + (0x2000 * (n)))
+#define EIP197_PE_ICE_FPP_CTRL(n)		(0x0d80 + (0x2000 * (n)))
+#define EIP197_PE_ICE_RAM_CTRL(n)		(0x0ff0 + (0x2000 * (n)))
+#define EIP197_PE_EIP96_FUNCTION_EN(n)		(0x1004 + (0x2000 * (n)))
+#define EIP197_PE_EIP96_CONTEXT_CTRL(n)		(0x1008 + (0x2000 * (n)))
+#define EIP197_PE_EIP96_CONTEXT_STAT(n)		(0x100c + (0x2000 * (n)))
+#define EIP197_PE_OUT_DBUF_THRES(n)		(0x1c00 + (0x2000 * (n)))
+#define EIP197_PE_OUT_TBUF_THRES(n)		(0x1d00 + (0x2000 * (n)))
 #define EIP197_MST_CTRL				0xfff4
 
 /* EIP197-specific registers, no indirection */
@@ -184,6 +184,11 @@
 #define EIP197_HIA_RA_PE_CTRL_RESET		BIT(31)
 #define EIP197_HIA_RA_PE_CTRL_EN		BIT(30)
 
+/* EIP197_HIA_OPTIONS */
+#define EIP197_N_PES_OFFSET			4
+#define EIP197_N_PES_MASK			GENMASK(4, 0)
+#define EIP97_N_PES_MASK			GENMASK(2, 0)
+
 /* EIP197_HIA_AIC_R_ENABLE_CTRL */
 #define EIP197_CDR_IRQ(n)			BIT((n) * 2)
 #define EIP197_RDR_IRQ(n)			BIT((n) * 2 + 1)
@@ -513,6 +518,7 @@ struct safexcel_request {
 };
 
 struct safexcel_config {
+	u32 pes;
 	u32 rings;
 
 	u32 cd_size;
-- 
cgit v1.2.3


From 5eb0911894b17e17859443b4c924583eb4bb20d0 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 28 Jun 2018 17:15:38 +0200
Subject: crypto: inside-secure - eip197d support

This patch adds support for the eip197d engine to the Inside Secure
SafeXcel cryptographic driver. This new engine is similar to the eip197b
and reuse most of its code.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        | 46 ++++++++++++++++++++------
 drivers/crypto/inside-secure/safexcel.h        |  1 +
 drivers/crypto/inside-secure/safexcel_cipher.c | 14 ++++----
 drivers/crypto/inside-secure/safexcel_hash.c   | 20 +++++------
 4 files changed, 54 insertions(+), 27 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index eefa6221533b..4ad1bfd77359 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -132,15 +132,32 @@ static int eip197_load_firmwares(struct safexcel_crypto_priv *priv)
 {
 	const char *fw_name[] = {"ifpp.bin", "ipue.bin"};
 	const struct firmware *fw[FW_NB];
-	char fw_path[31];
+	char fw_path[31], *dir = NULL;
 	int i, j, ret = 0, pe;
 	u32 val;
 
+	switch (priv->version) {
+	case EIP197B:
+		dir = "eip197b";
+		break;
+	case EIP197D:
+		dir = "eip197d";
+		break;
+	default:
+		/* No firmware is required */
+		return 0;
+	}
+
 	for (i = 0; i < FW_NB; i++) {
-		snprintf(fw_path, 31, "inside-secure/eip197b/%s", fw_name[i]);
+		snprintf(fw_path, 31, "inside-secure/%s/%s", dir, fw_name[i]);
 		ret = request_firmware(&fw[i], fw_path, priv->dev);
 		if (ret) {
-			/* Fallback to the old firmware location. */
+			if (priv->version != EIP197B)
+				goto release_fw;
+
+			/* Fallback to the old firmware location for the
+			 * EIP197b.
+			 */
 			ret = request_firmware(&fw[i], fw_name[i], priv->dev);
 			if (ret) {
 				dev_err(priv->dev,
@@ -300,7 +317,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		writel(EIP197_DxE_THR_CTRL_RESET_PE,
 		       EIP197_HIA_DFE_THR(priv) + EIP197_HIA_DFE_THR_CTRL(pe));
 
-		if (priv->version == EIP197B) {
+		if (priv->version == EIP197B || priv->version == EIP197D) {
 			/* Reset HIA input interface arbiter */
 			writel(EIP197_HIA_RA_PE_CTRL_RESET,
 			       EIP197_HIA_AIC(priv) + EIP197_HIA_RA_PE_CTRL(pe));
@@ -327,7 +344,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		       EIP197_PE_IN_xBUF_THRES_MAX(7),
 		       EIP197_PE(priv) + EIP197_PE_IN_TBUF_THRES(pe));
 
-		if (priv->version == EIP197B) {
+		if (priv->version == EIP197B || priv->version == EIP197D) {
 			/* enable HIA input interface arbiter and rings */
 			writel(EIP197_HIA_RA_PE_CTRL_EN |
 			       GENMASK(priv->config.rings - 1, 0),
@@ -354,7 +371,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		/* FIXME: instability issues can occur for EIP97 but disabling it impact
 		 * performances.
 		 */
-		if (priv->version == EIP197B)
+		if (priv->version == EIP197B || priv->version == EIP197D)
 			val |= EIP197_HIA_DSE_CFG_EN_SINGLE_WR;
 		writel(val, EIP197_HIA_DSE(priv) + EIP197_HIA_DSE_CFG(pe));
 
@@ -440,7 +457,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	/* Clear any HIA interrupt */
 	writel(GENMASK(30, 20), EIP197_HIA_AIC_G(priv) + EIP197_HIA_AIC_G_ACK);
 
-	if (priv->version == EIP197B) {
+	if (priv->version == EIP197B || priv->version == EIP197D) {
 		eip197_trc_cache_init(priv);
 
 		ret = eip197_load_firmwares(priv);
@@ -890,6 +907,7 @@ static void safexcel_configure(struct safexcel_crypto_priv *priv)
 	/* Read number of PEs from the engine */
 	switch (priv->version) {
 	case EIP197B:
+	case EIP197D:
 		mask = EIP197_N_PES_MASK;
 		break;
 	default:
@@ -914,7 +932,9 @@ static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
 {
 	struct safexcel_register_offsets *offsets = &priv->offsets;
 
-	if (priv->version == EIP197B) {
+	switch (priv->version) {
+	case EIP197B:
+	case EIP197D:
 		offsets->hia_aic	= EIP197_HIA_AIC_BASE;
 		offsets->hia_aic_g	= EIP197_HIA_AIC_G_BASE;
 		offsets->hia_aic_r	= EIP197_HIA_AIC_R_BASE;
@@ -925,7 +945,8 @@ static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
 		offsets->hia_dse_thr	= EIP197_HIA_DSE_THR_BASE;
 		offsets->hia_gen_cfg	= EIP197_HIA_GEN_CFG_BASE;
 		offsets->pe		= EIP197_PE_BASE;
-	} else {
+		break;
+	case EIP97IES:
 		offsets->hia_aic	= EIP97_HIA_AIC_BASE;
 		offsets->hia_aic_g	= EIP97_HIA_AIC_G_BASE;
 		offsets->hia_aic_r	= EIP97_HIA_AIC_R_BASE;
@@ -936,6 +957,7 @@ static void safexcel_init_register_offsets(struct safexcel_crypto_priv *priv)
 		offsets->hia_dse_thr	= EIP97_HIA_DSE_THR_BASE;
 		offsets->hia_gen_cfg	= EIP97_HIA_GEN_CFG_BASE;
 		offsets->pe		= EIP97_PE_BASE;
+		break;
 	}
 }
 
@@ -953,7 +975,7 @@ static int safexcel_probe(struct platform_device *pdev)
 	priv->dev = dev;
 	priv->version = (enum safexcel_eip_version)of_device_get_match_data(dev);
 
-	if (priv->version == EIP197B)
+	if (priv->version == EIP197B || priv->version == EIP197D)
 		priv->flags |= EIP197_TRC_CACHE;
 
 	safexcel_init_register_offsets(priv);
@@ -1115,6 +1137,10 @@ static const struct of_device_id safexcel_of_match_table[] = {
 		.compatible = "inside-secure,safexcel-eip197b",
 		.data = (void *)EIP197B,
 	},
+	{
+		.compatible = "inside-secure,safexcel-eip197d",
+		.data = (void *)EIP197D,
+	},
 	{
 		/* Deprecated. Kept for backward compatibility. */
 		.compatible = "inside-secure,safexcel-eip97",
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 4b7445b1af22..46c72306ca9f 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -566,6 +566,7 @@ struct safexcel_ring {
 enum safexcel_eip_version {
 	EIP97IES = BIT(0),
 	EIP197B  = BIT(1),
+	EIP197D  = BIT(2),
 };
 
 struct safexcel_register_offsets {
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 566c97223d67..7dbe991be83c 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -835,7 +835,7 @@ static void safexcel_aead_cra_exit(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_ecb_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.skcipher = {
 		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_ecb_aes_encrypt,
@@ -872,7 +872,7 @@ static int safexcel_cbc_aes_decrypt(struct skcipher_request *req)
 
 struct safexcel_alg_template safexcel_alg_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.skcipher = {
 		.setkey = safexcel_skcipher_aes_setkey,
 		.encrypt = safexcel_cbc_aes_encrypt,
@@ -942,7 +942,7 @@ static int safexcel_aead_sha1_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -977,7 +977,7 @@ static int safexcel_aead_sha256_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -1012,7 +1012,7 @@ static int safexcel_aead_sha224_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -1047,7 +1047,7 @@ static int safexcel_aead_sha512_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
@@ -1082,7 +1082,7 @@ static int safexcel_aead_sha384_cra_init(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_aes = {
 	.type = SAFEXCEL_ALG_TYPE_AEAD,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.aead = {
 		.setkey = safexcel_aead_aes_setkey,
 		.encrypt = safexcel_aead_encrypt,
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 94841df4b6bd..c266398647bc 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -796,7 +796,7 @@ static void safexcel_ahash_cra_exit(struct crypto_tfm *tfm)
 
 struct safexcel_alg_template safexcel_alg_sha1 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha1_init,
 		.update = safexcel_ahash_update,
@@ -1030,7 +1030,7 @@ static int safexcel_hmac_sha1_setkey(struct crypto_ahash *tfm, const u8 *key,
 
 struct safexcel_alg_template safexcel_alg_hmac_sha1 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha1_init,
 		.update = safexcel_ahash_update,
@@ -1094,7 +1094,7 @@ static int safexcel_sha256_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha256 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha256_init,
 		.update = safexcel_ahash_update,
@@ -1157,7 +1157,7 @@ static int safexcel_sha224_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha224 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha224_init,
 		.update = safexcel_ahash_update,
@@ -1213,7 +1213,7 @@ static int safexcel_hmac_sha224_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha224 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha224_init,
 		.update = safexcel_ahash_update,
@@ -1270,7 +1270,7 @@ static int safexcel_hmac_sha256_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha256 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha256_init,
 		.update = safexcel_ahash_update,
@@ -1342,7 +1342,7 @@ static int safexcel_sha512_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha512 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha512_init,
 		.update = safexcel_ahash_update,
@@ -1413,7 +1413,7 @@ static int safexcel_sha384_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_sha384 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_sha384_init,
 		.update = safexcel_ahash_update,
@@ -1469,7 +1469,7 @@ static int safexcel_hmac_sha512_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha512 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha512_init,
 		.update = safexcel_ahash_update,
@@ -1526,7 +1526,7 @@ static int safexcel_hmac_sha384_digest(struct ahash_request *areq)
 
 struct safexcel_alg_template safexcel_alg_hmac_sha384 = {
 	.type = SAFEXCEL_ALG_TYPE_AHASH,
-	.engines = EIP97IES | EIP197B,
+	.engines = EIP97IES | EIP197B | EIP197D,
 	.alg.ahash = {
 		.init = safexcel_hmac_sha384_init,
 		.update = safexcel_ahash_update,
-- 
cgit v1.2.3


From 6cdc06d639dfe57749586a57bfff39d4731ca81d Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 28 Jun 2018 17:15:39 +0200
Subject: Documentation/bindings: crypto: inside-secure: eip197d support

This patch documents the new compatible used for the eip197d engine, as
this new engine is now supported by the Inside Secure SafeXcel
cryptographic driver.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
index dc8678db52fa..3bbf144c9988 100644
--- a/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
+++ b/Documentation/devicetree/bindings/crypto/inside-secure-safexcel.txt
@@ -1,7 +1,8 @@
 Inside Secure SafeXcel cryptographic engine
 
 Required properties:
-- compatible: Should be "inside-secure,safexcel-eip197b" or
+- compatible: Should be "inside-secure,safexcel-eip197b",
+	      "inside-secure,safexcel-eip197d" or
               "inside-secure,safexcel-eip97ies".
 - reg: Base physical address of the engine and length of memory mapped region.
 - interrupts: Interrupt numbers for the rings and engine.
-- 
cgit v1.2.3


From fbd0a7c920686721cbc6671cc7dd6c31d5ac6430 Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:15:40 +0200
Subject: crypto: inside-secure - adjust the TRC configuration for EIP197D

This patch updates the TRC configuration so that the version of the
EIP197 engine being used is taken into account, as the configuration
differs between the EIP197B and the EIP197D.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
[Antoine: commit message]
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c | 30 +++++++++++++++++++++---------
 drivers/crypto/inside-secure/safexcel.h | 12 +++++++++---
 2 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 4ad1bfd77359..b70694090353 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -33,7 +33,19 @@ MODULE_PARM_DESC(max_rings, "Maximum number of rings to use.");
 static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 {
 	u32 val, htable_offset;
-	int i;
+	int i, cs_rc_max, cs_ht_wc, cs_trc_rec_wc, cs_trc_lg_rec_wc;
+
+	if (priv->version == EIP197B) {
+		cs_rc_max = EIP197B_CS_RC_MAX;
+		cs_ht_wc = EIP197B_CS_HT_WC;
+		cs_trc_rec_wc = EIP197B_CS_TRC_REC_WC;
+		cs_trc_lg_rec_wc = EIP197B_CS_TRC_LG_REC_WC;
+	} else {
+		cs_rc_max = EIP197D_CS_RC_MAX;
+		cs_ht_wc = EIP197D_CS_HT_WC;
+		cs_trc_rec_wc = EIP197D_CS_TRC_REC_WC;
+		cs_trc_lg_rec_wc = EIP197D_CS_TRC_LG_REC_WC;
+	}
 
 	/* Enable the record cache memory access */
 	val = readl(priv->base + EIP197_CS_RAM_CTRL);
@@ -54,7 +66,7 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 	writel(val, priv->base + EIP197_TRC_PARAMS);
 
 	/* Clear all records */
-	for (i = 0; i < EIP197_CS_RC_MAX; i++) {
+	for (i = 0; i < cs_rc_max; i++) {
 		u32 val, offset = EIP197_CLASSIFICATION_RAMS + i * EIP197_CS_RC_SIZE;
 
 		writel(EIP197_CS_RC_NEXT(EIP197_RC_NULL) |
@@ -64,14 +76,14 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 		val = EIP197_CS_RC_NEXT(i+1) | EIP197_CS_RC_PREV(i-1);
 		if (i == 0)
 			val |= EIP197_CS_RC_PREV(EIP197_RC_NULL);
-		else if (i == EIP197_CS_RC_MAX - 1)
+		else if (i == cs_rc_max - 1)
 			val |= EIP197_CS_RC_NEXT(EIP197_RC_NULL);
 		writel(val, priv->base + offset + sizeof(u32));
 	}
 
 	/* Clear the hash table entries */
-	htable_offset = EIP197_CS_RC_MAX * EIP197_CS_RC_SIZE;
-	for (i = 0; i < 64; i++)
+	htable_offset = cs_rc_max * EIP197_CS_RC_SIZE;
+	for (i = 0; i < cs_ht_wc; i++)
 		writel(GENMASK(29, 0),
 		       priv->base + EIP197_CLASSIFICATION_RAMS + htable_offset + i * sizeof(u32));
 
@@ -82,16 +94,16 @@ static void eip197_trc_cache_init(struct safexcel_crypto_priv *priv)
 
 	/* Write head and tail pointers of the record free chain */
 	val = EIP197_TRC_FREECHAIN_HEAD_PTR(0) |
-	      EIP197_TRC_FREECHAIN_TAIL_PTR(EIP197_CS_RC_MAX - 1);
+	      EIP197_TRC_FREECHAIN_TAIL_PTR(cs_rc_max - 1);
 	writel(val, priv->base + EIP197_TRC_FREECHAIN);
 
 	/* Configure the record cache #1 */
-	val = EIP197_TRC_PARAMS2_RC_SZ_SMALL(EIP197_CS_TRC_REC_WC) |
-	      EIP197_TRC_PARAMS2_HTABLE_PTR(EIP197_CS_RC_MAX);
+	val = EIP197_TRC_PARAMS2_RC_SZ_SMALL(cs_trc_rec_wc) |
+	      EIP197_TRC_PARAMS2_HTABLE_PTR(cs_rc_max);
 	writel(val, priv->base + EIP197_TRC_PARAMS2);
 
 	/* Configure the record cache #2 */
-	val = EIP197_TRC_PARAMS_RC_SZ_LARGE(EIP197_CS_TRC_LG_REC_WC) |
+	val = EIP197_TRC_PARAMS_RC_SZ_LARGE(cs_trc_lg_rec_wc) |
 	      EIP197_TRC_PARAMS_BLK_TIMER_SPEED(1) |
 	      EIP197_TRC_PARAMS_HTABLE_SZ(2);
 	writel(val, priv->base + EIP197_TRC_PARAMS);
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 46c72306ca9f..94a89664f3d0 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -361,13 +361,19 @@ struct safexcel_context_record {
 #define EIP197_TRC_PARAMS2_RC_SZ_SMALL(n)	((n) << 18)
 
 /* Cache helpers */
-#define EIP197_CS_RC_MAX			52
+#define EIP197B_CS_RC_MAX			52
+#define EIP197D_CS_RC_MAX			96
 #define EIP197_CS_RC_SIZE			(4 * sizeof(u32))
 #define EIP197_CS_RC_NEXT(x)			(x)
 #define EIP197_CS_RC_PREV(x)			((x) << 10)
 #define EIP197_RC_NULL				0x3ff
-#define EIP197_CS_TRC_REC_WC			59
-#define EIP197_CS_TRC_LG_REC_WC			73
+#define EIP197B_CS_TRC_REC_WC			59
+#define EIP197D_CS_TRC_REC_WC			64
+#define EIP197B_CS_TRC_LG_REC_WC		73
+#define EIP197D_CS_TRC_LG_REC_WC		80
+#define EIP197B_CS_HT_WC			64
+#define EIP197D_CS_HT_WC			256
+
 
 /* Result data */
 struct result_data_desc {
-- 
cgit v1.2.3


From f1edf29a770ce97cd6b7e028a4999d24bb5ae492 Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:15:41 +0200
Subject: crypto: inside-secure - reset CDR and RDR rings on module removal

This patch adds extra steps in the module removal path, to reset the
command and result rings. The corresponding interrupts are cleared, and
the ring address configuration is reset.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
[Antoine: small reworks, commit message]
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index b70694090353..5feb83c6238b 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -1125,6 +1125,24 @@ err_core_clk:
 	return ret;
 }
 
+static void safexcel_hw_reset_rings(struct safexcel_crypto_priv *priv)
+{
+	int i;
+
+	for (i = 0; i < priv->config.rings; i++) {
+		/* clear any pending interrupt */
+		writel(GENMASK(5, 0), EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_STAT);
+		writel(GENMASK(7, 0), EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_STAT);
+
+		/* Reset the CDR base address */
+		writel(0, EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		writel(0, EIP197_HIA_CDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+
+		/* Reset the RDR base address */
+		writel(0, EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_LO);
+		writel(0, EIP197_HIA_RDR(priv, i) + EIP197_HIA_xDR_RING_BASE_ADDR_HI);
+	}
+}
 
 static int safexcel_remove(struct platform_device *pdev)
 {
@@ -1132,6 +1150,8 @@ static int safexcel_remove(struct platform_device *pdev)
 	int i;
 
 	safexcel_unregister_algorithms(priv);
+	safexcel_hw_reset_rings(priv);
+
 	clk_disable_unprepare(priv->clk);
 
 	for (i = 0; i < priv->config.rings; i++)
-- 
cgit v1.2.3


From 63b942782f1dd241d19a7584b4b644da0f5338c0 Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:15:42 +0200
Subject: crypto: inside-secure - set tx_max_cmd_queue to 32

The ORO bridge (connected to the EIP197 write channel) does not
generate back pressure towards the EIP197 when its internal FIFO is
full. It assumes that the EIP will not drive more write transactions
than the maximal supported outstanding (32).

Hence tx_max_cmd_queue must be configured to 5 (or less).

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c | 4 ++++
 drivers/crypto/inside-secure/safexcel.h | 1 +
 2 files changed, 5 insertions(+)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 5feb83c6238b..9e5d2bf232eb 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -306,6 +306,10 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 	else if (((version >> 16) & 0xffff) == EIP197_HIA_VERSION_LE)
 		val |= (EIP197_MST_CTRL_NO_BYTE_SWAP >> 24);
 
+	/* For EIP197 set maximum number of TX commands to 2^5 = 32 */
+	if (priv->version == EIP197B || priv->version == EIP197D)
+		val |= EIP197_MST_CTRL_TX_MAX_CMD(5);
+
 	writel(val, EIP197_HIA_AIC(priv) + EIP197_HIA_MST_CTRL);
 
 	/* Configure wr/rd cache values */
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 94a89664f3d0..95095cb95ba4 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -222,6 +222,7 @@
 #define WR_CACHE_4BITS				(WR_CACHE_3BITS << 1 | BIT(0))
 #define EIP197_MST_CTRL_RD_CACHE(n)		(((n) & 0xf) << 0)
 #define EIP197_MST_CTRL_WD_CACHE(n)		(((n) & 0xf) << 4)
+#define EIP197_MST_CTRL_TX_MAX_CMD(n)		(((n) & 0xf) << 20)
 #define EIP197_MST_CTRL_BYTE_SWAP		BIT(24)
 #define EIP197_MST_CTRL_NO_BYTE_SWAP		BIT(25)
 
-- 
cgit v1.2.3


From 293f89cf930e7f0e99e74223673e3dc46380b26b Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:21:53 +0200
Subject: crypto: inside-secure - md5 support

This patch adds the MD5 algorithm support to the Inside Secure SafeXcel
cryptographic engine driver.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/Kconfig                       |  1 +
 drivers/crypto/inside-secure/safexcel.c      |  2 +
 drivers/crypto/inside-secure/safexcel.h      |  2 +
 drivers/crypto/inside-secure/safexcel_hash.c | 69 +++++++++++++++++++++++++++-
 4 files changed, 72 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 43cccf6aff61..265f987a969b 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -691,6 +691,7 @@ config CRYPTO_DEV_SAFEXCEL
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_HASH
 	select CRYPTO_HMAC
+	select CRYPTO_MD5
 	select CRYPTO_SHA1
 	select CRYPTO_SHA256
 	select CRYPTO_SHA512
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 9e5d2bf232eb..188e459aa923 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -406,6 +406,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
 		val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
 		val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
+		val |= EIP197_ALG_MD5;
 		val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
 		val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
 		writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN(pe));
@@ -841,6 +842,7 @@ static int safexcel_request_ring_irq(struct platform_device *pdev, const char *n
 static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_ecb_aes,
 	&safexcel_alg_cbc_aes,
+	&safexcel_alg_md5,
 	&safexcel_alg_sha1,
 	&safexcel_alg_sha224,
 	&safexcel_alg_sha256,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 95095cb95ba4..fcd26ae70166 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -316,6 +316,7 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES256	(0x7 << 17)
 #define CONTEXT_CONTROL_DIGEST_PRECOMPUTED	(0x1 << 21)
 #define CONTEXT_CONTROL_DIGEST_HMAC		(0x3 << 21)
+#define CONTEXT_CONTROL_CRYPTO_ALG_MD5		(0x0 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA1		(0x2 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA224	(0x4 << 23)
 #define CONTEXT_CONTROL_CRYPTO_ALG_SHA256	(0x3 << 23)
@@ -691,6 +692,7 @@ int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
 /* available algorithms */
 extern struct safexcel_alg_template safexcel_alg_ecb_aes;
 extern struct safexcel_alg_template safexcel_alg_cbc_aes;
+extern struct safexcel_alg_template safexcel_alg_md5;
 extern struct safexcel_alg_template safexcel_alg_sha1;
 extern struct safexcel_alg_template safexcel_alg_sha224;
 extern struct safexcel_alg_template safexcel_alg_sha256;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index c266398647bc..4fec8fe07044 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -9,6 +9,7 @@
  */
 
 #include <crypto/hmac.h>
+#include <crypto/md5.h>
 #include <crypto/sha.h>
 #include <linux/device.h>
 #include <linux/dma-mapping.h>
@@ -91,7 +92,9 @@ static void safexcel_context_control(struct safexcel_ahash_ctx *ctx,
 
 	if (req->digest == CONTEXT_CONTROL_DIGEST_PRECOMPUTED) {
 		if (req->processed[0] || req->processed[1]) {
-			if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
+			if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_MD5)
+				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(5);
+			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
 				cdesc->control_data.control0 |= CONTEXT_CONTROL_SIZE(6);
 			else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224 ||
 				 ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA256)
@@ -652,7 +655,10 @@ static int safexcel_ahash_final(struct ahash_request *areq)
 
 	/* If we have an overall 0 length request */
 	if (!req->len[0] && !req->len[1] && !areq->nbytes) {
-		if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
+		if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_MD5)
+			memcpy(areq->result, md5_zero_message_hash,
+			       MD5_DIGEST_SIZE);
+		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA1)
 			memcpy(areq->result, sha1_zero_message_hash,
 			       SHA1_DIGEST_SIZE);
 		else if (ctx->alg == CONTEXT_CONTROL_CRYPTO_ALG_SHA224)
@@ -1554,3 +1560,62 @@ struct safexcel_alg_template safexcel_alg_hmac_sha384 = {
 		},
 	},
 };
+
+static int safexcel_md5_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	memset(req, 0, sizeof(*req));
+
+	req->state[0] = MD5_H0;
+	req->state[1] = MD5_H1;
+	req->state[2] = MD5_H2;
+	req->state[3] = MD5_H3;
+
+	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_MD5;
+	req->digest = CONTEXT_CONTROL_DIGEST_PRECOMPUTED;
+	req->state_sz = MD5_DIGEST_SIZE;
+
+	return 0;
+}
+
+static int safexcel_md5_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_md5_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_md5 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_md5_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_md5_digest,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = MD5_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "md5",
+				.cra_driver_name = "safexcel-md5",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
-- 
cgit v1.2.3


From b471e4b988af70eeb1940dddea62a92eff49023e Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:21:54 +0200
Subject: crypto: inside-secure - hmac(md5) support

This patch adds support for the hmac(md5) algorithm in the Inside Secure
SafeXcel cryptographic engine driver.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c      |  3 +-
 drivers/crypto/inside-secure/safexcel.h      |  1 +
 drivers/crypto/inside-secure/safexcel_hash.c | 57 ++++++++++++++++++++++++++++
 3 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 188e459aa923..a52f0dabe8d4 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -406,7 +406,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
 		val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
 		val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
-		val |= EIP197_ALG_MD5;
+		val |= EIP197_ALG_MD5 | EIP197_ALG_HMAC_MD5;
 		val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
 		val |= EIP197_ALG_SHA2 | EIP197_ALG_HMAC_SHA2;
 		writel(val, EIP197_PE(priv) + EIP197_PE_EIP96_FUNCTION_EN(pe));
@@ -848,6 +848,7 @@ static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_sha256,
 	&safexcel_alg_sha384,
 	&safexcel_alg_sha512,
+	&safexcel_alg_hmac_md5,
 	&safexcel_alg_hmac_sha1,
 	&safexcel_alg_hmac_sha224,
 	&safexcel_alg_hmac_sha256,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index fcd26ae70166..19610b03bceb 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -698,6 +698,7 @@ extern struct safexcel_alg_template safexcel_alg_sha224;
 extern struct safexcel_alg_template safexcel_alg_sha256;
 extern struct safexcel_alg_template safexcel_alg_sha384;
 extern struct safexcel_alg_template safexcel_alg_sha512;
+extern struct safexcel_alg_template safexcel_alg_hmac_md5;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha1;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha224;
 extern struct safexcel_alg_template safexcel_alg_hmac_sha256;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 4fec8fe07044..46aac55c0b31 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -1619,3 +1619,60 @@ struct safexcel_alg_template safexcel_alg_md5 = {
 		},
 	},
 };
+
+static int safexcel_hmac_md5_init(struct ahash_request *areq)
+{
+	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
+
+	safexcel_md5_init(areq);
+	req->digest = CONTEXT_CONTROL_DIGEST_HMAC;
+	return 0;
+}
+
+static int safexcel_hmac_md5_setkey(struct crypto_ahash *tfm, const u8 *key,
+				     unsigned int keylen)
+{
+	return safexcel_hmac_alg_setkey(tfm, key, keylen, "safexcel-md5",
+					MD5_DIGEST_SIZE);
+}
+
+static int safexcel_hmac_md5_digest(struct ahash_request *areq)
+{
+	int ret = safexcel_hmac_md5_init(areq);
+
+	if (ret)
+		return ret;
+
+	return safexcel_ahash_finup(areq);
+}
+
+struct safexcel_alg_template safexcel_alg_hmac_md5 = {
+	.type = SAFEXCEL_ALG_TYPE_AHASH,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.ahash = {
+		.init = safexcel_hmac_md5_init,
+		.update = safexcel_ahash_update,
+		.final = safexcel_ahash_final,
+		.finup = safexcel_ahash_finup,
+		.digest = safexcel_hmac_md5_digest,
+		.setkey = safexcel_hmac_md5_setkey,
+		.export = safexcel_ahash_export,
+		.import = safexcel_ahash_import,
+		.halg = {
+			.digestsize = MD5_DIGEST_SIZE,
+			.statesize = sizeof(struct safexcel_ahash_export_state),
+			.base = {
+				.cra_name = "hmac(md5)",
+				.cra_driver_name = "safexcel-hmac-md5",
+				.cra_priority = 300,
+				.cra_flags = CRYPTO_ALG_ASYNC |
+					     CRYPTO_ALG_KERN_DRIVER_ONLY,
+				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
+				.cra_ctxsize = sizeof(struct safexcel_ahash_ctx),
+				.cra_init = safexcel_ahash_cra_init,
+				.cra_exit = safexcel_ahash_cra_exit,
+				.cra_module = THIS_MODULE,
+			},
+		},
+	},
+};
-- 
cgit v1.2.3


From a7dea8c0ff9f2573b1b34d320670693f979136b8 Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:21:55 +0200
Subject: crypto: inside-secure - ecb(des) and cbc(des) support

This patch adds support for two algorithms in the Inside Secure SafeXcel
cryptographic engine driver: ecb(des) and cbc(des).

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/Kconfig                         |   1 +
 drivers/crypto/inside-secure/safexcel.c        |   3 +
 drivers/crypto/inside-secure/safexcel.h        |   4 +
 drivers/crypto/inside-secure/safexcel_cipher.c | 222 ++++++++++++++++++++-----
 4 files changed, 186 insertions(+), 44 deletions(-)

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 265f987a969b..7c6ba111671d 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -689,6 +689,7 @@ config CRYPTO_DEV_SAFEXCEL
 	select CRYPTO_AES
 	select CRYPTO_AUTHENC
 	select CRYPTO_BLKCIPHER
+	select CRYPTO_DES
 	select CRYPTO_HASH
 	select CRYPTO_HMAC
 	select CRYPTO_MD5
diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index a52f0dabe8d4..b2809bbd8303 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -405,6 +405,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		val = EIP197_FUNCTION_RSVD;
 		val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
 		val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
+		val |= EIP197_ALG_DES_ECB | EIP197_ALG_DES_CBC;
 		val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
 		val |= EIP197_ALG_MD5 | EIP197_ALG_HMAC_MD5;
 		val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
@@ -840,6 +841,8 @@ static int safexcel_request_ring_irq(struct platform_device *pdev, const char *n
 }
 
 static struct safexcel_alg_template *safexcel_algs[] = {
+	&safexcel_alg_ecb_des,
+	&safexcel_alg_cbc_des,
 	&safexcel_alg_ecb_aes,
 	&safexcel_alg_cbc_aes,
 	&safexcel_alg_md5,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 19610b03bceb..31d4fd259229 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -311,6 +311,7 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_NO_FINISH_HASH		BIT(5)
 #define CONTEXT_CONTROL_SIZE(n)			((n) << 8)
 #define CONTEXT_CONTROL_KEY_EN			BIT(16)
+#define CONTEXT_CONTROL_CRYPTO_ALG_DES		(0x0 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES128	(0x5 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES192	(0x6 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES256	(0x7 << 17)
@@ -470,6 +471,7 @@ struct safexcel_control_data_desc {
 #define EIP197_OPTION_MAGIC_VALUE	BIT(0)
 #define EIP197_OPTION_64BIT_CTX		BIT(1)
 #define EIP197_OPTION_CTX_CTRL_IN_CMD	BIT(8)
+#define EIP197_OPTION_2_TOKEN_IV_CMD	GENMASK(11, 10)
 #define EIP197_OPTION_4_TOKEN_IV_CMD	GENMASK(11, 9)
 
 #define EIP197_TYPE_EXTENDED		0x3
@@ -690,6 +692,8 @@ int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
 			 void *istate, void *ostate);
 
 /* available algorithms */
+extern struct safexcel_alg_template safexcel_alg_ecb_des;
+extern struct safexcel_alg_template safexcel_alg_cbc_des;
 extern struct safexcel_alg_template safexcel_alg_ecb_aes;
 extern struct safexcel_alg_template safexcel_alg_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_md5;
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 7dbe991be83c..e27b689ee641 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -15,6 +15,7 @@
 #include <crypto/aead.h>
 #include <crypto/aes.h>
 #include <crypto/authenc.h>
+#include <crypto/des.h>
 #include <crypto/sha.h>
 #include <crypto/skcipher.h>
 #include <crypto/internal/aead.h>
@@ -27,18 +28,24 @@ enum safexcel_cipher_direction {
 	SAFEXCEL_DECRYPT,
 };
 
+enum safexcel_cipher_alg {
+	SAFEXCEL_DES,
+	SAFEXCEL_AES,
+};
+
 struct safexcel_cipher_ctx {
 	struct safexcel_context base;
 	struct safexcel_crypto_priv *priv;
 
 	u32 mode;
+	enum safexcel_cipher_alg alg;
 	bool aead;
 
 	__le32 key[8];
 	unsigned int key_len;
 
 	/* All the below is AEAD specific */
-	u32 alg;
+	u32 hash_alg;
 	u32 state_sz;
 	u32 ipad[SHA512_DIGEST_SIZE / sizeof(u32)];
 	u32 opad[SHA512_DIGEST_SIZE / sizeof(u32)];
@@ -57,10 +64,18 @@ static void safexcel_skcipher_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 	unsigned offset = 0;
 
 	if (ctx->mode == CONTEXT_CONTROL_CRYPTO_MODE_CBC) {
-		offset = AES_BLOCK_SIZE / sizeof(u32);
-		memcpy(cdesc->control_data.token, iv, AES_BLOCK_SIZE);
-
-		cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+		switch (ctx->alg) {
+		case SAFEXCEL_DES:
+			offset = DES_BLOCK_SIZE / sizeof(u32);
+			memcpy(cdesc->control_data.token, iv, DES_BLOCK_SIZE);
+			cdesc->control_data.options |= EIP197_OPTION_2_TOKEN_IV_CMD;
+			break;
+		case SAFEXCEL_AES:
+			offset = AES_BLOCK_SIZE / sizeof(u32);
+			memcpy(cdesc->control_data.token, iv, AES_BLOCK_SIZE);
+			cdesc->control_data.options |= EIP197_OPTION_4_TOKEN_IV_CMD;
+			break;
+		}
 	}
 
 	token = (struct safexcel_token *)(cdesc->control_data.token + offset);
@@ -184,7 +199,7 @@ static int safexcel_aead_aes_setkey(struct crypto_aead *ctfm, const u8 *key,
 		ctx->base.needs_inv = true;
 
 	/* Auth key */
-	switch (ctx->alg) {
+	switch (ctx->hash_alg) {
 	case CONTEXT_CONTROL_CRYPTO_ALG_SHA1:
 		if (safexcel_hmac_setkey("safexcel-sha1", keys.authkey,
 					 keys.authkeylen, &istate, &ostate))
@@ -268,22 +283,26 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 
 	if (ctx->aead)
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_DIGEST_HMAC |
-						ctx->alg;
-
-	switch (ctx->key_len) {
-	case AES_KEYSIZE_128:
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES128;
-		break;
-	case AES_KEYSIZE_192:
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES192;
-		break;
-	case AES_KEYSIZE_256:
-		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES256;
-		break;
-	default:
-		dev_err(priv->dev, "aes keysize not supported: %u\n",
-			ctx->key_len);
-		return -EINVAL;
+						ctx->hash_alg;
+
+	if (ctx->alg == SAFEXCEL_DES) {
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_DES;
+	} else if (ctx->alg == SAFEXCEL_AES) {
+		switch (ctx->key_len) {
+		case AES_KEYSIZE_128:
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES128;
+			break;
+		case AES_KEYSIZE_192:
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES192;
+			break;
+		case AES_KEYSIZE_256:
+			cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_AES256;
+			break;
+		default:
+			dev_err(priv->dev, "aes keysize not supported: %u\n",
+				ctx->key_len);
+			return -EINVAL;
+		}
 	}
 
 	ctrl_size = ctx->key_len / sizeof(u32);
@@ -345,7 +364,7 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	return ndesc;
 }
 
-static int safexcel_aes_send(struct crypto_async_request *base, int ring,
+static int safexcel_send_req(struct crypto_async_request *base, int ring,
 			     struct safexcel_request *request,
 			     struct safexcel_cipher_req *sreq,
 			     struct scatterlist *src, struct scatterlist *dst,
@@ -618,7 +637,7 @@ static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
 		ret = safexcel_cipher_send_inv(async, ring, request, commands,
 					       results);
 	else
-		ret = safexcel_aes_send(async, ring, request, sreq, req->src,
+		ret = safexcel_send_req(async, ring, request, sreq, req->src,
 					req->dst, req->cryptlen, 0, 0, req->iv,
 					commands, results);
 	return ret;
@@ -641,7 +660,7 @@ static int safexcel_aead_send(struct crypto_async_request *async, int ring,
 		ret = safexcel_cipher_send_inv(async, ring, request, commands,
 					       results);
 	else
-		ret = safexcel_aes_send(async, ring, request, sreq, req->src,
+		ret = safexcel_send_req(async, ring, request, sreq, req->src,
 					req->dst, req->cryptlen, req->assoclen,
 					crypto_aead_authsize(tfm), req->iv,
 					commands, results);
@@ -712,9 +731,10 @@ static int safexcel_aead_exit_inv(struct crypto_tfm *tfm)
 	return safexcel_cipher_exit_inv(tfm, &req->base, sreq, &result);
 }
 
-static int safexcel_aes(struct crypto_async_request *base,
+static int safexcel_queue_req(struct crypto_async_request *base,
 			struct safexcel_cipher_req *sreq,
-			enum safexcel_cipher_direction dir, u32 mode)
+			enum safexcel_cipher_direction dir, u32 mode,
+			enum safexcel_cipher_alg alg)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
@@ -722,6 +742,7 @@ static int safexcel_aes(struct crypto_async_request *base,
 
 	sreq->needs_inv = false;
 	sreq->direction = dir;
+	ctx->alg = alg;
 	ctx->mode = mode;
 
 	if (ctx->base.ctxr) {
@@ -752,14 +773,16 @@ static int safexcel_aes(struct crypto_async_request *base,
 
 static int safexcel_ecb_aes_encrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_AES);
 }
 
 static int safexcel_ecb_aes_decrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_AES);
 }
 
 static int safexcel_skcipher_cra_init(struct crypto_tfm *tfm)
@@ -860,14 +883,16 @@ struct safexcel_alg_template safexcel_alg_ecb_aes = {
 
 static int safexcel_cbc_aes_encrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_AES);
 }
 
 static int safexcel_cbc_aes_decrypt(struct skcipher_request *req)
 {
-	return safexcel_aes(&req->base, skcipher_request_ctx(req),
-			    SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_AES);
 }
 
 struct safexcel_alg_template safexcel_alg_cbc_aes = {
@@ -896,20 +921,129 @@ struct safexcel_alg_template safexcel_alg_cbc_aes = {
 	},
 };
 
+static int safexcel_cbc_des_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_DES);
+}
+
+static int safexcel_cbc_des_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_DES);
+}
+
+static int safexcel_des_setkey(struct crypto_skcipher *ctfm, const u8 *key,
+			       unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+	u32 tmp[DES_EXPKEY_WORDS];
+	int ret;
+
+	if (len != DES_KEY_SIZE) {
+		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	ret = des_ekey(tmp, key);
+	if (!ret && (tfm->crt_flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
+		tfm->crt_flags |= CRYPTO_TFM_RES_WEAK_KEY;
+		return -EINVAL;
+	}
+
+	/* if context exits and key changed, need to invalidate it */
+	if (ctx->base.ctxr_dma)
+		if (memcmp(ctx->key, key, len))
+			ctx->base.needs_inv = true;
+
+	memcpy(ctx->key, key, len);
+	ctx->key_len = len;
+
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_cbc_des = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des_setkey,
+		.encrypt = safexcel_cbc_des_encrypt,
+		.decrypt = safexcel_cbc_des_decrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = DES_BLOCK_SIZE,
+		.base = {
+			.cra_name = "cbc(des)",
+			.cra_driver_name = "safexcel-cbc-des",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_ecb_des_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_DES);
+}
+
+static int safexcel_ecb_des_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_DES);
+}
+
+struct safexcel_alg_template safexcel_alg_ecb_des = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des_setkey,
+		.encrypt = safexcel_ecb_des_encrypt,
+		.decrypt = safexcel_ecb_des_decrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = DES_BLOCK_SIZE,
+		.base = {
+			.cra_name = "ecb(des)",
+			.cra_driver_name = "safexcel-ecb-des",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
 static int safexcel_aead_encrypt(struct aead_request *req)
 {
 	struct safexcel_cipher_req *creq = aead_request_ctx(req);
 
-	return safexcel_aes(&req->base, creq, SAFEXCEL_ENCRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, creq, SAFEXCEL_ENCRYPT,
+			CONTEXT_CONTROL_CRYPTO_MODE_CBC, SAFEXCEL_AES);
 }
 
 static int safexcel_aead_decrypt(struct aead_request *req)
 {
 	struct safexcel_cipher_req *creq = aead_request_ctx(req);
 
-	return safexcel_aes(&req->base, creq, SAFEXCEL_DECRYPT,
-			    CONTEXT_CONTROL_CRYPTO_MODE_CBC);
+	return safexcel_queue_req(&req->base, creq, SAFEXCEL_DECRYPT,
+			CONTEXT_CONTROL_CRYPTO_MODE_CBC, SAFEXCEL_AES);
 }
 
 static int safexcel_aead_cra_init(struct crypto_tfm *tfm)
@@ -935,7 +1069,7 @@ static int safexcel_aead_sha1_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA1;
 	ctx->state_sz = SHA1_DIGEST_SIZE;
 	return 0;
 }
@@ -970,7 +1104,7 @@ static int safexcel_aead_sha256_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA256;
 	ctx->state_sz = SHA256_DIGEST_SIZE;
 	return 0;
 }
@@ -1005,7 +1139,7 @@ static int safexcel_aead_sha224_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA224;
 	ctx->state_sz = SHA256_DIGEST_SIZE;
 	return 0;
 }
@@ -1040,7 +1174,7 @@ static int safexcel_aead_sha512_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA512;
 	ctx->state_sz = SHA512_DIGEST_SIZE;
 	return 0;
 }
@@ -1075,7 +1209,7 @@ static int safexcel_aead_sha384_cra_init(struct crypto_tfm *tfm)
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
 
 	safexcel_aead_cra_init(tfm);
-	ctx->alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
+	ctx->hash_alg = CONTEXT_CONTROL_CRYPTO_ALG_SHA384;
 	ctx->state_sz = SHA512_DIGEST_SIZE;
 	return 0;
 }
-- 
cgit v1.2.3


From 6246987932a52c2676a3bab7d624a607aa228e59 Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:21:56 +0200
Subject: crypto: inside-secure - ecb(des3_ede) and cbc(des3_ede) support

This patch adds support for two new algorithms in the Inside Secure
SafeXcel cryptographic engine driver: ecb(des3_ede) and cbc(des3_ede).

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        |   3 +
 drivers/crypto/inside-secure/safexcel.h        |   3 +
 drivers/crypto/inside-secure/safexcel_cipher.c | 114 +++++++++++++++++++++++++
 3 files changed, 120 insertions(+)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index b2809bbd8303..7bfdba1ada26 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -406,6 +406,7 @@ static int safexcel_hw_init(struct safexcel_crypto_priv *priv)
 		val |= EIP197_PROTOCOL_ENCRYPT_ONLY | EIP197_PROTOCOL_HASH_ONLY;
 		val |= EIP197_PROTOCOL_ENCRYPT_HASH | EIP197_PROTOCOL_HASH_DECRYPT;
 		val |= EIP197_ALG_DES_ECB | EIP197_ALG_DES_CBC;
+		val |= EIP197_ALG_3DES_ECB | EIP197_ALG_3DES_CBC;
 		val |= EIP197_ALG_AES_ECB | EIP197_ALG_AES_CBC;
 		val |= EIP197_ALG_MD5 | EIP197_ALG_HMAC_MD5;
 		val |= EIP197_ALG_SHA1 | EIP197_ALG_HMAC_SHA1;
@@ -843,6 +844,8 @@ static int safexcel_request_ring_irq(struct platform_device *pdev, const char *n
 static struct safexcel_alg_template *safexcel_algs[] = {
 	&safexcel_alg_ecb_des,
 	&safexcel_alg_cbc_des,
+	&safexcel_alg_ecb_des3_ede,
+	&safexcel_alg_cbc_des3_ede,
 	&safexcel_alg_ecb_aes,
 	&safexcel_alg_cbc_aes,
 	&safexcel_alg_md5,
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 31d4fd259229..839f63ef1556 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -312,6 +312,7 @@ struct safexcel_context_record {
 #define CONTEXT_CONTROL_SIZE(n)			((n) << 8)
 #define CONTEXT_CONTROL_KEY_EN			BIT(16)
 #define CONTEXT_CONTROL_CRYPTO_ALG_DES		(0x0 << 17)
+#define CONTEXT_CONTROL_CRYPTO_ALG_3DES		(0x2 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES128	(0x5 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES192	(0x6 << 17)
 #define CONTEXT_CONTROL_CRYPTO_ALG_AES256	(0x7 << 17)
@@ -694,6 +695,8 @@ int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
 /* available algorithms */
 extern struct safexcel_alg_template safexcel_alg_ecb_des;
 extern struct safexcel_alg_template safexcel_alg_cbc_des;
+extern struct safexcel_alg_template safexcel_alg_ecb_des3_ede;
+extern struct safexcel_alg_template safexcel_alg_cbc_des3_ede;
 extern struct safexcel_alg_template safexcel_alg_ecb_aes;
 extern struct safexcel_alg_template safexcel_alg_cbc_aes;
 extern struct safexcel_alg_template safexcel_alg_md5;
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index e27b689ee641..e175d0bf69d8 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -30,6 +30,7 @@ enum safexcel_cipher_direction {
 
 enum safexcel_cipher_alg {
 	SAFEXCEL_DES,
+	SAFEXCEL_3DES,
 	SAFEXCEL_AES,
 };
 
@@ -70,6 +71,12 @@ static void safexcel_skcipher_token(struct safexcel_cipher_ctx *ctx, u8 *iv,
 			memcpy(cdesc->control_data.token, iv, DES_BLOCK_SIZE);
 			cdesc->control_data.options |= EIP197_OPTION_2_TOKEN_IV_CMD;
 			break;
+		case SAFEXCEL_3DES:
+			offset = DES3_EDE_BLOCK_SIZE / sizeof(u32);
+			memcpy(cdesc->control_data.token, iv, DES3_EDE_BLOCK_SIZE);
+			cdesc->control_data.options |= EIP197_OPTION_2_TOKEN_IV_CMD;
+			break;
+
 		case SAFEXCEL_AES:
 			offset = AES_BLOCK_SIZE / sizeof(u32);
 			memcpy(cdesc->control_data.token, iv, AES_BLOCK_SIZE);
@@ -287,6 +294,8 @@ static int safexcel_context_control(struct safexcel_cipher_ctx *ctx,
 
 	if (ctx->alg == SAFEXCEL_DES) {
 		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_DES;
+	} else if (ctx->alg == SAFEXCEL_3DES) {
+		cdesc->control_data.control0 |= CONTEXT_CONTROL_CRYPTO_ALG_3DES;
 	} else if (ctx->alg == SAFEXCEL_AES) {
 		switch (ctx->key_len) {
 		case AES_KEYSIZE_128:
@@ -1030,6 +1039,111 @@ struct safexcel_alg_template safexcel_alg_ecb_des = {
 		},
 	},
 };
+
+static int safexcel_cbc_des3_ede_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_3DES);
+}
+
+static int safexcel_cbc_des3_ede_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_CBC,
+			SAFEXCEL_3DES);
+}
+
+static int safexcel_des3_ede_setkey(struct crypto_skcipher *ctfm,
+				   const u8 *key, unsigned int len)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(ctfm);
+	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	if (len != DES3_EDE_KEY_SIZE) {
+		crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_RES_BAD_KEY_LEN);
+		return -EINVAL;
+	}
+
+	/* if context exits and key changed, need to invalidate it */
+	if (ctx->base.ctxr_dma) {
+		if (memcmp(ctx->key, key, len))
+			ctx->base.needs_inv = true;
+	}
+
+	memcpy(ctx->key, key, len);
+
+	ctx->key_len = len;
+
+	return 0;
+}
+
+struct safexcel_alg_template safexcel_alg_cbc_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des3_ede_setkey,
+		.encrypt = safexcel_cbc_des3_ede_encrypt,
+		.decrypt = safexcel_cbc_des3_ede_decrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.base = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "safexcel-cbc-des3_ede",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
+static int safexcel_ecb_des3_ede_encrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_ENCRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_3DES);
+}
+
+static int safexcel_ecb_des3_ede_decrypt(struct skcipher_request *req)
+{
+	return safexcel_queue_req(&req->base, skcipher_request_ctx(req),
+			SAFEXCEL_DECRYPT, CONTEXT_CONTROL_CRYPTO_MODE_ECB,
+			SAFEXCEL_3DES);
+}
+
+struct safexcel_alg_template safexcel_alg_ecb_des3_ede = {
+	.type = SAFEXCEL_ALG_TYPE_SKCIPHER,
+	.engines = EIP97IES | EIP197B | EIP197D,
+	.alg.skcipher = {
+		.setkey = safexcel_des3_ede_setkey,
+		.encrypt = safexcel_ecb_des3_ede_encrypt,
+		.decrypt = safexcel_ecb_des3_ede_decrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+		.base = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "safexcel-ecb-des3_ede",
+			.cra_priority = 300,
+			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
+			.cra_alignmask = 0,
+			.cra_init = safexcel_skcipher_cra_init,
+			.cra_exit = safexcel_skcipher_cra_exit,
+			.cra_module = THIS_MODULE,
+		},
+	},
+};
+
 static int safexcel_aead_encrypt(struct aead_request *req)
 {
 	struct safexcel_cipher_req *creq = aead_request_ctx(req);
-- 
cgit v1.2.3


From 9744fec95f0674fbf67b12c42c3784dc299dc904 Mon Sep 17 00:00:00 2001
From: Ofer Heifetz <oferh@marvell.com>
Date: Thu, 28 Jun 2018 17:21:57 +0200
Subject: crypto: inside-secure - remove request list to improve performance

This patch main goal is to improve driver performance by moving the
crypto request from a list to a RDR ring shadow.

This is possible since there is one producer and one consume for this
RDR request shadow and one ring descriptor is left unused.
Doing this change eliminates the use of spinlock when accessing the
descriptor ring and the need to dynamicaly allocate memory per crypto
request.

The crypto request is placed in the first RDR shadow descriptor only
if there are enough descriptors, when the result handler is invoked,
it fetches the first result descriptor from RDR shadow.

Signed-off-by: Ofer Heifetz <oferh@marvell.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        | 91 +++++++++++++-------------
 drivers/crypto/inside-secure/safexcel.h        | 31 +++++----
 drivers/crypto/inside-secure/safexcel_cipher.c | 39 ++++-------
 drivers/crypto/inside-secure/safexcel_hash.c   | 31 +++------
 drivers/crypto/inside-secure/safexcel_ring.c   | 48 ++++++++++----
 5 files changed, 119 insertions(+), 121 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index 7bfdba1ada26..bd3635cb1e50 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -509,7 +509,6 @@ void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
 {
 	struct crypto_async_request *req, *backlog;
 	struct safexcel_context *ctx;
-	struct safexcel_request *request;
 	int ret, nreq = 0, cdesc = 0, rdesc = 0, commands, results;
 
 	/* If a request wasn't properly dequeued because of a lack of resources,
@@ -533,16 +532,10 @@ void safexcel_dequeue(struct safexcel_crypto_priv *priv, int ring)
 		}
 
 handle_req:
-		request = kzalloc(sizeof(*request), EIP197_GFP_FLAGS(*req));
-		if (!request)
-			goto request_failed;
-
 		ctx = crypto_tfm_ctx(req->tfm);
-		ret = ctx->send(req, ring, request, &commands, &results);
-		if (ret) {
-			kfree(request);
+		ret = ctx->send(req, ring, &commands, &results);
+		if (ret)
 			goto request_failed;
-		}
 
 		if (backlog)
 			backlog->complete(backlog, -EINPROGRESS);
@@ -551,14 +544,8 @@ handle_req:
 		 * to the engine because the input data was cached, continue to
 		 * dequeue other requests as this is valid and not an error.
 		 */
-		if (!commands && !results) {
-			kfree(request);
+		if (!commands && !results)
 			continue;
-		}
-
-		spin_lock_bh(&priv->ring[ring].egress_lock);
-		list_add_tail(&request->list, &priv->ring[ring].list);
-		spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 		cdesc += commands;
 		rdesc += results;
@@ -576,7 +563,7 @@ finalize:
 	if (!nreq)
 		return;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
+	spin_lock_bh(&priv->ring[ring].lock);
 
 	priv->ring[ring].requests += nreq;
 
@@ -585,7 +572,7 @@ finalize:
 		priv->ring[ring].busy = true;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	spin_unlock_bh(&priv->ring[ring].lock);
 
 	/* let the RDR know we have pending descriptors */
 	writel((rdesc * priv->config.rd_offset) << 2,
@@ -617,6 +604,24 @@ inline int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
 	return -EINVAL;
 }
 
+inline void safexcel_rdr_req_set(struct safexcel_crypto_priv *priv,
+				 int ring,
+				 struct safexcel_result_desc *rdesc,
+				 struct crypto_async_request *req)
+{
+	int i = safexcel_ring_rdr_rdesc_index(priv, ring, rdesc);
+
+	priv->ring[ring].rdr_req[i] = req;
+}
+
+inline struct crypto_async_request *
+safexcel_rdr_req_get(struct safexcel_crypto_priv *priv, int ring)
+{
+	int i = safexcel_ring_first_rdr_index(priv, ring);
+
+	return priv->ring[ring].rdr_req[i];
+}
+
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring)
 {
 	struct safexcel_command_desc *cdesc;
@@ -645,21 +650,16 @@ void safexcel_inv_complete(struct crypto_async_request *req, int error)
 
 int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      struct safexcel_crypto_priv *priv,
-			      dma_addr_t ctxr_dma, int ring,
-			      struct safexcel_request *request)
+			      dma_addr_t ctxr_dma, int ring)
 {
 	struct safexcel_command_desc *cdesc;
 	struct safexcel_result_desc *rdesc;
 	int ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
-
 	/* Prepare command descriptor */
 	cdesc = safexcel_add_cdesc(priv, ring, true, true, 0, 0, 0, ctxr_dma);
-	if (IS_ERR(cdesc)) {
-		ret = PTR_ERR(cdesc);
-		goto unlock;
-	}
+	if (IS_ERR(cdesc))
+		return PTR_ERR(cdesc);
 
 	cdesc->control_data.type = EIP197_TYPE_EXTENDED;
 	cdesc->control_data.options = 0;
@@ -674,21 +674,20 @@ int safexcel_invalidate_cache(struct crypto_async_request *async,
 		goto cdesc_rollback;
 	}
 
-	request->req = async;
-	goto unlock;
+	safexcel_rdr_req_set(priv, ring, rdesc, async);
+
+	return ret;
 
 cdesc_rollback:
 	safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
 
-unlock:
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 	return ret;
 }
 
 static inline void safexcel_handle_result_descriptor(struct safexcel_crypto_priv *priv,
 						     int ring)
 {
-	struct safexcel_request *sreq;
+	struct crypto_async_request *req;
 	struct safexcel_context *ctx;
 	int ret, i, nreq, ndesc, tot_descs, handled = 0;
 	bool should_complete;
@@ -703,28 +702,22 @@ handle_results:
 		goto requests_left;
 
 	for (i = 0; i < nreq; i++) {
-		spin_lock_bh(&priv->ring[ring].egress_lock);
-		sreq = list_first_entry(&priv->ring[ring].list,
-					struct safexcel_request, list);
-		list_del(&sreq->list);
-		spin_unlock_bh(&priv->ring[ring].egress_lock);
-
-		ctx = crypto_tfm_ctx(sreq->req->tfm);
-		ndesc = ctx->handle_result(priv, ring, sreq->req,
+		req = safexcel_rdr_req_get(priv, ring);
+
+		ctx = crypto_tfm_ctx(req->tfm);
+		ndesc = ctx->handle_result(priv, ring, req,
 					   &should_complete, &ret);
 		if (ndesc < 0) {
-			kfree(sreq);
 			dev_err(priv->dev, "failed to handle result (%d)", ndesc);
 			goto acknowledge;
 		}
 
 		if (should_complete) {
 			local_bh_disable();
-			sreq->req->complete(sreq->req, ret);
+			req->complete(req, ret);
 			local_bh_enable();
 		}
 
-		kfree(sreq);
 		tot_descs += ndesc;
 		handled++;
 	}
@@ -743,7 +736,7 @@ acknowledge:
 		goto handle_results;
 
 requests_left:
-	spin_lock_bh(&priv->ring[ring].egress_lock);
+	spin_lock_bh(&priv->ring[ring].lock);
 
 	priv->ring[ring].requests -= handled;
 	safexcel_try_push_requests(priv, ring);
@@ -751,7 +744,7 @@ requests_left:
 	if (!priv->ring[ring].requests)
 		priv->ring[ring].busy = false;
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	spin_unlock_bh(&priv->ring[ring].lock);
 }
 
 static void safexcel_dequeue_work(struct work_struct *work)
@@ -1073,6 +1066,14 @@ static int safexcel_probe(struct platform_device *pdev)
 		if (ret)
 			goto err_reg_clk;
 
+		priv->ring[i].rdr_req = devm_kzalloc(dev,
+			sizeof(priv->ring[i].rdr_req) * EIP197_DEFAULT_RING_SIZE,
+			GFP_KERNEL);
+		if (!priv->ring[i].rdr_req) {
+			ret = -ENOMEM;
+			goto err_reg_clk;
+		}
+
 		ring_irq = devm_kzalloc(dev, sizeof(*ring_irq), GFP_KERNEL);
 		if (!ring_irq) {
 			ret = -ENOMEM;
@@ -1108,9 +1109,7 @@ static int safexcel_probe(struct platform_device *pdev)
 		crypto_init_queue(&priv->ring[i].queue,
 				  EIP197_DEFAULT_RING_SIZE);
 
-		INIT_LIST_HEAD(&priv->ring[i].list);
 		spin_lock_init(&priv->ring[i].lock);
-		spin_lock_init(&priv->ring[i].egress_lock);
 		spin_lock_init(&priv->ring[i].queue_lock);
 	}
 
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 839f63ef1556..2f2834e67608 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -512,8 +512,7 @@ struct safexcel_desc_ring {
 	void *write;
 	void *read;
 
-	/* number of elements used in the ring */
-	unsigned nr;
+	/* descriptor element offset */
 	unsigned offset;
 };
 
@@ -523,11 +522,6 @@ enum safexcel_alg_type {
 	SAFEXCEL_ALG_TYPE_AHASH,
 };
 
-struct safexcel_request {
-	struct list_head list;
-	struct crypto_async_request *req;
-};
-
 struct safexcel_config {
 	u32 pes;
 	u32 rings;
@@ -547,9 +541,7 @@ struct safexcel_work_data {
 
 struct safexcel_ring {
 	spinlock_t lock;
-	spinlock_t egress_lock;
 
-	struct list_head list;
 	struct workqueue_struct *workqueue;
 	struct safexcel_work_data work_data;
 
@@ -557,6 +549,9 @@ struct safexcel_ring {
 	struct safexcel_desc_ring cdr;
 	struct safexcel_desc_ring rdr;
 
+	/* result ring crypto API request */
+	struct crypto_async_request **rdr_req;
+
 	/* queue */
 	struct crypto_queue queue;
 	spinlock_t queue_lock;
@@ -618,8 +613,7 @@ struct safexcel_crypto_priv {
 
 struct safexcel_context {
 	int (*send)(struct crypto_async_request *req, int ring,
-		    struct safexcel_request *request, int *commands,
-		    int *results);
+		    int *commands, int *results);
 	int (*handle_result)(struct safexcel_crypto_priv *priv, int ring,
 			     struct crypto_async_request *req, bool *complete,
 			     int *ret);
@@ -668,14 +662,14 @@ int safexcel_rdesc_check_errors(struct safexcel_crypto_priv *priv,
 void safexcel_complete(struct safexcel_crypto_priv *priv, int ring);
 int safexcel_invalidate_cache(struct crypto_async_request *async,
 			      struct safexcel_crypto_priv *priv,
-			      dma_addr_t ctxr_dma, int ring,
-			      struct safexcel_request *request);
+			      dma_addr_t ctxr_dma, int ring);
 int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
 				   struct safexcel_desc_ring *cdr,
 				   struct safexcel_desc_ring *rdr);
 int safexcel_select_ring(struct safexcel_crypto_priv *priv);
 void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
 			      struct safexcel_desc_ring *ring);
+void *safexcel_ring_first_rptr(struct safexcel_crypto_priv *priv, int  ring);
 void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
 				 struct safexcel_desc_ring *ring);
 struct safexcel_command_desc *safexcel_add_cdesc(struct safexcel_crypto_priv *priv,
@@ -688,6 +682,17 @@ struct safexcel_result_desc *safexcel_add_rdesc(struct safexcel_crypto_priv *pri
 						 int ring_id,
 						bool first, bool last,
 						dma_addr_t data, u32 len);
+int safexcel_ring_first_rdr_index(struct safexcel_crypto_priv *priv,
+				  int ring);
+int safexcel_ring_rdr_rdesc_index(struct safexcel_crypto_priv *priv,
+				  int ring,
+				  struct safexcel_result_desc *rdesc);
+void safexcel_rdr_req_set(struct safexcel_crypto_priv *priv,
+			  int ring,
+			  struct safexcel_result_desc *rdesc,
+			  struct crypto_async_request *req);
+inline struct crypto_async_request *
+safexcel_rdr_req_get(struct safexcel_crypto_priv *priv, int ring);
 void safexcel_inv_complete(struct crypto_async_request *req, int error);
 int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
 			 void *istate, void *ostate);
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index e175d0bf69d8..9d292427a488 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -336,7 +336,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	do {
 		rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 		if (IS_ERR(rdesc)) {
@@ -353,7 +352,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	} while (!rdesc->last_seg);
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (src == dst) {
 		dma_unmap_sg(priv->dev, src,
@@ -374,7 +372,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 }
 
 static int safexcel_send_req(struct crypto_async_request *base, int ring,
-			     struct safexcel_request *request,
 			     struct safexcel_cipher_req *sreq,
 			     struct scatterlist *src, struct scatterlist *dst,
 			     unsigned int cryptlen, unsigned int assoclen,
@@ -384,7 +381,7 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring,
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct safexcel_command_desc *cdesc;
-	struct safexcel_result_desc *rdesc;
+	struct safexcel_result_desc *rdesc, *first_rdesc;
 	struct scatterlist *sg;
 	unsigned int totlen = cryptlen + assoclen;
 	int nr_src, nr_dst, n_cdesc = 0, n_rdesc = 0, queued = totlen;
@@ -424,8 +421,6 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring,
 		       ctx->opad, ctx->state_sz);
 	}
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
-
 	/* command descriptors */
 	for_each_sg(src, sg, nr_src, i) {
 		int len = sg_dma_len(sg);
@@ -472,12 +467,12 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring,
 			ret = PTR_ERR(rdesc);
 			goto rdesc_rollback;
 		}
+		if (first)
+			first_rdesc = rdesc;
 		n_rdesc++;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
-
-	request->req = base;
+	safexcel_rdr_req_set(priv, ring, first_rdesc, base);
 
 	*commands = n_cdesc;
 	*results = n_rdesc;
@@ -490,8 +485,6 @@ cdesc_rollback:
 	for (i = 0; i < n_cdesc; i++)
 		safexcel_ring_rollback_wptr(priv, &priv->ring[ring].cdr);
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
-
 	if (src == dst) {
 		dma_unmap_sg(priv->dev, src,
 			     sg_nents_for_len(src, totlen),
@@ -519,7 +512,6 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	do {
 		rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 		if (IS_ERR(rdesc)) {
@@ -536,7 +528,6 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 	} while (!rdesc->last_seg);
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (ctx->base.exit_inv) {
 		dma_pool_free(priv->context_pool, ctx->base.ctxr,
@@ -612,15 +603,13 @@ static int safexcel_aead_handle_result(struct safexcel_crypto_priv *priv,
 }
 
 static int safexcel_cipher_send_inv(struct crypto_async_request *base,
-				    int ring, struct safexcel_request *request,
-				    int *commands, int *results)
+				    int ring, int *commands, int *results)
 {
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	int ret;
 
-	ret = safexcel_invalidate_cache(base, priv, ctx->base.ctxr_dma, ring,
-					request);
+	ret = safexcel_invalidate_cache(base, priv, ctx->base.ctxr_dma, ring);
 	if (unlikely(ret))
 		return ret;
 
@@ -631,7 +620,6 @@ static int safexcel_cipher_send_inv(struct crypto_async_request *base,
 }
 
 static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
-				  struct safexcel_request *request,
 				  int *commands, int *results)
 {
 	struct skcipher_request *req = skcipher_request_cast(async);
@@ -643,18 +631,16 @@ static int safexcel_skcipher_send(struct crypto_async_request *async, int ring,
 	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && sreq->needs_inv);
 
 	if (sreq->needs_inv)
-		ret = safexcel_cipher_send_inv(async, ring, request, commands,
-					       results);
+		ret = safexcel_cipher_send_inv(async, ring, commands, results);
 	else
-		ret = safexcel_send_req(async, ring, request, sreq, req->src,
+		ret = safexcel_send_req(async, ring, sreq, req->src,
 					req->dst, req->cryptlen, 0, 0, req->iv,
 					commands, results);
 	return ret;
 }
 
 static int safexcel_aead_send(struct crypto_async_request *async, int ring,
-			      struct safexcel_request *request, int *commands,
-			      int *results)
+			      int *commands, int *results)
 {
 	struct aead_request *req = aead_request_cast(async);
 	struct crypto_aead *tfm = crypto_aead_reqtfm(req);
@@ -666,11 +652,10 @@ static int safexcel_aead_send(struct crypto_async_request *async, int ring,
 	BUG_ON(!(priv->flags & EIP197_TRC_CACHE) && sreq->needs_inv);
 
 	if (sreq->needs_inv)
-		ret = safexcel_cipher_send_inv(async, ring, request, commands,
-					       results);
+		ret = safexcel_cipher_send_inv(async, ring, commands, results);
 	else
-		ret = safexcel_send_req(async, ring, request, sreq, req->src,
-					req->dst, req->cryptlen, req->assoclen,
+		ret = safexcel_send_req(async, ring, sreq, req->src, req->dst,
+					req->cryptlen, req->assoclen,
 					crypto_aead_authsize(tfm), req->iv,
 					commands, results);
 	return ret;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 46aac55c0b31..83bd49d1249b 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -160,7 +160,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 	if (IS_ERR(rdesc)) {
 		dev_err(priv->dev,
@@ -171,7 +170,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 	}
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (sreq->nents) {
 		dma_unmap_sg(priv->dev, areq->src, sreq->nents, DMA_TO_DEVICE);
@@ -204,7 +202,6 @@ static int safexcel_handle_req_result(struct safexcel_crypto_priv *priv, int rin
 }
 
 static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
-				   struct safexcel_request *request,
 				   int *commands, int *results)
 {
 	struct ahash_request *areq = ahash_request_cast(async);
@@ -251,16 +248,12 @@ static int safexcel_ahash_send_req(struct crypto_async_request *async, int ring,
 		}
 	}
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
-
 	/* Add a command descriptor for the cached data, if any */
 	if (cache_len) {
 		req->cache_dma = dma_map_single(priv->dev, req->cache,
 						cache_len, DMA_TO_DEVICE);
-		if (dma_mapping_error(priv->dev, req->cache_dma)) {
-			spin_unlock_bh(&priv->ring[ring].egress_lock);
+		if (dma_mapping_error(priv->dev, req->cache_dma))
 			return -EINVAL;
-		}
 
 		req->cache_sz = cache_len;
 		first_cdesc = safexcel_add_cdesc(priv, ring, 1,
@@ -333,14 +326,12 @@ send_command:
 		goto unmap_result;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
+	safexcel_rdr_req_set(priv, ring, rdesc, &areq->base);
 
 	req->processed[0] += len;
 	if (req->processed[0] < len)
 		req->processed[1]++;
 
-	request->req = &areq->base;
-
 	*commands = n_cdesc;
 	*results = 1;
 	return 0;
@@ -360,7 +351,6 @@ unmap_cache:
 		req->cache_sz = 0;
 	}
 
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 	return ret;
 }
 
@@ -398,7 +388,6 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 
 	*ret = 0;
 
-	spin_lock_bh(&priv->ring[ring].egress_lock);
 	rdesc = safexcel_ring_next_rptr(priv, &priv->ring[ring].rdr);
 	if (IS_ERR(rdesc)) {
 		dev_err(priv->dev,
@@ -409,7 +398,6 @@ static int safexcel_handle_inv_result(struct safexcel_crypto_priv *priv,
 	}
 
 	safexcel_complete(priv, ring);
-	spin_unlock_bh(&priv->ring[ring].egress_lock);
 
 	if (ctx->base.exit_inv) {
 		dma_pool_free(priv->context_pool, ctx->base.ctxr,
@@ -460,15 +448,14 @@ static int safexcel_handle_result(struct safexcel_crypto_priv *priv, int ring,
 }
 
 static int safexcel_ahash_send_inv(struct crypto_async_request *async,
-				   int ring, struct safexcel_request *request,
-				   int *commands, int *results)
+				   int ring, int *commands, int *results)
 {
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct safexcel_ahash_ctx *ctx = crypto_ahash_ctx(crypto_ahash_reqtfm(areq));
 	int ret;
 
 	ret = safexcel_invalidate_cache(async, ctx->priv,
-					ctx->base.ctxr_dma, ring, request);
+					ctx->base.ctxr_dma, ring);
 	if (unlikely(ret))
 		return ret;
 
@@ -479,19 +466,17 @@ static int safexcel_ahash_send_inv(struct crypto_async_request *async,
 }
 
 static int safexcel_ahash_send(struct crypto_async_request *async,
-			       int ring, struct safexcel_request *request,
-			       int *commands, int *results)
+			       int ring, int *commands, int *results)
 {
 	struct ahash_request *areq = ahash_request_cast(async);
 	struct safexcel_ahash_req *req = ahash_request_ctx(areq);
 	int ret;
 
 	if (req->needs_inv)
-		ret = safexcel_ahash_send_inv(async, ring, request,
-					      commands, results);
+		ret = safexcel_ahash_send_inv(async, ring, commands, results);
 	else
-		ret = safexcel_ahash_send_req(async, ring, request,
-					      commands, results);
+		ret = safexcel_ahash_send_req(async, ring, commands, results);
+
 	return ret;
 }
 
diff --git a/drivers/crypto/inside-secure/safexcel_ring.c b/drivers/crypto/inside-secure/safexcel_ring.c
index cfd843b834f1..a1e81cfdc1f1 100644
--- a/drivers/crypto/inside-secure/safexcel_ring.c
+++ b/drivers/crypto/inside-secure/safexcel_ring.c
@@ -24,7 +24,7 @@ int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
 	if (!cdr->base)
 		return -ENOMEM;
 	cdr->write = cdr->base;
-	cdr->base_end = cdr->base + cdr->offset * EIP197_DEFAULT_RING_SIZE;
+	cdr->base_end = cdr->base + cdr->offset * (EIP197_DEFAULT_RING_SIZE - 1);
 	cdr->read = cdr->base;
 
 	rdr->offset = sizeof(u32) * priv->config.rd_offset;
@@ -34,7 +34,7 @@ int safexcel_init_ring_descriptors(struct safexcel_crypto_priv *priv,
 	if (!rdr->base)
 		return -ENOMEM;
 	rdr->write = rdr->base;
-	rdr->base_end = rdr->base + rdr->offset * EIP197_DEFAULT_RING_SIZE;
+	rdr->base_end = rdr->base + rdr->offset  * (EIP197_DEFAULT_RING_SIZE - 1);
 	rdr->read = rdr->base;
 
 	return 0;
@@ -50,14 +50,15 @@ static void *safexcel_ring_next_wptr(struct safexcel_crypto_priv *priv,
 {
 	void *ptr = ring->write;
 
-	if (ring->nr == EIP197_DEFAULT_RING_SIZE - 1)
+	if ((ring->write == ring->read - ring->offset) ||
+	    (ring->read == ring->base && ring->write == ring->base_end))
 		return ERR_PTR(-ENOMEM);
 
-	ring->write += ring->offset;
 	if (ring->write == ring->base_end)
 		ring->write = ring->base;
+	else
+		ring->write += ring->offset;
 
-	ring->nr++;
 	return ptr;
 }
 
@@ -66,29 +67,52 @@ void *safexcel_ring_next_rptr(struct safexcel_crypto_priv *priv,
 {
 	void *ptr = ring->read;
 
-	if (!ring->nr)
+	if (ring->write == ring->read)
 		return ERR_PTR(-ENOENT);
 
-	ring->read += ring->offset;
 	if (ring->read == ring->base_end)
 		ring->read = ring->base;
+	else
+		ring->read += ring->offset;
 
-	ring->nr--;
 	return ptr;
 }
 
+inline void *safexcel_ring_curr_rptr(struct safexcel_crypto_priv *priv,
+				     int ring)
+{
+	struct safexcel_desc_ring *rdr = &priv->ring[ring].rdr;
+
+	return rdr->read;
+}
+
+inline int safexcel_ring_first_rdr_index(struct safexcel_crypto_priv *priv,
+					 int ring)
+{
+	struct safexcel_desc_ring *rdr = &priv->ring[ring].rdr;
+
+	return (rdr->read - rdr->base) / rdr->offset;
+}
+
+inline int safexcel_ring_rdr_rdesc_index(struct safexcel_crypto_priv *priv,
+					 int ring,
+					 struct safexcel_result_desc *rdesc)
+{
+	struct safexcel_desc_ring *rdr = &priv->ring[ring].rdr;
+
+	return ((void *)rdesc - rdr->base) / rdr->offset;
+}
+
 void safexcel_ring_rollback_wptr(struct safexcel_crypto_priv *priv,
 				 struct safexcel_desc_ring *ring)
 {
-	if (!ring->nr)
+	if (ring->write == ring->read)
 		return;
 
 	if (ring->write == ring->base)
-		ring->write = ring->base_end - ring->offset;
+		ring->write = ring->base_end;
 	else
 		ring->write -= ring->offset;
-
-	ring->nr--;
 }
 
 struct safexcel_command_desc *safexcel_add_cdesc(struct safexcel_crypto_priv *priv,
-- 
cgit v1.2.3


From af839b4e546613aed1fbd64def73956aa98631e7 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 29 Jun 2018 14:14:35 -0700
Subject: crypto: x86/sha256-mb - fix digest copy in
 sha256_mb_mgr_get_comp_job_avx2()

There is a copy-paste error where sha256_mb_mgr_get_comp_job_avx2()
copies the SHA-256 digest state from sha256_mb_mgr::args::digest to
job_sha256::result_digest.  Consequently, the sha256_mb algorithm
sometimes calculates the wrong digest.  Fix it.

Reproducer using AF_ALG:

    #include <assert.h>
    #include <linux/if_alg.h>
    #include <stdio.h>
    #include <string.h>
    #include <sys/socket.h>
    #include <unistd.h>

    static const __u8 expected[32] =
        "\xad\x7f\xac\xb2\x58\x6f\xc6\xe9\x66\xc0\x04\xd7\xd1\xd1\x6b\x02"
        "\x4f\x58\x05\xff\x7c\xb4\x7c\x7a\x85\xda\xbd\x8b\x48\x89\x2c\xa7";

    int main()
    {
        int fd;
        struct sockaddr_alg addr = {
            .salg_type = "hash",
            .salg_name = "sha256_mb",
        };
        __u8 data[4096] = { 0 };
        __u8 digest[32];
        int ret;
        int i;

        fd = socket(AF_ALG, SOCK_SEQPACKET, 0);
        bind(fd, (void *)&addr, sizeof(addr));
        fork();
        fd = accept(fd, 0, 0);
        do {
            ret = write(fd, data, 4096);
            assert(ret == 4096);
            ret = read(fd, digest, 32);
            assert(ret == 32);
        } while (memcmp(digest, expected, 32) == 0);

        printf("wrong digest: ");
        for (i = 0; i < 32; i++)
            printf("%02x", digest[i]);
        printf("\n");
    }

Output was:

    wrong digest: ad7facb2000000000000000000000000ffffffef7cb47c7a85dabd8b48892ca7

Fixes: 172b1d6b5a93 ("crypto: sha256-mb - fix ctx pointer and digest copy")
Cc: <stable@vger.kernel.org> # v4.8+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
index 16c4ccb1f154..d2364c55bbde 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
+++ b/arch/x86/crypto/sha256-mb/sha256_mb_mgr_flush_avx2.S
@@ -265,7 +265,7 @@ ENTRY(sha256_mb_mgr_get_comp_job_avx2)
 	vpinsrd	$1, _args_digest+1*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$2, _args_digest+2*32(state, idx, 4), %xmm0, %xmm0
 	vpinsrd	$3, _args_digest+3*32(state, idx, 4), %xmm0, %xmm0
-	vmovd   _args_digest(state , idx, 4) , %xmm0
+	vmovd	_args_digest+4*32(state, idx, 4), %xmm1
 	vpinsrd	$1, _args_digest+5*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$2, _args_digest+6*32(state, idx, 4), %xmm1, %xmm1
 	vpinsrd	$3, _args_digest+7*32(state, idx, 4), %xmm1, %xmm1
-- 
cgit v1.2.3


From 26ec38872b5bc2105037f7a03fdd72afdf9fd241 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 29 Jun 2018 14:21:11 -0700
Subject: crypto: MAINTAINERS - fix file path for SHA multibuffer code

"arch/x86/crypto/sha*-mb" needs a trailing slash, since it refers to
directories.  Otherwise get_maintainer.pl doesn't find the entry.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9d5eeff51b5f..bfcd5a7a83c8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7350,7 +7350,7 @@ M:	Megha Dey <megha.dey@linux.intel.com>
 R:	Tim Chen <tim.c.chen@linux.intel.com>
 L:	linux-crypto@vger.kernel.org
 S:	Supported
-F:	arch/x86/crypto/sha*-mb
+F:	arch/x86/crypto/sha*-mb/
 F:	crypto/mcryptd.c
 
 INTEL TELEMETRY DRIVER
-- 
cgit v1.2.3


From 90ef3e4835c33541f2eca0b4276fbc1dd83832d8 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 29 Jun 2018 17:01:41 -0700
Subject: crypto: sha1_generic - add cra_priority

sha1-generic had a cra_priority of 0, so it wasn't possible to have a
lower priority SHA-1 implementation, as is desired for sha1_mb which is
only useful under certain workloads and is otherwise extremely slow.
Change it to priority 100, which is the priority used for many of the
other generic algorithms.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/sha1_generic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index 6877cbb9105f..a3d701632ca2 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -76,6 +76,7 @@ static struct shash_alg alg = {
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-generic",
+		.cra_priority	=	100,
 		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
-- 
cgit v1.2.3


From b73b7ac0a77492b1bd671a72787931847b330c03 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 29 Jun 2018 17:01:42 -0700
Subject: crypto: sha256_generic - add cra_priority

sha256-generic and sha224-generic had a cra_priority of 0, so it wasn't
possible to have a lower priority SHA-256 or SHA-224 implementation, as
is desired for sha256_mb which is only useful under certain workloads
and is otherwise extremely slow.  Change them to priority 100, which is
the priority used for many of the other generic algorithms.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/sha256_generic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index 8f9c47e1a96e..dfcb7beb73a7 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -271,6 +271,7 @@ static struct shash_alg sha256_algs[2] = { {
 	.base		=	{
 		.cra_name	=	"sha256",
 		.cra_driver_name=	"sha256-generic",
+		.cra_priority	=	100,
 		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
@@ -285,6 +286,7 @@ static struct shash_alg sha256_algs[2] = { {
 	.base		=	{
 		.cra_name	=	"sha224",
 		.cra_driver_name=	"sha224-generic",
+		.cra_priority	=	100,
 		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
-- 
cgit v1.2.3


From e47890163a3c2a6ec5a18322d283046d1bdec5e6 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 29 Jun 2018 17:01:43 -0700
Subject: crypto: sha512_generic - add cra_priority

sha512-generic and sha384-generic had a cra_priority of 0, so it wasn't
possible to have a lower priority SHA-512 or SHA-384 implementation, as
is desired for sha512_mb which is only useful under certain workloads
and is otherwise extremely slow.  Change them to priority 100, which is
the priority used for many of the other generic algorithms.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/sha512_generic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 0b805d03b5e5..55377b1cba6b 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -193,6 +193,7 @@ static struct shash_alg sha512_algs[2] = { {
 	.base		=	{
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-generic",
+		.cra_priority	=	100,
 		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
@@ -207,6 +208,7 @@ static struct shash_alg sha512_algs[2] = { {
 	.base		=	{
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-generic",
+		.cra_priority	=	100,
 		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
-- 
cgit v1.2.3


From 8aeef492fe248e0e56d888e2d5432724ac45f80d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 29 Jun 2018 17:01:44 -0700
Subject: crypto: x86/sha-mb - decrease priority of multibuffer algorithms

With all the crypto modules enabled on x86, and with a CPU that supports
AVX-2 but not SHA-NI instructions (e.g. Haswell, Broadwell, Skylake),
the "multibuffer" implementations of SHA-1, SHA-256, and SHA-512 are the
highest priority.  However, these implementations only perform well when
many hash requests are being submitted concurrently, filling all 8 AVX-2
lanes.  Otherwise, they are incredibly slow, as they waste time waiting
for more requests to arrive before proceeding to execute each request.

For example, here are the speeds I see hashing 4096-byte buffers with a
single thread on a Haswell-based processor:

            generic            avx2          mb (multibuffer)
            -------            --------      ----------------
sha1        602 MB/s           997 MB/s      0.61 MB/s
sha256      228 MB/s           412 MB/s      0.61 MB/s
sha512      312 MB/s           559 MB/s      0.61 MB/s

So, the multibuffer implementation is 500 to 1000 times slower than the
other implementations.  Note that with smaller buffers or more update()s
per digest, the difference would be even greater.

I believe the vast majority of people are in the boat where the
multibuffer code is much slower, and only a small minority are doing the
highly parallel, hashing-intensive, latency-flexible workloads (maybe
IPsec on servers?) where the multibuffer code may be beneficial.  Yet,
people often aren't familiar with all the crypto config options and so
the multibuffer code may inadvertently be built into the kernel.

Also the multibuffer code apparently hasn't been very well tested,
seeing as it was sometimes computing the wrong SHA-256 digest.

So, let's make the multibuffer algorithms low priority.  Users who want
to use them can either request them explicitly by driver name, or use
NETLINK_CRYPTO (crypto_user) to increase their priority at runtime.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/x86/crypto/sha1-mb/sha1_mb.c     | 9 ++++++++-
 arch/x86/crypto/sha256-mb/sha256_mb.c | 9 ++++++++-
 arch/x86/crypto/sha512-mb/sha512_mb.c | 9 ++++++++-
 3 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/arch/x86/crypto/sha1-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c
index e17655ffde79..4b2430274935 100644
--- a/arch/x86/crypto/sha1-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb.c
@@ -871,7 +871,14 @@ static struct ahash_alg sha1_mb_async_alg = {
 		.base = {
 			.cra_name               = "sha1",
 			.cra_driver_name        = "sha1_mb",
-			.cra_priority           = 200,
+			/*
+			 * Low priority, since with few concurrent hash requests
+			 * this is extremely slow due to the flush delay.  Users
+			 * whose workloads would benefit from this can request
+			 * it explicitly by driver name, or can increase its
+			 * priority at runtime using NETLINK_CRYPTO.
+			 */
+			.cra_priority           = 50,
 			.cra_flags              = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA1_BLOCK_SIZE,
 			.cra_type               = &crypto_ahash_type,
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
index 4c46ac1b6653..4c07f6c12c37 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -870,7 +870,14 @@ static struct ahash_alg sha256_mb_async_alg = {
 		.base = {
 			.cra_name               = "sha256",
 			.cra_driver_name        = "sha256_mb",
-			.cra_priority           = 200,
+			/*
+			 * Low priority, since with few concurrent hash requests
+			 * this is extremely slow due to the flush delay.  Users
+			 * whose workloads would benefit from this can request
+			 * it explicitly by driver name, or can increase its
+			 * priority at runtime using NETLINK_CRYPTO.
+			 */
+			.cra_priority           = 50,
 			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
 							CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA256_BLOCK_SIZE,
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index 39e2bbdc1836..6a8c31581604 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -904,7 +904,14 @@ static struct ahash_alg sha512_mb_async_alg = {
 		.base = {
 			.cra_name               = "sha512",
 			.cra_driver_name        = "sha512_mb",
-			.cra_priority           = 200,
+			/*
+			 * Low priority, since with few concurrent hash requests
+			 * this is extremely slow due to the flush delay.  Users
+			 * whose workloads would benefit from this can request
+			 * it explicitly by driver name, or can increase its
+			 * priority at runtime using NETLINK_CRYPTO.
+			 */
+			.cra_priority           = 50,
 			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
 							CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA512_BLOCK_SIZE,
-- 
cgit v1.2.3


From e50944e219f908968a6e01fbd0e8811a33bd5f04 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:16:11 -0700
Subject: crypto: shash - remove useless setting of type flags

Many shash algorithms set .cra_flags = CRYPTO_ALG_TYPE_SHASH.  But this
is redundant with the C structure type ('struct shash_alg'), and
crypto_register_shash() already sets the type flag automatically,
clearing any type flag that was already there.  Apparently the useless
assignment has just been copy+pasted around.

So, remove the useless assignment from all the shash algorithms.

This patch shouldn't change any actual behavior.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/ghash-ce-glue.c                | 2 +-
 arch/arm/crypto/sha1-ce-glue.c                 | 1 -
 arch/arm/crypto/sha1_glue.c                    | 1 -
 arch/arm/crypto/sha1_neon_glue.c               | 1 -
 arch/arm/crypto/sha2-ce-glue.c                 | 2 --
 arch/arm/crypto/sha256_glue.c                  | 2 --
 arch/arm/crypto/sha256_neon_glue.c             | 2 --
 arch/arm/crypto/sha512-glue.c                  | 2 --
 arch/arm/crypto/sha512-neon-glue.c             | 2 --
 arch/arm64/crypto/aes-glue.c                   | 3 ---
 arch/arm64/crypto/ghash-ce-glue.c              | 1 -
 arch/arm64/crypto/sha1-ce-glue.c               | 1 -
 arch/arm64/crypto/sha2-ce-glue.c               | 2 --
 arch/arm64/crypto/sha256-glue.c                | 4 ----
 arch/arm64/crypto/sha3-ce-glue.c               | 4 ----
 arch/arm64/crypto/sha512-ce-glue.c             | 2 --
 arch/arm64/crypto/sha512-glue.c                | 2 --
 arch/arm64/crypto/sm3-ce-glue.c                | 1 -
 arch/mips/cavium-octeon/crypto/octeon-md5.c    | 1 -
 arch/mips/cavium-octeon/crypto/octeon-sha1.c   | 1 -
 arch/mips/cavium-octeon/crypto/octeon-sha256.c | 2 --
 arch/mips/cavium-octeon/crypto/octeon-sha512.c | 2 --
 arch/powerpc/crypto/md5-glue.c                 | 1 -
 arch/powerpc/crypto/sha1-spe-glue.c            | 1 -
 arch/powerpc/crypto/sha1.c                     | 1 -
 arch/powerpc/crypto/sha256-spe-glue.c          | 2 --
 arch/s390/crypto/ghash_s390.c                  | 1 -
 arch/s390/crypto/sha1_s390.c                   | 1 -
 arch/s390/crypto/sha256_s390.c                 | 2 --
 arch/s390/crypto/sha512_s390.c                 | 2 --
 arch/sparc/crypto/md5_glue.c                   | 1 -
 arch/sparc/crypto/sha1_glue.c                  | 1 -
 arch/sparc/crypto/sha256_glue.c                | 2 --
 arch/sparc/crypto/sha512_glue.c                | 2 --
 arch/x86/crypto/ghash-clmulni-intel_glue.c     | 3 +--
 arch/x86/crypto/poly1305_glue.c                | 1 -
 arch/x86/crypto/sha1_ssse3_glue.c              | 4 ----
 arch/x86/crypto/sha256_ssse3_glue.c            | 8 --------
 arch/x86/crypto/sha512_ssse3_glue.c            | 6 ------
 crypto/crypto_null.c                           | 1 -
 crypto/ghash-generic.c                         | 1 -
 crypto/md4.c                                   | 1 -
 crypto/md5.c                                   | 1 -
 crypto/poly1305_generic.c                      | 1 -
 crypto/rmd128.c                                | 1 -
 crypto/rmd160.c                                | 1 -
 crypto/rmd256.c                                | 1 -
 crypto/rmd320.c                                | 1 -
 crypto/sha1_generic.c                          | 1 -
 crypto/sha256_generic.c                        | 2 --
 crypto/sha3_generic.c                          | 4 ----
 crypto/sha512_generic.c                        | 2 --
 crypto/sm3_generic.c                           | 1 -
 crypto/tgr192.c                                | 3 ---
 crypto/wp512.c                                 | 3 ---
 drivers/crypto/nx/nx-aes-xcbc.c                | 1 -
 drivers/crypto/nx/nx-sha256.c                  | 1 -
 drivers/crypto/nx/nx-sha512.c                  | 1 -
 drivers/crypto/padlock-sha.c                   | 8 ++------
 drivers/crypto/vmx/ghash.c                     | 2 +-
 drivers/staging/skein/skein_generic.c          | 3 ---
 61 files changed, 5 insertions(+), 116 deletions(-)

diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index d9bb52cae2ac..f93c0761929d 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -152,7 +152,7 @@ static struct shash_alg ghash_alg = {
 		.cra_name	= "__ghash",
 		.cra_driver_name = "__driver-ghash-ce",
 		.cra_priority	= 0,
-		.cra_flags	= CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_INTERNAL,
+		.cra_flags	= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize	= GHASH_BLOCK_SIZE,
 		.cra_ctxsize	= sizeof(struct ghash_key),
 		.cra_module	= THIS_MODULE,
diff --git a/arch/arm/crypto/sha1-ce-glue.c b/arch/arm/crypto/sha1-ce-glue.c
index 555f72b5e659..b732522e20f8 100644
--- a/arch/arm/crypto/sha1-ce-glue.c
+++ b/arch/arm/crypto/sha1-ce-glue.c
@@ -75,7 +75,6 @@ static struct shash_alg alg = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sha1-ce",
 		.cra_priority		= 200,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha1_glue.c b/arch/arm/crypto/sha1_glue.c
index 6fc73bf8766d..98ab8239f919 100644
--- a/arch/arm/crypto/sha1_glue.c
+++ b/arch/arm/crypto/sha1_glue.c
@@ -67,7 +67,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-asm",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha1_neon_glue.c b/arch/arm/crypto/sha1_neon_glue.c
index 4e22f122f966..d15e0ea2c95e 100644
--- a/arch/arm/crypto/sha1_neon_glue.c
+++ b/arch/arm/crypto/sha1_neon_glue.c
@@ -83,7 +83,6 @@ static struct shash_alg alg = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sha1-neon",
 		.cra_priority		= 250,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha2-ce-glue.c b/arch/arm/crypto/sha2-ce-glue.c
index df4dcef054ae..1211a5c129fc 100644
--- a/arch/arm/crypto/sha2-ce-glue.c
+++ b/arch/arm/crypto/sha2-ce-glue.c
@@ -78,7 +78,6 @@ static struct shash_alg algs[] = { {
 		.cra_name		= "sha224",
 		.cra_driver_name	= "sha224-ce",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
@@ -93,7 +92,6 @@ static struct shash_alg algs[] = { {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "sha256-ce",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha256_glue.c b/arch/arm/crypto/sha256_glue.c
index a84e869ef900..bf8ccff2c9d0 100644
--- a/arch/arm/crypto/sha256_glue.c
+++ b/arch/arm/crypto/sha256_glue.c
@@ -71,7 +71,6 @@ static struct shash_alg algs[] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name =	"sha256-asm",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -86,7 +85,6 @@ static struct shash_alg algs[] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name =	"sha224-asm",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha256_neon_glue.c b/arch/arm/crypto/sha256_neon_glue.c
index 39ccd658817e..9bbee56fbdc8 100644
--- a/arch/arm/crypto/sha256_neon_glue.c
+++ b/arch/arm/crypto/sha256_neon_glue.c
@@ -79,7 +79,6 @@ struct shash_alg sha256_neon_algs[] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name =	"sha256-neon",
 		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -94,7 +93,6 @@ struct shash_alg sha256_neon_algs[] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name =	"sha224-neon",
 		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
index 269a394e4a53..86540cd4a6fa 100644
--- a/arch/arm/crypto/sha512-glue.c
+++ b/arch/arm/crypto/sha512-glue.c
@@ -63,7 +63,6 @@ static struct shash_alg sha512_arm_algs[] = { {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "sha384-arm",
 		.cra_priority		= 250,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
@@ -78,7 +77,6 @@ static struct shash_alg sha512_arm_algs[] = { {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "sha512-arm",
 		.cra_priority		= 250,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
index 32693684a3ab..8a5642b41fd6 100644
--- a/arch/arm/crypto/sha512-neon-glue.c
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -75,7 +75,6 @@ struct shash_alg sha512_neon_algs[] = { {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "sha384-neon",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA384_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 
@@ -91,7 +90,6 @@ struct shash_alg sha512_neon_algs[] = { {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "sha512-neon",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm64/crypto/aes-glue.c b/arch/arm64/crypto/aes-glue.c
index 253188fb8cb0..a615a9a991a3 100644
--- a/arch/arm64/crypto/aes-glue.c
+++ b/arch/arm64/crypto/aes-glue.c
@@ -567,7 +567,6 @@ static struct shash_alg mac_algs[] = { {
 	.base.cra_name		= "cmac(aes)",
 	.base.cra_driver_name	= "cmac-aes-" MODE,
 	.base.cra_priority	= PRIO,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx) +
 				  2 * AES_BLOCK_SIZE,
@@ -583,7 +582,6 @@ static struct shash_alg mac_algs[] = { {
 	.base.cra_name		= "xcbc(aes)",
 	.base.cra_driver_name	= "xcbc-aes-" MODE,
 	.base.cra_priority	= PRIO,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= AES_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx) +
 				  2 * AES_BLOCK_SIZE,
@@ -599,7 +597,6 @@ static struct shash_alg mac_algs[] = { {
 	.base.cra_name		= "cbcmac(aes)",
 	.base.cra_driver_name	= "cbcmac-aes-" MODE,
 	.base.cra_priority	= PRIO,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= 1,
 	.base.cra_ctxsize	= sizeof(struct mac_tfm_ctx),
 	.base.cra_module	= THIS_MODULE,
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 7cf0b1aa6ea8..757fae186753 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -204,7 +204,6 @@ static struct shash_alg ghash_alg = {
 	.base.cra_name		= "ghash",
 	.base.cra_driver_name	= "ghash-ce",
 	.base.cra_priority	= 200,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= GHASH_BLOCK_SIZE,
 	.base.cra_ctxsize	= sizeof(struct ghash_key),
 	.base.cra_module	= THIS_MODULE,
diff --git a/arch/arm64/crypto/sha1-ce-glue.c b/arch/arm64/crypto/sha1-ce-glue.c
index efbeb3e0dcfb..17fac2889f56 100644
--- a/arch/arm64/crypto/sha1-ce-glue.c
+++ b/arch/arm64/crypto/sha1-ce-glue.c
@@ -99,7 +99,6 @@ static struct shash_alg alg = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sha1-ce",
 		.cra_priority		= 200,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm64/crypto/sha2-ce-glue.c b/arch/arm64/crypto/sha2-ce-glue.c
index fd1ff2b13dfa..261f5195cab7 100644
--- a/arch/arm64/crypto/sha2-ce-glue.c
+++ b/arch/arm64/crypto/sha2-ce-glue.c
@@ -114,7 +114,6 @@ static struct shash_alg algs[] = { {
 		.cra_name		= "sha224",
 		.cra_driver_name	= "sha224-ce",
 		.cra_priority		= 200,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
@@ -129,7 +128,6 @@ static struct shash_alg algs[] = { {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "sha256-ce",
 		.cra_priority		= 200,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	}
diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index e8880ccdc71f..f1b4f4420ca1 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -68,7 +68,6 @@ static struct shash_alg algs[] = { {
 	.base.cra_name		= "sha256",
 	.base.cra_driver_name	= "sha256-arm64",
 	.base.cra_priority	= 100,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA256_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -81,7 +80,6 @@ static struct shash_alg algs[] = { {
 	.base.cra_name		= "sha224",
 	.base.cra_driver_name	= "sha224-arm64",
 	.base.cra_priority	= 100,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA224_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
@@ -153,7 +151,6 @@ static struct shash_alg neon_algs[] = { {
 	.base.cra_name		= "sha256",
 	.base.cra_driver_name	= "sha256-arm64-neon",
 	.base.cra_priority	= 150,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA256_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -166,7 +163,6 @@ static struct shash_alg neon_algs[] = { {
 	.base.cra_name		= "sha224",
 	.base.cra_driver_name	= "sha224-arm64-neon",
 	.base.cra_priority	= 150,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA224_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/arch/arm64/crypto/sha3-ce-glue.c b/arch/arm64/crypto/sha3-ce-glue.c
index da8222e528bd..a336feac0f59 100644
--- a/arch/arm64/crypto/sha3-ce-glue.c
+++ b/arch/arm64/crypto/sha3-ce-glue.c
@@ -105,7 +105,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-224",
 	.base.cra_driver_name	= "sha3-224-ce",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_224_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
@@ -117,7 +116,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-256",
 	.base.cra_driver_name	= "sha3-256-ce",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_256_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
@@ -129,7 +127,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-384",
 	.base.cra_driver_name	= "sha3-384-ce",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_384_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
@@ -141,7 +138,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-512",
 	.base.cra_driver_name	= "sha3-512-ce",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
diff --git a/arch/arm64/crypto/sha512-ce-glue.c b/arch/arm64/crypto/sha512-ce-glue.c
index a77c8632a589..f2c5f28c622a 100644
--- a/arch/arm64/crypto/sha512-ce-glue.c
+++ b/arch/arm64/crypto/sha512-ce-glue.c
@@ -87,7 +87,6 @@ static struct shash_alg algs[] = { {
 	.base.cra_name		= "sha384",
 	.base.cra_driver_name	= "sha384-ce",
 	.base.cra_priority	= 200,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -100,7 +99,6 @@ static struct shash_alg algs[] = { {
 	.base.cra_name		= "sha512",
 	.base.cra_driver_name	= "sha512-ce",
 	.base.cra_priority	= 200,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/arch/arm64/crypto/sha512-glue.c b/arch/arm64/crypto/sha512-glue.c
index 27db4851e380..325b23b43a9b 100644
--- a/arch/arm64/crypto/sha512-glue.c
+++ b/arch/arm64/crypto/sha512-glue.c
@@ -63,7 +63,6 @@ static struct shash_alg algs[] = { {
 	.base.cra_name		= "sha512",
 	.base.cra_driver_name	= "sha512-arm64",
 	.base.cra_priority	= 150,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -76,7 +75,6 @@ static struct shash_alg algs[] = { {
 	.base.cra_name		= "sha384",
 	.base.cra_driver_name	= "sha384-arm64",
 	.base.cra_priority	= 150,
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA384_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/arch/arm64/crypto/sm3-ce-glue.c b/arch/arm64/crypto/sm3-ce-glue.c
index 3b4948f7e26f..88938a20d9b2 100644
--- a/arch/arm64/crypto/sm3-ce-glue.c
+++ b/arch/arm64/crypto/sm3-ce-glue.c
@@ -72,7 +72,6 @@ static struct shash_alg sm3_alg = {
 	.descsize		= sizeof(struct sm3_state),
 	.base.cra_name		= "sm3",
 	.base.cra_driver_name	= "sm3-ce",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SM3_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 	.base.cra_priority	= 200,
diff --git a/arch/mips/cavium-octeon/crypto/octeon-md5.c b/arch/mips/cavium-octeon/crypto/octeon-md5.c
index af4c712f7afc..d1ed066e1a17 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-md5.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-md5.c
@@ -182,7 +182,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"md5",
 		.cra_driver_name=	"octeon-md5",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha1.c b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
index 2b74b5b67cae..80d71e775936 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha1.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha1.c
@@ -215,7 +215,6 @@ static struct shash_alg octeon_sha1_alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"octeon-sha1",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha256.c b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
index 97e96fead08a..8b931e640926 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha256.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha256.c
@@ -239,7 +239,6 @@ static struct shash_alg octeon_sha256_algs[2] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name=	"octeon-sha256",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -252,7 +251,6 @@ static struct shash_alg octeon_sha256_algs[2] = { {
 	.base		=	{
 		.cra_name	=	"sha224",
 		.cra_driver_name=	"octeon-sha224",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/mips/cavium-octeon/crypto/octeon-sha512.c b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
index d5fb3c6f22ae..6c9561496257 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-sha512.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-sha512.c
@@ -235,7 +235,6 @@ static struct shash_alg octeon_sha512_algs[2] = { {
 		.cra_name	=	"sha512",
 		.cra_driver_name=	"octeon-sha512",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -249,7 +248,6 @@ static struct shash_alg octeon_sha512_algs[2] = { {
 		.cra_name	=	"sha384",
 		.cra_driver_name=	"octeon-sha384",
 		.cra_priority	=	OCTEON_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/powerpc/crypto/md5-glue.c b/arch/powerpc/crypto/md5-glue.c
index 92289679b4c4..7e44cec37bdb 100644
--- a/arch/powerpc/crypto/md5-glue.c
+++ b/arch/powerpc/crypto/md5-glue.c
@@ -139,7 +139,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"md5",
 		.cra_driver_name=	"md5-ppc",
 		.cra_priority	=	200,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/powerpc/crypto/sha1-spe-glue.c b/arch/powerpc/crypto/sha1-spe-glue.c
index f9ebc38d3fe7..9e1814d99318 100644
--- a/arch/powerpc/crypto/sha1-spe-glue.c
+++ b/arch/powerpc/crypto/sha1-spe-glue.c
@@ -185,7 +185,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-ppc-spe",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/powerpc/crypto/sha1.c b/arch/powerpc/crypto/sha1.c
index c154cebc1041..3911d5c254fa 100644
--- a/arch/powerpc/crypto/sha1.c
+++ b/arch/powerpc/crypto/sha1.c
@@ -132,7 +132,6 @@ static struct shash_alg alg = {
 	.base		=	{
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-powerpc",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/powerpc/crypto/sha256-spe-glue.c b/arch/powerpc/crypto/sha256-spe-glue.c
index 718a079dcdbf..6227888dcf7e 100644
--- a/arch/powerpc/crypto/sha256-spe-glue.c
+++ b/arch/powerpc/crypto/sha256-spe-glue.c
@@ -231,7 +231,6 @@ static struct shash_alg algs[2] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name=	"sha256-ppc-spe",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -248,7 +247,6 @@ static struct shash_alg algs[2] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name=	"sha224-ppc-spe",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/s390/crypto/ghash_s390.c b/arch/s390/crypto/ghash_s390.c
index 3b7f96c9eead..86aed30fad3a 100644
--- a/arch/s390/crypto/ghash_s390.c
+++ b/arch/s390/crypto/ghash_s390.c
@@ -128,7 +128,6 @@ static struct shash_alg ghash_alg = {
 		.cra_name		= "ghash",
 		.cra_driver_name	= "ghash-s390",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= GHASH_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct ghash_ctx),
 		.cra_module		= THIS_MODULE,
diff --git a/arch/s390/crypto/sha1_s390.c b/arch/s390/crypto/sha1_s390.c
index a00c17f761c1..009572e8276d 100644
--- a/arch/s390/crypto/sha1_s390.c
+++ b/arch/s390/crypto/sha1_s390.c
@@ -78,7 +78,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-s390",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/s390/crypto/sha256_s390.c b/arch/s390/crypto/sha256_s390.c
index 944aa6b237cd..62833a1d8724 100644
--- a/arch/s390/crypto/sha256_s390.c
+++ b/arch/s390/crypto/sha256_s390.c
@@ -71,7 +71,6 @@ static struct shash_alg sha256_alg = {
 		.cra_name	=	"sha256",
 		.cra_driver_name=	"sha256-s390",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -108,7 +107,6 @@ static struct shash_alg sha224_alg = {
 		.cra_name	=	"sha224",
 		.cra_driver_name=	"sha224-s390",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/s390/crypto/sha512_s390.c b/arch/s390/crypto/sha512_s390.c
index b17eded532b1..be589c340d15 100644
--- a/arch/s390/crypto/sha512_s390.c
+++ b/arch/s390/crypto/sha512_s390.c
@@ -76,7 +76,6 @@ static struct shash_alg sha512_alg = {
 		.cra_name	=	"sha512",
 		.cra_driver_name=	"sha512-s390",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -115,7 +114,6 @@ static struct shash_alg sha384_alg = {
 		.cra_name	=	"sha384",
 		.cra_driver_name=	"sha384-s390",
 		.cra_priority	=	300,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_ctxsize	=	sizeof(struct s390_sha_ctx),
 		.cra_module	=	THIS_MODULE,
diff --git a/arch/sparc/crypto/md5_glue.c b/arch/sparc/crypto/md5_glue.c
index c9d2b922734b..bc9cc26efa3d 100644
--- a/arch/sparc/crypto/md5_glue.c
+++ b/arch/sparc/crypto/md5_glue.c
@@ -144,7 +144,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"md5",
 		.cra_driver_name=	"md5-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/sparc/crypto/sha1_glue.c b/arch/sparc/crypto/sha1_glue.c
index 1b3e47accc74..4d6d7faf728e 100644
--- a/arch/sparc/crypto/sha1_glue.c
+++ b/arch/sparc/crypto/sha1_glue.c
@@ -139,7 +139,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/sparc/crypto/sha256_glue.c b/arch/sparc/crypto/sha256_glue.c
index 285268ca9279..54c4de2db188 100644
--- a/arch/sparc/crypto/sha256_glue.c
+++ b/arch/sparc/crypto/sha256_glue.c
@@ -169,7 +169,6 @@ static struct shash_alg sha256 = {
 		.cra_name	=	"sha256",
 		.cra_driver_name=	"sha256-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -185,7 +184,6 @@ static struct shash_alg sha224 = {
 		.cra_name	=	"sha224",
 		.cra_driver_name=	"sha224-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/sparc/crypto/sha512_glue.c b/arch/sparc/crypto/sha512_glue.c
index 11eb36c3fc8c..4c55e97a4408 100644
--- a/arch/sparc/crypto/sha512_glue.c
+++ b/arch/sparc/crypto/sha512_glue.c
@@ -154,7 +154,6 @@ static struct shash_alg sha512 = {
 		.cra_name	=	"sha512",
 		.cra_driver_name=	"sha512-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -170,7 +169,6 @@ static struct shash_alg sha384 = {
 		.cra_name	=	"sha384",
 		.cra_driver_name=	"sha384-sparc64",
 		.cra_priority	=	SPARC_CR_OPCODE_PRIORITY,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index 2ddbe3a1868b..b1430e92e638 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -154,8 +154,7 @@ static struct shash_alg ghash_alg = {
 		.cra_name		= "__ghash",
 		.cra_driver_name	= "__ghash-pclmulqdqni",
 		.cra_priority		= 0,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH |
-					  CRYPTO_ALG_INTERNAL,
+		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= GHASH_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct ghash_ctx),
 		.cra_module		= THIS_MODULE,
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
index 790377797544..f012b7e28ad1 100644
--- a/arch/x86/crypto/poly1305_glue.c
+++ b/arch/x86/crypto/poly1305_glue.c
@@ -169,7 +169,6 @@ static struct shash_alg alg = {
 		.cra_name		= "poly1305",
 		.cra_driver_name	= "poly1305-simd",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= POLY1305_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	},
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
index fc61739150e7..7391c7de72c7 100644
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ b/arch/x86/crypto/sha1_ssse3_glue.c
@@ -104,7 +104,6 @@ static struct shash_alg sha1_ssse3_alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-ssse3",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -157,7 +156,6 @@ static struct shash_alg sha1_avx_alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-avx",
 		.cra_priority	=	160,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -249,7 +247,6 @@ static struct shash_alg sha1_avx2_alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-avx2",
 		.cra_priority	=	170,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -307,7 +304,6 @@ static struct shash_alg sha1_ni_alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name =	"sha1-ni",
 		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
index 9e79baf03a4b..773a873d2b28 100644
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ b/arch/x86/crypto/sha256_ssse3_glue.c
@@ -109,7 +109,6 @@ static struct shash_alg sha256_ssse3_algs[] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name =	"sha256-ssse3",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -124,7 +123,6 @@ static struct shash_alg sha256_ssse3_algs[] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name =	"sha224-ssse3",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -177,7 +175,6 @@ static struct shash_alg sha256_avx_algs[] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name =	"sha256-avx",
 		.cra_priority	=	160,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -192,7 +189,6 @@ static struct shash_alg sha256_avx_algs[] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name =	"sha224-avx",
 		.cra_priority	=	160,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -261,7 +257,6 @@ static struct shash_alg sha256_avx2_algs[] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name =	"sha256-avx2",
 		.cra_priority	=	170,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -276,7 +271,6 @@ static struct shash_alg sha256_avx2_algs[] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name =	"sha224-avx2",
 		.cra_priority	=	170,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -343,7 +337,6 @@ static struct shash_alg sha256_ni_algs[] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name =	"sha256-ni",
 		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -358,7 +351,6 @@ static struct shash_alg sha256_ni_algs[] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name =	"sha224-ni",
 		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
index 2b0e2a6825f3..f1b811b60ba6 100644
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ b/arch/x86/crypto/sha512_ssse3_glue.c
@@ -109,7 +109,6 @@ static struct shash_alg sha512_ssse3_algs[] = { {
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-ssse3",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -124,7 +123,6 @@ static struct shash_alg sha512_ssse3_algs[] = { {
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-ssse3",
 		.cra_priority	=	150,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -188,7 +186,6 @@ static struct shash_alg sha512_avx_algs[] = { {
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-avx",
 		.cra_priority	=	160,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -203,7 +200,6 @@ static struct shash_alg sha512_avx_algs[] = { {
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-avx",
 		.cra_priority	=	160,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -261,7 +257,6 @@ static struct shash_alg sha512_avx2_algs[] = { {
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-avx2",
 		.cra_priority	=	170,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -276,7 +271,6 @@ static struct shash_alg sha512_avx2_algs[] = { {
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-avx2",
 		.cra_priority	=	170,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/crypto/crypto_null.c b/crypto/crypto_null.c
index 20ff2c746e0b..0959b268966c 100644
--- a/crypto/crypto_null.c
+++ b/crypto/crypto_null.c
@@ -104,7 +104,6 @@ static struct shash_alg digest_null = {
 	.final  		=	null_final,
 	.base			=	{
 		.cra_name		=	"digest_null",
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	NULL_BLOCK_SIZE,
 		.cra_module		=	THIS_MODULE,
 	}
diff --git a/crypto/ghash-generic.c b/crypto/ghash-generic.c
index 1bffb3f712dd..d9f192b953b2 100644
--- a/crypto/ghash-generic.c
+++ b/crypto/ghash-generic.c
@@ -132,7 +132,6 @@ static struct shash_alg ghash_alg = {
 		.cra_name		= "ghash",
 		.cra_driver_name	= "ghash-generic",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= GHASH_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct ghash_ctx),
 		.cra_module		= THIS_MODULE,
diff --git a/crypto/md4.c b/crypto/md4.c
index 810fefb0a007..9965ec40d9f9 100644
--- a/crypto/md4.c
+++ b/crypto/md4.c
@@ -217,7 +217,6 @@ static struct shash_alg alg = {
 	.descsize	=	sizeof(struct md4_ctx),
 	.base		=	{
 		.cra_name	=	"md4",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	MD4_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/crypto/md5.c b/crypto/md5.c
index f776ef43d621..94dd78144ba3 100644
--- a/crypto/md5.c
+++ b/crypto/md5.c
@@ -229,7 +229,6 @@ static struct shash_alg alg = {
 	.statesize	=	sizeof(struct md5_state),
 	.base		=	{
 		.cra_name	=	"md5",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	MD5_HMAC_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index b7a3a0613a30..47d3a6b83931 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -279,7 +279,6 @@ static struct shash_alg poly1305_alg = {
 		.cra_name		= "poly1305",
 		.cra_driver_name	= "poly1305-generic",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		= POLY1305_BLOCK_SIZE,
 		.cra_module		= THIS_MODULE,
 	},
diff --git a/crypto/rmd128.c b/crypto/rmd128.c
index 40e053b97b69..5f4472256e27 100644
--- a/crypto/rmd128.c
+++ b/crypto/rmd128.c
@@ -303,7 +303,6 @@ static struct shash_alg alg = {
 	.descsize	=	sizeof(struct rmd128_ctx),
 	.base		=	{
 		.cra_name	 =	"rmd128",
-		.cra_flags	 =	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	 =	RMD128_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
diff --git a/crypto/rmd160.c b/crypto/rmd160.c
index 5f3e6ea35268..737645344d1c 100644
--- a/crypto/rmd160.c
+++ b/crypto/rmd160.c
@@ -347,7 +347,6 @@ static struct shash_alg alg = {
 	.descsize	=	sizeof(struct rmd160_ctx),
 	.base		=	{
 		.cra_name	 =	"rmd160",
-		.cra_flags	 =	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	 =	RMD160_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
diff --git a/crypto/rmd256.c b/crypto/rmd256.c
index f50c025cc962..0afbb5af4499 100644
--- a/crypto/rmd256.c
+++ b/crypto/rmd256.c
@@ -322,7 +322,6 @@ static struct shash_alg alg = {
 	.descsize	=	sizeof(struct rmd256_ctx),
 	.base		=	{
 		.cra_name	 =	"rmd256",
-		.cra_flags	 =	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	 =	RMD256_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
diff --git a/crypto/rmd320.c b/crypto/rmd320.c
index e1315e4869e8..ab3cf93624d2 100644
--- a/crypto/rmd320.c
+++ b/crypto/rmd320.c
@@ -371,7 +371,6 @@ static struct shash_alg alg = {
 	.descsize	=	sizeof(struct rmd320_ctx),
 	.base		=	{
 		.cra_name	 =	"rmd320",
-		.cra_flags	 =	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	 =	RMD320_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
diff --git a/crypto/sha1_generic.c b/crypto/sha1_generic.c
index a3d701632ca2..2af64ef81f40 100644
--- a/crypto/sha1_generic.c
+++ b/crypto/sha1_generic.c
@@ -77,7 +77,6 @@ static struct shash_alg alg = {
 		.cra_name	=	"sha1",
 		.cra_driver_name=	"sha1-generic",
 		.cra_priority	=	100,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA1_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/crypto/sha256_generic.c b/crypto/sha256_generic.c
index dfcb7beb73a7..1e5ba6649e8d 100644
--- a/crypto/sha256_generic.c
+++ b/crypto/sha256_generic.c
@@ -272,7 +272,6 @@ static struct shash_alg sha256_algs[2] = { {
 		.cra_name	=	"sha256",
 		.cra_driver_name=	"sha256-generic",
 		.cra_priority	=	100,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA256_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -287,7 +286,6 @@ static struct shash_alg sha256_algs[2] = { {
 		.cra_name	=	"sha224",
 		.cra_driver_name=	"sha224-generic",
 		.cra_priority	=	100,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA224_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/crypto/sha3_generic.c b/crypto/sha3_generic.c
index 264ec12c0b9c..153fe33b8c9b 100644
--- a/crypto/sha3_generic.c
+++ b/crypto/sha3_generic.c
@@ -250,7 +250,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-224",
 	.base.cra_driver_name	= "sha3-224-generic",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_224_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -261,7 +260,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-256",
 	.base.cra_driver_name	= "sha3-256-generic",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_256_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -272,7 +270,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-384",
 	.base.cra_driver_name	= "sha3-384-generic",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_384_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -283,7 +280,6 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha3_state),
 	.base.cra_name		= "sha3-512",
 	.base.cra_driver_name	= "sha3-512-generic",
-	.base.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
 	.base.cra_blocksize	= SHA3_512_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
diff --git a/crypto/sha512_generic.c b/crypto/sha512_generic.c
index 55377b1cba6b..4097cd555eb6 100644
--- a/crypto/sha512_generic.c
+++ b/crypto/sha512_generic.c
@@ -194,7 +194,6 @@ static struct shash_alg sha512_algs[2] = { {
 		.cra_name	=	"sha512",
 		.cra_driver_name =	"sha512-generic",
 		.cra_priority	=	100,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -209,7 +208,6 @@ static struct shash_alg sha512_algs[2] = { {
 		.cra_name	=	"sha384",
 		.cra_driver_name =	"sha384-generic",
 		.cra_priority	=	100,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	SHA384_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/crypto/sm3_generic.c b/crypto/sm3_generic.c
index 9e823d99f095..9a5c60f08aad 100644
--- a/crypto/sm3_generic.c
+++ b/crypto/sm3_generic.c
@@ -184,7 +184,6 @@ static struct shash_alg sm3_alg = {
 	.base		=	{
 		.cra_name	 =	"sm3",
 		.cra_driver_name =	"sm3-generic",
-		.cra_flags	 =	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	 =	SM3_BLOCK_SIZE,
 		.cra_module	 =	THIS_MODULE,
 	}
diff --git a/crypto/tgr192.c b/crypto/tgr192.c
index 321bc6ff2a9d..022d3dd76c3b 100644
--- a/crypto/tgr192.c
+++ b/crypto/tgr192.c
@@ -636,7 +636,6 @@ static struct shash_alg tgr_algs[3] = { {
 	.descsize	=	sizeof(struct tgr192_ctx),
 	.base		=	{
 		.cra_name	=	"tgr192",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	TGR192_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -648,7 +647,6 @@ static struct shash_alg tgr_algs[3] = { {
 	.descsize	=	sizeof(struct tgr192_ctx),
 	.base		=	{
 		.cra_name	=	"tgr160",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	TGR192_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -660,7 +658,6 @@ static struct shash_alg tgr_algs[3] = { {
 	.descsize	=	sizeof(struct tgr192_ctx),
 	.base		=	{
 		.cra_name	=	"tgr128",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	TGR192_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/crypto/wp512.c b/crypto/wp512.c
index 7ee5a043a988..149e577fb772 100644
--- a/crypto/wp512.c
+++ b/crypto/wp512.c
@@ -1127,7 +1127,6 @@ static struct shash_alg wp_algs[3] = { {
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	=	"wp512",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	WP512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -1139,7 +1138,6 @@ static struct shash_alg wp_algs[3] = { {
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	=	"wp384",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	WP512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
@@ -1151,7 +1149,6 @@ static struct shash_alg wp_algs[3] = { {
 	.descsize	=	sizeof(struct wp512_ctx),
 	.base		=	{
 		.cra_name	=	"wp256",
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize	=	WP512_BLOCK_SIZE,
 		.cra_module	=	THIS_MODULE,
 	}
diff --git a/drivers/crypto/nx/nx-aes-xcbc.c b/drivers/crypto/nx/nx-aes-xcbc.c
index c2f7d4befb55..ad3358e74f5c 100644
--- a/drivers/crypto/nx/nx-aes-xcbc.c
+++ b/drivers/crypto/nx/nx-aes-xcbc.c
@@ -386,7 +386,6 @@ struct shash_alg nx_shash_aes_xcbc_alg = {
 		.cra_name        = "xcbc(aes)",
 		.cra_driver_name = "xcbc-aes-nx",
 		.cra_priority    = 300,
-		.cra_flags       = CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize   = AES_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
diff --git a/drivers/crypto/nx/nx-sha256.c b/drivers/crypto/nx/nx-sha256.c
index becb738c897b..a6764af83c6d 100644
--- a/drivers/crypto/nx/nx-sha256.c
+++ b/drivers/crypto/nx/nx-sha256.c
@@ -288,7 +288,6 @@ struct shash_alg nx_shash_sha256_alg = {
 		.cra_name        = "sha256",
 		.cra_driver_name = "sha256-nx",
 		.cra_priority    = 300,
-		.cra_flags       = CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize   = SHA256_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
diff --git a/drivers/crypto/nx/nx-sha512.c b/drivers/crypto/nx/nx-sha512.c
index b6e183d58d73..92956bc6e45e 100644
--- a/drivers/crypto/nx/nx-sha512.c
+++ b/drivers/crypto/nx/nx-sha512.c
@@ -294,7 +294,6 @@ struct shash_alg nx_shash_sha512_alg = {
 		.cra_name        = "sha512",
 		.cra_driver_name = "sha512-nx",
 		.cra_priority    = 300,
-		.cra_flags       = CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize   = SHA512_BLOCK_SIZE,
 		.cra_module      = THIS_MODULE,
 		.cra_ctxsize     = sizeof(struct nx_crypto_ctx),
diff --git a/drivers/crypto/padlock-sha.c b/drivers/crypto/padlock-sha.c
index d32c79328876..21e5cae0a1e0 100644
--- a/drivers/crypto/padlock-sha.c
+++ b/drivers/crypto/padlock-sha.c
@@ -247,8 +247,7 @@ static struct shash_alg sha1_alg = {
 		.cra_name		=	"sha1",
 		.cra_driver_name	=	"sha1-padlock",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH |
-						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		=	SHA1_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(struct padlock_sha_ctx),
 		.cra_module		=	THIS_MODULE,
@@ -271,8 +270,7 @@ static struct shash_alg sha256_alg = {
 		.cra_name		=	"sha256",
 		.cra_driver_name	=	"sha256-padlock",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH |
-						CRYPTO_ALG_NEED_FALLBACK,
+		.cra_flags		=	CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		=	SHA256_BLOCK_SIZE,
 		.cra_ctxsize		=	sizeof(struct padlock_sha_ctx),
 		.cra_module		=	THIS_MODULE,
@@ -484,7 +482,6 @@ static struct shash_alg sha1_alg_nano = {
 		.cra_name		=	"sha1",
 		.cra_driver_name	=	"sha1-padlock-nano",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SHA1_BLOCK_SIZE,
 		.cra_module		=	THIS_MODULE,
 	}
@@ -503,7 +500,6 @@ static struct shash_alg sha256_alg_nano = {
 		.cra_name		=	"sha256",
 		.cra_driver_name	=	"sha256-padlock-nano",
 		.cra_priority		=	PADLOCK_CRA_PRIORITY,
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SHA256_BLOCK_SIZE,
 		.cra_module		=	THIS_MODULE,
 	}
diff --git a/drivers/crypto/vmx/ghash.c b/drivers/crypto/vmx/ghash.c
index 1c4b5b889fba..dd8b8716467a 100644
--- a/drivers/crypto/vmx/ghash.c
+++ b/drivers/crypto/vmx/ghash.c
@@ -215,7 +215,7 @@ struct shash_alg p8_ghash_alg = {
 		 .cra_name = "ghash",
 		 .cra_driver_name = "p8_ghash",
 		 .cra_priority = 1000,
-		 .cra_flags = CRYPTO_ALG_TYPE_SHASH | CRYPTO_ALG_NEED_FALLBACK,
+		 .cra_flags = CRYPTO_ALG_NEED_FALLBACK,
 		 .cra_blocksize = GHASH_BLOCK_SIZE,
 		 .cra_ctxsize = sizeof(struct p8_ghash_ctx),
 		 .cra_module = THIS_MODULE,
diff --git a/drivers/staging/skein/skein_generic.c b/drivers/staging/skein/skein_generic.c
index 11f5e530a75f..c31fc6408383 100644
--- a/drivers/staging/skein/skein_generic.c
+++ b/drivers/staging/skein/skein_generic.c
@@ -137,7 +137,6 @@ static struct shash_alg alg256 = {
 	.base		=	{
 		.cra_name		=	"skein256",
 		.cra_driver_name	=	"skein",
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SKEIN_256_BLOCK_BYTES,
 		.cra_module		=	THIS_MODULE,
 	}
@@ -155,7 +154,6 @@ static struct shash_alg alg512 = {
 	.base		=	{
 		.cra_name		=	"skein512",
 		.cra_driver_name	=	"skein",
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SKEIN_512_BLOCK_BYTES,
 		.cra_module		=	THIS_MODULE,
 	}
@@ -173,7 +171,6 @@ static struct shash_alg alg1024 = {
 	.base		=	{
 		.cra_name		=	"skein1024",
 		.cra_driver_name	=	"skein",
-		.cra_flags		=	CRYPTO_ALG_TYPE_SHASH,
 		.cra_blocksize		=	SKEIN_1024_BLOCK_BYTES,
 		.cra_module		=	THIS_MODULE,
 	}
-- 
cgit v1.2.3


From 6a38f62245c9d5217b696ec5aca6a5cf6351f615 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:16:12 -0700
Subject: crypto: ahash - remove useless setting of type flags

Many ahash algorithms set .cra_flags = CRYPTO_ALG_TYPE_AHASH.  But this
is redundant with the C structure type ('struct ahash_alg'), and
crypto_register_ahash() already sets the type flag automatically,
clearing any type flag that was already there.  Apparently the useless
assignment has just been copy+pasted around.

So, remove the useless assignment from all the ahash algorithms.

This patch shouldn't change any actual behavior.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/ghash-ce-glue.c            |  2 +-
 arch/x86/crypto/ghash-clmulni-intel_glue.c |  2 +-
 arch/x86/crypto/sha1-mb/sha1_mb.c          |  7 +++---
 arch/x86/crypto/sha256-mb/sha256_mb.c      |  8 +++----
 arch/x86/crypto/sha512-mb/sha512_mb.c      |  8 +++----
 drivers/crypto/axis/artpec6_crypto.c       | 14 ++++++------
 drivers/crypto/bcm/cipher.c                |  5 ++---
 drivers/crypto/caam/caamhash.c             |  2 +-
 drivers/crypto/ccp/ccp-crypto-aes-cmac.c   |  2 +-
 drivers/crypto/ccp/ccp-crypto-sha.c        |  2 +-
 drivers/crypto/ccree/cc_hash.c             |  3 +--
 drivers/crypto/chelsio/chcr_algo.c         |  3 +--
 drivers/crypto/n2_core.c                   |  3 +--
 drivers/crypto/omap-sham.c                 | 36 ++++++++++--------------------
 drivers/crypto/s5p-sss.c                   |  9 +++-----
 drivers/crypto/sahara.c                    |  6 ++---
 drivers/crypto/stm32/stm32-hash.c          | 24 +++++++-------------
 drivers/crypto/sunxi-ss/sun4i-ss-core.c    |  2 --
 drivers/crypto/talitos.c                   | 36 ++++++++++--------------------
 drivers/crypto/ux500/hash/hash_core.c      | 12 ++++------
 20 files changed, 67 insertions(+), 119 deletions(-)

diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index f93c0761929d..124fee03246e 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -308,7 +308,7 @@ static struct ahash_alg ghash_async_alg = {
 		.cra_name	= "ghash",
 		.cra_driver_name = "ghash-ce",
 		.cra_priority	= 300,
-		.cra_flags	= CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+		.cra_flags	= CRYPTO_ALG_ASYNC,
 		.cra_blocksize	= GHASH_BLOCK_SIZE,
 		.cra_type	= &crypto_ahash_type,
 		.cra_ctxsize	= sizeof(struct ghash_async_ctx),
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index b1430e92e638..a3de43b5e20a 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -314,7 +314,7 @@ static struct ahash_alg ghash_async_alg = {
 			.cra_driver_name	= "ghash-clmulni",
 			.cra_priority		= 400,
 			.cra_ctxsize		= sizeof(struct ghash_async_ctx),
-			.cra_flags		= CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags		= CRYPTO_ALG_ASYNC,
 			.cra_blocksize		= GHASH_BLOCK_SIZE,
 			.cra_type		= &crypto_ahash_type,
 			.cra_module		= THIS_MODULE,
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c
index 4b2430274935..f7929ba6cfb4 100644
--- a/arch/x86/crypto/sha1-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb.c
@@ -746,9 +746,8 @@ static struct ahash_alg sha1_mb_areq_alg = {
 			 * algo may not have completed before hashing thread
 			 * sleep
 			 */
-			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_INTERNAL,
+			.cra_flags	= CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_INTERNAL,
 			.cra_blocksize	= SHA1_BLOCK_SIZE,
 			.cra_module	= THIS_MODULE,
 			.cra_list	= LIST_HEAD_INIT
@@ -879,7 +878,7 @@ static struct ahash_alg sha1_mb_async_alg = {
 			 * priority at runtime using NETLINK_CRYPTO.
 			 */
 			.cra_priority           = 50,
-			.cra_flags              = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags              = CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA1_BLOCK_SIZE,
 			.cra_type               = &crypto_ahash_type,
 			.cra_module             = THIS_MODULE,
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
index 4c07f6c12c37..59a47048920a 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -745,9 +745,8 @@ static struct ahash_alg sha256_mb_areq_alg = {
 			 * algo may not have completed before hashing thread
 			 * sleep
 			 */
-			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_INTERNAL,
+			.cra_flags	= CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_INTERNAL,
 			.cra_blocksize	= SHA256_BLOCK_SIZE,
 			.cra_module	= THIS_MODULE,
 			.cra_list	= LIST_HEAD_INIT
@@ -878,8 +877,7 @@ static struct ahash_alg sha256_mb_async_alg = {
 			 * priority at runtime using NETLINK_CRYPTO.
 			 */
 			.cra_priority           = 50,
-			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
-							CRYPTO_ALG_ASYNC,
+			.cra_flags              = CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA256_BLOCK_SIZE,
 			.cra_type               = &crypto_ahash_type,
 			.cra_module             = THIS_MODULE,
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index 6a8c31581604..d3a758ac3ade 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -778,9 +778,8 @@ static struct ahash_alg sha512_mb_areq_alg = {
 			 * algo may not have completed before hashing thread
 			 * sleep
 			 */
-			.cra_flags	= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
-						CRYPTO_ALG_INTERNAL,
+			.cra_flags	= CRYPTO_ALG_ASYNC |
+					  CRYPTO_ALG_INTERNAL,
 			.cra_blocksize	= SHA512_BLOCK_SIZE,
 			.cra_module	= THIS_MODULE,
 			.cra_list	= LIST_HEAD_INIT
@@ -912,8 +911,7 @@ static struct ahash_alg sha512_mb_async_alg = {
 			 * priority at runtime using NETLINK_CRYPTO.
 			 */
 			.cra_priority           = 50,
-			.cra_flags              = CRYPTO_ALG_TYPE_AHASH |
-							CRYPTO_ALG_ASYNC,
+			.cra_flags              = CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA512_BLOCK_SIZE,
 			.cra_type               = &crypto_ahash_type,
 			.cra_module             = THIS_MODULE,
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 0fb8bbf41a8d..049af6de3cb6 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -2704,7 +2704,7 @@ static struct ahash_alg hash_algos[] = {
 			.cra_name = "sha1",
 			.cra_driver_name = "artpec-sha1",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA1_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2727,7 +2727,7 @@ static struct ahash_alg hash_algos[] = {
 			.cra_name = "sha256",
 			.cra_driver_name = "artpec-sha256",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA256_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2751,7 +2751,7 @@ static struct ahash_alg hash_algos[] = {
 			.cra_name = "hmac(sha256)",
 			.cra_driver_name = "artpec-hmac-sha256",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA256_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2777,7 +2777,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "sha384",
 			.cra_driver_name = "artpec-sha384",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA384_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2801,7 +2801,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "hmac(sha384)",
 			.cra_driver_name = "artpec-hmac-sha384",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA384_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2824,7 +2824,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "sha512",
 			.cra_driver_name = "artpec-sha512",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA512_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
@@ -2848,7 +2848,7 @@ static struct ahash_alg artpec7_hash_algos[] = {
 			.cra_name = "hmac(sha512)",
 			.cra_driver_name = "artpec-hmac-sha512",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = SHA512_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_hashalg_context),
 			.cra_alignmask = 3,
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 309c67c7012f..2f85a989c476 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -3914,8 +3914,7 @@ static struct iproc_alg_s driver_algs[] = {
 				    .cra_name = "md5",
 				    .cra_driver_name = "md5-iproc",
 				    .cra_blocksize = MD5_BLOCK_WORDS * 4,
-				    .cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				    .cra_flags = CRYPTO_ALG_ASYNC,
 				}
 		      },
 	 .cipher_info = {
@@ -4650,7 +4649,7 @@ static int spu_register_ahash(struct iproc_alg_s *driver_alg)
 	hash->halg.base.cra_init = ahash_cra_init;
 	hash->halg.base.cra_exit = generic_cra_exit;
 	hash->halg.base.cra_type = &crypto_ahash_type;
-	hash->halg.base.cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC;
+	hash->halg.base.cra_flags = CRYPTO_ALG_ASYNC;
 	hash->halg.statesize = sizeof(struct spu_hash_export_s);
 
 	if (driver_alg->auth_info.mode != HASH_MODE_HMAC) {
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index 0beb28196e20..a20123e28ce6 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1846,7 +1846,7 @@ caam_hash_alloc(struct caam_hash_template *template,
 	alg->cra_priority = CAAM_CRA_PRIORITY;
 	alg->cra_blocksize = template->blocksize;
 	alg->cra_alignmask = 0;
-	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_TYPE_AHASH;
+	alg->cra_flags = CRYPTO_ALG_ASYNC;
 	alg->cra_type = &crypto_ahash_type;
 
 	t_alg->alg_type = template->alg_type;
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
index 26687f318de6..bdc2715b3cac 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
@@ -399,7 +399,7 @@ int ccp_register_aes_cmac_algs(struct list_head *head)
 	base = &halg->base;
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "cmac(aes)");
 	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "cmac-aes-ccp");
-	base->cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC |
+	base->cra_flags = CRYPTO_ALG_ASYNC |
 			  CRYPTO_ALG_KERN_DRIVER_ONLY |
 			  CRYPTO_ALG_NEED_FALLBACK;
 	base->cra_blocksize = AES_BLOCK_SIZE;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 871c9628a2ee..366d3e914ac5 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -497,7 +497,7 @@ static int ccp_register_sha_alg(struct list_head *head,
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", def->name);
 	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s",
 		 def->drv_name);
-	base->cra_flags = CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC |
+	base->cra_flags = CRYPTO_ALG_ASYNC |
 			  CRYPTO_ALG_KERN_DRIVER_ONLY |
 			  CRYPTO_ALG_NEED_FALLBACK;
 	base->cra_blocksize = def->block_size;
diff --git a/drivers/crypto/ccree/cc_hash.c b/drivers/crypto/ccree/cc_hash.c
index 96ff777474d7..9cc7f8a95f96 100644
--- a/drivers/crypto/ccree/cc_hash.c
+++ b/drivers/crypto/ccree/cc_hash.c
@@ -1813,8 +1813,7 @@ static struct cc_hash_alg *cc_alloc_hash_alg(struct cc_hash_template *template,
 	alg->cra_exit = cc_cra_exit;
 
 	alg->cra_init = cc_cra_init;
-	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_TYPE_AHASH |
-			CRYPTO_ALG_KERN_DRIVER_ONLY;
+	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 	alg->cra_type = &crypto_ahash_type;
 
 	t_crypto_alg->hash_mode = template->hash_mode;
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index b916c4eb608c..6bbedf1bb7bd 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -4203,7 +4203,6 @@ static int chcr_unregister_alg(void)
 #define SZ_AHASH_CTX sizeof(struct chcr_context)
 #define SZ_AHASH_H_CTX (sizeof(struct chcr_context) + sizeof(struct hmac_ctx))
 #define SZ_AHASH_REQ_CTX sizeof(struct chcr_ahash_req_ctx)
-#define AHASH_CRA_FLAGS (CRYPTO_ALG_TYPE_AHASH | CRYPTO_ALG_ASYNC)
 
 /*
  *	chcr_register_alg - Register crypto algorithms with kernel framework.
@@ -4258,7 +4257,7 @@ static int chcr_register_alg(void)
 			a_hash->halg.statesize = SZ_AHASH_REQ_CTX;
 			a_hash->halg.base.cra_priority = CHCR_CRA_PRIORITY;
 			a_hash->halg.base.cra_module = THIS_MODULE;
-			a_hash->halg.base.cra_flags = AHASH_CRA_FLAGS;
+			a_hash->halg.base.cra_flags = CRYPTO_ALG_ASYNC;
 			a_hash->halg.base.cra_alignmask = 0;
 			a_hash->halg.base.cra_exit = NULL;
 			a_hash->halg.base.cra_type = &crypto_ahash_type;
diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
index ab6235b7ff22..55f34cfc43ff 100644
--- a/drivers/crypto/n2_core.c
+++ b/drivers/crypto/n2_core.c
@@ -1487,8 +1487,7 @@ static int __n2_register_one_ahash(const struct n2_hash_tmpl *tmpl)
 	snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "%s", tmpl->name);
 	snprintf(base->cra_driver_name, CRYPTO_MAX_ALG_NAME, "%s-n2", tmpl->name);
 	base->cra_priority = N2_CRA_PRIORITY;
-	base->cra_flags = CRYPTO_ALG_TYPE_AHASH |
-			  CRYPTO_ALG_KERN_DRIVER_ONLY |
+	base->cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY |
 			  CRYPTO_ALG_NEED_FALLBACK;
 	base->cra_blocksize = tmpl->block_size;
 	base->cra_ctxsize = sizeof(struct n2_hash_ctx);
diff --git a/drivers/crypto/omap-sham.c b/drivers/crypto/omap-sham.c
index d1a1c74fb56a..0641185bd82f 100644
--- a/drivers/crypto/omap-sham.c
+++ b/drivers/crypto/omap-sham.c
@@ -1464,8 +1464,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "omap-sha1",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1487,8 +1486,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "md5",
 		.cra_driver_name	= "omap-md5",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1511,8 +1509,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "hmac(sha1)",
 		.cra_driver_name	= "omap-hmac-sha1",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1536,8 +1533,7 @@ static struct ahash_alg algs_sha1_md5[] = {
 		.cra_name		= "hmac(md5)",
 		.cra_driver_name	= "omap-hmac-md5",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 						CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
@@ -1564,8 +1560,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "sha224",
 		.cra_driver_name	= "omap-sha224",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA224_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1586,8 +1581,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "omap-sha256",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1609,8 +1603,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "hmac(sha224)",
 		.cra_driver_name	= "omap-hmac-sha224",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA224_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
@@ -1633,8 +1626,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 		.cra_name		= "hmac(sha256)",
 		.cra_driver_name	= "omap-hmac-sha256",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
@@ -1659,8 +1651,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "sha384",
 		.cra_driver_name	= "omap-sha384",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA384_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1681,8 +1672,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "sha512",
 		.cra_driver_name	= "omap-sha512",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx),
@@ -1704,8 +1694,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "hmac(sha384)",
 		.cra_driver_name	= "omap-hmac-sha384",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA384_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
@@ -1728,8 +1717,7 @@ static struct ahash_alg algs_sha384_sha512[] = {
 		.cra_name		= "hmac(sha512)",
 		.cra_driver_name	= "omap-hmac-sha512",
 		.cra_priority		= 400,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA512_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct omap_sham_ctx) +
diff --git a/drivers/crypto/s5p-sss.c b/drivers/crypto/s5p-sss.c
index bf7163042569..faa282074e5a 100644
--- a/drivers/crypto/s5p-sss.c
+++ b/drivers/crypto/s5p-sss.c
@@ -1765,8 +1765,7 @@ static struct ahash_alg algs_sha1_md5_sha256[] = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "exynos-sha1",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-					  CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 					  CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= HASH_BLOCK_SIZE,
@@ -1791,8 +1790,7 @@ static struct ahash_alg algs_sha1_md5_sha256[] = {
 		.cra_name		= "md5",
 		.cra_driver_name	= "exynos-md5",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-					  CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 					  CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= HASH_BLOCK_SIZE,
@@ -1817,8 +1815,7 @@ static struct ahash_alg algs_sha1_md5_sha256[] = {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "exynos-sha256",
 		.cra_priority		= 100,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-					  CRYPTO_ALG_KERN_DRIVER_ONLY |
+		.cra_flags		= CRYPTO_ALG_KERN_DRIVER_ONLY |
 					  CRYPTO_ALG_ASYNC |
 					  CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= HASH_BLOCK_SIZE,
diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 0f2245e1af2b..4379f016fbee 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1253,8 +1253,7 @@ static struct ahash_alg sha_v3_algs[] = {
 		.cra_name		= "sha1",
 		.cra_driver_name	= "sahara-sha1",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA1_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct sahara_ctx),
@@ -1280,8 +1279,7 @@ static struct ahash_alg sha_v4_algs[] = {
 		.cra_name		= "sha256",
 		.cra_driver_name	= "sahara-sha256",
 		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_AHASH |
-						CRYPTO_ALG_ASYNC |
+		.cra_flags		= CRYPTO_ALG_ASYNC |
 						CRYPTO_ALG_NEED_FALLBACK,
 		.cra_blocksize		= SHA256_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct sahara_ctx),
diff --git a/drivers/crypto/stm32/stm32-hash.c b/drivers/crypto/stm32/stm32-hash.c
index d1d7233d7dd6..590d7352837e 100644
--- a/drivers/crypto/stm32/stm32-hash.c
+++ b/drivers/crypto/stm32/stm32-hash.c
@@ -1150,8 +1150,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "md5",
 				.cra_driver_name = "stm32-md5",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1177,8 +1176,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "hmac(md5)",
 				.cra_driver_name = "stm32-hmac-md5",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1203,8 +1201,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "sha1",
 				.cra_driver_name = "stm32-sha1",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1230,8 +1227,7 @@ static struct ahash_alg algs_md5_sha1[] = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "stm32-hmac-sha1",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1259,8 +1255,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "sha224",
 				.cra_driver_name = "stm32-sha224",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA224_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1286,8 +1281,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "stm32-hmac-sha224",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA224_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1312,8 +1306,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "sha256",
 				.cra_driver_name = "stm32-sha256",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
@@ -1339,8 +1332,7 @@ static struct ahash_alg algs_sha224_sha256[] = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "stm32-hmac-sha256",
 				.cra_priority = 200,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					CRYPTO_ALG_ASYNC |
+				.cra_flags = CRYPTO_ALG_ASYNC |
 					CRYPTO_ALG_KERN_DRIVER_ONLY,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct stm32_hash_ctx),
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
index a81d89b3b7d8..d96bf7578569 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -45,7 +45,6 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_driver_name = "md5-sun4i-ss",
 				.cra_priority = 300,
 				.cra_alignmask = 3,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
@@ -73,7 +72,6 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_driver_name = "sha1-sun4i-ss",
 				.cra_priority = 300,
 				.cra_alignmask = 3,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index cf14f099ce4a..323b46d2457d 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -2822,8 +2822,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "md5",
 				.cra_driver_name = "md5-talitos",
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2838,8 +2837,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha1",
 				.cra_driver_name = "sha1-talitos",
 				.cra_blocksize = SHA1_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2854,8 +2852,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha224",
 				.cra_driver_name = "sha224-talitos",
 				.cra_blocksize = SHA224_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2870,8 +2867,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha256",
 				.cra_driver_name = "sha256-talitos",
 				.cra_blocksize = SHA256_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2886,8 +2882,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha384",
 				.cra_driver_name = "sha384-talitos",
 				.cra_blocksize = SHA384_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2902,8 +2897,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "sha512",
 				.cra_driver_name = "sha512-talitos",
 				.cra_blocksize = SHA512_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2918,8 +2912,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(md5)",
 				.cra_driver_name = "hmac-md5-talitos",
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2934,8 +2927,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "hmac-sha1-talitos",
 				.cra_blocksize = SHA1_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2950,8 +2942,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha224)",
 				.cra_driver_name = "hmac-sha224-talitos",
 				.cra_blocksize = SHA224_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2966,8 +2957,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "hmac-sha256-talitos",
 				.cra_blocksize = SHA256_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2982,8 +2972,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha384)",
 				.cra_driver_name = "hmac-sha384-talitos",
 				.cra_blocksize = SHA384_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
@@ -2998,8 +2987,7 @@ static struct talitos_alg_template driver_algs[] = {
 				.cra_name = "hmac(sha512)",
 				.cra_driver_name = "hmac-sha512-talitos",
 				.cra_blocksize = SHA512_BLOCK_SIZE,
-				.cra_flags = CRYPTO_ALG_TYPE_AHASH |
-					     CRYPTO_ALG_ASYNC,
+				.cra_flags = CRYPTO_ALG_ASYNC,
 			}
 		},
 		.desc_hdr_template = DESC_HDR_TYPE_COMMON_NONSNOOP_NO_AFEU |
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 2d0a677bcc76..7de22a646adf 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1524,8 +1524,7 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "sha1",
 				.cra_driver_name = "sha1-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
 				.cra_init = hash_cra_init,
@@ -1548,8 +1547,7 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "sha256",
 				.cra_driver_name = "sha256-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
 				.cra_type = &crypto_ahash_type,
@@ -1574,8 +1572,7 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "hmac(sha1)",
 				.cra_driver_name = "hmac-sha1-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
 				.cra_type = &crypto_ahash_type,
@@ -1600,8 +1597,7 @@ static struct hash_algo_template hash_algs[] = {
 			.halg.base = {
 				.cra_name = "hmac(sha256)",
 				.cra_driver_name = "hmac-sha256-ux500",
-				.cra_flags = (CRYPTO_ALG_TYPE_AHASH |
-					      CRYPTO_ALG_ASYNC),
+				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
 				.cra_type = &crypto_ahash_type,
-- 
cgit v1.2.3


From c87a405e3bacaae324bb05ee9a48aa9844688469 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:16:13 -0700
Subject: crypto: ahash - remove useless setting of cra_type

Some ahash algorithms set .cra_type = &crypto_ahash_type.  But this is
redundant with the C structure type ('struct ahash_alg'), and
crypto_register_ahash() already sets the .cra_type automatically.
Apparently the useless assignment has just been copy+pasted around.

So, remove the useless assignment from all the ahash algorithms.

This patch shouldn't change any actual behavior.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/ghash-ce-glue.c            | 1 -
 arch/x86/crypto/ghash-clmulni-intel_glue.c | 1 -
 arch/x86/crypto/sha1-mb/sha1_mb.c          | 1 -
 arch/x86/crypto/sha256-mb/sha256_mb.c      | 1 -
 arch/x86/crypto/sha512-mb/sha512_mb.c      | 1 -
 drivers/crypto/bcm/cipher.c                | 1 -
 drivers/crypto/caam/caamhash.c             | 1 -
 drivers/crypto/ccp/ccp-crypto-aes-cmac.c   | 1 -
 drivers/crypto/ccp/ccp-crypto-sha.c        | 1 -
 drivers/crypto/ccree/cc_hash.c             | 1 -
 drivers/crypto/chelsio/chcr_algo.c         | 1 -
 drivers/crypto/sunxi-ss/sun4i-ss-core.c    | 2 --
 drivers/crypto/talitos.c                   | 1 -
 drivers/crypto/ux500/hash/hash_core.c      | 3 ---
 14 files changed, 17 deletions(-)

diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 124fee03246e..8930fc4e7c22 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -310,7 +310,6 @@ static struct ahash_alg ghash_async_alg = {
 		.cra_priority	= 300,
 		.cra_flags	= CRYPTO_ALG_ASYNC,
 		.cra_blocksize	= GHASH_BLOCK_SIZE,
-		.cra_type	= &crypto_ahash_type,
 		.cra_ctxsize	= sizeof(struct ghash_async_ctx),
 		.cra_module	= THIS_MODULE,
 		.cra_init	= ghash_async_init_tfm,
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index a3de43b5e20a..3582ae885ee1 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -316,7 +316,6 @@ static struct ahash_alg ghash_async_alg = {
 			.cra_ctxsize		= sizeof(struct ghash_async_ctx),
 			.cra_flags		= CRYPTO_ALG_ASYNC,
 			.cra_blocksize		= GHASH_BLOCK_SIZE,
-			.cra_type		= &crypto_ahash_type,
 			.cra_module		= THIS_MODULE,
 			.cra_init		= ghash_async_init_tfm,
 			.cra_exit		= ghash_async_exit_tfm,
diff --git a/arch/x86/crypto/sha1-mb/sha1_mb.c b/arch/x86/crypto/sha1-mb/sha1_mb.c
index f7929ba6cfb4..b93805664c1d 100644
--- a/arch/x86/crypto/sha1-mb/sha1_mb.c
+++ b/arch/x86/crypto/sha1-mb/sha1_mb.c
@@ -880,7 +880,6 @@ static struct ahash_alg sha1_mb_async_alg = {
 			.cra_priority           = 50,
 			.cra_flags              = CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA1_BLOCK_SIZE,
-			.cra_type               = &crypto_ahash_type,
 			.cra_module             = THIS_MODULE,
 			.cra_list               = LIST_HEAD_INIT(sha1_mb_async_alg.halg.base.cra_list),
 			.cra_init               = sha1_mb_async_init_tfm,
diff --git a/arch/x86/crypto/sha256-mb/sha256_mb.c b/arch/x86/crypto/sha256-mb/sha256_mb.c
index 59a47048920a..97c5fc43e115 100644
--- a/arch/x86/crypto/sha256-mb/sha256_mb.c
+++ b/arch/x86/crypto/sha256-mb/sha256_mb.c
@@ -879,7 +879,6 @@ static struct ahash_alg sha256_mb_async_alg = {
 			.cra_priority           = 50,
 			.cra_flags              = CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA256_BLOCK_SIZE,
-			.cra_type               = &crypto_ahash_type,
 			.cra_module             = THIS_MODULE,
 			.cra_list               = LIST_HEAD_INIT
 				(sha256_mb_async_alg.halg.base.cra_list),
diff --git a/arch/x86/crypto/sha512-mb/sha512_mb.c b/arch/x86/crypto/sha512-mb/sha512_mb.c
index d3a758ac3ade..26b85678012d 100644
--- a/arch/x86/crypto/sha512-mb/sha512_mb.c
+++ b/arch/x86/crypto/sha512-mb/sha512_mb.c
@@ -913,7 +913,6 @@ static struct ahash_alg sha512_mb_async_alg = {
 			.cra_priority           = 50,
 			.cra_flags              = CRYPTO_ALG_ASYNC,
 			.cra_blocksize          = SHA512_BLOCK_SIZE,
-			.cra_type               = &crypto_ahash_type,
 			.cra_module             = THIS_MODULE,
 			.cra_list               = LIST_HEAD_INIT
 				(sha512_mb_async_alg.halg.base.cra_list),
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 2f85a989c476..4e2babd6b89d 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -4648,7 +4648,6 @@ static int spu_register_ahash(struct iproc_alg_s *driver_alg)
 	hash->halg.base.cra_ctxsize = sizeof(struct iproc_ctx_s);
 	hash->halg.base.cra_init = ahash_cra_init;
 	hash->halg.base.cra_exit = generic_cra_exit;
-	hash->halg.base.cra_type = &crypto_ahash_type;
 	hash->halg.base.cra_flags = CRYPTO_ALG_ASYNC;
 	hash->halg.statesize = sizeof(struct spu_hash_export_s);
 
diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
index a20123e28ce6..43975ab5f09c 100644
--- a/drivers/crypto/caam/caamhash.c
+++ b/drivers/crypto/caam/caamhash.c
@@ -1847,7 +1847,6 @@ caam_hash_alloc(struct caam_hash_template *template,
 	alg->cra_blocksize = template->blocksize;
 	alg->cra_alignmask = 0;
 	alg->cra_flags = CRYPTO_ALG_ASYNC;
-	alg->cra_type = &crypto_ahash_type;
 
 	t_alg->alg_type = template->alg_type;
 
diff --git a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
index bdc2715b3cac..3c6fe57f91f8 100644
--- a/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
+++ b/drivers/crypto/ccp/ccp-crypto-aes-cmac.c
@@ -405,7 +405,6 @@ int ccp_register_aes_cmac_algs(struct list_head *head)
 	base->cra_blocksize = AES_BLOCK_SIZE;
 	base->cra_ctxsize = sizeof(struct ccp_ctx);
 	base->cra_priority = CCP_CRA_PRIORITY;
-	base->cra_type = &crypto_ahash_type;
 	base->cra_init = ccp_aes_cmac_cra_init;
 	base->cra_exit = ccp_aes_cmac_cra_exit;
 	base->cra_module = THIS_MODULE;
diff --git a/drivers/crypto/ccp/ccp-crypto-sha.c b/drivers/crypto/ccp/ccp-crypto-sha.c
index 366d3e914ac5..2ca64bb57d2e 100644
--- a/drivers/crypto/ccp/ccp-crypto-sha.c
+++ b/drivers/crypto/ccp/ccp-crypto-sha.c
@@ -503,7 +503,6 @@ static int ccp_register_sha_alg(struct list_head *head,
 	base->cra_blocksize = def->block_size;
 	base->cra_ctxsize = sizeof(struct ccp_ctx);
 	base->cra_priority = CCP_CRA_PRIORITY;
-	base->cra_type = &crypto_ahash_type;
 	base->cra_init = ccp_sha_cra_init;
 	base->cra_exit = ccp_sha_cra_exit;
 	base->cra_module = THIS_MODULE;
diff --git a/drivers/crypto/ccree/cc_hash.c b/drivers/crypto/ccree/cc_hash.c
index 9cc7f8a95f96..1da6cec2d963 100644
--- a/drivers/crypto/ccree/cc_hash.c
+++ b/drivers/crypto/ccree/cc_hash.c
@@ -1814,7 +1814,6 @@ static struct cc_hash_alg *cc_alloc_hash_alg(struct cc_hash_template *template,
 
 	alg->cra_init = cc_cra_init;
 	alg->cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
-	alg->cra_type = &crypto_ahash_type;
 
 	t_crypto_alg->hash_mode = template->hash_mode;
 	t_crypto_alg->hw_mode = template->hw_mode;
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 6bbedf1bb7bd..915b1500393c 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -4260,7 +4260,6 @@ static int chcr_register_alg(void)
 			a_hash->halg.base.cra_flags = CRYPTO_ALG_ASYNC;
 			a_hash->halg.base.cra_alignmask = 0;
 			a_hash->halg.base.cra_exit = NULL;
-			a_hash->halg.base.cra_type = &crypto_ahash_type;
 
 			if (driver_algs[i].type == CRYPTO_ALG_TYPE_HMAC) {
 				a_hash->halg.base.cra_init = chcr_hmac_cra_init;
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
index d96bf7578569..1ff8fe684d31 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -48,7 +48,6 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_blocksize = MD5_HMAC_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
-				.cra_type = &crypto_ahash_type,
 				.cra_init = sun4i_hash_crainit
 			}
 		}
@@ -75,7 +74,6 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 				.cra_module = THIS_MODULE,
-				.cra_type = &crypto_ahash_type,
 				.cra_init = sun4i_hash_crainit
 			}
 		}
diff --git a/drivers/crypto/talitos.c b/drivers/crypto/talitos.c
index 323b46d2457d..6988012deca4 100644
--- a/drivers/crypto/talitos.c
+++ b/drivers/crypto/talitos.c
@@ -3174,7 +3174,6 @@ static struct talitos_crypto_alg *talitos_alg_alloc(struct device *dev,
 		alg = &t_alg->algt.alg.hash.halg.base;
 		alg->cra_init = talitos_cra_init_ahash;
 		alg->cra_exit = talitos_cra_exit;
-		alg->cra_type = &crypto_ahash_type;
 		t_alg->algt.alg.hash.init = ahash_init;
 		t_alg->algt.alg.hash.update = ahash_update;
 		t_alg->algt.alg.hash.final = ahash_final;
diff --git a/drivers/crypto/ux500/hash/hash_core.c b/drivers/crypto/ux500/hash/hash_core.c
index 7de22a646adf..daf4fed0df8c 100644
--- a/drivers/crypto/ux500/hash/hash_core.c
+++ b/drivers/crypto/ux500/hash/hash_core.c
@@ -1550,7 +1550,6 @@ static struct hash_algo_template hash_algs[] = {
 				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
-				.cra_type = &crypto_ahash_type,
 				.cra_init = hash_cra_init,
 				.cra_module = THIS_MODULE,
 			}
@@ -1575,7 +1574,6 @@ static struct hash_algo_template hash_algs[] = {
 				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA1_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
-				.cra_type = &crypto_ahash_type,
 				.cra_init = hash_cra_init,
 				.cra_module = THIS_MODULE,
 			}
@@ -1600,7 +1598,6 @@ static struct hash_algo_template hash_algs[] = {
 				.cra_flags = CRYPTO_ALG_ASYNC,
 				.cra_blocksize = SHA256_BLOCK_SIZE,
 				.cra_ctxsize = sizeof(struct hash_ctx),
-				.cra_type = &crypto_ahash_type,
 				.cra_init = hash_cra_init,
 				.cra_module = THIS_MODULE,
 			}
-- 
cgit v1.2.3


From 3f4a537a26a68600ed1439222fb5e5c3aa513c7a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:16:14 -0700
Subject: crypto: aead - remove useless setting of type flags

Some aead algorithms set .cra_flags = CRYPTO_ALG_TYPE_AEAD.  But this is
redundant with the C structure type ('struct aead_alg'), and
crypto_register_aead() already sets the type flag automatically,
clearing any type flag that was already there.  Apparently the useless
assignment has just been copy+pasted around.

So, remove the useless assignment from all the aead algorithms.

This patch shouldn't change any actual behavior.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/s390/crypto/aes_s390.c                    |  1 -
 crypto/aegis128.c                              |  1 -
 crypto/aegis128l.c                             |  1 -
 crypto/aegis256.c                              |  1 -
 crypto/morus1280.c                             |  1 -
 crypto/morus640.c                              |  1 -
 drivers/crypto/axis/artpec6_crypto.c           |  2 +-
 drivers/crypto/bcm/cipher.c                    |  2 +-
 drivers/crypto/chelsio/chcr_algo.c             |  3 +--
 drivers/crypto/inside-secure/safexcel_cipher.c | 10 +++++-----
 10 files changed, 8 insertions(+), 15 deletions(-)

diff --git a/arch/s390/crypto/aes_s390.c b/arch/s390/crypto/aes_s390.c
index ad47abd08630..c54cb26eb7f5 100644
--- a/arch/s390/crypto/aes_s390.c
+++ b/arch/s390/crypto/aes_s390.c
@@ -1035,7 +1035,6 @@ static struct aead_alg gcm_aes_aead = {
 	.chunksize		= AES_BLOCK_SIZE,
 
 	.base			= {
-		.cra_flags		= CRYPTO_ALG_TYPE_AEAD,
 		.cra_blocksize		= 1,
 		.cra_ctxsize		= sizeof(struct s390_aes_ctx),
 		.cra_priority		= 900,
diff --git a/crypto/aegis128.c b/crypto/aegis128.c
index 38271303ce16..c22f4414856d 100644
--- a/crypto/aegis128.c
+++ b/crypto/aegis128.c
@@ -429,7 +429,6 @@ static struct aead_alg crypto_aegis128_alg = {
 	.chunksize = AEGIS_BLOCK_SIZE,
 
 	.base = {
-		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
 		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct aegis_ctx),
 		.cra_alignmask = 0,
diff --git a/crypto/aegis128l.c b/crypto/aegis128l.c
index 64dc2654b863..b6fb21ebdc3e 100644
--- a/crypto/aegis128l.c
+++ b/crypto/aegis128l.c
@@ -493,7 +493,6 @@ static struct aead_alg crypto_aegis128l_alg = {
 	.chunksize = AEGIS128L_CHUNK_SIZE,
 
 	.base = {
-		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
 		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct aegis_ctx),
 		.cra_alignmask = 0,
diff --git a/crypto/aegis256.c b/crypto/aegis256.c
index a489d741d33a..11f0f8ec9c7c 100644
--- a/crypto/aegis256.c
+++ b/crypto/aegis256.c
@@ -444,7 +444,6 @@ static struct aead_alg crypto_aegis256_alg = {
 	.chunksize = AEGIS_BLOCK_SIZE,
 
 	.base = {
-		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
 		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct aegis_ctx),
 		.cra_alignmask = 0,
diff --git a/crypto/morus1280.c b/crypto/morus1280.c
index 6180b2557836..d057cf5ac4a8 100644
--- a/crypto/morus1280.c
+++ b/crypto/morus1280.c
@@ -514,7 +514,6 @@ static struct aead_alg crypto_morus1280_alg = {
 	.chunksize = MORUS1280_BLOCK_SIZE,
 
 	.base = {
-		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
 		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct morus1280_ctx),
 		.cra_alignmask = 0,
diff --git a/crypto/morus640.c b/crypto/morus640.c
index 9fbcde307daf..5c48a7cb899e 100644
--- a/crypto/morus640.c
+++ b/crypto/morus640.c
@@ -510,7 +510,6 @@ static struct aead_alg crypto_morus640_alg = {
 	.chunksize = MORUS640_BLOCK_SIZE,
 
 	.base = {
-		.cra_flags = CRYPTO_ALG_TYPE_AEAD,
 		.cra_blocksize = 1,
 		.cra_ctxsize = sizeof(struct morus640_ctx),
 		.cra_alignmask = 0,
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 049af6de3cb6..59392178d8bc 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -2964,7 +2964,7 @@ static struct aead_alg aead_algos[] = {
 			.cra_name = "gcm(aes)",
 			.cra_driver_name = "artpec-gcm-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = 1,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
diff --git a/drivers/crypto/bcm/cipher.c b/drivers/crypto/bcm/cipher.c
index 4e2babd6b89d..2d1f1db9f807 100644
--- a/drivers/crypto/bcm/cipher.c
+++ b/drivers/crypto/bcm/cipher.c
@@ -4689,7 +4689,7 @@ static int spu_register_aead(struct iproc_alg_s *driver_alg)
 	aead->base.cra_ctxsize = sizeof(struct iproc_ctx_s);
 	INIT_LIST_HEAD(&aead->base.cra_list);
 
-	aead->base.cra_flags |= CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
+	aead->base.cra_flags |= CRYPTO_ALG_ASYNC;
 	/* setkey set in alg initialization */
 	aead->setauthsize = aead_setauthsize;
 	aead->encrypt = aead_encrypt;
diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c
index 915b1500393c..5c539af8ed60 100644
--- a/drivers/crypto/chelsio/chcr_algo.c
+++ b/drivers/crypto/chelsio/chcr_algo.c
@@ -4236,8 +4236,7 @@ static int chcr_register_alg(void)
 			break;
 		case CRYPTO_ALG_TYPE_AEAD:
 			driver_algs[i].alg.aead.base.cra_flags =
-				CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
-				CRYPTO_ALG_NEED_FALLBACK;
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK;
 			driver_algs[i].alg.aead.encrypt = chcr_aead_encrypt;
 			driver_algs[i].alg.aead.decrypt = chcr_aead_decrypt;
 			driver_algs[i].alg.aead.init = chcr_aead_cra_init;
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 9d292427a488..19024500a895 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -1186,7 +1186,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha1_cbc_aes = {
 			.cra_name = "authenc(hmac(sha1),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha1-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -1221,7 +1221,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha256_cbc_aes = {
 			.cra_name = "authenc(hmac(sha256),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha256-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -1256,7 +1256,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha224_cbc_aes = {
 			.cra_name = "authenc(hmac(sha224),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha224-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -1291,7 +1291,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha512_cbc_aes = {
 			.cra_name = "authenc(hmac(sha512),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha512-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -1326,7 +1326,7 @@ struct safexcel_alg_template safexcel_alg_authenc_hmac_sha384_cbc_aes = {
 			.cra_name = "authenc(hmac(sha384),cbc(aes))",
 			.cra_driver_name = "safexcel-authenc-hmac-sha384-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
-- 
cgit v1.2.3


From 2c95e6d97892235b5b98cd4805e47fac87c2226f Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:16:15 -0700
Subject: crypto: skcipher - remove useless setting of type flags

Some skcipher algorithms set .cra_flags = CRYPTO_ALG_TYPE_SKCIPHER.  But
this is redundant with the C structure type ('struct skcipher_alg'), and
crypto_register_skcipher() already sets the type flag automatically,
clearing any type flag that was already there.  Apparently the useless
assignment has just been copy+pasted around.

So, remove the useless assignment from all the skcipher algorithms.

This patch shouldn't change any actual behavior.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/amcc/crypto4xx_core.c           | 18 ++++++------------
 drivers/crypto/axis/artpec6_crypto.c           | 12 ++++--------
 drivers/crypto/ccree/cc_cipher.c               |  3 +--
 drivers/crypto/inside-secure/safexcel_cipher.c |  4 ++--
 drivers/crypto/sunxi-ss/sun4i-ss-core.c        | 16 +++++-----------
 5 files changed, 18 insertions(+), 35 deletions(-)

diff --git a/drivers/crypto/amcc/crypto4xx_core.c b/drivers/crypto/amcc/crypto4xx_core.c
index 05981ccd9901..6eaec9ba0f68 100644
--- a/drivers/crypto/amcc/crypto4xx_core.c
+++ b/drivers/crypto/amcc/crypto4xx_core.c
@@ -1132,8 +1132,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "cbc(aes)",
 			.cra_driver_name = "cbc-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1153,8 +1152,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "cfb(aes)",
 			.cra_driver_name = "cfb-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1174,8 +1172,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "ctr(aes)",
 			.cra_driver_name = "ctr-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_NEED_FALLBACK |
+			.cra_flags = CRYPTO_ALG_NEED_FALLBACK |
 				CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
@@ -1196,8 +1193,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "rfc3686(ctr(aes))",
 			.cra_driver_name = "rfc3686-ctr-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1217,8 +1213,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "ecb(aes)",
 			.cra_driver_name = "ecb-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
@@ -1237,8 +1232,7 @@ static struct crypto4xx_alg_common crypto4xx_alg[] = {
 			.cra_name = "ofb(aes)",
 			.cra_driver_name = "ofb-aes-ppc4xx",
 			.cra_priority = CRYPTO4XX_CRYPTO_PRIORITY,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct crypto4xx_ctx),
diff --git a/drivers/crypto/axis/artpec6_crypto.c b/drivers/crypto/axis/artpec6_crypto.c
index 59392178d8bc..7f07a5085e9b 100644
--- a/drivers/crypto/axis/artpec6_crypto.c
+++ b/drivers/crypto/axis/artpec6_crypto.c
@@ -2867,8 +2867,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "ecb(aes)",
 			.cra_driver_name = "artpec6-ecb-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
 			.cra_alignmask = 3,
@@ -2888,8 +2887,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "ctr(aes)",
 			.cra_driver_name = "artpec6-ctr-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_NEED_FALLBACK,
 			.cra_blocksize = 1,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
@@ -2911,8 +2909,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "cbc(aes)",
 			.cra_driver_name = "artpec6-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
 			.cra_alignmask = 3,
@@ -2933,8 +2930,7 @@ static struct skcipher_alg crypto_algos[] = {
 			.cra_name = "xts(aes)",
 			.cra_driver_name = "artpec6-xts-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_ASYNC,
+			.cra_flags = CRYPTO_ALG_ASYNC,
 			.cra_blocksize = 1,
 			.cra_ctxsize = sizeof(struct artpec6_cryptotfm_context),
 			.cra_alignmask = 3,
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index d2810c183b73..ec9f561e9387 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -1338,8 +1338,7 @@ static struct cc_crypto_alg *cc_create_alg(const struct cc_alg_template *tmpl,
 
 	alg->base.cra_init = cc_cipher_init;
 	alg->base.cra_exit = cc_cipher_exit;
-	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY |
-				CRYPTO_ALG_TYPE_SKCIPHER;
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 
 	t_alg->cipher_mode = tmpl->cipher_mode;
 	t_alg->flow_mode = tmpl->flow_mode;
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 19024500a895..1ae3c28fa898 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -863,7 +863,7 @@ struct safexcel_alg_template safexcel_alg_ecb_aes = {
 			.cra_name = "ecb(aes)",
 			.cra_driver_name = "safexcel-ecb-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
@@ -903,7 +903,7 @@ struct safexcel_alg_template safexcel_alg_cbc_aes = {
 			.cra_name = "cbc(aes)",
 			.cra_driver_name = "safexcel-cbc-aes",
 			.cra_priority = 300,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER | CRYPTO_ALG_ASYNC |
+			.cra_flags = CRYPTO_ALG_ASYNC |
 				     CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_blocksize = AES_BLOCK_SIZE,
 			.cra_ctxsize = sizeof(struct safexcel_cipher_ctx),
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-core.c b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
index 1ff8fe684d31..89adf9e0fed2 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-core.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-core.c
@@ -92,8 +92,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-aes-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -114,8 +113,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "ecb-aes-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = AES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_tfm_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -136,8 +134,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-des-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -157,8 +154,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "ecb-des-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -179,8 +175,7 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "cbc-des3-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER |
-				     CRYPTO_ALG_KERN_DRIVER_ONLY,
+			.cra_flags = CRYPTO_ALG_KERN_DRIVER_ONLY,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
@@ -201,7 +196,6 @@ static struct sun4i_ss_alg_template ss_algs[] = {
 			.cra_driver_name = "ecb-des3-sun4i-ss",
 			.cra_priority = 300,
 			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
-			.cra_flags = CRYPTO_ALG_TYPE_SKCIPHER,
 			.cra_ctxsize = sizeof(struct sun4i_req_ctx),
 			.cra_module = THIS_MODULE,
 			.cra_alignmask = 3,
-- 
cgit v1.2.3


From 85d7311f1908b9ca20c10c2c23f5dbb93875f0c6 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Sat, 30 Jun 2018 15:16:16 -0700
Subject: crypto: remove redundant type flags from tfm allocation

Some crypto API users allocating a tfm with crypto_alloc_$FOO() are also
specifying the type flags for $FOO, e.g. crypto_alloc_shash() with
CRYPTO_ALG_TYPE_SHASH.  But, that's redundant since the crypto API will
override any specified type flag/mask with the correct ones.

So, remove the unneeded flags.

This patch shouldn't change any actual behavior.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/crypto/api-samples.rst         | 2 +-
 drivers/crypto/atmel-sha.c                   | 4 +---
 drivers/crypto/inside-secure/safexcel_hash.c | 3 +--
 drivers/crypto/marvell/hash.c                | 3 +--
 drivers/crypto/qce/sha.c                     | 3 +--
 security/keys/dh.c                           | 2 +-
 6 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/Documentation/crypto/api-samples.rst b/Documentation/crypto/api-samples.rst
index 006827e30d06..0f6ca8b7261e 100644
--- a/Documentation/crypto/api-samples.rst
+++ b/Documentation/crypto/api-samples.rst
@@ -162,7 +162,7 @@ Code Example For Use of Operational State Memory With SHASH
         char *hash_alg_name = "sha1-padlock-nano";
         int ret;
 
-        alg = crypto_alloc_shash(hash_alg_name, CRYPTO_ALG_TYPE_SHASH, 0);
+        alg = crypto_alloc_shash(hash_alg_name, 0, 0);
         if (IS_ERR(alg)) {
                 pr_info("can't alloc alg %s\n", hash_alg_name);
                 return PTR_ERR(alg);
diff --git a/drivers/crypto/atmel-sha.c b/drivers/crypto/atmel-sha.c
index 4d43081120db..8a19df2fba6a 100644
--- a/drivers/crypto/atmel-sha.c
+++ b/drivers/crypto/atmel-sha.c
@@ -2316,9 +2316,7 @@ struct atmel_sha_authenc_ctx *atmel_sha_authenc_spawn(unsigned long mode)
 		goto error;
 	}
 
-	tfm = crypto_alloc_ahash(name,
-				 CRYPTO_ALG_TYPE_AHASH,
-				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	tfm = crypto_alloc_ahash(name, 0, 0);
 	if (IS_ERR(tfm)) {
 		err = PTR_ERR(tfm);
 		goto error;
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 83bd49d1249b..6a790f069ebf 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -941,8 +941,7 @@ int safexcel_hmac_setkey(const char *alg, const u8 *key, unsigned int keylen,
 	u8 *ipad, *opad;
 	int ret;
 
-	tfm = crypto_alloc_ahash(alg, CRYPTO_ALG_TYPE_AHASH,
-				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	tfm = crypto_alloc_ahash(alg, 0, 0);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index e34d80b6b7e5..99ff54cc8a15 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -1183,8 +1183,7 @@ static int mv_cesa_ahmac_setkey(const char *hash_alg_name,
 	u8 *opad;
 	int ret;
 
-	tfm = crypto_alloc_ahash(hash_alg_name, CRYPTO_ALG_TYPE_AHASH,
-				 CRYPTO_ALG_TYPE_AHASH_MASK);
+	tfm = crypto_alloc_ahash(hash_alg_name, 0, 0);
 	if (IS_ERR(tfm))
 		return PTR_ERR(tfm);
 
diff --git a/drivers/crypto/qce/sha.c b/drivers/crypto/qce/sha.c
index 53227d70d397..d8a5db11b7ea 100644
--- a/drivers/crypto/qce/sha.c
+++ b/drivers/crypto/qce/sha.c
@@ -378,8 +378,7 @@ static int qce_ahash_hmac_setkey(struct crypto_ahash *tfm, const u8 *key,
 	else
 		return -EINVAL;
 
-	ahash_tfm = crypto_alloc_ahash(alg_name, CRYPTO_ALG_TYPE_AHASH,
-				       CRYPTO_ALG_TYPE_AHASH_MASK);
+	ahash_tfm = crypto_alloc_ahash(alg_name, 0, 0);
 	if (IS_ERR(ahash_tfm))
 		return PTR_ERR(ahash_tfm);
 
diff --git a/security/keys/dh.c b/security/keys/dh.c
index f7403821db7f..04072cb59a98 100644
--- a/security/keys/dh.c
+++ b/security/keys/dh.c
@@ -315,7 +315,7 @@ long __keyctl_dh_compute(struct keyctl_dh_params __user *params,
 	if (ret)
 		goto out3;
 
-	tfm = crypto_alloc_kpp("dh", CRYPTO_ALG_TYPE_KPP, 0);
+	tfm = crypto_alloc_kpp("dh", 0, 0);
 	if (IS_ERR(tfm)) {
 		ret = PTR_ERR(tfm);
 		goto out3;
-- 
cgit v1.2.3


From 26497e72a1aba4d27c50c4cbf0182db94e58a590 Mon Sep 17 00:00:00 2001
From: Hadar Gat <hadar.gat@arm.com>
Date: Sun, 1 Jul 2018 08:02:34 +0100
Subject: crypto: ccree - fix finup

finup() operation was incorrect, padding was missing.
Fix by setting the ccree HW to enable padding.

Signed-off-by: Hadar Gat <hadar.gat@arm.com>
[ gilad@benyossef.com: refactored for better code sharing ]
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: stable@vger.kernel.org
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_hash.c | 81 +++++++++---------------------------------
 1 file changed, 16 insertions(+), 65 deletions(-)

diff --git a/drivers/crypto/ccree/cc_hash.c b/drivers/crypto/ccree/cc_hash.c
index 1da6cec2d963..b9313306c36f 100644
--- a/drivers/crypto/ccree/cc_hash.c
+++ b/drivers/crypto/ccree/cc_hash.c
@@ -602,66 +602,7 @@ static int cc_hash_update(struct ahash_request *req)
 	return rc;
 }
 
-static int cc_hash_finup(struct ahash_request *req)
-{
-	struct ahash_req_ctx *state = ahash_request_ctx(req);
-	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-	struct cc_hash_ctx *ctx = crypto_ahash_ctx(tfm);
-	u32 digestsize = crypto_ahash_digestsize(tfm);
-	struct scatterlist *src = req->src;
-	unsigned int nbytes = req->nbytes;
-	u8 *result = req->result;
-	struct device *dev = drvdata_to_dev(ctx->drvdata);
-	bool is_hmac = ctx->is_hmac;
-	struct cc_crypto_req cc_req = {};
-	struct cc_hw_desc desc[CC_MAX_HASH_SEQ_LEN];
-	unsigned int idx = 0;
-	int rc;
-	gfp_t flags = cc_gfp_flags(&req->base);
-
-	dev_dbg(dev, "===== %s-finup (%d) ====\n", is_hmac ? "hmac" : "hash",
-		nbytes);
-
-	if (cc_map_req(dev, state, ctx)) {
-		dev_err(dev, "map_ahash_source() failed\n");
-		return -EINVAL;
-	}
-
-	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, 1,
-				      flags)) {
-		dev_err(dev, "map_ahash_request_final() failed\n");
-		cc_unmap_req(dev, state, ctx);
-		return -ENOMEM;
-	}
-	if (cc_map_result(dev, state, digestsize)) {
-		dev_err(dev, "map_ahash_digest() failed\n");
-		cc_unmap_hash_request(dev, state, src, true);
-		cc_unmap_req(dev, state, ctx);
-		return -ENOMEM;
-	}
-
-	/* Setup request structure */
-	cc_req.user_cb = cc_hash_complete;
-	cc_req.user_arg = req;
-
-	idx = cc_restore_hash(desc, ctx, state, idx);
-
-	if (is_hmac)
-		idx = cc_fin_hmac(desc, req, idx);
-
-	idx = cc_fin_result(desc, req, idx);
-
-	rc = cc_send_request(ctx->drvdata, &cc_req, desc, idx, &req->base);
-	if (rc != -EINPROGRESS && rc != -EBUSY) {
-		dev_err(dev, "send_request() failed (rc=%d)\n", rc);
-		cc_unmap_hash_request(dev, state, src, true);
-		cc_unmap_result(dev, state, digestsize, result);
-		cc_unmap_req(dev, state, ctx);
-	}
-	return rc;
-}
-
-static int cc_hash_final(struct ahash_request *req)
+static int cc_do_finup(struct ahash_request *req, bool update)
 {
 	struct ahash_req_ctx *state = ahash_request_ctx(req);
 	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
@@ -678,21 +619,20 @@ static int cc_hash_final(struct ahash_request *req)
 	int rc;
 	gfp_t flags = cc_gfp_flags(&req->base);
 
-	dev_dbg(dev, "===== %s-final (%d) ====\n", is_hmac ? "hmac" : "hash",
-		nbytes);
+	dev_dbg(dev, "===== %s-%s (%d) ====\n", is_hmac ? "hmac" : "hash",
+		update ? "finup" : "final", nbytes);
 
 	if (cc_map_req(dev, state, ctx)) {
 		dev_err(dev, "map_ahash_source() failed\n");
 		return -EINVAL;
 	}
 
-	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, 0,
+	if (cc_map_hash_request_final(ctx->drvdata, state, src, nbytes, update,
 				      flags)) {
 		dev_err(dev, "map_ahash_request_final() failed\n");
 		cc_unmap_req(dev, state, ctx);
 		return -ENOMEM;
 	}
-
 	if (cc_map_result(dev, state, digestsize)) {
 		dev_err(dev, "map_ahash_digest() failed\n");
 		cc_unmap_hash_request(dev, state, src, true);
@@ -706,7 +646,7 @@ static int cc_hash_final(struct ahash_request *req)
 
 	idx = cc_restore_hash(desc, ctx, state, idx);
 
-	/* "DO-PAD" must be enabled only when writing current length to HW */
+	/* Pad the hash */
 	hw_desc_init(&desc[idx]);
 	set_cipher_do(&desc[idx], DO_PAD);
 	set_cipher_mode(&desc[idx], ctx->hw_mode);
@@ -731,6 +671,17 @@ static int cc_hash_final(struct ahash_request *req)
 	return rc;
 }
 
+static int cc_hash_finup(struct ahash_request *req)
+{
+	return cc_do_finup(req, true);
+}
+
+
+static int cc_hash_final(struct ahash_request *req)
+{
+	return cc_do_finup(req, false);
+}
+
 static int cc_hash_init(struct ahash_request *req)
 {
 	struct ahash_req_ctx *state = ahash_request_ctx(req);
-- 
cgit v1.2.3


From 76715095933b3a2e6082e171bc82ecd90baf9af0 Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Sun, 1 Jul 2018 08:02:35 +0100
Subject: crypto: testmgr - add hash finup tests

The testmgr hash tests were testing init, digest, update and final
methods but not the finup method. Add a test for this one too.

While doing this, make sure we only run the partial tests once with
the digest tests and skip them with the final and finup tests since
they are the same.

Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/testmgr.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 46 insertions(+), 9 deletions(-)

diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 63f263fd1dae..a1d42245082a 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -259,9 +259,15 @@ out_nostate:
 	return ret;
 }
 
+enum hash_test {
+	HASH_TEST_DIGEST,
+	HASH_TEST_FINAL,
+	HASH_TEST_FINUP
+};
+
 static int __test_hash(struct crypto_ahash *tfm,
 		       const struct hash_testvec *template, unsigned int tcount,
-		       bool use_digest, const int align_offset)
+		       enum hash_test test_type, const int align_offset)
 {
 	const char *algo = crypto_tfm_alg_driver_name(crypto_ahash_tfm(tfm));
 	size_t digest_size = crypto_ahash_digestsize(tfm);
@@ -332,14 +338,17 @@ static int __test_hash(struct crypto_ahash *tfm,
 		}
 
 		ahash_request_set_crypt(req, sg, result, template[i].psize);
-		if (use_digest) {
+		switch (test_type) {
+		case HASH_TEST_DIGEST:
 			ret = crypto_wait_req(crypto_ahash_digest(req), &wait);
 			if (ret) {
 				pr_err("alg: hash: digest failed on test %d "
 				       "for %s: ret=%d\n", j, algo, -ret);
 				goto out;
 			}
-		} else {
+			break;
+
+		case HASH_TEST_FINAL:
 			memset(result, 1, digest_size);
 			ret = crypto_wait_req(crypto_ahash_init(req), &wait);
 			if (ret) {
@@ -371,6 +380,29 @@ static int __test_hash(struct crypto_ahash *tfm,
 				       "for %s: ret=%d\n", j, algo, -ret);
 				goto out;
 			}
+			break;
+
+		case HASH_TEST_FINUP:
+			memset(result, 1, digest_size);
+			ret = crypto_wait_req(crypto_ahash_init(req), &wait);
+			if (ret) {
+				pr_err("alg: hash: init failed on test %d "
+				       "for %s: ret=%d\n", j, algo, -ret);
+				goto out;
+			}
+			ret = ahash_guard_result(result, 1, digest_size);
+			if (ret) {
+				pr_err("alg: hash: init failed on test %d "
+				       "for %s: used req->result\n", j, algo);
+				goto out;
+			}
+			ret = crypto_wait_req(crypto_ahash_finup(req), &wait);
+			if (ret) {
+				pr_err("alg: hash: final failed on test %d "
+				       "for %s: ret=%d\n", j, algo, -ret);
+				goto out;
+			}
+			break;
 		}
 
 		if (memcmp(result, template[i].digest,
@@ -383,6 +415,9 @@ static int __test_hash(struct crypto_ahash *tfm,
 		}
 	}
 
+	if (test_type)
+		goto out;
+
 	j = 0;
 	for (i = 0; i < tcount; i++) {
 		/* alignment tests are only done with continuous buffers */
@@ -540,24 +575,24 @@ out_nobuf:
 
 static int test_hash(struct crypto_ahash *tfm,
 		     const struct hash_testvec *template,
-		     unsigned int tcount, bool use_digest)
+		     unsigned int tcount, enum hash_test test_type)
 {
 	unsigned int alignmask;
 	int ret;
 
-	ret = __test_hash(tfm, template, tcount, use_digest, 0);
+	ret = __test_hash(tfm, template, tcount, test_type, 0);
 	if (ret)
 		return ret;
 
 	/* test unaligned buffers, check with one byte offset */
-	ret = __test_hash(tfm, template, tcount, use_digest, 1);
+	ret = __test_hash(tfm, template, tcount, test_type, 1);
 	if (ret)
 		return ret;
 
 	alignmask = crypto_tfm_alg_alignmask(&tfm->base);
 	if (alignmask) {
 		/* Check if alignment mask for tfm is correctly set. */
-		ret = __test_hash(tfm, template, tcount, use_digest,
+		ret = __test_hash(tfm, template, tcount, test_type,
 				  alignmask + 1);
 		if (ret)
 			return ret;
@@ -1803,9 +1838,11 @@ static int __alg_test_hash(const struct hash_testvec *template,
 		return PTR_ERR(tfm);
 	}
 
-	err = test_hash(tfm, template, tcount, true);
+	err = test_hash(tfm, template, tcount, HASH_TEST_DIGEST);
+	if (!err)
+		err = test_hash(tfm, template, tcount, HASH_TEST_FINAL);
 	if (!err)
-		err = test_hash(tfm, template, tcount, false);
+		err = test_hash(tfm, template, tcount, HASH_TEST_FINUP);
 	crypto_free_ahash(tfm);
 	return err;
 }
-- 
cgit v1.2.3


From 00904aa0cd59a36d659ec93d272309e2174bcb5b Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Sun, 1 Jul 2018 08:02:36 +0100
Subject: crypto: ccree - fix iv handling

We were copying our last cipher block into the request for use as IV for
all modes of operations. Fix this by discerning the behaviour based on
the mode of operation used: copy ciphertext for CBC, update counter for
CTR.

CC: stable@vger.kernel.org
Fixes: 63ee04c8b491 ("crypto: ccree - add skcipher support")
Reported by: Hadar Gat <hadar.gat@arm.com>
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_cipher.c | 111 +++++++++++++++++++++++++++++----------
 1 file changed, 84 insertions(+), 27 deletions(-)

diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index ec9f561e9387..b119a73c491d 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -593,34 +593,82 @@ static void cc_setup_cipher_data(struct crypto_tfm *tfm,
 	}
 }
 
+/*
+ * Update a CTR-AES 128 bit counter
+ */
+static void cc_update_ctr(u8 *ctr, unsigned int increment)
+{
+	if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) ||
+	    IS_ALIGNED((unsigned long)ctr, 8)) {
+
+		__be64 *high_be = (__be64 *)ctr;
+		__be64 *low_be = high_be + 1;
+		u64 orig_low = __be64_to_cpu(*low_be);
+		u64 new_low = orig_low + (u64)increment;
+
+		*low_be = __cpu_to_be64(new_low);
+
+		if (new_low < orig_low)
+			*high_be = __cpu_to_be64(__be64_to_cpu(*high_be) + 1);
+	} else {
+		u8 *pos = (ctr + AES_BLOCK_SIZE);
+		u8 val;
+		unsigned int size;
+
+		for (; increment; increment--)
+			for (size = AES_BLOCK_SIZE; size; size--) {
+				val = *--pos + 1;
+				*pos = val;
+				if (val)
+					break;
+			}
+	}
+}
+
 static void cc_cipher_complete(struct device *dev, void *cc_req, int err)
 {
 	struct skcipher_request *req = (struct skcipher_request *)cc_req;
 	struct scatterlist *dst = req->dst;
 	struct scatterlist *src = req->src;
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
-	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
-	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
+	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(sk_tfm);
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
+	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
+	unsigned int len;
 
-	cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
-	kzfree(req_ctx->iv);
+	switch (ctx_p->cipher_mode) {
+	case DRV_CIPHER_CBC:
+		/*
+		 * The crypto API expects us to set the req->iv to the last
+		 * ciphertext block. For encrypt, simply copy from the result.
+		 * For decrypt, we must copy from a saved buffer since this
+		 * could be an in-place decryption operation and the src is
+		 * lost by this point.
+		 */
+		if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT)  {
+			memcpy(req->iv, req_ctx->backup_info, ivsize);
+			kzfree(req_ctx->backup_info);
+		} else if (!err) {
+			len = req->cryptlen - ivsize;
+			scatterwalk_map_and_copy(req->iv, req->dst, len,
+						 ivsize, 0);
+		}
+		break;
 
-	/*
-	 * The crypto API expects us to set the req->iv to the last
-	 * ciphertext block. For encrypt, simply copy from the result.
-	 * For decrypt, we must copy from a saved buffer since this
-	 * could be an in-place decryption operation and the src is
-	 * lost by this point.
-	 */
-	if (req_ctx->gen_ctx.op_type == DRV_CRYPTO_DIRECTION_DECRYPT)  {
-		memcpy(req->iv, req_ctx->backup_info, ivsize);
-		kzfree(req_ctx->backup_info);
-	} else if (!err) {
-		scatterwalk_map_and_copy(req->iv, req->dst,
-					 (req->cryptlen - ivsize),
-					 ivsize, 0);
+	case DRV_CIPHER_CTR:
+		/* Compute the counter of the last block */
+		len = ALIGN(req->cryptlen, AES_BLOCK_SIZE) / AES_BLOCK_SIZE;
+		cc_update_ctr((u8 *)req->iv, len);
+		break;
+
+	default:
+		break;
 	}
 
+	cc_unmap_cipher_request(dev, req_ctx, ivsize, src, dst);
+	kzfree(req_ctx->iv);
+
 	skcipher_request_complete(req, err);
 }
 
@@ -752,20 +800,29 @@ static int cc_cipher_encrypt(struct skcipher_request *req)
 static int cc_cipher_decrypt(struct skcipher_request *req)
 {
 	struct crypto_skcipher *sk_tfm = crypto_skcipher_reqtfm(req);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(sk_tfm);
+	struct cc_cipher_ctx *ctx_p = crypto_tfm_ctx(tfm);
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
 	unsigned int ivsize = crypto_skcipher_ivsize(sk_tfm);
 	gfp_t flags = cc_gfp_flags(&req->base);
+	unsigned int len;
 
-	/*
-	 * Allocate and save the last IV sized bytes of the source, which will
-	 * be lost in case of in-place decryption and might be needed for CTS.
-	 */
-	req_ctx->backup_info = kmalloc(ivsize, flags);
-	if (!req_ctx->backup_info)
-		return -ENOMEM;
+	if (ctx_p->cipher_mode == DRV_CIPHER_CBC) {
+
+		/* Allocate and save the last IV sized bytes of the source,
+		 * which will be lost in case of in-place decryption.
+		 */
+		req_ctx->backup_info = kzalloc(ivsize, flags);
+		if (!req_ctx->backup_info)
+			return -ENOMEM;
+
+		len = req->cryptlen - ivsize;
+		scatterwalk_map_and_copy(req_ctx->backup_info, req->src, len,
+					 ivsize, 0);
+	} else {
+		req_ctx->backup_info = NULL;
+	}
 
-	scatterwalk_map_and_copy(req_ctx->backup_info, req->src,
-				 (req->cryptlen - ivsize), ivsize, 0);
 	req_ctx->is_giv = false;
 
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_DECRYPT);
-- 
cgit v1.2.3


From d6b609d1b8e99694cfc47180e395f14fde68addb Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Sun, 1 Jul 2018 08:02:37 +0100
Subject: crypto: ccree - remove dead legacy code

Remove legacy code no longer used by anything.

Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_cipher.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index b119a73c491d..a37934f72d12 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -730,12 +730,6 @@ static int cc_cipher_process(struct skcipher_request *req,
 	cc_req.user_cb = (void *)cc_cipher_complete;
 	cc_req.user_arg = (void *)req;
 
-#ifdef ENABLE_CYCLE_COUNT
-	cc_req.op_type = (direction == DRV_CRYPTO_DIRECTION_DECRYPT) ?
-		STAT_OP_TYPE_DECODE : STAT_OP_TYPE_ENCODE;
-
-#endif
-
 	/* Setup request context */
 	req_ctx->gen_ctx.op_type = direction;
 
-- 
cgit v1.2.3


From 84f366dadc6a03dd39a3f4b2fc63347f04a56628 Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Sun, 1 Jul 2018 08:02:38 +0100
Subject: crypto: ccree - use CBC-CS3 CTS mode

The ccree driver implemented NIST 800-38A CBC-CS2 ciphertext format,
which only reverses the last two blocks if the stolen ciphertext amount
are none zero. Move it to the kernel chosen format of CBC-CS3  which swaps
the final blocks unconditionally and rename it to "cts" now that it
complies with the kernel format and passes the self tests.

Ironically, the CryptoCell REE HW does just that, so the fix is dropping
the code that forced it to use plain CBC if the ciphertext was block
aligned.

Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_cipher.c | 20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)

diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index a37934f72d12..1100185215ac 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -687,7 +687,7 @@ static int cc_cipher_process(struct skcipher_request *req,
 	struct device *dev = drvdata_to_dev(ctx_p->drvdata);
 	struct cc_hw_desc desc[MAX_ABLKCIPHER_SEQ_LEN];
 	struct cc_crypto_req cc_req = {};
-	int rc, cts_restore_flag = 0;
+	int rc;
 	unsigned int seq_len = 0;
 	gfp_t flags = cc_gfp_flags(&req->base);
 
@@ -719,13 +719,6 @@ static int cc_cipher_process(struct skcipher_request *req,
 		goto exit_process;
 	}
 
-	/*For CTS in case of data size aligned to 16 use CBC mode*/
-	if (((nbytes % AES_BLOCK_SIZE) == 0) &&
-	    ctx_p->cipher_mode == DRV_CIPHER_CBC_CTS) {
-		ctx_p->cipher_mode = DRV_CIPHER_CBC;
-		cts_restore_flag = 1;
-	}
-
 	/* Setup request structure */
 	cc_req.user_cb = (void *)cc_cipher_complete;
 	cc_req.user_arg = (void *)req;
@@ -770,9 +763,6 @@ static int cc_cipher_process(struct skcipher_request *req,
 	}
 
 exit_process:
-	if (cts_restore_flag)
-		ctx_p->cipher_mode = DRV_CIPHER_CBC_CTS;
-
 	if (rc != -EINPROGRESS && rc != -EBUSY) {
 		kzfree(req_ctx->backup_info);
 		kzfree(req_ctx->iv);
@@ -1026,8 +1016,8 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.min_hw_rev = CC_HW_REV_712,
 	},
 	{
-		.name = "cts1(cbc(paes))",
-		.driver_name = "cts1-cbc-paes-ccree",
+		.name = "cts(cbc(paes))",
+		.driver_name = "cts-cbc-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
 		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
@@ -1261,8 +1251,8 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.min_hw_rev = CC_HW_REV_630,
 	},
 	{
-		.name = "cts1(cbc(aes))",
-		.driver_name = "cts1-cbc-aes-ccree",
+		.name = "cts(cbc(aes))",
+		.driver_name = "cts-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
 		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
-- 
cgit v1.2.3


From 5c324a2ffa06f8b6fda59a77c6807acb9f45cfee Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Sun, 1 Jul 2018 08:02:39 +0100
Subject: crypto: ccree - rate limit debug print

A debug print about register status post interrupt can happen
quite often. Rate limit it to avoid cluttering the log.

Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Reported-by: Geert Uytterhoeven <geert@linux-m68k.org>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_driver.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/ccree/cc_driver.c b/drivers/crypto/ccree/cc_driver.c
index bd974fef05e4..1ff229c2aeab 100644
--- a/drivers/crypto/ccree/cc_driver.c
+++ b/drivers/crypto/ccree/cc_driver.c
@@ -131,8 +131,8 @@ static irqreturn_t cc_isr(int irq, void *dev_id)
 	}
 
 	if (irr) {
-		dev_dbg(dev, "IRR includes unknown cause bits (0x%08X)\n",
-			irr);
+		dev_dbg_ratelimited(dev, "IRR includes unknown cause bits (0x%08X)\n",
+				    irr);
 		/* Just warning */
 	}
 
-- 
cgit v1.2.3


From f7b3182232c82bb9769e2d5471d702bae2972d2b Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Fri, 29 Jun 2018 17:38:14 +0300
Subject: clk: tegra: bpmp: Don't crash when a clock fails to register

When registering clocks, we just skip any that fail to register
(leaving a NULL hole in the clock table). However, our of_xlate
function still tries to dereference each entry while looking for
the clock with the requested id, causing a crash if any clocks
failed to register. Add a check to of_xlate to skip any NULL
clocks.

Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk-bpmp.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/tegra/clk-bpmp.c b/drivers/clk/tegra/clk-bpmp.c
index a896692b74ec..01dada561c10 100644
--- a/drivers/clk/tegra/clk-bpmp.c
+++ b/drivers/clk/tegra/clk-bpmp.c
@@ -586,9 +586,15 @@ static struct clk_hw *tegra_bpmp_clk_of_xlate(struct of_phandle_args *clkspec,
 	unsigned int id = clkspec->args[0], i;
 	struct tegra_bpmp *bpmp = data;
 
-	for (i = 0; i < bpmp->num_clocks; i++)
-		if (bpmp->clocks[i]->id == id)
-			return &bpmp->clocks[i]->hw;
+	for (i = 0; i < bpmp->num_clocks; i++) {
+		struct tegra_bpmp_clk *clk = bpmp->clocks[i];
+
+		if (!clk)
+			continue;
+
+		if (clk->id == id)
+			return &clk->hw;
+	}
 
 	return NULL;
 }
-- 
cgit v1.2.3


From 69448867abcb231afaa7891ff9d9fd04b2b94a0d Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Thu, 5 Jul 2018 09:25:43 +0300
Subject: fs: shave 8 bytes off of struct inode

Here is a link to Linus' reply to Jan's concern about making
i_blkbibts byte addressable:
https://marc.info/?l=linux-fsdevel&m=152882624707975&w=2

Here is a link to an lkp.org report about potential performance
improvement in some workload, which could(?) be related to packing
i_blkbits closer to i_bytes/i_lock:
https://marc.info/?l=linux-fsdevel&m=153077048108198&w=2

Changes since v1:
- Add links to relevant discussions

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index f140c11d35dd..9b00676f5d9d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -275,6 +275,7 @@ struct writeback_control;
 
 /*
  * Write life time hint values.
+ * Stored in struct inode as u8.
  */
 enum rw_hint {
 	WRITE_LIFE_NOT_SET	= 0,
@@ -609,8 +610,8 @@ struct inode {
 	struct timespec64	i_ctime;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
-	unsigned int		i_blkbits;
-	enum rw_hint		i_write_hint;
+	u8			i_blkbits;
+	u8			i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
-- 
cgit v1.2.3


From 26f8590c4a1f7bd30ef9b9d713388bd96eb43d16 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Mon, 11 Jun 2018 10:18:53 +0200
Subject: clk: tegra: Make vic03 a child of pll_c3

By default, the vic03 clock is a child of pll_m but that runs at 924 MHz
which is too fast for VIC. Make vic03 a child of pll_c3 by default so it
will run at a supported frequency.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk-tegra124.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index 0c69c7970950..f5048f82c0b9 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -1290,6 +1290,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = {
 	{ TEGRA124_CLK_MSELECT, TEGRA124_CLK_CLK_MAX, 0, 1 },
 	{ TEGRA124_CLK_CSITE, TEGRA124_CLK_CLK_MAX, 0, 1 },
 	{ TEGRA124_CLK_TSENSOR, TEGRA124_CLK_CLK_M, 400000, 0 },
+	{ TEGRA124_CLK_VIC03, TEGRA124_CLK_PLL_C3, 0, 0 },
 	/* must be the last entry */
 	{ TEGRA124_CLK_CLK_MAX, TEGRA124_CLK_CLK_MAX, 0, 0 },
 };
-- 
cgit v1.2.3


From 8097d4c75f00f3fce8f4916521ec61ec0c607324 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Mon, 11 Jun 2018 10:20:37 +0200
Subject: clk: tegra: Make vde a child of pll_c3

The current default is to leave the VDE clock's parent at the default,
which is clk_m. However, that is not a configuration that will allow the
VDE to function. Reparent it to pll_c3 instead to make sure the hardware
can actually decode video content.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk-tegra124.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/tegra/clk-tegra124.c b/drivers/clk/tegra/clk-tegra124.c
index f5048f82c0b9..b6cf28ca2ed2 100644
--- a/drivers/clk/tegra/clk-tegra124.c
+++ b/drivers/clk/tegra/clk-tegra124.c
@@ -1267,7 +1267,7 @@ static struct tegra_clk_init_table common_init_table[] __initdata = {
 	{ TEGRA124_CLK_I2S2, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
 	{ TEGRA124_CLK_I2S3, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
 	{ TEGRA124_CLK_I2S4, TEGRA124_CLK_PLL_A_OUT0, 11289600, 0 },
-	{ TEGRA124_CLK_VDE, TEGRA124_CLK_CLK_MAX, 600000000, 0 },
+	{ TEGRA124_CLK_VDE, TEGRA124_CLK_PLL_C3, 600000000, 0 },
 	{ TEGRA124_CLK_HOST1X, TEGRA124_CLK_PLL_P, 136000000, 1 },
 	{ TEGRA124_CLK_DSIALP, TEGRA124_CLK_PLL_P, 68000000, 0 },
 	{ TEGRA124_CLK_DSIBLP, TEGRA124_CLK_PLL_P, 68000000, 0 },
-- 
cgit v1.2.3


From da0d2239a56ec8fe6a617aade5901ab3bffc1ef4 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Mon, 4 Jun 2018 01:48:05 +0300
Subject: clk: tegra: Mark Memory Controller clock as critical

Memory Controller should be always-on. Currently the sibling EMC clock is
marked as critical, let's mark MC clock too for consistency.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Acked-By: Peter De Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk-divider.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 16e0aee14773..58874c1bbf5e 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -194,6 +194,7 @@ static const struct clk_div_table mc_div_table[] = {
 struct clk *tegra_clk_register_mc(const char *name, const char *parent_name,
 				  void __iomem *reg, spinlock_t *lock)
 {
-	return clk_register_divider_table(NULL, name, parent_name, 0, reg,
-					  16, 1, 0, mc_div_table, lock);
+	return clk_register_divider_table(NULL, name, parent_name,
+					  CLK_IS_CRITICAL, reg, 16, 1, 0,
+					  mc_div_table, lock);
 }
-- 
cgit v1.2.3


From 405fcacbd866cfe75733b94bacdef5bcb4aa6c6c Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Tue, 5 Jun 2018 15:12:32 +0300
Subject: clk: tegra: emc: Avoid out-of-bounds bug

Apparently there was an attempt to avoid out-of-bounds accesses when there
is only one memory timing available, but there is a typo in the code that
neglects that attempt.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk-emc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/tegra/clk-emc.c b/drivers/clk/tegra/clk-emc.c
index 5234acd30e89..0621a3a82ea6 100644
--- a/drivers/clk/tegra/clk-emc.c
+++ b/drivers/clk/tegra/clk-emc.c
@@ -132,7 +132,7 @@ static int emc_determine_rate(struct clk_hw *hw, struct clk_rate_request *req)
 		timing = tegra->timings + i;
 
 		if (timing->rate > req->max_rate) {
-			i = min(i, 1);
+			i = max(i, 1);
 			req->rate = tegra->timings[i - 1].rate;
 			return 0;
 		}
-- 
cgit v1.2.3


From b294657d1bab3371bf02c31a243232bfa9f4629f Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:33 +0800
Subject: drm/i915/gvt: Add new 64K entry type

Add a new entry type GTT_TYPE_PPGTT_PTE_64K_ENTRY. 64K entry is very
different from 2M/1G entry. 64K entry is controlled by IPS bit in upper
PDE. To leverage the current logic, I take IPS bit as 'PSE' for PTE
level. Which means, 64K entries can also processed by get_pse_type().

v2: Make it bisectable.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 26 ++++++++++++++++++++++----
 drivers/gpu/drm/i915/gvt/gtt.h |  1 +
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 6a8a9868bcfb..03f2a5b26546 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -216,16 +216,22 @@ static struct gtt_type_table_entry gtt_type_table[] = {
 			GTT_TYPE_PPGTT_PDE_PT,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_PPGTT_PTE_2M_ENTRY),
+	/* We take IPS bit as 'PSE' for PTE level. */
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_INVALID,
-			GTT_TYPE_INVALID),
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
 			GTT_TYPE_PPGTT_PTE_PT,
 			GTT_TYPE_INVALID,
-			GTT_TYPE_INVALID),
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
+	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+			GTT_TYPE_PPGTT_PTE_4K_ENTRY,
+			GTT_TYPE_PPGTT_PTE_PT,
+			GTT_TYPE_INVALID,
+			GTT_TYPE_PPGTT_PTE_64K_ENTRY),
 	GTT_TYPE_TABLE_ENTRY(GTT_TYPE_PPGTT_PTE_2M_ENTRY,
 			GTT_TYPE_PPGTT_PDE_ENTRY,
 			GTT_TYPE_PPGTT_PDE_PT,
@@ -339,6 +345,7 @@ static inline int gtt_set_entry64(void *pt,
 
 #define ADDR_1G_MASK	GENMASK_ULL(GTT_HAW - 1, 30)
 #define ADDR_2M_MASK	GENMASK_ULL(GTT_HAW - 1, 21)
+#define ADDR_64K_MASK	GENMASK_ULL(GTT_HAW - 1, 16)
 #define ADDR_4K_MASK	GENMASK_ULL(GTT_HAW - 1, 12)
 
 static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
@@ -349,6 +356,8 @@ static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
 		pfn = (e->val64 & ADDR_1G_MASK) >> PAGE_SHIFT;
 	else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY)
 		pfn = (e->val64 & ADDR_2M_MASK) >> PAGE_SHIFT;
+	else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY)
+		pfn = (e->val64 & ADDR_64K_MASK) >> PAGE_SHIFT;
 	else
 		pfn = (e->val64 & ADDR_4K_MASK) >> PAGE_SHIFT;
 	return pfn;
@@ -362,6 +371,9 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn)
 	} else if (e->type == GTT_TYPE_PPGTT_PTE_2M_ENTRY) {
 		e->val64 &= ~ADDR_2M_MASK;
 		pfn &= (ADDR_2M_MASK >> PAGE_SHIFT);
+	} else if (e->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY) {
+		e->val64 &= ~ADDR_64K_MASK;
+		pfn &= (ADDR_64K_MASK >> PAGE_SHIFT);
 	} else {
 		e->val64 &= ~ADDR_4K_MASK;
 		pfn &= (ADDR_4K_MASK >> PAGE_SHIFT);
@@ -380,6 +392,10 @@ static bool gen8_gtt_test_pse(struct intel_gvt_gtt_entry *e)
 	if (!(e->val64 & _PAGE_PSE))
 		return false;
 
+	/* We don't support 64K entry yet, will remove this later. */
+	if (get_pse_type(e->type) == GTT_TYPE_PPGTT_PTE_64K_ENTRY)
+		return false;
+
 	e->type = get_pse_type(e->type);
 	return true;
 }
@@ -871,9 +887,10 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 			gvt_vdbg_mm("invalidate 4K entry\n");
 			ppgtt_invalidate_pte(spt, &e);
 			break;
+		case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
 		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
 		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-			WARN(1, "GVT doesn't support 2M/1GB page\n");
+			WARN(1, "GVT doesn't support 64K/2M/1GB page\n");
 			continue;
 		case GTT_TYPE_PPGTT_PML4_ENTRY:
 		case GTT_TYPE_PPGTT_PDP_ENTRY:
@@ -970,9 +987,10 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	case GTT_TYPE_PPGTT_PTE_4K_ENTRY:
 		gvt_vdbg_mm("shadow 4K gtt entry\n");
 		break;
+	case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
 	case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
 	case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-		gvt_vgpu_err("GVT doesn't support 2M/1GB entry\n");
+		gvt_vgpu_err("GVT doesn't support 64K/2M/1GB entry\n");
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 3792f2b7f4ff..60630816df5c 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -95,6 +95,7 @@ typedef enum {
 	GTT_TYPE_GGTT_PTE,
 
 	GTT_TYPE_PPGTT_PTE_4K_ENTRY,
+	GTT_TYPE_PPGTT_PTE_64K_ENTRY,
 	GTT_TYPE_PPGTT_PTE_2M_ENTRY,
 	GTT_TYPE_PPGTT_PTE_1G_ENTRY,
 
-- 
cgit v1.2.3


From 6fd7937832698e73a5719ff488c2fc5e22c9c0ba Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:34 +0800
Subject: drm/i915/gvt: Add PTE IPS bit operations

Add three IPS operation functions to test/set/clear IPS in PDE.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 18 ++++++++++++++++++
 drivers/gpu/drm/i915/gvt/gtt.h |  2 ++
 2 files changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 03f2a5b26546..3e6733914530 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -400,6 +400,22 @@ static bool gen8_gtt_test_pse(struct intel_gvt_gtt_entry *e)
 	return true;
 }
 
+static bool gen8_gtt_test_ips(struct intel_gvt_gtt_entry *e)
+{
+	if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY))
+		return false;
+
+	return !!(e->val64 & GEN8_PDE_IPS_64K);
+}
+
+static void gen8_gtt_clear_ips(struct intel_gvt_gtt_entry *e)
+{
+	if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY))
+		return;
+
+	e->val64 &= ~GEN8_PDE_IPS_64K;
+}
+
 static bool gen8_gtt_test_present(struct intel_gvt_gtt_entry *e)
 {
 	/*
@@ -456,6 +472,8 @@ static struct intel_gvt_gtt_pte_ops gen8_gtt_pte_ops = {
 	.set_present = gtt_entry_set_present,
 	.test_present = gen8_gtt_test_present,
 	.test_pse = gen8_gtt_test_pse,
+	.clear_ips = gen8_gtt_clear_ips,
+	.test_ips = gen8_gtt_test_ips,
 	.get_pfn = gen8_gtt_get_pfn,
 	.set_pfn = gen8_gtt_set_pfn,
 };
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 60630816df5c..9257b7467b14 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -63,6 +63,8 @@ struct intel_gvt_gtt_pte_ops {
 	void (*clear_present)(struct intel_gvt_gtt_entry *e);
 	void (*set_present)(struct intel_gvt_gtt_entry *e);
 	bool (*test_pse)(struct intel_gvt_gtt_entry *e);
+	bool (*test_ips)(struct intel_gvt_gtt_entry *e);
+	void (*clear_ips)(struct intel_gvt_gtt_entry *e);
 	void (*set_pfn)(struct intel_gvt_gtt_entry *e, unsigned long pfn);
 	unsigned long (*get_pfn)(struct intel_gvt_gtt_entry *e);
 };
-- 
cgit v1.2.3


From 52ca14e6844a04e174b5cd3d7dbf63a23271775c Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:35 +0800
Subject: drm/i915/gvt: Handle MMIO GEN8_GAMW_ECO_DEV_RW_IA for 64K GTT

The register RENDER_HWS_PGA_GEN7 is renamed to GEN8_GAMW_ECO_DEV_RW_IA
from GEN8 which can control IPS enabling.

v3: MMIO control for IPS is not removed from gen9 but gen10 (Matthew Auld)
v2: IPS of all engines must be enabled together for gen9.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 29 ++++++++++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 0bc0c5418adb..17f56fc20613 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -210,6 +210,31 @@ static int sanitize_fence_mmio_access(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+static int gamw_echo_dev_rw_ia_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	u32 ips = (*(u32 *)p_data) & GAMW_ECO_ENABLE_64K_IPS_FIELD;
+
+	if (INTEL_GEN(vgpu->gvt->dev_priv) <= 10) {
+		if (ips == GAMW_ECO_ENABLE_64K_IPS_FIELD)
+			gvt_dbg_core("vgpu%d: ips enabled\n", vgpu->id);
+		else if (!ips)
+			gvt_dbg_core("vgpu%d: ips disabled\n", vgpu->id);
+		else {
+			/* All engines must be enabled together for vGPU,
+			 * since we don't know which engine the ppgtt will
+			 * bind to when shadowing.
+			 */
+			gvt_vgpu_err("Unsupported IPS setting %x, cannot enable 64K gtt.\n",
+				     ips);
+			return -EINVAL;
+		}
+	}
+
+	write_vreg(vgpu, offset, p_data, bytes);
+	return 0;
+}
+
 static int fence_mmio_read(struct intel_vgpu *vgpu, unsigned int off,
 		void *p_data, unsigned int bytes)
 {
@@ -1769,7 +1794,9 @@ static int init_generic_mmio_info(struct intel_gvt *gvt)
 
 	MMIO_RING_DFH(RING_HWSTAM, D_ALL, F_CMD_ACCESS, NULL, NULL);
 
-	MMIO_GM_RDR(RENDER_HWS_PGA_GEN7, D_ALL, NULL, NULL);
+	MMIO_DH(GEN8_GAMW_ECO_DEV_RW_IA, D_BDW_PLUS, NULL,
+		gamw_echo_dev_rw_ia_write);
+
 	MMIO_GM_RDR(BSD_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 	MMIO_GM_RDR(BLT_HWS_PGA_GEN7, D_ALL, NULL, NULL);
 	MMIO_GM_RDR(VEBOX_HWS_PGA_GEN7, D_ALL, NULL, NULL);
-- 
cgit v1.2.3


From 40b271767dcf9748327619ed550be810cc2e10ae Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:36 +0800
Subject: drm/i915/gvt: Detect 64K gtt entry by IPS bit of PDE

This change help us detect the real entry type per PSE and IPS setting.
For 64K entry, we also need to check reg GEN8_GAMW_ECO_DEV_RW_IA.

v2: Extend IPS mmio control to Gen10. (Matthew Auld)

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 70 +++++++++++++++++++++++++++++-------------
 drivers/gpu/drm/i915/gvt/gtt.h |  2 ++
 2 files changed, 51 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 3e6733914530..3dae75b5b574 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -384,20 +384,7 @@ static void gen8_gtt_set_pfn(struct intel_gvt_gtt_entry *e, unsigned long pfn)
 
 static bool gen8_gtt_test_pse(struct intel_gvt_gtt_entry *e)
 {
-	/* Entry doesn't have PSE bit. */
-	if (get_pse_type(e->type) == GTT_TYPE_INVALID)
-		return false;
-
-	e->type = get_entry_type(e->type);
-	if (!(e->val64 & _PAGE_PSE))
-		return false;
-
-	/* We don't support 64K entry yet, will remove this later. */
-	if (get_pse_type(e->type) == GTT_TYPE_PPGTT_PTE_64K_ENTRY)
-		return false;
-
-	e->type = get_pse_type(e->type);
-	return true;
+	return !!(e->val64 & _PAGE_PSE);
 }
 
 static bool gen8_gtt_test_ips(struct intel_gvt_gtt_entry *e)
@@ -487,6 +474,27 @@ static struct intel_gvt_gtt_gma_ops gen8_gtt_gma_ops = {
 	.gma_to_pml4_index = gen8_gma_to_pml4_index,
 };
 
+/* Update entry type per pse and ips bit. */
+static void update_entry_type_for_real(struct intel_gvt_gtt_pte_ops *pte_ops,
+	struct intel_gvt_gtt_entry *entry, bool ips)
+{
+	switch (entry->type) {
+	case GTT_TYPE_PPGTT_PDE_ENTRY:
+	case GTT_TYPE_PPGTT_PDP_ENTRY:
+		if (pte_ops->test_pse(entry))
+			entry->type = get_pse_type(entry->type);
+		break;
+	case GTT_TYPE_PPGTT_PTE_4K_ENTRY:
+		if (ips)
+			entry->type = get_pse_type(entry->type);
+		break;
+	default:
+		GEM_BUG_ON(!gtt_type_is_entry(entry->type));
+	}
+
+	GEM_BUG_ON(entry->type == GTT_TYPE_INVALID);
+}
+
 /*
  * MM helpers.
  */
@@ -502,8 +510,7 @@ static void _ppgtt_get_root_entry(struct intel_vgpu_mm *mm,
 	pte_ops->get_entry(guest ? mm->ppgtt_mm.guest_pdps :
 			   mm->ppgtt_mm.shadow_pdps,
 			   entry, index, false, 0, mm->vgpu);
-
-	pte_ops->test_pse(entry);
+	update_entry_type_for_real(pte_ops, entry, false);
 }
 
 static inline void ppgtt_get_guest_root_entry(struct intel_vgpu_mm *mm,
@@ -608,7 +615,8 @@ static inline int ppgtt_spt_get_entry(
 	if (ret)
 		return ret;
 
-	ops->test_pse(e);
+	update_entry_type_for_real(ops, e, guest ?
+				   spt->guest_page.pde_ips : false);
 
 	gvt_vdbg_mm("read ppgtt entry, spt type %d, entry type %d, index %lu, value %llx\n",
 		    type, e->type, index, e->val64);
@@ -752,7 +760,8 @@ static inline struct intel_vgpu_ppgtt_spt *intel_vgpu_find_spt_by_mfn(
 static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt);
 
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt(
-		struct intel_vgpu *vgpu, int type, unsigned long gfn)
+		struct intel_vgpu *vgpu, int type, unsigned long gfn,
+		bool guest_pde_ips)
 {
 	struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
@@ -792,6 +801,7 @@ retry:
 	 */
 	spt->guest_page.type = type;
 	spt->guest_page.gfn = gfn;
+	spt->guest_page.pde_ips = guest_pde_ips;
 
 	ret = intel_vgpu_register_page_track(vgpu, spt->guest_page.gfn,
 					ppgtt_write_protection_handler, spt);
@@ -934,6 +944,22 @@ fail:
 	return ret;
 }
 
+static bool vgpu_ips_enabled(struct intel_vgpu *vgpu)
+{
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
+
+	if (INTEL_GEN(dev_priv) == 9 || INTEL_GEN(dev_priv) == 10) {
+		u32 ips = vgpu_vreg_t(vgpu, GEN8_GAMW_ECO_DEV_RW_IA) &
+			GAMW_ECO_ENABLE_64K_IPS_FIELD;
+
+		return ips == GAMW_ECO_ENABLE_64K_IPS_FIELD;
+	} else if (INTEL_GEN(dev_priv) >= 11) {
+		/* 64K paging only controlled by IPS bit in PTE now. */
+		return true;
+	} else
+		return false;
+}
+
 static int ppgtt_populate_spt(struct intel_vgpu_ppgtt_spt *spt);
 
 static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
@@ -941,6 +967,7 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 {
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
+	bool ips = false;
 	int ret;
 
 	GEM_BUG_ON(!gtt_type_is_pt(get_next_pt_type(we->type)));
@@ -951,7 +978,10 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 	else {
 		int type = get_next_pt_type(we->type);
 
-		spt = ppgtt_alloc_spt(vgpu, type, ops->get_pfn(we));
+		if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+			ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
+
+		spt = ppgtt_alloc_spt(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
 			ret = PTR_ERR(spt);
 			goto fail;
@@ -1427,8 +1457,6 @@ static int ppgtt_handle_guest_write_page_table_bytes(
 
 	ppgtt_get_guest_entry(spt, &we, index);
 
-	ops->test_pse(&we);
-
 	if (bytes == info->gtt_entry_size) {
 		ret = ppgtt_handle_guest_write_page_table(spt, &we, index);
 		if (ret)
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 9257b7467b14..c11284bb291b 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -223,6 +223,7 @@ struct intel_vgpu_ppgtt_spt {
 
 	struct {
 		intel_gvt_gtt_type_t type;
+		bool pde_ips; /* for 64KB PTEs */
 		void *vaddr;
 		struct page *page;
 		unsigned long mfn;
@@ -230,6 +231,7 @@ struct intel_vgpu_ppgtt_spt {
 
 	struct {
 		intel_gvt_gtt_type_t type;
+		bool pde_ips; /* for 64KB PTEs */
 		unsigned long gfn;
 		unsigned long write_cnt;
 		struct intel_vgpu_oos_page *oos_page;
-- 
cgit v1.2.3


From 716348485695de1a91b2f8b398f9c08687f794af Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:37 +0800
Subject: drm/i915/gvt: Add software PTE flag to mark special 64K splited entry

This add a software PTE flag on the Ignored bit of PTE. It will be used
to identify splited 64K shadow entries.

v2: fix mask definition.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 21 +++++++++++++++++++++
 drivers/gpu/drm/i915/gvt/gtt.h |  3 +++
 2 files changed, 24 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 3dae75b5b574..34c401fb37d1 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -348,6 +348,9 @@ static inline int gtt_set_entry64(void *pt,
 #define ADDR_64K_MASK	GENMASK_ULL(GTT_HAW - 1, 16)
 #define ADDR_4K_MASK	GENMASK_ULL(GTT_HAW - 1, 12)
 
+#define GTT_SPTE_FLAG_MASK GENMASK_ULL(62, 52)
+#define GTT_SPTE_FLAG_64K_SPLITED BIT(52) /* splited 64K gtt entry */
+
 static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
 {
 	unsigned long pfn;
@@ -427,6 +430,21 @@ static void gtt_entry_set_present(struct intel_gvt_gtt_entry *e)
 	e->val64 |= _PAGE_PRESENT;
 }
 
+static bool gen8_gtt_test_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	return !!(e->val64 & GTT_SPTE_FLAG_64K_SPLITED);
+}
+
+static void gen8_gtt_set_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	e->val64 |= GTT_SPTE_FLAG_64K_SPLITED;
+}
+
+static void gen8_gtt_clear_64k_splited(struct intel_gvt_gtt_entry *e)
+{
+	e->val64 &= ~GTT_SPTE_FLAG_64K_SPLITED;
+}
+
 /*
  * Per-platform GMA routines.
  */
@@ -461,6 +479,9 @@ static struct intel_gvt_gtt_pte_ops gen8_gtt_pte_ops = {
 	.test_pse = gen8_gtt_test_pse,
 	.clear_ips = gen8_gtt_clear_ips,
 	.test_ips = gen8_gtt_test_ips,
+	.clear_64k_splited = gen8_gtt_clear_64k_splited,
+	.set_64k_splited = gen8_gtt_set_64k_splited,
+	.test_64k_splited = gen8_gtt_test_64k_splited,
 	.get_pfn = gen8_gtt_get_pfn,
 	.set_pfn = gen8_gtt_set_pfn,
 };
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index c11284bb291b..162ef19f4117 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -65,6 +65,9 @@ struct intel_gvt_gtt_pte_ops {
 	bool (*test_pse)(struct intel_gvt_gtt_entry *e);
 	bool (*test_ips)(struct intel_gvt_gtt_entry *e);
 	void (*clear_ips)(struct intel_gvt_gtt_entry *e);
+	bool (*test_64k_splited)(struct intel_gvt_gtt_entry *e);
+	void (*clear_64k_splited)(struct intel_gvt_gtt_entry *e);
+	void (*set_64k_splited)(struct intel_gvt_gtt_entry *e);
 	void (*set_pfn)(struct intel_gvt_gtt_entry *e, unsigned long pfn);
 	unsigned long (*get_pfn)(struct intel_gvt_gtt_entry *e);
 };
-- 
cgit v1.2.3


From c3e697635fcc9173e1d7116d9ebfd2fd0887177d Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:38 +0800
Subject: drm/i915/gvt: Add GTT clear_pse operation

Add clear_pse operation in case we need to split huge gtt into small pages.

v2: correct description.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 19 +++++++++++++++++++
 drivers/gpu/drm/i915/gvt/gtt.h |  1 +
 2 files changed, 20 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 34c401fb37d1..d34dc9ab66e1 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -390,6 +390,24 @@ static bool gen8_gtt_test_pse(struct intel_gvt_gtt_entry *e)
 	return !!(e->val64 & _PAGE_PSE);
 }
 
+static void gen8_gtt_clear_pse(struct intel_gvt_gtt_entry *e)
+{
+	if (gen8_gtt_test_pse(e)) {
+		switch (e->type) {
+		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+			e->val64 &= ~_PAGE_PSE;
+			e->type = GTT_TYPE_PPGTT_PDE_ENTRY;
+			break;
+		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
+			e->type = GTT_TYPE_PPGTT_PDP_ENTRY;
+			e->val64 &= ~_PAGE_PSE;
+			break;
+		default:
+			WARN_ON(1);
+		}
+	}
+}
+
 static bool gen8_gtt_test_ips(struct intel_gvt_gtt_entry *e)
 {
 	if (GEM_WARN_ON(e->type != GTT_TYPE_PPGTT_PDE_ENTRY))
@@ -477,6 +495,7 @@ static struct intel_gvt_gtt_pte_ops gen8_gtt_pte_ops = {
 	.set_present = gtt_entry_set_present,
 	.test_present = gen8_gtt_test_present,
 	.test_pse = gen8_gtt_test_pse,
+	.clear_pse = gen8_gtt_clear_pse,
 	.clear_ips = gen8_gtt_clear_ips,
 	.test_ips = gen8_gtt_test_ips,
 	.clear_64k_splited = gen8_gtt_clear_64k_splited,
diff --git a/drivers/gpu/drm/i915/gvt/gtt.h b/drivers/gpu/drm/i915/gvt/gtt.h
index 162ef19f4117..b7bf68cc8418 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.h
+++ b/drivers/gpu/drm/i915/gvt/gtt.h
@@ -63,6 +63,7 @@ struct intel_gvt_gtt_pte_ops {
 	void (*clear_present)(struct intel_gvt_gtt_entry *e);
 	void (*set_present)(struct intel_gvt_gtt_entry *e);
 	bool (*test_pse)(struct intel_gvt_gtt_entry *e);
+	void (*clear_pse)(struct intel_gvt_gtt_entry *e);
 	bool (*test_ips)(struct intel_gvt_gtt_entry *e);
 	void (*clear_ips)(struct intel_gvt_gtt_entry *e);
 	bool (*test_64k_splited)(struct intel_gvt_gtt_entry *e);
-- 
cgit v1.2.3


From 155521c93e468211673206e1871b53d26a44a82d Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:39 +0800
Subject: drm/i915/gvt: Split ppgtt_alloc_spt into two parts

We need a interface to allocate a pure shadow page which doesn't have
a guest page associated with. Such shadow page is used to shadow 2M
huge gtt entry.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 62 +++++++++++++++++++++++++++---------------
 1 file changed, 40 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index d34dc9ab66e1..15f6908fc648 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -735,10 +735,12 @@ static void ppgtt_free_spt(struct intel_vgpu_ppgtt_spt *spt)
 
 	radix_tree_delete(&spt->vgpu->gtt.spt_tree, spt->shadow_page.mfn);
 
-	if (spt->guest_page.oos_page)
-		detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
+	if (spt->guest_page.gfn) {
+		if (spt->guest_page.oos_page)
+			detach_oos_page(spt->vgpu, spt->guest_page.oos_page);
 
-	intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+		intel_vgpu_unregister_page_track(spt->vgpu, spt->guest_page.gfn);
+	}
 
 	list_del_init(&spt->post_shadow_list);
 	free_spt(spt);
@@ -799,9 +801,9 @@ static inline struct intel_vgpu_ppgtt_spt *intel_vgpu_find_spt_by_mfn(
 
 static int reclaim_one_ppgtt_mm(struct intel_gvt *gvt);
 
+/* Allocate shadow page table without guest page. */
 static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt(
-		struct intel_vgpu *vgpu, int type, unsigned long gfn,
-		bool guest_pde_ips)
+		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type)
 {
 	struct device *kdev = &vgpu->gvt->dev_priv->drm.pdev->dev;
 	struct intel_vgpu_ppgtt_spt *spt = NULL;
@@ -836,27 +838,12 @@ retry:
 	spt->shadow_page.vaddr = page_address(spt->shadow_page.page);
 	spt->shadow_page.mfn = daddr >> I915_GTT_PAGE_SHIFT;
 
-	/*
-	 * Init guest_page.
-	 */
-	spt->guest_page.type = type;
-	spt->guest_page.gfn = gfn;
-	spt->guest_page.pde_ips = guest_pde_ips;
-
-	ret = intel_vgpu_register_page_track(vgpu, spt->guest_page.gfn,
-					ppgtt_write_protection_handler, spt);
-	if (ret)
-		goto err_unmap_dma;
-
 	ret = radix_tree_insert(&vgpu->gtt.spt_tree, spt->shadow_page.mfn, spt);
 	if (ret)
-		goto err_unreg_page_track;
+		goto err_unmap_dma;
 
-	trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
 	return spt;
 
-err_unreg_page_track:
-	intel_vgpu_unregister_page_track(vgpu, spt->guest_page.gfn);
 err_unmap_dma:
 	dma_unmap_page(kdev, daddr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
 err_free_spt:
@@ -864,6 +851,37 @@ err_free_spt:
 	return ERR_PTR(ret);
 }
 
+/* Allocate shadow page table associated with specific gfn. */
+static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
+		struct intel_vgpu *vgpu, intel_gvt_gtt_type_t type,
+		unsigned long gfn, bool guest_pde_ips)
+{
+	struct intel_vgpu_ppgtt_spt *spt;
+	int ret;
+
+	spt = ppgtt_alloc_spt(vgpu, type);
+	if (IS_ERR(spt))
+		return spt;
+
+	/*
+	 * Init guest_page.
+	 */
+	ret = intel_vgpu_register_page_track(vgpu, gfn,
+			ppgtt_write_protection_handler, spt);
+	if (ret) {
+		ppgtt_free_spt(spt);
+		return ERR_PTR(ret);
+	}
+
+	spt->guest_page.type = type;
+	spt->guest_page.gfn = gfn;
+	spt->guest_page.pde_ips = guest_pde_ips;
+
+	trace_spt_alloc(vgpu->id, spt, type, spt->shadow_page.mfn, gfn);
+
+	return spt;
+}
+
 #define pt_entry_size_shift(spt) \
 	((spt)->vgpu->gvt->device_info.gtt_entry_size_shift)
 
@@ -1021,7 +1039,7 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 		if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
 			ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
 
-		spt = ppgtt_alloc_spt(vgpu, type, ops->get_pfn(we), ips);
+		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
 			ret = PTR_ERR(spt);
 			goto fail;
-- 
cgit v1.2.3


From 4c9414d7b152bf344521bf786b5748e833270776 Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:40 +0800
Subject: drm/i915/gvt: Make PTE iterator 64K entry aware

64K PTE is special, only PTE#0, PTE#16, PTE#32, ... PTE#496 are used in
the page table.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 15f6908fc648..7fc277cceb23 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -351,6 +351,8 @@ static inline int gtt_set_entry64(void *pt,
 #define GTT_SPTE_FLAG_MASK GENMASK_ULL(62, 52)
 #define GTT_SPTE_FLAG_64K_SPLITED BIT(52) /* splited 64K gtt entry */
 
+#define GTT_64K_PTE_STRIDE 16
+
 static unsigned long gen8_gtt_get_pfn(struct intel_gvt_gtt_entry *e)
 {
 	unsigned long pfn;
@@ -889,12 +891,14 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
 	(I915_GTT_PAGE_SIZE >> pt_entry_size_shift(spt))
 
 #define for_each_present_guest_entry(spt, e, i) \
-	for (i = 0; i < pt_entries(spt); i++) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += spt->guest_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
 		if (!ppgtt_get_guest_entry(spt, e, i) && \
 		    spt->vgpu->gvt->gtt.pte_ops->test_present(e))
 
 #define for_each_present_shadow_entry(spt, e, i) \
-	for (i = 0; i < pt_entries(spt); i++) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1) \
 		if (!ppgtt_get_shadow_entry(spt, e, i) && \
 		    spt->vgpu->gvt->gtt.pte_ops->test_present(e))
 
-- 
cgit v1.2.3


From eb3a353014d2c2402e572ab7bef86bf5e328160f Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:41 +0800
Subject: drm/i915/gvt: Add 64K huge gtt support

Finally, this add the first huge gtt support for GVTg - 64K pages. Since
64K page and 4K page cannot be mixed on the same page table, so we always
split a 64K entry into small 4K page. And when unshadow guest 64K entry,
we need ensure all the shadowed entries in shadow page table also get
cleared.

For page table which has 64K gtt entry, only PTE#0, PTE#16, PTE#32, ...
PTE#496 are used. Unused PTEs update should be ignored.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 86 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 80 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 7fc277cceb23..54c221dedfe8 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -978,9 +978,12 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 			ppgtt_invalidate_pte(spt, &e);
 			break;
 		case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+			/* We don't setup 64K shadow entry so far. */
+			WARN(1, "suspicious 64K gtt entry\n");
+			continue;
 		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
 		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-			WARN(1, "GVT doesn't support 64K/2M/1GB page\n");
+			WARN(1, "GVT doesn't support 2M/1GB page\n");
 			continue;
 		case GTT_TYPE_PPGTT_PML4_ENTRY:
 		case GTT_TYPE_PPGTT_PDP_ENTRY:
@@ -1075,9 +1078,44 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se,
 	se->type = ge->type;
 	se->val64 = ge->val64;
 
+	/* Because we always split 64KB pages, so clear IPS in shadow PDE. */
+	if (se->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+		ops->clear_ips(se);
+
 	ops->set_pfn(se, s->shadow_page.mfn);
 }
 
+static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
+	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+	struct intel_gvt_gtt_entry *se)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_gvt_gtt_entry entry = *se;
+	unsigned long start_gfn;
+	dma_addr_t dma_addr;
+	int i, ret;
+
+	gvt_vdbg_mm("Split 64K gtt entry, index %lu\n", index);
+
+	GEM_BUG_ON(index % GTT_64K_PTE_STRIDE);
+
+	start_gfn = ops->get_pfn(se);
+
+	entry.type = GTT_TYPE_PPGTT_PTE_4K_ENTRY;
+	ops->set_64k_splited(&entry);
+
+	for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+						start_gfn + i, &dma_addr);
+		if (ret)
+			return ret;
+
+		ops->set_pfn(&entry, dma_addr >> PAGE_SHIFT);
+		ppgtt_set_shadow_entry(spt, &entry, index + i);
+	}
+	return 0;
+}
+
 static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
 	struct intel_gvt_gtt_entry *ge)
@@ -1098,9 +1136,16 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 		gvt_vdbg_mm("shadow 4K gtt entry\n");
 		break;
 	case GTT_TYPE_PPGTT_PTE_64K_ENTRY:
+		gvt_vdbg_mm("shadow 64K gtt entry\n");
+		/*
+		 * The layout of 64K page is special, the page size is
+		 * controlled by uper PDE. To be simple, we always split
+		 * 64K page to smaller 4K pages in shadow PT.
+		 */
+		return split_64KB_gtt_entry(vgpu, spt, index, &se);
 	case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
 	case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-		gvt_vgpu_err("GVT doesn't support 64K/2M/1GB entry\n");
+		gvt_vgpu_err("GVT doesn't support 2M/1GB entry\n");
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
@@ -1190,8 +1235,12 @@ static int ppgtt_handle_guest_entry_removal(struct intel_vgpu_ppgtt_spt *spt,
 		ret = ppgtt_invalidate_spt(s);
 		if (ret)
 			goto fail;
-	} else
+	} else {
+		/* We don't setup 64K shadow entry so far. */
+		WARN(se->type == GTT_TYPE_PPGTT_PTE_64K_ENTRY,
+		     "suspicious 64K entry\n");
 		ppgtt_invalidate_pte(spt, se);
+	}
 
 	return 0;
 fail:
@@ -1414,7 +1463,7 @@ static int ppgtt_handle_guest_write_page_table(
 	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry old_se;
 	int new_present;
-	int ret;
+	int i, ret;
 
 	new_present = ops->test_present(we);
 
@@ -1436,8 +1485,21 @@ static int ppgtt_handle_guest_write_page_table(
 		goto fail;
 
 	if (!new_present) {
-		ops->set_pfn(&old_se, vgpu->gtt.scratch_pt[type].page_mfn);
-		ppgtt_set_shadow_entry(spt, &old_se, index);
+		/* For 64KB splited entries, we need clear them all. */
+		if (ops->test_64k_splited(&old_se) &&
+		    !(index % GTT_64K_PTE_STRIDE)) {
+			gvt_vdbg_mm("remove splited 64K shadow entries\n");
+			for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
+				ops->clear_64k_splited(&old_se);
+				ops->set_pfn(&old_se,
+					vgpu->gtt.scratch_pt[type].page_mfn);
+				ppgtt_set_shadow_entry(spt, &old_se, index + i);
+			}
+		} else {
+			ops->set_pfn(&old_se,
+				     vgpu->gtt.scratch_pt[type].page_mfn);
+			ppgtt_set_shadow_entry(spt, &old_se, index);
+		}
 	}
 
 	return 0;
@@ -1519,6 +1581,18 @@ static int ppgtt_handle_guest_write_page_table_bytes(
 
 	ppgtt_get_guest_entry(spt, &we, index);
 
+	/*
+	 * For page table which has 64K gtt entry, only PTE#0, PTE#16,
+	 * PTE#32, ... PTE#496 are used. Unused PTEs update should be
+	 * ignored.
+	 */
+	if (we.type == GTT_TYPE_PPGTT_PTE_64K_ENTRY &&
+	    (index % GTT_64K_PTE_STRIDE)) {
+		gvt_vdbg_mm("Ignore write to unused PTE entry, index %lu\n",
+			    index);
+		return 0;
+	}
+
 	if (bytes == info->gtt_entry_size) {
 		ret = ppgtt_handle_guest_write_page_table(spt, &we, index);
 		if (ret)
-- 
cgit v1.2.3


From 79e542f5af79918e5e766c441561fb9bff8af3aa Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:42 +0800
Subject: drm/i915/kvmgt: Support setting dma map for huge pages

To support huge gtt, we need to support huge pages in kvmgt first.
This patch adds a 'size' param to the intel_gvt_mpt::dma_map_guest_page
API and implements it in kvmgt.

v2: rebase.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c       |   6 +-
 drivers/gpu/drm/i915/gvt/hypercall.h |   2 +-
 drivers/gpu/drm/i915/gvt/kvmgt.c     | 126 ++++++++++++++++++++++++++---------
 drivers/gpu/drm/i915/gvt/mpt.h       |   7 +-
 4 files changed, 102 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 54c221dedfe8..e26c01da2bd6 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1106,7 +1106,7 @@ static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
 
 	for (i = 0; i < GTT_64K_PTE_STRIDE; i++) {
 		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
-						start_gfn + i, &dma_addr);
+					start_gfn + i, PAGE_SIZE, &dma_addr);
 		if (ret)
 			return ret;
 
@@ -1152,7 +1152,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 	};
 
 	/* direct shadow */
-	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, &dma_addr);
+	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, PAGE_SIZE, &dma_addr);
 	if (ret)
 		return -ENXIO;
 
@@ -2080,7 +2080,7 @@ static int emulate_ggtt_mmio_write(struct intel_vgpu *vgpu, unsigned int off,
 		}
 
 		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn,
-							      &dma_addr);
+							PAGE_SIZE, &dma_addr);
 		if (ret) {
 			gvt_vgpu_err("fail to populate guest ggtt entry\n");
 			/* guest driver may read/write the entry when partial
diff --git a/drivers/gpu/drm/i915/gvt/hypercall.h b/drivers/gpu/drm/i915/gvt/hypercall.h
index f6dd9f717888..5af11cf1b482 100644
--- a/drivers/gpu/drm/i915/gvt/hypercall.h
+++ b/drivers/gpu/drm/i915/gvt/hypercall.h
@@ -53,7 +53,7 @@ struct intel_gvt_mpt {
 	unsigned long (*gfn_to_mfn)(unsigned long handle, unsigned long gfn);
 
 	int (*dma_map_guest_page)(unsigned long handle, unsigned long gfn,
-				  dma_addr_t *dma_addr);
+				  unsigned long size, dma_addr_t *dma_addr);
 	void (*dma_unmap_guest_page)(unsigned long handle, dma_addr_t dma_addr);
 
 	int (*map_gfn_to_mfn)(unsigned long handle, unsigned long gfn,
diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 1466d8769ec9..685cb3de6dab 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -94,6 +94,7 @@ struct gvt_dma {
 	struct rb_node dma_addr_node;
 	gfn_t gfn;
 	dma_addr_t dma_addr;
+	unsigned long size;
 	struct kref ref;
 };
 
@@ -106,45 +107,103 @@ static int kvmgt_guest_init(struct mdev_device *mdev);
 static void intel_vgpu_release_work(struct work_struct *work);
 static bool kvmgt_guest_exit(struct kvmgt_guest_info *info);
 
+static void gvt_unpin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
+		unsigned long size)
+{
+	int total_pages;
+	int npage;
+	int ret;
+
+	total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE;
+
+	for (npage = 0; npage < total_pages; npage++) {
+		unsigned long cur_gfn = gfn + npage;
+
+		ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 1);
+		WARN_ON(ret != 1);
+	}
+}
+
+/* Pin a normal or compound guest page for dma. */
+static int gvt_pin_guest_page(struct intel_vgpu *vgpu, unsigned long gfn,
+		unsigned long size, struct page **page)
+{
+	unsigned long base_pfn = 0;
+	int total_pages;
+	int npage;
+	int ret;
+
+	total_pages = roundup(size, PAGE_SIZE) / PAGE_SIZE;
+	/*
+	 * We pin the pages one-by-one to avoid allocating a big arrary
+	 * on stack to hold pfns.
+	 */
+	for (npage = 0; npage < total_pages; npage++) {
+		unsigned long cur_gfn = gfn + npage;
+		unsigned long pfn;
+
+		ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &cur_gfn, 1,
+				     IOMMU_READ | IOMMU_WRITE, &pfn);
+		if (ret != 1) {
+			gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx, ret %d\n",
+				     cur_gfn, ret);
+			goto err;
+		}
+
+		if (!pfn_valid(pfn)) {
+			gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);
+			npage++;
+			ret = -EFAULT;
+			goto err;
+		}
+
+		if (npage == 0)
+			base_pfn = pfn;
+		else if (base_pfn + npage != pfn) {
+			gvt_vgpu_err("The pages are not continuous\n");
+			ret = -EINVAL;
+			npage++;
+			goto err;
+		}
+	}
+
+	*page = pfn_to_page(base_pfn);
+	return 0;
+err:
+	gvt_unpin_guest_page(vgpu, gfn, npage * PAGE_SIZE);
+	return ret;
+}
+
 static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn,
-		dma_addr_t *dma_addr)
+		dma_addr_t *dma_addr, unsigned long size)
 {
 	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
-	struct page *page;
-	unsigned long pfn;
+	struct page *page = NULL;
 	int ret;
 
-	/* Pin the page first. */
-	ret = vfio_pin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1,
-			     IOMMU_READ | IOMMU_WRITE, &pfn);
-	if (ret != 1) {
-		gvt_vgpu_err("vfio_pin_pages failed for gfn 0x%lx: %d\n",
-			     gfn, ret);
-		return -EINVAL;
-	}
+	ret = gvt_pin_guest_page(vgpu, gfn, size, &page);
+	if (ret)
+		return ret;
 
 	/* Setup DMA mapping. */
-	page = pfn_to_page(pfn);
-	*dma_addr = dma_map_page(dev, page, 0, PAGE_SIZE,
-				 PCI_DMA_BIDIRECTIONAL);
-	if (dma_mapping_error(dev, *dma_addr)) {
-		gvt_vgpu_err("DMA mapping failed for gfn 0x%lx\n", gfn);
-		vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-		return -ENOMEM;
+	*dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL);
+	ret = dma_mapping_error(dev, *dma_addr);
+	if (ret) {
+		gvt_vgpu_err("DMA mapping failed for pfn 0x%lx, ret %d\n",
+			     page_to_pfn(page), ret);
+		gvt_unpin_guest_page(vgpu, gfn, size);
 	}
 
-	return 0;
+	return ret;
 }
 
 static void gvt_dma_unmap_page(struct intel_vgpu *vgpu, unsigned long gfn,
-		dma_addr_t dma_addr)
+		dma_addr_t dma_addr, unsigned long size)
 {
 	struct device *dev = &vgpu->gvt->dev_priv->drm.pdev->dev;
-	int ret;
 
-	dma_unmap_page(dev, dma_addr, PAGE_SIZE, PCI_DMA_BIDIRECTIONAL);
-	ret = vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-	WARN_ON(ret != 1);
+	dma_unmap_page(dev, dma_addr, size, PCI_DMA_BIDIRECTIONAL);
+	gvt_unpin_guest_page(vgpu, gfn, size);
 }
 
 static struct gvt_dma *__gvt_cache_find_dma_addr(struct intel_vgpu *vgpu,
@@ -185,7 +244,7 @@ static struct gvt_dma *__gvt_cache_find_gfn(struct intel_vgpu *vgpu, gfn_t gfn)
 }
 
 static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn,
-		dma_addr_t dma_addr)
+		dma_addr_t dma_addr, unsigned long size)
 {
 	struct gvt_dma *new, *itr;
 	struct rb_node **link, *parent = NULL;
@@ -197,6 +256,7 @@ static int __gvt_cache_add(struct intel_vgpu *vgpu, gfn_t gfn,
 	new->vgpu = vgpu;
 	new->gfn = gfn;
 	new->dma_addr = dma_addr;
+	new->size = size;
 	kref_init(&new->ref);
 
 	/* gfn_cache maps gfn to struct gvt_dma. */
@@ -254,7 +314,7 @@ static void gvt_cache_destroy(struct intel_vgpu *vgpu)
 			break;
 		}
 		dma = rb_entry(node, struct gvt_dma, gfn_node);
-		gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr);
+		gvt_dma_unmap_page(vgpu, dma->gfn, dma->dma_addr, dma->size);
 		__gvt_cache_remove_entry(vgpu, dma);
 		mutex_unlock(&vgpu->vdev.cache_lock);
 	}
@@ -509,7 +569,8 @@ static int intel_vgpu_iommu_notifier(struct notifier_block *nb,
 			if (!entry)
 				continue;
 
-			gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr);
+			gvt_dma_unmap_page(vgpu, entry->gfn, entry->dma_addr,
+					   entry->size);
 			__gvt_cache_remove_entry(vgpu, entry);
 		}
 		mutex_unlock(&vgpu->vdev.cache_lock);
@@ -1616,7 +1677,7 @@ static unsigned long kvmgt_gfn_to_pfn(unsigned long handle, unsigned long gfn)
 }
 
 int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
-		dma_addr_t *dma_addr)
+		unsigned long size, dma_addr_t *dma_addr)
 {
 	struct kvmgt_guest_info *info;
 	struct intel_vgpu *vgpu;
@@ -1633,11 +1694,11 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
 
 	entry = __gvt_cache_find_gfn(info->vgpu, gfn);
 	if (!entry) {
-		ret = gvt_dma_map_page(vgpu, gfn, dma_addr);
+		ret = gvt_dma_map_page(vgpu, gfn, dma_addr, size);
 		if (ret)
 			goto err_unlock;
 
-		ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr);
+		ret = __gvt_cache_add(info->vgpu, gfn, *dma_addr, size);
 		if (ret)
 			goto err_unmap;
 	} else {
@@ -1649,7 +1710,7 @@ int kvmgt_dma_map_guest_page(unsigned long handle, unsigned long gfn,
 	return 0;
 
 err_unmap:
-	gvt_dma_unmap_page(vgpu, gfn, *dma_addr);
+	gvt_dma_unmap_page(vgpu, gfn, *dma_addr, size);
 err_unlock:
 	mutex_unlock(&info->vgpu->vdev.cache_lock);
 	return ret;
@@ -1659,7 +1720,8 @@ static void __gvt_dma_release(struct kref *ref)
 {
 	struct gvt_dma *entry = container_of(ref, typeof(*entry), ref);
 
-	gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr);
+	gvt_dma_unmap_page(entry->vgpu, entry->gfn, entry->dma_addr,
+			   entry->size);
 	__gvt_cache_remove_entry(entry->vgpu, entry);
 }
 
diff --git a/drivers/gpu/drm/i915/gvt/mpt.h b/drivers/gpu/drm/i915/gvt/mpt.h
index 32ffcd566cdd..67f19992b226 100644
--- a/drivers/gpu/drm/i915/gvt/mpt.h
+++ b/drivers/gpu/drm/i915/gvt/mpt.h
@@ -230,17 +230,18 @@ static inline unsigned long intel_gvt_hypervisor_gfn_to_mfn(
 /**
  * intel_gvt_hypervisor_dma_map_guest_page - setup dma map for guest page
  * @vgpu: a vGPU
- * @gpfn: guest pfn
+ * @gfn: guest pfn
+ * @size: page size
  * @dma_addr: retrieve allocated dma addr
  *
  * Returns:
  * 0 on success, negative error code if failed.
  */
 static inline int intel_gvt_hypervisor_dma_map_guest_page(
-		struct intel_vgpu *vgpu, unsigned long gfn,
+		struct intel_vgpu *vgpu, unsigned long gfn, unsigned long size,
 		dma_addr_t *dma_addr)
 {
-	return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn,
+	return intel_gvt_host.mpt->dma_map_guest_page(vgpu->handle, gfn, size,
 						      dma_addr);
 }
 
-- 
cgit v1.2.3


From b901b252b6cf5cecc612059ccf05d974a9085c58 Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:43 +0800
Subject: drm/i915/gvt: Add 2M huge gtt support

This add 2M huge gtt support for GVTg. Unlike 64K gtt entry, we can
shadow 2M guest entry with real huge gtt. But before that, we have to
check memory physical continuous, alignment and if it is supported on
the host. We can get all supported page sizes from
intel_device_info.page_sizes.

Finally we must split the 2M page into smaller pages if we cannot
satisfy guest Huge Page.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 100 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 95 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index e26c01da2bd6..5a66d0f3365c 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -902,6 +902,11 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
 		if (!ppgtt_get_shadow_entry(spt, e, i) && \
 		    spt->vgpu->gvt->gtt.pte_ops->test_present(e))
 
+#define for_each_shadow_entry(spt, e, i) \
+	for (i = 0; i < pt_entries(spt); \
+	     i += (spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1)) \
+		if (!ppgtt_get_shadow_entry(spt, e, i))
+
 static void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
 {
 	int v = atomic_read(&spt->refcount);
@@ -949,7 +954,8 @@ static inline void ppgtt_invalidate_pte(struct intel_vgpu_ppgtt_spt *spt,
 	pfn = ops->get_pfn(entry);
 	type = spt->shadow_page.type;
 
-	if (pfn == vgpu->gtt.scratch_pt[type].page_mfn)
+	/* Uninitialized spte or unshadowed spte. */
+	if (!pfn || pfn == vgpu->gtt.scratch_pt[type].page_mfn)
 		return;
 
 	intel_gvt_hypervisor_dma_unmap_guest_page(vgpu, pfn << PAGE_SHIFT);
@@ -982,8 +988,10 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 			WARN(1, "suspicious 64K gtt entry\n");
 			continue;
 		case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+			gvt_vdbg_mm("invalidate 2M entry\n");
+			continue;
 		case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-			WARN(1, "GVT doesn't support 2M/1GB page\n");
+			WARN(1, "GVT doesn't support 1GB page\n");
 			continue;
 		case GTT_TYPE_PPGTT_PML4_ENTRY:
 		case GTT_TYPE_PPGTT_PDP_ENTRY:
@@ -1085,6 +1093,73 @@ static inline void ppgtt_generate_shadow_entry(struct intel_gvt_gtt_entry *se,
 	ops->set_pfn(se, s->shadow_page.mfn);
 }
 
+/**
+ * Return 1 if 2MB huge gtt shadowing is possilbe, 0 if miscondition,
+ * negtive if found err.
+ */
+static int is_2MB_gtt_possible(struct intel_vgpu *vgpu,
+	struct intel_gvt_gtt_entry *entry)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	unsigned long pfn;
+
+	if (!HAS_PAGE_SIZES(vgpu->gvt->dev_priv, I915_GTT_PAGE_SIZE_2M))
+		return 0;
+
+	pfn = intel_gvt_hypervisor_gfn_to_mfn(vgpu, ops->get_pfn(entry));
+	if (pfn == INTEL_GVT_INVALID_ADDR)
+		return -EINVAL;
+
+	return PageTransHuge(pfn_to_page(pfn));
+}
+
+static int split_2MB_gtt_entry(struct intel_vgpu *vgpu,
+	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
+	struct intel_gvt_gtt_entry *se)
+{
+	struct intel_gvt_gtt_pte_ops *ops = vgpu->gvt->gtt.pte_ops;
+	struct intel_vgpu_ppgtt_spt *sub_spt;
+	struct intel_gvt_gtt_entry sub_se;
+	unsigned long start_gfn;
+	dma_addr_t dma_addr;
+	unsigned long sub_index;
+	int ret;
+
+	gvt_dbg_mm("Split 2M gtt entry, index %lu\n", index);
+
+	start_gfn = ops->get_pfn(se);
+
+	sub_spt = ppgtt_alloc_spt(vgpu, GTT_TYPE_PPGTT_PTE_PT);
+	if (IS_ERR(sub_spt))
+		return PTR_ERR(sub_spt);
+
+	for_each_shadow_entry(sub_spt, &sub_se, sub_index) {
+		ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu,
+				start_gfn + sub_index, PAGE_SIZE, &dma_addr);
+		if (ret) {
+			ppgtt_invalidate_spt(spt);
+			return ret;
+		}
+		sub_se.val64 = se->val64;
+
+		/* Copy the PAT field from PDE. */
+		sub_se.val64 &= ~_PAGE_PAT;
+		sub_se.val64 |= (se->val64 & _PAGE_PAT_LARGE) >> 5;
+
+		ops->set_pfn(&sub_se, dma_addr >> PAGE_SHIFT);
+		ppgtt_set_shadow_entry(sub_spt, &sub_se, sub_index);
+	}
+
+	/* Clear dirty field. */
+	se->val64 &= ~_PAGE_DIRTY;
+
+	ops->clear_pse(se);
+	ops->clear_ips(se);
+	ops->set_pfn(se, sub_spt->shadow_page.mfn);
+	ppgtt_set_shadow_entry(spt, se, index);
+	return 0;
+}
+
 static int split_64KB_gtt_entry(struct intel_vgpu *vgpu,
 	struct intel_vgpu_ppgtt_spt *spt, unsigned long index,
 	struct intel_gvt_gtt_entry *se)
@@ -1122,7 +1197,7 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 {
 	struct intel_gvt_gtt_pte_ops *pte_ops = vgpu->gvt->gtt.pte_ops;
 	struct intel_gvt_gtt_entry se = *ge;
-	unsigned long gfn;
+	unsigned long gfn, page_size = PAGE_SIZE;
 	dma_addr_t dma_addr;
 	int ret;
 
@@ -1144,15 +1219,24 @@ static int ppgtt_populate_shadow_entry(struct intel_vgpu *vgpu,
 		 */
 		return split_64KB_gtt_entry(vgpu, spt, index, &se);
 	case GTT_TYPE_PPGTT_PTE_2M_ENTRY:
+		gvt_vdbg_mm("shadow 2M gtt entry\n");
+		ret = is_2MB_gtt_possible(vgpu, ge);
+		if (ret == 0)
+			return split_2MB_gtt_entry(vgpu, spt, index, &se);
+		else if (ret < 0)
+			return ret;
+		page_size = I915_GTT_PAGE_SIZE_2M;
+		break;
 	case GTT_TYPE_PPGTT_PTE_1G_ENTRY:
-		gvt_vgpu_err("GVT doesn't support 2M/1GB entry\n");
+		gvt_vgpu_err("GVT doesn't support 1GB entry\n");
 		return -EINVAL;
 	default:
 		GEM_BUG_ON(1);
 	};
 
 	/* direct shadow */
-	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, PAGE_SIZE, &dma_addr);
+	ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, gfn, page_size,
+						      &dma_addr);
 	if (ret)
 		return -ENXIO;
 
@@ -1495,6 +1579,12 @@ static int ppgtt_handle_guest_write_page_table(
 					vgpu->gtt.scratch_pt[type].page_mfn);
 				ppgtt_set_shadow_entry(spt, &old_se, index + i);
 			}
+		} else if (old_se.type == GTT_TYPE_PPGTT_PTE_2M_ENTRY ||
+			   old_se.type == GTT_TYPE_PPGTT_PTE_1G_ENTRY) {
+			ops->clear_pse(&old_se);
+			ops->set_pfn(&old_se,
+				     vgpu->gtt.scratch_pt[type].page_mfn);
+			ppgtt_set_shadow_entry(spt, &old_se, index);
 		} else {
 			ops->set_pfn(&old_se,
 				     vgpu->gtt.scratch_pt[type].page_mfn);
-- 
cgit v1.2.3


From 54c81653bd67ce2a11fa08295d9148385ea29603 Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:44 +0800
Subject: drm/i915/gvt: Handle special sequence on PDE IPS bit

If the guest update the 64K gtt entry before changing IPS bit of PDE, we
need to re-shadow the whole page table. Because we have ignored all
updates to unused entries.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index 5a66d0f3365c..b40c6154e571 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -1045,14 +1045,24 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 
 	GEM_BUG_ON(!gtt_type_is_pt(get_next_pt_type(we->type)));
 
+	if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
+		ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
+
 	spt = intel_vgpu_find_spt_by_gfn(vgpu, ops->get_pfn(we));
-	if (spt)
+	if (spt) {
 		ppgtt_get_spt(spt);
-	else {
-		int type = get_next_pt_type(we->type);
 
-		if (we->type == GTT_TYPE_PPGTT_PDE_ENTRY)
-			ips = vgpu_ips_enabled(vgpu) && ops->test_ips(we);
+		if (ips != spt->guest_page.pde_ips) {
+			spt->guest_page.pde_ips = ips;
+
+			gvt_dbg_mm("reshadow PDE since ips changed\n");
+			clear_page(spt->shadow_page.vaddr);
+			ret = ppgtt_populate_spt(spt);
+			if (ret)
+				goto fail;
+		}
+	} else {
+		int type = get_next_pt_type(we->type);
 
 		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
-- 
cgit v1.2.3


From 80e76ea631de6e14c2c436b278ee0c6871227606 Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:45 +0800
Subject: drm/i915/gvt: Fix error handling in ppgtt_populate_spt_by_guest_entry

Don't forget to free allocated spt if shadowing failed.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gtt.c | 33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c
index b40c6154e571..156ceeeb7446 100644
--- a/drivers/gpu/drm/i915/gvt/gtt.c
+++ b/drivers/gpu/drm/i915/gvt/gtt.c
@@ -907,15 +907,22 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_alloc_spt_gfn(
 	     i += (spt->shadow_page.pde_ips ? GTT_64K_PTE_STRIDE : 1)) \
 		if (!ppgtt_get_shadow_entry(spt, e, i))
 
-static void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
+static inline void ppgtt_get_spt(struct intel_vgpu_ppgtt_spt *spt)
 {
 	int v = atomic_read(&spt->refcount);
 
 	trace_spt_refcount(spt->vgpu->id, "inc", spt, v, (v + 1));
-
 	atomic_inc(&spt->refcount);
 }
 
+static inline int ppgtt_put_spt(struct intel_vgpu_ppgtt_spt *spt)
+{
+	int v = atomic_read(&spt->refcount);
+
+	trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
+	return atomic_dec_return(&spt->refcount);
+}
+
 static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt);
 
 static int ppgtt_invalidate_spt_by_shadow_entry(struct intel_vgpu *vgpu,
@@ -967,14 +974,11 @@ static int ppgtt_invalidate_spt(struct intel_vgpu_ppgtt_spt *spt)
 	struct intel_gvt_gtt_entry e;
 	unsigned long index;
 	int ret;
-	int v = atomic_read(&spt->refcount);
 
 	trace_spt_change(spt->vgpu->id, "die", spt,
 			spt->guest_page.gfn, spt->shadow_page.type);
 
-	trace_spt_refcount(spt->vgpu->id, "dec", spt, v, (v - 1));
-
-	if (atomic_dec_return(&spt->refcount) > 0)
+	if (ppgtt_put_spt(spt) > 0)
 		return 0;
 
 	for_each_present_shadow_entry(spt, &e, index) {
@@ -1058,8 +1062,10 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 			gvt_dbg_mm("reshadow PDE since ips changed\n");
 			clear_page(spt->shadow_page.vaddr);
 			ret = ppgtt_populate_spt(spt);
-			if (ret)
-				goto fail;
+			if (ret) {
+				ppgtt_put_spt(spt);
+				goto err;
+			}
 		}
 	} else {
 		int type = get_next_pt_type(we->type);
@@ -1067,22 +1073,25 @@ static struct intel_vgpu_ppgtt_spt *ppgtt_populate_spt_by_guest_entry(
 		spt = ppgtt_alloc_spt_gfn(vgpu, type, ops->get_pfn(we), ips);
 		if (IS_ERR(spt)) {
 			ret = PTR_ERR(spt);
-			goto fail;
+			goto err;
 		}
 
 		ret = intel_vgpu_enable_page_track(vgpu, spt->guest_page.gfn);
 		if (ret)
-			goto fail;
+			goto err_free_spt;
 
 		ret = ppgtt_populate_spt(spt);
 		if (ret)
-			goto fail;
+			goto err_free_spt;
 
 		trace_spt_change(vgpu->id, "new", spt, spt->guest_page.gfn,
 				 spt->shadow_page.type);
 	}
 	return spt;
-fail:
+
+err_free_spt:
+	ppgtt_free_spt(spt);
+err:
 	gvt_vgpu_err("fail: shadow page %p guest entry 0x%llx type %d\n",
 		     spt, we->val64, we->type);
 	return ERR_PTR(ret);
-- 
cgit v1.2.3


From aa36ed6d9536ad694995340264b69d57b01da7d3 Mon Sep 17 00:00:00 2001
From: Changbin Du <changbin.du@intel.com>
Date: Tue, 15 May 2018 10:35:46 +0800
Subject: drm/i915: Enable platform support for vGPU huge gtt pages

Now GVTg supports shadowing both 2M/64K huge gtt pages. So let's turn on
the cap info bit VGT_CAPS_HUGE_GTT.

v2: Split changes in i915 side into a separated patch.

Signed-off-by: Changbin Du <changbin.du@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/vgpu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/i915/gvt/vgpu.c b/drivers/gpu/drm/i915/gvt/vgpu.c
index 889d10f8ee96..aa063b275e81 100644
--- a/drivers/gpu/drm/i915/gvt/vgpu.c
+++ b/drivers/gpu/drm/i915/gvt/vgpu.c
@@ -46,6 +46,7 @@ void populate_pvinfo_page(struct intel_vgpu *vgpu)
 
 	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) = VGT_CAPS_FULL_48BIT_PPGTT;
 	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HWSP_EMULATION;
+	vgpu_vreg_t(vgpu, vgtif_reg(vgt_caps)) |= VGT_CAPS_HUGE_GTT;
 
 	vgpu_vreg_t(vgpu, vgtif_reg(avail_rs.mappable_gmadr.base)) =
 		vgpu_aperture_gmadr_base(vgpu);
-- 
cgit v1.2.3


From 93d68b258e7d6b2b4b0716c6f33a38d5b6a536ff Mon Sep 17 00:00:00 2001
From: Colin Xu <colin.xu@intel.com>
Date: Mon, 9 Jul 2018 09:28:18 +0800
Subject: drm/i915/gvt: Handle EDP_PSR_IMR and EDP_PSR_IIR for BXT.

BXT supports EDP. However since GVT-g only simulate DP monitor
to guest and handles EDP_PSR_IMR and EDP_PSR_IIR as default MMIO
r/w. If guest r/w these IMR/IIR, GVT-g won't simulate the real
HW behavior and below warning is printed:
--------
Interrupt register 0x64838 is not zero: 0xffffffff
WARNING: CPU: 1 PID: 1 at drivers/gpu/drm/i915/i915_irq.c:161
gen3_assert_iir_is_zero+0x34/0xa0

Call Trace:
gen8_de_irq_postinstall+0xad/0x330
gen8_irq_postinstall+0x23/0x80
drm_irq_install+0xb5/0x130
i915_driver_load+0xafd/0xf70
--------
Since GVT-g won't simulate EDP to guest, always set EDP_PSR_IMR
and EDP_PSR_IIR IMR/IIR to 0.

Signed-off-by: Colin Xu <colin.xu@intel.com>

Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/handlers.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 17f56fc20613..e2e252c67de8 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1584,6 +1584,13 @@ static int bxt_gt_disp_pwron_write(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+static int bxt_edp_psr_imr_iir_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	vgpu_vreg(vgpu, offset) = 0;
+	return 0;
+}
+
 static int mmio_read_from_hw(struct intel_vgpu *vgpu,
 		unsigned int offset, void *p_data, unsigned int bytes)
 {
@@ -3182,6 +3189,9 @@ static int init_bxt_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_B), D_BXT);
 	MMIO_D(HSW_TVIDEO_DIP_GCP(TRANSCODER_C), D_BXT);
 
+	MMIO_DH(EDP_PSR_IMR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
+	MMIO_DH(EDP_PSR_IIR, D_BXT, NULL, bxt_edp_psr_imr_iir_write);
+
 	MMIO_D(RC6_CTX_BASE, D_BXT);
 
 	MMIO_D(GEN8_PUSHBUS_CONTROL, D_BXT);
-- 
cgit v1.2.3


From ec1460ef7a2c8f75e8efe9b140424dd1ab1e5e28 Mon Sep 17 00:00:00 2001
From: Jakob Albert <jakob.j.albert@fau.de>
Date: Wed, 13 Jun 2018 17:13:23 +0200
Subject: hwmon: (nct7904) Fix SPACING errors

Fix SPACING errors reported by checkpatch.pl

Signed-off-by: Lorenz Kaestle <lorenz.kaestle@fau.de>
Signed-off-by: Jakob Albert <jakob.j.albert@fau.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/nct7904.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 95a68ab175c7..7de2421aaba1 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -159,7 +159,7 @@ static int nct7904_read_fan(struct device *dev, u32 attr, int channel,
 	unsigned int cnt, rpm;
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_fan_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 FANIN1_HV_REG + channel * 2);
@@ -200,7 +200,7 @@ static int nct7904_read_in(struct device *dev, u32 attr, int channel,
 
 	index = nct7904_chan_to_index[channel];
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_in_input:
 		ret = nct7904_read_reg16(data, BANK_0,
 					 VSEN1_HV_REG + index * 2);
@@ -236,7 +236,7 @@ static int nct7904_read_temp(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret, temp;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_temp_input:
 		if (channel == 0)
 			ret = nct7904_read_reg16(data, BANK_0, LTD_HV_REG);
@@ -276,7 +276,7 @@ static int nct7904_read_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		ret = nct7904_read_reg(data, BANK_3, FANCTL1_OUT_REG + channel);
 		if (ret < 0)
@@ -301,7 +301,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 	struct nct7904_data *data = dev_get_drvdata(dev);
 	int ret;
 
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 		if (val < 0 || val > 255)
 			return -EINVAL;
@@ -322,7 +322,7 @@ static int nct7904_write_pwm(struct device *dev, u32 attr, int channel,
 
 static umode_t nct7904_pwm_is_visible(const void *_data, u32 attr, int channel)
 {
-	switch(attr) {
+	switch (attr) {
 	case hwmon_pwm_input:
 	case hwmon_pwm_enable:
 		return S_IRUGO | S_IWUSR;
-- 
cgit v1.2.3


From 12f0c3401cea2d0a62413a71a6f930a9e975265b Mon Sep 17 00:00:00 2001
From: Jakob Albert <jakob.j.albert@fau.de>
Date: Wed, 13 Jun 2018 17:13:24 +0200
Subject: hwmon: (nct7904) Fix CODE_INDENT error

Fix CODE_INDENT error reported by checkpatch.pl

Signed-off-by: Lorenz Kaestle <lorenz.kaestle@fau.de>
Signed-off-by: Jakob Albert <jakob.j.albert@fau.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/nct7904.c | 48 ++++++++++++++++++++++++------------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 7de2421aaba1..657ce88435a3 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -431,15 +431,15 @@ static const struct hwmon_channel_info nct7904_in = {
 };
 
 static const u32 nct7904_fan_config[] = {
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-            HWMON_F_INPUT,
-	    0
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_fan = {
@@ -448,11 +448,11 @@ static const struct hwmon_channel_info nct7904_fan = {
 };
 
 static const u32 nct7904_pwm_config[] = {
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-            HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
-	    0
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	HWMON_PWM_INPUT | HWMON_PWM_ENABLE,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_pwm = {
@@ -461,16 +461,16 @@ static const struct hwmon_channel_info nct7904_pwm = {
 };
 
 static const u32 nct7904_temp_config[] = {
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-            HWMON_T_INPUT,
-	    0
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	HWMON_T_INPUT,
+	0
 };
 
 static const struct hwmon_channel_info nct7904_temp = {
-- 
cgit v1.2.3


From 73ed6e22c34f4de09f5af5dfe3926e1d41082a89 Mon Sep 17 00:00:00 2001
From: Jakob Albert <jakob.j.albert@fau.de>
Date: Wed, 13 Jun 2018 17:13:25 +0200
Subject: hwmon: (nct7904) Fix UNSPECIFIED_INT warning

Fix UNSPECIFIED_INT warning reported by checkpatch.pl

Signed-off-by: Lorenz Kaestle <lorenz.kaestle@fau.de>
Signed-off-by: Jakob Albert <jakob.j.albert@fau.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/nct7904.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index 657ce88435a3..7815ddf149f6 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -77,7 +77,7 @@ struct nct7904_data {
 };
 
 /* Access functions */
-static int nct7904_bank_lock(struct nct7904_data *data, unsigned bank)
+static int nct7904_bank_lock(struct nct7904_data *data, unsigned int bank)
 {
 	int ret;
 
@@ -99,7 +99,7 @@ static inline void nct7904_bank_release(struct nct7904_data *data)
 
 /* Read 1-byte register. Returns unsigned reg or -ERRNO on error. */
 static int nct7904_read_reg(struct nct7904_data *data,
-			    unsigned bank, unsigned reg)
+			    unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret;
@@ -117,7 +117,7 @@ static int nct7904_read_reg(struct nct7904_data *data,
  * -ERRNO on error.
  */
 static int nct7904_read_reg16(struct nct7904_data *data,
-			      unsigned bank, unsigned reg)
+			      unsigned int bank, unsigned int reg)
 {
 	struct i2c_client *client = data->client;
 	int ret, hi;
@@ -139,7 +139,7 @@ static int nct7904_read_reg16(struct nct7904_data *data,
 
 /* Write 1-byte register. Returns 0 or -ERRNO on error. */
 static int nct7904_write_reg(struct nct7904_data *data,
-			     unsigned bank, unsigned reg, u8 val)
+			     unsigned int bank, unsigned int reg, u8 val)
 {
 	struct i2c_client *client = data->client;
 	int ret;
-- 
cgit v1.2.3


From 57fec3acb47c99c688de9daf4c6a2ffa364cdb16 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Mon, 18 Jun 2018 09:21:46 -0700
Subject: hwmon: (nct6775) Fix comment in the description of pwm_mode

Commit 415eb2a1aaa488 ("hwmon: (nct6775) Fix writing pwmX_mode") changed
the definition of the pwm_mode variable, but did not update the comment
describing it.

Reported-by: Ben Hutchings <ben.hutchings@codethink.co.uk>
Cc: Ben Hutchings <ben.hutchings@codethink.co.uk>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/nct6775.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index f9d1349c3286..37149909f8a8 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -1050,8 +1050,8 @@ struct nct6775_data {
 	u64 beeps;
 
 	u8 pwm_num;	/* number of pwm */
-	u8 pwm_mode[NUM_FAN];	/* 1->DC variable voltage,
-				 * 0->PWM variable duty cycle
+	u8 pwm_mode[NUM_FAN];	/* 0->DC variable voltage,
+				 * 1->PWM variable duty cycle
 				 */
 	enum pwm_enable pwm_enable[NUM_FAN];
 			/* 0->off
-- 
cgit v1.2.3


From ffb32432457c6a6deffb64982b54d8f7b72ef618 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 2 Jul 2018 16:30:17 -0500
Subject: hwmon: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/emc1403.c | 2 ++
 drivers/hwmon/nct6775.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/emc1403.c b/drivers/hwmon/emc1403.c
index 1ea7ca510f84..aaebeb726d6a 100644
--- a/drivers/hwmon/emc1403.c
+++ b/drivers/hwmon/emc1403.c
@@ -443,8 +443,10 @@ static int emc1403_probe(struct i2c_client *client,
 	switch (id->driver_data) {
 	case emc1404:
 		data->groups[2] = &emc1404_group;
+		/* fall through */
 	case emc1403:
 		data->groups[1] = &emc1403_group;
+		/* fall through */
 	case emc1402:
 		data->groups[0] = &emc1402_group;
 	}
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index 37149909f8a8..c6bd61e4695a 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -2541,7 +2541,7 @@ static void pwm_update_registers(struct nct6775_data *data, int nr)
 	case thermal_cruise:
 		nct6775_write_value(data, data->REG_TARGET[nr],
 				    data->target_temp[nr]);
-		/* intentional */
+		/* fall through  */
 	default:
 		reg = nct6775_read_value(data, data->REG_FAN_MODE[nr]);
 		reg = (reg & ~data->tolerance_mask) |
-- 
cgit v1.2.3


From 65afb4c8e7e4e7e74b28efa1df62da503ca3e7a6 Mon Sep 17 00:00:00 2001
From: Vadim Pasternak <vadimp@mellanox.com>
Date: Tue, 3 Jul 2018 07:00:09 +0000
Subject: hwmon: (mlxreg-fan) Add support for Mellanox FAN driver

Driver obtains PWM and tachometers registers location according to the
system configuration and creates FAN/PWM hwmon objects and a cooling
device. PWM and tachometers are controlled through the on-board
programmable device, which exports its register map. This device could be
attached to any bus type, for which register mapping is supported. Single
instance is created with one PWM control, up to 12 tachometers and one
cooling device. It could be as many instances as programmable device
supports.

Currently driver will be activated from the Mellanox platform driver:
drivers/platform/x86/mlx-platform.c.
For the future ARM based systems it could be activated from the ARM
platform module.

Signed-off-by: Vadim Pasternak <vadimp@mellanox.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/mlxreg-fan |  60 +++++
 drivers/hwmon/Kconfig          |  12 +
 drivers/hwmon/Makefile         |   1 +
 drivers/hwmon/mlxreg-fan.c     | 489 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 562 insertions(+)
 create mode 100644 Documentation/hwmon/mlxreg-fan
 create mode 100644 drivers/hwmon/mlxreg-fan.c

diff --git a/Documentation/hwmon/mlxreg-fan b/Documentation/hwmon/mlxreg-fan
new file mode 100644
index 000000000000..fc531c6978d4
--- /dev/null
+++ b/Documentation/hwmon/mlxreg-fan
@@ -0,0 +1,60 @@
+Kernel driver mlxreg-fan
+========================
+
+Provides FAN control for the next Mellanox systems:
+QMB700, equipped with 40x200GbE InfiniBand ports;
+MSN3700, equipped with 32x200GbE or 16x400GbE Ethernet ports;
+MSN3410, equipped with 6x400GbE plus 48x50GbE Ethernet ports;
+MSN3800, equipped with 64x1000GbE Ethernet ports;
+These are the Top of the Rack systems, equipped with Mellanox switch
+board with Mellanox Quantum or Spectrume-2 devices.
+FAN controller is implemented by the programmable device logic.
+
+The default registers offsets set within the programmable device is as
+following:
+- pwm1			0xe3
+- fan1 (tacho1)		0xe4
+- fan2 (tacho2)		0xe5
+- fan3 (tacho3)		0xe6
+- fan4 (tacho4)		0xe7
+- fan5 (tacho5)		0xe8
+- fan6 (tacho6)		0xe9
+- fan7 (tacho7)		0xea
+- fan8 (tacho8)		0xeb
+- fan9 (tacho9)		0xec
+- fan10 (tacho10)	0xed
+- fan11 (tacho11)	0xee
+- fan12 (tacho12)	0xef
+This setup can be re-programmed with other registers.
+
+Author: Vadim Pasternak <vadimp@mellanox.com>
+
+Description
+-----------
+
+The driver implements a simple interface for driving a fan connected to
+a PWM output and tachometer inputs.
+This driver obtains PWM and tachometers registers location according to
+the system configuration and creates FAN/PWM hwmon objects and a cooling
+device. PWM and tachometers are sensed through the on-board programmable
+device, which exports its register map. This device could be attached to
+any bus type, for which register mapping is supported.
+Single instance is created with one PWM control, up to 12 tachometers and
+one cooling device. It could be as many instances as programmable device
+supports.
+The driver exposes the fan to the user space through the hwmon's and
+thermal's sysfs interfaces.
+
+/sys files in hwmon subsystem
+-----------------------------
+
+fan[1-12]_fault - RO files for tachometers TACH1-TACH12 fault indication
+fan[1-12]_input - RO files for tachometers TACH1-TACH12 input (in RPM)
+pwm1		- RW file for fan[1-12] target duty cycle (0..255)
+
+/sys files in thermal subsystem
+-------------------------------
+
+cur_state	- RW file for current cooling state of the cooling device
+		  (0..max_state)
+max_state	- RO file for maximum cooling state of the cooling device
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index f10840ad465c..fd7fb6c041c2 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -937,6 +937,18 @@ config SENSORS_MCP3021
 	  This driver can also be built as a module.  If so, the module
 	  will be called mcp3021.
 
+config SENSORS_MLXREG_FAN
+	tristate "Mellanox Mellanox FAN driver"
+	depends on MELLANOX_PLATFORM
+	imply THERMAL
+	select REGMAP
+	help
+	  This option enables support for the FAN control on the Mellanox
+	  Ethernet and InfiniBand switches. The driver can be activated by the
+	  platform device add call. Say Y to enable these. To compile this
+	  driver as a module, choose 'M' here: the module will be called
+	  mlxreg-fan.
+
 config SENSORS_TC654
 	tristate "Microchip TC654/TC655 and compatibles"
 	depends on I2C
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index e7d52a36e6c4..cac3c06d2832 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -129,6 +129,7 @@ obj-$(CONFIG_SENSORS_MAX31790)	+= max31790.o
 obj-$(CONFIG_SENSORS_MC13783_ADC)+= mc13783-adc.o
 obj-$(CONFIG_SENSORS_MCP3021)	+= mcp3021.o
 obj-$(CONFIG_SENSORS_TC654)	+= tc654.o
+obj-$(CONFIG_SENSORS_MLXREG_FAN) += mlxreg-fan.o
 obj-$(CONFIG_SENSORS_MENF21BMC_HWMON) += menf21bmc_hwmon.o
 obj-$(CONFIG_SENSORS_NCT6683)	+= nct6683.o
 obj-$(CONFIG_SENSORS_NCT6775)	+= nct6775.o
diff --git a/drivers/hwmon/mlxreg-fan.c b/drivers/hwmon/mlxreg-fan.c
new file mode 100644
index 000000000000..de46577c7d5a
--- /dev/null
+++ b/drivers/hwmon/mlxreg-fan.c
@@ -0,0 +1,489 @@
+// SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause)
+//
+// Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+// Copyright (c) 2018 Vadim Pasternak <vadimp@mellanox.com>
+
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/module.h>
+#include <linux/platform_data/mlxreg.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/thermal.h>
+
+#define MLXREG_FAN_MAX_TACHO		12
+#define MLXREG_FAN_MAX_STATE		10
+#define MLXREG_FAN_MIN_DUTY		51	/* 20% */
+#define MLXREG_FAN_MAX_DUTY		255	/* 100% */
+/*
+ * Minimum and maximum FAN allowed speed in percent: from 20% to 100%. Values
+ * MLXREG_FAN_MAX_STATE + x, where x is between 2 and 10 are used for
+ * setting FAN speed dynamic minimum. For example, if value is set to 14 (40%)
+ * cooling levels vector will be set to 4, 4, 4, 4, 4, 5, 6, 7, 8, 9, 10 to
+ * introduce PWM speed in percent: 40, 40, 40, 40, 40, 50, 60. 70, 80, 90, 100.
+ */
+#define MLXREG_FAN_SPEED_MIN			(MLXREG_FAN_MAX_STATE + 2)
+#define MLXREG_FAN_SPEED_MAX			(MLXREG_FAN_MAX_STATE * 2)
+#define MLXREG_FAN_SPEED_MIN_LEVEL		2	/* 20 percent */
+#define MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF	44
+#define MLXREG_FAN_TACHO_DIVIDER_DEF		1132
+/*
+ * FAN datasheet defines the formula for RPM calculations as RPM = 15/t-high.
+ * The logic in a programmable device measures the time t-high by sampling the
+ * tachometer every t-sample (with the default value 11.32 uS) and increment
+ * a counter (N) as long as the pulse has not change:
+ * RPM = 15 / (t-sample * (K + Regval)), where:
+ * Regval: is the value read from the programmable device register;
+ *  - 0xff - represents tachometer fault;
+ *  - 0xfe - represents tachometer minimum value , which is 4444 RPM;
+ *  - 0x00 - represents tachometer maximum value , which is 300000 RPM;
+ * K: is 44 and it represents the minimum allowed samples per pulse;
+ * N: is equal K + Regval;
+ * In order to calculate RPM from the register value the following formula is
+ * used: RPM = 15 / ((Regval + K) * 11.32) * 10^(-6)), which in  the
+ * default case is modified to:
+ * RPM = 15000000 * 100 / ((Regval + 44) * 1132);
+ * - for Regval 0x00, RPM will be 15000000 * 100 / (44 * 1132) = 30115;
+ * - for Regval 0xfe, RPM will be 15000000 * 100 / ((254 + 44) * 1132) = 4446;
+ * In common case the formula is modified to:
+ * RPM = 15000000 * 100 / ((Regval + samples) * divider).
+ */
+#define MLXREG_FAN_GET_RPM(rval, d, s)	(DIV_ROUND_CLOSEST(15000000 * 100, \
+					 ((rval) + (s)) * (d)))
+#define MLXREG_FAN_GET_FAULT(val, mask) (!!((val) ^ (mask)))
+#define MLXREG_FAN_PWM_DUTY2STATE(duty)	(DIV_ROUND_CLOSEST((duty) *	\
+					 MLXREG_FAN_MAX_STATE,		\
+					 MLXREG_FAN_MAX_DUTY))
+#define MLXREG_FAN_PWM_STATE2DUTY(stat)	(DIV_ROUND_CLOSEST((stat) *	\
+					 MLXREG_FAN_MAX_DUTY,		\
+					 MLXREG_FAN_MAX_STATE))
+
+/*
+ * struct mlxreg_fan_tacho - tachometer data (internal use):
+ *
+ * @connected: indicates if tachometer is connected;
+ * @reg: register offset;
+ * @mask: fault mask;
+ */
+struct mlxreg_fan_tacho {
+	bool connected;
+	u32 reg;
+	u32 mask;
+};
+
+/*
+ * struct mlxreg_fan_pwm - PWM data (internal use):
+ *
+ * @connected: indicates if PWM is connected;
+ * @reg: register offset;
+ */
+struct mlxreg_fan_pwm {
+	bool connected;
+	u32 reg;
+};
+
+/*
+ * struct mlxreg_fan - private data (internal use):
+ *
+ * @dev: basic device;
+ * @regmap: register map of parent device;
+ * @tacho: tachometer data;
+ * @pwm: PWM data;
+ * @samples: minimum allowed samples per pulse;
+ * @divider: divider value for tachometer RPM calculation;
+ * @cooling: cooling device levels;
+ * @cdev: cooling device;
+ */
+struct mlxreg_fan {
+	struct device *dev;
+	void *regmap;
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan_tacho tacho[MLXREG_FAN_MAX_TACHO];
+	struct mlxreg_fan_pwm pwm;
+	int samples;
+	int divider;
+	u8 cooling_levels[MLXREG_FAN_MAX_STATE + 1];
+	struct thermal_cooling_device *cdev;
+};
+
+static int
+mlxreg_fan_read(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		int channel, long *val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+	struct mlxreg_fan_tacho *tacho;
+	u32 regval;
+	int err;
+
+	switch (type) {
+	case hwmon_fan:
+		tacho = &fan->tacho[channel];
+		switch (attr) {
+		case hwmon_fan_input:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_RPM(regval, fan->divider,
+						  fan->samples);
+			break;
+
+		case hwmon_fan_fault:
+			err = regmap_read(fan->regmap, tacho->reg, &regval);
+			if (err)
+				return err;
+
+			*val = MLXREG_FAN_GET_FAULT(regval, tacho->mask);
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+			if (err)
+				return err;
+
+			*val = regval;
+			break;
+
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int
+mlxreg_fan_write(struct device *dev, enum hwmon_sensor_types type, u32 attr,
+		 int channel, long val)
+{
+	struct mlxreg_fan *fan = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_pwm:
+		switch (attr) {
+		case hwmon_pwm_input:
+			if (val < MLXREG_FAN_MIN_DUTY ||
+			    val > MLXREG_FAN_MAX_DUTY)
+				return -EINVAL;
+			return regmap_write(fan->regmap, fan->pwm.reg, val);
+		default:
+			return -EOPNOTSUPP;
+		}
+		break;
+
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static umode_t
+mlxreg_fan_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
+		      int channel)
+{
+	switch (type) {
+	case hwmon_fan:
+		if (!(((struct mlxreg_fan *)data)->tacho[channel].connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_fan_input:
+		case hwmon_fan_fault:
+			return 0444;
+		default:
+			break;
+		}
+		break;
+
+	case hwmon_pwm:
+		if (!(((struct mlxreg_fan *)data)->pwm.connected))
+			return 0;
+
+		switch (attr) {
+		case hwmon_pwm_input:
+			return 0644;
+		default:
+			break;
+		}
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const u32 mlxreg_fan_hwmon_fan_config[] = {
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	HWMON_F_INPUT | HWMON_F_FAULT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_fan = {
+	.type = hwmon_fan,
+	.config = mlxreg_fan_hwmon_fan_config,
+};
+
+static const u32 mlxreg_fan_hwmon_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info mlxreg_fan_hwmon_pwm = {
+	.type = hwmon_pwm,
+	.config = mlxreg_fan_hwmon_pwm_config,
+};
+
+static const struct hwmon_channel_info *mlxreg_fan_hwmon_info[] = {
+	&mlxreg_fan_hwmon_fan,
+	&mlxreg_fan_hwmon_pwm,
+	NULL
+};
+
+static const struct hwmon_ops mlxreg_fan_hwmon_hwmon_ops = {
+	.is_visible = mlxreg_fan_is_visible,
+	.read = mlxreg_fan_read,
+	.write = mlxreg_fan_write,
+};
+
+static const struct hwmon_chip_info mlxreg_fan_hwmon_chip_info = {
+	.ops = &mlxreg_fan_hwmon_hwmon_ops,
+	.info = mlxreg_fan_hwmon_info,
+};
+
+static int mlxreg_fan_get_max_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+{
+	*state = MLXREG_FAN_MAX_STATE;
+	return 0;
+}
+
+static int mlxreg_fan_get_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long *state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	u32 regval;
+	int err;
+
+	err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+	if (err) {
+		dev_err(fan->dev, "Failed to query PWM duty\n");
+		return err;
+	}
+
+	*state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+
+	return 0;
+}
+
+static int mlxreg_fan_set_cur_state(struct thermal_cooling_device *cdev,
+				    unsigned long state)
+
+{
+	struct mlxreg_fan *fan = cdev->devdata;
+	unsigned long cur_state;
+	u32 regval;
+	int i;
+	int err;
+
+	/*
+	 * Verify if this request is for changing allowed FAN dynamical
+	 * minimum. If it is - update cooling levels accordingly and update
+	 * state, if current state is below the newly requested minimum state.
+	 * For example, if current state is 5, and minimal state is to be
+	 * changed from 4 to 6, fan->cooling_levels[0 to 5] will be changed all
+	 * from 4 to 6. And state 5 (fan->cooling_levels[4]) should be
+	 * overwritten.
+	 */
+	if (state >= MLXREG_FAN_SPEED_MIN && state <= MLXREG_FAN_SPEED_MAX) {
+		state -= MLXREG_FAN_MAX_STATE;
+		for (i = 0; i < state; i++)
+			fan->cooling_levels[i] = state;
+		for (i = state; i <= MLXREG_FAN_MAX_STATE; i++)
+			fan->cooling_levels[i] = i;
+
+		err = regmap_read(fan->regmap, fan->pwm.reg, &regval);
+		if (err) {
+			dev_err(fan->dev, "Failed to query PWM duty\n");
+			return err;
+		}
+
+		cur_state = MLXREG_FAN_PWM_DUTY2STATE(regval);
+		if (state < cur_state)
+			return 0;
+
+		state = cur_state;
+	}
+
+	if (state > MLXREG_FAN_MAX_STATE)
+		return -EINVAL;
+
+	/* Normalize the state to the valid speed range. */
+	state = fan->cooling_levels[state];
+	err = regmap_write(fan->regmap, fan->pwm.reg,
+			   MLXREG_FAN_PWM_STATE2DUTY(state));
+	if (err) {
+		dev_err(fan->dev, "Failed to write PWM duty\n");
+		return err;
+	}
+	return 0;
+}
+
+static const struct thermal_cooling_device_ops mlxreg_fan_cooling_ops = {
+	.get_max_state	= mlxreg_fan_get_max_state,
+	.get_cur_state	= mlxreg_fan_get_cur_state,
+	.set_cur_state	= mlxreg_fan_set_cur_state,
+};
+
+static int mlxreg_fan_config(struct mlxreg_fan *fan,
+			     struct mlxreg_core_platform_data *pdata)
+{
+	struct mlxreg_core_data *data = pdata->data;
+	bool configured = false;
+	int tacho_num = 0, i;
+
+	fan->samples = MLXREG_FAN_TACHO_SAMPLES_PER_PULSE_DEF;
+	fan->divider = MLXREG_FAN_TACHO_DIVIDER_DEF;
+	for (i = 0; i < pdata->counter; i++, data++) {
+		if (strnstr(data->label, "tacho", sizeof(data->label))) {
+			if (tacho_num == MLXREG_FAN_MAX_TACHO) {
+				dev_err(fan->dev, "too many tacho entries: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->tacho[tacho_num].reg = data->reg;
+			fan->tacho[tacho_num].mask = data->mask;
+			fan->tacho[tacho_num++].connected = true;
+		} else if (strnstr(data->label, "pwm", sizeof(data->label))) {
+			if (fan->pwm.connected) {
+				dev_err(fan->dev, "duplicate pwm entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->pwm.reg = data->reg;
+			fan->pwm.connected = true;
+		} else if (strnstr(data->label, "conf", sizeof(data->label))) {
+			if (configured) {
+				dev_err(fan->dev, "duplicate conf entry: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			/* Validate that conf parameters are not zeros. */
+			if (!data->mask || !data->bit) {
+				dev_err(fan->dev, "invalid conf entry params: %s\n",
+					data->label);
+				return -EINVAL;
+			}
+			fan->samples = data->mask;
+			fan->divider = data->bit;
+			configured = true;
+		} else {
+			dev_err(fan->dev, "invalid label: %s\n", data->label);
+			return -EINVAL;
+		}
+	}
+
+	/* Init cooling levels per PWM state. */
+	for (i = 0; i < MLXREG_FAN_SPEED_MIN_LEVEL; i++)
+		fan->cooling_levels[i] = MLXREG_FAN_SPEED_MIN_LEVEL;
+	for (i = MLXREG_FAN_SPEED_MIN_LEVEL; i <= MLXREG_FAN_MAX_STATE; i++)
+		fan->cooling_levels[i] = i;
+
+	return 0;
+}
+
+static int mlxreg_fan_probe(struct platform_device *pdev)
+{
+	struct mlxreg_core_platform_data *pdata;
+	struct mlxreg_fan *fan;
+	struct device *hwm;
+	int err;
+
+	pdata = dev_get_platdata(&pdev->dev);
+	if (!pdata) {
+		dev_err(&pdev->dev, "Failed to get platform data.\n");
+		return -EINVAL;
+	}
+
+	fan = devm_kzalloc(&pdev->dev, sizeof(*fan), GFP_KERNEL);
+	if (!fan)
+		return -ENOMEM;
+
+	fan->dev = &pdev->dev;
+	fan->regmap = pdata->regmap;
+	platform_set_drvdata(pdev, fan);
+
+	err = mlxreg_fan_config(fan, pdata);
+	if (err)
+		return err;
+
+	hwm = devm_hwmon_device_register_with_info(&pdev->dev, "mlxreg_fan",
+						   fan,
+						   &mlxreg_fan_hwmon_chip_info,
+						   NULL);
+	if (IS_ERR(hwm)) {
+		dev_err(&pdev->dev, "Failed to register hwmon device\n");
+		return PTR_ERR(hwm);
+	}
+
+	if (IS_REACHABLE(CONFIG_THERMAL)) {
+		fan->cdev = thermal_cooling_device_register("mlxreg_fan", fan,
+						&mlxreg_fan_cooling_ops);
+		if (IS_ERR(fan->cdev)) {
+			dev_err(&pdev->dev, "Failed to register cooling device\n");
+			return PTR_ERR(fan->cdev);
+		}
+	}
+
+	return 0;
+}
+
+static int mlxreg_fan_remove(struct platform_device *pdev)
+{
+	struct mlxreg_fan *fan = platform_get_drvdata(pdev);
+
+	if (IS_REACHABLE(CONFIG_THERMAL))
+		thermal_cooling_device_unregister(fan->cdev);
+
+	return 0;
+}
+
+static struct platform_driver mlxreg_fan_driver = {
+	.driver = {
+	    .name = "mlxreg-fan",
+	},
+	.probe = mlxreg_fan_probe,
+	.remove = mlxreg_fan_remove,
+};
+
+module_platform_driver(mlxreg_fan_driver);
+
+MODULE_AUTHOR("Vadim Pasternak <vadimp@mellanox.com>");
+MODULE_DESCRIPTION("Mellanox FAN driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:mlxreg-fan");
-- 
cgit v1.2.3


From fb41a710f84efd1f7a85ffcc4adead6a971b5163 Mon Sep 17 00:00:00 2001
From: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
Date: Fri, 6 Jul 2018 17:26:06 +0530
Subject: hwmon: Document the sensor enable attribute

Document new ABI attributes:
	in[0-*]_enable
	fan[1-*]_enable
	temp[1-*]_enable
	curr[1-*]_enable
	power[1-*]_enable
	energy[1-*]_enable
	humidity[1-*]_enable

Signed-off-by: Shilpasri G Bhat <shilpa.bhat@linux.vnet.ibm.com>
[groeck: Updated commit text, removed unnecessary details from
 ABI description]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/sysfs-interface | 48 +++++++++++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/Documentation/hwmon/sysfs-interface b/Documentation/hwmon/sysfs-interface
index fc337c317c67..2b9e1005d88b 100644
--- a/Documentation/hwmon/sysfs-interface
+++ b/Documentation/hwmon/sysfs-interface
@@ -171,6 +171,13 @@ in[0-*]_label	Suggested voltage channel label.
 		user-space.
 		RO
 
+in[0-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 cpu[0-*]_vid	CPU core reference voltage.
 		Unit: millivolt
 		RO
@@ -236,6 +243,13 @@ fan[1-*]_label	Suggested fan channel label.
 		In all other cases, the label is provided by user-space.
 		RO
 
+fan[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Also see the Alarms section for status flags associated with fans.
 
 
@@ -409,6 +423,13 @@ temp_reset_history
 		Reset temp_lowest and temp_highest for all sensors
 		WO
 
+temp[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Some chips measure temperature using external thermistors and an ADC, and
 report the temperature measurement as a voltage. Converting this voltage
 back to a temperature (or the other way around for limits) requires
@@ -468,6 +489,13 @@ curr_reset_history
 		Reset currX_lowest and currX_highest for all sensors
 		WO
 
+curr[1-*]_enable
+		Enable or disable the sensors.
+		When disabled the sensor read will return -ENODATA.
+		1: Enable
+		0: Disable
+		RW
+
 Also see the Alarms section for status flags associated with currents.
 
 *********
@@ -566,6 +594,13 @@ power[1-*]_crit			Critical maximum power.
 				Unit: microWatt
 				RW
 
+power[1-*]_enable		Enable or disable the sensors.
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
+
 Also see the Alarms section for status flags associated with power readings.
 
 **********
@@ -576,6 +611,12 @@ energy[1-*]_input		Cumulative energy use
 				Unit: microJoule
 				RO
 
+energy[1-*]_enable		Enable or disable the sensors.
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
 
 ************
 * Humidity *
@@ -586,6 +627,13 @@ humidity[1-*]_input		Humidity
 				RO
 
 
+humidity[1-*]_enable		Enable or disable the sensors
+				When disabled the sensor read will return
+				-ENODATA.
+				1: Enable
+				0: Disable
+				RW
+
 **********
 * Alarms *
 **********
-- 
cgit v1.2.3


From 7a001dbab4ade869a149318f5f112c4f185a40dc Mon Sep 17 00:00:00 2001
From: Kun Yi <kunyi@google.com>
Date: Tue, 3 Jul 2018 15:26:49 -0700
Subject: hwmon: (pmbus/max34440) Add support for MAX34451.

MAX34451 is a 16-Channel Voltage/Current Monitor and 12-Channel
Sequencer.

Signed-off-by: Kun Yi <kunyi@google.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/max34440   | 16 ++++++--
 drivers/hwmon/pmbus/Kconfig    |  2 +-
 drivers/hwmon/pmbus/max34440.c | 93 ++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 103 insertions(+), 8 deletions(-)

diff --git a/Documentation/hwmon/max34440 b/Documentation/hwmon/max34440
index 9ba6587b7657..b2de8fa49273 100644
--- a/Documentation/hwmon/max34440
+++ b/Documentation/hwmon/max34440
@@ -16,6 +16,11 @@ Supported chips:
     Prefixes: 'max34446'
     Addresses scanned: -
     Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34446.pdf
+  * Maxim MAX34451
+    PMBus 16-Channel V/I Monitor and 12-Channel Sequencer/Marginer
+    Prefixes: 'max34451'
+    Addresses scanned: -
+    Datasheet: http://datasheets.maximintegrated.com/en/ds/MAX34451.pdf
   * Maxim MAX34460
     PMBus 12-Channel Voltage Monitor & Sequencer
     Prefix: 'max34460'
@@ -36,9 +41,10 @@ Description
 This driver supports hardware monitoring for Maxim MAX34440 PMBus 6-Channel
 Power-Supply Manager, MAX34441 PMBus 5-Channel Power-Supply Manager
 and Intelligent Fan Controller, and MAX34446 PMBus Power-Supply Data Logger.
-It also supports the MAX34460 and MAX34461 PMBus Voltage Monitor & Sequencers.
-The MAX34460 supports 12 voltage channels, and the MAX34461 supports 16 voltage
-channels.
+It also supports the MAX34451, MAX34460, and MAX34461 PMBus Voltage Monitor &
+Sequencers. The MAX34451 supports monitoring voltage or current of 12 channels
+based on GIN pins. The MAX34460 supports 12 voltage channels, and the MAX34461
+supports 16 voltage channels.
 
 The driver is a client driver to the core PMBus driver. Please see
 Documentation/hwmon/pmbus for details on PMBus client drivers.
@@ -93,7 +99,7 @@ curr[1-6]_max		Maximum current. From IOUT_OC_WARN_LIMIT register.
 curr[1-6]_crit		Critical maximum current. From IOUT_OC_FAULT_LIMIT register.
 curr[1-6]_max_alarm	Current high alarm. From IOUT_OC_WARNING status.
 curr[1-6]_crit_alarm	Current critical high alarm. From IOUT_OC_FAULT status.
-curr[1-4]_average	Historical average current (MAX34446 only).
+curr[1-4]_average	Historical average current (MAX34446/34451 only).
 curr[1-6]_highest	Historical maximum current.
 curr[1-6]_reset_history	Write any value to reset history.
 
@@ -123,5 +129,7 @@ temp[1-8]_reset_history	Write any value to reset history.
 			temp7 and temp8 attributes only exist for MAX34440.
 			MAX34446 only supports temp[1-3].
 
+MAX34451 supports attribute groups in[1-16] (or curr[1-16] based on input pins)
+and temp[1-5].
 MAX34460 supports attribute groups in[1-12] and temp[1-5].
 MAX34461 supports attribute groups in[1-16] and temp[1-5].
diff --git a/drivers/hwmon/pmbus/Kconfig b/drivers/hwmon/pmbus/Kconfig
index e71aec69e76e..a82018aaf473 100644
--- a/drivers/hwmon/pmbus/Kconfig
+++ b/drivers/hwmon/pmbus/Kconfig
@@ -130,7 +130,7 @@ config SENSORS_MAX34440
 	default n
 	help
 	  If you say yes here you get hardware monitoring support for Maxim
-	  MAX34440, MAX34441, MAX34446, MAX34460, and MAX34461.
+	  MAX34440, MAX34441, MAX34446, MAX34451, MAX34460, and MAX34461.
 
 	  This driver can also be built as a module. If so, the module will
 	  be called max34440.
diff --git a/drivers/hwmon/pmbus/max34440.c b/drivers/hwmon/pmbus/max34440.c
index 74a1f6f68fb3..47576c460010 100644
--- a/drivers/hwmon/pmbus/max34440.c
+++ b/drivers/hwmon/pmbus/max34440.c
@@ -27,7 +27,7 @@
 #include <linux/i2c.h>
 #include "pmbus.h"
 
-enum chips { max34440, max34441, max34446, max34460, max34461 };
+enum chips { max34440, max34441, max34446, max34451, max34460, max34461 };
 
 #define MAX34440_MFR_VOUT_PEAK		0xd4
 #define MAX34440_MFR_IOUT_PEAK		0xd5
@@ -44,6 +44,9 @@ enum chips { max34440, max34441, max34446, max34460, max34461 };
 #define MAX34440_STATUS_OT_FAULT	BIT(5)
 #define MAX34440_STATUS_OT_WARN		BIT(6)
 
+#define MAX34451_MFR_CHANNEL_CONFIG	0xe4
+#define MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK	0x3f
+
 struct max34440_data {
 	int id;
 	struct pmbus_driver_info info;
@@ -67,7 +70,7 @@ static int max34440_read_word_data(struct i2c_client *client, int page, int reg)
 					   MAX34440_MFR_VOUT_PEAK);
 		break;
 	case PMBUS_VIRT_READ_IOUT_AVG:
-		if (data->id != max34446)
+		if (data->id != max34446 && data->id != max34451)
 			return -ENXIO;
 		ret = pmbus_read_word_data(client, page,
 					   MAX34446_MFR_IOUT_AVG);
@@ -143,7 +146,7 @@ static int max34440_write_word_data(struct i2c_client *client, int page,
 	case PMBUS_VIRT_RESET_IOUT_HISTORY:
 		ret = pmbus_write_word_data(client, page,
 					    MAX34440_MFR_IOUT_PEAK, 0);
-		if (!ret && data->id == max34446)
+		if (!ret && (data->id == max34446 || data->id == max34451))
 			ret = pmbus_write_word_data(client, page,
 					MAX34446_MFR_IOUT_AVG, 0);
 
@@ -202,6 +205,58 @@ static int max34440_read_byte_data(struct i2c_client *client, int page, int reg)
 	return ret;
 }
 
+static int max34451_set_supported_funcs(struct i2c_client *client,
+					 struct max34440_data *data)
+{
+	/*
+	 * Each of the channel 0-15 can be configured to monitor the following
+	 * functions based on MFR_CHANNEL_CONFIG[5:0]
+	 * 0x10: Sequencing + voltage monitoring (only valid for PAGES 0–11)
+	 * 0x20: Voltage monitoring (no sequencing)
+	 * 0x21: Voltage read only
+	 * 0x22: Current monitoring
+	 * 0x23: Current read only
+	 * 0x30: General-purpose input active low
+	 * 0x34: General-purpose input active high
+	 * 0x00:  Disabled
+	 */
+
+	int page, rv;
+
+	for (page = 0; page < 16; page++) {
+		rv = i2c_smbus_write_byte_data(client, PMBUS_PAGE, page);
+		if (rv < 0)
+			return rv;
+
+		rv = i2c_smbus_read_word_data(client,
+					      MAX34451_MFR_CHANNEL_CONFIG);
+		if (rv < 0)
+			return rv;
+
+		switch (rv & MAX34451_MFR_CHANNEL_CONFIG_SEL_MASK) {
+		case 0x10:
+		case 0x20:
+			data->info.func[page] = PMBUS_HAVE_VOUT |
+				PMBUS_HAVE_STATUS_VOUT;
+			break;
+		case 0x21:
+			data->info.func[page] = PMBUS_HAVE_VOUT;
+			break;
+		case 0x22:
+			data->info.func[page] = PMBUS_HAVE_IOUT |
+				PMBUS_HAVE_STATUS_IOUT;
+			break;
+		case 0x23:
+			data->info.func[page] = PMBUS_HAVE_IOUT;
+			break;
+		default:
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct pmbus_driver_info max34440_info[] = {
 	[max34440] = {
 		.pages = 14,
@@ -325,6 +380,30 @@ static struct pmbus_driver_info max34440_info[] = {
 		.read_word_data = max34440_read_word_data,
 		.write_word_data = max34440_write_word_data,
 	},
+	[max34451] = {
+		.pages = 21,
+		.format[PSC_VOLTAGE_OUT] = direct,
+		.format[PSC_TEMPERATURE] = direct,
+		.format[PSC_CURRENT_OUT] = direct,
+		.m[PSC_VOLTAGE_OUT] = 1,
+		.b[PSC_VOLTAGE_OUT] = 0,
+		.R[PSC_VOLTAGE_OUT] = 3,
+		.m[PSC_CURRENT_OUT] = 1,
+		.b[PSC_CURRENT_OUT] = 0,
+		.R[PSC_CURRENT_OUT] = 2,
+		.m[PSC_TEMPERATURE] = 1,
+		.b[PSC_TEMPERATURE] = 0,
+		.R[PSC_TEMPERATURE] = 2,
+		/* func 0-15 is set dynamically before probing */
+		.func[16] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[17] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[18] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[19] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.func[20] = PMBUS_HAVE_TEMP | PMBUS_HAVE_STATUS_TEMP,
+		.read_byte_data = max34440_read_byte_data,
+		.read_word_data = max34440_read_word_data,
+		.write_word_data = max34440_write_word_data,
+	},
 	[max34460] = {
 		.pages = 18,
 		.format[PSC_VOLTAGE_OUT] = direct,
@@ -398,6 +477,7 @@ static int max34440_probe(struct i2c_client *client,
 			  const struct i2c_device_id *id)
 {
 	struct max34440_data *data;
+	int rv;
 
 	data = devm_kzalloc(&client->dev, sizeof(struct max34440_data),
 			    GFP_KERNEL);
@@ -406,6 +486,12 @@ static int max34440_probe(struct i2c_client *client,
 	data->id = id->driver_data;
 	data->info = max34440_info[id->driver_data];
 
+	if (data->id == max34451) {
+		rv = max34451_set_supported_funcs(client, data);
+		if (rv)
+			return rv;
+	}
+
 	return pmbus_do_probe(client, id, &data->info);
 }
 
@@ -413,6 +499,7 @@ static const struct i2c_device_id max34440_id[] = {
 	{"max34440", max34440},
 	{"max34441", max34441},
 	{"max34446", max34446},
+	{"max34451", max34451},
 	{"max34460", max34460},
 	{"max34461", max34461},
 	{}
-- 
cgit v1.2.3


From 68dde6cae6e523dfec8ec097af2c41680fb766c6 Mon Sep 17 00:00:00 2001
From: Tomer Maimon <tmaimon77@gmail.com>
Date: Wed, 4 Jul 2018 02:23:25 +0300
Subject: dt-binding: hwmon: Add NPCM7xx PWM and Fan controller documentation

Added device tree binding documentation for Nuvoton BMC
NPCM7xx Pulse Width Modulation (PWM)  and Fan tach controller.
The Nuvoton BMC NPCM7XX supports 8 PWM controller outputs
and 16 Fan tachometer controller inputs.

Signed-off-by: Tomer Maimon <tmaimon77@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
[groeck: Fixed whitespace errors noticed by git]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 .../devicetree/bindings/hwmon/npcm750-pwm-fan.txt  | 84 ++++++++++++++++++++++
 1 file changed, 84 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt

diff --git a/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt b/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt
new file mode 100644
index 000000000000..28f43e929f6d
--- /dev/null
+++ b/Documentation/devicetree/bindings/hwmon/npcm750-pwm-fan.txt
@@ -0,0 +1,84 @@
+Nuvoton NPCM7xx PWM and Fan Tacho controller device
+
+The Nuvoton BMC NPCM7XX supports 8 Pulse-width modulation (PWM)
+controller outputs and 16 Fan tachometer controller inputs.
+
+Required properties for pwm-fan node
+- #address-cells : should be 1.
+- #size-cells	: should be 0.
+- compatible	: "nuvoton,npcm750-pwm-fan" for Poleg NPCM7XX.
+- reg			: specifies physical base address and size of the registers.
+- reg-names	: must contain:
+					* "pwm" for the PWM registers.
+					* "fan" for the Fan registers.
+- clocks		: phandle of reference clocks.
+- clock-names	: must contain
+					* "pwm" for PWM controller operating clock.
+					* "fan" for Fan controller operating clock.
+- interrupts	: contain the Fan interrupts with flags for falling edge.
+- pinctrl-names	: a pinctrl state named "default" must be defined.
+- pinctrl-0	: phandle referencing pin configuration of the PWM and Fan
+					controller ports.
+
+fan subnode format:
+===================
+Under fan subnode can be upto 8 child nodes, each child node representing a fan.
+Each fan subnode must have one PWM channel and atleast one Fan tach channel.
+
+For PWM channel can be configured cooling-levels to create cooling device.
+Cooling device could be bound to a thermal zone for the thermal control.
+
+Required properties for each child node:
+- reg : specify the PWM output channel.
+	integer value in the range 0 through 7, that represent
+	the PWM channel number that used.
+
+- fan-tach-ch : specify the Fan tach input channel.
+		integer value in the range 0 through 15, that represent
+		the fan tach channel number that used.
+
+		At least one Fan tach input channel is required
+
+Optional property for each child node:
+- cooling-levels: PWM duty cycle values in a range from 0 to 255
+                  which correspond to thermal cooling states.
+
+Examples:
+
+pwm_fan:pwm-fan-controller@103000 {
+	#address-cells = <1>;
+	#size-cells = <0>;
+	compatible = "nuvoton,npcm750-pwm-fan";
+	reg = <0x103000 0x2000>,
+		<0x180000 0x8000>;
+	reg-names = "pwm", "fan";
+	clocks = <&clk NPCM7XX_CLK_APB3>,
+		<&clk NPCM7XX_CLK_APB4>;
+	clock-names = "pwm","fan";
+	interrupts = <GIC_SPI 96 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 98 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 100 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 101 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 102 IRQ_TYPE_LEVEL_HIGH>,
+			<GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>;
+	pinctrl-names = "default";
+	pinctrl-0 = <&pwm0_pins &pwm1_pins &pwm2_pins
+			&fanin0_pins &fanin1_pins &fanin2_pins
+			&fanin3_pins &fanin4_pins>;
+	fan@0 {
+		reg = <0x00>;
+		fan-tach-ch = /bits/ 8 <0x00 0x01>;
+		cooling-levels = <127 255>;
+	};
+	fan@1 {
+		reg = <0x01>;
+		fan-tach-ch = /bits/ 8 <0x02 0x03>;
+	};
+	fan@2 {
+		reg = <0x02>;
+		fan-tach-ch = /bits/ 8 <0x04>;
+	};
+
+};
-- 
cgit v1.2.3


From f1fd4a4db777030a2542701fb0d3a261d4472d6d Mon Sep 17 00:00:00 2001
From: Tomer Maimon <tmaimon77@gmail.com>
Date: Wed, 4 Jul 2018 02:23:26 +0300
Subject: hwmon: Add NPCM7xx PWM and Fan driver

Add Nuvoton BMC NPCM750/730/715/705 Pulse Width Modulation (PWM)
and Fan tacho driver.

The Nuvoton BMC NPCM750/730/715/705 supports 8 PWM controller outputs
and 16 Fan controller inputs.

The driver provides a sysfs entries through which the user can
configure the duty-cycle value from 0(off) and 255(full speed)
and read the fan tacho rpm value.

Signed-off-by: Tomer Maimon <tmaimon77@gmail.com>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 Documentation/hwmon/npcm750-pwm-fan |   22 +
 drivers/hwmon/Kconfig               |   10 +
 drivers/hwmon/Makefile              |    1 +
 drivers/hwmon/npcm750-pwm-fan.c     | 1057 +++++++++++++++++++++++++++++++++++
 4 files changed, 1090 insertions(+)
 create mode 100644 Documentation/hwmon/npcm750-pwm-fan
 create mode 100644 drivers/hwmon/npcm750-pwm-fan.c

diff --git a/Documentation/hwmon/npcm750-pwm-fan b/Documentation/hwmon/npcm750-pwm-fan
new file mode 100644
index 000000000000..6156ef7398e6
--- /dev/null
+++ b/Documentation/hwmon/npcm750-pwm-fan
@@ -0,0 +1,22 @@
+Kernel driver npcm750-pwm-fan
+=============================
+
+Supported chips:
+	NUVOTON NPCM750/730/715/705
+
+Authors:
+	<tomer.maimon@nuvoton.com>
+
+Description:
+------------
+This driver implements support for NUVOTON NPCM7XX PWM and Fan Tacho
+controller. The PWM controller supports up to 8 PWM outputs. The Fan tacho
+controller supports up to 16 tachometer inputs.
+
+The driver provides the following sensor accesses in sysfs:
+
+fanX_input	ro	provide current fan rotation value in RPM as reported
+			by the fan to the device.
+
+pwmX		rw	get or set PWM fan control value. This is an integer
+			value between 0(off) and 255(full speed).
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index fd7fb6c041c2..ccf42663a908 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1268,6 +1268,16 @@ config SENSORS_NCT7904
 	  This driver can also be built as a module.  If so, the module
 	  will be called nct7904.
 
+config SENSORS_NPCM7XX
+	tristate "Nuvoton NPCM750 and compatible PWM and Fan controllers"
+	imply THERMAL
+	help
+	  This driver provides support for Nuvoton NPCM750/730/715/705 PWM
+          and Fan controllers.
+
+          This driver can also be built as a module. If so, the module
+          will be called npcm750-pwm-fan.
+
 config SENSORS_NSA320
 	tristate "ZyXEL NSA320 and compatible fan speed and temperature sensors"
 	depends on GPIOLIB && OF
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index cac3c06d2832..842c92f83ce6 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -135,6 +135,7 @@ obj-$(CONFIG_SENSORS_NCT6683)	+= nct6683.o
 obj-$(CONFIG_SENSORS_NCT6775)	+= nct6775.o
 obj-$(CONFIG_SENSORS_NCT7802)	+= nct7802.o
 obj-$(CONFIG_SENSORS_NCT7904)	+= nct7904.o
+obj-$(CONFIG_SENSORS_NPCM7XX)	+= npcm750-pwm-fan.o
 obj-$(CONFIG_SENSORS_NSA320)	+= nsa320-hwmon.o
 obj-$(CONFIG_SENSORS_NTC_THERMISTOR)	+= ntc_thermistor.o
 obj-$(CONFIG_SENSORS_PC87360)	+= pc87360.o
diff --git a/drivers/hwmon/npcm750-pwm-fan.c b/drivers/hwmon/npcm750-pwm-fan.c
new file mode 100644
index 000000000000..8474d601aa63
--- /dev/null
+++ b/drivers/hwmon/npcm750-pwm-fan.c
@@ -0,0 +1,1057 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2014-2018 Nuvoton Technology corporation.
+
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+#include <linux/sysfs.h>
+#include <linux/thermal.h>
+
+/* NPCM7XX PWM registers */
+#define NPCM7XX_PWM_REG_BASE(base, n)    ((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_PWM_REG_PR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_PWM_REG_CSR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_PWM_REG_CR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_PWM_REG_CNRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x0C + (12 * (ch)))
+#define NPCM7XX_PWM_REG_CMRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x10 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PDRx(base, n, ch) \
+			(NPCM7XX_PWM_REG_BASE(base, n) + 0x14 + (12 * (ch)))
+#define NPCM7XX_PWM_REG_PIER(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x3C)
+#define NPCM7XX_PWM_REG_PIIR(base, n)	(NPCM7XX_PWM_REG_BASE(base, n) + 0x40)
+
+#define NPCM7XX_PWM_CTRL_CH0_MODE_BIT		BIT(3)
+#define NPCM7XX_PWM_CTRL_CH1_MODE_BIT		BIT(11)
+#define NPCM7XX_PWM_CTRL_CH2_MODE_BIT		BIT(15)
+#define NPCM7XX_PWM_CTRL_CH3_MODE_BIT		BIT(19)
+
+#define NPCM7XX_PWM_CTRL_CH0_INV_BIT		BIT(2)
+#define NPCM7XX_PWM_CTRL_CH1_INV_BIT		BIT(10)
+#define NPCM7XX_PWM_CTRL_CH2_INV_BIT		BIT(14)
+#define NPCM7XX_PWM_CTRL_CH3_INV_BIT		BIT(18)
+
+#define NPCM7XX_PWM_CTRL_CH0_EN_BIT		BIT(0)
+#define NPCM7XX_PWM_CTRL_CH1_EN_BIT		BIT(8)
+#define NPCM7XX_PWM_CTRL_CH2_EN_BIT		BIT(12)
+#define NPCM7XX_PWM_CTRL_CH3_EN_BIT		BIT(16)
+
+/* Define the maximum PWM channel number */
+#define NPCM7XX_PWM_MAX_CHN_NUM			8
+#define NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE	4
+#define NPCM7XX_PWM_MAX_MODULES                 2
+
+/* Define the Counter Register, value = 100 for match 100% */
+#define NPCM7XX_PWM_COUNTER_DEFAULT_NUM		255
+#define NPCM7XX_PWM_CMR_DEFAULT_NUM		127
+#define NPCM7XX_PWM_CMR_MAX			255
+
+/* default all PWM channels PRESCALE2 = 1 */
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0	0x4
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1	0x40
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2	0x400
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3	0x4000
+
+#define PWM_OUTPUT_FREQ_25KHZ			25000
+#define PWN_CNT_DEFAULT				256
+#define MIN_PRESCALE1				2
+#define NPCM7XX_PWM_PRESCALE_SHIFT_CH01		8
+
+#define NPCM7XX_PWM_PRESCALE2_DEFAULT	(NPCM7XX_PWM_PRESCALE2_DEFAULT_CH0 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH1 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH2 | \
+					NPCM7XX_PWM_PRESCALE2_DEFAULT_CH3)
+
+#define NPCM7XX_PWM_CTRL_MODE_DEFAULT	(NPCM7XX_PWM_CTRL_CH0_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH1_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH2_MODE_BIT | \
+					NPCM7XX_PWM_CTRL_CH3_MODE_BIT)
+
+/* NPCM7XX FAN Tacho registers */
+#define NPCM7XX_FAN_REG_BASE(base, n)	((base) + ((n) * 0x1000L))
+
+#define NPCM7XX_FAN_REG_TCNT1(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x00)
+#define NPCM7XX_FAN_REG_TCRA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x02)
+#define NPCM7XX_FAN_REG_TCRB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x04)
+#define NPCM7XX_FAN_REG_TCNT2(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x06)
+#define NPCM7XX_FAN_REG_TPRSC(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x08)
+#define NPCM7XX_FAN_REG_TCKC(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x0A)
+#define NPCM7XX_FAN_REG_TMCTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0C)
+#define NPCM7XX_FAN_REG_TICTRL(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x0E)
+#define NPCM7XX_FAN_REG_TICLR(base, n)    (NPCM7XX_FAN_REG_BASE(base, n) + 0x10)
+#define NPCM7XX_FAN_REG_TIEN(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x12)
+#define NPCM7XX_FAN_REG_TCPA(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x14)
+#define NPCM7XX_FAN_REG_TCPB(base, n)     (NPCM7XX_FAN_REG_BASE(base, n) + 0x16)
+#define NPCM7XX_FAN_REG_TCPCFG(base, n)   (NPCM7XX_FAN_REG_BASE(base, n) + 0x18)
+#define NPCM7XX_FAN_REG_TINASEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1A)
+#define NPCM7XX_FAN_REG_TINBSEL(base, n)  (NPCM7XX_FAN_REG_BASE(base, n) + 0x1C)
+
+#define NPCM7XX_FAN_TCKC_CLKX_NONE	0
+#define NPCM7XX_FAN_TCKC_CLK1_APB	BIT(0)
+#define NPCM7XX_FAN_TCKC_CLK2_APB	BIT(3)
+
+#define NPCM7XX_FAN_TMCTRL_TBEN		BIT(6)
+#define NPCM7XX_FAN_TMCTRL_TAEN		BIT(5)
+#define NPCM7XX_FAN_TMCTRL_TBEDG	BIT(4)
+#define NPCM7XX_FAN_TMCTRL_TAEDG	BIT(3)
+#define NPCM7XX_FAN_TMCTRL_MODE_5	BIT(2)
+
+#define NPCM7XX_FAN_TICLR_CLEAR_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TICLR_TFCLR		BIT(5)
+#define NPCM7XX_FAN_TICLR_TECLR		BIT(4)
+#define NPCM7XX_FAN_TICLR_TDCLR		BIT(3)
+#define NPCM7XX_FAN_TICLR_TCCLR		BIT(2)
+#define NPCM7XX_FAN_TICLR_TBCLR		BIT(1)
+#define NPCM7XX_FAN_TICLR_TACLR		BIT(0)
+
+#define NPCM7XX_FAN_TIEN_ENABLE_ALL	GENMASK(5, 0)
+#define NPCM7XX_FAN_TIEN_TFIEN		BIT(5)
+#define NPCM7XX_FAN_TIEN_TEIEN		BIT(4)
+#define NPCM7XX_FAN_TIEN_TDIEN		BIT(3)
+#define NPCM7XX_FAN_TIEN_TCIEN		BIT(2)
+#define NPCM7XX_FAN_TIEN_TBIEN		BIT(1)
+#define NPCM7XX_FAN_TIEN_TAIEN		BIT(0)
+
+#define NPCM7XX_FAN_TICTRL_TFPND	BIT(5)
+#define NPCM7XX_FAN_TICTRL_TEPND	BIT(4)
+#define NPCM7XX_FAN_TICTRL_TDPND	BIT(3)
+#define NPCM7XX_FAN_TICTRL_TCPND	BIT(2)
+#define NPCM7XX_FAN_TICTRL_TBPND	BIT(1)
+#define NPCM7XX_FAN_TICTRL_TAPND	BIT(0)
+
+#define NPCM7XX_FAN_TCPCFG_HIBEN	BIT(7)
+#define NPCM7XX_FAN_TCPCFG_EQBEN	BIT(6)
+#define NPCM7XX_FAN_TCPCFG_LOBEN	BIT(5)
+#define NPCM7XX_FAN_TCPCFG_CPBSEL	BIT(4)
+#define NPCM7XX_FAN_TCPCFG_HIAEN	BIT(3)
+#define NPCM7XX_FAN_TCPCFG_EQAEN	BIT(2)
+#define NPCM7XX_FAN_TCPCFG_LOAEN	BIT(1)
+#define NPCM7XX_FAN_TCPCFG_CPASEL	BIT(0)
+
+/* FAN General Definition */
+/* Define the maximum FAN channel number */
+#define NPCM7XX_FAN_MAX_MODULE			8
+#define NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE	2
+#define NPCM7XX_FAN_MAX_CHN_NUM			16
+
+/*
+ * Get Fan Tach Timeout (base on clock 214843.75Hz, 1 cnt = 4.654us)
+ * Timeout 94ms ~= 0x5000
+ * (The minimum FAN speed could to support ~640RPM/pulse 1,
+ * 320RPM/pulse 2, ...-- 10.6Hz)
+ */
+#define NPCM7XX_FAN_TIMEOUT	0x5000
+#define NPCM7XX_FAN_TCNT	0xFFFF
+#define NPCM7XX_FAN_TCPA	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+#define NPCM7XX_FAN_TCPB	(NPCM7XX_FAN_TCNT - NPCM7XX_FAN_TIMEOUT)
+
+#define NPCM7XX_FAN_POLL_TIMER_200MS			200
+#define NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION	2
+#define NPCM7XX_FAN_TINASEL_FANIN_DEFAULT		0
+#define NPCM7XX_FAN_CLK_PRESCALE			255
+
+#define NPCM7XX_FAN_CMPA				0
+#define NPCM7XX_FAN_CMPB				1
+
+/* Obtain the fan number */
+#define NPCM7XX_FAN_INPUT(fan, cmp)		(((fan) << 1) + (cmp))
+
+/* fan sample status */
+#define FAN_DISABLE				0xFF
+#define FAN_INIT				0x00
+#define FAN_PREPARE_TO_GET_FIRST_CAPTURE	0x01
+#define FAN_ENOUGH_SAMPLE			0x02
+
+struct npcm7xx_fan_dev {
+	u8 fan_st_flg;
+	u8 fan_pls_per_rev;
+	u16 fan_cnt;
+	u32 fan_cnt_tmp;
+};
+
+struct npcm7xx_cooling_device {
+	char name[THERMAL_NAME_LENGTH];
+	struct npcm7xx_pwm_fan_data *data;
+	struct thermal_cooling_device *tcdev;
+	int pwm_port;
+	u8 *cooling_levels;
+	u8 max_state;
+	u8 cur_state;
+};
+
+struct npcm7xx_pwm_fan_data {
+	void __iomem *pwm_base;
+	void __iomem *fan_base;
+	unsigned long pwm_clk_freq;
+	unsigned long fan_clk_freq;
+	struct clk *pwm_clk;
+	struct clk *fan_clk;
+	struct mutex pwm_lock[NPCM7XX_PWM_MAX_MODULES];
+	spinlock_t fan_lock[NPCM7XX_FAN_MAX_MODULE];
+	int fan_irq[NPCM7XX_FAN_MAX_MODULE];
+	bool pwm_present[NPCM7XX_PWM_MAX_CHN_NUM];
+	bool fan_present[NPCM7XX_FAN_MAX_CHN_NUM];
+	u32 input_clk_freq;
+	struct timer_list fan_timer;
+	struct npcm7xx_fan_dev fan_dev[NPCM7XX_FAN_MAX_CHN_NUM];
+	struct npcm7xx_cooling_device *cdev[NPCM7XX_PWM_MAX_CHN_NUM];
+	u8 fan_select;
+};
+
+static int npcm7xx_pwm_config_set(struct npcm7xx_pwm_fan_data *data,
+				  int channel, u16 val)
+{
+	u32 pwm_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 tmp_buf, ctrl_en_bit, env_bit;
+
+	/*
+	 * Config PWM Comparator register for setting duty cycle
+	 */
+	mutex_lock(&data->pwm_lock[module]);
+
+	/* write new CMR value  */
+	iowrite32(val, NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pwm_ch));
+	tmp_buf = ioread32(NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+
+	switch (pwm_ch) {
+	case 0:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH0_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH0_INV_BIT;
+		break;
+	case 1:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH1_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH1_INV_BIT;
+		break;
+	case 2:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH2_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH2_INV_BIT;
+		break;
+	case 3:
+		ctrl_en_bit = NPCM7XX_PWM_CTRL_CH3_EN_BIT;
+		env_bit = NPCM7XX_PWM_CTRL_CH3_INV_BIT;
+		break;
+	default:
+		mutex_unlock(&data->pwm_lock[module]);
+		return -ENODEV;
+	}
+
+	if (val == 0) {
+		/* Disable PWM */
+		tmp_buf &= ~ctrl_en_bit;
+		tmp_buf |= env_bit;
+	} else {
+		/* Enable PWM */
+		tmp_buf |= ctrl_en_bit;
+		tmp_buf &= ~env_bit;
+	}
+
+	iowrite32(tmp_buf, NPCM7XX_PWM_REG_CR(data->pwm_base, module));
+	mutex_unlock(&data->pwm_lock[module]);
+
+	return 0;
+}
+
+static inline void npcm7xx_fan_start_capture(struct npcm7xx_pwm_fan_data *data,
+					     u8 fan, u8 cmp)
+{
+	u8 fan_id;
+	u8 reg_mode;
+	u8 reg_int;
+	unsigned long flags;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	/* to check whether any fan tach is enable */
+	if (data->fan_dev[fan_id].fan_st_flg != FAN_DISABLE) {
+		/* reset status */
+		spin_lock_irqsave(&data->fan_lock[fan], flags);
+
+		data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		reg_int = ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/*
+		 * the interrupt enable bits do not need to be cleared before
+		 * it sets, the interrupt enable bits are cleared only on reset.
+		 * the clock unit control register is behaving in the same
+		 * manner that the interrupt enable register behave.
+		 */
+		if (cmp == NPCM7XX_FAN_CMPA) {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TAIEN |
+					    NPCM7XX_FAN_TIEN_TEIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode = NPCM7XX_FAN_TCKC_CLK1_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode, NPCM7XX_FAN_REG_TCKC(data->fan_base,
+								fan));
+		} else {
+			/* enable interrupt */
+			iowrite8(reg_int | (NPCM7XX_FAN_TIEN_TBIEN |
+					    NPCM7XX_FAN_TIEN_TFIEN),
+				 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+			reg_mode =
+				NPCM7XX_FAN_TCKC_CLK2_APB
+				| ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base,
+							       fan));
+
+			/* start to Capture */
+			iowrite8(reg_mode,
+				 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+		}
+
+		spin_unlock_irqrestore(&data->fan_lock[fan], flags);
+	}
+}
+
+/*
+ * Enable a background timer to poll fan tach value, (200ms * 4)
+ * to polling all fan
+ */
+static void npcm7xx_fan_polling(struct timer_list *t)
+{
+	struct npcm7xx_pwm_fan_data *data;
+	int i;
+
+	data = from_timer(data, t, fan_timer);
+
+	/*
+	 * Polling two module per one round,
+	 * FAN01 & FAN89 / FAN23 & FAN1011 / FAN45 & FAN1213 / FAN67 & FAN1415
+	 */
+	for (i = data->fan_select; i < NPCM7XX_FAN_MAX_MODULE;
+	      i = i + 4) {
+		/* clear the flag and reset the counter (TCNT) */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, i));
+
+		if (data->fan_present[i * 2]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT1(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPA);
+		}
+		if (data->fan_present[(i * 2) + 1]) {
+			iowrite16(NPCM7XX_FAN_TCNT,
+				  NPCM7XX_FAN_REG_TCNT2(data->fan_base, i));
+			npcm7xx_fan_start_capture(data, i, NPCM7XX_FAN_CMPB);
+		}
+	}
+
+	data->fan_select++;
+	data->fan_select &= 0x3;
+
+	/* reset the timer interval */
+	data->fan_timer.expires = jiffies +
+		msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+	add_timer(&data->fan_timer);
+}
+
+static inline void npcm7xx_fan_compute(struct npcm7xx_pwm_fan_data *data,
+				       u8 fan, u8 cmp, u8 fan_id, u8 flag_int,
+				       u8 flag_mode, u8 flag_clear)
+{
+	u8  reg_int;
+	u8  reg_mode;
+	u16 fan_cap;
+
+	if (cmp == NPCM7XX_FAN_CMPA)
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRA(data->fan_base, fan));
+	else
+		fan_cap = ioread16(NPCM7XX_FAN_REG_TCRB(data->fan_base, fan));
+
+	/* clear capature flag, H/W will auto reset the NPCM7XX_FAN_TCNTx */
+	iowrite8(flag_clear, NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+	if (data->fan_dev[fan_id].fan_st_flg == FAN_INIT) {
+		/* First capture, drop it */
+		data->fan_dev[fan_id].fan_st_flg =
+			FAN_PREPARE_TO_GET_FIRST_CAPTURE;
+
+		/* reset counter */
+		data->fan_dev[fan_id].fan_cnt_tmp = 0;
+	} else if (data->fan_dev[fan_id].fan_st_flg < FAN_ENOUGH_SAMPLE) {
+		/*
+		 * collect the enough sample,
+		 * (ex: 2 pulse fan need to get 2 sample)
+		 */
+		data->fan_dev[fan_id].fan_cnt_tmp +=
+			(NPCM7XX_FAN_TCNT - fan_cap);
+
+		data->fan_dev[fan_id].fan_st_flg++;
+	} else {
+		/* get enough sample or fan disable */
+		if (data->fan_dev[fan_id].fan_st_flg == FAN_ENOUGH_SAMPLE) {
+			data->fan_dev[fan_id].fan_cnt_tmp +=
+				(NPCM7XX_FAN_TCNT - fan_cap);
+
+			/* compute finial average cnt per pulse */
+			data->fan_dev[fan_id].fan_cnt =
+				data->fan_dev[fan_id].fan_cnt_tmp /
+				FAN_ENOUGH_SAMPLE;
+
+			data->fan_dev[fan_id].fan_st_flg = FAN_INIT;
+		}
+
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+	}
+}
+
+static inline void npcm7xx_check_cmp(struct npcm7xx_pwm_fan_data *data,
+				     u8 fan, u8 cmp, u8 flag)
+{
+	u8 reg_int;
+	u8 reg_mode;
+	u8 flag_timeout;
+	u8 flag_cap;
+	u8 flag_clear;
+	u8 flag_int;
+	u8 flag_mode;
+	u8 fan_id;
+
+	fan_id = NPCM7XX_FAN_INPUT(fan, cmp);
+
+	if (cmp == NPCM7XX_FAN_CMPA) {
+		flag_cap = NPCM7XX_FAN_TICTRL_TAPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TEPND;
+		flag_int = NPCM7XX_FAN_TIEN_TAIEN | NPCM7XX_FAN_TIEN_TEIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK1_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TACLR | NPCM7XX_FAN_TICLR_TECLR;
+	} else {
+		flag_cap = NPCM7XX_FAN_TICTRL_TBPND;
+		flag_timeout = NPCM7XX_FAN_TICTRL_TFPND;
+		flag_int = NPCM7XX_FAN_TIEN_TBIEN | NPCM7XX_FAN_TIEN_TFIEN;
+		flag_mode = NPCM7XX_FAN_TCKC_CLK2_APB;
+		flag_clear = NPCM7XX_FAN_TICLR_TBCLR | NPCM7XX_FAN_TICLR_TFCLR;
+	}
+
+	if (flag & flag_timeout) {
+		reg_int =  ioread8(NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* disable interrupt */
+		iowrite8((reg_int & ~flag_int),
+			 NPCM7XX_FAN_REG_TIEN(data->fan_base, fan));
+
+		/* clear interrupt flag */
+		iowrite8(flag_clear,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, fan));
+
+		reg_mode =  ioread8(NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/* stop capturing */
+		iowrite8((reg_mode & ~flag_mode),
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, fan));
+
+		/*
+		 *  If timeout occurs (NPCM7XX_FAN_TIMEOUT), the fan doesn't
+		 *  connect or speed is lower than 10.6Hz (320RPM/pulse2).
+		 *  In these situation, the RPM output should be zero.
+		 */
+		data->fan_dev[fan_id].fan_cnt = 0;
+	} else {
+	    /* input capture is occurred */
+		if (flag & flag_cap)
+			npcm7xx_fan_compute(data, fan, cmp, fan_id, flag_int,
+					    flag_mode, flag_clear);
+	}
+}
+
+static irqreturn_t npcm7xx_fan_isr(int irq, void *dev_id)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_id;
+	unsigned long flags;
+	int module;
+	u8 flag;
+
+	module = irq - data->fan_irq[0];
+	spin_lock_irqsave(&data->fan_lock[module], flags);
+
+	flag = ioread8(NPCM7XX_FAN_REG_TICTRL(data->fan_base, module));
+	if (flag > 0) {
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPA, flag);
+		npcm7xx_check_cmp(data, module, NPCM7XX_FAN_CMPB, flag);
+		spin_unlock_irqrestore(&data->fan_lock[module], flags);
+		return IRQ_HANDLED;
+	}
+
+	spin_unlock_irqrestore(&data->fan_lock[module], flags);
+
+	return IRQ_NONE;
+}
+
+static int npcm7xx_read_pwm(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	u32 pmw_ch = (channel % NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+	u32 module = (channel / NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE);
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		*val = ioread32
+			(NPCM7XX_PWM_REG_CMRx(data->pwm_base, module, pmw_ch));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write_pwm(struct device *dev, u32 attr, int channel,
+			     long val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+	int err;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		if (val < 0 || val > NPCM7XX_PWM_CMR_MAX)
+			return -EINVAL;
+		err = npcm7xx_pwm_config_set(data, channel, (u16)val);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+static umode_t npcm7xx_pwm_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->pwm_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_pwm_input:
+		return 0644;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read_fan(struct device *dev, u32 attr, int channel,
+			    long *val)
+{
+	struct npcm7xx_pwm_fan_data *data = dev_get_drvdata(dev);
+
+	switch (attr) {
+	case hwmon_fan_input:
+		*val = 0;
+		if (data->fan_dev[channel].fan_cnt <= 0)
+			return data->fan_dev[channel].fan_cnt;
+
+		/* Convert the raw reading to RPM */
+		if (data->fan_dev[channel].fan_cnt > 0 &&
+		    data->fan_dev[channel].fan_pls_per_rev > 0)
+			*val = ((data->input_clk_freq * 60) /
+				(data->fan_dev[channel].fan_cnt *
+				 data->fan_dev[channel].fan_pls_per_rev));
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_fan_is_visible(const void *_data, u32 attr, int channel)
+{
+	const struct npcm7xx_pwm_fan_data *data = _data;
+
+	if (!data->fan_present[channel])
+		return 0;
+
+	switch (attr) {
+	case hwmon_fan_input:
+		return 0444;
+	default:
+		return 0;
+	}
+}
+
+static int npcm7xx_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_read_pwm(dev, attr, channel, val);
+	case hwmon_fan:
+		return npcm7xx_read_fan(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int npcm7xx_write(struct device *dev, enum hwmon_sensor_types type,
+			 u32 attr, int channel, long val)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_write_pwm(dev, attr, channel, val);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static umode_t npcm7xx_is_visible(const void *data,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	switch (type) {
+	case hwmon_pwm:
+		return npcm7xx_pwm_is_visible(data, attr, channel);
+	case hwmon_fan:
+		return npcm7xx_fan_is_visible(data, attr, channel);
+	default:
+		return 0;
+	}
+}
+
+static const u32 npcm7xx_pwm_config[] = {
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	HWMON_PWM_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_pwm = {
+	.type = hwmon_pwm,
+	.config = npcm7xx_pwm_config,
+};
+
+static const u32 npcm7xx_fan_config[] = {
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	HWMON_F_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info npcm7xx_fan = {
+	.type = hwmon_fan,
+	.config = npcm7xx_fan_config,
+};
+
+static const struct hwmon_channel_info *npcm7xx_info[] = {
+	&npcm7xx_pwm,
+	&npcm7xx_fan,
+	NULL
+};
+
+static const struct hwmon_ops npcm7xx_hwmon_ops = {
+	.is_visible = npcm7xx_is_visible,
+	.read = npcm7xx_read,
+	.write = npcm7xx_write,
+};
+
+static const struct hwmon_chip_info npcm7xx_chip_info = {
+	.ops = &npcm7xx_hwmon_ops,
+	.info = npcm7xx_info,
+};
+
+static u32 npcm7xx_pwm_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int m, ch;
+	u32 prescale_val, output_freq;
+
+	data->pwm_clk_freq = clk_get_rate(data->pwm_clk);
+
+	/* Adjust NPCM7xx PWMs output frequency to ~25Khz */
+	output_freq = data->pwm_clk_freq / PWN_CNT_DEFAULT;
+	prescale_val = DIV_ROUND_CLOSEST(output_freq, PWM_OUTPUT_FREQ_25KHZ);
+
+	/* If prescale_val = 0, then the prescale output clock is stopped */
+	if (prescale_val < MIN_PRESCALE1)
+		prescale_val = MIN_PRESCALE1;
+	/*
+	 * prescale_val need to decrement in one because in the PWM Prescale
+	 * register the Prescale value increment by one
+	 */
+	prescale_val--;
+
+	/* Setting PWM Prescale Register value register to both modules */
+	prescale_val |= (prescale_val << NPCM7XX_PWM_PRESCALE_SHIFT_CH01);
+
+	for (m = 0; m < NPCM7XX_PWM_MAX_MODULES  ; m++) {
+		iowrite32(prescale_val, NPCM7XX_PWM_REG_PR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_PRESCALE2_DEFAULT,
+			  NPCM7XX_PWM_REG_CSR(data->pwm_base, m));
+		iowrite32(NPCM7XX_PWM_CTRL_MODE_DEFAULT,
+			  NPCM7XX_PWM_REG_CR(data->pwm_base, m));
+
+		for (ch = 0; ch < NPCM7XX_PWM_MAX_CHN_NUM_IN_A_MODULE; ch++) {
+			iowrite32(NPCM7XX_PWM_COUNTER_DEFAULT_NUM,
+				  NPCM7XX_PWM_REG_CNRx(data->pwm_base, m, ch));
+		}
+	}
+
+	return output_freq / ((prescale_val & 0xf) + 1);
+}
+
+static void npcm7xx_fan_init(struct npcm7xx_pwm_fan_data *data)
+{
+	int md;
+	int ch;
+	int i;
+	u32 apb_clk_freq;
+
+	for (md = 0; md < NPCM7XX_FAN_MAX_MODULE; md++) {
+		/* stop FAN0~7 clock */
+		iowrite8(NPCM7XX_FAN_TCKC_CLKX_NONE,
+			 NPCM7XX_FAN_REG_TCKC(data->fan_base, md));
+
+		/* disable all interrupt */
+		iowrite8(0x00, NPCM7XX_FAN_REG_TIEN(data->fan_base, md));
+
+		/* clear all interrupt */
+		iowrite8(NPCM7XX_FAN_TICLR_CLEAR_ALL,
+			 NPCM7XX_FAN_REG_TICLR(data->fan_base, md));
+
+		/* set FAN0~7 clock prescaler */
+		iowrite8(NPCM7XX_FAN_CLK_PRESCALE,
+			 NPCM7XX_FAN_REG_TPRSC(data->fan_base, md));
+
+		/* set FAN0~7 mode (high-to-low transition) */
+		iowrite8((NPCM7XX_FAN_TMCTRL_MODE_5 | NPCM7XX_FAN_TMCTRL_TBEN |
+			  NPCM7XX_FAN_TMCTRL_TAEN),
+			 NPCM7XX_FAN_REG_TMCTRL(data->fan_base, md));
+
+		/* set FAN0~7 Initial Count/Cap */
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT1(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCNT,
+			  NPCM7XX_FAN_REG_TCNT2(data->fan_base, md));
+
+		/* set FAN0~7 compare (equal to count) */
+		iowrite8((NPCM7XX_FAN_TCPCFG_EQAEN | NPCM7XX_FAN_TCPCFG_EQBEN),
+			 NPCM7XX_FAN_REG_TCPCFG(data->fan_base, md));
+
+		/* set FAN0~7 compare value */
+		iowrite16(NPCM7XX_FAN_TCPA,
+			  NPCM7XX_FAN_REG_TCPA(data->fan_base, md));
+		iowrite16(NPCM7XX_FAN_TCPB,
+			  NPCM7XX_FAN_REG_TCPB(data->fan_base, md));
+
+		/* set FAN0~7 fan input FANIN 0~15 */
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINASEL(data->fan_base, md));
+		iowrite8(NPCM7XX_FAN_TINASEL_FANIN_DEFAULT,
+			 NPCM7XX_FAN_REG_TINBSEL(data->fan_base, md));
+
+		for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE; i++) {
+			ch = md * NPCM7XX_FAN_MAX_CHN_NUM_IN_A_MODULE + i;
+			data->fan_dev[ch].fan_st_flg = FAN_DISABLE;
+			data->fan_dev[ch].fan_pls_per_rev =
+				NPCM7XX_FAN_DEFAULT_PULSE_PER_REVOLUTION;
+			data->fan_dev[ch].fan_cnt = 0;
+		}
+	}
+
+	apb_clk_freq = clk_get_rate(data->fan_clk);
+
+	/* Fan tach input clock = APB clock / prescalar, default is 255. */
+	data->input_clk_freq = apb_clk_freq / (NPCM7XX_FAN_CLK_PRESCALE + 1);
+}
+
+static int
+npcm7xx_pwm_cz_get_max_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->max_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_get_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long *state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+
+	*state = cdev->cur_state;
+
+	return 0;
+}
+
+static int
+npcm7xx_pwm_cz_set_cur_state(struct thermal_cooling_device *tcdev,
+			     unsigned long state)
+{
+	struct npcm7xx_cooling_device *cdev = tcdev->devdata;
+	int ret;
+
+	if (state > cdev->max_state)
+		return -EINVAL;
+
+	cdev->cur_state = state;
+	ret = npcm7xx_pwm_config_set(cdev->data, cdev->pwm_port,
+				     cdev->cooling_levels[cdev->cur_state]);
+
+	return ret;
+}
+
+static const struct thermal_cooling_device_ops npcm7xx_pwm_cool_ops = {
+	.get_max_state = npcm7xx_pwm_cz_get_max_state,
+	.get_cur_state = npcm7xx_pwm_cz_get_cur_state,
+	.set_cur_state = npcm7xx_pwm_cz_set_cur_state,
+};
+
+static int npcm7xx_create_pwm_cooling(struct device *dev,
+				      struct device_node *child,
+				      struct npcm7xx_pwm_fan_data *data,
+				      u32 pwm_port, u8 num_levels)
+{
+	int ret;
+	struct npcm7xx_cooling_device *cdev;
+
+	cdev = devm_kzalloc(dev, sizeof(*cdev), GFP_KERNEL);
+	if (!cdev)
+		return -ENOMEM;
+
+	cdev->cooling_levels = devm_kzalloc(dev, num_levels, GFP_KERNEL);
+	if (!cdev->cooling_levels)
+		return -ENOMEM;
+
+	cdev->max_state = num_levels - 1;
+	ret = of_property_read_u8_array(child, "cooling-levels",
+					cdev->cooling_levels,
+					num_levels);
+	if (ret) {
+		dev_err(dev, "Property 'cooling-levels' cannot be read.\n");
+		return ret;
+	}
+	snprintf(cdev->name, THERMAL_NAME_LENGTH, "%s%d", child->name,
+		 pwm_port);
+
+	cdev->tcdev = thermal_of_cooling_device_register(child,
+							 cdev->name,
+							 cdev,
+							 &npcm7xx_pwm_cool_ops);
+	if (IS_ERR(cdev->tcdev))
+		return PTR_ERR(cdev->tcdev);
+
+	cdev->data = data;
+	cdev->pwm_port = pwm_port;
+
+	data->cdev[pwm_port] = cdev;
+
+	return 0;
+}
+
+static int npcm7xx_en_pwm_fan(struct device *dev,
+			      struct device_node *child,
+			      struct npcm7xx_pwm_fan_data *data)
+{
+	u8 *fan_ch;
+	u32 pwm_port;
+	int ret, fan_cnt;
+	u8 index, ch;
+
+	ret = of_property_read_u32(child, "reg", &pwm_port);
+	if (ret)
+		return ret;
+
+	data->pwm_present[pwm_port] = true;
+	ret = npcm7xx_pwm_config_set(data, pwm_port,
+				     NPCM7XX_PWM_CMR_DEFAULT_NUM);
+
+	ret = of_property_count_u8_elems(child, "cooling-levels");
+	if (ret > 0) {
+		ret = npcm7xx_create_pwm_cooling(dev, child, data, pwm_port,
+						 ret);
+		if (ret)
+			return ret;
+	}
+
+	fan_cnt = of_property_count_u8_elems(child, "fan-tach-ch");
+	if (fan_cnt < 1)
+		return -EINVAL;
+
+	fan_ch = devm_kzalloc(dev, sizeof(*fan_ch) * fan_cnt, GFP_KERNEL);
+	if (!fan_ch)
+		return -ENOMEM;
+
+	ret = of_property_read_u8_array(child, "fan-tach-ch", fan_ch, fan_cnt);
+	if (ret)
+		return ret;
+
+	for (ch = 0; ch < fan_cnt; ch++) {
+		index = fan_ch[ch];
+		data->fan_present[index] = true;
+		data->fan_dev[index].fan_st_flg = FAN_INIT;
+	}
+
+	return 0;
+}
+
+static int npcm7xx_pwm_fan_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np, *child;
+	struct npcm7xx_pwm_fan_data *data;
+	struct resource *res;
+	struct device *hwmon;
+	char name[20];
+	int ret, cnt;
+	u32 output_freq;
+	u32 i;
+
+	np = dev->of_node;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pwm");
+	if (!res) {
+		dev_err(dev, "pwm resource not found\n");
+		return -ENODEV;
+	}
+
+	data->pwm_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "pwm base resource is %pR\n", res);
+	if (IS_ERR(data->pwm_base))
+		return PTR_ERR(data->pwm_base);
+
+	data->pwm_clk = devm_clk_get(dev, "pwm");
+	if (IS_ERR(data->pwm_clk)) {
+		dev_err(dev, "couldn't get pwm clock\n");
+		return PTR_ERR(data->pwm_clk);
+	}
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "fan");
+	if (!res) {
+		dev_err(dev, "fan resource not found\n");
+		return -ENODEV;
+	}
+
+	data->fan_base = devm_ioremap_resource(dev, res);
+	dev_dbg(dev, "fan base resource is %pR\n", res);
+	if (IS_ERR(data->fan_base))
+		return PTR_ERR(data->fan_base);
+
+	data->fan_clk = devm_clk_get(dev, "fan");
+	if (IS_ERR(data->fan_clk)) {
+		dev_err(dev, "couldn't get fan clock\n");
+		return PTR_ERR(data->fan_clk);
+	}
+
+	output_freq = npcm7xx_pwm_init(data);
+	npcm7xx_fan_init(data);
+
+	for (cnt = 0; cnt < NPCM7XX_PWM_MAX_MODULES  ; cnt++)
+		mutex_init(&data->pwm_lock[cnt]);
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_MODULE; i++) {
+		spin_lock_init(&data->fan_lock[i]);
+
+		data->fan_irq[i] = platform_get_irq(pdev, i);
+		if (data->fan_irq[i] < 0) {
+			dev_err(dev, "get IRQ fan%d failed\n", i);
+			return data->fan_irq[i];
+		}
+
+		sprintf(name, "NPCM7XX-FAN-MD%d", i);
+		ret = devm_request_irq(dev, data->fan_irq[i], npcm7xx_fan_isr,
+				       0, name, (void *)data);
+		if (ret) {
+			dev_err(dev, "register IRQ fan%d failed\n", i);
+			return ret;
+		}
+	}
+
+	for_each_child_of_node(np, child) {
+		ret = npcm7xx_en_pwm_fan(dev, child, data);
+		if (ret) {
+			dev_err(dev, "enable pwm and fan failed\n");
+			of_node_put(child);
+			return ret;
+		}
+	}
+
+	hwmon = devm_hwmon_device_register_with_info(dev, "npcm7xx_pwm_fan",
+						     data, &npcm7xx_chip_info,
+						     NULL);
+	if (IS_ERR(hwmon)) {
+		dev_err(dev, "unable to register hwmon device\n");
+		return PTR_ERR(hwmon);
+	}
+
+	for (i = 0; i < NPCM7XX_FAN_MAX_CHN_NUM; i++) {
+		if (data->fan_present[i]) {
+			/* fan timer initialization */
+			data->fan_timer.expires = jiffies +
+				msecs_to_jiffies(NPCM7XX_FAN_POLL_TIMER_200MS);
+			timer_setup(&data->fan_timer,
+				    npcm7xx_fan_polling, 0);
+			add_timer(&data->fan_timer);
+			break;
+		}
+	}
+
+	pr_info("NPCM7XX PWM-FAN Driver probed, output Freq %dHz[PWM], input Freq %dHz[FAN]\n",
+		output_freq, data->input_clk_freq);
+
+	return 0;
+}
+
+static const struct of_device_id of_pwm_fan_match_table[] = {
+	{ .compatible = "nuvoton,npcm750-pwm-fan", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match_table);
+
+static struct platform_driver npcm7xx_pwm_fan_driver = {
+	.probe		= npcm7xx_pwm_fan_probe,
+	.driver		= {
+		.name	= "npcm7xx_pwm_fan",
+		.of_match_table = of_pwm_fan_match_table,
+	},
+};
+
+module_platform_driver(npcm7xx_pwm_fan_driver);
+
+MODULE_DESCRIPTION("Nuvoton NPCM7XX PWM and Fan Tacho driver");
+MODULE_AUTHOR("Tomer Maimon <tomer.maimon@nuvoton.com>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 215af5499d9e2b55f111d2431ea20218115f29b3 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sat, 7 Jul 2018 11:40:18 +0200
Subject: cpu/hotplug: Online siblings when SMT control is turned on

Writing 'off' to /sys/devices/system/cpu/smt/control offlines all SMT
siblings. Writing 'on' merily enables the abilify to online them, but does
not online them automatically.

Make 'on' more useful by onlining all offline siblings.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 kernel/cpu.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 5a00ebdf98c6..d79e24df2420 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1979,6 +1979,15 @@ static void cpuhp_offline_cpu_device(unsigned int cpu)
 	kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
 }
 
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+	struct device *dev = get_cpu_device(cpu);
+
+	dev->offline = false;
+	/* Tell user space about the state change */
+	kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
 static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
 {
 	int cpu, ret = 0;
@@ -2011,11 +2020,24 @@ static int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
 	return ret;
 }
 
-static void cpuhp_smt_enable(void)
+static int cpuhp_smt_enable(void)
 {
+	int cpu, ret = 0;
+
 	cpu_maps_update_begin();
 	cpu_smt_control = CPU_SMT_ENABLED;
+	for_each_present_cpu(cpu) {
+		/* Skip online CPUs and CPUs on offline nodes */
+		if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+			continue;
+		ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+		if (ret)
+			break;
+		/* See comment in cpuhp_smt_disable() */
+		cpuhp_online_cpu_device(cpu);
+	}
 	cpu_maps_update_done();
+	return ret;
 }
 
 static ssize_t
@@ -2046,7 +2068,7 @@ store_smt_control(struct device *dev, struct device_attribute *attr,
 	if (ctrlval != cpu_smt_control) {
 		switch (ctrlval) {
 		case CPU_SMT_ENABLED:
-			cpuhp_smt_enable();
+			ret = cpuhp_smt_enable();
 			break;
 		case CPU_SMT_DISABLED:
 		case CPU_SMT_FORCE_DISABLED:
-- 
cgit v1.2.3


From 0832b603c7583e75f149ea984827b6d929f336b5 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 3 Jul 2018 14:47:25 +0200
Subject: mac80211: don't put null-data frames on the normal TXQ

Since (QoS) NDP frames shouldn't be put into aggregation nor are
assigned real sequence numbers, etc. it's better to treat them as
non-data packets and not put them on the normal TXQs, for example
when building A-MPDUs they need to be treated specially, and they
are more used for management (e.g. to see if the station is alive)
anyway.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 6a79d564de35..cd332e3e1134 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1249,7 +1249,7 @@ static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
 	    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
 		return NULL;
 
-	if (!ieee80211_is_data(hdr->frame_control))
+	if (!ieee80211_is_data_present(hdr->frame_control))
 		return NULL;
 
 	if (sta) {
-- 
cgit v1.2.3


From 518ea3c54eb7e454b718a50aa35bc5ea7856aa20 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Fri, 6 Jul 2018 15:29:05 +0300
Subject: mac80211_hwsim: Add support for HE

Add support for HE in mac8011_hwsim, conforming with P802.11ax_D2.0.

Signed-off-by: Liad Kaufman <liad.kaufman@intel.com>
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mac80211_hwsim.c | 123 ++++++++++++++++++++++++++++++++++
 1 file changed, 123 insertions(+)

diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index 18e819d964f1..998dfac0fcff 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -2,6 +2,7 @@
  * mac80211_hwsim - software simulator of 802.11 radio(s) for mac80211
  * Copyright (c) 2008, Jouni Malinen <j@w1.fi>
  * Copyright (c) 2011, Javier Lopez <jlopex@gmail.com>
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -2517,6 +2518,123 @@ out_err:
 	nlmsg_free(mcast_skb);
 }
 
+static const struct ieee80211_sband_iftype_data he_capa_2ghz = {
+	/* TODO: should we support other types, e.g., P2P?*/
+	.types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP),
+	.he_cap = {
+		.has_he = true,
+		.he_cap_elem = {
+			.mac_cap_info[0] =
+				IEEE80211_HE_MAC_CAP0_HTC_HE,
+			.mac_cap_info[1] =
+				IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+				IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8,
+			.mac_cap_info[2] =
+				IEEE80211_HE_MAC_CAP2_BSR |
+				IEEE80211_HE_MAC_CAP2_MU_CASCADING |
+				IEEE80211_HE_MAC_CAP2_ACK_EN,
+			.mac_cap_info[3] =
+				IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU |
+				IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
+				IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2,
+			.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU,
+			.phy_cap_info[0] =
+				IEEE80211_HE_PHY_CAP0_DUAL_BAND,
+			.phy_cap_info[1] =
+				IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
+				IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
+				IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+				IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS,
+			.phy_cap_info[2] =
+				IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+				IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
+				IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO,
+
+			/* Leave all the other PHY capability bytes unset, as
+			 * DCM, beam forming, RU and PPE threshold information
+			 * are not supported
+			 */
+		},
+		.he_mcs_nss_supp = {
+			.rx_mcs_80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80 = cpu_to_le16(0xfffa),
+			.rx_mcs_160 = cpu_to_le16(0xffff),
+			.tx_mcs_160 = cpu_to_le16(0xffff),
+			.rx_mcs_80p80 = cpu_to_le16(0xffff),
+			.tx_mcs_80p80 = cpu_to_le16(0xffff),
+		},
+	},
+};
+
+static const struct ieee80211_sband_iftype_data he_capa_5ghz = {
+	/* TODO: should we support other types, e.g., P2P?*/
+	.types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP),
+	.he_cap = {
+		.has_he = true,
+		.he_cap_elem = {
+			.mac_cap_info[0] =
+				IEEE80211_HE_MAC_CAP0_HTC_HE,
+			.mac_cap_info[1] =
+				IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+				IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8,
+			.mac_cap_info[2] =
+				IEEE80211_HE_MAC_CAP2_BSR |
+				IEEE80211_HE_MAC_CAP2_MU_CASCADING |
+				IEEE80211_HE_MAC_CAP2_ACK_EN,
+			.mac_cap_info[3] =
+				IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU |
+				IEEE80211_HE_MAC_CAP3_OMI_CONTROL |
+				IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2,
+			.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU,
+			.phy_cap_info[0] =
+				IEEE80211_HE_PHY_CAP0_DUAL_BAND |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G,
+			.phy_cap_info[1] =
+				IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK |
+				IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
+				IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+				IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS,
+			.phy_cap_info[2] =
+				IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+				IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO |
+				IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO,
+
+			/* Leave all the other PHY capability bytes unset, as
+			 * DCM, beam forming, RU and PPE threshold information
+			 * are not supported
+			 */
+		},
+		.he_mcs_nss_supp = {
+			.rx_mcs_80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80 = cpu_to_le16(0xfffa),
+			.rx_mcs_160 = cpu_to_le16(0xfffa),
+			.tx_mcs_160 = cpu_to_le16(0xfffa),
+			.rx_mcs_80p80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80p80 = cpu_to_le16(0xfffa),
+		},
+	},
+};
+
+static void mac80211_hswim_he_capab(struct ieee80211_supported_band *sband)
+{
+	if (sband->band == NL80211_BAND_2GHZ)
+		sband->iftype_data =
+			(struct ieee80211_sband_iftype_data *)&he_capa_2ghz;
+	else if (sband->band == NL80211_BAND_5GHZ)
+		sband->iftype_data =
+			(struct ieee80211_sband_iftype_data *)&he_capa_5ghz;
+	else
+		return;
+
+	sband->n_iftype_data = 1;
+}
+
 static int mac80211_hwsim_new_radio(struct genl_info *info,
 				    struct hwsim_new_radio_params *param)
 {
@@ -2678,6 +2796,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 
 	for (band = NL80211_BAND_2GHZ; band < NUM_NL80211_BANDS; band++) {
 		struct ieee80211_supported_band *sband = &data->bands[band];
+
+		sband->band = band;
+
 		switch (band) {
 		case NL80211_BAND_2GHZ:
 			sband->channels = data->channels_2ghz;
@@ -2734,6 +2855,8 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 		sband->ht_cap.mcs.rx_mask[1] = 0xff;
 		sband->ht_cap.mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
 
+		mac80211_hswim_he_capab(sband);
+
 		hw->wiphy->bands[band] = sband;
 	}
 
-- 
cgit v1.2.3


From da7f7126f04c37cf0b33a75b7a5dd3c1b2adfa2b Mon Sep 17 00:00:00 2001
From: Erik Schmauss <erik.schmauss@intel.com>
Date: Fri, 29 Jun 2018 11:28:11 -0700
Subject: ACPICA: Revert "iASL: change processing of external op namespace
 nodes for correctness"

Revert commit b43eac6f3384 (ACPICA: iASL: change processing of
external op namespace nodes for correctness; upstream ACPICA
commit aa866a9b4f24bbec9f158d10325b486d7d12d90f).

This was done in order to allow more relaxed usage of ASL external
declarations.

Signed-off-by: Erik Schmauss <erik.schmauss@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/nsaccess.c | 13 ++++++-------
 drivers/acpi/acpica/nssearch.c |  1 -
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 220a718fbce9..3c571fe98990 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -608,18 +608,17 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 					    this_node->object;
 				}
 			}
+#ifdef ACPI_ASL_COMPILER
+			if (!acpi_gbl_disasm_flag &&
+			    (this_node->flags & ANOBJ_IS_EXTERNAL)) {
+				this_node->flags |= IMPLICIT_EXTERNAL;
+			}
+#endif
 		}
 
 		/* Special handling for the last segment (num_segments == 0) */
 
 		else {
-#ifdef ACPI_ASL_COMPILER
-			if (!acpi_gbl_disasm_flag
-			    && (this_node->flags & ANOBJ_IS_EXTERNAL)) {
-				this_node->flags &= ~IMPLICIT_EXTERNAL;
-			}
-#endif
-
 			/*
 			 * Sanity typecheck of the target object:
 			 *
diff --git a/drivers/acpi/acpica/nssearch.c b/drivers/acpi/acpica/nssearch.c
index e9c9a63bb6a4..f594ab75a5fe 100644
--- a/drivers/acpi/acpica/nssearch.c
+++ b/drivers/acpi/acpica/nssearch.c
@@ -381,7 +381,6 @@ acpi_ns_search_and_enter(u32 target_name,
 	if (flags & ACPI_NS_EXTERNAL ||
 	    (walk_state && walk_state->opcode == AML_SCOPE_OP)) {
 		new_node->flags |= ANOBJ_IS_EXTERNAL;
-		new_node->flags |= IMPLICIT_EXTERNAL;
 	}
 #endif
 
-- 
cgit v1.2.3


From a9efdcffd54dc1098a089c3c833eef8d7bee4d77 Mon Sep 17 00:00:00 2001
From: Erik Schmauss <erik.schmauss@intel.com>
Date: Fri, 29 Jun 2018 11:28:12 -0700
Subject: ACPICA: Revert "iASL compiler: allow compilation of externals with
 paths that refer to existing names"

Revert commit 3ddd3f6a9410 (ACPICA: iASL compiler: allow compilation
of externals with paths that refer to existing names; upstream
ACPICA commit 9a252114197409290813bee570e9d53c22b99d32).

This was done in order to allow more relaxed usage of ASL external
declarations.

Signed-off-by: Erik Schmauss <erik.schmauss@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/acpica/aclocal.h  | 1 -
 drivers/acpi/acpica/nsaccess.c | 6 ------
 2 files changed, 7 deletions(-)

diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h
index 51c386bf230d..c5367bf5487f 100644
--- a/drivers/acpi/acpica/aclocal.h
+++ b/drivers/acpi/acpica/aclocal.h
@@ -165,7 +165,6 @@ struct acpi_namespace_node {
 #define ANOBJ_EVALUATED                 0x20	/* Set on first evaluation of node */
 #define ANOBJ_ALLOCATED_BUFFER          0x40	/* Method AML buffer is dynamic (install_method) */
 
-#define IMPLICIT_EXTERNAL               0x02	/* iASL only: This object created implicitly via External */
 #define ANOBJ_IS_EXTERNAL               0x08	/* iASL only: This object created via External() */
 #define ANOBJ_METHOD_NO_RETVAL          0x10	/* iASL only: Method has no return value */
 #define ANOBJ_METHOD_SOME_NO_RETVAL     0x20	/* iASL only: Method has at least one return value */
diff --git a/drivers/acpi/acpica/nsaccess.c b/drivers/acpi/acpica/nsaccess.c
index 3c571fe98990..83a593e2155d 100644
--- a/drivers/acpi/acpica/nsaccess.c
+++ b/drivers/acpi/acpica/nsaccess.c
@@ -608,12 +608,6 @@ acpi_ns_lookup(union acpi_generic_state *scope_info,
 					    this_node->object;
 				}
 			}
-#ifdef ACPI_ASL_COMPILER
-			if (!acpi_gbl_disasm_flag &&
-			    (this_node->flags & ANOBJ_IS_EXTERNAL)) {
-				this_node->flags |= IMPLICIT_EXTERNAL;
-			}
-#endif
 		}
 
 		/* Special handling for the last segment (num_segments == 0) */
-- 
cgit v1.2.3


From e74770fb6823c6fde49c3f2b38e3a2e68ae46682 Mon Sep 17 00:00:00 2001
From: Bob Moore <robert.moore@intel.com>
Date: Fri, 29 Jun 2018 11:28:13 -0700
Subject: ACPICA: Update version to 20180629

Version 20180629.

Signed-off-by: Bob Moore <robert.moore@intel.com>
Signed-off-by: Erik Schmauss <erik.schmauss@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/acpi/acpixf.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
index 48d84f0d9547..88072c92ace2 100644
--- a/include/acpi/acpixf.h
+++ b/include/acpi/acpixf.h
@@ -12,7 +12,7 @@
 
 /* Current ACPICA subsystem version in YYYYMMDD format */
 
-#define ACPI_CA_VERSION                 0x20180531
+#define ACPI_CA_VERSION                 0x20180629
 
 #include <acpi/acconfig.h>
 #include <acpi/actypes.h>
-- 
cgit v1.2.3


From 2c4c2a71bd6f75c3982ac09407889b110673ac83 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sat, 7 Jul 2018 08:25:01 -0700
Subject: ACPI / button: fix defined but not used warning

Fix a build warning in the ACPI button driver when CONFIG_PROC_FS
is not enabled by marking the unused function as __maybe_unused.

../drivers/acpi/button.c:252:12: warning: 'acpi_button_state_seq_show' defined but not used [-Wunused-function]

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/button.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/button.c b/drivers/acpi/button.c
index 40ed3ec9fc94..a19ff3977ac4 100644
--- a/drivers/acpi/button.c
+++ b/drivers/acpi/button.c
@@ -21,6 +21,7 @@
 
 #define pr_fmt(fmt) "ACPI: button: " fmt
 
+#include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -249,7 +250,8 @@ static int acpi_lid_notify_state(struct acpi_device *device, int state)
 	return ret;
 }
 
-static int acpi_button_state_seq_show(struct seq_file *seq, void *offset)
+static int __maybe_unused acpi_button_state_seq_show(struct seq_file *seq,
+						     void *offset)
 {
 	struct acpi_device *device = seq->private;
 	int state;
-- 
cgit v1.2.3


From 6663484b4e2d98f5609dc1b90fe4c242dd8fe18a Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 29 Jun 2018 11:48:50 -0700
Subject: EDAC, thunderx: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], switch to
using a kmalloc-allocated buffer instead of stack space. This should be
fine since the existing routine is allocating memory too.

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Jan Glauber <jglauber@cavium.com>
Cc: David Daney <david.daney@cavium.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/20180629184850.GA37464@beast
Link: https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com [1]
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/thunderx_edac.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/edac/thunderx_edac.c b/drivers/edac/thunderx_edac.c
index 4803c6468bab..c009d94f40c5 100644
--- a/drivers/edac/thunderx_edac.c
+++ b/drivers/edac/thunderx_edac.c
@@ -408,26 +408,29 @@ static ssize_t thunderx_lmc_inject_ecc_write(struct file *file,
 					     size_t count, loff_t *ppos)
 {
 	struct thunderx_lmc *lmc = file->private_data;
-
 	unsigned int cline_size = cache_line_size();
-
-	u8 tmp[cline_size];
+	u8 *tmp;
 	void __iomem *addr;
 	unsigned int offs, timeout = 100000;
 
 	atomic_set(&lmc->ecc_int, 0);
 
 	lmc->mem = alloc_pages_node(lmc->node, GFP_KERNEL, 0);
-
 	if (!lmc->mem)
 		return -ENOMEM;
 
+	tmp = kmalloc(cline_size, GFP_KERNEL);
+	if (!tmp) {
+		__free_pages(lmc->mem, 0);
+		return -ENOMEM;
+	}
+
 	addr = page_address(lmc->mem);
 
 	while (!atomic_read(&lmc->ecc_int) && timeout--) {
 		stop_machine(inject_ecc_fn, lmc, NULL);
 
-		for (offs = 0; offs < PAGE_SIZE; offs += sizeof(tmp)) {
+		for (offs = 0; offs < PAGE_SIZE; offs += cline_size) {
 			/*
 			 * Do a load from the previously rigged location
 			 * This should generate an error interrupt.
@@ -437,6 +440,7 @@ static ssize_t thunderx_lmc_inject_ecc_write(struct file *file,
 		}
 	}
 
+	kfree(tmp);
 	__free_pages(lmc->mem, 0);
 
 	return count;
-- 
cgit v1.2.3


From e147913247e3a7ea98e72e8537336bcea06c2405 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Sat, 7 Jul 2018 11:04:05 +0100
Subject: drm/i915/selftests: Magic numbers for old Y-tiling

i915g has a slightly different tiling layout, and so requires a
different reference swizzle pattern.

Testcase: igt/drv_selftests/live_objects #gdg
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180707100405.817-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_object.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index 25c2b2d433bd..f4a5099c75b5 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -169,9 +169,16 @@ static u64 tiled_offset(const struct tile *tile, u64 v)
 		v += y * tile->width;
 		v += div64_u64_rem(x, tile->width, &x) << tile->size;
 		v += x;
-	} else {
+	} else if (tile->width == 128) {
 		const unsigned int ytile_span = 16;
-		const unsigned int ytile_height = 32 * ytile_span;
+		const unsigned int ytile_height = 512;
+
+		v += y * ytile_span;
+		v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
+		v += x;
+	} else {
+		const unsigned int ytile_span = 32;
+		const unsigned int ytile_height = 256;
 
 		v += y * ytile_span;
 		v += div64_u64_rem(x, ytile_span, &x) * ytile_height;
-- 
cgit v1.2.3


From 79a5c45199cd942047b1cf7bb50ff0699c2a3af0 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 29 Jun 2018 13:04:30 +0200
Subject: PM / Domains: dt: Add a power-domain-names property

Let's add a power-domain-names property, to allow consumer drivers to match
the power-domains specifiers via a list of power domain names. This follows
the same concept as for other similar DT bindings.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Rajendra Nayak <rnayak@codeaurora.org>
Reviewed-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/devicetree/bindings/power/power_domain.txt | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/devicetree/bindings/power/power_domain.txt b/Documentation/devicetree/bindings/power/power_domain.txt
index 9b387f861aed..4d6bc8829468 100644
--- a/Documentation/devicetree/bindings/power/power_domain.txt
+++ b/Documentation/devicetree/bindings/power/power_domain.txt
@@ -114,18 +114,26 @@ Required properties:
  - power-domains : A list of PM domain specifiers, as defined by bindings of
 		the power controller that is the PM domain provider.
 
+Optional properties:
+ - power-domain-names : A list of power domain name strings sorted in the same
+		order as the power-domains property. Consumers drivers will use
+		power-domain-names to match power domains with power-domains
+		specifiers.
+
 Example:
 
 	leaky-device@12350000 {
 		compatible = "foo,i-leak-current";
 		reg = <0x12350000 0x1000>;
 		power-domains = <&power 0>;
+		power-domain-names = "io";
 	};
 
 	leaky-device@12351000 {
 		compatible = "foo,i-leak-current";
 		reg = <0x12351000 0x1000>;
 		power-domains = <&power 0>, <&power 1> ;
+		power-domain-names = "io", "clk";
 	};
 
 The first example above defines a typical PM domain consumer device, which is
-- 
cgit v1.2.3


From 5d6be70add65e3f236642ab0029e356261617cd0 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 29 Jun 2018 13:04:31 +0200
Subject: PM / Domains: Introduce option to attach a device by name to genpd

For the multiple PM domain case, let's introduce a new function called
genpd_dev_pm_attach_by_name(). This allows a device to be associated with
its PM domain through genpd, by using a name based lookup.

Note that, genpd_dev_pm_attach_by_name() shall only be called by the driver
core / PM core, similar to how the existing dev_pm_domain_attach_by_id()
makes use of genpd_dev_pm_attach_by_id(). However, this is implemented by
following changes on top.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Rajendra Nayak <rnayak@codeaurora.org>
Reviewed-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/domain.c | 24 ++++++++++++++++++++++++
 include/linux/pm_domain.h   |  8 ++++++++
 2 files changed, 32 insertions(+)

diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 9e8484189034..79bdca70a81a 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -2374,6 +2374,30 @@ struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach_by_id);
 
+/**
+ * genpd_dev_pm_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * Parse device's OF node to find a PM domain specifier using the
+ * power-domain-names DT property. For further description see
+ * genpd_dev_pm_attach_by_id().
+ */
+struct device *genpd_dev_pm_attach_by_name(struct device *dev, char *name)
+{
+	int index;
+
+	if (!dev->of_node)
+		return NULL;
+
+	index = of_property_match_string(dev->of_node, "power-domain-names",
+					 name);
+	if (index < 0)
+		return NULL;
+
+	return genpd_dev_pm_attach_by_id(dev, index);
+}
+
 static const struct of_device_id idle_state_match[] = {
 	{ .compatible = "domain-idle-state", },
 	{ }
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index cb8d84090cfb..03e14a38462d 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -239,6 +239,8 @@ unsigned int of_genpd_opp_to_performance_state(struct device *dev,
 int genpd_dev_pm_attach(struct device *dev);
 struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 					 unsigned int index);
+struct device *genpd_dev_pm_attach_by_name(struct device *dev,
+					   char *name);
 #else /* !CONFIG_PM_GENERIC_DOMAINS_OF */
 static inline int of_genpd_add_provider_simple(struct device_node *np,
 					struct generic_pm_domain *genpd)
@@ -290,6 +292,12 @@ static inline struct device *genpd_dev_pm_attach_by_id(struct device *dev,
 	return NULL;
 }
 
+static inline struct device *genpd_dev_pm_attach_by_name(struct device *dev,
+							 char *name)
+{
+	return NULL;
+}
+
 static inline
 struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 {
-- 
cgit v1.2.3


From 27dceb81f445c58b1d10d27d26eaf4ac2e9e0b00 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Fri, 29 Jun 2018 13:04:32 +0200
Subject: PM / Domains: Introduce dev_pm_domain_attach_by_name()

For the multiple PM domain case, let's introduce a new API called
dev_pm_domain_attach_by_name(). This allows a consumer driver to associate
its device with one of its PM domains, by using a name based lookup.

Do note that, currently it's only genpd that supports multiple PM domains
per device, but dev_pm_domain_attach_by_name() can easily by extended to
cover other PM domain types, if/when needed.

Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Tested-by: Rajendra Nayak <rnayak@codeaurora.org>
Reviewed-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/common.c | 17 +++++++++++++++++
 include/linux/pm_domain.h   |  7 +++++++
 2 files changed, 24 insertions(+)

diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index df41b4780b3b..b413951c6abc 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -152,6 +152,23 @@ struct device *dev_pm_domain_attach_by_id(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_id);
 
+/**
+ * dev_pm_domain_attach_by_name - Associate a device with one of its PM domains.
+ * @dev: The device used to lookup the PM domain.
+ * @name: The name of the PM domain.
+ *
+ * For a detailed function description, see dev_pm_domain_attach_by_id().
+ */
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+					    char *name)
+{
+	if (dev->pm_domain)
+		return ERR_PTR(-EEXIST);
+
+	return genpd_dev_pm_attach_by_name(dev, name);
+}
+EXPORT_SYMBOL_GPL(dev_pm_domain_attach_by_name);
+
 /**
  * dev_pm_domain_detach - Detach a device from its PM domain.
  * @dev: Device to detach.
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 03e14a38462d..776c546d581a 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -309,6 +309,8 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 int dev_pm_domain_attach(struct device *dev, bool power_on);
 struct device *dev_pm_domain_attach_by_id(struct device *dev,
 					  unsigned int index);
+struct device *dev_pm_domain_attach_by_name(struct device *dev,
+					    char *name);
 void dev_pm_domain_detach(struct device *dev, bool power_off);
 void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
 #else
@@ -321,6 +323,11 @@ static inline struct device *dev_pm_domain_attach_by_id(struct device *dev,
 {
 	return NULL;
 }
+static inline struct device *dev_pm_domain_attach_by_name(struct device *dev,
+							  char *name)
+{
+	return NULL;
+}
 static inline void dev_pm_domain_detach(struct device *dev, bool power_off) {}
 static inline void dev_pm_domain_set(struct device *dev,
 				     struct dev_pm_domain *pd) {}
-- 
cgit v1.2.3


From e88728f46cfbb59cc7e7acf1d230c05ec093764e Mon Sep 17 00:00:00 2001
From: Vivek Gautam <vivek.gautam@codeaurora.org>
Date: Wed, 27 Jun 2018 18:20:55 +0530
Subject: driver core: Rename flag AUTOREMOVE to AUTOREMOVE_CONSUMER

Now that we want to add another flag to autoremove the device link
on supplier unbind, it's fair to rename the existing flag from
DL_FLAG_AUTOREMOVE to DL_FLAG_AUTOREMOVE_CONSUMER so that we can
add similar flag for supplier later.
And, while we are touching device.h, fix a doc build warning.

Signed-off-by: Vivek Gautam <vivek.gautam@codeaurora.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/driver-api/device_link.rst |  8 ++++----
 drivers/base/core.c                      | 15 ++++++++-------
 drivers/gpu/drm/tegra/dc.c               |  2 +-
 drivers/gpu/ipu-v3/ipu-pre.c             |  3 ++-
 drivers/gpu/ipu-v3/ipu-prg.c             |  3 ++-
 drivers/soc/imx/gpc.c                    |  2 +-
 include/linux/device.h                   | 12 ++++++------
 7 files changed, 24 insertions(+), 21 deletions(-)

diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst
index 70e328e16aad..a005b904a264 100644
--- a/Documentation/driver-api/device_link.rst
+++ b/Documentation/driver-api/device_link.rst
@@ -81,10 +81,10 @@ integration is desired.
 Two other flags are specifically targeted at use cases where the device
 link is added from the consumer's ``->probe`` callback:  ``DL_FLAG_RPM_ACTIVE``
 can be specified to runtime resume the supplier upon addition of the
-device link.  ``DL_FLAG_AUTOREMOVE`` causes the device link to be automatically
-purged when the consumer fails to probe or later unbinds.  This obviates
-the need to explicitly delete the link in the ``->remove`` callback or in
-the error path of the ``->probe`` callback.
+device link.  ``DL_FLAG_AUTOREMOVE_CONSUMER`` causes the device link to be
+automatically purged when the consumer fails to probe or later unbinds.
+This obviates the need to explicitly delete the link in the ``->remove``
+callback or in the error path of the ``->probe`` callback.
 
 Limitations
 ===========
diff --git a/drivers/base/core.c b/drivers/base/core.c
index df3e1a44707a..14c1e3151e08 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -178,10 +178,10 @@ void device_pm_move_to_tail(struct device *dev)
  * of the link.  If DL_FLAG_PM_RUNTIME is not set, DL_FLAG_RPM_ACTIVE will be
  * ignored.
  *
- * If the DL_FLAG_AUTOREMOVE is set, the link will be removed automatically
- * when the consumer device driver unbinds from it.  The combination of both
- * DL_FLAG_AUTOREMOVE and DL_FLAG_STATELESS set is invalid and will cause NULL
- * to be returned.
+ * If the DL_FLAG_AUTOREMOVE_CONSUMER is set, the link will be removed
+ * automatically when the consumer device driver unbinds from it.
+ * The combination of both DL_FLAG_AUTOREMOVE_CONSUMER and DL_FLAG_STATELESS
+ * set is invalid and will cause NULL to be returned.
  *
  * A side effect of the link creation is re-ordering of dpm_list and the
  * devices_kset list by moving the consumer device and all devices depending
@@ -198,7 +198,8 @@ struct device_link *device_link_add(struct device *consumer,
 	struct device_link *link;
 
 	if (!consumer || !supplier ||
-	    ((flags & DL_FLAG_STATELESS) && (flags & DL_FLAG_AUTOREMOVE)))
+	    ((flags & DL_FLAG_STATELESS) &&
+	     (flags & DL_FLAG_AUTOREMOVE_CONSUMER)))
 		return NULL;
 
 	device_links_write_lock();
@@ -479,7 +480,7 @@ static void __device_links_no_driver(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		if (link->flags & DL_FLAG_AUTOREMOVE)
+		if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
 			kref_put(&link->kref, __device_link_del);
 		else if (link->status != DL_STATE_SUPPLIER_UNBIND)
 			WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
@@ -515,7 +516,7 @@ void device_links_driver_cleanup(struct device *dev)
 		if (link->flags & DL_FLAG_STATELESS)
 			continue;
 
-		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE);
+		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
 		WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
diff --git a/drivers/gpu/drm/tegra/dc.c b/drivers/gpu/drm/tegra/dc.c
index c3afe7b2237e..965088afcfad 100644
--- a/drivers/gpu/drm/tegra/dc.c
+++ b/drivers/gpu/drm/tegra/dc.c
@@ -2312,7 +2312,7 @@ static int tegra_dc_couple(struct tegra_dc *dc)
 	 * POWER_CONTROL registers during CRTC enabling.
 	 */
 	if (dc->soc->coupled_pm && dc->pipe == 1) {
-		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE;
+		u32 flags = DL_FLAG_PM_RUNTIME | DL_FLAG_AUTOREMOVE_CONSUMER;
 		struct device_link *link;
 		struct device *partner;
 
diff --git a/drivers/gpu/ipu-v3/ipu-pre.c b/drivers/gpu/ipu-v3/ipu-pre.c
index 0f70e8847540..2f8db9d62551 100644
--- a/drivers/gpu/ipu-v3/ipu-pre.c
+++ b/drivers/gpu/ipu-v3/ipu-pre.c
@@ -128,7 +128,8 @@ ipu_pre_lookup_by_phandle(struct device *dev, const char *name, int index)
 	list_for_each_entry(pre, &ipu_pre_list, list) {
 		if (pre_node == pre->dev->of_node) {
 			mutex_unlock(&ipu_pre_list_mutex);
-			device_link_add(dev, pre->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, pre->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			of_node_put(pre_node);
 			return pre;
 		}
diff --git a/drivers/gpu/ipu-v3/ipu-prg.c b/drivers/gpu/ipu-v3/ipu-prg.c
index 83f9dd934a5d..38a3a9764e49 100644
--- a/drivers/gpu/ipu-v3/ipu-prg.c
+++ b/drivers/gpu/ipu-v3/ipu-prg.c
@@ -100,7 +100,8 @@ ipu_prg_lookup_by_phandle(struct device *dev, const char *name, int ipu_id)
 	list_for_each_entry(prg, &ipu_prg_list, list) {
 		if (prg_node == prg->dev->of_node) {
 			mutex_unlock(&ipu_prg_list_mutex);
-			device_link_add(dev, prg->dev, DL_FLAG_AUTOREMOVE);
+			device_link_add(dev, prg->dev,
+					DL_FLAG_AUTOREMOVE_CONSUMER);
 			prg->id = ipu_id;
 			of_node_put(prg_node);
 			return prg;
diff --git a/drivers/soc/imx/gpc.c b/drivers/soc/imx/gpc.c
index 32f0748fd067..aa9e65bc965e 100644
--- a/drivers/soc/imx/gpc.c
+++ b/drivers/soc/imx/gpc.c
@@ -202,7 +202,7 @@ static int imx_pgc_power_domain_probe(struct platform_device *pdev)
 			goto genpd_err;
 	}
 
-	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE);
+	device_link_add(dev, dev->parent, DL_FLAG_AUTOREMOVE_CONSUMER);
 
 	return 0;
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69dbcd18..3929805cdd59 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -90,7 +90,7 @@ extern void bus_remove_file(struct bus_type *, struct bus_attribute *);
  * @num_vf:	Called to find out how many virtual functions a device on this
  *		bus supports.
  * @dma_configure:	Called to setup DMA configuration on a device on
-			this bus.
+ *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
  * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
@@ -784,14 +784,14 @@ enum device_link_state {
  * Device link flags.
  *
  * STATELESS: The core won't track the presence of supplier/consumer drivers.
- * AUTOREMOVE: Remove this link automatically on consumer driver unbind.
+ * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind.
  * PM_RUNTIME: If set, the runtime PM framework will use this link.
  * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation.
  */
-#define DL_FLAG_STATELESS	BIT(0)
-#define DL_FLAG_AUTOREMOVE	BIT(1)
-#define DL_FLAG_PM_RUNTIME	BIT(2)
-#define DL_FLAG_RPM_ACTIVE	BIT(3)
+#define DL_FLAG_STATELESS		BIT(0)
+#define DL_FLAG_AUTOREMOVE_CONSUMER	BIT(1)
+#define DL_FLAG_PM_RUNTIME		BIT(2)
+#define DL_FLAG_RPM_ACTIVE		BIT(3)
 
 /**
  * struct device_link - Device link representation.
-- 
cgit v1.2.3


From 1689cac5b32a6db6f812e8063ea418a7cf023d03 Mon Sep 17 00:00:00 2001
From: Vivek Gautam <vivek.gautam@codeaurora.org>
Date: Wed, 27 Jun 2018 18:20:56 +0530
Subject: driver core: Add flag to autoremove device link on supplier unbind

Add a flag to autoremove the device links on supplier driver
unbind. This obviates the need to explicitly delete the link
in the remove path.
We remove these links only when the supplier's link to its
consumers has gone to DL_STATE_SUPPLIER_UNBIND state.

Signed-off-by: Vivek Gautam <vivek.gautam@codeaurora.org>
Suggested-by: Lukas Wunner <lukas@wunner.de>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/driver-api/device_link.rst |  4 ++++
 drivers/base/core.c                      | 10 ++++++++++
 include/linux/device.h                   |  2 ++
 3 files changed, 16 insertions(+)

diff --git a/Documentation/driver-api/device_link.rst b/Documentation/driver-api/device_link.rst
index a005b904a264..d6763272e747 100644
--- a/Documentation/driver-api/device_link.rst
+++ b/Documentation/driver-api/device_link.rst
@@ -86,6 +86,10 @@ automatically purged when the consumer fails to probe or later unbinds.
 This obviates the need to explicitly delete the link in the ``->remove``
 callback or in the error path of the ``->probe`` callback.
 
+Similarly, when the device link is added from supplier's ``->probe`` callback,
+``DL_FLAG_AUTOREMOVE_SUPPLIER`` causes the device link to be automatically
+purged when the supplier fails to probe or later unbinds.
+
 Limitations
 ===========
 
diff --git a/drivers/base/core.c b/drivers/base/core.c
index 14c1e3151e08..e721218bf352 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -518,6 +518,16 @@ void device_links_driver_cleanup(struct device *dev)
 
 		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
 		WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
+
+		/*
+		 * autoremove the links between this @dev and its consumer
+		 * devices that are not active, i.e. where the link state
+		 * has moved to DL_STATE_SUPPLIER_UNBIND.
+		 */
+		if (link->status == DL_STATE_SUPPLIER_UNBIND &&
+		    link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+			kref_put(&link->kref, __device_link_del);
+
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
 	}
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 3929805cdd59..e80920452b49 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -787,11 +787,13 @@ enum device_link_state {
  * AUTOREMOVE_CONSUMER: Remove the link automatically on consumer driver unbind.
  * PM_RUNTIME: If set, the runtime PM framework will use this link.
  * RPM_ACTIVE: Run pm_runtime_get_sync() on the supplier during link creation.
+ * AUTOREMOVE_SUPPLIER: Remove the link automatically on supplier driver unbind.
  */
 #define DL_FLAG_STATELESS		BIT(0)
 #define DL_FLAG_AUTOREMOVE_CONSUMER	BIT(1)
 #define DL_FLAG_PM_RUNTIME		BIT(2)
 #define DL_FLAG_RPM_ACTIVE		BIT(3)
+#define DL_FLAG_AUTOREMOVE_SUPPLIER	BIT(4)
 
 /**
  * struct device_link - Device link representation.
-- 
cgit v1.2.3


From 63f3fb8d7ccb813e0a1f2ceedb9a3ebe2685b620 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Mon, 2 Jul 2018 15:59:37 -0700
Subject: pinctrl: Document pin_config_group_get() return codes like
 pin_config_get()

The pinconf_generic_dump_one() function makes the assumption that
pin_config_group_get() should return -EINVAL and -ENOTSUPP just like
pin_config_get() does.  Document that so it's more obvious.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/pinctrl/pinconf.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/pinctrl/pinconf.h b/include/linux/pinctrl/pinconf.h
index 09eb80f2574a..8dd85d302b90 100644
--- a/include/linux/pinctrl/pinconf.h
+++ b/include/linux/pinctrl/pinconf.h
@@ -28,7 +28,8 @@ struct seq_file;
  *	is not available on this controller this should return -ENOTSUPP
  *	and if it is available but disabled it should return -EINVAL
  * @pin_config_set: configure an individual pin
- * @pin_config_group_get: get configurations for an entire pin group
+ * @pin_config_group_get: get configurations for an entire pin group; should
+ *	return -ENOTSUPP and -EINVAL using the same rules as pin_config_get.
  * @pin_config_group_set: configure all pins in a group
  * @pin_config_dbg_parse_modify: optional debugfs to modify a pin configuration
  * @pin_config_dbg_show: optional debugfs display hook that will provide
-- 
cgit v1.2.3


From b1911710e6e5a9faf91e1925b1e2cdd007920c4c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 3 Jul 2018 03:39:03 +0300
Subject: gpiolib: Join string literals back

For easy grepping on debug purposes join string literals back in the
messages.

While here, fix couple of small indentation issues.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index c6f77e806cb8..f15a222205c6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1664,8 +1664,7 @@ static void gpiochip_set_cascaded_irqchip(struct gpio_chip *gpiochip,
 	if (parent_handler) {
 		if (gpiochip->can_sleep) {
 			chip_err(gpiochip,
-				 "you cannot have chained interrupts on a "
-				 "chip that may sleep\n");
+				 "you cannot have chained interrupts on a chip that may sleep\n");
 			return;
 		}
 		/*
@@ -1850,8 +1849,7 @@ static int gpiochip_add_irqchip(struct gpio_chip *gpiochip,
 		return 0;
 
 	if (gpiochip->irq.parent_handler && gpiochip->can_sleep) {
-		chip_err(gpiochip, "you cannot have chained interrupts on a "
-			 "chip that may sleep\n");
+		chip_err(gpiochip, "you cannot have chained interrupts on a chip that may sleep\n");
 		return -EINVAL;
 	}
 
@@ -3272,8 +3270,8 @@ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 
 	if (test_bit(FLAG_IS_OUT, &desc->flags)) {
 		chip_err(chip,
-			  "%s: tried to flag a GPIO set as output for IRQ\n",
-			  __func__);
+			 "%s: tried to flag a GPIO set as output for IRQ\n",
+			 __func__);
 		return -EIO;
 	}
 
@@ -4228,7 +4226,7 @@ static int __init gpiolib_dev_init(void)
 	int ret;
 
 	/* Register GPIO sysfs bus */
-	ret  = bus_register(&gpio_bus_type);
+	ret = bus_register(&gpio_bus_type);
 	if (ret < 0) {
 		pr_err("gpiolib: could not register GPIO bus type\n");
 		return ret;
-- 
cgit v1.2.3


From 05e0c828955c1cab58dd71a04539442e5375d917 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Mon, 2 Jul 2018 15:59:38 -0700
Subject: pinctrl: msm: Fix msm_config_group_get() to be compliant

If you do this on an sdm845 board:
  cat /sys/kernel/debug/pinctrl/3400000.pinctrl/pinconf-groups

...it looks like nonsense.  For every pin you see listed:
  input bias bus hold, input bias disabled, input bias pull down, input bias pull up

That's because msm_config_group_get() isn't complying with the rules
that pinconf_generic_dump_one() expects.  Specifically for boolean
parameters (anything with a "struct pin_config_item" where has_arg is
false) the function expects that the function should return its value
not through the "config" parameter but should return "0" if the value
is set and "-EINVAL" if the value isn't set.

Let's fix this.

From a quick sample of other pinctrl drivers, it appears to be
tradition to also return 1 through the config parameter for these
boolean parameters when they exist.  I'm not one to knock tradition,
so I'll follow tradition and return 1 in these cases.  While I'm at
it, I'll also continue searching for four leaf clovers, kocking on
wood three times, and trying not to break mirrors.

Fixes: f365be092572 ("pinctrl: Add Qualcomm TLMM driver")
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-msm.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 0e22f52b2a19..2155a30c282b 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -250,22 +250,30 @@ static int msm_config_group_get(struct pinctrl_dev *pctldev,
 	/* Convert register value to pinconf value */
 	switch (param) {
 	case PIN_CONFIG_BIAS_DISABLE:
-		arg = arg == MSM_NO_PULL;
+		if (arg != MSM_NO_PULL)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		arg = arg == MSM_PULL_DOWN;
+		if (arg != MSM_PULL_DOWN)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_BUS_HOLD:
 		if (pctrl->soc->pull_no_keeper)
 			return -ENOTSUPP;
 
-		arg = arg == MSM_KEEPER;
+		if (arg != MSM_KEEPER)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_UP:
 		if (pctrl->soc->pull_no_keeper)
 			arg = arg == MSM_PULL_UP_NO_KEEPER;
 		else
 			arg = arg == MSM_PULL_UP;
+		if (!arg)
+			return -EINVAL;
 		break;
 	case PIN_CONFIG_DRIVE_STRENGTH:
 		arg = msm_regval_to_drive(arg);
-- 
cgit v1.2.3


From 8db339d66774821091f73bd0e57c8a7511c5988e Mon Sep 17 00:00:00 2001
From: "benjamin.gaignard@linaro.org" <benjamin.gaignard@linaro.org>
Date: Fri, 6 Jul 2018 15:07:03 +0200
Subject: ASoC: stm32: replace "%p" with "%pK"

The format specifier "%p" can leak kernel addresses.
Use "%pK" instead.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@st.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/stm/stm32_adfsdm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/stm/stm32_adfsdm.c b/sound/soc/stm/stm32_adfsdm.c
index db73fef3e500..0e9373064032 100644
--- a/sound/soc/stm/stm32_adfsdm.c
+++ b/sound/soc/stm/stm32_adfsdm.c
@@ -149,7 +149,7 @@ static int stm32_afsdm_pcm_cb(const void *data, size_t size, void *private)
 	unsigned int old_pos = priv->pos;
 	unsigned int cur_size = size;
 
-	dev_dbg(rtd->dev, "%s: buff_add :%p, pos = %d, size = %zu\n",
+	dev_dbg(rtd->dev, "%s: buff_add :%pK, pos = %d, size = %zu\n",
 		__func__, &pcm_buff[priv->pos], priv->pos, size);
 
 	if ((priv->pos + size) > buff_size) {
-- 
cgit v1.2.3


From 1cf86bc21257a330e3af51f2a4e885f1a705f6a5 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Mon, 2 Jul 2018 15:59:39 -0700
Subject: pinctrl: qcom: spmi-gpio: Fix pmic_gpio_config_get() to be compliant

If you do this on an sdm845 board:
  grep "" /sys/kernel/debug/pinctrl/*spmi:pmic*/pinconf-groups

...it looks like nonsense.  For every pin you see listed:
  input bias disabled, input bias high impedance, input bias pull down, input bias pull up, ...

That's because pmic_gpio_config_get() isn't complying with the rules
that pinconf_generic_dump_one() expects.  Specifically for boolean
parameters (anything with a "struct pin_config_item" where has_arg is
false) the function expects that the function should return its value
not through the "config" parameter but should return "0" if the value
is set and "-EINVAL" if the value isn't set.

Let's fix this.

From a quick sample of other pinctrl drivers, it appears to be
tradition to also return 1 through the config parameter for these
boolean parameters when they exist.  I'm not one to knock tradition,
so I'll follow tradition and return 1 in these cases.  While I'm at
it, I'll also continue searching for four leaf clovers, kocking on
wood three times, and trying not to break mirrors.

NOTE: This also fixes an apparent typo for reading
PIN_CONFIG_BIAS_DISABLE where the old driver was accidentally
using "=" instead of "==" and thus was setting some internal
state when you tried to query PIN_CONFIG_BIAS_DISABLE.  Oops.

Fixes: eadff3024472 ("pinctrl: Qualcomm SPMI PMIC GPIO pin controller driver")
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index 3e66e0d10010..cf82db78e69e 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -390,31 +390,47 @@ static int pmic_gpio_config_get(struct pinctrl_dev *pctldev,
 
 	switch (param) {
 	case PIN_CONFIG_DRIVE_PUSH_PULL:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_CMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_CMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_DRIVE_OPEN_DRAIN:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_OPEN_DRAIN_NMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_OPEN_DRAIN_NMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_DRIVE_OPEN_SOURCE:
-		arg = pad->buffer_type == PMIC_GPIO_OUT_BUF_OPEN_DRAIN_PMOS;
+		if (pad->buffer_type != PMIC_GPIO_OUT_BUF_OPEN_DRAIN_PMOS)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_DOWN:
-		arg = pad->pullup == PMIC_GPIO_PULL_DOWN;
+		if (pad->pullup != PMIC_GPIO_PULL_DOWN)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_DISABLE:
-		arg = pad->pullup = PMIC_GPIO_PULL_DISABLE;
+		if (pad->pullup != PMIC_GPIO_PULL_DISABLE)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_PULL_UP:
-		arg = pad->pullup == PMIC_GPIO_PULL_UP_30;
+		if (pad->pullup != PMIC_GPIO_PULL_UP_30)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_BIAS_HIGH_IMPEDANCE:
-		arg = !pad->is_enabled;
+		if (pad->is_enabled)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_POWER_SOURCE:
 		arg = pad->power_source;
 		break;
 	case PIN_CONFIG_INPUT_ENABLE:
-		arg = pad->input_enabled;
+		if (!pad->input_enabled)
+			return -EINVAL;
+		arg = 1;
 		break;
 	case PIN_CONFIG_OUTPUT:
 		arg = pad->out_value;
-- 
cgit v1.2.3


From 1aa1b918946537c089716bffd1399e30a2981cb7 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 6 Jul 2018 11:37:18 +0300
Subject: regulator: max8997: clean up a condition in max8997_list_voltage()

The current code generates a static cehcker warnings because "rid < 0"
is always false:

    drivers/regulator/max8997-regulator.c:169 max8997_list_voltage()
    warn: condition is always false

The problem is that because of type promotion, if "rid" is negative the
comparison against ARRAY_SIZE() is type promoted to size_t and it's
treated as a very high positive value.  I've changed the order of the
checks so now everyone is happy.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/max8997-regulator.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/regulator/max8997-regulator.c b/drivers/regulator/max8997-regulator.c
index a8ea30ee18a6..029a6ee426ab 100644
--- a/drivers/regulator/max8997-regulator.c
+++ b/drivers/regulator/max8997-regulator.c
@@ -165,8 +165,7 @@ static int max8997_list_voltage(struct regulator_dev *rdev,
 	int rid = rdev_get_id(rdev);
 	int val;
 
-	if (rid >= ARRAY_SIZE(reg_voltage_map) ||
-			rid < 0)
+	if (rid < 0 || rid >= ARRAY_SIZE(reg_voltage_map))
 		return -EINVAL;
 
 	desc = reg_voltage_map[rid];
-- 
cgit v1.2.3


From 9d1310daedae494874fe36a995172e64b06e29a4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Jul 2018 15:30:48 +0200
Subject: ASoC: pxa: make SND_PXA_SOC_SSP depend on PLAT_PXA

For the moment, we can't enable CONFIG_SND_PXA_SOC_SSP unless we are
building for ARM PXA or MMP:

WARNING: unmet direct dependencies detected for PXA_SSP
  Depends on [n]: PLAT_PXA [=n]
  Selected by [y]:
  - SND_PXA_SOC_SSP [=y] && SOUND [=y] && !UML && SND [=y] && SND_SOC [=y]

This adds an explicit dependency for it.

Fixes: 0a94cf345740 ("ASoC: pxa: make SND_PXA2XX_SOC_I2S selectable")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/pxa/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/pxa/Kconfig b/sound/soc/pxa/Kconfig
index 2fc02c227f69..776e148b0aa2 100644
--- a/sound/soc/pxa/Kconfig
+++ b/sound/soc/pxa/Kconfig
@@ -34,6 +34,7 @@ config SND_PXA2XX_SOC_I2S
 
 config SND_PXA_SOC_SSP
 	tristate "Soc Audio via PXA2xx/PXA3xx SSP ports"
+	depends on PLAT_PXA
 	select PXA_SSP
 	select SND_PXA2XX_LIB
 
-- 
cgit v1.2.3


From 5bea327962fa296efd16f2d3369dd339ddd7ce6f Mon Sep 17 00:00:00 2001
From: Lars-Peter Clausen <lars@metafoo.de>
Date: Fri, 6 Jul 2018 16:19:14 +0300
Subject: ASoC: adau171x1: Connect playback DAI to the DSP

The playback DAI is connected to the DSP and the DSP might be sourcing
signals from the playback stream. Add a DAPM route between the two to make
sure that the playback DAI is powered up, when the DSP is active.

Signed-off-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Alexandru Ardelean <alexandru.ardelean@analog.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/adau17x1.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/adau17x1.c b/sound/soc/codecs/adau17x1.c
index ae41edd1c406..57169b8ff14e 100644
--- a/sound/soc/codecs/adau17x1.c
+++ b/sound/soc/codecs/adau17x1.c
@@ -299,6 +299,7 @@ static const struct snd_soc_dapm_route adau17x1_dsp_dapm_routes[] = {
 
 	{ "DSP", NULL, "Left Decimator" },
 	{ "DSP", NULL, "Right Decimator" },
+	{ "DSP", NULL, "Playback" },
 };
 
 static const struct snd_soc_dapm_route adau17x1_no_dsp_dapm_routes[] = {
-- 
cgit v1.2.3


From af2b04d19242686a2c30e526c9b7a9e9c57bbce9 Mon Sep 17 00:00:00 2001
From: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Date: Thu, 5 Jul 2018 15:43:11 +0200
Subject: gpio: mt7621: Add DT bindings

Add a devicetree binding documentation for the mt7621 gpio.

Signed-off-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Reviewed-by: NeilBrown <neil@brown.name>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/gpio/mediatek,mt7621-gpio.txt         | 35 ++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt

diff --git a/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt b/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt
new file mode 100644
index 000000000000..ba455589f869
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/mediatek,mt7621-gpio.txt
@@ -0,0 +1,35 @@
+Mediatek MT7621 SoC GPIO controller bindings
+
+The IP core used inside these SoCs has 3 banks of 32 GPIOs each.
+The registers of all the banks are interwoven inside one single IO range.
+We load one GPIO controller instance per bank. Also the GPIO controller can receive
+interrupts on any of the GPIOs, either edge or level. It then interrupts the CPU
+using GIC INT12.
+
+Required properties for the top level node:
+- #gpio-cells : Should be two. The first cell is the GPIO pin number and the
+   second cell specifies GPIO flags, as defined in <dt-bindings/gpio/gpio.h>.
+   Only the GPIO_ACTIVE_HIGH and GPIO_ACTIVE_LOW flags are supported.
+- #interrupt-cells : Specifies the number of cells needed to encode an
+   interrupt. Should be 2. The first cell defines the interrupt number,
+   the second encodes the triger flags encoded as described in
+   Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
+- compatible:
+  - "mediatek,mt7621-gpio" for Mediatek controllers
+- reg : Physical base address and length of the controller's registers
+- interrupt-parent : phandle of the parent interrupt controller.
+- interrupts : Interrupt specifier for the controllers interrupt.
+- interrupt-controller : Mark the device node as an interrupt controller.
+- gpio-controller : Marks the device node as a GPIO controller.
+
+Example:
+	gpio@600 {
+		#gpio-cells = <2>;
+		#interrupt-cells = <2>;
+		compatible = "mediatek,mt7621-gpio";
+		gpio-controller;
+		interrupt-controller;
+		reg = <0x600 0x100>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SHARED 12 IRQ_TYPE_LEVEL_HIGH>;
+	};
-- 
cgit v1.2.3


From de3c1e71d412d7e254e3eebeb82e260fb8513566 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 4 Jul 2018 18:54:57 +0200
Subject: clk: meson: expose GEN_CLK clkid

Expose GEN_CLK clock id

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 include/dt-bindings/clock/axg-clkc.h  | 1 +
 include/dt-bindings/clock/gxbb-clkc.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/dt-bindings/clock/axg-clkc.h b/include/dt-bindings/clock/axg-clkc.h
index 70371228b7e0..fd1f938c38d1 100644
--- a/include/dt-bindings/clock/axg-clkc.h
+++ b/include/dt-bindings/clock/axg-clkc.h
@@ -71,5 +71,6 @@
 #define CLKID_PCIE_CML_EN0			79
 #define CLKID_PCIE_CML_EN1			80
 #define CLKID_MIPI_ENABLE			81
+#define CLKID_GEN_CLK				84
 
 #endif /* __AXG_CLKC_H */
diff --git a/include/dt-bindings/clock/gxbb-clkc.h b/include/dt-bindings/clock/gxbb-clkc.h
index 7a892be90549..3979d48c025f 100644
--- a/include/dt-bindings/clock/gxbb-clkc.h
+++ b/include/dt-bindings/clock/gxbb-clkc.h
@@ -127,5 +127,6 @@
 #define CLKID_VAPB		140
 #define CLKID_VDEC_1		153
 #define CLKID_VDEC_HEVC		156
+#define CLKID_GEN_CLK		159
 
 #endif /* __GXBB_CLKC_H */
-- 
cgit v1.2.3


From 8599dc7dec874b137384714bfe3ddbbf5d4a614e Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Wed, 27 Jun 2018 17:06:41 +0200
Subject: printk: Clean up syslog_print_all()

syslog_print_all() is called twice. Once with a valid buffer
and once just to set the indexes.

Both variants are already handled separately. This patch just
makes it more obvious. It does not change the existing behavior.

Link: http://lkml.kernel.org/r/20180627150641.p56xyy6mdzvnfpig@pathway.suse.cz
Cc: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Cc: Namit Gupta <gupta.namit@samsung.com>
Cc: linux-kernel@vger.kernel.org
Cc: pankaj.m@samsung.com
Cc: a.sahrawat@samsung.com
Cc: himanshu.m@samsung.com
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 kernel/printk/printk.c | 20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 16b02cc51a14..fcc1992c040a 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1356,16 +1356,6 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 	u64 seq;
 	u32 idx;
 
-	if (!buf) {
-		if (clear) {
-			logbuf_lock_irq();
-			clear_seq = log_next_seq;
-			clear_idx = log_next_idx;
-			logbuf_unlock_irq();
-		}
-		return 0;
-	}
-
 	text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL);
 	if (!text)
 		return -ENOMEM;
@@ -1437,6 +1427,14 @@ static int syslog_print_all(char __user *buf, int size, bool clear)
 	return len;
 }
 
+static void syslog_clear(void)
+{
+	logbuf_lock_irq();
+	clear_seq = log_next_seq;
+	clear_idx = log_next_idx;
+	logbuf_unlock_irq();
+}
+
 int do_syslog(int type, char __user *buf, int len, int source)
 {
 	bool clear = false;
@@ -1481,7 +1479,7 @@ int do_syslog(int type, char __user *buf, int len, int source)
 		break;
 	/* Clear ring buffer */
 	case SYSLOG_ACTION_CLEAR:
-		syslog_print_all(NULL, 0, true);
+		syslog_clear();
 		break;
 	/* Disable logging to console */
 	case SYSLOG_ACTION_CONSOLE_OFF:
-- 
cgit v1.2.3


From 4ba9c3afda41213ec98c30053e32963892e6dc7c Mon Sep 17 00:00:00 2001
From: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Date: Thu, 5 Jul 2018 15:43:10 +0200
Subject: gpio: mt7621: Add a driver for MT7621

Add driver support for gpio of MT7621 SoC.

Signed-off-by: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Reviewed-by: NeilBrown <neil@brown.name>
[Switched wording WIDTH to STRIDE]
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig       |   8 ++
 drivers/gpio/Makefile      |   1 +
 drivers/gpio/gpio-mt7621.c | 335 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 344 insertions(+)
 create mode 100644 drivers/gpio/gpio-mt7621.c

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 71c0ab46f216..836aa2173e44 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -359,6 +359,14 @@ config GPIO_MPC8XXX
 	  Say Y here if you're going to use hardware that connects to the
 	  MPC512x/831x/834x/837x/8572/8610/QorIQ GPIOs.
 
+config GPIO_MT7621
+	bool "Mediatek MT7621 GPIO Support"
+	depends on SOC_MT7620 || SOC_MT7621 || COMPILE_TEST
+	select GPIO_GENERIC
+	select GPIOLIB_IRQCHIP
+	help
+	  Say yes here to support the Mediatek MT7621 SoC GPIO device
+
 config GPIO_MVEBU
 	def_bool y
 	depends on PLAT_ORION || ARCH_MVEBU
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 1324c8f966a7..fc77989371be 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -88,6 +88,7 @@ obj-$(CONFIG_GPIO_MOCKUP)      += gpio-mockup.o
 obj-$(CONFIG_GPIO_MPC5200)	+= gpio-mpc5200.o
 obj-$(CONFIG_GPIO_MPC8XXX)	+= gpio-mpc8xxx.o
 obj-$(CONFIG_GPIO_MSIC)		+= gpio-msic.o
+obj-$(CONFIG_GPIO_MT7621)		+= gpio-mt7621.o
 obj-$(CONFIG_GPIO_MVEBU)        += gpio-mvebu.o
 obj-$(CONFIG_GPIO_MXC)		+= gpio-mxc.o
 obj-$(CONFIG_GPIO_MXS)		+= gpio-mxs.o
diff --git a/drivers/gpio/gpio-mt7621.c b/drivers/gpio/gpio-mt7621.c
new file mode 100644
index 000000000000..14660d38dd1a
--- /dev/null
+++ b/drivers/gpio/gpio-mt7621.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2009-2011 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2013 John Crispin <blogic@openwrt.org>
+ */
+
+#include <linux/err.h>
+#include <linux/gpio/driver.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock.h>
+
+#define MTK_BANK_CNT	3
+#define MTK_BANK_WIDTH	32
+
+#define GPIO_BANK_STRIDE	0x04
+#define GPIO_REG_CTRL		0x00
+#define GPIO_REG_POL		0x10
+#define GPIO_REG_DATA		0x20
+#define GPIO_REG_DSET		0x30
+#define GPIO_REG_DCLR		0x40
+#define GPIO_REG_REDGE		0x50
+#define GPIO_REG_FEDGE		0x60
+#define GPIO_REG_HLVL		0x70
+#define GPIO_REG_LLVL		0x80
+#define GPIO_REG_STAT		0x90
+#define GPIO_REG_EDGE		0xA0
+
+struct mtk_gc {
+	struct gpio_chip chip;
+	spinlock_t lock;
+	int bank;
+	u32 rising;
+	u32 falling;
+	u32 hlevel;
+	u32 llevel;
+};
+
+/**
+ * struct mtk_data - state container for
+ * data of the platform driver. It is 3
+ * separate gpio-chip each one with its
+ * own irq_chip.
+ * @dev: device instance
+ * @gpio_membase: memory base address
+ * @gpio_irq: irq number from the device tree
+ * @gc_map: array of the gpio chips
+ */
+struct mtk_data {
+	struct device *dev;
+	void __iomem *gpio_membase;
+	int gpio_irq;
+	struct mtk_gc gc_map[MTK_BANK_CNT];
+};
+
+static inline struct mtk_gc *
+to_mediatek_gpio(struct gpio_chip *chip)
+{
+	return container_of(chip, struct mtk_gc, chip);
+}
+
+static inline void
+mtk_gpio_w32(struct mtk_gc *rg, u32 offset, u32 val)
+{
+	struct gpio_chip *gc = &rg->chip;
+	struct mtk_data *gpio_data = gpiochip_get_data(gc);
+
+	offset = (rg->bank * GPIO_BANK_STRIDE) + offset;
+	gc->write_reg(gpio_data->gpio_membase + offset, val);
+}
+
+static inline u32
+mtk_gpio_r32(struct mtk_gc *rg, u32 offset)
+{
+	struct gpio_chip *gc = &rg->chip;
+	struct mtk_data *gpio_data = gpiochip_get_data(gc);
+
+	offset = (rg->bank * GPIO_BANK_STRIDE) + offset;
+	return gc->read_reg(gpio_data->gpio_membase + offset);
+}
+
+static irqreturn_t
+mediatek_gpio_irq_handler(int irq, void *data)
+{
+	struct gpio_chip *gc = data;
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	irqreturn_t ret = IRQ_NONE;
+	unsigned long pending;
+	int bit;
+
+	pending = mtk_gpio_r32(rg, GPIO_REG_STAT);
+
+	for_each_set_bit(bit, &pending, MTK_BANK_WIDTH) {
+		u32 map = irq_find_mapping(gc->irq.domain, bit);
+
+		generic_handle_irq(map);
+		mtk_gpio_w32(rg, GPIO_REG_STAT, BIT(bit));
+		ret |= IRQ_HANDLED;
+	}
+
+	return ret;
+}
+
+static void
+mediatek_gpio_irq_unmask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	int pin = d->hwirq;
+	unsigned long flags;
+	u32 rise, fall, high, low;
+
+	spin_lock_irqsave(&rg->lock, flags);
+	rise = mtk_gpio_r32(rg, GPIO_REG_REDGE);
+	fall = mtk_gpio_r32(rg, GPIO_REG_FEDGE);
+	high = mtk_gpio_r32(rg, GPIO_REG_HLVL);
+	low = mtk_gpio_r32(rg, GPIO_REG_LLVL);
+	mtk_gpio_w32(rg, GPIO_REG_REDGE, rise | (BIT(pin) & rg->rising));
+	mtk_gpio_w32(rg, GPIO_REG_FEDGE, fall | (BIT(pin) & rg->falling));
+	mtk_gpio_w32(rg, GPIO_REG_HLVL, high | (BIT(pin) & rg->hlevel));
+	mtk_gpio_w32(rg, GPIO_REG_LLVL, low | (BIT(pin) & rg->llevel));
+	spin_unlock_irqrestore(&rg->lock, flags);
+}
+
+static void
+mediatek_gpio_irq_mask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	int pin = d->hwirq;
+	unsigned long flags;
+	u32 rise, fall, high, low;
+
+	spin_lock_irqsave(&rg->lock, flags);
+	rise = mtk_gpio_r32(rg, GPIO_REG_REDGE);
+	fall = mtk_gpio_r32(rg, GPIO_REG_FEDGE);
+	high = mtk_gpio_r32(rg, GPIO_REG_HLVL);
+	low = mtk_gpio_r32(rg, GPIO_REG_LLVL);
+	mtk_gpio_w32(rg, GPIO_REG_FEDGE, fall & ~BIT(pin));
+	mtk_gpio_w32(rg, GPIO_REG_REDGE, rise & ~BIT(pin));
+	mtk_gpio_w32(rg, GPIO_REG_HLVL, high & ~BIT(pin));
+	mtk_gpio_w32(rg, GPIO_REG_LLVL, low & ~BIT(pin));
+	spin_unlock_irqrestore(&rg->lock, flags);
+}
+
+static int
+mediatek_gpio_irq_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct mtk_gc *rg = to_mediatek_gpio(gc);
+	int pin = d->hwirq;
+	u32 mask = BIT(pin);
+
+	if (type == IRQ_TYPE_PROBE) {
+		if ((rg->rising | rg->falling |
+		     rg->hlevel | rg->llevel) & mask)
+			return 0;
+
+		type = IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING;
+	}
+
+	rg->rising &= ~mask;
+	rg->falling &= ~mask;
+	rg->hlevel &= ~mask;
+	rg->llevel &= ~mask;
+
+	switch (type & IRQ_TYPE_SENSE_MASK) {
+	case IRQ_TYPE_EDGE_BOTH:
+		rg->rising |= mask;
+		rg->falling |= mask;
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+		rg->rising |= mask;
+		break;
+	case IRQ_TYPE_EDGE_FALLING:
+		rg->falling |= mask;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+		rg->hlevel |= mask;
+		break;
+	case IRQ_TYPE_LEVEL_LOW:
+		rg->llevel |= mask;
+		break;
+	}
+
+	return 0;
+}
+
+static struct irq_chip mediatek_gpio_irq_chip = {
+	.irq_unmask		= mediatek_gpio_irq_unmask,
+	.irq_mask		= mediatek_gpio_irq_mask,
+	.irq_mask_ack		= mediatek_gpio_irq_mask,
+	.irq_set_type		= mediatek_gpio_irq_type,
+};
+
+static int
+mediatek_gpio_xlate(struct gpio_chip *chip,
+		    const struct of_phandle_args *spec, u32 *flags)
+{
+	int gpio = spec->args[0];
+	struct mtk_gc *rg = to_mediatek_gpio(chip);
+
+	if (rg->bank != gpio / MTK_BANK_WIDTH)
+		return -EINVAL;
+
+	if (flags)
+		*flags = spec->args[1];
+
+	return gpio % MTK_BANK_WIDTH;
+}
+
+static int
+mediatek_gpio_bank_probe(struct platform_device *pdev,
+			 struct device_node *node, int bank)
+{
+	struct mtk_data *gpio = dev_get_drvdata(&pdev->dev);
+	struct mtk_gc *rg;
+	void __iomem *dat, *set, *ctrl, *diro;
+	int ret;
+
+	rg = &gpio->gc_map[bank];
+	memset(rg, 0, sizeof(*rg));
+
+	spin_lock_init(&rg->lock);
+	rg->chip.of_node = node;
+	rg->bank = bank;
+
+	dat = gpio->gpio_membase + GPIO_REG_DATA +
+		(rg->bank * GPIO_BANK_STRIDE);
+	set = gpio->gpio_membase + GPIO_REG_DSET +
+		(rg->bank * GPIO_BANK_STRIDE);
+	ctrl = gpio->gpio_membase + GPIO_REG_DCLR +
+		(rg->bank * GPIO_BANK_STRIDE);
+	diro = gpio->gpio_membase + GPIO_REG_CTRL +
+		(rg->bank * GPIO_BANK_STRIDE);
+
+	ret = bgpio_init(&rg->chip, &pdev->dev, 4,
+			 dat, set, ctrl, diro, NULL, 0);
+	if (ret) {
+		dev_err(&pdev->dev, "bgpio_init() failed\n");
+		return ret;
+	}
+
+	rg->chip.of_gpio_n_cells = 2;
+	rg->chip.of_xlate = mediatek_gpio_xlate;
+	rg->chip.label = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-bank%d",
+					dev_name(&pdev->dev), bank);
+
+	ret = devm_gpiochip_add_data(&pdev->dev, &rg->chip, gpio);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "Could not register gpio %d, ret=%d\n",
+			rg->chip.ngpio, ret);
+		return ret;
+	}
+
+	if (gpio->gpio_irq) {
+		/*
+		 * Manually request the irq here instead of passing
+		 * a flow-handler to gpiochip_set_chained_irqchip,
+		 * because the irq is shared.
+		 */
+		ret = devm_request_irq(&pdev->dev, gpio->gpio_irq,
+				       mediatek_gpio_irq_handler, IRQF_SHARED,
+				       rg->chip.label, &rg->chip);
+
+		if (ret) {
+			dev_err(&pdev->dev, "Error requesting IRQ %d: %d\n",
+				gpio->gpio_irq, ret);
+			return ret;
+		}
+
+		ret = gpiochip_irqchip_add(&rg->chip, &mediatek_gpio_irq_chip,
+					   0, handle_simple_irq, IRQ_TYPE_NONE);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to add gpiochip_irqchip\n");
+			return ret;
+		}
+
+		gpiochip_set_chained_irqchip(&rg->chip, &mediatek_gpio_irq_chip,
+					     gpio->gpio_irq, NULL);
+	}
+
+	/* set polarity to low for all gpios */
+	mtk_gpio_w32(rg, GPIO_REG_POL, 0);
+
+	dev_info(&pdev->dev, "registering %d gpios\n", rg->chip.ngpio);
+
+	return 0;
+}
+
+static int
+mediatek_gpio_probe(struct platform_device *pdev)
+{
+	struct device_node *np = pdev->dev.of_node;
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	struct mtk_data *gpio_data;
+	int i;
+
+	gpio_data = devm_kzalloc(&pdev->dev, sizeof(*gpio_data), GFP_KERNEL);
+	if (!gpio_data)
+		return -ENOMEM;
+
+	gpio_data->gpio_membase = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(gpio_data->gpio_membase))
+		return PTR_ERR(gpio_data->gpio_membase);
+
+	gpio_data->gpio_irq = irq_of_parse_and_map(np, 0);
+	gpio_data->dev = &pdev->dev;
+	platform_set_drvdata(pdev, gpio_data);
+	mediatek_gpio_irq_chip.name = dev_name(&pdev->dev);
+
+	for (i = 0; i < MTK_BANK_CNT; i++)
+		mediatek_gpio_bank_probe(pdev, np, i);
+
+	return 0;
+}
+
+static const struct of_device_id mediatek_gpio_match[] = {
+	{ .compatible = "mediatek,mt7621-gpio" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, mediatek_gpio_match);
+
+static struct platform_driver mediatek_gpio_driver = {
+	.probe = mediatek_gpio_probe,
+	.driver = {
+		.name = "mt7621_gpio",
+		.of_match_table = mediatek_gpio_match,
+	},
+};
+
+builtin_platform_driver(mediatek_gpio_driver);
-- 
cgit v1.2.3


From 60e267f3fd73366feac2c0be5a50feb24118c2ca Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 19 Jun 2018 18:00:50 +0200
Subject: clk: meson: remove obsolete register access

The legacy method to access the hhi register space is not longer used.
We can safely drop it now.

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/axg.c  | 37 ++-----------------------------------
 drivers/clk/meson/gxbb.c | 36 ++----------------------------------
 2 files changed, 4 insertions(+), 69 deletions(-)

diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c
index bd4dbc696b88..3fb884db1b10 100644
--- a/drivers/clk/meson/axg.c
+++ b/drivers/clk/meson/axg.c
@@ -12,7 +12,6 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/init.h>
-#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
@@ -995,49 +994,17 @@ static const struct of_device_id clkc_match_table[] = {
 	{}
 };
 
-static const struct regmap_config clkc_regmap_config = {
-	.reg_bits       = 32,
-	.val_bits       = 32,
-	.reg_stride     = 4,
-};
-
 static int axg_clkc_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct resource *res;
-	void __iomem *clk_base = NULL;
 	struct regmap *map;
 	int ret, i;
 
 	/* Get the hhi system controller node if available */
 	map = syscon_node_to_regmap(of_get_parent(dev->of_node));
 	if (IS_ERR(map)) {
-		dev_err(dev,
-			"failed to get HHI regmap - Trying obsolete regs\n");
-
-		/*
-		 * FIXME: HHI registers should be accessed through
-		 * the appropriate system controller. This is required because
-		 * there is more than just clocks in this register space
-		 *
-		 * This fallback method is only provided temporarily until
-		 * all the platform DTs are properly using the syscon node
-		 */
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		if (!res)
-			return -EINVAL;
-
-
-		clk_base = devm_ioremap(dev, res->start, resource_size(res));
-		if (!clk_base) {
-			dev_err(dev, "Unable to map clk base\n");
-			return -ENXIO;
-		}
-
-		map = devm_regmap_init_mmio(dev, clk_base,
-					    &clkc_regmap_config);
-		if (IS_ERR(map))
-			return PTR_ERR(map);
+		dev_err(dev, "failed to get HHI regmap\n");
+		return PTR_ERR(map);
 	}
 
 	/* Populate regmap for the regmap backed clocks */
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 177fffb9ebef..297ebc391475 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -7,7 +7,6 @@
 #include <linux/clk.h>
 #include <linux/clk-provider.h>
 #include <linux/init.h>
-#include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/mfd/syscon.h>
 #include <linux/platform_device.h>
@@ -2228,17 +2227,9 @@ static const struct of_device_id clkc_match_table[] = {
 	{},
 };
 
-static const struct regmap_config clkc_regmap_config = {
-	.reg_bits       = 32,
-	.val_bits       = 32,
-	.reg_stride     = 4,
-};
-
 static int gxbb_clkc_probe(struct platform_device *pdev)
 {
 	const struct clkc_data *clkc_data;
-	struct resource *res;
-	void __iomem *clk_base;
 	struct regmap *map;
 	int ret, i;
 	struct device *dev = &pdev->dev;
@@ -2250,31 +2241,8 @@ static int gxbb_clkc_probe(struct platform_device *pdev)
 	/* Get the hhi system controller node if available */
 	map = syscon_node_to_regmap(of_get_parent(dev->of_node));
 	if (IS_ERR(map)) {
-		dev_err(dev,
-			"failed to get HHI regmap - Trying obsolete regs\n");
-
-		/*
-		 * FIXME: HHI registers should be accessed through
-		 * the appropriate system controller. This is required because
-		 * there is more than just clocks in this register space
-		 *
-		 * This fallback method is only provided temporarily until
-		 * all the platform DTs are properly using the syscon node
-		 */
-		res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-		if (!res)
-			return -EINVAL;
-
-		clk_base = devm_ioremap(dev, res->start, resource_size(res));
-		if (!clk_base) {
-			dev_err(dev, "Unable to map clk base\n");
-			return -ENXIO;
-		}
-
-		map = devm_regmap_init_mmio(dev, clk_base,
-					    &clkc_regmap_config);
-		if (IS_ERR(map))
-			return PTR_ERR(map);
+		dev_err(dev, "failed to get HHI regmap\n");
+		return PTR_ERR(map);
 	}
 
 	/* Populate regmap for the common regmap backed clocks */
-- 
cgit v1.2.3


From 443f2285789d2a4bf616b610c4cd8db839660a4a Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 22 May 2018 18:34:52 +0200
Subject: clk: meson: clean-up meson clock configuration

Clean the dependencies in meson clock Kconfig.
CLK_AMLOGIC should actually select CLK_REGMAP_MESON which it uses. Also,
each platform should select CLK_AMLOGIC, so everything is properly turned
on when the platform Kconfig enable each configuration flag

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/Kconfig | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig
index 815659eebea3..9d00809f07fc 100644
--- a/drivers/clk/meson/Kconfig
+++ b/drivers/clk/meson/Kconfig
@@ -1,13 +1,14 @@
 config COMMON_CLK_AMLOGIC
 	bool
-	depends on OF
 	depends on ARCH_MESON || COMPILE_TEST
+	select COMMON_CLK_REGMAP_MESON
 
 config COMMON_CLK_MESON_AO
 	bool
 	depends on OF
 	depends on ARCH_MESON || COMPILE_TEST
 	select COMMON_CLK_REGMAP_MESON
+	select RESET_CONTROLLER
 
 config COMMON_CLK_REGMAP_MESON
 	bool
@@ -15,9 +16,8 @@ config COMMON_CLK_REGMAP_MESON
 
 config COMMON_CLK_MESON8B
 	bool
-	depends on COMMON_CLK_AMLOGIC
+	select COMMON_CLK_AMLOGIC
 	select RESET_CONTROLLER
-	select COMMON_CLK_REGMAP_MESON
 	help
 	  Support for the clock controller on AmLogic S802 (Meson8),
 	  S805 (Meson8b) and S812 (Meson8m2) devices. Say Y if you
@@ -25,10 +25,8 @@ config COMMON_CLK_MESON8B
 
 config COMMON_CLK_GXBB
 	bool
-	depends on COMMON_CLK_AMLOGIC
-	select RESET_CONTROLLER
+	select COMMON_CLK_AMLOGIC
 	select COMMON_CLK_MESON_AO
-	select COMMON_CLK_REGMAP_MESON
 	select MFD_SYSCON
 	help
 	  Support for the clock controller on AmLogic S905 devices, aka gxbb.
@@ -36,10 +34,8 @@ config COMMON_CLK_GXBB
 
 config COMMON_CLK_AXG
 	bool
-	depends on COMMON_CLK_AMLOGIC
-	select RESET_CONTROLLER
+	select COMMON_CLK_AMLOGIC
 	select COMMON_CLK_MESON_AO
-	select COMMON_CLK_REGMAP_MESON
 	select MFD_SYSCON
 	help
 	  Support for the clock controller on AmLogic A113D devices, aka axg.
-- 
cgit v1.2.3


From 47f21315a6e4454ed9d8a450288a0989113e1e44 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 22 May 2018 18:34:53 +0200
Subject: clk: meson: add clk-phase clock driver

Add a driver based meson clk-regmap to control clock phase on
amlogic SoCs

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/Makefile    |  1 +
 drivers/clk/meson/clk-phase.c | 63 +++++++++++++++++++++++++++++++++++++++++++
 drivers/clk/meson/clkc.h      |  8 ++++++
 3 files changed, 72 insertions(+)
 create mode 100644 drivers/clk/meson/clk-phase.c

diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index d0d13aeb369a..162e4a6f5c55 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -3,6 +3,7 @@
 #
 
 obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-mpll.o clk-audio-divider.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-phase.o
 obj-$(CONFIG_COMMON_CLK_MESON_AO) += meson-aoclk.o
 obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
 obj-$(CONFIG_COMMON_CLK_GXBB)	 += gxbb.o gxbb-aoclk.o gxbb-aoclk-32k.o
diff --git a/drivers/clk/meson/clk-phase.c b/drivers/clk/meson/clk-phase.c
new file mode 100644
index 000000000000..cba43748ce3d
--- /dev/null
+++ b/drivers/clk/meson/clk-phase.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#include <linux/clk-provider.h>
+#include "clkc.h"
+
+#define phase_step(_width) (360 / (1 << (_width)))
+
+static inline struct meson_clk_phase_data *
+meson_clk_phase_data(struct clk_regmap *clk)
+{
+	return (struct meson_clk_phase_data *)clk->data;
+}
+
+int meson_clk_degrees_from_val(unsigned int val, unsigned int width)
+{
+	return phase_step(width) * val;
+}
+EXPORT_SYMBOL_GPL(meson_clk_degrees_from_val);
+
+unsigned int meson_clk_degrees_to_val(int degrees, unsigned int width)
+{
+	unsigned int val = DIV_ROUND_CLOSEST(degrees, phase_step(width));
+
+	/*
+	 * This last calculation is here for cases when degrees is rounded
+	 * to 360, in which case val == (1 << width).
+	 */
+	return val % (1 << width);
+}
+EXPORT_SYMBOL_GPL(meson_clk_degrees_to_val);
+
+static int meson_clk_phase_get_phase(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_phase_data *phase = meson_clk_phase_data(clk);
+	unsigned int val;
+
+	val = meson_parm_read(clk->map, &phase->ph);
+
+	return meson_clk_degrees_from_val(val, phase->ph.width);
+}
+
+static int meson_clk_phase_set_phase(struct clk_hw *hw, int degrees)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_phase_data *phase = meson_clk_phase_data(clk);
+	unsigned int val;
+
+	val = meson_clk_degrees_to_val(degrees, phase->ph.width);
+	meson_parm_write(clk->map, &phase->ph, val);
+
+	return 0;
+}
+
+const struct clk_ops meson_clk_phase_ops = {
+	.get_phase	= meson_clk_phase_get_phase,
+	.set_phase	= meson_clk_phase_set_phase,
+};
+EXPORT_SYMBOL_GPL(meson_clk_phase_ops);
diff --git a/drivers/clk/meson/clkc.h b/drivers/clk/meson/clkc.h
index 2fb084330ee9..fd520ccdd1be 100644
--- a/drivers/clk/meson/clkc.h
+++ b/drivers/clk/meson/clkc.h
@@ -96,6 +96,13 @@ struct meson_clk_audio_div_data {
 	u8 flags;
 };
 
+struct meson_clk_phase_data {
+	struct parm ph;
+};
+
+int meson_clk_degrees_from_val(unsigned int val, unsigned int width);
+unsigned int meson_clk_degrees_to_val(int degrees, unsigned int width);
+
 #define MESON_GATE(_name, _reg, _bit)					\
 struct clk_regmap _name = {						\
 	.data = &(struct clk_regmap_gate_data){				\
@@ -119,5 +126,6 @@ extern const struct clk_ops meson_clk_mpll_ro_ops;
 extern const struct clk_ops meson_clk_mpll_ops;
 extern const struct clk_ops meson_clk_audio_divider_ro_ops;
 extern const struct clk_ops meson_clk_audio_divider_ops;
+extern const struct clk_ops meson_clk_phase_ops;
 
 #endif /* __CLKC_H */
-- 
cgit v1.2.3


From e8dd9207763e0317ac256c78dcd50dca7826f2f6 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 22 May 2018 18:34:54 +0200
Subject: clk: meson: add triple phase clock driver

Add a driver to control the output of the sample clock generator found
in the axg audio clock controller.

The goal of this driver is to coherently control the phase provided to
the different element using the sample clock generator. This simplify
the usage of the sample clock generator a lot, without comprising the
ability of the SoC.

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/Kconfig        |  5 +++
 drivers/clk/meson/Makefile       |  1 +
 drivers/clk/meson/clk-triphase.c | 68 ++++++++++++++++++++++++++++++++++++++++
 drivers/clk/meson/clkc-audio.h   | 20 ++++++++++++
 4 files changed, 94 insertions(+)
 create mode 100644 drivers/clk/meson/clk-triphase.c
 create mode 100644 drivers/clk/meson/clkc-audio.h

diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig
index 9d00809f07fc..9ad95966aa3d 100644
--- a/drivers/clk/meson/Kconfig
+++ b/drivers/clk/meson/Kconfig
@@ -3,6 +3,11 @@ config COMMON_CLK_AMLOGIC
 	depends on ARCH_MESON || COMPILE_TEST
 	select COMMON_CLK_REGMAP_MESON
 
+config COMMON_CLK_AMLOGIC_AUDIO
+	bool
+	depends on ARCH_MESON || COMPILE_TEST
+	select COMMON_CLK_AMLOGIC
+
 config COMMON_CLK_MESON_AO
 	bool
 	depends on OF
diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index 162e4a6f5c55..74ec070b0974 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -4,6 +4,7 @@
 
 obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-mpll.o clk-audio-divider.o
 obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-phase.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC_AUDIO)	+= clk-triphase.o
 obj-$(CONFIG_COMMON_CLK_MESON_AO) += meson-aoclk.o
 obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
 obj-$(CONFIG_COMMON_CLK_GXBB)	 += gxbb.o gxbb-aoclk.o gxbb-aoclk-32k.o
diff --git a/drivers/clk/meson/clk-triphase.c b/drivers/clk/meson/clk-triphase.c
new file mode 100644
index 000000000000..4a59936251e5
--- /dev/null
+++ b/drivers/clk/meson/clk-triphase.c
@@ -0,0 +1,68 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#include <linux/clk-provider.h>
+#include "clkc-audio.h"
+
+/*
+ * This is a special clock for the audio controller.
+ * The phase of mst_sclk clock output can be controlled independently
+ * for the outside world (ph0), the tdmout (ph1) and tdmin (ph2).
+ * Controlling these 3 phases as just one makes things simpler and
+ * give the same clock view to all the element on the i2s bus.
+ * If necessary, we can still control the phase in the tdm block
+ * which makes these independent control redundant.
+ */
+static inline struct meson_clk_triphase_data *
+meson_clk_triphase_data(struct clk_regmap *clk)
+{
+	return (struct meson_clk_triphase_data *)clk->data;
+}
+
+static void meson_clk_triphase_sync(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_triphase_data *tph = meson_clk_triphase_data(clk);
+	unsigned int val;
+
+	/* Get phase 0 and sync it to phase 1 and 2 */
+	val = meson_parm_read(clk->map, &tph->ph0);
+	meson_parm_write(clk->map, &tph->ph1, val);
+	meson_parm_write(clk->map, &tph->ph2, val);
+}
+
+static int meson_clk_triphase_get_phase(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_triphase_data *tph = meson_clk_triphase_data(clk);
+	unsigned int val;
+
+	/* Phase are in sync, reading phase 0 is enough */
+	val = meson_parm_read(clk->map, &tph->ph0);
+
+	return meson_clk_degrees_from_val(val, tph->ph0.width);
+}
+
+static int meson_clk_triphase_set_phase(struct clk_hw *hw, int degrees)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_clk_triphase_data *tph = meson_clk_triphase_data(clk);
+	unsigned int val;
+
+	val = meson_clk_degrees_to_val(degrees, tph->ph0.width);
+	meson_parm_write(clk->map, &tph->ph0, val);
+	meson_parm_write(clk->map, &tph->ph1, val);
+	meson_parm_write(clk->map, &tph->ph2, val);
+
+	return 0;
+}
+
+const struct clk_ops meson_clk_triphase_ops = {
+	.init		= meson_clk_triphase_sync,
+	.get_phase	= meson_clk_triphase_get_phase,
+	.set_phase	= meson_clk_triphase_set_phase,
+};
+EXPORT_SYMBOL_GPL(meson_clk_triphase_ops);
diff --git a/drivers/clk/meson/clkc-audio.h b/drivers/clk/meson/clkc-audio.h
new file mode 100644
index 000000000000..286ff1201258
--- /dev/null
+++ b/drivers/clk/meson/clkc-audio.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef __MESON_CLKC_AUDIO_H
+#define __MESON_CLKC_AUDIO_H
+
+#include "clkc.h"
+
+struct meson_clk_triphase_data {
+	struct parm ph0;
+	struct parm ph1;
+	struct parm ph2;
+};
+
+extern const struct clk_ops meson_clk_triphase_ops;
+
+#endif /* __MESON_CLKC_AUDIO_H */
-- 
cgit v1.2.3


From 3054a55c5dd2619a597d6e96d8589318f2b210ad Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 22 May 2018 18:34:55 +0200
Subject: clk: meson: add axg audio sclk divider driver

Add a driver to control the clock divider found in the sample clock
generator of the axg audio clock controller.

The sclk divider accumulates specific features which make the generic
divider unsuitable to control it:
- zero based divider (div = val + 1), but zero value gates the clock,
  so minimum divider value is 2.
- lrclk variant may adjust the duty cycle depending the divider value
  and the 'hi' value.

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/Makefile     |   2 +-
 drivers/clk/meson/clkc-audio.h |   8 ++
 drivers/clk/meson/sclk-div.c   | 243 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 252 insertions(+), 1 deletion(-)
 create mode 100644 drivers/clk/meson/sclk-div.c

diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index 74ec070b0974..1574e3f0de5c 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -4,7 +4,7 @@
 
 obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-mpll.o clk-audio-divider.o
 obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-phase.o
-obj-$(CONFIG_COMMON_CLK_AMLOGIC_AUDIO)	+= clk-triphase.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC_AUDIO)	+= clk-triphase.o sclk-div.o
 obj-$(CONFIG_COMMON_CLK_MESON_AO) += meson-aoclk.o
 obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
 obj-$(CONFIG_COMMON_CLK_GXBB)	 += gxbb.o gxbb-aoclk.o gxbb-aoclk-32k.o
diff --git a/drivers/clk/meson/clkc-audio.h b/drivers/clk/meson/clkc-audio.h
index 286ff1201258..0a7c157ebf81 100644
--- a/drivers/clk/meson/clkc-audio.h
+++ b/drivers/clk/meson/clkc-audio.h
@@ -15,6 +15,14 @@ struct meson_clk_triphase_data {
 	struct parm ph2;
 };
 
+struct meson_sclk_div_data {
+	struct parm div;
+	struct parm hi;
+	unsigned int cached_div;
+	struct clk_duty cached_duty;
+};
+
 extern const struct clk_ops meson_clk_triphase_ops;
+extern const struct clk_ops meson_sclk_div_ops;
 
 #endif /* __MESON_CLKC_AUDIO_H */
diff --git a/drivers/clk/meson/sclk-div.c b/drivers/clk/meson/sclk-div.c
new file mode 100644
index 000000000000..bc64019b8eeb
--- /dev/null
+++ b/drivers/clk/meson/sclk-div.c
@@ -0,0 +1,243 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ *
+ * Sample clock generator divider:
+ * This HW divider gates with value 0 but is otherwise a zero based divider:
+ *
+ * val >= 1
+ * divider = val + 1
+ *
+ * The duty cycle may also be set for the LR clock variant. The duty cycle
+ * ratio is:
+ *
+ * hi = [0 - val]
+ * duty_cycle = (1 + hi) / (1 + val)
+ */
+
+#include "clkc-audio.h"
+
+static inline struct meson_sclk_div_data *
+meson_sclk_div_data(struct clk_regmap *clk)
+{
+	return (struct meson_sclk_div_data *)clk->data;
+}
+
+static int sclk_div_maxval(struct meson_sclk_div_data *sclk)
+{
+	return (1 << sclk->div.width) - 1;
+}
+
+static int sclk_div_maxdiv(struct meson_sclk_div_data *sclk)
+{
+	return sclk_div_maxval(sclk) + 1;
+}
+
+static int sclk_div_getdiv(struct clk_hw *hw, unsigned long rate,
+			   unsigned long prate, int maxdiv)
+{
+	int div = DIV_ROUND_CLOSEST_ULL((u64)prate, rate);
+
+	return clamp(div, 2, maxdiv);
+}
+
+static int sclk_div_bestdiv(struct clk_hw *hw, unsigned long rate,
+			    unsigned long *prate,
+			    struct meson_sclk_div_data *sclk)
+{
+	struct clk_hw *parent = clk_hw_get_parent(hw);
+	int bestdiv = 0, i;
+	unsigned long maxdiv, now, parent_now;
+	unsigned long best = 0, best_parent = 0;
+
+	if (!rate)
+		rate = 1;
+
+	maxdiv = sclk_div_maxdiv(sclk);
+
+	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT))
+		return sclk_div_getdiv(hw, rate, *prate, maxdiv);
+
+	/*
+	 * The maximum divider we can use without overflowing
+	 * unsigned long in rate * i below
+	 */
+	maxdiv = min(ULONG_MAX / rate, maxdiv);
+
+	for (i = 2; i <= maxdiv; i++) {
+		/*
+		 * It's the most ideal case if the requested rate can be
+		 * divided from parent clock without needing to change
+		 * parent rate, so return the divider immediately.
+		 */
+		if (rate * i == *prate)
+			return i;
+
+		parent_now = clk_hw_round_rate(parent, rate * i);
+		now = DIV_ROUND_UP_ULL((u64)parent_now, i);
+
+		if (abs(rate - now) < abs(rate - best)) {
+			bestdiv = i;
+			best = now;
+			best_parent = parent_now;
+		}
+	}
+
+	if (!bestdiv)
+		bestdiv = sclk_div_maxdiv(sclk);
+	else
+		*prate = best_parent;
+
+	return bestdiv;
+}
+
+static long sclk_div_round_rate(struct clk_hw *hw, unsigned long rate,
+				unsigned long *prate)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	int div;
+
+	div = sclk_div_bestdiv(hw, rate, prate, sclk);
+
+	return DIV_ROUND_UP_ULL((u64)*prate, div);
+}
+
+static void sclk_apply_ratio(struct clk_regmap *clk,
+			     struct meson_sclk_div_data *sclk)
+{
+	unsigned int hi = DIV_ROUND_CLOSEST(sclk->cached_div *
+					    sclk->cached_duty.num,
+					    sclk->cached_duty.den);
+
+	if (hi)
+		hi -= 1;
+
+	meson_parm_write(clk->map, &sclk->hi, hi);
+}
+
+static int sclk_div_set_duty_cycle(struct clk_hw *hw,
+				   struct clk_duty *duty)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	if (MESON_PARM_APPLICABLE(&sclk->hi)) {
+		memcpy(&sclk->cached_duty, duty, sizeof(*duty));
+		sclk_apply_ratio(clk, sclk);
+	}
+
+	return 0;
+}
+
+static int sclk_div_get_duty_cycle(struct clk_hw *hw,
+				   struct clk_duty *duty)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	int hi;
+
+	if (!MESON_PARM_APPLICABLE(&sclk->hi)) {
+		duty->num = 1;
+		duty->den = 2;
+		return 0;
+	}
+
+	hi = meson_parm_read(clk->map, &sclk->hi);
+	duty->num = hi + 1;
+	duty->den = sclk->cached_div;
+	return 0;
+}
+
+static void sclk_apply_divider(struct clk_regmap *clk,
+			       struct meson_sclk_div_data *sclk)
+{
+	if (MESON_PARM_APPLICABLE(&sclk->hi))
+		sclk_apply_ratio(clk, sclk);
+
+	meson_parm_write(clk->map, &sclk->div, sclk->cached_div - 1);
+}
+
+static int sclk_div_set_rate(struct clk_hw *hw, unsigned long rate,
+			     unsigned long prate)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	unsigned long maxdiv = sclk_div_maxdiv(sclk);
+
+	sclk->cached_div = sclk_div_getdiv(hw, rate, prate, maxdiv);
+
+	if (clk_hw_is_enabled(hw))
+		sclk_apply_divider(clk, sclk);
+
+	return 0;
+}
+
+static unsigned long sclk_div_recalc_rate(struct clk_hw *hw,
+					  unsigned long prate)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	return DIV_ROUND_UP_ULL((u64)prate, sclk->cached_div);
+}
+
+static int sclk_div_enable(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	sclk_apply_divider(clk, sclk);
+
+	return 0;
+}
+
+static void sclk_div_disable(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	meson_parm_write(clk->map, &sclk->div, 0);
+}
+
+static int sclk_div_is_enabled(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+
+	if (meson_parm_read(clk->map, &sclk->div))
+		return 1;
+
+	return 0;
+}
+
+static void sclk_div_init(struct clk_hw *hw)
+{
+	struct clk_regmap *clk = to_clk_regmap(hw);
+	struct meson_sclk_div_data *sclk = meson_sclk_div_data(clk);
+	unsigned int val;
+
+	val = meson_parm_read(clk->map, &sclk->div);
+
+	/* if the divider is initially disabled, assume max */
+	if (!val)
+		sclk->cached_div = sclk_div_maxdiv(sclk);
+	else
+		sclk->cached_div = val + 1;
+
+	sclk_div_get_duty_cycle(hw, &sclk->cached_duty);
+}
+
+const struct clk_ops meson_sclk_div_ops = {
+	.recalc_rate	= sclk_div_recalc_rate,
+	.round_rate	= sclk_div_round_rate,
+	.set_rate	= sclk_div_set_rate,
+	.enable		= sclk_div_enable,
+	.disable	= sclk_div_disable,
+	.is_enabled	= sclk_div_is_enabled,
+	.get_duty_cycle	= sclk_div_get_duty_cycle,
+	.set_duty_cycle = sclk_div_set_duty_cycle,
+	.init		= sclk_div_init,
+};
+EXPORT_SYMBOL_GPL(meson_sclk_div_ops);
-- 
cgit v1.2.3


From 1cd50181750f4bde1e4305812a8df5a5731ed28a Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 22 May 2018 18:34:57 +0200
Subject: clk: meson: axg: add the audio clock controller driver

The axg audio clock controller is the clock generation unit for the
amlogic audio subsystem of A113 based SoCs. It may be clocked by 8
different plls provided by the primary clock controller and also by
10 slave bit clocks and 10 slave sample clocks which may be provided
by external components, such as audio codecs, through the SoC pads.

It contains several muxes, dividers and gates which are fed into the
the different devices of the audio subsystem.

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/Kconfig     |   9 +
 drivers/clk/meson/Makefile    |   1 +
 drivers/clk/meson/axg-audio.c | 845 ++++++++++++++++++++++++++++++++++++++++++
 drivers/clk/meson/axg-audio.h | 127 +++++++
 4 files changed, 982 insertions(+)
 create mode 100644 drivers/clk/meson/axg-audio.c
 create mode 100644 drivers/clk/meson/axg-audio.h

diff --git a/drivers/clk/meson/Kconfig b/drivers/clk/meson/Kconfig
index 9ad95966aa3d..efaa70f682b4 100644
--- a/drivers/clk/meson/Kconfig
+++ b/drivers/clk/meson/Kconfig
@@ -45,3 +45,12 @@ config COMMON_CLK_AXG
 	help
 	  Support for the clock controller on AmLogic A113D devices, aka axg.
 	  Say Y if you want peripherals and CPU frequency scaling to work.
+
+config COMMON_CLK_AXG_AUDIO
+	tristate "Meson AXG Audio Clock Controller Driver"
+	depends on COMMON_CLK_AXG
+	select COMMON_CLK_AMLOGIC_AUDIO
+	select MFD_SYSCON
+	help
+	  Support for the audio clock controller on AmLogic A113D devices,
+	  aka axg, Say Y if you want audio subsystem to work.
diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index 1574e3f0de5c..fd97f5ba317d 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -9,4 +9,5 @@ obj-$(CONFIG_COMMON_CLK_MESON_AO) += meson-aoclk.o
 obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
 obj-$(CONFIG_COMMON_CLK_GXBB)	 += gxbb.o gxbb-aoclk.o gxbb-aoclk-32k.o
 obj-$(CONFIG_COMMON_CLK_AXG)	 += axg.o axg-aoclk.o
+obj-$(CONFIG_COMMON_CLK_AXG_AUDIO)	+= axg-audio.o
 obj-$(CONFIG_COMMON_CLK_REGMAP_MESON)	+= clk-regmap.o
diff --git a/drivers/clk/meson/axg-audio.c b/drivers/clk/meson/axg-audio.c
new file mode 100644
index 000000000000..a0ed41e73bde
--- /dev/null
+++ b/drivers/clk/meson/axg-audio.c
@@ -0,0 +1,845 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/init.h>
+#include <linux/of_device.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <linux/slab.h>
+
+#include "clkc-audio.h"
+#include "axg-audio.h"
+
+#define AXG_MST_IN_COUNT	8
+#define AXG_SLV_SCLK_COUNT	10
+#define AXG_SLV_LRCLK_COUNT	10
+
+#define AXG_AUD_GATE(_name, _reg, _bit, _pname, _iflags)		\
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct clk_regmap_gate_data){				\
+		.offset = (_reg),					\
+		.bit_idx = (_bit),					\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_"#_name,					\
+		.ops = &clk_regmap_gate_ops,				\
+		.parent_names = (const char *[]){ _pname },		\
+		.num_parents = 1,					\
+		.flags = CLK_DUTY_CYCLE_PARENT | (_iflags),		\
+	},								\
+}
+
+#define AXG_AUD_MUX(_name, _reg, _mask, _shift, _dflags, _pnames, _iflags) \
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct clk_regmap_mux_data){				\
+		.offset = (_reg),					\
+		.mask = (_mask),					\
+		.shift = (_shift),					\
+		.flags = (_dflags),					\
+	},								\
+	.hw.init = &(struct clk_init_data){				\
+		.name = "axg_"#_name,					\
+		.ops = &clk_regmap_mux_ops,				\
+		.parent_names = (_pnames),				\
+		.num_parents = ARRAY_SIZE(_pnames),			\
+		.flags = CLK_DUTY_CYCLE_PARENT | (_iflags),		\
+	},								\
+}
+
+#define AXG_AUD_DIV(_name, _reg, _shift, _width, _dflags, _pname, _iflags) \
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct clk_regmap_div_data){				\
+		.offset = (_reg),					\
+		.shift = (_shift),					\
+		.width = (_width),					\
+		.flags = (_dflags),					\
+	},								\
+	.hw.init = &(struct clk_init_data){				\
+		.name = "axg_"#_name,					\
+		.ops = &clk_regmap_divider_ops,				\
+		.parent_names = (const char *[]) { _pname },		\
+		.num_parents = 1,					\
+		.flags = (_iflags),					\
+	},								\
+}
+
+#define AXG_PCLK_GATE(_name, _bit)				\
+	AXG_AUD_GATE(_name, AUDIO_CLK_GATE_EN, _bit, "axg_audio_pclk", 0)
+
+/* Audio peripheral clocks */
+static AXG_PCLK_GATE(ddr_arb,	   0);
+static AXG_PCLK_GATE(pdm,	   1);
+static AXG_PCLK_GATE(tdmin_a,	   2);
+static AXG_PCLK_GATE(tdmin_b,	   3);
+static AXG_PCLK_GATE(tdmin_c,	   4);
+static AXG_PCLK_GATE(tdmin_lb,	   5);
+static AXG_PCLK_GATE(tdmout_a,	   6);
+static AXG_PCLK_GATE(tdmout_b,	   7);
+static AXG_PCLK_GATE(tdmout_c,	   8);
+static AXG_PCLK_GATE(frddr_a,	   9);
+static AXG_PCLK_GATE(frddr_b,	   10);
+static AXG_PCLK_GATE(frddr_c,	   11);
+static AXG_PCLK_GATE(toddr_a,	   12);
+static AXG_PCLK_GATE(toddr_b,	   13);
+static AXG_PCLK_GATE(toddr_c,	   14);
+static AXG_PCLK_GATE(loopback,	   15);
+static AXG_PCLK_GATE(spdifin,	   16);
+static AXG_PCLK_GATE(spdifout,	   17);
+static AXG_PCLK_GATE(resample,	   18);
+static AXG_PCLK_GATE(power_detect, 19);
+
+/* Audio Master Clocks */
+static const char * const mst_mux_parent_names[] = {
+	"axg_mst_in0", "axg_mst_in1", "axg_mst_in2", "axg_mst_in3",
+	"axg_mst_in4", "axg_mst_in5", "axg_mst_in6", "axg_mst_in7",
+};
+
+#define AXG_MST_MCLK_MUX(_name, _reg)					\
+	AXG_AUD_MUX(_name##_sel, _reg, 0x7, 24, CLK_MUX_ROUND_CLOSEST, \
+		    mst_mux_parent_names, CLK_SET_RATE_PARENT)
+
+static AXG_MST_MCLK_MUX(mst_a_mclk,   AUDIO_MCLK_A_CTRL);
+static AXG_MST_MCLK_MUX(mst_b_mclk,   AUDIO_MCLK_B_CTRL);
+static AXG_MST_MCLK_MUX(mst_c_mclk,   AUDIO_MCLK_C_CTRL);
+static AXG_MST_MCLK_MUX(mst_d_mclk,   AUDIO_MCLK_D_CTRL);
+static AXG_MST_MCLK_MUX(mst_e_mclk,   AUDIO_MCLK_E_CTRL);
+static AXG_MST_MCLK_MUX(mst_f_mclk,   AUDIO_MCLK_F_CTRL);
+static AXG_MST_MCLK_MUX(spdifout_clk, AUDIO_CLK_SPDIFOUT_CTRL);
+static AXG_MST_MCLK_MUX(spdifin_clk,  AUDIO_CLK_SPDIFIN_CTRL);
+static AXG_MST_MCLK_MUX(pdm_dclk,     AUDIO_CLK_PDMIN_CTRL0);
+static AXG_MST_MCLK_MUX(pdm_sysclk,   AUDIO_CLK_PDMIN_CTRL1);
+
+#define AXG_MST_MCLK_DIV(_name, _reg)					\
+	AXG_AUD_DIV(_name##_div, _reg, 0, 16, CLK_DIVIDER_ROUND_CLOSEST, \
+		    "axg_"#_name"_sel", CLK_SET_RATE_PARENT)		\
+
+static AXG_MST_MCLK_DIV(mst_a_mclk,   AUDIO_MCLK_A_CTRL);
+static AXG_MST_MCLK_DIV(mst_b_mclk,   AUDIO_MCLK_B_CTRL);
+static AXG_MST_MCLK_DIV(mst_c_mclk,   AUDIO_MCLK_C_CTRL);
+static AXG_MST_MCLK_DIV(mst_d_mclk,   AUDIO_MCLK_D_CTRL);
+static AXG_MST_MCLK_DIV(mst_e_mclk,   AUDIO_MCLK_E_CTRL);
+static AXG_MST_MCLK_DIV(mst_f_mclk,   AUDIO_MCLK_F_CTRL);
+static AXG_MST_MCLK_DIV(spdifout_clk, AUDIO_CLK_SPDIFOUT_CTRL);
+static AXG_MST_MCLK_DIV(spdifin_clk,  AUDIO_CLK_SPDIFIN_CTRL);
+static AXG_MST_MCLK_DIV(pdm_dclk,     AUDIO_CLK_PDMIN_CTRL0);
+static AXG_MST_MCLK_DIV(pdm_sysclk,   AUDIO_CLK_PDMIN_CTRL1);
+
+#define AXG_MST_MCLK_GATE(_name, _reg)					\
+	AXG_AUD_GATE(_name, _reg, 31,  "axg_"#_name"_div",		\
+		     CLK_SET_RATE_PARENT)
+
+static AXG_MST_MCLK_GATE(mst_a_mclk,   AUDIO_MCLK_A_CTRL);
+static AXG_MST_MCLK_GATE(mst_b_mclk,   AUDIO_MCLK_B_CTRL);
+static AXG_MST_MCLK_GATE(mst_c_mclk,   AUDIO_MCLK_C_CTRL);
+static AXG_MST_MCLK_GATE(mst_d_mclk,   AUDIO_MCLK_D_CTRL);
+static AXG_MST_MCLK_GATE(mst_e_mclk,   AUDIO_MCLK_E_CTRL);
+static AXG_MST_MCLK_GATE(mst_f_mclk,   AUDIO_MCLK_F_CTRL);
+static AXG_MST_MCLK_GATE(spdifout_clk, AUDIO_CLK_SPDIFOUT_CTRL);
+static AXG_MST_MCLK_GATE(spdifin_clk,  AUDIO_CLK_SPDIFIN_CTRL);
+static AXG_MST_MCLK_GATE(pdm_dclk,     AUDIO_CLK_PDMIN_CTRL0);
+static AXG_MST_MCLK_GATE(pdm_sysclk,   AUDIO_CLK_PDMIN_CTRL1);
+
+/* Sample Clocks */
+#define AXG_MST_SCLK_PRE_EN(_name, _reg)			\
+	AXG_AUD_GATE(mst_##_name##_sclk_pre_en, _reg, 31,	\
+		     "axg_mst_"#_name"_mclk", 0)
+
+static AXG_MST_SCLK_PRE_EN(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_SCLK_PRE_EN(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_AUD_SCLK_DIV(_name, _reg, _div_shift, _div_width,		\
+			 _hi_shift, _hi_width, _pname, _iflags)		\
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct meson_sclk_div_data) {				\
+		.div = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_div_shift),			\
+			.width   = (_div_width),			\
+		},							\
+		.hi = {							\
+			.reg_off = (_reg),				\
+			.shift   = (_hi_shift),				\
+			.width   = (_hi_width),				\
+		},							\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_"#_name,					\
+		.ops = &meson_sclk_div_ops,				\
+		.parent_names = (const char *[]) { _pname },		\
+		.num_parents = 1,					\
+		.flags = (_iflags),					\
+	},								\
+}
+
+#define AXG_MST_SCLK_DIV(_name, _reg)					\
+	AXG_AUD_SCLK_DIV(mst_##_name##_sclk_div, _reg, 20, 10, 0, 0,	\
+			 "axg_mst_"#_name"_sclk_pre_en",		\
+			 CLK_SET_RATE_PARENT)
+
+static AXG_MST_SCLK_DIV(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_SCLK_DIV(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_MST_SCLK_POST_EN(_name, _reg)				\
+	AXG_AUD_GATE(mst_##_name##_sclk_post_en, _reg, 30,		\
+		     "axg_mst_"#_name"_sclk_div", CLK_SET_RATE_PARENT)
+
+static AXG_MST_SCLK_POST_EN(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_SCLK_POST_EN(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_AUD_TRIPHASE(_name, _reg, _width, _shift0, _shift1, _shift2, \
+			 _pname, _iflags)				\
+struct clk_regmap axg_##_name = {					\
+	.data = &(struct meson_clk_triphase_data) {			\
+		.ph0 = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_shift0),				\
+			.width   = (_width),				\
+		},							\
+		.ph1 = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_shift1),				\
+			.width   = (_width),				\
+		},							\
+		.ph2 = {						\
+			.reg_off = (_reg),				\
+			.shift   = (_shift2),				\
+			.width   = (_width),				\
+		},							\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_"#_name,					\
+		.ops = &meson_clk_triphase_ops,				\
+		.parent_names = (const char *[]) { _pname },		\
+		.num_parents = 1,					\
+		.flags = CLK_DUTY_CYCLE_PARENT | (_iflags),		\
+	},								\
+}
+
+#define AXG_MST_SCLK(_name, _reg)					\
+	AXG_AUD_TRIPHASE(mst_##_name##_sclk, _reg, 1, 0, 2, 4,		\
+			 "axg_mst_"#_name"_sclk_post_en", CLK_SET_RATE_PARENT)
+
+static AXG_MST_SCLK(a, AUDIO_MST_A_SCLK_CTRL1);
+static AXG_MST_SCLK(b, AUDIO_MST_B_SCLK_CTRL1);
+static AXG_MST_SCLK(c, AUDIO_MST_C_SCLK_CTRL1);
+static AXG_MST_SCLK(d, AUDIO_MST_D_SCLK_CTRL1);
+static AXG_MST_SCLK(e, AUDIO_MST_E_SCLK_CTRL1);
+static AXG_MST_SCLK(f, AUDIO_MST_F_SCLK_CTRL1);
+
+#define AXG_MST_LRCLK_DIV(_name, _reg)					\
+	AXG_AUD_SCLK_DIV(mst_##_name##_lrclk_div, _reg, 0, 10, 10, 10,	\
+		    "axg_mst_"#_name"_sclk_post_en", 0)			\
+
+static AXG_MST_LRCLK_DIV(a, AUDIO_MST_A_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(b, AUDIO_MST_B_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(c, AUDIO_MST_C_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(d, AUDIO_MST_D_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(e, AUDIO_MST_E_SCLK_CTRL0);
+static AXG_MST_LRCLK_DIV(f, AUDIO_MST_F_SCLK_CTRL0);
+
+#define AXG_MST_LRCLK(_name, _reg)					\
+	AXG_AUD_TRIPHASE(mst_##_name##_lrclk, _reg, 1, 1, 3, 5,		\
+			 "axg_mst_"#_name"_lrclk_div", CLK_SET_RATE_PARENT)
+
+static AXG_MST_LRCLK(a, AUDIO_MST_A_SCLK_CTRL1);
+static AXG_MST_LRCLK(b, AUDIO_MST_B_SCLK_CTRL1);
+static AXG_MST_LRCLK(c, AUDIO_MST_C_SCLK_CTRL1);
+static AXG_MST_LRCLK(d, AUDIO_MST_D_SCLK_CTRL1);
+static AXG_MST_LRCLK(e, AUDIO_MST_E_SCLK_CTRL1);
+static AXG_MST_LRCLK(f, AUDIO_MST_F_SCLK_CTRL1);
+
+static const char * const tdm_sclk_parent_names[] = {
+	"axg_mst_a_sclk", "axg_mst_b_sclk", "axg_mst_c_sclk",
+	"axg_mst_d_sclk", "axg_mst_e_sclk", "axg_mst_f_sclk",
+	"axg_slv_sclk0", "axg_slv_sclk1", "axg_slv_sclk2",
+	"axg_slv_sclk3", "axg_slv_sclk4", "axg_slv_sclk5",
+	"axg_slv_sclk6", "axg_slv_sclk7", "axg_slv_sclk8",
+	"axg_slv_sclk9"
+};
+
+#define AXG_TDM_SCLK_MUX(_name, _reg)				\
+	AXG_AUD_MUX(tdm##_name##_sclk_sel, _reg, 0xf, 24,	\
+		    CLK_MUX_ROUND_CLOSEST,			\
+		    tdm_sclk_parent_names, 0)
+
+static AXG_TDM_SCLK_MUX(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK_MUX(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK_MUX(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK_MUX(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK_MUX(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK_MUX(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK_MUX(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+#define AXG_TDM_SCLK_PRE_EN(_name, _reg)				\
+	AXG_AUD_GATE(tdm##_name##_sclk_pre_en, _reg, 31,		\
+		     "axg_tdm"#_name"_sclk_sel", CLK_SET_RATE_PARENT)
+
+static AXG_TDM_SCLK_PRE_EN(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK_PRE_EN(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK_PRE_EN(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK_PRE_EN(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK_PRE_EN(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK_PRE_EN(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK_PRE_EN(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+#define AXG_TDM_SCLK_POST_EN(_name, _reg)				\
+	AXG_AUD_GATE(tdm##_name##_sclk_post_en, _reg, 30,		\
+		     "axg_tdm"#_name"_sclk_pre_en", CLK_SET_RATE_PARENT)
+
+static AXG_TDM_SCLK_POST_EN(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK_POST_EN(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK_POST_EN(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK_POST_EN(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK_POST_EN(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK_POST_EN(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK_POST_EN(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+#define AXG_TDM_SCLK(_name, _reg)					\
+	struct clk_regmap axg_tdm##_name##_sclk = {			\
+	.data = &(struct meson_clk_phase_data) {			\
+		.ph = {							\
+			.reg_off = (_reg),				\
+			.shift   = 29,					\
+			.width   = 1,					\
+		},							\
+	},								\
+	.hw.init = &(struct clk_init_data) {				\
+		.name = "axg_tdm"#_name"_sclk",				\
+		.ops = &meson_clk_phase_ops,				\
+		.parent_names = (const char *[])			\
+		{ "axg_tdm"#_name"_sclk_post_en" },			\
+		.num_parents = 1,					\
+		.flags = CLK_DUTY_CYCLE_PARENT | CLK_SET_RATE_PARENT,	\
+	},								\
+}
+
+static AXG_TDM_SCLK(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_SCLK(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_SCLK(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_SCLK(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_SCLK(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_SCLK(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_SCLK(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+static const char * const tdm_lrclk_parent_names[] = {
+	"axg_mst_a_lrclk", "axg_mst_b_lrclk", "axg_mst_c_lrclk",
+	"axg_mst_d_lrclk", "axg_mst_e_lrclk", "axg_mst_f_lrclk",
+	"axg_slv_lrclk0", "axg_slv_lrclk1", "axg_slv_lrclk2",
+	"axg_slv_lrclk3", "axg_slv_lrclk4", "axg_slv_lrclk5",
+	"axg_slv_lrclk6", "axg_slv_lrclk7", "axg_slv_lrclk8",
+	"axg_slv_lrclk9"
+};
+
+#define AXG_TDM_LRLCK(_name, _reg)		       \
+	AXG_AUD_MUX(tdm##_name##_lrclk, _reg, 0xf, 20, \
+		    CLK_MUX_ROUND_CLOSEST,	       \
+		    tdm_lrclk_parent_names, 0)
+
+static AXG_TDM_LRLCK(in_a,  AUDIO_CLK_TDMIN_A_CTRL);
+static AXG_TDM_LRLCK(in_b,  AUDIO_CLK_TDMIN_B_CTRL);
+static AXG_TDM_LRLCK(in_c,  AUDIO_CLK_TDMIN_C_CTRL);
+static AXG_TDM_LRLCK(in_lb, AUDIO_CLK_TDMIN_LB_CTRL);
+static AXG_TDM_LRLCK(out_a, AUDIO_CLK_TDMOUT_A_CTRL);
+static AXG_TDM_LRLCK(out_b, AUDIO_CLK_TDMOUT_B_CTRL);
+static AXG_TDM_LRLCK(out_c, AUDIO_CLK_TDMOUT_C_CTRL);
+
+/*
+ * Array of all clocks provided by this provider
+ * The input clocks of the controller will be populated at runtime
+ */
+static struct clk_hw_onecell_data axg_audio_hw_onecell_data = {
+	.hws = {
+		[AUD_CLKID_DDR_ARB]		= &axg_ddr_arb.hw,
+		[AUD_CLKID_PDM]			= &axg_pdm.hw,
+		[AUD_CLKID_TDMIN_A]		= &axg_tdmin_a.hw,
+		[AUD_CLKID_TDMIN_B]		= &axg_tdmin_b.hw,
+		[AUD_CLKID_TDMIN_C]		= &axg_tdmin_c.hw,
+		[AUD_CLKID_TDMIN_LB]		= &axg_tdmin_lb.hw,
+		[AUD_CLKID_TDMOUT_A]		= &axg_tdmout_a.hw,
+		[AUD_CLKID_TDMOUT_B]		= &axg_tdmout_b.hw,
+		[AUD_CLKID_TDMOUT_C]		= &axg_tdmout_c.hw,
+		[AUD_CLKID_FRDDR_A]		= &axg_frddr_a.hw,
+		[AUD_CLKID_FRDDR_B]		= &axg_frddr_b.hw,
+		[AUD_CLKID_FRDDR_C]		= &axg_frddr_c.hw,
+		[AUD_CLKID_TODDR_A]		= &axg_toddr_a.hw,
+		[AUD_CLKID_TODDR_B]		= &axg_toddr_b.hw,
+		[AUD_CLKID_TODDR_C]		= &axg_toddr_c.hw,
+		[AUD_CLKID_LOOPBACK]		= &axg_loopback.hw,
+		[AUD_CLKID_SPDIFIN]		= &axg_spdifin.hw,
+		[AUD_CLKID_SPDIFOUT]		= &axg_spdifout.hw,
+		[AUD_CLKID_RESAMPLE]		= &axg_resample.hw,
+		[AUD_CLKID_POWER_DETECT]	= &axg_power_detect.hw,
+		[AUD_CLKID_MST_A_MCLK_SEL]	= &axg_mst_a_mclk_sel.hw,
+		[AUD_CLKID_MST_B_MCLK_SEL]	= &axg_mst_b_mclk_sel.hw,
+		[AUD_CLKID_MST_C_MCLK_SEL]	= &axg_mst_c_mclk_sel.hw,
+		[AUD_CLKID_MST_D_MCLK_SEL]	= &axg_mst_d_mclk_sel.hw,
+		[AUD_CLKID_MST_E_MCLK_SEL]	= &axg_mst_e_mclk_sel.hw,
+		[AUD_CLKID_MST_F_MCLK_SEL]	= &axg_mst_f_mclk_sel.hw,
+		[AUD_CLKID_MST_A_MCLK_DIV]	= &axg_mst_a_mclk_div.hw,
+		[AUD_CLKID_MST_B_MCLK_DIV]	= &axg_mst_b_mclk_div.hw,
+		[AUD_CLKID_MST_C_MCLK_DIV]	= &axg_mst_c_mclk_div.hw,
+		[AUD_CLKID_MST_D_MCLK_DIV]	= &axg_mst_d_mclk_div.hw,
+		[AUD_CLKID_MST_E_MCLK_DIV]	= &axg_mst_e_mclk_div.hw,
+		[AUD_CLKID_MST_F_MCLK_DIV]	= &axg_mst_f_mclk_div.hw,
+		[AUD_CLKID_MST_A_MCLK]		= &axg_mst_a_mclk.hw,
+		[AUD_CLKID_MST_B_MCLK]		= &axg_mst_b_mclk.hw,
+		[AUD_CLKID_MST_C_MCLK]		= &axg_mst_c_mclk.hw,
+		[AUD_CLKID_MST_D_MCLK]		= &axg_mst_d_mclk.hw,
+		[AUD_CLKID_MST_E_MCLK]		= &axg_mst_e_mclk.hw,
+		[AUD_CLKID_MST_F_MCLK]		= &axg_mst_f_mclk.hw,
+		[AUD_CLKID_SPDIFOUT_CLK_SEL]	= &axg_spdifout_clk_sel.hw,
+		[AUD_CLKID_SPDIFOUT_CLK_DIV]	= &axg_spdifout_clk_div.hw,
+		[AUD_CLKID_SPDIFOUT_CLK]	= &axg_spdifout_clk.hw,
+		[AUD_CLKID_SPDIFIN_CLK_SEL]	= &axg_spdifin_clk_sel.hw,
+		[AUD_CLKID_SPDIFIN_CLK_DIV]	= &axg_spdifin_clk_div.hw,
+		[AUD_CLKID_SPDIFIN_CLK]		= &axg_spdifin_clk.hw,
+		[AUD_CLKID_PDM_DCLK_SEL]	= &axg_pdm_dclk_sel.hw,
+		[AUD_CLKID_PDM_DCLK_DIV]	= &axg_pdm_dclk_div.hw,
+		[AUD_CLKID_PDM_DCLK]		= &axg_pdm_dclk.hw,
+		[AUD_CLKID_PDM_SYSCLK_SEL]	= &axg_pdm_sysclk_sel.hw,
+		[AUD_CLKID_PDM_SYSCLK_DIV]	= &axg_pdm_sysclk_div.hw,
+		[AUD_CLKID_PDM_SYSCLK]		= &axg_pdm_sysclk.hw,
+		[AUD_CLKID_MST_A_SCLK_PRE_EN]	= &axg_mst_a_sclk_pre_en.hw,
+		[AUD_CLKID_MST_B_SCLK_PRE_EN]	= &axg_mst_b_sclk_pre_en.hw,
+		[AUD_CLKID_MST_C_SCLK_PRE_EN]	= &axg_mst_c_sclk_pre_en.hw,
+		[AUD_CLKID_MST_D_SCLK_PRE_EN]	= &axg_mst_d_sclk_pre_en.hw,
+		[AUD_CLKID_MST_E_SCLK_PRE_EN]	= &axg_mst_e_sclk_pre_en.hw,
+		[AUD_CLKID_MST_F_SCLK_PRE_EN]	= &axg_mst_f_sclk_pre_en.hw,
+		[AUD_CLKID_MST_A_SCLK_DIV]	= &axg_mst_a_sclk_div.hw,
+		[AUD_CLKID_MST_B_SCLK_DIV]	= &axg_mst_b_sclk_div.hw,
+		[AUD_CLKID_MST_C_SCLK_DIV]	= &axg_mst_c_sclk_div.hw,
+		[AUD_CLKID_MST_D_SCLK_DIV]	= &axg_mst_d_sclk_div.hw,
+		[AUD_CLKID_MST_E_SCLK_DIV]	= &axg_mst_e_sclk_div.hw,
+		[AUD_CLKID_MST_F_SCLK_DIV]	= &axg_mst_f_sclk_div.hw,
+		[AUD_CLKID_MST_A_SCLK_POST_EN]	= &axg_mst_a_sclk_post_en.hw,
+		[AUD_CLKID_MST_B_SCLK_POST_EN]	= &axg_mst_b_sclk_post_en.hw,
+		[AUD_CLKID_MST_C_SCLK_POST_EN]	= &axg_mst_c_sclk_post_en.hw,
+		[AUD_CLKID_MST_D_SCLK_POST_EN]	= &axg_mst_d_sclk_post_en.hw,
+		[AUD_CLKID_MST_E_SCLK_POST_EN]	= &axg_mst_e_sclk_post_en.hw,
+		[AUD_CLKID_MST_F_SCLK_POST_EN]	= &axg_mst_f_sclk_post_en.hw,
+		[AUD_CLKID_MST_A_SCLK]		= &axg_mst_a_sclk.hw,
+		[AUD_CLKID_MST_B_SCLK]		= &axg_mst_b_sclk.hw,
+		[AUD_CLKID_MST_C_SCLK]		= &axg_mst_c_sclk.hw,
+		[AUD_CLKID_MST_D_SCLK]		= &axg_mst_d_sclk.hw,
+		[AUD_CLKID_MST_E_SCLK]		= &axg_mst_e_sclk.hw,
+		[AUD_CLKID_MST_F_SCLK]		= &axg_mst_f_sclk.hw,
+		[AUD_CLKID_MST_A_LRCLK_DIV]	= &axg_mst_a_lrclk_div.hw,
+		[AUD_CLKID_MST_B_LRCLK_DIV]	= &axg_mst_b_lrclk_div.hw,
+		[AUD_CLKID_MST_C_LRCLK_DIV]	= &axg_mst_c_lrclk_div.hw,
+		[AUD_CLKID_MST_D_LRCLK_DIV]	= &axg_mst_d_lrclk_div.hw,
+		[AUD_CLKID_MST_E_LRCLK_DIV]	= &axg_mst_e_lrclk_div.hw,
+		[AUD_CLKID_MST_F_LRCLK_DIV]	= &axg_mst_f_lrclk_div.hw,
+		[AUD_CLKID_MST_A_LRCLK]		= &axg_mst_a_lrclk.hw,
+		[AUD_CLKID_MST_B_LRCLK]		= &axg_mst_b_lrclk.hw,
+		[AUD_CLKID_MST_C_LRCLK]		= &axg_mst_c_lrclk.hw,
+		[AUD_CLKID_MST_D_LRCLK]		= &axg_mst_d_lrclk.hw,
+		[AUD_CLKID_MST_E_LRCLK]		= &axg_mst_e_lrclk.hw,
+		[AUD_CLKID_MST_F_LRCLK]		= &axg_mst_f_lrclk.hw,
+		[AUD_CLKID_TDMIN_A_SCLK_SEL]	= &axg_tdmin_a_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_B_SCLK_SEL]	= &axg_tdmin_b_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_C_SCLK_SEL]	= &axg_tdmin_c_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK_SEL]	= &axg_tdmin_lb_sclk_sel.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK_SEL]	= &axg_tdmout_a_sclk_sel.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK_SEL]	= &axg_tdmout_b_sclk_sel.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK_SEL]	= &axg_tdmout_c_sclk_sel.hw,
+		[AUD_CLKID_TDMIN_A_SCLK_PRE_EN]	= &axg_tdmin_a_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_B_SCLK_PRE_EN]	= &axg_tdmin_b_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_C_SCLK_PRE_EN]	= &axg_tdmin_c_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK_PRE_EN] = &axg_tdmin_lb_sclk_pre_en.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK_PRE_EN] = &axg_tdmout_a_sclk_pre_en.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK_PRE_EN] = &axg_tdmout_b_sclk_pre_en.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK_PRE_EN] = &axg_tdmout_c_sclk_pre_en.hw,
+		[AUD_CLKID_TDMIN_A_SCLK_POST_EN] = &axg_tdmin_a_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_B_SCLK_POST_EN] = &axg_tdmin_b_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_C_SCLK_POST_EN] = &axg_tdmin_c_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK_POST_EN] = &axg_tdmin_lb_sclk_post_en.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK_POST_EN] = &axg_tdmout_a_sclk_post_en.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK_POST_EN] = &axg_tdmout_b_sclk_post_en.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK_POST_EN] = &axg_tdmout_c_sclk_post_en.hw,
+		[AUD_CLKID_TDMIN_A_SCLK]	= &axg_tdmin_a_sclk.hw,
+		[AUD_CLKID_TDMIN_B_SCLK]	= &axg_tdmin_b_sclk.hw,
+		[AUD_CLKID_TDMIN_C_SCLK]	= &axg_tdmin_c_sclk.hw,
+		[AUD_CLKID_TDMIN_LB_SCLK]	= &axg_tdmin_lb_sclk.hw,
+		[AUD_CLKID_TDMOUT_A_SCLK]	= &axg_tdmout_a_sclk.hw,
+		[AUD_CLKID_TDMOUT_B_SCLK]	= &axg_tdmout_b_sclk.hw,
+		[AUD_CLKID_TDMOUT_C_SCLK]	= &axg_tdmout_c_sclk.hw,
+		[AUD_CLKID_TDMIN_A_LRCLK]	= &axg_tdmin_a_lrclk.hw,
+		[AUD_CLKID_TDMIN_B_LRCLK]	= &axg_tdmin_b_lrclk.hw,
+		[AUD_CLKID_TDMIN_C_LRCLK]	= &axg_tdmin_c_lrclk.hw,
+		[AUD_CLKID_TDMIN_LB_LRCLK]	= &axg_tdmin_lb_lrclk.hw,
+		[AUD_CLKID_TDMOUT_A_LRCLK]	= &axg_tdmout_a_lrclk.hw,
+		[AUD_CLKID_TDMOUT_B_LRCLK]	= &axg_tdmout_b_lrclk.hw,
+		[AUD_CLKID_TDMOUT_C_LRCLK]	= &axg_tdmout_c_lrclk.hw,
+		[NR_CLKS] = NULL,
+	},
+	.num = NR_CLKS,
+};
+
+/* Convenience table to populate regmap in .probe() */
+static struct clk_regmap *const axg_audio_clk_regmaps[] = {
+	&axg_ddr_arb,
+	&axg_pdm,
+	&axg_tdmin_a,
+	&axg_tdmin_b,
+	&axg_tdmin_c,
+	&axg_tdmin_lb,
+	&axg_tdmout_a,
+	&axg_tdmout_b,
+	&axg_tdmout_c,
+	&axg_frddr_a,
+	&axg_frddr_b,
+	&axg_frddr_c,
+	&axg_toddr_a,
+	&axg_toddr_b,
+	&axg_toddr_c,
+	&axg_loopback,
+	&axg_spdifin,
+	&axg_spdifout,
+	&axg_resample,
+	&axg_power_detect,
+	&axg_mst_a_mclk_sel,
+	&axg_mst_b_mclk_sel,
+	&axg_mst_c_mclk_sel,
+	&axg_mst_d_mclk_sel,
+	&axg_mst_e_mclk_sel,
+	&axg_mst_f_mclk_sel,
+	&axg_mst_a_mclk_div,
+	&axg_mst_b_mclk_div,
+	&axg_mst_c_mclk_div,
+	&axg_mst_d_mclk_div,
+	&axg_mst_e_mclk_div,
+	&axg_mst_f_mclk_div,
+	&axg_mst_a_mclk,
+	&axg_mst_b_mclk,
+	&axg_mst_c_mclk,
+	&axg_mst_d_mclk,
+	&axg_mst_e_mclk,
+	&axg_mst_f_mclk,
+	&axg_spdifout_clk_sel,
+	&axg_spdifout_clk_div,
+	&axg_spdifout_clk,
+	&axg_spdifin_clk_sel,
+	&axg_spdifin_clk_div,
+	&axg_spdifin_clk,
+	&axg_pdm_dclk_sel,
+	&axg_pdm_dclk_div,
+	&axg_pdm_dclk,
+	&axg_pdm_sysclk_sel,
+	&axg_pdm_sysclk_div,
+	&axg_pdm_sysclk,
+	&axg_mst_a_sclk_pre_en,
+	&axg_mst_b_sclk_pre_en,
+	&axg_mst_c_sclk_pre_en,
+	&axg_mst_d_sclk_pre_en,
+	&axg_mst_e_sclk_pre_en,
+	&axg_mst_f_sclk_pre_en,
+	&axg_mst_a_sclk_div,
+	&axg_mst_b_sclk_div,
+	&axg_mst_c_sclk_div,
+	&axg_mst_d_sclk_div,
+	&axg_mst_e_sclk_div,
+	&axg_mst_f_sclk_div,
+	&axg_mst_a_sclk_post_en,
+	&axg_mst_b_sclk_post_en,
+	&axg_mst_c_sclk_post_en,
+	&axg_mst_d_sclk_post_en,
+	&axg_mst_e_sclk_post_en,
+	&axg_mst_f_sclk_post_en,
+	&axg_mst_a_sclk,
+	&axg_mst_b_sclk,
+	&axg_mst_c_sclk,
+	&axg_mst_d_sclk,
+	&axg_mst_e_sclk,
+	&axg_mst_f_sclk,
+	&axg_mst_a_lrclk_div,
+	&axg_mst_b_lrclk_div,
+	&axg_mst_c_lrclk_div,
+	&axg_mst_d_lrclk_div,
+	&axg_mst_e_lrclk_div,
+	&axg_mst_f_lrclk_div,
+	&axg_mst_a_lrclk,
+	&axg_mst_b_lrclk,
+	&axg_mst_c_lrclk,
+	&axg_mst_d_lrclk,
+	&axg_mst_e_lrclk,
+	&axg_mst_f_lrclk,
+	&axg_tdmin_a_sclk_sel,
+	&axg_tdmin_b_sclk_sel,
+	&axg_tdmin_c_sclk_sel,
+	&axg_tdmin_lb_sclk_sel,
+	&axg_tdmout_a_sclk_sel,
+	&axg_tdmout_b_sclk_sel,
+	&axg_tdmout_c_sclk_sel,
+	&axg_tdmin_a_sclk_pre_en,
+	&axg_tdmin_b_sclk_pre_en,
+	&axg_tdmin_c_sclk_pre_en,
+	&axg_tdmin_lb_sclk_pre_en,
+	&axg_tdmout_a_sclk_pre_en,
+	&axg_tdmout_b_sclk_pre_en,
+	&axg_tdmout_c_sclk_pre_en,
+	&axg_tdmin_a_sclk_post_en,
+	&axg_tdmin_b_sclk_post_en,
+	&axg_tdmin_c_sclk_post_en,
+	&axg_tdmin_lb_sclk_post_en,
+	&axg_tdmout_a_sclk_post_en,
+	&axg_tdmout_b_sclk_post_en,
+	&axg_tdmout_c_sclk_post_en,
+	&axg_tdmin_a_sclk,
+	&axg_tdmin_b_sclk,
+	&axg_tdmin_c_sclk,
+	&axg_tdmin_lb_sclk,
+	&axg_tdmout_a_sclk,
+	&axg_tdmout_b_sclk,
+	&axg_tdmout_c_sclk,
+	&axg_tdmin_a_lrclk,
+	&axg_tdmin_b_lrclk,
+	&axg_tdmin_c_lrclk,
+	&axg_tdmin_lb_lrclk,
+	&axg_tdmout_a_lrclk,
+	&axg_tdmout_b_lrclk,
+	&axg_tdmout_c_lrclk,
+};
+
+static struct clk *devm_clk_get_enable(struct device *dev, char *id)
+{
+	struct clk *clk;
+	int ret;
+
+	clk = devm_clk_get(dev, id);
+	if (IS_ERR(clk)) {
+		if (PTR_ERR(clk) != -EPROBE_DEFER)
+			dev_err(dev, "failed to get %s", id);
+		return clk;
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		dev_err(dev, "failed to enable %s", id);
+		return ERR_PTR(ret);
+	}
+
+	ret = devm_add_action_or_reset(dev,
+				       (void(*)(void *))clk_disable_unprepare,
+				       clk);
+	if (ret) {
+		dev_err(dev, "failed to add reset action on %s", id);
+		return ERR_PTR(ret);
+	}
+
+	return clk;
+}
+
+static const struct clk_ops axg_clk_no_ops = {};
+
+static struct clk_hw *axg_clk_hw_register_bypass(struct device *dev,
+						 const char *name,
+						 const char *parent_name)
+{
+	struct clk_hw *hw;
+	struct clk_init_data init;
+	char *clk_name;
+	int ret;
+
+	hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL);
+	if (!hw)
+		return ERR_PTR(-ENOMEM);
+
+	clk_name = kasprintf(GFP_KERNEL, "axg_%s", name);
+	if (!clk_name)
+		return ERR_PTR(-ENOMEM);
+
+	init.name = clk_name;
+	init.ops = &axg_clk_no_ops;
+	init.flags = 0;
+	init.parent_names = parent_name ? &parent_name : NULL;
+	init.num_parents = parent_name ? 1 : 0;
+	hw->init = &init;
+
+	ret = devm_clk_hw_register(dev, hw);
+	kfree(clk_name);
+
+	return ret ? ERR_PTR(ret) : hw;
+}
+
+static int axg_register_clk_hw_input(struct device *dev,
+				     const char *name,
+				     unsigned int clkid)
+{
+	struct clk *parent_clk = devm_clk_get(dev, name);
+	struct clk_hw *hw = NULL;
+
+	if (IS_ERR(parent_clk)) {
+		int err = PTR_ERR(parent_clk);
+
+		/* It is ok if an input clock is missing */
+		if (err == -ENOENT) {
+			dev_dbg(dev, "%s not provided", name);
+		} else {
+			if (err != -EPROBE_DEFER)
+				dev_err(dev, "failed to get %s clock", name);
+			return err;
+		}
+	} else {
+		hw = axg_clk_hw_register_bypass(dev, name,
+						__clk_get_name(parent_clk));
+	}
+
+	if (IS_ERR(hw)) {
+		dev_err(dev, "failed to register %s clock", name);
+		return PTR_ERR(hw);
+	}
+
+	axg_audio_hw_onecell_data.hws[clkid] = hw;
+	return 0;
+}
+
+static int axg_register_clk_hw_inputs(struct device *dev,
+				      const char *basename,
+				      unsigned int count,
+				      unsigned int clkid)
+{
+	char *name;
+	int i, ret;
+
+	for (i = 0; i < count; i++) {
+		name = kasprintf(GFP_KERNEL, "%s%d", basename, i);
+		if (!name)
+			return -ENOMEM;
+
+		ret = axg_register_clk_hw_input(dev, name, clkid + i);
+		kfree(name);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct regmap_config axg_audio_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= AUDIO_CLK_PDMIN_CTRL1,
+};
+
+static int axg_audio_clkc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct regmap *map;
+	struct resource *res;
+	void __iomem *regs;
+	struct clk *clk;
+	struct clk_hw *hw;
+	int ret, i;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	map = devm_regmap_init_mmio(dev, regs, &axg_audio_regmap_cfg);
+	if (IS_ERR(map)) {
+		dev_err(dev, "failed to init regmap: %ld\n", PTR_ERR(map));
+		return PTR_ERR(map);
+	}
+
+	/* Get the mandatory peripheral clock */
+	clk = devm_clk_get_enable(dev, "pclk");
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
+
+	ret = device_reset(dev);
+	if (ret) {
+		dev_err(dev, "failed to reset device\n");
+		return ret;
+	}
+
+	/* Register the peripheral input clock */
+	hw = axg_clk_hw_register_bypass(dev, "audio_pclk",
+					__clk_get_name(clk));
+	if (IS_ERR(hw))
+		return PTR_ERR(hw);
+
+	axg_audio_hw_onecell_data.hws[AUD_CLKID_PCLK] = hw;
+
+	/* Register optional input master clocks */
+	ret = axg_register_clk_hw_inputs(dev, "mst_in",
+					 AXG_MST_IN_COUNT,
+					 AUD_CLKID_MST0);
+	if (ret)
+		return ret;
+
+	/* Register optional input slave sclks */
+	ret = axg_register_clk_hw_inputs(dev, "slv_sclk",
+					 AXG_SLV_SCLK_COUNT,
+					 AUD_CLKID_SLV_SCLK0);
+	if (ret)
+		return ret;
+
+	/* Register optional input slave lrclks */
+	ret = axg_register_clk_hw_inputs(dev, "slv_lrclk",
+					 AXG_SLV_LRCLK_COUNT,
+					 AUD_CLKID_SLV_LRCLK0);
+	if (ret)
+		return ret;
+
+	/* Populate regmap for the regmap backed clocks */
+	for (i = 0; i < ARRAY_SIZE(axg_audio_clk_regmaps); i++)
+		axg_audio_clk_regmaps[i]->map = map;
+
+	/* Take care to skip the registered input clocks */
+	for (i = AUD_CLKID_DDR_ARB; i < axg_audio_hw_onecell_data.num; i++) {
+		hw = axg_audio_hw_onecell_data.hws[i];
+		/* array might be sparse */
+		if (!hw)
+			continue;
+
+		ret = devm_clk_hw_register(dev, hw);
+		if (ret) {
+			dev_err(dev, "failed to register clock %s\n",
+				hw->init->name);
+			return ret;
+		}
+	}
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get,
+					   &axg_audio_hw_onecell_data);
+}
+
+static const struct of_device_id clkc_match_table[] = {
+	{ .compatible = "amlogic,axg-audio-clkc" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, clkc_match_table);
+
+static struct platform_driver axg_audio_driver = {
+	.probe		= axg_audio_clkc_probe,
+	.driver		= {
+		.name	= "axg-audio-clkc",
+		.of_match_table = clkc_match_table,
+	},
+};
+module_platform_driver(axg_audio_driver);
+
+MODULE_DESCRIPTION("Amlogic A113x Audio Clock driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/clk/meson/axg-audio.h b/drivers/clk/meson/axg-audio.h
new file mode 100644
index 000000000000..7191b39c9d65
--- /dev/null
+++ b/drivers/clk/meson/axg-audio.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef __AXG_AUDIO_CLKC_H
+#define __AXG_AUDIO_CLKC_H
+
+/*
+ * Audio Clock  register offsets
+ *
+ * Register offsets from the datasheet must be multiplied by 4 before
+ * to get the right offset
+ */
+#define AUDIO_CLK_GATE_EN	0x000
+#define AUDIO_MCLK_A_CTRL	0x004
+#define AUDIO_MCLK_B_CTRL	0x008
+#define AUDIO_MCLK_C_CTRL	0x00C
+#define AUDIO_MCLK_D_CTRL	0x010
+#define AUDIO_MCLK_E_CTRL	0x014
+#define AUDIO_MCLK_F_CTRL	0x018
+#define AUDIO_MST_A_SCLK_CTRL0	0x040
+#define AUDIO_MST_A_SCLK_CTRL1	0x044
+#define AUDIO_MST_B_SCLK_CTRL0	0x048
+#define AUDIO_MST_B_SCLK_CTRL1	0x04C
+#define AUDIO_MST_C_SCLK_CTRL0	0x050
+#define AUDIO_MST_C_SCLK_CTRL1	0x054
+#define AUDIO_MST_D_SCLK_CTRL0	0x058
+#define AUDIO_MST_D_SCLK_CTRL1	0x05C
+#define AUDIO_MST_E_SCLK_CTRL0	0x060
+#define AUDIO_MST_E_SCLK_CTRL1	0x064
+#define AUDIO_MST_F_SCLK_CTRL0	0x068
+#define AUDIO_MST_F_SCLK_CTRL1	0x06C
+#define AUDIO_CLK_TDMIN_A_CTRL	0x080
+#define AUDIO_CLK_TDMIN_B_CTRL	0x084
+#define AUDIO_CLK_TDMIN_C_CTRL	0x088
+#define AUDIO_CLK_TDMIN_LB_CTRL 0x08C
+#define AUDIO_CLK_TDMOUT_A_CTRL 0x090
+#define AUDIO_CLK_TDMOUT_B_CTRL 0x094
+#define AUDIO_CLK_TDMOUT_C_CTRL 0x098
+#define AUDIO_CLK_SPDIFIN_CTRL	0x09C
+#define AUDIO_CLK_SPDIFOUT_CTRL 0x0A0
+#define AUDIO_CLK_RESAMPLE_CTRL 0x0A4
+#define AUDIO_CLK_LOCKER_CTRL	0x0A8
+#define AUDIO_CLK_PDMIN_CTRL0	0x0AC
+#define AUDIO_CLK_PDMIN_CTRL1	0x0B0
+
+/*
+ * CLKID index values
+ * These indices are entirely contrived and do not map onto the hardware.
+ */
+
+#define AUD_CLKID_PCLK			0
+#define AUD_CLKID_MST0			1
+#define AUD_CLKID_MST1			2
+#define AUD_CLKID_MST2			3
+#define AUD_CLKID_MST3			4
+#define AUD_CLKID_MST4			5
+#define AUD_CLKID_MST5			6
+#define AUD_CLKID_MST6			7
+#define AUD_CLKID_MST7			8
+#define AUD_CLKID_MST_A_MCLK_SEL	59
+#define AUD_CLKID_MST_B_MCLK_SEL	60
+#define AUD_CLKID_MST_C_MCLK_SEL	61
+#define AUD_CLKID_MST_D_MCLK_SEL	62
+#define AUD_CLKID_MST_E_MCLK_SEL	63
+#define AUD_CLKID_MST_F_MCLK_SEL	64
+#define AUD_CLKID_MST_A_MCLK_DIV	65
+#define AUD_CLKID_MST_B_MCLK_DIV	66
+#define AUD_CLKID_MST_C_MCLK_DIV	67
+#define AUD_CLKID_MST_D_MCLK_DIV	68
+#define AUD_CLKID_MST_E_MCLK_DIV	69
+#define AUD_CLKID_MST_F_MCLK_DIV	70
+#define AUD_CLKID_SPDIFOUT_CLK_SEL	71
+#define AUD_CLKID_SPDIFOUT_CLK_DIV	72
+#define AUD_CLKID_SPDIFIN_CLK_SEL	73
+#define AUD_CLKID_SPDIFIN_CLK_DIV	74
+#define AUD_CLKID_PDM_DCLK_SEL		75
+#define AUD_CLKID_PDM_DCLK_DIV		76
+#define AUD_CLKID_PDM_SYSCLK_SEL	77
+#define AUD_CLKID_PDM_SYSCLK_DIV	78
+#define AUD_CLKID_MST_A_SCLK_PRE_EN	92
+#define AUD_CLKID_MST_B_SCLK_PRE_EN	93
+#define AUD_CLKID_MST_C_SCLK_PRE_EN	94
+#define AUD_CLKID_MST_D_SCLK_PRE_EN	95
+#define AUD_CLKID_MST_E_SCLK_PRE_EN	96
+#define AUD_CLKID_MST_F_SCLK_PRE_EN	97
+#define AUD_CLKID_MST_A_SCLK_DIV	98
+#define AUD_CLKID_MST_B_SCLK_DIV	99
+#define AUD_CLKID_MST_C_SCLK_DIV	100
+#define AUD_CLKID_MST_D_SCLK_DIV	101
+#define AUD_CLKID_MST_E_SCLK_DIV	102
+#define AUD_CLKID_MST_F_SCLK_DIV	103
+#define AUD_CLKID_MST_A_SCLK_POST_EN	104
+#define AUD_CLKID_MST_B_SCLK_POST_EN	105
+#define AUD_CLKID_MST_C_SCLK_POST_EN	106
+#define AUD_CLKID_MST_D_SCLK_POST_EN	107
+#define AUD_CLKID_MST_E_SCLK_POST_EN	108
+#define AUD_CLKID_MST_F_SCLK_POST_EN	109
+#define AUD_CLKID_MST_A_LRCLK_DIV	110
+#define AUD_CLKID_MST_B_LRCLK_DIV	111
+#define AUD_CLKID_MST_C_LRCLK_DIV	112
+#define AUD_CLKID_MST_D_LRCLK_DIV	113
+#define AUD_CLKID_MST_E_LRCLK_DIV	114
+#define AUD_CLKID_MST_F_LRCLK_DIV	115
+#define AUD_CLKID_TDMIN_A_SCLK_PRE_EN	137
+#define AUD_CLKID_TDMIN_B_SCLK_PRE_EN	138
+#define AUD_CLKID_TDMIN_C_SCLK_PRE_EN	139
+#define AUD_CLKID_TDMIN_LB_SCLK_PRE_EN	140
+#define AUD_CLKID_TDMOUT_A_SCLK_PRE_EN	141
+#define AUD_CLKID_TDMOUT_B_SCLK_PRE_EN	142
+#define AUD_CLKID_TDMOUT_C_SCLK_PRE_EN	143
+#define AUD_CLKID_TDMIN_A_SCLK_POST_EN	144
+#define AUD_CLKID_TDMIN_B_SCLK_POST_EN	145
+#define AUD_CLKID_TDMIN_C_SCLK_POST_EN	146
+#define AUD_CLKID_TDMIN_LB_SCLK_POST_EN	147
+#define AUD_CLKID_TDMOUT_A_SCLK_POST_EN	148
+#define AUD_CLKID_TDMOUT_B_SCLK_POST_EN	149
+#define AUD_CLKID_TDMOUT_C_SCLK_POST_EN	150
+
+/* include the CLKIDs which are part of the DT bindings */
+#include <dt-bindings/clock/axg-audio-clkc.h>
+
+#define NR_CLKS	151
+
+#endif /*__AXG_AUDIO_CLKC_H */
-- 
cgit v1.2.3


From 9799d5ae003c05f0db5d6c5884183a388b74ba3c Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 20 Jun 2018 12:06:09 +0200
Subject: clk: meson: stop rate propagation for audio clocks

It is actually a lot easier to setup the PLL with carefully chosen rates
than relying on CCF clock propagation for this audio use case.
This way, we can make sure we will always be able to provide the common
audio clock rates, while having the PLL in the optimal operating range.

For this, we stop the rate propagation at the mux picking the
PLL and let it round to the closest matching PLL.

Doing so, we can use the generic divider for the i2s clock.
clk-audio-divider is no longer required. It was a (poor) attempt
to use CCF rate propagation while making sure the PLL rate would
be high enough to work with audio use cases.

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/gxbb.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 297ebc391475..894a6adaa17a 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -970,28 +970,26 @@ static struct clk_regmap gxbb_cts_amclk_sel = {
 		.mask = 0x3,
 		.shift = 9,
 		.table = (u32[]){ 1, 2, 3 },
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cts_amclk_sel",
 		.ops = &clk_regmap_mux_ops,
 		.parent_names = (const char *[]){ "mpll0", "mpll1", "mpll2" },
 		.num_parents = 3,
-		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
 static struct clk_regmap gxbb_cts_amclk_div = {
-	.data = &(struct meson_clk_audio_div_data){
-		.div = {
-			.reg_off = HHI_AUD_CLK_CNTL,
-			.shift   = 0,
-			.width   = 8,
-		},
+	.data = &(struct clk_regmap_div_data) {
+		.offset = HHI_AUD_CLK_CNTL,
+		.shift = 0,
+		.width = 8,
 		.flags = CLK_DIVIDER_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data){
 		.name = "cts_amclk_div",
-		.ops = &meson_clk_audio_divider_ops,
+		.ops = &clk_regmap_divider_ops,
 		.parent_names = (const char *[]){ "cts_amclk_sel" },
 		.num_parents = 1,
 		.flags = CLK_SET_RATE_PARENT,
@@ -1018,13 +1016,13 @@ static struct clk_regmap gxbb_cts_mclk_i958_sel = {
 		.mask = 0x3,
 		.shift = 25,
 		.table = (u32[]){ 1, 2, 3 },
+		.flags = CLK_MUX_ROUND_CLOSEST,
 	},
 	.hw.init = &(struct clk_init_data) {
 		.name = "cts_mclk_i958_sel",
 		.ops = &clk_regmap_mux_ops,
 		.parent_names = (const char *[]){ "mpll0", "mpll1", "mpll2" },
 		.num_parents = 3,
-		.flags = CLK_SET_RATE_PARENT,
 	},
 };
 
-- 
cgit v1.2.3


From 85ddc1a32cace10bc8b7dc5dfae98b6a1785fc0c Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 20 Jun 2018 12:06:10 +0200
Subject: clk: meson: remove unused clk-audio-divider driver

clk-audio-divider is no longer used, we can remove it.

Acked-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/Makefile            |   3 +-
 drivers/clk/meson/clk-audio-divider.c | 110 ----------------------------------
 drivers/clk/meson/clkc.h              |   7 ---
 3 files changed, 1 insertion(+), 119 deletions(-)
 delete mode 100644 drivers/clk/meson/clk-audio-divider.c

diff --git a/drivers/clk/meson/Makefile b/drivers/clk/meson/Makefile
index fd97f5ba317d..72ec8c40d848 100644
--- a/drivers/clk/meson/Makefile
+++ b/drivers/clk/meson/Makefile
@@ -2,8 +2,7 @@
 # Makefile for Meson specific clk
 #
 
-obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-mpll.o clk-audio-divider.o
-obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-phase.o
+obj-$(CONFIG_COMMON_CLK_AMLOGIC) += clk-pll.o clk-mpll.o clk-phase.o
 obj-$(CONFIG_COMMON_CLK_AMLOGIC_AUDIO)	+= clk-triphase.o sclk-div.o
 obj-$(CONFIG_COMMON_CLK_MESON_AO) += meson-aoclk.o
 obj-$(CONFIG_COMMON_CLK_MESON8B) += meson8b.o
diff --git a/drivers/clk/meson/clk-audio-divider.c b/drivers/clk/meson/clk-audio-divider.c
deleted file mode 100644
index e4cf96ba704e..000000000000
--- a/drivers/clk/meson/clk-audio-divider.c
+++ /dev/null
@@ -1,110 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (c) 2017 AmLogic, Inc.
- * Author: Jerome Brunet <jbrunet@baylibre.com>
- */
-
-/*
- * i2s master clock divider: The algorithm of the generic clk-divider used with
- * a very precise clock parent such as the mpll tends to select a low divider
- * factor. This gives poor results with this particular divider, especially with
- * high frequencies (> 100 MHz)
- *
- * This driver try to select the maximum possible divider with the rate the
- * upstream clock can provide.
- */
-
-#include <linux/clk-provider.h>
-#include "clkc.h"
-
-static inline struct meson_clk_audio_div_data *
-meson_clk_audio_div_data(struct clk_regmap *clk)
-{
-	return (struct meson_clk_audio_div_data *)clk->data;
-}
-
-static int _div_round(unsigned long parent_rate, unsigned long rate,
-		      unsigned long flags)
-{
-	if (flags & CLK_DIVIDER_ROUND_CLOSEST)
-		return DIV_ROUND_CLOSEST_ULL((u64)parent_rate, rate);
-
-	return DIV_ROUND_UP_ULL((u64)parent_rate, rate);
-}
-
-static int _get_val(unsigned long parent_rate, unsigned long rate)
-{
-	return DIV_ROUND_UP_ULL((u64)parent_rate, rate) - 1;
-}
-
-static int _valid_divider(unsigned int width, int divider)
-{
-	int max_divider = 1 << width;
-
-	return clamp(divider, 1, max_divider);
-}
-
-static unsigned long audio_divider_recalc_rate(struct clk_hw *hw,
-					       unsigned long parent_rate)
-{
-	struct clk_regmap *clk = to_clk_regmap(hw);
-	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
-	unsigned long divider;
-
-	divider = meson_parm_read(clk->map, &adiv->div) + 1;
-
-	return DIV_ROUND_UP_ULL((u64)parent_rate, divider);
-}
-
-static long audio_divider_round_rate(struct clk_hw *hw,
-				     unsigned long rate,
-				     unsigned long *parent_rate)
-{
-	struct clk_regmap *clk = to_clk_regmap(hw);
-	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
-	unsigned long max_prate;
-	int divider;
-
-	if (!(clk_hw_get_flags(hw) & CLK_SET_RATE_PARENT)) {
-		divider = _div_round(*parent_rate, rate, adiv->flags);
-		divider = _valid_divider(adiv->div.width, divider);
-		return DIV_ROUND_UP_ULL((u64)*parent_rate, divider);
-	}
-
-	/* Get the maximum parent rate */
-	max_prate = clk_hw_round_rate(clk_hw_get_parent(hw), ULONG_MAX);
-
-	/* Get the corresponding rounded down divider */
-	divider = max_prate / rate;
-	divider = _valid_divider(adiv->div.width, divider);
-
-	/* Get actual rate of the parent */
-	*parent_rate = clk_hw_round_rate(clk_hw_get_parent(hw),
-					 divider * rate);
-
-	return DIV_ROUND_UP_ULL((u64)*parent_rate, divider);
-}
-
-static int audio_divider_set_rate(struct clk_hw *hw,
-				  unsigned long rate,
-				  unsigned long parent_rate)
-{
-	struct clk_regmap *clk = to_clk_regmap(hw);
-	struct meson_clk_audio_div_data *adiv = meson_clk_audio_div_data(clk);
-	int val = _get_val(parent_rate, rate);
-
-	meson_parm_write(clk->map, &adiv->div, val);
-
-	return 0;
-}
-
-const struct clk_ops meson_clk_audio_divider_ro_ops = {
-	.recalc_rate	= audio_divider_recalc_rate,
-	.round_rate	= audio_divider_round_rate,
-};
-
-const struct clk_ops meson_clk_audio_divider_ops = {
-	.recalc_rate	= audio_divider_recalc_rate,
-	.round_rate	= audio_divider_round_rate,
-	.set_rate	= audio_divider_set_rate,
-};
diff --git a/drivers/clk/meson/clkc.h b/drivers/clk/meson/clkc.h
index fd520ccdd1be..24cec16b6038 100644
--- a/drivers/clk/meson/clkc.h
+++ b/drivers/clk/meson/clkc.h
@@ -91,11 +91,6 @@ struct meson_clk_mpll_data {
 
 #define CLK_MESON_MPLL_ROUND_CLOSEST	BIT(0)
 
-struct meson_clk_audio_div_data {
-	struct parm div;
-	u8 flags;
-};
-
 struct meson_clk_phase_data {
 	struct parm ph;
 };
@@ -124,8 +119,6 @@ extern const struct clk_ops meson_clk_pll_ops;
 extern const struct clk_ops meson_clk_cpu_ops;
 extern const struct clk_ops meson_clk_mpll_ro_ops;
 extern const struct clk_ops meson_clk_mpll_ops;
-extern const struct clk_ops meson_clk_audio_divider_ro_ops;
-extern const struct clk_ops meson_clk_audio_divider_ops;
 extern const struct clk_ops meson_clk_phase_ops;
 
 #endif /* __CLKC_H */
-- 
cgit v1.2.3


From cddcb20b2bb36401e038d0ae41ba8a956d91f82e Mon Sep 17 00:00:00 2001
From: Yixun Lan <yixun.lan@amlogic.com>
Date: Mon, 2 Jul 2018 21:31:18 +0000
Subject: clk: meson-axg: add clocks required by pcie driver

Adding clocks for the pcie driver. Due to the ASIC design,
the pcie controller re-use part of the mipi clock logic,
so the mipi clock is also added.

Tested-by: Jianxin Qin <jianxin.qin@amlogic.com>
Signed-off-by: Yixun Lan <yixun.lan@amlogic.com>
[amended to remove unnecessary locales]
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/axg.c | 145 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/clk/meson/axg.h |   6 +-
 2 files changed, 150 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c
index 3fb884db1b10..2d458092884a 100644
--- a/drivers/clk/meson/axg.c
+++ b/drivers/clk/meson/axg.c
@@ -625,6 +625,137 @@ static struct clk_regmap axg_mpll3 = {
 	},
 };
 
+static const struct pll_rate_table axg_pcie_pll_rate_table[] = {
+	{
+		.rate	= 100000000,
+		.m	= 200,
+		.n	= 3,
+		.od	= 1,
+		.od2	= 3,
+	},
+	{ /* sentinel */ },
+};
+
+static const struct reg_sequence axg_pcie_init_regs[] = {
+	{ .reg = HHI_PCIE_PLL_CNTL,	.def = 0x400106c8 },
+	{ .reg = HHI_PCIE_PLL_CNTL1,	.def = 0x0084a2aa },
+	{ .reg = HHI_PCIE_PLL_CNTL2,	.def = 0xb75020be },
+	{ .reg = HHI_PCIE_PLL_CNTL3,	.def = 0x0a47488e },
+	{ .reg = HHI_PCIE_PLL_CNTL4,	.def = 0xc000004d },
+	{ .reg = HHI_PCIE_PLL_CNTL5,	.def = 0x00078000 },
+	{ .reg = HHI_PCIE_PLL_CNTL6,	.def = 0x002323c6 },
+};
+
+static struct clk_regmap axg_pcie_pll = {
+	.data = &(struct meson_clk_pll_data){
+		.m = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 0,
+			.width   = 9,
+		},
+		.n = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 9,
+			.width   = 5,
+		},
+		.od = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 16,
+			.width   = 2,
+		},
+		.od2 = {
+			.reg_off = HHI_PCIE_PLL_CNTL6,
+			.shift   = 6,
+			.width   = 2,
+		},
+		.frac = {
+			.reg_off = HHI_PCIE_PLL_CNTL1,
+			.shift   = 0,
+			.width   = 12,
+		},
+		.l = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 31,
+			.width   = 1,
+		},
+		.rst = {
+			.reg_off = HHI_PCIE_PLL_CNTL,
+			.shift   = 29,
+			.width   = 1,
+		},
+		.table = axg_pcie_pll_rate_table,
+		.init_regs = axg_pcie_init_regs,
+		.init_count = ARRAY_SIZE(axg_pcie_init_regs),
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "pcie_pll",
+		.ops = &meson_clk_pll_ops,
+		.parent_names = (const char *[]){ "xtal" },
+		.num_parents = 1,
+	},
+};
+
+static struct clk_regmap axg_pcie_mux = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.mask = 0x1,
+		.shift = 2,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "pcie_mux",
+		.ops = &clk_regmap_mux_ops,
+		.parent_names = (const char *[]){ "mpll3", "pcie_pll" },
+		.num_parents = 2,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_pcie_ref = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.mask = 0x1,
+		.shift = 1,
+		/* skip the parent 0, reserved for debug */
+		.table = (u32[]){ 1 },
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "pcie_ref",
+		.ops = &clk_regmap_mux_ops,
+		.parent_names = (const char *[]){ "pcie_mux" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_pcie_cml_en0 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.bit_idx = 4,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "pcie_cml_en0",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "pcie_ref" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+
+	},
+};
+
+static struct clk_regmap axg_pcie_cml_en1 = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_PCIE_PLL_CNTL6,
+		.bit_idx = 3,
+	},
+	.hw.init = &(struct clk_init_data) {
+		.name = "pcie_cml_en1",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "pcie_ref" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 static u32 mux_table_clk81[]	= { 0, 2, 3, 4, 5, 6, 7 };
 static const char * const clk81_parent_names[] = {
 	"xtal", "fclk_div7", "mpll1", "mpll2", "fclk_div4",
@@ -820,6 +951,7 @@ static MESON_GATE(axg_mmc_pclk, HHI_GCLK_MPEG2, 11);
 static MESON_GATE(axg_vpu_intr, HHI_GCLK_MPEG2, 25);
 static MESON_GATE(axg_sec_ahb_ahb3_bridge, HHI_GCLK_MPEG2, 26);
 static MESON_GATE(axg_gic, HHI_GCLK_MPEG2, 30);
+static MESON_GATE(axg_mipi_enable, HHI_MIPI_CNTL0, 29);
 
 /* Always On (AO) domain gates */
 
@@ -909,6 +1041,13 @@ static struct clk_hw_onecell_data axg_hw_onecell_data = {
 		[CLKID_FCLK_DIV4_DIV]		= &axg_fclk_div4_div.hw,
 		[CLKID_FCLK_DIV5_DIV]		= &axg_fclk_div5_div.hw,
 		[CLKID_FCLK_DIV7_DIV]		= &axg_fclk_div7_div.hw,
+		[CLKID_PCIE_PLL]		= &axg_pcie_pll.hw,
+		[CLKID_PCIE_MUX]		= &axg_pcie_mux.hw,
+		[CLKID_PCIE_REF]		= &axg_pcie_ref.hw,
+		[CLKID_PCIE_CML_EN0]		= &axg_pcie_cml_en0.hw,
+		[CLKID_PCIE_CML_EN1]		= &axg_pcie_cml_en1.hw,
+		[CLKID_MIPI_ENABLE]		= &axg_mipi_enable.hw,
+
 		[NR_CLKS]			= NULL,
 	},
 	.num = NR_CLKS,
@@ -987,6 +1126,12 @@ static struct clk_regmap *const axg_clk_regmaps[] = {
 	&axg_fclk_div4,
 	&axg_fclk_div5,
 	&axg_fclk_div7,
+	&axg_pcie_pll,
+	&axg_pcie_mux,
+	&axg_pcie_ref,
+	&axg_pcie_cml_en0,
+	&axg_pcie_cml_en1,
+	&axg_mipi_enable,
 };
 
 static const struct of_device_id clkc_match_table[] = {
diff --git a/drivers/clk/meson/axg.h b/drivers/clk/meson/axg.h
index b421df6a7ea0..6e55ebd6c77d 100644
--- a/drivers/clk/meson/axg.h
+++ b/drivers/clk/meson/axg.h
@@ -16,6 +16,7 @@
  * Register offsets from the data sheet must be multiplied by 4 before
  * adding them to the base address to get the right value.
  */
+#define HHI_MIPI_CNTL0			0x00
 #define HHI_GP0_PLL_CNTL		0x40
 #define HHI_GP0_PLL_CNTL2		0x44
 #define HHI_GP0_PLL_CNTL3		0x48
@@ -127,8 +128,11 @@
 #define CLKID_FCLK_DIV4_DIV			73
 #define CLKID_FCLK_DIV5_DIV			74
 #define CLKID_FCLK_DIV7_DIV			75
+#define CLKID_PCIE_PLL				76
+#define CLKID_PCIE_MUX				77
+#define CLKID_PCIE_REF				78
 
-#define NR_CLKS					76
+#define NR_CLKS					82
 
 /* include the CLKIDs that have been made part of the DT binding */
 #include <dt-bindings/clock/axg-clkc.h>
-- 
cgit v1.2.3


From 80d396b5118f448cb2206a509aba6917691a835e Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 4 Jul 2018 18:54:56 +0200
Subject: clk: meson: gxbb: remove HHI_GEN_CLK_CTNL duplicate definition

HHI_GEN_CLK_CTNL is defined twice, just remove the duplicate definition

Fixes: 738f66d3211d ("clk: gxbb: add AmLogic GXBB clk controller driver")
Acked-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/gxbb.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
index ec1a812bf1fd..df6c21d368c6 100644
--- a/drivers/clk/meson/gxbb.h
+++ b/drivers/clk/meson/gxbb.h
@@ -66,7 +66,6 @@
 #define HHI_USB_CLK_CNTL		0x220 /* 0x88 offset in data sheet */
 #define HHI_32K_CLK_CNTL		0x224 /* 0x89 offset in data sheet */
 #define HHI_GEN_CLK_CNTL		0x228 /* 0x8a offset in data sheet */
-#define HHI_GEN_CLK_CNTL		0x228 /* 0x8a offset in data sheet */
 
 #define HHI_PCM_CLK_CNTL		0x258 /* 0x96 offset in data sheet */
 #define HHI_NAND_CLK_CNTL		0x25C /* 0x97 offset in data sheet */
-- 
cgit v1.2.3


From 7df533a7e3d2216e860ecf147ae8cee49bf133e9 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 4 Jul 2018 18:54:58 +0200
Subject: clk: meson: add gen_clk

GEN_CLK is able to route several internal clocks to one of the SoC
pads. In the future, even more clocks could be made accessible using
cts_msr_clk - the clock measure block.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
---
 drivers/clk/meson/axg.c  | 64 +++++++++++++++++++++++++++++++++++++++++++++-
 drivers/clk/meson/axg.h  |  4 ++-
 drivers/clk/meson/gxbb.c | 66 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/clk/meson/gxbb.h |  4 ++-
 4 files changed, 135 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/meson/axg.c b/drivers/clk/meson/axg.c
index 2d458092884a..00ce62ad6416 100644
--- a/drivers/clk/meson/axg.c
+++ b/drivers/clk/meson/axg.c
@@ -909,6 +909,63 @@ static struct clk_regmap axg_sd_emmc_c_clk0 = {
 	},
 };
 
+static u32 mux_table_gen_clk[]	= { 0, 4, 5, 6, 7, 8,
+				    9, 10, 11, 13, 14, };
+static const char * const gen_clk_parent_names[] = {
+	"xtal", "hifi_pll", "mpll0", "mpll1", "mpll2", "mpll3",
+	"fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7", "gp0_pll",
+};
+
+static struct clk_regmap axg_gen_clk_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.mask = 0xf,
+		.shift = 12,
+		.table = mux_table_gen_clk,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_sel",
+		.ops = &clk_regmap_mux_ops,
+		/*
+		 * bits 15:12 selects from 14 possible parents:
+		 * xtal, [rtc_oscin_i], [sys_cpu_div16], [ddr_dpll_pt],
+		 * hifi_pll, mpll0, mpll1, mpll2, mpll3, fdiv4,
+		 * fdiv3, fdiv5, [cts_msr_clk], fdiv7, gp0_pll
+		 */
+		.parent_names = gen_clk_parent_names,
+		.num_parents = ARRAY_SIZE(gen_clk_parent_names),
+	},
+};
+
+static struct clk_regmap axg_gen_clk_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.shift = 0,
+		.width = 11,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_names = (const char *[]){ "gen_clk_sel" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap axg_gen_clk = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.bit_idx = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "gen_clk_div" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 /* Everything Else (EE) domain gates */
 static MESON_GATE(axg_ddr, HHI_GCLK_MPEG0, 0);
 static MESON_GATE(axg_audio_locker, HHI_GCLK_MPEG0, 2);
@@ -1047,7 +1104,9 @@ static struct clk_hw_onecell_data axg_hw_onecell_data = {
 		[CLKID_PCIE_CML_EN0]		= &axg_pcie_cml_en0.hw,
 		[CLKID_PCIE_CML_EN1]		= &axg_pcie_cml_en1.hw,
 		[CLKID_MIPI_ENABLE]		= &axg_mipi_enable.hw,
-
+		[CLKID_GEN_CLK_SEL]		= &axg_gen_clk_sel.hw,
+		[CLKID_GEN_CLK_DIV]		= &axg_gen_clk_div.hw,
+		[CLKID_GEN_CLK]			= &axg_gen_clk.hw,
 		[NR_CLKS]			= NULL,
 	},
 	.num = NR_CLKS,
@@ -1132,6 +1191,9 @@ static struct clk_regmap *const axg_clk_regmaps[] = {
 	&axg_pcie_cml_en0,
 	&axg_pcie_cml_en1,
 	&axg_mipi_enable,
+	&axg_gen_clk_sel,
+	&axg_gen_clk_div,
+	&axg_gen_clk,
 };
 
 static const struct of_device_id clkc_match_table[] = {
diff --git a/drivers/clk/meson/axg.h b/drivers/clk/meson/axg.h
index 6e55ebd6c77d..1d04144a1b2c 100644
--- a/drivers/clk/meson/axg.h
+++ b/drivers/clk/meson/axg.h
@@ -131,8 +131,10 @@
 #define CLKID_PCIE_PLL				76
 #define CLKID_PCIE_MUX				77
 #define CLKID_PCIE_REF				78
+#define CLKID_GEN_CLK_SEL			82
+#define CLKID_GEN_CLK_DIV			83
 
-#define NR_CLKS					82
+#define NR_CLKS					85
 
 /* include the CLKIDs that have been made part of the DT binding */
 #include <dt-bindings/clock/axg-clkc.h>
diff --git a/drivers/clk/meson/gxbb.c b/drivers/clk/meson/gxbb.c
index 894a6adaa17a..86d3ae58e84c 100644
--- a/drivers/clk/meson/gxbb.c
+++ b/drivers/clk/meson/gxbb.c
@@ -1624,6 +1624,63 @@ static struct clk_regmap gxbb_vdec_hevc = {
 	},
 };
 
+static u32 mux_table_gen_clk[]	= { 0, 4, 5, 6, 7, 8,
+				    9, 10, 11, 13, 14, };
+static const char * const gen_clk_parent_names[] = {
+	"xtal", "vdec_1", "vdec_hevc", "mpll0", "mpll1", "mpll2",
+	"fclk_div4", "fclk_div3", "fclk_div5", "fclk_div7", "gp0_pll",
+};
+
+static struct clk_regmap gxbb_gen_clk_sel = {
+	.data = &(struct clk_regmap_mux_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.mask = 0xf,
+		.shift = 12,
+		.table = mux_table_gen_clk,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_sel",
+		.ops = &clk_regmap_mux_ops,
+		/*
+		 * bits 15:12 selects from 14 possible parents:
+		 * xtal, [rtc_oscin_i], [sys_cpu_div16], [ddr_dpll_pt],
+		 * vid_pll, vid2_pll (hevc), mpll0, mpll1, mpll2, fdiv4,
+		 * fdiv3, fdiv5, [cts_msr_clk], fdiv7, gp0_pll
+		 */
+		.parent_names = gen_clk_parent_names,
+		.num_parents = ARRAY_SIZE(gen_clk_parent_names),
+	},
+};
+
+static struct clk_regmap gxbb_gen_clk_div = {
+	.data = &(struct clk_regmap_div_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.shift = 0,
+		.width = 11,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk_div",
+		.ops = &clk_regmap_divider_ops,
+		.parent_names = (const char *[]){ "gen_clk_sel" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
+static struct clk_regmap gxbb_gen_clk = {
+	.data = &(struct clk_regmap_gate_data){
+		.offset = HHI_GEN_CLK_CNTL,
+		.bit_idx = 7,
+	},
+	.hw.init = &(struct clk_init_data){
+		.name = "gen_clk",
+		.ops = &clk_regmap_gate_ops,
+		.parent_names = (const char *[]){ "gen_clk_div" },
+		.num_parents = 1,
+		.flags = CLK_SET_RATE_PARENT,
+	},
+};
+
 /* Everything Else (EE) domain gates */
 static MESON_GATE(gxbb_ddr, HHI_GCLK_MPEG0, 0);
 static MESON_GATE(gxbb_dos, HHI_GCLK_MPEG0, 1);
@@ -1873,6 +1930,9 @@ static struct clk_hw_onecell_data gxbb_hw_onecell_data = {
 		[CLKID_VDEC_HEVC_SEL]	    = &gxbb_vdec_hevc_sel.hw,
 		[CLKID_VDEC_HEVC_DIV]	    = &gxbb_vdec_hevc_div.hw,
 		[CLKID_VDEC_HEVC]	    = &gxbb_vdec_hevc.hw,
+		[CLKID_GEN_CLK_SEL]	    = &gxbb_gen_clk_sel.hw,
+		[CLKID_GEN_CLK_DIV]	    = &gxbb_gen_clk_div.hw,
+		[CLKID_GEN_CLK]		    = &gxbb_gen_clk.hw,
 		[NR_CLKS]		    = NULL,
 	},
 	.num = NR_CLKS,
@@ -2035,6 +2095,9 @@ static struct clk_hw_onecell_data gxl_hw_onecell_data = {
 		[CLKID_VDEC_HEVC_SEL]	    = &gxbb_vdec_hevc_sel.hw,
 		[CLKID_VDEC_HEVC_DIV]	    = &gxbb_vdec_hevc_div.hw,
 		[CLKID_VDEC_HEVC]	    = &gxbb_vdec_hevc.hw,
+		[CLKID_GEN_CLK_SEL]	    = &gxbb_gen_clk_sel.hw,
+		[CLKID_GEN_CLK_DIV]	    = &gxbb_gen_clk_div.hw,
+		[CLKID_GEN_CLK]		    = &gxbb_gen_clk.hw,
 		[NR_CLKS]		    = NULL,
 	},
 	.num = NR_CLKS,
@@ -2199,6 +2262,9 @@ static struct clk_regmap *const gx_clk_regmaps[] = {
 	&gxbb_vdec_hevc_sel,
 	&gxbb_vdec_hevc_div,
 	&gxbb_vdec_hevc,
+	&gxbb_gen_clk_sel,
+	&gxbb_gen_clk_div,
+	&gxbb_gen_clk,
 };
 
 struct clkc_data {
diff --git a/drivers/clk/meson/gxbb.h b/drivers/clk/meson/gxbb.h
index df6c21d368c6..20dfb1daf5b8 100644
--- a/drivers/clk/meson/gxbb.h
+++ b/drivers/clk/meson/gxbb.h
@@ -157,8 +157,10 @@
 #define CLKID_VDEC_1_DIV	  152
 #define CLKID_VDEC_HEVC_SEL	  154
 #define CLKID_VDEC_HEVC_DIV	  155
+#define CLKID_GEN_CLK_SEL	  157
+#define CLKID_GEN_CLK_DIV	  158
 
-#define NR_CLKS			  157
+#define NR_CLKS			  160
 
 /* include the CLKIDs that have been made part of the DT binding */
 #include <dt-bindings/clock/gxbb-clkc.h>
-- 
cgit v1.2.3


From 8512486ba2d441187d6d619006f034704a3e5a31 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 9 Jul 2018 13:51:57 +0200
Subject: gpio: mt7621: Edit to preferred syntax

This fixes some syntactic nits that makes the GPIO maintainer
happier. It is way easier to show by example and do it myself
than to try to explain it with comments. It's just my personal
taste of minimalism.

Cc: Sergio Paracuellos <sergio.paracuellos@gmail.com>
Cc: NeilBrown <neil@brown.name>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-mt7621.c | 85 ++++++++++++++++++++++------------------------
 1 file changed, 41 insertions(+), 44 deletions(-)

diff --git a/drivers/gpio/gpio-mt7621.c b/drivers/gpio/gpio-mt7621.c
index 14660d38dd1a..d72af6f6cdbd 100644
--- a/drivers/gpio/gpio-mt7621.c
+++ b/drivers/gpio/gpio-mt7621.c
@@ -40,18 +40,18 @@ struct mtk_gc {
 };
 
 /**
- * struct mtk_data - state container for
+ * struct mtk - state container for
  * data of the platform driver. It is 3
  * separate gpio-chip each one with its
  * own irq_chip.
  * @dev: device instance
- * @gpio_membase: memory base address
+ * @base: memory base address
  * @gpio_irq: irq number from the device tree
  * @gc_map: array of the gpio chips
  */
-struct mtk_data {
+struct mtk {
 	struct device *dev;
-	void __iomem *gpio_membase;
+	void __iomem *base;
 	int gpio_irq;
 	struct mtk_gc gc_map[MTK_BANK_CNT];
 };
@@ -66,20 +66,20 @@ static inline void
 mtk_gpio_w32(struct mtk_gc *rg, u32 offset, u32 val)
 {
 	struct gpio_chip *gc = &rg->chip;
-	struct mtk_data *gpio_data = gpiochip_get_data(gc);
+	struct mtk *mtk = gpiochip_get_data(gc);
 
 	offset = (rg->bank * GPIO_BANK_STRIDE) + offset;
-	gc->write_reg(gpio_data->gpio_membase + offset, val);
+	gc->write_reg(mtk->base + offset, val);
 }
 
 static inline u32
 mtk_gpio_r32(struct mtk_gc *rg, u32 offset)
 {
 	struct gpio_chip *gc = &rg->chip;
-	struct mtk_data *gpio_data = gpiochip_get_data(gc);
+	struct mtk *mtk = gpiochip_get_data(gc);
 
 	offset = (rg->bank * GPIO_BANK_STRIDE) + offset;
-	return gc->read_reg(gpio_data->gpio_membase + offset);
+	return gc->read_reg(mtk->base + offset);
 }
 
 static irqreturn_t
@@ -213,80 +213,76 @@ mediatek_gpio_xlate(struct gpio_chip *chip,
 }
 
 static int
-mediatek_gpio_bank_probe(struct platform_device *pdev,
+mediatek_gpio_bank_probe(struct device *dev,
 			 struct device_node *node, int bank)
 {
-	struct mtk_data *gpio = dev_get_drvdata(&pdev->dev);
+	struct mtk *mtk = dev_get_drvdata(dev);
 	struct mtk_gc *rg;
 	void __iomem *dat, *set, *ctrl, *diro;
 	int ret;
 
-	rg = &gpio->gc_map[bank];
+	rg = &mtk->gc_map[bank];
 	memset(rg, 0, sizeof(*rg));
 
 	spin_lock_init(&rg->lock);
 	rg->chip.of_node = node;
 	rg->bank = bank;
 
-	dat = gpio->gpio_membase + GPIO_REG_DATA +
-		(rg->bank * GPIO_BANK_STRIDE);
-	set = gpio->gpio_membase + GPIO_REG_DSET +
-		(rg->bank * GPIO_BANK_STRIDE);
-	ctrl = gpio->gpio_membase + GPIO_REG_DCLR +
-		(rg->bank * GPIO_BANK_STRIDE);
-	diro = gpio->gpio_membase + GPIO_REG_CTRL +
-		(rg->bank * GPIO_BANK_STRIDE);
+	dat = mtk->base + GPIO_REG_DATA + (rg->bank * GPIO_BANK_STRIDE);
+	set = mtk->base + GPIO_REG_DSET + (rg->bank * GPIO_BANK_STRIDE);
+	ctrl = mtk->base + GPIO_REG_DCLR + (rg->bank * GPIO_BANK_STRIDE);
+	diro = mtk->base + GPIO_REG_CTRL + (rg->bank * GPIO_BANK_STRIDE);
 
-	ret = bgpio_init(&rg->chip, &pdev->dev, 4,
+	ret = bgpio_init(&rg->chip, dev, 4,
 			 dat, set, ctrl, diro, NULL, 0);
 	if (ret) {
-		dev_err(&pdev->dev, "bgpio_init() failed\n");
+		dev_err(dev, "bgpio_init() failed\n");
 		return ret;
 	}
 
 	rg->chip.of_gpio_n_cells = 2;
 	rg->chip.of_xlate = mediatek_gpio_xlate;
-	rg->chip.label = devm_kasprintf(&pdev->dev, GFP_KERNEL, "%s-bank%d",
-					dev_name(&pdev->dev), bank);
+	rg->chip.label = devm_kasprintf(dev, GFP_KERNEL, "%s-bank%d",
+					dev_name(dev), bank);
 
-	ret = devm_gpiochip_add_data(&pdev->dev, &rg->chip, gpio);
+	ret = devm_gpiochip_add_data(dev, &rg->chip, mtk);
 	if (ret < 0) {
-		dev_err(&pdev->dev, "Could not register gpio %d, ret=%d\n",
+		dev_err(dev, "Could not register gpio %d, ret=%d\n",
 			rg->chip.ngpio, ret);
 		return ret;
 	}
 
-	if (gpio->gpio_irq) {
+	if (mtk->gpio_irq) {
 		/*
 		 * Manually request the irq here instead of passing
 		 * a flow-handler to gpiochip_set_chained_irqchip,
 		 * because the irq is shared.
 		 */
-		ret = devm_request_irq(&pdev->dev, gpio->gpio_irq,
+		ret = devm_request_irq(dev, mtk->gpio_irq,
 				       mediatek_gpio_irq_handler, IRQF_SHARED,
 				       rg->chip.label, &rg->chip);
 
 		if (ret) {
-			dev_err(&pdev->dev, "Error requesting IRQ %d: %d\n",
-				gpio->gpio_irq, ret);
+			dev_err(dev, "Error requesting IRQ %d: %d\n",
+				mtk->gpio_irq, ret);
 			return ret;
 		}
 
 		ret = gpiochip_irqchip_add(&rg->chip, &mediatek_gpio_irq_chip,
 					   0, handle_simple_irq, IRQ_TYPE_NONE);
 		if (ret) {
-			dev_err(&pdev->dev, "failed to add gpiochip_irqchip\n");
+			dev_err(dev, "failed to add gpiochip_irqchip\n");
 			return ret;
 		}
 
 		gpiochip_set_chained_irqchip(&rg->chip, &mediatek_gpio_irq_chip,
-					     gpio->gpio_irq, NULL);
+					     mtk->gpio_irq, NULL);
 	}
 
 	/* set polarity to low for all gpios */
 	mtk_gpio_w32(rg, GPIO_REG_POL, 0);
 
-	dev_info(&pdev->dev, "registering %d gpios\n", rg->chip.ngpio);
+	dev_info(dev, "registering %d gpios\n", rg->chip.ngpio);
 
 	return 0;
 }
@@ -294,26 +290,27 @@ mediatek_gpio_bank_probe(struct platform_device *pdev,
 static int
 mediatek_gpio_probe(struct platform_device *pdev)
 {
-	struct device_node *np = pdev->dev.of_node;
 	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	struct mtk_data *gpio_data;
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct mtk *mtk;
 	int i;
 
-	gpio_data = devm_kzalloc(&pdev->dev, sizeof(*gpio_data), GFP_KERNEL);
-	if (!gpio_data)
+	mtk = devm_kzalloc(dev, sizeof(*mtk), GFP_KERNEL);
+	if (!mtk)
 		return -ENOMEM;
 
-	gpio_data->gpio_membase = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(gpio_data->gpio_membase))
-		return PTR_ERR(gpio_data->gpio_membase);
+	mtk->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(mtk->base))
+		return PTR_ERR(mtk->base);
 
-	gpio_data->gpio_irq = irq_of_parse_and_map(np, 0);
-	gpio_data->dev = &pdev->dev;
-	platform_set_drvdata(pdev, gpio_data);
-	mediatek_gpio_irq_chip.name = dev_name(&pdev->dev);
+	mtk->gpio_irq = irq_of_parse_and_map(np, 0);
+	mtk->dev = dev;
+	platform_set_drvdata(pdev, mtk);
+	mediatek_gpio_irq_chip.name = dev_name(dev);
 
 	for (i = 0; i < MTK_BANK_CNT; i++)
-		mediatek_gpio_bank_probe(pdev, np, i);
+		mediatek_gpio_bank_probe(dev, np, i);
 
 	return 0;
 }
-- 
cgit v1.2.3


From ba552399954dde1b388f7749fecad5c349216981 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Wed, 27 Jun 2018 16:08:15 +0200
Subject: printk: Split the code for storing a message into the log buffer

It is just a preparation step. The patch does not change
the existing behavior.

Link: http://lkml.kernel.org/r/20180627140817.27764-2-pmladek@suse.com
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 kernel/printk/printk.c | 43 ++++++++++++++++++++++++++-----------------
 1 file changed, 26 insertions(+), 17 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 247808333ba4..a844c611b17c 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1824,28 +1824,16 @@ static size_t log_output(int facility, int level, enum log_flags lflags, const c
 	return log_store(facility, level, lflags, 0, dict, dictlen, text, text_len);
 }
 
-asmlinkage int vprintk_emit(int facility, int level,
-			    const char *dict, size_t dictlen,
-			    const char *fmt, va_list args)
+/* Must be called under logbuf_lock. */
+int vprintk_store(int facility, int level,
+		  const char *dict, size_t dictlen,
+		  const char *fmt, va_list args)
 {
 	static char textbuf[LOG_LINE_MAX];
 	char *text = textbuf;
 	size_t text_len;
 	enum log_flags lflags = 0;
-	unsigned long flags;
-	int printed_len;
-	bool in_sched = false;
-
-	if (level == LOGLEVEL_SCHED) {
-		level = LOGLEVEL_DEFAULT;
-		in_sched = true;
-	}
-
-	boot_delay_msec(level);
-	printk_delay();
 
-	/* This stops the holder of console_sem just where we want him */
-	logbuf_lock_irqsave(flags);
 	/*
 	 * The printf needs to come first; we need the syslog
 	 * prefix which might be passed-in as a parameter.
@@ -1886,8 +1874,29 @@ asmlinkage int vprintk_emit(int facility, int level,
 	if (dict)
 		lflags |= LOG_PREFIX|LOG_NEWLINE;
 
-	printed_len = log_output(facility, level, lflags, dict, dictlen, text, text_len);
+	return log_output(facility, level, lflags,
+			  dict, dictlen, text, text_len);
+}
 
+asmlinkage int vprintk_emit(int facility, int level,
+			    const char *dict, size_t dictlen,
+			    const char *fmt, va_list args)
+{
+	int printed_len;
+	bool in_sched = false;
+	unsigned long flags;
+
+	if (level == LOGLEVEL_SCHED) {
+		level = LOGLEVEL_DEFAULT;
+		in_sched = true;
+	}
+
+	boot_delay_msec(level);
+	printk_delay();
+
+	/* This stops the holder of console_sem just where we want him */
+	logbuf_lock_irqsave(flags);
+	printed_len = vprintk_store(facility, level, dict, dictlen, fmt, args);
 	logbuf_unlock_irqrestore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
-- 
cgit v1.2.3


From d7c7118caf99fc4fe3b2e1f47e3d23b2bbaf7929 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Thu, 5 Jul 2018 17:18:05 +0100
Subject: MAINTAINERS: arm64: Remove boot/dts/ directory from arm64 entry

The arm-soc tree does a good job handling .dts files, so exclude them
from the ARM64 entry in MAINTAINERS.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 07d1576fc766..61301440e66f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2264,6 +2264,7 @@ L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux.git
 S:	Maintained
 F:	arch/arm64/
+X:	arch/arm64/boot/dts/
 F:	Documentation/arm64/
 
 AS3645A LED FLASH CONTROLLER DRIVER
-- 
cgit v1.2.3


From e7d4bac428edb806c5f5d903ab8850ffbe0ed9ce Mon Sep 17 00:00:00 2001
From: Nikunj Kela <nkela@cisco.com>
Date: Fri, 6 Jul 2018 10:47:24 -0700
Subject: arm64: add ARM64-specific support for flatmem

Flatmem is useful in reducing kernel memory usage.
One usecase is in kdump kernel. We are able to save
~14M by moving to flatmem scheme.

Cc: xe-kernel@external.cisco.com
Cc: Nikunj Kela <nkela@cisco.com>
Signed-off-by: Nikunj Kela <nkela@cisco.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 476de9b1d239..c548b3dd48ab 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -786,6 +786,9 @@ config ARCH_SPARSEMEM_DEFAULT
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool ARCH_SPARSEMEM_ENABLE
 
+config ARCH_FLATMEM_ENABLE
+	def_bool y
+
 config HAVE_ARCH_PFN_VALID
 	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
 
-- 
cgit v1.2.3


From a338f84dc196f44b63ba0863d2f34fd9b1613572 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Wed, 27 Jun 2018 16:08:16 +0200
Subject: printk: Create helper function to queue deferred console handling

It is just a preparation step. The patch does not change
the existing behavior.

Link: http://lkml.kernel.org/r/20180627140817.27764-3-pmladek@suse.com
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 kernel/printk/printk.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index a844c611b17c..1d1513215c22 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2887,16 +2887,20 @@ void wake_up_klogd(void)
 	preempt_enable();
 }
 
-int vprintk_deferred(const char *fmt, va_list args)
+void defer_console_output(void)
 {
-	int r;
-
-	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
-
 	preempt_disable();
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
 	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));
 	preempt_enable();
+}
+
+int vprintk_deferred(const char *fmt, va_list args)
+{
+	int r;
+
+	r = vprintk_emit(0, LOGLEVEL_SCHED, NULL, 0, fmt, args);
+	defer_console_output();
 
 	return r;
 }
-- 
cgit v1.2.3


From 03fc7f9c99c1e7ae2925d459e8487f1a6f199f79 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Wed, 27 Jun 2018 16:20:28 +0200
Subject: printk/nmi: Prevent deadlock when accessing the main log buffer in
 NMI

The commit 719f6a7040f1bdaf96 ("printk: Use the main logbuf in NMI
when logbuf_lock is available") brought back the possible deadlocks
in printk() and NMI.

The check of logbuf_lock is done only in printk_nmi_enter() to prevent
mixed output. But another CPU might take the lock later, enter NMI, and:

      + Both NMIs might be serialized by yet another lock, for example,
	the one in nmi_cpu_backtrace().

      + The other CPU might get stopped in NMI, see smp_send_stop()
	in panic().

The only safe solution is to use trylock when storing the message
into the main log-buffer. It might cause reordering when some lines
go to the main lock buffer directly and others are delayed via
the per-CPU buffer. It means that it is not useful in general.

This patch replaces the problematic NMI deferred context with NMI
direct context. It can be used to mark a code that might produce
many messages in NMI and the risk of losing them is more critical
than problems with eventual reordering.

The context is then used when dumping trace buffers on oops. It was
the primary motivation for the original fix. Also the reordering is
even smaller issue there because some traces have their own time stamps.

Finally, nmi_cpu_backtrace() need not longer be serialized because
it will always us the per-CPU buffers again.

Fixes: 719f6a7040f1bdaf96 ("printk: Use the main logbuf in NMI when logbuf_lock is available")
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/20180627142028.11259-1-pmladek@suse.com
To: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Sergey Senozhatsky <sergey.senozhatsky.work@gmail.com>
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 include/linux/printk.h      |  4 ++++
 kernel/printk/internal.h    |  9 ++++++-
 kernel/printk/printk_safe.c | 58 +++++++++++++++++++++++++++++----------------
 kernel/trace/trace.c        |  4 +++-
 lib/nmi_backtrace.c         |  3 ---
 5 files changed, 52 insertions(+), 26 deletions(-)

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 6d7e800affd8..3ede9f46a494 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -148,9 +148,13 @@ void early_printk(const char *s, ...) { }
 #ifdef CONFIG_PRINTK_NMI
 extern void printk_nmi_enter(void);
 extern void printk_nmi_exit(void);
+extern void printk_nmi_direct_enter(void);
+extern void printk_nmi_direct_exit(void);
 #else
 static inline void printk_nmi_enter(void) { }
 static inline void printk_nmi_exit(void) { }
+static inline void printk_nmi_direct_enter(void) { }
+static inline void printk_nmi_direct_exit(void) { }
 #endif /* PRINTK_NMI */
 
 #ifdef CONFIG_PRINTK
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 2a7d04049af4..0f1898820cba 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -19,11 +19,16 @@
 #ifdef CONFIG_PRINTK
 
 #define PRINTK_SAFE_CONTEXT_MASK	 0x3fffffff
-#define PRINTK_NMI_DEFERRED_CONTEXT_MASK 0x40000000
+#define PRINTK_NMI_DIRECT_CONTEXT_MASK	 0x40000000
 #define PRINTK_NMI_CONTEXT_MASK		 0x80000000
 
 extern raw_spinlock_t logbuf_lock;
 
+__printf(5, 0)
+int vprintk_store(int facility, int level,
+		  const char *dict, size_t dictlen,
+		  const char *fmt, va_list args);
+
 __printf(1, 0) int vprintk_default(const char *fmt, va_list args);
 __printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
 __printf(1, 0) int vprintk_func(const char *fmt, va_list args);
@@ -54,6 +59,8 @@ void __printk_safe_exit(void);
 		local_irq_enable();		\
 	} while (0)
 
+void defer_console_output(void);
+
 #else
 
 __printf(1, 0) int vprintk_func(const char *fmt, va_list args) { return 0; }
diff --git a/kernel/printk/printk_safe.c b/kernel/printk/printk_safe.c
index d7d091309054..a0a74c533e4b 100644
--- a/kernel/printk/printk_safe.c
+++ b/kernel/printk/printk_safe.c
@@ -308,24 +308,33 @@ static __printf(1, 0) int vprintk_nmi(const char *fmt, va_list args)
 
 void printk_nmi_enter(void)
 {
-	/*
-	 * The size of the extra per-CPU buffer is limited. Use it only when
-	 * the main one is locked. If this CPU is not in the safe context,
-	 * the lock must be taken on another CPU and we could wait for it.
-	 */
-	if ((this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK) &&
-	    raw_spin_is_locked(&logbuf_lock)) {
-		this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
-	} else {
-		this_cpu_or(printk_context, PRINTK_NMI_DEFERRED_CONTEXT_MASK);
-	}
+	this_cpu_or(printk_context, PRINTK_NMI_CONTEXT_MASK);
 }
 
 void printk_nmi_exit(void)
 {
-	this_cpu_and(printk_context,
-		     ~(PRINTK_NMI_CONTEXT_MASK |
-		       PRINTK_NMI_DEFERRED_CONTEXT_MASK));
+	this_cpu_and(printk_context, ~PRINTK_NMI_CONTEXT_MASK);
+}
+
+/*
+ * Marks a code that might produce many messages in NMI context
+ * and the risk of losing them is more critical than eventual
+ * reordering.
+ *
+ * It has effect only when called in NMI context. Then printk()
+ * will try to store the messages into the main logbuf directly
+ * and use the per-CPU buffers only as a fallback when the lock
+ * is not available.
+ */
+void printk_nmi_direct_enter(void)
+{
+	if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
+		this_cpu_or(printk_context, PRINTK_NMI_DIRECT_CONTEXT_MASK);
+}
+
+void printk_nmi_direct_exit(void)
+{
+	this_cpu_and(printk_context, ~PRINTK_NMI_DIRECT_CONTEXT_MASK);
 }
 
 #else
@@ -363,6 +372,20 @@ void __printk_safe_exit(void)
 
 __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 {
+	/*
+	 * Try to use the main logbuf even in NMI. But avoid calling console
+	 * drivers that might have their own locks.
+	 */
+	if ((this_cpu_read(printk_context) & PRINTK_NMI_DIRECT_CONTEXT_MASK) &&
+	    raw_spin_trylock(&logbuf_lock)) {
+		int len;
+
+		len = vprintk_store(0, LOGLEVEL_DEFAULT, NULL, 0, fmt, args);
+		raw_spin_unlock(&logbuf_lock);
+		defer_console_output();
+		return len;
+	}
+
 	/* Use extra buffer in NMI when logbuf_lock is taken or in safe mode. */
 	if (this_cpu_read(printk_context) & PRINTK_NMI_CONTEXT_MASK)
 		return vprintk_nmi(fmt, args);
@@ -371,13 +394,6 @@ __printf(1, 0) int vprintk_func(const char *fmt, va_list args)
 	if (this_cpu_read(printk_context) & PRINTK_SAFE_CONTEXT_MASK)
 		return vprintk_safe(fmt, args);
 
-	/*
-	 * Use the main logbuf when logbuf_lock is available in NMI.
-	 * But avoid calling console drivers that might have their own locks.
-	 */
-	if (this_cpu_read(printk_context) & PRINTK_NMI_DEFERRED_CONTEXT_MASK)
-		return vprintk_deferred(fmt, args);
-
 	/* No obstacles. */
 	return vprintk_default(fmt, args);
 }
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index bcd93031d042..f106ad12f72f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -8265,6 +8265,7 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	tracing_off();
 
 	local_irq_save(flags);
+	printk_nmi_direct_enter();
 
 	/* Simulate the iterator */
 	trace_init_global_iter(&iter);
@@ -8344,7 +8345,8 @@ void ftrace_dump(enum ftrace_dump_mode oops_dump_mode)
 	for_each_tracing_cpu(cpu) {
 		atomic_dec(&per_cpu_ptr(iter.trace_buffer->data, cpu)->disabled);
 	}
- 	atomic_dec(&dump_running);
+	atomic_dec(&dump_running);
+	printk_nmi_direct_exit();
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(ftrace_dump);
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 61a6b5aab07e..15ca78e1c7d4 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -87,11 +87,9 @@ void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
 
 bool nmi_cpu_backtrace(struct pt_regs *regs)
 {
-	static arch_spinlock_t lock = __ARCH_SPIN_LOCK_UNLOCKED;
 	int cpu = smp_processor_id();
 
 	if (cpumask_test_cpu(cpu, to_cpumask(backtrace_mask))) {
-		arch_spin_lock(&lock);
 		if (regs && cpu_in_idle(instruction_pointer(regs))) {
 			pr_warn("NMI backtrace for cpu %d skipped: idling at %pS\n",
 				cpu, (void *)instruction_pointer(regs));
@@ -102,7 +100,6 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 			else
 				dump_stack();
 		}
-		arch_spin_unlock(&lock);
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));
 		return true;
 	}
-- 
cgit v1.2.3


From 64b2f025715a68bed49fb14588c2d893dfbd00a8 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Sat, 7 Jul 2018 23:16:56 +0200
Subject: arm: perf: prevent unbind/bind via sysfs

Unbinding and rebinding the ARM PMU driver via sysfs leads to a
warning followed by more errors:
  WARNING: CPU: 0 PID: 217 at kernel/irq/chip.c:1034 irq_modify_status+0x150/0x16c
  ..
  genirq: Flags mismatch irq 19. 00010c04 (arm-pmu) vs. 00010c04 (arm-pmu)
  hw perfevents: unable to request IRQ19 for ARM PMU counters
  hw perfevents: /pmu: failed to register PMU devices!
  armv7-pmu: probe of pmu failed with error -16

The driver is clearly not designed to be removed. Disable bind/
unbind for this driver.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/kernel/perf_event_v7.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 57f01e059f39..5a5116794440 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -2030,6 +2030,7 @@ static struct platform_driver armv7_pmu_driver = {
 	.driver		= {
 		.name	= "armv7-pmu",
 		.of_match_table = armv7_pmu_of_device_ids,
+		.suppress_bind_attrs = true,
 	},
 	.probe		= armv7_pmu_device_probe,
 };
-- 
cgit v1.2.3


From ec625fb932bb057e2d3c2ed28eee56a827385ab8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 13:20:42 +0100
Subject: drm/i915: Provide a timeout to i915_gem_wait_for_idle()

Usually we have no idea about the upper bound we need to wait to catch
up with userspace when idling the device, but in a few situations we
know the system was idle beforehand and can provide a short timeout in
order to very quickly catch a failure, long before hangcheck kicks in.

In the following patches, we will use the timeout to curtain two overly
long waits, where we know we can expect the GPU to complete within a
reasonable time or declare it broken.

In particular, with a broken GPU we expect it to fail during the initial
GPU setup where do a couple of context switches to record the defaults.
This is a task that takes a few milliseconds even on the slowest of
devices, but we may have to wait 60s for hangcheck to give in and
declare the machine inoperable. In this a case where any gpu hang is
unacceptable, both from a timeliness and practical standpoint.

The other improvement is that in selftests, we do not need to arm an
independent timer to inject a wedge, as we can just limit the timeout on
the wait directly.

v2: Include the timeout parameter in the trace.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709122044.7028-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_debugfs.c               |  6 ++-
 drivers/gpu/drm/i915/i915_drv.h                   |  2 +-
 drivers/gpu/drm/i915/i915_gem.c                   | 48 ++++++++++++++---------
 drivers/gpu/drm/i915/i915_gem_evict.c             |  3 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c               |  2 +-
 drivers/gpu/drm/i915/i915_gem_shrinker.c          | 11 ++++--
 drivers/gpu/drm/i915/i915_perf.c                  |  4 +-
 drivers/gpu/drm/i915/i915_request.c               |  6 ++-
 drivers/gpu/drm/i915/selftests/i915_gem_context.c |  4 +-
 drivers/gpu/drm/i915/selftests/i915_request.c     |  4 +-
 drivers/gpu/drm/i915/selftests/igt_flush_test.c   |  2 +-
 11 files changed, 59 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 544e5e7f011f..099f97ef2303 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -4105,7 +4105,8 @@ fault_irq_set(struct drm_i915_private *i915,
 
 	err = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_LOCKED |
-				     I915_WAIT_INTERRUPTIBLE);
+				     I915_WAIT_INTERRUPTIBLE,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		goto err_unlock;
 
@@ -4210,7 +4211,8 @@ i915_drop_caches_set(void *data, u64 val)
 		if (val & DROP_ACTIVE)
 			ret = i915_gem_wait_for_idle(dev_priv,
 						     I915_WAIT_INTERRUPTIBLE |
-						     I915_WAIT_LOCKED);
+						     I915_WAIT_LOCKED,
+						     MAX_SCHEDULE_TIMEOUT);
 
 		if (val & DROP_RETIRE)
 			i915_retire_requests(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c79008177708..fcb8f49a9b8a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3157,7 +3157,7 @@ void i915_gem_init_swizzling(struct drm_i915_private *dev_priv);
 void i915_gem_fini(struct drm_i915_private *dev_priv);
 void i915_gem_cleanup_engines(struct drm_i915_private *dev_priv);
 int i915_gem_wait_for_idle(struct drm_i915_private *dev_priv,
-			   unsigned int flags);
+			   unsigned int flags, long timeout);
 int __must_check i915_gem_suspend(struct drm_i915_private *dev_priv);
 void i915_gem_suspend_late(struct drm_i915_private *dev_priv);
 void i915_gem_resume(struct drm_i915_private *dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1a9dab302433..91d705a67d38 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2267,7 +2267,9 @@ static int i915_gem_object_create_mmap_offset(struct drm_i915_gem_object *obj)
 
 	/* Attempt to reap some mmap space from dead objects */
 	do {
-		err = i915_gem_wait_for_idle(dev_priv, I915_WAIT_INTERRUPTIBLE);
+		err = i915_gem_wait_for_idle(dev_priv,
+					     I915_WAIT_INTERRUPTIBLE,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (err)
 			break;
 
@@ -3742,14 +3744,14 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 	return ret;
 }
 
-static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags)
+static long wait_for_timeline(struct i915_timeline *tl,
+			      unsigned int flags, long timeout)
 {
 	struct i915_request *rq;
-	long ret;
 
 	rq = i915_gem_active_get_unlocked(&tl->last_request);
 	if (!rq)
-		return 0;
+		return timeout;
 
 	/*
 	 * "Race-to-idle".
@@ -3763,10 +3765,10 @@ static int wait_for_timeline(struct i915_timeline *tl, unsigned int flags)
 	if (flags & I915_WAIT_FOR_IDLE_BOOST)
 		gen6_rps_boost(rq, NULL);
 
-	ret = i915_request_wait(rq, flags, MAX_SCHEDULE_TIMEOUT);
+	timeout = i915_request_wait(rq, flags, timeout);
 	i915_request_put(rq);
 
-	return ret < 0 ? ret : 0;
+	return timeout;
 }
 
 static int wait_for_engines(struct drm_i915_private *i915)
@@ -3782,10 +3784,12 @@ static int wait_for_engines(struct drm_i915_private *i915)
 	return 0;
 }
 
-int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
+int i915_gem_wait_for_idle(struct drm_i915_private *i915,
+			   unsigned int flags, long timeout)
 {
-	GEM_TRACE("flags=%x (%s)\n",
-		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked");
+	GEM_TRACE("flags=%x (%s), timeout=%ld%s\n",
+		  flags, flags & I915_WAIT_LOCKED ? "locked" : "unlocked",
+		  timeout, timeout == MAX_SCHEDULE_TIMEOUT ? " (forever)" : "");
 
 	/* If the device is asleep, we have no requests outstanding */
 	if (!READ_ONCE(i915->gt.awake))
@@ -3798,9 +3802,9 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 		lockdep_assert_held(&i915->drm.struct_mutex);
 
 		list_for_each_entry(tl, &i915->gt.timelines, link) {
-			err = wait_for_timeline(tl, flags);
-			if (err)
-				return err;
+			timeout = wait_for_timeline(tl, flags, timeout);
+			if (timeout < 0)
+				return timeout;
 		}
 
 		err = wait_for_engines(i915);
@@ -3812,12 +3816,13 @@ int i915_gem_wait_for_idle(struct drm_i915_private *i915, unsigned int flags)
 	} else {
 		struct intel_engine_cs *engine;
 		enum intel_engine_id id;
-		int err;
 
 		for_each_engine(engine, i915, id) {
-			err = wait_for_timeline(&engine->timeline, flags);
-			if (err)
-				return err;
+			struct i915_timeline *tl = &engine->timeline;
+
+			timeout = wait_for_timeline(tl, flags, timeout);
+			if (timeout < 0)
+				return timeout;
 		}
 	}
 
@@ -5052,7 +5057,8 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 		ret = i915_gem_wait_for_idle(dev_priv,
 					     I915_WAIT_INTERRUPTIBLE |
 					     I915_WAIT_LOCKED |
-					     I915_WAIT_FOR_IDLE_BOOST);
+					     I915_WAIT_FOR_IDLE_BOOST,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret && ret != -EIO)
 			goto err_unlock;
 
@@ -5356,7 +5362,9 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	if (err)
 		goto err_active;
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	err = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		goto err_active;
 
@@ -5421,7 +5429,9 @@ err_active:
 	if (WARN_ON(i915_gem_switch_to_kernel_context(i915)))
 		goto out_ctx;
 
-	if (WARN_ON(i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED)))
+	if (WARN_ON(i915_gem_wait_for_idle(i915,
+					   I915_WAIT_LOCKED,
+					   MAX_SCHEDULE_TIMEOUT)))
 		goto out_ctx;
 
 	i915_gem_contexts_lost(i915);
diff --git a/drivers/gpu/drm/i915/i915_gem_evict.c b/drivers/gpu/drm/i915/i915_gem_evict.c
index 54814a196ee4..02b83a5ed96c 100644
--- a/drivers/gpu/drm/i915/i915_gem_evict.c
+++ b/drivers/gpu/drm/i915/i915_gem_evict.c
@@ -69,7 +69,8 @@ static int ggtt_flush(struct drm_i915_private *i915)
 
 	err = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED);
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 4db31aaaa9d3..210baf3c8d11 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -2793,7 +2793,7 @@ void i915_gem_gtt_finish_pages(struct drm_i915_gem_object *obj,
 	struct i915_ggtt *ggtt = &dev_priv->ggtt;
 
 	if (unlikely(ggtt->do_idle_maps)) {
-		if (i915_gem_wait_for_idle(dev_priv, 0)) {
+		if (i915_gem_wait_for_idle(dev_priv, 0, MAX_SCHEDULE_TIMEOUT)) {
 			DRM_ERROR("Failed to wait for idle; VT'd may hang.\n");
 			/* Wait a bit, in hopes it avoids the hang */
 			udelay(10);
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 55e84e71f526..c61f5b80fee3 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -172,7 +172,9 @@ i915_gem_shrink(struct drm_i915_private *i915,
 	 * we will free as much as we can and hope to get a second chance.
 	 */
 	if (flags & I915_SHRINK_ACTIVE)
-		i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+		i915_gem_wait_for_idle(i915,
+				       I915_WAIT_LOCKED,
+				       MAX_SCHEDULE_TIMEOUT);
 
 	trace_i915_gem_shrink(i915, target, flags);
 	i915_retire_requests(i915);
@@ -392,7 +394,8 @@ shrinker_lock_uninterruptible(struct drm_i915_private *i915, bool *unlock,
 	unsigned long timeout = jiffies + msecs_to_jiffies_timeout(timeout_ms);
 
 	do {
-		if (i915_gem_wait_for_idle(i915, 0) == 0 &&
+		if (i915_gem_wait_for_idle(i915,
+					   0, MAX_SCHEDULE_TIMEOUT) == 0 &&
 		    shrinker_lock(i915, unlock))
 			break;
 
@@ -466,7 +469,9 @@ i915_gem_shrinker_vmap(struct notifier_block *nb, unsigned long event, void *ptr
 		return NOTIFY_DONE;
 
 	/* Force everything onto the inactive lists */
-	ret = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	ret = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
index 447407fee3b8..6bf10952c724 100644
--- a/drivers/gpu/drm/i915/i915_perf.c
+++ b/drivers/gpu/drm/i915/i915_perf.c
@@ -1836,7 +1836,9 @@ static int gen8_configure_all_contexts(struct drm_i915_private *dev_priv,
 	 * So far the best way to work around this issue seems to be draining
 	 * the GPU from any submitted work.
 	 */
-	ret = i915_gem_wait_for_idle(dev_priv, wait_flags);
+	ret = i915_gem_wait_for_idle(dev_priv,
+				     wait_flags,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		goto out;
 
diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c
index 3248369dbcfb..5c2c93cbab12 100644
--- a/drivers/gpu/drm/i915/i915_request.c
+++ b/drivers/gpu/drm/i915/i915_request.c
@@ -206,7 +206,8 @@ static int reset_all_global_seqno(struct drm_i915_private *i915, u32 seqno)
 	/* Carefully retire all requests without writing to the rings */
 	ret = i915_gem_wait_for_idle(i915,
 				     I915_WAIT_INTERRUPTIBLE |
-				     I915_WAIT_LOCKED);
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (ret)
 		return ret;
 
@@ -735,7 +736,8 @@ i915_request_alloc(struct intel_engine_cs *engine, struct i915_gem_context *ctx)
 		/* Ratelimit ourselves to prevent oom from malicious clients */
 		ret = i915_gem_wait_for_idle(i915,
 					     I915_WAIT_LOCKED |
-					     I915_WAIT_INTERRUPTIBLE);
+					     I915_WAIT_INTERRUPTIBLE,
+					     MAX_SCHEDULE_TIMEOUT);
 		if (ret)
 			goto err_unreserve;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 5fbe15f4effd..ab2590242033 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -478,7 +478,9 @@ static int __igt_switch_to_kernel_context(struct drm_i915_private *i915,
 		}
 	}
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	err = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err)
 		return err;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_request.c b/drivers/gpu/drm/i915/selftests/i915_request.c
index 43995fc3534d..c4aac6141e04 100644
--- a/drivers/gpu/drm/i915/selftests/i915_request.c
+++ b/drivers/gpu/drm/i915/selftests/i915_request.c
@@ -286,7 +286,9 @@ static int begin_live_test(struct live_test *t,
 	t->func = func;
 	t->name = name;
 
-	err = i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED);
+	err = i915_gem_wait_for_idle(i915,
+				     I915_WAIT_LOCKED,
+				     MAX_SCHEDULE_TIMEOUT);
 	if (err) {
 		pr_err("%s(%s): failed to idle before, with err=%d!",
 		       func, name, err);
diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index 0d06f559243f..09ab037ce803 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -64,7 +64,7 @@ int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 	}
 
 	wedge_on_timeout(&w, i915, HZ)
-		i915_gem_wait_for_idle(i915, flags);
+		i915_gem_wait_for_idle(i915, flags, MAX_SCHEDULE_TIMEOUT);
 
 	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
 }
-- 
cgit v1.2.3


From 2621cefaa42b3a7455d30e78831c6b55290d40c8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 13:20:43 +0100
Subject: drm/i915: Provide a timeout to i915_gem_wait_for_idle() on setup

With a broken GPU we expect it to fail during the initial
GPU setup where do a couple of context switches to record the defaults.
This is a task that takes a few milliseconds even on the slowest of
devices, but we may have to wait 60s for hangcheck to give in and
declare the machine inoperable. In this a case where any gpu hang is
unacceptable, both from a timeliness and practical standpoint.

We can therefore set a timeout on our wait-for-idle that is shorter than
the hangcheck (which may be up to 60s for a declaring a wedged driver)
and so detect the broken GPU much more quickly during driver load (and
so prevent stalling userspace for ages).

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709122044.7028-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 91d705a67d38..b35cbfd16c9c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5362,11 +5362,11 @@ static int __intel_engines_record_defaults(struct drm_i915_private *i915)
 	if (err)
 		goto err_active;
 
-	err = i915_gem_wait_for_idle(i915,
-				     I915_WAIT_LOCKED,
-				     MAX_SCHEDULE_TIMEOUT);
-	if (err)
+	if (i915_gem_wait_for_idle(i915, I915_WAIT_LOCKED, HZ / 5)) {
+		i915_gem_set_wedged(i915);
+		err = -EIO; /* Caller will declare us wedged */
 		goto err_active;
+	}
 
 	assert_kernel_context_is_current(i915);
 
-- 
cgit v1.2.3


From d9a13ce3fa5f396f100ab3f58e5ca127c77a74bb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 13:20:44 +0100
Subject: drm/i915/selftests: Replace wait-on-timeout with explicit timeout

In igt_flush_test() we install a background timer in order to ensure
that the wait completes within a certain time. We can now tell the wait
that it has to complete within a timeout, and so no longer need the
background timer.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709122044.7028-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/igt_flush_test.c | 55 ++++---------------------
 1 file changed, 9 insertions(+), 46 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/igt_flush_test.c b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
index 09ab037ce803..af66e3d4e23a 100644
--- a/drivers/gpu/drm/i915/selftests/igt_flush_test.c
+++ b/drivers/gpu/drm/i915/selftests/igt_flush_test.c
@@ -9,52 +9,8 @@
 #include "../i915_selftest.h"
 #include "igt_flush_test.h"
 
-struct wedge_me {
-	struct delayed_work work;
-	struct drm_i915_private *i915;
-	const void *symbol;
-};
-
-static void wedge_me(struct work_struct *work)
-{
-	struct wedge_me *w = container_of(work, typeof(*w), work.work);
-
-	pr_err("%pS timed out, cancelling all further testing.\n", w->symbol);
-
-	GEM_TRACE("%pS timed out.\n", w->symbol);
-	GEM_TRACE_DUMP();
-
-	i915_gem_set_wedged(w->i915);
-}
-
-static void __init_wedge(struct wedge_me *w,
-			 struct drm_i915_private *i915,
-			 long timeout,
-			 const void *symbol)
-{
-	w->i915 = i915;
-	w->symbol = symbol;
-
-	INIT_DELAYED_WORK_ONSTACK(&w->work, wedge_me);
-	schedule_delayed_work(&w->work, timeout);
-}
-
-static void __fini_wedge(struct wedge_me *w)
-{
-	cancel_delayed_work_sync(&w->work);
-	destroy_delayed_work_on_stack(&w->work);
-	w->i915 = NULL;
-}
-
-#define wedge_on_timeout(W, DEV, TIMEOUT)				\
-	for (__init_wedge((W), (DEV), (TIMEOUT), __builtin_return_address(0)); \
-	     (W)->i915;							\
-	     __fini_wedge((W)))
-
 int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 {
-	struct wedge_me w;
-
 	cond_resched();
 
 	if (flags & I915_WAIT_LOCKED &&
@@ -63,8 +19,15 @@ int igt_flush_test(struct drm_i915_private *i915, unsigned int flags)
 		i915_gem_set_wedged(i915);
 	}
 
-	wedge_on_timeout(&w, i915, HZ)
-		i915_gem_wait_for_idle(i915, flags, MAX_SCHEDULE_TIMEOUT);
+	if (i915_gem_wait_for_idle(i915, flags, HZ / 5) == -ETIME) {
+		pr_err("%pS timed out, cancelling all further testing.\n",
+		       __builtin_return_address(0));
+
+		GEM_TRACE("%pS timed out.\n", __builtin_return_address(0));
+		GEM_TRACE_DUMP();
+
+		i915_gem_set_wedged(i915);
+	}
 
 	return i915_terminally_wedged(&i915->gpu_error) ? -EIO : 0;
 }
-- 
cgit v1.2.3


From f8b52dd50ccdae7efc42ef54278f29d2f9d6cb36 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Tue, 3 Jul 2018 09:18:14 +0800
Subject: gpio: mxc: Add clocks optional binding for imx gpio

Some i.MX SoCs have GPIO clock gate in CCM, accessing
GPIO registers needs to enable GPIO clock gate first,
i.MX GPIO driver will enable clock gate if there is
clock property in GPIO node of dtb, add optional property
to i.MX GPIO binding doc.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/gpio/fsl-imx-gpio.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/gpio/fsl-imx-gpio.txt b/Documentation/devicetree/bindings/gpio/fsl-imx-gpio.txt
index dbd22e0df21e..b4cd9f906c24 100644
--- a/Documentation/devicetree/bindings/gpio/fsl-imx-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/fsl-imx-gpio.txt
@@ -19,6 +19,9 @@ Required properties:
       4 = active high level-sensitive.
       8 = active low level-sensitive.
 
+Optional properties:
+- clocks: the clock for clocking the GPIO silicon
+
 Example:
 
 gpio0: gpio@73f84000 {
-- 
cgit v1.2.3


From 36b312792b97933dc07abe074f50941199bd357c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 3 Jul 2018 03:38:31 +0300
Subject: gpiolib: Respect error code of ->get_direction()

In case we try to lock GPIO pin as IRQ when something going wrong
we print a misleading message.

Correct this by checking an error code from ->get_direction() in
gpiochip_lock_as_irq() and printing a corresponding message.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index f15a222205c6..8ec51b7777c6 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3262,6 +3262,12 @@ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 	if (!chip->can_sleep && chip->get_direction) {
 		int dir = chip->get_direction(chip, offset);
 
+		if (dir < 0) {
+			chip_err(chip, "%s: cannot get GPIO direction\n",
+				 __func__);
+			return dir;
+		}
+
 		if (dir)
 			clear_bit(FLAG_IS_OUT, &desc->flags);
 		else
-- 
cgit v1.2.3


From 8853daf3b4acb3bf8c0244a12b4f58ed5123f449 Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <jmkrzyszt@gmail.com>
Date: Wed, 4 Jul 2018 00:18:19 +0200
Subject: gpiolib: Defer on non-DT find_chip_by_name() failure

Avoid replication of error code conversion in non-DT GPIO consumers'
code by returning -EPROBE_DEFER from gpiod_find() in case a chip
identified by its label in a registered lookup table is not ready.

See https://lkml.org/lkml/2018/5/30/176 for example case.

Suggested-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Janusz Krzysztofik <jmkrzyszt@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 8ec51b7777c6..a9a290999990 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3656,9 +3656,16 @@ static struct gpio_desc *gpiod_find(struct device *dev, const char *con_id,
 		chip = find_chip_by_name(p->chip_label);
 
 		if (!chip) {
-			dev_err(dev, "cannot find GPIO chip %s\n",
-				p->chip_label);
-			return ERR_PTR(-ENODEV);
+			/*
+			 * As the lookup table indicates a chip with
+			 * p->chip_label should exist, assume it may
+			 * still appear later and let the interested
+			 * consumer be probed again or let the Deferred
+			 * Probe infrastructure handle the error.
+			 */
+			dev_warn(dev, "cannot find GPIO chip %s, deferring\n",
+				 p->chip_label);
+			return ERR_PTR(-EPROBE_DEFER);
 		}
 
 		if (chip->ngpio <= p->chip_hwnum) {
-- 
cgit v1.2.3


From 76411a0d97c3b216ce1c987aa4afa7f3789c89d9 Mon Sep 17 00:00:00 2001
From: Rafael David Tinoco <rafael.tinoco@linaro.org>
Date: Wed, 6 Jun 2018 14:44:24 -0300
Subject: gpio: selftests: gpio-mockup-chardev GPIOHANDLE_REQUEST_OUTPUT fix

Following logic from commit: 22f6592b23, GPIOHANDLE_REQUEST_OUTPUT
should handle errors same way as GPIOHANDLE_REQUEST_INPUT does, or else
the following error occurs:

gpio-mockup-chardev: gpio<gpiochip1> line<0> test flag<0x2> value<0>: No
such file or directory

despite the real result of gpio_pin_test(), gpio_debugfs_get() and
gpiotools_request_linehandle() functions.

Signed-off-by: Rafael David Tinoco <rafael.tinoco@linaro.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 tools/testing/selftests/gpio/gpio-mockup-chardev.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/gpio/gpio-mockup-chardev.c b/tools/testing/selftests/gpio/gpio-mockup-chardev.c
index 667e916fa7cc..f8d468f54e98 100644
--- a/tools/testing/selftests/gpio/gpio-mockup-chardev.c
+++ b/tools/testing/selftests/gpio/gpio-mockup-chardev.c
@@ -225,10 +225,10 @@ int gpio_pin_test(struct gpiochip_info *cinfo, int line, int flag, int value)
 		if (flag & GPIOHANDLE_REQUEST_ACTIVE_LOW)
 			debugfs_value = !debugfs_value;
 
-		if (!(debugfs_dir == OUT && value == debugfs_value))
+		if (!(debugfs_dir == OUT && value == debugfs_value)) {
 			errno = -EINVAL;
-		ret = -errno;
-
+			ret = -errno;
+		}
 	}
 	gpiotools_release_linehandle(fd);
 
-- 
cgit v1.2.3


From 932cac10c8fb07e72a1eba28e71b92f7f2cd756e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 14:01:58 +0100
Subject: drm/i915/selftests: Prevent background reaping of active objects

igt_mmap_offset_exhaustion() wants to test what happens when the mmap
space is filled with zombie objects, objects discarded by userspace but
still active on the GPU. As they are only protected by the active
reference, we have to be certain that active reference is kept while we
peek into our dangling pointer. That active reference should not be
freed until we retire, but we do that retirement from a background
thread. This leaves us with a subtle timing problem, exacerbated and
highlighted by KASAN:

<3>[  132.380399] BUG: KASAN: use-after-free in drm_gem_create_mmap_offset+0x8c/0xd0
<3>[  132.380430] Read of size 8 at addr ffff8801e13245f8 by task drv_selftest/5822

<4>[  132.380470] CPU: 0 PID: 5822 Comm: drv_selftest Tainted: G     U            4.18.0-rc3-g7ae7763aa2be-kasan_48+ #1
<4>[  132.380473] Hardware name: Dell Inc. XPS 8300  /0Y2MRG, BIOS A06 10/17/2011
<4>[  132.380475] Call Trace:
<4>[  132.380481]  dump_stack+0x7c/0xbb
<4>[  132.380487]  print_address_description+0x65/0x270
<4>[  132.380493]  kasan_report+0x25b/0x380
<4>[  132.380497]  ? drm_gem_create_mmap_offset+0x8c/0xd0
<4>[  132.380503]  drm_gem_create_mmap_offset+0x8c/0xd0
<4>[  132.380584]  i915_gem_object_create_mmap_offset+0x6d/0x100 [i915]
<4>[  132.380650]  igt_mmap_offset_exhaustion+0x462/0x940 [i915]
<4>[  132.380714]  ? i915_gem_close_object+0x740/0x740 [i915]
<4>[  132.380784]  ? igt_gem_huge+0x269/0x3d0 [i915]
<4>[  132.380865]  __i915_subtests+0x5a/0x160 [i915]
<4>[  132.380936]  __run_selftests+0x1a2/0x2f0 [i915]
<4>[  132.381008]  i915_live_selftests+0x4e/0x80 [i915]
<4>[  132.381071]  i915_pci_probe+0xd8/0x1b0 [i915]
<4>[  132.381077]  pci_device_probe+0x1c5/0x3a0
<4>[  132.381087]  driver_probe_device+0x6b6/0xcb0
<4>[  132.381094]  __driver_attach+0x22d/0x2c0
<4>[  132.381100]  ? driver_probe_device+0xcb0/0xcb0
<4>[  132.381103]  bus_for_each_dev+0x113/0x1a0
<4>[  132.381108]  ? check_flags.part.24+0x450/0x450
<4>[  132.381112]  ? subsys_dev_iter_exit+0x10/0x10
<4>[  132.381123]  bus_add_driver+0x38b/0x6e0
<4>[  132.381131]  driver_register+0x189/0x400
<4>[  132.381136]  ? 0xffffffffc12d8000
<4>[  132.381140]  do_one_initcall+0xa0/0x4c0
<4>[  132.381145]  ? initcall_blacklisted+0x180/0x180
<4>[  132.381152]  ? do_init_module+0x4a/0x54c
<4>[  132.381156]  ? rcu_lockdep_current_cpu_online+0xdc/0x130
<4>[  132.381161]  ? kasan_unpoison_shadow+0x30/0x40
<4>[  132.381169]  do_init_module+0x1b5/0x54c
<4>[  132.381177]  load_module+0x619e/0x9b70
<4>[  132.381202]  ? module_frob_arch_sections+0x20/0x20
<4>[  132.381211]  ? vfs_read+0x257/0x2f0
<4>[  132.381214]  ? vfs_read+0x257/0x2f0
<4>[  132.381221]  ? kernel_read+0x8b/0x130
<4>[  132.381231]  ? copy_strings_kernel+0x120/0x120
<4>[  132.381244]  ? __se_sys_finit_module+0x17c/0x1a0
<4>[  132.381248]  __se_sys_finit_module+0x17c/0x1a0
<4>[  132.381252]  ? __ia32_sys_init_module+0xa0/0xa0
<4>[  132.381261]  ? __se_sys_newstat+0x77/0xd0
<4>[  132.381265]  ? cp_new_stat+0x590/0x590
<4>[  132.381269]  ? kmem_cache_free+0x2f0/0x340
<4>[  132.381285]  do_syscall_64+0x97/0x400
<4>[  132.381292]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
<4>[  132.381295] RIP: 0033:0x7eff4af46839
<4>[  132.381297] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1f f6 2c 00 f7 d8 64 89 01 48
<4>[  132.381426] RSP: 002b:00007ffcd84f4cf8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
<4>[  132.381432] RAX: ffffffffffffffda RBX: 000055dfdeb429a0 RCX: 00007eff4af46839
<4>[  132.381435] RDX: 0000000000000000 RSI: 000055dfdeb43670 RDI: 0000000000000004
<4>[  132.381437] RBP: 000055dfdeb43670 R08: 0000000000000004 R09: 0000000000000000
<4>[  132.381440] R10: 00007ffcd84f4e60 R11: 0000000000000246 R12: 0000000000000000
<4>[  132.381442] R13: 000055dfdeb3bec0 R14: 0000000000000000 R15: 000000000000003b

<3>[  132.381466] Allocated by task 5822:
<4>[  132.381485]  kmem_cache_alloc+0xdf/0x2e0
<4>[  132.381546]  i915_gem_object_create_internal+0x24/0x1e0 [i915]
<4>[  132.381609]  igt_mmap_offset_exhaustion+0x257/0x940 [i915]
<4>[  132.381677]  __i915_subtests+0x5a/0x160 [i915]
<4>[  132.381742]  __run_selftests+0x1a2/0x2f0 [i915]
<4>[  132.381806]  i915_live_selftests+0x4e/0x80 [i915]
<4>[  132.381865]  i915_pci_probe+0xd8/0x1b0 [i915]
<4>[  132.381868]  pci_device_probe+0x1c5/0x3a0
<4>[  132.381871]  driver_probe_device+0x6b6/0xcb0
<4>[  132.381874]  __driver_attach+0x22d/0x2c0
<4>[  132.381877]  bus_for_each_dev+0x113/0x1a0
<4>[  132.381880]  bus_add_driver+0x38b/0x6e0
<4>[  132.381884]  driver_register+0x189/0x400
<4>[  132.381886]  do_one_initcall+0xa0/0x4c0
<4>[  132.381889]  do_init_module+0x1b5/0x54c
<4>[  132.381892]  load_module+0x619e/0x9b70
<4>[  132.381895]  __se_sys_finit_module+0x17c/0x1a0
<4>[  132.381898]  do_syscall_64+0x97/0x400
<4>[  132.381901]  entry_SYSCALL_64_after_hwframe+0x49/0xbe

<3>[  132.381914] Freed by task 150:
<4>[  132.381931]  kmem_cache_free+0xb7/0x340
<4>[  132.381995]  __i915_gem_free_objects+0x875/0xf50 [i915]
<4>[  132.382054]  __i915_gem_free_work+0x69/0xb0 [i915]
<4>[  132.382058]  process_one_work+0x78b/0x1740
<4>[  132.382061]  worker_thread+0x82/0xb80
<4>[  132.382064]  kthread+0x30c/0x3d0
<4>[  132.382067]  ret_from_fork+0x3a/0x50

<3>[  132.382081] The buggy address belongs to the object at ffff8801e1324500
                   which belongs to the cache drm_i915_gem_object of size 1168
<3>[  132.382133] The buggy address is located 248 bytes inside of
                   1168-byte region [ffff8801e1324500, ffff8801e1324990)
<3>[  132.382179] The buggy address belongs to the page:
<0>[  132.382202] page:ffffea000784c800 count:1 mapcount:0 mapping:ffff8801dedf6500 index:0xffff8801e1323ec0 compound_mapcount: 0
<0>[  132.382251] flags: 0x8000000000008100(slab|head)
<1>[  132.382274] raw: 8000000000008100 ffff8801d6317440 ffff8801d6317440 ffff8801dedf6500
<1>[  132.382307] raw: ffff8801e1323ec0 0000000000140013 00000001ffffffff 0000000000000000
<1>[  132.382339] page dumped because: kasan: bad access detected

<3>[  132.382373] Memory state around the buggy address:
<3>[  132.382395]  ffff8801e1324480: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
<3>[  132.382426]  ffff8801e1324500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
<3>[  132.382457] >ffff8801e1324580: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
<3>[  132.382488]                                                                 ^
<3>[  132.382517]  ffff8801e1324600: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
<3>[  132.382548]  ffff8801e1324680: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

This patch tricks the system into running without the background retire
thread, until after we finish the test. The only reaping should then be
performed by the mmap offset routine to reclaim the space as required.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709130208.11730-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_object.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index f4a5099c75b5..d77acf4cc439 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -507,6 +507,15 @@ static int igt_mmap_offset_exhaustion(void *arg)
 	u64 hole_start, hole_end;
 	int loop, err;
 
+	/* Disable background reaper */
+	mutex_lock(&i915->drm.struct_mutex);
+	if (!i915->gt.active_requests++)
+		i915_gem_unpark(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	cancel_delayed_work_sync(&i915->gt.retire_work);
+	cancel_delayed_work_sync(&i915->gt.idle_work);
+	GEM_BUG_ON(!i915->gt.awake);
+
 	/* Trim the device mmap space to only a page */
 	memset(&resv, 0, sizeof(resv));
 	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
@@ -515,7 +524,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 		err = drm_mm_reserve_node(mm, &resv);
 		if (err) {
 			pr_err("Failed to trim VMA manager, err=%d\n", err);
-			return err;
+			goto out_park;
 		}
 		break;
 	}
@@ -576,6 +585,7 @@ static int igt_mmap_offset_exhaustion(void *arg)
 			goto err_obj;
 		}
 
+		/* NB we rely on the _active_ reference to access obj now */
 		GEM_BUG_ON(!i915_gem_object_is_active(obj));
 		err = i915_gem_object_create_mmap_offset(obj);
 		if (err) {
@@ -587,6 +597,13 @@ static int igt_mmap_offset_exhaustion(void *arg)
 
 out:
 	drm_mm_remove_node(&resv);
+out_park:
+	mutex_lock(&i915->drm.struct_mutex);
+	if (--i915->gt.active_requests)
+		queue_delayed_work(i915->wq, &i915->gt.retire_work, 0);
+	else
+		queue_delayed_work(i915->wq, &i915->gt.idle_work, 0);
+	mutex_unlock(&i915->drm.struct_mutex);
 	return err;
 err_obj:
 	i915_gem_object_put(obj);
-- 
cgit v1.2.3


From f441108fa08c466d986a7dca776f59dabab58456 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:17 -0700
Subject: block: Remove a superfluous cast from blkdev_report_zones()

No cast is necessary when assigning a non-void pointer to a void
pointer.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 51000914e23f..c461cf63f1f4 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -200,7 +200,7 @@ int blkdev_report_zones(struct block_device *bdev,
 		/* Get header in the first page */
 		ofst = 0;
 		if (!nr_rep) {
-			hdr = (struct blk_zone_report_hdr *) addr;
+			hdr = addr;
 			nr_rep = hdr->nr_zones;
 			ofst = sizeof(struct blk_zone_report_hdr);
 		}
-- 
cgit v1.2.3


From b3e7e7d2d668de0102264302a4d10dd9d4438a42 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:18 -0700
Subject: include/uapi/linux/blkzoned.h: Remove a superfluous __packed
 directive

Using the __packed directive for a structure that does not need
it is wrong because it makes gcc generate suboptimal code on some
architectures. Hence remove the __packed directive from the
blk_zone_report structure definition. See also
http://digitalvampire.org/blog/index.php/2006/07/31/why-you-shouldnt-use-__attribute__packed/.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/blkzoned.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/blkzoned.h b/include/uapi/linux/blkzoned.h
index e3c70fe6bf0f..ff5a5db8906a 100644
--- a/include/uapi/linux/blkzoned.h
+++ b/include/uapi/linux/blkzoned.h
@@ -117,7 +117,7 @@ struct blk_zone_report {
 	__u32		nr_zones;
 	__u8		reserved[4];
 	struct blk_zone zones[0];
-} __packed;
+};
 
 /**
  * struct blk_zone_range - BLKRESETZONE ioctl request
-- 
cgit v1.2.3


From 6b1d83d274486615cc341e410467a98fd9c27c0a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:19 -0700
Subject: block: Remove bdev_nr_zones()

Remove this function since it has no callers. This function was
introduced in commit 6cc77e9cb080 ("block: introduce zoned block
devices zone write locking").

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Matias Bjorling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 79226ca8f80f..49a400afb146 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1639,15 +1639,6 @@ static inline unsigned int bdev_zone_sectors(struct block_device *bdev)
 	return 0;
 }
 
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return blk_queue_nr_zones(q);
-	return 0;
-}
-
 static inline int queue_dma_alignment(struct request_queue *q)
 {
 	return q ? q->dma_alignment : 511;
-- 
cgit v1.2.3


From 7c8542b7982264226cf94102950343185869b584 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:20 -0700
Subject: block: Inline blk_queue_nr_zones()

Since the implementation of blk_queue_nr_zones() is trivial and since
it only has a single caller, inline this function.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c | 2 +-
 include/linux/blkdev.h | 5 -----
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 1c4532e92938..26e1f8e425a8 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -214,7 +214,7 @@ static int queue_zone_wlock_show(void *data, struct seq_file *m)
 	if (!q->seq_zones_wlock)
 		return 0;
 
-	for (i = 0; i < blk_queue_nr_zones(q); i++)
+	for (i = 0; i < q->nr_zones; i++)
 		if (test_bit(i, q->seq_zones_wlock))
 			seq_printf(m, "%u\n", i);
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 49a400afb146..905daa7c647e 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -800,11 +800,6 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
-static inline unsigned int blk_queue_nr_zones(struct request_queue *q)
-{
-	return q->nr_zones;
-}
-
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
-- 
cgit v1.2.3


From 6a5ac9846508ad7d1d23881d9d5add35f2e6ae71 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 15 Jun 2018 14:55:21 -0700
Subject: block: Make struct request_queue smaller for CONFIG_BLK_DEV_ZONED=n

Exclude zoned block device members from struct request_queue for
CONFIG_BLK_DEV_ZONED == n. Avoid breaking the build by only building
the code that uses these struct request_queue members if
CONFIG_BLK_DEV_ZONED != n.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Damien Le Moal <damien.lemoal@wdc.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Kconfig                |  4 ++++
 block/Makefile               |  1 +
 block/blk-mq-debugfs-zoned.c | 24 ++++++++++++++++++++++++
 block/blk-mq-debugfs.c       | 15 ---------------
 block/blk-mq-debugfs.h       |  9 +++++++++
 include/linux/blkdev.h       |  6 ++++++
 6 files changed, 44 insertions(+), 15 deletions(-)
 create mode 100644 block/blk-mq-debugfs-zoned.c

diff --git a/block/Kconfig b/block/Kconfig
index eb50fd4977c2..dfe7bc770fc9 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -177,6 +177,10 @@ config BLK_DEBUG_FS
 	Unless you are building a kernel for a tiny system, you should
 	say Y here.
 
+config BLK_DEBUG_FS_ZONED
+       bool
+       default BLK_DEBUG_FS && BLK_DEV_ZONED
+
 config BLK_SED_OPAL
 	bool "Logic for interfacing with Opal enabled SEDs"
 	---help---
diff --git a/block/Makefile b/block/Makefile
index 6a56303b9925..a8f94cdb75c3 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -34,4 +34,5 @@ obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o
+obj-$(CONFIG_BLK_DEBUG_FS_ZONED)+= blk-mq-debugfs-zoned.o
 obj-$(CONFIG_BLK_SED_OPAL)	+= sed-opal.o
diff --git a/block/blk-mq-debugfs-zoned.c b/block/blk-mq-debugfs-zoned.c
new file mode 100644
index 000000000000..fb2c82c351e4
--- /dev/null
+++ b/block/blk-mq-debugfs-zoned.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2017 Western Digital Corporation or its affiliates.
+ *
+ * This file is released under the GPL.
+ */
+
+#include <linux/blkdev.h>
+#include "blk-mq-debugfs.h"
+
+int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	struct request_queue *q = data;
+	unsigned int i;
+
+	if (!q->seq_zones_wlock)
+		return 0;
+
+	for (i = 0; i < q->nr_zones; i++)
+		if (test_bit(i, q->seq_zones_wlock))
+			seq_printf(m, "%u\n", i);
+
+	return 0;
+}
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 26e1f8e425a8..7efe268e4447 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -206,21 +206,6 @@ static ssize_t queue_write_hint_store(void *data, const char __user *buf,
 	return count;
 }
 
-static int queue_zone_wlock_show(void *data, struct seq_file *m)
-{
-	struct request_queue *q = data;
-	unsigned int i;
-
-	if (!q->seq_zones_wlock)
-		return 0;
-
-	for (i = 0; i < q->nr_zones; i++)
-		if (test_bit(i, q->seq_zones_wlock))
-			seq_printf(m, "%u\n", i);
-
-	return 0;
-}
-
 static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
 	{ "poll_stat", 0400, queue_poll_stat_show },
 	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
diff --git a/block/blk-mq-debugfs.h b/block/blk-mq-debugfs.h
index b9d366e57097..a9160be12be0 100644
--- a/block/blk-mq-debugfs.h
+++ b/block/blk-mq-debugfs.h
@@ -80,4 +80,13 @@ static inline void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hc
 }
 #endif
 
+#ifdef CONFIG_BLK_DEBUG_FS_ZONED
+int queue_zone_wlock_show(void *data, struct seq_file *m);
+#else
+static inline int queue_zone_wlock_show(void *data, struct seq_file *m)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 905daa7c647e..ca5a8b046894 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -592,6 +592,7 @@ struct request_queue {
 
 	struct queue_limits	limits;
 
+#ifdef CONFIG_BLK_DEV_ZONED
 	/*
 	 * Zoned block device information for request dispatch control.
 	 * nr_zones is the total number of zones of the device. This is always
@@ -612,6 +613,7 @@ struct request_queue {
 	unsigned int		nr_zones;
 	unsigned long		*seq_zones_bitmap;
 	unsigned long		*seq_zones_wlock;
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 	/*
 	 * sg stuff
@@ -800,6 +802,7 @@ static inline unsigned int blk_queue_zone_sectors(struct request_queue *q)
 	return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_queue_zone_no(struct request_queue *q,
 					     sector_t sector)
 {
@@ -815,6 +818,7 @@ static inline bool blk_queue_zone_is_seq(struct request_queue *q,
 		return false;
 	return test_bit(blk_queue_zone_no(q, sector), q->seq_zones_bitmap);
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline bool rq_is_sync(struct request *rq)
 {
@@ -1065,6 +1069,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
 	return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT;
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
 static inline unsigned int blk_rq_zone_no(struct request *rq)
 {
 	return blk_queue_zone_no(rq->q, blk_rq_pos(rq));
@@ -1074,6 +1079,7 @@ static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
 {
 	return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq));
 }
+#endif /* CONFIG_BLK_DEV_ZONED */
 
 /*
  * Some commands like WRITE SAME have a payload or data transfer size which
-- 
cgit v1.2.3


From 0471559c2fbd2c19d183fc0f51ce88aefa0a13c8 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 25 Jun 2018 21:55:34 +0200
Subject: block, bfq: add/remove entity weights correctly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To keep I/O throughput high as often as possible, BFQ performs
I/O-dispatch plugging (aka device idling) only when beneficial exactly
for throughput, or when needed for service guarantees (low latency,
fairness). An important case where the latter condition holds is when
the scenario is 'asymmetric' in terms of weights: i.e., when some
bfq_queue or whole group of queues has a higher weight, and thus has
to receive more service, than other queues or groups. Without dispatch
plugging, lower-weight queues/groups may unjustly steal bandwidth to
higher-weight queues/groups.

To detect asymmetric scenarios, BFQ checks some sufficient
conditions. One of these conditions is that active groups have
different weights. BFQ controls this condition by maintaining a
special set of unique weights of active groups
(group_weights_tree). To this purpose, in the function
bfq_active_insert/bfq_active_extract BFQ adds/removes the weight of a
group to/from this set.

Unfortunately, the function bfq_active_extract may happen to be
invoked also for a group that is still active (to preserve the correct
update of the next queue to serve, see comments in function
bfq_no_longer_next_in_service() for details). In this case, removing
the weight of the group makes the set group_weights_tree
inconsistent. Service-guarantee violations follow.

This commit addresses this issue by moving group_weights_tree
insertions from their previous location (in bfq_active_insert) into
the function __bfq_activate_entity, and by moving group_weights_tree
extractions from bfq_active_extract to when the entity that represents
a group remains throughly idle, i.e., with no request either enqueued
or dispatched.

Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c | 45 +++++++++++++++++++++++++++++++++++++++++----
 block/bfq-iosched.h |  7 +++++--
 block/bfq-wf2q.c    | 24 +++++++++++++-----------
 3 files changed, 59 insertions(+), 17 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 495b9ddb3355..3f32e88c7e9b 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -742,8 +742,9 @@ inc_counter:
  * See the comments to the function bfq_weights_tree_add() for considerations
  * about overhead.
  */
-void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
-			     struct rb_root *root)
+void __bfq_weights_tree_remove(struct bfq_data *bfqd,
+			       struct bfq_entity *entity,
+			       struct rb_root *root)
 {
 	if (!entity->weight_counter)
 		return;
@@ -759,6 +760,43 @@ reset_entity_pointer:
 	entity->weight_counter = NULL;
 }
 
+/*
+ * Invoke __bfq_weights_tree_remove on bfqq and all its inactive
+ * parent entities.
+ */
+void bfq_weights_tree_remove(struct bfq_data *bfqd,
+			     struct bfq_queue *bfqq)
+{
+	struct bfq_entity *entity = bfqq->entity.parent;
+
+	__bfq_weights_tree_remove(bfqd, &bfqq->entity,
+				  &bfqd->queue_weights_tree);
+
+	for_each_entity(entity) {
+		struct bfq_sched_data *sd = entity->my_sched_data;
+
+		if (sd->next_in_service || sd->in_service_entity) {
+			/*
+			 * entity is still active, because either
+			 * next_in_service or in_service_entity is not
+			 * NULL (see the comments on the definition of
+			 * next_in_service for details on why
+			 * in_service_entity must be checked too).
+			 *
+			 * As a consequence, the weight of entity is
+			 * not to be removed. In addition, if entity
+			 * is active, then its parent entities are
+			 * active as well, and thus their weights are
+			 * not to be removed either. In the end, this
+			 * loop must stop here.
+			 */
+			break;
+		}
+		__bfq_weights_tree_remove(bfqd, entity,
+					  &bfqd->group_weights_tree);
+	}
+}
+
 /*
  * Return expired entry, or NULL to just start from scratch in rbtree.
  */
@@ -4582,8 +4620,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 		 */
 		bfqq->budget_timeout = jiffies;
 
-		bfq_weights_tree_remove(bfqd, &bfqq->entity,
-					&bfqd->queue_weights_tree);
+		bfq_weights_tree_remove(bfqd, bfqq);
 	}
 
 	now_ns = ktime_get_ns();
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 0f712e03b035..a8a2e5aca4d4 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -827,8 +827,11 @@ struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
 void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
 void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
 			  struct rb_root *root);
-void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
-			     struct rb_root *root);
+void __bfq_weights_tree_remove(struct bfq_data *bfqd,
+			       struct bfq_entity *entity,
+			       struct rb_root *root);
+void bfq_weights_tree_remove(struct bfq_data *bfqd,
+			     struct bfq_queue *bfqq);
 void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 		     bool compensate, enum bfqq_expiration reason);
 void bfq_put_queue(struct bfq_queue *bfqq);
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 4498c43245e2..58cf38fcee05 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -499,9 +499,6 @@ static void bfq_active_insert(struct bfq_service_tree *st,
 	if (bfqq)
 		list_add(&bfqq->bfqq_list, &bfqq->bfqd->active_list);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	else /* bfq_group */
-		bfq_weights_tree_add(bfqd, entity, &bfqd->group_weights_tree);
-
 	if (bfqg != bfqd->root_group)
 		bfqg->active_entities++;
 #endif
@@ -601,10 +598,6 @@ static void bfq_active_extract(struct bfq_service_tree *st,
 	if (bfqq)
 		list_del(&bfqq->bfqq_list);
 #ifdef CONFIG_BFQ_GROUP_IOSCHED
-	else /* bfq_group */
-		bfq_weights_tree_remove(bfqd, entity,
-					&bfqd->group_weights_tree);
-
 	if (bfqg != bfqd->root_group)
 		bfqg->active_entities--;
 #endif
@@ -799,7 +792,7 @@ __bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
 		if (prev_weight != new_weight) {
 			root = bfqq ? &bfqd->queue_weights_tree :
 				      &bfqd->group_weights_tree;
-			bfq_weights_tree_remove(bfqd, entity, root);
+			__bfq_weights_tree_remove(bfqd, entity, root);
 		}
 		entity->weight = new_weight;
 		/*
@@ -971,7 +964,7 @@ static void bfq_update_fin_time_enqueue(struct bfq_entity *entity,
  * one of its children receives a new request.
  *
  * Basically, this function updates the timestamps of entity and
- * inserts entity into its active tree, ater possibly extracting it
+ * inserts entity into its active tree, after possibly extracting it
  * from its idle tree.
  */
 static void __bfq_activate_entity(struct bfq_entity *entity,
@@ -1015,6 +1008,16 @@ static void __bfq_activate_entity(struct bfq_entity *entity,
 		entity->on_st = true;
 	}
 
+#ifdef BFQ_GROUP_IOSCHED_ENABLED
+	if (!bfq_entity_to_bfqq(entity)) { /* bfq_group */
+		struct bfq_group *bfqg =
+			container_of(entity, struct bfq_group, entity);
+
+		bfq_weights_tree_add(bfqg->bfqd, entity,
+				     &bfqd->group_weights_tree);
+	}
+#endif
+
 	bfq_update_fin_time_enqueue(entity, st, backshifted);
 }
 
@@ -1664,8 +1667,7 @@ void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
 	bfqd->busy_queues--;
 
 	if (!bfqq->dispatched)
-		bfq_weights_tree_remove(bfqd, &bfqq->entity,
-					&bfqd->queue_weights_tree);
+		bfq_weights_tree_remove(bfqd, bfqq);
 
 	if (bfqq->wr_coeff > 1)
 		bfqd->wr_busy_queues--;
-- 
cgit v1.2.3


From 4420b095cc474759f6fbdb6351648c7ff9833a54 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 25 Jun 2018 21:55:35 +0200
Subject: block, bfq: do not expire a queue that will deserve dispatch plugging
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For some bfq_queues, BFQ plugs I/O dispatching when the queue becomes
idle, and keeps the plug until a new request of the queue arrives, or
a timeout fires. BFQ does so either to boost throughput or to preserve
service guarantees for the queue.

More precisely, for such a queue, plugging starts when the queue
happens to have either no request enqueued, or no request in flight,
that is, no request already dispatched but not yet completed.

On the opposite end, BFQ may happen to expire a queue with no request
enqueued, without doing any plugging, if the queue still has some
request in flight. Unfortunately, such a premature expiration causes
the queue to lose its chance to enjoy dispatch plugging a moment
later, i.e., when its in-flight requests finally get completed. This
breaks service guarantees for the queue.

This commit prevents BFQ from expiring an empty queue if the latter
still has in-flight requests.

Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c | 36 +++++++++++++++++++++++++++++++++---
 1 file changed, 33 insertions(+), 3 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 3f32e88c7e9b..4fd4f1996498 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -3597,8 +3597,14 @@ static struct bfq_queue *bfq_select_queue(struct bfq_data *bfqd)
 
 	bfq_log_bfqq(bfqd, bfqq, "select_queue: already in-service queue");
 
+	/*
+	 * Do not expire bfqq for budget timeout if bfqq may be about
+	 * to enjoy device idling. The reason why, in this case, we
+	 * prevent bfqq from expiring is the same as in the comments
+	 * on the case where bfq_bfqq_must_idle() returns true, in
+	 * bfq_completed_request().
+	 */
 	if (bfq_may_expire_for_budg_timeout(bfqq) &&
-	    !bfq_bfqq_wait_request(bfqq) &&
 	    !bfq_bfqq_must_idle(bfqq))
 		goto expire;
 
@@ -4674,8 +4680,32 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 	 * or if we want to idle in case it has no pending requests.
 	 */
 	if (bfqd->in_service_queue == bfqq) {
-		if (bfqq->dispatched == 0 && bfq_bfqq_must_idle(bfqq)) {
-			bfq_arm_slice_timer(bfqd);
+		if (bfq_bfqq_must_idle(bfqq)) {
+			if (bfqq->dispatched == 0)
+				bfq_arm_slice_timer(bfqd);
+			/*
+			 * If we get here, we do not expire bfqq, even
+			 * if bfqq was in budget timeout or had no
+			 * more requests (as controlled in the next
+			 * conditional instructions). The reason for
+			 * not expiring bfqq is as follows.
+			 *
+			 * Here bfqq->dispatched > 0 holds, but
+			 * bfq_bfqq_must_idle() returned true. This
+			 * implies that, even if no request arrives
+			 * for bfqq before bfqq->dispatched reaches 0,
+			 * bfqq will, however, not be expired on the
+			 * completion event that causes bfqq->dispatch
+			 * to reach zero. In contrast, on this event,
+			 * bfqq will start enjoying device idling
+			 * (I/O-dispatch plugging).
+			 *
+			 * But, if we expired bfqq here, bfqq would
+			 * not have the chance to enjoy device idling
+			 * when bfqq->dispatched finally reaches
+			 * zero. This would expose bfqq to violation
+			 * of its reserved service guarantees.
+			 */
 			return;
 		} else if (bfq_may_expire_for_budg_timeout(bfqq))
 			bfq_bfqq_expire(bfqd, bfqq, false,
-- 
cgit v1.2.3


From 9fae8dd59ff3d9c19570cbddf12e87d7bb66c8a2 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 25 Jun 2018 21:55:36 +0200
Subject: block, bfq: fix service being wrongly set to zero in case of
 preemption
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If
- a bfq_queue Q preempts another queue, because one request of Q
arrives in time,
- but, after this preemption, Q is not the queue that is set in service,
then Q->entity.service is set to 0 when Q is eventually set in
service. But Q should have continued receiving service with its old
budget (which is why preemption has occurred) and its old service.

This commit addresses this issue by resetting service on queue real
expiration.

Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c | 34 ++++++++++++++++++++++++++++------
 block/bfq-wf2q.c    |  6 ------
 2 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index 4fd4f1996498..d579cc8e0db6 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -1382,18 +1382,30 @@ static bool bfq_bfqq_update_budg_for_activation(struct bfq_data *bfqd,
 		 * remain unchanged after such an expiration, and the
 		 * following statement therefore assigns to
 		 * entity->budget the remaining budget on such an
-		 * expiration. For clarity, entity->service is not
-		 * updated on expiration in any case, and, in normal
-		 * operation, is reset only when bfqq is selected for
-		 * service (see bfq_get_next_queue).
+		 * expiration.
 		 */
 		entity->budget = min_t(unsigned long,
 				       bfq_bfqq_budget_left(bfqq),
 				       bfqq->max_budget);
 
+		/*
+		 * At this point, we have used entity->service to get
+		 * the budget left (needed for updating
+		 * entity->budget). Thus we finally can, and have to,
+		 * reset entity->service. The latter must be reset
+		 * because bfqq would otherwise be charged again for
+		 * the service it has received during its previous
+		 * service slot(s).
+		 */
+		entity->service = 0;
+
 		return true;
 	}
 
+	/*
+	 * We can finally complete expiration, by setting service to 0.
+	 */
+	entity->service = 0;
 	entity->budget = max_t(unsigned long, bfqq->max_budget,
 			       bfq_serv_to_charge(bfqq->next_rq, bfqq));
 	bfq_clear_bfqq_non_blocking_wait_rq(bfqq);
@@ -3271,11 +3283,21 @@ void bfq_bfqq_expire(struct bfq_data *bfqd,
 	ref = bfqq->ref;
 	__bfq_bfqq_expire(bfqd, bfqq);
 
+	if (ref == 1) /* bfqq is gone, no more actions on it */
+		return;
+
 	/* mark bfqq as waiting a request only if a bic still points to it */
-	if (ref > 1 && !bfq_bfqq_busy(bfqq) &&
+	if (!bfq_bfqq_busy(bfqq) &&
 	    reason != BFQQE_BUDGET_TIMEOUT &&
-	    reason != BFQQE_BUDGET_EXHAUSTED)
+	    reason != BFQQE_BUDGET_EXHAUSTED) {
 		bfq_mark_bfqq_non_blocking_wait_rq(bfqq);
+		/*
+		 * Not setting service to 0, because, if the next rq
+		 * arrives in time, the queue will go on receiving
+		 * service with this same budget (as if it never expired)
+		 */
+	} else
+		entity->service = 0;
 }
 
 /*
diff --git a/block/bfq-wf2q.c b/block/bfq-wf2q.c
index 58cf38fcee05..dbc07b456059 100644
--- a/block/bfq-wf2q.c
+++ b/block/bfq-wf2q.c
@@ -1544,12 +1544,6 @@ struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd)
 		entity = sd->next_in_service;
 		sd->in_service_entity = entity;
 
-		/*
-		 * Reset the accumulator of the amount of service that
-		 * the entity is about to receive.
-		 */
-		entity->service = 0;
-
 		/*
 		 * If entity is no longer a candidate for next
 		 * service, then it must be extracted from its active
-- 
cgit v1.2.3


From 277a4a9b56cde0f3d53ea8abc0e43ff636820007 Mon Sep 17 00:00:00 2001
From: Paolo Valente <paolo.valente@linaro.org>
Date: Mon, 25 Jun 2018 21:55:37 +0200
Subject: block, bfq: give a better name to bfq_bfqq_may_idle
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The actual goal of the function bfq_bfqq_may_idle is to tell whether
it is better to perform device idling (more precisely: I/O-dispatch
plugging) for the input bfq_queue, either to boost throughput or to
preserve service guarantees. This commit improves the name of the
function accordingly.

Tested-by: Holger Hoffstätte <holger@applied-asynchrony.com>
Tested-by: Oleksandr Natalenko <oleksandr@natalenko.name>
Signed-off-by: Paolo Valente <paolo.valente@linaro.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index d579cc8e0db6..41d9036b1822 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -634,7 +634,7 @@ static bool bfq_differentiated_weights(struct bfq_data *bfqd)
  * The following function returns true if every queue must receive the
  * same share of the throughput (this condition is used when deciding
  * whether idling may be disabled, see the comments in the function
- * bfq_bfqq_may_idle()).
+ * bfq_better_to_idle()).
  *
  * Such a scenario occurs when:
  * 1) all active queues have the same weight,
@@ -3355,7 +3355,7 @@ static bool bfq_may_expire_for_budg_timeout(struct bfq_queue *bfqq)
  * issues taken into account are not trivial. We discuss these issues
  * individually while introducing the variables.
  */
-static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
+static bool bfq_better_to_idle(struct bfq_queue *bfqq)
 {
 	struct bfq_data *bfqd = bfqq->bfqd;
 	bool rot_without_queueing =
@@ -3588,19 +3588,19 @@ static bool bfq_bfqq_may_idle(struct bfq_queue *bfqq)
 }
 
 /*
- * If the in-service queue is empty but the function bfq_bfqq_may_idle
+ * If the in-service queue is empty but the function bfq_better_to_idle
  * returns true, then:
  * 1) the queue must remain in service and cannot be expired, and
  * 2) the device must be idled to wait for the possible arrival of a new
  *    request for the queue.
- * See the comments on the function bfq_bfqq_may_idle for the reasons
+ * See the comments on the function bfq_better_to_idle for the reasons
  * why performing device idling is the best choice to boost the throughput
- * and preserve service guarantees when bfq_bfqq_may_idle itself
+ * and preserve service guarantees when bfq_better_to_idle itself
  * returns true.
  */
 static bool bfq_bfqq_must_idle(struct bfq_queue *bfqq)
 {
-	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_bfqq_may_idle(bfqq);
+	return RB_EMPTY_ROOT(&bfqq->sort_list) && bfq_better_to_idle(bfqq);
 }
 
 /*
@@ -3686,7 +3686,7 @@ check_queue:
 	 * may idle after their completion, then keep it anyway.
 	 */
 	if (bfq_bfqq_wait_request(bfqq) ||
-	    (bfqq->dispatched != 0 && bfq_bfqq_may_idle(bfqq))) {
+	    (bfqq->dispatched != 0 && bfq_better_to_idle(bfqq))) {
 		bfqq = NULL;
 		goto keep_queue;
 	}
@@ -4734,7 +4734,7 @@ static void bfq_completed_request(struct bfq_queue *bfqq, struct bfq_data *bfqd)
 					BFQQE_BUDGET_TIMEOUT);
 		else if (RB_EMPTY_ROOT(&bfqq->sort_list) &&
 			 (bfqq->dispatched == 0 ||
-			  !bfq_bfqq_may_idle(bfqq)))
+			  !bfq_better_to_idle(bfqq)))
 			bfq_bfqq_expire(bfqd, bfqq, false,
 					BFQQE_NO_MORE_REQUESTS);
 	}
-- 
cgit v1.2.3


From 8ab6bb9ee8d04ba56b9eb19cc7e4f56d0a43ad1a Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 25 Jun 2018 19:31:45 +0800
Subject: blk-mq: cleanup blk_mq_get_driver_tag()

We never pass 'wait' as true to blk_mq_get_driver_tag(), and hence
we never change '**hctx' as well. The last use of these went away
with the flush cleanup, commit 0c2a6fe4dc3e.

So cleanup the usage and remove the two extra parameters.

Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Tested-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 19 +++++++------------
 block/blk-mq.h |  3 +--
 2 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 95919268564b..ae8a6b2c7c22 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -964,17 +964,14 @@ static inline unsigned int queued_to_index(unsigned int queued)
 	return min(BLK_MQ_MAX_DISPATCH_ORDER - 1, ilog2(queued) + 1);
 }
 
-bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
-			   bool wait)
+bool blk_mq_get_driver_tag(struct request *rq)
 {
 	struct blk_mq_alloc_data data = {
 		.q = rq->q,
 		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
-		.flags = wait ? 0 : BLK_MQ_REQ_NOWAIT,
+		.flags = BLK_MQ_REQ_NOWAIT,
 	};
 
-	might_sleep_if(wait);
-
 	if (rq->tag != -1)
 		goto done;
 
@@ -991,8 +988,6 @@ bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
 	}
 
 done:
-	if (hctx)
-		*hctx = data.hctx;
 	return rq->tag != -1;
 }
 
@@ -1034,7 +1029,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 		 * Don't clear RESTART here, someone else could have set it.
 		 * At most this will cost an extra queue run.
 		 */
-		return blk_mq_get_driver_tag(rq, hctx, false);
+		return blk_mq_get_driver_tag(rq);
 	}
 
 	wait = &this_hctx->dispatch_wait;
@@ -1055,7 +1050,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 	 * allocation failure and adding the hardware queue to the wait
 	 * queue.
 	 */
-	ret = blk_mq_get_driver_tag(rq, hctx, false);
+	ret = blk_mq_get_driver_tag(rq);
 	if (!ret) {
 		spin_unlock(&this_hctx->lock);
 		return false;
@@ -1105,7 +1100,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		if (!got_budget && !blk_mq_get_dispatch_budget(hctx))
 			break;
 
-		if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+		if (!blk_mq_get_driver_tag(rq)) {
 			/*
 			 * The initial allocation attempt failed, so we need to
 			 * rerun the hardware queue when a tag is freed. The
@@ -1137,7 +1132,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			bd.last = true;
 		else {
 			nxt = list_first_entry(list, struct request, queuelist);
-			bd.last = !blk_mq_get_driver_tag(nxt, NULL, false);
+			bd.last = !blk_mq_get_driver_tag(nxt);
 		}
 
 		ret = q->mq_ops->queue_rq(hctx, &bd);
@@ -1700,7 +1695,7 @@ static blk_status_t __blk_mq_try_issue_directly(struct blk_mq_hw_ctx *hctx,
 	if (!blk_mq_get_dispatch_budget(hctx))
 		goto insert;
 
-	if (!blk_mq_get_driver_tag(rq, NULL, false)) {
+	if (!blk_mq_get_driver_tag(rq)) {
 		blk_mq_put_dispatch_budget(hctx);
 		goto insert;
 	}
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 89231e439b2f..23659f41bf2c 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -36,8 +36,7 @@ int blk_mq_update_nr_requests(struct request_queue *q, unsigned int nr);
 void blk_mq_wake_waiters(struct request_queue *q);
 bool blk_mq_dispatch_rq_list(struct request_queue *, struct list_head *, bool);
 void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list);
-bool blk_mq_get_driver_tag(struct request *rq, struct blk_mq_hw_ctx **hctx,
-				bool wait);
+bool blk_mq_get_driver_tag(struct request *rq);
 struct request *blk_mq_dequeue_from_ctx(struct blk_mq_hw_ctx *hctx,
 					struct blk_mq_ctx *start);
 
-- 
cgit v1.2.3


From 2278d69f030f6cb7fdacba6281a46fb9d637d2aa Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 25 Jun 2018 19:31:46 +0800
Subject: blk-mq: don't pass **hctx to blk_mq_mark_tag_wait()

'hctx' won't be changed at all, so not necessary to pass
'**hctx' to blk_mq_mark_tag_wait().

Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Andrew Jones <drjones@redhat.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index ae8a6b2c7c22..9eee896a3592 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1009,17 +1009,16 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
  * restart. For both cases, take care to check the condition again after
  * marking us as waiting.
  */
-static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
+static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
-	struct blk_mq_hw_ctx *this_hctx = *hctx;
 	struct sbq_wait_state *ws;
 	wait_queue_entry_t *wait;
 	bool ret;
 
-	if (!(this_hctx->flags & BLK_MQ_F_TAG_SHARED)) {
-		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state))
-			set_bit(BLK_MQ_S_SCHED_RESTART, &this_hctx->state);
+	if (!(hctx->flags & BLK_MQ_F_TAG_SHARED)) {
+		if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
+			set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
 		/*
 		 * It's possible that a tag was freed in the window between the
@@ -1032,17 +1031,17 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 		return blk_mq_get_driver_tag(rq);
 	}
 
-	wait = &this_hctx->dispatch_wait;
+	wait = &hctx->dispatch_wait;
 	if (!list_empty_careful(&wait->entry))
 		return false;
 
-	spin_lock(&this_hctx->lock);
+	spin_lock(&hctx->lock);
 	if (!list_empty(&wait->entry)) {
-		spin_unlock(&this_hctx->lock);
+		spin_unlock(&hctx->lock);
 		return false;
 	}
 
-	ws = bt_wait_ptr(&this_hctx->tags->bitmap_tags, this_hctx);
+	ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx);
 	add_wait_queue(&ws->wait, wait);
 
 	/*
@@ -1052,7 +1051,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 	 */
 	ret = blk_mq_get_driver_tag(rq);
 	if (!ret) {
-		spin_unlock(&this_hctx->lock);
+		spin_unlock(&hctx->lock);
 		return false;
 	}
 
@@ -1063,7 +1062,7 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx **hctx,
 	spin_lock_irq(&ws->wait.lock);
 	list_del_init(&wait->entry);
 	spin_unlock_irq(&ws->wait.lock);
-	spin_unlock(&this_hctx->lock);
+	spin_unlock(&hctx->lock);
 
 	return true;
 }
@@ -1108,7 +1107,7 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 			 * before we add this entry back on the dispatch list,
 			 * we'll re-run it below.
 			 */
-			if (!blk_mq_mark_tag_wait(&hctx, rq)) {
+			if (!blk_mq_mark_tag_wait(hctx, rq)) {
 				blk_mq_put_dispatch_budget(hctx);
 				/*
 				 * For non-shared tags, the RESTART check
-- 
cgit v1.2.3


From 5815839b3ca16bb1d45939270871169f6803a121 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 25 Jun 2018 19:31:47 +0800
Subject: blk-mq: introduce new lock for protecting hctx->dispatch_wait

Now hctx->lock is only acquired when adding hctx->dispatch_wait to
one wait queue, but not held when removing it from the wait queue.

IO hang can be observed easily if SCHED RESTART is disabled, that means
now RESTART exits just for fixing the issue in blk_mq_mark_tag_wait().

This patch fixes the issue by introducing hctx->dispatch_wait_lock and
holding it for removing hctx->dispatch_wait in blk_mq_dispatch_wake(),
since we need to avoid acquiring hctx->lock in irq context.

Fixes: eb619fdb2d4cb8b3d3419 ("blk-mq: fix issue with shared tag queue re-running")
Cc: Christoph Hellwig <hch@lst.de>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c         | 26 +++++++++++++++++---------
 include/linux/blk-mq.h |  1 +
 2 files changed, 18 insertions(+), 9 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 9eee896a3592..df84281f6af6 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -998,7 +998,10 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 
 	hctx = container_of(wait, struct blk_mq_hw_ctx, dispatch_wait);
 
+	spin_lock(&hctx->dispatch_wait_lock);
 	list_del_init(&wait->entry);
+	spin_unlock(&hctx->dispatch_wait_lock);
+
 	blk_mq_run_hw_queue(hctx, true);
 	return 1;
 }
@@ -1012,7 +1015,7 @@ static int blk_mq_dispatch_wake(wait_queue_entry_t *wait, unsigned mode,
 static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 				 struct request *rq)
 {
-	struct sbq_wait_state *ws;
+	struct wait_queue_head *wq;
 	wait_queue_entry_t *wait;
 	bool ret;
 
@@ -1035,14 +1038,18 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	if (!list_empty_careful(&wait->entry))
 		return false;
 
-	spin_lock(&hctx->lock);
+	wq = &bt_wait_ptr(&hctx->tags->bitmap_tags, hctx)->wait;
+
+	spin_lock_irq(&wq->lock);
+	spin_lock(&hctx->dispatch_wait_lock);
 	if (!list_empty(&wait->entry)) {
-		spin_unlock(&hctx->lock);
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
 		return false;
 	}
 
-	ws = bt_wait_ptr(&hctx->tags->bitmap_tags, hctx);
-	add_wait_queue(&ws->wait, wait);
+	wait->flags &= ~WQ_FLAG_EXCLUSIVE;
+	__add_wait_queue(wq, wait);
 
 	/*
 	 * It's possible that a tag was freed in the window between the
@@ -1051,7 +1058,8 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	 */
 	ret = blk_mq_get_driver_tag(rq);
 	if (!ret) {
-		spin_unlock(&hctx->lock);
+		spin_unlock(&hctx->dispatch_wait_lock);
+		spin_unlock_irq(&wq->lock);
 		return false;
 	}
 
@@ -1059,10 +1067,9 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	 * We got a tag, remove ourselves from the wait queue to ensure
 	 * someone else gets the wakeup.
 	 */
-	spin_lock_irq(&ws->wait.lock);
 	list_del_init(&wait->entry);
-	spin_unlock_irq(&ws->wait.lock);
-	spin_unlock(&hctx->lock);
+	spin_unlock(&hctx->dispatch_wait_lock);
+	spin_unlock_irq(&wq->lock);
 
 	return true;
 }
@@ -2142,6 +2149,7 @@ static int blk_mq_init_hctx(struct request_queue *q,
 
 	hctx->nr_ctx = 0;
 
+	spin_lock_init(&hctx->dispatch_wait_lock);
 	init_waitqueue_func_entry(&hctx->dispatch_wait, blk_mq_dispatch_wake);
 	INIT_LIST_HEAD(&hctx->dispatch_wait.entry);
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index e3147eb74222..ea690254dab7 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -39,6 +39,7 @@ struct blk_mq_hw_ctx {
 	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
 
+	spinlock_t		dispatch_wait_lock;
 	wait_queue_entry_t	dispatch_wait;
 	atomic_t		wait_index;
 
-- 
cgit v1.2.3


From 97889f9ac24f8d2fc8e703ea7f80c162bab10d4d Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 25 Jun 2018 19:31:48 +0800
Subject: blk-mq: remove synchronize_rcu() from blk_mq_del_queue_tag_set()

We have to remove synchronize_rcu() from blk_queue_cleanup(),
otherwise long delay can be caused during lun probe. For removing
it, we have to avoid to iterate the set->tag_list in IO path, eg,
blk_mq_sched_restart().

This patch reverts 5b79413946d (Revert "blk-mq: don't handle
TAG_SHARED in restart"). Given we have fixed enough IO hang issue,
and there isn't any reason to restart all queues in one tags any more,
see the following reasons:

1) blk-mq core can deal with shared-tags case well via blk_mq_get_driver_tag(),
which can wake up queues waiting for driver tag.

2) SCSI is a bit special because it may return BLK_STS_RESOURCE if queue,
target or host is ready, but SCSI built-in restart can cover all these well,
see scsi_end_request(), queue will be rerun after any request initiated from
this host/target is completed.

In my test on scsi_debug(8 luns), this patch may improve IOPS by 20% ~ 30%
when running I/O on these 8 luns concurrently.

Fixes: 705cda97ee3a ("blk-mq: Make it safe to use RCU to iterate over blk_mq_tag_set.tag_list")
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Cc: linux-scsi@vger.kernel.org
Reported-by: Andrew Jones <drjones@redhat.com>
Tested-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c   | 85 +++-----------------------------------------------
 block/blk-mq.c         | 10 ++----
 include/linux/blkdev.h |  2 --
 3 files changed, 7 insertions(+), 90 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 56c493c6cd90..4e027f6108ae 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -59,29 +59,16 @@ static void blk_mq_sched_mark_restart_hctx(struct blk_mq_hw_ctx *hctx)
 	if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
 		return;
 
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (!test_and_set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_inc(&q->shared_hctx_restart);
-	} else
-		set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+	set_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 }
 
-static bool blk_mq_sched_restart_hctx(struct blk_mq_hw_ctx *hctx)
+void blk_mq_sched_restart(struct blk_mq_hw_ctx *hctx)
 {
 	if (!test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-		return false;
-
-	if (hctx->flags & BLK_MQ_F_TAG_SHARED) {
-		struct request_queue *q = hctx->queue;
-
-		if (test_and_clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-			atomic_dec(&q->shared_hctx_restart);
-	} else
-		clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
+		return;
+	clear_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state);
 
-	return blk_mq_run_hw_queue(hctx, true);
+	blk_mq_run_hw_queue(hctx, true);
 }
 
 /*
@@ -380,68 +367,6 @@ static bool blk_mq_sched_bypass_insert(struct blk_mq_hw_ctx *hctx,
 	return false;
 }
 
-/**
- * list_for_each_entry_rcu_rr - iterate in a round-robin fashion over rcu list
- * @pos:    loop cursor.
- * @skip:   the list element that will not be examined. Iteration starts at
- *          @skip->next.
- * @head:   head of the list to examine. This list must have at least one
- *          element, namely @skip.
- * @member: name of the list_head structure within typeof(*pos).
- */
-#define list_for_each_entry_rcu_rr(pos, skip, head, member)		\
-	for ((pos) = (skip);						\
-	     (pos = (pos)->member.next != (head) ? list_entry_rcu(	\
-			(pos)->member.next, typeof(*pos), member) :	\
-	      list_entry_rcu((pos)->member.next->next, typeof(*pos), member)), \
-	     (pos) != (skip); )
-
-/*
- * Called after a driver tag has been freed to check whether a hctx needs to
- * be restarted. Restarts @hctx if its tag set is not shared. Restarts hardware
- * queues in a round-robin fashion if the tag set of @hctx is shared with other
- * hardware queues.
- */
-void blk_mq_sched_restart(struct blk_mq_hw_ctx *const hctx)
-{
-	struct blk_mq_tags *const tags = hctx->tags;
-	struct blk_mq_tag_set *const set = hctx->queue->tag_set;
-	struct request_queue *const queue = hctx->queue, *q;
-	struct blk_mq_hw_ctx *hctx2;
-	unsigned int i, j;
-
-	if (set->flags & BLK_MQ_F_TAG_SHARED) {
-		/*
-		 * If this is 0, then we know that no hardware queues
-		 * have RESTART marked. We're done.
-		 */
-		if (!atomic_read(&queue->shared_hctx_restart))
-			return;
-
-		rcu_read_lock();
-		list_for_each_entry_rcu_rr(q, queue, &set->tag_list,
-					   tag_set_list) {
-			queue_for_each_hw_ctx(q, hctx2, i)
-				if (hctx2->tags == tags &&
-				    blk_mq_sched_restart_hctx(hctx2))
-					goto done;
-		}
-		j = hctx->queue_num + 1;
-		for (i = 0; i < queue->nr_hw_queues; i++, j++) {
-			if (j == queue->nr_hw_queues)
-				j = 0;
-			hctx2 = queue->queue_hw_ctx[j];
-			if (hctx2->tags == tags &&
-			    blk_mq_sched_restart_hctx(hctx2))
-				break;
-		}
-done:
-		rcu_read_unlock();
-	} else {
-		blk_mq_sched_restart_hctx(hctx);
-	}
-}
-
 void blk_mq_sched_insert_request(struct request *rq, bool at_head,
 				 bool run_queue, bool async)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index df84281f6af6..7c6ff13171ef 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2335,15 +2335,10 @@ static void queue_set_hctx_shared(struct request_queue *q, bool shared)
 	int i;
 
 	queue_for_each_hw_ctx(q, hctx, i) {
-		if (shared) {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_inc(&q->shared_hctx_restart);
+		if (shared)
 			hctx->flags |= BLK_MQ_F_TAG_SHARED;
-		} else {
-			if (test_bit(BLK_MQ_S_SCHED_RESTART, &hctx->state))
-				atomic_dec(&q->shared_hctx_restart);
+		else
 			hctx->flags &= ~BLK_MQ_F_TAG_SHARED;
-		}
 	}
 }
 
@@ -2374,7 +2369,6 @@ static void blk_mq_del_queue_tag_set(struct request_queue *q)
 		blk_mq_update_tag_set_depth(set, false);
 	}
 	mutex_unlock(&set->tag_list_lock);
-	synchronize_rcu();
 	INIT_LIST_HEAD(&q->tag_set_list);
 }
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ca5a8b046894..9d05646d5059 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -442,8 +442,6 @@ struct request_queue {
 	int			nr_rqs[2];	/* # allocated [a]sync rqs */
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
-	atomic_t		shared_hctx_restart;
-
 	struct blk_queue_stats	*stats;
 	struct rq_wb		*rq_wb;
 
-- 
cgit v1.2.3


From 1311326cf4755c7ffefd20f576144ecf46d9906b Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 25 Jun 2018 19:31:49 +0800
Subject: blk-mq: avoid to synchronize rcu inside blk_cleanup_queue()

SCSI probing may synchronously create and destroy a lot of request_queues
for non-existent devices. Any synchronize_rcu() in queue creation or
destroy path may introduce long latency during booting, see detailed
description in comment of blk_register_queue().

This patch removes one synchronize_rcu() inside blk_cleanup_queue()
for this case, commit c2856ae2f315d75(blk-mq: quiesce queue before freeing queue)
needs synchronize_rcu() for implementing blk_mq_quiesce_queue(), but
when queue isn't initialized, it isn't necessary to do that since
only pass-through requests are involved, no original issue in
scsi_execute() at all.

Without this patch and previous one, it may take more 20+ seconds for
virtio-scsi to complete disk probe. With the two patches, the time becomes
less than 100ms.

Fixes: c2856ae2f315d75 ("blk-mq: quiesce queue before freeing queue")
Reported-by: Andrew Jones <drjones@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: linux-scsi@vger.kernel.org
Cc: "Martin K. Petersen" <martin.petersen@oracle.com>
Cc: Christoph Hellwig <hch@lst.de>
Tested-by: Andrew Jones <drjones@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index f84a9b7b6f5a..947e7a4abd8c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -762,9 +762,13 @@ void blk_cleanup_queue(struct request_queue *q)
 	 * make sure all in-progress dispatch are completed because
 	 * blk_freeze_queue() can only complete all requests, and
 	 * dispatch may still be in-progress since we dispatch requests
-	 * from more than one contexts
+	 * from more than one contexts.
+	 *
+	 * No need to quiesce queue if it isn't initialized yet since
+	 * blk_freeze_queue() should be enough for cases of passthrough
+	 * request.
 	 */
-	if (q->mq_ops)
+	if (q->mq_ops && blk_queue_init_done(q))
 		blk_mq_quiesce_queue(q);
 
 	/* for synchronous bio-based driver finish in-flight integrity i/o */
-- 
cgit v1.2.3


From d05d199883b09cd34937ebb045adbed9098e9780 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 25 Jun 2018 15:51:00 -0700
Subject: drbd: Do not redefine __must_hold()

Since __must_hold() is defined in <linux/compiler_types.h>, do not
redefine it in DRBD. Compile-tested only.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_int.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/block/drbd/drbd_int.h b/drivers/block/drbd/drbd_int.h
index bc4ed2ed40a2..e35a234b0a8f 100644
--- a/drivers/block/drbd/drbd_int.h
+++ b/drivers/block/drbd/drbd_int.h
@@ -55,12 +55,10 @@
 # define __protected_by(x)       __attribute__((require_context(x,1,999,"rdwr")))
 # define __protected_read_by(x)  __attribute__((require_context(x,1,999,"read")))
 # define __protected_write_by(x) __attribute__((require_context(x,1,999,"write")))
-# define __must_hold(x)       __attribute__((context(x,1,1), require_context(x,1,999,"call")))
 #else
 # define __protected_by(x)
 # define __protected_read_by(x)
 # define __protected_write_by(x)
-# define __must_hold(x)
 #endif
 
 /* shared module parameters, defined in drbd_main.c */
-- 
cgit v1.2.3


From 1954e9a998d59d08520d7d4bebeafb8f66ba0d0f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Wed, 27 Jun 2018 13:09:05 -0700
Subject: block: Document how blk_update_request() handles RQF_SPECIAL_PAYLOAD
 requests

The payload of struct request is stored in the request.bio chain if
the RQF_SPECIAL_PAYLOAD flag is not set and in request.special_vec if
RQF_SPECIAL_PAYLOAD has been set. However, blk_update_request()
iterates over req->bio whether or not RQF_SPECIAL_PAYLOAD has been
set. Additionally, the RQF_SPECIAL_PAYLOAD flag is ignored by
blk_rq_bytes() which means that the value returned by that function
is incorrect if the RQF_SPECIAL_PAYLOAD flag has been set. It is not
clear to me whether this is an oversight or whether this happened on
purpose. Anyway, document that it is known that both functions ignore
RQF_SPECIAL_PAYLOAD. See also commit f9d03f96b988 ("block: improve
handling of the magic discard payload").

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/block/blk-core.c b/block/blk-core.c
index 947e7a4abd8c..2ff8e131a892 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -3056,6 +3056,10 @@ EXPORT_SYMBOL_GPL(blk_steal_bios);
  *     Passing the result of blk_rq_bytes() as @nr_bytes guarantees
  *     %false return from this function.
  *
+ * Note:
+ *	The RQF_SPECIAL_PAYLOAD flag is ignored on purpose in both
+ *	blk_rq_bytes() and in blk_update_request().
+ *
  * Return:
  *     %false - this request doesn't have any more data
  *     %true  - this request has more data
-- 
cgit v1.2.3


From e1a413245a564683697a3d02ec197b72cf009b89 Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.liu@linux.alibaba.com>
Date: Fri, 29 Jun 2018 09:56:08 +0800
Subject: Blktrace: bail out early if block debugfs is not configured

Since @blk_debugfs_root couldn't be configured dynamically, we can
save a few memory allocation if it's not there.

Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/trace/blktrace.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 987d9a9ae283..b951aa1fac61 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -494,6 +494,9 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 	if (!buts->buf_size || !buts->buf_nr)
 		return -EINVAL;
 
+	if (!blk_debugfs_root)
+		return -ENOENT;
+
 	strncpy(buts->name, name, BLKTRACE_BDEV_SIZE);
 	buts->name[BLKTRACE_BDEV_SIZE - 1] = '\0';
 
@@ -518,9 +521,6 @@ static int do_blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
 
 	ret = -ENOENT;
 
-	if (!blk_debugfs_root)
-		goto err;
-
 	dir = debugfs_lookup(buts->name, blk_debugfs_root);
 	if (!dir)
 		bt->dir = dir = debugfs_create_dir(buts->name, blk_debugfs_root);
-- 
cgit v1.2.3


From 43ada78781246cb36036f26158a645c17550ac54 Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.liu@linux.alibaba.com>
Date: Fri, 29 Jun 2018 09:56:56 +0800
Subject: Block: blk-throttle: set low_valid immediately once one cgroup has
 io.low configured

Once one cgroup has io.low configured, @low_valid becomes true and other
cgroups won't switch it back whatsoever.

Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 82282e6fdcf8..63bb261811dd 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -579,8 +579,10 @@ static void blk_throtl_update_limit_valid(struct throtl_data *td)
 		struct throtl_grp *tg = blkg_to_tg(blkg);
 
 		if (tg->bps[READ][LIMIT_LOW] || tg->bps[WRITE][LIMIT_LOW] ||
-		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW])
+		    tg->iops[READ][LIMIT_LOW] || tg->iops[WRITE][LIMIT_LOW]) {
 			low_valid = true;
+			break;
+		}
 	}
 	rcu_read_unlock();
 
-- 
cgit v1.2.3


From b64a71a0130dd2a88b0fc36a3c0a4882f47813e8 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 2 Jul 2018 08:42:34 +0100
Subject: block/floppy: remove redundant variable dflags

Variable dflags is being assigned but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: variable 'dflags' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/floppy.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index 8871b5044d9e..48f622728ce6 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -1461,7 +1461,6 @@ static void setup_rw_floppy(void)
 	int i;
 	int r;
 	int flags;
-	int dflags;
 	unsigned long ready_date;
 	void (*function)(void);
 
@@ -1485,8 +1484,6 @@ static void setup_rw_floppy(void)
 		if (fd_wait_for_completion(ready_date, function))
 			return;
 	}
-	dflags = DRS->flags;
-
 	if ((flags & FD_RAW_READ) || (flags & FD_RAW_WRITE))
 		setup_DMA();
 
-- 
cgit v1.2.3


From f4354a94e2097fe87a14d47ff502754bb547029a Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 2 Jul 2018 08:47:06 +0100
Subject: loop: remove redundant pointer inode

Pointer inode is being assigned but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: variable 'inode' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 4cb1d1be3cfb..bae472646e4a 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -690,7 +690,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 			  unsigned int arg)
 {
 	struct file	*file, *old_file;
-	struct inode	*inode;
 	int		error;
 
 	error = -ENXIO;
@@ -711,7 +710,6 @@ static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
 	if (error)
 		goto out_putf;
 
-	inode = file->f_mapping->host;
 	old_file = lo->lo_backing_file;
 
 	error = -EINVAL;
-- 
cgit v1.2.3


From e84422cdf3caa9cf35e625076dc62977f0023992 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 2 Jul 2018 08:13:59 +0100
Subject: partitions/ldm: remove redundant pointer dgrp

Pointer dgrp is being assigned but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: variable 'dgrp' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/ldm.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/block/partitions/ldm.c b/block/partitions/ldm.c
index 0417937dfe99..16766f267559 100644
--- a/block/partitions/ldm.c
+++ b/block/partitions/ldm.c
@@ -830,7 +830,6 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb)
 {
 	char buf[64];
 	int r_objid, r_name, r_id1, r_id2, len;
-	struct vblk_dgrp *dgrp;
 
 	BUG_ON (!buffer || !vb);
 
@@ -853,8 +852,6 @@ static bool ldm_parse_dgr4 (const u8 *buffer, int buflen, struct vblk *vb)
 	if (len != get_unaligned_be32(buffer + 0x14))
 		return false;
 
-	dgrp = &vb->vblk.dgrp;
-
 	ldm_get_vstr (buffer + 0x18 + r_objid, buf, sizeof (buf));
 	return true;
 }
-- 
cgit v1.2.3


From 5efac89c849849ad3a959224eb711f9c311e5bde Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 2 Jul 2018 09:14:19 +0100
Subject: paride: remove redundant variable n

Variable n is being assigned but is never used hence it is redundant
and can be removed. Also put spacing between variables in declaration
to clean up checkpatch warnings.

Cleans up clang warning:
warning: variable 'n' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/paride/bpck.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/block/paride/bpck.c b/drivers/block/paride/bpck.c
index 4f27e7392e38..f5f63ca2889d 100644
--- a/drivers/block/paride/bpck.c
+++ b/drivers/block/paride/bpck.c
@@ -347,7 +347,7 @@ static int bpck_test_proto( PIA *pi, char * scratch, int verbose )
 
 static void bpck_read_eeprom ( PIA *pi, char * buf )
 
-{       int i,j,k,n,p,v,f, om, od;
+{       int i, j, k, p, v, f, om, od;
 
 	bpck_force_spp(pi);
 
@@ -356,7 +356,6 @@ static void bpck_read_eeprom ( PIA *pi, char * buf )
 
 	bpck_connect(pi);
 	
-	n = 0;
 	WR(4,0);
 	for (i=0;i<64;i++) {
 	    WR(6,8);  
-- 
cgit v1.2.3


From 0da73d00ca111a6175825a00d94dbeae185f6d7e Mon Sep 17 00:00:00 2001
From: Minwoo Im <minwoo.im.dev@gmail.com>
Date: Mon, 2 Jul 2018 23:46:43 +0900
Subject: blk-mq: code clean-up by adding an API to clear set->mq_map

set->mq_map is now currently cleared if something goes wrong when
establishing a queue map in blk-mq-pci.c.  It's also cleared before
updating a queue map in blk_mq_update_queue_map().

This patch provides an API to clear set->mq_map to make it clear.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-pci.c | 5 +++--
 block/blk-mq.c     | 4 +---
 block/blk-mq.h     | 8 ++++++++
 3 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/block/blk-mq-pci.c b/block/blk-mq-pci.c
index e233996bb76f..db644ec624f5 100644
--- a/block/blk-mq-pci.c
+++ b/block/blk-mq-pci.c
@@ -17,6 +17,8 @@
 #include <linux/pci.h>
 #include <linux/module.h>
 
+#include "blk-mq.h"
+
 /**
  * blk_mq_pci_map_queues - provide a default queue mapping for PCI device
  * @set:	tagset to provide the mapping for
@@ -48,8 +50,7 @@ int blk_mq_pci_map_queues(struct blk_mq_tag_set *set, struct pci_dev *pdev,
 
 fallback:
 	WARN_ON_ONCE(set->nr_hw_queues > 1);
-	for_each_possible_cpu(cpu)
-		set->mq_map[cpu] = 0;
+	blk_mq_clear_mq_map(set);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(blk_mq_pci_map_queues);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 7c6ff13171ef..3cc074ae5c59 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2683,7 +2683,6 @@ static int blk_mq_alloc_rq_maps(struct blk_mq_tag_set *set)
 static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 {
 	if (set->ops->map_queues) {
-		int cpu;
 		/*
 		 * transport .map_queues is usually done in the following
 		 * way:
@@ -2698,8 +2697,7 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 		 * killing stale mapping since one CPU may not be mapped
 		 * to any hw queue.
 		 */
-		for_each_possible_cpu(cpu)
-			set->mq_map[cpu] = 0;
+		blk_mq_clear_mq_map(set);
 
 		return set->ops->map_queues(set);
 	} else
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 23659f41bf2c..bc2b24735ed4 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -202,4 +202,12 @@ static inline void blk_mq_put_driver_tag(struct request *rq)
 	__blk_mq_put_driver_tag(hctx, rq);
 }
 
+static inline void blk_mq_clear_mq_map(struct blk_mq_tag_set *set)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		set->mq_map[cpu] = 0;
+}
+
 #endif
-- 
cgit v1.2.3


From c018c84fdb453ae057f3bcc87a1f1f730d41628b Mon Sep 17 00:00:00 2001
From: Minwoo Im <minwoo.im.dev@gmail.com>
Date: Sat, 30 Jun 2018 22:12:41 +0900
Subject: blk-mq: fix typo in a function comment

Fix typo in a function blk_mq_alloc_tag_set() comment.
if if it too large -> if it's too large.

Signed-off-by: Minwoo Im <minwoo.im.dev@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 3cc074ae5c59..acf31ad733bf 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -2707,7 +2707,7 @@ static int blk_mq_update_queue_map(struct blk_mq_tag_set *set)
 /*
  * Alloc a tag set to be associated with one or more request queues.
  * May fail with EINVAL for various error conditions. May adjust the
- * requested depth down, if if it too large. In that case, the set
+ * requested depth down, if it's too large. In that case, the set
  * value will be stored in set->queue_depth.
  */
 int blk_mq_alloc_tag_set(struct blk_mq_tag_set *set)
-- 
cgit v1.2.3


From 3f0cedc7e9a0b32e79c79d2aac0c96d2b870ae55 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 2 Jul 2018 17:35:58 +0800
Subject: blk-mq: use list_splice_tail_init() to insert requests

list_splice_tail_init() is much more faster than inserting each
request one by one, given all requets in 'list' belong to
same sw queue and ctx->lock is required to insert requests.

Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index acf31ad733bf..795ba859b16b 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1545,19 +1545,19 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 			    struct list_head *list)
 
 {
+	struct request *rq;
+
 	/*
 	 * preemption doesn't flush plug list, so it's possible ctx->cpu is
 	 * offline now
 	 */
-	spin_lock(&ctx->lock);
-	while (!list_empty(list)) {
-		struct request *rq;
-
-		rq = list_first_entry(list, struct request, queuelist);
+	list_for_each_entry(rq, list, queuelist) {
 		BUG_ON(rq->mq_ctx != ctx);
-		list_del_init(&rq->queuelist);
-		__blk_mq_insert_req_list(hctx, rq, false);
+		trace_block_rq_insert(hctx->queue, rq);
 	}
+
+	spin_lock(&ctx->lock);
+	list_splice_tail_init(list, &ctx->rq_list);
 	blk_mq_hctx_mark_pending(hctx, ctx);
 	spin_unlock(&ctx->lock);
 }
-- 
cgit v1.2.3


From b04f50ab8a74129b3041a2836c33c916be3c6667 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 2 Jul 2018 17:35:59 +0800
Subject: blk-mq: only attempt to merge bio if there is rq in sw queue

Only attempt to merge bio iff the ctx->rq_list isn't empty, because:

1) for high-performance SSD, most of times dispatch may succeed, then
there may be nothing left in ctx->rq_list, so don't try to merge over
sw queue if it is empty, then we can save one acquiring of ctx->lock

2) we can't expect good merge performance on per-cpu sw queue, and missing
one merge on sw queue won't be a big deal since tasks can be scheduled from
one CPU to another.

Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reported-by: Kashyap Desai <kashyap.desai@broadcom.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index 4e027f6108ae..f3b4b5ceb4d1 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -326,7 +326,8 @@ bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
 		return e->type->ops.mq.bio_merge(hctx, bio);
 	}
 
-	if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) {
+	if ((hctx->flags & BLK_MQ_F_SHOULD_MERGE) &&
+			!list_empty_careful(&ctx->rq_list)) {
 		/* default per sw-queue merge */
 		spin_lock(&ctx->lock);
 		ret = blk_mq_attempt_merge(q, ctx, bio);
-- 
cgit v1.2.3


From d769a992966b0a188096fda24fc08fc769ec6547 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 2 Jul 2018 12:49:02 -0500
Subject: drbd: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Warning level 2 was used in this case: -Wimplicit-fallthrough=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_receiver.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index be9450f5ad1c..a36a30795c43 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2790,6 +2790,7 @@ static int receive_DataRequest(struct drbd_connection *connection, struct packet
 		   then we would do something smarter here than reading
 		   the block... */
 		peer_req->flags |= EE_RS_THIN_REQ;
+		/* fall through */
 	case P_RS_DATA_REQUEST:
 		peer_req->w.cb = w_e_end_rsdata_req;
 		fault_type = DRBD_FAULT_RS_RD;
@@ -2968,6 +2969,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		/* Else fall through to one of the other strategies... */
 		drbd_warn(device, "Discard younger/older primary did not find a decision\n"
 		     "Using discard-least-changes instead\n");
+		/* fall through */
 	case ASB_DISCARD_ZERO_CHG:
 		if (ch_peer == 0 && ch_self == 0) {
 			rv = test_bit(RESOLVE_CONFLICTS, &peer_device->connection->flags)
@@ -2979,6 +2981,7 @@ static int drbd_asb_recover_0p(struct drbd_peer_device *peer_device) __must_hold
 		}
 		if (after_sb_0p == ASB_DISCARD_ZERO_CHG)
 			break;
+		/* else: fall through */
 	case ASB_DISCARD_LEAST_CHG:
 		if	(ch_self < ch_peer)
 			rv = -1;
-- 
cgit v1.2.3


From d893ff86034f7107f89d8b740c2b5902a21a49db Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 2 Jul 2018 12:52:06 -0500
Subject: block/loop: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/loop.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index bae472646e4a..ea9debf59b22 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -1609,6 +1609,7 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 	case LOOP_GET_STATUS64:
 	case LOOP_SET_STATUS64:
 		arg = (unsigned long) compat_ptr(arg);
+		/* fall through */
 	case LOOP_SET_FD:
 	case LOOP_CHANGE_FD:
 	case LOOP_SET_BLOCK_SIZE:
-- 
cgit v1.2.3


From 6e768717304bdbe8d2897ca8298f6b58863fdc41 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 3 Jul 2018 09:03:16 -0600
Subject: blk-mq: dequeue request one by one from sw queue if hctx is busy

It won't be efficient to dequeue request one by one from sw queue,
but we have to do that when queue is busy for better merge performance.

This patch takes the Exponential Weighted Moving Average(EWMA) to figure
out if queue is busy, then only dequeue request one by one from sw queue
when queue is busy.

Fixes: b347689ffbca ("blk-mq-sched: improve dispatching from sw queue")
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Reported-by: Kashyap Desai <kashyap.desai@broadcom.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-debugfs.c |  9 +++++++++
 block/blk-mq-sched.c   | 11 ++---------
 block/blk-mq.c         | 33 ++++++++++++++++++++++++++++++++-
 include/linux/blk-mq.h |  3 ++-
 4 files changed, 45 insertions(+), 11 deletions(-)

diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 7efe268e4447..cb1e6cf7ac48 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -622,6 +622,14 @@ static int hctx_active_show(void *data, struct seq_file *m)
 	return 0;
 }
 
+static int hctx_dispatch_busy_show(void *data, struct seq_file *m)
+{
+	struct blk_mq_hw_ctx *hctx = data;
+
+	seq_printf(m, "%u\n", hctx->dispatch_busy);
+	return 0;
+}
+
 static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
 	__acquires(&ctx->lock)
 {
@@ -783,6 +791,7 @@ static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
 	{"queued", 0600, hctx_queued_show, hctx_queued_write},
 	{"run", 0600, hctx_run_show, hctx_run_write},
 	{"active", 0400, hctx_active_show},
+	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
 	{},
 };
 
diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index f3b4b5ceb4d1..fdc129e64cc4 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -206,15 +206,8 @@ void blk_mq_sched_dispatch_requests(struct blk_mq_hw_ctx *hctx)
 		}
 	} else if (has_sched_dispatch) {
 		blk_mq_do_dispatch_sched(hctx);
-	} else if (q->mq_ops->get_budget) {
-		/*
-		 * If we need to get budget before queuing request, we
-		 * dequeue request one by one from sw queue for avoiding
-		 * to mess up I/O merge when dispatch runs out of resource.
-		 *
-		 * TODO: get more budgets, and dequeue more requests in
-		 * one time.
-		 */
+	} else if (hctx->dispatch_busy) {
+		/* dequeue request one by one from sw queue if queue is busy */
 		blk_mq_do_dispatch_ctx(hctx);
 	} else {
 		blk_mq_flush_busy_ctxs(hctx, &rq_list);
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 795ba859b16b..850fdd02c385 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1074,6 +1074,35 @@ static bool blk_mq_mark_tag_wait(struct blk_mq_hw_ctx *hctx,
 	return true;
 }
 
+#define BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT  8
+#define BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR  4
+/*
+ * Update dispatch busy with the Exponential Weighted Moving Average(EWMA):
+ * - EWMA is one simple way to compute running average value
+ * - weight(7/8 and 1/8) is applied so that it can decrease exponentially
+ * - take 4 as factor for avoiding to get too small(0) result, and this
+ *   factor doesn't matter because EWMA decreases exponentially
+ */
+static void blk_mq_update_dispatch_busy(struct blk_mq_hw_ctx *hctx, bool busy)
+{
+	unsigned int ewma;
+
+	if (hctx->queue->elevator)
+		return;
+
+	ewma = hctx->dispatch_busy;
+
+	if (!ewma && !busy)
+		return;
+
+	ewma *= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT - 1;
+	if (busy)
+		ewma += 1 << BLK_MQ_DISPATCH_BUSY_EWMA_FACTOR;
+	ewma /= BLK_MQ_DISPATCH_BUSY_EWMA_WEIGHT;
+
+	hctx->dispatch_busy = ewma;
+}
+
 #define BLK_MQ_RESOURCE_DELAY	3		/* ms units */
 
 /*
@@ -1210,8 +1239,10 @@ bool blk_mq_dispatch_rq_list(struct request_queue *q, struct list_head *list,
 		else if (needs_restart && (ret == BLK_STS_RESOURCE))
 			blk_mq_delay_run_hw_queue(hctx, BLK_MQ_RESOURCE_DELAY);
 
+		blk_mq_update_dispatch_busy(hctx, true);
 		return false;
-	}
+	} else
+		blk_mq_update_dispatch_busy(hctx, false);
 
 	/*
 	 * If the host/device is unable to accept more work, inform the
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index ea690254dab7..d710e92874cc 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -35,9 +35,10 @@ struct blk_mq_hw_ctx {
 	struct sbitmap		ctx_map;
 
 	struct blk_mq_ctx	*dispatch_from;
+	unsigned int		dispatch_busy;
 
-	struct blk_mq_ctx	**ctxs;
 	unsigned int		nr_ctx;
+	struct blk_mq_ctx	**ctxs;
 
 	spinlock_t		dispatch_wait_lock;
 	wait_queue_entry_t	dispatch_wait;
-- 
cgit v1.2.3


From 08e18eab0c579ad84399c1899c11899734854eb2 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:14:50 -0400
Subject: block: add bi_blkg to the bio for cgroups

Currently io.low uses a bi_cg_private to stash its private data for the
blkg, however other blkcg policies may want to use this as well.  Since
we can get the private data out of the blkg, move this to bi_blkg in the
bio and make it generic, then we can use bio_associate_blkg() to attach
the blkg to the bio.

Theoretically we could simply replace the bi_css with this since we can
get to all the same information from the blkg, however you have to
lookup the blkg, so for example wbc_init_bio() would have to lookup and
possibly allocate the blkg for the css it was trying to attach to the
bio.  This could be problematic and result in us either not attaching
the css at all to the bio, or falling back to the root blkcg if we are
unable to allocate the corresponding blkg.

So for now do this, and in the future if possible we could just replace
the bi_css with bi_blkg and update the helpers to do the correct
translation.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c               | 23 +++++++++++++++++++++++
 block/blk-throttle.c      | 21 +++++++--------------
 include/linux/bio.h       |  1 +
 include/linux/blk_types.h |  2 +-
 4 files changed, 32 insertions(+), 15 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 67eff5eddc49..044571538574 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -28,6 +28,7 @@
 #include <linux/mempool.h>
 #include <linux/workqueue.h>
 #include <linux/cgroup.h>
+#include <linux/blk-cgroup.h>
 
 #include <trace/events/block.h>
 #include "blk.h"
@@ -2036,6 +2037,24 @@ int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css)
 }
 EXPORT_SYMBOL_GPL(bio_associate_blkcg);
 
+/**
+ * bio_associate_blkg - associate a bio with the specified blkg
+ * @bio: target bio
+ * @blkg: the blkg to associate
+ *
+ * Associate @bio with the blkg specified by @blkg.  This is the queue specific
+ * blkcg information associated with the @bio, a reference will be taken on the
+ * @blkg and will be freed when the bio is freed.
+ */
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg)
+{
+	if (unlikely(bio->bi_blkg))
+		return -EBUSY;
+	blkg_get(blkg);
+	bio->bi_blkg = blkg;
+	return 0;
+}
+
 /**
  * bio_disassociate_task - undo bio_associate_current()
  * @bio: target bio
@@ -2050,6 +2069,10 @@ void bio_disassociate_task(struct bio *bio)
 		css_put(bio->bi_css);
 		bio->bi_css = NULL;
 	}
+	if (bio->bi_blkg) {
+		blkg_put(bio->bi_blkg);
+		bio->bi_blkg = NULL;
+	}
 }
 
 /**
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 63bb261811dd..caaabbe8a7a5 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -2134,12 +2134,8 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td)
 static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio)
 {
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	if (bio->bi_css) {
-		if (bio->bi_cg_private)
-			blkg_put(tg_to_blkg(bio->bi_cg_private));
-		bio->bi_cg_private = tg;
-		blkg_get(tg_to_blkg(tg));
-	}
+	if (bio->bi_css)
+		bio_associate_blkg(bio, tg_to_blkg(tg));
 	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
 #endif
 }
@@ -2287,6 +2283,7 @@ void blk_throtl_stat_add(struct request *rq, u64 time_ns)
 
 void blk_throtl_bio_endio(struct bio *bio)
 {
+	struct blkcg_gq *blkg;
 	struct throtl_grp *tg;
 	u64 finish_time_ns;
 	unsigned long finish_time;
@@ -2294,20 +2291,18 @@ void blk_throtl_bio_endio(struct bio *bio)
 	unsigned long lat;
 	int rw = bio_data_dir(bio);
 
-	tg = bio->bi_cg_private;
-	if (!tg)
+	blkg = bio->bi_blkg;
+	if (!blkg)
 		return;
-	bio->bi_cg_private = NULL;
+	tg = blkg_to_tg(blkg);
 
 	finish_time_ns = ktime_get_ns();
 	tg->last_finish_time = finish_time_ns >> 10;
 
 	start_time = bio_issue_time(&bio->bi_issue) >> 10;
 	finish_time = __bio_issue_time(finish_time_ns) >> 10;
-	if (!start_time || finish_time <= start_time) {
-		blkg_put(tg_to_blkg(tg));
+	if (!start_time || finish_time <= start_time)
 		return;
-	}
 
 	lat = finish_time - start_time;
 	/* this is only for bio based driver */
@@ -2336,8 +2331,6 @@ void blk_throtl_bio_endio(struct bio *bio)
 		tg->bio_cnt /= 2;
 		tg->bad_bio_cnt /= 2;
 	}
-
-	blkg_put(tg_to_blkg(tg));
 }
 #endif
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index f08f5fe7bd08..a279ba384da9 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -555,6 +555,7 @@ do {						\
 
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
+int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg);
 void bio_disassociate_task(struct bio *bio);
 void bio_clone_blkcg_association(struct bio *dst, struct bio *src);
 #else	/* CONFIG_BLK_CGROUP */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 3c4f390aea4b..3364d42ebe08 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -179,8 +179,8 @@ struct bio {
 	 */
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
+	struct blkcg_gq		*bi_blkg;
 #ifdef CONFIG_BLK_DEV_THROTTLING_LOW
-	void			*bi_cg_private;
 	struct bio_issue	bi_issue;
 #endif
 #endif
-- 
cgit v1.2.3


From c7c98fd37653955d3a17dd4f1fa67aba070096a9 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:14:51 -0400
Subject: block: introduce bio_issue_as_root_blkg

Instead of forcing all file systems to get the right context on their
bio's, simply check for REQ_META to see if we need to issue as the root
blkg.  We don't want to force all bio's to have the root blkg associated
with them if REQ_META is set, as some controllers (blk-iolatency) need
to know who the originating cgroup is so it can backcharge them for the
work they are doing.  This helper will make sure that the controllers do
the proper thing wrt the IO priority and backcharging.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-cgroup.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 6c666fd7de3c..69aa71dc0c04 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -238,6 +238,22 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return css_to_blkcg(task_css(current, io_cgrp_id));
 }
 
+/**
+ * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
+ * @return: true if this bio needs to be submitted with the root blkg context.
+ *
+ * In order to avoid priority inversions we sometimes need to issue a bio as if
+ * it were attached to the root blkg, and then backcharge to the actual owning
+ * blkg.  The idea is we do bio_blkcg() to look up the actual context for the
+ * bio and attach the appropriate blkg to the bio.  Then we call this helper and
+ * if it is true run with the root blkg for that queue and then do any
+ * backcharging to the originating cgroup once the io is complete.
+ */
+static inline bool bio_issue_as_root_blkg(struct bio *bio)
+{
+	return (bio->bi_opf & REQ_META);
+}
+
 /**
  * blkcg_parent - get the parent of a blkcg
  * @blkcg: blkcg of interest
-- 
cgit v1.2.3


From 903d23f0a354f226fa78f1c1c34b60aaf992e812 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:14:52 -0400
Subject: blk-cgroup: allow controllers to output their own stats

blk-iolatency has a few stats that it would like to print out, and
instead of adding a bunch of crap to the generic code just provide a
helper so that controllers can add stuff to the stat line if they want
to.

Hide it behind a boot option since it changes the output of io.stat from
normal, and these stats are only interesting to developers.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c         | 47 +++++++++++++++++++++++++++++++++++++++++++---
 include/linux/blk-cgroup.h |  3 +++
 2 files changed, 47 insertions(+), 3 deletions(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index eb85cb87c40f..7dc6f05cc44b 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -50,6 +50,8 @@ static struct blkcg_policy *blkcg_policy[BLKCG_MAX_POLS];
 
 static LIST_HEAD(all_blkcgs);		/* protected by blkcg_pol_mutex */
 
+static bool blkcg_debug_stats = false;
+
 static bool blkcg_policy_enabled(struct request_queue *q,
 				 const struct blkcg_policy *pol)
 {
@@ -954,13 +956,25 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 	hlist_for_each_entry_rcu(blkg, &blkcg->blkg_list, blkcg_node) {
 		const char *dname;
+		char *buf;
 		struct blkg_rwstat rwstat;
 		u64 rbytes, wbytes, rios, wios;
+		size_t size = seq_get_buf(sf, &buf), off = 0;
+		int i;
+		bool has_stats = false;
 
 		dname = blkg_dev_name(blkg);
 		if (!dname)
 			continue;
 
+		/*
+		 * Hooray string manipulation, count is the size written NOT
+		 * INCLUDING THE \0, so size is now count+1 less than what we
+		 * had before, but we want to start writing the next bit from
+		 * the \0 so we only add count to buf.
+		 */
+		off += scnprintf(buf+off, size-off, "%s ", dname);
+
 		spin_lock_irq(blkg->q->queue_lock);
 
 		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
@@ -975,9 +989,33 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 
 		spin_unlock_irq(blkg->q->queue_lock);
 
-		if (rbytes || wbytes || rios || wios)
-			seq_printf(sf, "%s rbytes=%llu wbytes=%llu rios=%llu wios=%llu\n",
-				   dname, rbytes, wbytes, rios, wios);
+		if (rbytes || wbytes || rios || wios) {
+			has_stats = true;
+			off += scnprintf(buf+off, size-off,
+					 "rbytes=%llu wbytes=%llu rios=%llu wios=%llu",
+					 rbytes, wbytes, rios, wios);
+		}
+
+		if (!blkcg_debug_stats)
+			goto next;
+
+		for (i = 0; i < BLKCG_MAX_POLS; i++) {
+			struct blkcg_policy *pol = blkcg_policy[i];
+			size_t written;
+
+			if (!blkg->pd[i] || !pol->pd_stat_fn)
+				continue;
+
+			written = pol->pd_stat_fn(blkg->pd[i], buf+off, size-off);
+			if (written)
+				has_stats = true;
+			off += written;
+		}
+next:
+		if (has_stats) {
+			off += scnprintf(buf+off, size-off, "\n");
+			seq_commit(sf, off);
+		}
 	}
 
 	rcu_read_unlock();
@@ -1547,3 +1585,6 @@ out_unlock:
 	mutex_unlock(&blkcg_pol_register_mutex);
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
+
+module_param(blkcg_debug_stats, bool, 0644);
+MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 69aa71dc0c04..b41292726c0f 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -148,6 +148,8 @@ typedef void (blkcg_pol_online_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_offline_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_free_pd_fn)(struct blkg_policy_data *pd);
 typedef void (blkcg_pol_reset_pd_stats_fn)(struct blkg_policy_data *pd);
+typedef size_t (blkcg_pol_stat_pd_fn)(struct blkg_policy_data *pd, char *buf,
+				      size_t size);
 
 struct blkcg_policy {
 	int				plid;
@@ -167,6 +169,7 @@ struct blkcg_policy {
 	blkcg_pol_offline_pd_fn		*pd_offline_fn;
 	blkcg_pol_free_pd_fn		*pd_free_fn;
 	blkcg_pol_reset_pd_stats_fn	*pd_reset_stats_fn;
+	blkcg_pol_stat_pd_fn		*pd_stat_fn;
 };
 
 extern struct blkcg blkcg_root;
-- 
cgit v1.2.3


From 0d1e0c7cd5909d6c6aa0957179318e13fcca971a Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:14:53 -0400
Subject: blk: introduce REQ_SWAP

Just like REQ_META, it's important to know the IO coming down is swap
in order to guard against potential IO priority inversion issues with
cgroups.  Add REQ_SWAP and use it for all swap IO, and add it to our
bio_issue_as_root_blkg helper.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-cgroup.h | 2 +-
 include/linux/blk_types.h  | 3 ++-
 mm/page_io.c               | 2 +-
 3 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index b41292726c0f..a8f9ba8f33a4 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -254,7 +254,7 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
  */
 static inline bool bio_issue_as_root_blkg(struct bio *bio)
 {
-	return (bio->bi_opf & REQ_META);
+	return (bio->bi_opf & (REQ_META | REQ_SWAP)) != 0;
 }
 
 /**
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 3364d42ebe08..0ffc34c5cc83 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -329,7 +329,7 @@ enum req_flag_bits {
 
 	/* for driver use */
 	__REQ_DRV,
-
+	__REQ_SWAP,		/* swapping request. */
 	__REQ_NR_BITS,		/* stops here */
 };
 
@@ -351,6 +351,7 @@ enum req_flag_bits {
 #define REQ_NOUNMAP		(1ULL << __REQ_NOUNMAP)
 
 #define REQ_DRV			(1ULL << __REQ_DRV)
+#define REQ_SWAP		(1ULL << __REQ_SWAP)
 
 #define REQ_FAILFAST_MASK \
 	(REQ_FAILFAST_DEV | REQ_FAILFAST_TRANSPORT | REQ_FAILFAST_DRIVER)
diff --git a/mm/page_io.c b/mm/page_io.c
index b41cf9644585..a552cb37e220 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -338,7 +338,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		ret = -ENOMEM;
 		goto out;
 	}
-	bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
+	bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
 	count_swpout_vm_event(page);
 	set_page_writeback(page);
 	unlock_page(page);
-- 
cgit v1.2.3


From 0d3bd88d54f513723602b361dccfc71639f50779 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 3 Jul 2018 11:14:54 -0400
Subject: swap,blkcg: issue swap io with the appropriate context

For backcharging we need to know who the page belongs to when swapping
it out.  We don't worry about things that do ->rw_page (zram etc) at the
moment, we're only worried about pages that actually go to a block
device.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c         | 24 ++++++++++++++++++++++++
 include/linux/bio.h |  7 +++++++
 mm/page_io.c        |  1 +
 3 files changed, 32 insertions(+)

diff --git a/block/bio.c b/block/bio.c
index 044571538574..5f84f5c3887b 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -2015,6 +2015,30 @@ EXPORT_SYMBOL(bioset_init_from_src);
 
 #ifdef CONFIG_BLK_CGROUP
 
+#ifdef CONFIG_MEMCG
+/**
+ * bio_associate_blkcg_from_page - associate a bio with the page's blkcg
+ * @bio: target bio
+ * @page: the page to lookup the blkcg from
+ *
+ * Associate @bio with the blkcg from @page's owning memcg.  This works like
+ * every other associate function wrt references.
+ */
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page)
+{
+	struct cgroup_subsys_state *blkcg_css;
+
+	if (unlikely(bio->bi_css))
+		return -EBUSY;
+	if (!page->mem_cgroup)
+		return 0;
+	blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup,
+				     &io_cgrp_subsys);
+	bio->bi_css = blkcg_css;
+	return 0;
+}
+#endif /* CONFIG_MEMCG */
+
 /**
  * bio_associate_blkcg - associate a bio with the specified blkcg
  * @bio: target bio
diff --git a/include/linux/bio.h b/include/linux/bio.h
index a279ba384da9..a00dfff51aa5 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -553,6 +553,13 @@ do {						\
 #define bio_dev(bio) \
 	disk_devt((bio)->bi_disk)
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+int bio_associate_blkcg_from_page(struct bio *bio, struct page *page);
+#else
+static inline int bio_associate_blkcg_from_page(struct bio *bio,
+						struct page *page) {  return 0; }
+#endif
+
 #ifdef CONFIG_BLK_CGROUP
 int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css);
 int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg);
diff --git a/mm/page_io.c b/mm/page_io.c
index a552cb37e220..aafd19ec1db4 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -339,6 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc,
 		goto out;
 	}
 	bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc);
+	bio_associate_blkcg_from_page(bio, page);
 	count_swpout_vm_event(page);
 	set_page_writeback(page);
 	unlock_page(page);
-- 
cgit v1.2.3


From d09d8df3a29403693d9d20cc34ed101f2c558e2b Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:14:55 -0400
Subject: blkcg: add generic throttling mechanism

Since IO can be issued from literally anywhere it's almost impossible to
do throttling without having some sort of adverse effect somewhere else
in the system because of locking or other dependencies.  The best way to
solve this is to do the throttling when we know we aren't holding any
other kernel resources.  Do this by tracking throttling in a per-blkg
basis, and if we require throttling flag the task that it needs to check
before it returns to user space and possibly sleep there.

This is to address the case where a process is doing work that is
generating IO that can't be throttled, whether that is directly with a
lot of REQ_META IO, or indirectly by allocating so much memory that it
is swamping the disk with REQ_SWAP.  We can't use task_add_work as we
don't want to induce a memory allocation in the IO path, so simply
saving the request queue in the task and flagging it to do the
notify_resume thing achieves the same result without the overhead of a
memory allocation.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c          | 220 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/blk-cgroup.h  |  99 ++++++++++++++++++++
 include/linux/cgroup-defs.h |   3 +
 include/linux/sched.h       |   8 ++
 include/linux/tracehook.h   |   2 +
 5 files changed, 332 insertions(+)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 7dc6f05cc44b..d3310ec96c2a 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -27,6 +27,7 @@
 #include <linux/atomic.h>
 #include <linux/ctype.h>
 #include <linux/blk-cgroup.h>
+#include <linux/tracehook.h>
 #include "blk.h"
 
 #define MAX_KEY_LEN 100
@@ -999,6 +1000,14 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		if (!blkcg_debug_stats)
 			goto next;
 
+		if (atomic_read(&blkg->use_delay)) {
+			has_stats = true;
+			off += scnprintf(buf+off, size-off,
+					 " use_delay=%d delay_nsec=%llu",
+					 atomic_read(&blkg->use_delay),
+					(unsigned long long)atomic64_read(&blkg->delay_nsec));
+		}
+
 		for (i = 0; i < BLKCG_MAX_POLS; i++) {
 			struct blkcg_policy *pol = blkcg_policy[i];
 			size_t written;
@@ -1326,6 +1335,13 @@ static void blkcg_bind(struct cgroup_subsys_state *root_css)
 	mutex_unlock(&blkcg_pol_mutex);
 }
 
+static void blkcg_exit(struct task_struct *tsk)
+{
+	if (tsk->throttle_queue)
+		blk_put_queue(tsk->throttle_queue);
+	tsk->throttle_queue = NULL;
+}
+
 struct cgroup_subsys io_cgrp_subsys = {
 	.css_alloc = blkcg_css_alloc,
 	.css_offline = blkcg_css_offline,
@@ -1335,6 +1351,7 @@ struct cgroup_subsys io_cgrp_subsys = {
 	.dfl_cftypes = blkcg_files,
 	.legacy_cftypes = blkcg_legacy_files,
 	.legacy_name = "blkio",
+	.exit = blkcg_exit,
 #ifdef CONFIG_MEMCG
 	/*
 	 * This ensures that, if available, memcg is automatically enabled
@@ -1586,5 +1603,208 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(blkcg_policy_unregister);
 
+/*
+ * Scale the accumulated delay based on how long it has been since we updated
+ * the delay.  We only call this when we are adding delay, in case it's been a
+ * while since we added delay, and when we are checking to see if we need to
+ * delay a task, to account for any delays that may have occurred.
+ */
+static void blkcg_scale_delay(struct blkcg_gq *blkg, u64 now)
+{
+	u64 old = atomic64_read(&blkg->delay_start);
+
+	/*
+	 * We only want to scale down every second.  The idea here is that we
+	 * want to delay people for min(delay_nsec, NSEC_PER_SEC) in a certain
+	 * time window.  We only want to throttle tasks for recent delay that
+	 * has occurred, in 1 second time windows since that's the maximum
+	 * things can be throttled.  We save the current delay window in
+	 * blkg->last_delay so we know what amount is still left to be charged
+	 * to the blkg from this point onward.  blkg->last_use keeps track of
+	 * the use_delay counter.  The idea is if we're unthrottling the blkg we
+	 * are ok with whatever is happening now, and we can take away more of
+	 * the accumulated delay as we've already throttled enough that
+	 * everybody is happy with their IO latencies.
+	 */
+	if (time_before64(old + NSEC_PER_SEC, now) &&
+	    atomic64_cmpxchg(&blkg->delay_start, old, now) == old) {
+		u64 cur = atomic64_read(&blkg->delay_nsec);
+		u64 sub = min_t(u64, blkg->last_delay, now - old);
+		int cur_use = atomic_read(&blkg->use_delay);
+
+		/*
+		 * We've been unthrottled, subtract a larger chunk of our
+		 * accumulated delay.
+		 */
+		if (cur_use < blkg->last_use)
+			sub = max_t(u64, sub, blkg->last_delay >> 1);
+
+		/*
+		 * This shouldn't happen, but handle it anyway.  Our delay_nsec
+		 * should only ever be growing except here where we subtract out
+		 * min(last_delay, 1 second), but lord knows bugs happen and I'd
+		 * rather not end up with negative numbers.
+		 */
+		if (unlikely(cur < sub)) {
+			atomic64_set(&blkg->delay_nsec, 0);
+			blkg->last_delay = 0;
+		} else {
+			atomic64_sub(sub, &blkg->delay_nsec);
+			blkg->last_delay = cur - sub;
+		}
+		blkg->last_use = cur_use;
+	}
+}
+
+/*
+ * This is called when we want to actually walk up the hierarchy and check to
+ * see if we need to throttle, and then actually throttle if there is some
+ * accumulated delay.  This should only be called upon return to user space so
+ * we're not holding some lock that would induce a priority inversion.
+ */
+static void blkcg_maybe_throttle_blkg(struct blkcg_gq *blkg, bool use_memdelay)
+{
+	u64 now = ktime_to_ns(ktime_get());
+	u64 exp;
+	u64 delay_nsec = 0;
+	int tok;
+
+	while (blkg->parent) {
+		if (atomic_read(&blkg->use_delay)) {
+			blkcg_scale_delay(blkg, now);
+			delay_nsec = max_t(u64, delay_nsec,
+					   atomic64_read(&blkg->delay_nsec));
+		}
+		blkg = blkg->parent;
+	}
+
+	if (!delay_nsec)
+		return;
+
+	/*
+	 * Let's not sleep for all eternity if we've amassed a huge delay.
+	 * Swapping or metadata IO can accumulate 10's of seconds worth of
+	 * delay, and we want userspace to be able to do _something_ so cap the
+	 * delays at 1 second.  If there's 10's of seconds worth of delay then
+	 * the tasks will be delayed for 1 second for every syscall.
+	 */
+	delay_nsec = min_t(u64, delay_nsec, 250 * NSEC_PER_MSEC);
+
+	/*
+	 * TODO: the use_memdelay flag is going to be for the upcoming psi stuff
+	 * that hasn't landed upstream yet.  Once that stuff is in place we need
+	 * to do a psi_memstall_enter/leave if memdelay is set.
+	 */
+
+	exp = ktime_add_ns(now, delay_nsec);
+	tok = io_schedule_prepare();
+	do {
+		__set_current_state(TASK_KILLABLE);
+		if (!schedule_hrtimeout(&exp, HRTIMER_MODE_ABS))
+			break;
+	} while (!fatal_signal_pending(current));
+	io_schedule_finish(tok);
+}
+
+/**
+ * blkcg_maybe_throttle_current - throttle the current task if it has been marked
+ *
+ * This is only called if we've been marked with set_notify_resume().  Obviously
+ * we can be set_notify_resume() for reasons other than blkcg throttling, so we
+ * check to see if current->throttle_queue is set and if not this doesn't do
+ * anything.  This should only ever be called by the resume code, it's not meant
+ * to be called by people willy-nilly as it will actually do the work to
+ * throttle the task if it is setup for throttling.
+ */
+void blkcg_maybe_throttle_current(void)
+{
+	struct request_queue *q = current->throttle_queue;
+	struct cgroup_subsys_state *css;
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+	bool use_memdelay = current->use_memdelay;
+
+	if (!q)
+		return;
+
+	current->throttle_queue = NULL;
+	current->use_memdelay = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (css)
+		blkcg = css_to_blkcg(css);
+	else
+		blkcg = css_to_blkcg(task_css(current, io_cgrp_id));
+
+	if (!blkcg)
+		goto out;
+	blkg = blkg_lookup(blkcg, q);
+	if (!blkg)
+		goto out;
+	blkg = blkg_try_get(blkg);
+	if (!blkg)
+		goto out;
+	rcu_read_unlock();
+	blk_put_queue(q);
+
+	blkcg_maybe_throttle_blkg(blkg, use_memdelay);
+	blkg_put(blkg);
+	return;
+out:
+	rcu_read_unlock();
+	blk_put_queue(q);
+}
+EXPORT_SYMBOL_GPL(blkcg_maybe_throttle_current);
+
+/**
+ * blkcg_schedule_throttle - this task needs to check for throttling
+ * @q - the request queue IO was submitted on
+ * @use_memdelay - do we charge this to memory delay for PSI
+ *
+ * This is called by the IO controller when we know there's delay accumulated
+ * for the blkg for this task.  We do not pass the blkg because there are places
+ * we call this that may not have that information, the swapping code for
+ * instance will only have a request_queue at that point.  This set's the
+ * notify_resume for the task to check and see if it requires throttling before
+ * returning to user space.
+ *
+ * We will only schedule once per syscall.  You can call this over and over
+ * again and it will only do the check once upon return to user space, and only
+ * throttle once.  If the task needs to be throttled again it'll need to be
+ * re-set at the next time we see the task.
+ */
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay)
+{
+	if (unlikely(current->flags & PF_KTHREAD))
+		return;
+
+	if (!blk_get_queue(q))
+		return;
+
+	if (current->throttle_queue)
+		blk_put_queue(current->throttle_queue);
+	current->throttle_queue = q;
+	if (use_memdelay)
+		current->use_memdelay = use_memdelay;
+	set_notify_resume(current);
+}
+EXPORT_SYMBOL_GPL(blkcg_schedule_throttle);
+
+/**
+ * blkcg_add_delay - add delay to this blkg
+ * @now - the current time in nanoseconds
+ * @delta - how many nanoseconds of delay to add
+ *
+ * Charge @delta to the blkg's current delay accumulation.  This is used to
+ * throttle tasks if an IO controller thinks we need more throttling.
+ */
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta)
+{
+	blkcg_scale_delay(blkg, now);
+	atomic64_add(delta, &blkg->delay_nsec);
+}
+EXPORT_SYMBOL_GPL(blkcg_add_delay);
+
 module_param(blkcg_debug_stats, bool, 0644);
 MODULE_PARM_DESC(blkcg_debug_stats, "True if you want debug stats, false if not");
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index a8f9ba8f33a4..de57de4831d5 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -136,6 +136,12 @@ struct blkcg_gq {
 	struct blkg_policy_data		*pd[BLKCG_MAX_POLS];
 
 	struct rcu_head			rcu_head;
+
+	atomic_t			use_delay;
+	atomic64_t			delay_nsec;
+	atomic64_t			delay_start;
+	u64				last_delay;
+	int				last_use;
 };
 
 typedef struct blkcg_policy_data *(blkcg_pol_alloc_cpd_fn)(gfp_t gfp);
@@ -241,6 +247,26 @@ static inline struct blkcg *bio_blkcg(struct bio *bio)
 	return css_to_blkcg(task_css(current, io_cgrp_id));
 }
 
+static inline bool blk_cgroup_congested(void)
+{
+	struct cgroup_subsys_state *css;
+	bool ret = false;
+
+	rcu_read_lock();
+	css = kthread_blkcg();
+	if (!css)
+		css = task_css(current, io_cgrp_id);
+	while (css) {
+		if (atomic_read(&css->cgroup->congestion_count)) {
+			ret = true;
+			break;
+		}
+		css = css->parent;
+	}
+	rcu_read_unlock();
+	return ret;
+}
+
 /**
  * bio_issue_as_root_blkg - see if this bio needs to be issued as root blkg
  * @return: true if this bio needs to be submitted with the root blkg context.
@@ -374,6 +400,21 @@ static inline void blkg_get(struct blkcg_gq *blkg)
 	atomic_inc(&blkg->refcnt);
 }
 
+/**
+ * blkg_try_get - try and get a blkg reference
+ * @blkg: blkg to get
+ *
+ * This is for use when doing an RCU lookup of the blkg.  We may be in the midst
+ * of freeing this blkg, so we can only use it if the refcnt is not zero.
+ */
+static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg)
+{
+	if (atomic_inc_not_zero(&blkg->refcnt))
+		return blkg;
+	return NULL;
+}
+
+
 void __blkg_release_rcu(struct rcu_head *rcu);
 
 /**
@@ -734,6 +775,59 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 	return !throtl;
 }
 
+static inline void blkcg_use_delay(struct blkcg_gq *blkg)
+{
+	if (atomic_add_return(1, &blkg->use_delay) == 1)
+		atomic_inc(&blkg->blkcg->css.cgroup->congestion_count);
+}
+
+static inline int blkcg_unuse_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+
+	if (old == 0)
+		return 0;
+
+	/*
+	 * We do this song and dance because we can race with somebody else
+	 * adding or removing delay.  If we just did an atomic_dec we'd end up
+	 * negative and we'd already be in trouble.  We need to subtract 1 and
+	 * then check to see if we were the last delay so we can drop the
+	 * congestion count on the cgroup.
+	 */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, old - 1);
+		if (cur == old)
+			break;
+		old = cur;
+	}
+
+	if (old == 0)
+		return 0;
+	if (old == 1)
+		atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+	return 1;
+}
+
+static inline void blkcg_clear_delay(struct blkcg_gq *blkg)
+{
+	int old = atomic_read(&blkg->use_delay);
+	if (!old)
+		return;
+	/* We only want 1 person clearing the congestion count for this blkg. */
+	while (old) {
+		int cur = atomic_cmpxchg(&blkg->use_delay, old, 0);
+		if (cur == old) {
+			atomic_dec(&blkg->blkcg->css.cgroup->congestion_count);
+			break;
+		}
+		old = cur;
+	}
+}
+
+void blkcg_add_delay(struct blkcg_gq *blkg, u64 now, u64 delta);
+void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay);
+void blkcg_maybe_throttle_current(void);
 #else	/* CONFIG_BLK_CGROUP */
 
 struct blkcg {
@@ -753,8 +847,13 @@ struct blkcg_policy {
 
 #define blkcg_root_css	((struct cgroup_subsys_state *)ERR_PTR(-EINVAL))
 
+static inline void blkcg_maybe_throttle_current(void) { }
+static inline bool blk_cgroup_congested(void) { return false; }
+
 #ifdef CONFIG_BLOCK
 
+static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
+
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index c0e68f903011..ff20b677fb9f 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -438,6 +438,9 @@ struct cgroup {
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 
+	/* If there is block congestion on this cgroup. */
+	atomic_t congestion_count;
+
 	/* ids of the ancestors at each level including self */
 	int ancestor_ids[];
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 43731fe51c97..c2e993de67ec 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -734,6 +734,10 @@ struct task_struct {
 	/* disallow userland-initiated cgroup migration */
 	unsigned			no_cgroup_migration:1;
 #endif
+#ifdef CONFIG_BLK_CGROUP
+	/* to be used once the psi infrastructure lands upstream. */
+	unsigned			use_memdelay:1;
+#endif
 
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
@@ -1151,6 +1155,10 @@ struct task_struct {
 	unsigned int			memcg_nr_pages_over_high;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	struct request_queue		*throttle_queue;
+#endif
+
 #ifdef CONFIG_UPROBES
 	struct uprobe_task		*utask;
 #endif
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 4a8841963c2e..05589a3e37f4 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -51,6 +51,7 @@
 #include <linux/security.h>
 #include <linux/task_work.h>
 #include <linux/memcontrol.h>
+#include <linux/blk-cgroup.h>
 struct linux_binprm;
 
 /*
@@ -192,6 +193,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 		task_work_run();
 
 	mem_cgroup_handle_over_high();
+	blkcg_maybe_throttle_current();
 }
 
 #endif	/* <linux/tracehook.h> */
-- 
cgit v1.2.3


From 2cf855837b89d92996cf264713f3bed2bf9b0b4f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 3 Jul 2018 11:14:56 -0400
Subject: memcontrol: schedule throttling if we are congested

Memory allocations can induce swapping via kswapd or direct reclaim.  If
we are having IO done for us by kswapd and don't actually go into direct
reclaim we may never get scheduled for throttling.  So instead check to
see if our cgroup is congested, and if so schedule the throttling.
Before we return to user space the throttling stuff will only throttle
if we actually required it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/memcontrol.h | 13 +++++++++++++
 include/linux/swap.h       | 11 ++++++++++-
 mm/huge_memory.c           |  6 +++---
 mm/memcontrol.c            | 13 +++++++++++++
 mm/memory.c                | 11 ++++++-----
 mm/shmem.c                 | 10 +++++-----
 mm/swapfile.c              | 31 +++++++++++++++++++++++++++++++
 7 files changed, 81 insertions(+), 14 deletions(-)

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 6c6fb116e925..680d3395fc83 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -317,6 +317,9 @@ enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root,
 int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
 			  bool compound);
+int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound);
 void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg,
 			      bool lrucare, bool compound);
 void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg,
@@ -789,6 +792,16 @@ static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm,
 	return 0;
 }
 
+static inline int mem_cgroup_try_charge_delay(struct page *page,
+					      struct mm_struct *mm,
+					      gfp_t gfp_mask,
+					      struct mem_cgroup **memcgp,
+					      bool compound)
+{
+	*memcgp = NULL;
+	return 0;
+}
+
 static inline void mem_cgroup_commit_charge(struct page *page,
 					    struct mem_cgroup *memcg,
 					    bool lrucare, bool compound)
diff --git a/include/linux/swap.h b/include/linux/swap.h
index c063443d8638..1a8bd05a335e 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -629,7 +629,6 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg)
 
 	return memcg->swappiness;
 }
-
 #else
 static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 {
@@ -637,6 +636,16 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 }
 #endif
 
+#if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+extern void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+					 gfp_t gfp_mask);
+#else
+static inline void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg,
+						int node, gfp_t gfp_mask)
+{
+}
+#endif
+
 #ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
 extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1cd7c1a57a14..b87d5b151db2 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -552,7 +552,7 @@ static int __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page,
 
 	VM_BUG_ON_PAGE(!PageCompound(page), page);
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, gfp, &memcg, true)) {
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, gfp, &memcg, true)) {
 		put_page(page);
 		count_vm_event(THP_FAULT_FALLBACK);
 		return VM_FAULT_FALLBACK;
@@ -1142,7 +1142,7 @@ static int do_huge_pmd_wp_page_fallback(struct vm_fault *vmf, pmd_t orig_pmd,
 		pages[i] = alloc_page_vma_node(GFP_HIGHUSER_MOVABLE, vma,
 					       vmf->address, page_to_nid(page));
 		if (unlikely(!pages[i] ||
-			     mem_cgroup_try_charge(pages[i], vma->vm_mm,
+			     mem_cgroup_try_charge_delay(pages[i], vma->vm_mm,
 				     GFP_KERNEL, &memcg, false))) {
 			if (pages[i])
 				put_page(pages[i]);
@@ -1312,7 +1312,7 @@ alloc:
 		goto out;
 	}
 
-	if (unlikely(mem_cgroup_try_charge(new_page, vma->vm_mm,
+	if (unlikely(mem_cgroup_try_charge_delay(new_page, vma->vm_mm,
 					huge_gfp, &memcg, true))) {
 		put_page(new_page);
 		split_huge_pmd(vma, vmf->pmd, vmf->address);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e6f0d5ef320a..64bd28d35388 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5593,6 +5593,19 @@ out:
 	return ret;
 }
 
+int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm,
+			  gfp_t gfp_mask, struct mem_cgroup **memcgp,
+			  bool compound)
+{
+	struct mem_cgroup *memcg;
+	int ret;
+
+	ret = mem_cgroup_try_charge(page, mm, gfp_mask, memcgp, compound);
+	memcg = *memcgp;
+	mem_cgroup_throttle_swaprate(memcg, page_to_nid(page), gfp_mask);
+	return ret;
+}
+
 /**
  * mem_cgroup_commit_charge - commit a page charge
  * @page: page to charge
diff --git a/mm/memory.c b/mm/memory.c
index 7206a634270b..dfe80c574282 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2503,7 +2503,7 @@ static int wp_page_copy(struct vm_fault *vmf)
 		cow_user_page(new_page, old_page, vmf->address, vma);
 	}
 
-	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
+	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))
 		goto oom_free_new;
 
 	__SetPageUptodate(new_page);
@@ -3003,8 +3003,8 @@ int do_swap_page(struct vm_fault *vmf)
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL,
-				&memcg, false)) {
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL,
+					&memcg, false)) {
 		ret = VM_FAULT_OOM;
 		goto out_page;
 	}
@@ -3165,7 +3165,8 @@ static int do_anonymous_page(struct vm_fault *vmf)
 	if (!page)
 		goto oom;
 
-	if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false))
+	if (mem_cgroup_try_charge_delay(page, vma->vm_mm, GFP_KERNEL, &memcg,
+					false))
 		goto oom_free_page;
 
 	/*
@@ -3661,7 +3662,7 @@ static int do_cow_fault(struct vm_fault *vmf)
 	if (!vmf->cow_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_try_charge(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
+	if (mem_cgroup_try_charge_delay(vmf->cow_page, vma->vm_mm, GFP_KERNEL,
 				&vmf->memcg, false)) {
 		put_page(vmf->cow_page);
 		return VM_FAULT_OOM;
diff --git a/mm/shmem.c b/mm/shmem.c
index 2cab84403055..6206ca3510cf 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1239,8 +1239,8 @@ int shmem_unuse(swp_entry_t swap, struct page *page)
 	 * the shmem_swaplist_mutex which might hold up shmem_writepage().
 	 * Charged back to the user (not to caller) when swap account is used.
 	 */
-	error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg,
-			false);
+	error = mem_cgroup_try_charge_delay(page, current->mm, GFP_KERNEL,
+					    &memcg, false);
 	if (error)
 		goto out;
 	/* No radix_tree_preload: swap entry keeps a place for page in tree */
@@ -1712,7 +1712,7 @@ repeat:
 				goto failed;
 		}
 
-		error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
+		error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 				false);
 		if (!error) {
 			error = shmem_add_to_page_cache(page, mapping, index,
@@ -1818,7 +1818,7 @@ alloc_nohuge:		page = shmem_alloc_and_acct_page(gfp, inode,
 		if (sgp == SGP_WRITE)
 			__SetPageReferenced(page);
 
-		error = mem_cgroup_try_charge(page, charge_mm, gfp, &memcg,
+		error = mem_cgroup_try_charge_delay(page, charge_mm, gfp, &memcg,
 				PageTransHuge(page));
 		if (error)
 			goto unacct;
@@ -2291,7 +2291,7 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm,
 	__SetPageSwapBacked(page);
 	__SetPageUptodate(page);
 
-	ret = mem_cgroup_try_charge(page, dst_mm, gfp, &memcg, false);
+	ret = mem_cgroup_try_charge_delay(page, dst_mm, gfp, &memcg, false);
 	if (ret)
 		goto out_release;
 
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2cc2972eedaf..db4ec8ae1c8c 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3731,6 +3731,37 @@ static void free_swap_count_continuations(struct swap_info_struct *si)
 	}
 }
 
+#if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP)
+void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node,
+				  gfp_t gfp_mask)
+{
+	struct swap_info_struct *si, *next;
+	if (!(gfp_mask & __GFP_IO) || !memcg)
+		return;
+
+	if (!blk_cgroup_congested())
+		return;
+
+	/*
+	 * We've already scheduled a throttle, avoid taking the global swap
+	 * lock.
+	 */
+	if (current->throttle_queue)
+		return;
+
+	spin_lock(&swap_avail_lock);
+	plist_for_each_entry_safe(si, next, &swap_avail_heads[node],
+				  avail_lists[node]) {
+		if (si->bdev) {
+			blkcg_schedule_throttle(bdev_get_queue(si->bdev),
+						true);
+			break;
+		}
+	}
+	spin_unlock(&swap_avail_lock);
+}
+#endif
+
 static int __init swapfile_init(void)
 {
 	int nid;
-- 
cgit v1.2.3


From 2ecbf456352d0699f51b4c6d70ea5bf29766579c Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:14:57 -0400
Subject: blk-stat: export helpers for modifying blk_rq_stat

We need to use blk_rq_stat in the blkcg qos stuff, so export some of
these helpers so they can be used by other things.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-stat.c | 16 ++++++++--------
 block/blk-stat.h |  4 ++++
 2 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/block/blk-stat.c b/block/blk-stat.c
index 175c143ac5b9..7587b1c3caaf 100644
--- a/block/blk-stat.c
+++ b/block/blk-stat.c
@@ -17,7 +17,7 @@ struct blk_queue_stats {
 	bool enable_accounting;
 };
 
-static void blk_stat_init(struct blk_rq_stat *stat)
+void blk_rq_stat_init(struct blk_rq_stat *stat)
 {
 	stat->min = -1ULL;
 	stat->max = stat->nr_samples = stat->mean = 0;
@@ -25,7 +25,7 @@ static void blk_stat_init(struct blk_rq_stat *stat)
 }
 
 /* src is a per-cpu stat, mean isn't initialized */
-static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
+void blk_rq_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 {
 	if (!src->nr_samples)
 		return;
@@ -39,7 +39,7 @@ static void blk_stat_sum(struct blk_rq_stat *dst, struct blk_rq_stat *src)
 	dst->nr_samples += src->nr_samples;
 }
 
-static void __blk_stat_add(struct blk_rq_stat *stat, u64 value)
+void blk_rq_stat_add(struct blk_rq_stat *stat, u64 value)
 {
 	stat->min = min(stat->min, value);
 	stat->max = max(stat->max, value);
@@ -69,7 +69,7 @@ void blk_stat_add(struct request *rq, u64 now)
 			continue;
 
 		stat = &get_cpu_ptr(cb->cpu_stat)[bucket];
-		__blk_stat_add(stat, value);
+		blk_rq_stat_add(stat, value);
 		put_cpu_ptr(cb->cpu_stat);
 	}
 	rcu_read_unlock();
@@ -82,15 +82,15 @@ static void blk_stat_timer_fn(struct timer_list *t)
 	int cpu;
 
 	for (bucket = 0; bucket < cb->buckets; bucket++)
-		blk_stat_init(&cb->stat[bucket]);
+		blk_rq_stat_init(&cb->stat[bucket]);
 
 	for_each_online_cpu(cpu) {
 		struct blk_rq_stat *cpu_stat;
 
 		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
 		for (bucket = 0; bucket < cb->buckets; bucket++) {
-			blk_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
-			blk_stat_init(&cpu_stat[bucket]);
+			blk_rq_stat_sum(&cb->stat[bucket], &cpu_stat[bucket]);
+			blk_rq_stat_init(&cpu_stat[bucket]);
 		}
 	}
 
@@ -143,7 +143,7 @@ void blk_stat_add_callback(struct request_queue *q,
 
 		cpu_stat = per_cpu_ptr(cb->cpu_stat, cpu);
 		for (bucket = 0; bucket < cb->buckets; bucket++)
-			blk_stat_init(&cpu_stat[bucket]);
+			blk_rq_stat_init(&cpu_stat[bucket]);
 	}
 
 	spin_lock(&q->stats->lock);
diff --git a/block/blk-stat.h b/block/blk-stat.h
index 78399cdde9c9..f4a1568e81a4 100644
--- a/block/blk-stat.h
+++ b/block/blk-stat.h
@@ -159,4 +159,8 @@ static inline void blk_stat_activate_msecs(struct blk_stat_callback *cb,
 	mod_timer(&cb->timer, jiffies + msecs_to_jiffies(msecs));
 }
 
+void blk_rq_stat_add(struct blk_rq_stat *, u64);
+void blk_rq_stat_sum(struct blk_rq_stat *, struct blk_rq_stat *);
+void blk_rq_stat_init(struct blk_rq_stat *);
+
 #endif
-- 
cgit v1.2.3


From a79050434b45959f397042080fd1d70ffa9bd9df Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 09:32:35 -0600
Subject: blk-rq-qos: refactor out common elements of blk-wbt

blkcg-qos is going to do essentially what wbt does, only on a cgroup
basis.  Break out the common code that will be shared between blkcg-qos
and wbt into blk-rq-qos.* so they can both utilize the same
infrastructure.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Makefile         |   2 +-
 block/blk-core.c       |  12 +-
 block/blk-mq.c         |  12 +-
 block/blk-rq-qos.c     | 178 +++++++++++++++++++++++++++
 block/blk-rq-qos.h     | 106 ++++++++++++++++
 block/blk-settings.c   |   4 +-
 block/blk-sysfs.c      |  22 ++--
 block/blk-wbt.c        | 326 ++++++++++++++++++++++---------------------------
 block/blk-wbt.h        |  63 ++++------
 include/linux/blkdev.h |   4 +-
 10 files changed, 478 insertions(+), 251 deletions(-)
 create mode 100644 block/blk-rq-qos.c
 create mode 100644 block/blk-rq-qos.h

diff --git a/block/Makefile b/block/Makefile
index a8f94cdb75c3..57d0f47ab05f 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_BLOCK) := bio.o elevator.o blk-core.o blk-tag.o blk-sysfs.o \
 			blk-lib.o blk-mq.o blk-mq-tag.o blk-stat.o \
 			blk-mq-sysfs.o blk-mq-cpumap.o blk-mq-sched.o ioctl.o \
 			genhd.o partition-generic.o ioprio.o \
-			badblocks.o partitions/
+			badblocks.o partitions/ blk-rq-qos.o
 
 obj-$(CONFIG_BOUNCE)		+= bounce.o
 obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_ioctl.o
diff --git a/block/blk-core.c b/block/blk-core.c
index 2ff8e131a892..b33a73bcf2d0 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1645,7 +1645,7 @@ void blk_requeue_request(struct request_queue *q, struct request *rq)
 	blk_delete_timer(rq);
 	blk_clear_rq_complete(rq);
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (rq->rq_flags & RQF_QUEUED)
 		blk_queue_end_tag(q, rq);
@@ -1752,7 +1752,7 @@ void __blk_put_request(struct request_queue *q, struct request *req)
 	/* this is a bio leak */
 	WARN_ON(req->bio != NULL);
 
-	wbt_done(q->rq_wb, req);
+	rq_qos_done(q, req);
 
 	/*
 	 * Request may not have originated from ll_rw_blk. if not,
@@ -2044,7 +2044,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	wb_acct = wbt_wait(q->rq_wb, bio, q->queue_lock);
+	wb_acct = rq_qos_throttle(q, bio, q->queue_lock);
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -2054,7 +2054,7 @@ get_rq:
 	req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, wb_acct);
 		if (PTR_ERR(req) == -ENOMEM)
 			bio->bi_status = BLK_STS_RESOURCE;
 		else
@@ -2983,7 +2983,7 @@ void blk_start_request(struct request *req)
 		req->throtl_size = blk_rq_sectors(req);
 #endif
 		req->rq_flags |= RQF_STATS;
-		wbt_issue(req->q->rq_wb, req);
+		rq_qos_issue(req->q, req);
 	}
 
 	BUG_ON(blk_rq_is_complete(req));
@@ -3207,7 +3207,7 @@ void blk_finish_request(struct request *req, blk_status_t error)
 	blk_account_io_done(req, now);
 
 	if (req->end_io) {
-		wbt_done(req->q->rq_wb, req);
+		rq_qos_done(q, req);
 		req->end_io(req, error);
 	} else {
 		if (blk_bidi_rq(req))
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 850fdd02c385..ea2a226457fa 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -504,7 +504,7 @@ void blk_mq_free_request(struct request *rq)
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->backing_dev_info);
 
-	wbt_done(q->rq_wb, rq);
+	rq_qos_done(q, rq);
 
 	if (blk_rq_rl(rq))
 		blk_put_rl(blk_rq_rl(rq));
@@ -527,7 +527,7 @@ inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
 	blk_account_io_done(rq, now);
 
 	if (rq->end_io) {
-		wbt_done(rq->q->rq_wb, rq);
+		rq_qos_done(rq->q, rq);
 		rq->end_io(rq, error);
 	} else {
 		if (unlikely(blk_bidi_rq(rq)))
@@ -641,7 +641,7 @@ void blk_mq_start_request(struct request *rq)
 		rq->throtl_size = blk_rq_sectors(rq);
 #endif
 		rq->rq_flags |= RQF_STATS;
-		wbt_issue(q->rq_wb, rq);
+		rq_qos_issue(q, rq);
 	}
 
 	WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
@@ -667,7 +667,7 @@ static void __blk_mq_requeue_request(struct request *rq)
 	blk_mq_put_driver_tag(rq);
 
 	trace_block_rq_requeue(q, rq);
-	wbt_requeue(q->rq_wb, rq);
+	rq_qos_requeue(q, rq);
 
 	if (blk_mq_request_started(rq)) {
 		WRITE_ONCE(rq->state, MQ_RQ_IDLE);
@@ -1806,13 +1806,13 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	if (blk_mq_sched_bio_merge(q, bio))
 		return BLK_QC_T_NONE;
 
-	wb_acct = wbt_wait(q->rq_wb, bio, NULL);
+	wb_acct = rq_qos_throttle(q, bio, NULL);
 
 	trace_block_getrq(q, bio, bio->bi_opf);
 
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
-		__wbt_done(q->rq_wb, wb_acct);
+		rq_qos_cleanup(q, wb_acct);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
new file mode 100644
index 000000000000..d2f2af8aa10c
--- /dev/null
+++ b/block/blk-rq-qos.c
@@ -0,0 +1,178 @@
+#include "blk-rq-qos.h"
+
+#include "blk-wbt.h"
+
+/*
+ * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
+ * false if 'v' + 1 would be bigger than 'below'.
+ */
+static bool atomic_inc_below(atomic_t *v, int below)
+{
+	int cur = atomic_read(v);
+
+	for (;;) {
+		int old;
+
+		if (cur >= below)
+			return false;
+		old = atomic_cmpxchg(v, cur, cur + 1);
+		if (old == cur)
+			break;
+		cur = old;
+	}
+
+	return true;
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit)
+{
+	return atomic_inc_below(&rq_wait->inflight, limit);
+}
+
+void rq_qos_cleanup(struct request_queue *q, enum wbt_flags wb_acct)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->cleanup)
+			rqos->ops->cleanup(rqos, wb_acct);
+	}
+}
+
+void rq_qos_done(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done)
+			rqos->ops->done(rqos, rq);
+	}
+}
+
+void rq_qos_issue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->issue)
+			rqos->ops->issue(rqos, rq);
+	}
+}
+
+void rq_qos_requeue(struct request_queue *q, struct request *rq)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->requeue)
+			rqos->ops->requeue(rqos, rq);
+	}
+}
+
+enum wbt_flags rq_qos_throttle(struct request_queue *q, struct bio *bio,
+			       spinlock_t *lock)
+{
+	struct rq_qos *rqos;
+	enum wbt_flags flags = 0;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->throttle)
+			flags |= rqos->ops->throttle(rqos, bio, lock);
+	}
+	return flags;
+}
+
+/*
+ * Return true, if we can't increase the depth further by scaling
+ */
+bool rq_depth_calc_max_depth(struct rq_depth *rqd)
+{
+	unsigned int depth;
+	bool ret = false;
+
+	/*
+	 * For QD=1 devices, this is a special case. It's important for those
+	 * to have one request ready when one completes, so force a depth of
+	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
+	 * since the device can't have more than that in flight. If we're
+	 * scaling down, then keep a setting of 1/1/1.
+	 */
+	if (rqd->queue_depth == 1) {
+		if (rqd->scale_step > 0)
+			rqd->max_depth = 1;
+		else {
+			rqd->max_depth = 2;
+			ret = true;
+		}
+	} else {
+		/*
+		 * scale_step == 0 is our default state. If we have suffered
+		 * latency spikes, step will be > 0, and we shrink the
+		 * allowed write depths. If step is < 0, we're only doing
+		 * writes, and we allow a temporarily higher depth to
+		 * increase performance.
+		 */
+		depth = min_t(unsigned int, rqd->default_depth,
+			      rqd->queue_depth);
+		if (rqd->scale_step > 0)
+			depth = 1 + ((depth - 1) >> min(31, rqd->scale_step));
+		else if (rqd->scale_step < 0) {
+			unsigned int maxd = 3 * rqd->queue_depth / 4;
+
+			depth = 1 + ((depth - 1) << -rqd->scale_step);
+			if (depth > maxd) {
+				depth = maxd;
+				ret = true;
+			}
+		}
+
+		rqd->max_depth = depth;
+	}
+
+	return ret;
+}
+
+void rq_depth_scale_up(struct rq_depth *rqd)
+{
+	/*
+	 * Hit max in previous round, stop here
+	 */
+	if (rqd->scaled_max)
+		return;
+
+	rqd->scale_step--;
+
+	rqd->scaled_max = rq_depth_calc_max_depth(rqd);
+}
+
+/*
+ * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
+ * had a latency violation.
+ */
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle)
+{
+	/*
+	 * Stop scaling down when we've hit the limit. This also prevents
+	 * ->scale_step from going to crazy values, if the device can't
+	 * keep up.
+	 */
+	if (rqd->max_depth == 1)
+		return;
+
+	if (rqd->scale_step < 0 && hard_throttle)
+		rqd->scale_step = 0;
+	else
+		rqd->scale_step++;
+
+	rqd->scaled_max = false;
+	rq_depth_calc_max_depth(rqd);
+}
+
+void rq_qos_exit(struct request_queue *q)
+{
+	while (q->rq_qos) {
+		struct rq_qos *rqos = q->rq_qos;
+		q->rq_qos = rqos->next;
+		rqos->ops->exit(rqos);
+	}
+}
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
new file mode 100644
index 000000000000..f9a39bd6ece3
--- /dev/null
+++ b/block/blk-rq-qos.h
@@ -0,0 +1,106 @@
+#ifndef RQ_QOS_H
+#define RQ_QOS_H
+
+#include <linux/kernel.h>
+#include <linux/blkdev.h>
+#include <linux/blk_types.h>
+#include <linux/atomic.h>
+#include <linux/wait.h>
+
+enum rq_qos_id {
+	RQ_QOS_WBT,
+	RQ_QOS_CGROUP,
+};
+
+struct rq_wait {
+	wait_queue_head_t wait;
+	atomic_t inflight;
+};
+
+struct rq_qos {
+	struct rq_qos_ops *ops;
+	struct request_queue *q;
+	enum rq_qos_id id;
+	struct rq_qos *next;
+};
+
+struct rq_qos_ops {
+	enum wbt_flags (*throttle)(struct rq_qos *, struct bio *,
+				   spinlock_t *);
+	void (*issue)(struct rq_qos *, struct request *);
+	void (*requeue)(struct rq_qos *, struct request *);
+	void (*done)(struct rq_qos *, struct request *);
+	void (*cleanup)(struct rq_qos *, enum wbt_flags);
+	void (*exit)(struct rq_qos *);
+};
+
+struct rq_depth {
+	unsigned int max_depth;
+
+	int scale_step;
+	bool scaled_max;
+
+	unsigned int queue_depth;
+	unsigned int default_depth;
+};
+
+static inline struct rq_qos *rq_qos_id(struct request_queue *q,
+				       enum rq_qos_id id)
+{
+	struct rq_qos *rqos;
+	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->id == id)
+			break;
+	}
+	return rqos;
+}
+
+static inline struct rq_qos *wbt_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_WBT);
+}
+
+static inline struct rq_qos *blkcg_rq_qos(struct request_queue *q)
+{
+	return rq_qos_id(q, RQ_QOS_CGROUP);
+}
+
+static inline void rq_wait_init(struct rq_wait *rq_wait)
+{
+	atomic_set(&rq_wait->inflight, 0);
+	init_waitqueue_head(&rq_wait->wait);
+}
+
+static inline void rq_qos_add(struct request_queue *q, struct rq_qos *rqos)
+{
+	rqos->next = q->rq_qos;
+	q->rq_qos = rqos;
+}
+
+static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
+{
+	struct rq_qos *cur, *prev = NULL;
+	for (cur = q->rq_qos; cur; cur = cur->next) {
+		if (cur == rqos) {
+			if (prev)
+				prev->next = rqos->next;
+			else
+				q->rq_qos = cur;
+			break;
+		}
+		prev = cur;
+	}
+}
+
+bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit);
+void rq_depth_scale_up(struct rq_depth *rqd);
+void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
+bool rq_depth_calc_max_depth(struct rq_depth *rqd);
+
+void rq_qos_cleanup(struct request_queue *, enum wbt_flags);
+void rq_qos_done(struct request_queue *, struct request *);
+void rq_qos_issue(struct request_queue *, struct request *);
+void rq_qos_requeue(struct request_queue *, struct request *);
+enum wbt_flags rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
+void rq_qos_exit(struct request_queue *);
+#endif
diff --git a/block/blk-settings.c b/block/blk-settings.c
index d1de71124656..053de87d1fda 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -875,7 +875,7 @@ EXPORT_SYMBOL_GPL(blk_queue_flush_queueable);
 void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 	q->queue_depth = depth;
-	wbt_set_queue_depth(q->rq_wb, depth);
+	wbt_set_queue_depth(q, depth);
 }
 EXPORT_SYMBOL(blk_set_queue_depth);
 
@@ -900,7 +900,7 @@ void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
 		queue_flag_clear(QUEUE_FLAG_FUA, q);
 	spin_unlock_irq(q->queue_lock);
 
-	wbt_set_write_cache(q->rq_wb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 }
 EXPORT_SYMBOL_GPL(blk_queue_write_cache);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 94987b1f69e1..49c29a5d06bb 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -422,16 +422,16 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
 
 static ssize_t queue_wb_lat_show(struct request_queue *q, char *page)
 {
-	if (!q->rq_wb)
+	if (!wbt_rq_qos(q))
 		return -EINVAL;
 
-	return sprintf(page, "%llu\n", div_u64(q->rq_wb->min_lat_nsec, 1000));
+	return sprintf(page, "%llu\n", div_u64(wbt_get_min_lat(q), 1000));
 }
 
 static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 				  size_t count)
 {
-	struct rq_wb *rwb;
+	struct rq_qos *rqos;
 	ssize_t ret;
 	s64 val;
 
@@ -441,23 +441,21 @@ static ssize_t queue_wb_lat_store(struct request_queue *q, const char *page,
 	if (val < -1)
 		return -EINVAL;
 
-	rwb = q->rq_wb;
-	if (!rwb) {
+	rqos = wbt_rq_qos(q);
+	if (!rqos) {
 		ret = wbt_init(q);
 		if (ret)
 			return ret;
 	}
 
-	rwb = q->rq_wb;
 	if (val == -1)
-		rwb->min_lat_nsec = wbt_default_latency_nsec(q);
+		val = wbt_default_latency_nsec(q);
 	else if (val >= 0)
-		rwb->min_lat_nsec = val * 1000ULL;
+		val *= 1000ULL;
 
-	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		rwb->enable_state = WBT_STATE_ON_MANUAL;
+	wbt_set_min_lat(q, val);
 
-	wbt_update_limits(rwb);
+	wbt_update_limits(q);
 	return count;
 }
 
@@ -964,7 +962,7 @@ void blk_unregister_queue(struct gendisk *disk)
 	kobject_del(&q->kobj);
 	blk_trace_remove_sysfs(disk_to_dev(disk));
 
-	wbt_exit(q);
+	rq_qos_exit(q);
 
 	mutex_lock(&q->sysfs_lock);
 	if (q->request_fn || (q->mq_ops && q->elevator))
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 4f89b28fa652..6fe20fb823e4 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -25,6 +25,7 @@
 #include <linux/swap.h>
 
 #include "blk-wbt.h"
+#include "blk-rq-qos.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/wbt.h>
@@ -78,28 +79,6 @@ static inline bool rwb_enabled(struct rq_wb *rwb)
 	return rwb && rwb->wb_normal != 0;
 }
 
-/*
- * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
- * false if 'v' + 1 would be bigger than 'below'.
- */
-static bool atomic_inc_below(atomic_t *v, int below)
-{
-	int cur = atomic_read(v);
-
-	for (;;) {
-		int old;
-
-		if (cur >= below)
-			return false;
-		old = atomic_cmpxchg(v, cur, cur + 1);
-		if (old == cur)
-			break;
-		cur = old;
-	}
-
-	return true;
-}
-
 static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
 {
 	if (rwb_enabled(rwb)) {
@@ -116,7 +95,7 @@ static void wb_timestamp(struct rq_wb *rwb, unsigned long *var)
  */
 static bool wb_recent_wait(struct rq_wb *rwb)
 {
-	struct bdi_writeback *wb = &rwb->queue->backing_dev_info->wb;
+	struct bdi_writeback *wb = &rwb->rqos.q->backing_dev_info->wb;
 
 	return time_before(jiffies, wb->dirty_sleep + HZ);
 }
@@ -144,8 +123,9 @@ static void rwb_wake_all(struct rq_wb *rwb)
 	}
 }
 
-void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
+static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	struct rq_wait *rqw;
 	int inflight, limit;
 
@@ -194,10 +174,9 @@ void __wbt_done(struct rq_wb *rwb, enum wbt_flags wb_acct)
  * Called on completion of a request. Note that it's also called when
  * a request is merged, when the request gets freed.
  */
-void wbt_done(struct rq_wb *rwb, struct request *rq)
+static void wbt_done(struct rq_qos *rqos, struct request *rq)
 {
-	if (!rwb)
-		return;
+	struct rq_wb *rwb = RQWB(rqos);
 
 	if (!wbt_is_tracked(rq)) {
 		if (rwb->sync_cookie == rq) {
@@ -209,72 +188,11 @@ void wbt_done(struct rq_wb *rwb, struct request *rq)
 			wb_timestamp(rwb, &rwb->last_comp);
 	} else {
 		WARN_ON_ONCE(rq == rwb->sync_cookie);
-		__wbt_done(rwb, wbt_flags(rq));
+		__wbt_done(rqos, wbt_flags(rq));
 	}
 	wbt_clear_state(rq);
 }
 
-/*
- * Return true, if we can't increase the depth further by scaling
- */
-static bool calc_wb_limits(struct rq_wb *rwb)
-{
-	unsigned int depth;
-	bool ret = false;
-
-	if (!rwb->min_lat_nsec) {
-		rwb->wb_max = rwb->wb_normal = rwb->wb_background = 0;
-		return false;
-	}
-
-	/*
-	 * For QD=1 devices, this is a special case. It's important for those
-	 * to have one request ready when one completes, so force a depth of
-	 * 2 for those devices. On the backend, it'll be a depth of 1 anyway,
-	 * since the device can't have more than that in flight. If we're
-	 * scaling down, then keep a setting of 1/1/1.
-	 */
-	if (rwb->queue_depth == 1) {
-		if (rwb->scale_step > 0)
-			rwb->wb_max = rwb->wb_normal = 1;
-		else {
-			rwb->wb_max = rwb->wb_normal = 2;
-			ret = true;
-		}
-		rwb->wb_background = 1;
-	} else {
-		/*
-		 * scale_step == 0 is our default state. If we have suffered
-		 * latency spikes, step will be > 0, and we shrink the
-		 * allowed write depths. If step is < 0, we're only doing
-		 * writes, and we allow a temporarily higher depth to
-		 * increase performance.
-		 */
-		depth = min_t(unsigned int, RWB_DEF_DEPTH, rwb->queue_depth);
-		if (rwb->scale_step > 0)
-			depth = 1 + ((depth - 1) >> min(31, rwb->scale_step));
-		else if (rwb->scale_step < 0) {
-			unsigned int maxd = 3 * rwb->queue_depth / 4;
-
-			depth = 1 + ((depth - 1) << -rwb->scale_step);
-			if (depth > maxd) {
-				depth = maxd;
-				ret = true;
-			}
-		}
-
-		/*
-		 * Set our max/normal/bg queue depths based on how far
-		 * we have scaled down (->scale_step).
-		 */
-		rwb->wb_max = depth;
-		rwb->wb_normal = (rwb->wb_max + 1) / 2;
-		rwb->wb_background = (rwb->wb_max + 3) / 4;
-	}
-
-	return ret;
-}
-
 static inline bool stat_sample_valid(struct blk_rq_stat *stat)
 {
 	/*
@@ -307,7 +225,8 @@ enum {
 
 static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	u64 thislat;
 
 	/*
@@ -351,7 +270,7 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 		return LAT_EXCEEDED;
 	}
 
-	if (rwb->scale_step)
+	if (rqd->scale_step)
 		trace_wbt_stat(bdi, stat);
 
 	return LAT_OK;
@@ -359,58 +278,48 @@ static int latency_exceeded(struct rq_wb *rwb, struct blk_rq_stat *stat)
 
 static void rwb_trace_step(struct rq_wb *rwb, const char *msg)
 {
-	struct backing_dev_info *bdi = rwb->queue->backing_dev_info;
+	struct backing_dev_info *bdi = rwb->rqos.q->backing_dev_info;
+	struct rq_depth *rqd = &rwb->rq_depth;
 
-	trace_wbt_step(bdi, msg, rwb->scale_step, rwb->cur_win_nsec,
-			rwb->wb_background, rwb->wb_normal, rwb->wb_max);
+	trace_wbt_step(bdi, msg, rqd->scale_step, rwb->cur_win_nsec,
+			rwb->wb_background, rwb->wb_normal, rqd->max_depth);
 }
 
-static void scale_up(struct rq_wb *rwb)
+static void calc_wb_limits(struct rq_wb *rwb)
 {
-	/*
-	 * Hit max in previous round, stop here
-	 */
-	if (rwb->scaled_max)
-		return;
+	if (rwb->min_lat_nsec == 0) {
+		rwb->wb_normal = rwb->wb_background = 0;
+	} else if (rwb->rq_depth.max_depth <= 2) {
+		rwb->wb_normal = rwb->rq_depth.max_depth;
+		rwb->wb_background = 1;
+	} else {
+		rwb->wb_normal = (rwb->rq_depth.max_depth + 1) / 2;
+		rwb->wb_background = (rwb->rq_depth.max_depth + 3) / 4;
+	}
+}
 
-	rwb->scale_step--;
+static void scale_up(struct rq_wb *rwb)
+{
+	rq_depth_scale_up(&rwb->rq_depth);
+	calc_wb_limits(rwb);
 	rwb->unknown_cnt = 0;
-
-	rwb->scaled_max = calc_wb_limits(rwb);
-
-	rwb_wake_all(rwb);
-
-	rwb_trace_step(rwb, "step up");
+	rwb_trace_step(rwb, "scale up");
 }
 
-/*
- * Scale rwb down. If 'hard_throttle' is set, do it quicker, since we
- * had a latency violation.
- */
 static void scale_down(struct rq_wb *rwb, bool hard_throttle)
 {
-	/*
-	 * Stop scaling down when we've hit the limit. This also prevents
-	 * ->scale_step from going to crazy values, if the device can't
-	 * keep up.
-	 */
-	if (rwb->wb_max == 1)
-		return;
-
-	if (rwb->scale_step < 0 && hard_throttle)
-		rwb->scale_step = 0;
-	else
-		rwb->scale_step++;
-
-	rwb->scaled_max = false;
-	rwb->unknown_cnt = 0;
+	rq_depth_scale_down(&rwb->rq_depth, hard_throttle);
 	calc_wb_limits(rwb);
-	rwb_trace_step(rwb, "step down");
+	rwb->unknown_cnt = 0;
+	rwb_wake_all(rwb);
+	rwb_trace_step(rwb, "scale down");
 }
 
 static void rwb_arm_timer(struct rq_wb *rwb)
 {
-	if (rwb->scale_step > 0) {
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	if (rqd->scale_step > 0) {
 		/*
 		 * We should speed this up, using some variant of a fast
 		 * integer inverse square root calculation. Since we only do
@@ -418,7 +327,7 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 		 * though.
 		 */
 		rwb->cur_win_nsec = div_u64(rwb->win_nsec << 4,
-					int_sqrt((rwb->scale_step + 1) << 8));
+					int_sqrt((rqd->scale_step + 1) << 8));
 	} else {
 		/*
 		 * For step < 0, we don't want to increase/decrease the
@@ -433,12 +342,13 @@ static void rwb_arm_timer(struct rq_wb *rwb)
 static void wb_timer_fn(struct blk_stat_callback *cb)
 {
 	struct rq_wb *rwb = cb->data;
+	struct rq_depth *rqd = &rwb->rq_depth;
 	unsigned int inflight = wbt_inflight(rwb);
 	int status;
 
 	status = latency_exceeded(rwb, cb->stat);
 
-	trace_wbt_timer(rwb->queue->backing_dev_info, status, rwb->scale_step,
+	trace_wbt_timer(rwb->rqos.q->backing_dev_info, status, rqd->scale_step,
 			inflight);
 
 	/*
@@ -469,9 +379,9 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 		 * currently don't have a valid read/write sample. For that
 		 * case, slowly return to center state (step == 0).
 		 */
-		if (rwb->scale_step > 0)
+		if (rqd->scale_step > 0)
 			scale_up(rwb);
-		else if (rwb->scale_step < 0)
+		else if (rqd->scale_step < 0)
 			scale_down(rwb, false);
 		break;
 	default:
@@ -481,19 +391,50 @@ static void wb_timer_fn(struct blk_stat_callback *cb)
 	/*
 	 * Re-arm timer, if we have IO in flight
 	 */
-	if (rwb->scale_step || inflight)
+	if (rqd->scale_step || inflight)
 		rwb_arm_timer(rwb);
 }
 
-void wbt_update_limits(struct rq_wb *rwb)
+static void __wbt_update_limits(struct rq_wb *rwb)
 {
-	rwb->scale_step = 0;
-	rwb->scaled_max = false;
+	struct rq_depth *rqd = &rwb->rq_depth;
+
+	rqd->scale_step = 0;
+	rqd->scaled_max = false;
+
+	rq_depth_calc_max_depth(rqd);
 	calc_wb_limits(rwb);
 
 	rwb_wake_all(rwb);
 }
 
+void wbt_update_limits(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+u64 wbt_get_min_lat(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return 0;
+	return RQWB(rqos)->min_lat_nsec;
+}
+
+void wbt_set_min_lat(struct request_queue *q, u64 val)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (!rqos)
+		return;
+	RQWB(rqos)->min_lat_nsec = val;
+	RQWB(rqos)->enable_state = WBT_STATE_ON_MANUAL;
+	__wbt_update_limits(RQWB(rqos));
+}
+
+
 static bool close_io(struct rq_wb *rwb)
 {
 	const unsigned long now = jiffies;
@@ -520,7 +461,7 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	 * IO for a bit.
 	 */
 	if ((rw & REQ_HIPRIO) || wb_recent_wait(rwb) || current_is_kswapd())
-		limit = rwb->wb_max;
+		limit = rwb->rq_depth.max_depth;
 	else if ((rw & REQ_BACKGROUND) || close_io(rwb)) {
 		/*
 		 * If less than 100ms since we completed unrelated IO,
@@ -554,7 +495,7 @@ static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
 	    rqw->wait.head.next != &wait->entry)
 		return false;
 
-	return atomic_inc_below(&rqw->inflight, get_limit(rwb, rw));
+	return rq_wait_inc_below(rqw, get_limit(rwb, rw));
 }
 
 /*
@@ -614,8 +555,10 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
  * in an irq held spinlock, if it holds one when calling this function.
  * If we do sleep, we'll release and re-grab it.
  */
-enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
+static enum wbt_flags wbt_wait(struct rq_qos *rqos, struct bio *bio,
+			       spinlock_t *lock)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	enum wbt_flags ret = 0;
 
 	if (!rwb_enabled(rwb))
@@ -643,8 +586,10 @@ enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio, spinlock_t *lock)
 	return ret | WBT_TRACKED;
 }
 
-void wbt_issue(struct rq_wb *rwb, struct request *rq)
+void wbt_issue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
+
 	if (!rwb_enabled(rwb))
 		return;
 
@@ -661,8 +606,9 @@ void wbt_issue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+void wbt_requeue(struct rq_qos *rqos, struct request *rq)
 {
+	struct rq_wb *rwb = RQWB(rqos);
 	if (!rwb_enabled(rwb))
 		return;
 	if (rq == rwb->sync_cookie) {
@@ -671,39 +617,30 @@ void wbt_requeue(struct rq_wb *rwb, struct request *rq)
 	}
 }
 
-void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
-	if (rwb) {
-		rwb->queue_depth = depth;
-		wbt_update_limits(rwb);
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos) {
+		RQWB(rqos)->rq_depth.queue_depth = depth;
+		__wbt_update_limits(RQWB(rqos));
 	}
 }
 
-void wbt_set_write_cache(struct rq_wb *rwb, bool write_cache_on)
-{
-	if (rwb)
-		rwb->wc = write_cache_on;
-}
-
-/*
- * Disable wbt, if enabled by default.
- */
-void wbt_disable_default(struct request_queue *q)
+void wbt_set_write_cache(struct request_queue *q, bool write_cache_on)
 {
-	struct rq_wb *rwb = q->rq_wb;
-
-	if (rwb && rwb->enable_state == WBT_STATE_ON_DEFAULT)
-		wbt_exit(q);
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	if (rqos)
+		RQWB(rqos)->wc = write_cache_on;
 }
-EXPORT_SYMBOL_GPL(wbt_disable_default);
 
 /*
  * Enable wbt if defaults are configured that way
  */
 void wbt_enable_default(struct request_queue *q)
 {
+	struct rq_qos *rqos = wbt_rq_qos(q);
 	/* Throttling already enabled? */
-	if (q->rq_wb)
+	if (rqos)
 		return;
 
 	/* Queue not registered? Maybe shutting down... */
@@ -741,6 +678,41 @@ static int wbt_data_dir(const struct request *rq)
 	return -1;
 }
 
+static void wbt_exit(struct rq_qos *rqos)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	struct request_queue *q = rqos->q;
+
+	blk_stat_remove_callback(q, rwb->cb);
+	blk_stat_free_callback(rwb->cb);
+	kfree(rwb);
+}
+
+/*
+ * Disable wbt, if enabled by default.
+ */
+void wbt_disable_default(struct request_queue *q)
+{
+	struct rq_qos *rqos = wbt_rq_qos(q);
+	struct rq_wb *rwb;
+	if (!rqos)
+		return;
+	rwb = RQWB(rqos);
+	if (rwb->enable_state == WBT_STATE_ON_DEFAULT)
+		rwb->wb_normal = 0;
+}
+EXPORT_SYMBOL_GPL(wbt_disable_default);
+
+
+static struct rq_qos_ops wbt_rqos_ops = {
+	.throttle = wbt_wait,
+	.issue = wbt_issue,
+	.requeue = wbt_requeue,
+	.done = wbt_done,
+	.cleanup = __wbt_done,
+	.exit = wbt_exit,
+};
+
 int wbt_init(struct request_queue *q)
 {
 	struct rq_wb *rwb;
@@ -756,39 +728,29 @@ int wbt_init(struct request_queue *q)
 		return -ENOMEM;
 	}
 
-	for (i = 0; i < WBT_NUM_RWQ; i++) {
-		atomic_set(&rwb->rq_wait[i].inflight, 0);
-		init_waitqueue_head(&rwb->rq_wait[i].wait);
-	}
+	for (i = 0; i < WBT_NUM_RWQ; i++)
+		rq_wait_init(&rwb->rq_wait[i]);
 
+	rwb->rqos.id = RQ_QOS_WBT;
+	rwb->rqos.ops = &wbt_rqos_ops;
+	rwb->rqos.q = q;
 	rwb->last_comp = rwb->last_issue = jiffies;
-	rwb->queue = q;
 	rwb->win_nsec = RWB_WINDOW_NSEC;
 	rwb->enable_state = WBT_STATE_ON_DEFAULT;
-	wbt_update_limits(rwb);
+	rwb->wc = 1;
+	rwb->rq_depth.default_depth = RWB_DEF_DEPTH;
+	__wbt_update_limits(rwb);
 
 	/*
 	 * Assign rwb and add the stats callback.
 	 */
-	q->rq_wb = rwb;
+	rq_qos_add(q, &rwb->rqos);
 	blk_stat_add_callback(q, rwb->cb);
 
 	rwb->min_lat_nsec = wbt_default_latency_nsec(q);
 
-	wbt_set_queue_depth(rwb, blk_queue_depth(q));
-	wbt_set_write_cache(rwb, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
+	wbt_set_queue_depth(q, blk_queue_depth(q));
+	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
 
 	return 0;
 }
-
-void wbt_exit(struct request_queue *q)
-{
-	struct rq_wb *rwb = q->rq_wb;
-
-	if (rwb) {
-		blk_stat_remove_callback(q, rwb->cb);
-		blk_stat_free_callback(rwb->cb);
-		q->rq_wb = NULL;
-		kfree(rwb);
-	}
-}
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 300df531d0a6..53b20a58c0a2 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -9,6 +9,7 @@
 #include <linux/ktime.h>
 
 #include "blk-stat.h"
+#include "blk-rq-qos.h"
 
 enum wbt_flags {
 	WBT_TRACKED		= 1,	/* write, tracked for throttling */
@@ -35,20 +36,12 @@ enum {
 	WBT_STATE_ON_MANUAL	= 2,
 };
 
-struct rq_wait {
-	wait_queue_head_t wait;
-	atomic_t inflight;
-};
-
 struct rq_wb {
 	/*
 	 * Settings that govern how we throttle
 	 */
 	unsigned int wb_background;		/* background writeback */
 	unsigned int wb_normal;			/* normal writeback */
-	unsigned int wb_max;			/* max throughput writeback */
-	int scale_step;
-	bool scaled_max;
 
 	short enable_state;			/* WBT_STATE_* */
 
@@ -67,15 +60,20 @@ struct rq_wb {
 	void *sync_cookie;
 
 	unsigned int wc;
-	unsigned int queue_depth;
 
 	unsigned long last_issue;		/* last non-throttled issue */
 	unsigned long last_comp;		/* last non-throttled comp */
 	unsigned long min_lat_nsec;
-	struct request_queue *queue;
+	struct rq_qos rqos;
 	struct rq_wait rq_wait[WBT_NUM_RWQ];
+	struct rq_depth rq_depth;
 };
 
+static inline struct rq_wb *RQWB(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct rq_wb, rqos);
+}
+
 static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 {
 	unsigned int i, ret = 0;
@@ -86,6 +84,7 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 	return ret;
 }
 
+
 #ifdef CONFIG_BLK_WBT
 
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
@@ -93,19 +92,16 @@ static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 	rq->wbt_flags |= flags;
 }
 
-void __wbt_done(struct rq_wb *, enum wbt_flags);
-void wbt_done(struct rq_wb *, struct request *);
-enum wbt_flags wbt_wait(struct rq_wb *, struct bio *, spinlock_t *);
 int wbt_init(struct request_queue *);
-void wbt_exit(struct request_queue *);
-void wbt_update_limits(struct rq_wb *);
-void wbt_requeue(struct rq_wb *, struct request *);
-void wbt_issue(struct rq_wb *, struct request *);
+void wbt_update_limits(struct request_queue *);
 void wbt_disable_default(struct request_queue *);
 void wbt_enable_default(struct request_queue *);
 
-void wbt_set_queue_depth(struct rq_wb *, unsigned int);
-void wbt_set_write_cache(struct rq_wb *, bool);
+u64 wbt_get_min_lat(struct request_queue *q);
+void wbt_set_min_lat(struct request_queue *q, u64 val);
+
+void wbt_set_queue_depth(struct request_queue *, unsigned int);
+void wbt_set_write_cache(struct request_queue *, bool);
 
 u64 wbt_default_latency_nsec(struct request_queue *);
 
@@ -114,43 +110,30 @@ u64 wbt_default_latency_nsec(struct request_queue *);
 static inline void wbt_track(struct request *rq, enum wbt_flags flags)
 {
 }
-static inline void __wbt_done(struct rq_wb *rwb, enum wbt_flags flags)
-{
-}
-static inline void wbt_done(struct rq_wb *rwb, struct request *rq)
-{
-}
-static inline enum wbt_flags wbt_wait(struct rq_wb *rwb, struct bio *bio,
-				      spinlock_t *lock)
-{
-	return 0;
-}
 static inline int wbt_init(struct request_queue *q)
 {
 	return -EINVAL;
 }
-static inline void wbt_exit(struct request_queue *q)
-{
-}
-static inline void wbt_update_limits(struct rq_wb *rwb)
+static inline void wbt_update_limits(struct request_queue *q)
 {
 }
-static inline void wbt_requeue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_disable_default(struct request_queue *q)
 {
 }
-static inline void wbt_issue(struct rq_wb *rwb, struct request *rq)
+static inline void wbt_enable_default(struct request_queue *q)
 {
 }
-static inline void wbt_disable_default(struct request_queue *q)
+static inline void wbt_set_queue_depth(struct request_queue *q, unsigned int depth)
 {
 }
-static inline void wbt_enable_default(struct request_queue *q)
+static inline void wbt_set_write_cache(struct request_queue *q, bool wc)
 {
 }
-static inline void wbt_set_queue_depth(struct rq_wb *rwb, unsigned int depth)
+static inline u64 wbt_get_min_lat(struct request_queue *q)
 {
+	return 0;
 }
-static inline void wbt_set_write_cache(struct rq_wb *rwb, bool wc)
+static inline void wbt_set_min_lat(struct request_queue *q, u64 val)
 {
 }
 static inline u64 wbt_default_latency_nsec(struct request_queue *q)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 9d05646d5059..137759862f07 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -42,7 +42,7 @@ struct bsg_job;
 struct blkcg_gq;
 struct blk_flush_queue;
 struct pr_ops;
-struct rq_wb;
+struct rq_qos;
 struct blk_queue_stats;
 struct blk_stat_callback;
 
@@ -443,7 +443,7 @@ struct request_queue {
 	int			nr_rqs_elvpriv;	/* # allocated rqs w/ elvpriv */
 
 	struct blk_queue_stats	*stats;
-	struct rq_wb		*rq_wb;
+	struct rq_qos		*rq_qos;
 
 	/*
 	 * If blkcg is not used, @q->root_rl serves all requests.  If blkcg
-- 
cgit v1.2.3


From c1c80384c8f47021a01a0cc42894a06bed2b801b Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:14:59 -0400
Subject: block: remove external dependency on wbt_flags

We don't really need to save this stuff in the core block code, we can
just pass the bio back into the helpers later on to derive the same
flags and update the rq->wbt_flags appropriately.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c   |  9 ++++-----
 block/blk-mq.c     |  9 ++++-----
 block/blk-rq-qos.c | 24 +++++++++++++++---------
 block/blk-rq-qos.h | 11 ++++++-----
 block/blk-wbt.c    | 52 +++++++++++++++++++++++++++++++++++++++-------------
 block/blk-wbt.h    |  5 -----
 6 files changed, 68 insertions(+), 42 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index b33a73bcf2d0..687d7732f23a 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -42,7 +42,7 @@
 #include "blk.h"
 #include "blk-mq.h"
 #include "blk-mq-sched.h"
-#include "blk-wbt.h"
+#include "blk-rq-qos.h"
 
 #ifdef CONFIG_DEBUG_FS
 struct dentry *blk_debugfs_root;
@@ -1986,7 +1986,6 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	int where = ELEVATOR_INSERT_SORT;
 	struct request *req, *free;
 	unsigned int request_count = 0;
-	unsigned int wb_acct;
 
 	/*
 	 * low level driver can indicate that it wants pages above a
@@ -2044,7 +2043,7 @@ static blk_qc_t blk_queue_bio(struct request_queue *q, struct bio *bio)
 	}
 
 get_rq:
-	wb_acct = rq_qos_throttle(q, bio, q->queue_lock);
+	rq_qos_throttle(q, bio, q->queue_lock);
 
 	/*
 	 * Grab a free request. This is might sleep but can not fail.
@@ -2054,7 +2053,7 @@ get_rq:
 	req = get_request(q, bio->bi_opf, bio, 0, GFP_NOIO);
 	if (IS_ERR(req)) {
 		blk_queue_exit(q);
-		rq_qos_cleanup(q, wb_acct);
+		rq_qos_cleanup(q, bio);
 		if (PTR_ERR(req) == -ENOMEM)
 			bio->bi_status = BLK_STS_RESOURCE;
 		else
@@ -2063,7 +2062,7 @@ get_rq:
 		goto out_unlock;
 	}
 
-	wbt_track(req, wb_acct);
+	rq_qos_track(q, req, bio);
 
 	/*
 	 * After dropping the lock and possibly sleeping here, our request
diff --git a/block/blk-mq.c b/block/blk-mq.c
index ea2a226457fa..73a43b81b17d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -34,8 +34,8 @@
 #include "blk-mq-debugfs.h"
 #include "blk-mq-tag.h"
 #include "blk-stat.h"
-#include "blk-wbt.h"
 #include "blk-mq-sched.h"
+#include "blk-rq-qos.h"
 
 static bool blk_mq_poll(struct request_queue *q, blk_qc_t cookie);
 static void blk_mq_poll_stats_start(struct request_queue *q);
@@ -1790,7 +1790,6 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	struct blk_plug *plug;
 	struct request *same_queue_rq = NULL;
 	blk_qc_t cookie;
-	unsigned int wb_acct;
 
 	blk_queue_bounce(q, &bio);
 
@@ -1806,19 +1805,19 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 	if (blk_mq_sched_bio_merge(q, bio))
 		return BLK_QC_T_NONE;
 
-	wb_acct = rq_qos_throttle(q, bio, NULL);
+	rq_qos_throttle(q, bio, NULL);
 
 	trace_block_getrq(q, bio, bio->bi_opf);
 
 	rq = blk_mq_get_request(q, bio, bio->bi_opf, &data);
 	if (unlikely(!rq)) {
-		rq_qos_cleanup(q, wb_acct);
+		rq_qos_cleanup(q, bio);
 		if (bio->bi_opf & REQ_NOWAIT)
 			bio_wouldblock_error(bio);
 		return BLK_QC_T_NONE;
 	}
 
-	wbt_track(rq, wb_acct);
+	rq_qos_track(q, rq, bio);
 
 	cookie = request_to_qc_t(data.hctx, rq);
 
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index d2f2af8aa10c..b7b02e04f64f 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -1,7 +1,5 @@
 #include "blk-rq-qos.h"
 
-#include "blk-wbt.h"
-
 /*
  * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
  * false if 'v' + 1 would be bigger than 'below'.
@@ -29,13 +27,13 @@ bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit)
 	return atomic_inc_below(&rq_wait->inflight, limit);
 }
 
-void rq_qos_cleanup(struct request_queue *q, enum wbt_flags wb_acct)
+void rq_qos_cleanup(struct request_queue *q, struct bio *bio)
 {
 	struct rq_qos *rqos;
 
 	for (rqos = q->rq_qos; rqos; rqos = rqos->next) {
 		if (rqos->ops->cleanup)
-			rqos->ops->cleanup(rqos, wb_acct);
+			rqos->ops->cleanup(rqos, bio);
 	}
 }
 
@@ -69,17 +67,25 @@ void rq_qos_requeue(struct request_queue *q, struct request *rq)
 	}
 }
 
-enum wbt_flags rq_qos_throttle(struct request_queue *q, struct bio *bio,
-			       spinlock_t *lock)
+void rq_qos_throttle(struct request_queue *q, struct bio *bio,
+		     spinlock_t *lock)
 {
 	struct rq_qos *rqos;
-	enum wbt_flags flags = 0;
 
 	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
 		if (rqos->ops->throttle)
-			flags |= rqos->ops->throttle(rqos, bio, lock);
+			rqos->ops->throttle(rqos, bio, lock);
+	}
+}
+
+void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->track)
+			rqos->ops->track(rqos, rq, bio);
 	}
-	return flags;
 }
 
 /*
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index f9a39bd6ece3..a6d13b8ce0dc 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -25,12 +25,12 @@ struct rq_qos {
 };
 
 struct rq_qos_ops {
-	enum wbt_flags (*throttle)(struct rq_qos *, struct bio *,
-				   spinlock_t *);
+	void (*throttle)(struct rq_qos *, struct bio *, spinlock_t *);
+	void (*track)(struct rq_qos *, struct request *, struct bio *);
 	void (*issue)(struct rq_qos *, struct request *);
 	void (*requeue)(struct rq_qos *, struct request *);
 	void (*done)(struct rq_qos *, struct request *);
-	void (*cleanup)(struct rq_qos *, enum wbt_flags);
+	void (*cleanup)(struct rq_qos *, struct bio *);
 	void (*exit)(struct rq_qos *);
 };
 
@@ -97,10 +97,11 @@ void rq_depth_scale_up(struct rq_depth *rqd);
 void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
 bool rq_depth_calc_max_depth(struct rq_depth *rqd);
 
-void rq_qos_cleanup(struct request_queue *, enum wbt_flags);
+void rq_qos_cleanup(struct request_queue *, struct bio *);
 void rq_qos_done(struct request_queue *, struct request *);
 void rq_qos_issue(struct request_queue *, struct request *);
 void rq_qos_requeue(struct request_queue *, struct request *);
-enum wbt_flags rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
+void rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
+void rq_qos_track(struct request_queue *q, struct request *, struct bio *);
 void rq_qos_exit(struct request_queue *);
 #endif
diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 6fe20fb823e4..461a9af11efe 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -549,41 +549,66 @@ static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
 	}
 }
 
+static enum wbt_flags bio_to_wbt_flags(struct rq_wb *rwb, struct bio *bio)
+{
+	enum wbt_flags flags = 0;
+
+	if (bio_op(bio) == REQ_OP_READ) {
+		flags = WBT_READ;
+	} else if (wbt_should_throttle(rwb, bio)) {
+		if (current_is_kswapd())
+			flags |= WBT_KSWAPD;
+		if (bio_op(bio) == REQ_OP_DISCARD)
+			flags |= WBT_DISCARD;
+		flags |= WBT_TRACKED;
+	}
+	return flags;
+}
+
+static void wbt_cleanup(struct rq_qos *rqos, struct bio *bio)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	enum wbt_flags flags = bio_to_wbt_flags(rwb, bio);
+	__wbt_done(rqos, flags);
+}
+
 /*
  * Returns true if the IO request should be accounted, false if not.
  * May sleep, if we have exceeded the writeback limits. Caller can pass
  * in an irq held spinlock, if it holds one when calling this function.
  * If we do sleep, we'll release and re-grab it.
  */
-static enum wbt_flags wbt_wait(struct rq_qos *rqos, struct bio *bio,
-			       spinlock_t *lock)
+static void wbt_wait(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock)
 {
 	struct rq_wb *rwb = RQWB(rqos);
-	enum wbt_flags ret = 0;
+	enum wbt_flags flags;
 
 	if (!rwb_enabled(rwb))
-		return 0;
+		return;
 
-	if (bio_op(bio) == REQ_OP_READ)
-		ret = WBT_READ;
+	flags = bio_to_wbt_flags(rwb, bio);
 
 	if (!wbt_should_throttle(rwb, bio)) {
-		if (ret & WBT_READ)
+		if (flags & WBT_READ)
 			wb_timestamp(rwb, &rwb->last_issue);
-		return ret;
+		return;
 	}
 
 	if (current_is_kswapd())
-		ret |= WBT_KSWAPD;
+		flags |= WBT_KSWAPD;
 	if (bio_op(bio) == REQ_OP_DISCARD)
-		ret |= WBT_DISCARD;
+		flags |= WBT_DISCARD;
 
-	__wbt_wait(rwb, ret, bio->bi_opf, lock);
+	__wbt_wait(rwb, flags, bio->bi_opf, lock);
 
 	if (!blk_stat_is_active(rwb->cb))
 		rwb_arm_timer(rwb);
+}
 
-	return ret | WBT_TRACKED;
+static void wbt_track(struct rq_qos *rqos, struct request *rq, struct bio *bio)
+{
+	struct rq_wb *rwb = RQWB(rqos);
+	rq->wbt_flags |= bio_to_wbt_flags(rwb, bio);
 }
 
 void wbt_issue(struct rq_qos *rqos, struct request *rq)
@@ -707,9 +732,10 @@ EXPORT_SYMBOL_GPL(wbt_disable_default);
 static struct rq_qos_ops wbt_rqos_ops = {
 	.throttle = wbt_wait,
 	.issue = wbt_issue,
+	.track = wbt_track,
 	.requeue = wbt_requeue,
 	.done = wbt_done,
-	.cleanup = __wbt_done,
+	.cleanup = wbt_cleanup,
 	.exit = wbt_exit,
 };
 
diff --git a/block/blk-wbt.h b/block/blk-wbt.h
index 53b20a58c0a2..f47218d5b3b2 100644
--- a/block/blk-wbt.h
+++ b/block/blk-wbt.h
@@ -87,11 +87,6 @@ static inline unsigned int wbt_inflight(struct rq_wb *rwb)
 
 #ifdef CONFIG_BLK_WBT
 
-static inline void wbt_track(struct request *rq, enum wbt_flags flags)
-{
-	rq->wbt_flags |= flags;
-}
-
 int wbt_init(struct request_queue *);
 void wbt_update_limits(struct request_queue *);
 void wbt_disable_default(struct request_queue *);
-- 
cgit v1.2.3


From 67b42d0bf7a8fd1ec0cf1acdc9550e688d7c8578 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:15:00 -0400
Subject: rq-qos: introduce dio_bio callback

wbt cares only about request completion time, but controllers may need
information that is on the bio itself, so add a done_bio callback for
rq-qos so things like blk-iolatency can use it to have the bio when it
completes.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c        |  4 ++++
 block/blk-rq-qos.c | 10 ++++++++++
 block/blk-rq-qos.h |  2 ++
 3 files changed, 16 insertions(+)

diff --git a/block/bio.c b/block/bio.c
index 5f84f5c3887b..f3536bfc8298 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -32,6 +32,7 @@
 
 #include <trace/events/block.h>
 #include "blk.h"
+#include "blk-rq-qos.h"
 
 /*
  * Test patch to inline a certain number of bi_io_vec's inside the bio
@@ -1808,6 +1809,9 @@ again:
 	if (!bio_integrity_endio(bio))
 		return;
 
+	if (bio->bi_disk)
+		rq_qos_done_bio(bio->bi_disk->queue, bio);
+
 	/*
 	 * Need to have a real endio function for chained bios, otherwise
 	 * various corner cases will break (like stacking block devices that
diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index b7b02e04f64f..5134b24482f6 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -88,6 +88,16 @@ void rq_qos_track(struct request_queue *q, struct request *rq, struct bio *bio)
 	}
 }
 
+void rq_qos_done_bio(struct request_queue *q, struct bio *bio)
+{
+	struct rq_qos *rqos;
+
+	for(rqos = q->rq_qos; rqos; rqos = rqos->next) {
+		if (rqos->ops->done_bio)
+			rqos->ops->done_bio(rqos, bio);
+	}
+}
+
 /*
  * Return true, if we can't increase the depth further by scaling
  */
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index a6d13b8ce0dc..d5e2f68fe41e 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -30,6 +30,7 @@ struct rq_qos_ops {
 	void (*issue)(struct rq_qos *, struct request *);
 	void (*requeue)(struct rq_qos *, struct request *);
 	void (*done)(struct rq_qos *, struct request *);
+	void (*done_bio)(struct rq_qos *, struct bio *);
 	void (*cleanup)(struct rq_qos *, struct bio *);
 	void (*exit)(struct rq_qos *);
 };
@@ -101,6 +102,7 @@ void rq_qos_cleanup(struct request_queue *, struct bio *);
 void rq_qos_done(struct request_queue *, struct request *);
 void rq_qos_issue(struct request_queue *, struct request *);
 void rq_qos_requeue(struct request_queue *, struct request *);
+void rq_qos_done_bio(struct request_queue *q, struct bio *bio);
 void rq_qos_throttle(struct request_queue *, struct bio *, spinlock_t *);
 void rq_qos_track(struct request_queue *q, struct request *, struct bio *);
 void rq_qos_exit(struct request_queue *);
-- 
cgit v1.2.3


From d70675121546c35feaceebf7ed9caed8716640f3 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:15:01 -0400
Subject: block: introduce blk-iolatency io controller

Current IO controllers for the block layer are less than ideal for our
use case.  The io.max controller is great at hard limiting, but it is
not work conserving.  This patch introduces io.latency.  You provide a
latency target for your group and we monitor the io in short windows to
make sure we are not exceeding those latency targets.  This makes use of
the rq-qos infrastructure and works much like the wbt stuff.  There are
a few differences from wbt

 - It's bio based, so the latency covers the whole block layer in addition to
   the actual io.
 - We will throttle all IO types that comes in here if we need to.
 - We use the mean latency over the 100ms window.  This is because writes can
   be particularly fast, which could give us a false sense of the impact of
   other workloads on our protected workload.
 - By default there's no throttling, we set the queue_depth to INT_MAX so that
   we can have as many outstanding bio's as we're allowed to.  Only at
   throttle time do we pay attention to the actual queue depth.
 - We backcharge cgroups for root cg issued IO and induce artificial
   delays in order to deal with cases like metadata only or swap heavy
   workloads.

In testing this has worked out relatively well.  Protected workloads
will throttle noisy workloads down to 1 io at time if they are doing
normal IO on their own, or induce up to a 1 second delay per syscall if
they are doing a lot of root issued IO (metadata/swap IO).

Our testing has revolved mostly around our production web servers where
we have hhvm (the web server application) in a protected group and
everything else in another group.  We see slightly higher requests per
second (RPS) on the test tier vs the control tier, and much more stable
RPS across all machines in the test tier vs the control tier.

Another test we run is a slow memory allocator in the unprotected group.
Before this would eventually push us into swap and cause the whole box
to die and not recover at all.  With these patches we see slight RPS
drops (usually 10-15%) before the memory consumer is properly killed and
things recover within seconds.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/Kconfig             |  12 +
 block/Makefile            |   1 +
 block/blk-cgroup.c        |   8 +
 block/blk-iolatency.c     | 930 ++++++++++++++++++++++++++++++++++++++++++++++
 block/blk.h               |   6 +
 include/linux/blk_types.h |   2 -
 6 files changed, 957 insertions(+), 2 deletions(-)
 create mode 100644 block/blk-iolatency.c

diff --git a/block/Kconfig b/block/Kconfig
index dfe7bc770fc9..1f2469a0123c 100644
--- a/block/Kconfig
+++ b/block/Kconfig
@@ -149,6 +149,18 @@ config BLK_WBT
 	dynamically on an algorithm loosely based on CoDel, factoring in
 	the realtime performance of the disk.
 
+config BLK_CGROUP_IOLATENCY
+	bool "Enable support for latency based cgroup IO protection"
+	depends on BLK_CGROUP=y
+	default n
+	---help---
+	Enabling this option enables the .latency interface for IO throttling.
+	The IO controller will attempt to maintain average IO latencies below
+	the configured latency target, throttling anybody with a higher latency
+	target than the victimized group.
+
+	Note, this is an experimental interface and could be changed someday.
+
 config BLK_WBT_SQ
 	bool "Single queue writeback throttling"
 	default n
diff --git a/block/Makefile b/block/Makefile
index 57d0f47ab05f..572b33f32c07 100644
--- a/block/Makefile
+++ b/block/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_BLK_DEV_BSG)	+= bsg.o
 obj-$(CONFIG_BLK_DEV_BSGLIB)	+= bsg-lib.o
 obj-$(CONFIG_BLK_CGROUP)	+= blk-cgroup.o
 obj-$(CONFIG_BLK_DEV_THROTTLING)	+= blk-throttle.o
+obj-$(CONFIG_BLK_CGROUP_IOLATENCY)	+= blk-iolatency.o
 obj-$(CONFIG_IOSCHED_NOOP)	+= noop-iosched.o
 obj-$(CONFIG_IOSCHED_DEADLINE)	+= deadline-iosched.o
 obj-$(CONFIG_IOSCHED_CFQ)	+= cfq-iosched.o
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index d3310ec96c2a..7e2c19ce1a08 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1238,6 +1238,14 @@ int blkcg_init_queue(struct request_queue *q)
 	if (preloaded)
 		radix_tree_preload_end();
 
+	ret = blk_iolatency_init(q);
+	if (ret) {
+		spin_lock_irq(q->queue_lock);
+		blkg_destroy_all(q);
+		spin_unlock_irq(q->queue_lock);
+		return ret;
+	}
+
 	ret = blk_throtl_init(q);
 	if (ret) {
 		spin_lock_irq(q->queue_lock);
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
new file mode 100644
index 000000000000..a35a1f580337
--- /dev/null
+++ b/block/blk-iolatency.c
@@ -0,0 +1,930 @@
+/*
+ * Block rq-qos base io controller
+ *
+ * This works similar to wbt with a few exceptions
+ *
+ * - It's bio based, so the latency covers the whole block layer in addition to
+ *   the actual io.
+ * - We will throttle all IO that comes in here if we need to.
+ * - We use the mean latency over the 100ms window.  This is because writes can
+ *   be particularly fast, which could give us a false sense of the impact of
+ *   other workloads on our protected workload.
+ * - By default there's no throttling, we set the queue_depth to INT_MAX so that
+ *   we can have as many outstanding bio's as we're allowed to.  Only at
+ *   throttle time do we pay attention to the actual queue depth.
+ *
+ * The hierarchy works like the cpu controller does, we track the latency at
+ * every configured node, and each configured node has it's own independent
+ * queue depth.  This means that we only care about our latency targets at the
+ * peer level.  Some group at the bottom of the hierarchy isn't going to affect
+ * a group at the end of some other path if we're only configred at leaf level.
+ *
+ * Consider the following
+ *
+ *                   root blkg
+ *             /                     \
+ *        fast (target=5ms)     slow (target=10ms)
+ *         /     \                  /        \
+ *       a        b          normal(15ms)   unloved
+ *
+ * "a" and "b" have no target, but their combined io under "fast" cannot exceed
+ * an average latency of 5ms.  If it does then we will throttle the "slow"
+ * group.  In the case of "normal", if it exceeds its 15ms target, we will
+ * throttle "unloved", but nobody else.
+ *
+ * In this example "fast", "slow", and "normal" will be the only groups actually
+ * accounting their io latencies.  We have to walk up the heirarchy to the root
+ * on every submit and complete so we can do the appropriate stat recording and
+ * adjust the queue depth of ourselves if needed.
+ *
+ * There are 2 ways we throttle IO.
+ *
+ * 1) Queue depth throttling.  As we throttle down we will adjust the maximum
+ * number of IO's we're allowed to have in flight.  This starts at (u64)-1 down
+ * to 1.  If the group is only ever submitting IO for itself then this is the
+ * only way we throttle.
+ *
+ * 2) Induced delay throttling.  This is for the case that a group is generating
+ * IO that has to be issued by the root cg to avoid priority inversion. So think
+ * REQ_META or REQ_SWAP.  If we are already at qd == 1 and we're getting a lot
+ * of work done for us on behalf of the root cg and are being asked to scale
+ * down more then we induce a latency at userspace return.  We accumulate the
+ * total amount of time we need to be punished by doing
+ *
+ * total_time += min_lat_nsec - actual_io_completion
+ *
+ * and then at throttle time will do
+ *
+ * throttle_time = min(total_time, NSEC_PER_SEC)
+ *
+ * This induced delay will throttle back the activity that is generating the
+ * root cg issued io's, wethere that's some metadata intensive operation or the
+ * group is using so much memory that it is pushing us into swap.
+ *
+ * Copyright (C) 2018 Josef Bacik
+ */
+#include <linux/kernel.h>
+#include <linux/blk_types.h>
+#include <linux/backing-dev.h>
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/memcontrol.h>
+#include <linux/sched/signal.h>
+#include <trace/events/block.h>
+#include "blk-rq-qos.h"
+#include "blk-stat.h"
+
+#define DEFAULT_SCALE_COOKIE 1000000U
+
+static struct blkcg_policy blkcg_policy_iolatency;
+struct iolatency_grp;
+
+struct blk_iolatency {
+	struct rq_qos rqos;
+	struct timer_list timer;
+	atomic_t enabled;
+};
+
+static inline struct blk_iolatency *BLKIOLATENCY(struct rq_qos *rqos)
+{
+	return container_of(rqos, struct blk_iolatency, rqos);
+}
+
+static inline bool blk_iolatency_enabled(struct blk_iolatency *blkiolat)
+{
+	return atomic_read(&blkiolat->enabled) > 0;
+}
+
+struct child_latency_info {
+	spinlock_t lock;
+
+	/* Last time we adjusted the scale of everybody. */
+	u64 last_scale_event;
+
+	/* The latency that we missed. */
+	u64 scale_lat;
+
+	/* Total io's from all of our children for the last summation. */
+	u64 nr_samples;
+
+	/* The guy who actually changed the latency numbers. */
+	struct iolatency_grp *scale_grp;
+
+	/* Cookie to tell if we need to scale up or down. */
+	atomic_t scale_cookie;
+};
+
+struct iolatency_grp {
+	struct blkg_policy_data pd;
+	struct blk_rq_stat __percpu *stats;
+	struct blk_iolatency *blkiolat;
+	struct rq_depth rq_depth;
+	struct rq_wait rq_wait;
+	atomic64_t window_start;
+	atomic_t scale_cookie;
+	u64 min_lat_nsec;
+	u64 cur_win_nsec;
+
+	/* total running average of our io latency. */
+	u64 total_lat_avg;
+	u64 total_lat_nr;
+
+	/* Our current number of IO's for the last summation. */
+	u64 nr_samples;
+
+	struct child_latency_info child_lat;
+};
+
+static inline struct iolatency_grp *pd_to_lat(struct blkg_policy_data *pd)
+{
+	return pd ? container_of(pd, struct iolatency_grp, pd) : NULL;
+}
+
+static inline struct iolatency_grp *blkg_to_lat(struct blkcg_gq *blkg)
+{
+	return pd_to_lat(blkg_to_pd(blkg, &blkcg_policy_iolatency));
+}
+
+static inline struct blkcg_gq *lat_to_blkg(struct iolatency_grp *iolat)
+{
+	return pd_to_blkg(&iolat->pd);
+}
+
+static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
+				       wait_queue_entry_t *wait,
+				       bool first_block)
+{
+	struct rq_wait *rqw = &iolat->rq_wait;
+
+	if (first_block && waitqueue_active(&rqw->wait) &&
+	    rqw->wait.head.next != &wait->entry)
+		return false;
+	return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
+}
+
+static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
+				       struct iolatency_grp *iolat,
+				       spinlock_t *lock, bool issue_as_root,
+				       bool use_memdelay)
+	__releases(lock)
+	__acquires(lock)
+{
+	struct rq_wait *rqw = &iolat->rq_wait;
+	unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
+	DEFINE_WAIT(wait);
+	bool first_block = true;
+
+	if (use_delay)
+		blkcg_schedule_throttle(rqos->q, use_memdelay);
+
+	/*
+	 * To avoid priority inversions we want to just take a slot if we are
+	 * issuing as root.  If we're being killed off there's no point in
+	 * delaying things, we may have been killed by OOM so throttling may
+	 * make recovery take even longer, so just let the IO's through so the
+	 * task can go away.
+	 */
+	if (issue_as_root || fatal_signal_pending(current)) {
+		atomic_inc(&rqw->inflight);
+		return;
+	}
+
+	if (iolatency_may_queue(iolat, &wait, first_block))
+		return;
+
+	do {
+		prepare_to_wait_exclusive(&rqw->wait, &wait,
+					  TASK_UNINTERRUPTIBLE);
+
+		if (iolatency_may_queue(iolat, &wait, first_block))
+			break;
+		first_block = false;
+
+		if (lock) {
+			spin_unlock_irq(lock);
+			io_schedule();
+			spin_lock_irq(lock);
+		} else {
+			io_schedule();
+		}
+	} while (1);
+
+	finish_wait(&rqw->wait, &wait);
+}
+
+#define SCALE_DOWN_FACTOR 2
+#define SCALE_UP_FACTOR 4
+
+static inline unsigned long scale_amount(unsigned long qd, bool up)
+{
+	return max(up ? qd >> SCALE_UP_FACTOR : qd >> SCALE_DOWN_FACTOR, 1UL);
+}
+
+/*
+ * We scale the qd down faster than we scale up, so we need to use this helper
+ * to adjust the scale_cookie accordingly so we don't prematurely get
+ * scale_cookie at DEFAULT_SCALE_COOKIE and unthrottle too much.
+ *
+ * Each group has their own local copy of the last scale cookie they saw, so if
+ * the global scale cookie goes up or down they know which way they need to go
+ * based on their last knowledge of it.
+ */
+static void scale_cookie_change(struct blk_iolatency *blkiolat,
+				struct child_latency_info *lat_info,
+				bool up)
+{
+	unsigned long qd = blk_queue_depth(blkiolat->rqos.q);
+	unsigned long scale = scale_amount(qd, up);
+	unsigned long old = atomic_read(&lat_info->scale_cookie);
+	unsigned long max_scale = qd << 1;
+	unsigned long diff = 0;
+
+	if (old < DEFAULT_SCALE_COOKIE)
+		diff = DEFAULT_SCALE_COOKIE - old;
+
+	if (up) {
+		if (scale + old > DEFAULT_SCALE_COOKIE)
+			atomic_set(&lat_info->scale_cookie,
+				   DEFAULT_SCALE_COOKIE);
+		else if (diff > qd)
+			atomic_inc(&lat_info->scale_cookie);
+		else
+			atomic_add(scale, &lat_info->scale_cookie);
+	} else {
+		/*
+		 * We don't want to dig a hole so deep that it takes us hours to
+		 * dig out of it.  Just enough that we don't throttle/unthrottle
+		 * with jagged workloads but can still unthrottle once pressure
+		 * has sufficiently dissipated.
+		 */
+		if (diff > qd) {
+			if (diff < max_scale)
+				atomic_dec(&lat_info->scale_cookie);
+		} else {
+			atomic_sub(scale, &lat_info->scale_cookie);
+		}
+	}
+}
+
+/*
+ * Change the queue depth of the iolatency_grp.  We add/subtract 1/16th of the
+ * queue depth at a time so we don't get wild swings and hopefully dial in to
+ * fairer distribution of the overall queue depth.
+ */
+static void scale_change(struct iolatency_grp *iolat, bool up)
+{
+	unsigned long qd = blk_queue_depth(iolat->blkiolat->rqos.q);
+	unsigned long scale = scale_amount(qd, up);
+	unsigned long old = iolat->rq_depth.max_depth;
+	bool changed = false;
+
+	if (old > qd)
+		old = qd;
+
+	if (up) {
+		if (old == 1 && blkcg_unuse_delay(lat_to_blkg(iolat)))
+			return;
+
+		if (old < qd) {
+			changed = true;
+			old += scale;
+			old = min(old, qd);
+			iolat->rq_depth.max_depth = old;
+			wake_up_all(&iolat->rq_wait.wait);
+		}
+	} else if (old > 1) {
+		old >>= 1;
+		changed = true;
+		iolat->rq_depth.max_depth = max(old, 1UL);
+	}
+}
+
+/* Check our parent and see if the scale cookie has changed. */
+static void check_scale_change(struct iolatency_grp *iolat)
+{
+	struct iolatency_grp *parent;
+	struct child_latency_info *lat_info;
+	unsigned int cur_cookie;
+	unsigned int our_cookie = atomic_read(&iolat->scale_cookie);
+	u64 scale_lat;
+	unsigned int old;
+	int direction = 0;
+
+	if (lat_to_blkg(iolat)->parent == NULL)
+		return;
+
+	parent = blkg_to_lat(lat_to_blkg(iolat)->parent);
+	if (!parent)
+		return;
+
+	lat_info = &parent->child_lat;
+	cur_cookie = atomic_read(&lat_info->scale_cookie);
+	scale_lat = READ_ONCE(lat_info->scale_lat);
+
+	if (cur_cookie < our_cookie)
+		direction = -1;
+	else if (cur_cookie > our_cookie)
+		direction = 1;
+	else
+		return;
+
+	old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie);
+
+	/* Somebody beat us to the punch, just bail. */
+	if (old != our_cookie)
+		return;
+
+	if (direction < 0 && iolat->min_lat_nsec) {
+		u64 samples_thresh;
+
+		if (!scale_lat || iolat->min_lat_nsec <= scale_lat)
+			return;
+
+		/*
+		 * Sometimes high priority groups are their own worst enemy, so
+		 * instead of taking it out on some poor other group that did 5%
+		 * or less of the IO's for the last summation just skip this
+		 * scale down event.
+		 */
+		samples_thresh = lat_info->nr_samples * 5;
+		samples_thresh = div64_u64(samples_thresh, 100);
+		if (iolat->nr_samples <= samples_thresh)
+			return;
+	}
+
+	/* We're as low as we can go. */
+	if (iolat->rq_depth.max_depth == 1 && direction < 0) {
+		blkcg_use_delay(lat_to_blkg(iolat));
+		return;
+	}
+
+	/* We're back to the default cookie, unthrottle all the things. */
+	if (cur_cookie == DEFAULT_SCALE_COOKIE) {
+		blkcg_clear_delay(lat_to_blkg(iolat));
+		iolat->rq_depth.max_depth = INT_MAX;
+		wake_up_all(&iolat->rq_wait.wait);
+		return;
+	}
+
+	scale_change(iolat, direction > 0);
+}
+
+static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
+				     spinlock_t *lock)
+{
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+	struct blkcg *blkcg;
+	struct blkcg_gq *blkg;
+	struct request_queue *q = rqos->q;
+	bool issue_as_root = bio_issue_as_root_blkg(bio);
+
+	if (!blk_iolatency_enabled(blkiolat))
+		return;
+
+	rcu_read_lock();
+	blkcg = bio_blkcg(bio);
+	bio_associate_blkcg(bio, &blkcg->css);
+	blkg = blkg_lookup(blkcg, q);
+	if (unlikely(!blkg)) {
+		if (!lock)
+			spin_lock_irq(q->queue_lock);
+		blkg = blkg_lookup_create(blkcg, q);
+		if (IS_ERR(blkg))
+			blkg = NULL;
+		if (!lock)
+			spin_unlock_irq(q->queue_lock);
+	}
+	if (!blkg)
+		goto out;
+
+	bio_issue_init(&bio->bi_issue, bio_sectors(bio));
+	bio_associate_blkg(bio, blkg);
+out:
+	rcu_read_unlock();
+	while (blkg && blkg->parent) {
+		struct iolatency_grp *iolat = blkg_to_lat(blkg);
+		if (!iolat) {
+			blkg = blkg->parent;
+			continue;
+		}
+
+		check_scale_change(iolat);
+		__blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
+				     (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
+		blkg = blkg->parent;
+	}
+	if (!timer_pending(&blkiolat->timer))
+		mod_timer(&blkiolat->timer, jiffies + HZ);
+}
+
+static void iolatency_record_time(struct iolatency_grp *iolat,
+				  struct bio_issue *issue, u64 now,
+				  bool issue_as_root)
+{
+	struct blk_rq_stat *rq_stat;
+	u64 start = bio_issue_time(issue);
+	u64 req_time;
+
+	if (now <= start)
+		return;
+
+	req_time = now - start;
+
+	/*
+	 * We don't want to count issue_as_root bio's in the cgroups latency
+	 * statistics as it could skew the numbers downwards.
+	 */
+	if (unlikely(issue_as_root && iolat->rq_depth.max_depth != (u64)-1)) {
+		u64 sub = iolat->min_lat_nsec;
+		if (req_time < sub)
+			blkcg_add_delay(lat_to_blkg(iolat), now, sub - req_time);
+		return;
+	}
+
+	rq_stat = get_cpu_ptr(iolat->stats);
+	blk_rq_stat_add(rq_stat, req_time);
+	put_cpu_ptr(rq_stat);
+}
+
+#define BLKIOLATENCY_MIN_ADJUST_TIME (500 * NSEC_PER_MSEC)
+#define BLKIOLATENCY_MIN_GOOD_SAMPLES 5
+
+static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
+{
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+	struct iolatency_grp *parent;
+	struct child_latency_info *lat_info;
+	struct blk_rq_stat stat;
+	unsigned long flags;
+	int cpu;
+
+	blk_rq_stat_init(&stat);
+	preempt_disable();
+	for_each_online_cpu(cpu) {
+		struct blk_rq_stat *s;
+		s = per_cpu_ptr(iolat->stats, cpu);
+		blk_rq_stat_sum(&stat, s);
+		blk_rq_stat_init(s);
+	}
+	preempt_enable();
+
+	/*
+	 * Our average exceeded our window, scale up our window so we are more
+	 * accurate, but not more than the global timer.
+	 */
+	if (stat.mean > iolat->cur_win_nsec) {
+		iolat->cur_win_nsec <<= 1;
+		iolat->cur_win_nsec =
+			max_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC);
+	}
+
+	parent = blkg_to_lat(blkg->parent);
+	if (!parent)
+		return;
+
+	lat_info = &parent->child_lat;
+
+	iolat->total_lat_avg =
+		div64_u64((iolat->total_lat_avg * iolat->total_lat_nr) +
+			  stat.mean, iolat->total_lat_nr + 1);
+
+	iolat->total_lat_nr++;
+
+	/* Everything is ok and we don't need to adjust the scale. */
+	if (stat.mean <= iolat->min_lat_nsec &&
+	    atomic_read(&lat_info->scale_cookie) == DEFAULT_SCALE_COOKIE)
+		return;
+
+	/* Somebody beat us to the punch, just bail. */
+	spin_lock_irqsave(&lat_info->lock, flags);
+	lat_info->nr_samples -= iolat->nr_samples;
+	lat_info->nr_samples += stat.nr_samples;
+	iolat->nr_samples = stat.nr_samples;
+
+	if ((lat_info->last_scale_event >= now ||
+	    now - lat_info->last_scale_event < BLKIOLATENCY_MIN_ADJUST_TIME) &&
+	    lat_info->scale_lat <= iolat->min_lat_nsec)
+		goto out;
+
+	if (stat.mean <= iolat->min_lat_nsec &&
+	    stat.nr_samples >= BLKIOLATENCY_MIN_GOOD_SAMPLES) {
+		if (lat_info->scale_grp == iolat) {
+			lat_info->last_scale_event = now;
+			scale_cookie_change(iolat->blkiolat, lat_info, true);
+		}
+	} else if (stat.mean > iolat->min_lat_nsec) {
+		lat_info->last_scale_event = now;
+		if (!lat_info->scale_grp ||
+		    lat_info->scale_lat > iolat->min_lat_nsec) {
+			WRITE_ONCE(lat_info->scale_lat, iolat->min_lat_nsec);
+			lat_info->scale_grp = iolat;
+		}
+		scale_cookie_change(iolat->blkiolat, lat_info, false);
+	}
+out:
+	spin_unlock_irqrestore(&lat_info->lock, flags);
+}
+
+static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
+{
+	struct blkcg_gq *blkg;
+	struct rq_wait *rqw;
+	struct iolatency_grp *iolat;
+	u64 window_start;
+	u64 now = ktime_to_ns(ktime_get());
+	bool issue_as_root = bio_issue_as_root_blkg(bio);
+	bool enabled = false;
+
+	blkg = bio->bi_blkg;
+	if (!blkg)
+		return;
+
+	iolat = blkg_to_lat(bio->bi_blkg);
+	if (!iolat)
+		return;
+
+	enabled = blk_iolatency_enabled(iolat->blkiolat);
+	while (blkg && blkg->parent) {
+		iolat = blkg_to_lat(blkg);
+		if (!iolat) {
+			blkg = blkg->parent;
+			continue;
+		}
+		rqw = &iolat->rq_wait;
+
+		atomic_dec(&rqw->inflight);
+		if (!enabled || iolat->min_lat_nsec == 0)
+			goto next;
+		iolatency_record_time(iolat, &bio->bi_issue, now,
+				      issue_as_root);
+		window_start = atomic64_read(&iolat->window_start);
+		if (now > window_start &&
+		    (now - window_start) >= iolat->cur_win_nsec) {
+			if (atomic64_cmpxchg(&iolat->window_start,
+					window_start, now) == window_start)
+				iolatency_check_latencies(iolat, now);
+		}
+next:
+		wake_up(&rqw->wait);
+		blkg = blkg->parent;
+	}
+}
+
+static void blkcg_iolatency_cleanup(struct rq_qos *rqos, struct bio *bio)
+{
+	struct blkcg_gq *blkg;
+
+	blkg = bio->bi_blkg;
+	while (blkg && blkg->parent) {
+		struct rq_wait *rqw;
+		struct iolatency_grp *iolat;
+
+		iolat = blkg_to_lat(blkg);
+		if (!iolat)
+			goto next;
+
+		rqw = &iolat->rq_wait;
+		atomic_dec(&rqw->inflight);
+		wake_up(&rqw->wait);
+next:
+		blkg = blkg->parent;
+	}
+}
+
+static void blkcg_iolatency_exit(struct rq_qos *rqos)
+{
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+
+	del_timer_sync(&blkiolat->timer);
+	blkcg_deactivate_policy(rqos->q, &blkcg_policy_iolatency);
+	kfree(blkiolat);
+}
+
+static struct rq_qos_ops blkcg_iolatency_ops = {
+	.throttle = blkcg_iolatency_throttle,
+	.cleanup = blkcg_iolatency_cleanup,
+	.done_bio = blkcg_iolatency_done_bio,
+	.exit = blkcg_iolatency_exit,
+};
+
+static void blkiolatency_timer_fn(struct timer_list *t)
+{
+	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
+	struct blkcg_gq *blkg;
+	struct cgroup_subsys_state *pos_css;
+	u64 now = ktime_to_ns(ktime_get());
+
+	rcu_read_lock();
+	blkg_for_each_descendant_pre(blkg, pos_css,
+				     blkiolat->rqos.q->root_blkg) {
+		struct iolatency_grp *iolat;
+		struct child_latency_info *lat_info;
+		unsigned long flags;
+		u64 cookie;
+
+		/*
+		 * We could be exiting, don't access the pd unless we have a
+		 * ref on the blkg.
+		 */
+		if (!blkg_try_get(blkg))
+			continue;
+
+		iolat = blkg_to_lat(blkg);
+		if (!iolat)
+			continue;
+
+		lat_info = &iolat->child_lat;
+		cookie = atomic_read(&lat_info->scale_cookie);
+
+		if (cookie >= DEFAULT_SCALE_COOKIE)
+			goto next;
+
+		spin_lock_irqsave(&lat_info->lock, flags);
+		if (lat_info->last_scale_event >= now)
+			goto next_lock;
+
+		/*
+		 * We scaled down but don't have a scale_grp, scale up and carry
+		 * on.
+		 */
+		if (lat_info->scale_grp == NULL) {
+			scale_cookie_change(iolat->blkiolat, lat_info, true);
+			goto next_lock;
+		}
+
+		/*
+		 * It's been 5 seconds since our last scale event, clear the
+		 * scale grp in case the group that needed the scale down isn't
+		 * doing any IO currently.
+		 */
+		if (now - lat_info->last_scale_event >=
+		    ((u64)NSEC_PER_SEC * 5))
+			lat_info->scale_grp = NULL;
+next_lock:
+		spin_unlock_irqrestore(&lat_info->lock, flags);
+next:
+		blkg_put(blkg);
+	}
+	rcu_read_unlock();
+}
+
+int blk_iolatency_init(struct request_queue *q)
+{
+	struct blk_iolatency *blkiolat;
+	struct rq_qos *rqos;
+	int ret;
+
+	blkiolat = kzalloc(sizeof(*blkiolat), GFP_KERNEL);
+	if (!blkiolat)
+		return -ENOMEM;
+
+	rqos = &blkiolat->rqos;
+	rqos->id = RQ_QOS_CGROUP;
+	rqos->ops = &blkcg_iolatency_ops;
+	rqos->q = q;
+
+	rq_qos_add(q, rqos);
+
+	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
+	if (ret) {
+		rq_qos_del(q, rqos);
+		kfree(blkiolat);
+		return ret;
+	}
+
+	timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);
+
+	return 0;
+}
+
+static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
+{
+	struct iolatency_grp *iolat = blkg_to_lat(blkg);
+	struct blk_iolatency *blkiolat = iolat->blkiolat;
+	u64 oldval = iolat->min_lat_nsec;
+
+	iolat->min_lat_nsec = val;
+	iolat->cur_win_nsec = max_t(u64, val << 4, 100 * NSEC_PER_MSEC);
+	iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC);
+
+	if (!oldval && val)
+		atomic_inc(&blkiolat->enabled);
+	if (oldval && !val)
+		atomic_dec(&blkiolat->enabled);
+}
+
+static void iolatency_clear_scaling(struct blkcg_gq *blkg)
+{
+	if (blkg->parent) {
+		struct iolatency_grp *iolat = blkg_to_lat(blkg->parent);
+		struct child_latency_info *lat_info;
+		if (!iolat)
+			return;
+
+		lat_info = &iolat->child_lat;
+		spin_lock(&lat_info->lock);
+		atomic_set(&lat_info->scale_cookie, DEFAULT_SCALE_COOKIE);
+		lat_info->last_scale_event = 0;
+		lat_info->scale_grp = NULL;
+		lat_info->scale_lat = 0;
+		spin_unlock(&lat_info->lock);
+	}
+}
+
+static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
+			     size_t nbytes, loff_t off)
+{
+	struct blkcg *blkcg = css_to_blkcg(of_css(of));
+	struct blkcg_gq *blkg;
+	struct blk_iolatency *blkiolat;
+	struct blkg_conf_ctx ctx;
+	struct iolatency_grp *iolat;
+	char *p, *tok;
+	u64 lat_val = 0;
+	u64 oldval;
+	int ret;
+
+	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
+	if (ret)
+		return ret;
+
+	iolat = blkg_to_lat(ctx.blkg);
+	blkiolat = iolat->blkiolat;
+	p = ctx.body;
+
+	ret = -EINVAL;
+	while ((tok = strsep(&p, " "))) {
+		char key[16];
+		char val[21];	/* 18446744073709551616 */
+
+		if (sscanf(tok, "%15[^=]=%20s", key, val) != 2)
+			goto out;
+
+		if (!strcmp(key, "target")) {
+			u64 v;
+
+			if (!strcmp(val, "max"))
+				lat_val = 0;
+			else if (sscanf(val, "%llu", &v) == 1)
+				lat_val = v * NSEC_PER_USEC;
+			else
+				goto out;
+		} else {
+			goto out;
+		}
+	}
+
+	/* Walk up the tree to see if our new val is lower than it should be. */
+	blkg = ctx.blkg;
+	oldval = iolat->min_lat_nsec;
+
+	iolatency_set_min_lat_nsec(blkg, lat_val);
+	if (oldval != iolat->min_lat_nsec) {
+		iolatency_clear_scaling(blkg);
+	}
+
+	ret = 0;
+out:
+	blkg_conf_finish(&ctx);
+	return ret ?: nbytes;
+}
+
+static u64 iolatency_prfill_limit(struct seq_file *sf,
+				  struct blkg_policy_data *pd, int off)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	const char *dname = blkg_dev_name(pd->blkg);
+
+	if (!dname || !iolat->min_lat_nsec)
+		return 0;
+	seq_printf(sf, "%s target=%llu\n",
+		   dname,
+		   (unsigned long long)iolat->min_lat_nsec / NSEC_PER_USEC);
+	return 0;
+}
+
+static int iolatency_print_limit(struct seq_file *sf, void *v)
+{
+	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
+			  iolatency_prfill_limit,
+			  &blkcg_policy_iolatency, seq_cft(sf)->private, false);
+	return 0;
+}
+
+static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
+				size_t size)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	unsigned long long avg_lat = div64_u64(iolat->total_lat_avg, NSEC_PER_USEC);
+
+	if (iolat->rq_depth.max_depth == (u64)-1)
+		return scnprintf(buf, size, " depth=max avg_lat=%llu",
+				 avg_lat);
+
+	return scnprintf(buf, size, " depth=%u avg_lat=%llu",
+			 iolat->rq_depth.max_depth, avg_lat);
+}
+
+
+static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node)
+{
+	struct iolatency_grp *iolat;
+
+	iolat = kzalloc_node(sizeof(*iolat), gfp, node);
+	if (!iolat)
+		return NULL;
+	iolat->stats = __alloc_percpu_gfp(sizeof(struct blk_rq_stat),
+				       __alignof__(struct blk_rq_stat), gfp);
+	if (!iolat->stats) {
+		kfree(iolat);
+		return NULL;
+	}
+	return &iolat->pd;
+}
+
+static void iolatency_pd_init(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
+	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
+	u64 now = ktime_to_ns(ktime_get());
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct blk_rq_stat *stat;
+		stat = per_cpu_ptr(iolat->stats, cpu);
+		blk_rq_stat_init(stat);
+	}
+
+	rq_wait_init(&iolat->rq_wait);
+	spin_lock_init(&iolat->child_lat.lock);
+	iolat->rq_depth.queue_depth = blk_queue_depth(blkg->q);
+	iolat->rq_depth.max_depth = INT_MAX;
+	iolat->rq_depth.default_depth = iolat->rq_depth.queue_depth;
+	iolat->blkiolat = blkiolat;
+	iolat->cur_win_nsec = 100 * NSEC_PER_MSEC;
+	atomic64_set(&iolat->window_start, now);
+
+	/*
+	 * We init things in list order, so the pd for the parent may not be
+	 * init'ed yet for whatever reason.
+	 */
+	if (blkg->parent && blkg_to_pd(blkg->parent, &blkcg_policy_iolatency)) {
+		struct iolatency_grp *parent = blkg_to_lat(blkg->parent);
+		atomic_set(&iolat->scale_cookie,
+			   atomic_read(&parent->child_lat.scale_cookie));
+	} else {
+		atomic_set(&iolat->scale_cookie, DEFAULT_SCALE_COOKIE);
+	}
+
+	atomic_set(&iolat->child_lat.scale_cookie, DEFAULT_SCALE_COOKIE);
+}
+
+static void iolatency_pd_offline(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	struct blkcg_gq *blkg = lat_to_blkg(iolat);
+
+	iolatency_set_min_lat_nsec(blkg, 0);
+	iolatency_clear_scaling(blkg);
+}
+
+static void iolatency_pd_free(struct blkg_policy_data *pd)
+{
+	struct iolatency_grp *iolat = pd_to_lat(pd);
+	free_percpu(iolat->stats);
+	kfree(iolat);
+}
+
+static struct cftype iolatency_files[] = {
+	{
+		.name = "latency",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.seq_show = iolatency_print_limit,
+		.write = iolatency_set_limit,
+	},
+	{}
+};
+
+static struct blkcg_policy blkcg_policy_iolatency = {
+	.dfl_cftypes	= iolatency_files,
+	.pd_alloc_fn	= iolatency_pd_alloc,
+	.pd_init_fn	= iolatency_pd_init,
+	.pd_offline_fn	= iolatency_pd_offline,
+	.pd_free_fn	= iolatency_pd_free,
+	.pd_stat_fn	= iolatency_pd_stat,
+};
+
+static int __init iolatency_init(void)
+{
+	return blkcg_policy_register(&blkcg_policy_iolatency);
+}
+
+static void __exit iolatency_exit(void)
+{
+	return blkcg_policy_unregister(&blkcg_policy_iolatency);
+}
+
+module_init(iolatency_init);
+module_exit(iolatency_exit);
diff --git a/block/blk.h b/block/blk.h
index 8d23aea96ce9..69b14cd2bb22 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -412,4 +412,10 @@ static inline void blk_queue_bounce(struct request_queue *q, struct bio **bio)
 
 extern void blk_drain_queue(struct request_queue *q);
 
+#ifdef CONFIG_BLK_CGROUP_IOLATENCY
+extern int blk_iolatency_init(struct request_queue *q);
+#else
+static inline int blk_iolatency_init(struct request_queue *q) { return 0; }
+#endif
+
 #endif /* BLK_INTERNAL_H */
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 0ffc34c5cc83..e13449a379a1 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -180,9 +180,7 @@ struct bio {
 	struct io_context	*bi_ioc;
 	struct cgroup_subsys_state *bi_css;
 	struct blkcg_gq		*bi_blkg;
-#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
 	struct bio_issue	bi_issue;
-#endif
 #endif
 	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
-- 
cgit v1.2.3


From b351f0c76c3eb94c9ccfb68d0b23899a35e47f27 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:15:02 -0400
Subject: Documentation: add a doc for blk-iolatency

A basic documentation to describe the interface, statistics, and
behavior of io.latency.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/admin-guide/cgroup-v2.rst | 79 +++++++++++++++++++++++++++++++++
 1 file changed, 79 insertions(+)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 8a2c52d5c53b..569ce27b85e5 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -51,6 +51,9 @@ v1 is available under Documentation/cgroup-v1/.
      5-3. IO
        5-3-1. IO Interface Files
        5-3-2. Writeback
+       5-3-3. IO Latency
+         5-3-3-1. How IO Latency Throttling Works
+         5-3-3-2. IO Latency Interface Files
      5-4. PID
        5-4-1. PID Interface Files
      5-5. Device
@@ -1446,6 +1449,82 @@ writeback as follows.
 	vm.dirty[_background]_ratio.
 
 
+IO Latency
+~~~~~~~~~~
+
+This is a cgroup v2 controller for IO workload protection.  You provide a group
+with a latency target, and if the average latency exceeds that target the
+controller will throttle any peers that have a lower latency target than the
+protected workload.
+
+The limits are only applied at the peer level in the hierarchy.  This means that
+in the diagram below, only groups A, B, and C will influence each other, and
+groups D and F will influence each other.  Group G will influence nobody.
+
+			[root]
+		/	   |		\
+		A	   B		C
+	       /  \        |
+	      D    F	   G
+
+
+So the ideal way to configure this is to set io.latency in groups A, B, and C.
+Generally you do not want to set a value lower than the latency your device
+supports.  Experiment to find the value that works best for your workload.
+Start at higher than the expected latency for your device and watch the
+total_lat_avg value in io.stat for your workload group to get an idea of the
+latency you see during normal operation.  Use this value as a basis for your
+real setting, setting at 10-15% higher than the value in io.stat.
+Experimentation is key here because total_lat_avg is a running total, so is the
+"statistics" portion of "lies, damned lies, and statistics."
+
+How IO Latency Throttling Works
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+io.latency is work conserving; so as long as everybody is meeting their latency
+target the controller doesn't do anything.  Once a group starts missing its
+target it begins throttling any peer group that has a higher target than itself.
+This throttling takes 2 forms:
+
+- Queue depth throttling.  This is the number of outstanding IO's a group is
+  allowed to have.  We will clamp down relatively quickly, starting at no limit
+  and going all the way down to 1 IO at a time.
+
+- Artificial delay induction.  There are certain types of IO that cannot be
+  throttled without possibly adversely affecting higher priority groups.  This
+  includes swapping and metadata IO.  These types of IO are allowed to occur
+  normally, however they are "charged" to the originating group.  If the
+  originating group is being throttled you will see the use_delay and delay
+  fields in io.stat increase.  The delay value is how many microseconds that are
+  being added to any process that runs in this group.  Because this number can
+  grow quite large if there is a lot of swapping or metadata IO occurring we
+  limit the individual delay events to 1 second at a time.
+
+Once the victimized group starts meeting its latency target again it will start
+unthrottling any peer groups that were throttled previously.  If the victimized
+group simply stops doing IO the global counter will unthrottle appropriately.
+
+IO Latency Interface Files
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+  io.latency
+	This takes a similar format as the other controllers.
+
+		"MAJOR:MINOR target=<target time in microseconds"
+
+  io.stat
+	If the controller is enabled you will see extra stats in io.stat in
+	addition to the normal ones.
+
+	  depth
+		This is the current queue depth for the group.
+
+	  avg_lat
+		The running average IO latency for this group in microseconds.
+		Running average is generally flawed, but will give an
+		administrator a general idea of the overall latency they can
+		expect for their workload on the given disk.
+
 PID
 ---
 
-- 
cgit v1.2.3


From ca47e8c72ae141587cabf3dab693f6754d8c416b Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Tue, 3 Jul 2018 11:15:03 -0400
Subject: mm: skip readahead if the cgroup is congested

We noticed in testing we'd get pretty bad latency stalls under heavy
pressure because read ahead would try to do its thing while the cgroup
was under severe pressure.  If we're under this much pressure we want to
do as little IO as possible so we can still make progress on real work
if we're a throttled cgroup, so just skip readahead if our group is
under pressure.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 mm/readahead.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/mm/readahead.c b/mm/readahead.c
index e273f0de3376..9f62b7151100 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -19,6 +19,7 @@
 #include <linux/syscalls.h>
 #include <linux/file.h>
 #include <linux/mm_inline.h>
+#include <linux/blk-cgroup.h>
 
 #include "internal.h"
 
@@ -505,6 +506,9 @@ void page_cache_sync_readahead(struct address_space *mapping,
 	if (!ra->ra_pages)
 		return;
 
+	if (blk_cgroup_congested())
+		return;
+
 	/* be dumb */
 	if (filp && (filp->f_mode & FMODE_RANDOM)) {
 		force_page_cache_readahead(mapping, filp, offset, req_size);
@@ -555,6 +559,9 @@ page_cache_async_readahead(struct address_space *mapping,
 	if (inode_read_congested(mapping->host))
 		return;
 
+	if (blk_cgroup_congested())
+		return;
+
 	/* do read-ahead */
 	ondemand_readahead(mapping, ra, filp, true, offset, req_size);
 }
-- 
cgit v1.2.3


From 00a8cdb84fcb64c7f9f1061298ff676a96dfaf41 Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.liu@linux.alibaba.com>
Date: Fri, 6 Jul 2018 03:07:13 +0800
Subject: null_blk: remove NULLB_DEV_FL_CONFIGURED on turning off nullb device

Currently mbps knob could only be set once before switching power knob to
on, after power knob has been set at least once, there is no way to set
mbps knob again due to -EBUSY.

As nullb is mainly used for testing, in order to make it flexible, this
removes the flag NULLB_DEV_FL_CONFIGURED so that mbps knob can be reset
when power knob is off, e.g.

echo 0 > /config/nullb/a/power
echo 40 > /config/nullb/a/mbps
echo 1 > /config/nullb/a/power

So does other knobs under /config/nullb/a.

Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 042c778e5a4e..8abfb1059909 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -390,6 +390,7 @@ static ssize_t nullb_device_power_store(struct config_item *item,
 		null_del_dev(dev->nullb);
 		mutex_unlock(&lock);
 		clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
 	}
 
 	return count;
-- 
cgit v1.2.3


From c137969bd4c5b2a67803d10518e3d60d3b13d0cb Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeelb@google.com>
Date: Tue, 3 Jul 2018 10:14:46 -0700
Subject: block, mm: remove unnecessary __GFP_HIGH flag

The flag GFP_ATOMIC already contains __GFP_HIGH. There is no need to
explicitly or __GFP_HIGH again. So, just remove unnecessary __GFP_HIGH.

Signed-off-by: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-ioc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index f23311e4b201..01580f88fcb3 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -278,7 +278,7 @@ int create_task_io_context(struct task_struct *task, gfp_t gfp_flags, int node)
 	atomic_set(&ioc->nr_tasks, 1);
 	atomic_set(&ioc->active_ref, 1);
 	spin_lock_init(&ioc->lock);
-	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC | __GFP_HIGH);
+	INIT_RADIX_TREE(&ioc->icq_tree, GFP_ATOMIC);
 	INIT_HLIST_HEAD(&ioc->icq_list);
 	INIT_WORK(&ioc->release_work, ioc_release_fn);
 
-- 
cgit v1.2.3


From b88aef36b87c9787a4db724923ec4f57dfd513f3 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Tue, 3 Jul 2018 13:34:22 -0400
Subject: block: fix infinite loop if the device loses discard capability

If __blkdev_issue_discard is in progress and a device mapper device is
reloaded with a table that doesn't support discard,
q->limits.max_discard_sectors is set to zero. This results in infinite
loop in __blkdev_issue_discard.

This patch checks if max_discard_sectors is zero and aborts with
-EOPNOTSUPP.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Tested-by: Zdenek Kabelac <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-lib.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/block/blk-lib.c b/block/blk-lib.c
index 8faa70f26fcd..d1b9dd03da25 100644
--- a/block/blk-lib.c
+++ b/block/blk-lib.c
@@ -68,6 +68,8 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 		 */
 		req_sects = min_t(sector_t, nr_sects,
 					q->limits.max_discard_sectors);
+		if (!req_sects)
+			goto fail;
 		if (req_sects > UINT_MAX >> 9)
 			req_sects = UINT_MAX >> 9;
 
@@ -105,6 +107,14 @@ int __blkdev_issue_discard(struct block_device *bdev, sector_t sector,
 
 	*biop = bio;
 	return 0;
+
+fail:
+	if (bio) {
+		submit_bio_wait(bio);
+		bio_put(bio);
+	}
+	*biop = NULL;
+	return -EOPNOTSUPP;
 }
 EXPORT_SYMBOL(__blkdev_issue_discard);
 
-- 
cgit v1.2.3


From e9a83853302b339e63dea4072f6210e5a88ab4bb Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 6 Jul 2018 10:49:35 +0200
Subject: block: Add default switch case to blk_pm_allow_request() to kill
 warning

With gcc 4.9.0 and 7.3.0:

    block/blk-core.c: In function 'blk_pm_allow_request':
    block/blk-core.c:2747:2: warning: enumeration value 'RPM_ACTIVE' not handled in switch [-Wswitch]
      switch (rq->q->rpm_status) {
      ^

Convert the return statement below the switch() block into a default
case to fix this.

Fixes: e4f36b249b4d4e75 ("block: fix peeking requests during PM")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 687d7732f23a..c4b57d8806fe 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2753,9 +2753,9 @@ static bool blk_pm_allow_request(struct request *rq)
 		return rq->rq_flags & RQF_PM;
 	case RPM_SUSPENDED:
 		return false;
+	default:
+		return true;
 	}
-
-	return true;
 }
 #else
 static bool blk_pm_allow_request(struct request *rq)
-- 
cgit v1.2.3


From 6dad38d38f20c0c8a84b5ae4f23c62b2c8758ec5 Mon Sep 17 00:00:00 2001
From: Matias Bjørling <matias.bjorling@wdc.com>
Date: Fri, 6 Jul 2018 19:38:38 +0200
Subject: null_blk: move shared definitions to header file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Split the null_blk device driver, such that it can prepare for
zoned block interface support.

Signed-off-by: Matias Bjørling <matias.bjorling@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk.c | 76 +--------------------------------------------
 drivers/block/null_blk.h | 80 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 81 insertions(+), 75 deletions(-)
 create mode 100644 drivers/block/null_blk.h

diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 8abfb1059909..47dd08499145 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -7,14 +7,8 @@
 #include <linux/moduleparam.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
-#include <linux/blkdev.h>
 #include <linux/init.h>
-#include <linux/slab.h>
-#include <linux/blk-mq.h>
-#include <linux/hrtimer.h>
-#include <linux/configfs.h>
-#include <linux/badblocks.h>
-#include <linux/fault-inject.h>
+#include "null_blk.h"
 
 #define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
 #define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
@@ -35,28 +29,6 @@ static inline u64 mb_per_tick(int mbps)
 	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
 }
 
-struct nullb_cmd {
-	struct list_head list;
-	struct llist_node ll_list;
-	struct __call_single_data csd;
-	struct request *rq;
-	struct bio *bio;
-	unsigned int tag;
-	blk_status_t error;
-	struct nullb_queue *nq;
-	struct hrtimer timer;
-};
-
-struct nullb_queue {
-	unsigned long *tag_map;
-	wait_queue_head_t wait;
-	unsigned int queue_depth;
-	struct nullb_device *dev;
-	unsigned int requeue_selection;
-
-	struct nullb_cmd *cmds;
-};
-
 /*
  * Status flags for nullb_device.
  *
@@ -92,52 +64,6 @@ struct nullb_page {
 #define NULLB_PAGE_LOCK (MAP_SZ - 1)
 #define NULLB_PAGE_FREE (MAP_SZ - 2)
 
-struct nullb_device {
-	struct nullb *nullb;
-	struct config_item item;
-	struct radix_tree_root data; /* data stored in the disk */
-	struct radix_tree_root cache; /* disk cache data */
-	unsigned long flags; /* device flags */
-	unsigned int curr_cache;
-	struct badblocks badblocks;
-
-	unsigned long size; /* device size in MB */
-	unsigned long completion_nsec; /* time in ns to complete a request */
-	unsigned long cache_size; /* disk cache size in MB */
-	unsigned int submit_queues; /* number of submission queues */
-	unsigned int home_node; /* home node for the device */
-	unsigned int queue_mode; /* block interface */
-	unsigned int blocksize; /* block size */
-	unsigned int irqmode; /* IRQ completion handler */
-	unsigned int hw_queue_depth; /* queue depth */
-	unsigned int index; /* index of the disk, only valid with a disk */
-	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
-	bool blocking; /* blocking blk-mq device */
-	bool use_per_node_hctx; /* use per-node allocation for hardware context */
-	bool power; /* power on/off the device */
-	bool memory_backed; /* if data is stored in memory */
-	bool discard; /* if support discard */
-};
-
-struct nullb {
-	struct nullb_device *dev;
-	struct list_head list;
-	unsigned int index;
-	struct request_queue *q;
-	struct gendisk *disk;
-	struct blk_mq_tag_set *tag_set;
-	struct blk_mq_tag_set __tag_set;
-	unsigned int queue_depth;
-	atomic_long_t cur_bytes;
-	struct hrtimer bw_timer;
-	unsigned long cache_flush_pos;
-	spinlock_t lock;
-
-	struct nullb_queue *queues;
-	unsigned int nr_queues;
-	char disk_name[DISK_NAME_LEN];
-};
-
 static LIST_HEAD(nullb_list);
 static struct mutex lock;
 static int null_major;
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
new file mode 100644
index 000000000000..d82c5501806d
--- /dev/null
+++ b/drivers/block/null_blk.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __BLK_NULL_BLK_H
+#define __BLK_NULL_BLK_H
+
+#include <linux/blkdev.h>
+#include <linux/slab.h>
+#include <linux/blk-mq.h>
+#include <linux/hrtimer.h>
+#include <linux/configfs.h>
+#include <linux/badblocks.h>
+#include <linux/fault-inject.h>
+
+struct nullb_cmd {
+	struct list_head list;
+	struct llist_node ll_list;
+	struct __call_single_data csd;
+	struct request *rq;
+	struct bio *bio;
+	unsigned int tag;
+	blk_status_t error;
+	struct nullb_queue *nq;
+	struct hrtimer timer;
+};
+
+struct nullb_queue {
+	unsigned long *tag_map;
+	wait_queue_head_t wait;
+	unsigned int queue_depth;
+	struct nullb_device *dev;
+	unsigned int requeue_selection;
+
+	struct nullb_cmd *cmds;
+};
+
+struct nullb_device {
+	struct nullb *nullb;
+	struct config_item item;
+	struct radix_tree_root data; /* data stored in the disk */
+	struct radix_tree_root cache; /* disk cache data */
+	unsigned long flags; /* device flags */
+	unsigned int curr_cache;
+	struct badblocks badblocks;
+
+	unsigned long size; /* device size in MB */
+	unsigned long completion_nsec; /* time in ns to complete a request */
+	unsigned long cache_size; /* disk cache size in MB */
+	unsigned int submit_queues; /* number of submission queues */
+	unsigned int home_node; /* home node for the device */
+	unsigned int queue_mode; /* block interface */
+	unsigned int blocksize; /* block size */
+	unsigned int irqmode; /* IRQ completion handler */
+	unsigned int hw_queue_depth; /* queue depth */
+	unsigned int index; /* index of the disk, only valid with a disk */
+	unsigned int mbps; /* Bandwidth throttle cap (in MB/s) */
+	bool blocking; /* blocking blk-mq device */
+	bool use_per_node_hctx; /* use per-node allocation for hardware context */
+	bool power; /* power on/off the device */
+	bool memory_backed; /* if data is stored in memory */
+	bool discard; /* if support discard */
+};
+
+struct nullb {
+	struct nullb_device *dev;
+	struct list_head list;
+	unsigned int index;
+	struct request_queue *q;
+	struct gendisk *disk;
+	struct blk_mq_tag_set *tag_set;
+	struct blk_mq_tag_set __tag_set;
+	unsigned int queue_depth;
+	atomic_long_t cur_bytes;
+	struct hrtimer bw_timer;
+	unsigned long cache_flush_pos;
+	spinlock_t lock;
+
+	struct nullb_queue *queues;
+	unsigned int nr_queues;
+	char disk_name[DISK_NAME_LEN];
+};
+#endif /* __NULL_BLK_H */
-- 
cgit v1.2.3


From ca4b2a011948fae4e4d31490107db4926385a983 Mon Sep 17 00:00:00 2001
From: Matias Bjørling <matias.bjorling@wdc.com>
Date: Fri, 6 Jul 2018 19:38:39 +0200
Subject: null_blk: add zone support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Adds support for exposing a null_blk device through the zone device
interface.

The interface is managed with the parameters zoned and zone_size.
If zoned is set, the null_blk instance registers as a zoned block
device. The zone_size parameter defines how big each zone will be.

Signed-off-by: Matias Bjørling <matias.bjorling@wdc.com>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/block/null_blk.txt |   7 ++
 drivers/block/Makefile           |   5 +-
 drivers/block/null_blk.c         |  48 ++++++++++++-
 drivers/block/null_blk.h         |  28 ++++++++
 drivers/block/null_blk_zoned.c   | 149 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 234 insertions(+), 3 deletions(-)
 create mode 100644 drivers/block/null_blk_zoned.c

diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt
index 07f147381f32..ea2dafe49ae8 100644
--- a/Documentation/block/null_blk.txt
+++ b/Documentation/block/null_blk.txt
@@ -85,3 +85,10 @@ shared_tags=[0/1]: Default: 0
   0: Tag set is not shared.
   1: Tag set shared between devices for blk-mq. Only makes sense with
      nr_devices > 1, otherwise there's no tag set to share.
+
+zoned=[0/1]: Default: 0
+  0: Block device is exposed as a random-access block device.
+  1: Block device is exposed as a host-managed zoned block device.
+
+zone_size=[MB]: Default: 256
+  Per zone size when exposed as a zoned block device. Must be a power of two.
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index dc061158b403..a0d88aa0c05d 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -36,8 +36,11 @@ obj-$(CONFIG_BLK_DEV_RBD)     += rbd.o
 obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX)	+= mtip32xx/
 
 obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
-obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
 obj-$(CONFIG_ZRAM) += zram/
 
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk_mod.o
+null_blk_mod-objs	:= null_blk.o
+null_blk_mod-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
+
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 47dd08499145..86cafa6d3b41 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -180,6 +180,14 @@ static bool g_use_per_node_hctx;
 module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
 MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
 
+static bool g_zoned;
+module_param_named(zoned, g_zoned, bool, S_IRUGO);
+MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
+
+static unsigned long g_zone_size = 256;
+module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
+MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
+
 static struct nullb_device *null_alloc_dev(void);
 static void null_free_dev(struct nullb_device *dev);
 static void null_del_dev(struct nullb *nullb);
@@ -283,6 +291,8 @@ NULLB_DEVICE_ATTR(memory_backed, bool);
 NULLB_DEVICE_ATTR(discard, bool);
 NULLB_DEVICE_ATTR(mbps, uint);
 NULLB_DEVICE_ATTR(cache_size, ulong);
+NULLB_DEVICE_ATTR(zoned, bool);
+NULLB_DEVICE_ATTR(zone_size, ulong);
 
 static ssize_t nullb_device_power_show(struct config_item *item, char *page)
 {
@@ -395,6 +405,8 @@ static struct configfs_attribute *nullb_device_attrs[] = {
 	&nullb_device_attr_mbps,
 	&nullb_device_attr_cache_size,
 	&nullb_device_attr_badblocks,
+	&nullb_device_attr_zoned,
+	&nullb_device_attr_zone_size,
 	NULL,
 };
 
@@ -447,7 +459,7 @@ nullb_group_drop_item(struct config_group *group, struct config_item *item)
 
 static ssize_t memb_group_features_show(struct config_item *item, char *page)
 {
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks\n");
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
 }
 
 CONFIGFS_ATTR_RO(memb_group_, features);
@@ -506,6 +518,8 @@ static struct nullb_device *null_alloc_dev(void)
 	dev->hw_queue_depth = g_hw_queue_depth;
 	dev->blocking = g_blocking;
 	dev->use_per_node_hctx = g_use_per_node_hctx;
+	dev->zoned = g_zoned;
+	dev->zone_size = g_zone_size;
 	return dev;
 }
 
@@ -514,6 +528,7 @@ static void null_free_dev(struct nullb_device *dev)
 	if (!dev)
 		return;
 
+	null_zone_exit(dev);
 	badblocks_exit(&dev->badblocks);
 	kfree(dev);
 }
@@ -1146,6 +1161,11 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 	struct nullb *nullb = dev->nullb;
 	int err = 0;
 
+	if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
+		cmd->error = null_zone_report(nullb, cmd);
+		goto out;
+	}
+
 	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
 		struct request *rq = cmd->rq;
 
@@ -1210,6 +1230,13 @@ static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
 		}
 	}
 	cmd->error = errno_to_blk_status(err);
+
+	if (!cmd->error && dev->zoned) {
+		if (req_op(cmd->rq) == REQ_OP_WRITE)
+			null_zone_write(cmd);
+		else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET)
+			null_zone_reset(cmd);
+	}
 out:
 	/* Complete IO by inline, softirq or timer */
 	switch (dev->irqmode) {
@@ -1737,6 +1764,15 @@ static int null_add_dev(struct nullb_device *dev)
 		blk_queue_flush_queueable(nullb->q, true);
 	}
 
+	if (dev->zoned) {
+		rv = null_zone_init(dev);
+		if (rv)
+			goto out_cleanup_blk_queue;
+
+		blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
+		nullb->q->limits.zoned = BLK_ZONED_HM;
+	}
+
 	nullb->q->queuedata = nullb;
 	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
 	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
@@ -1755,13 +1791,16 @@ static int null_add_dev(struct nullb_device *dev)
 
 	rv = null_gendisk_register(nullb);
 	if (rv)
-		goto out_cleanup_blk_queue;
+		goto out_cleanup_zone;
 
 	mutex_lock(&lock);
 	list_add_tail(&nullb->list, &nullb_list);
 	mutex_unlock(&lock);
 
 	return 0;
+out_cleanup_zone:
+	if (dev->zoned)
+		null_zone_exit(dev);
 out_cleanup_blk_queue:
 	blk_cleanup_queue(nullb->q);
 out_cleanup_tags:
@@ -1788,6 +1827,11 @@ static int __init null_init(void)
 		g_bs = PAGE_SIZE;
 	}
 
+	if (!is_power_of_2(g_zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
 	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
 		if (g_submit_queues != nr_online_nodes) {
 			pr_warn("null_blk: submit_queues param is set to %u.\n",
diff --git a/drivers/block/null_blk.h b/drivers/block/null_blk.h
index d82c5501806d..d81781f22dba 100644
--- a/drivers/block/null_blk.h
+++ b/drivers/block/null_blk.h
@@ -41,9 +41,14 @@ struct nullb_device {
 	unsigned int curr_cache;
 	struct badblocks badblocks;
 
+	unsigned int nr_zones;
+	struct blk_zone *zones;
+	sector_t zone_size_sects;
+
 	unsigned long size; /* device size in MB */
 	unsigned long completion_nsec; /* time in ns to complete a request */
 	unsigned long cache_size; /* disk cache size in MB */
+	unsigned long zone_size; /* zone size in MB if device is zoned */
 	unsigned int submit_queues; /* number of submission queues */
 	unsigned int home_node; /* home node for the device */
 	unsigned int queue_mode; /* block interface */
@@ -57,6 +62,7 @@ struct nullb_device {
 	bool power; /* power on/off the device */
 	bool memory_backed; /* if data is stored in memory */
 	bool discard; /* if support discard */
+	bool zoned; /* if device is zoned */
 };
 
 struct nullb {
@@ -77,4 +83,26 @@ struct nullb {
 	unsigned int nr_queues;
 	char disk_name[DISK_NAME_LEN];
 };
+
+#ifdef CONFIG_BLK_DEV_ZONED
+int null_zone_init(struct nullb_device *dev);
+void null_zone_exit(struct nullb_device *dev);
+blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd);
+void null_zone_write(struct nullb_cmd *cmd);
+void null_zone_reset(struct nullb_cmd *cmd);
+#else
+static inline int null_zone_init(struct nullb_device *dev)
+{
+	return -EINVAL;
+}
+static inline void null_zone_exit(struct nullb_device *dev) {}
+static inline blk_status_t null_zone_report(struct nullb *nullb,
+					    struct nullb_cmd *cmd)
+{
+	return BLK_STS_NOTSUPP;
+}
+static inline void null_zone_write(struct nullb_cmd *cmd) {}
+static inline void null_zone_reset(struct nullb_cmd *cmd) {}
+#endif /* CONFIG_BLK_DEV_ZONED */
 #endif /* __NULL_BLK_H */
diff --git a/drivers/block/null_blk_zoned.c b/drivers/block/null_blk_zoned.c
new file mode 100644
index 000000000000..a979ca00d7be
--- /dev/null
+++ b/drivers/block/null_blk_zoned.c
@@ -0,0 +1,149 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/vmalloc.h>
+#include "null_blk.h"
+
+/* zone_size in MBs to sectors. */
+#define ZONE_SIZE_SHIFT		11
+
+static inline unsigned int null_zone_no(struct nullb_device *dev, sector_t sect)
+{
+	return sect >> ilog2(dev->zone_size_sects);
+}
+
+int null_zone_init(struct nullb_device *dev)
+{
+	sector_t dev_size = (sector_t)dev->size * 1024 * 1024;
+	sector_t sector = 0;
+	unsigned int i;
+
+	if (!is_power_of_2(dev->zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
+	dev->zone_size_sects = dev->zone_size << ZONE_SIZE_SHIFT;
+	dev->nr_zones = dev_size >>
+				(SECTOR_SHIFT + ilog2(dev->zone_size_sects));
+	dev->zones = kvmalloc_array(dev->nr_zones, sizeof(struct blk_zone),
+			GFP_KERNEL | __GFP_ZERO);
+	if (!dev->zones)
+		return -ENOMEM;
+
+	for (i = 0; i < dev->nr_zones; i++) {
+		struct blk_zone *zone = &dev->zones[i];
+
+		zone->start = zone->wp = sector;
+		zone->len = dev->zone_size_sects;
+		zone->type = BLK_ZONE_TYPE_SEQWRITE_REQ;
+		zone->cond = BLK_ZONE_COND_EMPTY;
+
+		sector += dev->zone_size_sects;
+	}
+
+	return 0;
+}
+
+void null_zone_exit(struct nullb_device *dev)
+{
+	kvfree(dev->zones);
+}
+
+static void null_zone_fill_rq(struct nullb_device *dev, struct request *rq,
+			      unsigned int zno, unsigned int nr_zones)
+{
+	struct blk_zone_report_hdr *hdr = NULL;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+	void *addr;
+	unsigned int zones_to_cpy;
+
+	bio_for_each_segment(bvec, rq->bio, iter) {
+		addr = kmap_atomic(bvec.bv_page);
+
+		zones_to_cpy = bvec.bv_len / sizeof(struct blk_zone);
+
+		if (!hdr) {
+			hdr = (struct blk_zone_report_hdr *)addr;
+			hdr->nr_zones = nr_zones;
+			zones_to_cpy--;
+			addr += sizeof(struct blk_zone_report_hdr);
+		}
+
+		zones_to_cpy = min_t(unsigned int, zones_to_cpy, nr_zones);
+
+		memcpy(addr, &dev->zones[zno],
+				zones_to_cpy * sizeof(struct blk_zone));
+
+		kunmap_atomic(addr);
+
+		nr_zones -= zones_to_cpy;
+		zno += zones_to_cpy;
+
+		if (!nr_zones)
+			break;
+	}
+}
+
+blk_status_t null_zone_report(struct nullb *nullb,
+				     struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = nullb->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	unsigned int nr_zones = dev->nr_zones - zno;
+	unsigned int max_zones = (blk_rq_bytes(rq) /
+					sizeof(struct blk_zone)) - 1;
+
+	nr_zones = min_t(unsigned int, nr_zones, max_zones);
+
+	null_zone_fill_rq(nullb->dev, rq, zno, nr_zones);
+
+	return BLK_STS_OK;
+}
+
+void null_zone_write(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	sector_t sector = blk_rq_pos(rq);
+	unsigned int rq_sectors = blk_rq_sectors(rq);
+	unsigned int zno = null_zone_no(dev, sector);
+	struct blk_zone *zone = &dev->zones[zno];
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_FULL:
+		/* Cannot write to a full zone */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	case BLK_ZONE_COND_EMPTY:
+	case BLK_ZONE_COND_IMP_OPEN:
+		/* Writes must be at the write pointer position */
+		if (blk_rq_pos(rq) != zone->wp) {
+			cmd->error = BLK_STS_IOERR;
+			break;
+		}
+
+		if (zone->cond == BLK_ZONE_COND_EMPTY)
+			zone->cond = BLK_ZONE_COND_IMP_OPEN;
+
+		zone->wp += rq_sectors;
+		if (zone->wp == zone->start + zone->len)
+			zone->cond = BLK_ZONE_COND_FULL;
+		break;
+	default:
+		/* Invalid zone condition */
+		cmd->error = BLK_STS_IOERR;
+		break;
+	}
+}
+
+void null_zone_reset(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct request *rq = cmd->rq;
+	unsigned int zno = null_zone_no(dev, blk_rq_pos(rq));
+	struct blk_zone *zone = &dev->zones[zno];
+
+	zone->cond = BLK_ZONE_COND_EMPTY;
+	zone->wp = zone->start;
+}
-- 
cgit v1.2.3


From 3993e501bf853cce85c5114a704b86b8f486790c Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 6 Jul 2018 20:49:19 -0700
Subject: block/DAC960.c: fix defined but not used build warnings

Fix build warnings in DAC960.c when CONFIG_PROC_FS is not enabled
by marking the unused functions as __maybe_unused.

../drivers/block/DAC960.c:6429:12: warning: 'dac960_proc_show' defined but not used [-Wunused-function]
../drivers/block/DAC960.c:6449:12: warning: 'dac960_initial_status_proc_show' defined but not used [-Wunused-function]
../drivers/block/DAC960.c:6456:12: warning: 'dac960_current_status_proc_show' defined but not used [-Wunused-function]

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/DAC960.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/block/DAC960.c b/drivers/block/DAC960.c
index f6518067aa7d..f99e5c883368 100644
--- a/drivers/block/DAC960.c
+++ b/drivers/block/DAC960.c
@@ -21,6 +21,7 @@
 #define DAC960_DriverDate			"21 Aug 2007"
 
 
+#include <linux/compiler.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/miscdevice.h>
@@ -6426,7 +6427,7 @@ static bool DAC960_V2_ExecuteUserCommand(DAC960_Controller_T *Controller,
   return true;
 }
 
-static int dac960_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_proc_show(struct seq_file *m, void *v)
 {
   unsigned char *StatusMessage = "OK\n";
   int ControllerNumber;
@@ -6446,14 +6447,16 @@ static int dac960_proc_show(struct seq_file *m, void *v)
   return 0;
 }
 
-static int dac960_initial_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_initial_status_proc_show(struct seq_file *m,
+							  void *v)
 {
 	DAC960_Controller_T *Controller = (DAC960_Controller_T *)m->private;
 	seq_printf(m, "%.*s", Controller->InitialStatusLength, Controller->CombinedStatusBuffer);
 	return 0;
 }
 
-static int dac960_current_status_proc_show(struct seq_file *m, void *v)
+static int __maybe_unused dac960_current_status_proc_show(struct seq_file *m,
+							  void *v)
 {
   DAC960_Controller_T *Controller = (DAC960_Controller_T *) m->private;
   unsigned char *StatusMessage =
-- 
cgit v1.2.3


From 66c7bb7c4133c5cc4e9962d5951bf3bd65e29120 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Tue, 19 Jun 2018 14:34:46 +0200
Subject: clk: mvebu: armada-37xx-periph: switch to SPDX license identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/mvebu/armada-37xx-periph.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 6860bd5a37c5..c179eff6a7e9 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Marvell Armada 37xx SoC Peripheral clocks
  *
@@ -5,10 +6,6 @@
  *
  * Gregory CLEMENT <gregory.clement@free-electrons.com>
  *
- * This file is licensed under the terms of the GNU General Public
- * License version 2 or later. This program is licensed "as is"
- * without any warranty of any kind, whether express or implied.
- *
  * Most of the peripheral clocks can be modelled like this:
  *             _____    _______    _______
  * TBG-A-P  --|     |  |       |  |       |   ______
-- 
cgit v1.2.3


From 5ba57babcb40227ceb70d9bc71afa57e004f8417 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 9 Jul 2018 17:48:18 +0200
Subject: drm: vkms: select DRM_KMS_HELPER

Without this, we get link errors during randconfig build:

drivers/gpu/drm/vkms/vkms_drv.o:(.rodata+0xa0): undefined reference to `drm_atomic_helper_check'
drivers/gpu/drm/vkms/vkms_drv.o:(.rodata+0xa8): undefined reference to `drm_atomic_helper_commit'
drivers/gpu/drm/vkms/vkms_plane.o:(.rodata+0x0): undefined reference to `drm_atomic_helper_update_plane'
drivers/gpu/drm/vkms/vkms_plane.o:(.rodata+0x8): undefined reference to `drm_atomic_helper_disable_plane'
drivers/gpu/drm/vkms/vkms_plane.o:(.rodata+0x18): undefined reference to `drm_atomic_helper_plane_reset'
drivers/gpu/drm/vkms/vkms_plane.o:(.rodata+0x28): undefined reference to `drm_atomic_helper_plane_duplicate_state'
drivers/gpu/drm/vkms/vkms_plane.o:(.rodata+0x30): undefined reference to `drm_atomic_helper_plane_destroy_state'
drivers/gpu/drm/vkms/vkms_output.o:(.rodata+0x1c0): undefined reference to `drm_helper_probe_single_connector_modes'
drivers/gpu/drm/vkms/vkms_crtc.o:(.rodata+0x40): undefined reference to `drm_atomic_helper_crtc_reset'
drivers/gpu/drm/vkms/vkms_crtc.o:(.rodata+0x70): undefined reference to `drm_atomic_helper_set_config'
drivers/gpu/drm/vkms/vkms_crtc.o:(.rodata+0x78): undefined reference to `drm_atomic_helper_page_flip'
drivers/gpu/drm/vkms/vkms_crtc.o:(.rodata+0x90): undefined reference to `drm_atomic_helper_crtc_duplicate_state'
drivers/gpu/drm/vkms/vkms_crtc.o:(.rodata+0x98): undefined reference to `drm_atomic_helper_crtc_destroy_state'

Fixes: 854502fa0a38 ("drm/vkms: Add basic CRTC initialization")
Fixes: 1c7c5fd916a0 ("drm/vkms: Introduce basic VKMS driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709154901.1989316-1-arnd@arndb.de
---
 drivers/gpu/drm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index 10f9f01123ea..a8054dde49b5 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -216,6 +216,7 @@ config DRM_VGEM
 config DRM_VKMS
 	tristate "Virtual KMS (EXPERIMENTAL)"
 	depends on DRM
+	select DRM_KMS_HELPER
 	default n
 	help
 	  Virtual Kernel Mode-Setting (VKMS) is used for testing or for
-- 
cgit v1.2.3


From 30343897d8fd84c630ee2c7f5b38c16da2c7ee4b Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 15 Jun 2018 11:51:04 +0200
Subject: clk: imx7d: add IMX7D_MU_ROOT_CLK

This clock is needed for iMX mailbox driver

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Dong Aisheng <aisheng.dong@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx7d.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/imx/clk-imx7d.c b/drivers/clk/imx/clk-imx7d.c
index 27217a7ea17e..881b772c4ac9 100644
--- a/drivers/clk/imx/clk-imx7d.c
+++ b/drivers/clk/imx/clk-imx7d.c
@@ -797,6 +797,7 @@ static void __init imx7d_clocks_init(struct device_node *ccm_node)
 	clks[IMX7D_DRAM_ALT_ROOT_CLK] = imx_clk_gate4("dram_alt_root_clk", "dram_alt_post_div", base + 0x4130, 0);
 	clks[IMX7D_OCOTP_CLK] = imx_clk_gate4("ocotp_clk", "ipg_root_clk", base + 0x4230, 0);
 	clks[IMX7D_SNVS_CLK] = imx_clk_gate4("snvs_clk", "ipg_root_clk", base + 0x4250, 0);
+	clks[IMX7D_MU_ROOT_CLK] = imx_clk_gate4("mu_root_clk", "ipg_root_clk", base + 0x4270, 0);
 	clks[IMX7D_CAAM_CLK] = imx_clk_gate4("caam_clk", "ipg_root_clk", base + 0x4240, 0);
 	clks[IMX7D_USB_HSIC_ROOT_CLK] = imx_clk_gate4("usb_hsic_root_clk", "usb_hsic_post_div", base + 0x4690, 0);
 	clks[IMX7D_SDMA_CORE_CLK] = imx_clk_gate4("sdma_root_clk", "ahb_root_clk", base + 0x4480, 0);
-- 
cgit v1.2.3


From e189624916961c735c18e3c75acc478661403830 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Mon, 25 Jun 2018 14:05:52 +0100
Subject: arm64: numa: rework ACPI NUMA initialization

Current ACPI ARM64 NUMA initialization code in

acpi_numa_gicc_affinity_init()

carries out NUMA nodes creation and cpu<->node mappings at the same time
in the arch backend so that a single SRAT walk is needed to parse both
pieces of information.  This implies that the cpu<->node mappings must
be stashed in an array (sized NR_CPUS) so that SMP code can later use
the stashed values to avoid another SRAT table walk to set-up the early
cpu<->node mappings.

If the kernel is configured with a NR_CPUS value less than the actual
processor entries in the SRAT (and MADT), the logic in
acpi_numa_gicc_affinity_init() is broken in that the cpu<->node mapping
is only carried out (and stashed for future use) only for a number of
SRAT entries up to NR_CPUS, which do not necessarily correspond to the
possible cpus detected at SMP initialization in
acpi_map_gic_cpu_interface() (ie MADT and SRAT processor entries order
is not enforced), which leaves the kernel with broken cpu<->node
mappings.

Furthermore, given the current ACPI NUMA code parsing logic in
acpi_numa_gicc_affinity_init(), PXM domains for CPUs that are not parsed
because they exceed NR_CPUS entries are not mapped to NUMA nodes (ie the
PXM corresponding node is not created in the kernel) leaving the system
with a broken NUMA topology.

Rework the ACPI ARM64 NUMA initialization process so that the NUMA
nodes creation and cpu<->node mappings are decoupled. cpu<->node
mappings are moved to SMP initialization code (where they are needed),
at the cost of an extra SRAT walk so that ACPI NUMA mappings can be
batched before being applied, fixing current parsing pitfalls.

Acked-by: Hanjun Guo <hanjun.guo@linaro.org>
Tested-by: John Garry <john.garry@huawei.com>
Fixes: d8b47fca8c23 ("arm64, ACPI, NUMA: NUMA support based on SRAT and
SLIT")
Link: http://lkml.kernel.org/r/1527768879-88161-2-git-send-email-xiexiuqi@huawei.com
Reported-by: Xie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Punit Agrawal <punit.agrawal@arm.com>
Cc: Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Hanjun Guo <guohanjun@huawei.com>
Cc: Ganapatrao Kulkarni <gkulkarni@caviumnetworks.com>
Cc: Jeremy Linton <jeremy.linton@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Xie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/acpi.h |  6 ++-
 arch/arm64/kernel/acpi_numa.c | 88 ++++++++++++++++++++++++++-----------------
 arch/arm64/kernel/smp.c       | 39 +++++++++++++------
 3 files changed, 85 insertions(+), 48 deletions(-)

diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index 0db62a4cbce2..d1c290f29b6f 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -134,10 +134,12 @@ pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
 
 #ifdef CONFIG_ACPI_NUMA
 int arm64_acpi_numa_init(void);
-int acpi_numa_get_nid(unsigned int cpu, u64 hwid);
+int acpi_numa_get_nid(unsigned int cpu);
+void acpi_map_cpus_to_nodes(void);
 #else
 static inline int arm64_acpi_numa_init(void) { return -ENOSYS; }
-static inline int acpi_numa_get_nid(unsigned int cpu, u64 hwid) { return NUMA_NO_NODE; }
+static inline int acpi_numa_get_nid(unsigned int cpu) { return NUMA_NO_NODE; }
+static inline void acpi_map_cpus_to_nodes(void) { }
 #endif /* CONFIG_ACPI_NUMA */
 
 #define ACPI_TABLE_UPGRADE_MAX_PHYS MEMBLOCK_ALLOC_ACCESSIBLE
diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
index d190a7b231bf..4f4f1815e047 100644
--- a/arch/arm64/kernel/acpi_numa.c
+++ b/arch/arm64/kernel/acpi_numa.c
@@ -26,36 +26,73 @@
 #include <linux/module.h>
 #include <linux/topology.h>
 
-#include <acpi/processor.h>
 #include <asm/numa.h>
 
-static int cpus_in_srat;
+static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE };
 
-struct __node_cpu_hwid {
-	u32 node_id;    /* logical node containing this CPU */
-	u64 cpu_hwid;   /* MPIDR for this CPU */
-};
+int __init acpi_numa_get_nid(unsigned int cpu)
+{
+	return acpi_early_node_map[cpu];
+}
+
+static inline int get_cpu_for_acpi_id(u32 uid)
+{
+	int cpu;
+
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+		if (uid == get_acpi_id_for_cpu(cpu))
+			return cpu;
 
-static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = {
-[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} };
+	return -EINVAL;
+}
 
-int acpi_numa_get_nid(unsigned int cpu, u64 hwid)
+static int __init acpi_parse_gicc_pxm(struct acpi_subtable_header *header,
+				      const unsigned long end)
 {
-	int i;
+	struct acpi_srat_gicc_affinity *pa;
+	int cpu, pxm, node;
 
-	for (i = 0; i < cpus_in_srat; i++) {
-		if (hwid == early_node_cpu_hwid[i].cpu_hwid)
-			return early_node_cpu_hwid[i].node_id;
-	}
+	if (srat_disabled())
+		return -EINVAL;
+
+	pa = (struct acpi_srat_gicc_affinity *)header;
+	if (!pa)
+		return -EINVAL;
+
+	if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
+		return 0;
 
-	return NUMA_NO_NODE;
+	pxm = pa->proximity_domain;
+	node = pxm_to_node(pxm);
+
+	/*
+	 * If we can't map the UID to a logical cpu this
+	 * means that the UID is not part of possible cpus
+	 * so we do not need a NUMA mapping for it, skip
+	 * the SRAT entry and keep parsing.
+	 */
+	cpu = get_cpu_for_acpi_id(pa->acpi_processor_uid);
+	if (cpu < 0)
+		return 0;
+
+	acpi_early_node_map[cpu] = node;
+	pr_info("SRAT: PXM %d -> MPIDR 0x%llx -> Node %d\n", pxm,
+		cpu_logical_map(cpu), node);
+
+	return 0;
+}
+
+void __init acpi_map_cpus_to_nodes(void)
+{
+	acpi_table_parse_entries(ACPI_SIG_SRAT, sizeof(struct acpi_table_srat),
+					    ACPI_SRAT_TYPE_GICC_AFFINITY,
+					    acpi_parse_gicc_pxm, 0);
 }
 
 /* Callback for Proximity Domain -> ACPI processor UID mapping */
 void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
 {
 	int pxm, node;
-	phys_cpuid_t mpidr;
 
 	if (srat_disabled())
 		return;
@@ -70,12 +107,6 @@ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
 	if (!(pa->flags & ACPI_SRAT_GICC_ENABLED))
 		return;
 
-	if (cpus_in_srat >= NR_CPUS) {
-		pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n",
-			     NR_CPUS);
-		return;
-	}
-
 	pxm = pa->proximity_domain;
 	node = acpi_map_pxm_to_node(pxm);
 
@@ -85,20 +116,7 @@ void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa)
 		return;
 	}
 
-	mpidr = acpi_map_madt_entry(pa->acpi_processor_uid);
-	if (mpidr == PHYS_CPUID_INVALID) {
-		pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n",
-			pxm, pa->acpi_processor_uid);
-		bad_srat();
-		return;
-	}
-
-	early_node_cpu_hwid[cpus_in_srat].node_id = node;
-	early_node_cpu_hwid[cpus_in_srat].cpu_hwid =  mpidr;
 	node_set(node, numa_nodes_parsed);
-	cpus_in_srat++;
-	pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n",
-		pxm, mpidr, node);
 }
 
 int __init arm64_acpi_numa_init(void)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index a44cc09059b5..25fcd22a4bb2 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -522,7 +522,6 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 		}
 		bootcpu_valid = true;
 		cpu_madt_gicc[0] = *processor;
-		early_map_cpu_to_node(0, acpi_numa_get_nid(0, hwid));
 		return;
 	}
 
@@ -545,8 +544,6 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor)
 	 */
 	acpi_set_mailbox_entry(cpu_count, processor);
 
-	early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid));
-
 	cpu_count++;
 }
 
@@ -566,8 +563,34 @@ acpi_parse_gic_cpu_interface(struct acpi_subtable_header *header,
 
 	return 0;
 }
+
+static void __init acpi_parse_and_init_cpus(void)
+{
+	int i;
+
+	/*
+	 * do a walk of MADT to determine how many CPUs
+	 * we have including disabled CPUs, and get information
+	 * we need for SMP init.
+	 */
+	acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
+				      acpi_parse_gic_cpu_interface, 0);
+
+	/*
+	 * In ACPI, SMP and CPU NUMA information is provided in separate
+	 * static tables, namely the MADT and the SRAT.
+	 *
+	 * Thus, it is simpler to first create the cpu logical map through
+	 * an MADT walk and then map the logical cpus to their node ids
+	 * as separate steps.
+	 */
+	acpi_map_cpus_to_nodes();
+
+	for (i = 0; i < nr_cpu_ids; i++)
+		early_map_cpu_to_node(i, acpi_numa_get_nid(i));
+}
 #else
-#define acpi_table_parse_madt(...)	do { } while (0)
+#define acpi_parse_and_init_cpus(...)	do { } while (0)
 #endif
 
 /*
@@ -640,13 +663,7 @@ void __init smp_init_cpus(void)
 	if (acpi_disabled)
 		of_parse_and_init_cpus();
 	else
-		/*
-		 * do a walk of MADT to determine how many CPUs
-		 * we have including disabled CPUs, and get information
-		 * we need for SMP init
-		 */
-		acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT,
-				      acpi_parse_gic_cpu_interface, 0);
+		acpi_parse_and_init_cpus();
 
 	if (cpu_count > nr_cpu_ids)
 		pr_warn("Number of cores (%d) exceeds configured maximum of %u - clipping\n",
-- 
cgit v1.2.3


From d7be97756f8a4874ac17003de5843c742dd84153 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 9 Jul 2018 12:19:32 -0400
Subject: net-sysfs: Drop support for XPS and traffic_class on single queue
 device

This patch makes it so that we do not report the traffic class or allow XPS
configuration on single queue devices. This is mostly to avoid unnecessary
complexity with changes I have planned that will allow us to reuse
the unused tc_to_txq and XPS configuration on a single queue device to
allow it to make use of a subset of queues on an underlying device.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 net/core/net-sysfs.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f25ac5ff48a6..dce3ae0fbca2 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1047,9 +1047,14 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 				  char *buf)
 {
 	struct net_device *dev = queue->dev;
-	int index = get_netdev_queue_index(queue);
-	int tc = netdev_txq_to_tc(dev, index);
+	int index;
+	int tc;
 
+	if (!netif_is_multiqueue(dev))
+		return -ENOENT;
+
+	index = get_netdev_queue_index(queue);
+	tc = netdev_txq_to_tc(dev, index);
 	if (tc < 0)
 		return -EINVAL;
 
@@ -1214,6 +1219,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	cpumask_var_t mask;
 	unsigned long index;
 
+	if (!netif_is_multiqueue(dev))
+		return -ENOENT;
+
 	index = get_netdev_queue_index(queue);
 
 	if (dev->num_tc) {
@@ -1260,6 +1268,9 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 	cpumask_var_t mask;
 	int err;
 
+	if (!netif_is_multiqueue(dev))
+		return -ENOENT;
+
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
-- 
cgit v1.2.3


From ffcfe25bb50f27395e15fa999f1a7eb769f55360 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 9 Jul 2018 12:19:38 -0400
Subject: net: Add support for subordinate device traffic classes

This patch is meant to provide the basic tools needed to allow us to create
subordinate device traffic classes. The general idea here is to allow
subdividing the queues of a device into queue groups accessible through an
upper device such as a macvlan.

The idea here is to enforce the idea that an upper device has to be a
single queue device, ideally with IFF_NO_QUQUE set. With that being the
case we can pretty much guarantee that the tc_to_txq mappings and XPS maps
for the upper device are unused. As such we could reuse those in order to
support subdividing the lower device and distributing those queues between
the subordinate devices.

In order to distinguish between a regular set of traffic classes and if a
device is carrying subordinate traffic classes I changed num_tc from a u8
to a s16 value and use the negative values to represent the subordinate
pool values. So starting at -1 and running to -32768 we can encode those as
pool values, and the existing values of 0 to 15 can be maintained.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 include/linux/netdevice.h | 16 ++++++++-
 net/core/dev.c            | 89 +++++++++++++++++++++++++++++++++++++++++++++++
 net/core/net-sysfs.c      | 21 ++++++++++-
 3 files changed, 124 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b683971e500d..b1ff77276bc4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -575,6 +575,9 @@ struct netdev_queue {
 	 * (/sys/class/net/DEV/Q/trans_timeout)
 	 */
 	unsigned long		trans_timeout;
+
+	/* Subordinate device that the queue has been assigned to */
+	struct net_device	*sb_dev;
 /*
  * write-mostly part
  */
@@ -1991,7 +1994,7 @@ struct net_device {
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
 #endif
-	u8			num_tc;
+	s16			num_tc;
 	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
 	u8			prio_tc_map[TC_BITMASK + 1];
 
@@ -2045,6 +2048,17 @@ int netdev_get_num_tc(struct net_device *dev)
 	return dev->num_tc;
 }
 
+void netdev_unbind_sb_channel(struct net_device *dev,
+			      struct net_device *sb_dev);
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+				 struct net_device *sb_dev,
+				 u8 tc, u16 count, u16 offset);
+int netdev_set_sb_channel(struct net_device *dev, u16 channel);
+static inline int netdev_get_sb_channel(struct net_device *dev)
+{
+	return max_t(int, -dev->num_tc, 0);
+}
+
 static inline
 struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
 					 unsigned int index)
diff --git a/net/core/dev.c b/net/core/dev.c
index 89825c1eccdc..cc1d6bba017a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2067,11 +2067,13 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
 		struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
 		int i;
 
+		/* walk through the TCs and see if it falls into any of them */
 		for (i = 0; i < TC_MAX_QUEUE; i++, tc++) {
 			if ((txq - tc->offset) < tc->count)
 				return i;
 		}
 
+		/* didn't find it, just return -1 to indicate no match */
 		return -1;
 	}
 
@@ -2260,7 +2262,14 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	unsigned int nr_ids;
 
 	if (dev->num_tc) {
+		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
+		if (num_tc < 0)
+			return -EINVAL;
+
+		/* If queue belongs to subordinate dev use its map */
+		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
 		tc = netdev_txq_to_tc(dev, index);
 		if (tc < 0)
 			return -EINVAL;
@@ -2448,11 +2457,25 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 EXPORT_SYMBOL(netif_set_xps_queue);
 
 #endif
+static void netdev_unbind_all_sb_channels(struct net_device *dev)
+{
+	struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+	/* Unbind any subordinate channels */
+	while (txq-- != &dev->_tx[0]) {
+		if (txq->sb_dev)
+			netdev_unbind_sb_channel(dev, txq->sb_dev);
+	}
+}
+
 void netdev_reset_tc(struct net_device *dev)
 {
 #ifdef CONFIG_XPS
 	netif_reset_xps_queues_gt(dev, 0);
 #endif
+	netdev_unbind_all_sb_channels(dev);
+
+	/* Reset TC configuration of device */
 	dev->num_tc = 0;
 	memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
 	memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
@@ -2481,11 +2504,77 @@ int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
 #ifdef CONFIG_XPS
 	netif_reset_xps_queues_gt(dev, 0);
 #endif
+	netdev_unbind_all_sb_channels(dev);
+
 	dev->num_tc = num_tc;
 	return 0;
 }
 EXPORT_SYMBOL(netdev_set_num_tc);
 
+void netdev_unbind_sb_channel(struct net_device *dev,
+			      struct net_device *sb_dev)
+{
+	struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+#ifdef CONFIG_XPS
+	netif_reset_xps_queues_gt(sb_dev, 0);
+#endif
+	memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq));
+	memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map));
+
+	while (txq-- != &dev->_tx[0]) {
+		if (txq->sb_dev == sb_dev)
+			txq->sb_dev = NULL;
+	}
+}
+EXPORT_SYMBOL(netdev_unbind_sb_channel);
+
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+				 struct net_device *sb_dev,
+				 u8 tc, u16 count, u16 offset)
+{
+	/* Make certain the sb_dev and dev are already configured */
+	if (sb_dev->num_tc >= 0 || tc >= dev->num_tc)
+		return -EINVAL;
+
+	/* We cannot hand out queues we don't have */
+	if ((offset + count) > dev->real_num_tx_queues)
+		return -EINVAL;
+
+	/* Record the mapping */
+	sb_dev->tc_to_txq[tc].count = count;
+	sb_dev->tc_to_txq[tc].offset = offset;
+
+	/* Provide a way for Tx queue to find the tc_to_txq map or
+	 * XPS map for itself.
+	 */
+	while (count--)
+		netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev;
+
+	return 0;
+}
+EXPORT_SYMBOL(netdev_bind_sb_channel_queue);
+
+int netdev_set_sb_channel(struct net_device *dev, u16 channel)
+{
+	/* Do not use a multiqueue device to represent a subordinate channel */
+	if (netif_is_multiqueue(dev))
+		return -ENODEV;
+
+	/* We allow channels 1 - 32767 to be used for subordinate channels.
+	 * Channel 0 is meant to be "native" mode and used only to represent
+	 * the main root device. We allow writing 0 to reset the device back
+	 * to normal mode after being used as a subordinate channel.
+	 */
+	if (channel > S16_MAX)
+		return -EINVAL;
+
+	dev->num_tc = -channel;
+
+	return 0;
+}
+EXPORT_SYMBOL(netdev_set_sb_channel);
+
 /*
  * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
  * greater than real_num_tx_queues stale skbs on the qdisc must be flushed.
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index dce3ae0fbca2..ffa1d18f2c2c 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1054,11 +1054,23 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 		return -ENOENT;
 
 	index = get_netdev_queue_index(queue);
+
+	/* If queue belongs to subordinate dev use its TC mapping */
+	dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
 	tc = netdev_txq_to_tc(dev, index);
 	if (tc < 0)
 		return -EINVAL;
 
-	return sprintf(buf, "%u\n", tc);
+	/* We can report the traffic class one of two ways:
+	 * Subordinate device traffic classes are reported with the traffic
+	 * class first, and then the subordinate class so for example TC0 on
+	 * subordinate device 2 will be reported as "0-2". If the queue
+	 * belongs to the root device it will be reported with just the
+	 * traffic class, so just "0" for TC 0 for example.
+	 */
+	return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) :
+				 sprintf(buf, "%u\n", tc);
 }
 
 #ifdef CONFIG_XPS
@@ -1225,7 +1237,14 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	index = get_netdev_queue_index(queue);
 
 	if (dev->num_tc) {
+		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
+		if (num_tc < 0)
+			return -EINVAL;
+
+		/* If queue belongs to subordinate dev use its map */
+		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
 		tc = netdev_txq_to_tc(dev, index);
 		if (tc < 0)
 			return -EINVAL;
-- 
cgit v1.2.3


From 58b0b3ed4c226f62fcdf82df366d644b7a2226ca Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 9 Jul 2018 12:19:43 -0400
Subject: ixgbe: Add code to populate and use macvlan TC to Tx queue map

This patch makes it so that we use the tc_to_txq mapping in the macvlan
device in order to select the Tx queue for outgoing packets.

The idea here is to try and move away from using ixgbe_select_queue and to
come up with a generic way to make this work for devices going forward. By
encoding this information in the netdev this can become something that can
be used generically as a solution for similar setups going forward.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 44 +++++++++++++++++++++++----
 1 file changed, 38 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a8e21becb619..80225af2acb1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5275,6 +5275,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 			     struct ixgbe_fwd_adapter *accel)
 {
+	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
+	int num_tc = netdev_get_num_tc(adapter->netdev);
 	struct net_device *vdev = accel->netdev;
 	int i, baseq, err;
 
@@ -5286,6 +5288,11 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 	accel->rx_base_queue = baseq;
 	accel->tx_base_queue = baseq;
 
+	/* record configuration for macvlan interface in vdev */
+	for (i = 0; i < num_tc; i++)
+		netdev_bind_sb_channel_queue(adapter->netdev, vdev,
+					     i, rss_i, baseq + (rss_i * i));
+
 	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
 		adapter->rx_ring[baseq + i]->netdev = vdev;
 
@@ -5310,6 +5317,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 
 	netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 
@@ -8201,18 +8212,22 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 			      void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
-	struct ixgbe_adapter *adapter;
-	int txq;
 #ifdef IXGBE_FCOE
+	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
 #endif
+	int txq;
 
 	if (fwd_adapter) {
-		adapter = netdev_priv(dev);
-		txq = reciprocal_scale(skb_get_hash(skb),
-				       adapter->num_rx_queues_per_pool);
+		u8 tc = netdev_get_num_tc(dev) ?
+			netdev_get_prio_tc_map(dev, skb->priority) : 0;
+		struct net_device *vdev = fwd_adapter->netdev;
+
+		txq = vdev->tc_to_txq[tc].offset;
+		txq += reciprocal_scale(skb_get_hash(skb),
+					vdev->tc_to_txq[tc].count);
 
-		return txq + fwd_adapter->tx_base_queue;
+		return txq;
 	}
 
 #ifdef IXGBE_FCOE
@@ -8766,6 +8781,11 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
 	/* if we cannot find a free pool then disable the offload */
 	netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
 	macvlan_release_l2fw_offload(vdev);
+
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	kfree(accel);
 
 	return 0;
@@ -9769,6 +9789,13 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 	if (!macvlan_supports_dest_filter(vdev))
 		return ERR_PTR(-EMEDIUMTYPE);
 
+	/* We need to lock down the macvlan to be a single queue device so that
+	 * we can reuse the tc_to_txq field in the macvlan netdev to represent
+	 * the queue mapping to our netdev.
+	 */
+	if (netif_is_multiqueue(vdev))
+		return ERR_PTR(-ERANGE);
+
 	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
 	if (pool == adapter->num_rx_pools) {
 		u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
@@ -9825,6 +9852,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 		return ERR_PTR(-ENOMEM);
 
 	set_bit(pool, adapter->fwd_bitmask);
+	netdev_set_sb_channel(vdev, pool);
 	accel->pool = pool;
 	accel->netdev = vdev;
 
@@ -9866,6 +9894,10 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 		ring->netdev = NULL;
 	}
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(pdev, accel->netdev);
+	netdev_set_sb_channel(accel->netdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 }
-- 
cgit v1.2.3


From eadec877ce9ca46a94e9036b5a44e7941d4fc501 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 9 Jul 2018 12:19:48 -0400
Subject: net: Add support for subordinate traffic classes to netdev_pick_tx

This change makes it so that we can support the concept of subordinate
device traffic classes to the core networking code. In doing this we can
start pulling out the driver specific bits needed to support selecting a
queue based on an upper device.

The solution at is currently stands is only partially implemented. I have
the start of some XPS bits in here, but I would still need to allow for
configuration of the XPS maps on the queues reserved for the subordinate
devices. For now I am using the reference to the sb_dev XPS map as just a
way to skip the lookup of the lower device XPS map for now as that would
result in the wrong queue being picked.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 19 +++------
 drivers/net/macvlan.c                         | 10 +----
 include/linux/netdevice.h                     |  4 +-
 net/core/dev.c                                | 58 ++++++++++++++++-----------
 4 files changed, 45 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 80225af2acb1..abb176df2e7f 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8208,20 +8208,17 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 					      input, common, ring->queue_index);
 }
 
+#ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 			      void *accel_priv, select_queue_fallback_t fallback)
 {
-	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
-#ifdef IXGBE_FCOE
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
-#endif
 	int txq;
 
-	if (fwd_adapter) {
-		u8 tc = netdev_get_num_tc(dev) ?
-			netdev_get_prio_tc_map(dev, skb->priority) : 0;
-		struct net_device *vdev = fwd_adapter->netdev;
+	if (accel_priv) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+		struct net_device *vdev = accel_priv;
 
 		txq = vdev->tc_to_txq[tc].offset;
 		txq += reciprocal_scale(skb_get_hash(skb),
@@ -8230,8 +8227,6 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return txq;
 	}
 
-#ifdef IXGBE_FCOE
-
 	/*
 	 * only execute the code below if protocol is FCoE
 	 * or FIP and we have FCoE enabled on the adapter
@@ -8257,11 +8252,9 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 		txq -= f->indices;
 
 	return txq + f->offset;
-#else
-	return fallback(dev, skb);
-#endif
 }
 
+#endif
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_frame *xdpf)
 {
@@ -10058,7 +10051,6 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
 	.ndo_start_xmit		= ixgbe_xmit_frame,
-	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgbe_set_mac,
@@ -10081,6 +10073,7 @@ static const struct net_device_ops ixgbe_netdev_ops = {
 	.ndo_poll_controller	= ixgbe_netpoll,
 #endif
 #ifdef IXGBE_FCOE
+	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
 	.ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target,
 	.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index adde8fc45588..401e1d1ce1ec 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -514,7 +514,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct macvlan_port *port = vlan->port;
 	const struct macvlan_dev *dest;
-	void *accel_priv = NULL;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
 		const struct ethhdr *eth = (void *)skb->data;
@@ -533,15 +532,10 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NET_XMIT_SUCCESS;
 		}
 	}
-
-	/* For packets that are non-multicast and not bridged we will pass
-	 * the necessary information so that the lowerdev can distinguish
-	 * the source of the packets via the accel_priv value.
-	 */
-	accel_priv = vlan->accel_priv;
 xmit_world:
 	skb->dev = vlan->lowerdev;
-	return dev_queue_xmit_accel(skb, accel_priv);
+	return dev_queue_xmit_accel(skb,
+				    netdev_get_sb_channel(dev) ? dev : NULL);
 }
 
 static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b1ff77276bc4..fda0bcda7a42 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2103,7 +2103,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
-				    void *accel_priv);
+				    struct net_device *sb_dev);
 
 /* returns the headroom that the master device needs to take in account
  * when forwarding to this dev
@@ -2568,7 +2568,7 @@ void dev_close_many(struct list_head *head, bool unlink);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 int dev_queue_xmit(struct sk_buff *skb);
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
 int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index cc1d6bba017a..09a7cc2f3c55 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2786,24 +2786,26 @@ EXPORT_SYMBOL(netif_device_attach);
  * Returns a Tx hash based on the given packet descriptor a Tx queues' number
  * to be used as a distribution range.
  */
-static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb)
+static u16 skb_tx_hash(const struct net_device *dev,
+		       const struct net_device *sb_dev,
+		       struct sk_buff *skb)
 {
 	u32 hash;
 	u16 qoffset = 0;
 	u16 qcount = dev->real_num_tx_queues;
 
+	if (dev->num_tc) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+
+		qoffset = sb_dev->tc_to_txq[tc].offset;
+		qcount = sb_dev->tc_to_txq[tc].count;
+	}
+
 	if (skb_rx_queue_recorded(skb)) {
 		hash = skb_get_rx_queue(skb);
 		while (unlikely(hash >= qcount))
 			hash -= qcount;
-		return hash;
-	}
-
-	if (dev->num_tc) {
-		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
-
-		qoffset = dev->tc_to_txq[tc].offset;
-		qcount = dev->tc_to_txq[tc].count;
+		return hash + qoffset;
 	}
 
 	return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
@@ -3573,7 +3575,8 @@ static int __get_xps_queue_idx(struct net_device *dev, struct sk_buff *skb,
 }
 #endif
 
-static int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+static int get_xps_queue(struct net_device *dev, struct net_device *sb_dev,
+			 struct sk_buff *skb)
 {
 #ifdef CONFIG_XPS
 	struct xps_dev_maps *dev_maps;
@@ -3587,7 +3590,7 @@ static int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 	if (!static_key_false(&xps_rxqs_needed))
 		goto get_cpus_map;
 
-	dev_maps = rcu_dereference(dev->xps_rxqs_map);
+	dev_maps = rcu_dereference(sb_dev->xps_rxqs_map);
 	if (dev_maps) {
 		int tci = sk_rx_queue_get(sk);
 
@@ -3598,7 +3601,7 @@ static int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 
 get_cpus_map:
 	if (queue_index < 0) {
-		dev_maps = rcu_dereference(dev->xps_cpus_map);
+		dev_maps = rcu_dereference(sb_dev->xps_cpus_map);
 		if (dev_maps) {
 			unsigned int tci = skb->sender_cpu - 1;
 
@@ -3614,17 +3617,20 @@ get_cpus_map:
 #endif
 }
 
-static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+			     struct net_device *sb_dev)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
 
+	sb_dev = sb_dev ? : dev;
+
 	if (queue_index < 0 || skb->ooo_okay ||
 	    queue_index >= dev->real_num_tx_queues) {
-		int new_index = get_xps_queue(dev, skb);
+		int new_index = get_xps_queue(dev, sb_dev, skb);
 
 		if (new_index < 0)
-			new_index = skb_tx_hash(dev, skb);
+			new_index = skb_tx_hash(dev, sb_dev, skb);
 
 		if (queue_index != new_index && sk &&
 		    sk_fullsock(sk) &&
@@ -3637,9 +3643,15 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 	return queue_index;
 }
 
+static u16 __netdev_pick_tx(struct net_device *dev,
+			    struct sk_buff *skb)
+{
+	return ___netdev_pick_tx(dev, skb, NULL);
+}
+
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
-				    void *accel_priv)
+				    struct net_device *sb_dev)
 {
 	int queue_index = 0;
 
@@ -3654,10 +3666,10 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 		const struct net_device_ops *ops = dev->netdev_ops;
 
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+			queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
 							    __netdev_pick_tx);
 		else
-			queue_index = __netdev_pick_tx(dev, skb);
+			queue_index = ___netdev_pick_tx(dev, skb, sb_dev);
 
 		queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
@@ -3669,7 +3681,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 /**
  *	__dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
- *	@accel_priv: private data used for L2 forwarding offload
+ *	@sb_dev: suboordinate device used for L2 forwarding offload
  *
  *	Queue a buffer for transmission to a network device. The caller must
  *	have set the device and priority and built the buffer before calling
@@ -3692,7 +3704,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
+static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq;
@@ -3731,7 +3743,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 	else
 		skb_dst_force(skb);
 
-	txq = netdev_pick_tx(dev, skb, accel_priv);
+	txq = netdev_pick_tx(dev, skb, sb_dev);
 	q = rcu_dereference_bh(txq->qdisc);
 
 	trace_net_dev_queue(skb);
@@ -3805,9 +3817,9 @@ int dev_queue_xmit(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dev_queue_xmit);
 
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
 {
-	return __dev_queue_xmit(skb, accel_priv);
+	return __dev_queue_xmit(skb, sb_dev);
 }
 EXPORT_SYMBOL(dev_queue_xmit_accel);
 
-- 
cgit v1.2.3


From a4ea8a3dacc312c3402c78f6e4843afdda9b43a0 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 9 Jul 2018 12:19:54 -0400
Subject: net: Add generic ndo_select_queue functions

This patch adds a generic version of the ndo_select_queue functions for
either returning 0 or selecting a queue based on the processor ID. This is
generally meant to just reduce the number of functions we have to change
in the future when we have to deal with ndo_select_queue changes.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/lantiq_etop.c   | 10 +---------
 drivers/net/ethernet/ti/netcp_core.c |  9 +--------
 drivers/staging/netlogic/xlr_net.c   |  9 +--------
 include/linux/netdevice.h            |  4 ++++
 net/core/dev.c                       | 14 ++++++++++++++
 net/packet/af_packet.c               |  2 +-
 6 files changed, 22 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/lantiq_etop.c b/drivers/net/ethernet/lantiq_etop.c
index afc810069440..7a637b51c7d2 100644
--- a/drivers/net/ethernet/lantiq_etop.c
+++ b/drivers/net/ethernet/lantiq_etop.c
@@ -563,14 +563,6 @@ ltq_etop_set_multicast_list(struct net_device *dev)
 	spin_unlock_irqrestore(&priv->lock, flags);
 }
 
-static u16
-ltq_etop_select_queue(struct net_device *dev, struct sk_buff *skb,
-		      void *accel_priv, select_queue_fallback_t fallback)
-{
-	/* we are currently only using the first queue */
-	return 0;
-}
-
 static int
 ltq_etop_init(struct net_device *dev)
 {
@@ -641,7 +633,7 @@ static const struct net_device_ops ltq_eth_netdev_ops = {
 	.ndo_set_mac_address = ltq_etop_set_mac_address,
 	.ndo_validate_addr = eth_validate_addr,
 	.ndo_set_rx_mode = ltq_etop_set_multicast_list,
-	.ndo_select_queue = ltq_etop_select_queue,
+	.ndo_select_queue = dev_pick_tx_zero,
 	.ndo_init = ltq_etop_init,
 	.ndo_tx_timeout = ltq_etop_tx_timeout,
 };
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index 6ebf110cd594..a1d335a3c5e4 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -1889,13 +1889,6 @@ static int netcp_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 	return err;
 }
 
-static u16 netcp_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      void *accel_priv,
-			      select_queue_fallback_t fallback)
-{
-	return 0;
-}
-
 static int netcp_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			  void *type_data)
 {
@@ -1972,7 +1965,7 @@ static const struct net_device_ops netcp_netdev_ops = {
 	.ndo_vlan_rx_add_vid	= netcp_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= netcp_rx_kill_vid,
 	.ndo_tx_timeout		= netcp_ndo_tx_timeout,
-	.ndo_select_queue	= netcp_select_queue,
+	.ndo_select_queue	= dev_pick_tx_zero,
 	.ndo_setup_tc		= netcp_setup_tc,
 };
 
diff --git a/drivers/staging/netlogic/xlr_net.c b/drivers/staging/netlogic/xlr_net.c
index e461168313bf..4e6611e4c59b 100644
--- a/drivers/staging/netlogic/xlr_net.c
+++ b/drivers/staging/netlogic/xlr_net.c
@@ -290,13 +290,6 @@ static netdev_tx_t xlr_net_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
-static u16 xlr_net_select_queue(struct net_device *ndev, struct sk_buff *skb,
-				void *accel_priv,
-				select_queue_fallback_t fallback)
-{
-	return (u16)smp_processor_id();
-}
-
 static void xlr_hw_set_mac_addr(struct net_device *ndev)
 {
 	struct xlr_net_priv *priv = netdev_priv(ndev);
@@ -403,7 +396,7 @@ static const struct net_device_ops xlr_netdev_ops = {
 	.ndo_open = xlr_net_open,
 	.ndo_stop = xlr_net_stop,
 	.ndo_start_xmit = xlr_net_start_xmit,
-	.ndo_select_queue = xlr_net_select_queue,
+	.ndo_select_queue = dev_pick_tx_cpu_id,
 	.ndo_set_mac_address = xlr_net_set_mac_addr,
 	.ndo_set_rx_mode = xlr_set_rx_mode,
 	.ndo_get_stats64 = xlr_stats,
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index fda0bcda7a42..46f4c44ce3e4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2567,6 +2567,10 @@ void dev_close(struct net_device *dev);
 void dev_close_many(struct list_head *head, bool unlink);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
+u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
+		     void *accel_priv, select_queue_fallback_t fallback);
+u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv, select_queue_fallback_t fallback);
 int dev_queue_xmit(struct sk_buff *skb);
 int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
 int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
diff --git a/net/core/dev.c b/net/core/dev.c
index 09a7cc2f3c55..b5e538032d5e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3617,6 +3617,20 @@ get_cpus_map:
 #endif
 }
 
+u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
+		     void *accel_priv, select_queue_fallback_t fallback)
+{
+	return 0;
+}
+EXPORT_SYMBOL(dev_pick_tx_zero);
+
+u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
+		       void *accel_priv, select_queue_fallback_t fallback)
+{
+	return (u16)raw_smp_processor_id() % dev->real_num_tx_queues;
+}
+EXPORT_SYMBOL(dev_pick_tx_cpu_id);
+
 static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 			     struct net_device *sb_dev)
 {
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 47931ebfaef3..f37d087ae652 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -277,7 +277,7 @@ static bool packet_use_direct_xmit(const struct packet_sock *po)
 
 static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
 {
-	return (u16) raw_smp_processor_id() % dev->real_num_tx_queues;
+	return dev_pick_tx_cpu_id(dev, skb, NULL, NULL);
 }
 
 static u16 packet_pick_tx_queue(struct sk_buff *skb)
-- 
cgit v1.2.3


From 4f49dec9075aa0277b8c9c657ec31e6361f88724 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 9 Jul 2018 12:19:59 -0400
Subject: net: allow ndo_select_queue to pass netdev

This patch makes it so that instead of passing a void pointer as the
accel_priv we instead pass a net_device pointer as sb_dev. Making this
change allows us to pass the subordinate device through to the fallback
function eventually so that we can keep the actual code in the
ndo_select_queue call as focused on possible on the exception cases.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/infiniband/hw/hfi1/vnic_main.c            |  2 +-
 drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c |  4 ++--
 drivers/net/bonding/bond_main.c                   |  3 ++-
 drivers/net/ethernet/amazon/ena/ena_netdev.c      |  3 ++-
 drivers/net/ethernet/broadcom/bcmsysport.c        |  2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c   |  3 ++-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h   |  3 ++-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c   |  3 ++-
 drivers/net/ethernet/hisilicon/hns/hns_enet.c     |  3 ++-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c     |  7 ++++---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c        |  3 ++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h      |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  3 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c   |  3 ++-
 drivers/net/ethernet/renesas/ravb_main.c          |  3 ++-
 drivers/net/ethernet/sun/ldmvsw.c                 |  3 ++-
 drivers/net/ethernet/sun/sunvnet.c                |  3 ++-
 drivers/net/hyperv/netvsc_drv.c                   |  4 ++--
 drivers/net/net_failover.c                        |  5 +++--
 drivers/net/team/team.c                           |  3 ++-
 drivers/net/tun.c                                 |  3 ++-
 drivers/net/wireless/marvell/mwifiex/main.c       |  3 ++-
 drivers/net/xen-netback/interface.c               |  2 +-
 drivers/net/xen-netfront.c                        |  3 ++-
 drivers/staging/rtl8188eu/os_dep/os_intfs.c       |  3 ++-
 drivers/staging/rtl8723bs/os_dep/os_intfs.c       |  7 +++----
 include/linux/netdevice.h                         | 11 +++++++----
 net/core/dev.c                                    |  6 ++++--
 net/mac80211/iface.c                              |  4 ++--
 29 files changed, 66 insertions(+), 42 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/vnic_main.c b/drivers/infiniband/hw/hfi1/vnic_main.c
index 5d65582fe4d9..616fc9b6fad8 100644
--- a/drivers/infiniband/hw/hfi1/vnic_main.c
+++ b/drivers/infiniband/hw/hfi1/vnic_main.c
@@ -423,7 +423,7 @@ tx_finish:
 
 static u16 hfi1_vnic_select_queue(struct net_device *netdev,
 				  struct sk_buff *skb,
-				  void *accel_priv,
+				  struct net_device *sb_dev,
 				  select_queue_fallback_t fallback)
 {
 	struct hfi1_vnic_vport_info *vinfo = opa_vnic_dev_priv(netdev);
diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
index 0c8aec62a425..61558788b3fa 100644
--- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
+++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c
@@ -95,7 +95,7 @@ static netdev_tx_t opa_netdev_start_xmit(struct sk_buff *skb,
 }
 
 static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
-				 void *accel_priv,
+				 struct net_device *sb_dev,
 				 select_queue_fallback_t fallback)
 {
 	struct opa_vnic_adapter *adapter = opa_vnic_priv(netdev);
@@ -107,7 +107,7 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb,
 	mdata->entropy = opa_vnic_calc_entropy(skb);
 	mdata->vl = opa_vnic_get_vl(adapter, skb);
 	rc = adapter->rn_ops->ndo_select_queue(netdev, skb,
-					       accel_priv, fallback);
+					       sb_dev, fallback);
 	skb_pull(skb, sizeof(*mdata));
 	return rc;
 }
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 63e3844c5bec..9a2ea3c1f949 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4094,7 +4094,8 @@ static inline int bond_slave_override(struct bonding *bond,
 
 
 static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/* This helper function exists to help dev_pick_tx get the correct
 	 * destination queue.  Using a helper function skips a call to
diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index f2af87d70594..e3befb1f9204 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2213,7 +2213,8 @@ static void ena_netpoll(struct net_device *netdev)
 #endif /* CONFIG_NET_POLL_CONTROLLER */
 
 static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	u16 qid;
 	/* we suspect that this is good for in--kernel network services that
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index d5fca2e5a9bc..32f548e6431d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2107,7 +2107,7 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 };
 
 static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
-				    void *accel_priv,
+				    struct net_device *sb_dev,
 				    select_queue_fallback_t fallback)
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index af7b5a4d8ba0..e4e1cf907ac6 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1910,7 +1910,8 @@ void bnx2x_netif_stop(struct bnx2x *bp, int disable_hw)
 }
 
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	struct bnx2x *bp = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
index a8ce5c55bbb0..0e508e5defce 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.h
@@ -497,7 +497,8 @@ int bnx2x_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos,
 
 /* select_queue callback */
 u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 
 static inline void bnx2x_update_rx_prod(struct bnx2x *bp,
 					struct bnx2x_fastpath *fp,
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 0d91716a2566..5dc5e5604f05 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -930,7 +930,8 @@ freeout:
 }
 
 static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	int txq;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index ef9ef703d13a..ff7a74ec8f11 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2022,7 +2022,8 @@ static void hns_nic_get_stats64(struct net_device *ndev,
 
 static u16
 hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
-		     void *accel_priv, select_queue_fallback_t fallback)
+		     struct net_device *sb_dev,
+		     select_queue_fallback_t fallback)
 {
 	struct ethhdr *eth_hdr = (struct ethhdr *)skb->data;
 	struct hns_nic_priv *priv = netdev_priv(ndev);
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index abb176df2e7f..8c7a68c57afa 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8210,15 +8210,16 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 
 #ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
-			      void *accel_priv, select_queue_fallback_t fallback)
+			      struct net_device *sb_dev,
+			      select_queue_fallback_t fallback)
 {
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
 	int txq;
 
-	if (accel_priv) {
+	if (sb_dev) {
 		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
-		struct net_device *vdev = accel_priv;
+		struct net_device *vdev = sb_dev;
 
 		txq = vdev->tc_to_txq[tc].offset;
 		txq += reciprocal_scale(skb_get_hash(skb),
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 0227786308af..df2996618cd1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -688,7 +688,8 @@ static void build_inline_wqe(struct mlx4_en_tx_desc *tx_desc,
 }
 
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv, select_queue_fallback_t fallback)
+			 struct net_device *sb_dev,
+			 select_queue_fallback_t fallback)
 {
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	u16 rings_p_up = priv->num_tx_rings_p_up;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index ace6545f82e6..c3228b89df46 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -699,7 +699,8 @@ void mlx4_en_arm_cq(struct mlx4_en_priv *priv, struct mlx4_en_cq *cq);
 
 void mlx4_en_tx_irq(struct mlx4_cq *mcq);
 u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
-			 void *accel_priv, select_queue_fallback_t fallback);
+			 struct net_device *sb_dev,
+			 select_queue_fallback_t fallback);
 netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_rx_alloc *frame,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e2b7586ed7a0..e1b237ccdf56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -865,7 +865,8 @@ struct mlx5e_profile {
 void mlx5e_build_ptys2ethtool_map(void);
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 			  struct mlx5e_tx_wqe *wqe, u16 pi);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f0739dae7b56..dfcc3710b65f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -111,7 +111,8 @@ static inline int mlx5e_get_dscp_up(struct mlx5e_priv *priv, struct sk_buff *skb
 #endif
 
 u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	int channel_ix = fallback(dev, skb);
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 68f122140966..4a7f54c8e7aa 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1656,7 +1656,8 @@ drop:
 }
 
 static u16 ravb_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/* If skb needs TX timestamp, it is handled in network control queue */
 	return (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) ? RAVB_NC :
diff --git a/drivers/net/ethernet/sun/ldmvsw.c b/drivers/net/ethernet/sun/ldmvsw.c
index a5dd627fe2f9..d42f47f6c632 100644
--- a/drivers/net/ethernet/sun/ldmvsw.c
+++ b/drivers/net/ethernet/sun/ldmvsw.c
@@ -101,7 +101,8 @@ static struct vnet_port *vsw_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vsw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct vnet_port *port = netdev_priv(dev);
 
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index a94f50442613..12539b357a78 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -234,7 +234,8 @@ static struct vnet_port *vnet_tx_port_find(struct sk_buff *skb,
 }
 
 static u16 vnet_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	struct vnet *vp = netdev_priv(dev);
 	struct vnet_port *port = __tx_port_find(vp, skb);
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index dd1d6e115145..98c0107d6ca1 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -329,7 +329,7 @@ static u16 netvsc_pick_tx(struct net_device *ndev, struct sk_buff *skb)
 }
 
 static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
-			       void *accel_priv,
+			       struct net_device *sb_dev,
 			       select_queue_fallback_t fallback)
 {
 	struct net_device_context *ndc = netdev_priv(ndev);
@@ -343,7 +343,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 
 		if (vf_ops->ndo_select_queue)
 			txq = vf_ops->ndo_select_queue(vf_netdev, skb,
-						       accel_priv, fallback);
+						       sb_dev, fallback);
 		else
 			txq = fallback(vf_netdev, skb);
 
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index 4f390fa557e4..78b549698b7b 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -115,7 +115,8 @@ static netdev_tx_t net_failover_start_xmit(struct sk_buff *skb,
 }
 
 static u16 net_failover_select_queue(struct net_device *dev,
-				     struct sk_buff *skb, void *accel_priv,
+				     struct sk_buff *skb,
+				     struct net_device *sb_dev,
 				     select_queue_fallback_t fallback)
 {
 	struct net_failover_info *nfo_info = netdev_priv(dev);
@@ -128,7 +129,7 @@ static u16 net_failover_select_queue(struct net_device *dev,
 
 		if (ops->ndo_select_queue)
 			txq = ops->ndo_select_queue(primary_dev, skb,
-						    accel_priv, fallback);
+						    sb_dev, fallback);
 		else
 			txq = fallback(primary_dev, skb);
 
diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index b070959737ff..3a95eaae0c98 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -1707,7 +1707,8 @@ static netdev_tx_t team_xmit(struct sk_buff *skb, struct net_device *dev)
 }
 
 static u16 team_select_queue(struct net_device *dev, struct sk_buff *skb,
-			     void *accel_priv, select_queue_fallback_t fallback)
+			     struct net_device *sb_dev,
+			     select_queue_fallback_t fallback)
 {
 	/*
 	 * This helper function exists to help dev_pick_tx get the correct
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a192a017cc68..76f0f4131197 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -607,7 +607,8 @@ static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 }
 
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct tun_struct *tun = netdev_priv(dev);
 	u16 ret;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 510f6b8e717d..fa3e8ddfe9a9 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -1279,7 +1279,8 @@ static struct net_device_stats *mwifiex_get_stats(struct net_device *dev)
 
 static u16
 mwifiex_netdev_select_wmm_queue(struct net_device *dev, struct sk_buff *skb,
-				void *accel_priv, select_queue_fallback_t fallback)
+				struct net_device *sb_dev,
+				select_queue_fallback_t fallback)
 {
 	skb->priority = cfg80211_classify8021d(skb, NULL);
 	return mwifiex_1d_to_wmm_queue[skb->priority];
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 78ebe494fef0..19c4c585f472 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -148,7 +148,7 @@ void xenvif_wake_queue(struct xenvif_queue *queue)
 }
 
 static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
-			       void *accel_priv,
+			       struct net_device *sb_dev,
 			       select_queue_fallback_t fallback)
 {
 	struct xenvif *vif = netdev_priv(dev);
diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index a57daecf1d57..d67cd379d156 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -545,7 +545,8 @@ static int xennet_count_skb_slots(struct sk_buff *skb)
 }
 
 static u16 xennet_select_queue(struct net_device *dev, struct sk_buff *skb,
-			       void *accel_priv, select_queue_fallback_t fallback)
+			       struct net_device *sb_dev,
+			       select_queue_fallback_t fallback)
 {
 	unsigned int num_queues = dev->real_num_tx_queues;
 	u32 hash;
diff --git a/drivers/staging/rtl8188eu/os_dep/os_intfs.c b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
index add1ba00f3e9..38e85c8a85c8 100644
--- a/drivers/staging/rtl8188eu/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8188eu/os_dep/os_intfs.c
@@ -253,7 +253,8 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 }
 
 static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
-			    void *accel_priv, select_queue_fallback_t fallback)
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/drivers/staging/rtl8723bs/os_dep/os_intfs.c b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
index ace68f023b49..181642358e3f 100644
--- a/drivers/staging/rtl8723bs/os_dep/os_intfs.c
+++ b/drivers/staging/rtl8723bs/os_dep/os_intfs.c
@@ -403,10 +403,9 @@ static unsigned int rtw_classify8021d(struct sk_buff *skb)
 }
 
 
-static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb
-				, void *accel_priv
-				, select_queue_fallback_t fallback
-)
+static u16 rtw_select_queue(struct net_device *dev, struct sk_buff *skb,
+			    struct net_device *sb_dev,
+			    select_queue_fallback_t fallback)
 {
 	struct adapter	*padapter = rtw_netdev_priv(dev);
 	struct mlme_priv *pmlmepriv = &padapter->mlmepriv;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 46f4c44ce3e4..bbf062c1ca8a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -957,7 +957,8 @@ struct dev_ifalias {
  *	those the driver believes to be appropriate.
  *
  * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb,
- *                         void *accel_priv, select_queue_fallback_t fallback);
+ *                         struct net_device *sb_dev,
+ *                         select_queue_fallback_t fallback);
  *	Called to decide which queue to use when device supports multiple
  *	transmit queues.
  *
@@ -1229,7 +1230,7 @@ struct net_device_ops {
 						      netdev_features_t features);
 	u16			(*ndo_select_queue)(struct net_device *dev,
 						    struct sk_buff *skb,
-						    void *accel_priv,
+						    struct net_device *sb_dev,
 						    select_queue_fallback_t fallback);
 	void			(*ndo_change_rx_flags)(struct net_device *dev,
 						       int flags);
@@ -2568,9 +2569,11 @@ void dev_close_many(struct list_head *head, bool unlink);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
-		     void *accel_priv, select_queue_fallback_t fallback);
+		     struct net_device *sb_dev,
+		     select_queue_fallback_t fallback);
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback);
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback);
 int dev_queue_xmit(struct sk_buff *skb);
 int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
 int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
diff --git a/net/core/dev.c b/net/core/dev.c
index b5e538032d5e..a051ce27198b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3618,14 +3618,16 @@ get_cpus_map:
 }
 
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
-		     void *accel_priv, select_queue_fallback_t fallback)
+		     struct net_device *sb_dev,
+		     select_queue_fallback_t fallback)
 {
 	return 0;
 }
 EXPORT_SYMBOL(dev_pick_tx_zero);
 
 u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
-		       void *accel_priv, select_queue_fallback_t fallback)
+		       struct net_device *sb_dev,
+		       select_queue_fallback_t fallback)
 {
 	return (u16)raw_smp_processor_id() % dev->real_num_tx_queues;
 }
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 555e389b7dfa..5e6cf2cee965 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1130,7 +1130,7 @@ static void ieee80211_uninit(struct net_device *dev)
 
 static u16 ieee80211_netdev_select_queue(struct net_device *dev,
 					 struct sk_buff *skb,
-					 void *accel_priv,
+					 struct net_device *sb_dev,
 					 select_queue_fallback_t fallback)
 {
 	return ieee80211_select_queue(IEEE80211_DEV_TO_SUB_IF(dev), skb);
@@ -1176,7 +1176,7 @@ static const struct net_device_ops ieee80211_dataif_ops = {
 
 static u16 ieee80211_monitor_select_queue(struct net_device *dev,
 					  struct sk_buff *skb,
-					  void *accel_priv,
+					  struct net_device *sb_dev,
 					  select_queue_fallback_t fallback)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
-- 
cgit v1.2.3


From 8ec56fc3c5ee6f9700adac190e9ce5b8859a58b6 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Mon, 9 Jul 2018 12:20:04 -0400
Subject: net: allow fallback function to pass netdev

For most of these calls we can just pass NULL through to the fallback
function as the sb_dev. The only cases where we cannot are the cases where
we might be dealing with either an upper device or a driver that would
have configured things to support an sb_dev itself.

The only driver that has any significant change in this patch set should be
ixgbe as we can drop the redundant functionality that existed in both the
ndo_select_queue function and the fallback function that was passed through
to us.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c    |  2 +-
 drivers/net/ethernet/broadcom/bcmsysport.c      |  4 ++--
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c |  3 ++-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c |  2 +-
 drivers/net/ethernet/hisilicon/hns/hns_enet.c   |  2 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c   |  4 ++--
 drivers/net/ethernet/mellanox/mlx4/en_tx.c      |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c |  2 +-
 drivers/net/hyperv/netvsc_drv.c                 |  2 +-
 drivers/net/net_failover.c                      |  2 +-
 drivers/net/xen-netback/interface.c             |  2 +-
 include/linux/netdevice.h                       |  3 ++-
 net/core/dev.c                                  | 12 +++---------
 net/packet/af_packet.c                          |  7 ++++---
 14 files changed, 24 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index e3befb1f9204..c673ac2df65b 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -2224,7 +2224,7 @@ static u16 ena_select_queue(struct net_device *dev, struct sk_buff *skb,
 	if (skb_rx_queue_recorded(skb))
 		qid = skb_get_rx_queue(skb);
 	else
-		qid = fallback(dev, skb);
+		qid = fallback(dev, skb, NULL);
 
 	return qid;
 }
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 32f548e6431d..eb890c4b3b2d 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2116,7 +2116,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	unsigned int q, port;
 
 	if (!netdev_uses_dsa(dev))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
 	/* DSA tagging layer will have configured the correct queue */
 	q = BRCM_TAG_GET_QUEUE(queue);
@@ -2124,7 +2124,7 @@ static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
 	tx_ring = priv->ring_map[q + port * priv->per_port_num_tx_queues];
 
 	if (unlikely(!tx_ring))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
 	return tx_ring->index;
 }
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
index e4e1cf907ac6..5a727d4729da 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c
@@ -1933,7 +1933,8 @@ u16 bnx2x_select_queue(struct net_device *dev, struct sk_buff *skb,
 	}
 
 	/* select a non-FCoE queue */
-	return fallback(dev, skb) % (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
+	return fallback(dev, skb, NULL) %
+	       (BNX2X_NUM_ETH_QUEUES(bp) * bp->max_cos);
 }
 
 void bnx2x_set_num_queues(struct bnx2x *bp)
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 5dc5e5604f05..40cf8dc9f163 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -973,7 +973,7 @@ static u16 cxgb_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return txq;
 	}
 
-	return fallback(dev, skb) % dev->real_num_tx_queues;
+	return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
 }
 
 static int closest_timer(const struct sge *s, int time)
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index ff7a74ec8f11..948b3e0d18f4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2033,7 +2033,7 @@ hns_nic_select_queue(struct net_device *ndev, struct sk_buff *skb,
 	    is_multicast_ether_addr(eth_hdr->h_dest))
 		return 0;
 	else
-		return fallback(ndev, skb);
+		return fallback(ndev, skb, NULL);
 }
 
 static const struct net_device_ops hns_nic_netdev_ops = {
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 8c7a68c57afa..bd6d9ea27b4b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8237,11 +8237,11 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 	case htons(ETH_P_FIP):
 		adapter = netdev_priv(dev);
 
-		if (adapter->flags & IXGBE_FLAG_FCOE_ENABLED)
+		if (!sb_dev && (adapter->flags & IXGBE_FLAG_FCOE_ENABLED))
 			break;
 		/* fall through */
 	default:
-		return fallback(dev, skb);
+		return fallback(dev, skb, sb_dev);
 	}
 
 	f = &adapter->ring_feature[RING_F_FCOE];
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index df2996618cd1..1857ee0f0871 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -695,9 +695,9 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb,
 	u16 rings_p_up = priv->num_tx_rings_p_up;
 
 	if (netdev_get_num_tc(dev))
-		return fallback(dev, skb);
+		return fallback(dev, skb, NULL);
 
-	return fallback(dev, skb) % rings_p_up;
+	return fallback(dev, skb, NULL) % rings_p_up;
 }
 
 static void mlx4_bf_copy(void __iomem *dst, const void *src,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index dfcc3710b65f..9106ea45e3cb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -115,7 +115,7 @@ u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb,
 		       select_queue_fallback_t fallback)
 {
 	struct mlx5e_priv *priv = netdev_priv(dev);
-	int channel_ix = fallback(dev, skb);
+	int channel_ix = fallback(dev, skb, NULL);
 	u16 num_channels;
 	int up = 0;
 
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 98c0107d6ca1..cf4f40a04194 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -345,7 +345,7 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb,
 			txq = vf_ops->ndo_select_queue(vf_netdev, skb,
 						       sb_dev, fallback);
 		else
-			txq = fallback(vf_netdev, skb);
+			txq = fallback(vf_netdev, skb, NULL);
 
 		/* Record the queue selected by VF so that it can be
 		 * used for common case where VF has more queues than
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index 78b549698b7b..d00d42c845b7 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -131,7 +131,7 @@ static u16 net_failover_select_queue(struct net_device *dev,
 			txq = ops->ndo_select_queue(primary_dev, skb,
 						    sb_dev, fallback);
 		else
-			txq = fallback(primary_dev, skb);
+			txq = fallback(primary_dev, skb, NULL);
 
 		qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping;
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 19c4c585f472..92274c237200 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -155,7 +155,7 @@ static u16 xenvif_select_queue(struct net_device *dev, struct sk_buff *skb,
 	unsigned int size = vif->hash.size;
 
 	if (vif->hash.alg == XEN_NETIF_CTRL_HASH_ALGORITHM_NONE)
-		return fallback(dev, skb) % dev->real_num_tx_queues;
+		return fallback(dev, skb, NULL) % dev->real_num_tx_queues;
 
 	xenvif_set_skb_hash(vif, skb);
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bbf062c1ca8a..2daf2fa6554f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -793,7 +793,8 @@ static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a,
 }
 
 typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
-				       struct sk_buff *skb);
+				       struct sk_buff *skb,
+				       struct net_device *sb_dev);
 
 enum tc_setup_type {
 	TC_SETUP_QDISC_MQPRIO,
diff --git a/net/core/dev.c b/net/core/dev.c
index a051ce27198b..e18d81837a6c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3633,8 +3633,8 @@ u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(dev_pick_tx_cpu_id);
 
-static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
-			     struct net_device *sb_dev)
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+			    struct net_device *sb_dev)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
@@ -3659,12 +3659,6 @@ static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 	return queue_index;
 }
 
-static u16 __netdev_pick_tx(struct net_device *dev,
-			    struct sk_buff *skb)
-{
-	return ___netdev_pick_tx(dev, skb, NULL);
-}
-
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
 				    struct net_device *sb_dev)
@@ -3685,7 +3679,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 			queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
 							    __netdev_pick_tx);
 		else
-			queue_index = ___netdev_pick_tx(dev, skb, sb_dev);
+			queue_index = __netdev_pick_tx(dev, skb, sb_dev);
 
 		queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index f37d087ae652..00189a3b07f2 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -275,9 +275,10 @@ static bool packet_use_direct_xmit(const struct packet_sock *po)
 	return po->xmit == packet_direct_xmit;
 }
 
-static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb)
+static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb,
+				  struct net_device *sb_dev)
 {
-	return dev_pick_tx_cpu_id(dev, skb, NULL, NULL);
+	return dev_pick_tx_cpu_id(dev, skb, sb_dev, NULL);
 }
 
 static u16 packet_pick_tx_queue(struct sk_buff *skb)
@@ -291,7 +292,7 @@ static u16 packet_pick_tx_queue(struct sk_buff *skb)
 						    __packet_pick_tx_queue);
 		queue_index = netdev_cap_txqueue(dev, queue_index);
 	} else {
-		queue_index = __packet_pick_tx_queue(dev, skb);
+		queue_index = __packet_pick_tx_queue(dev, skb, NULL);
 	}
 
 	return queue_index;
-- 
cgit v1.2.3


From 8c057efaebb557b60ba514b5e39e8000a1eab0f1 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 9 Jul 2018 18:09:54 +0100
Subject: net: core: fix uses-after-free in list processing

In netif_receive_skb_list_internal(), all of skb_defer_rx_timestamp(),
 do_xdp_generic() and enqueue_to_backlog() can lead to kfree(skb).  Thus,
 we cannot wait until after they return to remove the skb from the list;
 instead, we remove it first and, in the pass case, add it to a sublist
 afterwards.
In the case of enqueue_to_backlog() we have already decided not to pass
 when we call the function, so we do not need a sublist.

Fixes: 7da517a3bc52 ("net: core: Another step of skb receive list processing")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 89825c1eccdc..ce4583564e00 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4982,25 +4982,30 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 {
 	struct bpf_prog *xdp_prog = NULL;
 	struct sk_buff *skb, *next;
+	struct list_head sublist;
 
+	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		net_timestamp_check(netdev_tstamp_prequeue, skb);
-		if (skb_defer_rx_timestamp(skb))
-			/* Handled, remove from list */
-			list_del(&skb->list);
+		list_del(&skb->list);
+		if (!skb_defer_rx_timestamp(skb))
+			list_add_tail(&skb->list, &sublist);
 	}
+	list_splice_init(&sublist, head);
 
 	if (static_branch_unlikely(&generic_xdp_needed_key)) {
 		preempt_disable();
 		rcu_read_lock();
 		list_for_each_entry_safe(skb, next, head, list) {
 			xdp_prog = rcu_dereference(skb->dev->xdp_prog);
-			if (do_xdp_generic(xdp_prog, skb) != XDP_PASS)
-				/* Dropped, remove from list */
-				list_del(&skb->list);
+			list_del(&skb->list);
+			if (do_xdp_generic(xdp_prog, skb) == XDP_PASS)
+				list_add_tail(&skb->list, &sublist);
 		}
 		rcu_read_unlock();
 		preempt_enable();
+		/* Put passed packets back on main list */
+		list_splice_init(&sublist, head);
 	}
 
 	rcu_read_lock();
@@ -5011,9 +5016,9 @@ static void netif_receive_skb_list_internal(struct list_head *head)
 			int cpu = get_rps_cpu(skb->dev, skb, &rflow);
 
 			if (cpu >= 0) {
-				enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
-				/* Handled, remove from list */
+				/* Will be handled, remove from list */
 				list_del(&skb->list);
+				enqueue_to_backlog(skb, cpu, &rflow->last_qtail);
 			}
 		}
 	}
-- 
cgit v1.2.3


From 9f17dbf04ddf55ae48f5bbafea4c4920ea943215 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 9 Jul 2018 18:10:02 +0100
Subject: netfilter: fix use-after-free in NF_HOOK_LIST

nf_hook() can free the skb, so we need to remove it from the list before
 calling, and add passed skbs to a sublist afterwards.

Fixes: 17266ee93984 ("net: ipv4: listified version of ip_rcv")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 5a5e0a2ab2a3..23b48de8c2e2 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -294,12 +294,16 @@ NF_HOOK_LIST(uint8_t pf, unsigned int hook, struct net *net, struct sock *sk,
 	     int (*okfn)(struct net *, struct sock *, struct sk_buff *))
 {
 	struct sk_buff *skb, *next;
+	struct list_head sublist;
 
+	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
-		int ret = nf_hook(pf, hook, net, sk, skb, in, out, okfn);
-		if (ret != 1)
-			list_del(&skb->list);
+		list_del(&skb->list);
+		if (nf_hook(pf, hook, net, sk, skb, in, out, okfn) == 1)
+			list_add_tail(&skb->list, &sublist);
 	}
+	/* Put passed packets back on main list */
+	list_splice(&sublist, head);
 }
 
 /* Call setsockopt() */
-- 
cgit v1.2.3


From 9af86f9338949a9369bda5e6fed69347d1813054 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Mon, 9 Jul 2018 18:10:19 +0100
Subject: net: core: fix use-after-free in __netif_receive_skb_list_core

__netif_receive_skb_core can free the skb, so we have to use the dequeue-
 enqueue model when calling it from __netif_receive_skb_list_core.

Fixes: 88eb1944e18c ("net: core: propagate SKB lists through packet_type lookup")
Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index ce4583564e00..d13cddcac41f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4830,23 +4830,28 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo
 	struct list_head sublist;
 	struct sk_buff *skb, *next;
 
+	INIT_LIST_HEAD(&sublist);
 	list_for_each_entry_safe(skb, next, head, list) {
 		struct net_device *orig_dev = skb->dev;
 		struct packet_type *pt_prev = NULL;
 
+		list_del(&skb->list);
 		__netif_receive_skb_core(skb, pfmemalloc, &pt_prev);
+		if (!pt_prev)
+			continue;
 		if (pt_curr != pt_prev || od_curr != orig_dev) {
 			/* dispatch old sublist */
-			list_cut_before(&sublist, head, &skb->list);
 			__netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr);
 			/* start new sublist */
+			INIT_LIST_HEAD(&sublist);
 			pt_curr = pt_prev;
 			od_curr = orig_dev;
 		}
+		list_add_tail(&skb->list, &sublist);
 	}
 
 	/* dispatch final sublist */
-	__netif_receive_skb_list_ptype(head, pt_curr, od_curr);
+	__netif_receive_skb_list_ptype(&sublist, pt_curr, od_curr);
 }
 
 static int __netif_receive_skb(struct sk_buff *skb)
-- 
cgit v1.2.3


From 82edc7e8b8c06151bdc653935bc13b83e2f0fcfa Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Mon, 9 Jul 2018 15:39:27 -0700
Subject: drm/i915: Update DRIVER_DATE to 20180709

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index fcb8f49a9b8a..a90a37ce2ef9 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -86,8 +86,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180620"
-#define DRIVER_TIMESTAMP	1529529048
+#define DRIVER_DATE		"20180709"
+#define DRIVER_TIMESTAMP	1531175967
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
-- 
cgit v1.2.3


From 95765a6ca1288121ddcbf07cd60ec65341829ddc Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Mon, 9 Jul 2018 09:45:14 +0200
Subject: tcp: remove SG-related comment in tcp_sendmsg()

Since commit 74d4a8f8d378 ("tcp: remove sk_can_gso() use"), the code
doesn't care whether the interface supports SG.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c4082cd50257..e3704a49164b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1274,9 +1274,6 @@ restart:
 			int linear;
 
 new_segment:
-			/* Allocate new segment. If the interface is SG,
-			 * allocate skb fitting to single page.
-			 */
 			if (!sk_stream_memory_free(sk))
 				goto wait_for_sndbuf;
 
-- 
cgit v1.2.3


From eec4edc9ee08fe5c2f219b4fab7aed71b409e196 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 4 Jul 2018 10:28:47 -0700
Subject: net/mlx5: Use 2-factor allocator calls

This restores the use of 2-factor allocation helpers that were already
fixed treewide. Please do not use open-coded multiplication; prefer,
instead, using 2-factor allocation helpers.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bbd2fd0b2e06..c7791d036e9f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -349,7 +349,8 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 {
 	int wq_sz = mlx5_wq_ll_get_size(&rq->mpwqe.wq);
 
-	rq->mpwqe.info = kvzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
+	rq->mpwqe.info = kvzalloc_node(array_size(wq_sz,
+						  sizeof(*rq->mpwqe.info)),
 				       GFP_KERNEL, cpu_to_node(c->cpu));
 	if (!rq->mpwqe.info)
 		return -ENOMEM;
@@ -969,7 +970,7 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.di = kvzalloc_node(sizeof(*sq->db.di) * wq_sz,
+	sq->db.di = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.di)),
 				  GFP_KERNEL, numa);
 	if (!sq->db.di) {
 		mlx5e_free_xdpsq_db(sq);
@@ -1028,7 +1029,8 @@ static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa)
 {
 	u8 wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.ico_wqe = kvzalloc_node(sizeof(*sq->db.ico_wqe) * wq_sz,
+	sq->db.ico_wqe = kvzalloc_node(array_size(wq_sz,
+						  sizeof(*sq->db.ico_wqe)),
 				       GFP_KERNEL, numa);
 	if (!sq->db.ico_wqe)
 		return -ENOMEM;
@@ -1083,9 +1085,11 @@ static int mlx5e_alloc_txqsq_db(struct mlx5e_txqsq *sq, int numa)
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 	int df_sz = wq_sz * MLX5_SEND_WQEBB_NUM_DS;
 
-	sq->db.dma_fifo = kvzalloc_node(df_sz * sizeof(*sq->db.dma_fifo),
+	sq->db.dma_fifo = kvzalloc_node(array_size(df_sz,
+						   sizeof(*sq->db.dma_fifo)),
 					GFP_KERNEL, numa);
-	sq->db.wqe_info = kvzalloc_node(wq_sz * sizeof(*sq->db.wqe_info),
+	sq->db.wqe_info = kvzalloc_node(array_size(wq_sz,
+						   sizeof(*sq->db.wqe_info)),
 					GFP_KERNEL, numa);
 	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
 		mlx5e_free_txqsq_db(sq);
-- 
cgit v1.2.3


From ebcff74386e6fbfe1d5dc406b99db63481f9c2c7 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:16 +0300
Subject: mlxsw: spectrum_kvdl: Push out KVD linear management into ops

In Spectrum-2 there is a different implementation of KVD linear
management. Unlike in Spectrum where there is a single index space,
in Spectrum-2 the indexes are per-resource. Also there is need to
explicitly tell HW that an entry is no longer used.
So push out the existing implementation into spectrum1_kvdl.c and
prepare ops infrastructure to allow new implementation in a follow-up.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   9 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |   3 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  21 +-
 .../net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c   | 455 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_kvdl.c    | 421 ++-----------------
 5 files changed, 516 insertions(+), 393 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 0cadcabfe86f..546a13c0974f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -15,10 +15,11 @@ mlxsw_switchx2-objs		:= switchx2.o
 obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o spectrum_router.o \
-				   spectrum_kvdl.o spectrum_acl_tcam.o \
-				   spectrum_acl.o spectrum_flower.o \
-				   spectrum_cnt.o spectrum_fid.o \
-				   spectrum_ipip.o spectrum_acl_flex_actions.o \
+				   spectrum1_kvdl.o spectrum_kvdl.o \
+				   spectrum_acl_tcam.o spectrum_acl.o \
+				   spectrum_flower.o spectrum_cnt.o \
+				   spectrum_fid.o spectrum_ipip.o \
+				   spectrum_acl_flex_actions.o \
 				   spectrum_mr.o spectrum_mr_tcam.o \
 				   spectrum_qdisc.o spectrum_span.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index cba0e9ba7dea..bb8ed98d4861 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3621,6 +3621,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
+	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
 	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
 
 	mlxsw_sp->core = mlxsw_core;
@@ -3880,7 +3881,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 	if (err)
 		return err;
 
-	err = mlxsw_sp_kvdl_resources_register(mlxsw_core);
+	err = mlxsw_sp1_kvdl_resources_register(mlxsw_core);
 	if  (err)
 		return err;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f5294c9a4c92..334cdb6a7010 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -145,6 +145,7 @@ struct mlxsw_sp_acl;
 struct mlxsw_sp_counter_pool;
 struct mlxsw_sp_fid_core;
 struct mlxsw_sp_kvdl;
+struct mlxsw_sp_kvdl_ops;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
@@ -168,6 +169,7 @@ struct mlxsw_sp {
 		struct mlxsw_sp_span_entry *entries;
 		int entries_count;
 	} span;
+	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
 	const struct mlxsw_afa_ops *afa_ops;
 };
 
@@ -436,6 +438,20 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 
 /* spectrum_kvdl.c */
+struct mlxsw_sp_kvdl_ops {
+	size_t priv_size;
+	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	int (*alloc)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		     unsigned int entry_count, u32 *p_entry_index);
+	void (*free)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		     int entry_index);
+	int (*alloc_size_query)(struct mlxsw_sp *mlxsw_sp, void *priv,
+				unsigned int entry_count,
+				unsigned int *p_alloc_size);
+	int (*resources_register)(struct mlxsw_sp *mlxsw_sp, void *priv);
+};
+
 int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
@@ -444,7 +460,10 @@ void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
 int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
 				   unsigned int entry_count,
 				   unsigned int *p_alloc_size);
-int mlxsw_sp_kvdl_resources_register(struct mlxsw_core *mlxsw_core);
+
+/* spectrum1_kvdl.c */
+extern const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops;
+int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core);
 
 struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
new file mode 100644
index 000000000000..afcadaad8edd
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
@@ -0,0 +1,455 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum.h"
+
+#define MLXSW_SP1_KVDL_SINGLE_BASE 0
+#define MLXSW_SP1_KVDL_SINGLE_SIZE 16384
+#define MLXSW_SP1_KVDL_SINGLE_END \
+	(MLXSW_SP1_KVDL_SINGLE_SIZE + MLXSW_SP1_KVDL_SINGLE_BASE - 1)
+
+#define MLXSW_SP1_KVDL_CHUNKS_BASE \
+	(MLXSW_SP1_KVDL_SINGLE_BASE + MLXSW_SP1_KVDL_SINGLE_SIZE)
+#define MLXSW_SP1_KVDL_CHUNKS_SIZE 49152
+#define MLXSW_SP1_KVDL_CHUNKS_END \
+	(MLXSW_SP1_KVDL_CHUNKS_SIZE + MLXSW_SP1_KVDL_CHUNKS_BASE - 1)
+
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE \
+	(MLXSW_SP1_KVDL_CHUNKS_BASE + MLXSW_SP1_KVDL_CHUNKS_SIZE)
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE \
+	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE)
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_END \
+	(MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP1_KVDL_LARGE_CHUNKS_BASE - 1)
+
+#define MLXSW_SP1_KVDL_SINGLE_ALLOC_SIZE 1
+#define MLXSW_SP1_KVDL_CHUNKS_ALLOC_SIZE 32
+#define MLXSW_SP1_KVDL_LARGE_CHUNKS_ALLOC_SIZE 512
+
+struct mlxsw_sp1_kvdl_part_info {
+	unsigned int part_index;
+	unsigned int start_index;
+	unsigned int end_index;
+	unsigned int alloc_size;
+	enum mlxsw_sp_resource_id resource_id;
+};
+
+enum mlxsw_sp1_kvdl_part_id {
+	MLXSW_SP1_KVDL_PART_ID_SINGLE,
+	MLXSW_SP1_KVDL_PART_ID_CHUNKS,
+	MLXSW_SP1_KVDL_PART_ID_LARGE_CHUNKS,
+};
+
+#define MLXSW_SP1_KVDL_PART_INFO(id)				\
+[MLXSW_SP1_KVDL_PART_ID_##id] = {				\
+	.start_index = MLXSW_SP1_KVDL_##id##_BASE,		\
+	.end_index = MLXSW_SP1_KVDL_##id##_END,			\
+	.alloc_size = MLXSW_SP1_KVDL_##id##_ALLOC_SIZE,		\
+	.resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_##id,	\
+}
+
+static const struct mlxsw_sp1_kvdl_part_info mlxsw_sp1_kvdl_parts_info[] = {
+	MLXSW_SP1_KVDL_PART_INFO(SINGLE),
+	MLXSW_SP1_KVDL_PART_INFO(CHUNKS),
+	MLXSW_SP1_KVDL_PART_INFO(LARGE_CHUNKS),
+};
+
+#define MLXSW_SP1_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp1_kvdl_parts_info)
+
+struct mlxsw_sp1_kvdl_part {
+	struct mlxsw_sp1_kvdl_part_info info;
+	unsigned long usage[0];	/* Entries */
+};
+
+struct mlxsw_sp1_kvdl {
+	struct mlxsw_sp1_kvdl_part *parts[MLXSW_SP1_KVDL_PARTS_INFO_LEN];
+};
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_alloc_size_part(struct mlxsw_sp1_kvdl *kvdl,
+			       unsigned int alloc_size)
+{
+	struct mlxsw_sp1_kvdl_part *part, *min_part = NULL;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+		part = kvdl->parts[i];
+		if (alloc_size <= part->info.alloc_size &&
+		    (!min_part ||
+		     part->info.alloc_size <= min_part->info.alloc_size))
+			min_part = part;
+	}
+
+	return min_part ?: ERR_PTR(-ENOBUFS);
+}
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_index_part(struct mlxsw_sp1_kvdl *kvdl, u32 kvdl_index)
+{
+	struct mlxsw_sp1_kvdl_part *part;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+		part = kvdl->parts[i];
+		if (kvdl_index >= part->info.start_index &&
+		    kvdl_index <= part->info.end_index)
+			return part;
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static u32
+mlxsw_sp1_kvdl_to_kvdl_index(const struct mlxsw_sp1_kvdl_part_info *info,
+			     unsigned int entry_index)
+{
+	return info->start_index + entry_index * info->alloc_size;
+}
+
+static unsigned int
+mlxsw_sp1_kvdl_to_entry_index(const struct mlxsw_sp1_kvdl_part_info *info,
+			      u32 kvdl_index)
+{
+	return (kvdl_index - info->start_index) / info->alloc_size;
+}
+
+static int mlxsw_sp1_kvdl_part_alloc(struct mlxsw_sp1_kvdl_part *part,
+				     u32 *p_kvdl_index)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+	unsigned int entry_index, nr_entries;
+
+	nr_entries = (info->end_index - info->start_index + 1) /
+		     info->alloc_size;
+	entry_index = find_first_zero_bit(part->usage, nr_entries);
+	if (entry_index == nr_entries)
+		return -ENOBUFS;
+	__set_bit(entry_index, part->usage);
+
+	*p_kvdl_index = mlxsw_sp1_kvdl_to_kvdl_index(info, entry_index);
+
+	return 0;
+}
+
+static void mlxsw_sp1_kvdl_part_free(struct mlxsw_sp1_kvdl_part *part,
+				     u32 kvdl_index)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+	unsigned int entry_index;
+
+	entry_index = mlxsw_sp1_kvdl_to_entry_index(info, kvdl_index);
+	__clear_bit(entry_index, part->usage);
+}
+
+static int mlxsw_sp1_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
+				unsigned int entry_count,
+				u32 *p_entry_index)
+{
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	/* Find partition with smallest allocation size satisfying the
+	 * requested size.
+	 */
+	part = mlxsw_sp1_kvdl_alloc_size_part(kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	return mlxsw_sp1_kvdl_part_alloc(part, p_entry_index);
+}
+
+static void mlxsw_sp1_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
+				int entry_index)
+{
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = mlxsw_sp1_kvdl_index_part(kvdl, entry_index);
+	if (IS_ERR(part))
+		return;
+	mlxsw_sp1_kvdl_part_free(part, entry_index);
+}
+
+static int mlxsw_sp1_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+					   void *priv, unsigned int entry_count,
+					   unsigned int *p_alloc_size)
+{
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = mlxsw_sp1_kvdl_alloc_size_part(kvdl, entry_count);
+	if (IS_ERR(part))
+		return PTR_ERR(part);
+
+	*p_alloc_size = part->info.alloc_size;
+
+	return 0;
+}
+
+static void mlxsw_sp1_kvdl_part_update(struct mlxsw_sp1_kvdl_part *part,
+				       struct mlxsw_sp1_kvdl_part *part_prev,
+				       unsigned int size)
+{
+	if (!part_prev) {
+		part->info.end_index = size - 1;
+	} else {
+		part->info.start_index = part_prev->info.end_index + 1;
+		part->info.end_index = part->info.start_index + size - 1;
+	}
+}
+
+static struct mlxsw_sp1_kvdl_part *
+mlxsw_sp1_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp1_kvdl_part_info *info,
+			 struct mlxsw_sp1_kvdl_part *part_prev)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp1_kvdl_part *part;
+	bool need_update = true;
+	unsigned int nr_entries;
+	size_t usage_size;
+	u64 resource_size;
+	int err;
+
+	err = devlink_resource_size_get(devlink, info->resource_id,
+					&resource_size);
+	if (err) {
+		need_update = false;
+		resource_size = info->end_index - info->start_index + 1;
+	}
+
+	nr_entries = div_u64(resource_size, info->alloc_size);
+	usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
+	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+	if (!part)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(&part->info, info, sizeof(part->info));
+
+	if (need_update)
+		mlxsw_sp1_kvdl_part_update(part, part_prev, resource_size);
+	return part;
+}
+
+static void mlxsw_sp1_kvdl_part_fini(struct mlxsw_sp1_kvdl_part *part)
+{
+	kfree(part);
+}
+
+static int mlxsw_sp1_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp1_kvdl *kvdl)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info;
+	struct mlxsw_sp1_kvdl_part *part_prev = NULL;
+	int err, i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++) {
+		info = &mlxsw_sp1_kvdl_parts_info[i];
+		kvdl->parts[i] = mlxsw_sp1_kvdl_part_init(mlxsw_sp, info,
+							  part_prev);
+		if (IS_ERR(kvdl->parts[i])) {
+			err = PTR_ERR(kvdl->parts[i]);
+			goto err_kvdl_part_init;
+		}
+		part_prev = kvdl->parts[i];
+	}
+	return 0;
+
+err_kvdl_part_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp1_kvdl_part_fini(kvdl->parts[i]);
+	return err;
+}
+
+static void mlxsw_sp1_kvdl_parts_fini(struct mlxsw_sp1_kvdl *kvdl)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++)
+		mlxsw_sp1_kvdl_part_fini(kvdl->parts[i]);
+}
+
+static u64 mlxsw_sp1_kvdl_part_occ(struct mlxsw_sp1_kvdl_part *part)
+{
+	const struct mlxsw_sp1_kvdl_part_info *info = &part->info;
+	unsigned int nr_entries;
+	int bit = -1;
+	u64 occ = 0;
+
+	nr_entries = (info->end_index -
+		      info->start_index + 1) /
+		      info->alloc_size;
+	while ((bit = find_next_bit(part->usage, nr_entries, bit + 1))
+		< nr_entries)
+		occ += info->alloc_size;
+	return occ;
+}
+
+static u64 mlxsw_sp1_kvdl_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	u64 occ = 0;
+	int i;
+
+	for (i = 0; i < MLXSW_SP1_KVDL_PARTS_INFO_LEN; i++)
+		occ += mlxsw_sp1_kvdl_part_occ(kvdl->parts[i]);
+
+	return occ;
+}
+
+static u64 mlxsw_sp1_kvdl_single_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_SINGLE];
+	return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static u64 mlxsw_sp1_kvdl_chunks_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_CHUNKS];
+	return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static u64 mlxsw_sp1_kvdl_large_chunks_occ_get(void *priv)
+{
+	const struct mlxsw_sp1_kvdl *kvdl = priv;
+	struct mlxsw_sp1_kvdl_part *part;
+
+	part = kvdl->parts[MLXSW_SP1_KVDL_PART_ID_LARGE_CHUNKS];
+	return mlxsw_sp1_kvdl_part_occ(part);
+}
+
+static int mlxsw_sp1_kvdl_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+	int err;
+
+	err = mlxsw_sp1_kvdl_parts_init(mlxsw_sp, kvdl);
+	if (err)
+		return err;
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR,
+					  mlxsw_sp1_kvdl_occ_get,
+					  kvdl);
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
+					  mlxsw_sp1_kvdl_single_occ_get,
+					  kvdl);
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
+					  mlxsw_sp1_kvdl_chunks_occ_get,
+					  kvdl);
+	devlink_resource_occ_get_register(devlink,
+					  MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
+					  mlxsw_sp1_kvdl_large_chunks_occ_get,
+					  kvdl);
+	return 0;
+}
+
+static void mlxsw_sp1_kvdl_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
+	struct mlxsw_sp1_kvdl *kvdl = priv;
+
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS);
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS);
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE);
+	devlink_resource_occ_get_unregister(devlink,
+					    MLXSW_SP_RESOURCE_KVD_LINEAR);
+	mlxsw_sp1_kvdl_parts_fini(kvdl);
+}
+
+const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops = {
+	.priv_size = sizeof(struct mlxsw_sp1_kvdl),
+	.init = mlxsw_sp1_kvdl_init,
+	.fini = mlxsw_sp1_kvdl_fini,
+	.alloc = mlxsw_sp1_kvdl_alloc,
+	.free = mlxsw_sp1_kvdl_free,
+	.alloc_size_query = mlxsw_sp1_kvdl_alloc_size_query,
+};
+
+int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core)
+{
+	struct devlink *devlink = priv_to_devlink(mlxsw_core);
+	static struct devlink_resource_size_params size_params;
+	u32 kvdl_max_size;
+	int err;
+
+	kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) -
+			MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) -
+			MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE);
+
+	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+					  MLXSW_SP1_KVDL_SINGLE_ALLOC_SIZE,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES,
+					MLXSW_SP1_KVDL_SINGLE_SIZE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR,
+					&size_params);
+	if (err)
+		return err;
+
+	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+					  MLXSW_SP1_KVDL_CHUNKS_ALLOC_SIZE,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS,
+					MLXSW_SP1_KVDL_CHUNKS_SIZE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
+					MLXSW_SP_RESOURCE_KVD_LINEAR,
+					&size_params);
+	if (err)
+		return err;
+
+	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
+					  MLXSW_SP1_KVDL_LARGE_CHUNKS_ALLOC_SIZE,
+					  DEVLINK_RESOURCE_UNIT_ENTRY);
+	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS,
+					MLXSW_SP1_KVDL_LARGE_CHUNKS_SIZE,
+					MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
+					MLXSW_SP_RESOURCE_KVD_LINEAR,
+					&size_params);
+	return err;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index fe4327f547d2..2b514e47ca2b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -1,7 +1,7 @@
 /*
  * drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2018 Jiri Pirko <jiri@mellanox.com>
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -33,422 +33,69 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/bitops.h>
+#include <linux/slab.h>
 
 #include "spectrum.h"
 
-#define MLXSW_SP_KVDL_SINGLE_BASE 0
-#define MLXSW_SP_KVDL_SINGLE_SIZE 16384
-#define MLXSW_SP_KVDL_SINGLE_END \
-	(MLXSW_SP_KVDL_SINGLE_SIZE + MLXSW_SP_KVDL_SINGLE_BASE - 1)
-
-#define MLXSW_SP_KVDL_CHUNKS_BASE \
-	(MLXSW_SP_KVDL_SINGLE_BASE + MLXSW_SP_KVDL_SINGLE_SIZE)
-#define MLXSW_SP_KVDL_CHUNKS_SIZE 49152
-#define MLXSW_SP_KVDL_CHUNKS_END \
-	(MLXSW_SP_KVDL_CHUNKS_SIZE + MLXSW_SP_KVDL_CHUNKS_BASE - 1)
-
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_BASE \
-	(MLXSW_SP_KVDL_CHUNKS_BASE + MLXSW_SP_KVDL_CHUNKS_SIZE)
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE \
-	(MLXSW_SP_KVD_LINEAR_SIZE - MLXSW_SP_KVDL_LARGE_CHUNKS_BASE)
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_END \
-	(MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE + MLXSW_SP_KVDL_LARGE_CHUNKS_BASE - 1)
-
-#define MLXSW_SP_KVDL_SINGLE_ALLOC_SIZE 1
-#define MLXSW_SP_KVDL_CHUNKS_ALLOC_SIZE 32
-#define MLXSW_SP_KVDL_LARGE_CHUNKS_ALLOC_SIZE 512
-
-struct mlxsw_sp_kvdl_part_info {
-	unsigned int part_index;
-	unsigned int start_index;
-	unsigned int end_index;
-	unsigned int alloc_size;
-	enum mlxsw_sp_resource_id resource_id;
-};
-
-enum mlxsw_sp_kvdl_part_id {
-	MLXSW_SP_KVDL_PART_ID_SINGLE,
-	MLXSW_SP_KVDL_PART_ID_CHUNKS,
-	MLXSW_SP_KVDL_PART_ID_LARGE_CHUNKS,
-};
-
-#define MLXSW_SP_KVDL_PART_INFO(id)				\
-[MLXSW_SP_KVDL_PART_ID_##id] = {				\
-	.start_index = MLXSW_SP_KVDL_##id##_BASE,		\
-	.end_index = MLXSW_SP_KVDL_##id##_END,			\
-	.alloc_size = MLXSW_SP_KVDL_##id##_ALLOC_SIZE,		\
-	.resource_id = MLXSW_SP_RESOURCE_KVD_LINEAR_##id,	\
-}
-
-static const struct mlxsw_sp_kvdl_part_info mlxsw_sp_kvdl_parts_info[] = {
-	MLXSW_SP_KVDL_PART_INFO(SINGLE),
-	MLXSW_SP_KVDL_PART_INFO(CHUNKS),
-	MLXSW_SP_KVDL_PART_INFO(LARGE_CHUNKS),
-};
-
-#define MLXSW_SP_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp_kvdl_parts_info)
-
-struct mlxsw_sp_kvdl_part {
-	struct mlxsw_sp_kvdl_part_info info;
-	unsigned long usage[0];	/* Entries */
-};
-
 struct mlxsw_sp_kvdl {
-	struct mlxsw_sp_kvdl_part *parts[MLXSW_SP_KVDL_PARTS_INFO_LEN];
+	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
 };
 
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_alloc_size_part(struct mlxsw_sp_kvdl *kvdl,
-			      unsigned int alloc_size)
-{
-	struct mlxsw_sp_kvdl_part *part, *min_part = NULL;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
-		part = kvdl->parts[i];
-		if (alloc_size <= part->info.alloc_size &&
-		    (!min_part ||
-		     part->info.alloc_size <= min_part->info.alloc_size))
-			min_part = part;
-	}
-
-	return min_part ?: ERR_PTR(-ENOBUFS);
-}
-
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_index_part(struct mlxsw_sp_kvdl *kvdl, u32 kvdl_index)
-{
-	struct mlxsw_sp_kvdl_part *part;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
-		part = kvdl->parts[i];
-		if (kvdl_index >= part->info.start_index &&
-		    kvdl_index <= part->info.end_index)
-			return part;
-	}
-
-	return ERR_PTR(-EINVAL);
-}
-
-static u32
-mlxsw_sp_entry_index_kvdl_index(const struct mlxsw_sp_kvdl_part_info *info,
-				unsigned int entry_index)
-{
-	return info->start_index + entry_index * info->alloc_size;
-}
-
-static unsigned int
-mlxsw_sp_kvdl_index_entry_index(const struct mlxsw_sp_kvdl_part_info *info,
-				u32 kvdl_index)
-{
-	return (kvdl_index - info->start_index) / info->alloc_size;
-}
-
-static int mlxsw_sp_kvdl_part_alloc(struct mlxsw_sp_kvdl_part *part,
-				    u32 *p_kvdl_index)
+int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
 {
-	const struct mlxsw_sp_kvdl_part_info *info = &part->info;
-	unsigned int entry_index, nr_entries;
-
-	nr_entries = (info->end_index - info->start_index + 1) /
-		     info->alloc_size;
-	entry_index = find_first_zero_bit(part->usage, nr_entries);
-	if (entry_index == nr_entries)
-		return -ENOBUFS;
-	__set_bit(entry_index, part->usage);
+	const struct mlxsw_sp_kvdl_ops *kvdl_ops = mlxsw_sp->kvdl_ops;
+	struct mlxsw_sp_kvdl *kvdl;
+	int err;
 
-	*p_kvdl_index = mlxsw_sp_entry_index_kvdl_index(info, entry_index);
+	kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl) + kvdl_ops->priv_size,
+		       GFP_KERNEL);
+	if (!kvdl)
+		return -ENOMEM;
+	kvdl->kvdl_ops = kvdl_ops;
+	mlxsw_sp->kvdl = kvdl;
 
+	err = kvdl_ops->init(mlxsw_sp, kvdl->priv);
+	if (err)
+		goto err_init;
 	return 0;
+
+err_init:
+	kfree(kvdl);
+	return err;
 }
 
-static void mlxsw_sp_kvdl_part_free(struct mlxsw_sp_kvdl_part *part,
-				    u32 kvdl_index)
+void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
 {
-	const struct mlxsw_sp_kvdl_part_info *info = &part->info;
-	unsigned int entry_index;
+	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	entry_index = mlxsw_sp_kvdl_index_entry_index(info, kvdl_index);
-	__clear_bit(entry_index, part->usage);
+	kvdl->kvdl_ops->fini(mlxsw_sp, kvdl->priv);
+	kfree(kvdl);
 }
 
 int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
 			u32 *p_entry_index)
 {
-	struct mlxsw_sp_kvdl_part *part;
-
-	/* Find partition with smallest allocation size satisfying the
-	 * requested size.
-	 */
-	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
-	if (IS_ERR(part))
-		return PTR_ERR(part);
+	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	return mlxsw_sp_kvdl_part_alloc(part, p_entry_index);
+	return kvdl->kvdl_ops->alloc(mlxsw_sp, kvdl->priv,
+				     entry_count, p_entry_index);
 }
 
 void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
 {
-	struct mlxsw_sp_kvdl_part *part;
+	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	part = mlxsw_sp_kvdl_index_part(mlxsw_sp->kvdl, entry_index);
-	if (IS_ERR(part))
-		return;
-	mlxsw_sp_kvdl_part_free(part, entry_index);
+	kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, entry_index);
 }
 
 int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
 				   unsigned int entry_count,
 				   unsigned int *p_alloc_size)
-{
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp_kvdl_alloc_size_part(mlxsw_sp->kvdl, entry_count);
-	if (IS_ERR(part))
-		return PTR_ERR(part);
-
-	*p_alloc_size = part->info.alloc_size;
-
-	return 0;
-}
-
-static void mlxsw_sp_kvdl_part_update(struct mlxsw_sp_kvdl_part *part,
-				      struct mlxsw_sp_kvdl_part *part_prev,
-				      unsigned int size)
-{
-
-	if (!part_prev) {
-		part->info.end_index = size - 1;
-	} else {
-		part->info.start_index = part_prev->info.end_index + 1;
-		part->info.end_index = part->info.start_index + size - 1;
-	}
-}
-
-static struct mlxsw_sp_kvdl_part *
-mlxsw_sp_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
-			const struct mlxsw_sp_kvdl_part_info *info,
-			struct mlxsw_sp_kvdl_part *part_prev)
-{
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
-	struct mlxsw_sp_kvdl_part *part;
-	bool need_update = true;
-	unsigned int nr_entries;
-	size_t usage_size;
-	u64 resource_size;
-	int err;
-
-	err = devlink_resource_size_get(devlink, info->resource_id,
-					&resource_size);
-	if (err) {
-		need_update = false;
-		resource_size = info->end_index - info->start_index + 1;
-	}
-
-	nr_entries = div_u64(resource_size, info->alloc_size);
-	usage_size = BITS_TO_LONGS(nr_entries) * sizeof(unsigned long);
-	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
-	if (!part)
-		return ERR_PTR(-ENOMEM);
-
-	memcpy(&part->info, info, sizeof(part->info));
-
-	if (need_update)
-		mlxsw_sp_kvdl_part_update(part, part_prev, resource_size);
-	return part;
-}
-
-static void mlxsw_sp_kvdl_part_fini(struct mlxsw_sp_kvdl_part *part)
-{
-	kfree(part);
-}
-
-static int mlxsw_sp_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
-	const struct mlxsw_sp_kvdl_part_info *info;
-	struct mlxsw_sp_kvdl_part *part_prev = NULL;
-	int err, i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++) {
-		info = &mlxsw_sp_kvdl_parts_info[i];
-		kvdl->parts[i] = mlxsw_sp_kvdl_part_init(mlxsw_sp, info,
-							 part_prev);
-		if (IS_ERR(kvdl->parts[i])) {
-			err = PTR_ERR(kvdl->parts[i]);
-			goto err_kvdl_part_init;
-		}
-		part_prev = kvdl->parts[i];
-	}
-	return 0;
-
-err_kvdl_part_init:
-	for (i--; i >= 0; i--)
-		mlxsw_sp_kvdl_part_fini(kvdl->parts[i]);
-	return err;
-}
-
-static void mlxsw_sp_kvdl_parts_fini(struct mlxsw_sp *mlxsw_sp)
-{
-	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++)
-		mlxsw_sp_kvdl_part_fini(kvdl->parts[i]);
-}
-
-static u64 mlxsw_sp_kvdl_part_occ(struct mlxsw_sp_kvdl_part *part)
-{
-	const struct mlxsw_sp_kvdl_part_info *info = &part->info;
-	unsigned int nr_entries;
-	int bit = -1;
-	u64 occ = 0;
-
-	nr_entries = (info->end_index -
-		      info->start_index + 1) /
-		      info->alloc_size;
-	while ((bit = find_next_bit(part->usage, nr_entries, bit + 1))
-		< nr_entries)
-		occ += info->alloc_size;
-	return occ;
-}
-
-static u64 mlxsw_sp_kvdl_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	u64 occ = 0;
-	int i;
-
-	for (i = 0; i < MLXSW_SP_KVDL_PARTS_INFO_LEN; i++)
-		occ += mlxsw_sp_kvdl_part_occ(mlxsw_sp->kvdl->parts[i]);
-
-	return occ;
-}
-
-static u64 mlxsw_sp_kvdl_single_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_SINGLE];
-	return mlxsw_sp_kvdl_part_occ(part);
-}
-
-static u64 mlxsw_sp_kvdl_chunks_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_CHUNKS];
-	return mlxsw_sp_kvdl_part_occ(part);
-}
-
-static u64 mlxsw_sp_kvdl_large_chunks_occ_get(void *priv)
-{
-	const struct mlxsw_sp *mlxsw_sp = priv;
-	struct mlxsw_sp_kvdl_part *part;
-
-	part = mlxsw_sp->kvdl->parts[MLXSW_SP_KVDL_PART_ID_LARGE_CHUNKS];
-	return mlxsw_sp_kvdl_part_occ(part);
-}
-
-int mlxsw_sp_kvdl_resources_register(struct mlxsw_core *mlxsw_core)
-{
-	struct devlink *devlink = priv_to_devlink(mlxsw_core);
-	static struct devlink_resource_size_params size_params;
-	u32 kvdl_max_size;
-	int err;
-
-	kvdl_max_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE) -
-			MLXSW_CORE_RES_GET(mlxsw_core, KVD_SINGLE_MIN_SIZE) -
-			MLXSW_CORE_RES_GET(mlxsw_core, KVD_DOUBLE_MIN_SIZE);
-
-	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
-					  MLXSW_SP_KVDL_SINGLE_ALLOC_SIZE,
-					  DEVLINK_RESOURCE_UNIT_ENTRY);
-	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_SINGLES,
-					MLXSW_SP_KVDL_SINGLE_SIZE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR,
-					&size_params);
-	if (err)
-		return err;
-
-	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
-					  MLXSW_SP_KVDL_CHUNKS_ALLOC_SIZE,
-					  DEVLINK_RESOURCE_UNIT_ENTRY);
-	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_CHUNKS,
-					MLXSW_SP_KVDL_CHUNKS_SIZE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
-					MLXSW_SP_RESOURCE_KVD_LINEAR,
-					&size_params);
-	if (err)
-		return err;
-
-	devlink_resource_size_params_init(&size_params, 0, kvdl_max_size,
-					  MLXSW_SP_KVDL_LARGE_CHUNKS_ALLOC_SIZE,
-					  DEVLINK_RESOURCE_UNIT_ENTRY);
-	err = devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD_LINEAR_LARGE_CHUNKS,
-					MLXSW_SP_KVDL_LARGE_CHUNKS_SIZE,
-					MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
-					MLXSW_SP_RESOURCE_KVD_LINEAR,
-					&size_params);
-	return err;
-}
-
-int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp)
-{
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
-	struct mlxsw_sp_kvdl *kvdl;
-	int err;
-
-	kvdl = kzalloc(sizeof(*mlxsw_sp->kvdl), GFP_KERNEL);
-	if (!kvdl)
-		return -ENOMEM;
-	mlxsw_sp->kvdl = kvdl;
-
-	err = mlxsw_sp_kvdl_parts_init(mlxsw_sp);
-	if (err)
-		goto err_kvdl_parts_init;
-
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR,
-					  mlxsw_sp_kvdl_occ_get,
-					  mlxsw_sp);
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE,
-					  mlxsw_sp_kvdl_single_occ_get,
-					  mlxsw_sp);
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS,
-					  mlxsw_sp_kvdl_chunks_occ_get,
-					  mlxsw_sp);
-	devlink_resource_occ_get_register(devlink,
-					  MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS,
-					  mlxsw_sp_kvdl_large_chunks_occ_get,
-					  mlxsw_sp);
-
-	return 0;
-
-err_kvdl_parts_init:
-	kfree(mlxsw_sp->kvdl);
-	return err;
-}
-
-void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
-{
-	struct devlink *devlink = priv_to_devlink(mlxsw_sp->core);
 
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR_LARGE_CHUNKS);
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR_CHUNKS);
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR_SINGLE);
-	devlink_resource_occ_get_unregister(devlink,
-					    MLXSW_SP_RESOURCE_KVD_LINEAR);
-	mlxsw_sp_kvdl_parts_fini(mlxsw_sp);
-	kfree(mlxsw_sp->kvdl);
+	return kvdl->kvdl_ops->alloc_size_query(mlxsw_sp, kvdl->priv,
+						entry_count, p_alloc_size);
 }
-- 
cgit v1.2.3


From 4b6b18692aec205b98dd333938b714af9d7aefe1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:17 +0300
Subject: mlxsw: spectrum_kvdl: Pass entry type to alloc/free

Future Spectrum-2 KVD linear manager implementation needs to know type
of the entry to alloc and free. So define the types in an enum and
pass it down to alloc and free functions. Once the entry type
is passed down, KVDL common part knows sizes of each entry types,
so replace size function arg with entry count.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 41 ++++++++++++++++++----
 .../net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c   |  6 +++-
 .../mellanox/mlxsw/spectrum_acl_flex_actions.c     | 21 ++++++-----
 .../net/ethernet/mellanox/mlxsw/spectrum_kvdl.c    | 24 +++++++------
 .../net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c |  9 +++--
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 20 +++++++----
 6 files changed, 82 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 334cdb6a7010..a67d1dd8a607 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -438,28 +438,55 @@ mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy(struct mlxsw_sp_rif *rif);
 
 /* spectrum_kvdl.c */
+enum mlxsw_sp_kvdl_entry_type {
+	MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+	MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+	MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+	MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+};
+
+static inline unsigned int
+mlxsw_sp_kvdl_entry_size(enum mlxsw_sp_kvdl_entry_type type)
+{
+	switch (type) {
+	case MLXSW_SP_KVDL_ENTRY_TYPE_ADJ: /* fall through */
+	case MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET: /* fall through */
+	case MLXSW_SP_KVDL_ENTRY_TYPE_PBS: /* fall through */
+	case MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR: /* fall through */
+	default:
+		return 1;
+	}
+}
+
 struct mlxsw_sp_kvdl_ops {
 	size_t priv_size;
 	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
 	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
 	int (*alloc)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		     enum mlxsw_sp_kvdl_entry_type type,
 		     unsigned int entry_count, u32 *p_entry_index);
 	void (*free)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		     enum mlxsw_sp_kvdl_entry_type type,
 		     int entry_index);
 	int (*alloc_size_query)(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
 				unsigned int entry_count,
-				unsigned int *p_alloc_size);
+				unsigned int *p_alloc_count);
 	int (*resources_register)(struct mlxsw_sp *mlxsw_sp, void *priv);
 };
 
 int mlxsw_sp_kvdl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp);
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
-			u32 *p_entry_index);
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index);
-int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
-				   unsigned int entry_count,
-				   unsigned int *p_alloc_size);
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			unsigned int entry_count, u32 *p_entry_index);
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			int entry_index);
+int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
+				    enum mlxsw_sp_kvdl_entry_type type,
+				    unsigned int entry_count,
+				    unsigned int *p_alloc_count);
 
 /* spectrum1_kvdl.c */
 extern const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
index afcadaad8edd..86e0b993f8b3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
@@ -175,6 +175,7 @@ static void mlxsw_sp1_kvdl_part_free(struct mlxsw_sp1_kvdl_part *part,
 }
 
 static int mlxsw_sp1_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
 				unsigned int entry_count,
 				u32 *p_entry_index)
 {
@@ -192,6 +193,7 @@ static int mlxsw_sp1_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
 }
 
 static void mlxsw_sp1_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
 				int entry_index)
 {
 	struct mlxsw_sp1_kvdl *kvdl = priv;
@@ -204,7 +206,9 @@ static void mlxsw_sp1_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
 }
 
 static int mlxsw_sp1_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
-					   void *priv, unsigned int entry_count,
+					   void *priv,
+					   enum mlxsw_sp_kvdl_entry_type type,
+					   unsigned int entry_count,
 					   unsigned int *p_alloc_size)
 {
 	struct mlxsw_sp1_kvdl *kvdl = priv;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index 5ab070916949..f98fb2c76cd8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -37,8 +37,6 @@
 #include "core_acl_flex_actions.h"
 #include "spectrum_span.h"
 
-#define MLXSW_SP_KVDL_ACT_EXT_SIZE 1
-
 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 				     char *enc_actions, bool is_first)
 {
@@ -53,8 +51,8 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	if (is_first)
 		return 0;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ACT_EXT_SIZE,
-				  &kvdl_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+				  1, &kvdl_index);
 	if (err)
 		return err;
 	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
@@ -65,7 +63,8 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 	return 0;
 
 err_pefa_write:
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   kvdl_index);
 	return err;
 }
 
@@ -76,7 +75,8 @@ static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
 
 	if (is_first)
 		return;
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   kvdl_index);
 }
 
 static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
@@ -87,7 +87,8 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 	u32 kvdl_index;
 	int err;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &kvdl_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+				  1, &kvdl_index);
 	if (err)
 		return err;
 	mlxsw_reg_ppbs_pack(ppbs_pl, kvdl_index, local_port);
@@ -98,7 +99,8 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 	return 0;
 
 err_ppbs_write:
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+			   kvdl_index);
 	return err;
 }
 
@@ -106,7 +108,8 @@ static void mlxsw_sp_act_kvdl_fwd_entry_del(void *priv, u32 kvdl_index)
 {
 	struct mlxsw_sp *mlxsw_sp = priv;
 
-	mlxsw_sp_kvdl_free(mlxsw_sp, kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
+			   kvdl_index);
 }
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index 2b514e47ca2b..3f9130afe5ea 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -74,28 +74,32 @@ void mlxsw_sp_kvdl_fini(struct mlxsw_sp *mlxsw_sp)
 	kfree(kvdl);
 }
 
-int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, unsigned int entry_count,
-			u32 *p_entry_index)
+int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			unsigned int entry_count, u32 *p_entry_index)
 {
 	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	return kvdl->kvdl_ops->alloc(mlxsw_sp, kvdl->priv,
+	return kvdl->kvdl_ops->alloc(mlxsw_sp, kvdl->priv, type,
 				     entry_count, p_entry_index);
 }
 
-void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp, int entry_index)
+void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
+			enum mlxsw_sp_kvdl_entry_type type,
+			int entry_index)
 {
 	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, entry_index);
+	kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, type, entry_index);
 }
 
-int mlxsw_sp_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
-				   unsigned int entry_count,
-				   unsigned int *p_alloc_size)
+int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
+				    enum mlxsw_sp_kvdl_entry_type type,
+				    unsigned int entry_count,
+				    unsigned int *p_alloc_count)
 {
 	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	return kvdl->kvdl_ops->alloc_size_query(mlxsw_sp, kvdl->priv,
-						entry_count, p_alloc_size);
+	return kvdl->kvdl_ops->alloc_size_query(mlxsw_sp, kvdl->priv, type,
+						entry_count, p_alloc_count);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index 4f4c0d311883..d1fd85ade425 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -84,8 +84,6 @@ mlxsw_sp_mr_erif_list_init(struct mlxsw_sp_mr_tcam_erif_list *erif_list)
 	INIT_LIST_HEAD(&erif_list->erif_sublists);
 }
 
-#define MLXSW_SP_KVDL_RIGR2_SIZE 1
-
 static struct mlxsw_sp_mr_erif_sublist *
 mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_mr_tcam_erif_list *erif_list)
@@ -96,8 +94,8 @@ mlxsw_sp_mr_erif_sublist_create(struct mlxsw_sp *mlxsw_sp,
 	erif_sublist = kzalloc(sizeof(*erif_sublist), GFP_KERNEL);
 	if (!erif_sublist)
 		return ERR_PTR(-ENOMEM);
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_RIGR2_SIZE,
-				  &erif_sublist->rigr2_kvdl_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+				  1, &erif_sublist->rigr2_kvdl_index);
 	if (err) {
 		kfree(erif_sublist);
 		return ERR_PTR(err);
@@ -112,7 +110,8 @@ mlxsw_sp_mr_erif_sublist_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_mr_erif_sublist *erif_sublist)
 {
 	list_del(&erif_sublist->list);
-	mlxsw_sp_kvdl_free(mlxsw_sp, erif_sublist->rigr2_kvdl_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
+			   erif_sublist->rigr2_kvdl_index);
 	kfree(erif_sublist);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 79dcadb40857..fb5980e92e3b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1106,7 +1106,8 @@ mlxsw_sp_fib_entry_decap_init(struct mlxsw_sp *mlxsw_sp,
 	u32 tunnel_index;
 	int err;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, 1, &tunnel_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+				  1, &tunnel_index);
 	if (err)
 		return err;
 
@@ -1122,7 +1123,8 @@ static void mlxsw_sp_fib_entry_decap_fini(struct mlxsw_sp *mlxsw_sp,
 	/* Unlink this node from the IPIP entry that it's the decap entry of. */
 	fib_entry->decap.ipip_entry->decap_fib_entry = NULL;
 	fib_entry->decap.ipip_entry = NULL;
-	mlxsw_sp_kvdl_free(mlxsw_sp, fib_entry->decap.tunnel_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+			   fib_entry->decap.tunnel_index);
 }
 
 static struct mlxsw_sp_fib_node *
@@ -3162,8 +3164,9 @@ static int mlxsw_sp_fix_adj_grp_size(struct mlxsw_sp *mlxsw_sp,
 	 * by the device and make sure the request can be satisfied.
 	 */
 	mlxsw_sp_adj_grp_size_round_up(p_adj_grp_size);
-	err = mlxsw_sp_kvdl_alloc_size_query(mlxsw_sp, *p_adj_grp_size,
-					     &alloc_size);
+	err = mlxsw_sp_kvdl_alloc_count_query(mlxsw_sp,
+					      MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+					      *p_adj_grp_size, &alloc_size);
 	if (err)
 		return err;
 	/* It is possible the allocation results in more allocated
@@ -3275,7 +3278,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 		/* No valid allocation size available. */
 		goto set_trap;
 
-	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, ecmp_size, &adj_index);
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+				  ecmp_size, &adj_index);
 	if (err) {
 		/* We ran out of KVD linear space, just set the
 		 * trap and let everything flow through kernel.
@@ -3310,7 +3314,8 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 
 	err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp,
 					     old_adj_index, old_ecmp_size);
-	mlxsw_sp_kvdl_free(mlxsw_sp, old_adj_index);
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+			   old_adj_index);
 	if (err) {
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n");
 		goto set_trap;
@@ -3332,7 +3337,8 @@ set_trap:
 	if (err)
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
 	if (old_adj_index_valid)
-		mlxsw_sp_kvdl_free(mlxsw_sp, nh_grp->adj_index);
+		mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
+				   nh_grp->adj_index);
 }
 
 static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
-- 
cgit v1.2.3


From 0304c00546fce74028ce5e3ea5990e784c67a8a3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:18 +0300
Subject: mlxsw: spectrum_kvdl: Pass entry_count to free function

For the Spectrum-2 KVD linear manager implementation, entry_count will be
needed even for the free function. So pass it down.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h                  | 4 ++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c            | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c | 8 ++++----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c             | 5 +++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c          | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c           | 6 +++---
 6 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a67d1dd8a607..25ea06dc8bff 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -467,7 +467,7 @@ struct mlxsw_sp_kvdl_ops {
 		     unsigned int entry_count, u32 *p_entry_index);
 	void (*free)(struct mlxsw_sp *mlxsw_sp, void *priv,
 		     enum mlxsw_sp_kvdl_entry_type type,
-		     int entry_index);
+		     unsigned int entry_count, int entry_index);
 	int (*alloc_size_query)(struct mlxsw_sp *mlxsw_sp, void *priv,
 				enum mlxsw_sp_kvdl_entry_type type,
 				unsigned int entry_count,
@@ -482,7 +482,7 @@ int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
 			unsigned int entry_count, u32 *p_entry_index);
 void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
 			enum mlxsw_sp_kvdl_entry_type type,
-			int entry_index);
+			unsigned int entry_count, int entry_index);
 int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
 				    enum mlxsw_sp_kvdl_entry_type type,
 				    unsigned int entry_count,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
index 86e0b993f8b3..0d4583894a97 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
@@ -194,7 +194,7 @@ static int mlxsw_sp1_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
 
 static void mlxsw_sp1_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
 				enum mlxsw_sp_kvdl_entry_type type,
-				int entry_index)
+				unsigned int entry_count, int entry_index)
 {
 	struct mlxsw_sp1_kvdl *kvdl = priv;
 	struct mlxsw_sp1_kvdl_part *part;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index f98fb2c76cd8..6a7c3406b724 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -64,7 +64,7 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 
 err_pefa_write:
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
-			   kvdl_index);
+			   1, kvdl_index);
 	return err;
 }
 
@@ -76,7 +76,7 @@ static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
 	if (is_first)
 		return;
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
-			   kvdl_index);
+			   1, kvdl_index);
 }
 
 static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
@@ -100,7 +100,7 @@ static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 
 err_ppbs_write:
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
-			   kvdl_index);
+			   1, kvdl_index);
 	return err;
 }
 
@@ -109,7 +109,7 @@ static void mlxsw_sp_act_kvdl_fwd_entry_del(void *priv, u32 kvdl_index)
 	struct mlxsw_sp *mlxsw_sp = priv;
 
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_PBS,
-			   kvdl_index);
+			   1, kvdl_index);
 }
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index 3f9130afe5ea..fd557585514d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -86,11 +86,12 @@ int mlxsw_sp_kvdl_alloc(struct mlxsw_sp *mlxsw_sp,
 
 void mlxsw_sp_kvdl_free(struct mlxsw_sp *mlxsw_sp,
 			enum mlxsw_sp_kvdl_entry_type type,
-			int entry_index)
+			unsigned int entry_count, int entry_index)
 {
 	struct mlxsw_sp_kvdl *kvdl = mlxsw_sp->kvdl;
 
-	kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, type, entry_index);
+	kvdl->kvdl_ops->free(mlxsw_sp, kvdl->priv, type,
+			     entry_count, entry_index);
 }
 
 int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index d1fd85ade425..87d9423dacdc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -111,7 +111,7 @@ mlxsw_sp_mr_erif_sublist_destroy(struct mlxsw_sp *mlxsw_sp,
 {
 	list_del(&erif_sublist->list);
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_MCRIGR,
-			   erif_sublist->rigr2_kvdl_index);
+			   1, erif_sublist->rigr2_kvdl_index);
 	kfree(erif_sublist);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index fb5980e92e3b..b4126db695dd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1124,7 +1124,7 @@ static void mlxsw_sp_fib_entry_decap_fini(struct mlxsw_sp *mlxsw_sp,
 	fib_entry->decap.ipip_entry->decap_fib_entry = NULL;
 	fib_entry->decap.ipip_entry = NULL;
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
-			   fib_entry->decap.tunnel_index);
+			   1, fib_entry->decap.tunnel_index);
 }
 
 static struct mlxsw_sp_fib_node *
@@ -3315,7 +3315,7 @@ mlxsw_sp_nexthop_group_refresh(struct mlxsw_sp *mlxsw_sp,
 	err = mlxsw_sp_adj_index_mass_update(mlxsw_sp, nh_grp,
 					     old_adj_index, old_ecmp_size);
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
-			   old_adj_index);
+			   old_ecmp_size, old_adj_index);
 	if (err) {
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to mass-update adjacency index for nexthop group.\n");
 		goto set_trap;
@@ -3338,7 +3338,7 @@ set_trap:
 		dev_warn(mlxsw_sp->bus_info->dev, "Failed to set traps for fib entries.\n");
 	if (old_adj_index_valid)
 		mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ADJ,
-				   nh_grp->adj_index);
+				   nh_grp->ecmp_size, nh_grp->adj_index);
 }
 
 static void __mlxsw_sp_nexthop_neigh_update(struct mlxsw_sp_nexthop *nh,
-- 
cgit v1.2.3


From 8fae4392d4ad8bea3a60829ff71b0735abc307c1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:19 +0300
Subject: mlxsw: spectrum_mr_tcam: Push Spectrum-specific operations into a
 separate file

Since Spectrum-2 has different handling of TCAM, push Spectrum MR TCAM
bits to a separate file accessible by ops which allows to implement
Spectrum-2 specific ops.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   3 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |   1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  35 ++
 .../ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c    | 374 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c  |   2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h  |  11 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c | 313 +++--------------
 7 files changed, 455 insertions(+), 284 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 546a13c0974f..cd9a281e0395 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -20,7 +20,8 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
-				   spectrum_mr.o spectrum_mr_tcam.o \
+				   spectrum1_mr_tcam.o \
+				   spectrum_mr_tcam.o spectrum_mr.o \
 				   spectrum_qdisc.o spectrum_span.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
 mlxsw_spectrum-$(CONFIG_NET_DEVLINK) += spectrum_dpipe.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index bb8ed98d4861..ea72556b9e6a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3623,6 +3623,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 
 	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
 	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
+	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
 
 	mlxsw_sp->core = mlxsw_core;
 	mlxsw_sp->bus_info = mlxsw_bus_info;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 25ea06dc8bff..a3fff2ba1ccb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -146,6 +146,7 @@ struct mlxsw_sp_counter_pool;
 struct mlxsw_sp_fid_core;
 struct mlxsw_sp_kvdl;
 struct mlxsw_sp_kvdl_ops;
+struct mlxsw_sp_mr_tcam_ops;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
@@ -171,6 +172,7 @@ struct mlxsw_sp {
 	} span;
 	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
 	const struct mlxsw_afa_ops *afa_ops;
+	const struct mlxsw_sp_mr_tcam_ops *mr_tcam_ops;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -681,4 +683,37 @@ void mlxsw_sp_port_fids_fini(struct mlxsw_sp_port *mlxsw_sp_port);
 int mlxsw_sp_fids_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_fids_fini(struct mlxsw_sp *mlxsw_sp);
 
+/* spectrum_mr.c */
+enum mlxsw_sp_mr_route_prio {
+	MLXSW_SP_MR_ROUTE_PRIO_SG,
+	MLXSW_SP_MR_ROUTE_PRIO_STARG,
+	MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
+	__MLXSW_SP_MR_ROUTE_PRIO_MAX
+};
+
+#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
+
+struct mlxsw_sp_mr_route_key;
+
+struct mlxsw_sp_mr_tcam_ops {
+	size_t priv_size;
+	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
+	void (*fini)(void *priv);
+	size_t route_priv_size;
+	int (*route_create)(struct mlxsw_sp *mlxsw_sp, void *priv,
+			    void *route_priv,
+			    struct mlxsw_sp_mr_route_key *key,
+			    struct mlxsw_afa_block *afa_block,
+			    enum mlxsw_sp_mr_route_prio prio);
+	void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
+			      void *route_priv,
+			      struct mlxsw_sp_mr_route_key *key);
+	int (*route_update)(struct mlxsw_sp *mlxsw_sp, void *route_priv,
+			    struct mlxsw_sp_mr_route_key *key,
+			    struct mlxsw_afa_block *afa_block);
+};
+
+/* spectrum1_mr_tcam.c */
+extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops;
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
new file mode 100644
index 000000000000..fc649fe7134e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
@@ -0,0 +1,374 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_actions.h"
+#include "spectrum_mr.h"
+
+struct mlxsw_sp1_mr_tcam_region {
+	struct mlxsw_sp *mlxsw_sp;
+	enum mlxsw_reg_rtar_key_type rtar_key_type;
+	struct parman *parman;
+	struct parman_prio *parman_prios;
+};
+
+struct mlxsw_sp1_mr_tcam {
+	struct mlxsw_sp1_mr_tcam_region tcam_regions[MLXSW_SP_L3_PROTO_MAX];
+};
+
+struct mlxsw_sp1_mr_tcam_route {
+	struct parman_item parman_item;
+	struct parman_prio *parman_prio;
+};
+
+static int mlxsw_sp1_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
+					   struct parman_item *parman_item,
+					   struct mlxsw_sp_mr_route_key *key,
+					   struct mlxsw_afa_block *afa_block)
+{
+	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
+					  key->vrid,
+					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+					  ntohl(key->group.addr4),
+					  ntohl(key->group_mask.addr4),
+					  ntohl(key->source.addr4),
+					  ntohl(key->source_mask.addr4),
+					  mlxsw_afa_block_first_set(afa_block));
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, true, parman_item->index,
+					  key->vrid,
+					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
+					  key->group.addr6,
+					  key->group_mask.addr6,
+					  key->source.addr6,
+					  key->source_mask.addr6,
+					  mlxsw_afa_block_first_set(afa_block));
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static int mlxsw_sp1_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp,
+					  struct parman_item *parman_item,
+					  struct mlxsw_sp_mr_route_key *key)
+{
+	struct in6_addr zero_addr = IN6ADDR_ANY_INIT;
+	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
+
+	switch (key->proto) {
+	case MLXSW_SP_L3_PROTO_IPV4:
+		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index,
+					  key->vrid, 0, 0, 0, 0, 0, 0, NULL);
+		break;
+	case MLXSW_SP_L3_PROTO_IPV6:
+		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, false, parman_item->index,
+					  key->vrid, 0, 0, zero_addr, zero_addr,
+					  zero_addr, zero_addr, NULL);
+		break;
+	}
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
+}
+
+static struct mlxsw_sp1_mr_tcam_region *
+mlxsw_sp1_mr_tcam_protocol_region(struct mlxsw_sp1_mr_tcam *mr_tcam,
+				  enum mlxsw_sp_l3proto proto)
+{
+	return &mr_tcam->tcam_regions[proto];
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_parman_item_add(struct mlxsw_sp1_mr_tcam *mr_tcam,
+					struct mlxsw_sp1_mr_tcam_route *route,
+					struct mlxsw_sp_mr_route_key *key,
+					enum mlxsw_sp_mr_route_prio prio)
+{
+	struct mlxsw_sp1_mr_tcam_region *tcam_region;
+	int err;
+
+	tcam_region = mlxsw_sp1_mr_tcam_protocol_region(mr_tcam, key->proto);
+	err = parman_item_add(tcam_region->parman,
+			      &tcam_region->parman_prios[prio],
+			      &route->parman_item);
+	if (err)
+		return err;
+
+	route->parman_prio = &tcam_region->parman_prios[prio];
+	return 0;
+}
+
+static void
+mlxsw_sp1_mr_tcam_route_parman_item_remove(struct mlxsw_sp1_mr_tcam *mr_tcam,
+					   struct mlxsw_sp1_mr_tcam_route *route,
+					   struct mlxsw_sp_mr_route_key *key)
+{
+	struct mlxsw_sp1_mr_tcam_region *tcam_region;
+
+	tcam_region = mlxsw_sp1_mr_tcam_protocol_region(mr_tcam, key->proto);
+	parman_item_remove(tcam_region->parman,
+			   route->parman_prio, &route->parman_item);
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block,
+			       enum mlxsw_sp_mr_route_prio prio)
+{
+	struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+	int err;
+
+	err = mlxsw_sp1_mr_tcam_route_parman_item_add(mr_tcam, route,
+						      key, prio);
+	if (err)
+		return err;
+
+	err = mlxsw_sp1_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					      key, afa_block);
+	if (err)
+		goto err_route_replace;
+	return 0;
+
+err_route_replace:
+	mlxsw_sp1_mr_tcam_route_parman_item_remove(mr_tcam, route, key);
+	return err;
+}
+
+static void
+mlxsw_sp1_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, void *priv,
+				void *route_priv,
+				struct mlxsw_sp_mr_route_key *key)
+{
+	struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+
+	mlxsw_sp1_mr_tcam_route_remove(mlxsw_sp, &route->parman_item, key);
+	mlxsw_sp1_mr_tcam_route_parman_item_remove(mr_tcam, route, key);
+}
+
+static int
+mlxsw_sp1_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block)
+{
+	struct mlxsw_sp1_mr_tcam_route *route = route_priv;
+
+	return mlxsw_sp1_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
+					       key, afa_block);
+}
+
+#define MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP1_MR_TCAM_REGION_RESIZE_STEP 16
+
+static int
+mlxsw_sp1_mr_tcam_region_alloc(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
+			    mr_tcam_region->rtar_key_type,
+			    MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void
+mlxsw_sp1_mr_tcam_region_free(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
+			    mr_tcam_region->rtar_key_type, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static int mlxsw_sp1_mr_tcam_region_parman_resize(void *priv,
+						  unsigned long new_count)
+{
+	struct mlxsw_sp1_mr_tcam_region *mr_tcam_region = priv;
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rtar_pl[MLXSW_REG_RTAR_LEN];
+	u64 max_tcam_rules;
+
+	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+	if (new_count > max_tcam_rules)
+		return -EINVAL;
+	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
+			    mr_tcam_region->rtar_key_type, new_count);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
+}
+
+static void mlxsw_sp1_mr_tcam_region_parman_move(void *priv,
+						 unsigned long from_index,
+						 unsigned long to_index,
+						 unsigned long count)
+{
+	struct mlxsw_sp1_mr_tcam_region *mr_tcam_region = priv;
+	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
+	char rrcr_pl[MLXSW_REG_RRCR_LEN];
+
+	mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
+			    from_index, count,
+			    mr_tcam_region->rtar_key_type, to_index);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
+}
+
+static const struct parman_ops mlxsw_sp1_mr_tcam_region_parman_ops = {
+	.base_count	= MLXSW_SP1_MR_TCAM_REGION_BASE_COUNT,
+	.resize_step	= MLXSW_SP1_MR_TCAM_REGION_RESIZE_STEP,
+	.resize		= mlxsw_sp1_mr_tcam_region_parman_resize,
+	.move		= mlxsw_sp1_mr_tcam_region_parman_move,
+	.algo		= PARMAN_ALGO_TYPE_LSORT,
+};
+
+static int
+mlxsw_sp1_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			      struct mlxsw_sp1_mr_tcam_region *mr_tcam_region,
+			      enum mlxsw_reg_rtar_key_type rtar_key_type)
+{
+	struct parman_prio *parman_prios;
+	struct parman *parman;
+	int err;
+	int i;
+
+	mr_tcam_region->rtar_key_type = rtar_key_type;
+	mr_tcam_region->mlxsw_sp = mlxsw_sp;
+
+	err = mlxsw_sp1_mr_tcam_region_alloc(mr_tcam_region);
+	if (err)
+		return err;
+
+	parman = parman_create(&mlxsw_sp1_mr_tcam_region_parman_ops,
+			       mr_tcam_region);
+	if (!parman) {
+		err = -ENOMEM;
+		goto err_parman_create;
+	}
+	mr_tcam_region->parman = parman;
+
+	parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
+				     sizeof(*parman_prios), GFP_KERNEL);
+	if (!parman_prios) {
+		err = -ENOMEM;
+		goto err_parman_prios_alloc;
+	}
+	mr_tcam_region->parman_prios = parman_prios;
+
+	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+		parman_prio_init(mr_tcam_region->parman,
+				 &mr_tcam_region->parman_prios[i], i);
+	return 0;
+
+err_parman_prios_alloc:
+	parman_destroy(parman);
+err_parman_create:
+	mlxsw_sp1_mr_tcam_region_free(mr_tcam_region);
+	return err;
+}
+
+static void
+mlxsw_sp1_mr_tcam_region_fini(struct mlxsw_sp1_mr_tcam_region *mr_tcam_region)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
+		parman_prio_fini(&mr_tcam_region->parman_prios[i]);
+	kfree(mr_tcam_region->parman_prios);
+	parman_destroy(mr_tcam_region->parman);
+	mlxsw_sp1_mr_tcam_region_free(mr_tcam_region);
+}
+
+static int mlxsw_sp1_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp1_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
+	u32 rtar_key;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+		return -EIO;
+
+	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST;
+	err = mlxsw_sp1_mr_tcam_region_init(mlxsw_sp,
+					    &region[MLXSW_SP_L3_PROTO_IPV4],
+					    rtar_key);
+	if (err)
+		return err;
+
+	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST;
+	err = mlxsw_sp1_mr_tcam_region_init(mlxsw_sp,
+					    &region[MLXSW_SP_L3_PROTO_IPV6],
+					    rtar_key);
+	if (err)
+		goto err_ipv6_region_init;
+
+	return 0;
+
+err_ipv6_region_init:
+	mlxsw_sp1_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+	return err;
+}
+
+static void mlxsw_sp1_mr_tcam_fini(void *priv)
+{
+	struct mlxsw_sp1_mr_tcam *mr_tcam = priv;
+	struct mlxsw_sp1_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
+
+	mlxsw_sp1_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV6]);
+	mlxsw_sp1_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+}
+
+const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops = {
+	.priv_size = sizeof(struct mlxsw_sp1_mr_tcam),
+	.init = mlxsw_sp1_mr_tcam_init,
+	.fini = mlxsw_sp1_mr_tcam_fini,
+	.route_priv_size = sizeof(struct mlxsw_sp1_mr_tcam_route),
+	.route_create = mlxsw_sp1_mr_tcam_route_create,
+	.route_destroy = mlxsw_sp1_mr_tcam_route_destroy,
+	.route_update = mlxsw_sp1_mr_tcam_route_update,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index a82539609d49..98dcaf78365c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -1075,6 +1075,6 @@ void mlxsw_sp_mr_fini(struct mlxsw_sp *mlxsw_sp)
 	struct mlxsw_sp_mr *mr = mlxsw_sp->mr;
 
 	cancel_delayed_work_sync(&mr->stats_update_dw);
-	mr->mr_ops->fini(mr->priv);
+	mr->mr_ops->fini(mlxsw_sp, mr->priv);
 	kfree(mr);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
index 7c864a86811d..c92fa90dca31 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
@@ -46,15 +46,6 @@ enum mlxsw_sp_mr_route_action {
 	MLXSW_SP_MR_ROUTE_ACTION_TRAP_AND_FORWARD,
 };
 
-enum mlxsw_sp_mr_route_prio {
-	MLXSW_SP_MR_ROUTE_PRIO_SG,
-	MLXSW_SP_MR_ROUTE_PRIO_STARG,
-	MLXSW_SP_MR_ROUTE_PRIO_CATCHALL,
-	__MLXSW_SP_MR_ROUTE_PRIO_MAX
-};
-
-#define MLXSW_SP_MR_ROUTE_PRIO_MAX (__MLXSW_SP_MR_ROUTE_PRIO_MAX - 1)
-
 struct mlxsw_sp_mr_route_key {
 	int vrid;
 	enum mlxsw_sp_l3proto proto;
@@ -101,7 +92,7 @@ struct mlxsw_sp_mr_ops {
 			      u16 erif_index);
 	void (*route_destroy)(struct mlxsw_sp *mlxsw_sp, void *priv,
 			      void *route_priv);
-	void (*fini)(void *priv);
+	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
 };
 
 struct mlxsw_sp_mr;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index 87d9423dacdc..e9c9f1f45b9d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -1,7 +1,8 @@
 /*
  * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
  * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -35,7 +36,6 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/netdevice.h>
-#include <linux/parman.h>
 
 #include "spectrum_mr_tcam.h"
 #include "reg.h"
@@ -43,15 +43,8 @@
 #include "core_acl_flex_actions.h"
 #include "spectrum_mr.h"
 
-struct mlxsw_sp_mr_tcam_region {
-	struct mlxsw_sp *mlxsw_sp;
-	enum mlxsw_reg_rtar_key_type rtar_key_type;
-	struct parman *parman;
-	struct parman_prio *parman_prios;
-};
-
 struct mlxsw_sp_mr_tcam {
-	struct mlxsw_sp_mr_tcam_region tcam_regions[MLXSW_SP_L3_PROTO_MAX];
+	void *priv;
 };
 
 /* This struct maps to one RIGR2 register entry */
@@ -220,12 +213,11 @@ struct mlxsw_sp_mr_tcam_route {
 	struct mlxsw_sp_mr_tcam_erif_list erif_list;
 	struct mlxsw_afa_block *afa_block;
 	u32 counter_index;
-	struct parman_item parman_item;
-	struct parman_prio *parman_prio;
 	enum mlxsw_sp_mr_route_action action;
 	struct mlxsw_sp_mr_route_key key;
 	u16 irif_index;
 	u16 min_mtu;
+	void *priv;
 };
 
 static struct mlxsw_afa_block *
@@ -296,60 +288,6 @@ mlxsw_sp_mr_tcam_afa_block_destroy(struct mlxsw_afa_block *afa_block)
 	mlxsw_afa_block_destroy(afa_block);
 }
 
-static int mlxsw_sp_mr_tcam_route_replace(struct mlxsw_sp *mlxsw_sp,
-					  struct parman_item *parman_item,
-					  struct mlxsw_sp_mr_route_key *key,
-					  struct mlxsw_afa_block *afa_block)
-{
-	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
-
-	switch (key->proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, true, parman_item->index,
-					  key->vrid,
-					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
-					  ntohl(key->group.addr4),
-					  ntohl(key->group_mask.addr4),
-					  ntohl(key->source.addr4),
-					  ntohl(key->source_mask.addr4),
-					  mlxsw_afa_block_first_set(afa_block));
-		break;
-	case MLXSW_SP_L3_PROTO_IPV6:
-		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, true, parman_item->index,
-					  key->vrid,
-					  MLXSW_REG_RMFT2_IRIF_MASK_IGNORE, 0,
-					  key->group.addr6,
-					  key->group_mask.addr6,
-					  key->source.addr6,
-					  key->source_mask.addr6,
-					  mlxsw_afa_block_first_set(afa_block));
-	}
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
-}
-
-static int mlxsw_sp_mr_tcam_route_remove(struct mlxsw_sp *mlxsw_sp, int vrid,
-					 struct mlxsw_sp_mr_route_key *key,
-					 struct parman_item *parman_item)
-{
-	struct in6_addr zero_addr = IN6ADDR_ANY_INIT;
-	char rmft2_pl[MLXSW_REG_RMFT2_LEN];
-
-	switch (key->proto) {
-	case MLXSW_SP_L3_PROTO_IPV4:
-		mlxsw_reg_rmft2_ipv4_pack(rmft2_pl, false, parman_item->index,
-					  vrid, 0, 0, 0, 0, 0, 0, NULL);
-		break;
-	case MLXSW_SP_L3_PROTO_IPV6:
-		mlxsw_reg_rmft2_ipv6_pack(rmft2_pl, false, parman_item->index,
-					  vrid, 0, 0, zero_addr, zero_addr,
-					  zero_addr, zero_addr, NULL);
-		break;
-	}
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rmft2), rmft2_pl);
-}
-
 static int
 mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_mr_tcam_erif_list *erif_list,
@@ -369,51 +307,12 @@ mlxsw_sp_mr_tcam_erif_populate(struct mlxsw_sp *mlxsw_sp,
 	return 0;
 }
 
-static struct mlxsw_sp_mr_tcam_region *
-mlxsw_sp_mr_tcam_protocol_region(struct mlxsw_sp_mr_tcam *mr_tcam,
-				 enum mlxsw_sp_l3proto proto)
-{
-	return &mr_tcam->tcam_regions[proto];
-}
-
-static int
-mlxsw_sp_mr_tcam_route_parman_item_add(struct mlxsw_sp_mr_tcam *mr_tcam,
-				       struct mlxsw_sp_mr_tcam_route *route,
-				       enum mlxsw_sp_mr_route_prio prio)
-{
-	struct mlxsw_sp_mr_tcam_region *tcam_region;
-	int err;
-
-	tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
-						       route->key.proto);
-	err = parman_item_add(tcam_region->parman,
-			      &tcam_region->parman_prios[prio],
-			      &route->parman_item);
-	if (err)
-		return err;
-
-	route->parman_prio = &tcam_region->parman_prios[prio];
-	return 0;
-}
-
-static void
-mlxsw_sp_mr_tcam_route_parman_item_remove(struct mlxsw_sp_mr_tcam *mr_tcam,
-					  struct mlxsw_sp_mr_tcam_route *route)
-{
-	struct mlxsw_sp_mr_tcam_region *tcam_region;
-
-	tcam_region = mlxsw_sp_mr_tcam_protocol_region(mr_tcam,
-						       route->key.proto);
-
-	parman_item_remove(tcam_region->parman,
-			   route->parman_prio, &route->parman_item);
-}
-
 static int
 mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 			      void *route_priv,
 			      struct mlxsw_sp_mr_route_params *route_params)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
 	int err;
@@ -447,22 +346,23 @@ mlxsw_sp_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
 		goto err_afa_block_create;
 	}
 
-	/* Allocate place in the TCAM */
-	err = mlxsw_sp_mr_tcam_route_parman_item_add(mr_tcam, route,
-						     route_params->prio);
-	if (err)
-		goto err_parman_item_add;
+	route->priv = kzalloc(ops->route_priv_size, GFP_KERNEL);
+	if (!route->priv) {
+		err = -ENOMEM;
+		goto err_route_priv_alloc;
+	}
 
 	/* Write the route to the TCAM */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, route->afa_block);
+	err = ops->route_create(mlxsw_sp, mr_tcam->priv, route->priv,
+				&route->key, route->afa_block,
+				route_params->prio);
 	if (err)
-		goto err_route_replace;
+		goto err_route_create;
 	return 0;
 
-err_route_replace:
-	mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
-err_parman_item_add:
+err_route_create:
+	kfree(route->priv);
+err_route_priv_alloc:
 	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
 err_afa_block_create:
 	mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
@@ -475,12 +375,12 @@ err_counter_alloc:
 static void mlxsw_sp_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp,
 					   void *priv, void *route_priv)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
 
-	mlxsw_sp_mr_tcam_route_remove(mlxsw_sp, route->key.vrid,
-				      &route->key, &route->parman_item);
-	mlxsw_sp_mr_tcam_route_parman_item_remove(mr_tcam, route);
+	ops->route_destroy(mlxsw_sp, mr_tcam->priv, route->priv, &route->key);
+	kfree(route->priv);
 	mlxsw_sp_mr_tcam_afa_block_destroy(route->afa_block);
 	mlxsw_sp_flow_counter_free(mlxsw_sp, route->counter_index);
 	mlxsw_sp_mr_erif_list_flush(mlxsw_sp, &route->erif_list);
@@ -501,6 +401,7 @@ mlxsw_sp_mr_tcam_route_action_update(struct mlxsw_sp *mlxsw_sp,
 				     void *route_priv,
 				     enum mlxsw_sp_mr_route_action route_action)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_afa_block *afa_block;
 	int err;
@@ -515,8 +416,7 @@ mlxsw_sp_mr_tcam_route_action_update(struct mlxsw_sp *mlxsw_sp,
 		return PTR_ERR(afa_block);
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err;
 
@@ -533,6 +433,7 @@ err:
 static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp,
 						 void *route_priv, u16 min_mtu)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_afa_block *afa_block;
 	int err;
@@ -548,8 +449,7 @@ static int mlxsw_sp_mr_tcam_route_min_mtu_update(struct mlxsw_sp *mlxsw_sp,
 		return PTR_ERR(afa_block);
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err;
 
@@ -595,6 +495,7 @@ static int mlxsw_sp_mr_tcam_route_erif_add(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp,
 					   void *route_priv, u16 erif_index)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_erif_sublist *erif_sublist;
 	struct mlxsw_sp_mr_tcam_erif_list erif_list;
@@ -629,8 +530,7 @@ static int mlxsw_sp_mr_tcam_route_erif_del(struct mlxsw_sp *mlxsw_sp,
 	}
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err_route_write;
 
@@ -652,6 +552,7 @@ static int
 mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv,
 			      struct mlxsw_sp_mr_route_info *route_info)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam_route *route = route_priv;
 	struct mlxsw_sp_mr_tcam_erif_list erif_list;
 	struct mlxsw_afa_block *afa_block;
@@ -676,8 +577,7 @@ mlxsw_sp_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp, void *route_priv,
 	}
 
 	/* Update the TCAM route entry */
-	err = mlxsw_sp_mr_tcam_route_replace(mlxsw_sp, &route->parman_item,
-					     &route->key, afa_block);
+	err = ops->route_update(mlxsw_sp, route->priv, &route->key, afa_block);
 	if (err)
 		goto err_route_write;
 
@@ -698,167 +598,36 @@ err_erif_populate:
 	return err;
 }
 
-#define MLXSW_SP_MR_TCAM_REGION_BASE_COUNT 16
-#define MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP 16
-
-static int
-mlxsw_sp_mr_tcam_region_alloc(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rtar_pl[MLXSW_REG_RTAR_LEN];
-
-	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_ALLOCATE,
-			    mr_tcam_region->rtar_key_type,
-			    MLXSW_SP_MR_TCAM_REGION_BASE_COUNT);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static void
-mlxsw_sp_mr_tcam_region_free(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rtar_pl[MLXSW_REG_RTAR_LEN];
-
-	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_DEALLOCATE,
-			    mr_tcam_region->rtar_key_type, 0);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static int mlxsw_sp_mr_tcam_region_parman_resize(void *priv,
-						 unsigned long new_count)
-{
-	struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rtar_pl[MLXSW_REG_RTAR_LEN];
-	u64 max_tcam_rules;
-
-	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
-	if (new_count > max_tcam_rules)
-		return -EINVAL;
-	mlxsw_reg_rtar_pack(rtar_pl, MLXSW_REG_RTAR_OP_RESIZE,
-			    mr_tcam_region->rtar_key_type, new_count);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rtar), rtar_pl);
-}
-
-static void mlxsw_sp_mr_tcam_region_parman_move(void *priv,
-						unsigned long from_index,
-						unsigned long to_index,
-						unsigned long count)
-{
-	struct mlxsw_sp_mr_tcam_region *mr_tcam_region = priv;
-	struct mlxsw_sp *mlxsw_sp = mr_tcam_region->mlxsw_sp;
-	char rrcr_pl[MLXSW_REG_RRCR_LEN];
-
-	mlxsw_reg_rrcr_pack(rrcr_pl, MLXSW_REG_RRCR_OP_MOVE,
-			    from_index, count,
-			    mr_tcam_region->rtar_key_type, to_index);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rrcr), rrcr_pl);
-}
-
-static const struct parman_ops mlxsw_sp_mr_tcam_region_parman_ops = {
-	.base_count	= MLXSW_SP_MR_TCAM_REGION_BASE_COUNT,
-	.resize_step	= MLXSW_SP_MR_TCAM_REGION_RESIZE_STEP,
-	.resize		= mlxsw_sp_mr_tcam_region_parman_resize,
-	.move		= mlxsw_sp_mr_tcam_region_parman_move,
-	.algo		= PARMAN_ALGO_TYPE_LSORT,
-};
-
-static int
-mlxsw_sp_mr_tcam_region_init(struct mlxsw_sp *mlxsw_sp,
-			     struct mlxsw_sp_mr_tcam_region *mr_tcam_region,
-			     enum mlxsw_reg_rtar_key_type rtar_key_type)
-{
-	struct parman_prio *parman_prios;
-	struct parman *parman;
-	int err;
-	int i;
-
-	mr_tcam_region->rtar_key_type = rtar_key_type;
-	mr_tcam_region->mlxsw_sp = mlxsw_sp;
-
-	err = mlxsw_sp_mr_tcam_region_alloc(mr_tcam_region);
-	if (err)
-		return err;
-
-	parman = parman_create(&mlxsw_sp_mr_tcam_region_parman_ops,
-			       mr_tcam_region);
-	if (!parman) {
-		err = -ENOMEM;
-		goto err_parman_create;
-	}
-	mr_tcam_region->parman = parman;
-
-	parman_prios = kmalloc_array(MLXSW_SP_MR_ROUTE_PRIO_MAX + 1,
-				     sizeof(*parman_prios), GFP_KERNEL);
-	if (!parman_prios) {
-		err = -ENOMEM;
-		goto err_parman_prios_alloc;
-	}
-	mr_tcam_region->parman_prios = parman_prios;
-
-	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
-		parman_prio_init(mr_tcam_region->parman,
-				 &mr_tcam_region->parman_prios[i], i);
-	return 0;
-
-err_parman_prios_alloc:
-	parman_destroy(parman);
-err_parman_create:
-	mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
-	return err;
-}
-
-static void
-mlxsw_sp_mr_tcam_region_fini(struct mlxsw_sp_mr_tcam_region *mr_tcam_region)
-{
-	int i;
-
-	for (i = 0; i < MLXSW_SP_MR_ROUTE_PRIO_MAX + 1; i++)
-		parman_prio_fini(&mr_tcam_region->parman_prios[i]);
-	kfree(mr_tcam_region->parman_prios);
-	parman_destroy(mr_tcam_region->parman);
-	mlxsw_sp_mr_tcam_region_free(mr_tcam_region);
-}
-
 static int mlxsw_sp_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
-	struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
-	u32 rtar_key;
 	int err;
 
-	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES) ||
-	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_TCAM_RULES))
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MC_ERIF_LIST_ENTRIES))
 		return -EIO;
 
-	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV4_MULTICAST;
-	err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
-					   &region[MLXSW_SP_L3_PROTO_IPV4],
-					   rtar_key);
-	if (err)
-		return err;
+	mr_tcam->priv = kzalloc(ops->priv_size, GFP_KERNEL);
+	if (!mr_tcam->priv)
+		return -ENOMEM;
 
-	rtar_key = MLXSW_REG_RTAR_KEY_TYPE_IPV6_MULTICAST;
-	err = mlxsw_sp_mr_tcam_region_init(mlxsw_sp,
-					   &region[MLXSW_SP_L3_PROTO_IPV6],
-					   rtar_key);
+	err = ops->init(mlxsw_sp, mr_tcam->priv);
 	if (err)
-		goto err_ipv6_region_init;
-
+		goto err_init;
 	return 0;
 
-err_ipv6_region_init:
-	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+err_init:
+	kfree(mr_tcam->priv);
 	return err;
 }
 
-static void mlxsw_sp_mr_tcam_fini(void *priv)
+static void mlxsw_sp_mr_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
+	const struct mlxsw_sp_mr_tcam_ops *ops = mlxsw_sp->mr_tcam_ops;
 	struct mlxsw_sp_mr_tcam *mr_tcam = priv;
-	struct mlxsw_sp_mr_tcam_region *region = &mr_tcam->tcam_regions[0];
 
-	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV6]);
-	mlxsw_sp_mr_tcam_region_fini(&region[MLXSW_SP_L3_PROTO_IPV4]);
+	ops->fini(mr_tcam->priv);
+	kfree(mr_tcam->priv);
 }
 
 const struct mlxsw_sp_mr_ops mlxsw_sp_mr_tcam_ops = {
-- 
cgit v1.2.3


From 64eccd0066775aaf7442761413b3cac137c00ced Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:20 +0300
Subject: mlxsw: spectrum_acl: Split TCAM handling 3 ways

To allow easy and clean Spectrum-2 implementation for things that differ
from Spectrum, split the existing ACL TCAM code 3 ways:
1) common code that calls Spectrum/Spectrum-2 specific ops
2) Spectrum ops implementations
3) common C-TCAM code that is going to be shared between Spectrum and
   Spectrum-2 implementations

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   4 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |   1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  32 ++-
 .../ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c   | 231 ++++++++++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c |   4 +-
 .../ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c   | 205 +++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 289 ++++-----------------
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    | 103 ++++++++
 8 files changed, 622 insertions(+), 247 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index cd9a281e0395..54f1de4674ce 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -16,7 +16,9 @@ obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o spectrum_router.o \
 				   spectrum1_kvdl.o spectrum_kvdl.o \
-				   spectrum_acl_tcam.o spectrum_acl.o \
+				   spectrum_acl_tcam.o spectrum_acl_ctcam.o \
+				   spectrum1_acl_tcam.o \
+				   spectrum_acl.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ea72556b9e6a..5f5b476c0235 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3624,6 +3624,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
 	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
 	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
+	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
 
 	mlxsw_sp->core = mlxsw_core;
 	mlxsw_sp->bus_info = mlxsw_bus_info;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index a3fff2ba1ccb..fa495f787d22 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -147,6 +147,7 @@ struct mlxsw_sp_fid_core;
 struct mlxsw_sp_kvdl;
 struct mlxsw_sp_kvdl_ops;
 struct mlxsw_sp_mr_tcam_ops;
+struct mlxsw_sp_acl_tcam_ops;
 
 struct mlxsw_sp {
 	struct mlxsw_sp_port **ports;
@@ -173,6 +174,7 @@ struct mlxsw_sp {
 	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
 	const struct mlxsw_afa_ops *afa_ops;
 	const struct mlxsw_sp_mr_tcam_ops *mr_tcam_ops;
+	const struct mlxsw_sp_acl_tcam_ops *acl_tcam_ops;
 };
 
 static inline struct mlxsw_sp_upper *
@@ -517,7 +519,7 @@ struct mlxsw_sp_acl_profile_ops {
 			       struct mlxsw_sp_port *mlxsw_sp_port,
 			       bool ingress);
 	u16 (*ruleset_group_id)(void *ruleset_priv);
-	size_t rule_priv_size;
+	size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp);
 	int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
 			void *ruleset_priv, void *rule_priv,
 			struct mlxsw_sp_acl_rule_info *rulei);
@@ -631,7 +633,33 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
 
 /* spectrum_acl_tcam.c */
-extern const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops;
+struct mlxsw_sp_acl_tcam_region;
+
+struct mlxsw_sp_acl_tcam_ops {
+	enum mlxsw_reg_ptar_key_type key_type;
+	size_t region_priv_size;
+	int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			   struct mlxsw_sp_acl_tcam_region *region);
+	void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv);
+	size_t chunk_priv_size;
+	void (*chunk_init)(void *region_priv, void *chunk_priv,
+			   unsigned int priority);
+	void (*chunk_fini)(void *chunk_priv);
+	size_t entry_priv_size;
+	int (*entry_add)(struct mlxsw_sp *mlxsw_sp,
+			 void *region_priv, void *chunk_priv,
+			 void *entry_priv,
+			 struct mlxsw_sp_acl_rule_info *rulei);
+	void (*entry_del)(struct mlxsw_sp *mlxsw_sp,
+			  void *region_priv, void *chunk_priv,
+			  void *entry_priv);
+	int (*entry_activity_get)(struct mlxsw_sp *mlxsw_sp,
+				  void *region_priv, void *entry_priv,
+				  bool *activity);
+};
+
+/* spectrum1_acl_tcam.c */
+extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops;
 
 /* spectrum_acl_flex_actions.c */
 extern const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
new file mode 100644
index 000000000000..aa7e03b81b4d
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -0,0 +1,231 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+struct mlxsw_sp1_acl_tcam_region {
+	struct mlxsw_sp_acl_ctcam_region cregion;
+	struct mlxsw_sp_acl_tcam_region *region;
+	struct {
+		struct mlxsw_sp_acl_ctcam_chunk cchunk;
+		struct mlxsw_sp_acl_ctcam_entry centry;
+		struct mlxsw_sp_acl_rule_info *rulei;
+	} catchall;
+};
+
+struct mlxsw_sp1_acl_tcam_chunk {
+	struct mlxsw_sp_acl_ctcam_chunk cchunk;
+};
+
+struct mlxsw_sp1_acl_tcam_entry {
+	struct mlxsw_sp_acl_ctcam_entry centry;
+};
+
+static int
+mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp1_acl_tcam_region *region)
+{
+	struct mlxsw_sp_acl_rule_info *rulei;
+	int err;
+
+	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion,
+				      &region->catchall.cchunk,
+				      MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
+	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
+	if (IS_ERR(rulei)) {
+		err = PTR_ERR(rulei);
+		goto err_rulei_create;
+	}
+	err = mlxsw_sp_acl_rulei_act_continue(rulei);
+	if (WARN_ON(err))
+		goto err_rulei_act_continue;
+	err = mlxsw_sp_acl_rulei_commit(rulei);
+	if (err)
+		goto err_rulei_commit;
+	err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
+					   &region->catchall.cchunk,
+					   &region->catchall.centry, rulei);
+	if (err)
+		goto err_entry_add;
+	region->catchall.rulei = rulei;
+	return 0;
+
+err_entry_add:
+err_rulei_commit:
+err_rulei_act_continue:
+	mlxsw_sp_acl_rulei_destroy(rulei);
+err_rulei_create:
+	mlxsw_sp_acl_ctcam_chunk_fini(&region->catchall.cchunk);
+	return err;
+}
+
+static void
+mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp1_acl_tcam_region *region)
+{
+	struct mlxsw_sp_acl_rule_info *rulei = region->catchall.rulei;
+
+	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->cregion,
+				     &region->catchall.cchunk,
+				     &region->catchall.centry);
+	mlxsw_sp_acl_rulei_destroy(rulei);
+	mlxsw_sp_acl_ctcam_chunk_fini(&region->catchall.cchunk);
+}
+
+static int
+mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			       struct mlxsw_sp_acl_tcam_region *_region)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	int err;
+
+	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &region->cregion,
+					     _region);
+	if (err)
+		return err;
+	err = mlxsw_sp1_acl_ctcam_region_catchall_add(mlxsw_sp, region);
+	if (err)
+		goto err_catchall_add;
+	region->region = _region;
+	return 0;
+
+err_catchall_add:
+	mlxsw_sp_acl_ctcam_region_fini(&region->cregion);
+	return err;
+}
+
+static void
+mlxsw_sp1_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+
+	mlxsw_sp1_acl_ctcam_region_catchall_del(mlxsw_sp, region);
+	mlxsw_sp_acl_ctcam_region_fini(&region->cregion);
+}
+
+static void mlxsw_sp1_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
+					  unsigned int priority)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion, &chunk->cchunk,
+				      priority);
+}
+
+static void mlxsw_sp1_acl_tcam_chunk_fini(void *chunk_priv)
+{
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_ctcam_chunk_fini(&chunk->cchunk);
+}
+
+static int mlxsw_sp1_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *chunk_priv,
+					void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+
+	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
+					    &chunk->cchunk, &entry->centry,
+					    rulei);
+}
+
+static void mlxsw_sp1_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+					 void *region_priv, void *chunk_priv,
+					 void *entry_priv)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+
+	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->cregion,
+				     &chunk->cchunk, &entry->centry);
+}
+
+static int
+mlxsw_sp1_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+					     struct mlxsw_sp_acl_tcam_region *_region,
+					     unsigned int offset,
+					     bool *activity)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	int err;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
+			     _region->tcam_region_info, offset);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	if (err)
+		return err;
+	*activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
+	return 0;
+}
+
+static int
+mlxsw_sp1_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				      void *region_priv, void *entry_priv,
+				      bool *activity)
+{
+	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp1_acl_tcam_entry *entry = entry_priv;
+	unsigned int offset;
+
+	offset = mlxsw_sp_acl_ctcam_entry_offset(&entry->centry);
+	return mlxsw_sp1_acl_tcam_region_entry_activity_get(mlxsw_sp,
+							    region->region,
+							    offset, activity);
+}
+
+const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops = {
+	.key_type		= MLXSW_REG_PTAR_KEY_TYPE_FLEX,
+	.region_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_region),
+	.region_init		= mlxsw_sp1_acl_tcam_region_init,
+	.region_fini		= mlxsw_sp1_acl_tcam_region_fini,
+	.chunk_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_chunk),
+	.chunk_init		= mlxsw_sp1_acl_tcam_chunk_init,
+	.chunk_fini		= mlxsw_sp1_acl_tcam_chunk_fini,
+	.entry_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_entry),
+	.entry_add		= mlxsw_sp1_acl_tcam_entry_add,
+	.entry_del		= mlxsw_sp1_acl_tcam_entry_del,
+	.entry_activity_get	= mlxsw_sp1_acl_tcam_entry_activity_get,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index b40569c67ddf..1bf963cd1f12 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -48,6 +48,7 @@
 #include "spectrum.h"
 #include "core_acl_flex_keys.h"
 #include "core_acl_flex_actions.h"
+#include "spectrum_acl_tcam.h"
 #include "spectrum_acl_flex_keys.h"
 
 struct mlxsw_sp_acl {
@@ -634,7 +635,8 @@ mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_sp_acl_ruleset_ref_inc(ruleset);
-	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size, GFP_KERNEL);
+	rule = kzalloc(sizeof(*rule) + ops->rule_priv_size(mlxsw_sp),
+		       GFP_KERNEL);
 	if (!rule) {
 		err = -ENOMEM;
 		goto err_alloc;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
new file mode 100644
index 000000000000..c5cbec5c7541
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -0,0 +1,205 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+static int
+mlxsw_sp_acl_ctcam_region_resize(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_tcam_region *region,
+				 u16 new_size)
+{
+	char ptar_pl[MLXSW_REG_PTAR_LEN];
+
+	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_RESIZE,
+			    region->key_type, new_size, region->id,
+			    region->tcam_region_info);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
+}
+
+static void
+mlxsw_sp_acl_ctcam_region_move(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       u16 src_offset, u16 dst_offset, u16 size)
+{
+	char prcr_pl[MLXSW_REG_PRCR_LEN];
+
+	mlxsw_reg_prcr_pack(prcr_pl, MLXSW_REG_PRCR_OP_MOVE,
+			    region->tcam_region_info, src_offset,
+			    region->tcam_region_info, dst_offset, size);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(prcr), prcr_pl);
+}
+
+static int
+mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_region *region,
+				       unsigned int offset,
+				       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	char *act_set;
+	char *mask;
+	char *key;
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
+			     region->tcam_region_info, offset);
+	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
+	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
+	mlxsw_afk_encode(region->key_info, &rulei->values, key, mask);
+
+	/* Only the first action set belongs here, the rest is in KVD */
+	act_set = mlxsw_afa_block_first_set(rulei->act_block);
+	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+}
+
+static void
+mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_tcam_region *region,
+				       unsigned int offset)
+{
+	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+
+	mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
+			     region->tcam_region_info, offset);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+}
+
+static int mlxsw_sp_acl_ctcam_region_parman_resize(void *priv,
+						   unsigned long new_count)
+{
+	struct mlxsw_sp_acl_ctcam_region *cregion = priv;
+	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+	u64 max_tcam_rules;
+
+	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
+	if (new_count > max_tcam_rules)
+		return -EINVAL;
+	return mlxsw_sp_acl_ctcam_region_resize(mlxsw_sp, region, new_count);
+}
+
+static void mlxsw_sp_acl_ctcam_region_parman_move(void *priv,
+						  unsigned long from_index,
+						  unsigned long to_index,
+						  unsigned long count)
+{
+	struct mlxsw_sp_acl_ctcam_region *cregion = priv;
+	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+
+	mlxsw_sp_acl_ctcam_region_move(mlxsw_sp, region,
+				       from_index, to_index, count);
+}
+
+static const struct parman_ops mlxsw_sp_acl_ctcam_region_parman_ops = {
+	.base_count	= MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
+	.resize_step	= MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP,
+	.resize		= mlxsw_sp_acl_ctcam_region_parman_resize,
+	.move		= mlxsw_sp_acl_ctcam_region_parman_move,
+	.algo		= PARMAN_ALGO_TYPE_LSORT,
+};
+
+int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_ctcam_region *cregion,
+				   struct mlxsw_sp_acl_tcam_region *region)
+{
+	cregion->region = region;
+	cregion->parman = parman_create(&mlxsw_sp_acl_ctcam_region_parman_ops,
+					cregion);
+	if (!cregion->parman)
+		return -ENOMEM;
+	return 0;
+}
+
+void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion)
+{
+	parman_destroy(cregion->parman);
+}
+
+void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion,
+				   struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				   unsigned int priority)
+{
+	parman_prio_init(cregion->parman, &cchunk->parman_prio, priority);
+}
+
+void mlxsw_sp_acl_ctcam_chunk_fini(struct mlxsw_sp_acl_ctcam_chunk *cchunk)
+{
+	parman_prio_fini(&cchunk->parman_prio);
+}
+
+int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_ctcam_region *cregion,
+				 struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				 struct mlxsw_sp_acl_ctcam_entry *centry,
+				 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	int err;
+
+	err = parman_item_add(cregion->parman, &cchunk->parman_prio,
+			      &centry->parman_item);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion->region,
+						     centry->parman_item.index,
+						     rulei);
+	if (err)
+		goto err_rule_insert;
+	return 0;
+
+err_rule_insert:
+	parman_item_remove(cregion->parman, &cchunk->parman_prio,
+			   &centry->parman_item);
+	return err;
+}
+
+void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_ctcam_region *cregion,
+				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				  struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	mlxsw_sp_acl_ctcam_region_entry_remove(mlxsw_sp, cregion->region,
+					       centry->parman_item.index);
+	parman_item_remove(cregion->parman, &cchunk->parman_prio,
+			   &centry->parman_item);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index efbd2062b6ec..d2e3d9cec805 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1,7 +1,7 @@
 /*
  * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions are met:
@@ -39,12 +39,12 @@
 #include <linux/list.h>
 #include <linux/rhashtable.h>
 #include <linux/netdevice.h>
-#include <linux/parman.h>
 
 #include "reg.h"
 #include "core.h"
 #include "resources.h"
 #include "spectrum.h"
+#include "spectrum_acl_tcam.h"
 #include "core_acl_flex_keys.h"
 
 struct mlxsw_sp_acl_tcam {
@@ -159,36 +159,21 @@ struct mlxsw_sp_acl_tcam_group {
 	unsigned int patterns_count;
 };
 
-struct mlxsw_sp_acl_tcam_region {
-	struct list_head list; /* Member of a TCAM group */
-	struct list_head chunk_list; /* List of chunks under this region */
-	struct parman *parman;
-	struct mlxsw_sp *mlxsw_sp;
-	struct mlxsw_sp_acl_tcam_group *group;
-	enum mlxsw_reg_ptar_key_type key_type;
-	u16 id; /* ACL ID and region ID - they are same */
-	char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
-	struct mlxsw_afk_key_info *key_info;
-	struct {
-		struct parman_prio parman_prio;
-		struct parman_item parman_item;
-		struct mlxsw_sp_acl_rule_info *rulei;
-	} catchall;
-};
-
 struct mlxsw_sp_acl_tcam_chunk {
 	struct list_head list; /* Member of a TCAM region */
 	struct rhash_head ht_node; /* Member of a chunk HT */
 	unsigned int priority; /* Priority within the region and group */
-	struct parman_prio parman_prio;
 	struct mlxsw_sp_acl_tcam_group *group;
 	struct mlxsw_sp_acl_tcam_region *region;
 	unsigned int ref_count;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
 };
 
 struct mlxsw_sp_acl_tcam_entry {
-	struct parman_item parman_item;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
 };
 
 static const struct rhashtable_params mlxsw_sp_acl_tcam_chunk_ht_params = {
@@ -442,9 +427,6 @@ mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
 	memcpy(out, elusage, sizeof(*out));
 }
 
-#define MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT 16
-#define MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP 16
-
 static int
 mlxsw_sp_acl_tcam_region_alloc(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_tcam_region *region)
@@ -485,19 +467,6 @@ mlxsw_sp_acl_tcam_region_free(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
 }
 
-static int
-mlxsw_sp_acl_tcam_region_resize(struct mlxsw_sp *mlxsw_sp,
-				struct mlxsw_sp_acl_tcam_region *region,
-				u16 new_size)
-{
-	char ptar_pl[MLXSW_REG_PTAR_LEN];
-
-	mlxsw_reg_ptar_pack(ptar_pl, MLXSW_REG_PTAR_OP_RESIZE,
-			    region->key_type, new_size, region->id,
-			    region->tcam_region_info);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptar), ptar_pl);
-}
-
 static int
 mlxsw_sp_acl_tcam_region_enable(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam_region *region)
@@ -520,193 +489,22 @@ mlxsw_sp_acl_tcam_region_disable(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pacl), pacl_pl);
 }
 
-static int
-mlxsw_sp_acl_tcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region,
-				      unsigned int offset,
-				      struct mlxsw_sp_acl_rule_info *rulei)
-{
-	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-	char *act_set;
-	char *mask;
-	char *key;
-
-	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset);
-	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
-	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
-	mlxsw_afk_encode(region->key_info, &rulei->values, key, mask);
-
-	/* Only the first action set belongs here, the rest is in KVD */
-	act_set = mlxsw_afa_block_first_set(rulei->act_block);
-	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
-
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-}
-
-static void
-mlxsw_sp_acl_tcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region,
-				      unsigned int offset)
-{
-	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-
-	mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-}
-
-static int
-mlxsw_sp_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
-					    struct mlxsw_sp_acl_tcam_region *region,
-					    unsigned int offset,
-					    bool *activity)
-{
-	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
-	int err;
-
-	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
-			     region->tcam_region_info, offset);
-	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
-	if (err)
-		return err;
-	*activity = mlxsw_reg_ptce2_a_get(ptce2_pl);
-	return 0;
-}
-
-#define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
-
-static int
-mlxsw_sp_acl_tcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region)
-{
-	struct parman_prio *parman_prio = &region->catchall.parman_prio;
-	struct parman_item *parman_item = &region->catchall.parman_item;
-	struct mlxsw_sp_acl_rule_info *rulei;
-	int err;
-
-	parman_prio_init(region->parman, parman_prio,
-			 MLXSW_SP_ACL_TCAM_CATCHALL_PRIO);
-	err = parman_item_add(region->parman, parman_prio, parman_item);
-	if (err)
-		goto err_parman_item_add;
-
-	rulei = mlxsw_sp_acl_rulei_create(mlxsw_sp->acl);
-	if (IS_ERR(rulei)) {
-		err = PTR_ERR(rulei);
-		goto err_rulei_create;
-	}
-
-	err = mlxsw_sp_acl_rulei_act_continue(rulei);
-	if (WARN_ON(err))
-		goto err_rulei_act_continue;
-
-	err = mlxsw_sp_acl_rulei_commit(rulei);
-	if (err)
-		goto err_rulei_commit;
-
-	err = mlxsw_sp_acl_tcam_region_entry_insert(mlxsw_sp, region,
-						    parman_item->index, rulei);
-	region->catchall.rulei = rulei;
-	if (err)
-		goto err_rule_insert;
-
-	return 0;
-
-err_rule_insert:
-err_rulei_commit:
-err_rulei_act_continue:
-	mlxsw_sp_acl_rulei_destroy(rulei);
-err_rulei_create:
-	parman_item_remove(region->parman, parman_prio, parman_item);
-err_parman_item_add:
-	parman_prio_fini(parman_prio);
-	return err;
-}
-
-static void
-mlxsw_sp_acl_tcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
-				      struct mlxsw_sp_acl_tcam_region *region)
-{
-	struct parman_prio *parman_prio = &region->catchall.parman_prio;
-	struct parman_item *parman_item = &region->catchall.parman_item;
-	struct mlxsw_sp_acl_rule_info *rulei = region->catchall.rulei;
-
-	mlxsw_sp_acl_tcam_region_entry_remove(mlxsw_sp, region,
-					      parman_item->index);
-	mlxsw_sp_acl_rulei_destroy(rulei);
-	parman_item_remove(region->parman, parman_prio, parman_item);
-	parman_prio_fini(parman_prio);
-}
-
-static void
-mlxsw_sp_acl_tcam_region_move(struct mlxsw_sp *mlxsw_sp,
-			      struct mlxsw_sp_acl_tcam_region *region,
-			      u16 src_offset, u16 dst_offset, u16 size)
-{
-	char prcr_pl[MLXSW_REG_PRCR_LEN];
-
-	mlxsw_reg_prcr_pack(prcr_pl, MLXSW_REG_PRCR_OP_MOVE,
-			    region->tcam_region_info, src_offset,
-			    region->tcam_region_info, dst_offset, size);
-	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(prcr), prcr_pl);
-}
-
-static int mlxsw_sp_acl_tcam_region_parman_resize(void *priv,
-						  unsigned long new_count)
-{
-	struct mlxsw_sp_acl_tcam_region *region = priv;
-	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
-	u64 max_tcam_rules;
-
-	max_tcam_rules = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_TCAM_RULES);
-	if (new_count > max_tcam_rules)
-		return -EINVAL;
-	return mlxsw_sp_acl_tcam_region_resize(mlxsw_sp, region, new_count);
-}
-
-static void mlxsw_sp_acl_tcam_region_parman_move(void *priv,
-						 unsigned long from_index,
-						 unsigned long to_index,
-						 unsigned long count)
-{
-	struct mlxsw_sp_acl_tcam_region *region = priv;
-	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
-
-	mlxsw_sp_acl_tcam_region_move(mlxsw_sp, region,
-				      from_index, to_index, count);
-}
-
-static const struct parman_ops mlxsw_sp_acl_tcam_region_parman_ops = {
-	.base_count	= MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT,
-	.resize_step	= MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP,
-	.resize		= mlxsw_sp_acl_tcam_region_parman_resize,
-	.move		= mlxsw_sp_acl_tcam_region_parman_move,
-	.algo		= PARMAN_ALGO_TYPE_LSORT,
-};
-
 static struct mlxsw_sp_acl_tcam_region *
 mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam *tcam,
 				struct mlxsw_afk_element_usage *elusage)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	struct mlxsw_sp_acl_tcam_region *region;
 	int err;
 
-	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	region = kzalloc(sizeof(*region) + ops->region_priv_size, GFP_KERNEL);
 	if (!region)
 		return ERR_PTR(-ENOMEM);
 	INIT_LIST_HEAD(&region->chunk_list);
 	region->mlxsw_sp = mlxsw_sp;
 
-	region->parman = parman_create(&mlxsw_sp_acl_tcam_region_parman_ops,
-				       region);
-	if (!region->parman) {
-		err = -ENOMEM;
-		goto err_parman_create;
-	}
-
 	region->key_info = mlxsw_afk_key_info_get(afk, elusage);
 	if (IS_ERR(region->key_info)) {
 		err = PTR_ERR(region->key_info);
@@ -717,7 +515,7 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_region_id_get;
 
-	region->key_type = MLXSW_REG_PTAR_KEY_TYPE_FLEX;
+	region->key_type = ops->key_type;
 	err = mlxsw_sp_acl_tcam_region_alloc(mlxsw_sp, region);
 	if (err)
 		goto err_tcam_region_alloc;
@@ -726,13 +524,13 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_tcam_region_enable;
 
-	err = mlxsw_sp_acl_tcam_region_catchall_add(mlxsw_sp, region);
+	err = ops->region_init(mlxsw_sp, region->priv, region);
 	if (err)
-		goto err_tcam_region_catchall_add;
+		goto err_tcam_region_init;
 
 	return region;
 
-err_tcam_region_catchall_add:
+err_tcam_region_init:
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 err_tcam_region_enable:
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
@@ -741,8 +539,6 @@ err_tcam_region_alloc:
 err_region_id_get:
 	mlxsw_afk_key_info_put(region->key_info);
 err_key_info_get:
-	parman_destroy(region->parman);
-err_parman_create:
 	kfree(region);
 	return ERR_PTR(err);
 }
@@ -751,12 +547,13 @@ static void
 mlxsw_sp_acl_tcam_region_destroy(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_tcam_region *region)
 {
-	mlxsw_sp_acl_tcam_region_catchall_del(mlxsw_sp, region);
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	ops->region_fini(mlxsw_sp, region->priv);
 	mlxsw_sp_acl_tcam_region_disable(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
 	mlxsw_sp_acl_tcam_region_id_put(region->group->tcam, region->id);
 	mlxsw_afk_key_info_put(region->key_info);
-	parman_destroy(region->parman);
 	kfree(region);
 }
 
@@ -831,13 +628,14 @@ mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
 			       unsigned int priority,
 			       struct mlxsw_afk_element_usage *elusage)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
 	int err;
 
 	if (priority == MLXSW_SP_ACL_TCAM_CATCHALL_PRIO)
 		return ERR_PTR(-EINVAL);
 
-	chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
+	chunk = kzalloc(sizeof(*chunk) + ops->chunk_priv_size, GFP_KERNEL);
 	if (!chunk)
 		return ERR_PTR(-ENOMEM);
 	chunk->priority = priority;
@@ -849,7 +647,7 @@ mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_chunk_assoc;
 
-	parman_prio_init(chunk->region->parman, &chunk->parman_prio, priority);
+	ops->chunk_init(chunk->region->priv, chunk->priv, priority);
 
 	err = rhashtable_insert_fast(&group->chunk_ht, &chunk->ht_node,
 				     mlxsw_sp_acl_tcam_chunk_ht_params);
@@ -859,7 +657,7 @@ mlxsw_sp_acl_tcam_chunk_create(struct mlxsw_sp *mlxsw_sp,
 	return chunk;
 
 err_rhashtable_insert:
-	parman_prio_fini(&chunk->parman_prio);
+	ops->chunk_fini(chunk->priv);
 	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
 err_chunk_assoc:
 	kfree(chunk);
@@ -870,11 +668,12 @@ static void
 mlxsw_sp_acl_tcam_chunk_destroy(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_tcam_chunk *chunk)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_group *group = chunk->group;
 
 	rhashtable_remove_fast(&group->chunk_ht, &chunk->ht_node,
 			       mlxsw_sp_acl_tcam_chunk_ht_params);
-	parman_prio_fini(&chunk->parman_prio);
+	ops->chunk_fini(chunk->priv);
 	mlxsw_sp_acl_tcam_chunk_deassoc(mlxsw_sp, chunk);
 	kfree(chunk);
 }
@@ -908,11 +707,19 @@ static void mlxsw_sp_acl_tcam_chunk_put(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_acl_tcam_chunk_destroy(mlxsw_sp, chunk);
 }
 
+static size_t mlxsw_sp_acl_tcam_entry_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	return ops->entry_priv_size;
+}
+
 static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_acl_tcam_group *group,
 				       struct mlxsw_sp_acl_tcam_entry *entry,
 				       struct mlxsw_sp_acl_rule_info *rulei)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk;
 	struct mlxsw_sp_acl_tcam_region *region;
 	int err;
@@ -923,24 +730,16 @@ static int mlxsw_sp_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 		return PTR_ERR(chunk);
 
 	region = chunk->region;
-	err = parman_item_add(region->parman, &chunk->parman_prio,
-			      &entry->parman_item);
-	if (err)
-		goto err_parman_item_add;
 
-	err = mlxsw_sp_acl_tcam_region_entry_insert(mlxsw_sp, region,
-						    entry->parman_item.index,
-						    rulei);
+	err = ops->entry_add(mlxsw_sp, region->priv, chunk->priv,
+			     entry->priv, rulei);
 	if (err)
-		goto err_rule_insert;
+		goto err_entry_add;
 	entry->chunk = chunk;
 
 	return 0;
 
-err_rule_insert:
-	parman_item_remove(region->parman, &chunk->parman_prio,
-			   &entry->parman_item);
-err_parman_item_add:
+err_entry_add:
 	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
 	return err;
 }
@@ -948,13 +747,11 @@ err_parman_item_add:
 static void mlxsw_sp_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 					struct mlxsw_sp_acl_tcam_entry *entry)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
 	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	mlxsw_sp_acl_tcam_region_entry_remove(mlxsw_sp, region,
-					      entry->parman_item.index);
-	parman_item_remove(region->parman, &chunk->parman_prio,
-			   &entry->parman_item);
+	ops->entry_del(mlxsw_sp, region->priv, chunk->priv, entry->priv);
 	mlxsw_sp_acl_tcam_chunk_put(mlxsw_sp, chunk);
 }
 
@@ -963,12 +760,12 @@ mlxsw_sp_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_tcam_entry *entry,
 				     bool *activity)
 {
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	struct mlxsw_sp_acl_tcam_chunk *chunk = entry->chunk;
 	struct mlxsw_sp_acl_tcam_region *region = chunk->region;
 
-	return mlxsw_sp_acl_tcam_region_entry_activity_get(mlxsw_sp, region,
-							   entry->parman_item.index,
-							   activity);
+	return ops->entry_activity_get(mlxsw_sp, region->priv,
+				       entry->priv, activity);
 }
 
 static const enum mlxsw_afk_element mlxsw_sp_acl_tcam_pattern_ipv4[] = {
@@ -1081,6 +878,12 @@ mlxsw_sp_acl_tcam_flower_ruleset_group_id(void *ruleset_priv)
 	return mlxsw_sp_acl_tcam_group_id(&ruleset->group);
 }
 
+static size_t mlxsw_sp_acl_tcam_flower_rule_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+	return sizeof(struct mlxsw_sp_acl_tcam_flower_rule) +
+	       mlxsw_sp_acl_tcam_entry_priv_size(mlxsw_sp);
+}
+
 static int
 mlxsw_sp_acl_tcam_flower_rule_add(struct mlxsw_sp *mlxsw_sp,
 				  void *ruleset_priv, void *rule_priv,
@@ -1118,7 +921,7 @@ static const struct mlxsw_sp_acl_profile_ops mlxsw_sp_acl_tcam_flower_ops = {
 	.ruleset_bind		= mlxsw_sp_acl_tcam_flower_ruleset_bind,
 	.ruleset_unbind		= mlxsw_sp_acl_tcam_flower_ruleset_unbind,
 	.ruleset_group_id	= mlxsw_sp_acl_tcam_flower_ruleset_group_id,
-	.rule_priv_size		= sizeof(struct mlxsw_sp_acl_tcam_flower_rule),
+	.rule_priv_size		= mlxsw_sp_acl_tcam_flower_rule_priv_size,
 	.rule_add		= mlxsw_sp_acl_tcam_flower_rule_add,
 	.rule_del		= mlxsw_sp_acl_tcam_flower_rule_del,
 	.rule_activity_get	= mlxsw_sp_acl_tcam_flower_rule_activity_get,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
new file mode 100644
index 000000000000..5d145abee694
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -0,0 +1,103 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#ifndef _MLXSW_SPECTRUM_ACL_TCAM_H
+#define _MLXSW_SPECTRUM_ACL_TCAM_H
+
+#include <linux/list.h>
+#include <linux/parman.h>
+
+#include "reg.h"
+#include "spectrum.h"
+#include "core_acl_flex_keys.h"
+
+extern const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops;
+
+#define MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT 16
+#define MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP 16
+
+#define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
+
+struct mlxsw_sp_acl_tcam_group;
+
+struct mlxsw_sp_acl_tcam_region {
+	struct list_head list; /* Member of a TCAM group */
+	struct list_head chunk_list; /* List of chunks under this region */
+	struct mlxsw_sp_acl_tcam_group *group;
+	enum mlxsw_reg_ptar_key_type key_type;
+	u16 id; /* ACL ID and region ID - they are same */
+	char tcam_region_info[MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN];
+	struct mlxsw_afk_key_info *key_info;
+	struct mlxsw_sp *mlxsw_sp;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
+};
+
+struct mlxsw_sp_acl_ctcam_region {
+	struct parman *parman;
+	struct mlxsw_sp_acl_tcam_region *region;
+};
+
+struct mlxsw_sp_acl_ctcam_chunk {
+	struct parman_prio parman_prio;
+};
+
+struct mlxsw_sp_acl_ctcam_entry {
+	struct parman_item parman_item;
+};
+
+int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_ctcam_region *cregion,
+				   struct mlxsw_sp_acl_tcam_region *region);
+void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion);
+void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion,
+				   struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				   unsigned int priority);
+void mlxsw_sp_acl_ctcam_chunk_fini(struct mlxsw_sp_acl_ctcam_chunk *cchunk);
+int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_ctcam_region *cregion,
+				 struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				 struct mlxsw_sp_acl_ctcam_entry *centry,
+				 struct mlxsw_sp_acl_rule_info *rulei);
+void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_ctcam_region *cregion,
+				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
+				  struct mlxsw_sp_acl_ctcam_entry *centry);
+static inline unsigned int
+mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	return centry->parman_item.index;
+}
+
+#endif
-- 
cgit v1.2.3


From bab5c1cfb7a80dd4e8a0c248cf9c31dd414c1391 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:21 +0300
Subject: mlxsw: spectrum_acl: Add tcam init/fini ops

Add ops to be called on driver instance init and fini.
This is needed in order to be possible to do Spectrum-2 specific init
and fini work.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 43 +++++----------------
 .../ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c   | 13 +++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 22 +++++------
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 44 +++++++++++-----------
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    | 41 +++++++++++++++++++-
 5 files changed, 94 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index fa495f787d22..9a53dd6deaa4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -503,44 +503,14 @@ struct mlxsw_sp_acl_rule_info {
 	unsigned int counter_index;
 };
 
-enum mlxsw_sp_acl_profile {
-	MLXSW_SP_ACL_PROFILE_FLOWER,
-};
-
-struct mlxsw_sp_acl_profile_ops {
-	size_t ruleset_priv_size;
-	int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
-			   void *priv, void *ruleset_priv);
-	void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
-	int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
-			    struct mlxsw_sp_port *mlxsw_sp_port,
-			    bool ingress);
-	void (*ruleset_unbind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
-			       struct mlxsw_sp_port *mlxsw_sp_port,
-			       bool ingress);
-	u16 (*ruleset_group_id)(void *ruleset_priv);
-	size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp);
-	int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
-			void *ruleset_priv, void *rule_priv,
-			struct mlxsw_sp_acl_rule_info *rulei);
-	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
-	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
-				 bool *activity);
-};
-
-struct mlxsw_sp_acl_ops {
-	size_t priv_size;
-	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv);
-	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
-	const struct mlxsw_sp_acl_profile_ops *
-			(*profile_ops)(struct mlxsw_sp *mlxsw_sp,
-				       enum mlxsw_sp_acl_profile profile);
-};
-
 struct mlxsw_sp_acl_block;
 struct mlxsw_sp_acl_ruleset;
 
 /* spectrum_acl.c */
+enum mlxsw_sp_acl_profile {
+	MLXSW_SP_ACL_PROFILE_FLOWER,
+};
+
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl);
 struct mlxsw_sp *mlxsw_sp_acl_block_mlxsw_sp(struct mlxsw_sp_acl_block *block);
 unsigned int mlxsw_sp_acl_block_rule_count(struct mlxsw_sp_acl_block *block);
@@ -633,10 +603,15 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp);
 
 /* spectrum_acl_tcam.c */
+struct mlxsw_sp_acl_tcam;
 struct mlxsw_sp_acl_tcam_region;
 
 struct mlxsw_sp_acl_tcam_ops {
 	enum mlxsw_reg_ptar_key_type key_type;
+	size_t priv_size;
+	int (*init)(struct mlxsw_sp *mlxsw_sp, void *priv,
+		    struct mlxsw_sp_acl_tcam *tcam);
+	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
 	size_t region_priv_size;
 	int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			   struct mlxsw_sp_acl_tcam_region *region);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index aa7e03b81b4d..6aecfd62c3b0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -58,6 +58,16 @@ struct mlxsw_sp1_acl_tcam_entry {
 	struct mlxsw_sp_acl_ctcam_entry centry;
 };
 
+static int mlxsw_sp1_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
+				   struct mlxsw_sp_acl_tcam *tcam)
+{
+	return 0;
+}
+
+static void mlxsw_sp1_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+}
+
 static int
 mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
 					struct mlxsw_sp1_acl_tcam_region *region)
@@ -218,6 +228,9 @@ mlxsw_sp1_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 
 const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops = {
 	.key_type		= MLXSW_REG_PTAR_KEY_TYPE_FLEX,
+	.priv_size		= 0,
+	.init			= mlxsw_sp1_acl_tcam_init,
+	.fini			= mlxsw_sp1_acl_tcam_fini,
 	.region_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_region),
 	.region_init		= mlxsw_sp1_acl_tcam_region_init,
 	.region_fini		= mlxsw_sp1_acl_tcam_region_fini,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 1bf963cd1f12..5f71d65a8f6b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -55,7 +55,6 @@ struct mlxsw_sp_acl {
 	struct mlxsw_sp *mlxsw_sp;
 	struct mlxsw_afk *afk;
 	struct mlxsw_sp_fid *dummy_fid;
-	const struct mlxsw_sp_acl_ops *ops;
 	struct rhashtable ruleset_ht;
 	struct list_head rules;
 	struct {
@@ -63,8 +62,7 @@ struct mlxsw_sp_acl {
 		unsigned long interval;	/* ms */
 #define MLXSW_SP_ACL_RULE_ACTIVITY_UPDATE_PERIOD_MS 1000
 	} rule_activity_update;
-	unsigned long priv[0];
-	/* priv has to be always the last item */
+	struct mlxsw_sp_acl_tcam tcam;
 };
 
 struct mlxsw_afk *mlxsw_sp_acl_afk(struct mlxsw_sp_acl *acl)
@@ -340,7 +338,7 @@ mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rhashtable_init;
 
-	err = ops->ruleset_add(mlxsw_sp, acl->priv, ruleset->priv);
+	err = ops->ruleset_add(mlxsw_sp, &acl->tcam, ruleset->priv);
 	if (err)
 		goto err_ops_ruleset_add;
 
@@ -410,7 +408,7 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	struct mlxsw_sp_acl_ruleset *ruleset;
 
-	ops = acl->ops->profile_ops(mlxsw_sp, profile);
+	ops = mlxsw_sp_acl_tcam_profile_ops(mlxsw_sp, profile);
 	if (!ops)
 		return ERR_PTR(-EINVAL);
 	ruleset = __mlxsw_sp_acl_ruleset_lookup(acl, block, chain_index, ops);
@@ -428,7 +426,7 @@ mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	struct mlxsw_sp_acl_ruleset *ruleset;
 
-	ops = acl->ops->profile_ops(mlxsw_sp, profile);
+	ops = mlxsw_sp_acl_tcam_profile_ops(mlxsw_sp, profile);
 	if (!ops)
 		return ERR_PTR(-EINVAL);
 
@@ -827,12 +825,13 @@ int mlxsw_sp_acl_rule_get_stats(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 {
-	const struct mlxsw_sp_acl_ops *acl_ops = &mlxsw_sp_acl_tcam_ops;
 	struct mlxsw_sp_fid *fid;
 	struct mlxsw_sp_acl *acl;
+	size_t alloc_size;
 	int err;
 
-	acl = kzalloc(sizeof(*acl) + acl_ops->priv_size, GFP_KERNEL);
+	alloc_size = sizeof(*acl) + mlxsw_sp_acl_tcam_priv_size(mlxsw_sp);
+	acl = kzalloc(alloc_size, GFP_KERNEL);
 	if (!acl)
 		return -ENOMEM;
 	mlxsw_sp->acl = acl;
@@ -859,12 +858,10 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	acl->dummy_fid = fid;
 
 	INIT_LIST_HEAD(&acl->rules);
-	err = acl_ops->init(mlxsw_sp, acl->priv);
+	err = mlxsw_sp_acl_tcam_init(mlxsw_sp, &acl->tcam);
 	if (err)
 		goto err_acl_ops_init;
 
-	acl->ops = acl_ops;
-
 	/* Create the delayed work for the rule activity_update */
 	INIT_DELAYED_WORK(&acl->rule_activity_update.dw,
 			  mlxsw_sp_acl_rul_activity_update_work);
@@ -886,10 +883,9 @@ err_afk_create:
 void mlxsw_sp_acl_fini(struct mlxsw_sp *mlxsw_sp)
 {
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
-	const struct mlxsw_sp_acl_ops *acl_ops = acl->ops;
 
 	cancel_delayed_work_sync(&mlxsw_sp->acl->rule_activity_update.dw);
-	acl_ops->fini(mlxsw_sp, acl->priv);
+	mlxsw_sp_acl_tcam_fini(mlxsw_sp, &acl->tcam);
 	WARN_ON(!list_empty(&acl->rules));
 	mlxsw_sp_fid_put(acl->dummy_fid);
 	rhashtable_destroy(&acl->ruleset_ht);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index d2e3d9cec805..f5015a787964 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -47,17 +47,17 @@
 #include "spectrum_acl_tcam.h"
 #include "core_acl_flex_keys.h"
 
-struct mlxsw_sp_acl_tcam {
-	unsigned long *used_regions; /* bit array */
-	unsigned int max_regions;
-	unsigned long *used_groups;  /* bit array */
-	unsigned int max_groups;
-	unsigned int max_group_size;
-};
+size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp)
+{
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
+
+	return ops->priv_size;
+}
 
-static int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_tcam *tcam)
 {
-	struct mlxsw_sp_acl_tcam *tcam = priv;
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 	u64 max_tcam_regions;
 	u64 max_regions;
 	u64 max_groups;
@@ -88,17 +88,26 @@ static int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
 	tcam->max_groups = max_groups;
 	tcam->max_group_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						 ACL_MAX_GROUP_SIZE);
+
+	err = ops->init(mlxsw_sp, tcam->priv, tcam);
+	if (err)
+		goto err_tcam_init;
+
 	return 0;
 
+err_tcam_init:
+	kfree(tcam->used_groups);
 err_alloc_used_groups:
 	kfree(tcam->used_regions);
 	return err;
 }
 
-static void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_tcam *tcam)
 {
-	struct mlxsw_sp_acl_tcam *tcam = priv;
+	const struct mlxsw_sp_acl_tcam_ops *ops = mlxsw_sp->acl_tcam_ops;
 
+	ops->fini(mlxsw_sp, tcam->priv);
 	kfree(tcam->used_groups);
 	kfree(tcam->used_regions);
 }
@@ -827,10 +836,10 @@ struct mlxsw_sp_acl_tcam_flower_rule {
 
 static int
 mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
-				     void *priv, void *ruleset_priv)
+				     struct mlxsw_sp_acl_tcam *tcam,
+				     void *ruleset_priv)
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
-	struct mlxsw_sp_acl_tcam *tcam = priv;
 
 	return mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
 					   mlxsw_sp_acl_tcam_patterns,
@@ -932,7 +941,7 @@ mlxsw_sp_acl_tcam_profile_ops_arr[] = {
 	[MLXSW_SP_ACL_PROFILE_FLOWER] = &mlxsw_sp_acl_tcam_flower_ops,
 };
 
-static const struct mlxsw_sp_acl_profile_ops *
+const struct mlxsw_sp_acl_profile_ops *
 mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
 			      enum mlxsw_sp_acl_profile profile)
 {
@@ -945,10 +954,3 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
 		return NULL;
 	return ops;
 }
-
-const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops = {
-	.priv_size		= sizeof(struct mlxsw_sp_acl_tcam),
-	.init			= mlxsw_sp_acl_tcam_init,
-	.fini			= mlxsw_sp_acl_tcam_fini,
-	.profile_ops		= mlxsw_sp_acl_tcam_profile_ops,
-};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 5d145abee694..e01b75bcf009 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -42,7 +42,46 @@
 #include "spectrum.h"
 #include "core_acl_flex_keys.h"
 
-extern const struct mlxsw_sp_acl_ops mlxsw_sp_acl_tcam_ops;
+struct mlxsw_sp_acl_tcam {
+	unsigned long *used_regions; /* bit array */
+	unsigned int max_regions;
+	unsigned long *used_groups;  /* bit array */
+	unsigned int max_groups;
+	unsigned int max_group_size;
+	unsigned long priv[0];
+	/* priv has to be always the last item */
+};
+
+size_t mlxsw_sp_acl_tcam_priv_size(struct mlxsw_sp *mlxsw_sp);
+int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_tcam *tcam);
+void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_tcam *tcam);
+
+struct mlxsw_sp_acl_profile_ops {
+	size_t ruleset_priv_size;
+	int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_tcam *tcam, void *ruleset_priv);
+	void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
+	int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+			    struct mlxsw_sp_port *mlxsw_sp_port,
+			    bool ingress);
+	void (*ruleset_unbind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
+			       struct mlxsw_sp_port *mlxsw_sp_port,
+			       bool ingress);
+	u16 (*ruleset_group_id)(void *ruleset_priv);
+	size_t (*rule_priv_size)(struct mlxsw_sp *mlxsw_sp);
+	int (*rule_add)(struct mlxsw_sp *mlxsw_sp,
+			void *ruleset_priv, void *rule_priv,
+			struct mlxsw_sp_acl_rule_info *rulei);
+	void (*rule_del)(struct mlxsw_sp *mlxsw_sp, void *rule_priv);
+	int (*rule_activity_get)(struct mlxsw_sp *mlxsw_sp, void *rule_priv,
+				 bool *activity);
+};
+
+const struct mlxsw_sp_acl_profile_ops *
+mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
+			      enum mlxsw_sp_acl_profile profile);
 
 #define MLXSW_SP_ACL_TCAM_REGION_BASE_COUNT 16
 #define MLXSW_SP_ACL_TCAM_REGION_RESIZE_STEP 16
-- 
cgit v1.2.3


From c17d20838eff75caf14a25cf7bf2a532fa360820 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:22 +0300
Subject: mlxsw: spectrum_acl: Convert mlxsw_afk_create args to ops

Since the flex keys for Spectrum-2 differ not only in blocks definitions
but also in encoding layout, prepare for the implementation and pass
Spectrum/Spectrum-2 specific ops down to mlxsw_afk_create.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   1 +
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.c   |   9 +-
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.h   |   8 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |   1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   4 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c |   4 +-
 .../mellanox/mlxsw/spectrum_acl_flex_keys.c        | 133 +++++++++++++++++++++
 .../mellanox/mlxsw/spectrum_acl_flex_keys.h        | 131 --------------------
 8 files changed, 151 insertions(+), 140 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 54f1de4674ce..981e621ef9c2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -22,6 +22,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
+				   spectrum_acl_flex_keys.o \
 				   spectrum1_mr_tcam.o \
 				   spectrum_mr_tcam.o spectrum_mr.o \
 				   spectrum_qdisc.o spectrum_span.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index b32a00972e83..098665ecba06 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -43,6 +43,7 @@
 struct mlxsw_afk {
 	struct list_head key_info_list;
 	unsigned int max_blocks;
+	const struct mlxsw_afk_ops *ops;
 	const struct mlxsw_afk_block *blocks;
 	unsigned int blocks_count;
 };
@@ -69,8 +70,7 @@ static bool mlxsw_afk_blocks_check(struct mlxsw_afk *mlxsw_afk)
 }
 
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
-				   const struct mlxsw_afk_block *blocks,
-				   unsigned int blocks_count)
+				   const struct mlxsw_afk_ops *ops)
 {
 	struct mlxsw_afk *mlxsw_afk;
 
@@ -79,8 +79,9 @@ struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
 		return NULL;
 	INIT_LIST_HEAD(&mlxsw_afk->key_info_list);
 	mlxsw_afk->max_blocks = max_blocks;
-	mlxsw_afk->blocks = blocks;
-	mlxsw_afk->blocks_count = blocks_count;
+	mlxsw_afk->ops = ops;
+	mlxsw_afk->blocks = ops->blocks;
+	mlxsw_afk->blocks_count = ops->blocks_count;
 	WARN_ON(!mlxsw_afk_blocks_check(mlxsw_afk));
 	return mlxsw_afk;
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 154eccd64019..6d3817dcb0f3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -216,9 +216,13 @@ mlxsw_afk_element_usage_subset(struct mlxsw_afk_element_usage *elusage_small,
 
 struct mlxsw_afk;
 
+struct mlxsw_afk_ops {
+	const struct mlxsw_afk_block *blocks;
+	unsigned int blocks_count;
+};
+
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
-				   const struct mlxsw_afk_block *blocks,
-				   unsigned int blocks_count);
+				   const struct mlxsw_afk_ops *ops);
 void mlxsw_afk_destroy(struct mlxsw_afk *mlxsw_afk);
 
 struct mlxsw_afk_key_info;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5f5b476c0235..64c4259866bb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3623,6 +3623,7 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 
 	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
 	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
+	mlxsw_sp->afk_ops = &mlxsw_sp1_afk_ops;
 	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
 	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 9a53dd6deaa4..aa07f5b9bb5d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -173,6 +173,7 @@ struct mlxsw_sp {
 	} span;
 	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
 	const struct mlxsw_afa_ops *afa_ops;
+	const struct mlxsw_afk_ops *afk_ops;
 	const struct mlxsw_sp_mr_tcam_ops *mr_tcam_ops;
 	const struct mlxsw_sp_acl_tcam_ops *acl_tcam_ops;
 };
@@ -639,6 +640,9 @@ extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops;
 /* spectrum_acl_flex_actions.c */
 extern const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops;
 
+/* spectrum_acl_flex_keys.c */
+extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
+
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 5f71d65a8f6b..217621d79e26 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -49,7 +49,6 @@
 #include "core_acl_flex_keys.h"
 #include "core_acl_flex_actions.h"
 #include "spectrum_acl_tcam.h"
-#include "spectrum_acl_flex_keys.h"
 
 struct mlxsw_sp_acl {
 	struct mlxsw_sp *mlxsw_sp;
@@ -838,8 +837,7 @@ int mlxsw_sp_acl_init(struct mlxsw_sp *mlxsw_sp)
 	acl->mlxsw_sp = mlxsw_sp;
 	acl->afk = mlxsw_afk_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
 						       ACL_FLEX_KEYS),
-				    mlxsw_sp1_afk_blocks,
-				    MLXSW_SP1_AFK_BLOCKS_COUNT);
+				    mlxsw_sp->afk_ops);
 	if (!acl->afk) {
 		err = -ENOMEM;
 		goto err_afk_create;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
new file mode 100644
index 000000000000..4ed9a5285303
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -0,0 +1,133 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+ * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include "spectrum.h"
+#include "item.h"
+#include "core_acl_flex_keys.h"
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x00, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x02, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x00, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x02, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x02, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x0C, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 4, 2),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 24, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x08, 0, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x08, 8, 9), /* TCP_CONTROL+TCP_ECN */
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_dip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_ex1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_96_127, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_64_95, 0x04, 4),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_32_63, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip_ex[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_96_127, 0x00, 4),
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_64_95, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_packet_type[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x00, 0, 16),
+};
+
+static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
+	MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_l2_dmac),
+	MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_l2_smac),
+	MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_l2_smac_ex),
+	MLXSW_AFK_BLOCK(0x30, mlxsw_sp_afk_element_info_ipv4_sip),
+	MLXSW_AFK_BLOCK(0x31, mlxsw_sp_afk_element_info_ipv4_dip),
+	MLXSW_AFK_BLOCK(0x32, mlxsw_sp_afk_element_info_ipv4),
+	MLXSW_AFK_BLOCK(0x33, mlxsw_sp_afk_element_info_ipv4_ex),
+	MLXSW_AFK_BLOCK(0x60, mlxsw_sp_afk_element_info_ipv6_dip),
+	MLXSW_AFK_BLOCK(0x65, mlxsw_sp_afk_element_info_ipv6_ex1),
+	MLXSW_AFK_BLOCK(0x62, mlxsw_sp_afk_element_info_ipv6_sip),
+	MLXSW_AFK_BLOCK(0x63, mlxsw_sp_afk_element_info_ipv6_sip_ex),
+	MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
+};
+
+const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
+	.blocks		= mlxsw_sp1_afk_blocks,
+	.blocks_count	= ARRAY_SIZE(mlxsw_sp1_afk_blocks),
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
deleted file mode 100644
index a120c0dccd78..000000000000
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
+++ /dev/null
@@ -1,131 +0,0 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
-#define _MLXSW_SPECTRUM_ACL_FLEX_KEYS_H
-
-#include "core_acl_flex_keys.h"
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_dmac[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x00, 2),
-	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x02, 4),
-	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
-	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x00, 2),
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x02, 4),
-	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 13, 3),
-	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x08, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l2_smac_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x02, 2),
-	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4),
-	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_sip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_dip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x00, 4),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x0C, 0, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x00, 4),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 4, 2),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 24, 8),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x08, 0, 6),
-	MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x08, 8, 9), /* TCP_CONTROL+TCP_ECN */
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x00, 0, 12),
-	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x08, 29, 3),
-	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x08, 0, 16),
-	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x0C, 0, 16),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_dip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x00, 4),
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x04, 4),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_ex1[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_96_127, 0x00, 4),
-	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_64_95, 0x04, 4),
-	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x08, 0, 8),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_32_63, 0x00, 4),
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_sip_ex[] = {
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_96_127, 0x00, 4),
-	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_64_95, 0x04, 4),
-};
-
-static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_packet_type[] = {
-	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x00, 0, 16),
-};
-
-static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
-	MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_l2_dmac),
-	MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_l2_smac),
-	MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_l2_smac_ex),
-	MLXSW_AFK_BLOCK(0x30, mlxsw_sp_afk_element_info_ipv4_sip),
-	MLXSW_AFK_BLOCK(0x31, mlxsw_sp_afk_element_info_ipv4_dip),
-	MLXSW_AFK_BLOCK(0x32, mlxsw_sp_afk_element_info_ipv4),
-	MLXSW_AFK_BLOCK(0x33, mlxsw_sp_afk_element_info_ipv4_ex),
-	MLXSW_AFK_BLOCK(0x60, mlxsw_sp_afk_element_info_ipv6_dip),
-	MLXSW_AFK_BLOCK(0x65, mlxsw_sp_afk_element_info_ipv6_ex1),
-	MLXSW_AFK_BLOCK(0x62, mlxsw_sp_afk_element_info_ipv6_sip),
-	MLXSW_AFK_BLOCK(0x63, mlxsw_sp_afk_element_info_ipv6_sip_ex),
-	MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
-};
-
-#define MLXSW_SP1_AFK_BLOCKS_COUNT ARRAY_SIZE(mlxsw_sp1_afk_blocks)
-
-#endif
-- 
cgit v1.2.3


From a5995cc801f9b6a66af1d20b2025ff0c20a4c0bf Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:23 +0300
Subject: mlxsw: spectrum_acl: Move block items encoding into Spectrum op

Since Spectrum-2 encodes blocks into different HW layout, push this
code into Spectrum-specific op.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.c   | 49 +++-------------------
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.h   |  5 ++-
 .../ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c   |  3 +-
 .../mellanox/mlxsw/spectrum_acl_flex_keys.c        | 41 ++++++++++++++++++
 4 files changed, 53 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index 098665ecba06..bf645215f514 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -416,45 +416,8 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 }
 EXPORT_SYMBOL(mlxsw_afk_values_add_buf);
 
-static void mlxsw_afk_encode_u32(const struct mlxsw_item *storage_item,
-				 const struct mlxsw_item *output_item,
-				 char *storage, char *output_indexed)
-{
-	u32 value;
-
-	value = __mlxsw_item_get32(storage, storage_item, 0);
-	__mlxsw_item_set32(output_indexed, output_item, 0, value);
-}
-
-static void mlxsw_afk_encode_buf(const struct mlxsw_item *storage_item,
-				 const struct mlxsw_item *output_item,
-				 char *storage, char *output_indexed)
-{
-	char *storage_data = __mlxsw_item_data(storage, storage_item, 0);
-	char *output_data = __mlxsw_item_data(output_indexed, output_item, 0);
-	size_t len = output_item->size.bytes;
-
-	memcpy(output_data, storage_data, len);
-}
-
-#define MLXSW_AFK_KEY_BLOCK_SIZE 16
-
-static void mlxsw_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
-				 int block_index, char *storage, char *output)
-{
-	char *output_indexed = output + block_index * MLXSW_AFK_KEY_BLOCK_SIZE;
-	const struct mlxsw_item *storage_item = &elinst->info->item;
-	const struct mlxsw_item *output_item = &elinst->item;
-
-	if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
-		mlxsw_afk_encode_u32(storage_item, output_item,
-				     storage, output_indexed);
-	else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
-		mlxsw_afk_encode_buf(storage_item, output_item,
-				     storage, output_indexed);
-}
-
-void mlxsw_afk_encode(struct mlxsw_afk_key_info *key_info,
+void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
+		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
 		      char *key, char *mask)
 {
@@ -467,10 +430,10 @@ void mlxsw_afk_encode(struct mlxsw_afk_key_info *key_info,
 						       &block_index);
 		if (!elinst)
 			continue;
-		mlxsw_afk_encode_one(elinst, block_index,
-				     values->storage.key, key);
-		mlxsw_afk_encode_one(elinst, block_index,
-				     values->storage.mask, mask);
+		mlxsw_afk->ops->encode_one(elinst, block_index,
+					   values->storage.key, key);
+		mlxsw_afk->ops->encode_one(elinst, block_index,
+					   values->storage.mask, mask);
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 6d3817dcb0f3..441636cd13d8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -219,6 +219,8 @@ struct mlxsw_afk;
 struct mlxsw_afk_ops {
 	const struct mlxsw_afk_block *blocks;
 	unsigned int blocks_count;
+	void (*encode_one)(const struct mlxsw_afk_element_inst *elinst,
+			   int block_index, char *storage, char *output);
 };
 
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
@@ -255,7 +257,8 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 			      enum mlxsw_afk_element element,
 			      const char *key_value, const char *mask_value,
 			      unsigned int len);
-void mlxsw_afk_encode(struct mlxsw_afk_key_info *key_info,
+void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
+		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
 		      char *key, char *mask);
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index c5cbec5c7541..013ab8592fb9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -73,6 +73,7 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 				       unsigned int offset,
 				       struct mlxsw_sp_acl_rule_info *rulei)
 {
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
 	char *act_set;
 	char *mask;
@@ -82,7 +83,7 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 			     region->tcam_region_info, offset);
 	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
 	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
-	mlxsw_afk_encode(region->key_info, &rulei->values, key, mask);
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask);
 
 	/* Only the first action set belongs here, the rest is in KVD */
 	act_set = mlxsw_afa_block_first_set(rulei->act_block);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 4ed9a5285303..80f22b7c21da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -127,7 +127,48 @@ static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
 };
 
+static void mlxsw_sp1_afk_encode_u32(const struct mlxsw_item *storage_item,
+				     const struct mlxsw_item *output_item,
+				     char *storage, char *output_indexed)
+{
+	u32 value;
+
+	value = __mlxsw_item_get32(storage, storage_item, 0);
+	__mlxsw_item_set32(output_indexed, output_item, 0, value);
+}
+
+static void mlxsw_sp1_afk_encode_buf(const struct mlxsw_item *storage_item,
+				     const struct mlxsw_item *output_item,
+				     char *storage, char *output_indexed)
+{
+	char *storage_data = __mlxsw_item_data(storage, storage_item, 0);
+	char *output_data = __mlxsw_item_data(output_indexed, output_item, 0);
+	size_t len = output_item->size.bytes;
+
+	memcpy(output_data, storage_data, len);
+}
+
+#define MLXSW_SP1_AFK_KEY_BLOCK_SIZE 16
+
+static void
+mlxsw_sp1_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
+			 int block_index, char *storage, char *output)
+{
+	unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
+	char *output_indexed = output + offset;
+	const struct mlxsw_item *storage_item = &elinst->info->item;
+	const struct mlxsw_item *output_item = &elinst->item;
+
+	if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
+		mlxsw_sp1_afk_encode_u32(storage_item, output_item,
+					 storage, output_indexed);
+	else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
+		mlxsw_sp1_afk_encode_buf(storage_item, output_item,
+					 storage, output_indexed);
+}
+
 const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
 	.blocks		= mlxsw_sp1_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp1_afk_blocks),
+	.encode_one	= mlxsw_sp1_afk_encode_one,
 };
-- 
cgit v1.2.3


From 42df8358c3f9909eba8f09c83fbc1c6559ac43a3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:24 +0300
Subject: mlxsw: reg: Add priority field for PTCEV2 register

This is going to be needed for Spectrum-2 C-TCAM implementation.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h                | 12 +++++++++++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c |  4 ++--
 3 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 29c51ae91241..ccf4aae91630 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2402,6 +2402,15 @@ MLXSW_ITEM32(reg, ptce2, op, 0x00, 20, 3);
  */
 MLXSW_ITEM32(reg, ptce2, offset, 0x00, 0, 16);
 
+/* reg_ptce2_priority
+ * Priority of the rule, higher values win. The range is 1..cap_kvd_size-1.
+ * Note: priority does not have to be unique per rule.
+ * Within a region, higher priority should have lower offset (no limitation
+ * between regions in a multi-region).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce2, priority, 0x04, 0, 24);
+
 /* reg_ptce2_tcam_region_info
  * Opaque object that represents the TCAM region.
  * Access: Index
@@ -2437,12 +2446,13 @@ MLXSW_ITEM_BUF(reg, ptce2, flex_action_set, 0xE0,
 static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
 					enum mlxsw_reg_ptce2_op op,
 					const char *tcam_region_info,
-					u16 offset)
+					u16 offset, u32 priority)
 {
 	MLXSW_REG_ZERO(ptce2, payload);
 	mlxsw_reg_ptce2_v_set(payload, valid);
 	mlxsw_reg_ptce2_op_set(payload, op);
 	mlxsw_reg_ptce2_offset_set(payload, offset);
+	mlxsw_reg_ptce2_priority_set(payload, priority);
 	mlxsw_reg_ptce2_tcam_region_info_memcpy_to(payload, tcam_region_info);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 6aecfd62c3b0..752c2ecd7a02 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -203,7 +203,7 @@ mlxsw_sp1_acl_tcam_region_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
 	int err;
 
 	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_QUERY_CLEAR_ON_READ,
-			     _region->tcam_region_info, offset);
+			     _region->tcam_region_info, offset, 0);
 	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
 	if (err)
 		return err;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index 013ab8592fb9..34546abb3fe5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -80,7 +80,7 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	char *key;
 
 	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset);
+			     region->tcam_region_info, offset, 0);
 	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
 	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask);
@@ -100,7 +100,7 @@ mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
 
 	mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset);
+			     region->tcam_region_info, offset, 0);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
 }
 
-- 
cgit v1.2.3


From ea8b2e28aacfe8f36bacde944c04c5b909d0f364 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:25 +0300
Subject: mlxsw: spectrum_acl: Implement priority setting for rules inserted to
 TCAM

For Spectrum-2, we need to insert priority to C-TCAM because HW
needs that info in order to correctly process scenarios where rules
are in both C-TCAM and A-TCAM.

So extend the mlxsw_sp_acl_ctcam_entry_add() args to accept indication
if priority needs to be filled up and implement the priority
computation and fill-up.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c   |  5 +++--
 .../ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c   | 17 ++++++++++++----
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 23 ++++++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  6 +++++-
 4 files changed, 44 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 752c2ecd7a02..04f0c9cfae24 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -91,7 +91,8 @@ mlxsw_sp1_acl_ctcam_region_catchall_add(struct mlxsw_sp *mlxsw_sp,
 		goto err_rulei_commit;
 	err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
 					   &region->catchall.cchunk,
-					   &region->catchall.centry, rulei);
+					   &region->catchall.centry,
+					   rulei, false);
 	if (err)
 		goto err_entry_add;
 	region->catchall.rulei = rulei;
@@ -178,7 +179,7 @@ static int mlxsw_sp1_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 
 	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
 					    &chunk->cchunk, &entry->centry,
-					    rulei);
+					    rulei, false);
 }
 
 static void mlxsw_sp1_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index 34546abb3fe5..ef0d4c0a5a1f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -71,16 +71,24 @@ static int
 mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 				       struct mlxsw_sp_acl_tcam_region *region,
 				       unsigned int offset,
-				       struct mlxsw_sp_acl_rule_info *rulei)
+				       struct mlxsw_sp_acl_rule_info *rulei,
+				       bool fillup_priority)
 {
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
 	char *act_set;
+	u32 priority;
 	char *mask;
 	char *key;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority,
+					     fillup_priority);
+	if (err)
+		return err;
 
 	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset, 0);
+			     region->tcam_region_info, offset, priority);
 	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
 	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask);
@@ -172,7 +180,8 @@ int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_ctcam_region *cregion,
 				 struct mlxsw_sp_acl_ctcam_chunk *cchunk,
 				 struct mlxsw_sp_acl_ctcam_entry *centry,
-				 struct mlxsw_sp_acl_rule_info *rulei)
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 bool fillup_priority)
 {
 	int err;
 
@@ -183,7 +192,7 @@ int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 
 	err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion->region,
 						     centry->parman_item.index,
-						     rulei);
+						     rulei, fillup_priority);
 	if (err)
 		goto err_rule_insert;
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index f5015a787964..53fe51a8d720 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -112,6 +112,29 @@ void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
 	kfree(tcam->used_regions);
 }
 
+int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_rule_info *rulei,
+				   u32 *priority, bool fillup_priority)
+{
+	u64 max_priority;
+
+	if (!fillup_priority) {
+		*priority = 0;
+		return 0;
+	}
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, KVD_SIZE))
+		return -EIO;
+
+	max_priority = MLXSW_CORE_RES_GET(mlxsw_sp->core, KVD_SIZE);
+	if (rulei->priority > max_priority)
+		return -EINVAL;
+
+	/* Unlike in TC, in HW, higher number means higher priority. */
+	*priority = max_priority - rulei->priority;
+	return 0;
+}
+
 static int mlxsw_sp_acl_tcam_region_id_get(struct mlxsw_sp_acl_tcam *tcam,
 					   u16 *p_id)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index e01b75bcf009..cef769764505 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -57,6 +57,9 @@ int mlxsw_sp_acl_tcam_init(struct mlxsw_sp *mlxsw_sp,
 			   struct mlxsw_sp_acl_tcam *tcam);
 void mlxsw_sp_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_tcam *tcam);
+int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_rule_info *rulei,
+				   u32 *priority, bool fillup_priority);
 
 struct mlxsw_sp_acl_profile_ops {
 	size_t ruleset_priv_size;
@@ -128,7 +131,8 @@ int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 				 struct mlxsw_sp_acl_ctcam_region *cregion,
 				 struct mlxsw_sp_acl_ctcam_chunk *cchunk,
 				 struct mlxsw_sp_acl_ctcam_entry *centry,
-				 struct mlxsw_sp_acl_rule_info *rulei);
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 bool fillup_priority);
 void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_ctcam_region *cregion,
 				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
-- 
cgit v1.2.3


From abfd61825bdecd03249c833630b0f3c20efa7f26 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:26 +0300
Subject: mlxsw: spectrum: Prepare for multiple FW versions for Spectrum and
 Spectrum-2

Prepare for Spectrum-2 FW version checking and
make mlxsw_sp_fw_rev_validate() per-ASIC as well as required FW revision
and FW filename.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 47 +++++++++++++++++---------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h |  2 ++
 2 files changed, 33 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 64c4259866bb..5b2f4c6f5e57 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -74,15 +74,22 @@
 #include "spectrum_span.h"
 #include "../mlxfw/mlxfw.h"
 
-#define MLXSW_FWREV_MAJOR 13
-#define MLXSW_FWREV_MINOR 1620
-#define MLXSW_FWREV_SUBMINOR 192
-#define MLXSW_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
+#define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
 
-#define MLXSW_SP_FW_FILENAME \
-	"mellanox/mlxsw_spectrum-" __stringify(MLXSW_FWREV_MAJOR) \
-	"." __stringify(MLXSW_FWREV_MINOR) \
-	"." __stringify(MLXSW_FWREV_SUBMINOR) ".mfa2"
+#define MLXSW_SP1_FWREV_MAJOR 13
+#define MLXSW_SP1_FWREV_MINOR 1620
+#define MLXSW_SP1_FWREV_SUBMINOR 192
+
+static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
+	.major = MLXSW_SP1_FWREV_MAJOR,
+	.minor = MLXSW_SP1_FWREV_MINOR,
+	.subminor = MLXSW_SP1_FWREV_SUBMINOR,
+};
+
+#define MLXSW_SP1_FW_FILENAME \
+	"mellanox/mlxsw_spectrum-" __stringify(MLXSW_SP1_FWREV_MAJOR) \
+	"." __stringify(MLXSW_SP1_FWREV_MINOR) \
+	"." __stringify(MLXSW_SP1_FWREV_SUBMINOR) ".mfa2"
 
 static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum";
 static const char mlxsw_sp_driver_version[] = "1.0";
@@ -338,29 +345,35 @@ static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp,
 static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 {
 	const struct mlxsw_fw_rev *rev = &mlxsw_sp->bus_info->fw_rev;
+	const struct mlxsw_fw_rev *req_rev = mlxsw_sp->req_rev;
+	const char *fw_filename = mlxsw_sp->fw_filename;
 	const struct firmware *firmware;
 	int err;
 
+	/* Don't check if driver does not require it */
+	if (!req_rev || !fw_filename)
+		return 0;
+
 	/* Validate driver & FW are compatible */
-	if (rev->major != MLXSW_FWREV_MAJOR) {
+	if (rev->major != req_rev->major) {
 		WARN(1, "Mismatch in major FW version [%d:%d] is never expected; Please contact support\n",
-		     rev->major, MLXSW_FWREV_MAJOR);
+		     rev->major, req_rev->major);
 		return -EINVAL;
 	}
-	if (MLXSW_FWREV_MINOR_TO_BRANCH(rev->minor) ==
-	    MLXSW_FWREV_MINOR_TO_BRANCH(MLXSW_FWREV_MINOR))
+	if (MLXSW_SP_FWREV_MINOR_TO_BRANCH(rev->minor) ==
+	    MLXSW_SP_FWREV_MINOR_TO_BRANCH(req_rev->minor))
 		return 0;
 
 	dev_info(mlxsw_sp->bus_info->dev, "The firmware version %d.%d.%d is incompatible with the driver\n",
 		 rev->major, rev->minor, rev->subminor);
 	dev_info(mlxsw_sp->bus_info->dev, "Flashing firmware using file %s\n",
-		 MLXSW_SP_FW_FILENAME);
+		 fw_filename);
 
-	err = request_firmware_direct(&firmware, MLXSW_SP_FW_FILENAME,
+	err = request_firmware_direct(&firmware, fw_filename,
 				      mlxsw_sp->bus_info->dev);
 	if (err) {
 		dev_err(mlxsw_sp->bus_info->dev, "Could not request firmware file %s\n",
-			MLXSW_SP_FW_FILENAME);
+			fw_filename);
 		return err;
 	}
 
@@ -3621,6 +3634,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
+	mlxsw_sp->req_rev = &mlxsw_sp1_fw_rev;
+	mlxsw_sp->fw_filename = MLXSW_SP1_FW_FILENAME;
 	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
 	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
 	mlxsw_sp->afk_ops = &mlxsw_sp1_afk_ops;
@@ -4745,4 +4760,4 @@ MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Spectrum driver");
 MODULE_DEVICE_TABLE(pci, mlxsw_sp_pci_id_table);
-MODULE_FIRMWARE(MLXSW_SP_FW_FILENAME);
+MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index aa07f5b9bb5d..eb3d3c0bdb03 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -171,6 +171,8 @@ struct mlxsw_sp {
 		struct mlxsw_sp_span_entry *entries;
 		int entries_count;
 	} span;
+	const struct mlxsw_fw_rev *req_rev;
+	const char *fw_filename;
 	const struct mlxsw_sp_kvdl_ops *kvdl_ops;
 	const struct mlxsw_afa_ops *afa_ops;
 	const struct mlxsw_afk_ops *afk_ops;
-- 
cgit v1.2.3


From a8b9f232ecd12ab85ed6772e6c16a5925224a8e4 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 8 Jul 2018 23:51:27 +0300
Subject: mlxsw: resources: Add couple of Spectrum-2 KVD resources

These resources are needed for Spectrum-2 KVD linear management
implementation.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/resources.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index fd9299ccec72..f672a7b71de7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -42,6 +42,8 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_KVD_SIZE,
 	MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE,
 	MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE,
+	MLXSW_RES_ID_MAX_KVD_LINEAR_RANGE,
+	MLXSW_RES_ID_MAX_KVD_ACTION_SETS,
 	MLXSW_RES_ID_MAX_TRAP_GROUPS,
 	MLXSW_RES_ID_CQE_V0,
 	MLXSW_RES_ID_CQE_V1,
@@ -83,6 +85,8 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_KVD_SIZE] = 0x1001,
 	[MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002,
 	[MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003,
+	[MLXSW_RES_ID_MAX_KVD_LINEAR_RANGE] = 0x1005,
+	[MLXSW_RES_ID_MAX_KVD_ACTION_SETS] = 0x1007,
 	[MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201,
 	[MLXSW_RES_ID_CQE_V0] = 0x2210,
 	[MLXSW_RES_ID_CQE_V1] = 0x2211,
-- 
cgit v1.2.3


From 52b509218f0ab5946f9cbaf5501d88f69333f0e3 Mon Sep 17 00:00:00 2001
From: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Date: Mon, 9 Jul 2018 16:20:56 -0700
Subject: net: Use __u32 in uapi net_stamp.h

We are not supposed to use u32 in uapi, so change the flags member of
struct sock_txtime from u32 to __u32 instead.

Fixes: 80b14dee2bea ("net: Add a new socket option for a future transmit time")
Reported-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/net_tstamp.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index f8f4539f1135..97ff3c17ec4d 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -155,8 +155,8 @@ enum txtime_flags {
 };
 
 struct sock_txtime {
-	clockid_t       clockid;        /* reference clockid */
-	u32             flags;          /* flags defined by enum txtime_flags */
+	clockid_t	clockid;	/* reference clockid */
+	__u32		flags;		/* as defined by enum txtime_flags */
 };
 
 #endif /* _NET_TIMESTAMPING_H */
-- 
cgit v1.2.3


From 279ce5d117078ee8ea40c40199399889981fd808 Mon Sep 17 00:00:00 2001
From: Hang Yuan <hang.yuan@linux.intel.com>
Date: Mon, 9 Jul 2018 18:24:10 +0800
Subject: drm/i915/gvt: declare gvt as i915's soft dependency

This helps initramfs builder and other tools to know the full dependencies
of i915 and have gvt module loaded with i915.

v2: add condition and change to pre-dependency (Chris)
v3: move declaration to gvt.c. (Chris)
v4: remove xengt (Zhenyu)

Signed-off-by: Hang Yuan <hang.yuan@linux.intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---
 drivers/gpu/drm/i915/gvt/gvt.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/gvt/gvt.c b/drivers/gpu/drm/i915/gvt/gvt.c
index 4e65266e7b95..712f9d14e720 100644
--- a/drivers/gpu/drm/i915/gvt/gvt.c
+++ b/drivers/gpu/drm/i915/gvt/gvt.c
@@ -468,3 +468,7 @@ out_clean_idr:
 	kfree(gvt);
 	return ret;
 }
+
+#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
+MODULE_SOFTDEP("pre: kvmgt");
+#endif
-- 
cgit v1.2.3


From 8cff1f4a3ca58ab426f224b4bd6af61c1a9976ab Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 14:48:58 +0100
Subject: drm/i915: Remove function details from device error messages

Error messages are intended to be addressed to the user; be clear,
succinct, instructive and unambiguous. Adding the function name to
that message does not add any information the user requires and in
the process makes the message less clear.

E.g.

[  245.539711] i915 0000:00:02.0: [drm:i915_gem_init [i915]] Failed to initialize GPU, declaring it wedged!

becomes

[  245.539711] i915 0000:00:02.0: Failed to initialize GPU, declaring it wedged!

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709134858.12446-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 2959c88a37a5..c2b9a4a0ee49 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -104,8 +104,13 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV",
-		   __builtin_return_address(0), &vaf);
+	if (is_error)
+		dev_printk(level, kdev, "%pV", &vaf);
+	else
+		dev_printk(level, kdev, "[" DRM_NAME ":%ps] %pV",
+			   __builtin_return_address(0), &vaf);
+
+	va_end(args);
 
 	if (is_error && !shown_bug_once) {
 		/*
@@ -117,8 +122,6 @@ __i915_printk(struct drm_i915_private *dev_priv, const char *level,
 			dev_notice(kdev, "%s", FDO_BUG_MSG);
 		shown_bug_once = true;
 	}
-
-	va_end(args);
 }
 
 /* Map PCH device id to PCH type, or PCH_NONE if unknown. */
-- 
cgit v1.2.3


From ebfa7944d6d951c77dca6911a252917f6cecaab3 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Jul 2018 09:04:24 +0100
Subject: drm/i915/selftests: Constrain mock_gtt tests to fit within RAM

Be pessimistic and presume that we actually allocate every page we
exercise via the mock_gtt (e.g. for gvt). In which case we have to keep
our working set under the available physical memory to prevent oom.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710080424.7821-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_gtt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
index 600a3bcbd3d6..8e2e269db97e 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_gtt.c
@@ -1244,6 +1244,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 				     u64 hole_start, u64 hole_end,
 				     unsigned long end_time))
 {
+	const u64 limit = totalram_pages << PAGE_SHIFT;
 	struct i915_gem_context *ctx;
 	struct i915_hw_ppgtt *ppgtt;
 	IGT_TIMEOUT(end_time);
@@ -1256,7 +1257,7 @@ static int exercise_mock(struct drm_i915_private *i915,
 	ppgtt = ctx->ppgtt;
 	GEM_BUG_ON(!ppgtt);
 
-	err = func(i915, &ppgtt->vm, 0, ppgtt->vm.total, end_time);
+	err = func(i915, &ppgtt->vm, 0, min(ppgtt->vm.total, limit), end_time);
 
 	mock_context_close(ctx);
 	return err;
-- 
cgit v1.2.3


From cecb368d2fe40e7f6a8166fef35abc69852f7501 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 20:49:15 +0100
Subject: drm/i915/selftests: Filter out both physical address swizzles

In our swizzling selftests, we cannot predict the physical address of
the target page (at least not simply!) and so skip bit17 swizzles.
However, there are two bit17 swizzle modes and we only skipped one, with
the second being observed on the lab gdg causing the test to fail,
as soon as we hit a page with bit17 set in its address.

Testcase: igt/drv_selftest/live_objects #gdg
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709194915.5789-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_gem_object.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_object.c b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
index d77acf4cc439..c69cbd5aed52 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_object.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_object.c
@@ -375,7 +375,8 @@ static int igt_partial_tiling(void *arg)
 		}
 
 		GEM_BUG_ON(tile.swizzle == I915_BIT_6_SWIZZLE_UNKNOWN);
-		if (tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
+		if (tile.swizzle == I915_BIT_6_SWIZZLE_9_17 ||
+		    tile.swizzle == I915_BIT_6_SWIZZLE_9_10_17)
 			continue;
 
 		if (INTEL_GEN(i915) <= 2) {
-- 
cgit v1.2.3


From b7bb6138c2d5fc0a79a465478c7bbf74902289f7 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 14:01:59 +0100
Subject: drm/i915: Only reset hangcheck at the start of an activity cycle

Across a reset, the seqno (and thus hangcheck) should restart and the
hangcheck naturally progress, for when it does not, we want to declare an
emergency. Currently, we only detect if reset and reinit fails, but we
do not detect if the call to reinit succeeds but the HW is fried - as we
are resetting hangcheck on initialisation the engine. Remove that and
rely on the natural progress to reset the hangcheck timer.

References: e21b141376f9 ("drm/i915: Mark the hangcheck as idle when unparking the engines")
References: 1fd00c0faeec ("drm/i915: Declare the driver wedged if hangcheck makes no progress")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709130208.11730-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c        | 1 -
 drivers/gpu/drm/i915/intel_ringbuffer.c | 2 --
 2 files changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 6ab6ddb103d1..d937a21da2d8 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -1853,7 +1853,6 @@ static int gen8_init_common_ring(struct intel_engine_cs *engine)
 		return ret;
 
 	intel_engine_reset_breadcrumbs(engine);
-	intel_engine_init_hangcheck(engine);
 
 	if (GEM_SHOW_DEBUG() && unexpected_starting_state(engine)) {
 		struct drm_printer p = drm_debug_printer(__func__);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index d248742b1473..fab83e3c1502 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -524,8 +524,6 @@ static int init_ring_common(struct intel_engine_cs *engine)
 		goto out;
 	}
 
-	intel_engine_init_hangcheck(engine);
-
 	if (INTEL_GEN(dev_priv) > 2)
 		I915_WRITE_MODE(engine, _MASKED_BIT_DISABLE(STOP_RING));
 
-- 
cgit v1.2.3


From bf06112f869dd6a6c85a8d9fbbe879fb363011d6 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 9 Jul 2018 14:02:04 +0100
Subject: drm/i915: Tidy i915_gem_suspend()

In the next patch, we will make a fairly minor change to flush
outstanding resets before suspend. In order to keep churn to a minimum
in that functional patch, we fix up the comments and coding style now.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709130208.11730-7-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 50 +++++++++++++++++++++--------------------
 1 file changed, 26 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index b35cbfd16c9c..25728c9d2727 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5029,32 +5029,32 @@ void i915_gem_sanitize(struct drm_i915_private *i915)
 	mutex_unlock(&i915->drm.struct_mutex);
 }
 
-int i915_gem_suspend(struct drm_i915_private *dev_priv)
+int i915_gem_suspend(struct drm_i915_private *i915)
 {
-	struct drm_device *dev = &dev_priv->drm;
 	int ret;
 
 	GEM_TRACE("\n");
 
-	intel_runtime_pm_get(dev_priv);
-	intel_suspend_gt_powersave(dev_priv);
+	intel_runtime_pm_get(i915);
+	intel_suspend_gt_powersave(i915);
 
-	mutex_lock(&dev->struct_mutex);
+	mutex_lock(&i915->drm.struct_mutex);
 
-	/* We have to flush all the executing contexts to main memory so
+	/*
+	 * We have to flush all the executing contexts to main memory so
 	 * that they can saved in the hibernation image. To ensure the last
 	 * context image is coherent, we have to switch away from it. That
-	 * leaves the dev_priv->kernel_context still active when
+	 * leaves the i915->kernel_context still active when
 	 * we actually suspend, and its image in memory may not match the GPU
 	 * state. Fortunately, the kernel_context is disposable and we do
 	 * not rely on its state.
 	 */
-	if (!i915_terminally_wedged(&dev_priv->gpu_error)) {
-		ret = i915_gem_switch_to_kernel_context(dev_priv);
+	if (!i915_terminally_wedged(&i915->gpu_error)) {
+		ret = i915_gem_switch_to_kernel_context(i915);
 		if (ret)
 			goto err_unlock;
 
-		ret = i915_gem_wait_for_idle(dev_priv,
+		ret = i915_gem_wait_for_idle(i915,
 					     I915_WAIT_INTERRUPTIBLE |
 					     I915_WAIT_LOCKED |
 					     I915_WAIT_FOR_IDLE_BOOST,
@@ -5062,33 +5062,35 @@ int i915_gem_suspend(struct drm_i915_private *dev_priv)
 		if (ret && ret != -EIO)
 			goto err_unlock;
 
-		assert_kernel_context_is_current(dev_priv);
+		assert_kernel_context_is_current(i915);
 	}
-	mutex_unlock(&dev->struct_mutex);
+	mutex_unlock(&i915->drm.struct_mutex);
 
-	intel_uc_suspend(dev_priv);
+	intel_uc_suspend(i915);
 
-	cancel_delayed_work_sync(&dev_priv->gpu_error.hangcheck_work);
-	cancel_delayed_work_sync(&dev_priv->gt.retire_work);
+	cancel_delayed_work_sync(&i915->gpu_error.hangcheck_work);
+	cancel_delayed_work_sync(&i915->gt.retire_work);
 
-	/* As the idle_work is rearming if it detects a race, play safe and
+	/*
+	 * As the idle_work is rearming if it detects a race, play safe and
 	 * repeat the flush until it is definitely idle.
 	 */
-	drain_delayed_work(&dev_priv->gt.idle_work);
+	drain_delayed_work(&i915->gt.idle_work);
 
-	/* Assert that we sucessfully flushed all the work and
+	/*
+	 * Assert that we successfully flushed all the work and
 	 * reset the GPU back to its idle, low power state.
 	 */
-	WARN_ON(dev_priv->gt.awake);
-	if (WARN_ON(!intel_engines_are_idle(dev_priv)))
-		i915_gem_set_wedged(dev_priv); /* no hope, discard everything */
+	WARN_ON(i915->gt.awake);
+	if (WARN_ON(!intel_engines_are_idle(i915)))
+		i915_gem_set_wedged(i915); /* no hope, discard everything */
 
-	intel_runtime_pm_put(dev_priv);
+	intel_runtime_pm_put(i915);
 	return 0;
 
 err_unlock:
-	mutex_unlock(&dev->struct_mutex);
-	intel_runtime_pm_put(dev_priv);
+	mutex_unlock(&i915->drm.struct_mutex);
+	intel_runtime_pm_put(i915);
 	return ret;
 }
 
-- 
cgit v1.2.3


From c76f0f7cb546b661b5e0ac769850a5c854927f65 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:47 +0200
Subject: drm: Begin an API for in-kernel clients
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This the beginning of an API for in-kernel clients.
First out is a way to get a framebuffer backed by a dumb buffer.

Only GEM drivers are supported.
The original idea of using an exported dma-buf was dropped because it
also creates an anonomous file descriptor which doesn't work when the
buffer is created from a kernel thread. The easy way out is to use
drm_driver.gem_prime_vmap to get the virtual address, which requires a
GEM object. This excludes the vmwgfx driver which is the only non-GEM
driver apart from the legacy ones. A solution for vmwgfx will have to be
worked out later if it wants to support the client API which it probably
will when we have a bootsplash client.

Suggested-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-2-noralf@tronnes.org
---
 Documentation/gpu/drm-client.rst   |  12 ++
 Documentation/gpu/index.rst        |   1 +
 drivers/gpu/drm/Makefile           |   2 +-
 drivers/gpu/drm/drm_client.c       | 387 +++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/drm_drv.c          |   8 +
 drivers/gpu/drm/drm_file.c         |   3 +
 drivers/gpu/drm/drm_probe_helper.c |   3 +
 include/drm/drm_client.h           | 136 +++++++++++++
 include/drm/drm_device.h           |  21 ++
 9 files changed, 572 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/gpu/drm-client.rst
 create mode 100644 drivers/gpu/drm/drm_client.c
 create mode 100644 include/drm/drm_client.h

diff --git a/Documentation/gpu/drm-client.rst b/Documentation/gpu/drm-client.rst
new file mode 100644
index 000000000000..7e672063e7eb
--- /dev/null
+++ b/Documentation/gpu/drm-client.rst
@@ -0,0 +1,12 @@
+=================
+Kernel clients
+=================
+
+.. kernel-doc:: drivers/gpu/drm/drm_client.c
+   :doc: overview
+
+.. kernel-doc:: include/drm/drm_client.h
+   :internal:
+
+.. kernel-doc:: drivers/gpu/drm/drm_client.c
+   :export:
diff --git a/Documentation/gpu/index.rst b/Documentation/gpu/index.rst
index 00288f34c5a6..1fcf8e851e15 100644
--- a/Documentation/gpu/index.rst
+++ b/Documentation/gpu/index.rst
@@ -10,6 +10,7 @@ Linux GPU Driver Developer's Guide
    drm-kms
    drm-kms-helpers
    drm-uapi
+   drm-client
    drivers
    vga-switcheroo
    vgaarbiter
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 6ae535ca0914..0e0a3ef1abad 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -18,7 +18,7 @@ drm-y       :=	drm_auth.o drm_bufs.o drm_cache.o \
 		drm_encoder.o drm_mode_object.o drm_property.o \
 		drm_plane.o drm_color_mgmt.o drm_print.o \
 		drm_dumb_buffers.o drm_mode_config.o drm_vblank.o \
-		drm_syncobj.o drm_lease.o drm_writeback.o
+		drm_syncobj.o drm_lease.o drm_writeback.o drm_client.o
 
 drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
 drm-$(CONFIG_DRM_VM) += drm_vm.o
diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
new file mode 100644
index 000000000000..743495f7f833
--- /dev/null
+++ b/drivers/gpu/drm/drm_client.c
@@ -0,0 +1,387 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2018 Noralf Trønnes
+ */
+
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/seq_file.h>
+#include <linux/slab.h>
+
+#include <drm/drm_client.h>
+#include <drm/drm_debugfs.h>
+#include <drm/drm_device.h>
+#include <drm/drm_drv.h>
+#include <drm/drm_file.h>
+#include <drm/drm_fourcc.h>
+#include <drm/drm_gem.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_print.h>
+#include <drm/drmP.h>
+
+#include "drm_crtc_internal.h"
+#include "drm_internal.h"
+
+/**
+ * DOC: overview
+ *
+ * This library provides support for clients running in the kernel like fbdev and bootsplash.
+ * Currently it's only partially implemented, just enough to support fbdev.
+ *
+ * GEM drivers which provide a GEM based dumb buffer with a virtual address are supported.
+ */
+
+static int drm_client_open(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+	struct drm_file *file;
+
+	file = drm_file_alloc(dev->primary);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&dev->filelist_mutex);
+	list_add(&file->lhead, &dev->filelist_internal);
+	mutex_unlock(&dev->filelist_mutex);
+
+	client->file = file;
+
+	return 0;
+}
+
+static void drm_client_close(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+
+	mutex_lock(&dev->filelist_mutex);
+	list_del(&client->file->lhead);
+	mutex_unlock(&dev->filelist_mutex);
+
+	drm_file_free(client->file);
+}
+EXPORT_SYMBOL(drm_client_close);
+
+/**
+ * drm_client_new - Create a DRM client
+ * @dev: DRM device
+ * @client: DRM client
+ * @name: Client name
+ * @funcs: DRM client functions (optional)
+ *
+ * The caller needs to hold a reference on @dev before calling this function.
+ * The client is freed when the &drm_device is unregistered. See drm_client_release().
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
+		   const char *name, const struct drm_client_funcs *funcs)
+{
+	bool registered;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET) ||
+	    !dev->driver->dumb_create || !dev->driver->gem_prime_vmap)
+		return -ENOTSUPP;
+
+	if (funcs && !try_module_get(funcs->owner))
+		return -ENODEV;
+
+	client->dev = dev;
+	client->name = name;
+	client->funcs = funcs;
+
+	ret = drm_client_open(client);
+	if (ret)
+		goto err_put_module;
+
+	mutex_lock(&dev->clientlist_mutex);
+	registered = dev->registered;
+	if (registered)
+		list_add(&client->list, &dev->clientlist);
+	mutex_unlock(&dev->clientlist_mutex);
+	if (!registered) {
+		ret = -ENODEV;
+		goto err_close;
+	}
+
+	drm_dev_get(dev);
+
+	return 0;
+
+err_close:
+	drm_client_close(client);
+err_put_module:
+	if (funcs)
+		module_put(funcs->owner);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_client_new);
+
+/**
+ * drm_client_release - Release DRM client resources
+ * @client: DRM client
+ *
+ * Releases resources by closing the &drm_file that was opened by drm_client_new().
+ * It is called automatically if the &drm_client_funcs.unregister callback is _not_ set.
+ *
+ * This function should only be called from the unregister callback. An exception
+ * is fbdev which cannot free the buffer if userspace has open file descriptors.
+ *
+ * Note:
+ * Clients cannot initiate a release by themselves. This is done to keep the code simple.
+ * The driver has to be unloaded before the client can be unloaded.
+ */
+void drm_client_release(struct drm_client_dev *client)
+{
+	struct drm_device *dev = client->dev;
+
+	DRM_DEV_DEBUG_KMS(dev->dev, "%s\n", client->name);
+
+	drm_client_close(client);
+	drm_dev_put(dev);
+	if (client->funcs)
+		module_put(client->funcs->owner);
+}
+EXPORT_SYMBOL(drm_client_release);
+
+void drm_client_dev_unregister(struct drm_device *dev)
+{
+	struct drm_client_dev *client, *tmp;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry_safe(client, tmp, &dev->clientlist, list) {
+		list_del(&client->list);
+		if (client->funcs && client->funcs->unregister) {
+			client->funcs->unregister(client);
+		} else {
+			drm_client_release(client);
+			kfree(client);
+		}
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+
+/**
+ * drm_client_dev_hotplug - Send hotplug event to clients
+ * @dev: DRM device
+ *
+ * This function calls the &drm_client_funcs.hotplug callback on the attached clients.
+ *
+ * drm_kms_helper_hotplug_event() calls this function, so drivers that use it
+ * don't need to call this function themselves.
+ */
+void drm_client_dev_hotplug(struct drm_device *dev)
+{
+	struct drm_client_dev *client;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list) {
+		if (!client->funcs || !client->funcs->hotplug)
+			continue;
+
+		ret = client->funcs->hotplug(client);
+		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+EXPORT_SYMBOL(drm_client_dev_hotplug);
+
+void drm_client_dev_restore(struct drm_device *dev)
+{
+	struct drm_client_dev *client;
+	int ret;
+
+	if (!drm_core_check_feature(dev, DRIVER_MODESET))
+		return;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list) {
+		if (!client->funcs || !client->funcs->restore)
+			continue;
+
+		ret = client->funcs->restore(client);
+		DRM_DEV_DEBUG_KMS(dev->dev, "%s: ret=%d\n", client->name, ret);
+		if (!ret) /* The first one to return zero gets the privilege to restore */
+			break;
+	}
+	mutex_unlock(&dev->clientlist_mutex);
+}
+
+static void drm_client_buffer_delete(struct drm_client_buffer *buffer)
+{
+	struct drm_device *dev = buffer->client->dev;
+
+	if (buffer->vaddr && dev->driver->gem_prime_vunmap)
+		dev->driver->gem_prime_vunmap(buffer->gem, buffer->vaddr);
+
+	if (buffer->gem)
+		drm_gem_object_put_unlocked(buffer->gem);
+
+	drm_mode_destroy_dumb(dev, buffer->handle, buffer->client->file);
+	kfree(buffer);
+}
+
+static struct drm_client_buffer *
+drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
+{
+	struct drm_mode_create_dumb dumb_args = { };
+	struct drm_device *dev = client->dev;
+	struct drm_client_buffer *buffer;
+	struct drm_gem_object *obj;
+	void *vaddr;
+	int ret;
+
+	buffer = kzalloc(sizeof(*buffer), GFP_KERNEL);
+	if (!buffer)
+		return ERR_PTR(-ENOMEM);
+
+	buffer->client = client;
+
+	dumb_args.width = width;
+	dumb_args.height = height;
+	dumb_args.bpp = drm_format_plane_cpp(format, 0) * 8;
+	ret = drm_mode_create_dumb(dev, &dumb_args, client->file);
+	if (ret)
+		goto err_free;
+
+	buffer->handle = dumb_args.handle;
+	buffer->pitch = dumb_args.pitch;
+
+	obj = drm_gem_object_lookup(client->file, dumb_args.handle);
+	if (!obj)  {
+		ret = -ENOENT;
+		goto err_delete;
+	}
+
+	buffer->gem = obj;
+
+	/*
+	 * FIXME: The dependency on GEM here isn't required, we could
+	 * convert the driver handle to a dma-buf instead and use the
+	 * backend-agnostic dma-buf vmap support instead. This would
+	 * require that the handle2fd prime ioctl is reworked to pull the
+	 * fd_install step out of the driver backend hooks, to make that
+	 * final step optional for internal users.
+	 */
+	vaddr = dev->driver->gem_prime_vmap(obj);
+	if (!vaddr) {
+		ret = -ENOMEM;
+		goto err_delete;
+	}
+
+	buffer->vaddr = vaddr;
+
+	return buffer;
+
+err_delete:
+	drm_client_buffer_delete(buffer);
+err_free:
+	kfree(buffer);
+
+	return ERR_PTR(ret);
+}
+
+static void drm_client_buffer_rmfb(struct drm_client_buffer *buffer)
+{
+	int ret;
+
+	if (!buffer->fb)
+		return;
+
+	ret = drm_mode_rmfb(buffer->client->dev, buffer->fb->base.id, buffer->client->file);
+	if (ret)
+		DRM_DEV_ERROR(buffer->client->dev->dev,
+			      "Error removing FB:%u (%d)\n", buffer->fb->base.id, ret);
+
+	buffer->fb = NULL;
+}
+
+static int drm_client_buffer_addfb(struct drm_client_buffer *buffer,
+				   u32 width, u32 height, u32 format)
+{
+	struct drm_client_dev *client = buffer->client;
+	struct drm_mode_fb_cmd fb_req = { };
+	const struct drm_format_info *info;
+	int ret;
+
+	info = drm_format_info(format);
+	fb_req.bpp = info->cpp[0] * 8;
+	fb_req.depth = info->depth;
+	fb_req.width = width;
+	fb_req.height = height;
+	fb_req.handle = buffer->handle;
+	fb_req.pitch = buffer->pitch;
+
+	ret = drm_mode_addfb(client->dev, &fb_req, client->file);
+	if (ret)
+		return ret;
+
+	buffer->fb = drm_framebuffer_lookup(client->dev, buffer->client->file, fb_req.fb_id);
+	if (WARN_ON(!buffer->fb))
+		return -ENOENT;
+
+	/* drop the reference we picked up in framebuffer lookup */
+	drm_framebuffer_put(buffer->fb);
+
+	strscpy(buffer->fb->comm, client->name, TASK_COMM_LEN);
+
+	return 0;
+}
+
+/**
+ * drm_client_framebuffer_create - Create a client framebuffer
+ * @client: DRM client
+ * @width: Framebuffer width
+ * @height: Framebuffer height
+ * @format: Buffer format
+ *
+ * This function creates a &drm_client_buffer which consists of a
+ * &drm_framebuffer backed by a dumb buffer.
+ * Call drm_client_framebuffer_delete() to free the buffer.
+ *
+ * Returns:
+ * Pointer to a client buffer or an error pointer on failure.
+ */
+struct drm_client_buffer *
+drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format)
+{
+	struct drm_client_buffer *buffer;
+	int ret;
+
+	buffer = drm_client_buffer_create(client, width, height, format);
+	if (IS_ERR(buffer))
+		return buffer;
+
+	ret = drm_client_buffer_addfb(buffer, width, height, format);
+	if (ret) {
+		drm_client_buffer_delete(buffer);
+		return ERR_PTR(ret);
+	}
+
+	return buffer;
+}
+EXPORT_SYMBOL(drm_client_framebuffer_create);
+
+/**
+ * drm_client_framebuffer_delete - Delete a client framebuffer
+ * @buffer: DRM client buffer (can be NULL)
+ */
+void drm_client_framebuffer_delete(struct drm_client_buffer *buffer)
+{
+	if (!buffer)
+		return;
+
+	drm_client_buffer_rmfb(buffer);
+	drm_client_buffer_delete(buffer);
+}
+EXPORT_SYMBOL(drm_client_framebuffer_delete);
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 7af748ed1c58..6eb935bb2f92 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -34,6 +34,7 @@
 #include <linux/slab.h>
 #include <linux/srcu.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_drv.h>
 #include <drm/drmP.h>
 
@@ -505,6 +506,8 @@ int drm_dev_init(struct drm_device *dev,
 	dev->driver = driver;
 
 	INIT_LIST_HEAD(&dev->filelist);
+	INIT_LIST_HEAD(&dev->filelist_internal);
+	INIT_LIST_HEAD(&dev->clientlist);
 	INIT_LIST_HEAD(&dev->ctxlist);
 	INIT_LIST_HEAD(&dev->vmalist);
 	INIT_LIST_HEAD(&dev->maplist);
@@ -514,6 +517,7 @@ int drm_dev_init(struct drm_device *dev,
 	spin_lock_init(&dev->event_lock);
 	mutex_init(&dev->struct_mutex);
 	mutex_init(&dev->filelist_mutex);
+	mutex_init(&dev->clientlist_mutex);
 	mutex_init(&dev->ctxlist_mutex);
 	mutex_init(&dev->master_mutex);
 
@@ -569,6 +573,7 @@ err_minors:
 err_free:
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->ctxlist_mutex);
+	mutex_destroy(&dev->clientlist_mutex);
 	mutex_destroy(&dev->filelist_mutex);
 	mutex_destroy(&dev->struct_mutex);
 	return ret;
@@ -603,6 +608,7 @@ void drm_dev_fini(struct drm_device *dev)
 
 	mutex_destroy(&dev->master_mutex);
 	mutex_destroy(&dev->ctxlist_mutex);
+	mutex_destroy(&dev->clientlist_mutex);
 	mutex_destroy(&dev->filelist_mutex);
 	mutex_destroy(&dev->struct_mutex);
 	kfree(dev->unique);
@@ -858,6 +864,8 @@ void drm_dev_unregister(struct drm_device *dev)
 
 	dev->registered = false;
 
+	drm_client_dev_unregister(dev);
+
 	if (drm_core_check_feature(dev, DRIVER_MODESET))
 		drm_modeset_unregister_all(dev);
 
diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
index 66bb403dc8ab..ffa8dc35515f 100644
--- a/drivers/gpu/drm/drm_file.c
+++ b/drivers/gpu/drm/drm_file.c
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_file.h>
 #include <drm/drmP.h>
 
@@ -444,6 +445,8 @@ void drm_lastclose(struct drm_device * dev)
 
 	if (drm_core_check_feature(dev, DRIVER_LEGACY))
 		drm_legacy_dev_reinit(dev);
+
+	drm_client_dev_restore(dev);
 }
 
 /**
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 1a901fe9e23e..34fe2704a31c 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -33,6 +33,7 @@
 #include <linux/moduleparam.h>
 
 #include <drm/drmP.h>
+#include <drm/drm_client.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_fourcc.h>
 #include <drm/drm_crtc_helper.h>
@@ -559,6 +560,8 @@ void drm_kms_helper_hotplug_event(struct drm_device *dev)
 	drm_sysfs_hotplug_event(dev);
 	if (dev->mode_config.funcs->output_poll_changed)
 		dev->mode_config.funcs->output_poll_changed(dev);
+
+	drm_client_dev_hotplug(dev);
 }
 EXPORT_SYMBOL(drm_kms_helper_hotplug_event);
 
diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h
new file mode 100644
index 000000000000..671052d80e38
--- /dev/null
+++ b/include/drm/drm_client.h
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _DRM_CLIENT_H_
+#define _DRM_CLIENT_H_
+
+#include <linux/types.h>
+
+struct drm_client_dev;
+struct drm_device;
+struct drm_file;
+struct drm_framebuffer;
+struct drm_gem_object;
+struct module;
+
+/**
+ * struct drm_client_funcs - DRM client callbacks
+ */
+struct drm_client_funcs {
+	/**
+	 * @owner: The module owner
+	 */
+	struct module *owner;
+
+	/**
+	 * @unregister:
+	 *
+	 * Called when &drm_device is unregistered. The client should respond by
+	 * releasing it's resources using drm_client_release().
+	 *
+	 * This callback is optional.
+	 */
+	void (*unregister)(struct drm_client_dev *client);
+
+	/**
+	 * @restore:
+	 *
+	 * Called on drm_lastclose(). The first client instance in the list that
+	 * returns zero gets the privilege to restore and no more clients are
+	 * called. This callback is not called after @unregister has been called.
+	 *
+	 * This callback is optional.
+	 */
+	int (*restore)(struct drm_client_dev *client);
+
+	/**
+	 * @hotplug:
+	 *
+	 * Called on drm_kms_helper_hotplug_event().
+	 * This callback is not called after @unregister has been called.
+	 *
+	 * This callback is optional.
+	 */
+	int (*hotplug)(struct drm_client_dev *client);
+};
+
+/**
+ * struct drm_client_dev - DRM client instance
+ */
+struct drm_client_dev {
+	/**
+	 * @dev: DRM device
+	 */
+	struct drm_device *dev;
+
+	/**
+	 * @name: Name of the client.
+	 */
+	const char *name;
+
+	/**
+	 * @list:
+	 *
+	 * List of all clients of a DRM device, linked into
+	 * &drm_device.clientlist. Protected by &drm_device.clientlist_mutex.
+	 */
+	struct list_head list;
+
+	/**
+	 * @funcs: DRM client functions (optional)
+	 */
+	const struct drm_client_funcs *funcs;
+
+	/**
+	 * @file: DRM file
+	 */
+	struct drm_file *file;
+};
+
+int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
+		   const char *name, const struct drm_client_funcs *funcs);
+void drm_client_release(struct drm_client_dev *client);
+
+void drm_client_dev_unregister(struct drm_device *dev);
+void drm_client_dev_hotplug(struct drm_device *dev);
+void drm_client_dev_restore(struct drm_device *dev);
+
+/**
+ * struct drm_client_buffer - DRM client buffer
+ */
+struct drm_client_buffer {
+	/**
+	 * @client: DRM client
+	 */
+	struct drm_client_dev *client;
+
+	/**
+	 * @handle: Buffer handle
+	 */
+	u32 handle;
+
+	/**
+	 * @pitch: Buffer pitch
+	 */
+	u32 pitch;
+
+	/**
+	 * @gem: GEM object backing this buffer
+	 */
+	struct drm_gem_object *gem;
+
+	/**
+	 * @vaddr: Virtual address for the buffer
+	 */
+	void *vaddr;
+
+	/**
+	 * @fb: DRM framebuffer
+	 */
+	struct drm_framebuffer *fb;
+};
+
+struct drm_client_buffer *
+drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format);
+void drm_client_framebuffer_delete(struct drm_client_buffer *buffer);
+
+#endif
diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
index 858ba19a3e29..f9c6e0e3aec7 100644
--- a/include/drm/drm_device.h
+++ b/include/drm/drm_device.h
@@ -74,6 +74,27 @@ struct drm_device {
 	struct mutex filelist_mutex;
 	struct list_head filelist;
 
+	/**
+	 * @filelist_internal:
+	 *
+	 * List of open DRM files for in-kernel clients. Protected by @filelist_mutex.
+	 */
+	struct list_head filelist_internal;
+
+	/**
+	 * @clientlist_mutex:
+	 *
+	 * Protects @clientlist access.
+	 */
+	struct mutex clientlist_mutex;
+
+	/**
+	 * @clientlist:
+	 *
+	 * List of in-kernel clients. Protected by @clientlist_mutex.
+	 */
+	struct list_head clientlist;
+
 	/** \name Memory management */
 	/*@{ */
 	struct list_head maplist;	/**< Linked list of regions */
-- 
cgit v1.2.3


From d536540f304ce0ee35db9f67f7d880bc09f3743f Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:48 +0200
Subject: drm/fb-helper: Add generic fbdev emulation .fb_probe function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is the first step in getting generic fbdev emulation.
A drm_fb_helper_funcs.fb_probe function is added which uses the
DRM client API to get a framebuffer backed by a dumb buffer.

Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-3-noralf@tronnes.org
---
 drivers/gpu/drm/drm_fb_helper.c | 199 +++++++++++++++++++++++++++++++++++++++-
 include/drm/drm_fb_helper.h     |  31 +++++++
 2 files changed, 229 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index d697c1c4a067..7e29d5340a17 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -30,6 +30,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/console.h>
+#include <linux/dma-buf.h>
 #include <linux/kernel.h>
 #include <linux/sysrq.h>
 #include <linux/slab.h>
@@ -738,6 +739,24 @@ static void drm_fb_helper_resume_worker(struct work_struct *work)
 	console_unlock();
 }
 
+static void drm_fb_helper_dirty_blit_real(struct drm_fb_helper *fb_helper,
+					  struct drm_clip_rect *clip)
+{
+	struct drm_framebuffer *fb = fb_helper->fb;
+	unsigned int cpp = drm_format_plane_cpp(fb->format->format, 0);
+	size_t offset = clip->y1 * fb->pitches[0] + clip->x1 * cpp;
+	void *src = fb_helper->fbdev->screen_buffer + offset;
+	void *dst = fb_helper->buffer->vaddr + offset;
+	size_t len = (clip->x2 - clip->x1) * cpp;
+	unsigned int y;
+
+	for (y = clip->y1; y < clip->y2; y++) {
+		memcpy(dst, src, len);
+		src += fb->pitches[0];
+		dst += fb->pitches[0];
+	}
+}
+
 static void drm_fb_helper_dirty_work(struct work_struct *work)
 {
 	struct drm_fb_helper *helper = container_of(work, struct drm_fb_helper,
@@ -753,8 +772,12 @@ static void drm_fb_helper_dirty_work(struct work_struct *work)
 	spin_unlock_irqrestore(&helper->dirty_lock, flags);
 
 	/* call dirty callback only when it has been really touched */
-	if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2)
+	if (clip_copy.x1 < clip_copy.x2 && clip_copy.y1 < clip_copy.y2) {
+		/* Generic fbdev uses a shadow buffer */
+		if (helper->buffer)
+			drm_fb_helper_dirty_blit_real(helper, &clip_copy);
 		helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, &clip_copy, 1);
+	}
 }
 
 /**
@@ -2921,6 +2944,180 @@ void drm_fb_helper_output_poll_changed(struct drm_device *dev)
 }
 EXPORT_SYMBOL(drm_fb_helper_output_poll_changed);
 
+/* @user: 1=userspace, 0=fbcon */
+static int drm_fbdev_fb_open(struct fb_info *info, int user)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	if (!try_module_get(fb_helper->dev->driver->fops->owner))
+		return -ENODEV;
+
+	return 0;
+}
+
+static int drm_fbdev_fb_release(struct fb_info *info, int user)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	module_put(fb_helper->dev->driver->fops->owner);
+
+	return 0;
+}
+
+/*
+ * fb_ops.fb_destroy is called by the last put_fb_info() call at the end of
+ * unregister_framebuffer() or fb_release().
+ */
+static void drm_fbdev_fb_destroy(struct fb_info *info)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+	struct fb_info *fbi = fb_helper->fbdev;
+	struct fb_ops *fbops = NULL;
+	void *shadow = NULL;
+
+	if (fbi->fbdefio) {
+		fb_deferred_io_cleanup(fbi);
+		shadow = fbi->screen_buffer;
+		fbops = fbi->fbops;
+	}
+
+	drm_fb_helper_fini(fb_helper);
+
+	if (shadow) {
+		vfree(shadow);
+		kfree(fbops);
+	}
+
+	drm_client_framebuffer_delete(fb_helper->buffer);
+	/*
+	 * FIXME:
+	 * Remove conditional when all CMA drivers have been moved over to using
+	 * drm_fbdev_generic_setup().
+	 */
+	if (fb_helper->client.funcs) {
+		drm_client_release(&fb_helper->client);
+		kfree(fb_helper);
+	}
+}
+
+static int drm_fbdev_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
+{
+	struct drm_fb_helper *fb_helper = info->par;
+
+	if (fb_helper->dev->driver->gem_prime_mmap)
+		return fb_helper->dev->driver->gem_prime_mmap(fb_helper->buffer->gem, vma);
+	else
+		return -ENODEV;
+}
+
+static struct fb_ops drm_fbdev_fb_ops = {
+	.owner		= THIS_MODULE,
+	DRM_FB_HELPER_DEFAULT_OPS,
+	.fb_open	= drm_fbdev_fb_open,
+	.fb_release	= drm_fbdev_fb_release,
+	.fb_destroy	= drm_fbdev_fb_destroy,
+	.fb_mmap	= drm_fbdev_fb_mmap,
+	.fb_read	= drm_fb_helper_sys_read,
+	.fb_write	= drm_fb_helper_sys_write,
+	.fb_fillrect	= drm_fb_helper_sys_fillrect,
+	.fb_copyarea	= drm_fb_helper_sys_copyarea,
+	.fb_imageblit	= drm_fb_helper_sys_imageblit,
+};
+
+static struct fb_deferred_io drm_fbdev_defio = {
+	.delay		= HZ / 20,
+	.deferred_io	= drm_fb_helper_deferred_io,
+};
+
+/**
+ * drm_fb_helper_generic_probe - Generic fbdev emulation probe helper
+ * @fb_helper: fbdev helper structure
+ * @sizes: describes fbdev size and scanout surface size
+ *
+ * This function uses the client API to crate a framebuffer backed by a dumb buffer.
+ *
+ * The _sys_ versions are used for &fb_ops.fb_read, fb_write, fb_fillrect,
+ * fb_copyarea, fb_imageblit.
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+				struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_client_dev *client = &fb_helper->client;
+	struct drm_client_buffer *buffer;
+	struct drm_framebuffer *fb;
+	struct fb_info *fbi;
+	u32 format;
+	int ret;
+
+	DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n",
+		      sizes->surface_width, sizes->surface_height,
+		      sizes->surface_bpp);
+
+	format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth);
+	buffer = drm_client_framebuffer_create(client, sizes->surface_width,
+					       sizes->surface_height, format);
+	if (IS_ERR(buffer))
+		return PTR_ERR(buffer);
+
+	fb_helper->buffer = buffer;
+	fb_helper->fb = buffer->fb;
+	fb = buffer->fb;
+
+	fbi = drm_fb_helper_alloc_fbi(fb_helper);
+	if (IS_ERR(fbi)) {
+		ret = PTR_ERR(fbi);
+		goto err_free_buffer;
+	}
+
+	fbi->par = fb_helper;
+	fbi->fbops = &drm_fbdev_fb_ops;
+	fbi->screen_size = fb->height * fb->pitches[0];
+	fbi->fix.smem_len = fbi->screen_size;
+	fbi->screen_buffer = buffer->vaddr;
+	strcpy(fbi->fix.id, "DRM emulated");
+
+	drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth);
+	drm_fb_helper_fill_var(fbi, fb_helper, sizes->fb_width, sizes->fb_height);
+
+	if (fb->funcs->dirty) {
+		struct fb_ops *fbops;
+		void *shadow;
+
+		/*
+		 * fb_deferred_io_cleanup() clears &fbops->fb_mmap so a per
+		 * instance version is necessary.
+		 */
+		fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
+		shadow = vzalloc(fbi->screen_size);
+		if (!fbops || !shadow) {
+			kfree(fbops);
+			vfree(shadow);
+			ret = -ENOMEM;
+			goto err_fb_info_destroy;
+		}
+
+		*fbops = *fbi->fbops;
+		fbi->fbops = fbops;
+		fbi->screen_buffer = shadow;
+		fbi->fbdefio = &drm_fbdev_defio;
+
+		fb_deferred_io_init(fbi);
+	}
+
+	return 0;
+
+err_fb_info_destroy:
+	drm_fb_helper_fini(fb_helper);
+err_free_buffer:
+	drm_client_framebuffer_delete(buffer);
+
+	return ret;
+}
+EXPORT_SYMBOL(drm_fb_helper_generic_probe);
+
 /* The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT)
  * but the module doesn't depend on any fb console symbols.  At least
  * attempt to load fbcon to avoid leaving the system without a usable console.
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index b069433e7fc1..c134bbcfd2e9 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -32,6 +32,7 @@
 
 struct drm_fb_helper;
 
+#include <drm/drm_client.h>
 #include <drm/drm_crtc.h>
 #include <drm/drm_device.h>
 #include <linux/kgdb.h>
@@ -154,6 +155,20 @@ struct drm_fb_helper_connector {
  * operations.
  */
 struct drm_fb_helper {
+	/**
+	 * @client:
+	 *
+	 * DRM client used by the generic fbdev emulation.
+	 */
+	struct drm_client_dev client;
+
+	/**
+	 * @buffer:
+	 *
+	 * Framebuffer used by the generic fbdev emulation.
+	 */
+	struct drm_client_buffer *buffer;
+
 	struct drm_framebuffer *fb;
 	struct drm_device *dev;
 	int crtc_count;
@@ -234,6 +249,12 @@ struct drm_fb_helper {
 	int preferred_bpp;
 };
 
+static inline struct drm_fb_helper *
+drm_fb_helper_from_client(struct drm_client_dev *client)
+{
+	return container_of(client, struct drm_fb_helper, client);
+}
+
 /**
  * define DRM_FB_HELPER_DEFAULT_OPS - helper define for drm drivers
  *
@@ -330,6 +351,9 @@ void drm_fb_helper_fbdev_teardown(struct drm_device *dev);
 
 void drm_fb_helper_lastclose(struct drm_device *dev);
 void drm_fb_helper_output_poll_changed(struct drm_device *dev);
+
+int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+				struct drm_fb_helper_surface_size *sizes);
 #else
 static inline void drm_fb_helper_prepare(struct drm_device *dev,
 					struct drm_fb_helper *helper,
@@ -564,6 +588,13 @@ static inline void drm_fb_helper_output_poll_changed(struct drm_device *dev)
 {
 }
 
+static inline int
+drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
+			    struct drm_fb_helper_surface_size *sizes)
+{
+	return 0;
+}
+
 #endif
 
 static inline int
-- 
cgit v1.2.3


From 244007ecb6bb94fa4e9b9a969fa86f2ad86ec543 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:49 +0200
Subject: drm/pl111: Set .gem_prime_vmap and .gem_prime_mmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These are needed for pl111 to use the generic fbdev emulation.

Cc: Eric Anholt <eric@anholt.net>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-4-noralf@tronnes.org
---
 drivers/gpu/drm/pl111/pl111_drv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index 054b93689d94..17a38e85ba7d 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -250,6 +250,8 @@ static struct drm_driver pl111_drm_driver = {
 	.gem_prime_import_sg_table = pl111_gem_import_sg_table,
 	.gem_prime_export = drm_gem_prime_export,
 	.gem_prime_get_sg_table	= drm_gem_cma_prime_get_sg_table,
+	.gem_prime_mmap = drm_gem_cma_prime_mmap,
+	.gem_prime_vmap = drm_gem_cma_prime_vmap,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = pl111_debugfs_init,
-- 
cgit v1.2.3


From 894a677f4b3e6d2ab8d01bb46c1fbd5f92e4591b Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:50 +0200
Subject: drm/cma-helper: Use the generic fbdev emulation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This switches the CMA helper drivers that use its fbdev emulation over
to the generic fbdev emulation. It's the first phase of using generic
fbdev. A later phase will use DRM client callbacks for the
lastclose/hotplug/remove callbacks.

There are currently 2 fbdev init/fini functions:
- drm_fb_cma_fbdev_init/drm_fb_cma_fbdev_fini
- drm_fbdev_cma_init/drm_fbdev_cma_fini

This is because the work on generic fbdev came up during a fbdev
refactoring and thus wasn't completed. No point in completing that
refactoring when drivers will soon move to drm_fb_helper_generic_probe().

tinydrm uses drm_fb_cma_fbdev_init_with_funcs().

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Acked-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-5-noralf@tronnes.org
---
 drivers/gpu/drm/drm_fb_cma_helper.c | 338 ++++--------------------------------
 include/drm/drm_fb_cma_helper.h     |   3 -
 2 files changed, 31 insertions(+), 310 deletions(-)

diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 186d00adfb5f..718c7f961d8a 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -18,6 +18,7 @@
  */
 
 #include <drm/drmP.h>
+#include <drm/drm_client.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_cma_helper.h>
@@ -26,11 +27,8 @@
 #include <drm/drm_print.h>
 #include <linux/module.h>
 
-#define DEFAULT_FBDEFIO_DELAY_MS 50
-
 struct drm_fbdev_cma {
 	struct drm_fb_helper	fb_helper;
-	const struct drm_framebuffer_funcs *fb_funcs;
 };
 
 /**
@@ -44,36 +42,6 @@ struct drm_fbdev_cma {
  *
  * An fbdev framebuffer backed by cma is also available by calling
  * drm_fb_cma_fbdev_init(). drm_fb_cma_fbdev_fini() tears it down.
- * If the &drm_framebuffer_funcs.dirty callback is set, fb_deferred_io will be
- * set up automatically. &drm_framebuffer_funcs.dirty is called by
- * drm_fb_helper_deferred_io() in process context (&struct delayed_work).
- *
- * Example fbdev deferred io code::
- *
- *     static int driver_fb_dirty(struct drm_framebuffer *fb,
- *                                struct drm_file *file_priv,
- *                                unsigned flags, unsigned color,
- *                                struct drm_clip_rect *clips,
- *                                unsigned num_clips)
- *     {
- *         struct drm_gem_cma_object *cma = drm_fb_cma_get_gem_obj(fb, 0);
- *         ... push changes ...
- *         return 0;
- *     }
- *
- *     static struct drm_framebuffer_funcs driver_fb_funcs = {
- *         .destroy       = drm_gem_fb_destroy,
- *         .create_handle = drm_gem_fb_create_handle,
- *         .dirty         = driver_fb_dirty,
- *     };
- *
- * Initialize::
- *
- *     fbdev = drm_fb_cma_fbdev_init_with_funcs(dev, 16,
- *                                           dev->mode_config.num_crtc,
- *                                           dev->mode_config.num_connector,
- *                                           &driver_fb_funcs);
- *
  */
 
 static inline struct drm_fbdev_cma *to_fbdev_cma(struct drm_fb_helper *helper)
@@ -131,153 +99,6 @@ dma_addr_t drm_fb_cma_get_gem_addr(struct drm_framebuffer *fb,
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_addr);
 
-static int drm_fb_cma_mmap(struct fb_info *info, struct vm_area_struct *vma)
-{
-	return dma_mmap_writecombine(info->device, vma, info->screen_base,
-				     info->fix.smem_start, info->fix.smem_len);
-}
-
-static struct fb_ops drm_fbdev_cma_ops = {
-	.owner		= THIS_MODULE,
-	DRM_FB_HELPER_DEFAULT_OPS,
-	.fb_fillrect	= drm_fb_helper_sys_fillrect,
-	.fb_copyarea	= drm_fb_helper_sys_copyarea,
-	.fb_imageblit	= drm_fb_helper_sys_imageblit,
-	.fb_mmap	= drm_fb_cma_mmap,
-};
-
-static int drm_fbdev_cma_deferred_io_mmap(struct fb_info *info,
-					  struct vm_area_struct *vma)
-{
-	fb_deferred_io_mmap(info, vma);
-	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
-
-	return 0;
-}
-
-static int drm_fbdev_cma_defio_init(struct fb_info *fbi,
-				    struct drm_gem_cma_object *cma_obj)
-{
-	struct fb_deferred_io *fbdefio;
-	struct fb_ops *fbops;
-
-	/*
-	 * Per device structures are needed because:
-	 * fbops: fb_deferred_io_cleanup() clears fbops.fb_mmap
-	 * fbdefio: individual delays
-	 */
-	fbdefio = kzalloc(sizeof(*fbdefio), GFP_KERNEL);
-	fbops = kzalloc(sizeof(*fbops), GFP_KERNEL);
-	if (!fbdefio || !fbops) {
-		kfree(fbdefio);
-		kfree(fbops);
-		return -ENOMEM;
-	}
-
-	/* can't be offset from vaddr since dirty() uses cma_obj */
-	fbi->screen_buffer = cma_obj->vaddr;
-	/* fb_deferred_io_fault() needs a physical address */
-	fbi->fix.smem_start = page_to_phys(virt_to_page(fbi->screen_buffer));
-
-	*fbops = *fbi->fbops;
-	fbi->fbops = fbops;
-
-	fbdefio->delay = msecs_to_jiffies(DEFAULT_FBDEFIO_DELAY_MS);
-	fbdefio->deferred_io = drm_fb_helper_deferred_io;
-	fbi->fbdefio = fbdefio;
-	fb_deferred_io_init(fbi);
-	fbi->fbops->fb_mmap = drm_fbdev_cma_deferred_io_mmap;
-
-	return 0;
-}
-
-static void drm_fbdev_cma_defio_fini(struct fb_info *fbi)
-{
-	if (!fbi->fbdefio)
-		return;
-
-	fb_deferred_io_cleanup(fbi);
-	kfree(fbi->fbdefio);
-	kfree(fbi->fbops);
-}
-
-static int
-drm_fbdev_cma_create(struct drm_fb_helper *helper,
-	struct drm_fb_helper_surface_size *sizes)
-{
-	struct drm_fbdev_cma *fbdev_cma = to_fbdev_cma(helper);
-	struct drm_device *dev = helper->dev;
-	struct drm_gem_cma_object *obj;
-	struct drm_framebuffer *fb;
-	unsigned int bytes_per_pixel;
-	unsigned long offset;
-	struct fb_info *fbi;
-	size_t size;
-	int ret;
-
-	DRM_DEBUG_KMS("surface width(%d), height(%d) and bpp(%d)\n",
-			sizes->surface_width, sizes->surface_height,
-			sizes->surface_bpp);
-
-	bytes_per_pixel = DIV_ROUND_UP(sizes->surface_bpp, 8);
-	size = sizes->surface_width * sizes->surface_height * bytes_per_pixel;
-	obj = drm_gem_cma_create(dev, size);
-	if (IS_ERR(obj))
-		return -ENOMEM;
-
-	fbi = drm_fb_helper_alloc_fbi(helper);
-	if (IS_ERR(fbi)) {
-		ret = PTR_ERR(fbi);
-		goto err_gem_free_object;
-	}
-
-	fb = drm_gem_fbdev_fb_create(dev, sizes, 0, &obj->base,
-				     fbdev_cma->fb_funcs);
-	if (IS_ERR(fb)) {
-		dev_err(dev->dev, "Failed to allocate DRM framebuffer.\n");
-		ret = PTR_ERR(fb);
-		goto err_fb_info_destroy;
-	}
-
-	helper->fb = fb;
-
-	fbi->par = helper;
-	fbi->flags = FBINFO_FLAG_DEFAULT;
-	fbi->fbops = &drm_fbdev_cma_ops;
-
-	drm_fb_helper_fill_fix(fbi, fb->pitches[0], fb->format->depth);
-	drm_fb_helper_fill_var(fbi, helper, sizes->fb_width, sizes->fb_height);
-
-	offset = fbi->var.xoffset * bytes_per_pixel;
-	offset += fbi->var.yoffset * fb->pitches[0];
-
-	dev->mode_config.fb_base = (resource_size_t)obj->paddr;
-	fbi->screen_base = obj->vaddr + offset;
-	fbi->fix.smem_start = (unsigned long)(obj->paddr + offset);
-	fbi->screen_size = size;
-	fbi->fix.smem_len = size;
-
-	if (fb->funcs->dirty) {
-		ret = drm_fbdev_cma_defio_init(fbi, obj);
-		if (ret)
-			goto err_cma_destroy;
-	}
-
-	return 0;
-
-err_cma_destroy:
-	drm_framebuffer_remove(fb);
-err_fb_info_destroy:
-	drm_fb_helper_fini(helper);
-err_gem_free_object:
-	drm_gem_object_put_unlocked(&obj->base);
-	return ret;
-}
-
-static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = {
-	.fb_probe = drm_fbdev_cma_create,
-};
-
 /**
  * drm_fb_cma_fbdev_init_with_funcs() - Allocate and initialize fbdev emulation
  * @dev: DRM device
@@ -295,53 +116,7 @@ int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev,
 	unsigned int preferred_bpp, unsigned int max_conn_count,
 	const struct drm_framebuffer_funcs *funcs)
 {
-	struct drm_fbdev_cma *fbdev_cma;
-	struct drm_fb_helper *fb_helper;
-	int ret;
-
-	if (!preferred_bpp)
-		preferred_bpp = dev->mode_config.preferred_depth;
-	if (!preferred_bpp)
-		preferred_bpp = 32;
-
-	if (!max_conn_count)
-		max_conn_count = dev->mode_config.num_connector;
-
-	fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL);
-	if (!fbdev_cma)
-		return -ENOMEM;
-
-	fbdev_cma->fb_funcs = funcs;
-	fb_helper = &fbdev_cma->fb_helper;
-
-	drm_fb_helper_prepare(dev, fb_helper, &drm_fb_cma_helper_funcs);
-
-	ret = drm_fb_helper_init(dev, fb_helper, max_conn_count);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to initialize fbdev helper.\n");
-		goto err_free;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(fb_helper);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to add connectors.\n");
-		goto err_drm_fb_helper_fini;
-	}
-
-	ret = drm_fb_helper_initial_config(fb_helper, preferred_bpp);
-	if (ret < 0) {
-		DRM_DEV_ERROR(dev->dev, "Failed to set fbdev configuration.\n");
-		goto err_drm_fb_helper_fini;
-	}
-
-	return 0;
-
-err_drm_fb_helper_fini:
-	drm_fb_helper_fini(fb_helper);
-err_free:
-	kfree(fbdev_cma);
-
-	return ret;
+	return drm_fb_cma_fbdev_init(dev, preferred_bpp, max_conn_count);
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs);
 
@@ -359,8 +134,14 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs);
 int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
 			  unsigned int max_conn_count)
 {
-	return drm_fb_cma_fbdev_init_with_funcs(dev, preferred_bpp,
-						max_conn_count, NULL);
+	struct drm_fbdev_cma *fbdev_cma;
+
+	/* dev->fb_helper will indirectly point to fbdev_cma after this call */
+	fbdev_cma = drm_fbdev_cma_init(dev, preferred_bpp, max_conn_count);
+	if (IS_ERR(fbdev_cma))
+		return PTR_ERR(fbdev_cma);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init);
 
@@ -370,104 +151,54 @@ EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init);
  */
 void drm_fb_cma_fbdev_fini(struct drm_device *dev)
 {
-	struct drm_fb_helper *fb_helper = dev->fb_helper;
-
-	if (!fb_helper)
-		return;
-
-	/* Unregister if it hasn't been done already */
-	if (fb_helper->fbdev && fb_helper->fbdev->dev)
-		drm_fb_helper_unregister_fbi(fb_helper);
-
-	if (fb_helper->fbdev)
-		drm_fbdev_cma_defio_fini(fb_helper->fbdev);
-
-	if (fb_helper->fb)
-		drm_framebuffer_remove(fb_helper->fb);
-
-	drm_fb_helper_fini(fb_helper);
-	kfree(to_fbdev_cma(fb_helper));
+	if (dev->fb_helper)
+		drm_fbdev_cma_fini(to_fbdev_cma(dev->fb_helper));
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_fini);
 
+static const struct drm_fb_helper_funcs drm_fb_cma_helper_funcs = {
+	.fb_probe = drm_fb_helper_generic_probe,
+};
+
 /**
- * drm_fbdev_cma_init_with_funcs() - Allocate and initializes a drm_fbdev_cma struct
+ * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct
  * @dev: DRM device
  * @preferred_bpp: Preferred bits per pixel for the device
  * @max_conn_count: Maximum number of connectors
- * @funcs: fb helper functions, in particular a custom dirty() callback
  *
  * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR.
  */
-struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs)
+struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
+	unsigned int preferred_bpp, unsigned int max_conn_count)
 {
 	struct drm_fbdev_cma *fbdev_cma;
-	struct drm_fb_helper *helper;
+	struct drm_fb_helper *fb_helper;
 	int ret;
 
 	fbdev_cma = kzalloc(sizeof(*fbdev_cma), GFP_KERNEL);
-	if (!fbdev_cma) {
-		dev_err(dev->dev, "Failed to allocate drm fbdev.\n");
+	if (!fbdev_cma)
 		return ERR_PTR(-ENOMEM);
-	}
-	fbdev_cma->fb_funcs = funcs;
-
-	helper = &fbdev_cma->fb_helper;
 
-	drm_fb_helper_prepare(dev, helper, &drm_fb_cma_helper_funcs);
+	fb_helper = &fbdev_cma->fb_helper;
 
-	ret = drm_fb_helper_init(dev, helper, max_conn_count);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to initialize drm fb helper.\n");
+	ret = drm_client_new(dev, &fb_helper->client, "fbdev", NULL);
+	if (ret)
 		goto err_free;
-	}
-
-	ret = drm_fb_helper_single_add_all_connectors(helper);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to add connectors.\n");
-		goto err_drm_fb_helper_fini;
 
-	}
-
-	ret = drm_fb_helper_initial_config(helper, preferred_bpp);
-	if (ret < 0) {
-		dev_err(dev->dev, "Failed to set initial hw configuration.\n");
-		goto err_drm_fb_helper_fini;
-	}
+	ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_cma_helper_funcs,
+					preferred_bpp, max_conn_count);
+	if (ret)
+		goto err_client_put;
 
 	return fbdev_cma;
 
-err_drm_fb_helper_fini:
-	drm_fb_helper_fini(helper);
+err_client_put:
+	drm_client_release(&fb_helper->client);
 err_free:
 	kfree(fbdev_cma);
 
 	return ERR_PTR(ret);
 }
-EXPORT_SYMBOL_GPL(drm_fbdev_cma_init_with_funcs);
-
-static const struct drm_framebuffer_funcs drm_fb_cma_funcs = {
-	.destroy	= drm_gem_fb_destroy,
-	.create_handle	= drm_gem_fb_create_handle,
-};
-
-/**
- * drm_fbdev_cma_init() - Allocate and initializes a drm_fbdev_cma struct
- * @dev: DRM device
- * @preferred_bpp: Preferred bits per pixel for the device
- * @max_conn_count: Maximum number of connectors
- *
- * Returns a newly allocated drm_fbdev_cma struct or a ERR_PTR.
- */
-struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count)
-{
-	return drm_fbdev_cma_init_with_funcs(dev, preferred_bpp,
-					     max_conn_count,
-					     &drm_fb_cma_funcs);
-}
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_init);
 
 /**
@@ -477,14 +208,7 @@ EXPORT_SYMBOL_GPL(drm_fbdev_cma_init);
 void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma)
 {
 	drm_fb_helper_unregister_fbi(&fbdev_cma->fb_helper);
-	if (fbdev_cma->fb_helper.fbdev)
-		drm_fbdev_cma_defio_fini(fbdev_cma->fb_helper.fbdev);
-
-	if (fbdev_cma->fb_helper.fb)
-		drm_framebuffer_remove(fbdev_cma->fb_helper.fb);
-
-	drm_fb_helper_fini(&fbdev_cma->fb_helper);
-	kfree(fbdev_cma);
+	/* All resources have now been freed by drm_fbdev_fb_destroy() */
 }
 EXPORT_SYMBOL_GPL(drm_fbdev_cma_fini);
 
diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h
index d532f88a8d55..a0546c3451f9 100644
--- a/include/drm/drm_fb_cma_helper.h
+++ b/include/drm/drm_fb_cma_helper.h
@@ -23,9 +23,6 @@ int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
 			  unsigned int max_conn_count);
 void drm_fb_cma_fbdev_fini(struct drm_device *dev);
 
-struct drm_fbdev_cma *drm_fbdev_cma_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs);
 struct drm_fbdev_cma *drm_fbdev_cma_init(struct drm_device *dev,
 	unsigned int preferred_bpp, unsigned int max_conn_count);
 void drm_fbdev_cma_fini(struct drm_fbdev_cma *fbdev_cma);
-- 
cgit v1.2.3


From e896c132eb2cb4975d99477ea7e95aedb6dffa95 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:51 +0200
Subject: drm/debugfs: Add internal client debugfs file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Print the names of the internal clients currently attached.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-6-noralf@tronnes.org
---
 drivers/gpu/drm/drm_client.c  | 28 ++++++++++++++++++++++++++++
 drivers/gpu/drm/drm_debugfs.c |  7 +++++++
 include/drm/drm_client.h      |  3 +++
 3 files changed, 38 insertions(+)

diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index 743495f7f833..4039a4d103a8 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -385,3 +385,31 @@ void drm_client_framebuffer_delete(struct drm_client_buffer *buffer)
 	drm_client_buffer_delete(buffer);
 }
 EXPORT_SYMBOL(drm_client_framebuffer_delete);
+
+#ifdef CONFIG_DEBUG_FS
+static int drm_client_debugfs_internal_clients(struct seq_file *m, void *data)
+{
+	struct drm_info_node *node = m->private;
+	struct drm_device *dev = node->minor->dev;
+	struct drm_printer p = drm_seq_file_printer(m);
+	struct drm_client_dev *client;
+
+	mutex_lock(&dev->clientlist_mutex);
+	list_for_each_entry(client, &dev->clientlist, list)
+		drm_printf(&p, "%s\n", client->name);
+	mutex_unlock(&dev->clientlist_mutex);
+
+	return 0;
+}
+
+static const struct drm_info_list drm_client_debugfs_list[] = {
+	{ "internal_clients", drm_client_debugfs_internal_clients, 0 },
+};
+
+int drm_client_debugfs_init(struct drm_minor *minor)
+{
+	return drm_debugfs_create_files(drm_client_debugfs_list,
+					ARRAY_SIZE(drm_client_debugfs_list),
+					minor->debugfs_root, minor);
+}
+#endif
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index b2482818fee8..50a20bfc07ea 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -28,6 +28,7 @@
 #include <linux/slab.h>
 #include <linux/export.h>
 
+#include <drm/drm_client.h>
 #include <drm/drm_debugfs.h>
 #include <drm/drm_edid.h>
 #include <drm/drm_atomic.h>
@@ -164,6 +165,12 @@ int drm_debugfs_init(struct drm_minor *minor, int minor_id,
 			DRM_ERROR("Failed to create framebuffer debugfs file\n");
 			return ret;
 		}
+
+		ret = drm_client_debugfs_init(minor);
+		if (ret) {
+			DRM_ERROR("Failed to create client debugfs file\n");
+			return ret;
+		}
 	}
 
 	if (dev->driver->debugfs_init) {
diff --git a/include/drm/drm_client.h b/include/drm/drm_client.h
index 671052d80e38..989f8e52864d 100644
--- a/include/drm/drm_client.h
+++ b/include/drm/drm_client.h
@@ -10,6 +10,7 @@ struct drm_device;
 struct drm_file;
 struct drm_framebuffer;
 struct drm_gem_object;
+struct drm_minor;
 struct module;
 
 /**
@@ -133,4 +134,6 @@ struct drm_client_buffer *
 drm_client_framebuffer_create(struct drm_client_dev *client, u32 width, u32 height, u32 format);
 void drm_client_framebuffer_delete(struct drm_client_buffer *buffer);
 
+int drm_client_debugfs_init(struct drm_minor *minor);
+
 #endif
-- 
cgit v1.2.3


From 9060d7f49376159dcc500a97cb247ca8e4b98f48 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:52 +0200
Subject: drm/fb-helper: Finish the generic fbdev emulation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds a drm_fbdev_generic_setup() function that sets up generic
fbdev emulation with client callbacks for restore, hotplug and
unregister.

Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-7-noralf@tronnes.org
---
 drivers/gpu/drm/drm_fb_helper.c | 117 ++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_fb_helper.h     |   7 +++
 2 files changed, 124 insertions(+)

diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
index 7e29d5340a17..4b0dd20bccb8 100644
--- a/drivers/gpu/drm/drm_fb_helper.c
+++ b/drivers/gpu/drm/drm_fb_helper.c
@@ -67,6 +67,9 @@ static DEFINE_MUTEX(kernel_fb_helper_lock);
  * helper functions used by many drivers to implement the kernel mode setting
  * interfaces.
  *
+ * Drivers that support a dumb buffer with a virtual address and mmap support,
+ * should try out the generic fbdev emulation using drm_fbdev_generic_setup().
+ *
  * Setup fbdev emulation by calling drm_fb_helper_fbdev_setup() and tear it
  * down by calling drm_fb_helper_fbdev_teardown().
  *
@@ -3118,6 +3121,120 @@ err_free_buffer:
 }
 EXPORT_SYMBOL(drm_fb_helper_generic_probe);
 
+static const struct drm_fb_helper_funcs drm_fb_helper_generic_funcs = {
+	.fb_probe = drm_fb_helper_generic_probe,
+};
+
+static void drm_fbdev_client_unregister(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	if (fb_helper->fbdev) {
+		drm_fb_helper_unregister_fbi(fb_helper);
+		/* drm_fbdev_fb_destroy() takes care of cleanup */
+		return;
+	}
+
+	/* Did drm_fb_helper_fbdev_setup() run? */
+	if (fb_helper->dev)
+		drm_fb_helper_fini(fb_helper);
+
+	drm_client_release(client);
+	kfree(fb_helper);
+}
+
+static int drm_fbdev_client_restore(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+
+	drm_fb_helper_restore_fbdev_mode_unlocked(fb_helper);
+
+	return 0;
+}
+
+static int drm_fbdev_client_hotplug(struct drm_client_dev *client)
+{
+	struct drm_fb_helper *fb_helper = drm_fb_helper_from_client(client);
+	struct drm_device *dev = client->dev;
+	int ret;
+
+	/* If drm_fb_helper_fbdev_setup() failed, we only try once */
+	if (!fb_helper->dev && fb_helper->funcs)
+		return 0;
+
+	if (dev->fb_helper)
+		return drm_fb_helper_hotplug_event(dev->fb_helper);
+
+	if (!dev->mode_config.num_connector)
+		return 0;
+
+	ret = drm_fb_helper_fbdev_setup(dev, fb_helper, &drm_fb_helper_generic_funcs,
+					fb_helper->preferred_bpp, 0);
+	if (ret) {
+		fb_helper->dev = NULL;
+		fb_helper->fbdev = NULL;
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct drm_client_funcs drm_fbdev_client_funcs = {
+	.owner		= THIS_MODULE,
+	.unregister	= drm_fbdev_client_unregister,
+	.restore	= drm_fbdev_client_restore,
+	.hotplug	= drm_fbdev_client_hotplug,
+};
+
+/**
+ * drm_fb_helper_generic_fbdev_setup() - Setup generic fbdev emulation
+ * @dev: DRM device
+ * @preferred_bpp: Preferred bits per pixel for the device.
+ *                 @dev->mode_config.preferred_depth is used if this is zero.
+ *
+ * This function sets up generic fbdev emulation for drivers that supports
+ * dumb buffers with a virtual address and that can be mmap'ed.
+ *
+ * Restore, hotplug events and teardown are all taken care of. Drivers that do
+ * suspend/resume need to call drm_fb_helper_set_suspend_unlocked() themselves.
+ * Simple drivers might use drm_mode_config_helper_suspend().
+ *
+ * Drivers that set the dirty callback on their framebuffer will get a shadow
+ * fbdev buffer that is blitted onto the real buffer. This is done in order to
+ * make deferred I/O work with all kinds of buffers.
+ *
+ * This function is safe to call even when there are no connectors present.
+ * Setup will be retried on the next hotplug event.
+ *
+ * Returns:
+ * Zero on success or negative error code on failure.
+ */
+int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
+{
+	struct drm_fb_helper *fb_helper;
+	int ret;
+
+	if (!drm_fbdev_emulation)
+		return 0;
+
+	fb_helper = kzalloc(sizeof(*fb_helper), GFP_KERNEL);
+	if (!fb_helper)
+		return -ENOMEM;
+
+	ret = drm_client_new(dev, &fb_helper->client, "fbdev", &drm_fbdev_client_funcs);
+	if (ret) {
+		kfree(fb_helper);
+		return ret;
+	}
+
+	fb_helper->preferred_bpp = preferred_bpp;
+
+	drm_fbdev_client_hotplug(&fb_helper->client);
+
+	return 0;
+}
+EXPORT_SYMBOL(drm_fbdev_generic_setup);
+
 /* The Kconfig DRM_KMS_HELPER selects FRAMEBUFFER_CONSOLE (if !EXPERT)
  * but the module doesn't depend on any fb console symbols.  At least
  * attempt to load fbcon to avoid leaving the system without a usable console.
diff --git a/include/drm/drm_fb_helper.h b/include/drm/drm_fb_helper.h
index c134bbcfd2e9..5db08c8f1d25 100644
--- a/include/drm/drm_fb_helper.h
+++ b/include/drm/drm_fb_helper.h
@@ -354,6 +354,7 @@ void drm_fb_helper_output_poll_changed(struct drm_device *dev);
 
 int drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
 				struct drm_fb_helper_surface_size *sizes);
+int drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp);
 #else
 static inline void drm_fb_helper_prepare(struct drm_device *dev,
 					struct drm_fb_helper *helper,
@@ -595,6 +596,12 @@ drm_fb_helper_generic_probe(struct drm_fb_helper *fb_helper,
 	return 0;
 }
 
+static inline int
+drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp)
+{
+	return 0;
+}
+
 #endif
 
 static inline int
-- 
cgit v1.2.3


From dff1c7032ffea20cca2ad3973ed4c69c8182683d Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:53 +0200
Subject: drm/tinydrm: Use drm_fbdev_generic_setup()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make full use of the generic fbdev client.

Cc: David Lechner <david@lechnology.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: David Lechner <david@lechnology.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-8-noralf@tronnes.org
---
 drivers/gpu/drm/tinydrm/core/tinydrm-core.c | 3 +--
 drivers/gpu/drm/tinydrm/ili9225.c           | 1 -
 drivers/gpu/drm/tinydrm/ili9341.c           | 1 -
 drivers/gpu/drm/tinydrm/mi0283qt.c          | 1 -
 drivers/gpu/drm/tinydrm/st7586.c            | 1 -
 drivers/gpu/drm/tinydrm/st7735r.c           | 1 -
 6 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
index 24a33bf862fa..19c7f70adfa5 100644
--- a/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
+++ b/drivers/gpu/drm/tinydrm/core/tinydrm-core.c
@@ -204,7 +204,7 @@ static int tinydrm_register(struct tinydrm_device *tdev)
 	if (ret)
 		return ret;
 
-	ret = drm_fb_cma_fbdev_init_with_funcs(drm, 0, 0, tdev->fb_funcs);
+	ret = drm_fbdev_generic_setup(drm, 0);
 	if (ret)
 		DRM_ERROR("Failed to initialize fbdev: %d\n", ret);
 
@@ -214,7 +214,6 @@ static int tinydrm_register(struct tinydrm_device *tdev)
 static void tinydrm_unregister(struct tinydrm_device *tdev)
 {
 	drm_atomic_helper_shutdown(tdev->drm);
-	drm_fb_cma_fbdev_fini(tdev->drm);
 	drm_dev_unregister(tdev->drm);
 }
 
diff --git a/drivers/gpu/drm/tinydrm/ili9225.c b/drivers/gpu/drm/tinydrm/ili9225.c
index 841c69aba059..455fefe012f5 100644
--- a/drivers/gpu/drm/tinydrm/ili9225.c
+++ b/drivers/gpu/drm/tinydrm/ili9225.c
@@ -368,7 +368,6 @@ static struct drm_driver ili9225_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &ili9225_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.name			= "ili9225",
 	.desc			= "Ilitek ILI9225",
 	.date			= "20171106",
diff --git a/drivers/gpu/drm/tinydrm/ili9341.c b/drivers/gpu/drm/tinydrm/ili9341.c
index 8864dcde6edc..6701037749a7 100644
--- a/drivers/gpu/drm/tinydrm/ili9341.c
+++ b/drivers/gpu/drm/tinydrm/ili9341.c
@@ -145,7 +145,6 @@ static struct drm_driver ili9341_driver = {
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET | DRIVER_PRIME | DRIVER_ATOMIC,
 	.fops			= &ili9341_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "ili9341",
 	.desc			= "Ilitek ILI9341",
diff --git a/drivers/gpu/drm/tinydrm/mi0283qt.c b/drivers/gpu/drm/tinydrm/mi0283qt.c
index 015d03f2acba..d7bb4c5e6657 100644
--- a/drivers/gpu/drm/tinydrm/mi0283qt.c
+++ b/drivers/gpu/drm/tinydrm/mi0283qt.c
@@ -154,7 +154,6 @@ static struct drm_driver mi0283qt_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &mi0283qt_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "mi0283qt",
 	.desc			= "Multi-Inno MI0283QT",
diff --git a/drivers/gpu/drm/tinydrm/st7586.c b/drivers/gpu/drm/tinydrm/st7586.c
index 5c29e3803ecb..2fcbc3067d71 100644
--- a/drivers/gpu/drm/tinydrm/st7586.c
+++ b/drivers/gpu/drm/tinydrm/st7586.c
@@ -304,7 +304,6 @@ static struct drm_driver st7586_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &st7586_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "st7586",
 	.desc			= "Sitronix ST7586",
diff --git a/drivers/gpu/drm/tinydrm/st7735r.c b/drivers/gpu/drm/tinydrm/st7735r.c
index 6c7b15c9da4f..3081bc57c116 100644
--- a/drivers/gpu/drm/tinydrm/st7735r.c
+++ b/drivers/gpu/drm/tinydrm/st7735r.c
@@ -120,7 +120,6 @@ static struct drm_driver st7735r_driver = {
 				  DRIVER_ATOMIC,
 	.fops			= &st7735r_fops,
 	TINYDRM_GEM_DRIVER_OPS,
-	.lastclose		= drm_fb_helper_lastclose,
 	.debugfs_init		= mipi_dbi_debugfs_init,
 	.name			= "st7735r",
 	.desc			= "Sitronix ST7735R",
-- 
cgit v1.2.3


From 85b5bafb86e64f5d0ef143ab1a8363f5511eaabb Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 3 Jul 2018 18:03:54 +0200
Subject: drm/cma-helper: Remove drm_fb_cma_fbdev_init_with_funcs()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove drm_fb_cma_fbdev_init_with_funcs(), its only user tinydrm has
moved to drm_fbdev_generic_setup().

Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: David Lechner <david@lechnology.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180703160354.59955-9-noralf@tronnes.org
---
 drivers/gpu/drm/drm_fb_cma_helper.c | 21 ---------------------
 include/drm/drm_fb_cma_helper.h     |  3 ---
 2 files changed, 24 deletions(-)

diff --git a/drivers/gpu/drm/drm_fb_cma_helper.c b/drivers/gpu/drm/drm_fb_cma_helper.c
index 718c7f961d8a..9da36a6271d3 100644
--- a/drivers/gpu/drm/drm_fb_cma_helper.c
+++ b/drivers/gpu/drm/drm_fb_cma_helper.c
@@ -99,27 +99,6 @@ dma_addr_t drm_fb_cma_get_gem_addr(struct drm_framebuffer *fb,
 }
 EXPORT_SYMBOL_GPL(drm_fb_cma_get_gem_addr);
 
-/**
- * drm_fb_cma_fbdev_init_with_funcs() - Allocate and initialize fbdev emulation
- * @dev: DRM device
- * @preferred_bpp: Preferred bits per pixel for the device.
- *                 @dev->mode_config.preferred_depth is used if this is zero.
- * @max_conn_count: Maximum number of connectors.
- *                  @dev->mode_config.num_connector is used if this is zero.
- * @funcs: Framebuffer functions, in particular a custom dirty() callback.
- *         Can be NULL.
- *
- * Returns:
- * Zero on success or negative error code on failure.
- */
-int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs)
-{
-	return drm_fb_cma_fbdev_init(dev, preferred_bpp, max_conn_count);
-}
-EXPORT_SYMBOL_GPL(drm_fb_cma_fbdev_init_with_funcs);
-
 /**
  * drm_fb_cma_fbdev_init() - Allocate and initialize fbdev emulation
  * @dev: DRM device
diff --git a/include/drm/drm_fb_cma_helper.h b/include/drm/drm_fb_cma_helper.h
index a0546c3451f9..96e26e3b9a0c 100644
--- a/include/drm/drm_fb_cma_helper.h
+++ b/include/drm/drm_fb_cma_helper.h
@@ -16,9 +16,6 @@ struct drm_mode_fb_cmd2;
 struct drm_plane;
 struct drm_plane_state;
 
-int drm_fb_cma_fbdev_init_with_funcs(struct drm_device *dev,
-	unsigned int preferred_bpp, unsigned int max_conn_count,
-	const struct drm_framebuffer_funcs *funcs);
 int drm_fb_cma_fbdev_init(struct drm_device *dev, unsigned int preferred_bpp,
 			  unsigned int max_conn_count);
 void drm_fb_cma_fbdev_fini(struct drm_device *dev);
-- 
cgit v1.2.3


From 8bcf9f7034d81979837e97a6509b0b2a96f8f4c8 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Jul 2018 10:44:20 +0100
Subject: drm/i915: Flush the residual parking on emergency shutdown

On unwinding following a critical failure inside GEM init, we also need
to be sure to flush the workers before unloading the module.

Testcase: igt/drv_module_reload/basic-reload-inject
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710094421.16223-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c      | 2 ++
 drivers/gpu/drm/i915/intel_display.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 25728c9d2727..07a92ca61dbf 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5550,6 +5550,8 @@ err_init_hw:
 	WARN_ON(i915_gem_suspend(dev_priv));
 	i915_gem_suspend_late(dev_priv);
 
+	i915_gem_drain_workqueue(dev_priv);
+
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uc_fini_hw(dev_priv);
 err_uc_init:
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 19f756d571ae..694975afe394 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15847,6 +15847,8 @@ void intel_modeset_cleanup(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = to_i915(dev);
 
+	flush_workqueue(dev_priv->modeset_wq);
+
 	flush_work(&dev_priv->atomic_helper.free_work);
 	WARN_ON(!llist_empty(&dev_priv->atomic_helper.free_list));
 
-- 
cgit v1.2.3


From 73bad7ca87b65a91f61cf34b92a1febd689c01c1 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Jul 2018 10:44:21 +0100
Subject: drm/i915: Cleanup modesetting on load-error path

After handling a critical failure initialising GEM we need to unwind the
modesetting setup.

Testcase: igt/drv_module_reload/basic-reload-inject
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710094421.16223-2-chris@chris-wilson.co.uk
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index c2b9a4a0ee49..f26cc721ee0f 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -682,7 +682,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	ret = i915_gem_init(dev_priv);
 	if (ret)
-		goto cleanup_irq;
+		goto cleanup_modeset;
 
 	intel_setup_overlay(dev_priv);
 
@@ -702,6 +702,8 @@ cleanup_gem:
 	if (i915_gem_suspend(dev_priv))
 		DRM_ERROR("failed to idle hardware; continuing to unload!\n");
 	i915_gem_fini(dev_priv);
+cleanup_modeset:
+	intel_modeset_cleanup(dev);
 cleanup_irq:
 	drm_irq_uninstall(dev);
 	intel_teardown_gmbus(dev_priv);
-- 
cgit v1.2.3


From cc55378c5f20af0864f4936d569ef59f8f94ce7c Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Wed, 6 Jun 2018 17:39:42 +0200
Subject: Documentation: devicetree: tilcdc: fix spelling mistake "suppors" ->
 "supports"

Trivial fix to spelling mistake in tilcdc.txt devicetree documentation.

Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
index 6fddb4f4f71a..3055d5c2c04e 100644
--- a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
+++ b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
@@ -36,7 +36,7 @@ Optional nodes:
 
  - port/ports: to describe a connection to an external encoder. The
    binding follows Documentation/devicetree/bindings/graph.txt and
-   suppors a single port with a single endpoint.
+   supports a single port with a single endpoint.
 
  - See also Documentation/devicetree/bindings/display/tilcdc/panel.txt and
    Documentation/devicetree/bindings/display/tilcdc/tfp410.txt for connecting
-- 
cgit v1.2.3


From b7394b7f5870234b77bf60224eb543a1b2d038a2 Mon Sep 17 00:00:00 2001
From: Michal Simek <monstr@monstr.eu>
Date: Wed, 6 Jun 2018 14:49:48 +0200
Subject: dt-bindings: Add bitmain vendor prefix

Bitmain (https://www.bitmain.com) is a vendor of cryptocurrency
hardware.

Signed-off-by: Michal Simek <monstr@monstr.eu>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 7cad066191ee..6975a6fbd8ba 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -53,6 +53,7 @@ axentia	Axentia Technologies AB
 axis	Axis Communications AB
 bananapi BIPAI KEJI LIMITED
 bhf	Beckhoff Automation GmbH & Co. KG
+bitmain	Bitmain Technologies
 boe	BOE Technology Group Co., Ltd.
 bosch	Bosch Sensortec GmbH
 boundary	Boundary Devices Inc.
-- 
cgit v1.2.3


From b01dcdd86e8c20599ee9293392d6fef8397fbc5d Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Tue, 12 Jun 2018 10:01:07 +1000
Subject: drivers/of: Make of_io_request_and_map() "name" argument optional

These days of_address_to_resource() puts a reasonable name
in the resource struct, thus make the "name" argument an
optional override.

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/address.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/of/address.c b/drivers/of/address.c
index 53349912ac75..7ddbf0a1ab86 100644
--- a/drivers/of/address.c
+++ b/drivers/of/address.c
@@ -846,7 +846,7 @@ EXPORT_SYMBOL(of_iomap);
  *			   for a given device_node
  * @device:	the device whose io range will be mapped
  * @index:	index of the io range
- * @name:	name of the resource
+ * @name:	name "override" for the memory region request or NULL
  *
  * Returns a pointer to the requested and mapped memory or an ERR_PTR() encoded
  * error code on failure. Usage example:
@@ -856,7 +856,7 @@ EXPORT_SYMBOL(of_iomap);
  *		return PTR_ERR(base);
  */
 void __iomem *of_io_request_and_map(struct device_node *np, int index,
-					const char *name)
+				    const char *name)
 {
 	struct resource res;
 	void __iomem *mem;
@@ -864,6 +864,8 @@ void __iomem *of_io_request_and_map(struct device_node *np, int index,
 	if (of_address_to_resource(np, index, &res))
 		return IOMEM_ERR_PTR(-EINVAL);
 
+	if (!name)
+		name = res.name;
 	if (!request_mem_region(res.start, resource_size(&res), name))
 		return IOMEM_ERR_PTR(-EBUSY);
 
-- 
cgit v1.2.3


From 24a29949230c95d528d890e67004f239d4227a02 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Tue, 19 Jun 2018 19:24:41 +0200
Subject: dt-bindings: gpio: pca953x: Document interrupts, update example

The device can optionally supply an interrupt, hence document that.

Add required GPIO properties to the example (extracted from a patch by
Wolfram Sang).

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/gpio/gpio-pca953x.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
index 88f228665507..4e3c550e319a 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-pca953x.txt
@@ -37,6 +37,7 @@ Required properties:
  - #interrupt-cells: if to be used as interrupt expander.
 
 Optional properties:
+ - interrupts: interrupt specifier for the device's interrupt output.
  - reset-gpios: GPIO specification for the RESET input. This is an
 		active low signal to the PCA953x.
  - vcc-supply:	power supply regulator.
@@ -49,6 +50,8 @@ Example:
 		reg = <0x20>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&pinctrl_pca9505>;
+		gpio-controller;
+		#gpio-cells = <2>;
 		interrupt-parent = <&gpio3>;
 		interrupts = <23 IRQ_TYPE_LEVEL_LOW>;
 	};
-- 
cgit v1.2.3


From 913097bcdc9010d1617cded9f623a52438531653 Mon Sep 17 00:00:00 2001
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Date: Wed, 27 Jun 2018 09:57:51 +1000
Subject: dt-bindings: misc: ASPEED coprocessor interrupt controller

Add the device-tree binding definition for the AST2400
and AST2500 coprocessor interrupt controller

Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../devicetree/bindings/misc/aspeed,cvic.txt       | 35 ++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/misc/aspeed,cvic.txt

diff --git a/Documentation/devicetree/bindings/misc/aspeed,cvic.txt b/Documentation/devicetree/bindings/misc/aspeed,cvic.txt
new file mode 100644
index 000000000000..d62c783d1d5e
--- /dev/null
+++ b/Documentation/devicetree/bindings/misc/aspeed,cvic.txt
@@ -0,0 +1,35 @@
+* ASPEED AST2400 and AST2500 coprocessor interrupt controller
+
+This file describes the bindings for the interrupt controller present
+in the AST2400 and AST2500 BMC SoCs which provides interrupt to the
+ColdFire coprocessor.
+
+It is not a normal interrupt controller and it would be rather
+inconvenient to create an interrupt tree for it as it somewhat shares
+some of the same sources as the main ARM interrupt controller but with
+different numbers.
+
+The AST2500 supports a SW generated interrupt
+
+Required properties:
+- reg: address and length of the register for the device.
+- compatible: "aspeed,cvic" and one of:
+		"aspeed,ast2400-cvic"
+	      or
+		"aspeed,ast2500-cvic"
+
+- valid-sources: One cell, bitmap of supported sources for the implementation
+
+Optional properties;
+- copro-sw-interrupts: List of interrupt numbers that can be used as
+		       SW interrupts from the ARM to the coprocessor.
+		       (AST2500 only)
+
+Example:
+
+	cvic: copro-interrupt-controller@1e6c2000 {
+		compatible = "aspeed,ast2500-cvic";
+		valid-sources = <0xffffffff>;
+		copro-sw-interrupts = <1>;
+		reg = <0x1e6c2000 0x80>;
+	};
-- 
cgit v1.2.3


From df0e0304466c4b0d8d8137d9c582961db5c65e87 Mon Sep 17 00:00:00 2001
From: Luis Araneda <luaraneda@gmail.com>
Date: Wed, 27 Jun 2018 16:33:15 -0400
Subject: dt-bindings: Add vendor prefix for AsusTek Computer Inc.

"AsusTek Computer Inc. is a Taiwanese multinational computer
and phone hardware and electronics company headquartered
in Beitou District, Taipei, Taiwan." - Wikipedia.org

Website: https://www.asus.com

The prefix is already in use by at least 5 ARM boards

Signed-off-by: Luis Araneda <luaraneda@gmail.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 6975a6fbd8ba..5b2d71a8907b 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -41,6 +41,7 @@ arrow	Arrow Electronics
 artesyn	Artesyn Embedded Technologies Inc.
 asahi-kasei	Asahi Kasei Corp.
 aspeed	ASPEED Technology Inc.
+asus	AsusTek Computer Inc.
 atlas	Atlas Scientific LLC
 atmel	Atmel Corporation
 auo	AU Optronics Corporation
-- 
cgit v1.2.3


From 11ca58727ee4486037a0ca88b6243cc2976ecba7 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 3 Jul 2018 19:51:16 -0300
Subject: dt-bindings: sram: Add 'clocks' as an optional property

Some SoCs (like i.MX53) need to specify the SRAM clock in the
device tree via the clocks property.

Add an entry to the optional property section.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/sram/sram.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/sram/sram.txt b/Documentation/devicetree/bindings/sram/sram.txt
index 267da4410aef..e98908bd4227 100644
--- a/Documentation/devicetree/bindings/sram/sram.txt
+++ b/Documentation/devicetree/bindings/sram/sram.txt
@@ -50,6 +50,8 @@ Optional properties in the area nodes:
 		 manipulation of the page attributes.
 - label : the name for the reserved partition, if omitted, the label
           is taken from the node name excluding the unit address.
+- clocks : a list of phandle and clock specifier pair that controls the
+	   single SRAM clock.
 
 Example:
 
-- 
cgit v1.2.3


From 7ab87ede5078af1daccf26951096e16ac16e19cb Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 10 Jul 2018 15:38:21 +0100
Subject: drm/i915: Unwind HW init after GVT setup failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Following intel_gvt_init() failure, we missed unwinding our setup
leaving pointers dangling past the module unload. For our example, the
pm_qos:

[  441.057615] top: 000000006b3baf1c, n: 0000000054d8ef33, p: 0000000097cdf1a2
               prev: 0000000054d8ef33, n: 0000000097cdf1a2, p: 000000006b3baf1c
               next: 0000000097cdf1a2, n: 000000006de8fc8b, p: 0000000081087253
[  441.057627] WARNING: CPU: 4 PID: 9277 at lib/plist.c:42 plist_check_prev_next+0x2d/0x40
[  441.057628] Modules linked in: i915(+) vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic x86_pkg_temp_thermal intel_powerclamp coretemp crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec snd_hwdep snd_hda_core e1000e snd_pcm mei_me mei prime_numbers [last unloaded: i915]
[  441.057652] CPU: 4 PID: 9277 Comm: drv_selftest Tainted: G     U            4.18.0-rc4-CI-CI_DRM_4464+ #1
[  441.057653] Hardware name: System manufacturer System Product Name/Z170 PRO GAMING, BIOS 3402 04/26/2017
[  441.057656] RIP: 0010:plist_check_prev_next+0x2d/0x40
[  441.057657] Code: 08 48 39 f0 74 2b 49 89 f0 48 8b 4f 08 50 ff 32 52 48 89 fe 41 ff 70 08 48 8b 17 48 c7 c7 d8 ae 14 82 4d 8b 08 e8 63 0e 76 ff <0f> 0b 48 83 c4 20 c3 48 39 10 75 d0 f3 c3 0f 1f 44 00 00 41 54 55
[  441.057717] RSP: 0018:ffffc900003a3a68 EFLAGS: 00010082
[  441.057720] RAX: 0000000000000000 RBX: ffff8802193978c0 RCX: 0000000000000002
[  441.057721] RDX: 0000000080000002 RSI: ffffffff820c65a4 RDI: 00000000ffffffff
[  441.057722] RBP: ffff8802193978c0 R08: 0000000000000000 R09: 0000000000000001
[  441.057724] R10: ffffc900003a3a70 R11: 0000000000000000 R12: ffffffff82243de0
[  441.057725] R13: ffffffff82243de0 R14: ffff88021a6c78c0 R15: 0000000077359400
[  441.057726] FS:  00007fc23a4a9980(0000) GS:ffff880236d00000(0000) knlGS:0000000000000000
[  441.057728] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  441.057729] CR2: 0000563e4503d038 CR3: 0000000138f86005 CR4: 00000000003606e0
[  441.057730] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  441.057731] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  441.057732] Call Trace:
[  441.057736]  plist_check_list+0x2e/0x40
[  441.057738]  plist_add+0x23/0x130
[  441.057743]  pm_qos_update_target+0x1bd/0x2f0
[  441.057771]  i915_driver_load+0xec4/0x1060 [i915]
[  441.057775]  ? trace_hardirqs_on_caller+0xe0/0x1b0
[  441.057800]  i915_pci_probe+0x29/0x90 [i915]
[  441.057804]  pci_device_probe+0xa1/0x130
[  441.057807]  driver_probe_device+0x306/0x480
[  441.057810]  __driver_attach+0xdb/0x100
[  441.057812]  ? driver_probe_device+0x480/0x480
[  441.057813]  ? driver_probe_device+0x480/0x480
[  441.057816]  bus_for_each_dev+0x74/0xc0
[  441.057819]  bus_add_driver+0x15f/0x250
[  441.057821]  ? 0xffffffffa0696000
[  441.057823]  driver_register+0x56/0xe0
[  441.057825]  ? 0xffffffffa0696000
[  441.057827]  do_one_initcall+0x58/0x370
[  441.057830]  ? do_init_module+0x1d/0x1ea
[  441.057832]  ? rcu_read_lock_sched_held+0x6f/0x80
[  441.057834]  ? kmem_cache_alloc_trace+0x282/0x2e0
[  441.057838]  do_init_module+0x56/0x1ea
[  441.057841]  load_module+0x2435/0x2b20
[  441.057852]  ? __se_sys_finit_module+0xd3/0xf0
[  441.057854]  __se_sys_finit_module+0xd3/0xf0
[  441.057861]  do_syscall_64+0x55/0x190
[  441.057863]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  441.057865] RIP: 0033:0x7fc239d75839
[  441.057866] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1f f6 2c 00 f7 d8 64 89 01 48
[  441.057927] RSP: 002b:00007fffb7825d38 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[  441.057930] RAX: ffffffffffffffda RBX: 0000563e45035dd0 RCX: 00007fc239d75839
[  441.057931] RDX: 0000000000000000 RSI: 0000563e4502f8a0 RDI: 0000000000000004
[  441.057932] RBP: 0000563e4502f8a0 R08: 0000000000000004 R09: 0000000000000000
[  441.057933] R10: 00007fffb7825ea0 R11: 0000000000000246 R12: 0000000000000000
[  441.057934] R13: 0000563e4502f690 R14: 0000000000000000 R15: 000000000000003f
[  441.057940] irq event stamp: 231338
[  441.057943] hardirqs last  enabled at (231337): [<ffffffff8193e3fc>] _raw_spin_unlock_irqrestore+0x4c/0x60
[  441.057944] hardirqs last disabled at (231338): [<ffffffff8193e26d>] _raw_spin_lock_irqsave+0xd/0x50
[  441.057947] softirqs last  enabled at (231024): [<ffffffff81c0034f>] __do_softirq+0x34f/0x505
[  441.057949] softirqs last disabled at (231005): [<ffffffff8108c7b9>] irq_exit+0xa9/0xc0
[  441.057951] WARNING: CPU: 4 PID: 9277 at lib/plist.c:42 plist_check_prev_next+0x2d/0x40

v2: Add a load failure point to intel_gvt_init() so that we always
exercise this path in future.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107129
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710143821.1889-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.c  | 10 +++++++---
 drivers/gpu/drm/i915/intel_gvt.c |  3 +++
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f26cc721ee0f..f059aa332323 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1154,8 +1154,6 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	intel_uncore_sanitize(dev_priv);
 
-	intel_opregion_setup(dev_priv);
-
 	i915_gem_load_init_fences(dev_priv);
 
 	/* On the 945G/GM, the chipset reports the MSI capability on the
@@ -1184,10 +1182,16 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv)
 
 	ret = intel_gvt_init(dev_priv);
 	if (ret)
-		goto err_ggtt;
+		goto err_msi;
+
+	intel_opregion_setup(dev_priv);
 
 	return 0;
 
+err_msi:
+	if (pdev->msi_enabled)
+		pci_disable_msi(pdev);
+	pm_qos_remove_request(&dev_priv->pm_qos);
 err_ggtt:
 	i915_ggtt_cleanup_hw(dev_priv);
 err_perf:
diff --git a/drivers/gpu/drm/i915/intel_gvt.c b/drivers/gpu/drm/i915/intel_gvt.c
index a6291f60545b..c22b3e18a0f5 100644
--- a/drivers/gpu/drm/i915/intel_gvt.c
+++ b/drivers/gpu/drm/i915/intel_gvt.c
@@ -92,6 +92,9 @@ int intel_gvt_init(struct drm_i915_private *dev_priv)
 {
 	int ret;
 
+	if (i915_inject_load_failure())
+		return -ENODEV;
+
 	if (!i915_modparams.enable_gvt) {
 		DRM_DEBUG_DRIVER("GVT-g is disabled by kernel params\n");
 		return 0;
-- 
cgit v1.2.3


From aef92a8bed25d03b8f03ce499a56e8e8e5e2c05e Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 10 Jul 2018 13:42:10 +0200
Subject: watchdog/softlockup: Fix the SOFTLOCKUP_DETECTOR=n build

I got confused by all the various CONFIG options here about and
conflated CONFIG_LOCKUP_DETECTOR and CONFIG_SOFTLOCKUP_DETECTOR.

This results in a build failure for:

   CONFIG_LOCKUP_DETECTOR=y && CONFIG_SOFTLOCKUP_DETECTOR=n

As reported by Abdul.

Reported-and-tested-by: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-next <linux-next@vger.kernel.org>
Cc: linuxppc-dev <linuxppc-dev@lists.ozlabs.org>
Cc: mpe <mpe@ellerman.id.au>
Cc: sachinp <sachinp@linux.vnet.ibm.com>
Cc: stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 9cf57731b63e ("watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work")
Link: http://lkml.kernel.org/r/20180710114210.GI2476@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/nmi.h | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 80664bbeca43..08f9247e9827 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -33,15 +33,10 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
 #define sysctl_hardlockup_all_cpu_backtrace 0
 #endif /* !CONFIG_SMP */
 
-extern int lockup_detector_online_cpu(unsigned int cpu);
-extern int lockup_detector_offline_cpu(unsigned int cpu);
-
 #else /* CONFIG_LOCKUP_DETECTOR */
 static inline void lockup_detector_init(void) { }
 static inline void lockup_detector_soft_poweroff(void) { }
 static inline void lockup_detector_cleanup(void) { }
-#define lockup_detector_online_cpu	NULL
-#define lockup_detector_offline_cpu	NULL
 #endif /* !CONFIG_LOCKUP_DETECTOR */
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
@@ -50,12 +45,18 @@ extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern unsigned int  softlockup_panic;
-#else
+
+extern int lockup_detector_online_cpu(unsigned int cpu);
+extern int lockup_detector_offline_cpu(unsigned int cpu);
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
 static inline void touch_softlockup_watchdog_sched(void) { }
 static inline void touch_softlockup_watchdog(void) { }
 static inline void touch_softlockup_watchdog_sync(void) { }
 static inline void touch_all_softlockup_watchdogs(void) { }
-#endif
+
+#define lockup_detector_online_cpu	NULL
+#define lockup_detector_offline_cpu	NULL
+#endif /* CONFIG_SOFTLOCKUP_DETECTOR */
 
 #ifdef CONFIG_DETECT_HUNG_TASK
 void reset_hung_task_detector(void);
-- 
cgit v1.2.3


From 23167fa9a519c5408c4aa7fd1dc85b7c48b37864 Mon Sep 17 00:00:00 2001
From: Jagan Teki <jagan@amarulasolutions.com>
Date: Thu, 7 Jun 2018 19:16:48 +0530
Subject: drm/panel: simple: Add support for Rocktech RK070ER9427 LCD panel

This adds support for the Rocktech Display Ltd. RK070ER9427
800(RGB)x480 TFT LCD panel, which can be supported by the
simple panel driver.

Signed-off-by: Jagan Teki <jagan@amarulasolutions.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180607134648.2902-1-jagan@amarulasolutions.com
---
 .../display/panel/rocktech,rk070er9427.txt         | 25 ++++++++++++++++
 drivers/gpu/drm/panel/panel-simple.c               | 33 ++++++++++++++++++++++
 2 files changed, 58 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/rocktech,rk070er9427.txt

diff --git a/Documentation/devicetree/bindings/display/panel/rocktech,rk070er9427.txt b/Documentation/devicetree/bindings/display/panel/rocktech,rk070er9427.txt
new file mode 100644
index 000000000000..eb1fb9f8d1f4
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/rocktech,rk070er9427.txt
@@ -0,0 +1,25 @@
+Rocktech Display Ltd. RK070ER9427 800(RGB)x480 TFT LCD panel
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
+
+Required properties:
+- compatible: should be "rocktech,rk070er9427"
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Optional nodes:
+- Video port for LCD panel input.
+
+Example:
+	panel {
+		compatible = "rocktech,rk070er9427";
+		backlight = <&backlight_lcd>;
+
+		port {
+			lcd_panel_in: endpoint {
+				remote-endpoint = <&lcd_display_out>;
+			};
+		};
+	};
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index ac6aaa174c0b..884fd534c8b3 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1747,6 +1747,36 @@ static const struct panel_desc qd43003c0_40 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct display_timing rocktech_rk070er9427_timing = {
+	.pixelclock = { 26400000, 33300000, 46800000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 16, 210, 354 },
+	.hback_porch = { 46, 46, 46 },
+	.hsync_len = { 1, 1, 1 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 7, 22, 147 },
+	.vback_porch = { 23, 23, 23 },
+	.vsync_len = { 1, 1, 1 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc rocktech_rk070er9427 = {
+	.timings = &rocktech_rk070er9427_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 154,
+		.height = 86,
+	},
+	.delay = {
+		.prepare = 41,
+		.enable = 50,
+		.unprepare = 41,
+		.disable = 50,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+};
+
 static const struct drm_display_mode samsung_lsn122dl01_c01_mode = {
 	.clock = 271560,
 	.hdisplay = 2560,
@@ -2283,6 +2313,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "qiaodian,qd43003c0-40",
 		.data = &qd43003c0_40,
+	}, {
+		.compatible = "rocktech,rk070er9427",
+		.data = &rocktech_rk070er9427,
 	}, {
 		.compatible = "samsung,lsn122dl01-c01",
 		.data = &samsung_lsn122dl01_c01,
-- 
cgit v1.2.3


From 2230ca12cca14c5f42e38f11d94d2f3c1f868453 Mon Sep 17 00:00:00 2001
From: Jan Tuerk <jan.tuerk@emtrion.com>
Date: Tue, 19 Jun 2018 11:55:43 +0200
Subject: dt-bindings: display: Document the EDT et* displays in one file.

Document the Emerging Display Technology Corp. (EDT) using the
simple-panel binding in one single file.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jan Tuerk <jan.tuerk@emtrion.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180619095546.24445-1-jan.tuerk@emtrion.com
---
 .../bindings/display/panel/edt,et-series.txt       | 39 ++++++++++++++++++++++
 .../bindings/display/panel/edt,et057090dhu.txt     |  7 ----
 .../bindings/display/panel/edt,et070080dh6.txt     | 10 ------
 .../bindings/display/panel/edt,etm0700g0dh6.txt    | 10 ------
 4 files changed, 39 insertions(+), 27 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/display/panel/edt,et-series.txt
 delete mode 100644 Documentation/devicetree/bindings/display/panel/edt,et057090dhu.txt
 delete mode 100644 Documentation/devicetree/bindings/display/panel/edt,et070080dh6.txt
 delete mode 100644 Documentation/devicetree/bindings/display/panel/edt,etm0700g0dh6.txt

diff --git a/Documentation/devicetree/bindings/display/panel/edt,et-series.txt b/Documentation/devicetree/bindings/display/panel/edt,et-series.txt
new file mode 100644
index 000000000000..f56b99ebd9be
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/edt,et-series.txt
@@ -0,0 +1,39 @@
+Emerging Display Technology Corp. Displays
+==========================================
+
+
+Display bindings for EDT Display Technology Corp. Displays which are
+compatible with the simple-panel binding, which is specified in
+simple-panel.txt
+
+
+5,7" WVGA TFT Panels
+--------------------
+
++-----------------+---------------------+-------------------------------------+
+| Identifier      | compatbile          | description                         |
++=================+=====================+=====================================+
+| ET057090DHU     | edt,et057090dhu     | 5.7" VGA TFT LCD panel              |
++-----------------+---------------------+-------------------------------------+
+
+
+7,0" WVGA TFT Panels
+--------------------
+
++-----------------+---------------------+-------------------------------------+
+| Identifier      | compatbile          | description                         |
++=================+=====================+=====================================+
+| ETM0700G0DH6    | edt,etm070080dh6    | WVGA TFT Display with capacitive    |
+|                 |                     | Touchscreen                         |
++-----------------+---------------------+-------------------------------------+
+| ETM0700G0BDH6   | edt,etm070080bdh6   | Same as ETM0700G0DH6 but with       |
+|                 |                     | inverted pixel clock.               |
++-----------------+---------------------+-------------------------------------+
+| ETM0700G0EDH6   | edt,etm070080edh6   | Same display as the ETM0700G0BDH6,  |
+|                 |                     | but with changed Hardware for the   |
+|                 |                     | backlight and the touch interface   |
++-----------------+---------------------+-------------------------------------+
+| ET070080DH6     | edt,etm070080dh6    | Same timings as the ETM0700G0DH6,   |
+|                 |                     | but with resistive touch.           |
++-----------------+---------------------+-------------------------------------+
+
diff --git a/Documentation/devicetree/bindings/display/panel/edt,et057090dhu.txt b/Documentation/devicetree/bindings/display/panel/edt,et057090dhu.txt
deleted file mode 100644
index 4903d7b1d947..000000000000
--- a/Documentation/devicetree/bindings/display/panel/edt,et057090dhu.txt
+++ /dev/null
@@ -1,7 +0,0 @@
-Emerging Display Technology Corp. 5.7" VGA TFT LCD panel
-
-Required properties:
-- compatible: should be "edt,et057090dhu"
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/edt,et070080dh6.txt b/Documentation/devicetree/bindings/display/panel/edt,et070080dh6.txt
deleted file mode 100644
index 20cb38e836e4..000000000000
--- a/Documentation/devicetree/bindings/display/panel/edt,et070080dh6.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-Emerging Display Technology Corp. ET070080DH6 7.0" WVGA TFT LCD panel
-
-Required properties:
-- compatible: should be "edt,et070080dh6"
-
-This panel is the same as ETM0700G0DH6 except for the touchscreen.
-ET070080DH6 is the model with resistive touch.
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
diff --git a/Documentation/devicetree/bindings/display/panel/edt,etm0700g0dh6.txt b/Documentation/devicetree/bindings/display/panel/edt,etm0700g0dh6.txt
deleted file mode 100644
index ee4b18053e40..000000000000
--- a/Documentation/devicetree/bindings/display/panel/edt,etm0700g0dh6.txt
+++ /dev/null
@@ -1,10 +0,0 @@
-Emerging Display Technology Corp. ETM0700G0DH6 7.0" WVGA TFT LCD panel
-
-Required properties:
-- compatible: should be "edt,etm0700g0dh6"
-
-This panel is the same as ET070080DH6 except for the touchscreen.
-ETM0700G0DH6 is the model with capacitive multitouch.
-
-This binding is compatible with the simple-panel binding, which is specified
-in simple-panel.txt in this directory.
-- 
cgit v1.2.3


From aa7e6455e1ef75113d47889badb21730f1436714 Mon Sep 17 00:00:00 2001
From: Jan Tuerk <jan.tuerk@emtrion.com>
Date: Tue, 19 Jun 2018 11:55:44 +0200
Subject: drm/panel: Add support for the EDT ETM0700G0BDH6

The Emerging Display Technology ETM0700G0BDH6 is exactly
the same display as the ETM0700G0DH6, exept the pixelclock
polarity. Therefore re-use the ETM0700G0DH6 modes. It is
used by default on emtrion Avari based development kits.

Signed-off-by: Jan Tuerk <jan.tuerk@emtrion.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180619095546.24445-2-jan.tuerk@emtrion.com
---
 drivers/gpu/drm/panel/panel-simple.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 884fd534c8b3..e05321d3442a 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -936,6 +936,18 @@ static const struct panel_desc edt_etm0700g0dh6 = {
 	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_NEGEDGE,
 };
 
+static const struct panel_desc edt_etm0700g0bdh6 = {
+	.modes = &edt_etm0700g0dh6_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE,
+};
+
 static const struct drm_display_mode foxlink_fl500wvr00_a0t_mode = {
 	.clock = 32260,
 	.hdisplay = 800,
@@ -2217,6 +2229,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "edt,etm0700g0dh6",
 		.data = &edt_etm0700g0dh6,
+	}, {
+		.compatible = "edt,etm0700g0bdh6",
+		.data = &edt_etm0700g0bdh6,
 	}, {
 		.compatible = "foxlink,fl500wvr00-a0t",
 		.data = &foxlink_fl500wvr00_a0t,
-- 
cgit v1.2.3


From aad34de22e6325727f7c716e2e7aa396031ceed5 Mon Sep 17 00:00:00 2001
From: Jan Tuerk <jan.tuerk@emtrion.com>
Date: Tue, 19 Jun 2018 11:55:45 +0200
Subject: drm/panel: Add support for the EDT ETM0700G0EDH6

The Emerging Display Technology ETM0700G0EDH6 is the
uses the same panel as the ETM0700G0BDH6. It differs
in the hardware design for the backlight and the
touchscreen i2c interface. As the new display type has
different requirements for drive-strengths on the i2c-bus,
add an additional compatible to allow the handling of it or warn
about incompatible cpu and display combinations.

Signed-off-by: Jan Tuerk <jan.tuerk@emtrion.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180619095546.24445-3-jan.tuerk@emtrion.com
---
 drivers/gpu/drm/panel/panel-simple.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index e05321d3442a..5eb506256d42 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -2232,6 +2232,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "edt,etm0700g0bdh6",
 		.data = &edt_etm0700g0bdh6,
+	}, {
+		.compatible = "edt,etm0700g0edh6",
+		.data = &edt_etm0700g0bdh6,
 	}, {
 		.compatible = "foxlink,fl500wvr00-a0t",
 		.data = &foxlink_fl500wvr00_a0t,
-- 
cgit v1.2.3


From 7a6aca49358a8b678304f7444ec615dbb1175ce8 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Wed, 23 May 2018 11:25:03 +0200
Subject: dt-bindings: Add vendor prefix for DLC Display Co., Ltd.

DLC provides a wide range of display solutions.
Website: http://www.dlcdisplay.com/

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180523092504.5142-2-m.felsch@pengutronix.de
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 698453943789..10fb0df60b6a 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -94,6 +94,7 @@ dh	DH electronics GmbH
 digi	Digi International Inc.
 digilent	Diglent, Inc.
 dioo	Dioo Microcircuit Co., Ltd
+dlc	DLC Display Co., Ltd.
 dlg	Dialog Semiconductor
 dlink	D-Link Corporation
 dmo	Data Modul AG
-- 
cgit v1.2.3


From 0ca0c827efdf248dfb4bbd4b9066acb6337e07ac Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Wed, 23 May 2018 11:25:04 +0200
Subject: drm/panel: simple: Add DLC DLC0700YZG-1 panel

This patch adds support for DLC DLC0700YZG-1 1024x600 LVDS panels
to the simple-panel driver.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
[m.felsch@pengutronix.de: fix typo in compatible dt-binding]
[m.felsch@pengutronix.de: add property bindings]
Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180523092504.5142-3-m.felsch@pengutronix.de
---
 .../bindings/display/panel/dlc,dlc0700yzg-1.txt    | 13 +++++++++
 drivers/gpu/drm/panel/panel-simple.c               | 32 ++++++++++++++++++++++
 2 files changed, 45 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/dlc,dlc0700yzg-1.txt

diff --git a/Documentation/devicetree/bindings/display/panel/dlc,dlc0700yzg-1.txt b/Documentation/devicetree/bindings/display/panel/dlc,dlc0700yzg-1.txt
new file mode 100644
index 000000000000..bf06bb025b08
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/dlc,dlc0700yzg-1.txt
@@ -0,0 +1,13 @@
+DLC Display Co. DLC0700YZG-1 7.0" WSVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "dlc,dlc0700yzg-1"
+- power-supply: See simple-panel.txt
+
+Optional properties:
+- reset-gpios: See panel-common.txt
+- enable-gpios: See simple-panel.txt
+- backlight: See simple-panel.txt
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 5eb506256d42..230f030d1ea9 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -884,6 +884,35 @@ static const struct panel_desc chunghwa_claa101wb01 = {
 	},
 };
 
+static const struct display_timing dlc_dlc0700yzg_1_timing = {
+	.pixelclock = { 45000000, 51200000, 57000000 },
+	.hactive = { 1024, 1024, 1024 },
+	.hfront_porch = { 100, 106, 113 },
+	.hback_porch = { 100, 106, 113 },
+	.hsync_len = { 100, 108, 114 },
+	.vactive = { 600, 600, 600 },
+	.vfront_porch = { 8, 11, 15 },
+	.vback_porch = { 8, 11, 15 },
+	.vsync_len = { 9, 13, 15 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc dlc_dlc0700yzg_1 = {
+	.timings = &dlc_dlc0700yzg_1_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 154,
+		.height = 86,
+	},
+	.delay = {
+		.prepare = 30,
+		.enable = 200,
+		.disable = 200,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X7X3_SPWG,
+};
+
 static const struct drm_display_mode edt_et057090dhu_mode = {
 	.clock = 25175,
 	.hdisplay = 640,
@@ -2220,6 +2249,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "chunghwa,claa101wb01",
 		.data = &chunghwa_claa101wb01
+	}, {
+		.compatible = "dlc,dlc0700yzg-1",
+		.data = &dlc_dlc0700yzg_1,
 	}, {
 		.compatible = "edt,et057090dhu",
 		.data = &edt_et057090dhu,
-- 
cgit v1.2.3


From 5fa8e4a22182df8ea39adeba4bd518506e26a96d Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 9 May 2018 15:00:39 +0200
Subject: drm/panel: Make of_drm_find_panel() return an ERR_PTR() instead of
 NULL

Right now, the DRM panel logic returns NULL when a panel pointing to
the passed OF node is not present in the list of registered panels.

Most drivers interpret this NULL value as -EPROBE_DEFER, but we are
about to modify the semantic of of_drm_find_panel() and let the
framework return -ENODEV when the device node we're pointing to has
a status property that is not equal to "okay" or "ok".

Let's first patch the of_drm_find_panel() implementation to return
ERR_PTR(-EPROBE_DEFER) instead of NULL and patch all callers to replace
the '!panel' check by an 'IS_ERR(panel)' one.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180509130042.9435-2-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/bridge/cdns-dsi.c                   | 2 +-
 drivers/gpu/drm/bridge/lvds-encoder.c               | 4 ++--
 drivers/gpu/drm/drm_of.c                            | 4 +++-
 drivers/gpu/drm/drm_panel.c                         | 6 ++++--
 drivers/gpu/drm/exynos/exynos_dp.c                  | 6 ++++--
 drivers/gpu/drm/exynos/exynos_drm_dpi.c             | 4 ++--
 drivers/gpu/drm/exynos/exynos_drm_dsi.c             | 3 +++
 drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c           | 5 +++--
 drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c   | 4 ++--
 drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c | 5 ++++-
 drivers/gpu/drm/msm/dsi/dsi_host.c                  | 2 +-
 drivers/gpu/drm/rcar-du/rcar_lvds.c                 | 4 ++--
 drivers/gpu/drm/rockchip/dw-mipi-dsi.c              | 2 +-
 drivers/gpu/drm/sti/sti_dvo.c                       | 4 +++-
 drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c              | 4 ++--
 drivers/gpu/drm/tegra/dsi.c                         | 3 +++
 drivers/gpu/drm/tegra/output.c                      | 4 ++--
 include/drm/drm_panel.h                             | 2 +-
 18 files changed, 43 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/bridge/cdns-dsi.c b/drivers/gpu/drm/bridge/cdns-dsi.c
index f2d43f24acfb..ce9496d13986 100644
--- a/drivers/gpu/drm/bridge/cdns-dsi.c
+++ b/drivers/gpu/drm/bridge/cdns-dsi.c
@@ -1152,7 +1152,7 @@ static int cdns_dsi_attach(struct mipi_dsi_host *host,
 		np = of_node_get(dev->dev.of_node);
 
 	panel = of_drm_find_panel(np);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		bridge = drm_panel_bridge_add(panel, DRM_MODE_CONNECTOR_DSI);
 	} else {
 		bridge = of_drm_find_bridge(dev->dev.of_node);
diff --git a/drivers/gpu/drm/bridge/lvds-encoder.c b/drivers/gpu/drm/bridge/lvds-encoder.c
index 75b0d3f6e4de..f56c92f7af7c 100644
--- a/drivers/gpu/drm/bridge/lvds-encoder.c
+++ b/drivers/gpu/drm/bridge/lvds-encoder.c
@@ -68,9 +68,9 @@ static int lvds_encoder_probe(struct platform_device *pdev)
 
 	panel = of_drm_find_panel(panel_node);
 	of_node_put(panel_node);
-	if (!panel) {
+	if (IS_ERR(panel)) {
 		dev_dbg(&pdev->dev, "panel not found, deferring probe\n");
-		return -EPROBE_DEFER;
+		return PTR_ERR(panel);
 	}
 
 	lvds_encoder->panel_bridge =
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 3b8c7a6a5720..1f4a16772583 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -241,8 +241,10 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 
 	if (panel) {
 		*panel = of_drm_find_panel(remote);
-		if (*panel)
+		if (!IS_ERR(*panel))
 			ret = 0;
+		else
+			*panel = NULL;
 	}
 
 	/* No panel found yet, check for a bridge next. */
diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 965530a6f4cd..7e5530a04846 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -151,7 +151,9 @@ EXPORT_SYMBOL(drm_panel_detach);
  * tree node. If a matching panel is found, return a pointer to it.
  *
  * Return: A pointer to the panel registered for the specified device tree
- * node or NULL if no panel matching the device tree node can be found.
+ * node or an ERR_PTR() if no panel matching the device tree node can be found.
+ * The only error that can be reported is -EPROBE_DEFER, meaning that the panel
+ * device has not been probed yet, and the caller should retry later.
  */
 struct drm_panel *of_drm_find_panel(const struct device_node *np)
 {
@@ -167,7 +169,7 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np)
 	}
 
 	mutex_unlock(&panel_lock);
-	return NULL;
+	return ERR_PTR(-EPROBE_DEFER);
 }
 EXPORT_SYMBOL(of_drm_find_panel);
 #endif
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index 86330f396784..af7ab1ceb50f 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -232,9 +232,11 @@ static int exynos_dp_probe(struct platform_device *pdev)
 	np = of_parse_phandle(dev->of_node, "panel", 0);
 	if (np) {
 		dp->plat_data.panel = of_drm_find_panel(np);
+
 		of_node_put(np);
-		if (!dp->plat_data.panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(dp->plat_data.panel))
+			return PTR_ERR(dp->plat_data.panel);
+
 		goto out;
 	}
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 66945e0dc57f..5887e8522b70 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -240,8 +240,8 @@ struct drm_encoder *exynos_dpi_probe(struct device *dev)
 
 	if (ctx->panel_node) {
 		ctx->panel = of_drm_find_panel(ctx->panel_node);
-		if (!ctx->panel)
-			return ERR_PTR(-EPROBE_DEFER);
+		if (IS_ERR(ctx->panel))
+			return ERR_CAST(ctx->panel);
 	}
 
 	return &ctx->encoder;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 6d29777884f9..809e1e0447df 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1519,6 +1519,9 @@ static int exynos_dsi_host_attach(struct mipi_dsi_host *host,
 	dsi->format = device->format;
 	dsi->mode_flags = device->mode_flags;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
+	if (IS_ERR(dsi->panel))
+		dsi->panel = NULL;
+
 	if (dsi->panel) {
 		drm_panel_attach(dsi->panel, &dsi->connector);
 		dsi->connector.status = connector_status_connected;
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index c54806d08dd7..681e2a07d03b 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -148,8 +148,9 @@ int fsl_dcu_create_outputs(struct fsl_dcu_drm_device *fsl_dev)
 	if (panel_node) {
 		fsl_dev->connector.panel = of_drm_find_panel(panel_node);
 		of_node_put(panel_node);
-		if (!fsl_dev->connector.panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(fsl_dev->connector.panel))
+			return PTR_ERR(fsl_dev->connector.panel);
+
 		return fsl_dcu_attach_panel(fsl_dev, fsl_dev->connector.panel);
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
index 4a645926edb7..2bfb39082f54 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lcdc_encoder.c
@@ -341,7 +341,7 @@ static void mdp4_lcdc_encoder_disable(struct drm_encoder *encoder)
 	mdp4_write(mdp4_kms, REG_MDP4_LCDC_ENABLE, 0);
 
 	panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		drm_panel_disable(panel);
 		drm_panel_unprepare(panel);
 	}
@@ -410,7 +410,7 @@ static void mdp4_lcdc_encoder_enable(struct drm_encoder *encoder)
 		dev_err(dev->dev, "failed to enable lcdc_clk: %d\n", ret);
 
 	panel = of_drm_find_panel(mdp4_lcdc_encoder->panel_node);
-	if (panel) {
+	if (!IS_ERR(panel)) {
 		drm_panel_prepare(panel);
 		drm_panel_enable(panel);
 	}
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
index e3b1c86b7aae..32fba5664b0e 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -34,9 +34,12 @@ static enum drm_connector_status mdp4_lvds_connector_detect(
 	struct mdp4_lvds_connector *mdp4_lvds_connector =
 			to_mdp4_lvds_connector(connector);
 
-	if (!mdp4_lvds_connector->panel)
+	if (!mdp4_lvds_connector->panel) {
 		mdp4_lvds_connector->panel =
 			of_drm_find_panel(mdp4_lvds_connector->panel_node);
+		if (IS_ERR(mdp4_lvds_connector->panel))
+			mdp4_lvds_connector->panel = NULL;
+	}
 
 	return mdp4_lvds_connector->panel ?
 			connector_status_connected :
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 2f1a2780658a..29841f440111 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -1898,7 +1898,7 @@ int msm_dsi_host_register(struct mipi_dsi_host *host, bool check_defer)
 		 * output
 		 */
 		if (check_defer && msm_host->device_node) {
-			if (!of_drm_find_panel(msm_host->device_node))
+			if (IS_ERR(of_drm_find_panel(msm_host->device_node)))
 				if (!of_drm_find_bridge(msm_host->device_node))
 					return -EPROBE_DEFER;
 		}
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 155ad840f3c5..5d8e391e75f4 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -434,8 +434,8 @@ static int rcar_lvds_parse_dt(struct rcar_lvds *lvds)
 			ret = -EPROBE_DEFER;
 	} else {
 		lvds->panel = of_drm_find_panel(remote);
-		if (!lvds->panel)
-			ret = -EPROBE_DEFER;
+		if (IS_ERR(lvds->panel))
+			ret = PTR_ERR(lvds->panel);
 	}
 
 done:
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
index d53d5a09547f..01642aaf6127 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
@@ -595,7 +595,7 @@ static int dw_mipi_dsi_host_attach(struct mipi_dsi_host *host,
 	dsi->format = device->format;
 	dsi->mode_flags = device->mode_flags;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
-	if (dsi->panel)
+	if (!IS_ERR(dsi->panel))
 		return drm_panel_attach(dsi->panel, &dsi->connector);
 
 	return -EINVAL;
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index a5979cd25cc7..030da55a8d30 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -387,7 +387,9 @@ sti_dvo_connector_detect(struct drm_connector *connector, bool force)
 
 	if (!dvo->panel) {
 		dvo->panel = of_drm_find_panel(dvo->panel_node);
-		if (dvo->panel)
+		if (IS_ERR(dvo->panel))
+			dvo->panel = NULL;
+		else
 			drm_panel_attach(dvo->panel, connector);
 	}
 
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index da9814f94d00..2b40d1f6aee8 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -833,8 +833,8 @@ static int sun6i_dsi_attach(struct mipi_dsi_host *host,
 
 	dsi->device = device;
 	dsi->panel = of_drm_find_panel(device->dev.of_node);
-	if (!dsi->panel)
-		return -EINVAL;
+	if (IS_ERR(dsi->panel))
+		return PTR_ERR(dsi->panel);
 
 	dev_info(host->dev, "Attached device %s\n", device->name);
 
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index 87c5d89bc9ba..ad88ec230329 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -1411,6 +1411,9 @@ static int tegra_dsi_host_attach(struct mipi_dsi_host *host,
 		struct tegra_output *output = &dsi->output;
 
 		output->panel = of_drm_find_panel(device->dev.of_node);
+		if (IS_ERR(output->panel))
+			output->panel = NULL;
+
 		if (output->panel && output->connector.dev) {
 			drm_panel_attach(output->panel, &output->connector);
 			drm_helper_hpd_irq_event(output->connector.dev);
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index ffe34bd0bb9d..0c0936511bb4 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -110,8 +110,8 @@ int tegra_output_probe(struct tegra_output *output)
 	panel = of_parse_phandle(output->of_node, "nvidia,panel", 0);
 	if (panel) {
 		output->panel = of_drm_find_panel(panel);
-		if (!output->panel)
-			return -EPROBE_DEFER;
+		if (IS_ERR(output->panel))
+			return PTR_ERR(output->panel);
 
 		of_node_put(panel);
 	}
diff --git a/include/drm/drm_panel.h b/include/drm/drm_panel.h
index 26a1b5fd8796..582a0ec0aa70 100644
--- a/include/drm/drm_panel.h
+++ b/include/drm/drm_panel.h
@@ -200,7 +200,7 @@ struct drm_panel *of_drm_find_panel(const struct device_node *np);
 #else
 static inline struct drm_panel *of_drm_find_panel(const struct device_node *np)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 #endif
 
-- 
cgit v1.2.3


From c59eb3cfde1faed960fe6de5040c4bd4310fb1cd Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 9 May 2018 15:00:40 +0200
Subject: drm/panel: Let of_drm_find_panel() return -ENODEV when the panel is
 disabled

DT nodes might be present in the DT but with a status property set to
"disabled" or "fail". In this case, we should not return -EPROBE_DEFER
when the caller asks for a drm_panel instance. Return -ENODEV instead.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180509130042.9435-3-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_panel.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_panel.c b/drivers/gpu/drm/drm_panel.c
index 7e5530a04846..b902361dee6e 100644
--- a/drivers/gpu/drm/drm_panel.c
+++ b/drivers/gpu/drm/drm_panel.c
@@ -152,13 +152,18 @@ EXPORT_SYMBOL(drm_panel_detach);
  *
  * Return: A pointer to the panel registered for the specified device tree
  * node or an ERR_PTR() if no panel matching the device tree node can be found.
- * The only error that can be reported is -EPROBE_DEFER, meaning that the panel
- * device has not been probed yet, and the caller should retry later.
+ * Possible error codes returned by this function:
+ * - EPROBE_DEFER: the panel device has not been probed yet, and the caller
+ *   should retry later
+ * - ENODEV: the device is not available (status != "okay" or "ok")
  */
 struct drm_panel *of_drm_find_panel(const struct device_node *np)
 {
 	struct drm_panel *panel;
 
+	if (!of_device_is_available(np))
+		return ERR_PTR(-ENODEV);
+
 	mutex_lock(&panel_lock);
 
 	list_for_each_entry(panel, &panel_list, list) {
-- 
cgit v1.2.3


From 2e64a174179a144742fa70f09803a012aceca476 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 9 May 2018 15:00:41 +0200
Subject: drm/of: Make drm_of_find_panel_or_bridge() fail when the device is
 disabled

There's no point searching for a drm_bridge or drm_panel if the OF node
we're pointing has a status property that is not "okay" or "ok". Just
return -ENODEV in this case.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180509130042.9435-4-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/drm_of.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 1f4a16772583..260612958cbe 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -239,6 +239,11 @@ int drm_of_find_panel_or_bridge(const struct device_node *np,
 	if (!remote)
 		return -ENODEV;
 
+	if (!of_device_is_available(remote)) {
+		of_node_put(remote);
+		return -ENODEV;
+	}
+
 	if (panel) {
 		*panel = of_drm_find_panel(remote);
 		if (!IS_ERR(*panel))
-- 
cgit v1.2.3


From 1b9883eae82251b742627ebd9d544d1b1bddf121 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 9 May 2018 15:00:42 +0200
Subject: drm/vc4: Support the case where the DSI device is disabled

Having a device with a status property != "okay" in the DT is a valid
use case, and we should not prevent the registration of the DRM device
when the DSI device connected to the DSI controller is disabled.

Consider the ENODEV return code as a valid result and do not expose the
DSI encoder/connector when it happens.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180509130042.9435-5-boris.brezillon@bootlin.com
---
 drivers/gpu/drm/vc4/vc4_dsi.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 9c8e89372d1c..0c607eb33d7e 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -1612,8 +1612,18 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 
 	ret = drm_of_find_panel_or_bridge(dev->of_node, 0, 0,
 					  &panel, &dsi->bridge);
-	if (ret)
+	if (ret) {
+		/* If the bridge or panel pointed by dev->of_node is not
+		 * enabled, just return 0 here so that we don't prevent the DRM
+		 * dev from being registered. Of course that means the DSI
+		 * encoder won't be exposed, but that's not a problem since
+		 * nothing is connected to it.
+		 */
+		if (ret == -ENODEV)
+			return 0;
+
 		return ret;
+	}
 
 	if (panel) {
 		dsi->bridge = devm_drm_panel_bridge_add(dev, panel,
@@ -1664,7 +1674,8 @@ static void vc4_dsi_unbind(struct device *dev, struct device *master,
 	struct vc4_dev *vc4 = to_vc4_dev(drm);
 	struct vc4_dsi *dsi = dev_get_drvdata(dev);
 
-	pm_runtime_disable(dev);
+	if (dsi->bridge)
+		pm_runtime_disable(dev);
 
 	vc4_dsi_encoder_destroy(dsi->encoder);
 
-- 
cgit v1.2.3


From b0b7aa407e929b8e25a2982bff428eacd50f1630 Mon Sep 17 00:00:00 2001
From: Andrzej Hajda <a.hajda@samsung.com>
Date: Tue, 19 Jun 2018 10:19:25 +0200
Subject: dt-bindings: display: Add DT bindings for BOE HV070WSA-100 panel

The patch adds bindings to BOE HV070-WSA WSVGA panel. Bindings are
compatible with simple panel bindings.

Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Maciej Purski <m.purski@samsung.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1529396370-18761-5-git-send-email-m.purski@samsung.com
---
 .../bindings/display/panel/boe,hv070wsa-100.txt    | 28 ++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/boe,hv070wsa-100.txt

diff --git a/Documentation/devicetree/bindings/display/panel/boe,hv070wsa-100.txt b/Documentation/devicetree/bindings/display/panel/boe,hv070wsa-100.txt
new file mode 100644
index 000000000000..55183d360032
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/boe,hv070wsa-100.txt
@@ -0,0 +1,28 @@
+BOE HV070WSA-100 7.01" WSVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "boe,hv070wsa-100"
+- power-supply: regulator to provide the VCC supply voltage (3.3 volts)
+- enable-gpios: GPIO pin to enable and disable panel (active high)
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
+
+The device node can contain one 'port' child node with one child
+'endpoint' node, according to the bindings defined in [1]. This
+node should describe panel's video bus.
+
+[1]: Documentation/devicetree/bindings/media/video-interfaces.txt
+
+Example:
+
+	panel: panel {
+		compatible = "boe,hv070wsa-100";
+		power-supply = <&vcc_3v3_reg>;
+		enable-gpios = <&gpd1 3 GPIO_ACTIVE_HIGH>;
+		port {
+			panel_ep: endpoint {
+				remote-endpoint = <&bridge_out_ep>;
+			};
+		};
+	};
-- 
cgit v1.2.3


From ae8cf41b6a5e3a0847cf5ef9bf6feb82e75ab5eb Mon Sep 17 00:00:00 2001
From: Andrzej Hajda <a.hajda@samsung.com>
Date: Tue, 19 Jun 2018 10:19:26 +0200
Subject: drm/panel: simple: Add support for BOE HV070WSA-100 panel to
 simple-panel

The patch adds support for BOE HV070WSA-100 WSVGA 7.01 inch panel to the
panel-simple driver. The panel is used in Exynos5250-arndale boards.

Signed-off-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Maciej Purski <m.purski@samsung.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1529396370-18761-6-git-send-email-m.purski@samsung.com
---
 drivers/gpu/drm/panel/panel-simple.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 230f030d1ea9..cca1168f0881 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -772,6 +772,28 @@ static const struct panel_desc avic_tm070ddh03 = {
 	},
 };
 
+static const struct drm_display_mode boe_hv070wsa_mode = {
+	.clock = 40800,
+	.hdisplay = 1024,
+	.hsync_start = 1024 + 90,
+	.hsync_end = 1024 + 90 + 90,
+	.htotal = 1024 + 90 + 90 + 90,
+	.vdisplay = 600,
+	.vsync_start = 600 + 3,
+	.vsync_end = 600 + 3 + 4,
+	.vtotal = 600 + 3 + 4 + 3,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc boe_hv070wsa = {
+	.modes = &boe_hv070wsa_mode,
+	.num_modes = 1,
+	.size = {
+		.width = 154,
+		.height = 90,
+	},
+};
+
 static const struct drm_display_mode boe_nv101wxmn51_modes[] = {
 	{
 		.clock = 71900,
@@ -2237,6 +2259,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "avic,tm070ddh03",
 		.data = &avic_tm070ddh03,
+	}, {
+		.compatible = "boe,hv070wsa-100",
+		.data = &boe_hv070wsa
 	}, {
 		.compatible = "boe,nv101wxmn51",
 		.data = &boe_nv101wxmn51,
-- 
cgit v1.2.3


From 955f60db0f2b87094f64df3d7f608fdac4a6ebb1 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@ti.com>
Date: Mon, 18 Jun 2018 16:22:34 +0300
Subject: drm: Add support for extracting sync signal drive edge from videomode

The sync in some panels needs to be driven by different edge of the pixel
clock compared to data. This is reflected by the
DISPLAY_FLAGS_SYNC_(POS|NEG)EDGE in videmode flags.
Add similar similar definitions for bus_flags and convert the sync drive
edge via drm_bus_flags_from_videomode().

Signed-off-by: Peter Ujfalusi <peter.ujfalusi@ti.com>
Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Signed-off-by: Jyri Sarha <jsarha@ti.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618132242.8673-2-tomi.valkeinen@ti.com
---
 drivers/gpu/drm/drm_modes.c | 15 +++++++++++----
 include/drm/drm_connector.h |  4 ++++
 2 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index 7f552d5fa88e..f8f7eae738ab 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -659,10 +659,12 @@ EXPORT_SYMBOL_GPL(drm_display_mode_to_videomode);
  * drm_bus_flags_from_videomode - extract information about pixelclk and
  * DE polarity from videomode and store it in a separate variable
  * @vm: videomode structure to use
- * @bus_flags: information about pixelclk and DE polarity will be stored here
+ * @bus_flags: information about pixelclk, sync and DE polarity will be stored
+ * here
  *
- * Sets DRM_BUS_FLAG_DE_(LOW|HIGH) and DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE
- * in @bus_flags according to DISPLAY_FLAGS found in @vm
+ * Sets DRM_BUS_FLAG_DE_(LOW|HIGH),  DRM_BUS_FLAG_PIXDATA_(POS|NEG)EDGE and
+ * DISPLAY_FLAGS_SYNC_(POS|NEG)EDGE in @bus_flags according to DISPLAY_FLAGS
+ * found in @vm
  */
 void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags)
 {
@@ -672,6 +674,11 @@ void drm_bus_flags_from_videomode(const struct videomode *vm, u32 *bus_flags)
 	if (vm->flags & DISPLAY_FLAGS_PIXDATA_NEGEDGE)
 		*bus_flags |= DRM_BUS_FLAG_PIXDATA_NEGEDGE;
 
+	if (vm->flags & DISPLAY_FLAGS_SYNC_POSEDGE)
+		*bus_flags |= DRM_BUS_FLAG_SYNC_POSEDGE;
+	if (vm->flags & DISPLAY_FLAGS_SYNC_NEGEDGE)
+		*bus_flags |= DRM_BUS_FLAG_SYNC_NEGEDGE;
+
 	if (vm->flags & DISPLAY_FLAGS_DE_LOW)
 		*bus_flags |= DRM_BUS_FLAG_DE_LOW;
 	if (vm->flags & DISPLAY_FLAGS_DE_HIGH)
@@ -684,7 +691,7 @@ EXPORT_SYMBOL_GPL(drm_bus_flags_from_videomode);
  * of_get_drm_display_mode - get a drm_display_mode from devicetree
  * @np: device_node with the timing specification
  * @dmode: will be set to the return value
- * @bus_flags: information about pixelclk and DE polarity
+ * @bus_flags: information about pixelclk, sync and DE polarity
  * @index: index into the list of display timings in devicetree
  *
  * This function is expensive and should only be used, if only one mode is to be
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index ad397dfc042b..a5179eb9e56f 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -290,6 +290,10 @@ struct drm_display_info {
 #define DRM_BUS_FLAG_DATA_MSB_TO_LSB	(1<<4)
 /* data is transmitted LSB to MSB on the bus */
 #define DRM_BUS_FLAG_DATA_LSB_TO_MSB	(1<<5)
+/* drive sync on pos. edge */
+#define DRM_BUS_FLAG_SYNC_POSEDGE	(1<<6)
+/* drive sync on neg. edge */
+#define DRM_BUS_FLAG_SYNC_NEGEDGE	(1<<7)
 
 	/**
 	 * @bus_flags: Additional information (like pixel signal polarity) for
-- 
cgit v1.2.3


From 3b39ad7a553f3ecdf16374973e4b0971b861769d Mon Sep 17 00:00:00 2001
From: Tomi Valkeinen <tomi.valkeinen@ti.com>
Date: Mon, 18 Jun 2018 16:22:40 +0300
Subject: drm/panel: simple: Add newhaven, nhd-4.3-480272ef-atxl LCD

Add support for newhaven,nhd-4.3-480272ef-atxl to panel-simple.

Signed-off-by: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: Thierry Reding <thierry.reding@gmail.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180618132242.8673-8-tomi.valkeinen@ti.com
---
 .../panel/newhaven,nhd-4.3-480272ef-atxl.txt       |  7 +++++
 drivers/gpu/drm/panel/panel-simple.c               | 30 ++++++++++++++++++++++
 2 files changed, 37 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/newhaven,nhd-4.3-480272ef-atxl.txt

diff --git a/Documentation/devicetree/bindings/display/panel/newhaven,nhd-4.3-480272ef-atxl.txt b/Documentation/devicetree/bindings/display/panel/newhaven,nhd-4.3-480272ef-atxl.txt
new file mode 100644
index 000000000000..e78292b1a131
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/newhaven,nhd-4.3-480272ef-atxl.txt
@@ -0,0 +1,7 @@
+Newhaven Display International 480 x 272 TFT LCD panel
+
+Required properties:
+- compatible: should be "newhaven,nhd-4.3-480272ef-atxl"
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index cca1168f0881..2c4857e08a76 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1625,6 +1625,33 @@ static const struct panel_desc netron_dy_e231732 = {
 	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
 };
 
+static const struct drm_display_mode newhaven_nhd_43_480272ef_atxl_mode = {
+	.clock = 9000,
+	.hdisplay = 480,
+	.hsync_start = 480 + 2,
+	.hsync_end = 480 + 2 + 41,
+	.htotal = 480 + 2 + 41 + 2,
+	.vdisplay = 272,
+	.vsync_start = 272 + 2,
+	.vsync_end = 272 + 2 + 10,
+	.vtotal = 272 + 2 + 10 + 2,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc newhaven_nhd_43_480272ef_atxl = {
+	.modes = &newhaven_nhd_43_480272ef_atxl_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 95,
+		.height = 54,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE |
+		     DRM_BUS_FLAG_SYNC_POSEDGE,
+};
+
 static const struct display_timing nlt_nl192108ac18_02d_timing = {
 	.pixelclock = { 130000000, 148350000, 163000000 },
 	.hactive = { 1920, 1920, 1920 },
@@ -2367,6 +2394,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "netron-dy,e231732",
 		.data = &netron_dy_e231732,
+	}, {
+		.compatible = "newhaven,nhd-4.3-480272ef-atxl",
+		.data = &newhaven_nhd_43_480272ef_atxl,
 	}, {
 		.compatible = "nlt,nl192108ac18-02d",
 		.data = &nlt_nl192108ac18_02d,
-- 
cgit v1.2.3


From a5d2ade627dcaa825707e20da6994e79c95e2434 Mon Sep 17 00:00:00 2001
From: Christoph Fritz <chf.fritz@googlemail.com>
Date: Mon, 4 Jun 2018 13:16:48 +0200
Subject: drm/panel: simple: Add support for Innolux G070Y2-L01

This patch adds support for Innolux G070Y2-L01 7" WVGA (800x480) TFT LCD
panel.

Signed-off-by: Christoph Fritz <chf.fritz@googlemail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1528111008.2818.20.camel@googlemail.com
---
 .../bindings/display/panel/innolux,g070y2-l01.txt  | 12 +++++++
 drivers/gpu/drm/panel/panel-simple.c               | 37 ++++++++++++++++++++--
 2 files changed, 47 insertions(+), 2 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/display/panel/innolux,g070y2-l01.txt

diff --git a/Documentation/devicetree/bindings/display/panel/innolux,g070y2-l01.txt b/Documentation/devicetree/bindings/display/panel/innolux,g070y2-l01.txt
new file mode 100644
index 000000000000..7c234cf68e11
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/innolux,g070y2-l01.txt
@@ -0,0 +1,12 @@
+Innolux G070Y2-L01 7" WVGA (800x480) TFT LCD panel
+
+Required properties:
+- compatible: should be "innolux,g070y2-l01"
+- power-supply: as specified in the base binding
+
+Optional properties:
+- backlight: as specified in the base binding
+- enable-gpios: as specified in the base binding
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 2c4857e08a76..da7fbd2b2a75 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1176,6 +1176,36 @@ static const struct panel_desc innolux_at070tn92 = {
 	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
 };
 
+static const struct display_timing innolux_g070y2_l01_timing = {
+	.pixelclock = { 28000000, 29500000, 32000000 },
+	.hactive = { 800, 800, 800 },
+	.hfront_porch = { 61, 91, 141 },
+	.hback_porch = { 60, 90, 140 },
+	.hsync_len = { 12, 12, 12 },
+	.vactive = { 480, 480, 480 },
+	.vfront_porch = { 4, 9, 30 },
+	.vback_porch = { 4, 8, 28 },
+	.vsync_len = { 2, 2, 2 },
+	.flags = DISPLAY_FLAGS_DE_HIGH,
+};
+
+static const struct panel_desc innolux_g070y2_l01 = {
+	.timings = &innolux_g070y2_l01_timing,
+	.num_timings = 1,
+	.bpc = 6,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.delay = {
+		.prepare = 10,
+		.enable = 100,
+		.disable = 100,
+		.unprepare = 800,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X7X4_SPWG,
+};
+
 static const struct display_timing innolux_g101ice_l01_timing = {
 	.pixelclock = { 60400000, 71100000, 74700000 },
 	.hactive = { 1280, 1280, 1280 },
@@ -2341,10 +2371,13 @@ static const struct of_device_id platform_of_match[] = {
 		.compatible = "innolux,at070tn92",
 		.data = &innolux_at070tn92,
 	}, {
-		.compatible ="innolux,g101ice-l01",
+		.compatible = "innolux,g070y2-l01",
+		.data = &innolux_g070y2_l01,
+	}, {
+		.compatible = "innolux,g101ice-l01",
 		.data = &innolux_g101ice_l01
 	}, {
-		.compatible ="innolux,g121i1-l01",
+		.compatible = "innolux,g121i1-l01",
 		.data = &innolux_g121i1_l01
 	}, {
 		.compatible = "innolux,g121x1-l03",
-- 
cgit v1.2.3


From 03fa9aa384940b006cabb03fe25a073f394f60d1 Mon Sep 17 00:00:00 2001
From: Michal Vokáč <michal.vokac@ysoft.com>
Date: Mon, 25 Jun 2018 14:41:29 +0200
Subject: dt-bindings: Add DataImage, Inc. vendor prefix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DataImage is a Taiwan-based manufacturer of LCD panels.

Signed-off-by: Michal Vokáč <michal.vokac@ysoft.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1529930490-11874-1-git-send-email-michal.vokac@ysoft.com
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 10fb0df60b6a..5fd6c539e898 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -86,6 +86,7 @@ cubietech	Cubietech, Ltd.
 cypress	Cypress Semiconductor Corporation
 cznic	CZ.NIC, z.s.p.o.
 dallas	Maxim Integrated Products (formerly Dallas Semiconductor)
+dataimage	DataImage, Inc.
 davicom	DAVICOM Semiconductor, Inc.
 delta	Delta Electronics, Inc.
 denx	Denx Software Engineering
-- 
cgit v1.2.3


From 97ceb1fb08b6a2f78aa44a7c229ca280964860c0 Mon Sep 17 00:00:00 2001
From: Michal Vokáč <michal.vokac@ysoft.com>
Date: Mon, 25 Jun 2018 14:41:30 +0200
Subject: drm/panel: simple: Add support for DataImage SCF0700C48GGU18
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds support for the DataImage SCF0700C48GGU18 7.0" WVGA (800x480)
TFT LCD panel. The panel has 24-bit parallel interface and can be
supported by the simple panel driver.

Signed-off-by: Michal Vokáč <michal.vokac@ysoft.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1529930490-11874-2-git-send-email-michal.vokac@ysoft.com
---
 .../display/panel/dataimage,scf0700c48ggu18.txt    |  8 ++++++
 drivers/gpu/drm/panel/panel-simple.c               | 29 ++++++++++++++++++++++
 2 files changed, 37 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/dataimage,scf0700c48ggu18.txt

diff --git a/Documentation/devicetree/bindings/display/panel/dataimage,scf0700c48ggu18.txt b/Documentation/devicetree/bindings/display/panel/dataimage,scf0700c48ggu18.txt
new file mode 100644
index 000000000000..897085ee3cd4
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/dataimage,scf0700c48ggu18.txt
@@ -0,0 +1,8 @@
+DataImage, Inc. 7" WVGA (800x480) TFT LCD panel with 24-bit parallel interface.
+
+Required properties:
+- compatible: should be "dataimage,scf0700c48ggu18"
+- power-supply: as specified in the base binding
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index da7fbd2b2a75..3b226ad8acad 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -906,6 +906,32 @@ static const struct panel_desc chunghwa_claa101wb01 = {
 	},
 };
 
+static const struct drm_display_mode dataimage_scf0700c48ggu18_mode = {
+	.clock = 33260,
+	.hdisplay = 800,
+	.hsync_start = 800 + 40,
+	.hsync_end = 800 + 40 + 128,
+	.htotal = 800 + 40 + 128 + 88,
+	.vdisplay = 480,
+	.vsync_start = 480 + 10,
+	.vsync_end = 480 + 10 + 2,
+	.vtotal = 480 + 10 + 2 + 33,
+	.vrefresh = 60,
+	.flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC,
+};
+
+static const struct panel_desc dataimage_scf0700c48ggu18 = {
+	.modes = &dataimage_scf0700c48ggu18_mode,
+	.num_modes = 1,
+	.bpc = 8,
+	.size = {
+		.width = 152,
+		.height = 91,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB888_1X24,
+	.bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_POSEDGE,
+};
+
 static const struct display_timing dlc_dlc0700yzg_1_timing = {
 	.pixelclock = { 45000000, 51200000, 57000000 },
 	.hactive = { 1024, 1024, 1024 },
@@ -2331,6 +2357,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "chunghwa,claa101wb01",
 		.data = &chunghwa_claa101wb01
+	}, {
+		.compatible = "dataimage,scf0700c48ggu18",
+		.data = &dataimage_scf0700c48ggu18,
 	}, {
 		.compatible = "dlc,dlc0700yzg-1",
 		.data = &dlc_dlc0700yzg_1,
-- 
cgit v1.2.3


From 3d5664f95ebe264c16f3ebfadce9eee6fee9acf7 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 26 Jun 2018 17:03:54 +0100
Subject: drm/panel: ili9881c: Fix missing assignment to error return ret

Currently, ret is being checked for an error condition however it
is not being assigned in the previous statement on the call of
function mipi_dsi_dcs_exit_sleep_mode.  Add in the missing assignment
of ret.

Detected by CoverityScan, CID#1470174, 1470178 ("Unchecked return value")

Fixes: 26aec25593c2 ("drm/panel: Add Ilitek ILI9881c panel driver")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180626160354.1363-1-colin.king@canonical.com
---
 drivers/gpu/drm/panel/panel-ilitek-ili9881c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
index e848af235df5..3ad4a46c4e94 100644
--- a/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
+++ b/drivers/gpu/drm/panel/panel-ilitek-ili9881c.c
@@ -334,7 +334,7 @@ static int ili9881c_prepare(struct drm_panel *panel)
 	if (ret)
 		return ret;
 
-	mipi_dsi_dcs_exit_sleep_mode(ctx->dsi);
+	ret = mipi_dsi_dcs_exit_sleep_mode(ctx->dsi);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 7ad4e4636c54dcfbcaf43c8737af3c294ed17d11 Mon Sep 17 00:00:00 2001
From: Lin Huang <hl@rock-chips.com>
Date: Mon, 2 Jul 2018 12:27:18 +0200
Subject: drm/panel: p079zca: Refactor panel driver to support multiple panels

Refactor Innolux P079ZCA panel driver, let it support multi panels from
Innolux that share similar power sequences.

Panels may require different power supplies so use regulator bulk
interfaces and define per panel supply-names.

Changes in v2:
- Change regulator property name to meet the panel datasheet
Changes in v3:
- this patch only refactor P079ZCA panel to support multi panel,
  support P097PFG panel in another patch
Changes in v4:
- Modify the patch which suggest by Thierry
Changes in v5:
- use regulator_bulk to handle different supply number

Signed-off-by: Lin Huang <hl@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702102721.3546-2-heiko@sntech.de
---
 drivers/gpu/drm/panel/panel-innolux-p079zca.c | 143 ++++++++++++++++++--------
 1 file changed, 102 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index bb53e0850764..185a55060195 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -20,12 +20,29 @@
 
 #include <video/mipi_display.h>
 
+struct panel_desc {
+	const struct drm_display_mode *mode;
+	unsigned int bpc;
+	struct {
+		unsigned int width;
+		unsigned int height;
+	} size;
+
+	unsigned long flags;
+	enum mipi_dsi_pixel_format format;
+	unsigned int lanes;
+	const char * const *supply_names;
+	unsigned int num_supplies;
+};
+
 struct innolux_panel {
 	struct drm_panel base;
 	struct mipi_dsi_device *link;
+	const struct panel_desc *desc;
 
 	struct backlight_device *backlight;
-	struct regulator *supply;
+	struct regulator_bulk_data *supplies;
+	unsigned int num_supplies;
 	struct gpio_desc *enable_gpio;
 
 	bool prepared;
@@ -77,7 +94,8 @@ static int innolux_panel_unprepare(struct drm_panel *panel)
 	/* T8: 80ms - 1000ms */
 	msleep(80);
 
-	err = regulator_disable(innolux->supply);
+	err = regulator_bulk_disable(innolux->desc->num_supplies,
+				     innolux->supplies);
 	if (err < 0)
 		return err;
 
@@ -89,14 +107,15 @@ static int innolux_panel_unprepare(struct drm_panel *panel)
 static int innolux_panel_prepare(struct drm_panel *panel)
 {
 	struct innolux_panel *innolux = to_innolux_panel(panel);
-	int err, regulator_err;
+	int err;
 
 	if (innolux->prepared)
 		return 0;
 
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
 
-	err = regulator_enable(innolux->supply);
+	err = regulator_bulk_enable(innolux->desc->num_supplies,
+				    innolux->supplies);
 	if (err < 0)
 		return err;
 
@@ -133,12 +152,9 @@ static int innolux_panel_prepare(struct drm_panel *panel)
 	return 0;
 
 poweroff:
-	regulator_err = regulator_disable(innolux->supply);
-	if (regulator_err)
-		DRM_DEV_ERROR(panel->dev, "failed to disable regulator: %d\n",
-			      regulator_err);
-
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
+	regulator_bulk_disable(innolux->desc->num_supplies, innolux->supplies);
+
 	return err;
 }
 
@@ -162,7 +178,11 @@ static int innolux_panel_enable(struct drm_panel *panel)
 	return 0;
 }
 
-static const struct drm_display_mode default_mode = {
+static const char * const innolux_p079zca_supply_names[] = {
+	"power",
+};
+
+static const struct drm_display_mode innolux_p079zca_mode = {
 	.clock = 56900,
 	.hdisplay = 768,
 	.hsync_start = 768 + 40,
@@ -175,15 +195,31 @@ static const struct drm_display_mode default_mode = {
 	.vrefresh = 60,
 };
 
+static const struct panel_desc innolux_p079zca_panel_desc = {
+	.mode = &innolux_p079zca_mode,
+	.bpc = 8,
+	.size = {
+		.width = 120,
+		.height = 160,
+	},
+	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+		 MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.lanes = 4,
+	.supply_names = innolux_p079zca_supply_names,
+	.num_supplies = ARRAY_SIZE(innolux_p079zca_supply_names),
+};
+
 static int innolux_panel_get_modes(struct drm_panel *panel)
 {
+	struct innolux_panel *innolux = to_innolux_panel(panel);
+	const struct drm_display_mode *m = innolux->desc->mode;
 	struct drm_display_mode *mode;
 
-	mode = drm_mode_duplicate(panel->drm, &default_mode);
+	mode = drm_mode_duplicate(panel->drm, m);
 	if (!mode) {
 		DRM_DEV_ERROR(panel->drm->dev, "failed to add mode %ux%ux@%u\n",
-			      default_mode.hdisplay, default_mode.vdisplay,
-			      default_mode.vrefresh);
+			      m->hdisplay, m->vdisplay, m->vrefresh);
 		return -ENOMEM;
 	}
 
@@ -191,9 +227,11 @@ static int innolux_panel_get_modes(struct drm_panel *panel)
 
 	drm_mode_probed_add(panel->connector, mode);
 
-	panel->connector->display_info.width_mm = 120;
-	panel->connector->display_info.height_mm = 160;
-	panel->connector->display_info.bpc = 8;
+	panel->connector->display_info.width_mm =
+			innolux->desc->size.width;
+	panel->connector->display_info.height_mm =
+			innolux->desc->size.height;
+	panel->connector->display_info.bpc = innolux->desc->bpc;
 
 	return 1;
 }
@@ -207,19 +245,39 @@ static const struct drm_panel_funcs innolux_panel_funcs = {
 };
 
 static const struct of_device_id innolux_of_match[] = {
-	{ .compatible = "innolux,p079zca", },
+	{ .compatible = "innolux,p079zca",
+	  .data = &innolux_p079zca_panel_desc
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, innolux_of_match);
 
-static int innolux_panel_add(struct innolux_panel *innolux)
+static int innolux_panel_add(struct mipi_dsi_device *dsi,
+			     const struct panel_desc *desc)
 {
-	struct device *dev = &innolux->link->dev;
-	int err;
+	struct innolux_panel *innolux;
+	struct device *dev = &dsi->dev;
+	int err, i;
+
+	innolux = devm_kzalloc(dev, sizeof(*innolux), GFP_KERNEL);
+	if (!innolux)
+		return -ENOMEM;
+
+	innolux->desc = desc;
+
+	innolux->supplies = devm_kcalloc(dev, desc->num_supplies,
+					 sizeof(*innolux->supplies),
+					 GFP_KERNEL);
+	if (!innolux->supplies)
+		return -ENOMEM;
 
-	innolux->supply = devm_regulator_get(dev, "power");
-	if (IS_ERR(innolux->supply))
-		return PTR_ERR(innolux->supply);
+	for (i = 0; i < desc->num_supplies; i++)
+		innolux->supplies[i].supply = desc->supply_names[i];
+
+	err = devm_regulator_bulk_get(dev, desc->num_supplies,
+				      innolux->supplies);
+	if (err < 0)
+		return err;
 
 	innolux->enable_gpio = devm_gpiod_get_optional(dev, "enable",
 						       GPIOD_OUT_HIGH);
@@ -230,15 +288,21 @@ static int innolux_panel_add(struct innolux_panel *innolux)
 	}
 
 	innolux->backlight = devm_of_find_backlight(dev);
-
 	if (IS_ERR(innolux->backlight))
 		return PTR_ERR(innolux->backlight);
 
 	drm_panel_init(&innolux->base);
 	innolux->base.funcs = &innolux_panel_funcs;
-	innolux->base.dev = &innolux->link->dev;
+	innolux->base.dev = dev;
+
+	err = drm_panel_add(&innolux->base);
+	if (err < 0)
+		return err;
+
+	mipi_dsi_set_drvdata(dsi, innolux);
+	innolux->link = dsi;
 
-	return drm_panel_add(&innolux->base);
+	return 0;
 }
 
 static void innolux_panel_del(struct innolux_panel *innolux)
@@ -249,28 +313,24 @@ static void innolux_panel_del(struct innolux_panel *innolux)
 
 static int innolux_panel_probe(struct mipi_dsi_device *dsi)
 {
-	struct innolux_panel *innolux;
+	const struct panel_desc *desc;
+	const struct of_device_id *id;
 	int err;
 
-	dsi->lanes = 4;
-	dsi->format = MIPI_DSI_FMT_RGB888;
-	dsi->mode_flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
-			  MIPI_DSI_MODE_LPM;
+	id = of_match_node(innolux_of_match, dsi->dev.of_node);
+	if (!id)
+		return -ENODEV;
 
-	innolux = devm_kzalloc(&dsi->dev, sizeof(*innolux), GFP_KERNEL);
-	if (!innolux)
-		return -ENOMEM;
+	desc = id->data;
+	dsi->mode_flags = desc->flags;
+	dsi->format = desc->format;
+	dsi->lanes = desc->lanes;
 
-	mipi_dsi_set_drvdata(dsi, innolux);
-
-	innolux->link = dsi;
-
-	err = innolux_panel_add(innolux);
+	err = innolux_panel_add(dsi, desc);
 	if (err < 0)
 		return err;
 
-	err = mipi_dsi_attach(dsi);
-	return err;
+	return mipi_dsi_attach(dsi);
 }
 
 static int innolux_panel_remove(struct mipi_dsi_device *dsi)
@@ -317,5 +377,6 @@ static struct mipi_dsi_driver innolux_panel_driver = {
 module_mipi_dsi_driver(innolux_panel_driver);
 
 MODULE_AUTHOR("Chris Zhong <zyw@rock-chips.com>");
+MODULE_AUTHOR("Lin Huang <hl@rock-chips.com>");
 MODULE_DESCRIPTION("Innolux P079ZCA panel driver");
 MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 48bd379aa23d0d6249490137e5ebe7f8aeeb887d Mon Sep 17 00:00:00 2001
From: Lin Huang <hl@rock-chips.com>
Date: Mon, 2 Jul 2018 12:27:19 +0200
Subject: drm/panel: p079zca: Add variable unprepare_delay properties

When panel power down, p079zca need delay between reset and disable
power supply, but p097pfg does not need it. Similarly p097zca needs
a delay after entering panel sleep mode. So add two delay properties,
so we can meet these two panel power down sequence.

Signed-off-by: Lin Huang <hl@rock-chips.com>
[add sleep-mode delay]
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702102721.3546-3-heiko@sntech.de
---
 drivers/gpu/drm/panel/panel-innolux-p079zca.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index 185a55060195..69bee4413aae 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -33,6 +33,8 @@ struct panel_desc {
 	unsigned int lanes;
 	const char * const *supply_names;
 	unsigned int num_supplies;
+	unsigned int sleep_mode_delay;
+	unsigned int power_down_delay;
 };
 
 struct innolux_panel {
@@ -89,10 +91,13 @@ static int innolux_panel_unprepare(struct drm_panel *panel)
 		return err;
 	}
 
+	if (innolux->desc->sleep_mode_delay)
+		msleep(innolux->desc->sleep_mode_delay);
+
 	gpiod_set_value_cansleep(innolux->enable_gpio, 0);
 
-	/* T8: 80ms - 1000ms */
-	msleep(80);
+	if (innolux->desc->power_down_delay)
+		msleep(innolux->desc->power_down_delay);
 
 	err = regulator_bulk_disable(innolux->desc->num_supplies,
 				     innolux->supplies);
@@ -208,6 +213,7 @@ static const struct panel_desc innolux_p079zca_panel_desc = {
 	.lanes = 4,
 	.supply_names = innolux_p079zca_supply_names,
 	.num_supplies = ARRAY_SIZE(innolux_p079zca_supply_names),
+	.power_down_delay = 80, /* T8: 80ms - 1000ms */
 };
 
 static int innolux_panel_get_modes(struct drm_panel *panel)
-- 
cgit v1.2.3


From 731edd4ce5d3fb477c808e2fc16f398c9ff3576b Mon Sep 17 00:00:00 2001
From: Lin Huang <hl@rock-chips.com>
Date: Mon, 2 Jul 2018 12:27:20 +0200
Subject: dt-bindings: Add Innolux P097PFG panel bindings

The Innolux P097PFG panel is 9.7" panel with 1536X2048
resolution, it reuse P079ZCA panel driver, so improve
p079ZCA dt-binding to support P097PFG.

Changes in v2:
- None
Changes in v3:
- None
Changes in v4:
- None
Changes in v5:
- use separate file for binding
- keep power supplies as required

Signed-off-by: Lin Huang <hl@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702102721.3546-4-heiko@sntech.de
---
 .../bindings/display/panel/innolux,p097pfg.txt     | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt

diff --git a/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt b/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt
new file mode 100644
index 000000000000..595d9dfeffd3
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/innolux,p097pfg.txt
@@ -0,0 +1,24 @@
+Innolux P097PFG 9.7" 1536x2048 TFT LCD panel
+
+Required properties:
+- compatible: should be "innolux,p097pfg"
+- reg: DSI virtual channel of the peripheral
+- avdd-supply: phandle of the regulator that provides positive voltage
+- avee-supply: phandle of the regulator that provides negative voltage
+- enable-gpios: panel enable gpio
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Example:
+
+	&mipi_dsi {
+		panel {
+			compatible = "innolux,p079zca";
+			reg = <0>;
+			avdd-supply = <...>;
+			avee-supply = <...>;
+			backlight = <&backlight>;
+			enable-gpios = <&gpio1 13 GPIO_ACTIVE_HIGH>;
+		};
+	};
-- 
cgit v1.2.3


From de04a462fdcee724462bd656c13d461fba5ece51 Mon Sep 17 00:00:00 2001
From: Lin Huang <hl@rock-chips.com>
Date: Mon, 2 Jul 2018 12:27:21 +0200
Subject: drm/panel: p079zca: Support Innolux P097PFG panel

Support Innolux P097PFG 9.7" 1536x2048 TFT LCD panel, it reuse
the Innolux P079ZCA panel driver.

Changes in v2:
- None
Changes in v3:
- None
Changes in v4:
- None
Changes in v5:
- Document source of init-commands
- 4 lanes per DSI interface

Signed-off-by: Lin Huang <hl@rock-chips.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702102721.3546-5-heiko@sntech.de
---
 drivers/gpu/drm/panel/panel-innolux-p079zca.c | 200 +++++++++++++++++++++++++-
 1 file changed, 196 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index 69bee4413aae..424d0bf3c595 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -20,6 +20,15 @@
 
 #include <video/mipi_display.h>
 
+struct panel_init_cmd {
+	size_t len;
+	const char *data;
+};
+
+#define _INIT_CMD(...) { \
+	.len = sizeof((char[]){__VA_ARGS__}), \
+	.data = (char[]){__VA_ARGS__} }
+
 struct panel_desc {
 	const struct drm_display_mode *mode;
 	unsigned int bpc;
@@ -30,6 +39,7 @@ struct panel_desc {
 
 	unsigned long flags;
 	enum mipi_dsi_pixel_format format;
+	const struct panel_init_cmd *init_cmds;
 	unsigned int lanes;
 	const char * const *supply_names;
 	unsigned int num_supplies;
@@ -124,13 +134,43 @@ static int innolux_panel_prepare(struct drm_panel *panel)
 	if (err < 0)
 		return err;
 
-	/* T2: 15ms - 1000ms */
-	usleep_range(15000, 16000);
+	/* p079zca: t2 (20ms), p097pfg: t4 (15ms) */
+	usleep_range(20000, 21000);
 
 	gpiod_set_value_cansleep(innolux->enable_gpio, 1);
 
-	/* T4: 15ms - 1000ms */
-	usleep_range(15000, 16000);
+	/* p079zca: t4, p097pfg: t5 */
+	usleep_range(20000, 21000);
+
+	if (innolux->desc->init_cmds) {
+		const struct panel_init_cmd *cmds =
+					innolux->desc->init_cmds;
+		unsigned int i;
+
+		for (i = 0; cmds[i].len != 0; i++) {
+			const struct panel_init_cmd *cmd = &cmds[i];
+
+			err = mipi_dsi_generic_write(innolux->link, cmd->data,
+						     cmd->len);
+			if (err < 0) {
+				dev_err(panel->dev,
+					"failed to write command %u\n", i);
+				goto poweroff;
+			}
+
+			/*
+			 * Included by random guessing, because without this
+			 * (or at least, some delay), the panel sometimes
+			 * didn't appear to pick up the command sequence.
+			 */
+			err = mipi_dsi_dcs_nop(innolux->link);
+			if (err < 0) {
+				dev_err(panel->dev,
+					"failed to send DCS nop: %d\n", err);
+				goto poweroff;
+			}
+		}
+	}
 
 	err = mipi_dsi_dcs_exit_sleep_mode(innolux->link);
 	if (err < 0) {
@@ -216,6 +256,155 @@ static const struct panel_desc innolux_p079zca_panel_desc = {
 	.power_down_delay = 80, /* T8: 80ms - 1000ms */
 };
 
+static const char * const innolux_p097pfg_supply_names[] = {
+	"avdd",
+	"avee",
+};
+
+static const struct drm_display_mode innolux_p097pfg_mode = {
+	.clock = 229000,
+	.hdisplay = 1536,
+	.hsync_start = 1536 + 100,
+	.hsync_end = 1536 + 100 + 24,
+	.htotal = 1536 + 100 + 24 + 100,
+	.vdisplay = 2048,
+	.vsync_start = 2048 + 100,
+	.vsync_end = 2048 + 100 + 2,
+	.vtotal = 2048 + 100 + 2 + 18,
+	.vrefresh = 60,
+};
+
+/*
+ * Display manufacturer failed to provide init sequencing according to
+ * https://chromium-review.googlesource.com/c/chromiumos/third_party/coreboot/+/892065/
+ * so the init sequence stems from a register dump of a working panel.
+ */
+static const struct panel_init_cmd innolux_p097pfg_init_cmds[] = {
+	/* page 0 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x00),
+	_INIT_CMD(0xB1, 0xE8, 0x11),
+	_INIT_CMD(0xB2, 0x25, 0x02),
+	_INIT_CMD(0xB5, 0x08, 0x00),
+	_INIT_CMD(0xBC, 0x0F, 0x00),
+	_INIT_CMD(0xB8, 0x03, 0x06, 0x00, 0x00),
+	_INIT_CMD(0xBD, 0x01, 0x90, 0x14, 0x14),
+	_INIT_CMD(0x6F, 0x01),
+	_INIT_CMD(0xC0, 0x03),
+	_INIT_CMD(0x6F, 0x02),
+	_INIT_CMD(0xC1, 0x0D),
+	_INIT_CMD(0xD9, 0x01, 0x09, 0x70),
+	_INIT_CMD(0xC5, 0x12, 0x21, 0x00),
+	_INIT_CMD(0xBB, 0x93, 0x93),
+
+	/* page 1 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x01),
+	_INIT_CMD(0xB3, 0x3C, 0x3C),
+	_INIT_CMD(0xB4, 0x0F, 0x0F),
+	_INIT_CMD(0xB9, 0x45, 0x45),
+	_INIT_CMD(0xBA, 0x14, 0x14),
+	_INIT_CMD(0xCA, 0x02),
+	_INIT_CMD(0xCE, 0x04),
+	_INIT_CMD(0xC3, 0x9B, 0x9B),
+	_INIT_CMD(0xD8, 0xC0, 0x03),
+	_INIT_CMD(0xBC, 0x82, 0x01),
+	_INIT_CMD(0xBD, 0x9E, 0x01),
+
+	/* page 2 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x02),
+	_INIT_CMD(0xB0, 0x82),
+	_INIT_CMD(0xD1, 0x00, 0x00, 0x00, 0x3E, 0x00, 0x82, 0x00, 0xA5,
+		  0x00, 0xC1, 0x00, 0xEA, 0x01, 0x0D, 0x01, 0x40),
+	_INIT_CMD(0xD2, 0x01, 0x6A, 0x01, 0xA8, 0x01, 0xDC, 0x02, 0x29,
+		  0x02, 0x67, 0x02, 0x68, 0x02, 0xA8, 0x02, 0xF0),
+	_INIT_CMD(0xD3, 0x03, 0x19, 0x03, 0x49, 0x03, 0x67, 0x03, 0x8C,
+		  0x03, 0xA6, 0x03, 0xC7, 0x03, 0xDE, 0x03, 0xEC),
+	_INIT_CMD(0xD4, 0x03, 0xFF, 0x03, 0xFF),
+	_INIT_CMD(0xE0, 0x00, 0x00, 0x00, 0x86, 0x00, 0xC5, 0x00, 0xE5,
+		  0x00, 0xFF, 0x01, 0x26, 0x01, 0x45, 0x01, 0x75),
+	_INIT_CMD(0xE1, 0x01, 0x9C, 0x01, 0xD5, 0x02, 0x05, 0x02, 0x4D,
+		  0x02, 0x86, 0x02, 0x87, 0x02, 0xC3, 0x03, 0x03),
+	_INIT_CMD(0xE2, 0x03, 0x2A, 0x03, 0x56, 0x03, 0x72, 0x03, 0x94,
+		  0x03, 0xAC, 0x03, 0xCB, 0x03, 0xE0, 0x03, 0xED),
+	_INIT_CMD(0xE3, 0x03, 0xFF, 0x03, 0xFF),
+
+	/* page 3 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x03),
+	_INIT_CMD(0xB0, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xB1, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xB2, 0x00, 0x00, 0x06, 0x04, 0x01, 0x40, 0x85),
+	_INIT_CMD(0xB3, 0x10, 0x07, 0xFC, 0x04, 0x01, 0x40, 0x80),
+	_INIT_CMD(0xB6, 0xF0, 0x08, 0x00, 0x04, 0x00, 0x00, 0x00, 0x01,
+		  0x40, 0x80),
+	_INIT_CMD(0xBA, 0xC5, 0x07, 0x00, 0x04, 0x11, 0x25, 0x8C),
+	_INIT_CMD(0xBB, 0xC5, 0x07, 0x00, 0x03, 0x11, 0x25, 0x8C),
+	_INIT_CMD(0xC0, 0x00, 0x3C, 0x00, 0x00, 0x00, 0x80, 0x80),
+	_INIT_CMD(0xC1, 0x00, 0x3C, 0x00, 0x00, 0x00, 0x80, 0x80),
+	_INIT_CMD(0xC4, 0x00, 0x00),
+	_INIT_CMD(0xEF, 0x41),
+
+	/* page 4 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x04),
+	_INIT_CMD(0xEC, 0x4C),
+
+	/* page 5 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x05),
+	_INIT_CMD(0xB0, 0x13, 0x03, 0x03, 0x01),
+	_INIT_CMD(0xB1, 0x30, 0x00),
+	_INIT_CMD(0xB2, 0x02, 0x02, 0x00),
+	_INIT_CMD(0xB3, 0x82, 0x23, 0x82, 0x9D),
+	_INIT_CMD(0xB4, 0xC5, 0x75, 0x24, 0x57),
+	_INIT_CMD(0xB5, 0x00, 0xD4, 0x72, 0x11, 0x11, 0xAB, 0x0A),
+	_INIT_CMD(0xB6, 0x00, 0x00, 0xD5, 0x72, 0x24, 0x56),
+	_INIT_CMD(0xB7, 0x5C, 0xDC, 0x5C, 0x5C),
+	_INIT_CMD(0xB9, 0x0C, 0x00, 0x00, 0x01, 0x00),
+	_INIT_CMD(0xC0, 0x75, 0x11, 0x11, 0x54, 0x05),
+	_INIT_CMD(0xC6, 0x00, 0x00, 0x00, 0x00),
+	_INIT_CMD(0xD0, 0x00, 0x48, 0x08, 0x00, 0x00),
+	_INIT_CMD(0xD1, 0x00, 0x48, 0x09, 0x00, 0x00),
+
+	/* page 6 */
+	_INIT_CMD(0xF0, 0x55, 0xAA, 0x52, 0x08, 0x06),
+	_INIT_CMD(0xB0, 0x02, 0x32, 0x32, 0x08, 0x2F),
+	_INIT_CMD(0xB1, 0x2E, 0x15, 0x14, 0x13, 0x12),
+	_INIT_CMD(0xB2, 0x11, 0x10, 0x00, 0x3D, 0x3D),
+	_INIT_CMD(0xB3, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xB4, 0x3D, 0x32),
+	_INIT_CMD(0xB5, 0x03, 0x32, 0x32, 0x09, 0x2F),
+	_INIT_CMD(0xB6, 0x2E, 0x1B, 0x1A, 0x19, 0x18),
+	_INIT_CMD(0xB7, 0x17, 0x16, 0x01, 0x3D, 0x3D),
+	_INIT_CMD(0xB8, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xB9, 0x3D, 0x32),
+	_INIT_CMD(0xC0, 0x01, 0x32, 0x32, 0x09, 0x2F),
+	_INIT_CMD(0xC1, 0x2E, 0x1A, 0x1B, 0x16, 0x17),
+	_INIT_CMD(0xC2, 0x18, 0x19, 0x03, 0x3D, 0x3D),
+	_INIT_CMD(0xC3, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xC4, 0x3D, 0x32),
+	_INIT_CMD(0xC5, 0x00, 0x32, 0x32, 0x08, 0x2F),
+	_INIT_CMD(0xC6, 0x2E, 0x14, 0x15, 0x10, 0x11),
+	_INIT_CMD(0xC7, 0x12, 0x13, 0x02, 0x3D, 0x3D),
+	_INIT_CMD(0xC8, 0x3D, 0x3D, 0x3D, 0x3D, 0x3D),
+	_INIT_CMD(0xC9, 0x3D, 0x32),
+
+	{},
+};
+
+static const struct panel_desc innolux_p097pfg_panel_desc = {
+	.mode = &innolux_p097pfg_mode,
+	.bpc = 8,
+	.size = {
+		.width = 147,
+		.height = 196,
+	},
+	.flags = MIPI_DSI_MODE_VIDEO | MIPI_DSI_MODE_VIDEO_SYNC_PULSE |
+		 MIPI_DSI_MODE_LPM,
+	.format = MIPI_DSI_FMT_RGB888,
+	.init_cmds = innolux_p097pfg_init_cmds,
+	.lanes = 4,
+	.supply_names = innolux_p097pfg_supply_names,
+	.num_supplies = ARRAY_SIZE(innolux_p097pfg_supply_names),
+	.sleep_mode_delay = 100, /* T15 */
+};
+
 static int innolux_panel_get_modes(struct drm_panel *panel)
 {
 	struct innolux_panel *innolux = to_innolux_panel(panel);
@@ -254,6 +443,9 @@ static const struct of_device_id innolux_of_match[] = {
 	{ .compatible = "innolux,p079zca",
 	  .data = &innolux_p079zca_panel_desc
 	},
+	{ .compatible = "innolux,p097pfg",
+	  .data = &innolux_p097pfg_panel_desc
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, innolux_of_match);
-- 
cgit v1.2.3


From 2bb7a39c1581a22efd6a6f21bbce9d5575ce9224 Mon Sep 17 00:00:00 2001
From: Nickey Yang <nickey.yang@rock-chips.com>
Date: Mon, 2 Jul 2018 12:32:27 +0200
Subject: dt-bindings: Add vendor prefix for kingdisplay

Kingdisplay Technology Co., Ltd, established in
China Shenzhen in 2006, is a national high-tech
enterprise specializing in the R&D, manufacturing
and marketing of TFT-LCM and touch panel.

Signed-off-by: Nickey Yang <nickey.yang@rock-chips.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702103229.3952-2-heiko@sntech.de
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 5fd6c539e898..2afaa633ffc8 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -191,6 +191,7 @@ keymile	Keymile GmbH
 khadas	Khadas
 kiebackpeter    Kieback & Peter GmbH
 kinetic Kinetic Technologies
+kingdisplay	King & Display Technology Co., Ltd.
 kingnovel	Kingnovel Technology Co., Ltd.
 koe	Kaohsiung Opto-Electronics Inc.
 kosagi	Sutajio Ko-Usagi PTE Ltd.
-- 
cgit v1.2.3


From ebc950fdff6d5f9250cd5a5a348af97f7d8508df Mon Sep 17 00:00:00 2001
From: Nickey Yang <nickey.yang@rock-chips.com>
Date: Mon, 2 Jul 2018 12:32:28 +0200
Subject: dt-bindings: Add KINGDISPLAY KD097D04 panel bindings

The KINGDISPLAY KD097D04 is a 9.7" panel with a 1536x2048
resolution and connected to DSI using 8 lanes.

Signed-off-by: Nickey Yang <nickey.yang@rock-chips.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180702103229.3952-3-heiko@sntech.de
---
 .../display/panel/kingdisplay,kd097d04.txt         | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt

diff --git a/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt
new file mode 100644
index 000000000000..164a5fa236da
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/kingdisplay,kd097d04.txt
@@ -0,0 +1,22 @@
+Kingdisplay KD097D04 9.7" 1536x2048 TFT LCD panel
+
+Required properties:
+- compatible: should be "kingdisplay,kd097d04"
+- reg: DSI virtual channel of the peripheral
+- power-supply: phandle of the regulator that provides the supply voltage
+- enable-gpios: panel enable gpio
+
+Optional properties:
+- backlight: phandle of the backlight device attached to the panel
+
+Example:
+
+	&mipi_dsi {
+		panel {
+			compatible = "kingdisplay,kd097d04";
+			reg = <0>;
+			power-supply = <...>;
+			backlight = <&backlight>;
+			enable-gpios = <&gpio1 13 GPIO_ACTIVE_HIGH>;
+		};
+	};
-- 
cgit v1.2.3


From cd0e0ca69109d025b1a1b6609f70682db62138b0 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 4 Jul 2018 12:38:09 +0300
Subject: drm/panel: type promotion bug in s6e8aa0_read_mtp_id()

The ARRAY_SIZE() macro is type size_t.  If s6e8aa0_dcs_read() returns a
negative error code, then "ret < ARRAY_SIZE(id)" is false because the
negative error code is type promoted to a high positive value.

Fixes: 02051ca06371 ("drm/panel: add S6E8AA0 driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Andrzej Hajda <a.hajda@samsung.com>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180704093807.s3lqsb2v6dg2k43d@kili.mountain
---
 drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
index a188a3959f1a..6ad827b93ae1 100644
--- a/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
+++ b/drivers/gpu/drm/panel/panel-samsung-s6e8aa0.c
@@ -823,7 +823,7 @@ static void s6e8aa0_read_mtp_id(struct s6e8aa0 *ctx)
 	int ret, i;
 
 	ret = s6e8aa0_dcs_read(ctx, 0xd1, id, ARRAY_SIZE(id));
-	if (ret < ARRAY_SIZE(id) || id[0] == 0x00) {
+	if (ret < 0 || ret < ARRAY_SIZE(id) || id[0] == 0x00) {
 		dev_err(ctx->dev, "read id failed\n");
 		ctx->error = -EIO;
 		return;
-- 
cgit v1.2.3


From b6d83fccd877221416658fbdb59ba4d1628ba800 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Tue, 10 Jul 2018 12:51:38 +0200
Subject: drm/panel: p079zca: Use of_device_get_match_data()

Use this helper to get rid of some extra boilerplate code.

Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710110127.12315-1-thierry.reding@gmail.com
---
 drivers/gpu/drm/panel/panel-innolux-p079zca.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-innolux-p079zca.c b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
index 424d0bf3c595..72edb334d997 100644
--- a/drivers/gpu/drm/panel/panel-innolux-p079zca.c
+++ b/drivers/gpu/drm/panel/panel-innolux-p079zca.c
@@ -11,6 +11,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/regulator/consumer.h>
 
 #include <drm/drmP.h>
@@ -512,14 +513,9 @@ static void innolux_panel_del(struct innolux_panel *innolux)
 static int innolux_panel_probe(struct mipi_dsi_device *dsi)
 {
 	const struct panel_desc *desc;
-	const struct of_device_id *id;
 	int err;
 
-	id = of_match_node(innolux_of_match, dsi->dev.of_node);
-	if (!id)
-		return -ENODEV;
-
-	desc = id->data;
+	desc = of_device_get_match_data(&dsi->dev);
 	dsi->mode_flags = desc->flags;
 	dsi->format = desc->format;
 	dsi->lanes = desc->lanes;
-- 
cgit v1.2.3


From 8d3e994241e6bcc7ead2b918c4f15b7683afa90a Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 10 Jul 2018 09:57:58 +0100
Subject: arm_pmu: Clean up maximum period handling

Each PMU defines their max_period of the counter as the maximum
value that can be counted. Since all the PMU backends support
32bit counters by default, let us remove the redundant field.

No functional changes.

Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/kernel/perf_event_v6.c     |  2 --
 arch/arm/kernel/perf_event_v7.c     |  1 -
 arch/arm/kernel/perf_event_xscale.c |  2 --
 arch/arm64/kernel/perf_event.c      |  1 -
 drivers/perf/arm_pmu.c              | 16 ++++++++++++----
 include/linux/perf/arm_pmu.h        |  1 -
 6 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index be42c4f66a40..f64a6bfebcec 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -495,7 +495,6 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6_map_event;
 	cpu_pmu->num_events	= 3;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 }
 
 static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu)
@@ -546,7 +545,6 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6mpcore_map_event;
 	cpu_pmu->num_events	= 3;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 
 	return 0;
 }
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 5a5116794440..2cf1ca2925c8 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1170,7 +1170,6 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start		= armv7pmu_start;
 	cpu_pmu->stop		= armv7pmu_stop;
 	cpu_pmu->reset		= armv7pmu_reset;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 };
 
 static void armv7_read_num_pmnc_events(void *info)
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 88d1a76f5367..c4f029458b52 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -374,7 +374,6 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->stop		= xscale1pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
 	cpu_pmu->num_events	= 3;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 
 	return 0;
 }
@@ -743,7 +742,6 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->stop		= xscale2pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
 	cpu_pmu->num_events	= 5;
-	cpu_pmu->max_period	= (1LLU << 32) - 1;
 
 	return 0;
 }
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 33147aacdafd..678ecffd3724 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -960,7 +960,6 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->start			= armv8pmu_start,
 	cpu_pmu->stop			= armv8pmu_stop,
 	cpu_pmu->reset			= armv8pmu_reset,
-	cpu_pmu->max_period		= (1LLU << 32) - 1,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 
 	return 0;
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index a6347d487635..6ddc00da5373 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -28,6 +28,11 @@
 static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
 static DEFINE_PER_CPU(int, cpu_irq);
 
+static inline u64 arm_pmu_max_period(void)
+{
+	return (1ULL << 32) - 1;
+}
+
 static int
 armpmu_map_cache_event(const unsigned (*cache_map)
 				      [PERF_COUNT_HW_CACHE_MAX]
@@ -114,8 +119,10 @@ int armpmu_event_set_period(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
+	u64 max_period;
 	int ret = 0;
 
+	max_period = arm_pmu_max_period();
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
@@ -136,8 +143,8 @@ int armpmu_event_set_period(struct perf_event *event)
 	 * effect we are reducing max_period to account for
 	 * interrupt latency (and we are being very conservative).
 	 */
-	if (left > (armpmu->max_period >> 1))
-		left = armpmu->max_period >> 1;
+	if (left > (max_period >> 1))
+		left = (max_period >> 1);
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
@@ -153,6 +160,7 @@ u64 armpmu_event_update(struct perf_event *event)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 delta, prev_raw_count, new_raw_count;
+	u64 max_period = arm_pmu_max_period();
 
 again:
 	prev_raw_count = local64_read(&hwc->prev_count);
@@ -162,7 +170,7 @@ again:
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
-	delta = (new_raw_count - prev_raw_count) & armpmu->max_period;
+	delta = (new_raw_count - prev_raw_count) & max_period;
 
 	local64_add(delta, &event->count);
 	local64_sub(delta, &hwc->period_left);
@@ -402,7 +410,7 @@ __hw_perf_event_init(struct perf_event *event)
 		 * is far less likely to overtake the previous one unless
 		 * you have some serious IRQ latency issues.
 		 */
-		hwc->sample_period  = armpmu->max_period >> 1;
+		hwc->sample_period  = arm_pmu_max_period() >> 1;
 		hwc->last_period    = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index ad5444491975..12c30a22fc8d 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -94,7 +94,6 @@ struct arm_pmu {
 	void		(*reset)(void *);
 	int		(*map_event)(struct perf_event *event);
 	int		num_events;
-	u64		max_period;
 	bool		secure_access; /* 32-bit ARM only */
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS 0x40
 	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
-- 
cgit v1.2.3


From 3a95200d3f89afd8b67f39d88d36cc7ec96ce385 Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 10 Jul 2018 09:57:59 +0100
Subject: arm_pmu: Change API to support 64bit counter values

Convert the {read/write}_counter APIs to handle 64bit values
to enable supporting chained event counters. The backends still
use 32bit values and we pass them 32bit values only. So in effect
there are no functional changes.

Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/kernel/perf_event_v6.c     | 4 ++--
 arch/arm/kernel/perf_event_v7.c     | 4 ++--
 arch/arm/kernel/perf_event_xscale.c | 8 ++++----
 arch/arm64/kernel/perf_event.c      | 9 ++++-----
 include/linux/perf/arm_pmu.h        | 4 ++--
 5 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index f64a6bfebcec..0729f9841ef4 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -233,7 +233,7 @@ armv6_pmcr_counter_has_overflowed(unsigned long pmcr,
 	return ret;
 }
 
-static inline u32 armv6pmu_read_counter(struct perf_event *event)
+static inline u64 armv6pmu_read_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -251,7 +251,7 @@ static inline u32 armv6pmu_read_counter(struct perf_event *event)
 	return value;
 }
 
-static inline void armv6pmu_write_counter(struct perf_event *event, u32 value)
+static inline void armv6pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 2cf1ca2925c8..973043dd6187 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -743,7 +743,7 @@ static inline void armv7_pmnc_select_counter(int idx)
 	isb();
 }
 
-static inline u32 armv7pmu_read_counter(struct perf_event *event)
+static inline u64 armv7pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -763,7 +763,7 @@ static inline u32 armv7pmu_read_counter(struct perf_event *event)
 	return value;
 }
 
-static inline void armv7pmu_write_counter(struct perf_event *event, u32 value)
+static inline void armv7pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index c4f029458b52..942230fe0426 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -316,7 +316,7 @@ static void xscale1pmu_stop(struct arm_pmu *cpu_pmu)
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static inline u32 xscale1pmu_read_counter(struct perf_event *event)
+static inline u64 xscale1pmu_read_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -337,7 +337,7 @@ static inline u32 xscale1pmu_read_counter(struct perf_event *event)
 	return val;
 }
 
-static inline void xscale1pmu_write_counter(struct perf_event *event, u32 val)
+static inline void xscale1pmu_write_counter(struct perf_event *event, u64 val)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -678,7 +678,7 @@ static void xscale2pmu_stop(struct arm_pmu *cpu_pmu)
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
-static inline u32 xscale2pmu_read_counter(struct perf_event *event)
+static inline u64 xscale2pmu_read_counter(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
@@ -705,7 +705,7 @@ static inline u32 xscale2pmu_read_counter(struct perf_event *event)
 	return val;
 }
 
-static inline void xscale2pmu_write_counter(struct perf_event *event, u32 val)
+static inline void xscale2pmu_write_counter(struct perf_event *event, u64 val)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	int counter = hwc->idx;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 678ecffd3724..66a2ffdca6dd 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -512,7 +512,7 @@ static inline int armv8pmu_select_counter(int idx)
 	return idx;
 }
 
-static inline u32 armv8pmu_read_counter(struct perf_event *event)
+static inline u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -530,7 +530,7 @@ static inline u32 armv8pmu_read_counter(struct perf_event *event)
 	return value;
 }
 
-static inline void armv8pmu_write_counter(struct perf_event *event, u32 value)
+static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
@@ -545,9 +545,8 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u32 value)
 		 * count using the lower 32bits and we want an interrupt when
 		 * it overflows.
 		 */
-		u64 value64 = 0xffffffff00000000ULL | value;
-
-		write_sysreg(value64, pmccntr_el0);
+		value |= 0xffffffff00000000ULL;
+		write_sysreg(value, pmccntr_el0);
 	} else if (armv8pmu_select_counter(idx) == idx)
 		write_sysreg(value, pmxevcntr_el0);
 }
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 12c30a22fc8d..f7126a21df30 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -87,8 +87,8 @@ struct arm_pmu {
 					 struct perf_event *event);
 	int		(*set_event_filter)(struct hw_perf_event *evt,
 					    struct perf_event_attr *attr);
-	u32		(*read_counter)(struct perf_event *event);
-	void		(*write_counter)(struct perf_event *event, u32 val);
+	u64		(*read_counter)(struct perf_event *event);
+	void		(*write_counter)(struct perf_event *event, u64 val);
 	void		(*start)(struct arm_pmu *);
 	void		(*stop)(struct arm_pmu *);
 	void		(*reset)(void *);
-- 
cgit v1.2.3


From e2da97d328d4951d25f6634eda7213f7257417b6 Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 10 Jul 2018 09:58:00 +0100
Subject: arm_pmu: Add support for 64bit event counters

Each PMU has a set of 32bit event counters. But in some
special cases, the events could be counted using counters
which are effectively 64bit wide.

e.g, Arm V8 PMUv3 has a 64 bit cycle counter which can count
only the CPU cycles. Also, the PMU can chain the event counters
to effectively count as a 64bit counter.

Add support for tracking the events that uses 64bit counters.
This only affects the periods set for each counter in the core
driver.

Cc: Will Deacon <will.deacon@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/perf/arm_pmu.c       | 16 ++++++++++------
 include/linux/perf/arm_pmu.h |  6 ++++++
 2 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 6ddc00da5373..8cad6b535a2c 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -28,9 +28,12 @@
 static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
 static DEFINE_PER_CPU(int, cpu_irq);
 
-static inline u64 arm_pmu_max_period(void)
+static inline u64 arm_pmu_event_max_period(struct perf_event *event)
 {
-	return (1ULL << 32) - 1;
+	if (event->hw.flags & ARMPMU_EVT_64BIT)
+		return GENMASK_ULL(63, 0);
+	else
+		return GENMASK_ULL(31, 0);
 }
 
 static int
@@ -122,7 +125,7 @@ int armpmu_event_set_period(struct perf_event *event)
 	u64 max_period;
 	int ret = 0;
 
-	max_period = arm_pmu_max_period();
+	max_period = arm_pmu_event_max_period(event);
 	if (unlikely(left <= -period)) {
 		left = period;
 		local64_set(&hwc->period_left, left);
@@ -148,7 +151,7 @@ int armpmu_event_set_period(struct perf_event *event)
 
 	local64_set(&hwc->prev_count, (u64)-left);
 
-	armpmu->write_counter(event, (u64)(-left) & 0xffffffff);
+	armpmu->write_counter(event, (u64)(-left) & max_period);
 
 	perf_event_update_userpage(event);
 
@@ -160,7 +163,7 @@ u64 armpmu_event_update(struct perf_event *event)
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	u64 delta, prev_raw_count, new_raw_count;
-	u64 max_period = arm_pmu_max_period();
+	u64 max_period = arm_pmu_event_max_period(event);
 
 again:
 	prev_raw_count = local64_read(&hwc->prev_count);
@@ -368,6 +371,7 @@ __hw_perf_event_init(struct perf_event *event)
 	struct hw_perf_event *hwc = &event->hw;
 	int mapping;
 
+	hwc->flags = 0;
 	mapping = armpmu->map_event(event);
 
 	if (mapping < 0) {
@@ -410,7 +414,7 @@ __hw_perf_event_init(struct perf_event *event)
 		 * is far less likely to overtake the previous one unless
 		 * you have some serious IRQ latency issues.
 		 */
-		hwc->sample_period  = arm_pmu_max_period() >> 1;
+		hwc->sample_period  = arm_pmu_event_max_period(event) >> 1;
 		hwc->last_period    = hwc->sample_period;
 		local64_set(&hwc->period_left, hwc->sample_period);
 	}
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index f7126a21df30..10f92e1d8e7b 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -25,6 +25,12 @@
  */
 #define ARMPMU_MAX_HWEVENTS		32
 
+/*
+ * ARM PMU hw_event flags
+ */
+/* Event uses a 64bit counter */
+#define ARMPMU_EVT_64BIT		1
+
 #define HW_OP_UNSUPPORTED		0xFFFF
 #define C(_x)				PERF_COUNT_HW_CACHE_##_x
 #define CACHE_OP_UNSUPPORTED		0xFFFF
-- 
cgit v1.2.3


From 7dfc8db1d117ae08c649266d5459ac8b10800d6e Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 10 Jul 2018 09:58:01 +0100
Subject: arm_pmu: Tidy up clear_event_idx call backs

The armpmu uses get_event_idx callback to allocate an event
counter for a given event, which marks the selected counter
as "used". Now, when we delete the counter, the arm_pmu goes
ahead and clears the "used" bit and then invokes the "clear_event_idx"
call back, which kind of splits the job between the core code
and the backend. To keep things tidy, mandate the implementation
of clear_event_idx() and add it for exisiting backends.
This will be useful for adding the chained event support, where
we leave the event idx maintenance to the backend.

Also, when an event is removed from the PMU, reset the hw.idx
to indicate that a counter is not allocated for this event,
to help the backends do better checks. This will be also used
for the chain counter support.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Julien Thierry <julien.thierry@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm/kernel/perf_event_v6.c     | 8 ++++++++
 arch/arm/kernel/perf_event_v7.c     | 9 +++++++++
 arch/arm/kernel/perf_event_xscale.c | 8 ++++++++
 arch/arm64/kernel/perf_event.c      | 7 +++++++
 drivers/perf/arm_pmu.c              | 7 +++----
 5 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index 0729f9841ef4..1ae99deeec54 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -411,6 +411,12 @@ armv6pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	}
 }
 
+static void armv6pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
 static void armv6pmu_disable_event(struct perf_event *event)
 {
 	unsigned long val, mask, evt, flags;
@@ -491,6 +497,7 @@ static void armv6pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= armv6pmu_read_counter;
 	cpu_pmu->write_counter	= armv6pmu_write_counter;
 	cpu_pmu->get_event_idx	= armv6pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx;
 	cpu_pmu->start		= armv6pmu_start;
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6_map_event;
@@ -541,6 +548,7 @@ static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= armv6pmu_read_counter;
 	cpu_pmu->write_counter	= armv6pmu_write_counter;
 	cpu_pmu->get_event_idx	= armv6pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx;
 	cpu_pmu->start		= armv6pmu_start;
 	cpu_pmu->stop		= armv6pmu_stop;
 	cpu_pmu->map_event	= armv6mpcore_map_event;
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 973043dd6187..a4fb0f8b8f84 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -1058,6 +1058,12 @@ static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	return -EAGAIN;
 }
 
+static void armv7pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
 /*
  * Add an event filter to a given event. This will only work for PMUv2 PMUs.
  */
@@ -1167,6 +1173,7 @@ static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= armv7pmu_read_counter;
 	cpu_pmu->write_counter	= armv7pmu_write_counter;
 	cpu_pmu->get_event_idx	= armv7pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = armv7pmu_clear_event_idx;
 	cpu_pmu->start		= armv7pmu_start;
 	cpu_pmu->stop		= armv7pmu_stop;
 	cpu_pmu->reset		= armv7pmu_reset;
@@ -1637,6 +1644,7 @@ static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 	bool venum_event = EVENT_VENUM(hwc->config_base);
 	bool krait_event = EVENT_CPU(hwc->config_base);
 
+	armv7pmu_clear_event_idx(cpuc, event);
 	if (venum_event || krait_event) {
 		bit = krait_event_to_bit(event, region, group);
 		clear_bit(bit, cpuc->used_mask);
@@ -1966,6 +1974,7 @@ static void scorpion_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
 	bool venum_event = EVENT_VENUM(hwc->config_base);
 	bool scorpion_event = EVENT_CPU(hwc->config_base);
 
+	armv7pmu_clear_event_idx(cpuc, event);
 	if (venum_event || scorpion_event) {
 		bit = scorpion_event_to_bit(event, region, group);
 		clear_bit(bit, cpuc->used_mask);
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 942230fe0426..f6cdcacfb96d 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -292,6 +292,12 @@ xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	}
 }
 
+static void xscalepmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				     struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
 static void xscale1pmu_start(struct arm_pmu *cpu_pmu)
 {
 	unsigned long flags, val;
@@ -370,6 +376,7 @@ static int xscale1pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= xscale1pmu_read_counter;
 	cpu_pmu->write_counter	= xscale1pmu_write_counter;
 	cpu_pmu->get_event_idx	= xscale1pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx;
 	cpu_pmu->start		= xscale1pmu_start;
 	cpu_pmu->stop		= xscale1pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
@@ -738,6 +745,7 @@ static int xscale2pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter	= xscale2pmu_read_counter;
 	cpu_pmu->write_counter	= xscale2pmu_write_counter;
 	cpu_pmu->get_event_idx	= xscale2pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx;
 	cpu_pmu->start		= xscale2pmu_start;
 	cpu_pmu->stop		= xscale2pmu_stop;
 	cpu_pmu->map_event	= xscale_map_event;
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index 66a2ffdca6dd..ac66851d4b13 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -778,6 +778,12 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	return -EAGAIN;
 }
 
+static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				  struct perf_event *event)
+{
+	clear_bit(event->hw.idx, cpuc->used_mask);
+}
+
 /*
  * Add an event filter to a given event. This will only work for PMUv2 PMUs.
  */
@@ -956,6 +962,7 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->read_counter		= armv8pmu_read_counter,
 	cpu_pmu->write_counter		= armv8pmu_write_counter,
 	cpu_pmu->get_event_idx		= armv8pmu_get_event_idx,
+	cpu_pmu->clear_event_idx	= armv8pmu_clear_event_idx,
 	cpu_pmu->start			= armv8pmu_start,
 	cpu_pmu->stop			= armv8pmu_stop,
 	cpu_pmu->reset			= armv8pmu_reset,
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 8cad6b535a2c..a28881058f18 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -238,11 +238,10 @@ armpmu_del(struct perf_event *event, int flags)
 
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
-	clear_bit(idx, hw_events->used_mask);
-	if (armpmu->clear_event_idx)
-		armpmu->clear_event_idx(hw_events, event);
-
+	armpmu->clear_event_idx(hw_events, event);
 	perf_event_update_userpage(event);
+	/* Clear the allocated counter */
+	hwc->idx = -1;
 }
 
 static int
-- 
cgit v1.2.3


From 0c55d19c1659d3fc38dcecca8bdaf6eabda39a9d Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 10 Jul 2018 09:58:02 +0100
Subject: arm64: perf: Clean up armv8pmu_select_counter

armv8pmu_select_counter always returns the passed idx. So
let us make that void and get rid of the pointless checks.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 29 +++++++++++++++++++----------
 1 file changed, 19 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index ac66851d4b13..bc014af59fb3 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -503,13 +503,17 @@ static inline int armv8pmu_counter_has_overflowed(u32 pmnc, int idx)
 	return pmnc & BIT(ARMV8_IDX_TO_COUNTER(idx));
 }
 
-static inline int armv8pmu_select_counter(int idx)
+static inline void armv8pmu_select_counter(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
 	write_sysreg(counter, pmselr_el0);
 	isb();
+}
 
-	return idx;
+static inline u32 armv8pmu_read_evcntr(int idx)
+{
+	armv8pmu_select_counter(idx);
+	return read_sysreg(pmxevcntr_el0);
 }
 
 static inline u64 armv8pmu_read_counter(struct perf_event *event)
@@ -524,12 +528,18 @@ static inline u64 armv8pmu_read_counter(struct perf_event *event)
 			smp_processor_id(), idx);
 	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
 		value = read_sysreg(pmccntr_el0);
-	else if (armv8pmu_select_counter(idx) == idx)
-		value = read_sysreg(pmxevcntr_el0);
+	else
+		value = armv8pmu_read_evcntr(idx);
 
 	return value;
 }
 
+static inline void armv8pmu_write_evcntr(int idx, u32 value)
+{
+	armv8pmu_select_counter(idx);
+	write_sysreg(value, pmxevcntr_el0);
+}
+
 static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
@@ -547,16 +557,15 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
 		 */
 		value |= 0xffffffff00000000ULL;
 		write_sysreg(value, pmccntr_el0);
-	} else if (armv8pmu_select_counter(idx) == idx)
-		write_sysreg(value, pmxevcntr_el0);
+	} else
+		armv8pmu_write_evcntr(idx, value);
 }
 
 static inline void armv8pmu_write_evtype(int idx, u32 val)
 {
-	if (armv8pmu_select_counter(idx) == idx) {
-		val &= ARMV8_PMU_EVTYPE_MASK;
-		write_sysreg(val, pmxevtyper_el0);
-	}
+	armv8pmu_select_counter(idx);
+	val &= ARMV8_PMU_EVTYPE_MASK;
+	write_sysreg(val, pmxevtyper_el0);
 }
 
 static inline int armv8pmu_enable_counter(int idx)
-- 
cgit v1.2.3


From 3cce50dfec4a5b0414c974190940f47dd32c6dee Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 10 Jul 2018 09:58:03 +0100
Subject: arm64: perf: Disable PMU while processing counter overflows

The arm64 PMU updates the event counters and reprograms the
counters in the overflow IRQ handler without disabling the
PMU. This could potentially cause skews in for group counters,
where the overflowed counters may potentially loose some event
counts, while they are reprogrammed. To prevent this, disable
the PMU while we process the counter overflows and enable it
right back when we are done.

This patch also moves the PMU stop/start routines to avoid a
forward declaration.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 50 +++++++++++++++++++++++-------------------
 1 file changed, 28 insertions(+), 22 deletions(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index bc014af59fb3..b414d81b80ca 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -678,6 +678,28 @@ static void armv8pmu_disable_event(struct perf_event *event)
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
 
+static void armv8pmu_start(struct arm_pmu *cpu_pmu)
+{
+	unsigned long flags;
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+	/* Enable all counters */
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
+{
+	unsigned long flags;
+	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
+
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+	/* Disable all counters */
+	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
 static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	u32 pmovsr;
@@ -702,6 +724,11 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	 */
 	regs = get_irq_regs();
 
+	/*
+	 * Stop the PMU while processing the counter overflows
+	 * to prevent skews in group events.
+	 */
+	armv8pmu_stop(cpu_pmu);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
@@ -726,6 +753,7 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 		if (perf_event_overflow(event, &data, regs))
 			cpu_pmu->disable(event);
 	}
+	armv8pmu_start(cpu_pmu);
 
 	/*
 	 * Handle the pending perf events.
@@ -739,28 +767,6 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	return IRQ_HANDLED;
 }
 
-static void armv8pmu_start(struct arm_pmu *cpu_pmu)
-{
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
-	/* Enable all counters */
-	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
-}
-
-static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
-{
-	unsigned long flags;
-	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-
-	raw_spin_lock_irqsave(&events->pmu_lock, flags);
-	/* Disable all counters */
-	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
-	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
-}
-
 static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				  struct perf_event *event)
 {
-- 
cgit v1.2.3


From c13207905340d85eaddd85b6d2868218f324b180 Mon Sep 17 00:00:00 2001
From: Suzuki K Poulose <suzuki.poulose@arm.com>
Date: Tue, 10 Jul 2018 09:58:04 +0100
Subject: arm64: perf: Add support for chaining event counters

Add support for 64bit event by using chained event counters
and 64bit cycle counters.

PMUv3 allows chaining a pair of adjacent 32-bit counters, effectively
forming a 64-bit counter. The low/even counter is programmed to count
the event of interest, and the high/odd counter is programmed to count
the CHAIN event, taken when the low/even counter overflows.

For CPU cycles, when 64bit mode is requested, the cycle counter
is used in 64bit mode. If the cycle counter is not available,
falls back to chaining.

Cc: Will Deacon <will.deacon@arm.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 185 +++++++++++++++++++++++++++++++++++------
 drivers/perf/arm_pmu.c         |   9 +-
 2 files changed, 160 insertions(+), 34 deletions(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index b414d81b80ca..dfff5ed5c625 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -446,9 +446,16 @@ static struct attribute_group armv8_pmuv3_events_attr_group = {
 };
 
 PMU_FORMAT_ATTR(event, "config:0-15");
+PMU_FORMAT_ATTR(long, "config1:0");
+
+static inline bool armv8pmu_event_is_64bit(struct perf_event *event)
+{
+	return event->attr.config1 & 0x1;
+}
 
 static struct attribute *armv8_pmuv3_format_attrs[] = {
 	&format_attr_event.attr,
+	&format_attr_long.attr,
 	NULL,
 };
 
@@ -465,6 +472,21 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 #define	ARMV8_IDX_COUNTER_LAST(cpu_pmu) \
 	(ARMV8_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1)
 
+/*
+ * We must chain two programmable counters for 64 bit events,
+ * except when we have allocated the 64bit cycle counter (for CPU
+ * cycles event). This must be called only when the event has
+ * a counter allocated.
+ */
+static inline bool armv8pmu_event_is_chained(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	return !WARN_ON(idx < 0) &&
+	       armv8pmu_event_is_64bit(event) &&
+	       (idx != ARMV8_IDX_CYCLE_COUNTER);
+}
+
 /*
  * ARMv8 low level PMU access
  */
@@ -516,12 +538,23 @@ static inline u32 armv8pmu_read_evcntr(int idx)
 	return read_sysreg(pmxevcntr_el0);
 }
 
+static inline u64 armv8pmu_read_hw_counter(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+	u64 val = 0;
+
+	val = armv8pmu_read_evcntr(idx);
+	if (armv8pmu_event_is_chained(event))
+		val = (val << 32) | armv8pmu_read_evcntr(idx - 1);
+	return val;
+}
+
 static inline u64 armv8pmu_read_counter(struct perf_event *event)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx;
-	u32 value = 0;
+	u64 value = 0;
 
 	if (!armv8pmu_counter_valid(cpu_pmu, idx))
 		pr_err("CPU%u reading wrong counter %d\n",
@@ -529,7 +562,7 @@ static inline u64 armv8pmu_read_counter(struct perf_event *event)
 	else if (idx == ARMV8_IDX_CYCLE_COUNTER)
 		value = read_sysreg(pmccntr_el0);
 	else
-		value = armv8pmu_read_evcntr(idx);
+		value = armv8pmu_read_hw_counter(event);
 
 	return value;
 }
@@ -540,6 +573,19 @@ static inline void armv8pmu_write_evcntr(int idx, u32 value)
 	write_sysreg(value, pmxevcntr_el0);
 }
 
+static inline void armv8pmu_write_hw_counter(struct perf_event *event,
+					     u64 value)
+{
+	int idx = event->hw.idx;
+
+	if (armv8pmu_event_is_chained(event)) {
+		armv8pmu_write_evcntr(idx, upper_32_bits(value));
+		armv8pmu_write_evcntr(idx - 1, lower_32_bits(value));
+	} else {
+		armv8pmu_write_evcntr(idx, value);
+	}
+}
+
 static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
 {
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
@@ -551,14 +597,16 @@ static inline void armv8pmu_write_counter(struct perf_event *event, u64 value)
 			smp_processor_id(), idx);
 	else if (idx == ARMV8_IDX_CYCLE_COUNTER) {
 		/*
-		 * Set the upper 32bits as this is a 64bit counter but we only
-		 * count using the lower 32bits and we want an interrupt when
-		 * it overflows.
+		 * The cycles counter is really a 64-bit counter.
+		 * When treating it as a 32-bit counter, we only count
+		 * the lower 32 bits, and set the upper 32-bits so that
+		 * we get an interrupt upon 32-bit overflow.
 		 */
-		value |= 0xffffffff00000000ULL;
+		if (!armv8pmu_event_is_64bit(event))
+			value |= 0xffffffff00000000ULL;
 		write_sysreg(value, pmccntr_el0);
 	} else
-		armv8pmu_write_evcntr(idx, value);
+		armv8pmu_write_hw_counter(event, value);
 }
 
 static inline void armv8pmu_write_evtype(int idx, u32 val)
@@ -568,6 +616,27 @@ static inline void armv8pmu_write_evtype(int idx, u32 val)
 	write_sysreg(val, pmxevtyper_el0);
 }
 
+static inline void armv8pmu_write_event_type(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	/*
+	 * For chained events, the low counter is programmed to count
+	 * the event of interest and the high counter is programmed
+	 * with CHAIN event code with filters set to count at all ELs.
+	 */
+	if (armv8pmu_event_is_chained(event)) {
+		u32 chain_evt = ARMV8_PMUV3_PERFCTR_CHAIN |
+				ARMV8_PMU_INCLUDE_EL2;
+
+		armv8pmu_write_evtype(idx - 1, hwc->config_base);
+		armv8pmu_write_evtype(idx, chain_evt);
+	} else {
+		armv8pmu_write_evtype(idx, hwc->config_base);
+	}
+}
+
 static inline int armv8pmu_enable_counter(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
@@ -575,6 +644,16 @@ static inline int armv8pmu_enable_counter(int idx)
 	return idx;
 }
 
+static inline void armv8pmu_enable_event_counter(struct perf_event *event)
+{
+	int idx = event->hw.idx;
+
+	armv8pmu_enable_counter(idx);
+	if (armv8pmu_event_is_chained(event))
+		armv8pmu_enable_counter(idx - 1);
+	isb();
+}
+
 static inline int armv8pmu_disable_counter(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
@@ -582,6 +661,16 @@ static inline int armv8pmu_disable_counter(int idx)
 	return idx;
 }
 
+static inline void armv8pmu_disable_event_counter(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+
+	if (armv8pmu_event_is_chained(event))
+		armv8pmu_disable_counter(idx - 1);
+	armv8pmu_disable_counter(idx);
+}
+
 static inline int armv8pmu_enable_intens(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
@@ -589,6 +678,11 @@ static inline int armv8pmu_enable_intens(int idx)
 	return idx;
 }
 
+static inline int armv8pmu_enable_event_irq(struct perf_event *event)
+{
+	return armv8pmu_enable_intens(event->hw.idx);
+}
+
 static inline int armv8pmu_disable_intens(int idx)
 {
 	u32 counter = ARMV8_IDX_TO_COUNTER(idx);
@@ -601,6 +695,11 @@ static inline int armv8pmu_disable_intens(int idx)
 	return idx;
 }
 
+static inline int armv8pmu_disable_event_irq(struct perf_event *event)
+{
+	return armv8pmu_disable_intens(event->hw.idx);
+}
+
 static inline u32 armv8pmu_getreset_flags(void)
 {
 	u32 value;
@@ -618,10 +717,8 @@ static inline u32 armv8pmu_getreset_flags(void)
 static void armv8pmu_enable_event(struct perf_event *event)
 {
 	unsigned long flags;
-	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-	int idx = hwc->idx;
 
 	/*
 	 * Enable counter and interrupt, and set the counter to count
@@ -632,22 +729,22 @@ static void armv8pmu_enable_event(struct perf_event *event)
 	/*
 	 * Disable counter
 	 */
-	armv8pmu_disable_counter(idx);
+	armv8pmu_disable_event_counter(event);
 
 	/*
 	 * Set event (if destined for PMNx counters).
 	 */
-	armv8pmu_write_evtype(idx, hwc->config_base);
+	armv8pmu_write_event_type(event);
 
 	/*
 	 * Enable interrupt for this counter
 	 */
-	armv8pmu_enable_intens(idx);
+	armv8pmu_enable_event_irq(event);
 
 	/*
 	 * Enable counter
 	 */
-	armv8pmu_enable_counter(idx);
+	armv8pmu_enable_event_counter(event);
 
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
@@ -655,10 +752,8 @@ static void armv8pmu_enable_event(struct perf_event *event)
 static void armv8pmu_disable_event(struct perf_event *event)
 {
 	unsigned long flags;
-	struct hw_perf_event *hwc = &event->hw;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events);
-	int idx = hwc->idx;
 
 	/*
 	 * Disable counter and interrupt
@@ -668,12 +763,12 @@ static void armv8pmu_disable_event(struct perf_event *event)
 	/*
 	 * Disable counter
 	 */
-	armv8pmu_disable_counter(idx);
+	armv8pmu_disable_event_counter(event);
 
 	/*
 	 * Disable interrupt for this counter
 	 */
-	armv8pmu_disable_intens(idx);
+	armv8pmu_disable_event_irq(event);
 
 	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
 }
@@ -767,10 +862,42 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 	return IRQ_HANDLED;
 }
 
+static int armv8pmu_get_single_idx(struct pmu_hw_events *cpuc,
+				    struct arm_pmu *cpu_pmu)
+{
+	int idx;
+
+	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; idx ++) {
+		if (!test_and_set_bit(idx, cpuc->used_mask))
+			return idx;
+	}
+	return -EAGAIN;
+}
+
+static int armv8pmu_get_chain_idx(struct pmu_hw_events *cpuc,
+				   struct arm_pmu *cpu_pmu)
+{
+	int idx;
+
+	/*
+	 * Chaining requires two consecutive event counters, where
+	 * the lower idx must be even.
+	 */
+	for (idx = ARMV8_IDX_COUNTER0 + 1; idx < cpu_pmu->num_events; idx += 2) {
+		if (!test_and_set_bit(idx, cpuc->used_mask)) {
+			/* Check if the preceding even counter is available */
+			if (!test_and_set_bit(idx - 1, cpuc->used_mask))
+				return idx;
+			/* Release the Odd counter */
+			clear_bit(idx, cpuc->used_mask);
+		}
+	}
+	return -EAGAIN;
+}
+
 static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 				  struct perf_event *event)
 {
-	int idx;
 	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
 	struct hw_perf_event *hwc = &event->hw;
 	unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
@@ -784,19 +911,20 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 	/*
 	 * Otherwise use events counters
 	 */
-	for (idx = ARMV8_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) {
-		if (!test_and_set_bit(idx, cpuc->used_mask))
-			return idx;
-	}
-
-	/* The counters are all in use. */
-	return -EAGAIN;
+	if (armv8pmu_event_is_64bit(event))
+		return	armv8pmu_get_chain_idx(cpuc, cpu_pmu);
+	else
+		return armv8pmu_get_single_idx(cpuc, cpu_pmu);
 }
 
 static void armv8pmu_clear_event_idx(struct pmu_hw_events *cpuc,
-				  struct perf_event *event)
+				     struct perf_event *event)
 {
-	clear_bit(event->hw.idx, cpuc->used_mask);
+	int idx = event->hw.idx;
+
+	clear_bit(idx, cpuc->used_mask);
+	if (armv8pmu_event_is_chained(event))
+		clear_bit(idx - 1, cpuc->used_mask);
 }
 
 /*
@@ -871,6 +999,9 @@ static int __armv8_pmuv3_map_event(struct perf_event *event,
 				       &armv8_pmuv3_perf_cache_map,
 				       ARMV8_PMU_EVTYPE_EVENT);
 
+	if (armv8pmu_event_is_64bit(event))
+		event->hw.flags |= ARMPMU_EVT_64BIT;
+
 	/* Onl expose micro/arch events supported by this PMU */
 	if ((hw_event_id > 0) && (hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS)
 	    && test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index a28881058f18..7f01f6f60b87 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -665,14 +665,9 @@ static void cpu_pm_pmu_setup(struct arm_pmu *armpmu, unsigned long cmd)
 	int idx;
 
 	for (idx = 0; idx < armpmu->num_events; idx++) {
-		/*
-		 * If the counter is not used skip it, there is no
-		 * need of stopping/restarting it.
-		 */
-		if (!test_bit(idx, hw_events->used_mask))
-			continue;
-
 		event = hw_events->events[idx];
+		if (!event)
+			continue;
 
 		switch (cmd) {
 		case CPU_PM_ENTER:
-- 
cgit v1.2.3


From 54501ac150fed82b256e6a9bd4e2201bc3b21b22 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jul 2018 17:16:27 +0200
Subject: arm64: make flatmem depend on !NUMA

Building without NUMA but with FLATMEM results in a link error
because mem_map[] is not available:

aarch64-linux-ld -EB -maarch64elfb --no-undefined -X -pie -shared -Bsymbolic --no-apply-dynamic-relocs --build-id -o .tmp_vmlinux1 -T ./arch/arm64/kernel/vmlinux.lds --whole-archive built-in.a --no-whole-archive --start-group arch/arm64/lib/lib.a lib/lib.a --end-group
init/do_mounts.o: In function `mount_block_root':
do_mounts.c:(.init.text+0x1e8): undefined reference to `mem_map'
arch/arm64/kernel/vdso.o: In function `vdso_init':
vdso.c:(.init.text+0xb4): undefined reference to `mem_map'

This uses the same trick as the other architectures, making flatmem
depend on !NUMA to avoid the broken configuration.

Fixes: e7d4bac428ed ("arm64: add ARM64-specific support for flatmem")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index c548b3dd48ab..2e7609e4d08a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -787,7 +787,7 @@ config ARCH_SELECT_MEMORY_MODEL
 	def_bool ARCH_SPARSEMEM_ENABLE
 
 config ARCH_FLATMEM_ENABLE
-	def_bool y
+	def_bool !NUMA
 
 config HAVE_ARCH_PFN_VALID
 	def_bool ARCH_HAS_HOLES_MEMORYMODEL || !SPARSEMEM
-- 
cgit v1.2.3


From 81583afe790c5bd86300537783b23f3b12794f03 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sat, 7 Jul 2018 12:22:10 +0200
Subject: ASoC: Intel: bytcr_rt5640: Add quirk for the Lenovo Miix2 8 tablet

Add a quirk for the Lenovo Miix2 8 tablet, this tablet uses a digital
mic on DMIC1 and has a mono-speaker. The jack-detect uses the default
settings..

Reported-and-tested-by: russianneuromancer@ya.ru
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5640.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 7456566c5648..657910a08261 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -552,6 +552,19 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 					BYT_RT5640_SSP0_AIF1 |
 					BYT_RT5640_MCLK_EN),
 	},
+	{	/* Lenovo Miix 2 8 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "20326"),
+			DMI_EXACT_MATCH(DMI_BOARD_NAME, "Hiking"),
+		},
+		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP |
+					BYT_RT5640_JD_SRC_JD2_IN4N |
+					BYT_RT5640_OVCD_TH_2000UA |
+					BYT_RT5640_OVCD_SF_0P75 |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_MCLK_EN),
+	},
 	{	/* MSI S100 tablet */
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Micro-Star International Co., Ltd."),
-- 
cgit v1.2.3


From fbea16dbc0a31484811c5f335ae344b2bbc66f40 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 1 Jul 2018 20:36:29 +0200
Subject: ASoC: Intel: bytcr_rt5651: Remove is_valleyview helper

Remove is_valleyview helper, this is not necessary, we can simply call
x86_match_cpu() directly instead.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index ba2753e0e12a..80f47a45cb10 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -28,6 +28,7 @@
 #include <linux/dmi.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
 #include <asm/platform_sst_audio.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
@@ -680,17 +681,10 @@ static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
 static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
 static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-mic[-swapped-hp]" */
 
-static bool is_valleyview(void)
-{
-	static const struct x86_cpu_id cpu_ids[] = {
-		{ X86_VENDOR_INTEL, 6, 55 }, /* Valleyview, Bay Trail */
-		{}
-	};
-
-	if (!x86_match_cpu(cpu_ids))
-		return false;
-	return true;
-}
+static const struct x86_cpu_id baytrail_cpu_ids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, /* Valleyview */
+	{}
+};
 
 struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 	u64 aif_value;       /* 1: AIF1, 2: AIF2 */
@@ -741,7 +735,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	 * swap SSP0 if bytcr is detected
 	 * (will be overridden if DMI quirk is detected)
 	 */
-	if (is_valleyview()) {
+	if (x86_match_cpu(baytrail_cpu_ids)) {
 		struct sst_platform_info *p_info = mach->pdata;
 		const struct sst_res_info *res_info = p_info->res_info;
 
-- 
cgit v1.2.3


From 2c375204bfad2f481feb006a82cdb67cc570b670 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 1 Jul 2018 20:36:30 +0200
Subject: ASoC: Intel: bytcr_rt5651: Move getting of codec_dev into probe()

Move the getting of the codec_dev, to add device-props to it, out of
byt_rt5651_add_codec_device_props() and into its caller,
snd_byt_rt5651_mc_probe().

This is a preparation patch for adding support for an external amplifier
enable GPIO, which requires further accesses to the codec_dev.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 80f47a45cb10..d920725ce603 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -403,15 +403,10 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
  * Note this MUST be called before snd_soc_register_card(), so that the props
  * are in place before the codec component driver's probe function parses them.
  */
-static int byt_rt5651_add_codec_device_props(const char *i2c_dev_name)
+static int byt_rt5651_add_codec_device_props(struct device *i2c_dev)
 {
 	struct property_entry props[MAX_NO_PROPS] = {};
-	struct device *i2c_dev;
-	int ret, cnt = 0;
-
-	i2c_dev = bus_find_device_by_name(&i2c_bus_type, NULL, i2c_dev_name);
-	if (!i2c_dev)
-		return -EPROBE_DEFER;
+	int cnt = 0;
 
 	props[cnt++] = PROPERTY_ENTRY_U32("realtek,jack-detect-source",
 				BYT_RT5651_JDSRC(byt_rt5651_quirk));
@@ -425,10 +420,7 @@ static int byt_rt5651_add_codec_device_props(const char *i2c_dev_name)
 	if (byt_rt5651_quirk & BYT_RT5651_DMIC_EN)
 		props[cnt++] = PROPERTY_ENTRY_BOOL("realtek,dmic-en");
 
-	ret = device_add_properties(i2c_dev, props);
-	put_device(i2c_dev);
-
-	return ret;
+	return device_add_properties(i2c_dev, props);
 }
 
 static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
@@ -696,6 +688,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	const char * const mic_name[] = { "dmic", "in1", "in12" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
+	struct device *codec_dev;
 	const char *i2c_name = NULL;
 	const char *hp_swapped;
 	bool is_bytcr = false;
@@ -731,6 +724,11 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 		"%s%s", "i2c-", i2c_name);
 	byt_rt5651_dais[dai_index].codec_name = byt_rt5651_codec_name;
 
+	codec_dev = bus_find_device_by_name(&i2c_bus_type, NULL,
+					    byt_rt5651_codec_name);
+	if (!codec_dev)
+		return -EPROBE_DEFER;
+
 	/*
 	 * swap SSP0 if bytcr is detected
 	 * (will be overridden if DMI quirk is detected)
@@ -794,7 +792,8 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 	dmi_check_system(byt_rt5651_quirk_table);
 
 	/* Must be called before register_card, also see declaration comment. */
-	ret_val = byt_rt5651_add_codec_device_props(byt_rt5651_codec_name);
+	ret_val = byt_rt5651_add_codec_device_props(codec_dev);
+	put_device(codec_dev);
 	if (ret_val)
 		return ret_val;
 
-- 
cgit v1.2.3


From 5f6fb23d2e114506ddb8437a3e65f4a20d081013 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 1 Jul 2018 20:36:31 +0200
Subject: ASoC: Intel: bytcr_rt5651: Add support for externar amplifier enable
 GPIO

The rt5651 does not have a built-in speaker amplifier, so it is often
used together with an external amplifier. On Cherry Trail boards this
external amplifier's enable pin is driven through a GPIO, which is
given as the first GPIO in the ACPI resources of the codec fwnode.

This commit adds support to the bytcr_rt5651 for this GPIO, fixing
the speaker not working on CHT devices with a rt5651 codec.

Cc: Carlo Caione <carlo@endlessm.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 65 +++++++++++++++++++++++++++++++++--
 1 file changed, 62 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index d920725ce603..5301205496be 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -26,6 +26,8 @@
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
+#include <linux/gpio/consumer.h>
+#include <linux/gpio/machine.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
@@ -86,6 +88,7 @@ enum {
 
 struct byt_rt5651_private {
 	struct clk *mclk;
+	struct gpio_desc *ext_amp_gpio;
 	struct snd_soc_jack jack;
 };
 
@@ -208,6 +211,20 @@ static int platform_clock_control(struct snd_soc_dapm_widget *w,
 	return 0;
 }
 
+static int rt5651_ext_amp_power_event(struct snd_soc_dapm_widget *w,
+	struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_card *card = w->dapm->card;
+	struct byt_rt5651_private *priv = snd_soc_card_get_drvdata(card);
+
+	if (SND_SOC_DAPM_EVENT_ON(event))
+		gpiod_set_value_cansleep(priv->ext_amp_gpio, 1);
+	else
+		gpiod_set_value_cansleep(priv->ext_amp_gpio, 0);
+
+	return 0;
+}
+
 static const struct snd_soc_dapm_widget byt_rt5651_widgets[] = {
 	SND_SOC_DAPM_HP("Headphone", NULL),
 	SND_SOC_DAPM_MIC("Headset Mic", NULL),
@@ -217,7 +234,9 @@ static const struct snd_soc_dapm_widget byt_rt5651_widgets[] = {
 	SND_SOC_DAPM_SUPPLY("Platform Clock", SND_SOC_NOPM, 0, 0,
 			    platform_clock_control, SND_SOC_DAPM_PRE_PMU |
 			    SND_SOC_DAPM_POST_PMD),
-
+	SND_SOC_DAPM_SUPPLY("Ext Amp Power", SND_SOC_NOPM, 0, 0,
+			    rt5651_ext_amp_power_event,
+			    SND_SOC_DAPM_PRE_PMD | SND_SOC_DAPM_POST_PMU),
 };
 
 static const struct snd_soc_dapm_route byt_rt5651_audio_map[] = {
@@ -225,6 +244,7 @@ static const struct snd_soc_dapm_route byt_rt5651_audio_map[] = {
 	{"Headset Mic", NULL, "Platform Clock"},
 	{"Internal Mic", NULL, "Platform Clock"},
 	{"Speaker", NULL, "Platform Clock"},
+	{"Speaker", NULL, "Ext Amp Power"},
 	{"Line In", NULL, "Platform Clock"},
 
 	{"Headset Mic", NULL, "micbias1"}, /* lowercase for rt5651 */
@@ -678,6 +698,18 @@ static const struct x86_cpu_id baytrail_cpu_ids[] = {
 	{}
 };
 
+static const struct x86_cpu_id cherrytrail_cpu_ids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_AIRMONT },     /* Braswell */
+	{}
+};
+
+static const struct acpi_gpio_params ext_amp_enable_gpios = { 0, 0, false };
+
+static const struct acpi_gpio_mapping byt_rt5651_gpios[] = {
+	{ "ext-amp-enable-gpios", &ext_amp_enable_gpios, 1 },
+	{ },
+};
+
 struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 	u64 aif_value;       /* 1: AIF1, 2: AIF2 */
 	u64 mclock_value;    /* usually 25MHz (0x17d7940), ignored */
@@ -793,9 +825,36 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 
 	/* Must be called before register_card, also see declaration comment. */
 	ret_val = byt_rt5651_add_codec_device_props(codec_dev);
-	put_device(codec_dev);
-	if (ret_val)
+	if (ret_val) {
+		put_device(codec_dev);
 		return ret_val;
+	}
+
+	/* Cherry Trail devices use an external amplifier enable gpio */
+	if (x86_match_cpu(cherrytrail_cpu_ids)) {
+		devm_acpi_dev_add_driver_gpios(codec_dev, byt_rt5651_gpios);
+		priv->ext_amp_gpio = devm_fwnode_get_index_gpiod_from_child(
+						&pdev->dev, "ext-amp-enable", 0,
+						codec_dev->fwnode,
+						GPIOD_OUT_LOW, "speaker-amp");
+		if (IS_ERR(priv->ext_amp_gpio)) {
+			ret_val = PTR_ERR(priv->ext_amp_gpio);
+			switch (ret_val) {
+			case -ENOENT:
+				priv->ext_amp_gpio = NULL;
+				break;
+			default:
+				dev_err(&pdev->dev, "Failed to get ext-amp-enable GPIO: %d\n",
+					ret_val);
+				/* fall through */
+			case -EPROBE_DEFER:
+				put_device(codec_dev);
+				return ret_val;
+			}
+		}
+	}
+
+	put_device(codec_dev);
 
 	log_quirks(&pdev->dev);
 
-- 
cgit v1.2.3


From 8d2d7bcdc1645dc243f7735278675b083c0e506c Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 5 Jul 2018 00:59:31 +0200
Subject: ASoC: rt5651: Fix workqueue cancel vs irq free race on remove

On removal we must free the IRQ *before* cancelling the jack-detect work,
so that the jack-detect work cannot be rescheduled by the IRQ.

Before this commit we were cancelling the jack-detect work from the
driver remove callback, while relying on devm to free the IRQ, which
happens after the remove callback.

This is the wrong order. This commit uses a devm-action to register
a devm callback which cancels the work, before requesting the IRQ
(devm tears things down in reverse order). This also allows us to
remove the now empty remove driver callback.

Cc: Carlo Caione <carlo@endlessm.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5651.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c
index 6b5669f3e85d..39d2c67cd064 100644
--- a/sound/soc/codecs/rt5651.c
+++ b/sound/soc/codecs/rt5651.c
@@ -1696,6 +1696,13 @@ static irqreturn_t rt5651_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static void rt5651_cancel_work(void *data)
+{
+	struct rt5651_priv *rt5651 = data;
+
+	cancel_work_sync(&rt5651->jack_detect_work);
+}
+
 static int rt5651_set_jack(struct snd_soc_component *component,
 			   struct snd_soc_jack *hp_jack, void *data)
 {
@@ -2036,6 +2043,11 @@ static int rt5651_i2c_probe(struct i2c_client *i2c,
 
 	INIT_WORK(&rt5651->jack_detect_work, rt5651_jack_detect_work);
 
+	/* Make sure work is stopped on probe-error / remove */
+	ret = devm_add_action_or_reset(&i2c->dev, rt5651_cancel_work, rt5651);
+	if (ret)
+		return ret;
+
 	ret = devm_snd_soc_register_component(&i2c->dev,
 				&soc_component_dev_rt5651,
 				rt5651_dai, ARRAY_SIZE(rt5651_dai));
@@ -2043,15 +2055,6 @@ static int rt5651_i2c_probe(struct i2c_client *i2c,
 	return ret;
 }
 
-static int rt5651_i2c_remove(struct i2c_client *i2c)
-{
-	struct rt5651_priv *rt5651 = i2c_get_clientdata(i2c);
-
-	cancel_work_sync(&rt5651->jack_detect_work);
-
-	return 0;
-}
-
 static struct i2c_driver rt5651_i2c_driver = {
 	.driver = {
 		.name = "rt5651",
@@ -2059,7 +2062,6 @@ static struct i2c_driver rt5651_i2c_driver = {
 		.of_match_table = of_match_ptr(rt5651_of_match),
 	},
 	.probe = rt5651_i2c_probe,
-	.remove   = rt5651_i2c_remove,
 	.id_table = rt5651_i2c_id,
 };
 module_i2c_driver(rt5651_i2c_driver);
-- 
cgit v1.2.3


From 34c906ddacd237511808fb2bbd941e6b91e9095a Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 5 Jul 2018 00:59:32 +0200
Subject: ASoC: rt5651: Allow disabling jack-detect by calling set_jack(NULL)

Allow the machine driver to disable jack-detect over a suspend/resume by
calling snd_soc_component_set_jack(NULL).

Note this renames rt5651_set_jack, where all the jack-enable work was done
to rt5651_enable_jack_detect. This function can now no longer fail as it
does not request the IRQ anymore. It can still be passed an invalid jack
source, but that should never happen, so this is now logged and treated as
no jack source.

Cc: Carlo Caione <carlo@endlessm.com>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5651.c | 55 +++++++++++++++++++++++++++++++----------------
 1 file changed, 36 insertions(+), 19 deletions(-)

diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c
index 39d2c67cd064..40bd1e70fee7 100644
--- a/sound/soc/codecs/rt5651.c
+++ b/sound/soc/codecs/rt5651.c
@@ -1703,14 +1703,10 @@ static void rt5651_cancel_work(void *data)
 	cancel_work_sync(&rt5651->jack_detect_work);
 }
 
-static int rt5651_set_jack(struct snd_soc_component *component,
-			   struct snd_soc_jack *hp_jack, void *data)
+static void rt5651_enable_jack_detect(struct snd_soc_component *component,
+				      struct snd_soc_jack *hp_jack)
 {
 	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
-	int ret;
-
-	if (!rt5651->irq)
-		return -EINVAL;
 
 	/* IRQ output on GPIO1 */
 	snd_soc_component_update_bits(component, RT5651_GPIO_CTRL1,
@@ -1737,10 +1733,10 @@ static int rt5651_set_jack(struct snd_soc_component *component,
 			RT5651_JD2_IRQ_EN, RT5651_JD2_IRQ_EN);
 		break;
 	case RT5651_JD_NULL:
-		return 0;
+		return;
 	default:
 		dev_err(component->dev, "Currently only JD1_1 / JD1_2 / JD2 are supported\n");
-		return -EINVAL;
+		return;
 	}
 
 	/* Enable jack detect power */
@@ -1774,19 +1770,28 @@ static int rt5651_set_jack(struct snd_soc_component *component,
 		RT5651_MB1_OC_STKY_MASK, RT5651_MB1_OC_STKY_EN);
 
 	rt5651->hp_jack = hp_jack;
-
-	ret = devm_request_threaded_irq(component->dev, rt5651->irq, NULL,
-					rt5651_irq,
-					IRQF_TRIGGER_RISING |
-					IRQF_TRIGGER_FALLING |
-					IRQF_ONESHOT, "rt5651", rt5651);
-	if (ret) {
-		dev_err(component->dev, "Failed to reguest IRQ: %d\n", ret);
-		return ret;
-	}
-
+	enable_irq(rt5651->irq);
 	/* sync initial jack state */
 	queue_work(system_power_efficient_wq, &rt5651->jack_detect_work);
+}
+
+static void rt5651_disable_jack_detect(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	disable_irq(rt5651->irq);
+	rt5651_cancel_work(rt5651);
+
+	rt5651->hp_jack = NULL;
+}
+
+static int rt5651_set_jack(struct snd_soc_component *component,
+			   struct snd_soc_jack *jack, void *data)
+{
+	if (jack)
+		rt5651_enable_jack_detect(component, jack);
+	else
+		rt5651_disable_jack_detect(component);
 
 	return 0;
 }
@@ -2048,6 +2053,18 @@ static int rt5651_i2c_probe(struct i2c_client *i2c,
 	if (ret)
 		return ret;
 
+	ret = devm_request_irq(&i2c->dev, rt5651->irq, rt5651_irq,
+			       IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
+			       | IRQF_ONESHOT, "rt5651", rt5651);
+	if (ret == 0) {
+		/* Gets re-enabled by rt5651_set_jack() */
+		disable_irq(rt5651->irq);
+	} else {
+		dev_warn(&i2c->dev, "Failed to reguest IRQ %d: %d\n",
+			 rt5651->irq, ret);
+		rt5651->irq = -ENXIO;
+	}
+
 	ret = devm_snd_soc_register_component(&i2c->dev,
 				&soc_component_dev_rt5651,
 				rt5651_dai, ARRAY_SIZE(rt5651_dai));
-- 
cgit v1.2.3


From df1569f2006b157caa944367d0d431eb4ea08624 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 5 Jul 2018 00:59:33 +0200
Subject: ASoC: rt5651: Add button press support

Enable button press detection for headsets by using the ovcd IRQ to get
notified of button presses.

This is modelled after (almost exactly copied from) the button press code
for the rt5640 which has identical ovcd hardware.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5651.c | 158 ++++++++++++++++++++++++++++++++++++++++++++--
 sound/soc/codecs/rt5651.h |   8 +++
 2 files changed, 159 insertions(+), 7 deletions(-)

diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c
index 40bd1e70fee7..0462049e739c 100644
--- a/sound/soc/codecs/rt5651.c
+++ b/sound/soc/codecs/rt5651.c
@@ -1581,6 +1581,24 @@ static void rt5651_disable_micbias1_for_ovcd(struct snd_soc_component *component
 	snd_soc_dapm_mutex_unlock(dapm);
 }
 
+static void rt5651_enable_micbias1_ovcd_irq(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	snd_soc_component_update_bits(component, RT5651_IRQ_CTRL2,
+		RT5651_IRQ_MB1_OC_MASK, RT5651_IRQ_MB1_OC_NOR);
+	rt5651->ovcd_irq_enabled = true;
+}
+
+static void rt5651_disable_micbias1_ovcd_irq(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	snd_soc_component_update_bits(component, RT5651_IRQ_CTRL2,
+		RT5651_IRQ_MB1_OC_MASK, RT5651_IRQ_MB1_OC_BP);
+	rt5651->ovcd_irq_enabled = false;
+}
+
 static void rt5651_clear_micbias1_ovcd(struct snd_soc_component *component)
 {
 	snd_soc_component_update_bits(component, RT5651_IRQ_CTRL2,
@@ -1622,10 +1640,80 @@ static bool rt5651_jack_inserted(struct snd_soc_component *component)
 	return val == 0;
 }
 
-/* Jack detect timings */
+/* Jack detect and button-press timings */
 #define JACK_SETTLE_TIME	100 /* milli seconds */
 #define JACK_DETECT_COUNT	5
 #define JACK_DETECT_MAXCOUNT	20  /* Aprox. 2 seconds worth of tries */
+#define JACK_UNPLUG_TIME	80  /* milli seconds */
+#define BP_POLL_TIME		10  /* milli seconds */
+#define BP_POLL_MAXCOUNT	200 /* assume something is wrong after this */
+#define BP_THRESHOLD		3
+
+static void rt5651_start_button_press_work(struct snd_soc_component *component)
+{
+	struct rt5651_priv *rt5651 = snd_soc_component_get_drvdata(component);
+
+	rt5651->poll_count = 0;
+	rt5651->press_count = 0;
+	rt5651->release_count = 0;
+	rt5651->pressed = false;
+	rt5651->press_reported = false;
+	rt5651_clear_micbias1_ovcd(component);
+	schedule_delayed_work(&rt5651->bp_work, msecs_to_jiffies(BP_POLL_TIME));
+}
+
+static void rt5651_button_press_work(struct work_struct *work)
+{
+	struct rt5651_priv *rt5651 =
+		container_of(work, struct rt5651_priv, bp_work.work);
+	struct snd_soc_component *component = rt5651->component;
+
+	/* Check the jack was not removed underneath us */
+	if (!rt5651_jack_inserted(component))
+		return;
+
+	if (rt5651_micbias1_ovcd(component)) {
+		rt5651->release_count = 0;
+		rt5651->press_count++;
+		/* Remember till after JACK_UNPLUG_TIME wait */
+		if (rt5651->press_count >= BP_THRESHOLD)
+			rt5651->pressed = true;
+		rt5651_clear_micbias1_ovcd(component);
+	} else {
+		rt5651->press_count = 0;
+		rt5651->release_count++;
+	}
+
+	/*
+	 * The pins get temporarily shorted on jack unplug, so we poll for
+	 * at least JACK_UNPLUG_TIME milli-seconds before reporting a press.
+	 */
+	rt5651->poll_count++;
+	if (rt5651->poll_count < (JACK_UNPLUG_TIME / BP_POLL_TIME)) {
+		schedule_delayed_work(&rt5651->bp_work,
+				      msecs_to_jiffies(BP_POLL_TIME));
+		return;
+	}
+
+	if (rt5651->pressed && !rt5651->press_reported) {
+		dev_dbg(component->dev, "headset button press\n");
+		snd_soc_jack_report(rt5651->hp_jack, SND_JACK_BTN_0,
+				    SND_JACK_BTN_0);
+		rt5651->press_reported = true;
+	}
+
+	if (rt5651->release_count >= BP_THRESHOLD) {
+		if (rt5651->press_reported) {
+			dev_dbg(component->dev, "headset button release\n");
+			snd_soc_jack_report(rt5651->hp_jack, 0, SND_JACK_BTN_0);
+		}
+		/* Re-enable OVCD IRQ to detect next press */
+		rt5651_enable_micbias1_ovcd_irq(component);
+		return; /* Stop polling */
+	}
+
+	schedule_delayed_work(&rt5651->bp_work, msecs_to_jiffies(BP_POLL_TIME));
+}
 
 static int rt5651_detect_headset(struct snd_soc_component *component)
 {
@@ -1676,15 +1764,58 @@ static void rt5651_jack_detect_work(struct work_struct *work)
 {
 	struct rt5651_priv *rt5651 =
 		container_of(work, struct rt5651_priv, jack_detect_work);
+	struct snd_soc_component *component = rt5651->component;
 	int report = 0;
 
-	if (rt5651_jack_inserted(rt5651->component)) {
-		rt5651_enable_micbias1_for_ovcd(rt5651->component);
-		report = rt5651_detect_headset(rt5651->component);
-		rt5651_disable_micbias1_for_ovcd(rt5651->component);
+	if (!rt5651_jack_inserted(component)) {
+		/* Jack removed, or spurious IRQ? */
+		if (rt5651->hp_jack->status & SND_JACK_HEADPHONE) {
+			if (rt5651->hp_jack->status & SND_JACK_MICROPHONE) {
+				cancel_delayed_work_sync(&rt5651->bp_work);
+				rt5651_disable_micbias1_ovcd_irq(component);
+				rt5651_disable_micbias1_for_ovcd(component);
+			}
+			snd_soc_jack_report(rt5651->hp_jack, 0,
+					    SND_JACK_HEADSET | SND_JACK_BTN_0);
+			dev_dbg(component->dev, "jack unplugged\n");
+		}
+	} else if (!(rt5651->hp_jack->status & SND_JACK_HEADPHONE)) {
+		/* Jack inserted */
+		WARN_ON(rt5651->ovcd_irq_enabled);
+		rt5651_enable_micbias1_for_ovcd(component);
+		report = rt5651_detect_headset(component);
+		if (report == SND_JACK_HEADSET) {
+			/* Enable ovcd IRQ for button press detect. */
+			rt5651_enable_micbias1_ovcd_irq(component);
+		} else {
+			/* No more need for overcurrent detect. */
+			rt5651_disable_micbias1_for_ovcd(component);
+		}
+		dev_dbg(component->dev, "detect report %#02x\n", report);
+		snd_soc_jack_report(rt5651->hp_jack, report, SND_JACK_HEADSET);
+	} else if (rt5651->ovcd_irq_enabled && rt5651_micbias1_ovcd(component)) {
+		dev_dbg(component->dev, "OVCD IRQ\n");
+
+		/*
+		 * The ovcd IRQ keeps firing while the button is pressed, so
+		 * we disable it and start polling the button until released.
+		 *
+		 * The disable will make the IRQ pin 0 again and since we get
+		 * IRQs on both edges (so as to detect both jack plugin and
+		 * unplug) this means we will immediately get another IRQ.
+		 * The ovcd_irq_enabled check above makes the 2ND IRQ a NOP.
+		 */
+		rt5651_disable_micbias1_ovcd_irq(component);
+		rt5651_start_button_press_work(component);
+
+		/*
+		 * If the jack-detect IRQ flag goes high (unplug) after our
+		 * above rt5651_jack_inserted() check and before we have
+		 * disabled the OVCD IRQ, the IRQ pin will stay high and as
+		 * we react to edges, we miss the unplug event -> recheck.
+		 */
+		queue_work(system_long_wq, &rt5651->jack_detect_work);
 	}
-
-	snd_soc_jack_report(rt5651->hp_jack, report, SND_JACK_HEADSET);
 }
 
 static irqreturn_t rt5651_irq(int irq, void *data)
@@ -1701,6 +1832,7 @@ static void rt5651_cancel_work(void *data)
 	struct rt5651_priv *rt5651 = data;
 
 	cancel_work_sync(&rt5651->jack_detect_work);
+	cancel_delayed_work_sync(&rt5651->bp_work);
 }
 
 static void rt5651_enable_jack_detect(struct snd_soc_component *component,
@@ -1770,6 +1902,11 @@ static void rt5651_enable_jack_detect(struct snd_soc_component *component,
 		RT5651_MB1_OC_STKY_MASK, RT5651_MB1_OC_STKY_EN);
 
 	rt5651->hp_jack = hp_jack;
+	if (rt5651->hp_jack->status & SND_JACK_MICROPHONE) {
+		rt5651_enable_micbias1_for_ovcd(component);
+		rt5651_enable_micbias1_ovcd_irq(component);
+	}
+
 	enable_irq(rt5651->irq);
 	/* sync initial jack state */
 	queue_work(system_power_efficient_wq, &rt5651->jack_detect_work);
@@ -1782,6 +1919,12 @@ static void rt5651_disable_jack_detect(struct snd_soc_component *component)
 	disable_irq(rt5651->irq);
 	rt5651_cancel_work(rt5651);
 
+	if (rt5651->hp_jack->status & SND_JACK_MICROPHONE) {
+		rt5651_disable_micbias1_ovcd_irq(component);
+		rt5651_disable_micbias1_for_ovcd(component);
+		snd_soc_jack_report(rt5651->hp_jack, 0, SND_JACK_BTN_0);
+	}
+
 	rt5651->hp_jack = NULL;
 }
 
@@ -2046,6 +2189,7 @@ static int rt5651_i2c_probe(struct i2c_client *i2c,
 	rt5651->irq = i2c->irq;
 	rt5651->hp_mute = 1;
 
+	INIT_DELAYED_WORK(&rt5651->bp_work, rt5651_button_press_work);
 	INIT_WORK(&rt5651->jack_detect_work, rt5651_jack_detect_work);
 
 	/* Make sure work is stopped on probe-error / remove */
diff --git a/sound/soc/codecs/rt5651.h b/sound/soc/codecs/rt5651.h
index 3a0968c53fde..ac6de6fb5414 100644
--- a/sound/soc/codecs/rt5651.h
+++ b/sound/soc/codecs/rt5651.h
@@ -2071,8 +2071,16 @@ struct rt5651_pll_code {
 struct rt5651_priv {
 	struct snd_soc_component *component;
 	struct regmap *regmap;
+	/* Jack and button detect data */
 	struct snd_soc_jack *hp_jack;
 	struct work_struct jack_detect_work;
+	struct delayed_work bp_work;
+	bool ovcd_irq_enabled;
+	bool pressed;
+	bool press_reported;
+	int press_count;
+	int release_count;
+	int poll_count;
 	unsigned int jd_src;
 	unsigned int ovcd_th;
 	unsigned int ovcd_sf;
-- 
cgit v1.2.3


From b91f432cbc3326f715b8c3f02ff4066ab398833f Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 5 Jul 2018 00:59:34 +0200
Subject: ASoC: Intel: bytcr_rt5651: Disable jack-detect over suspend/resume

Disable jack-detection and thus the codec IRQ over suspend/resume.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 49 +++++++++++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 5 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 5301205496be..2a8f86dfe4cb 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -676,6 +676,48 @@ static struct snd_soc_dai_link byt_rt5651_dais[] = {
 };
 
 /* SoC card */
+static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
+static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
+static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
+static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-mic[-swapped-hp]" */
+
+static int byt_rt5651_suspend(struct snd_soc_card *card)
+{
+	struct snd_soc_component *component;
+
+	if (!BYT_RT5651_JDSRC(byt_rt5651_quirk))
+		return 0;
+
+	list_for_each_entry(component, &card->component_dev_list, card_list) {
+		if (!strcmp(component->name, byt_rt5651_codec_name)) {
+			dev_dbg(component->dev, "disabling jack detect before suspend\n");
+			snd_soc_component_set_jack(component, NULL, NULL);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int byt_rt5651_resume(struct snd_soc_card *card)
+{
+	struct byt_rt5651_private *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_component *component;
+
+	if (!BYT_RT5651_JDSRC(byt_rt5651_quirk))
+		return 0;
+
+	list_for_each_entry(component, &card->component_dev_list, card_list) {
+		if (!strcmp(component->name, byt_rt5651_codec_name)) {
+			dev_dbg(component->dev, "re-enabling jack detect after resume\n");
+			snd_soc_component_set_jack(component, &priv->jack, NULL);
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static struct snd_soc_card byt_rt5651_card = {
 	.name = "bytcr-rt5651",
 	.owner = THIS_MODULE,
@@ -686,13 +728,10 @@ static struct snd_soc_card byt_rt5651_card = {
 	.dapm_routes = byt_rt5651_audio_map,
 	.num_dapm_routes = ARRAY_SIZE(byt_rt5651_audio_map),
 	.fully_routed = true,
+	.suspend_pre = byt_rt5651_suspend,
+	.resume_post = byt_rt5651_resume,
 };
 
-static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
-static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
-static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
-static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-mic[-swapped-hp]" */
-
 static const struct x86_cpu_id baytrail_cpu_ids[] = {
 	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT1 }, /* Valleyview */
 	{}
-- 
cgit v1.2.3


From caed9d636e857997e923dfe473b9310de645d916 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 5 Jul 2018 00:59:35 +0200
Subject: ASoC: Intel: bytcr_rt5651: Reporting button presses

Enable reporting of button presses now that the codec driver recently has
gotten support for this.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 2a8f86dfe4cb..b687043c8425 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -26,6 +26,7 @@
 #include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/dmi.h>
+#include <linux/input.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio/machine.h>
 #include <linux/slab.h>
@@ -531,13 +532,17 @@ static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
 
 	if (BYT_RT5651_JDSRC(byt_rt5651_quirk)) {
 		ret = snd_soc_card_jack_new(runtime->card, "Headset",
-				    SND_JACK_HEADSET, &priv->jack,
-				    bytcr_jack_pins, ARRAY_SIZE(bytcr_jack_pins));
+				    SND_JACK_HEADSET | SND_JACK_BTN_0,
+				    &priv->jack, bytcr_jack_pins,
+				    ARRAY_SIZE(bytcr_jack_pins));
 		if (ret) {
 			dev_err(runtime->dev, "jack creation failed %d\n", ret);
 			return ret;
 		}
 
+		snd_jack_set_key(priv->jack.jack, SND_JACK_BTN_0,
+				 KEY_PLAYPAUSE);
+
 		ret = snd_soc_component_set_jack(codec, &priv->jack, NULL);
 		if (ret)
 			return ret;
-- 
cgit v1.2.3


From 9748e33e26c65d84a0fb09df93c963d023f90a3f Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Mon, 9 Jul 2018 16:57:12 +0300
Subject: mips: mm: Create UCA-based ioremap_wc() method

Modern MIPS cores (like P5600/6600, M5150/6520, end so on) which
got L2-cache on chip also can enable a special type Cache-Coherency
attribute (CCA) named UnCached Accelerated attribute (UCA). In this
way uncached accelerated accesses are treated the same way as
non-accelerated uncached accesses, but uncached stores are gathered
together for more efficient bus utilization. So to speak this CCA
enables uncached transactions to better utilize bus bandwidth via
burst transactions.

This is exactly why ioremap_wc() method has been introduced in Linux.
Alas MIPS-platform code hasn't implemented it so far, instead default
one has been used which was an alias to ioremap_nocache. In order to
fix this we added MIPS-specific ioremap_wc() macro substituted by
generic __ioremap_mode() method call with writecombine CPU-info
field passed. It shall create real ioremap_wc() method if CPU-cache
supports UCA feature and fall-back to _CACHE_UNCACHED attribute
if one doesn't. Additionally platform-specific io.h shall declare
ARCH_HAS_IOREMAP_WC macro as indication of architectural definition
of ioremap_wc() (similar to x86/powerpc).

[paul.burton@mips.com:
  - Remove CC stable, this is new functionality.]

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19789/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: okaya@codeaurora.org
Cc: chenhc@lemote.com
Cc: Sergey.Semin@t-platforms.ru
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/include/asm/io.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index a363d5fa281f..01e1f62d9d12 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -12,6 +12,8 @@
 #ifndef _ASM_IO_H
 #define _ASM_IO_H
 
+#define ARCH_HAS_IOREMAP_WC
+
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/types.h>
@@ -277,6 +279,27 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si
 	__ioremap_mode((offset), (size), _page_cachable_default)
 #define ioremap_cache ioremap_cachable
 
+/*
+ * ioremap_wc     -   map bus memory into CPU space
+ * @offset:    bus address of the memory
+ * @size:      size of the resource to map
+ *
+ * ioremap_wc performs a platform specific sequence of operations to
+ * make bus memory CPU accessible via the readb/readw/readl/writeb/
+ * writew/writel functions and the other mmio helpers. The returned
+ * address is not guaranteed to be usable directly as a virtual
+ * address.
+ *
+ * This version of ioremap ensures that the memory is marked uncachable
+ * but accelerated by means of write-combining feature. It is specifically
+ * useful for PCIe prefetchable windows, which may vastly improve a
+ * communications performance. If it was determined on boot stage, what
+ * CPU CCA doesn't support UCA, the method shall fall-back to the
+ * _CACHE_UNCACHED option (see cpu_probe() method).
+ */
+#define ioremap_wc(offset, size)					\
+	__ioremap_mode((offset), (size), boot_cpu_data.writecombine)
+
 /*
  * These two are MIPS specific ioremap variant.	 ioremap_cacheable_cow
  * requests a cachable mapping, ioremap_uncached_accelerated requests a
-- 
cgit v1.2.3


From ddba595b7b24ac17d553814d9d525fe4472c89e6 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Mon, 9 Jul 2018 16:57:13 +0300
Subject: mips: mm: Discard ioremap_uncached_accelerated() method

Adaptive ioremap_wc() method is now available as of commit 9748e33e26c6
("mips: mm: Create UCA-based ioremap_wc() method"). We can use it to
obtain UnCached Accelerated (UCA) mappings safely on all MIPS systems,
and so we don't need the MIPS-specific ioremap_uncached_accelerated()
any longer. This macro hard-coded the UCA Cache Coherency Attribute
(CCA) in a manner that isn't safe for kernels that may run on different
CPUs, and it is also entirely unused so we can trivially remove it.

[paul.burton@mips.com:
  - Reword the commit message a little.
  - Remove CC stable.]

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19790/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: okaya@codeaurora.org
Cc: chenhc@lemote.com
Cc: Sergey.Semin@t-platforms.ru
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/include/asm/io.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index 01e1f62d9d12..f613d1df66c0 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -301,15 +301,11 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si
 	__ioremap_mode((offset), (size), boot_cpu_data.writecombine)
 
 /*
- * These two are MIPS specific ioremap variant.	 ioremap_cacheable_cow
- * requests a cachable mapping, ioremap_uncached_accelerated requests a
- * mapping using the uncached accelerated mode which isn't supported on
- * all processors.
+ * This is a MIPS specific ioremap variant. ioremap_cacheable_cow
+ * requests a cachable mapping with CWB attribute enabled.
  */
 #define ioremap_cacheable_cow(offset, size)				\
 	__ioremap_mode((offset), (size), _CACHE_CACHABLE_COW)
-#define ioremap_uncached_accelerated(offset, size)			\
-	__ioremap_mode((offset), (size), _CACHE_UNCACHED_ACCELERATED)
 
 static inline void iounmap(const volatile void __iomem *addr)
 {
-- 
cgit v1.2.3


From 88b7210c81096c018f5836aff4749743c0d34623 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jul 2018 17:21:34 +0200
Subject: block: iolatency: avoid 64-bit division

On 32-bit architectures, dividing a 64-bit number needs to use the
do_div() function or something like it to avoid a link failure:

block/blk-iolatency.o: In function `iolatency_prfill_limit':
blk-iolatency.c:(.text+0x8cc): undefined reference to `__aeabi_uldivmod'

Using div_u64() gives us the best output and avoids the need for an
explicit cast.

Fixes: d70675121546 ("block: introduce blk-iolatency io controller")
Reviewed-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iolatency.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index a35a1f580337..56ddb2c68752 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -798,8 +798,7 @@ static u64 iolatency_prfill_limit(struct seq_file *sf,
 	if (!dname || !iolat->min_lat_nsec)
 		return 0;
 	seq_printf(sf, "%s target=%llu\n",
-		   dname,
-		   (unsigned long long)iolat->min_lat_nsec / NSEC_PER_USEC);
+		   dname, div_u64(iolat->min_lat_nsec, NSEC_PER_USEC));
 	return 0;
 }
 
-- 
cgit v1.2.3


From 7b7c6c81b3a370b46b0c48f4ab7ac3be83237a12 Mon Sep 17 00:00:00 2001
From: Junwei Zhang <Jerry.Zhang@amd.com>
Date: Mon, 25 Jun 2018 12:51:14 +0800
Subject: drm/amdgpu: separate gpu address from bo pin
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It could be got by amdgpu_bo_gpu_offset() if need

Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c        |  6 ++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c     |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c        |  5 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_display.c       |  5 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c            |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c          |  6 ++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c        | 17 ++++++-----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h        |  5 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c         |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_test.c          |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c           |  2 +-
 drivers/gpu/drm/amd/amdgpu/dce_v10_0.c            | 10 +++++-----
 drivers/gpu/drm/amd/amdgpu/dce_v11_0.c            | 10 +++++-----
 drivers/gpu/drm/amd/amdgpu/dce_v6_0.c             | 10 +++++-----
 drivers/gpu/drm/amd/amdgpu/dce_v8_0.c             | 10 +++++-----
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c |  3 ++-
 17 files changed, 50 insertions(+), 57 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 305143fcc1ce..98e3bf890d5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -251,7 +251,6 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	struct amdgpu_bo *bo = NULL;
 	struct amdgpu_bo_param bp;
 	int r;
-	uint64_t gpu_addr_tmp = 0;
 	void *cpu_ptr_tmp = NULL;
 
 	memset(&bp, 0, sizeof(bp));
@@ -275,8 +274,7 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 		goto allocate_mem_reserve_bo_failed;
 	}
 
-	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT,
-				&gpu_addr_tmp);
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r) {
 		dev_err(adev->dev, "(%d) failed to pin bo for amdkfd\n", r);
 		goto allocate_mem_pin_bo_failed;
@@ -290,7 +288,7 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 	}
 
 	*mem_obj = bo;
-	*gpu_addr = gpu_addr_tmp;
+	*gpu_addr = amdgpu_bo_gpu_offset(bo);
 	*cpu_ptr = cpu_ptr_tmp;
 
 	amdgpu_bo_unreserve(bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index ff8fd75f7ca5..079af8ac2636 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1587,7 +1587,7 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 		goto bo_reserve_failed;
 	}
 
-	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	ret = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (ret) {
 		pr_err("Failed to pin bo. ret %d\n", ret);
 		goto pin_failed;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index 19cfff31f2e1..cb88d7e8b96b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -95,7 +95,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	r = amdgpu_bo_reserve(sobj, false);
 	if (unlikely(r != 0))
 		goto out_cleanup;
-	r = amdgpu_bo_pin(sobj, sdomain, &saddr);
+	r = amdgpu_bo_pin(sobj, sdomain);
+	saddr = amdgpu_bo_gpu_offset(sobj);
 	amdgpu_bo_unreserve(sobj);
 	if (r) {
 		goto out_cleanup;
@@ -108,7 +109,8 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	r = amdgpu_bo_reserve(dobj, false);
 	if (unlikely(r != 0))
 		goto out_cleanup;
-	r = amdgpu_bo_pin(dobj, ddomain, &daddr);
+	r = amdgpu_bo_pin(dobj, ddomain);
+	daddr = amdgpu_bo_gpu_offset(dobj);
 	amdgpu_bo_unreserve(dobj);
 	if (r) {
 		goto out_cleanup;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 9883fa9bb41b..2720444ff23a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2758,11 +2758,10 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
 			r = amdgpu_bo_reserve(aobj, true);
 			if (r == 0) {
-				r = amdgpu_bo_pin(aobj,
-						  AMDGPU_GEM_DOMAIN_VRAM,
-						  &amdgpu_crtc->cursor_addr);
+				r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 				if (r != 0)
 					DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+				amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 				amdgpu_bo_unreserve(aobj);
 			}
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index 76ee8e04ff11..a80407cf099b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -157,7 +157,6 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	struct amdgpu_bo *new_abo;
 	unsigned long flags;
 	u64 tiling_flags;
-	u64 base;
 	int i, r;
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
@@ -189,7 +188,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 		goto cleanup;
 	}
 
-	r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev), &base);
+	r = amdgpu_bo_pin(new_abo, amdgpu_display_supported_domains(adev));
 	if (unlikely(r != 0)) {
 		DRM_ERROR("failed to pin new abo buffer before flip\n");
 		goto unreserve;
@@ -206,7 +205,7 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 	amdgpu_bo_get_tiling_flags(new_abo, &tiling_flags);
 	amdgpu_bo_unreserve(new_abo);
 
-	work->base = base;
+	work->base = amdgpu_bo_gpu_offset(new_abo);
 	work->target_vblank = target - (uint32_t)drm_crtc_vblank_count(crtc) +
 		amdgpu_get_vblank_counter_kms(dev, work->crtc_id);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index 811c62927c38..c93fd9a6b59c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -168,7 +168,7 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 	}
 
 
-	ret = amdgpu_bo_pin(abo, domain, NULL);
+	ret = amdgpu_bo_pin(abo, domain);
 	if (ret) {
 		amdgpu_bo_unreserve(abo);
 		goto out_unref;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
index 36113cb60ca2..a54d5655a191 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -143,14 +143,12 @@ int amdgpu_gart_table_vram_alloc(struct amdgpu_device *adev)
  */
 int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev)
 {
-	uint64_t gpu_addr;
 	int r;
 
 	r = amdgpu_bo_reserve(adev->gart.robj, false);
 	if (unlikely(r != 0))
 		return r;
-	r = amdgpu_bo_pin(adev->gart.robj,
-				AMDGPU_GEM_DOMAIN_VRAM, &gpu_addr);
+	r = amdgpu_bo_pin(adev->gart.robj, AMDGPU_GEM_DOMAIN_VRAM);
 	if (r) {
 		amdgpu_bo_unreserve(adev->gart.robj);
 		return r;
@@ -159,7 +157,7 @@ int amdgpu_gart_table_vram_pin(struct amdgpu_device *adev)
 	if (r)
 		amdgpu_bo_unpin(adev->gart.robj);
 	amdgpu_bo_unreserve(adev->gart.robj);
-	adev->gart.table_addr = gpu_addr;
+	adev->gart.table_addr = amdgpu_bo_gpu_offset(adev->gart.robj);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 512f59836436..79cdbf1b9dc9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -252,11 +252,13 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 		goto error_free;
 	}
 
-	r = amdgpu_bo_pin(*bo_ptr, domain, gpu_addr);
+	r = amdgpu_bo_pin(*bo_ptr, domain);
 	if (r) {
 		dev_err(adev->dev, "(%d) kernel bo pin failed\n", r);
 		goto error_unreserve;
 	}
+	if (gpu_addr)
+		*gpu_addr = amdgpu_bo_gpu_offset(*bo_ptr);
 
 	if (cpu_addr) {
 		r = amdgpu_bo_kmap(*bo_ptr, cpu_addr);
@@ -817,7 +819,6 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
  * @domain: domain to be pinned to
  * @min_offset: the start of requested address range
  * @max_offset: the end of requested address range
- * @gpu_addr: GPU offset of the &amdgpu_bo buffer object
  *
  * Pins the buffer object according to requested domain and address range. If
  * the memory is unbound gart memory, binds the pages into gart table. Adjusts
@@ -835,8 +836,7 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
  * 0 for success or a negative error code on failure.
  */
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
-			     u64 min_offset, u64 max_offset,
-			     u64 *gpu_addr)
+			     u64 min_offset, u64 max_offset)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_operation_ctx ctx = { false, false };
@@ -868,8 +868,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 			return -EINVAL;
 
 		bo->pin_count++;
-		if (gpu_addr)
-			*gpu_addr = amdgpu_bo_gpu_offset(bo);
 
 		if (max_offset != 0) {
 			u64 domain_start = bo->tbo.bdev->man[mem_type].gpu_offset;
@@ -912,8 +910,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	}
 
 	bo->pin_count = 1;
-	if (gpu_addr != NULL)
-		*gpu_addr = amdgpu_bo_gpu_offset(bo);
 
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
@@ -931,7 +927,6 @@ error:
  * amdgpu_bo_pin - pin an &amdgpu_bo buffer object
  * @bo: &amdgpu_bo buffer object to be pinned
  * @domain: domain to be pinned to
- * @gpu_addr: GPU offset of the &amdgpu_bo buffer object
  *
  * A simple wrapper to amdgpu_bo_pin_restricted().
  * Provides a simpler API for buffers that do not have any strict restrictions
@@ -940,9 +935,9 @@ error:
  * Returns:
  * 0 for success or a negative error code on failure.
  */
-int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr)
+int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain)
 {
-	return amdgpu_bo_pin_restricted(bo, domain, 0, 0, gpu_addr);
+	return amdgpu_bo_pin_restricted(bo, domain, 0, 0);
 }
 
 /**
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 731748033878..9c3e29a04eb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -252,10 +252,9 @@ void *amdgpu_bo_kptr(struct amdgpu_bo *bo);
 void amdgpu_bo_kunmap(struct amdgpu_bo *bo);
 struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo);
 void amdgpu_bo_unref(struct amdgpu_bo **bo);
-int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain, u64 *gpu_addr);
+int amdgpu_bo_pin(struct amdgpu_bo *bo, u32 domain);
 int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
-			     u64 min_offset, u64 max_offset,
-			     u64 *gpu_addr);
+			     u64 min_offset, u64 max_offset);
 int amdgpu_bo_unpin(struct amdgpu_bo *bo);
 int amdgpu_bo_evict_vram(struct amdgpu_device *adev);
 int amdgpu_bo_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index df7226ad64b5..3ed02f472003 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -232,7 +232,7 @@ static int amdgpu_gem_map_attach(struct dma_buf *dma_buf,
 	}
 
 	/* pin buffer into GTT */
-	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT, NULL);
+	r = amdgpu_bo_pin(bo, AMDGPU_GEM_DOMAIN_GTT);
 	if (r)
 		goto error_unreserve;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index 57b14dccd8e0..007d70cd69dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -76,11 +76,12 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 	r = amdgpu_bo_reserve(vram_obj, false);
 	if (unlikely(r != 0))
 		goto out_unref;
-	r = amdgpu_bo_pin(vram_obj, AMDGPU_GEM_DOMAIN_VRAM, &vram_addr);
+	r = amdgpu_bo_pin(vram_obj, AMDGPU_GEM_DOMAIN_VRAM);
 	if (r) {
 		DRM_ERROR("Failed to pin VRAM object\n");
 		goto out_unres;
 	}
+	vram_addr = amdgpu_bo_gpu_offset(vram_obj);
 	for (i = 0; i < n; i++) {
 		void *gtt_map, *vram_map;
 		void **gart_start, **gart_end;
@@ -97,11 +98,12 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 		r = amdgpu_bo_reserve(gtt_obj[i], false);
 		if (unlikely(r != 0))
 			goto out_lclean_unref;
-		r = amdgpu_bo_pin(gtt_obj[i], AMDGPU_GEM_DOMAIN_GTT, &gart_addr);
+		r = amdgpu_bo_pin(gtt_obj[i], AMDGPU_GEM_DOMAIN_GTT);
 		if (r) {
 			DRM_ERROR("Failed to pin GTT object %d\n", i);
 			goto out_lclean_unres;
 		}
+		gart_addr = amdgpu_bo_gpu_offset(gtt_obj[i]);
 
 		r = amdgpu_bo_kmap(gtt_obj[i], &gtt_map);
 		if (r) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 0246cb87d9e4..0e47f15b0f97 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1695,7 +1695,7 @@ static int amdgpu_ttm_fw_reserve_vram_init(struct amdgpu_device *adev)
 			AMDGPU_GEM_DOMAIN_VRAM,
 			adev->fw_vram_usage.start_offset,
 			(adev->fw_vram_usage.start_offset +
-			adev->fw_vram_usage.size), NULL);
+			adev->fw_vram_usage.size));
 		if (r)
 			goto error_pin;
 		r = amdgpu_bo_kmap(adev->fw_vram_usage.reserved_bo,
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index ada241bfeee9..ab043228d8da 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -1855,15 +1855,14 @@ static int dce_v10_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2370,13 +2369,14 @@ static int dce_v10_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v10_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index a5b96eac3033..177851264754 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -1897,15 +1897,14 @@ static int dce_v11_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2449,13 +2448,14 @@ static int dce_v11_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v11_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
index 394cc1e8fe20..c9adc627305d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v6_0.c
@@ -1811,15 +1811,14 @@ static int dce_v6_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2263,13 +2262,14 @@ static int dce_v6_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v6_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
index c9b9ab8f1b05..50cd03beac7d 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v8_0.c
@@ -1786,15 +1786,14 @@ static int dce_v8_0_crtc_do_set_base(struct drm_crtc *crtc,
 	if (unlikely(r != 0))
 		return r;
 
-	if (atomic) {
-		fb_location = amdgpu_bo_gpu_offset(abo);
-	} else {
-		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM, &fb_location);
+	if (!atomic) {
+		r = amdgpu_bo_pin(abo, AMDGPU_GEM_DOMAIN_VRAM);
 		if (unlikely(r != 0)) {
 			amdgpu_bo_unreserve(abo);
 			return -EINVAL;
 		}
 	}
+	fb_location = amdgpu_bo_gpu_offset(abo);
 
 	amdgpu_bo_get_tiling_flags(abo, &tiling_flags);
 	amdgpu_bo_unreserve(abo);
@@ -2274,13 +2273,14 @@ static int dce_v8_0_crtc_cursor_set2(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM, &amdgpu_crtc->cursor_addr);
+	ret = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
 	amdgpu_bo_unreserve(aobj);
 	if (ret) {
 		DRM_ERROR("Failed to pin new cursor BO (%d)\n", ret);
 		drm_gem_object_put_unlocked(obj);
 		return ret;
 	}
+	amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
 
 	dce_v8_0_lock_cursor(crtc, true);
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index ca017c1dd4da..02d83c97f10b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3094,7 +3094,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 	else
 		domain = AMDGPU_GEM_DOMAIN_VRAM;
 
-	r = amdgpu_bo_pin(rbo, domain, &afb->address);
+	r = amdgpu_bo_pin(rbo, domain);
 	amdgpu_bo_unreserve(rbo);
 
 	if (unlikely(r != 0)) {
@@ -3102,6 +3102,7 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 			DRM_ERROR("Failed to pin framebuffer with error %d\n", r);
 		return r;
 	}
+	afb->address = amdgpu_bo_gpu_offset(rbo);
 
 	amdgpu_bo_ref(rbo);
 
-- 
cgit v1.2.3


From bb812f1ea87dd7a4f336242212219268393ed308 Mon Sep 17 00:00:00 2001
From: Junwei Zhang <Jerry.Zhang@amd.com>
Date: Mon, 25 Jun 2018 13:32:24 +0800
Subject: drm/amdgpu: allocate gart memory when it's required (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of calling gart address space on every bo pin,
allocates it on demand

v2: fix error handling
v3: drop the change on amdgpu_amdkfd_gpuvm.c, not needed.

Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c        |  6 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c     | 14 ++++++++++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_display.c       |  6 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c            |  8 ++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c        | 15 +++++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_test.c          |  5 +++++
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 13 +++++++++++--
 7 files changed, 57 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 98e3bf890d5b..e3ed08dca7b7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -280,6 +280,12 @@ int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 		goto allocate_mem_pin_bo_failed;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&bo->tbo);
+	if (r) {
+		dev_err(adev->dev, "%p bind failed\n", bo);
+		goto allocate_mem_kmap_bo_failed;
+	}
+
 	r = amdgpu_bo_kmap(bo, &cpu_ptr_tmp);
 	if (r) {
 		dev_err(adev->dev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
index cb88d7e8b96b..3079ea8523c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -96,11 +96,16 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	if (unlikely(r != 0))
 		goto out_cleanup;
 	r = amdgpu_bo_pin(sobj, sdomain);
-	saddr = amdgpu_bo_gpu_offset(sobj);
+	if (r) {
+		amdgpu_bo_unreserve(sobj);
+		goto out_cleanup;
+	}
+	r = amdgpu_ttm_alloc_gart(&sobj->tbo);
 	amdgpu_bo_unreserve(sobj);
 	if (r) {
 		goto out_cleanup;
 	}
+	saddr = amdgpu_bo_gpu_offset(sobj);
 	bp.domain = ddomain;
 	r = amdgpu_bo_create(adev, &bp, &dobj);
 	if (r) {
@@ -110,11 +115,16 @@ static void amdgpu_benchmark_move(struct amdgpu_device *adev, unsigned size,
 	if (unlikely(r != 0))
 		goto out_cleanup;
 	r = amdgpu_bo_pin(dobj, ddomain);
-	daddr = amdgpu_bo_gpu_offset(dobj);
+	if (r) {
+		amdgpu_bo_unreserve(sobj);
+		goto out_cleanup;
+	}
+	r = amdgpu_ttm_alloc_gart(&dobj->tbo);
 	amdgpu_bo_unreserve(dobj);
 	if (r) {
 		goto out_cleanup;
 	}
+	daddr = amdgpu_bo_gpu_offset(dobj);
 
 	if (adev->mman.buffer_funcs) {
 		time = amdgpu_benchmark_do_move(adev, size, saddr, daddr, n);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
index a80407cf099b..6748cd7fc129 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
@@ -194,6 +194,12 @@ int amdgpu_display_crtc_page_flip_target(struct drm_crtc *crtc,
 		goto unreserve;
 	}
 
+	r = amdgpu_ttm_alloc_gart(&new_abo->tbo);
+	if (unlikely(r != 0)) {
+		DRM_ERROR("%p bind failed\n", new_abo);
+		goto unpin;
+	}
+
 	r = reservation_object_get_fences_rcu(new_abo->tbo.resv, &work->excl,
 					      &work->shared_count,
 					      &work->shared);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index c93fd9a6b59c..d44b76455e89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -173,6 +173,14 @@ static int amdgpufb_create_pinned_object(struct amdgpu_fbdev *rfbdev,
 		amdgpu_bo_unreserve(abo);
 		goto out_unref;
 	}
+
+	ret = amdgpu_ttm_alloc_gart(&abo->tbo);
+	if (ret) {
+		amdgpu_bo_unreserve(abo);
+		dev_err(adev->dev, "%p bind failed\n", abo);
+		goto out_unref;
+	}
+
 	ret = amdgpu_bo_kmap(abo, NULL);
 	amdgpu_bo_unreserve(abo);
 	if (ret) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 79cdbf1b9dc9..7f7c2212aedd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -257,6 +257,13 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 		dev_err(adev->dev, "(%d) kernel bo pin failed\n", r);
 		goto error_unreserve;
 	}
+
+	r = amdgpu_ttm_alloc_gart(&(*bo_ptr)->tbo);
+	if (r) {
+		dev_err(adev->dev, "%p bind failed\n", *bo_ptr);
+		goto error_unpin;
+	}
+
 	if (gpu_addr)
 		*gpu_addr = amdgpu_bo_gpu_offset(*bo_ptr);
 
@@ -270,6 +277,8 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 
 	return 0;
 
+error_unpin:
+	amdgpu_bo_unpin(*bo_ptr);
 error_unreserve:
 	amdgpu_bo_unreserve(*bo_ptr);
 
@@ -903,12 +912,6 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 		goto error;
 	}
 
-	r = amdgpu_ttm_alloc_gart(&bo->tbo);
-	if (unlikely(r)) {
-		dev_err(adev->dev, "%p bind failed\n", bo);
-		goto error;
-	}
-
 	bo->pin_count = 1;
 
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
index 007d70cd69dd..8904e62dca7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -103,6 +103,11 @@ static void amdgpu_do_test_moves(struct amdgpu_device *adev)
 			DRM_ERROR("Failed to pin GTT object %d\n", i);
 			goto out_lclean_unres;
 		}
+		r = amdgpu_ttm_alloc_gart(&gtt_obj[i]->tbo);
+		if (r) {
+			DRM_ERROR("%p bind failed\n", gtt_obj[i]);
+			goto out_lclean_unpin;
+		}
 		gart_addr = amdgpu_bo_gpu_offset(gtt_obj[i]);
 
 		r = amdgpu_bo_kmap(gtt_obj[i], &gtt_map);
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 02d83c97f10b..d2cc32add5f7 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3095,13 +3095,22 @@ static int dm_plane_helper_prepare_fb(struct drm_plane *plane,
 		domain = AMDGPU_GEM_DOMAIN_VRAM;
 
 	r = amdgpu_bo_pin(rbo, domain);
-	amdgpu_bo_unreserve(rbo);
-
 	if (unlikely(r != 0)) {
 		if (r != -ERESTARTSYS)
 			DRM_ERROR("Failed to pin framebuffer with error %d\n", r);
+		amdgpu_bo_unreserve(rbo);
+		return r;
+	}
+
+	r = amdgpu_ttm_alloc_gart(&rbo->tbo);
+	if (unlikely(r != 0)) {
+		amdgpu_bo_unpin(rbo);
+		amdgpu_bo_unreserve(rbo);
+		DRM_ERROR("%p bind failed\n", rbo);
 		return r;
 	}
+	amdgpu_bo_unreserve(rbo);
+
 	afb->address = amdgpu_bo_gpu_offset(rbo);
 
 	amdgpu_bo_ref(rbo);
-- 
cgit v1.2.3


From dc407ee0bda07e1e992ed7c93c1faef13a1125bd Mon Sep 17 00:00:00 2001
From: Junwei Zhang <Jerry.Zhang@amd.com>
Date: Tue, 26 Jun 2018 16:23:48 +0800
Subject: drm/amdgpu: fix kmap error handling for bo creations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

kmap happens after bo pin, so unpin is required on error

Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 7f7c2212aedd..9ee678d63890 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -271,7 +271,7 @@ int amdgpu_bo_create_reserved(struct amdgpu_device *adev,
 		r = amdgpu_bo_kmap(*bo_ptr, cpu_addr);
 		if (r) {
 			dev_err(adev->dev, "(%d) kernel bo map failed\n", r);
-			goto error_unreserve;
+			goto error_unpin;
 		}
 	}
 
-- 
cgit v1.2.3


From 02374bbd3bfa38cc6922fe56736716308c48f538 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Mon, 25 Jun 2018 11:07:17 +0200
Subject: drm/amdgpu: Reserve VM root shared fence slot for command submission
 (v3)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Without this, there could not be enough slots, which could trigger the
BUG_ON in reservation_object_add_shared_fence.

v2:
* Jump to the error label instead of returning directly (Jerry Zhang)
v3:
* Reserve slots for command submission after VM updates (Christian König)

Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/106418
Reported-by: mikhail.v.gavrilov@gmail.com
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 7a625f3989a0..1bc02816989d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -928,6 +928,10 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 		r = amdgpu_bo_vm_update_pte(p);
 		if (r)
 			return r;
+
+		r = reservation_object_reserve_shared(vm->root.base.bo->tbo.resv);
+		if (r)
+			return r;
 	}
 
 	return amdgpu_cs_sync_rings(p);
-- 
cgit v1.2.3


From 73b1917454b3639ac1926c869f51e0dc20a0d22f Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Thu, 5 Jul 2018 16:34:13 +0800
Subject: drm/amdgpu: Add CLK IP base offset

so we can read/write the registers in CLK domain
through RREG32/WREG32_SOC15

Reviewed-by: Evan Quan <evan.quan@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h          | 1 +
 drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 8a440b9fa0fd..b38c170fb95c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1398,6 +1398,7 @@ enum amd_hw_ip_block_type {
 	PWR_HWIP,
 	NBIF_HWIP,
 	THM_HWIP,
+	CLK_HWIP,
 	MAX_HWIP
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
index 45aafca7f315..c5c9b2bc190d 100644
--- a/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
+++ b/drivers/gpu/drm/amd/amdgpu/vega10_reg_init.c
@@ -51,6 +51,7 @@ int vega10_reg_base_init(struct amdgpu_device *adev)
 		adev->reg_offset[PWR_HWIP][i] = (uint32_t *)(&(PWR_BASE.instance[i]));
 		adev->reg_offset[NBIF_HWIP][i] = (uint32_t *)(&(NBIF_BASE.instance[i]));
 		adev->reg_offset[THM_HWIP][i] = (uint32_t *)(&(THM_BASE.instance[i]));
+		adev->reg_offset[CLK_HWIP][i] = (uint32_t *)(&(CLK_BASE.instance[i]));
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From ed0926647daf855abd605525a123eb11a62f5498 Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Thu, 5 Jul 2018 16:45:21 +0800
Subject: drm/amd/pp: Convert 10KHz to KHz as variable name

The default clock unit in powerplay is 10KHz.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 5e771bc119d6..eb37316cfbf7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3801,7 +3801,7 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 
 	if (i < dpm_table->count) {
 		clock_req.clock_type = amd_pp_dcef_clock;
-		clock_req.clock_freq_in_khz = dpm_table->dpm_levels[i].value;
+		clock_req.clock_freq_in_khz = dpm_table->dpm_levels[i].value * 10;
 		if (!vega10_display_clock_voltage_request(hwmgr, &clock_req)) {
 			smum_send_msg_to_smc_with_parameter(
 					hwmgr, PPSMC_MSG_SetMinDeepSleepDcefclk,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 57492878874f..ed17c560b5ef 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1361,7 +1361,6 @@ int vega12_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
 	if (data->smu_features[GNLD_DPM_DCEFCLK].enabled) {
 		switch (clk_type) {
 		case amd_pp_dcef_clock:
-			clk_freq = clock_req->clock_freq_in_khz / 100;
 			clk_select = PPCLK_DCEFCLK;
 			break;
 		case amd_pp_disp_clock:
@@ -1410,7 +1409,7 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 
 	if (data->smu_features[GNLD_DPM_DCEFCLK].supported) {
 		clock_req.clock_type = amd_pp_dcef_clock;
-		clock_req.clock_freq_in_khz = min_clocks.dcefClock;
+		clock_req.clock_freq_in_khz = min_clocks.dcefClock/10;
 		if (!vega12_display_clock_voltage_request(hwmgr, &clock_req)) {
 			if (data->smu_features[GNLD_DS_DCEFCLK].supported)
 				PP_ASSERT_WITH_CODE(
-- 
cgit v1.2.3


From 10e7fddd4aebf95a9468f20fc1a87e6238b7d8d4 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 6 Jul 2018 13:46:05 +0200
Subject: drm/amd/display: fix invalid function table override
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise we try to program hardware with the wrong watermark functions
when multiple DCE generations are installed in one system.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c | 27 ++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index b235a75355b8..bae752332a9f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -741,6 +741,29 @@ static struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
+static struct mem_input_funcs dce112_mi_funcs = {
+	.mem_input_program_display_marks = dce112_mi_program_display_marks,
+	.allocate_mem_input = dce_mi_allocate_dmif,
+	.free_mem_input = dce_mi_free_dmif,
+	.mem_input_program_surface_flip_and_addr =
+			dce_mi_program_surface_flip_and_addr,
+	.mem_input_program_pte_vm = dce_mi_program_pte_vm,
+	.mem_input_program_surface_config =
+			dce_mi_program_surface_config,
+	.mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
+
+static struct mem_input_funcs dce120_mi_funcs = {
+	.mem_input_program_display_marks = dce120_mi_program_display_marks,
+	.allocate_mem_input = dce_mi_allocate_dmif,
+	.free_mem_input = dce_mi_free_dmif,
+	.mem_input_program_surface_flip_and_addr =
+			dce_mi_program_surface_flip_and_addr,
+	.mem_input_program_pte_vm = dce_mi_program_pte_vm,
+	.mem_input_program_surface_config =
+			dce_mi_program_surface_config,
+	.mem_input_is_flip_pending = dce_mi_is_flip_pending
+};
 
 void dce_mem_input_construct(
 	struct dce_mem_input *dce_mi,
@@ -769,7 +792,7 @@ void dce112_mem_input_construct(
 	const struct dce_mem_input_mask *mi_mask)
 {
 	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
-	dce_mi->base.funcs->mem_input_program_display_marks = dce112_mi_program_display_marks;
+	dce_mi->base.funcs = &dce112_mi_funcs;
 }
 
 void dce120_mem_input_construct(
@@ -781,5 +804,5 @@ void dce120_mem_input_construct(
 	const struct dce_mem_input_mask *mi_mask)
 {
 	dce_mem_input_construct(dce_mi, ctx, inst, regs, mi_shift, mi_mask);
-	dce_mi->base.funcs->mem_input_program_display_marks = dce120_mi_program_display_marks;
+	dce_mi->base.funcs = &dce120_mi_funcs;
 }
-- 
cgit v1.2.3


From a14cc8422a2601348bc5279c1d849920e91170f2 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 6 Jul 2018 14:19:07 +0200
Subject: drm/amd/display: make function tables const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is good practice to make global function tables const to avoid
accidental override.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c         | 6 +++---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c | 2 +-
 drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h          | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
index bae752332a9f..85686d917636 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_mem_input.c
@@ -729,7 +729,7 @@ static bool dce_mi_program_surface_flip_and_addr(
 	return true;
 }
 
-static struct mem_input_funcs dce_mi_funcs = {
+static const struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_program_display_marks = dce_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
 	.free_mem_input = dce_mi_free_dmif,
@@ -741,7 +741,7 @@ static struct mem_input_funcs dce_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
-static struct mem_input_funcs dce112_mi_funcs = {
+static const struct mem_input_funcs dce112_mi_funcs = {
 	.mem_input_program_display_marks = dce112_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
 	.free_mem_input = dce_mi_free_dmif,
@@ -753,7 +753,7 @@ static struct mem_input_funcs dce112_mi_funcs = {
 	.mem_input_is_flip_pending = dce_mi_is_flip_pending
 };
 
-static struct mem_input_funcs dce120_mi_funcs = {
+static const struct mem_input_funcs dce120_mi_funcs = {
 	.mem_input_program_display_marks = dce120_mi_program_display_marks,
 	.allocate_mem_input = dce_mi_allocate_dmif,
 	.free_mem_input = dce_mi_free_dmif,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
index 0564c8e31252..9b9fc3d96c07 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_mem_input_v.c
@@ -1011,7 +1011,7 @@ void dce110_free_mem_input_v(
 {
 }
 
-static struct mem_input_funcs dce110_mem_input_v_funcs = {
+static const struct mem_input_funcs dce110_mem_input_v_funcs = {
 	.mem_input_program_display_marks =
 			dce_mem_input_v_program_display_marks,
 	.mem_input_program_chroma_display_marks =
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
index 47f1dc5a43b7..da89c2edb07c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/mem_input.h
@@ -64,7 +64,7 @@ struct stutter_modes {
 };
 
 struct mem_input {
-	struct mem_input_funcs *funcs;
+	const struct mem_input_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
 	struct dc_plane_address current_address;
-- 
cgit v1.2.3


From bd4e725084189a198ca47d369d85100216d29b7e Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Fri, 6 Jul 2018 09:49:05 -0400
Subject: drm/amd/display: Make function pointer structs const
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

const to avoid hard-to-find bugs where some function overrides a
function pointer.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c     | 2 +-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c      | 2 +-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c      | 2 +-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 4 ++--
 drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h          | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 93f52c58bc69..a281bed9b413 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -1125,7 +1125,7 @@ void hubp1_vtg_sel(struct hubp *hubp, uint32_t otg_inst)
 	REG_UPDATE(DCHUBP_CNTL, HUBP_VTG_SEL, otg_inst);
 }
 
-static struct hubp_funcs dcn10_hubp_funcs = {
+static const struct hubp_funcs dcn10_hubp_funcs = {
 	.hubp_program_surface_flip_and_addr =
 			hubp1_program_surface_flip_and_addr,
 	.hubp_program_surface_config =
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
index 9ca51ae46de7..958994edf2c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_mpc.c
@@ -428,7 +428,7 @@ void mpc1_read_mpcc_state(
 			MPCC_BUSY, &s->busy);
 }
 
-const struct mpc_funcs dcn10_mpc_funcs = {
+static const struct mpc_funcs dcn10_mpc_funcs = {
 	.read_mpcc_state = mpc1_read_mpcc_state,
 	.insert_plane = mpc1_insert_plane,
 	.remove_mpcc = mpc1_remove_mpcc,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
index 77a1a9d541a4..ab958cff3b76 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c
@@ -385,7 +385,7 @@ void opp1_destroy(struct output_pixel_processor **opp)
 	*opp = NULL;
 }
 
-static struct opp_funcs dcn10_opp_funcs = {
+static const struct opp_funcs dcn10_opp_funcs = {
 		.opp_set_dyn_expansion = opp1_set_dyn_expansion,
 		.opp_program_fmt = opp1_program_fmt,
 		.opp_program_bit_depth_reduction = opp1_program_bit_depth_reduction,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 771e0cf29bba..84581b3c392b 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1035,11 +1035,11 @@ static enum dc_status dcn10_validate_plane(const struct dc_plane_state *plane_st
 	return DC_OK;
 }
 
-static struct dc_cap_funcs cap_funcs = {
+static const struct dc_cap_funcs cap_funcs = {
 	.get_dcc_compression_cap = dcn10_get_dcc_compression_cap
 };
 
-static struct resource_funcs dcn10_res_pool_funcs = {
+static const struct resource_funcs dcn10_res_pool_funcs = {
 	.destroy = dcn10_destroy_resource_pool,
 	.link_enc_create = dcn10_link_encoder_create,
 	.validate_bandwidth = dcn_validate_bandwidth,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 97df82cddf82..5b7976f6861a 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -43,7 +43,7 @@ enum cursor_lines_per_chunk {
 };
 
 struct hubp {
-	struct hubp_funcs *funcs;
+	const struct hubp_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
 	struct dc_plane_address current_address;
-- 
cgit v1.2.3


From 2aa37bf58838fd0251e0e6819767ffc8a83eac38 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Thu, 28 Jun 2018 22:51:32 -0400
Subject: drm/amdgpu: Add support for logging process info in amdgpu_vm.

Add process and thread names and pids and a function to extract
this info from relevant amdgpu_vm.

v2: Add documentation and fix identation.

v3: Add getter and setter functions for amdgpu_task_info.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 39 ++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h | 16 ++++++++++++++
 2 files changed, 55 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 712af5c1a5d6..d18f24748b34 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2942,3 +2942,42 @@ int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 
 	return 0;
 }
+
+/**
+ * amdgpu_vm_get_task_info - Extracts task info for a PASID.
+ *
+ * @dev: drm device pointer
+ * @pasid: PASID identifier for VM
+ * @task_info: task_info to fill.
+ */
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+			 struct amdgpu_task_info *task_info)
+{
+	struct amdgpu_vm *vm;
+
+	spin_lock(&adev->vm_manager.pasid_lock);
+
+	vm = idr_find(&adev->vm_manager.pasid_idr, pasid);
+	if (vm)
+		*task_info = vm->task_info;
+
+	spin_unlock(&adev->vm_manager.pasid_lock);
+}
+
+/**
+ * amdgpu_vm_set_task_info - Sets VMs task info.
+ *
+ * @vm: vm for which to set the info
+ */
+void amdgpu_vm_set_task_info(struct amdgpu_vm *vm)
+{
+	if (!vm->task_info.pid) {
+		vm->task_info.pid = current->pid;
+		get_task_comm(vm->task_info.task_name, current);
+
+		if (current->group_leader->mm == current->mm) {
+			vm->task_info.tgid = current->group_leader->pid;
+			get_task_comm(vm->task_info.process_name, current->group_leader);
+		}
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index 061b99a18cb8..d416f895233d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -164,6 +164,14 @@ struct amdgpu_vm_pt {
 #define AMDGPU_VM_FAULT_PASID(fault) ((u64)(fault) >> 48)
 #define AMDGPU_VM_FAULT_ADDR(fault)  ((u64)(fault) & 0xfffffffff000ULL)
 
+
+struct amdgpu_task_info {
+	char	process_name[TASK_COMM_LEN];
+	char	task_name[TASK_COMM_LEN];
+	pid_t	pid;
+	pid_t	tgid;
+};
+
 struct amdgpu_vm {
 	/* tree of virtual addresses mapped */
 	struct rb_root_cached	va;
@@ -215,6 +223,9 @@ struct amdgpu_vm {
 
 	/* Valid while the PD is reserved or fenced */
 	uint64_t		pd_phys_addr;
+
+	/* Some basic info about the task */
+	struct amdgpu_task_info task_info;
 };
 
 struct amdgpu_vm_manager {
@@ -317,4 +328,9 @@ bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
 				  struct amdgpu_job *job);
 void amdgpu_vm_check_compute_bug(struct amdgpu_device *adev);
 
+void amdgpu_vm_get_task_info(struct amdgpu_device *adev, unsigned int pasid,
+			 struct amdgpu_task_info *task_info);
+
+void amdgpu_vm_set_task_info(struct amdgpu_vm *vm);
+
 #endif
-- 
cgit v1.2.3


From efaa96463929684ceca4be96d0959e9ced1fa093 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Thu, 28 Jun 2018 22:55:27 -0400
Subject: drm/amdgpu: Present amdgpu_task_info in VM_FAULTS.

Extract and present the reposnsible process and thread when
VM_FAULT happens.

v2: Use getter and setter functions.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c |  4 ++++
 drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c  | 10 +++++++---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c  |  9 +++++++--
 3 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1bc02816989d..9881a1e55df3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -187,6 +187,10 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 	if (p->uf_entry.robj)
 		p->job->uf_addr = uf_offset;
 	kfree(chunk_array);
+
+	/* Use this opportunity to fill in task info for the vm */
+	amdgpu_vm_set_task_info(vm);
+
 	return 0;
 
 free_all_kdata:
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 1edbe6b477b5..a86332f36c3e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -44,7 +44,6 @@
 
 #include "amdgpu_atombios.h"
 
-
 static void gmc_v8_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v8_0_wait_for_idle(void *handle);
@@ -1447,8 +1446,13 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 		gmc_v8_0_set_fault_enable_default(adev, false);
 
 	if (printk_ratelimit()) {
-		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
-			entry->src_id, entry->src_data[0]);
+		struct amdgpu_task_info task_info = { 0 };
+
+		amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
+		dev_err(adev->dev, "GPU fault detected: %d 0x%08x for process %s pid %d thread %s pid %d\n",
+			entry->src_id, entry->src_data[0], task_info.process_name,
+			task_info.tgid, task_info.task_name, task_info.pid);
 		dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_ADDR   0x%08X\n",
 			addr);
 		dev_err(adev->dev, "  VM_CONTEXT1_PROTECTION_FAULT_STATUS 0x%08X\n",
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 3c0a85d4e4ab..7f238149ba54 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -257,11 +257,16 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 	}
 
 	if (printk_ratelimit()) {
+		struct amdgpu_task_info task_info = { 0 };
+
+		amdgpu_vm_get_task_info(adev, entry->pasid, &task_info);
+
 		dev_err(adev->dev,
-			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u)\n",
+			"[%s] VMC page fault (src_id:%u ring:%u vmid:%u pasid:%u, for process %s pid %d thread %s pid %d\n)\n",
 			entry->vmid_src ? "mmhub" : "gfxhub",
 			entry->src_id, entry->ring_id, entry->vmid,
-			entry->pasid);
+			entry->pasid, task_info.process_name, task_info.tgid,
+			task_info.task_name, task_info.pid);
 		dev_err(adev->dev, "  at page 0x%016llx from %d\n",
 			addr, entry->client_id);
 		if (!amdgpu_sriov_vf(adev))
-- 
cgit v1.2.3


From e85115786ae1bdcfd86da759928a2b644204d42a Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Thu, 5 Jul 2018 14:49:34 -0400
Subject: drm/amdgpu: Verify root PD is mapped into kernel address space (v4)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Problem: When PD/PT update made by CPU root PD was not yet mapped causing
page fault.

Fix: Verify root PD is mapped into CPU address space.

v2:
Make sure that we add the root PD to the relocated list
since then it's get mapped into CPU address space bt default
in amdgpu_vm_update_directories.

v3:
Drop change to not move kernel type BOs to evicted list.

v4:
Remove redundant bo move to relocated list.

Link: https://bugs.freedesktop.org/show_bug.cgi?id=107065
Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index d18f24748b34..0fd0a718763b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -156,6 +156,9 @@ static void amdgpu_vm_bo_base_init(struct amdgpu_vm_bo_base *base,
 		return;
 	list_add_tail(&base->bo_list, &bo->va);
 
+	if (bo->tbo.type == ttm_bo_type_kernel)
+		list_move(&base->vm_status, &vm->relocated);
+
 	if (bo->tbo.resv != vm->root.base.bo->tbo.resv)
 		return;
 
@@ -540,7 +543,6 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 			pt->parent = amdgpu_bo_ref(parent->base.bo);
 
 			amdgpu_vm_bo_base_init(&entry->base, vm, pt);
-			list_move(&entry->base.vm_status, &vm->relocated);
 		}
 
 		if (level < AMDGPU_VM_PTB) {
-- 
cgit v1.2.3


From c3cb424a086921f6bb0449b10d998352a756d6d5 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Mon, 9 Jul 2018 13:48:12 -0400
Subject: drm/amd/pp: Send khz clock values to DC for smu7/8

The previous change wasn't covering smu 7 and 8 and therefore DC was
seeing wrong clock values.

This fixes an issue where the pipes seem to hang with a 4k DP and 1080p
HDMI display.

Fixes: c3df50abc84b ("drm/amd/pp: Convert clock unit to KHz as defined")
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Cc:rex.zhu@amd.com
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c | 8 ++++----
 drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c | 6 +++---
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 077b79938528..2f7e70730e3c 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -4610,12 +4610,12 @@ static int smu7_get_sclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 			return -EINVAL;
 		dep_sclk_table = table_info->vdd_dep_on_sclk;
 		for (i = 0; i < dep_sclk_table->count; i++)
-			clocks->clock[i] = dep_sclk_table->entries[i].clk;
+			clocks->clock[i] = dep_sclk_table->entries[i].clk * 10;
 		clocks->count = dep_sclk_table->count;
 	} else if (hwmgr->pp_table_version == PP_TABLE_V0) {
 		sclk_table = hwmgr->dyn_state.vddc_dependency_on_sclk;
 		for (i = 0; i < sclk_table->count; i++)
-			clocks->clock[i] = sclk_table->entries[i].clk;
+			clocks->clock[i] = sclk_table->entries[i].clk * 10;
 		clocks->count = sclk_table->count;
 	}
 
@@ -4647,7 +4647,7 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 			return -EINVAL;
 		dep_mclk_table = table_info->vdd_dep_on_mclk;
 		for (i = 0; i < dep_mclk_table->count; i++) {
-			clocks->clock[i] = dep_mclk_table->entries[i].clk;
+			clocks->clock[i] = dep_mclk_table->entries[i].clk * 10;
 			clocks->latency[i] = smu7_get_mem_latency(hwmgr,
 						dep_mclk_table->entries[i].clk);
 		}
@@ -4655,7 +4655,7 @@ static int smu7_get_mclks(struct pp_hwmgr *hwmgr, struct amd_pp_clocks *clocks)
 	} else if (hwmgr->pp_table_version == PP_TABLE_V0) {
 		mclk_table = hwmgr->dyn_state.vddc_dependency_on_mclk;
 		for (i = 0; i < mclk_table->count; i++)
-			clocks->clock[i] = mclk_table->entries[i].clk;
+			clocks->clock[i] = mclk_table->entries[i].clk * 10;
 		clocks->count = mclk_table->count;
 	}
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
index 50690c72b2ea..288802f209dd 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
@@ -1604,17 +1604,17 @@ static int smu8_get_clock_by_type(struct pp_hwmgr *hwmgr, enum amd_pp_clock_type
 	switch (type) {
 	case amd_pp_disp_clock:
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = data->sys_info.display_clock[i];
+			clocks->clock[i] = data->sys_info.display_clock[i] * 10;
 		break;
 	case amd_pp_sys_clock:
 		table = hwmgr->dyn_state.vddc_dependency_on_sclk;
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = table->entries[i].clk;
+			clocks->clock[i] = table->entries[i].clk * 10;
 		break;
 	case amd_pp_mem_clock:
 		clocks->count = SMU8_NUM_NBPMEMORYCLOCK;
 		for (i = 0; i < clocks->count; i++)
-			clocks->clock[i] = data->sys_info.nbp_memory_clock[clocks->count - 1 - i];
+			clocks->clock[i] = data->sys_info.nbp_memory_clock[clocks->count - 1 - i] * 10;
 		break;
 	default:
 		return -1;
-- 
cgit v1.2.3


From 31e1c59796c8abeba8bbb961bc329a6aa5f5847c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 9 Jul 2018 10:24:47 -0500
Subject: drm/ttm: use swap macro in ttm_bo_handle_move_mem
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make use of the swap macro and remove unnecessary variable *tmp_mem*.
This makes the code easier to read and maintain. Also, reduces the
stack usage.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 5d8688e522d1..5142dcb8ce39 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -287,12 +287,9 @@ static int ttm_bo_handle_move_mem(struct ttm_buffer_object *bo,
 
 	if (ret) {
 		if (bdev->driver->move_notify) {
-			struct ttm_mem_reg tmp_mem = *mem;
-			*mem = bo->mem;
-			bo->mem = tmp_mem;
+			swap(*mem, bo->mem);
 			bdev->driver->move_notify(bo, false, mem);
-			bo->mem = *mem;
-			*mem = tmp_mem;
+			swap(*mem, bo->mem);
 		}
 
 		goto out_err;
-- 
cgit v1.2.3


From 89c815ef07a1db0ac2cc09d06cb2d5c3d86d6322 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <contact@tzimmermann.org>
Date: Thu, 21 Jun 2018 15:21:35 +0200
Subject: drm/ttm: Introduce ttm_bo_get() and ttm_bo_put() for ref counting
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The TTM buffer-object interface provides ttm_bo_reference() and
ttm_bo_unref() for managing reference counts. Replacing them with
ttm_bo_get() and ttm_bo_put() aligns the API with conventions used
throughout the Linux kernel.

The implementation of ttm_bo_unref() clears the supplied pointer
to NULL. This leads to workarounds where the caller saves the
pointer's value before de-referencing the BO. ttm_bo_put() does
not clear the supplied pointer.

Signed-off-by: Thomas Zimmermann <contact@tzimmermann.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c |  8 +++++++-
 include/drm/ttm/ttm_bo_api.h | 25 ++++++++++++++++++++++++-
 2 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 5142dcb8ce39..183e67c4197a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -587,12 +587,18 @@ static void ttm_bo_release(struct kref *kref)
 	kref_put(&bo->list_kref, ttm_bo_release_list);
 }
 
+void ttm_bo_put(struct ttm_buffer_object *bo)
+{
+	kref_put(&bo->kref, ttm_bo_release);
+}
+EXPORT_SYMBOL(ttm_bo_put);
+
 void ttm_bo_unref(struct ttm_buffer_object **p_bo)
 {
 	struct ttm_buffer_object *bo = *p_bo;
 
 	*p_bo = NULL;
-	kref_put(&bo->kref, ttm_bo_release);
+	ttm_bo_put(bo);
 }
 EXPORT_SYMBOL(ttm_bo_unref);
 
diff --git a/include/drm/ttm/ttm_bo_api.h b/include/drm/ttm/ttm_bo_api.h
index c67977aa1a0e..a01ba2032f0e 100644
--- a/include/drm/ttm/ttm_bo_api.h
+++ b/include/drm/ttm/ttm_bo_api.h
@@ -283,18 +283,30 @@ struct ttm_operation_ctx {
 /* when serving page fault or suspend, allow alloc anyway */
 #define TTM_OPT_FLAG_FORCE_ALLOC		0x2
 
+/**
+ * ttm_bo_get - reference a struct ttm_buffer_object
+ *
+ * @bo: The buffer object.
+ */
+static inline void ttm_bo_get(struct ttm_buffer_object *bo)
+{
+	kref_get(&bo->kref);
+}
+
 /**
  * ttm_bo_reference - reference a struct ttm_buffer_object
  *
  * @bo: The buffer object.
  *
  * Returns a refcounted pointer to a buffer object.
+ *
+ * This function is deprecated. Use @ttm_bo_get instead.
  */
 
 static inline struct ttm_buffer_object *
 ttm_bo_reference(struct ttm_buffer_object *bo)
 {
-	kref_get(&bo->kref);
+	ttm_bo_get(bo);
 	return bo;
 }
 
@@ -345,12 +357,23 @@ int ttm_bo_validate(struct ttm_buffer_object *bo,
 		    struct ttm_placement *placement,
 		    struct ttm_operation_ctx *ctx);
 
+/**
+ * ttm_bo_put
+ *
+ * @bo: The buffer object.
+ *
+ * Unreference a buffer object.
+ */
+void ttm_bo_put(struct ttm_buffer_object *bo);
+
 /**
  * ttm_bo_unref
  *
  * @bo: The buffer object.
  *
  * Unreference and clear a pointer to a buffer object.
+ *
+ * This function is deprecated. Use @ttm_bo_put instead.
  */
 void ttm_bo_unref(struct ttm_buffer_object **bo);
 
-- 
cgit v1.2.3


From 8129fdad387ae3cf6373d74a6afb5372bf773cbd Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <contact@tzimmermann.org>
Date: Thu, 21 Jun 2018 15:21:36 +0200
Subject: drm/ttm: Replace ttm_bo_reference() with ttm_bo_get()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Thomas Zimmermann <contact@tzimmermann.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo_util.c |  3 ++-
 drivers/gpu/drm/ttm/ttm_bo_vm.c   | 10 ++++++----
 2 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index f2c167702eef..897c799832f6 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -492,8 +492,9 @@ static int ttm_buffer_object_transfer(struct ttm_buffer_object *bo,
 	if (!fbo)
 		return -ENOMEM;
 
+	ttm_bo_get(bo);
 	fbo->base = *bo;
-	fbo->bo = ttm_bo_reference(bo);
+	fbo->bo = bo;
 
 	/**
 	 * Fix up members that we shouldn't copy directly:
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 0ca0ec47334e..9eaca0acb650 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -68,7 +68,7 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 		if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
 			goto out_unlock;
 
-		ttm_bo_reference(bo);
+		ttm_bo_get(bo);
 		up_read(&vmf->vma->vm_mm->mmap_sem);
 		(void) dma_fence_wait(bo->moving, true);
 		ttm_bo_unreserve(bo);
@@ -138,7 +138,7 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 
 		if (vmf->flags & FAULT_FLAG_ALLOW_RETRY) {
 			if (!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
-				ttm_bo_reference(bo);
+				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);
 				(void) ttm_bo_wait_unreserved(bo);
 				ttm_bo_unref(&bo);
@@ -302,7 +302,7 @@ static void ttm_bo_vm_open(struct vm_area_struct *vma)
 
 	WARN_ON(bo->bdev->dev_mapping != vma->vm_file->f_mapping);
 
-	(void)ttm_bo_reference(bo);
+	ttm_bo_get(bo);
 }
 
 static void ttm_bo_vm_close(struct vm_area_struct *vma)
@@ -471,8 +471,10 @@ int ttm_fbdev_mmap(struct vm_area_struct *vma, struct ttm_buffer_object *bo)
 	if (vma->vm_pgoff != 0)
 		return -EACCES;
 
+	ttm_bo_get(bo);
+
 	vma->vm_ops = &ttm_bo_vm_ops;
-	vma->vm_private_data = ttm_bo_reference(bo);
+	vma->vm_private_data = bo;
 	vma->vm_flags |= VM_MIXEDMAP;
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND;
 	return 0;
-- 
cgit v1.2.3


From f44907593d746d42821543992b7c7085d2cbeafb Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <contact@tzimmermann.org>
Date: Thu, 21 Jun 2018 15:21:37 +0200
Subject: drm/ttm: Replace ttm_bo_unref() with ttm_bo_put()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A call to ttm_bo_unref() clears the supplied pointer to NULL, while
ttm_bo_put() does not. None of the converted call sites requires the
pointer to become NULL, so the respective assign operations has been
left out from the patch.

Signed-off-by: Thomas Zimmermann <contact@tzimmermann.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_bo.c      | 2 +-
 drivers/gpu/drm/ttm/ttm_bo_util.c | 8 ++++----
 drivers/gpu/drm/ttm/ttm_bo_vm.c   | 8 ++++----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c
index 183e67c4197a..7c484729f9b2 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -1204,7 +1204,7 @@ int ttm_bo_init_reserved(struct ttm_bo_device *bdev,
 		if (!resv)
 			ttm_bo_unreserve(bo);
 
-		ttm_bo_unref(&bo);
+		ttm_bo_put(bo);
 		return ret;
 	}
 
diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c
index 897c799832f6..046a6dda690a 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_util.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_util.c
@@ -463,7 +463,7 @@ static void ttm_transfered_destroy(struct ttm_buffer_object *bo)
 	struct ttm_transfer_obj *fbo;
 
 	fbo = container_of(bo, struct ttm_transfer_obj, base);
-	ttm_bo_unref(&fbo->bo);
+	ttm_bo_put(fbo->bo);
 	kfree(fbo);
 }
 
@@ -731,7 +731,7 @@ int ttm_bo_move_accel_cleanup(struct ttm_buffer_object *bo,
 			bo->ttm = NULL;
 
 		ttm_bo_unreserve(ghost_obj);
-		ttm_bo_unref(&ghost_obj);
+		ttm_bo_put(ghost_obj);
 	}
 
 	*old_mem = *new_mem;
@@ -787,7 +787,7 @@ int ttm_bo_pipeline_move(struct ttm_buffer_object *bo,
 			bo->ttm = NULL;
 
 		ttm_bo_unreserve(ghost_obj);
-		ttm_bo_unref(&ghost_obj);
+		ttm_bo_put(ghost_obj);
 
 	} else if (from->flags & TTM_MEMTYPE_FLAG_FIXED) {
 
@@ -852,7 +852,7 @@ int ttm_bo_pipeline_gutting(struct ttm_buffer_object *bo)
 	bo->ttm = NULL;
 
 	ttm_bo_unreserve(ghost);
-	ttm_bo_unref(&ghost);
+	ttm_bo_put(ghost);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index 9eaca0acb650..6fe91c1b692d 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -72,7 +72,7 @@ static vm_fault_t ttm_bo_vm_fault_idle(struct ttm_buffer_object *bo,
 		up_read(&vmf->vma->vm_mm->mmap_sem);
 		(void) dma_fence_wait(bo->moving, true);
 		ttm_bo_unreserve(bo);
-		ttm_bo_unref(&bo);
+		ttm_bo_put(bo);
 		goto out_unlock;
 	}
 
@@ -141,7 +141,7 @@ static vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 				ttm_bo_get(bo);
 				up_read(&vmf->vma->vm_mm->mmap_sem);
 				(void) ttm_bo_wait_unreserved(bo);
-				ttm_bo_unref(&bo);
+				ttm_bo_put(bo);
 			}
 
 			return VM_FAULT_RETRY;
@@ -309,7 +309,7 @@ static void ttm_bo_vm_close(struct vm_area_struct *vma)
 {
 	struct ttm_buffer_object *bo = (struct ttm_buffer_object *)vma->vm_private_data;
 
-	ttm_bo_unref(&bo);
+	ttm_bo_put(bo);
 	vma->vm_private_data = NULL;
 }
 
@@ -461,7 +461,7 @@ int ttm_bo_mmap(struct file *filp, struct vm_area_struct *vma,
 	vma->vm_flags |= VM_IO | VM_DONTEXPAND | VM_DONTDUMP;
 	return 0;
 out_unref:
-	ttm_bo_unref(&bo);
+	ttm_bo_put(bo);
 	return ret;
 }
 EXPORT_SYMBOL(ttm_bo_mmap);
-- 
cgit v1.2.3


From 7b4e54a9729d0a57cf036af801aa1e78ef315982 Mon Sep 17 00:00:00 2001
From: Leo Liu <leo.liu@amd.com>
Date: Mon, 9 Jul 2018 11:59:01 -0400
Subject: drm/amdgpu: Take VCN jpeg ring into account in idle work handler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

VCN won't get power off when only jpeg active

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index a66cd521a875..4a3457236e85 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -211,6 +211,8 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
 		fences += amdgpu_fence_count_emitted(&adev->vcn.ring_enc[i]);
 	}
 
+	fences += amdgpu_fence_count_emitted(&adev->vcn.ring_jpeg);
+
 	if (fences == 0) {
 		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_uvd(adev, false);
-- 
cgit v1.2.3


From d02f16058e661608566e444e1a433db8b0a32c0b Mon Sep 17 00:00:00 2001
From: Leo Liu <leo.liu@amd.com>
Date: Wed, 4 Jul 2018 13:43:38 -0400
Subject: drm/amdgpu: move cache window setup after power and clock resume
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To make register read/write reliable

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index b82c92084b6f..ca4265bc10b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -600,12 +600,12 @@ static int vcn_v1_0_start(struct amdgpu_device *adev)
 	/* disable byte swapping */
 	lmi_swap_cntl = 0;
 
-	vcn_v1_0_mc_resume(adev);
-
 	vcn_1_0_disable_static_power_gating(adev);
 	/* disable clock gating */
 	vcn_v1_0_disable_clock_gating(adev);
 
+	vcn_v1_0_mc_resume(adev);
+
 	/* disable interupt */
 	WREG32_P(SOC15_REG_OFFSET(UVD, 0, mmUVD_MASTINT_EN), 0,
 			~UVD_MASTINT_EN__VCPU_EN_MASK);
-- 
cgit v1.2.3


From c1ee15b39fedbeb856cb5867762dd3f3fb779611 Mon Sep 17 00:00:00 2001
From: Leo Liu <leo.liu@amd.com>
Date: Wed, 4 Jul 2018 13:35:56 -0400
Subject: drm/amdgpu: get VCN start to process in the dpm disabled case
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes: 22cc6c5e19 (drm/amdgpu: Add runtime VCN PG support)

Signed-off-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 4a3457236e85..769c6723c9ca 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -229,7 +229,7 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
 	struct amdgpu_device *adev = ring->adev;
 	bool set_clocks = !cancel_delayed_work_sync(&adev->vcn.idle_work);
 
-	if (set_clocks && adev->pm.dpm_enabled) {
+	if (set_clocks) {
 		if (adev->pm.dpm_enabled)
 			amdgpu_dpm_enable_uvd(adev, true);
 		else
-- 
cgit v1.2.3


From 0d7f824b3342c774ea18062f5f0f39d542947c34 Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Wed, 11 Jul 2018 01:11:08 +0800
Subject: drm/amd/pp: fix semicolon.cocci warnings

drivers/gpu/drm/amd/amdgpu/../powerplay/amd_powerplay.c:1209:17-18: Unneeded semicolon

 Remove unneeded semicolon.

Generated by: scripts/coccinelle/misc/semicolon.cocci

Fixes: ea870e44415a ("drm/amd/pp: Export notify_smu_enable_pwe to display")
CC: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 145e5c403bea..75c208283e5f 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -1206,7 +1206,7 @@ static int pp_notify_smu_enable_pwe(void *handle)
 	struct pp_hwmgr *hwmgr = handle;
 
 	if (!hwmgr || !hwmgr->pm_en)
-		return -EINVAL;;
+		return -EINVAL;
 
 	if (hwmgr->hwmgr_func->smus_notify_pwe == NULL) {
 		pr_info("%s was not implemented.\n", __func__);
-- 
cgit v1.2.3


From 1416270f4a1ae83ea84156ceba19a66a8f88be1f Mon Sep 17 00:00:00 2001
From: John Stultz <john.stultz@linaro.org>
Date: Tue, 29 May 2018 19:12:18 -0700
Subject: selftest: timers: Tweak raw_skew to SKIP when ADJ_OFFSET/other clock
 adjustments are in progress

In the past we've warned when ADJ_OFFSET was in progress, usually
caused by ntpd or some other time adjusting daemon running in non
steady sate, which can cause the skew calculations to be
incorrect.

Thus, this patch checks to see if the clock was being adjusted
when we fail so that we don't cause false negatives.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: linux-kselftest@vger.kernel.org
Suggested-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
v2: Widened the checks to look for other clock adjustments that
    could happen, as suggested by Miroslav
v3: Fixed up commit message
---
 tools/testing/selftests/timers/raw_skew.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c
index ca6cd146aafe..dcf73c5dab6e 100644
--- a/tools/testing/selftests/timers/raw_skew.c
+++ b/tools/testing/selftests/timers/raw_skew.c
@@ -134,6 +134,11 @@ int main(int argv, char **argc)
 	printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000)));
 
 	if (llabs(eppm - ppm) > 1000) {
+		if (tx1.offset || tx2.offset ||
+		    tx1.freq != tx2.freq || tx1.tick != tx2.tick) {
+			printf("	[SKIP]\n");
+			return ksft_exit_skip("The clock was adjusted externally. Shutdown NTPd or other time sync daemons\n");
+		}
 		printf("	[FAILED]\n");
 		return ksft_exit_fail();
 	}
-- 
cgit v1.2.3


From b061c7a513afe14a68af41cec7c3476befc40e95 Mon Sep 17 00:00:00 2001
From: Miroslav Lichvar <mlichvar@redhat.com>
Date: Mon, 4 Jun 2018 15:34:21 +0200
Subject: timekeeping: Update multiplier when NTP frequency is set directly

When the NTP frequency is set directly from userspace using the
ADJ_FREQUENCY or ADJ_TICK timex mode, immediately update the
timekeeper's multiplier instead of waiting for the next tick.

This removes a hidden non-deterministic delay in setting of the
frequency and allows an extremely tight control of the system clock
with update rates close to or even exceeding the kernel HZ.

The update is limited to archs using modern timekeeping
(!ARCH_USES_GETTIMEOFFSET).

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Miroslav Lichvar <mlichvar@redhat.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 kernel/time/timekeeping.c | 36 ++++++++++++++++++++++++++++++------
 1 file changed, 30 insertions(+), 6 deletions(-)

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..67720110dc33 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -34,6 +34,14 @@
 #define TK_MIRROR		(1 << 1)
 #define TK_CLOCK_WAS_SET	(1 << 2)
 
+enum timekeeping_adv_mode {
+	/* Update timekeeper when a tick has passed */
+	TK_ADV_TICK,
+
+	/* Update timekeeper on a direct frequency change */
+	TK_ADV_FREQ
+};
+
 /*
  * The most important data for readout fits into a single 64 byte
  * cache line.
@@ -2021,11 +2029,11 @@ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset,
 	return offset;
 }
 
-/**
- * update_wall_time - Uses the current clocksource to increment the wall time
- *
+/*
+ * timekeeping_advance - Updates the timekeeper to the current time and
+ * current NTP tick length
  */
-void update_wall_time(void)
+static void timekeeping_advance(enum timekeeping_adv_mode mode)
 {
 	struct timekeeper *real_tk = &tk_core.timekeeper;
 	struct timekeeper *tk = &shadow_timekeeper;
@@ -2042,14 +2050,17 @@ void update_wall_time(void)
 
 #ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
 	offset = real_tk->cycle_interval;
+
+	if (mode != TK_ADV_TICK)
+		goto out;
 #else
 	offset = clocksource_delta(tk_clock_read(&tk->tkr_mono),
 				   tk->tkr_mono.cycle_last, tk->tkr_mono.mask);
-#endif
 
 	/* Check if there's really nothing to do */
-	if (offset < real_tk->cycle_interval)
+	if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK)
 		goto out;
+#endif
 
 	/* Do some additional sanity checking */
 	timekeeping_check_update(tk, offset);
@@ -2105,6 +2116,15 @@ out:
 		clock_was_set_delayed();
 }
 
+/**
+ * update_wall_time - Uses the current clocksource to increment the wall time
+ *
+ */
+void update_wall_time(void)
+{
+	timekeeping_advance(TK_ADV_TICK);
+}
+
 /**
  * getboottime64 - Return the real time of system boot.
  * @ts:		pointer to the timespec64 to be set
@@ -2327,6 +2347,10 @@ int do_adjtimex(struct timex *txc)
 	write_seqcount_end(&tk_core.seq);
 	raw_spin_unlock_irqrestore(&timekeeper_lock, flags);
 
+	/* Update the multiplier immediately if frequency was set directly */
+	if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK))
+		timekeeping_advance(TK_ADV_FREQ);
+
 	if (tai != orig_tai)
 		clock_was_set();
 
-- 
cgit v1.2.3


From 8dd99871f7acb776521b35a6107d3dd22f1522b8 Mon Sep 17 00:00:00 2001
From: Matthew Wilcox <willy@infradead.org>
Date: Tue, 3 Jul 2018 12:43:54 -0700
Subject: reed_solomon: Fix kernel-doc

The current doc build warns:
./lib/reed_solomon/reed_solomon.c:287: WARNING: Unknown target name: "gfp".

This is because it misinterprets the "GFP_" that is part of the
description.  Change the description to avoid the problem.

Signed-off-by: Matthew Wilcox <willy@infradead.org>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 lib/reed_solomon/reed_solomon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/reed_solomon/reed_solomon.c b/lib/reed_solomon/reed_solomon.c
index d8bb1a1eba72..e5fdc8b9e856 100644
--- a/lib/reed_solomon/reed_solomon.c
+++ b/lib/reed_solomon/reed_solomon.c
@@ -283,7 +283,7 @@ out:
  *		in index form
  *  @prim:	primitive element to generate polynomial roots
  *  @nroots:	RS code generator polynomial degree (number of roots)
- *  @gfp:	GFP_ flags for allocations
+ *  @gfp:	Memory allocation flags.
  */
 struct rs_control *init_rs_gfp(int symsize, int gfpoly, int fcr, int prim,
 			       int nroots, gfp_t gfp)
-- 
cgit v1.2.3


From 819d731fe3562783d5697f3269f7d15384b38f4c Mon Sep 17 00:00:00 2001
From: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Date: Thu, 5 Jul 2018 16:31:42 +0300
Subject: docs: kernel-parameters.txt: document xhci-hcd.quirks parameter

This parameter introduced several years ago in the XHCI host controller
driver was somehow left undocumented. Add a few lines in the kernel
parameters text.

Signed-off-by: Laurentiu Tudor <laurentiu.tudor@nxp.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/admin-guide/kernel-parameters.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..533ff5c68970 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4846,3 +4846,8 @@
 	xirc2ps_cs=	[NET,PCMCIA]
 			Format:
 			<irq>,<irq_mask>,<io>,<full_duplex>,<do_sound>,<lockup_hack>[,<irq2>[,<irq3>[,<irq4>]]]
+
+	xhci-hcd.quirks		[USB,KNL]
+			A hex value specifying bitmask with supplemental xhci
+			host controller quirks. Meaning of each bit can be
+			consulted in header drivers/usb/host/xhci.h.
-- 
cgit v1.2.3


From 9ac8c3bd50018c80ad413bff00f054496998cc0d Mon Sep 17 00:00:00 2001
From: Yohan Pipereau <yohan.pipereau@gmail.com>
Date: Sun, 8 Jul 2018 20:19:32 +0200
Subject: Documentation : Update relay function types

This patch updates two callback functions provided as an example in
relay API documentation : subbuf_start and create_buf_file_handler.

These functions were using older and incorrect types causing an
"initialization from incompatible pointer type".

Signed-off-by: Yohan Pipereau <yohan.pipereau@gmail.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/filesystems/relay.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/relay.txt b/Documentation/filesystems/relay.txt
index 33e2f3694733..cd709a94d054 100644
--- a/Documentation/filesystems/relay.txt
+++ b/Documentation/filesystems/relay.txt
@@ -222,7 +222,7 @@ using debugfs:
  */
 static struct dentry *create_buf_file_handler(const char *filename,
                                               struct dentry *parent,
-                                              int mode,
+                                              umode_t mode,
                                               struct rchan_buf *buf,
                                               int *is_global)
 {
@@ -375,7 +375,7 @@ would be very similar:
 static int subbuf_start(struct rchan_buf *buf,
                         void *subbuf,
 			void *prev_subbuf,
-			unsigned int prev_padding)
+			size_t prev_padding)
 {
 	if (prev_subbuf)
 		*((unsigned *)prev_subbuf) = prev_padding;
-- 
cgit v1.2.3


From 6b4c1360e8adc2cbecf400b97c1ffcf9c5aad31e Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Tue, 10 Jul 2018 12:08:36 +1000
Subject: Documentation: Add powerpc options for spec_store_bypass_disable

Document the support for spec_store_bypass_disable that was added for
powerpc in commit a048a07d7f45 ("powerpc/64s: Add support for a store
forwarding barrier at kernel entry/exit").

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Reviewed-by: Kees Cook <keescook@chromium.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/admin-guide/kernel-parameters.txt | 16 +++++++++++++---
 1 file changed, 13 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 533ff5c68970..4bb60048f583 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -4060,6 +4060,8 @@
 			This parameter controls whether the Speculative Store
 			Bypass optimization is used.
 
+			On x86 the options are:
+
 			on      - Unconditionally disable Speculative Store Bypass
 			off     - Unconditionally enable Speculative Store Bypass
 			auto    - Kernel detects whether the CPU model contains an
@@ -4075,12 +4077,20 @@
 			seccomp - Same as "prctl" above, but all seccomp threads
 				  will disable SSB unless they explicitly opt out.
 
-			Not specifying this option is equivalent to
-			spec_store_bypass_disable=auto.
-
 			Default mitigations:
 			X86:	If CONFIG_SECCOMP=y "seccomp", otherwise "prctl"
 
+			On powerpc the options are:
+
+			on,auto - On Power8 and Power9 insert a store-forwarding
+				  barrier on kernel entry and exit. On Power7
+				  perform a software flush on kernel entry and
+				  exit.
+			off	- No action.
+
+			Not specifying this option is equivalent to
+			spec_store_bypass_disable=auto.
+
 	spia_io_base=	[HW,MTD]
 	spia_fio_base=
 	spia_pedr=
-- 
cgit v1.2.3


From db0c8d8b031d2b5960f6407f7f2ca20e97e00605 Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 4 May 2018 13:32:51 -0700
Subject: x86/gpu: reserve ICL's graphics stolen memory

ICL changes the registers and addresses to 64 bits.

I also briefly looked at implementing an u64 version of the PCI config
read functions, but I concluded this wouldn't be trivial, so it's not
worth doing it for a single user that can't have any racing problems
while reading the register in two separate operations.

v2:
 - Scrub the development (non-public) changelog (Joonas).
 - Remove the i915.ko bits so this can be easily backported in order
   to properly avoid stolen memory even on machines without i915.ko
   (Joonas).
 - CC stable for the reasons above.

Issue: VIZ-9250
CC: stable@vger.kernel.org
Cc: Ingo Molnar <mingo@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Fixes: 412310019a20 ("drm/i915/icl: Add initial Icelake definitions.")
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180504203252.28048-1-paulo.r.zanoni@intel.com
---
 arch/x86/kernel/early-quirks.c | 18 ++++++++++++++++++
 include/drm/i915_drm.h         |  4 +++-
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index bae0d32e327b..72c2cf961d44 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -340,6 +340,18 @@ static resource_size_t __init gen3_stolen_base(int num, int slot, int func,
 	return bsm & INTEL_BSM_MASK;
 }
 
+static resource_size_t __init gen11_stolen_base(int num, int slot, int func,
+						resource_size_t stolen_size)
+{
+	u64 bsm;
+
+	bsm = read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW0);
+	bsm &= INTEL_BSM_MASK;
+	bsm |= (u64)read_pci_config(num, slot, func, INTEL_GEN11_BSM_DW1) << 32;
+
+	return bsm;
+}
+
 static resource_size_t __init i830_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
@@ -500,6 +512,11 @@ static const struct intel_early_ops chv_early_ops __initconst = {
 	.stolen_size = chv_stolen_size,
 };
 
+static const struct intel_early_ops gen11_early_ops __initconst = {
+	.stolen_base = gen11_stolen_base,
+	.stolen_size = gen9_stolen_size,
+};
+
 static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_I830_IDS(&i830_early_ops),
 	INTEL_I845G_IDS(&i845_early_ops),
@@ -531,6 +548,7 @@ static const struct pci_device_id intel_early_ids[] __initconst = {
 	INTEL_CFL_IDS(&gen9_early_ops),
 	INTEL_GLK_IDS(&gen9_early_ops),
 	INTEL_CNL_IDS(&gen9_early_ops),
+	INTEL_ICL_11_IDS(&gen11_early_ops),
 };
 
 struct resource intel_graphics_stolen_res __ro_after_init = DEFINE_RES_MEM(0, 0);
diff --git a/include/drm/i915_drm.h b/include/drm/i915_drm.h
index c9e5a6621b95..c44703f471b3 100644
--- a/include/drm/i915_drm.h
+++ b/include/drm/i915_drm.h
@@ -95,7 +95,9 @@ extern struct resource intel_graphics_stolen_res;
 #define    I845_TSEG_SIZE_512K	(2 << 1)
 #define    I845_TSEG_SIZE_1M	(3 << 1)
 
-#define INTEL_BSM 0x5c
+#define INTEL_BSM		0x5c
+#define INTEL_GEN11_BSM_DW0	0xc0
+#define INTEL_GEN11_BSM_DW1	0xc4
 #define   INTEL_BSM_MASK	(-(1u << 20))
 
 #endif				/* _I915_DRM_H_ */
-- 
cgit v1.2.3


From 185441e03aa9dde9fb99e6a015441fc9b312d2ef Mon Sep 17 00:00:00 2001
From: Paulo Zanoni <paulo.r.zanoni@intel.com>
Date: Fri, 4 May 2018 13:32:52 -0700
Subject: drm/i915: use the ICL stolen memory

Now that our stolen memory is already reserved by the x86 subsystem
(since commit "x86/gpu: reserve ICL's graphics stolen memory"), make
use of it.

Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: x86@kernel.org
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180504203252.28048-2-paulo.r.zanoni@intel.com
---
 drivers/gpu/drm/i915/i915_gem_stolen.c | 38 +++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/i915/i915_reg.h        |  1 +
 2 files changed, 38 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_stolen.c b/drivers/gpu/drm/i915/i915_gem_stolen.c
index 055f8687776d..53440bf87650 100644
--- a/drivers/gpu/drm/i915/i915_gem_stolen.c
+++ b/drivers/gpu/drm/i915/i915_gem_stolen.c
@@ -344,6 +344,35 @@ static void bdw_get_stolen_reserved(struct drm_i915_private *dev_priv,
 	*size = stolen_top - *base;
 }
 
+static void icl_get_stolen_reserved(struct drm_i915_private *dev_priv,
+				    resource_size_t *base,
+				    resource_size_t *size)
+{
+	u64 reg_val = I915_READ64(GEN6_STOLEN_RESERVED);
+
+	DRM_DEBUG_DRIVER("GEN6_STOLEN_RESERVED = 0x%016llx\n", reg_val);
+
+	*base = reg_val & GEN11_STOLEN_RESERVED_ADDR_MASK;
+
+	switch (reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK) {
+	case GEN8_STOLEN_RESERVED_1M:
+		*size = 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_2M:
+		*size = 2 * 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_4M:
+		*size = 4 * 1024 * 1024;
+		break;
+	case GEN8_STOLEN_RESERVED_8M:
+		*size = 8 * 1024 * 1024;
+		break;
+	default:
+		*size = 8 * 1024 * 1024;
+		MISSING_CASE(reg_val & GEN8_STOLEN_RESERVED_SIZE_MASK);
+	}
+}
+
 int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 {
 	resource_size_t reserved_base, stolen_top;
@@ -400,7 +429,9 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 			gen7_get_stolen_reserved(dev_priv,
 						 &reserved_base, &reserved_size);
 		break;
-	default:
+	case 8:
+	case 9:
+	case 10:
 		if (IS_LP(dev_priv))
 			chv_get_stolen_reserved(dev_priv,
 						&reserved_base, &reserved_size);
@@ -408,6 +439,11 @@ int i915_gem_init_stolen(struct drm_i915_private *dev_priv)
 			bdw_get_stolen_reserved(dev_priv,
 						&reserved_base, &reserved_size);
 		break;
+	case 11:
+	default:
+		icl_get_stolen_reserved(dev_priv, &reserved_base,
+					&reserved_size);
+		break;
 	}
 
 	/*
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 0424e45f88db..b95bab7a3d24 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -412,6 +412,7 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define GEN8_STOLEN_RESERVED_4M		(2 << 7)
 #define GEN8_STOLEN_RESERVED_8M		(3 << 7)
 #define GEN6_STOLEN_RESERVED_ENABLE	(1 << 0)
+#define GEN11_STOLEN_RESERVED_ADDR_MASK	(0xFFFFFFFFFFFULL << 20)
 
 /* VGA stuff */
 
-- 
cgit v1.2.3


From f075dce66c6039bb97b762b592a6db6d79e4350a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 10 Jul 2018 17:02:17 -0700
Subject: scsi sg: remove incorrect scsi command checking logic

The SCSI_IOCTL_SEND_COMMAND ioctl has interesting scsi command
"security" checking.

If the file was opened read-only (but only in that case), it will
fetch the first byte of the command from user space, and do
"sg_allow_access()" on it.  That, in turn, will check that
"blk_verify_command()" is ok with that command byte.

If that passes, it will then do call "sg_scsi_ioctl()" to execute
the command.

This is entirely nonsensical for several reasons.

It's nonsensical simply because it's racy: after it copies the command
byte from user mode to check it, user mode could just change the byte
before it is actually submitted later by "sg_scsi_ioctl()".

But it is nonsensical also because "sg_scsi_ioctl()" itself already does
blk_verify_command() on the command properly after it has been copied
from user space.

So it is an incorrect implementation of a pointless check. Remove it.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/scsi/sg.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/scsi/sg.c b/drivers/scsi/sg.c
index cd2fdac000c9..4f3450793273 100644
--- a/drivers/scsi/sg.c
+++ b/drivers/scsi/sg.c
@@ -1103,15 +1103,6 @@ sg_ioctl(struct file *filp, unsigned int cmd_in, unsigned long arg)
 	case SCSI_IOCTL_SEND_COMMAND:
 		if (atomic_read(&sdp->detaching))
 			return -ENODEV;
-		if (read_only) {
-			unsigned char opcode = WRITE_6;
-			Scsi_Ioctl_Command __user *siocp = p;
-
-			if (copy_from_user(&opcode, siocp->data, 1))
-				return -EFAULT;
-			if (sg_allow_access(filp, &opcode))
-				return -EPERM;
-		}
 		return sg_scsi_ioctl(sdp->device->request_queue, NULL, filp->f_mode, p);
 	case SG_SET_DEBUG:
 		result = get_user(val, ip);
-- 
cgit v1.2.3


From afff0d2321ea2beb6f4dcd029d4667acf73dec25 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:22 -0700
Subject: scsi: lpfc: Add Buffer overflow check, when nvme_info larger than
 PAGE_SIZE

Kernel crashes during fill_read_buffer when nvme_info sysfs file read.

With multiple NVME targets, approx 40, nvme_info may grow larger than
PAGE_SIZE bytes.  snprintf(buf + len, PAGE_SIZE - len, ...) logic is flawed
as PAGE_SIZE - len can be < 0 and is accepted by snprintf.  This results in
buffer overflow, and is detected with check from dev_attr_show and
fill_read_buffer.

Change to use scnprintf to a tmp array, before calling strlcat to ensure no
buffer overflow over PAGE_SIZE bytes.

Message "6314" created as a new message indicating when there is more nvme
info, but is truncated to fit within PAGE_SIZE bytes.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_attr.c | 432 +++++++++++++++++++++++++-----------------
 1 file changed, 257 insertions(+), 175 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 15c07481fe23..c06593e5aa32 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -64,6 +64,9 @@
 #define LPFC_MIN_MRQ_POST	512
 #define LPFC_MAX_MRQ_POST	2048
 
+#define LPFC_MAX_NVME_INFO_TMP_LEN	100
+#define LPFC_NVME_INFO_MORE_STR		"\nCould be more info...\n"
+
 /*
  * Write key size should be multiple of 4. If write key is changed
  * make sure that library write key is also changed.
@@ -158,14 +161,15 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	char *statep;
 	int i;
 	int len = 0;
+	char tmp[LPFC_MAX_NVME_INFO_TMP_LEN] = {0};
 
 	if (!(phba->cfg_enable_fc4_type & LPFC_ENABLE_NVME)) {
-		len += snprintf(buf, PAGE_SIZE, "NVME Disabled\n");
+		len = scnprintf(buf, PAGE_SIZE, "NVME Disabled\n");
 		return len;
 	}
 	if (phba->nvmet_support) {
 		if (!phba->targetport) {
-			len = snprintf(buf, PAGE_SIZE,
+			len = scnprintf(buf, PAGE_SIZE,
 					"NVME Target: x%llx is not allocated\n",
 					wwn_to_u64(vport->fc_portname.u.wwn));
 			return len;
@@ -175,135 +179,169 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 			statep = "REGISTERED";
 		else
 			statep = "INIT";
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"NVME Target Enabled  State %s\n",
-				statep);
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"%s%d WWPN x%llx WWNN x%llx DID x%06x\n",
-				"NVME Target: lpfc",
-				phba->brd_no,
-				wwn_to_u64(vport->fc_portname.u.wwn),
-				wwn_to_u64(vport->fc_nodename.u.wwn),
-				phba->targetport->port_id);
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"\nNVME Target: Statistics\n");
+		scnprintf(tmp, sizeof(tmp),
+			  "NVME Target Enabled  State %s\n",
+			  statep);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "%s%d WWPN x%llx WWNN x%llx DID x%06x\n",
+			  "NVME Target: lpfc",
+			  phba->brd_no,
+			  wwn_to_u64(vport->fc_portname.u.wwn),
+			  wwn_to_u64(vport->fc_nodename.u.wwn),
+			  phba->targetport->port_id);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		if (strlcat(buf, "\nNVME Target: Statistics\n", PAGE_SIZE)
+		    >= PAGE_SIZE)
+			goto buffer_done;
+
 		tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"LS: Rcv %08x Drop %08x Abort %08x\n",
-				atomic_read(&tgtp->rcv_ls_req_in),
-				atomic_read(&tgtp->rcv_ls_req_drop),
-				atomic_read(&tgtp->xmt_ls_abort));
+		scnprintf(tmp, sizeof(tmp),
+			  "LS: Rcv %08x Drop %08x Abort %08x\n",
+			  atomic_read(&tgtp->rcv_ls_req_in),
+			  atomic_read(&tgtp->rcv_ls_req_drop),
+			  atomic_read(&tgtp->xmt_ls_abort));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
 		if (atomic_read(&tgtp->rcv_ls_req_in) !=
 		    atomic_read(&tgtp->rcv_ls_req_out)) {
-			len += snprintf(buf+len, PAGE_SIZE-len,
-					"Rcv LS: in %08x != out %08x\n",
-					atomic_read(&tgtp->rcv_ls_req_in),
-					atomic_read(&tgtp->rcv_ls_req_out));
+			scnprintf(tmp, sizeof(tmp),
+				  "Rcv LS: in %08x != out %08x\n",
+				  atomic_read(&tgtp->rcv_ls_req_in),
+				  atomic_read(&tgtp->rcv_ls_req_out));
+			if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
 		}
 
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"LS: Xmt %08x Drop %08x Cmpl %08x\n",
-				atomic_read(&tgtp->xmt_ls_rsp),
-				atomic_read(&tgtp->xmt_ls_drop),
-				atomic_read(&tgtp->xmt_ls_rsp_cmpl));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"LS: RSP Abort %08x xb %08x Err %08x\n",
-				atomic_read(&tgtp->xmt_ls_rsp_aborted),
-				atomic_read(&tgtp->xmt_ls_rsp_xb_set),
-				atomic_read(&tgtp->xmt_ls_rsp_error));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP: Rcv %08x Defer %08x Release %08x "
-				"Drop %08x\n",
-				atomic_read(&tgtp->rcv_fcp_cmd_in),
-				atomic_read(&tgtp->rcv_fcp_cmd_defer),
-				atomic_read(&tgtp->xmt_fcp_release),
-				atomic_read(&tgtp->rcv_fcp_cmd_drop));
+		scnprintf(tmp, sizeof(tmp),
+			  "LS: Xmt %08x Drop %08x Cmpl %08x\n",
+			  atomic_read(&tgtp->xmt_ls_rsp),
+			  atomic_read(&tgtp->xmt_ls_drop),
+			  atomic_read(&tgtp->xmt_ls_rsp_cmpl));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "LS: RSP Abort %08x xb %08x Err %08x\n",
+			  atomic_read(&tgtp->xmt_ls_rsp_aborted),
+			  atomic_read(&tgtp->xmt_ls_rsp_xb_set),
+			  atomic_read(&tgtp->xmt_ls_rsp_error));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP: Rcv %08x Defer %08x Release %08x "
+			  "Drop %08x\n",
+			  atomic_read(&tgtp->rcv_fcp_cmd_in),
+			  atomic_read(&tgtp->rcv_fcp_cmd_defer),
+			  atomic_read(&tgtp->xmt_fcp_release),
+			  atomic_read(&tgtp->rcv_fcp_cmd_drop));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 
 		if (atomic_read(&tgtp->rcv_fcp_cmd_in) !=
 		    atomic_read(&tgtp->rcv_fcp_cmd_out)) {
-			len += snprintf(buf+len, PAGE_SIZE-len,
-					"Rcv FCP: in %08x != out %08x\n",
-					atomic_read(&tgtp->rcv_fcp_cmd_in),
-					atomic_read(&tgtp->rcv_fcp_cmd_out));
+			scnprintf(tmp, sizeof(tmp),
+				  "Rcv FCP: in %08x != out %08x\n",
+				  atomic_read(&tgtp->rcv_fcp_cmd_in),
+				  atomic_read(&tgtp->rcv_fcp_cmd_out));
+			if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
 		}
 
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x "
-				"drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_read),
-				atomic_read(&tgtp->xmt_fcp_read_rsp),
-				atomic_read(&tgtp->xmt_fcp_write),
-				atomic_read(&tgtp->xmt_fcp_rsp),
-				atomic_read(&tgtp->xmt_fcp_drop));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp Cmpl: %08x err %08x drop %08x\n",
-				atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
-				atomic_read(&tgtp->xmt_fcp_rsp_error),
-				atomic_read(&tgtp->xmt_fcp_rsp_drop));
-
-		len += snprintf(buf+len, PAGE_SIZE-len,
-				"FCP Rsp Abort: %08x xb %08x xricqe  %08x\n",
-				atomic_read(&tgtp->xmt_fcp_rsp_aborted),
-				atomic_read(&tgtp->xmt_fcp_rsp_xb_set),
-				atomic_read(&tgtp->xmt_fcp_xri_abort_cqe));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"ABORT: Xmt %08x Cmpl %08x\n",
-				atomic_read(&tgtp->xmt_fcp_abort),
-				atomic_read(&tgtp->xmt_fcp_abort_cmpl));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x",
-				atomic_read(&tgtp->xmt_abort_sol),
-				atomic_read(&tgtp->xmt_abort_unsol),
-				atomic_read(&tgtp->xmt_abort_rsp),
-				atomic_read(&tgtp->xmt_abort_rsp_error));
-
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"DELAY: ctx %08x  fod %08x wqfull %08x\n",
-				atomic_read(&tgtp->defer_ctx),
-				atomic_read(&tgtp->defer_fod),
-				atomic_read(&tgtp->defer_wqfull));
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP Rsp: RD %08x rsp %08x WR %08x rsp %08x "
+			  "drop %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_read),
+			  atomic_read(&tgtp->xmt_fcp_read_rsp),
+			  atomic_read(&tgtp->xmt_fcp_write),
+			  atomic_read(&tgtp->xmt_fcp_rsp),
+			  atomic_read(&tgtp->xmt_fcp_drop));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP Rsp Cmpl: %08x err %08x drop %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_rsp_cmpl),
+			  atomic_read(&tgtp->xmt_fcp_rsp_error),
+			  atomic_read(&tgtp->xmt_fcp_rsp_drop));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "FCP Rsp Abort: %08x xb %08x xricqe  %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_rsp_aborted),
+			  atomic_read(&tgtp->xmt_fcp_rsp_xb_set),
+			  atomic_read(&tgtp->xmt_fcp_xri_abort_cqe));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "ABORT: Xmt %08x Cmpl %08x\n",
+			  atomic_read(&tgtp->xmt_fcp_abort),
+			  atomic_read(&tgtp->xmt_fcp_abort_cmpl));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "ABORT: Sol %08x  Usol %08x Err %08x Cmpl %08x\n",
+			  atomic_read(&tgtp->xmt_abort_sol),
+			  atomic_read(&tgtp->xmt_abort_unsol),
+			  atomic_read(&tgtp->xmt_abort_rsp),
+			  atomic_read(&tgtp->xmt_abort_rsp_error));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp),
+			  "DELAY: ctx %08x  fod %08x wqfull %08x\n",
+			  atomic_read(&tgtp->defer_ctx),
+			  atomic_read(&tgtp->defer_fod),
+			  atomic_read(&tgtp->defer_wqfull));
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 
 		/* Calculate outstanding IOs */
 		tot = atomic_read(&tgtp->rcv_fcp_cmd_drop);
 		tot += atomic_read(&tgtp->xmt_fcp_release);
 		tot = atomic_read(&tgtp->rcv_fcp_cmd_in) - tot;
 
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"IO_CTX: %08x  WAIT: cur %08x tot %08x\n"
-				"CTX Outstanding %08llx\n",
-				phba->sli4_hba.nvmet_xri_cnt,
-				phba->sli4_hba.nvmet_io_wait_cnt,
-				phba->sli4_hba.nvmet_io_wait_total,
-				tot);
-
-		len +=  snprintf(buf+len, PAGE_SIZE-len, "\n");
-		return len;
+		scnprintf(tmp, sizeof(tmp),
+			  "IO_CTX: %08x  WAIT: cur %08x tot %08x\n"
+			  "CTX Outstanding %08llx\n\n",
+			  phba->sli4_hba.nvmet_xri_cnt,
+			  phba->sli4_hba.nvmet_io_wait_cnt,
+			  phba->sli4_hba.nvmet_io_wait_total,
+			  tot);
+		strlcat(buf, tmp, PAGE_SIZE);
+		goto buffer_done;
 	}
 
 	localport = vport->localport;
 	if (!localport) {
-		len = snprintf(buf, PAGE_SIZE,
+		len = scnprintf(buf, PAGE_SIZE,
 				"NVME Initiator x%llx is not allocated\n",
 				wwn_to_u64(vport->fc_portname.u.wwn));
 		return len;
 	}
 	lport = (struct lpfc_nvme_lport *)localport->private;
-	len = snprintf(buf, PAGE_SIZE, "NVME Initiator Enabled\n");
-
-	spin_lock_irq(shost->host_lock);
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"XRI Dist lpfc%d Total %d NVME %d SCSI %d ELS %d\n",
-			phba->brd_no,
-			phba->sli4_hba.max_cfg_param.max_xri,
-			phba->sli4_hba.nvme_xri_max,
-			phba->sli4_hba.scsi_xri_max,
-			lpfc_sli4_get_els_iocb_cnt(phba));
+	if (strlcat(buf, "\nNVME Initiator Enabled\n", PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	rcu_read_lock();
+	scnprintf(tmp, sizeof(tmp),
+		  "XRI Dist lpfc%d Total %d NVME %d SCSI %d ELS %d\n",
+		  phba->brd_no,
+		  phba->sli4_hba.max_cfg_param.max_xri,
+		  phba->sli4_hba.nvme_xri_max,
+		  phba->sli4_hba.scsi_xri_max,
+		  lpfc_sli4_get_els_iocb_cnt(phba));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
 
 	/* Port state is only one of two values for now. */
 	if (localport->port_id)
@@ -311,13 +349,15 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 	else
 		statep = "UNKNOWN ";
 
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"%s%d WWPN x%llx WWNN x%llx DID x%06x %s\n",
-			"NVME LPORT lpfc",
-			phba->brd_no,
-			wwn_to_u64(vport->fc_portname.u.wwn),
-			wwn_to_u64(vport->fc_nodename.u.wwn),
-			localport->port_id, statep);
+	scnprintf(tmp, sizeof(tmp),
+		  "%s%d WWPN x%llx WWNN x%llx DID x%06x %s\n",
+		  "NVME LPORT lpfc",
+		  phba->brd_no,
+		  wwn_to_u64(vport->fc_portname.u.wwn),
+		  wwn_to_u64(vport->fc_nodename.u.wwn),
+		  localport->port_id, statep);
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
 
 	list_for_each_entry(ndlp, &vport->fc_nodes, nlp_listp) {
 		rport = lpfc_ndlp_get_nrport(ndlp);
@@ -343,56 +383,77 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		}
 
 		/* Tab in to show lport ownership. */
-		len += snprintf(buf + len, PAGE_SIZE - len,
-				"NVME RPORT       ");
-		if (phba->brd_no >= 10)
-			len += snprintf(buf + len, PAGE_SIZE - len, " ");
-
-		len += snprintf(buf + len, PAGE_SIZE - len, "WWPN x%llx ",
-				nrport->port_name);
-		len += snprintf(buf + len, PAGE_SIZE - len, "WWNN x%llx ",
-				nrport->node_name);
-		len += snprintf(buf + len, PAGE_SIZE - len, "DID x%06x ",
-				nrport->port_id);
+		if (strlcat(buf, "NVME RPORT       ", PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+		if (phba->brd_no >= 10) {
+			if (strlcat(buf, " ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+
+		scnprintf(tmp, sizeof(tmp), "WWPN x%llx ",
+			  nrport->port_name);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp), "WWNN x%llx ",
+			  nrport->node_name);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
+
+		scnprintf(tmp, sizeof(tmp), "DID x%06x ",
+			  nrport->port_id);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 
 		/* An NVME rport can have multiple roles. */
-		if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR)
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "INITIATOR ");
-		if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET)
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "TARGET ");
-		if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY)
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "DISCSRVC ");
+		if (nrport->port_role & FC_PORT_ROLE_NVME_INITIATOR) {
+			if (strlcat(buf, "INITIATOR ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+		if (nrport->port_role & FC_PORT_ROLE_NVME_TARGET) {
+			if (strlcat(buf, "TARGET ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+		if (nrport->port_role & FC_PORT_ROLE_NVME_DISCOVERY) {
+			if (strlcat(buf, "DISCSRVC ", PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
 		if (nrport->port_role & ~(FC_PORT_ROLE_NVME_INITIATOR |
 					  FC_PORT_ROLE_NVME_TARGET |
-					  FC_PORT_ROLE_NVME_DISCOVERY))
-			len +=  snprintf(buf + len, PAGE_SIZE - len,
-					 "UNKNOWN ROLE x%x",
-					 nrport->port_role);
-
-		len +=  snprintf(buf + len, PAGE_SIZE - len, "%s  ", statep);
-		/* Terminate the string. */
-		len +=  snprintf(buf + len, PAGE_SIZE - len, "\n");
+					  FC_PORT_ROLE_NVME_DISCOVERY)) {
+			scnprintf(tmp, sizeof(tmp), "UNKNOWN ROLE x%x",
+				  nrport->port_role);
+			if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+				goto buffer_done;
+		}
+
+		scnprintf(tmp, sizeof(tmp), "%s\n", statep);
+		if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+			goto buffer_done;
 	}
-	spin_unlock_irq(shost->host_lock);
+	rcu_read_unlock();
 
 	if (!lport)
-		return len;
-
-	len += snprintf(buf + len, PAGE_SIZE - len, "\nNVME Statistics\n");
-	len += snprintf(buf+len, PAGE_SIZE-len,
-			"LS: Xmt %010x Cmpl %010x Abort %08x\n",
-			atomic_read(&lport->fc4NvmeLsRequests),
-			atomic_read(&lport->fc4NvmeLsCmpls),
-			atomic_read(&lport->xmt_ls_abort));
-
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"LS XMIT: Err %08x  CMPL: xb %08x Err %08x\n",
-			atomic_read(&lport->xmt_ls_err),
-			atomic_read(&lport->cmpl_ls_xb),
-			atomic_read(&lport->cmpl_ls_err));
+		goto buffer_done;
+
+	if (strlcat(buf, "\nNVME Statistics\n", PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "LS: Xmt %010x Cmpl %010x Abort %08x\n",
+		  atomic_read(&lport->fc4NvmeLsRequests),
+		  atomic_read(&lport->fc4NvmeLsCmpls),
+		  atomic_read(&lport->xmt_ls_abort));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "LS XMIT: Err %08x  CMPL: xb %08x Err %08x\n",
+		  atomic_read(&lport->xmt_ls_err),
+		  atomic_read(&lport->cmpl_ls_xb),
+		  atomic_read(&lport->cmpl_ls_err));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
 
 	totin = 0;
 	totout = 0;
@@ -405,25 +466,46 @@ lpfc_nvme_info_show(struct device *dev, struct device_attribute *attr,
 		data3 = atomic_read(&cstat->fc4NvmeControlRequests);
 		totout += (data1 + data2 + data3);
 	}
-	len += snprintf(buf+len, PAGE_SIZE-len,
-			"Total FCP Cmpl %016llx Issue %016llx "
-			"OutIO %016llx\n",
-			totin, totout, totout - totin);
-
-	len += snprintf(buf+len, PAGE_SIZE-len,
-			"      abort %08x noxri %08x nondlp %08x qdepth %08x "
-			"wqerr %08x err %08x\n",
-			atomic_read(&lport->xmt_fcp_abort),
-			atomic_read(&lport->xmt_fcp_noxri),
-			atomic_read(&lport->xmt_fcp_bad_ndlp),
-			atomic_read(&lport->xmt_fcp_qdepth),
-			atomic_read(&lport->xmt_fcp_err),
-			atomic_read(&lport->xmt_fcp_wqerr));
-
-	len += snprintf(buf + len, PAGE_SIZE - len,
-			"FCP CMPL: xb %08x Err %08x\n",
-			atomic_read(&lport->cmpl_fcp_xb),
-			atomic_read(&lport->cmpl_fcp_err));
+	scnprintf(tmp, sizeof(tmp),
+		  "Total FCP Cmpl %016llx Issue %016llx "
+		  "OutIO %016llx\n",
+		  totin, totout, totout - totin);
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "\tabort %08x noxri %08x nondlp %08x qdepth %08x "
+		  "wqerr %08x err %08x\n",
+		  atomic_read(&lport->xmt_fcp_abort),
+		  atomic_read(&lport->xmt_fcp_noxri),
+		  atomic_read(&lport->xmt_fcp_bad_ndlp),
+		  atomic_read(&lport->xmt_fcp_qdepth),
+		  atomic_read(&lport->xmt_fcp_err),
+		  atomic_read(&lport->xmt_fcp_wqerr));
+	if (strlcat(buf, tmp, PAGE_SIZE) >= PAGE_SIZE)
+		goto buffer_done;
+
+	scnprintf(tmp, sizeof(tmp),
+		  "FCP CMPL: xb %08x Err %08x\n",
+		  atomic_read(&lport->cmpl_fcp_xb),
+		  atomic_read(&lport->cmpl_fcp_err));
+	strlcat(buf, tmp, PAGE_SIZE);
+
+buffer_done:
+	len = strnlen(buf, PAGE_SIZE);
+
+	if (unlikely(len >= (PAGE_SIZE - 1))) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME,
+				"6314 Catching potential buffer "
+				"overflow > PAGE_SIZE = %lu bytes\n",
+				PAGE_SIZE);
+		strlcpy(buf + PAGE_SIZE - 1 -
+			strnlen(LPFC_NVME_INFO_MORE_STR, PAGE_SIZE - 1),
+			LPFC_NVME_INFO_MORE_STR,
+			strnlen(LPFC_NVME_INFO_MORE_STR, PAGE_SIZE - 1)
+			+ 1);
+	}
+
 	return len;
 }
 
-- 
cgit v1.2.3


From 5cc167ddb7441013e2b5a5f47bf11af0264bb3e8 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:23 -0700
Subject: scsi: lpfc: Fix driver not setting dpp bits correctly in doorbell
 word

Driver is incorrectly formatting a register on new hardware, using a format
for an older chip. This can result in non-deterministic behavior.

Ensure driver is not setting "workqueue index" in the WQ doorbell when
making a non-dpp doorbell write. The field must be zero when non-dpp.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_sli.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index e6786a5db502..89ebb07e203d 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -145,6 +145,7 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe128 *wqe)
 	uint32_t idx;
 	uint32_t i = 0;
 	uint8_t *tmp;
+	u32 if_type;
 
 	/* sanity check on queue memory */
 	if (unlikely(!q))
@@ -199,8 +200,14 @@ lpfc_sli4_wq_put(struct lpfc_queue *q, union lpfc_wqe128 *wqe)
 			    q->queue_id);
 		} else {
 			bf_set(lpfc_wq_db_list_fm_num_posted, &doorbell, 1);
-			bf_set(lpfc_wq_db_list_fm_index, &doorbell, host_index);
 			bf_set(lpfc_wq_db_list_fm_id, &doorbell, q->queue_id);
+
+			/* Leave bits <23:16> clear for if_type 6 dpp */
+			if_type = bf_get(lpfc_sli_intf_if_type,
+					 &q->phba->sli4_hba.sli_intf);
+			if (if_type != LPFC_SLI_INTF_IF_TYPE_6)
+				bf_set(lpfc_wq_db_list_fm_index, &doorbell,
+				       host_index);
 		}
 	} else if (q->db_format == LPFC_DB_RING_FORMAT) {
 		bf_set(lpfc_wq_db_ring_fm_num_posted, &doorbell, 1);
-- 
cgit v1.2.3


From d580c6137476ab307a66e278cf7dbc666230f714 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:24 -0700
Subject: scsi: lpfc: Fix panic if driver unloaded when port is offline

System crashes when the lpfc module is unloaded after making the port
offline

The nvme queue pointers were freed during port offline, but were later
accessed in pci remove path.

Validate the pointers in pci remove path before accessing them.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_nvme.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 76a5a99605aa..ada5a2aaee82 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -2970,7 +2970,7 @@ lpfc_nvme_wait_for_io_drain(struct lpfc_hba *phba)
 	struct lpfc_sli_ring  *pring;
 	u32 i, wait_cnt = 0;
 
-	if (phba->sli_rev < LPFC_SLI_REV4)
+	if (phba->sli_rev < LPFC_SLI_REV4 || !phba->sli4_hba.nvme_wq)
 		return;
 
 	/* Cycle through all NVME rings and make sure all outstanding
@@ -2979,6 +2979,9 @@ lpfc_nvme_wait_for_io_drain(struct lpfc_hba *phba)
 	for (i = 0; i < phba->cfg_nvme_io_channel; i++) {
 		pring = phba->sli4_hba.nvme_wq[i]->pring;
 
+		if (!pring)
+			continue;
+
 		/* Retrieve everything on the txcmplq */
 		while (!list_empty(&pring->txcmplq)) {
 			msleep(LPFC_XRI_EXCH_BUSY_WAIT_T1);
-- 
cgit v1.2.3


From 68c9b55deea51151d9da3d45ecc9a5ef72f9dfb1 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:25 -0700
Subject: scsi: lpfc: Fix abort error path for NVMET

rmmod of driver hangs

As driver instances were being unloaded, the NVME target port was unloaded
first. During the unload, the NVME initiator port sent a heartbeat
IO. Because of the target port state, that IO was scheduled for an Abort;
however, that abort subsequently failed. The failure was not cleaned up
properly and lpfc_sli4_xri_exchange_busy_wait silently hung forever.

Clean failed abort properly and make lpfc_sli4_xri_exchange_busy_wait not
hangs silently while waiting for aborts to complete.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_init.c  |  5 +++++
 drivers/scsi/lpfc/lpfc_nvmet.c | 15 +++++++++++----
 2 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 52cae87da0d2..150562b79eaa 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -10387,6 +10387,11 @@ lpfc_sli4_xri_exchange_busy_wait(struct lpfc_hba *phba)
 	while (!fcp_xri_cmpl || !els_xri_cmpl || !nvme_xri_cmpl ||
 	       !nvmet_xri_cmpl) {
 		if (wait_time > LPFC_XRI_EXCH_BUSY_WAIT_TMO) {
+			if (!nvmet_xri_cmpl)
+				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
+						"6424 NVMET XRI exchange busy "
+						"wait time: %d seconds.\n",
+						wait_time/1000);
 			if (!nvme_xri_cmpl)
 				lpfc_printf_log(phba, KERN_ERR, LOG_INIT,
 						"6100 NVME XRI exchange busy "
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 7271c9d885dd..102c970a00e6 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1732,9 +1732,12 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	uint32_t *payload;
 	uint32_t size, oxid, sid, rc;
 
+	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
+	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
+
 	if (!nvmebuf || !phba->targetport) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
-				"6154 LS Drop IO\n");
+				"6154 LS Drop IO x%x\n", oxid);
 		oxid = 0;
 		size = 0;
 		sid = 0;
@@ -1744,9 +1747,7 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 
 	tgtp = (struct lpfc_nvmet_tgtport *)phba->targetport->private;
 	payload = (uint32_t *)(nvmebuf->dbuf.virt);
-	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
 	size = bf_get(lpfc_rcqe_length,  &nvmebuf->cq_event.cqe.rcqe_cmpl);
-	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
 	sid = sli4_sid_from_fc_hdr(fc_hdr);
 
 	ctxp = kzalloc(sizeof(struct lpfc_nvmet_rcv_ctx), GFP_ATOMIC);
@@ -3105,11 +3106,17 @@ lpfc_nvmet_unsol_fcp_issue_abort(struct lpfc_hba *phba,
 	}
 
 aerr:
-	ctxp->flag &= ~LPFC_NVMET_ABORT_OP;
+	spin_lock_irqsave(&ctxp->ctxlock, flags);
+	if (ctxp->flag & LPFC_NVMET_CTX_RLS)
+		list_del(&ctxp->list);
+	ctxp->flag &= ~(LPFC_NVMET_ABORT_OP | LPFC_NVMET_CTX_RLS);
+	spin_unlock_irqrestore(&ctxp->ctxlock, flags);
+
 	atomic_inc(&tgtp->xmt_abort_rsp_error);
 	lpfc_printf_log(phba, KERN_ERR, LOG_NVME_ABTS,
 			"6135 Failed to Issue ABTS for oxid x%x. Status x%x\n",
 			ctxp->oxid, rc);
+	lpfc_nvmet_ctxbuf_post(phba, ctxp->ctxbuf);
 	return 1;
 }
 
-- 
cgit v1.2.3


From 414abe0ab66f951efe743a3293cb36ac3255214a Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:26 -0700
Subject: scsi: lpfc: Make PBDE optimizations configurable

The PBDE optimizations aren't supported in all firmware revs.

Make optimizations configurable in case there's a side effect on old
firmware.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc.h       |  3 +--
 drivers/scsi/lpfc/lpfc_attr.c  | 10 ++++++++++
 drivers/scsi/lpfc/lpfc_init.c  | 22 +++++++---------------
 drivers/scsi/lpfc/lpfc_nvme.c  |  8 ++++----
 drivers/scsi/lpfc/lpfc_nvmet.c | 23 +++++++++++++----------
 drivers/scsi/lpfc/lpfc_scsi.c  | 14 +++++++++++---
 drivers/scsi/lpfc/lpfc_sli.c   |  8 ++++----
 7 files changed, 50 insertions(+), 38 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index 20b249a649dd..fc580a9b2bae 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -840,8 +840,7 @@ struct lpfc_hba {
 #define LPFC_ENABLE_FCP  1
 #define LPFC_ENABLE_NVME 2
 #define LPFC_ENABLE_BOTH 3
-	uint32_t nvme_embed_pbde;
-	uint32_t fcp_embed_pbde;
+	uint32_t cfg_enable_pbde;
 	uint32_t io_channel_irqs;	/* number of irqs for io channels */
 	struct nvmet_fc_target_port *targetport;
 	lpfc_vpd_t vpd;		/* vital product data */
diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index c06593e5aa32..23a5a298d60e 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -5387,6 +5387,14 @@ LPFC_BBCR_ATTR_RW(enable_bbcr, 1, 0, 1, "Enable BBC Recovery");
  */
 LPFC_ATTR_RW(enable_dpp, 1, 0, 1, "Enable Direct Packet Push");
 
+/*
+ * lpfc_enable_pbde: Enable PBDE on PRISM - G7
+ *       0  = PBDE on G7 disabled
+ *       1  = PBDE on G7 enabled (default)
+ * Value range is [0,1]. Default value is 1
+ */
+LPFC_ATTR_R(enable_pbde, 1, 0, 1, "Enable PBDE support on PRISM");
+
 struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_nvme_info,
 	&dev_attr_bg_info,
@@ -5498,6 +5506,7 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_enable_mds_diags,
 	&dev_attr_lpfc_enable_bbcr,
 	&dev_attr_lpfc_enable_dpp,
+	&dev_attr_lpfc_enable_pbde,
 	NULL,
 };
 
@@ -6514,6 +6523,7 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	lpfc_nvme_io_channel_init(phba, lpfc_nvme_io_channel);
 	lpfc_enable_bbcr_init(phba, lpfc_enable_bbcr);
 	lpfc_enable_dpp_init(phba, lpfc_enable_dpp);
+	lpfc_enable_pbde_init(phba, lpfc_enable_pbde);
 
 	if (phba->sli_rev != LPFC_SLI_REV4) {
 		/* NVME only supported on SLI4 */
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index 150562b79eaa..f2f3b27d0b84 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -10673,18 +10673,10 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 		phba->cfg_enable_fc4_type = LPFC_ENABLE_FCP;
 	}
 
-	/* Only embed PBDE for if_type 6 */
-	if (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) ==
-	    LPFC_SLI_INTF_IF_TYPE_6) {
-		phba->fcp_embed_pbde = 1;
-		phba->nvme_embed_pbde = 1;
-	}
-
-	/* PBDE support requires xib be set */
-	if (!bf_get(cfg_xib, mbx_sli4_parameters)) {
-		phba->fcp_embed_pbde = 0;
-		phba->nvme_embed_pbde = 0;
-	}
+	/* Only embed PBDE for if_type 6, PBDE support requires xib be set */
+	if ((bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
+	    LPFC_SLI_INTF_IF_TYPE_6) || (!bf_get(cfg_xib, mbx_sli4_parameters)))
+		phba->cfg_enable_pbde = 0;
 
 	/*
 	 * To support Suppress Response feature we must satisfy 3 conditions.
@@ -10718,10 +10710,10 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 		phba->fcp_embed_io = 0;
 
 	lpfc_printf_log(phba, KERN_INFO, LOG_INIT | LOG_NVME,
-			"6422 XIB %d: FCP %d %d NVME %d %d %d %d\n",
+			"6422 XIB %d PBDE %d: FCP %d NVME %d %d %d\n",
 			bf_get(cfg_xib, mbx_sli4_parameters),
-			phba->fcp_embed_pbde, phba->fcp_embed_io,
-			phba->nvme_support, phba->nvme_embed_pbde,
+			phba->cfg_enable_pbde,
+			phba->fcp_embed_io, phba->nvme_support,
 			phba->cfg_nvme_embed_cmd, phba->cfg_suppress_rsp);
 
 	if ((bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) ==
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index ada5a2aaee82..4cc6783b6a9f 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1279,6 +1279,8 @@ lpfc_nvme_prep_io_cmd(struct lpfc_vport *vport,
 	/* Word 9 */
 	bf_set(wqe_reqtag, &wqe->generic.wqe_com, pwqeq->iotag);
 
+	/* Words 13 14 15 are for PBDE support */
+
 	pwqeq->vport = vport;
 	return 0;
 }
@@ -1378,7 +1380,7 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 			data_sg = sg_next(data_sg);
 			sgl++;
 		}
-		if (phba->nvme_embed_pbde) {
+		if (phba->cfg_enable_pbde) {
 			/* Use PBDE support for first SGL only, offset == 0 */
 			/* Words 13-15 */
 			bde = (struct ulp_bde64 *)
@@ -1394,10 +1396,8 @@ lpfc_nvme_prep_io_dma(struct lpfc_vport *vport,
 			memset(&wqe->words[13], 0, (sizeof(uint32_t) * 3));
 			bf_set(wqe_pbde, &wqe->generic.wqe_com, 0);
 		}
-	} else {
-		bf_set(wqe_pbde, &wqe->generic.wqe_com, 0);
-		memset(&wqe->words[13], 0, (sizeof(uint32_t) * 3));
 
+	} else {
 		/* For this clause to be valid, the payload_length
 		 * and sg_cnt must zero.
 		 */
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 102c970a00e6..ccb35efef1e1 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -2493,7 +2493,7 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			bf_set(wqe_xc, &wqe->fcp_treceive.wqe_com, 0);
 
 		/* Word 11 - set pbde later */
-		if (phba->nvme_embed_pbde) {
+		if (phba->cfg_enable_pbde) {
 			do_pbde = 1;
 		} else {
 			bf_set(wqe_pbde, &wqe->fcp_treceive.wqe_com, 0);
@@ -2608,16 +2608,19 @@ lpfc_nvmet_prep_fcp_wqe(struct lpfc_hba *phba,
 			bf_set(lpfc_sli4_sge_last, sgl, 1);
 		sgl->word2 = cpu_to_le32(sgl->word2);
 		sgl->sge_len = cpu_to_le32(cnt);
-		if (do_pbde && i == 0) {
+		if (i == 0) {
 			bde = (struct ulp_bde64 *)&wqe->words[13];
-			memset(bde, 0, sizeof(struct ulp_bde64));
-			/* Words 13-15  (PBDE)*/
-			bde->addrLow = sgl->addr_lo;
-			bde->addrHigh = sgl->addr_hi;
-			bde->tus.f.bdeSize =
-				le32_to_cpu(sgl->sge_len);
-			bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
-			bde->tus.w = cpu_to_le32(bde->tus.w);
+			if (do_pbde) {
+				/* Words 13-15  (PBDE) */
+				bde->addrLow = sgl->addr_lo;
+				bde->addrHigh = sgl->addr_hi;
+				bde->tus.f.bdeSize =
+					le32_to_cpu(sgl->sge_len);
+				bde->tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+				bde->tus.w = cpu_to_le32(bde->tus.w);
+			} else {
+				memset(bde, 0, sizeof(struct ulp_bde64));
+			}
 		}
 		sgl++;
 		ctxp->offset += cnt;
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index a94fb9f8bb44..c31c43f43553 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3311,12 +3311,13 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 		}
 		/*
 		 * Setup the first Payload BDE. For FCoE we just key off
-		 * Performance Hints, for FC we utilize fcp_embed_pbde.
+		 * Performance Hints, for FC we use lpfc_enable_pbde.
+		 * We populate words 13-15 of IOCB/WQE.
 		 */
 		if ((phba->sli3_options & LPFC_SLI4_PERFH_ENABLED) ||
-		    phba->fcp_embed_pbde) {
+		    phba->cfg_enable_pbde) {
 			bde = (struct ulp_bde64 *)
-					&(iocb_cmd->unsli3.sli3Words[5]);
+				&(iocb_cmd->unsli3.sli3Words[5]);
 			bde->addrLow = first_data_sgl->addr_lo;
 			bde->addrHigh = first_data_sgl->addr_hi;
 			bde->tus.f.bdeSize =
@@ -3330,6 +3331,13 @@ lpfc_scsi_prep_dma_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd)
 		sgl->word2 = le32_to_cpu(sgl->word2);
 		bf_set(lpfc_sli4_sge_last, sgl, 1);
 		sgl->word2 = cpu_to_le32(sgl->word2);
+
+		if ((phba->sli3_options & LPFC_SLI4_PERFH_ENABLED) ||
+		    phba->cfg_enable_pbde) {
+			bde = (struct ulp_bde64 *)
+				&(iocb_cmd->unsli3.sli3Words[5]);
+			memset(bde, 0, (sizeof(uint32_t) * 3));
+		}
 	}
 
 	/*
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 89ebb07e203d..b55873d50212 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -9117,8 +9117,8 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		}
 		/* Note, word 10 is already initialized to 0 */
 
-		/* Don't set PBDE for Perf hints, just fcp_embed_pbde */
-		if (phba->fcp_embed_pbde)
+		/* Don't set PBDE for Perf hints, just lpfc_enable_pbde */
+		if (phba->cfg_enable_pbde)
 			bf_set(wqe_pbde, &wqe->fcp_iwrite.wqe_com, 1);
 		else
 			bf_set(wqe_pbde, &wqe->fcp_iwrite.wqe_com, 0);
@@ -9181,8 +9181,8 @@ lpfc_sli4_iocb2wqe(struct lpfc_hba *phba, struct lpfc_iocbq *iocbq,
 		}
 		/* Note, word 10 is already initialized to 0 */
 
-		/* Don't set PBDE for Perf hints, just fcp_embed_pbde */
-		if (phba->fcp_embed_pbde)
+		/* Don't set PBDE for Perf hints, just lpfc_enable_pbde */
+		if (phba->cfg_enable_pbde)
 			bf_set(wqe_pbde, &wqe->fcp_iread.wqe_com, 1);
 		else
 			bf_set(wqe_pbde, &wqe->fcp_iread.wqe_com, 0);
-- 
cgit v1.2.3


From 66e9e6bf07cb0a2d4bbccebf6a6f1f27e6768e38 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:27 -0700
Subject: scsi: lpfc: Support duration field in Link Cable Beacon V1 command

Current implementation missed setting the duration field. Correct the code
to set the field.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_els.c  | 64 +++++++++++++++++++++++++++++++------------
 drivers/scsi/lpfc/lpfc_hw.h   | 18 +++++++-----
 drivers/scsi/lpfc/lpfc_hw4.h  | 46 ++++++++++++++++++++++++++++---
 drivers/scsi/lpfc/lpfc_init.c |  1 +
 drivers/scsi/lpfc/lpfc_sli4.h |  3 ++
 5 files changed, 104 insertions(+), 28 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 6d84a10fef07..4683154842f5 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -5640,8 +5640,9 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 				" mbx status x%x\n",
 				shdr_status, shdr_add_status, mb->mbxStatus);
 
-	if (mb->mbxStatus && !(shdr_status &&
-		shdr_add_status == ADD_STATUS_OPERATION_ALREADY_ACTIVE)) {
+	if ((mb->mbxStatus != MBX_SUCCESS) || shdr_status ||
+	    (shdr_add_status == ADD_STATUS_OPERATION_ALREADY_ACTIVE) ||
+	    (shdr_add_status == ADD_STATUS_INVALID_REQUEST)) {
 		mempool_free(pmb, phba->mbox_mem_pool);
 		goto error;
 	}
@@ -5670,6 +5671,7 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lcb_res->lcb_sub_command = lcb_context->sub_command;
 	lcb_res->lcb_type = lcb_context->type;
 	lcb_res->lcb_frequency = lcb_context->frequency;
+	lcb_res->lcb_duration = lcb_context->duration;
 	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
 	phba->fc_stat.elsXmitACC++;
 	rc = lpfc_sli_issue_iocb(phba, LPFC_ELS_RING, elsiocb, 0);
@@ -5712,6 +5714,7 @@ lpfc_sli4_set_beacon(struct lpfc_vport *vport,
 		     uint32_t beacon_state)
 {
 	struct lpfc_hba *phba = vport->phba;
+	union lpfc_sli4_cfg_shdr *cfg_shdr;
 	LPFC_MBOXQ_t *mbox = NULL;
 	uint32_t len;
 	int rc;
@@ -5720,6 +5723,7 @@ lpfc_sli4_set_beacon(struct lpfc_vport *vport,
 	if (!mbox)
 		return 1;
 
+	cfg_shdr = &mbox->u.mqe.un.sli4_config.header.cfg_shdr;
 	len = sizeof(struct lpfc_mbx_set_beacon_config) -
 		sizeof(struct lpfc_sli4_cfg_mhdr);
 	lpfc_sli4_config(phba, mbox, LPFC_MBOX_SUBSYSTEM_COMMON,
@@ -5732,8 +5736,40 @@ lpfc_sli4_set_beacon(struct lpfc_vport *vport,
 	       phba->sli4_hba.physical_port);
 	bf_set(lpfc_mbx_set_beacon_state, &mbox->u.mqe.un.beacon_config,
 	       beacon_state);
-	bf_set(lpfc_mbx_set_beacon_port_type, &mbox->u.mqe.un.beacon_config, 1);
-	bf_set(lpfc_mbx_set_beacon_duration, &mbox->u.mqe.un.beacon_config, 0);
+	mbox->u.mqe.un.beacon_config.word5 = 0;		/* Reserved */
+
+	/*
+	 *	Check bv1s bit before issuing the mailbox
+	 *	if bv1s == 1, LCB V1 supported
+	 *	else, LCB V0 supported
+	 */
+
+	if (phba->sli4_hba.pc_sli4_params.bv1s) {
+		/* COMMON_SET_BEACON_CONFIG_V1 */
+		cfg_shdr->request.word9 = BEACON_VERSION_V1;
+		lcb_context->capability |= LCB_CAPABILITY_DURATION;
+		bf_set(lpfc_mbx_set_beacon_port_type,
+		       &mbox->u.mqe.un.beacon_config, 0);
+		bf_set(lpfc_mbx_set_beacon_duration_v1,
+		       &mbox->u.mqe.un.beacon_config,
+		       be16_to_cpu(lcb_context->duration));
+	} else {
+		/* COMMON_SET_BEACON_CONFIG_V0 */
+		if (be16_to_cpu(lcb_context->duration) != 0) {
+			mempool_free(mbox, phba->mbox_mem_pool);
+			return 1;
+		}
+		cfg_shdr->request.word9 = BEACON_VERSION_V0;
+		lcb_context->capability &=  ~(LCB_CAPABILITY_DURATION);
+		bf_set(lpfc_mbx_set_beacon_state,
+		       &mbox->u.mqe.un.beacon_config, beacon_state);
+		bf_set(lpfc_mbx_set_beacon_port_type,
+		       &mbox->u.mqe.un.beacon_config, 1);
+		bf_set(lpfc_mbx_set_beacon_duration,
+		       &mbox->u.mqe.un.beacon_config,
+		       be16_to_cpu(lcb_context->duration));
+	}
+
 	rc = lpfc_sli_issue_mbox(phba, mbox, MBX_NOWAIT);
 	if (rc == MBX_NOT_FINISHED) {
 		mempool_free(mbox, phba->mbox_mem_pool);
@@ -5784,24 +5820,16 @@ lpfc_els_rcv_lcb(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 			beacon->lcb_frequency,
 			be16_to_cpu(beacon->lcb_duration));
 
-	if (phba->sli_rev < LPFC_SLI_REV4 ||
-	    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) !=
-	    LPFC_SLI_INTF_IF_TYPE_2)) {
-		rjt_err = LSRJT_CMD_UNSUPPORTED;
-		goto rjt;
-	}
-
-	if (phba->hba_flag & HBA_FCOE_MODE) {
-		rjt_err = LSRJT_CMD_UNSUPPORTED;
-		goto rjt;
-	}
 	if (beacon->lcb_sub_command != LPFC_LCB_ON &&
 	    beacon->lcb_sub_command != LPFC_LCB_OFF) {
 		rjt_err = LSRJT_CMD_UNSUPPORTED;
 		goto rjt;
 	}
-	if (beacon->lcb_sub_command == LPFC_LCB_ON &&
-	    be16_to_cpu(beacon->lcb_duration) != 0) {
+
+	if (phba->sli_rev < LPFC_SLI_REV4  ||
+	    phba->hba_flag & HBA_FCOE_MODE ||
+	    (bf_get(lpfc_sli_intf_if_type, &phba->sli4_hba.sli_intf) <
+	    LPFC_SLI_INTF_IF_TYPE_2)) {
 		rjt_err = LSRJT_CMD_UNSUPPORTED;
 		goto rjt;
 	}
@@ -5814,8 +5842,10 @@ lpfc_els_rcv_lcb(struct lpfc_vport *vport, struct lpfc_iocbq *cmdiocb,
 
 	state = (beacon->lcb_sub_command == LPFC_LCB_ON) ? 1 : 0;
 	lcb_context->sub_command = beacon->lcb_sub_command;
+	lcb_context->capability	= 0;
 	lcb_context->type = beacon->lcb_type;
 	lcb_context->frequency = beacon->lcb_frequency;
+	lcb_context->duration = beacon->lcb_duration;
 	lcb_context->ox_id = cmdiocb->iocb.unsli3.rcvsli3.ox_id;
 	lcb_context->rx_id = cmdiocb->iocb.ulpContext;
 	lcb_context->ndlp = lpfc_nlp_get(ndlp);
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index 08a3f1520159..f6dcabe27ca1 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -1065,14 +1065,17 @@ typedef struct _ELS_PKT {	/* Structure is in Big Endian format */
 struct fc_lcb_request_frame {
 	uint32_t      lcb_command;      /* ELS command opcode (0x81)     */
 	uint8_t       lcb_sub_command;/* LCB Payload Word 1, bit 24:31 */
-#define LPFC_LCB_ON    0x1
-#define LPFC_LCB_OFF   0x2
-	uint8_t       reserved[3];
-
+#define LPFC_LCB_ON		0x1
+#define LPFC_LCB_OFF		0x2
+	uint8_t       reserved[2];
+	uint8_t	      capability;	/* LCB Payload Word 1, bit 0:7 */
 	uint8_t       lcb_type; /* LCB Payload Word 2, bit 24:31 */
-#define LPFC_LCB_GREEN 0x1
-#define LPFC_LCB_AMBER 0x2
+#define LPFC_LCB_GREEN		0x1
+#define LPFC_LCB_AMBER		0x2
 	uint8_t       lcb_frequency;    /* LCB Payload Word 2, bit 16:23 */
+#define LCB_CAPABILITY_DURATION	1
+#define BEACON_VERSION_V1	1
+#define BEACON_VERSION_V0	0
 	uint16_t      lcb_duration;     /* LCB Payload Word 2, bit 15:0  */
 };
 
@@ -1082,7 +1085,8 @@ struct fc_lcb_request_frame {
 struct fc_lcb_res_frame {
 	uint32_t      lcb_ls_acc;       /* Acceptance of LCB request (0x02) */
 	uint8_t       lcb_sub_command;/* LCB Payload Word 1, bit 24:31 */
-	uint8_t       reserved[3];
+	uint8_t       reserved[2];
+	uint8_t	      capability;	/* LCB Payload Word 1, bit 0:7 */
 	uint8_t       lcb_type; /* LCB Payload Word 2, bit 24:31 */
 	uint8_t       lcb_frequency;    /* LCB Payload Word 2, bit 16:23 */
 	uint16_t      lcb_duration;     /* LCB Payload Word 2, bit 15:0  */
diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
index f43f0bacb77a..083f8c8706e5 100644
--- a/drivers/scsi/lpfc/lpfc_hw4.h
+++ b/drivers/scsi/lpfc/lpfc_hw4.h
@@ -1790,9 +1790,12 @@ struct lpfc_mbx_set_beacon_config {
 #define lpfc_mbx_set_beacon_duration_SHIFT		16
 #define lpfc_mbx_set_beacon_duration_MASK		0x000000FF
 #define lpfc_mbx_set_beacon_duration_WORD		word4
-#define lpfc_mbx_set_beacon_status_duration_SHIFT	24
-#define lpfc_mbx_set_beacon_status_duration_MASK	0x000000FF
-#define lpfc_mbx_set_beacon_status_duration_WORD	word4
+
+/* COMMON_SET_BEACON_CONFIG_V1 */
+#define lpfc_mbx_set_beacon_duration_v1_SHIFT		16
+#define lpfc_mbx_set_beacon_duration_v1_MASK		0x0000FFFF
+#define lpfc_mbx_set_beacon_duration_v1_WORD		word4
+	uint32_t word5;  /* RESERVED  */
 };
 
 struct lpfc_id_range {
@@ -2243,6 +2246,7 @@ struct lpfc_mbx_redisc_fcf_tbl {
  */
 #define ADD_STATUS_OPERATION_ALREADY_ACTIVE		0x67
 #define ADD_STATUS_FW_NOT_SUPPORTED			0xEB
+#define ADD_STATUS_INVALID_REQUEST			0x4B
 
 struct lpfc_mbx_sli4_config {
 	struct mbox_header header;
@@ -3392,7 +3396,41 @@ struct lpfc_sli4_parameters {
 #define cfg_nosr_SHIFT				9
 #define cfg_nosr_MASK				0x00000001
 #define cfg_nosr_WORD				word19
-#define LPFC_NODELAY_MAX_IO		32
+
+#define cfg_bv1s_SHIFT                          10
+#define cfg_bv1s_MASK                           0x00000001
+#define cfg_bv1s_WORD                           word19
+
+	uint32_t word20;
+#define cfg_max_tow_xri_SHIFT			0
+#define cfg_max_tow_xri_MASK			0x0000ffff
+#define cfg_max_tow_xri_WORD			word20
+
+	uint32_t word21;                        /* RESERVED */
+	uint32_t word22;                        /* RESERVED */
+	uint32_t word23;                        /* RESERVED */
+
+	uint32_t word24;
+#define cfg_frag_field_offset_SHIFT		0
+#define cfg_frag_field_offset_MASK		0x0000ffff
+#define cfg_frag_field_offset_WORD		word24
+
+#define cfg_frag_field_size_SHIFT		16
+#define cfg_frag_field_size_MASK		0x0000ffff
+#define cfg_frag_field_size_WORD		word24
+
+	uint32_t word25;
+#define cfg_sgl_field_offset_SHIFT		0
+#define cfg_sgl_field_offset_MASK		0x0000ffff
+#define cfg_sgl_field_offset_WORD		word25
+
+#define cfg_sgl_field_size_SHIFT		16
+#define cfg_sgl_field_size_MASK			0x0000ffff
+#define cfg_sgl_field_size_WORD			word25
+
+	uint32_t word26;	/* Chain SGE initial value LOW  */
+	uint32_t word27;	/* Chain SGE initial value HIGH */
+#define LPFC_NODELAY_MAX_IO			32
 };
 
 #define LPFC_SET_UE_RECOVERY		0x10
diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
index f2f3b27d0b84..f3cae733ae2d 100644
--- a/drivers/scsi/lpfc/lpfc_init.c
+++ b/drivers/scsi/lpfc/lpfc_init.c
@@ -10644,6 +10644,7 @@ lpfc_get_sli4_parameters(struct lpfc_hba *phba, LPFC_MBOXQ_t *mboxq)
 	sli4_params->eqav = bf_get(cfg_eqav, mbx_sli4_parameters);
 	sli4_params->cqav = bf_get(cfg_cqav, mbx_sli4_parameters);
 	sli4_params->wqsize = bf_get(cfg_wqsize, mbx_sli4_parameters);
+	sli4_params->bv1s = bf_get(cfg_bv1s, mbx_sli4_parameters);
 	sli4_params->sgl_pages_max = bf_get(cfg_sgl_page_cnt,
 					    mbx_sli4_parameters);
 	sli4_params->wqpcnt = bf_get(cfg_wqpcnt, mbx_sli4_parameters);
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index cf64aca82bd0..ada68de970b3 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -490,6 +490,7 @@ struct lpfc_pc_sli4_params {
 	uint8_t eqav;
 	uint8_t cqav;
 	uint8_t wqsize;
+	uint8_t bv1s;
 #define LPFC_WQ_SZ64_SUPPORT	1
 #define LPFC_WQ_SZ128_SUPPORT	2
 	uint8_t wqpcnt;
@@ -774,7 +775,9 @@ struct lpfc_rdp_context {
 struct lpfc_lcb_context {
 	uint8_t  sub_command;
 	uint8_t  type;
+	uint8_t  capability;
 	uint8_t  frequency;
+	uint16_t  duration;
 	uint16_t ox_id;
 	uint16_t rx_id;
 	struct lpfc_nodelist *ndlp;
-- 
cgit v1.2.3


From 6871e8144f935a1f08e7fc6269c894861ce494aa Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:28 -0700
Subject: scsi: lpfc: Fix NVME Target crash in defer rcv logic

Kernel occasionally crashed with the following
ops on NVME Target:
  BUG: unable to handle kernel NULL pointer dereference at 0000000000000058
  IP: [<ffffffffa042ee50>] lpfc_nvmet_defer_rcv+0x50/0x70 [lpfc]

Callback routine was called for deferred rcv when it should be treated as a
normal rcv.

Added code in callback routine to detect this condition and log a message,
then bail.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_nvmet.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index ccb35efef1e1..ff994712f58a 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -402,6 +402,7 @@ lpfc_nvmet_ctxbuf_post(struct lpfc_hba *phba, struct lpfc_nvmet_ctxbuf *ctx_buf)
 
 		/* Process FCP command */
 		if (rc == 0) {
+			ctxp->rqb_buffer = NULL;
 			atomic_inc(&tgtp->rcv_fcp_cmd_out);
 			nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
 			return;
@@ -1116,8 +1117,17 @@ lpfc_nvmet_defer_rcv(struct nvmet_fc_target_port *tgtport,
 	lpfc_nvmeio_data(phba, "NVMET DEFERRCV: xri x%x sz %d CPU %02x\n",
 			 ctxp->oxid, ctxp->size, smp_processor_id());
 
+	if (!nvmebuf) {
+		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_IOERR,
+				"6425 Defer rcv: no buffer xri x%x: "
+				"flg %x ste %x\n",
+				ctxp->oxid, ctxp->flag, ctxp->state);
+		return;
+	}
+
 	tgtp = phba->targetport->private;
-	atomic_inc(&tgtp->rcv_fcp_cmd_defer);
+	if (tgtp)
+		atomic_inc(&tgtp->rcv_fcp_cmd_defer);
 
 	/* Free the nvmebuf since a new buffer already replaced it */
 	nvmebuf->hrq->rqbp->rqb_free_buffer(phba, nvmebuf);
-- 
cgit v1.2.3


From b0e830125b669570d8096b8ba22eb00f659fc05e Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:29 -0700
Subject: scsi: lpfc: devloss timeout race condition caused null pointer
 reference

A race condition between the context of devloss timeout handler and I/O
completion caused devloss timeout handler de-referencing pointer that had
been released.

Added the check in lpfc_sli_validate_fcp_iocb() on LPFC_IO_ON_TXCMPLQ to
capture the race condition of I/O completion and devloss timeout handler
attemption for aborting the I/O. Also, added check on lpfc_cmd->rdata
pointer before de-referenceing lpfc_cmd->rdata->pnode.

Also, added protection in lpfc_sli_abort_iocb() routine on driver performed
FCP I/O FLUSHING already under way before proceeding to aborting I/Os.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_scsi.c |  5 +++++
 drivers/scsi/lpfc/lpfc_sli.c  | 13 +++++++++----
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index c31c43f43553..5e4cad6a531a 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -4538,6 +4538,11 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	int err;
 
 	rdata = lpfc_rport_data_from_scsi_device(cmnd->device);
+
+	/* sanity check on references */
+	if (unlikely(!rdata) || unlikely(!rport))
+		goto out_fail_command;
+
 	err = fc_remote_port_chkready(rport);
 	if (err) {
 		cmnd->result = err;
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index b55873d50212..72500dcb13a9 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -11091,10 +11091,11 @@ lpfc_sli_validate_fcp_iocb(struct lpfc_iocbq *iocbq, struct lpfc_vport *vport,
 	struct lpfc_scsi_buf *lpfc_cmd;
 	int rc = 1;
 
-	if (!(iocbq->iocb_flag &  LPFC_IO_FCP))
+	if (iocbq->vport != vport)
 		return rc;
 
-	if (iocbq->vport != vport)
+	if (!(iocbq->iocb_flag &  LPFC_IO_FCP) ||
+	    !(iocbq->iocb_flag & LPFC_IO_ON_TXCMPLQ))
 		return rc;
 
 	lpfc_cmd = container_of(iocbq, struct lpfc_scsi_buf, cur_iocbq);
@@ -11104,13 +11105,13 @@ lpfc_sli_validate_fcp_iocb(struct lpfc_iocbq *iocbq, struct lpfc_vport *vport,
 
 	switch (ctx_cmd) {
 	case LPFC_CTX_LUN:
-		if ((lpfc_cmd->rdata->pnode) &&
+		if ((lpfc_cmd->rdata) && (lpfc_cmd->rdata->pnode) &&
 		    (lpfc_cmd->rdata->pnode->nlp_sid == tgt_id) &&
 		    (scsilun_to_int(&lpfc_cmd->fcp_cmnd->fcp_lun) == lun_id))
 			rc = 0;
 		break;
 	case LPFC_CTX_TGT:
-		if ((lpfc_cmd->rdata->pnode) &&
+		if ((lpfc_cmd->rdata) && (lpfc_cmd->rdata->pnode) &&
 		    (lpfc_cmd->rdata->pnode->nlp_sid == tgt_id))
 			rc = 0;
 		break;
@@ -11225,6 +11226,10 @@ lpfc_sli_abort_iocb(struct lpfc_vport *vport, struct lpfc_sli_ring *pring,
 	int errcnt = 0, ret_val = 0;
 	int i;
 
+	/* all I/Os are in process of being flushed */
+	if (phba->hba_flag & HBA_FCP_IOQ_FLUSH)
+		return errcnt;
+
 	for (i = 1; i <= phba->sli.last_iotag; i++) {
 		iocbq = phba->sli.iocbq_lookup[i];
 
-- 
cgit v1.2.3


From 3e1ebadd889f2670ecef77157d84261d09a5ca41 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:30 -0700
Subject: scsi: lpfc: update driver version to 12.0.0.5

Update the driver version to 12.0.0.5

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_version.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 18c23afcf46b..30591e6364ec 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.0.0.4"
+#define LPFC_DRIVER_VERSION "12.0.0.5"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
-- 
cgit v1.2.3


From 4ae2ebde318fc120bc91c65a0127b6a225b2d6ed Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 26 Jun 2018 08:24:31 -0700
Subject: scsi: lpfc: Revise copyright for new company language

Change references from "Broadcom Limited" to "Broadcom Inc." in the
copyright message. Update copyright duration if not yet updated for 2018.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/Makefile         | 4 ++--
 drivers/scsi/lpfc/lpfc.h           | 2 +-
 drivers/scsi/lpfc/lpfc_attr.h      | 4 ++--
 drivers/scsi/lpfc/lpfc_bsg.c       | 2 +-
 drivers/scsi/lpfc/lpfc_bsg.h       | 4 ++--
 drivers/scsi/lpfc/lpfc_compat.h    | 4 ++--
 drivers/scsi/lpfc/lpfc_crtn.h      | 2 +-
 drivers/scsi/lpfc/lpfc_ct.c        | 2 +-
 drivers/scsi/lpfc/lpfc_debugfs.h   | 2 +-
 drivers/scsi/lpfc/lpfc_disc.h      | 4 ++--
 drivers/scsi/lpfc/lpfc_els.c       | 2 +-
 drivers/scsi/lpfc/lpfc_hbadisc.c   | 2 +-
 drivers/scsi/lpfc/lpfc_hw.h        | 2 +-
 drivers/scsi/lpfc/lpfc_ids.h       | 2 +-
 drivers/scsi/lpfc/lpfc_logmsg.h    | 4 ++--
 drivers/scsi/lpfc/lpfc_mbox.c      | 2 +-
 drivers/scsi/lpfc/lpfc_mem.c       | 2 +-
 drivers/scsi/lpfc/lpfc_nl.h        | 4 ++--
 drivers/scsi/lpfc/lpfc_nportdisc.c | 2 +-
 drivers/scsi/lpfc/lpfc_nvmet.c     | 2 +-
 drivers/scsi/lpfc/lpfc_nvmet.h     | 2 +-
 drivers/scsi/lpfc/lpfc_sli.h       | 4 ++--
 drivers/scsi/lpfc/lpfc_sli4.h      | 2 +-
 drivers/scsi/lpfc/lpfc_version.h   | 4 ++--
 drivers/scsi/lpfc/lpfc_vport.c     | 4 ++--
 drivers/scsi/lpfc/lpfc_vport.h     | 4 ++--
 26 files changed, 37 insertions(+), 37 deletions(-)

diff --git a/drivers/scsi/lpfc/Makefile b/drivers/scsi/lpfc/Makefile
index cb6aa802c48e..092a971d066b 100644
--- a/drivers/scsi/lpfc/Makefile
+++ b/drivers/scsi/lpfc/Makefile
@@ -1,8 +1,8 @@
 #/*******************************************************************
 # * This file is part of the Emulex Linux Device Driver for         *
 # * Fibre Channel Host Bus Adapters.                                *
-# * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
-# * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+# * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+# * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
 # * Copyright (C) 2004-2012 Emulex.  All rights reserved.           *
 # * EMULEX and SLI are trademarks of Emulex.                        *
 # * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc.h b/drivers/scsi/lpfc/lpfc.h
index fc580a9b2bae..e0d0da5f43d6 100644
--- a/drivers/scsi/lpfc/lpfc.h
+++ b/drivers/scsi/lpfc/lpfc.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_attr.h b/drivers/scsi/lpfc/lpfc_attr.h
index 931db52692f5..9659a8fff971 100644
--- a/drivers/scsi/lpfc/lpfc_attr.h
+++ b/drivers/scsi/lpfc/lpfc_attr.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
index edb1a18a6414..90745feca808 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.c
+++ b/drivers/scsi/lpfc/lpfc_bsg.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2009-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_bsg.h b/drivers/scsi/lpfc/lpfc_bsg.h
index e7d95a4e8042..32347c87e3b4 100644
--- a/drivers/scsi/lpfc/lpfc_bsg.h
+++ b/drivers/scsi/lpfc/lpfc_bsg.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2010-2015 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_compat.h b/drivers/scsi/lpfc/lpfc_compat.h
index 6b32b0ae7506..43cf46a3a71f 100644
--- a/drivers/scsi/lpfc/lpfc_compat.h
+++ b/drivers/scsi/lpfc/lpfc_compat.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2011 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index 4ae9ba425e78..d02b4b860110 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c
index d4a200ae5a6f..1cbdc892ff95 100644
--- a/drivers/scsi/lpfc/lpfc_ct.c
+++ b/drivers/scsi/lpfc/lpfc_ct.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_debugfs.h b/drivers/scsi/lpfc/lpfc_debugfs.h
index f32eaeb2225a..30efc7bf91bd 100644
--- a/drivers/scsi/lpfc/lpfc_debugfs.h
+++ b/drivers/scsi/lpfc/lpfc_debugfs.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2007-2011 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 5a7547f9d8d8..376f02819f20 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2013 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index 4683154842f5..df655f1284d0 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
index 2fef54fab86d..eb71877f12f8 100644
--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
+++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h
index f6dcabe27ca1..009aa0eee040 100644
--- a/drivers/scsi/lpfc/lpfc_hw.h
+++ b/drivers/scsi/lpfc/lpfc_hw.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_ids.h b/drivers/scsi/lpfc/lpfc_ids.h
index 07ee34017d88..d48414e295a0 100644
--- a/drivers/scsi/lpfc/lpfc_ids.h
+++ b/drivers/scsi/lpfc/lpfc_ids.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_logmsg.h b/drivers/scsi/lpfc/lpfc_logmsg.h
index 3b654ad08d1f..ea10f03437f5 100644
--- a/drivers/scsi/lpfc/lpfc_logmsg.h
+++ b/drivers/scsi/lpfc/lpfc_logmsg.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2009 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_mbox.c b/drivers/scsi/lpfc/lpfc_mbox.c
index 47c02da11f01..deb094fdbb79 100644
--- a/drivers/scsi/lpfc/lpfc_mbox.c
+++ b/drivers/scsi/lpfc/lpfc_mbox.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_mem.c b/drivers/scsi/lpfc/lpfc_mem.c
index 0758edb9dfe2..9c22a2c93462 100644
--- a/drivers/scsi/lpfc/lpfc_mem.c
+++ b/drivers/scsi/lpfc/lpfc_mem.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2014 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_nl.h b/drivers/scsi/lpfc/lpfc_nl.h
index b93e78f671fb..95d60ab5ebf9 100644
--- a/drivers/scsi/lpfc/lpfc_nl.h
+++ b/drivers/scsi/lpfc/lpfc_nl.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2010 Emulex.  All rights reserved.                *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 1a803975bcbc..1f0a7d7dbc54 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index ff994712f58a..22f8a204b69f 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channsel Host Bus Adapters.                               *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_nvmet.h b/drivers/scsi/lpfc/lpfc_nvmet.h
index 81f520abfd64..1aaff63f1f41 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.h
+++ b/drivers/scsi/lpfc/lpfc_nvmet.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_sli.h b/drivers/scsi/lpfc/lpfc_sli.h
index 80b191d73190..34b7ab69b9b4 100644
--- a/drivers/scsi/lpfc/lpfc_sli.h
+++ b/drivers/scsi/lpfc/lpfc_sli.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_sli4.h b/drivers/scsi/lpfc/lpfc_sli4.h
index ada68de970b3..399c0015c546 100644
--- a/drivers/scsi/lpfc/lpfc_sli4.h
+++ b/drivers/scsi/lpfc/lpfc_sli4.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2009-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index 30591e6364ec..a669af45fce7 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -2,7 +2,7 @@
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
  * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
- * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.  *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
@@ -33,5 +33,5 @@
 #define LPFC_MODULE_DESC "Emulex LightPulse Fibre Channel SCSI driver " \
 		LPFC_DRIVER_VERSION
 #define LPFC_COPYRIGHT "Copyright (C) 2017-2018 Broadcom. All Rights " \
-		"Reserved. The term \"Broadcom\" refers to Broadcom Limited " \
+		"Reserved. The term \"Broadcom\" refers to Broadcom Inc. " \
 		"and/or its subsidiaries."
diff --git a/drivers/scsi/lpfc/lpfc_vport.c b/drivers/scsi/lpfc/lpfc_vport.c
index 81bc12dedf41..1ff0f7de9105 100644
--- a/drivers/scsi/lpfc/lpfc_vport.c
+++ b/drivers/scsi/lpfc/lpfc_vport.c
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2016 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
diff --git a/drivers/scsi/lpfc/lpfc_vport.h b/drivers/scsi/lpfc/lpfc_vport.h
index 62295971f66c..f4b8528dd2e7 100644
--- a/drivers/scsi/lpfc/lpfc_vport.h
+++ b/drivers/scsi/lpfc/lpfc_vport.h
@@ -1,8 +1,8 @@
 /*******************************************************************
  * This file is part of the Emulex Linux Device Driver for         *
  * Fibre Channel Host Bus Adapters.                                *
- * Copyright (C) 2017 Broadcom. All Rights Reserved. The term      *
- * “Broadcom” refers to Broadcom Limited and/or its subsidiaries.  *
+ * Copyright (C) 2017-2018 Broadcom. All Rights Reserved. The term *
+ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.     *
  * Copyright (C) 2004-2006 Emulex.  All rights reserved.           *
  * EMULEX and SLI are trademarks of Emulex.                        *
  * www.broadcom.com                                                *
-- 
cgit v1.2.3


From 14b470b56840dbb093abd71f214e9d63770c87b8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 6 Jul 2018 22:19:07 +0200
Subject: scsi: target: sbitmap: add seq_file forward declaration

The target core runs into a warning in the linux/sbitmap.h
file in some configurations:

In file included from include/target/target_core_base.h:7,
                 from drivers/target/target_core_fabric_lib.c:41:
include/linux/sbitmap.h:331:46: error: 'struct seq_file' declared inside parameter list will not be visible outside of this definition or declaration [-Werror]
 void sbitmap_show(struct sbitmap *sb, struct seq_file *m);
                                              ^~~~~~~~

In general, headers should not depend on others being included first,
so this fixes it with a forward declaration for that struct name, but
we probably want to merge the patch through the scsi tree to help
bisection.

Fixes: 10e9cbb6b531 ("scsi: target: Convert target drivers to use sbitmap")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Omar Sandoval <osandov@fb.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 include/linux/sbitmap.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index e6539536dea9..804a50983ec5 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -23,6 +23,8 @@
 #include <linux/kernel.h>
 #include <linux/slab.h>
 
+struct seq_file;
+
 /**
  * struct sbitmap_word - Word in a &struct sbitmap.
  */
-- 
cgit v1.2.3


From fc21ae8927f391b6e3944f82e417355da5d06a83 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 3 Jul 2018 17:20:03 -0500
Subject: scsi: mptfusion: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases where
we are expecting to fall through.

Warning level 2 was used: -Wimplicit-fallthrough=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/message/fusion/mptbase.c | 3 +++
 drivers/message/fusion/mptsas.c  | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index a625ac4e2872..c8c8186f1148 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -642,6 +642,7 @@ mptbase_reply(MPT_ADAPTER *ioc, MPT_FRAME_HDR *req, MPT_FRAME_HDR *reply)
 			freereq = 0;
 		if (event != MPI_EVENT_EVENT_CHANGE)
 			break;
+		/* else: fall through */
 	case MPI_FUNCTION_CONFIG:
 	case MPI_FUNCTION_SAS_IO_UNIT_CONTROL:
 		ioc->mptbase_cmds.status |= MPT_MGMT_STATUS_COMMAND_GOOD;
@@ -1886,6 +1887,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	case MPI_MANUFACTPAGE_DEVICEID_FC939X:
 	case MPI_MANUFACTPAGE_DEVICEID_FC949X:
 		ioc->errata_flag_1064 = 1;
+		/* fall through */
 	case MPI_MANUFACTPAGE_DEVICEID_FC909:
 	case MPI_MANUFACTPAGE_DEVICEID_FC929:
 	case MPI_MANUFACTPAGE_DEVICEID_FC919:
@@ -1930,6 +1932,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 			pcixcmd &= 0x8F;
 			pci_write_config_byte(pdev, 0x6a, pcixcmd);
 		}
+		/* fall through */
 
 	case MPI_MANUFACTPAGE_DEVID_1030_53C1035:
 		ioc->bus_type = SPI;
diff --git a/drivers/message/fusion/mptsas.c b/drivers/message/fusion/mptsas.c
index 76a66da33996..b8cf2658649e 100644
--- a/drivers/message/fusion/mptsas.c
+++ b/drivers/message/fusion/mptsas.c
@@ -4327,6 +4327,7 @@ mptsas_hotplug_work(MPT_ADAPTER *ioc, struct fw_event_work *fw_event,
 			}
 		}
 		mpt_findImVolumes(ioc);
+		/* fall through */
 
 	case MPTSAS_ADD_DEVICE:
 		memset(&sas_device, 0, sizeof(struct mptsas_devinfo));
-- 
cgit v1.2.3


From d5038a13eca72fb216c07eb717169092e92284f1 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Wed, 4 Jul 2018 10:53:56 +0200
Subject: scsi: core: switch to scsi-mq by default

It has been more than one year since we tried to change the default from
legacy to multi queue in SCSI with commit c279bd9e406 ("scsi: default to
scsi-mq"). But due to issues with suspend/resume and performance problems
it had been reverted again with commit cbe7dfa26eee ("Revert "scsi: default
to scsi-mq"").

In the meantime there have been a substantial amount of performance
improvements and suspend/resume got fixed as well, thus we can re-enable
scsi-mq without a significant performance penalty.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Acked-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index 35c909bbf8ba..bd115bab162e 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -49,6 +49,7 @@ config SCSI_NETLINK
 
 config SCSI_MQ_DEFAULT
 	bool "SCSI: use blk-mq I/O path by default"
+	default y
 	depends on SCSI
 	---help---
 	  This option enables the new blk-mq based I/O path for SCSI
-- 
cgit v1.2.3


From ee35624e1e4e4e9a26a30d56c25a07ba9cdd8ecb Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 4 Jul 2018 13:56:48 +0200
Subject: scsi: libfc: Add lockdep annotations

Convert the free text locking notes into proper lockdep annotations.

Signed-off-by: Hannes Reinecke <hare@suse.com>
Acked-by: Johannes Thumshirn <jth@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libfc/fc_disc.c  |  32 +++++--------
 drivers/scsi/libfc/fc_lport.c | 108 +++++++++++++++++-------------------------
 drivers/scsi/libfc/fc_rport.c |  99 +++++++++++++++++---------------------
 3 files changed, 99 insertions(+), 140 deletions(-)

diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 3f3569ec5ce3..6125df787200 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -59,9 +59,6 @@ static void fc_disc_restart(struct fc_disc *);
 /**
  * fc_disc_stop_rports() - Delete all the remote ports associated with the lport
  * @disc: The discovery job to stop remote ports on
- *
- * Locking Note: This function expects that the lport mutex is locked before
- * calling it.
  */
 static void fc_disc_stop_rports(struct fc_disc *disc)
 {
@@ -69,6 +66,7 @@ static void fc_disc_stop_rports(struct fc_disc *disc)
 	struct fc_rport_priv *rdata;
 
 	lport = fc_disc_lport(disc);
+	lockdep_assert_held(&lport->lp_mutex);
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
@@ -84,9 +82,6 @@ static void fc_disc_stop_rports(struct fc_disc *disc)
  * fc_disc_recv_rscn_req() - Handle Registered State Change Notification (RSCN)
  * @disc:  The discovery object to which the RSCN applies
  * @fp:	   The RSCN frame
- *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  */
 static void fc_disc_recv_rscn_req(struct fc_disc *disc, struct fc_frame *fp)
 {
@@ -101,6 +96,8 @@ static void fc_disc_recv_rscn_req(struct fc_disc *disc, struct fc_frame *fp)
 	LIST_HEAD(disc_ports);
 	struct fc_disc_port *dp, *next;
 
+	lockdep_assert_held(&disc->disc_mutex);
+
 	lport = fc_disc_lport(disc);
 
 	FC_DISC_DBG(disc, "Received an RSCN event\n");
@@ -220,12 +217,11 @@ static void fc_disc_recv_req(struct fc_lport *lport, struct fc_frame *fp)
 /**
  * fc_disc_restart() - Restart discovery
  * @disc: The discovery object to be restarted
- *
- * Locking Note: This function expects that the disc mutex
- *		 is already locked.
  */
 static void fc_disc_restart(struct fc_disc *disc)
 {
+	lockdep_assert_held(&disc->disc_mutex);
+
 	if (!disc->disc_callback)
 		return;
 
@@ -271,16 +267,13 @@ static void fc_disc_start(void (*disc_callback)(struct fc_lport *,
  * fc_disc_done() - Discovery has been completed
  * @disc:  The discovery context
  * @event: The discovery completion status
- *
- * Locking Note: This function expects that the disc mutex is locked before
- * it is called. The discovery callback is then made with the lock released,
- * and the lock is re-taken before returning from this function
  */
 static void fc_disc_done(struct fc_disc *disc, enum fc_disc_event event)
 {
 	struct fc_lport *lport = fc_disc_lport(disc);
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&disc->disc_mutex);
 	FC_DISC_DBG(disc, "Discovery complete\n");
 
 	disc->pending = 0;
@@ -360,15 +353,14 @@ static void fc_disc_error(struct fc_disc *disc, struct fc_frame *fp)
 /**
  * fc_disc_gpn_ft_req() - Send Get Port Names by FC-4 type (GPN_FT) request
  * @lport: The discovery context
- *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  */
 static void fc_disc_gpn_ft_req(struct fc_disc *disc)
 {
 	struct fc_frame *fp;
 	struct fc_lport *lport = fc_disc_lport(disc);
 
+	lockdep_assert_held(&disc->disc_mutex);
+
 	WARN_ON(!fc_lport_test_ready(lport));
 
 	disc->pending = 1;
@@ -658,8 +650,6 @@ out:
  * @lport: The local port to initiate discovery on
  * @rdata: remote port private data
  *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  * On failure, an error code is returned.
  */
 static int fc_disc_gpn_id_req(struct fc_lport *lport,
@@ -667,6 +657,7 @@ static int fc_disc_gpn_id_req(struct fc_lport *lport,
 {
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&lport->disc.disc_mutex);
 	fp = fc_frame_alloc(lport, sizeof(struct fc_ct_hdr) +
 			    sizeof(struct fc_ns_fid));
 	if (!fp)
@@ -683,14 +674,13 @@ static int fc_disc_gpn_id_req(struct fc_lport *lport,
  * fc_disc_single() - Discover the directory information for a single target
  * @lport: The local port the remote port is associated with
  * @dp:	   The port to rediscover
- *
- * Locking Note: This function expects that the disc_mutex is locked
- *		 before it is called.
  */
 static int fc_disc_single(struct fc_lport *lport, struct fc_disc_port *dp)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->disc.disc_mutex);
+
 	rdata = fc_rport_create(lport, dp->port_id);
 	if (!rdata)
 		return -ENOMEM;
diff --git a/drivers/scsi/libfc/fc_lport.c b/drivers/scsi/libfc/fc_lport.c
index 21be672679fb..be83590ed955 100644
--- a/drivers/scsi/libfc/fc_lport.c
+++ b/drivers/scsi/libfc/fc_lport.c
@@ -237,14 +237,13 @@ static const char *fc_lport_state(struct fc_lport *lport)
  * @remote_fid:	 The FID of the ptp rport
  * @remote_wwpn: The WWPN of the ptp rport
  * @remote_wwnn: The WWNN of the ptp rport
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_ptp_setup(struct fc_lport *lport,
 			       u32 remote_fid, u64 remote_wwpn,
 			       u64 remote_wwnn)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (lport->ptp_rdata) {
 		fc_rport_logoff(lport->ptp_rdata);
 		kref_put(&lport->ptp_rdata->kref, fc_rport_destroy);
@@ -403,12 +402,11 @@ static void fc_lport_add_fc4_type(struct fc_lport *lport, enum fc_fh_type type)
  * fc_lport_recv_rlir_req() - Handle received Registered Link Incident Report.
  * @lport: Fibre Channel local port receiving the RLIR
  * @fp:	   The RLIR request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_rlir_req(struct fc_lport *lport, struct fc_frame *fp)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received RLIR request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -420,9 +418,6 @@ static void fc_lport_recv_rlir_req(struct fc_lport *lport, struct fc_frame *fp)
  * fc_lport_recv_echo_req() - Handle received ECHO request
  * @lport: The local port receiving the ECHO
  * @fp:	   ECHO request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_echo_req(struct fc_lport *lport,
 				   struct fc_frame *in_fp)
@@ -432,6 +427,8 @@ static void fc_lport_recv_echo_req(struct fc_lport *lport,
 	void *pp;
 	void *dp;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received ECHO request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -456,9 +453,6 @@ static void fc_lport_recv_echo_req(struct fc_lport *lport,
  * fc_lport_recv_rnid_req() - Handle received Request Node ID data request
  * @lport: The local port receiving the RNID
  * @fp:	   The RNID request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_rnid_req(struct fc_lport *lport,
 				   struct fc_frame *in_fp)
@@ -474,6 +468,8 @@ static void fc_lport_recv_rnid_req(struct fc_lport *lport,
 	u8 fmt;
 	size_t len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received RNID request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -515,12 +511,11 @@ static void fc_lport_recv_rnid_req(struct fc_lport *lport,
  * fc_lport_recv_logo_req() - Handle received fabric LOGO request
  * @lport: The local port receiving the LOGO
  * @fp:	   The LOGO request frame
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 	fc_lport_enter_reset(lport);
 	fc_frame_free(fp);
@@ -553,11 +548,11 @@ EXPORT_SYMBOL(fc_fabric_login);
 /**
  * __fc_linkup() - Handler for transport linkup events
  * @lport: The lport whose link is up
- *
- * Locking: must be called with the lp_mutex held
  */
 void __fc_linkup(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (!lport->link_up) {
 		lport->link_up = 1;
 
@@ -584,11 +579,11 @@ EXPORT_SYMBOL(fc_linkup);
 /**
  * __fc_linkdown() - Handler for transport linkdown events
  * @lport: The lport whose link is down
- *
- * Locking: must be called with the lp_mutex held
  */
 void __fc_linkdown(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (lport->link_up) {
 		lport->link_up = 0;
 		fc_lport_enter_reset(lport);
@@ -722,12 +717,11 @@ static void fc_lport_disc_callback(struct fc_lport *lport,
 /**
  * fc_rport_enter_ready() - Enter the ready state and start discovery
  * @lport: The local port that is ready
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_ready(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered READY from state %s\n",
 		     fc_lport_state(lport));
 
@@ -745,13 +739,12 @@ static void fc_lport_enter_ready(struct fc_lport *lport)
  * @lport: The local port which will have its Port ID set.
  * @port_id: The new port ID.
  * @fp: The frame containing the incoming request, or NULL.
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_set_port_id(struct fc_lport *lport, u32 port_id,
 				 struct fc_frame *fp)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (port_id)
 		printk(KERN_INFO "host%d: Assigned Port ID %6.6x\n",
 		       lport->host->host_no, port_id);
@@ -801,9 +794,6 @@ EXPORT_SYMBOL(fc_lport_set_local_id);
  * A received FLOGI request indicates a point-to-point connection.
  * Accept it with the common service parameters indicating our N port.
  * Set up to do a PLOGI if we have the higher-number WWPN.
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this function.
  */
 static void fc_lport_recv_flogi_req(struct fc_lport *lport,
 				    struct fc_frame *rx_fp)
@@ -816,6 +806,8 @@ static void fc_lport_recv_flogi_req(struct fc_lport *lport,
 	u32 remote_fid;
 	u32 local_fid;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Received FLOGI request while in state %s\n",
 		     fc_lport_state(lport));
 
@@ -1006,12 +998,11 @@ EXPORT_SYMBOL(fc_lport_reset);
 /**
  * fc_lport_reset_locked() - Reset the local port w/ the lport lock held
  * @lport: The local port to be reset
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_reset_locked(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	if (lport->dns_rdata) {
 		fc_rport_logoff(lport->dns_rdata);
 		lport->dns_rdata = NULL;
@@ -1035,12 +1026,11 @@ static void fc_lport_reset_locked(struct fc_lport *lport)
 /**
  * fc_lport_enter_reset() - Reset the local port
  * @lport: The local port to be reset
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_reset(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered RESET state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1065,12 +1055,11 @@ static void fc_lport_enter_reset(struct fc_lport *lport)
 /**
  * fc_lport_enter_disabled() - Disable the local port
  * @lport: The local port to be reset
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_disabled(struct fc_lport *lport)
 {
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered disabled state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1321,14 +1310,13 @@ err:
 /**
  * fc_lport_enter_scr() - Send a SCR (State Change Register) request
  * @lport: The local port to register for state changes
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_scr(struct fc_lport *lport)
 {
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered SCR state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1349,9 +1337,6 @@ static void fc_lport_enter_scr(struct fc_lport *lport)
 /**
  * fc_lport_enter_ns() - register some object with the name server
  * @lport: Fibre Channel local port to register
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_ns(struct fc_lport *lport, enum fc_lport_state state)
 {
@@ -1360,6 +1345,8 @@ static void fc_lport_enter_ns(struct fc_lport *lport, enum fc_lport_state state)
 	int size = sizeof(struct fc_ct_hdr);
 	size_t len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered %s state from %s state\n",
 		     fc_lport_state_names[state],
 		     fc_lport_state(lport));
@@ -1419,14 +1406,13 @@ static struct fc_rport_operations fc_lport_rport_ops = {
 /**
  * fc_rport_enter_dns() - Create a fc_rport for the name server
  * @lport: The local port requesting a remote port for the name server
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_dns(struct fc_lport *lport)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered DNS state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1449,9 +1435,6 @@ err:
 /**
  * fc_lport_enter_ms() - management server commands
  * @lport: Fibre Channel local port to register
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_ms(struct fc_lport *lport, enum fc_lport_state state)
 {
@@ -1461,6 +1444,8 @@ static void fc_lport_enter_ms(struct fc_lport *lport, enum fc_lport_state state)
 	size_t len;
 	int numattrs;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered %s state from %s state\n",
 		     fc_lport_state_names[state],
 		     fc_lport_state(lport));
@@ -1536,14 +1521,13 @@ static void fc_lport_enter_ms(struct fc_lport *lport, enum fc_lport_state state)
 /**
  * fc_rport_enter_fdmi() - Create a fc_rport for the management server
  * @lport: The local port requesting a remote port for the management server
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_fdmi(struct fc_lport *lport)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered FDMI state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1668,15 +1652,14 @@ EXPORT_SYMBOL(fc_lport_logo_resp);
 /**
  * fc_rport_enter_logo() - Logout of the fabric
  * @lport: The local port to be logged out
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_logo(struct fc_lport *lport)
 {
 	struct fc_frame *fp;
 	struct fc_els_logo *logo;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered LOGO state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1811,14 +1794,13 @@ EXPORT_SYMBOL(fc_lport_flogi_resp);
 /**
  * fc_rport_enter_flogi() - Send a FLOGI request to the fabric manager
  * @lport: Fibre Channel local port to be logged in to the fabric
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static void fc_lport_enter_flogi(struct fc_lport *lport)
 {
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_LPORT_DBG(lport, "Entered FLOGI state from %s state\n",
 		     fc_lport_state(lport));
 
@@ -1962,9 +1944,6 @@ static void fc_lport_bsg_resp(struct fc_seq *sp, struct fc_frame *fp,
  * @job:   The BSG Passthrough job
  * @lport: The local port sending the request
  * @did:   The destination port id
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static int fc_lport_els_request(struct bsg_job *job,
 				struct fc_lport *lport,
@@ -1976,6 +1955,8 @@ static int fc_lport_els_request(struct bsg_job *job,
 	char *pp;
 	int len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fp = fc_frame_alloc(lport, job->request_payload.payload_len);
 	if (!fp)
 		return -ENOMEM;
@@ -2023,9 +2004,6 @@ static int fc_lport_els_request(struct bsg_job *job,
  * @lport: The local port sending the request
  * @did:   The destination FC-ID
  * @tov:   The timeout period to wait for the response
- *
- * Locking Note: The lport lock is expected to be held before calling
- * this routine.
  */
 static int fc_lport_ct_request(struct bsg_job *job,
 			       struct fc_lport *lport, u32 did, u32 tov)
@@ -2036,6 +2014,8 @@ static int fc_lport_ct_request(struct bsg_job *job,
 	struct fc_ct_req *ct;
 	size_t len;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fp = fc_frame_alloc(lport, sizeof(struct fc_ct_hdr) +
 			    job->request_payload.payload_len);
 	if (!fp)
diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 31d31aad3de1..6aff9303251a 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -136,13 +136,13 @@ EXPORT_SYMBOL(fc_rport_lookup);
  * @ids:   The identifiers for the new remote port
  *
  * The remote port will start in the INIT state.
- *
- * Locking note:  must be called with the disc_mutex held.
  */
 struct fc_rport_priv *fc_rport_create(struct fc_lport *lport, u32 port_id)
 {
 	struct fc_rport_priv *rdata;
 
+	lockdep_assert_held(&lport->disc.disc_mutex);
+
 	rdata = fc_rport_lookup(lport, port_id);
 	if (rdata)
 		return rdata;
@@ -245,12 +245,12 @@ static unsigned int fc_plogi_get_maxframe(struct fc_els_flogi *flp,
  * fc_rport_state_enter() - Change the state of a remote port
  * @rdata: The remote port whose state should change
  * @new:   The new state
- *
- * Locking Note: Called with the rport lock held
  */
 static void fc_rport_state_enter(struct fc_rport_priv *rdata,
 				 enum fc_rport_state new)
 {
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (rdata->rp_state != new)
 		rdata->retries = 0;
 	rdata->rp_state = new;
@@ -469,8 +469,6 @@ EXPORT_SYMBOL(fc_rport_login);
  * @rdata: The remote port to be deleted
  * @event: The event to report as the reason for deletion
  *
- * Locking Note: Called with the rport lock held.
- *
  * Allow state change into DELETE only once.
  *
  * Call queue_work only if there's no event already pending.
@@ -483,6 +481,8 @@ EXPORT_SYMBOL(fc_rport_login);
 static void fc_rport_enter_delete(struct fc_rport_priv *rdata,
 				  enum fc_rport_event event)
 {
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (rdata->rp_state == RPORT_ST_DELETE)
 		return;
 
@@ -546,13 +546,12 @@ EXPORT_SYMBOL(fc_rport_logoff);
  * fc_rport_enter_ready() - Transition to the RPORT_ST_READY state
  * @rdata: The remote port that is ready
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: schedules workqueue, does not modify kref
  */
 static void fc_rport_enter_ready(struct fc_rport_priv *rdata)
 {
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	fc_rport_state_enter(rdata, RPORT_ST_READY);
 
 	FC_RPORT_DBG(rdata, "Port is Ready\n");
@@ -615,15 +614,14 @@ static void fc_rport_timeout(struct work_struct *work)
  * @rdata: The remote port the error is happened on
  * @err:   The error code
  *
- * Locking Note: The rport lock is expected to be held before
- * calling this routine
- *
  * Reference counting: does not modify kref
  */
 static void fc_rport_error(struct fc_rport_priv *rdata, int err)
 {
 	struct fc_lport *lport = rdata->local_port;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Error %d in state %s, retries %d\n",
 		     -err, fc_rport_state(rdata), rdata->retries);
 
@@ -662,15 +660,14 @@ static void fc_rport_error(struct fc_rport_priv *rdata, int err)
  * If the error was an exchange timeout retry immediately,
  * otherwise wait for E_D_TOV.
  *
- * Locking Note: The rport lock is expected to be held before
- * calling this routine
- *
  * Reference counting: increments kref when scheduling retry_work
  */
 static void fc_rport_error_retry(struct fc_rport_priv *rdata, int err)
 {
 	unsigned long delay = msecs_to_jiffies(rdata->e_d_tov);
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	/* make sure this isn't an FC_EX_CLOSED error, never retry those */
 	if (err == -FC_EX_CLOSED)
 		goto out;
@@ -822,9 +819,6 @@ bad:
  * fc_rport_enter_flogi() - Send a FLOGI request to the remote port for p-mp
  * @rdata: The remote port to send a FLOGI to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_flogi(struct fc_rport_priv *rdata)
@@ -832,6 +826,8 @@ static void fc_rport_enter_flogi(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (!lport->point_to_multipoint)
 		return fc_rport_enter_plogi(rdata);
 
@@ -1071,9 +1067,6 @@ fc_rport_compatible_roles(struct fc_lport *lport, struct fc_rport_priv *rdata)
  * fc_rport_enter_plogi() - Send Port Login (PLOGI) request
  * @rdata: The remote port to send a PLOGI to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_plogi(struct fc_rport_priv *rdata)
@@ -1081,6 +1074,8 @@ static void fc_rport_enter_plogi(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	if (!fc_rport_compatible_roles(lport, rdata)) {
 		FC_RPORT_DBG(rdata, "PLOGI suppressed for incompatible role\n");
 		fc_rport_state_enter(rdata, RPORT_ST_PLOGI_WAIT);
@@ -1232,9 +1227,6 @@ put:
  * fc_rport_enter_prli() - Send Process Login (PRLI) request
  * @rdata: The remote port to send the PRLI request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
@@ -1247,6 +1239,8 @@ static void fc_rport_enter_prli(struct fc_rport_priv *rdata)
 	struct fc_frame *fp;
 	struct fc4_prov *prov;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	/*
 	 * If the rport is one of the well known addresses
 	 * we skip PRLI and RTV and go straight to READY.
@@ -1372,9 +1366,6 @@ put:
  * fc_rport_enter_rtv() - Send Request Timeout Value (RTV) request
  * @rdata: The remote port to send the RTV request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
@@ -1382,6 +1373,8 @@ static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
 	struct fc_frame *fp;
 	struct fc_lport *lport = rdata->local_port;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Port entered RTV state from %s state\n",
 		     fc_rport_state(rdata));
 
@@ -1406,8 +1399,6 @@ static void fc_rport_enter_rtv(struct fc_rport_priv *rdata)
  * fc_rport_recv_rtv_req() - Handler for Read Timeout Value (RTV) requests
  * @rdata: The remote port that sent the RTV request
  * @in_fp: The RTV request frame
- *
- * Locking Note:  Called with the lport and rport locks held.
  */
 static void fc_rport_recv_rtv_req(struct fc_rport_priv *rdata,
 				  struct fc_frame *in_fp)
@@ -1417,6 +1408,9 @@ static void fc_rport_recv_rtv_req(struct fc_rport_priv *rdata,
 	struct fc_els_rtv_acc *rtv;
 	struct fc_seq_els_data rjt_data;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received RTV request\n");
 
 	fp = fc_frame_alloc(lport, sizeof(*rtv));
@@ -1460,9 +1454,6 @@ static void fc_rport_logo_resp(struct fc_seq *sp, struct fc_frame *fp,
  * fc_rport_enter_logo() - Send a logout (LOGO) request
  * @rdata: The remote port to send the LOGO request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_logo(struct fc_rport_priv *rdata)
@@ -1470,6 +1461,8 @@ static void fc_rport_enter_logo(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Port sending LOGO from %s state\n",
 		     fc_rport_state(rdata));
 
@@ -1548,9 +1541,6 @@ put:
  * fc_rport_enter_adisc() - Send Address Discover (ADISC) request
  * @rdata: The remote port to send the ADISC request to
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this routine.
- *
  * Reference counting: increments kref when sending ELS
  */
 static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
@@ -1558,6 +1548,8 @@ static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
 	struct fc_lport *lport = rdata->local_port;
 	struct fc_frame *fp;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "sending ADISC from %s state\n",
 		     fc_rport_state(rdata));
 
@@ -1581,8 +1573,6 @@ static void fc_rport_enter_adisc(struct fc_rport_priv *rdata)
  * fc_rport_recv_adisc_req() - Handler for Address Discovery (ADISC) requests
  * @rdata: The remote port that sent the ADISC request
  * @in_fp: The ADISC request frame
- *
- * Locking Note:  Called with the lport and rport locks held.
  */
 static void fc_rport_recv_adisc_req(struct fc_rport_priv *rdata,
 				    struct fc_frame *in_fp)
@@ -1592,6 +1582,9 @@ static void fc_rport_recv_adisc_req(struct fc_rport_priv *rdata,
 	struct fc_els_adisc *adisc;
 	struct fc_seq_els_data rjt_data;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+	lockdep_assert_held(&lport->lp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received ADISC request\n");
 
 	adisc = fc_frame_payload_get(in_fp, sizeof(*adisc));
@@ -1618,9 +1611,6 @@ drop:
  * fc_rport_recv_rls_req() - Handle received Read Link Status request
  * @rdata: The remote port that sent the RLS request
  * @rx_fp: The PRLI request frame
- *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
  */
 static void fc_rport_recv_rls_req(struct fc_rport_priv *rdata,
 				  struct fc_frame *rx_fp)
@@ -1634,6 +1624,8 @@ static void fc_rport_recv_rls_req(struct fc_rport_priv *rdata,
 	struct fc_seq_els_data rjt_data;
 	struct fc_host_statistics *hst;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received RLS request while in state %s\n",
 		     fc_rport_state(rdata));
 
@@ -1687,8 +1679,6 @@ out:
  * Handle incoming ELS requests that require port login.
  * The ELS opcode has already been validated by the caller.
  *
- * Locking Note: Called with the lport lock held.
- *
  * Reference counting: does not modify kref
  */
 static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
@@ -1696,6 +1686,8 @@ static void fc_rport_recv_els_req(struct fc_lport *lport, struct fc_frame *fp)
 	struct fc_rport_priv *rdata;
 	struct fc_seq_els_data els_data;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	rdata = fc_rport_lookup(lport, fc_frame_sid(fp));
 	if (!rdata) {
 		FC_RPORT_ID_DBG(lport, fc_frame_sid(fp),
@@ -1783,14 +1775,14 @@ busy:
  * @lport: The local port that received the request
  * @fp:	   The request frame
  *
- * Locking Note: Called with the lport lock held.
- *
  * Reference counting: does not modify kref
  */
 void fc_rport_recv_req(struct fc_lport *lport, struct fc_frame *fp)
 {
 	struct fc_seq_els_data els_data;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	/*
 	 * Handle FLOGI, PLOGI and LOGO requests separately, since they
 	 * don't require prior login.
@@ -1831,8 +1823,6 @@ EXPORT_SYMBOL(fc_rport_recv_req);
  * @lport: The local port that received the PLOGI request
  * @rx_fp: The PLOGI request frame
  *
- * Locking Note: The rport lock is held before calling this function.
- *
  * Reference counting: increments kref on return
  */
 static void fc_rport_recv_plogi_req(struct fc_lport *lport,
@@ -1845,6 +1835,8 @@ static void fc_rport_recv_plogi_req(struct fc_lport *lport,
 	struct fc_seq_els_data rjt_data;
 	u32 sid;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	sid = fc_frame_sid(fp);
 
 	FC_RPORT_ID_DBG(lport, sid, "Received PLOGI request\n");
@@ -1955,9 +1947,6 @@ reject:
  * fc_rport_recv_prli_req() - Handler for process login (PRLI) requests
  * @rdata: The remote port that sent the PRLI request
  * @rx_fp: The PRLI request frame
- *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
  */
 static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
 				   struct fc_frame *rx_fp)
@@ -1976,6 +1965,8 @@ static void fc_rport_recv_prli_req(struct fc_rport_priv *rdata,
 	struct fc_seq_els_data rjt_data;
 	struct fc4_prov *prov;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received PRLI request while in state %s\n",
 		     fc_rport_state(rdata));
 
@@ -2072,9 +2063,6 @@ drop:
  * fc_rport_recv_prlo_req() - Handler for process logout (PRLO) requests
  * @rdata: The remote port that sent the PRLO request
  * @rx_fp: The PRLO request frame
- *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
  */
 static void fc_rport_recv_prlo_req(struct fc_rport_priv *rdata,
 				   struct fc_frame *rx_fp)
@@ -2091,6 +2079,8 @@ static void fc_rport_recv_prlo_req(struct fc_rport_priv *rdata,
 	unsigned int plen;
 	struct fc_seq_els_data rjt_data;
 
+	lockdep_assert_held(&rdata->rp_mutex);
+
 	FC_RPORT_DBG(rdata, "Received PRLO request while in state %s\n",
 		     fc_rport_state(rdata));
 
@@ -2144,9 +2134,6 @@ drop:
  * @lport: The local port that received the LOGO request
  * @fp:	   The LOGO request frame
  *
- * Locking Note: The rport lock is expected to be held before calling
- * this function.
- *
  * Reference counting: drops kref on return
  */
 static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
@@ -2154,6 +2141,8 @@ static void fc_rport_recv_logo_req(struct fc_lport *lport, struct fc_frame *fp)
 	struct fc_rport_priv *rdata;
 	u32 sid;
 
+	lockdep_assert_held(&lport->lp_mutex);
+
 	fc_seq_els_rsp_send(fp, ELS_LS_ACC, NULL);
 
 	sid = fc_frame_sid(fp);
-- 
cgit v1.2.3


From fa519f701d27198a2858bb108fc18ea9d8c106a7 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 4 Jul 2018 13:59:16 +0200
Subject: scsi: libfc: fixup 'sleeping function called from invalid context'

fc_rport_login() will be calling mutex_lock() while running inside an
RCU-protected section, triggering the warning 'sleeping function called
from invalid context'.  To fix this we can drop the rcu functions here
altogether as the disc mutex protecting the list itself is already held,
preventing any list manipulation.

Fixes: a407c593398c ("scsi: libfc: Fixup disc_mutex handling")
Signed-off-by: Hannes Reinecke <hare@suse.com>
Acked-by: Johannes Thumshirn <jth@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libfc/fc_disc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index 6125df787200..c1756b9b3ea5 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -287,9 +287,11 @@ static void fc_disc_done(struct fc_disc *disc, enum fc_disc_event event)
 	 * discovery, reverify or log them in.	Otherwise, log them out.
 	 * Skip ports which were never discovered.  These are the dNS port
 	 * and ports which were created by PLOGI.
+	 *
+	 * We don't need to use the _rcu variant here as the rport list
+	 * is protected by the disc mutex which is already held on entry.
 	 */
-	rcu_read_lock();
-	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
+	list_for_each_entry(rdata, &disc->rports, peers) {
 		if (!kref_get_unless_zero(&rdata->kref))
 			continue;
 		if (rdata->disc_id) {
@@ -300,7 +302,6 @@ static void fc_disc_done(struct fc_disc *disc, enum fc_disc_event event)
 		}
 		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	rcu_read_unlock();
 	mutex_unlock(&disc->disc_mutex);
 	disc->disc_callback(lport, event);
 	mutex_lock(&disc->disc_mutex);
-- 
cgit v1.2.3


From 2d362b8ad57f42701ea435140ad800c415cd4527 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Thu, 5 Jul 2018 13:01:37 +0200
Subject: scsi: aacraid: remove AAC_STAT_GOOD define

Remove the AAC_STAT_GOOD definition and open code it in the places it was
used.

This will make subsequent refactoring in this area easier.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Dave Carroll <david.carroll@microsemi.com>
Cc: Raghava Aditya Renukunta <RaghavaAditya.Renukunta@microsemi.com>
Reviewed-by: Dave Carroll <david.carroll@microsemi.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/aachba.c | 41 +++++++++++++++++++++++++++--------------
 1 file changed, 27 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/aacraid/aachba.c b/drivers/scsi/aacraid/aachba.c
index a9831bd37a73..0b34d275523d 100644
--- a/drivers/scsi/aacraid/aachba.c
+++ b/drivers/scsi/aacraid/aachba.c
@@ -115,8 +115,6 @@
 #define ASENCODE_LUN_FAILED_SELF_CONFIG		0x00
 #define ASENCODE_OVERLAPPED_COMMAND		0x00
 
-#define AAC_STAT_GOOD (DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_GOOD)
-
 #define BYTE0(x) (unsigned char)(x)
 #define BYTE1(x) (unsigned char)((x) >> 8)
 #define BYTE2(x) (unsigned char)((x) >> 16)
@@ -2962,7 +2960,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 
 	case SYNCHRONIZE_CACHE:
 		if (((aac_cache & 6) == 6) && dev->cache_protected) {
-			scsicmd->result = AAC_STAT_GOOD;
+			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+					  SAM_STAT_GOOD;
 			break;
 		}
 		/* Issue FIB to tell Firmware to flush it's cache */
@@ -2990,7 +2989,9 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				arr[1] = scsicmd->cmnd[2];
 				scsi_sg_copy_from_buffer(scsicmd, &inq_data,
 							 sizeof(inq_data));
-				scsicmd->result = AAC_STAT_GOOD;
+				scsicmd->result = DID_OK << 16 |
+						  COMMAND_COMPLETE << 8 |
+						  SAM_STAT_GOOD;
 			} else if (scsicmd->cmnd[2] == 0x80) {
 				/* unit serial number page */
 				arr[3] = setinqserial(dev, &arr[4],
@@ -3001,7 +3002,9 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				if (aac_wwn != 2)
 					return aac_get_container_serial(
 						scsicmd);
-				scsicmd->result = AAC_STAT_GOOD;
+				scsicmd->result = DID_OK << 16 |
+						  COMMAND_COMPLETE << 8 |
+						  SAM_STAT_GOOD;
 			} else if (scsicmd->cmnd[2] == 0x83) {
 				/* vpd page 0x83 - Device Identification Page */
 				char *sno = (char *)&inq_data;
@@ -3010,7 +3013,9 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				if (aac_wwn != 2)
 					return aac_get_container_serial(
 						scsicmd);
-				scsicmd->result = AAC_STAT_GOOD;
+				scsicmd->result = DID_OK << 16 |
+						  COMMAND_COMPLETE << 8 |
+						  SAM_STAT_GOOD;
 			} else {
 				/* vpd page not implemented */
 				scsicmd->result = DID_OK << 16 |
@@ -3041,7 +3046,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 			inq_data.inqd_pdt = INQD_PDT_PROC;	/* Processor device */
 			scsi_sg_copy_from_buffer(scsicmd, &inq_data,
 						 sizeof(inq_data));
-			scsicmd->result = AAC_STAT_GOOD;
+			scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+					  SAM_STAT_GOOD;
 			break;
 		}
 		if (dev->in_reset)
@@ -3090,7 +3096,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		/* Do not cache partition table for arrays */
 		scsicmd->device->removable = 1;
 
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 
@@ -3116,7 +3123,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		scsi_sg_copy_from_buffer(scsicmd, cp, sizeof(cp));
 		/* Do not cache partition table for arrays */
 		scsicmd->device->removable = 1;
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 
@@ -3195,7 +3203,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		scsi_sg_copy_from_buffer(scsicmd,
 					 (char *)&mpd,
 					 mode_buf_length);
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 	case MODE_SENSE_10:
@@ -3272,7 +3281,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 					 (char *)&mpd10,
 					 mode_buf_length);
 
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	}
 	case REQUEST_SENSE:
@@ -3281,7 +3291,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 				sizeof(struct sense_data));
 		memset(&dev->fsa_dev[cid].sense_data, 0,
 				sizeof(struct sense_data));
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 
 	case ALLOW_MEDIUM_REMOVAL:
@@ -3291,7 +3302,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 		else
 			fsa_dev_ptr[cid].locked = 0;
 
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 	/*
 	 *	These commands are all No-Ops
@@ -3315,7 +3327,8 @@ int aac_scsi_cmd(struct scsi_cmnd * scsicmd)
 	case REZERO_UNIT:
 	case REASSIGN_BLOCKS:
 	case SEEK_10:
-		scsicmd->result = AAC_STAT_GOOD;
+		scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 |
+				  SAM_STAT_GOOD;
 		break;
 
 	case START_STOP:
-- 
cgit v1.2.3


From 55c9d37165d28f081b7ba11fc2a7938d4bbb75c6 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Thu, 5 Jul 2018 13:01:38 +0200
Subject: scsi: bfa: remove ScsiResult macro

Remove the ScsiResult macro and open code it on all call sites.

This will make subsequent refactoring in this area easier.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/bfa/bfad_im.c | 19 ++++++++-----------
 drivers/scsi/bfa/bfad_im.h |  1 -
 2 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/scsi/bfa/bfad_im.c b/drivers/scsi/bfa/bfad_im.c
index c05d6e91e4bd..c4a33317d344 100644
--- a/drivers/scsi/bfa/bfad_im.c
+++ b/drivers/scsi/bfa/bfad_im.c
@@ -70,21 +70,18 @@ bfa_cb_ioim_done(void *drv, struct bfad_ioim_s *dio,
 				host_status = DID_ERROR;
 			}
 		}
-		cmnd->result = ScsiResult(host_status, scsi_status);
+		cmnd->result = host_status << 16 | scsi_status;
 
 		break;
 
 	case BFI_IOIM_STS_TIMEDOUT:
-		host_status = DID_TIME_OUT;
-		cmnd->result = ScsiResult(host_status, 0);
+		cmnd->result = DID_TIME_OUT << 16;
 		break;
 	case BFI_IOIM_STS_PATHTOV:
-		host_status = DID_TRANSPORT_DISRUPTED;
-		cmnd->result = ScsiResult(host_status, 0);
+		cmnd->result = DID_TRANSPORT_DISRUPTED << 16;
 		break;
 	default:
-		host_status = DID_ERROR;
-		cmnd->result = ScsiResult(host_status, 0);
+		cmnd->result = DID_ERROR << 16;
 	}
 
 	/* Unmap DMA, if host is NULL, it means a scsi passthru cmd */
@@ -117,7 +114,7 @@ bfa_cb_ioim_good_comp(void *drv, struct bfad_ioim_s *dio)
 	struct bfad_itnim_data_s *itnim_data;
 	struct bfad_itnim_s *itnim;
 
-	cmnd->result = ScsiResult(DID_OK, SCSI_STATUS_GOOD);
+	cmnd->result = DID_OK << 16 | SCSI_STATUS_GOOD;
 
 	/* Unmap DMA, if host is NULL, it means a scsi passthru cmd */
 	if (cmnd->device->host != NULL)
@@ -144,7 +141,7 @@ bfa_cb_ioim_abort(void *drv, struct bfad_ioim_s *dio)
 	struct scsi_cmnd *cmnd = (struct scsi_cmnd *)dio;
 	struct bfad_s         *bfad = drv;
 
-	cmnd->result = ScsiResult(DID_ERROR, 0);
+	cmnd->result = DID_ERROR << 16;
 
 	/* Unmap DMA, if host is NULL, it means a scsi passthru cmd */
 	if (cmnd->device->host != NULL)
@@ -1253,14 +1250,14 @@ bfad_im_queuecommand_lck(struct scsi_cmnd *cmnd, void (*done) (struct scsi_cmnd
 		printk(KERN_WARNING
 			"bfad%d, queuecommand %p %x failed, BFA stopped\n",
 		       bfad->inst_no, cmnd, cmnd->cmnd[0]);
-		cmnd->result = ScsiResult(DID_NO_CONNECT, 0);
+		cmnd->result = DID_NO_CONNECT << 16;
 		goto out_fail_cmd;
 	}
 
 
 	itnim = itnim_data->itnim;
 	if (!itnim) {
-		cmnd->result = ScsiResult(DID_IMM_RETRY, 0);
+		cmnd->result = DID_IMM_RETRY << 16;
 		goto out_fail_cmd;
 	}
 
diff --git a/drivers/scsi/bfa/bfad_im.h b/drivers/scsi/bfa/bfad_im.h
index af66275570c3..e61ed8dad0b4 100644
--- a/drivers/scsi/bfa/bfad_im.h
+++ b/drivers/scsi/bfa/bfad_im.h
@@ -44,7 +44,6 @@ u32 bfad_im_supported_speeds(struct bfa_s *bfa);
 #define MAX_FCP_LUN 16384
 #define BFAD_TARGET_RESET_TMO 60
 #define BFAD_LUN_RESET_TMO 60
-#define ScsiResult(host_code, scsi_code) (((host_code) << 16) | scsi_code)
 #define BFA_QUEUE_FULL_RAMP_UP_TIME 120
 
 /*
-- 
cgit v1.2.3


From c6668cae16f046ba5c4b6090bb234bdbccdb70cf Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Thu, 5 Jul 2018 13:01:39 +0200
Subject: scsi: lpfc: remove ScsiResult macro

Remove the ScsiResult macro and open code it on all call sites.

This will make subsequent refactoring in this area easier.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Cc: James Smart <james.smart@broadcom.com>
Cc: Dick Kennedy <dick.kennedy@broadcom.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_crtn.h |  1 -
 drivers/scsi/lpfc/lpfc_scsi.c | 44 +++++++++++++++++++++----------------------
 2 files changed, 22 insertions(+), 23 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_crtn.h b/drivers/scsi/lpfc/lpfc_crtn.h
index d02b4b860110..bea24bc4410a 100644
--- a/drivers/scsi/lpfc/lpfc_crtn.h
+++ b/drivers/scsi/lpfc/lpfc_crtn.h
@@ -469,7 +469,6 @@ int lpfc_parse_vpd(struct lpfc_hba *, uint8_t *, int);
 void lpfc_start_fdiscs(struct lpfc_hba *phba);
 struct lpfc_vport *lpfc_find_vport_by_vpid(struct lpfc_hba *, uint16_t);
 struct lpfc_sglq *__lpfc_get_active_sglq(struct lpfc_hba *, uint16_t);
-#define ScsiResult(host_code, scsi_code) (((host_code) << 16) | scsi_code)
 #define HBA_EVENT_RSCN                   5
 #define HBA_EVENT_LINK_UP                2
 #define HBA_EVENT_LINK_DOWN              3
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 5e4cad6a531a..25ef2b6ccc34 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -3017,8 +3017,8 @@ out:
 	if (err_type == BGS_GUARD_ERR_MASK) {
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 					0x10, 0x1);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 		phba->bg_guard_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9069 BLKGRD: LBA %lx grd_tag error %x != %x\n",
@@ -3028,8 +3028,8 @@ out:
 	} else if (err_type == BGS_REFTAG_ERR_MASK) {
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 					0x10, 0x3);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_reftag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3040,8 +3040,8 @@ out:
 	} else if (err_type == BGS_APPTAG_ERR_MASK) {
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 					0x10, 0x2);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_apptag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3096,7 +3096,7 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 	spin_unlock(&_dump_buf_lock);
 
 	if (lpfc_bgs_get_invalid_prof(bgstat)) {
-		cmd->result = ScsiResult(DID_ERROR, 0);
+		cmd->result = DID_ERROR << 16;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9072 BLKGRD: Invalid BG Profile in cmd"
 				" 0x%x lba 0x%llx blk cnt 0x%x "
@@ -3108,7 +3108,7 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 	}
 
 	if (lpfc_bgs_get_uninit_dif_block(bgstat)) {
-		cmd->result = ScsiResult(DID_ERROR, 0);
+		cmd->result = DID_ERROR << 16;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9073 BLKGRD: Invalid BG PDIF Block in cmd"
 				" 0x%x lba 0x%llx blk cnt 0x%x "
@@ -3124,8 +3124,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 				0x10, 0x1);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 		phba->bg_guard_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
 				"9055 BLKGRD: Guard Tag error in cmd"
@@ -3140,8 +3140,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 				0x10, 0x3);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_reftag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3157,8 +3157,8 @@ lpfc_parse_bg_err(struct lpfc_hba *phba, struct lpfc_scsi_buf *lpfc_cmd,
 
 		scsi_build_sense_buffer(1, cmd->sense_buffer, ILLEGAL_REQUEST,
 				0x10, 0x2);
-		cmd->result = DRIVER_SENSE << 24
-			| ScsiResult(DID_ABORT, SAM_STAT_CHECK_CONDITION);
+		cmd->result = DRIVER_SENSE << 24 | DID_ABORT << 16 |
+			      SAM_STAT_CHECK_CONDITION;
 
 		phba->bg_apptag_err_cnt++;
 		lpfc_printf_log(phba, KERN_WARNING, LOG_FCP | LOG_BG,
@@ -3874,7 +3874,7 @@ lpfc_handle_fcp_err(struct lpfc_vport *vport, struct lpfc_scsi_buf *lpfc_cmd,
 	}
 
  out:
-	cmnd->result = ScsiResult(host_status, scsi_status);
+	cmnd->result = host_status << 16 | scsi_status;
 	lpfc_send_scsi_error_event(vport->phba, vport, lpfc_cmd, rsp_iocb);
 }
 
@@ -4027,7 +4027,7 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			break;
 		case IOSTAT_NPORT_BSY:
 		case IOSTAT_FABRIC_BSY:
-			cmd->result = ScsiResult(DID_TRANSPORT_DISRUPTED, 0);
+			cmd->result = DID_TRANSPORT_DISRUPTED << 16;
 			fast_path_evt = lpfc_alloc_fast_evt(phba);
 			if (!fast_path_evt)
 				break;
@@ -4061,14 +4061,14 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			    lpfc_cmd->result == IOERR_ELXSEC_CRYPTO_ERROR ||
 			    lpfc_cmd->result ==
 					IOERR_ELXSEC_CRYPTO_COMPARE_ERROR) {
-				cmd->result = ScsiResult(DID_NO_CONNECT, 0);
+				cmd->result = DID_NO_CONNECT << 16;
 				break;
 			}
 			if (lpfc_cmd->result == IOERR_INVALID_RPI ||
 			    lpfc_cmd->result == IOERR_NO_RESOURCES ||
 			    lpfc_cmd->result == IOERR_ABORT_REQUESTED ||
 			    lpfc_cmd->result == IOERR_SLER_CMD_RCV_FAILURE) {
-				cmd->result = ScsiResult(DID_REQUEUE, 0);
+				cmd->result = DID_REQUEUE << 16;
 				break;
 			}
 			if ((lpfc_cmd->result == IOERR_RX_DMA_FAILED ||
@@ -4102,16 +4102,16 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			}
 		/* else: fall through */
 		default:
-			cmd->result = ScsiResult(DID_ERROR, 0);
+			cmd->result = DID_ERROR << 16;
 			break;
 		}
 
 		if (!pnode || !NLP_CHK_NODE_ACT(pnode)
 		    || (pnode->nlp_state != NLP_STE_MAPPED_NODE))
-			cmd->result = ScsiResult(DID_TRANSPORT_DISRUPTED,
-						 SAM_STAT_BUSY);
+			cmd->result = DID_TRANSPORT_DISRUPTED << 16 |
+				      SAM_STAT_BUSY;
 	} else
-		cmd->result = ScsiResult(DID_OK, 0);
+		cmd->result = DID_OK << 16;
 
 	if (cmd->result || lpfc_cmd->fcp_rsp->rspSnsLen) {
 		uint32_t *lp = (uint32_t *)cmd->sense_buffer;
-- 
cgit v1.2.3


From 78adb2bc9f7216226799489c351f32ea3a092f49 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Thu, 5 Jul 2018 13:01:40 +0200
Subject: scsi: ncr53c8xx: remove ScsiResult macro

Remove the ScsiResult macro and open code it on all call sites.

This will make subsequent refactoring in this area easier.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ncr53c8xx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/ncr53c8xx.c b/drivers/scsi/ncr53c8xx.c
index dc4e801b2cef..6cd3e289ef99 100644
--- a/drivers/scsi/ncr53c8xx.c
+++ b/drivers/scsi/ncr53c8xx.c
@@ -4611,7 +4611,7 @@ static int ncr_reset_bus (struct ncb *np, struct scsi_cmnd *cmd, int sync_reset)
  * in order to keep it alive.
  */
 	if (!found && sync_reset && !retrieve_from_waiting_list(0, np, cmd)) {
-		cmd->result = ScsiResult(DID_RESET, 0);
+		cmd->result = DID_RESET << 16;
 		ncr_queue_done_cmd(np, cmd);
 	}
 
@@ -4957,7 +4957,7 @@ void ncr_complete (struct ncb *np, struct ccb *cp)
 		/*
 		**   Check condition code
 		*/
-		cmd->result = ScsiResult(DID_OK, S_CHECK_COND);
+		cmd->result = DID_OK << 16 | S_CHECK_COND;
 
 		/*
 		**	Copy back sense data to caller's buffer.
@@ -4978,7 +4978,7 @@ void ncr_complete (struct ncb *np, struct ccb *cp)
 		/*
 		**   Reservation Conflict condition code
 		*/
-		cmd->result = ScsiResult(DID_OK, S_CONFLICT);
+		cmd->result = DID_OK << 16 | S_CONFLICT;
 	
 	} else if ((cp->host_status == HS_COMPLETE)
 		&& (cp->scsi_status == S_BUSY ||
@@ -8043,7 +8043,7 @@ printk("ncr53c8xx_queue_command\n");
      spin_lock_irqsave(&np->smp_lock, flags);
 
      if ((sts = ncr_queue_command(np, cmd)) != DID_OK) {
-	  cmd->result = ScsiResult(sts, 0);
+	  cmd->result = sts << 16;
 #ifdef DEBUG_NCR53C8XX
 printk("ncr53c8xx : command not queued - result=%d\n", sts);
 #endif
@@ -8234,7 +8234,7 @@ static void process_waiting_list(struct ncb *np, int sts)
 #ifdef DEBUG_WAITING_LIST
 	printk("%s: cmd %lx done forced sts=%d\n", ncr_name(np), (u_long) wcmd, sts);
 #endif
-			wcmd->result = ScsiResult(sts, 0);
+			wcmd->result = sts << 16;
 			ncr_queue_done_cmd(np, wcmd);
 		}
 	}
-- 
cgit v1.2.3


From 54e45716a84ac9df9e5fef779ab54fc2f97ebdf3 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Fri, 6 Jul 2018 15:33:48 +0200
Subject: scsi: remove NCR_D700 driver

The NCR DUAL 700 SCSI driver depends on microchannel support, but
microchannel support was removed from the kernel with commit bb8187d35f82
("MCA: delete all remaining traces of microchannel bus support.") over 6
years ago.

So zap the D700 SCSI driver as well.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Acked-by: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 MAINTAINERS             |   6 -
 drivers/scsi/Kconfig    |  12 --
 drivers/scsi/Makefile   |   1 -
 drivers/scsi/NCR_D700.c | 405 ------------------------------------------------
 drivers/scsi/NCR_D700.h |  30 ----
 5 files changed, 454 deletions(-)
 delete mode 100644 drivers/scsi/NCR_D700.c
 delete mode 100644 drivers/scsi/NCR_D700.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 9d5eeff51b5f..f3de5d37179a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9750,12 +9750,6 @@ F:	drivers/scsi/mac_scsi.*
 F:	drivers/scsi/sun3_scsi.*
 F:	drivers/scsi/sun3_scsi_vme.c
 
-NCR DUAL 700 SCSI DRIVER (MICROCHANNEL)
-M:	"James E.J. Bottomley" <James.Bottomley@HansenPartnership.com>
-L:	linux-scsi@vger.kernel.org
-S:	Maintained
-F:	drivers/scsi/NCR_D700.*
-
 NCT6775 HARDWARE MONITOR DRIVER
 M:	Guenter Roeck <linux@roeck-us.net>
 L:	linux-hwmon@vger.kernel.org
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index bd115bab162e..a7675302f9a7 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -842,18 +842,6 @@ config SCSI_IZIP_SLOW_CTR
 
 	  Generally, saying N is fine.
 
-config SCSI_NCR_D700
-	tristate "NCR Dual 700 MCA SCSI support"
-	depends on MCA && SCSI
-	select SCSI_SPI_ATTRS
-	help
-	  This is a driver for the MicroChannel Dual 700 card produced by
-	  NCR and commonly used in 345x/35xx/4100 class machines.  It always
-	  tries to negotiate sync and uses tag command queueing.
-
-	  Unless you have an NCR manufactured machine, the chances are that
-	  you do not have this SCSI card, so say N.
-
 config SCSI_LASI700
 	tristate "HP Lasi SCSI support for 53c700/710"
 	depends on GSC && SCSI
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 80aca2456353..3729d0d1a5e7 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -76,7 +76,6 @@ obj-$(CONFIG_SCSI_PM8001)	+= pm8001/
 obj-$(CONFIG_SCSI_ISCI)		+= isci/
 obj-$(CONFIG_SCSI_IPS)		+= ips.o
 obj-$(CONFIG_SCSI_GENERIC_NCR5380) += g_NCR5380.o
-obj-$(CONFIG_SCSI_NCR_D700)	+= 53c700.o NCR_D700.o
 obj-$(CONFIG_SCSI_NCR_Q720)	+= NCR_Q720_mod.o
 obj-$(CONFIG_SCSI_QLOGIC_FAS)	+= qlogicfas408.o	qlogicfas.o
 obj-$(CONFIG_PCMCIA_QLOGIC)	+= qlogicfas408.o
diff --git a/drivers/scsi/NCR_D700.c b/drivers/scsi/NCR_D700.c
deleted file mode 100644
index b39a2409a507..000000000000
--- a/drivers/scsi/NCR_D700.c
+++ /dev/null
@@ -1,405 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Dual 700 MCA SCSI Driver
- *
- * Copyright (C) 2001 by James.Bottomley@HansenPartnership.com
-**-----------------------------------------------------------------------------
-**  
-**  This program is free software; you can redistribute it and/or modify
-**  it under the terms of the GNU General Public License as published by
-**  the Free Software Foundation; either version 2 of the License, or
-**  (at your option) any later version.
-**
-**  This program is distributed in the hope that it will be useful,
-**  but WITHOUT ANY WARRANTY; without even the implied warranty of
-**  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-**  GNU General Public License for more details.
-**
-**  You should have received a copy of the GNU General Public License
-**  along with this program; if not, write to the Free Software
-**  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
-**
-**-----------------------------------------------------------------------------
- */
-
-/* Notes:
- *
- * Most of the work is done in the chip specific module, 53c700.o
- *
- * TODO List:
- *
- * 1. Extract the SCSI ID from the voyager CMOS table (necessary to
- *    support multi-host environments.
- *
- * */
-
-
-/* CHANGELOG 
- *
- * Version 2.2
- *
- * Added mca_set_adapter_name().
- *
- * Version 2.1
- *
- * Modularise the driver into a Board piece (this file) and a chip
- * piece 53c700.[ch] and 53c700.scr, added module options.  You can
- * now specify the scsi id by the parameters
- *
- * NCR_D700=slot:<n> [siop:<n>] id:<n> ....
- *
- * They need to be comma separated if compiled into the kernel
- *
- * Version 2.0
- *
- * Initial implementation of TCQ (Tag Command Queueing).  TCQ is full
- * featured and uses the clock algorithm to keep track of outstanding
- * tags and guard against individual tag starvation.  Also fixed a bug
- * in all of the 1.x versions where the D700_data_residue() function
- * was returning results off by 32 bytes (and thus causing the same 32
- * bytes to be written twice corrupting the data block).  It turns out
- * the 53c700 only has a 6 bit DBC and DFIFO registers not 7 bit ones
- * like the 53c710 (The 710 is the only data manual still available,
- * which I'd been using to program the 700).
- *
- * Version 1.2
- *
- * Much improved message handling engine
- *
- * Version 1.1
- *
- * Add code to handle selection reasonably correctly.  By the time we
- * get the selection interrupt, we've already responded, but drop off the
- * bus and hope the selector will go away.
- *
- * Version 1.0:
- *
- *   Initial release.  Fully functional except for procfs and tag
- * command queueing.  Has only been tested on cards with 53c700-66
- * chips and only single ended. Features are
- *
- * 1. Synchronous data transfers to offset 8 (limit of 700-66) and
- *    100ns (10MHz) limit of SCSI-2
- *
- * 2. Disconnection and reselection
- *
- * Testing:
- * 
- *  I've only really tested this with the 700-66 chip, but have done
- * soak tests in multi-device environments to verify that
- * disconnections and reselections are being processed correctly.
- * */
-
-#define NCR_D700_VERSION "2.2"
-
-#include <linux/blkdev.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mca.h>
-#include <linux/slab.h>
-#include <asm/io.h>
-#include <scsi/scsi_host.h>
-#include <scsi/scsi_device.h>
-#include <scsi/scsi_transport.h>
-#include <scsi/scsi_transport_spi.h>
-
-#include "53c700.h"
-#include "NCR_D700.h"
-
-static char *NCR_D700;		/* command line from insmod */
-
-MODULE_AUTHOR("James Bottomley");
-MODULE_DESCRIPTION("NCR Dual700 SCSI Driver");
-MODULE_LICENSE("GPL");
-module_param(NCR_D700, charp, 0);
-
-static __u8 id_array[2*(MCA_MAX_SLOT_NR + 1)] =
-	{ [0 ... 2*(MCA_MAX_SLOT_NR + 1)-1] = 7 };
-
-#ifdef MODULE
-#define ARG_SEP ' '
-#else
-#define ARG_SEP ','
-#endif
-
-static int __init
-param_setup(char *string)
-{
-	char *pos = string, *next;
-	int slot = -1, siop = -1;
-
-	while(pos != NULL && (next = strchr(pos, ':')) != NULL) {
-		int val = (int)simple_strtoul(++next, NULL, 0);
-
-		if(!strncmp(pos, "slot:", 5))
-			slot = val;
-		else if(!strncmp(pos, "siop:", 5))
-			siop = val;
-		else if(!strncmp(pos, "id:", 3)) {
-			if(slot == -1) {
-				printk(KERN_WARNING "NCR D700: Must specify slot for id parameter\n");
-			} else if(slot > MCA_MAX_SLOT_NR) {
-				printk(KERN_WARNING "NCR D700: Illegal slot %d for id %d\n", slot, val);
-			} else {
-				if(siop != 0 && siop != 1) {
-					id_array[slot*2] = val;
-					id_array[slot*2 + 1] =val;
-				} else {
-					id_array[slot*2 + siop] = val;
-				}
-			}
-		}
-		if((pos = strchr(pos, ARG_SEP)) != NULL)
-			pos++;
-	}
-	return 1;
-}
-
-/* Host template.  The 53c700 routine NCR_700_detect will
- * fill in all of the missing routines */
-static struct scsi_host_template NCR_D700_driver_template = {
-	.module			= THIS_MODULE,
-	.name			= "NCR Dual 700 MCA",
-	.proc_name		= "NCR_D700",
-	.this_id		= 7,
-};
-
-/* We needs this helper because we have two hosts per struct device */
-struct NCR_D700_private {
-	struct device		*dev;
-	struct Scsi_Host	*hosts[2];
-	char			name[30];
-	char			pad;
-};
-
-static int
-NCR_D700_probe_one(struct NCR_D700_private *p, int siop, int irq,
-		   int slot, u32 region, int differential)
-{
-	struct NCR_700_Host_Parameters *hostdata;
-	struct Scsi_Host *host;
-	int ret;
-
-	hostdata = kzalloc(sizeof(*hostdata), GFP_KERNEL);
-	if (!hostdata) {
-		printk(KERN_ERR "NCR D700: SIOP%d: Failed to allocate host"
-		       "data, detatching\n", siop);
-		return -ENOMEM;
-	}
-
-	if (!request_region(region, 64, "NCR_D700")) {
-		printk(KERN_ERR "NCR D700: Failed to reserve IO region 0x%x\n",
-				region);
-		ret = -ENODEV;
-		goto region_failed;
-	}
-		
-	/* Fill in the three required pieces of hostdata */
-	hostdata->base = ioport_map(region, 64);
-	hostdata->differential = (((1<<siop) & differential) != 0);
-	hostdata->clock = NCR_D700_CLOCK_MHZ;
-	hostdata->burst_length = 8;
-
-	/* and register the siop */
-	host = NCR_700_detect(&NCR_D700_driver_template, hostdata, p->dev);
-	if (!host) {
-		ret = -ENOMEM;
-		goto detect_failed;
-	}
-
-	p->hosts[siop] = host;
-	/* FIXME: read this from SUS */
-	host->this_id = id_array[slot * 2 + siop];
-	host->irq = irq;
-	host->base = region;
-	scsi_scan_host(host);
-
-	return 0;
-
- detect_failed:
-	release_region(region, 64);
- region_failed:
-	kfree(hostdata);
-
-	return ret;
-}
-
-static irqreturn_t
-NCR_D700_intr(int irq, void *data)
-{
-	struct NCR_D700_private *p = (struct NCR_D700_private *)data;
-	int i, found = 0;
-
-	for (i = 0; i < 2; i++)
-		if (p->hosts[i] &&
-		    NCR_700_intr(irq, p->hosts[i]) == IRQ_HANDLED)
-			found++;
-
-	return found ? IRQ_HANDLED : IRQ_NONE;
-}
-
-/* Detect a D700 card.  Note, because of the setup --- the chips are
- * essentially connectecd to the MCA bus independently, it is easier
- * to set them up as two separate host adapters, rather than one
- * adapter with two channels */
-static int
-NCR_D700_probe(struct device *dev)
-{
-	struct NCR_D700_private *p;
-	int differential;
-	static int banner = 1;
-	struct mca_device *mca_dev = to_mca_device(dev);
-	int slot = mca_dev->slot;
-	int found = 0;
-	int irq, i;
-	int pos3j, pos3k, pos3a, pos3b, pos4;
-	__u32 base_addr, offset_addr;
-
-	/* enable board interrupt */
-	pos4 = mca_device_read_pos(mca_dev, 4);
-	pos4 |= 0x4;
-	mca_device_write_pos(mca_dev, 4, pos4);
-
-	mca_device_write_pos(mca_dev, 6, 9);
-	pos3j = mca_device_read_pos(mca_dev, 3);
-	mca_device_write_pos(mca_dev, 6, 10);
-	pos3k = mca_device_read_pos(mca_dev, 3);
-	mca_device_write_pos(mca_dev, 6, 0);
-	pos3a = mca_device_read_pos(mca_dev, 3);
-	mca_device_write_pos(mca_dev, 6, 1);
-	pos3b = mca_device_read_pos(mca_dev, 3);
-
-	base_addr = ((pos3j << 8) | pos3k) & 0xfffffff0;
-	offset_addr = ((pos3a << 8) | pos3b) & 0xffffff70;
-
-	irq = (pos4 & 0x3) + 11;
-	if(irq >= 13)
-		irq++;
-	if(banner) {
-		printk(KERN_NOTICE "NCR D700: Driver Version " NCR_D700_VERSION "\n"
-		       "NCR D700:  Copyright (c) 2001 by James.Bottomley@HansenPartnership.com\n"
-		       "NCR D700:\n");
-		banner = 0;
-	}
-	/* now do the bus related transforms */
-	irq = mca_device_transform_irq(mca_dev, irq);
-	base_addr = mca_device_transform_ioport(mca_dev, base_addr);
-	offset_addr = mca_device_transform_ioport(mca_dev, offset_addr);
-
-	printk(KERN_NOTICE "NCR D700: found in slot %d  irq = %d  I/O base = 0x%x\n", slot, irq, offset_addr);
-
-	/*outb(BOARD_RESET, base_addr);*/
-
-	/* clear any pending interrupts */
-	(void)inb(base_addr + 0x08);
-	/* get modctl, used later for setting diff bits */
-	switch(differential = (inb(base_addr + 0x08) >> 6)) {
-	case 0x00:
-		/* only SIOP1 differential */
-		differential = 0x02;
-		break;
-	case 0x01:
-		/* Both SIOPs differential */
-		differential = 0x03;
-		break;
-	case 0x03:
-		/* No SIOPs differential */
-		differential = 0x00;
-		break;
-	default:
-		printk(KERN_ERR "D700: UNEXPECTED DIFFERENTIAL RESULT 0x%02x\n",
-		       differential);
-		differential = 0x00;
-		break;
-	}
-
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	p->dev = dev;
-	snprintf(p->name, sizeof(p->name), "D700(%s)", dev_name(dev));
-	if (request_irq(irq, NCR_D700_intr, IRQF_SHARED, p->name, p)) {
-		printk(KERN_ERR "D700: request_irq failed\n");
-		kfree(p);
-		return -EBUSY;
-	}
-	/* plumb in both 700 chips */
-	for (i = 0; i < 2; i++) {
-		int err;
-
-		if ((err = NCR_D700_probe_one(p, i, irq, slot,
-					      offset_addr + (0x80 * i),
-					      differential)) != 0)
-			printk("D700: SIOP%d: probe failed, error = %d\n",
-			       i, err);
-		else
-			found++;
-	}
-
-	if (!found) {
-		kfree(p);
-		return -ENODEV;
-	}
-
-	mca_device_set_claim(mca_dev, 1);
-	mca_device_set_name(mca_dev, "NCR_D700");
-	dev_set_drvdata(dev, p);
-	return 0;
-}
-
-static void
-NCR_D700_remove_one(struct Scsi_Host *host)
-{
-	scsi_remove_host(host);
-	NCR_700_release(host);
-	kfree((struct NCR_700_Host_Parameters *)host->hostdata[0]);
-	free_irq(host->irq, host);
-	release_region(host->base, 64);
-}
-
-static int
-NCR_D700_remove(struct device *dev)
-{
-	struct NCR_D700_private *p = dev_get_drvdata(dev);
-	int i;
-
-	for (i = 0; i < 2; i++)
-		NCR_D700_remove_one(p->hosts[i]);
-
-	kfree(p);
-	return 0;
-}
-
-static short NCR_D700_id_table[] = { NCR_D700_MCA_ID, 0 };
-
-static struct mca_driver NCR_D700_driver = {
-	.id_table = NCR_D700_id_table,
-	.driver = {
-		.name		= "NCR_D700",
-		.bus		= &mca_bus_type,
-		.probe		= NCR_D700_probe,
-		.remove		= NCR_D700_remove,
-	},
-};
-
-static int __init NCR_D700_init(void)
-{
-#ifdef MODULE
-	if (NCR_D700)
-		param_setup(NCR_D700);
-#endif
-
-	return mca_register_driver(&NCR_D700_driver);
-}
-
-static void __exit NCR_D700_exit(void)
-{
-	mca_unregister_driver(&NCR_D700_driver);
-}
-
-module_init(NCR_D700_init);
-module_exit(NCR_D700_exit);
-
-__setup("NCR_D700=", param_setup);
diff --git a/drivers/scsi/NCR_D700.h b/drivers/scsi/NCR_D700.h
deleted file mode 100644
index eb675d782ef6..000000000000
--- a/drivers/scsi/NCR_D700.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Dual 700 MCA SCSI Driver
- *
- * Copyright (C) 2001 by James.Bottomley@HansenPartnership.com
- */
-
-#ifndef _NCR_D700_H
-#define _NCR_D700_H
-
-/* Don't turn on debugging messages */
-#undef NCR_D700_DEBUG
-
-/* The MCA identifier */
-#define NCR_D700_MCA_ID		0x0092
-
-/* Defines for the Board registers */
-#define	BOARD_RESET		0x80	/* board level reset */
-#define ADD_PARENB		0x04	/* Address Parity Enabled */
-#define DAT_PARENB		0x01	/* Data Parity Enabled */
-#define SFBK_ENB		0x10	/* SFDBK Interrupt Enabled */
-#define LED0GREEN		0x20	/* Led 0 (red 0; green 1) */
-#define LED1GREEN		0x40	/* Led 1 (red 0; green 1) */
-#define LED0RED			0xDF	/* Led 0 (red 0; green 1) */
-#define LED1RED			0xBF	/* Led 1 (red 0; green 1) */
-
-#define NCR_D700_CLOCK_MHZ	50
-
-#endif
-- 
cgit v1.2.3


From af8a6722fa39b9ddc63e8f3b97656ba168a04199 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Fri, 6 Jul 2018 15:33:49 +0200
Subject: scsi: remove NCR_Q720 driver

The NCR QUAD 720 SCSI driver depends on microchannel support, but
microchannel support was removed from the kernel with commit bb8187d35f82
("MCA: delete all remaining traces of microchannel bus support.") over 6
years ago.

So zap the Q720 SCSI driver as well.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Acked-by: James E.J. Bottomley <James.Bottomley@HansenPartnership.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/Kconfig    |  20 +--
 drivers/scsi/Makefile   |   2 -
 drivers/scsi/NCR_Q720.c | 376 ------------------------------------------------
 drivers/scsi/NCR_Q720.h |  29 ----
 4 files changed, 4 insertions(+), 423 deletions(-)
 delete mode 100644 drivers/scsi/NCR_Q720.c
 delete mode 100644 drivers/scsi/NCR_Q720.h

diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index a7675302f9a7..8fc851a9e116 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -989,21 +989,9 @@ config SCSI_ZALON
 	  used on the add-in Bluefish, Barracuda & Shrike SCSI cards.
 	  Say Y here if you have one of these machines or cards.
 
-config SCSI_NCR_Q720
-	tristate "NCR Quad 720 MCA SCSI support"
-	depends on MCA && SCSI
-	select SCSI_SPI_ATTRS
-	help
-	  This is a driver for the MicroChannel Quad 720 card produced by
-	  NCR and commonly used in 345x/35xx/4100 class machines.  It always
-	  tries to negotiate sync and uses tag command queueing.
-
-	  Unless you have an NCR manufactured machine, the chances are that
-	  you do not have this SCSI card, so say N.
-
 config SCSI_NCR53C8XX_DEFAULT_TAGS
 	int "default tagged command queue depth"
-	depends on SCSI_ZALON || SCSI_NCR_Q720
+	depends on SCSI_ZALON
 	default "8"
 	---help---
 	  "Tagged command queuing" is a feature of SCSI-2 which improves
@@ -1029,7 +1017,7 @@ config SCSI_NCR53C8XX_DEFAULT_TAGS
 
 config SCSI_NCR53C8XX_MAX_TAGS
 	int "maximum number of queued commands"
-	depends on SCSI_ZALON || SCSI_NCR_Q720
+	depends on SCSI_ZALON
 	default "32"
 	---help---
 	  This option allows you to specify the maximum number of commands
@@ -1046,7 +1034,7 @@ config SCSI_NCR53C8XX_MAX_TAGS
 
 config SCSI_NCR53C8XX_SYNC
 	int "synchronous transfers frequency in MHz"
-	depends on SCSI_ZALON || SCSI_NCR_Q720
+	depends on SCSI_ZALON
 	default "20"
 	---help---
 	  The SCSI Parallel Interface-2 Standard defines 5 classes of transfer
@@ -1080,7 +1068,7 @@ config SCSI_NCR53C8XX_SYNC
 
 config SCSI_NCR53C8XX_NO_DISCONNECT
 	bool "not allow targets to disconnect"
-	depends on (SCSI_ZALON || SCSI_NCR_Q720) && SCSI_NCR53C8XX_DEFAULT_TAGS=0
+	depends on SCSI_ZALON && SCSI_NCR53C8XX_DEFAULT_TAGS=0
 	help
 	  This option is only provided for safety if you suspect some SCSI
 	  device of yours to not support properly the target-disconnect
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 3729d0d1a5e7..d1bad43be396 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -76,7 +76,6 @@ obj-$(CONFIG_SCSI_PM8001)	+= pm8001/
 obj-$(CONFIG_SCSI_ISCI)		+= isci/
 obj-$(CONFIG_SCSI_IPS)		+= ips.o
 obj-$(CONFIG_SCSI_GENERIC_NCR5380) += g_NCR5380.o
-obj-$(CONFIG_SCSI_NCR_Q720)	+= NCR_Q720_mod.o
 obj-$(CONFIG_SCSI_QLOGIC_FAS)	+= qlogicfas408.o	qlogicfas.o
 obj-$(CONFIG_PCMCIA_QLOGIC)	+= qlogicfas408.o
 obj-$(CONFIG_SCSI_QLOGIC_1280)	+= qla1280.o 
@@ -179,7 +178,6 @@ ncr53c8xx-flags-$(CONFIG_SCSI_ZALON) \
 			-DCONFIG_SCSI_NCR53C8XX_NO_WORD_TRANSFERS
 CFLAGS_ncr53c8xx.o	:= $(ncr53c8xx-flags-y) $(ncr53c8xx-flags-m)
 zalon7xx-objs	:= zalon.o ncr53c8xx.o
-NCR_Q720_mod-objs	:= NCR_Q720.o ncr53c8xx.o
 
 # Files generated that shall be removed upon make clean
 clean-files :=	53c700_d.h 53c700_u.h scsi_devinfo_tbl.c
diff --git a/drivers/scsi/NCR_Q720.c b/drivers/scsi/NCR_Q720.c
deleted file mode 100644
index 54e7d26908ee..000000000000
--- a/drivers/scsi/NCR_Q720.c
+++ /dev/null
@@ -1,376 +0,0 @@
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Quad 720 MCA SCSI Driver
- *
- * Copyright (C) 2003 by James.Bottomley@HansenPartnership.com
- */
-
-#include <linux/blkdev.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mca.h>
-#include <linux/slab.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/delay.h>
-#include <asm/io.h>
-
-#include "scsi.h"
-#include <scsi/scsi_host.h>
-
-#include "ncr53c8xx.h"
-
-#include "NCR_Q720.h"
-
-static struct ncr_chip q720_chip __initdata = {
-	.revision_id =	0x0f,
-	.burst_max =	3,
-	.offset_max =	8,
-	.nr_divisor =	4,
-	.features =	FE_WIDE | FE_DIFF | FE_VARCLK,
-};
-
-MODULE_AUTHOR("James Bottomley");
-MODULE_DESCRIPTION("NCR Quad 720 SCSI Driver");
-MODULE_LICENSE("GPL");
-
-#define NCR_Q720_VERSION		"0.9"
-
-/* We needs this helper because we have up to four hosts per struct device */
-struct NCR_Q720_private {
-	struct device		*dev;
-	void __iomem *		mem_base;
-	__u32			phys_mem_base;
-	__u32			mem_size;
-	__u8			irq;
-	__u8			siops;
-	__u8			irq_enable;
-	struct Scsi_Host	*hosts[4];
-};
-
-static struct scsi_host_template NCR_Q720_tpnt = {
-	.module			= THIS_MODULE,
-	.proc_name		= "NCR_Q720",
-};
-
-static irqreturn_t
-NCR_Q720_intr(int irq, void *data)
-{
-	struct NCR_Q720_private *p = (struct NCR_Q720_private *)data;
-	__u8 sir = (readb(p->mem_base + 0x0d) & 0xf0) >> 4;
-	__u8 siop;
-
-	sir |= ~p->irq_enable;
-
-	if(sir == 0xff)
-		return IRQ_NONE;
-
-
-	while((siop = ffz(sir)) < p->siops) {
-		sir |= 1<<siop;
-		ncr53c8xx_intr(irq, p->hosts[siop]);
-	}
-	return IRQ_HANDLED;
-}
-
-static int __init
-NCR_Q720_probe_one(struct NCR_Q720_private *p, int siop,
-		int irq, int slot, __u32 paddr, void __iomem *vaddr)
-{
-	struct ncr_device device;
-	__u8 scsi_id;
-	static int unit = 0;
-	__u8 scsr1 = readb(vaddr + NCR_Q720_SCSR_OFFSET + 1);
-	__u8 differential = readb(vaddr + NCR_Q720_SCSR_OFFSET) & 0x20;
-	__u8 version;
-	int error;
-
-	scsi_id = scsr1 >> 4;
-	/* enable burst length 16 (FIXME: should allow this) */
-	scsr1 |= 0x02;
-	/* force a siop reset */
-	scsr1 |= 0x04;
-	writeb(scsr1, vaddr + NCR_Q720_SCSR_OFFSET + 1);
-	udelay(10);
-	version = readb(vaddr + 0x18) >> 4;
-
-	memset(&device, 0, sizeof(struct ncr_device));
-		/* Initialise ncr_device structure with items required by ncr_attach. */
-	device.chip		= q720_chip;
-	device.chip.revision_id	= version;
-	device.host_id		= scsi_id;
-	device.dev		= p->dev;
-	device.slot.base	= paddr;
-	device.slot.base_c	= paddr;
-	device.slot.base_v	= vaddr;
-	device.slot.irq		= irq;
-	device.differential	= differential ? 2 : 0;
-	printk("Q720 probe unit %d (siop%d) at 0x%lx, diff = %d, vers = %d\n", unit, siop,
-	       (unsigned long)paddr, differential, version);
-
-	p->hosts[siop] = ncr_attach(&NCR_Q720_tpnt, unit++, &device);
-	
-	if (!p->hosts[siop]) 
-		goto fail;
-
-	p->irq_enable |= (1<<siop);
-	scsr1 = readb(vaddr + NCR_Q720_SCSR_OFFSET + 1);
-	/* clear the disable interrupt bit */
-	scsr1 &= ~0x01;
-	writeb(scsr1, vaddr + NCR_Q720_SCSR_OFFSET + 1);
-
-	error = scsi_add_host(p->hosts[siop], p->dev);
-	if (error)
-		ncr53c8xx_release(p->hosts[siop]);
-	else
-		scsi_scan_host(p->hosts[siop]);
-	return error;
-
- fail:
-	return -ENODEV;
-}
-
-/* Detect a Q720 card.  Note, because of the setup --- the chips are
- * essentially connectecd to the MCA bus independently, it is easier
- * to set them up as two separate host adapters, rather than one
- * adapter with two channels */
-static int __init
-NCR_Q720_probe(struct device *dev)
-{
-	struct NCR_Q720_private *p;
-	static int banner = 1;
-	struct mca_device *mca_dev = to_mca_device(dev);
-	int slot = mca_dev->slot;
-	int found = 0;
-	int irq, i, siops;
-	__u8 pos2, pos4, asr2, asr9, asr10;
-	__u16 io_base;
-	__u32 base_addr, mem_size;
-	void __iomem *mem_base;
-
-	p = kzalloc(sizeof(*p), GFP_KERNEL);
-	if (!p)
-		return -ENOMEM;
-
-	pos2 = mca_device_read_pos(mca_dev, 2);
-	/* enable device */
-	pos2 |=  NCR_Q720_POS2_BOARD_ENABLE | NCR_Q720_POS2_INTERRUPT_ENABLE;
-	mca_device_write_pos(mca_dev, 2, pos2);
-
-	io_base = (pos2 & NCR_Q720_POS2_IO_MASK) << NCR_Q720_POS2_IO_SHIFT;
-
-
-	if(banner) {
-		printk(KERN_NOTICE "NCR Q720: Driver Version " NCR_Q720_VERSION "\n"
-		       "NCR Q720:  Copyright (c) 2003 by James.Bottomley@HansenPartnership.com\n"
-		       "NCR Q720:\n");
-		banner = 0;
-	}
-	io_base = mca_device_transform_ioport(mca_dev, io_base);
-
-	/* OK, this is phase one of the bootstrap, we now know the
-	 * I/O space base address.  All the configuration registers
-	 * are mapped here (including pos) */
-
-	/* sanity check I/O mapping */
-	i = inb(io_base) | (inb(io_base+1)<<8);
-	if(i != NCR_Q720_MCA_ID) {
-		printk(KERN_ERR "NCR_Q720, adapter failed to I/O map registers correctly at 0x%x(0x%x)\n", io_base, i);
-		kfree(p);
-		return -ENODEV;
-	}
-
-	/* Phase II, find the ram base and memory map the board register */
-	pos4 = inb(io_base + 4);
-	/* enable streaming data */
-	pos4 |= 0x01;
-	outb(pos4, io_base + 4);
-	base_addr = (pos4 & 0x7e) << 20;
-	base_addr += (pos4 & 0x80) << 23;
-	asr10 = inb(io_base + 0x12);
-	base_addr += (asr10 & 0x80) << 24;
-	base_addr += (asr10 & 0x70) << 23;
-
-	/* OK, got the base addr, now we need to find the ram size,
-	 * enable and map it */
-	asr9 = inb(io_base + 0x11);
-	i = (asr9 & 0xc0) >> 6;
-	if(i == 0)
-		mem_size = 1024;
-	else
-		mem_size = 1 << (19 + i);
-
-	/* enable the sram mapping */
-	asr9 |= 0x20;
-
-	/* disable the rom mapping */
-	asr9 &= ~0x10;
-
-	outb(asr9, io_base + 0x11);
-
-	if(!request_mem_region(base_addr, mem_size, "NCR_Q720")) {
-		printk(KERN_ERR "NCR_Q720: Failed to claim memory region 0x%lx\n-0x%lx",
-		       (unsigned long)base_addr,
-		       (unsigned long)(base_addr + mem_size));
-		goto out_free;
-	}
-	
-	if (dma_declare_coherent_memory(dev, base_addr, base_addr,
-					mem_size, 0)) {
-		printk(KERN_ERR "NCR_Q720: DMA declare memory failed\n");
-		goto out_release_region;
-	}
-
-	/* The first 1k of the memory buffer is a memory map of the registers
-	 */
-	mem_base = dma_mark_declared_memory_occupied(dev, base_addr,
-							    1024);
-	if (IS_ERR(mem_base)) {
-		printk("NCR_Q720 failed to reserve memory mapped region\n");
-		goto out_release;
-	}
-
-	/* now also enable accesses in asr 2 */
-	asr2 = inb(io_base + 0x0a);
-
-	asr2 |= 0x01;
-
-	outb(asr2, io_base + 0x0a);
-
-	/* get the number of SIOPs (this should be 2 or 4) */
-	siops = ((asr2 & 0xe0) >> 5) + 1;
-
-	/* sanity check mapping (again) */
-	i = readw(mem_base);
-	if(i != NCR_Q720_MCA_ID) {
-		printk(KERN_ERR "NCR_Q720, adapter failed to memory map registers correctly at 0x%lx(0x%x)\n", (unsigned long)base_addr, i);
-		goto out_release;
-	}
-
-	irq = readb(mem_base + 5) & 0x0f;
-	
-	
-	/* now do the bus related transforms */
-	irq = mca_device_transform_irq(mca_dev, irq);
-
-	printk(KERN_NOTICE "NCR Q720: found in slot %d  irq = %d  mem base = 0x%lx siops = %d\n", slot, irq, (unsigned long)base_addr, siops);
-	printk(KERN_NOTICE "NCR Q720: On board ram %dk\n", mem_size/1024);
-
-	p->dev = dev;
-	p->mem_base = mem_base;
-	p->phys_mem_base = base_addr;
-	p->mem_size = mem_size;
-	p->irq = irq;
-	p->siops = siops;
-
-	if (request_irq(irq, NCR_Q720_intr, IRQF_SHARED, "NCR_Q720", p)) {
-		printk(KERN_ERR "NCR_Q720: request irq %d failed\n", irq);
-		goto out_release;
-	}
-	/* disable all the siop interrupts */
-	for(i = 0; i < siops; i++) {
-		void __iomem *reg_scsr1 = mem_base + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT + NCR_Q720_SCSR_OFFSET + 1;
-		__u8 scsr1 = readb(reg_scsr1);
-		scsr1 |= 0x01;
-		writeb(scsr1, reg_scsr1);
-	}
-
-	/* plumb in all 720 chips */
-	for (i = 0; i < siops; i++) {
-		void __iomem *siop_v_base = mem_base + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT;
-		__u32 siop_p_base = base_addr + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT;
-		__u16 port = io_base + NCR_Q720_CHIP_REGISTER_OFFSET
-			+ i*NCR_Q720_SIOP_SHIFT;
-		int err;
-
-		outb(0xff, port + 0x40);
-		outb(0x07, port + 0x41);
-		if ((err = NCR_Q720_probe_one(p, i, irq, slot,
-					      siop_p_base, siop_v_base)) != 0)
-			printk("Q720: SIOP%d: probe failed, error = %d\n",
-			       i, err);
-		else
-			found++;
-	}
-
-	if (!found) {
-		kfree(p);
-		return -ENODEV;
-	}
-
-	mca_device_set_claim(mca_dev, 1);
-	mca_device_set_name(mca_dev, "NCR_Q720");
-	dev_set_drvdata(dev, p);
-
-	return 0;
-
- out_release:
-	dma_release_declared_memory(dev);
- out_release_region:
-	release_mem_region(base_addr, mem_size);
- out_free:
-	kfree(p);
-
-	return -ENODEV;
-}
-
-static void __exit
-NCR_Q720_remove_one(struct Scsi_Host *host)
-{
-	scsi_remove_host(host);
-	ncr53c8xx_release(host);
-}
-
-static int __exit
-NCR_Q720_remove(struct device *dev)
-{
-	struct NCR_Q720_private *p = dev_get_drvdata(dev);
-	int i;
-
-	for (i = 0; i < p->siops; i++)
-		if(p->hosts[i])
-			NCR_Q720_remove_one(p->hosts[i]);
-
-	dma_release_declared_memory(dev);
-	release_mem_region(p->phys_mem_base, p->mem_size);
-	free_irq(p->irq, p);
-	kfree(p);
-	return 0;
-}
-
-static short NCR_Q720_id_table[] = { NCR_Q720_MCA_ID, 0 };
-
-static struct mca_driver NCR_Q720_driver = {
-	.id_table = NCR_Q720_id_table,
-	.driver = {
-		.name		= "NCR_Q720",
-		.bus		= &mca_bus_type,
-		.probe		= NCR_Q720_probe,
-		.remove		= NCR_Q720_remove,
-	},
-};
-
-static int __init
-NCR_Q720_init(void)
-{
-	int ret = ncr53c8xx_init();
-	if (!ret)
-		ret = mca_register_driver(&NCR_Q720_driver);
-	if (ret)
-		ncr53c8xx_exit();
-	return ret;
-}
-
-static void __exit
-NCR_Q720_exit(void)
-{
-	mca_unregister_driver(&NCR_Q720_driver);
-	ncr53c8xx_exit();
-}
-
-module_init(NCR_Q720_init);
-module_exit(NCR_Q720_exit);
diff --git a/drivers/scsi/NCR_Q720.h b/drivers/scsi/NCR_Q720.h
deleted file mode 100644
index d5f46cdb736e..000000000000
--- a/drivers/scsi/NCR_Q720.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* -*- mode: c; c-basic-offset: 8 -*- */
-
-/* NCR Quad 720 MCA SCSI Driver
- *
- * Copyright (C) 2003 by James.Bottomley@HansenPartnership.com
- */
-
-#ifndef _NCR_Q720_H
-#define _NCR_Q720_H
-
-/* The MCA identifier */
-#define NCR_Q720_MCA_ID		0x0720
-
-#define NCR_Q720_CLOCK_MHZ	30
-
-#define NCR_Q720_POS2_BOARD_ENABLE	0x01
-#define NCR_Q720_POS2_INTERRUPT_ENABLE	0x02
-#define NCR_Q720_POS2_PARITY_DISABLE	0x04
-#define NCR_Q720_POS2_IO_MASK		0xf8
-#define NCR_Q720_POS2_IO_SHIFT		8
-
-#define NCR_Q720_CHIP_REGISTER_OFFSET	0x200
-#define NCR_Q720_SCSR_OFFSET		0x070
-#define NCR_Q720_SIOP_SHIFT		0x080
-
-#endif
-
-
-- 
cgit v1.2.3


From 046f6fd5daefac7f5abdafb436b30f63bc7c602b Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: sched: Add Common Applications Kept Enhanced (cake) qdisc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

sch_cake targets the home router use case and is intended to squeeze the
most bandwidth and latency out of even the slowest ISP links and routers,
while presenting an API simple enough that even an ISP can configure it.

Example of use on a cable ISP uplink:

tc qdisc add dev eth0 cake bandwidth 20Mbit nat docsis ack-filter

To shape a cable download link (ifb and tc-mirred setup elided)

tc qdisc add dev ifb0 cake bandwidth 200mbit nat docsis ingress wash

CAKE is filled with:

* A hybrid Codel/Blue AQM algorithm, "Cobalt", tied to an FQ_Codel
  derived Flow Queuing system, which autoconfigures based on the bandwidth.
* A novel "triple-isolate" mode (the default) which balances per-host
  and per-flow FQ even through NAT.
* An deficit based shaper, that can also be used in an unlimited mode.
* 8 way set associative hashing to reduce flow collisions to a minimum.
* A reasonable interpretation of various diffserv latency/loss tradeoffs.
* Support for zeroing diffserv markings for entering and exiting traffic.
* Support for interacting well with Docsis 3.0 shaper framing.
* Extensive support for DSL framing types.
* Support for ack filtering.
* Extensive statistics for measuring, loss, ecn markings, latency
  variation.

A paper describing the design of CAKE is available at
https://arxiv.org/abs/1804.07617, and will be published at the 2018 IEEE
International Symposium on Local and Metropolitan Area Networks (LANMAN).

This patch adds the base shaper and packet scheduler, while subsequent
commits add the optional (configurable) features. The full userspace API
and most data structures are included in this commit, but options not
understood in the base version will be ignored.

Various versions baking have been available as an out of tree build for
kernel versions going back to 3.10, as the embedded router world has been
running a few years behind mainline Linux. A stable version has been
generally available on lede-17.01 and later.

sch_cake replaces a combination of iptables, tc filter, htb and fq_codel
in the sqm-scripts, with sane defaults and vastly simpler configuration.

CAKE's principal author is Jonathan Morton, with contributions from
Kevin Darbyshire-Bryant, Toke Høiland-Jørgensen, Sebastian Moeller,
Ryan Mounce, Tony Ambardar, Dean Scarff, Nils Andreas Svee, Dave Täht,
and Loganaden Velvindron.

Testing from Pete Heist, Georgios Amanakis, and the many other members of
the cake@lists.bufferbloat.net mailing list.

tc -s qdisc show dev eth2
 qdisc cake 8017: root refcnt 2 bandwidth 1Gbit diffserv3 triple-isolate split-gso rtt 100.0ms noatm overhead 38 mpu 84
 Sent 51504294511 bytes 37724591 pkt (dropped 6, overlimits 64958695 requeues 12)
  backlog 0b 0p requeues 12
  memory used: 1053008b of 15140Kb
  capacity estimate: 970Mbit
  min/max network layer size:           28 /    1500
  min/max overhead-adjusted size:       84 /    1538
  average network hdr offset:           14
                    Bulk  Best Effort        Voice
   thresh      62500Kbit        1Gbit      250Mbit
   target          5.0ms        5.0ms        5.0ms
   interval      100.0ms      100.0ms      100.0ms
   pk_delay          5us          5us          6us
   av_delay          3us          2us          2us
   sp_delay          2us          1us          1us
   backlog            0b           0b           0b
   pkts          3164050     25030267      9530280
   bytes      3227519915  35396974782  12879808898
   way_inds            0            8            0
   way_miss           21          366           25
   way_cols            0            0            0
   drops               5            0            1
   marks               0            0            0
   ack_drop            0            0            0
   sp_flows            1            3            0
   bk_flows            0            1            1
   un_flows            0            0            0
   max_len         68130        68130        68130

Tested-by: Pete Heist <peteheist@gmail.com>
Tested-by: Georgios Amanakis <gamanakis@gmail.com>
Signed-off-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  114 +++
 net/sched/Kconfig              |   11 +
 net/sched/Makefile             |    1 +
 net/sched/sch_cake.c           | 1867 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 1993 insertions(+)
 create mode 100644 net/sched/sch_cake.c

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 949118461009..d9cc9dc4f547 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -955,4 +955,118 @@ enum {
 
 #define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
 
+
+/* CAKE */
+enum {
+	TCA_CAKE_UNSPEC,
+	TCA_CAKE_PAD,
+	TCA_CAKE_BASE_RATE64,
+	TCA_CAKE_DIFFSERV_MODE,
+	TCA_CAKE_ATM,
+	TCA_CAKE_FLOW_MODE,
+	TCA_CAKE_OVERHEAD,
+	TCA_CAKE_RTT,
+	TCA_CAKE_TARGET,
+	TCA_CAKE_AUTORATE,
+	TCA_CAKE_MEMORY,
+	TCA_CAKE_NAT,
+	TCA_CAKE_RAW,
+	TCA_CAKE_WASH,
+	TCA_CAKE_MPU,
+	TCA_CAKE_INGRESS,
+	TCA_CAKE_ACK_FILTER,
+	TCA_CAKE_SPLIT_GSO,
+	__TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX	(__TCA_CAKE_MAX - 1)
+
+enum {
+	__TCA_CAKE_STATS_INVALID,
+	TCA_CAKE_STATS_PAD,
+	TCA_CAKE_STATS_CAPACITY_ESTIMATE64,
+	TCA_CAKE_STATS_MEMORY_LIMIT,
+	TCA_CAKE_STATS_MEMORY_USED,
+	TCA_CAKE_STATS_AVG_NETOFF,
+	TCA_CAKE_STATS_MIN_NETLEN,
+	TCA_CAKE_STATS_MAX_NETLEN,
+	TCA_CAKE_STATS_MIN_ADJLEN,
+	TCA_CAKE_STATS_MAX_ADJLEN,
+	TCA_CAKE_STATS_TIN_STATS,
+	TCA_CAKE_STATS_DEFICIT,
+	TCA_CAKE_STATS_COBALT_COUNT,
+	TCA_CAKE_STATS_DROPPING,
+	TCA_CAKE_STATS_DROP_NEXT_US,
+	TCA_CAKE_STATS_P_DROP,
+	TCA_CAKE_STATS_BLUE_TIMER_US,
+	__TCA_CAKE_STATS_MAX
+};
+#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1)
+
+enum {
+	__TCA_CAKE_TIN_STATS_INVALID,
+	TCA_CAKE_TIN_STATS_PAD,
+	TCA_CAKE_TIN_STATS_SENT_PACKETS,
+	TCA_CAKE_TIN_STATS_SENT_BYTES64,
+	TCA_CAKE_TIN_STATS_DROPPED_PACKETS,
+	TCA_CAKE_TIN_STATS_DROPPED_BYTES64,
+	TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS,
+	TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64,
+	TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS,
+	TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64,
+	TCA_CAKE_TIN_STATS_BACKLOG_PACKETS,
+	TCA_CAKE_TIN_STATS_BACKLOG_BYTES,
+	TCA_CAKE_TIN_STATS_THRESHOLD_RATE64,
+	TCA_CAKE_TIN_STATS_TARGET_US,
+	TCA_CAKE_TIN_STATS_INTERVAL_US,
+	TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS,
+	TCA_CAKE_TIN_STATS_WAY_MISSES,
+	TCA_CAKE_TIN_STATS_WAY_COLLISIONS,
+	TCA_CAKE_TIN_STATS_PEAK_DELAY_US,
+	TCA_CAKE_TIN_STATS_AVG_DELAY_US,
+	TCA_CAKE_TIN_STATS_BASE_DELAY_US,
+	TCA_CAKE_TIN_STATS_SPARSE_FLOWS,
+	TCA_CAKE_TIN_STATS_BULK_FLOWS,
+	TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS,
+	TCA_CAKE_TIN_STATS_MAX_SKBLEN,
+	TCA_CAKE_TIN_STATS_FLOW_QUANTUM,
+	__TCA_CAKE_TIN_STATS_MAX
+};
+#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1)
+#define TC_CAKE_MAX_TINS (8)
+
+enum {
+	CAKE_FLOW_NONE = 0,
+	CAKE_FLOW_SRC_IP,
+	CAKE_FLOW_DST_IP,
+	CAKE_FLOW_HOSTS,    /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */
+	CAKE_FLOW_FLOWS,
+	CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */
+	CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */
+	CAKE_FLOW_TRIPLE,   /* = CAKE_FLOW_HOSTS  | CAKE_FLOW_FLOWS */
+	CAKE_FLOW_MAX,
+};
+
+enum {
+	CAKE_DIFFSERV_DIFFSERV3 = 0,
+	CAKE_DIFFSERV_DIFFSERV4,
+	CAKE_DIFFSERV_DIFFSERV8,
+	CAKE_DIFFSERV_BESTEFFORT,
+	CAKE_DIFFSERV_PRECEDENCE,
+	CAKE_DIFFSERV_MAX
+};
+
+enum {
+	CAKE_ACK_NONE = 0,
+	CAKE_ACK_FILTER,
+	CAKE_ACK_AGGRESSIVE,
+	CAKE_ACK_MAX
+};
+
+enum {
+	CAKE_ATM_NONE = 0,
+	CAKE_ATM_ATM,
+	CAKE_ATM_PTM,
+	CAKE_ATM_MAX
+};
+
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index fcc89706745b..7af246764a35 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -295,6 +295,17 @@ config NET_SCH_FQ_CODEL
 
 	  If unsure, say N.
 
+config NET_SCH_CAKE
+	tristate "Common Applications Kept Enhanced (CAKE)"
+	help
+	  Say Y here if you want to use the Common Applications Kept Enhanced
+          (CAKE) queue management algorithm.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_cake.
+
+	  If unsure, say N.
+
 config NET_SCH_FQ
 	tristate "Fair Queue"
 	help
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 9a5a7077d217..673ee7d26ff2 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_NET_SCH_CHOKE)	+= sch_choke.o
 obj-$(CONFIG_NET_SCH_QFQ)	+= sch_qfq.o
 obj-$(CONFIG_NET_SCH_CODEL)	+= sch_codel.o
 obj-$(CONFIG_NET_SCH_FQ_CODEL)	+= sch_fq_codel.o
+obj-$(CONFIG_NET_SCH_CAKE)	+= sch_cake.o
 obj-$(CONFIG_NET_SCH_FQ)	+= sch_fq.o
 obj-$(CONFIG_NET_SCH_HHF)	+= sch_hhf.o
 obj-$(CONFIG_NET_SCH_PIE)	+= sch_pie.o
diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
new file mode 100644
index 000000000000..ea0272615d63
--- /dev/null
+++ b/net/sched/sch_cake.c
@@ -0,0 +1,1867 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+
+/* COMMON Applications Kept Enhanced (CAKE) discipline
+ *
+ * Copyright (C) 2014-2018 Jonathan Morton <chromatix99@gmail.com>
+ * Copyright (C) 2015-2018 Toke Høiland-Jørgensen <toke@toke.dk>
+ * Copyright (C) 2014-2018 Dave Täht <dave.taht@gmail.com>
+ * Copyright (C) 2015-2018 Sebastian Moeller <moeller0@gmx.de>
+ * (C) 2015-2018 Kevin Darbyshire-Bryant <kevin@darbyshire-bryant.me.uk>
+ * Copyright (C) 2017-2018 Ryan Mounce <ryan@mounce.com.au>
+ *
+ * The CAKE Principles:
+ *		   (or, how to have your cake and eat it too)
+ *
+ * This is a combination of several shaping, AQM and FQ techniques into one
+ * easy-to-use package:
+ *
+ * - An overall bandwidth shaper, to move the bottleneck away from dumb CPE
+ *   equipment and bloated MACs.  This operates in deficit mode (as in sch_fq),
+ *   eliminating the need for any sort of burst parameter (eg. token bucket
+ *   depth).  Burst support is limited to that necessary to overcome scheduling
+ *   latency.
+ *
+ * - A Diffserv-aware priority queue, giving more priority to certain classes,
+ *   up to a specified fraction of bandwidth.  Above that bandwidth threshold,
+ *   the priority is reduced to avoid starving other tins.
+ *
+ * - Each priority tin has a separate Flow Queue system, to isolate traffic
+ *   flows from each other.  This prevents a burst on one flow from increasing
+ *   the delay to another.  Flows are distributed to queues using a
+ *   set-associative hash function.
+ *
+ * - Each queue is actively managed by Cobalt, which is a combination of the
+ *   Codel and Blue AQM algorithms.  This serves flows fairly, and signals
+ *   congestion early via ECN (if available) and/or packet drops, to keep
+ *   latency low.  The codel parameters are auto-tuned based on the bandwidth
+ *   setting, as is necessary at low bandwidths.
+ *
+ * The configuration parameters are kept deliberately simple for ease of use.
+ * Everything has sane defaults.  Complete generality of configuration is *not*
+ * a goal.
+ *
+ * The priority queue operates according to a weighted DRR scheme, combined with
+ * a bandwidth tracker which reuses the shaper logic to detect which side of the
+ * bandwidth sharing threshold the tin is operating.  This determines whether a
+ * priority-based weight (high) or a bandwidth-based weight (low) is used for
+ * that tin in the current pass.
+ *
+ * This qdisc was inspired by Eric Dumazet's fq_codel code, which he kindly
+ * granted us permission to leverage.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/string.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/skbuff.h>
+#include <linux/jhash.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+#include <linux/reciprocal_div.h>
+#include <net/netlink.h>
+#include <linux/version.h>
+#include <linux/if_vlan.h>
+#include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
+#include <net/tcp.h>
+#include <net/flow_dissector.h>
+
+#define CAKE_SET_WAYS (8)
+#define CAKE_MAX_TINS (8)
+#define CAKE_QUEUES (1024)
+#define CAKE_FLOW_MASK 63
+#define CAKE_FLOW_NAT_FLAG 64
+
+/* struct cobalt_params - contains codel and blue parameters
+ * @interval:	codel initial drop rate
+ * @target:     maximum persistent sojourn time & blue update rate
+ * @mtu_time:   serialisation delay of maximum-size packet
+ * @p_inc:      increment of blue drop probability (0.32 fxp)
+ * @p_dec:      decrement of blue drop probability (0.32 fxp)
+ */
+struct cobalt_params {
+	u64	interval;
+	u64	target;
+	u64	mtu_time;
+	u32	p_inc;
+	u32	p_dec;
+};
+
+/* struct cobalt_vars - contains codel and blue variables
+ * @count:		codel dropping frequency
+ * @rec_inv_sqrt:	reciprocal value of sqrt(count) >> 1
+ * @drop_next:		time to drop next packet, or when we dropped last
+ * @blue_timer:		Blue time to next drop
+ * @p_drop:		BLUE drop probability (0.32 fxp)
+ * @dropping:		set if in dropping state
+ * @ecn_marked:		set if marked
+ */
+struct cobalt_vars {
+	u32	count;
+	u32	rec_inv_sqrt;
+	ktime_t	drop_next;
+	ktime_t	blue_timer;
+	u32     p_drop;
+	bool	dropping;
+	bool    ecn_marked;
+};
+
+enum {
+	CAKE_SET_NONE = 0,
+	CAKE_SET_SPARSE,
+	CAKE_SET_SPARSE_WAIT, /* counted in SPARSE, actually in BULK */
+	CAKE_SET_BULK,
+	CAKE_SET_DECAYING
+};
+
+struct cake_flow {
+	/* this stuff is all needed per-flow at dequeue time */
+	struct sk_buff	  *head;
+	struct sk_buff	  *tail;
+	struct list_head  flowchain;
+	s32		  deficit;
+	u32		  dropped;
+	struct cobalt_vars cvars;
+	u16		  srchost; /* index into cake_host table */
+	u16		  dsthost;
+	u8		  set;
+}; /* please try to keep this structure <= 64 bytes */
+
+struct cake_host {
+	u32 srchost_tag;
+	u32 dsthost_tag;
+	u16 srchost_refcnt;
+	u16 dsthost_refcnt;
+};
+
+struct cake_heap_entry {
+	u16 t:3, b:10;
+};
+
+struct cake_tin_data {
+	struct cake_flow flows[CAKE_QUEUES];
+	u32	backlogs[CAKE_QUEUES];
+	u32	tags[CAKE_QUEUES]; /* for set association */
+	u16	overflow_idx[CAKE_QUEUES];
+	struct cake_host hosts[CAKE_QUEUES]; /* for triple isolation */
+	u16	flow_quantum;
+
+	struct cobalt_params cparams;
+	u32	drop_overlimit;
+	u16	bulk_flow_count;
+	u16	sparse_flow_count;
+	u16	decaying_flow_count;
+	u16	unresponsive_flow_count;
+
+	u32	max_skblen;
+
+	struct list_head new_flows;
+	struct list_head old_flows;
+	struct list_head decaying_flows;
+
+	/* time_next = time_this + ((len * rate_ns) >> rate_shft) */
+	ktime_t	time_next_packet;
+	u64	tin_rate_ns;
+	u64	tin_rate_bps;
+	u16	tin_rate_shft;
+
+	u16	tin_quantum_prio;
+	u16	tin_quantum_band;
+	s32	tin_deficit;
+	u32	tin_backlog;
+	u32	tin_dropped;
+	u32	tin_ecn_mark;
+
+	u32	packets;
+	u64	bytes;
+
+	u32	ack_drops;
+
+	/* moving averages */
+	u64 avge_delay;
+	u64 peak_delay;
+	u64 base_delay;
+
+	/* hash function stats */
+	u32	way_directs;
+	u32	way_hits;
+	u32	way_misses;
+	u32	way_collisions;
+}; /* number of tins is small, so size of this struct doesn't matter much */
+
+struct cake_sched_data {
+	struct tcf_proto __rcu *filter_list; /* optional external classifier */
+	struct tcf_block *block;
+	struct cake_tin_data *tins;
+
+	struct cake_heap_entry overflow_heap[CAKE_QUEUES * CAKE_MAX_TINS];
+	u16		overflow_timeout;
+
+	u16		tin_cnt;
+	u8		tin_mode;
+	u8		flow_mode;
+	u8		ack_filter;
+	u8		atm_mode;
+
+	/* time_next = time_this + ((len * rate_ns) >> rate_shft) */
+	u16		rate_shft;
+	ktime_t		time_next_packet;
+	ktime_t		failsafe_next_packet;
+	u64		rate_ns;
+	u64		rate_bps;
+	u16		rate_flags;
+	s16		rate_overhead;
+	u16		rate_mpu;
+	u64		interval;
+	u64		target;
+
+	/* resource tracking */
+	u32		buffer_used;
+	u32		buffer_max_used;
+	u32		buffer_limit;
+	u32		buffer_config_limit;
+
+	/* indices for dequeue */
+	u16		cur_tin;
+	u16		cur_flow;
+
+	struct qdisc_watchdog watchdog;
+	const u8	*tin_index;
+	const u8	*tin_order;
+
+	/* bandwidth capacity estimate */
+	ktime_t		last_packet_time;
+	ktime_t		avg_window_begin;
+	u64		avg_packet_interval;
+	u64		avg_window_bytes;
+	u64		avg_peak_bandwidth;
+	ktime_t		last_reconfig_time;
+
+	/* packet length stats */
+	u32		avg_netoff;
+	u16		max_netlen;
+	u16		max_adjlen;
+	u16		min_netlen;
+	u16		min_adjlen;
+};
+
+enum {
+	CAKE_FLAG_OVERHEAD	   = BIT(0),
+	CAKE_FLAG_AUTORATE_INGRESS = BIT(1),
+	CAKE_FLAG_INGRESS	   = BIT(2),
+	CAKE_FLAG_WASH		   = BIT(3),
+	CAKE_FLAG_SPLIT_GSO	   = BIT(4)
+};
+
+/* COBALT operates the Codel and BLUE algorithms in parallel, in order to
+ * obtain the best features of each.  Codel is excellent on flows which
+ * respond to congestion signals in a TCP-like way.  BLUE is more effective on
+ * unresponsive flows.
+ */
+
+struct cobalt_skb_cb {
+	ktime_t enqueue_time;
+};
+
+static u64 us_to_ns(u64 us)
+{
+	return us * NSEC_PER_USEC;
+}
+
+static struct cobalt_skb_cb *get_cobalt_cb(const struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct cobalt_skb_cb));
+	return (struct cobalt_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static ktime_t cobalt_get_enqueue_time(const struct sk_buff *skb)
+{
+	return get_cobalt_cb(skb)->enqueue_time;
+}
+
+static void cobalt_set_enqueue_time(struct sk_buff *skb,
+				    ktime_t now)
+{
+	get_cobalt_cb(skb)->enqueue_time = now;
+}
+
+static u16 quantum_div[CAKE_QUEUES + 1] = {0};
+
+#define REC_INV_SQRT_CACHE (16)
+static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0};
+
+/* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots
+ * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2)
+ *
+ * Here, invsqrt is a fixed point number (< 1.0), 32bit mantissa, aka Q0.32
+ */
+
+static void cobalt_newton_step(struct cobalt_vars *vars)
+{
+	u32 invsqrt, invsqrt2;
+	u64 val;
+
+	invsqrt = vars->rec_inv_sqrt;
+	invsqrt2 = ((u64)invsqrt * invsqrt) >> 32;
+	val = (3LL << 32) - ((u64)vars->count * invsqrt2);
+
+	val >>= 2; /* avoid overflow in following multiply */
+	val = (val * invsqrt) >> (32 - 2 + 1);
+
+	vars->rec_inv_sqrt = val;
+}
+
+static void cobalt_invsqrt(struct cobalt_vars *vars)
+{
+	if (vars->count < REC_INV_SQRT_CACHE)
+		vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count];
+	else
+		cobalt_newton_step(vars);
+}
+
+/* There is a big difference in timing between the accurate values placed in
+ * the cache and the approximations given by a single Newton step for small
+ * count values, particularly when stepping from count 1 to 2 or vice versa.
+ * Above 16, a single Newton step gives sufficient accuracy in either
+ * direction, given the precision stored.
+ *
+ * The magnitude of the error when stepping up to count 2 is such as to give
+ * the value that *should* have been produced at count 4.
+ */
+
+static void cobalt_cache_init(void)
+{
+	struct cobalt_vars v;
+
+	memset(&v, 0, sizeof(v));
+	v.rec_inv_sqrt = ~0U;
+	cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt;
+
+	for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) {
+		cobalt_newton_step(&v);
+		cobalt_newton_step(&v);
+		cobalt_newton_step(&v);
+		cobalt_newton_step(&v);
+
+		cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt;
+	}
+}
+
+static void cobalt_vars_init(struct cobalt_vars *vars)
+{
+	memset(vars, 0, sizeof(*vars));
+
+	if (!cobalt_rec_inv_sqrt_cache[0]) {
+		cobalt_cache_init();
+		cobalt_rec_inv_sqrt_cache[0] = ~0;
+	}
+}
+
+/* CoDel control_law is t + interval/sqrt(count)
+ * We maintain in rec_inv_sqrt the reciprocal value of sqrt(count) to avoid
+ * both sqrt() and divide operation.
+ */
+static ktime_t cobalt_control(ktime_t t,
+			      u64 interval,
+			      u32 rec_inv_sqrt)
+{
+	return ktime_add_ns(t, reciprocal_scale(interval,
+						rec_inv_sqrt));
+}
+
+/* Call this when a packet had to be dropped due to queue overflow.  Returns
+ * true if the BLUE state was quiescent before but active after this call.
+ */
+static bool cobalt_queue_full(struct cobalt_vars *vars,
+			      struct cobalt_params *p,
+			      ktime_t now)
+{
+	bool up = false;
+
+	if (ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) {
+		up = !vars->p_drop;
+		vars->p_drop += p->p_inc;
+		if (vars->p_drop < p->p_inc)
+			vars->p_drop = ~0;
+		vars->blue_timer = now;
+	}
+	vars->dropping = true;
+	vars->drop_next = now;
+	if (!vars->count)
+		vars->count = 1;
+
+	return up;
+}
+
+/* Call this when the queue was serviced but turned out to be empty.  Returns
+ * true if the BLUE state was active before but quiescent after this call.
+ */
+static bool cobalt_queue_empty(struct cobalt_vars *vars,
+			       struct cobalt_params *p,
+			       ktime_t now)
+{
+	bool down = false;
+
+	if (vars->p_drop &&
+	    ktime_to_ns(ktime_sub(now, vars->blue_timer)) > p->target) {
+		if (vars->p_drop < p->p_dec)
+			vars->p_drop = 0;
+		else
+			vars->p_drop -= p->p_dec;
+		vars->blue_timer = now;
+		down = !vars->p_drop;
+	}
+	vars->dropping = false;
+
+	if (vars->count && ktime_to_ns(ktime_sub(now, vars->drop_next)) >= 0) {
+		vars->count--;
+		cobalt_invsqrt(vars);
+		vars->drop_next = cobalt_control(vars->drop_next,
+						 p->interval,
+						 vars->rec_inv_sqrt);
+	}
+
+	return down;
+}
+
+/* Call this with a freshly dequeued packet for possible congestion marking.
+ * Returns true as an instruction to drop the packet, false for delivery.
+ */
+static bool cobalt_should_drop(struct cobalt_vars *vars,
+			       struct cobalt_params *p,
+			       ktime_t now,
+			       struct sk_buff *skb)
+{
+	bool next_due, over_target, drop = false;
+	ktime_t schedule;
+	u64 sojourn;
+
+/* The 'schedule' variable records, in its sign, whether 'now' is before or
+ * after 'drop_next'.  This allows 'drop_next' to be updated before the next
+ * scheduling decision is actually branched, without destroying that
+ * information.  Similarly, the first 'schedule' value calculated is preserved
+ * in the boolean 'next_due'.
+ *
+ * As for 'drop_next', we take advantage of the fact that 'interval' is both
+ * the delay between first exceeding 'target' and the first signalling event,
+ * *and* the scaling factor for the signalling frequency.  It's therefore very
+ * natural to use a single mechanism for both purposes, and eliminates a
+ * significant amount of reference Codel's spaghetti code.  To help with this,
+ * both the '0' and '1' entries in the invsqrt cache are 0xFFFFFFFF, as close
+ * as possible to 1.0 in fixed-point.
+ */
+
+	sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb)));
+	schedule = ktime_sub(now, vars->drop_next);
+	over_target = sojourn > p->target &&
+		      sojourn > p->mtu_time * 4;
+	next_due = vars->count && ktime_to_ns(schedule) >= 0;
+
+	vars->ecn_marked = false;
+
+	if (over_target) {
+		if (!vars->dropping) {
+			vars->dropping = true;
+			vars->drop_next = cobalt_control(now,
+							 p->interval,
+							 vars->rec_inv_sqrt);
+		}
+		if (!vars->count)
+			vars->count = 1;
+	} else if (vars->dropping) {
+		vars->dropping = false;
+	}
+
+	if (next_due && vars->dropping) {
+		/* Use ECN mark if possible, otherwise drop */
+		drop = !(vars->ecn_marked = INET_ECN_set_ce(skb));
+
+		vars->count++;
+		if (!vars->count)
+			vars->count--;
+		cobalt_invsqrt(vars);
+		vars->drop_next = cobalt_control(vars->drop_next,
+						 p->interval,
+						 vars->rec_inv_sqrt);
+		schedule = ktime_sub(now, vars->drop_next);
+	} else {
+		while (next_due) {
+			vars->count--;
+			cobalt_invsqrt(vars);
+			vars->drop_next = cobalt_control(vars->drop_next,
+							 p->interval,
+							 vars->rec_inv_sqrt);
+			schedule = ktime_sub(now, vars->drop_next);
+			next_due = vars->count && ktime_to_ns(schedule) >= 0;
+		}
+	}
+
+	/* Simple BLUE implementation.  Lack of ECN is deliberate. */
+	if (vars->p_drop)
+		drop |= (prandom_u32() < vars->p_drop);
+
+	/* Overload the drop_next field as an activity timeout */
+	if (!vars->count)
+		vars->drop_next = ktime_add_ns(now, p->interval);
+	else if (ktime_to_ns(schedule) > 0 && !drop)
+		vars->drop_next = now;
+
+	return drop;
+}
+
+/* Cake has several subtle multiple bit settings. In these cases you
+ *  would be matching triple isolate mode as well.
+ */
+
+static bool cake_dsrc(int flow_mode)
+{
+	return (flow_mode & CAKE_FLOW_DUAL_SRC) == CAKE_FLOW_DUAL_SRC;
+}
+
+static bool cake_ddst(int flow_mode)
+{
+	return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST;
+}
+
+static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
+		     int flow_mode)
+{
+	u32 flow_hash = 0, srchost_hash, dsthost_hash;
+	u16 reduced_hash, srchost_idx, dsthost_idx;
+	struct flow_keys keys, host_keys;
+
+	if (unlikely(flow_mode == CAKE_FLOW_NONE))
+		return 0;
+
+	skb_flow_dissect_flow_keys(skb, &keys,
+				   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+
+	/* flow_hash_from_keys() sorts the addresses by value, so we have
+	 * to preserve their order in a separate data structure to treat
+	 * src and dst host addresses as independently selectable.
+	 */
+	host_keys = keys;
+	host_keys.ports.ports     = 0;
+	host_keys.basic.ip_proto  = 0;
+	host_keys.keyid.keyid     = 0;
+	host_keys.tags.flow_label = 0;
+
+	switch (host_keys.control.addr_type) {
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		host_keys.addrs.v4addrs.src = 0;
+		dsthost_hash = flow_hash_from_keys(&host_keys);
+		host_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src;
+		host_keys.addrs.v4addrs.dst = 0;
+		srchost_hash = flow_hash_from_keys(&host_keys);
+		break;
+
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		memset(&host_keys.addrs.v6addrs.src, 0,
+		       sizeof(host_keys.addrs.v6addrs.src));
+		dsthost_hash = flow_hash_from_keys(&host_keys);
+		host_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src;
+		memset(&host_keys.addrs.v6addrs.dst, 0,
+		       sizeof(host_keys.addrs.v6addrs.dst));
+		srchost_hash = flow_hash_from_keys(&host_keys);
+		break;
+
+	default:
+		dsthost_hash = 0;
+		srchost_hash = 0;
+	}
+
+	/* This *must* be after the above switch, since as a
+	 * side-effect it sorts the src and dst addresses.
+	 */
+	if (flow_mode & CAKE_FLOW_FLOWS)
+		flow_hash = flow_hash_from_keys(&keys);
+
+	if (!(flow_mode & CAKE_FLOW_FLOWS)) {
+		if (flow_mode & CAKE_FLOW_SRC_IP)
+			flow_hash ^= srchost_hash;
+
+		if (flow_mode & CAKE_FLOW_DST_IP)
+			flow_hash ^= dsthost_hash;
+	}
+
+	reduced_hash = flow_hash % CAKE_QUEUES;
+
+	/* set-associative hashing */
+	/* fast path if no hash collision (direct lookup succeeds) */
+	if (likely(q->tags[reduced_hash] == flow_hash &&
+		   q->flows[reduced_hash].set)) {
+		q->way_directs++;
+	} else {
+		u32 inner_hash = reduced_hash % CAKE_SET_WAYS;
+		u32 outer_hash = reduced_hash - inner_hash;
+		bool allocate_src = false;
+		bool allocate_dst = false;
+		u32 i, k;
+
+		/* check if any active queue in the set is reserved for
+		 * this flow.
+		 */
+		for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+		     i++, k = (k + 1) % CAKE_SET_WAYS) {
+			if (q->tags[outer_hash + k] == flow_hash) {
+				if (i)
+					q->way_hits++;
+
+				if (!q->flows[outer_hash + k].set) {
+					/* need to increment host refcnts */
+					allocate_src = cake_dsrc(flow_mode);
+					allocate_dst = cake_ddst(flow_mode);
+				}
+
+				goto found;
+			}
+		}
+
+		/* no queue is reserved for this flow, look for an
+		 * empty one.
+		 */
+		for (i = 0; i < CAKE_SET_WAYS;
+			 i++, k = (k + 1) % CAKE_SET_WAYS) {
+			if (!q->flows[outer_hash + k].set) {
+				q->way_misses++;
+				allocate_src = cake_dsrc(flow_mode);
+				allocate_dst = cake_ddst(flow_mode);
+				goto found;
+			}
+		}
+
+		/* With no empty queues, default to the original
+		 * queue, accept the collision, update the host tags.
+		 */
+		q->way_collisions++;
+		q->hosts[q->flows[reduced_hash].srchost].srchost_refcnt--;
+		q->hosts[q->flows[reduced_hash].dsthost].dsthost_refcnt--;
+		allocate_src = cake_dsrc(flow_mode);
+		allocate_dst = cake_ddst(flow_mode);
+found:
+		/* reserve queue for future packets in same flow */
+		reduced_hash = outer_hash + k;
+		q->tags[reduced_hash] = flow_hash;
+
+		if (allocate_src) {
+			srchost_idx = srchost_hash % CAKE_QUEUES;
+			inner_hash = srchost_idx % CAKE_SET_WAYS;
+			outer_hash = srchost_idx - inner_hash;
+			for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+				i++, k = (k + 1) % CAKE_SET_WAYS) {
+				if (q->hosts[outer_hash + k].srchost_tag ==
+				    srchost_hash)
+					goto found_src;
+			}
+			for (i = 0; i < CAKE_SET_WAYS;
+				i++, k = (k + 1) % CAKE_SET_WAYS) {
+				if (!q->hosts[outer_hash + k].srchost_refcnt)
+					break;
+			}
+			q->hosts[outer_hash + k].srchost_tag = srchost_hash;
+found_src:
+			srchost_idx = outer_hash + k;
+			q->hosts[srchost_idx].srchost_refcnt++;
+			q->flows[reduced_hash].srchost = srchost_idx;
+		}
+
+		if (allocate_dst) {
+			dsthost_idx = dsthost_hash % CAKE_QUEUES;
+			inner_hash = dsthost_idx % CAKE_SET_WAYS;
+			outer_hash = dsthost_idx - inner_hash;
+			for (i = 0, k = inner_hash; i < CAKE_SET_WAYS;
+			     i++, k = (k + 1) % CAKE_SET_WAYS) {
+				if (q->hosts[outer_hash + k].dsthost_tag ==
+				    dsthost_hash)
+					goto found_dst;
+			}
+			for (i = 0; i < CAKE_SET_WAYS;
+			     i++, k = (k + 1) % CAKE_SET_WAYS) {
+				if (!q->hosts[outer_hash + k].dsthost_refcnt)
+					break;
+			}
+			q->hosts[outer_hash + k].dsthost_tag = dsthost_hash;
+found_dst:
+			dsthost_idx = outer_hash + k;
+			q->hosts[dsthost_idx].dsthost_refcnt++;
+			q->flows[reduced_hash].dsthost = dsthost_idx;
+		}
+	}
+
+	return reduced_hash;
+}
+
+/* helper functions : might be changed when/if skb use a standard list_head */
+/* remove one skb from head of slot queue */
+
+static struct sk_buff *dequeue_head(struct cake_flow *flow)
+{
+	struct sk_buff *skb = flow->head;
+
+	if (skb) {
+		flow->head = skb->next;
+		skb->next = NULL;
+	}
+
+	return skb;
+}
+
+/* add skb to flow queue (tail add) */
+
+static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb)
+{
+	if (!flow->head)
+		flow->head = skb;
+	else
+		flow->tail->next = skb;
+	flow->tail = skb;
+	skb->next = NULL;
+}
+
+static u64 cake_ewma(u64 avg, u64 sample, u32 shift)
+{
+	avg -= avg >> shift;
+	avg += sample >> shift;
+	return avg;
+}
+
+static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j)
+{
+	struct cake_heap_entry ii = q->overflow_heap[i];
+	struct cake_heap_entry jj = q->overflow_heap[j];
+
+	q->overflow_heap[i] = jj;
+	q->overflow_heap[j] = ii;
+
+	q->tins[ii.t].overflow_idx[ii.b] = j;
+	q->tins[jj.t].overflow_idx[jj.b] = i;
+}
+
+static u32 cake_heap_get_backlog(const struct cake_sched_data *q, u16 i)
+{
+	struct cake_heap_entry ii = q->overflow_heap[i];
+
+	return q->tins[ii.t].backlogs[ii.b];
+}
+
+static void cake_heapify(struct cake_sched_data *q, u16 i)
+{
+	static const u32 a = CAKE_MAX_TINS * CAKE_QUEUES;
+	u32 mb = cake_heap_get_backlog(q, i);
+	u32 m = i;
+
+	while (m < a) {
+		u32 l = m + m + 1;
+		u32 r = l + 1;
+
+		if (l < a) {
+			u32 lb = cake_heap_get_backlog(q, l);
+
+			if (lb > mb) {
+				m  = l;
+				mb = lb;
+			}
+		}
+
+		if (r < a) {
+			u32 rb = cake_heap_get_backlog(q, r);
+
+			if (rb > mb) {
+				m  = r;
+				mb = rb;
+			}
+		}
+
+		if (m != i) {
+			cake_heap_swap(q, i, m);
+			i = m;
+		} else {
+			break;
+		}
+	}
+}
+
+static void cake_heapify_up(struct cake_sched_data *q, u16 i)
+{
+	while (i > 0 && i < CAKE_MAX_TINS * CAKE_QUEUES) {
+		u16 p = (i - 1) >> 1;
+		u32 ib = cake_heap_get_backlog(q, i);
+		u32 pb = cake_heap_get_backlog(q, p);
+
+		if (ib > pb) {
+			cake_heap_swap(q, i, p);
+			i = p;
+		} else {
+			break;
+		}
+	}
+}
+
+static int cake_advance_shaper(struct cake_sched_data *q,
+			       struct cake_tin_data *b,
+			       struct sk_buff *skb,
+			       ktime_t now, bool drop)
+{
+	u32 len = qdisc_pkt_len(skb);
+
+	/* charge packet bandwidth to this tin
+	 * and to the global shaper.
+	 */
+	if (q->rate_ns) {
+		u64 tin_dur = (len * b->tin_rate_ns) >> b->tin_rate_shft;
+		u64 global_dur = (len * q->rate_ns) >> q->rate_shft;
+		u64 failsafe_dur = global_dur + (global_dur >> 1);
+
+		if (ktime_before(b->time_next_packet, now))
+			b->time_next_packet = ktime_add_ns(b->time_next_packet,
+							   tin_dur);
+
+		else if (ktime_before(b->time_next_packet,
+				      ktime_add_ns(now, tin_dur)))
+			b->time_next_packet = ktime_add_ns(now, tin_dur);
+
+		q->time_next_packet = ktime_add_ns(q->time_next_packet,
+						   global_dur);
+		if (!drop)
+			q->failsafe_next_packet = \
+				ktime_add_ns(q->failsafe_next_packet,
+					     failsafe_dur);
+	}
+	return len;
+}
+
+static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	ktime_t now = ktime_get();
+	u32 idx = 0, tin = 0, len;
+	struct cake_heap_entry qq;
+	struct cake_tin_data *b;
+	struct cake_flow *flow;
+	struct sk_buff *skb;
+
+	if (!q->overflow_timeout) {
+		int i;
+		/* Build fresh max-heap */
+		for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2; i >= 0; i--)
+			cake_heapify(q, i);
+	}
+	q->overflow_timeout = 65535;
+
+	/* select longest queue for pruning */
+	qq  = q->overflow_heap[0];
+	tin = qq.t;
+	idx = qq.b;
+
+	b = &q->tins[tin];
+	flow = &b->flows[idx];
+	skb = dequeue_head(flow);
+	if (unlikely(!skb)) {
+		/* heap has gone wrong, rebuild it next time */
+		q->overflow_timeout = 0;
+		return idx + (tin << 16);
+	}
+
+	if (cobalt_queue_full(&flow->cvars, &b->cparams, now))
+		b->unresponsive_flow_count++;
+
+	len = qdisc_pkt_len(skb);
+	q->buffer_used      -= skb->truesize;
+	b->backlogs[idx]    -= len;
+	b->tin_backlog      -= len;
+	sch->qstats.backlog -= len;
+	qdisc_tree_reduce_backlog(sch, 1, len);
+
+	flow->dropped++;
+	b->tin_dropped++;
+	sch->qstats.drops++;
+
+	__qdisc_drop(skb, to_free);
+	sch->q.qlen--;
+
+	cake_heapify(q, 0);
+
+	return idx + (tin << 16);
+}
+
+static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data *t,
+			 struct sk_buff *skb, int flow_mode, int *qerr)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct tcf_proto *filter;
+	struct tcf_result res;
+	int result;
+
+	filter = rcu_dereference_bh(q->filter_list);
+	if (!filter)
+		return cake_hash(t, skb, flow_mode) + 1;
+
+	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+	result = tcf_classify(skb, filter, &res, false);
+	if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+		switch (result) {
+		case TC_ACT_STOLEN:
+		case TC_ACT_QUEUED:
+		case TC_ACT_TRAP:
+			*qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+			/* fall through */
+		case TC_ACT_SHOT:
+			return 0;
+		}
+#endif
+		if (TC_H_MIN(res.classid) <= CAKE_QUEUES)
+			return TC_H_MIN(res.classid);
+	}
+	return 0;
+}
+
+static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			struct sk_buff **to_free)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	int len = qdisc_pkt_len(skb);
+	int uninitialized_var(ret);
+	ktime_t now = ktime_get();
+	struct cake_tin_data *b;
+	struct cake_flow *flow;
+	u32 idx, tin;
+
+	tin = 0;
+	b = &q->tins[tin];
+
+	/* choose flow to insert into */
+	idx = cake_classify(sch, b, skb, q->flow_mode, &ret);
+	if (idx == 0) {
+		if (ret & __NET_XMIT_BYPASS)
+			qdisc_qstats_drop(sch);
+		__qdisc_drop(skb, to_free);
+		return ret;
+	}
+	idx--;
+	flow = &b->flows[idx];
+
+	/* ensure shaper state isn't stale */
+	if (!b->tin_backlog) {
+		if (ktime_before(b->time_next_packet, now))
+			b->time_next_packet = now;
+
+		if (!sch->q.qlen) {
+			if (ktime_before(q->time_next_packet, now)) {
+				q->failsafe_next_packet = now;
+				q->time_next_packet = now;
+			} else if (ktime_after(q->time_next_packet, now) &&
+				   ktime_after(q->failsafe_next_packet, now)) {
+				u64 next = \
+					min(ktime_to_ns(q->time_next_packet),
+					    ktime_to_ns(
+						   q->failsafe_next_packet));
+				sch->qstats.overlimits++;
+				qdisc_watchdog_schedule_ns(&q->watchdog, next);
+			}
+		}
+	}
+
+	if (unlikely(len > b->max_skblen))
+		b->max_skblen = len;
+
+	cobalt_set_enqueue_time(skb, now);
+	flow_queue_add(flow, skb);
+
+	sch->q.qlen++;
+	q->buffer_used      += skb->truesize;
+
+	/* stats */
+	b->packets++;
+	b->bytes	    += len;
+	b->backlogs[idx]    += len;
+	b->tin_backlog      += len;
+	sch->qstats.backlog += len;
+	q->avg_window_bytes += len;
+
+	if (q->overflow_timeout)
+		cake_heapify_up(q, b->overflow_idx[idx]);
+
+	/* incoming bandwidth capacity estimate */
+	q->avg_window_bytes = 0;
+	q->last_packet_time = now;
+
+	/* flowchain */
+	if (!flow->set || flow->set == CAKE_SET_DECAYING) {
+		struct cake_host *srchost = &b->hosts[flow->srchost];
+		struct cake_host *dsthost = &b->hosts[flow->dsthost];
+		u16 host_load = 1;
+
+		if (!flow->set) {
+			list_add_tail(&flow->flowchain, &b->new_flows);
+		} else {
+			b->decaying_flow_count--;
+			list_move_tail(&flow->flowchain, &b->new_flows);
+		}
+		flow->set = CAKE_SET_SPARSE;
+		b->sparse_flow_count++;
+
+		if (cake_dsrc(q->flow_mode))
+			host_load = max(host_load, srchost->srchost_refcnt);
+
+		if (cake_ddst(q->flow_mode))
+			host_load = max(host_load, dsthost->dsthost_refcnt);
+
+		flow->deficit = (b->flow_quantum *
+				 quantum_div[host_load]) >> 16;
+	} else if (flow->set == CAKE_SET_SPARSE_WAIT) {
+		/* this flow was empty, accounted as a sparse flow, but actually
+		 * in the bulk rotation.
+		 */
+		flow->set = CAKE_SET_BULK;
+		b->sparse_flow_count--;
+		b->bulk_flow_count++;
+	}
+
+	if (q->buffer_used > q->buffer_max_used)
+		q->buffer_max_used = q->buffer_used;
+
+	if (q->buffer_used > q->buffer_limit) {
+		u32 dropped = 0;
+
+		while (q->buffer_used > q->buffer_limit) {
+			dropped++;
+			cake_drop(sch, to_free);
+		}
+		b->drop_overlimit += dropped;
+	}
+	return NET_XMIT_SUCCESS;
+}
+
+static struct sk_buff *cake_dequeue_one(struct Qdisc *sch)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct cake_tin_data *b = &q->tins[q->cur_tin];
+	struct cake_flow *flow = &b->flows[q->cur_flow];
+	struct sk_buff *skb = NULL;
+	u32 len;
+
+	if (flow->head) {
+		skb = dequeue_head(flow);
+		len = qdisc_pkt_len(skb);
+		b->backlogs[q->cur_flow] -= len;
+		b->tin_backlog		 -= len;
+		sch->qstats.backlog      -= len;
+		q->buffer_used		 -= skb->truesize;
+		sch->q.qlen--;
+
+		if (q->overflow_timeout)
+			cake_heapify(q, b->overflow_idx[q->cur_flow]);
+	}
+	return skb;
+}
+
+/* Discard leftover packets from a tin no longer in use. */
+static void cake_clear_tin(struct Qdisc *sch, u16 tin)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+
+	q->cur_tin = tin;
+	for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++)
+		while (!!(skb = cake_dequeue_one(sch)))
+			kfree_skb(skb);
+}
+
+static struct sk_buff *cake_dequeue(struct Qdisc *sch)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct cake_tin_data *b = &q->tins[q->cur_tin];
+	struct cake_host *srchost, *dsthost;
+	ktime_t now = ktime_get();
+	struct cake_flow *flow;
+	struct list_head *head;
+	bool first_flow = true;
+	struct sk_buff *skb;
+	u16 host_load;
+	u64 delay;
+	u32 len;
+
+begin:
+	if (!sch->q.qlen)
+		return NULL;
+
+	/* global hard shaper */
+	if (ktime_after(q->time_next_packet, now) &&
+	    ktime_after(q->failsafe_next_packet, now)) {
+		u64 next = min(ktime_to_ns(q->time_next_packet),
+			       ktime_to_ns(q->failsafe_next_packet));
+
+		sch->qstats.overlimits++;
+		qdisc_watchdog_schedule_ns(&q->watchdog, next);
+		return NULL;
+	}
+
+	/* Choose a class to work on. */
+	if (!q->rate_ns) {
+		/* In unlimited mode, can't rely on shaper timings, just balance
+		 * with DRR
+		 */
+		bool wrapped = false, empty = true;
+
+		while (b->tin_deficit < 0 ||
+		       !(b->sparse_flow_count + b->bulk_flow_count)) {
+			if (b->tin_deficit <= 0)
+				b->tin_deficit += b->tin_quantum_band;
+			if (b->sparse_flow_count + b->bulk_flow_count)
+				empty = false;
+
+			q->cur_tin++;
+			b++;
+			if (q->cur_tin >= q->tin_cnt) {
+				q->cur_tin = 0;
+				b = q->tins;
+
+				if (wrapped) {
+					/* It's possible for q->qlen to be
+					 * nonzero when we actually have no
+					 * packets anywhere.
+					 */
+					if (empty)
+						return NULL;
+				} else {
+					wrapped = true;
+				}
+			}
+		}
+	} else {
+		/* In shaped mode, choose:
+		 * - Highest-priority tin with queue and meeting schedule, or
+		 * - The earliest-scheduled tin with queue.
+		 */
+		ktime_t best_time = KTIME_MAX;
+		int tin, best_tin = 0;
+
+		for (tin = 0; tin < q->tin_cnt; tin++) {
+			b = q->tins + tin;
+			if ((b->sparse_flow_count + b->bulk_flow_count) > 0) {
+				ktime_t time_to_pkt = \
+					ktime_sub(b->time_next_packet, now);
+
+				if (ktime_to_ns(time_to_pkt) <= 0 ||
+				    ktime_compare(time_to_pkt,
+						  best_time) <= 0) {
+					best_time = time_to_pkt;
+					best_tin = tin;
+				}
+			}
+		}
+
+		q->cur_tin = best_tin;
+		b = q->tins + best_tin;
+
+		/* No point in going further if no packets to deliver. */
+		if (unlikely(!(b->sparse_flow_count + b->bulk_flow_count)))
+			return NULL;
+	}
+
+retry:
+	/* service this class */
+	head = &b->decaying_flows;
+	if (!first_flow || list_empty(head)) {
+		head = &b->new_flows;
+		if (list_empty(head)) {
+			head = &b->old_flows;
+			if (unlikely(list_empty(head))) {
+				head = &b->decaying_flows;
+				if (unlikely(list_empty(head)))
+					goto begin;
+			}
+		}
+	}
+	flow = list_first_entry(head, struct cake_flow, flowchain);
+	q->cur_flow = flow - b->flows;
+	first_flow = false;
+
+	/* triple isolation (modified DRR++) */
+	srchost = &b->hosts[flow->srchost];
+	dsthost = &b->hosts[flow->dsthost];
+	host_load = 1;
+
+	if (cake_dsrc(q->flow_mode))
+		host_load = max(host_load, srchost->srchost_refcnt);
+
+	if (cake_ddst(q->flow_mode))
+		host_load = max(host_load, dsthost->dsthost_refcnt);
+
+	WARN_ON(host_load > CAKE_QUEUES);
+
+	/* flow isolation (DRR++) */
+	if (flow->deficit <= 0) {
+		/* The shifted prandom_u32() is a way to apply dithering to
+		 * avoid accumulating roundoff errors
+		 */
+		flow->deficit += (b->flow_quantum * quantum_div[host_load] +
+				  (prandom_u32() >> 16)) >> 16;
+		list_move_tail(&flow->flowchain, &b->old_flows);
+
+		/* Keep all flows with deficits out of the sparse and decaying
+		 * rotations.  No non-empty flow can go into the decaying
+		 * rotation, so they can't get deficits
+		 */
+		if (flow->set == CAKE_SET_SPARSE) {
+			if (flow->head) {
+				b->sparse_flow_count--;
+				b->bulk_flow_count++;
+				flow->set = CAKE_SET_BULK;
+			} else {
+				/* we've moved it to the bulk rotation for
+				 * correct deficit accounting but we still want
+				 * to count it as a sparse flow, not a bulk one.
+				 */
+				flow->set = CAKE_SET_SPARSE_WAIT;
+			}
+		}
+		goto retry;
+	}
+
+	/* Retrieve a packet via the AQM */
+	while (1) {
+		skb = cake_dequeue_one(sch);
+		if (!skb) {
+			/* this queue was actually empty */
+			if (cobalt_queue_empty(&flow->cvars, &b->cparams, now))
+				b->unresponsive_flow_count--;
+
+			if (flow->cvars.p_drop || flow->cvars.count ||
+			    ktime_before(now, flow->cvars.drop_next)) {
+				/* keep in the flowchain until the state has
+				 * decayed to rest
+				 */
+				list_move_tail(&flow->flowchain,
+					       &b->decaying_flows);
+				if (flow->set == CAKE_SET_BULK) {
+					b->bulk_flow_count--;
+					b->decaying_flow_count++;
+				} else if (flow->set == CAKE_SET_SPARSE ||
+					   flow->set == CAKE_SET_SPARSE_WAIT) {
+					b->sparse_flow_count--;
+					b->decaying_flow_count++;
+				}
+				flow->set = CAKE_SET_DECAYING;
+			} else {
+				/* remove empty queue from the flowchain */
+				list_del_init(&flow->flowchain);
+				if (flow->set == CAKE_SET_SPARSE ||
+				    flow->set == CAKE_SET_SPARSE_WAIT)
+					b->sparse_flow_count--;
+				else if (flow->set == CAKE_SET_BULK)
+					b->bulk_flow_count--;
+				else
+					b->decaying_flow_count--;
+
+				flow->set = CAKE_SET_NONE;
+				srchost->srchost_refcnt--;
+				dsthost->dsthost_refcnt--;
+			}
+			goto begin;
+		}
+
+		/* Last packet in queue may be marked, shouldn't be dropped */
+		if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb) ||
+		    !flow->head)
+			break;
+
+		flow->dropped++;
+		b->tin_dropped++;
+		qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
+		qdisc_qstats_drop(sch);
+		kfree_skb(skb);
+	}
+
+	b->tin_ecn_mark += !!flow->cvars.ecn_marked;
+	qdisc_bstats_update(sch, skb);
+
+	/* collect delay stats */
+	delay = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb)));
+	b->avge_delay = cake_ewma(b->avge_delay, delay, 8);
+	b->peak_delay = cake_ewma(b->peak_delay, delay,
+				  delay > b->peak_delay ? 2 : 8);
+	b->base_delay = cake_ewma(b->base_delay, delay,
+				  delay < b->base_delay ? 2 : 8);
+
+	len = cake_advance_shaper(q, b, skb, now, false);
+	flow->deficit -= len;
+	b->tin_deficit -= len;
+
+	if (ktime_after(q->time_next_packet, now) && sch->q.qlen) {
+		u64 next = min(ktime_to_ns(q->time_next_packet),
+			       ktime_to_ns(q->failsafe_next_packet));
+
+		qdisc_watchdog_schedule_ns(&q->watchdog, next);
+	} else if (!sch->q.qlen) {
+		int i;
+
+		for (i = 0; i < q->tin_cnt; i++) {
+			if (q->tins[i].decaying_flow_count) {
+				ktime_t next = \
+					ktime_add_ns(now,
+						     q->tins[i].cparams.target);
+
+				qdisc_watchdog_schedule_ns(&q->watchdog,
+							   ktime_to_ns(next));
+				break;
+			}
+		}
+	}
+
+	if (q->overflow_timeout)
+		q->overflow_timeout--;
+
+	return skb;
+}
+
+static void cake_reset(struct Qdisc *sch)
+{
+	u32 c;
+
+	for (c = 0; c < CAKE_MAX_TINS; c++)
+		cake_clear_tin(sch, c);
+}
+
+static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = {
+	[TCA_CAKE_BASE_RATE64]   = { .type = NLA_U64 },
+	[TCA_CAKE_DIFFSERV_MODE] = { .type = NLA_U32 },
+	[TCA_CAKE_ATM]		 = { .type = NLA_U32 },
+	[TCA_CAKE_FLOW_MODE]     = { .type = NLA_U32 },
+	[TCA_CAKE_OVERHEAD]      = { .type = NLA_S32 },
+	[TCA_CAKE_RTT]		 = { .type = NLA_U32 },
+	[TCA_CAKE_TARGET]	 = { .type = NLA_U32 },
+	[TCA_CAKE_AUTORATE]      = { .type = NLA_U32 },
+	[TCA_CAKE_MEMORY]	 = { .type = NLA_U32 },
+	[TCA_CAKE_NAT]		 = { .type = NLA_U32 },
+	[TCA_CAKE_RAW]		 = { .type = NLA_U32 },
+	[TCA_CAKE_WASH]		 = { .type = NLA_U32 },
+	[TCA_CAKE_MPU]		 = { .type = NLA_U32 },
+	[TCA_CAKE_INGRESS]	 = { .type = NLA_U32 },
+	[TCA_CAKE_ACK_FILTER]	 = { .type = NLA_U32 },
+};
+
+static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
+			  u64 target_ns, u64 rtt_est_ns)
+{
+	/* convert byte-rate into time-per-byte
+	 * so it will always unwedge in reasonable time.
+	 */
+	static const u64 MIN_RATE = 64;
+	u32 byte_target = mtu;
+	u64 byte_target_ns;
+	u8  rate_shft = 0;
+	u64 rate_ns = 0;
+
+	b->flow_quantum = 1514;
+	if (rate) {
+		b->flow_quantum = max(min(rate >> 12, 1514ULL), 300ULL);
+		rate_shft = 34;
+		rate_ns = ((u64)NSEC_PER_SEC) << rate_shft;
+		rate_ns = div64_u64(rate_ns, max(MIN_RATE, rate));
+		while (!!(rate_ns >> 34)) {
+			rate_ns >>= 1;
+			rate_shft--;
+		}
+	} /* else unlimited, ie. zero delay */
+
+	b->tin_rate_bps  = rate;
+	b->tin_rate_ns   = rate_ns;
+	b->tin_rate_shft = rate_shft;
+
+	byte_target_ns = (byte_target * rate_ns) >> rate_shft;
+
+	b->cparams.target = max((byte_target_ns * 3) / 2, target_ns);
+	b->cparams.interval = max(rtt_est_ns +
+				     b->cparams.target - target_ns,
+				     b->cparams.target * 2);
+	b->cparams.mtu_time = byte_target_ns;
+	b->cparams.p_inc = 1 << 24; /* 1/256 */
+	b->cparams.p_dec = 1 << 20; /* 1/4096 */
+}
+
+static void cake_reconfigure(struct Qdisc *sch)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct cake_tin_data *b = &q->tins[0];
+	int c, ft = 0;
+
+	q->tin_cnt = 1;
+	cake_set_rate(b, q->rate_bps, psched_mtu(qdisc_dev(sch)),
+		      us_to_ns(q->target), us_to_ns(q->interval));
+	b->tin_quantum_band = 65535;
+	b->tin_quantum_prio = 65535;
+
+	for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) {
+		cake_clear_tin(sch, c);
+		q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time;
+	}
+
+	q->rate_ns   = q->tins[ft].tin_rate_ns;
+	q->rate_shft = q->tins[ft].tin_rate_shft;
+
+	if (q->buffer_config_limit) {
+		q->buffer_limit = q->buffer_config_limit;
+	} else if (q->rate_bps) {
+		u64 t = q->rate_bps * q->interval;
+
+		do_div(t, USEC_PER_SEC / 4);
+		q->buffer_limit = max_t(u32, t, 4U << 20);
+	} else {
+		q->buffer_limit = ~0;
+	}
+
+	sch->flags &= ~TCQ_F_CAN_BYPASS;
+
+	q->buffer_limit = min(q->buffer_limit,
+			      max(sch->limit * psched_mtu(qdisc_dev(sch)),
+				  q->buffer_config_limit));
+}
+
+static int cake_change(struct Qdisc *sch, struct nlattr *opt,
+		       struct netlink_ext_ack *extack)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tb[TCA_CAKE_MAX + 1];
+	int err;
+
+	if (!opt)
+		return -EINVAL;
+
+	err = nla_parse_nested(tb, TCA_CAKE_MAX, opt, cake_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (tb[TCA_CAKE_BASE_RATE64])
+		q->rate_bps = nla_get_u64(tb[TCA_CAKE_BASE_RATE64]);
+
+	if (tb[TCA_CAKE_FLOW_MODE])
+		q->flow_mode = (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
+				CAKE_FLOW_MASK);
+
+	if (tb[TCA_CAKE_RTT]) {
+		q->interval = nla_get_u32(tb[TCA_CAKE_RTT]);
+
+		if (!q->interval)
+			q->interval = 1;
+	}
+
+	if (tb[TCA_CAKE_TARGET]) {
+		q->target = nla_get_u32(tb[TCA_CAKE_TARGET]);
+
+		if (!q->target)
+			q->target = 1;
+	}
+
+	if (tb[TCA_CAKE_MEMORY])
+		q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
+
+	if (q->tins) {
+		sch_tree_lock(sch);
+		cake_reconfigure(sch);
+		sch_tree_unlock(sch);
+	}
+
+	return 0;
+}
+
+static void cake_destroy(struct Qdisc *sch)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+
+	qdisc_watchdog_cancel(&q->watchdog);
+	tcf_block_put(q->block);
+	kvfree(q->tins);
+}
+
+static int cake_init(struct Qdisc *sch, struct nlattr *opt,
+		     struct netlink_ext_ack *extack)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	int i, j, err;
+
+	sch->limit = 10240;
+	q->tin_mode = CAKE_DIFFSERV_BESTEFFORT;
+	q->flow_mode  = CAKE_FLOW_TRIPLE;
+
+	q->rate_bps = 0; /* unlimited by default */
+
+	q->interval = 100000; /* 100ms default */
+	q->target   =   5000; /* 5ms: codel RFC argues
+			       * for 5 to 10% of interval
+			       */
+
+	q->cur_tin = 0;
+	q->cur_flow  = 0;
+
+	qdisc_watchdog_init(&q->watchdog, sch);
+
+	if (opt) {
+		int err = cake_change(sch, opt, extack);
+
+		if (err)
+			return err;
+	}
+
+	err = tcf_block_get(&q->block, &q->filter_list, sch, extack);
+	if (err)
+		return err;
+
+	quantum_div[0] = ~0;
+	for (i = 1; i <= CAKE_QUEUES; i++)
+		quantum_div[i] = 65535 / i;
+
+	q->tins = kvzalloc(CAKE_MAX_TINS * sizeof(struct cake_tin_data),
+			   GFP_KERNEL);
+	if (!q->tins)
+		goto nomem;
+
+	for (i = 0; i < CAKE_MAX_TINS; i++) {
+		struct cake_tin_data *b = q->tins + i;
+
+		INIT_LIST_HEAD(&b->new_flows);
+		INIT_LIST_HEAD(&b->old_flows);
+		INIT_LIST_HEAD(&b->decaying_flows);
+		b->sparse_flow_count = 0;
+		b->bulk_flow_count = 0;
+		b->decaying_flow_count = 0;
+
+		for (j = 0; j < CAKE_QUEUES; j++) {
+			struct cake_flow *flow = b->flows + j;
+			u32 k = j * CAKE_MAX_TINS + i;
+
+			INIT_LIST_HEAD(&flow->flowchain);
+			cobalt_vars_init(&flow->cvars);
+
+			q->overflow_heap[k].t = i;
+			q->overflow_heap[k].b = j;
+			b->overflow_idx[j] = k;
+		}
+	}
+
+	cake_reconfigure(sch);
+	q->avg_peak_bandwidth = q->rate_bps;
+	q->min_netlen = ~0;
+	q->min_adjlen = ~0;
+	return 0;
+
+nomem:
+	cake_destroy(sch);
+	return -ENOMEM;
+}
+
+static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+
+	opts = nla_nest_start(skb, TCA_OPTIONS);
+	if (!opts)
+		goto nla_put_failure;
+
+	if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, q->rate_bps,
+			      TCA_CAKE_PAD))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE,
+			q->flow_mode & CAKE_FLOW_MASK))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_RTT, q->interval))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_TARGET, q->target))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_MEMORY, q->buffer_config_limit))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	return -1;
+}
+
+static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct nlattr *stats = nla_nest_start(d->skb, TCA_STATS_APP);
+	struct cake_sched_data *q = qdisc_priv(sch);
+	struct nlattr *tstats, *ts;
+	int i;
+
+	if (!stats)
+		return -1;
+
+#define PUT_STAT_U32(attr, data) do {				       \
+		if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \
+			goto nla_put_failure;			       \
+	} while (0)
+#define PUT_STAT_U64(attr, data) do {				       \
+		if (nla_put_u64_64bit(d->skb, TCA_CAKE_STATS_ ## attr, \
+					data, TCA_CAKE_STATS_PAD)) \
+			goto nla_put_failure;			       \
+	} while (0)
+
+	PUT_STAT_U64(CAPACITY_ESTIMATE64, q->avg_peak_bandwidth);
+	PUT_STAT_U32(MEMORY_LIMIT, q->buffer_limit);
+	PUT_STAT_U32(MEMORY_USED, q->buffer_max_used);
+	PUT_STAT_U32(AVG_NETOFF, ((q->avg_netoff + 0x8000) >> 16));
+	PUT_STAT_U32(MAX_NETLEN, q->max_netlen);
+	PUT_STAT_U32(MAX_ADJLEN, q->max_adjlen);
+	PUT_STAT_U32(MIN_NETLEN, q->min_netlen);
+	PUT_STAT_U32(MIN_ADJLEN, q->min_adjlen);
+
+#undef PUT_STAT_U32
+#undef PUT_STAT_U64
+
+	tstats = nla_nest_start(d->skb, TCA_CAKE_STATS_TIN_STATS);
+	if (!tstats)
+		goto nla_put_failure;
+
+#define PUT_TSTAT_U32(attr, data) do {					\
+		if (nla_put_u32(d->skb, TCA_CAKE_TIN_STATS_ ## attr, data)) \
+			goto nla_put_failure;				\
+	} while (0)
+#define PUT_TSTAT_U64(attr, data) do {					\
+		if (nla_put_u64_64bit(d->skb, TCA_CAKE_TIN_STATS_ ## attr, \
+					data, TCA_CAKE_TIN_STATS_PAD))	\
+			goto nla_put_failure;				\
+	} while (0)
+
+	for (i = 0; i < q->tin_cnt; i++) {
+		struct cake_tin_data *b = &q->tins[i];
+
+		ts = nla_nest_start(d->skb, i + 1);
+		if (!ts)
+			goto nla_put_failure;
+
+		PUT_TSTAT_U64(THRESHOLD_RATE64, b->tin_rate_bps);
+		PUT_TSTAT_U64(SENT_BYTES64, b->bytes);
+		PUT_TSTAT_U32(BACKLOG_BYTES, b->tin_backlog);
+
+		PUT_TSTAT_U32(TARGET_US,
+			      ktime_to_us(ns_to_ktime(b->cparams.target)));
+		PUT_TSTAT_U32(INTERVAL_US,
+			      ktime_to_us(ns_to_ktime(b->cparams.interval)));
+
+		PUT_TSTAT_U32(SENT_PACKETS, b->packets);
+		PUT_TSTAT_U32(DROPPED_PACKETS, b->tin_dropped);
+		PUT_TSTAT_U32(ECN_MARKED_PACKETS, b->tin_ecn_mark);
+		PUT_TSTAT_U32(ACKS_DROPPED_PACKETS, b->ack_drops);
+
+		PUT_TSTAT_U32(PEAK_DELAY_US,
+			      ktime_to_us(ns_to_ktime(b->peak_delay)));
+		PUT_TSTAT_U32(AVG_DELAY_US,
+			      ktime_to_us(ns_to_ktime(b->avge_delay)));
+		PUT_TSTAT_U32(BASE_DELAY_US,
+			      ktime_to_us(ns_to_ktime(b->base_delay)));
+
+		PUT_TSTAT_U32(WAY_INDIRECT_HITS, b->way_hits);
+		PUT_TSTAT_U32(WAY_MISSES, b->way_misses);
+		PUT_TSTAT_U32(WAY_COLLISIONS, b->way_collisions);
+
+		PUT_TSTAT_U32(SPARSE_FLOWS, b->sparse_flow_count +
+					    b->decaying_flow_count);
+		PUT_TSTAT_U32(BULK_FLOWS, b->bulk_flow_count);
+		PUT_TSTAT_U32(UNRESPONSIVE_FLOWS, b->unresponsive_flow_count);
+		PUT_TSTAT_U32(MAX_SKBLEN, b->max_skblen);
+
+		PUT_TSTAT_U32(FLOW_QUANTUM, b->flow_quantum);
+		nla_nest_end(d->skb, ts);
+	}
+
+#undef PUT_TSTAT_U32
+#undef PUT_TSTAT_U64
+
+	nla_nest_end(d->skb, tstats);
+	return nla_nest_end(d->skb, stats);
+
+nla_put_failure:
+	nla_nest_cancel(d->skb, stats);
+	return -1;
+}
+
+static struct Qdisc *cake_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	return NULL;
+}
+
+static unsigned long cake_find(struct Qdisc *sch, u32 classid)
+{
+	return 0;
+}
+
+static unsigned long cake_bind(struct Qdisc *sch, unsigned long parent,
+			       u32 classid)
+{
+	return 0;
+}
+
+static void cake_unbind(struct Qdisc *q, unsigned long cl)
+{
+}
+
+static struct tcf_block *cake_tcf_block(struct Qdisc *sch, unsigned long cl,
+					struct netlink_ext_ack *extack)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+
+	if (cl)
+		return NULL;
+	return q->block;
+}
+
+static int cake_dump_class(struct Qdisc *sch, unsigned long cl,
+			   struct sk_buff *skb, struct tcmsg *tcm)
+{
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	return 0;
+}
+
+static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+				 struct gnet_dump *d)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	const struct cake_flow *flow = NULL;
+	struct gnet_stats_queue qs = { 0 };
+	struct nlattr *stats;
+	u32 idx = cl - 1;
+
+	if (idx < CAKE_QUEUES * q->tin_cnt) {
+		const struct cake_tin_data *b = &q->tins[idx / CAKE_QUEUES];
+		const struct sk_buff *skb;
+
+		flow = &b->flows[idx % CAKE_QUEUES];
+
+		if (flow->head) {
+			sch_tree_lock(sch);
+			skb = flow->head;
+			while (skb) {
+				qs.qlen++;
+				skb = skb->next;
+			}
+			sch_tree_unlock(sch);
+		}
+		qs.backlog = b->backlogs[idx % CAKE_QUEUES];
+		qs.drops = flow->dropped;
+	}
+	if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
+		return -1;
+	if (flow) {
+		ktime_t now = ktime_get();
+
+		stats = nla_nest_start(d->skb, TCA_STATS_APP);
+		if (!stats)
+			return -1;
+
+#define PUT_STAT_U32(attr, data) do {				       \
+		if (nla_put_u32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \
+			goto nla_put_failure;			       \
+	} while (0)
+#define PUT_STAT_S32(attr, data) do {				       \
+		if (nla_put_s32(d->skb, TCA_CAKE_STATS_ ## attr, data)) \
+			goto nla_put_failure;			       \
+	} while (0)
+
+		PUT_STAT_S32(DEFICIT, flow->deficit);
+		PUT_STAT_U32(DROPPING, flow->cvars.dropping);
+		PUT_STAT_U32(COBALT_COUNT, flow->cvars.count);
+		PUT_STAT_U32(P_DROP, flow->cvars.p_drop);
+		if (flow->cvars.p_drop) {
+			PUT_STAT_S32(BLUE_TIMER_US,
+				     ktime_to_us(
+					     ktime_sub(now,
+						     flow->cvars.blue_timer)));
+		}
+		if (flow->cvars.dropping) {
+			PUT_STAT_S32(DROP_NEXT_US,
+				     ktime_to_us(
+					     ktime_sub(now,
+						       flow->cvars.drop_next)));
+		}
+
+		if (nla_nest_end(d->skb, stats) < 0)
+			return -1;
+	}
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(d->skb, stats);
+	return -1;
+}
+
+static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	unsigned int i, j;
+
+	if (arg->stop)
+		return;
+
+	for (i = 0; i < q->tin_cnt; i++) {
+		struct cake_tin_data *b = &q->tins[i];
+
+		for (j = 0; j < CAKE_QUEUES; j++) {
+			if (list_empty(&b->flows[j].flowchain) ||
+			    arg->count < arg->skip) {
+				arg->count++;
+				continue;
+			}
+			if (arg->fn(sch, i * CAKE_QUEUES + j + 1, arg) < 0) {
+				arg->stop = 1;
+				break;
+			}
+			arg->count++;
+		}
+	}
+}
+
+static const struct Qdisc_class_ops cake_class_ops = {
+	.leaf		=	cake_leaf,
+	.find		=	cake_find,
+	.tcf_block	=	cake_tcf_block,
+	.bind_tcf	=	cake_bind,
+	.unbind_tcf	=	cake_unbind,
+	.dump		=	cake_dump_class,
+	.dump_stats	=	cake_dump_class_stats,
+	.walk		=	cake_walk,
+};
+
+static struct Qdisc_ops cake_qdisc_ops __read_mostly = {
+	.cl_ops		=	&cake_class_ops,
+	.id		=	"cake",
+	.priv_size	=	sizeof(struct cake_sched_data),
+	.enqueue	=	cake_enqueue,
+	.dequeue	=	cake_dequeue,
+	.peek		=	qdisc_peek_dequeued,
+	.init		=	cake_init,
+	.reset		=	cake_reset,
+	.destroy	=	cake_destroy,
+	.change		=	cake_change,
+	.dump		=	cake_dump,
+	.dump_stats	=	cake_dump_stats,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init cake_module_init(void)
+{
+	return register_qdisc(&cake_qdisc_ops);
+}
+
+static void __exit cake_module_exit(void)
+{
+	unregister_qdisc(&cake_qdisc_ops);
+}
+
+module_init(cake_module_init)
+module_exit(cake_module_exit)
+MODULE_AUTHOR("Jonathan Morton");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("The CAKE shaper.");
-- 
cgit v1.2.3


From 7298de9cd7255a783ba93533acbf1c2b0a9c582d Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: sch_cake: Add ingress mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ingress mode is meant to be enabled when CAKE runs downlink of the
actual bottleneck (such as on an IFB device). The mode changes the shaper
to also account dropped packets to the shaped rate, as these have already
traversed the bottleneck.

Enabling ingress mode will also tune the AQM to always keep at least two
packets queued *for each flow*. This is done by scaling the minimum queue
occupancy level that will disable the AQM by the number of active bulk
flows. The rationale for this is that retransmits are more expensive in
ingress mode, since dropped packets have to traverse the bottleneck again
when they are retransmitted; thus, being more lenient and keeping a minimum
number of packets queued will improve throughput in cases where the number
of active flows are so large that they saturate the bottleneck even at
their minimum window size.

This commit also adds a separate switch to enable ingress mode rate
autoscaling. If enabled, the autoscaling code will observe the actual
traffic rate and adjust the shaper rate to match it. This can help avoid
latency increases in the case where the actual bottleneck rate decreases
below the shaped rate. The scaling filters out spikes by an EWMA filter.

Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 87 +++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 83 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index ea0272615d63..2950a8d07887 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -435,7 +435,8 @@ static bool cobalt_queue_empty(struct cobalt_vars *vars,
 static bool cobalt_should_drop(struct cobalt_vars *vars,
 			       struct cobalt_params *p,
 			       ktime_t now,
-			       struct sk_buff *skb)
+			       struct sk_buff *skb,
+			       u32 bulk_flows)
 {
 	bool next_due, over_target, drop = false;
 	ktime_t schedule;
@@ -459,6 +460,7 @@ static bool cobalt_should_drop(struct cobalt_vars *vars,
 	sojourn = ktime_to_ns(ktime_sub(now, cobalt_get_enqueue_time(skb)));
 	schedule = ktime_sub(now, vars->drop_next);
 	over_target = sojourn > p->target &&
+		      sojourn > p->mtu_time * bulk_flows * 2 &&
 		      sojourn > p->mtu_time * 4;
 	next_due = vars->count && ktime_to_ns(schedule) >= 0;
 
@@ -881,6 +883,9 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	b->tin_dropped++;
 	sch->qstats.drops++;
 
+	if (q->rate_flags & CAKE_FLAG_INGRESS)
+		cake_advance_shaper(q, b, skb, now, true);
+
 	__qdisc_drop(skb, to_free);
 	sch->q.qlen--;
 
@@ -921,6 +926,8 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data *t,
 	return 0;
 }
 
+static void cake_reconfigure(struct Qdisc *sch);
+
 static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 			struct sk_buff **to_free)
 {
@@ -988,8 +995,46 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		cake_heapify_up(q, b->overflow_idx[idx]);
 
 	/* incoming bandwidth capacity estimate */
-	q->avg_window_bytes = 0;
-	q->last_packet_time = now;
+	if (q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS) {
+		u64 packet_interval = \
+			ktime_to_ns(ktime_sub(now, q->last_packet_time));
+
+		if (packet_interval > NSEC_PER_SEC)
+			packet_interval = NSEC_PER_SEC;
+
+		/* filter out short-term bursts, eg. wifi aggregation */
+		q->avg_packet_interval = \
+			cake_ewma(q->avg_packet_interval,
+				  packet_interval,
+				  (packet_interval > q->avg_packet_interval ?
+					  2 : 8));
+
+		q->last_packet_time = now;
+
+		if (packet_interval > q->avg_packet_interval) {
+			u64 window_interval = \
+				ktime_to_ns(ktime_sub(now,
+						      q->avg_window_begin));
+			u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC;
+
+			do_div(b, window_interval);
+			q->avg_peak_bandwidth =
+				cake_ewma(q->avg_peak_bandwidth, b,
+					  b > q->avg_peak_bandwidth ? 2 : 8);
+			q->avg_window_bytes = 0;
+			q->avg_window_begin = now;
+
+			if (ktime_after(now,
+					ktime_add_ms(q->last_reconfig_time,
+						     250))) {
+				q->rate_bps = (q->avg_peak_bandwidth * 15) >> 4;
+				cake_reconfigure(sch);
+			}
+		}
+	} else {
+		q->avg_window_bytes = 0;
+		q->last_packet_time = now;
+	}
 
 	/* flowchain */
 	if (!flow->set || flow->set == CAKE_SET_DECAYING) {
@@ -1268,15 +1313,27 @@ retry:
 		}
 
 		/* Last packet in queue may be marked, shouldn't be dropped */
-		if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb) ||
+		if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb,
+					(b->bulk_flow_count *
+					 !!(q->rate_flags &
+					    CAKE_FLAG_INGRESS))) ||
 		    !flow->head)
 			break;
 
+		/* drop this packet, get another one */
+		if (q->rate_flags & CAKE_FLAG_INGRESS) {
+			len = cake_advance_shaper(q, b, skb,
+						  now, true);
+			flow->deficit -= len;
+			b->tin_deficit -= len;
+		}
 		flow->dropped++;
 		b->tin_dropped++;
 		qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 		qdisc_qstats_drop(sch);
 		kfree_skb(skb);
+		if (q->rate_flags & CAKE_FLAG_INGRESS)
+			goto retry;
 	}
 
 	b->tin_ecn_mark += !!flow->cvars.ecn_marked;
@@ -1459,6 +1516,20 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 			q->target = 1;
 	}
 
+	if (tb[TCA_CAKE_AUTORATE]) {
+		if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE]))
+			q->rate_flags |= CAKE_FLAG_AUTORATE_INGRESS;
+		else
+			q->rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS;
+	}
+
+	if (tb[TCA_CAKE_INGRESS]) {
+		if (!!nla_get_u32(tb[TCA_CAKE_INGRESS]))
+			q->rate_flags |= CAKE_FLAG_INGRESS;
+		else
+			q->rate_flags &= ~CAKE_FLAG_INGRESS;
+	}
+
 	if (tb[TCA_CAKE_MEMORY])
 		q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
 
@@ -1582,6 +1653,14 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put_u32(skb, TCA_CAKE_MEMORY, q->buffer_config_limit))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, TCA_CAKE_AUTORATE,
+			!!(q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS)))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_INGRESS,
+			!!(q->rate_flags & CAKE_FLAG_INGRESS)))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
-- 
cgit v1.2.3


From 8b7138814f29933898ecd31dfc83e35a30ee69f5 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: sch_cake: Add optional ACK filter
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ACK filter is an optional feature of CAKE which is designed to improve
performance on links with very asymmetrical rate limits. On such links
(which are unfortunately quite prevalent, especially for DSL and cable
subscribers), the downstream throughput can be limited by the number of
ACKs capable of being transmitted in the *upstream* direction.

Filtering ACKs can, in general, have adverse effects on TCP performance
because it interferes with ACK clocking (especially in slow start), and it
reduces the flow's resiliency to ACKs being dropped further along the path.
To alleviate these drawbacks, the ACK filter in CAKE tries its best to
always keep enough ACKs queued to ensure forward progress in the TCP flow
being filtered. It does this by only filtering redundant ACKs. In its
default 'conservative' mode, the filter will always keep at least two
redundant ACKs in the queue, while in 'aggressive' mode, it will filter
down to a single ACK.

The ACK filter works by inspecting the per-flow queue on every packet
enqueue. Starting at the head of the queue, the filter looks for another
eligible packet to drop (so the ACK being dropped is always closer to the
head of the queue than the packet being enqueued). An ACK is eligible only
if it ACKs *fewer* bytes than the new packet being enqueued, including any
SACK options. This prevents duplicate ACKs from being filtered, to avoid
interfering with retransmission logic. In addition, we check TCP header
options and only drop those that are known to not interfere with sender
state. In particular, packets with unknown option codes are never dropped.

In aggressive mode, an eligible packet is always dropped, while in
conservative mode, at least two ACKs are kept in the queue. Only pure ACKs
(with no data segments) are considered eligible for dropping, but when an
ACK with data segments is enqueued, this can cause another pure ACK to
become eligible for dropping.

The approach described above ensures that this ACK filter avoids most of
the drawbacks of a naive filtering mechanism that only keeps flow state but
does not inspect the queue. This is the rationale for including the ACK
filter in CAKE itself rather than as separate module (as the TC filter, for
instance).

Our performance evaluation has shown that on a 30/1 Mbps link with a
bidirectional traffic test (RRUL), turning on the ACK filter on the
upstream link improves downstream throughput by ~20% (both modes) and
upstream throughput by ~12% in conservative mode and ~40% in aggressive
mode, at the cost of ~5ms of inter-flow latency due to the increased
congestion.

In *really* pathological cases, the effect can be a lot more; for instance,
the ACK filter increases the achievable downstream throughput on a link
with 100 Kbps in the upstream direction by an order of magnitude (from ~2.5
Mbps to ~25 Mbps).

Finally, even though we consider the ACK filter to be safer than most, we
do not recommend turning it on everywhere: on more symmetrical link
bandwidths the effect is negligible at best.

Cc: Yuchung Cheng <ycheng@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 454 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 452 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 2950a8d07887..930096d46c4f 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -725,6 +725,433 @@ static void flow_queue_add(struct cake_flow *flow, struct sk_buff *skb)
 	skb->next = NULL;
 }
 
+static struct iphdr *cake_get_iphdr(const struct sk_buff *skb,
+				    struct ipv6hdr *buf)
+{
+	unsigned int offset = skb_network_offset(skb);
+	struct iphdr *iph;
+
+	iph = skb_header_pointer(skb, offset, sizeof(struct iphdr), buf);
+
+	if (!iph)
+		return NULL;
+
+	if (iph->version == 4 && iph->protocol == IPPROTO_IPV6)
+		return skb_header_pointer(skb, offset + iph->ihl * 4,
+					  sizeof(struct ipv6hdr), buf);
+
+	else if (iph->version == 4)
+		return iph;
+
+	else if (iph->version == 6)
+		return skb_header_pointer(skb, offset, sizeof(struct ipv6hdr),
+					  buf);
+
+	return NULL;
+}
+
+static struct tcphdr *cake_get_tcphdr(const struct sk_buff *skb,
+				      void *buf, unsigned int bufsize)
+{
+	unsigned int offset = skb_network_offset(skb);
+	const struct ipv6hdr *ipv6h;
+	const struct tcphdr *tcph;
+	const struct iphdr *iph;
+	struct ipv6hdr _ipv6h;
+	struct tcphdr _tcph;
+
+	ipv6h = skb_header_pointer(skb, offset, sizeof(_ipv6h), &_ipv6h);
+
+	if (!ipv6h)
+		return NULL;
+
+	if (ipv6h->version == 4) {
+		iph = (struct iphdr *)ipv6h;
+		offset += iph->ihl * 4;
+
+		/* special-case 6in4 tunnelling, as that is a common way to get
+		 * v6 connectivity in the home
+		 */
+		if (iph->protocol == IPPROTO_IPV6) {
+			ipv6h = skb_header_pointer(skb, offset,
+						   sizeof(_ipv6h), &_ipv6h);
+
+			if (!ipv6h || ipv6h->nexthdr != IPPROTO_TCP)
+				return NULL;
+
+			offset += sizeof(struct ipv6hdr);
+
+		} else if (iph->protocol != IPPROTO_TCP) {
+			return NULL;
+		}
+
+	} else if (ipv6h->version == 6) {
+		if (ipv6h->nexthdr != IPPROTO_TCP)
+			return NULL;
+
+		offset += sizeof(struct ipv6hdr);
+	} else {
+		return NULL;
+	}
+
+	tcph = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph);
+	if (!tcph)
+		return NULL;
+
+	return skb_header_pointer(skb, offset,
+				  min(__tcp_hdrlen(tcph), bufsize), buf);
+}
+
+static const void *cake_get_tcpopt(const struct tcphdr *tcph,
+				   int code, int *oplen)
+{
+	/* inspired by tcp_parse_options in tcp_input.c */
+	int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr);
+	const u8 *ptr = (const u8 *)(tcph + 1);
+
+	while (length > 0) {
+		int opcode = *ptr++;
+		int opsize;
+
+		if (opcode == TCPOPT_EOL)
+			break;
+		if (opcode == TCPOPT_NOP) {
+			length--;
+			continue;
+		}
+		opsize = *ptr++;
+		if (opsize < 2 || opsize > length)
+			break;
+
+		if (opcode == code) {
+			*oplen = opsize;
+			return ptr;
+		}
+
+		ptr += opsize - 2;
+		length -= opsize;
+	}
+
+	return NULL;
+}
+
+/* Compare two SACK sequences. A sequence is considered greater if it SACKs more
+ * bytes than the other. In the case where both sequences ACKs bytes that the
+ * other doesn't, A is considered greater. DSACKs in A also makes A be
+ * considered greater.
+ *
+ * @return -1, 0 or 1 as normal compare functions
+ */
+static int cake_tcph_sack_compare(const struct tcphdr *tcph_a,
+				  const struct tcphdr *tcph_b)
+{
+	const struct tcp_sack_block_wire *sack_a, *sack_b;
+	u32 ack_seq_a = ntohl(tcph_a->ack_seq);
+	u32 bytes_a = 0, bytes_b = 0;
+	int oplen_a, oplen_b;
+	bool first = true;
+
+	sack_a = cake_get_tcpopt(tcph_a, TCPOPT_SACK, &oplen_a);
+	sack_b = cake_get_tcpopt(tcph_b, TCPOPT_SACK, &oplen_b);
+
+	/* pointers point to option contents */
+	oplen_a -= TCPOLEN_SACK_BASE;
+	oplen_b -= TCPOLEN_SACK_BASE;
+
+	if (sack_a && oplen_a >= sizeof(*sack_a) &&
+	    (!sack_b || oplen_b < sizeof(*sack_b)))
+		return -1;
+	else if (sack_b && oplen_b >= sizeof(*sack_b) &&
+		 (!sack_a || oplen_a < sizeof(*sack_a)))
+		return 1;
+	else if ((!sack_a || oplen_a < sizeof(*sack_a)) &&
+		 (!sack_b || oplen_b < sizeof(*sack_b)))
+		return 0;
+
+	while (oplen_a >= sizeof(*sack_a)) {
+		const struct tcp_sack_block_wire *sack_tmp = sack_b;
+		u32 start_a = get_unaligned_be32(&sack_a->start_seq);
+		u32 end_a = get_unaligned_be32(&sack_a->end_seq);
+		int oplen_tmp = oplen_b;
+		bool found = false;
+
+		/* DSACK; always considered greater to prevent dropping */
+		if (before(start_a, ack_seq_a))
+			return -1;
+
+		bytes_a += end_a - start_a;
+
+		while (oplen_tmp >= sizeof(*sack_tmp)) {
+			u32 start_b = get_unaligned_be32(&sack_tmp->start_seq);
+			u32 end_b = get_unaligned_be32(&sack_tmp->end_seq);
+
+			/* first time through we count the total size */
+			if (first)
+				bytes_b += end_b - start_b;
+
+			if (!after(start_b, start_a) && !before(end_b, end_a)) {
+				found = true;
+				if (!first)
+					break;
+			}
+			oplen_tmp -= sizeof(*sack_tmp);
+			sack_tmp++;
+		}
+
+		if (!found)
+			return -1;
+
+		oplen_a -= sizeof(*sack_a);
+		sack_a++;
+		first = false;
+	}
+
+	/* If we made it this far, all ranges SACKed by A are covered by B, so
+	 * either the SACKs are equal, or B SACKs more bytes.
+	 */
+	return bytes_b > bytes_a ? 1 : 0;
+}
+
+static void cake_tcph_get_tstamp(const struct tcphdr *tcph,
+				 u32 *tsval, u32 *tsecr)
+{
+	const u8 *ptr;
+	int opsize;
+
+	ptr = cake_get_tcpopt(tcph, TCPOPT_TIMESTAMP, &opsize);
+
+	if (ptr && opsize == TCPOLEN_TIMESTAMP) {
+		*tsval = get_unaligned_be32(ptr);
+		*tsecr = get_unaligned_be32(ptr + 4);
+	}
+}
+
+static bool cake_tcph_may_drop(const struct tcphdr *tcph,
+			       u32 tstamp_new, u32 tsecr_new)
+{
+	/* inspired by tcp_parse_options in tcp_input.c */
+	int length = __tcp_hdrlen(tcph) - sizeof(struct tcphdr);
+	const u8 *ptr = (const u8 *)(tcph + 1);
+	u32 tstamp, tsecr;
+
+	/* 3 reserved flags must be unset to avoid future breakage
+	 * ACK must be set
+	 * ECE/CWR are handled separately
+	 * All other flags URG/PSH/RST/SYN/FIN must be unset
+	 * 0x0FFF0000 = all TCP flags (confirm ACK=1, others zero)
+	 * 0x00C00000 = CWR/ECE (handled separately)
+	 * 0x0F3F0000 = 0x0FFF0000 & ~0x00C00000
+	 */
+	if (((tcp_flag_word(tcph) &
+	      cpu_to_be32(0x0F3F0000)) != TCP_FLAG_ACK))
+		return false;
+
+	while (length > 0) {
+		int opcode = *ptr++;
+		int opsize;
+
+		if (opcode == TCPOPT_EOL)
+			break;
+		if (opcode == TCPOPT_NOP) {
+			length--;
+			continue;
+		}
+		opsize = *ptr++;
+		if (opsize < 2 || opsize > length)
+			break;
+
+		switch (opcode) {
+		case TCPOPT_MD5SIG: /* doesn't influence state */
+			break;
+
+		case TCPOPT_SACK: /* stricter checking performed later */
+			if (opsize % 8 != 2)
+				return false;
+			break;
+
+		case TCPOPT_TIMESTAMP:
+			/* only drop timestamps lower than new */
+			if (opsize != TCPOLEN_TIMESTAMP)
+				return false;
+			tstamp = get_unaligned_be32(ptr);
+			tsecr = get_unaligned_be32(ptr + 4);
+			if (after(tstamp, tstamp_new) ||
+			    after(tsecr, tsecr_new))
+				return false;
+			break;
+
+		case TCPOPT_MSS:  /* these should only be set on SYN */
+		case TCPOPT_WINDOW:
+		case TCPOPT_SACK_PERM:
+		case TCPOPT_FASTOPEN:
+		case TCPOPT_EXP:
+		default: /* don't drop if any unknown options are present */
+			return false;
+		}
+
+		ptr += opsize - 2;
+		length -= opsize;
+	}
+
+	return true;
+}
+
+static struct sk_buff *cake_ack_filter(struct cake_sched_data *q,
+				       struct cake_flow *flow)
+{
+	bool aggressive = q->ack_filter == CAKE_ACK_AGGRESSIVE;
+	struct sk_buff *elig_ack = NULL, *elig_ack_prev = NULL;
+	struct sk_buff *skb_check, *skb_prev = NULL;
+	const struct ipv6hdr *ipv6h, *ipv6h_check;
+	unsigned char _tcph[64], _tcph_check[64];
+	const struct tcphdr *tcph, *tcph_check;
+	const struct iphdr *iph, *iph_check;
+	struct ipv6hdr _iph, _iph_check;
+	const struct sk_buff *skb;
+	int seglen, num_found = 0;
+	u32 tstamp = 0, tsecr = 0;
+	__be32 elig_flags = 0;
+	int sack_comp;
+
+	/* no other possible ACKs to filter */
+	if (flow->head == flow->tail)
+		return NULL;
+
+	skb = flow->tail;
+	tcph = cake_get_tcphdr(skb, _tcph, sizeof(_tcph));
+	iph = cake_get_iphdr(skb, &_iph);
+	if (!tcph)
+		return NULL;
+
+	cake_tcph_get_tstamp(tcph, &tstamp, &tsecr);
+
+	/* the 'triggering' packet need only have the ACK flag set.
+	 * also check that SYN is not set, as there won't be any previous ACKs.
+	 */
+	if ((tcp_flag_word(tcph) &
+	     (TCP_FLAG_ACK | TCP_FLAG_SYN)) != TCP_FLAG_ACK)
+		return NULL;
+
+	/* the 'triggering' ACK is at the tail of the queue, we have already
+	 * returned if it is the only packet in the flow. loop through the rest
+	 * of the queue looking for pure ACKs with the same 5-tuple as the
+	 * triggering one.
+	 */
+	for (skb_check = flow->head;
+	     skb_check && skb_check != skb;
+	     skb_prev = skb_check, skb_check = skb_check->next) {
+		iph_check = cake_get_iphdr(skb_check, &_iph_check);
+		tcph_check = cake_get_tcphdr(skb_check, &_tcph_check,
+					     sizeof(_tcph_check));
+
+		/* only TCP packets with matching 5-tuple are eligible, and only
+		 * drop safe headers
+		 */
+		if (!tcph_check || iph->version != iph_check->version ||
+		    tcph_check->source != tcph->source ||
+		    tcph_check->dest != tcph->dest)
+			continue;
+
+		if (iph_check->version == 4) {
+			if (iph_check->saddr != iph->saddr ||
+			    iph_check->daddr != iph->daddr)
+				continue;
+
+			seglen = ntohs(iph_check->tot_len) -
+				       (4 * iph_check->ihl);
+		} else if (iph_check->version == 6) {
+			ipv6h = (struct ipv6hdr *)iph;
+			ipv6h_check = (struct ipv6hdr *)iph_check;
+
+			if (ipv6_addr_cmp(&ipv6h_check->saddr, &ipv6h->saddr) ||
+			    ipv6_addr_cmp(&ipv6h_check->daddr, &ipv6h->daddr))
+				continue;
+
+			seglen = ntohs(ipv6h_check->payload_len);
+		} else {
+			WARN_ON(1);  /* shouldn't happen */
+			continue;
+		}
+
+		/* If the ECE/CWR flags changed from the previous eligible
+		 * packet in the same flow, we should no longer be dropping that
+		 * previous packet as this would lose information.
+		 */
+		if (elig_ack && (tcp_flag_word(tcph_check) &
+				 (TCP_FLAG_ECE | TCP_FLAG_CWR)) != elig_flags) {
+			elig_ack = NULL;
+			elig_ack_prev = NULL;
+			num_found--;
+		}
+
+		/* Check TCP options and flags, don't drop ACKs with segment
+		 * data, and don't drop ACKs with a higher cumulative ACK
+		 * counter than the triggering packet. Check ACK seqno here to
+		 * avoid parsing SACK options of packets we are going to exclude
+		 * anyway.
+		 */
+		if (!cake_tcph_may_drop(tcph_check, tstamp, tsecr) ||
+		    (seglen - __tcp_hdrlen(tcph_check)) != 0 ||
+		    after(ntohl(tcph_check->ack_seq), ntohl(tcph->ack_seq)))
+			continue;
+
+		/* Check SACK options. The triggering packet must SACK more data
+		 * than the ACK under consideration, or SACK the same range but
+		 * have a larger cumulative ACK counter. The latter is a
+		 * pathological case, but is contained in the following check
+		 * anyway, just to be safe.
+		 */
+		sack_comp = cake_tcph_sack_compare(tcph_check, tcph);
+
+		if (sack_comp < 0 ||
+		    (ntohl(tcph_check->ack_seq) == ntohl(tcph->ack_seq) &&
+		     sack_comp == 0))
+			continue;
+
+		/* At this point we have found an eligible pure ACK to drop; if
+		 * we are in aggressive mode, we are done. Otherwise, keep
+		 * searching unless this is the second eligible ACK we
+		 * found.
+		 *
+		 * Since we want to drop ACK closest to the head of the queue,
+		 * save the first eligible ACK we find, even if we need to loop
+		 * again.
+		 */
+		if (!elig_ack) {
+			elig_ack = skb_check;
+			elig_ack_prev = skb_prev;
+			elig_flags = (tcp_flag_word(tcph_check)
+				      & (TCP_FLAG_ECE | TCP_FLAG_CWR));
+		}
+
+		if (num_found++ > 0)
+			goto found;
+	}
+
+	/* We made it through the queue without finding two eligible ACKs . If
+	 * we found a single eligible ACK we can drop it in aggressive mode if
+	 * we can guarantee that this does not interfere with ECN flag
+	 * information. We ensure this by dropping it only if the enqueued
+	 * packet is consecutive with the eligible ACK, and their flags match.
+	 */
+	if (elig_ack && aggressive && elig_ack->next == skb &&
+	    (elig_flags == (tcp_flag_word(tcph) &
+			    (TCP_FLAG_ECE | TCP_FLAG_CWR))))
+		goto found;
+
+	return NULL;
+
+found:
+	if (elig_ack_prev)
+		elig_ack_prev->next = elig_ack->next;
+	else
+		flow->head = elig_ack->next;
+
+	elig_ack->next = NULL;
+
+	return elig_ack;
+}
+
 static u64 cake_ewma(u64 avg, u64 sample, u32 shift)
 {
 	avg -= avg >> shift;
@@ -934,6 +1361,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct cake_sched_data *q = qdisc_priv(sch);
 	int len = qdisc_pkt_len(skb);
 	int uninitialized_var(ret);
+	struct sk_buff *ack = NULL;
 	ktime_t now = ktime_get();
 	struct cake_tin_data *b;
 	struct cake_flow *flow;
@@ -980,8 +1408,24 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	cobalt_set_enqueue_time(skb, now);
 	flow_queue_add(flow, skb);
 
-	sch->q.qlen++;
-	q->buffer_used      += skb->truesize;
+	if (q->ack_filter)
+		ack = cake_ack_filter(q, flow);
+
+	if (ack) {
+		b->ack_drops++;
+		sch->qstats.drops++;
+		b->bytes += qdisc_pkt_len(ack);
+		len -= qdisc_pkt_len(ack);
+		q->buffer_used += skb->truesize - ack->truesize;
+		if (q->rate_flags & CAKE_FLAG_INGRESS)
+			cake_advance_shaper(q, b, ack, now, true);
+
+		qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack));
+		consume_skb(ack);
+	} else {
+		sch->q.qlen++;
+		q->buffer_used      += skb->truesize;
+	}
 
 	/* stats */
 	b->packets++;
@@ -1530,6 +1974,9 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 			q->rate_flags &= ~CAKE_FLAG_INGRESS;
 	}
 
+	if (tb[TCA_CAKE_ACK_FILTER])
+		q->ack_filter = nla_get_u32(tb[TCA_CAKE_ACK_FILTER]);
+
 	if (tb[TCA_CAKE_MEMORY])
 		q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
 
@@ -1661,6 +2108,9 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 			!!(q->rate_flags & CAKE_FLAG_INGRESS)))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, q->ack_filter))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
-- 
cgit v1.2.3


From b60a60405fb95a688eb2ef4ef20f5fcaa7b64f68 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: netfilter: Add nf_ct_get_tuple_skb global lookup function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds a global netfilter function to extract a conntrack tuple from an
skb. The function uses a new function added to nf_ct_hook, which will try
to get the tuple from skb->_nfct, and do a full lookup if that fails. This
makes it possible to use the lookup function before the skb has passed
through the conntrack init hooks (e.g., in an ingress qdisc). The tuple is
copied to the caller to avoid issues with reference counting.

The function returns false if conntrack is not loaded, allowing it to be
used without incurring a module dependency on conntrack. This is used by
the NAT mode in sch_cake.

Cc: netfilter-devel@vger.kernel.org
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netfilter.h         | 11 +++++++++++
 net/netfilter/core.c              | 15 +++++++++++++++
 net/netfilter/nf_conntrack_core.c | 36 ++++++++++++++++++++++++++++++++++++
 3 files changed, 62 insertions(+)

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 23b48de8c2e2..07efffd0c759 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -414,8 +414,17 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 
 extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu;
 void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
+struct nf_conntrack_tuple;
+bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+			 const struct sk_buff *skb);
 #else
 static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {}
+struct nf_conntrack_tuple;
+static inline bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+				       const struct sk_buff *skb)
+{
+	return false;
+}
 #endif
 
 struct nf_conn;
@@ -424,6 +433,8 @@ enum ip_conntrack_info;
 struct nf_ct_hook {
 	int (*update)(struct net *net, struct sk_buff *skb);
 	void (*destroy)(struct nf_conntrack *);
+	bool (*get_tuple_skb)(struct nf_conntrack_tuple *,
+			      const struct sk_buff *);
 };
 extern struct nf_ct_hook __rcu *nf_ct_hook;
 
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index 168af54db975..dc240cb47ddf 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -603,6 +603,21 @@ void nf_conntrack_destroy(struct nf_conntrack *nfct)
 }
 EXPORT_SYMBOL(nf_conntrack_destroy);
 
+bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+			 const struct sk_buff *skb)
+{
+	struct nf_ct_hook *ct_hook;
+	bool ret = false;
+
+	rcu_read_lock();
+	ct_hook = rcu_dereference(nf_ct_hook);
+	if (ct_hook)
+		ret = ct_hook->get_tuple_skb(dst_tuple, skb);
+	rcu_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL(nf_ct_get_tuple_skb);
+
 /* Built-in default zone used e.g. by modules. */
 const struct nf_conntrack_zone nf_ct_zone_dflt = {
 	.id	= NF_CT_DEFAULT_ZONE_ID,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 3465da2a98bd..85ab2fd6a665 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1683,6 +1683,41 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 	return 0;
 }
 
+static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple,
+				       const struct sk_buff *skb)
+{
+	const struct nf_conntrack_tuple *src_tuple;
+	const struct nf_conntrack_tuple_hash *hash;
+	struct nf_conntrack_tuple srctuple;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (ct) {
+		src_tuple = nf_ct_tuple(ct, CTINFO2DIR(ctinfo));
+		memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple));
+		return true;
+	}
+
+	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb),
+			       NFPROTO_IPV4, dev_net(skb->dev),
+			       &srctuple))
+		return false;
+
+	hash = nf_conntrack_find_get(dev_net(skb->dev),
+				     &nf_ct_zone_dflt,
+				     &srctuple);
+	if (!hash)
+		return false;
+
+	ct = nf_ct_tuplehash_to_ctrack(hash);
+	src_tuple = nf_ct_tuple(ct, !hash->tuple.dst.dir);
+	memcpy(dst_tuple, src_tuple, sizeof(*dst_tuple));
+	nf_ct_put(ct);
+
+	return true;
+}
+
 /* Bring out ya dead! */
 static struct nf_conn *
 get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
@@ -2204,6 +2239,7 @@ err_cachep:
 static struct nf_ct_hook nf_conntrack_hook = {
 	.update		= nf_conntrack_update,
 	.destroy	= destroy_conntrack,
+	.get_tuple_skb  = nf_conntrack_get_tuple_skb,
 };
 
 void nf_conntrack_init_end(void)
-- 
cgit v1.2.3


From ea82511518f4f2e5fe83d2fe1884ef5fc6be6204 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: sch_cake: Add NAT awareness to packet classifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When CAKE is deployed on a gateway that also performs NAT (which is a
common deployment mode), the host fairness mechanism cannot distinguish
internal hosts from each other, and so fails to work correctly.

To fix this, we add an optional NAT awareness mode, which will query the
kernel conntrack mechanism to obtain the pre-NAT addresses for each packet
and use that in the flow and host hashing.

When the shaper is enabled and the host is already performing NAT, the cost
of this lookup is negligible. However, in unlimited mode with no NAT being
performed, there is a significant CPU cost at higher bandwidths. For this
reason, the feature is turned off by default.

Cc: netfilter-devel@vger.kernel.org
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 49 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 930096d46c4f..633ca1578114 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -71,6 +71,10 @@
 #include <net/tcp.h>
 #include <net/flow_dissector.h>
 
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack_core.h>
+#endif
+
 #define CAKE_SET_WAYS (8)
 #define CAKE_MAX_TINS (8)
 #define CAKE_QUEUES (1024)
@@ -516,6 +520,29 @@ static bool cobalt_should_drop(struct cobalt_vars *vars,
 	return drop;
 }
 
+static void cake_update_flowkeys(struct flow_keys *keys,
+				 const struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	struct nf_conntrack_tuple tuple = {};
+	bool rev = !skb->_nfct;
+
+	if (tc_skb_protocol(skb) != htons(ETH_P_IP))
+		return;
+
+	if (!nf_ct_get_tuple_skb(&tuple, skb))
+		return;
+
+	keys->addrs.v4addrs.src = rev ? tuple.dst.u3.ip : tuple.src.u3.ip;
+	keys->addrs.v4addrs.dst = rev ? tuple.src.u3.ip : tuple.dst.u3.ip;
+
+	if (keys->ports.ports) {
+		keys->ports.src = rev ? tuple.dst.u.all : tuple.src.u.all;
+		keys->ports.dst = rev ? tuple.src.u.all : tuple.dst.u.all;
+	}
+#endif
+}
+
 /* Cake has several subtle multiple bit settings. In these cases you
  *  would be matching triple isolate mode as well.
  */
@@ -543,6 +570,9 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
 	skb_flow_dissect_flow_keys(skb, &keys,
 				   FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
 
+	if (flow_mode & CAKE_FLOW_NAT_FLAG)
+		cake_update_flowkeys(&keys, skb);
+
 	/* flow_hash_from_keys() sorts the addresses by value, so we have
 	 * to preserve their order in a separate data structure to treat
 	 * src and dst host addresses as independently selectable.
@@ -1939,12 +1969,25 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		return err;
 
+	if (tb[TCA_CAKE_NAT]) {
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+		q->flow_mode &= ~CAKE_FLOW_NAT_FLAG;
+		q->flow_mode |= CAKE_FLOW_NAT_FLAG *
+			!!nla_get_u32(tb[TCA_CAKE_NAT]);
+#else
+		NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT],
+				    "No conntrack support in kernel");
+		return -EOPNOTSUPP;
+#endif
+	}
+
 	if (tb[TCA_CAKE_BASE_RATE64])
 		q->rate_bps = nla_get_u64(tb[TCA_CAKE_BASE_RATE64]);
 
 	if (tb[TCA_CAKE_FLOW_MODE])
-		q->flow_mode = (nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
-				CAKE_FLOW_MASK);
+		q->flow_mode = ((q->flow_mode & CAKE_FLOW_NAT_FLAG) |
+				(nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
+					CAKE_FLOW_MASK));
 
 	if (tb[TCA_CAKE_RTT]) {
 		q->interval = nla_get_u32(tb[TCA_CAKE_RTT]);
@@ -2111,6 +2154,10 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, q->ack_filter))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, TCA_CAKE_NAT,
+			!!(q->flow_mode & CAKE_FLOW_NAT_FLAG)))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
-- 
cgit v1.2.3


From 83f8fd69af4f62136765b60fd0efa1c9167917c5 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: sch_cake: Add DiffServ handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds support for DiffServ-based priority queueing to CAKE. If the
shaper is in use, each priority tier gets its own virtual clock, which
limits that tier's rate to a fraction of the overall shaped rate, to
discourage trying to game the priority mechanism.

CAKE defaults to a simple, three-tier mode that interprets most code points
as "best effort", but places CS1 traffic into a low-priority "bulk" tier
which is assigned 1/16 of the total rate, and a few code points indicating
latency-sensitive or control traffic (specifically TOS4, VA, EF, CS6, CS7)
into a "latency sensitive" high-priority tier, which is assigned 1/4 rate.
The other supported DiffServ modes are a 4-tier mode matching the 802.11e
precedence rules, as well as two 8-tier modes, one of which implements
strict precedence of the eight priority levels.

This commit also adds an optional DiffServ 'wash' mode, which will zero out
the DSCP fields of any packet passing through CAKE. While this can
technically be done with other mechanisms in the kernel, having the feature
available in CAKE significantly decreases configuration complexity; and the
implementation cost is low on top of the other DiffServ-handling code.

Filters and applications can set the skb->priority field to override the
DSCP-based classification into tiers. If TC_H_MAJ(skb->priority) matches
CAKE's qdisc handle, the minor number will be interpreted as a priority
tier if it is less than or equal to the number of configured priority
tiers.

Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 439 +++++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 423 insertions(+), 16 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 633ca1578114..43eeca81b247 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -296,6 +296,68 @@ static void cobalt_set_enqueue_time(struct sk_buff *skb,
 
 static u16 quantum_div[CAKE_QUEUES + 1] = {0};
 
+/* Diffserv lookup tables */
+
+static const u8 precedence[] = {
+	0, 0, 0, 0, 0, 0, 0, 0,
+	1, 1, 1, 1, 1, 1, 1, 1,
+	2, 2, 2, 2, 2, 2, 2, 2,
+	3, 3, 3, 3, 3, 3, 3, 3,
+	4, 4, 4, 4, 4, 4, 4, 4,
+	5, 5, 5, 5, 5, 5, 5, 5,
+	6, 6, 6, 6, 6, 6, 6, 6,
+	7, 7, 7, 7, 7, 7, 7, 7,
+};
+
+static const u8 diffserv8[] = {
+	2, 5, 1, 2, 4, 2, 2, 2,
+	0, 2, 1, 2, 1, 2, 1, 2,
+	5, 2, 4, 2, 4, 2, 4, 2,
+	3, 2, 3, 2, 3, 2, 3, 2,
+	6, 2, 3, 2, 3, 2, 3, 2,
+	6, 2, 2, 2, 6, 2, 6, 2,
+	7, 2, 2, 2, 2, 2, 2, 2,
+	7, 2, 2, 2, 2, 2, 2, 2,
+};
+
+static const u8 diffserv4[] = {
+	0, 2, 0, 0, 2, 0, 0, 0,
+	1, 0, 0, 0, 0, 0, 0, 0,
+	2, 0, 2, 0, 2, 0, 2, 0,
+	2, 0, 2, 0, 2, 0, 2, 0,
+	3, 0, 2, 0, 2, 0, 2, 0,
+	3, 0, 0, 0, 3, 0, 3, 0,
+	3, 0, 0, 0, 0, 0, 0, 0,
+	3, 0, 0, 0, 0, 0, 0, 0,
+};
+
+static const u8 diffserv3[] = {
+	0, 0, 0, 0, 2, 0, 0, 0,
+	1, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 2, 0, 2, 0,
+	2, 0, 0, 0, 0, 0, 0, 0,
+	2, 0, 0, 0, 0, 0, 0, 0,
+};
+
+static const u8 besteffort[] = {
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+	0, 0, 0, 0, 0, 0, 0, 0,
+};
+
+/* tin priority order for stats dumping */
+
+static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7};
+static const u8 bulk_order[] = {1, 0, 2, 3};
+
 #define REC_INV_SQRT_CACHE (16)
 static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0};
 
@@ -1351,20 +1413,91 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	return idx + (tin << 16);
 }
 
-static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data *t,
+static void cake_wash_diffserv(struct sk_buff *skb)
+{
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+		break;
+	case htons(ETH_P_IPV6):
+		ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+		break;
+	default:
+		break;
+	}
+}
+
+static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash)
+{
+	u8 dscp;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2;
+		if (wash && dscp)
+			ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0);
+		return dscp;
+
+	case htons(ETH_P_IPV6):
+		dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2;
+		if (wash && dscp)
+			ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0);
+		return dscp;
+
+	case htons(ETH_P_ARP):
+		return 0x38;  /* CS7 - Net Control */
+
+	default:
+		/* If there is no Diffserv field, treat as best-effort */
+		return 0;
+	}
+}
+
+static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
+					     struct sk_buff *skb)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	u32 tin;
+
+	if (TC_H_MAJ(skb->priority) == sch->handle &&
+	    TC_H_MIN(skb->priority) > 0 &&
+	    TC_H_MIN(skb->priority) <= q->tin_cnt) {
+		tin = TC_H_MIN(skb->priority) - 1;
+
+		if (q->rate_flags & CAKE_FLAG_WASH)
+			cake_wash_diffserv(skb);
+	} else if (q->tin_mode != CAKE_DIFFSERV_BESTEFFORT) {
+		/* extract the Diffserv Precedence field, if it exists */
+		/* and clear DSCP bits if washing */
+		tin = q->tin_index[cake_handle_diffserv(skb,
+				q->rate_flags & CAKE_FLAG_WASH)];
+		if (unlikely(tin >= q->tin_cnt))
+			tin = 0;
+	} else {
+		tin = 0;
+		if (q->rate_flags & CAKE_FLAG_WASH)
+			cake_wash_diffserv(skb);
+	}
+
+	return &q->tins[tin];
+}
+
+static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data **t,
 			 struct sk_buff *skb, int flow_mode, int *qerr)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct tcf_proto *filter;
 	struct tcf_result res;
+	u32 flow = 0;
 	int result;
 
 	filter = rcu_dereference_bh(q->filter_list);
 	if (!filter)
-		return cake_hash(t, skb, flow_mode) + 1;
+		goto hash;
 
 	*qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
 	result = tcf_classify(skb, filter, &res, false);
+
 	if (result >= 0) {
 #ifdef CONFIG_NET_CLS_ACT
 		switch (result) {
@@ -1378,9 +1511,11 @@ static u32 cake_classify(struct Qdisc *sch, struct cake_tin_data *t,
 		}
 #endif
 		if (TC_H_MIN(res.classid) <= CAKE_QUEUES)
-			return TC_H_MIN(res.classid);
+			flow = TC_H_MIN(res.classid);
 	}
-	return 0;
+hash:
+	*t = cake_select_tin(sch, skb);
+	return flow ?: cake_hash(*t, skb, flow_mode) + 1;
 }
 
 static void cake_reconfigure(struct Qdisc *sch);
@@ -1395,13 +1530,10 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	ktime_t now = ktime_get();
 	struct cake_tin_data *b;
 	struct cake_flow *flow;
-	u32 idx, tin;
-
-	tin = 0;
-	b = &q->tins[tin];
+	u32 idx;
 
 	/* choose flow to insert into */
-	idx = cake_classify(sch, b, skb, q->flow_mode, &ret);
+	idx = cake_classify(sch, &b, skb, q->flow_mode, &ret);
 	if (idx == 0) {
 		if (ret & __NET_XMIT_BYPASS)
 			qdisc_qstats_drop(sch);
@@ -1917,18 +2049,275 @@ static void cake_set_rate(struct cake_tin_data *b, u64 rate, u32 mtu,
 	b->cparams.p_dec = 1 << 20; /* 1/4096 */
 }
 
-static void cake_reconfigure(struct Qdisc *sch)
+static int cake_config_besteffort(struct Qdisc *sch)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct cake_tin_data *b = &q->tins[0];
-	int c, ft = 0;
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+	u64 rate = q->rate_bps;
 
 	q->tin_cnt = 1;
-	cake_set_rate(b, q->rate_bps, psched_mtu(qdisc_dev(sch)),
+
+	q->tin_index = besteffort;
+	q->tin_order = normal_order;
+
+	cake_set_rate(b, rate, mtu,
 		      us_to_ns(q->target), us_to_ns(q->interval));
 	b->tin_quantum_band = 65535;
 	b->tin_quantum_prio = 65535;
 
+	return 0;
+}
+
+static int cake_config_precedence(struct Qdisc *sch)
+{
+	/* convert high-level (user visible) parameters into internal format */
+	struct cake_sched_data *q = qdisc_priv(sch);
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+	u64 rate = q->rate_bps;
+	u32 quantum1 = 256;
+	u32 quantum2 = 256;
+	u32 i;
+
+	q->tin_cnt = 8;
+	q->tin_index = precedence;
+	q->tin_order = normal_order;
+
+	for (i = 0; i < q->tin_cnt; i++) {
+		struct cake_tin_data *b = &q->tins[i];
+
+		cake_set_rate(b, rate, mtu, us_to_ns(q->target),
+			      us_to_ns(q->interval));
+
+		b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+		b->tin_quantum_band = max_t(u16, 1U, quantum2);
+
+		/* calculate next class's parameters */
+		rate  *= 7;
+		rate >>= 3;
+
+		quantum1  *= 3;
+		quantum1 >>= 1;
+
+		quantum2  *= 7;
+		quantum2 >>= 3;
+	}
+
+	return 0;
+}
+
+/*	List of known Diffserv codepoints:
+ *
+ *	Least Effort (CS1)
+ *	Best Effort (CS0)
+ *	Max Reliability & LLT "Lo" (TOS1)
+ *	Max Throughput (TOS2)
+ *	Min Delay (TOS4)
+ *	LLT "La" (TOS5)
+ *	Assured Forwarding 1 (AF1x) - x3
+ *	Assured Forwarding 2 (AF2x) - x3
+ *	Assured Forwarding 3 (AF3x) - x3
+ *	Assured Forwarding 4 (AF4x) - x3
+ *	Precedence Class 2 (CS2)
+ *	Precedence Class 3 (CS3)
+ *	Precedence Class 4 (CS4)
+ *	Precedence Class 5 (CS5)
+ *	Precedence Class 6 (CS6)
+ *	Precedence Class 7 (CS7)
+ *	Voice Admit (VA)
+ *	Expedited Forwarding (EF)
+
+ *	Total 25 codepoints.
+ */
+
+/*	List of traffic classes in RFC 4594:
+ *		(roughly descending order of contended priority)
+ *		(roughly ascending order of uncontended throughput)
+ *
+ *	Network Control (CS6,CS7)      - routing traffic
+ *	Telephony (EF,VA)         - aka. VoIP streams
+ *	Signalling (CS5)               - VoIP setup
+ *	Multimedia Conferencing (AF4x) - aka. video calls
+ *	Realtime Interactive (CS4)     - eg. games
+ *	Multimedia Streaming (AF3x)    - eg. YouTube, NetFlix, Twitch
+ *	Broadcast Video (CS3)
+ *	Low Latency Data (AF2x,TOS4)      - eg. database
+ *	Ops, Admin, Management (CS2,TOS1) - eg. ssh
+ *	Standard Service (CS0 & unrecognised codepoints)
+ *	High Throughput Data (AF1x,TOS2)  - eg. web traffic
+ *	Low Priority Data (CS1)           - eg. BitTorrent
+
+ *	Total 12 traffic classes.
+ */
+
+static int cake_config_diffserv8(struct Qdisc *sch)
+{
+/*	Pruned list of traffic classes for typical applications:
+ *
+ *		Network Control          (CS6, CS7)
+ *		Minimum Latency          (EF, VA, CS5, CS4)
+ *		Interactive Shell        (CS2, TOS1)
+ *		Low Latency Transactions (AF2x, TOS4)
+ *		Video Streaming          (AF4x, AF3x, CS3)
+ *		Bog Standard             (CS0 etc.)
+ *		High Throughput          (AF1x, TOS2)
+ *		Background Traffic       (CS1)
+ *
+ *		Total 8 traffic classes.
+ */
+
+	struct cake_sched_data *q = qdisc_priv(sch);
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+	u64 rate = q->rate_bps;
+	u32 quantum1 = 256;
+	u32 quantum2 = 256;
+	u32 i;
+
+	q->tin_cnt = 8;
+
+	/* codepoint to class mapping */
+	q->tin_index = diffserv8;
+	q->tin_order = normal_order;
+
+	/* class characteristics */
+	for (i = 0; i < q->tin_cnt; i++) {
+		struct cake_tin_data *b = &q->tins[i];
+
+		cake_set_rate(b, rate, mtu, us_to_ns(q->target),
+			      us_to_ns(q->interval));
+
+		b->tin_quantum_prio = max_t(u16, 1U, quantum1);
+		b->tin_quantum_band = max_t(u16, 1U, quantum2);
+
+		/* calculate next class's parameters */
+		rate  *= 7;
+		rate >>= 3;
+
+		quantum1  *= 3;
+		quantum1 >>= 1;
+
+		quantum2  *= 7;
+		quantum2 >>= 3;
+	}
+
+	return 0;
+}
+
+static int cake_config_diffserv4(struct Qdisc *sch)
+{
+/*  Further pruned list of traffic classes for four-class system:
+ *
+ *	    Latency Sensitive  (CS7, CS6, EF, VA, CS5, CS4)
+ *	    Streaming Media    (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1)
+ *	    Best Effort        (CS0, AF1x, TOS2, and those not specified)
+ *	    Background Traffic (CS1)
+ *
+ *		Total 4 traffic classes.
+ */
+
+	struct cake_sched_data *q = qdisc_priv(sch);
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+	u64 rate = q->rate_bps;
+	u32 quantum = 1024;
+
+	q->tin_cnt = 4;
+
+	/* codepoint to class mapping */
+	q->tin_index = diffserv4;
+	q->tin_order = bulk_order;
+
+	/* class characteristics */
+	cake_set_rate(&q->tins[0], rate, mtu,
+		      us_to_ns(q->target), us_to_ns(q->interval));
+	cake_set_rate(&q->tins[1], rate >> 4, mtu,
+		      us_to_ns(q->target), us_to_ns(q->interval));
+	cake_set_rate(&q->tins[2], rate >> 1, mtu,
+		      us_to_ns(q->target), us_to_ns(q->interval));
+	cake_set_rate(&q->tins[3], rate >> 2, mtu,
+		      us_to_ns(q->target), us_to_ns(q->interval));
+
+	/* priority weights */
+	q->tins[0].tin_quantum_prio = quantum;
+	q->tins[1].tin_quantum_prio = quantum >> 4;
+	q->tins[2].tin_quantum_prio = quantum << 2;
+	q->tins[3].tin_quantum_prio = quantum << 4;
+
+	/* bandwidth-sharing weights */
+	q->tins[0].tin_quantum_band = quantum;
+	q->tins[1].tin_quantum_band = quantum >> 4;
+	q->tins[2].tin_quantum_band = quantum >> 1;
+	q->tins[3].tin_quantum_band = quantum >> 2;
+
+	return 0;
+}
+
+static int cake_config_diffserv3(struct Qdisc *sch)
+{
+/*  Simplified Diffserv structure with 3 tins.
+ *		Low Priority		(CS1)
+ *		Best Effort
+ *		Latency Sensitive	(TOS4, VA, EF, CS6, CS7)
+ */
+	struct cake_sched_data *q = qdisc_priv(sch);
+	u32 mtu = psched_mtu(qdisc_dev(sch));
+	u64 rate = q->rate_bps;
+	u32 quantum = 1024;
+
+	q->tin_cnt = 3;
+
+	/* codepoint to class mapping */
+	q->tin_index = diffserv3;
+	q->tin_order = bulk_order;
+
+	/* class characteristics */
+	cake_set_rate(&q->tins[0], rate, mtu,
+		      us_to_ns(q->target), us_to_ns(q->interval));
+	cake_set_rate(&q->tins[1], rate >> 4, mtu,
+		      us_to_ns(q->target), us_to_ns(q->interval));
+	cake_set_rate(&q->tins[2], rate >> 2, mtu,
+		      us_to_ns(q->target), us_to_ns(q->interval));
+
+	/* priority weights */
+	q->tins[0].tin_quantum_prio = quantum;
+	q->tins[1].tin_quantum_prio = quantum >> 4;
+	q->tins[2].tin_quantum_prio = quantum << 4;
+
+	/* bandwidth-sharing weights */
+	q->tins[0].tin_quantum_band = quantum;
+	q->tins[1].tin_quantum_band = quantum >> 4;
+	q->tins[2].tin_quantum_band = quantum >> 2;
+
+	return 0;
+}
+
+static void cake_reconfigure(struct Qdisc *sch)
+{
+	struct cake_sched_data *q = qdisc_priv(sch);
+	int c, ft;
+
+	switch (q->tin_mode) {
+	case CAKE_DIFFSERV_BESTEFFORT:
+		ft = cake_config_besteffort(sch);
+		break;
+
+	case CAKE_DIFFSERV_PRECEDENCE:
+		ft = cake_config_precedence(sch);
+		break;
+
+	case CAKE_DIFFSERV_DIFFSERV8:
+		ft = cake_config_diffserv8(sch);
+		break;
+
+	case CAKE_DIFFSERV_DIFFSERV4:
+		ft = cake_config_diffserv4(sch);
+		break;
+
+	case CAKE_DIFFSERV_DIFFSERV3:
+	default:
+		ft = cake_config_diffserv3(sch);
+		break;
+	}
+
 	for (c = q->tin_cnt; c < CAKE_MAX_TINS; c++) {
 		cake_clear_tin(sch, c);
 		q->tins[c].cparams.mtu_time = q->tins[ft].cparams.mtu_time;
@@ -1984,6 +2373,16 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_CAKE_BASE_RATE64])
 		q->rate_bps = nla_get_u64(tb[TCA_CAKE_BASE_RATE64]);
 
+	if (tb[TCA_CAKE_DIFFSERV_MODE])
+		q->tin_mode = nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE]);
+
+	if (tb[TCA_CAKE_WASH]) {
+		if (!!nla_get_u32(tb[TCA_CAKE_WASH]))
+			q->rate_flags |= CAKE_FLAG_WASH;
+		else
+			q->rate_flags &= ~CAKE_FLAG_WASH;
+	}
+
 	if (tb[TCA_CAKE_FLOW_MODE])
 		q->flow_mode = ((q->flow_mode & CAKE_FLOW_NAT_FLAG) |
 				(nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
@@ -2048,7 +2447,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	int i, j, err;
 
 	sch->limit = 10240;
-	q->tin_mode = CAKE_DIFFSERV_BESTEFFORT;
+	q->tin_mode = CAKE_DIFFSERV_DIFFSERV3;
 	q->flow_mode  = CAKE_FLOW_TRIPLE;
 
 	q->rate_bps = 0; /* unlimited by default */
@@ -2158,6 +2557,13 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 			!!(q->flow_mode & CAKE_FLOW_NAT_FLAG)))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, q->tin_mode))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_WASH,
+			!!(q->rate_flags & CAKE_FLAG_WASH)))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
@@ -2211,7 +2617,7 @@ static int cake_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
 	} while (0)
 
 	for (i = 0; i < q->tin_cnt; i++) {
-		struct cake_tin_data *b = &q->tins[i];
+		struct cake_tin_data *b = &q->tins[q->tin_order[i]];
 
 		ts = nla_nest_start(d->skb, i + 1);
 		if (!ts)
@@ -2310,7 +2716,8 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 	u32 idx = cl - 1;
 
 	if (idx < CAKE_QUEUES * q->tin_cnt) {
-		const struct cake_tin_data *b = &q->tins[idx / CAKE_QUEUES];
+		const struct cake_tin_data *b = \
+			&q->tins[q->tin_order[idx / CAKE_QUEUES]];
 		const struct sk_buff *skb;
 
 		flow = &b->flows[idx % CAKE_QUEUES];
@@ -2382,7 +2789,7 @@ static void cake_walk(struct Qdisc *sch, struct qdisc_walker *arg)
 		return;
 
 	for (i = 0; i < q->tin_cnt; i++) {
-		struct cake_tin_data *b = &q->tins[i];
+		struct cake_tin_data *b = &q->tins[q->tin_order[i]];
 
 		for (j = 0; j < CAKE_QUEUES; j++) {
 			if (list_empty(&b->flows[j].flowchain) ||
-- 
cgit v1.2.3


From a729b7f0bd5bf4919306556aed614438f5174537 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: sch_cake: Add overhead compensation support to the rate shaper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit adds configurable overhead compensation support to the rate
shaper. With this feature, userspace can configure the actual bottleneck
link overhead and encapsulation mode used, which will be used by the shaper
to calculate the precise duration of each packet on the wire.

This feature is needed because CAKE is often deployed one or two hops
upstream of the actual bottleneck (which can be, e.g., inside a DSL or
cable modem). In this case, the link layer characteristics and overhead
reported by the kernel does not match the actual bottleneck. Being able to
set the actual values in use makes it possible to configure the shaper rate
much closer to the actual bottleneck rate (our experience shows it is
possible to get with 0.1% of the actual physical bottleneck rate), thus
keeping latency low without sacrificing bandwidth.

The overhead compensation has three tunables: A fixed per-packet overhead
size (which, if set, will be accounted from the IP packet header), a
minimum packet size (MPU) and a framing mode supporting either ATM or PTM
framing. We include a set of common keywords in TC to help users configure
the right parameters. If no overhead value is set, the value reported by
the kernel is used.

Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 124 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 123 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 43eeca81b247..199670e1eb94 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -270,6 +270,7 @@ enum {
 
 struct cobalt_skb_cb {
 	ktime_t enqueue_time;
+	u32     adjusted_len;
 };
 
 static u64 us_to_ns(u64 us)
@@ -1251,6 +1252,88 @@ static u64 cake_ewma(u64 avg, u64 sample, u32 shift)
 	return avg;
 }
 
+static u32 cake_calc_overhead(struct cake_sched_data *q, u32 len, u32 off)
+{
+	if (q->rate_flags & CAKE_FLAG_OVERHEAD)
+		len -= off;
+
+	if (q->max_netlen < len)
+		q->max_netlen = len;
+	if (q->min_netlen > len)
+		q->min_netlen = len;
+
+	len += q->rate_overhead;
+
+	if (len < q->rate_mpu)
+		len = q->rate_mpu;
+
+	if (q->atm_mode == CAKE_ATM_ATM) {
+		len += 47;
+		len /= 48;
+		len *= 53;
+	} else if (q->atm_mode == CAKE_ATM_PTM) {
+		/* Add one byte per 64 bytes or part thereof.
+		 * This is conservative and easier to calculate than the
+		 * precise value.
+		 */
+		len += (len + 63) / 64;
+	}
+
+	if (q->max_adjlen < len)
+		q->max_adjlen = len;
+	if (q->min_adjlen > len)
+		q->min_adjlen = len;
+
+	return len;
+}
+
+static u32 cake_overhead(struct cake_sched_data *q, const struct sk_buff *skb)
+{
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+	unsigned int hdr_len, last_len = 0;
+	u32 off = skb_network_offset(skb);
+	u32 len = qdisc_pkt_len(skb);
+	u16 segs = 1;
+
+	q->avg_netoff = cake_ewma(q->avg_netoff, off << 16, 8);
+
+	if (!shinfo->gso_size)
+		return cake_calc_overhead(q, len, off);
+
+	/* borrowed from qdisc_pkt_len_init() */
+	hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+
+	/* + transport layer */
+	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 |
+						SKB_GSO_TCPV6))) {
+		const struct tcphdr *th;
+		struct tcphdr _tcphdr;
+
+		th = skb_header_pointer(skb, skb_transport_offset(skb),
+					sizeof(_tcphdr), &_tcphdr);
+		if (likely(th))
+			hdr_len += __tcp_hdrlen(th);
+	} else {
+		struct udphdr _udphdr;
+
+		if (skb_header_pointer(skb, skb_transport_offset(skb),
+				       sizeof(_udphdr), &_udphdr))
+			hdr_len += sizeof(struct udphdr);
+	}
+
+	if (unlikely(shinfo->gso_type & SKB_GSO_DODGY))
+		segs = DIV_ROUND_UP(skb->len - hdr_len,
+				    shinfo->gso_size);
+	else
+		segs = shinfo->gso_segs;
+
+	len = shinfo->gso_size + hdr_len;
+	last_len = skb->len - shinfo->gso_size * (segs - 1);
+
+	return (cake_calc_overhead(q, len, off) * (segs - 1) +
+		cake_calc_overhead(q, last_len, off));
+}
+
 static void cake_heap_swap(struct cake_sched_data *q, u16 i, u16 j)
 {
 	struct cake_heap_entry ii = q->overflow_heap[i];
@@ -1328,7 +1411,7 @@ static int cake_advance_shaper(struct cake_sched_data *q,
 			       struct sk_buff *skb,
 			       ktime_t now, bool drop)
 {
-	u32 len = qdisc_pkt_len(skb);
+	u32 len = get_cobalt_cb(skb)->adjusted_len;
 
 	/* charge packet bandwidth to this tin
 	 * and to the global shaper.
@@ -1568,6 +1651,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		b->max_skblen = len;
 
 	cobalt_set_enqueue_time(skb, now);
+	get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb);
 	flow_queue_add(flow, skb);
 
 	if (q->ack_filter)
@@ -2388,6 +2472,31 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 				(nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
 					CAKE_FLOW_MASK));
 
+	if (tb[TCA_CAKE_ATM])
+		q->atm_mode = nla_get_u32(tb[TCA_CAKE_ATM]);
+
+	if (tb[TCA_CAKE_OVERHEAD]) {
+		q->rate_overhead = nla_get_s32(tb[TCA_CAKE_OVERHEAD]);
+		q->rate_flags |= CAKE_FLAG_OVERHEAD;
+
+		q->max_netlen = 0;
+		q->max_adjlen = 0;
+		q->min_netlen = ~0;
+		q->min_adjlen = ~0;
+	}
+
+	if (tb[TCA_CAKE_RAW]) {
+		q->rate_flags &= ~CAKE_FLAG_OVERHEAD;
+
+		q->max_netlen = 0;
+		q->max_adjlen = 0;
+		q->min_netlen = ~0;
+		q->min_adjlen = ~0;
+	}
+
+	if (tb[TCA_CAKE_MPU])
+		q->rate_mpu = nla_get_u32(tb[TCA_CAKE_MPU]);
+
 	if (tb[TCA_CAKE_RTT]) {
 		q->interval = nla_get_u32(tb[TCA_CAKE_RTT]);
 
@@ -2564,6 +2673,19 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 			!!(q->rate_flags & CAKE_FLAG_WASH)))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, q->rate_overhead))
+		goto nla_put_failure;
+
+	if (!(q->rate_flags & CAKE_FLAG_OVERHEAD))
+		if (nla_put_u32(skb, TCA_CAKE_RAW, 0))
+			goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_ATM, q->atm_mode))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_CAKE_MPU, q->rate_mpu))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
-- 
cgit v1.2.3


From 0c850344d3882886f842bf0b50a9ff23001adb7e Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Fri, 6 Jul 2018 17:37:19 +0200
Subject: sch_cake: Conditionally split GSO segments
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

At lower bandwidths, the transmission time of a single GSO segment can add
an unacceptable amount of latency due to HOL blocking. Furthermore, with a
software shaper, any tuning mechanism employed by the kernel to control the
maximum size of GSO segments is thrown off by the artificial limit on
bandwidth. For this reason, we split GSO segments into their individual
packets iff the shaper is active and configured to a bandwidth <= 1 Gbps.

Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 99 ++++++++++++++++++++++++++++++++++++++--------------
 1 file changed, 73 insertions(+), 26 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 199670e1eb94..30695691e9ff 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -80,6 +80,7 @@
 #define CAKE_QUEUES (1024)
 #define CAKE_FLOW_MASK 63
 #define CAKE_FLOW_NAT_FLAG 64
+#define CAKE_SPLIT_GSO_THRESHOLD (125000000) /* 1Gbps */
 
 /* struct cobalt_params - contains codel and blue parameters
  * @interval:	codel initial drop rate
@@ -1650,36 +1651,73 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	if (unlikely(len > b->max_skblen))
 		b->max_skblen = len;
 
-	cobalt_set_enqueue_time(skb, now);
-	get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb);
-	flow_queue_add(flow, skb);
-
-	if (q->ack_filter)
-		ack = cake_ack_filter(q, flow);
+	if (skb_is_gso(skb) && q->rate_flags & CAKE_FLAG_SPLIT_GSO) {
+		struct sk_buff *segs, *nskb;
+		netdev_features_t features = netif_skb_features(skb);
+		unsigned int slen = 0;
+
+		segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+		if (IS_ERR_OR_NULL(segs))
+			return qdisc_drop(skb, sch, to_free);
+
+		while (segs) {
+			nskb = segs->next;
+			segs->next = NULL;
+			qdisc_skb_cb(segs)->pkt_len = segs->len;
+			cobalt_set_enqueue_time(segs, now);
+			get_cobalt_cb(segs)->adjusted_len = cake_overhead(q,
+									  segs);
+			flow_queue_add(flow, segs);
+
+			sch->q.qlen++;
+			slen += segs->len;
+			q->buffer_used += segs->truesize;
+			b->packets++;
+			segs = nskb;
+		}
 
-	if (ack) {
-		b->ack_drops++;
-		sch->qstats.drops++;
-		b->bytes += qdisc_pkt_len(ack);
-		len -= qdisc_pkt_len(ack);
-		q->buffer_used += skb->truesize - ack->truesize;
-		if (q->rate_flags & CAKE_FLAG_INGRESS)
-			cake_advance_shaper(q, b, ack, now, true);
+		/* stats */
+		b->bytes	    += slen;
+		b->backlogs[idx]    += slen;
+		b->tin_backlog      += slen;
+		sch->qstats.backlog += slen;
+		q->avg_window_bytes += slen;
 
-		qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack));
-		consume_skb(ack);
+		qdisc_tree_reduce_backlog(sch, 1, len);
+		consume_skb(skb);
 	} else {
-		sch->q.qlen++;
-		q->buffer_used      += skb->truesize;
-	}
+		/* not splitting */
+		cobalt_set_enqueue_time(skb, now);
+		get_cobalt_cb(skb)->adjusted_len = cake_overhead(q, skb);
+		flow_queue_add(flow, skb);
+
+		if (q->ack_filter)
+			ack = cake_ack_filter(q, flow);
+
+		if (ack) {
+			b->ack_drops++;
+			sch->qstats.drops++;
+			b->bytes += qdisc_pkt_len(ack);
+			len -= qdisc_pkt_len(ack);
+			q->buffer_used += skb->truesize - ack->truesize;
+			if (q->rate_flags & CAKE_FLAG_INGRESS)
+				cake_advance_shaper(q, b, ack, now, true);
+
+			qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(ack));
+			consume_skb(ack);
+		} else {
+			sch->q.qlen++;
+			q->buffer_used      += skb->truesize;
+		}
 
-	/* stats */
-	b->packets++;
-	b->bytes	    += len;
-	b->backlogs[idx]    += len;
-	b->tin_backlog      += len;
-	sch->qstats.backlog += len;
-	q->avg_window_bytes += len;
+		/* stats */
+		b->packets++;
+		b->bytes	    += len;
+		b->backlogs[idx]    += len;
+		b->tin_backlog      += len;
+		sch->qstats.backlog += len;
+		q->avg_window_bytes += len;
+	}
 
 	if (q->overflow_timeout)
 		cake_heapify_up(q, b->overflow_idx[idx]);
@@ -2531,6 +2569,11 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_CAKE_MEMORY])
 		q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
 
+	if (q->rate_bps && q->rate_bps <= CAKE_SPLIT_GSO_THRESHOLD)
+		q->rate_flags |= CAKE_FLAG_SPLIT_GSO;
+	else
+		q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO;
+
 	if (q->tins) {
 		sch_tree_lock(sch);
 		cake_reconfigure(sch);
@@ -2686,6 +2729,10 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (nla_put_u32(skb, TCA_CAKE_MPU, q->rate_mpu))
 		goto nla_put_failure;
 
+	if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO,
+			!!(q->rate_flags & CAKE_FLAG_SPLIT_GSO)))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, opts);
 
 nla_put_failure:
-- 
cgit v1.2.3


From e8cff84faa4ddb6716caed085f515fbb1d856099 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 11:24:21 -0400
Subject: fold security_file_free() into file_free()

.. and the call of file_free() in case of security_file_alloc() failure
in get_empty_filp() should be simply file_free_rcu() - no point in
rcu-delays there, anyway.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 7ec0b3e5f05d..eee7cf629e52 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -51,6 +51,7 @@ static void file_free_rcu(struct rcu_head *head)
 
 static inline void file_free(struct file *f)
 {
+	security_file_free(f);
 	percpu_counter_dec(&nr_files);
 	call_rcu(&f->f_u.fu_rcuhead, file_free_rcu);
 }
@@ -123,11 +124,10 @@ struct file *get_empty_filp(void)
 	if (unlikely(!f))
 		return ERR_PTR(-ENOMEM);
 
-	percpu_counter_inc(&nr_files);
 	f->f_cred = get_cred(cred);
 	error = security_file_alloc(f);
 	if (unlikely(error)) {
-		file_free(f);
+		file_free_rcu(&f->f_u.fu_rcuhead);
 		return ERR_PTR(error);
 	}
 
@@ -137,6 +137,7 @@ struct file *get_empty_filp(void)
 	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
 	/* f->f_version: 0 */
+	percpu_counter_inc(&nr_files);
 	return f;
 
 over:
@@ -207,7 +208,6 @@ static void __fput(struct file *file)
 	}
 	if (file->f_op->release)
 		file->f_op->release(inode, file);
-	security_file_free(file);
 	if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
 		     !(file->f_mode & FMODE_PATH))) {
 		cdev_put(inode->i_cdev);
@@ -302,10 +302,8 @@ EXPORT_SYMBOL(fput);
 
 void put_filp(struct file *file)
 {
-	if (atomic_long_dec_and_test(&file->f_count)) {
-		security_file_free(file);
+	if (atomic_long_dec_and_test(&file->f_count))
 		file_free(file);
-	}
 }
 
 void __init files_init(void)
-- 
cgit v1.2.3


From 19f391eb05b8b005f2907ddc8f284487b446abf3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 11:19:32 -0400
Subject: turn filp_clone_open() into inline wrapper for dentry_open()

it's exactly the same thing as
	dentry_open(&file->f_path, file->f_flags, file->f_cred)

... and rename it to file_clone_open(), while we are at it.
'filp' naming convention is bogus; sure, it's "file pointer",
but we generally don't do that kind of Hungarian notation.
Some of the instances have too many callers to touch, but this
one has only two, so let's sanitize it while we can...

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/gpu/drm/drm_lease.c |  2 +-
 fs/binfmt_misc.c            |  2 +-
 fs/open.c                   | 20 --------------------
 include/linux/fs.h          |  5 ++++-
 4 files changed, 6 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/drm_lease.c b/drivers/gpu/drm/drm_lease.c
index d638c0fb3418..b54fb78a283c 100644
--- a/drivers/gpu/drm/drm_lease.c
+++ b/drivers/gpu/drm/drm_lease.c
@@ -553,7 +553,7 @@ int drm_mode_create_lease_ioctl(struct drm_device *dev,
 
 	/* Clone the lessor file to create a new file for us */
 	DRM_DEBUG_LEASE("Allocating lease file\n");
-	lessee_file = filp_clone_open(lessor_file);
+	lessee_file = file_clone_open(lessor_file);
 	if (IS_ERR(lessee_file)) {
 		ret = PTR_ERR(lessee_file);
 		goto out_lessee;
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 4b5fff31ef27..aa4a7a23ff99 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -205,7 +205,7 @@ static int load_misc_binary(struct linux_binprm *bprm)
 		goto error;
 
 	if (fmt->flags & MISC_FMT_OPEN_FILE) {
-		interp_file = filp_clone_open(fmt->interp_file);
+		interp_file = file_clone_open(fmt->interp_file);
 		if (!IS_ERR(interp_file))
 			deny_write_access(interp_file);
 	} else {
diff --git a/fs/open.c b/fs/open.c
index d0e955b558ad..76c56966e297 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -1063,26 +1063,6 @@ struct file *file_open_root(struct dentry *dentry, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(file_open_root);
 
-struct file *filp_clone_open(struct file *oldfile)
-{
-	struct file *file;
-	int retval;
-
-	file = get_empty_filp();
-	if (IS_ERR(file))
-		return file;
-
-	file->f_flags = oldfile->f_flags;
-	retval = vfs_open(&oldfile->f_path, file, oldfile->f_cred);
-	if (retval) {
-		put_filp(file);
-		return ERR_PTR(retval);
-	}
-
-	return file;
-}
-EXPORT_SYMBOL(filp_clone_open);
-
 long do_sys_open(int dfd, const char __user *filename, int flags, umode_t mode)
 {
 	struct open_flags op;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index aa9b4c169ed2..c4ca4c9c1130 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2422,7 +2422,10 @@ extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(struct dentry *, struct vfsmount *,
 				   const char *, int, umode_t);
 extern struct file * dentry_open(const struct path *, int, const struct cred *);
-extern struct file *filp_clone_open(struct file *);
+static inline struct file *file_clone_open(struct file *file)
+{
+	return dentry_open(&file->f_path, file->f_flags, file->f_cred);
+}
 extern int filp_close(struct file *, fl_owner_t id);
 
 extern struct filename *getname_flags(const char __user *, int, int *);
-- 
cgit v1.2.3


From b10a4a9f7695335bd2bb19bffdda7fbefbc6581f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 02:29:58 -0400
Subject: create_pipe_files(): use fput() if allocation of the second file
 fails

... just use put_pipe_info() to get the pipe->files down to 1 and let
fput()-called pipe_release() do freeing.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/pipe.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index bb0840e234f3..9405e455f5b1 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -771,8 +771,9 @@ int create_pipe_files(struct file **res, int flags)
 
 	res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
 	if (IS_ERR(res[0])) {
-		err = PTR_ERR(res[0]);
-		goto err_file;
+		put_pipe_info(inode, inode->i_pipe);
+		fput(f);
+		return PTR_ERR(res[0]);
 	}
 
 	path_get(&path);
@@ -781,8 +782,6 @@ int create_pipe_files(struct file **res, int flags)
 	res[1] = f;
 	return 0;
 
-err_file:
-	put_filp(f);
 err_dentry:
 	free_pipe_info(inode->i_pipe);
 	path_put(&path);
-- 
cgit v1.2.3


From 6b4e8085c0004382b985a5c005c685073630e746 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 8 Jul 2018 21:45:07 -0400
Subject: make sure do_dentry_open() won't return positive as an error

An ->open() instances really, really should not be doing that.  There's
a lot of places e.g. around atomic_open() that could be confused by that,
so let's catch that early.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/open.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/open.c b/fs/open.c
index 76c56966e297..530da965e369 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -812,6 +812,8 @@ static int do_dentry_open(struct file *f,
 	return 0;
 
 cleanup_all:
+	if (WARN_ON_ONCE(error > 0))
+		error = -EINVAL;
 	fops_put(f->f_op);
 	if (f->f_mode & FMODE_WRITER) {
 		put_write_access(inode);
-- 
cgit v1.2.3


From db560d1612f81c932df8d31e6f3bf7581c32ba91 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 8 Jul 2018 19:58:55 +0200
Subject: selftests: forwarding: mirror_lib: Tighten up VLAN capture

The function do_test_span_vlan_dir_ips() is used for testing whether
mirrored packets are VLAN-encapsulated. But since it only considers
VLAN encapsulation, it may end up matching unmirrored ARP traffic as
well. One consequence is a rare failure of mirror_gre_vlan_bridge_1q's
test_gretap_untagged_egress. Decreasing ping cadence in mirror_test()
makes the problem easily reproducible.

Therefore tighten up the match criterion to only count those 802.1q
packets where the next header is IP.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/mirror_lib.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh
index d36dc26c6c51..07991e1025c7 100644
--- a/tools/testing/selftests/net/forwarding/mirror_lib.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh
@@ -105,7 +105,7 @@ do_test_span_vlan_dir_ips()
 	# Install the capture as skip_hw to avoid double-counting of packets.
 	# The traffic is meant for local box anyway, so will be trapped to
 	# kernel.
-	vlan_capture_install $dev "skip_hw vlan_id $vid"
+	vlan_capture_install $dev "skip_hw vlan_id $vid vlan_ethtype ip"
 	mirror_test v$h1 $ip1 $ip2 $dev 100 $expect
 	mirror_test v$h2 $ip2 $ip1 $dev 100 $expect
 	vlan_capture_uninstall $dev
-- 
cgit v1.2.3


From ff2d6acdf6f13d9f8fdcd890844c6d7535ac1f10 Mon Sep 17 00:00:00 2001
From: Timo Wischer <twischer@de.adit-jv.com>
Date: Tue, 10 Jul 2018 17:28:45 +0200
Subject: ALSA: pcm: Fix snd_interval_refine first/last with open min/max

Without this commit the following intervals [x y), (x y) were be
replaced to (y-1 y) by snd_interval_refine_last(). This was also done
if y-1 is part of the previous interval.
With this changes it will be replaced with [y-1 y) in case of y-1 is
part of the previous interval. A similar behavior will be used for
snd_interval_refine_first().

This commit adapts the changes for alsa-lib of commit
9bb985c ("pcm: snd_interval_refine_first/last: exclude value only if
also excluded before")

Signed-off-by: Timo Wischer <twischer@de.adit-jv.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/pcm_lib.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/sound/core/pcm_lib.c b/sound/core/pcm_lib.c
index 5736860f325b..4e6110d778bd 100644
--- a/sound/core/pcm_lib.c
+++ b/sound/core/pcm_lib.c
@@ -627,27 +627,33 @@ EXPORT_SYMBOL(snd_interval_refine);
 
 static int snd_interval_refine_first(struct snd_interval *i)
 {
+	const unsigned int last_max = i->max;
+
 	if (snd_BUG_ON(snd_interval_empty(i)))
 		return -EINVAL;
 	if (snd_interval_single(i))
 		return 0;
 	i->max = i->min;
-	i->openmax = i->openmin;
-	if (i->openmax)
+	if (i->openmin)
 		i->max++;
+	/* only exclude max value if also excluded before refine */
+	i->openmax = (i->openmax && i->max >= last_max);
 	return 1;
 }
 
 static int snd_interval_refine_last(struct snd_interval *i)
 {
+	const unsigned int last_min = i->min;
+
 	if (snd_BUG_ON(snd_interval_empty(i)))
 		return -EINVAL;
 	if (snd_interval_single(i))
 		return 0;
 	i->min = i->max;
-	i->openmin = i->openmax;
-	if (i->openmin)
+	if (i->openmax)
 		i->min--;
+	/* only exclude min value if also excluded before refine */
+	i->openmin = (i->openmin && i->min <= last_min);
 	return 1;
 }
 
-- 
cgit v1.2.3


From decac6b00542ea2b95b68863fe3890ed134e5b57 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:34:54 +0200
Subject: dt-bindings: display: sun4i-drm: Add R40 display engine compatible

R40 has pretty unique display pipeline. It supports two outputs at the
same time.

Possible outputs:
- 1x HDMI,
- 2x TV output
- 1x VGA,
- 1x MIPI DSI and
- 2x LCD outputs

That is the biggest number of possible outputs from all Allwinner SoC.
Because of that, add new compatible for it.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-2-jernej.skrabec@siol.net
---
 Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
index 5a9319ad8861..288b4cbc255e 100644
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
@@ -399,6 +399,7 @@ Required properties:
     * allwinner,sun8i-a33-display-engine
     * allwinner,sun8i-a83t-display-engine
     * allwinner,sun8i-h3-display-engine
+    * allwinner,sun8i-r40-display-engine
     * allwinner,sun8i-v3s-display-engine
     * allwinner,sun9i-a80-display-engine
 
-- 
cgit v1.2.3


From d978a94b0a9e011dc3a7528fc9a34f0553ad0890 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:34:55 +0200
Subject: drm/sun4i: Add R40 display engine compatible

R40 has versatile display pipeline. It supports two simultanious outputs
on various outputs (TVE, VGA, HDMI, MIPI DSI, LCD).

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-3-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_drv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 6ddf4eaccb40..a15feb807393 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -417,6 +417,7 @@ static const struct of_device_id sun4i_drv_of_table[] = {
 	{ .compatible = "allwinner,sun8i-a33-display-engine" },
 	{ .compatible = "allwinner,sun8i-a83t-display-engine" },
 	{ .compatible = "allwinner,sun8i-h3-display-engine" },
+	{ .compatible = "allwinner,sun8i-r40-display-engine" },
 	{ .compatible = "allwinner,sun8i-v3s-display-engine" },
 	{ .compatible = "allwinner,sun9i-a80-display-engine" },
 	{ }
-- 
cgit v1.2.3


From af11942ee44ed9d61ce7d8b1bd3277195ec4c1c1 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:34:57 +0200
Subject: drm/sun4i: tcon-top: Cleanup clock handling

There is no need to acquire reference to clock just to get its name.

This commit just cleans up the code. There is no functional change.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
[Maxime: Fixed the of_property_match_string error check]
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-5-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_tcon_top.c | 48 ++++++++--------------------------
 1 file changed, 11 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
index 8da0460e0028..ab2591a92ef0 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -44,15 +44,20 @@ static int sun8i_tcon_top_get_connected_ep_id(struct device_node *node,
 }
 
 static struct clk_hw *sun8i_tcon_top_register_gate(struct device *dev,
-						   struct clk *parent,
+						   const char *parent,
 						   void __iomem *regs,
 						   spinlock_t *lock,
 						   u8 bit, int name_index)
 {
 	const char *clk_name, *parent_name;
-	int ret;
+	int ret, index;
+
+	index = of_property_match_string(dev->of_node, "clock-names", parent);
+	if (index < 0)
+		return index;
+
+	parent_name = of_clk_get_parent_name(dev->of_node, index);
 
-	parent_name = __clk_get_name(parent);
 	ret = of_property_read_string_index(dev->of_node,
 					    "clock-output-names", name_index,
 					    &clk_name);
@@ -69,7 +74,6 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 			       void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
-	struct clk *dsi, *tcon_tv0, *tcon_tv1, *tve0, *tve1;
 	struct clk_hw_onecell_data *clk_data;
 	struct sun8i_tcon_top *tcon_top;
 	bool mixer0_unused = false;
@@ -103,36 +107,6 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 		return PTR_ERR(tcon_top->bus);
 	}
 
-	dsi = devm_clk_get(dev, "dsi");
-	if (IS_ERR(dsi)) {
-		dev_err(dev, "Couldn't get the dsi clock\n");
-		return PTR_ERR(dsi);
-	}
-
-	tcon_tv0 = devm_clk_get(dev, "tcon-tv0");
-	if (IS_ERR(tcon_tv0)) {
-		dev_err(dev, "Couldn't get the tcon-tv0 clock\n");
-		return PTR_ERR(tcon_tv0);
-	}
-
-	tcon_tv1 = devm_clk_get(dev, "tcon-tv1");
-	if (IS_ERR(tcon_tv1)) {
-		dev_err(dev, "Couldn't get the tcon-tv1 clock\n");
-		return PTR_ERR(tcon_tv1);
-	}
-
-	tve0 = devm_clk_get(dev, "tve0");
-	if (IS_ERR(tve0)) {
-		dev_err(dev, "Couldn't get the tve0 clock\n");
-		return PTR_ERR(tve0);
-	}
-
-	tve1 = devm_clk_get(dev, "tve1");
-	if (IS_ERR(tve1)) {
-		dev_err(dev, "Couldn't get the tve1 clock\n");
-		return PTR_ERR(tve1);
-	}
-
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(dev, res);
 	if (IS_ERR(regs))
@@ -203,17 +177,17 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 	 * to TVE clock parent.
 	 */
 	clk_data->hws[CLK_TCON_TOP_TV0] =
-		sun8i_tcon_top_register_gate(dev, tcon_tv0, regs,
+		sun8i_tcon_top_register_gate(dev, "tcon-tv0", regs,
 					     &tcon_top->reg_lock,
 					     TCON_TOP_TCON_TV0_GATE, 0);
 
 	clk_data->hws[CLK_TCON_TOP_TV1] =
-		sun8i_tcon_top_register_gate(dev, tcon_tv1, regs,
+		sun8i_tcon_top_register_gate(dev, "tcon-tv1", regs,
 					     &tcon_top->reg_lock,
 					     TCON_TOP_TCON_TV1_GATE, 1);
 
 	clk_data->hws[CLK_TCON_TOP_DSI] =
-		sun8i_tcon_top_register_gate(dev, dsi, regs,
+		sun8i_tcon_top_register_gate(dev, "dsi", regs,
 					     &tcon_top->reg_lock,
 					     TCON_TOP_TCON_DSI_GATE, 2);
 
-- 
cgit v1.2.3


From da82107ecf328d4914d316872866ceeb683c01eb Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:34:58 +0200
Subject: drm/sun4i: tcon: Release node when traversing of graph

Function sun4i_tcon_find_engine_traverse() doesn't release node if it
needs to traverse of graph deeper than 1 level.

Fix this by calling of_node_put().

Fixes: 49836b11fe71 ("drm/sun4i: tcon: Generalize engine search algorithm")

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-6-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun4i_tcon.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/sun4i/sun4i_tcon.c b/drivers/gpu/drm/sun4i/sun4i_tcon.c
index aacc841d3dc6..3fb084f802e2 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tcon.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tcon.c
@@ -811,6 +811,7 @@ sun4i_tcon_find_engine_traverse(struct sun4i_drv *drv,
 	 * remote output id. If this for some reason can't be done, 0
 	 * is used as input port id.
 	 */
+	of_node_put(port);
 	port = of_graph_get_remote_port(ep);
 	if (!of_property_read_u32(port, "reg", &reg) && reg > 0)
 		reg -= 1;
-- 
cgit v1.2.3


From 7a6677753413440781f07e372fd6f06a4b589c88 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:34:59 +0200
Subject: dt-bindings: display: sun4i-drm: Add R40 TV TCON description

TCON description is expanded with R40 TV TCON compatible. It is a bit
special, because it is connected to TCON TOP instead directly to mixer
and it needs special handling.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-7-jernej.skrabec@siol.net
---
 Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
index 288b4cbc255e..7e2451396a28 100644
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
@@ -147,6 +147,7 @@ Required properties:
    * allwinner,sun8i-a33-tcon
    * allwinner,sun8i-a83t-tcon-lcd
    * allwinner,sun8i-a83t-tcon-tv
+   * allwinner,sun8i-r40-tcon-tv
    * allwinner,sun8i-v3s-tcon
    * allwinner,sun9i-a80-tcon-lcd
    * allwinner,sun9i-a80-tcon-tv
@@ -181,7 +182,7 @@ For TCONs with channel 0, there is one more clock required:
 For TCONs with channel 1, there is one more clock required:
    - 'tcon-ch1': The clock driving the TCON channel 1
 
-When TCON support LVDS (all TCONs except TV TCON on A83T and those found
+When TCON support LVDS (all TCONs except TV TCONs on A83T, R40 and those found
 in A13, H3, H5 and V3s SoCs), you need one more reset line:
    - 'lvds': The reset line driving the LVDS logic
 
-- 
cgit v1.2.3


From 4a068c5c17e8e33518de0b102c0d23ed3615286b Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:35:00 +0200
Subject: drm/sun4i: DW HDMI: Release nodes if error happens during CRTC search

If error happens in sun8i_dw_hdmi_find_possible_crtcs(), nodes are not
released with of_node_put() before returning.

Fix that by calling of_node_put() when necessary. While on it, clean up
the code by using of_graph_get_remote_node() which also lowers number of
cases where error handling has to be performed.

Fixes: 57e23de02f48 ("drm/sun4i: DW HDMI: Expand algorithm for possible crtcs")

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-8-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index 3459b9ec56c9..21dc9ebad0b4 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -53,22 +53,14 @@ static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
 	struct device_node *port, *ep, *remote, *remote_port;
 	u32 crtcs = 0;
 
-	port = of_graph_get_port_by_id(node, 0);
-	if (!port)
-		return 0;
-
-	ep = of_get_next_available_child(port, NULL);
-	if (!ep)
-		return 0;
-
-	remote = of_graph_get_remote_port_parent(ep);
+	remote = of_graph_get_remote_node(node, 0, -1);
 	if (!remote)
 		return 0;
 
 	if (sun8i_dw_hdmi_node_is_tcon_top(remote)) {
 		port = of_graph_get_port_by_id(remote, 4);
 		if (!port)
-			return 0;
+			goto crtcs_exit;
 
 		for_each_child_of_node(port, ep) {
 			remote_port = of_graph_get_remote_port(ep);
@@ -81,6 +73,9 @@ static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
 		crtcs = drm_of_find_possible_crtcs(drm, node);
 	}
 
+crtcs_exit:
+	of_node_put(remote);
+
 	return crtcs;
 }
 
-- 
cgit v1.2.3


From e0f56782bc2d715d6386f77df40e31e64e2b80b7 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:35:02 +0200
Subject: drm/sun4i: mixer: Order includes alphabetically

Includes are not alphabetically ordered.

Reorder them.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-10-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_mixer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index ee8febb25903..aa81b9838ae8 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -21,8 +21,8 @@
 
 #include <linux/component.h>
 #include <linux/dma-mapping.h>
-#include <linux/reset.h>
 #include <linux/of_device.h>
+#include <linux/reset.h>
 
 #include "sun4i_drv.h"
 #include "sun8i_mixer.h"
-- 
cgit v1.2.3


From 05db311a792d65633ab77950e520eaa5f031cf80 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:35:04 +0200
Subject: drm/sun4i: tcon-top: Add helpers for mux switching

We want to be able to set TCON TOP muxes at runtime. Add helpers for
that.

Old, static configuration of muxes at probe time is preserved for now.
It will be removed when R40 TCON starts using them.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-12-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_tcon_top.c | 74 ++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/sun4i/sun8i_tcon_top.h |  4 ++
 2 files changed, 78 insertions(+)

diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
index ab2591a92ef0..14add8801cda 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -14,6 +14,79 @@
 
 #include "sun8i_tcon_top.h"
 
+static bool sun8i_tcon_top_node_is_tcon_top(struct device_node *node)
+{
+	return !!of_match_node(sun8i_tcon_top_of_table, node);
+}
+
+int sun8i_tcon_top_set_hdmi_src(struct device *dev, int tcon)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 val;
+
+	if (!sun8i_tcon_top_node_is_tcon_top(dev->of_node)) {
+		dev_err(dev, "Device is not TCON TOP!\n");
+		return -EINVAL;
+	}
+
+	if (tcon < 2 || tcon > 3) {
+		dev_err(dev, "TCON index must be 2 or 3!\n");
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&tcon_top->reg_lock, flags);
+
+	val = readl(tcon_top->regs + TCON_TOP_GATE_SRC_REG);
+	val &= ~TCON_TOP_HDMI_SRC_MSK;
+	val |= FIELD_PREP(TCON_TOP_HDMI_SRC_MSK, tcon - 1);
+	writel(val, tcon_top->regs + TCON_TOP_GATE_SRC_REG);
+
+	spin_unlock_irqrestore(&tcon_top->reg_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(sun8i_tcon_top_set_hdmi_src);
+
+int sun8i_tcon_top_de_config(struct device *dev, int mixer, int tcon)
+{
+	struct sun8i_tcon_top *tcon_top = dev_get_drvdata(dev);
+	unsigned long flags;
+	u32 reg;
+
+	if (!sun8i_tcon_top_node_is_tcon_top(dev->of_node)) {
+		dev_err(dev, "Device is not TCON TOP!\n");
+		return -EINVAL;
+	}
+
+	if (mixer > 1) {
+		dev_err(dev, "Mixer index is too high!\n");
+		return -EINVAL;
+	}
+
+	if (tcon > 3) {
+		dev_err(dev, "TCON index is too high!\n");
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&tcon_top->reg_lock, flags);
+
+	reg = readl(tcon_top->regs + TCON_TOP_PORT_SEL_REG);
+	if (mixer == 0) {
+		reg &= ~TCON_TOP_PORT_DE0_MSK;
+		reg |= FIELD_PREP(TCON_TOP_PORT_DE0_MSK, tcon);
+	} else {
+		reg &= ~TCON_TOP_PORT_DE1_MSK;
+		reg |= FIELD_PREP(TCON_TOP_PORT_DE1_MSK, tcon);
+	}
+	writel(reg, tcon_top->regs + TCON_TOP_PORT_SEL_REG);
+
+	spin_unlock_irqrestore(&tcon_top->reg_lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL(sun8i_tcon_top_de_config);
+
 static int sun8i_tcon_top_get_connected_ep_id(struct device_node *node,
 					      int port_id)
 {
@@ -109,6 +182,7 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	regs = devm_ioremap_resource(dev, res);
+	tcon_top->regs = regs;
 	if (IS_ERR(regs))
 		return PTR_ERR(regs);
 
diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.h b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
index 39838bbfeaee..0390584a330e 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.h
@@ -26,6 +26,7 @@
 struct sun8i_tcon_top {
 	struct clk			*bus;
 	struct clk_hw_onecell_data	*clk_data;
+	void __iomem			*regs;
 	struct reset_control		*rst;
 
 	/*
@@ -37,4 +38,7 @@ struct sun8i_tcon_top {
 
 extern const struct of_device_id sun8i_tcon_top_of_table[];
 
+int sun8i_tcon_top_set_hdmi_src(struct device *dev, int tcon);
+int sun8i_tcon_top_de_config(struct device *dev, int mixer, int tcon);
+
 #endif /* _SUN8I_TCON_TOP_H_ */
-- 
cgit v1.2.3


From 5e4965667a6edcf0d5b27fb982ecc07d3d0854f8 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:35:10 +0200
Subject: drm/sun4i: tcon-top: Remove mux configuration at probe time

Now that R40 TCON migrated to runtime mux configuration, old code can be
removed.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-18-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_tcon_top.c | 76 +---------------------------------
 1 file changed, 1 insertion(+), 75 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
index 14add8801cda..046f8dd66f90 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -87,34 +87,6 @@ int sun8i_tcon_top_de_config(struct device *dev, int mixer, int tcon)
 }
 EXPORT_SYMBOL(sun8i_tcon_top_de_config);
 
-static int sun8i_tcon_top_get_connected_ep_id(struct device_node *node,
-					      int port_id)
-{
-	struct device_node *ep, *remote, *port;
-	struct of_endpoint endpoint;
-
-	port = of_graph_get_port_by_id(node, port_id);
-	if (!port)
-		return -ENOENT;
-
-	for_each_available_child_of_node(port, ep) {
-		remote = of_graph_get_remote_port_parent(ep);
-		if (!remote)
-			continue;
-
-		if (of_device_is_available(remote)) {
-			of_graph_parse_endpoint(ep, &endpoint);
-
-			of_node_put(remote);
-
-			return endpoint.id;
-		}
-
-		of_node_put(remote);
-	}
-
-	return -ENOENT;
-}
 
 static struct clk_hw *sun8i_tcon_top_register_gate(struct device *dev,
 						   const char *parent,
@@ -149,11 +121,9 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 	struct platform_device *pdev = to_platform_device(dev);
 	struct clk_hw_onecell_data *clk_data;
 	struct sun8i_tcon_top *tcon_top;
-	bool mixer0_unused = false;
 	struct resource *res;
 	void __iomem *regs;
-	int ret, i, id;
-	u32 val;
+	int ret, i;
 
 	tcon_top = devm_kzalloc(dev, sizeof(*tcon_top), GFP_KERNEL);
 	if (!tcon_top)
@@ -198,50 +168,6 @@ static int sun8i_tcon_top_bind(struct device *dev, struct device *master,
 		goto err_assert_reset;
 	}
 
-	val = 0;
-
-	/* check if HDMI mux output is connected */
-	if (sun8i_tcon_top_get_connected_ep_id(dev->of_node, 5) >= 0) {
-		/* find HDMI input endpoint id, if it is connected at all*/
-		id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 4);
-		if (id >= 0)
-			val = FIELD_PREP(TCON_TOP_HDMI_SRC_MSK, id + 1);
-		else
-			DRM_DEBUG_DRIVER("TCON TOP HDMI input is not connected\n");
-	} else {
-		DRM_DEBUG_DRIVER("TCON TOP HDMI output is not connected\n");
-	}
-
-	writel(val, regs + TCON_TOP_GATE_SRC_REG);
-
-	val = 0;
-
-	/* process mixer0 mux output */
-	id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 1);
-	if (id >= 0) {
-		val = FIELD_PREP(TCON_TOP_PORT_DE0_MSK, id);
-	} else {
-		DRM_DEBUG_DRIVER("TCON TOP mixer0 output is not connected\n");
-		mixer0_unused = true;
-	}
-
-	/* process mixer1 mux output */
-	id = sun8i_tcon_top_get_connected_ep_id(dev->of_node, 3);
-	if (id >= 0) {
-		val |= FIELD_PREP(TCON_TOP_PORT_DE1_MSK, id);
-
-		/*
-		 * mixer0 mux has priority over mixer1 mux. We have to
-		 * make sure mixer0 doesn't overtake TCON from mixer1.
-		 */
-		if (mixer0_unused && id == 0)
-			val |= FIELD_PREP(TCON_TOP_PORT_DE0_MSK, 1);
-	} else {
-		DRM_DEBUG_DRIVER("TCON TOP mixer1 output is not connected\n");
-	}
-
-	writel(val, regs + TCON_TOP_PORT_SEL_REG);
-
 	/*
 	 * TCON TOP has two muxes, which select parent clock for each TCON TV
 	 * channel clock. Parent could be either TCON TV or TVE clock. For now
-- 
cgit v1.2.3


From ac1fe1322530ccca0771e3f680e8a6269c48c449 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Tue, 10 Jul 2018 22:35:11 +0200
Subject: dt-bindings: display: sun4i-drm: Fix order of DW HDMI PHY compatibles

They are currently sorted alphabetically. However, they should be sorted
by release date of the family and then alphabetically.

Fixes: 03c35dbf73e0 ("dt-bindings: display: sun4i-drm: Add description of A64 HDMI PHY")

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710203511.18454-19-jernej.skrabec@siol.net
---
 Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
index 7e2451396a28..f8773ecb7525 100644
--- a/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
+++ b/Documentation/devicetree/bindings/display/sunxi/sun4i-drm.txt
@@ -101,9 +101,9 @@ DWC HDMI PHY
 
 Required properties:
   - compatible: value must be one of:
-    * allwinner,sun50i-a64-hdmi-phy
     * allwinner,sun8i-a83t-hdmi-phy
     * allwinner,sun8i-h3-hdmi-phy
+    * allwinner,sun50i-a64-hdmi-phy
   - reg: base address and size of memory-mapped region
   - clocks: phandles to the clocks feeding the HDMI PHY
     * bus: the HDMI PHY interface clock
-- 
cgit v1.2.3


From ffaa619af1b062d5a37871df6363aa52356007a7 Mon Sep 17 00:00:00 2001
From: Petr Mladek <pmladek@suse.com>
Date: Tue, 10 Jul 2018 10:44:53 +0200
Subject: printk: Fix warning about unused suppress_message_printing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

suppress_message_printing() is not longer called in console_unlock().
Therefore it is not longer needed with disabled CONFIG_PRINTK.

This fixes the warning:

kernel/printk/printk.c:2033:13: warning: ‘suppress_message_printing’ defined but not used [-Wunused-function]
 static bool suppress_message_printing(int level) { return false; }

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Reported-by: Arnd Bergmann <arnd@arndb.de>
Suggested-by: Maninder Singh <maninder1.s@samsung.com>
Acked-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 kernel/printk/printk.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index fcc1992c040a..e2cb0fc18e2d 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2021,7 +2021,6 @@ static void call_console_drivers(const char *ext_text, size_t ext_len,
 				 const char *text, size_t len) {}
 static size_t msg_print_text(const struct printk_log *msg,
 			     bool syslog, char *buf, size_t size) { return 0; }
-static bool suppress_message_printing(int level) { return false; }
 
 #endif /* CONFIG_PRINTK */
 
-- 
cgit v1.2.3


From 7e37dc1db594d5a4ed062dbaf51ef89596a9df8a Mon Sep 17 00:00:00 2001
From: Alan Douglas <adouglas@cadence.com>
Date: Mon, 25 Jun 2018 09:30:49 +0100
Subject: PCI: cadence: Update cdns_pcie_writel() function signature

cdns_pcie_writel() writes a long value; change the value parameter type
from u16 to u32 to rectify the function signature and related behaviour.

Signed-off-by: Alan Douglas <adouglas@cadence.com>
[lorenzo.pieralisi@arm.com: updated commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pcie-cadence.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-cadence.h b/drivers/pci/controller/pcie-cadence.h
index 4bb27333b05c..ed336cc7f4ba 100644
--- a/drivers/pci/controller/pcie-cadence.h
+++ b/drivers/pci/controller/pcie-cadence.h
@@ -279,7 +279,7 @@ static inline void cdns_pcie_ep_fn_writew(struct cdns_pcie *pcie, u8 fn,
 }
 
 static inline void cdns_pcie_ep_fn_writel(struct cdns_pcie *pcie, u8 fn,
-					  u32 reg, u16 value)
+					  u32 reg, u32 value)
 {
 	writel(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg);
 }
-- 
cgit v1.2.3


From 64a7b80ba6ee80f64d36e59331d14b1d25cf7006 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Wed, 11 Jul 2018 13:30:51 +0900
Subject: dt-bindings: regulator: add DT bindings for UniPhier regulator

Add DT bindings for regulators implemented in UniPhier SoCs.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/regulator/uniphier-regulator.txt      | 57 ++++++++++++++++++++++
 1 file changed, 57 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/regulator/uniphier-regulator.txt

diff --git a/Documentation/devicetree/bindings/regulator/uniphier-regulator.txt b/Documentation/devicetree/bindings/regulator/uniphier-regulator.txt
new file mode 100644
index 000000000000..c9919f4b92d2
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/uniphier-regulator.txt
@@ -0,0 +1,57 @@
+Socionext UniPhier Regulator Controller
+
+This describes the devicetree bindings for regulator controller implemented
+on Socionext UniPhier SoCs.
+
+USB3 Controller
+---------------
+
+This regulator controls VBUS and belongs to USB3 glue layer. Before using
+the regulator, it is necessary to control the clocks and resets to enable
+this layer. These clocks and resets should be described in each property.
+
+Required properties:
+- compatible: Should be
+    "socionext,uniphier-pro4-usb3-regulator" - for Pro4 SoC
+    "socionext,uniphier-pxs2-usb3-regulator" - for PXs2 SoC
+    "socionext,uniphier-ld20-usb3-regulator" - for LD20 SoC
+    "socionext,uniphier-pxs3-usb3-regulator" - for PXs3 SoC
+- reg: Specifies offset and length of the register set for the device.
+- clocks: A list of phandles to the clock gate for USB3 glue layer.
+	According to the clock-names, appropriate clocks are required.
+- clock-names: Should contain
+    "gio", "link" - for Pro4 SoC
+    "link"        - for others
+- resets: A list of phandles to the reset control for USB3 glue layer.
+	According to the reset-names, appropriate resets are required.
+- reset-names: Should contain
+    "gio", "link" - for Pro4 SoC
+    "link"        - for others
+
+See Documentation/devicetree/bindings/regulator/regulator.txt
+for more details about the regulator properties.
+
+Example:
+
+	usb-glue@65b00000 {
+		compatible = "socionext,uniphier-ld20-dwc3-glue",
+			     "simple-mfd";
+		#address-cells = <1>;
+		#size-cells = <1>;
+		ranges = <0 0x65b00000 0x400>;
+
+		usb_vbus0: regulators@100 {
+			compatible = "socionext,uniphier-ld20-usb3-regulator";
+			reg = <0x100 0x10>;
+			clock-names = "link";
+			clocks = <&sys_clk 14>;
+			reset-names = "link";
+			resets = <&sys_rst 14>;
+		};
+
+		phy {
+			...
+			phy-supply = <&usb_vbus0>;
+		};
+		...
+	};
-- 
cgit v1.2.3


From 9df4f90954c860b9715f8fbca521781d8d5cf280 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Wed, 11 Jul 2018 13:30:52 +0900
Subject: regulator: uniphier: add regulator driver for UniPhier SoC

Initial commit to add support for regulators implemented in UniPhier SoCs.
This supports USB VBUS only.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig              |   8 ++
 drivers/regulator/Makefile             |   1 +
 drivers/regulator/uniphier-regulator.c | 213 +++++++++++++++++++++++++++++++++
 3 files changed, 222 insertions(+)
 create mode 100644 drivers/regulator/uniphier-regulator.c

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 2964eaea94c0..8233dc7f0a68 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -950,6 +950,14 @@ config REGULATOR_TWL4030
 	  This driver supports the voltage regulators provided by
 	  this family of companion chips.
 
+config REGULATOR_UNIPHIER
+	tristate "UniPhier regulator driver"
+	depends on ARCH_UNIPHIER || COMPILE_TEST
+	depends on OF && MFD_SYSCON
+	default ARCH_UNIPHIER
+	help
+	  Support for regulators implemented on Socionext UniPhier SoCs.
+
 config REGULATOR_VCTRL
 	tristate "Voltage controlled regulators"
 	depends on OF
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index bd818ceb7c72..b7839f41591e 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -118,6 +118,7 @@ obj-$(CONFIG_REGULATOR_TPS65912) += tps65912-regulator.o
 obj-$(CONFIG_REGULATOR_TPS80031) += tps80031-regulator.o
 obj-$(CONFIG_REGULATOR_TPS65132) += tps65132-regulator.o
 obj-$(CONFIG_REGULATOR_TWL4030) += twl-regulator.o twl6030-regulator.o
+obj-$(CONFIG_REGULATOR_UNIPHIER) += uniphier-regulator.o
 obj-$(CONFIG_REGULATOR_VCTRL) += vctrl-regulator.o
 obj-$(CONFIG_REGULATOR_VEXPRESS) += vexpress-regulator.o
 obj-$(CONFIG_REGULATOR_WM831X) += wm831x-dcdc.o
diff --git a/drivers/regulator/uniphier-regulator.c b/drivers/regulator/uniphier-regulator.c
new file mode 100644
index 000000000000..abf22acbd13e
--- /dev/null
+++ b/drivers/regulator/uniphier-regulator.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Regulator controller driver for UniPhier SoC
+// Copyright 2018 Socionext Inc.
+// Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
+
+#include <linux/clk.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/of_regulator.h>
+#include <linux/reset.h>
+
+#define MAX_CLKS	2
+#define MAX_RSTS	2
+
+struct uniphier_regulator_soc_data {
+	int nclks;
+	const char * const *clock_names;
+	int nrsts;
+	const char * const *reset_names;
+	const struct regulator_desc *desc;
+	const struct regmap_config *regconf;
+};
+
+struct uniphier_regulator_priv {
+	struct clk_bulk_data clk[MAX_CLKS];
+	struct reset_control *rst[MAX_RSTS];
+	const struct uniphier_regulator_soc_data *data;
+};
+
+static struct regulator_ops uniphier_regulator_ops = {
+	.enable     = regulator_enable_regmap,
+	.disable    = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+};
+
+static int uniphier_regulator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_regulator_priv *priv;
+	struct regulator_config config = { };
+	struct regulator_dev *rdev;
+	struct regmap *regmap;
+	struct resource *res;
+	void __iomem *base;
+	const char *name;
+	int i, ret, nr;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->data = of_device_get_match_data(dev);
+	if (WARN_ON(!priv->data))
+		return -EINVAL;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	for (i = 0; i < priv->data->nclks; i++)
+		priv->clk[i].id = priv->data->clock_names[i];
+	ret = devm_clk_bulk_get(dev, priv->data->nclks, priv->clk);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < priv->data->nrsts; i++) {
+		name = priv->data->reset_names[i];
+		priv->rst[i] = devm_reset_control_get_shared(dev, name);
+		if (IS_ERR(priv->rst[i]))
+			return PTR_ERR(priv->rst[i]);
+	}
+
+	ret = clk_bulk_prepare_enable(priv->data->nclks, priv->clk);
+	if (ret)
+		return ret;
+
+	for (nr = 0; nr < priv->data->nrsts; nr++) {
+		ret = reset_control_deassert(priv->rst[nr]);
+		if (ret)
+			goto out_rst_assert;
+	}
+
+	regmap = devm_regmap_init_mmio(dev, base, priv->data->regconf);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	config.dev = dev;
+	config.driver_data = priv;
+	config.of_node = dev->of_node;
+	config.regmap = regmap;
+	config.init_data = of_get_regulator_init_data(dev, dev->of_node,
+						      priv->data->desc);
+	rdev = devm_regulator_register(dev, priv->data->desc, &config);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
+		goto out_rst_assert;
+	}
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+out_rst_assert:
+	while (nr--)
+		reset_control_assert(priv->rst[nr]);
+
+	clk_bulk_disable_unprepare(priv->data->nclks, priv->clk);
+
+	return ret;
+}
+
+static int uniphier_regulator_remove(struct platform_device *pdev)
+{
+	struct uniphier_regulator_priv *priv = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < priv->data->nrsts; i++)
+		reset_control_assert(priv->rst[i]);
+
+	clk_bulk_disable_unprepare(priv->data->nclks, priv->clk);
+
+	return 0;
+}
+
+/* USB3 controller data */
+#define USB3VBUS_OFFSET		0x0
+#define USB3VBUS_REG		BIT(4)
+#define USB3VBUS_REG_EN		BIT(3)
+static const struct regulator_desc uniphier_usb3_regulator_desc = {
+	.name = "vbus",
+	.of_match = of_match_ptr("vbus"),
+	.ops = &uniphier_regulator_ops,
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+	.enable_reg  = USB3VBUS_OFFSET,
+	.enable_mask = USB3VBUS_REG_EN | USB3VBUS_REG,
+	.enable_val  = USB3VBUS_REG_EN | USB3VBUS_REG,
+	.disable_val = USB3VBUS_REG_EN,
+};
+
+static const struct regmap_config uniphier_usb3_regulator_regconf = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+	.max_register = 1,
+};
+
+static const char * const uniphier_pro4_clock_reset_names[] = {
+	"gio", "link",
+};
+
+static const struct uniphier_regulator_soc_data uniphier_pro4_usb3_data = {
+	.nclks = ARRAY_SIZE(uniphier_pro4_clock_reset_names),
+	.clock_names = uniphier_pro4_clock_reset_names,
+	.nrsts = ARRAY_SIZE(uniphier_pro4_clock_reset_names),
+	.reset_names = uniphier_pro4_clock_reset_names,
+	.desc = &uniphier_usb3_regulator_desc,
+	.regconf = &uniphier_usb3_regulator_regconf,
+};
+
+static const char * const uniphier_pxs2_clock_reset_names[] = {
+	"link",
+};
+
+static const struct uniphier_regulator_soc_data uniphier_pxs2_usb3_data = {
+	.nclks = ARRAY_SIZE(uniphier_pxs2_clock_reset_names),
+	.clock_names = uniphier_pxs2_clock_reset_names,
+	.nrsts = ARRAY_SIZE(uniphier_pxs2_clock_reset_names),
+	.reset_names = uniphier_pxs2_clock_reset_names,
+	.desc = &uniphier_usb3_regulator_desc,
+	.regconf = &uniphier_usb3_regulator_regconf,
+};
+
+static const struct of_device_id uniphier_regulator_match[] = {
+	/* USB VBUS */
+	{
+		.compatible = "socionext,uniphier-pro4-usb3-regulator",
+		.data = &uniphier_pro4_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-pxs2-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-ld20-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{
+		.compatible = "socionext,uniphier-pxs3-usb3-regulator",
+		.data = &uniphier_pxs2_usb3_data,
+	},
+	{ /* Sentinel */ },
+};
+
+static struct platform_driver uniphier_regulator_driver = {
+	.probe = uniphier_regulator_probe,
+	.remove = uniphier_regulator_remove,
+	.driver = {
+		.name  = "uniphier-regulator",
+		.of_match_table = uniphier_regulator_match,
+	},
+};
+module_platform_driver(uniphier_regulator_driver);
+
+MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
+MODULE_DESCRIPTION("UniPhier Regulator Controller Driver");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From dfb80534692ddc5b97e1da4384f13dc0287fccb2 Mon Sep 17 00:00:00 2001
From: Alan Douglas <adouglas@cadence.com>
Date: Mon, 25 Jun 2018 09:30:50 +0100
Subject: PCI: cadence: Add generic PHY support to host and EP drivers

If PHYs are present, initialize and enable them at driver probe.

Signed-off-by: Alan Douglas <adouglas@cadence.com>
[lorenzo.pieralisi@arm.com: updated commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pcie-cadence-ep.c   | 14 ++++-
 drivers/pci/controller/pcie-cadence-host.c | 15 +++++
 drivers/pci/controller/pcie-cadence.c      | 93 ++++++++++++++++++++++++++++++
 drivers/pci/controller/pcie-cadence.h      |  7 +++
 4 files changed, 128 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c
index e3fe4124e3af..c02f33d8e506 100644
--- a/drivers/pci/controller/pcie-cadence-ep.c
+++ b/drivers/pci/controller/pcie-cadence-ep.c
@@ -439,6 +439,7 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 	struct pci_epc *epc;
 	struct resource *res;
 	int ret;
+	int phy_count;
 
 	ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL);
 	if (!ep)
@@ -473,6 +474,12 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 	if (!ep->ob_addr)
 		return -ENOMEM;
 
+	ret = cdns_pcie_init_phy(dev, pcie);
+	if (ret) {
+		dev_err(dev, "failed to init phy\n");
+		return ret;
+	}
+	platform_set_drvdata(pdev, pcie);
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
@@ -521,6 +528,10 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 
  err_get_sync:
 	pm_runtime_disable(dev);
+	cdns_pcie_disable_phy(pcie);
+	phy_count = pcie->phy_count;
+	while (phy_count--)
+		device_link_del(pcie->link[phy_count]);
 
 	return ret;
 }
@@ -528,6 +539,7 @@ static int cdns_pcie_ep_probe(struct platform_device *pdev)
 static void cdns_pcie_ep_shutdown(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
 	int ret;
 
 	ret = pm_runtime_put_sync(dev);
@@ -536,7 +548,7 @@ static void cdns_pcie_ep_shutdown(struct platform_device *pdev)
 
 	pm_runtime_disable(dev);
 
-	/* The PCIe controller can't be disabled. */
+	cdns_pcie_disable_phy(pcie);
 }
 
 static struct platform_driver cdns_pcie_ep_driver = {
diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c
index a4ebbd37b553..36f31092562f 100644
--- a/drivers/pci/controller/pcie-cadence-host.c
+++ b/drivers/pci/controller/pcie-cadence-host.c
@@ -58,6 +58,9 @@ static void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn,
 
 		return pcie->reg_base + (where & 0xfff);
 	}
+	/* Check that the link is up */
+	if (!(cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE) & 0x1))
+		return NULL;
 
 	/* Update Output registers for AXI region 0. */
 	addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(12) |
@@ -239,6 +242,7 @@ static int cdns_pcie_host_probe(struct platform_device *pdev)
 	struct cdns_pcie *pcie;
 	struct resource *res;
 	int ret;
+	int phy_count;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc));
 	if (!bridge)
@@ -290,6 +294,13 @@ static int cdns_pcie_host_probe(struct platform_device *pdev)
 	}
 	pcie->mem_res = res;
 
+	ret = cdns_pcie_init_phy(dev, pcie);
+	if (ret) {
+		dev_err(dev, "failed to init phy\n");
+		return ret;
+	}
+	platform_set_drvdata(pdev, pcie);
+
 	pm_runtime_enable(dev);
 	ret = pm_runtime_get_sync(dev);
 	if (ret < 0) {
@@ -322,6 +333,10 @@ static int cdns_pcie_host_probe(struct platform_device *pdev)
 
  err_get_sync:
 	pm_runtime_disable(dev);
+	cdns_pcie_disable_phy(pcie);
+	phy_count = pcie->phy_count;
+	while (phy_count--)
+		device_link_del(pcie->link[phy_count]);
 
 	return ret;
 }
diff --git a/drivers/pci/controller/pcie-cadence.c b/drivers/pci/controller/pcie-cadence.c
index 138d113eb45d..2edc12661e44 100644
--- a/drivers/pci/controller/pcie-cadence.c
+++ b/drivers/pci/controller/pcie-cadence.c
@@ -124,3 +124,96 @@ void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r)
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), 0);
 	cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), 0);
 }
+
+void cdns_pcie_disable_phy(struct cdns_pcie *pcie)
+{
+	int i = pcie->phy_count;
+
+	while (i--) {
+		phy_power_off(pcie->phy[i]);
+		phy_exit(pcie->phy[i]);
+	}
+}
+
+int cdns_pcie_enable_phy(struct cdns_pcie *pcie)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < pcie->phy_count; i++) {
+		ret = phy_init(pcie->phy[i]);
+		if (ret < 0)
+			goto err_phy;
+
+		ret = phy_power_on(pcie->phy[i]);
+		if (ret < 0) {
+			phy_exit(pcie->phy[i]);
+			goto err_phy;
+		}
+	}
+
+	return 0;
+
+err_phy:
+	while (--i >= 0) {
+		phy_power_off(pcie->phy[i]);
+		phy_exit(pcie->phy[i]);
+	}
+
+	return ret;
+}
+
+int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie)
+{
+	struct device_node *np = dev->of_node;
+	int phy_count;
+	struct phy **phy;
+	struct device_link **link;
+	int i;
+	int ret;
+	const char *name;
+
+	phy_count = of_property_count_strings(np, "phy-names");
+	if (phy_count < 1) {
+		dev_err(dev, "no phy-names.  PHY will not be initialized\n");
+		pcie->phy_count = 0;
+		return 0;
+	}
+
+	phy = devm_kzalloc(dev, sizeof(*phy) * phy_count, GFP_KERNEL);
+	if (!phy)
+		return -ENOMEM;
+
+	link = devm_kzalloc(dev, sizeof(*link) * phy_count, GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+
+	for (i = 0; i < phy_count; i++) {
+		of_property_read_string_index(np, "phy-names", i, &name);
+		phy[i] = devm_phy_optional_get(dev, name);
+		if (IS_ERR(phy))
+			return PTR_ERR(phy);
+
+		link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS);
+		if (!link[i]) {
+			ret = -EINVAL;
+			goto err_link;
+		}
+	}
+
+	pcie->phy_count = phy_count;
+	pcie->phy = phy;
+	pcie->link = link;
+
+	ret =  cdns_pcie_enable_phy(pcie);
+	if (ret)
+		goto err_link;
+
+	return 0;
+
+err_link:
+	while (--i >= 0)
+		device_link_del(link[i]);
+
+	return ret;
+}
diff --git a/drivers/pci/controller/pcie-cadence.h b/drivers/pci/controller/pcie-cadence.h
index ed336cc7f4ba..b342c808f7d6 100644
--- a/drivers/pci/controller/pcie-cadence.h
+++ b/drivers/pci/controller/pcie-cadence.h
@@ -8,6 +8,7 @@
 
 #include <linux/kernel.h>
 #include <linux/pci.h>
+#include <linux/phy/phy.h>
 
 /*
  * Local Management Registers
@@ -229,6 +230,9 @@ struct cdns_pcie {
 	struct resource		*mem_res;
 	bool			is_rc;
 	u8			bus;
+	int			phy_count;
+	struct phy		**phy;
+	struct device_link	**link;
 };
 
 /* Register access */
@@ -307,5 +311,8 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, u8 fn,
 						  u32 r, u64 cpu_addr);
 
 void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r);
+void cdns_pcie_disable_phy(struct cdns_pcie *pcie);
+int cdns_pcie_enable_phy(struct cdns_pcie *pcie);
+int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie);
 
 #endif /* _PCIE_CADENCE_H */
-- 
cgit v1.2.3


From 82dfbd27c837b5a7c2a7a13b54a4f0b16c51222f Mon Sep 17 00:00:00 2001
From: Alan Douglas <adouglas@cadence.com>
Date: Mon, 25 Jun 2018 09:30:51 +0100
Subject: dt-bindings: PCI: cadence: Add DT bindings for optional PHYs

Update DT documentation to include optional PHYs for cadence PCIe
host and endpoint controllers.

Signed-off-by: Alan Douglas <adouglas@cadence.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt   | 5 +++++
 Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt | 6 ++++++
 2 files changed, 11 insertions(+)

diff --git a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt
index 9a305237fa6e..4a0475e2ba7e 100644
--- a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt
+++ b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-ep.txt
@@ -9,6 +9,9 @@ Required properties:
 
 Optional properties:
 - max-functions: Maximum number of functions that can be configured (default 1).
+- phys: From PHY bindings: List of Generic PHY phandles. One per lane if more
+  than one in the list.  If only one PHY listed it must manage all lanes. 
+- phy-names:  List of names to identify the PHY.
 
 Example:
 
@@ -19,4 +22,6 @@ pcie@fc000000 {
 	reg-names = "reg", "mem";
 	cdns,max-outbound-regions = <16>;
 	max-functions = /bits/ 8 <8>;
+	phys = <&ep_phy0 &ep_phy1>;
+	phy-names = "pcie-lane0","pcie-lane1";
 };
diff --git a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt
index 20a33f38f69d..91de69c713a9 100644
--- a/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt
+++ b/Documentation/devicetree/bindings/pci/cdns,cdns-pcie-host.txt
@@ -24,6 +24,9 @@ Optional properties:
   translations (default 32)
 - vendor-id: The PCI vendor ID (16 bits, default is design dependent)
 - device-id: The PCI device ID (16 bits, default is design dependent)
+- phys: From PHY bindings: List of Generic PHY phandles. One per lane if more
+  than one in the list.  If only one PHY listed it must manage all lanes. 
+- phy-names:  List of names to identify the PHY.
 
 Example:
 
@@ -57,4 +60,7 @@ pcie@fb000000 {
 	interrupt-map-mask = <0x0 0x0 0x0  0x7>;
 
 	msi-parent = <&its_pci>;
+
+	phys = <&pcie_phy0>;
+	phy-names = "pcie-phy";
 };
-- 
cgit v1.2.3


From 231f9415001138a000cd0f881c46654b7ea3f8c5 Mon Sep 17 00:00:00 2001
From: Willy Tarreau <w@1wt.eu>
Date: Mon, 9 Jul 2018 14:03:55 +0200
Subject: ACPI / PM: save NVS memory for ASUS 1025C laptop

Every time I tried to upgrade my laptop from 3.10.x to 4.x I faced an
issue by which the fan would run at full speed upon resume. Bisecting
it showed me the issue was introduced in 3.17 by commit 821d6f0359b0
(ACPI / sleep: Do not save NVS for new machines to accelerate S3). This
code only affects machines built starting as of 2012, but this Asus
1025C laptop was made in 2012 and apparently needs the NVS data to be
saved, otherwise the CPU's thermal state is not properly reported on
resume and the fan runs at full speed upon resume.

Here's a very simple way to check if such a machine is affected :

  # cat /sys/class/thermal/thermal_zone0/temp
  55000

  ( now suspend, wait one second and resume )

  # cat /sys/class/thermal/thermal_zone0/temp
  0

  (and after ~15 seconds the fan starts to spin)

Let's apply the same quirk as commit cbc00c13 (ACPI: save NVS memory
for Lenovo G50-45) and reuse the function it provides. Note that this
commit was already backported to 4.9.x but not 4.4.x.

Cc: 3.17+ <stable@vger.kernel.org> # 3.17+: requires cbc00c13
Signed-off-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/sleep.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 06ba8cc68889..754d59f95500 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -338,6 +338,14 @@ static const struct dmi_system_id acpisleep_dmi_table[] __initconst = {
 		DMI_MATCH(DMI_PRODUCT_NAME, "K54HR"),
 		},
 	},
+	{
+	.callback = init_nvs_save_s3,
+	.ident = "Asus 1025C",
+	.matches = {
+		DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+		DMI_MATCH(DMI_PRODUCT_NAME, "1025C"),
+		},
+	},
 	/*
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=189431
 	 * Lenovo G50-45 is a platform later than 2012, but needs nvs memory
-- 
cgit v1.2.3


From e69244d29558c947703851a26bfed833945c093a Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 26 Jun 2018 15:52:38 +0100
Subject: ARM: 8777/1: Hook up SYNC_CORE functionality for sys_membarrier()

Exception return implies context synchronization, so we can hook up the
SYNC_CORE option to sys_membarrier() simply by selecting the Kconfig option,
just like we've done for arm64 already.

Cc: Orion Hodson <oth@google.com>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 .../features/sched/membarrier-sync-core/arch-support.txt          | 8 ++++----
 arch/arm/Kconfig                                                  | 1 +
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/Documentation/features/sched/membarrier-sync-core/arch-support.txt b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
index dbdf62907703..c7858dd1ea8f 100644
--- a/Documentation/features/sched/membarrier-sync-core/arch-support.txt
+++ b/Documentation/features/sched/membarrier-sync-core/arch-support.txt
@@ -5,10 +5,10 @@
 #
 # Architecture requirements
 #
-# * arm64
+# * arm/arm64
 #
-# Rely on eret context synchronization when returning from IPI handler, and
-# when returning to user-space.
+# Rely on implicit context synchronization as a result of exception return
+# when returning from IPI handler, and when returning to user-space.
 #
 # * x86
 #
@@ -31,7 +31,7 @@
     -----------------------
     |       alpha: | TODO |
     |         arc: | TODO |
-    |         arm: | TODO |
+    |         arm: |  ok  |
     |       arm64: |  ok  |
     |         c6x: | TODO |
     |       h8300: | TODO |
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 54eeb8d00bc6..b0ac18547370 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -9,6 +9,7 @@ config ARM
 	select ARCH_HAS_ELF_RANDOMIZE
 	select ARCH_HAS_FORTIFY_SOURCE
 	select ARCH_HAS_KCOV
+	select ARCH_HAS_MEMBARRIER_SYNC_CORE
 	select ARCH_HAS_PTE_SPECIAL if ARM_LPAE
 	select ARCH_HAS_PHYS_TO_DMA
 	select ARCH_HAS_SET_MEMORY
-- 
cgit v1.2.3


From 2288fd51808cdf697f12d92706706554192db290 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Mon, 9 Jul 2018 03:09:42 +0100
Subject: ARM: 8779/1: add endianness option to LDFLAGS instead of LD

With the recent syntax extension, Kconfig is now able to evaluate the
compiler / toolchain capability.

However, accumulating flags to 'LD' is not compatible with the way
it works; 'LD' must be passed to Kconfig to call $(ld-option,...)
from Kconfig files.  If you tweak 'LD' in arch Makefile depending on
CONFIG_CPU_BIG_ENDIAN, this would end up with circular dependency
between Makefile and Kconfig.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/Makefile | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index fc26c3d7b9b6..62ebeae9f837 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -46,12 +46,12 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__ARMEB__
 AS		+= -EB
-LD		+= -EB
+LDFLAGS		+= -EB
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__ARMEL__
 AS		+= -EL
-LD		+= -EL
+LDFLAGS		+= -EL
 endif
 
 #
-- 
cgit v1.2.3


From 76672e2e5b86d330e236eabe3ca3d471a581df57 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 19 Jun 2018 15:32:05 +0100
Subject: ARM: 8776/1: clkdev: Remove duplicated negative index check from
 __of_clk_get()

__of_clk_get() calls of_parse_phandle_with_args(), which rejects
negative indices since commit bd69f73f2c81eed9 ("of: Create function for
counting number of phandles in a property").

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/clk/clkdev.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 7513411140b6..02fcee2012e0 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -35,9 +35,6 @@ static struct clk *__of_clk_get(struct device_node *np, int index,
 	struct clk *clk;
 	int rc;
 
-	if (index < 0)
-		return ERR_PTR(-EINVAL);
-
 	rc = of_parse_phandle_with_args(np, "clocks", "#clock-cells", index,
 					&clkspec);
 	if (rc)
-- 
cgit v1.2.3


From e76ad18b56775aa20c0fb8e6203fae2aaee57e5c Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 6 Jul 2018 16:05:27 +0100
Subject: regmap: slimbus: add support to multi read/write

SLIMbus supports upto 16 bytes in value management messages,
so add support to read/writes upto 16 bytes.

This also removes redundant single register reg_read/reg_write.

Also useful for paged register access on SLIMbus interfaced codecs.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap-slimbus.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/drivers/base/regmap/regmap-slimbus.c b/drivers/base/regmap/regmap-slimbus.c
index 91d501eda8a9..0968059f1ef5 100644
--- a/drivers/base/regmap/regmap-slimbus.c
+++ b/drivers/base/regmap/regmap-slimbus.c
@@ -7,33 +7,24 @@
 
 #include "internal.h"
 
-static int regmap_slimbus_byte_reg_read(void *context, unsigned int reg,
-					unsigned int *val)
+static int regmap_slimbus_write(void *context, const void *data, size_t count)
 {
 	struct slim_device *sdev = context;
-	int v;
 
-	v = slim_readb(sdev, reg);
-
-	if (v < 0)
-		return v;
-
-	*val = v;
-
-	return 0;
+	return slim_write(sdev, *(u16 *)data, count - 2, (u8 *)data + 2);
 }
 
-static int regmap_slimbus_byte_reg_write(void *context, unsigned int reg,
-					 unsigned int val)
+static int regmap_slimbus_read(void *context, const void *reg, size_t reg_size,
+			       void *val, size_t val_size)
 {
 	struct slim_device *sdev = context;
 
-	return slim_writeb(sdev, reg, val);
+	return slim_read(sdev, *(u16 *)reg, val_size, val);
 }
 
 static struct regmap_bus regmap_slimbus_bus = {
-	.reg_write = regmap_slimbus_byte_reg_write,
-	.reg_read = regmap_slimbus_byte_reg_read,
+	.write = regmap_slimbus_write,
+	.read = regmap_slimbus_read,
 	.reg_format_endian_default = REGMAP_ENDIAN_LITTLE,
 	.val_format_endian_default = REGMAP_ENDIAN_LITTLE,
 };
-- 
cgit v1.2.3


From 435ffb76f8b35be108a52bf1c43233a57b3c72b4 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 5 Jul 2018 12:13:48 +0200
Subject: ASoC: dpcm: rework runtime stream merge

The goal of this patch is to simplify a bit dpcm runtime stream merge
by removing several local variables.

ATM, merge functions return the BE 'filter' values which should then be
filtered against the FE stream values. This create a lot of local
variable and unnecessary init of min and max.

Instead of this, we can pass the FE stream values directly and let the
BE filtering functions perform the merge 'in-place'

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-pcm.c | 39 +++++++++++++++------------------------
 1 file changed, 15 insertions(+), 24 deletions(-)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index b7e67b871c0c..114e6c060cae 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1672,29 +1672,28 @@ unwind:
 }
 
 static void dpcm_init_runtime_hw(struct snd_pcm_runtime *runtime,
-				 struct snd_soc_pcm_stream *stream,
-				 u64 formats)
+				 struct snd_soc_pcm_stream *stream)
 {
 	runtime->hw.rate_min = stream->rate_min;
 	runtime->hw.rate_max = stream->rate_max;
 	runtime->hw.channels_min = stream->channels_min;
 	runtime->hw.channels_max = stream->channels_max;
 	if (runtime->hw.formats)
-		runtime->hw.formats &= formats & stream->formats;
+		runtime->hw.formats &= stream->formats;
 	else
-		runtime->hw.formats = formats & stream->formats;
+		runtime->hw.formats = stream->formats;
 	runtime->hw.rates = stream->rates;
 }
 
-static u64 dpcm_runtime_base_format(struct snd_pcm_substream *substream)
+static void dpcm_runtime_merge_format(struct snd_pcm_substream *substream,
+				      u64 *formats)
 {
 	struct snd_soc_pcm_runtime *fe = substream->private_data;
 	struct snd_soc_dpcm *dpcm;
-	u64 formats = ULLONG_MAX;
 	int stream = substream->stream;
 
 	if (!fe->dai_link->dpcm_merged_format)
-		return formats;
+		return;
 
 	/*
 	 * It returns merged BE codec format
@@ -1714,16 +1713,14 @@ static u64 dpcm_runtime_base_format(struct snd_pcm_substream *substream)
 			else
 				codec_stream = &codec_dai_drv->capture;
 
-			formats &= codec_stream->formats;
+			*formats &= codec_stream->formats;
 		}
 	}
-
-	return formats;
 }
 
-static void dpcm_runtime_base_chan(struct snd_pcm_substream *substream,
-				   unsigned int *channels_min,
-				   unsigned int *channels_max)
+static void dpcm_runtime_merge_chan(struct snd_pcm_substream *substream,
+				    unsigned int *channels_min,
+				    unsigned int *channels_max)
 {
 	struct snd_soc_pcm_runtime *fe = substream->private_data;
 	struct snd_soc_dpcm *dpcm;
@@ -1732,9 +1729,6 @@ static void dpcm_runtime_base_chan(struct snd_pcm_substream *substream,
 	if (!fe->dai_link->dpcm_merged_chan)
 		return;
 
-	*channels_min = 0;
-	*channels_max = UINT_MAX;
-
 	/*
 	 * It returns merged BE codec channel;
 	 * if FE want to use it (= dpcm_merged_chan)
@@ -1781,18 +1775,15 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
 	struct snd_soc_dai_driver *cpu_dai_drv = cpu_dai->driver;
-	u64 format = dpcm_runtime_base_format(substream);
-	unsigned int channels_min = 0, channels_max = UINT_MAX;
 
 	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK)
-		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->playback, format);
+		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->playback);
 	else
-		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture, format);
-
-	dpcm_runtime_base_chan(substream, &channels_min, &channels_max);
+		dpcm_init_runtime_hw(runtime, &cpu_dai_drv->capture);
 
-	runtime->hw.channels_min = max(channels_min, runtime->hw.channels_min);
-	runtime->hw.channels_max = min(channels_max, runtime->hw.channels_max);
+	dpcm_runtime_merge_format(substream, &runtime->hw.formats);
+	dpcm_runtime_merge_chan(substream, &runtime->hw.channels_min,
+				&runtime->hw.channels_max);
 }
 
 static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd);
-- 
cgit v1.2.3


From baacd8d100d571aa713c3c60b1471b9962e6ec8a Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 5 Jul 2018 12:13:49 +0200
Subject: ASoC: dpcm: add rate merge to the BE stream merge

As done for format and channels, add the possibility to merge
the backend rates on the frontend rates.

This useful if the backend does not support all rates supported by the
frontend, or if several backends (cpu and codecs) with different
capabilities are connected to the same frontend.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h |  2 ++
 sound/soc/soc-pcm.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index 870ba6b64817..a4915148f739 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -964,6 +964,8 @@ struct snd_soc_dai_link {
 	unsigned int dpcm_merged_format:1;
 	/* DPCM used FE & BE merged channel */
 	unsigned int dpcm_merged_chan:1;
+	/* DPCM used FE & BE merged rate */
+	unsigned int dpcm_merged_rate:1;
 
 	/* pmdown_time is ignored at stop */
 	unsigned int ignore_pmdown_time:1;
diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 114e6c060cae..4019bc10897c 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1769,6 +1769,64 @@ static void dpcm_runtime_merge_chan(struct snd_pcm_substream *substream,
 	}
 }
 
+static void dpcm_runtime_merge_rate(struct snd_pcm_substream *substream,
+				    unsigned int *rates,
+				    unsigned int *rate_min,
+				    unsigned int *rate_max)
+{
+	struct snd_soc_pcm_runtime *fe = substream->private_data;
+	struct snd_soc_dpcm *dpcm;
+	int stream = substream->stream;
+
+	if (!fe->dai_link->dpcm_merged_rate)
+		return;
+
+	/*
+	 * It returns merged BE codec channel;
+	 * if FE want to use it (= dpcm_merged_chan)
+	 */
+
+	list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be) {
+		struct snd_soc_pcm_runtime *be = dpcm->be;
+		struct snd_soc_dai_driver *cpu_dai_drv =  be->cpu_dai->driver;
+		struct snd_soc_dai_driver *codec_dai_drv;
+		struct snd_soc_pcm_stream *codec_stream;
+		struct snd_soc_pcm_stream *cpu_stream;
+		int i;
+
+		if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+			cpu_stream = &cpu_dai_drv->playback;
+		else
+			cpu_stream = &cpu_dai_drv->capture;
+
+		*rate_min = max(*rate_min, cpu_stream->rate_min);
+		*rate_max = min_not_zero(*rate_max, cpu_stream->rate_max);
+		*rates = snd_pcm_rate_mask_intersect(*rates, cpu_stream->rates);
+
+		for (i = 0; i < be->num_codecs; i++) {
+			/*
+			 * Skip CODECs which don't support the current stream
+			 * type. See soc_pcm_init_runtime_hw() for more details
+			 */
+			if (!snd_soc_dai_stream_valid(be->codec_dais[i],
+						      stream))
+				continue;
+
+			codec_dai_drv = be->codec_dais[i]->driver;
+			if (stream == SNDRV_PCM_STREAM_PLAYBACK)
+				codec_stream = &codec_dai_drv->playback;
+			else
+				codec_stream = &codec_dai_drv->capture;
+
+			*rate_min = max(*rate_min, codec_stream->rate_min);
+			*rate_max = min_not_zero(*rate_max,
+						 codec_stream->rate_max);
+			*rates = snd_pcm_rate_mask_intersect(*rates,
+						codec_stream->rates);
+		}
+	}
+}
+
 static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
@@ -1784,6 +1842,8 @@ static void dpcm_set_fe_runtime(struct snd_pcm_substream *substream)
 	dpcm_runtime_merge_format(substream, &runtime->hw.formats);
 	dpcm_runtime_merge_chan(substream, &runtime->hw.channels_min,
 				&runtime->hw.channels_max);
+	dpcm_runtime_merge_rate(substream, &runtime->hw.rates,
+				&runtime->hw.rate_min, &runtime->hw.rate_max);
 }
 
 static int dpcm_fe_dai_do_trigger(struct snd_pcm_substream *substream, int cmd);
-- 
cgit v1.2.3


From 141cb3d4ee521eff45d0520327106ddfe0abe90a Mon Sep 17 00:00:00 2001
From: Xiaowei Song <songxiaowei@hisilicon.com>
Date: Wed, 11 Jul 2018 16:09:46 +0800
Subject: PCI: kirin: Add MSI support

Add support for MSI to the kirin host controller driver, based
on the generic dwc infrastructure.

Signed-off-by: Xiaowei Song <songxiaowei@hisilicon.com>
Signed-off-by: Yao Chen <chenyao11@huawei.com>
[lorenzo.pieralisi@arm.com: updated commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
---
 drivers/pci/controller/dwc/pcie-kirin.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index d2970a009eb5..5352e0c3be82 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -430,6 +430,9 @@ static int kirin_pcie_host_init(struct pcie_port *pp)
 {
 	kirin_pcie_establish_link(pp);
 
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		dw_pcie_msi_init(pp);
+
 	return 0;
 }
 
@@ -445,9 +448,34 @@ static const struct dw_pcie_host_ops kirin_pcie_host_ops = {
 	.host_init = kirin_pcie_host_init,
 };
 
+static int kirin_pcie_add_msi(struct dw_pcie *pci,
+				struct platform_device *pdev)
+{
+	int irq;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		irq = platform_get_irq(pdev, 0);
+		if (irq < 0) {
+			dev_err(&pdev->dev,
+				"failed to get MSI IRQ (%d)\n", irq);
+			return irq;
+		}
+
+		pci->pp.msi_irq = irq;
+	}
+
+	return 0;
+}
+
 static int __init kirin_add_pcie_port(struct dw_pcie *pci,
 				      struct platform_device *pdev)
 {
+	int ret;
+
+	ret = kirin_pcie_add_msi(pci, pdev);
+	if (ret)
+		return ret;
+
 	pci->pp.ops = &kirin_pcie_host_ops;
 
 	return dw_pcie_host_init(&pci->pp);
-- 
cgit v1.2.3


From 409d5db49867c20d226a1fc50a73d646bd733dae Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 20 Jun 2018 14:46:50 +0100
Subject: arm64: rseq: Implement backend rseq calls and select HAVE_RSEQ

Implement calls to rseq_signal_deliver, rseq_handle_notify_resume
and rseq_syscall so that we can select HAVE_RSEQ on arm64.

Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig                | 1 +
 arch/arm64/include/asm/unistd.h   | 2 +-
 arch/arm64/include/asm/unistd32.h | 2 ++
 arch/arm64/kernel/entry.S         | 2 ++
 arch/arm64/kernel/ptrace.c        | 2 ++
 arch/arm64/kernel/signal.c        | 3 +++
 6 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 2e7609e4d08a..f4157d4a0289 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -138,6 +138,7 @@ config ARM64
 	select HAVE_PERF_USER_STACK_DUMP
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_RCU_TABLE_FREE
+	select HAVE_RSEQ
 	select HAVE_STACKPROTECTOR
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KPROBES
diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h
index a0baa9af5487..e0d0f5b856e7 100644
--- a/arch/arm64/include/asm/unistd.h
+++ b/arch/arm64/include/asm/unistd.h
@@ -43,7 +43,7 @@
 #define __ARM_NR_compat_cacheflush	(__ARM_NR_COMPAT_BASE+2)
 #define __ARM_NR_compat_set_tls		(__ARM_NR_COMPAT_BASE+5)
 
-#define __NR_compat_syscalls		398
+#define __NR_compat_syscalls		399
 #endif
 
 #define __ARCH_WANT_SYS_CLONE
diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index ef292160748c..0fdc7ef8a776 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -817,6 +817,8 @@ __SYSCALL(__NR_pkey_alloc, sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free, sys_pkey_free)
 #define __NR_statx 397
 __SYSCALL(__NR_statx, sys_statx)
+#define __NR_rseq 398
+__SYSCALL(__NR_rseq, sys_rseq)
 
 /*
  * Please add new compat syscalls above this comment and update
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 28ad8799406f..1eda9e1a1f4a 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -904,6 +904,7 @@ ENDPROC(el0_error)
 ret_fast_syscall:
 	disable_daif
 	str	x0, [sp, #S_X0]			// returned x0
+#ifndef CONFIG_DEBUG_RSEQ
 	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
 	cbnz	x2, ret_fast_syscall_trace
@@ -911,6 +912,7 @@ ret_fast_syscall:
 	cbnz	x2, work_pending
 	enable_step_tsk x1, x2
 	kernel_exit 0
+#endif
 ret_fast_syscall_trace:
 	enable_daif
 	b	__sys_trace_return_skipped	// we already saved x0
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 42ff28aa5a00..489db3624606 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1658,6 +1658,8 @@ asmlinkage void syscall_trace_exit(struct pt_regs *regs)
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_EXIT);
+
+	rseq_syscall(regs);
 }
 
 /*
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 511af13e8d8f..e3b1d1b0aee8 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -802,6 +802,8 @@ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs)
 	int usig = ksig->sig;
 	int ret;
 
+	rseq_signal_deliver(ksig, regs);
+
 	/*
 	 * Set up the stack frame
 	 */
@@ -940,6 +942,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 			if (thread_flags & _TIF_NOTIFY_RESUME) {
 				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);
+				rseq_handle_notify_resume(NULL, regs);
 			}
 
 			if (thread_flags & _TIF_FOREIGN_FPSTATE)
-- 
cgit v1.2.3


From db7a2d1809a5b6b08d138ff68837f805fc073351 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 20 Jun 2018 14:58:10 +0100
Subject: asm-generic: unistd.h: Wire up sys_rseq

The new rseq call arrived in 4.18-rc1, so provide it in the asm-generic
unistd.h for architectures such as arm64.

Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/uapi/asm-generic/unistd.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 42990676a55e..df4bedb9b01c 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -734,9 +734,11 @@ __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 __SYSCALL(__NR_statx,     sys_statx)
 #define __NR_io_pgetevents 292
 __SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+#define __NR_rseq 293
+__SYSCALL(__NR_rseq, sys_rseq)
 
 #undef __NR_syscalls
-#define __NR_syscalls 293
+#define __NR_syscalls 294
 
 /*
  * 32 bit systems traditionally used different
-- 
cgit v1.2.3


From 0337976f40b0a9605c24797762b95b3414619d71 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 14:41:00 +0200
Subject: drm/admkfd use modern ktime accessors

getrawmonotonic64() and get_monotonic_boottime64() are deprecated
because of the nonstandard naming.

The replacement functions ktime_get_raw_ns() and ktime_get_boot_ns()
also simplify the callers.

Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index f64c5551cdba..7e717716b90e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -754,7 +754,6 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 {
 	struct kfd_ioctl_get_clock_counters_args *args = data;
 	struct kfd_dev *dev;
-	struct timespec64 time;
 
 	dev = kfd_device_by_id(args->gpu_id);
 	if (dev)
@@ -766,11 +765,8 @@ static int kfd_ioctl_get_clock_counters(struct file *filep,
 		args->gpu_clock_counter = 0;
 
 	/* No access to rdtsc. Using raw monotonic time */
-	getrawmonotonic64(&time);
-	args->cpu_clock_counter = (uint64_t)timespec64_to_ns(&time);
-
-	get_monotonic_boottime64(&time);
-	args->system_clock_counter = (uint64_t)timespec64_to_ns(&time);
+	args->cpu_clock_counter = ktime_get_raw_ns();
+	args->system_clock_counter = ktime_get_boot_ns();
 
 	/* Since the counter is in nano-seconds we use 1GHz frequency */
 	args->system_clock_freq = 1000000000;
-- 
cgit v1.2.3


From 19bb33c756edee5e3f0fb126895f6ec23e60dd08 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 11 Jul 2018 08:36:02 +0100
Subject: drm/i915: Introduce i915_address_space.mutex

Add a mutex into struct i915_address_space to be used while operating on
the vma and their lists for a particular vm. As this may be called from
the shrinker, we taint the mutex with fs_reclaim so that from the start
lockdep warns us if we are caught holding the mutex across an
allocation. (With such small steps we will eventually rid ourselves of
struct_mutex recursion!)

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711073608.20286-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.h          |  2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c      | 10 ++++++++++
 drivers/gpu/drm/i915/i915_gem_gtt.h      |  2 ++
 drivers/gpu/drm/i915/i915_gem_shrinker.c | 12 ++++++++++++
 4 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a90a37ce2ef9..48b350116cba 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3307,7 +3307,7 @@ unsigned long i915_gem_shrink(struct drm_i915_private *i915,
 unsigned long i915_gem_shrink_all(struct drm_i915_private *i915);
 void i915_gem_shrinker_register(struct drm_i915_private *i915);
 void i915_gem_shrinker_unregister(struct drm_i915_private *i915);
-
+void i915_gem_shrinker_taints_mutex(struct mutex *mutex);
 
 /* i915_gem_tiling.c */
 static inline bool i915_gem_object_needs_bit17_swizzle(struct drm_i915_gem_object *obj)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 210baf3c8d11..502353b9bf84 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -531,6 +531,14 @@ static void vm_free_page(struct i915_address_space *vm, struct page *page)
 static void i915_address_space_init(struct i915_address_space *vm,
 				    struct drm_i915_private *dev_priv)
 {
+	/*
+	 * The vm->mutex must be reclaim safe (for use in the shrinker).
+	 * Do a dummy acquire now under fs_reclaim so that any allocation
+	 * attempt holding the lock is immediately reported by lockdep.
+	 */
+	mutex_init(&vm->mutex);
+	i915_gem_shrinker_taints_mutex(&vm->mutex);
+
 	GEM_BUG_ON(!vm->total);
 	drm_mm_init(&vm->mm, 0, vm->total);
 	vm->mm.head_node.color = I915_COLOR_UNEVICTABLE;
@@ -551,6 +559,8 @@ static void i915_address_space_fini(struct i915_address_space *vm)
 	spin_unlock(&vm->free_pages.lock);
 
 	drm_mm_takedown(&vm->mm);
+
+	mutex_destroy(&vm->mutex);
 }
 
 static int __setup_page_dma(struct i915_address_space *vm,
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index feda45dfd481..14e62651010b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -293,6 +293,8 @@ struct i915_address_space {
 
 	bool closed;
 
+	struct mutex mutex; /* protects vma and our lists */
+
 	struct i915_page_dma scratch_page;
 	struct i915_page_table *scratch_pt;
 	struct i915_page_directory *scratch_pd;
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index c61f5b80fee3..ea90d3a0d511 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/drivers/gpu/drm/i915/i915_gem_shrinker.c
@@ -23,6 +23,7 @@
  */
 
 #include <linux/oom.h>
+#include <linux/sched/mm.h>
 #include <linux/shmem_fs.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -531,3 +532,14 @@ void i915_gem_shrinker_unregister(struct drm_i915_private *i915)
 	WARN_ON(unregister_oom_notifier(&i915->mm.oom_notifier));
 	unregister_shrinker(&i915->mm.shrinker);
 }
+
+void i915_gem_shrinker_taints_mutex(struct mutex *mutex)
+{
+	if (!IS_ENABLED(CONFIG_LOCKDEP))
+		return;
+
+	fs_reclaim_acquire(GFP_KERNEL);
+	mutex_lock(mutex);
+	mutex_unlock(mutex);
+	fs_reclaim_release(GFP_KERNEL);
+}
-- 
cgit v1.2.3


From cb4dc8daf4cb72d7833148a6087b425b5c20e903 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Wed, 11 Jul 2018 13:29:52 +0100
Subject: drm/i915/selftests: Add a safety net to live_workarounds

Since live_workarounds poke around the w/a registers and checks to see
if they survive across a reset, we are prone to fouling the machine and
leaving it in a non-recoverable state. Wrap the probe inside a timeout
to abort the test if the reset fails.

v2: Include GEM_TRACE on declaring wedged.
v3: Add a few includes to make the header look standalone.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107188
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711122952.18448-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/igt_wedge_me.h      | 58 ++++++++++++++++++++++
 drivers/gpu/drm/i915/selftests/intel_workarounds.c |  8 ++-
 2 files changed, 65 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/i915/selftests/igt_wedge_me.h

diff --git a/drivers/gpu/drm/i915/selftests/igt_wedge_me.h b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
new file mode 100644
index 000000000000..08e5ff11bbd9
--- /dev/null
+++ b/drivers/gpu/drm/i915/selftests/igt_wedge_me.h
@@ -0,0 +1,58 @@
+/*
+ * SPDX-License-Identifier: MIT
+ *
+ * Copyright © 2018 Intel Corporation
+ */
+
+#ifndef IGT_WEDGE_ME_H
+#define IGT_WEDGE_ME_H
+
+#include <linux/workqueue.h>
+
+#include "../i915_gem.h"
+
+struct drm_i915_private;
+
+struct igt_wedge_me {
+	struct delayed_work work;
+	struct drm_i915_private *i915;
+	const char *name;
+};
+
+static void __igt_wedge_me(struct work_struct *work)
+{
+	struct igt_wedge_me *w = container_of(work, typeof(*w), work.work);
+
+	pr_err("%s timed out, cancelling test.\n", w->name);
+
+	GEM_TRACE("%s timed out.\n", w->name);
+	GEM_TRACE_DUMP();
+
+	i915_gem_set_wedged(w->i915);
+}
+
+static void __igt_init_wedge(struct igt_wedge_me *w,
+			     struct drm_i915_private *i915,
+			     long timeout,
+			     const char *name)
+{
+	w->i915 = i915;
+	w->name = name;
+
+	INIT_DELAYED_WORK_ONSTACK(&w->work, __igt_wedge_me);
+	schedule_delayed_work(&w->work, timeout);
+}
+
+static void __igt_fini_wedge(struct igt_wedge_me *w)
+{
+	cancel_delayed_work_sync(&w->work);
+	destroy_delayed_work_on_stack(&w->work);
+	w->i915 = NULL;
+}
+
+#define igt_wedge_on_timeout(W, DEV, TIMEOUT)				\
+	for (__igt_init_wedge((W), (DEV), (TIMEOUT), __func__);		\
+	     (W)->i915;							\
+	     __igt_fini_wedge((W)))
+
+#endif /* IGT_WEDGE_ME_H */
diff --git a/drivers/gpu/drm/i915/selftests/intel_workarounds.c b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
index fafdec3fe83e..0d39b3bf0c0d 100644
--- a/drivers/gpu/drm/i915/selftests/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/selftests/intel_workarounds.c
@@ -6,6 +6,7 @@
 
 #include "../i915_selftest.h"
 
+#include "igt_wedge_me.h"
 #include "mock_context.h"
 
 static struct drm_i915_gem_object *
@@ -111,6 +112,7 @@ static int check_whitelist(const struct whitelist *w,
 			   struct intel_engine_cs *engine)
 {
 	struct drm_i915_gem_object *results;
+	struct igt_wedge_me wedge;
 	u32 *vaddr;
 	int err;
 	int i;
@@ -119,7 +121,11 @@ static int check_whitelist(const struct whitelist *w,
 	if (IS_ERR(results))
 		return PTR_ERR(results);
 
-	err = i915_gem_object_set_to_cpu_domain(results, false);
+	err = 0;
+	igt_wedge_on_timeout(&wedge, ctx->i915, HZ / 5) /* a safety net! */
+		err = i915_gem_object_set_to_cpu_domain(results, false);
+	if (i915_terminally_wedged(&ctx->i915->gpu_error))
+		err = -EIO;
 	if (err)
 		goto out_put;
 
-- 
cgit v1.2.3


From 386c5680e2e80b012de557cf8326962070e0897b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 12:19:13 +0200
Subject: xfrm: use time64_t for in-kernel timestamps

The lifetime managment uses '__u64' timestamps on the user space
interface, but 'unsigned long' for reading the current time in the kernel
with get_seconds().

While this is probably safe beyond y2038, it will still overflow in 2106,
and the get_seconds() call is deprecated because fo that.

This changes the xfrm time handling to use time64_t consistently, along
with reading the time using the safer ktime_get_real_seconds(). It still
suffers from problems that can happen from a concurrent settimeofday()
call or (to a lesser degree) a leap second update, but since the time
stamps are part of the user API, there is nothing we can do to prevent
that.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 24 ++++++++++++------------
 net/xfrm/xfrm_state.c  | 10 +++++-----
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index ef75891450e7..5d2f734f4309 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -189,8 +189,8 @@ static inline unsigned long make_jiffies(long secs)
 static void xfrm_policy_timer(struct timer_list *t)
 {
 	struct xfrm_policy *xp = from_timer(xp, t, timer);
-	unsigned long now = get_seconds();
-	long next = LONG_MAX;
+	time64_t now = ktime_get_real_seconds();
+	time64_t next = TIME64_MAX;
 	int warn = 0;
 	int dir;
 
@@ -202,7 +202,7 @@ static void xfrm_policy_timer(struct timer_list *t)
 	dir = xfrm_policy_id2dir(xp->index);
 
 	if (xp->lft.hard_add_expires_seconds) {
-		long tmo = xp->lft.hard_add_expires_seconds +
+		time64_t tmo = xp->lft.hard_add_expires_seconds +
 			xp->curlft.add_time - now;
 		if (tmo <= 0)
 			goto expired;
@@ -210,7 +210,7 @@ static void xfrm_policy_timer(struct timer_list *t)
 			next = tmo;
 	}
 	if (xp->lft.hard_use_expires_seconds) {
-		long tmo = xp->lft.hard_use_expires_seconds +
+		time64_t tmo = xp->lft.hard_use_expires_seconds +
 			(xp->curlft.use_time ? : xp->curlft.add_time) - now;
 		if (tmo <= 0)
 			goto expired;
@@ -218,7 +218,7 @@ static void xfrm_policy_timer(struct timer_list *t)
 			next = tmo;
 	}
 	if (xp->lft.soft_add_expires_seconds) {
-		long tmo = xp->lft.soft_add_expires_seconds +
+		time64_t tmo = xp->lft.soft_add_expires_seconds +
 			xp->curlft.add_time - now;
 		if (tmo <= 0) {
 			warn = 1;
@@ -228,7 +228,7 @@ static void xfrm_policy_timer(struct timer_list *t)
 			next = tmo;
 	}
 	if (xp->lft.soft_use_expires_seconds) {
-		long tmo = xp->lft.soft_use_expires_seconds +
+		time64_t tmo = xp->lft.soft_use_expires_seconds +
 			(xp->curlft.use_time ? : xp->curlft.add_time) - now;
 		if (tmo <= 0) {
 			warn = 1;
@@ -240,7 +240,7 @@ static void xfrm_policy_timer(struct timer_list *t)
 
 	if (warn)
 		km_policy_expired(xp, dir, 0, 0);
-	if (next != LONG_MAX &&
+	if (next != TIME64_MAX &&
 	    !mod_timer(&xp->timer, jiffies + make_jiffies(next)))
 		xfrm_pol_hold(xp);
 
@@ -791,7 +791,7 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	}
 	policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index);
 	hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index));
-	policy->curlft.add_time = get_seconds();
+	policy->curlft.add_time = ktime_get_real_seconds();
 	policy->curlft.use_time = 0;
 	if (!mod_timer(&policy->timer, jiffies + HZ))
 		xfrm_pol_hold(policy);
@@ -1282,7 +1282,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol)
 	old_pol = rcu_dereference_protected(sk->sk_policy[dir],
 				lockdep_is_held(&net->xfrm.xfrm_policy_lock));
 	if (pol) {
-		pol->curlft.add_time = get_seconds();
+		pol->curlft.add_time = ktime_get_real_seconds();
 		pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0);
 		xfrm_sk_policy_link(pol, dir);
 	}
@@ -2132,7 +2132,7 @@ no_transform:
 	}
 
 	for (i = 0; i < num_pols; i++)
-		pols[i]->curlft.use_time = get_seconds();
+		pols[i]->curlft.use_time = ktime_get_real_seconds();
 
 	if (num_xfrms < 0) {
 		/* Prohibit the flow */
@@ -2352,7 +2352,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 		return 1;
 	}
 
-	pol->curlft.use_time = get_seconds();
+	pol->curlft.use_time = ktime_get_real_seconds();
 
 	pols[0] = pol;
 	npols++;
@@ -2366,7 +2366,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
 				return 0;
 			}
-			pols[1]->curlft.use_time = get_seconds();
+			pols[1]->curlft.use_time = ktime_get_real_seconds();
 			npols++;
 		}
 	}
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index c9ffcdfa89f6..27c84e63c7ff 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -475,8 +475,8 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 {
 	struct tasklet_hrtimer *thr = container_of(me, struct tasklet_hrtimer, timer);
 	struct xfrm_state *x = container_of(thr, struct xfrm_state, mtimer);
-	unsigned long now = get_seconds();
-	long next = LONG_MAX;
+	time64_t now = ktime_get_real_seconds();
+	time64_t next = TIME64_MAX;
 	int warn = 0;
 	int err = 0;
 
@@ -537,7 +537,7 @@ static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me)
 	if (warn)
 		km_state_expired(x, 0, 0);
 resched:
-	if (next != LONG_MAX) {
+	if (next != TIME64_MAX) {
 		tasklet_hrtimer_start(&x->mtimer, ktime_set(next, 0), HRTIMER_MODE_REL);
 	}
 
@@ -577,7 +577,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
 		tasklet_hrtimer_init(&x->mtimer, xfrm_timer_handler,
 					CLOCK_BOOTTIME, HRTIMER_MODE_ABS);
 		timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0);
-		x->curlft.add_time = get_seconds();
+		x->curlft.add_time = ktime_get_real_seconds();
 		x->lft.soft_byte_limit = XFRM_INF;
 		x->lft.soft_packet_limit = XFRM_INF;
 		x->lft.hard_byte_limit = XFRM_INF;
@@ -1588,7 +1588,7 @@ EXPORT_SYMBOL(xfrm_state_update);
 int xfrm_state_check_expire(struct xfrm_state *x)
 {
 	if (!x->curlft.use_time)
-		x->curlft.use_time = get_seconds();
+		x->curlft.use_time = ktime_get_real_seconds();
 
 	if (x->curlft.bytes >= x->lft.hard_byte_limit ||
 	    x->curlft.packets >= x->lft.hard_packet_limit) {
-- 
cgit v1.2.3


From 03dc7a35fcc83a199121a5156c4a7a976b836682 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 12:19:14 +0200
Subject: ipv6: xfrm: use 64-bit timestamps

get_seconds() is deprecated because it can overflow on 32-bit
architectures.  For the xfrm_state->lastused member, we treat the data
as a 64-bit number already, so we just need to use the right accessor
that works on both 32-bit and 64-bit machines.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/xfrm.h       | 2 +-
 net/ipv6/xfrm6_mode_ro.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index a5378613a49c..1350e2cf0749 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -227,7 +227,7 @@ struct xfrm_state {
 	long		saved_tmo;
 
 	/* Last used time */
-	unsigned long		lastused;
+	time64_t		lastused;
 
 	struct page_frag xfrag;
 
diff --git a/net/ipv6/xfrm6_mode_ro.c b/net/ipv6/xfrm6_mode_ro.c
index 07d36573f50b..da28e4407b8f 100644
--- a/net/ipv6/xfrm6_mode_ro.c
+++ b/net/ipv6/xfrm6_mode_ro.c
@@ -55,7 +55,7 @@ static int xfrm6_ro_output(struct xfrm_state *x, struct sk_buff *skb)
 	__skb_pull(skb, hdr_len);
 	memmove(ipv6_hdr(skb), iph, hdr_len);
 
-	x->lastused = get_seconds();
+	x->lastused = ktime_get_real_seconds();
 
 	return 0;
 }
-- 
cgit v1.2.3


From 655250a8d1aa3b18949a72869858d07ceac12799 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 29 Jun 2018 08:53:20 +0100
Subject: drm/i915/execlists: Switch to rb_root_cached

The kernel recently gained an augmented rbtree with the purpose of
cacheing the leftmost element of the rbtree, a frequent optimisation to
avoid calls to rb_first() which is also employed by the
execlists->queue. Switch from our open-coded cache to the library.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180629075348.27358-9-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c      |  7 +++----
 drivers/gpu/drm/i915/intel_guc_submission.c | 12 ++++-------
 drivers/gpu/drm/i915/intel_lrc.c            | 32 ++++++++++-------------------
 drivers/gpu/drm/i915/intel_ringbuffer.h     |  7 +------
 4 files changed, 19 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 0ac497275a51..220050107c48 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -467,8 +467,7 @@ static void intel_engine_init_execlist(struct intel_engine_cs *engine)
 	GEM_BUG_ON(execlists_num_ports(execlists) > EXECLIST_MAX_PORTS);
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 }
 
 /**
@@ -1004,7 +1003,7 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 	}
 
 	/* ELSP is empty, but there are ready requests? E.g. after reset */
-	if (READ_ONCE(engine->execlists.first))
+	if (!RB_EMPTY_ROOT(&engine->execlists.queue.rb_root))
 		return false;
 
 	/* Ring stopped? */
@@ -1540,7 +1539,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 	last = NULL;
 	count = 0;
 	drm_printf(m, "\t\tQueue priority: %d\n", execlists->queue_priority);
-	for (rb = execlists->first; rb; rb = rb_next(rb)) {
+	for (rb = rb_first_cached(&execlists->queue); rb; rb = rb_next(rb)) {
 		struct i915_priolist *p =
 			rb_entry(rb, typeof(*p), node);
 
diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index f3945258fe1b..3952656f4c9a 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -695,9 +695,6 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 
 	lockdep_assert_held(&engine->timeline.lock);
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (port_isset(port)) {
 		if (intel_engine_has_preemption(engine)) {
 			struct guc_preempt_work *preempt_work =
@@ -719,7 +716,7 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 	}
 	GEM_BUG_ON(port_isset(port));
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -744,15 +741,13 @@ static bool __guc_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
 	}
 done:
 	execlists->queue_priority = rb ? to_priolist(rb)->priority : INT_MIN;
-	execlists->first = rb;
 	if (submit)
 		port_assign(port, last);
 	if (last)
@@ -761,7 +756,8 @@ done:
 	/* We must always keep the beast fed if we have work piled up */
 	GEM_BUG_ON(port_isset(execlists->port) &&
 		   !execlists_is_active(execlists, EXECLISTS_ACTIVE_USER));
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	return submit;
 }
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index d937a21da2d8..ad436d200758 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -273,7 +273,7 @@ lookup_priolist(struct intel_engine_cs *engine, int prio)
 find_priolist:
 	/* most positive priority is scheduled first, equal priorities fifo */
 	rb = NULL;
-	parent = &execlists->queue.rb_node;
+	parent = &execlists->queue.rb_root.rb_node;
 	while (*parent) {
 		rb = *parent;
 		p = to_priolist(rb);
@@ -311,10 +311,7 @@ find_priolist:
 	p->priority = prio;
 	INIT_LIST_HEAD(&p->requests);
 	rb_link_node(&p->node, rb, parent);
-	rb_insert_color(&p->node, &execlists->queue);
-
-	if (first)
-		execlists->first = &p->node;
+	rb_insert_color_cached(&p->node, &execlists->queue, first);
 
 	return p;
 }
@@ -602,9 +599,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 	 * and context switches) submission.
 	 */
 
-	rb = execlists->first;
-	GEM_BUG_ON(rb_first(&execlists->queue) != rb);
-
 	if (last) {
 		/*
 		 * Don't resubmit or switch until all outstanding
@@ -666,7 +660,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 		last->tail = last->wa_tail;
 	}
 
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 		struct i915_request *rq, *rn;
 
@@ -725,8 +719,7 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
 			submit = true;
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -752,14 +745,14 @@ done:
 	execlists->queue_priority =
 		port != execlists->port ? rq_prio(last) : INT_MIN;
 
-	execlists->first = rb;
 	if (submit) {
 		port_assign(port, last);
 		execlists_submit_ports(engine);
 	}
 
 	/* We must always keep the beast fed if we have work piled up */
-	GEM_BUG_ON(execlists->first && !port_isset(execlists->port));
+	GEM_BUG_ON(rb_first_cached(&execlists->queue) &&
+		   !port_isset(execlists->port));
 
 	/* Re-evaluate the executing context setup after each preemptive kick */
 	if (last)
@@ -922,8 +915,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	}
 
 	/* Flush the queued requests to the timeline list (for retiring). */
-	rb = execlists->first;
-	while (rb) {
+	while ((rb = rb_first_cached(&execlists->queue))) {
 		struct i915_priolist *p = to_priolist(rb);
 
 		list_for_each_entry_safe(rq, rn, &p->requests, sched.link) {
@@ -933,8 +925,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 			__i915_request_submit(rq);
 		}
 
-		rb = rb_next(rb);
-		rb_erase(&p->node, &execlists->queue);
+		rb_erase_cached(&p->node, &execlists->queue);
 		INIT_LIST_HEAD(&p->requests);
 		if (p->priority != I915_PRIORITY_NORMAL)
 			kmem_cache_free(engine->i915->priorities, p);
@@ -943,8 +934,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	/* Remaining _unready_ requests will be nop'ed when submitted */
 
 	execlists->queue_priority = INT_MIN;
-	execlists->queue = RB_ROOT;
-	execlists->first = NULL;
+	execlists->queue = RB_ROOT_CACHED;
 	GEM_BUG_ON(port_isset(execlists->port));
 
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
@@ -1192,7 +1182,7 @@ static void execlists_submit_request(struct i915_request *request)
 
 	queue_request(engine, &request->sched, rq_prio(request));
 
-	GEM_BUG_ON(!engine->execlists.first);
+	GEM_BUG_ON(RB_EMPTY_ROOT(&engine->execlists.queue.rb_root));
 	GEM_BUG_ON(list_empty(&request->sched.link));
 
 	submit_queue(engine, rq_prio(request));
@@ -2044,7 +2034,7 @@ static void execlists_reset_finish(struct intel_engine_cs *engine)
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 
 	/* After a GPU reset, we may have requests to replay */
-	if (execlists->first)
+	if (!RB_EMPTY_ROOT(&execlists->queue.rb_root))
 		tasklet_schedule(&execlists->tasklet);
 
 	/*
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ce6cc2a6cf7a..d1eee08e5f6b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -292,12 +292,7 @@ struct intel_engine_execlists {
 	/**
 	 * @queue: queue of requests, in priority lists
 	 */
-	struct rb_root queue;
-
-	/**
-	 * @first: leftmost level in priority @queue
-	 */
-	struct rb_node *first;
+	struct rb_root_cached queue;
 
 	/**
 	 * @csb_read: control register for Context Switch buffer
-- 
cgit v1.2.3


From 2ba87a9bcc7a10aa28af9fbf5b4354b3168366e2 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 11 Jul 2018 13:18:59 +0000
Subject: spi: cadence: Fix missing clk_disable_unprepare() on error in
 cnds_runtime_resume()

Fix the missing clk_disable_unprepare() before return
from cnds_runtime_resume() in the error handling case.

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-cadence.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-cadence.c b/drivers/spi/spi-cadence.c
index a568f35522f9..7c88f74f7f47 100644
--- a/drivers/spi/spi-cadence.c
+++ b/drivers/spi/spi-cadence.c
@@ -739,7 +739,7 @@ static int __maybe_unused cnds_runtime_resume(struct device *dev)
 	ret = clk_prepare_enable(xspi->ref_clk);
 	if (ret) {
 		dev_err(dev, "Cannot enable device clock.\n");
-		clk_disable(xspi->pclk);
+		clk_disable_unprepare(xspi->pclk);
 		return ret;
 	}
 	return 0;
-- 
cgit v1.2.3


From a284390b397ae2f95de799bc591efbfe54bf0907 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Wed, 11 Jul 2018 10:34:42 -0400
Subject: blk-iolatency: fix max_depth comparisons

max_depth used to be a u64, but I changed it to a unsigned int but
didn't convert my comparisons over everywhere.  Fix by using UINT_MAX
everywhere instead of (u64)-1.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iolatency.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 56ddb2c68752..b59e5451680b 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -9,8 +9,8 @@
  * - We use the mean latency over the 100ms window.  This is because writes can
  *   be particularly fast, which could give us a false sense of the impact of
  *   other workloads on our protected workload.
- * - By default there's no throttling, we set the queue_depth to INT_MAX so that
- *   we can have as many outstanding bio's as we're allowed to.  Only at
+ * - By default there's no throttling, we set the queue_depth to UINT_MAX so
+ *   that we can have as many outstanding bio's as we're allowed to.  Only at
  *   throttle time do we pay attention to the actual queue depth.
  *
  * The hierarchy works like the cpu controller does, we track the latency at
@@ -361,7 +361,7 @@ static void check_scale_change(struct iolatency_grp *iolat)
 	/* We're back to the default cookie, unthrottle all the things. */
 	if (cur_cookie == DEFAULT_SCALE_COOKIE) {
 		blkcg_clear_delay(lat_to_blkg(iolat));
-		iolat->rq_depth.max_depth = INT_MAX;
+		iolat->rq_depth.max_depth = UINT_MAX;
 		wake_up_all(&iolat->rq_wait.wait);
 		return;
 	}
@@ -434,7 +434,7 @@ static void iolatency_record_time(struct iolatency_grp *iolat,
 	 * We don't want to count issue_as_root bio's in the cgroups latency
 	 * statistics as it could skew the numbers downwards.
 	 */
-	if (unlikely(issue_as_root && iolat->rq_depth.max_depth != (u64)-1)) {
+	if (unlikely(issue_as_root && iolat->rq_depth.max_depth != UINT_MAX)) {
 		u64 sub = iolat->min_lat_nsec;
 		if (req_time < sub)
 			blkcg_add_delay(lat_to_blkg(iolat), now, sub - req_time);
@@ -816,7 +816,7 @@ static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
 	struct iolatency_grp *iolat = pd_to_lat(pd);
 	unsigned long long avg_lat = div64_u64(iolat->total_lat_avg, NSEC_PER_USEC);
 
-	if (iolat->rq_depth.max_depth == (u64)-1)
+	if (iolat->rq_depth.max_depth == UINT_MAX)
 		return scnprintf(buf, size, " depth=max avg_lat=%llu",
 				 avg_lat);
 
@@ -859,7 +859,7 @@ static void iolatency_pd_init(struct blkg_policy_data *pd)
 	rq_wait_init(&iolat->rq_wait);
 	spin_lock_init(&iolat->child_lat.lock);
 	iolat->rq_depth.queue_depth = blk_queue_depth(blkg->q);
-	iolat->rq_depth.max_depth = INT_MAX;
+	iolat->rq_depth.max_depth = UINT_MAX;
 	iolat->rq_depth.default_depth = iolat->rq_depth.queue_depth;
 	iolat->blkiolat = blkiolat;
 	iolat->cur_win_nsec = 100 * NSEC_PER_MSEC;
-- 
cgit v1.2.3


From 03e3ec9ad1ee484f872bad6d673d46c9742e71ef Mon Sep 17 00:00:00 2001
From: Vladimir Zapolskiy <vz@mleia.com>
Date: Fri, 6 Jul 2018 21:51:01 +0300
Subject: drm/panel: simple: Add Sharp LQ035Q7DB03 panel support

The change adds support for Sharp LQ035Q7DB03 3.5" QVGA TFT panel.

Note that this aged panel is already found in the kernel sources,
for instance in board mach files mach-mx21ads.c, mach-mx27ads.c,
mach-pcm043.c, lpd270.c and imx27-phytec-phycore-rdk.dts.

Signed-off-by: Vladimir Zapolskiy <vz@mleia.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Thierry Reding <treding@nvidia.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706185101.31186-1-vz@mleia.com
---
 .../bindings/display/panel/sharp,lq035q7db03.txt   | 12 ++++++++++
 drivers/gpu/drm/panel/panel-simple.c               | 27 ++++++++++++++++++++++
 2 files changed, 39 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/panel/sharp,lq035q7db03.txt

diff --git a/Documentation/devicetree/bindings/display/panel/sharp,lq035q7db03.txt b/Documentation/devicetree/bindings/display/panel/sharp,lq035q7db03.txt
new file mode 100644
index 000000000000..0753f6967279
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/panel/sharp,lq035q7db03.txt
@@ -0,0 +1,12 @@
+Sharp LQ035Q7DB03 3.5" QVGA TFT LCD panel
+
+Required properties:
+- compatible: should be "sharp,lq035q7db03"
+- power-supply: phandle of the regulator that provides the supply voltage
+
+Optional properties:
+- enable-gpios: GPIO pin to enable or disable the panel
+- backlight: phandle of the backlight device attached to the panel
+
+This binding is compatible with the simple-panel binding, which is specified
+in simple-panel.txt in this directory.
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 3b226ad8acad..86fec03dd260 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -1991,6 +1991,30 @@ static const struct panel_desc samsung_ltn140at29_301 = {
 	},
 };
 
+static const struct drm_display_mode sharp_lq035q7db03_mode = {
+	.clock = 5500,
+	.hdisplay = 240,
+	.hsync_start = 240 + 16,
+	.hsync_end = 240 + 16 + 7,
+	.htotal = 240 + 16 + 7 + 5,
+	.vdisplay = 320,
+	.vsync_start = 320 + 9,
+	.vsync_end = 320 + 9 + 1,
+	.vtotal = 320 + 9 + 1 + 7,
+	.vrefresh = 60,
+};
+
+static const struct panel_desc sharp_lq035q7db03 = {
+	.modes = &sharp_lq035q7db03_mode,
+	.num_modes = 1,
+	.bpc = 6,
+	.size = {
+		.width = 54,
+		.height = 72,
+	},
+	.bus_format = MEDIA_BUS_FMT_RGB666_1X18,
+};
+
 static const struct display_timing sharp_lq101k1ly04_timing = {
 	.pixelclock = { 60000000, 65000000, 80000000 },
 	.hactive = { 1280, 1280, 1280 },
@@ -2492,6 +2516,9 @@ static const struct of_device_id platform_of_match[] = {
 	}, {
 		.compatible = "samsung,ltn140at29-301",
 		.data = &samsung_ltn140at29_301,
+	}, {
+		.compatible = "sharp,lq035q7db03",
+		.data = &sharp_lq035q7db03,
 	}, {
 		.compatible = "sharp,lq101k1ly04",
 		.data = &sharp_lq101k1ly04,
-- 
cgit v1.2.3


From 7479efc71f6da5fde6c67d91380ebc0fb455c53d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:42:55 -0700
Subject: selftests/bpf: remove duplicated word from test offloads

Trivial removal of duplicated "mode" in error message.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_offload.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index be800d0e7a84..a257e4b08392 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -830,7 +830,7 @@ try:
     check_extack_nsim(err, "program loaded with different flags.", args)
     ret, _, err = sim.unset_xdp("", force=True,
                                 fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode mode")
+    fail(ret == 0, "Removed program with a bad mode")
     check_extack_nsim(err, "program loaded with different flags.", args)
 
     start_test("Test MTU restrictions...")
-- 
cgit v1.2.3


From 219f860d2a11b285ac2e880ca4a73e0d36811c0c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:42:56 -0700
Subject: selftests/bpf: add Error: prefix in check_extack helper

Currently the test only checks errors, not warnings, so save typing
and prefix the extack messages with "Error:" inside the check helper.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_offload.py | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index a257e4b08392..f8d9bd81d9a4 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -547,11 +547,11 @@ def check_extack(output, reference, args):
     if skip_extack:
         return
     lines = output.split("\n")
-    comp = len(lines) >= 2 and lines[1] == reference
+    comp = len(lines) >= 2 and lines[1] == 'Error: ' + reference
     fail(not comp, "Missing or incorrect netlink extack message")
 
 def check_extack_nsim(output, reference, args):
-    check_extack(output, "Error: netdevsim: " + reference, args)
+    check_extack(output, "netdevsim: " + reference, args)
 
 def check_no_extack(res, needle):
     fail((res[1] + res[2]).count(needle) or (res[1] + res[2]).count("Warning:"),
@@ -654,7 +654,7 @@ try:
     ret, _, err = sim.cls_bpf_add_filter(obj, skip_sw=True,
                                          fail=False, include_stderr=True)
     fail(ret == 0, "TC filter loaded without enabling TC offloads")
-    check_extack(err, "Error: TC offload is disabled on net device.", args)
+    check_extack(err, "TC offload is disabled on net device.", args)
     sim.wait_for_flush()
 
     sim.set_ethtool_tc_offloads(True)
@@ -694,7 +694,7 @@ try:
                                          skip_sw=True,
                                          fail=False, include_stderr=True)
     fail(ret == 0, "Offloaded a filter to chain other than 0")
-    check_extack(err, "Error: Driver supports only offload of chain 0.", args)
+    check_extack(err, "Driver supports only offload of chain 0.", args)
     sim.tc_flush_filters()
 
     start_test("Test TC replace...")
-- 
cgit v1.2.3


From 8d1fc3de3d9f9bda0d8ec719d8686e9c5b432573 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:42:57 -0700
Subject: tools: bpftool: refactor argument parsing for prog load

Add a new macro for printing more informative message than straight
usage() when parameters are missing, and use it for prog do_load().
Save the object and pin path argument to variables for clarity.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/main.h | 15 +++++++++++++++
 tools/bpf/bpftool/prog.c | 11 +++++++----
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index d39f7ef01d23..15b6c49ae533 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -50,6 +50,21 @@
 #define NEXT_ARG()	({ argc--; argv++; if (argc < 0) usage(); })
 #define NEXT_ARGP()	({ (*argc)--; (*argv)++; if (*argc < 0) usage(); })
 #define BAD_ARG()	({ p_err("what is '%s'?", *argv); -1; })
+#define GET_ARG()	({ argc--; *argv++; })
+#define REQ_ARGS(cnt)							\
+	({								\
+		int _cnt = (cnt);					\
+		bool _res;						\
+									\
+		if (argc < _cnt) {					\
+			p_err("'%s' needs at least %d arguments, %d found", \
+			      argv[-1], _cnt, argc);			\
+			_res = false;					\
+		} else {						\
+			_res = true;					\
+		}							\
+		_res;							\
+	})
 
 #define ERR_MAX_LEN	1024
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a740da99d477..a5ef46c59029 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -681,18 +681,21 @@ static int do_pin(int argc, char **argv)
 
 static int do_load(int argc, char **argv)
 {
+	const char *objfile, *pinfile;
 	struct bpf_object *obj;
 	int prog_fd;
 
-	if (argc != 2)
-		usage();
+	if (!REQ_ARGS(2))
+		return -1;
+	objfile = GET_ARG();
+	pinfile = GET_ARG();
 
-	if (bpf_prog_load(argv[0], BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
+	if (bpf_prog_load(objfile, BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
 		p_err("failed to load program");
 		return -1;
 	}
 
-	if (do_pin_fd(prog_fd, argv[1]))
+	if (do_pin_fd(prog_fd, pinfile))
 		goto err_close_obj;
 
 	if (json_output)
-- 
cgit v1.2.3


From ba6dd679a3e81af023ec091c2fb7c82003a27316 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:42:58 -0700
Subject: tools: bpftool: add support for loading programs for offload

Extend the bpftool prog load command to also accept "dev"
parameter, which will allow us to load programs onto devices.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  6 ++--
 tools/bpf/bpftool/bash-completion/bpftool        | 23 ++++++++++++++--
 tools/bpf/bpftool/prog.c                         | 35 ++++++++++++++++++++++--
 3 files changed, 58 insertions(+), 6 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 43d34a5c3ec5..41723c6acaa6 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,7 +24,7 @@ MAP COMMANDS
 |	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
-|	**bpftool** **prog load** *OBJ* *FILE*
+|	**bpftool** **prog load** *OBJ* *FILE* [**dev** *NAME*]
 |	**bpftool** **prog help**
 |
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
@@ -64,8 +64,10 @@ DESCRIPTION
 
 		  Note: *FILE* must be located in *bpffs* mount.
 
-	**bpftool prog load** *OBJ* *FILE*
+	**bpftool prog load** *OBJ* *FILE* [**dev** *NAME*]
 		  Load bpf program from binary *OBJ* and pin as *FILE*.
+		  If **dev** *NAME* is specified program will be loaded onto
+		  given networking device (offload).
 
 		  Note: *FILE* must be located in *bpffs* mount.
 
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index ce0bc0cda361..238c2f80092a 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -99,6 +99,12 @@ _bpftool_get_prog_tags()
         command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
 }
 
+_sysfs_get_netdevs()
+{
+    COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \
+        "$cur" ) )
+}
+
 # For bpftool map update: retrieve type of the map to update.
 _bpftool_map_update_map_type()
 {
@@ -262,8 +268,21 @@ _bpftool()
                     return 0
                     ;;
                 load)
-                    _filedir
-                    return 0
+                    if [[ ${#words[@]} -lt 6 ]]; then
+                        _filedir
+                        return 0
+                    fi
+
+                    case $prev in
+                        dev)
+                            _sysfs_get_netdevs
+                            return 0
+                            ;;
+                        *)
+                            _bpftool_once_attr 'dev'
+                            return 0
+                            ;;
+                    esac
                     ;;
                 *)
                     [[ $prev == $object ]] && \
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index a5ef46c59029..21c74de7156f 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -39,6 +39,7 @@
 #include <string.h>
 #include <time.h>
 #include <unistd.h>
+#include <net/if.h>
 #include <sys/types.h>
 #include <sys/stat.h>
 
@@ -681,6 +682,9 @@ static int do_pin(int argc, char **argv)
 
 static int do_load(int argc, char **argv)
 {
+	struct bpf_prog_load_attr attr = {
+		.prog_type	= BPF_PROG_TYPE_UNSPEC,
+	};
 	const char *objfile, *pinfile;
 	struct bpf_object *obj;
 	int prog_fd;
@@ -690,7 +694,34 @@ static int do_load(int argc, char **argv)
 	objfile = GET_ARG();
 	pinfile = GET_ARG();
 
-	if (bpf_prog_load(objfile, BPF_PROG_TYPE_UNSPEC, &obj, &prog_fd)) {
+	while (argc) {
+		if (is_prefix(*argv, "dev")) {
+			NEXT_ARG();
+
+			if (attr.ifindex) {
+				p_err("offload device already specified");
+				return -1;
+			}
+			if (!REQ_ARGS(1))
+				return -1;
+
+			attr.ifindex = if_nametoindex(*argv);
+			if (!attr.ifindex) {
+				p_err("unrecognized netdevice '%s': %s",
+				      *argv, strerror(errno));
+				return -1;
+			}
+			NEXT_ARG();
+		} else {
+			p_err("expected no more arguments or 'dev', got: '%s'?",
+			      *argv);
+			return -1;
+		}
+	}
+
+	attr.file = objfile;
+
+	if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) {
 		p_err("failed to load program");
 		return -1;
 	}
@@ -722,7 +753,7 @@ static int do_help(int argc, char **argv)
 		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
 		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
-		"       %s %s load  OBJ  FILE\n"
+		"       %s %s load  OBJ  FILE [dev NAME]\n"
 		"       %s %s help\n"
 		"\n"
 		"       " HELP_SPEC_PROGRAM "\n"
-- 
cgit v1.2.3


From b60df2a0e11fcd24186c312b0307ab8494031e27 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:42:59 -0700
Subject: tools: libbpf: expose the prog type guessing from section name logic

libbpf can guess program type based on ELF section names.  As libbpf
becomes more popular its association between section name strings and
types becomes more of a standard.  Allow libbpf users to use the same
logic for matching strings to types, e.g. when the string originates
from command line.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 43 +++++++++++++++++++++++++------------------
 tools/lib/bpf/libbpf.h |  3 +++
 2 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 38ed3e92e393..42f31eff5f3f 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2081,23 +2081,31 @@ static const struct {
 #undef BPF_S_PROG_SEC
 #undef BPF_SA_PROG_SEC
 
-static int bpf_program__identify_section(struct bpf_program *prog)
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+			     enum bpf_attach_type *expected_attach_type)
 {
 	int i;
 
-	if (!prog->section_name)
-		goto err;
-
-	for (i = 0; i < ARRAY_SIZE(section_names); i++)
-		if (strncmp(prog->section_name, section_names[i].sec,
-			    section_names[i].len) == 0)
-			return i;
+	if (!name)
+		return -EINVAL;
 
-err:
-	pr_warning("failed to guess program type based on section name %s\n",
-		   prog->section_name);
+	for (i = 0; i < ARRAY_SIZE(section_names); i++) {
+		if (strncmp(name, section_names[i].sec, section_names[i].len))
+			continue;
+		*prog_type = section_names[i].prog_type;
+		*expected_attach_type = section_names[i].expected_attach_type;
+		return 0;
+	}
+	return -EINVAL;
+}
 
-	return -1;
+static int
+bpf_program__identify_section(struct bpf_program *prog,
+			      enum bpf_prog_type *prog_type,
+			      enum bpf_attach_type *expected_attach_type)
+{
+	return libbpf_prog_type_by_name(prog->section_name, prog_type,
+					expected_attach_type);
 }
 
 int bpf_map__fd(struct bpf_map *map)
@@ -2230,7 +2238,6 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	enum bpf_prog_type prog_type;
 	struct bpf_object *obj;
 	struct bpf_map *map;
-	int section_idx;
 	int err;
 
 	if (!attr)
@@ -2252,14 +2259,14 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 		prog->prog_ifindex = attr->ifindex;
 		expected_attach_type = attr->expected_attach_type;
 		if (prog_type == BPF_PROG_TYPE_UNSPEC) {
-			section_idx = bpf_program__identify_section(prog);
-			if (section_idx < 0) {
+			err = bpf_program__identify_section(prog, &prog_type,
+							    &expected_attach_type);
+			if (err < 0) {
+				pr_warning("failed to guess program type based on section name %s\n",
+					   prog->section_name);
 				bpf_object__close(obj);
 				return -EINVAL;
 			}
-			prog_type = section_names[section_idx].prog_type;
-			expected_attach_type =
-				section_names[section_idx].expected_attach_type;
 		}
 
 		bpf_program__set_type(prog, prog_type);
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 564f4be9bae0..d1ce5c828e2e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -92,6 +92,9 @@ int bpf_object__set_priv(struct bpf_object *obj, void *priv,
 			 bpf_object_clear_priv_t clear_priv);
 void *bpf_object__priv(struct bpf_object *prog);
 
+int libbpf_prog_type_by_name(const char *name, enum bpf_prog_type *prog_type,
+			     enum bpf_attach_type *expected_attach_type);
+
 /* Accessors of bpf_program */
 struct bpf_program;
 struct bpf_program *bpf_program__next(struct bpf_program *prog,
-- 
cgit v1.2.3


From 49f2cba3e57a4d71e3e7001cc2934b563ee495f4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:00 -0700
Subject: tools: bpftool: allow users to specify program type for prog load

Sometimes program section names don't match with libbpf's expectation.
In particular XDP's default section names differ between libbpf and
iproute2.  Allow users to pass program type on command line.  Name
the types like the libbpf expected section names.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst | 15 ++++++--
 tools/bpf/bpftool/bash-completion/bpftool        |  6 ++++
 tools/bpf/bpftool/prog.c                         | 44 ++++++++++++++++++++++--
 3 files changed, 60 insertions(+), 5 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index 41723c6acaa6..e53e1ad2caf0 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,10 +24,19 @@ MAP COMMANDS
 |	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
-|	**bpftool** **prog load** *OBJ* *FILE* [**dev** *NAME*]
+|	**bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
 |	**bpftool** **prog help**
 |
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
+|	*TYPE* := {
+|		**socket** | **kprobe** | **kretprobe** | **classifier** | **action** |
+|		**tracepoint** | **raw_tracepoint** | **xdp** | **perf_event** | **cgroup/skb** |
+|		**cgroup/sock** | **cgroup/dev** | **lwt_in** | **lwt_out** | **lwt_xmit** |
+|		**lwt_seg6local** | **sockops** | **sk_skb** | **sk_msg** | **lirc_mode2** |
+|		**cgroup/bind4** | **cgroup/bind6** | **cgroup/post_bind4** | **cgroup/post_bind6** |
+|		**cgroup/connect4** | **cgroup/connect6** | **cgroup/sendmsg4** | **cgroup/sendmsg6**
+|	}
+
 
 DESCRIPTION
 ===========
@@ -64,8 +73,10 @@ DESCRIPTION
 
 		  Note: *FILE* must be located in *bpffs* mount.
 
-	**bpftool prog load** *OBJ* *FILE* [**dev** *NAME*]
+	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
 		  Load bpf program from binary *OBJ* and pin as *FILE*.
+		  **type** is optional, if not specified program type will be
+		  inferred from section names.
 		  If **dev** *NAME* is specified program will be loaded onto
 		  given networking device (offload).
 
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index 238c2f80092a..caf8711993be 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -274,11 +274,17 @@ _bpftool()
                     fi
 
                     case $prev in
+                        type)
+                            COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
+                                                   "$cur" ) )
+                            return 0
+                            ;;
                         dev)
                             _sysfs_get_netdevs
                             return 0
                             ;;
                         *)
+                            _bpftool_once_attr 'type'
                             _bpftool_once_attr 'dev'
                             return 0
                             ;;
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 21c74de7156f..98695585bbb6 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -688,6 +688,7 @@ static int do_load(int argc, char **argv)
 	const char *objfile, *pinfile;
 	struct bpf_object *obj;
 	int prog_fd;
+	int err;
 
 	if (!REQ_ARGS(2))
 		return -1;
@@ -695,7 +696,37 @@ static int do_load(int argc, char **argv)
 	pinfile = GET_ARG();
 
 	while (argc) {
-		if (is_prefix(*argv, "dev")) {
+		if (is_prefix(*argv, "type")) {
+			char *type;
+
+			NEXT_ARG();
+
+			if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
+				p_err("program type already specified");
+				return -1;
+			}
+			if (!REQ_ARGS(1))
+				return -1;
+
+			/* Put a '/' at the end of type to appease libbpf */
+			type = malloc(strlen(*argv) + 2);
+			if (!type) {
+				p_err("mem alloc failed");
+				return -1;
+			}
+			*type = 0;
+			strcat(type, *argv);
+			strcat(type, "/");
+
+			err = libbpf_prog_type_by_name(type, &attr.prog_type,
+						       &attr.expected_attach_type);
+			free(type);
+			if (err < 0) {
+				p_err("unknown program type '%s'", *argv);
+				return err;
+			}
+			NEXT_ARG();
+		} else if (is_prefix(*argv, "dev")) {
 			NEXT_ARG();
 
 			if (attr.ifindex) {
@@ -713,7 +744,7 @@ static int do_load(int argc, char **argv)
 			}
 			NEXT_ARG();
 		} else {
-			p_err("expected no more arguments or 'dev', got: '%s'?",
+			p_err("expected no more arguments, 'type' or 'dev', got: '%s'?",
 			      *argv);
 			return -1;
 		}
@@ -753,10 +784,17 @@ static int do_help(int argc, char **argv)
 		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
 		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
-		"       %s %s load  OBJ  FILE [dev NAME]\n"
+		"       %s %s load  OBJ  FILE [type TYPE] [dev NAME]\n"
 		"       %s %s help\n"
 		"\n"
 		"       " HELP_SPEC_PROGRAM "\n"
+		"       TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
+		"                 tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
+		"                 cgroup/sock | cgroup/dev | lwt_in | lwt_out | lwt_xmit |\n"
+		"                 lwt_seg6local | sockops | sk_skb | sk_msg | lirc_mode2 |\n"
+		"                 cgroup/bind4 | cgroup/bind6 | cgroup/post_bind4 |\n"
+		"                 cgroup/post_bind6 | cgroup/connect4 | cgroup/connect6 |\n"
+		"                 cgroup/sendmsg4 | cgroup/sendmsg6 }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2],
-- 
cgit v1.2.3


From f83fb22c6c68fdbc98c76291c9e12a40d1eb7ca5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:01 -0700
Subject: tools: libbpf: recognize offload neutral maps

Add helper to libbpf for recognizing maps which should not have
ifindex set when program is loaded.  These maps only contain
host metadata and therefore are not marked for offload, e.g.
the perf event map.

Use this helper in bpf_prog_load_xattr().

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 8 +++++++-
 tools/lib/bpf/libbpf.h | 1 +
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 42f31eff5f3f..30992305f4c1 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -2154,6 +2154,11 @@ void *bpf_map__priv(struct bpf_map *map)
 	return map ? map->priv : ERR_PTR(-EINVAL);
 }
 
+bool bpf_map__is_offload_neutral(struct bpf_map *map)
+{
+	return map->def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
+}
+
 void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex)
 {
 	map->map_ifindex = ifindex;
@@ -2278,7 +2283,8 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	}
 
 	bpf_map__for_each(map, obj) {
-		map->map_ifindex = attr->ifindex;
+		if (!bpf_map__is_offload_neutral(map))
+			map->map_ifindex = attr->ifindex;
 	}
 
 	if (!first_prog) {
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index d1ce5c828e2e..749acf58a5da 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -255,6 +255,7 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		      bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
+bool bpf_map__is_offload_neutral(struct bpf_map *map);
 void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 int bpf_map__pin(struct bpf_map *map, const char *path);
 
-- 
cgit v1.2.3


From 07f2d4eac2a850fc9649b27aa935cdcd263fb1ff Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:02 -0700
Subject: tools: libbpf: add extended attributes version of bpf_object__open()

Similarly to bpf_prog_load() users of bpf_object__open() may need
to specify the expected program type.  Program type is needed at
open to avoid the kernel version check for program types which don't
require it.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 26 ++++++++++++++++++++------
 tools/lib/bpf/libbpf.h |  6 ++++++
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 30992305f4c1..06cd534d2fba 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1520,15 +1520,26 @@ out:
 	return ERR_PTR(err);
 }
 
-struct bpf_object *bpf_object__open(const char *path)
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr)
 {
 	/* param validation */
-	if (!path)
+	if (!attr->file)
 		return NULL;
 
-	pr_debug("loading %s\n", path);
+	pr_debug("loading %s\n", attr->file);
+
+	return __bpf_object__open(attr->file, NULL, 0,
+				  bpf_prog_type__needs_kver(attr->prog_type));
+}
+
+struct bpf_object *bpf_object__open(const char *path)
+{
+	struct bpf_object_open_attr attr = {
+		.file		= path,
+		.prog_type	= BPF_PROG_TYPE_UNSPEC,
+	};
 
-	return __bpf_object__open(path, NULL, 0, true);
+	return bpf_object__open_xattr(&attr);
 }
 
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
@@ -2238,6 +2249,10 @@ int bpf_prog_load(const char *file, enum bpf_prog_type type,
 int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 			struct bpf_object **pobj, int *prog_fd)
 {
+	struct bpf_object_open_attr open_attr = {
+		.file		= attr->file,
+		.prog_type	= attr->prog_type,
+	};
 	struct bpf_program *prog, *first_prog = NULL;
 	enum bpf_attach_type expected_attach_type;
 	enum bpf_prog_type prog_type;
@@ -2250,8 +2265,7 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr *attr,
 	if (!attr->file)
 		return -EINVAL;
 
-	obj = __bpf_object__open(attr->file, NULL, 0,
-				 bpf_prog_type__needs_kver(attr->prog_type));
+	obj = bpf_object__open_xattr(&open_attr);
 	if (IS_ERR_OR_NULL(obj))
 		return -ENOENT;
 
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 749acf58a5da..e911ad32d02e 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -66,7 +66,13 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 /* Hide internal to user */
 struct bpf_object;
 
+struct bpf_object_open_attr {
+	const char *file;
+	enum bpf_prog_type prog_type;
+};
+
 struct bpf_object *bpf_object__open(const char *path);
+struct bpf_object *bpf_object__open_xattr(struct bpf_object_open_attr *attr);
 struct bpf_object *bpf_object__open_buffer(void *obj_buf,
 					   size_t obj_buf_sz,
 					   const char *name);
-- 
cgit v1.2.3


From c8406848badd0a0b040b0d286e612678662a2ab3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:03 -0700
Subject: tools: bpftool: reimplement bpf_prog_load() for prog load

bpf_prog_load() is a very useful helper but it doesn't give us full
flexibility of modifying the BPF objects before loading.  Open code
bpf_prog_load() in bpftool so we can add extra logic in following
commits.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/prog.c | 61 +++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 48 insertions(+), 13 deletions(-)

diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 98695585bbb6..2bdd5ecd1aad 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -43,6 +43,8 @@
 #include <sys/types.h>
 #include <sys/stat.h>
 
+#include <linux/err.h>
+
 #include <bpf.h>
 #include <libbpf.h>
 
@@ -682,17 +684,20 @@ static int do_pin(int argc, char **argv)
 
 static int do_load(int argc, char **argv)
 {
-	struct bpf_prog_load_attr attr = {
+	enum bpf_attach_type expected_attach_type;
+	struct bpf_object_open_attr attr = {
 		.prog_type	= BPF_PROG_TYPE_UNSPEC,
 	};
-	const char *objfile, *pinfile;
+	struct bpf_program *prog;
 	struct bpf_object *obj;
-	int prog_fd;
+	struct bpf_map *map;
+	const char *pinfile;
+	__u32 ifindex = 0;
 	int err;
 
 	if (!REQ_ARGS(2))
 		return -1;
-	objfile = GET_ARG();
+	attr.file = GET_ARG();
 	pinfile = GET_ARG();
 
 	while (argc) {
@@ -719,7 +724,7 @@ static int do_load(int argc, char **argv)
 			strcat(type, "/");
 
 			err = libbpf_prog_type_by_name(type, &attr.prog_type,
-						       &attr.expected_attach_type);
+						       &expected_attach_type);
 			free(type);
 			if (err < 0) {
 				p_err("unknown program type '%s'", *argv);
@@ -729,15 +734,15 @@ static int do_load(int argc, char **argv)
 		} else if (is_prefix(*argv, "dev")) {
 			NEXT_ARG();
 
-			if (attr.ifindex) {
+			if (ifindex) {
 				p_err("offload device already specified");
 				return -1;
 			}
 			if (!REQ_ARGS(1))
 				return -1;
 
-			attr.ifindex = if_nametoindex(*argv);
-			if (!attr.ifindex) {
+			ifindex = if_nametoindex(*argv);
+			if (!ifindex) {
 				p_err("unrecognized netdevice '%s': %s",
 				      *argv, strerror(errno));
 				return -1;
@@ -750,14 +755,44 @@ static int do_load(int argc, char **argv)
 		}
 	}
 
-	attr.file = objfile;
-
-	if (bpf_prog_load_xattr(&attr, &obj, &prog_fd)) {
-		p_err("failed to load program");
+	obj = bpf_object__open_xattr(&attr);
+	if (IS_ERR_OR_NULL(obj)) {
+		p_err("failed to open object file");
 		return -1;
 	}
 
-	if (do_pin_fd(prog_fd, pinfile))
+	prog = bpf_program__next(NULL, obj);
+	if (!prog) {
+		p_err("object file doesn't contain any bpf program");
+		goto err_close_obj;
+	}
+
+	bpf_program__set_ifindex(prog, ifindex);
+	if (attr.prog_type == BPF_PROG_TYPE_UNSPEC) {
+		const char *sec_name = bpf_program__title(prog, false);
+
+		err = libbpf_prog_type_by_name(sec_name, &attr.prog_type,
+					       &expected_attach_type);
+		if (err < 0) {
+			p_err("failed to guess program type based on section name %s\n",
+			      sec_name);
+			goto err_close_obj;
+		}
+	}
+	bpf_program__set_type(prog, attr.prog_type);
+	bpf_program__set_expected_attach_type(prog, expected_attach_type);
+
+	bpf_map__for_each(map, obj)
+		if (!bpf_map__is_offload_neutral(map))
+			bpf_map__set_ifindex(map, ifindex);
+
+	err = bpf_object__load(obj);
+	if (err) {
+		p_err("failed to load object file");
+		goto err_close_obj;
+	}
+
+	if (do_pin_fd(bpf_program__fd(prog), pinfile))
 		goto err_close_obj;
 
 	if (json_output)
-- 
cgit v1.2.3


From 8d13406c02f9c38f106416e1dbe0e68059b9f59a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:04 -0700
Subject: tools: libbpf: move library error code into a separate file

libbpf_strerror() depends on XSI-compliant (POSIX) version of
strerror_r(), which prevents us from using GNU-extensions in
libbpf.c, like reallocarray() or dup3().  Move error printing
code into a separate file to allow it to continue using POSIX
strerror_r().

No functional changes.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/Build          |  2 +-
 tools/lib/bpf/libbpf.c       | 48 ----------------------------
 tools/lib/bpf/libbpf_errno.c | 74 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 75 insertions(+), 49 deletions(-)
 create mode 100644 tools/lib/bpf/libbpf_errno.c

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 6070e655042d..13a861135127 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 06cd534d2fba..f732237610e5 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -95,54 +95,6 @@ void libbpf_set_print(libbpf_print_fn_t warn,
 
 #define STRERR_BUFSIZE  128
 
-#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
-#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
-#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
-
-static const char *libbpf_strerror_table[NR_ERRNO] = {
-	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
-	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
-	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
-	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
-	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
-	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
-	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
-	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
-	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
-	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
-	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
-	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
-};
-
-int libbpf_strerror(int err, char *buf, size_t size)
-{
-	if (!buf || !size)
-		return -1;
-
-	err = err > 0 ? err : -err;
-
-	if (err < __LIBBPF_ERRNO__START) {
-		int ret;
-
-		ret = strerror_r(err, buf, size);
-		buf[size - 1] = '\0';
-		return ret;
-	}
-
-	if (err < __LIBBPF_ERRNO__END) {
-		const char *msg;
-
-		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
-		snprintf(buf, size, "%s", msg);
-		buf[size - 1] = '\0';
-		return 0;
-	}
-
-	snprintf(buf, size, "Unknown libbpf error %d", err);
-	buf[size - 1] = '\0';
-	return -1;
-}
-
 #define CHECK_ERR(action, err, out) do {	\
 	err = action;			\
 	if (err)			\
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
new file mode 100644
index 000000000000..d9ba851bd7f9
--- /dev/null
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: LGPL-2.1
+
+/*
+ * Copyright (C) 2013-2015 Alexei Starovoitov <ast@kernel.org>
+ * Copyright (C) 2015 Wang Nan <wangnan0@huawei.com>
+ * Copyright (C) 2015 Huawei Inc.
+ * Copyright (C) 2017 Nicira, Inc.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU Lesser General Public
+ * License as published by the Free Software Foundation;
+ * version 2.1 of the License (not later!)
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not,  see <http://www.gnu.org/licenses>
+ */
+
+#include <stdio.h>
+#include <string.h>
+
+#include "libbpf.h"
+
+#define ERRNO_OFFSET(e)		((e) - __LIBBPF_ERRNO__START)
+#define ERRCODE_OFFSET(c)	ERRNO_OFFSET(LIBBPF_ERRNO__##c)
+#define NR_ERRNO	(__LIBBPF_ERRNO__END - __LIBBPF_ERRNO__START)
+
+static const char *libbpf_strerror_table[NR_ERRNO] = {
+	[ERRCODE_OFFSET(LIBELF)]	= "Something wrong in libelf",
+	[ERRCODE_OFFSET(FORMAT)]	= "BPF object format invalid",
+	[ERRCODE_OFFSET(KVERSION)]	= "'version' section incorrect or lost",
+	[ERRCODE_OFFSET(ENDIAN)]	= "Endian mismatch",
+	[ERRCODE_OFFSET(INTERNAL)]	= "Internal error in libbpf",
+	[ERRCODE_OFFSET(RELOC)]		= "Relocation failed",
+	[ERRCODE_OFFSET(VERIFY)]	= "Kernel verifier blocks program loading",
+	[ERRCODE_OFFSET(PROG2BIG)]	= "Program too big",
+	[ERRCODE_OFFSET(KVER)]		= "Incorrect kernel version",
+	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
+	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
+	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
+};
+
+int libbpf_strerror(int err, char *buf, size_t size)
+{
+	if (!buf || !size)
+		return -1;
+
+	err = err > 0 ? err : -err;
+
+	if (err < __LIBBPF_ERRNO__START) {
+		int ret;
+
+		ret = strerror_r(err, buf, size);
+		buf[size - 1] = '\0';
+		return ret;
+	}
+
+	if (err < __LIBBPF_ERRNO__END) {
+		const char *msg;
+
+		msg = libbpf_strerror_table[ERRNO_OFFSET(err)];
+		snprintf(buf, size, "%s", msg);
+		buf[size - 1] = '\0';
+		return 0;
+	}
+
+	snprintf(buf, size, "Unknown libbpf error %d", err);
+	buf[size - 1] = '\0';
+	return -1;
+}
-- 
cgit v1.2.3


From 531b014e7a2fedaeff0b19b2934d830cd4b35dc0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:05 -0700
Subject: tools: bpf: make use of reallocarray

reallocarray() is a safer variant of realloc which checks for
multiplication overflow in case of array allocation.  Since it's
not available in Glibc < 2.26 import kernel's overflow.h and
add a static inline implementation when needed.  Use feature
detection to probe for existence of reallocarray.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Makefile              |   6 +-
 tools/bpf/bpftool/main.h                |   1 +
 tools/bpf/bpftool/xlated_dumper.c       |   6 +-
 tools/build/feature/Makefile            |   4 +
 tools/build/feature/test-reallocarray.c |   8 +
 tools/include/linux/compiler-gcc.h      |   4 +
 tools/include/linux/overflow.h          | 278 ++++++++++++++++++++++++++++++++
 tools/include/tools/libc_compat.h       |  20 +++
 tools/lib/bpf/Makefile                  |   6 +-
 tools/lib/bpf/libbpf.c                  |  10 +-
 10 files changed, 334 insertions(+), 9 deletions(-)
 create mode 100644 tools/build/feature/test-reallocarray.c
 create mode 100644 tools/include/linux/overflow.h
 create mode 100644 tools/include/tools/libc_compat.h

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 0911b00b25cc..6c4830e18879 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -52,7 +52,7 @@ INSTALL ?= install
 RM ?= rm -f
 
 FEATURE_USER = .bpftool
-FEATURE_TESTS = libbfd disassembler-four-args
+FEATURE_TESTS = libbfd disassembler-four-args reallocarray
 FEATURE_DISPLAY = libbfd disassembler-four-args
 
 check_feat := 1
@@ -75,6 +75,10 @@ ifeq ($(feature-disassembler-four-args), 1)
 CFLAGS += -DDISASM_FOUR_ARGS_SIGNATURE
 endif
 
+ifeq ($(feature-reallocarray), 0)
+CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
 include $(wildcard $(OUTPUT)*.d)
 
 all: $(OUTPUT)bpftool
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 15b6c49ae533..1e02e4031693 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -42,6 +42,7 @@
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/hashtable.h>
+#include <tools/libc_compat.h>
 
 #include "json_writer.h"
 
diff --git a/tools/bpf/bpftool/xlated_dumper.c b/tools/bpf/bpftool/xlated_dumper.c
index b97f1da60dd1..3284759df98a 100644
--- a/tools/bpf/bpftool/xlated_dumper.c
+++ b/tools/bpf/bpftool/xlated_dumper.c
@@ -35,6 +35,7 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#define _GNU_SOURCE
 #include <stdarg.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -66,9 +67,8 @@ void kernel_syms_load(struct dump_data *dd)
 	while (!feof(fp)) {
 		if (!fgets(buff, sizeof(buff), fp))
 			break;
-		tmp = realloc(dd->sym_mapping,
-			      (dd->sym_count + 1) *
-			      sizeof(*dd->sym_mapping));
+		tmp = reallocarray(dd->sym_mapping, dd->sym_count + 1,
+				   sizeof(*dd->sym_mapping));
 		if (!tmp) {
 out:
 			free(dd->sym_mapping);
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index dac9563b5470..0516259be70f 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -14,6 +14,7 @@ FILES=                                          \
          test-libaudit.bin                      \
          test-libbfd.bin                        \
          test-disassembler-four-args.bin        \
+         test-reallocarray.bin			\
          test-liberty.bin                       \
          test-liberty-z.bin                     \
          test-cplus-demangle.bin                \
@@ -204,6 +205,9 @@ $(OUTPUT)test-libbfd.bin:
 $(OUTPUT)test-disassembler-four-args.bin:
 	$(BUILD) -DPACKAGE='"perf"' -lbfd -lopcodes
 
+$(OUTPUT)test-reallocarray.bin:
+	$(BUILD)
+
 $(OUTPUT)test-liberty.bin:
 	$(CC) $(CFLAGS) -Wall -Werror -o $@ test-libbfd.c -DPACKAGE='"perf"' $(LDFLAGS) -lbfd -ldl -liberty
 
diff --git a/tools/build/feature/test-reallocarray.c b/tools/build/feature/test-reallocarray.c
new file mode 100644
index 000000000000..8170de35150d
--- /dev/null
+++ b/tools/build/feature/test-reallocarray.c
@@ -0,0 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
+#define _GNU_SOURCE
+#include <stdlib.h>
+
+int main(void)
+{
+	return !!reallocarray(NULL, 1, 1);
+}
diff --git a/tools/include/linux/compiler-gcc.h b/tools/include/linux/compiler-gcc.h
index 70fe61295733..0d35f18006a1 100644
--- a/tools/include/linux/compiler-gcc.h
+++ b/tools/include/linux/compiler-gcc.h
@@ -36,3 +36,7 @@
 #endif
 #define __printf(a, b)	__attribute__((format(printf, a, b)))
 #define __scanf(a, b)	__attribute__((format(scanf, a, b)))
+
+#if GCC_VERSION >= 50100
+#define COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW 1
+#endif
diff --git a/tools/include/linux/overflow.h b/tools/include/linux/overflow.h
new file mode 100644
index 000000000000..8712ff70995f
--- /dev/null
+++ b/tools/include/linux/overflow.h
@@ -0,0 +1,278 @@
+/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+#ifndef __LINUX_OVERFLOW_H
+#define __LINUX_OVERFLOW_H
+
+#include <linux/compiler.h>
+
+/*
+ * In the fallback code below, we need to compute the minimum and
+ * maximum values representable in a given type. These macros may also
+ * be useful elsewhere, so we provide them outside the
+ * COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW block.
+ *
+ * It would seem more obvious to do something like
+ *
+ * #define type_min(T) (T)(is_signed_type(T) ? (T)1 << (8*sizeof(T)-1) : 0)
+ * #define type_max(T) (T)(is_signed_type(T) ? ((T)1 << (8*sizeof(T)-1)) - 1 : ~(T)0)
+ *
+ * Unfortunately, the middle expressions, strictly speaking, have
+ * undefined behaviour, and at least some versions of gcc warn about
+ * the type_max expression (but not if -fsanitize=undefined is in
+ * effect; in that case, the warning is deferred to runtime...).
+ *
+ * The slightly excessive casting in type_min is to make sure the
+ * macros also produce sensible values for the exotic type _Bool. [The
+ * overflow checkers only almost work for _Bool, but that's
+ * a-feature-not-a-bug, since people shouldn't be doing arithmetic on
+ * _Bools. Besides, the gcc builtins don't allow _Bool* as third
+ * argument.]
+ *
+ * Idea stolen from
+ * https://mail-index.netbsd.org/tech-misc/2007/02/05/0000.html -
+ * credit to Christian Biere.
+ */
+#define is_signed_type(type)       (((type)(-1)) < (type)1)
+#define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
+#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+
+
+#ifdef COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW
+/*
+ * For simplicity and code hygiene, the fallback code below insists on
+ * a, b and *d having the same type (similar to the min() and max()
+ * macros), whereas gcc's type-generic overflow checkers accept
+ * different types. Hence we don't just make check_add_overflow an
+ * alias for __builtin_add_overflow, but add type checks similar to
+ * below.
+ */
+#define check_add_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_add_overflow(__a, __b, __d);	\
+})
+
+#define check_sub_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_sub_overflow(__a, __b, __d);	\
+})
+
+#define check_mul_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	__builtin_mul_overflow(__a, __b, __d);	\
+})
+
+#else
+
+
+/* Checking for unsigned overflow is relatively easy without causing UB. */
+#define __unsigned_add_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = __a + __b;			\
+	*__d < __a;				\
+})
+#define __unsigned_sub_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = __a - __b;			\
+	__a < __b;				\
+})
+/*
+ * If one of a or b is a compile-time constant, this avoids a division.
+ */
+#define __unsigned_mul_overflow(a, b, d) ({		\
+	typeof(a) __a = (a);				\
+	typeof(b) __b = (b);				\
+	typeof(d) __d = (d);				\
+	(void) (&__a == &__b);				\
+	(void) (&__a == __d);				\
+	*__d = __a * __b;				\
+	__builtin_constant_p(__b) ?			\
+	  __b > 0 && __a > type_max(typeof(__a)) / __b : \
+	  __a > 0 && __b > type_max(typeof(__b)) / __a;	 \
+})
+
+/*
+ * For signed types, detecting overflow is much harder, especially if
+ * we want to avoid UB. But the interface of these macros is such that
+ * we must provide a result in *d, and in fact we must produce the
+ * result promised by gcc's builtins, which is simply the possibly
+ * wrapped-around value. Fortunately, we can just formally do the
+ * operations in the widest relevant unsigned type (u64) and then
+ * truncate the result - gcc is smart enough to generate the same code
+ * with and without the (u64) casts.
+ */
+
+/*
+ * Adding two signed integers can overflow only if they have the same
+ * sign, and overflow has happened iff the result has the opposite
+ * sign.
+ */
+#define __signed_add_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = (u64)__a + (u64)__b;		\
+	(((~(__a ^ __b)) & (*__d ^ __a))	\
+		& type_min(typeof(__a))) != 0;	\
+})
+
+/*
+ * Subtraction is similar, except that overflow can now happen only
+ * when the signs are opposite. In this case, overflow has happened if
+ * the result has the opposite sign of a.
+ */
+#define __signed_sub_overflow(a, b, d) ({	\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	typeof(d) __d = (d);			\
+	(void) (&__a == &__b);			\
+	(void) (&__a == __d);			\
+	*__d = (u64)__a - (u64)__b;		\
+	((((__a ^ __b)) & (*__d ^ __a))		\
+		& type_min(typeof(__a))) != 0;	\
+})
+
+/*
+ * Signed multiplication is rather hard. gcc always follows C99, so
+ * division is truncated towards 0. This means that we can write the
+ * overflow check like this:
+ *
+ * (a > 0 && (b > MAX/a || b < MIN/a)) ||
+ * (a < -1 && (b > MIN/a || b < MAX/a) ||
+ * (a == -1 && b == MIN)
+ *
+ * The redundant casts of -1 are to silence an annoying -Wtype-limits
+ * (included in -Wextra) warning: When the type is u8 or u16, the
+ * __b_c_e in check_mul_overflow obviously selects
+ * __unsigned_mul_overflow, but unfortunately gcc still parses this
+ * code and warns about the limited range of __b.
+ */
+
+#define __signed_mul_overflow(a, b, d) ({				\
+	typeof(a) __a = (a);						\
+	typeof(b) __b = (b);						\
+	typeof(d) __d = (d);						\
+	typeof(a) __tmax = type_max(typeof(a));				\
+	typeof(a) __tmin = type_min(typeof(a));				\
+	(void) (&__a == &__b);						\
+	(void) (&__a == __d);						\
+	*__d = (u64)__a * (u64)__b;					\
+	(__b > 0   && (__a > __tmax/__b || __a < __tmin/__b)) ||	\
+	(__b < (typeof(__b))-1  && (__a > __tmin/__b || __a < __tmax/__b)) || \
+	(__b == (typeof(__b))-1 && __a == __tmin);			\
+})
+
+
+#define check_add_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_add_overflow(a, b, d),			\
+			__unsigned_add_overflow(a, b, d))
+
+#define check_sub_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_sub_overflow(a, b, d),			\
+			__unsigned_sub_overflow(a, b, d))
+
+#define check_mul_overflow(a, b, d)					\
+	__builtin_choose_expr(is_signed_type(typeof(a)),		\
+			__signed_mul_overflow(a, b, d),			\
+			__unsigned_mul_overflow(a, b, d))
+
+
+#endif /* COMPILER_HAS_GENERIC_BUILTIN_OVERFLOW */
+
+/**
+ * array_size() - Calculate size of 2-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ *
+ * Calculates size of 2-dimensional array: @a * @b.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array_size(size_t a, size_t b)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * array3_size() - Calculate size of 3-dimensional array.
+ *
+ * @a: dimension one
+ * @b: dimension two
+ * @c: dimension three
+ *
+ * Calculates size of 3-dimensional array: @a * @b * @c.
+ *
+ * Returns: number of bytes needed to represent the array or SIZE_MAX on
+ * overflow.
+ */
+static inline __must_check size_t array3_size(size_t a, size_t b, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(a, b, &bytes))
+		return SIZE_MAX;
+	if (check_mul_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+static inline __must_check size_t __ab_c_size(size_t n, size_t size, size_t c)
+{
+	size_t bytes;
+
+	if (check_mul_overflow(n, size, &bytes))
+		return SIZE_MAX;
+	if (check_add_overflow(bytes, c, &bytes))
+		return SIZE_MAX;
+
+	return bytes;
+}
+
+/**
+ * struct_size() - Calculate size of structure with trailing array.
+ * @p: Pointer to the structure.
+ * @member: Name of the array member.
+ * @n: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @p followed by an
+ * array of @n @member elements.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size(p, member, n)					\
+	__ab_c_size(n,							\
+		    sizeof(*(p)->member) + __must_be_array((p)->member),\
+		    sizeof(*(p)))
+
+#endif /* __LINUX_OVERFLOW_H */
diff --git a/tools/include/tools/libc_compat.h b/tools/include/tools/libc_compat.h
new file mode 100644
index 000000000000..664ced8cb1b0
--- /dev/null
+++ b/tools/include/tools/libc_compat.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Copyright (C) 2018 Netronome Systems, Inc. */
+
+#ifndef __TOOLS_LIBC_COMPAT_H
+#define __TOOLS_LIBC_COMPAT_H
+
+#include <stdlib.h>
+#include <linux/overflow.h>
+
+#ifdef COMPAT_NEED_REALLOCARRAY
+static inline void *reallocarray(void *ptr, size_t nmemb, size_t size)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(nmemb, size, &bytes)))
+		return NULL;
+	return realloc(ptr, bytes);
+}
+#endif
+#endif
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 5390e7725e43..7a8e4c98ef1a 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -66,7 +66,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf
+FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf reallocarray
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
@@ -120,6 +120,10 @@ ifeq ($(feature-libelf-getphdrnum), 1)
   override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
 endif
 
+ifeq ($(feature-reallocarray), 0)
+  override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
+endif
+
 # Append required CFLAGS
 override CFLAGS += $(EXTRA_WARNINGS)
 override CFLAGS += -Werror -Wall
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index f732237610e5..fd2c4433863d 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -22,6 +22,7 @@
  * License along with this program; if not,  see <http://www.gnu.org/licenses>
  */
 
+#define _GNU_SOURCE
 #include <stdlib.h>
 #include <stdio.h>
 #include <stdarg.h>
@@ -41,6 +42,7 @@
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
+#include <tools/libc_compat.h>
 #include <libelf.h>
 #include <gelf.h>
 
@@ -321,7 +323,7 @@ bpf_object__add_program(struct bpf_object *obj, void *data, size_t size,
 	progs = obj->programs;
 	nr_progs = obj->nr_programs;
 
-	progs = realloc(progs, sizeof(progs[0]) * (nr_progs + 1));
+	progs = reallocarray(progs, nr_progs + 1, sizeof(progs[0]));
 	if (!progs) {
 		/*
 		 * In this case the original obj->programs
@@ -822,8 +824,8 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 				continue;
 			}
 
-			reloc = realloc(reloc,
-					sizeof(*obj->efile.reloc) * nr_reloc);
+			reloc = reallocarray(reloc, nr_reloc,
+					     sizeof(*obj->efile.reloc));
 			if (!reloc) {
 				pr_warning("realloc failed\n");
 				err = -ENOMEM;
@@ -1115,7 +1117,7 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
 			return -LIBBPF_ERRNO__RELOC;
 		}
 		new_cnt = prog->insns_cnt + text->insns_cnt;
-		new_insn = realloc(prog->insns, new_cnt * sizeof(*insn));
+		new_insn = reallocarray(prog->insns, new_cnt, sizeof(*insn));
 		if (!new_insn) {
 			pr_warning("oom in prog realloc\n");
 			return -ENOMEM;
-- 
cgit v1.2.3


From 26736eb9a483715c2e971a8866f55fbb156903e2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:06 -0700
Subject: tools: libbpf: allow map reuse

More advanced applications may want to only replace programs without
destroying associated maps.  Allow libbpf users to achieve that.
Instead of always creating all of the maps at load time, expose to
users an API to reconstruct the map object from already existing
map.

The map parameters are read from the kernel and replace the parameters
of the ELF map.  libbpf does not restrict the map replacement, i.e.
the reused map does not have to be compatible with the ELF map
definition.  We relay on the verifier for checking the compatibility
between maps and programs.  The ELF map definition is completely
overwritten by the information read from the kernel, to make sure
libbpf's view of map object corresponds to the actual map.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.h |  1 +
 2 files changed, 54 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index fd2c4433863d..955f8eafbf41 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1035,6 +1035,53 @@ static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf)
 	return 0;
 }
 
+int bpf_map__reuse_fd(struct bpf_map *map, int fd)
+{
+	struct bpf_map_info info = {};
+	__u32 len = sizeof(info);
+	int new_fd, err;
+	char *new_name;
+
+	err = bpf_obj_get_info_by_fd(fd, &info, &len);
+	if (err)
+		return err;
+
+	new_name = strdup(info.name);
+	if (!new_name)
+		return -errno;
+
+	new_fd = open("/", O_RDONLY | O_CLOEXEC);
+	if (new_fd < 0)
+		goto err_free_new_name;
+
+	new_fd = dup3(fd, new_fd, O_CLOEXEC);
+	if (new_fd < 0)
+		goto err_close_new_fd;
+
+	err = zclose(map->fd);
+	if (err)
+		goto err_close_new_fd;
+	free(map->name);
+
+	map->fd = new_fd;
+	map->name = new_name;
+	map->def.type = info.type;
+	map->def.key_size = info.key_size;
+	map->def.value_size = info.value_size;
+	map->def.max_entries = info.max_entries;
+	map->def.map_flags = info.map_flags;
+	map->btf_key_type_id = info.btf_key_type_id;
+	map->btf_value_type_id = info.btf_value_type_id;
+
+	return 0;
+
+err_close_new_fd:
+	close(new_fd);
+err_free_new_name:
+	free(new_name);
+	return -errno;
+}
+
 static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
@@ -1047,6 +1094,12 @@ bpf_object__create_maps(struct bpf_object *obj)
 		struct bpf_map_def *def = &map->def;
 		int *pfd = &map->fd;
 
+		if (map->fd >= 0) {
+			pr_debug("skip map create (preset) %s: fd=%d\n",
+				 map->name, map->fd);
+			continue;
+		}
+
 		create_attr.name = map->name;
 		create_attr.map_ifindex = map->map_ifindex;
 		create_attr.map_type = def->type;
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index e911ad32d02e..1f8fc2060460 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -261,6 +261,7 @@ typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *);
 int bpf_map__set_priv(struct bpf_map *map, void *priv,
 		      bpf_map_clear_priv_t clear_priv);
 void *bpf_map__priv(struct bpf_map *map);
+int bpf_map__reuse_fd(struct bpf_map *map, int fd);
 bool bpf_map__is_offload_neutral(struct bpf_map *map);
 void bpf_map__set_ifindex(struct bpf_map *map, __u32 ifindex);
 int bpf_map__pin(struct bpf_map *map, const char *path);
-- 
cgit v1.2.3


From 3ff5a4dc5d890963e669fc99cc62ee07d1da24e8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 10 Jul 2018 14:43:07 -0700
Subject: tools: bpftool: allow reuse of maps with bpftool prog load

Add map parameter to prog load which will allow reuse of existing
maps instead of creating new ones.

We need feature detection and compat code for reallocarray, since
it's not available in many libc versions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/Documentation/bpftool-prog.rst |  20 ++-
 tools/bpf/bpftool/bash-completion/bpftool        |  67 +++++++++-
 tools/bpf/bpftool/main.h                         |   3 +
 tools/bpf/bpftool/map.c                          |   4 +-
 tools/bpf/bpftool/prog.c                         | 148 +++++++++++++++++++++--
 5 files changed, 219 insertions(+), 23 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
index e53e1ad2caf0..64156a16d530 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst
@@ -24,9 +24,10 @@ MAP COMMANDS
 |	**bpftool** **prog dump xlated** *PROG* [{**file** *FILE* | **opcodes** | **visual**}]
 |	**bpftool** **prog dump jited**  *PROG* [{**file** *FILE* | **opcodes**}]
 |	**bpftool** **prog pin** *PROG* *FILE*
-|	**bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
+|	**bpftool** **prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 |	**bpftool** **prog help**
 |
+|	*MAP* := { **id** *MAP_ID* | **pinned** *FILE* }
 |	*PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* }
 |	*TYPE* := {
 |		**socket** | **kprobe** | **kretprobe** | **classifier** | **action** |
@@ -73,10 +74,17 @@ DESCRIPTION
 
 		  Note: *FILE* must be located in *bpffs* mount.
 
-	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**dev** *NAME*]
+	**bpftool prog load** *OBJ* *FILE* [**type** *TYPE*] [**map** {**idx** *IDX* | **name** *NAME*} *MAP*] [**dev** *NAME*]
 		  Load bpf program from binary *OBJ* and pin as *FILE*.
 		  **type** is optional, if not specified program type will be
 		  inferred from section names.
+		  By default bpftool will create new maps as declared in the ELF
+		  object being loaded.  **map** parameter allows for the reuse
+		  of existing maps.  It can be specified multiple times, each
+		  time for a different map.  *IDX* refers to index of the map
+		  to be replaced in the ELF file counting from 0, while *NAME*
+		  allows to replace a map by name.  *MAP* specifies the map to
+		  use, referring to it by **id** or through a **pinned** file.
 		  If **dev** *NAME* is specified program will be loaded onto
 		  given networking device (offload).
 
@@ -172,6 +180,14 @@ EXAMPLES
     mov    %rbx,0x0(%rbp)
     48 89 5d 00
 
+|
+| **# bpftool prog load xdp1_kern.o /sys/fs/bpf/xdp1 type xdp map name rxcnt id 7**
+| **# bpftool prog show pinned /sys/fs/bpf/xdp1**
+|   9: xdp  name xdp_prog1  tag 539ec6ce11b52f98  gpl
+|	loaded_at 2018-06-25T16:17:31-0700  uid 0
+|	xlated 488B  jited 336B  memlock 4096B  map_ids 7
+| **# rm /sys/fs/bpf/xdp1**
+|
 
 SEE ALSO
 ========
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index caf8711993be..598066c40191 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -99,6 +99,29 @@ _bpftool_get_prog_tags()
         command sed -n 's/.*"tag": "\(.*\)",$/\1/p' )" -- "$cur" ) )
 }
 
+_bpftool_get_obj_map_names()
+{
+    local obj
+
+    obj=$1
+
+    maps=$(objdump -j maps -t $obj 2>/dev/null | \
+        command awk '/g     . maps/ {print $NF}')
+
+    COMPREPLY+=( $( compgen -W "$maps" -- "$cur" ) )
+}
+
+_bpftool_get_obj_map_idxs()
+{
+    local obj
+
+    obj=$1
+
+    nmaps=$(objdump -j maps -t $obj 2>/dev/null | grep -c 'g     . maps')
+
+    COMPREPLY+=( $( compgen -W "$(seq 0 $((nmaps - 1)))" -- "$cur" ) )
+}
+
 _sysfs_get_netdevs()
 {
     COMPREPLY+=( $( compgen -W "$( ls /sys/class/net 2>/dev/null )" -- \
@@ -220,12 +243,14 @@ _bpftool()
     # Completion depends on object and command in use
     case $object in
         prog)
-            case $prev in
-                id)
-                    _bpftool_get_prog_ids
-                    return 0
-                    ;;
-            esac
+            if [[ $command != "load" ]]; then
+                case $prev in
+                    id)
+                        _bpftool_get_prog_ids
+                        return 0
+                        ;;
+                esac
+            fi
 
             local PROG_TYPE='id pinned tag'
             case $command in
@@ -268,22 +293,52 @@ _bpftool()
                     return 0
                     ;;
                 load)
+                    local obj
+
                     if [[ ${#words[@]} -lt 6 ]]; then
                         _filedir
                         return 0
                     fi
 
+                    obj=${words[3]}
+
+                    if [[ ${words[-4]} == "map" ]]; then
+                        COMPREPLY=( $( compgen -W "id pinned" -- "$cur" ) )
+                        return 0
+                    fi
+                    if [[ ${words[-3]} == "map" ]]; then
+                        if [[ ${words[-2]} == "idx" ]]; then
+                            _bpftool_get_obj_map_idxs $obj
+                        elif [[ ${words[-2]} == "name" ]]; then
+                            _bpftool_get_obj_map_names $obj
+                        fi
+                        return 0
+                    fi
+                    if [[ ${words[-2]} == "map" ]]; then
+                        COMPREPLY=( $( compgen -W "idx name" -- "$cur" ) )
+                        return 0
+                    fi
+
                     case $prev in
                         type)
                             COMPREPLY=( $( compgen -W "socket kprobe kretprobe classifier action tracepoint raw_tracepoint xdp perf_event cgroup/skb cgroup/sock cgroup/dev lwt_in lwt_out lwt_xmit lwt_seg6local sockops sk_skb sk_msg lirc_mode2 cgroup/bind4 cgroup/bind6 cgroup/connect4 cgroup/connect6 cgroup/sendmsg4 cgroup/sendmsg6 cgroup/post_bind4 cgroup/post_bind6" -- \
                                                    "$cur" ) )
                             return 0
                             ;;
+                        id)
+                            _bpftool_get_map_ids
+                            return 0
+                            ;;
+                        pinned)
+                            _filedir
+                            return 0
+                            ;;
                         dev)
                             _sysfs_get_netdevs
                             return 0
                             ;;
                         *)
+                            COMPREPLY=( $( compgen -W "map" -- "$cur" ) )
                             _bpftool_once_attr 'type'
                             _bpftool_once_attr 'dev'
                             return 0
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 1e02e4031693..41004bb2644a 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -75,6 +75,8 @@
 	"PROG := { id PROG_ID | pinned FILE | tag PROG_TAG }"
 #define HELP_SPEC_OPTIONS						\
 	"OPTIONS := { {-j|--json} [{-p|--pretty}] | {-f|--bpffs} }"
+#define HELP_SPEC_MAP							\
+	"MAP := { id MAP_ID | pinned FILE }"
 
 enum bpf_obj_type {
 	BPF_OBJ_UNKNOWN,
@@ -136,6 +138,7 @@ int do_cgroup(int argc, char **arg);
 int do_perf(int argc, char **arg);
 
 int prog_parse_fd(int *argc, char ***argv);
+int map_parse_fd(int *argc, char ***argv);
 int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len);
 
 void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 5989e1575ae4..e2baec1122fb 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -93,7 +93,7 @@ static void *alloc_value(struct bpf_map_info *info)
 		return malloc(info->value_size);
 }
 
-static int map_parse_fd(int *argc, char ***argv)
+int map_parse_fd(int *argc, char ***argv)
 {
 	int fd;
 
@@ -824,7 +824,7 @@ static int do_help(int argc, char **argv)
 		"       %s %s event_pipe MAP [cpu N index M]\n"
 		"       %s %s help\n"
 		"\n"
-		"       MAP := { id MAP_ID | pinned FILE }\n"
+		"       " HELP_SPEC_MAP "\n"
 		"       DATA := { [hex] BYTES }\n"
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       VALUE := { DATA | MAP | PROG }\n"
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index 2bdd5ecd1aad..dce960d22106 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -31,6 +31,7 @@
  * SOFTWARE.
  */
 
+#define _GNU_SOURCE
 #include <errno.h>
 #include <fcntl.h>
 #include <stdarg.h>
@@ -682,18 +683,34 @@ static int do_pin(int argc, char **argv)
 	return err;
 }
 
+struct map_replace {
+	int idx;
+	int fd;
+	char *name;
+};
+
+int map_replace_compar(const void *p1, const void *p2)
+{
+	const struct map_replace *a = p1, *b = p2;
+
+	return a->idx - b->idx;
+}
+
 static int do_load(int argc, char **argv)
 {
 	enum bpf_attach_type expected_attach_type;
 	struct bpf_object_open_attr attr = {
 		.prog_type	= BPF_PROG_TYPE_UNSPEC,
 	};
+	struct map_replace *map_replace = NULL;
+	unsigned int old_map_fds = 0;
 	struct bpf_program *prog;
 	struct bpf_object *obj;
 	struct bpf_map *map;
 	const char *pinfile;
+	unsigned int i, j;
 	__u32 ifindex = 0;
-	int err;
+	int idx, err;
 
 	if (!REQ_ARGS(2))
 		return -1;
@@ -708,16 +725,16 @@ static int do_load(int argc, char **argv)
 
 			if (attr.prog_type != BPF_PROG_TYPE_UNSPEC) {
 				p_err("program type already specified");
-				return -1;
+				goto err_free_reuse_maps;
 			}
 			if (!REQ_ARGS(1))
-				return -1;
+				goto err_free_reuse_maps;
 
 			/* Put a '/' at the end of type to appease libbpf */
 			type = malloc(strlen(*argv) + 2);
 			if (!type) {
 				p_err("mem alloc failed");
-				return -1;
+				goto err_free_reuse_maps;
 			}
 			*type = 0;
 			strcat(type, *argv);
@@ -728,37 +745,81 @@ static int do_load(int argc, char **argv)
 			free(type);
 			if (err < 0) {
 				p_err("unknown program type '%s'", *argv);
-				return err;
+				goto err_free_reuse_maps;
 			}
 			NEXT_ARG();
+		} else if (is_prefix(*argv, "map")) {
+			char *endptr, *name;
+			int fd;
+
+			NEXT_ARG();
+
+			if (!REQ_ARGS(4))
+				goto err_free_reuse_maps;
+
+			if (is_prefix(*argv, "idx")) {
+				NEXT_ARG();
+
+				idx = strtoul(*argv, &endptr, 0);
+				if (*endptr) {
+					p_err("can't parse %s as IDX", *argv);
+					goto err_free_reuse_maps;
+				}
+				name = NULL;
+			} else if (is_prefix(*argv, "name")) {
+				NEXT_ARG();
+
+				name = *argv;
+				idx = -1;
+			} else {
+				p_err("expected 'idx' or 'name', got: '%s'?",
+				      *argv);
+				goto err_free_reuse_maps;
+			}
+			NEXT_ARG();
+
+			fd = map_parse_fd(&argc, &argv);
+			if (fd < 0)
+				goto err_free_reuse_maps;
+
+			map_replace = reallocarray(map_replace, old_map_fds + 1,
+						   sizeof(*map_replace));
+			if (!map_replace) {
+				p_err("mem alloc failed");
+				goto err_free_reuse_maps;
+			}
+			map_replace[old_map_fds].idx = idx;
+			map_replace[old_map_fds].name = name;
+			map_replace[old_map_fds].fd = fd;
+			old_map_fds++;
 		} else if (is_prefix(*argv, "dev")) {
 			NEXT_ARG();
 
 			if (ifindex) {
 				p_err("offload device already specified");
-				return -1;
+				goto err_free_reuse_maps;
 			}
 			if (!REQ_ARGS(1))
-				return -1;
+				goto err_free_reuse_maps;
 
 			ifindex = if_nametoindex(*argv);
 			if (!ifindex) {
 				p_err("unrecognized netdevice '%s': %s",
 				      *argv, strerror(errno));
-				return -1;
+				goto err_free_reuse_maps;
 			}
 			NEXT_ARG();
 		} else {
-			p_err("expected no more arguments, 'type' or 'dev', got: '%s'?",
+			p_err("expected no more arguments, 'type', 'map' or 'dev', got: '%s'?",
 			      *argv);
-			return -1;
+			goto err_free_reuse_maps;
 		}
 	}
 
 	obj = bpf_object__open_xattr(&attr);
 	if (IS_ERR_OR_NULL(obj)) {
 		p_err("failed to open object file");
-		return -1;
+		goto err_free_reuse_maps;
 	}
 
 	prog = bpf_program__next(NULL, obj);
@@ -782,10 +843,62 @@ static int do_load(int argc, char **argv)
 	bpf_program__set_type(prog, attr.prog_type);
 	bpf_program__set_expected_attach_type(prog, expected_attach_type);
 
-	bpf_map__for_each(map, obj)
+	qsort(map_replace, old_map_fds, sizeof(*map_replace),
+	      map_replace_compar);
+
+	/* After the sort maps by name will be first on the list, because they
+	 * have idx == -1.  Resolve them.
+	 */
+	j = 0;
+	while (j < old_map_fds && map_replace[j].name) {
+		i = 0;
+		bpf_map__for_each(map, obj) {
+			if (!strcmp(bpf_map__name(map), map_replace[j].name)) {
+				map_replace[j].idx = i;
+				break;
+			}
+			i++;
+		}
+		if (map_replace[j].idx == -1) {
+			p_err("unable to find map '%s'", map_replace[j].name);
+			goto err_close_obj;
+		}
+		j++;
+	}
+	/* Resort if any names were resolved */
+	if (j)
+		qsort(map_replace, old_map_fds, sizeof(*map_replace),
+		      map_replace_compar);
+
+	/* Set ifindex and name reuse */
+	j = 0;
+	idx = 0;
+	bpf_map__for_each(map, obj) {
 		if (!bpf_map__is_offload_neutral(map))
 			bpf_map__set_ifindex(map, ifindex);
 
+		if (j < old_map_fds && idx == map_replace[j].idx) {
+			err = bpf_map__reuse_fd(map, map_replace[j++].fd);
+			if (err) {
+				p_err("unable to set up map reuse: %d", err);
+				goto err_close_obj;
+			}
+
+			/* Next reuse wants to apply to the same map */
+			if (j < old_map_fds && map_replace[j].idx == idx) {
+				p_err("replacement for map idx %d specified more than once",
+				      idx);
+				goto err_close_obj;
+			}
+		}
+
+		idx++;
+	}
+	if (j < old_map_fds) {
+		p_err("map idx '%d' not used", map_replace[j].idx);
+		goto err_close_obj;
+	}
+
 	err = bpf_object__load(obj);
 	if (err) {
 		p_err("failed to load object file");
@@ -799,11 +912,18 @@ static int do_load(int argc, char **argv)
 		jsonw_null(json_wtr);
 
 	bpf_object__close(obj);
+	for (i = 0; i < old_map_fds; i++)
+		close(map_replace[i].fd);
+	free(map_replace);
 
 	return 0;
 
 err_close_obj:
 	bpf_object__close(obj);
+err_free_reuse_maps:
+	for (i = 0; i < old_map_fds; i++)
+		close(map_replace[i].fd);
+	free(map_replace);
 	return -1;
 }
 
@@ -819,9 +939,11 @@ static int do_help(int argc, char **argv)
 		"       %s %s dump xlated PROG [{ file FILE | opcodes | visual }]\n"
 		"       %s %s dump jited  PROG [{ file FILE | opcodes }]\n"
 		"       %s %s pin   PROG FILE\n"
-		"       %s %s load  OBJ  FILE [type TYPE] [dev NAME]\n"
+		"       %s %s load  OBJ  FILE [type TYPE] [dev NAME] \\\n"
+		"                         [map { idx IDX | name NAME } MAP]\n"
 		"       %s %s help\n"
 		"\n"
+		"       " HELP_SPEC_MAP "\n"
 		"       " HELP_SPEC_PROGRAM "\n"
 		"       TYPE := { socket | kprobe | kretprobe | classifier | action |\n"
 		"                 tracepoint | raw_tracepoint | xdp | perf_event | cgroup/skb |\n"
-- 
cgit v1.2.3


From 5685ca0ca292b656086085dc3847f10e7ff85225 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Tue, 10 Jul 2018 17:05:18 +0200
Subject: drm/tinydrm: Fix doc build warnings
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

include/drm/tinydrm/tinydrm.h:34: warning: Function parameter or member 'fb_dirty' not described in 'tinydrm_device'
drivers/gpu/drm/tinydrm/mipi-dbi.c:272: warning: Function parameter or member 'crtc_state' not described in 'mipi_dbi_enable_flush'
drivers/gpu/drm/tinydrm/mipi-dbi.c:272: warning: Function parameter or member 'plane_state' not described in 'mipi_dbi_enable_flush'

Move struct member docs inline so it's not missed next time.

Cc: David Lechner <david@lechnology.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: David Lechner <david@lechnology.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710150518.10528-1-noralf@tronnes.org
---
 drivers/gpu/drm/tinydrm/mipi-dbi.c |  2 ++
 include/drm/tinydrm/tinydrm.h      | 23 +++++++++++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/tinydrm/mipi-dbi.c b/drivers/gpu/drm/tinydrm/mipi-dbi.c
index 4d1fb31a781f..cb3441e51d5f 100644
--- a/drivers/gpu/drm/tinydrm/mipi-dbi.c
+++ b/drivers/gpu/drm/tinydrm/mipi-dbi.c
@@ -260,6 +260,8 @@ static const struct drm_framebuffer_funcs mipi_dbi_fb_funcs = {
 /**
  * mipi_dbi_enable_flush - MIPI DBI enable helper
  * @mipi: MIPI DBI structure
+ * @crtc_state: CRTC state
+ * @plane_state: Plane state
  *
  * This function sets &mipi_dbi->enabled, flushes the whole framebuffer and
  * enables the backlight. Drivers can use this in their
diff --git a/include/drm/tinydrm/tinydrm.h b/include/drm/tinydrm/tinydrm.h
index 56e4a916b5e8..fe9827d0ca8a 100644
--- a/include/drm/tinydrm/tinydrm.h
+++ b/include/drm/tinydrm/tinydrm.h
@@ -16,16 +16,31 @@
 
 /**
  * struct tinydrm_device - tinydrm device
- * @drm: DRM device
- * @pipe: Display pipe structure
- * @dirty_lock: Serializes framebuffer flushing
- * @fb_funcs: Framebuffer functions used when creating framebuffers
  */
 struct tinydrm_device {
+	/**
+	 * @drm: DRM device
+	 */
 	struct drm_device *drm;
+
+	/**
+	 * @pipe: Display pipe structure
+	 */
 	struct drm_simple_display_pipe pipe;
+
+	/**
+	 * @dirty_lock: Serializes framebuffer flushing
+	 */
 	struct mutex dirty_lock;
+
+	/**
+	 * @fb_funcs: Framebuffer functions used when creating framebuffers
+	 */
 	const struct drm_framebuffer_funcs *fb_funcs;
+
+	/**
+	 * @fb_dirty: Framebuffer dirty callback
+	 */
 	int (*fb_dirty)(struct drm_framebuffer *framebuffer,
 			struct drm_file *file_priv, unsigned flags,
 			unsigned color, struct drm_clip_rect *clips,
-- 
cgit v1.2.3


From ae61f61fa802c829fa8d505587f9b337e63ea586 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Wed, 11 Jul 2018 17:56:32 +0200
Subject: drm/client: Fix: drm_client_new: Don't require DRM to be registered
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 894a677f4b3e ("drm/cma-helper: Use the generic fbdev emulation")
broke almost all drivers that use the CMA helper.

The reason is that drm_client_new() requires that the DRM device has
been registered, but the drivers register fbdev before registering DRM.

Remove the requirement that DRM should be registered when creating a
new client.

Fixes: c76f0f7cb546 ("drm: Begin an API for in-kernel clients")
Cc: Maxime Ripard <maxime.ripard@bootlin.com>
Cc: Icenowy Zheng <icenowy@aosc.io>
Cc: Chen-Yu Tsai <wens@csie.org>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Tested-by: Icenowy Zheng <icenowy@aosc.io>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711155632.37437-1-noralf@tronnes.org
---
 drivers/gpu/drm/drm_client.c | 11 +----------
 1 file changed, 1 insertion(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index 4039a4d103a8..9b142f58d489 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -78,7 +78,6 @@ EXPORT_SYMBOL(drm_client_close);
 int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
 		   const char *name, const struct drm_client_funcs *funcs)
 {
-	bool registered;
 	int ret;
 
 	if (!drm_core_check_feature(dev, DRIVER_MODESET) ||
@@ -97,21 +96,13 @@ int drm_client_new(struct drm_device *dev, struct drm_client_dev *client,
 		goto err_put_module;
 
 	mutex_lock(&dev->clientlist_mutex);
-	registered = dev->registered;
-	if (registered)
-		list_add(&client->list, &dev->clientlist);
+	list_add(&client->list, &dev->clientlist);
 	mutex_unlock(&dev->clientlist_mutex);
-	if (!registered) {
-		ret = -ENODEV;
-		goto err_close;
-	}
 
 	drm_dev_get(dev);
 
 	return 0;
 
-err_close:
-	drm_client_close(client);
 err_put_module:
 	if (funcs)
 		module_put(funcs->owner);
-- 
cgit v1.2.3


From efeaed4d98eb4dc9ce01e1dca6d3778d180b272c Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Wed, 11 Jul 2018 22:32:44 -0400
Subject: drm/amdkfd: Reliably prevent reclaim-FS while holding DQM lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is needed to prevent deadlocks when MMU notifiers run in
reclaim-FS context and take the DQM lock for userptr evictions.
Previously this was done by making all memory allocations under
DQM locks GFP_NOIO. This is error prone. Using
memalloc_nofs_save/restore will reliably affect all memory
allocations anywhere in the kernel while the DQM lock is held.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 85 +++++++++++-----------
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.h  | 20 ++++-
 2 files changed, 62 insertions(+), 43 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 668ad07ebe1f..f2f81d26db0c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -240,7 +240,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 
 	print_queue(q);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new usermode queue because %d queues were already created\n",
@@ -297,7 +297,7 @@ static int create_queue_nocpsch(struct device_queue_manager *dqm,
 			dqm->total_queue_count);
 
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -457,9 +457,9 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 {
 	int retval;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	retval = destroy_queue_nocpsch_locked(dqm, qpd, q);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 }
@@ -471,7 +471,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 	struct kfd_process_device *pdd;
 	bool prev_active = false;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	pdd = kfd_get_process_device_data(q->device, q->process);
 	if (!pdd) {
 		retval = -ENODEV;
@@ -537,7 +537,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 				       &q->properties, q->process->mm);
 
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -570,7 +570,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 	struct kfd_process_device *pdd;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (qpd->evicted++ > 0) /* already evicted, do nothing */
 		goto out;
 
@@ -600,7 +600,7 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 	}
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -611,7 +611,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 	struct kfd_process_device *pdd;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (qpd->evicted++ > 0) /* already evicted, do nothing */
 		goto out;
 
@@ -633,7 +633,7 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 				KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -650,7 +650,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */
 		goto out;
 	if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */
@@ -695,7 +695,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	}
 	qpd->evicted = 0;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -711,7 +711,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (WARN_ON_ONCE(!qpd->evicted)) /* already restored, do nothing */
 		goto out;
 	if (qpd->evicted > 1) { /* ref count still > 0, decrement & quit */
@@ -739,7 +739,7 @@ static int restore_process_queues_cpsch(struct device_queue_manager *dqm,
 	if (!retval)
 		qpd->evicted = 0;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -761,7 +761,7 @@ static int register_process(struct device_queue_manager *dqm,
 	/* Retrieve PD base */
 	pd_base = dqm->dev->kfd2kgd->get_process_page_dir(pdd->vm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	list_add(&n->list, &dqm->queues);
 
 	/* Update PD Base in QPD */
@@ -771,7 +771,7 @@ static int register_process(struct device_queue_manager *dqm,
 
 	dqm->processes_count++;
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 }
@@ -786,7 +786,7 @@ static int unregister_process(struct device_queue_manager *dqm,
 			list_empty(&qpd->queues_list) ? "empty" : "not empty");
 
 	retval = 0;
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	list_for_each_entry_safe(cur, next, &dqm->queues, list) {
 		if (qpd == cur->qpd) {
@@ -799,7 +799,7 @@ static int unregister_process(struct device_queue_manager *dqm,
 	/* qpd not found in dqm list */
 	retval = 1;
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -838,7 +838,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	if (!dqm->allocated_queues)
 		return -ENOMEM;
 
-	mutex_init(&dqm->lock);
+	mutex_init(&dqm->lock_hidden);
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->next_pipe_to_allocate = 0;
 	dqm->sdma_queue_count = 0;
@@ -867,7 +867,7 @@ static void uninitialize(struct device_queue_manager *dqm)
 	kfree(dqm->allocated_queues);
 	for (i = 0 ; i < KFD_MQD_TYPE_MAX ; i++)
 		kfree(dqm->mqds[i]);
-	mutex_destroy(&dqm->lock);
+	mutex_destroy(&dqm->lock_hidden);
 	kfd_gtt_sa_free(dqm->dev, dqm->pipeline_mem);
 }
 
@@ -1003,7 +1003,7 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 {
 	pr_debug("num of pipes: %d\n", get_pipes_per_mec(dqm));
 
-	mutex_init(&dqm->lock);
+	mutex_init(&dqm->lock_hidden);
 	INIT_LIST_HEAD(&dqm->queues);
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
@@ -1041,9 +1041,9 @@ static int start_cpsch(struct device_queue_manager *dqm)
 
 	init_interrupts(dqm);
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return 0;
 fail_allocate_vidmem:
@@ -1055,9 +1055,9 @@ fail_packet_manager_init:
 
 static int stop_cpsch(struct device_queue_manager *dqm)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	unmap_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	kfd_gtt_sa_free(dqm->dev, dqm->fence_mem);
 	pm_uninit(&dqm->packets);
@@ -1069,11 +1069,11 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
 					struct qcm_process_device *qpd)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new kernel queue because %d queues were already created\n",
 				dqm->total_queue_count);
-		mutex_unlock(&dqm->lock);
+		dqm_unlock(dqm);
 		return -EPERM;
 	}
 
@@ -1089,7 +1089,7 @@ static int create_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	dqm->queue_count++;
 	qpd->is_debug = true;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return 0;
 }
@@ -1098,7 +1098,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 					struct kernel_queue *kq,
 					struct qcm_process_device *qpd)
 {
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 	list_del(&kq->list);
 	dqm->queue_count--;
 	qpd->is_debug = false;
@@ -1110,7 +1110,7 @@ static void destroy_kernel_queue_cpsch(struct device_queue_manager *dqm,
 	dqm->total_queue_count--;
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 }
 
 static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
@@ -1121,7 +1121,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 	retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (dqm->total_queue_count >= max_num_of_queues_per_device) {
 		pr_warn("Can't create new usermode queue because %d queues were already created\n",
@@ -1188,7 +1188,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 
 out_deallocate_doorbell:
@@ -1197,7 +1197,8 @@ out_deallocate_sdma_queue:
 	if (q->properties.type == KFD_QUEUE_TYPE_SDMA)
 		deallocate_sdma_queue(dqm, q->sdma_id);
 out_unlock:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
+
 	return retval;
 }
 
@@ -1314,7 +1315,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 	retval = 0;
 
 	/* remove queue from list to prevent rescheduling after preemption */
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (qpd->is_debug) {
 		/*
@@ -1360,14 +1361,14 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 
 	return retval;
 
 failed:
 failed_try_destroy_debugged_queue:
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1391,7 +1392,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 	if (!dqm->asic_ops.set_cache_memory_policy)
 		return retval;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	if (alternate_aperture_size == 0) {
 		/* base > limit disables APE1 */
@@ -1437,7 +1438,7 @@ static bool set_cache_memory_policy(struct device_queue_manager *dqm,
 		qpd->sh_mem_ape1_limit);
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1468,7 +1469,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 	struct device_process_node *cur, *next_dpn;
 	int retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	/* Clear all user mode queues */
 	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
@@ -1489,7 +1490,7 @@ static int process_termination_nocpsch(struct device_queue_manager *dqm,
 		}
 	}
 
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
@@ -1507,7 +1508,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 
 	retval = 0;
 
-	mutex_lock(&dqm->lock);
+	dqm_lock(dqm);
 
 	/* Clean all kernel queues */
 	list_for_each_entry_safe(kq, kq_next, &qpd->priv_queue_list, list) {
@@ -1562,7 +1563,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	}
 
 out:
-	mutex_unlock(&dqm->lock);
+	dqm_unlock(dqm);
 	return retval;
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 59a6b1956932..0a23ddac345e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -26,6 +26,8 @@
 
 #include <linux/rwsem.h>
 #include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/sched/mm.h>
 #include "kfd_priv.h"
 #include "kfd_mqd_manager.h"
 
@@ -173,8 +175,9 @@ struct device_queue_manager {
 	struct mqd_manager	*mqds[KFD_MQD_TYPE_MAX];
 	struct packet_manager	packets;
 	struct kfd_dev		*dev;
-	struct mutex		lock;
+	struct mutex		lock_hidden; /* use dqm_lock/unlock(dqm) */
 	struct list_head	queues;
+	unsigned int		saved_flags;
 	unsigned int		processes_count;
 	unsigned int		queue_count;
 	unsigned int		sdma_queue_count;
@@ -219,4 +222,19 @@ get_sh_mem_bases_nybble_64(struct kfd_process_device *pdd)
 	return (pdd->lds_base >> 60) & 0x0E;
 }
 
+/* The DQM lock can be taken in MMU notifiers. Make sure no reclaim-FS
+ * happens while holding this lock anywhere to prevent deadlocks when
+ * an MMU notifier runs in reclaim-FS context.
+ */
+static inline void dqm_lock(struct device_queue_manager *dqm)
+{
+	mutex_lock(&dqm->lock_hidden);
+	dqm->saved_flags = memalloc_nofs_save();
+}
+static inline void dqm_unlock(struct device_queue_manager *dqm)
+{
+	memalloc_nofs_restore(dqm->saved_flags);
+	mutex_unlock(&dqm->lock_hidden);
+}
+
 #endif /* KFD_DEVICE_QUEUE_MANAGER_H_ */
-- 
cgit v1.2.3


From 1cd106ecfc1f048db3795cc6aed8acb156ba6d4d Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Wed, 11 Jul 2018 22:32:45 -0400
Subject: drm/amdkfd: Stop using GFP_NOIO explicitly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is no longer needed with the memalloc_nofs_save/restore in
dqm_lock/unlock.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c          | 4 ++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c | 2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c  | 4 ++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c  | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 7ee6cec2c060..48c505e83217 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -739,8 +739,8 @@ int kfd_gtt_sa_allocate(struct kfd_dev *kfd, unsigned int size,
 	if (size > kfd->gtt_sa_num_of_chunks * kfd->gtt_sa_chunk_size)
 		return -ENOMEM;
 
-	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
-	if ((*mem_obj) == NULL)
+	*mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
+	if (!(*mem_obj))
 		return -ENOMEM;
 
 	pr_debug("Allocated mem_obj = %p for size = %d\n", *mem_obj, size);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index 06eaa218eba6..4872574f7a04 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -408,7 +408,7 @@ struct mqd_manager *mqd_manager_init_cik(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index 684054ff02cd..ad5c9f80cccd 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -55,7 +55,7 @@ static int init_mqd(struct mqd_manager *mm, void **mqd,
 	 * instead of sub-allocation function.
 	 */
 	if (kfd->cwsr_enabled && (q->type == KFD_QUEUE_TYPE_COMPUTE)) {
-		*mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_NOIO);
+		*mqd_mem_obj = kzalloc(sizeof(struct kfd_mem_obj), GFP_KERNEL);
 		if (!*mqd_mem_obj)
 			return -ENOMEM;
 		retval = kfd->kfd2kgd->init_gtt_mem_allocation(kfd->kgd,
@@ -393,7 +393,7 @@ struct mqd_manager *mqd_manager_init_v9(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 481307b8b4db..89e4242e43e7 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -394,7 +394,7 @@ struct mqd_manager *mqd_manager_init_vi(enum KFD_MQD_TYPE type,
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
-	mqd = kzalloc(sizeof(*mqd), GFP_NOIO);
+	mqd = kzalloc(sizeof(*mqd), GFP_KERNEL);
 	if (!mqd)
 		return NULL;
 
-- 
cgit v1.2.3


From a60d811b2bf45f2e776e00d71f0dc3c5043245d9 Mon Sep 17 00:00:00 2001
From: Jay Cornwall <Jay.Cornwall@amd.com>
Date: Wed, 11 Jul 2018 22:32:46 -0400
Subject: drm/amdkfd: Fix race between scheduler and context restore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The scheduler may raise SQ_WAVE_STATUS.SPI_PRIO via SQ_CMD before
context restore has completed. Restoring SPI_PRIO=0 after this point
may cause context save to fail as the lower priority wavefronts
are not selected for execution among spin-waiting wavefronts.

Leave SPI_PRIO at its SPI-initialized or scheduler-raised value.

v2: Also fix race with exception handler

Signed-off-by: Jay Cornwall <Jay.Cornwall@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h     | 458 +++++++++++----------
 .../gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm  |  18 +-
 .../gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm  |  16 +-
 3 files changed, 262 insertions(+), 230 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
index f68aef02fc1f..3621efbd5759 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler.h
@@ -21,18 +21,21 @@
  */
 
 static const uint32_t cwsr_trap_gfx8_hex[] = {
-	0xbf820001, 0xbf820125,
+	0xbf820001, 0xbf82012b,
 	0xb8f4f802, 0x89748674,
 	0xb8f5f803, 0x8675ff75,
-	0x00000400, 0xbf850011,
+	0x00000400, 0xbf850017,
 	0xc00a1e37, 0x00000000,
 	0xbf8c007f, 0x87777978,
-	0xbf840002, 0xb974f802,
-	0xbe801d78, 0xb8f5f803,
-	0x8675ff75, 0x000001ff,
-	0xbf850002, 0x80708470,
-	0x82718071, 0x8671ff71,
-	0x0000ffff, 0xb974f802,
+	0xbf840005, 0x8f728374,
+	0xb972e0c2, 0xbf800002,
+	0xb9740002, 0xbe801d78,
+	0xb8f5f803, 0x8675ff75,
+	0x000001ff, 0xbf850002,
+	0x80708470, 0x82718071,
+	0x8671ff71, 0x0000ffff,
+	0x8f728374, 0xb972e0c2,
+	0xbf800002, 0xb9740002,
 	0xbe801f70, 0xb8f5f803,
 	0x8675ff75, 0x00000100,
 	0xbf840006, 0xbefa0080,
@@ -168,7 +171,7 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 	0x807c847c, 0x806eff6e,
 	0x00000400, 0xbf0a757c,
 	0xbf85ffef, 0xbf9c0000,
-	0xbf8200ca, 0xbef8007e,
+	0xbf8200cd, 0xbef8007e,
 	0x8679ff7f, 0x0000ffff,
 	0x8779ff79, 0x00040000,
 	0xbefa0080, 0xbefb00ff,
@@ -268,16 +271,18 @@ static const uint32_t cwsr_trap_gfx8_hex[] = {
 	0x8f739773, 0xb976f807,
 	0x8671ff71, 0x0000ffff,
 	0x86fe7e7e, 0x86ea6a6a,
-	0xb974f802, 0xbf8a0000,
-	0x95807370, 0xbf810000,
+	0x8f768374, 0xb976e0c2,
+	0xbf800002, 0xb9740002,
+	0xbf8a0000, 0x95807370,
+	0xbf810000, 0x00000000,
 };
 
 
 static const uint32_t cwsr_trap_gfx9_hex[] = {
-	0xbf820001, 0xbf82015a,
+	0xbf820001, 0xbf82015d,
 	0xb8f8f802, 0x89788678,
 	0xb8f1f803, 0x866eff71,
-	0x00000400, 0xbf850034,
+	0x00000400, 0xbf850037,
 	0x866eff71, 0x00000800,
 	0xbf850003, 0x866eff71,
 	0x00000100, 0xbf840008,
@@ -303,258 +308,261 @@ static const uint32_t cwsr_trap_gfx9_hex[] = {
 	0x8f6e8b77, 0x866eff6e,
 	0x001f8000, 0xb96ef807,
 	0x86fe7e7e, 0x86ea6a6a,
-	0xb978f802, 0xbe801f6c,
-	0x866dff6d, 0x0000ffff,
-	0xbef00080, 0xb9700283,
-	0xb8f02407, 0x8e709c70,
-	0x876d706d, 0xb8f003c7,
-	0x8e709b70, 0x876d706d,
-	0xb8f0f807, 0x8670ff70,
-	0x00007fff, 0xb970f807,
-	0xbeee007e, 0xbeef007f,
-	0xbefe0180, 0xbf900004,
-	0x87708478, 0xb970f802,
-	0xbf8e0002, 0xbf88fffe,
-	0xb8f02a05, 0x80708170,
-	0x8e708a70, 0xb8f11605,
-	0x80718171, 0x8e718671,
-	0x80707170, 0x80707e70,
-	0x8271807f, 0x8671ff71,
-	0x0000ffff, 0xc0471cb8,
-	0x00000040, 0xbf8cc07f,
-	0xc04b1d38, 0x00000048,
-	0xbf8cc07f, 0xc0431e78,
-	0x00000058, 0xbf8cc07f,
-	0xc0471eb8, 0x0000005c,
-	0xbf8cc07f, 0xbef4007e,
-	0x8675ff7f, 0x0000ffff,
-	0x8775ff75, 0x00040000,
-	0xbef60080, 0xbef700ff,
-	0x00807fac, 0x8670ff7f,
-	0x08000000, 0x8f708370,
-	0x87777077, 0x8670ff7f,
-	0x70000000, 0x8f708170,
-	0x87777077, 0xbefb007c,
-	0xbefa0080, 0xb8fa2a05,
-	0x807a817a, 0x8e7a8a7a,
-	0xb8f01605, 0x80708170,
-	0x8e708670, 0x807a707a,
-	0xbef60084, 0xbef600ff,
-	0x01000000, 0xbefe007c,
-	0xbefc007a, 0xc0611efa,
-	0x0000007c, 0xbf8cc07f,
-	0x807a847a, 0xbefc007e,
+	0x8f6e8378, 0xb96ee0c2,
+	0xbf800002, 0xb9780002,
+	0xbe801f6c, 0x866dff6d,
+	0x0000ffff, 0xbef00080,
+	0xb9700283, 0xb8f02407,
+	0x8e709c70, 0x876d706d,
+	0xb8f003c7, 0x8e709b70,
+	0x876d706d, 0xb8f0f807,
+	0x8670ff70, 0x00007fff,
+	0xb970f807, 0xbeee007e,
+	0xbeef007f, 0xbefe0180,
+	0xbf900004, 0x87708478,
+	0xb970f802, 0xbf8e0002,
+	0xbf88fffe, 0xb8f02a05,
+	0x80708170, 0x8e708a70,
+	0xb8f11605, 0x80718171,
+	0x8e718671, 0x80707170,
+	0x80707e70, 0x8271807f,
+	0x8671ff71, 0x0000ffff,
+	0xc0471cb8, 0x00000040,
+	0xbf8cc07f, 0xc04b1d38,
+	0x00000048, 0xbf8cc07f,
+	0xc0431e78, 0x00000058,
+	0xbf8cc07f, 0xc0471eb8,
+	0x0000005c, 0xbf8cc07f,
+	0xbef4007e, 0x8675ff7f,
+	0x0000ffff, 0x8775ff75,
+	0x00040000, 0xbef60080,
+	0xbef700ff, 0x00807fac,
+	0x8670ff7f, 0x08000000,
+	0x8f708370, 0x87777077,
+	0x8670ff7f, 0x70000000,
+	0x8f708170, 0x87777077,
+	0xbefb007c, 0xbefa0080,
+	0xb8fa2a05, 0x807a817a,
+	0x8e7a8a7a, 0xb8f01605,
+	0x80708170, 0x8e708670,
+	0x807a707a, 0xbef60084,
+	0xbef600ff, 0x01000000,
 	0xbefe007c, 0xbefc007a,
-	0xc0611b3a, 0x0000007c,
+	0xc0611efa, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611b7a,
+	0xbefc007a, 0xc0611b3a,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611bba, 0x0000007c,
+	0xc0611b7a, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611bfa,
+	0xbefc007a, 0xc0611bba,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611e3a, 0x0000007c,
-	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0xb8f1f803,
-	0xbefe007c, 0xbefc007a,
-	0xc0611c7a, 0x0000007c,
+	0xc0611bfa, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
 	0xbefc007e, 0xbefe007c,
-	0xbefc007a, 0xc0611a3a,
+	0xbefc007a, 0xc0611e3a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xb8f1f803, 0xbefe007c,
+	0xbefc007a, 0xc0611c7a,
 	0x0000007c, 0xbf8cc07f,
 	0x807a847a, 0xbefc007e,
 	0xbefe007c, 0xbefc007a,
-	0xc0611a7a, 0x0000007c,
-	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0xb8fbf801,
-	0xbefe007c, 0xbefc007a,
-	0xc0611efa, 0x0000007c,
+	0xc0611a3a, 0x0000007c,
 	0xbf8cc07f, 0x807a847a,
-	0xbefc007e, 0x8670ff7f,
-	0x04000000, 0xbeef0080,
-	0x876f6f70, 0xb8fa2a05,
+	0xbefc007e, 0xbefe007c,
+	0xbefc007a, 0xc0611a7a,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0xb8fbf801, 0xbefe007c,
+	0xbefc007a, 0xc0611efa,
+	0x0000007c, 0xbf8cc07f,
+	0x807a847a, 0xbefc007e,
+	0x8670ff7f, 0x04000000,
+	0xbeef0080, 0x876f6f70,
+	0xb8fa2a05, 0x807a817a,
+	0x8e7a8a7a, 0xb8f11605,
+	0x80718171, 0x8e718471,
+	0x8e768271, 0xbef600ff,
+	0x01000000, 0xbef20174,
+	0x80747a74, 0x82758075,
+	0xbefc0080, 0xbf800000,
+	0xbe802b00, 0xbe822b02,
+	0xbe842b04, 0xbe862b06,
+	0xbe882b08, 0xbe8a2b0a,
+	0xbe8c2b0c, 0xbe8e2b0e,
+	0xc06b003a, 0x00000000,
+	0xbf8cc07f, 0xc06b013a,
+	0x00000010, 0xbf8cc07f,
+	0xc06b023a, 0x00000020,
+	0xbf8cc07f, 0xc06b033a,
+	0x00000030, 0xbf8cc07f,
+	0x8074c074, 0x82758075,
+	0x807c907c, 0xbf0a717c,
+	0xbf85ffe7, 0xbef40172,
+	0xbefa0080, 0xbefe00c1,
+	0xbeff00c1, 0xbee80080,
+	0xbee90080, 0xbef600ff,
+	0x01000000, 0xe0724000,
+	0x7a1d0000, 0xe0724100,
+	0x7a1d0100, 0xe0724200,
+	0x7a1d0200, 0xe0724300,
+	0x7a1d0300, 0xbefe00c1,
+	0xbeff00c1, 0xb8f14306,
+	0x8671c171, 0xbf84002c,
+	0xbf8a0000, 0x8670ff6f,
+	0x04000000, 0xbf840028,
+	0x8e718671, 0x8e718271,
+	0xbef60071, 0xb8fa2a05,
 	0x807a817a, 0x8e7a8a7a,
-	0xb8f11605, 0x80718171,
-	0x8e718471, 0x8e768271,
+	0xb8f01605, 0x80708170,
+	0x8e708670, 0x807a707a,
+	0x807aff7a, 0x00000080,
 	0xbef600ff, 0x01000000,
-	0xbef20174, 0x80747a74,
-	0x82758075, 0xbefc0080,
-	0xbf800000, 0xbe802b00,
-	0xbe822b02, 0xbe842b04,
-	0xbe862b06, 0xbe882b08,
-	0xbe8a2b0a, 0xbe8c2b0c,
-	0xbe8e2b0e, 0xc06b003a,
-	0x00000000, 0xbf8cc07f,
-	0xc06b013a, 0x00000010,
-	0xbf8cc07f, 0xc06b023a,
-	0x00000020, 0xbf8cc07f,
-	0xc06b033a, 0x00000030,
-	0xbf8cc07f, 0x8074c074,
-	0x82758075, 0x807c907c,
-	0xbf0a717c, 0xbf85ffe7,
-	0xbef40172, 0xbefa0080,
+	0xbefc0080, 0xd28c0002,
+	0x000100c1, 0xd28d0003,
+	0x000204c1, 0xd1060002,
+	0x00011103, 0x7e0602ff,
+	0x00000200, 0xbefc00ff,
+	0x00010000, 0xbe800077,
+	0x8677ff77, 0xff7fffff,
+	0x8777ff77, 0x00058000,
+	0xd8ec0000, 0x00000002,
+	0xbf8cc07f, 0xe0765000,
+	0x7a1d0002, 0x68040702,
+	0xd0c9006a, 0x0000e302,
+	0xbf87fff7, 0xbef70000,
+	0xbefa00ff, 0x00000400,
 	0xbefe00c1, 0xbeff00c1,
-	0xbee80080, 0xbee90080,
+	0xb8f12a05, 0x80718171,
+	0x8e718271, 0x8e768871,
 	0xbef600ff, 0x01000000,
+	0xbefc0084, 0xbf0a717c,
+	0xbf840015, 0xbf11017c,
+	0x8071ff71, 0x00001000,
+	0x7e000300, 0x7e020301,
+	0x7e040302, 0x7e060303,
 	0xe0724000, 0x7a1d0000,
 	0xe0724100, 0x7a1d0100,
 	0xe0724200, 0x7a1d0200,
 	0xe0724300, 0x7a1d0300,
+	0x807c847c, 0x807aff7a,
+	0x00000400, 0xbf0a717c,
+	0xbf85ffef, 0xbf9c0000,
+	0xbf8200dc, 0xbef4007e,
+	0x8675ff7f, 0x0000ffff,
+	0x8775ff75, 0x00040000,
+	0xbef60080, 0xbef700ff,
+	0x00807fac, 0x866eff7f,
+	0x08000000, 0x8f6e836e,
+	0x87776e77, 0x866eff7f,
+	0x70000000, 0x8f6e816e,
+	0x87776e77, 0x866eff7f,
+	0x04000000, 0xbf84001e,
 	0xbefe00c1, 0xbeff00c1,
-	0xb8f14306, 0x8671c171,
-	0xbf84002c, 0xbf8a0000,
-	0x8670ff6f, 0x04000000,
-	0xbf840028, 0x8e718671,
-	0x8e718271, 0xbef60071,
-	0xb8fa2a05, 0x807a817a,
-	0x8e7a8a7a, 0xb8f01605,
-	0x80708170, 0x8e708670,
-	0x807a707a, 0x807aff7a,
+	0xb8ef4306, 0x866fc16f,
+	0xbf840019, 0x8e6f866f,
+	0x8e6f826f, 0xbef6006f,
+	0xb8f82a05, 0x80788178,
+	0x8e788a78, 0xb8ee1605,
+	0x806e816e, 0x8e6e866e,
+	0x80786e78, 0x8078ff78,
 	0x00000080, 0xbef600ff,
 	0x01000000, 0xbefc0080,
-	0xd28c0002, 0x000100c1,
-	0xd28d0003, 0x000204c1,
-	0xd1060002, 0x00011103,
-	0x7e0602ff, 0x00000200,
-	0xbefc00ff, 0x00010000,
-	0xbe800077, 0x8677ff77,
-	0xff7fffff, 0x8777ff77,
-	0x00058000, 0xd8ec0000,
-	0x00000002, 0xbf8cc07f,
-	0xe0765000, 0x7a1d0002,
-	0x68040702, 0xd0c9006a,
-	0x0000e302, 0xbf87fff7,
-	0xbef70000, 0xbefa00ff,
-	0x00000400, 0xbefe00c1,
-	0xbeff00c1, 0xb8f12a05,
-	0x80718171, 0x8e718271,
-	0x8e768871, 0xbef600ff,
-	0x01000000, 0xbefc0084,
-	0xbf0a717c, 0xbf840015,
-	0xbf11017c, 0x8071ff71,
-	0x00001000, 0x7e000300,
+	0xe0510000, 0x781d0000,
+	0xe0510100, 0x781d0000,
+	0x807cff7c, 0x00000200,
+	0x8078ff78, 0x00000200,
+	0xbf0a6f7c, 0xbf85fff6,
+	0xbef80080, 0xbefe00c1,
+	0xbeff00c1, 0xb8ef2a05,
+	0x806f816f, 0x8e6f826f,
+	0x8e76886f, 0xbef600ff,
+	0x01000000, 0xbeee0078,
+	0x8078ff78, 0x00000400,
+	0xbefc0084, 0xbf11087c,
+	0x806fff6f, 0x00008000,
+	0xe0524000, 0x781d0000,
+	0xe0524100, 0x781d0100,
+	0xe0524200, 0x781d0200,
+	0xe0524300, 0x781d0300,
+	0xbf8c0f70, 0x7e000300,
 	0x7e020301, 0x7e040302,
-	0x7e060303, 0xe0724000,
-	0x7a1d0000, 0xe0724100,
-	0x7a1d0100, 0xe0724200,
-	0x7a1d0200, 0xe0724300,
-	0x7a1d0300, 0x807c847c,
-	0x807aff7a, 0x00000400,
-	0xbf0a717c, 0xbf85ffef,
-	0xbf9c0000, 0xbf8200d9,
-	0xbef4007e, 0x8675ff7f,
-	0x0000ffff, 0x8775ff75,
-	0x00040000, 0xbef60080,
-	0xbef700ff, 0x00807fac,
-	0x866eff7f, 0x08000000,
-	0x8f6e836e, 0x87776e77,
-	0x866eff7f, 0x70000000,
-	0x8f6e816e, 0x87776e77,
-	0x866eff7f, 0x04000000,
-	0xbf84001e, 0xbefe00c1,
-	0xbeff00c1, 0xb8ef4306,
-	0x866fc16f, 0xbf840019,
-	0x8e6f866f, 0x8e6f826f,
-	0xbef6006f, 0xb8f82a05,
+	0x7e060303, 0x807c847c,
+	0x8078ff78, 0x00000400,
+	0xbf0a6f7c, 0xbf85ffee,
+	0xbf9c0000, 0xe0524000,
+	0x6e1d0000, 0xe0524100,
+	0x6e1d0100, 0xe0524200,
+	0x6e1d0200, 0xe0524300,
+	0x6e1d0300, 0xb8f82a05,
 	0x80788178, 0x8e788a78,
 	0xb8ee1605, 0x806e816e,
 	0x8e6e866e, 0x80786e78,
-	0x8078ff78, 0x00000080,
-	0xbef600ff, 0x01000000,
-	0xbefc0080, 0xe0510000,
-	0x781d0000, 0xe0510100,
-	0x781d0000, 0x807cff7c,
-	0x00000200, 0x8078ff78,
-	0x00000200, 0xbf0a6f7c,
-	0xbf85fff6, 0xbef80080,
-	0xbefe00c1, 0xbeff00c1,
-	0xb8ef2a05, 0x806f816f,
-	0x8e6f826f, 0x8e76886f,
-	0xbef600ff, 0x01000000,
-	0xbeee0078, 0x8078ff78,
-	0x00000400, 0xbefc0084,
-	0xbf11087c, 0x806fff6f,
-	0x00008000, 0xe0524000,
-	0x781d0000, 0xe0524100,
-	0x781d0100, 0xe0524200,
-	0x781d0200, 0xe0524300,
-	0x781d0300, 0xbf8c0f70,
-	0x7e000300, 0x7e020301,
-	0x7e040302, 0x7e060303,
-	0x807c847c, 0x8078ff78,
-	0x00000400, 0xbf0a6f7c,
-	0xbf85ffee, 0xbf9c0000,
-	0xe0524000, 0x6e1d0000,
-	0xe0524100, 0x6e1d0100,
-	0xe0524200, 0x6e1d0200,
-	0xe0524300, 0x6e1d0300,
+	0x80f8c078, 0xb8ef1605,
+	0x806f816f, 0x8e6f846f,
+	0x8e76826f, 0xbef600ff,
+	0x01000000, 0xbefc006f,
+	0xc031003a, 0x00000078,
+	0x80f8c078, 0xbf8cc07f,
+	0x80fc907c, 0xbf800000,
+	0xbe802d00, 0xbe822d02,
+	0xbe842d04, 0xbe862d06,
+	0xbe882d08, 0xbe8a2d0a,
+	0xbe8c2d0c, 0xbe8e2d0e,
+	0xbf06807c, 0xbf84fff0,
 	0xb8f82a05, 0x80788178,
 	0x8e788a78, 0xb8ee1605,
 	0x806e816e, 0x8e6e866e,
-	0x80786e78, 0x80f8c078,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f846f, 0x8e76826f,
+	0x80786e78, 0xbef60084,
 	0xbef600ff, 0x01000000,
-	0xbefc006f, 0xc031003a,
-	0x00000078, 0x80f8c078,
-	0xbf8cc07f, 0x80fc907c,
-	0xbf800000, 0xbe802d00,
-	0xbe822d02, 0xbe842d04,
-	0xbe862d06, 0xbe882d08,
-	0xbe8a2d0a, 0xbe8c2d0c,
-	0xbe8e2d0e, 0xbf06807c,
-	0xbf84fff0, 0xb8f82a05,
-	0x80788178, 0x8e788a78,
-	0xb8ee1605, 0x806e816e,
-	0x8e6e866e, 0x80786e78,
-	0xbef60084, 0xbef600ff,
-	0x01000000, 0xc0211bfa,
+	0xc0211bfa, 0x00000078,
+	0x80788478, 0xc0211b3a,
 	0x00000078, 0x80788478,
-	0xc0211b3a, 0x00000078,
-	0x80788478, 0xc0211b7a,
+	0xc0211b7a, 0x00000078,
+	0x80788478, 0xc0211eba,
 	0x00000078, 0x80788478,
-	0xc0211eba, 0x00000078,
-	0x80788478, 0xc0211efa,
+	0xc0211efa, 0x00000078,
+	0x80788478, 0xc0211c3a,
 	0x00000078, 0x80788478,
-	0xc0211c3a, 0x00000078,
-	0x80788478, 0xc0211c7a,
+	0xc0211c7a, 0x00000078,
+	0x80788478, 0xc0211a3a,
 	0x00000078, 0x80788478,
-	0xc0211a3a, 0x00000078,
-	0x80788478, 0xc0211a7a,
+	0xc0211a7a, 0x00000078,
+	0x80788478, 0xc0211cfa,
 	0x00000078, 0x80788478,
-	0xc0211cfa, 0x00000078,
-	0x80788478, 0xbf8cc07f,
-	0xbefc006f, 0xbefe007a,
-	0xbeff007b, 0x866f71ff,
-	0x000003ff, 0xb96f4803,
-	0x866f71ff, 0xfffff800,
-	0x8f6f8b6f, 0xb96fa2c3,
-	0xb973f801, 0xb8ee2a05,
-	0x806e816e, 0x8e6e8a6e,
-	0xb8ef1605, 0x806f816f,
-	0x8e6f866f, 0x806e6f6e,
-	0x806e746e, 0x826f8075,
-	0x866fff6f, 0x0000ffff,
-	0xc0071cb7, 0x00000040,
-	0xc00b1d37, 0x00000048,
-	0xc0031e77, 0x00000058,
-	0xc0071eb7, 0x0000005c,
-	0xbf8cc07f, 0x866fff6d,
-	0xf0000000, 0x8f6f9c6f,
-	0x8e6f906f, 0xbeee0080,
-	0x876e6f6e, 0x866fff6d,
-	0x08000000, 0x8f6f9b6f,
-	0x8e6f8f6f, 0x876e6f6e,
-	0x866fff70, 0x00800000,
-	0x8f6f976f, 0xb96ef807,
-	0x866dff6d, 0x0000ffff,
-	0x86fe7e7e, 0x86ea6a6a,
-	0xb970f802, 0xbf8a0000,
+	0xbf8cc07f, 0xbefc006f,
+	0xbefe007a, 0xbeff007b,
+	0x866f71ff, 0x000003ff,
+	0xb96f4803, 0x866f71ff,
+	0xfffff800, 0x8f6f8b6f,
+	0xb96fa2c3, 0xb973f801,
+	0xb8ee2a05, 0x806e816e,
+	0x8e6e8a6e, 0xb8ef1605,
+	0x806f816f, 0x8e6f866f,
+	0x806e6f6e, 0x806e746e,
+	0x826f8075, 0x866fff6f,
+	0x0000ffff, 0xc0071cb7,
+	0x00000040, 0xc00b1d37,
+	0x00000048, 0xc0031e77,
+	0x00000058, 0xc0071eb7,
+	0x0000005c, 0xbf8cc07f,
+	0x866fff6d, 0xf0000000,
+	0x8f6f9c6f, 0x8e6f906f,
+	0xbeee0080, 0x876e6f6e,
+	0x866fff6d, 0x08000000,
+	0x8f6f9b6f, 0x8e6f8f6f,
+	0x876e6f6e, 0x866fff70,
+	0x00800000, 0x8f6f976f,
+	0xb96ef807, 0x866dff6d,
+	0x0000ffff, 0x86fe7e7e,
+	0x86ea6a6a, 0x8f6e8370,
+	0xb96ee0c2, 0xbf800002,
+	0xb9700002, 0xbf8a0000,
 	0x95806f6c, 0xbf810000,
 };
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
index a2a04bb64096..abe1a5da29fb 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx8.asm
@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_SHIFT  = 23
 var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT    = 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE     = 9
@@ -251,7 +255,7 @@ if (!EMU_RUN_HACK)
     s_waitcnt lgkmcnt(0)
     s_or_b32        ttmp7, ttmp8, ttmp9
     s_cbranch_scc0  L_NO_NEXT_TRAP //next level trap handler not been set
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_setpc_b64     [ttmp8,ttmp9] //jump to next level trap handler
 
 L_NO_NEXT_TRAP:
@@ -262,7 +266,7 @@ L_NO_NEXT_TRAP:
     s_addc_u32  ttmp1, ttmp1, 0
 L_EXCP_CASE:
     s_and_b32   ttmp1, ttmp1, 0xFFFF
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status //restore HW status(SCC)
+    set_status_without_spi_prio(s_save_status, ttmp2) //restore HW status(SCC)
     s_rfe_b64       [ttmp0, ttmp1]
 end
     // *********        End handling of non-CWSR traps   *******************
@@ -1053,7 +1057,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff      //pc[47:32]        //Do it here in order not to affect STATUS
     s_and_b64    exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64    vcc, vcc, vcc  // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status     // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier                                                   //barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1134,3 +1138,11 @@ end
 function get_hwreg_size_bytes
     return 128 //HWREG size 128 bytes
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end
diff --git a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
index 998be96be736..0bb9c577b3a2 100644
--- a/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
+++ b/drivers/gpu/drm/amd/amdkfd/cwsr_trap_handler_gfx9.asm
@@ -103,6 +103,10 @@ var SQ_WAVE_STATUS_INST_ATC_MASK   = 0x00800000
 var SQ_WAVE_STATUS_SPI_PRIO_SHIFT  = 1
 var SQ_WAVE_STATUS_SPI_PRIO_MASK   = 0x00000006
 var SQ_WAVE_STATUS_HALT_MASK       = 0x2000
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT   = 0
+var SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE    = 1
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT  = 3
+var SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE   = 29
 
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SHIFT	= 12
 var SQ_WAVE_LDS_ALLOC_LDS_SIZE_SIZE	= 9
@@ -317,7 +321,7 @@ L_EXCP_CASE:
     // Restore SQ_WAVE_STATUS.
     s_and_b64       exec, exec, exec // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64       vcc, vcc, vcc    // Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS), s_save_status
+    set_status_without_spi_prio(s_save_status, ttmp2)
 
     s_rfe_b64       [ttmp0, ttmp1]
 end
@@ -1120,7 +1124,7 @@ end
     s_and_b32 s_restore_pc_hi, s_restore_pc_hi, 0x0000ffff	//pc[47:32]	   //Do it here in order not to affect STATUS
     s_and_b64	 exec, exec, exec  // Restore STATUS.EXECZ, not writable by s_setreg_b32
     s_and_b64	 vcc, vcc, vcc	// Restore STATUS.VCCZ, not writable by s_setreg_b32
-    s_setreg_b32    hwreg(HW_REG_STATUS),   s_restore_status	 // SCC is included, which is changed by previous salu
+    set_status_without_spi_prio(s_restore_status, s_restore_tmp) // SCC is included, which is changed by previous salu
 
     s_barrier							//barrier to ensure the readiness of LDS before access attempts from any other wave in the same TG //FIXME not performance-optimal at this time
 
@@ -1212,3 +1216,11 @@ function ack_sqc_store_workaround
         s_waitcnt lgkmcnt(0)
     end
 end
+
+function set_status_without_spi_prio(status, tmp)
+    // Do not restore STATUS.SPI_PRIO since scheduler may have raised it.
+    s_lshr_b32      tmp, status, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_POST_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_POST_SPI_PRIO_SIZE), tmp
+    s_nop           0x2 // avoid S_SETREG => S_SETREG hazard
+    s_setreg_b32    hwreg(HW_REG_STATUS, SQ_WAVE_STATUS_PRE_SPI_PRIO_SHIFT, SQ_WAVE_STATUS_PRE_SPI_PRIO_SIZE), status
+end
-- 
cgit v1.2.3


From e47cb828eb3fca3e8999a0b9aa053dda18552071 Mon Sep 17 00:00:00 2001
From: Wei Lu <wei.lu2@amd.com>
Date: Wed, 11 Jul 2018 22:32:47 -0400
Subject: drm/amdkfd: Fix error codes in kfd_get_process
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return ERR_PTR(-EINVAL) if kfd_get_process fails to find the process.
This fixes kernel oopses when a child process calls KFD ioctls with
a file descriptor inherited from the parent process.

Signed-off-by: Wei Lu <wei.lu2@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_process.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process.c b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
index 1d80b4f7c681..4694386cc623 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process.c
@@ -244,6 +244,8 @@ struct kfd_process *kfd_get_process(const struct task_struct *thread)
 		return ERR_PTR(-EINVAL);
 
 	process = find_process(thread);
+	if (!process)
+		return ERR_PTR(-EINVAL);
 
 	return process;
 }
-- 
cgit v1.2.3


From 101fee63cbb0a3df9e54aaafbfad0ab5821a34e6 Mon Sep 17 00:00:00 2001
From: Moses Reuben <moses.reuben@amd.com>
Date: Wed, 11 Jul 2018 22:32:48 -0400
Subject: drm/amdkfd: send SIGSEGV to process upon KFD_EVENT_TYPE_MEMORY
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Moses Reuben <moses.reuben@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_events.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 5562e94e786a..3d5a8332e8c0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -850,6 +850,13 @@ static void lookup_events_by_type_and_signal(struct kfd_process *p,
 				ev->memory_exception_data = *ev_data;
 		}
 
+	if (type == KFD_EVENT_TYPE_MEMORY) {
+		dev_warn(kfd_device,
+			"Sending SIGSEGV to HSA Process with PID %d ",
+				p->lead_thread->pid);
+		send_sig(SIGSEGV, p->lead_thread, 0);
+	}
+
 	/* Send SIGTERM no event of type "type" has been found*/
 	if (send_signal) {
 		if (send_sigterm) {
-- 
cgit v1.2.3


From b97dfa27ef3ad3eddd2cb97a3b6a140d7037827a Mon Sep 17 00:00:00 2001
From: shaoyunl <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:49 -0400
Subject: drm/amdgpu: save vm fault information for amdkfd
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

amdgpu save the vm fault related information for KFD usage and keep the
copy until KFD read it.

Signed-off-by: shaoyun liu <shaoyun.liu@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h        |  3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c  | 14 ++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h           |  2 ++
 drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c             | 33 ++++++++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c             | 33 ++++++++++++++++++++++-
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h   | 20 ++++++++++++++
 8 files changed, 105 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index a8418a3f4e9d..3dc76d9b4d12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -183,6 +183,9 @@ int amdgpu_amdkfd_gpuvm_map_gtt_bo_to_kernel(struct kgd_dev *kgd,
 int amdgpu_amdkfd_gpuvm_restore_process_bos(void *process_info,
 					    struct dma_fence **ef);
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *info);
+
 void amdgpu_amdkfd_gpuvm_init_mem_limits(void);
 void amdgpu_amdkfd_unreserve_system_memory_limit(struct amdgpu_bo *bo);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index ea79908dac4c..befc7c48b1cf 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -216,6 +216,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 19dd665e7307..c68ef85f7753 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -176,6 +176,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index fa38a960ce00..8a707d8bbb1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1621,6 +1621,20 @@ bo_reserve_failed:
 	return ret;
 }
 
+int amdgpu_amdkfd_gpuvm_get_vm_fault_info(struct kgd_dev *kgd,
+					      struct kfd_vm_fault_info *mem)
+{
+	struct amdgpu_device *adev;
+
+	adev = (struct amdgpu_device *)kgd;
+	if (atomic_read(&adev->gmc.vm_fault_info_updated) == 1) {
+		*mem = *adev->gmc.vm_fault_info;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+	}
+	return 0;
+}
+
 /* Evict a userptr BO by stopping the queues if necessary
  *
  * Runs in MMU notifier, may be in RECLAIM_FS context. This means it
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
index 6cb4948233cb..bb5a47a45790 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h
@@ -105,6 +105,8 @@ struct amdgpu_gmc {
 	/* protects concurrent invalidation */
 	spinlock_t		invalidate_lock;
 	bool			translate_further;
+	struct kfd_vm_fault_info *vm_fault_info;
+	atomic_t		vm_fault_info_updated;
 
 	const struct amdgpu_gmc_funcs	*gmc_funcs;
 };
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 10920f0bd85f..36dc367c4b45 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -28,6 +28,7 @@
 #include "cik.h"
 #include "gmc_v7_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "bif/bif_4_1_d.h"
 #include "bif/bif_4_1_sh_mask.h"
@@ -1078,6 +1079,12 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1087,6 +1094,7 @@ static int gmc_v7_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v7_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1276,7 +1284,7 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	addr = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_ADDR);
 	status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
@@ -1301,6 +1309,29 @@ static int gmc_v7_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index 75f3ffb2891e..70fc97b59b4f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -26,6 +26,7 @@
 #include "amdgpu.h"
 #include "gmc_v8_0.h"
 #include "amdgpu_ucode.h"
+#include "amdgpu_amdkfd.h"
 
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
@@ -1182,6 +1183,12 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->vm_manager.vram_base_offset = 0;
 	}
 
+	adev->gmc.vm_fault_info = kmalloc(sizeof(struct kfd_vm_fault_info),
+					GFP_KERNEL);
+	if (!adev->gmc.vm_fault_info)
+		return -ENOMEM;
+	atomic_set(&adev->gmc.vm_fault_info_updated, 0);
+
 	return 0;
 }
 
@@ -1191,6 +1198,7 @@ static int gmc_v8_0_sw_fini(void *handle)
 
 	amdgpu_gem_force_release(adev);
 	amdgpu_vm_manager_fini(adev);
+	kfree(adev->gmc.vm_fault_info);
 	gmc_v8_0_gart_fini(adev);
 	amdgpu_bo_fini(adev);
 	release_firmware(adev->gmc.fw);
@@ -1426,7 +1434,7 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 				      struct amdgpu_irq_src *source,
 				      struct amdgpu_iv_entry *entry)
 {
-	u32 addr, status, mc_client;
+	u32 addr, status, mc_client, vmid;
 
 	if (amdgpu_sriov_vf(adev)) {
 		dev_err(adev->dev, "GPU fault detected: %d 0x%08x\n",
@@ -1463,6 +1471,29 @@ static int gmc_v8_0_process_interrupt(struct amdgpu_device *adev,
 					 entry->pasid);
 	}
 
+	vmid = REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+			     VMID);
+	if (amdgpu_amdkfd_is_kfd_vmid(adev, vmid)
+		&& !atomic_read(&adev->gmc.vm_fault_info_updated)) {
+		struct kfd_vm_fault_info *info = adev->gmc.vm_fault_info;
+		u32 protections = REG_GET_FIELD(status,
+					VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					PROTECTIONS);
+
+		info->vmid = vmid;
+		info->mc_id = REG_GET_FIELD(status,
+					    VM_CONTEXT1_PROTECTION_FAULT_STATUS,
+					    MEMORY_CLIENT_ID);
+		info->status = status;
+		info->page_addr = addr;
+		info->prot_valid = protections & 0x7 ? true : false;
+		info->prot_read = protections & 0x8 ? true : false;
+		info->prot_write = protections & 0x10 ? true : false;
+		info->prot_exec = protections & 0x20 ? true : false;
+		mb();
+		atomic_set(&adev->gmc.vm_fault_info_updated, 1);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 5733fbee07f7..28b11d105288 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -47,6 +47,17 @@ enum kfd_preempt_type {
 	KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 };
 
+struct kfd_vm_fault_info {
+	uint64_t	page_addr;
+	uint32_t	vmid;
+	uint32_t	mc_id;
+	uint32_t	status;
+	bool		prot_valid;
+	bool		prot_read;
+	bool		prot_write;
+	bool		prot_exec;
+};
+
 struct kfd_cu_info {
 	uint32_t num_shader_engines;
 	uint32_t num_shader_arrays_per_engine;
@@ -259,6 +270,12 @@ struct tile_config {
  * IB to the corresponding ring (ring type). The IB is executed with the
  * specified VMID in a user mode context.
  *
+ * @get_vm_fault_info: Return information about a recent VM fault on
+ * GFXv7 and v8. If multiple VM faults occurred since the last call of
+ * this function, it will return information about the first of those
+ * faults. On GFXv9 VM fault information is fully contained in the IH
+ * packet and this function is not needed.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -374,6 +391,9 @@ struct kfd2kgd_calls {
 	int (*submit_ib)(struct kgd_dev *kgd, enum kgd_engine_type engine,
 			uint32_t vmid, uint64_t gpu_addr,
 			uint32_t *ib_cmd, uint32_t ib_len);
+
+	int (*get_vm_fault_info)(struct kgd_dev *kgd,
+			struct kfd_vm_fault_info *info);
 };
 
 /**
-- 
cgit v1.2.3


From 2640c3facbd6e21e63c95f19588cc24913a263cd Mon Sep 17 00:00:00 2001
From: shaoyunl <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:50 -0400
Subject: drm/amdkfd: Handle VM faults in KFD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

1. Pre-GFX9 the amdgpu ISR saves the vm-fault status and address per
   per-vmid. amdkfd needs to get the information from amdgpu through the
   new get_vm_fault_info interface. On GFX9 and later, all the required
   information is in the IH ring
2. amdkfd unmaps all queues from the faulting process and create new
   run-list without the guilty process
3. amdkfd notifies the runtime of the vm fault trap via EVENT_TYPE_MEMORY

Signed-off-by: shaoyun liu <shaoyun.liu@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c   | 25 ++++++++++++---
 drivers/gpu/drm/amd/amdkfd/cik_int.h               |  2 ++
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 17 ++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_events.c            | 37 ++++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c    | 18 +++++++++--
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              |  4 +++
 include/uapi/linux/kfd_ioctl.h                     |  2 +-
 7 files changed, 98 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index 49df6c791cfc..cc33870e7edb 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -48,18 +48,19 @@ static bool cik_event_interrupt_isr(struct kfd_dev *dev,
 	return ihre->source_id == CIK_INTSRC_CP_END_OF_PIPE ||
 		ihre->source_id == CIK_INTSRC_SDMA_TRAP ||
 		ihre->source_id == CIK_INTSRC_SQ_INTERRUPT_MSG ||
-		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE;
+		ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE ||
+		ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT;
 }
 
 static void cik_event_interrupt_wq(struct kfd_dev *dev,
 					const uint32_t *ih_ring_entry)
 {
-	unsigned int pasid;
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
 	uint32_t context_id = ihre->data & 0xfffffff;
-
-	pasid = (ihre->ring_id & 0xffff0000) >> 16;
+	unsigned int vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
+	unsigned int pasid = (ihre->ring_id & 0xffff0000) >> 16;
 
 	if (pasid == 0)
 		return;
@@ -72,6 +73,22 @@ static void cik_event_interrupt_wq(struct kfd_dev *dev,
 		kfd_signal_event_interrupt(pasid, context_id & 0xff, 8);
 	else if (ihre->source_id == CIK_INTSRC_CP_BAD_OPCODE)
 		kfd_signal_hw_exception_event(pasid);
+	else if (ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) {
+		struct kfd_vm_fault_info info;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+
+		memset(&info, 0, sizeof(info));
+		dev->kfd2kgd->get_vm_fault_info(dev->kgd, &info);
+		if (!info.page_addr && !info.status)
+			return;
+
+		if (info.vmid == vmid)
+			kfd_signal_vm_fault_event(dev, pasid, &info);
+		else
+			kfd_signal_vm_fault_event(dev, pasid, NULL);
+	}
 }
 
 const struct kfd_event_interrupt_class event_interrupt_class_cik = {
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_int.h b/drivers/gpu/drm/amd/amdkfd/cik_int.h
index 109298b9d507..a2079a04a673 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_int.h
+++ b/drivers/gpu/drm/amd/amdkfd/cik_int.h
@@ -37,6 +37,8 @@ struct cik_ih_ring_entry {
 #define CIK_INTSRC_DEQUEUE_COMPLETE	0xC6
 #define CIK_INTSRC_SDMA_TRAP		0xE0
 #define CIK_INTSRC_SQ_INTERRUPT_MSG	0xEF
+#define CIK_INTSRC_GFX_PAGE_INV_FAULT	0x92
+#define CIK_INTSRC_GFX_MEM_PROT_FAULT	0x93
 
 #endif
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index f2f81d26db0c..44fc2038770e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1684,6 +1684,23 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm)
 	kfree(dqm);
 }
 
+int kfd_process_vm_fault(struct device_queue_manager *dqm,
+			 unsigned int pasid)
+{
+	struct kfd_process_device *pdd;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	int ret = 0;
+
+	if (!p)
+		return -EINVAL;
+	pdd = kfd_get_process_device_data(dqm->dev, p);
+	if (pdd)
+		ret = dqm->ops.evict_process_queues(dqm, &pdd->qpd);
+	kfd_unref_process(p);
+
+	return ret;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static void seq_reg_dump(struct seq_file *m,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 3d5a8332e8c0..b58a0e665ebc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -963,3 +963,40 @@ void kfd_signal_hw_exception_event(unsigned int pasid)
 	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
+
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info)
+{
+	struct kfd_event *ev;
+	uint32_t id;
+	struct kfd_process *p = kfd_lookup_process_by_pasid(pasid);
+	struct kfd_hsa_memory_exception_data memory_exception_data;
+
+	if (!p)
+		return; /* Presumably process exited. */
+	memset(&memory_exception_data, 0, sizeof(memory_exception_data));
+	memory_exception_data.gpu_id = dev->id;
+	memory_exception_data.failure.imprecise = 1;
+	/* Set failure reason */
+	if (info) {
+		memory_exception_data.va = (info->page_addr) << PAGE_SHIFT;
+		memory_exception_data.failure.NotPresent =
+			info->prot_valid ? 1 : 0;
+		memory_exception_data.failure.NoExecute =
+			info->prot_exec ? 1 : 0;
+		memory_exception_data.failure.ReadOnly =
+			info->prot_write ? 1 : 0;
+		memory_exception_data.failure.imprecise = 0;
+	}
+	mutex_lock(&p->event_mutex);
+
+	id = KFD_FIRST_NONSIGNAL_EVENT_ID;
+	idr_for_each_entry_continue(&p->event_idr, ev, id)
+		if (ev->type == KFD_EVENT_TYPE_MEMORY) {
+			ev->memory_exception_data = memory_exception_data;
+			set_event(ev);
+		}
+
+	mutex_unlock(&p->event_mutex);
+	kfd_unref_process(p);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index 37029baa3346..d6b64e692760 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -57,7 +57,9 @@ static bool event_interrupt_isr_v9(struct kfd_dev *dev,
 	return source_id == SOC15_INTSRC_CP_END_OF_PIPE ||
 		source_id == SOC15_INTSRC_SDMA_TRAP ||
 		source_id == SOC15_INTSRC_SQ_INTERRUPT_MSG ||
-		source_id == SOC15_INTSRC_CP_BAD_OPCODE;
+		source_id == SOC15_INTSRC_CP_BAD_OPCODE ||
+		client_id == SOC15_IH_CLIENTID_VMC ||
+		client_id == SOC15_IH_CLIENTID_UTCL2;
 }
 
 static void event_interrupt_wq_v9(struct kfd_dev *dev,
@@ -82,7 +84,19 @@ static void event_interrupt_wq_v9(struct kfd_dev *dev,
 		kfd_signal_hw_exception_event(pasid);
 	else if (client_id == SOC15_IH_CLIENTID_VMC ||
 		 client_id == SOC15_IH_CLIENTID_UTCL2) {
-		/* TODO */
+		struct kfd_vm_fault_info info = {0};
+		uint16_t ring_id = SOC15_RING_ID_FROM_IH_ENTRY(ih_ring_entry);
+
+		info.vmid = vmid;
+		info.mc_id = client_id;
+		info.page_addr = ih_ring_entry[4] |
+			(uint64_t)(ih_ring_entry[5] & 0xf) << 32;
+		info.prot_valid = ring_id & 0x08;
+		info.prot_read  = ring_id & 0x10;
+		info.prot_write = ring_id & 0x20;
+
+		kfd_process_vm_fault(dev->dqm, pasid);
+		kfd_signal_vm_fault_event(dev, pasid, &info);
 	}
 }
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 5e3990bb4c4b..91a3368421b1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -838,6 +838,7 @@ void device_queue_manager_uninit(struct device_queue_manager *dqm);
 struct kernel_queue *kernel_queue_init(struct kfd_dev *dev,
 					enum kfd_queue_type type);
 void kernel_queue_uninit(struct kernel_queue *kq);
+int kfd_process_vm_fault(struct device_queue_manager *dqm, unsigned int pasid);
 
 /* Process Queue Manager */
 struct process_queue_node {
@@ -964,6 +965,9 @@ int kfd_event_create(struct file *devkfd, struct kfd_process *p,
 		     uint64_t *event_page_offset, uint32_t *event_slot_index);
 int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 
+void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
+				struct kfd_vm_fault_info *info);
+
 void kfd_flush_tlb(struct kfd_process_device *pdd);
 
 int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index b4f5073dbac2..46a54ab1e728 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -219,7 +219,7 @@ struct kfd_memory_exception_failure {
 	__u32 NotPresent;	/* Page not present or supervisor privilege */
 	__u32 ReadOnly;	/* Write access to a read-only page */
 	__u32 NoExecute;	/* Execute access to a page marked NX */
-	__u32 pad;
+	__u32 imprecise;	/* Can't determine the	exact fault address */
 };
 
 /* memory exception data*/
-- 
cgit v1.2.3


From 58e698861255129a00765b69c0499bc0d044feb4 Mon Sep 17 00:00:00 2001
From: Lan Xiao <Lan.Xiao@amd.com>
Date: Wed, 11 Jul 2018 22:32:51 -0400
Subject: drm/amdkfd: fix zero reading of VMID and PASID for Hawaii
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Upon VM Fault, the VMID and PASID written by HW are zeros in
Hawaii. Instead of reading from ih_ring_entry, read directly
from the registers. This workaround fix the soft hang issues
caused by mishandled VM Fault in Hawaii.

Signed-off-by: Lan Xiao <Lan.Xiao@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 20 +++++++++++++++-
 drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c  | 29 ++++++++++++++++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_device.c           | 14 +++++++++--
 drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c   |  4 +++-
 drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c        |  6 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h             |  9 ++++---
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h   |  5 ++++
 7 files changed, 77 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index befc7c48b1cf..b4a05c510c75 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -145,6 +145,7 @@ static void set_vm_context_page_table_base(struct kgd_dev *kgd, uint32_t vmid,
 		uint32_t page_table_base);
 static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid);
 static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid);
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd);
 
 /* Because of REG_GET_FIELD() being used, we put this function in the
  * asic specific file.
@@ -216,7 +217,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
-	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
@@ -912,3 +914,19 @@ static int invalidate_tlbs_vmid(struct kgd_dev *kgd, uint16_t vmid)
 	RREG32(mmVM_INVALIDATE_RESPONSE);
 	return 0;
 }
+
+ /**
+  * read_vmid_from_vmfault_reg - read vmid from register
+  *
+  * adev: amdgpu_device pointer
+  * @vmid: vmid pointer
+  * read vmid from register (CIK).
+  */
+static uint32_t read_vmid_from_vmfault_reg(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = get_amdgpu_device(kgd);
+
+	uint32_t status = RREG32(mmVM_CONTEXT1_PROTECTION_FAULT_STATUS);
+
+	return REG_GET_FIELD(status, VM_CONTEXT1_PROTECTION_FAULT_STATUS, VMID);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
index cc33870e7edb..5d2475d5392c 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/cik_event_interrupt.c
@@ -25,12 +25,39 @@
 #include "cik_int.h"
 
 static bool cik_event_interrupt_isr(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	const struct cik_ih_ring_entry *ihre =
 			(const struct cik_ih_ring_entry *)ih_ring_entry;
+	const struct kfd2kgd_calls *f2g = dev->kfd2kgd;
 	unsigned int vmid, pasid;
 
+	/* This workaround is due to HW/FW limitation on Hawaii that
+	 * VMID and PASID are not written into ih_ring_entry
+	 */
+	if ((ihre->source_id == CIK_INTSRC_GFX_PAGE_INV_FAULT ||
+		ihre->source_id == CIK_INTSRC_GFX_MEM_PROT_FAULT) &&
+		dev->device_info->asic_family == CHIP_HAWAII) {
+		struct cik_ih_ring_entry *tmp_ihre =
+			(struct cik_ih_ring_entry *)patched_ihre;
+
+		*patched_flag = true;
+		*tmp_ihre = *ihre;
+
+		vmid = f2g->read_vmid_from_vmfault_reg(dev->kgd);
+		pasid = f2g->get_atc_vmid_pasid_mapping_pasid(dev->kgd, vmid);
+
+		tmp_ihre->ring_id &= 0x000000ff;
+		tmp_ihre->ring_id |= vmid << 8;
+		tmp_ihre->ring_id |= pasid << 16;
+
+		return (pasid != 0) &&
+			vmid >= dev->vm_info.first_vmid_kfd &&
+			vmid <= dev->vm_info.last_vmid_kfd;
+	}
+
 	/* Only handle interrupts from KFD VMIDs */
 	vmid  = (ihre->ring_id & 0x0000ff00) >> 8;
 	if (vmid < dev->vm_info.first_vmid_kfd ||
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 48c505e83217..600751175760 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -577,14 +577,24 @@ dqm_start_error:
 /* This is called directly from KGD at ISR. */
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry)
 {
+	uint32_t patched_ihre[KFD_MAX_RING_ENTRY_SIZE];
+	bool is_patched = false;
+
 	if (!kfd->init_complete)
 		return;
 
+	if (kfd->device_info->ih_ring_entry_size > sizeof(patched_ihre)) {
+		dev_err_once(kfd_device, "Ring entry too small\n");
+		return;
+	}
+
 	spin_lock(&kfd->interrupt_lock);
 
 	if (kfd->interrupts_active
-	    && interrupt_is_wanted(kfd, ih_ring_entry)
-	    && enqueue_ih_ring_entry(kfd, ih_ring_entry))
+	    && interrupt_is_wanted(kfd, ih_ring_entry,
+				   patched_ihre, &is_patched)
+	    && enqueue_ih_ring_entry(kfd,
+				     is_patched ? patched_ihre : ih_ring_entry))
 		queue_work(kfd->ih_wq, &kfd->interrupt_work);
 
 	spin_unlock(&kfd->interrupt_lock);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
index d6b64e692760..f836897bbf58 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
@@ -26,7 +26,9 @@
 
 
 static bool event_interrupt_isr_v9(struct kfd_dev *dev,
-					const uint32_t *ih_ring_entry)
+					const uint32_t *ih_ring_entry,
+					uint32_t *patched_ihre,
+					bool *patched_flag)
 {
 	uint16_t source_id, client_id, pasid, vmid;
 	const uint32_t *data = ih_ring_entry;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
index db6d9336b80d..c56ac47cd318 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_interrupt.c
@@ -151,13 +151,15 @@ static void interrupt_wq(struct work_struct *work)
 								ih_ring_entry);
 }
 
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry)
+bool interrupt_is_wanted(struct kfd_dev *dev,
+			const uint32_t *ih_ring_entry,
+			uint32_t *patched_ihre, bool *flag)
 {
 	/* integer and bitwise OR so there is no boolean short-circuiting */
 	unsigned int wanted = 0;
 
 	wanted |= dev->device_info->event_interrupt_class->interrupt_isr(dev,
-								ih_ring_entry);
+					 ih_ring_entry, patched_ihre, flag);
 
 	return wanted != 0;
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 91a3368421b1..cd5121d925e0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -180,9 +180,10 @@ enum cache_policy {
 
 struct kfd_event_interrupt_class {
 	bool (*interrupt_isr)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry, uint32_t *patched_ihre,
+			bool *patched_flag);
 	void (*interrupt_wq)(struct kfd_dev *dev,
-				const uint32_t *ih_ring_entry);
+			const uint32_t *ih_ring_entry);
 };
 
 struct kfd_device_info {
@@ -806,7 +807,9 @@ int kfd_interrupt_init(struct kfd_dev *dev);
 void kfd_interrupt_exit(struct kfd_dev *dev);
 void kgd2kfd_interrupt(struct kfd_dev *kfd, const void *ih_ring_entry);
 bool enqueue_ih_ring_entry(struct kfd_dev *kfd,	const void *ih_ring_entry);
-bool interrupt_is_wanted(struct kfd_dev *dev, const uint32_t *ih_ring_entry);
+bool interrupt_is_wanted(struct kfd_dev *dev,
+				const uint32_t *ih_ring_entry,
+				uint32_t *patched_ihre, bool *flag);
 
 /* Power Management */
 void kgd2kfd_suspend(struct kfd_dev *kfd);
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 28b11d105288..76a30cbeee19 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -276,6 +276,10 @@ struct tile_config {
  * faults. On GFXv9 VM fault information is fully contained in the IH
  * packet and this function is not needed.
  *
+ * @read_vmid_from_vmfault_reg: On Hawaii the VMID is not set in the
+ * IH ring entry. This function allows the KFD ISR to get the VMID
+ * from the fault status register as early as possible.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -394,6 +398,7 @@ struct kfd2kgd_calls {
 
 	int (*get_vm_fault_info)(struct kgd_dev *kgd,
 			struct kfd_vm_fault_info *info);
+	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
 };
 
 /**
-- 
cgit v1.2.3


From 6d15ca0af0e070e67863c46b54d14f3664d925b4 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:52 -0400
Subject: drm/amd: Add gpu reset interfaces between amdgpu and amdkfd
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 76a30cbeee19..7df5e4ab839f 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -280,6 +280,8 @@ struct tile_config {
  * IH ring entry. This function allows the KFD ISR to get the VMID
  * from the fault status register as early as possible.
  *
+ * @gpu_recover: let kgd reset gpu after kfd detect CPC hang
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -399,6 +401,8 @@ struct kfd2kgd_calls {
 	int (*get_vm_fault_info)(struct kgd_dev *kgd,
 			struct kfd_vm_fault_info *info);
 	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
+
+	void (*gpu_recover)(struct kgd_dev *kgd);
 };
 
 /**
@@ -424,6 +428,10 @@ struct kfd2kgd_calls {
  * @schedule_evict_and_restore_process: Schedules work queue that will prepare
  * for safe eviction of KFD BOs that belong to the specified process.
  *
+ * @pre_reset: Notifies amdkfd that amdgpu about to reset the gpu
+ *
+ * @post_reset: Notify amdkfd that amgpu successfully reseted the gpu
+ *
  * This structure contains function callback pointers so the kgd driver
  * will notify to the amdkfd about certain status changes.
  *
@@ -442,6 +450,8 @@ struct kgd2kfd_calls {
 	int (*resume_mm)(struct mm_struct *mm);
 	int (*schedule_evict_and_restore_process)(struct mm_struct *mm,
 			struct dma_fence *fence);
+	int  (*pre_reset)(struct kfd_dev *kfd);
+	int  (*post_reset)(struct kfd_dev *kfd);
 };
 
 int kgd2kfd_init(unsigned interface_version,
-- 
cgit v1.2.3


From 0c119abad7f0d7987c3ce4ea76b30bde76d0436e Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:53 -0400
Subject: drm/amd: Add kfd ioctl defines for hw_exception event
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 include/uapi/linux/kfd_ioctl.h | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 46a54ab1e728..88d17c39dbf9 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -189,6 +189,15 @@ struct kfd_ioctl_dbg_wave_control_args {
 
 #define KFD_SIGNAL_EVENT_LIMIT			4096
 
+/* For kfd_event_data.hw_exception_data.reset_type. */
+#define KFD_HW_EXCEPTION_WHOLE_GPU_RESET	0
+#define KFD_HW_EXCEPTION_PER_ENGINE_RESET	1
+
+/* For kfd_event_data.hw_exception_data.reset_cause. */
+#define KFD_HW_EXCEPTION_GPU_HANG	0
+#define KFD_HW_EXCEPTION_ECC		1
+
+
 struct kfd_ioctl_create_event_args {
 	__u64 event_page_offset;	/* from KFD */
 	__u32 event_trigger_data;	/* from KFD - signal events only */
@@ -230,10 +239,19 @@ struct kfd_hsa_memory_exception_data {
 	__u32 pad;
 };
 
-/* Event data*/
+/* hw exception data */
+struct kfd_hsa_hw_exception_data {
+	uint32_t reset_type;
+	uint32_t reset_cause;
+	uint32_t memory_lost;
+	uint32_t gpu_id;
+};
+
+/* Event data */
 struct kfd_event_data {
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};				/* From KFD */
 	__u64 kfd_event_data_ext;	/* pointer to an extension structure
 					   for future exception types */
-- 
cgit v1.2.3


From e3b7a967743c2e10457442ffafcb715a41255f28 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:54 -0400
Subject: drm/amdkfd: Add gpu reset interface and place holder
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c | 10 ++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_module.c |  2 ++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h   |  4 ++++
 3 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 600751175760..a8226d8b86cc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -514,6 +514,16 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 	kfree(kfd);
 }
 
+int kgd2kfd_pre_reset(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
+int kgd2kfd_post_reset(struct kfd_dev *kfd)
+{
+	return 0;
+}
+
 void kgd2kfd_suspend(struct kfd_dev *kfd)
 {
 	if (!kfd->init_complete)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 76bf2dc8aec4..ee7bf07db472 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -47,6 +47,8 @@ static const struct kgd2kfd_calls kgd2kfd = {
 	.resume_mm	= kgd2kfd_resume_mm,
 	.schedule_evict_and_restore_process =
 			  kgd2kfd_schedule_evict_and_restore_process,
+	.pre_reset	= kgd2kfd_pre_reset,
+	.post_reset	= kgd2kfd_post_reset,
 };
 
 int sched_policy = KFD_SCHED_POLICY_HWS;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index cd5121d925e0..4bc8d5af419d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -815,6 +815,10 @@ bool interrupt_is_wanted(struct kfd_dev *dev,
 void kgd2kfd_suspend(struct kfd_dev *kfd);
 int kgd2kfd_resume(struct kfd_dev *kfd);
 
+/* GPU reset */
+int kgd2kfd_pre_reset(struct kfd_dev *kfd);
+int kgd2kfd_post_reset(struct kfd_dev *kfd);
+
 /* amdkfd Apertures */
 int kfd_init_apertures(struct kfd_process *process);
 
-- 
cgit v1.2.3


From 5c6dd71e597f33d517710affe3b8d8de253bc86d Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:55 -0400
Subject: drm/amdgpu: Call KFD reset handlers during GPU reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c | 20 ++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h |  4 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  5 +++++
 3 files changed, 29 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index e3ed08dca7b7..f3a3aba08c2f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -243,6 +243,26 @@ int amdgpu_amdkfd_resume(struct amdgpu_device *adev)
 	return r;
 }
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->pre_reset(adev->kfd);
+
+	return r;
+}
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev)
+{
+	int r = 0;
+
+	if (adev->kfd)
+		r = kgd2kfd->post_reset(adev->kfd);
+
+	return r;
+}
+
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 3dc76d9b4d12..7dc551b8f682 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -126,6 +126,10 @@ struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void);
 
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid);
 
+int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
+
+int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
+
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ec53d8f96d06..b895584bb99f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3307,6 +3307,9 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 	atomic_inc(&adev->gpu_reset_counter);
 	adev->in_gpu_reset = 1;
 
+	/* Block kfd */
+	amdgpu_amdkfd_pre_reset(adev);
+
 	/* block TTM */
 	resched = ttm_bo_lock_delayed_workqueue(&adev->mman.bdev);
 
@@ -3363,6 +3366,8 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		dev_info(adev->dev, "GPU reset(%d) succeeded!\n",atomic_read(&adev->gpu_reset_counter));
 	}
 
+	/*unlock kfd */
+	amdgpu_amdkfd_post_reset(adev);
 	amdgpu_vf_error_trans_all(adev);
 	adev->in_gpu_reset = 0;
 	mutex_unlock(&adev->lock_reset);
-- 
cgit v1.2.3


From e42051d2133b7912db99bd3a307c9219a88fe7c2 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:56 -0400
Subject: drm/amdkfd: Implement GPU reset handlers in KFD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Lock KFD and evict existing queues on reset. Notify user mode by
signaling hw_exception events.

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c |  3 +++
 drivers/gpu/drm/amd/amdkfd/kfd_device.c  | 43 +++++++++++++++++++++++++++++---
 drivers/gpu/drm/amd/amdkfd/kfd_events.c  | 27 ++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_events.h  |  1 +
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h    |  4 +++
 5 files changed, 75 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index 7e717716b90e..b5338bff8cef 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -122,6 +122,9 @@ static int kfd_open(struct inode *inode, struct file *filep)
 	if (IS_ERR(process))
 		return PTR_ERR(process);
 
+	if (kfd_is_locked())
+		return -EAGAIN;
+
 	dev_dbg(kfd_device, "process %d opened, compat mode (32 bit) - %d\n",
 		process->pasid, process->is_32bit_user_mode);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index a8226d8b86cc..9f63ac366284 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -30,7 +30,13 @@
 #include "kfd_iommu.h"
 
 #define MQD_SIZE_ALIGNED 768
-static atomic_t kfd_device_suspended = ATOMIC_INIT(0);
+
+/*
+ * kfd_locked is used to lock the kfd driver during suspend or reset
+ * once locked, kfd driver will stop any further GPU execution.
+ * create process (open) will return -EAGAIN.
+ */
+static atomic_t kfd_locked = ATOMIC_INIT(0);
 
 #ifdef KFD_SUPPORT_IOMMU_V2
 static const struct kfd_device_info kaveri_device_info = {
@@ -516,21 +522,52 @@ void kgd2kfd_device_exit(struct kfd_dev *kfd)
 
 int kgd2kfd_pre_reset(struct kfd_dev *kfd)
 {
+	if (!kfd->init_complete)
+		return 0;
+	kgd2kfd_suspend(kfd);
+
+	/* hold dqm->lock to prevent further execution*/
+	dqm_lock(kfd->dqm);
+
+	kfd_signal_reset_event(kfd);
 	return 0;
 }
 
+/*
+ * Fix me. KFD won't be able to resume existing process for now.
+ * We will keep all existing process in a evicted state and
+ * wait the process to be terminated.
+ */
+
 int kgd2kfd_post_reset(struct kfd_dev *kfd)
 {
+	int ret, count;
+
+	if (!kfd->init_complete)
+		return 0;
+
+	dqm_unlock(kfd->dqm);
+
+	ret = kfd_resume(kfd);
+	if (ret)
+		return ret;
+	count = atomic_dec_return(&kfd_locked);
+	WARN_ONCE(count != 0, "KFD reset ref. error");
 	return 0;
 }
 
+bool kfd_is_locked(void)
+{
+	return  (atomic_read(&kfd_locked) > 0);
+}
+
 void kgd2kfd_suspend(struct kfd_dev *kfd)
 {
 	if (!kfd->init_complete)
 		return;
 
 	/* For first KFD device suspend all the KFD processes */
-	if (atomic_inc_return(&kfd_device_suspended) == 1)
+	if (atomic_inc_return(&kfd_locked) == 1)
 		kfd_suspend_all_processes();
 
 	kfd->dqm->ops.stop(kfd->dqm);
@@ -549,7 +586,7 @@ int kgd2kfd_resume(struct kfd_dev *kfd)
 	if (ret)
 		return ret;
 
-	count = atomic_dec_return(&kfd_device_suspended);
+	count = atomic_dec_return(&kfd_locked);
 	WARN_ONCE(count < 0, "KFD suspend / resume ref. error");
 	if (count == 0)
 		ret = kfd_resume_all_processes();
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index b58a0e665ebc..820133cdef83 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -1000,3 +1000,30 @@ void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
 	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
+
+void kfd_signal_reset_event(struct kfd_dev *dev)
+{
+	struct kfd_hsa_hw_exception_data hw_exception_data;
+	struct kfd_process *p;
+	struct kfd_event *ev;
+	unsigned int temp;
+	uint32_t id, idx;
+
+	/* Whole gpu reset caused by GPU hang and memory is lost */
+	memset(&hw_exception_data, 0, sizeof(hw_exception_data));
+	hw_exception_data.gpu_id = dev->id;
+	hw_exception_data.memory_lost = 1;
+
+	idx = srcu_read_lock(&kfd_processes_srcu);
+	hash_for_each_rcu(kfd_processes_table, temp, p, kfd_processes) {
+		mutex_lock(&p->event_mutex);
+		id = KFD_FIRST_NONSIGNAL_EVENT_ID;
+		idr_for_each_entry_continue(&p->event_idr, ev, id)
+			if (ev->type == KFD_EVENT_TYPE_HW_EXCEPTION) {
+				ev->hw_exception_data = hw_exception_data;
+				set_event(ev);
+			}
+		mutex_unlock(&p->event_mutex);
+	}
+	srcu_read_unlock(&kfd_processes_srcu, idx);
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.h b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
index abca5bfebbff..c7ac6c73af86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.h
@@ -66,6 +66,7 @@ struct kfd_event {
 	/* type specific data */
 	union {
 		struct kfd_hsa_memory_exception_data memory_exception_data;
+		struct kfd_hsa_hw_exception_data hw_exception_data;
 	};
 };
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 4bc8d5af419d..2e03d6c80aa0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -975,10 +975,14 @@ int kfd_event_destroy(struct kfd_process *p, uint32_t event_id);
 void kfd_signal_vm_fault_event(struct kfd_dev *dev, unsigned int pasid,
 				struct kfd_vm_fault_info *info);
 
+void kfd_signal_reset_event(struct kfd_dev *dev);
+
 void kfd_flush_tlb(struct kfd_process_device *pdd);
 
 int dbgdev_wave_reset_wavefronts(struct kfd_dev *dev, struct kfd_process *p);
 
+bool kfd_is_locked(void);
+
 /* Debugfs */
 #if defined(CONFIG_DEBUG_FS)
 
-- 
cgit v1.2.3


From 24da5a9ca6c225ecdc33ea9c7c1b3aa0debed203 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:57 -0400
Subject: drm/amdgpu: Enable the gpu reset from KFD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Hook up the gpu_recover callback from KFD to amdgpu to enable
handling of GPU hangs detected by KFD.

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c        | 7 +++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h        | 2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 1 +
 5 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index f3a3aba08c2f..454c22c722c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -263,6 +263,13 @@ int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev)
 	return r;
 }
 
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_device_gpu_recover(adev, NULL, false);
+}
+
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
 			void **cpu_ptr)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 7dc551b8f682..60207ea48bf5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -130,6 +130,8 @@ int amdgpu_amdkfd_pre_reset(struct amdgpu_device *adev);
 
 int amdgpu_amdkfd_post_reset(struct amdgpu_device *adev);
 
+void amdgpu_amdkfd_gpu_reset(struct kgd_dev *kgd);
+
 /* Shared API */
 int alloc_gtt_mem(struct kgd_dev *kgd, size_t size,
 			void **mem_obj, uint64_t *gpu_addr,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index b4a05c510c75..70b275a711c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -218,7 +218,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
 	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
-	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg
+	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index c68ef85f7753..6053b1d143ae 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -176,7 +176,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
-	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info
+	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 1db60aa5b7f0..56d29cfd8227 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -213,6 +213,7 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
+	.gpu_recover = amdgpu_amdkfd_gpu_reset
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
-- 
cgit v1.2.3


From 73ea648d921ed5c58895c8592321456fe12b697f Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:58 -0400
Subject: drm/amdkfd: Implement hang detection in KFD and call amdgpu
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The reset will be performed in a new hw_exception work thread to
handle HWS hang without blocking the thread that detected the hang.

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c   | 21 ++++++++++++++++++++-
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.h   |  4 ++++
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 44fc2038770e..6b59eab39fbe 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -61,6 +61,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
 				unsigned int sdma_queue_id);
 
+static void kfd_process_hw_exception(struct work_struct *work);
+
 static inline
 enum KFD_MQD_TYPE get_mqd_type_from_queue_type(enum kfd_queue_type type)
 {
@@ -1010,6 +1012,8 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 	dqm->active_runlist = false;
 	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
 
+	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
+
 	return 0;
 }
 
@@ -1042,6 +1046,8 @@ static int start_cpsch(struct device_queue_manager *dqm)
 	init_interrupts(dqm);
 
 	dqm_lock(dqm);
+	/* clear hang status when driver try to start the hw scheduler */
+	dqm->is_hws_hang = false;
 	execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES, 0);
 	dqm_unlock(dqm);
 
@@ -1255,6 +1261,8 @@ static int unmap_queues_cpsch(struct device_queue_manager *dqm,
 {
 	int retval = 0;
 
+	if (dqm->is_hws_hang)
+		return -EIO;
 	if (!dqm->active_runlist)
 		return retval;
 
@@ -1293,9 +1301,13 @@ static int execute_queues_cpsch(struct device_queue_manager *dqm,
 {
 	int retval;
 
+	if (dqm->is_hws_hang)
+		return -EIO;
 	retval = unmap_queues_cpsch(dqm, filter, filter_param);
 	if (retval) {
 		pr_err("The cp might be in an unrecoverable state due to an unsuccessful queues preemption\n");
+		dqm->is_hws_hang = true;
+		schedule_work(&dqm->hw_exception_work);
 		return retval;
 	}
 
@@ -1543,7 +1555,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	}
 
 	retval = execute_queues_cpsch(dqm, filter, 0);
-	if (retval || qpd->reset_wavefronts) {
+	if ((!dqm->is_hws_hang) && (retval || qpd->reset_wavefronts)) {
 		pr_warn("Resetting wave fronts (cpsch) on dev %p\n", dqm->dev);
 		dbgdev_wave_reset_wavefronts(dqm->dev, qpd->pqm->process);
 		qpd->reset_wavefronts = false;
@@ -1701,6 +1713,13 @@ int kfd_process_vm_fault(struct device_queue_manager *dqm,
 	return ret;
 }
 
+static void kfd_process_hw_exception(struct work_struct *work)
+{
+	struct device_queue_manager *dqm = container_of(work,
+			struct device_queue_manager, hw_exception_work);
+	dqm->dev->kfd2kgd->gpu_recover(dqm->dev->kgd);
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static void seq_reg_dump(struct seq_file *m,
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 0a23ddac345e..70179a6826f4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -193,6 +193,10 @@ struct device_queue_manager {
 	struct kfd_mem_obj	*fence_mem;
 	bool			active_runlist;
 	int			sched_policy;
+
+	/* hw exception  */
+	bool			is_hws_hang;
+	struct work_struct	hw_exception_work;
 };
 
 void device_queue_manager_init_cik(
-- 
cgit v1.2.3


From b5d21aac33179e55807d0fb0c0e1f694c1dce2c3 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:32:59 -0400
Subject: drm/amdgpu: Don't use shadow BO for compute context
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Compute contexts cannot keep going after a GPU reset. Currently the process
must terminate. In the future a process may be able recreate its context
from scratch. Either way, there is no need to restore the GPUVM page table
from shadow BOs.

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5d7d7900ccab..9eedc9810004 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -495,11 +495,12 @@ static int amdgpu_vm_alloc_levels(struct amdgpu_device *adev,
 	eaddr = eaddr & ((1 << shift) - 1);
 
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+	if (vm->root.base.bo->shadow)
+		flags |= AMDGPU_GEM_CREATE_SHADOW;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
 	else
-		flags |= (AMDGPU_GEM_CREATE_NO_CPU_ACCESS |
-				AMDGPU_GEM_CREATE_SHADOW);
+		flags |= AMDGPU_GEM_CREATE_NO_CPU_ACCESS;
 
 	/* walk over the address space and allocate the page tables */
 	for (pt_idx = from; pt_idx <= to; ++pt_idx) {
@@ -2587,7 +2588,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	flags = AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
 	if (vm->use_cpu_for_update)
 		flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	else
+	else if (vm_context != AMDGPU_VM_CONTEXT_COMPUTE)
 		flags |= AMDGPU_GEM_CREATE_SHADOW;
 
 	size = amdgpu_vm_bo_size(adev, adev->vm_manager.root_level);
@@ -2662,8 +2663,7 @@ error_free_sched_entity:
  * - pasid (old PASID is released, because compute manages its own PASIDs)
  *
  * Reinitializes the page directory to reflect the changed ATS
- * setting. May leave behind an unused shadow BO for the page
- * directory when switching from SDMA updates to CPU updates.
+ * setting.
  *
  * Returns:
  * 0 for success, -errno for errors.
@@ -2713,6 +2713,9 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		vm->pasid = 0;
 	}
 
+	/* Free the shadow bo for compute VM */
+	amdgpu_bo_unref(&vm->root.base.bo->shadow);
+
 error:
 	amdgpu_bo_unreserve(vm->root.base.bo);
 	return r;
-- 
cgit v1.2.3


From 67ccea60591a0515c885af9bf8dfb932a905457f Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:33:00 -0400
Subject: drm/amdgpu: Check NULL pointer for job before reset job's ring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

job could be NULL when amdgpu_device_gpu_recover is called

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index b895584bb99f..13acef526c5b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3325,7 +3325,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		if (job && job->base.sched == &ring->sched)
 			continue;
 
-		drm_sched_hw_job_reset(&ring->sched, &job->base);
+		drm_sched_hw_job_reset(&ring->sched, job ? &job->base : NULL);
 
 		/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
 		amdgpu_fence_driver_force_completion(ring);
-- 
cgit v1.2.3


From 951df6d9cfd07f205f1905bf3b27d994612e0614 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:33:01 -0400
Subject: drm/amdkfd: Fix kernel queue 64 bit doorbell offset calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bitmap index calculation should reverse the logic used on allocation
so it will clear the same bit used on allocation

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
index c3744d89352c..ebe79bf00145 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_doorbell.c
@@ -188,9 +188,9 @@ void __iomem *kfd_get_kernel_doorbell(struct kfd_dev *kfd,
 	*doorbell_off = kfd->doorbell_id_offset + inx;
 
 	pr_debug("Get kernel queue doorbell\n"
-			 "     doorbell offset   == 0x%08X\n"
-			 "     kernel address    == %p\n",
-		*doorbell_off, (kfd->doorbell_kernel_ptr + inx));
+			"     doorbell offset   == 0x%08X\n"
+			"     doorbell index    == 0x%x\n",
+		*doorbell_off, inx);
 
 	return kfd->doorbell_kernel_ptr + inx;
 }
@@ -199,7 +199,8 @@ void kfd_release_kernel_doorbell(struct kfd_dev *kfd, u32 __iomem *db_addr)
 {
 	unsigned int inx;
 
-	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr);
+	inx = (unsigned int)(db_addr - kfd->doorbell_kernel_ptr)
+		* sizeof(u32) / kfd->device_info->doorbell_size;
 
 	mutex_lock(&kfd->doorbell_mutex);
 	__clear_bit(inx, kfd->doorbell_available_index);
-- 
cgit v1.2.3


From bff418a2ee5df84bd75ac43659af7289ec1bab1c Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:33:02 -0400
Subject: drm/amdgpu: Avoid invalidate tlbs when gpu is on reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 3 +++
 3 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 70b275a711c2..2551a4547393 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -886,6 +886,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	unsigned int tmp;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 6053b1d143ae..55749ce4f166 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -846,6 +846,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	unsigned int tmp;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	for (vmid = 0; vmid < 16; vmid++) {
 		if (!amdgpu_amdkfd_is_kfd_vmid(adev, vmid))
 			continue;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 56d29cfd8227..847f6c1e3624 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -867,6 +867,9 @@ static int invalidate_tlbs(struct kgd_dev *kgd, uint16_t pasid)
 	int vmid;
 	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	if (ring->ready)
 		return invalidate_tlbs_with_kiq(adev, pasid);
 
-- 
cgit v1.2.3


From 1b0bfcff463f390c4032ebe36a4d5fb777c00a4c Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:33:03 -0400
Subject: drm/amdgpu: Avoid destroy hqd when GPU is on reset
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 3 +++
 3 files changed, 9 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 2551a4547393..98eac00e5d32 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -575,6 +575,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	unsigned long flags, end_jiffies;
 	int retry;
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 	WREG32(mmCP_HQD_PQ_DOORBELL_CONTROL, 0);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index 55749ce4f166..ad563b1ee547 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -570,6 +570,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	int retry;
 	struct vi_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 847f6c1e3624..3b07d37b6fd4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -680,6 +680,9 @@ static int kgd_hqd_destroy(struct kgd_dev *kgd, void *mqd,
 	uint32_t temp;
 	struct v9_mqd *m = get_mqd(mqd);
 
+	if (adev->in_gpu_reset)
+		return -EIO;
+
 	acquire_queue(kgd, pipe_id, queue_id);
 
 	if (m->cp_hqd_vmid == 0)
-- 
cgit v1.2.3


From a29ec470b19e58044005973301f233e0b20ed8c4 Mon Sep 17 00:00:00 2001
From: Shaoyun Liu <Shaoyun.Liu@amd.com>
Date: Wed, 11 Jul 2018 22:33:04 -0400
Subject: drm/amdkfd: Add debugfs interface to trigger HWS hang
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Shaoyun Liu <Shaoyun.Liu@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c           | 48 ++++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_device.c            | 23 +++++++++++
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 12 ++++++
 drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c    | 26 ++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              |  4 ++
 5 files changed, 113 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
index 4bd6ebfaf425..ab37d36d9cd6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_debugfs.c
@@ -21,6 +21,8 @@
  */
 
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
+
 #include "kfd_priv.h"
 
 static struct dentry *debugfs_root;
@@ -32,6 +34,38 @@ static int kfd_debugfs_open(struct inode *inode, struct file *file)
 	return single_open(file, show, NULL);
 }
 
+static ssize_t kfd_debugfs_hang_hws_write(struct file *file,
+	const char __user *user_buf, size_t size, loff_t *ppos)
+{
+	struct kfd_dev *dev;
+	char tmp[16];
+	uint32_t gpu_id;
+	int ret = -EINVAL;
+
+	memset(tmp, 0, 16);
+	if (size >= 16) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	if (copy_from_user(tmp, user_buf, size)) {
+		ret = -EFAULT;
+		goto out;
+	}
+	if (kstrtoint(tmp, 10, &gpu_id)) {
+		pr_err("Invalid input for gpu id.\n");
+		goto out;
+	}
+	dev = kfd_device_by_id(gpu_id);
+	if (dev) {
+		kfd_debugfs_hang_hws(dev);
+		ret = size;
+	} else
+		pr_err("Cannot find device %d.\n", gpu_id);
+
+out:
+	return ret;
+}
+
 static const struct file_operations kfd_debugfs_fops = {
 	.owner = THIS_MODULE,
 	.open = kfd_debugfs_open,
@@ -40,6 +74,15 @@ static const struct file_operations kfd_debugfs_fops = {
 	.release = single_release,
 };
 
+static const struct file_operations kfd_debugfs_hang_hws_fops = {
+	.owner = THIS_MODULE,
+	.open = kfd_debugfs_open,
+	.read = seq_read,
+	.write = kfd_debugfs_hang_hws_write,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
 void kfd_debugfs_init(void)
 {
 	struct dentry *ent;
@@ -65,6 +108,11 @@ void kfd_debugfs_init(void)
 	ent = debugfs_create_file("rls", S_IFREG | 0444, debugfs_root,
 				  kfd_debugfs_rls_by_device,
 				  &kfd_debugfs_fops);
+
+	ent = debugfs_create_file("hang_hws", S_IFREG | 0644, debugfs_root,
+				  NULL,
+				  &kfd_debugfs_hang_hws_fops);
+
 	if (!ent)
 		pr_warn("Failed to create rls in kfd debugfs\n");
 }
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 9f63ac366284..8faa8db3eba5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -914,3 +914,26 @@ int kfd_gtt_sa_free(struct kfd_dev *kfd, struct kfd_mem_obj *mem_obj)
 	kfree(mem_obj);
 	return 0;
 }
+
+#if defined(CONFIG_DEBUG_FS)
+
+/* This function will send a package to HIQ to hang the HWS
+ * which will trigger a GPU reset and bring the HWS back to normal state
+ */
+int kfd_debugfs_hang_hws(struct kfd_dev *dev)
+{
+	int r = 0;
+
+	if (dev->dqm->sched_policy != KFD_SCHED_POLICY_HWS) {
+		pr_err("HWS is not enabled");
+		return -EINVAL;
+	}
+
+	r = pm_debugfs_hang_hws(&dev->dqm->packets);
+	if (!r)
+		r = dqm_debugfs_execute_queues(dev->dqm);
+
+	return r;
+}
+
+#endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 6b59eab39fbe..32e93b53e7e8 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1801,4 +1801,16 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 	return r;
 }
 
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm)
+{
+	int r = 0;
+
+	dqm_lock(dqm);
+	dqm->active_runlist = true;
+	r = execute_queues_cpsch(dqm, KFD_UNMAP_QUEUES_FILTER_ALL_QUEUES, 0);
+	dqm_unlock(dqm);
+
+	return r;
+}
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
index c317feb43f69..1092631765cb 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_packet_manager.c
@@ -418,4 +418,30 @@ out:
 	return 0;
 }
 
+int pm_debugfs_hang_hws(struct packet_manager *pm)
+{
+	uint32_t *buffer, size;
+	int r = 0;
+
+	size = pm->pmf->query_status_size;
+	mutex_lock(&pm->lock);
+	pm->priv_queue->ops.acquire_packet_buffer(pm->priv_queue,
+			size / sizeof(uint32_t), (unsigned int **)&buffer);
+	if (!buffer) {
+		pr_err("Failed to allocate buffer on kernel queue\n");
+		r = -ENOMEM;
+		goto out;
+	}
+	memset(buffer, 0x55, size);
+	pm->priv_queue->ops.submit_packet(pm->priv_queue);
+
+	pr_info("Submitting %x %x %x %x %x %x %x to HIQ to hang the HWS.",
+		buffer[0], buffer[1], buffer[2], buffer[3],
+		buffer[4], buffer[5], buffer[6]);
+out:
+	mutex_unlock(&pm->lock);
+	return r;
+}
+
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 2e03d6c80aa0..d9bf70b52857 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -995,6 +995,10 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data);
 int kfd_debugfs_rls_by_device(struct seq_file *m, void *data);
 int pm_debugfs_runlist(struct seq_file *m, void *data);
 
+int kfd_debugfs_hang_hws(struct kfd_dev *dev);
+int pm_debugfs_hang_hws(struct packet_manager *pm);
+int dqm_debugfs_execute_queues(struct device_queue_manager *dqm);
+
 #else
 
 static inline void kfd_debugfs_init(void) {}
-- 
cgit v1.2.3


From 0e9a860c72ec387140a0feb4b8d9a6d0004e9316 Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Wed, 11 Jul 2018 22:33:05 -0400
Subject: drm/amdkfd: Introduce KFD module parameter halt_if_hws_hang
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This avoids triggering a GPU reset or otherwise changing the HW
state. Instead KFD will hang, which allows HW debugging tools to
analyze the problem.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 7 +++++++
 drivers/gpu/drm/amd/amdkfd/kfd_module.c               | 4 ++++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h                 | 5 +++++
 3 files changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 32e93b53e7e8..5d05d125c3c1 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1217,6 +1217,13 @@ int amdkfd_fence_wait_timeout(unsigned int *fence_addr,
 	while (*fence_addr != fence_value) {
 		if (time_after(jiffies, end_jiffies)) {
 			pr_err("qcm fence wait loop timeout expired\n");
+			/* In HWS case, this is used to halt the driver thread
+			 * in order not to mess up CP states before doing
+			 * scandumps for FW debugging.
+			 */
+			while (halt_if_hws_hang)
+				schedule();
+
 			return -ETIME;
 		}
 		schedule();
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index ee7bf07db472..3a8c15ad0c64 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -92,6 +92,10 @@ MODULE_PARM_DESC(noretry,
 
 static int amdkfd_init_completed;
 
+int halt_if_hws_hang;
+module_param(halt_if_hws_hang, int, 0644);
+MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
+
 int kgd2kfd_init(unsigned int interface_version,
 		const struct kgd2kfd_calls **g2f)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index d9bf70b52857..8473e7b3dcc2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -144,6 +144,11 @@ extern int ignore_crat;
  */
 extern int vega10_noretry;
 
+/*
+ * Halt if HWS hang is detected
+ */
+extern int halt_if_hws_hang;
+
 /**
  * enum kfd_sched_policy
  *
-- 
cgit v1.2.3


From 2b281977f5e072171bbd9e562c1dd27f0fe8461f Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Wed, 11 Jul 2018 22:33:06 -0400
Subject: drm/amdkfd: Use module parameters noretry as the internal variable
 name
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This makes all module parameters use the same form. Meanwhile clean up
the surrounding code.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c |  2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_module.c                  | 14 ++++++++------
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h                    |  2 +-
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
index 79e5bcf6367c..417515332c35 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager_v9.c
@@ -60,7 +60,7 @@ static int update_qpd_v9(struct device_queue_manager *dqm,
 		qpd->sh_mem_config =
 				SH_MEM_ALIGNMENT_MODE_UNALIGNED <<
 					SH_MEM_CONFIG__ALIGNMENT_MODE__SHIFT;
-		if (vega10_noretry &&
+		if (noretry &&
 		    !dqm->dev->device_info->needs_iommu_device)
 			qpd->sh_mem_config |=
 				1 << SH_MEM_CONFIG__RETRY_DISABLE__SHIFT;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index 3a8c15ad0c64..6e1f5c7c2d4b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -63,7 +63,7 @@ MODULE_PARM_DESC(hws_max_conc_proc,
 
 int cwsr_enable = 1;
 module_param(cwsr_enable, int, 0444);
-MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = Off, 1 = On (Default))");
+MODULE_PARM_DESC(cwsr_enable, "CWSR enable (0 = off, 1 = on (default))");
 
 int max_num_of_queues_per_device = KFD_MAX_NUM_OF_QUEUES_PER_DEVICE_DEFAULT;
 module_param(max_num_of_queues_per_device, int, 0444);
@@ -85,17 +85,19 @@ module_param(ignore_crat, int, 0444);
 MODULE_PARM_DESC(ignore_crat,
 	"Ignore CRAT table during KFD initialization (0 = use CRAT (default), 1 = ignore CRAT)");
 
-int vega10_noretry;
-module_param_named(noretry, vega10_noretry, int, 0644);
+int noretry;
+module_param(noretry, int, 0644);
 MODULE_PARM_DESC(noretry,
-	"Set sh_mem_config.retry_disable on Vega10 (0 = retry enabled (default), 1 = retry disabled)");
-
-static int amdkfd_init_completed;
+	"Set sh_mem_config.retry_disable on GFXv9+ dGPUs (0 = retry enabled (default), 1 = retry disabled)");
 
 int halt_if_hws_hang;
 module_param(halt_if_hws_hang, int, 0644);
 MODULE_PARM_DESC(halt_if_hws_hang, "Halt if HWS hang is detected (0 = off (default), 1 = on)");
 
+
+static int amdkfd_init_completed;
+
+
 int kgd2kfd_init(unsigned int interface_version,
 		const struct kgd2kfd_calls **g2f)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 8473e7b3dcc2..0646eda473df 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -142,7 +142,7 @@ extern int ignore_crat;
 /*
  * Set sh_mem_config.retry_disable on Vega10
  */
-extern int vega10_noretry;
+extern int noretry;
 
 /*
  * Halt if HWS hang is detected
-- 
cgit v1.2.3


From 8d5f355290880331e265d4c3f3b66c805969f18e Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Wed, 11 Jul 2018 22:33:07 -0400
Subject: drm/amdkfd: Replace mqd with mqd_mgr as the variable name for
 mqd_manager
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This will make reading code much easier.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 105 +++++++++++----------
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.h  |   2 +-
 drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c      |  17 ++--
 drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h      |   2 +-
 .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c |   8 +-
 5 files changed, 68 insertions(+), 66 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 5d05d125c3c1..97c9f10ff473 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -348,10 +348,10 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
-	mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
-	if (!mqd)
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_COMPUTE);
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	retval = allocate_hqd(dqm, q);
@@ -362,7 +362,7 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		goto out_deallocate_hqd;
 
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
@@ -376,15 +376,15 @@ static int create_compute_queue_nocpsch(struct device_queue_manager *dqm,
 	if (!q->properties.is_active)
 		return 0;
 
-	retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue, &q->properties,
-			       q->process->mm);
+	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
+			&q->properties, q->process->mm);
 	if (retval)
 		goto out_uninit_mqd;
 
 	return 0;
 
 out_uninit_mqd:
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_hqd:
@@ -401,11 +401,11 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 				struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 		get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd)
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	if (q->properties.type == KFD_QUEUE_TYPE_COMPUTE) {
@@ -422,14 +422,14 @@ static int destroy_queue_nocpsch_locked(struct device_queue_manager *dqm,
 
 	deallocate_doorbell(qpd, q);
 
-	retval = mqd->destroy_mqd(mqd, q->mqd,
+	retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 				KFD_UNMAP_LATENCY_MS,
 				q->pipe, q->queue);
 	if (retval == -ETIME)
 		qpd->reset_wavefronts = true;
 
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 
 	list_del(&q->list);
 	if (list_empty(&qpd->queues_list)) {
@@ -469,7 +469,7 @@ static int destroy_queue_nocpsch(struct device_queue_manager *dqm,
 static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	bool prev_active = false;
 
@@ -479,9 +479,9 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		retval = -ENODEV;
 		goto out_unlock;
 	}
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto out_unlock;
 	}
@@ -508,7 +508,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 	} else if (prev_active &&
 		   (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
 		    q->properties.type == KFD_QUEUE_TYPE_SDMA)) {
-		retval = mqd->destroy_mqd(mqd, q->mqd,
+		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval) {
@@ -517,7 +517,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 		}
 	}
 
-	retval = mqd->update_mqd(mqd, q->mqd, &q->properties);
+	retval = mqd_mgr->update_mqd(mqd_mgr, q->mqd, &q->properties);
 
 	/*
 	 * check active state vs. the previous state and modify
@@ -535,7 +535,7 @@ static int update_queue(struct device_queue_manager *dqm, struct queue *q)
 	else if (q->properties.is_active &&
 		 (q->properties.type == KFD_QUEUE_TYPE_COMPUTE ||
 		  q->properties.type == KFD_QUEUE_TYPE_SDMA))
-		retval = mqd->load_mqd(mqd, q->mqd, q->pipe, q->queue,
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe, q->queue,
 				       &q->properties, q->process->mm);
 
 out_unlock:
@@ -546,29 +546,29 @@ out_unlock:
 static struct mqd_manager *get_mqd_manager(
 		struct device_queue_manager *dqm, enum KFD_MQD_TYPE type)
 {
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
 	if (WARN_ON(type >= KFD_MQD_TYPE_MAX))
 		return NULL;
 
 	pr_debug("mqd type %d\n", type);
 
-	mqd = dqm->mqds[type];
-	if (!mqd) {
-		mqd = mqd_manager_init(type, dqm->dev);
-		if (!mqd)
+	mqd_mgr = dqm->mqd_mgrs[type];
+	if (!mqd_mgr) {
+		mqd_mgr = mqd_manager_init(type, dqm->dev);
+		if (!mqd_mgr)
 			pr_err("mqd manager is NULL");
-		dqm->mqds[type] = mqd;
+		dqm->mqd_mgrs[type] = mqd_mgr;
 	}
 
-	return mqd;
+	return mqd_mgr;
 }
 
 static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
 	struct queue *q;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	int retval = 0;
 
@@ -584,16 +584,16 @@ static int evict_process_queues_nocpsch(struct device_queue_manager *dqm,
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_active)
 			continue;
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) { /* should not be here */
+		if (!mqd_mgr) { /* should not be here */
 			pr_err("Cannot evict queue, mqd mgr is NULL\n");
 			retval = -ENOMEM;
 			goto out;
 		}
 		q->properties.is_evicted = true;
 		q->properties.is_active = false;
-		retval = mqd->destroy_mqd(mqd, q->mqd,
+		retval = mqd_mgr->destroy_mqd(mqd_mgr, q->mqd,
 				KFD_PREEMPT_TYPE_WAVEFRONT_DRAIN,
 				KFD_UNMAP_LATENCY_MS, q->pipe, q->queue);
 		if (retval)
@@ -643,7 +643,7 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 					  struct qcm_process_device *qpd)
 {
 	struct queue *q;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct kfd_process_device *pdd;
 	uint32_t pd_base;
 	int retval = 0;
@@ -679,16 +679,16 @@ static int restore_process_queues_nocpsch(struct device_queue_manager *dqm,
 	list_for_each_entry(q, &qpd->queues_list, list) {
 		if (!q->properties.is_evicted)
 			continue;
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) { /* should not be here */
+		if (!mqd_mgr) { /* should not be here */
 			pr_err("Cannot restore queue, mqd mgr is NULL\n");
 			retval = -ENOMEM;
 			goto out;
 		}
 		q->properties.is_evicted = false;
 		q->properties.is_active = true;
-		retval = mqd->load_mqd(mqd, q->mqd, q->pipe,
+		retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, q->pipe,
 				       q->queue, &q->properties,
 				       q->process->mm);
 		if (retval)
@@ -868,7 +868,7 @@ static void uninitialize(struct device_queue_manager *dqm)
 
 	kfree(dqm->allocated_queues);
 	for (i = 0 ; i < KFD_MQD_TYPE_MAX ; i++)
-		kfree(dqm->mqds[i]);
+		kfree(dqm->mqd_mgrs[i]);
 	mutex_destroy(&dqm->lock_hidden);
 	kfd_gtt_sa_free(dqm->dev, dqm->pipeline_mem);
 }
@@ -912,11 +912,11 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 					struct queue *q,
 					struct qcm_process_device *qpd)
 {
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	int retval;
 
-	mqd = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
-	if (!mqd)
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm, KFD_MQD_TYPE_SDMA);
+	if (!mqd_mgr)
 		return -ENOMEM;
 
 	retval = allocate_sdma_queue(dqm, &q->sdma_id);
@@ -935,19 +935,20 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	pr_debug("SDMA engine id: %d\n", q->properties.sdma_engine_id);
 
 	dqm->asic_ops.init_sdma_vm(dqm, q, qpd);
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
 
-	retval = mqd->load_mqd(mqd, q->mqd, 0, 0, &q->properties, NULL);
+	retval = mqd_mgr->load_mqd(mqd_mgr, q->mqd, 0, 0, &q->properties,
+				NULL);
 	if (retval)
 		goto out_uninit_mqd;
 
 	return 0;
 
 out_uninit_mqd:
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 out_deallocate_doorbell:
 	deallocate_doorbell(qpd, q);
 out_deallocate_sdma_queue:
@@ -1123,7 +1124,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 			struct qcm_process_device *qpd)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 
 	retval = 0;
 
@@ -1150,10 +1151,10 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 	if (retval)
 		goto out_deallocate_sdma_queue;
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
 
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto out_deallocate_doorbell;
 	}
@@ -1170,7 +1171,7 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 
 	q->properties.tba_addr = qpd->tba_addr;
 	q->properties.tma_addr = qpd->tma_addr;
-	retval = mqd->init_mqd(mqd, &q->mqd, &q->mqd_mem_obj,
+	retval = mqd_mgr->init_mqd(mqd_mgr, &q->mqd, &q->mqd_mem_obj,
 				&q->gart_mqd_addr, &q->properties);
 	if (retval)
 		goto out_deallocate_doorbell;
@@ -1326,7 +1327,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 				struct queue *q)
 {
 	int retval;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	bool preempt_all_queues;
 
 	preempt_all_queues = false;
@@ -1346,9 +1347,9 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 
 	}
 
-	mqd = dqm->ops.get_mqd_manager(dqm,
+	mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-	if (!mqd) {
+	if (!mqd_mgr) {
 		retval = -ENOMEM;
 		goto failed;
 	}
@@ -1370,7 +1371,7 @@ static int destroy_queue_cpsch(struct device_queue_manager *dqm,
 			qpd->reset_wavefronts = true;
 	}
 
-	mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+	mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 
 	/*
 	 * Unconditionally decrement this counter, regardless of the queue's
@@ -1520,7 +1521,7 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 	int retval;
 	struct queue *q, *next;
 	struct kernel_queue *kq, *kq_next;
-	struct mqd_manager *mqd;
+	struct mqd_manager *mqd_mgr;
 	struct device_process_node *cur, *next_dpn;
 	enum kfd_unmap_queues_filter filter =
 		KFD_UNMAP_QUEUES_FILTER_DYNAMIC_QUEUES;
@@ -1570,15 +1571,15 @@ static int process_termination_cpsch(struct device_queue_manager *dqm,
 
 	/* lastly, free mqd resources */
 	list_for_each_entry_safe(q, next, &qpd->queues_list, list) {
-		mqd = dqm->ops.get_mqd_manager(dqm,
+		mqd_mgr = dqm->ops.get_mqd_manager(dqm,
 			get_mqd_type_from_queue_type(q->properties.type));
-		if (!mqd) {
+		if (!mqd_mgr) {
 			retval = -ENOMEM;
 			goto out;
 		}
 		list_del(&q->list);
 		qpd->queue_count--;
-		mqd->uninit_mqd(mqd, q->mqd, q->mqd_mem_obj);
+		mqd_mgr->uninit_mqd(mqd_mgr, q->mqd, q->mqd_mem_obj);
 	}
 
 out:
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 70179a6826f4..52e708c4f9a5 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -172,7 +172,7 @@ struct device_queue_manager {
 	struct device_queue_manager_ops ops;
 	struct device_queue_manager_asic_ops asic_ops;
 
-	struct mqd_manager	*mqds[KFD_MQD_TYPE_MAX];
+	struct mqd_manager	*mqd_mgrs[KFD_MQD_TYPE_MAX];
 	struct packet_manager	packets;
 	struct kfd_dev		*dev;
 	struct mutex		lock_hidden; /* use dqm_lock/unlock(dqm) */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 476951d8c91c..2c8897e9073d 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -59,7 +59,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	switch (type) {
 	case KFD_QUEUE_TYPE_DIQ:
 	case KFD_QUEUE_TYPE_HIQ:
-		kq->mqd = dev->dqm->ops.get_mqd_manager(dev->dqm,
+		kq->mqd_mgr = dev->dqm->ops.get_mqd_manager(dev->dqm,
 						KFD_MQD_TYPE_HIQ);
 		break;
 	default:
@@ -67,7 +67,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		return false;
 	}
 
-	if (!kq->mqd)
+	if (!kq->mqd_mgr)
 		return false;
 
 	prop.doorbell_ptr = kfd_get_kernel_doorbell(dev, &prop.doorbell_off);
@@ -130,7 +130,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	kq->queue->device = dev;
 	kq->queue->process = kfd_get_process(current);
 
-	retval = kq->mqd->init_mqd(kq->mqd, &kq->queue->mqd,
+	retval = kq->mqd_mgr->init_mqd(kq->mqd_mgr, &kq->queue->mqd,
 					&kq->queue->mqd_mem_obj,
 					&kq->queue->gart_mqd_addr,
 					&kq->queue->properties);
@@ -142,9 +142,9 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 		pr_debug("Assigning hiq to hqd\n");
 		kq->queue->pipe = KFD_CIK_HIQ_PIPE;
 		kq->queue->queue = KFD_CIK_HIQ_QUEUE;
-		kq->mqd->load_mqd(kq->mqd, kq->queue->mqd, kq->queue->pipe,
-				  kq->queue->queue, &kq->queue->properties,
-				  NULL);
+		kq->mqd_mgr->load_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->pipe, kq->queue->queue,
+				&kq->queue->properties, NULL);
 	} else {
 		/* allocate fence for DIQ */
 
@@ -182,7 +182,7 @@ err_get_kernel_doorbell:
 static void uninitialize(struct kernel_queue *kq)
 {
 	if (kq->queue->properties.type == KFD_QUEUE_TYPE_HIQ)
-		kq->mqd->destroy_mqd(kq->mqd,
+		kq->mqd_mgr->destroy_mqd(kq->mqd_mgr,
 					kq->queue->mqd,
 					KFD_PREEMPT_TYPE_WAVEFRONT_RESET,
 					KFD_UNMAP_LATENCY_MS,
@@ -191,7 +191,8 @@ static void uninitialize(struct kernel_queue *kq)
 	else if (kq->queue->properties.type == KFD_QUEUE_TYPE_DIQ)
 		kfd_gtt_sa_free(kq->dev, kq->fence_mem_obj);
 
-	kq->mqd->uninit_mqd(kq->mqd, kq->queue->mqd, kq->queue->mqd_mem_obj);
+	kq->mqd_mgr->uninit_mqd(kq->mqd_mgr, kq->queue->mqd,
+				kq->queue->mqd_mem_obj);
 
 	kfd_gtt_sa_free(kq->dev, kq->rptr_mem);
 	kfd_gtt_sa_free(kq->dev, kq->wptr_mem);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
index 97aff2041a5d..a7116a939029 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.h
@@ -70,7 +70,7 @@ struct kernel_queue {
 
 	/* data */
 	struct kfd_dev		*dev;
-	struct mqd_manager	*mqd;
+	struct mqd_manager	*mqd_mgr;
 	struct queue		*queue;
 	uint64_t		pending_wptr64;
 	uint32_t		pending_wptr;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index d65ce0436b31..f85e5c06010e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -387,7 +387,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 	struct process_queue_node *pqn;
 	struct queue *q;
 	enum KFD_MQD_TYPE mqd_type;
-	struct mqd_manager *mqd_manager;
+	struct mqd_manager *mqd_mgr;
 	int r = 0;
 
 	list_for_each_entry(pqn, &pqm->queues, process_queue_list) {
@@ -410,11 +410,11 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 					   q->properties.type, q->device->id);
 				continue;
 			}
-			mqd_manager = q->device->dqm->ops.get_mqd_manager(
+			mqd_mgr = q->device->dqm->ops.get_mqd_manager(
 				q->device->dqm, mqd_type);
 		} else if (pqn->kq) {
 			q = pqn->kq->queue;
-			mqd_manager = pqn->kq->mqd;
+			mqd_mgr = pqn->kq->mqd_mgr;
 			switch (q->properties.type) {
 			case KFD_QUEUE_TYPE_DIQ:
 				seq_printf(m, "  DIQ on device %x\n",
@@ -434,7 +434,7 @@ int pqm_debugfs_mqds(struct seq_file *m, void *data)
 			continue;
 		}
 
-		r = mqd_manager->debugfs_show_mqd(m, q->mqd);
+		r = mqd_mgr->debugfs_show_mqd(m, q->mqd);
 		if (r != 0)
 			break;
 	}
-- 
cgit v1.2.3


From e7016d8e6f1b92888cc6093fd4e09d9f85934eb9 Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Wed, 11 Jul 2018 22:33:08 -0400
Subject: drm/amdkfd: Clean up reference of radeon
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/cik_int.h               |  5 ++-
 drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c            |  1 -
 drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h            | 37 ++++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              |  2 +-
 .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c |  2 +-
 5 files changed, 41 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/cik_int.h b/drivers/gpu/drm/amd/amdkfd/cik_int.h
index a2079a04a673..76f8677a7926 100644
--- a/drivers/gpu/drm/amd/amdkfd/cik_int.h
+++ b/drivers/gpu/drm/amd/amdkfd/cik_int.h
@@ -20,8 +20,8 @@
  * OTHER DEALINGS IN THE SOFTWARE.
  */
 
-#ifndef HSA_RADEON_CIK_INT_H_INCLUDED
-#define HSA_RADEON_CIK_INT_H_INCLUDED
+#ifndef CIK_INT_H_INCLUDED
+#define CIK_INT_H_INCLUDED
 
 #include <linux/types.h>
 
@@ -34,7 +34,6 @@ struct cik_ih_ring_entry {
 
 #define CIK_INTSRC_CP_END_OF_PIPE	0xB5
 #define CIK_INTSRC_CP_BAD_OPCODE	0xB7
-#define CIK_INTSRC_DEQUEUE_COMPLETE	0xC6
 #define CIK_INTSRC_SDMA_TRAP		0xE0
 #define CIK_INTSRC_SQ_INTERRUPT_MSG	0xEF
 #define CIK_INTSRC_GFX_PAGE_INV_FAULT	0x92
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
index afb26f205d29..a3441b0e385b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.c
@@ -38,7 +38,6 @@
 #include "kfd_dbgmgr.h"
 #include "kfd_dbgdev.h"
 #include "kfd_device_queue_manager.h"
-#include "../../radeon/cik_reg.h"
 
 static void dbgdev_address_watch_disable_nodiq(struct kfd_dev *dev)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
index 03424c20920c..0619c777b47e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_dbgdev.h
@@ -60,6 +60,9 @@ enum {
 	SH_REG_SIZE = SH_REG_END - SH_REG_BASE
 };
 
+/* SQ_CMD definitions */
+#define SQ_CMD						0x8DEC
+
 enum SQ_IND_CMD_CMD {
 	SQ_IND_CMD_CMD_NULL = 0x00000000,
 	SQ_IND_CMD_CMD_HALT = 0x00000001,
@@ -190,4 +193,38 @@ union ULARGE_INTEGER {
 void kfd_dbgdev_init(struct kfd_dbgdev *pdbgdev, struct kfd_dev *pdev,
 			enum DBGDEV_TYPE type);
 
+union TCP_WATCH_CNTL_BITS {
+	struct {
+		uint32_t mask:24;
+		uint32_t vmid:4;
+		uint32_t atc:1;
+		uint32_t mode:2;
+		uint32_t valid:1;
+	} bitfields, bits;
+	uint32_t u32All;
+	signed int i32All;
+	float f32All;
+};
+
+enum {
+	ADDRESS_WATCH_REG_CNTL_ATC_BIT = 0x10000000UL,
+	ADDRESS_WATCH_REG_CNTL_DEFAULT_MASK = 0x00FFFFFF,
+	ADDRESS_WATCH_REG_ADDLOW_MASK_EXTENSION = 0x03000000,
+	/* extend the mask to 26 bits in order to match the low address field */
+	ADDRESS_WATCH_REG_ADDLOW_SHIFT = 6,
+	ADDRESS_WATCH_REG_ADDHIGH_MASK = 0xFFFF
+};
+
+enum {
+	MAX_TRAPID = 8,		/* 3 bits in the bitfield. */
+	MAX_WATCH_ADDRESSES = 4
+};
+
+enum {
+	ADDRESS_WATCH_REG_ADDR_HI = 0,
+	ADDRESS_WATCH_REG_ADDR_LO,
+	ADDRESS_WATCH_REG_CNTL,
+	ADDRESS_WATCH_REG_MAX
+};
+
 #endif	/* KFD_DBGDEV_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 0646eda473df..37d179ed51dc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -73,7 +73,7 @@
 
 /*
  * When working with cp scheduler we should assign the HIQ manually or via
- * the radeon driver to a fixed hqd slot, here are the fixed HIQ hqd slot
+ * the amdgpu driver to a fixed hqd slot, here are the fixed HIQ hqd slot
  * definitions for Kaveri. In Kaveri only the first ME queues participates
  * in the cp scheduling taking that in mind we set the HIQ slot in the
  * second ME.
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index f85e5c06010e..1303b1457950 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -209,7 +209,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 		     KFD_SCHED_POLICY_HWS_NO_OVERSUBSCRIPTION) &&
 		((dev->dqm->processes_count >= dev->vm_info.vmid_num_kfd) ||
 		(dev->dqm->queue_count >= get_queues_num(dev->dqm)))) {
-			pr_err("Over-subscription is not allowed in radeon_kfd.sched_policy == 1\n");
+			pr_debug("Over-subscription is not allowed when amdkfd.sched_policy == 1\n");
 			retval = -EPERM;
 			goto err_create_queue;
 		}
-- 
cgit v1.2.3


From 8b2e77c1634935aefc9a4e2aacadda9cd30b78d7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:56 -0700
Subject: xfs: use iomap for blocksize == PAGE_SIZE readpage and readpages

For file systems with a block size that equals the page size we never do
partial reads, so we can use the buffer_head-less iomap versions of
readpage and readpages without conflicting with the buffer_head structures
create later in write_begin.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 8eb3ba3d4d00..85e1a625d42a 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1401,6 +1401,8 @@ xfs_vm_readpage(
 	struct page		*page)
 {
 	trace_xfs_vm_readpage(page->mapping->host, 1);
+	if (i_blocksize(page->mapping->host) == PAGE_SIZE)
+		return iomap_readpage(page, &xfs_iomap_ops);
 	return mpage_readpage(page, xfs_get_blocks);
 }
 
@@ -1412,6 +1414,8 @@ xfs_vm_readpages(
 	unsigned		nr_pages)
 {
 	trace_xfs_vm_readpages(mapping->host, nr_pages);
+	if (i_blocksize(mapping->host) == PAGE_SIZE)
+		return iomap_readpages(mapping, pages, nr_pages, &xfs_iomap_ops);
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
-- 
cgit v1.2.3


From 036257213836e13f08d1b28e528ba99e4ed3fc68 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:57 -0700
Subject: xfs: simplify xfs_aops_discard_page

Instead of looking at the buffer heads to see if a block is delalloc just
call xfs_bmap_punch_delalloc_range on the whole page - this will leave
any non-delalloc block intact and handle the iteration for us.  As a side
effect one more place stops caring about buffer heads and we can remove the
xfs_check_page_type function entirely.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 85 ++++++-------------------------------------------------
 1 file changed, 9 insertions(+), 76 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 85e1a625d42a..9b1a17b4cacb 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -710,49 +710,6 @@ xfs_map_at_offset(
 	clear_buffer_unwritten(bh);
 }
 
-/*
- * Test if a given page contains at least one buffer of a given @type.
- * If @check_all_buffers is true, then we walk all the buffers in the page to
- * try to find one of the type passed in. If it is not set, then the caller only
- * needs to check the first buffer on the page for a match.
- */
-STATIC bool
-xfs_check_page_type(
-	struct page		*page,
-	unsigned int		type,
-	bool			check_all_buffers)
-{
-	struct buffer_head	*bh;
-	struct buffer_head	*head;
-
-	if (PageWriteback(page))
-		return false;
-	if (!page->mapping)
-		return false;
-	if (!page_has_buffers(page))
-		return false;
-
-	bh = head = page_buffers(page);
-	do {
-		if (buffer_unwritten(bh)) {
-			if (type == XFS_IO_UNWRITTEN)
-				return true;
-		} else if (buffer_delay(bh)) {
-			if (type == XFS_IO_DELALLOC)
-				return true;
-		} else if (buffer_dirty(bh) && buffer_mapped(bh)) {
-			if (type == XFS_IO_OVERWRITE)
-				return true;
-		}
-
-		/* If we are only checking the first buffer, we are done now. */
-		if (!check_all_buffers)
-			break;
-	} while ((bh = bh->b_this_page) != head);
-
-	return false;
-}
-
 STATIC void
 xfs_vm_invalidatepage(
 	struct page		*page,
@@ -784,9 +741,6 @@ xfs_vm_invalidatepage(
  * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
  * truncation without a transaction as there is no space left for block
  * reservation (typically why we see a ENOSPC in writeback).
- *
- * This is not a performance critical path, so for now just do the punching a
- * buffer head at a time.
  */
 STATIC void
 xfs_aops_discard_page(
@@ -794,47 +748,26 @@ xfs_aops_discard_page(
 {
 	struct inode		*inode = page->mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
-	struct buffer_head	*bh, *head;
+	struct xfs_mount	*mp = ip->i_mount;
 	loff_t			offset = page_offset(page);
+	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	int			error;
 
-	if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
-		goto out_invalidate;
-
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(mp))
 		goto out_invalidate;
 
-	xfs_alert(ip->i_mount,
+	xfs_alert(mp,
 		"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
 			page, ip->i_ino, offset);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	bh = head = page_buffers(page);
-	do {
-		int		error;
-		xfs_fileoff_t	start_fsb;
-
-		if (!buffer_delay(bh))
-			goto next_buffer;
-
-		start_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
-		error = xfs_bmap_punch_delalloc_range(ip, start_fsb, 1);
-		if (error) {
-			/* something screwed, just bail */
-			if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
-				xfs_alert(ip->i_mount,
-			"page discard unable to remove delalloc mapping.");
-			}
-			break;
-		}
-next_buffer:
-		offset += i_blocksize(inode);
-
-	} while ((bh = bh->b_this_page) != head);
-
+	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
+			PAGE_SIZE / i_blocksize(inode));
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	if (error && !XFS_FORCED_SHUTDOWN(mp))
+		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
 	xfs_vm_invalidatepage(page, 0, PAGE_SIZE);
-	return;
 }
 
 static int
-- 
cgit v1.2.3


From d43801775766972535a0f4b78af65d0c13055e36 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:57 -0700
Subject: xfs: move locking into xfs_bmap_punch_delalloc_range

Both callers want the same looking, so do it only once.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c      | 2 --
 fs/xfs/xfs_bmap_util.c | 9 +++++----
 fs/xfs/xfs_iomap.c     | 3 ---
 3 files changed, 5 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 9b1a17b4cacb..5c549e983d69 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -760,10 +760,8 @@ xfs_aops_discard_page(
 		"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
 			page, ip->i_ino, offset);
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
 			PAGE_SIZE / i_blocksize(inode));
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 83b1e8c6c18f..da561882c349 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -702,16 +702,15 @@ xfs_bmap_punch_delalloc_range(
 	struct xfs_iext_cursor	icur;
 	int			error = 0;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
 		if (error)
-			return error;
+			goto out_unlock;
 	}
 
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
-		return 0;
+		goto out_unlock;
 
 	while (got.br_startoff + got.br_blockcount > start_fsb) {
 		del = got;
@@ -735,6 +734,8 @@ xfs_bmap_punch_delalloc_range(
 			break;
 	}
 
+out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index e08a84d9ee72..10c54fc7d1b4 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1204,11 +1204,8 @@ xfs_file_iomap_end_delalloc(
 		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
 					 XFS_FSB_TO_B(mp, end_fsb) - 1);
 
-		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
 					       end_fsb - start_fsb);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 		if (error && !XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_alert(mp, "%s: unable to clean up ino %lld",
 				__func__, ip->i_ino);
-- 
cgit v1.2.3


From 91cdfd1761659f338e673aca72af3d0d50b88847 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:58 -0700
Subject: xfs: do not set the page uptodate in xfs_writepage_map

We already track the page uptodate status based on the buffer uptodate
status, which is updated whenever reading or zeroing blocks.

This code has been there since commit a ptool commit in 2002, which
claims to:

    "merge" the 2.4 fsx fix for block size < page size to 2.5.  This needed
    major changes to actually fit.

and isn't present in other writepage implementations.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 5c549e983d69..df80a383ccd8 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -849,7 +849,6 @@ xfs_writepage_map(
 	uint64_t		offset;
 	int			error = 0;
 	int			count = 0;
-	int			uptodate = 1;
 	unsigned int		new_type;
 
 	bh = head = page_buffers(page);
@@ -857,8 +856,6 @@ xfs_writepage_map(
 	do {
 		if (offset >= end_offset)
 			break;
-		if (!buffer_uptodate(bh))
-			uptodate = 0;
 
 		/*
 		 * set_page_dirty dirties all buffers in a page, independent
@@ -922,9 +919,6 @@ xfs_writepage_map(
 
 	} while (offset += len, ((bh = bh->b_this_page) != head));
 
-	if (uptodate && bh == head)
-		SetPageUptodate(page);
-
 	ASSERT(wpc->ioend || list_empty(&submit_list));
 
 out:
-- 
cgit v1.2.3


From c57371a16d074bb4eafe6b73f29360085ecb2064 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:58 -0700
Subject: xfs: don't clear imap_valid for a non-uptodate buffers

Finding a buffer that isn't uptodate doesn't invalidate the mapping for
any given block.  The last_sector check will already take care of starting
another ioend as soon as we find any non-update buffer, and if the current
mapping doesn't include the next uptodate buffer the xfs_imap_valid check
will take care of it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index df80a383ccd8..1d1cb917cc6e 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -863,10 +863,8 @@ xfs_writepage_map(
 		 * meaningless for holes (!mapped && uptodate), so skip
 		 * buffers covering holes here.
 		 */
-		if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
-			wpc->imap_valid = false;
+		if (!buffer_mapped(bh) && buffer_uptodate(bh))
 			continue;
-		}
 
 		if (buffer_unwritten(bh))
 			new_type = XFS_IO_UNWRITTEN;
@@ -879,11 +877,8 @@ xfs_writepage_map(
 				ASSERT(buffer_mapped(bh));
 			/*
 			 * This buffer is not uptodate and will not be
-			 * written to disk.  Ensure that we will put any
-			 * subsequent writeable buffers into a new
-			 * ioend.
+			 * written to disk.
 			 */
-			wpc->imap_valid = false;
 			continue;
 		}
 
-- 
cgit v1.2.3


From a7b28f72ab90fe7a2f438360df5f6fda4237afdc Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:59 -0700
Subject: xfs: don't use XFS_BMAPI_IGSTATE in xfs_map_blocks

We want to be able to use the extent state as a reliably indicator for
the type of I/O, and stop using the buffer head state.  For this we
need to stop using the XFS_BMAPI_IGSTATE so that we don't see merged
extents of different types.

Based on a patch from Dave Chinner.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 1d1cb917cc6e..6b6150683343 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -373,7 +373,6 @@ xfs_map_blocks(
 	ssize_t			count = i_blocksize(inode);
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			error = 0;
-	int			bmapi_flags = XFS_BMAPI_ENTIRE;
 	int			nimaps = 1;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -393,8 +392,6 @@ xfs_map_blocks(
 		return 0;
 
 	ASSERT(type != XFS_IO_COW);
-	if (type == XFS_IO_UNWRITTEN)
-		bmapi_flags |= XFS_BMAPI_IGSTATE;
 
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
@@ -406,7 +403,7 @@ xfs_map_blocks(
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
-				imap, &nimaps, bmapi_flags);
+				imap, &nimaps, XFS_BMAPI_ENTIRE);
 	/*
 	 * Truncate an overwrite extent if there's a pending CoW
 	 * reservation before the end of this extent.  This forces us
-- 
cgit v1.2.3


From fca8c805425c0d9435097a6c780e95332e54613a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:59 -0700
Subject: xfs: remove xfs_reflink_trim_irec_to_next_cow

We already have to check for overlapping COW extents everytime we
come back to a page in xfs_writepage_map / xfs_map_cow, so this
additional trim is not required.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c    |  7 -------
 fs/xfs/xfs_reflink.c | 33 ---------------------------------
 fs/xfs/xfs_reflink.h |  2 --
 fs/xfs/xfs_trace.h   |  1 -
 4 files changed, 43 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 6b6150683343..08605432c497 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -404,13 +404,6 @@ xfs_map_blocks(
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
 				imap, &nimaps, XFS_BMAPI_ENTIRE);
-	/*
-	 * Truncate an overwrite extent if there's a pending CoW
-	 * reservation before the end of this extent.  This forces us
-	 * to come back to writepage to take care of the CoW.
-	 */
-	if (nimaps && type == XFS_IO_OVERWRITE)
-		xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb, imap);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 	if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 592fb2071a03..22c11b98ab26 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -500,39 +500,6 @@ xfs_reflink_find_cow_mapping(
 	return true;
 }
 
-/*
- * Trim an extent to end at the next CoW reservation past offset_fsb.
- */
-void
-xfs_reflink_trim_irec_to_next_cow(
-	struct xfs_inode		*ip,
-	xfs_fileoff_t			offset_fsb,
-	struct xfs_bmbt_irec		*imap)
-{
-	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	struct xfs_bmbt_irec		got;
-	struct xfs_iext_cursor		icur;
-
-	if (!xfs_is_reflink_inode(ip))
-		return;
-
-	/* Find the extent in the CoW fork. */
-	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got))
-		return;
-
-	/* This is the extent before; try sliding up one. */
-	if (got.br_startoff < offset_fsb) {
-		if (!xfs_iext_next_extent(ifp, &icur, &got))
-			return;
-	}
-
-	if (got.br_startoff >= imap->br_startoff + imap->br_blockcount)
-		return;
-
-	imap->br_blockcount = got.br_startoff - imap->br_startoff;
-	trace_xfs_reflink_trim_irec(ip, imap);
-}
-
 /*
  * Cancel CoW reservations for some block range of an inode.
  *
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 1532827ba911..6f9f98894abc 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -20,8 +20,6 @@ extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
 		struct xfs_bmbt_irec *imap);
-extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
-		xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap);
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 972d45d28097..a5b01529ecf6 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3216,7 +3216,6 @@ DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write);
 DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
-- 
cgit v1.2.3


From 5c665e5b5af6b8ad3e38ee73cb495ec695bcf589 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:25:59 -0700
Subject: xfs: remove xfs_map_cow

We can handle the existing cow mapping case as a special case directly
in xfs_writepage_map, and share code for allocating delalloc blocks
with regular I/O in xfs_map_blocks.  This means we need to always
call xfs_map_blocks for reflink inodes, but we can still skip most of
the work if it turns out that there is no COW mapping overlapping the
current block.

As a subtle detail we need to start caching holes in the wpc to deal
with the case of COW reservations between EOF.  But we'll need that
infrastructure later anyway, so this is no big deal.

Based on a patch from Dave Chinner.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 195 +++++++++++++++++++++++++++---------------------------
 fs/xfs/xfs_aops.h |   4 +-
 2 files changed, 100 insertions(+), 99 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 08605432c497..65454a4f4d93 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -363,70 +363,107 @@ xfs_end_bio(
 
 STATIC int
 xfs_map_blocks(
+	struct xfs_writepage_ctx *wpc,
 	struct inode		*inode,
-	loff_t			offset,
-	struct xfs_bmbt_irec	*imap,
-	int			type)
+	loff_t			offset)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			count = i_blocksize(inode);
-	xfs_fileoff_t		offset_fsb, end_fsb;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset), end_fsb;
+	struct xfs_bmbt_irec	imap;
+	int			whichfork = XFS_DATA_FORK;
 	int			error = 0;
 	int			nimaps = 1;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	/*
-	 * Truncate can race with writeback since writeback doesn't take the
-	 * iolock and truncate decreases the file size before it starts
-	 * truncating the pages between new_size and old_size.  Therefore, we
-	 * can end up in the situation where writeback gets a CoW fork mapping
-	 * but the truncate makes the mapping invalid and we end up in here
-	 * trying to get a new mapping.  Bail out here so that we simply never
-	 * get a valid mapping and so we drop the write altogether.  The page
-	 * truncation will kill the contents anyway.
-	 */
-	if (type == XFS_IO_COW && offset > i_size_read(inode))
-		return 0;
-
-	ASSERT(type != XFS_IO_COW);
-
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 
+	if (xfs_is_reflink_inode(ip) &&
+	    xfs_reflink_find_cow_mapping(ip, offset, &imap)) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		/*
+		 * Truncate can race with writeback since writeback doesn't
+		 * take the iolock and truncate decreases the file size before
+		 * it starts truncating the pages between new_size and old_size.
+		 * Therefore, we can end up in the situation where writeback
+		 * gets a CoW fork mapping but the truncate makes the mapping
+		 * invalid and we end up in here trying to get a new mapping.
+		 * bail out here so that we simply never get a valid mapping
+		 * and so we drop the write altogether.  The page truncation
+		 * will kill the contents anyway.
+		 */
+		if (offset > i_size_read(inode)) {
+			wpc->io_type = XFS_IO_HOLE;
+			return 0;
+		}
+		whichfork = XFS_COW_FORK;
+		wpc->io_type = XFS_IO_COW;
+		goto allocate_blocks;
+	}
+
+	/*
+	 * Map valid and no COW extent in the way?  We're done.
+	 */
+	if (wpc->imap_valid) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		return 0;
+	}
+
+	/*
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.
+	 */
 	if (offset > mp->m_super->s_maxbytes - count)
 		count = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
-				imap, &nimaps, XFS_BMAPI_ENTIRE);
+				&imap, &nimaps, XFS_BMAPI_ENTIRE);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
 	if (error)
 		return error;
 
-	if (type == XFS_IO_DELALLOC &&
-	    (!nimaps || isnullstartblock(imap->br_startblock))) {
-		error = xfs_iomap_write_allocate(ip, XFS_DATA_FORK, offset,
-				imap);
-		if (!error)
-			trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
-		return error;
+	if (!nimaps) {
+		/*
+		 * Lookup returns no match? Beyond eof? regardless,
+		 * return it as a hole so we don't write it
+		 */
+		imap.br_startoff = offset_fsb;
+		imap.br_blockcount = end_fsb - offset_fsb;
+		imap.br_startblock = HOLESTARTBLOCK;
+		wpc->io_type = XFS_IO_HOLE;
+	} else if (imap.br_startblock == HOLESTARTBLOCK) {
+		/* landed in a hole */
+		wpc->io_type = XFS_IO_HOLE;
 	}
 
+	if (wpc->io_type == XFS_IO_DELALLOC &&
+	    (!nimaps || isnullstartblock(imap.br_startblock)))
+		goto allocate_blocks;
+
 #ifdef DEBUG
-	if (type == XFS_IO_UNWRITTEN) {
+	if (wpc->io_type == XFS_IO_UNWRITTEN) {
 		ASSERT(nimaps);
-		ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-		ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
+		ASSERT(imap.br_startblock != HOLESTARTBLOCK);
+		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
 	}
 #endif
-	if (nimaps)
-		trace_xfs_map_blocks_found(ip, offset, count, type, imap);
+	wpc->imap = imap;
+	trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap);
+	return 0;
+allocate_blocks:
+	error = xfs_iomap_write_allocate(ip, whichfork, offset, &imap);
+	if (error)
+		return error;
+	wpc->imap = imap;
+	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap);
 	return 0;
 }
 
@@ -758,56 +795,6 @@ out_invalidate:
 	xfs_vm_invalidatepage(page, 0, PAGE_SIZE);
 }
 
-static int
-xfs_map_cow(
-	struct xfs_writepage_ctx *wpc,
-	struct inode		*inode,
-	loff_t			offset,
-	unsigned int		*new_type)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_bmbt_irec	imap;
-	bool			is_cow = false;
-	int			error;
-
-	/*
-	 * If we already have a valid COW mapping keep using it.
-	 */
-	if (wpc->io_type == XFS_IO_COW) {
-		wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap, offset);
-		if (wpc->imap_valid) {
-			*new_type = XFS_IO_COW;
-			return 0;
-		}
-	}
-
-	/*
-	 * Else we need to check if there is a COW mapping at this offset.
-	 */
-	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	if (!is_cow)
-		return 0;
-
-	/*
-	 * And if the COW mapping has a delayed extent here we need to
-	 * allocate real space for it now.
-	 */
-	if (isnullstartblock(imap.br_startblock)) {
-		error = xfs_iomap_write_allocate(ip, XFS_COW_FORK, offset,
-				&imap);
-		if (error)
-			return error;
-	}
-
-	wpc->io_type = *new_type = XFS_IO_COW;
-	wpc->imap_valid = true;
-	wpc->imap = imap;
-	return 0;
-}
-
 /*
  * We implement an immediate ioend submission policy here to avoid needing to
  * chain multiple ioends and hence nest mempool allocations which can violate
@@ -836,7 +823,7 @@ xfs_writepage_map(
 	struct xfs_ioend	*ioend, *next;
 	struct buffer_head	*bh, *head;
 	ssize_t			len = i_blocksize(inode);
-	uint64_t		offset;
+	uint64_t		offset;	/* file offset of page */
 	int			error = 0;
 	int			count = 0;
 	unsigned int		new_type;
@@ -872,10 +859,13 @@ xfs_writepage_map(
 			continue;
 		}
 
-		if (xfs_is_reflink_inode(XFS_I(inode))) {
-			error = xfs_map_cow(wpc, inode, offset, &new_type);
-			if (error)
-				goto out;
+		/*
+		 * If we already have a valid COW mapping keep using it.
+		 */
+		if (wpc->io_type == XFS_IO_COW &&
+		    xfs_imap_valid(inode, &wpc->imap, offset)) {
+			wpc->imap_valid = true;
+			new_type = XFS_IO_COW;
 		}
 
 		if (wpc->io_type != new_type) {
@@ -886,22 +876,31 @@ xfs_writepage_map(
 		if (wpc->imap_valid)
 			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
 							 offset);
-		if (!wpc->imap_valid) {
-			error = xfs_map_blocks(inode, offset, &wpc->imap,
-					     wpc->io_type);
+
+		/*
+		 * COW fork blocks can overlap data fork blocks even if the
+		 * blocks aren't shared. COW I/O always takes precedent, so we
+		 * must always check for overlap on reflink inodes unless the
+		 * mapping is already a COW one.
+		 */
+		if (!wpc->imap_valid ||
+		    (xfs_is_reflink_inode(XFS_I(inode)) &&
+		     wpc->io_type != XFS_IO_COW)) {
+			error = xfs_map_blocks(wpc, inode, offset);
 			if (error)
 				goto out;
 			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
 							 offset);
 		}
-		if (wpc->imap_valid) {
-			lock_buffer(bh);
-			if (wpc->io_type != XFS_IO_OVERWRITE)
-				xfs_map_at_offset(inode, bh, &wpc->imap, offset);
-			xfs_add_to_ioend(inode, bh, offset, wpc, wbc, &submit_list);
-			count++;
-		}
 
+		if (!wpc->imap_valid || wpc->io_type == XFS_IO_HOLE)
+			continue;
+
+		lock_buffer(bh);
+		if (wpc->io_type != XFS_IO_OVERWRITE)
+			xfs_map_at_offset(inode, bh, &wpc->imap, offset);
+		xfs_add_to_ioend(inode, bh, offset, wpc, wbc, &submit_list);
+		count++;
 	} while (offset += len, ((bh = bh->b_this_page) != head));
 
 	ASSERT(wpc->ioend || list_empty(&submit_list));
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index 25bc6d4a1231..9af867951a10 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -17,6 +17,7 @@ enum {
 	XFS_IO_UNWRITTEN,	/* covers allocated but uninitialized data */
 	XFS_IO_OVERWRITE,	/* covers already allocated extent */
 	XFS_IO_COW,		/* covers copy-on-write extent */
+	XFS_IO_HOLE,		/* covers region without any block allocation */
 };
 
 #define XFS_IO_TYPES \
@@ -24,7 +25,8 @@ enum {
 	{ XFS_IO_DELALLOC,		"delalloc" }, \
 	{ XFS_IO_UNWRITTEN,		"unwritten" }, \
 	{ XFS_IO_OVERWRITE,		"overwrite" }, \
-	{ XFS_IO_COW,			"CoW" }
+	{ XFS_IO_COW,			"CoW" }, \
+	{ XFS_IO_HOLE,			"hole" }
 
 /*
  * Structure for buffered I/O completions.
-- 
cgit v1.2.3


From 6a4c95013608120b2d88be67c6871cb6b86aa5d6 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:00 -0700
Subject: xfs: rename the offset variable in xfs_writepage_map

Calling it file_offset makes the usage more clear, especially with
a new poffset variable that will be added soon for the offset inside
the page.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 65454a4f4d93..4dc5fcff226e 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -823,15 +823,15 @@ xfs_writepage_map(
 	struct xfs_ioend	*ioend, *next;
 	struct buffer_head	*bh, *head;
 	ssize_t			len = i_blocksize(inode);
-	uint64_t		offset;	/* file offset of page */
+	uint64_t		file_offset;	/* file offset of page */
 	int			error = 0;
 	int			count = 0;
 	unsigned int		new_type;
 
 	bh = head = page_buffers(page);
-	offset = page_offset(page);
+	file_offset = page_offset(page);
 	do {
-		if (offset >= end_offset)
+		if (file_offset >= end_offset)
 			break;
 
 		/*
@@ -863,7 +863,7 @@ xfs_writepage_map(
 		 * If we already have a valid COW mapping keep using it.
 		 */
 		if (wpc->io_type == XFS_IO_COW &&
-		    xfs_imap_valid(inode, &wpc->imap, offset)) {
+		    xfs_imap_valid(inode, &wpc->imap, file_offset)) {
 			wpc->imap_valid = true;
 			new_type = XFS_IO_COW;
 		}
@@ -875,7 +875,7 @@ xfs_writepage_map(
 
 		if (wpc->imap_valid)
 			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 offset);
+							 file_offset);
 
 		/*
 		 * COW fork blocks can overlap data fork blocks even if the
@@ -886,11 +886,11 @@ xfs_writepage_map(
 		if (!wpc->imap_valid ||
 		    (xfs_is_reflink_inode(XFS_I(inode)) &&
 		     wpc->io_type != XFS_IO_COW)) {
-			error = xfs_map_blocks(wpc, inode, offset);
+			error = xfs_map_blocks(wpc, inode, file_offset);
 			if (error)
 				goto out;
 			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 offset);
+							 file_offset);
 		}
 
 		if (!wpc->imap_valid || wpc->io_type == XFS_IO_HOLE)
@@ -898,10 +898,10 @@ xfs_writepage_map(
 
 		lock_buffer(bh);
 		if (wpc->io_type != XFS_IO_OVERWRITE)
-			xfs_map_at_offset(inode, bh, &wpc->imap, offset);
-		xfs_add_to_ioend(inode, bh, offset, wpc, wbc, &submit_list);
+			xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
+		xfs_add_to_ioend(inode, bh, file_offset, wpc, wbc, &submit_list);
 		count++;
-	} while (offset += len, ((bh = bh->b_this_page) != head));
+	} while (file_offset += len, ((bh = bh->b_this_page) != head));
 
 	ASSERT(wpc->ioend || list_empty(&submit_list));
 
-- 
cgit v1.2.3


From e2f6ad4624dfbde3a6c42c0cfbfc5553d93c3cae Mon Sep 17 00:00:00 2001
From: Dave Chinner <dchinner@redhat.com>
Date: Wed, 11 Jul 2018 22:26:00 -0700
Subject: xfs: make xfs_writepage_map extent map centric

xfs_writepage_map() iterates over the bufferheads on a page to decide
what sort of IO to do and what actions to take.  However, when it comes
to reflink and deciding when it needs to execute a COW operation, we no
longer look at the bufferhead state but instead we ignore than and look
up internal state held in the COW fork extent list.

This means xfs_writepage_map() is somewhat confused. It does stuff, then
ignores it, then tries to handle the impedence mismatch by shovelling the
results inside the existing mapping code.  It works, but it's a bit of a
mess and it makes it hard to fix the cached map bug that the writepage
code currently has.

To unify the two different mechanisms, we first have to choose a direction.
That's already been set - we're de-emphasising bufferheads so they are no
longer a control structure as we need to do taht to allow for eventual
removal.  Hence we need to move away from looking at bufferhead state to
determine what operations we need to perform.

We can't completely get rid of bufferheads yet - they do contain some
state that is absolutely necessary, such as whether that part of the page
contains valid data or not (buffer_uptodate()).  Other state in the
bufferhead is redundant:

	BH_dirty - the page is dirty, so we can ignore this and just
		write it
	BH_delay - we have delalloc extent info in the DATA fork extent
		tree
	BH_unwritten - same as BH_delay
	BH_mapped - indicates we've already used it once for IO and it is
		mapped to a disk address. Needs to be ignored for COW
		blocks.

The BH_mapped flag is an interesting case - it's supposed to indicate that
it's already mapped to disk and so we can just use it "as is".  In theory,
we don't even have to do an extent lookup to find where to write it too,
but we have to do that anyway to determine we are actually writing over a
valid extent.  Hence it's not even serving the purpose of avoiding a an
extent lookup during writeback, and so we can pretty much ignore it.
Especially as we have to ignore it for COW operations...

Therefore, use the extent map as the source of information to tell us
what actions we need to take and what sort of IO we should perform.  The
first step is to have xfs_map_blocks() set the io type according to what
it looks up.  This means it can easily handle both normal overwrite and
COW cases.  The only thing we also need to add is the ability to return
hole mappings.

We need to return and cache hole mappings now for the case of multiple
blocks per page.  We no longer use the BH_mapped to indicate a block over
a hole, so we have to get that info from xfs_map_blocks().  We cache it so
that holes that span two pages don't need separate lookups.  This allows us
to avoid ever doing write IO over a hole, too.

Now that we have xfs_map_blocks() returning both a cached map and the type
of IO we need to perform, we can rewrite xfs_writepage_map() to drop all
the bufferhead control. It's also much simplified because it doesn't need
to explicitly handle COW operations.  Instead of iterating bufferheads, it
iterates blocks within the page and then looks up what per-block state is
required from the appropriate bufferhead.  It then validates the cached
map, and if it's not valid, we get a new map.  If we don't get a valid map
or it's over a hole, we skip the block.

At this point, we have to remap the bufferhead via xfs_map_at_offset().
As previously noted, we had to do this even if the buffer was already
mapped as the mapping would be stale for XFS_IO_DELALLOC, XFS_IO_UNWRITTEN
and XFS_IO_COW IO types.  With xfs_map_blocks() now controlling the type,
even XFS_IO_OVERWRITE types need remapping, as converted-but-not-yet-
written delalloc extents beyond EOF can be reported at XFS_IO_OVERWRITE.
Bufferheads that span such regions still need their BH_Delay flags cleared
and their block numbers calculated, so we now unconditionally map each
bufferhead before submission.

But wait! There's more - remember the old "treat unwritten extents as
holes on read" hack?  Yeah, that means we can have a dirty page with
unmapped, unwritten bufferheads that contain data!  What makes these so
special is that the unwritten "hole" bufferheads do not have a valid block
device pointer, so if we attempt to write them xfs_add_to_ioend() blows
up. So we make xfs_map_at_offset() do the "realtime or data device"
lookup from the inode and ignore what was or wasn't put into the
bufferhead when the buffer was instantiated.

The astute reader will have realised by now that this code treats
unwritten extents in multiple-blocks-per-page situations differently.
If we get any combination of unwritten blocks on a dirty page that contain
valid data in the page, we're going to convert them to real extents.  This
can actually be a win, because it means that pages with interleaving
unwritten and written blocks will get converted to a single written extent
with zeros replacing the interspersed unwritten blocks.  This is actually
good for reducing extent list and conversion overhead, and it means we
issue a contiguous IO instead of lots of little ones.  The downside is
that we use up a little extra IO bandwidth.  Neither of these seem like a
bad thing given that spinning disks are seek sensitive, and SSDs/pmem have
bandwidth to burn and the lower Io latency/CPU overhead of fewer, larger
IOs will result in better performance on them...

As a result of all this, the only state we actually care about from the
bufferhead is a single flag - BH_Uptodate. We still use the bufferhead to
pass some information to the bio via xfs_add_to_ioend(), but that is
trivial to separate and pass explicitly.  This means we really only need
1 bit of state per block per page from the buffered write path in the
writeback path.  Everything else we do with the bufferhead is purely to
make the buffered IO front end continue to work correctly. i.e we've
pretty much marginalised bufferheads in the writeback path completely.

Signed-off-By: Dave Chinner <dchinner@redhat.com>
[hch: forward port, refactor and split off bits into other commits]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 88 +++++++++++++++++++++++--------------------------------
 1 file changed, 36 insertions(+), 52 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 4dc5fcff226e..815b0b29438b 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -442,19 +442,19 @@ xfs_map_blocks(
 	} else if (imap.br_startblock == HOLESTARTBLOCK) {
 		/* landed in a hole */
 		wpc->io_type = XFS_IO_HOLE;
-	}
-
-	if (wpc->io_type == XFS_IO_DELALLOC &&
-	    (!nimaps || isnullstartblock(imap.br_startblock)))
-		goto allocate_blocks;
+	} else {
+		if (isnullstartblock(imap.br_startblock)) {
+			/* got a delalloc extent */
+			wpc->io_type = XFS_IO_DELALLOC;
+			goto allocate_blocks;
+		}
 
-#ifdef DEBUG
-	if (wpc->io_type == XFS_IO_UNWRITTEN) {
-		ASSERT(nimaps);
-		ASSERT(imap.br_startblock != HOLESTARTBLOCK);
-		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
+		if (imap.br_state == XFS_EXT_UNWRITTEN)
+			wpc->io_type = XFS_IO_UNWRITTEN;
+		else
+			wpc->io_type = XFS_IO_OVERWRITE;
 	}
-#endif
+
 	wpc->imap = imap;
 	trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap);
 	return 0;
@@ -735,6 +735,14 @@ xfs_map_at_offset(
 	set_buffer_mapped(bh);
 	clear_buffer_delay(bh);
 	clear_buffer_unwritten(bh);
+
+	/*
+	 * If this is a realtime file, data may be on a different device.
+	 * to that pointed to from the buffer_head b_bdev currently. We can't
+	 * trust that the bufferhead has a already been mapped correctly, so
+	 * set the bdev now.
+	 */
+	bh->b_bdev = xfs_find_bdev_for_inode(inode);
 }
 
 STATIC void
@@ -821,58 +829,35 @@ xfs_writepage_map(
 {
 	LIST_HEAD(submit_list);
 	struct xfs_ioend	*ioend, *next;
-	struct buffer_head	*bh, *head;
+	struct buffer_head	*bh;
 	ssize_t			len = i_blocksize(inode);
 	uint64_t		file_offset;	/* file offset of page */
+	unsigned		poffset;	/* offset into page */
 	int			error = 0;
 	int			count = 0;
-	unsigned int		new_type;
 
-	bh = head = page_buffers(page);
+	/*
+	 * Walk the blocks on the page, and if we run off the end of the current
+	 * map or find the current map invalid, grab a new one.  We only use
+	 * bufferheads here to check per-block state - they no longer control
+	 * the iteration through the page. This allows us to replace the
+	 * bufferhead with some other state tracking mechanism in future.
+	 */
 	file_offset = page_offset(page);
-	do {
+	bh = page_buffers(page);
+	for (poffset = 0;
+	     poffset < PAGE_SIZE;
+	     poffset += len, file_offset += len, bh = bh->b_this_page) {
+		/* past the range we are writing, so nothing more to write. */
 		if (file_offset >= end_offset)
 			break;
 
-		/*
-		 * set_page_dirty dirties all buffers in a page, independent
-		 * of their state.  The dirty state however is entirely
-		 * meaningless for holes (!mapped && uptodate), so skip
-		 * buffers covering holes here.
-		 */
-		if (!buffer_mapped(bh) && buffer_uptodate(bh))
-			continue;
-
-		if (buffer_unwritten(bh))
-			new_type = XFS_IO_UNWRITTEN;
-		else if (buffer_delay(bh))
-			new_type = XFS_IO_DELALLOC;
-		else if (buffer_uptodate(bh))
-			new_type = XFS_IO_OVERWRITE;
-		else {
+		if (!buffer_uptodate(bh)) {
 			if (PageUptodate(page))
 				ASSERT(buffer_mapped(bh));
-			/*
-			 * This buffer is not uptodate and will not be
-			 * written to disk.
-			 */
 			continue;
 		}
 
-		/*
-		 * If we already have a valid COW mapping keep using it.
-		 */
-		if (wpc->io_type == XFS_IO_COW &&
-		    xfs_imap_valid(inode, &wpc->imap, file_offset)) {
-			wpc->imap_valid = true;
-			new_type = XFS_IO_COW;
-		}
-
-		if (wpc->io_type != new_type) {
-			wpc->io_type = new_type;
-			wpc->imap_valid = false;
-		}
-
 		if (wpc->imap_valid)
 			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
 							 file_offset);
@@ -897,11 +882,10 @@ xfs_writepage_map(
 			continue;
 
 		lock_buffer(bh);
-		if (wpc->io_type != XFS_IO_OVERWRITE)
-			xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
+		xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
 		xfs_add_to_ioend(inode, bh, file_offset, wpc, wbc, &submit_list);
 		count++;
-	} while (file_offset += len, ((bh = bh->b_this_page) != head));
+	}
 
 	ASSERT(wpc->ioend || list_empty(&submit_list));
 
-- 
cgit v1.2.3


From c3a2f9fff1bbe3cfc2070b2e9f1f0ad0d5ccda91 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:01 -0700
Subject: xfs: remove the now unused XFS_BMAPI_IGSTATE flag

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 6 ++----
 fs/xfs/libxfs/xfs_bmap.h | 3 ---
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7205268b30bc..68ea1f4b9c3f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -3788,8 +3788,7 @@ xfs_bmapi_update_map(
 		   mval[-1].br_startblock != HOLESTARTBLOCK &&
 		   mval->br_startblock == mval[-1].br_startblock +
 					  mval[-1].br_blockcount &&
-		   ((flags & XFS_BMAPI_IGSTATE) ||
-			mval[-1].br_state == mval->br_state)) {
+		   mval[-1].br_state == mval->br_state) {
 		ASSERT(mval->br_startoff ==
 		       mval[-1].br_startoff + mval[-1].br_blockcount);
 		mval[-1].br_blockcount += mval->br_blockcount;
@@ -3834,7 +3833,7 @@ xfs_bmapi_read(
 
 	ASSERT(*nmap >= 1);
 	ASSERT(!(flags & ~(XFS_BMAPI_ATTRFORK|XFS_BMAPI_ENTIRE|
-			   XFS_BMAPI_IGSTATE|XFS_BMAPI_COWFORK)));
+			   XFS_BMAPI_COWFORK)));
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED|XFS_ILOCK_EXCL));
 
 	if (unlikely(XFS_TEST_ERROR(
@@ -4279,7 +4278,6 @@ xfs_bmapi_write(
 
 	ASSERT(*nmap >= 1);
 	ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
-	ASSERT(!(flags & XFS_BMAPI_IGSTATE));
 	ASSERT(tp != NULL ||
 	       (flags & (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)) ==
 			(XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK));
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 9b49ddf99c41..44639588d1c7 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -68,8 +68,6 @@ struct xfs_extent_free_item
 #define XFS_BMAPI_METADATA	0x002	/* mapping metadata not user data */
 #define XFS_BMAPI_ATTRFORK	0x004	/* use attribute fork not data */
 #define XFS_BMAPI_PREALLOC	0x008	/* preallocation op: unwritten space */
-#define XFS_BMAPI_IGSTATE	0x010	/* Ignore state - */
-					/* combine contig. space */
 #define XFS_BMAPI_CONTIG	0x020	/* must allocate only one extent */
 /*
  * unwritten extent conversion - this needs write cache flushing and no additional
@@ -116,7 +114,6 @@ struct xfs_extent_free_item
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \
 	{ XFS_BMAPI_ATTRFORK,	"ATTRFORK" }, \
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
-	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
 	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
 	{ XFS_BMAPI_ZERO,	"ZERO" }, \
-- 
cgit v1.2.3


From 060d4eaa0bf30a8fc2d189e4d4922f6e9027857b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:01 -0700
Subject: xfs: remove xfs_reflink_find_cow_mapping

We only have one caller left, and open coding the simple extent list
lookup in it allows us to make the code both more understandable and
reuse calculations and variables already present.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c    | 19 +++++++++++++------
 fs/xfs/xfs_reflink.c | 30 ------------------------------
 fs/xfs/xfs_reflink.h |  2 --
 fs/xfs/xfs_trace.h   |  1 -
 4 files changed, 13 insertions(+), 39 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 815b0b29438b..5c5d8c832dcc 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -370,9 +370,10 @@ xfs_map_blocks(
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			count = i_blocksize(inode);
-	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset), end_fsb;
+	xfs_fileoff_t		offset_fsb, end_fsb;
 	struct xfs_bmbt_irec	imap;
 	int			whichfork = XFS_DATA_FORK;
+	struct xfs_iext_cursor	icur;
 	int			error = 0;
 	int			nimaps = 1;
 
@@ -384,8 +385,18 @@ xfs_map_blocks(
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 
+	if (offset > mp->m_super->s_maxbytes - count)
+		count = mp->m_super->s_maxbytes - offset;
+	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
+	offset_fsb = XFS_B_TO_FSBT(mp, offset);
+
+	/*
+	 * Check if this is offset is covered by a COW extents, and if yes use
+	 * it directly instead of looking up anything in the data fork.
+	 */
 	if (xfs_is_reflink_inode(ip) &&
-	    xfs_reflink_find_cow_mapping(ip, offset, &imap)) {
+	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap) &&
+	    imap.br_startoff <= offset_fsb) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		/*
 		 * Truncate can race with writeback since writeback doesn't
@@ -420,10 +431,6 @@ xfs_map_blocks(
 	 * offset.  This will convert delayed allocations (including COW ones)
 	 * into real extents.
 	 */
-	if (offset > mp->m_super->s_maxbytes - count)
-		count = mp->m_super->s_maxbytes - offset;
-	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
 				&imap, &nimaps, XFS_BMAPI_ENTIRE);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 22c11b98ab26..49e4913fa779 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -470,36 +470,6 @@ out:
 	return error;
 }
 
-/*
- * Find the CoW reservation for a given byte offset of a file.
- */
-bool
-xfs_reflink_find_cow_mapping(
-	struct xfs_inode		*ip,
-	xfs_off_t			offset,
-	struct xfs_bmbt_irec		*imap)
-{
-	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	xfs_fileoff_t			offset_fsb;
-	struct xfs_bmbt_irec		got;
-	struct xfs_iext_cursor		icur;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
-
-	if (!xfs_is_reflink_inode(ip))
-		return false;
-	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
-	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &icur, &got))
-		return false;
-	if (got.br_startoff > offset_fsb)
-		return false;
-
-	trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE,
-			&got);
-	*imap = got;
-	return true;
-}
-
 /*
  * Cancel CoW reservations for some block range of an inode.
  *
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index 6f9f98894abc..c585ad9552b2 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -18,8 +18,6 @@ extern int xfs_reflink_allocate_cow(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode);
 extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
-extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
-		struct xfs_bmbt_irec *imap);
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index a5b01529ecf6..1af123df19b5 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -3215,7 +3215,6 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow);
 DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write);
-DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping);
 
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
-- 
cgit v1.2.3


From 3345746ef38bb794ae9d4d0762adf151e452663e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:02 -0700
Subject: xfs: simplify xfs_map_blocks by using xfs_iext_lookup_extent directly

xfs_bmapi_read adds zero value in xfs_map_blocks.  Replace it with a
direct call to the low-level extent lookup function.

Note that we now always pass a 0 length to the trace points as we ask
for an unspecified len.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 5c5d8c832dcc..0bfcc2d06658 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -375,7 +375,6 @@ xfs_map_blocks(
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_iext_cursor	icur;
 	int			error = 0;
-	int			nimaps = 1;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
@@ -431,24 +430,16 @@ xfs_map_blocks(
 	 * offset.  This will convert delayed allocations (including COW ones)
 	 * into real extents.
 	 */
-	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
-				&imap, &nimaps, XFS_BMAPI_ENTIRE);
+	if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap))
+		imap.br_startoff = end_fsb;	/* fake a hole past EOF */
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	if (error)
-		return error;
 
-	if (!nimaps) {
-		/*
-		 * Lookup returns no match? Beyond eof? regardless,
-		 * return it as a hole so we don't write it
-		 */
+	if (imap.br_startoff > offset_fsb) {
+		/* landed in a hole or beyond EOF */
+		imap.br_blockcount = imap.br_startoff - offset_fsb;
 		imap.br_startoff = offset_fsb;
-		imap.br_blockcount = end_fsb - offset_fsb;
 		imap.br_startblock = HOLESTARTBLOCK;
 		wpc->io_type = XFS_IO_HOLE;
-	} else if (imap.br_startblock == HOLESTARTBLOCK) {
-		/* landed in a hole */
-		wpc->io_type = XFS_IO_HOLE;
 	} else {
 		if (isnullstartblock(imap.br_startblock)) {
 			/* got a delalloc extent */
-- 
cgit v1.2.3


From 889c65b3f60af4c840896478fc6151363ffa279f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:02 -0700
Subject: xfs: remove the imap_valid flag

Simplify the way we check for a valid imap - we know we have a valid
mapping after xfs_map_blocks returned successfully, and we know we can
call xfs_imap_valid on any imap, as it will always fail on a
zero-initialized map.

We can also remove the xfs_imap_valid function and fold it into
xfs_map_blocks now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 89 ++++++++++++++++++++++++-------------------------------
 1 file changed, 38 insertions(+), 51 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0bfcc2d06658..09092f10cff3 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -30,7 +30,6 @@
  */
 struct xfs_writepage_ctx {
 	struct xfs_bmbt_irec    imap;
-	bool			imap_valid;
 	unsigned int		io_type;
 	struct xfs_ioend	*ioend;
 	sector_t		last_block;
@@ -370,15 +369,47 @@ xfs_map_blocks(
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			count = i_blocksize(inode);
-	xfs_fileoff_t		offset_fsb, end_fsb;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset), end_fsb;
 	struct xfs_bmbt_irec	imap;
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_iext_cursor	icur;
+	bool			imap_valid;
 	int			error = 0;
 
+	/*
+	 * We have to make sure the cached mapping is within EOF to protect
+	 * against eofblocks trimming on file release leaving us with a stale
+	 * mapping. Otherwise, a page for a subsequent file extending buffered
+	 * write could get picked up by this writeback cycle and written to the
+	 * wrong blocks.
+	 *
+	 * Note that what we really want here is a generic mapping invalidation
+	 * mechanism to protect us from arbitrary extent modifying contexts, not
+	 * just eofblocks.
+	 */
+	xfs_trim_extent_eof(&wpc->imap, ip);
+
+	/*
+	 * COW fork blocks can overlap data fork blocks even if the blocks
+	 * aren't shared.  COW I/O always takes precedent, so we must always
+	 * check for overlap on reflink inodes unless the mapping is already a
+	 * COW one.
+	 */
+	imap_valid = offset_fsb >= wpc->imap.br_startoff &&
+		     offset_fsb < wpc->imap.br_startoff + wpc->imap.br_blockcount;
+	if (imap_valid &&
+	    (!xfs_is_reflink_inode(ip) || wpc->io_type == XFS_IO_COW))
+		return 0;
+
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
+	/*
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.  If we return without a valid map, it means we
+	 * landed in a hole and we skip the block.
+	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
@@ -387,7 +418,6 @@ xfs_map_blocks(
 	if (offset > mp->m_super->s_maxbytes - count)
 		count = mp->m_super->s_maxbytes - offset;
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 
 	/*
 	 * Check if this is offset is covered by a COW extents, and if yes use
@@ -420,7 +450,7 @@ xfs_map_blocks(
 	/*
 	 * Map valid and no COW extent in the way?  We're done.
 	 */
-	if (wpc->imap_valid) {
+	if (imap_valid) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		return 0;
 	}
@@ -465,31 +495,6 @@ allocate_blocks:
 	return 0;
 }
 
-STATIC bool
-xfs_imap_valid(
-	struct inode		*inode,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	offset >>= inode->i_blkbits;
-
-	/*
-	 * We have to make sure the cached mapping is within EOF to protect
-	 * against eofblocks trimming on file release leaving us with a stale
-	 * mapping. Otherwise, a page for a subsequent file extending buffered
-	 * write could get picked up by this writeback cycle and written to the
-	 * wrong blocks.
-	 *
-	 * Note that what we really want here is a generic mapping invalidation
-	 * mechanism to protect us from arbitrary extent modifying contexts, not
-	 * just eofblocks.
-	 */
-	xfs_trim_extent_eof(imap, XFS_I(inode));
-
-	return offset >= imap->br_startoff &&
-		offset < imap->br_startoff + imap->br_blockcount;
-}
-
 STATIC void
 xfs_start_buffer_writeback(
 	struct buffer_head	*bh)
@@ -856,27 +861,10 @@ xfs_writepage_map(
 			continue;
 		}
 
-		if (wpc->imap_valid)
-			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 file_offset);
-
-		/*
-		 * COW fork blocks can overlap data fork blocks even if the
-		 * blocks aren't shared. COW I/O always takes precedent, so we
-		 * must always check for overlap on reflink inodes unless the
-		 * mapping is already a COW one.
-		 */
-		if (!wpc->imap_valid ||
-		    (xfs_is_reflink_inode(XFS_I(inode)) &&
-		     wpc->io_type != XFS_IO_COW)) {
-			error = xfs_map_blocks(wpc, inode, file_offset);
-			if (error)
-				goto out;
-			wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
-							 file_offset);
-		}
-
-		if (!wpc->imap_valid || wpc->io_type == XFS_IO_HOLE)
+		error = xfs_map_blocks(wpc, inode, file_offset);
+		if (error)
+			break;
+		if (wpc->io_type == XFS_IO_HOLE)
 			continue;
 
 		lock_buffer(bh);
@@ -887,7 +875,6 @@ xfs_writepage_map(
 
 	ASSERT(wpc->ioend || list_empty(&submit_list));
 
-out:
 	/*
 	 * On error, we have to fail the ioend here because we have locked
 	 * buffers in the ioend. If we don't do this, we'll deadlock
-- 
cgit v1.2.3


From 3faed667644d787c3cf6f977f80bac7a013eb045 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:02 -0700
Subject: xfs: don't look at buffer heads in xfs_add_to_ioend

Calculate all information for the bio based on the passed in information
without requiring a buffer_head structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 68 ++++++++++++++++++++++++++-----------------------------
 1 file changed, 32 insertions(+), 36 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 09092f10cff3..6402e4323031 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -32,7 +32,6 @@ struct xfs_writepage_ctx {
 	struct xfs_bmbt_irec    imap;
 	unsigned int		io_type;
 	struct xfs_ioend	*ioend;
-	sector_t		last_block;
 };
 
 void
@@ -534,11 +533,6 @@ xfs_start_page_writeback(
 	unlock_page(page);
 }
 
-static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
-{
-	return bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
-}
-
 /*
  * Submit the bio for an ioend. We are passed an ioend with a bio attached to
  * it, and we submit that bio. The ioend may be used for multiple bio
@@ -604,27 +598,20 @@ xfs_submit_ioend(
 	return 0;
 }
 
-static void
-xfs_init_bio_from_bh(
-	struct bio		*bio,
-	struct buffer_head	*bh)
-{
-	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
-	bio_set_dev(bio, bh->b_bdev);
-}
-
 static struct xfs_ioend *
 xfs_alloc_ioend(
 	struct inode		*inode,
 	unsigned int		type,
 	xfs_off_t		offset,
-	struct buffer_head	*bh)
+	struct block_device	*bdev,
+	sector_t		sector)
 {
 	struct xfs_ioend	*ioend;
 	struct bio		*bio;
 
 	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, &xfs_ioend_bioset);
-	xfs_init_bio_from_bh(bio, bh);
+	bio_set_dev(bio, bdev);
+	bio->bi_iter.bi_sector = sector;
 
 	ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
 	INIT_LIST_HEAD(&ioend->io_list);
@@ -649,13 +636,14 @@ static void
 xfs_chain_bio(
 	struct xfs_ioend	*ioend,
 	struct writeback_control *wbc,
-	struct buffer_head	*bh)
+	struct block_device	*bdev,
+	sector_t		sector)
 {
 	struct bio *new;
 
 	new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
-	xfs_init_bio_from_bh(new, bh);
-
+	bio_set_dev(new, bdev);
+	new->bi_iter.bi_sector = sector;
 	bio_chain(ioend->io_bio, new);
 	bio_get(ioend->io_bio);		/* for xfs_destroy_ioend */
 	ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
@@ -665,39 +653,45 @@ xfs_chain_bio(
 }
 
 /*
- * Test to see if we've been building up a completion structure for
- * earlier buffers -- if so, we try to append to this ioend if we
- * can, otherwise we finish off any current ioend and start another.
- * Return the ioend we finished off so that the caller can submit it
- * once it has finished processing the dirty page.
+ * Test to see if we have an existing ioend structure that we could append to
+ * first, otherwise finish off the current ioend and start another.
  */
 STATIC void
 xfs_add_to_ioend(
 	struct inode		*inode,
-	struct buffer_head	*bh,
 	xfs_off_t		offset,
+	struct page		*page,
 	struct xfs_writepage_ctx *wpc,
 	struct writeback_control *wbc,
 	struct list_head	*iolist)
 {
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct block_device	*bdev = xfs_find_bdev_for_inode(inode);
+	unsigned		len = i_blocksize(inode);
+	unsigned		poff = offset & (PAGE_SIZE - 1);
+	sector_t		sector;
+
+	sector = xfs_fsb_to_db(ip, wpc->imap.br_startblock) +
+		((offset - XFS_FSB_TO_B(mp, wpc->imap.br_startoff)) >> 9);
+
 	if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
-	    bh->b_blocknr != wpc->last_block + 1 ||
+	    sector != bio_end_sector(wpc->ioend->io_bio) ||
 	    offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
 		if (wpc->ioend)
 			list_add(&wpc->ioend->io_list, iolist);
-		wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset, bh);
+		wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset,
+				bdev, sector);
 	}
 
 	/*
-	 * If the buffer doesn't fit into the bio we need to allocate a new
-	 * one.  This shouldn't happen more than once for a given buffer.
+	 * If the block doesn't fit into the bio we need to allocate a new
+	 * one.  This shouldn't happen more than once for a given block.
 	 */
-	while (xfs_bio_add_buffer(wpc->ioend->io_bio, bh) != bh->b_size)
-		xfs_chain_bio(wpc->ioend, wbc, bh);
+	while (bio_add_page(wpc->ioend->io_bio, page, len, poff) != len)
+		xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
 
-	wpc->ioend->io_size += bh->b_size;
-	wpc->last_block = bh->b_blocknr;
-	xfs_start_buffer_writeback(bh);
+	wpc->ioend->io_size += len;
 }
 
 STATIC void
@@ -869,7 +863,9 @@ xfs_writepage_map(
 
 		lock_buffer(bh);
 		xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
-		xfs_add_to_ioend(inode, bh, file_offset, wpc, wbc, &submit_list);
+		xfs_add_to_ioend(inode, file_offset, page, wpc, wbc,
+				&submit_list);
+		xfs_start_buffer_writeback(bh);
 		count++;
 	}
 
-- 
cgit v1.2.3


From 6d465e895343225e3ad35fe10d7b3e9f2f18faec Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:03 -0700
Subject: xfs: move all writeback buffer_head manipulation into
 xfs_map_at_offset

This keeps it in a single place so it can be made otional more easily.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 22 +++++-----------------
 1 file changed, 5 insertions(+), 17 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 6402e4323031..71b4ca60ff40 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -494,21 +494,6 @@ allocate_blocks:
 	return 0;
 }
 
-STATIC void
-xfs_start_buffer_writeback(
-	struct buffer_head	*bh)
-{
-	ASSERT(buffer_mapped(bh));
-	ASSERT(buffer_locked(bh));
-	ASSERT(!buffer_delay(bh));
-	ASSERT(!buffer_unwritten(bh));
-
-	bh->b_end_io = NULL;
-	set_buffer_async_write(bh);
-	set_buffer_uptodate(bh);
-	clear_buffer_dirty(bh);
-}
-
 STATIC void
 xfs_start_page_writeback(
 	struct page		*page,
@@ -728,6 +713,7 @@ xfs_map_at_offset(
 	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
 	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
 
+	lock_buffer(bh);
 	xfs_map_buffer(inode, bh, imap, offset);
 	set_buffer_mapped(bh);
 	clear_buffer_delay(bh);
@@ -740,6 +726,10 @@ xfs_map_at_offset(
 	 * set the bdev now.
 	 */
 	bh->b_bdev = xfs_find_bdev_for_inode(inode);
+	bh->b_end_io = NULL;
+	set_buffer_async_write(bh);
+	set_buffer_uptodate(bh);
+	clear_buffer_dirty(bh);
 }
 
 STATIC void
@@ -861,11 +851,9 @@ xfs_writepage_map(
 		if (wpc->io_type == XFS_IO_HOLE)
 			continue;
 
-		lock_buffer(bh);
 		xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
 		xfs_add_to_ioend(inode, file_offset, page, wpc, wbc,
 				&submit_list);
-		xfs_start_buffer_writeback(bh);
 		count++;
 	}
 
-- 
cgit v1.2.3


From 1b65d3dd2d5e938b035b2ad73d0b47f35b5ef9a0 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:03 -0700
Subject: xfs: remove xfs_start_page_writeback

This helper only has two callers, one of them with a constant error
argument.  Remove it to make pending changes to the code a little easier.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 46 ++++++++++++++++++++--------------------------
 1 file changed, 20 insertions(+), 26 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 71b4ca60ff40..af9224ea4ebf 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -494,30 +494,6 @@ allocate_blocks:
 	return 0;
 }
 
-STATIC void
-xfs_start_page_writeback(
-	struct page		*page,
-	int			clear_dirty)
-{
-	ASSERT(PageLocked(page));
-	ASSERT(!PageWriteback(page));
-
-	/*
-	 * if the page was not fully cleaned, we need to ensure that the higher
-	 * layers come back to it correctly. That means we need to keep the page
-	 * dirty, and for WB_SYNC_ALL writeback we need to ensure the
-	 * PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to
-	 * write this page in this writeback sweep will be made.
-	 */
-	if (clear_dirty) {
-		clear_page_dirty_for_io(page);
-		set_page_writeback(page);
-	} else
-		set_page_writeback_keepwrite(page);
-
-	unlock_page(page);
-}
-
 /*
  * Submit the bio for an ioend. We are passed an ioend with a bio attached to
  * it, and we submit that bio. The ioend may be used for multiple bio
@@ -858,6 +834,8 @@ xfs_writepage_map(
 	}
 
 	ASSERT(wpc->ioend || list_empty(&submit_list));
+	ASSERT(PageLocked(page));
+	ASSERT(!PageWriteback(page));
 
 	/*
 	 * On error, we have to fail the ioend here because we have locked
@@ -877,7 +855,21 @@ xfs_writepage_map(
 	 * treated correctly on error.
 	 */
 	if (count) {
-		xfs_start_page_writeback(page, !error);
+		/*
+		 * If the page was not fully cleaned, we need to ensure that the
+		 * higher layers come back to it correctly.  That means we need
+		 * to keep the page dirty, and for WB_SYNC_ALL writeback we need
+		 * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
+		 * so another attempt to write this page in this writeback sweep
+		 * will be made.
+		 */
+		if (error) {
+			set_page_writeback_keepwrite(page);
+		} else {
+			clear_page_dirty_for_io(page);
+			set_page_writeback(page);
+		}
+		unlock_page(page);
 
 		/*
 		 * Preserve the original error if there was one, otherwise catch
@@ -902,7 +894,9 @@ xfs_writepage_map(
 		 * race with a partial page truncate on a sub-page block sized
 		 * filesystem. In that case we need to mark the page clean.
 		 */
-		xfs_start_page_writeback(page, 1);
+		clear_page_dirty_for_io(page);
+		set_page_writeback(page);
+		unlock_page(page);
 		end_page_writeback(page);
 	}
 
-- 
cgit v1.2.3


From 8e1f065bea1b1c128c92ef7e386779a23cd5d342 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:04 -0700
Subject: xfs: refactor the tail of xfs_writepage_map

Rejuggle how we deal with the different error vs non-error and have
ioends vs not have ioend cases to keep the fast path streamlined, and
the duplicate code at a minimum.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c | 65 +++++++++++++++++++++++++++----------------------------
 1 file changed, 32 insertions(+), 33 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index af9224ea4ebf..c8e0d3055153 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -854,7 +854,14 @@ xfs_writepage_map(
 	 * submission of outstanding ioends on the writepage context so they are
 	 * treated correctly on error.
 	 */
-	if (count) {
+	if (unlikely(error)) {
+		if (!count) {
+			xfs_aops_discard_page(page);
+			ClearPageUptodate(page);
+			unlock_page(page);
+			goto done;
+		}
+
 		/*
 		 * If the page was not fully cleaned, we need to ensure that the
 		 * higher layers come back to it correctly.  That means we need
@@ -863,43 +870,35 @@ xfs_writepage_map(
 		 * so another attempt to write this page in this writeback sweep
 		 * will be made.
 		 */
-		if (error) {
-			set_page_writeback_keepwrite(page);
-		} else {
-			clear_page_dirty_for_io(page);
-			set_page_writeback(page);
-		}
-		unlock_page(page);
-
-		/*
-		 * Preserve the original error if there was one, otherwise catch
-		 * submission errors here and propagate into subsequent ioend
-		 * submissions.
-		 */
-		list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
-			int error2;
-
-			list_del_init(&ioend->io_list);
-			error2 = xfs_submit_ioend(wbc, ioend, error);
-			if (error2 && !error)
-				error = error2;
-		}
-	} else if (error) {
-		xfs_aops_discard_page(page);
-		ClearPageUptodate(page);
-		unlock_page(page);
+		set_page_writeback_keepwrite(page);
 	} else {
-		/*
-		 * We can end up here with no error and nothing to write if we
-		 * race with a partial page truncate on a sub-page block sized
-		 * filesystem. In that case we need to mark the page clean.
-		 */
 		clear_page_dirty_for_io(page);
 		set_page_writeback(page);
-		unlock_page(page);
-		end_page_writeback(page);
 	}
 
+	unlock_page(page);
+
+	/*
+	 * Preserve the original error if there was one, otherwise catch
+	 * submission errors here and propagate into subsequent ioend
+	 * submissions.
+	 */
+	list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
+		int error2;
+
+		list_del_init(&ioend->io_list);
+		error2 = xfs_submit_ioend(wbc, ioend, error);
+		if (error2 && !error)
+			error = error2;
+	}
+
+	/*
+	 * We can end up here with no error and nothing to write if we race with
+	 * a partial page truncate on a sub-page block sized filesystem.
+	 */
+	if (!count)
+		end_page_writeback(page);
+done:
 	mapping_set_error(page->mapping, error);
 	return error;
 }
-- 
cgit v1.2.3


From ac8ee54669c07e6b38b4cae13a65f5ec06a11323 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:04 -0700
Subject: xfs: allow writeback on pages without buffer heads

Disable the IOMAP_F_BUFFER_HEAD flag on file systems with a block size
equal to the page size, and deal with pages without buffer heads in
writeback.  Thanks to the previous refactoring this is basically trivial
now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c  | 51 +++++++++++++++++++++++++++++++++++++--------------
 fs/xfs/xfs_iomap.c |  3 ++-
 2 files changed, 39 insertions(+), 15 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index c8e0d3055153..0058f9893705 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -79,6 +79,19 @@ xfs_find_daxdev_for_inode(
 		return mp->m_ddev_targp->bt_daxdev;
 }
 
+static void
+xfs_finish_page_writeback(
+	struct inode		*inode,
+	struct bio_vec		*bvec,
+	int			error)
+{
+	if (error) {
+		SetPageError(bvec->bv_page);
+		mapping_set_error(inode->i_mapping, -EIO);
+	}
+	end_page_writeback(bvec->bv_page);
+}
+
 /*
  * We're now finished for good with this page.  Update the page state via the
  * associated buffer_heads, paying attention to the start and end offsets that
@@ -91,7 +104,7 @@ xfs_find_daxdev_for_inode(
  * and buffers potentially freed after every call to end_buffer_async_write.
  */
 static void
-xfs_finish_page_writeback(
+xfs_finish_buffer_writeback(
 	struct inode		*inode,
 	struct bio_vec		*bvec,
 	int			error)
@@ -166,9 +179,12 @@ xfs_destroy_ioend(
 			next = bio->bi_private;
 
 		/* walk each page on bio, ending page IO on them */
-		bio_for_each_segment_all(bvec, bio, i)
-			xfs_finish_page_writeback(inode, bvec, error);
-
+		bio_for_each_segment_all(bvec, bio, i) {
+			if (page_has_buffers(bvec->bv_page))
+				xfs_finish_buffer_writeback(inode, bvec, error);
+			else
+				xfs_finish_page_writeback(inode, bvec, error);
+		}
 		bio_put(bio);
 	}
 
@@ -792,13 +808,16 @@ xfs_writepage_map(
 {
 	LIST_HEAD(submit_list);
 	struct xfs_ioend	*ioend, *next;
-	struct buffer_head	*bh;
+	struct buffer_head	*bh = NULL;
 	ssize_t			len = i_blocksize(inode);
 	uint64_t		file_offset;	/* file offset of page */
 	unsigned		poffset;	/* offset into page */
 	int			error = 0;
 	int			count = 0;
 
+	if (page_has_buffers(page))
+		bh = page_buffers(page);
+
 	/*
 	 * Walk the blocks on the page, and if we run off the end of the current
 	 * map or find the current map invalid, grab a new one.  We only use
@@ -806,28 +825,34 @@ xfs_writepage_map(
 	 * the iteration through the page. This allows us to replace the
 	 * bufferhead with some other state tracking mechanism in future.
 	 */
-	file_offset = page_offset(page);
-	bh = page_buffers(page);
-	for (poffset = 0;
+	for (poffset = 0, file_offset = page_offset(page);
 	     poffset < PAGE_SIZE;
-	     poffset += len, file_offset += len, bh = bh->b_this_page) {
+	     poffset += len, file_offset += len) {
 		/* past the range we are writing, so nothing more to write. */
 		if (file_offset >= end_offset)
 			break;
 
-		if (!buffer_uptodate(bh)) {
+		if (bh && !buffer_uptodate(bh)) {
 			if (PageUptodate(page))
 				ASSERT(buffer_mapped(bh));
+			bh = bh->b_this_page;
 			continue;
 		}
 
 		error = xfs_map_blocks(wpc, inode, file_offset);
 		if (error)
 			break;
-		if (wpc->io_type == XFS_IO_HOLE)
+
+		if (wpc->io_type == XFS_IO_HOLE) {
+			if (bh)
+				bh = bh->b_this_page;
 			continue;
+		}
 
-		xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
+		if (bh) {
+			xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
+			bh = bh->b_this_page;
+		}
 		xfs_add_to_ioend(inode, file_offset, page, wpc, wbc,
 				&submit_list);
 		count++;
@@ -925,8 +950,6 @@ xfs_do_writepage(
 
 	trace_xfs_writepage(inode, page, 0, 0);
 
-	ASSERT(page_has_buffers(page));
-
 	/*
 	 * Refuse to write the page out if we are called from reclaim context.
 	 *
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 10c54fc7d1b4..7fe42a126ec1 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1032,7 +1032,8 @@ xfs_file_iomap_begin(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	iomap->flags |= IOMAP_F_BUFFER_HEAD;
+	if (i_blocksize(inode) < PAGE_SIZE)
+		iomap->flags |= IOMAP_F_BUFFER_HEAD;
 
 	if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
 			!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
-- 
cgit v1.2.3


From 9dc55f1389f9569acf9659e58dd836a9c70df217 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:05 -0700
Subject: iomap: add support for sub-pagesize buffered I/O without buffer heads

After already supporting a simple implementation of buffered writes for
the blocksize == PAGE_SIZE case in the last commit this adds full support
even for smaller block sizes.   There are three bits of per-block
information in the buffer_head structure that really matter for the iomap
read and write path:

 - uptodate status (BH_uptodate)
 - marked as currently under read I/O (BH_Async_Read)
 - marked as currently under write I/O (BH_Async_Write)

Instead of having new per-block structures this now adds a per-page
structure called struct iomap_page to track this information in a slightly
different form:

 - a bitmap for the per-block uptodate status.  For worst case of a 64k
   page size system this bitmap needs to contain 128 bits.  For the
   typical 4k page size case it only needs 8 bits, although we still
   need a full unsigned long due to the way the atomic bitmap API works.
 - two atomic_t counters are used to track the outstanding read and write
   counts

There is quite a bit of boilerplate code as the buffered I/O path uses
various helper methods, but the actual code is very straight forward.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c            | 280 ++++++++++++++++++++++++++++++++++++++++++++++----
 include/linux/iomap.h |  31 ++++++
 2 files changed, 290 insertions(+), 21 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 13cdcf33e6c0..07501a647d13 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -17,6 +17,7 @@
 #include <linux/iomap.h>
 #include <linux/uaccess.h>
 #include <linux/gfp.h>
+#include <linux/migrate.h>
 #include <linux/mm.h>
 #include <linux/mm_inline.h>
 #include <linux/swap.h>
@@ -104,6 +105,138 @@ iomap_sector(struct iomap *iomap, loff_t pos)
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
+static struct iomap_page *
+iomap_page_create(struct inode *inode, struct page *page)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (iop || i_blocksize(inode) == PAGE_SIZE)
+		return iop;
+
+	iop = kmalloc(sizeof(*iop), GFP_NOFS | __GFP_NOFAIL);
+	atomic_set(&iop->read_count, 0);
+	atomic_set(&iop->write_count, 0);
+	bitmap_zero(iop->uptodate, PAGE_SIZE / SECTOR_SIZE);
+	set_page_private(page, (unsigned long)iop);
+	SetPagePrivate(page);
+	return iop;
+}
+
+static void
+iomap_page_release(struct page *page)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (!iop)
+		return;
+	WARN_ON_ONCE(atomic_read(&iop->read_count));
+	WARN_ON_ONCE(atomic_read(&iop->write_count));
+	ClearPagePrivate(page);
+	set_page_private(page, 0);
+	kfree(iop);
+}
+
+/*
+ * Calculate the range inside the page that we actually need to read.
+ */
+static void
+iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
+		loff_t *pos, loff_t length, unsigned *offp, unsigned *lenp)
+{
+	unsigned block_bits = inode->i_blkbits;
+	unsigned block_size = (1 << block_bits);
+	unsigned poff = *pos & (PAGE_SIZE - 1);
+	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
+	unsigned first = poff >> block_bits;
+	unsigned last = (poff + plen - 1) >> block_bits;
+	unsigned end = (i_size_read(inode) & (PAGE_SIZE - 1)) >> block_bits;
+
+	/*
+	 * If the block size is smaller than the page size we need to check the
+	 * per-block uptodate status and adjust the offset and length if needed
+	 * to avoid reading in already uptodate ranges.
+	 */
+	if (iop) {
+		unsigned int i;
+
+		/* move forward for each leading block marked uptodate */
+		for (i = first; i <= last; i++) {
+			if (!test_bit(i, iop->uptodate))
+				break;
+			*pos += block_size;
+			poff += block_size;
+			plen -= block_size;
+			first++;
+		}
+
+		/* truncate len if we find any trailing uptodate block(s) */
+		for ( ; i <= last; i++) {
+			if (test_bit(i, iop->uptodate)) {
+				plen -= (last - i + 1) * block_size;
+				last = i - 1;
+				break;
+			}
+		}
+	}
+
+	/*
+	 * If the extent spans the block that contains the i_size we need to
+	 * handle both halves separately so that we properly zero data in the
+	 * page cache for blocks that are entirely outside of i_size.
+	 */
+	if (first <= end && last > end)
+		plen -= (last - end) * block_size;
+
+	*offp = poff;
+	*lenp = plen;
+}
+
+static void
+iomap_set_range_uptodate(struct page *page, unsigned off, unsigned len)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+	struct inode *inode = page->mapping->host;
+	unsigned first = off >> inode->i_blkbits;
+	unsigned last = (off + len - 1) >> inode->i_blkbits;
+	unsigned int i;
+	bool uptodate = true;
+
+	if (iop) {
+		for (i = 0; i < PAGE_SIZE / i_blocksize(inode); i++) {
+			if (i >= first && i <= last)
+				set_bit(i, iop->uptodate);
+			else if (!test_bit(i, iop->uptodate))
+				uptodate = false;
+		}
+	}
+
+	if (uptodate && !PageError(page))
+		SetPageUptodate(page);
+}
+
+static void
+iomap_read_finish(struct iomap_page *iop, struct page *page)
+{
+	if (!iop || atomic_dec_and_test(&iop->read_count))
+		unlock_page(page);
+}
+
+static void
+iomap_read_page_end_io(struct bio_vec *bvec, int error)
+{
+	struct page *page = bvec->bv_page;
+	struct iomap_page *iop = to_iomap_page(page);
+
+	if (unlikely(error)) {
+		ClearPageUptodate(page);
+		SetPageError(page);
+	} else {
+		iomap_set_range_uptodate(page, bvec->bv_offset, bvec->bv_len);
+	}
+
+	iomap_read_finish(iop, page);
+}
+
 static void
 iomap_read_inline_data(struct inode *inode, struct page *page,
 		struct iomap *iomap)
@@ -132,7 +265,7 @@ iomap_read_end_io(struct bio *bio)
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i)
-		page_endio(bvec->bv_page, false, error);
+		iomap_read_page_end_io(bvec, error);
 	bio_put(bio);
 }
 
@@ -150,9 +283,10 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 {
 	struct iomap_readpage_ctx *ctx = data;
 	struct page *page = ctx->cur_page;
-	unsigned poff = pos & (PAGE_SIZE - 1);
-	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
+	struct iomap_page *iop = iomap_page_create(inode, page);
 	bool is_contig = false;
+	loff_t orig_pos = pos;
+	unsigned poff, plen;
 	sector_t sector;
 
 	if (iomap->type == IOMAP_INLINE) {
@@ -161,13 +295,14 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		return PAGE_SIZE;
 	}
 
-	/* we don't support blocksize < PAGE_SIZE quite yet. */
-	WARN_ON_ONCE(pos != page_offset(page));
-	WARN_ON_ONCE(plen != PAGE_SIZE);
+	/* zero post-eof blocks as the page may be mapped */
+	iomap_adjust_read_range(inode, iop, &pos, length, &poff, &plen);
+	if (plen == 0)
+		goto done;
 
 	if (iomap->type != IOMAP_MAPPED || pos >= i_size_read(inode)) {
 		zero_user(page, poff, plen);
-		SetPageUptodate(page);
+		iomap_set_range_uptodate(page, poff, plen);
 		goto done;
 	}
 
@@ -183,6 +318,14 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		is_contig = true;
 	}
 
+	/*
+	 * If we start a new segment we need to increase the read count, and we
+	 * need to do so before submitting any previous full bio to make sure
+	 * that we don't prematurely unlock the page.
+	 */
+	if (iop)
+		atomic_inc(&iop->read_count);
+
 	if (!ctx->bio || !is_contig || bio_full(ctx->bio)) {
 		gfp_t gfp = mapping_gfp_constraint(page->mapping, GFP_KERNEL);
 		int nr_vecs = (length + PAGE_SIZE - 1) >> PAGE_SHIFT;
@@ -203,7 +346,13 @@ iomap_readpage_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 	__bio_add_page(ctx->bio, page, plen, poff);
 done:
-	return plen;
+	/*
+	 * Move the caller beyond our range so that it keeps making progress.
+	 * For that we have to include any leading non-uptodate ranges, but
+	 * we can skip trailing ones as they will be handled in the next
+	 * iteration.
+	 */
+	return pos - orig_pos + plen;
 }
 
 int
@@ -214,8 +363,6 @@ iomap_readpage(struct page *page, const struct iomap_ops *ops)
 	unsigned poff;
 	loff_t ret;
 
-	WARN_ON_ONCE(page_has_buffers(page));
-
 	for (poff = 0; poff < PAGE_SIZE; poff += ret) {
 		ret = iomap_apply(inode, page_offset(page) + poff,
 				PAGE_SIZE - poff, 0, ops, &ctx,
@@ -341,6 +488,84 @@ done:
 }
 EXPORT_SYMBOL_GPL(iomap_readpages);
 
+int
+iomap_is_partially_uptodate(struct page *page, unsigned long from,
+		unsigned long count)
+{
+	struct iomap_page *iop = to_iomap_page(page);
+	struct inode *inode = page->mapping->host;
+	unsigned first = from >> inode->i_blkbits;
+	unsigned last = (from + count - 1) >> inode->i_blkbits;
+	unsigned i;
+
+	if (iop) {
+		for (i = first; i <= last; i++)
+			if (!test_bit(i, iop->uptodate))
+				return 0;
+		return 1;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iomap_is_partially_uptodate);
+
+int
+iomap_releasepage(struct page *page, gfp_t gfp_mask)
+{
+	/*
+	 * mm accommodates an old ext3 case where clean pages might not have had
+	 * the dirty bit cleared. Thus, it can send actual dirty pages to
+	 * ->releasepage() via shrink_active_list(), skip those here.
+	 */
+	if (PageDirty(page) || PageWriteback(page))
+		return 0;
+	iomap_page_release(page);
+	return 1;
+}
+EXPORT_SYMBOL_GPL(iomap_releasepage);
+
+void
+iomap_invalidatepage(struct page *page, unsigned int offset, unsigned int len)
+{
+	/*
+	 * If we are invalidating the entire page, clear the dirty state from it
+	 * and release it to avoid unnecessary buildup of the LRU.
+	 */
+	if (offset == 0 && len == PAGE_SIZE) {
+		WARN_ON_ONCE(PageWriteback(page));
+		cancel_dirty_page(page);
+		iomap_page_release(page);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_invalidatepage);
+
+#ifdef CONFIG_MIGRATION
+int
+iomap_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page, enum migrate_mode mode)
+{
+	int ret;
+
+	ret = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
+	if (ret != MIGRATEPAGE_SUCCESS)
+		return ret;
+
+	if (page_has_private(page)) {
+		ClearPagePrivate(page);
+		set_page_private(newpage, page_private(page));
+		set_page_private(page, 0);
+		SetPagePrivate(newpage);
+	}
+
+	if (mode != MIGRATE_SYNC_NO_COPY)
+		migrate_page_copy(newpage, page);
+	else
+		migrate_page_states(newpage, page);
+	return MIGRATEPAGE_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(iomap_migrate_page);
+#endif /* CONFIG_MIGRATION */
+
 static void
 iomap_write_failed(struct inode *inode, loff_t pos, unsigned len)
 {
@@ -364,6 +589,7 @@ iomap_read_page_sync(struct inode *inode, loff_t block_start, struct page *page,
 
 	if (iomap->type != IOMAP_MAPPED || block_start >= i_size_read(inode)) {
 		zero_user_segments(page, poff, from, to, poff + plen);
+		iomap_set_range_uptodate(page, poff, plen);
 		return 0;
 	}
 
@@ -379,21 +605,33 @@ static int
 __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
 		struct page *page, struct iomap *iomap)
 {
+	struct iomap_page *iop = iomap_page_create(inode, page);
 	loff_t block_size = i_blocksize(inode);
 	loff_t block_start = pos & ~(block_size - 1);
 	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
-	unsigned poff = block_start & (PAGE_SIZE - 1);
-	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, block_end - block_start);
-	unsigned from = pos & (PAGE_SIZE - 1), to = from + len;
-
-	WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE);
+	unsigned from = pos & (PAGE_SIZE - 1), to = from + len, poff, plen;
+	int status = 0;
 
 	if (PageUptodate(page))
 		return 0;
-	if (from <= poff && to >= poff + plen)
-		return 0;
-	return iomap_read_page_sync(inode, block_start, page,
-			poff, plen, from, to, iomap);
+
+	do {
+		iomap_adjust_read_range(inode, iop, &block_start,
+				block_end - block_start, &poff, &plen);
+		if (plen == 0)
+			break;
+
+		if ((from > poff && from < poff + plen) ||
+		    (to > poff && to < poff + plen)) {
+			status = iomap_read_page_sync(inode, block_start, page,
+					poff, plen, from, to, iomap);
+			if (status)
+				break;
+		}
+
+	} while ((block_start += plen) < block_end);
+
+	return status;
 }
 
 static int
@@ -476,7 +714,7 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	if (unlikely(copied < len && !PageUptodate(page))) {
 		copied = 0;
 	} else {
-		SetPageUptodate(page);
+		iomap_set_range_uptodate(page, pos & (PAGE_SIZE - 1), len);
 		iomap_set_page_dirty(page);
 	}
 	return __generic_write_end(inode, pos, copied, page);
@@ -812,7 +1050,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 		block_commit_write(page, 0, length);
 	} else {
 		WARN_ON_ONCE(!PageUptodate(page));
-		WARN_ON_ONCE(i_blocksize(inode) < PAGE_SIZE);
+		iomap_page_create(inode, page);
 	}
 
 	return length;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 5eb9ca8d7ce5..3555d54bf79a 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -2,6 +2,9 @@
 #ifndef LINUX_IOMAP_H
 #define LINUX_IOMAP_H 1
 
+#include <linux/atomic.h>
+#include <linux/bitmap.h>
+#include <linux/mm.h>
 #include <linux/types.h>
 
 struct address_space;
@@ -98,12 +101,40 @@ struct iomap_ops {
 			ssize_t written, unsigned flags, struct iomap *iomap);
 };
 
+/*
+ * Structure allocate for each page when block size < PAGE_SIZE to track
+ * sub-page uptodate status and I/O completions.
+ */
+struct iomap_page {
+	atomic_t		read_count;
+	atomic_t		write_count;
+	DECLARE_BITMAP(uptodate, PAGE_SIZE / 512);
+};
+
+static inline struct iomap_page *to_iomap_page(struct page *page)
+{
+	if (page_has_private(page))
+		return (struct iomap_page *)page_private(page);
+	return NULL;
+}
+
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
 int iomap_readpage(struct page *page, const struct iomap_ops *ops);
 int iomap_readpages(struct address_space *mapping, struct list_head *pages,
 		unsigned nr_pages, const struct iomap_ops *ops);
 int iomap_set_page_dirty(struct page *page);
+int iomap_is_partially_uptodate(struct page *page, unsigned long from,
+		unsigned long count);
+int iomap_releasepage(struct page *page, gfp_t gfp_mask);
+void iomap_invalidatepage(struct page *page, unsigned int offset,
+		unsigned int len);
+#ifdef CONFIG_MIGRATION
+int iomap_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page, enum migrate_mode mode);
+#else
+#define iomap_migrate_page NULL
+#endif
 int iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-- 
cgit v1.2.3


From 82cb14175e7ddb08721fb1d766195cd10dad791a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:05 -0700
Subject: xfs: add support for sub-pagesize writeback without buffer_heads

Switch to using the iomap_page structure for checking sub-page uptodate
status and track sub-page I/O completion status, and remove large
quantities of boilerplate code working around buffer heads.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c  | 492 +++++++----------------------------------------------
 fs/xfs/xfs_buf.h   |   1 -
 fs/xfs/xfs_iomap.c |   3 -
 fs/xfs/xfs_super.c |   2 +-
 fs/xfs/xfs_trace.h |  18 +-
 5 files changed, 61 insertions(+), 455 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 0058f9893705..bae88ac1101d 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -20,9 +20,6 @@
 #include "xfs_bmap_util.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
-#include <linux/gfp.h>
-#include <linux/mpage.h>
-#include <linux/pagevec.h>
 #include <linux/writeback.h>
 
 /*
@@ -34,25 +31,6 @@ struct xfs_writepage_ctx {
 	struct xfs_ioend	*ioend;
 };
 
-void
-xfs_count_page_state(
-	struct page		*page,
-	int			*delalloc,
-	int			*unwritten)
-{
-	struct buffer_head	*bh, *head;
-
-	*delalloc = *unwritten = 0;
-
-	bh = head = page_buffers(page);
-	do {
-		if (buffer_unwritten(bh))
-			(*unwritten) = 1;
-		else if (buffer_delay(bh))
-			(*delalloc) = 1;
-	} while ((bh = bh->b_this_page) != head);
-}
-
 struct block_device *
 xfs_find_bdev_for_inode(
 	struct inode		*inode)
@@ -85,67 +63,17 @@ xfs_finish_page_writeback(
 	struct bio_vec		*bvec,
 	int			error)
 {
+	struct iomap_page	*iop = to_iomap_page(bvec->bv_page);
+
 	if (error) {
 		SetPageError(bvec->bv_page);
 		mapping_set_error(inode->i_mapping, -EIO);
 	}
-	end_page_writeback(bvec->bv_page);
-}
 
-/*
- * We're now finished for good with this page.  Update the page state via the
- * associated buffer_heads, paying attention to the start and end offsets that
- * we need to process on the page.
- *
- * Note that we open code the action in end_buffer_async_write here so that we
- * only have to iterate over the buffers attached to the page once.  This is not
- * only more efficient, but also ensures that we only calls end_page_writeback
- * at the end of the iteration, and thus avoids the pitfall of having the page
- * and buffers potentially freed after every call to end_buffer_async_write.
- */
-static void
-xfs_finish_buffer_writeback(
-	struct inode		*inode,
-	struct bio_vec		*bvec,
-	int			error)
-{
-	struct buffer_head	*head = page_buffers(bvec->bv_page), *bh = head;
-	bool			busy = false;
-	unsigned int		off = 0;
-	unsigned long		flags;
-
-	ASSERT(bvec->bv_offset < PAGE_SIZE);
-	ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
-	ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE);
-	ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
-
-	local_irq_save(flags);
-	bit_spin_lock(BH_Uptodate_Lock, &head->b_state);
-	do {
-		if (off >= bvec->bv_offset &&
-		    off < bvec->bv_offset + bvec->bv_len) {
-			ASSERT(buffer_async_write(bh));
-			ASSERT(bh->b_end_io == NULL);
-
-			if (error) {
-				mark_buffer_write_io_error(bh);
-				clear_buffer_uptodate(bh);
-				SetPageError(bvec->bv_page);
-			} else {
-				set_buffer_uptodate(bh);
-			}
-			clear_buffer_async_write(bh);
-			unlock_buffer(bh);
-		} else if (buffer_async_write(bh)) {
-			ASSERT(buffer_locked(bh));
-			busy = true;
-		}
-		off += bh->b_size;
-	} while ((bh = bh->b_this_page) != head);
-	bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
-	local_irq_restore(flags);
+	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
+	ASSERT(!iop || atomic_read(&iop->write_count) > 0);
 
-	if (!busy)
+	if (!iop || atomic_dec_and_test(&iop->write_count))
 		end_page_writeback(bvec->bv_page);
 }
 
@@ -179,12 +107,8 @@ xfs_destroy_ioend(
 			next = bio->bi_private;
 
 		/* walk each page on bio, ending page IO on them */
-		bio_for_each_segment_all(bvec, bio, i) {
-			if (page_has_buffers(bvec->bv_page))
-				xfs_finish_buffer_writeback(inode, bvec, error);
-			else
-				xfs_finish_page_writeback(inode, bvec, error);
-		}
+		bio_for_each_segment_all(bvec, bio, i)
+			xfs_finish_page_writeback(inode, bvec, error);
 		bio_put(bio);
 	}
 
@@ -638,6 +562,7 @@ xfs_add_to_ioend(
 	struct inode		*inode,
 	xfs_off_t		offset,
 	struct page		*page,
+	struct iomap_page	*iop,
 	struct xfs_writepage_ctx *wpc,
 	struct writeback_control *wbc,
 	struct list_head	*iolist)
@@ -661,100 +586,37 @@ xfs_add_to_ioend(
 				bdev, sector);
 	}
 
-	/*
-	 * If the block doesn't fit into the bio we need to allocate a new
-	 * one.  This shouldn't happen more than once for a given block.
-	 */
-	while (bio_add_page(wpc->ioend->io_bio, page, len, poff) != len)
-		xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
+	if (!__bio_try_merge_page(wpc->ioend->io_bio, page, len, poff)) {
+		if (iop)
+			atomic_inc(&iop->write_count);
+		if (bio_full(wpc->ioend->io_bio))
+			xfs_chain_bio(wpc->ioend, wbc, bdev, sector);
+		__bio_add_page(wpc->ioend->io_bio, page, len, poff);
+	}
 
 	wpc->ioend->io_size += len;
 }
 
-STATIC void
-xfs_map_buffer(
-	struct inode		*inode,
-	struct buffer_head	*bh,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	sector_t		bn;
-	struct xfs_mount	*m = XFS_I(inode)->i_mount;
-	xfs_off_t		iomap_offset = XFS_FSB_TO_B(m, imap->br_startoff);
-	xfs_daddr_t		iomap_bn = xfs_fsb_to_db(XFS_I(inode), imap->br_startblock);
-
-	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
-
-	bn = (iomap_bn >> (inode->i_blkbits - BBSHIFT)) +
-	      ((offset - iomap_offset) >> inode->i_blkbits);
-
-	ASSERT(bn || XFS_IS_REALTIME_INODE(XFS_I(inode)));
-
-	bh->b_blocknr = bn;
-	set_buffer_mapped(bh);
-}
-
-STATIC void
-xfs_map_at_offset(
-	struct inode		*inode,
-	struct buffer_head	*bh,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
-{
-	ASSERT(imap->br_startblock != HOLESTARTBLOCK);
-	ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
-
-	lock_buffer(bh);
-	xfs_map_buffer(inode, bh, imap, offset);
-	set_buffer_mapped(bh);
-	clear_buffer_delay(bh);
-	clear_buffer_unwritten(bh);
-
-	/*
-	 * If this is a realtime file, data may be on a different device.
-	 * to that pointed to from the buffer_head b_bdev currently. We can't
-	 * trust that the bufferhead has a already been mapped correctly, so
-	 * set the bdev now.
-	 */
-	bh->b_bdev = xfs_find_bdev_for_inode(inode);
-	bh->b_end_io = NULL;
-	set_buffer_async_write(bh);
-	set_buffer_uptodate(bh);
-	clear_buffer_dirty(bh);
-}
-
 STATIC void
 xfs_vm_invalidatepage(
 	struct page		*page,
 	unsigned int		offset,
 	unsigned int		length)
 {
-	trace_xfs_invalidatepage(page->mapping->host, page, offset,
-				 length);
-
-	/*
-	 * If we are invalidating the entire page, clear the dirty state from it
-	 * so that we can check for attempts to release dirty cached pages in
-	 * xfs_vm_releasepage().
-	 */
-	if (offset == 0 && length >= PAGE_SIZE)
-		cancel_dirty_page(page);
-	block_invalidatepage(page, offset, length);
+	trace_xfs_invalidatepage(page->mapping->host, page, offset, length);
+	iomap_invalidatepage(page, offset, length);
 }
 
 /*
- * If the page has delalloc buffers on it, we need to punch them out before we
- * invalidate the page. If we don't, we leave a stale delalloc mapping on the
- * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
- * is done on that same region - the delalloc extent is returned when none is
- * supposed to be there.
+ * If the page has delalloc blocks on it, we need to punch them out before we
+ * invalidate the page.  If we don't, we leave a stale delalloc mapping on the
+ * inode that can trip up a later direct I/O read operation on the same region.
  *
- * We prevent this by truncating away the delalloc regions on the page before
- * invalidating it. Because they are delalloc, we can do this without needing a
- * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
- * truncation without a transaction as there is no space left for block
- * reservation (typically why we see a ENOSPC in writeback).
+ * We prevent this by truncating away the delalloc regions on the page.  Because
+ * they are delalloc, we can do this without needing a transaction. Indeed - if
+ * we get ENOSPC errors, we have to be able to do this truncation without a
+ * transaction as there is no space left for block reservation (typically why we
+ * see a ENOSPC in writeback).
  */
 STATIC void
 xfs_aops_discard_page(
@@ -786,7 +648,7 @@ out_invalidate:
  * We implement an immediate ioend submission policy here to avoid needing to
  * chain multiple ioends and hence nest mempool allocations which can violate
  * forward progress guarantees we need to provide. The current ioend we are
- * adding buffers to is cached on the writepage context, and if the new buffer
+ * adding blocks to is cached on the writepage context, and if the new block
  * does not append to the cached ioend it will create a new ioend and cache that
  * instead.
  *
@@ -807,54 +669,33 @@ xfs_writepage_map(
 	uint64_t		end_offset)
 {
 	LIST_HEAD(submit_list);
+	struct iomap_page	*iop = to_iomap_page(page);
+	unsigned		len = i_blocksize(inode);
 	struct xfs_ioend	*ioend, *next;
-	struct buffer_head	*bh = NULL;
-	ssize_t			len = i_blocksize(inode);
 	uint64_t		file_offset;	/* file offset of page */
-	unsigned		poffset;	/* offset into page */
-	int			error = 0;
-	int			count = 0;
+	int			error = 0, count = 0, i;
 
-	if (page_has_buffers(page))
-		bh = page_buffers(page);
+	ASSERT(iop || i_blocksize(inode) == PAGE_SIZE);
+	ASSERT(!iop || atomic_read(&iop->write_count) == 0);
 
 	/*
-	 * Walk the blocks on the page, and if we run off the end of the current
-	 * map or find the current map invalid, grab a new one.  We only use
-	 * bufferheads here to check per-block state - they no longer control
-	 * the iteration through the page. This allows us to replace the
-	 * bufferhead with some other state tracking mechanism in future.
+	 * Walk through the page to find areas to write back. If we run off the
+	 * end of the current map or find the current map invalid, grab a new
+	 * one.
 	 */
-	for (poffset = 0, file_offset = page_offset(page);
-	     poffset < PAGE_SIZE;
-	     poffset += len, file_offset += len) {
-		/* past the range we are writing, so nothing more to write. */
-		if (file_offset >= end_offset)
-			break;
-
-		if (bh && !buffer_uptodate(bh)) {
-			if (PageUptodate(page))
-				ASSERT(buffer_mapped(bh));
-			bh = bh->b_this_page;
+	for (i = 0, file_offset = page_offset(page);
+	     i < (PAGE_SIZE >> inode->i_blkbits) && file_offset < end_offset;
+	     i++, file_offset += len) {
+		if (iop && !test_bit(i, iop->uptodate))
 			continue;
-		}
 
 		error = xfs_map_blocks(wpc, inode, file_offset);
 		if (error)
 			break;
-
-		if (wpc->io_type == XFS_IO_HOLE) {
-			if (bh)
-				bh = bh->b_this_page;
+		if (wpc->io_type == XFS_IO_HOLE)
 			continue;
-		}
-
-		if (bh) {
-			xfs_map_at_offset(inode, bh, &wpc->imap, file_offset);
-			bh = bh->b_this_page;
-		}
-		xfs_add_to_ioend(inode, file_offset, page, wpc, wbc,
-				&submit_list);
+		xfs_add_to_ioend(inode, file_offset, page, iop, wpc, wbc,
+				 &submit_list);
 		count++;
 	}
 
@@ -863,21 +704,18 @@ xfs_writepage_map(
 	ASSERT(!PageWriteback(page));
 
 	/*
-	 * On error, we have to fail the ioend here because we have locked
-	 * buffers in the ioend. If we don't do this, we'll deadlock
-	 * invalidating the page as that tries to lock the buffers on the page.
-	 * Also, because we may have set pages under writeback, we have to make
-	 * sure we run IO completion to mark the error state of the IO
-	 * appropriately, so we can't cancel the ioend directly here. That means
-	 * we have to mark this page as under writeback if we included any
-	 * buffers from it in the ioend chain so that completion treats it
-	 * correctly.
+	 * On error, we have to fail the ioend here because we may have set
+	 * pages under writeback, we have to make sure we run IO completion to
+	 * mark the error state of the IO appropriately, so we can't cancel the
+	 * ioend directly here.  That means we have to mark this page as under
+	 * writeback if we included any blocks from it in the ioend chain so
+	 * that completion treats it correctly.
 	 *
 	 * If we didn't include the page in the ioend, the on error we can
 	 * simply discard and unlock it as there are no other users of the page
-	 * or it's buffers right now. The caller will still need to trigger
-	 * submission of outstanding ioends on the writepage context so they are
-	 * treated correctly on error.
+	 * now.  The caller will still need to trigger submission of outstanding
+	 * ioends on the writepage context so they are treated correctly on
+	 * error.
 	 */
 	if (unlikely(error)) {
 		if (!count) {
@@ -918,8 +756,8 @@ xfs_writepage_map(
 	}
 
 	/*
-	 * We can end up here with no error and nothing to write if we race with
-	 * a partial page truncate on a sub-page block sized filesystem.
+	 * We can end up here with no error and nothing to write only if we race
+	 * with a partial page truncate on a sub-page block sized filesystem.
 	 */
 	if (!count)
 		end_page_writeback(page);
@@ -934,7 +772,6 @@ done:
  * For delalloc space on the page we need to allocate space and flush it.
  * For unwritten space on the page we need to start the conversion to
  * regular allocated space.
- * For any other dirty buffer heads on the page we should flush them.
  */
 STATIC int
 xfs_do_writepage(
@@ -1088,166 +925,13 @@ xfs_dax_writepages(
 			xfs_find_bdev_for_inode(mapping->host), wbc);
 }
 
-/*
- * Called to move a page into cleanable state - and from there
- * to be released. The page should already be clean. We always
- * have buffer heads in this call.
- *
- * Returns 1 if the page is ok to release, 0 otherwise.
- */
 STATIC int
 xfs_vm_releasepage(
 	struct page		*page,
 	gfp_t			gfp_mask)
 {
-	int			delalloc, unwritten;
-
 	trace_xfs_releasepage(page->mapping->host, page, 0, 0);
-
-	/*
-	 * mm accommodates an old ext3 case where clean pages might not have had
-	 * the dirty bit cleared. Thus, it can send actual dirty pages to
-	 * ->releasepage() via shrink_active_list(). Conversely,
-	 * block_invalidatepage() can send pages that are still marked dirty but
-	 * otherwise have invalidated buffers.
-	 *
-	 * We want to release the latter to avoid unnecessary buildup of the
-	 * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages
-	 * that are entirely invalidated and need to be released.  Hence the
-	 * only time we should get dirty pages here is through
-	 * shrink_active_list() and so we can simply skip those now.
-	 *
-	 * warn if we've left any lingering delalloc/unwritten buffers on clean
-	 * or invalidated pages we are about to release.
-	 */
-	if (PageDirty(page))
-		return 0;
-
-	xfs_count_page_state(page, &delalloc, &unwritten);
-
-	if (WARN_ON_ONCE(delalloc))
-		return 0;
-	if (WARN_ON_ONCE(unwritten))
-		return 0;
-
-	return try_to_free_buffers(page);
-}
-
-/*
- * If this is O_DIRECT or the mpage code calling tell them how large the mapping
- * is, so that we can avoid repeated get_blocks calls.
- *
- * If the mapping spans EOF, then we have to break the mapping up as the mapping
- * for blocks beyond EOF must be marked new so that sub block regions can be
- * correctly zeroed. We can't do this for mappings within EOF unless the mapping
- * was just allocated or is unwritten, otherwise the callers would overwrite
- * existing data with zeros. Hence we have to split the mapping into a range up
- * to and including EOF, and a second mapping for beyond EOF.
- */
-static void
-xfs_map_trim_size(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset,
-	ssize_t			size)
-{
-	xfs_off_t		mapping_size;
-
-	mapping_size = imap->br_startoff + imap->br_blockcount - iblock;
-	mapping_size <<= inode->i_blkbits;
-
-	ASSERT(mapping_size > 0);
-	if (mapping_size > size)
-		mapping_size = size;
-	if (offset < i_size_read(inode) &&
-	    (xfs_ufsize_t)offset + mapping_size >= i_size_read(inode)) {
-		/* limit mapping to block that spans EOF */
-		mapping_size = roundup_64(i_size_read(inode) - offset,
-					  i_blocksize(inode));
-	}
-	if (mapping_size > LONG_MAX)
-		mapping_size = LONG_MAX;
-
-	bh_result->b_size = mapping_size;
-}
-
-static int
-xfs_get_blocks(
-	struct inode		*inode,
-	sector_t		iblock,
-	struct buffer_head	*bh_result,
-	int			create)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb, end_fsb;
-	int			error = 0;
-	int			lockmode = 0;
-	struct xfs_bmbt_irec	imap;
-	int			nimaps = 1;
-	xfs_off_t		offset;
-	ssize_t			size;
-
-	BUG_ON(create);
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	offset = (xfs_off_t)iblock << inode->i_blkbits;
-	ASSERT(bh_result->b_size >= i_blocksize(inode));
-	size = bh_result->b_size;
-
-	if (offset >= i_size_read(inode))
-		return 0;
-
-	/*
-	 * Direct I/O is usually done on preallocated files, so try getting
-	 * a block mapping without an exclusive lock first.
-	 */
-	lockmode = xfs_ilock_data_map_shared(ip);
-
-	ASSERT(offset <= mp->m_super->s_maxbytes);
-	if (offset > mp->m_super->s_maxbytes - size)
-		size = mp->m_super->s_maxbytes - offset;
-	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-
-	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
-			&nimaps, 0);
-	if (error)
-		goto out_unlock;
-	if (!nimaps) {
-		trace_xfs_get_blocks_notfound(ip, offset, size);
-		goto out_unlock;
-	}
-
-	trace_xfs_get_blocks_found(ip, offset, size,
-		imap.br_state == XFS_EXT_UNWRITTEN ?
-			XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, &imap);
-	xfs_iunlock(ip, lockmode);
-
-	/* trim mapping down to size requested */
-	xfs_map_trim_size(inode, iblock, bh_result, &imap, offset, size);
-
-	/*
-	 * For unwritten extents do not report a disk address in the buffered
-	 * read case (treat as if we're reading into a hole).
-	 */
-	if (xfs_bmap_is_real_extent(&imap))
-		xfs_map_buffer(inode, bh_result, &imap, offset);
-
-	/*
-	 * If this is a realtime file, data may be on a different device.
-	 * to that pointed to from the buffer_head b_bdev currently.
-	 */
-	bh_result->b_bdev = xfs_find_bdev_for_inode(inode);
-	return 0;
-
-out_unlock:
-	xfs_iunlock(ip, lockmode);
-	return error;
+	return iomap_releasepage(page, gfp_mask);
 }
 
 STATIC sector_t
@@ -1279,9 +963,7 @@ xfs_vm_readpage(
 	struct page		*page)
 {
 	trace_xfs_vm_readpage(page->mapping->host, 1);
-	if (i_blocksize(page->mapping->host) == PAGE_SIZE)
-		return iomap_readpage(page, &xfs_iomap_ops);
-	return mpage_readpage(page, xfs_get_blocks);
+	return iomap_readpage(page, &xfs_iomap_ops);
 }
 
 STATIC int
@@ -1292,65 +974,7 @@ xfs_vm_readpages(
 	unsigned		nr_pages)
 {
 	trace_xfs_vm_readpages(mapping->host, nr_pages);
-	if (i_blocksize(mapping->host) == PAGE_SIZE)
-		return iomap_readpages(mapping, pages, nr_pages, &xfs_iomap_ops);
-	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
-}
-
-/*
- * This is basically a copy of __set_page_dirty_buffers() with one
- * small tweak: buffers beyond EOF do not get marked dirty. If we mark them
- * dirty, we'll never be able to clean them because we don't write buffers
- * beyond EOF, and that means we can't invalidate pages that span EOF
- * that have been marked dirty. Further, the dirty state can leak into
- * the file interior if the file is extended, resulting in all sorts of
- * bad things happening as the state does not match the underlying data.
- *
- * XXX: this really indicates that bufferheads in XFS need to die. Warts like
- * this only exist because of bufferheads and how the generic code manages them.
- */
-STATIC int
-xfs_vm_set_page_dirty(
-	struct page		*page)
-{
-	struct address_space	*mapping = page->mapping;
-	struct inode		*inode = mapping->host;
-	loff_t			end_offset;
-	loff_t			offset;
-	int			newly_dirty;
-
-	if (unlikely(!mapping))
-		return !TestSetPageDirty(page);
-
-	end_offset = i_size_read(inode);
-	offset = page_offset(page);
-
-	spin_lock(&mapping->private_lock);
-	if (page_has_buffers(page)) {
-		struct buffer_head *head = page_buffers(page);
-		struct buffer_head *bh = head;
-
-		do {
-			if (offset < end_offset)
-				set_buffer_dirty(bh);
-			bh = bh->b_this_page;
-			offset += i_blocksize(inode);
-		} while (bh != head);
-	}
-	/*
-	 * Lock out page->mem_cgroup migration to keep PageDirty
-	 * synchronized with per-memcg dirty page counters.
-	 */
-	lock_page_memcg(page);
-	newly_dirty = !TestSetPageDirty(page);
-	spin_unlock(&mapping->private_lock);
-
-	if (newly_dirty)
-		__set_page_dirty(page, mapping, 1);
-	unlock_page_memcg(page);
-	if (newly_dirty)
-		__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
-	return newly_dirty;
+	return iomap_readpages(mapping, pages, nr_pages, &xfs_iomap_ops);
 }
 
 static int
@@ -1368,13 +992,13 @@ const struct address_space_operations xfs_address_space_operations = {
 	.readpages		= xfs_vm_readpages,
 	.writepage		= xfs_vm_writepage,
 	.writepages		= xfs_vm_writepages,
-	.set_page_dirty		= xfs_vm_set_page_dirty,
+	.set_page_dirty		= iomap_set_page_dirty,
 	.releasepage		= xfs_vm_releasepage,
 	.invalidatepage		= xfs_vm_invalidatepage,
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= noop_direct_IO,
-	.migratepage		= buffer_migrate_page,
-	.is_partially_uptodate  = block_is_partially_uptodate,
+	.migratepage		= iomap_migrate_page,
+	.is_partially_uptodate  = iomap_is_partially_uptodate,
 	.error_remove_page	= generic_error_remove_page,
 	.swap_activate		= xfs_iomap_swapfile_activate,
 };
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index d24dbd4dac39..6ddf1907fc7a 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -12,7 +12,6 @@
 #include <linux/mm.h>
 #include <linux/fs.h>
 #include <linux/dax.h>
-#include <linux/buffer_head.h>
 #include <linux/uio.h>
 #include <linux/list_lru.h>
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 7fe42a126ec1..778b8c850de3 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1032,9 +1032,6 @@ xfs_file_iomap_begin(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if (i_blocksize(inode) < PAGE_SIZE)
-		iomap->flags |= IOMAP_F_BUFFER_HEAD;
-
 	if (((flags & (IOMAP_WRITE | IOMAP_DIRECT)) == IOMAP_WRITE) &&
 			!IS_DAX(inode) && !xfs_get_extsz_hint(ip)) {
 		/* Reserve delalloc blocks for regular writeback. */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 9d791f158dfe..f9f8dc490d3d 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1860,7 +1860,7 @@ MODULE_ALIAS_FS("xfs");
 STATIC int __init
 xfs_init_zones(void)
 {
-	if (bioset_init(&xfs_ioend_bioset, 4 * MAX_BUF_PER_PAGE,
+	if (bioset_init(&xfs_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
 			offsetof(struct xfs_ioend, io_inline_bio),
 			BIOSET_NEED_BVECS))
 		goto out;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 1af123df19b5..7f4c7071e7ed 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1153,33 +1153,23 @@ DECLARE_EVENT_CLASS(xfs_page_class,
 		__field(loff_t, size)
 		__field(unsigned long, offset)
 		__field(unsigned int, length)
-		__field(int, delalloc)
-		__field(int, unwritten)
 	),
 	TP_fast_assign(
-		int delalloc = -1, unwritten = -1;
-
-		if (page_has_buffers(page))
-			xfs_count_page_state(page, &delalloc, &unwritten);
 		__entry->dev = inode->i_sb->s_dev;
 		__entry->ino = XFS_I(inode)->i_ino;
 		__entry->pgoff = page_offset(page);
 		__entry->size = i_size_read(inode);
 		__entry->offset = off;
 		__entry->length = len;
-		__entry->delalloc = delalloc;
-		__entry->unwritten = unwritten;
 	),
 	TP_printk("dev %d:%d ino 0x%llx pgoff 0x%lx size 0x%llx offset %lx "
-		  "length %x delalloc %d unwritten %d",
+		  "length %x",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->pgoff,
 		  __entry->size,
 		  __entry->offset,
-		  __entry->length,
-		  __entry->delalloc,
-		  __entry->unwritten)
+		  __entry->length)
 )
 
 #define DEFINE_PAGE_EVENT(name)		\
@@ -1263,9 +1253,6 @@ DEFINE_EVENT(xfs_imap_class, name,	\
 	TP_ARGS(ip, offset, count, type, irec))
 DEFINE_IOMAP_EVENT(xfs_map_blocks_found);
 DEFINE_IOMAP_EVENT(xfs_map_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_found);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
-DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
 DEFINE_IOMAP_EVENT(xfs_iomap_alloc);
 DEFINE_IOMAP_EVENT(xfs_iomap_found);
 
@@ -1304,7 +1291,6 @@ DEFINE_EVENT(xfs_simple_io_class, name,	\
 	TP_ARGS(ip, offset, count))
 DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc);
 DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert);
-DEFINE_SIMPLE_IO_EVENT(xfs_get_blocks_notfound);
 DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize);
 DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
-- 
cgit v1.2.3


From 98c1a7c0ece345dc8e34c0c85703e4df9fdfd071 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 11 Jul 2018 22:26:06 -0700
Subject: xfs: update my copyrights for the writeback and iomap code

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c  | 1 +
 fs/xfs/xfs_iomap.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index bae88ac1101d..f4d3252236c1 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include "xfs.h"
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 778b8c850de3..fb9746cc7338 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2006 Silicon Graphics, Inc.
- * Copyright (c) 2016 Christoph Hellwig.
+ * Copyright (c) 2016-2018 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include <linux/iomap.h>
-- 
cgit v1.2.3


From 8a749386498327c98c2792e19eeeaa21dafc6954 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:06 -0700
Subject: xfs: cow unwritten conversion uses uninitialized dfops

A couple COW fork unwritten extent conversion helpers pass an
uninitialized dfops pointer to xfs_bmapi_write(). This does not
cause problems because conversion does not use a transaction or the
dfops structure for the COW fork.  Drop the uninitialized usage of
dfops in these codepaths and pass NULL along to xfs_bmapi_write()
instead.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_reflink.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 49e4913fa779..33845009bec5 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -312,8 +312,7 @@ xfs_reflink_convert_cow_extent(
 	struct xfs_inode		*ip,
 	struct xfs_bmbt_irec		*imap,
 	xfs_fileoff_t			offset_fsb,
-	xfs_filblks_t			count_fsb,
-	struct xfs_defer_ops		*dfops)
+	xfs_filblks_t			count_fsb)
 {
 	xfs_fsblock_t			first_block = NULLFSBLOCK;
 	int				nimaps = 1;
@@ -327,7 +326,7 @@ xfs_reflink_convert_cow_extent(
 		return 0;
 	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block,
-			0, imap, &nimaps, dfops);
+			0, imap, &nimaps, NULL);
 }
 
 /* Convert all of the unwritten CoW extents in a file's range to real ones. */
@@ -342,7 +341,6 @@ xfs_reflink_convert_cow(
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
 	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
 	struct xfs_bmbt_irec	imap;
-	struct xfs_defer_ops	dfops;
 	xfs_fsblock_t		first_block = NULLFSBLOCK;
 	int			nimaps = 1, error = 0;
 
@@ -352,7 +350,7 @@ xfs_reflink_convert_cow(
 	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
 			XFS_BMAPI_CONVERT_ONLY, &first_block, 0, &imap, &nimaps,
-			&dfops);
+			NULL);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
@@ -458,8 +456,7 @@ retry:
 	if (nimaps == 0)
 		return -ENOSPC;
 convert:
-	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb,
-			&dfops);
+	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
 out_bmap_cancel:
 	xfs_defer_cancel(&dfops);
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
-- 
cgit v1.2.3


From 6aa6718439ac6907b3c34cbe7ac2c71408f84f6e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:07 -0700
Subject: xfs: rename xfs_trans ->t_agfl_dfops to ->t_dfops

The ->t_agfl_dfops field is currently used to defer agfl block frees
from associated transaction contexts. While all known problematic
contexts have already been updated to use ->t_agfl_dfops, the
broader goal is defer agfl frees from all callers that already use a
deferred operations structure. Further, the transaction field
facilitates a good amount of code clean up where the transaction and
dfops have historically been passed down through the stack
separately.

Rename the field to something more generic to prepare to use it as
such throughout XFS. This patch does not change behavior.
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c |  4 ++--
 fs/xfs/libxfs/xfs_defer.c |  8 ++++----
 fs/xfs/xfs_inode.c        | 10 +++++-----
 fs/xfs/xfs_symlink.c      |  2 +-
 fs/xfs/xfs_trans.c        |  6 +++---
 fs/xfs/xfs_trans.h        |  2 +-
 6 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index eef466260d43..5b1607d76fe9 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2323,8 +2323,8 @@ xfs_alloc_fix_freelist(
 			goto out_agbp_relse;
 
 		/* defer agfl frees if dfops is provided */
-		if (tp->t_agfl_dfops) {
-			xfs_defer_agfl_block(mp, tp->t_agfl_dfops, args->agno,
+		if (tp->t_dfops) {
+			xfs_defer_agfl_block(mp, tp->t_dfops, args->agno,
 					     bno, &targs.oinfo);
 		} else {
 			error = xfs_free_agfl_block(tp, args->agno, bno, agbp,
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index c3e5bffda4f5..560a7d178c1e 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -350,9 +350,9 @@ xfs_defer_finish(
 	 * Note that this code can go away once all dfops users attach to the
 	 * associated tp.
 	 */
-	ASSERT(!(*tp)->t_agfl_dfops || ((*tp)->t_agfl_dfops == dop));
-	orig_dop = (*tp)->t_agfl_dfops;
-	(*tp)->t_agfl_dfops = dop;
+	ASSERT(!(*tp)->t_dfops || ((*tp)->t_dfops == dop));
+	orig_dop = (*tp)->t_dfops;
+	(*tp)->t_dfops = dop;
 
 	/* Until we run out of pending work to finish... */
 	while (xfs_defer_has_unfinished_work(dop)) {
@@ -425,7 +425,7 @@ xfs_defer_finish(
 	}
 
 out:
-	(*tp)->t_agfl_dfops = orig_dop;
+	(*tp)->t_dfops = orig_dop;
 	if (error)
 		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
 	else
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5df4de666cc1..9c5fbc94cf14 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1196,7 +1196,7 @@ xfs_create(
 	unlock_dp_on_error = true;
 
 	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
+	tp->t_dfops = &dfops;
 
 	/*
 	 * Reserve disk quota and the inode.
@@ -1452,7 +1452,7 @@ xfs_link(
 	}
 
 	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
+	tp->t_dfops = &dfops;
 
 	/*
 	 * Handle initial link state of O_TMPFILE inode
@@ -1813,7 +1813,7 @@ xfs_inactive_ifree(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
+	tp->t_dfops = &dfops;
 	error = xfs_ifree(tp, ip, &dfops);
 	if (error) {
 		/*
@@ -2659,7 +2659,7 @@ xfs_remove(
 		goto out_trans_cancel;
 
 	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
+	tp->t_dfops = &dfops;
 	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
 					&first_block, &dfops, resblks);
 	if (error) {
@@ -3027,7 +3027,7 @@ xfs_rename(
 	}
 
 	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
+	tp->t_dfops = &dfops;
 
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 3783afcb68d2..44335bdebea2 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -247,7 +247,7 @@ xfs_symlink(
 	 * bmapi or the directory create code.
 	 */
 	xfs_defer_init(&dfops, &first_block);
-	tp->t_agfl_dfops = &dfops;
+	tp->t_dfops = &dfops;
 
 	/*
 	 * Allocate an inode for the symlink.
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 524f543c5b82..630993387517 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -118,7 +118,7 @@ xfs_trans_dup(
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
 	ntp->t_pflags = tp->t_pflags;
-	ntp->t_agfl_dfops = tp->t_agfl_dfops;
+	ntp->t_dfops = tp->t_dfops;
 
 	xfs_trans_dup_dqinfo(tp, ntp);
 
@@ -914,8 +914,8 @@ __xfs_trans_commit(
 	int			error = 0;
 	int			sync = tp->t_flags & XFS_TRANS_SYNC;
 
-	ASSERT(!tp->t_agfl_dfops ||
-	       !xfs_defer_has_unfinished_work(tp->t_agfl_dfops) || regrant);
+	ASSERT(!tp->t_dfops ||
+	       !xfs_defer_has_unfinished_work(tp->t_dfops) || regrant);
 
 	trace_xfs_trans_commit(tp, _RET_IP_);
 
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 6526314f0b8f..d8a695c57103 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -105,7 +105,7 @@ typedef struct xfs_trans {
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
-	struct xfs_defer_ops	*t_agfl_dfops;	/* optional agfl fixup dfops */
+	struct xfs_defer_ops	*t_dfops;	/* dfops reference */
 	unsigned int		t_flags;	/* misc flags */
 	int64_t			t_icount_delta;	/* superblock icount change */
 	int64_t			t_ifree_delta;	/* superblock ifree change */
-- 
cgit v1.2.3


From 0e0417f3e54668cec9f677850130e6fbb64edcf2 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:07 -0700
Subject: xfs: remove dfops parameter from ifree call stack

The inode free callchain starting in xfs_inactive_ifree() already
associates its dfops with the transaction. It still passes the dfops
on the stack down through xfs_difree_inobt(), however.

Clean up the call stack and reference dfops directly from the
transaction. This patch does not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_ialloc.c | 6 ++----
 fs/xfs/libxfs/xfs_ialloc.h | 1 -
 fs/xfs/xfs_inode.c         | 9 ++++-----
 fs/xfs/xfs_inode.h         | 3 +--
 4 files changed, 7 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 0d968e8143aa..c38d14106b53 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1915,7 +1915,6 @@ xfs_difree_inobt(
 	struct xfs_trans		*tp,
 	struct xfs_buf			*agbp,
 	xfs_agino_t			agino,
-	struct xfs_defer_ops		*dfops,
 	struct xfs_icluster		*xic,
 	struct xfs_inobt_rec_incore	*orec)
 {
@@ -2003,7 +2002,7 @@ xfs_difree_inobt(
 			goto error0;
 		}
 
-		xfs_difree_inode_chunk(mp, agno, &rec, dfops);
+		xfs_difree_inode_chunk(mp, agno, &rec, tp->t_dfops);
 	} else {
 		xic->deleted = false;
 
@@ -2148,7 +2147,6 @@ int
 xfs_difree(
 	struct xfs_trans	*tp,		/* transaction pointer */
 	xfs_ino_t		inode,		/* inode to be freed */
-	struct xfs_defer_ops	*dfops,		/* extents to free */
 	struct xfs_icluster	*xic)	/* cluster info if deleted */
 {
 	/* REFERENCED */
@@ -2200,7 +2198,7 @@ xfs_difree(
 	/*
 	 * Fix up the inode allocation btree.
 	 */
-	error = xfs_difree_inobt(mp, tp, agbp, agino, dfops, xic, &rec);
+	error = xfs_difree_inobt(mp, tp, agbp, agino, xic, &rec);
 	if (error)
 		goto error0;
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 90b09c5f163b..e936b7cc9389 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -82,7 +82,6 @@ int					/* error */
 xfs_difree(
 	struct xfs_trans *tp,		/* transaction pointer */
 	xfs_ino_t	inode,		/* inode to be freed */
-	struct xfs_defer_ops *dfops,	/* extents to free */
 	struct xfs_icluster *ifree);	/* cluster info if deleted */
 
 /*
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9c5fbc94cf14..f5649a023d46 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1814,7 +1814,7 @@ xfs_inactive_ifree(
 
 	xfs_defer_init(&dfops, &first_block);
 	tp->t_dfops = &dfops;
-	error = xfs_ifree(tp, ip, &dfops);
+	error = xfs_ifree(tp, ip);
 	if (error) {
 		/*
 		 * If we fail to free the inode, shut down.  The cancel
@@ -2445,9 +2445,8 @@ xfs_ifree_local_data(
  */
 int
 xfs_ifree(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*ip,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip)
 {
 	int			error;
 	struct xfs_icluster	xic = { 0 };
@@ -2466,7 +2465,7 @@ xfs_ifree(
 	if (error)
 		return error;
 
-	error = xfs_difree(tp, ip->i_ino, dfops, &xic);
+	error = xfs_difree(tp, ip->i_ino, &xic);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 2ed63a49e890..b1f0e8394f3b 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -415,8 +415,7 @@ uint		xfs_ilock_data_map_shared(struct xfs_inode *);
 uint		xfs_ilock_attr_map_shared(struct xfs_inode *);
 
 uint		xfs_ip2xflags(struct xfs_inode *);
-int		xfs_ifree(struct xfs_trans *, xfs_inode_t *,
-			   struct xfs_defer_ops *);
+int		xfs_ifree(struct xfs_trans *, struct xfs_inode *);
 int		xfs_itruncate_extents_flags(struct xfs_trans **,
 				struct xfs_inode *, int, xfs_fsize_t, int);
 void		xfs_iext_realloc(xfs_inode_t *, int, int);
-- 
cgit v1.2.3


From c9cfdb381172174ade2445e7b468f1be550b1a44 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:08 -0700
Subject: xfs: remove dfops param from high level dirname calls

All callers of the directory create, rename and remove interfaces
already associate the dfops with the transaction. Drop the dfops
parameters in these calls in preparation for further cleanups in the
layers below. This patch does not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_dir2.c | 17 ++++++++--------
 fs/xfs/libxfs/xfs_dir2.h |  9 +++------
 fs/xfs/xfs_inode.c       | 50 ++++++++++++++++++++++--------------------------
 fs/xfs/xfs_symlink.c     |  2 +-
 4 files changed, 36 insertions(+), 42 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 59169aff30fe..c98250f0de50 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -244,7 +244,6 @@ xfs_dir_createname(
 	struct xfs_name		*name,
 	xfs_ino_t		inum,		/* new entry inode number */
 	xfs_fsblock_t		*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
 	xfs_extlen_t		total)		/* bmap's total block count */
 {
 	struct xfs_da_args	*args;
@@ -252,6 +251,8 @@ xfs_dir_createname(
 	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	ASSERT(tp->t_dfops || !first);
+
 	if (inum) {
 		rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 		if (rval)
@@ -270,11 +271,11 @@ xfs_dir_createname(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = inum;
 	args->dp = dp;
-	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
+	args->dfops = tp->t_dfops;
+	args->firstblock = first;
 	args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	if (!inum)
 		args->op_flags |= XFS_DA_OP_JUSTCHECK;
@@ -421,7 +422,6 @@ xfs_dir_removename(
 	struct xfs_name	*name,
 	xfs_ino_t	ino,
 	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
 	xfs_extlen_t	total)		/* bmap's total block count */
 {
 	struct xfs_da_args *args;
@@ -429,6 +429,7 @@ xfs_dir_removename(
 	int		v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	ASSERT(tp->t_dfops);
 	XFS_STATS_INC(dp->i_mount, xs_dir_remove);
 
 	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
@@ -443,10 +444,10 @@ xfs_dir_removename(
 	args->inumber = ino;
 	args->dp = dp;
 	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
+	args->dfops = tp->t_dfops;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_removename(args);
@@ -483,7 +484,6 @@ xfs_dir_replace(
 	struct xfs_name	*name,		/* name of entry to replace */
 	xfs_ino_t	inum,		/* new inode number */
 	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	struct xfs_defer_ops	*dfops,		/* bmap's freeblock list */
 	xfs_extlen_t	total)		/* bmap's total block count */
 {
 	struct xfs_da_args *args;
@@ -491,6 +491,7 @@ xfs_dir_replace(
 	int		v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
+	ASSERT(tp->t_dfops);
 
 	rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 	if (rval)
@@ -508,10 +509,10 @@ xfs_dir_replace(
 	args->inumber = inum;
 	args->dp = dp;
 	args->firstblock = first;
-	args->dfops = dfops;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
+	args->dfops = tp->t_dfops;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_replace(args);
@@ -547,7 +548,7 @@ xfs_dir_canenter(
 	xfs_inode_t	*dp,
 	struct xfs_name	*name)		/* name of entry to add */
 {
-	return xfs_dir_createname(tp, dp, name, 0, NULL, NULL, 0);
+	return xfs_dir_createname(tp, dp, name, 0, NULL, 0);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index ed385316c7dc..f203aebc07ed 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -118,19 +118,16 @@ extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_inode *pdp);
 extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_fsblock_t *first, xfs_extlen_t tot);
 extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t *inum,
 				struct xfs_name *ci_name);
 extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t ino,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_fsblock_t *first, xfs_extlen_t tot);
 extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first,
-				struct xfs_defer_ops *dfops, xfs_extlen_t tot);
+				xfs_fsblock_t *first, xfs_extlen_t tot);
 extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name);
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f5649a023d46..e1bc686b70b4 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1225,8 +1225,8 @@ xfs_create(
 	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
 	unlock_dp_on_error = false;
 
-	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
-					&first_block, &dfops, resblks ?
+	error = xfs_dir_createname(tp, dp, name, ip->i_ino, &first_block,
+				   resblks ?
 					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
 		ASSERT(error != -ENOSPC);
@@ -1464,7 +1464,7 @@ xfs_link(
 	}
 
 	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
-					&first_block, &dfops, resblks);
+				   &first_block, resblks);
 	if (error)
 		goto error_return;
 	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -2659,8 +2659,8 @@ xfs_remove(
 
 	xfs_defer_init(&dfops, &first_block);
 	tp->t_dfops = &dfops;
-	error = xfs_dir_removename(tp, dp, name, ip->i_ino,
-					&first_block, &dfops, resblks);
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino, &first_block,
+				   resblks);
 	if (error) {
 		ASSERT(error != -ENOENT);
 		goto out_bmap_cancel;
@@ -2748,9 +2748,9 @@ xfs_sort_for_rename(
 
 static int
 xfs_finish_rename(
-	struct xfs_trans	*tp,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*tp)
 {
+	struct xfs_defer_ops	*dfops = tp->t_dfops;
 	int			error;
 
 	/*
@@ -2784,7 +2784,6 @@ xfs_cross_rename(
 	struct xfs_inode	*dp2,
 	struct xfs_name		*name2,
 	struct xfs_inode	*ip2,
-	struct xfs_defer_ops	*dfops,
 	xfs_fsblock_t		*first_block,
 	int			spaceres)
 {
@@ -2794,16 +2793,14 @@ xfs_cross_rename(
 	int		dp2_flags = 0;
 
 	/* Swap inode number for dirent in first parent */
-	error = xfs_dir_replace(tp, dp1, name1,
-				ip2->i_ino,
-				first_block, dfops, spaceres);
+	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, first_block,
+				spaceres);
 	if (error)
 		goto out_trans_abort;
 
 	/* Swap inode number for dirent in second parent */
-	error = xfs_dir_replace(tp, dp2, name2,
-				ip1->i_ino,
-				first_block, dfops, spaceres);
+	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, first_block,
+				spaceres);
 	if (error)
 		goto out_trans_abort;
 
@@ -2818,7 +2815,7 @@ xfs_cross_rename(
 		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
 			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
 						dp1->i_ino, first_block,
-						dfops, spaceres);
+						spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -2845,7 +2842,7 @@ xfs_cross_rename(
 		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
 			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
 						dp2->i_ino, first_block,
-						dfops, spaceres);
+						spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -2884,10 +2881,10 @@ xfs_cross_rename(
 	}
 	xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
-	return xfs_finish_rename(tp, dfops);
+	return xfs_finish_rename(tp);
 
 out_trans_abort:
-	xfs_defer_cancel(dfops);
+	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -3032,7 +3029,7 @@ xfs_rename(
 	if (flags & RENAME_EXCHANGE)
 		return xfs_cross_rename(tp, src_dp, src_name, src_ip,
 					target_dp, target_name, target_ip,
-					&dfops, &first_block, spaceres);
+					&first_block, spaceres);
 
 	/*
 	 * Set up the target.
@@ -3054,7 +3051,7 @@ xfs_rename(
 		 */
 		error = xfs_dir_createname(tp, target_dp, target_name,
 						src_ip->i_ino, &first_block,
-						&dfops, spaceres);
+						spaceres);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -3093,8 +3090,7 @@ xfs_rename(
 		 * name at the destination directory, remove it first.
 		 */
 		error = xfs_dir_replace(tp, target_dp, target_name,
-					src_ip->i_ino,
-					&first_block, &dfops, spaceres);
+					src_ip->i_ino, &first_block, spaceres);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -3128,8 +3124,8 @@ xfs_rename(
 		 * directory.
 		 */
 		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
-					target_dp->i_ino,
-					&first_block, &dfops, spaceres);
+					target_dp->i_ino, &first_block,
+					spaceres);
 		ASSERT(error != -EEXIST);
 		if (error)
 			goto out_bmap_cancel;
@@ -3168,10 +3164,10 @@ xfs_rename(
 	 */
 	if (wip) {
 		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
-					&first_block, &dfops, spaceres);
+					&first_block, spaceres);
 	} else
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
-					   &first_block, &dfops, spaceres);
+					   &first_block, spaceres);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -3206,7 +3202,7 @@ xfs_rename(
 	if (new_parent)
 		xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
 
-	error = xfs_finish_rename(tp, &dfops);
+	error = xfs_finish_rename(tp);
 	if (wip)
 		IRELE(wip);
 	return error;
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 44335bdebea2..e347a3db018f 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -339,7 +339,7 @@ xfs_symlink(
 	 * Create the directory entry for the symlink.
 	 */
 	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
-					&first_block, &dfops, resblks);
+				   &first_block, resblks);
 	if (error)
 		goto out_bmap_cancel;
 	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-- 
cgit v1.2.3


From 813d08cb6de0af43da40393aebff914d2de9e50e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:09 -0700
Subject: xfs: use ->t_dfops for recovery of [b|c]ui log items

Log recovery passes down a central dfops structure to recovery
handlers for bui and cui log items. Each of these handlers allocates
and commits a transaction and defers any remaining operations to be
completed by the main recovery sequence.

Since dfops outlives the transaction in this context, set and clear
->t_dfops appropriately such that the *_finish_item() paths and
below (i.e., xfs_bmapi*()) can expect to find the dfops in the
transaction without it being committed with the dfops attached. This
is required because transaction commit expects that an associated
dfops is finished and in this context the dfops may be populated at
commit time.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_item.c     | 8 ++++++++
 fs/xfs/xfs_refcount_item.c | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 956ebd583e27..478bfc798861 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -441,6 +441,7 @@ xfs_bui_recover(
 			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
 	if (error)
 		return error;
+	tp->t_dfops = dfops;
 	budp = xfs_trans_get_bud(tp, buip);
 
 	/* Grab the inode. */
@@ -487,6 +488,12 @@ xfs_bui_recover(
 	}
 
 	set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
+	/*
+	 * Recovery finishes all deferred ops once intent processing is
+	 * complete. Reset the trans reference because commit expects a finished
+	 * dfops or none at all.
+	 */
+	tp->t_dfops = NULL;
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	IRELE(ip);
@@ -494,6 +501,7 @@ xfs_bui_recover(
 	return error;
 
 err_inode:
+	tp->t_dfops = NULL;
 	xfs_trans_cancel(tp);
 	if (ip) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 472a73e9d331..2064c689bc72 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -452,6 +452,7 @@ xfs_cui_recover(
 			mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
+	tp->t_dfops = dfops;
 	cudp = xfs_trans_get_cud(tp, cuip);
 
 	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
@@ -514,11 +515,18 @@ xfs_cui_recover(
 
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
+	/*
+	 * Recovery finishes all deferred ops once intent processing is
+	 * complete. Reset the trans reference because commit expects a finished
+	 * dfops or none at all.
+	 */
+	tp->t_dfops = NULL;
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
+	tp->t_dfops = NULL;
 	xfs_trans_cancel(tp);
 	return error;
 }
-- 
cgit v1.2.3


From 40d03ac6aa2bebe05190462734690472310167e4 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:09 -0700
Subject: xfs: use ->t_dfops for attr set/remove operations

Attach the local dfops to the transaction allocated for xattr add
and remove operations. Add an earlier initialization in
xfs_attr_remove() to ensure the structure is valid if it remains
unused at transaction commit time.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c | 11 +++++++----
 fs/xfs/libxfs/xfs_bmap.c |  3 ++-
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 99590f61d624..cc23c269f2bf 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -254,6 +254,8 @@ xfs_attr_set(
 			rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
 	if (error)
 		return error;
+	xfs_defer_init(&dfops, &firstblock);
+	args.trans->t_dfops = &dfops;
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
@@ -315,7 +317,6 @@ xfs_attr_set(
 		 * It won't fit in the shortform, transform to a leaf block.
 		 * GROT: another possible req'mt for a double-split btree op.
 		 */
-		xfs_defer_init(args.dfops, args.firstblock);
 		error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
 		if (error)
 			goto out_defer_cancel;
@@ -325,9 +326,9 @@ xfs_attr_set(
 		 * buffer and run into problems with the write verifier.
 		 */
 		xfs_trans_bhold(args.trans, leaf_bp);
-		xfs_defer_bjoin(args.dfops, leaf_bp);
-		xfs_defer_ijoin(args.dfops, dp);
-		error = xfs_defer_finish(&args.trans, args.dfops);
+		xfs_defer_bjoin(&dfops, leaf_bp);
+		xfs_defer_ijoin(&dfops, dp);
+		error = xfs_defer_finish(&args.trans, &dfops);
 		if (error)
 			goto out_defer_cancel;
 
@@ -429,6 +430,8 @@ xfs_attr_remove(
 			&args.trans);
 	if (error)
 		return error;
+	xfs_defer_init(&dfops, &firstblock);
+	args.trans->t_dfops = &dfops;
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	/*
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 68ea1f4b9c3f..bc73375769a0 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1057,6 +1057,8 @@ xfs_bmap_add_attrfork(
 			rsvd ? XFS_TRANS_RESERVE : 0, &tp);
 	if (error)
 		return error;
+	xfs_defer_init(&dfops, &firstblock);
+	tp->t_dfops = &dfops;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
@@ -1104,7 +1106,6 @@ xfs_bmap_add_attrfork(
 	ip->i_afp = kmem_zone_zalloc(xfs_ifork_zone, KM_SLEEP);
 	ip->i_afp->if_flags = XFS_IFEXTENTS;
 	logflags = 0;
-	xfs_defer_init(&dfops, &firstblock);
 	switch (ip->i_d.di_format) {
 	case XFS_DINODE_FMT_LOCAL:
 		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &dfops,
-- 
cgit v1.2.3


From 0bd6207f836446f9d472f342a0ba3c21fe5e986f Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:10 -0700
Subject: xfs: remove dfops param in attr fork add path

Now that the attribute fork add tx carries dfops along with the
transaction, it is unnecessary to pass it down the stack. Remove the
dfops parameter and access ->t_dfops directly where necessary. This
patch does not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index bc73375769a0..7a414e7fbbb8 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -918,7 +918,6 @@ xfs_bmap_add_attrfork_btree(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* btree cursor */
@@ -931,7 +930,7 @@ xfs_bmap_add_attrfork_btree(
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
-		cur->bc_private.b.dfops = dfops;
+		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.firstblock = *firstblock;
 		error = xfs_bmbt_lookup_first(cur, &stat);
 		if (error)
@@ -962,7 +961,6 @@ xfs_bmap_add_attrfork_extents(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
@@ -971,7 +969,7 @@ xfs_bmap_add_attrfork_extents(
 	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
 		return 0;
 	cur = NULL;
-	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops, &cur, 0,
+	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, tp->t_dfops, &cur, 0,
 		flags, XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
@@ -997,7 +995,6 @@ xfs_bmap_add_attrfork_local(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first block allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks to free at commit */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_da_args_t		dargs;		/* args for dir/attr code */
@@ -1010,7 +1007,7 @@ xfs_bmap_add_attrfork_local(
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
 		dargs.firstblock = firstblock;
-		dargs.dfops = dfops;
+		dargs.dfops = tp->t_dfops;
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
@@ -1108,16 +1105,16 @@ xfs_bmap_add_attrfork(
 	logflags = 0;
 	switch (ip->i_d.di_format) {
 	case XFS_DINODE_FMT_LOCAL:
-		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock, &dfops,
-			&logflags);
+		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock,
+						    &logflags);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
 		error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
-			&dfops, &logflags);
+						      &logflags);
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock, &dfops,
-			&logflags);
+		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock,
+						    &logflags);
 		break;
 	default:
 		error = 0;
-- 
cgit v1.2.3


From d76e6ce8ed6943941c0c964d8ae43fdaefdcbb5a Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:10 -0700
Subject: xfs: use ->t_dfops in extent split tx and remove param

Attach the local dfops to ->t_dfops of the extent split transaction.
Since this is the only caller of xfs_bmap_split_extent_at(), remove
the dfops parameter as well.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7a414e7fbbb8..459a29cb17c2 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5919,8 +5919,7 @@ xfs_bmap_split_extent_at(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		split_fsb,
-	xfs_fsblock_t		*firstfsb,
-	struct xfs_defer_ops	*dfops)
+	xfs_fsblock_t		*firstfsb)
 {
 	int				whichfork = XFS_DATA_FORK;
 	struct xfs_btree_cur		*cur = NULL;
@@ -5970,7 +5969,7 @@ xfs_bmap_split_extent_at(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstfsb;
-		cur->bc_private.b.dfops = dfops;
+		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
@@ -6014,7 +6013,7 @@ xfs_bmap_split_extent_at(
 		int tmp_logflags; /* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, dfops,
+		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, tp->t_dfops,
 				&cur, 0, &tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
@@ -6046,14 +6045,14 @@ xfs_bmap_split_extent(
 			XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
 	if (error)
 		return error;
+	xfs_defer_init(&dfops, &firstfsb);
+	tp->t_dfops = &dfops;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-	xfs_defer_init(&dfops, &firstfsb);
-
 	error = xfs_bmap_split_extent_at(tp, ip, split_fsb,
-			&firstfsb, &dfops);
+					 &firstfsb);
 	if (error)
 		goto out;
 
-- 
cgit v1.2.3


From 32a9b7c65cfc7d9283055fc9d61e6393ee2aa984 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:11 -0700
Subject: xfs: replace xfs_da_args->dfops accesses with ->t_dfops and remove

Now that xfs_da_args->dfops is always assigned from a ->t_dfops
pointer (or one that is immediately attached), replace all
downstream accesses of the former with the latter and remove the
field from struct xfs_da_args.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 103 +++++++++++++++++++++-------------------
 fs/xfs/libxfs/xfs_attr_leaf.c   |  24 +++++-----
 fs/xfs/libxfs/xfs_attr_remote.c |  23 ++++-----
 fs/xfs/libxfs/xfs_bmap.c        |   1 -
 fs/xfs/libxfs/xfs_da_btree.c    |  19 ++++----
 fs/xfs/libxfs/xfs_da_btree.h    |   1 -
 fs/xfs/libxfs/xfs_dir2.c        |  65 ++++++++++++-------------
 7 files changed, 117 insertions(+), 119 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index cc23c269f2bf..a14ab9b2669e 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -220,7 +220,6 @@ xfs_attr_set(
 	args.value = value;
 	args.valuelen = valuelen;
 	args.firstblock = &firstblock;
-	args.dfops = &dfops;
 	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	args.total = xfs_attr_calc_size(&args, &local);
 
@@ -407,7 +406,6 @@ xfs_attr_remove(
 		return error;
 
 	args.firstblock = &firstblock;
-	args.dfops = &dfops;
 
 	/*
 	 * we have no control over the attribute names that userspace passes us
@@ -539,11 +537,12 @@ xfs_attr_shortform_addname(xfs_da_args_t *args)
  * if bmap_one_block() says there is only one block (ie: no remote blks).
  */
 STATIC int
-xfs_attr_leaf_addname(xfs_da_args_t *args)
+xfs_attr_leaf_addname(
+	struct xfs_da_args	*args)
 {
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int retval, error, forkoff;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
 
 	trace_xfs_attr_leaf_addname(args);
 
@@ -601,12 +600,12 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		 * Commit that transaction so that the node_addname() call
 		 * can manage its own transactions.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
+		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		xfs_defer_ijoin(args->trans->t_dfops, dp);
+		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 		if (error)
 			goto out_defer_cancel;
 
@@ -690,13 +689,13 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 		 * If the result is small enough, shrink it all into the inode.
 		 */
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->dfops, args->firstblock);
+			xfs_defer_init(args->trans->t_dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			xfs_defer_ijoin(args->trans->t_dfops, dp);
+			error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 			if (error)
 				goto out_defer_cancel;
 		}
@@ -714,7 +713,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
 	}
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans->t_dfops);
 	return error;
 }
 
@@ -725,11 +724,12 @@ out_defer_cancel:
  * if bmap_one_block() says there is only one block (ie: no remote blks).
  */
 STATIC int
-xfs_attr_leaf_removename(xfs_da_args_t *args)
+xfs_attr_leaf_removename(
+	struct xfs_da_args	*args)
 {
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int error, forkoff;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			error, forkoff;
 
 	trace_xfs_attr_leaf_removename(args);
 
@@ -754,19 +754,19 @@ xfs_attr_leaf_removename(xfs_da_args_t *args)
 	 * If the result is small enough, shrink it all into the inode.
 	 */
 	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		xfs_defer_init(args->dfops, args->firstblock);
+		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		xfs_defer_ijoin(args->trans->t_dfops, dp);
+		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 		if (error)
 			goto out_defer_cancel;
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans->t_dfops);
 	return error;
 }
 
@@ -817,13 +817,14 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
  * add a whole extra layer of confusion on top of that.
  */
 STATIC int
-xfs_attr_node_addname(xfs_da_args_t *args)
+xfs_attr_node_addname(
+	struct xfs_da_args	*args)
 {
-	xfs_da_state_t *state;
-	xfs_da_state_blk_t *blk;
-	xfs_inode_t *dp;
-	xfs_mount_t *mp;
-	int retval, error;
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_mount	*mp;
+	int			retval, error;
 
 	trace_xfs_attr_node_addname(args);
 
@@ -882,12 +883,13 @@ restart:
 			 */
 			xfs_da_state_free(state);
 			state = NULL;
-			xfs_defer_init(args->dfops, args->firstblock);
+			xfs_defer_init(args->trans->t_dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			xfs_defer_ijoin(args->trans->t_dfops, dp);
+			error = xfs_defer_finish(&args->trans,
+						 args->trans->t_dfops);
 			if (error)
 				goto out_defer_cancel;
 
@@ -908,12 +910,12 @@ restart:
 		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
 		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
+		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		xfs_defer_ijoin(args->trans->t_dfops, dp);
+		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 		if (error)
 			goto out_defer_cancel;
 	} else {
@@ -1006,12 +1008,12 @@ restart:
 		 * Check to see if the tree needs to be collapsed.
 		 */
 		if (retval && (state->path.active > 1)) {
-			xfs_defer_init(args->dfops, args->firstblock);
+			xfs_defer_init(args->trans->t_dfops, args->firstblock);
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			xfs_defer_ijoin(args->trans->t_dfops, dp);
+			error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 			if (error)
 				goto out_defer_cancel;
 		}
@@ -1040,7 +1042,7 @@ out:
 		return error;
 	return retval;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans->t_dfops);
 	goto out;
 }
 
@@ -1052,13 +1054,14 @@ out_defer_cancel:
  * the root node (a special case of an intermediate node).
  */
 STATIC int
-xfs_attr_node_removename(xfs_da_args_t *args)
+xfs_attr_node_removename(
+	struct xfs_da_args	*args)
 {
-	xfs_da_state_t *state;
-	xfs_da_state_blk_t *blk;
-	xfs_inode_t *dp;
-	struct xfs_buf *bp;
-	int retval, error, forkoff;
+	struct xfs_da_state	*state;
+	struct xfs_da_state_blk	*blk;
+	struct xfs_inode	*dp;
+	struct xfs_buf		*bp;
+	int			retval, error, forkoff;
 
 	trace_xfs_attr_node_removename(args);
 
@@ -1130,12 +1133,12 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 	 * Check to see if the tree needs to be collapsed.
 	 */
 	if (retval && (state->path.active > 1)) {
-		xfs_defer_init(args->dfops, args->firstblock);
+		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		xfs_defer_ijoin(args->trans->t_dfops, dp);
+		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 		if (error)
 			goto out_defer_cancel;
 		/*
@@ -1162,13 +1165,13 @@ xfs_attr_node_removename(xfs_da_args_t *args)
 			goto out;
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->dfops, args->firstblock);
+			xfs_defer_init(args->trans->t_dfops, args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->dfops);
+			xfs_defer_ijoin(args->trans->t_dfops, dp);
+			error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 			if (error)
 				goto out_defer_cancel;
 		} else
@@ -1180,7 +1183,7 @@ out:
 	xfs_da_state_free(state);
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans->t_dfops);
 	goto out;
 }
 
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 76e90046731c..c131469db0f1 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -747,18 +747,18 @@ xfs_attr_shortform_getvalue(xfs_da_args_t *args)
  */
 int
 xfs_attr_shortform_to_leaf(
-	struct xfs_da_args	*args,
-	struct xfs_buf		**leaf_bp)
+	struct xfs_da_args		*args,
+	struct xfs_buf			**leaf_bp)
 {
-	xfs_inode_t *dp;
-	xfs_attr_shortform_t *sf;
-	xfs_attr_sf_entry_t *sfe;
-	xfs_da_args_t nargs;
-	char *tmpbuffer;
-	int error, i, size;
-	xfs_dablk_t blkno;
-	struct xfs_buf *bp;
-	xfs_ifork_t *ifp;
+	struct xfs_inode		*dp;
+	struct xfs_attr_shortform	*sf;
+	struct xfs_attr_sf_entry	*sfe;
+	struct xfs_da_args		nargs;
+	char				*tmpbuffer;
+	int				error, i, size;
+	xfs_dablk_t			blkno;
+	struct xfs_buf			*bp;
+	struct xfs_ifork		*ifp;
 
 	trace_xfs_attr_sf_to_leaf(args);
 
@@ -803,7 +803,6 @@ xfs_attr_shortform_to_leaf(
 	nargs.dp = dp;
 	nargs.geo = args->geo;
 	nargs.firstblock = args->firstblock;
-	nargs.dfops = args->dfops;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
@@ -1007,7 +1006,6 @@ xfs_attr3_leaf_to_shortform(
 	nargs.geo = args->geo;
 	nargs.dp = dp;
 	nargs.firstblock = args->firstblock;
-	nargs.dfops = args->dfops;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index bf2e0371149b..577c4c372265 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -480,15 +480,16 @@ xfs_attr_rmtval_set(
 		 * extent and then crash then the block may not contain the
 		 * correct metadata after log recovery occurs.
 		 */
-		xfs_defer_init(args->dfops, args->firstblock);
+		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
 				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
-				  args->total, &map, &nmap, args->dfops);
+				  args->total, &map, &nmap,
+				  args->trans->t_dfops);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		xfs_defer_ijoin(args->trans->t_dfops, dp);
+		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 		if (error)
 			goto out_defer_cancel;
 
@@ -522,7 +523,7 @@ xfs_attr_rmtval_set(
 
 		ASSERT(blkcnt > 0);
 
-		xfs_defer_init(args->dfops, args->firstblock);
+		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
 				       blkcnt, &map, &nmap,
@@ -557,7 +558,7 @@ xfs_attr_rmtval_set(
 	ASSERT(valuelen == 0);
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans->t_dfops);
 	args->trans = NULL;
 	return error;
 }
@@ -626,14 +627,14 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		xfs_defer_init(args->dfops, args->firstblock);
+		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
 				    XFS_BMAPI_ATTRFORK, 1, args->firstblock,
-				    args->dfops, &done);
+				    args->trans->t_dfops, &done);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->dfops, args->dp);
-		error = xfs_defer_finish(&args->trans, args->dfops);
+		xfs_defer_ijoin(args->trans->t_dfops, args->dp);
+		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
 		if (error)
 			goto out_defer_cancel;
 
@@ -646,7 +647,7 @@ xfs_attr_rmtval_remove(
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->dfops);
+	xfs_defer_cancel(args->trans->t_dfops);
 	args->trans = NULL;
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 459a29cb17c2..c65aeb088552 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1007,7 +1007,6 @@ xfs_bmap_add_attrfork_local(
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
 		dargs.firstblock = firstblock;
-		dargs.dfops = tp->t_dfops;
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 8a301402bbc4..d2048e4e93ec 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2063,7 +2063,7 @@ xfs_da_grow_inode_int(
 	error = xfs_bmapi_write(tp, dp, *bno, count,
 			xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
 			args->firstblock, args->total, &map, &nmap,
-			args->dfops);
+			args->trans->t_dfops);
 	if (error)
 		return error;
 
@@ -2086,7 +2086,8 @@ xfs_da_grow_inode_int(
 			error = xfs_bmapi_write(tp, dp, b, c,
 					xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
 					args->firstblock, args->total,
-					&mapp[mapi], &nmap, args->dfops);
+					&mapp[mapi], &nmap,
+					args->trans->t_dfops);
 			if (error)
 				goto out_free_map;
 			if (nmap < 1)
@@ -2375,13 +2376,13 @@ done:
  */
 int
 xfs_da_shrink_inode(
-	xfs_da_args_t	*args,
-	xfs_dablk_t	dead_blkno,
-	struct xfs_buf	*dead_buf)
+	struct xfs_da_args	*args,
+	xfs_dablk_t		dead_blkno,
+	struct xfs_buf		*dead_buf)
 {
-	xfs_inode_t *dp;
-	int done, error, w, count;
-	xfs_trans_t *tp;
+	struct xfs_inode	*dp;
+	int			done, error, w, count;
+	struct xfs_trans	*tp;
 
 	trace_xfs_da_shrink_inode(args);
 
@@ -2396,7 +2397,7 @@ xfs_da_shrink_inode(
 		 */
 		error = xfs_bunmapi(tp, dp, dead_blkno, count,
 				    xfs_bmapi_aflag(w), 0, args->firstblock,
-				    args->dfops, &done);
+				    args->trans->t_dfops, &done);
 		if (error == -ENOSPC) {
 			if (w != XFS_DATA_FORK)
 				break;
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 28260073ae71..6b8a04f3f162 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -58,7 +58,6 @@ typedef struct xfs_da_args {
 	xfs_ino_t	inumber;	/* input/output inode number */
 	struct xfs_inode *dp;		/* directory inode to manipulate */
 	xfs_fsblock_t	*firstblock;	/* ptr to firstblock for bmap calls */
-	struct xfs_defer_ops *dfops;	/* ptr to freelist for bmap_finish */
 	struct xfs_trans *trans;	/* current trans (changes over time) */
 	xfs_extlen_t	total;		/* total blocks needed, for 1st bmap */
 	int		whichfork;	/* data or attribute fork */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index c98250f0de50..b21f55a11f35 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -239,8 +239,8 @@ xfs_dir_init(
  */
 int
 xfs_dir_createname(
-	xfs_trans_t		*tp,
-	xfs_inode_t		*dp,
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
 	struct xfs_name		*name,
 	xfs_ino_t		inum,		/* new entry inode number */
 	xfs_fsblock_t		*first,		/* bmap's firstblock */
@@ -274,7 +274,6 @@ xfs_dir_createname(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
-	args->dfops = tp->t_dfops;
 	args->firstblock = first;
 	args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	if (!inum)
@@ -417,16 +416,16 @@ out_free:
  */
 int
 xfs_dir_removename(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	struct xfs_name	*name,
-	xfs_ino_t	ino,
-	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	xfs_extlen_t	total)		/* bmap's total block count */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_name		*name,
+	xfs_ino_t		ino,
+	xfs_fsblock_t		*first,		/* bmap's firstblock */
+	xfs_extlen_t		total)		/* bmap's total block count */
 {
-	struct xfs_da_args *args;
-	int		rval;
-	int		v;		/* type-checking value */
+	struct xfs_da_args	*args;
+	int			rval;
+	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	ASSERT(tp->t_dfops);
@@ -447,7 +446,6 @@ xfs_dir_removename(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
-	args->dfops = tp->t_dfops;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_removename(args);
@@ -479,16 +477,16 @@ out_free:
  */
 int
 xfs_dir_replace(
-	xfs_trans_t	*tp,
-	xfs_inode_t	*dp,
-	struct xfs_name	*name,		/* name of entry to replace */
-	xfs_ino_t	inum,		/* new inode number */
-	xfs_fsblock_t	*first,		/* bmap's firstblock */
-	xfs_extlen_t	total)		/* bmap's total block count */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	struct xfs_name		*name,		/* name of entry to replace */
+	xfs_ino_t		inum,		/* new inode number */
+	xfs_fsblock_t		*first,		/* bmap's firstblock */
+	xfs_extlen_t		total)		/* bmap's total block count */
 {
-	struct xfs_da_args *args;
-	int		rval;
-	int		v;		/* type-checking value */
+	struct xfs_da_args	*args;
+	int			rval;
+	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
 	ASSERT(tp->t_dfops);
@@ -512,7 +510,6 @@ xfs_dir_replace(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
-	args->dfops = tp->t_dfops;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
 		rval = xfs_dir2_sf_replace(args);
@@ -646,17 +643,17 @@ xfs_dir2_isleaf(
  */
 int
 xfs_dir2_shrink_inode(
-	xfs_da_args_t	*args,
-	xfs_dir2_db_t	db,
-	struct xfs_buf	*bp)
+	struct xfs_da_args	*args,
+	xfs_dir2_db_t		db,
+	struct xfs_buf		*bp)
 {
-	xfs_fileoff_t	bno;		/* directory file offset */
-	xfs_dablk_t	da;		/* directory file offset */
-	int		done;		/* bunmap is finished */
-	xfs_inode_t	*dp;
-	int		error;
-	xfs_mount_t	*mp;
-	xfs_trans_t	*tp;
+	xfs_fileoff_t		bno;		/* directory file offset */
+	xfs_dablk_t		da;		/* directory file offset */
+	int			done;		/* bunmap is finished */
+	struct xfs_inode	*dp;
+	int			error;
+	struct xfs_mount	*mp;
+	struct xfs_trans	*tp;
 
 	trace_xfs_dir2_shrink_inode(args, db);
 
@@ -667,7 +664,7 @@ xfs_dir2_shrink_inode(
 
 	/* Unmap the fsblock(s). */
 	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0,
-			    args->firstblock, args->dfops, &done);
+			    args->firstblock, args->trans->t_dfops, &done);
 	if (error) {
 		/*
 		 * ENOSPC actually can happen if we're in a removename with no
-- 
cgit v1.2.3


From 2ba13721257e2c76e90e8d83dfd9ba91c434355d Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:11 -0700
Subject: xfs: use ->t_dfops in dqalloc transaction

xfs_dquot_disk_alloc() receives a transaction from the caller and
passes a local dfops along to xfs_bmapi_write(). If we attach this
dfops to the transaction, we have to make sure to clear it before
returning to avoid invalid access of stack memory.

Since xfs_qm_dqread_alloc() is the only caller, pull dfops into the
caller and attach it to the transaction to eliminate this pattern
entirely.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_dquot.c | 34 ++++++++++++++++++++--------------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 0973a0423bed..aa62f8b17376 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -286,8 +286,8 @@ xfs_dquot_disk_alloc(
 	struct xfs_buf		**bpp)
 {
 	struct xfs_bmbt_irec	map;
-	struct xfs_defer_ops	dfops;
-	struct xfs_mount	*mp = (*tpp)->t_mountp;
+	struct xfs_trans	*tp = *tpp;
+	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*bp;
 	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
 	xfs_fsblock_t		firstblock;
@@ -296,7 +296,8 @@ xfs_dquot_disk_alloc(
 
 	trace_xfs_dqalloc(dqp);
 
-	xfs_defer_init(&dfops, &firstblock);
+	xfs_defer_init(tp->t_dfops, &firstblock);
+
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
 		/*
@@ -308,11 +309,11 @@ xfs_dquot_disk_alloc(
 	}
 
 	/* Create the block mapping. */
-	xfs_trans_ijoin(*tpp, quotip, XFS_ILOCK_EXCL);
-	error = xfs_bmapi_write(*tpp, quotip, dqp->q_fileoffset,
+	xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
+	error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset,
 			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
 			&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
-			&map, &nmaps, &dfops);
+			&map, &nmaps, tp->t_dfops);
 	if (error)
 		goto error0;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
@@ -326,7 +327,7 @@ xfs_dquot_disk_alloc(
 	dqp->q_blkno = XFS_FSB_TO_DADDR(mp, map.br_startblock);
 
 	/* now we can just get the buffer (there's nothing to read yet) */
-	bp = xfs_trans_get_buf(*tpp, mp->m_ddev_targp, dqp->q_blkno,
+	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, dqp->q_blkno,
 			mp->m_quotainfo->qi_dqchunklen, 0);
 	if (!bp) {
 		error = -ENOMEM;
@@ -338,7 +339,7 @@ xfs_dquot_disk_alloc(
 	 * Make a chunk of dquots out of this buffer and log
 	 * the entire thing.
 	 */
-	xfs_qm_init_dquot_blk(*tpp, mp, be32_to_cpu(dqp->q_core.d_id),
+	xfs_qm_init_dquot_blk(tp, mp, be32_to_cpu(dqp->q_core.d_id),
 			      dqp->dq_flags & XFS_DQ_ALLTYPES, bp);
 	xfs_buf_set_ref(bp, XFS_DQUOT_REF);
 
@@ -364,14 +365,15 @@ xfs_dquot_disk_alloc(
 	 * is responsible for unlocking any buffer passed back, either
 	 * manually or by committing the transaction.
 	 */
-	xfs_trans_bhold(*tpp, bp);
-	error = xfs_defer_bjoin(&dfops, bp);
+	xfs_trans_bhold(tp, bp);
+	error = xfs_defer_bjoin(tp->t_dfops, bp);
 	if (error) {
-		xfs_trans_bhold_release(*tpp, bp);
-		xfs_trans_brelse(*tpp, bp);
+		xfs_trans_bhold_release(tp, bp);
+		xfs_trans_brelse(tp, bp);
 		goto error1;
 	}
-	error = xfs_defer_finish(tpp, &dfops);
+	error = xfs_defer_finish(tpp, tp->t_dfops);
+	tp = *tpp;
 	if (error) {
 		xfs_buf_relse(bp);
 		goto error1;
@@ -380,7 +382,7 @@ xfs_dquot_disk_alloc(
 	return 0;
 
 error1:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 error0:
 	return error;
 }
@@ -538,13 +540,17 @@ xfs_qm_dqread_alloc(
 	struct xfs_buf		**bpp)
 {
 	struct xfs_trans	*tp;
+	struct xfs_defer_ops	dfops;
 	struct xfs_buf		*bp;
+	xfs_fsblock_t		firstblock;
 	int			error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc,
 			XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
 	if (error)
 		goto err;
+	xfs_defer_init(&dfops, &firstblock);
+	tp->t_dfops = &dfops;
 
 	error = xfs_dquot_disk_alloc(&tp, dqp, &bp);
 	if (error)
-- 
cgit v1.2.3


From 175d1a013eaf35c802e0195d87ac2a8df83ad42a Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:12 -0700
Subject: xfs: use ->t_dfops for all xfs_bmapi_write() callers

Attach ->t_dfops for all remaining callers of xfs_bmapi_write().
This prepares the latter to no longer require a separate dfops
parameter.

Note that xfs_symlink() already uses ->t_dfops. Fix up the local
references for consistency.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c |  5 +++--
 fs/xfs/xfs_iomap.c     | 21 ++++++++++++---------
 fs/xfs/xfs_reflink.c   |  7 ++++---
 fs/xfs/xfs_rtalloc.c   |  7 ++++---
 fs/xfs/xfs_symlink.c   |  6 +++---
 5 files changed, 26 insertions(+), 20 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index da561882c349..4a698dab85d2 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -973,16 +973,17 @@ xfs_alloc_file_space(
 		xfs_trans_ijoin(tp, ip, 0);
 
 		xfs_defer_init(&dfops, &firstfsb);
+		tp->t_dfops = &dfops;
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
 					allocatesize_fsb, alloc_type, &firstfsb,
-					resblks, imapp, &nimaps, &dfops);
+					resblks, imapp, &nimaps, tp->t_dfops);
 		if (error)
 			goto error0;
 
 		/*
 		 * Complete the transaction
 		 */
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto error0;
 
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index fb9746cc7338..7c0b858f6723 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -255,17 +255,18 @@ xfs_iomap_write_direct(
 	 * caller gave to us.
 	 */
 	xfs_defer_init(&dfops, &firstfsb);
+	tp->t_dfops = &dfops;
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 				bmapi_flags, &firstfsb, resblks, imap,
-				&nimaps, &dfops);
+				&nimaps, tp->t_dfops);
 	if (error)
 		goto out_bmap_cancel;
 
 	/*
 	 * Complete the transaction
 	 */
-	error = xfs_defer_finish(&tp, &dfops);
+	error = xfs_defer_finish(&tp, tp->t_dfops);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -289,7 +290,7 @@ out_unlock:
 	return error;
 
 out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
@@ -717,6 +718,7 @@ xfs_iomap_write_allocate(
 			xfs_trans_ijoin(tp, ip, 0);
 
 			xfs_defer_init(&dfops, &first_block);
+			tp->t_dfops = &dfops;
 
 			/*
 			 * it is possible that the extents have changed since
@@ -772,11 +774,11 @@ xfs_iomap_write_allocate(
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
 						count_fsb, flags, &first_block,
 						nres, imap, &nimaps,
-						&dfops);
+						tp->t_dfops);
 			if (error)
 				goto trans_cancel;
 
-			error = xfs_defer_finish(&tp, &dfops);
+			error = xfs_defer_finish(&tp, tp->t_dfops);
 			if (error)
 				goto trans_cancel;
 
@@ -810,7 +812,7 @@ xfs_iomap_write_allocate(
 	}
 
 trans_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_cancel(tp);
 error0:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -878,10 +880,11 @@ xfs_iomap_write_unwritten(
 		 * Modify the unwritten extent state of the buffer.
 		 */
 		xfs_defer_init(&dfops, &firstfsb);
+		tp->t_dfops = &dfops;
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 					XFS_BMAPI_CONVERT, &firstfsb, resblks,
-					&imap, &nimaps, &dfops);
+					&imap, &nimaps, tp->t_dfops);
 		if (error)
 			goto error_on_bmapi_transaction;
 
@@ -901,7 +904,7 @@ xfs_iomap_write_unwritten(
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto error_on_bmapi_transaction;
 
@@ -928,7 +931,7 @@ xfs_iomap_write_unwritten(
 	return 0;
 
 error_on_bmapi_transaction:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 33845009bec5..3c28e7ff7365 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -429,19 +429,20 @@ retry:
 	xfs_trans_ijoin(tp, ip, 0);
 
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_dfops = &dfops;
 	nimaps = 1;
 
 	/* Allocate the entire reservation as unwritten blocks. */
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block,
-			resblks, imap, &nimaps, &dfops);
+			resblks, imap, &nimaps, tp->t_dfops);
 	if (error)
 		goto out_bmap_cancel;
 
 	xfs_inode_set_cowblocks_tag(ip);
 
 	/* Finish up. */
-	error = xfs_defer_finish(&tp, &dfops);
+	error = xfs_defer_finish(&tp, tp->t_dfops);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -458,7 +459,7 @@ retry:
 convert:
 	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
 out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
 			XFS_QMOPT_RES_REGBLKS);
 out:
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 329d4d26c13e..312d410d91fb 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -788,13 +788,14 @@ xfs_growfs_rt_alloc(
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
 		xfs_defer_init(&dfops, &firstblock);
+		tp->t_dfops = &dfops;
 		/*
 		 * Allocate blocks to the bitmap file.
 		 */
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
 					XFS_BMAPI_METADATA, &firstblock,
-					resblks, &map, &nmap, &dfops);
+					resblks, &map, &nmap, tp->t_dfops);
 		if (!error && nmap < 1)
 			error = -ENOSPC;
 		if (error)
@@ -802,7 +803,7 @@ xfs_growfs_rt_alloc(
 		/*
 		 * Free any blocks freed up in the transaction, then commit.
 		 */
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
@@ -855,7 +856,7 @@ xfs_growfs_rt_alloc(
 	return 0;
 
 out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index e347a3db018f..6825a31727d1 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -291,7 +291,7 @@ xfs_symlink(
 
 		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
 				  XFS_BMAPI_METADATA, &first_block, resblks,
-				  mval, &nmaps, &dfops);
+				  mval, &nmaps, tp->t_dfops);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -354,7 +354,7 @@ xfs_symlink(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_defer_finish(&tp, &dfops);
+	error = xfs_defer_finish(&tp, tp->t_dfops);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -370,7 +370,7 @@ xfs_symlink(
 	return 0;
 
 out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_inode:
-- 
cgit v1.2.3


From 6e702a5dcbe1d38cf479931dd2e2a3da884143f0 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:12 -0700
Subject: xfs: remove xfs_bmapi_write() dfops param

Now that all callers use ->t_dfops, the xfs_bmapi_write() dfops
parameter is no longer necessary. Remove it and access ->t_dfops
directly. This patch does not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_remote.c |  3 +--
 fs/xfs/libxfs/xfs_bmap.c        | 10 +++++-----
 fs/xfs/libxfs/xfs_bmap.h        |  3 +--
 fs/xfs/libxfs/xfs_da_btree.c    |  6 ++----
 fs/xfs/xfs_bmap_util.c          |  2 +-
 fs/xfs/xfs_dquot.c              |  2 +-
 fs/xfs/xfs_iomap.c              |  7 +++----
 fs/xfs/xfs_reflink.c            |  8 ++++----
 fs/xfs/xfs_rtalloc.c            |  2 +-
 fs/xfs/xfs_symlink.c            |  2 +-
 10 files changed, 20 insertions(+), 25 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 577c4c372265..1f2bc86a28ed 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -484,8 +484,7 @@ xfs_attr_rmtval_set(
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
 				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
-				  args->total, &map, &nmap,
-				  args->trans->t_dfops);
+				  args->total, &map, &nmap);
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, dp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c65aeb088552..02e72c195c4f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4245,8 +4245,7 @@ xfs_bmapi_write(
 						   controls a.g. for allocs */
 	xfs_extlen_t		total,		/* total blocks needed */
 	struct xfs_bmbt_irec	*mval,		/* output: map values */
-	int			*nmap,		/* i/o: mval size/count */
-	struct xfs_defer_ops	*dfops)		/* i/o: list extents to free */
+	int			*nmap)		/* i/o: mval size/count */
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
@@ -4337,7 +4336,7 @@ xfs_bmapi_write(
 	bma.ip = ip;
 	bma.total = total;
 	bma.datatype = 0;
-	bma.dfops = dfops;
+	bma.dfops = tp ? tp->t_dfops : NULL;
 	bma.firstblock = firstblock;
 
 	while (bno < end && n < *nmap) {
@@ -4414,8 +4413,9 @@ xfs_bmapi_write(
 			 * the refcount btree for orphan recovery.
 			 */
 			if (whichfork == XFS_COW_FORK) {
-				error = xfs_refcount_alloc_cow_extent(mp, dfops,
-						bma.blkno, bma.length);
+				error = xfs_refcount_alloc_cow_extent(mp,
+						tp->t_dfops, bma.blkno,
+						bma.length);
 				if (error)
 					goto error0;
 			}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 44639588d1c7..fc86cc218c58 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -203,8 +203,7 @@ int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
 		xfs_fsblock_t *firstblock, xfs_extlen_t total,
-		struct xfs_bmbt_irec *mval, int *nmap,
-		struct xfs_defer_ops *dfops);
+		struct xfs_bmbt_irec *mval, int *nmap);
 int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
 		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index d2048e4e93ec..e43f1dda02e4 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2062,8 +2062,7 @@ xfs_da_grow_inode_int(
 	ASSERT(args->firstblock != NULL);
 	error = xfs_bmapi_write(tp, dp, *bno, count,
 			xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
-			args->firstblock, args->total, &map, &nmap,
-			args->trans->t_dfops);
+			args->firstblock, args->total, &map, &nmap);
 	if (error)
 		return error;
 
@@ -2086,8 +2085,7 @@ xfs_da_grow_inode_int(
 			error = xfs_bmapi_write(tp, dp, b, c,
 					xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
 					args->firstblock, args->total,
-					&mapp[mapi], &nmap,
-					args->trans->t_dfops);
+					&mapp[mapi], &nmap);
 			if (error)
 				goto out_free_map;
 			if (nmap < 1)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 4a698dab85d2..cf54da3187d5 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -976,7 +976,7 @@ xfs_alloc_file_space(
 		tp->t_dfops = &dfops;
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
 					allocatesize_fsb, alloc_type, &firstfsb,
-					resblks, imapp, &nimaps, tp->t_dfops);
+					resblks, imapp, &nimaps);
 		if (error)
 			goto error0;
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index aa62f8b17376..1ef38e1df679 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -313,7 +313,7 @@ xfs_dquot_disk_alloc(
 	error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset,
 			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
 			&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
-			&map, &nmaps, tp->t_dfops);
+			&map, &nmaps);
 	if (error)
 		goto error0;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 7c0b858f6723..0c736c938f52 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -259,7 +259,7 @@ xfs_iomap_write_direct(
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 				bmapi_flags, &firstfsb, resblks, imap,
-				&nimaps, tp->t_dfops);
+				&nimaps);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -773,8 +773,7 @@ xfs_iomap_write_allocate(
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
 						count_fsb, flags, &first_block,
-						nres, imap, &nimaps,
-						tp->t_dfops);
+						nres, imap, &nimaps);
 			if (error)
 				goto trans_cancel;
 
@@ -884,7 +883,7 @@ xfs_iomap_write_unwritten(
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 					XFS_BMAPI_CONVERT, &firstfsb, resblks,
-					&imap, &nimaps, tp->t_dfops);
+					&imap, &nimaps);
 		if (error)
 			goto error_on_bmapi_transaction;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 3c28e7ff7365..9f3f144bf9ff 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -326,7 +326,7 @@ xfs_reflink_convert_cow_extent(
 		return 0;
 	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block,
-			0, imap, &nimaps, NULL);
+			0, imap, &nimaps);
 }
 
 /* Convert all of the unwritten CoW extents in a file's range to real ones. */
@@ -349,8 +349,8 @@ xfs_reflink_convert_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
-			XFS_BMAPI_CONVERT_ONLY, &first_block, 0, &imap, &nimaps,
-			NULL);
+			XFS_BMAPI_CONVERT_ONLY, &first_block, 0, &imap,
+			&nimaps);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
@@ -435,7 +435,7 @@ retry:
 	/* Allocate the entire reservation as unwritten blocks. */
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block,
-			resblks, imap, &nimaps, tp->t_dfops);
+			resblks, imap, &nimaps);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 312d410d91fb..1c7d1238ff3b 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -795,7 +795,7 @@ xfs_growfs_rt_alloc(
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
 					XFS_BMAPI_METADATA, &firstblock,
-					resblks, &map, &nmap, tp->t_dfops);
+					resblks, &map, &nmap);
 		if (!error && nmap < 1)
 			error = -ENOSPC;
 		if (error)
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 6825a31727d1..2b6bcfd39c14 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -291,7 +291,7 @@ xfs_symlink(
 
 		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
 				  XFS_BMAPI_METADATA, &first_block, resblks,
-				  mval, &nmaps, tp->t_dfops);
+				  mval, &nmaps);
 		if (error)
 			goto out_bmap_cancel;
 
-- 
cgit v1.2.3


From 4bcfa613a0582a9992a6c2af82273bd770103d12 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:13 -0700
Subject: xfs: use ->t_dfops for all xfs_bunmapi() callers

Use ->t_dfops for all remaining xfs_bunmapi() callers. This prepares
the latter to no longer require a dfops parameter.

Note that xfs_itruncate_extents_flags() associates a local dfops
with a transaction provided from the caller. Since there are
multiple callers, set and reset ->t_dfops before the function
returns to avoid exposure of stack memory to the caller.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c |  9 +++++----
 fs/xfs/xfs_inode.c     | 12 ++++++++----
 fs/xfs/xfs_reflink.c   | 27 +++++++++++++++------------
 fs/xfs/xfs_symlink.c   |  9 +++++----
 4 files changed, 33 insertions(+), 24 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index cf54da3187d5..76f28b823866 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1044,13 +1044,14 @@ xfs_unmap_extent(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	xfs_defer_init(&dfops, &firstfsb);
+	tp->t_dfops = &dfops;
 	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, &firstfsb,
-			&dfops, done);
+			tp->t_dfops, done);
 	if (error)
 		goto out_bmap_cancel;
 
-	xfs_defer_ijoin(&dfops, ip);
-	error = xfs_defer_finish(&tp, &dfops);
+	xfs_defer_ijoin(tp->t_dfops, ip);
+	error = xfs_defer_finish(&tp, tp->t_dfops);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -1060,7 +1061,7 @@ out_unlock:
 	return error;
 
 out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	goto out_unlock;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index e1bc686b70b4..539d96201666 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1545,6 +1545,7 @@ xfs_itruncate_extents_flags(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
+	struct xfs_defer_ops	*odfops = tp->t_dfops;
 	struct xfs_defer_ops	dfops;
 	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		first_unmap_block;
@@ -1584,9 +1585,10 @@ xfs_itruncate_extents_flags(
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
 		xfs_defer_init(&dfops, &first_block);
+		tp->t_dfops = &dfops;
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
 				    XFS_ITRUNC_MAX_EXTENTS, &first_block,
-				    &dfops, &done);
+				    tp->t_dfops, &done);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1594,8 +1596,8 @@ xfs_itruncate_extents_flags(
 		 * Duplicate the transaction that has the permanent
 		 * reservation and commit the old transaction.
 		 */
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		xfs_defer_ijoin(tp->t_dfops, ip);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1623,6 +1625,8 @@ xfs_itruncate_extents_flags(
 	trace_xfs_itruncate_extents_end(ip, new_size);
 
 out:
+	/* ->t_dfops points to local stack, don't leak it! */
+	tp->t_dfops = odfops;
 	*tpp = tp;
 	return error;
 out_bmap_cancel:
@@ -1631,7 +1635,7 @@ out_bmap_cancel:
 	 * the transaction can be properly aborted.  We just need to make sure
 	 * we're not holding any resources that we were not when we came in.
 	 */
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 	goto out;
 }
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 9f3f144bf9ff..c119cd33766e 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -700,9 +700,10 @@ xfs_reflink_end_cow(
 
 		/* Unmap the old blocks in the data fork. */
 		xfs_defer_init(&dfops, &firstfsb);
+		tp->t_dfops = &dfops;
 		rlen = del.br_blockcount;
 		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
-				&firstfsb, &dfops);
+				&firstfsb, tp->t_dfops);
 		if (error)
 			goto out_defer;
 
@@ -714,13 +715,14 @@ xfs_reflink_end_cow(
 		trace_xfs_reflink_cow_remap(ip, &del);
 
 		/* Free the CoW orphan record. */
-		error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
+		error = xfs_refcount_free_cow_extent(tp->t_mountp, tp->t_dfops,
 				del.br_startblock, del.br_blockcount);
 		if (error)
 			goto out_defer;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
+		error = xfs_bmap_map_extent(tp->t_mountp, tp->t_dfops, ip,
+					    &del);
 		if (error)
 			goto out_defer;
 
@@ -731,8 +733,8 @@ xfs_reflink_end_cow(
 		/* Remove the mapping from the CoW fork. */
 		xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
 
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		xfs_defer_ijoin(tp->t_dfops, ip);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto out_defer;
 		if (!xfs_iext_get_extent(ifp, &icur, &got))
@@ -750,7 +752,7 @@ prev_extent:
 	return 0;
 
 out_defer:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1049,8 +1051,9 @@ xfs_reflink_remap_extent(
 	rlen = unmap_len;
 	while (rlen) {
 		xfs_defer_init(&dfops, &firstfsb);
+		tp->t_dfops = &dfops;
 		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
-				&firstfsb, &dfops);
+				&firstfsb, tp->t_dfops);
 		if (error)
 			goto out_defer;
 
@@ -1071,12 +1074,12 @@ xfs_reflink_remap_extent(
 				uirec.br_blockcount, uirec.br_startblock);
 
 		/* Update the refcount tree */
-		error = xfs_refcount_increase_extent(mp, &dfops, &uirec);
+		error = xfs_refcount_increase_extent(mp, tp->t_dfops, &uirec);
 		if (error)
 			goto out_defer;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(mp, &dfops, ip, &uirec);
+		error = xfs_bmap_map_extent(mp, tp->t_dfops, ip, &uirec);
 		if (error)
 			goto out_defer;
 
@@ -1097,8 +1100,8 @@ xfs_reflink_remap_extent(
 
 next_extent:
 		/* Process all the deferred stuff. */
-		xfs_defer_ijoin(&dfops, ip);
-		error = xfs_defer_finish(&tp, &dfops);
+		xfs_defer_ijoin(tp->t_dfops, ip);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto out_defer;
 	}
@@ -1110,7 +1113,7 @@ next_extent:
 	return 0;
 
 out_defer:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 2b6bcfd39c14..290ae13d4673 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -444,6 +444,7 @@ xfs_inactive_symlink_rmt(
 	 */
 	done = 0;
 	xfs_defer_init(&dfops, &first_block);
+	tp->t_dfops = &dfops;
 	nmaps = ARRAY_SIZE(mval);
 	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
 				mval, &nmaps, 0);
@@ -466,15 +467,15 @@ xfs_inactive_symlink_rmt(
 	 * Unmap the dead block(s) to the dfops.
 	 */
 	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps,
-			    &first_block, &dfops, &done);
+			    &first_block, tp->t_dfops, &done);
 	if (error)
 		goto error_bmap_cancel;
 	ASSERT(done);
 	/*
 	 * Commit the first transaction.  This logs the EFI and the inode.
 	 */
-	xfs_defer_ijoin(&dfops, ip);
-	error = xfs_defer_finish(&tp, &dfops);
+	xfs_defer_ijoin(tp->t_dfops, ip);
+	error = xfs_defer_finish(&tp, tp->t_dfops);
 	if (error)
 		goto error_bmap_cancel;
 
@@ -499,7 +500,7 @@ xfs_inactive_symlink_rmt(
 	return 0;
 
 error_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 error_trans_cancel:
 	xfs_trans_cancel(tp);
 error_unlock:
-- 
cgit v1.2.3


From ccd9d91148780a5e979ac00bce67c2155fb6378f Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:13 -0700
Subject: xfs: remove xfs_bunmapi() dfops param

Now that all xfs_bunmapi() callers use ->t_dfops, remove the
unnecessary parameter and access ->t_dfops directly. This patch does
not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_remote.c |  2 +-
 fs/xfs/libxfs/xfs_bmap.c        | 20 +++++++++-----------
 fs/xfs/libxfs/xfs_bmap.h        |  5 ++---
 fs/xfs/libxfs/xfs_da_btree.c    |  2 +-
 fs/xfs/libxfs/xfs_dir2.c        |  2 +-
 fs/xfs/xfs_bmap_util.c          |  2 +-
 fs/xfs/xfs_inode.c              |  2 +-
 fs/xfs/xfs_reflink.c            |  5 ++---
 fs/xfs/xfs_symlink.c            |  3 +--
 9 files changed, 19 insertions(+), 24 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 1f2bc86a28ed..179259fd1b5e 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -629,7 +629,7 @@ xfs_attr_rmtval_remove(
 		xfs_defer_init(args->trans->t_dfops, args->firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
 				    XFS_BMAPI_ATTRFORK, 1, args->firstblock,
-				    args->trans->t_dfops, &done);
+				    &done);
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, args->dp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 02e72c195c4f..9c778e50ad19 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5143,26 +5143,26 @@ done:
  */
 int						/* error */
 __xfs_bunmapi(
-	xfs_trans_t		*tp,		/* transaction pointer */
+	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode */
 	xfs_fileoff_t		start,		/* first file offset deleted */
 	xfs_filblks_t		*rlen,		/* i/o: amount remaining */
 	int			flags,		/* misc flags */
 	xfs_extnum_t		nexts,		/* number of extents max */
-	xfs_fsblock_t		*firstblock,	/* first allocated block
+	xfs_fsblock_t		*firstblock)	/* first allocated block
 						   controls a.g. for allocs */
-	struct xfs_defer_ops	*dfops)		/* i/o: deferred updates */
 {
-	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
-	xfs_bmbt_irec_t		del;		/* extent being deleted */
+	struct xfs_defer_ops	*dfops = tp ? tp->t_dfops : NULL;
+	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
+	struct xfs_bmbt_irec	del;		/* extent being deleted */
 	int			error;		/* error return value */
 	xfs_extnum_t		extno;		/* extent number in list */
-	xfs_bmbt_irec_t		got;		/* current extent record */
+	struct xfs_bmbt_irec	got;		/* current extent record */
 	xfs_ifork_t		*ifp;		/* inode fork pointer */
 	int			isrt;		/* freeing in rt area */
 	int			logflags;	/* transaction logging flags */
 	xfs_extlen_t		mod;		/* rt extent offset */
-	xfs_mount_t		*mp;		/* mount structure */
+	struct xfs_mount	*mp;		/* mount structure */
 	int			tmp_logflags;	/* partial logging flags */
 	int			wasdel;		/* was a delayed alloc extent */
 	int			whichfork;	/* data or attribute fork */
@@ -5516,13 +5516,11 @@ xfs_bunmapi(
 	int			flags,
 	xfs_extnum_t		nexts,
 	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops,
 	int			*done)
 {
 	int			error;
 
-	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts, firstblock,
-			dfops);
+	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts, firstblock);
 	*done = (len == 0);
 	return error;
 }
@@ -6193,7 +6191,7 @@ xfs_bmap_finish_one(
 		break;
 	case XFS_BMAP_UNMAP:
 		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
-				XFS_BMAPI_REMAP, 1, &firstfsb, dfops);
+				XFS_BMAPI_REMAP, 1, &firstfsb);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index fc86cc218c58..a83906ec6141 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -206,12 +206,11 @@ int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		struct xfs_bmbt_irec *mval, int *nmap);
 int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
-		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		xfs_extnum_t nexts, xfs_fsblock_t *firstblock);
 int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
 		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops, int *done);
+		int *done);
 int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
 		struct xfs_bmbt_irec *del);
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index e43f1dda02e4..68a72e3d9f53 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2395,7 +2395,7 @@ xfs_da_shrink_inode(
 		 */
 		error = xfs_bunmapi(tp, dp, dead_blkno, count,
 				    xfs_bmapi_aflag(w), 0, args->firstblock,
-				    args->trans->t_dfops, &done);
+				    &done);
 		if (error == -ENOSPC) {
 			if (w != XFS_DATA_FORK)
 				break;
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index b21f55a11f35..781dc63d305d 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -664,7 +664,7 @@ xfs_dir2_shrink_inode(
 
 	/* Unmap the fsblock(s). */
 	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0,
-			    args->firstblock, args->trans->t_dfops, &done);
+			    args->firstblock, &done);
 	if (error) {
 		/*
 		 * ENOSPC actually can happen if we're in a removename with no
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 76f28b823866..6c02cd264045 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1046,7 +1046,7 @@ xfs_unmap_extent(
 	xfs_defer_init(&dfops, &firstfsb);
 	tp->t_dfops = &dfops;
 	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, &firstfsb,
-			tp->t_dfops, done);
+			    done);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 539d96201666..f456df2e1394 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1588,7 +1588,7 @@ xfs_itruncate_extents_flags(
 		tp->t_dfops = &dfops;
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
 				    XFS_ITRUNC_MAX_EXTENTS, &first_block,
-				    tp->t_dfops, &done);
+				    &done);
 		if (error)
 			goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index c119cd33766e..0ac0706c98e8 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -703,7 +703,7 @@ xfs_reflink_end_cow(
 		tp->t_dfops = &dfops;
 		rlen = del.br_blockcount;
 		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
-				&firstfsb, tp->t_dfops);
+				&firstfsb);
 		if (error)
 			goto out_defer;
 
@@ -1052,8 +1052,7 @@ xfs_reflink_remap_extent(
 	while (rlen) {
 		xfs_defer_init(&dfops, &firstfsb);
 		tp->t_dfops = &dfops;
-		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
-				&firstfsb, tp->t_dfops);
+		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1, &firstfsb);
 		if (error)
 			goto out_defer;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 290ae13d4673..a54f095c1409 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -466,8 +466,7 @@ xfs_inactive_symlink_rmt(
 	/*
 	 * Unmap the dead block(s) to the dfops.
 	 */
-	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps,
-			    &first_block, tp->t_dfops, &done);
+	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &first_block, &done);
 	if (error)
 		goto error_bmap_cancel;
 	ASSERT(done);
-- 
cgit v1.2.3


From ff3edf255da7a1ceb0fb2cb7f195fc27edd0091d Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:14 -0700
Subject: xfs: remove xfs_bmapi_remap() dfops param

All xfs_bmapi_remap() callers already use ->t_dfops. Note that
deferred completion context unconditionally sets ->t_dfops if it
hasn't already been set by the caller. Remove the unnecessary
parameter and access ->t_dfops directly.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 8 ++++----
 fs/xfs/libxfs/xfs_bmap.h | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 9c778e50ad19..236e773073cf 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4511,7 +4511,6 @@ xfs_bmapi_remap(
 	xfs_fileoff_t		bno,
 	xfs_filblks_t		len,
 	xfs_fsblock_t		startblock,
-	struct xfs_defer_ops	*dfops,
 	int			flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
@@ -4561,7 +4560,7 @@ xfs_bmapi_remap(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = firstblock;
-		cur->bc_private.b.dfops = dfops;
+		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -4574,7 +4573,7 @@ xfs_bmapi_remap(
 		got.br_state = XFS_EXT_NORM;
 
 	error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
-			&cur, &got, &firstblock, dfops, &logflags, flags);
+			&cur, &got, &firstblock, tp->t_dfops, &logflags, flags);
 	if (error)
 		goto error0;
 
@@ -6185,8 +6184,9 @@ xfs_bmap_finish_one(
 
 	switch (type) {
 	case XFS_BMAP_MAP:
+		ASSERT(dfops == tp->t_dfops);
 		error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
-				startblock, dfops, 0);
+				startblock, 0);
 		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index a83906ec6141..2728e98e991a 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -284,6 +284,6 @@ xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 
 int	xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
-		struct xfs_defer_ops *dfops, int flags);
+		int flags);
 
 #endif	/* __XFS_BMAP_H__ */
-- 
cgit v1.2.3


From 3e3673e3029c1dedf75a1688a5203d9550adf490 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:14 -0700
Subject: xfs: remove struct xfs_bmalloca dfops field

Now that bma.dfops is only assigned from ->t_dfops, replace all
accesses to the former with the latter and remove the unnecessary
field. This patch does not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 30 +++++++++++++++---------------
 fs/xfs/libxfs/xfs_bmap.h |  1 -
 fs/xfs/xfs_filestream.c  |  3 ++-
 3 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 236e773073cf..e24c54799aae 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1806,7 +1806,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->dfops,
+					bma->firstblock, bma->tp->t_dfops,
 					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -1884,7 +1884,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->dfops, &bma->cur, 1,
+				bma->firstblock, bma->tp->t_dfops, &bma->cur, 1,
 				&tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -1965,8 +1965,8 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->dfops, &bma->cur,
-					1, &tmp_rval, whichfork);
+					bma->firstblock, bma->tp->t_dfops,
+					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1991,7 +1991,7 @@ xfs_bmap_add_extent_delay_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(bma->flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip,
+		error = xfs_rmap_map_extent(mp, bma->tp->t_dfops, bma->ip,
 				whichfork, new);
 		if (error)
 			goto done;
@@ -2003,7 +2003,7 @@ xfs_bmap_add_extent_delay_real(
 
 		ASSERT(bma->cur == NULL);
 		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->dfops, &bma->cur,
+				bma->firstblock, bma->tp->t_dfops, &bma->cur,
 				da_old > 0, &tmp_logflags, whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
@@ -3480,7 +3480,7 @@ xfs_bmap_btalloc(
 			error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
 		if (error)
 			return error;
-	} else if (ap->dfops->dop_low) {
+	} else if (ap->tp->t_dfops->dop_low) {
 		if (xfs_inode_is_filestream(ap->ip))
 			args.type = XFS_ALLOCTYPE_FIRST_AG;
 		else
@@ -3515,7 +3515,7 @@ xfs_bmap_btalloc(
 	 * is >= the stripe unit and the allocation offset is
 	 * at the end of file.
 	 */
-	if (!ap->dfops->dop_low && ap->aeof) {
+	if (!ap->tp->t_dfops->dop_low && ap->aeof) {
 		if (!ap->offset) {
 			args.alignment = stripe_align;
 			atype = args.type;
@@ -3607,7 +3607,7 @@ xfs_bmap_btalloc(
 		args.total = ap->minlen;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
-		ap->dfops->dop_low = true;
+		ap->tp->t_dfops->dop_low = true;
 	}
 	if (args.fsbno != NULLFSBLOCK) {
 		/*
@@ -4082,7 +4082,7 @@ xfs_bmapi_allocate(
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->dfops;
+		bma->cur->bc_private.b.dfops = bma->tp->t_dfops;
 	}
 	/*
 	 * Bump the number of extents we've allocated
@@ -4118,8 +4118,8 @@ xfs_bmapi_allocate(
 	else
 		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
 				whichfork, &bma->icur, &bma->cur, &bma->got,
-				bma->firstblock, bma->dfops, &bma->logflags,
-				bma->flags);
+				bma->firstblock, bma->tp->t_dfops,
+				&bma->logflags, bma->flags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4171,7 +4171,7 @@ xfs_bmapi_convert_unwritten(
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->dfops;
+		bma->cur->bc_private.b.dfops = bma->tp->t_dfops;
 	}
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
@@ -4189,7 +4189,7 @@ xfs_bmapi_convert_unwritten(
 
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork,
 			&bma->icur, &bma->cur, mval, bma->firstblock,
-			bma->dfops, &tmp_logflags);
+			bma->tp->t_dfops, &tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
 	 * path because the conversion might not have done so (e.g., if the
@@ -4336,8 +4336,8 @@ xfs_bmapi_write(
 	bma.ip = ip;
 	bma.total = total;
 	bma.datatype = 0;
-	bma.dfops = tp ? tp->t_dfops : NULL;
 	bma.firstblock = firstblock;
+	ASSERT(!tp || tp->t_dfops);
 
 	while (bno < end && n < *nmap) {
 		bool			need_alloc = false, wasdelay = false;
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 2728e98e991a..560235603444 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -20,7 +20,6 @@ extern kmem_zone_t	*xfs_bmap_free_item_zone;
  */
 struct xfs_bmalloca {
 	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
-	struct xfs_defer_ops	*dfops;	/* bmap freelist */
 	struct xfs_trans	*tp;	/* transaction pointer */
 	struct xfs_inode	*ip;	/* incore inode pointer */
 	struct xfs_bmbt_irec	prev;	/* extent before the new one */
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 2d2c5ab9143c..56a3999cefae 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -19,6 +19,7 @@
 #include "xfs_filestream.h"
 #include "xfs_trace.h"
 #include "xfs_ag_resv.h"
+#include "xfs_trans.h"
 
 struct xfs_fstrm_item {
 	struct xfs_mru_cache_elem	mru;
@@ -377,7 +378,7 @@ xfs_filestream_new_ag(
 
 	if (xfs_alloc_is_userdata(ap->datatype))
 		flags |= XFS_PICK_USERDATA;
-	if (ap->dfops->dop_low)
+	if (ap->tp->t_dfops->dop_low)
 		flags |= XFS_PICK_LOWSPACE;
 
 	err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);
-- 
cgit v1.2.3


From f4a9cf97faf4adb27e4e105beda420bb5253c502 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:15 -0700
Subject: xfs: use ->t_dfops for collapse/insert range operations

Use ->t_dfops for the collapse and insert range transactions. These
are the only callers of the respective bmap helpers, so replace the
unnecessary dfops parameters with direct accesses to ->t_dfops.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 16 +++++++---------
 fs/xfs/libxfs/xfs_bmap.h |  6 ++----
 fs/xfs/xfs_bmap_util.c   | 14 ++++++++------
 3 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index e24c54799aae..89a21dc7a7cb 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5683,8 +5683,7 @@ xfs_bmap_collapse_extents(
 	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
 	bool			*done,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops)
+	xfs_fsblock_t		*firstblock)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5718,7 +5717,7 @@ xfs_bmap_collapse_extents(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
+		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5739,7 +5738,7 @@ xfs_bmap_collapse_extents(
 		if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) {
 			error = xfs_bmse_merge(ip, whichfork, offset_shift_fsb,
 					&icur, &got, &prev, cur, &logflags,
-					dfops);
+					tp->t_dfops);
 			if (error)
 				goto del_cursor;
 			goto done;
@@ -5752,7 +5751,7 @@ xfs_bmap_collapse_extents(
 	}
 
 	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, dfops, new_startoff);
+			&logflags, tp->t_dfops, new_startoff);
 	if (error)
 		goto del_cursor;
 
@@ -5806,8 +5805,7 @@ xfs_bmap_insert_extents(
 	xfs_fileoff_t		offset_shift_fsb,
 	bool			*done,
 	xfs_fileoff_t		stop_fsb,
-	xfs_fsblock_t		*firstblock,
-	struct xfs_defer_ops	*dfops)
+	xfs_fsblock_t		*firstblock)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5841,7 +5839,7 @@ xfs_bmap_insert_extents(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
+		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5884,7 +5882,7 @@ xfs_bmap_insert_extents(
 	}
 
 	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, dfops, new_startoff);
+			&logflags, tp->t_dfops, new_startoff);
 	if (error)
 		goto del_cursor;
 
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 560235603444..83180c7cf3ee 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -219,14 +219,12 @@ void	xfs_bmap_del_extent_cow(struct xfs_inode *ip,
 uint	xfs_default_attroffset(struct xfs_inode *ip);
 int	xfs_bmap_collapse_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		bool *done, xfs_fsblock_t *firstblock);
 int	xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
 		xfs_fileoff_t shift);
 int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock,
-		struct xfs_defer_ops *dfops);
+		bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock);
 int	xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
 int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 6c02cd264045..cd5d410acc73 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1348,12 +1348,13 @@ xfs_collapse_file_space(
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
 		xfs_defer_init(&dfops, &first_block);
+		tp->t_dfops = &dfops;
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, &first_block, &dfops);
+				&done, &first_block);
 		if (error)
 			goto out_bmap_cancel;
 
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
@@ -1362,7 +1363,7 @@ xfs_collapse_file_space(
 	return error;
 
 out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
@@ -1427,12 +1428,13 @@ xfs_insert_file_space(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 		xfs_defer_init(&dfops, &first_block);
+		tp->t_dfops = &dfops;
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, stop_fsb, &first_block, &dfops);
+				&done, stop_fsb, &first_block);
 		if (error)
 			goto out_bmap_cancel;
 
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
@@ -1441,7 +1443,7 @@ xfs_insert_file_space(
 	return error;
 
 out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
-- 
cgit v1.2.3


From 81ba8f3e947c3c53beb535c7f29fe402429cae37 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:16 -0700
Subject: xfs: remove dfops param from internal bmap extent helpers

All callers of the various bmap extent helpers now use ->t_dfops.
Remove the unnecessary dfops params and access ->t_dfops directly.
This patch does not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 92 +++++++++++++++++++++++-------------------------
 1 file changed, 44 insertions(+), 48 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 89a21dc7a7cb..66655973c229 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -644,25 +644,24 @@ xfs_bmap_btree_to_extents(
  */
 STATIC int					/* error */
 xfs_bmap_extents_to_btree(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first-block-allocated */
-	struct xfs_defer_ops	*dfops,		/* blocks freed in xaction */
-	xfs_btree_cur_t		**curp,		/* cursor returned to caller */
+	struct xfs_btree_cur	**curp,		/* cursor returned to caller */
 	int			wasdel,		/* converting a delayed alloc */
 	int			*logflagsp,	/* inode logging flags */
 	int			whichfork)	/* data or attr fork */
 {
 	struct xfs_btree_block	*ablock;	/* allocated (child) bt block */
-	xfs_buf_t		*abp;		/* buffer for ablock */
-	xfs_alloc_arg_t		args;		/* allocation arguments */
-	xfs_bmbt_rec_t		*arp;		/* child record pointer */
+	struct xfs_buf		*abp;		/* buffer for ablock */
+	struct xfs_alloc_arg	args;		/* allocation arguments */
+	struct xfs_bmbt_rec	*arp;		/* child record pointer */
 	struct xfs_btree_block	*block;		/* btree root block */
-	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
+	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
 	int			error;		/* error return value */
-	xfs_ifork_t		*ifp;		/* inode fork pointer */
-	xfs_bmbt_key_t		*kp;		/* root block key pointer */
-	xfs_mount_t		*mp;		/* mount structure */
+	struct xfs_ifork	*ifp;		/* inode fork pointer */
+	struct xfs_bmbt_key	*kp;		/* root block key pointer */
+	struct xfs_mount	*mp;		/* mount structure */
 	xfs_bmbt_ptr_t		*pp;		/* root block address pointer */
 	struct xfs_iext_cursor	icur;
 	struct xfs_bmbt_irec	rec;
@@ -691,7 +690,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 	cur->bc_private.b.firstblock = *firstblock;
-	cur->bc_private.b.dfops = dfops;
+	cur->bc_private.b.dfops = tp->t_dfops;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
 	/*
 	 * Convert to a btree with two levels, one record in root.
@@ -705,7 +704,7 @@ xfs_bmap_extents_to_btree(
 	if (*firstblock == NULLFSBLOCK) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
-	} else if (dfops->dop_low) {
+	} else if (tp->t_dfops->dop_low) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = *firstblock;
 	} else {
@@ -958,8 +957,8 @@ error0:
  */
 STATIC int					/* error */
 xfs_bmap_add_attrfork_extents(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
 	xfs_fsblock_t		*firstblock,	/* first block allocated */
 	int			*flags)		/* inode logging flags */
 {
@@ -969,8 +968,8 @@ xfs_bmap_add_attrfork_extents(
 	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
 		return 0;
 	cur = NULL;
-	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, tp->t_dfops, &cur, 0,
-		flags, XFS_DATA_FORK);
+	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, &cur, 0, flags,
+					  XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
 		xfs_btree_del_cursor(cur,
@@ -1806,8 +1805,8 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->tp->t_dfops,
-					&bma->cur, 1, &tmp_rval, whichfork);
+					bma->firstblock, &bma->cur, 1,
+					&tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1884,8 +1883,8 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->tp->t_dfops, &bma->cur, 1,
-				&tmp_rval, whichfork);
+				bma->firstblock, &bma->cur, 1, &tmp_rval,
+				whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1965,8 +1964,8 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, bma->tp->t_dfops,
-					&bma->cur, 1, &tmp_rval, whichfork);
+					bma->firstblock, &bma->cur, 1,
+					&tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -2003,8 +2002,8 @@ xfs_bmap_add_extent_delay_real(
 
 		ASSERT(bma->cur == NULL);
 		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->tp->t_dfops, &bma->cur,
-				da_old > 0, &tmp_logflags, whichfork);
+				bma->firstblock, &bma->cur, da_old > 0,
+				&tmp_logflags, whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2044,7 +2043,6 @@ xfs_bmap_add_extent_unwritten_real(
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
 	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
-	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	int			*logflagsp) /* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;	/* btree cursor */
@@ -2058,6 +2056,7 @@ xfs_bmap_add_extent_unwritten_real(
 	int			state = xfs_bmap_fork_to_state(whichfork);
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_bmbt_irec	old;
+	struct xfs_defer_ops	*dfops = tp ? tp->t_dfops : NULL;
 
 	*logflagsp = 0;
 
@@ -2485,8 +2484,8 @@ xfs_bmap_add_extent_unwritten_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur,
-				0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, first, &cur, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2658,7 +2657,6 @@ xfs_bmap_add_extent_hole_real(
 	struct xfs_btree_cur	**curp,
 	struct xfs_bmbt_irec	*new,
 	xfs_fsblock_t		*first,
-	struct xfs_defer_ops	*dfops,
 	int			*logflagsp,
 	int			flags)
 {
@@ -2839,7 +2837,8 @@ xfs_bmap_add_extent_hole_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
+		error = xfs_rmap_map_extent(mp, tp->t_dfops, ip, whichfork,
+				new);
 		if (error)
 			goto done;
 	}
@@ -2849,8 +2848,8 @@ xfs_bmap_add_extent_hole_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, curp,
-				0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, first, curp, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		cur = *curp;
 		if (error)
@@ -4118,8 +4117,7 @@ xfs_bmapi_allocate(
 	else
 		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
 				whichfork, &bma->icur, &bma->cur, &bma->got,
-				bma->firstblock, bma->tp->t_dfops,
-				&bma->logflags, bma->flags);
+				bma->firstblock, &bma->logflags, bma->flags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4189,7 +4187,7 @@ xfs_bmapi_convert_unwritten(
 
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork,
 			&bma->icur, &bma->cur, mval, bma->firstblock,
-			bma->tp->t_dfops, &tmp_logflags);
+			&tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
 	 * path because the conversion might not have done so (e.g., if the
@@ -4573,7 +4571,7 @@ xfs_bmapi_remap(
 		got.br_state = XFS_EXT_NORM;
 
 	error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
-			&cur, &got, &firstblock, tp->t_dfops, &logflags, flags);
+			&cur, &got, &firstblock, &logflags, flags);
 	if (error)
 		goto error0;
 
@@ -4892,7 +4890,6 @@ xfs_bmap_del_extent_real(
 	xfs_inode_t		*ip,	/* incore inode pointer */
 	xfs_trans_t		*tp,	/* current transaction pointer */
 	struct xfs_iext_cursor	*icur,
-	struct xfs_defer_ops	*dfops,	/* list of extents to be freed */
 	xfs_btree_cur_t		*cur,	/* if null, not a btree */
 	xfs_bmbt_irec_t		*del,	/* data to remove from extents */
 	int			*logflagsp, /* inode logging flags */
@@ -4915,6 +4912,7 @@ xfs_bmap_del_extent_real(
 	uint			qfield;	/* quota field to update */
 	int			state = xfs_bmap_fork_to_state(whichfork);
 	struct xfs_bmbt_irec	old;
+	struct xfs_defer_ops	*dfops = tp ? tp->t_dfops : NULL;
 
 	mp = ip->i_mount;
 	XFS_STATS_INC(mp, xs_del_exlist);
@@ -5341,7 +5339,7 @@ __xfs_bunmapi(
 			del.br_state = XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent_unwritten_real(tp, ip,
 					whichfork, &icur, &cur, &del,
-					firstblock, dfops, &logflags);
+					firstblock, &logflags);
 			if (error)
 				goto error0;
 			goto nodelete;
@@ -5398,8 +5396,7 @@ __xfs_bunmapi(
 				prev.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&prev, firstblock, dfops,
-						&logflags);
+						&prev, firstblock, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5408,8 +5405,7 @@ __xfs_bunmapi(
 				del.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&del, firstblock, dfops,
-						&logflags);
+						&del, firstblock, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5421,8 +5417,8 @@ delete:
 			error = xfs_bmap_del_extent_delay(ip, whichfork, &icur,
 					&got, &del);
 		} else {
-			error = xfs_bmap_del_extent_real(ip, tp, &icur, dfops,
-					cur, &del, &tmp_logflags, whichfork,
+			error = xfs_bmap_del_extent_real(ip, tp, &icur, cur,
+					&del, &tmp_logflags, whichfork,
 					flags);
 			logflags |= tmp_logflags;
 		}
@@ -5456,8 +5452,8 @@ nodelete:
 	 */
 	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, dfops,
-			&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
@@ -6007,8 +6003,8 @@ xfs_bmap_split_extent_at(
 		int tmp_logflags; /* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, tp->t_dfops,
-				&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
 
-- 
cgit v1.2.3


From 42b394a92562b464e9ef81954ca93930c037a51b Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:16 -0700
Subject: xfs: remove xfs_btree_cur bmbt dfops field

All assignments of xfs_btree_cur.bc_private.b.dfops originate from
->t_dfops. Replace accesses of the former with the latter and remove
the unnecessary field. This patch does not change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       | 12 +-----------
 fs/xfs/libxfs/xfs_bmap_btree.c |  9 +++------
 fs/xfs/libxfs/xfs_btree.h      |  1 -
 3 files changed, 4 insertions(+), 18 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 66655973c229..32d8d87b7582 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -624,7 +624,7 @@ xfs_bmap_btree_to_extents(
 	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, cbno, 1, &oinfo);
+	xfs_bmap_add_free(mp, cur->bc_tp->t_dfops, cbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	xfs_trans_binval(tp, cbp);
@@ -690,7 +690,6 @@ xfs_bmap_extents_to_btree(
 	 */
 	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 	cur->bc_private.b.firstblock = *firstblock;
-	cur->bc_private.b.dfops = tp->t_dfops;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
 	/*
 	 * Convert to a btree with two levels, one record in root.
@@ -929,7 +928,6 @@ xfs_bmap_add_attrfork_btree(
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
-		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.firstblock = *firstblock;
 		error = xfs_bmbt_lookup_first(cur, &stat);
 		if (error)
@@ -4081,7 +4079,6 @@ xfs_bmapi_allocate(
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->tp->t_dfops;
 	}
 	/*
 	 * Bump the number of extents we've allocated
@@ -4169,7 +4166,6 @@ xfs_bmapi_convert_unwritten(
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
 		bma->cur->bc_private.b.firstblock = *bma->firstblock;
-		bma->cur->bc_private.b.dfops = bma->tp->t_dfops;
 	}
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
@@ -4558,7 +4554,6 @@ xfs_bmapi_remap(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = firstblock;
-		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5149,7 +5144,6 @@ __xfs_bunmapi(
 	xfs_fsblock_t		*firstblock)	/* first allocated block
 						   controls a.g. for allocs */
 {
-	struct xfs_defer_ops	*dfops = tp ? tp->t_dfops : NULL;
 	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
 	struct xfs_bmbt_irec	del;		/* extent being deleted */
 	int			error;		/* error return value */
@@ -5223,7 +5217,6 @@ __xfs_bunmapi(
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = dfops;
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
@@ -5713,7 +5706,6 @@ xfs_bmap_collapse_extents(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5835,7 +5827,6 @@ xfs_bmap_insert_extents(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstblock;
-		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5959,7 +5950,6 @@ xfs_bmap_split_extent_at(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
 		cur->bc_private.b.firstblock = *firstfsb;
-		cur->bc_private.b.dfops = tp->t_dfops;
 		cur->bc_private.b.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index e1a2d9ceb615..e8b01af09db5 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -176,7 +176,6 @@ xfs_bmbt_dup_cursor(
 	 * since init cursor doesn't get them.
 	 */
 	new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
-	new->bc_private.b.dfops = cur->bc_private.b.dfops;
 	new->bc_private.b.flags = cur->bc_private.b.flags;
 
 	return new;
@@ -189,7 +188,6 @@ xfs_bmbt_update_cursor(
 {
 	ASSERT((dst->bc_private.b.firstblock != NULLFSBLOCK) ||
 	       (dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
-	ASSERT(dst->bc_private.b.dfops == src->bc_private.b.dfops);
 
 	dst->bc_private.b.allocated += src->bc_private.b.allocated;
 	dst->bc_private.b.firstblock = src->bc_private.b.firstblock;
@@ -230,7 +228,7 @@ xfs_bmbt_alloc_block(
 		 * block allocation here and corrupt the filesystem.
 		 */
 		args.minleft = args.tp->t_blk_res;
-	} else if (cur->bc_private.b.dfops->dop_low) {
+	} else if (cur->bc_tp->t_dfops->dop_low) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -257,7 +255,7 @@ xfs_bmbt_alloc_block(
 		error = xfs_alloc_vextent(&args);
 		if (error)
 			goto error0;
-		cur->bc_private.b.dfops->dop_low = true;
+		cur->bc_tp->t_dfops->dop_low = true;
 	}
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		*stat = 0;
@@ -293,7 +291,7 @@ xfs_bmbt_free_block(
 	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork);
-	xfs_bmap_add_free(mp, cur->bc_private.b.dfops, fsbno, 1, &oinfo);
+	xfs_bmap_add_free(mp, cur->bc_tp->t_dfops, fsbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
@@ -565,7 +563,6 @@ xfs_bmbt_init_cursor(
 	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
 	cur->bc_private.b.ip = ip;
 	cur->bc_private.b.firstblock = NULLFSBLOCK;
-	cur->bc_private.b.dfops = NULL;
 	cur->bc_private.b.allocated = 0;
 	cur->bc_private.b.flags = 0;
 	cur->bc_private.b.whichfork = whichfork;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 0a4fdf7f11a7..cc94ac765dec 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -215,7 +215,6 @@ typedef struct xfs_btree_cur
 		} a;
 		struct {			/* needed for BMAP */
 			struct xfs_inode *ip;	/* pointer to our inode */
-			struct xfs_defer_ops *dfops;	/* deferred updates */
 			xfs_fsblock_t	firstblock;	/* 1st blk allocated */
 			int		allocated;	/* count of alloced */
 			short		forksize;	/* fork's inode space */
-- 
cgit v1.2.3


From ed7ef8e55c6f24ae4347b5bda89e00af475ebc89 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:17 -0700
Subject: xfs: remove unused btree cursor bc_private.a.dfops field

The xfs_btree_cur.bc_private.a.dfops field is only ever initialized
by the refcountbt cursor init function. The only caller of that
function with a non-NULL dfops is from deferred completion context,
which already has attached to ->t_dfops.

In addition to that, the only actual reference of a.dfops is the
cursor duplication function, which means the field is effectively
unused.

Remove the dfops field from the bc_private.a union. Any future users
can acquire the dfops from the transaction. This patch does not
change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_btree.h          | 1 -
 fs/xfs/libxfs/xfs_refcount.c       | 4 ++--
 fs/xfs/libxfs/xfs_refcount_btree.c | 7 ++-----
 fs/xfs/libxfs/xfs_refcount_btree.h | 4 ++--
 fs/xfs/scrub/common.c              | 2 +-
 fs/xfs/xfs_fsmap.c                 | 2 +-
 fs/xfs/xfs_reflink.c               | 2 +-
 7 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index cc94ac765dec..b986a8fc8d40 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -209,7 +209,6 @@ typedef struct xfs_btree_cur
 	union {
 		struct {			/* needed for BNO, CNT, INO */
 			struct xfs_buf	*agbp;	/* agf/agi buffer pointer */
-			struct xfs_defer_ops *dfops;	/* deferred updates */
 			xfs_agnumber_t	agno;	/* ag number */
 			union xfs_btree_cur_private	priv;
 		} a;
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 9dda6fd0bb13..8e330a196060 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1132,7 +1132,7 @@ xfs_refcount_finish_one(
 		if (!agbp)
 			return -EFSCORRUPTED;
 
-		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, dfops);
+		rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 		if (!rcur) {
 			error = -ENOMEM;
 			goto out_cur;
@@ -1666,7 +1666,7 @@ xfs_refcount_recover_cow_leftovers(
 		error = -ENOMEM;
 		goto out_trans;
 	}
-	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 
 	/* Find all the leftover CoW staging extents. */
 	memset(&low, 0, sizeof(low));
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index b71937982c5b..393aa88f93db 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -27,8 +27,7 @@ xfs_refcountbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
 {
 	return xfs_refcountbt_init_cursor(cur->bc_mp, cur->bc_tp,
-			cur->bc_private.a.agbp, cur->bc_private.a.agno,
-			cur->bc_private.a.dfops);
+			cur->bc_private.a.agbp, cur->bc_private.a.agno);
 }
 
 STATIC void
@@ -323,8 +322,7 @@ xfs_refcountbt_init_cursor(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
 	struct xfs_buf		*agbp,
-	xfs_agnumber_t		agno,
-	struct xfs_defer_ops	*dfops)
+	xfs_agnumber_t		agno)
 {
 	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
 	struct xfs_btree_cur	*cur;
@@ -344,7 +342,6 @@ xfs_refcountbt_init_cursor(
 
 	cur->bc_private.a.agbp = agbp;
 	cur->bc_private.a.agno = agno;
-	cur->bc_private.a.dfops = dfops;
 	cur->bc_flags |= XFS_BTREE_CRC_BLOCKS;
 
 	cur->bc_private.a.priv.refc.nr_ops = 0;
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index d2852b6e1fa8..801c2c7732fd 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -44,8 +44,8 @@ struct xfs_mount;
 		 ((index) - 1) * sizeof(xfs_refcount_ptr_t)))
 
 extern struct xfs_btree_cur *xfs_refcountbt_init_cursor(struct xfs_mount *mp,
-		struct xfs_trans *tp, struct xfs_buf *agbp, xfs_agnumber_t agno,
-		struct xfs_defer_ops *dfops);
+		struct xfs_trans *tp, struct xfs_buf *agbp,
+		xfs_agnumber_t agno);
 extern int xfs_refcountbt_maxrecs(int blocklen, bool leaf);
 extern void xfs_refcountbt_compute_maxlevels(struct xfs_mount *mp);
 
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 70e70c69f83f..385fa5b9c878 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -499,7 +499,7 @@ xfs_scrub_ag_btcur_init(
 	/* Set up a refcountbt cursor for cross-referencing. */
 	if (sa->agf_bp && xfs_sb_version_hasreflink(&mp->m_sb)) {
 		sa->refc_cur = xfs_refcountbt_init_cursor(mp, sc->tp,
-				sa->agf_bp, agno, NULL);
+				sa->agf_bp, agno);
 		if (!sa->refc_cur)
 			goto err;
 	}
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index c7157bc48bd1..297d7ce2901e 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -214,7 +214,7 @@ xfs_getfsmap_is_shared(
 	/* Are there any shared blocks here? */
 	flen = 0;
 	cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp,
-			info->agno, NULL);
+			info->agno);
 
 	error = xfs_refcount_find_shared(cur, rec->rm_startblock,
 			rec->rm_blockcount, &fbno, &flen, false);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 0ac0706c98e8..90457c2a7569 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -157,7 +157,7 @@ xfs_reflink_find_shared(
 	if (!agbp)
 		return -ENOMEM;
 
-	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno);
 
 	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
 			find_end_of_shared);
-- 
cgit v1.2.3


From 7a7943c7e09546d4cc78b9756de23fd395b2cba4 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:17 -0700
Subject: xfs: use ->t_dfops for rmap extent swap operations

xfs_swap_extent_rmap() uses a local dfops instance with a
transaction from the caller. Since there is only one caller, pull
the dfops structure into the caller and attach it to the
transaction. This avoids the need to clear ->t_dfops to prevent
invalid stack memory access.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index cd5d410acc73..6bea8df348bc 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1571,6 +1571,8 @@ xfs_swap_extent_rmap(
 	struct xfs_inode		*ip,
 	struct xfs_inode		*tip)
 {
+	struct xfs_trans		*tp = *tpp;
+	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_bmbt_irec		irec;
 	struct xfs_bmbt_irec		uirec;
 	struct xfs_bmbt_irec		tirec;
@@ -1578,7 +1580,6 @@ xfs_swap_extent_rmap(
 	xfs_fileoff_t			end_fsb;
 	xfs_filblks_t			count_fsb;
 	xfs_fsblock_t			firstfsb;
-	struct xfs_defer_ops		dfops;
 	int				error;
 	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
@@ -1614,7 +1615,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			xfs_defer_init(&dfops, &firstfsb);
+			xfs_defer_init(tp->t_dfops, &firstfsb);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
@@ -1636,31 +1637,32 @@ xfs_swap_extent_rmap(
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
 
 			/* Remove the mapping from the donor file. */
-			error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
-					tip, &uirec);
+			error = xfs_bmap_unmap_extent(mp, tp->t_dfops, tip,
+					&uirec);
 			if (error)
 				goto out_defer;
 
 			/* Remove the mapping from the source file. */
-			error = xfs_bmap_unmap_extent((*tpp)->t_mountp, &dfops,
-					ip, &irec);
+			error = xfs_bmap_unmap_extent(mp, tp->t_dfops, ip,
+					&irec);
 			if (error)
 				goto out_defer;
 
 			/* Map the donor file's blocks into the source file. */
-			error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
-					ip, &uirec);
+			error = xfs_bmap_map_extent(mp, tp->t_dfops, ip,
+					&uirec);
 			if (error)
 				goto out_defer;
 
 			/* Map the source file's blocks into the donor file. */
-			error = xfs_bmap_map_extent((*tpp)->t_mountp, &dfops,
-					tip, &irec);
+			error = xfs_bmap_map_extent(mp, tp->t_dfops, tip,
+					&irec);
 			if (error)
 				goto out_defer;
 
-			xfs_defer_ijoin(&dfops, ip);
-			error = xfs_defer_finish(tpp, &dfops);
+			xfs_defer_ijoin(tp->t_dfops, ip);
+			error = xfs_defer_finish(tpp, tp->t_dfops);
+			tp = *tpp;
 			if (error)
 				goto out_defer;
 
@@ -1680,7 +1682,7 @@ xfs_swap_extent_rmap(
 	return 0;
 
 out_defer:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out:
 	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
 	tip->i_d.di_flags2 = tip_flags2;
@@ -1847,6 +1849,7 @@ xfs_swap_extents(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
+	struct xfs_defer_ops	dfops;
 	struct xfs_bstat	*sbp = &sxp->sx_stat;
 	int			src_log_flags, target_log_flags;
 	int			error = 0;
@@ -1854,6 +1857,7 @@ xfs_swap_extents(
 	struct xfs_ifork	*cowfp;
 	uint64_t		f;
 	int			resblks = 0;
+	xfs_fsblock_t		firstfsb;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
@@ -1916,6 +1920,8 @@ xfs_swap_extents(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
+	xfs_defer_init(&dfops, &firstfsb);
+	tp->t_dfops = &dfops;
 
 	/*
 	 * Lock and join the inodes to the tansaction so that transaction commit
-- 
cgit v1.2.3


From 27356a063a8572b2d3bf57d92b0a12399478958a Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:18 -0700
Subject: xfs: use ->t_dfops in cancel cow blocks operation

Use ->t_dfops of the transaction from the caller. Reset it before we
return to avoid leaks of local stack memory.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_reflink.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 90457c2a7569..8ea4ba0e45d8 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -490,6 +490,7 @@ xfs_reflink_cancel_cow_blocks(
 	struct xfs_iext_cursor		icur;
 	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
+	struct xfs_defer_ops		*odfops = (*tpp)->t_dfops;
 	int				error = 0;
 
 	if (!xfs_is_reflink_inode(ip))
@@ -517,23 +518,24 @@ xfs_reflink_cancel_cow_blocks(
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
 			xfs_defer_init(&dfops, &firstfsb);
+			(*tpp)->t_dfops = &dfops;
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
-					&dfops, del.br_startblock,
+					(*tpp)->t_dfops, del.br_startblock,
 					del.br_blockcount);
 			if (error)
 				break;
 
-			xfs_bmap_add_free(ip->i_mount, &dfops,
+			xfs_bmap_add_free(ip->i_mount, (*tpp)->t_dfops,
 					del.br_startblock, del.br_blockcount,
 					NULL);
 
 			/* Roll the transaction */
-			xfs_defer_ijoin(&dfops, ip);
-			error = xfs_defer_finish(tpp, &dfops);
+			xfs_defer_ijoin((*tpp)->t_dfops, ip);
+			error = xfs_defer_finish(tpp, (*tpp)->t_dfops);
 			if (error) {
-				xfs_defer_cancel(&dfops);
+				xfs_defer_cancel((*tpp)->t_dfops);
 				break;
 			}
 
@@ -558,7 +560,7 @@ next_extent:
 	/* clear tag if cow fork is emptied */
 	if (!ifp->if_bytes)
 		xfs_inode_clear_cowblocks_tag(ip);
-
+	(*tpp)->t_dfops = odfops;
 	return error;
 }
 
-- 
cgit v1.2.3


From d5669ed58175f85d2c13e914c5c4e2bd3647d893 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:18 -0700
Subject: xfs: use ->t_dfops in reflink cow recover path

Use ->t_dfops of the leftover COW reservation cleanup transaction.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_refcount.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 8e330a196060..df67821fb5f4 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1692,18 +1692,19 @@ xfs_refcount_recover_cow_leftovers(
 
 		/* Free the orphan record */
 		xfs_defer_init(&dfops, &fsb);
+		tp->t_dfops = &dfops;
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
-		error = xfs_refcount_free_cow_extent(mp, &dfops, fsb,
+		error = xfs_refcount_free_cow_extent(mp, tp->t_dfops, fsb,
 				rr->rr_rrec.rc_blockcount);
 		if (error)
 			goto out_defer;
 
 		/* Free the block. */
-		xfs_bmap_add_free(mp, &dfops, fsb,
+		xfs_bmap_add_free(mp, tp->t_dfops, fsb,
 				rr->rr_rrec.rc_blockcount, NULL);
 
-		error = xfs_defer_finish(&tp, &dfops);
+		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
 			goto out_defer;
 
@@ -1717,7 +1718,7 @@ xfs_refcount_recover_cow_leftovers(
 
 	return error;
 out_defer:
-	xfs_defer_cancel(&dfops);
+	xfs_defer_cancel(tp->t_dfops);
 out_trans:
 	xfs_trans_cancel(tp);
 out_free:
-- 
cgit v1.2.3


From bcd2c9f33559764e0d306e226a8aa88bc2e1e6fb Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:19 -0700
Subject: xfs: refactor dfops init to attach to transaction

Most callers of xfs_defer_init() immediately attach the dfops
structure to a transaction. Add a transaction parameter to eliminate
much of this boilerplate code. This also helps self-document the
fact that many codepaths now expect a dfops pointer implicitly via
xfs_trans->t_dfops.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 26 ++++++++++++++------------
 fs/xfs/libxfs/xfs_attr_remote.c |  6 +++---
 fs/xfs/libxfs/xfs_bmap.c        |  6 ++----
 fs/xfs/libxfs/xfs_defer.c       |  9 ++++++++-
 fs/xfs/libxfs/xfs_defer.h       |  3 ++-
 fs/xfs/libxfs/xfs_refcount.c    |  3 +--
 fs/xfs/xfs_bmap_util.c          | 17 ++++++-----------
 fs/xfs/xfs_dquot.c              |  5 ++---
 fs/xfs/xfs_inode.c              | 18 ++++++------------
 fs/xfs/xfs_iomap.c              |  9 +++------
 fs/xfs/xfs_log_recover.c        |  2 +-
 fs/xfs/xfs_reflink.c            | 12 ++++--------
 fs/xfs/xfs_rtalloc.c            |  3 +--
 fs/xfs/xfs_symlink.c            |  6 ++----
 14 files changed, 55 insertions(+), 70 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index a14ab9b2669e..8a7e2c0308c4 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -253,8 +253,7 @@ xfs_attr_set(
 			rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(&dfops, &firstblock);
-	args.trans->t_dfops = &dfops;
+	xfs_defer_init(args.trans, &dfops, &firstblock);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
@@ -428,8 +427,7 @@ xfs_attr_remove(
 			&args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(&dfops, &firstblock);
-	args.trans->t_dfops = &dfops;
+	xfs_defer_init(args.trans, &dfops, &firstblock);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	/*
@@ -600,7 +598,7 @@ xfs_attr_leaf_addname(
 		 * Commit that transaction so that the node_addname() call
 		 * can manage its own transactions.
 		 */
-		xfs_defer_init(args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
@@ -689,7 +687,8 @@ xfs_attr_leaf_addname(
 		 * If the result is small enough, shrink it all into the inode.
 		 */
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->trans->t_dfops, args->firstblock);
+			xfs_defer_init(NULL, args->trans->t_dfops,
+				       args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
@@ -754,7 +753,7 @@ xfs_attr_leaf_removename(
 	 * If the result is small enough, shrink it all into the inode.
 	 */
 	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		xfs_defer_init(args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
@@ -883,7 +882,8 @@ restart:
 			 */
 			xfs_da_state_free(state);
 			state = NULL;
-			xfs_defer_init(args->trans->t_dfops, args->firstblock);
+			xfs_defer_init(NULL, args->trans->t_dfops,
+				       args->firstblock);
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
@@ -910,7 +910,7 @@ restart:
 		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
 		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
 		 */
-		xfs_defer_init(args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
@@ -1008,7 +1008,8 @@ restart:
 		 * Check to see if the tree needs to be collapsed.
 		 */
 		if (retval && (state->path.active > 1)) {
-			xfs_defer_init(args->trans->t_dfops, args->firstblock);
+			xfs_defer_init(NULL, args->trans->t_dfops,
+				       args->firstblock);
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
@@ -1133,7 +1134,7 @@ xfs_attr_node_removename(
 	 * Check to see if the tree needs to be collapsed.
 	 */
 	if (retval && (state->path.active > 1)) {
-		xfs_defer_init(args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
@@ -1165,7 +1166,8 @@ xfs_attr_node_removename(
 			goto out;
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->trans->t_dfops, args->firstblock);
+			xfs_defer_init(NULL, args->trans->t_dfops,
+				       args->firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 179259fd1b5e..ab7c2755ad8c 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -480,7 +480,7 @@ xfs_attr_rmtval_set(
 		 * extent and then crash then the block may not contain the
 		 * correct metadata after log recovery occurs.
 		 */
-		xfs_defer_init(args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
 				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
@@ -522,7 +522,7 @@ xfs_attr_rmtval_set(
 
 		ASSERT(blkcnt > 0);
 
-		xfs_defer_init(args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
 				       blkcnt, &map, &nmap,
@@ -626,7 +626,7 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		xfs_defer_init(args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
 				    XFS_BMAPI_ATTRFORK, 1, args->firstblock,
 				    &done);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 32d8d87b7582..dfff840c79f9 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1050,8 +1050,7 @@ xfs_bmap_add_attrfork(
 			rsvd ? XFS_TRANS_RESERVE : 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(&dfops, &firstblock);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &firstblock);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
@@ -6025,8 +6024,7 @@ xfs_bmap_split_extent(
 			XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(&dfops, &firstfsb);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &firstfsb);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 560a7d178c1e..6b25a9436829 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -523,12 +523,19 @@ xfs_defer_init_op_type(
 /* Initialize a deferred operation. */
 void
 xfs_defer_init(
+	struct xfs_trans		*tp,
 	struct xfs_defer_ops		*dop,
 	xfs_fsblock_t			*fbp)
 {
+	struct xfs_mount		*mp = NULL;
+
 	memset(dop, 0, sizeof(struct xfs_defer_ops));
 	*fbp = NULLFSBLOCK;
 	INIT_LIST_HEAD(&dop->dop_intake);
 	INIT_LIST_HEAD(&dop->dop_pending);
-	trace_xfs_defer_init(NULL, dop, _RET_IP_);
+	if (tp) {
+		tp->t_dfops = dop;
+		mp = tp->t_mountp;
+	}
+	trace_xfs_defer_init(mp, dop, _RET_IP_);
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index a02b2b748b6d..56eaaac31df5 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -63,7 +63,8 @@ void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
 		struct list_head *h);
 int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop);
 void xfs_defer_cancel(struct xfs_defer_ops *dop);
-void xfs_defer_init(struct xfs_defer_ops *dop, xfs_fsblock_t *fbp);
+void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop,
+		    xfs_fsblock_t *fbp);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
 int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index df67821fb5f4..8dc380574cd8 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1691,8 +1691,7 @@ xfs_refcount_recover_cow_leftovers(
 		trace_xfs_refcount_recover_extent(mp, agno, &rr->rr_rrec);
 
 		/* Free the orphan record */
-		xfs_defer_init(&dfops, &fsb);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &fsb);
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
 		error = xfs_refcount_free_cow_extent(mp, tp->t_dfops, fsb,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 6bea8df348bc..1259e599158d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -972,8 +972,7 @@ xfs_alloc_file_space(
 
 		xfs_trans_ijoin(tp, ip, 0);
 
-		xfs_defer_init(&dfops, &firstfsb);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &firstfsb);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
 					allocatesize_fsb, alloc_type, &firstfsb,
 					resblks, imapp, &nimaps);
@@ -1043,8 +1042,7 @@ xfs_unmap_extent(
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &firstfsb);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &firstfsb);
 	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, &firstfsb,
 			    done);
 	if (error)
@@ -1347,8 +1345,7 @@ xfs_collapse_file_space(
 			goto out_trans_cancel;
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(&dfops, &first_block);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &first_block);
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
 				&done, &first_block);
 		if (error)
@@ -1427,8 +1424,7 @@ xfs_insert_file_space(
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_defer_init(&dfops, &first_block);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &first_block);
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
 				&done, stop_fsb, &first_block);
 		if (error)
@@ -1615,7 +1611,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			xfs_defer_init(tp->t_dfops, &firstfsb);
+			xfs_defer_init(tp, tp->t_dfops, &firstfsb);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
@@ -1920,8 +1916,7 @@ xfs_swap_extents(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
-	xfs_defer_init(&dfops, &firstfsb);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &firstfsb);
 
 	/*
 	 * Lock and join the inodes to the tansaction so that transaction commit
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 1ef38e1df679..c698e7f6f744 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -296,7 +296,7 @@ xfs_dquot_disk_alloc(
 
 	trace_xfs_dqalloc(dqp);
 
-	xfs_defer_init(tp->t_dfops, &firstblock);
+	xfs_defer_init(tp, tp->t_dfops, &firstblock);
 
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
@@ -549,8 +549,7 @@ xfs_qm_dqread_alloc(
 			XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
 	if (error)
 		goto err;
-	xfs_defer_init(&dfops, &firstblock);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &firstblock);
 
 	error = xfs_dquot_disk_alloc(&tp, dqp, &bp);
 	if (error)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f456df2e1394..04e17234e5d7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1195,8 +1195,7 @@ xfs_create(
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 
 	/*
 	 * Reserve disk quota and the inode.
@@ -1451,8 +1450,7 @@ xfs_link(
 			goto error_return;
 	}
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 
 	/*
 	 * Handle initial link state of O_TMPFILE inode
@@ -1584,8 +1582,7 @@ xfs_itruncate_extents_flags(
 	ASSERT(first_unmap_block < last_block);
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
-		xfs_defer_init(&dfops, &first_block);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &first_block);
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
 				    XFS_ITRUNC_MAX_EXTENTS, &first_block,
 				    &done);
@@ -1816,8 +1813,7 @@ xfs_inactive_ifree(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 	error = xfs_ifree(tp, ip);
 	if (error) {
 		/*
@@ -2661,8 +2657,7 @@ xfs_remove(
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 	error = xfs_dir_removename(tp, dp, name, ip->i_ino, &first_block,
 				   resblks);
 	if (error) {
@@ -3026,8 +3021,7 @@ xfs_rename(
 		goto out_trans_cancel;
 	}
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 0c736c938f52..777c349607b3 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -254,8 +254,7 @@ xfs_iomap_write_direct(
 	 * From this point onwards we overwrite the imap pointer that the
 	 * caller gave to us.
 	 */
-	xfs_defer_init(&dfops, &firstfsb);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &firstfsb);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 				bmapi_flags, &firstfsb, resblks, imap,
@@ -717,8 +716,7 @@ xfs_iomap_write_allocate(
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			xfs_trans_ijoin(tp, ip, 0);
 
-			xfs_defer_init(&dfops, &first_block);
-			tp->t_dfops = &dfops;
+			xfs_defer_init(tp, &dfops, &first_block);
 
 			/*
 			 * it is possible that the extents have changed since
@@ -878,8 +876,7 @@ xfs_iomap_write_unwritten(
 		/*
 		 * Modify the unwritten extent state of the buffer.
 		 */
-		xfs_defer_init(&dfops, &firstfsb);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &firstfsb);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 					XFS_BMAPI_CONVERT, &firstfsb, resblks,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b181b5f57a19..940eb30e0271 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4902,7 +4902,7 @@ xlog_recover_process_intents(
 #if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
 #endif
-	xfs_defer_init(&dfops, &firstfsb);
+	xfs_defer_init(NULL, &dfops, &firstfsb);
 	while (lip != NULL) {
 		/*
 		 * We're done when we see something other than an intent.
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 8ea4ba0e45d8..bef780171962 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -428,8 +428,7 @@ retry:
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 	nimaps = 1;
 
 	/* Allocate the entire reservation as unwritten blocks. */
@@ -517,8 +516,7 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			xfs_defer_init(&dfops, &firstfsb);
-			(*tpp)->t_dfops = &dfops;
+			xfs_defer_init(*tpp, &dfops, &firstfsb);
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
@@ -701,8 +699,7 @@ xfs_reflink_end_cow(
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */
-		xfs_defer_init(&dfops, &firstfsb);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &firstfsb);
 		rlen = del.br_blockcount;
 		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
 				&firstfsb);
@@ -1052,8 +1049,7 @@ xfs_reflink_remap_extent(
 	/* Unmap the old blocks in the data fork. */
 	rlen = unmap_len;
 	while (rlen) {
-		xfs_defer_init(&dfops, &firstfsb);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &firstfsb);
 		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1, &firstfsb);
 		if (error)
 			goto out_defer;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 1c7d1238ff3b..c102b0d26bc1 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -787,8 +787,7 @@ xfs_growfs_rt_alloc(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(&dfops, &firstblock);
-		tp->t_dfops = &dfops;
+		xfs_defer_init(tp, &dfops, &firstblock);
 		/*
 		 * Allocate blocks to the bitmap file.
 		 */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index a54f095c1409..e50e97308f81 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -246,8 +246,7 @@ xfs_symlink(
 	 * Initialize the bmap freelist prior to calling either
 	 * bmapi or the directory create code.
 	 */
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 
 	/*
 	 * Allocate an inode for the symlink.
@@ -443,8 +442,7 @@ xfs_inactive_symlink_rmt(
 	 * Find the block(s) so we can inval and unmap them.
 	 */
 	done = 0;
-	xfs_defer_init(&dfops, &first_block);
-	tp->t_dfops = &dfops;
+	xfs_defer_init(tp, &dfops, &first_block);
 	nmaps = ARRAY_SIZE(mval);
 	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
 				mval, &nmaps, 0);
-- 
cgit v1.2.3


From 3ae2d89174e4ba581093320afb48421ca95191d2 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:19 -0700
Subject: xfs: allow null firstblock in xfs_bmapi_write() when tp is null

xfs_bmapi_write() always expects a valid firstblock pointer. It
immediately dereferences the pointer to help determine how to
initialize the bma.minleft field. The remaining accesses are
related to modifying btree format forks, which is only relevant for
!COW fork callers.

The reflink code passes a NULL transaction to xfs_bmapi_write() in a
couple places that do COW fork unwritten conversion. The purpose of
the firstblock field is to track the first block allocation in the
current transaction, so technically firstblock should not be
required for these callers either.

Tweak xfs_bmapi_write() to initialize the bma correctly without
accessing the firstblock pointer if no transaction is provided in
the first place. Update the reflink callers to pass NULL instead of
otherwise unused firstblock references.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 2 +-
 fs/xfs/xfs_reflink.c     | 9 +++------
 2 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index dfff840c79f9..0b476a8e751c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4302,7 +4302,7 @@ xfs_bmapi_write(
 
 	XFS_STATS_INC(mp, xs_blk_mapw);
 
-	if (*firstblock == NULLFSBLOCK) {
+	if (!tp || *firstblock == NULLFSBLOCK) {
 		if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE)
 			bma.minleft = be16_to_cpu(ifp->if_broot->bb_level) + 1;
 		else
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index bef780171962..b1bc2eb54a14 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -314,7 +314,6 @@ xfs_reflink_convert_cow_extent(
 	xfs_fileoff_t			offset_fsb,
 	xfs_filblks_t			count_fsb)
 {
-	xfs_fsblock_t			first_block = NULLFSBLOCK;
 	int				nimaps = 1;
 
 	if (imap->br_state == XFS_EXT_NORM)
@@ -325,8 +324,8 @@ xfs_reflink_convert_cow_extent(
 	if (imap->br_blockcount == 0)
 		return 0;
 	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block,
-			0, imap, &nimaps);
+			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, NULL, 0, imap,
+			&nimaps);
 }
 
 /* Convert all of the unwritten CoW extents in a file's range to real ones. */
@@ -341,7 +340,6 @@ xfs_reflink_convert_cow(
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
 	xfs_filblks_t		count_fsb = end_fsb - offset_fsb;
 	struct xfs_bmbt_irec	imap;
-	xfs_fsblock_t		first_block = NULLFSBLOCK;
 	int			nimaps = 1, error = 0;
 
 	ASSERT(count != 0);
@@ -349,8 +347,7 @@ xfs_reflink_convert_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
-			XFS_BMAPI_CONVERT_ONLY, &first_block, 0, &imap,
-			&nimaps);
+			XFS_BMAPI_CONVERT_ONLY, NULL, 0, &imap, &nimaps);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
-- 
cgit v1.2.3


From bba59c5e4b38e160c6be25b2f4fe36ebc84f53df Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:20 -0700
Subject: xfs: add firstblock field to xfs_trans

A firstblock var is typically allocated and initialized along with
xfs_defer_ops structures and passed around independent from the
associated transaction. To facilitate combining the two, add an
optional ->t_firstblock field to xfs_trans that can be used in place
of an on-stack variable.

The firstblock value follows the lifetime of the transaction, so
initialize it on allocation and when a transaction rolls.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_trans.c | 2 ++
 fs/xfs/xfs_trans.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 630993387517..de00f79ff698 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -100,6 +100,7 @@ xfs_trans_dup(
 	ntp->t_mountp = tp->t_mountp;
 	INIT_LIST_HEAD(&ntp->t_items);
 	INIT_LIST_HEAD(&ntp->t_busy);
+	ntp->t_firstblock = NULLFSBLOCK;
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(tp->t_ticket != NULL);
@@ -273,6 +274,7 @@ xfs_trans_alloc(
 	tp->t_mountp = mp;
 	INIT_LIST_HEAD(&tp->t_items);
 	INIT_LIST_HEAD(&tp->t_busy);
+	tp->t_firstblock = NULLFSBLOCK;
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error) {
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index d8a695c57103..37fdacc690c7 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -102,6 +102,7 @@ typedef struct xfs_trans {
 	unsigned int		t_blk_res_used;	/* # of resvd blocks used */
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
+	xfs_fsblock_t		t_firstblock;	/* first block allocated */
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
-- 
cgit v1.2.3


From f16dea54b789aad464ae4f34caea9f8d81052729 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:20 -0700
Subject: xfs: use ->t_firstblock in dir ops

Callers of the xfs_dir_*() functions currently pass an on-stack
firstblock variable. While the dirops infrastructure carries a
pointer to this variable, it never rolls the transaction and so it
is safe to use ->t_firstblock instead.

Fix up the various xfs_dir_*() callers to use ->t_firstblock. Also
remove the unnecessary parameter for xfs_cross_rename().

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_inode.c   | 42 +++++++++++++++++++-----------------------
 fs/xfs/xfs_symlink.c |  9 ++++-----
 2 files changed, 23 insertions(+), 28 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 04e17234e5d7..6a3fe2d3df6c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1143,7 +1143,6 @@ xfs_create(
 	struct xfs_trans	*tp = NULL;
 	int			error;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
 	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
@@ -1195,7 +1194,7 @@ xfs_create(
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	xfs_defer_init(tp, &dfops, &first_block);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	/*
 	 * Reserve disk quota and the inode.
@@ -1224,7 +1223,7 @@ xfs_create(
 	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
 	unlock_dp_on_error = false;
 
-	error = xfs_dir_createname(tp, dp, name, ip->i_ino, &first_block,
+	error = xfs_dir_createname(tp, dp, name, ip->i_ino, &tp->t_firstblock,
 				   resblks ?
 					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
@@ -1401,7 +1400,6 @@ xfs_link(
 	xfs_trans_t		*tp;
 	int			error;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t           first_block;
 	int			resblks;
 
 	trace_xfs_link(tdp, target_name);
@@ -1450,7 +1448,7 @@ xfs_link(
 			goto error_return;
 	}
 
-	xfs_defer_init(tp, &dfops, &first_block);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	/*
 	 * Handle initial link state of O_TMPFILE inode
@@ -1462,7 +1460,7 @@ xfs_link(
 	}
 
 	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
-				   &first_block, resblks);
+				   &tp->t_firstblock, resblks);
 	if (error)
 		goto error_return;
 	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -2577,7 +2575,6 @@ xfs_remove(
 	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
 	int                     error = 0;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t           first_block;
 	uint			resblks;
 
 	trace_xfs_remove(dp, name);
@@ -2657,8 +2654,8 @@ xfs_remove(
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_defer_init(tp, &dfops, &first_block);
-	error = xfs_dir_removename(tp, dp, name, ip->i_ino, &first_block,
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino, &tp->t_firstblock,
 				   resblks);
 	if (error) {
 		ASSERT(error != -ENOENT);
@@ -2783,7 +2780,6 @@ xfs_cross_rename(
 	struct xfs_inode	*dp2,
 	struct xfs_name		*name2,
 	struct xfs_inode	*ip2,
-	xfs_fsblock_t		*first_block,
 	int			spaceres)
 {
 	int		error = 0;
@@ -2792,13 +2788,13 @@ xfs_cross_rename(
 	int		dp2_flags = 0;
 
 	/* Swap inode number for dirent in first parent */
-	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, first_block,
+	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, &tp->t_firstblock,
 				spaceres);
 	if (error)
 		goto out_trans_abort;
 
 	/* Swap inode number for dirent in second parent */
-	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, first_block,
+	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, &tp->t_firstblock,
 				spaceres);
 	if (error)
 		goto out_trans_abort;
@@ -2813,7 +2809,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
 			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
-						dp1->i_ino, first_block,
+						dp1->i_ino, &tp->t_firstblock,
 						spaceres);
 			if (error)
 				goto out_trans_abort;
@@ -2840,7 +2836,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
 			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
-						dp2->i_ino, first_block,
+						dp2->i_ino, &tp->t_firstblock,
 						spaceres);
 			if (error)
 				goto out_trans_abort;
@@ -2939,7 +2935,6 @@ xfs_rename(
 	struct xfs_mount	*mp = src_dp->i_mount;
 	struct xfs_trans	*tp;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	struct xfs_inode	*wip = NULL;		/* whiteout inode */
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
 	int			num_inodes = __XFS_SORT_INODES;
@@ -3021,13 +3016,13 @@ xfs_rename(
 		goto out_trans_cancel;
 	}
 
-	xfs_defer_init(tp, &dfops, &first_block);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
 		return xfs_cross_rename(tp, src_dp, src_name, src_ip,
 					target_dp, target_name, target_ip,
-					&first_block, spaceres);
+					spaceres);
 
 	/*
 	 * Set up the target.
@@ -3048,8 +3043,8 @@ xfs_rename(
 		 * to account for the ".." reference from the new entry.
 		 */
 		error = xfs_dir_createname(tp, target_dp, target_name,
-						src_ip->i_ino, &first_block,
-						spaceres);
+					   src_ip->i_ino, &tp->t_firstblock,
+					   spaceres);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -3088,7 +3083,8 @@ xfs_rename(
 		 * name at the destination directory, remove it first.
 		 */
 		error = xfs_dir_replace(tp, target_dp, target_name,
-					src_ip->i_ino, &first_block, spaceres);
+					src_ip->i_ino, &tp->t_firstblock,
+					spaceres);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -3122,7 +3118,7 @@ xfs_rename(
 		 * directory.
 		 */
 		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
-					target_dp->i_ino, &first_block,
+					target_dp->i_ino, &tp->t_firstblock,
 					spaceres);
 		ASSERT(error != -EEXIST);
 		if (error)
@@ -3162,10 +3158,10 @@ xfs_rename(
 	 */
 	if (wip) {
 		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
-					&first_block, spaceres);
+					&tp->t_firstblock, spaceres);
 	} else
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
-					   &first_block, spaceres);
+					   &tp->t_firstblock, spaceres);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index e50e97308f81..8ddc7f1147dc 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -164,7 +164,6 @@ xfs_symlink(
 	int			error = 0;
 	int			pathlen;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	bool                    unlock_dp_on_error = false;
 	xfs_fileoff_t		first_fsb;
 	xfs_filblks_t		fs_blocks;
@@ -246,7 +245,7 @@ xfs_symlink(
 	 * Initialize the bmap freelist prior to calling either
 	 * bmapi or the directory create code.
 	 */
-	xfs_defer_init(tp, &dfops, &first_block);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	/*
 	 * Allocate an inode for the symlink.
@@ -289,8 +288,8 @@ xfs_symlink(
 		nmaps = XFS_SYMLINK_MAPS;
 
 		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
-				  XFS_BMAPI_METADATA, &first_block, resblks,
-				  mval, &nmaps);
+				  XFS_BMAPI_METADATA, &tp->t_firstblock,
+				  resblks, mval, &nmaps);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -338,7 +337,7 @@ xfs_symlink(
 	 * Create the directory entry for the symlink.
 	 */
 	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
-				   &first_block, resblks);
+				   &tp->t_firstblock, resblks);
 	if (error)
 		goto out_bmap_cancel;
 	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-- 
cgit v1.2.3


From 381eee69f862d38bef468e91517e37fc53f60885 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:21 -0700
Subject: xfs: remove firstblock param from xfs dir ops

All callers of the xfs_dir_*() functions pass ->t_firstblock as the
firstblock parameter. Drop the parameter and access ->t_firstblock
directly.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_dir2.c | 12 ++++--------
 fs/xfs/libxfs/xfs_dir2.h |  6 +++---
 fs/xfs/xfs_inode.c       | 32 ++++++++++++--------------------
 fs/xfs/xfs_symlink.c     |  3 +--
 4 files changed, 20 insertions(+), 33 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 781dc63d305d..a3983e3eb64a 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -243,7 +243,6 @@ xfs_dir_createname(
 	struct xfs_inode	*dp,
 	struct xfs_name		*name,
 	xfs_ino_t		inum,		/* new entry inode number */
-	xfs_fsblock_t		*first,		/* bmap's firstblock */
 	xfs_extlen_t		total)		/* bmap's total block count */
 {
 	struct xfs_da_args	*args;
@@ -251,7 +250,6 @@ xfs_dir_createname(
 	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
-	ASSERT(tp->t_dfops || !first);
 
 	if (inum) {
 		rval = xfs_dir_ino_validate(tp->t_mountp, inum);
@@ -274,7 +272,7 @@ xfs_dir_createname(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
-	args->firstblock = first;
+	args->firstblock = &tp->t_firstblock;
 	args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	if (!inum)
 		args->op_flags |= XFS_DA_OP_JUSTCHECK;
@@ -420,7 +418,6 @@ xfs_dir_removename(
 	struct xfs_inode	*dp,
 	struct xfs_name		*name,
 	xfs_ino_t		ino,
-	xfs_fsblock_t		*first,		/* bmap's firstblock */
 	xfs_extlen_t		total)		/* bmap's total block count */
 {
 	struct xfs_da_args	*args;
@@ -442,7 +439,7 @@ xfs_dir_removename(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = ino;
 	args->dp = dp;
-	args->firstblock = first;
+	args->firstblock = &tp->t_firstblock;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -481,7 +478,6 @@ xfs_dir_replace(
 	struct xfs_inode	*dp,
 	struct xfs_name		*name,		/* name of entry to replace */
 	xfs_ino_t		inum,		/* new inode number */
-	xfs_fsblock_t		*first,		/* bmap's firstblock */
 	xfs_extlen_t		total)		/* bmap's total block count */
 {
 	struct xfs_da_args	*args;
@@ -506,7 +502,7 @@ xfs_dir_replace(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = inum;
 	args->dp = dp;
-	args->firstblock = first;
+	args->firstblock = &tp->t_firstblock;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -545,7 +541,7 @@ xfs_dir_canenter(
 	xfs_inode_t	*dp,
 	struct xfs_name	*name)		/* name of entry to add */
 {
-	return xfs_dir_createname(tp, dp, name, 0, NULL, 0);
+	return xfs_dir_createname(tp, dp, name, 0, 0);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index f203aebc07ed..ba5acd03de94 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -118,16 +118,16 @@ extern int xfs_dir_init(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_inode *pdp);
 extern int xfs_dir_createname(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_lookup(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t *inum,
 				struct xfs_name *ci_name);
 extern int xfs_dir_removename(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t ino,
-				xfs_fsblock_t *first, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name, xfs_ino_t inum,
-				xfs_fsblock_t *first, xfs_extlen_t tot);
+				xfs_extlen_t tot);
 extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
 				struct xfs_name *name);
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 6a3fe2d3df6c..ab1fd696500c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1223,7 +1223,7 @@ xfs_create(
 	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
 	unlock_dp_on_error = false;
 
-	error = xfs_dir_createname(tp, dp, name, ip->i_ino, &tp->t_firstblock,
+	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
 				   resblks ?
 					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
@@ -1460,7 +1460,7 @@ xfs_link(
 	}
 
 	error = xfs_dir_createname(tp, tdp, target_name, sip->i_ino,
-				   &tp->t_firstblock, resblks);
+				   resblks);
 	if (error)
 		goto error_return;
 	xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -2655,8 +2655,7 @@ xfs_remove(
 		goto out_trans_cancel;
 
 	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
-	error = xfs_dir_removename(tp, dp, name, ip->i_ino, &tp->t_firstblock,
-				   resblks);
+	error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
 	if (error) {
 		ASSERT(error != -ENOENT);
 		goto out_bmap_cancel;
@@ -2788,14 +2787,12 @@ xfs_cross_rename(
 	int		dp2_flags = 0;
 
 	/* Swap inode number for dirent in first parent */
-	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, &tp->t_firstblock,
-				spaceres);
+	error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres);
 	if (error)
 		goto out_trans_abort;
 
 	/* Swap inode number for dirent in second parent */
-	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, &tp->t_firstblock,
-				spaceres);
+	error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres);
 	if (error)
 		goto out_trans_abort;
 
@@ -2809,8 +2806,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip2)->i_mode)) {
 			error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
-						dp1->i_ino, &tp->t_firstblock,
-						spaceres);
+						dp1->i_ino, spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -2836,8 +2832,7 @@ xfs_cross_rename(
 
 		if (S_ISDIR(VFS_I(ip1)->i_mode)) {
 			error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
-						dp2->i_ino, &tp->t_firstblock,
-						spaceres);
+						dp2->i_ino, spaceres);
 			if (error)
 				goto out_trans_abort;
 
@@ -3043,8 +3038,7 @@ xfs_rename(
 		 * to account for the ".." reference from the new entry.
 		 */
 		error = xfs_dir_createname(tp, target_dp, target_name,
-					   src_ip->i_ino, &tp->t_firstblock,
-					   spaceres);
+					   src_ip->i_ino, spaceres);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -3083,8 +3077,7 @@ xfs_rename(
 		 * name at the destination directory, remove it first.
 		 */
 		error = xfs_dir_replace(tp, target_dp, target_name,
-					src_ip->i_ino, &tp->t_firstblock,
-					spaceres);
+					src_ip->i_ino, spaceres);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -3118,8 +3111,7 @@ xfs_rename(
 		 * directory.
 		 */
 		error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
-					target_dp->i_ino, &tp->t_firstblock,
-					spaceres);
+					target_dp->i_ino, spaceres);
 		ASSERT(error != -EEXIST);
 		if (error)
 			goto out_bmap_cancel;
@@ -3158,10 +3150,10 @@ xfs_rename(
 	 */
 	if (wip) {
 		error = xfs_dir_replace(tp, src_dp, src_name, wip->i_ino,
-					&tp->t_firstblock, spaceres);
+					spaceres);
 	} else
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
-					   &tp->t_firstblock, spaceres);
+					   spaceres);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 8ddc7f1147dc..583ca83353f7 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -336,8 +336,7 @@ xfs_symlink(
 	/*
 	 * Create the directory entry for the symlink.
 	 */
-	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino,
-				   &tp->t_firstblock, resblks);
+	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino, resblks);
 	if (error)
 		goto out_bmap_cancel;
 	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-- 
cgit v1.2.3


From 825d75cd8c1b53883dd8c2fe1d8833c371b08074 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:21 -0700
Subject: xfs: use ->t_firstblock in attrfork add

Note that this codepath is a user of struct xfs_da_args. Switch it
over to ->t_firstblock in preparation to remove
xfs_da_args.firstblock.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 33 +++++++++++++--------------------
 1 file changed, 13 insertions(+), 20 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 0b476a8e751c..da73c1a011d3 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -915,7 +915,6 @@ STATIC int					/* error */
 xfs_bmap_add_attrfork_btree(
 	xfs_trans_t		*tp,		/* transaction pointer */
 	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* btree cursor */
@@ -928,7 +927,7 @@ xfs_bmap_add_attrfork_btree(
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
-		cur->bc_private.b.firstblock = *firstblock;
+		cur->bc_private.b.firstblock = tp->t_firstblock;
 		error = xfs_bmbt_lookup_first(cur, &stat);
 		if (error)
 			goto error0;
@@ -940,7 +939,7 @@ xfs_bmap_add_attrfork_btree(
 			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 			return -ENOSPC;
 		}
-		*firstblock = cur->bc_private.b.firstblock;
+		tp->t_firstblock = cur->bc_private.b.firstblock;
 		cur->bc_private.b.allocated = 0;
 		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	}
@@ -957,7 +956,6 @@ STATIC int					/* error */
 xfs_bmap_add_attrfork_extents(
 	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
 	int			*flags)		/* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
@@ -966,8 +964,8 @@ xfs_bmap_add_attrfork_extents(
 	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
 		return 0;
 	cur = NULL;
-	error = xfs_bmap_extents_to_btree(tp, ip, firstblock, &cur, 0, flags,
-					  XFS_DATA_FORK);
+	error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock, &cur, 0,
+					  flags, XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
 		xfs_btree_del_cursor(cur,
@@ -989,12 +987,11 @@ xfs_bmap_add_attrfork_extents(
  */
 STATIC int					/* error */
 xfs_bmap_add_attrfork_local(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first block allocated */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode pointer */
 	int			*flags)		/* inode logging flags */
 {
-	xfs_da_args_t		dargs;		/* args for dir/attr code */
+	struct xfs_da_args	dargs;		/* args for dir/attr code */
 
 	if (ip->i_df.if_bytes <= XFS_IFORK_DSIZE(ip))
 		return 0;
@@ -1003,7 +1000,7 @@ xfs_bmap_add_attrfork_local(
 		memset(&dargs, 0, sizeof(dargs));
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
-		dargs.firstblock = firstblock;
+		dargs.firstblock = &tp->t_firstblock;
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
@@ -1011,7 +1008,7 @@ xfs_bmap_add_attrfork_local(
 	}
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
-		return xfs_bmap_local_to_extents(tp, ip, firstblock, 1,
+		return xfs_bmap_local_to_extents(tp, ip, &tp->t_firstblock, 1,
 						 flags, XFS_DATA_FORK,
 						 xfs_symlink_local_to_remote);
 
@@ -1030,7 +1027,6 @@ xfs_bmap_add_attrfork(
 	int			size,		/* space new attribute needs */
 	int			rsvd)		/* xact may use reserved blks */
 {
-	xfs_fsblock_t		firstblock;	/* 1st block/ag allocated */
 	struct xfs_defer_ops	dfops;		/* freed extent records */
 	xfs_mount_t		*mp;		/* mount structure */
 	xfs_trans_t		*tp;		/* transaction pointer */
@@ -1050,7 +1046,7 @@ xfs_bmap_add_attrfork(
 			rsvd ? XFS_TRANS_RESERVE : 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(tp, &dfops, &firstblock);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
@@ -1100,16 +1096,13 @@ xfs_bmap_add_attrfork(
 	logflags = 0;
 	switch (ip->i_d.di_format) {
 	case XFS_DINODE_FMT_LOCAL:
-		error = xfs_bmap_add_attrfork_local(tp, ip, &firstblock,
-						    &logflags);
+		error = xfs_bmap_add_attrfork_local(tp, ip, &logflags);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
-		error = xfs_bmap_add_attrfork_extents(tp, ip, &firstblock,
-						      &logflags);
+		error = xfs_bmap_add_attrfork_extents(tp, ip, &logflags);
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		error = xfs_bmap_add_attrfork_btree(tp, ip, &firstblock,
-						    &logflags);
+		error = xfs_bmap_add_attrfork_btree(tp, ip, &logflags);
 		break;
 	default:
 		error = 0;
-- 
cgit v1.2.3


From 766139032f95bb41031f6de9c2ee0538bd035229 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:22 -0700
Subject: xfs: use ->t_firstblock in xattr ops

Similar to the dirops code, the xattr code uses an on-stack
firstblock variable for the various operations. This code rolls the
underlying transaction in various places, however, which means we
cannot simply replace the local firstblock vars with ->t_firstblock.
Doing so (without further changes) would invalidate the memory
pointed to by xfs_da_args.firstblock as soon as the first
transaction rolls.

To avoid this problem, remove xfs_da_args.firstblock and replace all
such accesses with ->t_firstblock at the same time. This ensures
that accesses to the current firstblock always occur through the
current transaction rather than a potentially invalid xfs_da_args
pointer.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 37 ++++++++++++++++++-------------------
 fs/xfs/libxfs/xfs_attr_leaf.c   |  2 --
 fs/xfs/libxfs/xfs_attr_remote.c | 18 +++++++++++-------
 fs/xfs/libxfs/xfs_bmap.c        |  1 -
 fs/xfs/libxfs/xfs_da_btree.c    |  7 +++----
 fs/xfs/libxfs/xfs_da_btree.h    |  1 -
 fs/xfs/libxfs/xfs_dir2.c        |  5 +----
 7 files changed, 33 insertions(+), 38 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 8a7e2c0308c4..153d2e29f872 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -204,7 +204,6 @@ xfs_attr_set(
 	struct xfs_da_args	args;
 	struct xfs_defer_ops	dfops;
 	struct xfs_trans_res	tres;
-	xfs_fsblock_t		firstblock;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
 	int			error, err2, local;
 
@@ -219,7 +218,6 @@ xfs_attr_set(
 
 	args.value = value;
 	args.valuelen = valuelen;
-	args.firstblock = &firstblock;
 	args.op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	args.total = xfs_attr_calc_size(&args, &local);
 
@@ -253,7 +251,7 @@ xfs_attr_set(
 			rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(args.trans, &dfops, &firstblock);
+	xfs_defer_init(args.trans, &dfops, &args.trans->t_firstblock);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
@@ -392,7 +390,6 @@ xfs_attr_remove(
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_args	args;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		firstblock;
 	int			error;
 
 	XFS_STATS_INC(mp, xs_attr_remove);
@@ -404,8 +401,6 @@ xfs_attr_remove(
 	if (error)
 		return error;
 
-	args.firstblock = &firstblock;
-
 	/*
 	 * we have no control over the attribute names that userspace passes us
 	 * to remove, so we have to allow the name lookup prior to attribute
@@ -427,7 +422,7 @@ xfs_attr_remove(
 			&args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(args.trans, &dfops, &firstblock);
+	xfs_defer_init(args.trans, &dfops, &args.trans->t_firstblock);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	/*
@@ -598,7 +593,8 @@ xfs_attr_leaf_addname(
 		 * Commit that transaction so that the node_addname() call
 		 * can manage its own transactions.
 		 */
-		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops,
+			       &args->trans->t_firstblock);
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
@@ -687,8 +683,8 @@ xfs_attr_leaf_addname(
 		 * If the result is small enough, shrink it all into the inode.
 		 */
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(NULL, args->trans->t_dfops,
-				       args->firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops,
+				       &args->trans->t_firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
@@ -753,7 +749,8 @@ xfs_attr_leaf_removename(
 	 * If the result is small enough, shrink it all into the inode.
 	 */
 	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops,
+			       &args->trans->t_firstblock);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
@@ -882,8 +879,8 @@ restart:
 			 */
 			xfs_da_state_free(state);
 			state = NULL;
-			xfs_defer_init(NULL, args->trans->t_dfops,
-				       args->firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops,
+				       &args->trans->t_firstblock);
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
@@ -910,7 +907,8 @@ restart:
 		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
 		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
 		 */
-		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops,
+			       &args->trans->t_firstblock);
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
@@ -1008,8 +1006,8 @@ restart:
 		 * Check to see if the tree needs to be collapsed.
 		 */
 		if (retval && (state->path.active > 1)) {
-			xfs_defer_init(NULL, args->trans->t_dfops,
-				       args->firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops,
+				       &args->trans->t_firstblock);
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
@@ -1134,7 +1132,8 @@ xfs_attr_node_removename(
 	 * Check to see if the tree needs to be collapsed.
 	 */
 	if (retval && (state->path.active > 1)) {
-		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops,
+			       &args->trans->t_firstblock);
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
@@ -1166,8 +1165,8 @@ xfs_attr_node_removename(
 			goto out;
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(NULL, args->trans->t_dfops,
-				       args->firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops,
+				       &args->trans->t_firstblock);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index c131469db0f1..251304f3bc5d 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -802,7 +802,6 @@ xfs_attr_shortform_to_leaf(
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.dp = dp;
 	nargs.geo = args->geo;
-	nargs.firstblock = args->firstblock;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
@@ -1005,7 +1004,6 @@ xfs_attr3_leaf_to_shortform(
 	memset((char *)&nargs, 0, sizeof(nargs));
 	nargs.geo = args->geo;
 	nargs.dp = dp;
-	nargs.firstblock = args->firstblock;
 	nargs.total = args->total;
 	nargs.whichfork = XFS_ATTR_FORK;
 	nargs.trans = args->trans;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index ab7c2755ad8c..205098aeb4bc 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -480,11 +480,13 @@ xfs_attr_rmtval_set(
 		 * extent and then crash then the block may not contain the
 		 * correct metadata after log recovery occurs.
 		 */
-		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops,
+			       &args->trans->t_firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
-				  args->total, &map, &nmap);
+				  blkcnt, XFS_BMAPI_ATTRFORK,
+				  &args->trans->t_firstblock, args->total, &map,
+				  &nmap);
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, dp);
@@ -522,7 +524,8 @@ xfs_attr_rmtval_set(
 
 		ASSERT(blkcnt > 0);
 
-		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops,
+			       &args->trans->t_firstblock);
 		nmap = 1;
 		error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
 				       blkcnt, &map, &nmap,
@@ -626,10 +629,11 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		xfs_defer_init(NULL, args->trans->t_dfops, args->firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops,
+			       &args->trans->t_firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
-				    XFS_BMAPI_ATTRFORK, 1, args->firstblock,
-				    &done);
+				    XFS_BMAPI_ATTRFORK, 1,
+				    &args->trans->t_firstblock, &done);
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, args->dp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index da73c1a011d3..6f9b2cddb933 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1000,7 +1000,6 @@ xfs_bmap_add_attrfork_local(
 		memset(&dargs, 0, sizeof(dargs));
 		dargs.geo = ip->i_mount->m_dir_geo;
 		dargs.dp = ip;
-		dargs.firstblock = &tp->t_firstblock;
 		dargs.total = dargs.geo->fsbcount;
 		dargs.whichfork = XFS_DATA_FORK;
 		dargs.trans = tp;
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 68a72e3d9f53..2f2be86c10dc 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2059,10 +2059,9 @@ xfs_da_grow_inode_int(
 	 * Try mapping it in one filesystem block.
 	 */
 	nmap = 1;
-	ASSERT(args->firstblock != NULL);
 	error = xfs_bmapi_write(tp, dp, *bno, count,
 			xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
-			args->firstblock, args->total, &map, &nmap);
+			&tp->t_firstblock, args->total, &map, &nmap);
 	if (error)
 		return error;
 
@@ -2084,7 +2083,7 @@ xfs_da_grow_inode_int(
 			c = (int)(*bno + count - b);
 			error = xfs_bmapi_write(tp, dp, b, c,
 					xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
-					args->firstblock, args->total,
+					&tp->t_firstblock, args->total,
 					&mapp[mapi], &nmap);
 			if (error)
 				goto out_free_map;
@@ -2394,7 +2393,7 @@ xfs_da_shrink_inode(
 		 * the last block to the place we want to kill.
 		 */
 		error = xfs_bunmapi(tp, dp, dead_blkno, count,
-				    xfs_bmapi_aflag(w), 0, args->firstblock,
+				    xfs_bmapi_aflag(w), 0, &tp->t_firstblock,
 				    &done);
 		if (error == -ENOSPC) {
 			if (w != XFS_DATA_FORK)
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 6b8a04f3f162..59e290ef334f 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -57,7 +57,6 @@ typedef struct xfs_da_args {
 	xfs_dahash_t	hashval;	/* hash value of name */
 	xfs_ino_t	inumber;	/* input/output inode number */
 	struct xfs_inode *dp;		/* directory inode to manipulate */
-	xfs_fsblock_t	*firstblock;	/* ptr to firstblock for bmap calls */
 	struct xfs_trans *trans;	/* current trans (changes over time) */
 	xfs_extlen_t	total;		/* total blocks needed, for 1st bmap */
 	int		whichfork;	/* data or attribute fork */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index a3983e3eb64a..5db73d96b99e 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -272,7 +272,6 @@ xfs_dir_createname(
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
-	args->firstblock = &tp->t_firstblock;
 	args->op_flags = XFS_DA_OP_ADDNAME | XFS_DA_OP_OKNOENT;
 	if (!inum)
 		args->op_flags |= XFS_DA_OP_JUSTCHECK;
@@ -439,7 +438,6 @@ xfs_dir_removename(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = ino;
 	args->dp = dp;
-	args->firstblock = &tp->t_firstblock;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -502,7 +500,6 @@ xfs_dir_replace(
 	args->hashval = dp->i_mount->m_dirnameops->hashname(name);
 	args->inumber = inum;
 	args->dp = dp;
-	args->firstblock = &tp->t_firstblock;
 	args->total = total;
 	args->whichfork = XFS_DATA_FORK;
 	args->trans = tp;
@@ -660,7 +657,7 @@ xfs_dir2_shrink_inode(
 
 	/* Unmap the fsblock(s). */
 	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0,
-			    args->firstblock, &done);
+			    &tp->t_firstblock, &done);
 	if (error) {
 		/*
 		 * ENOSPC actually can happen if we're in a removename with no
-- 
cgit v1.2.3


From 650919f13182e8deeeeaeb580570afb0cdf8bd0d Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:23 -0700
Subject: xfs: use ->t_firstblock for all xfs_bmapi_write() callers

Convert all xfs_bmapi_write() users to ->t_firstblock.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c |  8 ++++----
 fs/xfs/xfs_dquot.c     |  5 ++---
 fs/xfs/xfs_iomap.c     | 20 +++++++++-----------
 fs/xfs/xfs_reflink.c   |  7 +++----
 fs/xfs/xfs_rtalloc.c   |  5 ++---
 5 files changed, 20 insertions(+), 25 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 1259e599158d..dd563f4a82e8 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -873,7 +873,6 @@ xfs_alloc_file_space(
 	xfs_filblks_t		allocatesize_fsb;
 	xfs_extlen_t		extsz, temp;
 	xfs_fileoff_t		startoffset_fsb;
-	xfs_fsblock_t		firstfsb;
 	int			nimaps;
 	int			quota_flag;
 	int			rt;
@@ -972,10 +971,11 @@ xfs_alloc_file_space(
 
 		xfs_trans_ijoin(tp, ip, 0);
 
-		xfs_defer_init(tp, &dfops, &firstfsb);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-					allocatesize_fsb, alloc_type, &firstfsb,
-					resblks, imapp, &nimaps);
+					allocatesize_fsb, alloc_type,
+					&tp->t_firstblock, resblks, imapp,
+					&nimaps);
 		if (error)
 			goto error0;
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index c698e7f6f744..2fc5e21373be 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -290,13 +290,12 @@ xfs_dquot_disk_alloc(
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_buf		*bp;
 	struct xfs_inode	*quotip = xfs_quota_inode(mp, dqp->dq_flags);
-	xfs_fsblock_t		firstblock;
 	int			nmaps = 1;
 	int			error;
 
 	trace_xfs_dqalloc(dqp);
 
-	xfs_defer_init(tp, tp->t_dfops, &firstblock);
+	xfs_defer_init(tp, tp->t_dfops, &tp->t_firstblock);
 
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
@@ -312,7 +311,7 @@ xfs_dquot_disk_alloc(
 	xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset,
 			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
-			&firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
+			&tp->t_firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
 			&map, &nmaps);
 	if (error)
 		goto error0;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 777c349607b3..a2b302ba40a8 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -152,7 +152,6 @@ xfs_iomap_write_direct(
 	xfs_fileoff_t	offset_fsb;
 	xfs_fileoff_t	last_fsb;
 	xfs_filblks_t	count_fsb, resaligned;
-	xfs_fsblock_t	firstfsb;
 	xfs_extlen_t	extsz;
 	int		nimaps;
 	int		quota_flag;
@@ -254,10 +253,10 @@ xfs_iomap_write_direct(
 	 * From this point onwards we overwrite the imap pointer that the
 	 * caller gave to us.
 	 */
-	xfs_defer_init(tp, &dfops, &firstfsb);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				bmapi_flags, &firstfsb, resblks, imap,
+				bmapi_flags, &tp->t_firstblock, resblks, imap,
 				&nimaps);
 	if (error)
 		goto out_bmap_cancel;
@@ -665,7 +664,6 @@ xfs_iomap_write_allocate(
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb, last_block;
 	xfs_fileoff_t	end_fsb, map_start_fsb;
-	xfs_fsblock_t	first_block;
 	struct xfs_defer_ops	dfops;
 	xfs_filblks_t	count_fsb;
 	xfs_trans_t	*tp;
@@ -716,7 +714,7 @@ xfs_iomap_write_allocate(
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			xfs_trans_ijoin(tp, ip, 0);
 
-			xfs_defer_init(tp, &dfops, &first_block);
+			xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 			/*
 			 * it is possible that the extents have changed since
@@ -770,8 +768,9 @@ xfs_iomap_write_allocate(
 			 * pointer that the caller gave to us.
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
-						count_fsb, flags, &first_block,
-						nres, imap, &nimaps);
+						count_fsb, flags,
+						&tp->t_firstblock, nres, imap,
+						&nimaps);
 			if (error)
 				goto trans_cancel;
 
@@ -827,7 +826,6 @@ xfs_iomap_write_unwritten(
 	xfs_fileoff_t	offset_fsb;
 	xfs_filblks_t	count_fsb;
 	xfs_filblks_t	numblks_fsb;
-	xfs_fsblock_t	firstfsb;
 	int		nimaps;
 	xfs_trans_t	*tp;
 	xfs_bmbt_irec_t imap;
@@ -876,11 +874,11 @@ xfs_iomap_write_unwritten(
 		/*
 		 * Modify the unwritten extent state of the buffer.
 		 */
-		xfs_defer_init(tp, &dfops, &firstfsb);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-					XFS_BMAPI_CONVERT, &firstfsb, resblks,
-					&imap, &nimaps);
+					XFS_BMAPI_CONVERT, &tp->t_firstblock,
+					resblks, &imap, &nimaps);
 		if (error)
 			goto error_on_bmapi_transaction;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index b1bc2eb54a14..d0397622be9f 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -366,7 +366,6 @@ xfs_reflink_allocate_cow(
 	struct xfs_bmbt_irec	got;
 	struct xfs_defer_ops	dfops;
 	struct xfs_trans	*tp = NULL;
-	xfs_fsblock_t		first_block;
 	int			nimaps, error = 0;
 	bool			trimmed;
 	xfs_filblks_t		resaligned;
@@ -425,13 +424,13 @@ retry:
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops, &first_block);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 	nimaps = 1;
 
 	/* Allocate the entire reservation as unwritten blocks. */
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block,
-			resblks, imap, &nimaps);
+			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
+			&tp->t_firstblock, resblks, imap, &nimaps);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index c102b0d26bc1..1c894ea2abca 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -761,7 +761,6 @@ xfs_growfs_rt_alloc(
 	struct xfs_buf		*bp;	/* temporary buffer for zeroing */
 	xfs_daddr_t		d;		/* disk block address */
 	int			error;		/* error return value */
-	xfs_fsblock_t		firstblock;/* first block allocated in xaction */
 	struct xfs_defer_ops	dfops;		/* list of freed blocks */
 	xfs_fsblock_t		fsbno;		/* filesystem block for bno */
 	struct xfs_bmbt_irec	map;		/* block map output */
@@ -787,13 +786,13 @@ xfs_growfs_rt_alloc(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(tp, &dfops, &firstblock);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		/*
 		 * Allocate blocks to the bitmap file.
 		 */
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
-					XFS_BMAPI_METADATA, &firstblock,
+					XFS_BMAPI_METADATA, &tp->t_firstblock,
 					resblks, &map, &nmap);
 		if (!error && nmap < 1)
 			error = -ENOSPC;
-- 
cgit v1.2.3


From 372837978d90d1c563315192196735c09623a5d6 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:23 -0700
Subject: xfs: use ->t_firstblock for all xfs_bunmapi() callers

Convert all xfs_bunmapi() callers to ->t_firstblock.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 12 ++----------
 fs/xfs/xfs_bmap_util.c   |  7 +++----
 fs/xfs/xfs_inode.c       |  5 ++---
 fs/xfs/xfs_reflink.c     | 11 +++++------
 fs/xfs/xfs_symlink.c     |  6 +++---
 5 files changed, 15 insertions(+), 26 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 6f9b2cddb933..572c8d0c40db 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6132,17 +6132,9 @@ xfs_bmap_finish_one(
 	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
-	xfs_fsblock_t			firstfsb;
 	int				error = 0;
 
-	/*
-	 * firstfsb is tied to the transaction lifetime and is used to
-	 * ensure correct AG locking order and schedule work item
-	 * continuations.  XFS_BUI_MAX_FAST_EXTENTS (== 1) restricts us
-	 * to only making one bmap call per transaction, so it should
-	 * be safe to have it as a local variable here.
-	 */
-	firstfsb = NULLFSBLOCK;
+	ASSERT(tp->t_firstblock == NULLFSBLOCK);
 
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
@@ -6165,7 +6157,7 @@ xfs_bmap_finish_one(
 		break;
 	case XFS_BMAP_UNMAP:
 		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
-				XFS_BMAPI_REMAP, 1, &firstfsb);
+				XFS_BMAPI_REMAP, 1, &tp->t_firstblock);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index dd563f4a82e8..0b2b52854061 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1024,7 +1024,6 @@ xfs_unmap_extent(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		firstfsb;
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
 	int			error;
 
@@ -1042,9 +1041,9 @@ xfs_unmap_extent(
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops, &firstfsb);
-	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, &firstfsb,
-			    done);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2,
+			    &tp->t_firstblock, done);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index ab1fd696500c..3cdfd795a50c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1543,7 +1543,6 @@ xfs_itruncate_extents_flags(
 	struct xfs_trans	*tp = *tpp;
 	struct xfs_defer_ops	*odfops = tp->t_dfops;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		first_unmap_block;
 	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
@@ -1580,9 +1579,9 @@ xfs_itruncate_extents_flags(
 	ASSERT(first_unmap_block < last_block);
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
-		xfs_defer_init(tp, &dfops, &first_block);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &first_block,
+				    XFS_ITRUNC_MAX_EXTENTS, &tp->t_firstblock,
 				    &done);
 		if (error)
 			goto out_bmap_cancel;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index d0397622be9f..83c02f6b1d02 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -627,7 +627,6 @@ xfs_reflink_end_cow(
 	struct xfs_trans		*tp;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
-	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
 	int				error;
 	unsigned int			resblks;
@@ -695,10 +694,10 @@ xfs_reflink_end_cow(
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */
-		xfs_defer_init(tp, &dfops, &firstfsb);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		rlen = del.br_blockcount;
 		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
-				&firstfsb);
+				&tp->t_firstblock);
 		if (error)
 			goto out_defer;
 
@@ -1002,7 +1001,6 @@ xfs_reflink_remap_extent(
 	struct xfs_mount	*mp = ip->i_mount;
 	bool			real_extent = xfs_bmap_is_real_extent(irec);
 	struct xfs_trans	*tp;
-	xfs_fsblock_t		firstfsb;
 	unsigned int		resblks;
 	struct xfs_defer_ops	dfops;
 	struct xfs_bmbt_irec	uirec;
@@ -1045,8 +1043,9 @@ xfs_reflink_remap_extent(
 	/* Unmap the old blocks in the data fork. */
 	rlen = unmap_len;
 	while (rlen) {
-		xfs_defer_init(tp, &dfops, &firstfsb);
-		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1, &firstfsb);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
+				      &tp->t_firstblock);
 		if (error)
 			goto out_defer;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 583ca83353f7..18d9b4d301e5 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -400,7 +400,6 @@ xfs_inactive_symlink_rmt(
 	xfs_buf_t	*bp;
 	int		done;
 	int		error;
-	xfs_fsblock_t	first_block;
 	struct xfs_defer_ops	dfops;
 	int		i;
 	xfs_mount_t	*mp;
@@ -440,7 +439,7 @@ xfs_inactive_symlink_rmt(
 	 * Find the block(s) so we can inval and unmap them.
 	 */
 	done = 0;
-	xfs_defer_init(tp, &dfops, &first_block);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 	nmaps = ARRAY_SIZE(mval);
 	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
 				mval, &nmaps, 0);
@@ -462,7 +461,8 @@ xfs_inactive_symlink_rmt(
 	/*
 	 * Unmap the dead block(s) to the dfops.
 	 */
-	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &first_block, &done);
+	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &tp->t_firstblock,
+			    &done);
 	if (error)
 		goto error_bmap_cancel;
 	ASSERT(done);
-- 
cgit v1.2.3


From 580c4ff9484ac3395ad48b1118b269a6d68c9318 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:24 -0700
Subject: xfs: use ->t_firstblock in xfs_bmapi_remap()

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 572c8d0c40db..e37e1319d733 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4501,7 +4501,6 @@ xfs_bmapi_remap(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
 	struct xfs_btree_cur	*cur = NULL;
-	xfs_fsblock_t		firstblock = NULLFSBLOCK;
 	struct xfs_bmbt_irec	got;
 	struct xfs_iext_cursor	icur;
 	int			whichfork = xfs_bmapi_whichfork(flags);
@@ -4544,7 +4543,7 @@ xfs_bmapi_remap(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = firstblock;
+		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -4557,7 +4556,7 @@ xfs_bmapi_remap(
 		got.br_state = XFS_EXT_NORM;
 
 	error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
-			&cur, &got, &firstblock, &logflags, flags);
+			&cur, &got, &tp->t_firstblock, &logflags, flags);
 	if (error)
 		goto error0;
 
-- 
cgit v1.2.3


From d0a9d795729945fc7eea77387af7780a5a0ec4c5 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:24 -0700
Subject: xfs: use ->t_firstblock in insert/collapse range

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 0b2b52854061..d98f6e3065db 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1311,7 +1311,6 @@ xfs_collapse_file_space(
 	struct xfs_trans	*tp;
 	int			error;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		next_fsb = XFS_B_TO_FSB(mp, offset + len);
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
@@ -1344,9 +1343,9 @@ xfs_collapse_file_space(
 			goto out_trans_cancel;
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(tp, &dfops, &first_block);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, &first_block);
+				&done, &tp->t_firstblock);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1387,7 +1386,6 @@ xfs_insert_file_space(
 	struct xfs_trans	*tp;
 	int			error;
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	xfs_fileoff_t		stop_fsb = XFS_B_TO_FSB(mp, offset);
 	xfs_fileoff_t		next_fsb = NULLFSBLOCK;
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
@@ -1423,9 +1421,9 @@ xfs_insert_file_space(
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_defer_init(tp, &dfops, &first_block);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, stop_fsb, &first_block);
+				&done, stop_fsb, &tp->t_firstblock);
 		if (error)
 			goto out_bmap_cancel;
 
-- 
cgit v1.2.3


From a7beabeae221db2118a51f6948239d63b84499ca Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:25 -0700
Subject: xfs: remove xfs_bmapi_write() firstblock param

All callers pass ->t_firstblock from the current transaction.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_remote.c |  3 +--
 fs/xfs/libxfs/xfs_bmap.c        | 18 +++++-------------
 fs/xfs/libxfs/xfs_bmap.h        |  3 +--
 fs/xfs/libxfs/xfs_da_btree.c    |  5 ++---
 fs/xfs/xfs_bmap_util.c          |  5 ++---
 fs/xfs/xfs_dquot.c              |  3 +--
 fs/xfs/xfs_iomap.c              | 10 ++++------
 fs/xfs/xfs_reflink.c            |  6 +++---
 fs/xfs/xfs_rtalloc.c            |  4 ++--
 fs/xfs/xfs_symlink.c            |  3 +--
 10 files changed, 22 insertions(+), 38 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 205098aeb4bc..2db9ef186e05 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -484,8 +484,7 @@ xfs_attr_rmtval_set(
 			       &args->trans->t_firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt, XFS_BMAPI_ATTRFORK,
-				  &args->trans->t_firstblock, args->total, &map,
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
 				  &nmap);
 		if (error)
 			goto out_defer_cancel;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index e37e1319d733..ca30e972288a 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4212,12 +4212,6 @@ xfs_bmapi_convert_unwritten(
  * extent state if necessary.  Details behaviour is controlled by the flags
  * parameter.  Only allocates blocks from a single allocation group, to avoid
  * locking problems.
- *
- * The returned value in "firstblock" from the first call in a transaction
- * must be remembered and presented to subsequent calls in "firstblock".
- * An upper bound for the number of blocks to be allocated is supplied to
- * the first call in "total"; if no allocation group has that many free
- * blocks then the call will fail (return NULLFSBLOCK in "firstblock").
  */
 int
 xfs_bmapi_write(
@@ -4226,8 +4220,6 @@ xfs_bmapi_write(
 	xfs_fileoff_t		bno,		/* starting file offs. mapped */
 	xfs_filblks_t		len,		/* length to map in file */
 	int			flags,		/* XFS_BMAPI_... */
-	xfs_fsblock_t		*firstblock,	/* first allocated block
-						   controls a.g. for allocs */
 	xfs_extlen_t		total,		/* total blocks needed */
 	struct xfs_bmbt_irec	*mval,		/* output: map values */
 	int			*nmap)		/* i/o: mval size/count */
@@ -4294,7 +4286,7 @@ xfs_bmapi_write(
 
 	XFS_STATS_INC(mp, xs_blk_mapw);
 
-	if (!tp || *firstblock == NULLFSBLOCK) {
+	if (!tp || tp->t_firstblock == NULLFSBLOCK) {
 		if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE)
 			bma.minleft = be16_to_cpu(ifp->if_broot->bb_level) + 1;
 		else
@@ -4321,7 +4313,7 @@ xfs_bmapi_write(
 	bma.ip = ip;
 	bma.total = total;
 	bma.datatype = 0;
-	bma.firstblock = firstblock;
+	bma.firstblock = &tp->t_firstblock;
 	ASSERT(!tp || tp->t_dfops);
 
 	while (bno < end && n < *nmap) {
@@ -4474,11 +4466,11 @@ error0:
 
 	if (bma.cur) {
 		if (!error) {
-			ASSERT(*firstblock == NULLFSBLOCK ||
-			       XFS_FSB_TO_AGNO(mp, *firstblock) <=
+			ASSERT(tp->t_firstblock == NULLFSBLOCK ||
+			       XFS_FSB_TO_AGNO(mp, tp->t_firstblock) <=
 			       XFS_FSB_TO_AGNO(mp,
 				       bma.cur->bc_private.b.firstblock));
-			*firstblock = bma.cur->bc_private.b.firstblock;
+			tp->t_firstblock = bma.cur->bc_private.b.firstblock;
 		}
 		xfs_btree_del_cursor(bma.cur,
 			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 83180c7cf3ee..88c2b5dc499e 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -201,8 +201,7 @@ int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 		int *nmap, int flags);
 int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
-		xfs_fsblock_t *firstblock, xfs_extlen_t total,
-		struct xfs_bmbt_irec *mval, int *nmap);
+		xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
 int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
 		xfs_extnum_t nexts, xfs_fsblock_t *firstblock);
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 2f2be86c10dc..fe4a192696ae 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2061,7 +2061,7 @@ xfs_da_grow_inode_int(
 	nmap = 1;
 	error = xfs_bmapi_write(tp, dp, *bno, count,
 			xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA|XFS_BMAPI_CONTIG,
-			&tp->t_firstblock, args->total, &map, &nmap);
+			args->total, &map, &nmap);
 	if (error)
 		return error;
 
@@ -2083,8 +2083,7 @@ xfs_da_grow_inode_int(
 			c = (int)(*bno + count - b);
 			error = xfs_bmapi_write(tp, dp, b, c,
 					xfs_bmapi_aflag(w)|XFS_BMAPI_METADATA,
-					&tp->t_firstblock, args->total,
-					&mapp[mapi], &nmap);
+					args->total, &mapp[mapi], &nmap);
 			if (error)
 				goto out_free_map;
 			if (nmap < 1)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d98f6e3065db..4f4b1d3fb898 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -973,9 +973,8 @@ xfs_alloc_file_space(
 
 		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-					allocatesize_fsb, alloc_type,
-					&tp->t_firstblock, resblks, imapp,
-					&nimaps);
+					allocatesize_fsb, alloc_type, resblks,
+					imapp, &nimaps);
 		if (error)
 			goto error0;
 
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 2fc5e21373be..84359eeb20f4 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -311,8 +311,7 @@ xfs_dquot_disk_alloc(
 	xfs_trans_ijoin(tp, quotip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(tp, quotip, dqp->q_fileoffset,
 			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
-			&tp->t_firstblock, XFS_QM_DQALLOC_SPACE_RES(mp),
-			&map, &nmaps);
+			XFS_QM_DQALLOC_SPACE_RES(mp), &map, &nmaps);
 	if (error)
 		goto error0;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index a2b302ba40a8..0ae822538a63 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -256,8 +256,7 @@ xfs_iomap_write_direct(
 	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				bmapi_flags, &tp->t_firstblock, resblks, imap,
-				&nimaps);
+				bmapi_flags, resblks, imap, &nimaps);
 	if (error)
 		goto out_bmap_cancel;
 
@@ -768,8 +767,7 @@ xfs_iomap_write_allocate(
 			 * pointer that the caller gave to us.
 			 */
 			error = xfs_bmapi_write(tp, ip, map_start_fsb,
-						count_fsb, flags,
-						&tp->t_firstblock, nres, imap,
+						count_fsb, flags, nres, imap,
 						&nimaps);
 			if (error)
 				goto trans_cancel;
@@ -877,8 +875,8 @@ xfs_iomap_write_unwritten(
 		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-					XFS_BMAPI_CONVERT, &tp->t_firstblock,
-					resblks, &imap, &nimaps);
+					XFS_BMAPI_CONVERT, resblks, &imap,
+					&nimaps);
 		if (error)
 			goto error_on_bmapi_transaction;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 83c02f6b1d02..7010f3453c29 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -324,7 +324,7 @@ xfs_reflink_convert_cow_extent(
 	if (imap->br_blockcount == 0)
 		return 0;
 	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
-			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, NULL, 0, imap,
+			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, 0, imap,
 			&nimaps);
 }
 
@@ -347,7 +347,7 @@ xfs_reflink_convert_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_bmapi_write(NULL, ip, offset_fsb, count_fsb,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT |
-			XFS_BMAPI_CONVERT_ONLY, NULL, 0, &imap, &nimaps);
+			XFS_BMAPI_CONVERT_ONLY, 0, &imap, &nimaps);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }
@@ -430,7 +430,7 @@ retry:
 	/* Allocate the entire reservation as unwritten blocks. */
 	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
-			&tp->t_firstblock, resblks, imap, &nimaps);
+			resblks, imap, &nimaps);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 1c894ea2abca..edd949376a51 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -792,8 +792,8 @@ xfs_growfs_rt_alloc(
 		 */
 		nmap = 1;
 		error = xfs_bmapi_write(tp, ip, oblocks, nblocks - oblocks,
-					XFS_BMAPI_METADATA, &tp->t_firstblock,
-					resblks, &map, &nmap);
+					XFS_BMAPI_METADATA, resblks, &map,
+					&nmap);
 		if (!error && nmap < 1)
 			error = -ENOSPC;
 		if (error)
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 18d9b4d301e5..94301b63525f 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -288,8 +288,7 @@ xfs_symlink(
 		nmaps = XFS_SYMLINK_MAPS;
 
 		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
-				  XFS_BMAPI_METADATA, &tp->t_firstblock,
-				  resblks, mval, &nmaps);
+				  XFS_BMAPI_METADATA, resblks, mval, &nmaps);
 		if (error)
 			goto out_bmap_cancel;
 
-- 
cgit v1.2.3


From 2af528425342dc8f696b28693c5e61587cd72b43 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:25 -0700
Subject: xfs: remove xfs_bunmapi() firstblock param

All callers pass ->t_firstblock from the current transaction.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_remote.c |  3 +--
 fs/xfs/libxfs/xfs_bmap.c        | 25 ++++++++++++-------------
 fs/xfs/libxfs/xfs_bmap.h        |  5 ++---
 fs/xfs/libxfs/xfs_da_btree.c    |  3 +--
 fs/xfs/libxfs/xfs_dir2.c        |  3 +--
 fs/xfs/xfs_bmap_util.c          |  3 +--
 fs/xfs/xfs_inode.c              |  3 +--
 fs/xfs/xfs_reflink.c            |  6 ++----
 fs/xfs/xfs_symlink.c            |  3 +--
 9 files changed, 22 insertions(+), 32 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 2db9ef186e05..f02c705965ff 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -631,8 +631,7 @@ xfs_attr_rmtval_remove(
 		xfs_defer_init(args->trans, args->trans->t_dfops,
 			       &args->trans->t_firstblock);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
-				    XFS_BMAPI_ATTRFORK, 1,
-				    &args->trans->t_firstblock, &done);
+				    XFS_BMAPI_ATTRFORK, 1, &done);
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, args->dp);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index ca30e972288a..619d3adc5923 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5122,9 +5122,7 @@ __xfs_bunmapi(
 	xfs_fileoff_t		start,		/* first file offset deleted */
 	xfs_filblks_t		*rlen,		/* i/o: amount remaining */
 	int			flags,		/* misc flags */
-	xfs_extnum_t		nexts,		/* number of extents max */
-	xfs_fsblock_t		*firstblock)	/* first allocated block
-						   controls a.g. for allocs */
+	xfs_extnum_t		nexts)		/* number of extents max */
 {
 	struct xfs_btree_cur	*cur;		/* bmap btree cursor */
 	struct xfs_bmbt_irec	del;		/* extent being deleted */
@@ -5198,7 +5196,7 @@ __xfs_bunmapi(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
+		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
@@ -5314,7 +5312,7 @@ __xfs_bunmapi(
 			del.br_state = XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent_unwritten_real(tp, ip,
 					whichfork, &icur, &cur, &del,
-					firstblock, &logflags);
+					&tp->t_firstblock, &logflags);
 			if (error)
 				goto error0;
 			goto nodelete;
@@ -5371,7 +5369,8 @@ __xfs_bunmapi(
 				prev.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&prev, firstblock, &logflags);
+						&prev, &tp->t_firstblock,
+						&logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5380,7 +5379,8 @@ __xfs_bunmapi(
 				del.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&del, firstblock, &logflags);
+						&del, &tp->t_firstblock,
+						&logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5427,8 +5427,8 @@ nodelete:
 	 */
 	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstblock, &cur, 0,
-				&tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
+				&cur, 0, &tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
@@ -5467,7 +5467,7 @@ error0:
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (cur) {
 		if (!error) {
-			*firstblock = cur->bc_private.b.firstblock;
+			tp->t_firstblock = cur->bc_private.b.firstblock;
 			cur->bc_private.b.allocated = 0;
 		}
 		xfs_btree_del_cursor(cur,
@@ -5485,12 +5485,11 @@ xfs_bunmapi(
 	xfs_filblks_t		len,
 	int			flags,
 	xfs_extnum_t		nexts,
-	xfs_fsblock_t		*firstblock,
 	int			*done)
 {
 	int			error;
 
-	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts, firstblock);
+	error = __xfs_bunmapi(tp, ip, bno, &len, flags, nexts);
 	*done = (len == 0);
 	return error;
 }
@@ -6148,7 +6147,7 @@ xfs_bmap_finish_one(
 		break;
 	case XFS_BMAP_UNMAP:
 		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
-				XFS_BMAPI_REMAP, 1, &tp->t_firstblock);
+				XFS_BMAPI_REMAP, 1);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 88c2b5dc499e..108a3073d658 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -204,11 +204,10 @@ int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
 int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
-		xfs_extnum_t nexts, xfs_fsblock_t *firstblock);
+		xfs_extnum_t nexts);
 int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
-		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
-		int *done);
+		xfs_extnum_t nexts, int *done);
 int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
 		struct xfs_bmbt_irec *del);
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index fe4a192696ae..9efbd2038ffb 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -2392,8 +2392,7 @@ xfs_da_shrink_inode(
 		 * the last block to the place we want to kill.
 		 */
 		error = xfs_bunmapi(tp, dp, dead_blkno, count,
-				    xfs_bmapi_aflag(w), 0, &tp->t_firstblock,
-				    &done);
+				    xfs_bmapi_aflag(w), 0, &done);
 		if (error == -ENOSPC) {
 			if (w != XFS_DATA_FORK)
 				break;
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 5db73d96b99e..4ea1fddb126f 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -656,8 +656,7 @@ xfs_dir2_shrink_inode(
 	da = xfs_dir2_db_to_da(args->geo, db);
 
 	/* Unmap the fsblock(s). */
-	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0,
-			    &tp->t_firstblock, &done);
+	error = xfs_bunmapi(tp, dp, da, args->geo->fsbcount, 0, 0, &done);
 	if (error) {
 		/*
 		 * ENOSPC actually can happen if we're in a removename with no
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 4f4b1d3fb898..f225707c89be 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1041,8 +1041,7 @@ xfs_unmap_extent(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
-	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2,
-			    &tp->t_firstblock, done);
+	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done);
 	if (error)
 		goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 3cdfd795a50c..5e1eaa26435c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1581,8 +1581,7 @@ xfs_itruncate_extents_flags(
 	while (!done) {
 		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &tp->t_firstblock,
-				    &done);
+				    XFS_ITRUNC_MAX_EXTENTS, &done);
 		if (error)
 			goto out_bmap_cancel;
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 7010f3453c29..2972efeee5cc 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -696,8 +696,7 @@ xfs_reflink_end_cow(
 		/* Unmap the old blocks in the data fork. */
 		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		rlen = del.br_blockcount;
-		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
-				&tp->t_firstblock);
+		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
 		if (error)
 			goto out_defer;
 
@@ -1044,8 +1043,7 @@ xfs_reflink_remap_extent(
 	rlen = unmap_len;
 	while (rlen) {
 		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
-		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1,
-				      &tp->t_firstblock);
+		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
 		if (error)
 			goto out_defer;
 
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 94301b63525f..a3dc552a5b97 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -460,8 +460,7 @@ xfs_inactive_symlink_rmt(
 	/*
 	 * Unmap the dead block(s) to the dfops.
 	 */
-	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &tp->t_firstblock,
-			    &done);
+	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &done);
 	if (error)
 		goto error_bmap_cancel;
 	ASSERT(done);
-- 
cgit v1.2.3


From 333f950c89a17018f812eae13daaa2a404c413c1 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:27 -0700
Subject: xfs: remove bmap insert/collapse firstblock param

The only callers pass ->t_firstblock.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 10 ++++------
 fs/xfs/libxfs/xfs_bmap.h |  4 ++--
 fs/xfs/xfs_bmap_util.c   |  4 ++--
 3 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 619d3adc5923..5b4bee4645df 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5652,8 +5652,7 @@ xfs_bmap_collapse_extents(
 	struct xfs_inode	*ip,
 	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
-	bool			*done,
-	xfs_fsblock_t		*firstblock)
+	bool			*done)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5686,7 +5685,7 @@ xfs_bmap_collapse_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
+		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5773,8 +5772,7 @@ xfs_bmap_insert_extents(
 	xfs_fileoff_t		*next_fsb,
 	xfs_fileoff_t		offset_shift_fsb,
 	bool			*done,
-	xfs_fileoff_t		stop_fsb,
-	xfs_fsblock_t		*firstblock)
+	xfs_fileoff_t		stop_fsb)
 {
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5807,7 +5805,7 @@ xfs_bmap_insert_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
+		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	}
 
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 108a3073d658..3cad9c3e3bda 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -217,12 +217,12 @@ void	xfs_bmap_del_extent_cow(struct xfs_inode *ip,
 uint	xfs_default_attroffset(struct xfs_inode *ip);
 int	xfs_bmap_collapse_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fsblock_t *firstblock);
+		bool *done);
 int	xfs_bmap_can_insert_extents(struct xfs_inode *ip, xfs_fileoff_t off,
 		xfs_fileoff_t shift);
 int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
-		bool *done, xfs_fileoff_t stop_fsb, xfs_fsblock_t *firstblock);
+		bool *done, xfs_fileoff_t stop_fsb);
 int	xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
 int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index f225707c89be..e9907bbe9529 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1343,7 +1343,7 @@ xfs_collapse_file_space(
 
 		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, &tp->t_firstblock);
+				&done);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1421,7 +1421,7 @@ xfs_insert_file_space(
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
-				&done, stop_fsb, &tp->t_firstblock);
+				&done, stop_fsb);
 		if (error)
 			goto out_bmap_cancel;
 
-- 
cgit v1.2.3


From 4b77a088d781b53d263c37e75222439297b410e5 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:27 -0700
Subject: xfs: use ->t_firstblock in bmap extent split

Also remove the unnecessary xfs_bmap_split_extent_at() parameter.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 5b4bee4645df..6e8254599fab 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -5878,8 +5878,7 @@ STATIC int
 xfs_bmap_split_extent_at(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		split_fsb,
-	xfs_fsblock_t		*firstfsb)
+	xfs_fileoff_t		split_fsb)
 {
 	int				whichfork = XFS_DATA_FORK;
 	struct xfs_btree_cur		*cur = NULL;
@@ -5928,7 +5927,7 @@ xfs_bmap_split_extent_at(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstfsb;
+		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
@@ -5972,8 +5971,8 @@ xfs_bmap_split_extent_at(
 		int tmp_logflags; /* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, firstfsb, &cur, 0,
-				&tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
+				&cur, 0, &tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
 
@@ -5997,20 +5996,18 @@ xfs_bmap_split_extent(
 	struct xfs_mount        *mp = ip->i_mount;
 	struct xfs_trans        *tp;
 	struct xfs_defer_ops    dfops;
-	xfs_fsblock_t           firstfsb;
 	int                     error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
 			XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(tp, &dfops, &firstfsb);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-	error = xfs_bmap_split_extent_at(tp, ip, split_fsb,
-					 &firstfsb);
+	error = xfs_bmap_split_extent_at(tp, ip, split_fsb);
 	if (error)
 		goto out;
 
-- 
cgit v1.2.3


From 94c07b4dba01481740ce893d05a71578150b8f0b Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:28 -0700
Subject: xfs: remove xfs_bmalloca firstblock field

The xfs_bmalloca.firstblock field carries the firstblock value from
the transaction into the bmap infrastructure. It's initialized in
one place from ->t_firstblock, so drop the field and access
->t_firstblock directly throughout the bmap code.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 44 +++++++++++++++++++++++---------------------
 fs/xfs/libxfs/xfs_bmap.h |  1 -
 2 files changed, 23 insertions(+), 22 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 6e8254599fab..815600d39b03 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1794,7 +1794,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, &bma->cur, 1,
+					&bma->tp->t_firstblock, &bma->cur, 1,
 					&tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -1872,7 +1872,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, &bma->cur, 1, &tmp_rval,
+				&bma->tp->t_firstblock, &bma->cur, 1, &tmp_rval,
 				whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -1953,7 +1953,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					bma->firstblock, &bma->cur, 1,
+					&bma->tp->t_firstblock, &bma->cur, 1,
 					&tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
@@ -1991,7 +1991,7 @@ xfs_bmap_add_extent_delay_real(
 
 		ASSERT(bma->cur == NULL);
 		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, &bma->cur, da_old > 0,
+				&bma->tp->t_firstblock, &bma->cur, da_old > 0,
 				&tmp_logflags, whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
@@ -3056,10 +3056,11 @@ xfs_bmap_adjacent(
 		XFS_FSB_TO_AGBNO(mp, x) < mp->m_sb.sb_agblocks)
 
 	mp = ap->ip->i_mount;
-	nullfb = *ap->firstblock == NULLFSBLOCK;
+	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
 	rt = XFS_IS_REALTIME_INODE(ap->ip) &&
 		xfs_alloc_is_userdata(ap->datatype);
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
+	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
+							ap->tp->t_firstblock);
 	/*
 	 * If allocating at eof, and there's a previous real block,
 	 * try to use its last block as our starting point.
@@ -3417,8 +3418,9 @@ xfs_bmap_btalloc(
 	}
 
 
-	nullfb = *ap->firstblock == NULLFSBLOCK;
-	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, *ap->firstblock);
+	nullfb = ap->tp->t_firstblock == NULLFSBLOCK;
+	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
+							ap->tp->t_firstblock);
 	if (nullfb) {
 		if (xfs_alloc_is_userdata(ap->datatype) &&
 		    xfs_inode_is_filestream(ap->ip)) {
@@ -3429,7 +3431,7 @@ xfs_bmap_btalloc(
 			ap->blkno = XFS_INO_TO_FSB(mp, ap->ip->i_ino);
 		}
 	} else
-		ap->blkno = *ap->firstblock;
+		ap->blkno = ap->tp->t_firstblock;
 
 	xfs_bmap_adjacent(ap);
 
@@ -3440,7 +3442,7 @@ xfs_bmap_btalloc(
 	if (nullfb || XFS_FSB_TO_AGNO(mp, ap->blkno) == fb_agno)
 		;
 	else
-		ap->blkno = *ap->firstblock;
+		ap->blkno = ap->tp->t_firstblock;
 	/*
 	 * Normal allocation, done through xfs_alloc_vextent.
 	 */
@@ -3453,7 +3455,7 @@ xfs_bmap_btalloc(
 
 	/* Trim the allocation back to the maximum an AG can fit. */
 	args.maxlen = min(ap->length, mp->m_ag_max_usable);
-	args.firstblock = *ap->firstblock;
+	args.firstblock = ap->tp->t_firstblock;
 	blen = 0;
 	if (nullfb) {
 		/*
@@ -3602,13 +3604,13 @@ xfs_bmap_btalloc(
 		 * check the allocation happened at the same or higher AG than
 		 * the first block that was allocated.
 		 */
-		ASSERT(*ap->firstblock == NULLFSBLOCK ||
-		       XFS_FSB_TO_AGNO(mp, *ap->firstblock) <=
+		ASSERT(ap->tp->t_firstblock == NULLFSBLOCK ||
+		       XFS_FSB_TO_AGNO(mp, ap->tp->t_firstblock) <=
 		       XFS_FSB_TO_AGNO(mp, args.fsbno));
 
 		ap->blkno = args.fsbno;
-		if (*ap->firstblock == NULLFSBLOCK)
-			*ap->firstblock = args.fsbno;
+		if (ap->tp->t_firstblock == NULLFSBLOCK)
+			ap->tp->t_firstblock = args.fsbno;
 		ASSERT(nullfb || fb_agno <= args.agno);
 		ap->length = args.len;
 		/*
@@ -4064,12 +4066,12 @@ xfs_bmapi_allocate(
 		return error;
 
 	if (bma->cur)
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
+		bma->cur->bc_private.b.firstblock = bma->tp->t_firstblock;
 	if (bma->blkno == NULLFSBLOCK)
 		return 0;
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
+		bma->cur->bc_private.b.firstblock = bma->tp->t_firstblock;
 	}
 	/*
 	 * Bump the number of extents we've allocated
@@ -4105,7 +4107,8 @@ xfs_bmapi_allocate(
 	else
 		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
 				whichfork, &bma->icur, &bma->cur, &bma->got,
-				bma->firstblock, &bma->logflags, bma->flags);
+				&bma->tp->t_firstblock, &bma->logflags,
+				bma->flags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4156,7 +4159,7 @@ xfs_bmapi_convert_unwritten(
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = *bma->firstblock;
+		bma->cur->bc_private.b.firstblock = bma->tp->t_firstblock;
 	}
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
@@ -4173,7 +4176,7 @@ xfs_bmapi_convert_unwritten(
 	}
 
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork,
-			&bma->icur, &bma->cur, mval, bma->firstblock,
+			&bma->icur, &bma->cur, mval, &bma->tp->t_firstblock,
 			&tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
@@ -4313,7 +4316,6 @@ xfs_bmapi_write(
 	bma.ip = ip;
 	bma.total = total;
 	bma.datatype = 0;
-	bma.firstblock = &tp->t_firstblock;
 	ASSERT(!tp || tp->t_dfops);
 
 	while (bno < end && n < *nmap) {
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 3cad9c3e3bda..2e8555c1229a 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -19,7 +19,6 @@ extern kmem_zone_t	*xfs_bmap_free_item_zone;
  * Argument structure for xfs_bmap_alloc.
  */
 struct xfs_bmalloca {
-	xfs_fsblock_t		*firstblock; /* i/o first block allocated */
 	struct xfs_trans	*tp;	/* transaction pointer */
 	struct xfs_inode	*ip;	/* incore inode pointer */
 	struct xfs_bmbt_irec	prev;	/* extent before the new one */
-- 
cgit v1.2.3


From 92f9da30f57bdb653ee46f26df2d51484b27c7f0 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:28 -0700
Subject: xfs: remove bmap extent add helper firstblock params

The add extent helpers all receive firstblock via ->t_firstblock.
Drop the parameter and access it directly.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 26 ++++++++++----------------
 1 file changed, 10 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 815600d39b03..cb2a4cde4c3f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -2031,7 +2031,6 @@ xfs_bmap_add_extent_unwritten_real(
 	struct xfs_iext_cursor	*icur,
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
-	xfs_fsblock_t		*first,	/* pointer to firstblock variable */
 	int			*logflagsp) /* inode logging flags */
 {
 	xfs_btree_cur_t		*cur;	/* btree cursor */
@@ -2473,8 +2472,8 @@ xfs_bmap_add_extent_unwritten_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, &cur, 0,
-				&tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
+				&cur, 0, &tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2645,7 +2644,6 @@ xfs_bmap_add_extent_hole_real(
 	struct xfs_iext_cursor	*icur,
 	struct xfs_btree_cur	**curp,
 	struct xfs_bmbt_irec	*new,
-	xfs_fsblock_t		*first,
 	int			*logflagsp,
 	int			flags)
 {
@@ -2837,8 +2835,8 @@ xfs_bmap_add_extent_hole_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, first, curp, 0,
-				&tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
+				curp, 0, &tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		cur = *curp;
 		if (error)
@@ -4107,8 +4105,7 @@ xfs_bmapi_allocate(
 	else
 		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
 				whichfork, &bma->icur, &bma->cur, &bma->got,
-				&bma->tp->t_firstblock, &bma->logflags,
-				bma->flags);
+				&bma->logflags, bma->flags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4176,8 +4173,7 @@ xfs_bmapi_convert_unwritten(
 	}
 
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork,
-			&bma->icur, &bma->cur, mval, &bma->tp->t_firstblock,
-			&tmp_logflags);
+			&bma->icur, &bma->cur, mval, &tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
 	 * path because the conversion might not have done so (e.g., if the
@@ -4550,7 +4546,7 @@ xfs_bmapi_remap(
 		got.br_state = XFS_EXT_NORM;
 
 	error = xfs_bmap_add_extent_hole_real(tp, ip, whichfork, &icur,
-			&cur, &got, &tp->t_firstblock, &logflags, flags);
+			&cur, &got, &logflags, flags);
 	if (error)
 		goto error0;
 
@@ -5314,7 +5310,7 @@ __xfs_bunmapi(
 			del.br_state = XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent_unwritten_real(tp, ip,
 					whichfork, &icur, &cur, &del,
-					&tp->t_firstblock, &logflags);
+					&logflags);
 			if (error)
 				goto error0;
 			goto nodelete;
@@ -5371,8 +5367,7 @@ __xfs_bunmapi(
 				prev.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&prev, &tp->t_firstblock,
-						&logflags);
+						&prev, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5381,8 +5376,7 @@ __xfs_bunmapi(
 				del.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
 						ip, whichfork, &icur, &cur,
-						&del, &tp->t_firstblock,
-						&logflags);
+						&del, &logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
-- 
cgit v1.2.3


From 280253d213fb735b565532be2836f94cf574260d Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:29 -0700
Subject: xfs: remove bmap format helpers firstblock params

The bmap format helpers receive firstblock via ->t_firstblock. Drop
the param and access it directly.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 63 ++++++++++++++++++++++--------------------------
 1 file changed, 29 insertions(+), 34 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index cb2a4cde4c3f..183450f1df19 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -646,7 +646,6 @@ STATIC int					/* error */
 xfs_bmap_extents_to_btree(
 	struct xfs_trans	*tp,		/* transaction pointer */
 	struct xfs_inode	*ip,		/* incore inode pointer */
-	xfs_fsblock_t		*firstblock,	/* first-block-allocated */
 	struct xfs_btree_cur	**curp,		/* cursor returned to caller */
 	int			wasdel,		/* converting a delayed alloc */
 	int			*logflagsp,	/* inode logging flags */
@@ -689,7 +688,7 @@ xfs_bmap_extents_to_btree(
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
 	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-	cur->bc_private.b.firstblock = *firstblock;
+	cur->bc_private.b.firstblock = tp->t_firstblock;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
 	/*
 	 * Convert to a btree with two levels, one record in root.
@@ -699,16 +698,16 @@ xfs_bmap_extents_to_btree(
 	args.tp = tp;
 	args.mp = mp;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
-	args.firstblock = *firstblock;
-	if (*firstblock == NULLFSBLOCK) {
+	args.firstblock = tp->t_firstblock;
+	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
 	} else if (tp->t_dfops->dop_low) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 	}
 	args.minlen = args.maxlen = args.prod = 1;
 	args.wasdel = wasdel;
@@ -731,9 +730,9 @@ xfs_bmap_extents_to_btree(
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
-	ASSERT(*firstblock == NULLFSBLOCK ||
-	       args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
-	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
+	ASSERT(tp->t_firstblock == NULLFSBLOCK ||
+	       args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
+	tp->t_firstblock = cur->bc_private.b.firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	ip->i_d.di_nblocks++;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
@@ -810,7 +809,6 @@ STATIC int				/* error */
 xfs_bmap_local_to_extents(
 	xfs_trans_t	*tp,		/* transaction pointer */
 	xfs_inode_t	*ip,		/* incore inode pointer */
-	xfs_fsblock_t	*firstblock,	/* first block allocated in xaction */
 	xfs_extlen_t	total,		/* total blocks needed by transaction */
 	int		*logflagsp,	/* inode logging flags */
 	int		whichfork,
@@ -848,16 +846,16 @@ xfs_bmap_local_to_extents(
 	args.tp = tp;
 	args.mp = ip->i_mount;
 	xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
-	args.firstblock = *firstblock;
+	args.firstblock = tp->t_firstblock;
 	/*
 	 * Allocate a block.  We know we need only one, since the
 	 * file currently fits in an inode.
 	 */
-	if (*firstblock == NULLFSBLOCK) {
+	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
-		args.fsbno = *firstblock;
+		args.fsbno = tp->t_firstblock;
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
 	}
 	args.total = total;
@@ -869,7 +867,7 @@ xfs_bmap_local_to_extents(
 	/* Can't fail, the space was reserved. */
 	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(args.len == 1);
-	*firstblock = args.fsbno;
+	tp->t_firstblock = args.fsbno;
 	bp = xfs_btree_get_bufl(args.mp, tp, args.fsbno, 0);
 
 	/*
@@ -964,8 +962,8 @@ xfs_bmap_add_attrfork_extents(
 	if (ip->i_d.di_nextents * sizeof(xfs_bmbt_rec_t) <= XFS_IFORK_DSIZE(ip))
 		return 0;
 	cur = NULL;
-	error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock, &cur, 0,
-					  flags, XFS_DATA_FORK);
+	error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0, flags,
+					  XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
 		xfs_btree_del_cursor(cur,
@@ -1007,8 +1005,8 @@ xfs_bmap_add_attrfork_local(
 	}
 
 	if (S_ISLNK(VFS_I(ip)->i_mode))
-		return xfs_bmap_local_to_extents(tp, ip, &tp->t_firstblock, 1,
-						 flags, XFS_DATA_FORK,
+		return xfs_bmap_local_to_extents(tp, ip, 1, flags,
+						 XFS_DATA_FORK,
 						 xfs_symlink_local_to_remote);
 
 	/* should only be called for types that support local format data */
@@ -1794,8 +1792,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					&bma->tp->t_firstblock, &bma->cur, 1,
-					&tmp_rval, whichfork);
+					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1872,8 +1869,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				&bma->tp->t_firstblock, &bma->cur, 1, &tmp_rval,
-				whichfork);
+				&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1953,8 +1949,7 @@ xfs_bmap_add_extent_delay_real(
 
 		if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
 			error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-					&bma->tp->t_firstblock, &bma->cur, 1,
-					&tmp_rval, whichfork);
+					&bma->cur, 1, &tmp_rval, whichfork);
 			rval |= tmp_rval;
 			if (error)
 				goto done;
@@ -1991,8 +1986,8 @@ xfs_bmap_add_extent_delay_real(
 
 		ASSERT(bma->cur == NULL);
 		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				&bma->tp->t_firstblock, &bma->cur, da_old > 0,
-				&tmp_logflags, whichfork);
+				&bma->cur, da_old > 0, &tmp_logflags,
+				whichfork);
 		bma->logflags |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2472,8 +2467,8 @@ xfs_bmap_add_extent_unwritten_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
-				&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2835,8 +2830,8 @@ xfs_bmap_add_extent_hole_real(
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
-				curp, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, curp, 0,
+				&tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		cur = *curp;
 		if (error)
@@ -5423,8 +5418,8 @@ nodelete:
 	 */
 	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
-				&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 		if (error)
 			goto error0;
@@ -5967,8 +5962,8 @@ xfs_bmap_split_extent_at(
 		int tmp_logflags; /* partial log flag return val */
 
 		ASSERT(cur == NULL);
-		error = xfs_bmap_extents_to_btree(tp, ip, &tp->t_firstblock,
-				&cur, 0, &tmp_logflags, whichfork);
+		error = xfs_bmap_extents_to_btree(tp, ip, &cur, 0,
+				&tmp_logflags, whichfork);
 		logflags |= tmp_logflags;
 	}
 
-- 
cgit v1.2.3


From cf612de732cb6ef626019ca085406d183f0a055a Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:29 -0700
Subject: xfs: remove xfs_btree_cur private firstblock field

The bmbt cursor private structure has a firstblock field that is
used to maintain locking order on bmbt allocations. The field holds
an actual firstblock value (as opposed to a pointer), so it is
initialized on cursor creation, updated on allocation and then the
value is transferred back to the source before the cursor is
destroyed.

This value is always transferred from and back to the ->t_firstblock
field. Since xfs_btree_cur already carries a reference to the
transaction, we can remove this field from xfs_btree_cur and the
associated copying. The bmbt allocations will update the value in
the transaction directly.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       | 28 +++-------------------------
 fs/xfs/libxfs/xfs_bmap_btree.c | 10 ++++------
 fs/xfs/libxfs/xfs_btree.h      |  1 -
 3 files changed, 7 insertions(+), 32 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 183450f1df19..8a1e6890a64b 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -688,7 +688,6 @@ xfs_bmap_extents_to_btree(
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
 	cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-	cur->bc_private.b.firstblock = tp->t_firstblock;
 	cur->bc_private.b.flags = wasdel ? XFS_BTCUR_BPRV_WASDEL : 0;
 	/*
 	 * Convert to a btree with two levels, one record in root.
@@ -732,7 +731,7 @@ xfs_bmap_extents_to_btree(
 	 */
 	ASSERT(tp->t_firstblock == NULLFSBLOCK ||
 	       args.agno >= XFS_FSB_TO_AGNO(mp, tp->t_firstblock));
-	tp->t_firstblock = cur->bc_private.b.firstblock = args.fsbno;
+	tp->t_firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	ip->i_d.di_nblocks++;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
@@ -925,7 +924,6 @@ xfs_bmap_add_attrfork_btree(
 		*flags |= XFS_ILOG_DBROOT;
 	else {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
-		cur->bc_private.b.firstblock = tp->t_firstblock;
 		error = xfs_bmbt_lookup_first(cur, &stat);
 		if (error)
 			goto error0;
@@ -937,7 +935,6 @@ xfs_bmap_add_attrfork_btree(
 			xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 			return -ENOSPC;
 		}
-		tp->t_firstblock = cur->bc_private.b.firstblock;
 		cur->bc_private.b.allocated = 0;
 		xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
 	}
@@ -4058,14 +4055,10 @@ xfs_bmapi_allocate(
 	if (error)
 		return error;
 
-	if (bma->cur)
-		bma->cur->bc_private.b.firstblock = bma->tp->t_firstblock;
 	if (bma->blkno == NULLFSBLOCK)
 		return 0;
-	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
+	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur)
 		bma->cur = xfs_bmbt_init_cursor(mp, bma->tp, bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = bma->tp->t_firstblock;
-	}
 	/*
 	 * Bump the number of extents we've allocated
 	 * in this call.
@@ -4151,7 +4144,6 @@ xfs_bmapi_convert_unwritten(
 	if ((ifp->if_flags & XFS_IFBROOT) && !bma->cur) {
 		bma->cur = xfs_bmbt_init_cursor(bma->ip->i_mount, bma->tp,
 					bma->ip, whichfork);
-		bma->cur->bc_private.b.firstblock = bma->tp->t_firstblock;
 	}
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
@@ -4458,13 +4450,6 @@ error0:
 		xfs_trans_log_inode(tp, ip, bma.logflags);
 
 	if (bma.cur) {
-		if (!error) {
-			ASSERT(tp->t_firstblock == NULLFSBLOCK ||
-			       XFS_FSB_TO_AGNO(mp, tp->t_firstblock) <=
-			       XFS_FSB_TO_AGNO(mp,
-				       bma.cur->bc_private.b.firstblock));
-			tp->t_firstblock = bma.cur->bc_private.b.firstblock;
-		}
 		xfs_btree_del_cursor(bma.cur,
 			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
 	}
@@ -4528,7 +4513,6 @@ xfs_bmapi_remap(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5189,7 +5173,6 @@ __xfs_bunmapi(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	} else
 		cur = NULL;
@@ -5457,10 +5440,8 @@ error0:
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (cur) {
-		if (!error) {
-			tp->t_firstblock = cur->bc_private.b.firstblock;
+		if (!error)
 			cur->bc_private.b.allocated = 0;
-		}
 		xfs_btree_del_cursor(cur,
 			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
 	}
@@ -5676,7 +5657,6 @@ xfs_bmap_collapse_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5796,7 +5776,6 @@ xfs_bmap_insert_extents(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 	}
 
@@ -5918,7 +5897,6 @@ xfs_bmap_split_extent_at(
 
 	if (ifp->if_flags & XFS_IFBROOT) {
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = tp->t_firstblock;
 		cur->bc_private.b.flags = 0;
 		error = xfs_bmbt_lookup_eq(cur, &got, &i);
 		if (error)
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index e8b01af09db5..8a9b98b11e34 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -175,7 +175,6 @@ xfs_bmbt_dup_cursor(
 	 * Copy the firstblock, dfops, and flags values,
 	 * since init cursor doesn't get them.
 	 */
-	new->bc_private.b.firstblock = cur->bc_private.b.firstblock;
 	new->bc_private.b.flags = cur->bc_private.b.flags;
 
 	return new;
@@ -186,11 +185,11 @@ xfs_bmbt_update_cursor(
 	struct xfs_btree_cur	*src,
 	struct xfs_btree_cur	*dst)
 {
-	ASSERT((dst->bc_private.b.firstblock != NULLFSBLOCK) ||
+	ASSERT((dst->bc_tp->t_firstblock != NULLFSBLOCK) ||
 	       (dst->bc_private.b.ip->i_d.di_flags & XFS_DIFLAG_REALTIME));
 
 	dst->bc_private.b.allocated += src->bc_private.b.allocated;
-	dst->bc_private.b.firstblock = src->bc_private.b.firstblock;
+	dst->bc_tp->t_firstblock = src->bc_tp->t_firstblock;
 
 	src->bc_private.b.allocated = 0;
 }
@@ -208,7 +207,7 @@ xfs_bmbt_alloc_block(
 	memset(&args, 0, sizeof(args));
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
-	args.fsbno = cur->bc_private.b.firstblock;
+	args.fsbno = cur->bc_tp->t_firstblock;
 	args.firstblock = args.fsbno;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino,
 			cur->bc_private.b.whichfork);
@@ -263,7 +262,7 @@ xfs_bmbt_alloc_block(
 	}
 
 	ASSERT(args.len == 1);
-	cur->bc_private.b.firstblock = args.fsbno;
+	cur->bc_tp->t_firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	cur->bc_private.b.ip->i_d.di_nblocks++;
 	xfs_trans_log_inode(args.tp, cur->bc_private.b.ip, XFS_ILOG_CORE);
@@ -562,7 +561,6 @@ xfs_bmbt_init_cursor(
 
 	cur->bc_private.b.forksize = XFS_IFORK_SIZE(ip, whichfork);
 	cur->bc_private.b.ip = ip;
-	cur->bc_private.b.firstblock = NULLFSBLOCK;
 	cur->bc_private.b.allocated = 0;
 	cur->bc_private.b.flags = 0;
 	cur->bc_private.b.whichfork = whichfork;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index b986a8fc8d40..503615f4d729 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -214,7 +214,6 @@ typedef struct xfs_btree_cur
 		} a;
 		struct {			/* needed for BMAP */
 			struct xfs_inode *ip;	/* pointer to our inode */
-			xfs_fsblock_t	firstblock;	/* 1st blk allocated */
 			int		allocated;	/* count of alloced */
 			short		forksize;	/* fork's inode space */
 			char		whichfork;	/* data or attr fork */
-- 
cgit v1.2.3


From 64396ff2c25b2cd8156948a64ae0da5ff962e3f2 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:30 -0700
Subject: xfs: remove xfs_alloc_arg firstblock field

The xfs_alloc_arg.firstblock field is used to control the starting
agno for an allocation. The structure already carries a pointer to
the transaction, which carries the current firstblock value.

Remove the field and access ->t_firstblock directly in the
allocation code.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c          | 20 ++++++++++----------
 fs/xfs/libxfs/xfs_alloc.h          |  1 -
 fs/xfs/libxfs/xfs_bmap.c           |  3 ---
 fs/xfs/libxfs/xfs_bmap_btree.c     |  1 -
 fs/xfs/libxfs/xfs_refcount_btree.c |  1 -
 fs/xfs/xfs_trace.h                 |  2 +-
 6 files changed, 11 insertions(+), 17 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 5b1607d76fe9..bd6d8aeea825 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2783,16 +2783,16 @@ xfs_alloc_read_agf(
  */
 int				/* error */
 xfs_alloc_vextent(
-	xfs_alloc_arg_t	*args)	/* allocation argument structure */
+	struct xfs_alloc_arg	*args)	/* allocation argument structure */
 {
-	xfs_agblock_t	agsize;	/* allocation group size */
-	int		error;
-	int		flags;	/* XFS_ALLOC_FLAG_... locking flags */
-	xfs_mount_t	*mp;	/* mount structure pointer */
-	xfs_agnumber_t	sagno;	/* starting allocation group number */
-	xfs_alloctype_t	type;	/* input allocation type */
-	int		bump_rotor = 0;
-	xfs_agnumber_t	rotorstep = xfs_rotorstep; /* inode32 agf stepper */
+	xfs_agblock_t		agsize;	/* allocation group size */
+	int			error;
+	int			flags;	/* XFS_ALLOC_FLAG_... locking flags */
+	struct xfs_mount	*mp;	/* mount structure pointer */
+	xfs_agnumber_t		sagno;	/* starting allocation group number */
+	xfs_alloctype_t		type;	/* input allocation type */
+	int			bump_rotor = 0;
+	xfs_agnumber_t		rotorstep = xfs_rotorstep; /* inode32 agf stepper */
 
 	mp = args->mp;
 	type = args->otype = args->type;
@@ -2913,7 +2913,7 @@ xfs_alloc_vextent(
 			* locking of AGF, which might cause deadlock.
 			*/
 			if (++(args->agno) == mp->m_sb.sb_agcount) {
-				if (args->firstblock != NULLFSBLOCK)
+				if (args->tp->t_firstblock != NULLFSBLOCK)
 					args->agno = sagno;
 				else
 					args->agno = 0;
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index e716c993ac4c..00cd5ec4cb6b 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -74,7 +74,6 @@ typedef struct xfs_alloc_arg {
 	int		datatype;	/* mask defining data type treatment */
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
-	xfs_fsblock_t	firstblock;	/* io first block allocated */
 	struct xfs_owner_info	oinfo;	/* owner of blocks being allocated */
 	enum xfs_ag_resv_type	resv;	/* block reservation to use */
 } xfs_alloc_arg_t;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 8a1e6890a64b..12be9ad888c3 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -697,7 +697,6 @@ xfs_bmap_extents_to_btree(
 	args.tp = tp;
 	args.mp = mp;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, ip->i_ino, whichfork);
-	args.firstblock = tp->t_firstblock;
 	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
@@ -845,7 +844,6 @@ xfs_bmap_local_to_extents(
 	args.tp = tp;
 	args.mp = ip->i_mount;
 	xfs_rmap_ino_owner(&args.oinfo, ip->i_ino, whichfork, 0);
-	args.firstblock = tp->t_firstblock;
 	/*
 	 * Allocate a block.  We know we need only one, since the
 	 * file currently fits in an inode.
@@ -3445,7 +3443,6 @@ xfs_bmap_btalloc(
 
 	/* Trim the allocation back to the maximum an AG can fit. */
 	args.maxlen = min(ap->length, mp->m_ag_max_usable);
-	args.firstblock = ap->tp->t_firstblock;
 	blen = 0;
 	if (nullfb) {
 		/*
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 8a9b98b11e34..628ed82ca286 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -208,7 +208,6 @@ xfs_bmbt_alloc_block(
 	args.tp = cur->bc_tp;
 	args.mp = cur->bc_mp;
 	args.fsbno = cur->bc_tp->t_firstblock;
-	args.firstblock = args.fsbno;
 	xfs_rmap_ino_bmbt_owner(&args.oinfo, cur->bc_private.b.ip->i_ino,
 			cur->bc_private.b.whichfork);
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 393aa88f93db..26d2300ed865 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -70,7 +70,6 @@ xfs_refcountbt_alloc_block(
 	args.type = XFS_ALLOCTYPE_NEAR_BNO;
 	args.fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
 			xfs_refc_block(args.mp));
-	args.firstblock = args.fsbno;
 	xfs_rmap_ag_owner(&args.oinfo, XFS_RMAP_OWN_REFC);
 	args.minlen = args.maxlen = args.prod = 1;
 	args.resv = XFS_AG_RESV_METADATA;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 7f4c7071e7ed..9d741571b61e 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -1590,7 +1590,7 @@ DECLARE_EVENT_CLASS(xfs_alloc_class,
 		__entry->wasfromfl = args->wasfromfl;
 		__entry->resv = args->resv;
 		__entry->datatype = args->datatype;
-		__entry->firstblock = args->firstblock;
+		__entry->firstblock = args->tp->t_firstblock;
 	),
 	TP_printk("dev %d:%d agno %u agbno %u minlen %u maxlen %u mod %u "
 		  "prod %u minleft %u total %u alignment %u minalignslop %u "
-- 
cgit v1.2.3


From 058529c5f51cd680eddbc6c42f56d490e290dd78 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:30 -0700
Subject: xfs: use ->t_firstblock in dq alloc

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_dquot.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 84359eeb20f4..3b61b4d266b4 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -540,14 +540,13 @@ xfs_qm_dqread_alloc(
 	struct xfs_trans	*tp;
 	struct xfs_defer_ops	dfops;
 	struct xfs_buf		*bp;
-	xfs_fsblock_t		firstblock;
 	int			error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_qm_dqalloc,
 			XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
 	if (error)
 		goto err;
-	xfs_defer_init(tp, &dfops, &firstblock);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	error = xfs_dquot_disk_alloc(&tp, dqp, &bp);
 	if (error)
-- 
cgit v1.2.3


From fb91f4b5d6187996796f4a9989decdf6ead12851 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:31 -0700
Subject: xfs: replace no-op firstblock init with ->t_firstblock

xfs_refcount_recover_cow_leftovers() has no need for a firstblock
variable and so passes an unrelated xfs_fsblock_t to
xfs_defer_init() to avoid declaring one. Replace this no-op
initialization with ->t_firstblock. This will be optimized away by
the removal of the xfs_defer_init() firstblock param.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_refcount.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 8dc380574cd8..d81c17aac710 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1691,7 +1691,7 @@ xfs_refcount_recover_cow_leftovers(
 		trace_xfs_refcount_recover_extent(mp, agno, &rr->rr_rrec);
 
 		/* Free the orphan record */
-		xfs_defer_init(tp, &dfops, &fsb);
+		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
 		error = xfs_refcount_free_cow_extent(mp, tp->t_dfops, fsb,
-- 
cgit v1.2.3


From 381d592848721cb1b82b4ea9f57b46cf4a4a6973 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:31 -0700
Subject: xfs: use ->t_firstblock in reflink cow block cancel

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_reflink.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 2972efeee5cc..891214242118 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -483,7 +483,6 @@ xfs_reflink_cancel_cow_blocks(
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
 	struct xfs_iext_cursor		icur;
-	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
 	struct xfs_defer_ops		*odfops = (*tpp)->t_dfops;
 	int				error = 0;
@@ -512,7 +511,7 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			xfs_defer_init(*tpp, &dfops, &firstfsb);
+			xfs_defer_init(*tpp, &dfops, &(*tpp)->t_firstblock);
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
-- 
cgit v1.2.3


From f537538921872c772aa743d8b58b69e7729c73aa Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:32 -0700
Subject: xfs: use ->t_firstblock in extent swap

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index e9907bbe9529..765859843606 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1570,7 +1570,6 @@ xfs_swap_extent_rmap(
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
 	xfs_filblks_t			count_fsb;
-	xfs_fsblock_t			firstfsb;
 	int				error;
 	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
@@ -1606,7 +1605,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			xfs_defer_init(tp, tp->t_dfops, &firstfsb);
+			xfs_defer_init(tp, tp->t_dfops, &tp->t_firstblock);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
@@ -1848,7 +1847,6 @@ xfs_swap_extents(
 	struct xfs_ifork	*cowfp;
 	uint64_t		f;
 	int			resblks = 0;
-	xfs_fsblock_t		firstfsb;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
@@ -1911,7 +1909,7 @@ xfs_swap_extents(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
-	xfs_defer_init(tp, &dfops, &firstfsb);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 
 	/*
 	 * Lock and join the inodes to the tansaction so that transaction commit
-- 
cgit v1.2.3


From 9c3bf5da80efc1d502c7ef55ea5b77628e341510 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:32 -0700
Subject: xfs: use ->t_firstblock in inode inactivate

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_inode.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5e1eaa26435c..48d22134b06f 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1772,7 +1772,6 @@ xfs_inactive_ifree(
 	struct xfs_inode *ip)
 {
 	struct xfs_defer_ops	dfops;
-	xfs_fsblock_t		first_block;
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
@@ -1809,7 +1808,7 @@ xfs_inactive_ifree(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops, &first_block);
+	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
 	error = xfs_ifree(tp, ip);
 	if (error) {
 		/*
-- 
cgit v1.2.3


From 5fdd97944ee5ae0fcdd88227224d0c2c87aa6db9 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:33 -0700
Subject: xfs: remove xfs_defer_init() firstblock param

All but one caller of xfs_defer_init() passes in the ->t_firstblock
of the associated transaction. The one outlier is
xlog_recover_process_intents(), which simply passes a dummy value
because a valid pointer is required. This firstblock variable can
simply be removed.

At this point we could remove the xfs_defer_init() firstblock
parameter and initialize ->t_firstblock directly. Even that is not
necessary, however, because ->t_firstblock is automatically
reinitialized in the new transaction on a transaction roll. Since
xfs_defer_init() should never occur more than once on a particular
transaction (since the corresponding finish will roll it), replace
the reinit from xfs_defer_init() with an assert that verifies the
transaction has a NULLFSBLOCK firstblock.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 28 ++++++++++------------------
 fs/xfs/libxfs/xfs_attr_remote.c |  9 +++------
 fs/xfs/libxfs/xfs_bmap.c        |  4 ++--
 fs/xfs/libxfs/xfs_defer.c       |  5 ++---
 fs/xfs/libxfs/xfs_defer.h       |  3 +--
 fs/xfs/libxfs/xfs_refcount.c    |  2 +-
 fs/xfs/xfs_bmap_util.c          | 12 ++++++------
 fs/xfs/xfs_dquot.c              |  4 ++--
 fs/xfs/xfs_inode.c              | 12 ++++++------
 fs/xfs/xfs_iomap.c              |  6 +++---
 fs/xfs/xfs_log_recover.c        |  3 +--
 fs/xfs/xfs_reflink.c            |  8 ++++----
 fs/xfs/xfs_rtalloc.c            |  2 +-
 fs/xfs/xfs_symlink.c            |  4 ++--
 14 files changed, 44 insertions(+), 58 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 153d2e29f872..927d4c968f9a 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -251,7 +251,7 @@ xfs_attr_set(
 			rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(args.trans, &dfops, &args.trans->t_firstblock);
+	xfs_defer_init(args.trans, &dfops);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
@@ -422,7 +422,7 @@ xfs_attr_remove(
 			&args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(args.trans, &dfops, &args.trans->t_firstblock);
+	xfs_defer_init(args.trans, &dfops);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	/*
@@ -593,8 +593,7 @@ xfs_attr_leaf_addname(
 		 * Commit that transaction so that the node_addname() call
 		 * can manage its own transactions.
 		 */
-		xfs_defer_init(args->trans, args->trans->t_dfops,
-			       &args->trans->t_firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
@@ -683,8 +682,7 @@ xfs_attr_leaf_addname(
 		 * If the result is small enough, shrink it all into the inode.
 		 */
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->trans, args->trans->t_dfops,
-				       &args->trans->t_firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
@@ -749,8 +747,7 @@ xfs_attr_leaf_removename(
 	 * If the result is small enough, shrink it all into the inode.
 	 */
 	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		xfs_defer_init(args->trans, args->trans->t_dfops,
-			       &args->trans->t_firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
@@ -879,8 +876,7 @@ restart:
 			 */
 			xfs_da_state_free(state);
 			state = NULL;
-			xfs_defer_init(args->trans, args->trans->t_dfops,
-				       &args->trans->t_firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
@@ -907,8 +903,7 @@ restart:
 		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
 		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
 		 */
-		xfs_defer_init(args->trans, args->trans->t_dfops,
-			       &args->trans->t_firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
@@ -1006,8 +1001,7 @@ restart:
 		 * Check to see if the tree needs to be collapsed.
 		 */
 		if (retval && (state->path.active > 1)) {
-			xfs_defer_init(args->trans, args->trans->t_dfops,
-				       &args->trans->t_firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
@@ -1132,8 +1126,7 @@ xfs_attr_node_removename(
 	 * Check to see if the tree needs to be collapsed.
 	 */
 	if (retval && (state->path.active > 1)) {
-		xfs_defer_init(args->trans, args->trans->t_dfops,
-			       &args->trans->t_firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
@@ -1165,8 +1158,7 @@ xfs_attr_node_removename(
 			goto out;
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->trans, args->trans->t_dfops,
-				       &args->trans->t_firstblock);
+			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index f02c705965ff..7841e6255129 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -480,8 +480,7 @@ xfs_attr_rmtval_set(
 		 * extent and then crash then the block may not contain the
 		 * correct metadata after log recovery occurs.
 		 */
-		xfs_defer_init(args->trans, args->trans->t_dfops,
-			       &args->trans->t_firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
 				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
@@ -523,8 +522,7 @@ xfs_attr_rmtval_set(
 
 		ASSERT(blkcnt > 0);
 
-		xfs_defer_init(args->trans, args->trans->t_dfops,
-			       &args->trans->t_firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops);
 		nmap = 1;
 		error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
 				       blkcnt, &map, &nmap,
@@ -628,8 +626,7 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		xfs_defer_init(args->trans, args->trans->t_dfops,
-			       &args->trans->t_firstblock);
+		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
 				    XFS_BMAPI_ATTRFORK, 1, &done);
 		if (error)
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 12be9ad888c3..7b93b1e16ad9 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1038,7 +1038,7 @@ xfs_bmap_add_attrfork(
 			rsvd ? XFS_TRANS_RESERVE : 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
@@ -5968,7 +5968,7 @@ xfs_bmap_split_extent(
 			XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 6b25a9436829..2713e2d808a7 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -524,16 +524,15 @@ xfs_defer_init_op_type(
 void
 xfs_defer_init(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
-	xfs_fsblock_t			*fbp)
+	struct xfs_defer_ops		*dop)
 {
 	struct xfs_mount		*mp = NULL;
 
 	memset(dop, 0, sizeof(struct xfs_defer_ops));
-	*fbp = NULLFSBLOCK;
 	INIT_LIST_HEAD(&dop->dop_intake);
 	INIT_LIST_HEAD(&dop->dop_pending);
 	if (tp) {
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		tp->t_dfops = dop;
 		mp = tp->t_mountp;
 	}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 56eaaac31df5..c17c9deda995 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -63,8 +63,7 @@ void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
 		struct list_head *h);
 int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop);
 void xfs_defer_cancel(struct xfs_defer_ops *dop);
-void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop,
-		    xfs_fsblock_t *fbp);
+void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
 int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index d81c17aac710..2ecfb0518580 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1691,7 +1691,7 @@ xfs_refcount_recover_cow_leftovers(
 		trace_xfs_refcount_recover_extent(mp, agno, &rr->rr_rrec);
 
 		/* Free the orphan record */
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
 		error = xfs_refcount_free_cow_extent(mp, tp->t_dfops, fsb,
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 765859843606..d3a314fd721f 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -971,7 +971,7 @@ xfs_alloc_file_space(
 
 		xfs_trans_ijoin(tp, ip, 0);
 
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
 					allocatesize_fsb, alloc_type, resblks,
 					imapp, &nimaps);
@@ -1040,7 +1040,7 @@ xfs_unmap_extent(
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done);
 	if (error)
 		goto out_bmap_cancel;
@@ -1341,7 +1341,7 @@ xfs_collapse_file_space(
 			goto out_trans_cancel;
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
 				&done);
 		if (error)
@@ -1419,7 +1419,7 @@ xfs_insert_file_space(
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
 				&done, stop_fsb);
 		if (error)
@@ -1605,7 +1605,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			xfs_defer_init(tp, tp->t_dfops, &tp->t_firstblock);
+			xfs_defer_init(tp, tp->t_dfops);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
@@ -1909,7 +1909,7 @@ xfs_swap_extents(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	/*
 	 * Lock and join the inodes to the tansaction so that transaction commit
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 3b61b4d266b4..c53de34c9ae5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -295,7 +295,7 @@ xfs_dquot_disk_alloc(
 
 	trace_xfs_dqalloc(dqp);
 
-	xfs_defer_init(tp, tp->t_dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, tp->t_dfops);
 
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
@@ -546,7 +546,7 @@ xfs_qm_dqread_alloc(
 			XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
 	if (error)
 		goto err;
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	error = xfs_dquot_disk_alloc(&tp, dqp, &bp);
 	if (error)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 48d22134b06f..7b2694d3901a 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1194,7 +1194,7 @@ xfs_create(
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	/*
 	 * Reserve disk quota and the inode.
@@ -1448,7 +1448,7 @@ xfs_link(
 			goto error_return;
 	}
 
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	/*
 	 * Handle initial link state of O_TMPFILE inode
@@ -1579,7 +1579,7 @@ xfs_itruncate_extents_flags(
 	ASSERT(first_unmap_block < last_block);
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
 				    XFS_ITRUNC_MAX_EXTENTS, &done);
 		if (error)
@@ -1808,7 +1808,7 @@ xfs_inactive_ifree(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 	error = xfs_ifree(tp, ip);
 	if (error) {
 		/*
@@ -2651,7 +2651,7 @@ xfs_remove(
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 	error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
 	if (error) {
 		ASSERT(error != -ENOENT);
@@ -3008,7 +3008,7 @@ xfs_rename(
 		goto out_trans_cancel;
 	}
 
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 0ae822538a63..756694219f77 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -253,7 +253,7 @@ xfs_iomap_write_direct(
 	 * From this point onwards we overwrite the imap pointer that the
 	 * caller gave to us.
 	 */
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 				bmapi_flags, resblks, imap, &nimaps);
@@ -713,7 +713,7 @@ xfs_iomap_write_allocate(
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			xfs_trans_ijoin(tp, ip, 0);
 
-			xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+			xfs_defer_init(tp, &dfops);
 
 			/*
 			 * it is possible that the extents have changed since
@@ -872,7 +872,7 @@ xfs_iomap_write_unwritten(
 		/*
 		 * Modify the unwritten extent state of the buffer.
 		 */
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 					XFS_BMAPI_CONVERT, resblks, &imap,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 940eb30e0271..8317023293a5 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4890,7 +4890,6 @@ xlog_recover_process_intents(
 	struct xfs_ail_cursor	cur;
 	struct xfs_log_item	*lip;
 	struct xfs_ail		*ailp;
-	xfs_fsblock_t		firstfsb;
 	int			error = 0;
 #if defined(DEBUG) || defined(XFS_WARN)
 	xfs_lsn_t		last_lsn;
@@ -4902,7 +4901,7 @@ xlog_recover_process_intents(
 #if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
 #endif
-	xfs_defer_init(NULL, &dfops, &firstfsb);
+	xfs_defer_init(NULL, &dfops);
 	while (lip != NULL) {
 		/*
 		 * We're done when we see something other than an intent.
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 891214242118..3143889097f1 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -424,7 +424,7 @@ retry:
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 	nimaps = 1;
 
 	/* Allocate the entire reservation as unwritten blocks. */
@@ -511,7 +511,7 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			xfs_defer_init(*tpp, &dfops, &(*tpp)->t_firstblock);
+			xfs_defer_init(*tpp, &dfops);
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
@@ -693,7 +693,7 @@ xfs_reflink_end_cow(
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		rlen = del.br_blockcount;
 		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
 		if (error)
@@ -1041,7 +1041,7 @@ xfs_reflink_remap_extent(
 	/* Unmap the old blocks in the data fork. */
 	rlen = unmap_len;
 	while (rlen) {
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
 		if (error)
 			goto out_defer;
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index edd949376a51..bc471d42a968 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -786,7 +786,7 @@ xfs_growfs_rt_alloc(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+		xfs_defer_init(tp, &dfops);
 		/*
 		 * Allocate blocks to the bitmap file.
 		 */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index a3dc552a5b97..d1ab0afa2723 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -245,7 +245,7 @@ xfs_symlink(
 	 * Initialize the bmap freelist prior to calling either
 	 * bmapi or the directory create code.
 	 */
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 
 	/*
 	 * Allocate an inode for the symlink.
@@ -438,7 +438,7 @@ xfs_inactive_symlink_rmt(
 	 * Find the block(s) so we can inval and unmap them.
 	 */
 	done = 0;
-	xfs_defer_init(tp, &dfops, &tp->t_firstblock);
+	xfs_defer_init(tp, &dfops);
 	nmaps = ARRAY_SIZE(mval);
 	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
 				mval, &nmaps, 0);
-- 
cgit v1.2.3


From eaebb515f1a4728565c482b13dfb17273dc4ddc8 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:34 -0700
Subject: xfs: refactor buffer submission into a common helper

Sync and async buffer submission both do generally similar things
with a couple odd exceptions. Refactor the core buffer submission
code into a common helper to isolate buffer submission from
completion handling of synchronous buffer I/O.

This patch does not change behavior. It is a step towards support
for using synchronous buffer I/O via synchronous delwri queue
submission.

Designed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_buf.c   | 85 ++++++++++++++++++++++++------------------------------
 fs/xfs/xfs_trace.h |  1 -
 2 files changed, 37 insertions(+), 49 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e9c058e3761c..7b0f7c79cd62 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1458,22 +1458,20 @@ _xfs_buf_ioapply(
  * a call to this function unless the caller holds an additional reference
  * itself.
  */
-void
-xfs_buf_submit(
+static int
+__xfs_buf_submit(
 	struct xfs_buf	*bp)
 {
 	trace_xfs_buf_submit(bp, _RET_IP_);
 
 	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
-	ASSERT(bp->b_flags & XBF_ASYNC);
 
 	/* on shutdown we stale and complete the buffer immediately */
 	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
 		xfs_buf_ioerror(bp, -EIO);
 		bp->b_flags &= ~XBF_DONE;
 		xfs_buf_stale(bp);
-		xfs_buf_ioend(bp);
-		return;
+		return -EIO;
 	}
 
 	if (bp->b_flags & XBF_WRITE)
@@ -1482,23 +1480,14 @@ xfs_buf_submit(
 	/* clear the internal error state to avoid spurious errors */
 	bp->b_io_error = 0;
 
-	/*
-	 * The caller's reference is released during I/O completion.
-	 * This occurs some time after the last b_io_remaining reference is
-	 * released, so after we drop our Io reference we have to have some
-	 * other reference to ensure the buffer doesn't go away from underneath
-	 * us. Take a direct reference to ensure we have safe access to the
-	 * buffer until we are finished with it.
-	 */
-	xfs_buf_hold(bp);
-
 	/*
 	 * Set the count to 1 initially, this will stop an I/O completion
 	 * callout which happens before we have started all the I/O from calling
 	 * xfs_buf_ioend too early.
 	 */
 	atomic_set(&bp->b_io_remaining, 1);
-	xfs_buf_ioacct_inc(bp);
+	if (bp->b_flags & XBF_ASYNC)
+		xfs_buf_ioacct_inc(bp);
 	_xfs_buf_ioapply(bp);
 
 	/*
@@ -1507,14 +1496,39 @@ xfs_buf_submit(
 	 * that we don't return to the caller with completion still pending.
 	 */
 	if (atomic_dec_and_test(&bp->b_io_remaining) == 1) {
-		if (bp->b_error)
+		if (bp->b_error || !(bp->b_flags & XBF_ASYNC))
 			xfs_buf_ioend(bp);
 		else
 			xfs_buf_ioend_async(bp);
 	}
 
-	xfs_buf_rele(bp);
+	return 0;
+}
+
+void
+xfs_buf_submit(
+	struct xfs_buf	*bp)
+{
+	int		error;
+
+	ASSERT(bp->b_flags & XBF_ASYNC);
+
+	/*
+	 * The caller's reference is released during I/O completion.
+	 * This occurs some time after the last b_io_remaining reference is
+	 * released, so after we drop our Io reference we have to have some
+	 * other reference to ensure the buffer doesn't go away from underneath
+	 * us. Take a direct reference to ensure we have safe access to the
+	 * buffer until we are finished with it.
+	 */
+	xfs_buf_hold(bp);
+
+	error = __xfs_buf_submit(bp);
+	if (error)
+		xfs_buf_ioend(bp);
+
 	/* Note: it is not safe to reference bp now we've dropped our ref */
+	xfs_buf_rele(bp);
 }
 
 /*
@@ -1526,22 +1540,7 @@ xfs_buf_submit_wait(
 {
 	int		error;
 
-	trace_xfs_buf_submit_wait(bp, _RET_IP_);
-
-	ASSERT(!(bp->b_flags & (_XBF_DELWRI_Q | XBF_ASYNC)));
-
-	if (XFS_FORCED_SHUTDOWN(bp->b_target->bt_mount)) {
-		xfs_buf_ioerror(bp, -EIO);
-		xfs_buf_stale(bp);
-		bp->b_flags &= ~XBF_DONE;
-		return -EIO;
-	}
-
-	if (bp->b_flags & XBF_WRITE)
-		xfs_buf_wait_unpin(bp);
-
-	/* clear the internal error state to avoid spurious errors */
-	bp->b_io_error = 0;
+	ASSERT(!(bp->b_flags & XBF_ASYNC));
 
 	/*
 	 * For synchronous IO, the IO does not inherit the submitters reference
@@ -1551,20 +1550,9 @@ xfs_buf_submit_wait(
 	 */
 	xfs_buf_hold(bp);
 
-	/*
-	 * Set the count to 1 initially, this will stop an I/O completion
-	 * callout which happens before we have started all the I/O from calling
-	 * xfs_buf_ioend too early.
-	 */
-	atomic_set(&bp->b_io_remaining, 1);
-	_xfs_buf_ioapply(bp);
-
-	/*
-	 * make sure we run completion synchronously if it raced with us and is
-	 * already complete.
-	 */
-	if (atomic_dec_and_test(&bp->b_io_remaining) == 1)
-		xfs_buf_ioend(bp);
+	error = __xfs_buf_submit(bp);
+	if (error)
+		goto out;
 
 	/* wait for completion before gathering the error from the buffer */
 	trace_xfs_buf_iowait(bp, _RET_IP_);
@@ -1572,6 +1560,7 @@ xfs_buf_submit_wait(
 	trace_xfs_buf_iowait_done(bp, _RET_IP_);
 	error = bp->b_error;
 
+out:
 	/*
 	 * all done now, we can release the hold that keeps the buffer
 	 * referenced for the entire IO.
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 9d741571b61e..b668fc127aa7 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -310,7 +310,6 @@ DEFINE_BUF_EVENT(xfs_buf_hold);
 DEFINE_BUF_EVENT(xfs_buf_rele);
 DEFINE_BUF_EVENT(xfs_buf_iodone);
 DEFINE_BUF_EVENT(xfs_buf_submit);
-DEFINE_BUF_EVENT(xfs_buf_submit_wait);
 DEFINE_BUF_EVENT(xfs_buf_lock);
 DEFINE_BUF_EVENT(xfs_buf_lock_done);
 DEFINE_BUF_EVENT(xfs_buf_trylock_fail);
-- 
cgit v1.2.3


From e339dd8d8b045399e918c6737b2cc435b21a451e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:34 -0700
Subject: xfs: use sync buffer I/O for sync delwri queue submission

If a delwri queue occurs of a buffer that sits on a delwri queue
wait list, the queue sets _XBF_DELWRI_Q without changing the state
of ->b_list. This occurs, for example, if another thread beats the
current delwri waiter thread to the buffer lock after I/O
completion. Once the waiter acquires the lock, it removes the buffer
from the wait list and leaves a buffer with _XBF_DELWRI_Q set but
not populated on a list. This results in a lost buffer submission
and in turn can result in assert failures due to _XBF_DELWRI_Q being
set on buffer reclaim or filesystem lockups if the buffer happens to
cover an item in the AIL.

This problem has been reproduced by repeated iterations of xfs/305
on high CPU count (28xcpu) systems with limited memory (~1GB). Dirty
dquot reclaim races with an xfsaild push of a separate dquot backed
by the same buffer such that the buffer sits on the reclaim wait
list at the time xfsaild attempts to queue it. Since the latter
dquot has been flush locked but the underlying buffer not submitted
for I/O, the dquot pins the AIL and causes the filesystem to
livelock.

This race is essentially made possible by the buffer lock cycle
involved with waiting on a synchronous delwri queue submission.
Close the race by using synchronous buffer I/O for respective delwri
queue submission. This means the buffer remains locked across the
I/O and so is inaccessible from other contexts while in the
intermediate wait list state. The sync buffer I/O wait mechanism is
factored into a helper such that sync delwri buffer submission and
serialization are batched operations.

Designed-by: Dave Chinner <dchinner@redhat.com>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_buf.c | 80 +++++++++++++++++++++++++++++---------------------------
 1 file changed, 41 insertions(+), 39 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 7b0f7c79cd62..ef234847b4e6 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1531,6 +1531,20 @@ xfs_buf_submit(
 	xfs_buf_rele(bp);
 }
 
+/*
+ * Wait for I/O completion of a sync buffer and return the I/O error code.
+ */
+static int
+xfs_buf_iowait(
+	struct xfs_buf	*bp)
+{
+	trace_xfs_buf_iowait(bp, _RET_IP_);
+	wait_for_completion(&bp->b_iowait);
+	trace_xfs_buf_iowait_done(bp, _RET_IP_);
+
+	return bp->b_error;
+}
+
 /*
  * Synchronous buffer IO submission path, read or write.
  */
@@ -1553,12 +1567,7 @@ xfs_buf_submit_wait(
 	error = __xfs_buf_submit(bp);
 	if (error)
 		goto out;
-
-	/* wait for completion before gathering the error from the buffer */
-	trace_xfs_buf_iowait(bp, _RET_IP_);
-	wait_for_completion(&bp->b_iowait);
-	trace_xfs_buf_iowait_done(bp, _RET_IP_);
-	error = bp->b_error;
+	error = xfs_buf_iowait(bp);
 
 out:
 	/*
@@ -1961,16 +1970,11 @@ xfs_buf_cmp(
 }
 
 /*
- * submit buffers for write.
- *
- * When we have a large buffer list, we do not want to hold all the buffers
- * locked while we block on the request queue waiting for IO dispatch. To avoid
- * this problem, we lock and submit buffers in groups of 50, thereby minimising
- * the lock hold times for lists which may contain thousands of objects.
- *
- * To do this, we sort the buffer list before we walk the list to lock and
- * submit buffers, and we plug and unplug around each group of buffers we
- * submit.
+ * Submit buffers for write. If wait_list is specified, the buffers are
+ * submitted using sync I/O and placed on the wait list such that the caller can
+ * iowait each buffer. Otherwise async I/O is used and the buffers are released
+ * at I/O completion time. In either case, buffers remain locked until I/O
+ * completes and the buffer is released from the queue.
  */
 static int
 xfs_buf_delwri_submit_buffers(
@@ -2012,21 +2016,22 @@ xfs_buf_delwri_submit_buffers(
 		trace_xfs_buf_delwri_split(bp, _RET_IP_);
 
 		/*
-		 * We do all IO submission async. This means if we need
-		 * to wait for IO completion we need to take an extra
-		 * reference so the buffer is still valid on the other
-		 * side. We need to move the buffer onto the io_list
-		 * at this point so the caller can still access it.
+		 * If we have a wait list, each buffer (and associated delwri
+		 * queue reference) transfers to it and is submitted
+		 * synchronously. Otherwise, drop the buffer from the delwri
+		 * queue and submit async.
 		 */
 		bp->b_flags &= ~(_XBF_DELWRI_Q | XBF_WRITE_FAIL);
-		bp->b_flags |= XBF_WRITE | XBF_ASYNC;
+		bp->b_flags |= XBF_WRITE;
 		if (wait_list) {
-			xfs_buf_hold(bp);
+			bp->b_flags &= ~XBF_ASYNC;
 			list_move_tail(&bp->b_list, wait_list);
-		} else
+			__xfs_buf_submit(bp);
+		} else {
+			bp->b_flags |= XBF_ASYNC;
 			list_del_init(&bp->b_list);
-
-		xfs_buf_submit(bp);
+			xfs_buf_submit(bp);
+		}
 	}
 	blk_finish_plug(&plug);
 
@@ -2073,9 +2078,11 @@ xfs_buf_delwri_submit(
 
 		list_del_init(&bp->b_list);
 
-		/* locking the buffer will wait for async IO completion. */
-		xfs_buf_lock(bp);
-		error2 = bp->b_error;
+		/*
+		 * Wait on the locked buffer, check for errors and unlock and
+		 * release the delwri queue reference.
+		 */
+		error2 = xfs_buf_iowait(bp);
 		xfs_buf_relse(bp);
 		if (!error)
 			error = error2;
@@ -2121,23 +2128,18 @@ xfs_buf_delwri_pushbuf(
 
 	/*
 	 * Delwri submission clears the DELWRI_Q buffer flag and returns with
-	 * the buffer on the wait list with an associated reference. Rather than
+	 * the buffer on the wait list with the original reference. Rather than
 	 * bounce the buffer from a local wait list back to the original list
 	 * after I/O completion, reuse the original list as the wait list.
 	 */
 	xfs_buf_delwri_submit_buffers(&submit_list, buffer_list);
 
 	/*
-	 * The buffer is now under I/O and wait listed as during typical delwri
-	 * submission. Lock the buffer to wait for I/O completion. Rather than
-	 * remove the buffer from the wait list and release the reference, we
-	 * want to return with the buffer queued to the original list. The
-	 * buffer already sits on the original list with a wait list reference,
-	 * however. If we let the queue inherit that wait list reference, all we
-	 * need to do is reset the DELWRI_Q flag.
+	 * The buffer is now locked, under I/O and wait listed on the original
+	 * delwri queue. Wait for I/O completion, restore the DELWRI_Q flag and
+	 * return with the buffer unlocked and on the original queue.
 	 */
-	xfs_buf_lock(bp);
-	error = bp->b_error;
+	error = xfs_buf_iowait(bp);
 	bp->b_flags |= _XBF_DELWRI_Q;
 	xfs_buf_unlock(bp);
 
-- 
cgit v1.2.3


From 6af88cda007695af003a1cd41f077c826aa59b97 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:35 -0700
Subject: xfs: combine [a]sync buffer submission apis

The buffer I/O submission path consists of separate function calls
per type. The buffer I/O type is already controlled via buffer
state (XBF_ASYNC), however, so there is no real need for separate
submission functions.

Combine the buffer submission functions into a single function that
processes the buffer appropriately based on XBF_ASYNC. Retain an
internal helper with a conditional wait parameter to continue to
support batched !XBF_ASYNC submission/completion required by delwri
queues.

Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_buf.c         | 72 ++++++++++++++++--------------------------------
 fs/xfs/xfs_buf.h         | 10 +++++--
 fs/xfs/xfs_log_recover.c |  4 +--
 3 files changed, 33 insertions(+), 53 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index ef234847b4e6..be79dd25b8cf 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -757,11 +757,7 @@ _xfs_buf_read(
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD);
 	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
 
-	if (flags & XBF_ASYNC) {
-		xfs_buf_submit(bp);
-		return 0;
-	}
-	return xfs_buf_submit_wait(bp);
+	return xfs_buf_submit(bp);
 }
 
 xfs_buf_t *
@@ -846,7 +842,7 @@ xfs_buf_read_uncached(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = ops;
 
-	xfs_buf_submit_wait(bp);
+	xfs_buf_submit(bp);
 	if (bp->b_error) {
 		int	error = bp->b_error;
 		xfs_buf_relse(bp);
@@ -1249,7 +1245,7 @@ xfs_bwrite(
 	bp->b_flags &= ~(XBF_ASYNC | XBF_READ | _XBF_DELWRI_Q |
 			 XBF_WRITE_FAIL | XBF_DONE);
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error) {
 		xfs_force_shutdown(bp->b_target->bt_mount,
 				   SHUTDOWN_META_IO_ERROR);
@@ -1459,7 +1455,7 @@ _xfs_buf_ioapply(
  * itself.
  */
 static int
-__xfs_buf_submit(
+__xfs_buf_submit_common(
 	struct xfs_buf	*bp)
 {
 	trace_xfs_buf_submit(bp, _RET_IP_);
@@ -1505,32 +1501,6 @@ __xfs_buf_submit(
 	return 0;
 }
 
-void
-xfs_buf_submit(
-	struct xfs_buf	*bp)
-{
-	int		error;
-
-	ASSERT(bp->b_flags & XBF_ASYNC);
-
-	/*
-	 * The caller's reference is released during I/O completion.
-	 * This occurs some time after the last b_io_remaining reference is
-	 * released, so after we drop our Io reference we have to have some
-	 * other reference to ensure the buffer doesn't go away from underneath
-	 * us. Take a direct reference to ensure we have safe access to the
-	 * buffer until we are finished with it.
-	 */
-	xfs_buf_hold(bp);
-
-	error = __xfs_buf_submit(bp);
-	if (error)
-		xfs_buf_ioend(bp);
-
-	/* Note: it is not safe to reference bp now we've dropped our ref */
-	xfs_buf_rele(bp);
-}
-
 /*
  * Wait for I/O completion of a sync buffer and return the I/O error code.
  */
@@ -1538,6 +1508,8 @@ static int
 xfs_buf_iowait(
 	struct xfs_buf	*bp)
 {
+	ASSERT(!(bp->b_flags & XBF_ASYNC));
+
 	trace_xfs_buf_iowait(bp, _RET_IP_);
 	wait_for_completion(&bp->b_iowait);
 	trace_xfs_buf_iowait_done(bp, _RET_IP_);
@@ -1549,30 +1521,33 @@ xfs_buf_iowait(
  * Synchronous buffer IO submission path, read or write.
  */
 int
-xfs_buf_submit_wait(
-	struct xfs_buf	*bp)
+__xfs_buf_submit(
+	struct xfs_buf	*bp,
+	bool		wait)
 {
 	int		error;
 
-	ASSERT(!(bp->b_flags & XBF_ASYNC));
-
 	/*
-	 * For synchronous IO, the IO does not inherit the submitters reference
-	 * count, nor the buffer lock. Hence we cannot release the reference we
-	 * are about to take until we've waited for all IO completion to occur,
-	 * including any xfs_buf_ioend_async() work that may be pending.
+	 * Grab a reference so the buffer does not go away underneath us. For
+	 * async buffers, I/O completion drops the callers reference, which
+	 * could occur before submission returns.
 	 */
 	xfs_buf_hold(bp);
 
-	error = __xfs_buf_submit(bp);
-	if (error)
+	error = __xfs_buf_submit_common(bp);
+	if (error) {
+		if (bp->b_flags & XBF_ASYNC)
+			xfs_buf_ioend(bp);
 		goto out;
-	error = xfs_buf_iowait(bp);
+	}
 
+	if (wait)
+		error = xfs_buf_iowait(bp);
 out:
 	/*
-	 * all done now, we can release the hold that keeps the buffer
-	 * referenced for the entire IO.
+	 * Release the hold that keeps the buffer referenced for the entire
+	 * I/O. Note that if the buffer is async, it is not safe to reference
+	 * after this release.
 	 */
 	xfs_buf_rele(bp);
 	return error;
@@ -2026,12 +2001,11 @@ xfs_buf_delwri_submit_buffers(
 		if (wait_list) {
 			bp->b_flags &= ~XBF_ASYNC;
 			list_move_tail(&bp->b_list, wait_list);
-			__xfs_buf_submit(bp);
 		} else {
 			bp->b_flags |= XBF_ASYNC;
 			list_del_init(&bp->b_list);
-			xfs_buf_submit(bp);
 		}
+		__xfs_buf_submit(bp, false);
 	}
 	blk_finish_plug(&plug);
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 6ddf1907fc7a..f04613181ca1 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -297,8 +297,14 @@ extern void __xfs_buf_ioerror(struct xfs_buf *bp, int error,
 		xfs_failaddr_t failaddr);
 #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
 extern void xfs_buf_ioerror_alert(struct xfs_buf *, const char *func);
-extern void xfs_buf_submit(struct xfs_buf *bp);
-extern int xfs_buf_submit_wait(struct xfs_buf *bp);
+
+extern int __xfs_buf_submit(struct xfs_buf *bp, bool);
+static inline int xfs_buf_submit(struct xfs_buf *bp)
+{
+	bool wait = bp->b_flags & XBF_ASYNC ? false : true;
+	return __xfs_buf_submit(bp, wait);
+}
+
 extern void xfs_buf_iomove(xfs_buf_t *, size_t, size_t, void *,
 				xfs_buf_rw_t);
 #define xfs_buf_zero(bp, off, len) \
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 8317023293a5..cbac943896f4 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -196,7 +196,7 @@ xlog_bread_noalign(
 	bp->b_io_length = nbblks;
 	bp->b_error = 0;
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error && !XFS_FORCED_SHUTDOWN(log->l_mp))
 		xfs_buf_ioerror_alert(bp, __func__);
 	return error;
@@ -5706,7 +5706,7 @@ xlog_do_recover(
 	bp->b_flags |= XBF_READ;
 	bp->b_ops = &xfs_sb_buf_ops;
 
-	error = xfs_buf_submit_wait(bp);
+	error = xfs_buf_submit(bp);
 	if (error) {
 		if (!XFS_FORCED_SHUTDOWN(mp)) {
 			xfs_buf_ioerror_alert(bp, __func__);
-- 
cgit v1.2.3


From bb00b6f1e2b9699f6140849ab3d6a252b130f44e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 11 Jul 2018 22:26:35 -0700
Subject: xfs: kill __xfs_buf_submit_common()

Now that there is only one caller, fold the common submission helper
into __xfs_buf_submit().

Suggested-by: Christoph Hellwig <hch@infradead.org>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_buf.c | 83 +++++++++++++++++++++++---------------------------------
 1 file changed, 34 insertions(+), 49 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index be79dd25b8cf..c641c7fa1a03 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1449,15 +1449,34 @@ _xfs_buf_ioapply(
 }
 
 /*
- * Asynchronous IO submission path. This transfers the buffer lock ownership and
- * the current reference to the IO. It is not safe to reference the buffer after
- * a call to this function unless the caller holds an additional reference
- * itself.
+ * Wait for I/O completion of a sync buffer and return the I/O error code.
  */
 static int
-__xfs_buf_submit_common(
+xfs_buf_iowait(
 	struct xfs_buf	*bp)
 {
+	ASSERT(!(bp->b_flags & XBF_ASYNC));
+
+	trace_xfs_buf_iowait(bp, _RET_IP_);
+	wait_for_completion(&bp->b_iowait);
+	trace_xfs_buf_iowait_done(bp, _RET_IP_);
+
+	return bp->b_error;
+}
+
+/*
+ * Buffer I/O submission path, read or write. Asynchronous submission transfers
+ * the buffer lock ownership and the current reference to the IO. It is not
+ * safe to reference the buffer after a call to this function unless the caller
+ * holds an additional reference itself.
+ */
+int
+__xfs_buf_submit(
+	struct xfs_buf	*bp,
+	bool		wait)
+{
+	int		error = 0;
+
 	trace_xfs_buf_submit(bp, _RET_IP_);
 
 	ASSERT(!(bp->b_flags & _XBF_DELWRI_Q));
@@ -1467,9 +1486,18 @@ __xfs_buf_submit_common(
 		xfs_buf_ioerror(bp, -EIO);
 		bp->b_flags &= ~XBF_DONE;
 		xfs_buf_stale(bp);
+		if (bp->b_flags & XBF_ASYNC)
+			xfs_buf_ioend(bp);
 		return -EIO;
 	}
 
+	/*
+	 * Grab a reference so the buffer does not go away underneath us. For
+	 * async buffers, I/O completion drops the callers reference, which
+	 * could occur before submission returns.
+	 */
+	xfs_buf_hold(bp);
+
 	if (bp->b_flags & XBF_WRITE)
 		xfs_buf_wait_unpin(bp);
 
@@ -1498,52 +1526,9 @@ __xfs_buf_submit_common(
 			xfs_buf_ioend_async(bp);
 	}
 
-	return 0;
-}
-
-/*
- * Wait for I/O completion of a sync buffer and return the I/O error code.
- */
-static int
-xfs_buf_iowait(
-	struct xfs_buf	*bp)
-{
-	ASSERT(!(bp->b_flags & XBF_ASYNC));
-
-	trace_xfs_buf_iowait(bp, _RET_IP_);
-	wait_for_completion(&bp->b_iowait);
-	trace_xfs_buf_iowait_done(bp, _RET_IP_);
-
-	return bp->b_error;
-}
-
-/*
- * Synchronous buffer IO submission path, read or write.
- */
-int
-__xfs_buf_submit(
-	struct xfs_buf	*bp,
-	bool		wait)
-{
-	int		error;
-
-	/*
-	 * Grab a reference so the buffer does not go away underneath us. For
-	 * async buffers, I/O completion drops the callers reference, which
-	 * could occur before submission returns.
-	 */
-	xfs_buf_hold(bp);
-
-	error = __xfs_buf_submit_common(bp);
-	if (error) {
-		if (bp->b_flags & XBF_ASYNC)
-			xfs_buf_ioend(bp);
-		goto out;
-	}
-
 	if (wait)
 		error = xfs_buf_iowait(bp);
-out:
+
 	/*
 	 * Release the hold that keeps the buffer referenced for the entire
 	 * I/O. Note that if the buffer is async, it is not safe to reference
-- 
cgit v1.2.3


From a4722a643fbb9e1466491fbe5a3c44591805dcc8 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Wed, 11 Jul 2018 22:26:36 -0700
Subject: xfs: remove unused iolock arg from xfs_break_dax_layouts

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_file.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index a3e7767a5715..6b31f41eafa2 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -735,7 +735,6 @@ xfs_wait_dax_page(
 static int
 xfs_break_dax_layouts(
 	struct inode		*inode,
-	uint			iolock,
 	bool			*did_unlock)
 {
 	struct page		*page;
@@ -766,7 +765,7 @@ xfs_break_layouts(
 		retry = false;
 		switch (reason) {
 		case BREAK_UNMAP:
-			error = xfs_break_dax_layouts(inode, *iolock, &retry);
+			error = xfs_break_dax_layouts(inode, &retry);
 			if (error || retry)
 				break;
 			/* fall through */
-- 
cgit v1.2.3


From efe803277364a621348b679058222d644e113c9c Mon Sep 17 00:00:00 2001
From: Carlos Maiolino <cmaiolino@redhat.com>
Date: Wed, 11 Jul 2018 22:26:36 -0700
Subject: xfs: Initialize variables in xfs_alloc_get_rec before using them

Make sure we initialize *bno and *len, before jumping to out_bad_rec
label, and risk calling xfs_warn() with uninitialized variables.

Coverity: 100898
Coverity: 1437081
Coverity: 1437129
Coverity: 1437191
Coverity: 1437201
Coverity: 1437212
Coverity: 1437341
Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index bd6d8aeea825..3c3f2d5119ea 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -223,12 +223,13 @@ xfs_alloc_get_rec(
 	error = xfs_btree_get_rec(cur, &rec, stat);
 	if (error || !(*stat))
 		return error;
-	if (rec->alloc.ar_blockcount == 0)
-		goto out_bad_rec;
 
 	*bno = be32_to_cpu(rec->alloc.ar_startblock);
 	*len = be32_to_cpu(rec->alloc.ar_blockcount);
 
+	if (*len == 0)
+		goto out_bad_rec;
+
 	/* check for valid extent range, including overflow */
 	if (!xfs_verify_agbno(mp, agno, *bno))
 		goto out_bad_rec;
-- 
cgit v1.2.3


From 5e9a0fe492f89ff1c7583ee6ea89dc37b8c2e5c2 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Mon, 9 Jul 2018 02:26:20 +0000
Subject: net/sched: flower: Fix null pointer dereference when run tc vlan
 command

Zahari issued tc vlan command without setting vlan_ethtype, which will
crash kernel. To avoid this, we must check tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]
is not null before use it.
Also we don't need to dump vlan_ethtype or cvlan_ethtype in this case.

Fixes: d64efd0926ba ('net/sched: flower: Add supprt for matching on QinQ vlan headers')
Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reported-by: Zahari Doychev <zahari.doychev@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 48 ++++++++++++++++++++++++++----------------------
 1 file changed, 26 insertions(+), 22 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 487a152a852c..8b2474293db1 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -605,20 +605,22 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 					TCA_FLOWER_KEY_VLAN_PRIO, &key->vlan,
 					&mask->vlan);
 
-			ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
-			if (eth_type_vlan(ethertype)) {
-				fl_set_key_vlan(tb, ethertype,
-						TCA_FLOWER_KEY_CVLAN_ID,
-						TCA_FLOWER_KEY_CVLAN_PRIO,
-						&key->cvlan, &mask->cvlan);
-				fl_set_key_val(tb, &key->basic.n_proto,
-					       TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
-					       &mask->basic.n_proto,
-					       TCA_FLOWER_UNSPEC,
-					       sizeof(key->basic.n_proto));
-			} else {
-				key->basic.n_proto = ethertype;
-				mask->basic.n_proto = cpu_to_be16(~0);
+			if (tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]) {
+				ethertype = nla_get_be16(tb[TCA_FLOWER_KEY_VLAN_ETH_TYPE]);
+				if (eth_type_vlan(ethertype)) {
+					fl_set_key_vlan(tb, ethertype,
+							TCA_FLOWER_KEY_CVLAN_ID,
+							TCA_FLOWER_KEY_CVLAN_PRIO,
+							&key->cvlan, &mask->cvlan);
+					fl_set_key_val(tb, &key->basic.n_proto,
+						       TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
+						       &mask->basic.n_proto,
+						       TCA_FLOWER_UNSPEC,
+						       sizeof(key->basic.n_proto));
+				} else {
+					key->basic.n_proto = ethertype;
+					mask->basic.n_proto = cpu_to_be16(~0);
+				}
 			}
 		} else {
 			key->basic.n_proto = ethertype;
@@ -1344,14 +1346,16 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 			 key->cvlan.vlan_tpid)))
 		goto nla_put_failure;
 
-	if (mask->cvlan.vlan_tpid) {
-		if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
-				 key->basic.n_proto))
-			goto nla_put_failure;
-	} else if (mask->vlan.vlan_tpid) {
-		if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
-				 key->basic.n_proto))
-			goto nla_put_failure;
+	if (mask->basic.n_proto) {
+		if (mask->cvlan.vlan_tpid) {
+			if (nla_put_be16(skb, TCA_FLOWER_KEY_CVLAN_ETH_TYPE,
+					 key->basic.n_proto))
+				goto nla_put_failure;
+		} else if (mask->vlan.vlan_tpid) {
+			if (nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+					 key->basic.n_proto))
+				goto nla_put_failure;
+		}
 	}
 
 	if ((key->basic.n_proto == htons(ETH_P_IP) ||
-- 
cgit v1.2.3


From c6dbf7aaa48289d2eeacbef06785c069869ed0c0 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Jul 2018 12:25:14 +0200
Subject: net/ipv6: fix addrconf_sysctl_addr_gen_mode

addrconf_sysctl_addr_gen_mode() has multiple problems. First, it ignores
the errors returned by proc_dointvec().

addrconf_sysctl_addr_gen_mode() calls proc_dointvec() directly, which
writes the value to memory, and then checks if it's valid and may return
EINVAL. If a bad value is given, the value displayed when reading
net.ipv6.conf.foo.addr_gen_mode next time will be invalid. In case the
value provided by the user was valid, addrconf_dev_config() won't be
called since idev->cnf.addr_gen_mode has already been updated.

Fix this in the usual way we deal with values that need to be checked
after the proc_do*() helper has returned: define a local ctl_table and
storage, call proc_dointvec() on that temporary area, then check and
store.

addrconf_sysctl_addr_gen_mode() also writes the new value to the global
ipv6_devconf_dflt, when we're writing to some netns's default, so that
new netns will inherit the value that was set by the change occuring in
any netns. That doesn't make any sense, so let's drop this assignment.

Finally, since addr_gen_mode is a __u32, switch to proc_douintvec().

Fixes: d35a00b8e33d ("net/ipv6: allow sysctl to change link-local address generation mode")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 27 ++++++++++++++-------------
 1 file changed, 14 insertions(+), 13 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 91580c62bb86..e9ba53d2a147 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5892,32 +5892,31 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
 					 loff_t *ppos)
 {
 	int ret = 0;
-	int new_val;
+	u32 new_val;
 	struct inet6_dev *idev = (struct inet6_dev *)ctl->extra1;
 	struct net *net = (struct net *)ctl->extra2;
+	struct ctl_table tmp = {
+		.data = &new_val,
+		.maxlen = sizeof(new_val),
+		.mode = ctl->mode,
+	};
 
 	if (!rtnl_trylock())
 		return restart_syscall();
 
-	ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
+	new_val = *((u32 *)ctl->data);
 
-	if (write) {
-		new_val = *((int *)ctl->data);
+	ret = proc_douintvec(&tmp, write, buffer, lenp, ppos);
+	if (ret != 0)
+		goto out;
 
+	if (write) {
 		if (check_addr_gen_mode(new_val) < 0) {
 			ret = -EINVAL;
 			goto out;
 		}
 
-		/* request for default */
-		if (&net->ipv6.devconf_dflt->addr_gen_mode == ctl->data) {
-			ipv6_devconf_dflt.addr_gen_mode = new_val;
-
-		/* request for individual net device */
-		} else {
-			if (!idev)
-				goto out;
-
+		if (idev) {
 			if (check_stable_privacy(idev, net, new_val) < 0) {
 				ret = -EINVAL;
 				goto out;
@@ -5928,6 +5927,8 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
 				addrconf_dev_config(idev->dev);
 			}
 		}
+
+		*((u32 *)ctl->data) = new_val;
 	}
 
 out:
-- 
cgit v1.2.3


From 70c30d76e580fe4aefe6facdf0f1edb1aa9a0e7a Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Jul 2018 12:25:15 +0200
Subject: net/ipv6: don't reinitialize ndev->cnf.addr_gen_mode on new inet6_dev

The value has already been copied from this netns's devconf_dflt, it
shouldn't be reset to the global kernel default.

Fixes: d35a00b8e33d ("net/ipv6: allow sysctl to change link-local address generation mode")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e9ba53d2a147..e20f8a1d8cdb 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -385,8 +385,6 @@ static struct inet6_dev *ipv6_add_dev(struct net_device *dev)
 
 	if (ndev->cnf.stable_secret.initialized)
 		ndev->cnf.addr_gen_mode = IN6_ADDR_GEN_MODE_STABLE_PRIVACY;
-	else
-		ndev->cnf.addr_gen_mode = ipv6_devconf_dflt.addr_gen_mode;
 
 	ndev->cnf.mtu6 = dev->mtu;
 	ndev->nd_parms = neigh_parms_alloc(dev, &nd_tbl);
-- 
cgit v1.2.3


From bdd72f41333d9f61a22e4c4494e95782e9731fdb Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Jul 2018 12:25:16 +0200
Subject: net/ipv6: reserve room for IFLA_INET6_ADDR_GEN_MODE

inet6_ifla6_size() is called to check how much space is needed by
inet6_fill_link_af() and inet6_fill_ifinfo(), both of which include
the IFLA_INET6_ADDR_GEN_MODE attribute. Reserve some room for it.

Fixes: bc91b0f07ada ("ipv6: addrconf: implement address generation modes")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e20f8a1d8cdb..e89bca83e0e4 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5208,7 +5208,9 @@ static inline size_t inet6_ifla6_size(void)
 	     + nla_total_size(DEVCONF_MAX * 4) /* IFLA_INET6_CONF */
 	     + nla_total_size(IPSTATS_MIB_MAX * 8) /* IFLA_INET6_STATS */
 	     + nla_total_size(ICMP6_MIB_MAX * 8) /* IFLA_INET6_ICMP6STATS */
-	     + nla_total_size(sizeof(struct in6_addr)); /* IFLA_INET6_TOKEN */
+	     + nla_total_size(sizeof(struct in6_addr)) /* IFLA_INET6_TOKEN */
+	     + nla_total_size(1) /* IFLA_INET6_ADDR_GEN_MODE */
+	     + 0;
 }
 
 static inline size_t inet6_if_nlmsg_size(void)
-- 
cgit v1.2.3


From f24c5987dddd28b23443e7b21b55d47549207755 Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Jul 2018 12:25:17 +0200
Subject: net/ipv6: propagate net.ipv6.conf.all.addr_gen_mode to devices

This aligns the addr_gen_mode sysctl with the expected behavior of the
"all" variant.

Fixes: d35a00b8e33d ("net/ipv6: allow sysctl to change link-local address generation mode")
Suggested-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/addrconf.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index e89bca83e0e4..1659a6b3cf42 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5926,6 +5926,18 @@ static int addrconf_sysctl_addr_gen_mode(struct ctl_table *ctl, int write,
 				idev->cnf.addr_gen_mode = new_val;
 				addrconf_dev_config(idev->dev);
 			}
+		} else if (&net->ipv6.devconf_all->addr_gen_mode == ctl->data) {
+			struct net_device *dev;
+
+			net->ipv6.devconf_dflt->addr_gen_mode = new_val;
+			for_each_netdev(net, dev) {
+				idev = __in6_dev_get(dev);
+				if (idev &&
+				    idev->cnf.addr_gen_mode != new_val) {
+					idev->cnf.addr_gen_mode = new_val;
+					addrconf_dev_config(idev->dev);
+				}
+			}
 		}
 
 		*((u32 *)ctl->data) = new_val;
-- 
cgit v1.2.3


From f168db5e25f762b96d00ffd8c3908cf4066741dd Mon Sep 17 00:00:00 2001
From: Sabrina Dubroca <sd@queasysnail.net>
Date: Mon, 9 Jul 2018 12:25:18 +0200
Subject: Documentation: ip-sysctl.txt: document addr_gen_mode

addr_gen_mode was introduced in without documentation, add it now.

Fixes: d35a00b8e33d ("net/ipv6: allow sysctl to change link-local address generation mode")
Signed-off-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index f4c042be0216..77c37fb0b6a6 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1834,6 +1834,16 @@ stable_secret - IPv6 address
 
 	By default the stable secret is unset.
 
+addr_gen_mode - INTEGER
+	Defines how link-local and autoconf addresses are generated.
+
+	0: generate address based on EUI64 (default)
+	1: do no generate a link-local address, use EUI64 for addresses generated
+	   from autoconf
+	2: generate stable privacy addresses, using the secret from
+	   stable_secret (RFC7217)
+	3: generate stable privacy addresses, using a random secret if unset
+
 drop_unicast_in_l2_multicast - BOOLEAN
 	Drop any unicast IPv6 packets that are received in link-layer
 	multicast (or broadcast) frames.
-- 
cgit v1.2.3


From 8dce04f1fd64ce5cf03e942d7644967890ae4483 Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Mon, 9 Jul 2018 16:52:03 +0530
Subject: cxgb4: specify IQTYPE in fw_iq_cmd

congestion argument passed to t4_sge_alloc_rxq() is used
to differentiate between nic/ofld queues.

Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/sge.c      |  4 +++-
 drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h | 12 ++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c
index ebb46c472d52..6807bc3a44fb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/sge.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c
@@ -3412,7 +3412,9 @@ int t4_sge_alloc_rxq(struct adapter *adap, struct sge_rspq *iq, bool fwevtq,
 	c.iqsize = htons(iq->size);
 	c.iqaddr = cpu_to_be64(iq->phys_addr);
 	if (cong >= 0)
-		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F);
+		c.iqns_to_fl0congen = htonl(FW_IQ_CMD_IQFLINTCONGEN_F |
+				FW_IQ_CMD_IQTYPE_V(cong ? FW_IQ_IQTYPE_NIC
+							:  FW_IQ_IQTYPE_OFLD));
 
 	if (fl) {
 		enum chip_type chip = CHELSIO_CHIP_VERSION(adap->params.chip);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
index f1967cf6d43c..5dc6c4154af8 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h
@@ -1472,6 +1472,12 @@ enum fw_iq_type {
 	FW_IQ_TYPE_NO_FL_INT_CAP
 };
 
+enum fw_iq_iqtype {
+	FW_IQ_IQTYPE_OTHER,
+	FW_IQ_IQTYPE_NIC,
+	FW_IQ_IQTYPE_OFLD,
+};
+
 struct fw_iq_cmd {
 	__be32 op_to_vfn;
 	__be32 alloc_to_len16;
@@ -1586,6 +1592,12 @@ struct fw_iq_cmd {
 #define FW_IQ_CMD_IQFLINTISCSIC_S	26
 #define FW_IQ_CMD_IQFLINTISCSIC_V(x)	((x) << FW_IQ_CMD_IQFLINTISCSIC_S)
 
+#define FW_IQ_CMD_IQTYPE_S		24
+#define FW_IQ_CMD_IQTYPE_M		0x3
+#define FW_IQ_CMD_IQTYPE_V(x)		((x) << FW_IQ_CMD_IQTYPE_S)
+#define FW_IQ_CMD_IQTYPE_G(x)		\
+	(((x) >> FW_IQ_CMD_IQTYPE_S) & FW_IQ_CMD_IQTYPE_M)
+
 #define FW_IQ_CMD_FL0CNGCHMAP_S		20
 #define FW_IQ_CMD_FL0CNGCHMAP_V(x)	((x) << FW_IQ_CMD_FL0CNGCHMAP_S)
 
-- 
cgit v1.2.3


From 01e866bf07fbb10e96bff46ea1e5e0410d6e40b9 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Mon, 9 Jul 2018 14:33:26 +0300
Subject: net: sched: act_ife: fix memory leak in ife init

Free params if tcf_idr_check_alloc() returned error.

Fixes: 0190c1d452a9 ("net: sched: atomically check-allocate action")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index a3eef00cd711..3d6e265758c0 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -485,8 +485,10 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 		return -ENOMEM;
 
 	err = tcf_idr_check_alloc(tn, &parm->index, a, bind);
-	if (err < 0)
+	if (err < 0) {
+		kfree(p);
 		return err;
+	}
 	exists = err;
 	if (exists && bind) {
 		kfree(p);
-- 
cgit v1.2.3


From 3c546728df983c3c1c232241249c238c143bcb9e Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 9 Jul 2018 13:23:13 +0100
Subject: wimax/i2400m: remove redundant variables ack_status, bcf and protocol

Variables ack_status, bcf and protocol are being assigned but are
never used hence they are redundant and can be removed.

Also declare ack_type as unsigned int rather than unsigned to clean
up a checkpatch warning.

Cleans up clang warnings:
warning: variable 'ack_status' set but not used [-Wunused-but-set-variable]
warning: variable 'bcf' set but not used [-Wunused-but-set-variable]
warning: variable 'protocol' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wimax/i2400m/control.c | 3 +--
 drivers/net/wimax/i2400m/fw.c      | 3 +--
 drivers/net/wimax/i2400m/netdev.c  | 2 --
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wimax/i2400m/control.c b/drivers/net/wimax/i2400m/control.c
index 4c417903e9be..094cea775d0c 100644
--- a/drivers/net/wimax/i2400m/control.c
+++ b/drivers/net/wimax/i2400m/control.c
@@ -566,13 +566,12 @@ static void i2400m_msg_ack_hook(struct i2400m *i2400m,
 {
 	int result;
 	struct device *dev = i2400m_dev(i2400m);
-	unsigned ack_type, ack_status;
+	unsigned int ack_type;
 	char strerr[32];
 
 	/* Chew on the message, we might need some information from
 	 * here */
 	ack_type = le16_to_cpu(l3l4_hdr->type);
-	ack_status = le16_to_cpu(l3l4_hdr->status);
 	switch (ack_type) {
 	case I2400M_MT_CMD_ENTER_POWERSAVE:
 		/* This is just left here for the sake of example, as
diff --git a/drivers/net/wimax/i2400m/fw.c b/drivers/net/wimax/i2400m/fw.c
index a89b5685e68b..e9fc168bb734 100644
--- a/drivers/net/wimax/i2400m/fw.c
+++ b/drivers/net/wimax/i2400m/fw.c
@@ -1552,7 +1552,6 @@ int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
 	int ret, itr;
 	struct device *dev = i2400m_dev(i2400m);
 	struct i2400m_fw *i2400m_fw;
-	const struct i2400m_bcf_hdr *bcf;	/* Firmware data */
 	const struct firmware *fw;
 	const char *fw_name;
 
@@ -1574,7 +1573,7 @@ int i2400m_dev_bootstrap(struct i2400m *i2400m, enum i2400m_bri flags)
 	}
 
 	/* Load firmware files to memory. */
-	for (itr = 0, bcf = NULL, ret = -ENOENT; ; itr++) {
+	for (itr = 0, ret = -ENOENT; ; itr++) {
 		fw_name = i2400m->bus_fw_names[itr];
 		if (fw_name == NULL) {
 			dev_err(dev, "Could not find a usable firmware image\n");
diff --git a/drivers/net/wimax/i2400m/netdev.c b/drivers/net/wimax/i2400m/netdev.c
index a654687b5fa2..9ab3f0fdfea4 100644
--- a/drivers/net/wimax/i2400m/netdev.c
+++ b/drivers/net/wimax/i2400m/netdev.c
@@ -535,14 +535,12 @@ void i2400m_net_erx(struct i2400m *i2400m, struct sk_buff *skb,
 {
 	struct net_device *net_dev = i2400m->wimax_dev.net_dev;
 	struct device *dev = i2400m_dev(i2400m);
-	int protocol;
 
 	d_fnstart(2, dev, "(i2400m %p skb %p [%u] cs %d)\n",
 		  i2400m, skb, skb->len, cs);
 	switch(cs) {
 	case I2400M_CS_IPV4_0:
 	case I2400M_CS_IPV4:
-		protocol = ETH_P_IP;
 		i2400m_rx_fake_eth_header(i2400m->wimax_dev.net_dev,
 					  skb->data - ETH_HLEN,
 					  cpu_to_be16(ETH_P_IP));
-- 
cgit v1.2.3


From fb8ed3af74e3fc0ae1c72b363af2f0d7783e1cd5 Mon Sep 17 00:00:00 2001
From: Jan Dakinevich <jan.dakinevich@virtuozzo.com>
Date: Mon, 9 Jul 2018 16:51:19 +0300
Subject: cnic: use kvzalloc to allocate memory for csk_tbl

Size of csk_tbl is about 58K, which means 3rd order page allocation.
kvzalloc provides a fallback if no high order memory is available.

Signed-off-by: Jan Dakinevich <jan.dakinevich@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/cnic.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c
index 2369b2f0d95a..d83233ae4a15 100644
--- a/drivers/net/ethernet/broadcom/cnic.c
+++ b/drivers/net/ethernet/broadcom/cnic.c
@@ -4088,7 +4088,7 @@ static void cnic_cm_free_mem(struct cnic_dev *dev)
 {
 	struct cnic_local *cp = dev->cnic_priv;
 
-	kfree(cp->csk_tbl);
+	kvfree(cp->csk_tbl);
 	cp->csk_tbl = NULL;
 	cnic_free_id_tbl(&cp->csk_port_tbl);
 }
@@ -4098,8 +4098,8 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev)
 	struct cnic_local *cp = dev->cnic_priv;
 	u32 port_id;
 
-	cp->csk_tbl = kcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock),
-			      GFP_KERNEL);
+	cp->csk_tbl = kvcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock),
+			       GFP_KERNEL);
 	if (!cp->csk_tbl)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From b32b088181b96035e187cdd4a69813f04ba20380 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Mon, 9 Jul 2018 17:00:43 +0200
Subject: net: mvpp2: explicitly include linux/interrupt.h

The Marvell PPv2 driver uses interrupts and tasklet but does not
explicitly include linux/interrupt.h, relying on implicit includes. This
one particularly is included by chance after a long unlogical chain of
inclusions. Fix this so we do not get future build breaks.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 81a66cce7fa8..18834619bb3a 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -12,6 +12,7 @@
 #ifndef _MVPP2_H_
 #define _MVPP2_H_
 
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/phy.h>
-- 
cgit v1.2.3


From b351b16d8aa75856592d47600d6b3c6abee7ecbd Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Mon, 9 Jul 2018 21:42:46 +0530
Subject: cxgb4: remove stats fetched from firmware

When running ethtool -S, some stats are requested from firmware.
Since getting these stats via firmware mailbox is slow, some packets
get dropped under heavy load while running ethtool -S.

So, remove these stats from ethtool -S.

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 133 ---------------------
 1 file changed, 133 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index ddb8b9eba6bf..a14a290a56ee 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -115,42 +115,10 @@ static char adapter_stats_strings[][ETH_GSTRING_LEN] = {
 	"db_drop                ",
 	"db_full                ",
 	"db_empty               ",
-	"tcp_ipv4_out_rsts      ",
-	"tcp_ipv4_in_segs       ",
-	"tcp_ipv4_out_segs      ",
-	"tcp_ipv4_retrans_segs  ",
-	"tcp_ipv6_out_rsts      ",
-	"tcp_ipv6_in_segs       ",
-	"tcp_ipv6_out_segs      ",
-	"tcp_ipv6_retrans_segs  ",
-	"usm_ddp_frames         ",
-	"usm_ddp_octets         ",
-	"usm_ddp_drops          ",
-	"rdma_no_rqe_mod_defer  ",
-	"rdma_no_rqe_pkt_defer  ",
-	"tp_err_ofld_no_neigh   ",
-	"tp_err_ofld_cong_defer ",
 	"write_coal_success     ",
 	"write_coal_fail        ",
 };
 
-static char channel_stats_strings[][ETH_GSTRING_LEN] = {
-	"--------Channel--------- ",
-	"tp_cpl_requests        ",
-	"tp_cpl_responses       ",
-	"tp_mac_in_errs         ",
-	"tp_hdr_in_errs         ",
-	"tp_tcp_in_errs         ",
-	"tp_tcp6_in_errs        ",
-	"tp_tnl_cong_drops      ",
-	"tp_tnl_tx_drops        ",
-	"tp_ofld_vlan_drops     ",
-	"tp_ofld_chan_drops     ",
-	"fcoe_octets_ddp        ",
-	"fcoe_frames_ddp        ",
-	"fcoe_frames_drop       ",
-};
-
 static char loopback_stats_strings[][ETH_GSTRING_LEN] = {
 	"-------Loopback----------- ",
 	"octets_ok              ",
@@ -187,7 +155,6 @@ static int get_sset_count(struct net_device *dev, int sset)
 	case ETH_SS_STATS:
 		return ARRAY_SIZE(stats_strings) +
 		       ARRAY_SIZE(adapter_stats_strings) +
-		       ARRAY_SIZE(channel_stats_strings) +
 		       ARRAY_SIZE(loopback_stats_strings);
 	case ETH_SS_PRIV_FLAGS:
 		return ARRAY_SIZE(cxgb4_priv_flags_strings);
@@ -252,9 +219,6 @@ static void get_strings(struct net_device *dev, u32 stringset, u8 *data)
 		memcpy(data, adapter_stats_strings,
 		       sizeof(adapter_stats_strings));
 		data += sizeof(adapter_stats_strings);
-		memcpy(data, channel_stats_strings,
-		       sizeof(channel_stats_strings));
-		data += sizeof(channel_stats_strings);
 		memcpy(data, loopback_stats_strings,
 		       sizeof(loopback_stats_strings));
 	} else if (stringset == ETH_SS_PRIV_FLAGS) {
@@ -280,41 +244,10 @@ struct adapter_stats {
 	u64 db_drop;
 	u64 db_full;
 	u64 db_empty;
-	u64 tcp_v4_out_rsts;
-	u64 tcp_v4_in_segs;
-	u64 tcp_v4_out_segs;
-	u64 tcp_v4_retrans_segs;
-	u64 tcp_v6_out_rsts;
-	u64 tcp_v6_in_segs;
-	u64 tcp_v6_out_segs;
-	u64 tcp_v6_retrans_segs;
-	u64 frames;
-	u64 octets;
-	u64 drops;
-	u64 rqe_dfr_mod;
-	u64 rqe_dfr_pkt;
-	u64 ofld_no_neigh;
-	u64 ofld_cong_defer;
 	u64 wc_success;
 	u64 wc_fail;
 };
 
-struct channel_stats {
-	u64 cpl_req;
-	u64 cpl_rsp;
-	u64 mac_in_errs;
-	u64 hdr_in_errs;
-	u64 tcp_in_errs;
-	u64 tcp6_in_errs;
-	u64 tnl_cong_drops;
-	u64 tnl_tx_drops;
-	u64 ofld_vlan_drops;
-	u64 ofld_chan_drops;
-	u64 octets_ddp;
-	u64 frames_ddp;
-	u64 frames_drop;
-};
-
 static void collect_sge_port_stats(const struct adapter *adap,
 				   const struct port_info *p,
 				   struct queue_port_stats *s)
@@ -337,45 +270,14 @@ static void collect_sge_port_stats(const struct adapter *adap,
 
 static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
 {
-	struct tp_tcp_stats v4, v6;
-	struct tp_rdma_stats rdma_stats;
-	struct tp_err_stats err_stats;
-	struct tp_usm_stats usm_stats;
 	u64 val1, val2;
 
 	memset(s, 0, sizeof(*s));
 
-	spin_lock(&adap->stats_lock);
-	t4_tp_get_tcp_stats(adap, &v4, &v6, false);
-	t4_tp_get_rdma_stats(adap, &rdma_stats, false);
-	t4_get_usm_stats(adap, &usm_stats, false);
-	t4_tp_get_err_stats(adap, &err_stats, false);
-	spin_unlock(&adap->stats_lock);
-
 	s->db_drop = adap->db_stats.db_drop;
 	s->db_full = adap->db_stats.db_full;
 	s->db_empty = adap->db_stats.db_empty;
 
-	s->tcp_v4_out_rsts = v4.tcp_out_rsts;
-	s->tcp_v4_in_segs = v4.tcp_in_segs;
-	s->tcp_v4_out_segs = v4.tcp_out_segs;
-	s->tcp_v4_retrans_segs = v4.tcp_retrans_segs;
-	s->tcp_v6_out_rsts = v6.tcp_out_rsts;
-	s->tcp_v6_in_segs = v6.tcp_in_segs;
-	s->tcp_v6_out_segs = v6.tcp_out_segs;
-	s->tcp_v6_retrans_segs = v6.tcp_retrans_segs;
-
-	if (is_offload(adap)) {
-		s->frames = usm_stats.frames;
-		s->octets = usm_stats.octets;
-		s->drops = usm_stats.drops;
-		s->rqe_dfr_mod = rdma_stats.rqe_dfr_mod;
-		s->rqe_dfr_pkt = rdma_stats.rqe_dfr_pkt;
-	}
-
-	s->ofld_no_neigh = err_stats.ofld_no_neigh;
-	s->ofld_cong_defer = err_stats.ofld_cong_defer;
-
 	if (!is_t4(adap->params.chip)) {
 		int v;
 
@@ -389,36 +291,6 @@ static void collect_adapter_stats(struct adapter *adap, struct adapter_stats *s)
 	}
 }
 
-static void collect_channel_stats(struct adapter *adap, struct channel_stats *s,
-				  u8 i)
-{
-	struct tp_cpl_stats cpl_stats;
-	struct tp_err_stats err_stats;
-	struct tp_fcoe_stats fcoe_stats;
-
-	memset(s, 0, sizeof(*s));
-
-	spin_lock(&adap->stats_lock);
-	t4_tp_get_cpl_stats(adap, &cpl_stats, false);
-	t4_tp_get_err_stats(adap, &err_stats, false);
-	t4_get_fcoe_stats(adap, i, &fcoe_stats, false);
-	spin_unlock(&adap->stats_lock);
-
-	s->cpl_req = cpl_stats.req[i];
-	s->cpl_rsp = cpl_stats.rsp[i];
-	s->mac_in_errs = err_stats.mac_in_errs[i];
-	s->hdr_in_errs = err_stats.hdr_in_errs[i];
-	s->tcp_in_errs = err_stats.tcp_in_errs[i];
-	s->tcp6_in_errs = err_stats.tcp6_in_errs[i];
-	s->tnl_cong_drops = err_stats.tnl_cong_drops[i];
-	s->tnl_tx_drops = err_stats.tnl_tx_drops[i];
-	s->ofld_vlan_drops = err_stats.ofld_vlan_drops[i];
-	s->ofld_chan_drops = err_stats.ofld_chan_drops[i];
-	s->octets_ddp = fcoe_stats.octets_ddp;
-	s->frames_ddp = fcoe_stats.frames_ddp;
-	s->frames_drop = fcoe_stats.frames_drop;
-}
-
 static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
 		      u64 *data)
 {
@@ -438,11 +310,6 @@ static void get_stats(struct net_device *dev, struct ethtool_stats *stats,
 	collect_adapter_stats(adapter, (struct adapter_stats *)data);
 	data += sizeof(struct adapter_stats) / sizeof(u64);
 
-	*data++ = (u64)pi->port_id;
-	collect_channel_stats(adapter, (struct channel_stats *)data,
-			      pi->port_id);
-	data += sizeof(struct channel_stats) / sizeof(u64);
-
 	*data++ = (u64)pi->port_id;
 	memset(&s, 0, sizeof(s));
 	t4_get_lb_stats(adapter, pi->port_id, &s);
-- 
cgit v1.2.3


From 31e5f5c3e92f6560485d7625f772e36aec6d42ec Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Mon, 9 Jul 2018 21:42:47 +0530
Subject: cxgb4: expose stats fetched from firmware via debugfs

Expose stats obtained from firmware via debugfs. These stats can't
be part of ethtool -S because the slow firmware mailbox can cause
packet drops under heavy load.

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 164 +++++++++++++++++++++
 1 file changed, 164 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 516c883e1613..511606fd1b20 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2962,6 +2962,169 @@ static const struct file_operations chcr_stats_debugfs_fops = {
         .llseek  = seq_lseek,
         .release = single_release,
 };
+
+#define PRINT_ADAP_STATS(string, value) \
+	seq_printf(seq, "%-25s %-20llu\n", (string), \
+		   (unsigned long long)(value))
+
+#define PRINT_CH_STATS(string, value) \
+do { \
+	seq_printf(seq, "%-25s ", (string)); \
+	for (i = 0; i < adap->params.arch.nchan; i++) \
+		seq_printf(seq, "%-20llu ", \
+			   (unsigned long long)stats.value[i]); \
+	seq_printf(seq, "\n"); \
+} while (0)
+
+#define PRINT_CH_STATS2(string, value) \
+do { \
+	seq_printf(seq, "%-25s ", (string)); \
+	for (i = 0; i < adap->params.arch.nchan; i++) \
+		seq_printf(seq, "%-20llu ", \
+			   (unsigned long long)stats[i].value); \
+	seq_printf(seq, "\n"); \
+} while (0)
+
+static void show_tcp_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_tcp_stats v4, v6;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_tcp_stats(adap, &v4, &v6, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("tcp_ipv4_out_rsts:", v4.tcp_out_rsts);
+	PRINT_ADAP_STATS("tcp_ipv4_in_segs:", v4.tcp_in_segs);
+	PRINT_ADAP_STATS("tcp_ipv4_out_segs:", v4.tcp_out_segs);
+	PRINT_ADAP_STATS("tcp_ipv4_retrans_segs:", v4.tcp_retrans_segs);
+	PRINT_ADAP_STATS("tcp_ipv6_out_rsts:", v6.tcp_out_rsts);
+	PRINT_ADAP_STATS("tcp_ipv6_in_segs:", v6.tcp_in_segs);
+	PRINT_ADAP_STATS("tcp_ipv6_out_segs:", v6.tcp_out_segs);
+	PRINT_ADAP_STATS("tcp_ipv6_retrans_segs:", v6.tcp_retrans_segs);
+}
+
+static void show_ddp_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_usm_stats stats;
+
+	spin_lock(&adap->stats_lock);
+	t4_get_usm_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("usm_ddp_frames:", stats.frames);
+	PRINT_ADAP_STATS("usm_ddp_octets:", stats.octets);
+	PRINT_ADAP_STATS("usm_ddp_drops:", stats.drops);
+}
+
+static void show_rdma_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_rdma_stats stats;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_rdma_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("rdma_no_rqe_mod_defer:", stats.rqe_dfr_mod);
+	PRINT_ADAP_STATS("rdma_no_rqe_pkt_defer:", stats.rqe_dfr_pkt);
+}
+
+static void show_tp_err_adapter_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_err_stats stats;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_err_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_ADAP_STATS("tp_err_ofld_no_neigh:", stats.ofld_no_neigh);
+	PRINT_ADAP_STATS("tp_err_ofld_cong_defer:", stats.ofld_cong_defer);
+}
+
+static void show_cpl_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_cpl_stats stats;
+	u8 i;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_cpl_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_CH_STATS("tp_cpl_requests:", req);
+	PRINT_CH_STATS("tp_cpl_responses:", rsp);
+}
+
+static void show_tp_err_channel_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_err_stats stats;
+	u8 i;
+
+	spin_lock(&adap->stats_lock);
+	t4_tp_get_err_stats(adap, &stats, false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_CH_STATS("tp_mac_in_errs:", mac_in_errs);
+	PRINT_CH_STATS("tp_hdr_in_errs:", hdr_in_errs);
+	PRINT_CH_STATS("tp_tcp_in_errs:", tcp_in_errs);
+	PRINT_CH_STATS("tp_tcp6_in_errs:", tcp6_in_errs);
+	PRINT_CH_STATS("tp_tnl_cong_drops:", tnl_cong_drops);
+	PRINT_CH_STATS("tp_tnl_tx_drops:", tnl_tx_drops);
+	PRINT_CH_STATS("tp_ofld_vlan_drops:", ofld_vlan_drops);
+	PRINT_CH_STATS("tp_ofld_chan_drops:", ofld_chan_drops);
+}
+
+static void show_fcoe_stats(struct seq_file *seq)
+{
+	struct adapter *adap = seq->private;
+	struct tp_fcoe_stats stats[NCHAN];
+	u8 i;
+
+	spin_lock(&adap->stats_lock);
+	for (i = 0; i < adap->params.arch.nchan; i++)
+		t4_get_fcoe_stats(adap, i, &stats[i], false);
+	spin_unlock(&adap->stats_lock);
+
+	PRINT_CH_STATS2("fcoe_octets_ddp", octets_ddp);
+	PRINT_CH_STATS2("fcoe_frames_ddp", frames_ddp);
+	PRINT_CH_STATS2("fcoe_frames_drop", frames_drop);
+}
+
+#undef PRINT_CH_STATS2
+#undef PRINT_CH_STATS
+#undef PRINT_ADAP_STATS
+
+static int tp_stats_show(struct seq_file *seq, void *v)
+{
+	struct adapter *adap = seq->private;
+
+	seq_puts(seq, "\n--------Adapter Stats--------\n");
+	show_tcp_stats(seq);
+	show_ddp_stats(seq);
+	show_rdma_stats(seq);
+	show_tp_err_adapter_stats(seq);
+
+	seq_puts(seq, "\n-------- Channel Stats --------\n");
+	if (adap->params.arch.nchan == NCHAN)
+		seq_printf(seq, "%-25s %-20s %-20s %-20s %-20s\n",
+			   " ", "channel 0", "channel 1",
+			   "channel 2", "channel 3");
+	else
+		seq_printf(seq, "%-25s %-20s %-20s\n",
+			   " ", "channel 0", "channel 1");
+	show_cpl_stats(seq);
+	show_tp_err_channel_stats(seq);
+	show_fcoe_stats(seq);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_DEBUGFS_FILE(tp_stats);
+
 /* Add an array of Debug FS files.
  */
 void add_debugfs_files(struct adapter *adap,
@@ -3038,6 +3201,7 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "blocked_fl", &blocked_fl_fops, 0600, 0 },
 		{ "meminfo", &meminfo_fops, 0400, 0 },
 		{ "crypto", &chcr_stats_debugfs_fops, 0400, 0 },
+		{ "tp_stats", &tp_stats_debugfs_fops, 0400, 0 },
 	};
 
 	/* Debug FS nodes common to all T5 and later adapters.
-- 
cgit v1.2.3


From e0479b670d394d478907bd4fc22daab6516953c7 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Mon, 9 Jul 2018 20:26:47 +0300
Subject: net: sched: fix unprotected access to rcu cookie pointer

Fix action attribute size calculation function to take rcu read lock and
access act_cookie pointer with rcu dereference.

Fixes: eec94fdb0480 ("net: sched: use rcu for action cookie update")
Reported-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_api.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 66dc19746c63..148a89ab789b 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -149,10 +149,15 @@ EXPORT_SYMBOL(__tcf_idr_release);
 
 static size_t tcf_action_shared_attrs_size(const struct tc_action *act)
 {
+	struct tc_cookie *act_cookie;
 	u32 cookie_len = 0;
 
-	if (act->act_cookie)
-		cookie_len = nla_total_size(act->act_cookie->len);
+	rcu_read_lock();
+	act_cookie = rcu_dereference(act->act_cookie);
+
+	if (act_cookie)
+		cookie_len = nla_total_size(act_cookie->len);
+	rcu_read_unlock();
 
 	return  nla_total_size(0) /* action number nested */
 		+ nla_total_size(IFNAMSIZ) /* TCA_ACT_KIND */
-- 
cgit v1.2.3


From 4929c9428a171145f82f81aae0c3c25ef7d82837 Mon Sep 17 00:00:00 2001
From: Deepti Raghavan <deeptir@mit.edu>
Date: Mon, 9 Jul 2018 17:53:39 +0000
Subject: tcp: expose both send and receive intervals for rate sample

Congestion control algorithms, which access the rate sample
through the tcp_cong_control function, only have access to the maximum
of the send and receive interval, for cases where the acknowledgment
rate may be inaccurate due to ACK compression or decimation. Algorithms
may want to use send rates and receive rates as separate signals.

Signed-off-by: Deepti Raghavan <deeptir@mit.edu>
Acked-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h   | 2 ++
 net/ipv4/tcp_rate.c | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index cce37694776e..f6cb20e6e524 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -954,6 +954,8 @@ struct rate_sample {
 	u32  prior_delivered;	/* tp->delivered at "prior_mstamp" */
 	s32  delivered;		/* number of packets delivered over interval */
 	long interval_us;	/* time for tp->delivered to incr "delivered" */
+	u32 snd_interval_us;	/* snd interval for delivered packets */
+	u32 rcv_interval_us;	/* rcv interval for delivered packets */
 	long rtt_us;		/* RTT of last (S)ACKed packet (or -1) */
 	int  losses;		/* number of packets marked lost upon ACK */
 	u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index c61240e43923..4dff40dad4dc 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -146,6 +146,10 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,
 				    rs->prior_mstamp); /* ack phase */
 	rs->interval_us = max(snd_us, ack_us);
 
+	/* Record both segment send and ack receive intervals */
+	rs->snd_interval_us = snd_us;
+	rs->rcv_interval_us = ack_us;
+
 	/* Normally we expect interval_us >= min-rtt.
 	 * Note that rate may still be over-estimated when a spuriously
 	 * retransmistted skb was first (s)acked because "interval_us"
-- 
cgit v1.2.3


From 9012de5089560136b849b920ad038b96160ed8f6 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Tue, 10 Jul 2018 01:07:35 +0200
Subject: tipc: add sequence number check for link STATE messages

Some switch infrastructures produce huge amounts of packet duplicates.
This becomes a problem if those messages are STATE/NACK protocol
messages, causing unnecessary retransmissions of already accepted
packets.

We now introduce a unique sequence number per STATE protocol message
so that duplicates can be identified and ignored. This will also be
useful when tracing such cases, and to avert replay attacks when TIPC
is encrypted.

For compatibility reasons we have to introduce a new capability flag
TIPC_LINK_PROTO_SEQNO to handle this new feature.

Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 16 ++++++++++++++++
 net/tipc/link.h |  1 +
 net/tipc/node.c |  7 +++++++
 net/tipc/node.h | 14 ++++++++------
 4 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index ec4d28328652..065e9e67da5d 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -130,6 +130,8 @@ struct tipc_link {
 	/* Management and link supervision data */
 	u32 peer_session;
 	u32 session;
+	u16 snd_nxt_state;
+	u16 rcv_nxt_state;
 	u32 peer_bearer_id;
 	u32 bearer_id;
 	u32 tolerance;
@@ -339,6 +341,11 @@ char tipc_link_plane(struct tipc_link *l)
 	return l->net_plane;
 }
 
+void tipc_link_update_caps(struct tipc_link *l, u16 capabilities)
+{
+	l->peer_caps = capabilities;
+}
+
 void tipc_link_add_bc_peer(struct tipc_link *snd_l,
 			   struct tipc_link *uc_l,
 			   struct sk_buff_head *xmitq)
@@ -859,6 +866,8 @@ void tipc_link_reset(struct tipc_link *l)
 	l->rcv_unacked = 0;
 	l->snd_nxt = 1;
 	l->rcv_nxt = 1;
+	l->snd_nxt_state = 1;
+	l->rcv_nxt_state = 1;
 	l->acked = 0;
 	l->silent_intv_cnt = 0;
 	l->rst_cnt = 0;
@@ -1353,6 +1362,8 @@ static void tipc_link_build_proto_msg(struct tipc_link *l, int mtyp, bool probe,
 	msg_set_seqno(hdr, l->snd_nxt + U16_MAX / 2);
 
 	if (mtyp == STATE_MSG) {
+		if (l->peer_caps & TIPC_LINK_PROTO_SEQNO)
+			msg_set_seqno(hdr, l->snd_nxt_state++);
 		msg_set_seq_gap(hdr, rcvgap);
 		msg_set_bc_gap(hdr, link_bc_rcv_gap(bcl));
 		msg_set_probe(hdr, probe);
@@ -1522,6 +1533,11 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 
 	case STATE_MSG:
 
+		if (l->peer_caps & TIPC_LINK_PROTO_SEQNO &&
+		    less(msg_seqno(hdr), l->rcv_nxt_state))
+			break;
+		l->rcv_nxt_state = msg_seqno(hdr) + 1;
+
 		/* Update own tolerance if peer indicates a non-zero value */
 		if (in_range(peers_tol, TIPC_MIN_LINK_TOL, TIPC_MAX_LINK_TOL))
 			l->tolerance = peers_tol;
diff --git a/net/tipc/link.h b/net/tipc/link.h
index ec59348a81e8..d56f9c9e5000 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -110,6 +110,7 @@ char *tipc_link_name(struct tipc_link *l);
 char tipc_link_plane(struct tipc_link *l);
 int tipc_link_prio(struct tipc_link *l);
 int tipc_link_window(struct tipc_link *l);
+void tipc_link_update_caps(struct tipc_link *l, u16 capabilities);
 unsigned long tipc_link_tolerance(struct tipc_link *l);
 void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
 			     struct sk_buff_head *xmitq);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index cfdbaf479fd1..1cdb176798f7 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -363,6 +363,8 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
 {
 	struct tipc_net *tn = net_generic(net, tipc_net_id);
 	struct tipc_node *n, *temp_node;
+	struct tipc_link *l;
+	int bearer_id;
 	int i;
 
 	spin_lock_bh(&tn->node_list_lock);
@@ -370,6 +372,11 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
 	if (n) {
 		/* Same node may come back with new capabilities */
 		n->capabilities = capabilities;
+		for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
+			l = n->links[bearer_id].link;
+			if (l)
+				tipc_link_update_caps(l, capabilities);
+		}
 		goto exit;
 	}
 	n = kzalloc(sizeof(*n), GFP_ATOMIC);
diff --git a/net/tipc/node.h b/net/tipc/node.h
index 846c8f240872..48b3298a248d 100644
--- a/net/tipc/node.h
+++ b/net/tipc/node.h
@@ -49,14 +49,16 @@ enum {
 	TIPC_BCAST_STATE_NACK = (1 << 2),
 	TIPC_BLOCK_FLOWCTL    = (1 << 3),
 	TIPC_BCAST_RCAST      = (1 << 4),
-	TIPC_NODE_ID128       = (1 << 5)
+	TIPC_NODE_ID128       = (1 << 5),
+	TIPC_LINK_PROTO_SEQNO = (1 << 6)
 };
 
-#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH | \
-				TIPC_BCAST_STATE_NACK | \
-				TIPC_BCAST_RCAST | \
-				TIPC_BLOCK_FLOWCTL | \
-				TIPC_NODE_ID128)
+#define TIPC_NODE_CAPABILITIES (TIPC_BCAST_SYNCH       |  \
+				TIPC_BCAST_STATE_NACK  |  \
+				TIPC_BCAST_RCAST       |  \
+				TIPC_BLOCK_FLOWCTL     |  \
+				TIPC_NODE_ID128        |  \
+				TIPC_LINK_PROTO_SEQNO)
 #define INVALID_BEARER_ID -1
 
 void tipc_node_stop(struct net *net);
-- 
cgit v1.2.3


From 7ea817f4e8322fa27fb860d15025bf72f68b179f Mon Sep 17 00:00:00 2001
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Tue, 10 Jul 2018 01:07:36 +0200
Subject: tipc: check session number before accepting link protocol messages

In some virtual environments we observe a significant higher number of
packet reordering and delays than we have been used to traditionally.

This makes it necessary with stricter checks on incoming link protocol
messages' session number, which until now only has been validated for
RESET messages.

Since the other two message types, ACTIVATE and STATE messages also
carry this number, it is easy to extend the validation check to those
messages.

We also introduce a flag indicating if a link has a valid peer session
number or not. This eliminates the mixing of 32- and 16-bit arithmethics
we are currently using to achieve this.

Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 68 +++++++++++++++++++++++++++++++++++++++------------------
 net/tipc/link.h |  1 +
 net/tipc/node.c |  5 ++++-
 3 files changed, 52 insertions(+), 22 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 065e9e67da5d..df763be38541 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -128,8 +128,8 @@ struct tipc_link {
 	struct net *net;
 
 	/* Management and link supervision data */
-	u32 peer_session;
-	u32 session;
+	u16 peer_session;
+	u16 session;
 	u16 snd_nxt_state;
 	u16 rcv_nxt_state;
 	u32 peer_bearer_id;
@@ -138,6 +138,7 @@ struct tipc_link {
 	u32 abort_limit;
 	u32 state;
 	u16 peer_caps;
+	bool in_session;
 	bool active;
 	u32 silent_intv_cnt;
 	char if_name[TIPC_MAX_IF_NAME];
@@ -216,11 +217,6 @@ enum {
  */
 #define TIPC_NACK_INTV (TIPC_MIN_LINK_WIN * 2)
 
-/* Wildcard value for link session numbers. When it is known that
- * peer endpoint is down, any session number must be accepted.
- */
-#define ANY_SESSION 0x10000
-
 /* Link FSM states:
  */
 enum {
@@ -478,7 +474,7 @@ bool tipc_link_create(struct net *net, char *if_name, int bearer_id,
 	l->addr = peer;
 	l->peer_caps = peer_caps;
 	l->net = net;
-	l->peer_session = ANY_SESSION;
+	l->in_session = false;
 	l->bearer_id = bearer_id;
 	l->tolerance = tolerance;
 	l->net_plane = net_plane;
@@ -847,7 +843,7 @@ void link_prepare_wakeup(struct tipc_link *l)
 
 void tipc_link_reset(struct tipc_link *l)
 {
-	l->peer_session = ANY_SESSION;
+	l->in_session = false;
 	l->session++;
 	l->mtu = l->advertised_mtu;
 	__skb_queue_purge(&l->transmq);
@@ -1455,6 +1451,44 @@ tnl:
 	}
 }
 
+/* tipc_link_validate_msg(): validate message against current link state
+ * Returns true if message should be accepted, otherwise false
+ */
+bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr)
+{
+	u16 curr_session = l->peer_session;
+	u16 session = msg_session(hdr);
+	int mtyp = msg_type(hdr);
+
+	if (msg_user(hdr) != LINK_PROTOCOL)
+		return true;
+
+	switch (mtyp) {
+	case RESET_MSG:
+		if (!l->in_session)
+			return true;
+		/* Accept only RESET with new session number */
+		return more(session, curr_session);
+	case ACTIVATE_MSG:
+		if (!l->in_session)
+			return true;
+		/* Accept only ACTIVATE with new or current session number */
+		return !less(session, curr_session);
+	case STATE_MSG:
+		/* Accept only STATE with current session number */
+		if (!l->in_session)
+			return false;
+		if (session != curr_session)
+			return false;
+		if (!(l->peer_caps & TIPC_LINK_PROTO_SEQNO))
+			return true;
+		/* Accept only STATE with new sequence number */
+		return !less(msg_seqno(hdr), l->rcv_nxt_state);
+	default:
+		return false;
+	}
+}
+
 /* tipc_link_proto_rcv(): receive link level protocol message :
  * Note that network plane id propagates through the network, and may
  * change at any time. The node with lowest numerical id determines
@@ -1488,17 +1522,12 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 	hdr = buf_msg(skb);
 	data = msg_data(hdr);
 
+	if (!tipc_link_validate_msg(l, hdr))
+		goto exit;
+
 	switch (mtyp) {
 	case RESET_MSG:
-
-		/* Ignore duplicate RESET with old session number */
-		if ((less_eq(msg_session(hdr), l->peer_session)) &&
-		    (l->peer_session != ANY_SESSION))
-			break;
-		/* fall thru' */
-
 	case ACTIVATE_MSG:
-
 		/* Complete own link name with peer's interface name */
 		if_name =  strrchr(l->name, ':') + 1;
 		if (sizeof(l->name) - (if_name - l->name) <= TIPC_MAX_IF_NAME)
@@ -1526,16 +1555,13 @@ static int tipc_link_proto_rcv(struct tipc_link *l, struct sk_buff *skb,
 			rc = TIPC_LINK_UP_EVT;
 
 		l->peer_session = msg_session(hdr);
+		l->in_session = true;
 		l->peer_bearer_id = msg_bearer_id(hdr);
 		if (l->mtu > msg_max_pkt(hdr))
 			l->mtu = msg_max_pkt(hdr);
 		break;
 
 	case STATE_MSG:
-
-		if (l->peer_caps & TIPC_LINK_PROTO_SEQNO &&
-		    less(msg_seqno(hdr), l->rcv_nxt_state))
-			break;
 		l->rcv_nxt_state = msg_seqno(hdr) + 1;
 
 		/* Update own tolerance if peer indicates a non-zero value */
diff --git a/net/tipc/link.h b/net/tipc/link.h
index d56f9c9e5000..7bc494a33fdf 100644
--- a/net/tipc/link.h
+++ b/net/tipc/link.h
@@ -111,6 +111,7 @@ char tipc_link_plane(struct tipc_link *l);
 int tipc_link_prio(struct tipc_link *l);
 int tipc_link_window(struct tipc_link *l);
 void tipc_link_update_caps(struct tipc_link *l, u16 capabilities);
+bool tipc_link_validate_msg(struct tipc_link *l, struct tipc_msg *hdr);
 unsigned long tipc_link_tolerance(struct tipc_link *l);
 void tipc_link_set_tolerance(struct tipc_link *l, u32 tol,
 			     struct sk_buff_head *xmitq);
diff --git a/net/tipc/node.c b/net/tipc/node.c
index 1cdb176798f7..52fd80b0e728 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -1540,7 +1540,7 @@ static void tipc_node_bc_rcv(struct net *net, struct sk_buff *skb, int bearer_id
  * tipc_node_check_state - check and if necessary update node state
  * @skb: TIPC packet
  * @bearer_id: identity of bearer delivering the packet
- * Returns true if state is ok, otherwise consumes buffer and returns false
+ * Returns true if state and msg are ok, otherwise false
  */
 static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 				  int bearer_id, struct sk_buff_head *xmitq)
@@ -1574,6 +1574,9 @@ static bool tipc_node_check_state(struct tipc_node *n, struct sk_buff *skb,
 		}
 	}
 
+	if (!tipc_link_validate_msg(l, hdr))
+		return false;
+
 	/* Check and update node accesibility if applicable */
 	if (state == SELF_UP_PEER_COMING) {
 		if (!tipc_link_is_up(l))
-- 
cgit v1.2.3


From 80fd2d6ca5461b2752744df2e6e387cc65e7b86c Mon Sep 17 00:00:00 2001
From: Travis Brown <travisb@arista.com>
Date: Tue, 10 Jul 2018 00:35:01 +0000
Subject: macvlan: Change status when lower device goes down

Today macvlan ignores the notification when a lower device goes
administratively down, preventing the lack of connectivity from
bubbling up.

Processing NETDEV_DOWN results in a macvlan state of LOWERLAYERDOWN
with NO-CARRIER which should be easy to interpret in userspace.

2: lower: <BROADCAST,MULTICAST> mtu 1500 qdisc mq state DOWN mode DEFAULT group default qlen 1000
3: macvlan@lower: <NO-CARRIER,BROADCAST,MULTICAST,UP,M-DOWN> mtu 1500 qdisc noqueue state LOWERLAYERDOWN mode DEFAULT group default qlen 1000

Signed-off-by: Suresh Krishnan <skrishnan@arista.com>
Signed-off-by: Travis Brown <travisb@arista.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/macvlan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 401e1d1ce1ec..cfda146f3b3b 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1641,6 +1641,7 @@ static int macvlan_device_event(struct notifier_block *unused,
 
 	switch (event) {
 	case NETDEV_UP:
+	case NETDEV_DOWN:
 	case NETDEV_CHANGE:
 		list_for_each_entry(vlan, &port->vlans, list)
 			netif_stacked_transfer_operstate(vlan->lowerdev,
-- 
cgit v1.2.3


From 3443b00e07eed5798605ba6524de37e1d3f1a4bf Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 10 Jul 2018 10:02:57 +0300
Subject: team: Publish team_port_get_rcu()

A follow-up patch adds a new entry point, team_port_dev_txable(). Making
it an ordinary exported function would mean that any module that may
need the service in one of the supported configurations also
unconditionally needs to pull in the team module, whether or not the
user actually intends to create team interfaces.

To prevent that, team_port_dev_txable() is defined in if_team.h, and
therefore all dependencies of that function also need to be
publicly-visible.

Therefore move team_port_get_rcu() from team.c to if_team.h.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/team/team.c | 5 -----
 include/linux/if_team.h | 5 +++++
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c
index 3a95eaae0c98..6a047d30e8c6 100644
--- a/drivers/net/team/team.c
+++ b/drivers/net/team/team.c
@@ -41,11 +41,6 @@
 
 #define team_port_exists(dev) (dev->priv_flags & IFF_TEAM_PORT)
 
-static struct team_port *team_port_get_rcu(const struct net_device *dev)
-{
-	return rcu_dereference(dev->rx_handler_data);
-}
-
 static struct team_port *team_port_get_rtnl(const struct net_device *dev)
 {
 	struct team_port *port = rtnl_dereference(dev->rx_handler_data);
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index d95cae09dea0..0d07c6655cce 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -74,6 +74,11 @@ struct team_port {
 	long mode_priv[0];
 };
 
+static inline struct team_port *team_port_get_rcu(const struct net_device *dev)
+{
+	return rcu_dereference(dev->rx_handler_data);
+}
+
 static inline bool team_port_enabled(struct team_port *port)
 {
 	return port->index != -1;
-- 
cgit v1.2.3


From eeed992b776c54af6108187c87ac60d028e69d37 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 10 Jul 2018 10:02:58 +0300
Subject: net: Add lag.h, net_lag_port_dev_txable()

LAG devices (team or bond) recognize for each one of their slave devices
whether LAG traffic is going to be sent through that device. Bond calls
such devices "active", team calls them "txable". When this state
changes, a NETDEV_CHANGELOWERSTATE notification is distributed, together
with a netdev_notifier_changelowerstate_info structure that for LAG
devices includes a tx_enabled flag that refers to the new state. The
notification thus makes it possible to react to the changes in txability
in drivers.

However there's no way to query txability from the outside on demand.
That is problematic namely for mlxsw, which when resolving ERSPAN packet
path, may encounter a LAG device, and needs to determine which of the
slaves it should choose.

To that end, introduce a new function, net_lag_port_dev_txable(), which
determines whether a given slave device is "active" or
"txable" (depending on the flavor of the LAG device). That function then
dispatches to per-LAG-flavor helpers, bond_is_active_slave_dev() resp.
team_port_dev_txable().

Because there currently is no good place where net_lag_port_dev_txable()
should be added, introduce a new header file, lag.h, which should from
now on hold any logic common to both team and bond. (But keep
netif_is_lag_master() together with the rest of netif_is_*_master()
functions).

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/if_team.h | 13 +++++++++++++
 include/net/bonding.h   | 13 +++++++++++++
 include/net/lag.h       | 17 +++++++++++++++++
 3 files changed, 43 insertions(+)
 create mode 100644 include/net/lag.h

diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 0d07c6655cce..ac42da56f7a2 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -89,6 +89,19 @@ static inline bool team_port_txable(struct team_port *port)
 	return port->linkup && team_port_enabled(port);
 }
 
+static inline bool team_port_dev_txable(const struct net_device *port_dev)
+{
+	struct team_port *port;
+	bool txable;
+
+	rcu_read_lock();
+	port = team_port_get_rcu(port_dev);
+	txable = port ? team_port_txable(port) : false;
+	rcu_read_unlock();
+
+	return txable;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 static inline void team_netpoll_send_skb(struct team_port *port,
 					 struct sk_buff *skb)
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 808f1d167349..a2d058170ea3 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -411,6 +411,19 @@ static inline bool bond_slave_can_tx(struct slave *slave)
 	       bond_is_active_slave(slave);
 }
 
+static inline bool bond_is_active_slave_dev(const struct net_device *slave_dev)
+{
+	struct slave *slave;
+	bool active;
+
+	rcu_read_lock();
+	slave = bond_slave_get_rcu(slave_dev);
+	active = bond_is_active_slave(slave);
+	rcu_read_unlock();
+
+	return active;
+}
+
 static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len)
 {
 	if (len == ETH_ALEN) {
diff --git a/include/net/lag.h b/include/net/lag.h
new file mode 100644
index 000000000000..95b880e6fdde
--- /dev/null
+++ b/include/net/lag.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IF_LAG_H
+#define _LINUX_IF_LAG_H
+
+#include <linux/netdevice.h>
+#include <linux/if_team.h>
+#include <net/bonding.h>
+
+static inline bool net_lag_port_dev_txable(const struct net_device *port_dev)
+{
+	if (netif_is_team_port(port_dev))
+		return team_port_dev_txable(port_dev);
+	else
+		return bond_is_active_slave_dev(port_dev);
+}
+
+#endif /* _LINUX_IF_LAG_H */
-- 
cgit v1.2.3


From b5de82f3dfbebc2d1b6db72c68f119a1e0427ca8 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 10 Jul 2018 10:02:59 +0300
Subject: mlxsw: spectrum_span: Change LAG lower selection

When offloading mirror-to-gretap, mlxsw needs to preroute the path that
the encapsulated packet will take. That path may include a LAG device
above a front panel port. So far, mlxsw resolved the path to the first
up front panel slave of the LAG interface, but that only reflects
administrative state of the port. It neglects to consider whether the
port actually has a carrier, and what the LACP state is.

So instead of checking upness of the device, check carrier state and
txability.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index 3d187d88cc7c..e42d640cddab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -36,6 +36,7 @@
 #include <linux/list.h>
 #include <net/arp.h>
 #include <net/gre.h>
+#include <net/lag.h>
 #include <net/ndisc.h>
 #include <net/ip6_tunnel.h>
 
@@ -254,7 +255,9 @@ mlxsw_sp_span_entry_lag(struct net_device *lag_dev)
 	struct list_head *iter;
 
 	netdev_for_each_lower_dev(lag_dev, dev, iter)
-		if ((dev->flags & IFF_UP) && mlxsw_sp_port_dev_check(dev))
+		if (netif_carrier_ok(dev) &&
+		    net_lag_port_dev_txable(dev) &&
+		    mlxsw_sp_port_dev_check(dev))
 			return dev;
 
 	return NULL;
-- 
cgit v1.2.3


From 559e50fd34d1c556d42016cbb9affce89cee9ea4 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Wed, 11 Jul 2018 23:01:47 -0300
Subject: drm/vkms: Add dumb operations

VKMS currently does not handle dumb data, and as a consequence, it does
not provide mechanisms for handling gem. This commit adds the necessary
support for gem object/handler and the dumb functions.

Changes since V1:
 Daniel Vetter:
 - Add dumb buffer support to the same patchset
Changes since V2:
 Haneen:
 - Add missing gem_free_object_unlocked callback to fix the warning
   "Memory manager not clean during takedown"

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/70b7becc91c6a323dbc15cb5fc912cbdfe4ef7d9.1531359228.git.rodrigosiqueiramelo@gmail.com
---
 drivers/gpu/drm/vkms/Makefile   |   2 +-
 drivers/gpu/drm/vkms/vkms_drv.c |  10 +++
 drivers/gpu/drm/vkms/vkms_drv.h |  23 ++++++
 drivers/gpu/drm/vkms/vkms_gem.c | 179 ++++++++++++++++++++++++++++++++++++++++
 4 files changed, 213 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/vkms/vkms_gem.c

diff --git a/drivers/gpu/drm/vkms/Makefile b/drivers/gpu/drm/vkms/Makefile
index 3f774a6a9c58..986297da51bf 100644
--- a/drivers/gpu/drm/vkms/Makefile
+++ b/drivers/gpu/drm/vkms/Makefile
@@ -1,3 +1,3 @@
-vkms-y := vkms_drv.o vkms_plane.o vkms_output.o vkms_crtc.o
+vkms-y := vkms_drv.o vkms_plane.o vkms_output.o vkms_crtc.o vkms_gem.o
 
 obj-$(CONFIG_DRM_VKMS) += vkms.o
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 740a4cbfed91..6ea2fd97bef9 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -37,6 +37,12 @@ static const struct file_operations vkms_driver_fops = {
 	.release	= drm_release,
 };
 
+static const struct vm_operations_struct vkms_gem_vm_ops = {
+	.fault = vkms_gem_fault,
+	.open = drm_gem_vm_open,
+	.close = drm_gem_vm_close,
+};
+
 static void vkms_release(struct drm_device *dev)
 {
 	struct vkms_device *vkms = container_of(dev, struct vkms_device, drm);
@@ -50,6 +56,10 @@ static struct drm_driver vkms_driver = {
 	.driver_features	= DRIVER_MODESET | DRIVER_ATOMIC | DRIVER_GEM,
 	.release		= vkms_release,
 	.fops			= &vkms_driver_fops,
+	.dumb_create		= vkms_dumb_create,
+	.dumb_map_offset	= vkms_dumb_map,
+	.gem_vm_ops		= &vkms_gem_vm_ops,
+	.gem_free_object_unlocked = vkms_gem_free_object,
 
 	.name			= DRIVER_NAME,
 	.desc			= DRIVER_DESC,
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index b0f9d2e61a42..cce4694cafb9 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -3,6 +3,7 @@
 
 #include <drm/drmP.h>
 #include <drm/drm.h>
+#include <drm/drm_gem.h>
 #include <drm/drm_encoder.h>
 
 static const u32 vkms_formats[] = {
@@ -21,6 +22,12 @@ struct vkms_device {
 	struct vkms_output output;
 };
 
+struct vkms_gem_object {
+	struct drm_gem_object gem;
+	struct mutex pages_lock; /* Page lock used in page fault handler */
+	struct page **pages;
+};
+
 int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
 		   struct drm_plane *primary, struct drm_plane *cursor);
 
@@ -28,4 +35,20 @@ int vkms_output_init(struct vkms_device *vkmsdev);
 
 struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev);
 
+/* Gem stuff */
+struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+				       struct drm_file *file,
+				       u32 *handle,
+				       u64 size);
+
+int vkms_gem_fault(struct vm_fault *vmf);
+
+int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
+		     struct drm_mode_create_dumb *args);
+
+int vkms_dumb_map(struct drm_file *file, struct drm_device *dev,
+		  u32 handle, u64 *offset);
+
+void vkms_gem_free_object(struct drm_gem_object *obj);
+
 #endif /* _VKMS_DRV_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_gem.c b/drivers/gpu/drm/vkms/vkms_gem.c
new file mode 100644
index 000000000000..c7e38368602b
--- /dev/null
+++ b/drivers/gpu/drm/vkms/vkms_gem.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/shmem_fs.h>
+
+#include "vkms_drv.h"
+
+static struct vkms_gem_object *__vkms_gem_create(struct drm_device *dev,
+						 u64 size)
+{
+	struct vkms_gem_object *obj;
+	int ret;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	size = roundup(size, PAGE_SIZE);
+	ret = drm_gem_object_init(dev, &obj->gem, size);
+	if (ret) {
+		kfree(obj);
+		return ERR_PTR(ret);
+	}
+
+	mutex_init(&obj->pages_lock);
+
+	return obj;
+}
+
+void vkms_gem_free_object(struct drm_gem_object *obj)
+{
+	struct vkms_gem_object *gem = container_of(obj, struct vkms_gem_object,
+						   gem);
+
+	kvfree(gem->pages);
+	mutex_destroy(&gem->pages_lock);
+	drm_gem_object_release(obj);
+	kfree(gem);
+}
+
+int vkms_gem_fault(struct vm_fault *vmf)
+{
+	struct vm_area_struct *vma = vmf->vma;
+	struct vkms_gem_object *obj = vma->vm_private_data;
+	unsigned long vaddr = vmf->address;
+	pgoff_t page_offset;
+	loff_t num_pages;
+	int ret;
+
+	page_offset = (vaddr - vma->vm_start) >> PAGE_SHIFT;
+	num_pages = DIV_ROUND_UP(obj->gem.size, PAGE_SIZE);
+
+	if (page_offset > num_pages)
+		return VM_FAULT_SIGBUS;
+
+	ret = -ENOENT;
+	mutex_lock(&obj->pages_lock);
+	if (obj->pages) {
+		get_page(obj->pages[page_offset]);
+		vmf->page = obj->pages[page_offset];
+		ret = 0;
+	}
+	mutex_unlock(&obj->pages_lock);
+	if (ret) {
+		struct page *page;
+		struct address_space *mapping;
+
+		mapping = file_inode(obj->gem.filp)->i_mapping;
+		page = shmem_read_mapping_page(mapping, page_offset);
+
+		if (!IS_ERR(page)) {
+			vmf->page = page;
+			ret = 0;
+		} else {
+			switch (PTR_ERR(page)) {
+			case -ENOSPC:
+			case -ENOMEM:
+				ret = VM_FAULT_OOM;
+				break;
+			case -EBUSY:
+				ret = VM_FAULT_RETRY;
+				break;
+			case -EFAULT:
+			case -EINVAL:
+				ret = VM_FAULT_SIGBUS;
+				break;
+			default:
+				WARN_ON(PTR_ERR(page));
+				ret = VM_FAULT_SIGBUS;
+				break;
+			}
+		}
+	}
+	return ret;
+}
+
+struct drm_gem_object *vkms_gem_create(struct drm_device *dev,
+				       struct drm_file *file,
+				       u32 *handle,
+				       u64 size)
+{
+	struct vkms_gem_object *obj;
+	int ret;
+
+	if (!file || !dev || !handle)
+		return ERR_PTR(-EINVAL);
+
+	obj = __vkms_gem_create(dev, size);
+	if (IS_ERR(obj))
+		return ERR_CAST(obj);
+
+	ret = drm_gem_handle_create(file, &obj->gem, handle);
+	drm_gem_object_put_unlocked(&obj->gem);
+	if (ret) {
+		drm_gem_object_release(&obj->gem);
+		kfree(obj);
+		return ERR_PTR(ret);
+	}
+
+	return &obj->gem;
+}
+
+int vkms_dumb_create(struct drm_file *file, struct drm_device *dev,
+		     struct drm_mode_create_dumb *args)
+{
+	struct drm_gem_object *gem_obj;
+	u64 pitch, size;
+
+	if (!args || !dev || !file)
+		return -EINVAL;
+
+	pitch = args->width * DIV_ROUND_UP(args->bpp, 8);
+	size = pitch * args->height;
+
+	if (!size)
+		return -EINVAL;
+
+	gem_obj = vkms_gem_create(dev, file, &args->handle, size);
+	if (IS_ERR(gem_obj))
+		return PTR_ERR(gem_obj);
+
+	args->size = gem_obj->size;
+	args->pitch = pitch;
+
+	DRM_DEBUG_DRIVER("Created object of size %lld\n", size);
+
+	return 0;
+}
+
+int vkms_dumb_map(struct drm_file *file, struct drm_device *dev,
+		  u32 handle, u64 *offset)
+{
+	struct drm_gem_object *obj;
+	int ret;
+
+	obj = drm_gem_object_lookup(file, handle);
+	if (!obj)
+		return -ENOENT;
+
+	if (!obj->filp) {
+		ret = -EINVAL;
+		goto unref;
+	}
+
+	ret = drm_gem_create_mmap_offset(obj);
+	if (ret)
+		goto unref;
+
+	*offset = drm_vma_node_offset_addr(&obj->vma_node);
+unref:
+	drm_gem_object_put_unlocked(obj);
+
+	return ret;
+}
-- 
cgit v1.2.3


From 657cd71e8eb3ac9ba91b8e1e403632b24d6cfdf9 Mon Sep 17 00:00:00 2001
From: Eames Trinh <eamestrinh@gmail.com>
Date: Tue, 10 Jul 2018 15:00:21 +0200
Subject: drm: gma500: Changed __attribute__((packed)) to __packed

Signed-off-by: Eames Trinh <eamestrinh@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710130021.4499-1-eamestrinh@gmail.com
---
 drivers/gpu/drm/gma500/intel_bios.h | 38 ++++++++++++++++++-------------------
 1 file changed, 19 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/gma500/intel_bios.h b/drivers/gpu/drm/gma500/intel_bios.h
index 978ae4b25e82..e0ccf1d19a4d 100644
--- a/drivers/gpu/drm/gma500/intel_bios.h
+++ b/drivers/gpu/drm/gma500/intel_bios.h
@@ -34,7 +34,7 @@ struct vbt_header {
 	u8 reserved0;
 	u32 bdb_offset;			/**< from beginning of VBT */
 	u32 aim_offset[4];		/**< from beginning of VBT */
-} __attribute__((packed));
+} __packed;
 
 
 struct bdb_header {
@@ -61,7 +61,7 @@ struct vbios_data {
 	u8 rsvd4; /* popup memory size */
 	u8 resize_pci_bios;
 	u8 rsvd5; /* is crt already on ddc2 */
-} __attribute__((packed));
+} __packed;
 
 /*
  * There are several types of BIOS data blocks (BDBs), each block has
@@ -133,7 +133,7 @@ struct bdb_general_features {
 	u8 dp_ssc_enb:1;	/* PCH attached eDP supports SSC */
 	u8 dp_ssc_freq:1;	/* SSC freq for PCH attached eDP */
 	u8 rsvd11:3; /* finish byte */
-} __attribute__((packed));
+} __packed;
 
 /* pre-915 */
 #define GPIO_PIN_DVI_LVDS	0x03 /* "DVI/LVDS DDC GPIO pins" */
@@ -213,7 +213,7 @@ struct child_device_config {
 	u8  dvo2_wiring;
 	u16 extended_type;
 	u8  dvo_function;
-} __attribute__((packed));
+} __packed;
 
 
 struct bdb_general_definitions {
@@ -256,7 +256,7 @@ struct bdb_lvds_options {
 	u8 lvds_edid:1;
 	u8 rsvd2:1;
 	u8 rsvd4;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_backlight {
 	u8 type:2;
@@ -268,7 +268,7 @@ struct bdb_lvds_backlight {
 	u8 i2caddr;
 	u8 brightnesscmd;
 	/*FIXME: more...*/
-} __attribute__((packed));
+} __packed;
 
 /* LFP pointer table contains entries to the struct below */
 struct bdb_lvds_lfp_data_ptr {
@@ -278,12 +278,12 @@ struct bdb_lvds_lfp_data_ptr {
 	u8 dvo_table_size;
 	u16 panel_pnp_id_offset;
 	u8 pnp_table_size;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_ptrs {
 	u8 lvds_entries; /* followed by one or more lvds_data_ptr structs */
 	struct bdb_lvds_lfp_data_ptr ptr[16];
-} __attribute__((packed));
+} __packed;
 
 /* LFP data has 3 blocks per entry */
 struct lvds_fp_timing {
@@ -300,7 +300,7 @@ struct lvds_fp_timing {
 	u32 pfit_reg;
 	u32 pfit_reg_val;
 	u16 terminator;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_dvo_timing {
 	u16 clock;		/**< In 10khz */
@@ -328,7 +328,7 @@ struct lvds_dvo_timing {
 	u8 vsync_positive:1;
 	u8 hsync_positive:1;
 	u8 rsvd2:1;
-} __attribute__((packed));
+} __packed;
 
 struct lvds_pnp_id {
 	u16 mfg_name;
@@ -336,17 +336,17 @@ struct lvds_pnp_id {
 	u32 serial;
 	u8 mfg_week;
 	u8 mfg_year;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data_entry {
 	struct lvds_fp_timing fp_timing;
 	struct lvds_dvo_timing dvo_timing;
 	struct lvds_pnp_id pnp_id;
-} __attribute__((packed));
+} __packed;
 
 struct bdb_lvds_lfp_data {
 	struct bdb_lvds_lfp_data_entry data[16];
-} __attribute__((packed));
+} __packed;
 
 struct aimdb_header {
 	char signature[16];
@@ -354,12 +354,12 @@ struct aimdb_header {
 	u16 aimdb_version;
 	u16 aimdb_header_size;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct aimdb_block {
 	u8 aimdb_id;
 	u16 aimdb_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_panel_data {
 	u16 fp_timing_offset;
@@ -370,12 +370,12 @@ struct vch_panel_data {
 	u8 text_fitting_size;
 	u16 graphics_fitting_offset;
 	u8 graphics_fitting_size;
-} __attribute__((packed));
+} __packed;
 
 struct vch_bdb_22 {
 	struct aimdb_block aimdb_block;
 	struct vch_panel_data panels[16];
-} __attribute__((packed));
+} __packed;
 
 struct bdb_sdvo_lvds_options {
 	u8 panel_backlight;
@@ -391,7 +391,7 @@ struct bdb_sdvo_lvds_options {
 	u8 panel_misc_bits_2;
 	u8 panel_misc_bits_3;
 	u8 panel_misc_bits_4;
-} __attribute__((packed));
+} __packed;
 
 #define BDB_DRIVER_FEATURE_NO_LVDS		0
 #define BDB_DRIVER_FEATURE_INT_LVDS		1
@@ -436,7 +436,7 @@ struct bdb_driver_features {
 
 	u8 hdmi_termination;
 	u8 custom_vbt_version;
-} __attribute__((packed));
+} __packed;
 
 #define EDP_18BPP	0
 #define EDP_24BPP	1
-- 
cgit v1.2.3


From d16489307a52f028dcb072addf681f9280f585c6 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Wed, 11 Jul 2018 23:02:14 -0300
Subject: drm/vkms: Add connectors helpers

This patch adds the struct drm_connector_helper_funcs with some
necessary hooks. Additionally, it also adds some missing hooks at
drm_connector_funcs.

Changes since V1:
- None
Change since V2:
 Daniel Vetter:
 - Remove vkms_conn_mode_valid

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/c8ee28b889234e866ef18bce4216385661c48041.1531359228.git.rodrigosiqueiramelo@gmail.com
---
 drivers/gpu/drm/vkms/vkms_drv.c    |  6 ------
 drivers/gpu/drm/vkms/vkms_drv.h    |  9 +++++++++
 drivers/gpu/drm/vkms/vkms_output.c | 20 ++++++++++++++++++++
 3 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 6ea2fd97bef9..823693235545 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -17,12 +17,6 @@
 #define DRIVER_MAJOR	1
 #define DRIVER_MINOR	0
 
-#define XRES_MIN    32
-#define YRES_MIN    32
-
-#define XRES_MAX  8192
-#define YRES_MAX  8192
-
 static struct vkms_device *vkms_device;
 
 static const struct file_operations vkms_driver_fops = {
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index cce4694cafb9..57d7367fd814 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -6,6 +6,15 @@
 #include <drm/drm_gem.h>
 #include <drm/drm_encoder.h>
 
+#define XRES_MIN    32
+#define YRES_MIN    32
+
+#define XRES_DEF  1024
+#define YRES_DEF   768
+
+#define XRES_MAX  8192
+#define YRES_MAX  8192
+
 static const u32 vkms_formats[] = {
 	DRM_FORMAT_XRGB8888,
 };
diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c
index 48143eac3c12..a7c0ec9b643f 100644
--- a/drivers/gpu/drm/vkms/vkms_output.c
+++ b/drivers/gpu/drm/vkms/vkms_output.c
@@ -8,6 +8,7 @@
 
 #include "vkms_drv.h"
 #include <drm/drm_crtc_helper.h>
+#include <drm/drm_atomic_helper.h>
 
 static void vkms_connector_destroy(struct drm_connector *connector)
 {
@@ -18,12 +19,29 @@ static void vkms_connector_destroy(struct drm_connector *connector)
 static const struct drm_connector_funcs vkms_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.destroy = vkms_connector_destroy,
+	.reset = drm_atomic_helper_connector_reset,
+	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 };
 
 static const struct drm_encoder_funcs vkms_encoder_funcs = {
 	.destroy = drm_encoder_cleanup,
 };
 
+static int vkms_conn_get_modes(struct drm_connector *connector)
+{
+	int count;
+
+	count = drm_add_modes_noedid(connector, XRES_MAX, YRES_MAX);
+	drm_set_preferred_mode(connector, XRES_DEF, YRES_DEF);
+
+	return count;
+}
+
+static const struct drm_connector_helper_funcs vkms_conn_helper_funcs = {
+	.get_modes    = vkms_conn_get_modes,
+};
+
 int vkms_output_init(struct vkms_device *vkmsdev)
 {
 	struct vkms_output *output = &vkmsdev->output;
@@ -49,6 +67,8 @@ int vkms_output_init(struct vkms_device *vkmsdev)
 		goto err_connector;
 	}
 
+	drm_connector_helper_add(connector, &vkms_conn_helper_funcs);
+
 	ret = drm_connector_register(connector);
 	if (ret) {
 		DRM_ERROR("Failed to register connector\n");
-- 
cgit v1.2.3


From 3a0709928b172a4123a76078f70e0a706265690c Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Wed, 11 Jul 2018 23:02:26 -0300
Subject: drm/vkms: Add vblank events simulated by hrtimers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This commit adds regular vblank events simulated through hrtimers, which
is a feature required by VKMS to mimic real hardware. Additionally, all
the vblank event send after pageflip is kept in the atomic_flush
function.

Changes since V1:
 - Compute the vblank timer interval per interruption
 Ville Syrjälä and Daniel Vetter:
 - Removes hardcoded vblank interval to get it from user space

Changes since V2:
 Chris Wilson
 - Removes unnecessary algorithm to compute the next period
 Daniel Vetter:
 - Uses drm_calc_timestamping_constants to get the vblank interval
   instead of calculating it manually
 - Adds disable_vblank helper that turns of crtc
 - Simplifies implementation by using drm_crtc_arm_vblank_event
 - Replaces the code in atomic_begin to atomic_flush
 - Removes unnecessary field in vkms_output

Changes since V3:
 Daniel Vetter:
 - Squash "drm/vkms: Add atomic helpers functions" into the commit that
   handling vblank events simulated by hrtimers

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/7709bba40782ec06332d57fff337797b272581fc.1531359228.git.rodrigosiqueiramelo@gmail.com
---
 drivers/gpu/drm/vkms/vkms_crtc.c | 95 ++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/vkms/vkms_drv.c  |  9 ++++
 drivers/gpu/drm/vkms/vkms_drv.h  | 15 +++++++
 3 files changed, 119 insertions(+)

diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
index bf76cd39ece7..875fca662ac0 100644
--- a/drivers/gpu/drm/vkms/vkms_crtc.c
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -10,6 +10,60 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 
+static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer)
+{
+	struct vkms_output *output = container_of(timer, struct vkms_output,
+						  vblank_hrtimer);
+	struct drm_crtc *crtc = &output->crtc;
+	int ret_overrun;
+	bool ret;
+
+	ret = drm_crtc_handle_vblank(crtc);
+	if (!ret)
+		DRM_ERROR("vkms failure on handling vblank");
+
+	ret_overrun = hrtimer_forward_now(&output->vblank_hrtimer,
+					  output->period_ns);
+
+	return HRTIMER_RESTART;
+}
+
+static int vkms_enable_vblank(struct drm_crtc *crtc)
+{
+	struct drm_device *dev = crtc->dev;
+	unsigned int pipe = drm_crtc_index(crtc);
+	struct drm_vblank_crtc *vblank = &dev->vblank[pipe];
+	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
+
+	drm_calc_timestamping_constants(crtc, &crtc->mode);
+
+	hrtimer_init(&out->vblank_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	out->vblank_hrtimer.function = &vkms_vblank_simulate;
+	out->period_ns = ktime_set(0, vblank->framedur_ns);
+	hrtimer_start(&out->vblank_hrtimer, out->period_ns, HRTIMER_MODE_REL);
+
+	return 0;
+}
+
+static void vkms_disable_vblank(struct drm_crtc *crtc)
+{
+	struct vkms_output *out = drm_crtc_to_vkms_output(crtc);
+
+	hrtimer_cancel(&out->vblank_hrtimer);
+}
+
+bool vkms_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe,
+			       int *max_error, ktime_t *vblank_time,
+			       bool in_vblank_irq)
+{
+	struct vkms_device *vkmsdev = drm_device_to_vkms_device(dev);
+	struct vkms_output *output = &vkmsdev->output;
+
+	*vblank_time = output->vblank_hrtimer.node.expires;
+
+	return true;
+}
+
 static const struct drm_crtc_funcs vkms_crtc_funcs = {
 	.set_config             = drm_atomic_helper_set_config,
 	.destroy                = drm_crtc_cleanup,
@@ -17,6 +71,45 @@ static const struct drm_crtc_funcs vkms_crtc_funcs = {
 	.reset                  = drm_atomic_helper_crtc_reset,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state   = drm_atomic_helper_crtc_destroy_state,
+	.enable_vblank		= vkms_enable_vblank,
+	.disable_vblank		= vkms_disable_vblank,
+};
+
+static void vkms_crtc_atomic_enable(struct drm_crtc *crtc,
+				    struct drm_crtc_state *old_state)
+{
+	drm_crtc_vblank_on(crtc);
+}
+
+static void vkms_crtc_atomic_disable(struct drm_crtc *crtc,
+				     struct drm_crtc_state *old_state)
+{
+	drm_crtc_vblank_off(crtc);
+}
+
+static void vkms_crtc_atomic_flush(struct drm_crtc *crtc,
+				   struct drm_crtc_state *old_crtc_state)
+{
+	unsigned long flags;
+
+	if (crtc->state->event) {
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+
+		if (drm_crtc_vblank_get(crtc) != 0)
+			drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		else
+			drm_crtc_arm_vblank_event(crtc, crtc->state->event);
+
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+
+		crtc->state->event = NULL;
+	}
+}
+
+static const struct drm_crtc_helper_funcs vkms_crtc_helper_funcs = {
+	.atomic_flush	= vkms_crtc_atomic_flush,
+	.atomic_enable	= vkms_crtc_atomic_enable,
+	.atomic_disable	= vkms_crtc_atomic_disable,
 };
 
 int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
@@ -31,5 +124,7 @@ int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
 		return ret;
 	}
 
+	drm_crtc_helper_add(crtc, &vkms_crtc_helper_funcs);
+
 	return ret;
 }
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 823693235545..a1448fb56893 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -54,6 +54,7 @@ static struct drm_driver vkms_driver = {
 	.dumb_map_offset	= vkms_dumb_map,
 	.gem_vm_ops		= &vkms_gem_vm_ops,
 	.gem_free_object_unlocked = vkms_gem_free_object,
+	.get_vblank_timestamp	= vkms_get_vblank_timestamp,
 
 	.name			= DRIVER_NAME,
 	.desc			= DRIVER_DESC,
@@ -100,6 +101,14 @@ static int __init vkms_init(void)
 		goto out_fini;
 	}
 
+	vkms_device->drm.irq_enabled = true;
+
+	ret = drm_vblank_init(&vkms_device->drm, 1);
+	if (ret) {
+		DRM_ERROR("Failed to vblank\n");
+		goto out_fini;
+	}
+
 	ret = vkms_modeset_init(vkms_device);
 	if (ret)
 		goto out_unregister;
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index 57d7367fd814..07be29f2dc44 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -5,6 +5,7 @@
 #include <drm/drm.h>
 #include <drm/drm_gem.h>
 #include <drm/drm_encoder.h>
+#include <linux/hrtimer.h>
 
 #define XRES_MIN    32
 #define YRES_MIN    32
@@ -23,6 +24,9 @@ struct vkms_output {
 	struct drm_crtc crtc;
 	struct drm_encoder encoder;
 	struct drm_connector connector;
+	struct hrtimer vblank_hrtimer;
+	ktime_t period_ns;
+	struct drm_pending_vblank_event *event;
 };
 
 struct vkms_device {
@@ -37,9 +41,20 @@ struct vkms_gem_object {
 	struct page **pages;
 };
 
+#define drm_crtc_to_vkms_output(target) \
+	container_of(target, struct vkms_output, crtc)
+
+#define drm_device_to_vkms_device(target) \
+	container_of(target, struct vkms_device, drm)
+
+/* CRTC */
 int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
 		   struct drm_plane *primary, struct drm_plane *cursor);
 
+bool vkms_get_vblank_timestamp(struct drm_device *dev, unsigned int pipe,
+			       int *max_error, ktime_t *vblank_time,
+			       bool in_vblank_irq);
+
 int vkms_output_init(struct vkms_device *vkmsdev);
 
 struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev);
-- 
cgit v1.2.3


From 42801298386c7c261f376a7f08446b2633fe7bc2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Tue, 10 Jul 2018 14:44:26 +0200
Subject: selftests: forwarding: mirror_gre_nh: Unset rp_filter on host VRF

The mirrored packets arrive at $h3 encapsulated in GRE/IPv4, with IP
address from 192.0.2.128/28 network. However the interface is configured
as a member of 192.0.2.160/28 and there's no route directing traffic
from the former network through that interface. Correspondingly, the RP
filter on the VRF rejects it.

Therefore turn off the VRF's RP filter.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/mirror_gre_nh.sh | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
index 8fa681eb90e7..6f9ef1820e93 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh
@@ -35,6 +35,8 @@ setup_prepare()
 	vrf_prepare
 	mirror_gre_topo_create
 
+	sysctl_set net.ipv4.conf.v$h3.rp_filter 0
+
 	ip address add dev $swp3 192.0.2.161/28
 	ip address add dev $h3 192.0.2.162/28
 	ip address add dev gt4 192.0.2.129/32
@@ -61,6 +63,8 @@ cleanup()
 	ip address del dev $h3 192.0.2.162/28
 	ip address del dev $swp3 192.0.2.161/28
 
+	sysctl_restore net.ipv4.conf.v$h3.rp_filter 0
+
 	mirror_gre_topo_destroy
 	vrf_cleanup
 
-- 
cgit v1.2.3


From d0c694fc7b01a500741d4085d26ed78df5aa6c7a Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 10 Jul 2018 16:04:04 +0300
Subject: net: ethernet: ti: cpts: break cycle once late ts is matched

The late ts queue can contain a bunch of skbs while hi rate testing,
no need to check all of them if timestamp is already matched.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index 6f63c8729afc..b4ea58dc8caf 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -114,7 +114,10 @@ static bool cpts_match_tx_ts(struct cpts *cpts, struct cpts_event *event)
 			dev_consume_skb_any(skb);
 			dev_dbg(cpts->dev, "match tx timestamp mtype %u seqid %04x\n",
 				mtype, seqid);
-		} else if (time_after(jiffies, skb_cb->tmo)) {
+			break;
+		}
+
+		if (time_after(jiffies, skb_cb->tmo)) {
 			/* timeout any expired skbs over 1s */
 			dev_dbg(cpts->dev,
 				"expiring tx timestamp mtype %u seqid %04x\n",
-- 
cgit v1.2.3


From a5d7fcb689eba7884c3bd5d42cebebdf0e99b978 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:41 +0200
Subject: be2net: remove unused old AIC info

The commit 2632bafd74ae ("be2net: fix adaptive interrupt coalescing")
introduced a separate struct be_aic_obj to hold AIC information but
unfortunately left the old stuff in be_eq_obj. So remove it.

Fixes: 2632bafd74ae ("be2net: fix adaptive interrupt coalescing")
Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 382891f81e09..6cf9d106c989 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -187,13 +187,6 @@ struct be_eq_obj {
 	struct be_queue_info q;
 	char desc[32];
 
-	/* Adaptive interrupt coalescing (AIC) info */
-	bool enable_aic;
-	u32 min_eqd;		/* in usecs */
-	u32 max_eqd;		/* in usecs */
-	u32 eqd;		/* configured val when aic is off */
-	u32 cur_eqd;		/* in usecs */
-
 	u8 idx;			/* array index */
 	u8 msix_idx;
 	u16 spurious_intr;
-- 
cgit v1.2.3


From c1328a27bb8cdbe3ff1677cc263d302fb8a72075 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:42 +0200
Subject: be2net: remove unused old custom busy-poll fields

The commit fb6113e688e0 ("be2net: get rid of custom busy poll code")
replaced custom busy-poll code by the generic one but left several
macros and fields in struct be_eq_obj that are currently unused.
Remove this stuff.

Fixes: fb6113e688e0 ("be2net: get rid of custom busy poll code")
Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 6cf9d106c989..a4604dea4560 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -193,19 +193,6 @@ struct be_eq_obj {
 	struct napi_struct napi;
 	struct be_adapter *adapter;
 	cpumask_var_t  affinity_mask;
-
-#ifdef CONFIG_NET_RX_BUSY_POLL
-#define BE_EQ_IDLE		0
-#define BE_EQ_NAPI		1	/* napi owns this EQ */
-#define BE_EQ_POLL		2	/* poll owns this EQ */
-#define BE_EQ_LOCKED		(BE_EQ_NAPI | BE_EQ_POLL)
-#define BE_EQ_NAPI_YIELD	4	/* napi yielded this EQ */
-#define BE_EQ_POLL_YIELD	8	/* poll yielded this EQ */
-#define BE_EQ_YIELD		(BE_EQ_NAPI_YIELD | BE_EQ_POLL_YIELD)
-#define BE_EQ_USER_PEND		(BE_EQ_POLL | BE_EQ_POLL_YIELD)
-	unsigned int state;
-	spinlock_t lock;	/* lock to serialize napi and busy-poll */
-#endif  /* CONFIG_NET_RX_BUSY_POLL */
 } ____cacheline_aligned_in_smp;
 
 struct be_aic_obj {		/* Adaptive interrupt coalescing (AIC) info */
-- 
cgit v1.2.3


From d6d9704af8f42155791dc46d39d380e200c819ae Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:43 +0200
Subject: be2net: remove desc field from be_eq_obj

The event queue description (be_eq_obj.desc) field is used only to format
string for IRQ name and it is not really needed to hold this value.
Remove it and use local variable to format string for IRQ name.

Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h      | 1 -
 drivers/net/ethernet/emulex/benet/be_main.c | 6 ++++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index a4604dea4560..e71e5e592626 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -185,7 +185,6 @@ static inline void queue_tail_inc(struct be_queue_info *q)
 
 struct be_eq_obj {
 	struct be_queue_info q;
-	char desc[32];
 
 	u8 idx;			/* array index */
 	u8 msix_idx;
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 8f755009ff38..05e4c0bb25f4 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -3403,9 +3403,11 @@ static int be_msix_register(struct be_adapter *adapter)
 	int status, i, vec;
 
 	for_all_evt_queues(adapter, eqo, i) {
-		sprintf(eqo->desc, "%s-q%d", netdev->name, i);
+		char irq_name[IFNAMSIZ+4];
+
+		snprintf(irq_name, sizeof(irq_name), "%s-q%d", netdev->name, i);
 		vec = be_msix_vec_get(adapter, eqo);
-		status = request_irq(vec, be_msix, 0, eqo->desc, eqo);
+		status = request_irq(vec, be_msix, 0, irq_name, eqo);
 		if (status)
 			goto err_msix;
 
-- 
cgit v1.2.3


From e9c74cd85c00e46bff62d3bb2ce8c5fd02bf465e Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:44 +0200
Subject: be2net: reorder fields in be_eq_obj structure

Re-order fields in struct be_eq_obj to ensure that .napi field begins
at start of cache-line. Also the .adapter field is moved to the first
cache-line next to .q field and 3 fields (idx,msi_idx,spurious_intr)
and the 4-bytes hole to 3rd cache-line.

Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index e71e5e592626..716b4bc410f5 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -186,11 +186,11 @@ static inline void queue_tail_inc(struct be_queue_info *q)
 struct be_eq_obj {
 	struct be_queue_info q;
 
+	struct be_adapter *adapter;
+	struct napi_struct napi;
 	u8 idx;			/* array index */
 	u8 msix_idx;
 	u16 spurious_intr;
-	struct napi_struct napi;
-	struct be_adapter *adapter;
 	cpumask_var_t  affinity_mask;
 } ____cacheline_aligned_in_smp;
 
-- 
cgit v1.2.3


From 646d2c10aaa060281b4ce7c1d3649d7df2ba9e7f Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:45 +0200
Subject: be2net: move txcp field in be_tx_obj to eliminate holes in the struct

Before patch:
struct be_tx_obj {
        u32                        db_offset;            /*     0     4 */

        /* XXX 4 bytes hole, try to pack */

        struct be_queue_info       q;                    /*     8    56 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        struct be_queue_info       cq;                   /*    64    56 */
        struct be_tx_compl_info    txcp;                 /*   120     4 */

        /* XXX 4 bytes hole, try to pack */

        /* --- cacheline 2 boundary (128 bytes) --- */
        struct sk_buff *           sent_skb_list[2048];  /*   128 16384 */
        ...
}:

After patch:
struct be_tx_obj {
        u32                        db_offset;            /*     0     4 */
        struct be_tx_compl_info    txcp;                 /*     4     4 */
        struct be_queue_info       q;                    /*     8    56 */
        /* --- cacheline 1 boundary (64 bytes) --- */
        struct be_queue_info       cq;                   /*    64    56 */
        struct sk_buff *           sent_skb_list[2048];  /*   120 16384 */
        ...
};

Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 716b4bc410f5..91ca8d132e87 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -240,9 +240,9 @@ struct be_tx_compl_info {
 
 struct be_tx_obj {
 	u32 db_offset;
+	struct be_tx_compl_info txcp;
 	struct be_queue_info q;
 	struct be_queue_info cq;
-	struct be_tx_compl_info txcp;
 	/* Remember the skbs that were transmitted */
 	struct sk_buff *sent_skb_list[TX_Q_LEN];
 	struct be_tx_stats stats;
-- 
cgit v1.2.3


From f9520b86dc22b6ac0ad2926cfa334e9fecb68a12 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:46 +0200
Subject: be2net: remove unused tx_jiffies field from be_tx_stats

Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 91ca8d132e87..d521364e17cf 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -217,7 +217,6 @@ struct be_tx_stats {
 	u64 tx_vxlan_offload_pkts;
 	u64 tx_reqs;
 	u64 tx_compl;
-	ulong tx_jiffies;
 	u32 tx_stops;
 	u32 tx_drv_drops;	/* pkts dropped by driver */
 	/* the error counters are described in be_ethtool.c */
-- 
cgit v1.2.3


From 03d231a963ae1179d05f552db75b661d1099272f Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:47 +0200
Subject: be2net: re-order fields in be_error_recovert to avoid hole

- Unionize two u8 fields where only one of them is used depending on NIC
chipset.
- Move recovery_supported field after that union

These changes eliminate 7-bytes hole in the struct and makes it smaller
by 8 bytes.

Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index d521364e17cf..4f805be43180 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -522,11 +522,13 @@ enum {
 };
 
 struct be_error_recovery {
-	/* Lancer error recovery variables */
-	u8 recovery_retries;
+	union {
+		u8 recovery_retries;	/* used for Lancer		*/
+		u8 recovery_state;	/* used for BEx and Skyhawk	*/
+	};
 
 	/* BEx/Skyhawk error recovery variables */
-	u8 recovery_state;
+	bool recovery_supported;
 	u16 ue_to_reset_time;		/* Time after UE, to soft reset
 					 * the chip - PF0 only
 					 */
@@ -534,7 +536,6 @@ struct be_error_recovery {
 					 * of SLIPORT_SEMAPHORE reg
 					 */
 	u16 last_err_code;
-	bool recovery_supported;
 	unsigned long probe_time;
 	unsigned long last_recovery_time;
 
-- 
cgit v1.2.3


From 28ace84b10fa5a1bb542ee7198743e3c02e23a07 Mon Sep 17 00:00:00 2001
From: Ivan Vecera <cera@cera.cz>
Date: Tue, 10 Jul 2018 22:59:48 +0200
Subject: be2net: move rss_flags field in rss_info to ensure proper alignment

The current position of .rss_flags field in struct rss_info causes
that fields .rsstable and .rssqueue (both 128 bytes long) crosses
cache-line boundaries. Moving it at the end properly align all fields.

Before patch:
struct rss_info {
        u64                        rss_flags;            /*     0     8 */
        u8                         rsstable[128];        /*     8   128 */
        /* --- cacheline 2 boundary (128 bytes) was 8 bytes ago --- */
        u8                         rss_queue[128];       /*   136   128 */
        /* --- cacheline 4 boundary (256 bytes) was 8 bytes ago --- */
        u8                         rss_hkey[40];         /*   264    40 */
};

After patch:
struct rss_info {
        u8                         rsstable[128];        /*     0   128 */
        /* --- cacheline 2 boundary (128 bytes) --- */
        u8                         rss_queue[128];       /*   128   128 */
        /* --- cacheline 4 boundary (256 bytes) --- */
        u8                         rss_hkey[40];         /*   256    40 */
        u64                        rss_flags;            /*   296     8 */
};

Signed-off-by: Ivan Vecera <cera@cera.cz>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 4f805be43180..7005949dc17b 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -436,10 +436,10 @@ struct be_port_resources {
 #define be_is_os2bmc_enabled(adapter) (adapter->flags & BE_FLAGS_OS2BMC)
 
 struct rss_info {
-	u64 rss_flags;
 	u8 rsstable[RSS_INDIR_TABLE_LEN];
 	u8 rss_queue[RSS_INDIR_TABLE_LEN];
 	u8 rss_hkey[RSS_HASH_KEY_LEN];
+	u64 rss_flags;
 };
 
 #define BE_INVALID_DIE_TEMP	0xFF
-- 
cgit v1.2.3


From c089af18b2bdc859f0c923bc6c026d96532797b4 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 11 Jul 2018 13:22:47 +0000
Subject: drm/sun4i: DW HDMI: Make symbol sun8i_dw_hdmi_pltfm_driver static

Fixes the following sparse warning:

drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c:228:24: warning:
 symbol 'sun8i_dw_hdmi_pltfm_driver' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531315367-190647-1-git-send-email-weiyongjun1@huawei.com
---
 drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index 21dc9ebad0b4..4cbe744e15a9 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -220,7 +220,7 @@ static const struct of_device_id sun8i_dw_hdmi_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, sun8i_dw_hdmi_dt_ids);
 
-struct platform_driver sun8i_dw_hdmi_pltfm_driver = {
+static struct platform_driver sun8i_dw_hdmi_pltfm_driver = {
 	.probe  = sun8i_dw_hdmi_probe,
 	.remove = sun8i_dw_hdmi_remove,
 	.driver = {
-- 
cgit v1.2.3


From 7da9b2e47fefb419a21e1c4c5a0682846b41b4a0 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Wed, 11 Jul 2018 13:27:06 +0200
Subject: drm/sun4i: mixer: Read id from DT

Currently, TCON supports 2 ways to match TCON with engine (mixer in this
case). Old way is to just traverse of graph backwards and compare node
pointer. New way is to match TCON and engine by their respective ids.
All SoCs with DE2 enabled till now used the old way, which means mixer
id was never used and thus never implemented.

However, for R40, only the new way will be used. To prepare for that,
implement mixer id fetching from DT.

Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711112706.30222-1-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_mixer.c | 49 +++++++++++++++++++++++++++++++++++--
 1 file changed, 47 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index aa81b9838ae8..da34fc394902 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -22,6 +22,7 @@
 #include <linux/component.h>
 #include <linux/dma-mapping.h>
 #include <linux/of_device.h>
+#include <linux/of_graph.h>
 #include <linux/reset.h>
 
 #include "sun4i_drv.h"
@@ -322,6 +323,42 @@ static struct regmap_config sun8i_mixer_regmap_config = {
 	.max_register	= 0xbfffc, /* guessed */
 };
 
+static int sun8i_mixer_of_get_id(struct device_node *node)
+{
+	struct device_node *port, *ep;
+	int ret = -EINVAL;
+
+	/* output is port 1 */
+	port = of_graph_get_port_by_id(node, 1);
+	if (!port)
+		return -EINVAL;
+
+	/* try to find downstream endpoint */
+	for_each_available_child_of_node(port, ep) {
+		struct device_node *remote;
+		u32 reg;
+
+		remote = of_graph_get_remote_endpoint(ep);
+		if (!remote)
+			continue;
+
+		ret = of_property_read_u32(remote, "reg", &reg);
+		if (!ret) {
+			of_node_put(remote);
+			of_node_put(ep);
+			of_node_put(port);
+
+			return reg;
+		}
+
+		of_node_put(remote);
+	}
+
+	of_node_put(port);
+
+	return ret;
+}
+
 static int sun8i_mixer_bind(struct device *dev, struct device *master,
 			      void *data)
 {
@@ -353,8 +390,16 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 	dev_set_drvdata(dev, mixer);
 	mixer->engine.ops = &sun8i_engine_ops;
 	mixer->engine.node = dev->of_node;
-	/* The ID of the mixer currently doesn't matter */
-	mixer->engine.id = -1;
+
+	/*
+	 * While this function can fail, we shouldn't do anything
+	 * if this happens. Some early DE2 DT entries don't provide
+	 * mixer id but work nevertheless because matching between
+	 * TCON and mixer is done by comparing node pointers (old
+	 * way) instead comparing ids. If this function fails and
+	 * id is needed, it will fail during id matching anyway.
+	 */
+	mixer->engine.id = sun8i_mixer_of_get_id(dev->of_node);
 
 	mixer->cfg = of_device_get_match_data(dev);
 	if (!mixer->cfg)
-- 
cgit v1.2.3


From 58d4d29823d9a6c4593c48a1a24e6a9dcec8e3ff Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 16:43:10 +0200
Subject: drm/sun4i: fix build failure with CONFIG_DRM_SUN8I_MIXER=m

Having DRM_SUN4I built-in but DRM_SUN8I_MIXER as a loadable module results in
a link error, as we try to access a symbol from the sun8i_tcon_top.ko module:

ERROR: "sun8i_tcon_top_of_table" [drivers/gpu/drm/sun4i/sun8i-drm-hdmi.ko] undefined!
ERROR: "sun8i_tcon_top_of_table" [drivers/gpu/drm/sun4i/sun4i-drm.ko] undefined!

This solves the problem by adding a silent symbol for the tcon_top module,
building it as a separate module in exactly the cases that we need it,
but in a way that it is reachable by the other modules.

Fixes: 57e23de02f48 ("drm/sun4i: DW HDMI: Expand algorithm for possible crtcs")
Fixes: ef0cf6441fbb ("drm/sun4i: Add support for traversing graph with TCON TOP")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711144403.1022829-1-arnd@arndb.de
---
 drivers/gpu/drm/sun4i/Kconfig         | 7 +++++++
 drivers/gpu/drm/sun4i/Makefile        | 3 ++-
 drivers/gpu/drm/sun4i/sun4i_drv.c     | 3 ++-
 drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c | 3 ++-
 4 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/Kconfig b/drivers/gpu/drm/sun4i/Kconfig
index 156a865c3e6d..c2c042287c19 100644
--- a/drivers/gpu/drm/sun4i/Kconfig
+++ b/drivers/gpu/drm/sun4i/Kconfig
@@ -68,4 +68,11 @@ config DRM_SUN8I_MIXER
 	  graphics mixture and feed graphics to TCON, If M is
 	  selected the module will be called sun8i-mixer.
 
+config DRM_SUN8I_TCON_TOP
+	tristate
+	default DRM_SUN4I if DRM_SUN8I_MIXER!=n
+	help
+	  TCON TOP is responsible for configuring display pipeline for
+	  HTMI, TVE and LCD.
+
 endif
diff --git a/drivers/gpu/drm/sun4i/Makefile b/drivers/gpu/drm/sun4i/Makefile
index 14f420f1d4ae..b04ea0f3da75 100644
--- a/drivers/gpu/drm/sun4i/Makefile
+++ b/drivers/gpu/drm/sun4i/Makefile
@@ -36,4 +36,5 @@ obj-$(CONFIG_DRM_SUN4I_BACKEND)	+= sun4i-backend.o sun4i-frontend.o
 obj-$(CONFIG_DRM_SUN4I_HDMI)	+= sun4i-drm-hdmi.o
 obj-$(CONFIG_DRM_SUN6I_DSI)	+= sun6i-dsi.o
 obj-$(CONFIG_DRM_SUN8I_DW_HDMI)	+= sun8i-drm-hdmi.o
-obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o sun8i_tcon_top.o
+obj-$(CONFIG_DRM_SUN8I_MIXER)	+= sun8i-mixer.o
+obj-$(CONFIG_DRM_SUN8I_TCON_TOP) += sun8i_tcon_top.o
diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index a15feb807393..03ffbcc98dd0 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -216,7 +216,8 @@ static bool sun4i_drv_node_is_tcon_with_ch0(struct device_node *node)
 
 static bool sun4i_drv_node_is_tcon_top(struct device_node *node)
 {
-	return !!of_match_node(sun8i_tcon_top_of_table, node);
+	return IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
+		!!of_match_node(sun8i_tcon_top_of_table, node);
 }
 
 static int compare_of(struct device *dev, void *data)
diff --git a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
index 4cbe744e15a9..31875b636434 100644
--- a/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
+++ b/drivers/gpu/drm/sun4i/sun8i_dw_hdmi.c
@@ -44,7 +44,8 @@ sun8i_dw_hdmi_mode_valid(struct drm_connector *connector,
 
 static bool sun8i_dw_hdmi_node_is_tcon_top(struct device_node *node)
 {
-	return !!of_match_node(sun8i_tcon_top_of_table, node);
+	return IS_ENABLED(CONFIG_DRM_SUN8I_TCON_TOP) &&
+		!!of_match_node(sun8i_tcon_top_of_table, node);
 }
 
 static u32 sun8i_dw_hdmi_find_possible_crtcs(struct drm_device *drm,
-- 
cgit v1.2.3


From d6b4ea866b8117c1c4a048e2e2dadf0c83776a84 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Thu, 12 Jul 2018 08:41:03 +0100
Subject: drm/i915/tv: fix strncpy truncation warning

Change it to use strlcpy instead

Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712074103.21571-1-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_tv.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index 24dc368fdaa1..b5b04cb892e9 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1347,8 +1347,7 @@ intel_tv_get_modes(struct drm_connector *connector)
 		mode_ptr = drm_mode_create(connector->dev);
 		if (!mode_ptr)
 			continue;
-		strncpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN);
-		mode_ptr->name[DRM_DISPLAY_MODE_LEN - 1] = '\0';
+		strlcpy(mode_ptr->name, input->name, DRM_DISPLAY_MODE_LEN);
 
 		mode_ptr->hdisplay = hactive_s;
 		mode_ptr->hsync_start = hactive_s + 1;
-- 
cgit v1.2.3


From e87a4a92fba3721eb06ba8d061b550e09e3d063a Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Thu, 12 Jul 2018 11:37:40 +0100
Subject: Revert "arm64: fix infinite stacktrace"

This reverts commit 7e7df71fd57ff2894d96abb0080922bf39460a79.

When unwinding out of the IRQ stack and onto the interrupted EL1 stack,
we cannot rely on the frame pointer being strictly increasing, as this
could terminate the backtrace early depending on how the stacks have
been allocated.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/stacktrace.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index e160ca123da3..d5718a060672 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -56,9 +56,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
 	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
 
-	if (frame->fp <= fp)
-		return -EINVAL;
-
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	if (tsk->ret_stack &&
 			(frame->pc == (unsigned long)return_to_handler)) {
-- 
cgit v1.2.3


From ee12c9efe685428ebfae1bf5347b5375f54ce44e Mon Sep 17 00:00:00 2001
From: Alan Douglas <adouglas@cadence.com>
Date: Mon, 25 Jun 2018 09:30:52 +0100
Subject: PCI: cadence: Add Power Management ops for host and EP

These PM ops will enable/disable the optional PHYs if present.  The
AXI link-down register in the host driver is now cleared in
cdns_pci_map_bus() since the link-down bit will be set if the PHY has
been disabled. It is not cleared when enabling the PHY, since the
link will not yet be up (e.g. when an EP controller is connected
back-to-back to the host controller and its PHY is still disabled).

Link: http://lkml.kernel.org/r/1529915453-4633-5-git-send-email-adouglas@cadence.com
Signed-off-by: Alan Douglas <adouglas@cadence.com>
[lorenzo.pieralisi@arm.com: updated commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pcie-cadence-ep.c   |  1 +
 drivers/pci/controller/pcie-cadence-host.c |  3 +++
 drivers/pci/controller/pcie-cadence.c      | 30 ++++++++++++++++++++++++++++++
 drivers/pci/controller/pcie-cadence.h      |  4 ++++
 4 files changed, 38 insertions(+)

diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c
index c02f33d8e506..3eabd99a1233 100644
--- a/drivers/pci/controller/pcie-cadence-ep.c
+++ b/drivers/pci/controller/pcie-cadence-ep.c
@@ -555,6 +555,7 @@ static struct platform_driver cdns_pcie_ep_driver = {
 	.driver = {
 		.name = "cdns-pcie-ep",
 		.of_match_table = cdns_pcie_ep_of_match,
+		.pm	= &cdns_pcie_pm_ops,
 	},
 	.probe = cdns_pcie_ep_probe,
 	.shutdown = cdns_pcie_ep_shutdown,
diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c
index 36f31092562f..e3e9b7de8592 100644
--- a/drivers/pci/controller/pcie-cadence-host.c
+++ b/drivers/pci/controller/pcie-cadence-host.c
@@ -61,6 +61,8 @@ static void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn,
 	/* Check that the link is up */
 	if (!(cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE) & 0x1))
 		return NULL;
+	/* Clear AXI link-down status */
+	cdns_pcie_writel(pcie, CDNS_PCIE_AT_LINKDOWN, 0x0);
 
 	/* Update Output registers for AXI region 0. */
 	addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(12) |
@@ -345,6 +347,7 @@ static struct platform_driver cdns_pcie_host_driver = {
 	.driver = {
 		.name = "cdns-pcie-host",
 		.of_match_table = cdns_pcie_host_of_match,
+		.pm	= &cdns_pcie_pm_ops,
 	},
 	.probe = cdns_pcie_host_probe,
 };
diff --git a/drivers/pci/controller/pcie-cadence.c b/drivers/pci/controller/pcie-cadence.c
index 2edc12661e44..86f1b002c846 100644
--- a/drivers/pci/controller/pcie-cadence.c
+++ b/drivers/pci/controller/pcie-cadence.c
@@ -217,3 +217,33 @@ err_link:
 
 	return ret;
 }
+
+#ifdef CONFIG_PM_SLEEP
+static int cdns_pcie_suspend_noirq(struct device *dev)
+{
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
+
+	cdns_pcie_disable_phy(pcie);
+
+	return 0;
+}
+
+static int cdns_pcie_resume_noirq(struct device *dev)
+{
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
+	int ret;
+
+	ret = cdns_pcie_enable_phy(pcie);
+	if (ret) {
+		dev_err(dev, "failed to enable phy\n");
+		return ret;
+	}
+
+	return 0;
+}
+#endif
+
+const struct dev_pm_ops cdns_pcie_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(cdns_pcie_suspend_noirq,
+				      cdns_pcie_resume_noirq)
+};
diff --git a/drivers/pci/controller/pcie-cadence.h b/drivers/pci/controller/pcie-cadence.h
index b342c808f7d6..ae6bf2a2b3d3 100644
--- a/drivers/pci/controller/pcie-cadence.h
+++ b/drivers/pci/controller/pcie-cadence.h
@@ -166,6 +166,9 @@
 #define CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar) \
 	(CDNS_PCIE_AT_BASE + 0x0804 + (bar) * 0x0008)
 
+/* AXI link down register */
+#define CDNS_PCIE_AT_LINKDOWN (CDNS_PCIE_AT_BASE + 0x0824)
+
 enum cdns_pcie_rp_bar {
 	RP_BAR0,
 	RP_BAR1,
@@ -314,5 +317,6 @@ void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r);
 void cdns_pcie_disable_phy(struct cdns_pcie *pcie);
 int cdns_pcie_enable_phy(struct cdns_pcie *pcie);
 int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie);
+extern const struct dev_pm_ops cdns_pcie_pm_ops;
 
 #endif /* _PCIE_CADENCE_H */
-- 
cgit v1.2.3


From 0ae7383e83c6b1cea1e31173e362765dc24068c7 Mon Sep 17 00:00:00 2001
From: Alan Douglas <adouglas@cadence.com>
Date: Mon, 25 Jun 2018 09:30:53 +0100
Subject: PCI: cadence: Add shutdown callback to host driver

Add shutdown callback to host driver which will disable PHY and
PM runtime.

Signed-off-by: Alan Douglas <adouglas@cadence.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pcie-cadence-host.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c
index e3e9b7de8592..ec394f6a19c8 100644
--- a/drivers/pci/controller/pcie-cadence-host.c
+++ b/drivers/pci/controller/pcie-cadence-host.c
@@ -343,6 +343,20 @@ static int cdns_pcie_host_probe(struct platform_device *pdev)
 	return ret;
 }
 
+static void cdns_pcie_shutdown(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct cdns_pcie *pcie = dev_get_drvdata(dev);
+	int ret;
+
+	ret = pm_runtime_put_sync(dev);
+	if (ret < 0)
+		dev_dbg(dev, "pm_runtime_put_sync failed\n");
+
+	pm_runtime_disable(dev);
+	cdns_pcie_disable_phy(pcie);
+}
+
 static struct platform_driver cdns_pcie_host_driver = {
 	.driver = {
 		.name = "cdns-pcie-host",
@@ -350,5 +364,6 @@ static struct platform_driver cdns_pcie_host_driver = {
 		.pm	= &cdns_pcie_pm_ops,
 	},
 	.probe = cdns_pcie_host_probe,
+	.shutdown = cdns_pcie_shutdown,
 };
 builtin_platform_driver(cdns_pcie_host_driver);
-- 
cgit v1.2.3


From 818fed4f25bbfa729096d2adcdc779c52c932fa7 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Jul 2018 11:54:54 +0100
Subject: drm/i915: Silence warning for no vlv powercontext

Along a module load error path, we may try to cleanup the powercontext
even before we have allocated it.  Reorganising GT powermanagement is an
 on going process, so for simplicity handle it.

[  522.733832] WARN_ON(!dev_priv->vlv_pctx)
[  522.733986] WARNING: CPU: 1 PID: 3856 at drivers/gpu/drm/i915/intel_pm.c:7350 intel_cleanup_gt_powersave+0x5f/0x70 [i915]
[  522.733991] Modules linked in: i915(+) vgem snd_hda_codec_hdmi snd_hda_codec_realtek snd_hda_codec_generic btusb btrtl btbcm btintel intel_powerclamp coretemp crct10dif_pclmul crc32_pclmul bluetooth snd_hda_codec ghash_clmulni_intel snd_hwdep snd_hda_core ecdh_generic lpc_ich r8169 snd_pcm mii i2c_hid prime_numbers [last unloaded: i915]
[  522.734105] CPU: 1 PID: 3856 Comm: drv_module_relo Tainted: G     U            4.18.0-rc4-CI-CI_DRM_4474+ #1
[  522.734110] Hardware name: \xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff \xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff\xff/DN2820FYK, BIOS FYBYT10H.86A.0059.2017.0607.2130 06/07/2017
[  522.734193] RIP: 0010:intel_cleanup_gt_powersave+0x5f/0x70 [i915]
[  522.734197] Code: 00 74 0d 48 c7 83 68 a6 00 00 00 00 00 00 eb c8 e8 36 6f 37 e1 eb ec 48 c7 c6 c5 7a 3d a0 48 c7 c7 b5 78 3d a0 e8 71 04 e0 e0 <0f> 0b eb aa 0f 1f 00 66 2e 0f 1f 84 00 00 00 00 00 f3 c3 0f 1f 40
[  522.734445] RSP: 0018:ffffc900004f3af0 EFLAGS: 00010282
[  522.734453] RAX: 0000000000000000 RBX: ffff880106360000 RCX: 0000000000000001
[  522.734458] RDX: 0000000080000001 RSI: ffffffff820c65c4 RDI: 00000000ffffffff
[  522.734463] RBP: ffff880106360000 R08: 000000009f79baee R09: 0000000000000000
[  522.734467] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88013b3133f8
[  522.734472] R13: 00000000ffffffed R14: ffff880106360d58 R15: ffff88013b3133f8
[  522.734477] FS:  00007f43f70af980(0000) GS:ffff88013fd00000(0000) knlGS:0000000000000000
[  522.734481] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  522.734486] CR2: 000055a13a787580 CR3: 00000001325e6000 CR4: 00000000001006e0
[  522.734490] Call Trace:
[  522.734595]  intel_modeset_cleanup+0xcf/0x140 [i915]
[  522.734682]  i915_driver_load+0xc85/0x10a0 [i915]
[  522.734694]  ? _raw_spin_unlock_irqrestore+0x4c/0x60
[  522.734703]  ? trace_hardirqs_on_caller+0xe0/0x1b0
[  522.734790]  i915_pci_probe+0x29/0x90 [i915]
[  522.734801]  pci_device_probe+0xa1/0x130
[  522.734813]  driver_probe_device+0x306/0x480
[  522.734824]  __driver_attach+0xdb/0x100
[  522.734830]  ? driver_probe_device+0x480/0x480
[  522.734836]  ? driver_probe_device+0x480/0x480
[  522.734844]  bus_for_each_dev+0x74/0xc0
[  522.734855]  bus_add_driver+0x15f/0x250
[  522.734863]  ? 0xffffffffa0793000
[  522.734870]  driver_register+0x56/0xe0
[  522.734877]  ? 0xffffffffa0793000
[  522.734883]  do_one_initcall+0x58/0x370
[  522.734893]  ? do_init_module+0x1d/0x1ea
[  522.734900]  ? rcu_read_lock_sched_held+0x6f/0x80
[  522.734906]  ? kmem_cache_alloc_trace+0x282/0x2e0
[  522.734918]  do_init_module+0x56/0x1ea
[  522.734927]  load_module+0x2435/0x2b20
[  522.734965]  ? __se_sys_finit_module+0xd3/0xf0
[  522.734972]  __se_sys_finit_module+0xd3/0xf0
[  522.734995]  do_syscall_64+0x55/0x190
[  522.735003]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  522.735009] RIP: 0033:0x7f43f675d839
[  522.735014] Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1f f6 2c 00 f7 d8 64 89 01 48
[  522.735260] RSP: 002b:00007ffe69384238 EFLAGS: 00000246 ORIG_RAX: 0000000000000139
[  522.735269] RAX: ffffffffffffffda RBX: 000056100e387090 RCX: 00007f43f675d839
[  522.735273] RDX: 0000000000000000 RSI: 000056100e37bff0 RDI: 0000000000000003
[  522.735278] RBP: 000056100e37bff0 R08: 0000000000000000 R09: 0000000000000000
[  522.735282] R10: 0000000000000003 R11: 0000000000000246 R12: 0000000000000000
[  522.735286] R13: 000056100e37c890 R14: 0000000000000020 R15: 0000000000000027
[  522.735309] irq event stamp: 1389594
[  522.735316] hardirqs last  enabled at (1389593): [<ffffffff810f896c>] console_unlock+0x3fc/0x600
[  522.735323] hardirqs last disabled at (1389594): [<ffffffff81a0111c>] error_entry+0x7c/0x100
[  522.735329] softirqs last  enabled at (1389356): [<ffffffff81c0034f>] __do_softirq+0x34f/0x505
[  522.735336] softirqs last disabled at (1389335): [<ffffffff8108c7b9>] irq_exit+0xa9/0xc0
[  522.735432] WARNING: CPU: 1 PID: 3856 at drivers/gpu/drm/i915/intel_pm.c:7350 intel_cleanup_gt_powersave+0x5f/0x70 [i915]

Testcase: igt/drv_module_reload/basic-reload-inject
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712105454.16091-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_pm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 53aaaa3e6886..7312ecb73415 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -7347,11 +7347,11 @@ out:
 
 static void valleyview_cleanup_pctx(struct drm_i915_private *dev_priv)
 {
-	if (WARN_ON(!dev_priv->vlv_pctx))
-		return;
+	struct drm_i915_gem_object *pctx;
 
-	i915_gem_object_put(dev_priv->vlv_pctx);
-	dev_priv->vlv_pctx = NULL;
+	pctx = fetch_and_zero(&dev_priv->vlv_pctx);
+	if (pctx)
+		i915_gem_object_put(pctx);
 }
 
 static void vlv_init_gpll_ref_freq(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From 5bfbeacf1983de58782b3aeb59b87d216091751c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Jul 2018 11:58:30 +0100
Subject: drm/i915/guc: Skip cleaning up the doorbells on error-before-allocate
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If we fail the module load, we may try and cleanup before we even
allocate the GuC clients. KISS in order to try and re-enable
drv_module_reload for BAT.

Testcase: igt/drv_module_reload/basic-reload-inject
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712105830.20390-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 3952656f4c9a..cd51be8ff025 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -910,8 +910,12 @@ static void guc_clients_doorbell_fini(struct intel_guc *guc)
 		__update_doorbell_desc(guc->preempt_client,
 				       GUC_DOORBELL_INVALID);
 	}
-	__destroy_doorbell(guc->execbuf_client);
-	__update_doorbell_desc(guc->execbuf_client, GUC_DOORBELL_INVALID);
+
+	if (guc->execbuf_client) {
+		__destroy_doorbell(guc->execbuf_client);
+		__update_doorbell_desc(guc->execbuf_client,
+				       GUC_DOORBELL_INVALID);
+	}
 }
 
 /**
-- 
cgit v1.2.3


From 3eb6f1f9e6364d5eca1ddf3c9e963c5916069190 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:36 +0100
Subject: arm64: consistently use unsigned long for thread flags

In do_notify_resume, we manipulate thread_flags as a 32-bit unsigned
int, whereas thread_info::flags is a 64-bit unsigned long, and elsewhere
(e.g. in the entry assembly) we manipulate the flags as a 64-bit
quantity.

For consistency, and to avoid problems if we end up with more than 32
flags, let's make do_notify_resume take the flags as a 64-bit unsigned
long.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/signal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index e3b1d1b0aee8..5a8df96dc4ab 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -912,7 +912,7 @@ static void do_signal(struct pt_regs *regs)
 }
 
 asmlinkage void do_notify_resume(struct pt_regs *regs,
-				 unsigned int thread_flags)
+				 unsigned long thread_flags)
 {
 	/*
 	 * The assembly code enters us with IRQs off, but it hasn't
-- 
cgit v1.2.3


From 1c312e84c2d71da4101754fa6118f703f7473e01 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:37 +0100
Subject: arm64: move SCTLR_EL{1,2} assertions to <asm/sysreg.h>

Currently we assert that the SCTLR_EL{1,2}_{SET,CLEAR} bits are
self-consistent with an assertion in config_sctlr_el1(). This is a bit
unusual, since config_sctlr_el1() doesn't make use of these definitions,
and is far away from the definitions themselves.

We can use the CPP #error directive to have equivalent assertions in
<asm/sysreg.h>, next to the definitions of the set/clear bits, which is
a bit clearer and simpler.

At the same time, lets fill in the upper 32 bits for both registers in
their respective RES0 definitions. This could be a little nicer with
GENMASK_ULL(63, 32), but this currently lives in <linux/bitops.h>, which
cannot safely be included from assembly, as <asm/sysreg.h> can.

Note the when the preprocessor evaluates an expression for an #if
directive, all signed or unsigned values are treated as intmax_t or
uintmax_t respectively. To avoid ambiguity, we define explicitly define
the mask of all 64 bits.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Dave Martin <dave.martin@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/sysreg.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index a8f84812c6e8..fefc17dae8ee 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -436,7 +436,8 @@
 #define SCTLR_EL2_RES0	((1 << 6)  | (1 << 7)  | (1 << 8)  | (1 << 9)  | \
 			 (1 << 10) | (1 << 13) | (1 << 14) | (1 << 15) | \
 			 (1 << 17) | (1 << 20) | (1 << 24) | (1 << 26) | \
-			 (1 << 27) | (1 << 30) | (1 << 31))
+			 (1 << 27) | (1 << 30) | (1 << 31) | \
+			 (0xffffffffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL2		SCTLR_ELx_EE
@@ -452,9 +453,9 @@
 			 SCTLR_ELx_SA     | SCTLR_ELx_I    | SCTLR_ELx_WXN | \
 			 ENDIAN_CLEAR_EL2 | SCTLR_EL2_RES0)
 
-/* Check all the bits are accounted for */
-#define SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS	BUILD_BUG_ON((SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != ~0)
-
+#if (SCTLR_EL2_SET ^ SCTLR_EL2_CLEAR) != 0xffffffffffffffff
+#error "Inconsistent SCTLR_EL2 set/clear bits"
+#endif
 
 /* SCTLR_EL1 specific flags. */
 #define SCTLR_EL1_UCI		(1 << 26)
@@ -473,7 +474,8 @@
 #define SCTLR_EL1_RES1	((1 << 11) | (1 << 20) | (1 << 22) | (1 << 28) | \
 			 (1 << 29))
 #define SCTLR_EL1_RES0  ((1 << 6)  | (1 << 10) | (1 << 13) | (1 << 17) | \
-			 (1 << 27) | (1 << 30) | (1 << 31))
+			 (1 << 27) | (1 << 30) | (1 << 31) | \
+			 (0xffffffffUL << 32))
 
 #ifdef CONFIG_CPU_BIG_ENDIAN
 #define ENDIAN_SET_EL1		(SCTLR_EL1_E0E | SCTLR_ELx_EE)
@@ -492,8 +494,9 @@
 			 SCTLR_EL1_UMA | SCTLR_ELx_WXN     | ENDIAN_CLEAR_EL1 |\
 			 SCTLR_EL1_RES0)
 
-/* Check all the bits are accounted for */
-#define SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS	BUILD_BUG_ON((SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != ~0)
+#if (SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != 0xffffffffffffffff
+#error "Inconsistent SCTLR_EL1 set/clear bits"
+#endif
 
 /* id_aa64isar0 */
 #define ID_AA64ISAR0_TS_SHIFT		52
@@ -743,9 +746,6 @@ static inline void config_sctlr_el1(u32 clear, u32 set)
 {
 	u32 val;
 
-	SCTLR_EL2_BUILD_BUG_ON_MISSING_BITS;
-	SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS;
-
 	val = read_sysreg(sctlr_el1);
 	val &= ~clear;
 	val |= set;
-- 
cgit v1.2.3


From 25be597ada0b49d2748ab520a78a28c1764d69e4 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:38 +0100
Subject: arm64: kill config_sctlr_el1()

Now that we have sysreg_clear_set(), we can consistently use this
instead of config_sctlr_el1().

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/sysreg.h      | 10 ----------
 arch/arm64/kernel/armv8_deprecated.c |  8 ++++----
 arch/arm64/kernel/cpu_errata.c       |  3 +--
 arch/arm64/kernel/traps.c            |  2 +-
 arch/arm64/mm/fault.c                |  2 +-
 5 files changed, 7 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index fefc17dae8ee..e205ec8489e9 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -742,16 +742,6 @@ asm(
 		write_sysreg(__scs_new, sysreg);			\
 } while (0)
 
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
-	u32 val;
-
-	val = read_sysreg(sctlr_el1);
-	val &= ~clear;
-	val |= set;
-	write_sysreg(val, sctlr_el1);
-}
-
 #endif
 
 #endif	/* __ASM_SYSREG_H */
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index d2c0938ccaec..92be1d12d590 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -511,9 +511,9 @@ ret:
 static int cp15_barrier_set_hw_mode(bool enable)
 {
 	if (enable)
-		config_sctlr_el1(0, SCTLR_EL1_CP15BEN);
+		sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_CP15BEN);
 	else
-		config_sctlr_el1(SCTLR_EL1_CP15BEN, 0);
+		sysreg_clear_set(sctlr_el1, SCTLR_EL1_CP15BEN, 0);
 	return 0;
 }
 
@@ -548,9 +548,9 @@ static int setend_set_hw_mode(bool enable)
 		return -EINVAL;
 
 	if (enable)
-		config_sctlr_el1(SCTLR_EL1_SED, 0);
+		sysreg_clear_set(sctlr_el1, SCTLR_EL1_SED, 0);
 	else
-		config_sctlr_el1(0, SCTLR_EL1_SED);
+		sysreg_clear_set(sctlr_el1, 0, SCTLR_EL1_SED);
 	return 0;
 }
 
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 94876ab071c7..dec10898d688 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -82,8 +82,7 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 static void
 cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *__unused)
 {
-	/* Clear SCTLR_EL1.UCT */
-	config_sctlr_el1(SCTLR_EL1_UCT, 0);
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCT, 0);
 }
 
 atomic_t arm64_el2_vector_last_slot = ATOMIC_INIT(-1);
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index d399d459397b..c27292703bd1 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -411,7 +411,7 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 
 void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused)
 {
-	config_sctlr_el1(SCTLR_EL1_UCI, 0);
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_UCI, 0);
 }
 
 #define __user_cache_maint(insn, address, res)			\
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index b8eecc7b9531..ea591c9e5144 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -879,7 +879,7 @@ void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused)
 	 */
 	WARN_ON_ONCE(in_interrupt());
 
-	config_sctlr_el1(SCTLR_EL1_SPAN, 0);
+	sysreg_clear_set(sctlr_el1, SCTLR_EL1_SPAN, 0);
 	asm(SET_PSTATE_PAN(1));
 }
 #endif /* CONFIG_ARM64_PAN */
-- 
cgit v1.2.3


From 8d370933faecec098acb99fbf317cf9dfa9ee995 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:39 +0100
Subject: arm64: kill change_cpacr()

Now that we have sysreg_clear_set(), we can use this instead of
change_cpacr().

Note that the order of the set and clear arguments differs between
change_cpacr() and sysreg_clear_set(), so these are flipped as part of
the conversion. Also, sve_user_enable() redundantly clears
CPACR_EL1_ZEN_EL0EN before setting it; this is removed for clarity.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/fpsimd.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index 84c68b14f1b2..a98a7f96aff1 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -159,23 +159,14 @@ static void sve_free(struct task_struct *task)
 	__sve_free(task);
 }
 
-static void change_cpacr(u64 val, u64 mask)
-{
-	u64 cpacr = read_sysreg(CPACR_EL1);
-	u64 new = (cpacr & ~mask) | val;
-
-	if (new != cpacr)
-		write_sysreg(new, CPACR_EL1);
-}
-
 static void sve_user_disable(void)
 {
-	change_cpacr(0, CPACR_EL1_ZEN_EL0EN);
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0);
 }
 
 static void sve_user_enable(void)
 {
-	change_cpacr(CPACR_EL1_ZEN_EL0EN, CPACR_EL1_ZEN_EL0EN);
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN);
 }
 
 /*
-- 
cgit v1.2.3


From f9209e26293300db80a57a6bf2f71ccb26ad45db Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:40 +0100
Subject: arm64: move sve_user_{enable,disable} to <asm/fpsimd.h>

In subsequent patches, we'll want to make use of sve_user_enable() and
sve_user_disable() outside of kernel/fpsimd.c. Let's move these to
<asm/fpsimd.h> where we can make use of them.

To avoid ifdeffery in sequences like:

if (system_supports_sve() && some_condition)
	sve_user_disable();

... empty stubs are provided when support for SVE is not enabled. Note
that system_supports_sve() contains as IS_ENABLED(CONFIG_ARM64_SVE), so
the sve_user_disable() call should be optimized away entirely when
CONFIG_ARM64_SVE is not selected.

To ensure that this is the case, the stub definitions contain a
BUILD_BUG(), as we do for other stubs for which calls should always be
optimized away when the relevant config option is not selected.

At the same time, the include list of <asm/fpsimd.h> is sorted while
adding <asm/sysreg.h>.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/fpsimd.h | 17 ++++++++++++++++-
 arch/arm64/kernel/fpsimd.c      | 10 ----------
 2 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index fa92747a49c8..dd1ad3950ef5 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -16,13 +16,15 @@
 #ifndef __ASM_FP_H
 #define __ASM_FP_H
 
-#include <asm/ptrace.h>
 #include <asm/errno.h>
+#include <asm/ptrace.h>
 #include <asm/processor.h>
 #include <asm/sigcontext.h>
+#include <asm/sysreg.h>
 
 #ifndef __ASSEMBLY__
 
+#include <linux/build_bug.h>
 #include <linux/cache.h>
 #include <linux/init.h>
 #include <linux/stddef.h>
@@ -102,6 +104,16 @@ extern int sve_set_vector_length(struct task_struct *task,
 extern int sve_set_current_vl(unsigned long arg);
 extern int sve_get_current_vl(void);
 
+static inline void sve_user_disable(void)
+{
+	sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0);
+}
+
+static inline void sve_user_enable(void)
+{
+	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN);
+}
+
 /*
  * Probing and setup functions.
  * Calls to these functions must be serialised with one another.
@@ -128,6 +140,9 @@ static inline int sve_get_current_vl(void)
 	return -EINVAL;
 }
 
+static inline void sve_user_disable(void) { BUILD_BUG(); }
+static inline void sve_user_enable(void) { BUILD_BUG(); }
+
 static inline void sve_init_vq_map(void) { }
 static inline void sve_update_vq_map(void) { }
 static inline int sve_verify_vq_map(void) { return 0; }
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index a98a7f96aff1..58c53bc96928 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -159,16 +159,6 @@ static void sve_free(struct task_struct *task)
 	__sve_free(task);
 }
 
-static void sve_user_disable(void)
-{
-	sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0);
-}
-
-static void sve_user_enable(void)
-{
-	sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN);
-}
-
 /*
  * TIF_SVE controls whether a task can use SVE without trapping while
  * in userspace, and also the way a task's FPSIMD/SVE state is stored
-- 
cgit v1.2.3


From 3085e1645e23888125224f66a710077cdb03106a Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:41 +0100
Subject: arm64: remove sigreturn wrappers

The arm64 sigreturn* syscall handlers are non-standard. Rather than
taking a number of user parameters in registers as per the AAPCS,
they expect the pt_regs as their sole argument.

To make this work, we override the syscall definitions to invoke
wrappers written in assembly, which mov the SP into x0, and branch to
their respective C functions.

On other architectures (such as x86), the sigreturn* functions take no
argument and instead use current_pt_regs() to acquire the user
registers. This requires less boilerplate code, and allows for other
features such as interposing C code in this path.

This patch takes the same approach for arm64.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tentatively-reviewed-by: Dave Martin <dave.martin@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/unistd32.h |  4 ++--
 arch/arm64/kernel/entry.S         |  8 --------
 arch/arm64/kernel/entry32.S       | 10 ----------
 arch/arm64/kernel/signal.c        |  3 ++-
 arch/arm64/kernel/signal32.c      |  6 ++++--
 arch/arm64/kernel/sys.c           |  3 +--
 arch/arm64/kernel/sys32.c         |  4 ++--
 7 files changed, 11 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 0fdc7ef8a776..023d64af8339 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -260,7 +260,7 @@ __SYSCALL(117, sys_ni_syscall)
 #define __NR_fsync 118
 __SYSCALL(__NR_fsync, sys_fsync)
 #define __NR_sigreturn 119
-__SYSCALL(__NR_sigreturn, compat_sys_sigreturn_wrapper)
+__SYSCALL(__NR_sigreturn, compat_sys_sigreturn)
 #define __NR_clone 120
 __SYSCALL(__NR_clone, sys_clone)
 #define __NR_setdomainname 121
@@ -368,7 +368,7 @@ __SYSCALL(__NR_getresgid, sys_getresgid16)
 #define __NR_prctl 172
 __SYSCALL(__NR_prctl, sys_prctl)
 #define __NR_rt_sigreturn 173
-__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn_wrapper)
+__SYSCALL(__NR_rt_sigreturn, compat_sys_rt_sigreturn)
 #define __NR_rt_sigaction 174
 __SYSCALL(__NR_rt_sigaction, compat_sys_rt_sigaction)
 #define __NR_rt_sigprocmask 175
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 1eda9e1a1f4a..201809537343 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -1139,14 +1139,6 @@ __entry_tramp_data_start:
 #endif /* CONFIG_RANDOMIZE_BASE */
 #endif /* CONFIG_UNMAP_KERNEL_AT_EL0 */
 
-/*
- * Special system call wrappers.
- */
-ENTRY(sys_rt_sigreturn_wrapper)
-	mov	x0, sp
-	b	sys_rt_sigreturn
-ENDPROC(sys_rt_sigreturn_wrapper)
-
 /*
  * Register switch for AArch64. The callee-saved registers need to be saved
  * and restored. On entry:
diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S
index f332d5d1f6b4..f9461696dde4 100644
--- a/arch/arm64/kernel/entry32.S
+++ b/arch/arm64/kernel/entry32.S
@@ -30,16 +30,6 @@
  * System call wrappers for the AArch32 compatibility layer.
  */
 
-ENTRY(compat_sys_sigreturn_wrapper)
-	mov	x0, sp
-	b	compat_sys_sigreturn
-ENDPROC(compat_sys_sigreturn_wrapper)
-
-ENTRY(compat_sys_rt_sigreturn_wrapper)
-	mov	x0, sp
-	b	compat_sys_rt_sigreturn
-ENDPROC(compat_sys_rt_sigreturn_wrapper)
-
 ENTRY(compat_sys_statfs64_wrapper)
 	mov	w3, #84
 	cmp	w1, #88
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 5a8df96dc4ab..b6f3c3d76901 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -539,8 +539,9 @@ static int restore_sigframe(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage long sys_rt_sigreturn(struct pt_regs *regs)
+asmlinkage long sys_rt_sigreturn(void)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index fca761be18c8..9aac1253e0a6 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -285,8 +285,9 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage int compat_sys_sigreturn(struct pt_regs *regs)
+asmlinkage int compat_sys_sigreturn(void)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct compat_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
@@ -315,8 +316,9 @@ badframe:
 	return 0;
 }
 
-asmlinkage int compat_sys_rt_sigreturn(struct pt_regs *regs)
+asmlinkage int compat_sys_rt_sigreturn(void)
 {
+	struct pt_regs *regs = current_pt_regs();
 	struct compat_rt_sigframe __user *frame;
 
 	/* Always make any pending restarted system calls return -EINTR */
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index 72981bae10eb..31045f3fed92 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -48,8 +48,7 @@ SYSCALL_DEFINE1(arm64_personality, unsigned int, personality)
 /*
  * Wrappers to pass the pt_regs argument.
  */
-asmlinkage long sys_rt_sigreturn_wrapper(void);
-#define sys_rt_sigreturn	sys_rt_sigreturn_wrapper
+asmlinkage long sys_rt_sigreturn(void);
 #define sys_personality		sys_arm64_personality
 
 #undef __SYSCALL
diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c
index a40b1343b819..1ef103c95410 100644
--- a/arch/arm64/kernel/sys32.c
+++ b/arch/arm64/kernel/sys32.c
@@ -25,8 +25,8 @@
 #include <linux/compiler.h>
 #include <linux/syscalls.h>
 
-asmlinkage long compat_sys_sigreturn_wrapper(void);
-asmlinkage long compat_sys_rt_sigreturn_wrapper(void);
+asmlinkage long compat_sys_sigreturn(void);
+asmlinkage long compat_sys_rt_sigreturn(void);
 asmlinkage long compat_sys_statfs64_wrapper(void);
 asmlinkage long compat_sys_fstatfs64_wrapper(void);
 asmlinkage long compat_sys_pread64_wrapper(void);
-- 
cgit v1.2.3


From 27d83e68f307ee55b70fdfdc7a9ba3f25f276189 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:42 +0100
Subject: arm64: introduce syscall_fn_t

In preparation for invoking arbitrary syscalls from C code, let's define
a type for an arbitrary syscall, matching the parameter passing rules of
the AAPCS.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/syscall.h | 6 +++++-
 arch/arm64/kernel/sys.c          | 8 +++++---
 arch/arm64/kernel/sys32.c        | 8 +++++---
 3 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 709a574468f0..50841cb1bfa9 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -20,7 +20,11 @@
 #include <linux/compat.h>
 #include <linux/err.h>
 
-extern const void *sys_call_table[];
+typedef long (*syscall_fn_t)(unsigned long, unsigned long,
+			     unsigned long, unsigned long,
+			     unsigned long, unsigned long);
+
+extern const syscall_fn_t sys_call_table[];
 
 static inline int syscall_get_nr(struct task_struct *task,
 				 struct pt_regs *regs)
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index 31045f3fed92..7f0907261269 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -25,7 +25,9 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
+
 #include <asm/cpufeature.h>
+#include <asm/syscall.h>
 
 asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
 			 unsigned long prot, unsigned long flags,
@@ -52,13 +54,13 @@ asmlinkage long sys_rt_sigreturn(void);
 #define sys_personality		sys_arm64_personality
 
 #undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = sym,
+#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)sym,
 
 /*
  * The sys_call_table array must be 4K aligned to be accessible from
  * kernel/entry.S.
  */
-void * const sys_call_table[__NR_syscalls] __aligned(4096) = {
-	[0 ... __NR_syscalls - 1] = sys_ni_syscall,
+const syscall_fn_t sys_call_table[__NR_syscalls] __aligned(4096) = {
+	[0 ... __NR_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
 #include <asm/unistd.h>
 };
diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c
index 1ef103c95410..d993214118aa 100644
--- a/arch/arm64/kernel/sys32.c
+++ b/arch/arm64/kernel/sys32.c
@@ -25,6 +25,8 @@
 #include <linux/compiler.h>
 #include <linux/syscalls.h>
 
+#include <asm/syscall.h>
+
 asmlinkage long compat_sys_sigreturn(void);
 asmlinkage long compat_sys_rt_sigreturn(void);
 asmlinkage long compat_sys_statfs64_wrapper(void);
@@ -40,13 +42,13 @@ asmlinkage long compat_sys_fallocate_wrapper(void);
 asmlinkage long compat_sys_mmap2_wrapper(void);
 
 #undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = sym,
+#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)sym,
 
 /*
  * The sys_call_table array must be 4K aligned to be accessible from
  * kernel/entry.S.
  */
-void * const compat_sys_call_table[__NR_compat_syscalls] __aligned(4096) = {
-	[0 ... __NR_compat_syscalls - 1] = sys_ni_syscall,
+const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] __aligned(4096) = {
+	[0 ... __NR_compat_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
 #include <asm/unistd32.h>
 };
-- 
cgit v1.2.3


From 4141c857fd09dbed480f021b3eece4f46c653161 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:43 +0100
Subject: arm64: convert raw syscall invocation to C

As a first step towards invoking syscalls with a pt_regs argument,
convert the raw syscall invocation logic to C. We end up with a bit more
register shuffling, but the unified invocation logic means we can unify
the tracing paths, too.

Previously, assembly had to open-code calls to ni_sys() when the system
call number was out-of-bounds for the relevant syscall table. This case
is now handled by invoke_syscall(), and the assembly no longer need to
handle this case explicitly. This allows the tracing paths to be
simplified and unified, as we no longer need the __ni_sys_trace path and
the __sys_trace_return label.

This only converts the invocation of the syscall. The rest of the
syscall triage and tracing is left in assembly for now, and will be
converted in subsequent patches.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/Makefile  |  3 ++-
 arch/arm64/kernel/entry.S   | 36 ++++++++++------------------------
 arch/arm64/kernel/syscall.c | 47 +++++++++++++++++++++++++++++++++++++++++++++
 arch/arm64/kernel/traps.c   | 16 ---------------
 4 files changed, 59 insertions(+), 43 deletions(-)
 create mode 100644 arch/arm64/kernel/syscall.c

diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 0025f8691046..4e24d2244bd1 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -18,7 +18,8 @@ arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   hyp-stub.o psci.o cpu_ops.o insn.o	\
 			   return_address.o cpuinfo.o cpu_errata.o		\
 			   cpufeature.o alternative.o cacheinfo.o		\
-			   smp.o smp_spin_table.o topology.o smccc-call.o
+			   smp.o smp_spin_table.o topology.o smccc-call.o	\
+			   syscall.o
 
 extra-$(CONFIG_EFI)			:= efi-entry.o
 
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 201809537343..2045aec79ccb 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -903,7 +903,6 @@ ENDPROC(el0_error)
  */
 ret_fast_syscall:
 	disable_daif
-	str	x0, [sp, #S_X0]			// returned x0
 #ifndef CONFIG_DEBUG_RSEQ
 	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
@@ -978,15 +977,11 @@ el0_svc_naked:					// compat entry point
 
 	tst	x16, #_TIF_SYSCALL_WORK		// check for syscall hooks
 	b.ne	__sys_trace
-	cmp     wscno, wsc_nr			// check upper syscall limit
-	b.hs	ni_sys
-	mask_nospec64 xscno, xsc_nr, x19	// enforce bounds for syscall number
-	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
-	blr	x16				// call sys_* routine
-	b	ret_fast_syscall
-ni_sys:
 	mov	x0, sp
-	bl	do_ni_syscall
+	mov	w1, wscno
+	mov	w2, wsc_nr
+	mov	x3, stbl
+	bl	invoke_syscall
 	b	ret_fast_syscall
 ENDPROC(el0_svc)
 
@@ -1003,29 +998,18 @@ __sys_trace:
 	bl	syscall_trace_enter
 	cmp	w0, #NO_SYSCALL			// skip the syscall?
 	b.eq	__sys_trace_return_skipped
-	mov	wscno, w0			// syscall number (possibly new)
-	mov	x1, sp				// pointer to regs
-	cmp	wscno, wsc_nr			// check upper syscall limit
-	b.hs	__ni_sys_trace
-	ldp	x0, x1, [sp]			// restore the syscall args
-	ldp	x2, x3, [sp, #S_X2]
-	ldp	x4, x5, [sp, #S_X4]
-	ldp	x6, x7, [sp, #S_X6]
-	ldr	x16, [stbl, xscno, lsl #3]	// address in the syscall table
-	blr	x16				// call sys_* routine
 
-__sys_trace_return:
-	str	x0, [sp, #S_X0]			// save returned x0
+	mov	x0, sp
+	mov	w1, wscno
+	mov	w2, wsc_nr
+	mov	x3, stbl
+	bl	invoke_syscall
+
 __sys_trace_return_skipped:
 	mov	x0, sp
 	bl	syscall_trace_exit
 	b	ret_to_user
 
-__ni_sys_trace:
-	mov	x0, sp
-	bl	do_ni_syscall
-	b	__sys_trace_return
-
 	.popsection				// .entry.text
 
 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
new file mode 100644
index 000000000000..93d36f22647e
--- /dev/null
+++ b/arch/arm64/kernel/syscall.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/errno.h>
+#include <linux/nospec.h>
+#include <linux/ptrace.h>
+#include <linux/syscalls.h>
+
+#include <asm/syscall.h>
+
+long compat_arm_syscall(struct pt_regs *regs);
+
+asmlinkage long do_ni_syscall(struct pt_regs *regs)
+{
+#ifdef CONFIG_COMPAT
+	long ret;
+	if (is_compat_task()) {
+		ret = compat_arm_syscall(regs);
+		if (ret != -ENOSYS)
+			return ret;
+	}
+#endif
+
+	return sys_ni_syscall();
+}
+
+static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn)
+{
+	return syscall_fn(regs->regs[0], regs->regs[1], regs->regs[2],
+			  regs->regs[3], regs->regs[4], regs->regs[5]);
+}
+
+asmlinkage void invoke_syscall(struct pt_regs *regs, unsigned int scno,
+			       unsigned int sc_nr,
+			       const syscall_fn_t syscall_table[])
+{
+	long ret;
+
+	if (scno < sc_nr) {
+		syscall_fn_t syscall_fn;
+		syscall_fn = syscall_table[array_index_nospec(scno, sc_nr)];
+		ret = __invoke_syscall(regs, syscall_fn);
+	} else {
+		ret = do_ni_syscall(regs);
+	}
+
+	regs->regs[0] = ret;
+}
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index c27292703bd1..039e9ff379cc 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -547,22 +547,6 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 	do_undefinstr(regs);
 }
 
-long compat_arm_syscall(struct pt_regs *regs);
-
-asmlinkage long do_ni_syscall(struct pt_regs *regs)
-{
-#ifdef CONFIG_COMPAT
-	long ret;
-	if (is_compat_task()) {
-		ret = compat_arm_syscall(regs);
-		if (ret != -ENOSYS)
-			return ret;
-	}
-#endif
-
-	return sys_ni_syscall();
-}
-
 static const char *esr_class_str[] = {
 	[0 ... ESR_ELx_EC_MAX]		= "UNRECOGNIZED EC",
 	[ESR_ELx_EC_UNKNOWN]		= "Unknown/Uncategorized",
-- 
cgit v1.2.3


From f37099b6992a0b818c7b51b899e435f4006a9f90 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:44 +0100
Subject: arm64: convert syscall trace logic to C

Currently syscall tracing is a tricky assembly state machine, which can
be rather difficult to follow, and even harder to modify. Before we
start fiddling with it for pt_regs syscalls, let's convert it to C.

This is not intended to have any functional change.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/entry.S   | 55 ++-----------------------------------------
 arch/arm64/kernel/syscall.c | 57 ++++++++++++++++++++++++++++++++++++++++++---
 2 files changed, 56 insertions(+), 56 deletions(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 2045aec79ccb..05b9f03f3e00 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -896,26 +896,6 @@ el0_error_naked:
 	b	ret_to_user
 ENDPROC(el0_error)
 
-
-/*
- * This is the fast syscall return path.  We do as little as possible here,
- * and this includes saving x0 back into the kernel stack.
- */
-ret_fast_syscall:
-	disable_daif
-#ifndef CONFIG_DEBUG_RSEQ
-	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
-	and	x2, x1, #_TIF_SYSCALL_WORK
-	cbnz	x2, ret_fast_syscall_trace
-	and	x2, x1, #_TIF_WORK_MASK
-	cbnz	x2, work_pending
-	enable_step_tsk x1, x2
-	kernel_exit 0
-#endif
-ret_fast_syscall_trace:
-	enable_daif
-	b	__sys_trace_return_skipped	// we already saved x0
-
 /*
  * Ok, we need to do extra processing, enter the slow path.
  */
@@ -971,44 +951,13 @@ alternative_else_nop_endif
 #endif
 
 el0_svc_naked:					// compat entry point
-	stp	x0, xscno, [sp, #S_ORIG_X0]	// save the original x0 and syscall number
-	enable_daif
-	ct_user_exit 1
-
-	tst	x16, #_TIF_SYSCALL_WORK		// check for syscall hooks
-	b.ne	__sys_trace
 	mov	x0, sp
 	mov	w1, wscno
 	mov	w2, wsc_nr
 	mov	x3, stbl
-	bl	invoke_syscall
-	b	ret_fast_syscall
-ENDPROC(el0_svc)
-
-	/*
-	 * This is the really slow path.  We're going to be doing context
-	 * switches, and waiting for our parent to respond.
-	 */
-__sys_trace:
-	cmp     wscno, #NO_SYSCALL		// user-issued syscall(-1)?
-	b.ne	1f
-	mov	x0, #-ENOSYS			// set default errno if so
-	str	x0, [sp, #S_X0]
-1:	mov	x0, sp
-	bl	syscall_trace_enter
-	cmp	w0, #NO_SYSCALL			// skip the syscall?
-	b.eq	__sys_trace_return_skipped
-
-	mov	x0, sp
-	mov	w1, wscno
-	mov	w2, wsc_nr
-	mov	x3, stbl
-	bl	invoke_syscall
-
-__sys_trace_return_skipped:
-	mov	x0, sp
-	bl	syscall_trace_exit
+	bl	el0_svc_common
 	b	ret_to_user
+ENDPROC(el0_svc)
 
 	.popsection				// .entry.text
 
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 93d36f22647e..82098e6f6aa3 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -1,11 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/compiler.h>
+#include <linux/context_tracking.h>
 #include <linux/errno.h>
 #include <linux/nospec.h>
 #include <linux/ptrace.h>
 #include <linux/syscalls.h>
 
+#include <asm/daifflags.h>
 #include <asm/syscall.h>
+#include <asm/thread_info.h>
 
 long compat_arm_syscall(struct pt_regs *regs);
 
@@ -29,9 +33,9 @@ static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn)
 			  regs->regs[3], regs->regs[4], regs->regs[5]);
 }
 
-asmlinkage void invoke_syscall(struct pt_regs *regs, unsigned int scno,
-			       unsigned int sc_nr,
-			       const syscall_fn_t syscall_table[])
+static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
+			   unsigned int sc_nr,
+			   const syscall_fn_t syscall_table[])
 {
 	long ret;
 
@@ -45,3 +49,50 @@ asmlinkage void invoke_syscall(struct pt_regs *regs, unsigned int scno,
 
 	regs->regs[0] = ret;
 }
+
+static inline bool has_syscall_work(unsigned long flags)
+{
+	return unlikely(flags & _TIF_SYSCALL_WORK);
+}
+
+int syscall_trace_enter(struct pt_regs *regs);
+void syscall_trace_exit(struct pt_regs *regs);
+
+asmlinkage void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
+			       const syscall_fn_t syscall_table[])
+{
+	unsigned long flags = current_thread_info()->flags;
+
+	regs->orig_x0 = regs->regs[0];
+	regs->syscallno = scno;
+
+	local_daif_restore(DAIF_PROCCTX);
+	user_exit();
+
+	if (has_syscall_work(flags)) {
+		/* set default errno for user-issued syscall(-1) */
+		if (scno == NO_SYSCALL)
+			regs->regs[0] = -ENOSYS;
+		scno = syscall_trace_enter(regs);
+		if (scno == NO_SYSCALL)
+			goto trace_exit;
+	}
+
+	invoke_syscall(regs, scno, sc_nr, syscall_table);
+
+	/*
+	 * The tracing status may have changed under our feet, so we have to
+	 * check again. However, if we were tracing entry, then we always trace
+	 * exit regardless, as the old entry assembly did.
+	 */
+	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
+		local_daif_mask();
+		flags = current_thread_info()->flags;
+		if (!has_syscall_work(flags))
+			return;
+		local_daif_restore(DAIF_PROCCTX);
+	}
+
+trace_exit:
+	syscall_trace_exit(regs);
+}
-- 
cgit v1.2.3


From 3b7142752e4bee153df6db4a76ca104ef0d7c0b4 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:45 +0100
Subject: arm64: convert native/compat syscall entry to C

Now that the syscall invocation logic is in C, we can migrate the rest
of the syscall entry logic over, so that the entry assembly needn't look
at the register values at all.

The SVE reset across syscall logic now unconditionally clears TIF_SVE,
but sve_user_disable() will only write back to CPACR_EL1 when SVE is
actually enabled.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Dave Martin <dave.martin@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/syscall.h |  4 ++++
 arch/arm64/kernel/entry.S        | 42 ++++------------------------------------
 arch/arm64/kernel/syscall.c      | 37 +++++++++++++++++++++++++++++++++--
 3 files changed, 43 insertions(+), 40 deletions(-)

diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index 50841cb1bfa9..b83d0e6980a3 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -26,6 +26,10 @@ typedef long (*syscall_fn_t)(unsigned long, unsigned long,
 
 extern const syscall_fn_t sys_call_table[];
 
+#ifdef CONFIG_COMPAT
+extern const syscall_fn_t compat_sys_call_table[];
+#endif
+
 static inline int syscall_get_nr(struct task_struct *task,
 				 struct pt_regs *regs)
 {
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 05b9f03f3e00..156c4e3fd1a4 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -720,14 +720,9 @@ el0_sync_compat:
 	b.ge	el0_dbg
 	b	el0_inv
 el0_svc_compat:
-	/*
-	 * AArch32 syscall handling
-	 */
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
-	adrp	stbl, compat_sys_call_table	// load compat syscall table pointer
-	mov	wscno, w7			// syscall number in w7 (r7)
-	mov     wsc_nr, #__NR_compat_syscalls
-	b	el0_svc_naked
+	mov	x0, sp
+	bl	el0_svc_compat_handler
+	b	ret_to_user
 
 	.align	6
 el0_irq_compat:
@@ -925,37 +920,8 @@ ENDPROC(ret_to_user)
  */
 	.align	6
 el0_svc:
-	ldr	x16, [tsk, #TSK_TI_FLAGS]	// load thread flags
-	adrp	stbl, sys_call_table		// load syscall table pointer
-	mov	wscno, w8			// syscall number in w8
-	mov	wsc_nr, #__NR_syscalls
-
-#ifdef CONFIG_ARM64_SVE
-alternative_if_not ARM64_SVE
-	b	el0_svc_naked
-alternative_else_nop_endif
-	tbz	x16, #TIF_SVE, el0_svc_naked	// Skip unless TIF_SVE set:
-	bic	x16, x16, #_TIF_SVE		// discard SVE state
-	str	x16, [tsk, #TSK_TI_FLAGS]
-
-	/*
-	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
-	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
-	 * happens if a context switch or kernel_neon_begin() or context
-	 * modification (sigreturn, ptrace) intervenes.
-	 * So, ensure that CPACR_EL1 is already correct for the fast-path case:
-	 */
-	mrs	x9, cpacr_el1
-	bic	x9, x9, #CPACR_EL1_ZEN_EL0EN	// disable SVE for el0
-	msr	cpacr_el1, x9			// synchronised by eret to el0
-#endif
-
-el0_svc_naked:					// compat entry point
 	mov	x0, sp
-	mov	w1, wscno
-	mov	w2, wsc_nr
-	mov	x3, stbl
-	bl	el0_svc_common
+	bl	el0_svc_handler
 	b	ret_to_user
 ENDPROC(el0_svc)
 
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 82098e6f6aa3..7ff2d7b9f517 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -8,8 +8,10 @@
 #include <linux/syscalls.h>
 
 #include <asm/daifflags.h>
+#include <asm/fpsimd.h>
 #include <asm/syscall.h>
 #include <asm/thread_info.h>
+#include <asm/unistd.h>
 
 long compat_arm_syscall(struct pt_regs *regs);
 
@@ -58,8 +60,8 @@ static inline bool has_syscall_work(unsigned long flags)
 int syscall_trace_enter(struct pt_regs *regs);
 void syscall_trace_exit(struct pt_regs *regs);
 
-asmlinkage void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
-			       const syscall_fn_t syscall_table[])
+static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
+			   const syscall_fn_t syscall_table[])
 {
 	unsigned long flags = current_thread_info()->flags;
 
@@ -96,3 +98,34 @@ asmlinkage void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 trace_exit:
 	syscall_trace_exit(regs);
 }
+
+static inline void sve_user_discard(void)
+{
+	if (!system_supports_sve())
+		return;
+
+	clear_thread_flag(TIF_SVE);
+
+	/*
+	 * task_fpsimd_load() won't be called to update CPACR_EL1 in
+	 * ret_to_user unless TIF_FOREIGN_FPSTATE is still set, which only
+	 * happens if a context switch or kernel_neon_begin() or context
+	 * modification (sigreturn, ptrace) intervenes.
+	 * So, ensure that CPACR_EL1 is already correct for the fast-path case.
+	 */
+	sve_user_disable();
+}
+
+asmlinkage void el0_svc_handler(struct pt_regs *regs)
+{
+	sve_user_discard();
+	el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table);
+}
+
+#ifdef CONFIG_COMPAT
+asmlinkage void el0_svc_compat_handler(struct pt_regs *regs)
+{
+	el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls,
+		       compat_sys_call_table);
+}
+#endif
-- 
cgit v1.2.3


From d9be03256d745360a859b11091e5a43f7828382b Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:46 +0100
Subject: arm64: don't restore GPRs when context tracking

Now that syscalls are invoked with pt_regs, we no longer need to ensure
that the argument regsiters are live in the entry assembly, and it's
fine to not restore them after context_tracking_user_exit() has
corrupted them.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/entry.S | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 156c4e3fd1a4..c41b84d06644 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -41,19 +41,9 @@
  * Context tracking subsystem.  Used to instrument transitions
  * between user and kernel mode.
  */
-	.macro ct_user_exit, syscall = 0
+	.macro ct_user_exit
 #ifdef CONFIG_CONTEXT_TRACKING
 	bl	context_tracking_user_exit
-	.if \syscall == 1
-	/*
-	 * Save/restore needed during syscalls.  Restore syscall arguments from
-	 * the values already saved on stack during kernel_entry.
-	 */
-	ldp	x0, x1, [sp]
-	ldp	x2, x3, [sp, #S_X2]
-	ldp	x4, x5, [sp, #S_X4]
-	ldp	x6, x7, [sp, #S_X6]
-	.endif
 #endif
 	.endm
 
-- 
cgit v1.2.3


From 99ed3ed08d629eb0db6866d266e2bbe35efa5f9d Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:47 +0100
Subject: arm64: don't reload GPRs after apply_ssbd

Now that all of the syscall logic works on the saved pt_regs, apply_ssbd
can safely corrupt x0-x3 in the entry paths, and we no longer need to
restore them. So let's remove the logic doing so.

With that logic gone, we can fold the branch target into the macro, so
that callers need not deal with this. GAS provides \@, which provides a
unique value per macro invocation, which we can use to create a unique
label.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Marc Zyngier <marc.zyngier@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/entry.S | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index c41b84d06644..22b240da949b 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -130,20 +130,21 @@ alternative_else_nop_endif
 
 	// This macro corrupts x0-x3. It is the caller's duty
 	// to save/restore them if required.
-	.macro	apply_ssbd, state, targ, tmp1, tmp2
+	.macro	apply_ssbd, state, tmp1, tmp2
 #ifdef CONFIG_ARM64_SSBD
 alternative_cb	arm64_enable_wa2_handling
-	b	\targ
+	b	.L__asm_ssbd_skip\@
 alternative_cb_end
 	ldr_this_cpu	\tmp2, arm64_ssbd_callback_required, \tmp1
-	cbz	\tmp2, \targ
+	cbz	\tmp2,	.L__asm_ssbd_skip\@
 	ldr	\tmp2, [tsk, #TSK_TI_FLAGS]
-	tbnz	\tmp2, #TIF_SSBD, \targ
+	tbnz	\tmp2, #TIF_SSBD, .L__asm_ssbd_skip\@
 	mov	w0, #ARM_SMCCC_ARCH_WORKAROUND_2
 	mov	w1, #\state
 alternative_cb	arm64_update_smccc_conduit
 	nop					// Patched to SMC/HVC #0
 alternative_cb_end
+.L__asm_ssbd_skip\@:
 #endif
 	.endm
 
@@ -173,13 +174,7 @@ alternative_cb_end
 	ldr	x19, [tsk, #TSK_TI_FLAGS]	// since we can unmask debug
 	disable_step_tsk x19, x20		// exceptions when scheduling.
 
-	apply_ssbd 1, 1f, x22, x23
-
-#ifdef CONFIG_ARM64_SSBD
-	ldp	x0, x1, [sp, #16 * 0]
-	ldp	x2, x3, [sp, #16 * 1]
-#endif
-1:
+	apply_ssbd 1, x22, x23
 
 	mov	x29, xzr			// fp pointed to user-space
 	.else
@@ -321,8 +316,7 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 3:
-	apply_ssbd 0, 5f, x0, x1
-5:
+	apply_ssbd 0, x0, x1
 	.endif
 
 	msr	elr_el1, x21			// set up the return data
-- 
cgit v1.2.3


From baaa7237fecc5ada99e518f38541126977ca7ff4 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:48 +0100
Subject: arm64: zero GPRs upon entry from EL0

We can zero GPRs x0 - x29 upon entry from EL0 to make it harder for
userspace to control values consumed by speculative gadgets.

We don't blat x30, since this is stashed much later, and we'll blat it
before invoking C code.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/entry.S | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 22b240da949b..d1440f84668b 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -53,6 +53,12 @@
 #endif
 	.endm
 
+	.macro	clear_gp_regs
+	.irp	n,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29
+	mov	x\n, xzr
+	.endr
+	.endm
+
 /*
  * Bad Abort numbers
  *-----------------
@@ -169,6 +175,7 @@ alternative_cb_end
 	stp	x28, x29, [sp, #16 * 14]
 
 	.if	\el == 0
+	clear_gp_regs
 	mrs	x21, sp_el0
 	ldr_this_cpu	tsk, __entry_task, x20	// Ensure MDSCR_EL1.SS is clear,
 	ldr	x19, [tsk, #TSK_TI_FLAGS]	// since we can unmask debug
@@ -176,7 +183,6 @@ alternative_cb_end
 
 	apply_ssbd 1, x22, x23
 
-	mov	x29, xzr			// fp pointed to user-space
 	.else
 	add	x21, sp, #S_FRAME_SIZE
 	get_thread_info tsk
-- 
cgit v1.2.3


From 80d63bc39f9ace9c1d2bef7f921d2f3ef2037d4b Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:49 +0100
Subject: arm64: drop alignment from syscall tables

Our syscall tables are aligned to 4096 bytes, which allowed their
addresses to be generated with a single adrp in entry.S. This has the
unfortunate property of wasting space in .rodata for the necessary
padding.

Now that the address is generated by C code, we can rely on the compiler
to do the right thing, and drop the alignemnt.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/sys.c   | 6 +-----
 arch/arm64/kernel/sys32.c | 6 +-----
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index 7f0907261269..df8180175515 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -56,11 +56,7 @@ asmlinkage long sys_rt_sigreturn(void);
 #undef __SYSCALL
 #define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)sym,
 
-/*
- * The sys_call_table array must be 4K aligned to be accessible from
- * kernel/entry.S.
- */
-const syscall_fn_t sys_call_table[__NR_syscalls] __aligned(4096) = {
+const syscall_fn_t sys_call_table[__NR_syscalls] = {
 	[0 ... __NR_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
 #include <asm/unistd.h>
 };
diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c
index d993214118aa..4ddeaae90128 100644
--- a/arch/arm64/kernel/sys32.c
+++ b/arch/arm64/kernel/sys32.c
@@ -44,11 +44,7 @@ asmlinkage long compat_sys_mmap2_wrapper(void);
 #undef __SYSCALL
 #define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)sym,
 
-/*
- * The sys_call_table array must be 4K aligned to be accessible from
- * kernel/entry.S.
- */
-const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] __aligned(4096) = {
+const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] = {
 	[0 ... __NR_compat_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
 #include <asm/unistd32.h>
 };
-- 
cgit v1.2.3


From bf1c77b4644f46d2986b7ca5e43e012f0fc8984b Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:50 +0100
Subject: kernel: add ksys_personality()

Using this helper allows us to avoid the in-kernel call to the
sys_personality() syscall. The ksys_ prefix denotes that this function
is meant as a drop-in replacement for the syscall. In particular, it
uses the same calling convention as sys_personality().

Since ksys_personality is trivial, it is implemented directly in
<linux/syscalls.h>, as we do for ksys_close() and friends.

This helper is necessary to enable conversion of arm64's syscall
handling to use pt_regs wrappers.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Martin <dave.martin@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 include/linux/syscalls.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index a368a68cb667..abfe12d8a9c5 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -80,6 +80,7 @@ union bpf_attr;
 #include <linux/unistd.h>
 #include <linux/quota.h>
 #include <linux/key.h>
+#include <linux/personality.h>
 #include <trace/syscall.h>
 
 #ifdef CONFIG_ARCH_HAS_SYSCALL_WRAPPER
@@ -1281,4 +1282,14 @@ static inline long ksys_truncate(const char __user *pathname, loff_t length)
 	return do_sys_truncate(pathname, length);
 }
 
+static inline unsigned int ksys_personality(unsigned int personality)
+{
+	unsigned int old = current->personality;
+
+	if (personality != 0xffffffff)
+		set_personality(personality);
+
+	return old;
+}
+
 #endif
-- 
cgit v1.2.3


From 9b54bf9d6a5b30e2cc22b18793e9a4158c5b4882 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:51 +0100
Subject: kernel: add kcompat_sys_{f,}statfs64()

Using this helper allows us to avoid the in-kernel calls to the
compat_sys_{f,}statfs64() sycalls, as are necessary for parameter
mangling in arm64's compat handling.

Following the example of ksys_* functions, kcompat_sys_* functions are
intended to be a drop-in replacement for their compat_sys_*
counterparts, with the same calling convention.

This is necessary to enable conversion of arm64's syscall handling to
use pt_regs wrappers.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 fs/statfs.c            | 14 ++++++++++++--
 include/linux/compat.h | 11 +++++++++++
 2 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/fs/statfs.c b/fs/statfs.c
index 5b2a24f0f263..f0216629621d 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -335,7 +335,7 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat
 	return 0;
 }
 
-COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz, struct compat_statfs64 __user * buf)
 {
 	struct kstatfs tmp;
 	int error;
@@ -349,7 +349,12 @@ COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, s
 	return error;
 }
 
-COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	return kcompat_sys_statfs64(pathname, sz, buf);
+}
+
+int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user * buf)
 {
 	struct kstatfs tmp;
 	int error;
@@ -363,6 +368,11 @@ COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct co
 	return error;
 }
 
+COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	return kcompat_sys_fstatfs64(fd, sz, buf);
+}
+
 /*
  * This is a copy of sys_ustat, just dealing with a structure layout.
  * Given how simple this syscall is that apporach is more maintainable
diff --git a/include/linux/compat.h b/include/linux/compat.h
index c68acc47da57..43f4ed44c5d5 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -1028,6 +1028,17 @@ static inline struct compat_timeval ns_to_compat_timeval(s64 nsec)
 	return ctv;
 }
 
+/*
+ * Kernel code should not call compat syscalls (i.e., compat_sys_xyzyyz())
+ * directly.  Instead, use one of the functions which work equivalently, such
+ * as the kcompat_sys_xyzyyz() functions prototyped below.
+ */
+
+int kcompat_sys_statfs64(const char __user * pathname, compat_size_t sz,
+		     struct compat_statfs64 __user * buf);
+int kcompat_sys_fstatfs64(unsigned int fd, compat_size_t sz,
+			  struct compat_statfs64 __user * buf);
+
 #else /* !CONFIG_COMPAT */
 
 #define is_compat_task() (0)
-- 
cgit v1.2.3


From 3f7deccb037cc2bd2f848576439c033f81daeb6a Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:52 +0100
Subject: arm64: remove in-kernel call to sys_personality()

With pt_regs syscall wrappers, the calling convention for
sys_personality() will change. Use ksys_personality(), which is
functionally equivalent.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/sys.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index df8180175515..f4e02f6aceb8 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -44,7 +44,7 @@ SYSCALL_DEFINE1(arm64_personality, unsigned int, personality)
 	if (personality(personality) == PER_LINUX32 &&
 		!system_supports_32bit_el0())
 		return -EINVAL;
-	return sys_personality(personality);
+	return ksys_personality(personality);
 }
 
 /*
-- 
cgit v1.2.3


From bf4ce5cc23c9f8357bfd9c0328bf59685664cbc7 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:53 +0100
Subject: arm64: use {COMPAT,}SYSCALL_DEFINE0 for sigreturn

We don't currently annotate our various sigreturn functions as syscalls,
as we need to do to use pt_regs syscall wrappers.

Let's mark them as real syscalls.

For compat_sys_sigreturn and compat_sys_rt_sigreturn, this changes the
return type from int to long, matching the prototypes in sys32.c.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/signal.c   | 2 +-
 arch/arm64/kernel/signal32.c | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index b6f3c3d76901..5dcc942906db 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -539,7 +539,7 @@ static int restore_sigframe(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage long sys_rt_sigreturn(void)
+SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct rt_sigframe __user *frame;
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 9aac1253e0a6..24b09003f821 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -285,7 +285,7 @@ static int compat_restore_sigframe(struct pt_regs *regs,
 	return err;
 }
 
-asmlinkage int compat_sys_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct compat_sigframe __user *frame;
@@ -316,7 +316,7 @@ badframe:
 	return 0;
 }
 
-asmlinkage int compat_sys_rt_sigreturn(void)
+COMPAT_SYSCALL_DEFINE0(rt_sigreturn)
 {
 	struct pt_regs *regs = current_pt_regs();
 	struct compat_rt_sigframe __user *frame;
-- 
cgit v1.2.3


From d3516c9073b4b81410195489dc169891cd64e4cd Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:54 +0100
Subject: arm64: use SYSCALL_DEFINE6() for mmap

We don't currently annotate our mmap implementation as a syscall, as we
need to do to use pt_regs syscall wrappers.

Let's mark it as a real syscall.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/sys.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index f4e02f6aceb8..f249d9735f4c 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -29,9 +29,9 @@
 #include <asm/cpufeature.h>
 #include <asm/syscall.h>
 
-asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
-			 unsigned long prot, unsigned long flags,
-			 unsigned long fd, off_t off)
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, off_t, off)
 {
 	if (offset_in_page(off) != 0)
 		return -EINVAL;
-- 
cgit v1.2.3


From 55f849265af886aaf404cbf8a659b2c8d411fc3a Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:55 +0100
Subject: arm64: convert compat wrappers to C

In preparation for converting to pt_regs syscall wrappers, convert our
existing compat wrappers to C. This will allow the pt_regs wrappers to
be automatically generated, and will allow for the compat register
manipulation to be folded in with the pt_regs accesses.

To avoid confusion with the upcoming pt_regs wrappers and existing
compat wrappers provided by core code, the C wrappers are renamed to
compat_sys_aarch32_<syscall>.

With the assembly wrappers gone, we can get rid of entry32.S and the
associated boilerplate.

Note that these must call the ksys_* syscall entry points, as the usual
sys_* entry points will be modified to take a single pt_regs pointer
argument.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/unistd32.h |  22 ++++----
 arch/arm64/kernel/Makefile        |   2 +-
 arch/arm64/kernel/entry32.S       | 111 -------------------------------------
 arch/arm64/kernel/sys32.c         | 114 ++++++++++++++++++++++++++++++++++----
 4 files changed, 115 insertions(+), 134 deletions(-)
 delete mode 100644 arch/arm64/kernel/entry32.S

diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h
index 023d64af8339..2cd6dcf8d246 100644
--- a/arch/arm64/include/asm/unistd32.h
+++ b/arch/arm64/include/asm/unistd32.h
@@ -382,9 +382,9 @@ __SYSCALL(__NR_rt_sigqueueinfo, compat_sys_rt_sigqueueinfo)
 #define __NR_rt_sigsuspend 179
 __SYSCALL(__NR_rt_sigsuspend, compat_sys_rt_sigsuspend)
 #define __NR_pread64 180
-__SYSCALL(__NR_pread64, compat_sys_pread64_wrapper)
+__SYSCALL(__NR_pread64, compat_sys_aarch32_pread64)
 #define __NR_pwrite64 181
-__SYSCALL(__NR_pwrite64, compat_sys_pwrite64_wrapper)
+__SYSCALL(__NR_pwrite64, compat_sys_aarch32_pwrite64)
 #define __NR_chown 182
 __SYSCALL(__NR_chown, sys_chown16)
 #define __NR_getcwd 183
@@ -406,11 +406,11 @@ __SYSCALL(__NR_vfork, sys_vfork)
 #define __NR_ugetrlimit 191	/* SuS compliant getrlimit */
 __SYSCALL(__NR_ugetrlimit, compat_sys_getrlimit)		/* SuS compliant getrlimit */
 #define __NR_mmap2 192
-__SYSCALL(__NR_mmap2, compat_sys_mmap2_wrapper)
+__SYSCALL(__NR_mmap2, compat_sys_aarch32_mmap2)
 #define __NR_truncate64 193
-__SYSCALL(__NR_truncate64, compat_sys_truncate64_wrapper)
+__SYSCALL(__NR_truncate64, compat_sys_aarch32_truncate64)
 #define __NR_ftruncate64 194
-__SYSCALL(__NR_ftruncate64, compat_sys_ftruncate64_wrapper)
+__SYSCALL(__NR_ftruncate64, compat_sys_aarch32_ftruncate64)
 #define __NR_stat64 195
 __SYSCALL(__NR_stat64, sys_stat64)
 #define __NR_lstat64 196
@@ -472,7 +472,7 @@ __SYSCALL(223, sys_ni_syscall)
 #define __NR_gettid 224
 __SYSCALL(__NR_gettid, sys_gettid)
 #define __NR_readahead 225
-__SYSCALL(__NR_readahead, compat_sys_readahead_wrapper)
+__SYSCALL(__NR_readahead, compat_sys_aarch32_readahead)
 #define __NR_setxattr 226
 __SYSCALL(__NR_setxattr, sys_setxattr)
 #define __NR_lsetxattr 227
@@ -554,15 +554,15 @@ __SYSCALL(__NR_clock_getres, compat_sys_clock_getres)
 #define __NR_clock_nanosleep 265
 __SYSCALL(__NR_clock_nanosleep, compat_sys_clock_nanosleep)
 #define __NR_statfs64 266
-__SYSCALL(__NR_statfs64, compat_sys_statfs64_wrapper)
+__SYSCALL(__NR_statfs64, compat_sys_aarch32_statfs64)
 #define __NR_fstatfs64 267
-__SYSCALL(__NR_fstatfs64, compat_sys_fstatfs64_wrapper)
+__SYSCALL(__NR_fstatfs64, compat_sys_aarch32_fstatfs64)
 #define __NR_tgkill 268
 __SYSCALL(__NR_tgkill, sys_tgkill)
 #define __NR_utimes 269
 __SYSCALL(__NR_utimes, compat_sys_utimes)
 #define __NR_arm_fadvise64_64 270
-__SYSCALL(__NR_arm_fadvise64_64, compat_sys_fadvise64_64_wrapper)
+__SYSCALL(__NR_arm_fadvise64_64, compat_sys_aarch32_fadvise64_64)
 #define __NR_pciconfig_iobase 271
 __SYSCALL(__NR_pciconfig_iobase, sys_pciconfig_iobase)
 #define __NR_pciconfig_read 272
@@ -704,7 +704,7 @@ __SYSCALL(__NR_get_robust_list, compat_sys_get_robust_list)
 #define __NR_splice 340
 __SYSCALL(__NR_splice, sys_splice)
 #define __NR_sync_file_range2 341
-__SYSCALL(__NR_sync_file_range2, compat_sys_sync_file_range2_wrapper)
+__SYSCALL(__NR_sync_file_range2, compat_sys_aarch32_sync_file_range2)
 #define __NR_tee 342
 __SYSCALL(__NR_tee, sys_tee)
 #define __NR_vmsplice 343
@@ -726,7 +726,7 @@ __SYSCALL(__NR_timerfd_create, sys_timerfd_create)
 #define __NR_eventfd 351
 __SYSCALL(__NR_eventfd, sys_eventfd)
 #define __NR_fallocate 352
-__SYSCALL(__NR_fallocate, compat_sys_fallocate_wrapper)
+__SYSCALL(__NR_fallocate, compat_sys_aarch32_fallocate)
 #define __NR_timerfd_settime 353
 __SYSCALL(__NR_timerfd_settime, compat_sys_timerfd_settime)
 #define __NR_timerfd_gettime 354
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile
index 4e24d2244bd1..95ac7374d723 100644
--- a/arch/arm64/kernel/Makefile
+++ b/arch/arm64/kernel/Makefile
@@ -28,7 +28,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE
 	$(call if_changed,objcopy)
 
 arm64-obj-$(CONFIG_COMPAT)		+= sys32.o kuser32.o signal32.o 	\
-					   sys_compat.o entry32.o
+					   sys_compat.o
 arm64-obj-$(CONFIG_FUNCTION_TRACER)	+= ftrace.o entry-ftrace.o
 arm64-obj-$(CONFIG_MODULES)		+= arm64ksyms.o module.o
 arm64-obj-$(CONFIG_ARM64_MODULE_PLTS)	+= module-plts.o
diff --git a/arch/arm64/kernel/entry32.S b/arch/arm64/kernel/entry32.S
deleted file mode 100644
index f9461696dde4..000000000000
--- a/arch/arm64/kernel/entry32.S
+++ /dev/null
@@ -1,111 +0,0 @@
-/*
- * Compat system call wrappers
- *
- * Copyright (C) 2012 ARM Ltd.
- * Authors: Will Deacon <will.deacon@arm.com>
- *	    Catalin Marinas <catalin.marinas@arm.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include <linux/linkage.h>
-#include <linux/const.h>
-
-#include <asm/assembler.h>
-#include <asm/asm-offsets.h>
-#include <asm/errno.h>
-#include <asm/page.h>
-
-/*
- * System call wrappers for the AArch32 compatibility layer.
- */
-
-ENTRY(compat_sys_statfs64_wrapper)
-	mov	w3, #84
-	cmp	w1, #88
-	csel	w1, w3, w1, eq
-	b	compat_sys_statfs64
-ENDPROC(compat_sys_statfs64_wrapper)
-
-ENTRY(compat_sys_fstatfs64_wrapper)
-	mov	w3, #84
-	cmp	w1, #88
-	csel	w1, w3, w1, eq
-	b	compat_sys_fstatfs64
-ENDPROC(compat_sys_fstatfs64_wrapper)
-
-/*
- * Note: off_4k (w5) is always in units of 4K. If we can't do the
- * requested offset because it is not page-aligned, we return -EINVAL.
- */
-ENTRY(compat_sys_mmap2_wrapper)
-#if PAGE_SHIFT > 12
-	tst	w5, #~PAGE_MASK >> 12
-	b.ne	1f
-	lsr	w5, w5, #PAGE_SHIFT - 12
-#endif
-	b	sys_mmap_pgoff
-1:	mov	x0, #-EINVAL
-	ret
-ENDPROC(compat_sys_mmap2_wrapper)
-
-/*
- * Wrappers for AArch32 syscalls that either take 64-bit parameters
- * in registers or that take 32-bit parameters which require sign
- * extension.
- */
-ENTRY(compat_sys_pread64_wrapper)
-	regs_to_64	x3, x4, x5
-	b	sys_pread64
-ENDPROC(compat_sys_pread64_wrapper)
-
-ENTRY(compat_sys_pwrite64_wrapper)
-	regs_to_64	x3, x4, x5
-	b	sys_pwrite64
-ENDPROC(compat_sys_pwrite64_wrapper)
-
-ENTRY(compat_sys_truncate64_wrapper)
-	regs_to_64	x1, x2, x3
-	b	sys_truncate
-ENDPROC(compat_sys_truncate64_wrapper)
-
-ENTRY(compat_sys_ftruncate64_wrapper)
-	regs_to_64	x1, x2, x3
-	b	sys_ftruncate
-ENDPROC(compat_sys_ftruncate64_wrapper)
-
-ENTRY(compat_sys_readahead_wrapper)
-	regs_to_64	x1, x2, x3
-	mov	w2, w4
-	b	sys_readahead
-ENDPROC(compat_sys_readahead_wrapper)
-
-ENTRY(compat_sys_fadvise64_64_wrapper)
-	mov	w6, w1
-	regs_to_64	x1, x2, x3
-	regs_to_64	x2, x4, x5
-	mov	w3, w6
-	b	sys_fadvise64_64
-ENDPROC(compat_sys_fadvise64_64_wrapper)
-
-ENTRY(compat_sys_sync_file_range2_wrapper)
-	regs_to_64	x2, x2, x3
-	regs_to_64	x3, x4, x5
-	b	sys_sync_file_range2
-ENDPROC(compat_sys_sync_file_range2_wrapper)
-
-ENTRY(compat_sys_fallocate_wrapper)
-	regs_to_64	x2, x2, x3
-	regs_to_64	x3, x4, x5
-	b	sys_fallocate
-ENDPROC(compat_sys_fallocate_wrapper)
diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c
index 4ddeaae90128..a205d4ff4776 100644
--- a/arch/arm64/kernel/sys32.c
+++ b/arch/arm64/kernel/sys32.c
@@ -22,6 +22,7 @@
  */
 #define __COMPAT_SYSCALL_NR
 
+#include <linux/compat.h>
 #include <linux/compiler.h>
 #include <linux/syscalls.h>
 
@@ -29,17 +30,108 @@
 
 asmlinkage long compat_sys_sigreturn(void);
 asmlinkage long compat_sys_rt_sigreturn(void);
-asmlinkage long compat_sys_statfs64_wrapper(void);
-asmlinkage long compat_sys_fstatfs64_wrapper(void);
-asmlinkage long compat_sys_pread64_wrapper(void);
-asmlinkage long compat_sys_pwrite64_wrapper(void);
-asmlinkage long compat_sys_truncate64_wrapper(void);
-asmlinkage long compat_sys_ftruncate64_wrapper(void);
-asmlinkage long compat_sys_readahead_wrapper(void);
-asmlinkage long compat_sys_fadvise64_64_wrapper(void);
-asmlinkage long compat_sys_sync_file_range2_wrapper(void);
-asmlinkage long compat_sys_fallocate_wrapper(void);
-asmlinkage long compat_sys_mmap2_wrapper(void);
+
+COMPAT_SYSCALL_DEFINE3(aarch32_statfs64, const char __user *, pathname,
+		       compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	/*
+	 * 32-bit ARM applies an OABI compatibility fixup to statfs64 and
+	 * fstatfs64 regardless of whether OABI is in use, and therefore
+	 * arbitrary binaries may rely upon it, so we must do the same.
+	 * For more details, see commit:
+	 *
+	 * 713c481519f19df9 ("[ARM] 3108/2: old ABI compat: statfs64 and
+	 * fstatfs64")
+	 */
+	if (sz == 88)
+		sz = 84;
+
+	return kcompat_sys_statfs64(pathname, sz, buf);
+}
+
+COMPAT_SYSCALL_DEFINE3(aarch32_fstatfs64, unsigned int, fd, compat_size_t, sz,
+		       struct compat_statfs64 __user *, buf)
+{
+	/* see aarch32_statfs64 */
+	if (sz == 88)
+		sz = 84;
+
+	return kcompat_sys_fstatfs64(fd, sz, buf);
+}
+
+/*
+ * Note: off_4k is always in units of 4K. If we can't do the
+ * requested offset because it is not page-aligned, we return -EINVAL.
+ */
+COMPAT_SYSCALL_DEFINE6(aarch32_mmap2, unsigned long, addr, unsigned long, len,
+		       unsigned long, prot, unsigned long, flags,
+		       unsigned long, fd, unsigned long, off_4k)
+{
+	if (off_4k & (~PAGE_MASK >> 12))
+		return -EINVAL;
+
+	off_4k >>= (PAGE_SHIFT - 12);
+
+	return ksys_mmap_pgoff(addr, len, prot, flags, fd, off_4k);
+}
+
+#ifdef CONFIG_CPU_BIG_ENDIAN
+#define arg_u32p(name)	u32, name##_hi, u32, name##_lo
+#else
+#define arg_u32p(name)	u32, name##_lo, u32, name##_hi
+#endif
+
+#define arg_u64(name)	(((u64)name##_hi << 32) | name##_lo)
+
+COMPAT_SYSCALL_DEFINE6(aarch32_pread64, unsigned int, fd, char __user *, buf,
+		       size_t, count, u32, __pad, arg_u32p(pos))
+{
+	return ksys_pread64(fd, buf, count, arg_u64(pos));
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_pwrite64, unsigned int, fd,
+		       const char __user *, buf, size_t, count, u32, __pad,
+		       arg_u32p(pos))
+{
+	return ksys_pwrite64(fd, buf, count, arg_u64(pos));
+}
+
+COMPAT_SYSCALL_DEFINE4(aarch32_truncate64, const char __user *, pathname,
+		       u32, __pad, arg_u32p(length))
+{
+	return ksys_truncate(pathname, arg_u64(length));
+}
+
+COMPAT_SYSCALL_DEFINE4(aarch32_ftruncate64, unsigned int, fd, u32, __pad,
+		       arg_u32p(length))
+{
+	return ksys_ftruncate(fd, arg_u64(length));
+}
+
+COMPAT_SYSCALL_DEFINE5(aarch32_readahead, int, fd, u32, __pad,
+		       arg_u32p(offset), size_t, count)
+{
+	return ksys_readahead(fd, arg_u64(offset), count);
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_fadvise64_64, int, fd, int, advice,
+		       arg_u32p(offset), arg_u32p(len))
+{
+	return ksys_fadvise64_64(fd, arg_u64(offset), arg_u64(len), advice);
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_sync_file_range2, int, fd, unsigned int, flags,
+		       arg_u32p(offset), arg_u32p(nbytes))
+{
+	return ksys_sync_file_range(fd, arg_u64(offset), arg_u64(nbytes),
+				    flags);
+}
+
+COMPAT_SYSCALL_DEFINE6(aarch32_fallocate, int, fd, int, mode,
+		       arg_u32p(offset), arg_u32p(len))
+{
+	return ksys_fallocate(fd, mode, arg_u64(offset), arg_u64(len));
+}
 
 #undef __SYSCALL
 #define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)sym,
-- 
cgit v1.2.3


From 4378a7d4be30ec6994702b19936f7d1465193541 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 14:56:56 +0100
Subject: arm64: implement syscall wrappers

To minimize the risk of userspace-controlled values being used under
speculation, this patch adds pt_regs based syscall wrappers for arm64,
which pass the minimum set of required userspace values to syscall
implementations. For each syscall, a wrapper which takes a pt_regs
argument is automatically generated, and this extracts the arguments
before calling the "real" syscall implementation.

Each syscall has three functions generated:

* __do_<compat_>sys_<name> is the "real" syscall implementation, with
  the expected prototype.

* __se_<compat_>sys_<name> is the sign-extension/narrowing wrapper,
  inherited from common code. This takes a series of long parameters,
  casting each to the requisite types required by the "real" syscall
  implementation in __do_<compat_>sys_<name>.

  This wrapper *may* not be necessary on arm64 given the AAPCS rules on
  unused register bits, but it seemed safer to keep the wrapper for now.

* __arm64_<compat_>_sys_<name> takes a struct pt_regs pointer, and
  extracts *only* the relevant register values, passing these on to the
  __se_<compat_>sys_<name> wrapper.

The syscall invocation code is updated to handle the calling convention
required by __arm64_<compat_>_sys_<name>, and passes a single struct
pt_regs pointer.

The compiler can fold the syscall implementation and its wrappers, such
that the overhead of this approach is minimized.

Note that we play games with sys_ni_syscall(). It can't be defined with
SYSCALL_DEFINE0() because we must avoid the possibility of error
injection. Additionally, there are a couple of locations where we need
to call it from C code, and we don't (currently) have a
ksys_ni_syscall().  While it has no wrapper, passing in a redundant
pt_regs pointer is benign per the AAPCS.

When ARCH_HAS_SYSCALL_WRAPPER is selected, no prototype is defines for
sys_ni_syscall(). Since we need to treat it differently for in-kernel
calls and the syscall tables, the prototype is defined as-required.

The wrappers are largely the same as their x86 counterparts, but
simplified as we don't have a variety of compat calling conventions that
require separate stubs. Unlike x86, we have some zero-argument compat
syscalls, and must define COMPAT_SYSCALL_DEFINE0() to ensure that these
are also given an __arm64_compat_sys_ prefix.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Dominik Brodowski <linux@dominikbrodowski.net>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig                       |  1 +
 arch/arm64/include/asm/syscall.h         |  4 +-
 arch/arm64/include/asm/syscall_wrapper.h | 80 ++++++++++++++++++++++++++++++++
 arch/arm64/kernel/sys.c                  | 10 +++-
 arch/arm64/kernel/sys32.c                |  9 +++-
 arch/arm64/kernel/syscall.c              |  5 +-
 6 files changed, 101 insertions(+), 8 deletions(-)
 create mode 100644 arch/arm64/include/asm/syscall_wrapper.h

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index f4157d4a0289..e2823362c324 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -24,6 +24,7 @@ config ARM64
 	select ARCH_HAS_SG_CHAIN
 	select ARCH_HAS_STRICT_KERNEL_RWX
 	select ARCH_HAS_STRICT_MODULE_RWX
+	select ARCH_HAS_SYSCALL_WRAPPER
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_INLINE_READ_LOCK if !PREEMPT
diff --git a/arch/arm64/include/asm/syscall.h b/arch/arm64/include/asm/syscall.h
index b83d0e6980a3..ad8be16a39c9 100644
--- a/arch/arm64/include/asm/syscall.h
+++ b/arch/arm64/include/asm/syscall.h
@@ -20,9 +20,7 @@
 #include <linux/compat.h>
 #include <linux/err.h>
 
-typedef long (*syscall_fn_t)(unsigned long, unsigned long,
-			     unsigned long, unsigned long,
-			     unsigned long, unsigned long);
+typedef long (*syscall_fn_t)(struct pt_regs *regs);
 
 extern const syscall_fn_t sys_call_table[];
 
diff --git a/arch/arm64/include/asm/syscall_wrapper.h b/arch/arm64/include/asm/syscall_wrapper.h
new file mode 100644
index 000000000000..a4477e515b79
--- /dev/null
+++ b/arch/arm64/include/asm/syscall_wrapper.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * syscall_wrapper.h - arm64 specific wrappers to syscall definitions
+ *
+ * Based on arch/x86/include/asm_syscall_wrapper.h
+ */
+
+#ifndef __ASM_SYSCALL_WRAPPER_H
+#define __ASM_SYSCALL_WRAPPER_H
+
+#define SC_ARM64_REGS_TO_ARGS(x, ...)				\
+	__MAP(x,__SC_ARGS					\
+	      ,,regs->regs[0],,regs->regs[1],,regs->regs[2]	\
+	      ,,regs->regs[3],,regs->regs[4],,regs->regs[5])
+
+#ifdef CONFIG_COMPAT
+
+#define COMPAT_SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__arm64_compat_sys##name, ERRNO);				\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __arm64_compat_sys##name(const struct pt_regs *regs)		\
+	{										\
+		return __se_compat_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}										\
+	static long __se_compat_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{										\
+		return __do_compat_sys##name(__MAP(x,__SC_DELOUSE,__VA_ARGS__));	\
+	}										\
+	static inline long __do_compat_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#define COMPAT_SYSCALL_DEFINE0(sname)					\
+	asmlinkage long __arm64_compat_sys_##sname(void);		\
+	ALLOW_ERROR_INJECTION(__arm64_compat_sys_##sname, ERRNO);	\
+	asmlinkage long __arm64_compat_sys_##sname(void)
+
+#define COND_SYSCALL_COMPAT(name) \
+	cond_syscall(__arm64_compat_sys_##name);
+
+#define COMPAT_SYS_NI(name) \
+	SYSCALL_ALIAS(__arm64_compat_sys_##name, sys_ni_posix_timers);
+
+#endif /* CONFIG_COMPAT */
+
+#define __SYSCALL_DEFINEx(x, name, ...)						\
+	asmlinkage long __arm64_sys##name(const struct pt_regs *regs);		\
+	ALLOW_ERROR_INJECTION(__arm64_sys##name, ERRNO);			\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));		\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));	\
+	asmlinkage long __arm64_sys##name(const struct pt_regs *regs)		\
+	{									\
+		return __se_sys##name(SC_ARM64_REGS_TO_ARGS(x,__VA_ARGS__));	\
+	}									\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))		\
+	{									\
+		long ret = __do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));	\
+		__MAP(x,__SC_TEST,__VA_ARGS__);					\
+		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));		\
+		return ret;							\
+	}									\
+	static inline long __do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#ifndef SYSCALL_DEFINE0
+#define SYSCALL_DEFINE0(sname)					\
+	SYSCALL_METADATA(_##sname, 0);				\
+	asmlinkage long __arm64_sys_##sname(void);		\
+	ALLOW_ERROR_INJECTION(__arm64_sys_##sname, ERRNO);	\
+	asmlinkage long __arm64_sys_##sname(void)
+#endif
+
+#ifndef COND_SYSCALL
+#define COND_SYSCALL(name) cond_syscall(__arm64_sys_##name)
+#endif
+
+#ifndef SYS_NI
+#define SYS_NI(name) SYSCALL_ALIAS(__arm64_sys_##name, sys_ni_posix_timers);
+#endif
+
+#endif /* __ASM_SYSCALL_WRAPPER_H */
diff --git a/arch/arm64/kernel/sys.c b/arch/arm64/kernel/sys.c
index f249d9735f4c..b44065fb1616 100644
--- a/arch/arm64/kernel/sys.c
+++ b/arch/arm64/kernel/sys.c
@@ -50,11 +50,17 @@ SYSCALL_DEFINE1(arm64_personality, unsigned int, personality)
 /*
  * Wrappers to pass the pt_regs argument.
  */
-asmlinkage long sys_rt_sigreturn(void);
 #define sys_personality		sys_arm64_personality
 
+asmlinkage long sys_ni_syscall(const struct pt_regs *);
+#define __arm64_sys_ni_syscall	sys_ni_syscall
+
+#undef __SYSCALL
+#define __SYSCALL(nr, sym)	asmlinkage long __arm64_##sym(const struct pt_regs *);
+#include <asm/unistd.h>
+
 #undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)sym,
+#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)__arm64_##sym,
 
 const syscall_fn_t sys_call_table[__NR_syscalls] = {
 	[0 ... __NR_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
diff --git a/arch/arm64/kernel/sys32.c b/arch/arm64/kernel/sys32.c
index a205d4ff4776..0f8bcb7de700 100644
--- a/arch/arm64/kernel/sys32.c
+++ b/arch/arm64/kernel/sys32.c
@@ -133,8 +133,15 @@ COMPAT_SYSCALL_DEFINE6(aarch32_fallocate, int, fd, int, mode,
 	return ksys_fallocate(fd, mode, arg_u64(offset), arg_u64(len));
 }
 
+asmlinkage long sys_ni_syscall(const struct pt_regs *);
+#define __arm64_sys_ni_syscall	sys_ni_syscall
+
+#undef __SYSCALL
+#define __SYSCALL(nr, sym)	asmlinkage long __arm64_##sym(const struct pt_regs *);
+#include <asm/unistd32.h>
+
 #undef __SYSCALL
-#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)sym,
+#define __SYSCALL(nr, sym)	[nr] = (syscall_fn_t)__arm64_##sym,
 
 const syscall_fn_t compat_sys_call_table[__NR_compat_syscalls] = {
 	[0 ... __NR_compat_syscalls - 1] = (syscall_fn_t)sys_ni_syscall,
diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index 7ff2d7b9f517..be00c85794db 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -15,6 +15,8 @@
 
 long compat_arm_syscall(struct pt_regs *regs);
 
+long sys_ni_syscall(void);
+
 asmlinkage long do_ni_syscall(struct pt_regs *regs)
 {
 #ifdef CONFIG_COMPAT
@@ -31,8 +33,7 @@ asmlinkage long do_ni_syscall(struct pt_regs *regs)
 
 static long __invoke_syscall(struct pt_regs *regs, syscall_fn_t syscall_fn)
 {
-	return syscall_fn(regs->regs[0], regs->regs[1], regs->regs[2],
-			  regs->regs[3], regs->regs[4], regs->regs[5]);
+	return syscall_fn(regs);
 }
 
 static void invoke_syscall(struct pt_regs *regs, unsigned int scno,
-- 
cgit v1.2.3


From c9c554f21490bbc96cc554f80024d27d09670480 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 11 Jul 2018 14:19:04 -0400
Subject: alloc_file(): switch to passing O_... flags instead of FMODE_... mode

... so that it could set both ->f_flags and ->f_mode, without callers
having to set ->f_flags manually.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/misc/cxl/api.c          |  3 +--
 drivers/scsi/cxlflash/ocxl_hw.c |  3 +--
 fs/aio.c                        |  8 ++------
 fs/anon_inodes.c                |  3 +--
 fs/file_table.c                 | 17 +++++++++--------
 fs/hugetlbfs/inode.c            |  3 +--
 fs/pipe.c                       |  8 ++++----
 include/linux/file.h            |  2 +-
 ipc/shm.c                       |  8 ++++----
 mm/memfd.c                      |  2 +-
 mm/shmem.c                      |  3 +--
 net/socket.c                    |  3 +--
 12 files changed, 27 insertions(+), 36 deletions(-)

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 6b16946f9b05..0b5cb6cf91a0 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -102,12 +102,11 @@ static struct file *cxl_getfile(const char *name,
 	path.mnt = mntget(cxl_vfs_mount);
 	d_instantiate(path.dentry, inode);
 
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		path_put(&path);
 		goto err_fs;
 	}
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 497a68389461..99bb393a8a34 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -129,7 +129,7 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 	path.mnt = mntget(ocxlflash_vfs_mount);
 	d_instantiate(path.dentry, inode);
 
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
@@ -138,7 +138,6 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err3;
 	}
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 out:
 	return file;
diff --git a/fs/aio.c b/fs/aio.c
index e1d20124ec0e..9eea53887d6c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -234,13 +234,9 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 	path.mnt = mntget(aio_mnt);
 
 	d_instantiate(path.dentry, inode);
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE, &aio_ring_fops);
-	if (IS_ERR(file)) {
+	file = alloc_file(&path, O_RDWR, &aio_ring_fops);
+	if (IS_ERR(file))
 		path_put(&path);
-		return file;
-	}
-
-	file->f_flags = O_RDWR;
 	return file;
 }
 
diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 3168ee4e77f4..6b235ab1df6c 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -102,12 +102,11 @@ struct file *anon_inode_getfile(const char *name,
 
 	d_instantiate(path.dentry, anon_inode_inode);
 
-	file = alloc_file(&path, OPEN_FMODE(flags), fops);
+	file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file))
 		goto err_dput;
 	file->f_mapping = anon_inode_inode->i_mapping;
 
-	file->f_flags = flags & (O_ACCMODE | O_NONBLOCK);
 	file->private_data = priv;
 
 	return file;
diff --git a/fs/file_table.c b/fs/file_table.c
index eee7cf629e52..086c3f5ec31a 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -153,10 +153,10 @@ over:
  * alloc_file - allocate and initialize a 'struct file'
  *
  * @path: the (dentry, vfsmount) pair for the new file
- * @mode: the mode with which the new file will be opened
+ * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-struct file *alloc_file(const struct path *path, fmode_t mode,
+struct file *alloc_file(const struct path *path, int flags,
 		const struct file_operations *fop)
 {
 	struct file *file;
@@ -165,19 +165,20 @@ struct file *alloc_file(const struct path *path, fmode_t mode,
 	if (IS_ERR(file))
 		return file;
 
+	file->f_mode = OPEN_FMODE(flags);
+	file->f_flags = flags;
 	file->f_path = *path;
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
 	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
-	if ((mode & FMODE_READ) &&
+	if ((file->f_mode & FMODE_READ) &&
 	     likely(fop->read || fop->read_iter))
-		mode |= FMODE_CAN_READ;
-	if ((mode & FMODE_WRITE) &&
+		file->f_mode |= FMODE_CAN_READ;
+	if ((file->f_mode & FMODE_WRITE) &&
 	     likely(fop->write || fop->write_iter))
-		mode |= FMODE_CAN_WRITE;
-	file->f_mode = mode;
+		file->f_mode |= FMODE_CAN_WRITE;
 	file->f_op = fop;
-	if ((mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
+	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index d508c7844681..71aed47422e2 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1375,8 +1375,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-			&hugetlbfs_file_operations);
+	file = alloc_file(&path, O_RDWR, &hugetlbfs_file_operations);
 	if (IS_ERR(file))
 		goto out_dentry; /* inode is already attached */
 
diff --git a/fs/pipe.c b/fs/pipe.c
index 9405e455f5b1..1909422e5a78 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -760,16 +760,17 @@ int create_pipe_files(struct file **res, int flags)
 
 	d_instantiate(path.dentry, inode);
 
-	f = alloc_file(&path, FMODE_WRITE, &pipefifo_fops);
+	f = alloc_file(&path, O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
+			&pipefifo_fops);
 	if (IS_ERR(f)) {
 		err = PTR_ERR(f);
 		goto err_dentry;
 	}
 
-	f->f_flags = O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT));
 	f->private_data = inode->i_pipe;
 
-	res[0] = alloc_file(&path, FMODE_READ, &pipefifo_fops);
+	res[0] = alloc_file(&path, O_RDONLY | (flags & O_NONBLOCK),
+			&pipefifo_fops);
 	if (IS_ERR(res[0])) {
 		put_pipe_info(inode, inode->i_pipe);
 		fput(f);
@@ -778,7 +779,6 @@ int create_pipe_files(struct file **res, int flags)
 
 	path_get(&path);
 	res[0]->private_data = inode->i_pipe;
-	res[0]->f_flags = O_RDONLY | (flags & O_NONBLOCK);
 	res[1] = f;
 	return 0;
 
diff --git a/include/linux/file.h b/include/linux/file.h
index 279720db984a..6d34a1262b31 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -18,7 +18,7 @@ struct file_operations;
 struct vfsmount;
 struct dentry;
 struct path;
-extern struct file *alloc_file(const struct path *, fmode_t mode,
+extern struct file *alloc_file(const struct path *, int flags,
 	const struct file_operations *fop);
 
 static inline void fput_light(struct file *file, int fput_needed)
diff --git a/ipc/shm.c b/ipc/shm.c
index 051a3e1fb8df..c702abd578a7 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1362,7 +1362,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	struct ipc_namespace *ns;
 	struct shm_file_data *sfd;
 	struct path path;
-	fmode_t f_mode;
+	int f_flags;
 	unsigned long populate = 0;
 
 	err = -EINVAL;
@@ -1395,11 +1395,11 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	if (shmflg & SHM_RDONLY) {
 		prot = PROT_READ;
 		acc_mode = S_IRUGO;
-		f_mode = FMODE_READ;
+		f_flags = O_RDONLY;
 	} else {
 		prot = PROT_READ | PROT_WRITE;
 		acc_mode = S_IRUGO | S_IWUGO;
-		f_mode = FMODE_READ | FMODE_WRITE;
+		f_flags = O_RDWR;
 	}
 	if (shmflg & SHM_EXEC) {
 		prot |= PROT_EXEC;
@@ -1449,7 +1449,7 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 		goto out_nattch;
 	}
 
-	file = alloc_file(&path, f_mode,
+	file = alloc_file(&path, f_flags,
 			  is_file_hugepages(shp->shm_file) ?
 				&shm_file_operations_huge :
 				&shm_file_operations);
diff --git a/mm/memfd.c b/mm/memfd.c
index 27069518e3c5..2bb5e257080e 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -326,7 +326,7 @@ SYSCALL_DEFINE2(memfd_create,
 		goto err_fd;
 	}
 	file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
-	file->f_flags |= O_RDWR | O_LARGEFILE;
+	file->f_flags |= O_LARGEFILE;
 
 	if (flags & MFD_ALLOW_SEALING) {
 		file_seals = memfd_file_seals_ptr(file);
diff --git a/mm/shmem.c b/mm/shmem.c
index 2cab84403055..84844e52bf24 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3942,8 +3942,7 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 	if (IS_ERR(res))
 		goto put_path;
 
-	res = alloc_file(&path, FMODE_WRITE | FMODE_READ,
-		  &shmem_file_operations);
+	res = alloc_file(&path, O_RDWR, &shmem_file_operations);
 	if (IS_ERR(res))
 		goto put_path;
 
diff --git a/net/socket.c b/net/socket.c
index 8a109012608a..2cdbe8f71b7f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -411,7 +411,7 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 
 	d_instantiate(path.dentry, SOCK_INODE(sock));
 
-	file = alloc_file(&path, FMODE_READ | FMODE_WRITE,
+	file = alloc_file(&path, O_RDWR | (flags & O_NONBLOCK),
 		  &socket_file_ops);
 	if (IS_ERR(file)) {
 		/* drop dentry, keep inode for a bit */
@@ -423,7 +423,6 @@ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 	}
 
 	sock->file = file;
-	file->f_flags = O_RDWR | (flags & O_NONBLOCK);
 	file->private_data = sock;
 	return file;
 }
-- 
cgit v1.2.3


From 28519c891c5ad569203636b3b65d36bcb4333d4c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 12 Jul 2018 10:09:59 +0200
Subject: bsg: remove read/write support

The code poses a security risk due to user memory access in ->release
and had an API that can't be used reliably.  As far as we know it was
never used for real, but if that turns out wrong we'll have to revert
this commit and come up with a band aid.

Jann Horn did look software archives for users of this interface,
and the only users found were example code in sg3_utils, and optional
support in an optional module of the tgt user space iscsi target,
which looks like a proof of concept extension of the /dev/sg
read/write support.

Tony Battersby chimes in that the code is basically unsafe to use in
general:

  The read/write interface on /dev/bsg is impossible to use safely
  because the list of completed commands is per-device (bd->done_list)
  rather than per-fd like it is with /dev/sg.  So if program A and
  program B are both using the write/read interface on the same bsg
  device, then their command responses will get mixed up, and program
  A will read() some command results from program B and vice versa.
  So no, I don't use read/write on /dev/bsg.  From a security standpoint,
  it should definitely be fixed or removed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bsg.c | 460 +-----------------------------------------------------------
 1 file changed, 6 insertions(+), 454 deletions(-)

diff --git a/block/bsg.c b/block/bsg.c
index 66602c489956..0d2e9bf6208b 100644
--- a/block/bsg.c
+++ b/block/bsg.c
@@ -13,11 +13,9 @@
 #include <linux/init.h>
 #include <linux/file.h>
 #include <linux/blkdev.h>
-#include <linux/poll.h>
 #include <linux/cdev.h>
 #include <linux/jiffies.h>
 #include <linux/percpu.h>
-#include <linux/uio.h>
 #include <linux/idr.h>
 #include <linux/bsg.h>
 #include <linux/slab.h>
@@ -38,21 +36,10 @@
 struct bsg_device {
 	struct request_queue *queue;
 	spinlock_t lock;
-	struct list_head busy_list;
-	struct list_head done_list;
 	struct hlist_node dev_list;
 	atomic_t ref_count;
-	int queued_cmds;
-	int done_cmds;
-	wait_queue_head_t wq_done;
-	wait_queue_head_t wq_free;
 	char name[20];
 	int max_queue;
-	unsigned long flags;
-};
-
-enum {
-	BSG_F_BLOCK		= 1,
 };
 
 #define BSG_DEFAULT_CMDS	64
@@ -67,64 +54,6 @@ static struct hlist_head bsg_device_list[BSG_LIST_ARRAY_SIZE];
 static struct class *bsg_class;
 static int bsg_major;
 
-static struct kmem_cache *bsg_cmd_cachep;
-
-/*
- * our internal command type
- */
-struct bsg_command {
-	struct bsg_device *bd;
-	struct list_head list;
-	struct request *rq;
-	struct bio *bio;
-	struct bio *bidi_bio;
-	int err;
-	struct sg_io_v4 hdr;
-};
-
-static void bsg_free_command(struct bsg_command *bc)
-{
-	struct bsg_device *bd = bc->bd;
-	unsigned long flags;
-
-	kmem_cache_free(bsg_cmd_cachep, bc);
-
-	spin_lock_irqsave(&bd->lock, flags);
-	bd->queued_cmds--;
-	spin_unlock_irqrestore(&bd->lock, flags);
-
-	wake_up(&bd->wq_free);
-}
-
-static struct bsg_command *bsg_alloc_command(struct bsg_device *bd)
-{
-	struct bsg_command *bc = ERR_PTR(-EINVAL);
-
-	spin_lock_irq(&bd->lock);
-
-	if (bd->queued_cmds >= bd->max_queue)
-		goto out;
-
-	bd->queued_cmds++;
-	spin_unlock_irq(&bd->lock);
-
-	bc = kmem_cache_zalloc(bsg_cmd_cachep, GFP_KERNEL);
-	if (unlikely(!bc)) {
-		spin_lock_irq(&bd->lock);
-		bd->queued_cmds--;
-		bc = ERR_PTR(-ENOMEM);
-		goto out;
-	}
-
-	bc->bd = bd;
-	INIT_LIST_HEAD(&bc->list);
-	bsg_dbg(bd, "returning free cmd %p\n", bc);
-	return bc;
-out:
-	spin_unlock_irq(&bd->lock);
-	return bc;
-}
-
 static inline struct hlist_head *bsg_dev_idx_hash(int index)
 {
 	return &bsg_device_list[index & (BSG_LIST_ARRAY_SIZE - 1)];
@@ -287,101 +216,6 @@ out:
 	return ERR_PTR(ret);
 }
 
-/*
- * async completion call-back from the block layer, when scsi/ide/whatever
- * calls end_that_request_last() on a request
- */
-static void bsg_rq_end_io(struct request *rq, blk_status_t status)
-{
-	struct bsg_command *bc = rq->end_io_data;
-	struct bsg_device *bd = bc->bd;
-	unsigned long flags;
-
-	bsg_dbg(bd, "finished rq %p bc %p, bio %p\n",
-		rq, bc, bc->bio);
-
-	bc->hdr.duration = jiffies_to_msecs(jiffies - bc->hdr.duration);
-
-	spin_lock_irqsave(&bd->lock, flags);
-	list_move_tail(&bc->list, &bd->done_list);
-	bd->done_cmds++;
-	spin_unlock_irqrestore(&bd->lock, flags);
-
-	wake_up(&bd->wq_done);
-}
-
-/*
- * do final setup of a 'bc' and submit the matching 'rq' to the block
- * layer for io
- */
-static void bsg_add_command(struct bsg_device *bd, struct request_queue *q,
-			    struct bsg_command *bc, struct request *rq)
-{
-	int at_head = (0 == (bc->hdr.flags & BSG_FLAG_Q_AT_TAIL));
-
-	/*
-	 * add bc command to busy queue and submit rq for io
-	 */
-	bc->rq = rq;
-	bc->bio = rq->bio;
-	if (rq->next_rq)
-		bc->bidi_bio = rq->next_rq->bio;
-	bc->hdr.duration = jiffies;
-	spin_lock_irq(&bd->lock);
-	list_add_tail(&bc->list, &bd->busy_list);
-	spin_unlock_irq(&bd->lock);
-
-	bsg_dbg(bd, "queueing rq %p, bc %p\n", rq, bc);
-
-	rq->end_io_data = bc;
-	blk_execute_rq_nowait(q, NULL, rq, at_head, bsg_rq_end_io);
-}
-
-static struct bsg_command *bsg_next_done_cmd(struct bsg_device *bd)
-{
-	struct bsg_command *bc = NULL;
-
-	spin_lock_irq(&bd->lock);
-	if (bd->done_cmds) {
-		bc = list_first_entry(&bd->done_list, struct bsg_command, list);
-		list_del(&bc->list);
-		bd->done_cmds--;
-	}
-	spin_unlock_irq(&bd->lock);
-
-	return bc;
-}
-
-/*
- * Get a finished command from the done list
- */
-static struct bsg_command *bsg_get_done_cmd(struct bsg_device *bd)
-{
-	struct bsg_command *bc;
-	int ret;
-
-	do {
-		bc = bsg_next_done_cmd(bd);
-		if (bc)
-			break;
-
-		if (!test_bit(BSG_F_BLOCK, &bd->flags)) {
-			bc = ERR_PTR(-EAGAIN);
-			break;
-		}
-
-		ret = wait_event_interruptible(bd->wq_done, bd->done_cmds);
-		if (ret) {
-			bc = ERR_PTR(-ERESTARTSYS);
-			break;
-		}
-	} while (1);
-
-	bsg_dbg(bd, "returning done %p\n", bc);
-
-	return bc;
-}
-
 static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 				    struct bio *bio, struct bio *bidi_bio)
 {
@@ -400,234 +234,6 @@ static int blk_complete_sgv4_hdr_rq(struct request *rq, struct sg_io_v4 *hdr,
 	return ret;
 }
 
-static bool bsg_complete(struct bsg_device *bd)
-{
-	bool ret = false;
-	bool spin;
-
-	do {
-		spin_lock_irq(&bd->lock);
-
-		BUG_ON(bd->done_cmds > bd->queued_cmds);
-
-		/*
-		 * All commands consumed.
-		 */
-		if (bd->done_cmds == bd->queued_cmds)
-			ret = true;
-
-		spin = !test_bit(BSG_F_BLOCK, &bd->flags);
-
-		spin_unlock_irq(&bd->lock);
-	} while (!ret && spin);
-
-	return ret;
-}
-
-static int bsg_complete_all_commands(struct bsg_device *bd)
-{
-	struct bsg_command *bc;
-	int ret, tret;
-
-	bsg_dbg(bd, "entered\n");
-
-	/*
-	 * wait for all commands to complete
-	 */
-	io_wait_event(bd->wq_done, bsg_complete(bd));
-
-	/*
-	 * discard done commands
-	 */
-	ret = 0;
-	do {
-		spin_lock_irq(&bd->lock);
-		if (!bd->queued_cmds) {
-			spin_unlock_irq(&bd->lock);
-			break;
-		}
-		spin_unlock_irq(&bd->lock);
-
-		bc = bsg_get_done_cmd(bd);
-		if (IS_ERR(bc))
-			break;
-
-		tret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio,
-						bc->bidi_bio);
-		if (!ret)
-			ret = tret;
-
-		bsg_free_command(bc);
-	} while (1);
-
-	return ret;
-}
-
-static int
-__bsg_read(char __user *buf, size_t count, struct bsg_device *bd,
-	   const struct iovec *iov, ssize_t *bytes_read)
-{
-	struct bsg_command *bc;
-	int nr_commands, ret;
-
-	if (count % sizeof(struct sg_io_v4))
-		return -EINVAL;
-
-	ret = 0;
-	nr_commands = count / sizeof(struct sg_io_v4);
-	while (nr_commands) {
-		bc = bsg_get_done_cmd(bd);
-		if (IS_ERR(bc)) {
-			ret = PTR_ERR(bc);
-			break;
-		}
-
-		/*
-		 * this is the only case where we need to copy data back
-		 * after completing the request. so do that here,
-		 * bsg_complete_work() cannot do that for us
-		 */
-		ret = blk_complete_sgv4_hdr_rq(bc->rq, &bc->hdr, bc->bio,
-					       bc->bidi_bio);
-
-		if (copy_to_user(buf, &bc->hdr, sizeof(bc->hdr)))
-			ret = -EFAULT;
-
-		bsg_free_command(bc);
-
-		if (ret)
-			break;
-
-		buf += sizeof(struct sg_io_v4);
-		*bytes_read += sizeof(struct sg_io_v4);
-		nr_commands--;
-	}
-
-	return ret;
-}
-
-static inline void bsg_set_block(struct bsg_device *bd, struct file *file)
-{
-	if (file->f_flags & O_NONBLOCK)
-		clear_bit(BSG_F_BLOCK, &bd->flags);
-	else
-		set_bit(BSG_F_BLOCK, &bd->flags);
-}
-
-/*
- * Check if the error is a "real" error that we should return.
- */
-static inline int err_block_err(int ret)
-{
-	if (ret && ret != -ENOSPC && ret != -ENODATA && ret != -EAGAIN)
-		return 1;
-
-	return 0;
-}
-
-static ssize_t
-bsg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
-{
-	struct bsg_device *bd = file->private_data;
-	int ret;
-	ssize_t bytes_read;
-
-	bsg_dbg(bd, "read %zd bytes\n", count);
-
-	bsg_set_block(bd, file);
-
-	bytes_read = 0;
-	ret = __bsg_read(buf, count, bd, NULL, &bytes_read);
-	*ppos = bytes_read;
-
-	if (!bytes_read || err_block_err(ret))
-		bytes_read = ret;
-
-	return bytes_read;
-}
-
-static int __bsg_write(struct bsg_device *bd, const char __user *buf,
-		       size_t count, ssize_t *bytes_written, fmode_t mode)
-{
-	struct bsg_command *bc;
-	struct request *rq;
-	int ret, nr_commands;
-
-	if (count % sizeof(struct sg_io_v4))
-		return -EINVAL;
-
-	nr_commands = count / sizeof(struct sg_io_v4);
-	rq = NULL;
-	bc = NULL;
-	ret = 0;
-	while (nr_commands) {
-		struct request_queue *q = bd->queue;
-
-		bc = bsg_alloc_command(bd);
-		if (IS_ERR(bc)) {
-			ret = PTR_ERR(bc);
-			bc = NULL;
-			break;
-		}
-
-		if (copy_from_user(&bc->hdr, buf, sizeof(bc->hdr))) {
-			ret = -EFAULT;
-			break;
-		}
-
-		/*
-		 * get a request, fill in the blanks, and add to request queue
-		 */
-		rq = bsg_map_hdr(bd->queue, &bc->hdr, mode);
-		if (IS_ERR(rq)) {
-			ret = PTR_ERR(rq);
-			rq = NULL;
-			break;
-		}
-
-		bsg_add_command(bd, q, bc, rq);
-		bc = NULL;
-		rq = NULL;
-		nr_commands--;
-		buf += sizeof(struct sg_io_v4);
-		*bytes_written += sizeof(struct sg_io_v4);
-	}
-
-	if (bc)
-		bsg_free_command(bc);
-
-	return ret;
-}
-
-static ssize_t
-bsg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
-{
-	struct bsg_device *bd = file->private_data;
-	ssize_t bytes_written;
-	int ret;
-
-	bsg_dbg(bd, "write %zd bytes\n", count);
-
-	if (unlikely(uaccess_kernel()))
-		return -EINVAL;
-
-	bsg_set_block(bd, file);
-
-	bytes_written = 0;
-	ret = __bsg_write(bd, buf, count, &bytes_written, file->f_mode);
-
-	*ppos = bytes_written;
-
-	/*
-	 * return bytes written on non-fatal errors
-	 */
-	if (!bytes_written || err_block_err(ret))
-		bytes_written = ret;
-
-	bsg_dbg(bd, "returning %zd\n", bytes_written);
-	return bytes_written;
-}
-
 static struct bsg_device *bsg_alloc_device(void)
 {
 	struct bsg_device *bd;
@@ -637,29 +243,20 @@ static struct bsg_device *bsg_alloc_device(void)
 		return NULL;
 
 	spin_lock_init(&bd->lock);
-
 	bd->max_queue = BSG_DEFAULT_CMDS;
-
-	INIT_LIST_HEAD(&bd->busy_list);
-	INIT_LIST_HEAD(&bd->done_list);
 	INIT_HLIST_NODE(&bd->dev_list);
-
-	init_waitqueue_head(&bd->wq_free);
-	init_waitqueue_head(&bd->wq_done);
 	return bd;
 }
 
 static int bsg_put_device(struct bsg_device *bd)
 {
-	int ret = 0, do_free;
 	struct request_queue *q = bd->queue;
 
 	mutex_lock(&bsg_mutex);
 
-	do_free = atomic_dec_and_test(&bd->ref_count);
-	if (!do_free) {
+	if (!atomic_dec_and_test(&bd->ref_count)) {
 		mutex_unlock(&bsg_mutex);
-		goto out;
+		return 0;
 	}
 
 	hlist_del(&bd->dev_list);
@@ -670,20 +267,9 @@ static int bsg_put_device(struct bsg_device *bd)
 	/*
 	 * close can always block
 	 */
-	set_bit(BSG_F_BLOCK, &bd->flags);
-
-	/*
-	 * correct error detection baddies here again. it's the responsibility
-	 * of the app to properly reap commands before close() if it wants
-	 * fool-proof error detection
-	 */
-	ret = bsg_complete_all_commands(bd);
-
 	kfree(bd);
-out:
-	if (do_free)
-		blk_put_queue(q);
-	return ret;
+	blk_put_queue(q);
+	return 0;
 }
 
 static struct bsg_device *bsg_add_device(struct inode *inode,
@@ -706,8 +292,6 @@ static struct bsg_device *bsg_add_device(struct inode *inode,
 
 	bd->queue = rq;
 
-	bsg_set_block(bd, file);
-
 	atomic_set(&bd->ref_count, 1);
 	hlist_add_head(&bd->dev_list, bsg_dev_idx_hash(iminor(inode)));
 
@@ -781,24 +365,6 @@ static int bsg_release(struct inode *inode, struct file *file)
 	return bsg_put_device(bd);
 }
 
-static __poll_t bsg_poll(struct file *file, poll_table *wait)
-{
-	struct bsg_device *bd = file->private_data;
-	__poll_t mask = 0;
-
-	poll_wait(file, &bd->wq_done, wait);
-	poll_wait(file, &bd->wq_free, wait);
-
-	spin_lock_irq(&bd->lock);
-	if (!list_empty(&bd->done_list))
-		mask |= EPOLLIN | EPOLLRDNORM;
-	if (bd->queued_cmds < bd->max_queue)
-		mask |= EPOLLOUT;
-	spin_unlock_irq(&bd->lock);
-
-	return mask;
-}
-
 static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct bsg_device *bd = file->private_data;
@@ -872,9 +438,6 @@ static long bsg_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 }
 
 static const struct file_operations bsg_fops = {
-	.read		=	bsg_read,
-	.write		=	bsg_write,
-	.poll		=	bsg_poll,
 	.open		=	bsg_open,
 	.release	=	bsg_release,
 	.unlocked_ioctl	=	bsg_ioctl,
@@ -979,21 +542,12 @@ static int __init bsg_init(void)
 	int ret, i;
 	dev_t devid;
 
-	bsg_cmd_cachep = kmem_cache_create("bsg_cmd",
-				sizeof(struct bsg_command), 0, 0, NULL);
-	if (!bsg_cmd_cachep) {
-		printk(KERN_ERR "bsg: failed creating slab cache\n");
-		return -ENOMEM;
-	}
-
 	for (i = 0; i < BSG_LIST_ARRAY_SIZE; i++)
 		INIT_HLIST_HEAD(&bsg_device_list[i]);
 
 	bsg_class = class_create(THIS_MODULE, "bsg");
-	if (IS_ERR(bsg_class)) {
-		ret = PTR_ERR(bsg_class);
-		goto destroy_kmemcache;
-	}
+	if (IS_ERR(bsg_class))
+		return PTR_ERR(bsg_class);
 	bsg_class->devnode = bsg_devnode;
 
 	ret = alloc_chrdev_region(&devid, 0, BSG_MAX_DEVS, "bsg");
@@ -1014,8 +568,6 @@ unregister_chrdev:
 	unregister_chrdev_region(MKDEV(bsg_major, 0), BSG_MAX_DEVS);
 destroy_bsg_class:
 	class_destroy(bsg_class);
-destroy_kmemcache:
-	kmem_cache_destroy(bsg_cmd_cachep);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 6de37b6dc085e7c5e092b69289af66876526da44 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 10 Jul 2018 13:12:05 -0400
Subject: pass creds to get_empty_filp(), make sure dentry_open() passes the
 right creds

... and rename get_empty_filp() to alloc_empty_file().

dentry_open() gets creds as argument, but the only thing that sees those is
security_file_open() - file->f_cred still ends up with current_cred().  For
almost all callers it's the same thing, but there are several broken cases.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c | 5 ++---
 fs/internal.h   | 2 +-
 fs/namei.c      | 2 +-
 fs/open.c       | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 086c3f5ec31a..76cfa4c43e13 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -101,9 +101,8 @@ int proc_nr_files(struct ctl_table *table, int write,
  * done, you will imbalance int the mount's writer count
  * and a warning at __fput() time.
  */
-struct file *get_empty_filp(void)
+struct file *alloc_empty_file(const struct cred *cred)
 {
-	const struct cred *cred = current_cred();
 	static long old_max;
 	struct file *f;
 	int error;
@@ -161,7 +160,7 @@ struct file *alloc_file(const struct path *path, int flags,
 {
 	struct file *file;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(current_cred());
 	if (IS_ERR(file))
 		return file;
 
diff --git a/fs/internal.h b/fs/internal.h
index 5645b4ebf494..66473bf388e4 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -93,7 +93,7 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *get_empty_filp(void);
+extern struct file *alloc_empty_file(const struct cred *);
 
 /*
  * super.c
diff --git a/fs/namei.c b/fs/namei.c
index 734cef54fdf8..af2ec1803f57 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3513,7 +3513,7 @@ static struct file *path_openat(struct nameidata *nd,
 	int opened = 0;
 	int error;
 
-	file = get_empty_filp();
+	file = alloc_empty_file(current_cred());
 	if (IS_ERR(file))
 		return file;
 
diff --git a/fs/open.c b/fs/open.c
index 530da965e369..0061f9ea044d 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -921,7 +921,7 @@ struct file *dentry_open(const struct path *path, int flags,
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
-	f = get_empty_filp();
+	f = alloc_empty_file(cred);
 	if (!IS_ERR(f)) {
 		f->f_flags = flags;
 		error = vfs_open(path, f, cred);
-- 
cgit v1.2.3


From ea73ea7279884ba80896d4ea0f0443bf48b9e311 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 11 Jul 2018 15:00:04 -0400
Subject: pass ->f_flags value to alloc_empty_file()

... and have it set the f_flags-derived part of ->f_mode.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c | 8 ++++----
 fs/internal.h   | 2 +-
 fs/namei.c      | 4 +---
 fs/open.c       | 8 +++-----
 4 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 76cfa4c43e13..705f486f7007 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -101,7 +101,7 @@ int proc_nr_files(struct ctl_table *table, int write,
  * done, you will imbalance int the mount's writer count
  * and a warning at __fput() time.
  */
-struct file *alloc_empty_file(const struct cred *cred)
+struct file *alloc_empty_file(int flags, const struct cred *cred)
 {
 	static long old_max;
 	struct file *f;
@@ -135,6 +135,8 @@ struct file *alloc_empty_file(const struct cred *cred)
 	spin_lock_init(&f->f_lock);
 	mutex_init(&f->f_pos_lock);
 	eventpoll_init_file(f);
+	f->f_flags = flags;
+	f->f_mode = OPEN_FMODE(flags);
 	/* f->f_version: 0 */
 	percpu_counter_inc(&nr_files);
 	return f;
@@ -160,12 +162,10 @@ struct file *alloc_file(const struct path *path, int flags,
 {
 	struct file *file;
 
-	file = alloc_empty_file(current_cred());
+	file = alloc_empty_file(flags, current_cred());
 	if (IS_ERR(file))
 		return file;
 
-	file->f_mode = OPEN_FMODE(flags);
-	file->f_flags = flags;
 	file->f_path = *path;
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
diff --git a/fs/internal.h b/fs/internal.h
index 66473bf388e4..661c314aba30 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -93,7 +93,7 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern struct file *alloc_empty_file(const struct cred *);
+extern struct file *alloc_empty_file(int, const struct cred *);
 
 /*
  * super.c
diff --git a/fs/namei.c b/fs/namei.c
index af2ec1803f57..223925e30adb 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3513,12 +3513,10 @@ static struct file *path_openat(struct nameidata *nd,
 	int opened = 0;
 	int error;
 
-	file = alloc_empty_file(current_cred());
+	file = alloc_empty_file(op->open_flag, current_cred());
 	if (IS_ERR(file))
 		return file;
 
-	file->f_flags = op->open_flag;
-
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(nd, flags, op, file, &opened);
 		goto out2;
diff --git a/fs/open.c b/fs/open.c
index 0061f9ea044d..15d2c3ab91ff 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -742,9 +742,6 @@ static int do_dentry_open(struct file *f,
 	static const struct file_operations empty_fops = {};
 	int error;
 
-	f->f_mode = OPEN_FMODE(f->f_flags) | FMODE_LSEEK |
-				FMODE_PREAD | FMODE_PWRITE;
-
 	path_get(&f->f_path);
 	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
@@ -788,6 +785,8 @@ static int do_dentry_open(struct file *f,
 	if (error)
 		goto cleanup_all;
 
+	/* normally all 3 are set; ->open() can clear them if needed */
+	f->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
 	if (!open)
 		open = f->f_op->open;
 	if (open) {
@@ -921,9 +920,8 @@ struct file *dentry_open(const struct path *path, int flags,
 	/* We must always pass in a valid mount pointer. */
 	BUG_ON(!path->mnt);
 
-	f = alloc_empty_file(cred);
+	f = alloc_empty_file(flags, cred);
 	if (!IS_ERR(f)) {
-		f->f_flags = flags;
 		error = vfs_open(path, f, cred);
 		if (!error) {
 			/* from now on we need fput() to dispose of f */
-- 
cgit v1.2.3


From ae2bb293a3e8adbc54d08cede5afc22929030c03 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 10 Jul 2018 13:22:28 -0400
Subject: get rid of cred argument of vfs_open() and do_dentry_open()

always equal to ->f_cred

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/internal.h |  2 +-
 fs/namei.c    |  4 ++--
 fs/open.c     | 15 ++++++---------
 3 files changed, 9 insertions(+), 12 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index 661c314aba30..baeab53aeaff 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -126,7 +126,7 @@ int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 
 extern int open_check_o_direct(struct file *f);
-extern int vfs_open(const struct path *, struct file *, const struct cred *);
+extern int vfs_open(const struct path *, struct file *);
 
 /*
  * inode.c
diff --git a/fs/namei.c b/fs/namei.c
index 223925e30adb..3cf02804d5ff 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3396,7 +3396,7 @@ finish_open_created:
 	if (error)
 		goto out;
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
-	error = vfs_open(&nd->path, file, current_cred());
+	error = vfs_open(&nd->path, file);
 	if (error)
 		goto out;
 	*opened |= FILE_OPENED;
@@ -3499,7 +3499,7 @@ static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
 	int error = path_lookupat(nd, flags, &path);
 	if (!error) {
 		audit_inode(nd->name, path.dentry, 0);
-		error = vfs_open(&path, file, current_cred());
+		error = vfs_open(&path, file);
 		path_put(&path);
 	}
 	return error;
diff --git a/fs/open.c b/fs/open.c
index 15d2c3ab91ff..0a9f00b7f3d5 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -736,8 +736,7 @@ int open_check_o_direct(struct file *f)
 
 static int do_dentry_open(struct file *f,
 			  struct inode *inode,
-			  int (*open)(struct inode *, struct file *),
-			  const struct cred *cred)
+			  int (*open)(struct inode *, struct file *))
 {
 	static const struct file_operations empty_fops = {};
 	int error;
@@ -777,7 +776,7 @@ static int do_dentry_open(struct file *f,
 		goto cleanup_all;
 	}
 
-	error = security_file_open(f, cred);
+	error = security_file_open(f, f->f_cred);
 	if (error)
 		goto cleanup_all;
 
@@ -855,8 +854,7 @@ int finish_open(struct file *file, struct dentry *dentry,
 	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, d_backing_inode(dentry), open,
-			       current_cred());
+	error = do_dentry_open(file, d_backing_inode(dentry), open);
 	if (!error)
 		*opened |= FILE_OPENED;
 
@@ -897,8 +895,7 @@ EXPORT_SYMBOL(file_path);
  * @file: newly allocated file with f_flag initialized
  * @cred: credentials to use
  */
-int vfs_open(const struct path *path, struct file *file,
-	     const struct cred *cred)
+int vfs_open(const struct path *path, struct file *file)
 {
 	struct dentry *dentry = d_real(path->dentry, NULL, file->f_flags, 0);
 
@@ -906,7 +903,7 @@ int vfs_open(const struct path *path, struct file *file,
 		return PTR_ERR(dentry);
 
 	file->f_path = *path;
-	return do_dentry_open(file, d_backing_inode(dentry), NULL, cred);
+	return do_dentry_open(file, d_backing_inode(dentry), NULL);
 }
 
 struct file *dentry_open(const struct path *path, int flags,
@@ -922,7 +919,7 @@ struct file *dentry_open(const struct path *path, int flags,
 
 	f = alloc_empty_file(flags, cred);
 	if (!IS_ERR(f)) {
-		error = vfs_open(path, f, cred);
+		error = vfs_open(path, f);
 		if (!error) {
 			/* from now on we need fput() to dispose of f */
 			error = open_check_o_direct(f);
-- 
cgit v1.2.3


From e3f20ae21079ecac282df65d83865c5771f4bca0 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 10 Jul 2018 13:25:29 -0400
Subject: security_file_open(): lose cred argument

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/open.c                | 2 +-
 include/linux/security.h | 5 ++---
 security/security.c      | 4 ++--
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/open.c b/fs/open.c
index 0a9f00b7f3d5..4c65edefa487 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -776,7 +776,7 @@ static int do_dentry_open(struct file *f,
 		goto cleanup_all;
 	}
 
-	error = security_file_open(f, f->f_cred);
+	error = security_file_open(f);
 	if (error)
 		goto cleanup_all;
 
diff --git a/include/linux/security.h b/include/linux/security.h
index 63030c85ee19..88d30fc975e7 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -309,7 +309,7 @@ void security_file_set_fowner(struct file *file);
 int security_file_send_sigiotask(struct task_struct *tsk,
 				 struct fown_struct *fown, int sig);
 int security_file_receive(struct file *file);
-int security_file_open(struct file *file, const struct cred *cred);
+int security_file_open(struct file *file);
 int security_task_alloc(struct task_struct *task, unsigned long clone_flags);
 void security_task_free(struct task_struct *task);
 int security_cred_alloc_blank(struct cred *cred, gfp_t gfp);
@@ -858,8 +858,7 @@ static inline int security_file_receive(struct file *file)
 	return 0;
 }
 
-static inline int security_file_open(struct file *file,
-				     const struct cred *cred)
+static inline int security_file_open(struct file *file)
 {
 	return 0;
 }
diff --git a/security/security.c b/security/security.c
index 68f46d849abe..235b35f58a65 100644
--- a/security/security.c
+++ b/security/security.c
@@ -970,11 +970,11 @@ int security_file_receive(struct file *file)
 	return call_int_hook(file_receive, 0, file);
 }
 
-int security_file_open(struct file *file, const struct cred *cred)
+int security_file_open(struct file *file)
 {
 	int ret;
 
-	ret = call_int_hook(file_open, 0, file, cred);
+	ret = call_int_hook(file_open, 0, file, file->f_cred);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 9481769208b5e39b871ae4e89f5328c776ec38dc Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 10 Jul 2018 14:13:18 -0400
Subject: ->file_open(): lose cred argument

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/lsm_hooks.h  | 2 +-
 security/apparmor/lsm.c    | 4 ++--
 security/security.c        | 2 +-
 security/selinux/hooks.c   | 4 ++--
 security/smack/smack_lsm.c | 6 +++---
 security/tomoyo/tomoyo.c   | 2 +-
 6 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 8f1131c8dd54..a8ee106b865d 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -1569,7 +1569,7 @@ union security_list_options {
 	int (*file_send_sigiotask)(struct task_struct *tsk,
 					struct fown_struct *fown, int sig);
 	int (*file_receive)(struct file *file);
-	int (*file_open)(struct file *file, const struct cred *cred);
+	int (*file_open)(struct file *file);
 
 	int (*task_alloc)(struct task_struct *task, unsigned long clone_flags);
 	void (*task_free)(struct task_struct *task);
diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
index 74f17376202b..8b8b70620bbe 100644
--- a/security/apparmor/lsm.c
+++ b/security/apparmor/lsm.c
@@ -395,7 +395,7 @@ static int apparmor_inode_getattr(const struct path *path)
 	return common_perm_cond(OP_GETATTR, path, AA_MAY_GETATTR);
 }
 
-static int apparmor_file_open(struct file *file, const struct cred *cred)
+static int apparmor_file_open(struct file *file)
 {
 	struct aa_file_ctx *fctx = file_ctx(file);
 	struct aa_label *label;
@@ -414,7 +414,7 @@ static int apparmor_file_open(struct file *file, const struct cred *cred)
 		return 0;
 	}
 
-	label = aa_get_newest_cred_label(cred);
+	label = aa_get_newest_cred_label(file->f_cred);
 	if (!unconfined(label)) {
 		struct inode *inode = file_inode(file);
 		struct path_cond cond = { inode->i_uid, inode->i_mode };
diff --git a/security/security.c b/security/security.c
index 235b35f58a65..5dce67070cdf 100644
--- a/security/security.c
+++ b/security/security.c
@@ -974,7 +974,7 @@ int security_file_open(struct file *file)
 {
 	int ret;
 
-	ret = call_int_hook(file_open, 0, file, file->f_cred);
+	ret = call_int_hook(file_open, 0, file);
 	if (ret)
 		return ret;
 
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2b5ee5fbd652..18006be15713 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3862,7 +3862,7 @@ static int selinux_file_receive(struct file *file)
 	return file_has_perm(cred, file, file_to_av(file));
 }
 
-static int selinux_file_open(struct file *file, const struct cred *cred)
+static int selinux_file_open(struct file *file)
 {
 	struct file_security_struct *fsec;
 	struct inode_security_struct *isec;
@@ -3886,7 +3886,7 @@ static int selinux_file_open(struct file *file, const struct cred *cred)
 	 * new inode label or new policy.
 	 * This check is not redundant - do not remove.
 	 */
-	return file_path_has_perm(cred, file, open_file_to_av(file));
+	return file_path_has_perm(file->f_cred, file, open_file_to_av(file));
 }
 
 /* task security operations */
diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 7ad226018f51..e7b6c012431d 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -1927,9 +1927,9 @@ static int smack_file_receive(struct file *file)
  *
  * Returns 0
  */
-static int smack_file_open(struct file *file, const struct cred *cred)
+static int smack_file_open(struct file *file)
 {
-	struct task_smack *tsp = cred->security;
+	struct task_smack *tsp = file->f_cred->security;
 	struct inode *inode = file_inode(file);
 	struct smk_audit_info ad;
 	int rc;
@@ -1937,7 +1937,7 @@ static int smack_file_open(struct file *file, const struct cred *cred)
 	smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_PATH);
 	smk_ad_setfield_u_fs_path(&ad, file->f_path);
 	rc = smk_tskacc(tsp, smk_of_inode(inode), MAY_READ, &ad);
-	rc = smk_bu_credfile(cred, file, MAY_READ, rc);
+	rc = smk_bu_credfile(file->f_cred, file, MAY_READ, rc);
 
 	return rc;
 }
diff --git a/security/tomoyo/tomoyo.c b/security/tomoyo/tomoyo.c
index 213b8c593668..9f932e2d6852 100644
--- a/security/tomoyo/tomoyo.c
+++ b/security/tomoyo/tomoyo.c
@@ -320,7 +320,7 @@ static int tomoyo_file_fcntl(struct file *file, unsigned int cmd,
  *
  * Returns 0 on success, negative value otherwise.
  */
-static int tomoyo_file_open(struct file *f, const struct cred *cred)
+static int tomoyo_file_open(struct file *f)
 {
 	int flags = f->f_flags;
 	/* Don't check read permission here if called from do_execve(). */
-- 
cgit v1.2.3


From f5d11409e61dadf1f9af91b22bbedc28a60a2e2c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 02:35:08 -0400
Subject: introduce FMODE_OPENED

basically, "is that instance set up enough for regular fput(), or
do we want put_filp() for that one".

NOTE: the only alloc_file() caller that could be followed by put_filp()
is in arch/ia64/kernel/perfmon.c, which is (Kconfig-level) broken.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c    | 1 +
 fs/open.c          | 3 ++-
 include/linux/fs.h | 2 ++
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 705f486f7007..d664d10acfeb 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -176,6 +176,7 @@ struct file *alloc_file(const struct path *path, int flags,
 	if ((file->f_mode & FMODE_WRITE) &&
 	     likely(fop->write || fop->write_iter))
 		file->f_mode |= FMODE_CAN_WRITE;
+	file->f_mode |= FMODE_OPENED;
 	file->f_op = fop;
 	if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(path->dentry->d_inode);
diff --git a/fs/open.c b/fs/open.c
index 4c65edefa487..f3c6cb6a57b9 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -749,7 +749,7 @@ static int do_dentry_open(struct file *f,
 	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
 
 	if (unlikely(f->f_flags & O_PATH)) {
-		f->f_mode = FMODE_PATH;
+		f->f_mode = FMODE_PATH | FMODE_OPENED;
 		f->f_op = &empty_fops;
 		return 0;
 	}
@@ -793,6 +793,7 @@ static int do_dentry_open(struct file *f,
 		if (error)
 			goto cleanup_all;
 	}
+	f->f_mode |= FMODE_OPENED;
 	if ((f->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ)
 		i_readcount_inc(inode);
 	if ((f->f_mode & FMODE_READ) &&
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c4ca4c9c1130..05f34726e29c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -148,6 +148,8 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 /* Has write method(s) */
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
+#define FMODE_OPENED		((__force fmode_t)0x80000)
+
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
 
-- 
cgit v1.2.3


From 4d27f3266f14e4d1d13125ce32cb49a40f3122c3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 11:14:39 -0400
Subject: fold put_filp() into fput()

Just check FMODE_OPENED in __fput() and be done with that...

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c      | 15 +++++----------
 fs/namei.c           |  4 ++--
 fs/open.c            | 11 +++--------
 include/linux/file.h |  1 -
 4 files changed, 10 insertions(+), 21 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index d664d10acfeb..9b70ed2bbc4e 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -192,6 +192,9 @@ static void __fput(struct file *file)
 	struct vfsmount *mnt = file->f_path.mnt;
 	struct inode *inode = file->f_inode;
 
+	if (unlikely(!(file->f_mode & FMODE_OPENED)))
+		goto out;
+
 	might_sleep();
 
 	fsnotify_close(file);
@@ -221,12 +224,10 @@ static void __fput(struct file *file)
 		put_write_access(inode);
 		__mnt_drop_write(mnt);
 	}
-	file->f_path.dentry = NULL;
-	file->f_path.mnt = NULL;
-	file->f_inode = NULL;
-	file_free(file);
 	dput(dentry);
 	mntput(mnt);
+out:
+	file_free(file);
 }
 
 static LLIST_HEAD(delayed_fput_list);
@@ -301,12 +302,6 @@ void __fput_sync(struct file *file)
 
 EXPORT_SYMBOL(fput);
 
-void put_filp(struct file *file)
-{
-	if (atomic_long_dec_and_test(&file->f_count))
-		file_free(file);
-}
-
 void __init files_init(void)
 {
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
diff --git a/fs/namei.c b/fs/namei.c
index 3cf02804d5ff..503c4b968415 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3531,7 +3531,7 @@ static struct file *path_openat(struct nameidata *nd,
 
 	s = path_init(nd, flags);
 	if (IS_ERR(s)) {
-		put_filp(file);
+		fput(file);
 		return ERR_CAST(s);
 	}
 	while (!(error = link_path_walk(s, nd)) &&
@@ -3547,7 +3547,7 @@ static struct file *path_openat(struct nameidata *nd,
 out2:
 	if (!(opened & FILE_OPENED)) {
 		BUG_ON(!error);
-		put_filp(file);
+		fput(file);
 	}
 	if (unlikely(error)) {
 		if (error == -EOPENSTALE) {
diff --git a/fs/open.c b/fs/open.c
index f3c6cb6a57b9..3d09b823f12b 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -921,15 +921,10 @@ struct file *dentry_open(const struct path *path, int flags,
 	f = alloc_empty_file(flags, cred);
 	if (!IS_ERR(f)) {
 		error = vfs_open(path, f);
-		if (!error) {
-			/* from now on we need fput() to dispose of f */
+		if (!error)
 			error = open_check_o_direct(f);
-			if (error) {
-				fput(f);
-				f = ERR_PTR(error);
-			}
-		} else { 
-			put_filp(f);
+		if (error) {
+			fput(f);
 			f = ERR_PTR(error);
 		}
 	}
diff --git a/include/linux/file.h b/include/linux/file.h
index 6d34a1262b31..aed45d69811e 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -78,7 +78,6 @@ extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
 extern int replace_fd(unsigned fd, struct file *file, unsigned flags);
 extern void set_close_on_exec(unsigned int fd, int flag);
 extern bool get_close_on_exec(unsigned int fd);
-extern void put_filp(struct file *);
 extern int get_unused_fd_flags(unsigned flags);
 extern void put_unused_fd(unsigned int fd);
 
-- 
cgit v1.2.3


From 7c1c01ec20d61ef52dba9b6f85435e53449bea71 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 12:56:55 -0400
Subject: lift fput() on late failures into path_openat()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 28 ++++++++++++----------------
 1 file changed, 12 insertions(+), 16 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 503c4b968415..bb77f6cc3ea8 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3407,8 +3407,6 @@ opened:
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
-	if (unlikely(error) && (*opened & FILE_OPENED))
-		fput(file);
 	if (unlikely(error > 0)) {
 		WARN_ON(1);
 		error = -EINVAL;
@@ -3484,8 +3482,6 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	error = open_check_o_direct(file);
-	if (error)
-		fput(file);
 out2:
 	mnt_drop_write(path.mnt);
 out:
@@ -3545,20 +3541,20 @@ static struct file *path_openat(struct nameidata *nd,
 	}
 	terminate_walk(nd);
 out2:
-	if (!(opened & FILE_OPENED)) {
-		BUG_ON(!error);
-		fput(file);
+	if (likely(!error)) {
+		if (likely(opened & FILE_OPENED))
+			return file;
+		WARN_ON(1);
+		error = -EINVAL;
 	}
-	if (unlikely(error)) {
-		if (error == -EOPENSTALE) {
-			if (flags & LOOKUP_RCU)
-				error = -ECHILD;
-			else
-				error = -ESTALE;
-		}
-		file = ERR_PTR(error);
+	fput(file);
+	if (error == -EOPENSTALE) {
+		if (flags & LOOKUP_RCU)
+			error = -ECHILD;
+		else
+			error = -ESTALE;
 	}
-	return file;
+	return ERR_PTR(error);
 }
 
 struct file *do_filp_open(int dfd, struct filename *pathname,
-- 
cgit v1.2.3


From 69527c554f82d4bca4b154ccc06ad1554806bdc0 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 13:01:49 -0400
Subject: now we can fold open_check_o_direct() into do_dentry_open()

These checks are better off in do_dentry_open(); the reason we couldn't
put them there used to be that callers couldn't tell what kind of cleanup
would do_dentry_open() failure call for.  Now that we have FMODE_OPENED,
cleanup is the same in all cases - it's simply fput().  So let's fold
that into do_dentry_open(), as Christoph's patch tried to.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/internal.h |  1 -
 fs/namei.c    |  7 +------
 fs/open.c     | 17 +++++------------
 3 files changed, 6 insertions(+), 19 deletions(-)

diff --git a/fs/internal.h b/fs/internal.h
index baeab53aeaff..52a346903748 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -125,7 +125,6 @@ int do_fchmodat(int dfd, const char __user *filename, umode_t mode);
 int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group,
 		int flag);
 
-extern int open_check_o_direct(struct file *f);
 extern int vfs_open(const struct path *, struct file *);
 
 /*
diff --git a/fs/namei.c b/fs/namei.c
index bb77f6cc3ea8..d152cc05fdc3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3401,9 +3401,7 @@ finish_open_created:
 		goto out;
 	*opened |= FILE_OPENED;
 opened:
-	error = open_check_o_direct(file);
-	if (!error)
-		error = ima_file_check(file, op->acc_mode, *opened);
+	error = ima_file_check(file, op->acc_mode, *opened);
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
@@ -3479,9 +3477,6 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		goto out2;
 	file->f_path.mnt = path.mnt;
 	error = finish_open(file, child, NULL, opened);
-	if (error)
-		goto out2;
-	error = open_check_o_direct(file);
 out2:
 	mnt_drop_write(path.mnt);
 out:
diff --git a/fs/open.c b/fs/open.c
index 3d09b823f12b..ee893240d199 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -724,16 +724,6 @@ SYSCALL_DEFINE3(fchown, unsigned int, fd, uid_t, user, gid_t, group)
 	return ksys_fchown(fd, user, group);
 }
 
-int open_check_o_direct(struct file *f)
-{
-	/* NB: we're sure to have correct a_ops only after f_op->open */
-	if (f->f_flags & O_DIRECT) {
-		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
-			return -EINVAL;
-	}
-	return 0;
-}
-
 static int do_dentry_open(struct file *f,
 			  struct inode *inode,
 			  int (*open)(struct inode *, struct file *))
@@ -808,6 +798,11 @@ static int do_dentry_open(struct file *f,
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
 
+	/* NB: we're sure to have correct a_ops only after f_op->open */
+	if (f->f_flags & O_DIRECT) {
+		if (!f->f_mapping->a_ops || !f->f_mapping->a_ops->direct_IO)
+			return -EINVAL;
+	}
 	return 0;
 
 cleanup_all:
@@ -921,8 +916,6 @@ struct file *dentry_open(const struct path *path, int flags,
 	f = alloc_empty_file(flags, cred);
 	if (!IS_ERR(f)) {
 		error = vfs_open(path, f);
-		if (!error)
-			error = open_check_o_direct(f);
 		if (error) {
 			fput(f);
 			f = ERR_PTR(error);
-- 
cgit v1.2.3


From aad888f828fec1e7160b67f122172e7ab7f82e03 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 12:58:04 -0400
Subject: switch all remaining checks for FILE_OPENED to FMODE_OPENED

... and don't bother with setting FILE_OPENED at all.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/gfs2/inode.c | 2 +-
 fs/namei.c      | 7 ++-----
 fs/open.c       | 9 ++-------
 3 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index feda55f67050..67c588edf8d8 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1250,7 +1250,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (d != NULL)
 		dentry = d;
 	if (d_really_is_positive(dentry)) {
-		if (!(*opened & FILE_OPENED))
+		if (!(file->f_mode & FMODE_OPENED))
 			return finish_no_open(file, d);
 		dput(d);
 		return 0;
diff --git a/fs/namei.c b/fs/namei.c
index d152cc05fdc3..8a1ae074c1c1 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3395,11 +3395,10 @@ finish_open_created:
 	error = may_open(&nd->path, acc_mode, open_flag);
 	if (error)
 		goto out;
-	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
+	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
 	error = vfs_open(&nd->path, file);
 	if (error)
 		goto out;
-	*opened |= FILE_OPENED;
 opened:
 	error = ima_file_check(file, op->acc_mode, *opened);
 	if (!error && will_truncate)
@@ -3515,8 +3514,6 @@ static struct file *path_openat(struct nameidata *nd,
 
 	if (unlikely(file->f_flags & O_PATH)) {
 		error = do_o_path(nd, flags, file);
-		if (!error)
-			opened |= FILE_OPENED;
 		goto out2;
 	}
 
@@ -3537,7 +3534,7 @@ static struct file *path_openat(struct nameidata *nd,
 	terminate_walk(nd);
 out2:
 	if (likely(!error)) {
-		if (likely(opened & FILE_OPENED))
+		if (likely(file->f_mode & FMODE_OPENED))
 			return file;
 		WARN_ON(1);
 		error = -EINVAL;
diff --git a/fs/open.c b/fs/open.c
index ee893240d199..d2030a3c5c52 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -846,15 +846,10 @@ int finish_open(struct file *file, struct dentry *dentry,
 		int (*open)(struct inode *, struct file *),
 		int *opened)
 {
-	int error;
-	BUG_ON(*opened & FILE_OPENED); /* once it's opened, it's opened */
+	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
 
 	file->f_path.dentry = dentry;
-	error = do_dentry_open(file, d_backing_inode(dentry), open);
-	if (!error)
-		*opened |= FILE_OPENED;
-
-	return error;
+	return do_dentry_open(file, d_backing_inode(dentry), open);
 }
 EXPORT_SYMBOL(finish_open);
 
-- 
cgit v1.2.3


From 73a09dd94377e4b186b300bd5461920710c7c3d5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 13:22:02 -0400
Subject: introduce FMODE_CREATED and switch to it

Parallel to FILE_CREATED, goes into ->f_mode instead of *opened.
NFS is a bit of a wart here - it doesn't have file at the point
where FILE_CREATED used to be set, so we need to propagate it
there (for now).  IMA is another one (here and everywhere)...

Note that this needs do_dentry_open() to leave old bits in ->f_mode
alone - we want it to preserve FMODE_CREATED if it had been already
set (no other bit can be there).

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/9p/vfs_inode.c      |  2 +-
 fs/9p/vfs_inode_dotl.c |  2 +-
 fs/ceph/file.c         |  2 +-
 fs/cifs/dir.c          |  2 +-
 fs/fuse/dir.c          |  2 +-
 fs/gfs2/inode.c        |  2 +-
 fs/namei.c             | 15 ++++++++-------
 fs/nfs/dir.c           |  5 ++++-
 fs/nfs/nfs4proc.c      |  2 +-
 include/linux/fs.h     |  1 +
 10 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 42e102e2e74a..566929792480 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -925,7 +925,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(d_inode(dentry), file);
 
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	dput(res);
 	return err;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 7f6ae21a27b3..ee65db5c7eb0 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -358,7 +358,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	file->private_data = ofid;
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		v9fs_cache_inode_set_cookie(inode, file);
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 out:
 	v9fs_put_acl(dacl, pacl);
 	dput(res);
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index ad0bed99b1d5..38a63fff7903 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -507,7 +507,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 		dout("atomic_open finish_open on dn %p\n", dn);
 		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
 			ceph_init_inode_acls(d_inode(dentry), &acls);
-			*opened |= FILE_CREATED;
+			file->f_mode |= FMODE_CREATED;
 		}
 		err = finish_open(file, dentry, ceph_open, opened);
 	}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index ddae52bd1993..21d7e393900e 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -539,7 +539,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	}
 
 	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 
 	rc = finish_open(file, direntry, generic_file_open, opened);
 	if (rc) {
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 56231b31f806..d4bdcf51e6cb 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -508,7 +508,7 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 		goto no_open;
 
 	/* Only creates */
-	*opened |= FILE_CREATED;
+	file->f_mode |= FMODE_CREATED;
 
 	if (fc->no_create)
 		goto mknod;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 67c588edf8d8..4aba00a6004b 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -767,7 +767,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	mark_inode_dirty(inode);
 	d_instantiate(dentry, inode);
 	if (file) {
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 		error = finish_open(file, dentry, gfs2_open_common, opened);
 	}
 	gfs2_glock_dq_uninit(ghs);
diff --git a/fs/namei.c b/fs/namei.c
index 8a1ae074c1c1..4bd7cc0d7522 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3061,7 +3061,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 		 * permission here.
 		 */
 		int acc_mode = op->acc_mode;
-		if (*opened & FILE_CREATED) {
+		if (file->f_mode & FMODE_CREATED) {
 			WARN_ON(!(open_flag & O_CREAT));
 			fsnotify_create(dir, dentry);
 			acc_mode = 0;
@@ -3077,7 +3077,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 				dput(dentry);
 				dentry = file->f_path.dentry;
 			}
-			if (*opened & FILE_CREATED)
+			if (file->f_mode & FMODE_CREATED)
 				fsnotify_create(dir, dentry);
 			if (unlikely(d_is_negative(dentry))) {
 				error = -ENOENT;
@@ -3126,7 +3126,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 	if (unlikely(IS_DEADDIR(dir_inode)))
 		return -ENOENT;
 
-	*opened &= ~FILE_CREATED;
+	file->f_mode &= ~FMODE_CREATED;
 	dentry = d_lookup(dir, &nd->last);
 	for (;;) {
 		if (!dentry) {
@@ -3211,7 +3211,7 @@ no_open:
 
 	/* Negative dentry, just create the file */
 	if (!dentry->d_inode && (open_flag & O_CREAT)) {
-		*opened |= FILE_CREATED;
+		file->f_mode |= FMODE_CREATED;
 		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 		if (!dir_inode->i_op->create) {
 			error = -EACCES;
@@ -3318,7 +3318,7 @@ static int do_last(struct nameidata *nd,
 		if (error)
 			goto out;
 
-		if ((*opened & FILE_CREATED) ||
+		if ((file->f_mode & FMODE_CREATED) ||
 		    !S_ISREG(file_inode(file)->i_mode))
 			will_truncate = false;
 
@@ -3326,7 +3326,7 @@ static int do_last(struct nameidata *nd,
 		goto opened;
 	}
 
-	if (*opened & FILE_CREATED) {
+	if (file->f_mode & FMODE_CREATED) {
 		/* Don't check for write permission, don't truncate */
 		open_flag &= ~O_TRUNC;
 		will_truncate = false;
@@ -3400,7 +3400,8 @@ finish_open_created:
 	if (error)
 		goto out;
 opened:
-	error = ima_file_check(file, op->acc_mode, *opened);
+	error = ima_file_check(file, op->acc_mode,
+				file->f_mode & FMODE_CREATED ? FILE_CREATED : 0);
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 7a9c14426855..0ac50983fc4e 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1461,6 +1461,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	unsigned int lookup_flags = 0;
 	bool switched = false;
+	int created = 0;
 	int err;
 
 	/* Expect a negative dentry */
@@ -1521,7 +1522,9 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto out;
 
 	trace_nfs_atomic_open_enter(dir, ctx, open_flags);
-	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, opened);
+	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, &created);
+	if (created)
+		file->f_mode |= FMODE_CREATED;
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ed45090e4df6..2c4df0ffbca1 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2951,7 +2951,7 @@ static int _nfs4_do_open(struct inode *dir,
 		}
 	}
 	if (opened && opendata->file_created)
-		*opened |= FILE_CREATED;
+		*opened = 1;
 
 	if (pnfs_use_threshold(ctx_th, opendata->f_attr.mdsthreshold, server)) {
 		*ctx_th = opendata->f_attr.mdsthreshold;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 05f34726e29c..ca668c7e48a7 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -149,6 +149,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
 
 #define FMODE_OPENED		((__force fmode_t)0x80000)
+#define FMODE_CREATED		((__force fmode_t)0x100000)
 
 /* File was opened by fanotify and shouldn't generate fanotify events */
 #define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
-- 
cgit v1.2.3


From 6035a27b25ab9dadc8c3d5c5df5eae3fca62fc95 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 13:40:10 -0400
Subject: IMA: don't propagate opened through the entire thing

just check ->f_mode in ima_appraise_measurement()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c                            |  3 +--
 fs/nfsd/vfs.c                         |  2 +-
 include/linux/ima.h                   |  4 ++--
 security/integrity/ima/ima.h          |  4 ++--
 security/integrity/ima/ima_appraise.c |  4 ++--
 security/integrity/ima/ima_main.c     | 16 ++++++++--------
 6 files changed, 16 insertions(+), 17 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 4bd7cc0d7522..d2aeb282ed05 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3400,8 +3400,7 @@ finish_open_created:
 	if (error)
 		goto out;
 opened:
-	error = ima_file_check(file, op->acc_mode,
-				file->f_mode & FMODE_CREATED ? FILE_CREATED : 0);
+	error = ima_file_check(file, op->acc_mode);
 	if (!error && will_truncate)
 		error = handle_truncate(file);
 out:
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index b0555d7d8200..55a099e47ba2 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -763,7 +763,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, umode_t type,
 		goto out_nfserr;
 	}
 
-	host_err = ima_file_check(file, may_flags, 0);
+	host_err = ima_file_check(file, may_flags);
 	if (host_err) {
 		fput(file);
 		goto out_nfserr;
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 0e4647e0eb60..d9ba3fc363b7 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -16,7 +16,7 @@ struct linux_binprm;
 
 #ifdef CONFIG_IMA
 extern int ima_bprm_check(struct linux_binprm *bprm);
-extern int ima_file_check(struct file *file, int mask, int opened);
+extern int ima_file_check(struct file *file, int mask);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
@@ -34,7 +34,7 @@ static inline int ima_bprm_check(struct linux_binprm *bprm)
 	return 0;
 }
 
-static inline int ima_file_check(struct file *file, int mask, int opened)
+static inline int ima_file_check(struct file *file, int mask)
 {
 	return 0;
 }
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 354bb5716ce3..e4c1a236976c 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -238,7 +238,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 			     struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len, int opened);
+			     int xattr_len);
 int ima_must_appraise(struct inode *inode, int mask, enum ima_hooks func);
 void ima_update_xattr(struct integrity_iint_cache *iint, struct file *file);
 enum integrity_status ima_get_cache_status(struct integrity_iint_cache *iint,
@@ -254,7 +254,7 @@ static inline int ima_appraise_measurement(enum ima_hooks func,
 					   struct file *file,
 					   const unsigned char *filename,
 					   struct evm_ima_xattr_data *xattr_value,
-					   int xattr_len, int opened)
+					   int xattr_len)
 {
 	return INTEGRITY_UNKNOWN;
 }
diff --git a/security/integrity/ima/ima_appraise.c b/security/integrity/ima/ima_appraise.c
index 8bd7a0733e51..deec1804a00a 100644
--- a/security/integrity/ima/ima_appraise.c
+++ b/security/integrity/ima/ima_appraise.c
@@ -212,7 +212,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 			     struct integrity_iint_cache *iint,
 			     struct file *file, const unsigned char *filename,
 			     struct evm_ima_xattr_data *xattr_value,
-			     int xattr_len, int opened)
+			     int xattr_len)
 {
 	static const char op[] = "appraise_data";
 	const char *cause = "unknown";
@@ -231,7 +231,7 @@ int ima_appraise_measurement(enum ima_hooks func,
 		cause = iint->flags & IMA_DIGSIG_REQUIRED ?
 				"IMA-signature-required" : "missing-hash";
 		status = INTEGRITY_NOLABEL;
-		if (opened & FILE_CREATED)
+		if (file->f_mode & FMODE_CREATED)
 			iint->flags |= IMA_NEW_FILE;
 		if ((iint->flags & IMA_NEW_FILE) &&
 		    (!(iint->flags & IMA_DIGSIG_REQUIRED) ||
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index dca44cf7838e..b286f37712d5 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -168,7 +168,7 @@ void ima_file_free(struct file *file)
 
 static int process_measurement(struct file *file, const struct cred *cred,
 			       u32 secid, char *buf, loff_t size, int mask,
-			       enum ima_hooks func, int opened)
+			       enum ima_hooks func)
 {
 	struct inode *inode = file_inode(file);
 	struct integrity_iint_cache *iint = NULL;
@@ -294,7 +294,7 @@ static int process_measurement(struct file *file, const struct cred *cred,
 	if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) {
 		inode_lock(inode);
 		rc = ima_appraise_measurement(func, iint, file, pathname,
-					      xattr_value, xattr_len, opened);
+					      xattr_value, xattr_len);
 		inode_unlock(inode);
 	}
 	if (action & IMA_AUDIT)
@@ -338,7 +338,7 @@ int ima_file_mmap(struct file *file, unsigned long prot)
 	if (file && (prot & PROT_EXEC)) {
 		security_task_getsecid(current, &secid);
 		return process_measurement(file, current_cred(), secid, NULL,
-					   0, MAY_EXEC, MMAP_CHECK, 0);
+					   0, MAY_EXEC, MMAP_CHECK);
 	}
 
 	return 0;
@@ -364,13 +364,13 @@ int ima_bprm_check(struct linux_binprm *bprm)
 
 	security_task_getsecid(current, &secid);
 	ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0,
-				  MAY_EXEC, BPRM_CHECK, 0);
+				  MAY_EXEC, BPRM_CHECK);
 	if (ret)
 		return ret;
 
 	security_cred_getsecid(bprm->cred, &secid);
 	return process_measurement(bprm->file, bprm->cred, secid, NULL, 0,
-				   MAY_EXEC, CREDS_CHECK, 0);
+				   MAY_EXEC, CREDS_CHECK);
 }
 
 /**
@@ -383,14 +383,14 @@ int ima_bprm_check(struct linux_binprm *bprm)
  * On success return 0.  On integrity appraisal error, assuming the file
  * is in policy and IMA-appraisal is in enforcing mode, return -EACCES.
  */
-int ima_file_check(struct file *file, int mask, int opened)
+int ima_file_check(struct file *file, int mask)
 {
 	u32 secid;
 
 	security_task_getsecid(current, &secid);
 	return process_measurement(file, current_cred(), secid, NULL, 0,
 				   mask & (MAY_READ | MAY_WRITE | MAY_EXEC |
-					   MAY_APPEND), FILE_CHECK, opened);
+					   MAY_APPEND), FILE_CHECK);
 }
 EXPORT_SYMBOL_GPL(ima_file_check);
 
@@ -493,7 +493,7 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 	func = read_idmap[read_id] ?: FILE_CHECK;
 	security_task_getsecid(current, &secid);
 	return process_measurement(file, current_cred(), secid, buf, size,
-				   MAY_READ, func, 0);
+				   MAY_READ, func);
 }
 
 static int __init init_ima(void)
-- 
cgit v1.2.3


From be12af3ef5e61ebc44d065e121424ac605d7bb8e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 11:44:56 -0400
Subject: getting rid of 'opened' argument of ->atomic_open() - part 1

'opened' argument of finish_open() is unused.  Kill it.

Signed-off-by Al Viro <viro@zeniv.linux.org.uk>
---
 fs/9p/vfs_inode.c      | 2 +-
 fs/9p/vfs_inode_dotl.c | 2 +-
 fs/ceph/file.c         | 2 +-
 fs/cifs/dir.c          | 2 +-
 fs/fuse/dir.c          | 2 +-
 fs/gfs2/inode.c        | 6 +++---
 fs/namei.c             | 2 +-
 fs/nfs/dir.c           | 2 +-
 fs/open.c              | 3 +--
 include/linux/fs.h     | 3 +--
 10 files changed, 12 insertions(+), 14 deletions(-)

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 566929792480..7b6ff3275d9c 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -917,7 +917,7 @@ v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		v9inode->writeback_fid = (void *) inode_fid;
 	}
 	mutex_unlock(&v9inode->v_mutex);
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto error;
 
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index ee65db5c7eb0..c6939b7cb18c 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -352,7 +352,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	}
 	mutex_unlock(&v9inode->v_mutex);
 	/* Since we are opening a file, assign the open fid to the file */
-	err = finish_open(file, dentry, generic_file_open, opened);
+	err = finish_open(file, dentry, generic_file_open);
 	if (err)
 		goto err_clunk_old_fid;
 	file->private_data = ofid;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 38a63fff7903..38b28cb2fac1 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -509,7 +509,7 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 			ceph_init_inode_acls(d_inode(dentry), &acls);
 			file->f_mode |= FMODE_CREATED;
 		}
-		err = finish_open(file, dentry, ceph_open, opened);
+		err = finish_open(file, dentry, ceph_open);
 	}
 out_req:
 	if (!req->r_err && req->r_target_inode)
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 21d7e393900e..891bfd62e67a 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -541,7 +541,7 @@ cifs_atomic_open(struct inode *inode, struct dentry *direntry,
 	if ((oflags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
 		file->f_mode |= FMODE_CREATED;
 
-	rc = finish_open(file, direntry, generic_file_open, opened);
+	rc = finish_open(file, direntry, generic_file_open);
 	if (rc) {
 		if (server->ops->close)
 			server->ops->close(xid, tcon, &fid);
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index d4bdcf51e6cb..a5b1f5ff8cb7 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -469,7 +469,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	d_instantiate(entry, inode);
 	fuse_change_entry_timeout(entry, &outentry);
 	fuse_invalidate_attr(dir);
-	err = finish_open(file, entry, generic_file_open, opened);
+	err = finish_open(file, entry, generic_file_open);
 	if (err) {
 		fuse_sync_release(ff, flags);
 	} else {
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 4aba00a6004b..59f695e96d63 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -626,7 +626,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		error = 0;
 		if (file) {
 			if (S_ISREG(inode->i_mode))
-				error = finish_open(file, dentry, gfs2_open_common, opened);
+				error = finish_open(file, dentry, gfs2_open_common);
 			else
 				error = finish_no_open(file, NULL);
 		}
@@ -768,7 +768,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	d_instantiate(dentry, inode);
 	if (file) {
 		file->f_mode |= FMODE_CREATED;
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		error = finish_open(file, dentry, gfs2_open_common);
 	}
 	gfs2_glock_dq_uninit(ghs);
 	gfs2_glock_dq_uninit(ghs + 1);
@@ -866,7 +866,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 		return d;
 	}
 	if (file && S_ISREG(inode->i_mode))
-		error = finish_open(file, dentry, gfs2_open_common, opened);
+		error = finish_open(file, dentry, gfs2_open_common);
 
 	gfs2_glock_dq_uninit(&gh);
 	if (error) {
diff --git a/fs/namei.c b/fs/namei.c
index d2aeb282ed05..117b118853f2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3475,7 +3475,7 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	file->f_path.mnt = path.mnt;
-	error = finish_open(file, child, NULL, opened);
+	error = finish_open(file, child, NULL);
 out2:
 	mnt_drop_write(path.mnt);
 out:
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 0ac50983fc4e..22176a3818d5 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1439,7 +1439,7 @@ static int nfs_finish_open(struct nfs_open_context *ctx,
 {
 	int err;
 
-	err = finish_open(file, dentry, do_open, opened);
+	err = finish_open(file, dentry, do_open);
 	if (err)
 		goto out;
 	if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
diff --git a/fs/open.c b/fs/open.c
index d2030a3c5c52..dbaac9efc7fc 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -843,8 +843,7 @@ cleanup_file:
  * Returns zero on success or -errno if the open failed.
  */
 int finish_open(struct file *file, struct dentry *dentry,
-		int (*open)(struct inode *, struct file *),
-		int *opened)
+		int (*open)(struct inode *, struct file *))
 {
 	BUG_ON(file->f_mode & FMODE_OPENED); /* once it's opened, it's opened */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ca668c7e48a7..70be3e4c26ac 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2441,8 +2441,7 @@ enum {
 	FILE_OPENED = 2
 };
 extern int finish_open(struct file *file, struct dentry *dentry,
-			int (*open)(struct inode *, struct file *),
-			int *opened);
+			int (*open)(struct inode *, struct file *));
 extern int finish_no_open(struct file *file, struct dentry *dentry);
 
 /* fs/ioctl.c */
-- 
cgit v1.2.3


From b452a458caaa95d02b74897d35e87aa080122f07 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 13:06:28 -0400
Subject: getting rid of 'opened' argument of ->atomic_open() - part 2

__gfs2_lookup(), gfs2_create_inode(), nfs_finish_open() and fuse_create_open()
don't need 'opened' anymore.  Get rid of that argument in those.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/fuse/dir.c   |  4 ++--
 fs/gfs2/inode.c | 19 +++++++++----------
 fs/nfs/dir.c    |  5 ++---
 3 files changed, 13 insertions(+), 15 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index a5b1f5ff8cb7..b8d7e9d423c8 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -399,7 +399,7 @@ static struct dentry *fuse_lookup(struct inode *dir, struct dentry *entry,
  */
 static int fuse_create_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct inode *inode;
@@ -513,7 +513,7 @@ static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 	if (fc->no_create)
 		goto mknod;
 
-	err = fuse_create_open(dir, entry, file, flags, mode, opened);
+	err = fuse_create_open(dir, entry, file, flags, mode);
 	if (err == -ENOSYS) {
 		fc->no_create = 1;
 		goto mknod;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 59f695e96d63..15e2a8a3b917 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -580,7 +580,7 @@ static int gfs2_initxattrs(struct inode *inode, const struct xattr *xattr_array,
 static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 			     struct file *file,
 			     umode_t mode, dev_t dev, const char *symname,
-			     unsigned int size, int excl, int *opened)
+			     unsigned int size, int excl)
 {
 	const struct qstr *name = &dentry->d_name;
 	struct posix_acl *default_acl, *acl;
@@ -822,7 +822,7 @@ fail:
 static int gfs2_create(struct inode *dir, struct dentry *dentry,
 		       umode_t mode, bool excl)
 {
-	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /**
@@ -830,14 +830,13 @@ static int gfs2_create(struct inode *dir, struct dentry *dentry,
  * @dir: The directory inode
  * @dentry: The dentry of the new inode
  * @file: File to be opened
- * @opened: atomic_open flags
  *
  *
  * Returns: errno
  */
 
 static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
-				    struct file *file, int *opened)
+				    struct file *file)
 {
 	struct inode *inode;
 	struct dentry *d;
@@ -879,7 +878,7 @@ static struct dentry *__gfs2_lookup(struct inode *dir, struct dentry *dentry,
 static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
 				  unsigned flags)
 {
-	return __gfs2_lookup(dir, dentry, NULL, NULL);
+	return __gfs2_lookup(dir, dentry, NULL);
 }
 
 /**
@@ -1189,7 +1188,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 	if (size >= gfs2_max_stuffed_size(GFS2_I(dir)))
 		return -ENAMETOOLONG;
 
-	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFLNK | S_IRWXUGO, 0, symname, size, 0);
 }
 
 /**
@@ -1204,7 +1203,7 @@ static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
 static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 {
 	unsigned dsize = gfs2_max_stuffed_size(GFS2_I(dir));
-	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, S_IFDIR | mode, 0, NULL, dsize, 0);
 }
 
 /**
@@ -1219,7 +1218,7 @@ static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
 		      dev_t dev)
 {
-	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0, NULL);
+	return gfs2_create_inode(dir, dentry, NULL, mode, dev, NULL, 0, 0);
 }
 
 /**
@@ -1244,7 +1243,7 @@ static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 	if (!d_in_lookup(dentry))
 		goto skip_lookup;
 
-	d = __gfs2_lookup(dir, dentry, file, opened);
+	d = __gfs2_lookup(dir, dentry, file);
 	if (IS_ERR(d))
 		return PTR_ERR(d);
 	if (d != NULL)
@@ -1262,7 +1261,7 @@ skip_lookup:
 	if (!(flags & O_CREAT))
 		return -ENOENT;
 
-	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl, opened);
+	return gfs2_create_inode(dir, dentry, file, S_IFREG | mode, 0, NULL, 0, excl);
 }
 
 /*
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 22176a3818d5..71ae3cc3e53a 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1434,8 +1434,7 @@ static int do_open(struct inode *inode, struct file *filp)
 
 static int nfs_finish_open(struct nfs_open_context *ctx,
 			   struct dentry *dentry,
-			   struct file *file, unsigned open_flags,
-			   int *opened)
+			   struct file *file, unsigned open_flags)
 {
 	int err;
 
@@ -1549,7 +1548,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags, opened);
+	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags);
 	trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
 	put_nfs_open_context(ctx);
 out:
-- 
cgit v1.2.3


From 44907d79002466049fdbb8ef15730d185e0808b4 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 13:32:02 -0400
Subject: get rid of 'opened' argument of ->atomic_open() - part 3

now it can be done...

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/9p/vfs_inode.c      | 3 +--
 fs/9p/vfs_inode_dotl.c | 3 +--
 fs/bad_inode.c         | 2 +-
 fs/ceph/file.c         | 3 +--
 fs/ceph/super.h        | 3 +--
 fs/cifs/cifsfs.h       | 3 +--
 fs/cifs/dir.c          | 3 +--
 fs/fuse/dir.c          | 2 +-
 fs/gfs2/inode.c        | 3 +--
 fs/namei.c             | 3 +--
 fs/nfs/dir.c           | 2 +-
 fs/nfs/nfs4_fs.h       | 2 +-
 include/linux/fs.h     | 2 +-
 13 files changed, 13 insertions(+), 21 deletions(-)

diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index 7b6ff3275d9c..85ff859d3af5 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -859,8 +859,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 
 static int
 v9fs_vfs_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	int err;
 	u32 perm;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index c6939b7cb18c..4823e1c46999 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -241,8 +241,7 @@ v9fs_vfs_create_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 
 static int
 v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
-			  struct file *file, unsigned flags, umode_t omode,
-			  int *opened)
+			  struct file *file, unsigned flags, umode_t omode)
 {
 	int err = 0;
 	kgid_t gid;
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 125e8bbd22a2..8035d2a44561 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -134,7 +134,7 @@ static int bad_inode_update_time(struct inode *inode, struct timespec64 *time,
 
 static int bad_inode_atomic_open(struct inode *inode, struct dentry *dentry,
 				 struct file *file, unsigned int open_flag,
-				 umode_t create_mode, int *opened)
+				 umode_t create_mode)
 {
 	return -EIO;
 }
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 38b28cb2fac1..e2679e8a2535 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -429,8 +429,7 @@ out:
  * file or symlink, return 1 so the VFS can retry.
  */
 int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-		     struct file *file, unsigned flags, umode_t mode,
-		     int *opened)
+		     struct file *file, unsigned flags, umode_t mode)
 {
 	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
 	struct ceph_mds_client *mdsc = fsc->mdsc;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index a7077a0c989f..971328b99ede 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -1025,8 +1025,7 @@ extern const struct file_operations ceph_file_fops;
 extern int ceph_renew_caps(struct inode *inode);
 extern int ceph_open(struct inode *inode, struct file *file);
 extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
-			    struct file *file, unsigned flags, umode_t mode,
-			    int *opened);
+			    struct file *file, unsigned flags, umode_t mode);
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index 5f0231803431..f3a78efc3109 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -65,8 +65,7 @@ extern struct inode *cifs_root_iget(struct super_block *);
 extern int cifs_create(struct inode *, struct dentry *, umode_t,
 		       bool excl);
 extern int cifs_atomic_open(struct inode *, struct dentry *,
-			    struct file *, unsigned, umode_t,
-			    int *);
+			    struct file *, unsigned, umode_t);
 extern struct dentry *cifs_lookup(struct inode *, struct dentry *,
 				  unsigned int);
 extern int cifs_unlink(struct inode *dir, struct dentry *dentry);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 891bfd62e67a..3713d22b95a7 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -465,8 +465,7 @@ out_err:
 
 int
 cifs_atomic_open(struct inode *inode, struct dentry *direntry,
-		 struct file *file, unsigned oflags, umode_t mode,
-		 int *opened)
+		 struct file *file, unsigned oflags, umode_t mode)
 {
 	int rc;
 	unsigned int xid;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index b8d7e9d423c8..c979329311c8 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -489,7 +489,7 @@ out_err:
 static int fuse_mknod(struct inode *, struct dentry *, umode_t, dev_t);
 static int fuse_atomic_open(struct inode *dir, struct dentry *entry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	int err;
 	struct fuse_conn *fc = get_fuse_conn(dir);
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 15e2a8a3b917..648f0ca1ad57 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1228,14 +1228,13 @@ static int gfs2_mknod(struct inode *dir, struct dentry *dentry, umode_t mode,
  * @file: The proposed new struct file
  * @flags: open flags
  * @mode: File mode
- * @opened: Flag to say whether the file has been opened or not
  *
  * Returns: error code or 0 for success
  */
 
 static int gfs2_atomic_open(struct inode *dir, struct dentry *dentry,
 			    struct file *file, unsigned flags,
-			    umode_t mode, int *opened)
+			    umode_t mode)
 {
 	struct dentry *d;
 	bool excl = !!(flags & O_EXCL);
diff --git a/fs/namei.c b/fs/namei.c
index 117b118853f2..1da272bf8ed3 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3052,8 +3052,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 	file->f_path.dentry = DENTRY_NOT_SET;
 	file->f_path.mnt = nd->path.mnt;
 	error = dir->i_op->atomic_open(dir, dentry, file,
-				       open_to_namei_flags(open_flag),
-				       mode, opened);
+				       open_to_namei_flags(open_flag), mode);
 	d_lookup_done(dentry);
 	if (!error) {
 		/*
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 71ae3cc3e53a..f447b1a24350 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1451,7 +1451,7 @@ out:
 
 int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		    struct file *file, unsigned open_flags,
-		    umode_t mode, int *opened)
+		    umode_t mode)
 {
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
 	struct nfs_open_context *ctx;
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 137e18abb7e7..51beb6e38c90 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -258,7 +258,7 @@ extern const struct dentry_operations nfs4_dentry_operations;
 
 /* dir.c */
 int nfs_atomic_open(struct inode *, struct dentry *, struct file *,
-		    unsigned, umode_t, int *);
+		    unsigned, umode_t);
 
 /* super.c */
 extern struct file_system_type nfs4_fs_type;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 70be3e4c26ac..c25896b30e9f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1781,7 +1781,7 @@ struct inode_operations {
 	int (*update_time)(struct inode *, struct timespec64 *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 			   struct file *, unsigned open_flag,
-			   umode_t create_mode, int *opened);
+			   umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 	int (*set_acl)(struct inode *, struct posix_acl *, int);
 } ____cacheline_aligned;
-- 
cgit v1.2.3


From 3ec2eef116e900099edc6d31a1a0423166e2906d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 13:43:47 -0400
Subject: get rid of 'opened' in path_openat() and the helpers downstream

unused now

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 22 ++++++++--------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 1da272bf8ed3..6def3e148f90 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3036,8 +3036,7 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m
 static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 			struct path *path, struct file *file,
 			const struct open_flags *op,
-			int open_flag, umode_t mode,
-			int *opened)
+			int open_flag, umode_t mode)
 {
 	struct dentry *const DENTRY_NOT_SET = (void *) -1UL;
 	struct inode *dir =  nd->path.dentry->d_inode;
@@ -3105,14 +3104,11 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
  * specified then a negative dentry may be returned.
  *
  * An error code is returned otherwise.
- *
- * FILE_CREATE will be set in @*opened if the dentry was created and will be
- * cleared otherwise prior to returning.
  */
 static int lookup_open(struct nameidata *nd, struct path *path,
 			struct file *file,
 			const struct open_flags *op,
-			bool got_write, int *opened)
+			bool got_write)
 {
 	struct dentry *dir = nd->path.dentry;
 	struct inode *dir_inode = dir->d_inode;
@@ -3187,7 +3183,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 
 	if (dir_inode->i_op->atomic_open) {
 		error = atomic_open(nd, dentry, path, file, op, open_flag,
-				    mode, opened);
+				    mode);
 		if (unlikely(error == -ENOENT) && create_error)
 			error = create_error;
 		return error;
@@ -3240,8 +3236,7 @@ out_dput:
  * Handle the last step of open()
  */
 static int do_last(struct nameidata *nd,
-		   struct file *file, const struct open_flags *op,
-		   int *opened)
+		   struct file *file, const struct open_flags *op)
 {
 	struct dentry *dir = nd->path.dentry;
 	int open_flag = op->open_flag;
@@ -3307,7 +3302,7 @@ static int do_last(struct nameidata *nd,
 		inode_lock(dir->d_inode);
 	else
 		inode_lock_shared(dir->d_inode);
-	error = lookup_open(nd, &path, file, op, got_write, opened);
+	error = lookup_open(nd, &path, file, op, got_write);
 	if (open_flag & O_CREAT)
 		inode_unlock(dir->d_inode);
 	else
@@ -3452,7 +3447,7 @@ EXPORT_SYMBOL(vfs_tmpfile);
 
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
-		struct file *file, int *opened)
+		struct file *file)
 {
 	struct dentry *child;
 	struct path path;
@@ -3499,7 +3494,6 @@ static struct file *path_openat(struct nameidata *nd,
 {
 	const char *s;
 	struct file *file;
-	int opened = 0;
 	int error;
 
 	file = alloc_empty_file(op->open_flag, current_cred());
@@ -3507,7 +3501,7 @@ static struct file *path_openat(struct nameidata *nd,
 		return file;
 
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
-		error = do_tmpfile(nd, flags, op, file, &opened);
+		error = do_tmpfile(nd, flags, op, file);
 		goto out2;
 	}
 
@@ -3522,7 +3516,7 @@ static struct file *path_openat(struct nameidata *nd,
 		return ERR_CAST(s);
 	}
 	while (!(error = link_path_walk(s, nd)) &&
-		(error = do_last(nd, file, op, &opened)) > 0) {
+		(error = do_last(nd, file, op)) > 0) {
 		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
 		s = trailing_symlink(nd);
 		if (IS_ERR(s)) {
-- 
cgit v1.2.3


From 64e1ac4d46f9f5d8284aefb97e1b550dbb26abe8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 19:17:52 -0400
Subject: ->atomic_open(): return 0 in all success cases

FMODE_OPENED can be used to distingusish "successful open" from the
"called finish_no_open(), do it yourself" cases.  Since finish_no_open()
has been adjusted, no changes in the instances were actually needed.
The caller has been adjusted.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 30 +++++++++++++++---------------
 fs/open.c  |  4 ++--
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 6def3e148f90..e213e7bf028a 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3054,21 +3054,21 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 				       open_to_namei_flags(open_flag), mode);
 	d_lookup_done(dentry);
 	if (!error) {
-		/*
-		 * We didn't have the inode before the open, so check open
-		 * permission here.
-		 */
-		int acc_mode = op->acc_mode;
-		if (file->f_mode & FMODE_CREATED) {
-			WARN_ON(!(open_flag & O_CREAT));
-			fsnotify_create(dir, dentry);
-			acc_mode = 0;
-		}
-		error = may_open(&file->f_path, acc_mode, open_flag);
-		if (WARN_ON(error > 0))
-			error = -EINVAL;
-	} else if (error > 0) {
-		if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
+		if (file->f_mode & FMODE_OPENED) {
+			/*
+			 * We didn't have the inode before the open, so check open
+			 * permission here.
+			 */
+			int acc_mode = op->acc_mode;
+			if (file->f_mode & FMODE_CREATED) {
+				WARN_ON(!(open_flag & O_CREAT));
+				fsnotify_create(dir, dentry);
+				acc_mode = 0;
+			}
+			error = may_open(&file->f_path, acc_mode, open_flag);
+			if (WARN_ON(error > 0))
+				error = -EINVAL;
+		} else if (WARN_ON(file->f_path.dentry == DENTRY_NOT_SET)) {
 			error = -EIO;
 		} else {
 			if (file->f_path.dentry) {
diff --git a/fs/open.c b/fs/open.c
index dbaac9efc7fc..d98e19239bb7 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -863,13 +863,13 @@ EXPORT_SYMBOL(finish_open);
  * NB: unlike finish_open() this function does consume the dentry reference and
  * the caller need not dput() it.
  *
- * Returns "1" which must be the return value of ->atomic_open() after having
+ * Returns "0" which must be the return value of ->atomic_open() after having
  * called this function.
  */
 int finish_no_open(struct file *file, struct dentry *dentry)
 {
 	file->f_path.dentry = dentry;
-	return 1;
+	return 0;
 }
 EXPORT_SYMBOL(finish_no_open);
 
-- 
cgit v1.2.3


From 6c9b1de172bdd0450d56e2cb3b2da5fc1833619e Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 19:20:08 -0400
Subject: document ->atomic_open() changes

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/Locking |  2 +-
 Documentation/filesystems/porting |  8 ++++++++
 Documentation/filesystems/vfs.txt | 18 ++++++++++--------
 3 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 2c391338c675..04c867981375 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -64,7 +64,7 @@ prototypes:
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 				struct file *, unsigned open_flag,
-				umode_t create_mode, int *opened);
+				umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 
 locking rules:
diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index 17bb4dc28fae..c68ea9294b5f 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -602,3 +602,11 @@ in your dentry operations instead.
 	dentry separately, and it now has request_mask and query_flags arguments
 	to specify the fields and sync type requested by statx.  Filesystems not
 	supporting any statx-specific features may ignore the new arguments.
+--
+[mandatory]
+	->atomic_open() calling conventions have changed.  Gone is int *opened,
+	along with FILE_OPENED/FILE_CREATED.  In place of those we have
+	FMODE_OPENED/FMODE_CREATED, set in file->f_mode.  Additionally, return
+	value for 'called finish_no_open(), open it yourself' case has become
+	0, not 1.  Since finish_no_open() itself is returning 0 now, that part
+	does not need any changes in ->atomic_open() instances.
diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt
index 829a7b7857a4..d564cc44397e 100644
--- a/Documentation/filesystems/vfs.txt
+++ b/Documentation/filesystems/vfs.txt
@@ -386,7 +386,7 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	void (*update_time)(struct inode *, struct timespec *, int);
 	int (*atomic_open)(struct inode *, struct dentry *, struct file *,
-			unsigned open_flag, umode_t create_mode, int *opened);
+			unsigned open_flag, umode_t create_mode);
 	int (*tmpfile) (struct inode *, struct dentry *, umode_t);
 };
 
@@ -496,13 +496,15 @@ otherwise noted.
 
   atomic_open: called on the last component of an open.  Using this optional
   	method the filesystem can look up, possibly create and open the file in
-  	one atomic operation.  If it cannot perform this (e.g. the file type
-  	turned out to be wrong) it may signal this by returning 1 instead of
-	usual 0 or -ve .  This method is only called if the last component is
-	negative or needs lookup.  Cached positive dentries are still handled by
-	f_op->open().  If the file was created, the FILE_CREATED flag should be
-	set in "opened".  In case of O_EXCL the method must only succeed if the
-	file didn't exist and hence FILE_CREATED shall always be set on success.
+	one atomic operation.  If it wants to leave actual opening to the
+	caller (e.g. if the file turned out to be a symlink, device, or just
+	something filesystem won't do atomic open for), it may signal this by
+	returning finish_no_open(file, dentry).  This method is only called if
+	the last component is negative or needs lookup.  Cached positive dentries
+	are still handled by f_op->open().  If the file was created,
+	FMODE_CREATED flag should be set in file->f_mode.  In case of O_EXCL
+	the method must only succeed if the file didn't exist and hence FMODE_CREATED
+	shall always be set on success.
 
   tmpfile: called in the end of O_TMPFILE open().  Optional, equivalent to
 	atomically creating, opening and unlinking a file in given directory.
-- 
cgit v1.2.3


From 00a07c1591a3fb3d71f7083361eab4a2444938a3 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 19:30:20 -0400
Subject: switch atomic_open() and lookup_open() to returning 0 in all success
 cases

caller can tell "opened" from "open it yourself" by looking at ->f_mode.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index e213e7bf028a..8311dce1c649 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3027,9 +3027,9 @@ static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t m
  * Returns 0 if successful.  The file will have been created and attached to
  * @file by the filesystem calling finish_open().
  *
- * Returns 1 if the file was looked up only or didn't need creating.  The
- * caller will need to perform the open themselves.  @path will have been
- * updated to point to the new dentry.  This may be negative.
+ * If the file was looked up only or didn't need creating, FMODE_OPENED won't
+ * be set.  The caller will need to perform the open themselves.  @path will
+ * have been updated to point to the new dentry.  This may be negative.
  *
  * Returns an error code otherwise.
  */
@@ -3082,7 +3082,7 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 			} else {
 				path->dentry = dentry;
 				path->mnt = nd->path.mnt;
-				return 1;
+				return 0;
 			}
 		}
 	}
@@ -3093,17 +3093,17 @@ static int atomic_open(struct nameidata *nd, struct dentry *dentry,
 /*
  * Look up and maybe create and open the last component.
  *
- * Must be called with i_mutex held on parent.
- *
- * Returns 0 if the file was successfully atomically created (if necessary) and
- * opened.  In this case the file will be returned attached to @file.
+ * Must be called with parent locked (exclusive in O_CREAT case).
  *
- * Returns 1 if the file was not completely opened at this time, though lookups
- * and creations will have been performed and the dentry returned in @path will
- * be positive upon return if O_CREAT was specified.  If O_CREAT wasn't
- * specified then a negative dentry may be returned.
+ * Returns 0 on success, that is, if
+ *  the file was successfully atomically created (if necessary) and opened, or
+ *  the file was not completely opened at this time, though lookups and
+ *  creations were performed.
+ * These case are distinguished by presence of FMODE_OPENED on file->f_mode.
+ * In the latter case dentry returned in @path might be negative if O_CREAT
+ * hadn't been specified.
  *
- * An error code is returned otherwise.
+ * An error code is returned on failure.
  */
 static int lookup_open(struct nameidata *nd, struct path *path,
 			struct file *file,
@@ -3225,7 +3225,7 @@ no_open:
 out_no_open:
 	path->dentry = dentry;
 	path->mnt = nd->path.mnt;
-	return 1;
+	return 0;
 
 out_dput:
 	dput(dentry);
@@ -3308,10 +3308,10 @@ static int do_last(struct nameidata *nd,
 	else
 		inode_unlock_shared(dir->d_inode);
 
-	if (error <= 0) {
-		if (error)
-			goto out;
+	if (error)
+		goto out;
 
+	if (file->f_mode & FMODE_OPENED) {
 		if ((file->f_mode & FMODE_CREATED) ||
 		    !S_ISREG(file_inode(file)->i_mode))
 			will_truncate = false;
-- 
cgit v1.2.3


From dbae8f2ca2f0586f4b80201c78ff0aed2a012ab5 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 8 Jun 2018 17:51:47 -0400
Subject: kill FILE_{CREATED,OPENED}

no users left

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/fs.h | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index c25896b30e9f..bd904c496878 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2436,10 +2436,6 @@ extern struct filename *getname(const char __user *);
 extern struct filename *getname_kernel(const char *);
 extern void putname(struct filename *name);
 
-enum {
-	FILE_CREATED = 1,
-	FILE_OPENED = 2
-};
 extern int finish_open(struct file *file, struct dentry *dentry,
 			int (*open)(struct inode *, struct file *));
 extern int finish_no_open(struct file *file, struct dentry *dentry);
-- 
cgit v1.2.3


From d93aa9d82aea80b80f225dbf9c7986df444d8106 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jun 2018 09:40:05 -0400
Subject: new wrapper: alloc_file_pseudo()

takes inode, vfsmount, name, O_... flags and file_operations and
either returns a new struct file (in which case inode reference we
held is consumed) or returns ERR_PTR(), in which case no refcounts
are altered.

converted aio_private_file() and sock_alloc_file() to it

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/aio.c             | 20 ++++----------------
 fs/file_table.c      | 27 +++++++++++++++++++++++++++
 include/linux/file.h |  3 +++
 net/socket.c         | 28 +++++-----------------------
 4 files changed, 39 insertions(+), 39 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 9eea53887d6c..c3a8bac16374 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -215,9 +215,7 @@ static const struct address_space_operations aio_ctx_aops;
 
 static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 {
-	struct qstr this = QSTR_INIT("[aio]", 5);
 	struct file *file;
-	struct path path;
 	struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
@@ -226,27 +224,17 @@ static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages)
 	inode->i_mapping->private_data = ctx;
 	inode->i_size = PAGE_SIZE * nr_pages;
 
-	path.dentry = d_alloc_pseudo(aio_mnt->mnt_sb, &this);
-	if (!path.dentry) {
-		iput(inode);
-		return ERR_PTR(-ENOMEM);
-	}
-	path.mnt = mntget(aio_mnt);
-
-	d_instantiate(path.dentry, inode);
-	file = alloc_file(&path, O_RDWR, &aio_ring_fops);
+	file = alloc_file_pseudo(inode, aio_mnt, "[aio]",
+				O_RDWR, &aio_ring_fops);
 	if (IS_ERR(file))
-		path_put(&path);
+		iput(inode);
 	return file;
 }
 
 static struct dentry *aio_mount(struct file_system_type *fs_type,
 				int flags, const char *dev_name, void *data)
 {
-	static const struct dentry_operations ops = {
-		.d_dname	= simple_dname,
-	};
-	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, &ops,
+	struct dentry *root = mount_pseudo(fs_type, "aio:", NULL, NULL,
 					   AIO_RING_MAGIC);
 
 	if (!IS_ERR(root))
diff --git a/fs/file_table.c b/fs/file_table.c
index 9b70ed2bbc4e..6b3723909342 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -184,6 +184,33 @@ struct file *alloc_file(const struct path *path, int flags,
 }
 EXPORT_SYMBOL(alloc_file);
 
+struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
+				const char *name, int flags,
+				const struct file_operations *fops)
+{
+	static const struct dentry_operations anon_ops = {
+		.d_dname = simple_dname
+	};
+	struct qstr this = QSTR_INIT(name, strlen(name));
+	struct path path;
+	struct file *file;
+
+	path.dentry = d_alloc_pseudo(mnt->mnt_sb, &this);
+	if (!path.dentry)
+		return ERR_PTR(-ENOMEM);
+	if (!mnt->mnt_sb->s_d_op)
+		d_set_d_op(path.dentry, &anon_ops);
+	path.mnt = mntget(mnt);
+	d_instantiate(path.dentry, inode);
+	file = alloc_file(&path, flags, fops);
+	if (IS_ERR(file)) {
+		ihold(inode);
+		path_put(&path);
+	}
+	return file;
+}
+EXPORT_SYMBOL(alloc_file_pseudo);
+
 /* the real guts of fput() - releasing the last reference to file
  */
 static void __fput(struct file *file)
diff --git a/include/linux/file.h b/include/linux/file.h
index aed45d69811e..5b25388f2f79 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -17,9 +17,12 @@ extern void fput(struct file *);
 struct file_operations;
 struct vfsmount;
 struct dentry;
+struct inode;
 struct path;
 extern struct file *alloc_file(const struct path *, int flags,
 	const struct file_operations *fop);
+extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
+	const char *, int flags, const struct file_operations *);
 
 static inline void fput_light(struct file *file, int fput_needed)
 {
diff --git a/net/socket.c b/net/socket.c
index 2cdbe8f71b7f..4cf3568caf9f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -391,33 +391,15 @@ static struct file_system_type sock_fs_type = {
 
 struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname)
 {
-	struct qstr name = { .name = "" };
-	struct path path;
 	struct file *file;
 
-	if (dname) {
-		name.name = dname;
-		name.len = strlen(name.name);
-	} else if (sock->sk) {
-		name.name = sock->sk->sk_prot_creator->name;
-		name.len = strlen(name.name);
-	}
-	path.dentry = d_alloc_pseudo(sock_mnt->mnt_sb, &name);
-	if (unlikely(!path.dentry)) {
-		sock_release(sock);
-		return ERR_PTR(-ENOMEM);
-	}
-	path.mnt = mntget(sock_mnt);
-
-	d_instantiate(path.dentry, SOCK_INODE(sock));
+	if (!dname)
+		dname = sock->sk ? sock->sk->sk_prot_creator->name : "";
 
-	file = alloc_file(&path, O_RDWR | (flags & O_NONBLOCK),
-		  &socket_file_ops);
+	file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname,
+				O_RDWR | (flags & O_NONBLOCK),
+				&socket_file_ops);
 	if (IS_ERR(file)) {
-		/* drop dentry, keep inode for a bit */
-		ihold(d_inode(path.dentry));
-		path_put(&path);
-		/* ... and now kill it properly */
 		sock_release(sock);
 		return file;
 	}
-- 
cgit v1.2.3


From dac2d1f6cbfe3f63867a601d2431b7749d9bdbcf Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jun 2018 09:27:41 -0400
Subject: __shmem_file_setup(): reorder allocations

grab inode and reserve memory first.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 mm/shmem.c | 43 ++++++++++++++++++++-----------------------
 1 file changed, 20 insertions(+), 23 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 84844e52bf24..35aabed7d64d 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3918,40 +3918,37 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 	if (shmem_acct_size(flags, size))
 		return ERR_PTR(-ENOMEM);
 
-	res = ERR_PTR(-ENOMEM);
+	sb = mnt->mnt_sb;
+	inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags);
+	if (unlikely(!inode)) {
+		shmem_unacct_size(flags, size);
+		return ERR_PTR(-ENOSPC);
+	}
+	inode->i_flags |= i_flags;
+	inode->i_size = size;
+	clear_nlink(inode);	/* It is unlinked */
+	res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
+	if (IS_ERR(res)) {
+		iput(inode);
+		return res;
+	}
+
 	this.name = name;
 	this.len = strlen(name);
 	this.hash = 0; /* will go */
-	sb = mnt->mnt_sb;
 	path.mnt = mntget(mnt);
 	path.dentry = d_alloc_pseudo(sb, &this);
-	if (!path.dentry)
-		goto put_memory;
+	if (!path.dentry) {
+		iput(inode);
+		return ERR_PTR(-ENOMEM);
+	}
 	d_set_d_op(path.dentry, &anon_ops);
 
-	res = ERR_PTR(-ENOSPC);
-	inode = shmem_get_inode(sb, NULL, S_IFREG | 0777, 0, flags);
-	if (!inode)
-		goto put_memory;
-
-	inode->i_flags |= i_flags;
 	d_instantiate(path.dentry, inode);
-	inode->i_size = size;
-	clear_nlink(inode);	/* It is unlinked */
-	res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
-	if (IS_ERR(res))
-		goto put_path;
 
 	res = alloc_file(&path, O_RDWR, &shmem_file_operations);
 	if (IS_ERR(res))
-		goto put_path;
-
-	return res;
-
-put_memory:
-	shmem_unacct_size(flags, size);
-put_path:
-	path_put(&path);
+		path_put(&path);
 	return res;
 }
 
-- 
cgit v1.2.3


From 93dec2da7b2349f0b294bbb23244cac135f13b79 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 8 Jul 2018 23:02:03 -0400
Subject: ... and switch shmem_file_setup() to alloc_file_pseudo()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 mm/shmem.c | 37 +++++++------------------------------
 1 file changed, 7 insertions(+), 30 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 35aabed7d64d..d7e984141be5 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3896,18 +3896,11 @@ EXPORT_SYMBOL_GPL(shmem_truncate_range);
 
 /* common code */
 
-static const struct dentry_operations anon_ops = {
-	.d_dname = simple_dname
-};
-
 static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, loff_t size,
 				       unsigned long flags, unsigned int i_flags)
 {
-	struct file *res;
 	struct inode *inode;
-	struct path path;
-	struct super_block *sb;
-	struct qstr this;
+	struct file *res;
 
 	if (IS_ERR(mnt))
 		return ERR_CAST(mnt);
@@ -3918,8 +3911,8 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 	if (shmem_acct_size(flags, size))
 		return ERR_PTR(-ENOMEM);
 
-	sb = mnt->mnt_sb;
-	inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags);
+	inode = shmem_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0,
+				flags);
 	if (unlikely(!inode)) {
 		shmem_unacct_size(flags, size);
 		return ERR_PTR(-ENOSPC);
@@ -3928,27 +3921,11 @@ static struct file *__shmem_file_setup(struct vfsmount *mnt, const char *name, l
 	inode->i_size = size;
 	clear_nlink(inode);	/* It is unlinked */
 	res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
-	if (IS_ERR(res)) {
-		iput(inode);
-		return res;
-	}
-
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0; /* will go */
-	path.mnt = mntget(mnt);
-	path.dentry = d_alloc_pseudo(sb, &this);
-	if (!path.dentry) {
-		iput(inode);
-		return ERR_PTR(-ENOMEM);
-	}
-	d_set_d_op(path.dentry, &anon_ops);
-
-	d_instantiate(path.dentry, inode);
-
-	res = alloc_file(&path, O_RDWR, &shmem_file_operations);
+	if (!IS_ERR(res))
+		res = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+				&shmem_file_operations);
 	if (IS_ERR(res))
-		path_put(&path);
+		iput(inode);
 	return res;
 }
 
-- 
cgit v1.2.3


From 908f7ca1731142e49e802b0277e94853cd772a8d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jun 2018 09:45:56 -0400
Subject: cxl_getfile(): switch to alloc_file_pseudo()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/misc/cxl/api.c | 21 ++++-----------------
 1 file changed, 4 insertions(+), 17 deletions(-)

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 0b5cb6cf91a0..8fd5ec4d6042 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -67,10 +67,8 @@ static struct file *cxl_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	/* strongly inspired by anon_inode_getfile() */
@@ -91,22 +89,11 @@ static struct file *cxl_getfile(const char *name,
 		goto err_fs;
 	}
 
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(cxl_vfs_mount->mnt_sb, &this);
-	if (!path.dentry)
+	file = alloc_file_pseudo(inode, cxl_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
+	if (IS_ERR(file))
 		goto err_inode;
 
-	path.mnt = mntget(cxl_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops);
-	if (IS_ERR(file)) {
-		path_put(&path);
-		goto err_fs;
-	}
 	file->private_data = priv;
 
 	return file;
-- 
cgit v1.2.3


From 118f4868616b2aef18ed93461b48f83c3a6bcc7f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 17 Jun 2018 12:42:49 -0400
Subject: ocxlflash_getfile(): switch to alloc_file_pseudo()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/scsi/cxlflash/ocxl_hw.c | 23 ++++-------------------
 1 file changed, 4 insertions(+), 19 deletions(-)

diff --git a/drivers/scsi/cxlflash/ocxl_hw.c b/drivers/scsi/cxlflash/ocxl_hw.c
index 99bb393a8a34..a43d44e7e7dd 100644
--- a/drivers/scsi/cxlflash/ocxl_hw.c
+++ b/drivers/scsi/cxlflash/ocxl_hw.c
@@ -88,10 +88,8 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 				      const struct file_operations *fops,
 				      void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
-	struct inode *inode = NULL;
+	struct inode *inode;
 	int rc;
 
 	if (fops->owner && !try_module_get(fops->owner)) {
@@ -116,26 +114,13 @@ static struct file *ocxlflash_getfile(struct device *dev, const char *name,
 		goto err3;
 	}
 
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(ocxlflash_vfs_mount->mnt_sb, &this);
-	if (!path.dentry) {
-		dev_err(dev, "%s: d_alloc_pseudo failed\n", __func__);
-		rc = -ENOMEM;
-		goto err4;
-	}
-
-	path.mnt = mntget(ocxlflash_vfs_mount);
-	d_instantiate(path.dentry, inode);
-
-	file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops);
+	file = alloc_file_pseudo(inode, ocxlflash_vfs_mount, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file)) {
 		rc = PTR_ERR(file);
 		dev_err(dev, "%s: alloc_file failed rc=%d\n",
 			__func__, rc);
-		path_put(&path);
-		goto err3;
+		goto err4;
 	}
 
 	file->private_data = priv;
-- 
cgit v1.2.3


From e68375c850b0d5699a27bb598317a3274913824b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jun 2018 09:50:46 -0400
Subject: hugetlb_file_setup(): switch to alloc_file_pseudo()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/hugetlbfs/inode.c | 53 ++++++++++++++++------------------------------------
 1 file changed, 16 insertions(+), 37 deletions(-)

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 71aed47422e2..87605c73361b 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1308,10 +1308,6 @@ static int get_hstate_idx(int page_size_log)
 	return h - hstates;
 }
 
-static const struct dentry_operations anon_ops = {
-	.d_dname = simple_dname
-};
-
 /*
  * Note that size should be aligned to proper hugepage size in caller side,
  * otherwise hugetlb_reserve_pages reserves one less hugepages than intended.
@@ -1320,19 +1316,18 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 				vm_flags_t acctflag, struct user_struct **user,
 				int creat_flags, int page_size_log)
 {
-	struct file *file = ERR_PTR(-ENOMEM);
 	struct inode *inode;
-	struct path path;
-	struct super_block *sb;
-	struct qstr quick_string;
+	struct vfsmount *mnt;
 	int hstate_idx;
+	struct file *file;
 
 	hstate_idx = get_hstate_idx(page_size_log);
 	if (hstate_idx < 0)
 		return ERR_PTR(-ENODEV);
 
 	*user = NULL;
-	if (!hugetlbfs_vfsmount[hstate_idx])
+	mnt = hugetlbfs_vfsmount[hstate_idx];
+	if (!mnt)
 		return ERR_PTR(-ENOENT);
 
 	if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) {
@@ -1348,44 +1343,28 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 		}
 	}
 
-	sb = hugetlbfs_vfsmount[hstate_idx]->mnt_sb;
-	quick_string.name = name;
-	quick_string.len = strlen(quick_string.name);
-	quick_string.hash = 0;
-	path.dentry = d_alloc_pseudo(sb, &quick_string);
-	if (!path.dentry)
-		goto out_shm_unlock;
-
-	d_set_d_op(path.dentry, &anon_ops);
-	path.mnt = mntget(hugetlbfs_vfsmount[hstate_idx]);
 	file = ERR_PTR(-ENOSPC);
-	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
+	inode = hugetlbfs_get_inode(mnt->mnt_sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
-		goto out_dentry;
+		goto out;
 	if (creat_flags == HUGETLB_SHMFS_INODE)
 		inode->i_flags |= S_PRIVATE;
 
-	file = ERR_PTR(-ENOMEM);
-	if (hugetlb_reserve_pages(inode, 0,
-			size >> huge_page_shift(hstate_inode(inode)), NULL,
-			acctflag))
-		goto out_inode;
-
-	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	file = alloc_file(&path, O_RDWR, &hugetlbfs_file_operations);
-	if (IS_ERR(file))
-		goto out_dentry; /* inode is already attached */
-
-	return file;
+	if (hugetlb_reserve_pages(inode, 0,
+			size >> huge_page_shift(hstate_inode(inode)), NULL,
+			acctflag))
+		file = ERR_PTR(-ENOMEM);
+	else
+		file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
+					&hugetlbfs_file_operations);
+	if (!IS_ERR(file))
+		return file;
 
-out_inode:
 	iput(inode);
-out_dentry:
-	path_put(&path);
-out_shm_unlock:
+out:
 	if (*user) {
 		user_shm_unlock(size, *user);
 		*user = NULL;
-- 
cgit v1.2.3


From 52c91f8b3b1f5f69e47f7f65f76066d0c940b191 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jun 2018 09:58:23 -0400
Subject: anon_inode_getfile(): switch to alloc_file_pseudo()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/anon_inodes.c | 29 ++++++-----------------------
 1 file changed, 6 insertions(+), 23 deletions(-)

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index 6b235ab1df6c..91262c34b797 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -71,8 +71,6 @@ struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags)
 {
-	struct qstr this;
-	struct path path;
 	struct file *file;
 
 	if (IS_ERR(anon_inode_inode))
@@ -81,39 +79,24 @@ struct file *anon_inode_getfile(const char *name,
 	if (fops->owner && !try_module_get(fops->owner))
 		return ERR_PTR(-ENOENT);
 
-	/*
-	 * Link the inode to a directory entry by creating a unique name
-	 * using the inode sequence number.
-	 */
-	file = ERR_PTR(-ENOMEM);
-	this.name = name;
-	this.len = strlen(name);
-	this.hash = 0;
-	path.dentry = d_alloc_pseudo(anon_inode_mnt->mnt_sb, &this);
-	if (!path.dentry)
-		goto err_module;
-
-	path.mnt = mntget(anon_inode_mnt);
 	/*
 	 * We know the anon_inode inode count is always greater than zero,
 	 * so ihold() is safe.
 	 */
 	ihold(anon_inode_inode);
-
-	d_instantiate(path.dentry, anon_inode_inode);
-
-	file = alloc_file(&path, flags & (O_ACCMODE | O_NONBLOCK), fops);
+	file = alloc_file_pseudo(anon_inode_inode, anon_inode_mnt, name,
+				 flags & (O_ACCMODE | O_NONBLOCK), fops);
 	if (IS_ERR(file))
-		goto err_dput;
+		goto err;
+
 	file->f_mapping = anon_inode_inode->i_mapping;
 
 	file->private_data = priv;
 
 	return file;
 
-err_dput:
-	path_put(&path);
-err_module:
+err:
+	iput(anon_inode_inode);
 	module_put(fops->owner);
 	return file;
 }
-- 
cgit v1.2.3


From 152b6372c90630ef6787334e84cdddbcf8beb241 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 9 Jun 2018 10:05:18 -0400
Subject: create_pipe_files(): switch the first allocation to
 alloc_file_pseudo()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/pipe.c | 34 ++++++++--------------------------
 1 file changed, 8 insertions(+), 26 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index 1909422e5a78..9701bd3458d1 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -744,32 +744,24 @@ fail_inode:
 
 int create_pipe_files(struct file **res, int flags)
 {
-	int err;
 	struct inode *inode = get_pipe_inode();
 	struct file *f;
-	struct path path;
 
 	if (!inode)
 		return -ENFILE;
 
-	err = -ENOMEM;
-	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name);
-	if (!path.dentry)
-		goto err_inode;
-	path.mnt = mntget(pipe_mnt);
-
-	d_instantiate(path.dentry, inode);
-
-	f = alloc_file(&path, O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
-			&pipefifo_fops);
+	f = alloc_file_pseudo(inode, pipe_mnt, "",
+				O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)),
+				&pipefifo_fops);
 	if (IS_ERR(f)) {
-		err = PTR_ERR(f);
-		goto err_dentry;
+		free_pipe_info(inode->i_pipe);
+		iput(inode);
+		return PTR_ERR(f);
 	}
 
 	f->private_data = inode->i_pipe;
 
-	res[0] = alloc_file(&path, O_RDONLY | (flags & O_NONBLOCK),
+	res[0] = alloc_file(&f->f_path, O_RDONLY | (flags & O_NONBLOCK),
 			&pipefifo_fops);
 	if (IS_ERR(res[0])) {
 		put_pipe_info(inode, inode->i_pipe);
@@ -777,20 +769,10 @@ int create_pipe_files(struct file **res, int flags)
 		return PTR_ERR(res[0]);
 	}
 
-	path_get(&path);
+	path_get(&f->f_path);
 	res[0]->private_data = inode->i_pipe;
 	res[1] = f;
 	return 0;
-
-err_dentry:
-	free_pipe_info(inode->i_pipe);
-	path_put(&path);
-	return err;
-
-err_inode:
-	free_pipe_info(inode->i_pipe);
-	iput(inode);
-	return err;
 }
 
 static int __do_pipe_flags(int *fd, struct file **files, int flags)
-- 
cgit v1.2.3


From 183266f26f45a47958afb5c9aa1b3d4651e2eb8c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 17 Jun 2018 14:15:10 -0400
Subject: new helper: alloc_file_clone()

alloc_file_clone(old_file, mode, ops): create a new struct file with
->f_path equal to that of old_file.  pipe converted.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c      | 11 +++++++++++
 fs/pipe.c            |  6 ++----
 include/linux/file.h |  2 ++
 3 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 6b3723909342..78b067ddb386 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -211,6 +211,17 @@ struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
 }
 EXPORT_SYMBOL(alloc_file_pseudo);
 
+struct file *alloc_file_clone(struct file *base, int flags,
+				const struct file_operations *fops)
+{
+	struct file *f = alloc_file(&base->f_path, flags, fops);
+	if (!IS_ERR(f)) {
+		path_get(&f->f_path);
+		f->f_mapping = base->f_mapping;
+	}
+	return f;
+}
+
 /* the real guts of fput() - releasing the last reference to file
  */
 static void __fput(struct file *file)
diff --git a/fs/pipe.c b/fs/pipe.c
index 9701bd3458d1..5f50070774bc 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -761,15 +761,13 @@ int create_pipe_files(struct file **res, int flags)
 
 	f->private_data = inode->i_pipe;
 
-	res[0] = alloc_file(&f->f_path, O_RDONLY | (flags & O_NONBLOCK),
-			&pipefifo_fops);
+	res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK),
+				  &pipefifo_fops);
 	if (IS_ERR(res[0])) {
 		put_pipe_info(inode, inode->i_pipe);
 		fput(f);
 		return PTR_ERR(res[0]);
 	}
-
-	path_get(&f->f_path);
 	res[0]->private_data = inode->i_pipe;
 	res[1] = f;
 	return 0;
diff --git a/include/linux/file.h b/include/linux/file.h
index 5b25388f2f79..60914843c737 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -23,6 +23,8 @@ extern struct file *alloc_file(const struct path *, int flags,
 	const struct file_operations *fop);
 extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
 	const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_clone(struct file *, int flags,
+	const struct file_operations *);
 
 static inline void fput_light(struct file *file, int fput_needed)
 {
-- 
cgit v1.2.3


From 4f089acc5f76ab1dff17b5f0be7608671a8441dc Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 17 Jun 2018 12:24:00 -0400
Subject: do_shmat(): grab shp->shm_file earlier, switch to alloc_file_clone()

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 ipc/shm.c | 39 ++++++++++++++++++---------------------
 1 file changed, 18 insertions(+), 21 deletions(-)

diff --git a/ipc/shm.c b/ipc/shm.c
index c702abd578a7..7c8de9511950 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -1354,14 +1354,13 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 	struct shmid_kernel *shp;
 	unsigned long addr = (unsigned long)shmaddr;
 	unsigned long size;
-	struct file *file;
+	struct file *file, *base;
 	int    err;
 	unsigned long flags = MAP_SHARED;
 	unsigned long prot;
 	int acc_mode;
 	struct ipc_namespace *ns;
 	struct shm_file_data *sfd;
-	struct path path;
 	int f_flags;
 	unsigned long populate = 0;
 
@@ -1435,46 +1434,44 @@ long do_shmat(int shmid, char __user *shmaddr, int shmflg,
 		goto out_unlock;
 	}
 
-	path = shp->shm_file->f_path;
-	path_get(&path);
+	/*
+	 * We need to take a reference to the real shm file to prevent the
+	 * pointer from becoming stale in cases where the lifetime of the outer
+	 * file extends beyond that of the shm segment.  It's not usually
+	 * possible, but it can happen during remap_file_pages() emulation as
+	 * that unmaps the memory, then does ->mmap() via file reference only.
+	 * We'll deny the ->mmap() if the shm segment was since removed, but to
+	 * detect shm ID reuse we need to compare the file pointers.
+	 */
+	base = get_file(shp->shm_file);
 	shp->shm_nattch++;
-	size = i_size_read(d_inode(path.dentry));
+	size = i_size_read(file_inode(base));
 	ipc_unlock_object(&shp->shm_perm);
 	rcu_read_unlock();
 
 	err = -ENOMEM;
 	sfd = kzalloc(sizeof(*sfd), GFP_KERNEL);
 	if (!sfd) {
-		path_put(&path);
+		fput(base);
 		goto out_nattch;
 	}
 
-	file = alloc_file(&path, f_flags,
-			  is_file_hugepages(shp->shm_file) ?
+	file = alloc_file_clone(base, f_flags,
+			  is_file_hugepages(base) ?
 				&shm_file_operations_huge :
 				&shm_file_operations);
 	err = PTR_ERR(file);
 	if (IS_ERR(file)) {
 		kfree(sfd);
-		path_put(&path);
+		fput(base);
 		goto out_nattch;
 	}
 
-	file->private_data = sfd;
-	file->f_mapping = shp->shm_file->f_mapping;
 	sfd->id = shp->shm_perm.id;
 	sfd->ns = get_ipc_ns(ns);
-	/*
-	 * We need to take a reference to the real shm file to prevent the
-	 * pointer from becoming stale in cases where the lifetime of the outer
-	 * file extends beyond that of the shm segment.  It's not usually
-	 * possible, but it can happen during remap_file_pages() emulation as
-	 * that unmaps the memory, then does ->mmap() via file reference only.
-	 * We'll deny the ->mmap() if the shm segment was since removed, but to
-	 * detect shm ID reuse we need to compare the file pointers.
-	 */
-	sfd->file = get_file(shp->shm_file);
+	sfd->file = base;
 	sfd->vm_ops = NULL;
+	file->private_data = sfd;
 
 	err = security_mmap_file(file, prot, flags);
 	if (err)
-- 
cgit v1.2.3


From ee1904ba44bd4a242b453e8fe179b374906da173 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 17 Jun 2018 14:21:27 -0400
Subject: make alloc_file() static

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/file_table.c      | 3 +--
 include/linux/file.h | 2 --
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/fs/file_table.c b/fs/file_table.c
index 78b067ddb386..d6eccd04d703 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -157,7 +157,7 @@ over:
  * @flags: O_... flags with which the new file will be opened
  * @fop: the 'struct file_operations' for the new file
  */
-struct file *alloc_file(const struct path *path, int flags,
+static struct file *alloc_file(const struct path *path, int flags,
 		const struct file_operations *fop)
 {
 	struct file *file;
@@ -182,7 +182,6 @@ struct file *alloc_file(const struct path *path, int flags,
 		i_readcount_inc(path->dentry->d_inode);
 	return file;
 }
-EXPORT_SYMBOL(alloc_file);
 
 struct file *alloc_file_pseudo(struct inode *inode, struct vfsmount *mnt,
 				const char *name, int flags,
diff --git a/include/linux/file.h b/include/linux/file.h
index 60914843c737..6b2fb032416c 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -19,8 +19,6 @@ struct vfsmount;
 struct dentry;
 struct inode;
 struct path;
-extern struct file *alloc_file(const struct path *, int flags,
-	const struct file_operations *fop);
 extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
 	const char *, int flags, const struct file_operations *);
 extern struct file *alloc_file_clone(struct file *, int flags,
-- 
cgit v1.2.3


From 5014c2f378ca3f6ddfe310e4b5ef7027acfc2d45 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 19:20:08 -0400
Subject: document alloc_file() changes

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/Documentation/filesystems/porting b/Documentation/filesystems/porting
index c68ea9294b5f..7b7b845c490a 100644
--- a/Documentation/filesystems/porting
+++ b/Documentation/filesystems/porting
@@ -610,3 +610,15 @@ in your dentry operations instead.
 	value for 'called finish_no_open(), open it yourself' case has become
 	0, not 1.  Since finish_no_open() itself is returning 0 now, that part
 	does not need any changes in ->atomic_open() instances.
+--
+[mandatory]
+	alloc_file() has become static now; two wrappers are to be used instead.
+	alloc_file_pseudo(inode, vfsmount, name, flags, ops) is for the cases
+	when dentry needs to be created; that's the majority of old alloc_file()
+	users.  Calling conventions: on success a reference to new struct file
+	is returned and callers reference to inode is subsumed by that.  On
+	failure, ERR_PTR() is returned and no caller's references are affected,
+	so the caller needs to drop the inode reference it held.
+	alloc_file_clone(file, flags, ops) does not affect any caller's references.
+	On success you get a new struct file sharing the mount/dentry with the
+	original, on failure - ERR_PTR().
-- 
cgit v1.2.3


From edc2b1da779887c74ade799574efc5819906598f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 16:27:23 -0400
Subject: make path_init() unconditionally paired with terminate_walk()

including the failure exits

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 8311dce1c649..1b5c58ad4113 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2125,12 +2125,15 @@ OK:
 	}
 }
 
+/* must be paired with terminate_walk() */
 static const char *path_init(struct nameidata *nd, unsigned flags)
 {
 	const char *s = nd->name->name;
 
 	if (!*s)
 		flags &= ~LOOKUP_RCU;
+	if (flags & LOOKUP_RCU)
+		rcu_read_lock();
 
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
@@ -2143,7 +2146,6 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
 			nd->root_seq = nd->seq;
 			nd->m_seq = read_seqbegin(&mount_lock);
@@ -2159,21 +2161,15 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 	nd->m_seq = read_seqbegin(&mount_lock);
 	if (*s == '/') {
-		if (flags & LOOKUP_RCU)
-			rcu_read_lock();
 		set_root(nd);
 		if (likely(!nd_jump_root(nd)))
 			return s;
-		nd->root.mnt = NULL;
-		rcu_read_unlock();
 		return ERR_PTR(-ECHILD);
 	} else if (nd->dfd == AT_FDCWD) {
 		if (flags & LOOKUP_RCU) {
 			struct fs_struct *fs = current->fs;
 			unsigned seq;
 
-			rcu_read_lock();
-
 			do {
 				seq = read_seqcount_begin(&fs->seq);
 				nd->path = fs->pwd;
@@ -2195,16 +2191,13 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 
 		dentry = f.file->f_path.dentry;
 
-		if (*s) {
-			if (!d_can_lookup(dentry)) {
-				fdput(f);
-				return ERR_PTR(-ENOTDIR);
-			}
+		if (*s && unlikely(!d_can_lookup(dentry))) {
+			fdput(f);
+			return ERR_PTR(-ENOTDIR);
 		}
 
 		nd->path = f.file->f_path;
 		if (flags & LOOKUP_RCU) {
-			rcu_read_lock();
 			nd->inode = nd->path.dentry->d_inode;
 			nd->seq = read_seqcount_begin(&nd->path.dentry->d_seq);
 		} else {
@@ -2272,8 +2265,10 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	const char *s = path_init(nd, flags);
 	int err;
 
-	if (IS_ERR(s))
+	if (IS_ERR(s)) {
+		terminate_walk(nd);
 		return PTR_ERR(s);
+	}
 
 	if (unlikely(flags & LOOKUP_DOWN)) {
 		err = handle_lookup_down(nd);
@@ -2337,8 +2332,10 @@ static int path_parentat(struct nameidata *nd, unsigned flags,
 {
 	const char *s = path_init(nd, flags);
 	int err;
-	if (IS_ERR(s))
+	if (IS_ERR(s)) {
+		terminate_walk(nd);
 		return PTR_ERR(s);
+	}
 	err = link_path_walk(s, nd);
 	if (!err)
 		err = complete_walk(nd);
@@ -2666,8 +2663,10 @@ path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
 {
 	const char *s = path_init(nd, flags);
 	int err;
-	if (IS_ERR(s))
+	if (IS_ERR(s)) {
+		terminate_walk(nd);
 		return PTR_ERR(s);
+	}
 	while (!(err = link_path_walk(s, nd)) &&
 		(err = mountpoint_last(nd)) > 0) {
 		s = trailing_symlink(nd);
@@ -3512,6 +3511,7 @@ static struct file *path_openat(struct nameidata *nd,
 
 	s = path_init(nd, flags);
 	if (IS_ERR(s)) {
+		terminate_walk(nd);
 		fput(file);
 		return ERR_CAST(s);
 	}
-- 
cgit v1.2.3


From 9b5858e99ae1cfb60dc00461cfc7bd4dd077d7d7 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 16:33:23 -0400
Subject: allow link_path_walk() to take ERR_PTR()

There is a check for IS_ERR(name) immediately upstream of each call
of link_path_walk(name, nd), with positives treated as if link_path_walk()
failed with PTR_ERR(name).  Taking that check into link_path_walk() itself
simplifies things nicely.

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 38 +++++---------------------------------
 1 file changed, 5 insertions(+), 33 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 1b5c58ad4113..22535f133200 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2028,6 +2028,8 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 {
 	int err;
 
+	if (IS_ERR(name))
+		return PTR_ERR(name);
 	while (*name=='/')
 		name++;
 	if (!*name)
@@ -2265,12 +2267,7 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	const char *s = path_init(nd, flags);
 	int err;
 
-	if (IS_ERR(s)) {
-		terminate_walk(nd);
-		return PTR_ERR(s);
-	}
-
-	if (unlikely(flags & LOOKUP_DOWN)) {
+	if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
 		err = handle_lookup_down(nd);
 		if (unlikely(err < 0)) {
 			terminate_walk(nd);
@@ -2281,10 +2278,6 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 	while (!(err = link_path_walk(s, nd))
 		&& ((err = lookup_last(nd)) > 0)) {
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			err = PTR_ERR(s);
-			break;
-		}
 	}
 	if (!err)
 		err = complete_walk(nd);
@@ -2331,12 +2324,7 @@ static int path_parentat(struct nameidata *nd, unsigned flags,
 				struct path *parent)
 {
 	const char *s = path_init(nd, flags);
-	int err;
-	if (IS_ERR(s)) {
-		terminate_walk(nd);
-		return PTR_ERR(s);
-	}
-	err = link_path_walk(s, nd);
+	int err = link_path_walk(s, nd);
 	if (!err)
 		err = complete_walk(nd);
 	if (!err) {
@@ -2663,17 +2651,10 @@ path_mountpoint(struct nameidata *nd, unsigned flags, struct path *path)
 {
 	const char *s = path_init(nd, flags);
 	int err;
-	if (IS_ERR(s)) {
-		terminate_walk(nd);
-		return PTR_ERR(s);
-	}
+
 	while (!(err = link_path_walk(s, nd)) &&
 		(err = mountpoint_last(nd)) > 0) {
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			err = PTR_ERR(s);
-			break;
-		}
 	}
 	if (!err) {
 		*path = nd->path;
@@ -3510,19 +3491,10 @@ static struct file *path_openat(struct nameidata *nd,
 	}
 
 	s = path_init(nd, flags);
-	if (IS_ERR(s)) {
-		terminate_walk(nd);
-		fput(file);
-		return ERR_CAST(s);
-	}
 	while (!(error = link_path_walk(s, nd)) &&
 		(error = do_last(nd, file, op)) > 0) {
 		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
 		s = trailing_symlink(nd);
-		if (IS_ERR(s)) {
-			error = PTR_ERR(s);
-			break;
-		}
 	}
 	terminate_walk(nd);
 out2:
-- 
cgit v1.2.3


From 5f336e722cc961be94d264d96b90c92888fffae1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 9 Jul 2018 16:38:06 -0400
Subject: few more cleanups of link_path_walk() callers

Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 30 +++++++++++-------------------
 1 file changed, 11 insertions(+), 19 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 22535f133200..278e494bcbd2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2269,10 +2269,8 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 
 	if (unlikely(flags & LOOKUP_DOWN) && !IS_ERR(s)) {
 		err = handle_lookup_down(nd);
-		if (unlikely(err < 0)) {
-			terminate_walk(nd);
-			return err;
-		}
+		if (unlikely(err < 0))
+			s = ERR_PTR(err);
 	}
 
 	while (!(err = link_path_walk(s, nd))
@@ -3472,7 +3470,6 @@ static int do_o_path(struct nameidata *nd, unsigned flags, struct file *file)
 static struct file *path_openat(struct nameidata *nd,
 			const struct open_flags *op, unsigned flags)
 {
-	const char *s;
 	struct file *file;
 	int error;
 
@@ -3482,22 +3479,17 @@ static struct file *path_openat(struct nameidata *nd,
 
 	if (unlikely(file->f_flags & __O_TMPFILE)) {
 		error = do_tmpfile(nd, flags, op, file);
-		goto out2;
-	}
-
-	if (unlikely(file->f_flags & O_PATH)) {
+	} else if (unlikely(file->f_flags & O_PATH)) {
 		error = do_o_path(nd, flags, file);
-		goto out2;
-	}
-
-	s = path_init(nd, flags);
-	while (!(error = link_path_walk(s, nd)) &&
-		(error = do_last(nd, file, op)) > 0) {
-		nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
-		s = trailing_symlink(nd);
+	} else {
+		const char *s = path_init(nd, flags);
+		while (!(error = link_path_walk(s, nd)) &&
+			(error = do_last(nd, file, op)) > 0) {
+			nd->flags &= ~(LOOKUP_OPEN|LOOKUP_CREATE|LOOKUP_EXCL);
+			s = trailing_symlink(nd);
+		}
+		terminate_walk(nd);
 	}
-	terminate_walk(nd);
-out2:
 	if (likely(!error)) {
 		if (likely(file->f_mode & FMODE_OPENED))
 			return file;
-- 
cgit v1.2.3


From 11527b3e0b577513ea318f01e392ccf7feb9d2a4 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Thu, 12 Jul 2018 15:14:23 +0100
Subject: arm64: Drop asmlinkage qualifier from syscall_trace_{enter,exit}

syscall_trace_{enter,exit} are only called from C code, so drop the
asmlinkage qualifier from their definitions.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/ptrace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 489db3624606..379b2b714193 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -1631,7 +1631,7 @@ static void tracehook_report_syscall(struct pt_regs *regs,
 	regs->regs[regno] = saved_reg;
 }
 
-asmlinkage int syscall_trace_enter(struct pt_regs *regs)
+int syscall_trace_enter(struct pt_regs *regs)
 {
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER);
@@ -1649,7 +1649,7 @@ asmlinkage int syscall_trace_enter(struct pt_regs *regs)
 	return regs->syscallno;
 }
 
-asmlinkage void syscall_trace_exit(struct pt_regs *regs)
+void syscall_trace_exit(struct pt_regs *regs)
 {
 	audit_syscall_exit(regs);
 
-- 
cgit v1.2.3


From 60c0a66ee96cbdb22e029da70ec42e249f1996a5 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Thu, 12 Jul 2018 14:48:10 +0200
Subject: drm/i915: Tidy error handling in i915_gem_init_hw
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's reorder things so that we can do onion teardown rather than double
goto.

References: b96f6ebfd024 ("drm/i915: Correctly handle error path in i915_gem_init_hw")
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Sagar Arun Kamble <sagar.a.kamble@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712124810.25241-1-michal.winiarski@intel.com
---
 drivers/gpu/drm/i915/i915_gem.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 07a92ca61dbf..ed2be33ec58a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5313,13 +5313,17 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv)
 	ret = __i915_gem_restart_engines(dev_priv);
 	if (ret)
 		goto cleanup_uc;
-out:
+
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	return ret;
+
+	return 0;
 
 cleanup_uc:
 	intel_uc_fini_hw(dev_priv);
-	goto out;
+out:
+	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
+
+	return ret;
 }
 
 static int __intel_engines_record_defaults(struct drm_i915_private *i915)
-- 
cgit v1.2.3


From a63983f26008804e8db12457e429e5fc18841894 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Thu, 12 Jul 2018 12:20:13 +0100
Subject: drm/i915/selftests: Fixup GuC FW negative test
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since:
0d4b78b3d2c0 ("drm/i915/guc: Assert we have the doorbell before setting it up")

We have asserts in GuC doorbell related functions, which is a good thing.
Unfortunately, we were using those to check whether GuC FW is refusing
to allocate invalid doorbell - which makes the test fail.
Well, it would make the test WARN, except we fumbled cleanup ordering
and eat the BUG_ON instead.
Let's keep the asserts and use the internal implementation in the test.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107186
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712112013.3253-1-chris@chris-wilson.co.uk
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/selftests/intel_guc.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/intel_guc.c b/drivers/gpu/drm/i915/selftests/intel_guc.c
index fb74e2cf8a0a..407c98fb9170 100644
--- a/drivers/gpu/drm/i915/selftests/intel_guc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_guc.c
@@ -196,19 +196,23 @@ static int igt_guc_clients(void *args)
 	}
 
 	unreserve_doorbell(guc->execbuf_client);
-	err = guc_clients_doorbell_init(guc);
+
+	__create_doorbell(guc->execbuf_client);
+	err = __guc_allocate_doorbell(guc, guc->execbuf_client->stage_id);
 	if (err != -EIO) {
 		pr_err("unexpected (err = %d)", err);
-		goto out;
+		goto out_db;
 	}
 
 	if (!available_dbs(guc, guc->execbuf_client->priority)) {
 		pr_err("doorbell not available when it should\n");
 		err = -EIO;
-		goto out;
+		goto out_db;
 	}
 
+out_db:
 	/* clean after test */
+	__destroy_doorbell(guc->execbuf_client);
 	err = reserve_doorbell(guc->execbuf_client);
 	if (err) {
 		pr_err("failed to reserve back the doorbell back\n");
-- 
cgit v1.2.3


From 42ac03213b7f102682157c2821e3fd9657ce4eb7 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Thu, 12 Jul 2018 10:41:02 -0300
Subject: drm/vkms: Add framebuffer and plane helpers

This patch appends the minimum helpers related to framebuffer and plane
to make vkms minimally usable.

Changes since V1:
- None
Changes since V2:
- Squash "Add plane helper struct" and "Add helper for framebuffer
  create"
Changes since V3:
 Daniel Vetter:
 - Remove atomic_check from plane helper

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/d37807da7d3b39444b4c9abb149fe3c518d07c61.1531402095.git.rodrigosiqueiramelo@gmail.com
---
 drivers/gpu/drm/vkms/vkms_drv.c   |  3 +++
 drivers/gpu/drm/vkms/vkms_plane.c | 11 +++++++++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index a1448fb56893..37aa2ef33b21 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -9,6 +9,8 @@
 #include <drm/drm_gem.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_fb_helper.h>
 #include "vkms_drv.h"
 
 #define DRIVER_NAME	"vkms"
@@ -64,6 +66,7 @@ static struct drm_driver vkms_driver = {
 };
 
 static const struct drm_mode_config_funcs vkms_mode_funcs = {
+	.fb_create = drm_gem_fb_create,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
diff --git a/drivers/gpu/drm/vkms/vkms_plane.c b/drivers/gpu/drm/vkms/vkms_plane.c
index 2c25b1d6ab5b..9f75b1e2c1c4 100644
--- a/drivers/gpu/drm/vkms/vkms_plane.c
+++ b/drivers/gpu/drm/vkms/vkms_plane.c
@@ -19,6 +19,15 @@ static const struct drm_plane_funcs vkms_plane_funcs = {
 	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
 };
 
+static void vkms_primary_plane_update(struct drm_plane *plane,
+				      struct drm_plane_state *old_state)
+{
+}
+
+static const struct drm_plane_helper_funcs vkms_primary_helper_funcs = {
+	.atomic_update		= vkms_primary_plane_update,
+};
+
 struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev)
 {
 	struct drm_device *dev = &vkmsdev->drm;
@@ -42,5 +51,7 @@ struct drm_plane *vkms_plane_init(struct vkms_device *vkmsdev)
 		return ERR_PTR(ret);
 	}
 
+	drm_plane_helper_add(plane, &vkms_primary_helper_funcs);
+
 	return plane;
 }
-- 
cgit v1.2.3


From 73675cf6979bb80534641b1814a971eaf9f649b5 Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Thu, 28 Jun 2018 19:04:48 +0530
Subject: drm/i915/gmbus: Increase the Bytes per Rd/Wr Op

GMBUS HW supports 511Bytes as Max Bytes per single RD/WR op. Instead of
enabling the 511Bytes per RD/WR cycle on legacy platforms for no
absolute ROIs, this change allows the max bytes per op upto 511Bytes
from Gen9 onwards.

v2:
  No Change.
v3:
  Inline function for max_xfer_size and renaming of the macro.[Jani]
v4:
  Extra brackets removed [ville]
  Commit msg is modified.
v5:
  Collecting the Reviewed-By received.

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1530192889-5789-2-git-send-email-ramalingam.c@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h  |  1 +
 drivers/gpu/drm/i915/intel_i2c.c | 11 +++++++++--
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index b95bab7a3d24..2da870a8948e 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3152,6 +3152,7 @@ enum i915_power_well_id {
 #define   GMBUS_CYCLE_STOP	(4 << 25)
 #define   GMBUS_BYTE_COUNT_SHIFT 16
 #define   GMBUS_BYTE_COUNT_MAX   256U
+#define   GEN9_GMBUS_BYTE_COUNT_MAX 511U
 #define   GMBUS_SLAVE_INDEX_SHIFT 8
 #define   GMBUS_SLAVE_ADDR_SHIFT 1
 #define   GMBUS_SLAVE_READ	(1 << 0)
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 97606c1be70d..82bb9c33ab1c 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -361,6 +361,13 @@ gmbus_wait_idle(struct drm_i915_private *dev_priv)
 	return ret;
 }
 
+static inline
+unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv)
+{
+	return INTEL_GEN(dev_priv) >= 9 ? GEN9_GMBUS_BYTE_COUNT_MAX :
+	       GMBUS_BYTE_COUNT_MAX;
+}
+
 static int
 gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 		      unsigned short addr, u8 *buf, unsigned int len,
@@ -400,7 +407,7 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 	int ret;
 
 	do {
-		len = min(rx_size, GMBUS_BYTE_COUNT_MAX);
+		len = min(rx_size, gmbus_max_xfer_size(dev_priv));
 
 		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr,
 					    buf, len, gmbus1_index);
@@ -462,7 +469,7 @@ gmbus_xfer_write(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 	int ret;
 
 	do {
-		len = min(tx_size, GMBUS_BYTE_COUNT_MAX);
+		len = min(tx_size, gmbus_max_xfer_size(dev_priv));
 
 		ret = gmbus_xfer_write_chunk(dev_priv, msg->addr, buf, len,
 					     gmbus1_index);
-- 
cgit v1.2.3


From d5dc0f43f268bf2b6bb61f109a18a652a49c6f4e Mon Sep 17 00:00:00 2001
From: Ramalingam C <ramalingam.c@intel.com>
Date: Thu, 28 Jun 2018 19:04:49 +0530
Subject: drm/i915/gmbus: Enable burst read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Support for Burst read in HW is added for HDCP2.2 compliance
requirement.

This patch enables the burst read for all the gmbus read of more than
511Bytes, on capable platforms.

v2:
  Extra line is removed.
v3:
  Macro is added for detecting the BURST_READ Support [Jani]
  Runtime detection of the need for burst_read [Jani]
  Calculation enhancement.
v4:
  GMBUS0 reg val is passed from caller [ville]
  Removed a extra var [ville]
  Extra brackets are removed [ville]
  Implemented the handling of 512Bytes Burst Read.
v5:
  Burst read max length is fixed at 767Bytes [Ville]
v6:
  Collecting the received reviewed-by.

Signed-off-by: Ramalingam C <ramalingam.c@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/1530192889-5789-3-git-send-email-ramalingam.c@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h  |  3 ++
 drivers/gpu/drm/i915/i915_reg.h  |  1 +
 drivers/gpu/drm/i915/intel_i2c.c | 61 +++++++++++++++++++++++++++++++++-------
 3 files changed, 55 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 48b350116cba..a6c6decd0546 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2560,6 +2560,9 @@ intel_info(const struct drm_i915_private *dev_priv)
 	 IS_SKL_GT3(dev_priv) || IS_SKL_GT4(dev_priv))
 
 #define HAS_GMBUS_IRQ(dev_priv) (INTEL_GEN(dev_priv) >= 4)
+#define HAS_GMBUS_BURST_READ(dev_priv) (INTEL_GEN(dev_priv) >= 10 || \
+					IS_GEMINILAKE(dev_priv) || \
+					IS_KABYLAKE(dev_priv))
 
 /* With the 945 and later, Y tiling got adjusted so that it was 32 128-byte
  * rows, which changed the alignment requirements and fence programming.
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 2da870a8948e..1f222af0324d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3123,6 +3123,7 @@ enum i915_power_well_id {
 #define   GMBUS_RATE_400KHZ	(2 << 8) /* reserved on Pineview */
 #define   GMBUS_RATE_1MHZ	(3 << 8) /* reserved on Pineview */
 #define   GMBUS_HOLD_EXT	(1 << 7) /* 300ns hold time, rsvd on Pineview */
+#define   GMBUS_BYTE_CNT_OVERRIDE (1 << 6)
 #define   GMBUS_PIN_DISABLED	0
 #define   GMBUS_PIN_SSC		1
 #define   GMBUS_PIN_VGADDC	2
diff --git a/drivers/gpu/drm/i915/intel_i2c.c b/drivers/gpu/drm/i915/intel_i2c.c
index 82bb9c33ab1c..bef32b7c248e 100644
--- a/drivers/gpu/drm/i915/intel_i2c.c
+++ b/drivers/gpu/drm/i915/intel_i2c.c
@@ -371,12 +371,29 @@ unsigned int gmbus_max_xfer_size(struct drm_i915_private *dev_priv)
 static int
 gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 		      unsigned short addr, u8 *buf, unsigned int len,
-		      u32 gmbus1_index)
+		      u32 gmbus0_reg, u32 gmbus1_index)
 {
+	unsigned int size = len;
+	bool burst_read = len > gmbus_max_xfer_size(dev_priv);
+	bool extra_byte_added = false;
+
+	if (burst_read) {
+		/*
+		 * As per HW Spec, for 512Bytes need to read extra Byte and
+		 * Ignore the extra byte read.
+		 */
+		if (len == 512) {
+			extra_byte_added = true;
+			len++;
+		}
+		size = len % 256 + 256;
+		I915_WRITE_FW(GMBUS0, gmbus0_reg | GMBUS_BYTE_CNT_OVERRIDE);
+	}
+
 	I915_WRITE_FW(GMBUS1,
 		      gmbus1_index |
 		      GMBUS_CYCLE_WAIT |
-		      (len << GMBUS_BYTE_COUNT_SHIFT) |
+		      (size << GMBUS_BYTE_COUNT_SHIFT) |
 		      (addr << GMBUS_SLAVE_ADDR_SHIFT) |
 		      GMBUS_SLAVE_READ | GMBUS_SW_RDY);
 	while (len) {
@@ -389,17 +406,34 @@ gmbus_xfer_read_chunk(struct drm_i915_private *dev_priv,
 
 		val = I915_READ_FW(GMBUS3);
 		do {
+			if (extra_byte_added && len == 1)
+				break;
+
 			*buf++ = val & 0xff;
 			val >>= 8;
 		} while (--len && ++loop < 4);
+
+		if (burst_read && len == size - 4)
+			/* Reset the override bit */
+			I915_WRITE_FW(GMBUS0, gmbus0_reg);
 	}
 
 	return 0;
 }
 
+/*
+ * HW spec says that 512Bytes in Burst read need special treatment.
+ * But it doesn't talk about other multiple of 256Bytes. And couldn't locate
+ * an I2C slave, which supports such a lengthy burst read too for experiments.
+ *
+ * So until things get clarified on HW support, to avoid the burst read length
+ * in fold of 256Bytes except 512, max burst read length is fixed at 767Bytes.
+ */
+#define INTEL_GMBUS_BURST_READ_MAX_LEN		767U
+
 static int
 gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
-		u32 gmbus1_index)
+		u32 gmbus0_reg, u32 gmbus1_index)
 {
 	u8 *buf = msg->buf;
 	unsigned int rx_size = msg->len;
@@ -407,10 +441,13 @@ gmbus_xfer_read(struct drm_i915_private *dev_priv, struct i2c_msg *msg,
 	int ret;
 
 	do {
-		len = min(rx_size, gmbus_max_xfer_size(dev_priv));
+		if (HAS_GMBUS_BURST_READ(dev_priv))
+			len = min(rx_size, INTEL_GMBUS_BURST_READ_MAX_LEN);
+		else
+			len = min(rx_size, gmbus_max_xfer_size(dev_priv));
 
-		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr,
-					    buf, len, gmbus1_index);
+		ret = gmbus_xfer_read_chunk(dev_priv, msg->addr, buf, len,
+					    gmbus0_reg, gmbus1_index);
 		if (ret)
 			return ret;
 
@@ -498,7 +535,8 @@ gmbus_is_index_xfer(struct i2c_msg *msgs, int i, int num)
 }
 
 static int
-gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
+gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs,
+		 u32 gmbus0_reg)
 {
 	u32 gmbus1_index = 0;
 	u32 gmbus5 = 0;
@@ -516,7 +554,8 @@ gmbus_index_xfer(struct drm_i915_private *dev_priv, struct i2c_msg *msgs)
 		I915_WRITE_FW(GMBUS5, gmbus5);
 
 	if (msgs[1].flags & I2C_M_RD)
-		ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus1_index);
+		ret = gmbus_xfer_read(dev_priv, &msgs[1], gmbus0_reg,
+				      gmbus1_index);
 	else
 		ret = gmbus_xfer_write(dev_priv, &msgs[1], gmbus1_index);
 
@@ -551,10 +590,12 @@ retry:
 	for (; i < num; i += inc) {
 		inc = 1;
 		if (gmbus_is_index_xfer(msgs, i, num)) {
-			ret = gmbus_index_xfer(dev_priv, &msgs[i]);
+			ret = gmbus_index_xfer(dev_priv, &msgs[i],
+					       gmbus0_source | bus->reg0);
 			inc = 2; /* an index transmission is two msgs */
 		} else if (msgs[i].flags & I2C_M_RD) {
-			ret = gmbus_xfer_read(dev_priv, &msgs[i], 0);
+			ret = gmbus_xfer_read(dev_priv, &msgs[i],
+					      gmbus0_source | bus->reg0, 0);
 		} else {
 			ret = gmbus_xfer_write(dev_priv, &msgs[i], 0);
 		}
-- 
cgit v1.2.3


From b5d69129ea2b86d8a357efe3eca664b44860406e Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Thu, 12 Jul 2018 15:42:55 +0200
Subject: mips/jazz: provide missing dma_mask/coherent_dma_mask

Commit 205e1b7f51e4 ("dma-mapping: warn when there is no
coherent_dma_mask") introduced a warning, if a device is missing a
coherent_dma_mask. ESP and sonic are using dma mapping functions, so
they need dma masks.

[paul.burton@mips.com:
  - Wrap commit message.]

Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19828/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/jazz/setup.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/arch/mips/jazz/setup.c b/arch/mips/jazz/setup.c
index 448fd41792e4..1b5e121c3f0d 100644
--- a/arch/mips/jazz/setup.c
+++ b/arch/mips/jazz/setup.c
@@ -16,6 +16,7 @@
 #include <linux/screen_info.h>
 #include <linux/platform_device.h>
 #include <linux/serial_8250.h>
+#include <linux/dma-mapping.h>
 
 #include <asm/jazz.h>
 #include <asm/jazzdma.h>
@@ -136,10 +137,16 @@ static struct resource jazz_esp_rsrc[] = {
 	}
 };
 
+static u64 jazz_esp_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device jazz_esp_pdev = {
 	.name		= "jazz_esp",
 	.num_resources	= ARRAY_SIZE(jazz_esp_rsrc),
-	.resource	= jazz_esp_rsrc
+	.resource	= jazz_esp_rsrc,
+	.dev = {
+		.dma_mask	   = &jazz_esp_dma_mask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+	}
 };
 
 static struct resource jazz_sonic_rsrc[] = {
@@ -155,10 +162,16 @@ static struct resource jazz_sonic_rsrc[] = {
 	}
 };
 
+static u64 jazz_sonic_dma_mask = DMA_BIT_MASK(32);
+
 static struct platform_device jazz_sonic_pdev = {
 	.name		= "jazzsonic",
 	.num_resources	= ARRAY_SIZE(jazz_sonic_rsrc),
-	.resource	= jazz_sonic_rsrc
+	.resource	= jazz_sonic_rsrc,
+	.dev = {
+		.dma_mask	   = &jazz_sonic_dma_mask,
+		.coherent_dma_mask = DMA_BIT_MASK(32),
+	}
 };
 
 static struct resource jazz_cmos_rsrc[] = {
-- 
cgit v1.2.3


From f88c5ee77496886071e76b5b9fdfee7158f6d079 Mon Sep 17 00:00:00 2001
From: Jernej Skrabec <jernej.skrabec@siol.net>
Date: Fri, 6 Jul 2018 18:47:32 +0200
Subject: drm/sun4i: Implement zpos for DE2

Initial implementation of DE2 planes only supported fixed zpos.

Expand implementation with configurable zpos property.

Implementation background:
Channel in DE2 driver represents one DRM plane, whereas pipe is just
mapped channel to known Z position. Pipe 0 will always be at the bottom,
pipe 1 just above pipe 0 and so on. If, for example, channel 1 is mapped
at pipe 0 and channel 0 at pipe 1, whatever is on channel 0 will appear
on top.

Before this commit, channel id was used for addressing channel related
registers (prefixed with SUN8I_MIXER_CHAN_UI_ or SUN8I_MIXER_CHAN_VI_)
and pipe registers (prefixed with SUN8I_MIXER_BLEND_). Additionally,
register SUN8I_MIXER_BLEND_ROUTE, which takes care for mapping channels
to pipes had fixed value. It mapped channel 0 to pipe 0, 1 to 1 and so
on. Consequence of all that was fixed Z order of planes.

With this commit, pipe registers are using zpos property as index and
channel related registers still use channel id as index. Pipe mapping
register is now set dynamically too and pipe enable register is rebuild
every time to make sure only active pipes are enabled.

Testing was done to confirm that there is no issues if bottom plane
contains pixels with alpha value < 0xff and if it doesn't whole screen.

Tested-by: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Signed-off-by: Jernej Skrabec <jernej.skrabec@siol.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180706164732.24166-1-jernej.skrabec@siol.net
---
 drivers/gpu/drm/sun4i/sun8i_mixer.c    | 15 +++++++++---
 drivers/gpu/drm/sun4i/sun8i_mixer.h    |  4 +++
 drivers/gpu/drm/sun4i/sun8i_ui_layer.c | 45 +++++++++++++++++++++-------------
 drivers/gpu/drm/sun4i/sun8i_vi_layer.c | 45 +++++++++++++++++++++-------------
 4 files changed, 72 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index da34fc394902..f76a5576c0e6 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -261,6 +261,17 @@ const struct de2_fmt_info *sun8i_mixer_format_info(u32 format)
 	return NULL;
 }
 
+static void sun8i_mixer_atomic_begin(struct sunxi_engine *engine,
+				     struct drm_crtc_state *old_state)
+{
+	/*
+	 * Disable all pipes at the beginning. They will be enabled
+	 * again if needed in plane update callback.
+	 */
+	regmap_update_bits(engine->regs, SUN8I_MIXER_BLEND_PIPE_CTL,
+			   SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK, 0);
+}
+
 static void sun8i_mixer_commit(struct sunxi_engine *engine)
 {
 	DRM_DEBUG_DRIVER("Committing changes\n");
@@ -312,6 +323,7 @@ static struct drm_plane **sun8i_layers_init(struct drm_device *drm,
 }
 
 static const struct sunxi_engine_ops sun8i_engine_ops = {
+	.atomic_begin	= sun8i_mixer_atomic_begin,
 	.commit		= sun8i_mixer_commit,
 	.layers_init	= sun8i_layers_init,
 };
@@ -477,9 +489,6 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 	regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_ATTR_FCOLOR(0),
 		     SUN8I_MIXER_BLEND_COLOR_BLACK);
 
-	/* Fixed zpos for now */
-	regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_ROUTE, 0x43210);
-
 	plane_cnt = mixer->cfg->vi_num + mixer->cfg->ui_num;
 	for (i = 0; i < plane_cnt; i++)
 		regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_MODE(i),
diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.h b/drivers/gpu/drm/sun4i/sun8i_mixer.h
index f34e70c42adf..406c42e752d7 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.h
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.h
@@ -44,6 +44,7 @@
 #define SUN8I_MIXER_BLEND_CK_MIN(x)		(0x10e0 + 0x04 * (x))
 #define SUN8I_MIXER_BLEND_OUTCTL		0x10fc
 
+#define SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK	GENMASK(12, 8)
 #define SUN8I_MIXER_BLEND_PIPE_CTL_EN(pipe)	BIT(8 + pipe)
 #define SUN8I_MIXER_BLEND_PIPE_CTL_FC_EN(pipe)	BIT(pipe)
 /* colors are always in AARRGGBB format */
@@ -51,6 +52,9 @@
 /* The following numbers are some still unknown magic numbers */
 #define SUN8I_MIXER_BLEND_MODE_DEF		0x03010301
 
+#define SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(n)	(0xf << ((n) << 2))
+#define SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(n)	((n) << 2)
+
 #define SUN8I_MIXER_BLEND_OUTCTL_INTERLACED	BIT(1)
 
 #define SUN8I_MIXER_FBFMT_ARGB8888	0
diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
index 9a540330cb79..518e1921f47e 100644
--- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
@@ -27,7 +27,7 @@
 #include "sun8i_ui_scaler.h"
 
 static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable)
+				  int overlay, bool enable, unsigned int zpos)
 {
 	u32 val;
 
@@ -43,18 +43,24 @@ static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR_EN, val);
 
-	if (enable)
-		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel);
-	else
-		val = 0;
+	if (enable) {
+		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
 
-	regmap_update_bits(mixer->engine.regs,
-			   SUN8I_MIXER_BLEND_PIPE_CTL,
-			   SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel), val);
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL, val, val);
+
+		val = channel << SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(zpos),
+				   val);
+	}
 }
 
 static int sun8i_ui_layer_update_coord(struct sun8i_mixer *mixer, int channel,
-				       int overlay, struct drm_plane *plane)
+				       int overlay, struct drm_plane *plane,
+				       unsigned int zpos)
 {
 	struct drm_plane_state *state = plane->state;
 	u32 src_w, src_h, dst_w, dst_h;
@@ -137,10 +143,10 @@ static int sun8i_ui_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 			 state->dst.x1, state->dst.y1);
 	DRM_DEBUG_DRIVER("Layer destination size W: %d H: %d\n", dst_w, dst_h);
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_COORD(channel),
+		     SUN8I_MIXER_BLEND_ATTR_COORD(zpos),
 		     SUN8I_MIXER_COORD(state->dst.x1, state->dst.y1));
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_INSIZE(channel),
+		     SUN8I_MIXER_BLEND_ATTR_INSIZE(zpos),
 		     outsize);
 
 	return 0;
@@ -238,28 +244,30 @@ static void sun8i_ui_layer_atomic_disable(struct drm_plane *plane,
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false);
+	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false, 0);
 }
 
 static void sun8i_ui_layer_atomic_update(struct drm_plane *plane,
 					 struct drm_plane_state *old_state)
 {
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
+	unsigned int zpos = plane->state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_ui_layer_enable(mixer, layer->channel,
-				      layer->overlay, false);
+				      layer->overlay, false, 0);
 		return;
 	}
 
 	sun8i_ui_layer_update_coord(mixer, layer->channel,
-				    layer->overlay, plane);
+				    layer->overlay, plane, zpos);
 	sun8i_ui_layer_update_formats(mixer, layer->channel,
 				      layer->overlay, plane);
 	sun8i_ui_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
-	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, true);
+	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay,
+			      true, zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_ui_layer_helper_funcs = {
@@ -307,6 +315,7 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm,
 	enum drm_plane_type type = DRM_PLANE_TYPE_OVERLAY;
 	int channel = mixer->cfg->vi_num + index;
 	struct sun8i_ui_layer *layer;
+	unsigned int plane_cnt;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
@@ -327,8 +336,10 @@ struct sun8i_ui_layer *sun8i_ui_layer_init_one(struct drm_device *drm,
 		return ERR_PTR(ret);
 	}
 
-	/* fixed zpos for now */
-	ret = drm_plane_create_zpos_immutable_property(&layer->plane, channel);
+	plane_cnt = mixer->cfg->ui_num + mixer->cfg->vi_num;
+
+	ret = drm_plane_create_zpos_property(&layer->plane, channel,
+					     0, plane_cnt - 1);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't add zpos property\n");
 		return ERR_PTR(ret);
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 5877f8ef5895..17e0d00cfd8a 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -21,7 +21,7 @@
 #include "sun8i_vi_scaler.h"
 
 static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable)
+				  int overlay, bool enable, unsigned int zpos)
 {
 	u32 val;
 
@@ -37,18 +37,24 @@ static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR_EN, val);
 
-	if (enable)
-		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel);
-	else
-		val = 0;
+	if (enable) {
+		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
 
-	regmap_update_bits(mixer->engine.regs,
-			   SUN8I_MIXER_BLEND_PIPE_CTL,
-			   SUN8I_MIXER_BLEND_PIPE_CTL_EN(channel), val);
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL, val, val);
+
+		val = channel << SUN8I_MIXER_BLEND_ROUTE_PIPE_SHIFT(zpos);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(zpos),
+				   val);
+	}
 }
 
 static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
-				       int overlay, struct drm_plane *plane)
+				       int overlay, struct drm_plane *plane,
+				       unsigned int zpos)
 {
 	struct drm_plane_state *state = plane->state;
 	const struct drm_format_info *format = state->fb->format;
@@ -130,10 +136,10 @@ static int sun8i_vi_layer_update_coord(struct sun8i_mixer *mixer, int channel,
 			 state->dst.x1, state->dst.y1);
 	DRM_DEBUG_DRIVER("Layer destination size W: %d H: %d\n", dst_w, dst_h);
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_COORD(channel),
+		     SUN8I_MIXER_BLEND_ATTR_COORD(zpos),
 		     SUN8I_MIXER_COORD(state->dst.x1, state->dst.y1));
 	regmap_write(mixer->engine.regs,
-		     SUN8I_MIXER_BLEND_ATTR_INSIZE(channel),
+		     SUN8I_MIXER_BLEND_ATTR_INSIZE(zpos),
 		     outsize);
 
 	return 0;
@@ -266,28 +272,30 @@ static void sun8i_vi_layer_atomic_disable(struct drm_plane *plane,
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false);
+	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false, 0);
 }
 
 static void sun8i_vi_layer_atomic_update(struct drm_plane *plane,
 					 struct drm_plane_state *old_state)
 {
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
+	unsigned int zpos = plane->state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_vi_layer_enable(mixer, layer->channel,
-				      layer->overlay, false);
+				      layer->overlay, false, 0);
 		return;
 	}
 
 	sun8i_vi_layer_update_coord(mixer, layer->channel,
-				    layer->overlay, plane);
+				    layer->overlay, plane, zpos);
 	sun8i_vi_layer_update_formats(mixer, layer->channel,
 				      layer->overlay, plane);
 	sun8i_vi_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
-	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, true);
+	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay,
+			      true, zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_vi_layer_helper_funcs = {
@@ -351,6 +359,7 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 					       int index)
 {
 	struct sun8i_vi_layer *layer;
+	unsigned int plane_cnt;
 	int ret;
 
 	layer = devm_kzalloc(drm->dev, sizeof(*layer), GFP_KERNEL);
@@ -368,8 +377,10 @@ struct sun8i_vi_layer *sun8i_vi_layer_init_one(struct drm_device *drm,
 		return ERR_PTR(ret);
 	}
 
-	/* fixed zpos for now */
-	ret = drm_plane_create_zpos_immutable_property(&layer->plane, index);
+	plane_cnt = mixer->cfg->ui_num + mixer->cfg->vi_num;
+
+	ret = drm_plane_create_zpos_property(&layer->plane, index,
+					     0, plane_cnt - 1);
 	if (ret) {
 		dev_err(drm->dev, "Couldn't add zpos property\n");
 		return ERR_PTR(ret);
-- 
cgit v1.2.3


From b7178ffe7eb86fb9d428801509a5bd54d3ba94da Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime.ripard@bootlin.com>
Date: Thu, 12 Jul 2018 10:08:18 +0200
Subject: drm/sun4i: tcon-top: Fix return type warning

When commit af11942ee44e ("drm/sun4i: tcon-top: Cleanup clock handling")
was merged, the error handling path of the of_property_match_string was
changed to take into account the fact that the returned value of that
function wasn't an error pointer but an error code.

Unfortunately, this introduced a warning since the now returned value is an
integer, while the sun8i_tcon_top_register_gate function should return an
error pointer.

Fix that by calling ERR_PTR.

Cc: Jernej Skrabec <jernej.skrabec@siol.net>
Cc: Chen-Yu Tsai <wens@csie.org>
Fixes: af11942ee44e ("drm/sun4i: tcon-top: Cleanup clock handling")
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Reported-by: kbuild test robot <lkp@intel.com>
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712080818.3571-1-maxime.ripard@bootlin.com
---
 drivers/gpu/drm/sun4i/sun8i_tcon_top.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
index 046f8dd66f90..55fe398d8290 100644
--- a/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
+++ b/drivers/gpu/drm/sun4i/sun8i_tcon_top.c
@@ -99,7 +99,7 @@ static struct clk_hw *sun8i_tcon_top_register_gate(struct device *dev,
 
 	index = of_property_match_string(dev->of_node, "clock-names", parent);
 	if (index < 0)
-		return index;
+		return ERR_PTR(index);
 
 	parent_name = of_clk_get_parent_name(dev->of_node, index);
 
-- 
cgit v1.2.3


From 2bae79d2d38f3dc50bfef81d3b4f7328b2883a17 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 12 Jul 2018 12:52:22 +0100
Subject: bpf: fix documentation for eBPF helpers

Minor formatting edits for eBPF helpers documentation, including blank
lines removal, fix of item list for return values in bpf_fib_lookup(),
and missing prefix on bpf_skb_load_bytes_relative().

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b7db3261c62d..6bcb287a888d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1826,7 +1826,7 @@ union bpf_attr {
  * 		A non-negative value equal to or less than *size* on success,
  * 		or a negative error in case of failure.
  *
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
  * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
  * 		it provides an easy way to load *len* bytes from *offset*
@@ -1877,7 +1877,7 @@ union bpf_attr {
  *		* < 0 if any input argument is invalid
  *		*   0 on success (packet is forwarded, nexthop neighbor exists)
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
- *		*     packet is not forwarded or needs assist from full stack
+ *		  packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2033,7 +2033,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
@@ -2053,7 +2052,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
-- 
cgit v1.2.3


From 9b8ca3795199f333269859b0c8393f810b9616a3 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 12 Jul 2018 12:52:23 +0100
Subject: tools: bpf: synchronise BPF UAPI header with tools

Update with latest changes from include/uapi/linux/bpf.h header.

Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 32 ++++++++++++++++++++++++--------
 1 file changed, 24 insertions(+), 8 deletions(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 59b19b6a40d7..6bcb287a888d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1826,7 +1826,7 @@ union bpf_attr {
  * 		A non-negative value equal to or less than *size* on success,
  * 		or a negative error in case of failure.
  *
- * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
+ * int bpf_skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header)
  * 	Description
  * 		This helper is similar to **bpf_skb_load_bytes**\ () in that
  * 		it provides an easy way to load *len* bytes from *offset*
@@ -1857,7 +1857,8 @@ union bpf_attr {
  *		is resolved), the nexthop address is returned in ipv4_dst
  *		or ipv6_dst based on family, smac is set to mac address of
  *		egress device, dmac is set to nexthop mac address, rt_metric
- *		is set to metric from route (IPv4/IPv6 only).
+ *		is set to metric from route (IPv4/IPv6 only), and ifindex
+ *		is set to the device index of the nexthop from the FIB lookup.
  *
  *             *plen* argument is the size of the passed in struct.
  *             *flags* argument can be a combination of one or more of the
@@ -1873,9 +1874,10 @@ union bpf_attr {
  *             *ctx* is either **struct xdp_md** for XDP programs or
  *             **struct sk_buff** tc cls_act programs.
  *     Return
- *             Egress device index on success, 0 if packet needs to continue
- *             up the stack for further processing or a negative error in case
- *             of failure.
+ *		* < 0 if any input argument is invalid
+ *		*   0 on success (packet is forwarded, nexthop neighbor exists)
+ *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
+ *		  packet is not forwarded or needs assist from full stack
  *
  * int bpf_sock_hash_update(struct bpf_sock_ops_kern *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
@@ -2031,7 +2033,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
@@ -2051,7 +2052,6 @@ union bpf_attr {
  *		This helper is only available is the kernel was compiled with
  *		the **CONFIG_BPF_LIRC_MODE2** configuration option set to
  *		"**y**".
- *
  *	Return
  *		0
  *
@@ -2612,6 +2612,18 @@ struct bpf_raw_tracepoint_args {
 #define BPF_FIB_LOOKUP_DIRECT  BIT(0)
 #define BPF_FIB_LOOKUP_OUTPUT  BIT(1)
 
+enum {
+	BPF_FIB_LKUP_RET_SUCCESS,      /* lookup successful */
+	BPF_FIB_LKUP_RET_BLACKHOLE,    /* dest is blackholed; can be dropped */
+	BPF_FIB_LKUP_RET_UNREACHABLE,  /* dest is unreachable; can be dropped */
+	BPF_FIB_LKUP_RET_PROHIBIT,     /* dest not allowed; can be dropped */
+	BPF_FIB_LKUP_RET_NOT_FWDED,    /* packet is not forwarded */
+	BPF_FIB_LKUP_RET_FWD_DISABLED, /* fwding is not enabled on ingress */
+	BPF_FIB_LKUP_RET_UNSUPP_LWT,   /* fwd requires encapsulation */
+	BPF_FIB_LKUP_RET_NO_NEIGH,     /* no neighbor entry for nh */
+	BPF_FIB_LKUP_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+};
+
 struct bpf_fib_lookup {
 	/* input:  network family for lookup (AF_INET, AF_INET6)
 	 * output: network family of egress nexthop
@@ -2625,7 +2637,11 @@ struct bpf_fib_lookup {
 
 	/* total length of packet from network header - used for MTU check */
 	__u16	tot_len;
-	__u32	ifindex;  /* L3 device index for lookup */
+
+	/* input: L3 device index for lookup
+	 * output: device index from FIB lookup
+	 */
+	__u32	ifindex;
 
 	union {
 		/* inputs to lookup */
-- 
cgit v1.2.3


From 86f7d85cec9e1dba735ac5bd4b751b1908fedf80 Mon Sep 17 00:00:00 2001
From: Quentin Monnet <quentin.monnet@netronome.com>
Date: Thu, 12 Jul 2018 12:52:24 +0100
Subject: tools: bpf: build and install man page for eBPF helpers from bpftool/

Provide a new Makefile.helpers in tools/bpf, in order to build and
install the man page for eBPF helpers. This Makefile is also included in
the one used to build bpftool documentation, so that it can be called
either on its own (cd tools/bpf && make -f Makefile.helpers) or from
bpftool directory (cd tools/bpf/bpftool && make doc, or
cd tools/bpf/bpftool/Documentation && make helpers).

Makefile.helpers is not added directly to bpftool to avoid changing its
Makefile too much (helpers are not 100% directly related with bpftool).
But the possibility to build the page from bpftool directory makes us
able to package the helpers man page with bpftool, and to install it
along with bpftool documentation, so that the doc for helpers becomes
easily available to developers through the "man" program.

Cc: linux-man@vger.kernel.org
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Quentin Monnet <quentin.monnet@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/Makefile.helpers               | 59 ++++++++++++++++++++++++++++++++
 tools/bpf/bpftool/Documentation/Makefile | 13 ++++---
 2 files changed, 67 insertions(+), 5 deletions(-)
 create mode 100644 tools/bpf/Makefile.helpers

diff --git a/tools/bpf/Makefile.helpers b/tools/bpf/Makefile.helpers
new file mode 100644
index 000000000000..c34fea77f39f
--- /dev/null
+++ b/tools/bpf/Makefile.helpers
@@ -0,0 +1,59 @@
+ifndef allow-override
+  include ../scripts/Makefile.include
+  include ../scripts/utilities.mak
+else
+  # Assume Makefile.helpers is being run from bpftool/Documentation
+  # subdirectory. Go up two more directories to fetch bpf.h header and
+  # associated script.
+  UP2DIR := ../../
+endif
+
+INSTALL ?= install
+RM ?= rm -f
+RMDIR ?= rmdir --ignore-fail-on-non-empty
+
+ifeq ($(V),1)
+  Q =
+else
+  Q = @
+endif
+
+prefix ?= /usr/local
+mandir ?= $(prefix)/man
+man7dir = $(mandir)/man7
+
+HELPERS_RST = bpf-helpers.rst
+MAN7_RST = $(HELPERS_RST)
+
+_DOC_MAN7 = $(patsubst %.rst,%.7,$(MAN7_RST))
+DOC_MAN7 = $(addprefix $(OUTPUT),$(_DOC_MAN7))
+
+helpers: man7
+man7: $(DOC_MAN7)
+
+RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
+
+$(OUTPUT)$(HELPERS_RST): $(UP2DIR)../../include/uapi/linux/bpf.h
+	$(QUIET_GEN)$(UP2DIR)../../scripts/bpf_helpers_doc.py --filename $< > $@
+
+$(OUTPUT)%.7: $(OUTPUT)%.rst
+ifndef RST2MAN_DEP
+	$(error "rst2man not found, but required to generate man pages")
+endif
+	$(QUIET_GEN)rst2man $< > $@
+
+helpers-clean:
+	$(call QUIET_CLEAN, eBPF_helpers-manpage)
+	$(Q)$(RM) $(DOC_MAN7) $(OUTPUT)$(HELPERS_RST)
+
+helpers-install: helpers
+	$(call QUIET_INSTALL, eBPF_helpers-manpage)
+	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man7dir)
+	$(Q)$(INSTALL) -m 644 $(DOC_MAN7) $(DESTDIR)$(man7dir)
+
+helpers-uninstall:
+	$(call QUIET_UNINST, eBPF_helpers-manpage)
+	$(Q)$(RM) $(addprefix $(DESTDIR)$(man7dir)/,$(_DOC_MAN7))
+	$(Q)$(RMDIR) $(DESTDIR)$(man7dir)
+
+.PHONY: helpers helpers-clean helpers-install helpers-uninstall
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index a9d47c1558bb..f7663a3e60c9 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -15,12 +15,15 @@ prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man8dir = $(mandir)/man8
 
-MAN8_RST = $(wildcard *.rst)
+# Load targets for building eBPF helpers man page.
+include ../../Makefile.helpers
+
+MAN8_RST = $(filter-out $(HELPERS_RST),$(wildcard *.rst))
 
 _DOC_MAN8 = $(patsubst %.rst,%.8,$(MAN8_RST))
 DOC_MAN8 = $(addprefix $(OUTPUT),$(_DOC_MAN8))
 
-man: man8
+man: man8 helpers
 man8: $(DOC_MAN8)
 
 RST2MAN_DEP := $(shell command -v rst2man 2>/dev/null)
@@ -31,16 +34,16 @@ ifndef RST2MAN_DEP
 endif
 	$(QUIET_GEN)rst2man $< > $@
 
-clean:
+clean: helpers-clean
 	$(call QUIET_CLEAN, Documentation)
 	$(Q)$(RM) $(DOC_MAN8)
 
-install: man
+install: man helpers-install
 	$(call QUIET_INSTALL, Documentation-man)
 	$(Q)$(INSTALL) -d -m 755 $(DESTDIR)$(man8dir)
 	$(Q)$(INSTALL) -m 644 $(DOC_MAN8) $(DESTDIR)$(man8dir)
 
-uninstall:
+uninstall: helpers-uninstall
 	$(call QUIET_UNINST, Documentation-man)
 	$(Q)$(RM) $(addprefix $(DESTDIR)$(man8dir)/,$(_DOC_MAN8))
 	$(Q)$(RMDIR) $(DESTDIR)$(man8dir)
-- 
cgit v1.2.3


From 77c56fd3c8cf5adcba9cffcc29ead295211bdae8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 9 Jul 2018 17:20:29 +0200
Subject: drm/tinydrm: add backlight dependency for ili9341
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This tinydrm driver fails to link without the backlight support:

drivers/gpu/drm/tinydrm/ili9341.o: In function `ili9341_probe':
ili9341.c:(.text+0x578): undefined reference to `devm_of_find_backlight'

Fixes: 3fa0e8f6f960 ("drm/tinydrm: new driver for ILI9341 display panels")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Noralf Trønnes <noralf@tronnes.org>
Signed-off-by: David Lechner <david@lechnology.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709152106.990066-1-arnd@arndb.de
---
 drivers/gpu/drm/tinydrm/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/tinydrm/Kconfig b/drivers/gpu/drm/tinydrm/Kconfig
index 7a8008b0783f..16f4b5c91f1b 100644
--- a/drivers/gpu/drm/tinydrm/Kconfig
+++ b/drivers/gpu/drm/tinydrm/Kconfig
@@ -23,6 +23,7 @@ config TINYDRM_ILI9225
 config TINYDRM_ILI9341
 	tristate "DRM support for ILI9341 display panels"
 	depends on DRM_TINYDRM && SPI
+	depends on BACKLIGHT_CLASS_DEVICE
 	select TINYDRM_MIPI_DBI
 	help
 	  DRM driver for the following Ilitek ILI9341 panels:
-- 
cgit v1.2.3


From a0a5ac3ce8fe6bf26694f49f9ba42ed859487424 Mon Sep 17 00:00:00 2001
From: Joshua Kinard <kumba@gentoo.org>
Date: Sat, 18 Nov 2017 22:29:56 -0500
Subject: MIPS: Fix delay slot bug in `atomic*_sub_if_positive' for
 R10000_LLSC_WAR

This patch fixes an old bug in MIPS ll/sc atomics, in the
`atomic_sub_if_positive' and `atomic64_sub_if_positive' functions, for
the R10000_LLSC_WAR case where the result of the subu/dsubu instruction
would potentially not be made available to the sc/scd instruction due
to being in the delay-slot of the branch-likely (beqzl) instruction.

This also removes the need for the `noreorder' directive, allowing GAS
to use delay slot scheduling as needed.

The same fix is also applied to the standard branch (beqz) case in
preparation for a follow-up patch that will cleanup/merge the
R10000_LLSC_WAR and non-R10K sections together.

Signed-off-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Tested-by: Joshua Kinard <kumba@gentoo.org>
Patchwork: https://patchwork.linux-mips.org/patch/17735/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <james.hogan@mips.com>
Cc: "Maciej W. Rozycki" <macro@mips.com>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/atomic.h | 32 ++++++++++++--------------------
 1 file changed, 12 insertions(+), 20 deletions(-)

diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 0ab176bdb8e8..0babf2775d8e 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -225,12 +225,10 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"	.set	arch=r4000				\n"
 		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
 		"	subu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	sc	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqzl	%0, 1b					\n"
-		"	 subu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	sc	%1, %2					\n"
+		"	beqzl	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -244,12 +242,10 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
 		"	subu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	sc	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqz	%0, 1b					\n"
-		"	 subu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	sc	%1, %2					\n"
+		"	beqz	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -570,12 +566,10 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"	.set	arch=r4000				\n"
 		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
 		"	dsubu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	scd	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqzl	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	scd	%1, %2					\n"
+		"	beqzl	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -589,12 +583,10 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"	.set	"MIPS_ISA_LEVEL"			\n"
 		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
 		"	dsubu	%0, %1, %3				\n"
+		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
-		"	scd	%0, %2					\n"
-		"	.set	noreorder				\n"
-		"	beqz	%0, 1b					\n"
-		"	 dsubu	%0, %1, %3				\n"
-		"	.set	reorder					\n"
+		"	scd	%1, %2					\n"
+		"	beqz	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-- 
cgit v1.2.3


From 4936084c2ee227524c242d790a9fbad7650320c7 Mon Sep 17 00:00:00 2001
From: Joshua Kinard <kumba@gentoo.org>
Date: Sat, 18 Nov 2017 23:00:51 -0500
Subject: MIPS: Cleanup R10000_LLSC_WAR logic in atomic.h

This patch reduces down the conditionals in MIPS atomic code that deal
with a silicon bug in early R10000 cpus that required a workaround of
a branch-likely instruction following a store-conditional in order to
to guarantee the whole ll/sc sequence is atomic.  As the only real
difference is a branch-likely instruction (beqzl) over a standard
branch (beqz), the conditional is reduced down to a single preprocessor
check at the top to pick the required instruction.

This requires writing the uses in assembler, thus we discard the
non-R10000 case that uses a mixture of a C do...while loop with
embedded assembler that was added back in commit 7837314d141c ("MIPS:
Get rid of branches to .subsections.").  A note found in the git log
for commit 5999eca25c1f ("[MIPS] Improve branch prediction in ll/sc
atomic operations.") is also addressed.

The macro definition for the branch instruction and the code comment
derives from a patch sent in earlier by Paul Burton for various cmpxchg
cleanups.

[paul.burton@mips.com:
  - Minor whitespace fix for checkpatch.]

Signed-off-by: Joshua Kinard <kumba@gentoo.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/17736/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <james.hogan@mips.com>
Cc: "Maciej W. Rozycki" <macro@mips.com>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/atomic.h | 179 ++++++++---------------------------------
 1 file changed, 32 insertions(+), 147 deletions(-)

diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 0babf2775d8e..3ccea238be2d 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -22,6 +22,17 @@
 #include <asm/cmpxchg.h>
 #include <asm/war.h>
 
+/*
+ * Using a branch-likely instruction to check the result of an sc instruction
+ * works around a bug present in R10000 CPUs prior to revision 3.0 that could
+ * cause ll-sc sequences to execute non-atomically.
+ */
+#if R10000_LLSC_WAR
+# define __scbeqz "beqzl"
+#else
+# define __scbeqz "beqz"
+#endif
+
 #define ATOMIC_INIT(i)	  { (i) }
 
 /*
@@ -44,31 +55,18 @@
 #define ATOMIC_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 {									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%0, %1		# atomic_" #op "	\n"   \
 		"	" #asm_op " %0, %2				\n"   \
 		"	sc	%0, %1					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%0, %1		# atomic_" #op "\n"   \
-			"	" #asm_op " %0, %2			\n"   \
-			"	sc	%0, %1				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)  \
-			: "Ir" (i));					      \
-		} while (unlikely(!temp));				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -83,36 +81,20 @@ static __inline__ int atomic_##op##_return_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%1, %2		# atomic_" #op "_return	\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	sc	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%1, %2	# atomic_" #op "_return	\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	sc	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i));					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp; result c_op i;				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -131,36 +113,20 @@ static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
 {									      \
 	int result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		int temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	ll	%1, %2		# atomic_fetch_" #op "	\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	sc	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	move	%0, %1					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		int temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	ll	%1, %2	# atomic_fetch_" #op "	\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	sc	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i));					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp;						      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -218,24 +184,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 
 	smp_mb__before_llsc();
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		int temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	ll	%1, %2		# atomic_sub_if_positive\n"
-		"	subu	%0, %1, %3				\n"
-		"	move	%1, %0					\n"
-		"	bltz	%0, 1f					\n"
-		"	sc	%1, %2					\n"
-		"	beqzl	%1, 1b					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "+" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
-		: "memory");
-	} else if (kernel_uses_llsc) {
+	if (kernel_uses_llsc) {
 		int temp;
 
 		__asm__ __volatile__(
@@ -245,7 +194,7 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
 		"	sc	%1, %2					\n"
-		"	beqz	%1, 1b					\n"
+		"\t" __scbeqz "	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
@@ -382,31 +331,18 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 #define ATOMIC64_OP(op, c_op, asm_op)					      \
 static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 {									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%0, %1		# atomic64_" #op "	\n"   \
 		"	" #asm_op " %0, %2				\n"   \
 		"	scd	%0, %1					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)	      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%0, %1		# atomic64_" #op "\n" \
-			"	" #asm_op " %0, %2			\n"   \
-			"	scd	%0, %1				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
-			: "Ir" (i));					      \
-		} while (unlikely(!temp));				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -421,37 +357,20 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 {									      \
 	long result;							      \
 									      \
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+	if (kernel_uses_llsc) {						      \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%1, %2		# atomic64_" #op "_return\n"  \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	scd	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%1, %2	# atomic64_" #op "_return\n"  \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	scd	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
-			: "memory");					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp; result c_op i;				      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -474,33 +393,16 @@ static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
 		long temp;						      \
 									      \
 		__asm__ __volatile__(					      \
-		"	.set	arch=r4000				\n"   \
+		"	.set	"MIPS_ISA_LEVEL"			\n"   \
 		"1:	lld	%1, %2		# atomic64_fetch_" #op "\n"   \
 		"	" #asm_op " %0, %1, %3				\n"   \
 		"	scd	%0, %2					\n"   \
-		"	beqzl	%0, 1b					\n"   \
+		"\t" __scbeqz "	%0, 1b					\n"   \
 		"	move	%0, %1					\n"   \
 		"	.set	mips0					\n"   \
 		: "=&r" (result), "=&r" (temp),				      \
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
 		: "Ir" (i));						      \
-	} else if (kernel_uses_llsc) {					      \
-		long temp;						      \
-									      \
-		do {							      \
-			__asm__ __volatile__(				      \
-			"	.set	"MIPS_ISA_LEVEL"		\n"   \
-			"	lld	%1, %2	# atomic64_fetch_" #op "\n"   \
-			"	" #asm_op " %0, %1, %3			\n"   \
-			"	scd	%0, %2				\n"   \
-			"	.set	mips0				\n"   \
-			: "=&r" (result), "=&r" (temp),			      \
-			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
-			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
-			: "memory");					      \
-		} while (unlikely(!result));				      \
-									      \
-		result = temp;						      \
 	} else {							      \
 		unsigned long flags;					      \
 									      \
@@ -559,24 +461,7 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 
 	smp_mb__before_llsc();
 
-	if (kernel_uses_llsc && R10000_LLSC_WAR) {
-		long temp;
-
-		__asm__ __volatile__(
-		"	.set	arch=r4000				\n"
-		"1:	lld	%1, %2		# atomic64_sub_if_positive\n"
-		"	dsubu	%0, %1, %3				\n"
-		"	move	%1, %0					\n"
-		"	bltz	%0, 1f					\n"
-		"	scd	%1, %2					\n"
-		"	beqzl	%1, 1b					\n"
-		"1:							\n"
-		"	.set	mips0					\n"
-		: "=&r" (result), "=&r" (temp),
-		  "=" GCC_OFF_SMALL_ASM() (v->counter)
-		: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)
-		: "memory");
-	} else if (kernel_uses_llsc) {
+	if (kernel_uses_llsc) {
 		long temp;
 
 		__asm__ __volatile__(
@@ -586,7 +471,7 @@ static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
 		"	move	%1, %0					\n"
 		"	bltz	%0, 1f					\n"
 		"	scd	%1, %2					\n"
-		"	beqz	%1, 1b					\n"
+		"\t" __scbeqz "	%1, 1b					\n"
 		"1:							\n"
 		"	.set	mips0					\n"
 		: "=&r" (result), "=&r" (temp),
-- 
cgit v1.2.3


From d449ceb11b3884770c06e71cf15edc9f3b4c9b05 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:31:31 +0100
Subject: ARM: net: bpf: enumerate the JIT scratch stack layout

Enumerate the contents of the JIT scratch stack layout used for storing
some of the JITs 64-bit registers, tail call counter and AX register.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 59 +++++++++++++++++++++++++++++++++--------------
 1 file changed, 42 insertions(+), 17 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index f6a62ae44a65..f2e6ffe57788 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -72,7 +72,38 @@
 #define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
 #define CALLEE_POP_MASK  (CALLEE_MASK | 1 << ARM_PC)
 
-#define STACK_OFFSET(k)	(k)
+enum {
+	/* Stack layout - these are offsets from (top of stack - 4) */
+	BPF_R2_HI,
+	BPF_R2_LO,
+	BPF_R3_HI,
+	BPF_R3_LO,
+	BPF_R4_HI,
+	BPF_R4_LO,
+	BPF_R5_HI,
+	BPF_R5_LO,
+	BPF_R7_HI,
+	BPF_R7_LO,
+	BPF_R8_HI,
+	BPF_R8_LO,
+	BPF_R9_HI,
+	BPF_R9_LO,
+	BPF_FP_HI,
+	BPF_FP_LO,
+	BPF_TC_HI,
+	BPF_TC_LO,
+	BPF_AX_HI,
+	BPF_AX_LO,
+	/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
+	 * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
+	 * BPF_REG_FP and Tail call counts.
+	 */
+	BPF_JIT_SCRATCH_REGS,
+};
+
+#define STACK_OFFSET(k)	((k) * 4)
+#define SCRATCH_SIZE	(BPF_JIT_SCRATCH_REGS * 4)
+
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)	/* TEMP Register 1 */
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)	/* TEMP Register 2 */
 #define TCALL_CNT	(MAX_BPF_JIT_REG + 2)	/* Tail Call Count */
@@ -100,29 +131,29 @@ static const u8 bpf2a32[][2] = {
 	/* arguments from eBPF program to in-kernel function */
 	[BPF_REG_1] = {ARM_R3, ARM_R2},
 	/* Stored on stack scratch space */
-	[BPF_REG_2] = {STACK_OFFSET(0), STACK_OFFSET(4)},
-	[BPF_REG_3] = {STACK_OFFSET(8), STACK_OFFSET(12)},
-	[BPF_REG_4] = {STACK_OFFSET(16), STACK_OFFSET(20)},
-	[BPF_REG_5] = {STACK_OFFSET(24), STACK_OFFSET(28)},
+	[BPF_REG_2] = {STACK_OFFSET(BPF_R2_HI), STACK_OFFSET(BPF_R2_LO)},
+	[BPF_REG_3] = {STACK_OFFSET(BPF_R3_HI), STACK_OFFSET(BPF_R3_LO)},
+	[BPF_REG_4] = {STACK_OFFSET(BPF_R4_HI), STACK_OFFSET(BPF_R4_LO)},
+	[BPF_REG_5] = {STACK_OFFSET(BPF_R5_HI), STACK_OFFSET(BPF_R5_LO)},
 	/* callee saved registers that in-kernel function will preserve */
 	[BPF_REG_6] = {ARM_R5, ARM_R4},
 	/* Stored on stack scratch space */
-	[BPF_REG_7] = {STACK_OFFSET(32), STACK_OFFSET(36)},
-	[BPF_REG_8] = {STACK_OFFSET(40), STACK_OFFSET(44)},
-	[BPF_REG_9] = {STACK_OFFSET(48), STACK_OFFSET(52)},
+	[BPF_REG_7] = {STACK_OFFSET(BPF_R7_HI), STACK_OFFSET(BPF_R7_LO)},
+	[BPF_REG_8] = {STACK_OFFSET(BPF_R8_HI), STACK_OFFSET(BPF_R8_LO)},
+	[BPF_REG_9] = {STACK_OFFSET(BPF_R9_HI), STACK_OFFSET(BPF_R9_LO)},
 	/* Read only Frame Pointer to access Stack */
-	[BPF_REG_FP] = {STACK_OFFSET(56), STACK_OFFSET(60)},
+	[BPF_REG_FP] = {STACK_OFFSET(BPF_FP_HI), STACK_OFFSET(BPF_FP_LO)},
 	/* Temporary Register for internal BPF JIT, can be used
 	 * for constant blindings and others.
 	 */
 	[TMP_REG_1] = {ARM_R7, ARM_R6},
 	[TMP_REG_2] = {ARM_R10, ARM_R8},
 	/* Tail call count. Stored on stack scratch space. */
-	[TCALL_CNT] = {STACK_OFFSET(64), STACK_OFFSET(68)},
+	[TCALL_CNT] = {STACK_OFFSET(BPF_TC_HI), STACK_OFFSET(BPF_TC_LO)},
 	/* temporary register for blinding constants.
 	 * Stored on stack scratch space.
 	 */
-	[BPF_REG_AX] = {STACK_OFFSET(72), STACK_OFFSET(76)},
+	[BPF_REG_AX] = {STACK_OFFSET(BPF_AX_HI), STACK_OFFSET(BPF_AX_LO)},
 };
 
 #define	dst_lo	dst[1]
@@ -227,12 +258,6 @@ static void jit_fill_hole(void *area, unsigned int size)
 #define STACK_ALIGNMENT	4
 #endif
 
-/* Stack space for BPF_REG_2, BPF_REG_3, BPF_REG_4,
- * BPF_REG_5, BPF_REG_7, BPF_REG_8, BPF_REG_9,
- * BPF_REG_FP and Tail call counts.
- */
-#define SCRATCH_SIZE 80
-
 /* total stack size used in JITed code */
 #define _STACK_SIZE	(ctx->prog->aux->stack_depth + SCRATCH_SIZE)
 #define STACK_SIZE	ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
-- 
cgit v1.2.3


From a8ef95a034233190b1dd73ff03472ff0f7f4fbdf Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:31:36 +0100
Subject: ARM: net: bpf: provide load/store ops with negative immediates

Provide a set of load/store opcode generators that work with negative
immediates as well as positive ones.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 28 ++++++++++++++++++++++++++++
 arch/arm/net/bpf_jit_32.h | 35 +++++++++++++----------------------
 2 files changed, 41 insertions(+), 22 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index f2e6ffe57788..c81da1a50834 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -239,6 +239,34 @@ static int16_t imm8m(u32 x)
 	return -1;
 }
 
+static u32 arm_bpf_ldst_imm12(u32 op, u8 rt, u8 rn, s16 imm12)
+{
+	op |= rt << 12 | rn << 16;
+	if (imm12 >= 0)
+		op |= ARM_INST_LDST__U;
+	else
+		imm12 = -imm12;
+	return op | (imm12 & 0xfff);
+}
+
+static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
+{
+	op |= rt << 12 | rn << 16;
+	if (imm8 >= 0)
+		op |= ARM_INST_LDST__U;
+	else
+		imm8 = -imm8;
+	return op | (imm8 & 0xf0) << 4 | (imm8 & 0x0f);
+}
+
+#define ARM_LDR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_LDR_I, rt, rn, off)
+#define ARM_LDRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_LDRB_I, rt, rn, off)
+#define ARM_LDRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off)
+
+#define ARM_STR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off)
+#define ARM_STRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off)
+#define ARM_STRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_STRH_I, rt, rn, off)
+
 /*
  * Initializes the JIT space with undefined instructions.
  */
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index d5cf5f6208aa..c55bc39d3e22 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -77,11 +77,12 @@
 #define ARM_INST_EOR_R		0x00200000
 #define ARM_INST_EOR_I		0x02200000
 
-#define ARM_INST_LDRB_I		0x05d00000
+#define ARM_INST_LDST__U	0x00800000
+#define ARM_INST_LDRB_I		0x05500000
 #define ARM_INST_LDRB_R		0x07d00000
-#define ARM_INST_LDRH_I		0x01d000b0
+#define ARM_INST_LDRH_I		0x015000b0
 #define ARM_INST_LDRH_R		0x019000b0
-#define ARM_INST_LDR_I		0x05900000
+#define ARM_INST_LDR_I		0x05100000
 #define ARM_INST_LDR_R		0x07900000
 
 #define ARM_INST_LDM		0x08900000
@@ -124,9 +125,9 @@
 #define ARM_INST_SBC_R		0x00c00000
 #define ARM_INST_SBCS_R		0x00d00000
 
-#define ARM_INST_STR_I		0x05800000
-#define ARM_INST_STRB_I		0x05c00000
-#define ARM_INST_STRH_I		0x01c000b0
+#define ARM_INST_STR_I		0x05000000
+#define ARM_INST_STRB_I		0x05400000
+#define ARM_INST_STRH_I		0x014000b0
 
 #define ARM_INST_TST_R		0x01100000
 #define ARM_INST_TST_I		0x03100000
@@ -183,17 +184,14 @@
 #define ARM_EOR_R(rd, rn, rm)	_AL3_R(ARM_INST_EOR, rd, rn, rm)
 #define ARM_EOR_I(rd, rn, imm)	_AL3_I(ARM_INST_EOR, rd, rn, imm)
 
-#define ARM_LDR_I(rt, rn, off)	(ARM_INST_LDR_I | (rt) << 12 | (rn) << 16 \
-				 | ((off) & 0xfff))
-#define ARM_LDR_R(rt, rn, rm)	(ARM_INST_LDR_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDR_R(rt, rn, rm)	(ARM_INST_LDR_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
-#define ARM_LDRB_I(rt, rn, off)	(ARM_INST_LDRB_I | (rt) << 12 | (rn) << 16 \
-				 | (off))
-#define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
-#define ARM_LDRH_I(rt, rn, off)	(ARM_INST_LDRH_I | (rt) << 12 | (rn) << 16 \
-				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
-#define ARM_LDRH_R(rt, rn, rm)	(ARM_INST_LDRH_R | (rt) << 12 | (rn) << 16 \
+#define ARM_LDRH_R(rt, rn, rm)	(ARM_INST_LDRH_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
 
 #define ARM_LDM(rn, regs)	(ARM_INST_LDM | (rn) << 16 | (regs))
@@ -254,13 +252,6 @@
 #define ARM_SUBS_I(rd, rn, imm)	_AL3_I(ARM_INST_SUBS, rd, rn, imm)
 #define ARM_SBC_I(rd, rn, imm)	_AL3_I(ARM_INST_SBC, rd, rn, imm)
 
-#define ARM_STR_I(rt, rn, off)	(ARM_INST_STR_I | (rt) << 12 | (rn) << 16 \
-				 | ((off) & 0xfff))
-#define ARM_STRH_I(rt, rn, off)	(ARM_INST_STRH_I | (rt) << 12 | (rn) << 16 \
-				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
-#define ARM_STRB_I(rt, rn, off)	(ARM_INST_STRB_I | (rt) << 12 | (rn) << 16 \
-				 | (((off) & 0xf0) << 4) | ((off) & 0xf))
-
 #define ARM_TST_R(rn, rm)	_AL3_R(ARM_INST_TST, 0, rn, rm)
 #define ARM_TST_I(rn, imm)	_AL3_I(ARM_INST_TST, 0, rn, imm)
 
-- 
cgit v1.2.3


From 1c35ba122d4a4eb32c3f8d63a445c1ebfd66d7bc Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:31:41 +0100
Subject: ARM: net: bpf: use negative numbers for stacked registers

Use negative numbers for eBPF registers that live on the stack.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 200 +++++++++++++++++++++++-----------------------
 1 file changed, 102 insertions(+), 98 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index c81da1a50834..69bf7ab18bf9 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -101,7 +101,11 @@ enum {
 	BPF_JIT_SCRATCH_REGS,
 };
 
-#define STACK_OFFSET(k)	((k) * 4)
+/*
+ * Negative "register" values indicate the register is stored on the stack
+ * and are the offset from the top of the eBPF JIT scratch space.
+ */
+#define STACK_OFFSET(k)	(-4 - (k) * 4)
 #define SCRATCH_SIZE	(BPF_JIT_SCRATCH_REGS * 4)
 
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)	/* TEMP Register 1 */
@@ -125,7 +129,7 @@ enum {
  * scratch memory space and we have to build eBPF 64 bit register from those.
  *
  */
-static const u8 bpf2a32[][2] = {
+static const s8 bpf2a32[][2] = {
 	/* return value from in-kernel function, and exit value from eBPF */
 	[BPF_REG_0] = {ARM_R1, ARM_R0},
 	/* arguments from eBPF program to in-kernel function */
@@ -291,7 +295,7 @@ static void jit_fill_hole(void *area, unsigned int size)
 #define STACK_SIZE	ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
 
 /* Get the offset of eBPF REGISTERs stored on scratch space. */
-#define STACK_VAR(off) (STACK_SIZE - off)
+#define STACK_VAR(off) (STACK_SIZE + (off))
 
 #if __LINUX_ARM_ARCH__ < 7
 
@@ -408,7 +412,7 @@ static inline int epilogue_offset(const struct jit_ctx *ctx)
 
 static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
 
 #if __LINUX_ARM_ARCH__ == 7
 	if (elf_hwcap & HWCAP_IDIVA) {
@@ -470,10 +474,10 @@ static inline bool is_on_stack(u8 bpf_reg)
 	return false;
 }
 
-static inline void emit_a32_mov_i(const u8 dst, const u32 val,
+static inline void emit_a32_mov_i(const s8 dst, const u32 val,
 				  bool dstk, struct jit_ctx *ctx)
 {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
 
 	if (dstk) {
 		emit_mov_i(tmp[1], val, ctx);
@@ -484,7 +488,7 @@ static inline void emit_a32_mov_i(const u8 dst, const u32 val,
 }
 
 /* Sign extended move */
-static inline void emit_a32_mov_i64(const bool is64, const u8 dst[],
+static inline void emit_a32_mov_i64(const bool is64, const s8 dst[],
 				  const u32 val, bool dstk,
 				  struct jit_ctx *ctx) {
 	u32 hi = 0;
@@ -574,12 +578,12 @@ static inline void emit_alu_r(const u8 dst, const u8 src, const bool is64,
 /* ALU operation (32 bit)
  * dst = dst (op) src
  */
-static inline void emit_a32_alu_r(const u8 dst, const u8 src,
+static inline void emit_a32_alu_r(const s8 dst, const s8 src,
 				  bool dstk, bool sstk,
 				  struct jit_ctx *ctx, const bool is64,
 				  const bool hi, const u8 op) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rn = sstk ? tmp[1] : src;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rn = sstk ? tmp[1] : src;
 
 	if (sstk)
 		emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx);
@@ -595,8 +599,8 @@ static inline void emit_a32_alu_r(const u8 dst, const u8 src,
 }
 
 /* ALU operation (64 bit) */
-static inline void emit_a32_alu_r64(const bool is64, const u8 dst[],
-				  const u8 src[], bool dstk,
+static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
+				  const s8 src[], bool dstk,
 				  bool sstk, struct jit_ctx *ctx,
 				  const u8 op) {
 	emit_a32_alu_r(dst_lo, src_lo, dstk, sstk, ctx, is64, false, op);
@@ -607,11 +611,11 @@ static inline void emit_a32_alu_r64(const bool is64, const u8 dst[],
 }
 
 /* dst = imm (4 bytes)*/
-static inline void emit_a32_mov_r(const u8 dst, const u8 src,
+static inline void emit_a32_mov_r(const s8 dst, const s8 src,
 				  bool dstk, bool sstk,
 				  struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rt = sstk ? tmp[0] : src;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rt = sstk ? tmp[0] : src;
 
 	if (sstk)
 		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx);
@@ -622,8 +626,8 @@ static inline void emit_a32_mov_r(const u8 dst, const u8 src,
 }
 
 /* dst = src */
-static inline void emit_a32_mov_r64(const bool is64, const u8 dst[],
-				  const u8 src[], bool dstk,
+static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
+				  const s8 src[], bool dstk,
 				  bool sstk, struct jit_ctx *ctx) {
 	emit_a32_mov_r(dst_lo, src_lo, dstk, sstk, ctx);
 	if (is64) {
@@ -636,10 +640,10 @@ static inline void emit_a32_mov_r64(const bool is64, const u8 dst[],
 }
 
 /* Shift operations */
-static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk,
+static inline void emit_a32_alu_i(const s8 dst, const u32 val, bool dstk,
 				struct jit_ctx *ctx, const u8 op) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[0] : dst;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rd = dstk ? tmp[0] : dst;
 
 	if (dstk)
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
@@ -662,11 +666,11 @@ static inline void emit_a32_alu_i(const u8 dst, const u32 val, bool dstk,
 }
 
 /* dst = ~dst (64 bit) */
-static inline void emit_a32_neg64(const u8 dst[], bool dstk,
+static inline void emit_a32_neg64(const s8 dst[], bool dstk,
 				struct jit_ctx *ctx){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[1] : dst[1];
-	u8 rm = dstk ? tmp[0] : dst[0];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rd = dstk ? tmp[1] : dst[1];
+	s8 rm = dstk ? tmp[0] : dst[0];
 
 	/* Setup Operand */
 	if (dstk) {
@@ -685,15 +689,15 @@ static inline void emit_a32_neg64(const u8 dst[], bool dstk,
 }
 
 /* dst = dst << src */
-static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
+static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[], bool dstk,
 				    bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 
 	/* Setup Operands */
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rt = sstk ? tmp2[1] : src_lo;
+	s8 rd = dstk ? tmp[1] : dst_lo;
+	s8 rm = dstk ? tmp[0] : dst_hi;
 
 	if (sstk)
 		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
@@ -720,14 +724,14 @@ static inline void emit_a32_lsh_r64(const u8 dst[], const u8 src[], bool dstk,
 }
 
 /* dst = dst >> src (signed)*/
-static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
+static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[], bool dstk,
 				    bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup Operands */
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rt = sstk ? tmp2[1] : src_lo;
+	s8 rd = dstk ? tmp[1] : dst_lo;
+	s8 rm = dstk ? tmp[0] : dst_hi;
 
 	if (sstk)
 		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
@@ -754,14 +758,14 @@ static inline void emit_a32_arsh_r64(const u8 dst[], const u8 src[], bool dstk,
 }
 
 /* dst = dst >> src */
-static inline void emit_a32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
+static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[], bool dstk,
 				     bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup Operands */
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rt = sstk ? tmp2[1] : src_lo;
+	s8 rd = dstk ? tmp[1] : dst_lo;
+	s8 rm = dstk ? tmp[0] : dst_hi;
 
 	if (sstk)
 		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
@@ -787,13 +791,13 @@ static inline void emit_a32_rsh_r64(const u8 dst[], const u8 src[], bool dstk,
 }
 
 /* dst = dst << val */
-static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_lsh_i64(const s8 dst[], bool dstk,
 				     const u32 val, struct jit_ctx *ctx){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup operands */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rd = dstk ? tmp[1] : dst_lo;
+	s8 rm = dstk ? tmp[0] : dst_hi;
 
 	if (dstk) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
@@ -820,13 +824,13 @@ static inline void emit_a32_lsh_i64(const u8 dst[], bool dstk,
 }
 
 /* dst = dst >> val */
-static inline void emit_a32_rsh_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_rsh_i64(const s8 dst[], bool dstk,
 				    const u32 val, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup operands */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rd = dstk ? tmp[1] : dst_lo;
+	s8 rm = dstk ? tmp[0] : dst_hi;
 
 	if (dstk) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
@@ -853,13 +857,13 @@ static inline void emit_a32_rsh_i64(const u8 dst[], bool dstk,
 }
 
 /* dst = dst >> val (signed) */
-static inline void emit_a32_arsh_i64(const u8 dst[], bool dstk,
+static inline void emit_a32_arsh_i64(const s8 dst[], bool dstk,
 				     const u32 val, struct jit_ctx *ctx){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	 /* Setup operands */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rd = dstk ? tmp[1] : dst_lo;
+	s8 rm = dstk ? tmp[0] : dst_hi;
 
 	if (dstk) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
@@ -885,15 +889,15 @@ static inline void emit_a32_arsh_i64(const u8 dst[], bool dstk,
 	}
 }
 
-static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
+static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[], bool dstk,
 				    bool sstk, struct jit_ctx *ctx) {
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup operands for multiplication */
-	u8 rd = dstk ? tmp[1] : dst_lo;
-	u8 rm = dstk ? tmp[0] : dst_hi;
-	u8 rt = sstk ? tmp2[1] : src_lo;
-	u8 rn = sstk ? tmp2[0] : src_hi;
+	s8 rd = dstk ? tmp[1] : dst_lo;
+	s8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rt = sstk ? tmp2[1] : src_lo;
+	s8 rn = sstk ? tmp2[0] : src_hi;
 
 	if (dstk) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
@@ -920,10 +924,10 @@ static inline void emit_a32_mul_r64(const u8 dst[], const u8 src[], bool dstk,
 }
 
 /* *(size *)(dst + off) = src */
-static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
+static inline void emit_str_r(const s8 dst, const s8 src, bool dstk,
 			      const s32 off, struct jit_ctx *ctx, const u8 sz){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	u8 rd = dstk ? tmp[1] : dst;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s8 rd = dstk ? tmp[1] : dst;
 
 	if (dstk)
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
@@ -949,11 +953,11 @@ static inline void emit_str_r(const u8 dst, const u8 src, bool dstk,
 }
 
 /* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const u8 dst[], const u8 src, bool dstk,
+static inline void emit_ldx_r(const s8 dst[], const s8 src, bool dstk,
 			      s32 off, struct jit_ctx *ctx, const u8 sz){
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *rd = dstk ? tmp : dst;
-	u8 rm = src;
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rd = dstk ? tmp : dst;
+	s8 rm = src;
 	s32 off_max;
 
 	if (sz == BPF_H)
@@ -1034,11 +1038,11 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 {
 
 	/* bpf_tail_call(void *prog_ctx, struct bpf_array *array, u64 index) */
-	const u8 *r2 = bpf2a32[BPF_REG_2];
-	const u8 *r3 = bpf2a32[BPF_REG_3];
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
-	const u8 *tcc = bpf2a32[TCALL_CNT];
+	const s8 *r2 = bpf2a32[BPF_REG_2];
+	const s8 *r3 = bpf2a32[BPF_REG_3];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tcc = bpf2a32[TCALL_CNT];
 	const int idx0 = ctx->idx;
 #define cur_offset (ctx->idx - idx0)
 #define jmp_offset (out_offset - (cur_offset) - 2)
@@ -1112,7 +1116,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 {
 #if __LINUX_ARM_ARCH__ < 6
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 
 	emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
 	emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 8), ctx);
@@ -1127,7 +1131,7 @@ static inline void emit_rev16(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 {
 #if __LINUX_ARM_ARCH__ < 6
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 
 	emit(ARM_AND_I(tmp2[1], rn, 0xff), ctx);
 	emit(ARM_MOV_SI(tmp2[0], rn, SRTYPE_LSR, 24), ctx);
@@ -1147,10 +1151,10 @@ static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 }
 
 // push the scratch stack register on top of the stack
-static inline void emit_push_r64(const u8 src[], const u8 shift,
+static inline void emit_push_r64(const s8 src[], const u8 shift,
 		struct jit_ctx *ctx)
 {
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	u16 reg_set = 0;
 
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(src[1]+shift)), ctx);
@@ -1162,13 +1166,13 @@ static inline void emit_push_r64(const u8 src[], const u8 shift,
 
 static void build_prologue(struct jit_ctx *ctx)
 {
-	const u8 r0 = bpf2a32[BPF_REG_0][1];
-	const u8 r2 = bpf2a32[BPF_REG_1][1];
-	const u8 r3 = bpf2a32[BPF_REG_1][0];
-	const u8 r4 = bpf2a32[BPF_REG_6][1];
-	const u8 fplo = bpf2a32[BPF_REG_FP][1];
-	const u8 fphi = bpf2a32[BPF_REG_FP][0];
-	const u8 *tcc = bpf2a32[TCALL_CNT];
+	const s8 r0 = bpf2a32[BPF_REG_0][1];
+	const s8 r2 = bpf2a32[BPF_REG_1][1];
+	const s8 r3 = bpf2a32[BPF_REG_1][0];
+	const s8 r4 = bpf2a32[BPF_REG_6][1];
+	const s8 fplo = bpf2a32[BPF_REG_FP][1];
+	const s8 fphi = bpf2a32[BPF_REG_FP][0];
+	const s8 *tcc = bpf2a32[TCALL_CNT];
 
 	/* Save callee saved registers. */
 #ifdef CONFIG_FRAME_POINTER
@@ -1231,17 +1235,17 @@ static void build_epilogue(struct jit_ctx *ctx)
 static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 {
 	const u8 code = insn->code;
-	const u8 *dst = bpf2a32[insn->dst_reg];
-	const u8 *src = bpf2a32[insn->src_reg];
-	const u8 *tmp = bpf2a32[TMP_REG_1];
-	const u8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *dst = bpf2a32[insn->dst_reg];
+	const s8 *src = bpf2a32[insn->src_reg];
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	const s16 off = insn->off;
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
 	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
 	const bool dstk = is_on_stack(insn->dst_reg);
 	const bool sstk = is_on_stack(insn->src_reg);
-	u8 rd, rt, rm, rn;
+	s8 rd, rt, rm, rn;
 	s32 jmp_offset;
 
 #define check_imm(bits, imm) do {				\
@@ -1672,12 +1676,12 @@ go_jmp:
 	/* function call */
 	case BPF_JMP | BPF_CALL:
 	{
-		const u8 *r0 = bpf2a32[BPF_REG_0];
-		const u8 *r1 = bpf2a32[BPF_REG_1];
-		const u8 *r2 = bpf2a32[BPF_REG_2];
-		const u8 *r3 = bpf2a32[BPF_REG_3];
-		const u8 *r4 = bpf2a32[BPF_REG_4];
-		const u8 *r5 = bpf2a32[BPF_REG_5];
+		const s8 *r0 = bpf2a32[BPF_REG_0];
+		const s8 *r1 = bpf2a32[BPF_REG_1];
+		const s8 *r2 = bpf2a32[BPF_REG_2];
+		const s8 *r3 = bpf2a32[BPF_REG_3];
+		const s8 *r4 = bpf2a32[BPF_REG_4];
+		const s8 *r5 = bpf2a32[BPF_REG_5];
 		const u32 func = (u32)__bpf_call_base + (u32)imm;
 
 		emit_a32_mov_r64(true, r0, r1, false, false, ctx);
-- 
cgit v1.2.3


From 47b9c3bf416d80515901469f05aef2870b37c010 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:31:47 +0100
Subject: ARM: net: bpf: remove is_on_stack() and sstk/dstk

The decision about whether a BPF register is on the stack or in a CPU
register is detected at the top BPF insn processing level, and then
percolated throughout the remainder of the code.  Since we now use
negative register values to represent stacked registers, we can detect
where a BPF register is stored without restoring to carrying this
additional metadata through all code paths.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 336 ++++++++++++++++++++++------------------------
 1 file changed, 160 insertions(+), 176 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 69bf7ab18bf9..e81401aca2df 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -459,27 +459,18 @@ static inline void emit_udivmod(u8 rd, u8 rm, u8 rn, struct jit_ctx *ctx, u8 op)
 		emit(ARM_MOV_R(ARM_R0, tmp[1]), ctx);
 }
 
-/* Checks whether BPF register is on scratch stack space or not. */
-static inline bool is_on_stack(u8 bpf_reg)
+/* Is the translated BPF register on stack? */
+static bool is_stacked(s8 reg)
 {
-	static u8 stack_regs[] = {BPF_REG_AX, BPF_REG_3, BPF_REG_4, BPF_REG_5,
-				BPF_REG_7, BPF_REG_8, BPF_REG_9, TCALL_CNT,
-				BPF_REG_2, BPF_REG_FP};
-	int i, reg_len = sizeof(stack_regs);
-
-	for (i = 0 ; i < reg_len ; i++) {
-		if (bpf_reg == stack_regs[i])
-			return true;
-	}
-	return false;
+	return reg < 0;
 }
 
 static inline void emit_a32_mov_i(const s8 dst, const u32 val,
-				  bool dstk, struct jit_ctx *ctx)
+				  struct jit_ctx *ctx)
 {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 
-	if (dstk) {
+	if (is_stacked(dst)) {
 		emit_mov_i(tmp[1], val, ctx);
 		emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(dst)), ctx);
 	} else {
@@ -489,14 +480,13 @@ static inline void emit_a32_mov_i(const s8 dst, const u32 val,
 
 /* Sign extended move */
 static inline void emit_a32_mov_i64(const bool is64, const s8 dst[],
-				  const u32 val, bool dstk,
-				  struct jit_ctx *ctx) {
+				  const u32 val, struct jit_ctx *ctx) {
 	u32 hi = 0;
 
 	if (is64 && (val & (1<<31)))
 		hi = (u32)~0;
-	emit_a32_mov_i(dst_lo, val, dstk, ctx);
-	emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+	emit_a32_mov_i(dst_lo, val, ctx);
+	emit_a32_mov_i(dst_hi, hi, ctx);
 }
 
 static inline void emit_a32_add_r(const u8 dst, const u8 src,
@@ -579,17 +569,16 @@ static inline void emit_alu_r(const u8 dst, const u8 src, const bool is64,
  * dst = dst (op) src
  */
 static inline void emit_a32_alu_r(const s8 dst, const s8 src,
-				  bool dstk, bool sstk,
 				  struct jit_ctx *ctx, const bool is64,
 				  const bool hi, const u8 op) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rn = sstk ? tmp[1] : src;
+	s8 rn = is_stacked(src) ? tmp[1] : src;
 
-	if (sstk)
+	if (is_stacked(src))
 		emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx);
 
 	/* ALU operation */
-	if (dstk) {
+	if (is_stacked(dst)) {
 		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
 		emit_alu_r(tmp[0], rn, is64, hi, op, ctx);
 		emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
@@ -600,26 +589,24 @@ static inline void emit_a32_alu_r(const s8 dst, const s8 src,
 
 /* ALU operation (64 bit) */
 static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
-				  const s8 src[], bool dstk,
-				  bool sstk, struct jit_ctx *ctx,
+				  const s8 src[], struct jit_ctx *ctx,
 				  const u8 op) {
-	emit_a32_alu_r(dst_lo, src_lo, dstk, sstk, ctx, is64, false, op);
+	emit_a32_alu_r(dst_lo, src_lo, ctx, is64, false, op);
 	if (is64)
-		emit_a32_alu_r(dst_hi, src_hi, dstk, sstk, ctx, is64, true, op);
+		emit_a32_alu_r(dst_hi, src_hi, ctx, is64, true, op);
 	else
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+		emit_a32_mov_i(dst_hi, 0, ctx);
 }
 
 /* dst = imm (4 bytes)*/
 static inline void emit_a32_mov_r(const s8 dst, const s8 src,
-				  bool dstk, bool sstk,
 				  struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rt = sstk ? tmp[0] : src;
+	s8 rt = is_stacked(src) ? tmp[0] : src;
 
-	if (sstk)
+	if (is_stacked(src))
 		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx);
-	if (dstk)
+	if (is_stacked(dst))
 		emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst)), ctx);
 	else
 		emit(ARM_MOV_R(dst, rt), ctx);
@@ -627,25 +614,25 @@ static inline void emit_a32_mov_r(const s8 dst, const s8 src,
 
 /* dst = src */
 static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
-				  const s8 src[], bool dstk,
-				  bool sstk, struct jit_ctx *ctx) {
-	emit_a32_mov_r(dst_lo, src_lo, dstk, sstk, ctx);
+				  const s8 src[],
+				  struct jit_ctx *ctx) {
+	emit_a32_mov_r(dst_lo, src_lo, ctx);
 	if (is64) {
 		/* complete 8 byte move */
-		emit_a32_mov_r(dst_hi, src_hi, dstk, sstk, ctx);
+		emit_a32_mov_r(dst_hi, src_hi, ctx);
 	} else {
 		/* Zero out high 4 bytes */
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+		emit_a32_mov_i(dst_hi, 0, ctx);
 	}
 }
 
 /* Shift operations */
-static inline void emit_a32_alu_i(const s8 dst, const u32 val, bool dstk,
+static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 				struct jit_ctx *ctx, const u8 op) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rd = dstk ? tmp[0] : dst;
+	s8 rd = is_stacked(dst) ? tmp[0] : dst;
 
-	if (dstk)
+	if (is_stacked(dst))
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
 
 	/* Do shift operation */
@@ -661,19 +648,19 @@ static inline void emit_a32_alu_i(const s8 dst, const u32 val, bool dstk,
 		break;
 	}
 
-	if (dstk)
+	if (is_stacked(dst))
 		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
 }
 
 /* dst = ~dst (64 bit) */
-static inline void emit_a32_neg64(const s8 dst[], bool dstk,
+static inline void emit_a32_neg64(const s8 dst[],
 				struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rd = dstk ? tmp[1] : dst[1];
-	s8 rm = dstk ? tmp[0] : dst[0];
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst[1];
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst[0];
 
 	/* Setup Operand */
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
@@ -682,26 +669,26 @@ static inline void emit_a32_neg64(const s8 dst[], bool dstk,
 	emit(ARM_RSBS_I(rd, rd, 0), ctx);
 	emit(ARM_RSC_I(rm, rm, 0), ctx);
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
 }
 
 /* dst = dst << src */
-static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[], bool dstk,
-				    bool sstk, struct jit_ctx *ctx) {
+static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[],
+				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 
 	/* Setup Operands */
-	s8 rt = sstk ? tmp2[1] : src_lo;
-	s8 rd = dstk ? tmp[1] : dst_lo;
-	s8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
 
-	if (sstk)
+	if (is_stacked(src_lo))
 		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
@@ -714,7 +701,7 @@ static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[], bool dstk,
 	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx);
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	} else {
@@ -724,18 +711,18 @@ static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[], bool dstk,
 }
 
 /* dst = dst >> src (signed)*/
-static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[], bool dstk,
-				    bool sstk, struct jit_ctx *ctx) {
+static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
+				     struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup Operands */
-	s8 rt = sstk ? tmp2[1] : src_lo;
-	s8 rd = dstk ? tmp[1] : dst_lo;
-	s8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
 
-	if (sstk)
+	if (is_stacked(src_lo))
 		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
@@ -748,7 +735,7 @@ static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[], bool dstk,
 	_emit(ARM_COND_MI, ARM_B(0), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx);
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	} else {
@@ -758,18 +745,18 @@ static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[], bool dstk,
 }
 
 /* dst = dst >> src */
-static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[], bool dstk,
-				     bool sstk, struct jit_ctx *ctx) {
+static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[],
+				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup Operands */
-	s8 rt = sstk ? tmp2[1] : src_lo;
-	s8 rd = dstk ? tmp[1] : dst_lo;
-	s8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
 
-	if (sstk)
+	if (is_stacked(src_lo))
 		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
@@ -781,7 +768,7 @@ static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[], bool dstk,
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx);
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	} else {
@@ -791,15 +778,15 @@ static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[], bool dstk,
 }
 
 /* dst = dst << val */
-static inline void emit_a32_lsh_i64(const s8 dst[], bool dstk,
-				     const u32 val, struct jit_ctx *ctx){
+static inline void emit_a32_lsh_i64(const s8 dst[],
+				    const u32 val, struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup operands */
-	s8 rd = dstk ? tmp[1] : dst_lo;
-	s8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
@@ -817,22 +804,22 @@ static inline void emit_a32_lsh_i64(const s8 dst[], bool dstk,
 		emit(ARM_EOR_R(rd, rd, rd), ctx);
 	}
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
 }
 
 /* dst = dst >> val */
-static inline void emit_a32_rsh_i64(const s8 dst[], bool dstk,
+static inline void emit_a32_rsh_i64(const s8 dst[],
 				    const u32 val, struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup operands */
-	s8 rd = dstk ? tmp[1] : dst_lo;
-	s8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
@@ -850,22 +837,22 @@ static inline void emit_a32_rsh_i64(const s8 dst[], bool dstk,
 		emit(ARM_MOV_I(rm, 0), ctx);
 	}
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
 }
 
 /* dst = dst >> val (signed) */
-static inline void emit_a32_arsh_i64(const s8 dst[], bool dstk,
+static inline void emit_a32_arsh_i64(const s8 dst[],
 				     const u32 val, struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	 /* Setup operands */
-	s8 rd = dstk ? tmp[1] : dst_lo;
-	s8 rm = dstk ? tmp[0] : dst_hi;
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
@@ -883,27 +870,27 @@ static inline void emit_a32_arsh_i64(const s8 dst[], bool dstk,
 		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
 	}
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
 }
 
-static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[], bool dstk,
-				    bool sstk, struct jit_ctx *ctx) {
+static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
+				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	/* Setup operands for multiplication */
-	s8 rd = dstk ? tmp[1] : dst_lo;
-	s8 rm = dstk ? tmp[0] : dst_hi;
-	s8 rt = sstk ? tmp2[1] : src_lo;
-	s8 rn = sstk ? tmp2[0] : src_hi;
+	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
+	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
+	s8 rn = is_stacked(src_lo) ? tmp2[0] : src_hi;
 
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	}
-	if (sstk) {
+	if (is_stacked(src_lo)) {
 		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
 		emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_hi)), ctx);
 	}
@@ -915,7 +902,7 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[], bool dstk,
 
 	emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
 	emit(ARM_ADD_R(rm, ARM_LR, rm), ctx);
-	if (dstk) {
+	if (is_stacked(dst_lo)) {
 		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
 	} else {
@@ -924,15 +911,15 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[], bool dstk,
 }
 
 /* *(size *)(dst + off) = src */
-static inline void emit_str_r(const s8 dst, const s8 src, bool dstk,
+static inline void emit_str_r(const s8 dst, const s8 src,
 			      const s32 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rd = dstk ? tmp[1] : dst;
+	s8 rd = is_stacked(dst) ? tmp[1] : dst;
 
-	if (dstk)
+	if (is_stacked(dst))
 		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
 	if (off) {
-		emit_a32_mov_i(tmp[0], off, false, ctx);
+		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx);
 		rd = tmp[0];
 	}
@@ -953,10 +940,10 @@ static inline void emit_str_r(const s8 dst, const s8 src, bool dstk,
 }
 
 /* dst = *(size*)(src + off) */
-static inline void emit_ldx_r(const s8 dst[], const s8 src, bool dstk,
+static inline void emit_ldx_r(const s8 dst[], const s8 src,
 			      s32 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	const s8 *rd = dstk ? tmp : dst;
+	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
 	s8 rm = src;
 	s32 off_max;
 
@@ -966,7 +953,7 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src, bool dstk,
 		off_max = 0xfff;
 
 	if (off < 0 || off > off_max) {
-		emit_a32_mov_i(tmp[0], off, false, ctx);
+		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], tmp[0], src), ctx);
 		rm = tmp[0];
 		off = 0;
@@ -978,17 +965,17 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src, bool dstk,
 	case BPF_B:
 		/* Load a Byte */
 		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		emit_a32_mov_i(dst[0], 0, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
 		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		emit_a32_mov_i(dst[0], 0, ctx);
 		break;
 	case BPF_W:
 		/* Load a Word */
 		emit(ARM_LDR_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, dstk, ctx);
+		emit_a32_mov_i(dst[0], 0, ctx);
 		break;
 	case BPF_DW:
 		/* Load a Double Word */
@@ -996,10 +983,10 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src, bool dstk,
 		emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
 		break;
 	}
-	if (dstk)
-		emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst[1])), ctx);
-	if (dstk && sz == BPF_DW)
-		emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst[0])), ctx);
+	if (is_stacked(dst_lo))
+		emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst_lo)), ctx);
+	if (is_stacked(dst_lo) && sz == BPF_DW)
+		emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst_hi)), ctx);
 }
 
 /* Arithmatic Operation */
@@ -1053,7 +1040,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	off = offsetof(struct bpf_array, map.max_entries);
 	/* array->map.max_entries */
-	emit_a32_mov_i(tmp[1], off, false, ctx);
+	emit_a32_mov_i(tmp[1], off, ctx);
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
 	emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
 	/* index is 32-bit for arrays */
@@ -1083,7 +1070,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 *	goto out;
 	 */
 	off = offsetof(struct bpf_array, ptrs);
-	emit_a32_mov_i(tmp[1], off, false, ctx);
+	emit_a32_mov_i(tmp[1], off, ctx);
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
 	emit(ARM_ADD_R(tmp[1], tmp2[1], tmp[1]), ctx);
 	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
@@ -1094,7 +1081,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 
 	/* goto *(prog->bpf_func + prologue_size); */
 	off = offsetof(struct bpf_prog, bpf_func);
-	emit_a32_mov_i(tmp2[1], off, false, ctx);
+	emit_a32_mov_i(tmp2[1], off, ctx);
 	emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
 	emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
 	emit_bx_r(tmp[1], ctx);
@@ -1193,8 +1180,8 @@ static void build_prologue(struct jit_ctx *ctx)
 	emit(ARM_SUB_I(ARM_SP, ARM_SP, ctx->stack_size), ctx);
 
 	/* Set up BPF prog stack base register */
-	emit_a32_mov_r(fplo, ARM_IP, true, false, ctx);
-	emit_a32_mov_i(fphi, 0, true, ctx);
+	emit_a32_mov_r(fplo, ARM_IP, ctx);
+	emit_a32_mov_i(fphi, 0, ctx);
 
 	/* mov r4, 0 */
 	emit(ARM_MOV_I(r4, 0), ctx);
@@ -1243,8 +1230,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
 	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
-	const bool dstk = is_on_stack(insn->dst_reg);
-	const bool sstk = is_on_stack(insn->src_reg);
 	s8 rd, rt, rm, rn;
 	s32 jmp_offset;
 
@@ -1268,11 +1253,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_MOV | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			emit_a32_mov_r64(is64, dst, src, dstk, sstk, ctx);
+			emit_a32_mov_r64(is64, dst, src, ctx);
 			break;
 		case BPF_K:
 			/* Sign-extend immediate value to destination reg */
-			emit_a32_mov_i64(is64, dst, imm, dstk, ctx);
+			emit_a32_mov_i64(is64, dst, imm, ctx);
 			break;
 		}
 		break;
@@ -1312,8 +1297,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU64 | BPF_XOR | BPF_X:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			emit_a32_alu_r64(is64, dst, src, dstk, sstk,
-					 ctx, BPF_OP(code));
+			emit_a32_alu_r64(is64, dst, src, ctx, BPF_OP(code));
 			break;
 		case BPF_K:
 			/* Move immediate value to the temporary register
@@ -1322,9 +1306,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			 * value into temporary reg and then it would be
 			 * safe to do the operation on it.
 			 */
-			emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
-			emit_a32_alu_r64(is64, dst, tmp2, dstk, false,
-					 ctx, BPF_OP(code));
+			emit_a32_mov_i64(is64, tmp2, imm, ctx);
+			emit_a32_alu_r64(is64, dst, tmp2, ctx, BPF_OP(code));
 			break;
 		}
 		break;
@@ -1334,26 +1317,28 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU | BPF_MOD | BPF_X:
-		rt = src_lo;
-		rd = dstk ? tmp2[1] : dst_lo;
-		if (dstk)
+		rd = is_stacked(dst_lo) ? tmp2[1] : dst_lo;
+		if (is_stacked(dst_lo))
 			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			rt = sstk ? tmp2[0] : rt;
-			if (sstk)
+			rt = is_stacked(rt) ? tmp2[0] : src_lo;
+			if (is_stacked(src_lo))
 				emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)),
 				     ctx);
 			break;
 		case BPF_K:
 			rt = tmp2[0];
-			emit_a32_mov_i(rt, imm, false, ctx);
+			emit_a32_mov_i(rt, imm, ctx);
+			break;
+		default:
+			rt = src_lo;
 			break;
 		}
 		emit_udivmod(rd, rd, rt, ctx, BPF_OP(code));
-		if (dstk)
+		if (is_stacked(dst_lo))
 			emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
 	case BPF_ALU64 | BPF_DIV | BPF_X:
@@ -1367,54 +1352,54 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 		if (unlikely(imm > 31))
 			return -EINVAL;
 		if (imm)
-			emit_a32_alu_i(dst_lo, imm, dstk, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+			emit_a32_alu_i(dst_lo, imm, ctx, BPF_OP(code));
+		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = dst << imm */
 	case BPF_ALU64 | BPF_LSH | BPF_K:
 		if (unlikely(imm > 63))
 			return -EINVAL;
-		emit_a32_lsh_i64(dst, dstk, imm, ctx);
+		emit_a32_lsh_i64(dst, imm, ctx);
 		break;
 	/* dst = dst >> imm */
 	case BPF_ALU64 | BPF_RSH | BPF_K:
 		if (unlikely(imm > 63))
 			return -EINVAL;
-		emit_a32_rsh_i64(dst, dstk, imm, ctx);
+		emit_a32_rsh_i64(dst, imm, ctx);
 		break;
 	/* dst = dst << src */
 	case BPF_ALU64 | BPF_LSH | BPF_X:
-		emit_a32_lsh_r64(dst, src, dstk, sstk, ctx);
+		emit_a32_lsh_r64(dst, src, ctx);
 		break;
 	/* dst = dst >> src */
 	case BPF_ALU64 | BPF_RSH | BPF_X:
-		emit_a32_rsh_r64(dst, src, dstk, sstk, ctx);
+		emit_a32_rsh_r64(dst, src, ctx);
 		break;
 	/* dst = dst >> src (signed) */
 	case BPF_ALU64 | BPF_ARSH | BPF_X:
-		emit_a32_arsh_r64(dst, src, dstk, sstk, ctx);
+		emit_a32_arsh_r64(dst, src, ctx);
 		break;
 	/* dst = dst >> imm (signed) */
 	case BPF_ALU64 | BPF_ARSH | BPF_K:
 		if (unlikely(imm > 63))
 			return -EINVAL;
-		emit_a32_arsh_i64(dst, dstk, imm, ctx);
+		emit_a32_arsh_i64(dst, imm, ctx);
 		break;
 	/* dst = ~dst */
 	case BPF_ALU | BPF_NEG:
-		emit_a32_alu_i(dst_lo, 0, dstk, ctx, BPF_OP(code));
-		emit_a32_mov_i(dst_hi, 0, dstk, ctx);
+		emit_a32_alu_i(dst_lo, 0, ctx, BPF_OP(code));
+		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	/* dst = ~dst (64 bit) */
 	case BPF_ALU64 | BPF_NEG:
-		emit_a32_neg64(dst, dstk, ctx);
+		emit_a32_neg64(dst, ctx);
 		break;
 	/* dst = dst * src/imm */
 	case BPF_ALU64 | BPF_MUL | BPF_X:
 	case BPF_ALU64 | BPF_MUL | BPF_K:
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			emit_a32_mul_r64(dst, src, dstk, sstk, ctx);
+			emit_a32_mul_r64(dst, src, ctx);
 			break;
 		case BPF_K:
 			/* Move immediate value to the temporary register
@@ -1423,8 +1408,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			 * reg then it would be safe to do the operation
 			 * on it.
 			 */
-			emit_a32_mov_i64(is64, tmp2, imm, false, ctx);
-			emit_a32_mul_r64(dst, tmp2, dstk, false, ctx);
+			emit_a32_mov_i64(is64, tmp2, imm, ctx);
+			emit_a32_mul_r64(dst, tmp2, ctx);
 			break;
 		}
 		break;
@@ -1432,9 +1417,9 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = htobe(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
-		rd = dstk ? tmp[0] : dst_hi;
-		rt = dstk ? tmp[1] : dst_lo;
-		if (dstk) {
+		rd = is_stacked(dst_lo) ? tmp[0] : dst_hi;
+		rt = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+		if (is_stacked(dst_lo)) {
 			emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
 			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
 		}
@@ -1459,7 +1444,7 @@ emit_bswap_uxt:
 		case 16:
 			/* zero-extend 16 bits into 64 bits */
 #if __LINUX_ARM_ARCH__ < 6
-			emit_a32_mov_i(tmp2[1], 0xffff, false, ctx);
+			emit_a32_mov_i(tmp2[1], 0xffff, ctx);
 			emit(ARM_AND_R(rt, rt, tmp2[1]), ctx);
 #else /* ARMv6+ */
 			emit(ARM_UXTH(rt, rt), ctx);
@@ -1475,7 +1460,7 @@ emit_bswap_uxt:
 			break;
 		}
 exit:
-		if (dstk) {
+		if (is_stacked(dst_lo)) {
 			emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
 			emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
 		}
@@ -1487,8 +1472,8 @@ exit:
 		u32 hi, lo = imm;
 
 		hi = insn1.imm;
-		emit_a32_mov_i(dst_lo, lo, dstk, ctx);
-		emit_a32_mov_i(dst_hi, hi, dstk, ctx);
+		emit_a32_mov_i(dst_lo, lo, ctx);
+		emit_a32_mov_i(dst_hi, hi, ctx);
 
 		return 1;
 	}
@@ -1497,10 +1482,10 @@ exit:
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_DW:
-		rn = sstk ? tmp2[1] : src_lo;
-		if (sstk)
+		rn = is_stacked(src_lo) ? tmp2[1] : src_lo;
+		if (is_stacked(src_lo))
 			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-		emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code));
+		emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
 		break;
 	/* ST: *(size *)(dst + off) = imm */
 	case BPF_ST | BPF_MEM | BPF_W:
@@ -1510,16 +1495,15 @@ exit:
 		switch (BPF_SIZE(code)) {
 		case BPF_DW:
 			/* Sign-extend immediate value into temp reg */
-			emit_a32_mov_i64(true, tmp2, imm, false, ctx);
-			emit_str_r(dst_lo, tmp2[1], dstk, off, ctx, BPF_W);
-			emit_str_r(dst_lo, tmp2[0], dstk, off+4, ctx, BPF_W);
+			emit_a32_mov_i64(true, tmp2, imm, ctx);
+			emit_str_r(dst_lo, tmp2[1], off, ctx, BPF_W);
+			emit_str_r(dst_lo, tmp2[0], off+4, ctx, BPF_W);
 			break;
 		case BPF_W:
 		case BPF_H:
 		case BPF_B:
-			emit_a32_mov_i(tmp2[1], imm, false, ctx);
-			emit_str_r(dst_lo, tmp2[1], dstk, off, ctx,
-				   BPF_SIZE(code));
+			emit_a32_mov_i(tmp2[1], imm, ctx);
+			emit_str_r(dst_lo, tmp2[1], off, ctx, BPF_SIZE(code));
 			break;
 		}
 		break;
@@ -1536,19 +1520,19 @@ exit:
 	{
 		u8 sz = BPF_SIZE(code);
 
-		rn = sstk ? tmp2[1] : src_lo;
-		rm = sstk ? tmp2[0] : src_hi;
-		if (sstk) {
+		rn = is_stacked(src_lo) ? tmp2[1] : src_lo;
+		rm = is_stacked(src_lo) ? tmp2[0] : src_hi;
+		if (is_stacked(src_lo)) {
 			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
 			emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
 		}
 
 		/* Store the value */
 		if (BPF_SIZE(code) == BPF_DW) {
-			emit_str_r(dst_lo, rn, dstk, off, ctx, BPF_W);
-			emit_str_r(dst_lo, rm, dstk, off+4, ctx, BPF_W);
+			emit_str_r(dst_lo, rn, off, ctx, BPF_W);
+			emit_str_r(dst_lo, rm, off+4, ctx, BPF_W);
 		} else {
-			emit_str_r(dst_lo, rn, dstk, off, ctx, sz);
+			emit_str_r(dst_lo, rn, off, ctx, sz);
 		}
 		break;
 	}
@@ -1575,9 +1559,9 @@ exit:
 	case BPF_JMP | BPF_JSLT | BPF_X:
 	case BPF_JMP | BPF_JSLE | BPF_X:
 		/* Setup source registers */
-		rm = sstk ? tmp2[0] : src_hi;
-		rn = sstk ? tmp2[1] : src_lo;
-		if (sstk) {
+		rm = is_stacked(src_lo) ? tmp2[0] : src_hi;
+		rn = is_stacked(src_lo) ? tmp2[1] : src_lo;
+		if (is_stacked(src_lo)) {
 			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
 			emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
 		}
@@ -1609,12 +1593,12 @@ exit:
 		rm = tmp2[0];
 		rn = tmp2[1];
 		/* Sign-extend immediate value */
-		emit_a32_mov_i64(true, tmp2, imm, false, ctx);
+		emit_a32_mov_i64(true, tmp2, imm, ctx);
 go_jmp:
 		/* Setup destination register */
-		rd = dstk ? tmp[0] : dst_hi;
-		rt = dstk ? tmp[1] : dst_lo;
-		if (dstk) {
+		rd = is_stacked(dst_lo) ? tmp[0] : dst_hi;
+		rt = is_stacked(dst_lo) ? tmp[1] : dst_lo;
+		if (is_stacked(dst_lo)) {
 			emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
 			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
 		}
@@ -1684,13 +1668,13 @@ go_jmp:
 		const s8 *r5 = bpf2a32[BPF_REG_5];
 		const u32 func = (u32)__bpf_call_base + (u32)imm;
 
-		emit_a32_mov_r64(true, r0, r1, false, false, ctx);
-		emit_a32_mov_r64(true, r1, r2, false, true, ctx);
+		emit_a32_mov_r64(true, r0, r1, ctx);
+		emit_a32_mov_r64(true, r1, r2, ctx);
 		emit_push_r64(r5, 0, ctx);
 		emit_push_r64(r4, 8, ctx);
 		emit_push_r64(r3, 16, ctx);
 
-		emit_a32_mov_i(tmp[1], func, false, ctx);
+		emit_a32_mov_i(tmp[1], func, ctx);
 		emit_blx_r(tmp[1], ctx);
 
 		emit(ARM_ADD_I(ARM_SP, ARM_SP, imm8m(24)), ctx); // callee clean
-- 
cgit v1.2.3


From 7a9870256361d4a36cb42e0301540256bb4b864e Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:31:52 +0100
Subject: ARM: net: bpf: provide accessor functions for BPF registers

Many of the code paths need to have knowledge about whether a register
is stacked or in a CPU register.  Move this decision making to a pair
of helper functions instead of having it scattered throughout the
code.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 329 ++++++++++++++++++----------------------------
 1 file changed, 128 insertions(+), 201 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e81401aca2df..08fb4eb285a2 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -465,6 +465,31 @@ static bool is_stacked(s8 reg)
 	return reg < 0;
 }
 
+/* If a BPF register is on the stack (stk is true), load it to the
+ * supplied temporary register and return the temporary register
+ * for subsequent operations, otherwise just use the CPU register.
+ */
+static s8 arm_bpf_get_reg32(s8 reg, s8 tmp, struct jit_ctx *ctx)
+{
+	if (is_stacked(reg)) {
+		emit(ARM_LDR_I(tmp, ARM_SP, STACK_VAR(reg)), ctx);
+		reg = tmp;
+	}
+	return reg;
+}
+
+/* If a BPF register is on the stack (stk is true), save the register
+ * back to the stack.  If the source register is not the same, then
+ * move it into the correct register.
+ */
+static void arm_bpf_put_reg32(s8 reg, s8 src, struct jit_ctx *ctx)
+{
+	if (is_stacked(reg))
+		emit(ARM_STR_I(src, ARM_SP, STACK_VAR(reg)), ctx);
+	else if (reg != src)
+		emit(ARM_MOV_R(reg, src), ctx);
+}
+
 static inline void emit_a32_mov_i(const s8 dst, const u32 val,
 				  struct jit_ctx *ctx)
 {
@@ -472,7 +497,7 @@ static inline void emit_a32_mov_i(const s8 dst, const u32 val,
 
 	if (is_stacked(dst)) {
 		emit_mov_i(tmp[1], val, ctx);
-		emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(dst)), ctx);
+		arm_bpf_put_reg32(dst, tmp[1], ctx);
 	} else {
 		emit_mov_i(dst, val, ctx);
 	}
@@ -572,19 +597,13 @@ static inline void emit_a32_alu_r(const s8 dst, const s8 src,
 				  struct jit_ctx *ctx, const bool is64,
 				  const bool hi, const u8 op) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rn = is_stacked(src) ? tmp[1] : src;
-
-	if (is_stacked(src))
-		emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src)), ctx);
+	s8 rn, rd;
 
+	rn = arm_bpf_get_reg32(src, tmp[1], ctx);
+	rd = arm_bpf_get_reg32(dst, tmp[0], ctx);
 	/* ALU operation */
-	if (is_stacked(dst)) {
-		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
-		emit_alu_r(tmp[0], rn, is64, hi, op, ctx);
-		emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(dst)), ctx);
-	} else {
-		emit_alu_r(dst, rn, is64, hi, op, ctx);
-	}
+	emit_alu_r(rd, rn, is64, hi, op, ctx);
+	arm_bpf_put_reg32(dst, rd, ctx);
 }
 
 /* ALU operation (64 bit) */
@@ -598,18 +617,14 @@ static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 		emit_a32_mov_i(dst_hi, 0, ctx);
 }
 
-/* dst = imm (4 bytes)*/
+/* dst = src (4 bytes)*/
 static inline void emit_a32_mov_r(const s8 dst, const s8 src,
 				  struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rt = is_stacked(src) ? tmp[0] : src;
+	s8 rt;
 
-	if (is_stacked(src))
-		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(src)), ctx);
-	if (is_stacked(dst))
-		emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst)), ctx);
-	else
-		emit(ARM_MOV_R(dst, rt), ctx);
+	rt = arm_bpf_get_reg32(src, tmp[0], ctx);
+	arm_bpf_put_reg32(dst, rt, ctx);
 }
 
 /* dst = src */
@@ -630,10 +645,9 @@ static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 				struct jit_ctx *ctx, const u8 op) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rd = is_stacked(dst) ? tmp[0] : dst;
+	s8 rd;
 
-	if (is_stacked(dst))
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+	rd = arm_bpf_get_reg32(dst, tmp[0], ctx);
 
 	/* Do shift operation */
 	switch (op) {
@@ -648,31 +662,25 @@ static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 		break;
 	}
 
-	if (is_stacked(dst))
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+	arm_bpf_put_reg32(dst, rd, ctx);
 }
 
 /* dst = ~dst (64 bit) */
 static inline void emit_a32_neg64(const s8 dst[],
 				struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst[1];
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst[0];
+	s8 rd, rm;
 
 	/* Setup Operand */
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 	/* Do Negate Operation */
 	emit(ARM_RSBS_I(rd, rd, 0), ctx);
 	emit(ARM_RSC_I(rm, rm, 0), ctx);
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg32(dst_lo, rd, ctx);
+	arm_bpf_put_reg32(dst_hi, rm, ctx);
 }
 
 /* dst = dst << src */
@@ -680,18 +688,12 @@ static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[],
 				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	s8 rt, rd, rm;
 
 	/* Setup Operands */
-	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
-
-	if (is_stacked(src_lo))
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 	/* Do LSH operation */
 	emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
@@ -701,13 +703,8 @@ static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[],
 	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx);
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_LR), ctx);
-		emit(ARM_MOV_R(rm, ARM_IP), ctx);
-	}
+	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
 }
 
 /* dst = dst >> src (signed)*/
@@ -715,17 +712,12 @@ static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
 				     struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	s8 rt, rd, rm;
+
 	/* Setup Operands */
-	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
-
-	if (is_stacked(src_lo))
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 	/* Do the ARSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
@@ -735,13 +727,9 @@ static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
 	_emit(ARM_COND_MI, ARM_B(0), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx);
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_LR), ctx);
-		emit(ARM_MOV_R(rm, ARM_IP), ctx);
-	}
+
+	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
 }
 
 /* dst = dst >> src */
@@ -749,17 +737,12 @@ static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[],
 				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	s8 rt, rd, rm;
+
 	/* Setup Operands */
-	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
-
-	if (is_stacked(src_lo))
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 	/* Do RSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
@@ -768,13 +751,9 @@ static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[],
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
 	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
 	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx);
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(ARM_LR, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_LR), ctx);
-		emit(ARM_MOV_R(rm, ARM_IP), ctx);
-	}
+
+	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
+	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
 }
 
 /* dst = dst << val */
@@ -782,14 +761,11 @@ static inline void emit_a32_lsh_i64(const s8 dst[],
 				    const u32 val, struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	/* Setup operands */
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
+	s8 rd, rm;
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup operands */
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 	/* Do LSH operation */
 	if (val < 32) {
@@ -804,10 +780,8 @@ static inline void emit_a32_lsh_i64(const s8 dst[],
 		emit(ARM_EOR_R(rd, rd, rd), ctx);
 	}
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg32(dst_lo, rd, ctx);
+	arm_bpf_put_reg32(dst_hi, rm, ctx);
 }
 
 /* dst = dst >> val */
@@ -815,14 +789,11 @@ static inline void emit_a32_rsh_i64(const s8 dst[],
 				    const u32 val, struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	/* Setup operands */
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
+	s8 rd, rm;
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup operands */
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 	/* Do LSR operation */
 	if (val < 32) {
@@ -837,10 +808,8 @@ static inline void emit_a32_rsh_i64(const s8 dst[],
 		emit(ARM_MOV_I(rm, 0), ctx);
 	}
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg32(dst_lo, rd, ctx);
+	arm_bpf_put_reg32(dst_hi, rm, ctx);
 }
 
 /* dst = dst >> val (signed) */
@@ -848,14 +817,11 @@ static inline void emit_a32_arsh_i64(const s8 dst[],
 				     const u32 val, struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	 /* Setup operands */
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
+	s8 rd, rm;
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	/* Setup operands */
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 	/* Do ARSH operation */
 	if (val < 32) {
@@ -870,30 +836,21 @@ static inline void emit_a32_arsh_i64(const s8 dst[],
 		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
 	}
 
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
+	arm_bpf_put_reg32(dst_lo, rd, ctx);
+	arm_bpf_put_reg32(dst_hi, rm, ctx);
 }
 
 static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
 				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	s8 rd, rm, rt, rn;
+
 	/* Setup operands for multiplication */
-	s8 rd = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-	s8 rm = is_stacked(dst_lo) ? tmp[0] : dst_hi;
-	s8 rt = is_stacked(src_lo) ? tmp2[1] : src_lo;
-	s8 rn = is_stacked(src_lo) ? tmp2[0] : src_hi;
-
-	if (is_stacked(dst_lo)) {
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	}
-	if (is_stacked(src_lo)) {
-		emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)), ctx);
-		emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_hi)), ctx);
-	}
+	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+	rn = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
 
 	/* Do Multiplication */
 	emit(ARM_MUL(ARM_IP, rd, rn), ctx);
@@ -902,22 +859,18 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
 
 	emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
 	emit(ARM_ADD_R(rm, ARM_LR, rm), ctx);
-	if (is_stacked(dst_lo)) {
-		emit(ARM_STR_I(ARM_IP, ARM_SP, STACK_VAR(dst_lo)), ctx);
-		emit(ARM_STR_I(rm, ARM_SP, STACK_VAR(dst_hi)), ctx);
-	} else {
-		emit(ARM_MOV_R(rd, ARM_IP), ctx);
-	}
+
+	arm_bpf_put_reg32(dst_lo, ARM_IP, ctx);
+	arm_bpf_put_reg32(dst_hi, rm, ctx);
 }
 
 /* *(size *)(dst + off) = src */
 static inline void emit_str_r(const s8 dst, const s8 src,
 			      const s32 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rd = is_stacked(dst) ? tmp[1] : dst;
+	s8 rd;
 
-	if (is_stacked(dst))
-		emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst)), ctx);
+	rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
 	if (off) {
 		emit_a32_mov_i(tmp[0], off, ctx);
 		emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx);
@@ -983,10 +936,9 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 		emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
 		break;
 	}
-	if (is_stacked(dst_lo))
-		emit(ARM_STR_I(rd[1], ARM_SP, STACK_VAR(dst_lo)), ctx);
-	if (is_stacked(dst_lo) && sz == BPF_DW)
-		emit(ARM_STR_I(rd[0], ARM_SP, STACK_VAR(dst_hi)), ctx);
+	arm_bpf_put_reg32(dst[1], rd[1], ctx);
+	if (sz == BPF_DW)
+		arm_bpf_put_reg32(dst[0], rd[0], ctx);
 }
 
 /* Arithmatic Operation */
@@ -1034,6 +986,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 #define cur_offset (ctx->idx - idx0)
 #define jmp_offset (out_offset - (cur_offset) - 2)
 	u32 off, lo, hi;
+	s8 r_array, r_index, r_tc_lo, r_tc_hi;
 
 	/* if (index >= array->map.max_entries)
 	 *	goto out;
@@ -1041,12 +994,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	off = offsetof(struct bpf_array, map.max_entries);
 	/* array->map.max_entries */
 	emit_a32_mov_i(tmp[1], off, ctx);
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
-	emit(ARM_LDR_R(tmp[1], tmp2[1], tmp[1]), ctx);
+	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
+	emit(ARM_LDR_R(tmp[1], r_array, tmp[1]), ctx);
 	/* index is 32-bit for arrays */
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
+	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
 	/* index >= array->map.max_entries */
-	emit(ARM_CMP_R(tmp2[1], tmp[1]), ctx);
+	emit(ARM_CMP_R(r_index, tmp[1]), ctx);
 	_emit(ARM_COND_CS, ARM_B(jmp_offset), ctx);
 
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
@@ -1055,15 +1008,15 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	lo = (u32)MAX_TAIL_CALL_CNT;
 	hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32);
-	emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
-	emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
-	emit(ARM_CMP_I(tmp[0], hi), ctx);
-	_emit(ARM_COND_EQ, ARM_CMP_I(tmp[1], lo), ctx);
+	r_tc_lo = arm_bpf_get_reg32(tcc[1], tmp[1], ctx);
+	r_tc_hi = arm_bpf_get_reg32(tcc[0], tmp[0], ctx);
+	emit(ARM_CMP_I(r_tc_hi, hi), ctx);
+	_emit(ARM_COND_EQ, ARM_CMP_I(r_tc_lo, lo), ctx);
 	_emit(ARM_COND_HI, ARM_B(jmp_offset), ctx);
-	emit(ARM_ADDS_I(tmp[1], tmp[1], 1), ctx);
-	emit(ARM_ADC_I(tmp[0], tmp[0], 0), ctx);
-	emit(ARM_STR_I(tmp[1], ARM_SP, STACK_VAR(tcc[1])), ctx);
-	emit(ARM_STR_I(tmp[0], ARM_SP, STACK_VAR(tcc[0])), ctx);
+	emit(ARM_ADDS_I(r_tc_lo, r_tc_lo, 1), ctx);
+	emit(ARM_ADC_I(r_tc_hi, r_tc_hi, 0), ctx);
+	arm_bpf_put_reg32(tcc[1], r_tc_lo, ctx);
+	arm_bpf_put_reg32(tcc[0], r_tc_hi, ctx);
 
 	/* prog = array->ptrs[index]
 	 * if (prog == NULL)
@@ -1071,10 +1024,10 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	off = offsetof(struct bpf_array, ptrs);
 	emit_a32_mov_i(tmp[1], off, ctx);
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r2[1])), ctx);
-	emit(ARM_ADD_R(tmp[1], tmp2[1], tmp[1]), ctx);
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(r3[1])), ctx);
-	emit(ARM_MOV_SI(tmp[0], tmp2[1], SRTYPE_ASL, 2), ctx);
+	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
+	emit(ARM_ADD_R(tmp[1], r_array, tmp[1]), ctx);
+	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
+	emit(ARM_MOV_SI(tmp[0], r_index, SRTYPE_ASL, 2), ctx);
 	emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx);
 	emit(ARM_CMP_I(tmp[1], 0), ctx);
 	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
@@ -1317,15 +1270,10 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU | BPF_MOD | BPF_X:
-		rd = is_stacked(dst_lo) ? tmp2[1] : dst_lo;
-		if (is_stacked(dst_lo))
-			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+		rd = arm_bpf_get_reg32(dst_lo, tmp2[1], ctx);
 		switch (BPF_SRC(code)) {
 		case BPF_X:
-			rt = is_stacked(rt) ? tmp2[0] : src_lo;
-			if (is_stacked(src_lo))
-				emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(src_lo)),
-				     ctx);
+			rt = arm_bpf_get_reg32(src_lo, tmp2[0], ctx);
 			break;
 		case BPF_K:
 			rt = tmp2[0];
@@ -1336,8 +1284,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			break;
 		}
 		emit_udivmod(rd, rd, rt, ctx, BPF_OP(code));
-		if (is_stacked(dst_lo))
-			emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_lo)), ctx);
+		arm_bpf_put_reg32(dst_lo, rd, ctx);
 		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
@@ -1417,12 +1364,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = htobe(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
-		rd = is_stacked(dst_lo) ? tmp[0] : dst_hi;
-		rt = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-		if (is_stacked(dst_lo)) {
-			emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
-			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
-		}
+		rt = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+		rd = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 		if (BPF_SRC(code) == BPF_FROM_LE)
 			goto emit_bswap_uxt;
 		switch (imm) {
@@ -1460,10 +1403,8 @@ emit_bswap_uxt:
 			break;
 		}
 exit:
-		if (is_stacked(dst_lo)) {
-			emit(ARM_STR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
-			emit(ARM_STR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
-		}
+		arm_bpf_put_reg32(dst_lo, rt, ctx);
+		arm_bpf_put_reg32(dst_hi, rd, ctx);
 		break;
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
@@ -1482,9 +1423,7 @@ exit:
 	case BPF_LDX | BPF_MEM | BPF_H:
 	case BPF_LDX | BPF_MEM | BPF_B:
 	case BPF_LDX | BPF_MEM | BPF_DW:
-		rn = is_stacked(src_lo) ? tmp2[1] : src_lo;
-		if (is_stacked(src_lo))
-			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
+		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
 		emit_ldx_r(dst, rn, off, ctx, BPF_SIZE(code));
 		break;
 	/* ST: *(size *)(dst + off) = imm */
@@ -1520,12 +1459,8 @@ exit:
 	{
 		u8 sz = BPF_SIZE(code);
 
-		rn = is_stacked(src_lo) ? tmp2[1] : src_lo;
-		rm = is_stacked(src_lo) ? tmp2[0] : src_hi;
-		if (is_stacked(src_lo)) {
-			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-			emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
-		}
+		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+		rm = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
 
 		/* Store the value */
 		if (BPF_SIZE(code) == BPF_DW) {
@@ -1559,12 +1494,8 @@ exit:
 	case BPF_JMP | BPF_JSLT | BPF_X:
 	case BPF_JMP | BPF_JSLE | BPF_X:
 		/* Setup source registers */
-		rm = is_stacked(src_lo) ? tmp2[0] : src_hi;
-		rn = is_stacked(src_lo) ? tmp2[1] : src_lo;
-		if (is_stacked(src_lo)) {
-			emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx);
-			emit(ARM_LDR_I(rm, ARM_SP, STACK_VAR(src_hi)), ctx);
-		}
+		rm = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
+		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
 		goto go_jmp;
 	/* PC += off if dst == imm */
 	/* PC += off if dst > imm */
@@ -1596,12 +1527,8 @@ exit:
 		emit_a32_mov_i64(true, tmp2, imm, ctx);
 go_jmp:
 		/* Setup destination register */
-		rd = is_stacked(dst_lo) ? tmp[0] : dst_hi;
-		rt = is_stacked(dst_lo) ? tmp[1] : dst_lo;
-		if (is_stacked(dst_lo)) {
-			emit(ARM_LDR_I(rt, ARM_SP, STACK_VAR(dst_lo)), ctx);
-			emit(ARM_LDR_I(rd, ARM_SP, STACK_VAR(dst_hi)), ctx);
-		}
+		rt = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
+		rd = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
 
 		/* Check for the condition */
 		emit_ar_r(rd, rt, rm, rn, ctx, BPF_OP(code));
-- 
cgit v1.2.3


From a6eccac507e5e4aed63fb23320fcadeb253c2af6 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:31:57 +0100
Subject: ARM: net: bpf: 64-bit accessor functions for BPF registers

Provide a couple of 64-bit register accessors, and use them where
appropriate

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 235 ++++++++++++++++++++++++----------------------
 1 file changed, 122 insertions(+), 113 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 08fb4eb285a2..45a3599e94a4 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -478,6 +478,17 @@ static s8 arm_bpf_get_reg32(s8 reg, s8 tmp, struct jit_ctx *ctx)
 	return reg;
 }
 
+static const s8 *arm_bpf_get_reg64(const s8 *reg, const s8 *tmp,
+				   struct jit_ctx *ctx)
+{
+	if (is_stacked(reg[1])) {
+		emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(reg[1])), ctx);
+		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(reg[0])), ctx);
+		reg = tmp;
+	}
+	return reg;
+}
+
 /* If a BPF register is on the stack (stk is true), save the register
  * back to the stack.  If the source register is not the same, then
  * move it into the correct register.
@@ -490,6 +501,20 @@ static void arm_bpf_put_reg32(s8 reg, s8 src, struct jit_ctx *ctx)
 		emit(ARM_MOV_R(reg, src), ctx);
 }
 
+static void arm_bpf_put_reg64(const s8 *reg, const s8 *src,
+			      struct jit_ctx *ctx)
+{
+	if (is_stacked(reg[1])) {
+		emit(ARM_STR_I(src[1], ARM_SP, STACK_VAR(reg[1])), ctx);
+		emit(ARM_STR_I(src[0], ARM_SP, STACK_VAR(reg[0])), ctx);
+	} else {
+		if (reg[1] != src[1])
+			emit(ARM_MOV_R(reg[1], src[1]), ctx);
+		if (reg[0] != src[0])
+			emit(ARM_MOV_R(reg[0], src[0]), ctx);
+	}
+}
+
 static inline void emit_a32_mov_i(const s8 dst, const u32 val,
 				  struct jit_ctx *ctx)
 {
@@ -669,18 +694,16 @@ static inline void emit_a32_alu_i(const s8 dst, const u32 val,
 static inline void emit_a32_neg64(const s8 dst[],
 				struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
-	s8 rd, rm;
+	const s8 *rd;
 
 	/* Setup Operand */
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do Negate Operation */
-	emit(ARM_RSBS_I(rd, rd, 0), ctx);
-	emit(ARM_RSC_I(rm, rm, 0), ctx);
+	emit(ARM_RSBS_I(rd[1], rd[1], 0), ctx);
+	emit(ARM_RSC_I(rd[0], rd[0], 0), ctx);
 
-	arm_bpf_put_reg32(dst_lo, rd, ctx);
-	arm_bpf_put_reg32(dst_hi, rm, ctx);
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* dst = dst << src */
@@ -688,20 +711,20 @@ static inline void emit_a32_lsh_r64(const s8 dst[], const s8 src[],
 				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	s8 rt, rd, rm;
+	const s8 *rd;
+	s8 rt;
 
 	/* Setup Operands */
 	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSH operation */
 	emit(ARM_SUB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_RSB_I(tmp2[0], rt, 32), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rm, SRTYPE_ASL, rt), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd, SRTYPE_ASL, ARM_IP), ctx);
-	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd, SRTYPE_LSR, tmp2[0]), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_ASL, rt), ctx);
+	emit(ARM_MOV_SR(ARM_LR, rd[0], SRTYPE_ASL, rt), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[1], SRTYPE_ASL, ARM_IP), ctx);
+	emit(ARM_ORR_SR(ARM_IP, ARM_LR, rd[1], SRTYPE_LSR, tmp2[0]), ctx);
+	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_ASL, rt), ctx);
 
 	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
 	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
@@ -712,21 +735,21 @@ static inline void emit_a32_arsh_r64(const s8 dst[], const s8 src[],
 				     struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	s8 rt, rd, rm;
+	const s8 *rd;
+	s8 rt;
 
 	/* Setup Operands */
 	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do the ARSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
+	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
 	_emit(ARM_COND_MI, ARM_B(0), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASR, tmp2[0]), ctx);
-	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_ASR, rt), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASR, tmp2[0]), ctx);
+	emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_ASR, rt), ctx);
 
 	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
 	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
@@ -737,20 +760,20 @@ static inline void emit_a32_rsh_r64(const s8 dst[], const s8 src[],
 				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	s8 rt, rd, rm;
+	const s8 *rd;
+	s8 rt;
 
 	/* Setup Operands */
 	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do RSH operation */
 	emit(ARM_RSB_I(ARM_IP, rt, 32), ctx);
 	emit(ARM_SUBS_I(tmp2[0], rt, 32), ctx);
-	emit(ARM_MOV_SR(ARM_LR, rd, SRTYPE_LSR, rt), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_ASL, ARM_IP), ctx);
-	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rm, SRTYPE_LSR, tmp2[0]), ctx);
-	emit(ARM_MOV_SR(ARM_IP, rm, SRTYPE_LSR, rt), ctx);
+	emit(ARM_MOV_SR(ARM_LR, rd[1], SRTYPE_LSR, rt), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_ASL, ARM_IP), ctx);
+	emit(ARM_ORR_SR(ARM_LR, ARM_LR, rd[0], SRTYPE_LSR, tmp2[0]), ctx);
+	emit(ARM_MOV_SR(ARM_IP, rd[0], SRTYPE_LSR, rt), ctx);
 
 	arm_bpf_put_reg32(dst_lo, ARM_LR, ctx);
 	arm_bpf_put_reg32(dst_hi, ARM_IP, ctx);
@@ -761,27 +784,25 @@ static inline void emit_a32_lsh_i64(const s8 dst[],
 				    const u32 val, struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	s8 rd, rm;
+	const s8 *rd;
 
 	/* Setup operands */
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSH operation */
 	if (val < 32) {
-		emit(ARM_MOV_SI(tmp2[0], rm, SRTYPE_ASL, val), ctx);
-		emit(ARM_ORR_SI(rm, tmp2[0], rd, SRTYPE_LSR, 32 - val), ctx);
-		emit(ARM_MOV_SI(rd, rd, SRTYPE_ASL, val), ctx);
+		emit(ARM_MOV_SI(tmp2[0], rd[0], SRTYPE_ASL, val), ctx);
+		emit(ARM_ORR_SI(rd[0], tmp2[0], rd[1], SRTYPE_LSR, 32 - val), ctx);
+		emit(ARM_MOV_SI(rd[1], rd[1], SRTYPE_ASL, val), ctx);
 	} else {
 		if (val == 32)
-			emit(ARM_MOV_R(rm, rd), ctx);
+			emit(ARM_MOV_R(rd[0], rd[1]), ctx);
 		else
-			emit(ARM_MOV_SI(rm, rd, SRTYPE_ASL, val - 32), ctx);
-		emit(ARM_EOR_R(rd, rd, rd), ctx);
+			emit(ARM_MOV_SI(rd[0], rd[1], SRTYPE_ASL, val - 32), ctx);
+		emit(ARM_EOR_R(rd[1], rd[1], rd[1]), ctx);
 	}
 
-	arm_bpf_put_reg32(dst_lo, rd, ctx);
-	arm_bpf_put_reg32(dst_hi, rm, ctx);
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* dst = dst >> val */
@@ -789,27 +810,25 @@ static inline void emit_a32_rsh_i64(const s8 dst[],
 				    const u32 val, struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	s8 rd, rm;
+	const s8 *rd;
 
 	/* Setup operands */
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do LSR operation */
 	if (val < 32) {
-		emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
-		emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_LSR, val), ctx);
+		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
+		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_LSR, val), ctx);
 	} else if (val == 32) {
-		emit(ARM_MOV_R(rd, rm), ctx);
-		emit(ARM_MOV_I(rm, 0), ctx);
+		emit(ARM_MOV_R(rd[1], rd[0]), ctx);
+		emit(ARM_MOV_I(rd[0], 0), ctx);
 	} else {
-		emit(ARM_MOV_SI(rd, rm, SRTYPE_LSR, val - 32), ctx);
-		emit(ARM_MOV_I(rm, 0), ctx);
+		emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_LSR, val - 32), ctx);
+		emit(ARM_MOV_I(rd[0], 0), ctx);
 	}
 
-	arm_bpf_put_reg32(dst_lo, rd, ctx);
-	arm_bpf_put_reg32(dst_hi, rm, ctx);
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* dst = dst >> val (signed) */
@@ -817,51 +836,47 @@ static inline void emit_a32_arsh_i64(const s8 dst[],
 				     const u32 val, struct jit_ctx *ctx){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	s8 rd, rm;
+	const s8 *rd;
 
 	/* Setup operands */
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 	/* Do ARSH operation */
 	if (val < 32) {
-		emit(ARM_MOV_SI(tmp2[1], rd, SRTYPE_LSR, val), ctx);
-		emit(ARM_ORR_SI(rd, tmp2[1], rm, SRTYPE_ASL, 32 - val), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, val), ctx);
+		emit(ARM_MOV_SI(tmp2[1], rd[1], SRTYPE_LSR, val), ctx);
+		emit(ARM_ORR_SI(rd[1], tmp2[1], rd[0], SRTYPE_ASL, 32 - val), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, val), ctx);
 	} else if (val == 32) {
-		emit(ARM_MOV_R(rd, rm), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+		emit(ARM_MOV_R(rd[1], rd[0]), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx);
 	} else {
-		emit(ARM_MOV_SI(rd, rm, SRTYPE_ASR, val - 32), ctx);
-		emit(ARM_MOV_SI(rm, rm, SRTYPE_ASR, 31), ctx);
+		emit(ARM_MOV_SI(rd[1], rd[0], SRTYPE_ASR, val - 32), ctx);
+		emit(ARM_MOV_SI(rd[0], rd[0], SRTYPE_ASR, 31), ctx);
 	}
 
-	arm_bpf_put_reg32(dst_lo, rd, ctx);
-	arm_bpf_put_reg32(dst_hi, rm, ctx);
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
 				    struct jit_ctx *ctx) {
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
-	s8 rd, rm, rt, rn;
+	const s8 *rd, *rt;
 
 	/* Setup operands for multiplication */
-	rd = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-	rm = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
-	rt = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
-	rn = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
+	rt = arm_bpf_get_reg64(src, tmp2, ctx);
 
 	/* Do Multiplication */
-	emit(ARM_MUL(ARM_IP, rd, rn), ctx);
-	emit(ARM_MUL(ARM_LR, rm, rt), ctx);
+	emit(ARM_MUL(ARM_IP, rd[1], rt[0]), ctx);
+	emit(ARM_MUL(ARM_LR, rd[0], rt[1]), ctx);
 	emit(ARM_ADD_R(ARM_LR, ARM_IP, ARM_LR), ctx);
 
-	emit(ARM_UMULL(ARM_IP, rm, rd, rt), ctx);
-	emit(ARM_ADD_R(rm, ARM_LR, rm), ctx);
+	emit(ARM_UMULL(ARM_IP, rd[0], rd[1], rt[1]), ctx);
+	emit(ARM_ADD_R(rd[0], ARM_LR, rd[0]), ctx);
 
 	arm_bpf_put_reg32(dst_lo, ARM_IP, ctx);
-	arm_bpf_put_reg32(dst_hi, rm, ctx);
+	arm_bpf_put_reg32(dst_hi, rd[0], ctx);
 }
 
 /* *(size *)(dst + off) = src */
@@ -918,17 +933,17 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 	case BPF_B:
 		/* Load a Byte */
 		emit(ARM_LDRB_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_H:
 		/* Load a HalfWord */
 		emit(ARM_LDRH_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_W:
 		/* Load a Word */
 		emit(ARM_LDR_I(rd[1], rm, off), ctx);
-		emit_a32_mov_i(dst[0], 0, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
 		break;
 	case BPF_DW:
 		/* Load a Double Word */
@@ -936,9 +951,7 @@ static inline void emit_ldx_r(const s8 dst[], const s8 src,
 		emit(ARM_LDR_I(rd[0], rm, off + 4), ctx);
 		break;
 	}
-	arm_bpf_put_reg32(dst[1], rd[1], ctx);
-	if (sz == BPF_DW)
-		arm_bpf_put_reg32(dst[0], rd[0], ctx);
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* Arithmatic Operation */
@@ -982,11 +995,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	const s8 *tmp = bpf2a32[TMP_REG_1];
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
 	const s8 *tcc = bpf2a32[TCALL_CNT];
+	const s8 *tc;
 	const int idx0 = ctx->idx;
 #define cur_offset (ctx->idx - idx0)
 #define jmp_offset (out_offset - (cur_offset) - 2)
 	u32 off, lo, hi;
-	s8 r_array, r_index, r_tc_lo, r_tc_hi;
+	s8 r_array, r_index;
 
 	/* if (index >= array->map.max_entries)
 	 *	goto out;
@@ -1008,15 +1022,13 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	lo = (u32)MAX_TAIL_CALL_CNT;
 	hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32);
-	r_tc_lo = arm_bpf_get_reg32(tcc[1], tmp[1], ctx);
-	r_tc_hi = arm_bpf_get_reg32(tcc[0], tmp[0], ctx);
-	emit(ARM_CMP_I(r_tc_hi, hi), ctx);
-	_emit(ARM_COND_EQ, ARM_CMP_I(r_tc_lo, lo), ctx);
+	tc = arm_bpf_get_reg64(tcc, tmp, ctx);
+	emit(ARM_CMP_I(tc[0], hi), ctx);
+	_emit(ARM_COND_EQ, ARM_CMP_I(tc[1], lo), ctx);
 	_emit(ARM_COND_HI, ARM_B(jmp_offset), ctx);
-	emit(ARM_ADDS_I(r_tc_lo, r_tc_lo, 1), ctx);
-	emit(ARM_ADC_I(r_tc_hi, r_tc_hi, 0), ctx);
-	arm_bpf_put_reg32(tcc[1], r_tc_lo, ctx);
-	arm_bpf_put_reg32(tcc[0], r_tc_hi, ctx);
+	emit(ARM_ADDS_I(tc[1], tc[1], 1), ctx);
+	emit(ARM_ADC_I(tc[0], tc[0], 0), ctx);
+	arm_bpf_put_reg64(tcc, tmp, ctx);
 
 	/* prog = array->ptrs[index]
 	 * if (prog == NULL)
@@ -1183,7 +1195,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	const s32 imm = insn->imm;
 	const int i = insn - ctx->prog->insnsi;
 	const bool is64 = BPF_CLASS(code) == BPF_ALU64;
-	s8 rd, rt, rm, rn;
+	const s8 *rd, *rs;
+	s8 rd_lo, rt, rm, rn;
 	s32 jmp_offset;
 
 #define check_imm(bits, imm) do {				\
@@ -1270,7 +1283,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	case BPF_ALU | BPF_DIV | BPF_X:
 	case BPF_ALU | BPF_MOD | BPF_K:
 	case BPF_ALU | BPF_MOD | BPF_X:
-		rd = arm_bpf_get_reg32(dst_lo, tmp2[1], ctx);
+		rd_lo = arm_bpf_get_reg32(dst_lo, tmp2[1], ctx);
 		switch (BPF_SRC(code)) {
 		case BPF_X:
 			rt = arm_bpf_get_reg32(src_lo, tmp2[0], ctx);
@@ -1283,8 +1296,8 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			rt = src_lo;
 			break;
 		}
-		emit_udivmod(rd, rd, rt, ctx, BPF_OP(code));
-		arm_bpf_put_reg32(dst_lo, rd, ctx);
+		emit_udivmod(rd_lo, rd_lo, rt, ctx, BPF_OP(code));
+		arm_bpf_put_reg32(dst_lo, rd_lo, ctx);
 		emit_a32_mov_i(dst_hi, 0, ctx);
 		break;
 	case BPF_ALU64 | BPF_DIV | BPF_K:
@@ -1364,21 +1377,20 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 	/* dst = htobe(dst) */
 	case BPF_ALU | BPF_END | BPF_FROM_LE:
 	case BPF_ALU | BPF_END | BPF_FROM_BE:
-		rt = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-		rd = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+		rd = arm_bpf_get_reg64(dst, tmp, ctx);
 		if (BPF_SRC(code) == BPF_FROM_LE)
 			goto emit_bswap_uxt;
 		switch (imm) {
 		case 16:
-			emit_rev16(rt, rt, ctx);
+			emit_rev16(rd[1], rd[1], ctx);
 			goto emit_bswap_uxt;
 		case 32:
-			emit_rev32(rt, rt, ctx);
+			emit_rev32(rd[1], rd[1], ctx);
 			goto emit_bswap_uxt;
 		case 64:
-			emit_rev32(ARM_LR, rt, ctx);
-			emit_rev32(rt, rd, ctx);
-			emit(ARM_MOV_R(rd, ARM_LR), ctx);
+			emit_rev32(ARM_LR, rd[1], ctx);
+			emit_rev32(rd[1], rd[0], ctx);
+			emit(ARM_MOV_R(rd[0], ARM_LR), ctx);
 			break;
 		}
 		goto exit;
@@ -1388,23 +1400,22 @@ emit_bswap_uxt:
 			/* zero-extend 16 bits into 64 bits */
 #if __LINUX_ARM_ARCH__ < 6
 			emit_a32_mov_i(tmp2[1], 0xffff, ctx);
-			emit(ARM_AND_R(rt, rt, tmp2[1]), ctx);
+			emit(ARM_AND_R(rd[1], rd[1], tmp2[1]), ctx);
 #else /* ARMv6+ */
-			emit(ARM_UXTH(rt, rt), ctx);
+			emit(ARM_UXTH(rd[1], rd[1]), ctx);
 #endif
-			emit(ARM_EOR_R(rd, rd, rd), ctx);
+			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 32:
 			/* zero-extend 32 bits into 64 bits */
-			emit(ARM_EOR_R(rd, rd, rd), ctx);
+			emit(ARM_EOR_R(rd[0], rd[0], rd[0]), ctx);
 			break;
 		case 64:
 			/* nop */
 			break;
 		}
 exit:
-		arm_bpf_put_reg32(dst_lo, rt, ctx);
-		arm_bpf_put_reg32(dst_hi, rd, ctx);
+		arm_bpf_put_reg64(dst, rd, ctx);
 		break;
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
@@ -1459,15 +1470,14 @@ exit:
 	{
 		u8 sz = BPF_SIZE(code);
 
-		rn = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
-		rm = arm_bpf_get_reg32(src_hi, tmp2[0], ctx);
+		rs = arm_bpf_get_reg64(src, tmp2, ctx);
 
 		/* Store the value */
 		if (BPF_SIZE(code) == BPF_DW) {
-			emit_str_r(dst_lo, rn, off, ctx, BPF_W);
-			emit_str_r(dst_lo, rm, off+4, ctx, BPF_W);
+			emit_str_r(dst_lo, rs[1], off, ctx, BPF_W);
+			emit_str_r(dst_lo, rs[0], off+4, ctx, BPF_W);
 		} else {
-			emit_str_r(dst_lo, rn, off, ctx, sz);
+			emit_str_r(dst_lo, rs[1], off, ctx, sz);
 		}
 		break;
 	}
@@ -1527,11 +1537,10 @@ exit:
 		emit_a32_mov_i64(true, tmp2, imm, ctx);
 go_jmp:
 		/* Setup destination register */
-		rt = arm_bpf_get_reg32(dst_lo, tmp[1], ctx);
-		rd = arm_bpf_get_reg32(dst_hi, tmp[0], ctx);
+		rd = arm_bpf_get_reg64(dst, tmp, ctx);
 
 		/* Check for the condition */
-		emit_ar_r(rd, rt, rm, rn, ctx, BPF_OP(code));
+		emit_ar_r(rd[0], rd[1], rm, rn, ctx, BPF_OP(code));
 
 		/* Setup JUMP instruction */
 		jmp_offset = bpf2a32_offset(i+off, i, ctx);
-- 
cgit v1.2.3


From 96cced4e774a2728710c8f8f48441fc7b29d6177 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:02 +0100
Subject: ARM: net: bpf: access eBPF scratch space using ARM FP register

Access the eBPF scratch space using the frame pointer rather than our
stack pointer, as the offsets from the ARM frame pointer are constant
across all eBPF programs.

Since we no longer reference the scratch space registers from the stack
pointer, this simplifies emit_push_r64() as it no longer needs to know
how many words are pushed onto the stack.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 44 +++++++++++++++++++++++++-------------------
 1 file changed, 25 insertions(+), 19 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 45a3599e94a4..753b5b2b2e3d 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -108,6 +108,12 @@ enum {
 #define STACK_OFFSET(k)	(-4 - (k) * 4)
 #define SCRATCH_SIZE	(BPF_JIT_SCRATCH_REGS * 4)
 
+#ifdef CONFIG_FRAME_POINTER
+#define EBPF_SCRATCH_TO_ARM_FP(x) ((x) - 4 * hweight16(CALLEE_PUSH_MASK) - 4)
+#else
+#define EBPF_SCRATCH_TO_ARM_FP(x) (x)
+#endif
+
 #define TMP_REG_1	(MAX_BPF_JIT_REG + 0)	/* TEMP Register 1 */
 #define TMP_REG_2	(MAX_BPF_JIT_REG + 1)	/* TEMP Register 2 */
 #define TCALL_CNT	(MAX_BPF_JIT_REG + 2)	/* Tail Call Count */
@@ -294,9 +300,6 @@ static void jit_fill_hole(void *area, unsigned int size)
 #define _STACK_SIZE	(ctx->prog->aux->stack_depth + SCRATCH_SIZE)
 #define STACK_SIZE	ALIGN(_STACK_SIZE, STACK_ALIGNMENT)
 
-/* Get the offset of eBPF REGISTERs stored on scratch space. */
-#define STACK_VAR(off) (STACK_SIZE + (off))
-
 #if __LINUX_ARM_ARCH__ < 7
 
 static u16 imm_offset(u32 k, struct jit_ctx *ctx)
@@ -472,7 +475,7 @@ static bool is_stacked(s8 reg)
 static s8 arm_bpf_get_reg32(s8 reg, s8 tmp, struct jit_ctx *ctx)
 {
 	if (is_stacked(reg)) {
-		emit(ARM_LDR_I(tmp, ARM_SP, STACK_VAR(reg)), ctx);
+		emit(ARM_LDR_I(tmp, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx);
 		reg = tmp;
 	}
 	return reg;
@@ -482,8 +485,10 @@ static const s8 *arm_bpf_get_reg64(const s8 *reg, const s8 *tmp,
 				   struct jit_ctx *ctx)
 {
 	if (is_stacked(reg[1])) {
-		emit(ARM_LDR_I(tmp[1], ARM_SP, STACK_VAR(reg[1])), ctx);
-		emit(ARM_LDR_I(tmp[0], ARM_SP, STACK_VAR(reg[0])), ctx);
+		emit(ARM_LDR_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[1])),
+		     ctx);
+		emit(ARM_LDR_I(tmp[0], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[0])),
+		     ctx);
 		reg = tmp;
 	}
 	return reg;
@@ -496,7 +501,7 @@ static const s8 *arm_bpf_get_reg64(const s8 *reg, const s8 *tmp,
 static void arm_bpf_put_reg32(s8 reg, s8 src, struct jit_ctx *ctx)
 {
 	if (is_stacked(reg))
-		emit(ARM_STR_I(src, ARM_SP, STACK_VAR(reg)), ctx);
+		emit(ARM_STR_I(src, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg)), ctx);
 	else if (reg != src)
 		emit(ARM_MOV_R(reg, src), ctx);
 }
@@ -505,8 +510,10 @@ static void arm_bpf_put_reg64(const s8 *reg, const s8 *src,
 			      struct jit_ctx *ctx)
 {
 	if (is_stacked(reg[1])) {
-		emit(ARM_STR_I(src[1], ARM_SP, STACK_VAR(reg[1])), ctx);
-		emit(ARM_STR_I(src[0], ARM_SP, STACK_VAR(reg[0])), ctx);
+		emit(ARM_STR_I(src[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[1])),
+		     ctx);
+		emit(ARM_STR_I(src[0], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[0])),
+		     ctx);
 	} else {
 		if (reg[1] != src[1])
 			emit(ARM_MOV_R(reg[1], src[1]), ctx);
@@ -1103,16 +1110,15 @@ static inline void emit_rev32(const u8 rd, const u8 rn, struct jit_ctx *ctx)
 }
 
 // push the scratch stack register on top of the stack
-static inline void emit_push_r64(const s8 src[], const u8 shift,
-		struct jit_ctx *ctx)
+static inline void emit_push_r64(const s8 src[], struct jit_ctx *ctx)
 {
 	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rt;
 	u16 reg_set = 0;
 
-	emit(ARM_LDR_I(tmp2[1], ARM_SP, STACK_VAR(src[1]+shift)), ctx);
-	emit(ARM_LDR_I(tmp2[0], ARM_SP, STACK_VAR(src[0]+shift)), ctx);
+	rt = arm_bpf_get_reg64(src, tmp2, ctx);
 
-	reg_set = (1 << tmp2[1]) | (1 << tmp2[0]);
+	reg_set = (1 << rt[1]) | (1 << rt[0]);
 	emit(ARM_PUSH(reg_set), ctx);
 }
 
@@ -1155,8 +1161,8 @@ static void build_prologue(struct jit_ctx *ctx)
 	emit(ARM_MOV_R(r3, r4), ctx);
 	emit(ARM_MOV_R(r2, r0), ctx);
 	/* Initialize Tail Count */
-	emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[0])), ctx);
-	emit(ARM_STR_I(r4, ARM_SP, STACK_VAR(tcc[1])), ctx);
+	emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[0])), ctx);
+	emit(ARM_STR_I(r4, ARM_FP, EBPF_SCRATCH_TO_ARM_FP(tcc[1])), ctx);
 	/* end of prologue */
 }
 
@@ -1606,9 +1612,9 @@ go_jmp:
 
 		emit_a32_mov_r64(true, r0, r1, ctx);
 		emit_a32_mov_r64(true, r1, r2, ctx);
-		emit_push_r64(r5, 0, ctx);
-		emit_push_r64(r4, 8, ctx);
-		emit_push_r64(r3, 16, ctx);
+		emit_push_r64(r5, ctx);
+		emit_push_r64(r4, ctx);
+		emit_push_r64(r3, ctx);
 
 		emit_a32_mov_i(tmp[1], func, ctx);
 		emit_blx_r(tmp[1], ctx);
-- 
cgit v1.2.3


From 1ca3b17b777c4136f9dba0195e13502c445f4ade Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:07 +0100
Subject: ARM: net: bpf: imm12 constant conversion

Provide a version of the imm8m() function that the compiler can optimise
when used with a constant expression.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 50 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 49 insertions(+), 1 deletion(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 753b5b2b2e3d..2cc66aa44dfe 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -236,10 +236,56 @@ static inline void emit(u32 inst, struct jit_ctx *ctx)
 	_emit(ARM_COND_AL, inst, ctx);
 }
 
+/*
+ * This is rather horrid, but necessary to convert an integer constant
+ * to an immediate operand for the opcodes, and be able to detect at
+ * build time whether the constant can't be converted (iow, usable in
+ * BUILD_BUG_ON()).
+ */
+#define imm12val(v, s) (rol32(v, (s)) | (s) << 7)
+#define const_imm8m(x)					\
+	({ int r;					\
+	   u32 v = (x);					\
+	   if (!(v & ~0x000000ff))			\
+		r = imm12val(v, 0);			\
+	   else if (!(v & ~0xc000003f))			\
+		r = imm12val(v, 2);			\
+	   else if (!(v & ~0xf000000f))			\
+		r = imm12val(v, 4);			\
+	   else if (!(v & ~0xfc000003))			\
+		r = imm12val(v, 6);			\
+	   else if (!(v & ~0xff000000))			\
+		r = imm12val(v, 8);			\
+	   else if (!(v & ~0x3fc00000))			\
+		r = imm12val(v, 10);			\
+	   else if (!(v & ~0x0ff00000))			\
+		r = imm12val(v, 12);			\
+	   else if (!(v & ~0x03fc0000))			\
+		r = imm12val(v, 14);			\
+	   else if (!(v & ~0x00ff0000))			\
+		r = imm12val(v, 16);			\
+	   else if (!(v & ~0x003fc000))			\
+		r = imm12val(v, 18);			\
+	   else if (!(v & ~0x000ff000))			\
+		r = imm12val(v, 20);			\
+	   else if (!(v & ~0x0003fc00))			\
+		r = imm12val(v, 22);			\
+	   else if (!(v & ~0x0000ff00))			\
+		r = imm12val(v, 24);			\
+	   else if (!(v & ~0x00003fc0))			\
+		r = imm12val(v, 26);			\
+	   else if (!(v & ~0x00000ff0))			\
+		r = imm12val(v, 28);			\
+	   else if (!(v & ~0x000003fc))			\
+		r = imm12val(v, 30);			\
+	   else						\
+		r = -1;					\
+	   r; })
+
 /*
  * Checks if immediate value can be converted to imm12(12 bits) value.
  */
-static int16_t imm8m(u32 x)
+static int imm8m(u32 x)
 {
 	u32 rot;
 
@@ -249,6 +295,8 @@ static int16_t imm8m(u32 x)
 	return -1;
 }
 
+#define imm8m(x) (__builtin_constant_p(x) ? const_imm8m(x) : imm8m(x))
+
 static u32 arm_bpf_ldst_imm12(u32 op, u8 rt, u8 rn, s16 imm12)
 {
 	op |= rt << 12 | rn << 16;
-- 
cgit v1.2.3


From 828e2b90e8e9b5bd844a25f22ceeb8df4dd18b07 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:12 +0100
Subject: ARM: net: bpf: use immediate forms of instructions where possible

Rather than moving constants to a register and then using them in a
subsequent instruction, use them directly in the desired instruction
cutting out the "middle" register.  This removes two instructions from
the tail call code path.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 21 ++++++++++++---------
 arch/arm/net/bpf_jit_32.h |  1 +
 2 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 2cc66aa44dfe..645653e1931e 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -304,7 +304,7 @@ static u32 arm_bpf_ldst_imm12(u32 op, u8 rt, u8 rn, s16 imm12)
 		op |= ARM_INST_LDST__U;
 	else
 		imm12 = -imm12;
-	return op | (imm12 & 0xfff);
+	return op | (imm12 & ARM_INST_LDST__IMM12);
 }
 
 static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
@@ -1054,17 +1054,19 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	const int idx0 = ctx->idx;
 #define cur_offset (ctx->idx - idx0)
 #define jmp_offset (out_offset - (cur_offset) - 2)
-	u32 off, lo, hi;
+	u32 lo, hi;
 	s8 r_array, r_index;
+	int off;
 
 	/* if (index >= array->map.max_entries)
 	 *	goto out;
 	 */
+	BUILD_BUG_ON(offsetof(struct bpf_array, map.max_entries) >
+		     ARM_INST_LDST__IMM12);
 	off = offsetof(struct bpf_array, map.max_entries);
 	/* array->map.max_entries */
-	emit_a32_mov_i(tmp[1], off, ctx);
 	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
-	emit(ARM_LDR_R(tmp[1], r_array, tmp[1]), ctx);
+	emit(ARM_LDR_I(tmp[1], r_array, off), ctx);
 	/* index is 32-bit for arrays */
 	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
 	/* index >= array->map.max_entries */
@@ -1089,10 +1091,10 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 * if (prog == NULL)
 	 *	goto out;
 	 */
-	off = offsetof(struct bpf_array, ptrs);
-	emit_a32_mov_i(tmp[1], off, ctx);
+	BUILD_BUG_ON(imm8m(offsetof(struct bpf_array, ptrs)) < 0);
+	off = imm8m(offsetof(struct bpf_array, ptrs));
 	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
-	emit(ARM_ADD_R(tmp[1], r_array, tmp[1]), ctx);
+	emit(ARM_ADD_I(tmp[1], r_array, off), ctx);
 	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
 	emit(ARM_MOV_SI(tmp[0], r_index, SRTYPE_ASL, 2), ctx);
 	emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx);
@@ -1100,9 +1102,10 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 
 	/* goto *(prog->bpf_func + prologue_size); */
+	BUILD_BUG_ON(offsetof(struct bpf_prog, bpf_func) >
+		     ARM_INST_LDST__IMM12);
 	off = offsetof(struct bpf_prog, bpf_func);
-	emit_a32_mov_i(tmp2[1], off, ctx);
-	emit(ARM_LDR_R(tmp[1], tmp[1], tmp2[1]), ctx);
+	emit(ARM_LDR_I(tmp[1], tmp[1], off), ctx);
 	emit(ARM_ADD_I(tmp[1], tmp[1], ctx->prologue_bytes), ctx);
 	emit_bx_r(tmp[1], ctx);
 
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index c55bc39d3e22..dee8a76fb0bc 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -78,6 +78,7 @@
 #define ARM_INST_EOR_I		0x02200000
 
 #define ARM_INST_LDST__U	0x00800000
+#define ARM_INST_LDST__IMM12	0x00000fff
 #define ARM_INST_LDRB_I		0x05500000
 #define ARM_INST_LDRB_R		0x07d00000
 #define ARM_INST_LDRH_I		0x015000b0
-- 
cgit v1.2.3


From 2b6958ef1151452cb2160fde75a5c5382b512c34 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:17 +0100
Subject: ARM: net: bpf: use ldr instructions with shifted rm register

Rather than pre-shifting the rm register for the ldr in the tail call,
shift it in the load instruction.  This eliminates one unnecessary
instruction.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 3 +--
 arch/arm/net/bpf_jit_32.h | 4 ++++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 645653e1931e..e22dc828420c 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1096,8 +1096,7 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
 	emit(ARM_ADD_I(tmp[1], r_array, off), ctx);
 	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
-	emit(ARM_MOV_SI(tmp[0], r_index, SRTYPE_ASL, 2), ctx);
-	emit(ARM_LDR_R(tmp[1], tmp[1], tmp[0]), ctx);
+	emit(ARM_LDR_R_SI(tmp[1], tmp[1], r_index, SRTYPE_ASL, 2), ctx);
 	emit(ARM_CMP_I(tmp[1], 0), ctx);
 	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
 
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index dee8a76fb0bc..e541a7a6139a 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -188,6 +188,10 @@
 #define ARM_LDR_R(rt, rn, rm)	(ARM_INST_LDR_R | ARM_INST_LDST__U \
 				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
+#define ARM_LDR_R_SI(rt, rn, rm, type, imm) \
+				(ARM_INST_LDR_R | ARM_INST_LDST__U \
+				 | (rt) << 12 | (rn) << 16 \
+				 | (imm) << 7 | (type) << 5 | (rm))
 #define ARM_LDRB_R(rt, rn, rm)	(ARM_INST_LDRB_R | ARM_INST_LDST__U \
 				 | (rt) << 12 | (rn) << 16 \
 				 | (rm))
-- 
cgit v1.2.3


From aaffd2f5c3d58f154ca7b3d104a2ee6b6e40bc6b Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:22 +0100
Subject: ARM: net: bpf: avoid reloading 'index'

Avoid reloading 'index' after we have validated it - it remains in
tmp2[1] up to the point that we begin the code to index the pointer
array, so with a little rearrangement of the registers, we can use
the already loaded value.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index e22dc828420c..0a8b3d0903c4 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1073,6 +1073,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	emit(ARM_CMP_R(r_index, tmp[1]), ctx);
 	_emit(ARM_COND_CS, ARM_B(jmp_offset), ctx);
 
+	/* tmp2[1] = index */
+
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
 	 * tail_call_cnt++;
@@ -1093,9 +1095,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	BUILD_BUG_ON(imm8m(offsetof(struct bpf_array, ptrs)) < 0);
 	off = imm8m(offsetof(struct bpf_array, ptrs));
-	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
+	r_array = arm_bpf_get_reg32(r2[1], tmp2[0], ctx);
 	emit(ARM_ADD_I(tmp[1], r_array, off), ctx);
-	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
 	emit(ARM_LDR_R_SI(tmp[1], tmp[1], r_index, SRTYPE_ASL, 2), ctx);
 	emit(ARM_CMP_I(tmp[1], 0), ctx);
 	_emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx);
-- 
cgit v1.2.3


From b50452299864fbc00a576241e1490541c8754d50 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:28 +0100
Subject: ARM: net: bpf: avoid reloading 'array'

Rearranging the order of the initial tail call code a little allows is
to avoid reloading the 'array' pointer.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 0a8b3d0903c4..f0cad9692952 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -1064,16 +1064,16 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	BUILD_BUG_ON(offsetof(struct bpf_array, map.max_entries) >
 		     ARM_INST_LDST__IMM12);
 	off = offsetof(struct bpf_array, map.max_entries);
-	/* array->map.max_entries */
-	r_array = arm_bpf_get_reg32(r2[1], tmp2[1], ctx);
-	emit(ARM_LDR_I(tmp[1], r_array, off), ctx);
+	r_array = arm_bpf_get_reg32(r2[1], tmp2[0], ctx);
 	/* index is 32-bit for arrays */
 	r_index = arm_bpf_get_reg32(r3[1], tmp2[1], ctx);
+	/* array->map.max_entries */
+	emit(ARM_LDR_I(tmp[1], r_array, off), ctx);
 	/* index >= array->map.max_entries */
 	emit(ARM_CMP_R(r_index, tmp[1]), ctx);
 	_emit(ARM_COND_CS, ARM_B(jmp_offset), ctx);
 
-	/* tmp2[1] = index */
+	/* tmp2[0] = array, tmp2[1] = index */
 
 	/* if (tail_call_cnt > MAX_TAIL_CALL_CNT)
 	 *	goto out;
@@ -1095,7 +1095,6 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
 	 */
 	BUILD_BUG_ON(imm8m(offsetof(struct bpf_array, ptrs)) < 0);
 	off = imm8m(offsetof(struct bpf_array, ptrs));
-	r_array = arm_bpf_get_reg32(r2[1], tmp2[0], ctx);
 	emit(ARM_ADD_I(tmp[1], r_array, off), ctx);
 	emit(ARM_LDR_R_SI(tmp[1], tmp[1], r_index, SRTYPE_ASL, 2), ctx);
 	emit(ARM_CMP_I(tmp[1], 0), ctx);
-- 
cgit v1.2.3


From bef8968df8a6e3eb91081d68affc64b8d87d5721 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:33 +0100
Subject: ARM: net: bpf: always use odd/even register pair

Always use an odd/even register pair for our 64-bit registers, so that
we're able to use the double-word load/store instructions in the future.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index f0cad9692952..006ff9615850 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -47,27 +47,27 @@
  * The callee saved registers depends on whether frame pointers are enabled.
  * With frame pointers (to be compliant with the ABI):
  *
- *                                high
- * original ARM_SP =>     +------------------+ \
- *                        |        pc        | |
- * current ARM_FP =>      +------------------+ } callee saved registers
- *                        |r4-r8,r10,fp,ip,lr| |
- *                        +------------------+ /
- *                                low
+ *                              high
+ * original ARM_SP =>     +--------------+ \
+ *                        |      pc      | |
+ * current ARM_FP =>      +--------------+ } callee saved registers
+ *                        |r4-r9,fp,ip,lr| |
+ *                        +--------------+ /
+ *                              low
  *
  * Without frame pointers:
  *
- *                                high
- * original ARM_SP =>     +------------------+
- *                        | r4-r8,r10,fp,lr  | callee saved registers
- * current ARM_FP =>      +------------------+
- *                                low
+ *                              high
+ * original ARM_SP =>     +--------------+
+ *                        |  r4-r9,fp,lr | callee saved registers
+ * current ARM_FP =>      +--------------+
+ *                              low
  *
  * When popping registers off the stack at the end of a BPF function, we
  * reference them via the current ARM_FP register.
  */
 #define CALLEE_MASK	(1 << ARM_R4 | 1 << ARM_R5 | 1 << ARM_R6 | \
-			 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R10 | \
+			 1 << ARM_R7 | 1 << ARM_R8 | 1 << ARM_R9 | \
 			 1 << ARM_FP)
 #define CALLEE_PUSH_MASK (CALLEE_MASK | 1 << ARM_LR)
 #define CALLEE_POP_MASK  (CALLEE_MASK | 1 << ARM_PC)
@@ -157,7 +157,7 @@ static const s8 bpf2a32[][2] = {
 	 * for constant blindings and others.
 	 */
 	[TMP_REG_1] = {ARM_R7, ARM_R6},
-	[TMP_REG_2] = {ARM_R10, ARM_R8},
+	[TMP_REG_2] = {ARM_R9, ARM_R8},
 	/* Tail call count. Stored on stack scratch space. */
 	[TCALL_CNT] = {STACK_OFFSET(BPF_TC_HI), STACK_OFFSET(BPF_TC_LO)},
 	/* temporary register for blinding constants.
-- 
cgit v1.2.3


From 8c9602d38c7262664c31332101f540c1e179797d Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jul 2018 10:32:38 +0100
Subject: ARM: net: bpf: use double-word load/stores where available

Use double-word load and stores where support for this instruction is
supported by the CPU architecture.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 55 ++++++++++++++++++++++++++++++++++++-----------
 arch/arm/net/bpf_jit_32.h |  2 ++
 2 files changed, 45 insertions(+), 12 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 006ff9615850..a9f68a924800 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -22,6 +22,7 @@
 #include <asm/cacheflush.h>
 #include <asm/hwcap.h>
 #include <asm/opcodes.h>
+#include <asm/system_info.h>
 
 #include "bpf_jit_32.h"
 
@@ -192,6 +193,7 @@ struct jit_ctx {
 	unsigned int idx;
 	unsigned int prologue_bytes;
 	unsigned int epilogue_offset;
+	unsigned int cpu_architecture;
 	u32 flags;
 	u32 *offsets;
 	u32 *target;
@@ -319,10 +321,12 @@ static u32 arm_bpf_ldst_imm8(u32 op, u8 rt, u8 rn, s16 imm8)
 
 #define ARM_LDR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_LDR_I, rt, rn, off)
 #define ARM_LDRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_LDRB_I, rt, rn, off)
+#define ARM_LDRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRD_I, rt, rn, off)
 #define ARM_LDRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_LDRH_I, rt, rn, off)
 
 #define ARM_STR_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STR_I, rt, rn, off)
 #define ARM_STRB_I(rt, rn, off)	arm_bpf_ldst_imm12(ARM_INST_STRB_I, rt, rn, off)
+#define ARM_STRD_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_STRD_I, rt, rn, off)
 #define ARM_STRH_I(rt, rn, off)	arm_bpf_ldst_imm8(ARM_INST_STRH_I, rt, rn, off)
 
 /*
@@ -533,10 +537,16 @@ static const s8 *arm_bpf_get_reg64(const s8 *reg, const s8 *tmp,
 				   struct jit_ctx *ctx)
 {
 	if (is_stacked(reg[1])) {
-		emit(ARM_LDR_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[1])),
-		     ctx);
-		emit(ARM_LDR_I(tmp[0], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[0])),
-		     ctx);
+		if (__LINUX_ARM_ARCH__ >= 6 ||
+		    ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) {
+			emit(ARM_LDRD_I(tmp[1], ARM_FP,
+					EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+		} else {
+			emit(ARM_LDR_I(tmp[1], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+			emit(ARM_LDR_I(tmp[0], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx);
+		}
 		reg = tmp;
 	}
 	return reg;
@@ -558,10 +568,16 @@ static void arm_bpf_put_reg64(const s8 *reg, const s8 *src,
 			      struct jit_ctx *ctx)
 {
 	if (is_stacked(reg[1])) {
-		emit(ARM_STR_I(src[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[1])),
-		     ctx);
-		emit(ARM_STR_I(src[0], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(reg[0])),
-		     ctx);
+		if (__LINUX_ARM_ARCH__ >= 6 ||
+		    ctx->cpu_architecture >= CPU_ARCH_ARMv5TE) {
+			emit(ARM_STRD_I(src[1], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+		} else {
+			emit(ARM_STR_I(src[1], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[1])), ctx);
+			emit(ARM_STR_I(src[0], ARM_FP,
+				       EBPF_SCRATCH_TO_ARM_FP(reg[0])), ctx);
+		}
 	} else {
 		if (reg[1] != src[1])
 			emit(ARM_MOV_R(reg[1], src[1]), ctx);
@@ -711,13 +727,27 @@ static inline void emit_a32_mov_r(const s8 dst, const s8 src,
 static inline void emit_a32_mov_r64(const bool is64, const s8 dst[],
 				  const s8 src[],
 				  struct jit_ctx *ctx) {
-	emit_a32_mov_r(dst_lo, src_lo, ctx);
-	if (is64) {
+	if (!is64) {
+		emit_a32_mov_r(dst_lo, src_lo, ctx);
+		/* Zero out high 4 bytes */
+		emit_a32_mov_i(dst_hi, 0, ctx);
+	} else if (__LINUX_ARM_ARCH__ < 6 &&
+		   ctx->cpu_architecture < CPU_ARCH_ARMv5TE) {
 		/* complete 8 byte move */
+		emit_a32_mov_r(dst_lo, src_lo, ctx);
 		emit_a32_mov_r(dst_hi, src_hi, ctx);
+	} else if (is_stacked(src_lo) && is_stacked(dst_lo)) {
+		const u8 *tmp = bpf2a32[TMP_REG_1];
+
+		emit(ARM_LDRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx);
+		emit(ARM_STRD_I(tmp[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx);
+	} else if (is_stacked(src_lo)) {
+		emit(ARM_LDRD_I(dst[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(src_lo)), ctx);
+	} else if (is_stacked(dst_lo)) {
+		emit(ARM_STRD_I(src[1], ARM_FP, EBPF_SCRATCH_TO_ARM_FP(dst_lo)), ctx);
 	} else {
-		/* Zero out high 4 bytes */
-		emit_a32_mov_i(dst_hi, 0, ctx);
+		emit(ARM_MOV_R(dst[0], src[0]), ctx);
+		emit(ARM_MOV_R(dst[1], src[1]), ctx);
 	}
 }
 
@@ -1778,6 +1808,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 
 	memset(&ctx, 0, sizeof(ctx));
 	ctx.prog = prog;
+	ctx.cpu_architecture = cpu_architecture();
 
 	/* Not able to allocate memory for offsets[] , then
 	 * we must fall back to the interpreter
diff --git a/arch/arm/net/bpf_jit_32.h b/arch/arm/net/bpf_jit_32.h
index e541a7a6139a..f4e58bcdaa43 100644
--- a/arch/arm/net/bpf_jit_32.h
+++ b/arch/arm/net/bpf_jit_32.h
@@ -81,6 +81,7 @@
 #define ARM_INST_LDST__IMM12	0x00000fff
 #define ARM_INST_LDRB_I		0x05500000
 #define ARM_INST_LDRB_R		0x07d00000
+#define ARM_INST_LDRD_I		0x014000d0
 #define ARM_INST_LDRH_I		0x015000b0
 #define ARM_INST_LDRH_R		0x019000b0
 #define ARM_INST_LDR_I		0x05100000
@@ -128,6 +129,7 @@
 
 #define ARM_INST_STR_I		0x05000000
 #define ARM_INST_STRB_I		0x05400000
+#define ARM_INST_STRD_I		0x014000f0
 #define ARM_INST_STRH_I		0x014000b0
 
 #define ARM_INST_TST_R		0x01100000
-- 
cgit v1.2.3


From 7a6e55375d5c584c7c11cfdcaa8ad9d6cccb419d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 12 Jul 2018 16:41:18 +0200
Subject: hrtimer: Improve kernel message printing

  - Join split message for easier grepping,
  - Use pr_*() instead of printk*(),
  - Use %u to format unsigned cpu numbers.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180712144118.8819-1-geert+renesas@glider.be
---
 kernel/time/hrtimer.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 055a4a728c00..5c2af16c7c14 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -718,8 +718,8 @@ static void hrtimer_switch_to_hres(void)
 	struct hrtimer_cpu_base *base = this_cpu_ptr(&hrtimer_bases);
 
 	if (tick_init_highres()) {
-		printk(KERN_WARNING "Could not switch to high resolution "
-				    "mode on CPU %d\n", base->cpu);
+		pr_warn("Could not switch to high resolution mode on CPU %u\n",
+			base->cpu);
 		return;
 	}
 	base->hres_active = 1;
@@ -1573,8 +1573,7 @@ retry:
 	else
 		expires_next = ktime_add(now, delta);
 	tick_program_event(expires_next, 1);
-	printk_once(KERN_WARNING "hrtimer: interrupt took %llu ns\n",
-		    ktime_to_ns(delta));
+	pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta));
 }
 
 /* called with interrupts disabled */
-- 
cgit v1.2.3


From 2989360d9c6669d8ae64edc933088e640481b48b Mon Sep 17 00:00:00 2001
From: Reinette Chatre <reinette.chatre@intel.com>
Date: Wed, 11 Jul 2018 13:06:07 -0700
Subject: x86/intel_rdt: Fix possible circular lock dependency

Lockdep is reporting a possible circular locking dependency:

 ======================================================
 WARNING: possible circular locking dependency detected
 4.18.0-rc1-test-test+ #4 Not tainted
 ------------------------------------------------------
 user_example/766 is trying to acquire lock:
 0000000073479a0f (rdtgroup_mutex){+.+.}, at: pseudo_lock_dev_mmap

 but task is already holding lock:
 000000001ef7a35b (&mm->mmap_sem){++++}, at: vm_mmap_pgoff+0x9f/0x

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #2 (&mm->mmap_sem){++++}:
        _copy_to_user+0x1e/0x70
        filldir+0x91/0x100
        dcache_readdir+0x54/0x160
        iterate_dir+0x142/0x190
        __x64_sys_getdents+0xb9/0x170
        do_syscall_64+0x86/0x200
        entry_SYSCALL_64_after_hwframe+0x49/0xbe

 -> #1 (&sb->s_type->i_mutex_key#3){++++}:
        start_creating+0x60/0x100
        debugfs_create_dir+0xc/0xc0
        rdtgroup_pseudo_lock_create+0x217/0x4d0
        rdtgroup_schemata_write+0x313/0x3d0
        kernfs_fop_write+0xf0/0x1a0
        __vfs_write+0x36/0x190
        vfs_write+0xb7/0x190
        ksys_write+0x52/0xc0
        do_syscall_64+0x86/0x200
        entry_SYSCALL_64_after_hwframe+0x49/0xbe

 -> #0 (rdtgroup_mutex){+.+.}:
        __mutex_lock+0x80/0x9b0
        pseudo_lock_dev_mmap+0x2f/0x170
        mmap_region+0x3d6/0x610
        do_mmap+0x387/0x580
        vm_mmap_pgoff+0xcf/0x110
        ksys_mmap_pgoff+0x170/0x1f0
        do_syscall_64+0x86/0x200
        entry_SYSCALL_64_after_hwframe+0x49/0xbe

 other info that might help us debug this:

 Chain exists of:
   rdtgroup_mutex --> &sb->s_type->i_mutex_key#3 --> &mm->mmap_sem

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&mm->mmap_sem);
                                lock(&sb->s_type->i_mutex_key#3);
                                lock(&mm->mmap_sem);
   lock(rdtgroup_mutex);

  *** DEADLOCK ***

 1 lock held by user_example/766:
  #0: 000000001ef7a35b (&mm->mmap_sem){++++}, at: vm_mmap_pgoff+0x9f/0x110

rdtgroup_mutex is already being released temporarily during pseudo-lock
region creation to prevent the potential deadlock between rdtgroup_mutex
and mm->mmap_sem that is obtained during device_create(). Move the
debugfs creation into this area to avoid the same circular dependency.

Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
Cc: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/fffb57f9c6b8285904c9a60cc91ce21591af17fe.1531332480.git.reinette.chatre@intel.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 29 ++++++++++++++---------------
 1 file changed, 14 insertions(+), 15 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index 751c78f9992f..f80c58f8adc3 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -1254,19 +1254,10 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		goto out_cstates;
 	}
 
-	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
-		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
-						      debugfs_resctrl);
-		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
-			debugfs_create_file("pseudo_lock_measure", 0200,
-					    plr->debugfs_dir, rdtgrp,
-					    &pseudo_measure_fops);
-	}
-
 	ret = pseudo_lock_minor_get(&new_minor);
 	if (ret < 0) {
 		rdt_last_cmd_puts("unable to obtain a new minor number\n");
-		goto out_debugfs;
+		goto out_cstates;
 	}
 
 	/*
@@ -1275,11 +1266,20 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 	 *
 	 * The mutex has to be released temporarily to avoid a potential
 	 * deadlock with the mm->mmap_sem semaphore which is obtained in
-	 * the device_create() callpath below as well as before the mmap()
-	 * callback is called.
+	 * the device_create() and debugfs_create_dir() callpath below
+	 * as well as before the mmap() callback is called.
 	 */
 	mutex_unlock(&rdtgroup_mutex);
 
+	if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
+		plr->debugfs_dir = debugfs_create_dir(rdtgrp->kn->name,
+						      debugfs_resctrl);
+		if (!IS_ERR_OR_NULL(plr->debugfs_dir))
+			debugfs_create_file("pseudo_lock_measure", 0200,
+					    plr->debugfs_dir, rdtgrp,
+					    &pseudo_measure_fops);
+	}
+
 	dev = device_create(pseudo_lock_class, NULL,
 			    MKDEV(pseudo_lock_major, new_minor),
 			    rdtgrp, "%s", rdtgrp->kn->name);
@@ -1290,7 +1290,7 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 		ret = PTR_ERR(dev);
 		rdt_last_cmd_printf("failed to create character device: %d\n",
 				    ret);
-		goto out_minor;
+		goto out_debugfs;
 	}
 
 	/* We released the mutex - check if group was removed while we did so */
@@ -1311,10 +1311,9 @@ int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
 
 out_device:
 	device_destroy(pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
-out_minor:
-	pseudo_lock_minor_release(new_minor);
 out_debugfs:
 	debugfs_remove_recursive(plr->debugfs_dir);
+	pseudo_lock_minor_release(new_minor);
 out_cstates:
 	pseudo_lock_cstates_relax(plr);
 out_region:
-- 
cgit v1.2.3


From cba54f9cf4ec1126dde5576e025691c27f669d85 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 10 Jul 2018 18:22:31 -0700
Subject: tc-testing: add geneve options in tunnel_key unit tests

Extend tc tunnel_key action unit tests with geneve options. Tests
include testing single and multiple geneve options, as well as
testing geneve options that are expected to fail.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Acked-by: Lucas Bates <lucasb@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/tunnel_key.json    | 168 +++++++++++++++++++++
 1 file changed, 168 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
index d878ce1c7d08..10b2d894e436 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/tunnel_key.json
@@ -640,6 +640,174 @@
             "$TC actions flush action tunnel_key"
         ]
     },
+    {
+        "id": "4f20",
+        "name": "Add tunnel_key action with a single geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "e33d",
+        "name": "Add tunnel_key action with multiple geneve options parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344 index 1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:0040007611223344,0111:02:1020304011223344.*index 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "0778",
+        "name": "Add tunnel_key action with invalid class geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 824212:80:00880022 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 824212:80:00880022.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "4ae8",
+        "name": "Add tunnel_key action with invalid type geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:4224:00880022 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:4224:00880022.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "4039",
+        "name": "Add tunnel_key action with short data length geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "26a6",
+        "name": "Add tunnel_key action with non-multiple of 4 data length geneve option parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:4288428822 index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:4288428822.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
+    {
+        "id": "f44d",
+        "name": "Add tunnel_key action with incomplete geneve options parameter",
+        "category": [
+            "actions",
+            "tunnel_key"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action tunnel_key",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action tunnel_key set src_ip 1.1.1.1 dst_ip 2.2.2.2 id 42 dst_port 6081 geneve_opts 0102:80:00880022,0408:42: index 1",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action tunnel_key index 1",
+        "matchPattern": "action order [0-9]+: tunnel_key.*set.*src_ip 1.1.1.1.*dst_ip 2.2.2.2.*key_id 42.*dst_port 6081.*geneve_opt 0102:80:00880022,0408:42:.*index 1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC actions flush action tunnel_key"
+        ]
+    },
     {
         "id": "7afc",
         "name": "Replace tunnel_key set action with all parameters",
-- 
cgit v1.2.3


From a8802d97e73346bc81609df9dfba7d3306f40d87 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 11 Jul 2018 11:16:41 -0700
Subject: ktime: Provide typesafe ktime_to_ns()

Using ktime_to_ns() is nice to help backports to stable kernels.

Having a typesafe function instead of a macro avoid stupid typos
and waste of time tracking these typos.

Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Eric Dumazet <eric.dumazet@gmail.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20180711181641.10369-1-edumazet@google.com
---
 include/linux/ktime.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 5b9fddbaac41..b2bb44f87f5a 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -93,8 +93,11 @@ static inline ktime_t timeval_to_ktime(struct timeval tv)
 /* Map the ktime_t to timeval conversion to ns_to_timeval function */
 #define ktime_to_timeval(kt)		ns_to_timeval((kt))
 
-/* Convert ktime_t to nanoseconds - NOP in the scalar storage format: */
-#define ktime_to_ns(kt)			(kt)
+/* Convert ktime_t to nanoseconds */
+static inline s64 ktime_to_ns(const ktime_t kt)
+{
+	return kt;
+}
 
 /**
  * ktime_compare - Compares two ktime_t variables for less, greater or equal
-- 
cgit v1.2.3


From fcc63543650150629c8a873cbef3578770acecd9 Mon Sep 17 00:00:00 2001
From: Boqun Feng <boqun.feng@gmail.com>
Date: Fri, 15 Jun 2018 12:06:31 -0700
Subject: rcu: Make expedited GPs handle CPU 0 being offline

Currently, the parallelized initialization of expedited grace periods uses
the workqueue associated with each rcu_node structure's ->grplo field.
This works fine unless that CPU is offline.  This commit therefore uses
the CPU corresponding to the lowest-numbered online CPU, or just queues
the work on WORK_CPU_UNBOUND if there are no online CPUs corresponding
to this rcu_node structure.

Note that this patch uses cpu_is_offline() instead of the usual approach
of checking bits in the rcu_node structure's ->qsmaskinitnext field.  This
is safe because preemption is disabled across both the cpu_is_offline()
check and the call to queue_work_on().

Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
[ paulmck: Disable preemption to close offline race window. ]
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Apply Peter Zijlstra feedback on CPU selection. ]
Tested-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
---
 kernel/rcu/tree_exp.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index c6385ee1af65..b3df3b770afb 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -472,6 +472,7 @@ retry_ipi:
 static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 				     smp_call_func_t func)
 {
+	int cpu;
 	struct rcu_node *rnp;
 
 	trace_rcu_exp_grace_period(rsp->name, rcu_exp_gp_seq_endval(rsp), TPS("reset"));
@@ -493,7 +494,13 @@ static void sync_rcu_exp_select_cpus(struct rcu_state *rsp,
 			continue;
 		}
 		INIT_WORK(&rnp->rew.rew_work, sync_rcu_exp_select_node_cpus);
-		queue_work_on(rnp->grplo, rcu_par_gp_wq, &rnp->rew.rew_work);
+		preempt_disable();
+		cpu = cpumask_next(rnp->grplo - 1, cpu_online_mask);
+		/* If all offline, queue the work on an unbound CPU. */
+		if (unlikely(cpu > rnp->grphi))
+			cpu = WORK_CPU_UNBOUND;
+		queue_work_on(cpu, rcu_par_gp_wq, &rnp->rew.rew_work);
+		preempt_enable();
 		rnp->exp_need_flush = true;
 	}
 
-- 
cgit v1.2.3


From ea870bb2ae6cbc1a5ba1f3ec8c8fca921a51880b Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Thu, 12 Jul 2018 22:29:16 +0200
Subject: block: skd: Use %pad printk format for dma_addr_t values

Use the existing %pad printk format to print dma_addr_t values.
This avoids the following warnings when compiling on the parisc64 platform:

drivers/block/skd_main.c: In function 'skd_preop_sg_list':
drivers/block/skd_main.c:660:4: warning: format '%llx' expects argument of type 'long long unsigned int', but argument 6 has type 'dma_addr_t {aka unsigned int}' [-Wformat=]

Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Helge Deller <deller@gmx.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/skd_main.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c
index bc7aea6d7b7c..87b9e7fbf062 100644
--- a/drivers/block/skd_main.c
+++ b/drivers/block/skd_main.c
@@ -657,8 +657,8 @@ static bool skd_preop_sg_list(struct skd_device *skdev,
 
 	if (unlikely(skdev->dbg_level > 1)) {
 		dev_dbg(&skdev->pdev->dev,
-			"skreq=%x sksg_list=%p sksg_dma=%llx\n",
-			skreq->id, skreq->sksg_list, skreq->sksg_dma_address);
+			"skreq=%x sksg_list=%p sksg_dma=%pad\n",
+			skreq->id, skreq->sksg_list, &skreq->sksg_dma_address);
 		for (i = 0; i < n_sg; i++) {
 			struct fit_sg_descriptor *sgd = &skreq->sksg_list[i];
 
@@ -1190,8 +1190,8 @@ static void skd_send_fitmsg(struct skd_device *skdev,
 {
 	u64 qcmd;
 
-	dev_dbg(&skdev->pdev->dev, "dma address 0x%llx, busy=%d\n",
-		skmsg->mb_dma_address, skd_in_flight(skdev));
+	dev_dbg(&skdev->pdev->dev, "dma address %pad, busy=%d\n",
+		&skmsg->mb_dma_address, skd_in_flight(skdev));
 	dev_dbg(&skdev->pdev->dev, "msg_buf %p\n", skmsg->msg_buf);
 
 	qcmd = skmsg->mb_dma_address;
@@ -1250,9 +1250,9 @@ static void skd_send_special_fitmsg(struct skd_device *skdev,
 		}
 
 		dev_dbg(&skdev->pdev->dev,
-			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%llx\n",
+			"skspcl=%p id=%04x sksg_list=%p sksg_dma=%pad\n",
 			skspcl, skspcl->req.id, skspcl->req.sksg_list,
-			skspcl->req.sksg_dma_address);
+			&skspcl->req.sksg_dma_address);
 		for (i = 0; i < skspcl->req.n_sg; i++) {
 			struct fit_sg_descriptor *sgd =
 				&skspcl->req.sksg_list[i];
@@ -2685,8 +2685,8 @@ static int skd_cons_skmsg(struct skd_device *skdev)
 
 		WARN(((uintptr_t)skmsg->msg_buf | skmsg->mb_dma_address) &
 		     (FIT_QCMD_ALIGN - 1),
-		     "not aligned: msg_buf %p mb_dma_address %#llx\n",
-		     skmsg->msg_buf, skmsg->mb_dma_address);
+		     "not aligned: msg_buf %p mb_dma_address %pad\n",
+		     skmsg->msg_buf, &skmsg->mb_dma_address);
 		memset(skmsg->msg_buf, 0, SKD_N_FITMSG_BYTES);
 	}
 
-- 
cgit v1.2.3


From 26d950a9451336a6b5abc1c8ca6c21df58e8d89f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 21 Apr 2018 20:44:11 -0700
Subject: rcu: Diagnostics for grace-period startup hangs

This commit causes a splat if RCU is idle and a request for a new grace
period is ignored for more than one second.  This splat normally indicates
that some code path asked for a new grace period, but failed to wake up
the RCU grace-period kthread.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Fix bug located by Dan Carpenter and his static checker. ]
[ paulmck: Fix self-deadlock bug located 0day test robot. ]
[ paulmck: Disable unless CONFIG_PROVE_RCU=y. ]
---
 kernel/rcu/tree.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++++--
 kernel/rcu/tree.h |  2 ++
 2 files changed, 66 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b1fffa21b9e4..6ce82c009195 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1681,6 +1681,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	}
 	trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
 	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
+	rsp->gp_req_activity = jiffies;
 	if (!rsp->gp_kthread) {
 		trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
 		goto unlock_out;
@@ -2113,6 +2114,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	/* Advance CBs to reduce false positives below. */
 	if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
 		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
+		rsp->gp_req_activity = jiffies;
 		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
 				       TPS("newreq"));
 	}
@@ -2744,6 +2746,65 @@ static void force_quiescent_state(struct rcu_state *rsp)
 	rcu_gp_kthread_wake(rsp);
 }
 
+/*
+ * This function checks for grace-period requests that fail to motivate
+ * RCU to come out of its idle mode.
+ */
+static void
+rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
+			 struct rcu_data *rdp)
+{
+	unsigned long flags;
+	unsigned long j;
+	struct rcu_node *rnp_root = rcu_get_root(rsp);
+	static atomic_t warned = ATOMIC_INIT(0);
+
+	if (!IS_ENABLED(CONFIG_PROVE_RCU) ||
+	    rcu_gp_in_progress(rsp) || !need_any_future_gp(rcu_get_root(rsp)))
+		return;
+	j = jiffies; /* Expensive access, and in common case don't get here. */
+	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + HZ) ||
+	    atomic_read(&warned))
+		return;
+
+	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	j = jiffies;
+	if (rcu_gp_in_progress(rsp) || !need_any_future_gp(rcu_get_root(rsp)) ||
+	    time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + HZ) ||
+	    atomic_read(&warned)) {
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	/* Hold onto the leaf lock to make others see warned==1. */
+
+	if (rnp_root != rnp)
+		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
+	j = jiffies;
+	if (rcu_gp_in_progress(rsp) || !need_any_future_gp(rcu_get_root(rsp)) ||
+	    time_before(j, rsp->gp_req_activity + HZ) ||
+	    time_before(j, rsp->gp_activity + HZ) ||
+	    atomic_xchg(&warned, 1)) {
+		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		return;
+	}
+	pr_alert("%s: g%lu %d%d%d%d gar:%lu ga:%lu f%#x %s->state:%#lx\n",
+		 __func__, READ_ONCE(rsp->gpnum),
+		 need_future_gp_element(rcu_get_root(rsp), 0),
+		 need_future_gp_element(rcu_get_root(rsp), 1),
+		 need_future_gp_element(rcu_get_root(rsp), 2),
+		 need_future_gp_element(rcu_get_root(rsp), 3),
+		 j - rsp->gp_req_activity, j - rsp->gp_activity,
+		 rsp->gp_flags, rsp->name,
+		 rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
+	WARN_ON(1);
+	if (rnp_root != rnp)
+		raw_spin_unlock_rcu_node(rnp_root);
+	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+}
+
 /*
  * This does the RCU core processing work for the specified rcu_state
  * and rcu_data structures.  This may be called only from the CPU to
@@ -2755,7 +2816,7 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	unsigned long flags;
 	bool needwake;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
-	struct rcu_node *rnp;
+	struct rcu_node *rnp = rdp->mynode;
 
 	WARN_ON_ONCE(!rdp->beenonline);
 
@@ -2769,7 +2830,6 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 		if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
 			local_irq_restore(flags);
 		} else {
-			rnp = rdp->mynode;
 			raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
 			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
@@ -2778,6 +2838,8 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 		}
 	}
 
+	rcu_check_gp_start_stall(rsp, rnp, rdp);
+
 	/* If there are callbacks ready, invoke them. */
 	if (rcu_segcblist_ready_cbs(&rdp->cblist))
 		invoke_rcu_callbacks(rsp, rdp);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 7365ac53fdd9..3c1942174c56 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -374,6 +374,8 @@ struct rcu_state {
 						/*  but in jiffies. */
 	unsigned long gp_activity;		/* Time of last GP kthread */
 						/*  activity in jiffies. */
+	unsigned long gp_req_activity;		/* Time of last GP request */
+						/*  in jiffies. */
 	unsigned long jiffies_stall;		/* Time at which to check */
 						/*  for CPU stalls. */
 	unsigned long jiffies_resched;		/* Time at which to resched */
-- 
cgit v1.2.3


From 18390aeae7010ee56b132dcfb663ba362a099d99 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 22 Apr 2018 15:06:05 -0700
Subject: rcu: Make rcu_gp_cleanup() write only once to ->gp_flags

At the end of rcu_gp_cleanup(), if another grace period is needed, but
not via rcu_accelerate_cbs(), the ->gp_flags field is written twice,
once when making the new grace-period request, and once when clearing
all other types of requests.  This commit therefore adds an else-clause
to avoid this double write.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6ce82c009195..a9a4a260ea7d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2117,8 +2117,9 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		rsp->gp_req_activity = jiffies;
 		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
 				       TPS("newreq"));
+	} else {
+		WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
 	}
-	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
 	raw_spin_unlock_irq_rcu_node(rnp);
 }
 
-- 
cgit v1.2.3


From de30ad512a668b56e7ad7a5a7c379d7c5d138a94 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 26 Apr 2018 11:52:09 -0700
Subject: rcu: Introduce grace-period sequence numbers

This commit adds grace-period sequence numbers (->gp_seq) to the
rcu_state, rcu_node, and rcu_data structures, and updates them.
It also checks for consistency between rsp->gpnum and rsp->gp_seq.
These ->gp_seq counters will eventually replace the existing ->gpnum
and ->completed counters, allowing a single memory access to determine
whether or not a grace period is in progress and if so, which one.
This in turn will enable changes that will reduce ->lock contention on
the leaf rcu_node structures.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 16 +++++++++++++++-
 kernel/rcu/tree.h |  3 +++
 2 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a9a4a260ea7d..467cd8e5c6ff 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -97,6 +97,7 @@ struct rcu_state sname##_state = { \
 	.gp_state = RCU_GP_IDLE, \
 	.gpnum = 0UL - 300UL, \
 	.completed = 0UL - 300UL, \
+	.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.name = RCU_STATE_NAME(sname), \
 	.abbr = sabbr, \
@@ -1849,6 +1850,8 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		WRITE_ONCE(rdp->gpwrap, false);
 		rcu_gpnum_ovf(rnp, rdp);
 	}
+	if (rdp->gp_seq != rnp->gp_seq)
+		rdp->gp_seq = rnp->gp_seq;
 	return ret;
 }
 
@@ -1910,7 +1913,10 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	/* Advance to a new grace period and initialize state. */
 	record_gp_stall_check_time(rsp);
 	/* Record GP times before starting GP, hence smp_store_release(). */
+	WARN_ON_ONCE(rsp->gpnum << RCU_SEQ_CTR_SHIFT != rsp->gp_seq);
 	smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
+	smp_mb(); /* Pairs with barriers in stall-warning code. */
+	rcu_seq_start(&rsp->gp_seq);
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
@@ -1984,6 +1990,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		WRITE_ONCE(rnp->gpnum, rsp->gpnum);
 		if (WARN_ON_ONCE(rnp->completed != rsp->completed))
 			WRITE_ONCE(rnp->completed, rsp->completed);
+		WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
@@ -2050,6 +2057,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 {
 	unsigned long gp_duration;
 	bool needgp = false;
+	unsigned long new_gp_seq;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	struct swait_queue_head *sq;
@@ -2079,12 +2087,15 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 * all of the rcu_node structures before the beginning of the next
 	 * grace period is recorded in any of the rcu_node structures.
 	 */
+	new_gp_seq = rsp->gp_seq;
+	rcu_seq_end(&new_gp_seq);
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
 			dump_blkd_tasks(rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->completed, rsp->gpnum);
+		WRITE_ONCE(rnp->gp_seq, new_gp_seq);
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
 			needgp = __note_gp_changes(rsp, rnp, rdp) || needgp;
@@ -2098,10 +2109,11 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		rcu_gp_slow(rsp, gp_cleanup_delay);
 	}
 	rnp = rcu_get_root(rsp);
-	raw_spin_lock_irq_rcu_node(rnp); /* Order GP before ->completed update. */
+	raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */
 
 	/* Declare grace period done. */
 	WRITE_ONCE(rsp->completed, rsp->gpnum);
+	rcu_seq_end(&rsp->gp_seq);
 	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
 	rsp->gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
@@ -3612,6 +3624,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->beenonline = true;	 /* We have now been online. */
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
+	rdp->gp_seq = rnp->gp_seq;
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
@@ -3991,6 +4004,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 						   &rcu_fqs_class[i], fqs[i]);
 			rnp->gpnum = rsp->gpnum;
 			rnp->completed = rsp->completed;
+			rnp->gp_seq = rsp->gp_seq;
 			rnp->completedqs = rsp->completed;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 3c1942174c56..50a28d1cf5a1 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -87,6 +87,7 @@ struct rcu_node {
 	unsigned long completed; /* Last GP completed for this node. */
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
+	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
 	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
@@ -211,6 +212,7 @@ struct rcu_data {
 					/*  in order to detect GP end. */
 	unsigned long	gpnum;		/* Highest gp number that this CPU */
 					/*  is aware of having started. */
+	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
 	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
 					/*  for rcu_all_qs() invocations. */
 	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
@@ -343,6 +345,7 @@ struct rcu_state {
 						/* Subject to priority boost. */
 	unsigned long gpnum;			/* Current gp number. */
 	unsigned long completed;		/* # of last completed gp. */
+	unsigned long gp_seq;			/* Grace-period sequence #. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	struct swait_queue_head gp_wq;		/* Where GP task waits. */
 	short gp_flags;				/* Commands for GP task. */
-- 
cgit v1.2.3


From dee4f42298bba030e84035aca5c114f9fee8fa6a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 26 Apr 2018 15:30:28 -0700
Subject: rcu: Move rcu_gp_slow() to ->gp_seq

This commit moves rcu_gp_slow() to ->gp_seq.  This function only uses
the grace-period number to modulate delay, so rcu_seq_ctr(rsp->gp_seq)
gets the same effect, at least in cases where the delay is to happen
more than four times per wrap of an unsigned long.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 467cd8e5c6ff..3c3af7e2758f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1879,7 +1879,8 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 static void rcu_gp_slow(struct rcu_state *rsp, int delay)
 {
 	if (delay > 0 &&
-	    !(rsp->gpnum % (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
+	    !(rcu_seq_ctr(rsp->gp_seq) %
+	      (rcu_num_nodes * PER_RCU_NODE_PERIOD * delay)))
 		schedule_timeout_uninterruptible(delay);
 }
 
-- 
cgit v1.2.3


From 17ef2fe97c8c8e754e4a702c42f8e5b0ffadf4dd Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 11:39:34 -0700
Subject: rcu: Make rcutorture's batches-completed API use ->gp_seq

The rcutorture test invokes rcu_batches_started(),
rcu_batches_completed(), rcu_batches_started_bh(),
rcu_batches_completed_bh(), rcu_batches_started_sched(), and
rcu_batches_completed_sched() to do grace-period consistency checks,
and rcuperf uses the _completed variants for statistics.
These functions use ->gpnum and ->completed.  This commit therefore
replaces them with rcu_get_gp_seq(), rcu_bh_get_gp_seq(), and
rcu_sched_get_gp_seq(), adjusting rcutorture and rcuperf to make
use of them.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h        | 18 ++++++-----------
 kernel/rcu/rcuperf.c    | 26 +++++++++----------------
 kernel/rcu/rcutorture.c | 50 +++++++++++++++++-------------------------------
 kernel/rcu/tree.c       | 51 ++++++++++++-------------------------------------
 4 files changed, 45 insertions(+), 100 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index db0870acfdff..f0907f9f6cd0 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -463,12 +463,9 @@ void srcutorture_get_gp_data(enum rcutorture_type test_type,
 #endif
 
 #ifdef CONFIG_TINY_RCU
-static inline unsigned long rcu_batches_started(void) { return 0; }
-static inline unsigned long rcu_batches_started_bh(void) { return 0; }
-static inline unsigned long rcu_batches_started_sched(void) { return 0; }
-static inline unsigned long rcu_batches_completed(void) { return 0; }
-static inline unsigned long rcu_batches_completed_bh(void) { return 0; }
-static inline unsigned long rcu_batches_completed_sched(void) { return 0; }
+static inline unsigned long rcu_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_bh_get_gp_seq(void) { return 0; }
+static inline unsigned long rcu_sched_get_gp_seq(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed(void) { return 0; }
 static inline unsigned long rcu_exp_batches_completed_sched(void) { return 0; }
 static inline unsigned long
@@ -480,12 +477,9 @@ static inline void show_rcu_gp_kthreads(void) { }
 #else /* #ifdef CONFIG_TINY_RCU */
 extern unsigned long rcutorture_testseq;
 extern unsigned long rcutorture_vernum;
-unsigned long rcu_batches_started(void);
-unsigned long rcu_batches_started_bh(void);
-unsigned long rcu_batches_started_sched(void);
-unsigned long rcu_batches_completed(void);
-unsigned long rcu_batches_completed_bh(void);
-unsigned long rcu_batches_completed_sched(void);
+unsigned long rcu_get_gp_seq(void);
+unsigned long rcu_bh_get_gp_seq(void);
+unsigned long rcu_sched_get_gp_seq(void);
 unsigned long rcu_exp_batches_completed(void);
 unsigned long rcu_exp_batches_completed_sched(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index df29119b2013..2b5a613afcf3 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -138,8 +138,7 @@ struct rcu_perf_ops {
 	void (*cleanup)(void);
 	int (*readlock)(void);
 	void (*readunlock)(int idx);
-	unsigned long (*started)(void);
-	unsigned long (*completed)(void);
+	unsigned long (*get_gp_seq)(void);
 	unsigned long (*exp_completed)(void);
 	void (*async)(struct rcu_head *head, rcu_callback_t func);
 	void (*gp_barrier)(void);
@@ -179,8 +178,7 @@ static struct rcu_perf_ops rcu_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= rcu_perf_read_lock,
 	.readunlock	= rcu_perf_read_unlock,
-	.started	= rcu_batches_started,
-	.completed	= rcu_batches_completed,
+	.get_gp_seq	= rcu_get_gp_seq,
 	.exp_completed	= rcu_exp_batches_completed,
 	.async		= call_rcu,
 	.gp_barrier	= rcu_barrier,
@@ -209,8 +207,7 @@ static struct rcu_perf_ops rcu_bh_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= rcu_bh_perf_read_lock,
 	.readunlock	= rcu_bh_perf_read_unlock,
-	.started	= rcu_batches_started_bh,
-	.completed	= rcu_batches_completed_bh,
+	.get_gp_seq	= rcu_bh_get_gp_seq,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_bh,
 	.gp_barrier	= rcu_barrier_bh,
@@ -266,8 +263,7 @@ static struct rcu_perf_ops srcu_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_perf_completed,
+	.get_gp_seq	= srcu_perf_completed,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -295,8 +291,7 @@ static struct rcu_perf_ops srcud_ops = {
 	.cleanup	= srcu_sync_perf_cleanup,
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_perf_completed,
+	.get_gp_seq	= srcu_perf_completed,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -325,8 +320,7 @@ static struct rcu_perf_ops sched_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= sched_perf_read_lock,
 	.readunlock	= sched_perf_read_unlock,
-	.started	= rcu_batches_started_sched,
-	.completed	= rcu_batches_completed_sched,
+	.get_gp_seq	= rcu_sched_get_gp_seq,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_sched,
 	.gp_barrier	= rcu_barrier_sched,
@@ -353,8 +347,7 @@ static struct rcu_perf_ops tasks_ops = {
 	.init		= rcu_sync_perf_init,
 	.readlock	= tasks_perf_read_lock,
 	.readunlock	= tasks_perf_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
 	.async		= call_rcu_tasks,
 	.gp_barrier	= rcu_barrier_tasks,
 	.sync		= synchronize_rcu_tasks,
@@ -447,8 +440,7 @@ rcu_perf_writer(void *arg)
 			b_rcu_perf_writer_started =
 				cur_ops->exp_completed() / 2;
 		} else {
-			b_rcu_perf_writer_started =
-				cur_ops->completed();
+			b_rcu_perf_writer_started = cur_ops->get_gp_seq();
 		}
 	}
 
@@ -505,7 +497,7 @@ retry:
 						cur_ops->exp_completed() / 2;
 				} else {
 					b_rcu_perf_writer_finished =
-						cur_ops->completed();
+						cur_ops->get_gp_seq();
 				}
 				if (shutdown) {
 					smp_mb(); /* Assign before wake. */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 5604bfac8df4..1f66597c7783 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -264,8 +264,7 @@ struct rcu_torture_ops {
 	int (*readlock)(void);
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
-	unsigned long (*started)(void);
-	unsigned long (*completed)(void);
+	unsigned long (*get_gp_seq)(void);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
@@ -305,10 +304,10 @@ static void rcu_read_delay(struct torture_random_state *rrsp)
 	 * force_quiescent_state. */
 
 	if (!(torture_random(rrsp) % (nrealreaders * 2000 * longdelay_ms))) {
-		started = cur_ops->completed();
+		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
 		mdelay(longdelay_ms);
-		completed = cur_ops->completed();
+		completed = cur_ops->get_gp_seq();
 		do_trace_rcu_torture_read(cur_ops->name, NULL, ts,
 					  started, completed);
 	}
@@ -400,8 +399,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
-	.started	= rcu_batches_started,
-	.completed	= rcu_batches_completed,
+	.get_gp_seq	= rcu_get_gp_seq,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
@@ -442,8 +440,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.readlock	= rcu_bh_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
-	.started	= rcu_batches_started_bh,
-	.completed	= rcu_batches_completed_bh,
+	.get_gp_seq	= rcu_bh_get_gp_seq,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
 	.exp_sync	= synchronize_rcu_bh_expedited,
@@ -486,8 +483,7 @@ static struct rcu_torture_ops rcu_busted_ops = {
 	.readlock	= rcu_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_torture_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_busted_torture_deferred_free,
 	.sync		= synchronize_rcu_busted,
 	.exp_sync	= synchronize_rcu_busted,
@@ -575,8 +571,7 @@ static struct rcu_torture_ops srcu_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_torture_completed,
+	.get_gp_seq	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
 	.exp_sync	= srcu_torture_synchronize_expedited,
@@ -613,8 +608,7 @@ static struct rcu_torture_ops srcud_ops = {
 	.readlock	= srcu_torture_read_lock,
 	.read_delay	= srcu_read_delay,
 	.readunlock	= srcu_torture_read_unlock,
-	.started	= NULL,
-	.completed	= srcu_torture_completed,
+	.get_gp_seq	= srcu_torture_completed,
 	.deferred_free	= srcu_torture_deferred_free,
 	.sync		= srcu_torture_synchronize,
 	.exp_sync	= srcu_torture_synchronize_expedited,
@@ -651,8 +645,7 @@ static struct rcu_torture_ops sched_ops = {
 	.readlock	= sched_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
-	.started	= rcu_batches_started_sched,
-	.completed	= rcu_batches_completed_sched,
+	.get_gp_seq	= rcu_sched_get_gp_seq,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
@@ -690,8 +683,7 @@ static struct rcu_torture_ops tasks_ops = {
 	.readlock	= tasks_torture_read_lock,
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= tasks_torture_read_unlock,
-	.started	= rcu_no_completed,
-	.completed	= rcu_no_completed,
+	.get_gp_seq	= rcu_no_completed,
 	.deferred_free	= rcu_tasks_torture_deferred_free,
 	.sync		= synchronize_rcu_tasks,
 	.exp_sync	= synchronize_rcu_tasks,
@@ -1104,10 +1096,7 @@ static void rcu_torture_timer(struct timer_list *unused)
 	unsigned long long ts;
 
 	idx = cur_ops->readlock();
-	if (cur_ops->started)
-		started = cur_ops->started();
-	else
-		started = cur_ops->completed();
+	started = cur_ops->get_gp_seq();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
 				  rcu_read_lock_bh_held() ||
@@ -1131,7 +1120,7 @@ static void rcu_torture_timer(struct timer_list *unused)
 		/* Should not happen, but... */
 		pipe_count = RCU_TORTURE_PIPE_LEN;
 	}
-	completed = cur_ops->completed();
+	completed = cur_ops->get_gp_seq();
 	if (pipe_count > 1) {
 		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
 					  started, completed);
@@ -1139,8 +1128,8 @@ static void rcu_torture_timer(struct timer_list *unused)
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
 	completed = completed - started;
-	if (cur_ops->started)
-		completed++;
+	if (completed > ULONG_MAX >> 1)
+		completed = 0; /* Not all gp_seq have full range. */
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1187,10 +1176,7 @@ rcu_torture_reader(void *arg)
 				mod_timer(&t, jiffies + 1);
 		}
 		idx = cur_ops->readlock();
-		if (cur_ops->started)
-			started = cur_ops->started();
-		else
-			started = cur_ops->completed();
+		started = cur_ops->get_gp_seq();
 		ts = rcu_trace_clock_local();
 		p = rcu_dereference_check(rcu_torture_current,
 					  rcu_read_lock_bh_held() ||
@@ -1212,7 +1198,7 @@ rcu_torture_reader(void *arg)
 			/* Should not happen, but... */
 			pipe_count = RCU_TORTURE_PIPE_LEN;
 		}
-		completed = cur_ops->completed();
+		completed = cur_ops->get_gp_seq();
 		if (pipe_count > 1) {
 			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
 						  ts, started, completed);
@@ -1220,8 +1206,8 @@ rcu_torture_reader(void *arg)
 		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
 		completed = completed - started;
-		if (cur_ops->started)
-			completed++;
+		if (completed > ULONG_MAX >> 1)
+			completed = 0; /* Not all gp_seq have full range. */
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3c3af7e2758f..547112bec26a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -530,58 +530,31 @@ static void force_quiescent_state(struct rcu_state *rsp);
 static int rcu_pending(void);
 
 /*
- * Return the number of RCU batches started thus far for debug & stats.
+ * Return the number of RCU GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started(void)
+unsigned long rcu_get_gp_seq(void)
 {
-	return rcu_state_p->gpnum;
+	return rcu_seq_ctr(READ_ONCE(rcu_state_p->gp_seq));
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started);
+EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
 
 /*
- * Return the number of RCU-sched batches started thus far for debug & stats.
+ * Return the number of RCU-sched GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started_sched(void)
+unsigned long rcu_sched_get_gp_seq(void)
 {
-	return rcu_sched_state.gpnum;
+	return rcu_seq_ctr(READ_ONCE(rcu_sched_state.gp_seq));
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started_sched);
+EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
 
 /*
- * Return the number of RCU BH batches started thus far for debug & stats.
+ * Return the number of RCU-bh GPs completed thus far for debug & stats.
  */
-unsigned long rcu_batches_started_bh(void)
+unsigned long rcu_bh_get_gp_seq(void)
 {
-	return rcu_bh_state.gpnum;
+	return rcu_seq_ctr(READ_ONCE(rcu_bh_state.gp_seq));
 }
-EXPORT_SYMBOL_GPL(rcu_batches_started_bh);
-
-/*
- * Return the number of RCU batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed(void)
-{
-	return rcu_state_p->completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed);
-
-/*
- * Return the number of RCU-sched batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_sched(void)
-{
-	return rcu_sched_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_sched);
-
-/*
- * Return the number of RCU BH batches completed thus far for debug & stats.
- */
-unsigned long rcu_batches_completed_bh(void)
-{
-	return rcu_bh_state.completed;
-}
-EXPORT_SYMBOL_GPL(rcu_batches_completed_bh);
+EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq);
 
 /*
  * Return the number of RCU expedited batches completed thus far for
-- 
cgit v1.2.3


From 78c5a67f1788f59d991c8e78d674ad3c8542f0ac Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 13:32:28 -0700
Subject: rcu: Convert rcu_check_gp_kthread_starvation() to GP sequence number

This commit switches rcu_check_gp_kthread_starvation() from printing
->gpnum and ->completed to printing ->gp_seq upon detecting a starving
RCU grace-period kthread during an RCU CPU stall warning.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 547112bec26a..002f85357226 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1276,9 +1276,9 @@ static void rcu_check_gp_kthread_starvation(struct rcu_state *rsp)
 	j = jiffies;
 	gpa = READ_ONCE(rsp->gp_activity);
 	if (j - gpa > 2 * HZ) {
-		pr_err("%s kthread starved for %ld jiffies! g%lu c%lu f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
+		pr_err("%s kthread starved for %ld jiffies! g%ld f%#x %s(%d) ->state=%#lx ->cpu=%d\n",
 		       rsp->name, j - gpa,
-		       rsp->gpnum, rsp->completed,
+		       (long)rcu_seq_current(&rsp->gp_seq),
 		       rsp->gp_flags,
 		       gp_state_getname(rsp->gp_state), rsp->gp_state,
 		       rsp->gp_kthread ? rsp->gp_kthread->state : ~0,
-- 
cgit v1.2.3


From c9a24e2d0c7d33b141167f5fa13f95cf6d35cb1e Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 14:54:46 -0700
Subject: rcu: Make quiescent-state reporting use ->gp_seq

This commit switches the functions reporting quiescent states from
use of ->gpnum to ->gp_seq.  In either case, the point is to handle
races where a given grace period ends before a quiescent state can
be reported.  Failing to catch these races would result in too-short
grace periods, hence the checking.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 002f85357226..a54587dc13f0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2242,7 +2242,7 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
  * must be represented by the same rcu_node structure (which need not be a
  * leaf rcu_node structure, though it often will be).  The gps parameter
  * is the grace-period snapshot, which means that the quiescent states
- * are valid only if rnp->gpnum is equal to gps.  That structure's lock
+ * are valid only if rnp->gp_seq is equal to gps.  That structure's lock
  * must be held upon entry, and it is released before return.
  */
 static void
@@ -2257,7 +2257,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 
 	/* Walk up the rcu_node hierarchy. */
 	for (;;) {
-		if (!(rnp->qsmask & mask) || rnp->gpnum != gps) {
+		if (!(rnp->qsmask & mask) || rnp->gp_seq != gps) {
 
 			/*
 			 * Our bit has already been cleared, or the
@@ -2335,8 +2335,8 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 		return;
 	}
 
-	/* Report up the rest of the hierarchy, tracking current ->gpnum. */
-	gps = rnp->gpnum;
+	/* Report up the rest of the hierarchy, tracking current ->gp_seq. */
+	gps = rnp->gp_seq;
 	mask = rnp->grpmask;
 	raw_spin_unlock_rcu_node(rnp);	/* irqs remain disabled. */
 	raw_spin_lock_rcu_node(rnp_p);	/* irqs already disabled. */
@@ -2357,8 +2357,8 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	if (rdp->cpu_no_qs.b.norm || rdp->gpnum != rnp->gpnum ||
-	    rnp->completed == rnp->gpnum || rdp->gpwrap) {
+	if (rdp->cpu_no_qs.b.norm || rdp->gp_seq != rnp->gp_seq ||
+	    rdp->gpwrap) {
 
 		/*
 		 * The grace period in which this quiescent state was
@@ -2383,7 +2383,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 		 */
 		needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
 
-		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		/* ^^^ Released rnp->lock */
 		if (needwake)
 			rcu_gp_kthread_wake(rsp);
@@ -2688,8 +2688,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 			}
 		}
 		if (mask != 0) {
-			/* Idle/offline CPUs, report (releases rnp->lock. */
-			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gpnum, flags);
+			/* Idle/offline CPUs, report (releases rnp->lock). */
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		} else {
 			/* Nothing to do here, so just drop the lock. */
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-- 
cgit v1.2.3


From e4be81a2ed3a7356a2c22c7571af622ceb57eb2b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 15:16:50 -0700
Subject: rcu: Convert conditional grace-period primitives to ->gp_seq

This commit converts get_state_synchronize_rcu(), cond_synchronize_rcu(),
get_state_synchronize_sched(), and cond_synchronize_sched() from ->gpnum
and ->completed to ->gp_seq.  Note that this also introduces a full
memory barrier in the already-done paths off cond_synchronize_rcu() and
cond_synchronize_sched(), as work with LKMM indicates that the earlier
smp_load_acquire() were insufficiently strong in some situations where
these two functions were called just as the grace period ended.  In such
cases, these two functions would not gain the benefit of memory ordering
at the end of the grace period.

Please note that the performance impact is negligible, as you shouldn't
be using either function anywhere near a fastpath in any case.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 42 ++++++++++--------------------------------
 1 file changed, 10 insertions(+), 32 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a54587dc13f0..fd2f582a6db0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3183,16 +3183,10 @@ unsigned long get_state_synchronize_rcu(void)
 {
 	/*
 	 * Any prior manipulation of RCU-protected data must happen
-	 * before the load from ->gpnum.
+	 * before the load from ->gp_seq.
 	 */
 	smp_mb();  /* ^^^ */
-
-	/*
-	 * Make sure this load happens before the purportedly
-	 * time-consuming work between get_state_synchronize_rcu()
-	 * and cond_synchronize_rcu().
-	 */
-	return smp_load_acquire(&rcu_state_p->gpnum);
+	return rcu_seq_snap(&rcu_state_p->gp_seq);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
 
@@ -3212,15 +3206,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_rcu);
  */
 void cond_synchronize_rcu(unsigned long oldstate)
 {
-	unsigned long newstate;
-
-	/*
-	 * Ensure that this load happens before any RCU-destructive
-	 * actions the caller might carry out after we return.
-	 */
-	newstate = smp_load_acquire(&rcu_state_p->completed);
-	if (ULONG_CMP_GE(oldstate, newstate))
+	if (!rcu_seq_done(&rcu_state_p->gp_seq, oldstate))
 		synchronize_rcu();
+	else
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_rcu);
 
@@ -3235,16 +3224,10 @@ unsigned long get_state_synchronize_sched(void)
 {
 	/*
 	 * Any prior manipulation of RCU-protected data must happen
-	 * before the load from ->gpnum.
+	 * before the load from ->gp_seq.
 	 */
 	smp_mb();  /* ^^^ */
-
-	/*
-	 * Make sure this load happens before the purportedly
-	 * time-consuming work between get_state_synchronize_sched()
-	 * and cond_synchronize_sched().
-	 */
-	return smp_load_acquire(&rcu_sched_state.gpnum);
+	return rcu_seq_snap(&rcu_sched_state.gp_seq);
 }
 EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
 
@@ -3264,15 +3247,10 @@ EXPORT_SYMBOL_GPL(get_state_synchronize_sched);
  */
 void cond_synchronize_sched(unsigned long oldstate)
 {
-	unsigned long newstate;
-
-	/*
-	 * Ensure that this load happens before any RCU-destructive
-	 * actions the caller might carry out after we return.
-	 */
-	newstate = smp_load_acquire(&rcu_sched_state.completed);
-	if (ULONG_CMP_GE(oldstate, newstate))
+	if (!rcu_seq_done(&rcu_sched_state.gp_seq, oldstate))
 		synchronize_sched();
+	else
+		smp_mb(); /* Ensure GP ends before subsequent accesses. */
 }
 EXPORT_SYMBOL_GPL(cond_synchronize_sched);
 
-- 
cgit v1.2.3


From 67e14c1e39d2d956300b3d6ad00f7708e3285531 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 16:01:46 -0700
Subject: rcu: Move RCU's grace-period-change code to ->gp_seq

This commit moves __note_gp_changes(), note_gp_changes(), and
__rcu_pending() to ->gp_seq, creating new rcu_seq_completed_gp() and
rcu_seq_new_gp() functions for this purpose.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Reinstate "cpuend: trace as suggested by Joel Fernandes. ]
---
 kernel/rcu/rcu.h  | 17 +++++++++++++++++
 kernel/rcu/tree.c | 39 ++++++++++++++++-----------------------
 2 files changed, 33 insertions(+), 23 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index f0907f9f6cd0..7568a3fd0815 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -116,6 +116,23 @@ static inline bool rcu_seq_done(unsigned long *sp, unsigned long s)
 	return ULONG_CMP_GE(READ_ONCE(*sp), s);
 }
 
+/*
+ * Has a grace period completed since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_completed_gp(unsigned long old, unsigned long new)
+{
+	return ULONG_CMP_LT(old, new & ~RCU_SEQ_STATE_MASK);
+}
+
+/*
+ * Has a grace period started since the time the old gp_seq was collected?
+ */
+static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
+{
+	return ULONG_CMP_LT((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK,
+			    new);
+}
+
 /*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
  * by call_rcu() and rcu callback execution, and are therefore not part of the
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index fd2f582a6db0..bcd659e65dfd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1790,24 +1790,23 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	raw_lockdep_assert_held_rcu_node(rnp);
 
-	/* Handle the ends of any preceding grace periods first. */
-	if (rdp->completed == rnp->completed &&
-	    !unlikely(READ_ONCE(rdp->gpwrap))) {
-
-		/* No grace period end, so just accelerate recent callbacks. */
-		ret = rcu_accelerate_cbs(rsp, rnp, rdp);
-
-	} else {
-
-		/* Advance callbacks. */
-		ret = rcu_advance_cbs(rsp, rnp, rdp);
+	if (rdp->gp_seq == rnp->gp_seq)
+		return false; /* Nothing to do. */
 
+	/* Handle the ends of any preceding grace periods first. */
+	if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) {
+		ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */
 		/* Remember that we saw this grace-period completion. */
 		rdp->completed = rnp->completed;
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuend"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend"));
+	} else {
+		ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */
 	}
 
-	if (rdp->gpnum != rnp->gpnum || unlikely(READ_ONCE(rdp->gpwrap))) {
+	/* Now handle the beginnings of any new-to-this-CPU grace periods. */
+	if (rcu_seq_new_gp(rdp->gp_seq, rnp->gp_seq) ||
+	    unlikely(READ_ONCE(rdp->gpwrap))) {
 		/*
 		 * If the current grace period is waiting for this CPU,
 		 * set up to detect a quiescent state, otherwise don't
@@ -1823,8 +1822,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		WRITE_ONCE(rdp->gpwrap, false);
 		rcu_gpnum_ovf(rnp, rdp);
 	}
-	if (rdp->gp_seq != rnp->gp_seq)
-		rdp->gp_seq = rnp->gp_seq;
+	rdp->gp_seq = rnp->gp_seq;  /* Remember new grace-period state. */
 	return ret;
 }
 
@@ -1836,8 +1834,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 
 	local_irq_save(flags);
 	rnp = rdp->mynode;
-	if ((rdp->gpnum == READ_ONCE(rnp->gpnum) &&
-	     rdp->completed == READ_ONCE(rnp->completed) &&
+	if ((rdp->gp_seq == rcu_seq_current(&rnp->gp_seq) &&
 	     !unlikely(READ_ONCE(rdp->gpwrap))) || /* w/out lock. */
 	    !raw_spin_trylock_rcu_node(rnp)) { /* irqs already off, so later. */
 		local_irq_restore(flags);
@@ -3286,12 +3283,8 @@ static int __rcu_pending(struct rcu_state *rsp, struct rcu_data *rdp)
 	    !rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
 		return 1;
 
-	/* Has another RCU grace period completed?  */
-	if (READ_ONCE(rnp->completed) != rdp->completed) /* outside lock */
-		return 1;
-
-	/* Has a new RCU grace period started? */
-	if (READ_ONCE(rnp->gpnum) != rdp->gpnum ||
+	/* Have RCU grace period completed or started?  */
+	if (rcu_seq_current(&rnp->gp_seq) != rdp->gp_seq ||
 	    unlikely(READ_ONCE(rdp->gpwrap))) /* outside lock */
 		return 1;
 
-- 
cgit v1.2.3


From a66ae8ae35de60a85d2d89689d8c2d6a4dc15d85 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 18:06:08 -0700
Subject: rcu: Convert rcu_gpnum_ovf() to ->gp_seq

This commit converts rcu_gpnum_ovf() to use ->gp_seq instead of ->gpnum.
Same size unsigned long, so same approach.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index bcd659e65dfd..de2e2c5d64bb 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1089,14 +1089,15 @@ static int rcu_is_cpu_rrupt_from_idle(void)
 /*
  * We are reporting a quiescent state on behalf of some other CPU, so
  * it is our responsibility to check for and handle potential overflow
- * of the rcu_node ->gpnum counter with respect to the rcu_data counters.
+ * of the rcu_node ->gp_seq counter with respect to the rcu_data counters.
  * After all, the CPU might be in deep idle state, and thus executing no
  * code whatsoever.
  */
 static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
 {
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (ULONG_CMP_LT(READ_ONCE(rdp->gpnum) + ULONG_MAX / 4, rnp->gpnum))
+	if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
+			 rnp->gp_seq))
 		WRITE_ONCE(rdp->gpwrap, true);
 	if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
 		rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4;
-- 
cgit v1.2.3


From e05720b0977bd50707ea6cf296f99e709de3f760 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 18:58:58 -0700
Subject: rcu: Move rcu_implicit_dynticks_qs() to ->gp_seq

This commit makes rcu_implicit_dynticks_qs() use ->gp_seq, with the
exception of tracing, which will be converted later.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index de2e2c5d64bb..b3af3d24286c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1178,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	ruqp = per_cpu_ptr(&rcu_dynticks.rcu_urgent_qs, rdp->cpu);
 	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
 	    READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
-	    READ_ONCE(rdp->gpnum) == rnp->gpnum && !rdp->gpwrap) {
+	    rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) {
 		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
-- 
cgit v1.2.3


From 03c8cb765a747c02fd8d3fade1efe9d529ad54bd Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 19:56:16 -0700
Subject: rcu: Move rcu_try_advance_all_cbs() to ->gp_seq

This commit makes rcu_try_advance_all_cbs() use ->gp_seq, with the
exception of tracing, which will be converted later.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index e387ea712758..d893899b72f4 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1467,7 +1467,8 @@ static bool __maybe_unused rcu_try_advance_all_cbs(void)
 		 * completed since we last checked and there are
 		 * callbacks not yet ready to invoke.
 		 */
-		if ((rdp->completed != rnp->completed ||
+		if ((rcu_seq_completed_gp(rdp->gp_seq,
+					  rcu_seq_current(&rnp->gp_seq)) ||
 		     unlikely(READ_ONCE(rdp->gpwrap))) &&
 		    rcu_segcblist_pend_cbs(&rdp->cblist))
 			note_gp_changes(rsp, rdp);
-- 
cgit v1.2.3


From e0da2374c3881cb9a512e2718f9ca655a48de9db Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 20:51:36 -0700
Subject: rcu: Move rcu_nocb_gp_get() to ->gp_seq

This commit makes rcu_try_advance_all_cbs() use ->gp_seq.  It uses
rcu_seq_ctr() in order to shift away the state bits, so that the
low-order bits of the result may safely be used to index ->nocb_gp_wq[].

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index d893899b72f4..5b10904669c5 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1852,7 +1852,7 @@ static void rcu_nocb_gp_cleanup(struct swait_queue_head *sq)
 
 static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp)
 {
-	return &rnp->nocb_gp_wq[rnp->completed & 0x1];
+	return &rnp->nocb_gp_wq[rcu_seq_ctr(rnp->gp_seq) & 0x1];
 }
 
 static void rcu_init_one_nocb(struct rcu_node *rnp)
-- 
cgit v1.2.3


From ba04107fc901ddce49686944f7e038b4f0b0a359 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 21:25:01 -0700
Subject: rcu: Move rcu_gp_in_progress() to ->gp_seq

This commit makes rcu_gp_in_progress() use ->gp_seq instead of
->completed and ->gpnum.  The READ_ONCE() invocations are buried
in rcu_seq_current().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index b3af3d24286c..56445f4c09a8 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -219,7 +219,7 @@ unsigned long rcu_rnp_online_cpus(struct rcu_node *rnp)
  */
 static int rcu_gp_in_progress(struct rcu_state *rsp)
 {
-	return READ_ONCE(rsp->completed) != READ_ONCE(rsp->gpnum);
+	return rcu_seq_state(rcu_seq_current(&rsp->gp_seq));
 }
 
 /*
-- 
cgit v1.2.3


From 8aa670cdacc1820cb0597e4b4b413ef91ede2dd9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 28 Apr 2018 14:15:40 -0700
Subject: rcu: Convert ->rcu_iw_gpnum to ->gp_seq

This commit switches the interrupt-disabled detection mechanism to
->gp_seq.  This mechanism is used as part of RCU CPU stall warnings,
and detects cases where the stall is due to a CPU having interrupts
disabled.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 12 ++++++------
 kernel/rcu/tree.h        |  2 +-
 kernel/rcu/tree_plugin.h |  2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 56445f4c09a8..2ddbd1cfb31a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1099,8 +1099,8 @@ static void rcu_gpnum_ovf(struct rcu_node *rnp, struct rcu_data *rdp)
 	if (ULONG_CMP_LT(rcu_seq_current(&rdp->gp_seq) + ULONG_MAX / 4,
 			 rnp->gp_seq))
 		WRITE_ONCE(rdp->gpwrap, true);
-	if (ULONG_CMP_LT(rdp->rcu_iw_gpnum + ULONG_MAX / 4, rnp->gpnum))
-		rdp->rcu_iw_gpnum = rnp->gpnum + ULONG_MAX / 4;
+	if (ULONG_CMP_LT(rdp->rcu_iw_gp_seq + ULONG_MAX / 4, rnp->gp_seq))
+		rdp->rcu_iw_gp_seq = rnp->gp_seq + ULONG_MAX / 4;
 }
 
 /*
@@ -1134,7 +1134,7 @@ static void rcu_iw_handler(struct irq_work *iwp)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);
 	if (!WARN_ON_ONCE(!rdp->rcu_iw_pending)) {
-		rdp->rcu_iw_gpnum = rnp->gpnum;
+		rdp->rcu_iw_gp_seq = rnp->gp_seq;
 		rdp->rcu_iw_pending = false;
 	}
 	raw_spin_unlock_rcu_node(rnp);
@@ -1231,11 +1231,11 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (jiffies - rdp->rsp->gp_start > rcu_jiffies_till_stall_check() / 2) {
 		resched_cpu(rdp->cpu);
 		if (IS_ENABLED(CONFIG_IRQ_WORK) &&
-		    !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum &&
+		    !rdp->rcu_iw_pending && rdp->rcu_iw_gp_seq != rnp->gp_seq &&
 		    (rnp->ffmask & rdp->grpmask)) {
 			init_irq_work(&rdp->rcu_iw, rcu_iw_handler);
 			rdp->rcu_iw_pending = true;
-			rdp->rcu_iw_gpnum = rnp->gpnum;
+			rdp->rcu_iw_gp_seq = rnp->gp_seq;
 			irq_work_queue_on(&rdp->rcu_iw, rdp->cpu);
 		}
 	}
@@ -3575,7 +3575,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
 	rdp->rcu_iw_pending = false;
-	rdp->rcu_iw_gpnum = rnp->gpnum - 1;
+	rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
 	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 50a28d1cf5a1..6d6cbc8b3a9c 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -286,7 +286,7 @@ struct rcu_data {
 	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
 	struct irq_work rcu_iw;		/* Check for non-irq activity. */
 	bool rcu_iw_pending;		/* Is ->rcu_iw pending? */
-	unsigned long rcu_iw_gpnum;	/* ->gpnum associated with ->rcu_iw. */
+	unsigned long rcu_iw_gp_seq;	/* ->gp_seq associated with ->rcu_iw. */
 
 	int cpu;
 	struct rcu_state *rsp;
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 5b10904669c5..bc32e1f434a6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1763,7 +1763,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
-	delta = rdp->mynode->gpnum - rdp->rcu_iw_gpnum;
+	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
 	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
-- 
cgit v1.2.3


From d43a5d32e125db1e34641922e52baaa4fee3510a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 28 Apr 2018 18:50:06 -0700
Subject: rcu: Convert ->completedqs to ->gp_seq

This commit switches the quiescent-state no-backtracking checks from
->gpnum and ->completed to ->gp_seq.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 4 ++--
 kernel/rcu/tree_plugin.h | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2ddbd1cfb31a..da2ca9cc078b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2278,7 +2278,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			return;
 		}
-		rnp->completedqs = rnp->gpnum;
+		rnp->completedqs = rnp->gp_seq;
 		mask = rnp->grpmask;
 		if (rnp->parent == NULL) {
 
@@ -3951,7 +3951,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			rnp->gpnum = rsp->gpnum;
 			rnp->completed = rsp->completed;
 			rnp->gp_seq = rsp->gp_seq;
-			rnp->completedqs = rsp->completed;
+			rnp->completedqs = rsp->gp_seq;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
 			rnp->grplo = j * cpustride;
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index bc32e1f434a6..2a81d243521f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -262,7 +262,7 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	 */
 	if (!rnp->gp_tasks && (blkd_state & RCU_GP_BLKD)) {
 		rnp->gp_tasks = &t->rcu_node_entry;
-		WARN_ON_ONCE(rnp->completedqs == rnp->gpnum);
+		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq);
 	}
 	if (!rnp->exp_tasks && (blkd_state & RCU_EXP_BLKD))
 		rnp->exp_tasks = &t->rcu_node_entry;
@@ -537,7 +537,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		WARN_ON_ONCE(rnp != t->rcu_blocked_node);
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
 		empty_norm = !rcu_preempt_blocked_readers_cgp(rnp);
-		WARN_ON_ONCE(rnp->completedqs == rnp->gpnum &&
+		WARN_ON_ONCE(rnp->completedqs == rnp->gp_seq &&
 			     (!empty_norm || rnp->qsmask));
 		empty_exp = sync_rcu_preempt_exp_done(rnp);
 		smp_mb(); /* ensure expedited fastpath sees end of RCU c-s. */
-- 
cgit v1.2.3


From 29365e563b1e4e5bfde211280d37dc6127c019ed Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Apr 2018 10:57:36 -0700
Subject: rcu: Convert grace-period requests to ->gp_seq

This commit converts the grace-period request code paths from ->completed
and ->gpnum to ->gp_seq.  The need_future_gp_element() macro encapsulates
the shift operation required to use ->gp_seq as an index to the
->need_future_gp[] array.  The rcu_cbs_completed() function is removed
in favor of the rcu_seq_snap() function.  The rcu_start_this_gp()
gets some temporary consistency checks and uses rcu_seq_done(),
rcu_seq_current(), rcu_seq_state(), and rcu_gp_in_progress() in place
of the earlier open-coded comparisons of ->gpnum and ->completed.
The rcu_future_gp_cleanup() function replaces use of ->completed
with ->gp_seq.  The rcu_accelerate_cbs() function replaces a call to
rcu_cbs_completed() with one to rcu_seq_snap().  The rcu_advance_cbs()
function replaces an access to >completed with one to ->gp_seq and adds
some temporary warnings.  The rcu_nocb_wait_gp() function replaces a
call to rcu_cbs_completed() with one to rcu_seq_snap() and an open-coded
comparison with rcu_seq_done().

The temporary warnings will be removed when the various ->gpnum and
->completed fields are removed.  Their purpose is to locate code who
might still be using ->gpnum and ->completed.  (Much easier that way
than trying to trace down the causes of too-short grace periods and
grace-period hangs!)

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 84 ++++++++++++------------------------------------
 kernel/rcu/tree.h        |  2 +-
 kernel/rcu/tree_plugin.h |  6 ++--
 3 files changed, 24 insertions(+), 68 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index da2ca9cc078b..ffa45b6175d9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1548,52 +1548,6 @@ void rcu_cpu_stall_reset(void)
 		WRITE_ONCE(rsp->jiffies_stall, jiffies + ULONG_MAX / 2);
 }
 
-/*
- * Determine the value that ->completed will have at the end of the
- * next subsequent grace period.  This is used to tag callbacks so that
- * a CPU can invoke callbacks in a timely fashion even if that CPU has
- * been dyntick-idle for an extended period with callbacks under the
- * influence of RCU_FAST_NO_HZ.
- *
- * The caller must hold rnp->lock with interrupts disabled.
- */
-static unsigned long rcu_cbs_completed(struct rcu_state *rsp,
-				       struct rcu_node *rnp)
-{
-	raw_lockdep_assert_held_rcu_node(rnp);
-
-	/*
-	 * If RCU is idle, we just wait for the next grace period.
-	 * But we can only be sure that RCU is idle if we are looking
-	 * at the root rcu_node structure -- otherwise, a new grace
-	 * period might have started, but just not yet gotten around
-	 * to initializing the current non-root rcu_node structure.
-	 */
-	if (rcu_get_root(rsp) == rnp && rnp->gpnum == rnp->completed)
-		return rnp->completed + 1;
-
-	/*
-	 * If the current rcu_node structure believes that RCU is
-	 * idle, and if the rcu_state structure does not yet reflect
-	 * the start of a new grace period, then the next grace period
-	 * will suffice.  The memory barrier is needed to accurately
-	 * sample the rsp->gpnum, and pairs with the second lock
-	 * acquisition in rcu_gp_init(), which is augmented with
-	 * smp_mb__after_unlock_lock() for this purpose.
-	 */
-	if (rnp->gpnum == rnp->completed) {
-		smp_mb(); /* See above block comment. */
-		if (READ_ONCE(rsp->gpnum) == rnp->completed)
-			return rnp->completed + 1;
-	}
-
-	/*
-	 * Otherwise, wait for a possible partial grace period and
-	 * then the subsequent full grace period.
-	 */
-	return rnp->completed + 2;
-}
-
 /* Trace-event wrapper function for trace_rcu_future_grace_period.  */
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 			      unsigned long c, const char *s)
@@ -1629,16 +1583,16 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * not be released.
 	 */
 	raw_lockdep_assert_held_rcu_node(rnp);
+	WARN_ON_ONCE(c & 0x2); /* Catch any lingering use of ->gpnum. */
+	WARN_ON_ONCE(((rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT) != rcu_seq_ctr(rnp->gp_seq)); /* Catch any ->completed/->gp_seq mismatches. */
 	trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
 	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
 		if (rnp_root != rnp)
 			raw_spin_lock_rcu_node(rnp_root);
-		WARN_ON_ONCE(ULONG_CMP_LT(rnp_root->gpnum +
-					  need_future_gp_mask(), c));
 		if (need_future_gp_element(rnp_root, c) ||
-		    ULONG_CMP_GE(rnp_root->gpnum, c) ||
+		    rcu_seq_done(&rnp_root->gp_seq, c) ||
 		    (rnp != rnp_root &&
-		     rnp_root->gpnum != rnp_root->completed)) {
+		     rcu_seq_state(rcu_seq_current(&rnp_root->gp_seq)))) {
 			trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
 			goto unlock_out;
 		}
@@ -1650,7 +1604,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	}
 
 	/* If GP already in progress, just leave, otherwise start one. */
-	if (rnp_root->gpnum != rnp_root->completed) {
+	if (rcu_gp_in_progress(rsp)) {
 		trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
 		goto unlock_out;
 	}
@@ -1675,7 +1629,7 @@ unlock_out:
  */
 static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-	unsigned long c = rnp->completed;
+	unsigned long c = rnp->gp_seq;
 	bool needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
@@ -1703,14 +1657,14 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 }
 
 /*
- * If there is room, assign a ->completed number to any callbacks on
- * this CPU that have not already been assigned.  Also accelerate any
- * callbacks that were previously assigned a ->completed number that has
- * since proven to be too conservative, which can happen if callbacks get
- * assigned a ->completed number while RCU is idle, but with reference to
- * a non-root rcu_node structure.  This function is idempotent, so it does
- * not hurt to call it repeatedly.  Returns an flag saying that we should
- * awaken the RCU grace-period kthread.
+ * If there is room, assign a ->gp_seq number to any callbacks on this
+ * CPU that have not already been assigned.  Also accelerate any callbacks
+ * that were previously assigned a ->gp_seq number that has since proven
+ * to be too conservative, which can happen if callbacks get assigned a
+ * ->gp_seq number while RCU is idle, but with reference to a non-root
+ * rcu_node structure.  This function is idempotent, so it does not hurt
+ * to call it repeatedly.  Returns an flag saying that we should awaken
+ * the RCU grace-period kthread.
  *
  * The caller must hold rnp->lock with interrupts disabled.
  */
@@ -1736,7 +1690,7 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	 * accelerating callback invocation to an earlier grace-period
 	 * number.
 	 */
-	c = rcu_cbs_completed(rsp, rnp);
+	c = rcu_seq_snap(&rsp->gp_seq);
 	if (rcu_segcblist_accelerate(&rdp->cblist, c))
 		ret = rcu_start_this_gp(rnp, rdp, c);
 
@@ -1751,7 +1705,7 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 /*
  * Move any callbacks whose grace period has completed to the
  * RCU_DONE_TAIL sublist, then compact the remaining sublists and
- * assign ->completed numbers to any callbacks in the RCU_NEXT_TAIL
+ * assign ->gp_seq numbers to any callbacks in the RCU_NEXT_TAIL
  * sublist.  This function is idempotent, so it does not hurt to
  * invoke it repeatedly.  As long as it is not invoked -too- often...
  * Returns true if the RCU grace-period kthread needs to be awakened.
@@ -1768,10 +1722,10 @@ static bool rcu_advance_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 		return false;
 
 	/*
-	 * Find all callbacks whose ->completed numbers indicate that they
+	 * Find all callbacks whose ->gp_seq numbers indicate that they
 	 * are ready to invoke, and put them into the RCU_DONE_TAIL sublist.
 	 */
-	rcu_segcblist_advance(&rdp->cblist, rnp->completed);
+	rcu_segcblist_advance(&rdp->cblist, rnp->gp_seq);
 
 	/* Classify any remaining callbacks. */
 	return rcu_accelerate_cbs(rsp, rnp, rdp);
@@ -1889,6 +1843,8 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
 	smp_mb(); /* Pairs with barriers in stall-warning code. */
 	rcu_seq_start(&rsp->gp_seq);
+	if (WARN_ON_ONCE(((rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT) != rcu_seq_ctr(rnp->gp_seq))) /* Catch any ->completed/->gp_seq mismatches. */
+		pr_info("%s ->completed: %#lx (%#lx) ->gp_seq %#lx (%#lx)\n", __func__, rnp->completed, (rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT, rnp->gp_seq, rcu_seq_ctr(rnp->gp_seq));
 	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 6d6cbc8b3a9c..a21d403a6010 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -174,7 +174,7 @@ struct rcu_node {
 #define need_future_gp_mask() \
 	(ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
 #define need_future_gp_element(rnp, c) \
-	((rnp)->need_future_gp[(c) & need_future_gp_mask()])
+	((rnp)->need_future_gp[(c >> RCU_SEQ_CTR_SHIFT) & need_future_gp_mask()])
 #define need_any_future_gp(rnp)						\
 ({									\
 	int __i;							\
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2a81d243521f..2036dc7426ac 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2105,7 +2105,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
-	c = rcu_cbs_completed(rdp->rsp, rnp);
+	c = rcu_seq_snap(&rdp->rsp->gp_seq);
 	needwake = rcu_start_this_gp(rnp, rdp, c);
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 	if (needwake)
@@ -2118,8 +2118,8 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	trace_rcu_this_gp(rnp, rdp, c, TPS("StartWait"));
 	for (;;) {
 		swait_event_interruptible(
-			rnp->nocb_gp_wq[c & 0x1],
-			(d = ULONG_CMP_GE(READ_ONCE(rnp->completed), c)));
+			rnp->nocb_gp_wq[rcu_seq_ctr(c) & 0x1],
+			(d = rcu_seq_done(&rnp->gp_seq, c)));
 		if (likely(d))
 			break;
 		WARN_ON(signal_pending(current));
-- 
cgit v1.2.3


From 471f87c3d91bd0884451c0e3071473476c165630 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 30 Apr 2018 13:09:17 -0700
Subject: rcu: Make RCU CPU stall warnings use ->gp_seq

This commit makes the RCU CPU stall-warning code in print_other_cpu_stall(),
print_cpu_stall(), and check_cpu_stall() use ->gp_seq instead of ->gpnum
and ->completed.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 51 ++++++++++++++++++++++++------------------------
 kernel/rcu/tree_plugin.h |  8 ++++----
 2 files changed, 30 insertions(+), 29 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ffa45b6175d9..9e619c4878d3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1340,7 +1340,7 @@ static inline void panic_on_rcu_stall(void)
 		panic("RCU Stall\n");
 }
 
-static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
+static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
 {
 	int cpu;
 	unsigned long flags;
@@ -1350,6 +1350,8 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	long totqlen = 0;
 
+	WARN_ON_ONCE(gp_seq & 0x2); /* Remove when ->gpnum removed. */
+
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads(rsp);
 	if (rcu_cpu_stall_suppress)
@@ -1380,17 +1382,16 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gpnum)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
 							    cpu)->cblist);
-	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, c=%ld, q=%lu)\n",
+	pr_cont("(detected by %d, t=%ld jiffies, g=%ld, q=%lu)\n",
 	       smp_processor_id(), (long)(jiffies - rsp->gp_start),
-	       (long)rsp->gpnum, (long)rsp->completed, totqlen);
+	       (long)rcu_seq_current(&rsp->gp_seq), totqlen);
 	if (ndetected) {
 		rcu_dump_cpu_stacks(rsp);
 
 		/* Complain about tasks blocking the grace period. */
 		rcu_print_detail_task_stall(rsp);
 	} else {
-		if (READ_ONCE(rsp->gpnum) != gpnum ||
-		    READ_ONCE(rsp->completed) == gpnum) {
+		if (rcu_seq_current(&rsp->gp_seq) != gp_seq) {
 			pr_err("INFO: Stall ended before state dump start\n");
 		} else {
 			j = jiffies;
@@ -1442,9 +1443,9 @@ static void print_cpu_stall(struct rcu_state *rsp)
 	for_each_possible_cpu(cpu)
 		totqlen += rcu_segcblist_n_cbs(&per_cpu_ptr(rsp->rda,
 							    cpu)->cblist);
-	pr_cont(" (t=%lu jiffies g=%ld c=%ld q=%lu)\n",
+	pr_cont(" (t=%lu jiffies g=%ld q=%lu)\n",
 		jiffies - rsp->gp_start,
-		(long)rsp->gpnum, (long)rsp->completed, totqlen);
+		(long)rcu_seq_current(&rsp->gp_seq), totqlen);
 
 	rcu_check_gp_kthread_starvation(rsp);
 
@@ -1471,8 +1472,8 @@ static void print_cpu_stall(struct rcu_state *rsp)
 
 static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 {
-	unsigned long completed;
-	unsigned long gpnum;
+	unsigned long gs1;
+	unsigned long gs2;
 	unsigned long gps;
 	unsigned long j;
 	unsigned long jn;
@@ -1488,28 +1489,28 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 	/*
 	 * Lots of memory barriers to reject false positives.
 	 *
-	 * The idea is to pick up rsp->gpnum, then rsp->jiffies_stall,
-	 * then rsp->gp_start, and finally rsp->completed.  These values
-	 * are updated in the opposite order with memory barriers (or
-	 * equivalent) during grace-period initialization and cleanup.
-	 * Now, a false positive can occur if we get an new value of
-	 * rsp->gp_start and a old value of rsp->jiffies_stall.  But given
-	 * the memory barriers, the only way that this can happen is if one
-	 * grace period ends and another starts between these two fetches.
-	 * Detect this by comparing rsp->completed with the previous fetch
-	 * from rsp->gpnum.
+	 * The idea is to pick up rsp->gp_seq, then rsp->jiffies_stall,
+	 * then rsp->gp_start, and finally another copy of rsp->gp_seq.
+	 * These values are updated in the opposite order with memory
+	 * barriers (or equivalent) during grace-period initialization
+	 * and cleanup.  Now, a false positive can occur if we get an new
+	 * value of rsp->gp_start and a old value of rsp->jiffies_stall.
+	 * But given the memory barriers, the only way that this can happen
+	 * is if one grace period ends and another starts between these
+	 * two fetches.  This is detected by comparing the second fetch
+	 * of rsp->gp_seq with the previous fetch from rsp->gp_seq.
 	 *
 	 * Given this check, comparisons of jiffies, rsp->jiffies_stall,
 	 * and rsp->gp_start suffice to forestall false positives.
 	 */
-	gpnum = READ_ONCE(rsp->gpnum);
-	smp_rmb(); /* Pick up ->gpnum first... */
+	gs1 = READ_ONCE(rsp->gp_seq);
+	smp_rmb(); /* Pick up ->gp_seq first... */
 	js = READ_ONCE(rsp->jiffies_stall);
 	smp_rmb(); /* ...then ->jiffies_stall before the rest... */
 	gps = READ_ONCE(rsp->gp_start);
-	smp_rmb(); /* ...and finally ->gp_start before ->completed. */
-	completed = READ_ONCE(rsp->completed);
-	if (ULONG_CMP_GE(completed, gpnum) ||
+	smp_rmb(); /* ...and finally ->gp_start before ->gp_seq again. */
+	gs2 = READ_ONCE(rsp->gp_seq);
+	if (gs1 != gs2 ||
 	    ULONG_CMP_LT(j, js) ||
 	    ULONG_CMP_GE(gps, js))
 		return; /* No stall or GP completed since entering function. */
@@ -1527,7 +1528,7 @@ static void check_cpu_stall(struct rcu_state *rsp, struct rcu_data *rdp)
 		   cmpxchg(&rsp->jiffies_stall, js, jn) == js) {
 
 		/* They had a few time units to dump stack, so complain. */
-		print_other_cpu_stall(rsp, gpnum);
+		print_other_cpu_stall(rsp, gs2);
 	}
 }
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2036dc7426ac..f4a88e3c388d 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1755,12 +1755,12 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	 */
 	touch_nmi_watchdog();
 
-	if (rsp->gpnum == rdp->gpnum) {
+	ticks_value = rcu_seq_ctr(rsp->gp_seq - rdp->gp_seq);
+	if (ticks_value) {
+		ticks_title = "GPs behind";
+	} else {
 		ticks_title = "ticks this GP";
 		ticks_value = rdp->ticks_this_gp;
-	} else {
-		ticks_title = "GPs behind";
-		ticks_value = rsp->gpnum - rdp->gpnum;
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
-- 
cgit v1.2.3


From aebc82644b2c8eafa15e8c481fbafc1b41f4fbf9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 06:42:51 -0700
Subject: rcutorture: Convert rcutorture_get_gp_data() to ->gp_seq

SRCU has long used ->srcu_gp_seq, and now RCU uses ->gp_seq.  This
commit therefore moves the rcutorture_get_gp_data() function from
a ->gpnum / ->completed pair to ->gp_seq.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h        | 17 ++++++-----------
 kernel/rcu/rcutorture.c | 24 ++++++++++--------------
 kernel/rcu/srcutree.c   |  5 ++---
 kernel/rcu/tree.c       |  5 ++---
 4 files changed, 20 insertions(+), 31 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 7568a3fd0815..003671825d62 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -425,7 +425,7 @@ enum rcutorture_type {
 
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
-			    unsigned long *gpnum, unsigned long *completed);
+			    unsigned long *gp_seq);
 void rcutorture_record_test_transition(void);
 void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
@@ -435,13 +435,10 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 			       unsigned long c);
 #else
 static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
-					  int *flags,
-					  unsigned long *gpnum,
-					  unsigned long *completed)
+					  int *flags, unsigned long *gp_seq)
 {
 	*flags = 0;
-	*gpnum = 0;
-	*completed = 0;
+	*gp_seq = 0;
 }
 static inline void rcutorture_record_test_transition(void) { }
 static inline void rcutorture_record_progress(unsigned long vernum) { }
@@ -461,21 +458,19 @@ void do_trace_rcu_torture_read(const char *rcutorturename,
 
 static inline void srcutorture_get_gp_data(enum rcutorture_type test_type,
 					   struct srcu_struct *sp, int *flags,
-					   unsigned long *gpnum,
-					   unsigned long *completed)
+					   unsigned long *gp_seq)
 {
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*completed = sp->srcu_idx;
-	*gpnum = *completed;
+	*gp_seq = sp->srcu_idx;
 }
 
 #elif defined(CONFIG_TREE_SRCU)
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
 			     struct srcu_struct *sp, int *flags,
-			     unsigned long *gpnum, unsigned long *completed);
+			     unsigned long *gp_seq);
 
 #endif
 
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 1f66597c7783..81fb43530d64 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1313,18 +1313,16 @@ rcu_torture_stats_print(void)
 	if (rtcv_snap == rcu_torture_current_version &&
 	    rcu_torture_current != NULL) {
 		int __maybe_unused flags = 0;
-		unsigned long __maybe_unused gpnum = 0;
-		unsigned long __maybe_unused completed = 0;
+		unsigned long __maybe_unused gp_seq = 0;
 
 		rcutorture_get_gp_data(cur_ops->ttype,
-				       &flags, &gpnum, &completed);
+				       &flags, &gp_seq);
 		srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
-					&flags, &gpnum, &completed);
+					&flags, &gp_seq);
 		wtp = READ_ONCE(writer_task);
-		pr_alert("??? Writer stall state %s(%d) g%lu c%lu f%#x ->state %#lx cpu %d\n",
+		pr_alert("??? Writer stall state %s(%d) g%lu f%#x ->state %#lx cpu %d\n",
 			 rcu_torture_writer_state_getname(),
-			 rcu_torture_writer_state,
-			 gpnum, completed, flags,
+			 rcu_torture_writer_state, gp_seq, flags,
 			 wtp == NULL ? ~0UL : wtp->state,
 			 wtp == NULL ? -1 : (int)task_cpu(wtp));
 		if (!splatted && wtp) {
@@ -1605,8 +1603,7 @@ static void
 rcu_torture_cleanup(void)
 {
 	int flags = 0;
-	unsigned long gpnum = 0;
-	unsigned long completed = 0;
+	unsigned long gp_seq = 0;
 	int i;
 
 	rcutorture_record_test_transition();
@@ -1637,11 +1634,10 @@ rcu_torture_cleanup(void)
 		fakewriter_tasks = NULL;
 	}
 
-	rcutorture_get_gp_data(cur_ops->ttype, &flags, &gpnum, &completed);
-	srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp,
-				&flags, &gpnum, &completed);
-	pr_alert("%s:  End-test grace-period state: g%lu c%lu f%#x\n",
-		 cur_ops->name, gpnum, completed, flags);
+	rcutorture_get_gp_data(cur_ops->ttype, &flags, &gp_seq);
+	srcutorture_get_gp_data(cur_ops->ttype, srcu_ctlp, &flags, &gp_seq);
+	pr_alert("%s:  End-test grace-period state: g%lu f%#x\n",
+		 cur_ops->name, gp_seq, flags);
 	torture_stop_kthread(rcu_torture_stats, stats_task);
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
 	for (i = 0; i < ncbflooders; i++)
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 5a1a9a07b407..d6d6ea9738c0 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1249,13 +1249,12 @@ static void process_srcu(struct work_struct *work)
 
 void srcutorture_get_gp_data(enum rcutorture_type test_type,
 			     struct srcu_struct *sp, int *flags,
-			     unsigned long *gpnum, unsigned long *completed)
+			     unsigned long *gp_seq)
 {
 	if (test_type != SRCU_FLAVOR)
 		return;
 	*flags = 0;
-	*completed = rcu_seq_ctr(sp->srcu_gp_seq);
-	*gpnum = rcu_seq_ctr(sp->srcu_gp_seq_needed);
+	*gp_seq = rcu_seq_current(&sp->srcu_gp_seq);
 }
 EXPORT_SYMBOL_GPL(srcutorture_get_gp_data);
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9e619c4878d3..4a528a062cd4 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -638,7 +638,7 @@ EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
  * Send along grace-period-related data for rcutorture diagnostics.
  */
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
-			    unsigned long *gpnum, unsigned long *completed)
+			    unsigned long *gp_seq)
 {
 	struct rcu_state *rsp = NULL;
 
@@ -658,8 +658,7 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 	if (rsp == NULL)
 		return;
 	*flags = READ_ONCE(rsp->gp_flags);
-	*gpnum = READ_ONCE(rsp->gpnum);
-	*completed = READ_ONCE(rsp->completed);
+	*gp_seq = rcu_seq_current(&rsp->gp_seq);
 }
 EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
 
-- 
cgit v1.2.3


From d2bdd2681278d66fd34cd8e0cf724de918f429b2 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Wed, 11 Jul 2018 14:32:20 +0530
Subject: net/tls: Use aead_request_alloc/free for request alloc/free

Instead of kzalloc/free for aead_request allocation and free, use
functions aead_request_alloc(), aead_request_free(). It ensures that
any sensitive crypto material held in crypto transforms is securely
erased from memory.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 0d670c8adf18..7453f5ae0819 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -57,14 +57,11 @@ static int tls_do_decryption(struct sock *sk,
 	struct aead_request *aead_req;
 
 	int ret;
-	unsigned int req_size = sizeof(struct aead_request) +
-		crypto_aead_reqsize(ctx->aead_recv);
 
-	aead_req = kzalloc(req_size, flags);
+	aead_req = aead_request_alloc(ctx->aead_recv, flags);
 	if (!aead_req)
 		return -ENOMEM;
 
-	aead_request_set_tfm(aead_req, ctx->aead_recv);
 	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
 	aead_request_set_crypt(aead_req, sgin, sgout,
 			       data_len + tls_ctx->rx.tag_size,
@@ -86,7 +83,7 @@ static int tls_do_decryption(struct sock *sk,
 	ctx->saved_data_ready(sk);
 
 out:
-	kfree(aead_req);
+	aead_request_free(aead_req);
 	return ret;
 }
 
@@ -224,8 +221,7 @@ static int tls_push_record(struct sock *sk, int flags,
 	struct aead_request *req;
 	int rc;
 
-	req = kzalloc(sizeof(struct aead_request) +
-		      crypto_aead_reqsize(ctx->aead_send), sk->sk_allocation);
+	req = aead_request_alloc(ctx->aead_send, sk->sk_allocation);
 	if (!req)
 		return -ENOMEM;
 
@@ -267,7 +263,7 @@ static int tls_push_record(struct sock *sk, int flags,
 
 	tls_advance_record_sn(sk, &tls_ctx->tx);
 out_req:
-	kfree(req);
+	aead_request_free(req);
 	return rc;
 }
 
-- 
cgit v1.2.3


From cca9bab1b72cd2296097c75f59ef11ef80461279 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 12:16:12 +0200
Subject: tcp: use monotonic timestamps for PAWS

Using get_seconds() for timestamps is deprecated since it can lead
to overflows on 32-bit systems. While the interface generally doesn't
overflow until year 2106, the specific implementation of the TCP PAWS
algorithm breaks in 2038 when the intermediate signed 32-bit timestamps
overflow.

A related problem is that the local timestamps in CLOCK_REALTIME form
lead to unexpected behavior when settimeofday is called to set the system
clock backwards or forwards by more than 24 days.

While the first problem could be solved by using an overflow-safe method
of comparing the timestamps, a nicer solution is to use a monotonic
clocksource with ktime_get_seconds() that simply doesn't overflow (at
least not until 136 years after boot) and that doesn't change during
settimeofday().

To make 32-bit and 64-bit architectures behave the same way here, and
also save a few bytes in the tcp_options_received structure, I'm changing
the type to a 32-bit integer, which is now safe on all architectures.

Finally, the ts_recent_stamp field also (confusingly) gets used to store
a jiffies value in tcp_synq_overflow()/tcp_synq_no_recent_overflow().
This is currently safe, but changing the type to 32-bit requires
some small changes there to keep it working.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/crypto/chelsio/chtls/chtls_cm.c |  2 +-
 include/linux/tcp.h                     |  4 ++--
 include/net/tcp.h                       | 17 ++++++++++-------
 net/ipv4/tcp_input.c                    |  2 +-
 net/ipv4/tcp_ipv4.c                     |  3 ++-
 net/ipv4/tcp_minisocks.c                |  8 ++++----
 6 files changed, 20 insertions(+), 16 deletions(-)

diff --git a/drivers/crypto/chelsio/chtls/chtls_cm.c b/drivers/crypto/chelsio/chtls/chtls_cm.c
index 2bb6f0380758..0997e166ea57 100644
--- a/drivers/crypto/chelsio/chtls/chtls_cm.c
+++ b/drivers/crypto/chelsio/chtls/chtls_cm.c
@@ -1673,7 +1673,7 @@ static void chtls_timewait(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	tp->rcv_nxt++;
-	tp->rx_opt.ts_recent_stamp = get_seconds();
+	tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 	tp->srtt_us = 0;
 	tcp_time_wait(sk, TCP_TIME_WAIT, 0);
 }
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 3dbea6610304..58a8d7d71354 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -89,7 +89,7 @@ struct tcp_sack_block {
 
 struct tcp_options_received {
 /*	PAWS/RTTM data	*/
-	long	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
+	int	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
 	u32	ts_recent;	/* Time stamp to echo next		*/
 	u32	rcv_tsval;	/* Time stamp value             	*/
 	u32	rcv_tsecr;	/* Time stamp echo reply        	*/
@@ -426,7 +426,7 @@ struct tcp_timewait_sock {
 	/* The time we sent the last out-of-window ACK: */
 	u32			  tw_last_oow_ack_time;
 
-	long			  tw_ts_recent_stamp;
+	int			  tw_ts_recent_stamp;
 #ifdef CONFIG_TCP_MD5SIG
 	struct tcp_md5sig_key	  *tw_md5_key;
 #endif
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f6cb20e6e524..582304955087 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -472,19 +472,20 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
  */
 static inline void tcp_synq_overflow(const struct sock *sk)
 {
-	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
-	unsigned long now = jiffies;
+	unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int now = jiffies;
 
-	if (time_after(now, last_overflow + HZ))
+	if (time_after32(now, last_overflow + HZ))
 		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
 }
 
 /* syncookies: no recent synqueue overflow on this listening socket? */
 static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 {
-	unsigned long last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int now = jiffies;
 
-	return time_after(jiffies, last_overflow + TCP_SYNCOOKIE_VALID);
+	return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
 }
 
 static inline u32 tcp_cookie_time(void)
@@ -1375,7 +1376,8 @@ static inline bool tcp_paws_check(const struct tcp_options_received *rx_opt,
 {
 	if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
 		return true;
-	if (unlikely(get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS))
+	if (unlikely(!time_before32(ktime_get_seconds(),
+				    rx_opt->ts_recent_stamp + TCP_PAWS_24DAYS)))
 		return true;
 	/*
 	 * Some OSes send SYN and SYNACK messages with tsval=0 tsecr=0,
@@ -1405,7 +1407,8 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
 
 	   However, we can relax time bounds for RST segments to MSL.
 	 */
-	if (rst && get_seconds() >= rx_opt->ts_recent_stamp + TCP_PAWS_MSL)
+	if (rst && !time_before32(ktime_get_seconds(),
+				  rx_opt->ts_recent_stamp + TCP_PAWS_MSL))
 		return false;
 	return true;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 814ea43dd12f..d3b6390ecf23 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3462,7 +3462,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb)
 static void tcp_store_ts_recent(struct tcp_sock *tp)
 {
 	tp->rx_opt.ts_recent = tp->rx_opt.rcv_tsval;
-	tp->rx_opt.ts_recent_stamp = get_seconds();
+	tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 }
 
 static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index bea17f1e8302..dc415c66a33a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -155,7 +155,8 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 	   and use initial timestamp retrieved from peer table.
 	 */
 	if (tcptw->tw_ts_recent_stamp &&
-	    (!twp || (reuse && get_seconds() - tcptw->tw_ts_recent_stamp > 1))) {
+	    (!twp || (reuse && time_after32(ktime_get_seconds(),
+					    tcptw->tw_ts_recent_stamp)))) {
 		tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
 		if (tp->write_seq == 0)
 			tp->write_seq = 1;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index dac5893a52b4..75ef332a7caf 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -144,7 +144,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 		tw->tw_substate	  = TCP_TIME_WAIT;
 		tcptw->tw_rcv_nxt = TCP_SKB_CB(skb)->end_seq;
 		if (tmp_opt.saw_tstamp) {
-			tcptw->tw_ts_recent_stamp = get_seconds();
+			tcptw->tw_ts_recent_stamp = ktime_get_seconds();
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
 		}
 
@@ -189,7 +189,7 @@ kill:
 
 		if (tmp_opt.saw_tstamp) {
 			tcptw->tw_ts_recent	  = tmp_opt.rcv_tsval;
-			tcptw->tw_ts_recent_stamp = get_seconds();
+			tcptw->tw_ts_recent_stamp = ktime_get_seconds();
 		}
 
 		inet_twsk_put(tw);
@@ -537,7 +537,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 	if (newtp->rx_opt.tstamp_ok) {
 		newtp->rx_opt.ts_recent = req->ts_recent;
-		newtp->rx_opt.ts_recent_stamp = get_seconds();
+		newtp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 		newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
 	} else {
 		newtp->rx_opt.ts_recent_stamp = 0;
@@ -603,7 +603,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			 * it can be estimated (approximately)
 			 * from another data.
 			 */
-			tmp_opt.ts_recent_stamp = get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
+			tmp_opt.ts_recent_stamp = ktime_get_seconds() - ((TCP_TIMEOUT_INIT/HZ)<<req->num_timeout);
 			paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
 		}
 	}
-- 
cgit v1.2.3


From 6f3dfb0dc831953187fea8e3b798768611441321 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 11 Jul 2018 16:04:49 +0200
Subject: net/sched: skbedit: use per-cpu counters

use per-CPU counters, instead of sharing a single set of stats with all
cores: this removes the need of spinlocks when stats are read/updated.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbedit.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 86521a74ecdd..8651b5bd6b59 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -38,10 +38,10 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 {
 	struct tcf_skbedit *d = to_skbedit(a);
 
-	spin_lock(&d->tcf_lock);
 	tcf_lastuse_update(&d->tcf_tm);
-	bstats_update(&d->tcf_bstats, skb);
+	bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
 
+	spin_lock(&d->tcf_lock);
 	if (d->flags & SKBEDIT_F_PRIORITY)
 		skb->priority = d->priority;
 	if (d->flags & SKBEDIT_F_INHERITDSFIELD) {
@@ -77,8 +77,8 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 	return d->tcf_action;
 
 err:
-	d->tcf_qstats.drops++;
 	spin_unlock(&d->tcf_lock);
+	qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats));
 	return TC_ACT_SHOT;
 }
 
@@ -169,7 +169,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
-				     &act_skbedit_ops, bind, false);
+				     &act_skbedit_ops, bind, true);
 		if (ret) {
 			tcf_idr_cleanup(tn, parm->index);
 			return ret;
-- 
cgit v1.2.3


From c749cdda9089eb1fdb6a9ab98f945124d12f2595 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Wed, 11 Jul 2018 16:04:50 +0200
Subject: net/sched: act_skbedit: don't use spinlock in the data path

use RCU instead of spin_{,un}lock_bh, to protect concurrent read/write on
act_skbedit configuration. This reduces the effects of contention in the
data path, in case multiple readers are present.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tc_act/tc_skbedit.h |  37 ++++++++++----
 net/sched/act_skbedit.c         | 107 +++++++++++++++++++++++++---------------
 2 files changed, 95 insertions(+), 49 deletions(-)

diff --git a/include/net/tc_act/tc_skbedit.h b/include/net/tc_act/tc_skbedit.h
index 19cd3d345804..911bbac838a2 100644
--- a/include/net/tc_act/tc_skbedit.h
+++ b/include/net/tc_act/tc_skbedit.h
@@ -22,14 +22,19 @@
 #include <net/act_api.h>
 #include <linux/tc_act/tc_skbedit.h>
 
+struct tcf_skbedit_params {
+	u32 flags;
+	u32 priority;
+	u32 mark;
+	u32 mask;
+	u16 queue_mapping;
+	u16 ptype;
+	struct rcu_head rcu;
+};
+
 struct tcf_skbedit {
-	struct tc_action	common;
-	u32		flags;
-	u32		priority;
-	u32		mark;
-	u32		mask;
-	u16		queue_mapping;
-	u16		ptype;
+	struct tc_action common;
+	struct tcf_skbedit_params __rcu *params;
 };
 #define to_skbedit(a) ((struct tcf_skbedit *)a)
 
@@ -37,15 +42,27 @@ struct tcf_skbedit {
 static inline bool is_tcf_skbedit_mark(const struct tc_action *a)
 {
 #ifdef CONFIG_NET_CLS_ACT
-	if (a->ops && a->ops->type == TCA_ACT_SKBEDIT)
-		return to_skbedit(a)->flags == SKBEDIT_F_MARK;
+	u32 flags;
+
+	if (a->ops && a->ops->type == TCA_ACT_SKBEDIT) {
+		rcu_read_lock();
+		flags = rcu_dereference(to_skbedit(a)->params)->flags;
+		rcu_read_unlock();
+		return flags == SKBEDIT_F_MARK;
+	}
 #endif
 	return false;
 }
 
 static inline u32 tcf_skbedit_mark(const struct tc_action *a)
 {
-	return to_skbedit(a)->mark;
+	u32 mark;
+
+	rcu_read_lock();
+	mark = rcu_dereference(to_skbedit(a)->params)->mark;
+	rcu_read_unlock();
+
+	return mark;
 }
 
 #endif /* __NET_TC_SKBEDIT_H */
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index 8651b5bd6b59..da56e6938c9e 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -37,14 +37,19 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 		       struct tcf_result *res)
 {
 	struct tcf_skbedit *d = to_skbedit(a);
+	struct tcf_skbedit_params *params;
+	int action;
 
 	tcf_lastuse_update(&d->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
 
-	spin_lock(&d->tcf_lock);
-	if (d->flags & SKBEDIT_F_PRIORITY)
-		skb->priority = d->priority;
-	if (d->flags & SKBEDIT_F_INHERITDSFIELD) {
+	rcu_read_lock();
+	params = rcu_dereference(d->params);
+	action = READ_ONCE(d->tcf_action);
+
+	if (params->flags & SKBEDIT_F_PRIORITY)
+		skb->priority = params->priority;
+	if (params->flags & SKBEDIT_F_INHERITDSFIELD) {
 		int wlen = skb_network_offset(skb);
 
 		switch (tc_skb_protocol(skb)) {
@@ -63,23 +68,23 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 			break;
 		}
 	}
-	if (d->flags & SKBEDIT_F_QUEUE_MAPPING &&
-	    skb->dev->real_num_tx_queues > d->queue_mapping)
-		skb_set_queue_mapping(skb, d->queue_mapping);
-	if (d->flags & SKBEDIT_F_MARK) {
-		skb->mark &= ~d->mask;
-		skb->mark |= d->mark & d->mask;
+	if (params->flags & SKBEDIT_F_QUEUE_MAPPING &&
+	    skb->dev->real_num_tx_queues > params->queue_mapping)
+		skb_set_queue_mapping(skb, params->queue_mapping);
+	if (params->flags & SKBEDIT_F_MARK) {
+		skb->mark &= ~params->mask;
+		skb->mark |= params->mark & params->mask;
 	}
-	if (d->flags & SKBEDIT_F_PTYPE)
-		skb->pkt_type = d->ptype;
-
-	spin_unlock(&d->tcf_lock);
-	return d->tcf_action;
+	if (params->flags & SKBEDIT_F_PTYPE)
+		skb->pkt_type = params->ptype;
 
+unlock:
+	rcu_read_unlock();
+	return action;
 err:
-	spin_unlock(&d->tcf_lock);
 	qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats));
-	return TC_ACT_SHOT;
+	action = TC_ACT_SHOT;
+	goto unlock;
 }
 
 static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
@@ -98,6 +103,7 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 			    struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, skbedit_net_id);
+	struct tcf_skbedit_params *params_old, *params_new;
 	struct nlattr *tb[TCA_SKBEDIT_MAX + 1];
 	struct tc_skbedit *parm;
 	struct tcf_skbedit *d;
@@ -185,25 +191,34 @@ static int tcf_skbedit_init(struct net *net, struct nlattr *nla,
 		}
 	}
 
-	spin_lock_bh(&d->tcf_lock);
+	ASSERT_RTNL();
 
-	d->flags = flags;
+	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
+	if (unlikely(!params_new)) {
+		if (ret == ACT_P_CREATED)
+			tcf_idr_release(*a, bind);
+		return -ENOMEM;
+	}
+
+	params_new->flags = flags;
 	if (flags & SKBEDIT_F_PRIORITY)
-		d->priority = *priority;
+		params_new->priority = *priority;
 	if (flags & SKBEDIT_F_QUEUE_MAPPING)
-		d->queue_mapping = *queue_mapping;
+		params_new->queue_mapping = *queue_mapping;
 	if (flags & SKBEDIT_F_MARK)
-		d->mark = *mark;
+		params_new->mark = *mark;
 	if (flags & SKBEDIT_F_PTYPE)
-		d->ptype = *ptype;
+		params_new->ptype = *ptype;
 	/* default behaviour is to use all the bits */
-	d->mask = 0xffffffff;
+	params_new->mask = 0xffffffff;
 	if (flags & SKBEDIT_F_MASK)
-		d->mask = *mask;
+		params_new->mask = *mask;
 
 	d->tcf_action = parm->action;
-
-	spin_unlock_bh(&d->tcf_lock);
+	params_old = rtnl_dereference(d->params);
+	rcu_assign_pointer(d->params, params_new);
+	if (params_old)
+		kfree_rcu(params_old, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -215,33 +230,36 @@ static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a,
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_skbedit *d = to_skbedit(a);
+	struct tcf_skbedit_params *params;
 	struct tc_skbedit opt = {
 		.index   = d->tcf_index,
 		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
 		.action  = d->tcf_action,
 	};
-	struct tcf_t t;
 	u64 pure_flags = 0;
+	struct tcf_t t;
+
+	params = rtnl_dereference(d->params);
 
 	if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_PRIORITY) &&
-	    nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, d->priority))
+	if ((params->flags & SKBEDIT_F_PRIORITY) &&
+	    nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_QUEUE_MAPPING) &&
-	    nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, d->queue_mapping))
+	if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) &&
+	    nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_MARK) &&
-	    nla_put_u32(skb, TCA_SKBEDIT_MARK, d->mark))
+	if ((params->flags & SKBEDIT_F_MARK) &&
+	    nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_PTYPE) &&
-	    nla_put_u16(skb, TCA_SKBEDIT_PTYPE, d->ptype))
+	if ((params->flags & SKBEDIT_F_PTYPE) &&
+	    nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype))
 		goto nla_put_failure;
-	if ((d->flags & SKBEDIT_F_MASK) &&
-	    nla_put_u32(skb, TCA_SKBEDIT_MASK, d->mask))
+	if ((params->flags & SKBEDIT_F_MASK) &&
+	    nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask))
 		goto nla_put_failure;
-	if (d->flags & SKBEDIT_F_INHERITDSFIELD)
+	if (params->flags & SKBEDIT_F_INHERITDSFIELD)
 		pure_flags |= SKBEDIT_F_INHERITDSFIELD;
 	if (pure_flags != 0 &&
 	    nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags))
@@ -257,6 +275,16 @@ nla_put_failure:
 	return -1;
 }
 
+static void tcf_skbedit_cleanup(struct tc_action *a)
+{
+	struct tcf_skbedit *d = to_skbedit(a);
+	struct tcf_skbedit_params *params;
+
+	params = rcu_dereference_protected(d->params, 1);
+	if (params)
+		kfree_rcu(params, rcu);
+}
+
 static int tcf_skbedit_walker(struct net *net, struct sk_buff *skb,
 			      struct netlink_callback *cb, int type,
 			      const struct tc_action_ops *ops,
@@ -289,6 +317,7 @@ static struct tc_action_ops act_skbedit_ops = {
 	.act		=	tcf_skbedit,
 	.dump		=	tcf_skbedit_dump,
 	.init		=	tcf_skbedit_init,
+	.cleanup	=	tcf_skbedit_cleanup,
 	.walk		=	tcf_skbedit_walker,
 	.lookup		=	tcf_skbedit_search,
 	.delete		=	tcf_skbedit_delete,
-- 
cgit v1.2.3


From aa667c6408d20a84c7637420bc3b7aa0abab59a2 Mon Sep 17 00:00:00 2001
From: James Puthukattukaran <james.puthukattukaran@oracle.com>
Date: Mon, 9 Jul 2018 11:31:25 -0400
Subject: PCI: Workaround IDT switch ACS Source Validation erratum

Some IDT switches incorrectly flag an ACS Source Validation error on
completions for config read requests even though PCIe r4.0, sec 6.12.1.1,
says that completions are never affected by ACS Source Validation.  Here's
the text of IDT 89H32H8G3-YC, erratum #36:

  Item #36 - Downstream port applies ACS Source Validation to Completions
  Section 6.12.1.1 of the PCI Express Base Specification 3.1 states that
  completions are never affected by ACS Source Validation.  However,
  completions received by a downstream port of the PCIe switch from a
  device that has not yet captured a PCIe bus number are incorrectly
  dropped by ACS Source Validation by the switch downstream port.

  Workaround: Issue a CfgWr1 to the downstream device before issuing the
  first CfgRd1 to the device.  This allows the downstream device to capture
  its bus number; ACS Source Validation no longer stops completions from
  being forwarded by the downstream port.  It has been observed that
  Microsoft Windows implements this workaround already; however, some
  versions of Linux and other operating systems may not.

When doing the first config read to probe for a device, if the device is
behind an IDT switch with this erratum:

  1. Disable ACS Source Validation if enabled
  2. Wait for device to become ready to accept config accesses (by using
     the Config Request Retry Status mechanism)
  3. Do a config write to the endpoint
  4. Enable ACS Source Validation (if it was enabled to begin with)

The workaround suggested by IDT is basically only step 3, but we don't know
when the device is ready to accept config requests.  That means we need to
do config reads until we receive a non-Config Request Retry Status, which
means we need to disable ACS SV temporarily.

Signed-off-by: James Puthukattukaran <james.puthukattukaran@oracle.com>
[bhelgaas: changelog, clean up whitespace, fold in unused variable fix
from Anders Roxell <anders.roxell@linaro.org>]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/pci/pci.h    |  4 ++++
 drivers/pci/probe.c  | 22 +++++++++++++++++++--
 drivers/pci/quirks.c | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 79 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c358e7a07f3f..70808c168fb9 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -225,6 +225,10 @@ enum pci_bar_type {
 int pci_configure_extended_tags(struct pci_dev *dev, void *ign);
 bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
 				int crs_timeout);
+bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
+					int crs_timeout);
+int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int crs_timeout);
+
 int pci_setup_device(struct pci_dev *dev);
 int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		    struct resource *res, unsigned int reg);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..7c0c8ab94bcf 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2156,8 +2156,8 @@ static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l,
 	return true;
 }
 
-bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
-				int timeout)
+bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
+					int timeout)
 {
 	if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l))
 		return false;
@@ -2172,6 +2172,24 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 
 	return true;
 }
+
+bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
+				int timeout)
+{
+#ifdef CONFIG_PCI_QUIRKS
+	struct pci_dev *bridge = bus->self;
+
+	/*
+	 * Certain IDT switches have an issue where they improperly trigger
+	 * ACS Source Validation errors on completions for config reads.
+	 */
+	if (bridge && bridge->vendor == PCI_VENDOR_ID_IDT &&
+	    bridge->device == 0x80b5)
+		return pci_idt_bus_quirk(bus, devfn, l, timeout);
+#endif
+
+	return pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout);
+}
 EXPORT_SYMBOL(pci_bus_read_dev_vendor_id);
 
 /*
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f439de848658..cab2d5f922a9 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4753,3 +4753,58 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMD, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
+
+/*
+ * Some IDT switches incorrectly flag an ACS Source Validation error on
+ * completions for config read requests even though PCIe r4.0, sec
+ * 6.12.1.1, says that completions are never affected by ACS Source
+ * Validation.  Here's the text of IDT 89H32H8G3-YC, erratum #36:
+ *
+ *   Item #36 - Downstream port applies ACS Source Validation to Completions
+ *   Section 6.12.1.1 of the PCI Express Base Specification 3.1 states that
+ *   completions are never affected by ACS Source Validation.  However,
+ *   completions received by a downstream port of the PCIe switch from a
+ *   device that has not yet captured a PCIe bus number are incorrectly
+ *   dropped by ACS Source Validation by the switch downstream port.
+ *
+ * The workaround suggested by IDT is to issue a config write to the
+ * downstream device before issuing the first config read.  This allows the
+ * downstream device to capture its bus and device numbers (see PCIe r4.0,
+ * sec 2.2.9), thus avoiding the ACS error on the completion.
+ *
+ * However, we don't know when the device is ready to accept the config
+ * write, so we do config reads until we receive a non-Config Request Retry
+ * Status, then do the config write.
+ *
+ * To avoid hitting the erratum when doing the config reads, we disable ACS
+ * SV around this process.
+ */
+int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *l, int timeout)
+{
+	int pos;
+	u16 ctrl = 0;
+	bool found;
+	struct pci_dev *bridge = bus->self;
+
+	pos = pci_find_ext_capability(bridge, PCI_EXT_CAP_ID_ACS);
+
+	/* Disable ACS SV before initial config reads */
+	if (pos) {
+		pci_read_config_word(bridge, pos + PCI_ACS_CTRL, &ctrl);
+		if (ctrl & PCI_ACS_SV)
+			pci_write_config_word(bridge, pos + PCI_ACS_CTRL,
+					      ctrl & ~PCI_ACS_SV);
+	}
+
+	found = pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout);
+
+	/* Write Vendor ID (read-only) so the endpoint latches its bus/dev */
+	if (found)
+		pci_bus_write_config_word(bus, devfn, PCI_VENDOR_ID, 0);
+
+	/* Re-enable ACS_SV if it was previously enabled */
+	if (ctrl & PCI_ACS_SV)
+		pci_write_config_word(bridge, pos + PCI_ACS_CTRL, ctrl);
+
+	return found;
+}
-- 
cgit v1.2.3


From 44c58899b09d6cbf113f50465215fc66258461df Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 14:29:52 +0200
Subject: liquidio: use ktime_get_real_ts64() instead of getnstimeofday64()

The two do the same thing, but we want to have a consistent
naming in the kernel.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/lio_main.c       | 2 +-
 drivers/net/ethernet/cavium/liquidio/octeon_console.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index ebda6efc3290..a60d5afeac28 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -684,7 +684,7 @@ static void lio_sync_octeon_time(struct work_struct *work)
 	lt = (struct lio_time *)sc->virtdptr;
 
 	/* Get time of the day */
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 	lt->sec = ts.tv_sec;
 	lt->nsec = ts.tv_nsec;
 	octeon_swap_8B_data((u64 *)lt, (sizeof(struct lio_time)) / 8);
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_console.c b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
index 7f97ae48efed..0cc2338d8d2a 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_console.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_console.c
@@ -902,7 +902,7 @@ int octeon_download_firmware(struct octeon_device *oct, const u8 *data,
 	 *
 	 * Octeon always uses UTC time. so timezone information is not sent.
 	 */
-	getnstimeofday64(&ts);
+	ktime_get_real_ts64(&ts);
 	ret = snprintf(boottime, MAX_BOOTTIME_SIZE,
 		       " time_sec=%lld time_nsec=%ld",
 		       (s64)ts.tv_sec, ts.tv_nsec);
-- 
cgit v1.2.3


From 51bef926be1e3154996ce400d862aebb98ccbed6 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 14:29:53 +0200
Subject: nfp: avoid using getnstimeofday64()

getnstimeofday64 is deprecated in favor of the ktime_get() family of
functions. The direct replacement would be ktime_get_real_ts64(),
but I'm picking the basic ktime_get() instead:

- using a ktime_t simplifies the code compared to timespec64
- using monotonic time instead of real time avoids issues caused
  by a concurrent settimeofday() or during a leap second adjustment.

Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/main.h     |  2 +-
 drivers/net/ethernet/netronome/nfp/flower/metadata.c | 12 +++++-------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index bbe5764d26cb..ef2114d13387 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -73,7 +73,7 @@ struct nfp_app;
 
 struct nfp_fl_mask_id {
 	struct circ_buf mask_id_free_list;
-	struct timespec64 *last_used;
+	ktime_t *last_used;
 	u8 init_unallocated;
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
index 93fb809f50d1..c098730544b7 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c
@@ -158,7 +158,6 @@ static int nfp_release_mask_id(struct nfp_app *app, u8 mask_id)
 {
 	struct nfp_flower_priv *priv = app->priv;
 	struct circ_buf *ring;
-	struct timespec64 now;
 
 	ring = &priv->mask_ids.mask_id_free_list;
 	/* Checking if buffer is full. */
@@ -169,8 +168,7 @@ static int nfp_release_mask_id(struct nfp_app *app, u8 mask_id)
 	ring->head = (ring->head + NFP_FLOWER_MASK_ELEMENT_RS) %
 		     (NFP_FLOWER_MASK_ENTRY_RS * NFP_FLOWER_MASK_ELEMENT_RS);
 
-	getnstimeofday64(&now);
-	priv->mask_ids.last_used[mask_id] = now;
+	priv->mask_ids.last_used[mask_id] = ktime_get();
 
 	return 0;
 }
@@ -178,7 +176,7 @@ static int nfp_release_mask_id(struct nfp_app *app, u8 mask_id)
 static int nfp_mask_alloc(struct nfp_app *app, u8 *mask_id)
 {
 	struct nfp_flower_priv *priv = app->priv;
-	struct timespec64 delta, now;
+	ktime_t reuse_timeout;
 	struct circ_buf *ring;
 	u8 temp_id, freed_id;
 
@@ -198,10 +196,10 @@ static int nfp_mask_alloc(struct nfp_app *app, u8 *mask_id)
 	memcpy(&temp_id, &ring->buf[ring->tail], NFP_FLOWER_MASK_ELEMENT_RS);
 	*mask_id = temp_id;
 
-	getnstimeofday64(&now);
-	delta = timespec64_sub(now, priv->mask_ids.last_used[*mask_id]);
+	reuse_timeout = ktime_add_ns(priv->mask_ids.last_used[*mask_id],
+				     NFP_FL_MASK_REUSE_TIME_NS);
 
-	if (timespec64_to_ns(&delta) < NFP_FL_MASK_REUSE_TIME_NS)
+	if (ktime_before(ktime_get(), reuse_timeout))
 		goto err_not_found;
 
 	memcpy(&ring->buf[ring->tail], &freed_id, NFP_FLOWER_MASK_ELEMENT_RS);
-- 
cgit v1.2.3


From d6488ac19aabcc6c85a74b69eaf1b7301124c323 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 5 Jul 2018 09:56:00 -0500
Subject: PCI: Mark fall-through switch cases before enabling
 -Wimplicit-fallthrough

In preparation to enabling -Wimplicit-fallthrough, mark switch cases where
we are expecting to fall through.

Warning level 2 was used: -Wimplicit-fallthrough=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp_ctrl.c | 2 ++
 drivers/pci/hotplug/shpchp_ctrl.c | 2 ++
 drivers/pci/pci.c                 | 1 +
 drivers/pci/quirks.c              | 1 +
 4 files changed, 6 insertions(+)

diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index c684faa43387..cfc46e82ceca 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -436,6 +436,7 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
 		cancel_delayed_work(&p_slot->work);
+		/* fall through */
 	case STATIC_STATE:
 		p_slot->state = POWERON_STATE;
 		mutex_unlock(&p_slot->lock);
@@ -473,6 +474,7 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&p_slot->work);
+		/* fall through */
 	case STATIC_STATE:
 		p_slot->state = POWEROFF_STATE;
 		mutex_unlock(&p_slot->lock);
diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c
index 1047b56e5730..1267dcc5a531 100644
--- a/drivers/pci/hotplug/shpchp_ctrl.c
+++ b/drivers/pci/hotplug/shpchp_ctrl.c
@@ -654,6 +654,7 @@ int shpchp_sysfs_enable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
 		cancel_delayed_work(&p_slot->work);
+		/* fall through */
 	case STATIC_STATE:
 		p_slot->state = POWERON_STATE;
 		mutex_unlock(&p_slot->lock);
@@ -689,6 +690,7 @@ int shpchp_sysfs_disable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&p_slot->work);
+		/* fall through */
 	case STATIC_STATE:
 		p_slot->state = POWEROFF_STATE;
 		mutex_unlock(&p_slot->lock);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..f5c6ab14fb31 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2045,6 +2045,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 		case PCI_D2:
 			if (pci_no_d1d2(dev))
 				break;
+			/* else: fall through */
 		default:
 			target_state = state;
 		}
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f439de848658..502275c092ae 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2105,6 +2105,7 @@ static void quirk_netmos(struct pci_dev *dev)
 		if (dev->subsystem_vendor == PCI_VENDOR_ID_IBM &&
 				dev->subsystem_device == 0x0299)
 			return;
+		/* else: fall through */
 	case PCI_DEVICE_ID_NETMOS_9735:
 	case PCI_DEVICE_ID_NETMOS_9745:
 	case PCI_DEVICE_ID_NETMOS_9845:
-- 
cgit v1.2.3


From 7a1d0f23ad70cd4813bf4b72735ea2c26a4f53fe Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 10:26:57 -0700
Subject: rcu: Move from ->need_future_gp[] to ->gp_seq_needed

One problem with the ->need_future_gp[] array is that the grace-period
assignment of each element changes as the grace periods complete.
This means that it is necessary to hold a lock when checking this
array to learn if a given grace period has already been requested.
This increase lock contention, which is the opposite of helpful.
This commit therefore replaces the ->need_future_gp[] with a single
->gp_seq_needed value and keeps it updated in the rcu_data structure.

This will enable reliable lockless checking of whether or not a given
grace period has already been requested.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 34 ++++++++++++++++++----------------
 kernel/rcu/tree.h | 19 ++-----------------
 2 files changed, 20 insertions(+), 33 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4a528a062cd4..1ede51690e4a 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1560,7 +1560,7 @@ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 /*
  * Start the specified grace period, as needed to handle newly arrived
  * callbacks.  The required future grace periods are recorded in each
- * rcu_node structure's ->need_future_gp[] field.  Returns true if there
+ * rcu_node structure's ->gp_seq_needed field.  Returns true if there
  * is reason to awaken the grace-period kthread.
  *
  * The caller must hold the specified rcu_node structure's ->lock, which
@@ -1589,14 +1589,14 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
 		if (rnp_root != rnp)
 			raw_spin_lock_rcu_node(rnp_root);
-		if (need_future_gp_element(rnp_root, c) ||
+		if (ULONG_CMP_GE(rnp_root->gp_seq_needed, c) ||
 		    rcu_seq_done(&rnp_root->gp_seq, c) ||
 		    (rnp != rnp_root &&
 		     rcu_seq_state(rcu_seq_current(&rnp_root->gp_seq)))) {
 			trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
 			goto unlock_out;
 		}
-		need_future_gp_element(rnp_root, c) = true;
+		rnp_root->gp_seq_needed = c;
 		if (rnp_root != rnp && rnp_root->parent != NULL)
 			raw_spin_unlock_rcu_node(rnp_root);
 		if (!rnp_root->parent)
@@ -1633,8 +1633,9 @@ static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 	bool needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
-	need_future_gp_element(rnp, c) = false;
-	needmore = need_any_future_gp(rnp);
+	needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
+	if (!needmore)
+		rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
 	trace_rcu_this_gp(rnp, rdp, c,
 			  needmore ? TPS("CleanupMore") : TPS("Cleanup"));
 	return needmore;
@@ -2046,7 +2047,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rsp->gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(rsp->rda);
-	if (need_any_future_gp(rnp)) {
+	if (ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
 		trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
 				  TPS("CleanupMore"));
 		needgp = true;
@@ -2700,8 +2701,8 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
 	static atomic_t warned = ATOMIC_INIT(0);
 
-	if (!IS_ENABLED(CONFIG_PROVE_RCU) ||
-	    rcu_gp_in_progress(rsp) || !need_any_future_gp(rcu_get_root(rsp)))
+	if (!IS_ENABLED(CONFIG_PROVE_RCU) || rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
 		return;
 	j = jiffies; /* Expensive access, and in common case don't get here. */
 	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
@@ -2711,7 +2712,8 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	raw_spin_lock_irqsave_rcu_node(rnp, flags);
 	j = jiffies;
-	if (rcu_gp_in_progress(rsp) || !need_any_future_gp(rcu_get_root(rsp)) ||
+	if (rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
 	    time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
 	    time_before(j, READ_ONCE(rsp->gp_activity) + HZ) ||
 	    atomic_read(&warned)) {
@@ -2723,7 +2725,8 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	if (rnp_root != rnp)
 		raw_spin_lock_rcu_node(rnp_root); /* irqs already disabled. */
 	j = jiffies;
-	if (rcu_gp_in_progress(rsp) || !need_any_future_gp(rcu_get_root(rsp)) ||
+	if (rcu_gp_in_progress(rsp) ||
+	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
 	    time_before(j, rsp->gp_req_activity + HZ) ||
 	    time_before(j, rsp->gp_activity + HZ) ||
 	    atomic_xchg(&warned, 1)) {
@@ -2731,12 +2734,9 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
-	pr_alert("%s: g%lu %d%d%d%d gar:%lu ga:%lu f%#x %s->state:%#lx\n",
-		 __func__, READ_ONCE(rsp->gpnum),
-		 need_future_gp_element(rcu_get_root(rsp), 0),
-		 need_future_gp_element(rcu_get_root(rsp), 1),
-		 need_future_gp_element(rcu_get_root(rsp), 2),
-		 need_future_gp_element(rcu_get_root(rsp), 3),
+	pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x %s->state:%#lx\n",
+		 __func__, (long)READ_ONCE(rsp->gp_seq),
+		 (long)READ_ONCE(rnp_root->gp_seq_needed),
 		 j - rsp->gp_req_activity, j - rsp->gp_activity,
 		 rsp->gp_flags, rsp->name,
 		 rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
@@ -3527,6 +3527,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
 	rdp->completed = rnp->completed;
 	rdp->gp_seq = rnp->gp_seq;
+	rdp->gp_seq_needed = rnp->gp_seq;
 	rdp->cpu_no_qs.b.norm = true;
 	rdp->rcu_qs_ctr_snap = per_cpu(rcu_dynticks.rcu_qs_ctr, cpu);
 	rdp->core_needs_qs = false;
@@ -3907,6 +3908,7 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			rnp->gpnum = rsp->gpnum;
 			rnp->completed = rsp->completed;
 			rnp->gp_seq = rsp->gp_seq;
+			rnp->gp_seq_needed = rsp->gp_seq;
 			rnp->completedqs = rsp->gp_seq;
 			rnp->qsmask = 0;
 			rnp->qsmaskinit = 0;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index a21d403a6010..9329c1ff695f 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -88,6 +88,7 @@ struct rcu_node {
 				/*  This will either be equal to or one */
 				/*  behind the root rcu_node's gpnum. */
 	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
+	unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
 	unsigned long completedqs; /* All QSes done for this node. */
 	unsigned long qsmask;	/* CPUs or groups that need to switch in */
 				/*  order for current grace period to proceed.*/
@@ -160,7 +161,6 @@ struct rcu_node {
 	struct swait_queue_head nocb_gp_wq[2];
 				/* Place for rcu_nocb_kthread() to wait GP. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-	u8 need_future_gp[4];	/* Counts of upcoming GP requests. */
 	raw_spinlock_t fqslock ____cacheline_internodealigned_in_smp;
 
 	spinlock_t exp_lock ____cacheline_internodealigned_in_smp;
@@ -170,22 +170,6 @@ struct rcu_node {
 	bool exp_need_flush;	/* Need to flush workitem? */
 } ____cacheline_internodealigned_in_smp;
 
-/* Accessors for ->need_future_gp[] array. */
-#define need_future_gp_mask() \
-	(ARRAY_SIZE(((struct rcu_node *)NULL)->need_future_gp) - 1)
-#define need_future_gp_element(rnp, c) \
-	((rnp)->need_future_gp[(c >> RCU_SEQ_CTR_SHIFT) & need_future_gp_mask()])
-#define need_any_future_gp(rnp)						\
-({									\
-	int __i;							\
-	bool __nonzero = false;						\
-									\
-	for (__i = 0; __i < ARRAY_SIZE((rnp)->need_future_gp); __i++)	\
-		__nonzero = __nonzero ||				\
-			    READ_ONCE((rnp)->need_future_gp[__i]);	\
-	__nonzero;							\
-})
-
 /*
  * Bitmasks in an rcu_node cover the interval [grplo, grphi] of CPU IDs, and
  * are indexed relative to this interval rather than the global CPU ID space.
@@ -213,6 +197,7 @@ struct rcu_data {
 	unsigned long	gpnum;		/* Highest gp number that this CPU */
 					/*  is aware of having started. */
 	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
+	unsigned long	gp_seq_needed;	/* Track rsp->rcu_gp_seq_needed ctr. */
 	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
 					/*  for rcu_all_qs() invocations. */
 	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
-- 
cgit v1.2.3


From ab5e869c1f7aa30a1210f5e8a277758b0599609f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 11:07:23 -0700
Subject: rcu: Make rcu_nocb_wait_gp() check if GP already requested

This commit makes rcu_nocb_wait_gp() check rdp->gp_seq_needed to see
if the current CPU already knows about the needed grace period having
already been requested.  If so, it avoids acquiring the corresponding
leaf rcu_node structure's ->lock, thus decreasing contention.  This
optimization is intended for cases where either multiple leader rcuo
kthreads are running on the same CPU or these kthreads are running on
a non-offloaded (e.g., housekeeping) CPU.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Move lock release past "if" as suggested by Joel Fernandes. ]
[ paulmck: Fix caching of furthest-future requested grace period. ]
---
 kernel/rcu/tree.c        |  5 +++++
 kernel/rcu/tree_plugin.h | 15 ++++++++++-----
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1ede51690e4a..4826598867c3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1618,6 +1618,11 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
+	/* Push furthest requested GP to leaf node and rcu_data structure. */
+	if (ULONG_CMP_LT(c, rnp_root->gp_seq_needed)) {
+		rnp->gp_seq_needed = rnp_root->gp_seq_needed;
+		rdp->gp_seq_needed = rnp_root->gp_seq_needed;
+	}
 	if (rnp != rnp_root)
 		raw_spin_unlock_rcu_node(rnp_root);
 	return ret;
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index f4a88e3c388d..ca73931f7b30 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2104,12 +2104,17 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	bool needwake;
 	struct rcu_node *rnp = rdp->mynode;
 
-	raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	local_irq_save(flags);
 	c = rcu_seq_snap(&rdp->rsp->gp_seq);
-	needwake = rcu_start_this_gp(rnp, rdp, c);
-	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-	if (needwake)
-		rcu_gp_kthread_wake(rdp->rsp);
+	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+		local_irq_restore(flags);
+	} else {
+		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+		needwake = rcu_start_this_gp(rnp, rdp, c);
+		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		if (needwake)
+			rcu_gp_kthread_wake(rdp->rsp);
+	}
 
 	/*
 	 * Wait for the grace period.  Do so interruptibly to avoid messing
-- 
cgit v1.2.3


From 477351f7829d2268769c5d545511081555066529 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 12:54:11 -0700
Subject: rcu: Convert rcu_grace_period tracepoint to gp_seq

This commit makes the rcu_grace_period tracepoint use gp_seq instead
of ->gpnum or ->completed.  It also introduces a "cpuofl-bgp" string to
less obscurely indicate when a CPU has gone offline while a grace period
is waiting on it.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 13 +++++++------
 kernel/rcu/tree.c          | 43 +++++++++++++++++++++----------------------
 kernel/rcu/tree_plugin.h   |  2 +-
 3 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5936aac357ab..cd229e82ec8b 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -52,6 +52,7 @@ TRACE_EVENT(rcu_utilization,
  *	"cpuqs": CPU passes through a quiescent state.
  *	"cpuonl": CPU comes online.
  *	"cpuofl": CPU goes offline.
+ *	"cpuofl-bgp": CPU goes offline while blocking a grace period.
  *	"reqwait": GP kthread sleeps waiting for grace-period request.
  *	"reqwaitsig": GP kthread awakened by signal from reqwait state.
  *	"fqswait": GP kthread waiting until time to force quiescent states.
@@ -63,24 +64,24 @@ TRACE_EVENT(rcu_utilization,
  */
 TRACE_EVENT(rcu_grace_period,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, const char *gpevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, const char *gpevent),
 
-	TP_ARGS(rcuname, gpnum, gpevent),
+	TP_ARGS(rcuname, gp_seq, gpevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(const char *, gpevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->gpevent = gpevent;
 	),
 
 	TP_printk("%s %lu %s",
-		  __entry->rcuname, __entry->gpnum, __entry->gpevent)
+		  __entry->rcuname, __entry->gp_seq, __entry->gpevent)
 );
 
 /*
@@ -753,7 +754,7 @@ TRACE_EVENT(rcu_barrier,
 
 #else /* #ifdef CONFIG_RCU_TRACE */
 
-#define trace_rcu_grace_period(rcuname, gpnum, gpevent) do { } while (0)
+#define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0)
 #define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4826598867c3..7ce85ad39af6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -234,7 +234,7 @@ void rcu_sched_qs(void)
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.s))
 		return;
 	trace_rcu_grace_period(TPS("rcu_sched"),
-			       __this_cpu_read(rcu_sched_data.gpnum),
+			       __this_cpu_read(rcu_sched_data.gp_seq),
 			       TPS("cpuqs"));
 	__this_cpu_write(rcu_sched_data.cpu_no_qs.b.norm, false);
 	if (!__this_cpu_read(rcu_sched_data.cpu_no_qs.b.exp))
@@ -249,7 +249,7 @@ void rcu_bh_qs(void)
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!");
 	if (__this_cpu_read(rcu_bh_data.cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_bh"),
-				       __this_cpu_read(rcu_bh_data.gpnum),
+				       __this_cpu_read(rcu_bh_data.gp_seq),
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false);
 	}
@@ -1615,7 +1615,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 		trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
-	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum), TPS("newreq"));
+	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
 	/* Push furthest requested GP to leaf node and rcu_data structure. */
@@ -1702,9 +1702,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 
 	/* Trace depending on how much we were able to accelerate. */
 	if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccWaitCB"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccWaitCB"));
 	else
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("AccReadyCB"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("AccReadyCB"));
 	return ret;
 }
 
@@ -1774,7 +1774,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		 * go looking for one.
 		 */
 		rdp->gpnum = rnp->gpnum;
-		trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpustart"));
+		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpustart"));
 		need_gp = !!(rnp->qsmask & rdp->grpmask);
 		rdp->cpu_no_qs.b.norm = need_gp;
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
@@ -1851,7 +1851,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	rcu_seq_start(&rsp->gp_seq);
 	if (WARN_ON_ONCE(((rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT) != rcu_seq_ctr(rnp->gp_seq))) /* Catch any ->completed/->gp_seq mismatches. */
 		pr_info("%s ->completed: %#lx (%#lx) ->gp_seq %#lx (%#lx)\n", __func__, rnp->completed, (rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT, rnp->gp_seq, rcu_seq_ctr(rnp->gp_seq));
-	trace_rcu_grace_period(rsp->name, rsp->gpnum, TPS("start"));
+	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
@@ -1928,7 +1928,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
 		rcu_preempt_boost_start_gp(rnp);
-		trace_rcu_grace_period_init(rsp->name, rnp->gpnum,
+		trace_rcu_grace_period_init(rsp->name, rnp->gp_seq,
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
 		raw_spin_unlock_irq_rcu_node(rnp);
@@ -2048,7 +2048,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	/* Declare grace period done. */
 	WRITE_ONCE(rsp->completed, rsp->gpnum);
 	rcu_seq_end(&rsp->gp_seq);
-	trace_rcu_grace_period(rsp->name, rsp->completed, TPS("end"));
+	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end"));
 	rsp->gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(rsp->rda);
@@ -2061,7 +2061,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	if (!rcu_accelerate_cbs(rsp, rnp, rdp) && needgp) {
 		WRITE_ONCE(rsp->gp_flags, RCU_GP_FLAG_INIT);
 		rsp->gp_req_activity = jiffies;
-		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gpnum),
+		trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq),
 				       TPS("newreq"));
 	} else {
 		WRITE_ONCE(rsp->gp_flags, rsp->gp_flags & RCU_GP_FLAG_INIT);
@@ -2087,7 +2087,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		/* Handle grace-period start. */
 		for (;;) {
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("reqwait"));
 			rsp->gp_state = RCU_GP_WAIT_GPS;
 			swait_event_idle(rsp->gp_wq, READ_ONCE(rsp->gp_flags) &
@@ -2100,7 +2100,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			WRITE_ONCE(rsp->gp_activity, jiffies);
 			WARN_ON(signal_pending(current));
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("reqwaitsig"));
 		}
 
@@ -2119,7 +2119,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 					   jiffies + 3 * j);
 			}
 			trace_rcu_grace_period(rsp->name,
-					       READ_ONCE(rsp->gpnum),
+					       READ_ONCE(rsp->gp_seq),
 					       TPS("fqswait"));
 			rsp->gp_state = RCU_GP_WAIT_FQS;
 			ret = swait_event_idle_timeout(rsp->gp_wq,
@@ -2134,12 +2134,12 @@ static int __noreturn rcu_gp_kthread(void *arg)
 			if (ULONG_CMP_GE(jiffies, rsp->jiffies_force_qs) ||
 			    (gf & RCU_GP_FLAG_FQS)) {
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqsstart"));
 				rcu_gp_fqs(rsp, first_gp_fqs);
 				first_gp_fqs = false;
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqsend"));
 				cond_resched_tasks_rcu_qs();
 				WRITE_ONCE(rsp->gp_activity, jiffies);
@@ -2158,7 +2158,7 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				WARN_ON(signal_pending(current));
 				trace_rcu_grace_period(rsp->name,
-						       READ_ONCE(rsp->gpnum),
+						       READ_ONCE(rsp->gp_seq),
 						       TPS("fqswaitsig"));
 				ret = 1; /* Keep old FQS timing. */
 				j = jiffies;
@@ -2388,17 +2388,16 @@ rcu_check_quiescent_state(struct rcu_state *rsp, struct rcu_data *rdp)
  */
 static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
 {
-	RCU_TRACE(unsigned long mask;)
+	RCU_TRACE(bool blkd;)
 	RCU_TRACE(struct rcu_data *rdp = this_cpu_ptr(rsp->rda);)
 	RCU_TRACE(struct rcu_node *rnp = rdp->mynode;)
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU))
 		return;
 
-	RCU_TRACE(mask = rdp->grpmask;)
-	trace_rcu_grace_period(rsp->name,
-			       rnp->gpnum + 1 - !!(rnp->qsmask & mask),
-			       TPS("cpuofl"));
+	RCU_TRACE(blkd = !!(rnp->qsmask & rdp->grpmask);)
+	trace_rcu_grace_period(rsp->name, rnp->gp_seq,
+			       blkd ? TPS("cpuofl") : TPS("cpuofl-bgp"));
 }
 
 /*
@@ -3538,7 +3537,7 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->core_needs_qs = false;
 	rdp->rcu_iw_pending = false;
 	rdp->rcu_iw_gp_seq = rnp->gp_seq - 1;
-	trace_rcu_grace_period(rsp->name, rdp->gpnum, TPS("cpuonl"));
+	trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuonl"));
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
 
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index ca73931f7b30..aca9d187c509 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -301,7 +301,7 @@ static void rcu_preempt_qs(void)
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_qs() invoked with preemption enabled!!!\n");
 	if (__this_cpu_read(rcu_data_p->cpu_no_qs.s)) {
 		trace_rcu_grace_period(TPS("rcu_preempt"),
-				       __this_cpu_read(rcu_data_p->gpnum),
+				       __this_cpu_read(rcu_data_p->gp_seq),
 				       TPS("cpuqs"));
 		__this_cpu_write(rcu_data_p->cpu_no_qs.b.norm, false);
 		barrier(); /* Coordinate with rcu_preempt_check_callbacks(). */
-- 
cgit v1.2.3


From abd13fdd9516e5baae2257721b921684ecb090d3 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 13:08:46 -0700
Subject: rcu: Convert rcu_future_grace_period tracepoint to gp_seq

This commit makes the rcu_future_grace_period tracepoint use gp_seq
instead of ->gpnum and ->completed.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 22 +++++++++-------------
 kernel/rcu/tree.c          |  7 +++----
 2 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index cd229e82ec8b..286047d22314 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -103,16 +103,14 @@ TRACE_EVENT(rcu_grace_period,
  */
 TRACE_EVENT(rcu_future_grace_period,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, unsigned long completed,
-		 unsigned long c, u8 level, int grplo, int grphi,
-		 const char *gpevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, unsigned long c,
+		 u8 level, int grplo, int grphi, const char *gpevent),
 
-	TP_ARGS(rcuname, gpnum, completed, c, level, grplo, grphi, gpevent),
+	TP_ARGS(rcuname, gp_seq, c, level, grplo, grphi, gpevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
-		__field(unsigned long, completed)
+		__field(unsigned long, gp_seq)
 		__field(unsigned long, c)
 		__field(u8, level)
 		__field(int, grplo)
@@ -122,8 +120,7 @@ TRACE_EVENT(rcu_future_grace_period,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
-		__entry->completed = completed;
+		__entry->gp_seq = gp_seq;
 		__entry->c = c;
 		__entry->level = level;
 		__entry->grplo = grplo;
@@ -131,10 +128,9 @@ TRACE_EVENT(rcu_future_grace_period,
 		__entry->gpevent = gpevent;
 	),
 
-	TP_printk("%s %lu %lu %lu %u %d %d %s",
-		  __entry->rcuname, __entry->gpnum, __entry->completed,
-		  __entry->c, __entry->level, __entry->grplo, __entry->grphi,
-		  __entry->gpevent)
+	TP_printk("%s %lu %lu %u %d %d %s",
+		  __entry->rcuname, __entry->gp_seq, __entry->c, __entry->level,
+		  __entry->grplo, __entry->grphi, __entry->gpevent)
 );
 
 /*
@@ -755,7 +751,7 @@ TRACE_EVENT(rcu_barrier,
 #else /* #ifdef CONFIG_RCU_TRACE */
 
 #define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0)
-#define trace_rcu_future_grace_period(rcuname, gpnum, completed, c, \
+#define trace_rcu_future_grace_period(rcuname, gp_seq, c, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
 #define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7ce85ad39af6..066dbaacec30 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1552,9 +1552,8 @@ void rcu_cpu_stall_reset(void)
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 			      unsigned long c, const char *s)
 {
-	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gpnum,
-				      rnp->completed, c, rnp->level,
-				      rnp->grplo, rnp->grphi, s);
+	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, c,
+				      rnp->level, rnp->grplo, rnp->grphi, s);
 }
 
 /*
@@ -2053,7 +2052,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(rsp->rda);
 	if (ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
-		trace_rcu_this_gp(rnp, rdp, rsp->completed - 1,
+		trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
 				  TPS("CleanupMore"));
 		needgp = true;
 	}
-- 
cgit v1.2.3


From 63d86a7e85f84b8ac3b2f394570965aedbb03787 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 13:08:46 -0700
Subject: rcu: Convert rcu_grace_period_init tracepoint to gp_seq

This commit makes the rcu_grace_period_init tracepoint use gp_seq instead
of ->gpnum.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 286047d22314..892016ad0647 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -142,14 +142,14 @@ TRACE_EVENT(rcu_future_grace_period,
  */
 TRACE_EVENT(rcu_grace_period_init,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, u8 level,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, u8 level,
 		 int grplo, int grphi, unsigned long qsmask),
 
-	TP_ARGS(rcuname, gpnum, level, grplo, grphi, qsmask),
+	TP_ARGS(rcuname, gp_seq, level, grplo, grphi, qsmask),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -158,7 +158,7 @@ TRACE_EVENT(rcu_grace_period_init,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
@@ -166,7 +166,7 @@ TRACE_EVENT(rcu_grace_period_init,
 	),
 
 	TP_printk("%s %lu %u %d %d %lx",
-		  __entry->rcuname, __entry->gpnum, __entry->level,
+		  __entry->rcuname, __entry->gp_seq, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->qsmask)
 );
 
@@ -754,7 +754,7 @@ TRACE_EVENT(rcu_barrier,
 #define trace_rcu_future_grace_period(rcuname, gp_seq, c, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
-#define trace_rcu_grace_period_init(rcuname, gpnum, level, grplo, grphi, \
+#define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \
 				    qsmask) do { } while (0)
 #define trace_rcu_exp_grace_period(rcuname, gqseq, gpevent) \
 	do { } while (0)
-- 
cgit v1.2.3


From 598ce09480efb6b48799df60c66bac70bea5ef54 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 13:35:20 -0700
Subject: rcu: Convert rcu_preempt_task tracepoint to ->gp_seq

This commit makes the rcu_preempt_task tracepoint use ->gp_seq instead
of ->gpnum.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 12 ++++++------
 kernel/rcu/tree_plugin.h   |  4 ++--
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 892016ad0647..38dbd97d65a3 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -298,24 +298,24 @@ TRACE_EVENT(rcu_nocb_wake,
  */
 TRACE_EVENT(rcu_preempt_task,
 
-	TP_PROTO(const char *rcuname, int pid, unsigned long gpnum),
+	TP_PROTO(const char *rcuname, int pid, unsigned long gp_seq),
 
-	TP_ARGS(rcuname, pid, gpnum),
+	TP_ARGS(rcuname, pid, gp_seq),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->pid = pid;
 	),
 
 	TP_printk("%s %lu %d",
-		  __entry->rcuname, __entry->gpnum, __entry->pid)
+		  __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
 /*
@@ -761,7 +761,7 @@ TRACE_EVENT(rcu_barrier,
 #define trace_rcu_exp_funnel_lock(rcuname, level, grplo, grphi, gpevent) \
 	do { } while (0)
 #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
-#define trace_rcu_preempt_task(rcuname, pid, gpnum) do { } while (0)
+#define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0)
 #define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
 #define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
 					 grplo, grphi, gp_tasks) do { } \
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index aca9d187c509..02ca3b4e6a8f 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -350,8 +350,8 @@ static void rcu_preempt_note_context_switch(bool preempt)
 		trace_rcu_preempt_task(rdp->rsp->name,
 				       t->pid,
 				       (rnp->qsmask & rdp->grpmask)
-				       ? rnp->gpnum
-				       : rnp->gpnum + 1);
+				       ? rnp->gp_seq
+				       : rcu_seq_snap(&rnp->gp_seq));
 		rcu_preempt_ctxt_queue(rnp, rdp);
 	} else if (t->rcu_read_lock_nesting < 0 &&
 		   t->rcu_read_unlock_special.s) {
-- 
cgit v1.2.3


From 865aa1e08d8aefdfd1f5d30ecfce1b8ef8cd520a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 13:35:20 -0700
Subject: rcu: Convert rcu_unlock_preempted_task tracepoint to ->gp_seq

This commit makes the rcu_unlock_preempted_task tracepoint use ->gp_seq
instead of ->gpnum.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 12 ++++++------
 kernel/rcu/tree_plugin.h   |  4 ++--
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 38dbd97d65a3..95b7491196aa 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -325,23 +325,23 @@ TRACE_EVENT(rcu_preempt_task,
  */
 TRACE_EVENT(rcu_unlock_preempted_task,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, int pid),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, int pid),
 
-	TP_ARGS(rcuname, gpnum, pid),
+	TP_ARGS(rcuname, gp_seq, pid),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, pid)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->pid = pid;
 	),
 
-	TP_printk("%s %lu %d", __entry->rcuname, __entry->gpnum, __entry->pid)
+	TP_printk("%s %lu %d", __entry->rcuname, __entry->gp_seq, __entry->pid)
 );
 
 /*
@@ -762,7 +762,7 @@ TRACE_EVENT(rcu_barrier,
 	do { } while (0)
 #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
 #define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0)
-#define trace_rcu_unlock_preempted_task(rcuname, gpnum, pid) do { } while (0)
+#define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0)
 #define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
 					 grplo, grphi, gp_tasks) do { } \
 	while (0)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 02ca3b4e6a8f..a10b0e26ce19 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -545,7 +545,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		list_del_init(&t->rcu_node_entry);
 		t->rcu_blocked_node = NULL;
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt"),
-						rnp->gpnum, t->pid);
+						rnp->gp_seq, t->pid);
 		if (&t->rcu_node_entry == rnp->gp_tasks)
 			rnp->gp_tasks = np;
 		if (&t->rcu_node_entry == rnp->exp_tasks)
@@ -708,7 +708,7 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 		t = container_of(rnp->gp_tasks, struct task_struct,
 				 rcu_node_entry);
 		trace_rcu_unlock_preempted_task(TPS("rcu_preempt-GPS"),
-						rnp->gpnum, t->pid);
+						rnp->gp_seq, t->pid);
 	}
 	WARN_ON_ONCE(rnp->qsmask);
 }
-- 
cgit v1.2.3


From db023296f0115d2fe01fdabad54678f2b806da23 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 13:35:20 -0700
Subject: rcu: Convert rcu_quiescent_state_report tracepoint to ->gp_seq

This commit makes the rcu_quiescent_state_report tracepoint use ->gp_seq
instead of ->gpnum.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 12 ++++++------
 kernel/rcu/tree.c          |  2 +-
 kernel/rcu/tree_plugin.h   |  2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 95b7491196aa..ac4d9d4a1ebf 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -354,15 +354,15 @@ TRACE_EVENT(rcu_unlock_preempted_task,
  */
 TRACE_EVENT(rcu_quiescent_state_report,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum,
+	TP_PROTO(const char *rcuname, unsigned long gp_seq,
 		 unsigned long mask, unsigned long qsmask,
 		 u8 level, int grplo, int grphi, int gp_tasks),
 
-	TP_ARGS(rcuname, gpnum, mask, qsmask, level, grplo, grphi, gp_tasks),
+	TP_ARGS(rcuname, gp_seq, mask, qsmask, level, grplo, grphi, gp_tasks),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(unsigned long, mask)
 		__field(unsigned long, qsmask)
 		__field(u8, level)
@@ -373,7 +373,7 @@ TRACE_EVENT(rcu_quiescent_state_report,
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->mask = mask;
 		__entry->qsmask = qsmask;
 		__entry->level = level;
@@ -383,7 +383,7 @@ TRACE_EVENT(rcu_quiescent_state_report,
 	),
 
 	TP_printk("%s %lu %lx>%lx %u %d %d %u",
-		  __entry->rcuname, __entry->gpnum,
+		  __entry->rcuname, __entry->gp_seq,
 		  __entry->mask, __entry->qsmask, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->gp_tasks)
 );
@@ -763,7 +763,7 @@ TRACE_EVENT(rcu_barrier,
 #define trace_rcu_nocb_wake(rcuname, cpu, reason) do { } while (0)
 #define trace_rcu_preempt_task(rcuname, pid, gp_seq) do { } while (0)
 #define trace_rcu_unlock_preempted_task(rcuname, gp_seq, pid) do { } while (0)
-#define trace_rcu_quiescent_state_report(rcuname, gpnum, mask, qsmask, level, \
+#define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \
 					 grplo, grphi, gp_tasks) do { } \
 	while (0)
 #define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 066dbaacec30..7c6c11d5479c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2229,7 +2229,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		WARN_ON_ONCE(!rcu_is_leaf_node(rnp) &&
 			     rcu_preempt_blocked_readers_cgp(rnp));
 		rnp->qsmask &= ~mask;
-		trace_rcu_quiescent_state_report(rsp->name, rnp->gpnum,
+		trace_rcu_quiescent_state_report(rsp->name, rnp->gp_seq,
 						 mask, rnp->qsmask, rnp->level,
 						 rnp->grplo, rnp->grphi,
 						 !!rnp->gp_tasks);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index a10b0e26ce19..c8a2c7760121 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -566,7 +566,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		empty_exp_now = sync_rcu_preempt_exp_done(rnp);
 		if (!empty_norm && !rcu_preempt_blocked_readers_cgp(rnp)) {
 			trace_rcu_quiescent_state_report(TPS("preempt_rcu"),
-							 rnp->gpnum,
+							 rnp->gp_seq,
 							 0, rnp->qsmask,
 							 rnp->level,
 							 rnp->grplo,
-- 
cgit v1.2.3


From fee5997c17562e95fb1fecc142efb2da0934baa4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 13:35:20 -0700
Subject: rcu: Convert rcu_fqs tracepoint to ->gp_seq

This commit makes the rcu_fqs tracepoint use ->gp_seq instead of ->gpnum.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 12 ++++++------
 kernel/rcu/tree.c          |  8 ++++----
 2 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index ac4d9d4a1ebf..7d3650cc9d30 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -398,26 +398,26 @@ TRACE_EVENT(rcu_quiescent_state_report,
  */
 TRACE_EVENT(rcu_fqs,
 
-	TP_PROTO(const char *rcuname, unsigned long gpnum, int cpu, const char *qsevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq, int cpu, const char *qsevent),
 
-	TP_ARGS(rcuname, gpnum, cpu, qsevent),
+	TP_ARGS(rcuname, gp_seq, cpu, qsevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
-		__field(unsigned long, gpnum)
+		__field(unsigned long, gp_seq)
 		__field(int, cpu)
 		__field(const char *, qsevent)
 	),
 
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
-		__entry->gpnum = gpnum;
+		__entry->gp_seq = gp_seq;
 		__entry->cpu = cpu;
 		__entry->qsevent = qsevent;
 	),
 
 	TP_printk("%s %lu %d %s",
-		  __entry->rcuname, __entry->gpnum,
+		  __entry->rcuname, __entry->gp_seq,
 		  __entry->cpu, __entry->qsevent)
 );
 
@@ -766,7 +766,7 @@ TRACE_EVENT(rcu_barrier,
 #define trace_rcu_quiescent_state_report(rcuname, gp_seq, mask, qsmask, level, \
 					 grplo, grphi, gp_tasks) do { } \
 	while (0)
-#define trace_rcu_fqs(rcuname, gpnum, cpu, qsevent) do { } while (0)
+#define trace_rcu_fqs(rcuname, gp_seq, cpu, qsevent) do { } while (0)
 #define trace_rcu_dyntick(polarity, oldnesting, newnesting, dyntick) do { } while (0)
 #define trace_rcu_callback(rcuname, rhp, qlen_lazy, qlen) do { } while (0)
 #define trace_rcu_kfree_callback(rcuname, rhp, offset, qlen_lazy, qlen) \
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7c6c11d5479c..42e89d4f1e33 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1111,7 +1111,7 @@ static int dyntick_save_progress_counter(struct rcu_data *rdp)
 {
 	rdp->dynticks_snap = rcu_dynticks_snap(rdp->dynticks);
 	if (rcu_dynticks_in_eqs(rdp->dynticks_snap)) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
 		rcu_gpnum_ovf(rdp->mynode, rdp);
 		return 1;
 	}
@@ -1161,7 +1161,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	 * of the current RCU grace period.
 	 */
 	if (rcu_dynticks_in_eqs_since(rdp->dynticks, rdp->dynticks_snap)) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("dti"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("dti"));
 		rdp->dynticks_fqs++;
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
@@ -1178,7 +1178,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 	if (time_after(jiffies, rdp->rsp->gp_start + jtsq) &&
 	    READ_ONCE(rdp->rcu_qs_ctr_snap) != per_cpu(rcu_dynticks.rcu_qs_ctr, rdp->cpu) &&
 	    rcu_seq_current(&rdp->gp_seq) == rnp->gp_seq && !rdp->gpwrap) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("rqc"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("rqc"));
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
 	} else if (time_after(jiffies, rdp->rsp->gp_start + jtsq)) {
@@ -1188,7 +1188,7 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 
 	/* Check for the CPU being offline. */
 	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gpnum, rdp->cpu, TPS("ofl"));
+		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("ofl"));
 		rdp->offline_fqs++;
 		rcu_gpnum_ovf(rnp, rdp);
 		return 1;
-- 
cgit v1.2.3


From ff3bb6f4d06247508489345ee90a8a9b6f3ffd3b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 14:34:08 -0700
Subject: rcu: Remove ->gpnum and ->completed

Now that everything has been converted to use ->gp_seq instead of
->gpnum and ->completed, this commit removes ->gpnum and ->completed.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 45 +++++++++++----------------------------------
 kernel/rcu/tree.h        | 14 +-------------
 kernel/rcu/tree_plugin.h |  2 +-
 3 files changed, 13 insertions(+), 48 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 42e89d4f1e33..0aeddc908181 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -95,8 +95,6 @@ struct rcu_state sname##_state = { \
 	.rda = &sname##_data, \
 	.call = cr, \
 	.gp_state = RCU_GP_IDLE, \
-	.gpnum = 0UL - 300UL, \
-	.completed = 0UL - 300UL, \
 	.gp_seq = (0UL - 300UL) << RCU_SEQ_CTR_SHIFT, \
 	.barrier_mutex = __MUTEX_INITIALIZER(sname##_state.barrier_mutex), \
 	.name = RCU_STATE_NAME(sname), \
@@ -1349,8 +1347,6 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 	long totqlen = 0;
 
-	WARN_ON_ONCE(gp_seq & 0x2); /* Remove when ->gpnum removed. */
-
 	/* Kick and suppress, if so configured. */
 	rcu_stall_kick_kthreads(rsp);
 	if (rcu_cpu_stall_suppress)
@@ -1582,8 +1578,6 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * not be released.
 	 */
 	raw_lockdep_assert_held_rcu_node(rnp);
-	WARN_ON_ONCE(c & 0x2); /* Catch any lingering use of ->gpnum. */
-	WARN_ON_ONCE(((rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT) != rcu_seq_ctr(rnp->gp_seq)); /* Catch any ->completed/->gp_seq mismatches. */
 	trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
 	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
 		if (rnp_root != rnp)
@@ -1757,8 +1751,6 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 	if (rcu_seq_completed_gp(rdp->gp_seq, rnp->gp_seq) ||
 	    unlikely(READ_ONCE(rdp->gpwrap))) {
 		ret = rcu_advance_cbs(rsp, rnp, rdp); /* Advance callbacks. */
-		/* Remember that we saw this grace-period completion. */
-		rdp->completed = rnp->completed;
 		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpuend"));
 	} else {
 		ret = rcu_accelerate_cbs(rsp, rnp, rdp); /* Recent callbacks. */
@@ -1772,7 +1764,6 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		 * set up to detect a quiescent state, otherwise don't
 		 * go looking for one.
 		 */
-		rdp->gpnum = rnp->gpnum;
 		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpustart"));
 		need_gp = !!(rnp->qsmask & rdp->grpmask);
 		rdp->cpu_no_qs.b.norm = need_gp;
@@ -1843,13 +1834,8 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 
 	/* Advance to a new grace period and initialize state. */
 	record_gp_stall_check_time(rsp);
-	/* Record GP times before starting GP, hence smp_store_release(). */
-	WARN_ON_ONCE(rsp->gpnum << RCU_SEQ_CTR_SHIFT != rsp->gp_seq);
-	smp_store_release(&rsp->gpnum, rsp->gpnum + 1);
-	smp_mb(); /* Pairs with barriers in stall-warning code. */
+	/* Record GP times before starting GP, hence rcu_seq_start(). */
 	rcu_seq_start(&rsp->gp_seq);
-	if (WARN_ON_ONCE(((rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT) != rcu_seq_ctr(rnp->gp_seq))) /* Catch any ->completed/->gp_seq mismatches. */
-		pr_info("%s ->completed: %#lx (%#lx) ->gp_seq %#lx (%#lx)\n", __func__, rnp->completed, (rnp->completed << RCU_SEQ_CTR_SHIFT) >> RCU_SEQ_CTR_SHIFT, rnp->gp_seq, rcu_seq_ctr(rnp->gp_seq));
 	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("start"));
 	raw_spin_unlock_irq_rcu_node(rnp);
 
@@ -1920,9 +1906,6 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
-		WRITE_ONCE(rnp->gpnum, rsp->gpnum);
-		if (WARN_ON_ONCE(rnp->completed != rsp->completed))
-			WRITE_ONCE(rnp->completed, rsp->completed);
 		WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
 		if (rnp == rdp->mynode)
 			(void)__note_gp_changes(rsp, rnp, rdp);
@@ -2012,13 +1995,13 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	raw_spin_unlock_irq_rcu_node(rnp);
 
 	/*
-	 * Propagate new ->completed value to rcu_node structures so
-	 * that other CPUs don't have to wait until the start of the next
-	 * grace period to process their callbacks.  This also avoids
-	 * some nasty RCU grace-period initialization races by forcing
-	 * the end of the current grace period to be completely recorded in
-	 * all of the rcu_node structures before the beginning of the next
-	 * grace period is recorded in any of the rcu_node structures.
+	 * Propagate new ->gp_seq value to rcu_node structures so that
+	 * other CPUs don't have to wait until the start of the next grace
+	 * period to process their callbacks.  This also avoids some nasty
+	 * RCU grace-period initialization races by forcing the end of
+	 * the current grace period to be completely recorded in all of
+	 * the rcu_node structures before the beginning of the next grace
+	 * period is recorded in any of the rcu_node structures.
 	 */
 	new_gp_seq = rsp->gp_seq;
 	rcu_seq_end(&new_gp_seq);
@@ -2027,7 +2010,6 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
 			dump_blkd_tasks(rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
-		WRITE_ONCE(rnp->completed, rsp->gpnum);
 		WRITE_ONCE(rnp->gp_seq, new_gp_seq);
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
@@ -2045,7 +2027,6 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	raw_spin_lock_irq_rcu_node(rnp); /* GP before rsp->gp_seq update. */
 
 	/* Declare grace period done. */
-	WRITE_ONCE(rsp->completed, rsp->gpnum);
 	rcu_seq_end(&rsp->gp_seq);
 	trace_rcu_grace_period(rsp->name, rsp->gp_seq, TPS("end"));
 	rsp->gp_state = RCU_GP_IDLE;
@@ -3496,9 +3477,9 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 
 /*
  * Initialize a CPU's per-CPU RCU data.  Note that only one online or
- * offline event can be happening at a given time.  Note also that we
- * can accept some slop in the rsp->completed access due to the fact
- * that this CPU cannot possibly have any RCU callbacks in flight yet.
+ * offline event can be happening at a given time.  Note also that we can
+ * accept some slop in the rsp->gp_seq access due to the fact that this
+ * CPU cannot possibly have any RCU callbacks in flight yet.
  */
 static void
 rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
@@ -3527,8 +3508,6 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rnp = rdp->mynode;
 	raw_spin_lock_rcu_node(rnp);		/* irqs already disabled. */
 	rdp->beenonline = true;	 /* We have now been online. */
-	rdp->gpnum = rnp->completed; /* Make CPU later note any new GP. */
-	rdp->completed = rnp->completed;
 	rdp->gp_seq = rnp->gp_seq;
 	rdp->gp_seq_needed = rnp->gp_seq;
 	rdp->cpu_no_qs.b.norm = true;
@@ -3908,8 +3887,6 @@ static void __init rcu_init_one(struct rcu_state *rsp)
 			raw_spin_lock_init(&rnp->fqslock);
 			lockdep_set_class_and_name(&rnp->fqslock,
 						   &rcu_fqs_class[i], fqs[i]);
-			rnp->gpnum = rsp->gpnum;
-			rnp->completed = rsp->completed;
 			rnp->gp_seq = rsp->gp_seq;
 			rnp->gp_seq_needed = rsp->gp_seq;
 			rnp->completedqs = rsp->gp_seq;
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 9329c1ff695f..3def94fc9c74 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -81,12 +81,6 @@ struct rcu_node {
 	raw_spinlock_t __private lock;	/* Root rcu_node's lock protects */
 					/*  some rcu_state fields as well as */
 					/*  following. */
-	unsigned long gpnum;	/* Current grace period for this node. */
-				/*  This will either be equal to or one */
-				/*  behind the root rcu_node's gpnum. */
-	unsigned long completed; /* Last GP completed for this node. */
-				/*  This will either be equal to or one */
-				/*  behind the root rcu_node's gpnum. */
 	unsigned long gp_seq;	/* Track rsp->rcu_gp_seq. */
 	unsigned long gp_seq_needed; /* Track rsp->rcu_gp_seq_needed. */
 	unsigned long completedqs; /* All QSes done for this node. */
@@ -192,10 +186,6 @@ union rcu_noqs {
 /* Per-CPU data for read-copy update. */
 struct rcu_data {
 	/* 1) quiescent-state and grace-period handling : */
-	unsigned long	completed;	/* Track rsp->completed gp number */
-					/*  in order to detect GP end. */
-	unsigned long	gpnum;		/* Highest gp number that this CPU */
-					/*  is aware of having started. */
 	unsigned long	gp_seq;		/* Track rsp->rcu_gp_seq counter. */
 	unsigned long	gp_seq_needed;	/* Track rsp->rcu_gp_seq_needed ctr. */
 	unsigned long	rcu_qs_ctr_snap;/* Snapshot of rcu_qs_ctr to check */
@@ -203,7 +193,7 @@ struct rcu_data {
 	union rcu_noqs	cpu_no_qs;	/* No QSes yet for this CPU. */
 	bool		core_needs_qs;	/* Core waits for quiesc state. */
 	bool		beenonline;	/* CPU online at least once. */
-	bool		gpwrap;		/* Possible gpnum/completed wrap. */
+	bool		gpwrap;		/* Possible ->gp_seq wrap. */
 	struct rcu_node *mynode;	/* This CPU's leaf of hierarchy */
 	unsigned long grpmask;		/* Mask to apply to leaf qsmask. */
 	unsigned long	ticks_this_gp;	/* The number of scheduling-clock */
@@ -328,8 +318,6 @@ struct rcu_state {
 
 	u8	boost ____cacheline_internodealigned_in_smp;
 						/* Subject to priority boost. */
-	unsigned long gpnum;			/* Current gp number. */
-	unsigned long completed;		/* # of last completed gp. */
 	unsigned long gp_seq;			/* Grace-period sequence #. */
 	struct task_struct *gp_kthread;		/* Task for grace periods. */
 	struct swait_queue_head gp_wq;		/* Where GP task waits. */
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c8a2c7760121..3a6e04103de1 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -690,7 +690,7 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * Check that the list of blocked tasks for the newly completed grace
  * period is in fact empty.  It is a serious bug to complete a grace
  * period that still has RCU readers blocked!  This function must be
- * invoked -before- updating this rnp's ->gpnum, and the rnp's ->lock
+ * invoked -before- updating this rnp's ->gp_seq, and the rnp's ->lock
  * must be held by the caller.
  *
  * Also, if there are blocked tasks on the list, they automatically
-- 
cgit v1.2.3


From e44e73ca47b47510dac491329d453d82aea1d8d8 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 16:29:47 -0700
Subject: rcu: Make simple callback acceleration refer to rdp->gp_seq_needed

Now that the rcu_data structure contains ->gp_seq_needed, create an
rcu_accelerate_cbs_unlocked() helper function that locklessly checks to
see if new callbacks' required grace period has already been requested.
If so, update the callback list locally and again locklessly.  (Though
interrupts must be and are disabled to avoid racing with conflicting
updates in interrupt handlers.)

Otherwise, call rcu_accelerate_cbs() as before.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 51 ++++++++++++++++++++++++++++++++-------------------
 1 file changed, 32 insertions(+), 19 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 0aeddc908181..5643c135fb06 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1701,6 +1701,34 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	return ret;
 }
 
+/*
+ * Similar to rcu_accelerate_cbs(), but does not require that the leaf
+ * rcu_node structure's ->lock be held.  It consults the cached value
+ * of ->gp_seq_needed in the rcu_data structure, and if that indicates
+ * that a new grace-period request be made, invokes rcu_accelerate_cbs()
+ * while holding the leaf rcu_node structure's ->lock.
+ */
+static void rcu_accelerate_cbs_unlocked(struct rcu_state *rsp,
+					struct rcu_node *rnp,
+					struct rcu_data *rdp)
+{
+	unsigned long c;
+	bool needwake;
+
+	lockdep_assert_irqs_disabled();
+	c = rcu_seq_snap(&rsp->gp_seq);
+	if (!rdp->gpwrap && ULONG_CMP_GE(rdp->gp_seq_needed, c)) {
+		/* Old request still live, so mark recent callbacks. */
+		(void)rcu_segcblist_accelerate(&rdp->cblist, c);
+		return;
+	}
+	raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
+	needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
+	raw_spin_unlock_rcu_node(rnp); /* irqs remain disabled. */
+	if (needwake)
+		rcu_gp_kthread_wake(rsp);
+}
+
 /*
  * Move any callbacks whose grace period has completed to the
  * RCU_DONE_TAIL sublist, then compact the remaining sublists and
@@ -2739,7 +2767,6 @@ static void
 __rcu_process_callbacks(struct rcu_state *rsp)
 {
 	unsigned long flags;
-	bool needwake;
 	struct rcu_data *rdp = raw_cpu_ptr(rsp->rda);
 	struct rcu_node *rnp = rdp->mynode;
 
@@ -2752,15 +2779,9 @@ __rcu_process_callbacks(struct rcu_state *rsp)
 	if (!rcu_gp_in_progress(rsp) &&
 	    rcu_segcblist_is_enabled(&rdp->cblist)) {
 		local_irq_save(flags);
-		if (rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL)) {
-			local_irq_restore(flags);
-		} else {
-			raw_spin_lock_rcu_node(rnp); /* irqs disabled. */
-			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
-			if (needwake)
-				rcu_gp_kthread_wake(rsp);
-		}
+		if (!rcu_segcblist_restempty(&rdp->cblist, RCU_NEXT_READY_TAIL))
+			rcu_accelerate_cbs_unlocked(rsp, rnp, rdp);
+		local_irq_restore(flags);
 	}
 
 	rcu_check_gp_start_stall(rsp, rnp, rdp);
@@ -2818,8 +2839,6 @@ static void invoke_rcu_core(void)
 static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			    struct rcu_head *head, unsigned long flags)
 {
-	bool needwake;
-
 	/*
 	 * If called from an extended quiescent state, invoke the RCU
 	 * core in order to force a re-evaluation of RCU's idleness.
@@ -2846,13 +2865,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 
 		/* Start a new grace period if one not already started. */
 		if (!rcu_gp_in_progress(rsp)) {
-			struct rcu_node *rnp = rdp->mynode;
-
-			raw_spin_lock_rcu_node(rnp);
-			needwake = rcu_accelerate_cbs(rsp, rnp, rdp);
-			raw_spin_unlock_rcu_node(rnp);
-			if (needwake)
-				rcu_gp_kthread_wake(rsp);
+			rcu_accelerate_cbs_unlocked(rsp, rdp->mynode, rdp);
 		} else {
 			/* Give the grace period a kick. */
 			rdp->blimit = LONG_MAX;
-- 
cgit v1.2.3


From b1e1f21f5b8f8a25e53b9f7c59bca9a1d749547e Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 15:51:32 -0700
Subject: doc: Update data-structure documentation for ->gp_seq

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 .../Design/Data-Structures/Data-Structures.html    | 118 +++++++++++----------
 1 file changed, 63 insertions(+), 55 deletions(-)

diff --git a/Documentation/RCU/Design/Data-Structures/Data-Structures.html b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
index 6c06e10bd04b..f5120a00f511 100644
--- a/Documentation/RCU/Design/Data-Structures/Data-Structures.html
+++ b/Documentation/RCU/Design/Data-Structures/Data-Structures.html
@@ -380,31 +380,26 @@ and therefore need no protection.
 as follows:
 
 <pre>
-  1   unsigned long gpnum;
-  2   unsigned long completed;
+  1   unsigned long gp_seq;
 </pre>
 
 <p>RCU grace periods are numbered, and
-the <tt>-&gt;gpnum</tt> field contains the number of the grace
-period that started most recently.
-The <tt>-&gt;completed</tt> field contains the number of the
-grace period that completed most recently.
-If the two fields are equal, the RCU grace period that most recently
-started has already completed, and therefore the corresponding
-flavor of RCU is idle.
-If <tt>-&gt;gpnum</tt> is one greater than <tt>-&gt;completed</tt>,
-then <tt>-&gt;gpnum</tt> gives the number of the current RCU
-grace period, which has not yet completed.
-Any other combination of values indicates that something is broken.
-These two fields are protected by the root <tt>rcu_node</tt>'s
+the <tt>-&gt;gp_seq</tt> field contains the current grace-period
+sequence number.
+The bottom two bits are the state of the current grace period,
+which can be zero for not yet started or one for in progress.
+In other words, if the bottom two bits of <tt>-&gt;gp_seq</tt> are
+zero, the corresponding flavor of RCU is idle.
+Any other value in the bottom two bits indicates that something is broken.
+This field is protected by the root <tt>rcu_node</tt> structure's
 <tt>-&gt;lock</tt> field.
 
-</p><p>There are <tt>-&gt;gpnum</tt> and <tt>-&gt;completed</tt> fields
+</p><p>There are <tt>-&gt;gp_seq</tt> fields
 in the <tt>rcu_node</tt> and <tt>rcu_data</tt> structures
 as well.
 The fields in the <tt>rcu_state</tt> structure represent the
-most current values, and those of the other structures are compared
-in order to detect the start of a new grace period in a distributed
+most current value, and those of the other structures are compared
+in order to detect the beginnings and ends of grace periods in a distributed
 fashion.
 The values flow from <tt>rcu_state</tt> to <tt>rcu_node</tt>
 (down the tree from the root to the leaves) to <tt>rcu_data</tt>.
@@ -512,27 +507,47 @@ than to be heisenbugged out of existence.
 as follows:
 
 <pre>
-  1   unsigned long gpnum;
-  2   unsigned long completed;
+  1   unsigned long gp_seq;
+  2   unsigned long gp_seq_needed;
 </pre>
 
-<p>These fields are the counterparts of the fields of the same name in
-the <tt>rcu_state</tt> structure.
-They each may lag up to one behind their <tt>rcu_state</tt>
-counterparts.
-If a given <tt>rcu_node</tt> structure's <tt>-&gt;gpnum</tt> and
-<tt>-&gt;complete</tt> fields are equal, then this <tt>rcu_node</tt>
+<p>The <tt>rcu_node</tt> structures' <tt>-&gt;gp_seq</tt> fields are
+the counterparts of the field of the same name in the <tt>rcu_state</tt>
+structure.
+They each may lag up to one step behind their <tt>rcu_state</tt>
+counterpart.
+If the bottom two bits of a given <tt>rcu_node</tt> structure's
+<tt>-&gt;gp_seq</tt> field is zero, then this <tt>rcu_node</tt>
 structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> structure,
-the <tt>-&gt;gpnum</tt> field will be one greater than the
-<tt>-&gt;complete</tt> fields, with <tt>-&gt;gpnum</tt>
-indicating which grace period this <tt>rcu_node</tt> believes
-is still being waited for.
+</p><p>The <tt>&gt;gp_seq</tt> field of each <tt>rcu_node</tt>
+structure is updated at the beginning and the end
+of each grace period.
+
+<p>The <tt>-&gt;gp_seq_needed</tt> fields record the
+furthest-in-the-future grace period request seen by the corresponding
+<tt>rcu_node</tt> structure.  The request is considered fulfilled when
+the value of the <tt>-&gt;gp_seq</tt> field equals or exceeds that of
+the <tt>-&gt;gp_seq_needed</tt> field.
 
-</p><p>The <tt>&gt;gpnum</tt> field of each <tt>rcu_node</tt>
-structure is updated at the beginning
-of each grace period, and the <tt>-&gt;completed</tt> fields are
-updated at the end of each grace period.
+<table>
+<tr><th>&nbsp;</th></tr>
+<tr><th align="left">Quick Quiz:</th></tr>
+<tr><td>
+	Suppose that this <tt>rcu_node</tt> structure doesn't see
+	a request for a very long time.
+	Won't wrapping of the <tt>-&gt;gp_seq</tt> field cause
+	problems?
+</td></tr>
+<tr><th align="left">Answer:</th></tr>
+<tr><td bgcolor="#ffffff"><font color="ffffff">
+	No, because if the <tt>-&gt;gp_seq_needed</tt> field lags behind the
+	<tt>-&gt;gp_seq</tt> field, the <tt>-&gt;gp_seq_needed</tt> field
+	will be updated at the end of the grace period.
+	Modulo-arithmetic comparisons therefore will always get the
+	correct answer, even with wrapping.
+</font></td></tr>
+<tr><td>&nbsp;</td></tr>
+</table>
 
 <h5>Quiescent-State Tracking</h5>
 
@@ -626,9 +641,8 @@ normal and expedited grace periods, respectively.
 	</ol>
 
 	<p><font color="ffffff">So the locking is absolutely required in
-	order to coordinate
-	clearing of the bits with the grace-period numbers in
-	<tt>-&gt;gpnum</tt> and <tt>-&gt;completed</tt>.
+	order to coordinate clearing of the bits with updating of the
+	grace-period sequence number in <tt>-&gt;gp_seq</tt>.
 </font></td></tr>
 <tr><td>&nbsp;</td></tr>
 </table>
@@ -1038,15 +1052,15 @@ out any <tt>rcu_data</tt> structure for which this flag is not set.
 as follows:
 
 <pre>
-  1   unsigned long completed;
-  2   unsigned long gpnum;
+  1   unsigned long gp_seq;
+  2   unsigned long gp_seq_needed;
   3   bool cpu_no_qs;
   4   bool core_needs_qs;
   5   bool gpwrap;
   6   unsigned long rcu_qs_ctr_snap;
 </pre>
 
-<p>The <tt>completed</tt> and <tt>gpnum</tt>
+<p>The <tt>-&gt;gp_seq</tt> and <tt>-&gt;gp_seq_needed</tt>
 fields are the counterparts of the fields of the same name
 in the <tt>rcu_state</tt> and <tt>rcu_node</tt> structures.
 They may each lag up to one behind their <tt>rcu_node</tt>
@@ -1054,15 +1068,9 @@ counterparts, but in <tt>CONFIG_NO_HZ_IDLE</tt> and
 <tt>CONFIG_NO_HZ_FULL</tt> kernels can lag
 arbitrarily far behind for CPUs in dyntick-idle mode (but these counters
 will catch up upon exit from dyntick-idle mode).
-If a given <tt>rcu_data</tt> structure's <tt>-&gt;gpnum</tt> and
-<tt>-&gt;complete</tt> fields are equal, then this <tt>rcu_data</tt>
+If the lower two bits of a given <tt>rcu_data</tt> structure's
+<tt>-&gt;gp_seq</tt> are zero, then this <tt>rcu_data</tt>
 structure believes that RCU is idle.
-Otherwise, as with the <tt>rcu_state</tt> and <tt>rcu_node</tt>
-structure,
-the <tt>-&gt;gpnum</tt> field will be one greater than the
-<tt>-&gt;complete</tt> fields, with <tt>-&gt;gpnum</tt>
-indicating which grace period this <tt>rcu_data</tt> believes
-is still being waited for.
 
 <table>
 <tr><th>&nbsp;</th></tr>
@@ -1070,13 +1078,13 @@ is still being waited for.
 <tr><td>
 	All this replication of the grace period numbers can only cause
 	massive confusion.
-	Why not just keep a global pair of counters and be done with it???
+	Why not just keep a global sequence number and be done with it???
 </td></tr>
 <tr><th align="left">Answer:</th></tr>
 <tr><td bgcolor="#ffffff"><font color="ffffff">
-	Because if there was only a single global pair of grace-period
+	Because if there was only a single global sequence
 	numbers, there would need to be a single global lock to allow
-	safely accessing and updating them.
+	safely accessing and updating it.
 	And if we are not going to have a single global lock, we need
 	to carefully manage the numbers on a per-node basis.
 	Recall from the answer to a previous Quick Quiz that the consequences
@@ -1091,8 +1099,8 @@ CPU has not yet passed through a quiescent state,
 while the <tt>-&gt;core_needs_qs</tt> flag indicates that the
 RCU core needs a quiescent state from the corresponding CPU.
 The <tt>-&gt;gpwrap</tt> field indicates that the corresponding
-CPU has remained idle for so long that the <tt>completed</tt>
-and <tt>gpnum</tt> counters are in danger of overflow, which
+CPU has remained idle for so long that the
+<tt>gp_seq</tt> counter is in danger of overflow, which
 will cause the CPU to disregard the values of its counters on
 its next exit from idle.
 Finally, the <tt>rcu_qs_ctr_snap</tt> field is used to detect
@@ -1130,10 +1138,10 @@ The CPU advances the callbacks in its <tt>rcu_data</tt> structure
 whenever it notices that another RCU grace period has completed.
 The CPU detects the completion of an RCU grace period by noticing
 that the value of its <tt>rcu_data</tt> structure's
-<tt>-&gt;completed</tt> field differs from that of its leaf
+<tt>-&gt;gp_seq</tt> field differs from that of its leaf
 <tt>rcu_node</tt> structure.
 Recall that each <tt>rcu_node</tt> structure's
-<tt>-&gt;completed</tt> field is updated at the end of each
+<tt>-&gt;gp_seq</tt> field is updated at the beginnings and ends of each
 grace period.
 
 <p>
-- 
cgit v1.2.3


From 869cc745bfbd1d8fda8b1dae1a8882b85393cdfa Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 16:26:46 -0700
Subject: doc: Update memory-ordering documentation for ->gp-seq

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 .../Memory-Ordering/Tree-RCU-Memory-Ordering.html  |  22 +-
 .../Design/Memory-Ordering/TreeRCU-gp-cleanup.svg  | 123 ++++++-----
 .../Design/Memory-Ordering/TreeRCU-gp-init-1.svg   |  16 +-
 .../Design/Memory-Ordering/TreeRCU-gp-init-3.svg   |  56 ++---
 .../RCU/Design/Memory-Ordering/TreeRCU-gp.svg      | 237 +++++++++++----------
 .../RCU/Design/Memory-Ordering/TreeRCU-qs.svg      |  12 +-
 6 files changed, 243 insertions(+), 223 deletions(-)

diff --git a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
index 8651b0b4fd79..a346ce0116eb 100644
--- a/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
+++ b/Documentation/RCU/Design/Memory-Ordering/Tree-RCU-Memory-Ordering.html
@@ -357,7 +357,7 @@ parts, starting in this section with the various phases of
 grace-period initialization.
 
 <p>The first ordering-related grace-period initialization action is to
-increment the <tt>rcu_state</tt> structure's <tt>-&gt;gpnum</tt>
+advance the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt>
 grace-period-number counter, as shown below:
 
 </p><p><img src="TreeRCU-gp-init-1.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
@@ -388,7 +388,7 @@ its last CPU and if the next <tt>rcu_node</tt> structure has no online CPUs).
 
 <p>The final <tt>rcu_gp_init()</tt> pass through the <tt>rcu_node</tt>
 tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
-<tt>-&gt;gpnum</tt> field to the newly incremented value from the
+<tt>-&gt;gp_seq</tt> field to the newly advanced value from the
 <tt>rcu_state</tt> structure, as shown in the following diagram.
 
 </p><p><img src="TreeRCU-gp-init-3.svg" alt="TreeRCU-gp-init-1.svg" width="75%">
@@ -398,9 +398,9 @@ tree traverses breadth-first, setting each <tt>rcu_node</tt> structure's
 to notice that a new grace period has started, as described in the next
 section.
 But because the grace-period kthread started the grace period at the
-root (with the increment of the <tt>rcu_state</tt> structure's
-<tt>-&gt;gpnum</tt> field) before setting each leaf <tt>rcu_node</tt>
-structure's <tt>-&gt;gpnum</tt> field, each CPU's observation of
+root (with the advancing of the <tt>rcu_state</tt> structure's
+<tt>-&gt;gp_seq</tt> field) before setting each leaf <tt>rcu_node</tt>
+structure's <tt>-&gt;gp_seq</tt> field, each CPU's observation of
 the start of the grace period will happen after the actual start
 of the grace period.
 
@@ -466,7 +466,7 @@ section that the grace period must wait on.
 <tr><td>
 	But a RCU read-side critical section might have started
 	after the beginning of the grace period
-	(the <tt>-&gt;gpnum++</tt> from earlier), so why should
+	(the advancing of <tt>-&gt;gp_seq</tt> from earlier), so why should
 	the grace period wait on such a critical section?
 </td></tr>
 <tr><th align="left">Answer:</th></tr>
@@ -609,10 +609,8 @@ states outstanding from other CPUs.
 <h4><a name="Grace-Period Cleanup">Grace-Period Cleanup</a></h4>
 
 <p>Grace-period cleanup first scans the <tt>rcu_node</tt> tree
-breadth-first setting all the <tt>-&gt;completed</tt> fields equal
-to the number of the newly completed grace period, then it sets
-the <tt>rcu_state</tt> structure's <tt>-&gt;completed</tt> field,
-again to the number of the newly completed grace period.
+breadth-first advancing all the <tt>-&gt;gp_seq</tt> fields, then it
+advances the <tt>rcu_state</tt> structure's <tt>-&gt;gp_seq</tt> field.
 The ordering effects are shown below:
 
 </p><p><img src="TreeRCU-gp-cleanup.svg" alt="TreeRCU-gp-cleanup.svg" width="75%">
@@ -634,7 +632,7 @@ grace-period cleanup is complete, the next grace period can begin.
 	CPU has reported its quiescent state, but it may be some
 	milliseconds before RCU becomes aware of this.
 	The latest reasonable candidate is once the <tt>rcu_state</tt>
-	structure's <tt>-&gt;completed</tt> field has been updated,
+	structure's <tt>-&gt;gp_seq</tt> field has been updated,
 	but it is quite possible that some CPUs have already completed
 	phase two of their updates by that time.
 	In short, if you are going to work with RCU, you need to
@@ -647,7 +645,7 @@ grace-period cleanup is complete, the next grace period can begin.
 <h4><a name="Callback Invocation">Callback Invocation</a></h4>
 
 <p>Once a given CPU's leaf <tt>rcu_node</tt> structure's
-<tt>-&gt;completed</tt> field has been updated, that CPU can begin
+<tt>-&gt;gp_seq</tt> field has been updated, that CPU can begin
 invoking its RCU callbacks that were waiting for this grace period
 to end.
 These callbacks are identified by <tt>rcu_advance_cbs()</tt>,
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
index 754f426b297a..bf84fbab27ee 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-cleanup.svg
@@ -384,11 +384,11 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="617.89017"
-     inkscape:cy="542.52419"
-     inkscape:window-x="86"
-     inkscape:window-y="28"
+     inkscape:zoom="0.78716603"
+     inkscape:cx="513.06403"
+     inkscape:cy="623.1214"
+     inkscape:window-x="102"
+     inkscape:window-y="38"
      inkscape:window-maximized="0"
      inkscape:current-layer="g3188-3"
      fit-margin-top="5"
@@ -417,13 +417,15 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3199.1516"
+       x="3145.9592"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3143">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
@@ -502,13 +504,15 @@
     </g>
     <text
        xml:space="preserve"
-       x="5324.5371"
-       y="15414.598"
+       x="5264.4731"
+       y="15428.84"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-753"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-7"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-5">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      style="fill:none;stroke-width:0.025in"
@@ -547,15 +551,6 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-6-0">Leaf</tspan></text>
-    <text
-       xml:space="preserve"
-       x="7479.5796"
-       y="17699.943"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-9"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <path
        sodipodi:nodetypes="cc"
        inkscape:connector-curvature="0"
@@ -566,15 +561,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(-737.93887,7732.6672)"
        id="g3188-3">
-      <text
-         xml:space="preserve"
-         x="3225.7478"
-         y="13175.802"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-60"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;completed =</text>
       <g
          id="g3107-62"
          transform="translate(947.90548,11584.029)">
@@ -607,15 +593,6 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-7">Root</tspan></text>
-      <text
-         xml:space="preserve"
-         x="3225.7478"
-         y="13390.038"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-60-3"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">       rnp-&gt;completed</text>
       <flowRoot
          xml:space="preserve"
          id="flowRoot3356"
@@ -627,7 +604,18 @@
              height="63.63961"
              x="332.34018"
              y="681.87292" /></flowRegion><flowPara
-           id="flowPara3362" /></flowRoot>    </g>
+           id="flowPara3362" /></flowRoot>      <text
+         xml:space="preserve"
+         x="3156.6121"
+         y="13317.754"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-36-6"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-0">rcu_seq_end(&amp;rsp-&gt;gp_seq)</tspan></text>
+    </g>
     <g
        style="fill:none;stroke-width:0.025in"
        transform="translate(-858.40227,7769.0342)"
@@ -859,6 +847,17 @@
        id="path3414-8-3-6-6"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
+    <text
+       xml:space="preserve"
+       x="7418.769"
+       y="17646.104"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-70"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-93">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-1642.5377,-11611.245)"
@@ -887,13 +886,15 @@
     </g>
     <text
        xml:space="preserve"
-       x="5327.3057"
+       x="5274.1133"
        y="15428.84"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-36"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-151.71746,-11647.612)"
@@ -972,13 +973,15 @@
          id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7486.4907"
-       y="17670.119"
+       x="7408.5918"
+       y="17619.504"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-6"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-2"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-9">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <g
      transform="translate(-6817.1997,-11647.612)"
@@ -1019,13 +1022,15 @@
          id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7474.1382"
-       y="17688.926"
+       x="7416.8003"
+       y="17619.504"
        font-style="normal"
        font-weight="bold"
        font-size="192"
-       id="text202-5"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+       id="text202-36-3"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-56">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
   </g>
   <path
      style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -1059,15 +1064,6 @@
      id="path3414-8-3-6"
      inkscape:connector-curvature="0"
      sodipodi:nodetypes="cc" />
-  <text
-     xml:space="preserve"
-     x="7318.9653"
-     y="6031.6353"
-     font-style="normal"
-     font-weight="bold"
-     font-size="192"
-     id="text202-2"
-     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
   <g
      style="fill:none;stroke-width:0.025in"
      id="g4504-3-9"
@@ -1123,4 +1119,15 @@
      id="path3134-9-0-3-5"
      d="m 6875.6003,15833.906 1595.7755,0"
      style="fill:none;stroke:#969696;stroke-width:53.19251633;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send-36)" />
+  <text
+     xml:space="preserve"
+     x="7275.2612"
+     y="5971.8916"
+     font-style="normal"
+     font-weight="bold"
+     font-size="192"
+     id="text202-36-1"
+     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+       style="font-size:172.87567139px"
+       id="tspan3166-2">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
index 0161262904ec..8c207550818f 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-1.svg
@@ -272,13 +272,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="617.89019"
-     inkscape:cy="636.57143"
-     inkscape:window-x="697"
+     inkscape:zoom="2.6330492"
+     inkscape:cx="524.82797"
+     inkscape:cy="519.31194"
+     inkscape:window-x="79"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g3188"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -305,13 +305,15 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3305.5364"
+       x="3119.363"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;gpnum++</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3071">rcu_seq_start(rsp-&gt;gp_seq)</tspan></text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
index de6ecc51b00e..d24d7d555dbc 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp-init-3.svg
@@ -19,7 +19,7 @@
    id="svg2"
    version="1.1"
    inkscape:version="0.48.4 r9939"
-   sodipodi:docname="TreeRCU-gp-init-2.svg">
+   sodipodi:docname="TreeRCU-gp-init-3.svg">
   <metadata
      id="metadata212">
     <rdf:RDF>
@@ -257,18 +257,22 @@
      inkscape:window-width="1087"
      inkscape:window-height="1144"
      id="namedview208"
-     showgrid="false"
-     inkscape:zoom="0.70710678"
+     showgrid="true"
+     inkscape:zoom="0.68224756"
      inkscape:cx="617.89019"
      inkscape:cy="625.84293"
-     inkscape:window-x="697"
+     inkscape:window-x="54"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g3153"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
-     fit-margin-bottom="5" />
+     fit-margin-bottom="5">
+    <inkscape:grid
+       type="xygrid"
+       id="grid3090" />
+  </sodipodi:namedview>
   <path
      sodipodi:nodetypes="cccccccccccccccccccccccc"
      inkscape:connector-curvature="0"
@@ -281,13 +285,13 @@
      id="g3188">
     <text
        xml:space="preserve"
-       x="3305.5364"
+       x="3145.9592"
        y="13255.592"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     <g
        id="g3107"
        transform="translate(947.90548,11584.029)">
@@ -366,13 +370,13 @@
     </g>
     <text
        xml:space="preserve"
-       x="5392.3345"
-       y="15407.104"
+       x="5253.6904"
+       y="15407.032"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-6"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      style="fill:none;stroke-width:0.025in"
@@ -413,13 +417,13 @@
          id="tspan3104-6-5-6-0">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7536.4883"
-       y="17640.934"
+       x="7415.4365"
+       y="17670.572"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-9"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-1642.5375,-11610.962)"
@@ -448,13 +452,13 @@
     </g>
     <text
        xml:space="preserve"
-       x="5378.4146"
-       y="15436.927"
+       x="5258.0688"
+       y="15412.313"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-3"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-151.71726,-11647.329)"
@@ -533,13 +537,13 @@
          id="tspan3104-6-5-6-0-92">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7520.1294"
-       y="17673.639"
+       x="7405.2607"
+       y="17670.572"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-35"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <g
      transform="translate(-6817.1998,-11647.329)"
@@ -580,13 +584,13 @@
          id="tspan3104-6-5-6-0-1">Leaf</tspan></text>
     <text
        xml:space="preserve"
-       x="7521.4663"
-       y="17666.062"
+       x="7413.4688"
+       y="17670.566"
        font-style="normal"
        font-weight="bold"
        font-size="192"
        id="text202-75"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
   <path
      style="fill:none;stroke:#000000;stroke-width:13.29812908px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -622,11 +626,11 @@
      sodipodi:nodetypes="cc" />
   <text
      xml:space="preserve"
-     x="7370.856"
-     y="5997.5972"
+     x="7271.9297"
+     y="6023.2412"
      font-style="normal"
      font-weight="bold"
      font-size="192"
      id="text202-62"
-     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+     style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
index b13b7b01bb3a..acd73c7ad0f4 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-gp.svg
@@ -1070,13 +1070,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.6004608"
-     inkscape:cx="826.65969"
-     inkscape:cy="483.3047"
-     inkscape:window-x="66"
-     inkscape:window-y="28"
+     inkscape:zoom="0.81932583"
+     inkscape:cx="840.45848"
+     inkscape:cy="5052.4242"
+     inkscape:window-x="787"
+     inkscape:window-y="24"
      inkscape:window-maximized="0"
-     inkscape:current-layer="svg2"
+     inkscape:current-layer="g4"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -1543,15 +1543,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1749.0282,658.72243)"
        id="g3188">
-      <text
-         xml:space="preserve"
-         x="3305.5364"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-5"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">rsp-&gt;gpnum++</text>
       <g
          id="g3107-62"
          transform="translate(947.90548,11584.029)">
@@ -1584,6 +1575,17 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-7">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3137.9988"
+         y="13271.316"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-626"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3071">rcu_seq_start(rsp-&gt;gp_seq)</tspan></text>
     </g>
     <rect
        ry="0"
@@ -2318,15 +2320,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1739.0986,17188.625)"
        id="g3188-6">
-      <text
-         xml:space="preserve"
-         x="3305.5364"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
       <g
          id="g3107-5"
          transform="translate(947.90548,11584.029)">
@@ -2359,6 +2352,15 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-1">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3147.9268"
+         y="13240.524"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-1"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -2387,13 +2389,13 @@
       </g>
       <text
          xml:space="preserve"
-         x="5392.3345"
-         y="15407.104"
+         x="5263.1094"
+         y="15411.646"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-6-7"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-92"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -2434,13 +2436,13 @@
            id="tspan3104-6-5-6-0-94">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7536.4883"
-         y="17640.934"
+         x="7417.4053"
+         y="17655.502"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-9"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-759"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-2353.8462,17224.992)"
@@ -2469,13 +2471,13 @@
       </g>
       <text
          xml:space="preserve"
-         x="5378.4146"
-         y="15436.927"
+         x="5246.1548"
+         y="15411.648"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-3"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-87"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-863.02613,17188.625)"
@@ -2554,13 +2556,13 @@
            id="tspan3104-6-5-6-0-92-6">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7520.1294"
-         y="17673.639"
+         x="7433.8257"
+         y="17682.098"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-35"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-2"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <g
        transform="translate(-7528.5085,17188.625)"
@@ -2601,13 +2603,13 @@
            id="tspan3104-6-5-6-0-1-8">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7521.4663"
-         y="17666.062"
+         x="7415.4404"
+         y="17682.098"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-75-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
+         id="text202-0"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
     </g>
     <path
        style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -2641,15 +2643,6 @@
        id="path3414-8-3-6-4"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
-    <text
-       xml:space="preserve"
-       x="6659.5469"
-       y="34833.551"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-62"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gpnum = rsp-&gt;gpnum</text>
     <path
        sodipodi:nodetypes="ccc"
        inkscape:connector-curvature="0"
@@ -3844,7 +3837,7 @@
          font-weight="bold"
          font-size="192"
          id="text202-6-6-5"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gp_seq</text>
       <text
          xml:space="preserve"
          x="5035.4155"
@@ -4284,15 +4277,6 @@
        style="fill:none;stroke-width:0.025in"
        transform="translate(1874.038,53203.538)"
        id="g3188-7">
-      <text
-         xml:space="preserve"
-         x="3199.1516"
-         y="13255.592"
-         font-style="normal"
-         font-weight="bold"
-         font-size="192"
-         id="text202-82"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
       <g
          id="g3107-53"
          transform="translate(947.90548,11584.029)">
@@ -4325,6 +4309,17 @@
          sodipodi:linespacing="125%"><tspan
            style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
            id="tspan3104-6-5-19">Root</tspan></text>
+      <text
+         xml:space="preserve"
+         x="3175.896"
+         y="13240.11"
+         font-style="normal"
+         font-weight="bold"
+         font-size="192"
+         id="text202-36-3"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <rect
        ry="0"
@@ -4371,13 +4366,15 @@
       </g>
       <text
          xml:space="preserve"
-         x="5324.5371"
-         y="15414.598"
+         x="5264.4829"
+         y="15411.231"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-753"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-7"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-5">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        style="fill:none;stroke-width:0.025in"
@@ -4412,30 +4409,12 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-6-0-4">Leaf</tspan></text>
-    <text
-       xml:space="preserve"
-       x="10084.225"
-       y="70903.312"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-9-0"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <path
        sodipodi:nodetypes="ccc"
        inkscape:connector-curvature="0"
        id="path3134-9-0-3-9"
        d="m 6315.6122,72629.054 -20.9533,8108.684 1648.968,0"
        style="fill:none;stroke:#969696;stroke-width:53.19251251;stroke-linecap:butt;stroke-linejoin:miter;stroke-miterlimit:4;stroke-opacity:1;stroke-dasharray:none;marker-end:url(#Arrow1Send)" />
-    <text
-       xml:space="preserve"
-       x="5092.4683"
-       y="74111.672"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-60"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rsp-&gt;completed =</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g3107-62-6"
@@ -4469,15 +4448,6 @@
        sodipodi:linespacing="125%"><tspan
          style="font-size:159.57754517px;font-style:normal;font-variant:normal;font-weight:normal;font-stretch:normal;text-align:start;line-height:125%;writing-mode:lr-tb;text-anchor:start;font-family:Liberation Sans;-inkscape-font-specification:Liberation Sans"
          id="tspan3104-6-5-7-7">Root</tspan></text>
-    <text
-       xml:space="preserve"
-       x="5092.4683"
-       y="74325.906"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-60-3"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">       rnp-&gt;completed</text>
     <g
        style="fill:none;stroke-width:0.025in"
        transform="translate(1746.2528,60972.572)"
@@ -4736,13 +4706,15 @@
       </g>
       <text
          xml:space="preserve"
-         x="5327.3057"
-         y="15428.84"
+         x="5274.1216"
+         y="15411.231"
          font-style="normal"
          font-weight="bold"
          font-size="192"
          id="text202-36"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-6">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        transform="translate(-728.08545,53203.538)"
@@ -4821,13 +4793,15 @@
            id="tspan3104-6-5-6-0-92-5">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7486.4907"
-         y="17670.119"
+         x="7435.1987"
+         y="17708.281"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-6-2"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-9"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-1">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <g
        transform="translate(-7393.5687,53203.538)"
@@ -4868,13 +4842,15 @@
            id="tspan3104-6-5-6-0-1-5">Leaf</tspan></text>
       <text
          xml:space="preserve"
-         x="7474.1382"
-         y="17688.926"
+         x="7416.8125"
+         y="17708.281"
          font-style="normal"
          font-weight="bold"
          font-size="192"
-         id="text202-5-1"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
+         id="text202-36-35"
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+           style="font-size:172.87567139px"
+           id="tspan3166-62">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
     </g>
     <path
        style="fill:none;stroke:#000000;stroke-width:13.29812813px;stroke-linecap:butt;stroke-linejoin:miter;stroke-opacity:1;marker-end:url(#Arrow2Lend)"
@@ -4908,15 +4884,6 @@
        id="path3414-8-3-6-67"
        inkscape:connector-curvature="0"
        sodipodi:nodetypes="cc" />
-    <text
-       xml:space="preserve"
-       x="6742.6001"
-       y="70882.617"
-       font-style="normal"
-       font-weight="bold"
-       font-size="192"
-       id="text202-2"
-       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;completed = -&gt;gpnum</text>
     <g
        style="fill:none;stroke-width:0.025in"
        id="g4504-3-9-6"
@@ -5131,5 +5098,47 @@
        font-size="192"
        id="text202-7-9-6-6-7"
        style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rcu_do_batch()</text>
+    <text
+       xml:space="preserve"
+       x="6698.9019"
+       y="70885.211"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-2"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-7">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="10023.457"
+       y="70885.234"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-0"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-9">rcu_seq_end(&amp;rnp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="5023.3389"
+       y="74209.773"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-36-36"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier"><tspan
+         style="font-size:172.87567139px"
+         id="tspan3166-0">rcu_seq_end(&amp;rsp-&gt;gp_seq)</tspan></text>
+    <text
+       xml:space="preserve"
+       x="6562.5884"
+       y="34870.727"
+       font-style="normal"
+       font-weight="bold"
+       font-size="192"
+       id="text202-3"
+       style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">-&gt;gp_seq = rsp-&gt;gp_seq</text>
   </g>
 </svg>
diff --git a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
index de3992f4cbe1..149bec2a4493 100644
--- a/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
+++ b/Documentation/RCU/Design/Memory-Ordering/TreeRCU-qs.svg
@@ -300,13 +300,13 @@
      inkscape:window-height="1144"
      id="namedview208"
      showgrid="true"
-     inkscape:zoom="0.70710678"
-     inkscape:cx="616.47598"
-     inkscape:cy="595.41964"
-     inkscape:window-x="813"
+     inkscape:zoom="0.96484375"
+     inkscape:cx="507.0191"
+     inkscape:cy="885.62207"
+     inkscape:window-x="47"
      inkscape:window-y="28"
      inkscape:window-maximized="0"
-     inkscape:current-layer="g4405"
+     inkscape:current-layer="g3115"
      fit-margin-top="5"
      fit-margin-right="5"
      fit-margin-left="5"
@@ -710,7 +710,7 @@
          font-weight="bold"
          font-size="192"
          id="text202-6-6"
-         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gpnum</text>
+         style="font-size:192px;font-style:normal;font-weight:bold;text-anchor:start;fill:#000000;stroke-width:0.025in;font-family:Courier">rdp-&gt;gp_seq</text>
       <text
          xml:space="preserve"
          x="5035.4155"
-- 
cgit v1.2.3


From e1333462e3cf933ab860c693ef1ff50775c7ea7f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 2 May 2018 12:39:42 -0700
Subject: doc: Update RCU CPU stall-warning documentation

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/RCU/stallwarn.txt | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/Documentation/RCU/stallwarn.txt b/Documentation/RCU/stallwarn.txt
index 4259f95c3261..f99cf11b314b 100644
--- a/Documentation/RCU/stallwarn.txt
+++ b/Documentation/RCU/stallwarn.txt
@@ -172,7 +172,7 @@ it will print a message similar to the following:
 	INFO: rcu_sched detected stalls on CPUs/tasks:
 	2-...: (3 GPs behind) idle=06c/0/0 softirq=1453/1455 fqs=0
 	16-...: (0 ticks this GP) idle=81c/0/0 softirq=764/764 fqs=0
-	(detected by 32, t=2603 jiffies, g=7073, c=7072, q=625)
+	(detected by 32, t=2603 jiffies, g=7075, q=625)
 
 This message indicates that CPU 32 detected that CPUs 2 and 16 were both
 causing stalls, and that the stall was affecting RCU-sched.  This message
@@ -215,11 +215,10 @@ CPU since the last time that this CPU noted the beginning of a grace
 period.
 
 The "detected by" line indicates which CPU detected the stall (in this
-case, CPU 32), how many jiffies have elapsed since the start of the
-grace period (in this case 2603), the number of the last grace period
-to start and to complete (7073 and 7072, respectively), and an estimate
-of the total number of RCU callbacks queued across all CPUs (625 in
-this case).
+case, CPU 32), how many jiffies have elapsed since the start of the grace
+period (in this case 2603), the grace-period sequence number (7075), and
+an estimate of the total number of RCU callbacks queued across all CPUs
+(625 in this case).
 
 In kernels with CONFIG_RCU_FAST_NO_HZ, more information is printed
 for each CPU:
@@ -266,15 +265,16 @@ If the relevant grace-period kthread has been unable to run prior to
 the stall warning, as was the case in the "All QSes seen" line above,
 the following additional line is printed:
 
-	kthread starved for 23807 jiffies! g7073 c7072 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1
+	kthread starved for 23807 jiffies! g7075 f0x0 RCU_GP_WAIT_FQS(3) ->state=0x1 ->cpu=5
 
 Starving the grace-period kthreads of CPU time can of course result
 in RCU CPU stall warnings even when all CPUs and tasks have passed
-through the required quiescent states.  The "g" and "c" numbers flag the
-number of the last grace period started and completed, respectively,
-the "f" precedes the ->gp_flags command to the grace-period kthread,
-the "RCU_GP_WAIT_FQS" indicates that the kthread is waiting for a short
-timeout, and the "state" precedes value of the task_struct ->state field.
+through the required quiescent states.  The "g" number shows the current
+grace-period sequence number, the "f" precedes the ->gp_flags command
+to the grace-period kthread, the "RCU_GP_WAIT_FQS" indicates that the
+kthread is waiting for a short timeout, the "state" precedes value of the
+task_struct ->state field, and the "cpu" indicates that the grace-period
+kthread last ran on CPU 5.
 
 
 Multiple Warnings From One Stall
-- 
cgit v1.2.3


From a2165e416878b325747f871df4b236b49bf61486 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 12 May 2018 07:42:20 -0700
Subject: rcu: Don't funnel-lock above leaf node if GP in progress

The old grace-period start code would acquire only the leaf's rcu_node
structure's ->lock if that structure believed that a grace period was
in progress.  The new code advances to the leaf's parent in this case,
needlessly acquiring then leaf's parent's ->lock.  This commit therefore
checks the grace-period state after marking the leaf with the need for
the specified grace period, and if the leaf believes that a grace period
is in progress, takes an early exit.

Reported-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Add "Startedleaf" tracing as suggested by Joel Fernandes. ]
---
 include/trace/events/rcu.h | 4 ++--
 kernel/rcu/tree.c          | 9 +++++++++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 7d3650cc9d30..5ab1df0a2801 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -91,8 +91,8 @@ TRACE_EVENT(rcu_grace_period,
  *
  * "Startleaf": Request a grace period based on leaf-node data.
  * "Prestarted": Someone beat us to the request
- * "Startedleaf": Leaf-node start proved sufficient.
- * "Startedleafroot": Leaf-node start proved sufficient after checking root.
+ * "Startedleaf": Leaf node marked for future GP.
+ * "Startedleafroot": All nodes from leaf to root marked for future GP.
  * "Startedroot": Requested a nocb grace period based on root-node data.
  * "NoGPkthread": The RCU grace-period kthread has not yet started.
  * "StartWait": Start waiting for the requested grace period.
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 5643c135fb06..24a79e85b81f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1590,6 +1590,15 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 			goto unlock_out;
 		}
 		rnp_root->gp_seq_needed = c;
+		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
+			/*
+			 * We just marked the leaf, and a grace period
+			 * is in progress, which means that rcu_gp_cleanup()
+			 * will see the marking.  Bail to reduce contention.
+			 */
+			trace_rcu_this_gp(rnp, rdp, c, TPS("Startedleaf"));
+			goto unlock_out;
+		}
 		if (rnp_root != rnp && rnp_root->parent != NULL)
 			raw_spin_unlock_rcu_node(rnp_root);
 		if (!rnp_root->parent)
-- 
cgit v1.2.3


From 5b55072f22ba2ed136b7a1b6c5beea9ace8415a7 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Sun, 13 May 2018 20:15:40 -0700
Subject: rcu: Produce last "CleanupMore" trace only if late-breaking request

Currently Tree RCU's clean-up code emits a "CleanupMore" trace event in
response to late-arriving grace-period requests even if the grace period
was already requested. This makes "CleanupMore" show up an extra time (in
addition to once for each rcu_node structure that was previously marked
with the request), and for no good reason.  This commit therefore avoids
emitting this trace message unless the the only request for this next
grace period arrived during or after the cleanup scan of the rcu_node
structures.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 24a79e85b81f..73a33b82cfcd 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2069,7 +2069,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rsp->gp_state = RCU_GP_IDLE;
 	/* Check for GP requests since above loop. */
 	rdp = this_cpu_ptr(rsp->rda);
-	if (ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
+	if (!needgp && ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed)) {
 		trace_rcu_this_gp(rnp, rdp, rnp->gp_seq_needed,
 				  TPS("CleanupMore"));
 		needgp = true;
-- 
cgit v1.2.3


From 5ca0905f6787e930bc2a626cf1d8f69fab52acef Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Sun, 13 May 2018 20:15:41 -0700
Subject: rcu: Fix cpustart tracepoint gp_seq number

The "cpustart" trace event shows a stale gp_seq. This is because it uses
rdp->gp_seq, which is updated only at the end of the __note_gp_changes()
function. This commit therefore instead uses rnp->gp_seq.

An alternative fix would be to update rdp->gp_seq earlier, but this would
break RCU's detection of the beginning of a new-to-this-CPU grace period.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 73a33b82cfcd..973250503d98 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1801,7 +1801,7 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		 * set up to detect a quiescent state, otherwise don't
 		 * go looking for one.
 		 */
-		trace_rcu_grace_period(rsp->name, rdp->gp_seq, TPS("cpustart"));
+		trace_rcu_grace_period(rsp->name, rnp->gp_seq, TPS("cpustart"));
 		need_gp = !!(rnp->qsmask & rdp->grpmask);
 		rdp->cpu_no_qs.b.norm = need_gp;
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
-- 
cgit v1.2.3


From 2e3e5e55010105f9d4351f68e15dbc43402a7794 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 May 2018 11:53:41 -0700
Subject: rcu: Make rcu_start_this_gp() check for grace period already started

In the old days of ->gpnum and ->completed, the code requesting a new
grace period checked to see if that grace period had already started,
bailing early if so.  The new-age ->gp_seq approach instead checks
whether the grace period has already finished.  A compensating change
pushed the requested grace period down to the bottom of the tree, thus
reducing lock contention and even eliminating it in some cases.  But why
not further reduce contention, especially on large systems, by doing both,
especially given that the cost of doing both is extremely small?

This commit therefore adds a new rcu_seq_started() function that checks
whether a specified grace period has already started.  It then uses
this new function in place of rcu_seq_done() in the rcu_start_this_gp()
function's funnel locking code.

Reported-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h  | 9 +++++++++
 kernel/rcu/tree.c | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 003671825d62..1c5cbd9d7c97 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -107,6 +107,15 @@ static inline unsigned long rcu_seq_current(unsigned long *sp)
 	return READ_ONCE(*sp);
 }
 
+/*
+ * Given a snapshot from rcu_seq_snap(), determine whether or not the
+ * corresponding update-side operation has started.
+ */
+static inline bool rcu_seq_started(unsigned long *sp, unsigned long s)
+{
+	return ULONG_CMP_LT((s - 1) & ~RCU_SEQ_STATE_MASK, READ_ONCE(*sp));
+}
+
 /*
  * Given a snapshot from rcu_seq_snap(), determine whether or not a
  * full update-side operation has occurred.
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 973250503d98..cbf2bcde5e60 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1583,7 +1583,7 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 		if (rnp_root != rnp)
 			raw_spin_lock_rcu_node(rnp_root);
 		if (ULONG_CMP_GE(rnp_root->gp_seq_needed, c) ||
-		    rcu_seq_done(&rnp_root->gp_seq, c) ||
+		    rcu_seq_started(&rnp_root->gp_seq, c) ||
 		    (rnp != rnp_root &&
 		     rcu_seq_state(rcu_seq_current(&rnp_root->gp_seq)))) {
 			trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
-- 
cgit v1.2.3


From d72193123c81ae6123d108b3be2096f3f13b25a6 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 May 2018 15:24:41 -0700
Subject: rcutorture: Correctly handle grace-period sequence wrap

The new ->gq_seq grace-period sequence numbers must be shifted down,
which give artifacts when these numbers wrap.  This commit therefore
enables rcutorture and rcuperf to handle grace-period sequence numbers
even if they do wrap.  It does this by allowing a special subtraction
function to be specified, and this function subtracts before shifting.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h        |  9 +++++++++
 kernel/rcu/rcuperf.c    | 18 ++++++++++++++++--
 kernel/rcu/rcutorture.c | 19 +++++++++++++------
 kernel/rcu/tree.c       |  6 +++---
 4 files changed, 41 insertions(+), 11 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 1c5cbd9d7c97..aa215d6355f8 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -142,6 +142,15 @@ static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
 			    new);
 }
 
+/*
+ * Roughly how many full grace periods have elapsed between the collection
+ * of the two specified grace periods?
+ */
+static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
+{
+	return (new - old) >> RCU_SEQ_CTR_SHIFT;
+}
+
 /*
  * debug_rcu_head_queue()/debug_rcu_head_unqueue() are used internally
  * by call_rcu() and rcu callback execution, and are therefore not part of the
diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 2b5a613afcf3..b080bc4a4f45 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -139,6 +139,7 @@ struct rcu_perf_ops {
 	int (*readlock)(void);
 	void (*readunlock)(int idx);
 	unsigned long (*get_gp_seq)(void);
+	unsigned long (*gp_diff)(unsigned long new, unsigned long old);
 	unsigned long (*exp_completed)(void);
 	void (*async)(struct rcu_head *head, rcu_callback_t func);
 	void (*gp_barrier)(void);
@@ -179,6 +180,7 @@ static struct rcu_perf_ops rcu_ops = {
 	.readlock	= rcu_perf_read_lock,
 	.readunlock	= rcu_perf_read_unlock,
 	.get_gp_seq	= rcu_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed,
 	.async		= call_rcu,
 	.gp_barrier	= rcu_barrier,
@@ -208,6 +210,7 @@ static struct rcu_perf_ops rcu_bh_ops = {
 	.readlock	= rcu_bh_perf_read_lock,
 	.readunlock	= rcu_bh_perf_read_unlock,
 	.get_gp_seq	= rcu_bh_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_bh,
 	.gp_barrier	= rcu_barrier_bh,
@@ -264,6 +267,7 @@ static struct rcu_perf_ops srcu_ops = {
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
 	.get_gp_seq	= srcu_perf_completed,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -292,6 +296,7 @@ static struct rcu_perf_ops srcud_ops = {
 	.readlock	= srcu_perf_read_lock,
 	.readunlock	= srcu_perf_read_unlock,
 	.get_gp_seq	= srcu_perf_completed,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= srcu_perf_completed,
 	.async		= srcu_call_rcu,
 	.gp_barrier	= srcu_rcu_barrier,
@@ -321,6 +326,7 @@ static struct rcu_perf_ops sched_ops = {
 	.readlock	= sched_perf_read_lock,
 	.readunlock	= sched_perf_read_unlock,
 	.get_gp_seq	= rcu_sched_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.exp_completed	= rcu_exp_batches_completed_sched,
 	.async		= call_rcu_sched,
 	.gp_barrier	= rcu_barrier_sched,
@@ -348,6 +354,7 @@ static struct rcu_perf_ops tasks_ops = {
 	.readlock	= tasks_perf_read_lock,
 	.readunlock	= tasks_perf_read_unlock,
 	.get_gp_seq	= rcu_no_completed,
+	.gp_diff	= rcu_seq_diff,
 	.async		= call_rcu_tasks,
 	.gp_barrier	= rcu_barrier_tasks,
 	.sync		= synchronize_rcu_tasks,
@@ -355,6 +362,13 @@ static struct rcu_perf_ops tasks_ops = {
 	.name		= "tasks"
 };
 
+static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
+{
+	if (!cur_ops->gp_diff)
+		return new - old;
+	return cur_ops->gp_diff(new, old);
+}
+
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
@@ -577,8 +591,8 @@ rcu_perf_cleanup(void)
 			 t_rcu_perf_writer_finished -
 			 t_rcu_perf_writer_started,
 			 ngps,
-			 b_rcu_perf_writer_finished -
-			 b_rcu_perf_writer_started);
+			 rcuperf_seq_diff(b_rcu_perf_writer_finished,
+					  b_rcu_perf_writer_started));
 		for (i = 0; i < nrealwriters; i++) {
 			if (!writer_durations)
 				break;
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 81fb43530d64..0481c7286875 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -265,6 +265,7 @@ struct rcu_torture_ops {
 	void (*read_delay)(struct torture_random_state *rrsp);
 	void (*readunlock)(int idx);
 	unsigned long (*get_gp_seq)(void);
+	unsigned long (*gp_diff)(unsigned long new, unsigned long old);
 	void (*deferred_free)(struct rcu_torture *p);
 	void (*sync)(void);
 	void (*exp_sync)(void);
@@ -400,6 +401,7 @@ static struct rcu_torture_ops rcu_ops = {
 	.read_delay	= rcu_read_delay,
 	.readunlock	= rcu_torture_read_unlock,
 	.get_gp_seq	= rcu_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_torture_deferred_free,
 	.sync		= synchronize_rcu,
 	.exp_sync	= synchronize_rcu_expedited,
@@ -441,6 +443,7 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= rcu_bh_torture_read_unlock,
 	.get_gp_seq	= rcu_bh_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_bh_torture_deferred_free,
 	.sync		= synchronize_rcu_bh,
 	.exp_sync	= synchronize_rcu_bh_expedited,
@@ -646,6 +649,7 @@ static struct rcu_torture_ops sched_ops = {
 	.read_delay	= rcu_read_delay,  /* just reuse rcu's version. */
 	.readunlock	= sched_torture_read_unlock,
 	.get_gp_seq	= rcu_sched_get_gp_seq,
+	.gp_diff	= rcu_seq_diff,
 	.deferred_free	= rcu_sched_torture_deferred_free,
 	.sync		= synchronize_sched,
 	.exp_sync	= synchronize_sched_expedited,
@@ -695,6 +699,13 @@ static struct rcu_torture_ops tasks_ops = {
 	.name		= "tasks"
 };
 
+static unsigned long rcutorture_seq_diff(unsigned long new, unsigned long old)
+{
+	if (!cur_ops->gp_diff)
+		return new - old;
+	return cur_ops->gp_diff(new, old);
+}
+
 static bool __maybe_unused torturing_tasks(void)
 {
 	return cur_ops == &tasks_ops;
@@ -1127,9 +1138,7 @@ static void rcu_torture_timer(struct timer_list *unused)
 		rcu_ftrace_dump(DUMP_ALL);
 	}
 	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = completed - started;
-	if (completed > ULONG_MAX >> 1)
-		completed = 0; /* Not all gp_seq have full range. */
+	completed = rcutorture_seq_diff(completed, started);
 	if (completed > RCU_TORTURE_PIPE_LEN) {
 		/* Should not happen, but... */
 		completed = RCU_TORTURE_PIPE_LEN;
@@ -1205,9 +1214,7 @@ rcu_torture_reader(void *arg)
 			rcu_ftrace_dump(DUMP_ALL);
 		}
 		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = completed - started;
-		if (completed > ULONG_MAX >> 1)
-			completed = 0; /* Not all gp_seq have full range. */
+		completed = rcutorture_seq_diff(completed, started);
 		if (completed > RCU_TORTURE_PIPE_LEN) {
 			/* Should not happen, but... */
 			completed = RCU_TORTURE_PIPE_LEN;
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cbf2bcde5e60..fa219eea0ae7 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -532,7 +532,7 @@ static int rcu_pending(void);
  */
 unsigned long rcu_get_gp_seq(void)
 {
-	return rcu_seq_ctr(READ_ONCE(rcu_state_p->gp_seq));
+	return READ_ONCE(rcu_state_p->gp_seq);
 }
 EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
 
@@ -541,7 +541,7 @@ EXPORT_SYMBOL_GPL(rcu_get_gp_seq);
  */
 unsigned long rcu_sched_get_gp_seq(void)
 {
-	return rcu_seq_ctr(READ_ONCE(rcu_sched_state.gp_seq));
+	return READ_ONCE(rcu_sched_state.gp_seq);
 }
 EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
 
@@ -550,7 +550,7 @@ EXPORT_SYMBOL_GPL(rcu_sched_get_gp_seq);
  */
 unsigned long rcu_bh_get_gp_seq(void)
 {
-	return rcu_seq_ctr(READ_ONCE(rcu_bh_state.gp_seq));
+	return READ_ONCE(rcu_bh_state.gp_seq);
 }
 EXPORT_SYMBOL_GPL(rcu_bh_get_gp_seq);
 
-- 
cgit v1.2.3


From 3d18469a2bb3988e669d67e097eff42dd40663d4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 May 2018 16:47:30 -0700
Subject: rcu: Regularize resetting of rcu_data wrap indicator

The rcu_data structure's ->gpwrap indicator is currently reset only
when the CPU in question detects a new grace period.  This is in theory
sufficient because any CPU that has been out of action for long enough
that its ->gpwrap indicator is set is guaranteed to see both the end
of an old grace period and the start of a new one.

However, the current code leaves a short window during which the ->gpwrap
indicator has been reset but the corresponding ->gp_seq counter has not
yet been brought up to date.  This is harmless because interrupts are
disabled, but it is likely to (at the very least) cause confusion.

This commit therefore moves the resetting of ->gpwrap to follow the
updating of ->gp_seq.  While in the area, it also resets ->gp_seq_needed.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index fa219eea0ae7..161e8fb8b83f 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1807,10 +1807,12 @@ static bool __note_gp_changes(struct rcu_state *rsp, struct rcu_node *rnp,
 		rdp->rcu_qs_ctr_snap = __this_cpu_read(rcu_dynticks.rcu_qs_ctr);
 		rdp->core_needs_qs = need_gp;
 		zero_cpu_stall_ticks(rdp);
-		WRITE_ONCE(rdp->gpwrap, false);
-		rcu_gpnum_ovf(rnp, rdp);
 	}
 	rdp->gp_seq = rnp->gp_seq;  /* Remember new grace-period state. */
+	if (ULONG_CMP_GE(rnp->gp_seq_needed, rdp->gp_seq_needed) || rdp->gpwrap)
+		rdp->gp_seq_needed = rnp->gp_seq_needed;
+	WRITE_ONCE(rdp->gpwrap, false);
+	rcu_gpnum_ovf(rnp, rdp);
 	return ret;
 }
 
-- 
cgit v1.2.3


From b73de91d6a4c97ed586b2a5a6ce7c6fe395d9a3b Mon Sep 17 00:00:00 2001
From: Joel Fernandes <joelaf@google.com>
Date: Sun, 20 May 2018 21:42:18 -0700
Subject: rcu: Rename the grace-period-request variables and parameters

The name 'c' is used for variables and parameters holding the requested
grace-period sequence number.  However it is no longer very meaningful
given the conversions from ->gpnum and (especially) ->completed to
->gp_seq. This commit therefore renames 'c' to 'gp_seq_req'.

Previous patch discussion is at:
https://patchwork.kernel.org/patch/10396579/

Signed-off-by: Joel Fernandes <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 15 ++++++++-------
 kernel/rcu/tree.c          | 46 +++++++++++++++++++++++++++-------------------
 2 files changed, 35 insertions(+), 26 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 5ab1df0a2801..759e7e83733d 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -103,15 +103,16 @@ TRACE_EVENT(rcu_grace_period,
  */
 TRACE_EVENT(rcu_future_grace_period,
 
-	TP_PROTO(const char *rcuname, unsigned long gp_seq, unsigned long c,
-		 u8 level, int grplo, int grphi, const char *gpevent),
+	TP_PROTO(const char *rcuname, unsigned long gp_seq,
+		 unsigned long gp_seq_req, u8 level, int grplo, int grphi,
+		 const char *gpevent),
 
-	TP_ARGS(rcuname, gp_seq, c, level, grplo, grphi, gpevent),
+	TP_ARGS(rcuname, gp_seq, gp_seq_req, level, grplo, grphi, gpevent),
 
 	TP_STRUCT__entry(
 		__field(const char *, rcuname)
 		__field(unsigned long, gp_seq)
-		__field(unsigned long, c)
+		__field(unsigned long, gp_seq_req)
 		__field(u8, level)
 		__field(int, grplo)
 		__field(int, grphi)
@@ -121,7 +122,7 @@ TRACE_EVENT(rcu_future_grace_period,
 	TP_fast_assign(
 		__entry->rcuname = rcuname;
 		__entry->gp_seq = gp_seq;
-		__entry->c = c;
+		__entry->gp_seq_req = gp_seq_req;
 		__entry->level = level;
 		__entry->grplo = grplo;
 		__entry->grphi = grphi;
@@ -129,7 +130,7 @@ TRACE_EVENT(rcu_future_grace_period,
 	),
 
 	TP_printk("%s %lu %lu %u %d %d %s",
-		  __entry->rcuname, __entry->gp_seq, __entry->c, __entry->level,
+		  __entry->rcuname, __entry->gp_seq, __entry->gp_seq_req, __entry->level,
 		  __entry->grplo, __entry->grphi, __entry->gpevent)
 );
 
@@ -751,7 +752,7 @@ TRACE_EVENT(rcu_barrier,
 #else /* #ifdef CONFIG_RCU_TRACE */
 
 #define trace_rcu_grace_period(rcuname, gp_seq, gpevent) do { } while (0)
-#define trace_rcu_future_grace_period(rcuname, gp_seq, c, \
+#define trace_rcu_future_grace_period(rcuname, gp_seq, gp_seq_req, \
 				      level, grplo, grphi, event) \
 				      do { } while (0)
 #define trace_rcu_grace_period_init(rcuname, gp_seq, level, grplo, grphi, \
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 161e8fb8b83f..8c31b1740afc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1546,13 +1546,18 @@ void rcu_cpu_stall_reset(void)
 
 /* Trace-event wrapper function for trace_rcu_future_grace_period.  */
 static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-			      unsigned long c, const char *s)
+			      unsigned long gp_seq_req, const char *s)
 {
-	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, c,
+	trace_rcu_future_grace_period(rdp->rsp->name, rnp->gp_seq, gp_seq_req,
 				      rnp->level, rnp->grplo, rnp->grphi, s);
 }
 
 /*
+ * rcu_start_this_gp - Request the start of a particular grace period
+ * @rnp: The leaf node of the CPU from which to start.
+ * @rdp: The rcu_data corresponding to the CPU from which to start.
+ * @gp_seq_req: The gp_seq of the grace period to start.
+ *
  * Start the specified grace period, as needed to handle newly arrived
  * callbacks.  The required future grace periods are recorded in each
  * rcu_node structure's ->gp_seq_needed field.  Returns true if there
@@ -1560,9 +1565,11 @@ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
  *
  * The caller must hold the specified rcu_node structure's ->lock, which
  * is why the caller is responsible for waking the grace-period kthread.
+ *
+ * Returns true if the GP thread needs to be awakened else false.
  */
 static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
-			      unsigned long c)
+			      unsigned long gp_seq_req)
 {
 	bool ret = false;
 	struct rcu_state *rsp = rdp->rsp;
@@ -1578,25 +1585,27 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 	 * not be released.
 	 */
 	raw_lockdep_assert_held_rcu_node(rnp);
-	trace_rcu_this_gp(rnp, rdp, c, TPS("Startleaf"));
+	trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startleaf"));
 	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
 		if (rnp_root != rnp)
 			raw_spin_lock_rcu_node(rnp_root);
-		if (ULONG_CMP_GE(rnp_root->gp_seq_needed, c) ||
-		    rcu_seq_started(&rnp_root->gp_seq, c) ||
+		if (ULONG_CMP_GE(rnp_root->gp_seq_needed, gp_seq_req) ||
+		    rcu_seq_started(&rnp_root->gp_seq, gp_seq_req) ||
 		    (rnp != rnp_root &&
 		     rcu_seq_state(rcu_seq_current(&rnp_root->gp_seq)))) {
-			trace_rcu_this_gp(rnp_root, rdp, c, TPS("Prestarted"));
+			trace_rcu_this_gp(rnp_root, rdp, gp_seq_req,
+					  TPS("Prestarted"));
 			goto unlock_out;
 		}
-		rnp_root->gp_seq_needed = c;
+		rnp_root->gp_seq_needed = gp_seq_req;
 		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
 			/*
 			 * We just marked the leaf, and a grace period
 			 * is in progress, which means that rcu_gp_cleanup()
 			 * will see the marking.  Bail to reduce contention.
 			 */
-			trace_rcu_this_gp(rnp, rdp, c, TPS("Startedleaf"));
+			trace_rcu_this_gp(rnp, rdp, gp_seq_req,
+					  TPS("Startedleaf"));
 			goto unlock_out;
 		}
 		if (rnp_root != rnp && rnp_root->parent != NULL)
@@ -1607,21 +1616,21 @@ static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 
 	/* If GP already in progress, just leave, otherwise start one. */
 	if (rcu_gp_in_progress(rsp)) {
-		trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedleafroot"));
+		trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("Startedleafroot"));
 		goto unlock_out;
 	}
-	trace_rcu_this_gp(rnp_root, rdp, c, TPS("Startedroot"));
+	trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("Startedroot"));
 	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
 	rsp->gp_req_activity = jiffies;
 	if (!rsp->gp_kthread) {
-		trace_rcu_this_gp(rnp_root, rdp, c, TPS("NoGPkthread"));
+		trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
 	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
 	/* Push furthest requested GP to leaf node and rcu_data structure. */
-	if (ULONG_CMP_LT(c, rnp_root->gp_seq_needed)) {
+	if (ULONG_CMP_LT(gp_seq_req, rnp_root->gp_seq_needed)) {
 		rnp->gp_seq_needed = rnp_root->gp_seq_needed;
 		rdp->gp_seq_needed = rnp_root->gp_seq_needed;
 	}
@@ -1636,14 +1645,13 @@ unlock_out:
  */
 static bool rcu_future_gp_cleanup(struct rcu_state *rsp, struct rcu_node *rnp)
 {
-	unsigned long c = rnp->gp_seq;
 	bool needmore;
 	struct rcu_data *rdp = this_cpu_ptr(rsp->rda);
 
 	needmore = ULONG_CMP_LT(rnp->gp_seq, rnp->gp_seq_needed);
 	if (!needmore)
 		rnp->gp_seq_needed = rnp->gp_seq; /* Avoid counter wrap. */
-	trace_rcu_this_gp(rnp, rdp, c,
+	trace_rcu_this_gp(rnp, rdp, rnp->gp_seq,
 			  needmore ? TPS("CleanupMore") : TPS("Cleanup"));
 	return needmore;
 }
@@ -1679,7 +1687,7 @@ static void rcu_gp_kthread_wake(struct rcu_state *rsp)
 static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 			       struct rcu_data *rdp)
 {
-	unsigned long c;
+	unsigned long gp_seq_req;
 	bool ret = false;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
@@ -1698,9 +1706,9 @@ static bool rcu_accelerate_cbs(struct rcu_state *rsp, struct rcu_node *rnp,
 	 * accelerating callback invocation to an earlier grace-period
 	 * number.
 	 */
-	c = rcu_seq_snap(&rsp->gp_seq);
-	if (rcu_segcblist_accelerate(&rdp->cblist, c))
-		ret = rcu_start_this_gp(rnp, rdp, c);
+	gp_seq_req = rcu_seq_snap(&rsp->gp_seq);
+	if (rcu_segcblist_accelerate(&rdp->cblist, gp_seq_req))
+		ret = rcu_start_this_gp(rnp, rdp, gp_seq_req);
 
 	/* Trace depending on how much we were able to accelerate. */
 	if (rcu_segcblist_restempty(&rdp->cblist, RCU_WAIT_TAIL))
-- 
cgit v1.2.3


From df2bf8f7f776cef57e6b27690c7b78c86f259515 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Tue, 22 May 2018 23:38:14 -0700
Subject: rcu: Use better variable names in funnel locking loop

The funnel locking loop in rcu_start_this_gp uses rcu_root as a
temporary variable while walking the combining tree. This causes a
tiresome exercise of a code reader reminding themselves that rcu_root
may not be root. Lets just call it rnp, and rename other variables as
well to be more appropriate.

Original patch: https://patchwork.kernel.org/patch/10396577/

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Fix name in comment as well. ]
---
 kernel/rcu/tree.c | 64 +++++++++++++++++++++++++++----------------------------
 1 file changed, 32 insertions(+), 32 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 8c31b1740afc..1af58f4b8a25 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1554,7 +1554,7 @@ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
 
 /*
  * rcu_start_this_gp - Request the start of a particular grace period
- * @rnp: The leaf node of the CPU from which to start.
+ * @rnp_start: The leaf node of the CPU from which to start.
  * @rdp: The rcu_data corresponding to the CPU from which to start.
  * @gp_seq_req: The gp_seq of the grace period to start.
  *
@@ -1568,74 +1568,74 @@ static void trace_rcu_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
  *
  * Returns true if the GP thread needs to be awakened else false.
  */
-static bool rcu_start_this_gp(struct rcu_node *rnp, struct rcu_data *rdp,
+static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 			      unsigned long gp_seq_req)
 {
 	bool ret = false;
 	struct rcu_state *rsp = rdp->rsp;
-	struct rcu_node *rnp_root;
+	struct rcu_node *rnp;
 
 	/*
 	 * Use funnel locking to either acquire the root rcu_node
 	 * structure's lock or bail out if the need for this grace period
-	 * has already been recorded -- or has already started.  If there
-	 * is already a grace period in progress in a non-leaf node, no
-	 * recording is needed because the end of the grace period will
-	 * scan the leaf rcu_node structures.  Note that rnp->lock must
-	 * not be released.
+	 * has already been recorded -- or if that grace period has in
+	 * fact already started.  If there is already a grace period in
+	 * progress in a non-leaf node, no recording is needed because the
+	 * end of the grace period will scan the leaf rcu_node structures.
+	 * Note that rnp_start->lock must not be released.
 	 */
-	raw_lockdep_assert_held_rcu_node(rnp);
-	trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startleaf"));
-	for (rnp_root = rnp; 1; rnp_root = rnp_root->parent) {
-		if (rnp_root != rnp)
-			raw_spin_lock_rcu_node(rnp_root);
-		if (ULONG_CMP_GE(rnp_root->gp_seq_needed, gp_seq_req) ||
-		    rcu_seq_started(&rnp_root->gp_seq, gp_seq_req) ||
-		    (rnp != rnp_root &&
-		     rcu_seq_state(rcu_seq_current(&rnp_root->gp_seq)))) {
-			trace_rcu_this_gp(rnp_root, rdp, gp_seq_req,
+	raw_lockdep_assert_held_rcu_node(rnp_start);
+	trace_rcu_this_gp(rnp_start, rdp, gp_seq_req, TPS("Startleaf"));
+	for (rnp = rnp_start; 1; rnp = rnp->parent) {
+		if (rnp != rnp_start)
+			raw_spin_lock_rcu_node(rnp);
+		if (ULONG_CMP_GE(rnp->gp_seq_needed, gp_seq_req) ||
+		    rcu_seq_started(&rnp->gp_seq, gp_seq_req) ||
+		    (rnp != rnp_start &&
+		     rcu_seq_state(rcu_seq_current(&rnp->gp_seq)))) {
+			trace_rcu_this_gp(rnp, rdp, gp_seq_req,
 					  TPS("Prestarted"));
 			goto unlock_out;
 		}
-		rnp_root->gp_seq_needed = gp_seq_req;
-		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
+		rnp->gp_seq_needed = gp_seq_req;
+		if (rcu_seq_state(rcu_seq_current(&rnp_start->gp_seq))) {
 			/*
 			 * We just marked the leaf, and a grace period
 			 * is in progress, which means that rcu_gp_cleanup()
 			 * will see the marking.  Bail to reduce contention.
 			 */
-			trace_rcu_this_gp(rnp, rdp, gp_seq_req,
+			trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
 					  TPS("Startedleaf"));
 			goto unlock_out;
 		}
-		if (rnp_root != rnp && rnp_root->parent != NULL)
-			raw_spin_unlock_rcu_node(rnp_root);
-		if (!rnp_root->parent)
+		if (rnp != rnp_start && rnp->parent != NULL)
+			raw_spin_unlock_rcu_node(rnp);
+		if (!rnp->parent)
 			break;  /* At root, and perhaps also leaf. */
 	}
 
 	/* If GP already in progress, just leave, otherwise start one. */
 	if (rcu_gp_in_progress(rsp)) {
-		trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("Startedleafroot"));
+		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedleafroot"));
 		goto unlock_out;
 	}
-	trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("Startedroot"));
+	trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("Startedroot"));
 	WRITE_ONCE(rsp->gp_flags, rsp->gp_flags | RCU_GP_FLAG_INIT);
 	rsp->gp_req_activity = jiffies;
 	if (!rsp->gp_kthread) {
-		trace_rcu_this_gp(rnp_root, rdp, gp_seq_req, TPS("NoGPkthread"));
+		trace_rcu_this_gp(rnp, rdp, gp_seq_req, TPS("NoGPkthread"));
 		goto unlock_out;
 	}
 	trace_rcu_grace_period(rsp->name, READ_ONCE(rsp->gp_seq), TPS("newreq"));
 	ret = true;  /* Caller must wake GP kthread. */
 unlock_out:
 	/* Push furthest requested GP to leaf node and rcu_data structure. */
-	if (ULONG_CMP_LT(gp_seq_req, rnp_root->gp_seq_needed)) {
-		rnp->gp_seq_needed = rnp_root->gp_seq_needed;
-		rdp->gp_seq_needed = rnp_root->gp_seq_needed;
+	if (ULONG_CMP_LT(gp_seq_req, rnp->gp_seq_needed)) {
+		rnp_start->gp_seq_needed = rnp->gp_seq_needed;
+		rdp->gp_seq_needed = rnp->gp_seq_needed;
 	}
-	if (rnp != rnp_root)
-		raw_spin_unlock_rcu_node(rnp_root);
+	if (rnp != rnp_start)
+		raw_spin_unlock_rcu_node(rnp);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 226ca5e76692e2c82c17e8e8eedab22043f6ffee Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Tue, 22 May 2018 23:38:15 -0700
Subject: rcu: Identify grace period is in progress as we advance up the tree

There's no need to keep checking the same starting node for whether a
grace period is in progress as we advance up the funnel lock loop. Its
sufficient if we just checked it in the start, and then subsequently
checked the internal nodes as we advanced up the combining tree. This
also makes sense because the grace-period updates propogate from the
root to the leaf, so there's a chance we may find a grace period has
started as we advance up, lets check for the same.

Reported-by: Paul McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 1af58f4b8a25..a6863b813f0c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1598,11 +1598,12 @@ static bool rcu_start_this_gp(struct rcu_node *rnp_start, struct rcu_data *rdp,
 			goto unlock_out;
 		}
 		rnp->gp_seq_needed = gp_seq_req;
-		if (rcu_seq_state(rcu_seq_current(&rnp_start->gp_seq))) {
+		if (rcu_seq_state(rcu_seq_current(&rnp->gp_seq))) {
 			/*
-			 * We just marked the leaf, and a grace period
-			 * is in progress, which means that rcu_gp_cleanup()
-			 * will see the marking.  Bail to reduce contention.
+			 * We just marked the leaf or internal node, and a
+			 * grace period is in progress, which means that
+			 * rcu_gp_cleanup() will see the marking.  Bail to
+			 * reduce contention.
 			 */
 			trace_rcu_this_gp(rnp_start, rdp, gp_seq_req,
 					  TPS("Startedleaf"));
-- 
cgit v1.2.3


From 962aff03c315b508d980422db5b49b49e4382119 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 2 May 2018 12:49:21 -0700
Subject: rcu: Clean up handling of tasks blocked across full-rcu_node offline

Commit 0aa04b055e71 ("rcu: Process offlining and onlining only at
grace-period start") deferred handling of CPU-hotplug events until the
start of the next grace period, but consider the following sequence
of events:

1.	A task is preempted within an RCU-preempt read-side critical
	section.

2.	The CPU that this task was running on goes offline, along with all
	other CPUs sharing the corresponding leaf rcu_node structure.

3.	The task resumes execution.

4.	One of those CPUs comes back online before a new grace period starts.

In step 2, the code in the next rcu_gp_init() invocation will (correctly)
defer removing the leaf rcu_node structure from the upper-level bitmasks,
and will (correctly) set that structure's ->wait_blkd_tasks field.  During
the ensuing interval, RCU will (correctly) track the tasks preempted on
that structure because they must block any subsequent grace period.

In step 3, the code in rcu_read_unlock_special() will (correctly) remove
the task from the leaf rcu_node structure.  From this point forward, RCU
need not pay attention to this structure, at least not until one of the
corresponding CPUs comes back online.

In step 4, the code in the next rcu_gp_init() invocation will
(incorrectly) invoke rcu_init_new_rnp().  This is incorrect because
the corresponding rcu_cleanup_dead_rnp() was never invoked.  This is
nevertheless harmless because the upper-level bits are still set.
So, no harm, no foul, right?

At least, all is well until a little further into rcu_gp_init()
invocation, which will notice that there are no longer any tasks blocked
on the leaf rcu_node structure, conclude that there is no longer anything
left over from step 2's offline operation, and will therefore invoke
rcu_cleanup_dead_rnp().  But this invocation of rcu_cleanup_dead_rnp()
is for the beginning of the earlier offline interval, and the previous
invocation of rcu_init_new_rnp() is for the end of that same interval.
That is right, they are invoked out of order.

That cannot be good, can it?

It turns out that this is not a (correctness!) problem because
rcu_cleanup_dead_rnp() checks to see if any of the corresponding CPUs
are online, and refuses to do anything if so.  In other words, in the
case where rcu_init_new_rnp() and rcu_cleanup_dead_rnp() execute out of
order, they both have no effect.

But this is at best an accident waiting to happen.

This commit therefore adds logic to rcu_gp_init() so that
rcu_init_new_rnp() and rcu_cleanup_dead_rnp() are always invoked in
order, and so that neither are invoked at all in cases where RCU had to
pay attention to the leaf rcu_node structure during the entire time that
all corresponding CPUs were offline.

And, while in the area, this commit reduces confusion by using formal
parameters rather than local variables that just happen to have the same
value at that particular point in the code.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a6863b813f0c..9a5ba6db7b60 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1909,12 +1909,14 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 
 		/* If zero-ness of ->qsmaskinit changed, propagate up tree. */
 		if (!oldmask != !rnp->qsmaskinit) {
-			if (!oldmask) /* First online CPU for this rcu_node. */
-				rcu_init_new_rnp(rnp);
-			else if (rcu_preempt_has_tasks(rnp)) /* blocked tasks */
-				rnp->wait_blkd_tasks = true;
-			else /* Last offline CPU and can propagate. */
+			if (!oldmask) { /* First online CPU for rcu_node. */
+				if (!rnp->wait_blkd_tasks) /* Ever offline? */
+					rcu_init_new_rnp(rnp);
+			} else if (rcu_preempt_has_tasks(rnp)) {
+				rnp->wait_blkd_tasks = true; /* blocked tasks */
+			} else { /* Last offline CPU and can propagate. */
 				rcu_cleanup_dead_rnp(rnp);
+			}
 		}
 
 		/*
@@ -1923,14 +1925,13 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		 * still offline, propagate up the rcu_node tree and
 		 * clear ->wait_blkd_tasks.  Otherwise, if one of this
 		 * rcu_node structure's CPUs has since come back online,
-		 * simply clear ->wait_blkd_tasks (but rcu_cleanup_dead_rnp()
-		 * checks for this, so just call it unconditionally).
+		 * simply clear ->wait_blkd_tasks.
 		 */
 		if (rnp->wait_blkd_tasks &&
-		    (!rcu_preempt_has_tasks(rnp) ||
-		     rnp->qsmaskinit)) {
+		    (!rcu_preempt_has_tasks(rnp) || rnp->qsmaskinit)) {
 			rnp->wait_blkd_tasks = false;
-			rcu_cleanup_dead_rnp(rnp);
+			if (!rnp->qsmaskinit)
+				rcu_cleanup_dead_rnp(rnp);
 		}
 
 		raw_spin_unlock_irq_rcu_node(rnp);
@@ -2450,9 +2451,10 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 	long mask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	raw_lockdep_assert_held_rcu_node(rnp);
+	raw_lockdep_assert_held_rcu_node(rnp_leaf);
 	if (!IS_ENABLED(CONFIG_HOTPLUG_CPU) ||
-	    rnp->qsmaskinit || rcu_preempt_has_tasks(rnp))
+	    WARN_ON_ONCE(rnp_leaf->qsmaskinit) ||
+	    WARN_ON_ONCE(rcu_preempt_has_tasks(rnp_leaf)))
 		return;
 	for (;;) {
 		mask = rnp->grpmask;
@@ -2461,7 +2463,8 @@ static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf)
 			break;
 		raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
 		rnp->qsmaskinit &= ~mask;
-		rnp->qsmask &= ~mask;
+		/* Between grace periods, so better already be zero! */
+		WARN_ON_ONCE(rnp->qsmask);
 		if (rnp->qsmaskinit) {
 			raw_spin_unlock_rcu_node(rnp);
 			/* irqs remain disabled. */
@@ -3479,6 +3482,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 	struct rcu_node *rnp = rnp_leaf;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
+	WARN_ON_ONCE(rnp->wait_blkd_tasks);
 	for (;;) {
 		mask = rnp->grpmask;
 		rnp = rnp->parent;
-- 
cgit v1.2.3


From c50cbe535c972150c2caf923239ef77e85c5ad60 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 2 May 2018 13:51:57 -0700
Subject: rcu: Fix an obsolete ->qsmaskinit comment

Back in the old days, when grace-period initialization blocked CPU
hotplug, the ->qsmaskinit mask was indeed updated at the time that
a given CPU went offline.  However, with the deferral of these updates
until the beginning of the next grace period in commit 0aa04b055e71
("rcu: Process offlining and onlining only at grace-period start"),
it is instead ->qsmaskinitnext that gets updated at that time.

This commit therefore updates the obsolete comment.  It also fixes
punctuation while on the topic of comments mentioning ->qsmaskinit.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9a5ba6db7b60..05f69b787a57 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2438,7 +2438,7 @@ static void rcu_cleanup_dying_cpu(struct rcu_state *rsp)
  * This function therefore goes up the tree of rcu_node structures,
  * clearing the corresponding bits in the ->qsmaskinit fields.  Note that
  * the leaf rcu_node structure's ->qsmaskinit field has already been
- * updated
+ * updated.
  *
  * This function does check that the specified rcu_node structure has
  * all CPUs offline and no blocked tasks, so it is OK to invoke it
@@ -3709,7 +3709,7 @@ void rcu_cpu_starting(unsigned int cpu)
 #ifdef CONFIG_HOTPLUG_CPU
 /*
  * The CPU is exiting the idle loop into the arch_cpu_idle_dead()
- * function.  We now remove it from the rcu_node tree's ->qsmaskinit
+ * function.  We now remove it from the rcu_node tree's ->qsmaskinitnext
  * bit masks.
  */
 static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
-- 
cgit v1.2.3


From 8d672fa6bf68ffc36a0c5e4868499f86bbea2308 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 2 May 2018 14:46:43 -0700
Subject: rcu: Make rcu_init_new_rnp() stop upon already-set bit

Currently, rcu_init_new_rnp() walks up the rcu_node combining tree,
setting bits in the ->qsmaskinit fields on the way up.  It walks up
unconditionally, regardless of the initial state of these bits.  This is
OK because only the corresponding RCU grace-period kthread ever tests
or sets these bits during runtime.  However, it is also pointless, and
it increases both memory and lock contention (albeit only slightly), so
this commit stops the walk as soon as an already-set bit is encountered.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 05f69b787a57..3fe854a15d82 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3479,9 +3479,10 @@ EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 {
 	long mask;
+	long oldmask;
 	struct rcu_node *rnp = rnp_leaf;
 
-	raw_lockdep_assert_held_rcu_node(rnp);
+	raw_lockdep_assert_held_rcu_node(rnp_leaf);
 	WARN_ON_ONCE(rnp->wait_blkd_tasks);
 	for (;;) {
 		mask = rnp->grpmask;
@@ -3489,8 +3490,11 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 		if (rnp == NULL)
 			return;
 		raw_spin_lock_rcu_node(rnp); /* Interrupts already disabled. */
+		oldmask = rnp->qsmaskinit;
 		rnp->qsmaskinit |= mask;
 		raw_spin_unlock_rcu_node(rnp); /* Interrupts remain disabled. */
+		if (oldmask)
+			return;
 	}
 }
 
-- 
cgit v1.2.3


From c74859d1eb2d8578bdf6d78ba893e394085aba1a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 27 Apr 2018 14:05:27 -0700
Subject: rcu: Make rcu_report_unblock_qs_rnp() warn on violated preconditions

If rcu_report_unblock_qs_rnp() is invoked on something other than
preemptible RCU or if there are still preempted tasks blocking the
current grace period, something went badly wrong in the caller.
This commit therefore adds WARN_ON_ONCE() to these conditions, but
leaving the legitimate reason for early exit (rnp->qsmask != 0)
unwarned.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3fe854a15d82..85417584ffd0 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2308,8 +2308,10 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 	struct rcu_node *rnp_p;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
-	if (rcu_state_p == &rcu_sched_state || rsp != rcu_state_p ||
-	    rnp->qsmask != 0 || rcu_preempt_blocked_readers_cgp(rnp)) {
+	if (WARN_ON_ONCE(rcu_state_p == &rcu_sched_state) ||
+	    WARN_ON_ONCE(rsp != rcu_state_p) ||
+	    WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)) ||
+	    rnp->qsmask != 0) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;  /* Still need more quiescent states! */
 	}
-- 
cgit v1.2.3


From 77cfc7bf24ba0ba37be54e224007847d485a860f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 15:00:10 -0700
Subject: rcu: Fix typo and add additional debug

This commit fixes a typo and adds some additional debugging to the
message emitted when a task blocking the current grace period is listed
as blocking it when either that grace period ends or the next grace
period begins.  This commit also reformats the console message for
readability.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        |  1 +
 kernel/rcu/tree_plugin.h | 10 ++++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 85417584ffd0..a4277c1087d9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2316,6 +2316,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
 		return;  /* Still need more quiescent states! */
 	}
 
+	rnp->completedqs = rnp->gp_seq;
 	rnp_p = rnp->parent;
 	if (rnp_p == NULL) {
 		/*
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 3a6e04103de1..677b0c9f548d 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -856,8 +856,14 @@ static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 	struct list_head *lhp;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
-	pr_info("%s: grp: %d-%d level: %d ->qamask %#lx ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p &->blkd_tasks: %p offset: %u\n", __func__, rnp->grplo, rnp->grphi, rnp->level, rnp->qsmask, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks, &rnp->blkd_tasks, (unsigned int)offsetof(typeof(*rnp), blkd_tasks));
-	pr_cont("\t->blkd_tasks");
+	pr_info("%s: grp: %d-%d level: %d ->gp_seq %#lx ->completedqs %#lx\n",
+		__func__, rnp->grplo, rnp->grphi, rnp->level,
+		rnp->gp_seq, rnp->completedqs);
+	pr_info("%s: ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
+		__func__, rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext);
+	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
+		__func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
+	pr_info("%s: ->blkd_tasks", __func__);
 	i = 0;
 	list_for_each(lhp, &rnp->blkd_tasks) {
 		pr_cont(" %p", lhp);
-- 
cgit v1.2.3


From 91f63ced7dc4e80acd13386204327d5de00a672d Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 1 May 2018 15:05:45 -0700
Subject: rcu: Replace smp_wmb() with smp_store_release() for stall check

This commit gets rid of the smp_wmb() in record_gp_stall_check_time()
in favor of an smp_store_release().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a4277c1087d9..439228b79811 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1246,9 +1246,9 @@ static void record_gp_stall_check_time(struct rcu_state *rsp)
 	unsigned long j1;
 
 	rsp->gp_start = j;
-	smp_wmb(); /* Record start time before stall time. */
 	j1 = rcu_jiffies_till_stall_check();
-	WRITE_ONCE(rsp->jiffies_stall, j + j1);
+	/* Record ->gp_start before ->jiffies_stall. */
+	smp_store_release(&rsp->jiffies_stall, j + j1); /* ^^^ */
 	rsp->jiffies_resched = j + j1 / 2;
 	rsp->n_force_qs_gpstart = READ_ONCE(rsp->n_force_qs);
 }
-- 
cgit v1.2.3


From 928164351e700f91ab588f20fe470cac9db477a9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 2 May 2018 11:07:02 -0700
Subject: rcu: Prevent useless FQS scan after all CPUs have checked in

The force_qs_rnp() function checks for ->qsmask being all zero, that is,
all CPUs for the current rcu_node structure having already passed through
quiescent states.  But with RCU-preempt, this is not sufficient to report
quiescent states further up the tree, so there are further checks that
can initiate RCU priority boosting and also for races with CPU-hotplug
operations.  However, if neither of these further checks apply, the code
proceeds to carry out a useless scan of an all-zero ->qsmask.

This commit therefore adds code to release the current rcu_node
structure's lock and continue on to the next rcu_node structure, thereby
avoiding this useless scan.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 439228b79811..3efd591fcd15 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2672,6 +2672,8 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 				/* rcu_report_unblock_qs_rnp() rlses ->lock */
 				continue;
 			}
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+			continue;
 		}
 		for_each_leaf_node_possible_cpu(rnp, cpu) {
 			unsigned long bit = leaf_node_cpu_bit(rnp, cpu);
-- 
cgit v1.2.3


From 5554788e1d4253a92b794a9006b7ae2c10be52af Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 May 2018 10:14:34 -0700
Subject: rcu: Suppress false-positive offline-CPU lockdep-RCU splat

The rcu_lockdep_current_cpu_online() function currently checks only the
RCU-sched data structures to determine whether or not RCU believes that a
given CPU is offline.  Unfortunately, there are multiple flavors of RCU,
which means that there is a short window of time during which the various
flavors disagree as to whether or not a given CPU is offline.  This can
result in false-positive lockdep-RCU splats in which some other flavor
of RCU tries to do something based on its view that the CPU is online,
only to get hit with a lockdep-RCU splat because RCU-sched instead
believes that the CPU is offline.

This commit therefore changes rcu_lockdep_current_cpu_online() to scan
all RCU flavors and to consider a given CPU to be online if any of the
RCU flavors believe it to be online, thus preventing these false-positive
splats.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 48 ++++++++++++++++++++++++------------------------
 1 file changed, 24 insertions(+), 24 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3efd591fcd15..a7773fc72b0c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1030,41 +1030,41 @@ void rcu_request_urgent_qs_task(struct task_struct *t)
 #if defined(CONFIG_PROVE_RCU) && defined(CONFIG_HOTPLUG_CPU)
 
 /*
- * Is the current CPU online?  Disable preemption to avoid false positives
- * that could otherwise happen due to the current CPU number being sampled,
- * this task being preempted, its old CPU being taken offline, resuming
- * on some other CPU, then determining that its old CPU is now offline.
- * It is OK to use RCU on an offline processor during initial boot, hence
- * the check for rcu_scheduler_fully_active.  Note also that it is OK
- * for a CPU coming online to use RCU for one jiffy prior to marking itself
- * online in the cpu_online_mask.  Similarly, it is OK for a CPU going
- * offline to continue to use RCU for one jiffy after marking itself
- * offline in the cpu_online_mask.  This leniency is necessary given the
- * non-atomic nature of the online and offline processing, for example,
- * the fact that a CPU enters the scheduler after completing the teardown
- * of the CPU.
+ * Is the current CPU online as far as RCU is concerned?
  *
- * This is also why RCU internally marks CPUs online during in the
- * preparation phase and offline after the CPU has been taken down.
+ * Disable preemption to avoid false positives that could otherwise
+ * happen due to the current CPU number being sampled, this task being
+ * preempted, its old CPU being taken offline, resuming on some other CPU,
+ * then determining that its old CPU is now offline.  Because there are
+ * multiple flavors of RCU, and because this function can be called in the
+ * midst of updating the flavors while a given CPU coming online or going
+ * offline, it is necessary to check all flavors.  If any of the flavors
+ * believe that given CPU is online, it is considered to be online.
  *
- * Disable checking if in an NMI handler because we cannot safely report
- * errors from NMI handlers anyway.
+ * Disable checking if in an NMI handler because we cannot safely
+ * report errors from NMI handlers anyway.  In addition, it is OK to use
+ * RCU on an offline processor during initial boot, hence the check for
+ * rcu_scheduler_fully_active.
  */
 bool rcu_lockdep_current_cpu_online(void)
 {
 	struct rcu_data *rdp;
 	struct rcu_node *rnp;
-	bool ret;
+	struct rcu_state *rsp;
 
-	if (in_nmi())
+	if (in_nmi() || !rcu_scheduler_fully_active)
 		return true;
 	preempt_disable();
-	rdp = this_cpu_ptr(&rcu_sched_data);
-	rnp = rdp->mynode;
-	ret = (rdp->grpmask & rcu_rnp_online_cpus(rnp)) ||
-	      !rcu_scheduler_fully_active;
+	for_each_rcu_flavor(rsp) {
+		rdp = this_cpu_ptr(rsp->rda);
+		rnp = rdp->mynode;
+		if (rdp->grpmask & rcu_rnp_online_cpus(rnp)) {
+			preempt_enable();
+			return true;
+		}
+	}
 	preempt_enable();
-	return ret;
+	return false;
 }
 EXPORT_SYMBOL_GPL(rcu_lockdep_current_cpu_online);
 
-- 
cgit v1.2.3


From fece27760ff57a0ca16c37e144f6a58a2f1851e9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 2 May 2018 20:04:12 -0700
Subject: rcu: Suppress false-positive preempted-task splats

Consider the following sequence of events in a PREEMPT=y kernel:

1.	All CPUs corresponding to a given rcu_node structure go offline.
	A new grace period starts just after the CPU-hotplug code path
	does its synchronize_rcu() for the last CPU, so at least this
	CPU is present in that structure's ->qsmask.

2.	Before the grace period ends, a CPU comes back online, and not
	just any CPU, but the one corresponding to a non-zero bit in
	the leaf rcu_node structure's ->qsmask.

3.	A task running on the newly onlined CPU is preempted while in
	an RCU read-side critical section.  Because this CPU's ->qsmask
	bit is net, not only does this task queue itself on the leaf
	rcu_node structure's ->blkd_tasks list, it also sets that
	structure's ->gp_tasks pointer to reference it.

4.	The grace period started in #1 above comes to an end.  This
	results in rcu_gp_cleanup() being invoked, which, among other
	things, checks to make sure that there are no tasks blocking the
	just-ended grace period, that is, that all ->gp_tasks pointers
	are NULL.  The ->gp_tasks pointer corresponding to the task
	preempted in #3 above is non-NULL, which results in a splat.

This splat is a false positive.  The task's RCU read-side critical
section cannot have begun before the just-ended grace period because
this would mean either: (1) The CPU came online before the grace period
started, which cannot have happened because the grace period started
before that CPU was all the way offline, or (2) The task started its
RCU read-side critical section on some other CPU, but then it would
have had to have been preempted before migrating to this CPU, which
would mean that it would have instead queued itself on that other CPU's
rcu_node structure.

This commit eliminates this false positive by adding code to the end
of rcu_cleanup_dying_idle_cpu() that reports a quiescent state to RCU,
which has the side-effect of clearing that CPU's ->qsmask bit, preventing
the above scenario.  This approach has the added benefit of more promptly
reporting quiescent states corresponding to offline CPUs.

Note well that the call to rcu_report_qs_rnp() reporting the quiescent
state must come -before- the clearing of this CPU's bit in the leaf
rcu_node structure's ->qsmaskinitnext field.  Otherwise, lockdep-RCU
will complain bitterly about quiescent states coming from an offline CPU.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a7773fc72b0c..72adf97458e3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3731,6 +3731,11 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+	if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
+		/* Report quiescent state -before- changing ->qsmaskinitnext! */
+		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
+	}
 	rnp->qsmaskinitnext &= ~mask;
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 }
-- 
cgit v1.2.3


From 99990da1b3c00f6c05a330e06a76b9dbc8416d7e Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 3 May 2018 09:45:00 -0700
Subject: rcu: Suppress more involved false-positive preempted-task splats

Consider the following sequence of events in a PREEMPT=y kernel:

1.	All but one of the CPUs corresponding to a given leaf rcu_node
	structure go offline.  Each of these CPUs clears its bit in that
	structure's ->qsmaskinitnext field.

2.	A new grace period starts, and rcu_gp_init() scans the leaf
	rcu_node structures, applying CPU-hotplug changes since the
	start of the previous grace period, including those changes in
	#1 above.  This copies each leaf structure's ->qsmaskinitnext
	to its ->qsmask field, which represents the CPUs that this new
	grace period will wait on.  Each copy operation is done holding
	the corresponding leaf rcu_node structure's ->lock, and at the
	end of this scan, rcu_gp_init() holds no locks.

3.	The last CPU corresponding to #1's leaf rcu_node structure goes
	offline, clearing its bit in that structure's ->qsmaskinitnext
	field, but not touching the ->qsmaskinit field.  Note that
	rcu_gp_init() is not currently holding any locks!  This CPU does
	-not- report a quiescent state because the grace period has not
	yet initialized itself sufficiently to have set any bits in any
	of the leaf rcu_node structures' ->qsmask fields.

4.	The rcu_gp_init() function continues initializing the new grace
	period, copying each leaf rcu_node structure's ->qsmaskinit
	field to its ->qsmask field while holding the corresponding ->lock.
	This sets the ->qsmask bit corresponding to #3's CPU.

5.	Before the grace period ends, #3's CPU comes back online.
	Because te grace period has not yet done any force-quiescent-state
	scans (which would report a quiescent state on behalf of any
	offline CPUs), this CPU's ->qsmask bit is still set.

6.	A task running on the newly onlined CPU is preempted while in
	an RCU read-side critical section.  Because this CPU's ->qsmask
	bit is net, not only does this task queue itself on the leaf
	rcu_node structure's ->blkd_tasks list, it also sets that
	structure's ->gp_tasks pointer to reference it.

7.	The grace period started in #1 above comes to an end.  This
	results in rcu_gp_cleanup() being invoked, which, among other
	things, checks to make sure that there are no tasks blocking the
	just-ended grace period, that is, that all ->gp_tasks pointers
	are NULL.  The ->gp_tasks pointer corresponding to the task
	preempted in #3 above is non-NULL, which results in a splat.

This splat is a false positive.  The task's RCU read-side critical
section cannot have begun before the just-ended grace period because
this would mean either: (1) The CPU came online before the grace period
started, which cannot have happened because the grace period started
before that CPU went offline, or (2) The task started its RCU read-side
critical section on some other CPU, but then it would have had to have
been preempted before migrating to this CPU, which would mean that it
would have instead queued itself on that other CPU's rcu_node structure.
RCU's grace periods thus are working correctly.  Or, more accurately,
that remaining bugs in RCU's grace periods are elsewhere.

This commit eliminates this false positive by adding code to the end
of rcu_cpu_starting() that reports a quiescent state to RCU, which has
the side-effect of clearing that CPU's ->qsmask bit, preventing the
above scenario.  This approach has the added benefit of more promptly
reporting quiescent states corresponding to offline CPUs.  Nevertheless,
this commit does -not- remove the need for the force-quiescent-state
scans to check for offline CPUs, given that a CPU might remain offline
indefinitely.  And without the checks in the force-quiescent-state scans,
the grace period would also persist indefinitely, which could result in
hangs or memory exhaustion.

Note well that the call to rcu_report_qs_rnp() reporting the quiescent
state must come -after- the setting of this CPU's bit in the leaf rcu_node
structure's ->qsmaskinitnext field.  Otherwise, lockdep-RCU will complain
bitterly about quiescent states coming from an offline CPU.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 72adf97458e3..6275ed3925e9 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3710,7 +3710,12 @@ void rcu_cpu_starting(unsigned int cpu)
 		nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
 		/* Allow lockless access for expedited grace periods. */
 		smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
-		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
+			/* Report QS -after- changing ->qsmaskinitnext! */
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		} else {
+			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+		}
 	}
 	smp_mb(); /* Ensure RCU read-side usage follows above initialization. */
 }
-- 
cgit v1.2.3


From 0b107d24d9361132758374a7b007c7c74efa007f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 8 May 2018 16:18:28 -0700
Subject: rcu: Suppress false-positive splats from mid-init task resume

Consider the following sequence of events in a PREEMPT=y kernel:

1.	All CPUs corresponding to a given leaf rcu_node structure are
	offline.

2.	The first phase of the rcu_gp_init() function's grace-period
	initialization runs, and sets that rcu_node structure's
	->qsmaskinit to zero, as it should.

3.	One of the CPUs corresponding to that rcu_node structure comes
	back online.  Note that because this CPU came online after the
	grace period started, this grace period can safely ignore this
	newly onlined CPU.

4.	A task running on the newly onlined CPU enters an RCU-preempt
	read-side critical section, and is then preempted.  Because
	the corresponding rcu_node structure's ->qsmask is zero,
	rcu_preempt_ctxt_queue() leaves the rcu_node structure's
	->gp_tasks field NULL, as it should.

5.	The rcu_gp_init() function continues running the second phase of
	grace-period initialization.  The ->qsmask field of the parent of
	the aforementioned leaf rcu_node structure is set to not expect
	a quiescent state from the leaf, as is only right and proper.

	However, when rcu_gp_init() reaches the leaf, it invokes
	rcu_preempt_check_blocked_tasks(), which sees that the leaf's
	->blkd_tasks list is non-empty, and therefore sets the leaf's
	->gp_tasks field to reference the first task on that list.

6.	The grace period ends before the preempted task resumes, which
	is perfectly fine, given that this grace period was under no
	obligation to wait for that task to exit its late-starting
	RCU-preempt read-side critical section.  Unfortunately, the
	leaf's ->gp_tasks field is non-NULL, so rcu_gp_cleanup() splats.
	After all, it appears to rcu_gp_cleanup() that the grace period
	failed to wait for a task that was supposed to be blocking that
	grace period.

This commit avoids this false-positive splat by adding a check of both
->qsmaskinit and ->wait_blkd_tasks to rcu_preempt_check_blocked_tasks().
If both ->qsmaskinit and ->wait_blkd_tasks are zero, then the task must
have entered its RCU-preempt read-side critical section late (after all,
the CPU that it is running on was not online at that time), which means
that the upper-level rcu_node structure won't be waiting for anything
on the leaf anyway.

If ->wait_blkd_tasks is non-zero, then there is at least one task on
ths rcu_node structure's ->blkd_tasks list whose RCU read-side
critical section predates the current grace period.  If ->qsmaskinit
is non-zero, there is at least one CPU that was online at the start
of the current grace period.  Thus, if both are zero, there is nothing
to wait for.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 677b0c9f548d..1c9a836af5b6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -703,7 +703,8 @@ static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
 	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
 		dump_blkd_tasks(rnp, 10);
-	if (rcu_preempt_has_tasks(rnp)) {
+	if (rcu_preempt_has_tasks(rnp) &&
+	    (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
 		t = container_of(rnp->gp_tasks, struct task_struct,
 				 rcu_node_entry);
-- 
cgit v1.2.3


From ec2c29765a4ab12c236ac5a89b89660222ff6b01 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 7 May 2018 09:34:17 -0700
Subject: rcu: Fix grace-period hangs from mid-init task resume

Without special fail-safe quiescent-state-propagation checks, grace-period
hangs can result from the following scenario:

1.	A task running on a given CPU is preempted in its RCU read-side
	critical section.

2.	That CPU goes offline, and there are now no online CPUs
	corresponding to that CPU's leaf rcu_node structure.

3.	The rcu_gp_init() function does the first phase of grace-period
	initialization, and sets the aforementioned leaf rcu_node
	structure's ->qsmaskinit field to all zeroes.  Because there
	is a blocked task, it does not propagate the zeroing of either
	->qsmaskinit or ->qsmaskinitnext up the rcu_node tree.

4.	The task resumes on some other CPU and exits its critical section.
	There is no grace period in progress, so the resulting quiescent
	state is not reported up the tree.

5.	The rcu_gp_init() function does the second phase of grace-period
	initialization, which results in the leaf rcu_node structure
	being initialized to expect no further quiescent states, but
	with that structure's parent expecting a quiescent-state report.

	The parent will never receive a quiescent state from this leaf
	rcu_node structure, so the grace period will hang, resulting in
	RCU CPU stall warnings.

It would be good to get rid of the special fail-safe quiescent-state
propagation checks.  This commit therefore checks the leaf rcu_node
structure's ->wait_blkd_tasks field during grace-period initialization.
If this flag is set, the rcu_report_qs_rnp() is invoked to immediately
report the possible quiescent state.  While in the neighborhood, this
commit also report quiescent states for any CPUs that went offline between
the two phases of grace-period initialization, thus reducing grace-period
delays and hopefully eventually allowing removal of offline-CPU checks
from the force-quiescent-state code path.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6275ed3925e9..7f872721c54e 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -154,6 +154,9 @@ EXPORT_SYMBOL_GPL(rcu_scheduler_active);
  */
 static int rcu_scheduler_fully_active __read_mostly;
 
+static void
+rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
+		  struct rcu_node *rnp, unsigned long gps, unsigned long flags);
 static void rcu_init_new_rnp(struct rcu_node *rnp_leaf);
 static void rcu_cleanup_dead_rnp(struct rcu_node *rnp_leaf);
 static void rcu_boost_kthread_setaffinity(struct rcu_node *rnp, int outgoingcpu);
@@ -1858,7 +1861,9 @@ static void rcu_gp_slow(struct rcu_state *rsp, int delay)
  */
 static bool rcu_gp_init(struct rcu_state *rsp)
 {
+	unsigned long flags;
 	unsigned long oldmask;
+	unsigned long mask;
 	struct rcu_data *rdp;
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
@@ -1951,7 +1956,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_init_delay);
-		raw_spin_lock_irq_rcu_node(rnp);
+		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1962,7 +1967,12 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		trace_rcu_grace_period_init(rsp->name, rnp->gp_seq,
 					    rnp->level, rnp->grplo,
 					    rnp->grphi, rnp->qsmask);
-		raw_spin_unlock_irq_rcu_node(rnp);
+		/* Quiescent states for tasks on any now-offline CPUs. */
+		mask = rnp->qsmask & ~rnp->qsmaskinitnext;
+		if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
+			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
+		else
+			raw_spin_unlock_irq_rcu_node(rnp);
 		cond_resched_tasks_rcu_qs();
 		WRITE_ONCE(rsp->gp_activity, jiffies);
 	}
@@ -2233,6 +2243,10 @@ static void rcu_report_qs_rsp(struct rcu_state *rsp, unsigned long flags)
  * is the grace-period snapshot, which means that the quiescent states
  * are valid only if rnp->gp_seq is equal to gps.  That structure's lock
  * must be held upon entry, and it is released before return.
+ *
+ * As a special case, if mask is zero, the bit-already-cleared check is
+ * disabled.  This allows propagating quiescent state due to resumed tasks
+ * during grace-period initialization.
  */
 static void
 rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
@@ -2246,7 +2260,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 
 	/* Walk up the rcu_node hierarchy. */
 	for (;;) {
-		if (!(rnp->qsmask & mask) || rnp->gp_seq != gps) {
+		if ((!(rnp->qsmask & mask) && mask) || rnp->gp_seq != gps) {
 
 			/*
 			 * Our bit has already been cleared, or the
-- 
cgit v1.2.3


From 1e64b15a4b102e1cd059d4d798b7a78f93341333 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 25 May 2018 19:23:09 -0700
Subject: rcu: Fix grace-period hangs due to race with CPU offline

Without special fail-safe quiescent-state-propagation checks, grace-period
hangs can result from the following scenario:

1.	CPU 1 goes offline.

2.	Because CPU 1 is the only CPU in the system blocking the current
	grace period, the grace period ends as soon as
	rcu_cleanup_dying_idle_cpu()'s call to rcu_report_qs_rnp()
	returns.

3.	At this point, the leaf rcu_node structure's ->lock is no longer
	held: rcu_report_qs_rnp() has released it, as it must in order
	to awaken the RCU grace-period kthread.

4.	At this point, that same leaf rcu_node structure's ->qsmaskinitnext
	field still records CPU 1 as being online.  This is absolutely
	necessary because the scheduler uses RCU (in this case on the
	wake-up path while awakening RCU's grace-period kthread), and
	->qsmaskinitnext contains RCU's idea as to which CPUs are online.
	Therefore, invoking rcu_report_qs_rnp() after clearing CPU 1's
	bit from ->qsmaskinitnext would result in a lockdep-RCU splat
	due to RCU being used from an offline CPU.

5.	RCU's grace-period kthread awakens, sees that the old grace period
	has completed and that a new one is needed.  It therefore starts
	a new grace period, but because CPU 1's leaf rcu_node structure's
	->qsmaskinitnext field still shows CPU 1 as being online, this new
	grace period is initialized to wait for a quiescent state from the
	now-offline CPU 1.

6.	Without the fail-safe force-quiescent-state checks, there would
	be no quiescent state from the now-offline CPU 1, which would
	eventually result in RCU CPU stall warnings and memory exhaustion.

It would be good to get rid of the special fail-safe quiescent-state
propagation checks, and thus it would be good to fix things so that
the above scenario cannot happen.  This commit therefore adds a new
->ofl_lock to the rcu_state structure.  This lock is held by rcu_gp_init()
across the applying of buffered online and offline operations to the
rcu_node tree, and it is also held by rcu_cleanup_dying_idle_cpu()
when buffering a new offline operation.  This prevents rcu_gp_init()
from acquiring the leaf rcu_node structure's lock during the interval
between when rcu_cleanup_dying_idle_cpu() invokes rcu_report_qs_rnp(),
which releases ->lock and the re-acquisition of that same lock.
This in turn prevents the failure scenario outlined above, and will
hopefully eventually allow removal of the offline-CPU checks from the
force-quiescent-state code path.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 6 ++++++
 kernel/rcu/tree.h | 4 ++++
 2 files changed, 10 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7f872721c54e..50e4f7ebf8cf 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -101,6 +101,7 @@ struct rcu_state sname##_state = { \
 	.abbr = sabbr, \
 	.exp_mutex = __MUTEX_INITIALIZER(sname##_state.exp_mutex), \
 	.exp_wake_mutex = __MUTEX_INITIALIZER(sname##_state.exp_wake_mutex), \
+	.ofl_lock = __SPIN_LOCK_UNLOCKED(sname##_state.ofl_lock), \
 }
 
 RCU_STATE_INITIALIZER(rcu_sched, 's', call_rcu_sched);
@@ -1900,11 +1901,13 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_preinit_delay);
+		spin_lock(&rsp->ofl_lock);
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
 		    !rnp->wait_blkd_tasks) {
 			/* Nothing to do on this leaf rcu_node structure. */
 			raw_spin_unlock_irq_rcu_node(rnp);
+			spin_unlock(&rsp->ofl_lock);
 			continue;
 		}
 
@@ -1940,6 +1943,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		}
 
 		raw_spin_unlock_irq_rcu_node(rnp);
+		spin_unlock(&rsp->ofl_lock);
 	}
 
 	/*
@@ -3749,6 +3753,7 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 
 	/* Remove outgoing CPU from mask in the leaf rcu_node structure. */
 	mask = rdp->grpmask;
+	spin_lock(&rsp->ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
 	if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
 		/* Report quiescent state -before- changing ->qsmaskinitnext! */
@@ -3757,6 +3762,7 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 	}
 	rnp->qsmaskinitnext &= ~mask;
 	raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
+	spin_unlock(&rsp->ofl_lock);
 }
 
 /*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 3def94fc9c74..6683da6e4ecc 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -363,6 +363,10 @@ struct rcu_state {
 	const char *name;			/* Name of structure. */
 	char abbr;				/* Abbreviated name. */
 	struct list_head flavors;		/* List of RCU flavors. */
+
+	spinlock_t ofl_lock ____cacheline_internodealigned_in_smp;
+						/* Synchronize offline with */
+						/*  GP pre-initialization. */
 };
 
 /* Values for rcu_state structure's gp_flags field. */
-- 
cgit v1.2.3


From 1f3e5f51b933cbc25e3da0cdbdac40716df04ddb Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 3 May 2018 10:35:33 -0700
Subject: rcu: Add RCU-preempt check for waiting on newly onlined CPU

RCU should only be waiting on CPUs that were online at the time that the
current grace period started.  Failure to abide by this rule can result
in confusing splats during grace-period cleanup and initialization.
This commit therefore adds a check to RCU-preempt's preempted-task
queuing that checks for waiting on newly onlined CPUs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 1c9a836af5b6..6b85ce936ad4 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -183,6 +183,9 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 	raw_lockdep_assert_held_rcu_node(rnp);
 	WARN_ON_ONCE(rdp->mynode != rnp);
 	WARN_ON_ONCE(!rcu_is_leaf_node(rnp));
+	/* RCU better not be waiting on newly onlined CPUs! */
+	WARN_ON_ONCE(rnp->qsmaskinitnext & ~rnp->qsmaskinit & rnp->qsmask &
+		     rdp->grpmask);
 
 	/*
 	 * Decide where to queue the newly blocked task.  In theory,
-- 
cgit v1.2.3


From f34f2f5852e556ee1c3b3b294571086b1791008a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 3 May 2018 13:40:25 -0700
Subject: rcu: Move grace-period pre-init delay after pre-init

The main race with the early part of grace-period initialization appears
to be with CPU hotplug.  To more fully open this race window, this commit
moves the rcu_gp_slow() from the beginning of the early initialization
loop to follow that loop, thus widening the race window, especially for
the rcu_node structures that are initialized last.  This commit also
expands rcutree.gp_preinit_delay from 3 to 12, giving the same overall
delay in the grace period, but concentrated in the spot where it will
do the most good.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c                                          | 2 +-
 tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 50e4f7ebf8cf..c577cadcc4f8 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1900,7 +1900,6 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * will handle subsequent offline CPUs.
 	 */
 	rcu_for_each_leaf_node(rsp, rnp) {
-		rcu_gp_slow(rsp, gp_preinit_delay);
 		spin_lock(&rsp->ofl_lock);
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (rnp->qsmaskinit == rnp->qsmaskinitnext &&
@@ -1945,6 +1944,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		raw_spin_unlock_irq_rcu_node(rnp);
 		spin_unlock(&rsp->ofl_lock);
 	}
+	rcu_gp_slow(rsp, gp_preinit_delay); /* Races with CPU hotplug. */
 
 	/*
 	 * Set the quiescent-state-needed bits in all the rcu_node
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
index 5d2cc0bd50a0..b79ddb9eb9e8 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
@@ -1,5 +1,5 @@
 rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
-rcutree.gp_preinit_delay=3
+rcutree.gp_preinit_delay=12
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
 rcutree.kthread_prio=2
-- 
cgit v1.2.3


From 17a8212b8de21ce1b9a91fb75c8a6fb337685b9a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 3 May 2018 14:30:02 -0700
Subject: rcu: Remove failsafe check for lost quiescent state

Now that quiescent-state reporting is fully event-driven, this commit
removes the check for a lost quiescent state from force_qs_rnp().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index c577cadcc4f8..770f0df54015 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2317,8 +2317,9 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
  * irqs disabled, and this lock is released upon return, but irqs remain
  * disabled.
  */
-static void rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
-				      struct rcu_node *rnp, unsigned long flags)
+static void __maybe_unused
+rcu_report_unblock_qs_rnp(struct rcu_state *rsp,
+			  struct rcu_node *rnp, unsigned long flags)
 	__releases(rnp->lock)
 {
 	unsigned long gps;
@@ -2679,17 +2680,6 @@ static void force_qs_rnp(struct rcu_state *rsp, int (*f)(struct rcu_data *rsp))
 				/* rcu_initiate_boost() releases rnp->lock */
 				continue;
 			}
-			if (rnp->parent &&
-			    (rnp->parent->qsmask & rnp->grpmask)) {
-				/*
-				 * Race between grace-period
-				 * initialization and task exiting RCU
-				 * read-side critical section: Report.
-				 */
-				rcu_report_unblock_qs_rnp(rsp, rnp, flags);
-				/* rcu_report_unblock_qs_rnp() rlses ->lock */
-				continue;
-			}
 			raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 			continue;
 		}
-- 
cgit v1.2.3


From e05121ba5b81e2f85349f038642410578457f6db Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 7 May 2018 12:07:48 -0700
Subject: rcu: Remove CPU-hotplug failsafe from force-quiescent-state code path

Now that quiescent states for newly offlined CPUs are reported either
when that CPU goes offline or at the end of grace-period initialization,
the CPU-hotplug failsafe in the force-quiescent-state code path is no
longer needed.

This commit therefore removes this failsafe.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/trace/events/rcu.h | 10 +++++-----
 kernel/rcu/tree.c          |  9 +--------
 kernel/rcu/tree.h          |  1 -
 3 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/include/trace/events/rcu.h b/include/trace/events/rcu.h
index 759e7e83733d..a8d07feff6a0 100644
--- a/include/trace/events/rcu.h
+++ b/include/trace/events/rcu.h
@@ -391,11 +391,11 @@ TRACE_EVENT(rcu_quiescent_state_report,
 
 /*
  * Tracepoint for quiescent states detected by force_quiescent_state().
- * These trace events include the type of RCU, the grace-period number that
- * was blocked by the CPU, the CPU itself, and the type of quiescent state,
- * which can be "dti" for dyntick-idle mode, "ofl" for CPU offline, "kick"
- * when kicking a CPU that has been in dyntick-idle mode for too long, or
- * "rqc" if the CPU got a quiescent state via its rcu_qs_ctr.
+ * These trace events include the type of RCU, the grace-period number
+ * that was blocked by the CPU, the CPU itself, and the type of quiescent
+ * state, which can be "dti" for dyntick-idle mode, "kick" when kicking
+ * a CPU that has been in dyntick-idle mode for too long, or "rqc" if the
+ * CPU got a quiescent state via its rcu_qs_ctr.
  */
 TRACE_EVENT(rcu_fqs,
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 770f0df54015..5f1a11f1f7bc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1188,14 +1188,6 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		smp_store_release(ruqp, true);
 	}
 
-	/* Check for the CPU being offline. */
-	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp))) {
-		trace_rcu_fqs(rdp->rsp->name, rdp->gp_seq, rdp->cpu, TPS("ofl"));
-		rdp->offline_fqs++;
-		rcu_gpnum_ovf(rnp, rdp);
-		return 1;
-	}
-
 	/*
 	 * A CPU running for an extended time within the kernel can
 	 * delay RCU grace periods.  When the CPU is in NO_HZ_FULL mode,
@@ -3718,6 +3710,7 @@ void rcu_cpu_starting(unsigned int cpu)
 		nbits = bitmap_weight(&oldmask, BITS_PER_LONG);
 		/* Allow lockless access for expedited grace periods. */
 		smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
+		rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
 		if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
 			/* Report QS -after- changing ->qsmaskinitnext! */
 			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 6683da6e4ecc..795d469c6f67 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -217,7 +217,6 @@ struct rcu_data {
 
 	/* 4) reasons this CPU needed to be kicked by force_quiescent_state */
 	unsigned long dynticks_fqs;	/* Kicked due to dynticks idle. */
-	unsigned long offline_fqs;	/* Kicked due to being offline. */
 	unsigned long cond_resched_completed;
 					/* Grace period that needs help */
 					/*  from cond_resched(). */
-- 
cgit v1.2.3


From ff3cee39088b1931a432587059d66cd505f785dc Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 8 May 2018 12:50:14 -0700
Subject: rcu: Add up-tree information to dump_blkd_tasks() diagnostics

This commit updates dump_blkd_tasks() to print out quiescent-state
bitmasks for the rcu_node structures further up the tree.  This
information helps debugging of interactions between CPU-hotplug
operations and RCU grace-period initialization.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6b85ce936ad4..f45ff97b0d51 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -858,13 +858,15 @@ static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 {
 	int i;
 	struct list_head *lhp;
+	struct rcu_node *rnp1;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
-	pr_info("%s: grp: %d-%d level: %d ->gp_seq %#lx ->completedqs %#lx\n",
+	pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
 		__func__, rnp->grplo, rnp->grphi, rnp->level,
-		rnp->gp_seq, rnp->completedqs);
-	pr_info("%s: ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
-		__func__, rnp->qsmask, rnp->qsmaskinit, rnp->qsmaskinitnext);
+		(long)rnp->gp_seq, (long)rnp->completedqs);
+	for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+		pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx\n",
+			__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext);
 	pr_info("%s: ->gp_tasks %p ->boost_tasks %p ->exp_tasks %p\n",
 		__func__, rnp->gp_tasks, rnp->boost_tasks, rnp->exp_tasks);
 	pr_info("%s: ->blkd_tasks", __func__);
-- 
cgit v1.2.3


From 577389423187d8b51dfe6199297e579a3419b72b Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 8 May 2018 14:18:57 -0700
Subject: rcu: Add CPU online/offline state to dump_blkd_tasks()

Interactions between CPU-hotplug operations and grace-period
initialization can result in dump_blkd_tasks().  One of the first
debugging actions in this case is to search back in dmesg to work
out which of the affected rcu_node structure's CPUs are online and to
determine the last CPU-hotplug operation affecting any of those CPUs.
This can be laborious and error-prone, especially when console output
is lost.

This commit therefore causes dump_blkd_tasks() to dump the state of
the affected rcu_node structure's CPUs and the last grace period during
which the last offline and online operation affected each of these CPUs.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c        | 12 ++++++++++--
 kernel/rcu/tree.h        | 12 +++++++++---
 kernel/rcu/tree_plugin.h | 25 ++++++++++++++++++++-----
 3 files changed, 39 insertions(+), 10 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 5f1a11f1f7bc..a2503ef1bbe2 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1954,7 +1954,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 		rcu_gp_slow(rsp, gp_init_delay);
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
 		rdp = this_cpu_ptr(rsp->rda);
-		rcu_preempt_check_blocked_tasks(rnp);
+		rcu_preempt_check_blocked_tasks(rsp, rnp);
 		rnp->qsmask = rnp->qsmaskinit;
 		WRITE_ONCE(rnp->gp_seq, rsp->gp_seq);
 		if (rnp == rdp->mynode)
@@ -2063,7 +2063,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq_rcu_node(rnp);
 		if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
-			dump_blkd_tasks(rnp, 10);
+			dump_blkd_tasks(rsp, rnp, 10);
 		WARN_ON_ONCE(rnp->qsmask);
 		WRITE_ONCE(rnp->gp_seq, new_gp_seq);
 		rdp = this_cpu_ptr(rsp->rda);
@@ -3516,6 +3516,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	rdp->dynticks = &per_cpu(rcu_dynticks, cpu);
 	WARN_ON_ONCE(rdp->dynticks->dynticks_nesting != 1);
 	WARN_ON_ONCE(rcu_dynticks_in_eqs(rcu_dynticks_snap(rdp->dynticks)));
+	rdp->rcu_ofl_gp_seq = rsp->gp_seq;
+	rdp->rcu_ofl_gp_flags = RCU_GP_CLEANED;
+	rdp->rcu_onl_gp_seq = rsp->gp_seq;
+	rdp->rcu_onl_gp_flags = RCU_GP_CLEANED;
 	rdp->cpu = cpu;
 	rdp->rsp = rsp;
 	rcu_boot_init_nocb_percpu_data(rdp);
@@ -3711,6 +3715,8 @@ void rcu_cpu_starting(unsigned int cpu)
 		/* Allow lockless access for expedited grace periods. */
 		smp_store_release(&rsp->ncpus, rsp->ncpus + nbits); /* ^^^ */
 		rcu_gpnum_ovf(rnp, rdp); /* Offline-induced counter wrap? */
+		rdp->rcu_onl_gp_seq = READ_ONCE(rsp->gp_seq);
+		rdp->rcu_onl_gp_flags = READ_ONCE(rsp->gp_flags);
 		if (rnp->qsmask & mask) { /* RCU waiting on incoming CPU? */
 			/* Report QS -after- changing ->qsmaskinitnext! */
 			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
@@ -3738,6 +3744,8 @@ static void rcu_cleanup_dying_idle_cpu(int cpu, struct rcu_state *rsp)
 	mask = rdp->grpmask;
 	spin_lock(&rsp->ofl_lock);
 	raw_spin_lock_irqsave_rcu_node(rnp, flags); /* Enforce GP memory-order guarantee. */
+	rdp->rcu_ofl_gp_seq = READ_ONCE(rsp->gp_seq);
+	rdp->rcu_ofl_gp_flags = READ_ONCE(rsp->gp_flags);
 	if (rnp->qsmask & mask) { /* RCU waiting on outgoing CPU? */
 		/* Report quiescent state -before- changing ->qsmaskinitnext! */
 		rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 795d469c6f67..f52bc059bfec 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -255,12 +255,16 @@ struct rcu_data {
 					/* Leader CPU takes GP-end wakeups. */
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
 
-	/* 7) RCU CPU stall data. */
+	/* 7) Diagnostic data, including RCU CPU stall warnings. */
 	unsigned int softirq_snap;	/* Snapshot of softirq activity. */
 	/* ->rcu_iw* fields protected by leaf rcu_node ->lock. */
 	struct irq_work rcu_iw;		/* Check for non-irq activity. */
 	bool rcu_iw_pending;		/* Is ->rcu_iw pending? */
 	unsigned long rcu_iw_gp_seq;	/* ->gp_seq associated with ->rcu_iw. */
+	unsigned long rcu_ofl_gp_seq;	/* ->gp_seq at last offline. */
+	short rcu_ofl_gp_flags;		/* ->gp_flags at last offline. */
+	unsigned long rcu_onl_gp_seq;	/* ->gp_seq at last online. */
+	short rcu_onl_gp_flags;		/* ->gp_flags at last online. */
 
 	int cpu;
 	struct rcu_state *rsp;
@@ -431,11 +435,13 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
 static void rcu_print_detail_task_stall(struct rcu_state *rsp);
 static int rcu_print_task_stall(struct rcu_node *rnp);
 static int rcu_print_task_exp_stall(struct rcu_node *rnp);
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp);
+static void rcu_preempt_check_blocked_tasks(struct rcu_state *rsp,
+					    struct rcu_node *rnp);
 static void rcu_preempt_check_callbacks(void);
 void call_rcu(struct rcu_head *head, rcu_callback_t func);
 static void __init __rcu_init_preempt(void);
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck);
+static void dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp,
+			    int ncheck);
 static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags);
 static void rcu_preempt_boost_start_gp(struct rcu_node *rnp);
 static void invoke_rcu_callbacks_kthread(void);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index f45ff97b0d51..613372246a07 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -699,13 +699,14 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * Also, if there are blocked tasks on the list, they automatically
  * block the newly created grace period, so set up ->gp_tasks accordingly.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	struct task_struct *t;
 
 	RCU_LOCKDEP_WARN(preemptible(), "rcu_preempt_check_blocked_tasks() invoked with preemption enabled!!!\n");
 	if (WARN_ON_ONCE(rcu_preempt_blocked_readers_cgp(rnp)))
-		dump_blkd_tasks(rnp, 10);
+		dump_blkd_tasks(rsp, rnp, 10);
 	if (rcu_preempt_has_tasks(rnp) &&
 	    (rnp->qsmaskinit || rnp->wait_blkd_tasks)) {
 		rnp->gp_tasks = rnp->blkd_tasks.next;
@@ -854,10 +855,14 @@ void exit_rcu(void)
  * Dump the blocked-tasks state, but limit the list dump to the
  * specified number of elements.
  */
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
 {
+	int cpu;
 	int i;
 	struct list_head *lhp;
+	bool onl;
+	struct rcu_data *rdp;
 	struct rcu_node *rnp1;
 
 	raw_lockdep_assert_held_rcu_node(rnp);
@@ -877,6 +882,14 @@ static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
 			break;
 	}
 	pr_cont("\n");
+	for (cpu = rnp->grplo; cpu <= rnp->grphi; cpu++) {
+		rdp = per_cpu_ptr(rsp->rda, cpu);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("\t%d: %c online: %ld(%d) offline: %ld(%d)\n",
+			cpu, ".o"[onl],
+			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+	}
 }
 
 #else /* #ifdef CONFIG_PREEMPT_RCU */
@@ -949,7 +962,8 @@ static int rcu_print_task_exp_stall(struct rcu_node *rnp)
  * so there is no need to check for blocked tasks.  So check only for
  * bogus qsmask values.
  */
-static void rcu_preempt_check_blocked_tasks(struct rcu_node *rnp)
+static void
+rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
 {
 	WARN_ON_ONCE(rnp->qsmask);
 }
@@ -990,7 +1004,8 @@ void exit_rcu(void)
 /*
  * Dump the guaranteed-empty blocked-tasks state.  Trust but verify.
  */
-static void dump_blkd_tasks(struct rcu_node *rnp, int ncheck)
+static void
+dump_blkd_tasks(struct rcu_state *rsp, struct rcu_node *rnp, int ncheck)
 {
 	WARN_ON_ONCE(!list_empty(&rnp->blkd_tasks));
 }
-- 
cgit v1.2.3


From fea3f222d3523dfdd0e86b11227d3cda20765102 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 May 2018 15:47:30 -0700
Subject: rcu: Record ->gp_state for both phases of grace-period initialization

Grace-period initialization first processes any recent CPU-hotplug
operations, and then initializes state for the new grace period.  These
two phases of initialization are currently not distinguished in debug
prints, but the distinction is valuable in a number of debug situations.
This commit therefore introduces two new values for ->gp_state,
RCU_GP_ONOFF and RCU_GP_INIT, in order to make this distinction.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c |  2 ++
 kernel/rcu/tree.h | 12 ++++++++----
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index a2503ef1bbe2..ee218d743226 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1891,6 +1891,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * for subsequent online CPUs, and that quiescent-state forcing
 	 * will handle subsequent offline CPUs.
 	 */
+	rsp->gp_state = RCU_GP_ONOFF;
 	rcu_for_each_leaf_node(rsp, rnp) {
 		spin_lock(&rsp->ofl_lock);
 		raw_spin_lock_irq_rcu_node(rnp);
@@ -1950,6 +1951,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 	 * The grace period cannot complete until the initialization
 	 * process finishes, because this kthread handles both.
 	 */
+	rsp->gp_state = RCU_GP_INIT;
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		rcu_gp_slow(rsp, gp_init_delay);
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index f52bc059bfec..8077aff7ab40 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -380,16 +380,20 @@ struct rcu_state {
 #define RCU_GP_IDLE	 0	/* Initial state and no GP in progress. */
 #define RCU_GP_WAIT_GPS  1	/* Wait for grace-period start. */
 #define RCU_GP_DONE_GPS  2	/* Wait done for grace-period start. */
-#define RCU_GP_WAIT_FQS  3	/* Wait for force-quiescent-state time. */
-#define RCU_GP_DOING_FQS 4	/* Wait done for force-quiescent-state time. */
-#define RCU_GP_CLEANUP   5	/* Grace-period cleanup started. */
-#define RCU_GP_CLEANED   6	/* Grace-period cleanup complete. */
+#define RCU_GP_ONOFF     3	/* Grace-period initialization hotplug. */
+#define RCU_GP_INIT      4	/* Grace-period initialization. */
+#define RCU_GP_WAIT_FQS  5	/* Wait for force-quiescent-state time. */
+#define RCU_GP_DOING_FQS 6	/* Wait done for force-quiescent-state time. */
+#define RCU_GP_CLEANUP   7	/* Grace-period cleanup started. */
+#define RCU_GP_CLEANED   8	/* Grace-period cleanup complete. */
 
 #ifndef RCU_TREE_NONCORE
 static const char * const gp_state_names[] = {
 	"RCU_GP_IDLE",
 	"RCU_GP_WAIT_GPS",
 	"RCU_GP_DONE_GPS",
+	"RCU_GP_ONOFF",
+	"RCU_GP_INIT",
 	"RCU_GP_WAIT_FQS",
 	"RCU_GP_DOING_FQS",
 	"RCU_GP_CLEANUP",
-- 
cgit v1.2.3


From f2e2df59786d7bd52e6e7e2d10c1c6ba433a0ee7 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 15 May 2018 16:23:23 -0700
Subject: rcu: Add diagnostics for offline CPUs failing to report QS

CPUs are expected to report quiescent states when coming online and
when going offline, and grace-period initialization is supposed to
handle any race conditions where a CPU's ->qsmask bit is set just after
it goes offline.  This commit adds diagnostics for the case where an
offline CPU nevertheless has a grace period waiting on it.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 22 ++++++++++++++++++++++
 kernel/rcu/tree.h |  1 +
 2 files changed, 23 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ee218d743226..d3333ee2c6f5 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1188,6 +1188,27 @@ static int rcu_implicit_dynticks_qs(struct rcu_data *rdp)
 		smp_store_release(ruqp, true);
 	}
 
+	/* If waiting too long on an offline CPU, complain. */
+	if (!(rdp->grpmask & rcu_rnp_online_cpus(rnp)) &&
+	    time_after(jiffies, rdp->rsp->gp_start + HZ)) {
+		bool onl;
+		struct rcu_node *rnp1;
+
+		WARN_ON(1);  /* Offline CPUs are supposed to report QS! */
+		pr_info("%s: grp: %d-%d level: %d ->gp_seq %ld ->completedqs %ld\n",
+			__func__, rnp->grplo, rnp->grphi, rnp->level,
+			(long)rnp->gp_seq, (long)rnp->completedqs);
+		for (rnp1 = rnp; rnp1; rnp1 = rnp1->parent)
+			pr_info("%s: %d:%d ->qsmask %#lx ->qsmaskinit %#lx ->qsmaskinitnext %#lx ->rcu_gp_init_mask %#lx\n",
+				__func__, rnp1->grplo, rnp1->grphi, rnp1->qsmask, rnp1->qsmaskinit, rnp1->qsmaskinitnext, rnp1->rcu_gp_init_mask);
+		onl = !!(rdp->grpmask & rcu_rnp_online_cpus(rnp));
+		pr_info("%s %d: %c online: %ld(%d) offline: %ld(%d)\n",
+			__func__, rdp->cpu, ".o"[onl],
+			(long)rdp->rcu_onl_gp_seq, rdp->rcu_onl_gp_flags,
+			(long)rdp->rcu_ofl_gp_seq, rdp->rcu_ofl_gp_flags);
+		return 1; /* Break things loose after complaining. */
+	}
+
 	/*
 	 * A CPU running for an extended time within the kernel can
 	 * delay RCU grace periods.  When the CPU is in NO_HZ_FULL mode,
@@ -1967,6 +1988,7 @@ static bool rcu_gp_init(struct rcu_state *rsp)
 					    rnp->grphi, rnp->qsmask);
 		/* Quiescent states for tasks on any now-offline CPUs. */
 		mask = rnp->qsmask & ~rnp->qsmaskinitnext;
+		rnp->rcu_gp_init_mask = mask;
 		if ((mask || rnp->wait_blkd_tasks) && rcu_is_leaf_node(rnp))
 			rcu_report_qs_rnp(mask, rsp, rnp, rnp->gp_seq, flags);
 		else
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 8077aff7ab40..d51e6edc8e83 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -90,6 +90,7 @@ struct rcu_node {
 				/*  an rcu_data structure, otherwise, each */
 				/*  bit corresponds to a child rcu_node */
 				/*  structure. */
+	unsigned long rcu_gp_init_mask;	/* Mask of offline CPUs at GP init. */
 	unsigned long qsmaskinit;
 				/* Per-GP initial value for qsmask. */
 				/*  Initialized from ->qsmaskinitnext at the */
-- 
cgit v1.2.3


From 3949fa9bac090ad217534c30bc3b6572289abf21 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 8 May 2018 15:29:10 -0700
Subject: rcu: Make rcu_read_unlock_special() static

Because rcu_read_unlock_special() is no longer used outside of
kernel/rcu/tree_plugin.h, this commit makes it static.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 1 -
 kernel/rcu/tree_plugin.h | 3 ++-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 65163aa0bb04..67ec077c7ee5 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -64,7 +64,6 @@ void rcu_barrier_tasks(void);
 
 void __rcu_read_lock(void);
 void __rcu_read_unlock(void);
-void rcu_read_unlock_special(struct task_struct *t);
 void synchronize_rcu(void);
 
 /*
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 613372246a07..54a251640f53 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -127,6 +127,7 @@ static struct rcu_data __percpu *const rcu_data_p = &rcu_preempt_data;
 
 static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 			       bool wake);
+static void rcu_read_unlock_special(struct task_struct *t);
 
 /*
  * Tell them what RCU they are running.
@@ -461,7 +462,7 @@ static bool rcu_preempt_has_tasks(struct rcu_node *rnp)
  * notify RCU core processing or task having blocked during the RCU
  * read-side critical section.
  */
-void rcu_read_unlock_special(struct task_struct *t)
+static void rcu_read_unlock_special(struct task_struct *t)
 {
 	bool empty_exp;
 	bool empty_norm;
-- 
cgit v1.2.3


From 07f27570dcd148a5f4de7dc3513c1d1cd069b362 Mon Sep 17 00:00:00 2001
From: Byungchul Park <byungchul.park@lge.com>
Date: Fri, 11 May 2018 17:30:34 +0900
Subject: rcu: Improve rcu_note_voluntary_context_switch() reporting

We expect a quiescent state of TASKS_RCU when cond_resched_tasks_rcu_qs()
is called, no matter whether it actually be scheduled or not. However,
it currently doesn't report the quiescent state when the task enters
into __schedule() as it's called with preempt = true. So make it report
the quiescent state unconditionally when cond_resched_tasks_rcu_qs() is
called.

And in TINY_RCU, even though the quiescent state of rcu_bh also should
be reported when the tick interrupt comes from user, it doesn't. So make
it reported.

Lastly in TREE_RCU, rcu_note_voluntary_context_switch() should be
reported when the tick interrupt comes from not only user but also idle,
as an extended quiescent state.

Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Simplify rcutiny portion given no RCU-tasks for !PREEMPT. ]
---
 include/linux/rcupdate.h | 4 ++--
 kernel/rcu/tiny.c        | 4 +---
 kernel/rcu/tree.c        | 4 ++--
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 67ec077c7ee5..5cab15e7ec83 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -194,8 +194,8 @@ static inline void exit_tasks_rcu_finish(void) { }
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
-	if (!cond_resched()) \
-		rcu_note_voluntary_context_switch_lite(current); \
+	rcu_note_voluntary_context_switch_lite(current); \
+	cond_resched(); \
 } while (0)
 
 /*
diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c
index a64eee0db39e..befc9321a89c 100644
--- a/kernel/rcu/tiny.c
+++ b/kernel/rcu/tiny.c
@@ -122,10 +122,8 @@ void rcu_check_callbacks(int user)
 {
 	if (user)
 		rcu_sched_qs();
-	else if (!in_softirq())
+	if (user || !in_softirq())
 		rcu_bh_qs();
-	if (user)
-		rcu_note_voluntary_context_switch(current);
 }
 
 /*
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d3333ee2c6f5..19beabe73629 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2645,6 +2645,7 @@ void rcu_check_callbacks(int user)
 
 		rcu_sched_qs();
 		rcu_bh_qs();
+		rcu_note_voluntary_context_switch(current);
 
 	} else if (!in_softirq()) {
 
@@ -2660,8 +2661,7 @@ void rcu_check_callbacks(int user)
 	rcu_preempt_check_callbacks();
 	if (rcu_pending())
 		invoke_rcu_core();
-	if (user)
-		rcu_note_voluntary_context_switch(current);
+
 	trace_rcu_utilization(TPS("End scheduler-tick"));
 }
 
-- 
cgit v1.2.3


From 1445e9175bead409bb9930f3c745246a09f22cf6 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Mon, 7 May 2018 06:35:46 -0300
Subject: rcu: rcupdate.h: Get rid of Sphinx warnings at rcu_pointer_handoff()

The code example at rcupdate.h currently produce lots of warnings:

	./include/linux/rcupdate.h:572: WARNING: Unexpected indentation.
	./include/linux/rcupdate.h:576: WARNING: Unexpected indentation.
	./include/linux/rcupdate.h:580: WARNING: Block quote ends without a blank line; unexpected unindent.
	./include/linux/rcupdate.h:582: WARNING: Block quote ends without a blank line; unexpected unindent.
	./include/linux/rcupdate.h:582: WARNING: Inline literal start-string without end-string.

This commit therefore changes it to a code-block.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index 5cab15e7ec83..dacc90358b33 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -566,8 +566,8 @@ static inline void rcu_preempt_sleep_check(void) { }
  * This is simply an identity function, but it documents where a pointer
  * is handed off from RCU to some other synchronization mechanism, for
  * example, reference counting or locking.  In C11, it would map to
- * kill_dependency().  It could be used as follows:
- * ``
+ * kill_dependency().  It could be used as follows::
+ *
  *	rcu_read_lock();
  *	p = rcu_dereference(gp);
  *	long_lived = is_long_lived(p);
@@ -578,7 +578,6 @@ static inline void rcu_preempt_sleep_check(void) { }
  *			p = rcu_pointer_handoff(p);
  *	}
  *	rcu_read_unlock();
- *``
  */
 #define rcu_pointer_handoff(p) (p)
 
-- 
cgit v1.2.3


From a7538352da722fae5cc95ae6656ea2013f5b8b21 Mon Sep 17 00:00:00 2001
From: Joe Perches <joe@perches.com>
Date: Mon, 14 May 2018 13:27:33 -0700
Subject: rcu: Use pr_fmt to prefix "rcu: " to logging output

This commit also adjusts some whitespace while in the area.

Signed-off-by: Joe Perches <joe@perches.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Revert string-breaking %s as requested by Andy Shevchenko. ]
---
 kernel/rcu/rcuperf.c     |  7 +++----
 kernel/rcu/rcutorture.c  |  4 ++--
 kernel/rcu/srcutree.c    |  5 ++++-
 kernel/rcu/tree.c        |  8 +++++---
 kernel/rcu/tree_plugin.h | 10 ++++++----
 5 files changed, 20 insertions(+), 14 deletions(-)

diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index b080bc4a4f45..00e395c0d7d0 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -680,12 +680,11 @@ rcu_perf_init(void)
 			break;
 	}
 	if (i == ARRAY_SIZE(perf_ops)) {
-		pr_alert("rcu-perf: invalid perf type: \"%s\"\n",
-			 perf_type);
+		pr_alert("rcu-perf: invalid perf type: \"%s\"\n", perf_type);
 		pr_alert("rcu-perf types:");
 		for (i = 0; i < ARRAY_SIZE(perf_ops); i++)
-			pr_alert(" %s", perf_ops[i]->name);
-		pr_alert("\n");
+			pr_cont(" %s", perf_ops[i]->name);
+		pr_cont("\n");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 0481c7286875..90a94fecdd73 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1755,8 +1755,8 @@ rcu_torture_init(void)
 			 torture_type);
 		pr_alert("rcu-torture types:");
 		for (i = 0; i < ARRAY_SIZE(torture_ops); i++)
-			pr_alert(" %s", torture_ops[i]->name);
-		pr_alert("\n");
+			pr_cont(" %s", torture_ops[i]->name);
+		pr_cont("\n");
 		firsterr = -EINVAL;
 		goto unwind;
 	}
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index d6d6ea9738c0..e526b56998af 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -26,6 +26,8 @@
  *
  */
 
+#define pr_fmt(fmt) "rcu: " fmt
+
 #include <linux/export.h>
 #include <linux/mutex.h>
 #include <linux/percpu.h>
@@ -390,7 +392,8 @@ void _cleanup_srcu_struct(struct srcu_struct *sp, bool quiesced)
 		}
 	if (WARN_ON(rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)) != SRCU_STATE_IDLE) ||
 	    WARN_ON(srcu_readers_active(sp))) {
-		pr_info("%s: Active srcu_struct %p state: %d\n", __func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
+		pr_info("%s: Active srcu_struct %p state: %d\n",
+			__func__, sp, rcu_seq_state(READ_ONCE(sp->srcu_gp_seq)));
 		return; /* Caller forgot to stop doing call_srcu()? */
 	}
 	free_percpu(sp->sda);
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 19beabe73629..6f2922168216 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -27,6 +27,9 @@
  * For detailed explanation of Read-Copy Update mechanism see -
  *	Documentation/RCU
  */
+
+#define pr_fmt(fmt) "rcu: " fmt
+
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -1374,8 +1377,7 @@ static void print_other_cpu_stall(struct rcu_state *rsp, unsigned long gp_seq)
 	 * See Documentation/RCU/stallwarn.txt for info on how to debug
 	 * RCU CPU stall warnings.
 	 */
-	pr_err("INFO: %s detected stalls on CPUs/tasks:",
-	       rsp->name);
+	pr_err("INFO: %s detected stalls on CPUs/tasks:", rsp->name);
 	print_cpu_stall_info_begin();
 	rcu_for_each_leaf_node(rsp, rnp) {
 		raw_spin_lock_irqsave_rcu_node(rnp, flags);
@@ -4048,7 +4050,7 @@ static void __init rcu_init_geometry(void)
 	if (rcu_fanout_leaf == RCU_FANOUT_LEAF &&
 	    nr_cpu_ids == NR_CPUS)
 		return;
-	pr_info("RCU: Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
+	pr_info("Adjusting geometry for rcu_fanout_leaf=%d, nr_cpu_ids=%u\n",
 		rcu_fanout_leaf, nr_cpu_ids);
 
 	/*
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 54a251640f53..dbfe90191e19 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -74,8 +74,8 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tRCU event tracing is enabled.\n");
 	if ((IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 64) ||
 	    (!IS_ENABLED(CONFIG_64BIT) && RCU_FANOUT != 32))
-		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d\n",
-		       RCU_FANOUT);
+		pr_info("\tCONFIG_RCU_FANOUT set to non-default value of %d.\n",
+			RCU_FANOUT);
 	if (rcu_fanout_exact)
 		pr_info("\tHierarchical RCU autobalancing is disabled.\n");
 	if (IS_ENABLED(CONFIG_RCU_FAST_NO_HZ))
@@ -88,11 +88,13 @@ static void __init rcu_bootup_announce_oddness(void)
 		pr_info("\tBuild-time adjustment of leaf fanout to %d.\n",
 			RCU_FANOUT_LEAF);
 	if (rcu_fanout_leaf != RCU_FANOUT_LEAF)
-		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n", rcu_fanout_leaf);
+		pr_info("\tBoot-time adjustment of leaf fanout to %d.\n",
+			rcu_fanout_leaf);
 	if (nr_cpu_ids != NR_CPUS)
 		pr_info("\tRCU restricting CPUs from NR_CPUS=%d to nr_cpu_ids=%u.\n", NR_CPUS, nr_cpu_ids);
 #ifdef CONFIG_RCU_BOOST
-	pr_info("\tRCU priority boosting: priority %d delay %d ms.\n", kthread_prio, CONFIG_RCU_BOOST_DELAY);
+	pr_info("\tRCU priority boosting: priority %d delay %d ms.\n",
+		kthread_prio, CONFIG_RCU_BOOST_DELAY);
 #endif
 	if (blimit != DEFAULT_RCU_BLIMIT)
 		pr_info("\tBoot-time adjustment of callback invocation limit to %ld.\n", blimit);
-- 
cgit v1.2.3


From 6f56f714db067056c80f5d71510118f82872e34c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 14 May 2018 13:52:27 -0700
Subject: rcu: Improve RCU-tasks naming and comments

The naming and comments associated with some RCU-tasks code make
the faulty assumption that context switches due to cond_resched()
are voluntary.  As several people pointed out, this is not the case.
This commit therefore updates function names and comments to better
reflect current reality.

Reported-by: Byungchul Park <byungchul.park@lge.com>
Reported-by: Joel Fernandes <joel@joelfernandes.org>
Reported-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 include/linux/rcupdate.h | 12 ++++++------
 include/linux/rcutiny.h  |  2 +-
 kernel/rcu/tree.c        |  2 +-
 kernel/rcu/update.c      | 27 ++++++++++++++-------------
 4 files changed, 22 insertions(+), 21 deletions(-)

diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index dacc90358b33..75e5b393cf44 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -158,11 +158,11 @@ static inline void rcu_init_nohz(void) { }
 	} while (0)
 
 /*
- * Note a voluntary context switch for RCU-tasks benefit.  This is a
- * macro rather than an inline function to avoid #include hell.
+ * Note a quasi-voluntary context switch for RCU-tasks's benefit.
+ * This is a macro rather than an inline function to avoid #include hell.
  */
 #ifdef CONFIG_TASKS_RCU
-#define rcu_note_voluntary_context_switch_lite(t) \
+#define rcu_tasks_qs(t) \
 	do { \
 		if (READ_ONCE((t)->rcu_tasks_holdout)) \
 			WRITE_ONCE((t)->rcu_tasks_holdout, false); \
@@ -170,14 +170,14 @@ static inline void rcu_init_nohz(void) { }
 #define rcu_note_voluntary_context_switch(t) \
 	do { \
 		rcu_all_qs(); \
-		rcu_note_voluntary_context_switch_lite(t); \
+		rcu_tasks_qs(t); \
 	} while (0)
 void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func);
 void synchronize_rcu_tasks(void);
 void exit_tasks_rcu_start(void);
 void exit_tasks_rcu_finish(void);
 #else /* #ifdef CONFIG_TASKS_RCU */
-#define rcu_note_voluntary_context_switch_lite(t)	do { } while (0)
+#define rcu_tasks_qs(t)	do { } while (0)
 #define rcu_note_voluntary_context_switch(t)		rcu_all_qs()
 #define call_rcu_tasks call_rcu_sched
 #define synchronize_rcu_tasks synchronize_sched
@@ -194,7 +194,7 @@ static inline void exit_tasks_rcu_finish(void) { }
  */
 #define cond_resched_tasks_rcu_qs() \
 do { \
-	rcu_note_voluntary_context_switch_lite(current); \
+	rcu_tasks_qs(current); \
 	cond_resched(); \
 } while (0)
 
diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h
index 7b3c82e8a625..8d9a0ea8f0b5 100644
--- a/include/linux/rcutiny.h
+++ b/include/linux/rcutiny.h
@@ -93,7 +93,7 @@ static inline void kfree_call_rcu(struct rcu_head *head,
 #define rcu_note_context_switch(preempt) \
 	do { \
 		rcu_sched_qs(); \
-		rcu_note_voluntary_context_switch_lite(current); \
+		rcu_tasks_qs(current); \
 	} while (0)
 
 static inline int rcu_needs_cpu(u64 basemono, u64 *nextevt)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 6f2922168216..ccc061acf887 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -457,7 +457,7 @@ void rcu_note_context_switch(bool preempt)
 		rcu_momentary_dyntick_idle();
 	this_cpu_inc(rcu_dynticks.rcu_qs_ctr);
 	if (!preempt)
-		rcu_note_voluntary_context_switch_lite(current);
+		rcu_tasks_qs(current);
 out:
 	trace_rcu_utilization(TPS("End context switch"));
 	barrier(); /* Avoid RCU read-side critical sections leaking up. */
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4c230a60ece4..5783bdf86e5a 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -507,14 +507,15 @@ early_initcall(check_cpu_stall_init);
 #ifdef CONFIG_TASKS_RCU
 
 /*
- * Simple variant of RCU whose quiescent states are voluntary context switch,
- * user-space execution, and idle.  As such, grace periods can take one good
- * long time.  There are no read-side primitives similar to rcu_read_lock()
- * and rcu_read_unlock() because this implementation is intended to get
- * the system into a safe state for some of the manipulations involved in
- * tracing and the like.  Finally, this implementation does not support
- * high call_rcu_tasks() rates from multiple CPUs.  If this is required,
- * per-CPU callback lists will be needed.
+ * Simple variant of RCU whose quiescent states are voluntary context
+ * switch, cond_resched_rcu_qs(), user-space execution, and idle.
+ * As such, grace periods can take one good long time.  There are no
+ * read-side primitives similar to rcu_read_lock() and rcu_read_unlock()
+ * because this implementation is intended to get the system into a safe
+ * state for some of the manipulations involved in tracing and the like.
+ * Finally, this implementation does not support high call_rcu_tasks()
+ * rates from multiple CPUs.  If this is required, per-CPU callback lists
+ * will be needed.
  */
 
 /* Global list of callbacks and associated lock. */
@@ -542,11 +543,11 @@ static struct task_struct *rcu_tasks_kthread_ptr;
  * period elapses, in other words after all currently executing RCU
  * read-side critical sections have completed. call_rcu_tasks() assumes
  * that the read-side critical sections end at a voluntary context
- * switch (not a preemption!), entry into idle, or transition to usermode
- * execution.  As such, there are no read-side primitives analogous to
- * rcu_read_lock() and rcu_read_unlock() because this primitive is intended
- * to determine that all tasks have passed through a safe state, not so
- * much for data-strcuture synchronization.
+ * switch (not a preemption!), cond_resched_rcu_qs(), entry into idle,
+ * or transition to usermode execution.  As such, there are no read-side
+ * primitives analogous to rcu_read_lock() and rcu_read_unlock() because
+ * this primitive is intended to determine that all tasks have passed
+ * through a safe state, not so much for data-strcuture synchronization.
  *
  * See the description of call_rcu() for more detailed information on
  * memory ordering guarantees.
-- 
cgit v1.2.3


From 15651201fa055ec81d3669b36ab7c2fb12c3ce36 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 16 May 2018 14:41:41 -0700
Subject: rcu: Mark task as .need_qs less aggressively

If any scheduling-clock interrupt interrupts an RCU-preempt read-side
critical section, the interrupted task's ->rcu_read_unlock_special.b.need_qs
field is set.  This causes the outermost rcu_read_unlock() to incur the
extra overhead of calling into rcu_read_unlock_special().  This commit
reduces that overhead by setting ->rcu_read_unlock_special.b.need_qs only
if the grace period has been in effect for more than one second.

Why one second?  Because this is comfortably smaller than the minimum
RCU CPU stall-warning timeout of three seconds, but long enough that the
.need_qs marking should happen quite rarely.  And if your RCU read-side
critical section has run on-CPU for a full second, it is not unreasonable
to invest some CPU time in ending the grace period quickly.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index dbfe90191e19..0239cf8a4be6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -730,6 +730,7 @@ rcu_preempt_check_blocked_tasks(struct rcu_state *rsp, struct rcu_node *rnp)
  */
 static void rcu_preempt_check_callbacks(void)
 {
+	struct rcu_state *rsp = &rcu_preempt_state;
 	struct task_struct *t = current;
 
 	if (t->rcu_read_lock_nesting == 0) {
@@ -738,7 +739,9 @@ static void rcu_preempt_check_callbacks(void)
 	}
 	if (t->rcu_read_lock_nesting > 0 &&
 	    __this_cpu_read(rcu_data_p->core_needs_qs) &&
-	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm))
+	    __this_cpu_read(rcu_data_p->cpu_no_qs.b.norm) &&
+	    !t->rcu_read_unlock_special.b.need_qs &&
+	    time_after(jiffies, rsp->gp_start + HZ))
 		t->rcu_read_unlock_special.b.need_qs = true;
 }
 
-- 
cgit v1.2.3


From 3b57a3994f330a102b91bd70c84c9530c0ae50f6 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 16 May 2018 16:01:56 -0700
Subject: rcu: Inline rcu_dynticks_momentary_idle() into its sole caller

The rcu_dynticks_momentary_idle() function is invoked only from
rcu_momentary_dyntick_idle(), and neither function is particularly
large.  This commit therefore saves a few lines by inlining
rcu_dynticks_momentary_idle() into rcu_momentary_dyntick_idle().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ccc061acf887..ebdbb5f96e5c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -385,20 +385,6 @@ static bool rcu_dynticks_in_eqs_since(struct rcu_dynticks *rdtp, int snap)
 	return snap != rcu_dynticks_snap(rdtp);
 }
 
-/*
- * Do a double-increment of the ->dynticks counter to emulate a
- * momentary idle-CPU quiescent state.
- */
-static void rcu_dynticks_momentary_idle(void)
-{
-	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
-	int special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR,
-					&rdtp->dynticks);
-
-	/* It is illegal to call this from idle state. */
-	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
-}
-
 /*
  * Set the special (bottom) bit of the specified CPU so that it
  * will take special action (such as flushing its TLB) on the
@@ -430,12 +416,17 @@ bool rcu_eqs_special_set(int cpu)
  *
  * We inform the RCU core by emulating a zero-duration dyntick-idle period.
  *
- * The caller must have disabled interrupts.
+ * The caller must have disabled interrupts and must not be idle.
  */
 static void rcu_momentary_dyntick_idle(void)
 {
+	struct rcu_dynticks *rdtp = this_cpu_ptr(&rcu_dynticks);
+	int special;
+
 	raw_cpu_write(rcu_dynticks.rcu_need_heavy_qs, false);
-	rcu_dynticks_momentary_idle();
+	special = atomic_add_return(2 * RCU_DYNTICK_CTRL_CTR, &rdtp->dynticks);
+	/* It is illegal to call this from idle state. */
+	WARN_ON_ONCE(!(special & RCU_DYNTICK_CTRL_CTR));
 }
 
 /*
-- 
cgit v1.2.3


From c7037ff5249cee237b8c8a6f99998ae4f3916b60 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 16 May 2018 18:00:17 -0700
Subject: rcu: Clarify and correct the rcu_preempt_qs() header comment

The rcu_preempt_qs() function only applies to the CPU, not the task.
A task really is allowed to invoke this function while in an RCU-preempt
read-side critical section, but only if it has first added itself to
some leaf rcu_node structure's ->blkd_tasks list.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 0239cf8a4be6..07d1ad175994 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -294,13 +294,17 @@ static void rcu_preempt_ctxt_queue(struct rcu_node *rnp, struct rcu_data *rdp)
 }
 
 /*
- * Record a preemptible-RCU quiescent state for the specified CPU.  Note
- * that this just means that the task currently running on the CPU is
- * not in a quiescent state.  There might be any number of tasks blocked
- * while in an RCU read-side critical section.
+ * Record a preemptible-RCU quiescent state for the specified CPU.
+ * Note that this does not necessarily mean that the task currently running
+ * on the CPU is in a quiescent state:  Instead, it means that the current
+ * grace period need not wait on any RCU read-side critical section that
+ * starts later on this CPU.  It also means that if the current task is
+ * in an RCU read-side critical section, it has already added itself to
+ * some leaf rcu_node structure's ->blkd_tasks list.  In addition to the
+ * current task, there might be any number of other tasks blocked while
+ * in an RCU read-side critical section.
  *
- * As with the other rcu_*_qs() functions, callers to this function
- * must disable preemption.
+ * Callers to this function must disable preemption.
  */
 static void rcu_preempt_qs(void)
 {
-- 
cgit v1.2.3


From 164ba3fc4864346dbc365f8b89d8888e1b6cd38c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 16 May 2018 20:41:36 -0700
Subject: rcu: Remove unused rcu_kick_nohz_cpu() function

The rcu_kick_nohz_cpu() function is no longer used, and the functionality
it used to provide is now provided by a call to resched_cpu() in the
force-quiescent-state function rcu_implicit_dynticks_qs().  This commit
therefore removes rcu_kick_nohz_cpu().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.h        |  1 -
 kernel/rcu/tree_plugin.h | 17 -----------------
 2 files changed, 18 deletions(-)

diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index d51e6edc8e83..4e74df768c57 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -483,7 +483,6 @@ static void __init rcu_spawn_nocb_kthreads(void);
 #ifdef CONFIG_RCU_NOCB_CPU
 static void __init rcu_organize_nocb_kthreads(struct rcu_state *rsp);
 #endif /* #ifdef CONFIG_RCU_NOCB_CPU */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu);
 static bool init_nocb_callback_list(struct rcu_data *rdp);
 static void rcu_bind_gp_kthread(void);
 static bool rcu_nohz_full_cpu(struct rcu_state *rsp);
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 07d1ad175994..75a91d58b8f7 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2645,23 +2645,6 @@ static bool init_nocb_callback_list(struct rcu_data *rdp)
 
 #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */
 
-/*
- * An adaptive-ticks CPU can potentially execute in kernel mode for an
- * arbitrarily long period of time with the scheduling-clock tick turned
- * off.  RCU will be paying attention to this CPU because it is in the
- * kernel, but the CPU cannot be guaranteed to be executing the RCU state
- * machine because the scheduling-clock tick has been disabled.  Therefore,
- * if an adaptive-ticks CPU is failing to respond to the current grace
- * period and has not be idle from an RCU perspective, kick it.
- */
-static void __maybe_unused rcu_kick_nohz_cpu(int cpu)
-{
-#ifdef CONFIG_NO_HZ_FULL
-	if (tick_nohz_full_cpu(cpu))
-		smp_send_reschedule(cpu);
-#endif /* #ifdef CONFIG_NO_HZ_FULL */
-}
-
 /*
  * Is this CPU a NO_HZ_FULL CPU that should ignore RCU so that the
  * grace-period kthread will do force_quiescent_state() processing?
-- 
cgit v1.2.3


From ab6b82147f471e31d9397c95d523631b6c8953f2 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 17 May 2018 11:21:20 -0700
Subject: rcu: Remove unused local variable "cpu"

One danger of using __maybe_unused is that the compiler doesn't yell
at you when you remove the last reference, witness rcu_bind_gp_kthread()
and its local variable "cpu".  This commit removes this local variable.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 75a91d58b8f7..2cc9bf0d363a 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2670,8 +2670,6 @@ static bool rcu_nohz_full_cpu(struct rcu_state *rsp)
  */
 static void rcu_bind_gp_kthread(void)
 {
-	int __maybe_unused cpu;
-
 	if (!tick_nohz_full_enabled())
 		return;
 	housekeeping_affine(current, HK_FLAG_RCU);
-- 
cgit v1.2.3


From 95394e69c42f0da83a176936fdb28f6cac57ea69 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 17 May 2018 11:33:17 -0700
Subject: rcu: Remove "inline" from panic_on_rcu_stall() and
 rcu_blocking_is_gp()

These functions are in kernel/rcu/tree.c, which is not an include file,
so there is no problem dropping the "inline", especially given that these
functions are nowhere near a fastpath.  This commit therefore delegates
the inlining decision to the compiler by dropping the "inline".

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index ebdbb5f96e5c..3504ee35e226 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -1342,7 +1342,7 @@ static void rcu_stall_kick_kthreads(struct rcu_state *rsp)
 	}
 }
 
-static inline void panic_on_rcu_stall(void)
+static void panic_on_rcu_stall(void)
 {
 	if (sysctl_panic_on_rcu_stall)
 		panic("RCU Stall\n");
@@ -3080,7 +3080,7 @@ EXPORT_SYMBOL_GPL(kfree_call_rcu);
  * when there was in fact only one the whole time, as this just adds
  * some overhead: RCU still operates correctly.
  */
-static inline int rcu_blocking_is_gp(void)
+static int rcu_blocking_is_gp(void)
 {
 	int ret;
 
-- 
cgit v1.2.3


From eac45e586cd38a1b56aa716560002e68741b78a7 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 17 May 2018 11:33:17 -0700
Subject: rcu: Remove "inline" from rcu_torture_print_module_parms()

This function is in rcutorture.c, which is not an include file, so there
is no problem dropping the "inline", especially given that this function
is invoked only twice per rcutorture run.  This commit therefore delegates
the inlining decision to the compiler by dropping the "inline".

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 90a94fecdd73..57a4277ccc63 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1359,7 +1359,7 @@ rcu_torture_stats(void *arg)
 	return 0;
 }
 
-static inline void
+static void
 rcu_torture_print_module_parms(struct rcu_torture_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" TORTURE_FLAG
-- 
cgit v1.2.3


From 9622179519c52ead944c3b6a07aed9c6db3659e2 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 17 May 2018 11:33:17 -0700
Subject: rcu: Remove "inline" from rcu_perf_print_module_parms()

This function is in rcuperf.c, which is not an include file, so there
is no problem dropping the "inline", especially given that this function
is invoked only twice per rcuperf run.  This commit therefore delegates
the inlining decision to the compiler by dropping the "inline".

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcuperf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index 00e395c0d7d0..3e86940245d9 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -536,7 +536,7 @@ retry:
 	return 0;
 }
 
-static inline void
+static void
 rcu_perf_print_module_parms(struct rcu_perf_ops *cur_ops, const char *tag)
 {
 	pr_alert("%s" PERF_FLAG
-- 
cgit v1.2.3


From 51fbb910f52c8559a78665d203e55ab2b95e7126 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 17 May 2018 13:15:40 -0700
Subject: rcu: Remove __maybe_unused from rcu_cpu_has_callbacks()

The rcu_cpu_has_callbacks() function is now used in all configurations,
so this commit removes the __maybe_unused.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 3504ee35e226..cdc4fca0c4cb 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3315,7 +3315,7 @@ static int rcu_pending(void)
  * non-NULL, store an indication of whether all callbacks are lazy.
  * (If there are no callbacks, all of them are deemed to be lazy.)
  */
-static bool __maybe_unused rcu_cpu_has_callbacks(bool *all_lazy)
+static bool rcu_cpu_has_callbacks(bool *all_lazy)
 {
 	bool al = true;
 	bool hc = false;
-- 
cgit v1.2.3


From b06ae25a1e2b54b2b5bc589a4a118b7bb39159fe Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 17 May 2018 13:32:51 -0700
Subject: rcu: Use RCU CPU stall timeout for rcu_check_gp_start_stall()

Currently, rcu_check_gp_start_stall() waits for one second after the first
request before complaining that a grace period has not yet started.  This
was desirable while testing the conversion from ->future_gp_needed[] to
->gp_seq_needed, but it is a bit on the hair-trigger side for production
use under heavy load.  This commit therefore makes this wait time be
exactly that of the RCU CPU stall warning, allowing easy adjustment of
both timeouts to suit the distribution or installation at hand.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index cdc4fca0c4cb..7746fe1ee3fc 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -2753,6 +2753,7 @@ static void
 rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 			 struct rcu_data *rdp)
 {
+	const unsigned long gpssdelay = rcu_jiffies_till_stall_check() * HZ;
 	unsigned long flags;
 	unsigned long j;
 	struct rcu_node *rnp_root = rcu_get_root(rsp);
@@ -2762,8 +2763,8 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed))
 		return;
 	j = jiffies; /* Expensive access, and in common case don't get here. */
-	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
-	    time_before(j, READ_ONCE(rsp->gp_activity) + HZ) ||
+	if (time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
 	    atomic_read(&warned))
 		return;
 
@@ -2771,8 +2772,8 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	j = jiffies;
 	if (rcu_gp_in_progress(rsp) ||
 	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, READ_ONCE(rsp->gp_req_activity) + HZ) ||
-	    time_before(j, READ_ONCE(rsp->gp_activity) + HZ) ||
+	    time_before(j, READ_ONCE(rsp->gp_req_activity) + gpssdelay) ||
+	    time_before(j, READ_ONCE(rsp->gp_activity) + gpssdelay) ||
 	    atomic_read(&warned)) {
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
@@ -2784,18 +2785,18 @@ rcu_check_gp_start_stall(struct rcu_state *rsp, struct rcu_node *rnp,
 	j = jiffies;
 	if (rcu_gp_in_progress(rsp) ||
 	    ULONG_CMP_GE(rnp_root->gp_seq, rnp_root->gp_seq_needed) ||
-	    time_before(j, rsp->gp_req_activity + HZ) ||
-	    time_before(j, rsp->gp_activity + HZ) ||
+	    time_before(j, rsp->gp_req_activity + gpssdelay) ||
+	    time_before(j, rsp->gp_activity + gpssdelay) ||
 	    atomic_xchg(&warned, 1)) {
 		raw_spin_unlock_rcu_node(rnp_root); /* irqs remain disabled. */
 		raw_spin_unlock_irqrestore_rcu_node(rnp, flags);
 		return;
 	}
-	pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x %s->state:%#lx\n",
+	pr_alert("%s: g%ld->%ld gar:%lu ga:%lu f%#x gs:%d %s->state:%#lx\n",
 		 __func__, (long)READ_ONCE(rsp->gp_seq),
 		 (long)READ_ONCE(rnp_root->gp_seq_needed),
 		 j - rsp->gp_req_activity, j - rsp->gp_activity,
-		 rsp->gp_flags, rsp->name,
+		 rsp->gp_flags, rsp->gp_state, rsp->name,
 		 rsp->gp_kthread ? rsp->gp_kthread->state : 0x1ffffL);
 	WARN_ON(1);
 	if (rnp_root != rnp)
-- 
cgit v1.2.3


From 0d805a70a652a6eef8d0283e5183879e7acb85ad Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Tue, 22 May 2018 23:38:13 -0700
Subject: rcu: Add comment documenting how rcu_seq_snap works

rcu_seq_snap may be tricky to decipher. Lets document how it works with
an example to make it easier.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Shrink comment as suggested by Peter Zijlstra. ]
---
 kernel/rcu/rcu.h | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index aa215d6355f8..89f13fffac73 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -91,7 +91,17 @@ static inline void rcu_seq_end(unsigned long *sp)
 	WRITE_ONCE(*sp, rcu_seq_endval(sp));
 }
 
-/* Take a snapshot of the update side's sequence number. */
+/*
+ * rcu_seq_snap - Take a snapshot of the update side's sequence number.
+ *
+ * This function returns the earliest value of the grace-period sequence number
+ * that will indicate that a full grace period has elapsed since the current
+ * time.  Once the grace-period sequence number has reached this value, it will
+ * be safe to invoke all callbacks that have been registered prior to the
+ * current time. This value is the current grace-period number plus two to the
+ * power of the number of low-order bits reserved for state, then rounded up to
+ * the next value in which the state bits are all zero.
+ */
 static inline unsigned long rcu_seq_snap(unsigned long *sp)
 {
 	unsigned long s;
-- 
cgit v1.2.3


From c03be752d39dc64dcfda0ac8ce87fb10b1ee5621 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 24 May 2018 18:49:46 -0400
Subject: rcu: Speed up calling of RCU tasks callbacks

Joel Fernandes found that the synchronize_rcu_tasks() was taking a
significant amount of time. He demonstrated it with the following test:

 # cd /sys/kernel/tracing
 # while [ 1 ]; do x=1; done &
 # echo '__schedule_bug:traceon' > set_ftrace_filter
 # time echo '!__schedule_bug:traceon' > set_ftrace_filter;

real	0m1.064s
user	0m0.000s
sys	0m0.004s

Where it takes a little over a second to perform the synchronize,
because there's a loop that waits 1 second at a time for tasks to get
through their quiescent points when there's a task that must be waited
for.

After discussion we came up with a simple way to wait for holdouts but
increase the time for each iteration of the loop but no more than a
full second.

With the new patch we have:

 # time echo '!__schedule_bug:traceon' > set_ftrace_filter;

real	0m0.131s
user	0m0.000s
sys	0m0.004s

Which drops it down to 13% of what the original wait time was.

Link: http://lkml.kernel.org/r/20180523063815.198302-2-joel@joelfernandes.org
Reported-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Suggested-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/update.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 5783bdf86e5a..4c7c49c106ee 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -668,6 +668,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 	struct rcu_head *list;
 	struct rcu_head *next;
 	LIST_HEAD(rcu_tasks_holdouts);
+	int fract;
 
 	/* Run on housekeeping CPUs by default.  Sysadm can move if desired. */
 	housekeeping_affine(current, HK_FLAG_RCU);
@@ -749,13 +750,25 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 		 * holdouts.  When the list is empty, we are done.
 		 */
 		lastreport = jiffies;
-		while (!list_empty(&rcu_tasks_holdouts)) {
+
+		/* Start off with HZ/10 wait and slowly back off to 1 HZ wait*/
+		fract = 10;
+
+		for (;;) {
 			bool firstreport;
 			bool needreport;
 			int rtst;
 			struct task_struct *t1;
 
-			schedule_timeout_interruptible(HZ);
+			if (list_empty(&rcu_tasks_holdouts))
+				break;
+
+			/* Slowly back off waiting for holdouts */
+			schedule_timeout_interruptible(HZ/fract);
+
+			if (fract > 1)
+				fract--;
+
 			rtst = READ_ONCE(rcu_task_stall_timeout);
 			needreport = rtst > 0 &&
 				     time_after(jiffies, lastreport + rtst);
-- 
cgit v1.2.3


From cd23ac8ddb7be993f88bee893b89a8b4971c3651 Mon Sep 17 00:00:00 2001
From: "Steven Rostedt (VMware)" <rostedt@goodmis.org>
Date: Thu, 24 May 2018 18:58:16 -0400
Subject: rcu: Add comment to the last sleep in the rcu tasks loop

At the end of rcu_tasks_kthread() there's a lonely
schedule_timeout_uninterruptible() call with no apparent rationale for
its existence. But there is. It is to keep the thread from going into
a tight loop if there's some anomaly. That really needs a comment.

Link: http://lkml.kernel.org/r/20180524223839.GU3803@linux.vnet.ibm.com
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/update.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 4c7c49c106ee..39cb23d22109 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -814,6 +814,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
 			list = next;
 			cond_resched();
 		}
+		/* Paranoid sleep to keep this from entering a tight loop */
 		schedule_timeout_uninterruptible(HZ/10);
 	}
 }
-- 
cgit v1.2.3


From 47199a0812535217c29933cecf468568bb37f933 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 28 May 2018 10:33:08 -0700
Subject: rcu: Add diagnostics for rcutorture writer stall warning

This commit adds any in-the-future ->gp_seq_needed fields to the
diagnostics for an rcutorture writer stall warning message.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7746fe1ee3fc..4915525559ac 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -606,11 +606,32 @@ EXPORT_SYMBOL_GPL(rcu_sched_force_quiescent_state);
  */
 void show_rcu_gp_kthreads(void)
 {
+	int cpu;
+	struct rcu_data *rdp;
+	struct rcu_node *rnp;
 	struct rcu_state *rsp;
 
 	for_each_rcu_flavor(rsp) {
 		pr_info("%s: wait state: %d ->state: %#lx\n",
 			rsp->name, rsp->gp_state, rsp->gp_kthread->state);
+		rcu_for_each_node_breadth_first(rsp, rnp) {
+			if (ULONG_CMP_GE(rsp->gp_seq, rnp->gp_seq_needed))
+				continue;
+			pr_info("\trcu_node %d:%d ->gp_seq %lu ->gp_seq_needed %lu\n",
+				rnp->grplo, rnp->grphi, rnp->gp_seq,
+				rnp->gp_seq_needed);
+			if (!rcu_is_leaf_node(rnp))
+				continue;
+			for_each_leaf_node_possible_cpu(rnp, cpu) {
+				rdp = per_cpu_ptr(rsp->rda, cpu);
+				if (rdp->gpwrap ||
+				    ULONG_CMP_GE(rsp->gp_seq,
+						 rdp->gp_seq_needed))
+					continue;
+				pr_info("\tcpu %d ->gp_seq_needed %lu\n",
+					cpu, rdp->gp_seq_needed);
+			}
+		}
 		/* sched_show_task(rsp->gp_kthread); */
 	}
 }
-- 
cgit v1.2.3


From 67abb96cbf307e16e3c6d1a0328ece085b5ce94c Mon Sep 17 00:00:00 2001
From: Byungchul Park <byungchul.park@lge.com>
Date: Fri, 1 Jun 2018 11:03:09 +0900
Subject: rcu: Check the range of jiffies_till_{first,next}_fqs when setting
 them

Currently, the range of jiffies_till_{first,next}_fqs are checked and
adjusted on and on in the loop of rcu_gp_kthread on runtime.

However, it's enough to check them only when setting them, not every
time in the loop. So make them handled on a setting time via sysfs.

Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 45 ++++++++++++++++++++++++++++++++-------------
 1 file changed, 32 insertions(+), 13 deletions(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 4915525559ac..7498a416f63b 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -510,8 +510,38 @@ static ulong jiffies_till_first_fqs = ULONG_MAX;
 static ulong jiffies_till_next_fqs = ULONG_MAX;
 static bool rcu_kick_kthreads;
 
-module_param(jiffies_till_first_fqs, ulong, 0644);
-module_param(jiffies_till_next_fqs, ulong, 0644);
+static int param_set_first_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+	ulong j;
+	int ret = kstrtoul(val, 0, &j);
+
+	if (!ret)
+		WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : j);
+	return ret;
+}
+
+static int param_set_next_fqs_jiffies(const char *val, const struct kernel_param *kp)
+{
+	ulong j;
+	int ret = kstrtoul(val, 0, &j);
+
+	if (!ret)
+		WRITE_ONCE(*(ulong *)kp->arg, (j > HZ) ? HZ : (j ?: 1));
+	return ret;
+}
+
+static struct kernel_param_ops first_fqs_jiffies_ops = {
+	.set = param_set_first_fqs_jiffies,
+	.get = param_get_ulong,
+};
+
+static struct kernel_param_ops next_fqs_jiffies_ops = {
+	.set = param_set_next_fqs_jiffies,
+	.get = param_get_ulong,
+};
+
+module_param_cb(jiffies_till_first_fqs, &first_fqs_jiffies_ops, &jiffies_till_first_fqs, 0644);
+module_param_cb(jiffies_till_next_fqs, &next_fqs_jiffies_ops, &jiffies_till_next_fqs, 0644);
 module_param(rcu_kick_kthreads, bool, 0644);
 
 /*
@@ -2180,10 +2210,6 @@ static int __noreturn rcu_gp_kthread(void *arg)
 		/* Handle quiescent-state forcing. */
 		first_gp_fqs = true;
 		j = jiffies_till_first_fqs;
-		if (j > HZ) {
-			j = HZ;
-			jiffies_till_first_fqs = HZ;
-		}
 		ret = 0;
 		for (;;) {
 			if (!ret) {
@@ -2218,13 +2244,6 @@ static int __noreturn rcu_gp_kthread(void *arg)
 				WRITE_ONCE(rsp->gp_activity, jiffies);
 				ret = 0; /* Force full wait till next FQS. */
 				j = jiffies_till_next_fqs;
-				if (j > HZ) {
-					j = HZ;
-					jiffies_till_next_fqs = HZ;
-				} else if (j < 1) {
-					j = 1;
-					jiffies_till_next_fqs = 1;
-				}
 			} else {
 				/* Deal with stray signal. */
 				cond_resched_tasks_rcu_qs();
-- 
cgit v1.2.3


From 264d4f88ad5ba0d3c890a70a1216b4e87e5c26ec Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Thu, 7 Jun 2018 12:01:57 +0200
Subject: doc: Update synchronize_rcu() definition in whatisRCU.txt

The synchronize_rcu() definition based on RW-locks in whatisRCU.txt
does not meet the "Memory-Barrier Guarantees" in Requirements.html;
for example, the following SB-like test:

    P0:                      P1:

    WRITE_ONCE(x, 1);        WRITE_ONCE(y, 1);
    synchronize_rcu();       smp_mb();
    r0 = READ_ONCE(y);       r1 = READ_ONCE(x);

should not be allowed to reach the state "r0 = 0 AND r1 = 0", but
the current write_lock()+write_unlock() definition can not ensure
this.  This commit therefore inserts an smp_mb__after_spinlock()
in order to cause this synchronize_rcu() implementation to provide
this memory-barrier guarantee.

Suggested-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/RCU/whatisRCU.txt | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 65eb856526b7..94288f1b8759 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -588,6 +588,7 @@ It is extremely simple:
 	void synchronize_rcu(void)
 	{
 		write_lock(&rcu_gp_mutex);
+		smp_mb__after_spinlock();
 		write_unlock(&rcu_gp_mutex);
 	}
 
@@ -609,12 +610,15 @@ don't forget about them when submitting patches making use of RCU!]
 
 The rcu_read_lock() and rcu_read_unlock() primitive read-acquire
 and release a global reader-writer lock.  The synchronize_rcu()
-primitive write-acquires this same lock, then immediately releases
-it.  This means that once synchronize_rcu() exits, all RCU read-side
-critical sections that were in progress before synchronize_rcu() was
-called are guaranteed to have completed -- there is no way that
-synchronize_rcu() would have been able to write-acquire the lock
-otherwise.
+primitive write-acquires this same lock, then releases it.  This means
+that once synchronize_rcu() exits, all RCU read-side critical sections
+that were in progress before synchronize_rcu() was called are guaranteed
+to have completed -- there is no way that synchronize_rcu() would have
+been able to write-acquire the lock otherwise.  The smp_mb__after_spinlock()
+promotes synchronize_rcu() to a full memory barrier in compliance with
+the "Memory-Barrier Guarantees" listed in:
+
+	Documentation/RCU/Design/Requirements/Requirements.html.
 
 It is possible to nest rcu_read_lock(), since reader-writer locks may
 be recursively acquired.  Note also that rcu_read_lock() is immune
-- 
cgit v1.2.3


From 2ee5aca54622aacc196106c623fea4116f1043a6 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sat, 9 Jun 2018 01:22:20 -0700
Subject: rcu: Make rcu_seq_diff() more exact

The current implementatation of rcu_seq_diff() follows tradition in
providing a rough-and-ready approximation of the number of elapsed grace
periods between the two rcu_seq values.  However, this difference is
used to flag RCU-failure "near misses", which can be a valuable debugging
aid, so more exactitude would be an improvement.  This commit therefore
improves the accuracy of rcu_seq_diff().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 89f13fffac73..d5e0294b8580 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -158,7 +158,20 @@ static inline bool rcu_seq_new_gp(unsigned long old, unsigned long new)
  */
 static inline unsigned long rcu_seq_diff(unsigned long new, unsigned long old)
 {
-	return (new - old) >> RCU_SEQ_CTR_SHIFT;
+	unsigned long rnd_diff;
+
+	if (old == new)
+		return 0;
+	/*
+	 * Compute the number of grace periods (still shifted up), plus
+	 * one if either of new and old is not an exact grace period.
+	 */
+	rnd_diff = (new & ~RCU_SEQ_STATE_MASK) -
+		   ((old + RCU_SEQ_STATE_MASK) & ~RCU_SEQ_STATE_MASK) +
+		   ((new & RCU_SEQ_STATE_MASK) || (old & RCU_SEQ_STATE_MASK));
+	if (ULONG_CMP_GE(RCU_SEQ_STATE_MASK, rnd_diff))
+		return 1; /* Definitely no grace period has elapsed. */
+	return ((rnd_diff - RCU_SEQ_STATE_MASK - 1) >> RCU_SEQ_CTR_SHIFT) + 2;
 }
 
 /*
-- 
cgit v1.2.3


From cfe15038f4fc83503711a0880ba438f2deee91ff Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 11 Jun 2018 05:22:03 -0700
Subject: MAINTAINERS: Update RCU, SRCU, and TORTURE-TEST entries

The RCU, SRCU, and TORTURE-TEST entries are missing some recent
changes, so this commit brings them up to date.

Reported-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
---
 MAINTAINERS | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9d5eeff51b5f..27bbc72c6191 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12021,9 +12021,9 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/
 X:	Documentation/RCU/torture.txt
 F:	include/linux/rcu*
-X:	include/linux/srcu.h
+X:	include/linux/srcu*.h
 F:	kernel/rcu/
-X:	kernel/torture.c
+X:	kernel/rcu/srcu*.c
 
 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>
@@ -13060,8 +13060,8 @@ L:	linux-kernel@vger.kernel.org
 W:	http://www.rdrop.com/users/paulmck/RCU/
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
-F:	include/linux/srcu.h
-F:	kernel/rcu/srcu.c
+F:	include/linux/srcu*.h
+F:	kernel/rcu/srcu*.c
 
 SERIAL LOW-POWER INTER-CHIP MEDIA BUS (SLIMbus)
 M:	Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
@@ -14420,6 +14420,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/torture.c
 F:	kernel/rcu/rcutorture.c
+F:	kernel/rcu/rcuperf.c
 F:	kernel/locking/locktorture.c
 
 TOSHIBA ACPI EXTRAS DRIVER
-- 
cgit v1.2.3


From 89b4cd4b9ebf15b01f70b85105ea5f5c6b2a3788 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 11 Jun 2018 12:29:16 -0700
Subject: rcu: Print stall-warning NMI dyntick state in hexadecimal

The ->dynticks_nmi_nesting field records the nesting depth of both
interrupt and NMI handlers.  Because the kernel can enter interrupts
and never leave them (and vice versa) and because NMIs can interrupt
manipulation of the ->dynticks_nmi_nesting field, the values in this
field must be both chosen and maniupated very carefully.  As a result,
although the value is zero when the corresponding CPU is executing
neither an interrupt nor an NMI handler, it is 4,611,686,018,427,387,906
on 64-bit systems when there is a single level of interrupt/NMI handling
in progress.

This number is difficult to remember and interpret, so this commit
switches the output to hexadecimal, resulting in the much nicer
0x4000000000000002.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree_plugin.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 2cc9bf0d363a..c1b17f5b9361 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1801,7 +1801,7 @@ static void print_cpu_stall_info(struct rcu_state *rsp, int cpu)
 	}
 	print_cpu_stall_fast_no_hz(fast_no_hz, cpu);
 	delta = rcu_seq_ctr(rdp->mynode->gp_seq - rdp->rcu_iw_gp_seq);
-	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%ld softirq=%u/%u fqs=%ld %s\n",
+	pr_err("\t%d-%c%c%c%c: (%lu %s) idle=%03x/%ld/%#lx softirq=%u/%u fqs=%ld %s\n",
 	       cpu,
 	       "O."[!!cpu_online(cpu)],
 	       "o."[!!(rdp->grpmask & rdp->mynode->qsmaskinit)],
-- 
cgit v1.2.3


From 52e17ba1d063ab6adb367f288babd380e30bad46 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 19 Jun 2018 08:54:37 -0700
Subject: srcu: Add grace-period number to rcutorture statistics printout

This commit adds the SRCU grace-period number to the rcutorture statistics
printout, which allows it to be compared to the rcutorture "Writer stall
state" message.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/srcutree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index e526b56998af..6c9866a854b1 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -1268,7 +1268,8 @@ void srcu_torture_stats_print(struct srcu_struct *sp, char *tt, char *tf)
 	unsigned long s0 = 0, s1 = 0;
 
 	idx = sp->srcu_idx & 0x1;
-	pr_alert("%s%s Tree SRCU per-CPU(idx=%d):", tt, tf, idx);
+	pr_alert("%s%s Tree SRCU g%ld per-CPU(idx=%d):",
+		 tt, tf, rcu_seq_current(&sp->srcu_gp_seq), idx);
 	for_each_possible_cpu(cpu) {
 		unsigned long l0, l1;
 		unsigned long u0, u1;
-- 
cgit v1.2.3


From b7b6f94cf6e6d961f78064315b6f5de5d9c6414b Mon Sep 17 00:00:00 2001
From: NeilBrown <neilb@suse.com>
Date: Mon, 18 Jun 2018 14:22:40 +1000
Subject: rculist: Improve documentation for list_for_each_entry_from_rcu()

Unfortunately the patch for adding list_for_each_entry_from_rcu()
wasn't the final patch after all review.  It is functionally
correct but the documentation was incomplete.

This patch adds this missing documentation which includes an update to
the documentation for list_for_each_entry_continue_rcu() to match the
documentation for the new list_for_each_entry_from_rcu(), and adds
list_for_each_entry_from_rcu() and the already existing
hlist_for_each_entry_from_rcu() to section 7 of whatisRCU.txt.

Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: NeilBrown <neilb@suse.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/RCU/whatisRCU.txt |  2 ++
 include/linux/rculist.h         | 19 ++++++++++++++++++-
 2 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/Documentation/RCU/whatisRCU.txt b/Documentation/RCU/whatisRCU.txt
index 94288f1b8759..c2a7facf7ff9 100644
--- a/Documentation/RCU/whatisRCU.txt
+++ b/Documentation/RCU/whatisRCU.txt
@@ -820,11 +820,13 @@ RCU list traversal:
 	list_next_rcu
 	list_for_each_entry_rcu
 	list_for_each_entry_continue_rcu
+	list_for_each_entry_from_rcu
 	hlist_first_rcu
 	hlist_next_rcu
 	hlist_pprev_rcu
 	hlist_for_each_entry_rcu
 	hlist_for_each_entry_rcu_bh
+	hlist_for_each_entry_from_rcu
 	hlist_for_each_entry_continue_rcu
 	hlist_for_each_entry_continue_rcu_bh
 	hlist_nulls_first_rcu
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index 36df6ccbc874..4786c2235b98 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -396,7 +396,16 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  * @member:	the name of the list_head within the struct.
  *
  * Continue to iterate over list of given type, continuing after
- * the current position.
+ * the current position which must have been in the list when the RCU read
+ * lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_from_rcu() except
+ * this starts after the given position and that one starts at the given
+ * position.
  */
 #define list_for_each_entry_continue_rcu(pos, head, member) 		\
 	for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \
@@ -411,6 +420,14 @@ static inline void list_splice_tail_init_rcu(struct list_head *list,
  *
  * Iterate over the tail of a list starting from a given position,
  * which must have been in the list when the RCU read lock was taken.
+ * This would typically require either that you obtained the node from a
+ * previous walk of the list in the same RCU read-side critical section, or
+ * that you held some sort of non-RCU reference (such as a reference count)
+ * to keep the node alive *and* in the list.
+ *
+ * This iterator is similar to list_for_each_entry_continue_rcu() except
+ * this starts from the given position and that one starts from the position
+ * after the given position.
  */
 #define list_for_each_entry_from_rcu(pos, head, member)			\
 	for (; &(pos)->member != (head);					\
-- 
cgit v1.2.3


From c7cd161ecb2188c07ba9560ca82aee756575359f Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Tue, 19 Jun 2018 15:14:17 -0700
Subject: rcu: Assign higher prio to RCU threads if rcutorture is built-in

The rcutorture RCU priority boosting tests fail even with CONFIG_RCU_BOOST
set because rcutorture's threads run at the same priority as the default
RCU kthreads (RT class with priority of 1).

This patch checks if RCU torture is built into the kernel and if so,
assigns RT priority 1 to the RCU threads, allowing the rcutorture boost
tests to pass.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/tree.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 7498a416f63b..8143b8d40a6c 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3923,12 +3923,16 @@ static int __init rcu_spawn_gp_kthread(void)
 	struct task_struct *t;
 
 	/* Force priority into range. */
-	if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
+	if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 2
+	    && IS_BUILTIN(CONFIG_RCU_TORTURE_TEST))
+		kthread_prio = 2;
+	else if (IS_ENABLED(CONFIG_RCU_BOOST) && kthread_prio < 1)
 		kthread_prio = 1;
 	else if (kthread_prio < 0)
 		kthread_prio = 0;
 	else if (kthread_prio > 99)
 		kthread_prio = 99;
+
 	if (kthread_prio != kthread_prio_in)
 		pr_alert("rcu_spawn_gp_kthread(): Limited prio to %d from %d\n",
 			 kthread_prio, kthread_prio_in);
-- 
cgit v1.2.3


From 028be12b294e3a059e6fc06852d458fdc82717ed Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 8 May 2018 09:20:34 -0700
Subject: rcutorture: Change units of onoff_interval to jiffies

Some RCU bugs have been sensitive to the frequency of CPU-hotplug
operations, which have been gradually increased over time.  But this
frequency is now at the one-second lower limit that can be specified using
the rcutorture.onoff_interval kernel parameter.  This commit therefore
changes the units of rcutorture.onoff_interval from seconds to jiffies,
and also sets the value specified for this kernel parameter in the TREE03
rcutorture scenario to 200, which is 200 milliseconds for HZ=1000.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 Documentation/admin-guide/kernel-parameters.txt                 | 4 ++--
 kernel/rcu/rcutorture.c                                         | 4 ++--
 tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot      | 2 +-
 tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..77bd3e635313 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3632,8 +3632,8 @@
 			Set time (s) after boot for CPU-hotplug testing.
 
 	rcutorture.onoff_interval= [KNL]
-			Set time (s) between CPU-hotplug operations, or
-			zero to disable CPU-hotplug testing.
+			Set time (jiffies) between CPU-hotplug operations,
+			or zero to disable CPU-hotplug testing.
 
 	rcutorture.shuffle_interval= [KNL]
 			Set task-shuffle interval (s).  Shuffling tasks
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 0481c7286875..eb6d4915b4e6 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -87,7 +87,7 @@ torture_param(int, object_debug, 0,
 	     "Enable debug-object double call_rcu() testing");
 torture_param(int, onoff_holdoff, 0, "Time after boot before CPU hotplugs (s)");
 torture_param(int, onoff_interval, 0,
-	     "Time between CPU hotplugs (s), 0=disable");
+	     "Time between CPU hotplugs (jiffies), 0=disable");
 torture_param(int, shuffle_interval, 3, "Number of seconds between shuffles");
 torture_param(int, shutdown_secs, 0, "Shutdown time (s), <= zero to disable.");
 torture_param(int, stall_cpu, 0, "Stall duration (s), zero to disable.");
@@ -1889,7 +1889,7 @@ rcu_torture_init(void)
 	firsterr = torture_shutdown_init(shutdown_secs, rcu_torture_cleanup);
 	if (firsterr)
 		goto unwind;
-	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval * HZ);
+	firsterr = torture_onoff_init(onoff_holdoff * HZ, onoff_interval);
 	if (firsterr)
 		goto unwind;
 	firsterr = rcu_torture_stall_init();
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
index b79ddb9eb9e8..5c3213cc3ad7 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE03.boot
@@ -1,4 +1,4 @@
-rcutorture.onoff_interval=1 rcutorture.onoff_holdoff=30
+rcutorture.onoff_interval=200 rcutorture.onoff_holdoff=30
 rcutree.gp_preinit_delay=12
 rcutree.gp_init_delay=3
 rcutree.gp_cleanup_delay=3
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
index 24ec91041957..7bab8246392b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcu/ver_functions.sh
@@ -39,7 +39,7 @@ rcutorture_param_onoff () {
 	if ! bootparam_hotplug_cpu "$1" && configfrag_hotplug_cpu "$2"
 	then
 		echo CPU-hotplug kernel, adding rcutorture onoff. 1>&2
-		echo rcutorture.onoff_interval=3 rcutorture.onoff_holdoff=30
+		echo rcutorture.onoff_interval=1000 rcutorture.onoff_holdoff=30
 	fi
 }
 
-- 
cgit v1.2.3


From 6bea2cc5a97b7e9677088b1a93e27edb74ae0e55 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Wed, 16 May 2018 15:30:36 -0700
Subject: rcu: Remove rcutorture test version and sequence number

Back when RCU had a debugfs interface, there was a test version and
sequence number that allowed associating debugfs data with a particular
test run, where the test run started with modprobe and ended with rmmod,
which was how tests were run back on the old ABAT system within IBM.
But rcutorture testing no longer runs on ABAT, and there is no longer an
RCU debugfs interface, so there is no longer any need for test versions
and sequence numbers.

This commit therefore removes the rcutorture_record_test_transition()
and rcutorture_record_progress() functions, and along with them the
rcutorture_testseq and rcutorture_vernum variables that they update.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h        |  4 ----
 kernel/rcu/rcutorture.c |  4 +---
 kernel/rcu/tree.c       | 37 -------------------------------------
 3 files changed, 1 insertion(+), 44 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index aa215d6355f8..0453a7d12b3f 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -444,7 +444,6 @@ enum rcutorture_type {
 #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU)
 void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 			    unsigned long *gp_seq);
-void rcutorture_record_test_transition(void);
 void rcutorture_record_progress(unsigned long vernum);
 void do_trace_rcu_torture_read(const char *rcutorturename,
 			       struct rcu_head *rhp,
@@ -458,7 +457,6 @@ static inline void rcutorture_get_gp_data(enum rcutorture_type test_type,
 	*flags = 0;
 	*gp_seq = 0;
 }
-static inline void rcutorture_record_test_transition(void) { }
 static inline void rcutorture_record_progress(unsigned long vernum) { }
 #ifdef CONFIG_RCU_TRACE
 void do_trace_rcu_torture_read(const char *rcutorturename,
@@ -505,8 +503,6 @@ static inline void rcu_bh_force_quiescent_state(void) { }
 static inline void rcu_sched_force_quiescent_state(void) { }
 static inline void show_rcu_gp_kthreads(void) { }
 #else /* #ifdef CONFIG_TINY_RCU */
-extern unsigned long rcutorture_testseq;
-extern unsigned long rcutorture_vernum;
 unsigned long rcu_get_gp_seq(void);
 unsigned long rcu_bh_get_gp_seq(void);
 unsigned long rcu_sched_get_gp_seq(void);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index eb6d4915b4e6..335387fabac2 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1016,7 +1016,7 @@ rcu_torture_writer(void *arg)
 				break;
 			}
 		}
-		rcutorture_record_progress(++rcu_torture_current_version);
+		rcu_torture_current_version++;
 		/* Cycle through nesting levels of rcu_expedite_gp() calls. */
 		if (can_expedite &&
 		    !(torture_random(&rand) & 0xff & (!!expediting - 1))) {
@@ -1613,7 +1613,6 @@ rcu_torture_cleanup(void)
 	unsigned long gp_seq = 0;
 	int i;
 
-	rcutorture_record_test_transition();
 	if (torture_cleanup_begin()) {
 		if (cur_ops->cb_barrier != NULL)
 			cur_ops->cb_barrier();
@@ -1918,7 +1917,6 @@ rcu_torture_init(void)
 				goto unwind;
 		}
 	}
-	rcutorture_record_test_transition();
 	torture_init_end();
 	return 0;
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index d3333ee2c6f5..65abb399b08d 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -191,18 +191,6 @@ module_param(gp_cleanup_delay, int, 0444);
  */
 #define PER_RCU_NODE_PERIOD 3	/* Number of grace periods between delays. */
 
-/*
- * Track the rcutorture test sequence number and the update version
- * number within a given test.  The rcutorture_testseq is incremented
- * on every rcutorture module load and unload, so has an odd value
- * when a test is running.  The rcutorture_vernum is set to zero
- * when rcutorture starts and is incremented on each rcutorture update.
- * These variables enable correlating rcutorture output with the
- * RCU tracing information.
- */
-unsigned long rcutorture_testseq;
-unsigned long rcutorture_vernum;
-
 /*
  * Compute the mask of online CPUs for the specified rcu_node structure.
  * This will not be stable unless the rcu_node structure's ->lock is
@@ -622,20 +610,6 @@ void show_rcu_gp_kthreads(void)
 }
 EXPORT_SYMBOL_GPL(show_rcu_gp_kthreads);
 
-/*
- * Record the number of times rcutorture tests have been initiated and
- * terminated.  This information allows the debugfs tracing stats to be
- * correlated to the rcutorture messages, even when the rcutorture module
- * is being repeatedly loaded and unloaded.  In other words, we cannot
- * store this state in rcutorture itself.
- */
-void rcutorture_record_test_transition(void)
-{
-	rcutorture_testseq++;
-	rcutorture_vernum = 0;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_test_transition);
-
 /*
  * Send along grace-period-related data for rcutorture diagnostics.
  */
@@ -664,17 +638,6 @@ void rcutorture_get_gp_data(enum rcutorture_type test_type, int *flags,
 }
 EXPORT_SYMBOL_GPL(rcutorture_get_gp_data);
 
-/*
- * Record the number of writer passes through the current rcutorture test.
- * This is also used to correlate debugfs tracing stats with the rcutorture
- * messages.
- */
-void rcutorture_record_progress(unsigned long vernum)
-{
-	rcutorture_vernum++;
-}
-EXPORT_SYMBOL_GPL(rcutorture_record_progress);
-
 /*
  * Return the root node of the specified rcu_state structure.
  */
-- 
cgit v1.2.3


From 2d3625841dcee549653b6f50ffa4e6431305035a Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Thu, 17 May 2018 11:09:47 -0700
Subject: rcuperf: Remove unused torturing_tasks() function

The torturing_tasks() function in rcuperf.c is not used, so this commit
removes it.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcuperf.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/kernel/rcu/rcuperf.c b/kernel/rcu/rcuperf.c
index b080bc4a4f45..06eb5e42726d 100644
--- a/kernel/rcu/rcuperf.c
+++ b/kernel/rcu/rcuperf.c
@@ -369,11 +369,6 @@ static unsigned long rcuperf_seq_diff(unsigned long new, unsigned long old)
 	return cur_ops->gp_diff(new, old);
 }
 
-static bool __maybe_unused torturing_tasks(void)
-{
-	return cur_ops == &tasks_ops;
-}
-
 /*
  * If performance tests complete, wait for shutdown to commence.
  */
-- 
cgit v1.2.3


From 6b06aa723ed705102f3c63a494ac45352ccc0e7c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 22 May 2018 10:56:05 -0700
Subject: rcutorture: Extract common code from rcu_torture_reader()

This commit extracts the code executed on each pass through the loop
in rcu_torture_reader() into a new rcu_torture_one_read() function.
This new function will also be used by rcu_torture_timer().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 98 +++++++++++++++++++++++++++----------------------
 1 file changed, 55 insertions(+), 43 deletions(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 335387fabac2..971e31ae9bcf 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1089,6 +1089,60 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp)
 	kfree(rhp);
 }
 
+/*
+ * Do one read-side critical section, returning false if there was
+ * no data to read.  Can be invoked both from process context and
+ * from a timer handler.
+ */
+static bool rcu_torture_one_read(struct torture_random_state *trsp)
+{
+	int idx;
+	unsigned long started;
+	unsigned long completed;
+	struct rcu_torture *p;
+	int pipe_count;
+	unsigned long long ts;
+
+	idx = cur_ops->readlock();
+	started = cur_ops->get_gp_seq();
+	ts = rcu_trace_clock_local();
+	p = rcu_dereference_check(rcu_torture_current,
+				  rcu_read_lock_bh_held() ||
+				  rcu_read_lock_sched_held() ||
+				  srcu_read_lock_held(srcu_ctlp) ||
+				  torturing_tasks());
+	if (p == NULL) {
+		/* Wait for rcu_torture_writer to get underway */
+		cur_ops->readunlock(idx);
+		return false;
+	}
+	if (p->rtort_mbtest == 0)
+		atomic_inc(&n_rcu_torture_mberror);
+	cur_ops->read_delay(trsp);
+	preempt_disable();
+	pipe_count = p->rtort_pipe_count;
+	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		pipe_count = RCU_TORTURE_PIPE_LEN;
+	}
+	completed = cur_ops->get_gp_seq();
+	if (pipe_count > 1) {
+		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
+					  ts, started, completed);
+		rcu_ftrace_dump(DUMP_ALL);
+	}
+	__this_cpu_inc(rcu_torture_count[pipe_count]);
+	completed = rcutorture_seq_diff(completed, started);
+	if (completed > RCU_TORTURE_PIPE_LEN) {
+		/* Should not happen, but... */
+		completed = RCU_TORTURE_PIPE_LEN;
+	}
+	__this_cpu_inc(rcu_torture_batch[completed]);
+	preempt_enable();
+	cur_ops->readunlock(idx);
+	return true;
+}
+
 /*
  * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
  * incrementing the corresponding element of the pipeline array.  The
@@ -1165,14 +1219,8 @@ static void rcu_torture_timer(struct timer_list *unused)
 static int
 rcu_torture_reader(void *arg)
 {
-	unsigned long started;
-	unsigned long completed;
-	int idx;
 	DEFINE_TORTURE_RANDOM(rand);
-	struct rcu_torture *p;
-	int pipe_count;
 	struct timer_list t;
-	unsigned long long ts;
 
 	VERBOSE_TOROUT_STRING("rcu_torture_reader task started");
 	set_user_nice(current, MAX_NICE);
@@ -1184,44 +1232,8 @@ rcu_torture_reader(void *arg)
 			if (!timer_pending(&t))
 				mod_timer(&t, jiffies + 1);
 		}
-		idx = cur_ops->readlock();
-		started = cur_ops->get_gp_seq();
-		ts = rcu_trace_clock_local();
-		p = rcu_dereference_check(rcu_torture_current,
-					  rcu_read_lock_bh_held() ||
-					  rcu_read_lock_sched_held() ||
-					  srcu_read_lock_held(srcu_ctlp) ||
-					  torturing_tasks());
-		if (p == NULL) {
-			/* Wait for rcu_torture_writer to get underway */
-			cur_ops->readunlock(idx);
+		if (!rcu_torture_one_read(&rand))
 			schedule_timeout_interruptible(HZ);
-			continue;
-		}
-		if (p->rtort_mbtest == 0)
-			atomic_inc(&n_rcu_torture_mberror);
-		cur_ops->read_delay(&rand);
-		preempt_disable();
-		pipe_count = p->rtort_pipe_count;
-		if (pipe_count > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			pipe_count = RCU_TORTURE_PIPE_LEN;
-		}
-		completed = cur_ops->get_gp_seq();
-		if (pipe_count > 1) {
-			do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu,
-						  ts, started, completed);
-			rcu_ftrace_dump(DUMP_ALL);
-		}
-		__this_cpu_inc(rcu_torture_count[pipe_count]);
-		completed = rcutorture_seq_diff(completed, started);
-		if (completed > RCU_TORTURE_PIPE_LEN) {
-			/* Should not happen, but... */
-			completed = RCU_TORTURE_PIPE_LEN;
-		}
-		__this_cpu_inc(rcu_torture_batch[completed]);
-		preempt_enable();
-		cur_ops->readunlock(idx);
 		stutter_wait("rcu_torture_reader");
 	} while (!torture_must_stop());
 	if (irqreader && cur_ops->irq_capable) {
-- 
cgit v1.2.3


From 8da9a59523b6608f4b21f3e489578d0993c0779f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 22 May 2018 11:17:51 -0700
Subject: rcutorture: Use atomic increment for n_rcu_torture_timers

Currently, rcu_torture_timer() relies on a lock to guard updates to
n_rcu_torture_timers.  Unfortunately, consolidating code with
rcu_torture_reader() will dispense with this lock.  This commit
therefore makes n_rcu_torture_timers be an atomic_long_t and uses
atomic_long_inc() to carry out the update.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 971e31ae9bcf..2452e4a29923 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -151,7 +151,7 @@ static long n_rcu_torture_boost_ktrerror;
 static long n_rcu_torture_boost_rterror;
 static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
-static long n_rcu_torture_timers;
+static atomic_long_t n_rcu_torture_timers;
 static long n_barrier_attempts;
 static long n_barrier_successes;
 static atomic_long_t n_cbfloods;
@@ -1160,6 +1160,7 @@ static void rcu_torture_timer(struct timer_list *unused)
 	int pipe_count;
 	unsigned long long ts;
 
+	atomic_long_inc(&n_rcu_torture_timers);
 	idx = cur_ops->readlock();
 	started = cur_ops->get_gp_seq();
 	ts = rcu_trace_clock_local();
@@ -1177,7 +1178,6 @@ static void rcu_torture_timer(struct timer_list *unused)
 		atomic_inc(&n_rcu_torture_mberror);
 	spin_lock(&rand_lock);
 	cur_ops->read_delay(&rand);
-	n_rcu_torture_timers++;
 	spin_unlock(&rand_lock);
 	preempt_disable();
 	pipe_count = p->rtort_pipe_count;
@@ -1290,7 +1290,7 @@ rcu_torture_stats_print(void)
 	pr_cont("rtbf: %ld rtb: %ld nt: %ld ",
 		n_rcu_torture_boost_failure,
 		n_rcu_torture_boosts,
-		n_rcu_torture_timers);
+		atomic_long_read(&n_rcu_torture_timers));
 	torture_onoff_stats();
 	pr_cont("barrier: %ld/%ld:%ld ",
 		n_barrier_successes,
-- 
cgit v1.2.3


From 3025520ec424df8b0fd5cdc319ad6b83406d9954 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 22 May 2018 11:38:47 -0700
Subject: rcutorture: Use per-CPU random state for rcu_torture_timer()

Currently, the rcu_torture_timer() function uses a single global
torture_random_state structure protected by a single global lock.
This conflicts to some extent with performance and scalability,
but even more with the goal of consolidating read-side testing
with rcu_torture_reader().  This commit therefore creates a per-CPU
torture_random_state structure for use by rcu_torture_timer() and
eliminates the lock.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
[ paulmck: Make rcu_torture_timer_rand static, per 0day Test Robot report. ]
---
 include/linux/torture.h |  2 ++
 kernel/rcu/rcutorture.c | 10 +++++-----
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/torture.h b/include/linux/torture.h
index a55e80817dae..61dfd93b6ee4 100644
--- a/include/linux/torture.h
+++ b/include/linux/torture.h
@@ -64,6 +64,8 @@ struct torture_random_state {
 	long trs_count;
 };
 #define DEFINE_TORTURE_RANDOM(name) struct torture_random_state name = { 0, 0 }
+#define DEFINE_TORTURE_RANDOM_PERCPU(name) \
+	DEFINE_PER_CPU(struct torture_random_state, name)
 unsigned long torture_random(struct torture_random_state *trsp);
 
 /* Task shuffler, which causes CPUs to occasionally go idle. */
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 2452e4a29923..d5a5465d2507 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1143,6 +1143,8 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 	return true;
 }
 
+static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand);
+
 /*
  * RCU torture reader from timer handler.  Dereferences rcu_torture_current,
  * incrementing the corresponding element of the pipeline array.  The
@@ -1154,12 +1156,12 @@ static void rcu_torture_timer(struct timer_list *unused)
 	int idx;
 	unsigned long started;
 	unsigned long completed;
-	static DEFINE_TORTURE_RANDOM(rand);
-	static DEFINE_SPINLOCK(rand_lock);
 	struct rcu_torture *p;
 	int pipe_count;
+	struct torture_random_state *trsp;
 	unsigned long long ts;
 
+	trsp = this_cpu_ptr(&rcu_torture_timer_rand);
 	atomic_long_inc(&n_rcu_torture_timers);
 	idx = cur_ops->readlock();
 	started = cur_ops->get_gp_seq();
@@ -1176,9 +1178,7 @@ static void rcu_torture_timer(struct timer_list *unused)
 	}
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
-	spin_lock(&rand_lock);
-	cur_ops->read_delay(&rand);
-	spin_unlock(&rand_lock);
+	cur_ops->read_delay(trsp);
 	preempt_disable();
 	pipe_count = p->rtort_pipe_count;
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
-- 
cgit v1.2.3


From 241b42522abb36c78cdc84d0cade358c4449306f Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Tue, 22 May 2018 11:59:31 -0700
Subject: rcutorture: Make rcu_torture_timer() use rcu_torture_one_read()

This commit saves a few lines of code by making rcu_torture_timer()
invoke rcu_torture_one_read(), thus completing the consolidation of
code between rcu_torture_timer() and rcu_torture_reader().

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 47 +----------------------------------------------
 1 file changed, 1 insertion(+), 46 deletions(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index d5a5465d2507..ac700aa6dcaf 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1153,53 +1153,8 @@ static DEFINE_TORTURE_RANDOM_PERCPU(rcu_torture_timer_rand);
  */
 static void rcu_torture_timer(struct timer_list *unused)
 {
-	int idx;
-	unsigned long started;
-	unsigned long completed;
-	struct rcu_torture *p;
-	int pipe_count;
-	struct torture_random_state *trsp;
-	unsigned long long ts;
-
-	trsp = this_cpu_ptr(&rcu_torture_timer_rand);
 	atomic_long_inc(&n_rcu_torture_timers);
-	idx = cur_ops->readlock();
-	started = cur_ops->get_gp_seq();
-	ts = rcu_trace_clock_local();
-	p = rcu_dereference_check(rcu_torture_current,
-				  rcu_read_lock_bh_held() ||
-				  rcu_read_lock_sched_held() ||
-				  srcu_read_lock_held(srcu_ctlp) ||
-				  torturing_tasks());
-	if (p == NULL) {
-		/* Leave because rcu_torture_writer is not yet underway */
-		cur_ops->readunlock(idx);
-		return;
-	}
-	if (p->rtort_mbtest == 0)
-		atomic_inc(&n_rcu_torture_mberror);
-	cur_ops->read_delay(trsp);
-	preempt_disable();
-	pipe_count = p->rtort_pipe_count;
-	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
-		/* Should not happen, but... */
-		pipe_count = RCU_TORTURE_PIPE_LEN;
-	}
-	completed = cur_ops->get_gp_seq();
-	if (pipe_count > 1) {
-		do_trace_rcu_torture_read(cur_ops->name, &p->rtort_rcu, ts,
-					  started, completed);
-		rcu_ftrace_dump(DUMP_ALL);
-	}
-	__this_cpu_inc(rcu_torture_count[pipe_count]);
-	completed = rcutorture_seq_diff(completed, started);
-	if (completed > RCU_TORTURE_PIPE_LEN) {
-		/* Should not happen, but... */
-		completed = RCU_TORTURE_PIPE_LEN;
-	}
-	__this_cpu_inc(rcu_torture_batch[completed]);
-	preempt_enable();
-	cur_ops->readunlock(idx);
+	(void)rcu_torture_one_read(this_cpu_ptr(&rcu_torture_timer_rand));
 
 	/* Test call_rcu() invocation from interrupt handler. */
 	if (cur_ops->call) {
-- 
cgit v1.2.3


From 2397d072f76b552fc21cda19686d24a8066ced22 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Fri, 25 May 2018 07:29:25 -0700
Subject: rcutorture: Handle extended read-side critical sections

This commit enables rcutorture to test whether RCU properly aggregates
different types of read-side critical sections into a larger section
covering the set.  It does this by extending an initial read-side
critical section randomly for a random number of extensions.  There is
a new rcu_torture_ops field ->extendable that specifies what extensions
are permitted for a given flavor of RCU (for example, SRCU does not
permit any extensions, while RCU-sched permits all types).  Note that
if a given operation (for example, local_bh_disable()) extends an RCU
read-side critical section, then rcutorture feels free to also start
and end the critical section with that operation's type of disabling.

Disabling operations include local_bh_disable(), local_irq_disable(),
and preempt_disable().  This commit also adds a new "busted_srcud"
torture type, which verifies rcutorture's ability to detect extensions
of RCU read-side critical sections that are not handled.  Gotta test
the test, after all!

Note that it is not legal to invoke local_bh_disable() with interrupts
disabled, and this transition is avoided by overriding the random-number
generator when it wants to call local_bh_disable() while interrupts
are disabled.  The code instead leaves both interrupts and bh/softirq
disabled in this case.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 158 ++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 152 insertions(+), 6 deletions(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index ac700aa6dcaf..f97757755207 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -62,6 +62,18 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@joshtriplett.org>");
 
 
+/* Bits for ->extendables field, extendables param, and related definitions. */
+#define RCUTORTURE_RDR_SHIFT	 8	/* Put SRCU index in upper bits. */
+#define RCUTORTURE_RDR_MASK	 ((1 << RCUTORTURE_RDR_SHIFT) - 1)
+#define RCUTORTURE_RDR_BH	 0x1	/* Extend readers by disabling bh. */
+#define RCUTORTURE_RDR_IRQ	 0x2	/*  ... disabling interrupts. */
+#define RCUTORTURE_RDR_PREEMPT	 0x4	/*  ... disabling preemption. */
+#define RCUTORTURE_RDR_RCU	 0x8	/*  ... entering another RCU reader. */
+#define RCUTORTURE_MAX_EXTEND	 (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \
+				  RCUTORTURE_RDR_PREEMPT)
+#define RCUTORTURE_RDR_MAX_LOOPS 0x7	/* Maximum reader extensions. */
+					/* Must be power of two minus one. */
+
 torture_param(int, cbflood_inter_holdoff, HZ,
 	      "Holdoff between floods (jiffies)");
 torture_param(int, cbflood_intra_holdoff, 1,
@@ -69,6 +81,8 @@ torture_param(int, cbflood_intra_holdoff, 1,
 torture_param(int, cbflood_n_burst, 3, "# bursts in flood, zero to disable");
 torture_param(int, cbflood_n_per_burst, 20000,
 	      "# callbacks per burst in flood");
+torture_param(int, extendables, RCUTORTURE_MAX_EXTEND,
+	      "Extend readers by disabling bh (1), irqs (2), or preempt (4)");
 torture_param(int, fqs_duration, 0,
 	      "Duration of fqs bursts (us), 0 to disable");
 torture_param(int, fqs_holdoff, 0, "Holdoff time within fqs bursts (us)");
@@ -277,6 +291,8 @@ struct rcu_torture_ops {
 	void (*stats)(void);
 	int irq_capable;
 	int can_boost;
+	int extendables;
+	int ext_irq_conflict;
 	const char *name;
 };
 
@@ -452,6 +468,8 @@ static struct rcu_torture_ops rcu_bh_ops = {
 	.fqs		= rcu_bh_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
+	.extendables	= (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ),
+	.ext_irq_conflict = RCUTORTURE_RDR_RCU,
 	.name		= "rcu_bh"
 };
 
@@ -622,6 +640,26 @@ static struct rcu_torture_ops srcud_ops = {
 	.name		= "srcud"
 };
 
+/* As above, but broken due to inappropriate reader extension. */
+static struct rcu_torture_ops busted_srcud_ops = {
+	.ttype		= SRCU_FLAVOR,
+	.init		= srcu_torture_init,
+	.cleanup	= srcu_torture_cleanup,
+	.readlock	= srcu_torture_read_lock,
+	.read_delay	= rcu_read_delay,
+	.readunlock	= srcu_torture_read_unlock,
+	.get_gp_seq	= srcu_torture_completed,
+	.deferred_free	= srcu_torture_deferred_free,
+	.sync		= srcu_torture_synchronize,
+	.exp_sync	= srcu_torture_synchronize_expedited,
+	.call		= srcu_torture_call,
+	.cb_barrier	= srcu_torture_barrier,
+	.stats		= srcu_torture_stats,
+	.irq_capable	= 1,
+	.extendables	= RCUTORTURE_MAX_EXTEND,
+	.name		= "busted_srcud"
+};
+
 /*
  * Definitions for sched torture testing.
  */
@@ -660,6 +698,7 @@ static struct rcu_torture_ops sched_ops = {
 	.fqs		= rcu_sched_force_quiescent_state,
 	.stats		= NULL,
 	.irq_capable	= 1,
+	.extendables	= RCUTORTURE_MAX_EXTEND,
 	.name		= "sched"
 };
 
@@ -1089,6 +1128,110 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp)
 	kfree(rhp);
 }
 
+/*
+ * Do one extension of an RCU read-side critical section using the
+ * current reader state in readstate (set to zero for initial entry
+ * to extended critical section), set the new state as specified by
+ * newstate (set to zero for final exit from extended critical section),
+ * and random-number-generator state in trsp.  If this is neither the
+ * beginning or end of the critical section and if there was actually a
+ * change, do a ->read_delay().
+ */
+static void rcutorture_one_extend(int *readstate, int newstate,
+				  struct torture_random_state *trsp)
+{
+	int idxnew = -1;
+	int idxold = *readstate;
+	int statesnew = ~*readstate & newstate;
+	int statesold = *readstate & ~newstate;
+
+	WARN_ON_ONCE(idxold < 0);
+	WARN_ON_ONCE((idxold >> RCUTORTURE_RDR_SHIFT) > 1);
+
+	/* First, put new protection in place to avoid critical-section gap. */
+	if (statesnew & RCUTORTURE_RDR_BH)
+		local_bh_disable();
+	if (statesnew & RCUTORTURE_RDR_IRQ)
+		local_irq_disable();
+	if (statesnew & RCUTORTURE_RDR_PREEMPT)
+		preempt_disable();
+	if (statesnew & RCUTORTURE_RDR_RCU)
+		idxnew = cur_ops->readlock() << RCUTORTURE_RDR_SHIFT;
+
+	/* Next, remove old protection, irq first due to bh conflict. */
+	if (statesold & RCUTORTURE_RDR_IRQ)
+		local_irq_enable();
+	if (statesold & RCUTORTURE_RDR_BH)
+		local_bh_enable();
+	if (statesold & RCUTORTURE_RDR_PREEMPT)
+		preempt_enable();
+	if (statesold & RCUTORTURE_RDR_RCU)
+		cur_ops->readunlock(idxold >> RCUTORTURE_RDR_SHIFT);
+
+	/* Delay if neither beginning nor end and there was a change. */
+	if ((statesnew || statesold) && *readstate && newstate)
+		cur_ops->read_delay(trsp);
+
+	/* Update the reader state. */
+	if (idxnew == -1)
+		idxnew = idxold & ~RCUTORTURE_RDR_MASK;
+	WARN_ON_ONCE(idxnew < 0);
+	WARN_ON_ONCE((idxnew >> RCUTORTURE_RDR_SHIFT) > 1);
+	*readstate = idxnew | newstate;
+	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) < 0);
+	WARN_ON_ONCE((*readstate >> RCUTORTURE_RDR_SHIFT) > 1);
+}
+
+/* Return the biggest extendables mask given current RCU and boot parameters. */
+static int rcutorture_extend_mask_max(void)
+{
+	int mask;
+
+	WARN_ON_ONCE(extendables & ~RCUTORTURE_MAX_EXTEND);
+	mask = extendables & RCUTORTURE_MAX_EXTEND & cur_ops->extendables;
+	mask = mask | RCUTORTURE_RDR_RCU;
+	return mask;
+}
+
+/* Return a random protection state mask, but with at least one bit set. */
+static int
+rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
+{
+	int mask = rcutorture_extend_mask_max();
+
+	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
+	mask = mask & (torture_random(trsp) >> RCUTORTURE_RDR_SHIFT);
+	if ((mask & RCUTORTURE_RDR_IRQ) &&
+	    !(mask & RCUTORTURE_RDR_BH) &&
+	    (oldmask & RCUTORTURE_RDR_BH))
+		mask |= RCUTORTURE_RDR_BH; /* Can't enable bh w/irq disabled. */
+	if ((mask & RCUTORTURE_RDR_IRQ) &&
+	    !(mask & cur_ops->ext_irq_conflict) &&
+	    (oldmask & cur_ops->ext_irq_conflict))
+		mask |= cur_ops->ext_irq_conflict; /* Or if readers object. */
+	return mask ?: RCUTORTURE_RDR_RCU;
+}
+
+/*
+ * Do a randomly selected number of extensions of an existing RCU read-side
+ * critical section.
+ */
+static void rcutorture_loop_extend(int *readstate,
+				   struct torture_random_state *trsp)
+{
+	int i;
+	int mask = rcutorture_extend_mask_max();
+
+	WARN_ON_ONCE(!*readstate); /* -Existing- RCU read-side critsect! */
+	if (!((mask - 1) & mask))
+		return;  /* Current RCU flavor not extendable. */
+	i = (torture_random(trsp) >> 3) & RCUTORTURE_RDR_MAX_LOOPS;
+	while (i--) {
+		mask = rcutorture_extend_mask(*readstate, trsp);
+		rcutorture_one_extend(readstate, mask, trsp);
+	}
+}
+
 /*
  * Do one read-side critical section, returning false if there was
  * no data to read.  Can be invoked both from process context and
@@ -1096,14 +1239,16 @@ static void rcu_torture_timer_cb(struct rcu_head *rhp)
  */
 static bool rcu_torture_one_read(struct torture_random_state *trsp)
 {
-	int idx;
 	unsigned long started;
 	unsigned long completed;
+	int newstate;
 	struct rcu_torture *p;
 	int pipe_count;
+	int readstate = 0;
 	unsigned long long ts;
 
-	idx = cur_ops->readlock();
+	newstate = rcutorture_extend_mask(readstate, trsp);
+	rcutorture_one_extend(&readstate, newstate, trsp);
 	started = cur_ops->get_gp_seq();
 	ts = rcu_trace_clock_local();
 	p = rcu_dereference_check(rcu_torture_current,
@@ -1113,12 +1258,12 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 				  torturing_tasks());
 	if (p == NULL) {
 		/* Wait for rcu_torture_writer to get underway */
-		cur_ops->readunlock(idx);
+		rcutorture_one_extend(&readstate, 0, trsp);
 		return false;
 	}
 	if (p->rtort_mbtest == 0)
 		atomic_inc(&n_rcu_torture_mberror);
-	cur_ops->read_delay(trsp);
+	rcutorture_loop_extend(&readstate, trsp);
 	preempt_disable();
 	pipe_count = p->rtort_pipe_count;
 	if (pipe_count > RCU_TORTURE_PIPE_LEN) {
@@ -1139,7 +1284,8 @@ static bool rcu_torture_one_read(struct torture_random_state *trsp)
 	}
 	__this_cpu_inc(rcu_torture_batch[completed]);
 	preempt_enable();
-	cur_ops->readunlock(idx);
+	rcutorture_one_extend(&readstate, 0, trsp);
+	WARN_ON_ONCE(readstate & RCUTORTURE_RDR_MASK);
 	return true;
 }
 
@@ -1704,7 +1850,7 @@ rcu_torture_init(void)
 	int firsterr = 0;
 	static struct rcu_torture_ops *torture_ops[] = {
 		&rcu_ops, &rcu_bh_ops, &rcu_busted_ops, &srcu_ops, &srcud_ops,
-		&sched_ops, &tasks_ops,
+		&busted_srcud_ops, &sched_ops, &tasks_ops,
 	};
 
 	if (!torture_init_begin(torture_type, verbose))
-- 
cgit v1.2.3


From bf1bef50bee13b2292929f4b86118302a3827a32 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Sun, 10 Jun 2018 08:50:09 -0700
Subject: rcutorture: Emphasize testing of single reader protection type

For RCU implementations supporting multiple types of reader protection,
rcutorture currently randomly selects the combinations of types of
protection for each phase of each reader.  The problem with this,
for example, given the four kinds of protection for RCU-sched
(local_irq_disable(), local_bh_disable(), preempt_disable(), and
rcu_read_lock_sched()), the reader will be protected by a single
mechanism only 25% of the time.  We really heavier testing of single
read-side mechanisms.

This commit therefore uses only a single mechanism about 60% of the time,
half of the time explicitly and one-eighth of the time by chance.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index f97757755207..aa0be7ec2a26 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -69,6 +69,7 @@ MODULE_AUTHOR("Paul E. McKenney <paulmck@us.ibm.com> and Josh Triplett <josh@jos
 #define RCUTORTURE_RDR_IRQ	 0x2	/*  ... disabling interrupts. */
 #define RCUTORTURE_RDR_PREEMPT	 0x4	/*  ... disabling preemption. */
 #define RCUTORTURE_RDR_RCU	 0x8	/*  ... entering another RCU reader. */
+#define RCUTORTURE_RDR_NBITS	 4	/* Number of bits defined above. */
 #define RCUTORTURE_MAX_EXTEND	 (RCUTORTURE_RDR_BH | RCUTORTURE_RDR_IRQ | \
 				  RCUTORTURE_RDR_PREEMPT)
 #define RCUTORTURE_RDR_MAX_LOOPS 0x7	/* Maximum reader extensions. */
@@ -1198,9 +1199,15 @@ static int
 rcutorture_extend_mask(int oldmask, struct torture_random_state *trsp)
 {
 	int mask = rcutorture_extend_mask_max();
+	unsigned long randmask1 = torture_random(trsp) >> 8;
+	unsigned long randmask2 = randmask1 >> 1;
 
 	WARN_ON_ONCE(mask >> RCUTORTURE_RDR_SHIFT);
-	mask = mask & (torture_random(trsp) >> RCUTORTURE_RDR_SHIFT);
+	/* Half the time lots of bits, half the time only one bit. */
+	if (randmask1 & 0x1)
+		mask = mask & randmask2;
+	else
+		mask = mask & (1 << (randmask2 % RCUTORTURE_RDR_NBITS));
 	if ((mask & RCUTORTURE_RDR_IRQ) &&
 	    !(mask & RCUTORTURE_RDR_BH) &&
 	    (oldmask & RCUTORTURE_RDR_BH))
-- 
cgit v1.2.3


From 450efca7182a516a12dfcc0311abfd242bde42b2 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Sun, 10 Jun 2018 16:45:43 -0700
Subject: rcutorture: Disable RT throttling for boost tests

Currently rcutorture is not able to torture RCU boosting properly. This
is because the rcutorture's boost threads which are doing the torturing
may be throttled due to RT throttling.

This patch makes rcutorture use the right torture technique (unthrottled
rcutorture boost tasks) for torturing RCU so that the test fails
correctly when no boost is available.

Currently this requires accessing sysctl_sched_rt_runtime directly, but
that should be Ok since rcutorture is test code. Such direct access is
also only possible if rcutorture is used as a built-in so make it
conditional on that.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index aa0be7ec2a26..74e47d0a618c 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -55,6 +55,7 @@
 #include <linux/torture.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/sysctl.h>
 
 #include "rcu.h"
 
@@ -772,6 +773,32 @@ static void rcu_torture_boost_cb(struct rcu_head *head)
 	smp_store_release(&rbip->inflight, 0);
 }
 
+static int old_rt_runtime = -1;
+
+static void rcu_torture_disable_rt_throttle(void)
+{
+	/*
+	 * Disable RT throttling so that rcutorture's boost threads don't get
+	 * throttled. Only possible if rcutorture is built-in otherwise the
+	 * user should manually do this by setting the sched_rt_period_us and
+	 * sched_rt_runtime sysctls.
+	 */
+	if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime != -1)
+		return;
+
+	old_rt_runtime = sysctl_sched_rt_runtime;
+	sysctl_sched_rt_runtime = -1;
+}
+
+static void rcu_torture_enable_rt_throttle(void)
+{
+	if (!IS_BUILTIN(CONFIG_RCU_TORTURE_TEST) || old_rt_runtime == -1)
+		return;
+
+	sysctl_sched_rt_runtime = old_rt_runtime;
+	old_rt_runtime = -1;
+}
+
 static int rcu_torture_boost(void *arg)
 {
 	unsigned long call_rcu_time;
@@ -1511,6 +1538,7 @@ static int rcutorture_booster_cleanup(unsigned int cpu)
 	mutex_lock(&boost_mutex);
 	t = boost_tasks[cpu];
 	boost_tasks[cpu] = NULL;
+	rcu_torture_enable_rt_throttle();
 	mutex_unlock(&boost_mutex);
 
 	/* This must be outside of the mutex, otherwise deadlock! */
@@ -1527,6 +1555,7 @@ static int rcutorture_booster_init(unsigned int cpu)
 
 	/* Don't allow time recalculation while creating a new task. */
 	mutex_lock(&boost_mutex);
+	rcu_torture_disable_rt_throttle();
 	VERBOSE_TOROUT_STRING("Creating rcu_torture_boost task");
 	boost_tasks[cpu] = kthread_create_on_node(rcu_torture_boost, NULL,
 						  cpu_to_node(cpu),
-- 
cgit v1.2.3


From 3b745c8969c752601cb68c82a06735363563ab42 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Sun, 10 Jun 2018 16:45:44 -0700
Subject: rcutorture: Make boost test more robust

Currently, with RCU_BOOST disabled, I get no failures when forcing
rcutorture to test RCU boost priority inversion. The reason seems to be
that we don't check for failures if the callback never ran at all for
the duration of the boost-test loop.

Further, the 'rtb' and 'rtbf' counters seem to be used inconsistently.
'rtb' is incremented at the start of each test and 'rtbf' is incremented
per-cpu on each failure of call_rcu. So its possible 'rtbf' > 'rtb'.

To test the boost with rcutorture, I did following on a 4-CPU x86 machine:

modprobe rcutorture  test_boost=2
sleep 20
rmmod rcutorture

With patch:
rtbf: 8 rtb: 12

Without patch:
rtbf: 0 rtb: 2

In summary this patch:
 - Increments failed and total test counters once per boost-test.
 - Checks for failure cases correctly.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 45 +++++++++++++++++++++++++++++++++++++++------
 1 file changed, 39 insertions(+), 6 deletions(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 74e47d0a618c..36b9b8266213 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -799,6 +799,18 @@ static void rcu_torture_enable_rt_throttle(void)
 	old_rt_runtime = -1;
 }
 
+static bool rcu_torture_boost_failed(unsigned long start, unsigned long end)
+{
+	if (end - start > test_boost_duration * HZ - HZ / 2) {
+		VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
+		n_rcu_torture_boost_failure++;
+
+		return true; /* failed */
+	}
+
+	return false; /* passed */
+}
+
 static int rcu_torture_boost(void *arg)
 {
 	unsigned long call_rcu_time;
@@ -819,6 +831,21 @@ static int rcu_torture_boost(void *arg)
 	init_rcu_head_on_stack(&rbi.rcu);
 	/* Each pass through the following loop does one boost-test cycle. */
 	do {
+		/* Track if the test failed already in this test interval? */
+		bool failed = false;
+
+		/* Increment n_rcu_torture_boosts once per boost-test */
+		while (!kthread_should_stop()) {
+			if (mutex_trylock(&boost_mutex)) {
+				n_rcu_torture_boosts++;
+				mutex_unlock(&boost_mutex);
+				break;
+			}
+			schedule_timeout_uninterruptible(1);
+		}
+		if (kthread_should_stop())
+			goto checkwait;
+
 		/* Wait for the next test interval. */
 		oldstarttime = boost_starttime;
 		while (ULONG_CMP_LT(jiffies, oldstarttime)) {
@@ -837,11 +864,10 @@ static int rcu_torture_boost(void *arg)
 				/* RCU core before ->inflight = 1. */
 				smp_store_release(&rbi.inflight, 1);
 				call_rcu(&rbi.rcu, rcu_torture_boost_cb);
-				if (jiffies - call_rcu_time >
-					 test_boost_duration * HZ - HZ / 2) {
-					VERBOSE_TOROUT_STRING("rcu_torture_boost boosting failed");
-					n_rcu_torture_boost_failure++;
-				}
+				/* Check if the boost test failed */
+				failed = failed ||
+					 rcu_torture_boost_failed(call_rcu_time,
+								 jiffies);
 				call_rcu_time = jiffies;
 			}
 			stutter_wait("rcu_torture_boost");
@@ -849,6 +875,14 @@ static int rcu_torture_boost(void *arg)
 				goto checkwait;
 		}
 
+		/*
+		 * If boost never happened, then inflight will always be 1, in
+		 * this case the boost check would never happen in the above
+		 * loop so do another one here.
+		 */
+		if (!failed && smp_load_acquire(&rbi.inflight))
+			rcu_torture_boost_failed(call_rcu_time, jiffies);
+
 		/*
 		 * Set the start time of the next test interval.
 		 * Yes, this is vulnerable to long delays, but such
@@ -861,7 +895,6 @@ static int rcu_torture_boost(void *arg)
 			if (mutex_trylock(&boost_mutex)) {
 				boost_starttime = jiffies +
 						  test_boost_interval * HZ;
-				n_rcu_torture_boosts++;
 				mutex_unlock(&boost_mutex);
 				break;
 			}
-- 
cgit v1.2.3


From 622be33fcbc93e9b672b99ed338369eb5e843ac3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 18 Jun 2018 16:47:34 +0200
Subject: rcutorture: Use monotonic timestamp for stall detection

The get_seconds() call is deprecated because it overflows on 32-bit
architectures. The algorithm in rcu_torture_stall() can deal with
the overflow, but another problem here is that using a CLOCK_REALTIME
stamp can lead to a false-positive stall warning when a settimeofday()
happens concurrently.

Using ktime_get_seconds() instead avoids those issues and will never
overflow. The added cast to 'unsigned long' however is necessary to
make ULONG_CMP_LT() work correctly.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 36b9b8266213..049b3735dba8 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1622,7 +1622,7 @@ static int rcu_torture_stall(void *args)
 		VERBOSE_TOROUT_STRING("rcu_torture_stall end holdoff");
 	}
 	if (!kthread_should_stop()) {
-		stop_at = get_seconds() + stall_cpu;
+		stop_at = ktime_get_seconds() + stall_cpu;
 		/* RCU CPU stall is expected behavior in following code. */
 		rcu_read_lock();
 		if (stall_cpu_irqsoff)
@@ -1631,7 +1631,8 @@ static int rcu_torture_stall(void *args)
 			preempt_disable();
 		pr_alert("rcu_torture_stall start on CPU %d.\n",
 			 smp_processor_id());
-		while (ULONG_CMP_LT(get_seconds(), stop_at))
+		while (ULONG_CMP_LT((unsigned long)ktime_get_seconds(),
+				    stop_at))
 			continue;  /* Induce RCU CPU stall warning. */
 		if (stall_cpu_irqsoff)
 			local_irq_enable();
-- 
cgit v1.2.3


From 4babd855fd6137f9792117eb73b096c221a49d3c Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Tue, 19 Jun 2018 15:14:18 -0700
Subject: rcutorture: Add support to detect if boost kthread prio is too low

When rcutorture is built in to the kernel, an earlier patch detects
that and raises the priority of RCU's kthreads to allow rcutorture's
RCU priority boosting tests to succeed.

However, if rcutorture is built as a module, those priorities must be
raised manually via the rcutree.kthread_prio kernel boot parameter.
If this manual step is not taken, rcutorture's RCU priority boosting
tests will fail due to kthread starvation.  One approach would be to
raise the default priority, but that risks breaking existing users.
Another approach would be to allow runtime adjustment of RCU's kthread
priorities, but that introduces numerous "interesting" race conditions.
This patch therefore instead detects too-low priorities, and prints a
message and disables the RCU priority boosting tests in that case.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcu.h        |  2 ++
 kernel/rcu/rcutorture.c | 32 ++++++++++++++++++++++++++++----
 kernel/rcu/tree.c       |  7 +++++++
 3 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/kernel/rcu/rcu.h b/kernel/rcu/rcu.h
index 0453a7d12b3f..bee070979970 100644
--- a/kernel/rcu/rcu.h
+++ b/kernel/rcu/rcu.h
@@ -502,6 +502,7 @@ static inline void rcu_force_quiescent_state(void) { }
 static inline void rcu_bh_force_quiescent_state(void) { }
 static inline void rcu_sched_force_quiescent_state(void) { }
 static inline void show_rcu_gp_kthreads(void) { }
+static inline int rcu_get_gp_kthreads_prio(void) { return 0; }
 #else /* #ifdef CONFIG_TINY_RCU */
 unsigned long rcu_get_gp_seq(void);
 unsigned long rcu_bh_get_gp_seq(void);
@@ -510,6 +511,7 @@ unsigned long rcu_exp_batches_completed(void);
 unsigned long rcu_exp_batches_completed_sched(void);
 unsigned long srcu_batches_completed(struct srcu_struct *sp);
 void show_rcu_gp_kthreads(void);
+int rcu_get_gp_kthreads_prio(void);
 void rcu_force_quiescent_state(void);
 void rcu_bh_force_quiescent_state(void);
 void rcu_sched_force_quiescent_state(void);
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 049b3735dba8..e3d2d4f1d928 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -1787,6 +1787,32 @@ static void rcu_torture_barrier_cleanup(void)
 	}
 }
 
+static bool rcu_torture_can_boost(void)
+{
+	static int boost_warn_once;
+	int prio;
+
+	if (!(test_boost == 1 && cur_ops->can_boost) && test_boost != 2)
+		return false;
+
+	prio = rcu_get_gp_kthreads_prio();
+	if (!prio)
+		return false;
+
+	if (prio < 2) {
+		if (boost_warn_once  == 1)
+			return false;
+
+		pr_alert("%s: WARN: RCU kthread priority too low to test boosting. "
+			 "Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 "
+			 "on the kernel command line.\n", KBUILD_MODNAME);
+		boost_warn_once = 1;
+		return false;
+	}
+
+	return true;
+}
+
 static enum cpuhp_state rcutor_hp;
 
 static void
@@ -1831,8 +1857,7 @@ rcu_torture_cleanup(void)
 	torture_stop_kthread(rcu_torture_fqs, fqs_task);
 	for (i = 0; i < ncbflooders; i++)
 		torture_stop_kthread(rcu_torture_cbflood, cbflood_task[i]);
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2)
+	if (rcu_torture_can_boost())
 		cpuhp_remove_state(rcutor_hp);
 
 	/*
@@ -2056,8 +2081,7 @@ rcu_torture_init(void)
 		test_boost_interval = 1;
 	if (test_boost_duration < 2)
 		test_boost_duration = 2;
-	if ((test_boost == 1 && cur_ops->can_boost) ||
-	    test_boost == 2) {
+	if (rcu_torture_can_boost()) {
 
 		boost_starttime = jiffies + test_boost_interval * HZ;
 
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 65abb399b08d..b4bcb5e21ca6 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -180,6 +180,13 @@ module_param(gp_init_delay, int, 0444);
 static int gp_cleanup_delay;
 module_param(gp_cleanup_delay, int, 0444);
 
+/* Retreive RCU kthreads priority for rcutorture */
+int rcu_get_gp_kthreads_prio(void)
+{
+	return kthread_prio;
+}
+EXPORT_SYMBOL_GPL(rcu_get_gp_kthreads_prio);
+
 /*
  * Number of grace periods between delays, normalized by the duration of
  * the delay.  The longer the delay, the more the grace periods between
-- 
cgit v1.2.3


From bf5b64355a3ce41752856b66c4efad4d7a88e84b Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Tue, 19 Jun 2018 15:14:19 -0700
Subject: rcutorture: Fix rcu_barrier successes counter

The rcutorture test module currently increments both successes and error
for the barrier test upon error, which results in misleading statistics
being printed.  This commit therefore changes the code to increment the
success counter only when the test actually passes.

This change was tested by by returning from the barrier callback without
incrementing the callback counter, thus introducing what appeared to
rcutorture to be rcu_barrier() failures.

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcu/rcutorture.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index e3d2d4f1d928..bdc86cdf3b8b 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -169,7 +169,7 @@ static long n_rcu_torture_boost_failure;
 static long n_rcu_torture_boosts;
 static atomic_long_t n_rcu_torture_timers;
 static long n_barrier_attempts;
-static long n_barrier_successes;
+static long n_barrier_successes; /* did rcu_barrier test succeed? */
 static atomic_long_t n_cbfloods;
 static struct list_head rcu_torture_removed;
 
@@ -1723,8 +1723,9 @@ static int rcu_torture_barrier(void *arg)
 			       atomic_read(&barrier_cbs_invoked),
 			       n_barrier_cbs);
 			WARN_ON_ONCE(1);
+		} else {
+			n_barrier_successes++;
 		}
-		n_barrier_successes++;
 		schedule_timeout_interruptible(HZ / 10);
 	} while (!torture_must_stop());
 	torture_kthread_stopping("rcu_torture_barrier");
@@ -1803,9 +1804,7 @@ static bool rcu_torture_can_boost(void)
 		if (boost_warn_once  == 1)
 			return false;
 
-		pr_alert("%s: WARN: RCU kthread priority too low to test boosting. "
-			 "Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 "
-			 "on the kernel command line.\n", KBUILD_MODNAME);
+		pr_alert("%s: WARN: RCU kthread priority too low to test boosting.  Skipping RCU boost test. Try passing rcutree.kthread_prio > 1 on the kernel command line.\n", KBUILD_MODNAME);
 		boost_warn_once = 1;
 		return false;
 	}
-- 
cgit v1.2.3


From 0761680d521559813648fb430ddeb479c97ab060 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Wed, 11 Jul 2018 17:01:20 +0200
Subject: net: ipv4: fix listify ip_rcv_finish in case of forwarding

In commit 5fa12739a53d ("net: ipv4: listify ip_rcv_finish") calling
dst_input(skb) was split-out.  The ip_sublist_rcv_finish() just calls
dst_input(skb) in a loop.

The problem is that ip_sublist_rcv_finish() forgot to remove the SKB
from the list before invoking dst_input().  Further more we need to
clear skb->next as other parts of the network stack use another kind
of SKB lists for xmit_more (see dev_hard_start_xmit).

A crash occurs if e.g. dst_input() invoke ip_forward(), which calls
dst_output()/ip_output() that eventually calls __dev_queue_xmit() +
sch_direct_xmit(), and a crash occurs in validate_xmit_skb_list().

This patch only fixes the crash, but there is a huge potential for
a performance boost if we can pass an SKB-list through to ip_forward.

Fixes: 5fa12739a53d ("net: ipv4: listify ip_rcv_finish")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_input.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 1a3b6f32b1c9..3196cf58f418 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -530,8 +530,14 @@ static void ip_sublist_rcv_finish(struct list_head *head)
 {
 	struct sk_buff *skb, *next;
 
-	list_for_each_entry_safe(skb, next, head, list)
+	list_for_each_entry_safe(skb, next, head, list) {
+		list_del(&skb->list);
+		/* Handle ip{6}_forward case, as sch_direct_xmit have
+		 * another kind of SKB-list usage (see validate_xmit_skb_list)
+		 */
+		skb->next = NULL;
 		dst_input(skb);
+	}
 }
 
 static void ip_list_rcv_finish(struct net *net, struct sock *sk,
-- 
cgit v1.2.3


From 3b346c18149674ee40dea5281c8644a572ef3fb1 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:38 +0200
Subject: s390/qeth: various buffer management cleanups

Use the new qeth_scrub_qdio_buffer() helper, remove an extra parameter
from qeth_clear_output_buffer(), init the bufstates.user field just once
(in qeth_flush_buffers()) and remove some noisy trace messages.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 66 ++++++++++++---------------------------
 1 file changed, 20 insertions(+), 46 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index d01ac29fd986..916c17d93ddb 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1267,8 +1267,7 @@ static void qeth_release_skbs(struct qeth_qdio_out_buffer *buf)
 }
 
 static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
-		struct qeth_qdio_out_buffer *buf,
-		enum qeth_qdio_buffer_states newbufstate)
+				     struct qeth_qdio_out_buffer *buf)
 {
 	int i;
 
@@ -1276,23 +1275,19 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 	if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ)
 		atomic_dec(&queue->set_pci_flags_count);
 
-	if (newbufstate == QETH_QDIO_BUF_EMPTY) {
-		qeth_release_skbs(buf);
-	}
+	qeth_release_skbs(buf);
+
 	for (i = 0; i < QETH_MAX_BUFFER_ELEMENTS(queue->card); ++i) {
 		if (buf->buffer->element[i].addr && buf->is_header[i])
 			kmem_cache_free(qeth_core_header_cache,
 				buf->buffer->element[i].addr);
 		buf->is_header[i] = 0;
-		buf->buffer->element[i].length = 0;
-		buf->buffer->element[i].addr = NULL;
-		buf->buffer->element[i].eflags = 0;
-		buf->buffer->element[i].sflags = 0;
 	}
-	buf->buffer->element[15].eflags = 0;
-	buf->buffer->element[15].sflags = 0;
+
+	qeth_scrub_qdio_buffer(buf->buffer,
+			       QETH_MAX_BUFFER_ELEMENTS(queue->card));
 	buf->next_element_to_fill = 0;
-	atomic_set(&buf->state, newbufstate);
+	atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
 }
 
 static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free)
@@ -1303,7 +1298,7 @@ static void qeth_clear_outq_buffers(struct qeth_qdio_out_q *q, int free)
 		if (!q->bufs[j])
 			continue;
 		qeth_cleanup_handled_pending(q, j, 1);
-		qeth_clear_output_buffer(q, q->bufs[j], QETH_QDIO_BUF_EMPTY);
+		qeth_clear_output_buffer(q, q->bufs[j]);
 		if (free) {
 			kmem_cache_free(qeth_qdio_outbuf_cache, q->bufs[j]);
 			q->bufs[j] = NULL;
@@ -2473,15 +2468,12 @@ static int qeth_ulp_setup(struct qeth_card *card)
 
 static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx)
 {
-	int rc;
 	struct qeth_qdio_out_buffer *newbuf;
 
-	rc = 0;
 	newbuf = kmem_cache_zalloc(qeth_qdio_outbuf_cache, GFP_ATOMIC);
-	if (!newbuf) {
-		rc = -ENOMEM;
-		goto out;
-	}
+	if (!newbuf)
+		return -ENOMEM;
+
 	newbuf->buffer = q->qdio_bufs[bidx];
 	skb_queue_head_init(&newbuf->skb_list);
 	lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key);
@@ -2490,15 +2482,7 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx)
 	newbuf->next_pending = q->bufs[bidx];
 	atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY);
 	q->bufs[bidx] = newbuf;
-	if (q->bufstates) {
-		q->bufstates[bidx].user = newbuf;
-		QETH_CARD_TEXT_(q->card, 2, "nbs%d", bidx);
-		QETH_CARD_TEXT_(q->card, 2, "%lx", (long) newbuf);
-		QETH_CARD_TEXT_(q->card, 2, "%lx",
-				(long) newbuf->next_pending);
-	}
-out:
-	return rc;
+	return 0;
 }
 
 static void qeth_free_qdio_out_buf(struct qeth_qdio_out_q *q)
@@ -2908,8 +2892,7 @@ int qeth_init_qdio_queues(struct qeth_card *card)
 				   QDIO_MAX_BUFFERS_PER_Q);
 		for (j = 0; j < QDIO_MAX_BUFFERS_PER_Q; ++j) {
 			qeth_clear_output_buffer(card->qdio.out_qs[i],
-					card->qdio.out_qs[i]->bufs[j],
-					QETH_QDIO_BUF_EMPTY);
+						 card->qdio.out_qs[i]->bufs[j]);
 		}
 		card->qdio.out_qs[i]->card = card;
 		card->qdio.out_qs[i]->next_buf_to_fill = 0;
@@ -3634,10 +3617,10 @@ out:
 }
 EXPORT_SYMBOL_GPL(qeth_configure_cq);
 
-
-static void qeth_qdio_cq_handler(struct qeth_card *card,
-		unsigned int qdio_err,
-		unsigned int queue, int first_element, int count) {
+static void qeth_qdio_cq_handler(struct qeth_card *card, unsigned int qdio_err,
+				 unsigned int queue, int first_element,
+				 int count)
+{
 	struct qeth_qdio_q *cq = card->qdio.c_q;
 	int i;
 	int rc;
@@ -3663,25 +3646,17 @@ static void qeth_qdio_cq_handler(struct qeth_card *card,
 	for (i = first_element; i < first_element + count; ++i) {
 		int bidx = i % QDIO_MAX_BUFFERS_PER_Q;
 		struct qdio_buffer *buffer = cq->qdio_bufs[bidx];
-		int e;
+		int e = 0;
 
-		e = 0;
 		while ((e < QDIO_MAX_ELEMENTS_PER_BUFFER) &&
 		       buffer->element[e].addr) {
 			unsigned long phys_aob_addr;
 
 			phys_aob_addr = (unsigned long) buffer->element[e].addr;
 			qeth_qdio_handle_aob(card, phys_aob_addr);
-			buffer->element[e].addr = NULL;
-			buffer->element[e].eflags = 0;
-			buffer->element[e].sflags = 0;
-			buffer->element[e].length = 0;
-
 			++e;
 		}
-
-		buffer->element[15].eflags = 0;
-		buffer->element[15].sflags = 0;
+		qeth_scrub_qdio_buffer(buffer, QDIO_MAX_ELEMENTS_PER_BUFFER);
 	}
 	rc = do_QDIO(CARD_DDEV(card), QDIO_FLAG_SYNC_INPUT, queue,
 		    card->qdio.c_q->next_buf_to_init,
@@ -3782,8 +3757,7 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 				qeth_notify_skbs(queue, buffer, n);
 			}
 
-			qeth_clear_output_buffer(queue, buffer,
-						QETH_QDIO_BUF_EMPTY);
+			qeth_clear_output_buffer(queue, buffer);
 		}
 		qeth_cleanup_handled_pending(queue, bidx, 0);
 	}
-- 
cgit v1.2.3


From f67a43a73b543f686577507fe9ccdfae212b9924 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:39 +0200
Subject: s390/qeth: remove unused buffer->aob pointer

Except for tracing, the pointer is not used.

At the same time, accessing it from qeth_qdio_output_handler() is racy:
whenever qeth_qdio_cq_handler() gets control, its call to
qeth_qdio_handle_aob() frees the AOB.

So the AOB pointer that qeth_qdio_output_handler() stores into 'buffer'
can go stale at any time, and trigger a use-after-free.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      | 1 -
 drivers/s390/net/qeth_core_main.c | 7 -------
 2 files changed, 8 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index a246a618f9a4..0ca6ea319d88 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -465,7 +465,6 @@ struct qeth_qdio_out_buffer {
 	struct sk_buff_head skb_list;
 	int is_header[QDIO_MAX_ELEMENTS_PER_BUFFER];
 
-	struct qaob *aob;
 	struct qeth_qdio_out_q *q;
 	struct qeth_qdio_out_buffer *next_pending;
 };
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 916c17d93ddb..cfe68e3bfe7a 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -473,7 +473,6 @@ static void qeth_cleanup_handled_pending(struct qeth_qdio_out_q *q, int bidx,
 	if (forced_cleanup && (atomic_read(&(q->bufs[bidx]->state)) ==
 					QETH_QDIO_BUF_HANDLED_DELAYED)) {
 		/* for recovery situations */
-		q->bufs[bidx]->aob = q->bufstates[bidx].aob;
 		qeth_init_qdio_out_buf(q, bidx);
 		QETH_CARD_TEXT(q->card, 2, "clprecov");
 	}
@@ -510,7 +509,6 @@ static void qeth_qdio_handle_aob(struct qeth_card *card,
 	}
 	qeth_notify_skbs(buffer->q, buffer, notification);
 
-	buffer->aob = NULL;
 	/* Free dangling allocations. The attached skbs are handled by
 	 * qeth_cleanup_handled_pending().
 	 */
@@ -2478,7 +2476,6 @@ static int qeth_init_qdio_out_buf(struct qeth_qdio_out_q *q, int bidx)
 	skb_queue_head_init(&newbuf->skb_list);
 	lockdep_set_class(&newbuf->skb_list.lock, &qdio_out_skb_queue_key);
 	newbuf->q = q;
-	newbuf->aob = NULL;
 	newbuf->next_pending = q->bufs[bidx];
 	atomic_set(&newbuf->state, QETH_QDIO_BUF_EMPTY);
 	q->bufs[bidx] = newbuf;
@@ -3735,11 +3732,7 @@ static void qeth_qdio_output_handler(struct ccw_device *ccwdev,
 				qeth_notify_skbs(queue, buffer,
 						 TX_NOTIFY_PENDING);
 			}
-			buffer->aob = queue->bufstates[bidx].aob;
 			QETH_CARD_TEXT_(queue->card, 5, "pel%d", bidx);
-			QETH_CARD_TEXT(queue->card, 5, "aob");
-			QETH_CARD_TEXT_(queue->card, 5, "%lx",
-					virt_to_phys(buffer->aob));
 
 			/* prepare the queue slot for re-use: */
 			qeth_scrub_qdio_buffer(buffer->buffer,
-- 
cgit v1.2.3


From 9aa17df3b84bc6df37398f51e8df6ed8e91049d4 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:40 +0200
Subject: s390/qeth: fine-tune RX modesetting

Changing a device's address lists (or its promisc mode) already triggers
an RX modeset, there's no need to do it manually from the L2 driver's
ndo_vlan_rx_kill_vid() hook.

Also when setting a device online, dev_open() already calls
dev_set_rx_mode(). So a manual modeset is only necessary from the
recovery path.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l2_main.c | 5 +----
 drivers/s390/net/qeth_l3_main.c | 7 ++++---
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 2487f0aeb165..730ab51fbac5 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -26,7 +26,6 @@
 
 static int qeth_l2_set_offline(struct ccwgroup_device *);
 static int qeth_l2_stop(struct net_device *);
-static void qeth_l2_set_rx_mode(struct net_device *);
 static void qeth_bridgeport_query_support(struct qeth_card *card);
 static void qeth_bridge_state_change(struct qeth_card *card,
 					struct qeth_ipa_cmd *cmd);
@@ -344,7 +343,6 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev,
 		rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN);
 		kfree(tmpid);
 	}
-	qeth_l2_set_rx_mode(card->dev);
 	return rc;
 }
 
@@ -1125,13 +1123,12 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		if (recovery_mode &&
 		    card->info.type != QETH_CARD_TYPE_OSN) {
 			__qeth_l2_open(card->dev);
+			qeth_l2_set_rx_mode(card->dev);
 		} else {
 			rtnl_lock();
 			dev_open(card->dev);
 			rtnl_unlock();
 		}
-		/* this also sets saved unicast addresses */
-		qeth_l2_set_rx_mode(card->dev);
 	}
 	/* let user_space know that device is online */
 	kobject_uevent(&gdev->dev.kobj, KOBJ_CHANGE);
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 5905dc63e256..a54881cdda82 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2666,11 +2666,12 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 	qeth_enable_hw_features(card->dev);
 	if (recover_flag == CARD_STATE_RECOVER) {
 		rtnl_lock();
-		if (recovery_mode)
+		if (recovery_mode) {
 			__qeth_l3_open(card->dev);
-		else
+			qeth_l3_set_rx_mode(card->dev);
+		} else {
 			dev_open(card->dev);
-		qeth_l3_set_rx_mode(card->dev);
+		}
 		rtnl_unlock();
 	}
 	qeth_trace_features(card);
-- 
cgit v1.2.3


From 86c0cdb9e0a5d15f908438bf0491192b35db0869 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:41 +0200
Subject: s390/qeth: clean up Output Queue selection

Consolidate duplicated code, fix the misuse of RTN_UNSPEC and simplify
the handling of non-unicast traffic on IQD devices.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      | 15 +++++++++++++--
 drivers/s390/net/qeth_core_main.c |  8 +-------
 drivers/s390/net/qeth_core_mpc.h  |  2 ++
 drivers/s390/net/qeth_l2_main.c   | 13 ++++---------
 drivers/s390/net/qeth_l3_main.c   | 16 +++++++---------
 5 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 0ca6ea319d88..082c06d6380b 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -661,7 +661,6 @@ struct qeth_card_info {
 	int portno;
 	enum qeth_card_types type;
 	enum qeth_link_types link_type;
-	int is_multicast_different;
 	int initial_mtu;
 	int max_mtu;
 	int broadcast_capable;
@@ -934,6 +933,19 @@ static inline int qeth_send_simple_setassparms_v6(struct qeth_card *card,
 						 data, QETH_PROT_IPV6);
 }
 
+int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
+			    int ipv);
+static inline struct qeth_qdio_out_q *qeth_get_tx_queue(struct qeth_card *card,
+							struct sk_buff *skb,
+							int ipv, int cast_type)
+{
+	if (IS_IQD(card) && cast_type != RTN_UNICAST)
+		return card->qdio.out_qs[card->qdio.no_out_queues - 1];
+	if (!card->qdio.do_prio_queueing)
+		return card->qdio.out_qs[card->qdio.default_out_queue];
+	return card->qdio.out_qs[qeth_get_priority_queue(card, skb, ipv)];
+}
+
 extern struct qeth_discipline qeth_l2_discipline;
 extern struct qeth_discipline qeth_l3_discipline;
 extern const struct attribute_group *qeth_generic_attr_groups[];
@@ -1001,7 +1013,6 @@ int qeth_bridgeport_query_ports(struct qeth_card *card,
 	enum qeth_sbp_roles *role, enum qeth_sbp_states *state);
 int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
 int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
-int qeth_get_priority_queue(struct qeth_card *, struct sk_buff *, int, int);
 int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
 			 int extra_elems, int data_offset);
 int qeth_get_elements_for_frags(struct sk_buff *);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index cfe68e3bfe7a..e8b18a9e07d7 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1537,8 +1537,6 @@ static void qeth_determine_card_type(struct qeth_card *card)
 	card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
 	card->info.type = CARD_RDEV(card)->id.driver_info;
 	card->qdio.no_out_queues = QETH_MAX_QUEUES;
-	if (card->info.type == QETH_CARD_TYPE_IQD)
-		card->info.is_multicast_different = 0x0103;
 	qeth_update_from_chp_desc(card);
 }
 
@@ -3777,15 +3775,11 @@ static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num)
  * Note: Function assumes that we have 4 outbound queues.
  */
 int qeth_get_priority_queue(struct qeth_card *card, struct sk_buff *skb,
-			int ipv, int cast_type)
+			    int ipv)
 {
 	__be16 *tci;
 	u8 tos;
 
-	if (cast_type && card->info.is_multicast_different)
-		return card->info.is_multicast_different &
-			(card->qdio.no_out_queues - 1);
-
 	switch (card->qdio.do_prio_queueing) {
 	case QETH_PRIO_Q_ING_TOS:
 	case QETH_PRIO_Q_ING_PREC:
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 878e62f35169..54c35224262a 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -64,6 +64,8 @@ enum qeth_card_types {
 	QETH_CARD_TYPE_OSX     = 2,
 };
 
+#define IS_IQD(card)	((card)->info.type == QETH_CARD_TYPE_IQD)
+
 #define QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE 0x18
 /* only the first two bytes are looked at in qeth_get_cardname_short */
 enum qeth_link_types {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 730ab51fbac5..5910fd524872 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -185,12 +185,12 @@ static void qeth_l2_del_all_macs(struct qeth_card *card)
 static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb)
 {
 	if (card->info.type == QETH_CARD_TYPE_OSN)
-		return RTN_UNSPEC;
+		return RTN_UNICAST;
 	if (is_broadcast_ether_addr(skb->data))
 		return RTN_BROADCAST;
 	if (is_multicast_ether_addr(skb->data))
 		return RTN_MULTICAST;
-	return RTN_UNSPEC;
+	return RTN_UNICAST;
 }
 
 static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb,
@@ -768,18 +768,13 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb,
 	int tx_bytes = skb->len;
 	int rc;
 
-	if (card->qdio.do_prio_queueing || (cast_type &&
-					card->info.is_multicast_different))
-		queue = card->qdio.out_qs[qeth_get_priority_queue(card, skb,
-					ipv, cast_type)];
-	else
-		queue = card->qdio.out_qs[card->qdio.default_out_queue];
-
 	if ((card->state != CARD_STATE_UP) || !card->lan_online) {
 		card->stats.tx_carrier_errors++;
 		goto tx_drop;
 	}
 
+	queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+
 	if (card->options.performance_stats) {
 		card->perf_stats.outbound_cnt++;
 		card->perf_stats.outbound_start_time = qeth_get_micros();
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index a54881cdda82..7b4de46bf6e3 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -1978,17 +1978,17 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb)
 		    (cast_type == RTN_MULTICAST) ||
 		    (cast_type == RTN_ANYCAST))
 			return cast_type;
-		return RTN_UNSPEC;
+		return RTN_UNICAST;
 	}
 	rcu_read_unlock();
 
 	/* no neighbour (eg AF_PACKET), fall back to target's IP address ... */
 	if (be16_to_cpu(skb->protocol) == ETH_P_IPV6)
 		return ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) ?
-				RTN_MULTICAST : RTN_UNSPEC;
+				RTN_MULTICAST : RTN_UNICAST;
 	else if (be16_to_cpu(skb->protocol) == ETH_P_IP)
 		return ipv4_is_multicast(ip_hdr(skb)->daddr) ?
-				RTN_MULTICAST : RTN_UNSPEC;
+				RTN_MULTICAST : RTN_UNICAST;
 
 	/* ... and MAC address */
 	if (ether_addr_equal_64bits(eth_hdr(skb)->h_dest, skb->dev->broadcast))
@@ -1997,7 +1997,7 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb)
 		return RTN_MULTICAST;
 
 	/* default to unicast */
-	return RTN_UNSPEC;
+	return RTN_UNICAST;
 }
 
 static void qeth_l3_fill_af_iucv_hdr(struct qeth_card *card,
@@ -2168,11 +2168,7 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 	struct sk_buff *new_skb = NULL;
 	int ipv = qeth_get_ip_version(skb);
 	int cast_type = qeth_l3_get_cast_type(skb);
-	struct qeth_qdio_out_q *queue =
-		card->qdio.out_qs[card->qdio.do_prio_queueing
-			|| (cast_type && card->info.is_multicast_different) ?
-			qeth_get_priority_queue(card, skb, ipv, cast_type) :
-			card->qdio.default_out_queue];
+	struct qeth_qdio_out_q *queue;
 	int tx_bytes = skb->len;
 	unsigned int hd_len = 0;
 	bool use_tso;
@@ -2195,6 +2191,8 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 	    (card->info.broadcast_capable == 0))
 		goto tx_drop;
 
+	queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+
 	if (card->options.performance_stats) {
 		card->perf_stats.outbound_cnt++;
 		card->perf_stats.outbound_start_time = qeth_get_micros();
-- 
cgit v1.2.3


From 6d8769abe44ad073bd3d08a9dfbcbd567e96e78b Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:42 +0200
Subject: s390/qeth: consolidate ccwgroup driver definition

Reshuffle the code a bit so that everything is in one place.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 42 +++++++++++++++++++--------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index e8b18a9e07d7..4ba40a64907a 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5848,31 +5848,13 @@ static int qeth_core_restore(struct ccwgroup_device *gdev)
 	return 0;
 }
 
-static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
-	.driver = {
-		.owner = THIS_MODULE,
-		.name = "qeth",
-	},
-	.ccw_driver = &qeth_ccw_driver,
-	.setup = qeth_core_probe_device,
-	.remove = qeth_core_remove_device,
-	.set_online = qeth_core_set_online,
-	.set_offline = qeth_core_set_offline,
-	.shutdown = qeth_core_shutdown,
-	.prepare = NULL,
-	.complete = NULL,
-	.freeze = qeth_core_freeze,
-	.thaw = qeth_core_thaw,
-	.restore = qeth_core_restore,
-};
-
 static ssize_t group_store(struct device_driver *ddrv, const char *buf,
 			   size_t count)
 {
 	int err;
 
-	err = ccwgroup_create_dev(qeth_core_root_dev,
-				  &qeth_core_ccwgroup_driver, 3, buf);
+	err = ccwgroup_create_dev(qeth_core_root_dev, to_ccwgroupdrv(ddrv), 3,
+				  buf);
 
 	return err ? err : count;
 }
@@ -5890,6 +5872,25 @@ static const struct attribute_group *qeth_drv_attr_groups[] = {
 	NULL,
 };
 
+static struct ccwgroup_driver qeth_core_ccwgroup_driver = {
+	.driver = {
+		.groups = qeth_drv_attr_groups,
+		.owner = THIS_MODULE,
+		.name = "qeth",
+	},
+	.ccw_driver = &qeth_ccw_driver,
+	.setup = qeth_core_probe_device,
+	.remove = qeth_core_remove_device,
+	.set_online = qeth_core_set_online,
+	.set_offline = qeth_core_set_offline,
+	.shutdown = qeth_core_shutdown,
+	.prepare = NULL,
+	.complete = NULL,
+	.freeze = qeth_core_freeze,
+	.thaw = qeth_core_thaw,
+	.restore = qeth_core_restore,
+};
+
 int qeth_do_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct qeth_card *card = dev->ml_priv;
@@ -6581,7 +6582,6 @@ static int __init qeth_core_init(void)
 	rc = ccw_driver_register(&qeth_ccw_driver);
 	if (rc)
 		goto ccw_err;
-	qeth_core_ccwgroup_driver.driver.groups = qeth_drv_attr_groups;
 	rc = ccwgroup_driver_register(&qeth_core_ccwgroup_driver);
 	if (rc)
 		goto ccwgroup_err;
-- 
cgit v1.2.3


From 09960b3a0a474f420894d88ae2e6f09ee4c60f9c Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:43 +0200
Subject: s390/qeth: clean up exported symbols

Remove some redundant EXPORTs. While at it, also move some L2-only
prototypes into the proper header file.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      | 6 ------
 drivers/s390/net/qeth_core_main.c | 8 +++-----
 drivers/s390/net/qeth_l2.h        | 5 +++++
 drivers/s390/net/qeth_l2_main.c   | 2 --
 4 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 082c06d6380b..a932aac62d0e 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -983,7 +983,6 @@ int qeth_send_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *,
 		  void *);
 struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *,
 			enum qeth_ipa_cmds, enum qeth_prot_versions);
-int qeth_query_setadapterparms(struct qeth_card *);
 struct sk_buff *qeth_core_get_next_skb(struct qeth_card *,
 		struct qeth_qdio_buffer *, struct qdio_buffer_element **, int *,
 		struct qeth_hdr **);
@@ -1009,10 +1008,6 @@ int qeth_query_switch_attributes(struct qeth_card *card,
 int qeth_send_control_data(struct qeth_card *, int, struct qeth_cmd_buffer *,
 	int (*reply_cb)(struct qeth_card *, struct qeth_reply*, unsigned long),
 	void *reply_param);
-int qeth_bridgeport_query_ports(struct qeth_card *card,
-	enum qeth_sbp_roles *role, enum qeth_sbp_states *state);
-int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
-int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
 int qeth_get_elements_no(struct qeth_card *card, struct sk_buff *skb,
 			 int extra_elems, int data_offset);
 int qeth_get_elements_for_frags(struct sk_buff *);
@@ -1036,7 +1031,6 @@ int qeth_set_access_ctrl_online(struct qeth_card *card, int fallback);
 int qeth_hdr_chk_and_bounce(struct sk_buff *, struct qeth_hdr **, int);
 int qeth_configure_cq(struct qeth_card *, enum qeth_cq);
 int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action);
-int qeth_query_ipassists(struct qeth_card *, enum qeth_prot_versions prot);
 void qeth_trace_features(struct qeth_card *);
 void qeth_close_dev(struct qeth_card *);
 int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16,
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 4ba40a64907a..d80972b9bfc7 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3054,7 +3054,7 @@ static struct qeth_cmd_buffer *qeth_get_adapter_cmd(struct qeth_card *card,
 	return iob;
 }
 
-int qeth_query_setadapterparms(struct qeth_card *card)
+static int qeth_query_setadapterparms(struct qeth_card *card)
 {
 	int rc;
 	struct qeth_cmd_buffer *iob;
@@ -3067,7 +3067,6 @@ int qeth_query_setadapterparms(struct qeth_card *card)
 	rc = qeth_send_ipa_cmd(card, iob, qeth_query_setadapterparms_cb, NULL);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_query_setadapterparms);
 
 static int qeth_query_ipassists_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
@@ -3107,7 +3106,8 @@ static int qeth_query_ipassists_cb(struct qeth_card *card,
 	return 0;
 }
 
-int qeth_query_ipassists(struct qeth_card *card, enum qeth_prot_versions prot)
+static int qeth_query_ipassists(struct qeth_card *card,
+				enum qeth_prot_versions prot)
 {
 	int rc;
 	struct qeth_cmd_buffer *iob;
@@ -3119,7 +3119,6 @@ int qeth_query_ipassists(struct qeth_card *card, enum qeth_prot_versions prot)
 	rc = qeth_send_ipa_cmd(card, iob, qeth_query_ipassists_cb, NULL);
 	return rc;
 }
-EXPORT_SYMBOL_GPL(qeth_query_ipassists);
 
 static int qeth_query_switch_attributes_cb(struct qeth_card *card,
 				struct qeth_reply *reply, unsigned long data)
@@ -3158,7 +3157,6 @@ int qeth_query_switch_attributes(struct qeth_card *card,
 	return qeth_send_ipa_cmd(card, iob,
 				qeth_query_switch_attributes_cb, sw_info);
 }
-EXPORT_SYMBOL_GPL(qeth_query_switch_attributes);
 
 static int qeth_query_setdiagass_cb(struct qeth_card *card,
 		struct qeth_reply *reply, unsigned long data)
diff --git a/drivers/s390/net/qeth_l2.h b/drivers/s390/net/qeth_l2.h
index f2130051ca11..ddc615b431a8 100644
--- a/drivers/s390/net/qeth_l2.h
+++ b/drivers/s390/net/qeth_l2.h
@@ -14,6 +14,11 @@ extern const struct attribute_group *qeth_l2_attr_groups[];
 int qeth_l2_create_device_attributes(struct device *);
 void qeth_l2_remove_device_attributes(struct device *);
 void qeth_l2_setup_bridgeport_attrs(struct qeth_card *card);
+int qeth_bridgeport_query_ports(struct qeth_card *card,
+				enum qeth_sbp_roles *role,
+				enum qeth_sbp_states *state);
+int qeth_bridgeport_setrole(struct qeth_card *card, enum qeth_sbp_roles role);
+int qeth_bridgeport_an_set(struct qeth_card *card, int enable);
 
 int qeth_l2_vnicc_set_state(struct qeth_card *card, u32 vnicc, bool state);
 int qeth_l2_vnicc_get_state(struct qeth_card *card, u32 vnicc, bool *state);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 5910fd524872..8ac243de7a9e 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1869,7 +1869,6 @@ int qeth_bridgeport_query_ports(struct qeth_card *card,
 		return rc;
 	return qeth_bridgeport_makerc(card, &cbctl, IPA_SBP_QUERY_BRIDGE_PORTS);
 }
-EXPORT_SYMBOL_GPL(qeth_bridgeport_query_ports);
 
 static int qeth_bridgeport_set_cb(struct qeth_card *card,
 	struct qeth_reply *reply, unsigned long data)
@@ -2017,7 +2016,6 @@ int qeth_bridgeport_an_set(struct qeth_card *card, int enable)
 		rc = qdio_pnso_brinfo(schid, 0, &response, NULL, NULL);
 	return qeth_anset_makerc(card, rc, response);
 }
-EXPORT_SYMBOL_GPL(qeth_bridgeport_an_set);
 
 static bool qeth_bridgeport_is_in_use(struct qeth_card *card)
 {
-- 
cgit v1.2.3


From 371a1e7a07a0d1bb272f69ccb3df617f8a049d07 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:44 +0200
Subject: s390/qeth: increase GSO max size for eligible L3 devices

When a L3 device doesn't offer TSO, allow the stack to build full-size
GSO skbs.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 7b4de46bf6e3..d07803df460b 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2536,8 +2536,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
 	netif_keep_dst(card->dev);
-	netif_set_gso_max_size(card->dev, (QETH_MAX_BUFFER_ELEMENTS(card) - 1) *
-					  PAGE_SIZE);
+	if (card->dev->hw_features & NETIF_F_TSO)
+		netif_set_gso_max_size(card->dev,
+				       PAGE_SIZE * (QETH_MAX_BUFFER_ELEMENTS(card) - 1));
 
 	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
-- 
cgit v1.2.3


From ea1d4a0c7fa5a7aab823e77c3a9000035a231f77 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:45 +0200
Subject: s390/qeth: add a L3 xmit wrapper

In preparation for future work, move the high-level xmit work into a
separate wrapper. This matches the L2 xmit code.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 122 +++++++++++++++++++++-------------------
 1 file changed, 65 insertions(+), 57 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index d07803df460b..b5a54cc07017 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2156,48 +2156,21 @@ static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
 	return elements;
 }
 
-static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
-					   struct net_device *dev)
+static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
+			struct qeth_qdio_out_q *queue, int ipv, int cast_type)
 {
 	int rc;
 	__be16 *tag;
 	struct qeth_hdr *hdr = NULL;
 	int hdr_elements = 0;
 	int elements;
-	struct qeth_card *card = dev->ml_priv;
 	struct sk_buff *new_skb = NULL;
-	int ipv = qeth_get_ip_version(skb);
-	int cast_type = qeth_l3_get_cast_type(skb);
-	struct qeth_qdio_out_q *queue;
 	int tx_bytes = skb->len;
 	unsigned int hd_len = 0;
 	bool use_tso;
 	int data_offset = -1;
 	unsigned int nr_frags;
 
-	if (((card->info.type == QETH_CARD_TYPE_IQD) &&
-	     (((card->options.cq != QETH_CQ_ENABLED) && !ipv) ||
-	      ((card->options.cq == QETH_CQ_ENABLED) &&
-	       (be16_to_cpu(skb->protocol) != ETH_P_AF_IUCV)))) ||
-	    card->options.sniffer)
-			goto tx_drop;
-
-	if ((card->state != CARD_STATE_UP) || !card->lan_online) {
-		card->stats.tx_carrier_errors++;
-		goto tx_drop;
-	}
-
-	if ((cast_type == RTN_BROADCAST) &&
-	    (card->info.broadcast_capable == 0))
-		goto tx_drop;
-
-	queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
-
-	if (card->options.performance_stats) {
-		card->perf_stats.outbound_cnt++;
-		card->perf_stats.outbound_start_time = qeth_get_micros();
-	}
-
 	/* Ignore segment size from skb_is_gso(), 1 page is always used. */
 	use_tso = skb_is_gso(skb) &&
 		  (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4);
@@ -2208,14 +2181,14 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 		hd_len = sizeof(*hdr);
 		hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
 		if (!hdr)
-			goto tx_drop;
+			return -ENOMEM;
 		hdr_elements++;
 	} else {
 		/* create a clone with writeable headroom */
 		new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso)
 					+ VLAN_HLEN);
 		if (!new_skb)
-			goto tx_drop;
+			return -ENOMEM;
 
 		if (ipv == 4) {
 			skb_pull(new_skb, ETH_HLEN);
@@ -2234,24 +2207,22 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 		}
 	}
 
-	netif_stop_queue(dev);
-
 	/* fix hardware limitation: as long as we do not have sbal
 	 * chaining we can not send long frag lists
 	 */
 	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
 	    ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
 	     (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
-		int lin_rc = skb_linearize(new_skb);
+		rc = skb_linearize(new_skb);
 
 		if (card->options.performance_stats) {
-			if (lin_rc)
+			if (rc)
 				card->perf_stats.tx_linfail++;
 			else
 				card->perf_stats.tx_lin++;
 		}
-		if (lin_rc)
-			goto tx_drop;
+		if (rc)
+			goto out;
 	}
 	nr_frags = skb_shinfo(new_skb)->nr_frags;
 
@@ -2290,9 +2261,8 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 		   qeth_get_elements_no(card, new_skb, hdr_elements,
 					(data_offset > 0) ? data_offset : 0);
 	if (!elements) {
-		if (data_offset >= 0)
-			kmem_cache_free(qeth_core_header_cache, hdr);
-		goto tx_drop;
+		rc = -E2BIG;
+		goto out;
 	}
 	elements += hdr_elements;
 
@@ -2306,17 +2276,18 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 			len = sizeof(struct qeth_hdr_layer3);
 		}
 
-		if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len))
-			goto tx_drop;
+		if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) {
+			rc = -EINVAL;
+			goto out;
+		}
 		rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len,
 					 hd_len, elements);
 	} else
 		rc = qeth_do_send_packet_fast(queue, new_skb, hdr, data_offset,
 					      hd_len);
 
+out:
 	if (!rc) {
-		card->stats.tx_packets++;
-		card->stats.tx_bytes += tx_bytes;
 		if (new_skb != skb)
 			dev_kfree_skb_any(skb);
 		if (card->options.performance_stats) {
@@ -2330,30 +2301,67 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 				card->perf_stats.sg_frags_sent += nr_frags + 1;
 			}
 		}
-		rc = NETDEV_TX_OK;
 	} else {
+		if (new_skb != skb)
+			dev_kfree_skb_any(new_skb);
 		if (data_offset >= 0)
 			kmem_cache_free(qeth_core_header_cache, hdr);
+	}
+	return rc;
+}
 
-		if (rc == -EBUSY) {
-			if (new_skb != skb)
-				dev_kfree_skb_any(new_skb);
-			return NETDEV_TX_BUSY;
-		} else
+static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
+					   struct net_device *dev)
+{
+	int cast_type = qeth_l3_get_cast_type(skb);
+	struct qeth_card *card = dev->ml_priv;
+	int ipv = qeth_get_ip_version(skb);
+	struct qeth_qdio_out_q *queue;
+	int tx_bytes = skb->len;
+	int rc;
+
+	if (IS_IQD(card)) {
+		if (card->options.sniffer)
+			goto tx_drop;
+		if ((card->options.cq != QETH_CQ_ENABLED && !ipv) ||
+		    (card->options.cq == QETH_CQ_ENABLED &&
+		     skb->protocol != htons(ETH_P_AF_IUCV)))
 			goto tx_drop;
 	}
 
-	netif_wake_queue(dev);
-	if (card->options.performance_stats)
-		card->perf_stats.outbound_time += qeth_get_micros() -
-			card->perf_stats.outbound_start_time;
-	return rc;
+	if (card->state != CARD_STATE_UP || !card->lan_online) {
+		card->stats.tx_carrier_errors++;
+		goto tx_drop;
+	}
+
+	if (cast_type == RTN_BROADCAST && !card->info.broadcast_capable)
+		goto tx_drop;
+
+	queue = qeth_get_tx_queue(card, skb, ipv, cast_type);
+
+	if (card->options.performance_stats) {
+		card->perf_stats.outbound_cnt++;
+		card->perf_stats.outbound_start_time = qeth_get_micros();
+	}
+	netif_stop_queue(dev);
+
+	rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type);
+
+	if (!rc) {
+		card->stats.tx_packets++;
+		card->stats.tx_bytes += tx_bytes;
+		if (card->options.performance_stats)
+			card->perf_stats.outbound_time += qeth_get_micros() -
+				card->perf_stats.outbound_start_time;
+		netif_wake_queue(dev);
+		return NETDEV_TX_OK;
+	} else if (rc == -EBUSY) {
+		return NETDEV_TX_BUSY;
+	} /* else fall through */
 
 tx_drop:
 	card->stats.tx_dropped++;
 	card->stats.tx_errors++;
-	if ((new_skb != skb) && new_skb)
-		dev_kfree_skb_any(new_skb);
 	dev_kfree_skb_any(skb);
 	netif_wake_queue(dev);
 	return NETDEV_TX_OK;
-- 
cgit v1.2.3


From a647a02512ca346bb399d7dc4f57e327f2475286 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:46 +0200
Subject: s390/qeth: speed-up L3 IQD xmit

This implements a new xmit path for L3 HiperSockets, which carves the
HW header from skb headroom instead of allocating it from the hdr cache.
It also adds NETIF_F_SG support.

The delta in qeth_l3_xmit() is all just removal of IQD-specific code and
some minor consolidation.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 211 ++++++++++++++++++++++++----------------
 1 file changed, 128 insertions(+), 83 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index b5a54cc07017..0863ffa9ab59 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2000,19 +2000,18 @@ static int qeth_l3_get_cast_type(struct sk_buff *skb)
 	return RTN_UNICAST;
 }
 
-static void qeth_l3_fill_af_iucv_hdr(struct qeth_card *card,
-		struct qeth_hdr *hdr, struct sk_buff *skb)
+static void qeth_l3_fill_af_iucv_hdr(struct qeth_hdr *hdr, struct sk_buff *skb,
+				     unsigned int data_len)
 {
 	char daddr[16];
 	struct af_iucv_trans_hdr *iucv_hdr;
 
 	memset(hdr, 0, sizeof(struct qeth_hdr));
 	hdr->hdr.l3.id = QETH_HEADER_TYPE_LAYER3;
-	hdr->hdr.l3.ext_flags = 0;
-	hdr->hdr.l3.length = skb->len - ETH_HLEN;
+	hdr->hdr.l3.length = data_len;
 	hdr->hdr.l3.flags = QETH_HDR_IPV6 | QETH_CAST_UNICAST;
 
-	iucv_hdr = (struct af_iucv_trans_hdr *) (skb->data + ETH_HLEN);
+	iucv_hdr = (struct af_iucv_trans_hdr *)(skb_mac_header(skb) + ETH_HLEN);
 	memset(daddr, 0, sizeof(daddr));
 	daddr[0] = 0xfe;
 	daddr[1] = 0x80;
@@ -2156,63 +2155,122 @@ static int qeth_l3_get_elements_no_tso(struct qeth_card *card,
 	return elements;
 }
 
+static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
+				struct qeth_qdio_out_q *queue, int ipv,
+				int cast_type)
+{
+	const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
+	unsigned int frame_len, nr_frags;
+	unsigned char eth_hdr[ETH_HLEN];
+	unsigned int hdr_elements = 0;
+	struct qeth_hdr *hdr = NULL;
+	unsigned int hd_len = 0;
+	int push_len, rc;
+
+	/* compress skb to fit into one IO buffer: */
+	if (!qeth_get_elements_no(card, skb, 0, 0)) {
+		rc = skb_linearize(skb);
+
+		if (card->options.performance_stats) {
+			if (rc)
+				card->perf_stats.tx_linfail++;
+			else
+				card->perf_stats.tx_lin++;
+		}
+		if (rc)
+			return rc;
+	}
+
+	/* re-use the L2 header area for the HW header: */
+	rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN);
+	if (rc)
+		return rc;
+	skb_copy_from_linear_data(skb, eth_hdr, ETH_HLEN);
+	skb_pull(skb, ETH_HLEN);
+	frame_len = skb->len;
+	nr_frags = skb_shinfo(skb)->nr_frags;
+
+	push_len = qeth_push_hdr(skb, &hdr, hw_hdr_len);
+	if (push_len < 0)
+		return push_len;
+	if (!push_len) {
+		/* hdr was added discontiguous from skb->data */
+		hd_len = hw_hdr_len;
+		hdr_elements = 1;
+	}
+
+	if (!qeth_get_elements_no(card, skb, hdr_elements, 0)) {
+		rc = -E2BIG;
+		goto out;
+	}
+
+	if (skb->protocol == htons(ETH_P_AF_IUCV))
+		qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len);
+	else
+		qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
+
+	rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len);
+out:
+	if (!rc) {
+		if (card->options.performance_stats && nr_frags) {
+			card->perf_stats.sg_skbs_sent++;
+			/* nr_frags + skb->data */
+			card->perf_stats.sg_frags_sent += nr_frags + 1;
+		}
+	} else {
+		if (!push_len)
+			kmem_cache_free(qeth_core_header_cache, hdr);
+		if (rc == -EBUSY) {
+			/* roll back to ETH header */
+			skb_pull(skb, push_len);
+			skb_push(skb, ETH_HLEN);
+			skb_copy_to_linear_data(skb, eth_hdr, ETH_HLEN);
+		}
+	}
+	return rc;
+}
+
 static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 			struct qeth_qdio_out_q *queue, int ipv, int cast_type)
 {
-	int rc;
+	unsigned int hd_len, nr_frags;
+	int elements, len, rc;
 	__be16 *tag;
 	struct qeth_hdr *hdr = NULL;
 	int hdr_elements = 0;
-	int elements;
 	struct sk_buff *new_skb = NULL;
 	int tx_bytes = skb->len;
-	unsigned int hd_len = 0;
 	bool use_tso;
-	int data_offset = -1;
-	unsigned int nr_frags;
 
 	/* Ignore segment size from skb_is_gso(), 1 page is always used. */
 	use_tso = skb_is_gso(skb) &&
 		  (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4);
 
-	if (card->info.type == QETH_CARD_TYPE_IQD) {
-		new_skb = skb;
-		data_offset = ETH_HLEN;
-		hd_len = sizeof(*hdr);
-		hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
-		if (!hdr)
-			return -ENOMEM;
-		hdr_elements++;
-	} else {
-		/* create a clone with writeable headroom */
-		new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso)
-					+ VLAN_HLEN);
-		if (!new_skb)
-			return -ENOMEM;
-
-		if (ipv == 4) {
-			skb_pull(new_skb, ETH_HLEN);
-		}
+	/* create a clone with writeable headroom */
+	new_skb = skb_realloc_headroom(skb, sizeof(struct qeth_hdr_tso) +
+					    VLAN_HLEN);
+	if (!new_skb)
+		return -ENOMEM;
 
-		if (ipv != 4 && skb_vlan_tag_present(new_skb)) {
-			skb_push(new_skb, VLAN_HLEN);
-			skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4);
-			skb_copy_to_linear_data_offset(new_skb, 4,
-				new_skb->data + 8, 4);
-			skb_copy_to_linear_data_offset(new_skb, 8,
-				new_skb->data + 12, 4);
-			tag = (__be16 *)(new_skb->data + 12);
-			*tag = cpu_to_be16(ETH_P_8021Q);
-			*(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
-		}
+	if (ipv == 4) {
+		skb_pull(new_skb, ETH_HLEN);
+	} else if (skb_vlan_tag_present(new_skb)) {
+		skb_push(new_skb, VLAN_HLEN);
+		skb_copy_to_linear_data(new_skb, new_skb->data + 4, 4);
+		skb_copy_to_linear_data_offset(new_skb, 4,
+					       new_skb->data + 8, 4);
+		skb_copy_to_linear_data_offset(new_skb, 8,
+					       new_skb->data + 12, 4);
+		tag = (__be16 *)(new_skb->data + 12);
+		*tag = cpu_to_be16(ETH_P_8021Q);
+		*(tag + 1) = cpu_to_be16(skb_vlan_tag_get(new_skb));
 	}
 
 	/* fix hardware limitation: as long as we do not have sbal
 	 * chaining we can not send long frag lists
 	 */
-	if ((card->info.type != QETH_CARD_TYPE_IQD) &&
-	    ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
-	     (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0)))) {
+	if ((use_tso && !qeth_l3_get_elements_no_tso(card, new_skb, 1)) ||
+	    (!use_tso && !qeth_get_elements_no(card, new_skb, 0, 0))) {
 		rc = skb_linearize(new_skb);
 
 		if (card->options.performance_stats) {
@@ -2234,20 +2292,9 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 		qeth_tso_fill_header(card, hdr, new_skb);
 		hdr_elements++;
 	} else {
-		if (data_offset < 0) {
-			hdr = skb_push(new_skb, sizeof(struct qeth_hdr));
-			qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type,
-					    new_skb->len -
-					    sizeof(struct qeth_hdr));
-		} else {
-			if (be16_to_cpu(new_skb->protocol) == ETH_P_AF_IUCV)
-				qeth_l3_fill_af_iucv_hdr(card, hdr, new_skb);
-			else {
-				qeth_l3_fill_header(card, hdr, new_skb, ipv,
-						    cast_type,
-						    new_skb->len - data_offset);
-			}
-		}
+		hdr = skb_push(new_skb, sizeof(struct qeth_hdr));
+		qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type,
+				    new_skb->len - sizeof(struct qeth_hdr));
 
 		if (new_skb->ip_summed == CHECKSUM_PARTIAL) {
 			qeth_tx_csum(new_skb, &hdr->hdr.l3.ext_flags, ipv);
@@ -2258,34 +2305,28 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 
 	elements = use_tso ?
 		   qeth_l3_get_elements_no_tso(card, new_skb, hdr_elements) :
-		   qeth_get_elements_no(card, new_skb, hdr_elements,
-					(data_offset > 0) ? data_offset : 0);
+		   qeth_get_elements_no(card, new_skb, hdr_elements, 0);
 	if (!elements) {
 		rc = -E2BIG;
 		goto out;
 	}
 	elements += hdr_elements;
 
-	if (card->info.type != QETH_CARD_TYPE_IQD) {
-		int len;
-		if (use_tso) {
-			hd_len = sizeof(struct qeth_hdr_tso) +
-				 ip_hdrlen(new_skb) + tcp_hdrlen(new_skb);
-			len = hd_len;
-		} else {
-			len = sizeof(struct qeth_hdr_layer3);
-		}
-
-		if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) {
-			rc = -EINVAL;
-			goto out;
-		}
-		rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len,
-					 hd_len, elements);
-	} else
-		rc = qeth_do_send_packet_fast(queue, new_skb, hdr, data_offset,
-					      hd_len);
+	if (use_tso) {
+		hd_len = sizeof(struct qeth_hdr_tso) +
+			 ip_hdrlen(new_skb) + tcp_hdrlen(new_skb);
+		len = hd_len;
+	} else {
+		hd_len = 0;
+		len = sizeof(struct qeth_hdr_layer3);
+	}
 
+	if (qeth_hdr_chk_and_bounce(new_skb, &hdr, len)) {
+		rc = -EINVAL;
+		goto out;
+	}
+	rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len, hd_len,
+				 elements);
 out:
 	if (!rc) {
 		if (new_skb != skb)
@@ -2304,8 +2345,6 @@ out:
 	} else {
 		if (new_skb != skb)
 			dev_kfree_skb_any(new_skb);
-		if (data_offset >= 0)
-			kmem_cache_free(qeth_core_header_cache, hdr);
 	}
 	return rc;
 }
@@ -2345,7 +2384,10 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 	}
 	netif_stop_queue(dev);
 
-	rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type);
+	if (IS_IQD(card))
+		rc = qeth_l3_xmit_offload(card, skb, queue, ipv, cast_type);
+	else
+		rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type);
 
 	if (!rc) {
 		card->stats.tx_packets++;
@@ -2503,9 +2545,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 		if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD))
 			card->dev->dev_id = card->info.unique_id & 0xffff;
 
-		card->dev->hw_features |= NETIF_F_SG;
-		card->dev->vlan_features |= NETIF_F_SG;
-
 		if (!card->info.guestlan) {
 			card->dev->features |= NETIF_F_SG;
 			card->dev->hw_features |= NETIF_F_TSO |
@@ -2524,7 +2563,10 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 		if (!card->dev)
 			return -ENODEV;
 		card->dev->flags |= IFF_NOARP;
+		card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 		card->dev->netdev_ops = &qeth_l3_netdev_ops;
+		card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
+
 		rc = qeth_l3_iqd_read_initial_mac(card);
 		if (rc)
 			return rc;
@@ -2543,6 +2585,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 	card->dev->features |=	NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
+	card->dev->hw_features |= NETIF_F_SG;
+	card->dev->vlan_features |= NETIF_F_SG;
+
 	netif_keep_dst(card->dev);
 	if (card->dev->hw_features & NETIF_F_TSO)
 		netif_set_gso_max_size(card->dev,
-- 
cgit v1.2.3


From fb321f25e582ae45e6b792fb38a3fc261dc5131e Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Wed, 11 Jul 2018 17:42:47 +0200
Subject: s390/qeth: speed-up IPv4 OSA xmit

Move the xmit of offload-eligible (ie IPv4) traffic on OSA over to the
new, copy-free path.
As with L2, we'll need to preserve the skb_orphan() behaviour of the
old code path until TX completion is sufficiently fast.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 0863ffa9ab59..062f62b49294 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2050,6 +2050,12 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr,
 		hdr->hdr.l3.vlan_id = skb_vlan_tag_get(skb);
 	}
 
+	if (!skb_is_gso(skb) && skb->ip_summed == CHECKSUM_PARTIAL) {
+		qeth_tx_csum(skb, &hdr->hdr.l3.ext_flags, ipv);
+		if (card->options.performance_stats)
+			card->perf_stats.tx_csum++;
+	}
+
 	/* OSA only: */
 	if (!ipv) {
 		hdr->hdr.l3.flags = QETH_HDR_PASSTHRU;
@@ -2164,8 +2170,8 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 	unsigned char eth_hdr[ETH_HLEN];
 	unsigned int hdr_elements = 0;
 	struct qeth_hdr *hdr = NULL;
+	int elements, push_len, rc;
 	unsigned int hd_len = 0;
-	int push_len, rc;
 
 	/* compress skb to fit into one IO buffer: */
 	if (!qeth_get_elements_no(card, skb, 0, 0)) {
@@ -2199,17 +2205,26 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 		hdr_elements = 1;
 	}
 
-	if (!qeth_get_elements_no(card, skb, hdr_elements, 0)) {
+	elements = qeth_get_elements_no(card, skb, hdr_elements, 0);
+	if (!elements) {
 		rc = -E2BIG;
 		goto out;
 	}
+	elements += hdr_elements;
 
 	if (skb->protocol == htons(ETH_P_AF_IUCV))
 		qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len);
 	else
 		qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
 
-	rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len);
+	if (IS_IQD(card)) {
+		rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len);
+	} else {
+		/* TODO: drop skb_orphan() once TX completion is fast enough */
+		skb_orphan(skb);
+		rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len,
+					 elements);
+	}
 out:
 	if (!rc) {
 		if (card->options.performance_stats && nr_frags) {
@@ -2295,12 +2310,6 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 		hdr = skb_push(new_skb, sizeof(struct qeth_hdr));
 		qeth_l3_fill_header(card, hdr, new_skb, ipv, cast_type,
 				    new_skb->len - sizeof(struct qeth_hdr));
-
-		if (new_skb->ip_summed == CHECKSUM_PARTIAL) {
-			qeth_tx_csum(new_skb, &hdr->hdr.l3.ext_flags, ipv);
-			if (card->options.performance_stats)
-				card->perf_stats.tx_csum++;
-		}
 	}
 
 	elements = use_tso ?
@@ -2384,7 +2393,7 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb,
 	}
 	netif_stop_queue(dev);
 
-	if (IS_IQD(card))
+	if (IS_IQD(card) || (!skb_is_gso(skb) && ipv == 4))
 		rc = qeth_l3_xmit_offload(card, skb, queue, ipv, cast_type);
 	else
 		rc = qeth_l3_xmit(card, skb, queue, ipv, cast_type);
@@ -2563,9 +2572,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 		if (!card->dev)
 			return -ENODEV;
 		card->dev->flags |= IFF_NOARP;
-		card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 		card->dev->netdev_ops = &qeth_l3_netdev_ops;
-		card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
 
 		rc = qeth_l3_iqd_read_initial_mac(card);
 		if (rc)
@@ -2582,6 +2589,8 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 	card->dev->max_mtu = ETH_MAX_MTU;
 	card->dev->dev_port = card->info.portno;
 	card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
+	card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
 	card->dev->features |=	NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
-- 
cgit v1.2.3


From 68d2f84a1368cc5d4ccbbbfc6821f159d27681c9 Mon Sep 17 00:00:00 2001
From: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Date: Thu, 12 Jul 2018 16:24:59 +0900
Subject: net: gro: properly remove skb from list

Following crash occurs in validate_xmit_skb_list() when same skb is
iterated multiple times in the loop and consume_skb() is called.

The root cause is calling list_del_init(&skb->list) and not clearing
skb->next in d4546c2509b1. list_del_init(&skb->list) sets skb->next
to point to skb itself. skb->next needs to be cleared because other
parts of network stack uses another kind of SKB lists.
validate_xmit_skb_list() uses such list.

A similar type of bugfix was reported by Jesper Dangaard Brouer.
https://patchwork.ozlabs.org/patch/942541/

This patch clears skb->next and changes list_del_init() to list_del()
so that list->prev will maintain the list poison.

[  148.185511] ==================================================================
[  148.187865] BUG: KASAN: use-after-free in validate_xmit_skb_list+0x4b/0xa0
[  148.190158] Read of size 8 at addr ffff8801e52eefc0 by task swapper/1/0
[  148.192940]
[  148.193642] CPU: 1 PID: 0 Comm: swapper/1 Not tainted 4.18.0-rc3+ #25
[  148.195423] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20180531_142017-buildhw-08.phx2.fedoraproject.org-1.fc28 04/01/2014
[  148.199129] Call Trace:
[  148.200565]  <IRQ>
[  148.201911]  dump_stack+0xc6/0x14c
[  148.203572]  ? dump_stack_print_info.cold.1+0x2f/0x2f
[  148.205083]  ? kmsg_dump_rewind_nolock+0x59/0x59
[  148.206307]  ? validate_xmit_skb+0x2c6/0x560
[  148.207432]  ? debug_show_held_locks+0x30/0x30
[  148.208571]  ? validate_xmit_skb_list+0x4b/0xa0
[  148.211144]  print_address_description+0x6c/0x23c
[  148.212601]  ? validate_xmit_skb_list+0x4b/0xa0
[  148.213782]  kasan_report.cold.6+0x241/0x2fd
[  148.214958]  validate_xmit_skb_list+0x4b/0xa0
[  148.216494]  sch_direct_xmit+0x1b0/0x680
[  148.217601]  ? dev_watchdog+0x4e0/0x4e0
[  148.218675]  ? do_raw_spin_trylock+0x10/0x120
[  148.219818]  ? do_raw_spin_lock+0xe0/0xe0
[  148.221032]  __dev_queue_xmit+0x1167/0x1810
[  148.222155]  ? sched_clock+0x5/0x10
[...]

[  148.474257] Allocated by task 0:
[  148.475363]  kasan_kmalloc+0xbf/0xe0
[  148.476503]  kmem_cache_alloc+0xb4/0x1b0
[  148.477654]  __build_skb+0x91/0x250
[  148.478677]  build_skb+0x67/0x180
[  148.479657]  e1000_clean_rx_irq+0x542/0x8a0
[  148.480757]  e1000_clean+0x652/0xd10
[  148.481772]  net_rx_action+0x4ea/0xc20
[  148.482808]  __do_softirq+0x1f9/0x574
[  148.483831]
[  148.484575] Freed by task 0:
[  148.485504]  __kasan_slab_free+0x12e/0x180
[  148.486589]  kmem_cache_free+0xb4/0x240
[  148.487634]  kfree_skbmem+0xed/0x150
[  148.488648]  consume_skb+0x146/0x250
[  148.489665]  validate_xmit_skb+0x2b7/0x560
[  148.490754]  validate_xmit_skb_list+0x70/0xa0
[  148.491897]  sch_direct_xmit+0x1b0/0x680
[  148.493949]  __dev_queue_xmit+0x1167/0x1810
[  148.495103]  br_dev_queue_push_xmit+0xce/0x250
[  148.496196]  br_forward_finish+0x276/0x280
[  148.497234]  __br_forward+0x44f/0x520
[  148.498260]  br_forward+0x19f/0x1b0
[  148.499264]  br_handle_frame_finish+0x65e/0x980
[  148.500398]  NF_HOOK.constprop.10+0x290/0x2a0
[  148.501522]  br_handle_frame+0x417/0x640
[  148.502582]  __netif_receive_skb_core+0xaac/0x18f0
[  148.503753]  __netif_receive_skb_one_core+0x98/0x120
[  148.504958]  netif_receive_skb_internal+0xe3/0x330
[  148.506154]  napi_gro_complete+0x190/0x2a0
[  148.507243]  dev_gro_receive+0x9f7/0x1100
[  148.508316]  napi_gro_receive+0xcb/0x260
[  148.509387]  e1000_clean_rx_irq+0x2fc/0x8a0
[  148.510501]  e1000_clean+0x652/0xd10
[  148.511523]  net_rx_action+0x4ea/0xc20
[  148.512566]  __do_softirq+0x1f9/0x574
[  148.513598]
[  148.514346] The buggy address belongs to the object at ffff8801e52eefc0
[  148.514346]  which belongs to the cache skbuff_head_cache of size 232
[  148.517047] The buggy address is located 0 bytes inside of
[  148.517047]  232-byte region [ffff8801e52eefc0, ffff8801e52ef0a8)
[  148.519549] The buggy address belongs to the page:
[  148.520726] page:ffffea000794bb00 count:1 mapcount:0 mapping:ffff880106f4dfc0 index:0xffff8801e52ee840 compound_mapcount: 0
[  148.524325] flags: 0x17ffffc0008100(slab|head)
[  148.525481] raw: 0017ffffc0008100 ffff880106b938d0 ffff880106b938d0 ffff880106f4dfc0
[  148.527503] raw: ffff8801e52ee840 0000000000190011 00000001ffffffff 0000000000000000
[  148.529547] page dumped because: kasan: bad access detected

Fixes: d4546c2509b1 ("net: Convert GRO SKB handling to list_head.")
Signed-off-by: Prashant Bhole <bhole_prashant_q7@lab.ntt.co.jp>
Reported-by: Tyler Hicks <tyhicks@canonical.com>
Tested-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1c3f0997e857..14a748ee8cc9 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5280,7 +5280,8 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
 	list_for_each_entry_safe_reverse(skb, p, head, list) {
 		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
 			return;
-		list_del_init(&skb->list);
+		list_del(&skb->list);
+		skb->next = NULL;
 		napi_gro_complete(skb);
 		napi->gro_count--;
 		napi->gro_hash[index].count--;
@@ -5461,7 +5462,8 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	ret = NAPI_GRO_CB(skb)->free ? GRO_MERGED_FREE : GRO_MERGED;
 
 	if (pp) {
-		list_del_init(&pp->list);
+		list_del(&pp->list);
+		pp->next = NULL;
 		napi_gro_complete(pp);
 		napi->gro_count--;
 		napi->gro_hash[hash].count--;
-- 
cgit v1.2.3


From 53a40025c07a47eb9377bc243993a53799bd9f3b Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:10 +0200
Subject: net: mvpp2: fix include guards in mvpp2_prs.h

Include guards should be put before #includes. This doesn't fix any bug,
but prevent future compilation issues when adding new files in the mvpp2
driver

The Header Parser init function needs the platform_device definition,
and with the fixed include guards we need to add the missing include.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index a7c8d0818432..64a64666257c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -9,14 +9,15 @@
  * License version 2. This program is licensed "as is" without any
  * warranty of any kind, whether express or implied.
  */
+#ifndef _MVPP2_PRS_H_
+#define _MVPP2_PRS_H_
+
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
+#include <linux/platform_device.h>
 
 #include "mvpp2.h"
 
-#ifndef _MVPP2_PRS_H_
-#define _MVPP2_PRS_H_
-
 /* Parser constants */
 #define MVPP2_PRS_TCAM_SRAM_SIZE	256
 #define MVPP2_PRS_TCAM_WORDS		6
-- 
cgit v1.2.3


From 0ad2f53906f9a21cd72def8e1268e75a366dc7b6 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:11 +0200
Subject: net: mvpp2: define the number of RSS entries per table in mvpp2.h

The size of the the RSS indirection tables should be defined in mvpp2.h,
so that we can use it in all files of the PPv2 driver.

This commit moves the define in mvpp2.h, and adds the missing #include
in mvpp2_cls.h.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h     | 3 +++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h | 5 ++---
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 18834619bb3a..5ef5b99a1935 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -557,6 +557,9 @@
 #define MVPP2_BIT_TO_WORD(bit)		((bit) / 32)
 #define MVPP2_BIT_IN_WORD(bit)		((bit) % 32)
 
+/* RSS constants */
+#define MVPP22_RSS_TABLE_ENTRIES	32
+
 /* IPv6 max L3 address size */
 #define MVPP2_MAX_L3_ADDR_SIZE		16
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 8e1d7f9ffa0b..e571238a83cc 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -13,15 +13,14 @@
 #ifndef _MVPP2_CLS_H_
 #define _MVPP2_CLS_H_
 
+#include "mvpp2.h"
+
 /* Classifier constants */
 #define MVPP2_CLS_FLOWS_TBL_SIZE	512
 #define MVPP2_CLS_FLOWS_TBL_DATA_WORDS	3
 #define MVPP2_CLS_LKP_TBL_SIZE		64
 #define MVPP2_CLS_RX_QUEUES		256
 
-/* RSS constants */
-#define MVPP22_RSS_TABLE_ENTRIES	32
-
 struct mvpp2_cls_flow_entry {
 	u32 index;
 	u32 data[MVPP2_CLS_FLOWS_TBL_DATA_WORDS];
-- 
cgit v1.2.3


From 1e27a628e3f444f53ab8099dfb31c5156e38d112 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:12 +0200
Subject: net: mvpp2: make sure we use single queue mode on PPv2.1

The PPv2 driver defines 2 "queue_modes" :
 - QDIST_SINGLE_MODE, where each port share one rx queue vector
   between all CPUs
 - QDIST_MULTI_MODE, where each port has one rx queue vector per CPU.

Multi queue mode isn't available on PPv2.1, make sure we fallback to
single mode when running on this revision.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 88f3da184d76..0d2dde336ea2 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5014,6 +5014,12 @@ static int mvpp2_probe(struct platform_device *pdev)
 			(unsigned long)of_device_get_match_data(&pdev->dev);
 	}
 
+	/* multi queue mode isn't supported on PPV2.1, fallback to single
+	 * mode
+	 */
+	if (priv->hw_version == MVPP21)
+		queue_mode = MVPP2_QDIST_SINGLE_MODE;
+
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(base))
-- 
cgit v1.2.3


From 3f6aaf72895a9a1e1cffc6db29871d6664249752 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:13 +0200
Subject: net: mvpp2: make multi queue mode the default mode

The multi queue mode is needed to have RSS available, and offers some
nice advantages, being able to have one rx queue vector per CPU.

This mode has been usable through the use of a module parameter, this
commit makes it the default value.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 0d2dde336ea2..b1d812b12421 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -66,7 +66,7 @@ static void mvpp2_mac_config(struct net_device *dev, unsigned int mode,
 #define MVPP2_QDIST_SINGLE_MODE	0
 #define MVPP2_QDIST_MULTI_MODE	1
 
-static int queue_mode = MVPP2_QDIST_SINGLE_MODE;
+static int queue_mode = MVPP2_QDIST_MULTI_MODE;
 
 module_param(queue_mode, int, 0444);
 MODULE_PARM_DESC(queue_mode, "Set queue_mode (single=0, multi=1)");
-- 
cgit v1.2.3


From 4c4a5686c4e7475ab16fdaa4da375e43810da978 Mon Sep 17 00:00:00 2001
From: Yan Markman <ymarkman@marvell.com>
Date: Thu, 12 Jul 2018 13:54:14 +0200
Subject: net: mvpp2: use RSS only when using multi-queue mode

Since RSS only applies when we have per-cpu rx queues, it should only
be enabled when the driver is configured to make use of multi-queue
mode.

Signed-off-by: Yan Markman <ymarkman@marvell.com>
[Maxime: Commit message]
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index b1d812b12421..75aa0dece8ae 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3276,6 +3276,11 @@ static void mvpp2_irqs_deinit(struct mvpp2_port *port)
 	}
 }
 
+static bool mvpp22_rss_is_supported(void)
+{
+	return queue_mode == MVPP2_QDIST_MULTI_MODE;
+}
+
 static int mvpp2_open(struct net_device *dev)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
@@ -3368,7 +3373,7 @@ static int mvpp2_open(struct net_device *dev)
 
 	mvpp2_start_dev(port);
 
-	if (priv->hw_version == MVPP22)
+	if (mvpp22_rss_is_supported())
 		mvpp22_init_rss(port);
 
 	/* Start hardware statistics gathering */
-- 
cgit v1.2.3


From 790d32c6d35de186154d94d6df2f0c4be33c7c52 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:15 +0200
Subject: net: mvpp2: fix hardcoded number of rx queues

There's a dedicated #define that indicates the number of rx queues per
port per cpu, this commit removes a harcoded use of that value

This doesn't fix any runtime bugs since the harcoded value matches the
expected value.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 75aa0dece8ae..4bc0b893b026 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3993,8 +3993,8 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	    MVPP2_MAX_PORTS * priv->max_port_rxqs)
 		return -EINVAL;
 
-	if (port->nrxqs % 4 || (port->nrxqs > priv->max_port_rxqs) ||
-	    (port->ntxqs > MVPP2_MAX_TXQ))
+	if (port->nrxqs % MVPP2_DEFAULT_RXQ ||
+	    port->nrxqs > priv->max_port_rxqs || port->ntxqs > MVPP2_MAX_TXQ)
 		return -EINVAL;
 
 	/* Disable port */
-- 
cgit v1.2.3


From f8c6ba8424b0fa5e001c23a30099351170f5be0d Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:16 +0200
Subject: net: mvpp2: use only one rx queue per port per CPU

The number of receive queue per port is :
 - MVPP2_DEFAULT_RXQ if in single queue mode
 - MVPP2_DEFAULT_RXQ * num_possible_cpus if in multi queue mode

with MVPP2_DEFAULT_RXQ = 4.

However, we don't use the extra rx queues at the moment, we really only
need one per port per CPU, until some more advanced classification rules
are implemented.

Suggested-by: Stefan Chulski <stefanc@marvell.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 5ef5b99a1935..dee5231b0073 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -500,7 +500,7 @@
 #define MVPP2_MAX_SKB_DESCS		(MVPP2_MAX_TSO_SEGS * 2 + MAX_SKB_FRAGS)
 
 /* Dfault number of RXQs in use */
-#define MVPP2_DEFAULT_RXQ		4
+#define MVPP2_DEFAULT_RXQ		1
 
 /* Max number of Rx descriptors */
 #define MVPP2_MAX_RXD_MAX		1024
-- 
cgit v1.2.3


From 132baa0378c5abd07c8ac1f623a19e80d16a48bd Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:17 +0200
Subject: net: mvpp2: fix a typo in the RSS code

Cosmetic patch fixing a typo in one of the RSS comments.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 8581d5b17dd5..4d187f30725c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -128,7 +128,7 @@ void mvpp22_init_rss(struct mvpp2_port *port)
 	}
 
 	/* Configure the first table to evenly distribute the packets across
-	 * real Rx Queues. The table entries map a hash to an port Rx Queue.
+	 * real Rx Queues. The table entries map a hash to a port Rx Queue.
 	 */
 	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
 		u32 sel = MVPP22_RSS_INDEX_TABLE(0) |
-- 
cgit v1.2.3


From 4b86097be7f651ab931ae6571e27a798fccdbb84 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:18 +0200
Subject: net: mvpp2: fix RSS register definitions

There is no RSS_TABLE register in PPv2 Controller. The register 0x1510
which was specified is actually named "RSS_HASH_SEL", but isn't used by
this driver at all.

Based on how this register was used, it should have been the
RXQ2RSS_TABLE register, which allows to select the RSS table that will
be used for the incoming packet.

The RSS_TABLE_POINTER is actually a field of this RXQ2RSS_TABLE
register.

Since RSS tables are actually not used by the driver for now, this
commit does not fix a runtime bug.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h     | 4 ++--
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index dee5231b0073..e6b182d8be5b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -73,9 +73,9 @@
 #define     MVPP22_RSS_INDEX_TABLE_ENTRY(idx)	(idx)
 #define     MVPP22_RSS_INDEX_TABLE(idx)		((idx) << 8)
 #define     MVPP22_RSS_INDEX_QUEUE(idx)		((idx) << 16)
-#define MVPP22_RSS_TABLE_ENTRY			0x1508
-#define MVPP22_RSS_TABLE			0x1510
+#define MVPP22_RXQ2RSS_TABLE			0x1504
 #define     MVPP22_RSS_TABLE_POINTER(p)		(p)
+#define MVPP22_RSS_TABLE_ENTRY			0x1508
 #define MVPP22_RSS_WIDTH			0x150c
 
 /* Classifier Registers */
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 4d187f30725c..fe4bcaf983b2 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -123,7 +123,7 @@ void mvpp22_init_rss(struct mvpp2_port *port)
 	 */
 	for (i = 0; i < MVPP2_CLS_RX_QUEUES; i++) {
 		mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(i));
-		mvpp2_write(priv, MVPP22_RSS_TABLE,
+		mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
 			    MVPP22_RSS_TABLE_POINTER(0));
 	}
 
-- 
cgit v1.2.3


From a27a254c264293b8ab0fe34169c654047393d370 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:19 +0200
Subject: net: mvpp2: use one RSS table per port

PPv2 Controller has 8 RSS Tables, of 32 entries each. A lookup in the
RXQ2RSS_TABLE is performed for each incoming packet, and the RSS Table
to be used is chosen according to the default rx queue that would be
used for the packet.

This default rx queue is set in the Lookup_id Table (also called
Decoding Table), and is equal to the port->first_rxq.

Since the Classifier itself isn't active at any time for the moment,
this doesn't have a direct effect, the default rx queue at the moment is
the one where all packets end-up into.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index fe4bcaf983b2..c8cf3db85ffe 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -115,23 +115,22 @@ void mvpp22_init_rss(struct mvpp2_port *port)
 	/* Set the table width: replace the whole classifier Rx queue number
 	 * with the ones configured in RSS table entries.
 	 */
-	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(0));
+	mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_TABLE(port->id));
 	mvpp2_write(priv, MVPP22_RSS_WIDTH, 8);
 
-	/* Loop through the classifier Rx Queues and map them to a RSS table.
-	 * Map them all to the first table (0) by default.
+	/* The default RxQ is used as a key to select the RSS table to use.
+	 * We use one RSS table per port.
 	 */
-	for (i = 0; i < MVPP2_CLS_RX_QUEUES; i++) {
-		mvpp2_write(priv, MVPP22_RSS_INDEX, MVPP22_RSS_INDEX_QUEUE(i));
-		mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
-			    MVPP22_RSS_TABLE_POINTER(0));
-	}
+	mvpp2_write(priv, MVPP22_RSS_INDEX,
+		    MVPP22_RSS_INDEX_QUEUE(port->first_rxq));
+	mvpp2_write(priv, MVPP22_RXQ2RSS_TABLE,
+		    MVPP22_RSS_TABLE_POINTER(port->id));
 
 	/* Configure the first table to evenly distribute the packets across
 	 * real Rx Queues. The table entries map a hash to a port Rx Queue.
 	 */
 	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
-		u32 sel = MVPP22_RSS_INDEX_TABLE(0) |
+		u32 sel = MVPP22_RSS_INDEX_TABLE(port->id) |
 			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
 		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
 
-- 
cgit v1.2.3


From 8179642b52d945852c0cd9f1372e70b09ed153b7 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:20 +0200
Subject: net: mvpp2: RSS indirection table support

This patch adds the RSS indirection table support, allowing to use the
ethtool -x and -X options to dump and set this table.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
[Maxime: Small warning fixes, use one table per port]
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h      |  3 ++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c  | 24 ++++++---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h  |  2 +
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 70 +++++++++++++++++++++++++
 4 files changed, 92 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index e6b182d8be5b..2afbbf5e71e2 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -801,6 +801,9 @@ struct mvpp2_port {
 	bool has_tx_irqs;
 
 	u32 tx_time_coal;
+
+	/* RSS indirection table */
+	u32 indir[MVPP22_RSS_TABLE_ENTRIES];
 };
 
 /* The mvpp2_tx_desc and mvpp2_rx_desc structures describe the
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index c8cf3db85ffe..c80a1a549224 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -107,6 +107,20 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 	mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
 }
 
+void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
+{
+	struct mvpp2 *priv = port->priv;
+	int i;
+
+	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
+		u32 sel = MVPP22_RSS_INDEX_TABLE(table) |
+			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
+		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
+
+		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY, port->indir[i]);
+	}
+}
+
 void mvpp22_init_rss(struct mvpp2_port *port)
 {
 	struct mvpp2 *priv = port->priv;
@@ -129,12 +143,8 @@ void mvpp22_init_rss(struct mvpp2_port *port)
 	/* Configure the first table to evenly distribute the packets across
 	 * real Rx Queues. The table entries map a hash to a port Rx Queue.
 	 */
-	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++) {
-		u32 sel = MVPP22_RSS_INDEX_TABLE(port->id) |
-			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
-		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
-
-		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY, i % port->nrxqs);
-	}
+	for (i = 0; i < MVPP22_RSS_TABLE_ENTRIES; i++)
+		port->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
 
+	mvpp22_rss_fill_table(port, port->id);
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index e571238a83cc..4c7be7469a92 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -32,6 +32,8 @@ struct mvpp2_cls_lookup_entry {
 	u32 data;
 };
 
+void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table);
+
 void mvpp22_init_rss(struct mvpp2_port *port);
 
 void mvpp2_cls_init(struct mvpp2 *priv);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 4bc0b893b026..f0b5fb78cd67 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3821,6 +3821,71 @@ static int mvpp2_ethtool_set_link_ksettings(struct net_device *dev,
 	return phylink_ethtool_ksettings_set(port->phylink, cmd);
 }
 
+static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
+				   struct ethtool_rxnfc *info, u32 *rules)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	switch (info->cmd) {
+	case ETHTOOL_GRXRINGS:
+		info->data = port->nrxqs;
+		break;
+	default:
+		return -ENOTSUPP;
+	}
+
+	return 0;
+}
+
+static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev)
+{
+	return mvpp22_rss_is_supported() ? MVPP22_RSS_TABLE_ENTRIES : 0;
+}
+
+static int mvpp2_ethtool_get_rxfh(struct net_device *dev, u32 *indir, u8 *key,
+				  u8 *hfunc)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	if (indir)
+		memcpy(indir, port->indir,
+		       ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
+
+	if (hfunc)
+		*hfunc = ETH_RSS_HASH_CRC32;
+
+	return 0;
+}
+
+static int mvpp2_ethtool_set_rxfh(struct net_device *dev, const u32 *indir,
+				  const u8 *key, const u8 hfunc)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_CRC32)
+		return -EOPNOTSUPP;
+
+	if (key)
+		return -EOPNOTSUPP;
+
+	if (indir) {
+		memcpy(port->indir, indir,
+		       ARRAY_SIZE(port->indir) * sizeof(port->indir[0]));
+		mvpp22_rss_fill_table(port, port->id);
+	}
+
+	return 0;
+}
+
 /* Device ops */
 
 static const struct net_device_ops mvpp2_netdev_ops = {
@@ -3852,6 +3917,11 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.set_pauseparam		= mvpp2_ethtool_set_pause_param,
 	.get_link_ksettings	= mvpp2_ethtool_get_link_ksettings,
 	.set_link_ksettings	= mvpp2_ethtool_set_link_ksettings,
+	.get_rxnfc		= mvpp2_ethtool_get_rxnfc,
+	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
+	.get_rxfh		= mvpp2_ethtool_get_rxfh,
+	.set_rxfh		= mvpp2_ethtool_set_rxfh,
+
 };
 
 /* Used for PPv2.1, or PPv2.2 with the old Device Tree binding that
-- 
cgit v1.2.3


From 662ae3fe65000a6b7ceeed1ecf510346d8fec447 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:21 +0200
Subject: net: mvpp2: improve the distribution of packets on CPUs when using
 RSS

This patch adds an extra indirection when setting the indirection table
into the RSS hardware table to improve the packets distribution across
CPUs. For example, if 2 queues are used on a multi-core system this new
indirection will choose two queues on two different CPUs instead of the
two first queues which are on the same first CPU.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index c80a1a549224..7dafc8c425b8 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -107,6 +107,19 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 	mvpp2_write(port->priv, MVPP2_CLS_SWFWD_PCTRL_REG, val);
 }
 
+static inline u32 mvpp22_rxfh_indir(struct mvpp2_port *port, u32 rxq)
+{
+	int nrxqs, cpus = num_possible_cpus();
+
+	/* Number of RXQs per CPU */
+	nrxqs = port->nrxqs / cpus;
+
+	/* Indirection to better distribute the paquets on the CPUs when
+	 * configuring the RSS queues.
+	 */
+	return port->first_rxq + ((rxq * nrxqs + rxq / cpus) % port->nrxqs);
+}
+
 void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
 {
 	struct mvpp2 *priv = port->priv;
@@ -117,7 +130,8 @@ void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
 			  MVPP22_RSS_INDEX_TABLE_ENTRY(i);
 		mvpp2_write(priv, MVPP22_RSS_INDEX, sel);
 
-		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY, port->indir[i]);
+		mvpp2_write(priv, MVPP22_RSS_TABLE_ENTRY,
+			    mvpp22_rxfh_indir(port, port->indir[i]));
 	}
 }
 
-- 
cgit v1.2.3


From 2a2f467daf96f519f9d2ec69e133ad1365d3e8ff Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:22 +0200
Subject: net: mvpp2: make sure we don't spread load on disabled CPUs

When filling the RSS table, we have to make sure that the rx queue is
attached to an online CPU.

This patch is not a full support for cpu_hotplug, but rather a way to
make sure that we don't break network on system booted with the maxcpus
parameter.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 7dafc8c425b8..f2bcfa8f1dfd 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -109,11 +109,17 @@ void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 
 static inline u32 mvpp22_rxfh_indir(struct mvpp2_port *port, u32 rxq)
 {
-	int nrxqs, cpus = num_possible_cpus();
+	int nrxqs, cpu, cpus = num_possible_cpus();
 
 	/* Number of RXQs per CPU */
 	nrxqs = port->nrxqs / cpus;
 
+	/* CPU that will handle this rx queue */
+	cpu = rxq / nrxqs;
+
+	if (!cpu_online(cpu))
+		return port->first_rxq;
+
 	/* Indirection to better distribute the paquets on the CPUs when
 	 * configuring the RSS queues.
 	 */
-- 
cgit v1.2.3


From e6e21c024272302ea4f0e397f044e2323035342f Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:23 +0200
Subject: net: mvpp2: rename per-port RSS init function

mvpp22_init_rss function configures the RSS parameters for each port, so
rename it accordingly. Since this function relies on classifier
configuration, move its call right after the classifier config.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c  | 2 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h  | 2 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index f2bcfa8f1dfd..66160b9b8a9a 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -141,7 +141,7 @@ void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
 	}
 }
 
-void mvpp22_init_rss(struct mvpp2_port *port)
+void mvpp22_rss_port_init(struct mvpp2_port *port)
 {
 	struct mvpp2 *priv = port->priv;
 	int i;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 4c7be7469a92..38a8cf1172df 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -34,7 +34,7 @@ struct mvpp2_cls_lookup_entry {
 
 void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table);
 
-void mvpp22_init_rss(struct mvpp2_port *port);
+void mvpp22_rss_port_init(struct mvpp2_port *port);
 
 void mvpp2_cls_init(struct mvpp2 *priv);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index f0b5fb78cd67..93e37d20899d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3373,9 +3373,6 @@ static int mvpp2_open(struct net_device *dev)
 
 	mvpp2_start_dev(port);
 
-	if (mvpp22_rss_is_supported())
-		mvpp22_init_rss(port);
-
 	/* Start hardware statistics gathering */
 	queue_delayed_work(priv->stats_queue, &port->stats_work,
 			   MVPP2_MIB_COUNTERS_STATS_DELAY);
@@ -4153,6 +4150,9 @@ static int mvpp2_port_init(struct mvpp2_port *port)
 	mvpp2_cls_oversize_rxq_set(port);
 	mvpp2_cls_port_config(port);
 
+	if (mvpp22_rss_is_supported())
+		mvpp22_rss_port_init(port);
+
 	/* Provide an initial Rx packet size */
 	port->pkt_size = MVPP2_RX_PKT_SIZE(port->dev->mtu);
 
-- 
cgit v1.2.3


From b1a962c62c80da77751a296e27c944c9bae6c6f0 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:24 +0200
Subject: net: mvpp2: use classifier to assign default rx queue

The PPv2 Controller has a classifier, that can perform multiple lookup
operations for each packet, using different engines.

One of these engines is the C2 engine, which performs TCAM based lookups
on data extracted from the packet header. When a packet matches an
entry, the engine sets various attributes, used to perform
classification operations.

One of these attributes is the rx queue in which the packet should be sent.
The current code uses the lookup_id table (also called decoding table)
to assign the rx queue. However, this only works if we use one entry per
port in the decoding table, which won't be the case once we add RSS
lookups.

This patch uses the C2 engine to assign the rx queue to each packet.

The C2 engine is used through the flow table, which dictates what
classification operations are done for a given flow.

Right now, we have one flow per port, which contains every ingress
packet for this port.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h     |  40 +++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 150 +++++++++++++++++++++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h |  56 +++++++++
 3 files changed, 246 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 2afbbf5e71e2..749d9720bf5e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -87,11 +87,28 @@
 #define     MVPP2_CLS_LKP_INDEX_WAY_OFFS	6
 #define MVPP2_CLS_LKP_TBL_REG			0x1818
 #define     MVPP2_CLS_LKP_TBL_RXQ_MASK		0xff
+#define     MVPP2_CLS_LKP_FLOW_PTR(flow)	((flow) << 16)
 #define     MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK	BIT(25)
 #define MVPP2_CLS_FLOW_INDEX_REG		0x1820
 #define MVPP2_CLS_FLOW_TBL0_REG			0x1824
+#define     MVPP2_CLS_FLOW_TBL0_LAST		BIT(0)
+#define     MVPP2_CLS_FLOW_TBL0_ENG_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL0_OFFS		1
+#define     MVPP2_CLS_FLOW_TBL0_ENG(x)		((x) << 1)
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID_MASK	0xff
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID(port)	((port) << 4)
+#define     MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL	BIT(23)
 #define MVPP2_CLS_FLOW_TBL1_REG			0x1828
+#define     MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL1_N_FIELDS(x)	(x)
+#define     MVPP2_CLS_FLOW_TBL1_PRIO_MASK	0x3f
+#define     MVPP2_CLS_FLOW_TBL1_PRIO(x)		((x) << 9)
+#define     MVPP2_CLS_FLOW_TBL1_SEQ_MASK	0x7
+#define     MVPP2_CLS_FLOW_TBL1_SEQ(x)		((x) << 15)
 #define MVPP2_CLS_FLOW_TBL2_REG			0x182c
+#define     MVPP2_CLS_FLOW_TBL2_FLD_MASK	0x3f
+#define     MVPP2_CLS_FLOW_TBL2_FLD_OFFS(n)	((n) * 6)
+#define     MVPP2_CLS_FLOW_TBL2_FLD(n, x)	((x) << ((n) * 6))
 #define MVPP2_CLS_OVERSIZE_RXQ_LOW_REG(port)	(0x1980 + ((port) * 4))
 #define     MVPP2_CLS_OVERSIZE_RXQ_LOW_BITS	3
 #define     MVPP2_CLS_OVERSIZE_RXQ_LOW_MASK	0x7
@@ -99,6 +116,29 @@
 #define MVPP2_CLS_SWFWD_PCTRL_REG		0x19d0
 #define     MVPP2_CLS_SWFWD_PCTRL_MASK(port)	(1 << (port))
 
+/* Classifier C2 engine Registers */
+#define MVPP22_CLS_C2_TCAM_IDX			0x1b00
+#define MVPP22_CLS_C2_TCAM_DATA0		0x1b10
+#define MVPP22_CLS_C2_TCAM_DATA1		0x1b14
+#define MVPP22_CLS_C2_TCAM_DATA2		0x1b18
+#define MVPP22_CLS_C2_TCAM_DATA3		0x1b1c
+#define MVPP22_CLS_C2_TCAM_DATA4		0x1b20
+#define     MVPP22_CLS_C2_PORT_ID(port)		((port) << 8)
+#define MVPP22_CLS_C2_ACT			0x1b60
+#define     MVPP22_CLS_C2_ACT_RSS_EN(act)	(((act) & 0x3) << 19)
+#define     MVPP22_CLS_C2_ACT_FWD(act)		(((act) & 0x7) << 13)
+#define     MVPP22_CLS_C2_ACT_QHIGH(act)	(((act) & 0x3) << 11)
+#define     MVPP22_CLS_C2_ACT_QLOW(act)		(((act) & 0x3) << 9)
+#define MVPP22_CLS_C2_ATTR0			0x1b64
+#define     MVPP22_CLS_C2_ATTR0_QHIGH(qh)	(((qh) & 0x1f) << 24)
+#define     MVPP22_CLS_C2_ATTR0_QHIGH_MASK	0x1f
+#define     MVPP22_CLS_C2_ATTR0_QLOW(ql)	(((ql) & 0x7) << 21)
+#define     MVPP22_CLS_C2_ATTR0_QLOW_MASK	0x7
+#define MVPP22_CLS_C2_ATTR1			0x1b68
+#define MVPP22_CLS_C2_ATTR2			0x1b6c
+#define     MVPP22_CLS_C2_ATTR2_RSS_EN		BIT(30)
+#define MVPP22_CLS_C2_ATTR3			0x1b70
+
 /* Descriptor Manager Top Registers */
 #define MVPP2_RXQ_NUM_REG			0x2040
 #define MVPP2_RXQ_DESC_ADDR_REG			0x2044
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 66160b9b8a9a..7cee117efb4f 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -12,6 +12,7 @@
 
 #include "mvpp2.h"
 #include "mvpp2_cls.h"
+#include "mvpp2_prs.h"
 
 /* Update classification flow table registers */
 static void mvpp2_cls_flow_write(struct mvpp2 *priv,
@@ -34,6 +35,151 @@ static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_CLS_LKP_TBL_REG, le->data);
 }
 
+static void mvpp2_cls_flow_eng_set(struct mvpp2_cls_flow_entry *fe,
+				   int engine)
+{
+	fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_ENG(MVPP2_CLS_FLOW_TBL0_ENG_MASK);
+	fe->data[0] |= MVPP2_CLS_FLOW_TBL0_ENG(engine);
+}
+
+static void mvpp2_cls_flow_port_id_sel(struct mvpp2_cls_flow_entry *fe,
+				       bool from_packet)
+{
+	if (from_packet)
+		fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
+	else
+		fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_PORT_ID_SEL;
+}
+
+static void mvpp2_cls_flow_seq_set(struct mvpp2_cls_flow_entry *fe, u32 seq)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_SEQ(MVPP2_CLS_FLOW_TBL1_SEQ_MASK);
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_SEQ(seq);
+}
+
+static void mvpp2_cls_flow_last_set(struct mvpp2_cls_flow_entry *fe,
+				    bool is_last)
+{
+	fe->data[0] &= ~MVPP2_CLS_FLOW_TBL0_LAST;
+	fe->data[0] |= !!is_last;
+}
+
+static void mvpp2_cls_flow_pri_set(struct mvpp2_cls_flow_entry *fe, int prio)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_PRIO(MVPP2_CLS_FLOW_TBL1_PRIO_MASK);
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_PRIO(prio);
+}
+
+static void mvpp2_cls_flow_port_add(struct mvpp2_cls_flow_entry *fe,
+				    u32 port)
+{
+	fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
+}
+
+/* Initialize the Lookup Id table entry for the given flow */
+static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv, int port_id)
+{
+	struct mvpp2_cls_lookup_entry le;
+
+	le.way = 0;
+	le.lkpid = port_id;
+
+	/* The default RxQ for this port is set in the C2 lookup */
+	le.data = 0;
+
+	le.data |= MVPP2_CLS_LKP_FLOW_PTR(port_id);
+	le.data |= MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK;
+
+	mvpp2_cls_lookup_write(priv, &le);
+}
+
+/* Initialize the flow table entries for the given flow */
+static void mvpp2_cls_flow_init(struct mvpp2 *priv, int port_id)
+{
+	struct mvpp2_cls_flow_entry fe;
+	int i;
+
+	/* C2 lookup */
+	memset(&fe, 0, sizeof(fe));
+	fe.index = port_id;
+
+	mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
+	mvpp2_cls_flow_port_id_sel(&fe, true);
+	mvpp2_cls_flow_last_set(&fe, 1);
+	mvpp2_cls_flow_pri_set(&fe, 0);
+	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
+
+	/* Add all ports */
+	for (i = 0; i < MVPP2_MAX_PORTS; i++)
+		mvpp2_cls_flow_port_add(&fe, BIT(i));
+
+	mvpp2_cls_flow_write(priv, &fe);
+}
+
+static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
+{
+	int i;
+
+	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+		mvpp2_cls_flow_lkp_init(priv, i);
+		mvpp2_cls_flow_init(priv, i);
+	}
+}
+
+static void mvpp2_cls_c2_write(struct mvpp2 *priv,
+			       struct mvpp2_cls_c2_entry *c2)
+{
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2->index);
+
+	/* Write TCAM */
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA0, c2->tcam[0]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA1, c2->tcam[1]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA2, c2->tcam[2]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA3, c2->tcam[3]);
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_DATA4, c2->tcam[4]);
+
+	mvpp2_write(priv, MVPP22_CLS_C2_ACT, c2->act);
+
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR0, c2->attr[0]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR1, c2->attr[1]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR2, c2->attr[2]);
+	mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
+}
+
+static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+	u8 qh, ql, pmap;
+
+	memset(&c2, 0, sizeof(c2));
+
+	c2.index = MVPP22_CLS_C2_RSS_ENTRY(port->id);
+
+	pmap = BIT(port->id);
+	c2.tcam[4] = MVPP22_CLS_C2_PORT_ID(pmap);
+	c2.tcam[4] |= MVPP22_CLS_C2_TCAM_EN(MVPP22_CLS_C2_PORT_ID(pmap));
+
+	/* Update RSS status after matching this entry */
+	c2.act = MVPP22_CLS_C2_ACT_RSS_EN(MVPP22_C2_UPD_LOCK);
+
+	/* Mark packet as "forwarded to software", needed for RSS */
+	c2.act |= MVPP22_CLS_C2_ACT_FWD(MVPP22_C2_FWD_SW_LOCK);
+
+	/* Configure the default rx queue : Update Queue Low and Queue High, but
+	 * don't lock, since the rx queue selection might be overridden by RSS
+	 */
+	c2.act |= MVPP22_CLS_C2_ACT_QHIGH(MVPP22_C2_UPD) |
+		   MVPP22_CLS_C2_ACT_QLOW(MVPP22_C2_UPD);
+
+	qh = (port->first_rxq >> 3) & MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+	ql = port->first_rxq & MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+	c2.attr[0] = MVPP22_CLS_C2_ATTR0_QHIGH(qh) |
+		      MVPP22_CLS_C2_ATTR0_QLOW(ql);
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
 /* Classifier default initialization */
 void mvpp2_cls_init(struct mvpp2 *priv)
 {
@@ -61,6 +207,8 @@ void mvpp2_cls_init(struct mvpp2 *priv)
 		le.way = 1;
 		mvpp2_cls_lookup_write(priv, &le);
 	}
+
+	mvpp2_cls_port_init_flows(priv);
 }
 
 void mvpp2_cls_port_config(struct mvpp2_port *port)
@@ -89,6 +237,8 @@ void mvpp2_cls_port_config(struct mvpp2_port *port)
 
 	/* Update lookup ID table entry */
 	mvpp2_cls_lookup_write(port->priv, &le);
+
+	mvpp2_port_c2_cls_init(port);
 }
 
 /* Set CPU queue number for oversize packets */
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 38a8cf1172df..ee4933ca7ed8 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -14,6 +14,7 @@
 #define _MVPP2_CLS_H_
 
 #include "mvpp2.h"
+#include "mvpp2_prs.h"
 
 /* Classifier constants */
 #define MVPP2_CLS_FLOWS_TBL_SIZE	512
@@ -21,6 +22,61 @@
 #define MVPP2_CLS_LKP_TBL_SIZE		64
 #define MVPP2_CLS_RX_QUEUES		256
 
+/* Classifier flow constants */
+enum mvpp2_cls_engine {
+	MVPP22_CLS_ENGINE_C2 = 1,
+	MVPP22_CLS_ENGINE_C3A,
+	MVPP22_CLS_ENGINE_C3B,
+	MVPP22_CLS_ENGINE_C4,
+	MVPP22_CLS_ENGINE_C3HA = 6,
+	MVPP22_CLS_ENGINE_C3HB = 7,
+};
+
+enum mvpp2_cls_flow_seq {
+	MVPP2_CLS_FLOW_SEQ_NORMAL = 0,
+	MVPP2_CLS_FLOW_SEQ_FIRST1,
+	MVPP2_CLS_FLOW_SEQ_FIRST2,
+	MVPP2_CLS_FLOW_SEQ_LAST,
+	MVPP2_CLS_FLOW_SEQ_MIDDLE
+};
+
+/* Classifier C2 engine constants */
+#define MVPP22_CLS_C2_TCAM_EN(data)		((data) << 16)
+
+enum mvpp22_cls_c2_action {
+	MVPP22_C2_NO_UPD = 0,
+	MVPP22_C2_NO_UPD_LOCK,
+	MVPP22_C2_UPD,
+	MVPP22_C2_UPD_LOCK,
+};
+
+enum mvpp22_cls_c2_fwd_action {
+	MVPP22_C2_FWD_NO_UPD = 0,
+	MVPP22_C2_FWD_NO_UPD_LOCK,
+	MVPP22_C2_FWD_SW,
+	MVPP22_C2_FWD_SW_LOCK,
+	MVPP22_C2_FWD_HW,
+	MVPP22_C2_FWD_HW_LOCK,
+	MVPP22_C2_FWD_HW_LOW_LAT,
+	MVPP22_C2_FWD_HW_LOW_LAT_LOCK,
+};
+
+#define MVPP2_CLS_C2_TCAM_WORDS			5
+#define MVPP2_CLS_C2_ATTR_WORDS			5
+
+struct mvpp2_cls_c2_entry {
+	u32 index;
+	u32 tcam[MVPP2_CLS_C2_TCAM_WORDS];
+	u32 act;
+	u32 attr[MVPP2_CLS_C2_ATTR_WORDS];
+};
+
+/* Classifier C2 engine entries */
+#define MVPP22_CLS_C2_RSS_ENTRY(port)	(port)
+#define MVPP22_CLS_C2_N_ENTRIES		MVPP2_MAX_PORTS
+
+#define MVPP22_RSS_FLOW_C2_OFFS		0
+
 struct mvpp2_cls_flow_entry {
 	u32 index;
 	u32 data[MVPP2_CLS_FLOWS_TBL_DATA_WORDS];
-- 
cgit v1.2.3


From f9358e12a0af53d107df09d4c0254425b6a10468 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:25 +0200
Subject: net: mvpp2: split ingress traffic into multiple flows

The PPv2 classifier allows to perform classification operations on each
ingress packet, based on the flow the packet is assigned to.

The current code uses only 1 flow per port, and the only classification
action consists of assigning the rx queue to the packet, depending on the
port.

In preparation for adding RSS support, we have to split all incoming
traffic into different flows. Since RSS assigns a rx queue depending on
the hash of some header fields, we have to make sure that the hash is
generated in a consistent way for all packets in the same flow.

What we call a "flow" is actually a set of attributes attached to a
packet that depends on various L2/L3/L4 info.

This patch introduces 52 flows, wich are a combination of various L2, L3
and L4 attributes :
 - Whether or not the packet has a VLAN tag
 - Whether the packet is IPv4, IPv6 or something else
 - Whether the packet is TCP, UDP or something else
 - Whether or not the packet is fragmented at L3 level.

The flow is associated to a packet by the Header Parser. Each flow
corresponds to an entry in the decoding table. This entry then points to
the sequence of classification lookups to be performed by the
classifier, represented in the flow table.

For now, the only lookup we perform is a C2 lookup to set the default
rx queue.

               Header parser          Dec table
 Ingress pkt  +-------------+ flow id +----------------------------+
------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag  |
              +-------------+         |TCP IPv4 w/o VLAN, not frag |
                                      |TCP IPv4 w/ VLAN, frag      |--+
                                      |etc.                        |  |
                                      +----------------------------+  |
                                                                      |
                                           Flow table                 |
                +------------+        +---------------------+         |
     To RxQ <---| Classifier |<-------| flow 0: C2 lookup   |<--------+
                +------------+        | flow 1: C2 lookup   |
                       |              | ...                 |
                +------------+        | flow 51 : C2 lookup |
		| C2 engine  |        +---------------------+
                +------------+

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 355 ++++++++++++++++++++++++-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h |  96 +++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c |  35 +++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h |  11 +
 4 files changed, 489 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 7cee117efb4f..1fc8a446d94e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -14,6 +14,317 @@
 #include "mvpp2_cls.h"
 #include "mvpp2_prs.h"
 
+#define MVPP2_DEF_FLOW(_type, _id, _opts, _ri, _ri_mask)	\
+{								\
+	.flow_type = _type,					\
+	.flow_id = _id,						\
+	.supported_hash_opts = _opts,				\
+	.prs_ri = {						\
+		.ri = _ri,					\
+		.ri_mask = _ri_mask				\
+	}							\
+}
+
+static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
+	/* TCP over IPv4 flows, Not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv4 flows, Not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* TCP over IPv4 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv4 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V4_FLOW, MVPP2_FL_IP4_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv4 flows, Not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP4_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv4 flows, Not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP4_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv4 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4 |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv4 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4 | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V4_FLOW, MVPP2_FL_IP4_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* TCP over IPv6 flows, not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv6 flows, not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* TCP over IPv6 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* TCP over IPv6 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(TCP_V6_FLOW, MVPP2_FL_IP6_TCP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_TCP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv6 flows, not fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_UNTAG,
+		       MVPP22_CLS_HEK_IP6_5T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv6 flows, not fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_NF_TAG,
+		       MVPP22_CLS_HEK_IP6_5T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* UDP over IPv6 flows, fragmented, no vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6 |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6_EXT |
+		       MVPP2_PRS_RI_IP_FRAG_TRUE | MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK | MVPP2_PRS_RI_VLAN_MASK),
+
+	/* UDP over IPv6 flows, fragmented, with vlan tag */
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6 | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	MVPP2_DEF_FLOW(UDP_V6_FLOW, MVPP2_FL_IP6_UDP_FRAG_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6_EXT | MVPP2_PRS_RI_IP_FRAG_TRUE |
+		       MVPP2_PRS_RI_L4_UDP,
+		       MVPP2_PRS_IP_MASK),
+
+	/* IPv4 flows, no vlan tag */
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OPT,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_UNTAG,
+		       MVPP22_CLS_HEK_IP4_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP4_OTHER,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* IPv4 flows, with vlan tag */
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OPT,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV4_FLOW, MVPP2_FL_IP4_TAG,
+		       MVPP22_CLS_HEK_IP4_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP4_OTHER,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* IPv6 flows, no vlan tag */
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_UNTAG,
+		       MVPP22_CLS_HEK_IP6_2T,
+		       MVPP2_PRS_RI_VLAN_NONE | MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_VLAN_MASK | MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* IPv6 flows, with vlan tag */
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+	MVPP2_DEF_FLOW(IPV6_FLOW, MVPP2_FL_IP6_TAG,
+		       MVPP22_CLS_HEK_IP6_2T | MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP2_PRS_RI_L3_IP6,
+		       MVPP2_PRS_RI_L3_PROTO_MASK),
+
+	/* Non IP flow, no vlan tag */
+	MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_UNTAG,
+		       0,
+		       MVPP2_PRS_RI_VLAN_NONE,
+		       MVPP2_PRS_RI_VLAN_MASK),
+	/* Non IP flow, with vlan tag */
+	MVPP2_DEF_FLOW(ETHER_FLOW, MVPP2_FL_NON_IP_TAG,
+		       MVPP22_CLS_HEK_OPT_VLAN,
+		       0, 0),
+};
+
 /* Update classification flow table registers */
 static void mvpp2_cls_flow_write(struct mvpp2 *priv,
 				 struct mvpp2_cls_flow_entry *fe)
@@ -76,32 +387,46 @@ static void mvpp2_cls_flow_port_add(struct mvpp2_cls_flow_entry *fe,
 	fe->data[0] |= MVPP2_CLS_FLOW_TBL0_PORT_ID(port);
 }
 
+/* Initialize the parser entry for the given flow */
+static void mvpp2_cls_flow_prs_init(struct mvpp2 *priv,
+				    struct mvpp2_cls_flow *flow)
+{
+	mvpp2_prs_add_flow(priv, flow->flow_id, flow->prs_ri.ri,
+			   flow->prs_ri.ri_mask);
+}
+
 /* Initialize the Lookup Id table entry for the given flow */
-static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv, int port_id)
+static void mvpp2_cls_flow_lkp_init(struct mvpp2 *priv,
+				    struct mvpp2_cls_flow *flow)
 {
 	struct mvpp2_cls_lookup_entry le;
 
 	le.way = 0;
-	le.lkpid = port_id;
+	le.lkpid = flow->flow_id;
 
 	/* The default RxQ for this port is set in the C2 lookup */
 	le.data = 0;
 
-	le.data |= MVPP2_CLS_LKP_FLOW_PTR(port_id);
+	/* We point on the first lookup in the sequence for the flow, that is
+	 * the C2 lookup.
+	 */
+	le.data |= MVPP2_CLS_LKP_FLOW_PTR(MVPP2_FLOW_C2_ENTRY(flow->flow_id));
+
+	/* CLS is always enabled, RSS is enabled/disabled in C2 lookup */
 	le.data |= MVPP2_CLS_LKP_TBL_LOOKUP_EN_MASK;
 
 	mvpp2_cls_lookup_write(priv, &le);
 }
 
 /* Initialize the flow table entries for the given flow */
-static void mvpp2_cls_flow_init(struct mvpp2 *priv, int port_id)
+static void mvpp2_cls_flow_init(struct mvpp2 *priv, struct mvpp2_cls_flow *flow)
 {
 	struct mvpp2_cls_flow_entry fe;
 	int i;
 
 	/* C2 lookup */
 	memset(&fe, 0, sizeof(fe));
-	fe.index = port_id;
+	fe.index = MVPP2_FLOW_C2_ENTRY(flow->flow_id);
 
 	mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
 	mvpp2_cls_flow_port_id_sel(&fe, true);
@@ -116,13 +441,27 @@ static void mvpp2_cls_flow_init(struct mvpp2 *priv, int port_id)
 	mvpp2_cls_flow_write(priv, &fe);
 }
 
+struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
+{
+	if (flow >= MVPP2_N_FLOWS)
+		return NULL;
+
+	return &cls_flows[flow];
+}
+
 static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
 {
+	struct mvpp2_cls_flow *flow;
 	int i;
 
-	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
-		mvpp2_cls_flow_lkp_init(priv, i);
-		mvpp2_cls_flow_init(priv, i);
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			break;
+
+		mvpp2_cls_flow_prs_init(priv, flow);
+		mvpp2_cls_flow_lkp_init(priv, flow);
+		mvpp2_cls_flow_init(priv, flow);
 	}
 }
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index ee4933ca7ed8..747c5f055b82 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -23,6 +23,9 @@
 #define MVPP2_CLS_RX_QUEUES		256
 
 /* Classifier flow constants */
+
+#define MVPP2_FLOW_N_FIELDS		4
+
 enum mvpp2_cls_engine {
 	MVPP22_CLS_ENGINE_C2 = 1,
 	MVPP22_CLS_ENGINE_C3A,
@@ -32,6 +35,33 @@ enum mvpp2_cls_engine {
 	MVPP22_CLS_ENGINE_C3HB = 7,
 };
 
+#define MVPP22_CLS_HEK_OPT_MAC_DA	BIT(0)
+#define MVPP22_CLS_HEK_OPT_VLAN		BIT(1)
+#define MVPP22_CLS_HEK_OPT_L3_PROTO	BIT(2)
+#define MVPP22_CLS_HEK_OPT_IP4SA	BIT(3)
+#define MVPP22_CLS_HEK_OPT_IP4DA	BIT(4)
+#define MVPP22_CLS_HEK_OPT_IP6SA	BIT(5)
+#define MVPP22_CLS_HEK_OPT_IP6DA	BIT(6)
+#define MVPP22_CLS_HEK_OPT_L4SIP	BIT(7)
+#define MVPP22_CLS_HEK_OPT_L4DIP	BIT(8)
+#define MVPP22_CLS_HEK_N_FIELDS		9
+
+#define MVPP22_CLS_HEK_L4_OPTS	(MVPP22_CLS_HEK_OPT_L4SIP | \
+				 MVPP22_CLS_HEK_OPT_L4DIP)
+
+#define MVPP22_CLS_HEK_IP4_2T	(MVPP22_CLS_HEK_OPT_IP4SA | \
+				 MVPP22_CLS_HEK_OPT_IP4DA)
+
+#define MVPP22_CLS_HEK_IP6_2T	(MVPP22_CLS_HEK_OPT_IP6SA | \
+				 MVPP22_CLS_HEK_OPT_IP6DA)
+
+/* The fifth tuple in "5T" is the L4_Info field */
+#define MVPP22_CLS_HEK_IP4_5T	(MVPP22_CLS_HEK_IP4_2T | \
+				 MVPP22_CLS_HEK_L4_OPTS)
+
+#define MVPP22_CLS_HEK_IP6_5T	(MVPP22_CLS_HEK_IP6_2T | \
+				 MVPP22_CLS_HEK_L4_OPTS)
+
 enum mvpp2_cls_flow_seq {
 	MVPP2_CLS_FLOW_SEQ_NORMAL = 0,
 	MVPP2_CLS_FLOW_SEQ_FIRST1,
@@ -75,8 +105,74 @@ struct mvpp2_cls_c2_entry {
 #define MVPP22_CLS_C2_RSS_ENTRY(port)	(port)
 #define MVPP22_CLS_C2_N_ENTRIES		MVPP2_MAX_PORTS
 
+/* RSS flow entries in the flow table. We have 2 entries per port for RSS.
+ *
+ * The first performs a lookup using the C2 TCAM engine, to tag the
+ * packet for software forwarding (needed for RSS), enable or disable RSS, and
+ * assign the default rx queue.
+ *
+ * The second configures the hash generation, by specifying which fields of the
+ * packet header are used to generate the hash, and specifies the relevant hash
+ * engine to use.
+ */
 #define MVPP22_RSS_FLOW_C2_OFFS		0
+#define MVPP22_RSS_FLOW_HASH_OFFS	1
+#define MVPP22_RSS_FLOW_SIZE		(MVPP22_RSS_FLOW_HASH_OFFS + 1)
+
+#define MVPP22_RSS_FLOW_C2(port)	((port) * MVPP22_RSS_FLOW_SIZE + \
+					 MVPP22_RSS_FLOW_C2_OFFS)
+#define MVPP22_RSS_FLOW_HASH(port)	((port) * MVPP22_RSS_FLOW_SIZE + \
+					 MVPP22_RSS_FLOW_HASH_OFFS)
+#define MVPP22_RSS_FLOW_FIRST(port)	MVPP22_RSS_FLOW_C2(port)
+
+/* Packet flow ID */
+enum mvpp2_prs_flow {
+	MVPP2_FL_START = 8,
+	MVPP2_FL_IP4_TCP_NF_UNTAG = MVPP2_FL_START,
+	MVPP2_FL_IP4_UDP_NF_UNTAG,
+	MVPP2_FL_IP4_TCP_NF_TAG,
+	MVPP2_FL_IP4_UDP_NF_TAG,
+	MVPP2_FL_IP6_TCP_NF_UNTAG,
+	MVPP2_FL_IP6_UDP_NF_UNTAG,
+	MVPP2_FL_IP6_TCP_NF_TAG,
+	MVPP2_FL_IP6_UDP_NF_TAG,
+	MVPP2_FL_IP4_TCP_FRAG_UNTAG,
+	MVPP2_FL_IP4_UDP_FRAG_UNTAG,
+	MVPP2_FL_IP4_TCP_FRAG_TAG,
+	MVPP2_FL_IP4_UDP_FRAG_TAG,
+	MVPP2_FL_IP6_TCP_FRAG_UNTAG,
+	MVPP2_FL_IP6_UDP_FRAG_UNTAG,
+	MVPP2_FL_IP6_TCP_FRAG_TAG,
+	MVPP2_FL_IP6_UDP_FRAG_TAG,
+	MVPP2_FL_IP4_UNTAG, /* non-TCP, non-UDP, same for below */
+	MVPP2_FL_IP4_TAG,
+	MVPP2_FL_IP6_UNTAG,
+	MVPP2_FL_IP6_TAG,
+	MVPP2_FL_NON_IP_UNTAG,
+	MVPP2_FL_NON_IP_TAG,
+	MVPP2_FL_LAST,
+};
+
+struct mvpp2_cls_flow {
+	/* The L2-L4 traffic flow type */
+	int flow_type;
+
+	/* The first id in the flow table for this flow */
+	u16 flow_id;
+
+	/* The supported HEK fields for this flow */
+	u16 supported_hash_opts;
+
+	/* The Header Parser result_info that matches this flow */
+	struct mvpp2_prs_result_info prs_ri;
+};
+
+#define MVPP2_N_FLOWS	52
 
+#define MVPP2_ENTRIES_PER_FLOW			(MVPP2_MAX_PORTS + 1)
+#define MVPP2_FLOW_C2_ENTRY(id)			((id) * MVPP2_ENTRIES_PER_FLOW)
+#define MVPP2_PORT_FLOW_HASH_ENTRY(port, id)	((id) * MVPP2_ENTRIES_PER_FLOW + \
+						(port) + 1)
 struct mvpp2_cls_flow_entry {
 	u32 index;
 	u32 data[MVPP2_CLS_FLOWS_TBL_DATA_WORDS];
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index a882c14d7d77..acf9f78d5f80 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -2409,6 +2409,41 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 	return 0;
 }
 
+int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
+{
+	struct mvpp2_prs_entry pe;
+	u8 *ri_byte, *ri_byte_mask;
+	int tid, i;
+
+	memset(&pe, 0, sizeof(pe));
+
+	tid = mvpp2_prs_tcam_first_free(priv,
+					MVPP2_PE_LAST_FREE_TID,
+					MVPP2_PE_FIRST_FREE_TID);
+	if (tid < 0)
+		return tid;
+
+	pe.index = tid;
+
+	ri_byte = (u8 *)&ri;
+	ri_byte_mask = (u8 *)&ri_mask;
+
+	mvpp2_prs_sram_ai_update(&pe, flow, MVPP2_PRS_FLOW_ID_MASK);
+	mvpp2_prs_sram_bits_set(&pe, MVPP2_PRS_SRAM_LU_DONE_BIT, 1);
+
+	for (i = 0; i < 4; i++) {
+		mvpp2_prs_tcam_data_byte_set(&pe, i, ri_byte[i],
+					     ri_byte_mask[i]);
+	}
+
+	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_FLOWS);
+	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
+	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
+	mvpp2_prs_hw_write(priv, &pe);
+
+	return 0;
+}
+
 /* Set prs flow for the port */
 int mvpp2_prs_def_flow(struct mvpp2_port *port)
 {
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index 64a64666257c..368e90b54477 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -224,6 +224,10 @@
 #define MVPP2_PRS_RI_UDF7_IP6_LITE		BIT(29)
 #define MVPP2_PRS_RI_DROP_MASK			0x80000000
 
+#define MVPP2_PRS_IP_MASK			(MVPP2_PRS_RI_L3_PROTO_MASK | \
+						MVPP2_PRS_RI_IP_FRAG_MASK | \
+						MVPP2_PRS_RI_L4_PROTO_MASK)
+
 /* Sram additional info bits assignment */
 #define MVPP2_PRS_IPV4_DIP_AI_BIT		BIT(0)
 #define MVPP2_PRS_IPV6_NO_EXT_AI_BIT		BIT(0)
@@ -271,6 +275,11 @@ struct mvpp2_prs_entry {
 	u32 sram[MVPP2_PRS_SRAM_WORDS];
 };
 
+struct mvpp2_prs_result_info {
+	u32 ri;
+	u32 ri_mask;
+};
+
 struct mvpp2_prs_shadow {
 	bool valid;
 	bool finish;
@@ -292,6 +301,8 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add);
 
 int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type);
 
+int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask);
+
 int mvpp2_prs_def_flow(struct mvpp2_port *port);
 
 void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port);
-- 
cgit v1.2.3


From d33ec452500798868c430c5e2e4b5e8399ae70e3 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:26 +0200
Subject: net: mvpp2: add an RSS classification step for each flow

One of the classification action that can be performed is to compute a
hash of the packet header based on some header fields, and lookup a RSS
table based on this hash to determine the final RxQ.

This is done by adding one lookup entry per flow per port, so that we
can configure the hash generation parameters for each flow and each
port.

There are 2 possible engines that can be used for RSS hash generation :

 - C3HA, that generates a hash based on up to 4 header-extracted fields
 - C3HB, that does the same as c3HA, but also includes L4 info in the hash

There are a lot of fields that can be extracted from the header. For now,
we only use the ones that we can configure using ethtool :
 - DST MAC address
 - L3 info
 - Source IP
 - Destination IP
 - Source port
 - Destination port

The C3HB engine is selected when we use L4 fields (src/dst port).

               Header parser          Dec table
 Ingress pkt  +-------------+ flow id +----------------------------+
------------->| TCAM + SRAM |-------->|TCP IPv4 w/ VLAN, not frag  |
              +-------------+         |TCP IPv4 w/o VLAN, not frag |
                                      |TCP IPv4 w/ VLAN, frag      |--+
                                      |etc.                        |  |
                                      +----------------------------+  |
                                                                      |
                                            Flow table                |
  +---------+   +------------+         +--------------------------+   |
  | RSS tbl |<--| Classifier |<--------| flow 0: C2 lookup        |   |
  +---------+   +------------+         |         C3 lookup port 0 |   |
                 |         |           |         C3 lookup port 1 |   |
         +-----------+ +-------------+ |         ...              |   |
         | C2 engine | | C3H engines | | flow 1: C2 lookup        |<--+
         +-----------+ +-------------+ |         C3 lookup port 0 |
                                       |         ...              |
                                       | ...                      |
                                       | flow 51 : C2 lookup      |
                                       |           ...            |
                                       +--------------------------+

The C2 engine also gains the role of enabling and disabling the RSS
table lookup for this packet.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c  | 279 +++++++++++++++++++++++-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h  |  15 ++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c |  10 +
 3 files changed, 302 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 1fc8a446d94e..98e0e25f7dca 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -325,6 +325,16 @@ static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
 		       0, 0),
 };
 
+static void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+				struct mvpp2_cls_flow_entry *fe)
+{
+	fe->index = index;
+	mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, index);
+	fe->data[0] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL0_REG);
+	fe->data[1] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL1_REG);
+	fe->data[2] = mvpp2_read(priv, MVPP2_CLS_FLOW_TBL2_REG);
+}
+
 /* Update classification flow table registers */
 static void mvpp2_cls_flow_write(struct mvpp2 *priv,
 				 struct mvpp2_cls_flow_entry *fe)
@@ -346,6 +356,34 @@ static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_CLS_LKP_TBL_REG, le->data);
 }
 
+/* Operations on flow entry */
+static int mvpp2_cls_flow_hek_num_get(struct mvpp2_cls_flow_entry *fe)
+{
+	return fe->data[1] & MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+}
+
+static void mvpp2_cls_flow_hek_num_set(struct mvpp2_cls_flow_entry *fe,
+				       int num_of_fields)
+{
+	fe->data[1] &= ~MVPP2_CLS_FLOW_TBL1_N_FIELDS_MASK;
+	fe->data[1] |= MVPP2_CLS_FLOW_TBL1_N_FIELDS(num_of_fields);
+}
+
+static int mvpp2_cls_flow_hek_get(struct mvpp2_cls_flow_entry *fe,
+				  int field_index)
+{
+	return (fe->data[2] >> MVPP2_CLS_FLOW_TBL2_FLD_OFFS(field_index)) &
+		MVPP2_CLS_FLOW_TBL2_FLD_MASK;
+}
+
+static void mvpp2_cls_flow_hek_set(struct mvpp2_cls_flow_entry *fe,
+				   int field_index, int field_id)
+{
+	fe->data[2] &= ~MVPP2_CLS_FLOW_TBL2_FLD(field_index,
+						MVPP2_CLS_FLOW_TBL2_FLD_MASK);
+	fe->data[2] |= MVPP2_CLS_FLOW_TBL2_FLD(field_index, field_id);
+}
+
 static void mvpp2_cls_flow_eng_set(struct mvpp2_cls_flow_entry *fe,
 				   int engine)
 {
@@ -430,15 +468,93 @@ static void mvpp2_cls_flow_init(struct mvpp2 *priv, struct mvpp2_cls_flow *flow)
 
 	mvpp2_cls_flow_eng_set(&fe, MVPP22_CLS_ENGINE_C2);
 	mvpp2_cls_flow_port_id_sel(&fe, true);
-	mvpp2_cls_flow_last_set(&fe, 1);
+	mvpp2_cls_flow_last_set(&fe, 0);
 	mvpp2_cls_flow_pri_set(&fe, 0);
-	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
+	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_FIRST1);
 
 	/* Add all ports */
 	for (i = 0; i < MVPP2_MAX_PORTS; i++)
 		mvpp2_cls_flow_port_add(&fe, BIT(i));
 
 	mvpp2_cls_flow_write(priv, &fe);
+
+	/* C3Hx lookups */
+	for (i = 0; i < MVPP2_MAX_PORTS; i++) {
+		memset(&fe, 0, sizeof(fe));
+		fe.index = MVPP2_PORT_FLOW_HASH_ENTRY(i, flow->flow_id);
+
+		mvpp2_cls_flow_port_id_sel(&fe, true);
+		mvpp2_cls_flow_pri_set(&fe, i + 1);
+		mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_MIDDLE);
+		mvpp2_cls_flow_port_add(&fe, BIT(i));
+
+		mvpp2_cls_flow_write(priv, &fe);
+	}
+
+	/* Update the last entry */
+	mvpp2_cls_flow_last_set(&fe, 1);
+	mvpp2_cls_flow_seq_set(&fe, MVPP2_CLS_FLOW_SEQ_LAST);
+
+	mvpp2_cls_flow_write(priv, &fe);
+}
+
+/* Adds a field to the Header Extracted Key generation parameters*/
+static int mvpp2_flow_add_hek_field(struct mvpp2_cls_flow_entry *fe,
+				    u32 field_id)
+{
+	int nb_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+	if (nb_fields == MVPP2_FLOW_N_FIELDS)
+		return -EINVAL;
+
+	mvpp2_cls_flow_hek_set(fe, nb_fields, field_id);
+
+	mvpp2_cls_flow_hek_num_set(fe, nb_fields + 1);
+
+	return 0;
+}
+
+static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
+				     unsigned long hash_opts)
+{
+	u32 field_id;
+	int i;
+
+	/* Clear old fields */
+	mvpp2_cls_flow_hek_num_set(fe, 0);
+	fe->data[2] = 0;
+
+	for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
+		switch (BIT(i)) {
+		case MVPP22_CLS_HEK_OPT_VLAN:
+			field_id = MVPP22_CLS_FIELD_VLAN;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4SA:
+			field_id = MVPP22_CLS_FIELD_IP4SA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4DA:
+			field_id = MVPP22_CLS_FIELD_IP4DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP6SA:
+			field_id = MVPP22_CLS_FIELD_IP6SA;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP6DA:
+			field_id = MVPP22_CLS_FIELD_IP6DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4SIP:
+			field_id = MVPP22_CLS_FIELD_L4SIP;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4DIP:
+			field_id = MVPP22_CLS_FIELD_L4DIP;
+			break;
+		default:
+			return -EINVAL;
+		}
+		if (mvpp2_flow_add_hek_field(fe, field_id))
+			return -EINVAL;
+	}
+
+	return 0;
 }
 
 struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
@@ -449,6 +565,104 @@ struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
 	return &cls_flows[flow];
 }
 
+/* Set the hash generation options for the given traffic flow.
+ * One traffic flow (in the ethtool sense) has multiple classification flows,
+ * to handle specific cases such as fragmentation, or the presence of a
+ * VLAN / DSA Tag.
+ *
+ * Each of these individual flows has different constraints, for example we
+ * can't hash fragmented packets on L4 data (else we would risk having packet
+ * re-ordering), so each classification flows masks the options with their
+ * supported ones.
+ *
+ */
+static int mvpp2_port_rss_hash_opts_set(struct mvpp2_port *port, int flow_type,
+					u16 requested_opts)
+{
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *flow;
+	int i, engine, flow_index;
+	u16 hash_opts;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			return -EINVAL;
+
+		if (flow->flow_type != flow_type)
+			continue;
+
+		flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
+							flow->flow_id);
+
+		mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+		hash_opts = flow->supported_hash_opts & requested_opts;
+
+		/* Use C3HB engine to access L4 infos. This adds L4 infos to the
+		 * hash parameters
+		 */
+		if (hash_opts & MVPP22_CLS_HEK_L4_OPTS)
+			engine = MVPP22_CLS_ENGINE_C3HB;
+		else
+			engine = MVPP22_CLS_ENGINE_C3HA;
+
+		if (mvpp2_flow_set_hek_fields(&fe, hash_opts))
+			return -EINVAL;
+
+		mvpp2_cls_flow_eng_set(&fe, engine);
+
+		mvpp2_cls_flow_write(port->priv, &fe);
+	}
+
+	return 0;
+}
+
+u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
+{
+	u16 hash_opts = 0;
+	int n_fields, i, field;
+
+	n_fields = mvpp2_cls_flow_hek_num_get(fe);
+
+	for (i = 0; i < n_fields; i++) {
+		field = mvpp2_cls_flow_hek_get(fe, i);
+
+		switch (field) {
+		case MVPP22_CLS_FIELD_MAC_DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
+			break;
+		case MVPP22_CLS_FIELD_VLAN:
+			hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
+			break;
+		case MVPP22_CLS_FIELD_L3_PROTO:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
+			break;
+		case MVPP22_CLS_FIELD_IP4SA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP4SA;
+			break;
+		case MVPP22_CLS_FIELD_IP4DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP4DA;
+			break;
+		case MVPP22_CLS_FIELD_IP6SA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP6SA;
+			break;
+		case MVPP22_CLS_FIELD_IP6DA:
+			hash_opts |= MVPP22_CLS_HEK_OPT_IP6DA;
+			break;
+		case MVPP22_CLS_FIELD_L4SIP:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
+			break;
+		case MVPP22_CLS_FIELD_L4DIP:
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
+			break;
+		default:
+			break;
+		}
+	}
+	return hash_opts;
+}
+
 static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
 {
 	struct mvpp2_cls_flow *flow;
@@ -485,6 +699,27 @@ static void mvpp2_cls_c2_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
 }
 
+static void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+			      struct mvpp2_cls_c2_entry *c2)
+{
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
+
+	c2->index = index;
+
+	c2->tcam[0] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA0);
+	c2->tcam[1] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA1);
+	c2->tcam[2] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA2);
+	c2->tcam[3] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA3);
+	c2->tcam[4] = mvpp2_read(priv, MVPP22_CLS_C2_TCAM_DATA4);
+
+	c2->act = mvpp2_read(priv, MVPP22_CLS_C2_ACT);
+
+	c2->attr[0] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR0);
+	c2->attr[1] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR1);
+	c2->attr[2] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR2);
+	c2->attr[3] = mvpp2_read(priv, MVPP22_CLS_C2_ATTR3);
+}
+
 static void mvpp2_port_c2_cls_init(struct mvpp2_port *port)
 {
 	struct mvpp2_cls_c2_entry c2;
@@ -580,6 +815,38 @@ void mvpp2_cls_port_config(struct mvpp2_port *port)
 	mvpp2_port_c2_cls_init(port);
 }
 
+static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	c2.attr[2] |= MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+static void mvpp2_rss_port_c2_disable(struct mvpp2_port *port)
+{
+	struct mvpp2_cls_c2_entry c2;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	c2.attr[2] &= ~MVPP22_CLS_C2_ATTR2_RSS_EN;
+
+	mvpp2_cls_c2_write(port->priv, &c2);
+}
+
+void mvpp22_rss_enable(struct mvpp2_port *port)
+{
+	mvpp2_rss_port_c2_enable(port);
+}
+
+void mvpp22_rss_disable(struct mvpp2_port *port)
+{
+	mvpp2_rss_port_c2_disable(port);
+}
+
 /* Set CPU queue number for oversize packets */
 void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port)
 {
@@ -656,4 +923,12 @@ void mvpp22_rss_port_init(struct mvpp2_port *port)
 		port->indir[i] = ethtool_rxfh_indir_default(i, port->nrxqs);
 
 	mvpp22_rss_fill_table(port, port->id);
+
+	/* Configure default flows */
+	mvpp2_port_rss_hash_opts_set(port, IPV4_FLOW, MVPP22_CLS_HEK_IP4_2T);
+	mvpp2_port_rss_hash_opts_set(port, IPV6_FLOW, MVPP22_CLS_HEK_IP6_2T);
+	mvpp2_port_rss_hash_opts_set(port, TCP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, TCP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
+	mvpp2_port_rss_hash_opts_set(port, UDP_V4_FLOW, MVPP22_CLS_HEK_IP4_5T);
+	mvpp2_port_rss_hash_opts_set(port, UDP_V6_FLOW, MVPP22_CLS_HEK_IP6_5T);
 }
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 747c5f055b82..21bd0249be0d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -62,6 +62,18 @@ enum mvpp2_cls_engine {
 #define MVPP22_CLS_HEK_IP6_5T	(MVPP22_CLS_HEK_IP6_2T | \
 				 MVPP22_CLS_HEK_L4_OPTS)
 
+enum mvpp2_cls_field_id {
+	MVPP22_CLS_FIELD_MAC_DA = 0x03,
+	MVPP22_CLS_FIELD_VLAN = 0x06,
+	MVPP22_CLS_FIELD_L3_PROTO = 0x0f,
+	MVPP22_CLS_FIELD_IP4SA = 0x10,
+	MVPP22_CLS_FIELD_IP4DA = 0x11,
+	MVPP22_CLS_FIELD_IP6SA = 0x17,
+	MVPP22_CLS_FIELD_IP6DA = 0x1a,
+	MVPP22_CLS_FIELD_L4SIP = 0x1d,
+	MVPP22_CLS_FIELD_L4DIP = 0x1e,
+};
+
 enum mvpp2_cls_flow_seq {
 	MVPP2_CLS_FLOW_SEQ_NORMAL = 0,
 	MVPP2_CLS_FLOW_SEQ_FIRST1,
@@ -188,6 +200,9 @@ void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table);
 
 void mvpp22_rss_port_init(struct mvpp2_port *port);
 
+void mvpp22_rss_enable(struct mvpp2_port *port);
+void mvpp22_rss_disable(struct mvpp2_port *port);
+
 void mvpp2_cls_init(struct mvpp2 *priv);
 
 void mvpp2_cls_port_config(struct mvpp2_port *port);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 93e37d20899d..61e2d6886a4b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3631,6 +3631,13 @@ static int mvpp2_set_features(struct net_device *dev,
 		}
 	}
 
+	if (changed & NETIF_F_RXHASH) {
+		if (features & NETIF_F_RXHASH)
+			mvpp22_rss_enable(port);
+		else
+			mvpp22_rss_disable(port);
+	}
+
 	return 0;
 }
 
@@ -4759,6 +4766,9 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->hw_features |= features | NETIF_F_RXCSUM | NETIF_F_GRO |
 			    NETIF_F_HW_VLAN_CTAG_FILTER;
 
+	if (mvpp22_rss_is_supported())
+		dev->hw_features |= NETIF_F_RXHASH;
+
 	if (port->pool_long->id == MVPP2_BM_JUMBO && port->id != 0) {
 		dev->features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
 		dev->hw_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM);
-- 
cgit v1.2.3


From 436d4fdb208f25e17da854bcf58aab5716a483f1 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 12 Jul 2018 13:54:27 +0200
Subject: net: mvpp2: allow setting RSS flow hash parameters with ethtool

This commit allows setting the RSS hash generation parameters from
ethtool. When setting parameters for a given flow type from ethtool
(e.g. tcp4), all the corresponding flows in the flow table are updated,
according to the supported hash parameters.

For example, when configuring TCP over IPv4 hash parameters to be
src/dst IP  + src/dst port ("ethtool -N eth0 rx-flow-hash tcp4 sdfn"),
we only set the "src/dst port" hash parameters on the non-fragmented TCP
over IPv4 flows.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c  | 104 ++++++++++++++++++++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h  |   3 +
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c |  26 +++++-
 3 files changed, 132 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 98e0e25f7dca..dc7dfa9a6606 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -663,6 +663,35 @@ u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe)
 	return hash_opts;
 }
 
+/* Returns the hash opts for this flow. There are several classifier flows
+ * for one traffic flow, this returns an aggregation of all configurations.
+ */
+static u16 mvpp2_port_rss_hash_opts_get(struct mvpp2_port *port, int flow_type)
+{
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *flow;
+	int i, flow_index;
+	u16 hash_opts = 0;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		flow = mvpp2_cls_flow_get(i);
+		if (!flow)
+			return 0;
+
+		if (flow->flow_type != flow_type)
+			continue;
+
+		flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(port->id,
+							flow->flow_id);
+
+		mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+		hash_opts |= mvpp2_flow_get_hek_fields(&fe);
+	}
+
+	return hash_opts;
+}
+
 static void mvpp2_cls_port_init_flows(struct mvpp2 *priv)
 {
 	struct mvpp2_cls_flow *flow;
@@ -897,6 +926,81 @@ void mvpp22_rss_fill_table(struct mvpp2_port *port, u32 table)
 	}
 }
 
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+{
+	u16 hash_opts = 0;
+
+	switch (info->flow_type) {
+	case TCP_V4_FLOW:
+	case UDP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		if (info->data & RXH_L4_B_0_1)
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4SIP;
+		if (info->data & RXH_L4_B_2_3)
+			hash_opts |= MVPP22_CLS_HEK_OPT_L4DIP;
+		/* Fallthrough */
+	case IPV4_FLOW:
+	case IPV6_FLOW:
+		if (info->data & RXH_L2DA)
+			hash_opts |= MVPP22_CLS_HEK_OPT_MAC_DA;
+		if (info->data & RXH_VLAN)
+			hash_opts |= MVPP22_CLS_HEK_OPT_VLAN;
+		if (info->data & RXH_L3_PROTO)
+			hash_opts |= MVPP22_CLS_HEK_OPT_L3_PROTO;
+		if (info->data & RXH_IP_SRC)
+			hash_opts |= (MVPP22_CLS_HEK_OPT_IP4SA |
+				     MVPP22_CLS_HEK_OPT_IP6SA);
+		if (info->data & RXH_IP_DST)
+			hash_opts |= (MVPP22_CLS_HEK_OPT_IP4DA |
+				     MVPP22_CLS_HEK_OPT_IP6DA);
+		break;
+	default: return -EOPNOTSUPP;
+	}
+
+	return mvpp2_port_rss_hash_opts_set(port, info->flow_type, hash_opts);
+}
+
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info)
+{
+	unsigned long hash_opts;
+	int i;
+
+	hash_opts = mvpp2_port_rss_hash_opts_get(port, info->flow_type);
+	info->data = 0;
+
+	for_each_set_bit(i, &hash_opts, MVPP22_CLS_HEK_N_FIELDS) {
+		switch (BIT(i)) {
+		case MVPP22_CLS_HEK_OPT_MAC_DA:
+			info->data |= RXH_L2DA;
+			break;
+		case MVPP22_CLS_HEK_OPT_VLAN:
+			info->data |= RXH_VLAN;
+			break;
+		case MVPP22_CLS_HEK_OPT_L3_PROTO:
+			info->data |= RXH_L3_PROTO;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4SA:
+		case MVPP22_CLS_HEK_OPT_IP6SA:
+			info->data |= RXH_IP_SRC;
+			break;
+		case MVPP22_CLS_HEK_OPT_IP4DA:
+		case MVPP22_CLS_HEK_OPT_IP6DA:
+			info->data |= RXH_IP_DST;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4SIP:
+			info->data |= RXH_L4_B_0_1;
+			break;
+		case MVPP22_CLS_HEK_OPT_L4DIP:
+			info->data |= RXH_L4_B_2_3;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
 void mvpp22_rss_port_init(struct mvpp2_port *port)
 {
 	struct mvpp2 *priv = port->priv;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 21bd0249be0d..151d791a91b6 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -203,6 +203,9 @@ void mvpp22_rss_port_init(struct mvpp2_port *port);
 void mvpp22_rss_enable(struct mvpp2_port *port);
 void mvpp22_rss_disable(struct mvpp2_port *port);
 
+int mvpp2_ethtool_rxfh_get(struct mvpp2_port *port, struct ethtool_rxnfc *info);
+int mvpp2_ethtool_rxfh_set(struct mvpp2_port *port, struct ethtool_rxnfc *info);
+
 void mvpp2_cls_init(struct mvpp2 *priv);
 
 void mvpp2_cls_port_config(struct mvpp2_port *port);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 61e2d6886a4b..2283be12d700 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3829,11 +3829,15 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 				   struct ethtool_rxnfc *info, u32 *rules)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
 
 	if (!mvpp22_rss_is_supported())
 		return -EOPNOTSUPP;
 
 	switch (info->cmd) {
+	case ETHTOOL_GRXFH:
+		ret = mvpp2_ethtool_rxfh_get(port, info);
+		break;
 	case ETHTOOL_GRXRINGS:
 		info->data = port->nrxqs;
 		break;
@@ -3841,7 +3845,26 @@ static int mvpp2_ethtool_get_rxnfc(struct net_device *dev,
 		return -ENOTSUPP;
 	}
 
-	return 0;
+	return ret;
+}
+
+static int mvpp2_ethtool_set_rxnfc(struct net_device *dev,
+				   struct ethtool_rxnfc *info)
+{
+	struct mvpp2_port *port = netdev_priv(dev);
+	int ret = 0;
+
+	if (!mvpp22_rss_is_supported())
+		return -EOPNOTSUPP;
+
+	switch (info->cmd) {
+	case ETHTOOL_SRXFH:
+		ret = mvpp2_ethtool_rxfh_set(port, info);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	return ret;
 }
 
 static u32 mvpp2_ethtool_get_rxfh_indir_size(struct net_device *dev)
@@ -3922,6 +3945,7 @@ static const struct ethtool_ops mvpp2_eth_tool_ops = {
 	.get_link_ksettings	= mvpp2_ethtool_get_link_ksettings,
 	.set_link_ksettings	= mvpp2_ethtool_set_link_ksettings,
 	.get_rxnfc		= mvpp2_ethtool_get_rxnfc,
+	.set_rxnfc		= mvpp2_ethtool_set_rxnfc,
 	.get_rxfh_indir_size	= mvpp2_ethtool_get_rxfh_indir_size,
 	.get_rxfh		= mvpp2_ethtool_get_rxfh,
 	.set_rxfh		= mvpp2_ethtool_set_rxfh,
-- 
cgit v1.2.3


From b16ebe925a4400a2ec3dc663c81dce2fd9bf0998 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:08 +0300
Subject: devlink: Add support for creating and destroying regions

This allows a device to register its supported address regions.
Each address region can be accessed directly for example reading
the snapshots taken of this address space.
Drivers are not limited in the name selection for different regions.
An example of a region-name can be: pci cr-space, register-space.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 22 ++++++++++++++
 net/core/devlink.c    | 84 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 106 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index f67c29cede15..e5397652f2fb 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -28,6 +28,7 @@ struct devlink {
 	struct list_head dpipe_table_list;
 	struct list_head resource_list;
 	struct list_head param_list;
+	struct list_head region_list;
 	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
@@ -397,6 +398,8 @@ enum devlink_param_generic_id {
 	.validate = _validate,						\
 }
 
+struct devlink_region;
+
 struct devlink_ops {
 	int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
@@ -543,6 +546,11 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id,
 int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id,
 				       union devlink_param_value init_val);
 void devlink_param_value_changed(struct devlink *devlink, u32 param_id);
+struct devlink_region *devlink_region_create(struct devlink *devlink,
+					     const char *region_name,
+					     u32 region_max_snapshots,
+					     u64 region_size);
+void devlink_region_destroy(struct devlink_region *region);
 
 #else
 
@@ -770,6 +778,20 @@ devlink_param_value_changed(struct devlink *devlink, u32 param_id)
 {
 }
 
+static inline struct devlink_region *
+devlink_region_create(struct devlink *devlink,
+		      const char *region_name,
+		      u32 region_max_snapshots,
+		      u64 region_size)
+{
+	return NULL;
+}
+
+static inline void
+devlink_region_destroy(struct devlink_region *region)
+{
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 470f3dbfecfe..cac856136ac6 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -326,6 +326,28 @@ devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb,
 						  pool_type, p_tc_index);
 }
 
+struct devlink_region {
+	struct devlink *devlink;
+	struct list_head list;
+	const char *name;
+	struct list_head snapshot_list;
+	u32 max_snapshots;
+	u32 cur_snapshots;
+	u64 size;
+};
+
+static struct devlink_region *
+devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
+{
+	struct devlink_region *region;
+
+	list_for_each_entry(region, &devlink->region_list, list)
+		if (!strcmp(region->name, region_name))
+			return region;
+
+	return NULL;
+}
+
 #define DEVLINK_NL_FLAG_NEED_DEVLINK	BIT(0)
 #define DEVLINK_NL_FLAG_NEED_PORT	BIT(1)
 #define DEVLINK_NL_FLAG_NEED_SB		BIT(2)
@@ -3358,6 +3380,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size)
 	INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list);
 	INIT_LIST_HEAD(&devlink->resource_list);
 	INIT_LIST_HEAD(&devlink->param_list);
+	INIT_LIST_HEAD(&devlink->region_list);
 	mutex_init(&devlink->lock);
 	return devlink;
 }
@@ -4109,6 +4132,67 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id)
 }
 EXPORT_SYMBOL_GPL(devlink_param_value_changed);
 
+/**
+ *	devlink_region_create - create a new address region
+ *
+ *	@devlink: devlink
+ *	@region_name: region name
+ *	@region_max_snapshots: Maximum supported number of snapshots for region
+ *	@region_size: size of region
+ */
+struct devlink_region *devlink_region_create(struct devlink *devlink,
+					     const char *region_name,
+					     u32 region_max_snapshots,
+					     u64 region_size)
+{
+	struct devlink_region *region;
+	int err = 0;
+
+	mutex_lock(&devlink->lock);
+
+	if (devlink_region_get_by_name(devlink, region_name)) {
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	region = kzalloc(sizeof(*region), GFP_KERNEL);
+	if (!region) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	region->devlink = devlink;
+	region->max_snapshots = region_max_snapshots;
+	region->name = region_name;
+	region->size = region_size;
+	INIT_LIST_HEAD(&region->snapshot_list);
+	list_add_tail(&region->list, &devlink->region_list);
+
+	mutex_unlock(&devlink->lock);
+	return region;
+
+unlock:
+	mutex_unlock(&devlink->lock);
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(devlink_region_create);
+
+/**
+ *	devlink_region_destroy - destroy address region
+ *
+ *	@region: devlink region to destroy
+ */
+void devlink_region_destroy(struct devlink_region *region)
+{
+	struct devlink *devlink = region->devlink;
+
+	mutex_lock(&devlink->lock);
+	list_del(&region->list);
+	mutex_unlock(&devlink->lock);
+	kfree(region);
+}
+EXPORT_SYMBOL_GPL(devlink_region_destroy);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From ccadfa444b34c6ec7bb458eee17fdd8c9a456c63 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:09 +0300
Subject: devlink: Add callback to query for snapshot id before snapshot create

To restrict the driver with the snapshot ID selection a new callback
is introduced for the driver to get the snapshot ID before creating
a new snapshot. This will also allow giving the same ID for multiple
snapshots taken of different regions on the same time.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h |  8 ++++++++
 net/core/devlink.c    | 21 +++++++++++++++++++++
 2 files changed, 29 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index e5397652f2fb..f27d8593687a 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -29,6 +29,7 @@ struct devlink {
 	struct list_head resource_list;
 	struct list_head param_list;
 	struct list_head region_list;
+	u32 snapshot_id;
 	struct devlink_dpipe_headers *dpipe_headers;
 	const struct devlink_ops *ops;
 	struct device *dev;
@@ -551,6 +552,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink,
 					     u32 region_max_snapshots,
 					     u64 region_size);
 void devlink_region_destroy(struct devlink_region *region);
+u32 devlink_region_shapshot_id_get(struct devlink *devlink);
 
 #else
 
@@ -792,6 +794,12 @@ devlink_region_destroy(struct devlink_region *region)
 {
 }
 
+static inline u32
+devlink_region_shapshot_id_get(struct devlink *devlink)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index cac856136ac6..6c92ddd2465d 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -4193,6 +4193,27 @@ void devlink_region_destroy(struct devlink_region *region)
 }
 EXPORT_SYMBOL_GPL(devlink_region_destroy);
 
+/**
+ *	devlink_region_shapshot_id_get - get snapshot ID
+ *
+ *	This callback should be called when adding a new snapshot,
+ *	Driver should use the same id for multiple snapshots taken
+ *	on multiple regions at the same time/by the same trigger.
+ *
+ *	@devlink: devlink
+ */
+u32 devlink_region_shapshot_id_get(struct devlink *devlink)
+{
+	u32 id;
+
+	mutex_lock(&devlink->lock);
+	id = ++devlink->snapshot_id;
+	mutex_unlock(&devlink->lock);
+
+	return id;
+}
+EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From d7e5272282d93bedbbeb6174b8af8425d7dcfd6f Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:10 +0300
Subject: devlink: Add support for creating region snapshots

Each device address region can store multiple snapshots,
each snapshot is identified using a different numerical ID.
This ID is used when deleting a snapshot or showing an address
region specific snapshot. This patch exposes a callback to add
a new snapshot to an address region.
The snapshot will be deleted using the destructor function
when destroying a region or when a snapshot delete command
from devlink user tool.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 13 +++++++
 net/core/devlink.c    | 95 +++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 108 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index f27d8593687a..905f0bb7b4ba 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -401,6 +401,8 @@ enum devlink_param_generic_id {
 
 struct devlink_region;
 
+typedef void devlink_snapshot_data_dest_t(const void *data);
+
 struct devlink_ops {
 	int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack);
 	int (*port_type_set)(struct devlink_port *devlink_port,
@@ -553,6 +555,9 @@ struct devlink_region *devlink_region_create(struct devlink *devlink,
 					     u64 region_size);
 void devlink_region_destroy(struct devlink_region *region);
 u32 devlink_region_shapshot_id_get(struct devlink *devlink);
+int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+				   u8 *data, u32 snapshot_id,
+				   devlink_snapshot_data_dest_t *data_destructor);
 
 #else
 
@@ -800,6 +805,14 @@ devlink_region_shapshot_id_get(struct devlink *devlink)
 	return 0;
 }
 
+static inline int
+devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+			       u8 *data, u32 snapshot_id,
+			       devlink_snapshot_data_dest_t *data_destructor)
+{
+	return 0;
+}
+
 #endif
 
 #endif /* _NET_DEVLINK_H_ */
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 6c92ddd2465d..7d09fe60fa4b 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -336,6 +336,15 @@ struct devlink_region {
 	u64 size;
 };
 
+struct devlink_snapshot {
+	struct list_head list;
+	struct devlink_region *region;
+	devlink_snapshot_data_dest_t *data_destructor;
+	u64 data_len;
+	u8 *data;
+	u32 id;
+};
+
 static struct devlink_region *
 devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
 {
@@ -348,6 +357,26 @@ devlink_region_get_by_name(struct devlink *devlink, const char *region_name)
 	return NULL;
 }
 
+static struct devlink_snapshot *
+devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id)
+{
+	struct devlink_snapshot *snapshot;
+
+	list_for_each_entry(snapshot, &region->snapshot_list, list)
+		if (snapshot->id == id)
+			return snapshot;
+
+	return NULL;
+}
+
+static void devlink_region_snapshot_del(struct devlink_snapshot *snapshot)
+{
+	snapshot->region->cur_snapshots--;
+	list_del(&snapshot->list);
+	(*snapshot->data_destructor)(snapshot->data);
+	kfree(snapshot);
+}
+
 #define DEVLINK_NL_FLAG_NEED_DEVLINK	BIT(0)
 #define DEVLINK_NL_FLAG_NEED_PORT	BIT(1)
 #define DEVLINK_NL_FLAG_NEED_SB		BIT(2)
@@ -4185,8 +4214,14 @@ EXPORT_SYMBOL_GPL(devlink_region_create);
 void devlink_region_destroy(struct devlink_region *region)
 {
 	struct devlink *devlink = region->devlink;
+	struct devlink_snapshot *snapshot, *ts;
 
 	mutex_lock(&devlink->lock);
+
+	/* Free all snapshots of region */
+	list_for_each_entry_safe(snapshot, ts, &region->snapshot_list, list)
+		devlink_region_snapshot_del(snapshot);
+
 	list_del(&region->list);
 	mutex_unlock(&devlink->lock);
 	kfree(region);
@@ -4214,6 +4249,66 @@ u32 devlink_region_shapshot_id_get(struct devlink *devlink)
 }
 EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get);
 
+/**
+ *	devlink_region_snapshot_create - create a new snapshot
+ *	This will add a new snapshot of a region. The snapshot
+ *	will be stored on the region struct and can be accessed
+ *	from devlink. This is useful for future	analyses of snapshots.
+ *	Multiple snapshots can be created on a region.
+ *	The @snapshot_id should be obtained using the getter function.
+ *
+ *	@devlink_region: devlink region of the snapshot
+ *	@data_len: size of snapshot data
+ *	@data: snapshot data
+ *	@snapshot_id: snapshot id to be created
+ *	@data_destructor: pointer to destructor function to free data
+ */
+int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
+				   u8 *data, u32 snapshot_id,
+				   devlink_snapshot_data_dest_t *data_destructor)
+{
+	struct devlink *devlink = region->devlink;
+	struct devlink_snapshot *snapshot;
+	int err;
+
+	mutex_lock(&devlink->lock);
+
+	/* check if region can hold one more snapshot */
+	if (region->cur_snapshots == region->max_snapshots) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	if (devlink_region_snapshot_get_by_id(region, snapshot_id)) {
+		err = -EEXIST;
+		goto unlock;
+	}
+
+	snapshot = kzalloc(sizeof(*snapshot), GFP_KERNEL);
+	if (!snapshot) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	snapshot->id = snapshot_id;
+	snapshot->region = region;
+	snapshot->data = data;
+	snapshot->data_len = data_len;
+	snapshot->data_destructor = data_destructor;
+
+	list_add_tail(&snapshot->list, &region->snapshot_list);
+
+	region->cur_snapshots++;
+
+	mutex_unlock(&devlink->lock);
+	return 0;
+
+unlock:
+	mutex_unlock(&devlink->lock);
+	return err;
+}
+EXPORT_SYMBOL_GPL(devlink_region_snapshot_create);
+
 static int __init devlink_module_init(void)
 {
 	return genl_register_family(&devlink_nl_family);
-- 
cgit v1.2.3


From d8db7ea55f2ff5890ad31137233a3808d80c7f62 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:11 +0300
Subject: devlink: Add support for region get command

Add support for DEVLINK_CMD_REGION_GET command which is used for
querying for the supported DEV/REGION values of devlink devices.
The support is both for doit and dumpit.

Reply includes:
  BUS_NAME, DEVICE_NAME, REGION_NAME, REGION_SIZE

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h |   6 +++
 net/core/devlink.c           | 114 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 120 insertions(+)

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 68641fb56654..28bfa8aa3d91 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -83,6 +83,9 @@ enum devlink_command {
 	DEVLINK_CMD_PARAM_NEW,
 	DEVLINK_CMD_PARAM_DEL,
 
+	DEVLINK_CMD_REGION_GET,
+	DEVLINK_CMD_REGION_SET,
+
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
 	DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1
@@ -262,6 +265,9 @@ enum devlink_attr {
 	DEVLINK_ATTR_PARAM_VALUE_DATA,		/* dynamic */
 	DEVLINK_ATTR_PARAM_VALUE_CMODE,		/* u8 */
 
+	DEVLINK_ATTR_REGION_NAME,               /* string */
+	DEVLINK_ATTR_REGION_SIZE,               /* u64 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 7d09fe60fa4b..221ddb6bae48 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3149,6 +3149,111 @@ static void devlink_param_unregister_one(struct devlink *devlink,
 	kfree(param_item);
 }
 
+static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
+				  enum devlink_command cmd, u32 portid,
+				  u32 seq, int flags,
+				  struct devlink_region *region)
+{
+	void *hdr;
+	int err;
+
+	hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	err = devlink_nl_put_handle(msg, devlink);
+	if (err)
+		goto nla_put_failure;
+
+	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->name);
+	if (err)
+		goto nla_put_failure;
+
+	err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+				region->size,
+				DEVLINK_ATTR_PAD);
+	if (err)
+		goto nla_put_failure;
+
+	genlmsg_end(msg, hdr);
+	return 0;
+
+nla_put_failure:
+	genlmsg_cancel(msg, hdr);
+	return err;
+}
+
+static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
+					  struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_region *region;
+	const char *region_name;
+	struct sk_buff *msg;
+	int err;
+
+	if (!info->attrs[DEVLINK_ATTR_REGION_NAME])
+		return -EINVAL;
+
+	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+	region = devlink_region_get_by_name(devlink, region_name);
+	if (!region)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	err = devlink_nl_region_fill(msg, devlink, DEVLINK_CMD_REGION_GET,
+				     info->snd_portid, info->snd_seq, 0,
+				     region);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	return genlmsg_reply(msg, info);
+}
+
+static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg,
+					    struct netlink_callback *cb)
+{
+	struct devlink_region *region;
+	struct devlink *devlink;
+	int start = cb->args[0];
+	int idx = 0;
+	int err;
+
+	mutex_lock(&devlink_mutex);
+	list_for_each_entry(devlink, &devlink_list, list) {
+		if (!net_eq(devlink_net(devlink), sock_net(msg->sk)))
+			continue;
+
+		mutex_lock(&devlink->lock);
+		list_for_each_entry(region, &devlink->region_list, list) {
+			if (idx < start) {
+				idx++;
+				continue;
+			}
+			err = devlink_nl_region_fill(msg, devlink,
+						     DEVLINK_CMD_REGION_GET,
+						     NETLINK_CB(cb->skb).portid,
+						     cb->nlh->nlmsg_seq,
+						     NLM_F_MULTI, region);
+			if (err) {
+				mutex_unlock(&devlink->lock);
+				goto out;
+			}
+			idx++;
+		}
+		mutex_unlock(&devlink->lock);
+	}
+out:
+	mutex_unlock(&devlink_mutex);
+	cb->args[0] = idx;
+	return msg->len;
+}
+
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -3172,6 +3277,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PARAM_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
+	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -3370,6 +3476,14 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
+	{
+		.cmd = DEVLINK_CMD_REGION_GET,
+		.doit = devlink_nl_cmd_region_get_doit,
+		.dumpit = devlink_nl_cmd_region_get_dumpit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
-- 
cgit v1.2.3


From a006d467fbf1d405e73cd167829d7a9e3df600e3 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:12 +0300
Subject: devlink: Extend the support querying for region snapshot IDs

Extend the support for DEVLINK_CMD_REGION_GET command to also
return the IDs of the snapshot currently present on the region.
Each reply will include a nested snapshots attribute that
can contain multiple snapshot attributes each with an ID.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h |  3 +++
 net/core/devlink.c           | 53 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 56 insertions(+)

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 28bfa8aa3d91..abde4e306375 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -267,6 +267,9 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_REGION_NAME,               /* string */
 	DEVLINK_ATTR_REGION_SIZE,               /* u64 */
+	DEVLINK_ATTR_REGION_SNAPSHOTS,          /* nested */
+	DEVLINK_ATTR_REGION_SNAPSHOT,           /* nested */
+	DEVLINK_ATTR_REGION_SNAPSHOT_ID,        /* u32 */
 
 	/* add new attributes above here, update the policy in devlink.c */
 
diff --git a/net/core/devlink.c b/net/core/devlink.c
index 221ddb6bae48..cb75e26d70ff 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3149,6 +3149,55 @@ static void devlink_param_unregister_one(struct devlink *devlink,
 	kfree(param_item);
 }
 
+static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg,
+					     struct devlink *devlink,
+					     struct devlink_snapshot *snapshot)
+{
+	struct nlattr *snap_attr;
+	int err;
+
+	snap_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOT);
+	if (!snap_attr)
+		return -EINVAL;
+
+	err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID, snapshot->id);
+	if (err)
+		goto nla_put_failure;
+
+	nla_nest_end(msg, snap_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, snap_attr);
+	return err;
+}
+
+static int devlink_nl_region_snapshots_id_put(struct sk_buff *msg,
+					      struct devlink *devlink,
+					      struct devlink_region *region)
+{
+	struct devlink_snapshot *snapshot;
+	struct nlattr *snapshots_attr;
+	int err;
+
+	snapshots_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_SNAPSHOTS);
+	if (!snapshots_attr)
+		return -EINVAL;
+
+	list_for_each_entry(snapshot, &region->snapshot_list, list) {
+		err = devlink_nl_region_snapshot_id_put(msg, devlink, snapshot);
+		if (err)
+			goto nla_put_failure;
+	}
+
+	nla_nest_end(msg, snapshots_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, snapshots_attr);
+	return err;
+}
+
 static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
 				  enum devlink_command cmd, u32 portid,
 				  u32 seq, int flags,
@@ -3175,6 +3224,10 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink,
 	if (err)
 		goto nla_put_failure;
 
+	err = devlink_nl_region_snapshots_id_put(msg, devlink, region);
+	if (err)
+		goto nla_put_failure;
+
 	genlmsg_end(msg, hdr);
 	return 0;
 
-- 
cgit v1.2.3


From 866319bb9437614407ca36f8b16f89ab77a6a831 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:13 +0300
Subject: devlink: Add support for region snapshot delete command

Add support for DEVLINK_CMD_REGION_DEL used
for deleting a snapshot from a region. The snapshot ID is required.
Also added notification support for NEW and DEL of snapshots.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h |  2 +
 net/core/devlink.c           | 93 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 95 insertions(+)

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index abde4e306375..d212e02f843f 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -85,6 +85,8 @@ enum devlink_command {
 
 	DEVLINK_CMD_REGION_GET,
 	DEVLINK_CMD_REGION_SET,
+	DEVLINK_CMD_REGION_NEW,
+	DEVLINK_CMD_REGION_DEL,
 
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index cb75e26d70ff..fc0836371a71 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3236,6 +3236,58 @@ nla_put_failure:
 	return err;
 }
 
+static void devlink_nl_region_notify(struct devlink_region *region,
+				     struct devlink_snapshot *snapshot,
+				     enum devlink_command cmd)
+{
+	struct devlink *devlink = region->devlink;
+	struct sk_buff *msg;
+	void *hdr;
+	int err;
+
+	WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return;
+
+	hdr = genlmsg_put(msg, 0, 0, &devlink_nl_family, 0, cmd);
+	if (!hdr)
+		goto out_free_msg;
+
+	err = devlink_nl_put_handle(msg, devlink);
+	if (err)
+		goto out_cancel_msg;
+
+	err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME,
+			     region->name);
+	if (err)
+		goto out_cancel_msg;
+
+	if (snapshot) {
+		err = nla_put_u32(msg, DEVLINK_ATTR_REGION_SNAPSHOT_ID,
+				  snapshot->id);
+		if (err)
+			goto out_cancel_msg;
+	} else {
+		err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_SIZE,
+					region->size, DEVLINK_ATTR_PAD);
+		if (err)
+			goto out_cancel_msg;
+	}
+	genlmsg_end(msg, hdr);
+
+	genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink),
+				msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL);
+
+	return;
+
+out_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+out_free_msg:
+	nlmsg_free(msg);
+}
+
 static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb,
 					  struct genl_info *info)
 {
@@ -3307,6 +3359,35 @@ out:
 	return msg->len;
 }
 
+static int devlink_nl_cmd_region_del(struct sk_buff *skb,
+				     struct genl_info *info)
+{
+	struct devlink *devlink = info->user_ptr[0];
+	struct devlink_snapshot *snapshot;
+	struct devlink_region *region;
+	const char *region_name;
+	u32 snapshot_id;
+
+	if (!info->attrs[DEVLINK_ATTR_REGION_NAME] ||
+	    !info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID])
+		return -EINVAL;
+
+	region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]);
+	snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+
+	region = devlink_region_get_by_name(devlink, region_name);
+	if (!region)
+		return -EINVAL;
+
+	snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+	if (!snapshot)
+		return -EINVAL;
+
+	devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_DEL);
+	devlink_region_snapshot_del(snapshot);
+	return 0;
+}
+
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -3331,6 +3412,7 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_PARAM_TYPE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 },
 	[DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING },
+	[DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 },
 };
 
 static const struct genl_ops devlink_nl_ops[] = {
@@ -3537,6 +3619,13 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
+	{
+		.cmd = DEVLINK_CMD_REGION_DEL,
+		.doit = devlink_nl_cmd_region_del,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
@@ -4363,6 +4452,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink,
 	region->size = region_size;
 	INIT_LIST_HEAD(&region->snapshot_list);
 	list_add_tail(&region->list, &devlink->region_list);
+	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW);
 
 	mutex_unlock(&devlink->lock);
 	return region;
@@ -4390,6 +4480,8 @@ void devlink_region_destroy(struct devlink_region *region)
 		devlink_region_snapshot_del(snapshot);
 
 	list_del(&region->list);
+
+	devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL);
 	mutex_unlock(&devlink->lock);
 	kfree(region);
 }
@@ -4467,6 +4559,7 @@ int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len,
 
 	region->cur_snapshots++;
 
+	devlink_nl_region_notify(region, snapshot, DEVLINK_CMD_REGION_NEW);
 	mutex_unlock(&devlink->lock);
 	return 0;
 
-- 
cgit v1.2.3


From 4e54795a27f56102649f121a34b8445e42f79ccd Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:14 +0300
Subject: devlink: Add support for region snapshot read command

Add support for DEVLINK_CMD_REGION_READ_GET used for both reading
and dumping region data. Read allows reading from a region specific
address for given length. Dump allows reading the full region.
If only snapshot ID is provided a snapshot dump will be done.
If snapshot ID, Address and Length are provided a snapshot read
will done.

This is used for both snapshot access and will be used in the same
way to access current data on the region.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/devlink.h |   7 ++
 net/core/devlink.c           | 182 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 189 insertions(+)

diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index d212e02f843f..79407bbd296d 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -87,6 +87,7 @@ enum devlink_command {
 	DEVLINK_CMD_REGION_SET,
 	DEVLINK_CMD_REGION_NEW,
 	DEVLINK_CMD_REGION_DEL,
+	DEVLINK_CMD_REGION_READ,
 
 	/* add new commands above here */
 	__DEVLINK_CMD_MAX,
@@ -273,6 +274,12 @@ enum devlink_attr {
 	DEVLINK_ATTR_REGION_SNAPSHOT,           /* nested */
 	DEVLINK_ATTR_REGION_SNAPSHOT_ID,        /* u32 */
 
+	DEVLINK_ATTR_REGION_CHUNKS,             /* nested */
+	DEVLINK_ATTR_REGION_CHUNK,              /* nested */
+	DEVLINK_ATTR_REGION_CHUNK_DATA,         /* binary */
+	DEVLINK_ATTR_REGION_CHUNK_ADDR,         /* u64 */
+	DEVLINK_ATTR_REGION_CHUNK_LEN,          /* u64 */
+
 	/* add new attributes above here, update the policy in devlink.c */
 
 	__DEVLINK_ATTR_MAX,
diff --git a/net/core/devlink.c b/net/core/devlink.c
index fc0836371a71..e5118dba6bb4 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -3388,6 +3388,181 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb,
 	return 0;
 }
 
+static int devlink_nl_cmd_region_read_chunk_fill(struct sk_buff *msg,
+						 struct devlink *devlink,
+						 u8 *chunk, u32 chunk_size,
+						 u64 addr)
+{
+	struct nlattr *chunk_attr;
+	int err;
+
+	chunk_attr = nla_nest_start(msg, DEVLINK_ATTR_REGION_CHUNK);
+	if (!chunk_attr)
+		return -EINVAL;
+
+	err = nla_put(msg, DEVLINK_ATTR_REGION_CHUNK_DATA, chunk_size, chunk);
+	if (err)
+		goto nla_put_failure;
+
+	err = nla_put_u64_64bit(msg, DEVLINK_ATTR_REGION_CHUNK_ADDR, addr,
+				DEVLINK_ATTR_PAD);
+	if (err)
+		goto nla_put_failure;
+
+	nla_nest_end(msg, chunk_attr);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(msg, chunk_attr);
+	return err;
+}
+
+#define DEVLINK_REGION_READ_CHUNK_SIZE 256
+
+static int devlink_nl_region_read_snapshot_fill(struct sk_buff *skb,
+						struct devlink *devlink,
+						struct devlink_region *region,
+						struct nlattr **attrs,
+						u64 start_offset,
+						u64 end_offset,
+						bool dump,
+						u64 *new_offset)
+{
+	struct devlink_snapshot *snapshot;
+	u64 curr_offset = start_offset;
+	u32 snapshot_id;
+	int err = 0;
+
+	*new_offset = start_offset;
+
+	snapshot_id = nla_get_u32(attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]);
+	snapshot = devlink_region_snapshot_get_by_id(region, snapshot_id);
+	if (!snapshot)
+		return -EINVAL;
+
+	if (end_offset > snapshot->data_len || dump)
+		end_offset = snapshot->data_len;
+
+	while (curr_offset < end_offset) {
+		u32 data_size;
+		u8 *data;
+
+		if (end_offset - curr_offset < DEVLINK_REGION_READ_CHUNK_SIZE)
+			data_size = end_offset - curr_offset;
+		else
+			data_size = DEVLINK_REGION_READ_CHUNK_SIZE;
+
+		data = &snapshot->data[curr_offset];
+		err = devlink_nl_cmd_region_read_chunk_fill(skb, devlink,
+							    data, data_size,
+							    curr_offset);
+		if (err)
+			break;
+
+		curr_offset += data_size;
+	}
+	*new_offset = curr_offset;
+
+	return err;
+}
+
+static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb,
+					     struct netlink_callback *cb)
+{
+	u64 ret_offset, start_offset, end_offset = 0;
+	struct nlattr *attrs[DEVLINK_ATTR_MAX + 1];
+	const struct genl_ops *ops = cb->data;
+	struct devlink_region *region;
+	struct nlattr *chunks_attr;
+	const char *region_name;
+	struct devlink *devlink;
+	bool dump = true;
+	void *hdr;
+	int err;
+
+	start_offset = *((u64 *)&cb->args[0]);
+
+	err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize,
+			  attrs, DEVLINK_ATTR_MAX, ops->policy, NULL);
+	if (err)
+		goto out;
+
+	devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs);
+	if (IS_ERR(devlink))
+		goto out;
+
+	mutex_lock(&devlink_mutex);
+	mutex_lock(&devlink->lock);
+
+	if (!attrs[DEVLINK_ATTR_REGION_NAME] ||
+	    !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID])
+		goto out_unlock;
+
+	region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]);
+	region = devlink_region_get_by_name(devlink, region_name);
+	if (!region)
+		goto out_unlock;
+
+	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			  &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI,
+			  DEVLINK_CMD_REGION_READ);
+	if (!hdr)
+		goto out_unlock;
+
+	err = devlink_nl_put_handle(skb, devlink);
+	if (err)
+		goto nla_put_failure;
+
+	err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name);
+	if (err)
+		goto nla_put_failure;
+
+	chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS);
+	if (!chunks_attr)
+		goto nla_put_failure;
+
+	if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] &&
+	    attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) {
+		if (!start_offset)
+			start_offset =
+				nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+
+		end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]);
+		end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]);
+		dump = false;
+	}
+
+	err = devlink_nl_region_read_snapshot_fill(skb, devlink,
+						   region, attrs,
+						   start_offset,
+						   end_offset, dump,
+						   &ret_offset);
+
+	if (err && err != -EMSGSIZE)
+		goto nla_put_failure;
+
+	/* Check if there was any progress done to prevent infinite loop */
+	if (ret_offset == start_offset)
+		goto nla_put_failure;
+
+	*((u64 *)&cb->args[0]) = ret_offset;
+
+	nla_nest_end(skb, chunks_attr);
+	genlmsg_end(skb, hdr);
+	mutex_unlock(&devlink->lock);
+	mutex_unlock(&devlink_mutex);
+
+	return skb->len;
+
+nla_put_failure:
+	genlmsg_cancel(skb, hdr);
+out_unlock:
+	mutex_unlock(&devlink->lock);
+	mutex_unlock(&devlink_mutex);
+out:
+	return 0;
+}
+
 static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = {
 	[DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING },
 	[DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING },
@@ -3626,6 +3801,13 @@ static const struct genl_ops devlink_nl_ops[] = {
 		.flags = GENL_ADMIN_PERM,
 		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
 	},
+	{
+		.cmd = DEVLINK_CMD_REGION_READ,
+		.dumpit = devlink_nl_cmd_region_read_dumpit,
+		.policy = devlink_nl_policy,
+		.flags = GENL_ADMIN_PERM,
+		.internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK,
+	},
 };
 
 static struct genl_family devlink_nl_family __ro_after_init = {
-- 
cgit v1.2.3


From 523f9eb1ef25aab4aaf9aeb5356160e8039411ef Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:15 +0300
Subject: net/mlx4_core: Add health buffer address capability

Health buffer address is a 32 bit PCI address offset provided by
the FW. This offset is used for reading FW health debug data
located on the shared CR space. Cr space is accessible in both
driver and FW and allows for different queries and configurations.
Health buffer size is always 64B of readable data followed by a
lock which is used to block volatile CR space access.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/fw.c   | 5 ++++-
 drivers/net/ethernet/mellanox/mlx4/fw.h   | 1 +
 drivers/net/ethernet/mellanox/mlx4/main.c | 1 +
 include/linux/mlx4/device.h               | 1 +
 4 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 46dcbfbe4c5e..babcfd9c0571 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -825,7 +825,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_NUM_OFFSET	0xcc
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MAX_OFFSET	0xd0
 #define QUERY_DEV_CAP_QP_RATE_LIMIT_MIN_OFFSET	0xd2
-
+#define QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET	0xe4
 
 	dev_cap->flags2 = 0;
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -1082,6 +1082,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev_cap->rl_caps.min_unit = size >> 14;
 	}
 
+	MLX4_GET(dev_cap->health_buffer_addrs, outbox,
+		 QUERY_DEV_CAP_HEALTH_BUFFER_ADDRESS_OFFSET);
+
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
 	if (field32 & (1 << 16))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.h b/drivers/net/ethernet/mellanox/mlx4/fw.h
index cd6399c76bfd..650ae08c71de 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.h
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.h
@@ -128,6 +128,7 @@ struct mlx4_dev_cap {
 	u32 dmfs_high_rate_qpn_base;
 	u32 dmfs_high_rate_qpn_range;
 	struct mlx4_rate_limit_caps rl_caps;
+	u32 health_buffer_addrs;
 	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
 	bool wol_port[MLX4_MAX_PORTS + 1];
 };
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index c42eddfcd2b5..806d441b3701 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -523,6 +523,7 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	dev->caps.max_rss_tbl_sz     = dev_cap->max_rss_tbl_sz;
 	dev->caps.wol_port[1]          = dev_cap->wol_port[1];
 	dev->caps.wol_port[2]          = dev_cap->wol_port[2];
+	dev->caps.health_buffer_addrs  = dev_cap->health_buffer_addrs;
 
 	/* Save uar page shift */
 	if (!mlx4_is_slave(dev)) {
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 122e7e9d3091..e3bfe76aea98 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -630,6 +630,7 @@ struct mlx4_caps {
 	u32			vf_caps;
 	bool			wol_port[MLX4_MAX_PORTS + 1];
 	struct mlx4_rate_limit_caps rl_caps;
+	u32			health_buffer_addrs;
 };
 
 struct mlx4_buf_list {
-- 
cgit v1.2.3


From bedc989b0c98285b277ff8a08ff9514e580913f4 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:16 +0300
Subject: net/mlx4_core: Add Crdump FW snapshot support

Crdump allows the driver to create a snapshot of the FW PCI
crspace and health buffer during a critical FW issue.
In case of a FW command timeout, FW getting stuck or a non zero
value on the catastrophic buffer, a snapshot will be taken.

The snapshot is exposed using devlink, cr-space, fw-health
address regions are registered on init and snapshots are attached
once a new snapshot is collected by the driver.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/Makefile |   2 +-
 drivers/net/ethernet/mellanox/mlx4/catas.c  |   6 +-
 drivers/net/ethernet/mellanox/mlx4/crdump.c | 231 ++++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx4/main.c   |  10 +-
 drivers/net/ethernet/mellanox/mlx4/mlx4.h   |   4 +
 include/linux/mlx4/device.h                 |   6 +
 6 files changed, 255 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx4/crdump.c

diff --git a/drivers/net/ethernet/mellanox/mlx4/Makefile b/drivers/net/ethernet/mellanox/mlx4/Makefile
index 16b10d01fcf4..3f400770fcd8 100644
--- a/drivers/net/ethernet/mellanox/mlx4/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx4/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_MLX4_CORE)		+= mlx4_core.o
 
 mlx4_core-y :=	alloc.o catas.o cmd.o cq.o eq.o fw.o fw_qos.o icm.o intf.o \
 		main.o mcg.o mr.o pd.o port.o profile.o qp.o reset.o sense.o \
-		srq.o resource_tracker.o
+		srq.o resource_tracker.o crdump.o
 
 obj-$(CONFIG_MLX4_EN)               += mlx4_en.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c
index 8afe4b5fb09b..c81d15bf259c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/catas.c
+++ b/drivers/net/ethernet/mellanox/mlx4/catas.c
@@ -178,10 +178,12 @@ void mlx4_enter_error_state(struct mlx4_dev_persistent *persist)
 
 	dev = persist->dev;
 	mlx4_err(dev, "device is going to be reset\n");
-	if (mlx4_is_slave(dev))
+	if (mlx4_is_slave(dev)) {
 		err = mlx4_reset_slave(dev);
-	else
+	} else {
+		mlx4_crdump_collect(dev);
 		err = mlx4_reset_master(dev);
+	}
 
 	if (!err) {
 		mlx4_err(dev, "device was reset successfully\n");
diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c
new file mode 100644
index 000000000000..4d5524dffec4
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c
@@ -0,0 +1,231 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "mlx4.h"
+
+#define BAD_ACCESS			0xBADACCE5
+#define HEALTH_BUFFER_SIZE		0x40
+#define CR_ENABLE_BIT			swab32(BIT(6))
+#define CR_ENABLE_BIT_OFFSET		0xF3F04
+#define MAX_NUM_OF_DUMPS_TO_STORE	(8)
+
+static const char *region_cr_space_str = "cr-space";
+static const char *region_fw_health_str = "fw-health";
+
+/* Set to true in case cr enable bit was set to true before crdump */
+static bool crdump_enbale_bit_set;
+
+static void crdump_enable_crspace_access(struct mlx4_dev *dev,
+					 u8 __iomem *cr_space)
+{
+	/* Get current enable bit value */
+	crdump_enbale_bit_set =
+		readl(cr_space + CR_ENABLE_BIT_OFFSET) & CR_ENABLE_BIT;
+
+	/* Enable FW CR filter (set bit6 to 0) */
+	if (crdump_enbale_bit_set)
+		writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) & ~CR_ENABLE_BIT,
+		       cr_space + CR_ENABLE_BIT_OFFSET);
+
+	/* Enable block volatile crspace accesses */
+	writel(swab32(1), cr_space + dev->caps.health_buffer_addrs +
+	       HEALTH_BUFFER_SIZE);
+}
+
+static void crdump_disable_crspace_access(struct mlx4_dev *dev,
+					  u8 __iomem *cr_space)
+{
+	/* Disable block volatile crspace accesses */
+	writel(0, cr_space + dev->caps.health_buffer_addrs +
+	       HEALTH_BUFFER_SIZE);
+
+	/* Restore FW CR filter value (set bit6 to original value) */
+	if (crdump_enbale_bit_set)
+		writel(readl(cr_space + CR_ENABLE_BIT_OFFSET) | CR_ENABLE_BIT,
+		       cr_space + CR_ENABLE_BIT_OFFSET);
+}
+
+static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev,
+					u8 __iomem *cr_space,
+					u32 id)
+{
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	struct pci_dev *pdev = dev->persist->pdev;
+	unsigned long cr_res_size;
+	u8 *crspace_data;
+	int offset;
+	int err;
+
+	if (!crdump->region_crspace) {
+		mlx4_err(dev, "crdump: cr-space region is NULL\n");
+		return;
+	}
+
+	/* Try to collect CR space */
+	cr_res_size = pci_resource_len(pdev, 0);
+	crspace_data = kvmalloc(cr_res_size, GFP_KERNEL);
+	if (crspace_data) {
+		for (offset = 0; offset < cr_res_size; offset += 4)
+			*(u32 *)(crspace_data + offset) =
+					readl(cr_space + offset);
+
+		err = devlink_region_snapshot_create(crdump->region_crspace,
+						     cr_res_size, crspace_data,
+						     id, &kvfree);
+		if (err) {
+			kvfree(crspace_data);
+			mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+				  region_cr_space_str, id, err);
+		} else {
+			mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+				  id, region_cr_space_str);
+		}
+	} else {
+		mlx4_err(dev, "crdump: Failed to allocate crspace buffer\n");
+	}
+}
+
+static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev,
+					  u8 __iomem *cr_space,
+					  u32 id)
+{
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	u8 *health_data;
+	int offset;
+	int err;
+
+	if (!crdump->region_fw_health) {
+		mlx4_err(dev, "crdump: fw-health region is NULL\n");
+		return;
+	}
+
+	/* Try to collect health buffer */
+	health_data = kvmalloc(HEALTH_BUFFER_SIZE, GFP_KERNEL);
+	if (health_data) {
+		u8 __iomem *health_buf_start =
+				cr_space + dev->caps.health_buffer_addrs;
+
+		for (offset = 0; offset < HEALTH_BUFFER_SIZE; offset += 4)
+			*(u32 *)(health_data + offset) =
+					readl(health_buf_start + offset);
+
+		err = devlink_region_snapshot_create(crdump->region_fw_health,
+						     HEALTH_BUFFER_SIZE,
+						     health_data,
+						     id, &kvfree);
+		if (err) {
+			kvfree(health_data);
+			mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n",
+				  region_fw_health_str, id, err);
+		} else {
+			mlx4_info(dev, "crdump: added snapshot %d to devlink region %s\n",
+				  id, region_fw_health_str);
+		}
+	} else {
+		mlx4_err(dev, "crdump: Failed to allocate health buffer\n");
+	}
+}
+
+int mlx4_crdump_collect(struct mlx4_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+	struct pci_dev *pdev = dev->persist->pdev;
+	unsigned long cr_res_size;
+	u8 __iomem *cr_space;
+	u32 id;
+
+	if (!dev->caps.health_buffer_addrs) {
+		mlx4_info(dev, "crdump: FW doesn't support health buffer access, skipping\n");
+		return 0;
+	}
+
+	cr_res_size = pci_resource_len(pdev, 0);
+
+	cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size);
+	if (!cr_space) {
+		mlx4_err(dev, "crdump: Failed to map pci cr region\n");
+		return -ENODEV;
+	}
+
+	crdump_enable_crspace_access(dev, cr_space);
+
+	/* Get the available snapshot ID for the dumps */
+	id = devlink_region_shapshot_id_get(devlink);
+
+	/* Try to capture dumps */
+	mlx4_crdump_collect_crspace(dev, cr_space, id);
+	mlx4_crdump_collect_fw_health(dev, cr_space, id);
+
+	crdump_disable_crspace_access(dev, cr_space);
+
+	iounmap(cr_space);
+	return 0;
+}
+
+int mlx4_crdump_init(struct mlx4_dev *dev)
+{
+	struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+	struct pci_dev *pdev = dev->persist->pdev;
+
+	/* Create cr-space region */
+	crdump->region_crspace =
+		devlink_region_create(devlink,
+				      region_cr_space_str,
+				      MAX_NUM_OF_DUMPS_TO_STORE,
+				      pci_resource_len(pdev, 0));
+	if (IS_ERR(crdump->region_crspace))
+		mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+			  region_cr_space_str,
+			  PTR_ERR(crdump->region_crspace));
+
+	/* Create fw-health region */
+	crdump->region_fw_health =
+		devlink_region_create(devlink,
+				      region_fw_health_str,
+				      MAX_NUM_OF_DUMPS_TO_STORE,
+				      HEALTH_BUFFER_SIZE);
+	if (IS_ERR(crdump->region_fw_health))
+		mlx4_warn(dev, "crdump: create devlink region %s err %ld\n",
+			  region_fw_health_str,
+			  PTR_ERR(crdump->region_fw_health));
+
+	return 0;
+}
+
+void mlx4_crdump_end(struct mlx4_dev *dev)
+{
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
+
+	devlink_region_destroy(crdump->region_fw_health);
+	devlink_region_destroy(crdump->region_crspace);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 806d441b3701..46b021409b8b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -3807,10 +3807,14 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 		}
 	}
 
-	err = mlx4_catas_init(&priv->dev);
+	err = mlx4_crdump_init(&priv->dev);
 	if (err)
 		goto err_release_regions;
 
+	err = mlx4_catas_init(&priv->dev);
+	if (err)
+		goto err_crdump;
+
 	err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 0);
 	if (err)
 		goto err_catas;
@@ -3820,6 +3824,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data,
 err_catas:
 	mlx4_catas_end(&priv->dev);
 
+err_crdump:
+	mlx4_crdump_end(&priv->dev);
+
 err_release_regions:
 	pci_release_regions(pdev);
 
@@ -4081,6 +4088,7 @@ static void mlx4_remove_one(struct pci_dev *pdev)
 	else
 		mlx4_info(dev, "%s: interface is down\n", __func__);
 	mlx4_catas_end(dev);
+	mlx4_crdump_end(dev);
 	if (dev->flags & MLX4_FLAG_SRIOV && !active_vfs) {
 		mlx4_warn(dev, "Disabling SR-IOV\n");
 		pci_disable_sriov(pdev);
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 2ebaa3bee42f..6e016092a6f1 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1042,6 +1042,8 @@ void mlx4_start_catas_poll(struct mlx4_dev *dev);
 void mlx4_stop_catas_poll(struct mlx4_dev *dev);
 int mlx4_catas_init(struct mlx4_dev *dev);
 void mlx4_catas_end(struct mlx4_dev *dev);
+int mlx4_crdump_init(struct mlx4_dev *dev);
+void mlx4_crdump_end(struct mlx4_dev *dev);
 int mlx4_restart_one(struct pci_dev *pdev, bool reload,
 		     struct devlink *devlink);
 int mlx4_register_device(struct mlx4_dev *dev);
@@ -1228,6 +1230,8 @@ void mlx4_srq_event(struct mlx4_dev *dev, u32 srqn, int event_type);
 void mlx4_enter_error_state(struct mlx4_dev_persistent *persist);
 int mlx4_comm_internal_err(u32 slave_read);
 
+int mlx4_crdump_collect(struct mlx4_dev *dev);
+
 int mlx4_SENSE_PORT(struct mlx4_dev *dev, int port,
 		    enum mlx4_port_type *type);
 void mlx4_do_sense_ports(struct mlx4_dev *dev,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index e3bfe76aea98..300b944e6e1e 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -852,6 +852,11 @@ struct mlx4_vf_dev {
 	u8			n_ports;
 };
 
+struct mlx4_fw_crdump {
+	struct devlink_region *region_crspace;
+	struct devlink_region *region_fw_health;
+};
+
 enum mlx4_pci_status {
 	MLX4_PCI_STATUS_DISABLED,
 	MLX4_PCI_STATUS_ENABLED,
@@ -872,6 +877,7 @@ struct mlx4_dev_persistent {
 	u8	interface_state;
 	struct mutex		pci_status_mutex; /* sync pci state */
 	enum mlx4_pci_status	pci_status;
+	struct mlx4_fw_crdump	crdump;
 };
 
 struct mlx4_dev {
-- 
cgit v1.2.3


From f6a69885f2e38be0229ab9f6a2d9d4a1b4ba2be5 Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:17 +0300
Subject: devlink: Add generic parameters region_snapshot

region_snapshot - When set enables capturing region snapshots

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/devlink.h | 4 ++++
 net/core/devlink.c    | 5 +++++
 2 files changed, 9 insertions(+)

diff --git a/include/net/devlink.h b/include/net/devlink.h
index 905f0bb7b4ba..b9b89d6604d4 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -361,6 +361,7 @@ enum devlink_param_generic_id {
 	DEVLINK_PARAM_GENERIC_ID_INT_ERR_RESET,
 	DEVLINK_PARAM_GENERIC_ID_MAX_MACS,
 	DEVLINK_PARAM_GENERIC_ID_ENABLE_SRIOV,
+	DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
 
 	/* add new param generic ids above here*/
 	__DEVLINK_PARAM_GENERIC_ID_MAX,
@@ -376,6 +377,9 @@ enum devlink_param_generic_id {
 #define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME "enable_sriov"
 #define DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE DEVLINK_PARAM_TYPE_BOOL
 
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME "region_snapshot_enable"
+#define DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE DEVLINK_PARAM_TYPE_BOOL
+
 #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate)	\
 {									\
 	.id = DEVLINK_PARAM_GENERIC_ID_##_id,				\
diff --git a/net/core/devlink.c b/net/core/devlink.c
index e5118dba6bb4..65fc366a78a4 100644
--- a/net/core/devlink.c
+++ b/net/core/devlink.c
@@ -2671,6 +2671,11 @@ static const struct devlink_param devlink_param_generic[] = {
 		.name = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_NAME,
 		.type = DEVLINK_PARAM_GENERIC_ENABLE_SRIOV_TYPE,
 	},
+	{
+		.id = DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+		.name = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_NAME,
+		.type = DEVLINK_PARAM_GENERIC_REGION_SNAPSHOT_TYPE,
+	},
 };
 
 static int devlink_param_generic_verify(const struct devlink_param *param)
-- 
cgit v1.2.3


From 3c641ba4a852cf4e90e3d7f29c5df08e24213c5d Mon Sep 17 00:00:00 2001
From: Alex Vesker <valex@mellanox.com>
Date: Thu, 12 Jul 2018 15:13:18 +0300
Subject: net/mlx4_core: Use devlink region_snapshot parameter

This parameter enables capturing region snapshot of the crspace
during critical errors. The default value of this parameter is
disabled, it can be enabled using devlink param commands.
It is possible to configure during runtime and also driver init.

Signed-off-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/crdump.c |  8 ++++++
 drivers/net/ethernet/mellanox/mlx4/main.c   | 41 +++++++++++++++++++++++++++++
 include/linux/mlx4/device.h                 |  1 +
 3 files changed, 50 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c
index 4d5524dffec4..88316c743820 100644
--- a/drivers/net/ethernet/mellanox/mlx4/crdump.c
+++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c
@@ -158,6 +158,7 @@ static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev,
 int mlx4_crdump_collect(struct mlx4_dev *dev)
 {
 	struct devlink *devlink = priv_to_devlink(mlx4_priv(dev));
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
 	struct pci_dev *pdev = dev->persist->pdev;
 	unsigned long cr_res_size;
 	u8 __iomem *cr_space;
@@ -168,6 +169,11 @@ int mlx4_crdump_collect(struct mlx4_dev *dev)
 		return 0;
 	}
 
+	if (!crdump->snapshot_enable) {
+		mlx4_info(dev, "crdump: devlink snapshot disabled, skipping\n");
+		return 0;
+	}
+
 	cr_res_size = pci_resource_len(pdev, 0);
 
 	cr_space = ioremap(pci_resource_start(pdev, 0), cr_res_size);
@@ -197,6 +203,8 @@ int mlx4_crdump_init(struct mlx4_dev *dev)
 	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
 	struct pci_dev *pdev = dev->persist->pdev;
 
+	crdump->snapshot_enable = false;
+
 	/* Create cr-space region */
 	crdump->region_crspace =
 		devlink_region_create(devlink,
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 46b021409b8b..2d979a652b7b 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -191,6 +191,26 @@ static int mlx4_devlink_ierr_reset_set(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+static int mlx4_devlink_crdump_snapshot_get(struct devlink *devlink, u32 id,
+					    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+
+	ctx->val.vbool = dev->persist->crdump.snapshot_enable;
+	return 0;
+}
+
+static int mlx4_devlink_crdump_snapshot_set(struct devlink *devlink, u32 id,
+					    struct devlink_param_gset_ctx *ctx)
+{
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+
+	dev->persist->crdump.snapshot_enable = ctx->val.vbool;
+	return 0;
+}
+
 static int
 mlx4_devlink_max_macs_validate(struct devlink *devlink, u32 id,
 			       union devlink_param_value val,
@@ -224,6 +244,11 @@ static const struct devlink_param mlx4_devlink_params[] = {
 	DEVLINK_PARAM_GENERIC(MAX_MACS,
 			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
 			      NULL, NULL, mlx4_devlink_max_macs_validate),
+	DEVLINK_PARAM_GENERIC(REGION_SNAPSHOT,
+			      BIT(DEVLINK_PARAM_CMODE_RUNTIME) |
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      mlx4_devlink_crdump_snapshot_get,
+			      mlx4_devlink_crdump_snapshot_set, NULL),
 	DEVLINK_PARAM_DRIVER(MLX4_DEVLINK_PARAM_ID_ENABLE_64B_CQE_EQE,
 			     "enable_64b_cqe_eqe", DEVLINK_PARAM_TYPE_BOOL,
 			     BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
@@ -270,6 +295,11 @@ static void mlx4_devlink_set_params_init_values(struct devlink *devlink)
 	mlx4_devlink_set_init_value(devlink,
 				    MLX4_DEVLINK_PARAM_ID_ENABLE_4K_UAR,
 				    value);
+
+	value.vbool = false;
+	mlx4_devlink_set_init_value(devlink,
+				    DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+				    value);
 }
 
 static inline void mlx4_set_num_reserved_uars(struct mlx4_dev *dev,
@@ -3862,6 +3892,9 @@ static int mlx4_devlink_port_type_set(struct devlink_port *devlink_port,
 
 static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
 {
+	struct mlx4_priv *priv = devlink_priv(devlink);
+	struct mlx4_dev *dev = &priv->dev;
+	struct mlx4_fw_crdump *crdump = &dev->persist->crdump;
 	union devlink_param_value saved_value;
 	int err;
 
@@ -3889,6 +3922,14 @@ static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink)
 						 &saved_value);
 	if (!err)
 		enable_4k_uar = saved_value.vbool;
+	err = devlink_param_driverinit_value_get(devlink,
+						 DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT,
+						 &saved_value);
+	if (!err && crdump->snapshot_enable != saved_value.vbool) {
+		crdump->snapshot_enable = saved_value.vbool;
+		devlink_param_value_changed(devlink,
+					    DEVLINK_PARAM_GENERIC_ID_REGION_SNAPSHOT);
+	}
 }
 
 static int mlx4_devlink_reload(struct devlink *devlink,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 300b944e6e1e..dca6ab4eaa99 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -853,6 +853,7 @@ struct mlx4_vf_dev {
 };
 
 struct mlx4_fw_crdump {
+	bool snapshot_enable;
 	struct devlink_region *region_crspace;
 	struct devlink_region *region_fw_health;
 };
-- 
cgit v1.2.3


From cedca4180127e097e4823018e748b1635c0667f0 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 11 Jul 2018 21:32:41 +0200
Subject: net: gemini: Look up L3 maxlen from table
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The code to calculate the hardware register enumerator
for the maximum L3 length isn't entirely simple to read.
Use the existing defines and rewrite the function into a
table look-up.

Acked-by: Michał Mirosław <mirq-linux@rere.qmqm.pl>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 61 ++++++++++++++++++++++++++---------
 1 file changed, 46 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index ce1f04fdbf70..2f502c42a653 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -401,26 +401,57 @@ static int gmac_setup_phy(struct net_device *netdev)
 	return 0;
 }
 
-static int gmac_pick_rx_max_len(int max_l3_len)
-{
-	/* index = CONFIG_MAXLEN_XXX values */
-	static const int max_len[8] = {
-		1536, 1518, 1522, 1542,
-		9212, 10236, 1518, 1518
-	};
-	int i, n = 5;
+/* The maximum frame length is not logically enumerated in the
+ * hardware, so we do a table lookup to find the applicable max
+ * frame length.
+ */
+struct gmac_max_framelen {
+	unsigned int max_l3_len;
+	u8 val;
+};
 
-	max_l3_len += ETH_HLEN + VLAN_HLEN;
+static const struct gmac_max_framelen gmac_maxlens[] = {
+	{
+		.max_l3_len = 1518,
+		.val = CONFIG0_MAXLEN_1518,
+	},
+	{
+		.max_l3_len = 1522,
+		.val = CONFIG0_MAXLEN_1522,
+	},
+	{
+		.max_l3_len = 1536,
+		.val = CONFIG0_MAXLEN_1536,
+	},
+	{
+		.max_l3_len = 1542,
+		.val = CONFIG0_MAXLEN_1542,
+	},
+	{
+		.max_l3_len = 9212,
+		.val = CONFIG0_MAXLEN_9k,
+	},
+	{
+		.max_l3_len = 10236,
+		.val = CONFIG0_MAXLEN_10k,
+	},
+};
+
+static int gmac_pick_rx_max_len(unsigned int max_l3_len)
+{
+	const struct gmac_max_framelen *maxlen;
+	int maxtot;
+	int i;
 
-	if (max_l3_len > max_len[n])
-		return -1;
+	maxtot = max_l3_len + ETH_HLEN + VLAN_HLEN;
 
-	for (i = 0; i < 5; i++) {
-		if (max_len[i] >= max_l3_len && max_len[i] < max_len[n])
-			n = i;
+	for (i = 0; i < ARRAY_SIZE(gmac_maxlens); i++) {
+		maxlen = &gmac_maxlens[i];
+		if (maxtot <= maxlen->max_l3_len)
+			return maxlen->val;
 	}
 
-	return n;
+	return -1;
 }
 
 static int gmac_init(struct net_device *netdev)
-- 
cgit v1.2.3


From 9ab5c929e641c68ab3ade762b330e22e29c51f13 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 11 Jul 2018 21:32:42 +0200
Subject: net: gemini: Improve connection prints

Switch over to using a module parameter and debug prints
that can be controlled by this or ethtool like everyone
else. Depromote all other prints to debug messages.

The phy_print_status() was already in place, albeit never
really used because the debuglevel hiding it had to be
set up using ethtool.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 46 ++++++++++++++++++++---------------
 1 file changed, 26 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 2f502c42a653..7b880878f22b 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -46,6 +46,11 @@
 #define DRV_NAME		"gmac-gemini"
 #define DRV_VERSION		"1.0"
 
+#define DEFAULT_MSG_ENABLE (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK)
+static int debug = -1;
+module_param(debug, int, 0);
+MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+
 #define HSIZE_8			0x00
 #define HSIZE_16		0x01
 #define HSIZE_32		0x02
@@ -300,23 +305,26 @@ static void gmac_speed_set(struct net_device *netdev)
 		status.bits.speed = GMAC_SPEED_1000;
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
 			status.bits.mii_rmii = GMAC_PHY_RGMII_1000;
-		netdev_info(netdev, "connect to RGMII @ 1Gbit\n");
+		netdev_dbg(netdev, "connect %s to RGMII @ 1Gbit\n",
+			   phydev_name(phydev));
 		break;
 	case 100:
 		status.bits.speed = GMAC_SPEED_100;
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
 			status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
-		netdev_info(netdev, "connect to RGMII @ 100 Mbit\n");
+		netdev_dbg(netdev, "connect %s to RGMII @ 100 Mbit\n",
+			   phydev_name(phydev));
 		break;
 	case 10:
 		status.bits.speed = GMAC_SPEED_10;
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII)
 			status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
-		netdev_info(netdev, "connect to RGMII @ 10 Mbit\n");
+		netdev_dbg(netdev, "connect %s to RGMII @ 10 Mbit\n",
+			   phydev_name(phydev));
 		break;
 	default:
-		netdev_warn(netdev, "Not supported PHY speed (%d)\n",
-			    phydev->speed);
+		netdev_warn(netdev, "Unsupported PHY speed (%d) on %s\n",
+			    phydev->speed, phydev_name(phydev));
 	}
 
 	if (phydev->duplex == DUPLEX_FULL) {
@@ -363,12 +371,6 @@ static int gmac_setup_phy(struct net_device *netdev)
 		return -ENODEV;
 	netdev->phydev = phy;
 
-	netdev_info(netdev, "connected to PHY \"%s\"\n",
-		    phydev_name(phy));
-	phy_attached_print(phy, "phy_id=0x%.8lx, phy_mode=%s\n",
-			   (unsigned long)phy->phy_id,
-			   phy_modes(phy->interface));
-
 	phy->supported &= PHY_GBIT_FEATURES;
 	phy->supported |= SUPPORTED_Asym_Pause | SUPPORTED_Pause;
 	phy->advertising = phy->supported;
@@ -376,19 +378,19 @@ static int gmac_setup_phy(struct net_device *netdev)
 	/* set PHY interface type */
 	switch (phy->interface) {
 	case PHY_INTERFACE_MODE_MII:
-		netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+		netdev_dbg(netdev,
+			   "MII: set GMAC0 to GMII mode, GMAC1 disabled\n");
 		status.bits.mii_rmii = GMAC_PHY_MII;
-		netdev_info(netdev, "connect to MII\n");
 		break;
 	case PHY_INTERFACE_MODE_GMII:
-		netdev_info(netdev, "set GMAC0 to GMII mode, GMAC1 disabled\n");
+		netdev_dbg(netdev,
+			   "GMII: set GMAC0 to GMII mode, GMAC1 disabled\n");
 		status.bits.mii_rmii = GMAC_PHY_GMII;
-		netdev_info(netdev, "connect to GMII\n");
 		break;
 	case PHY_INTERFACE_MODE_RGMII:
-		dev_info(dev, "set GMAC0 and GMAC1 to MII/RGMII mode\n");
+		netdev_dbg(netdev,
+			   "RGMII: set GMAC0 and GMAC1 to MII/RGMII mode\n");
 		status.bits.mii_rmii = GMAC_PHY_RGMII_100_10;
-		netdev_info(netdev, "connect to RGMII\n");
 		break;
 	default:
 		netdev_err(netdev, "Unsupported MII interface\n");
@@ -398,6 +400,9 @@ static int gmac_setup_phy(struct net_device *netdev)
 	}
 	writel(status.bits32, port->gmac_base + GMAC_STATUS);
 
+	if (netif_msg_link(port))
+		phy_attached_info(phy);
+
 	return 0;
 }
 
@@ -1307,8 +1312,8 @@ static void gmac_enable_irq(struct net_device *netdev, int enable)
 	unsigned long flags;
 	u32 val, mask;
 
-	netdev_info(netdev, "%s device %d %s\n", __func__,
-		    netdev->dev_id, enable ? "enable" : "disable");
+	netdev_dbg(netdev, "%s device %d %s\n", __func__,
+		   netdev->dev_id, enable ? "enable" : "disable");
 	spin_lock_irqsave(&geth->irq_lock, flags);
 
 	mask = GMAC0_IRQ0_2 << (netdev->dev_id * 2);
@@ -1813,7 +1818,7 @@ static int gmac_open(struct net_device *netdev)
 		     HRTIMER_MODE_REL);
 	port->rx_coalesce_timer.function = &gmac_coalesce_delay_expired;
 
-	netdev_info(netdev, "opened\n");
+	netdev_dbg(netdev, "opened\n");
 
 	return 0;
 
@@ -2385,6 +2390,7 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 	port->id = id;
 	port->geth = geth;
 	port->dev = dev;
+	port->msg_enable = netif_msg_init(debug, DEFAULT_MSG_ENABLE);
 
 	/* DMA memory */
 	dmares = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-- 
cgit v1.2.3


From 60cc7767b901dd1e3f70755c3d2505556ba487c2 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 11 Jul 2018 21:32:43 +0200
Subject: net: gemini: Allow multiple ports to instantiate

The code was not tested with two ports actually in use at
the same time. (I blame this on lack of actual hardware using
that feature.) Now after locating a system using both ports,
add necessary fix to make both ports come up.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 7b880878f22b..bd4602ebcea1 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -1789,7 +1789,10 @@ static int gmac_open(struct net_device *netdev)
 	phy_start(netdev->phydev);
 
 	err = geth_resize_freeq(port);
-	if (err) {
+	/* It's fine if it's just busy, the other port has set up
+	 * the freeq in that case.
+	 */
+	if (err && (err != -EBUSY)) {
 		netdev_err(netdev, "could not resize freeq\n");
 		goto err_stop_phy;
 	}
-- 
cgit v1.2.3


From 06d51513129495fba9bb68ef7aa8cc5ca60e0556 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 11 Jul 2018 21:32:44 +0200
Subject: net: gemini: Move main init to port

The initialization sequence for the ethernet, setting up
interrupt routing and such things, need to be done after
both the ports are clocked and reset. Before this the
config will not "take". Move the initialization to the
port probe function and keep track of init status in
the state.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index bd4602ebcea1..050fffb77d11 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -151,6 +151,7 @@ struct gemini_ethernet {
 	void __iomem *base;
 	struct gemini_ethernet_port *port0;
 	struct gemini_ethernet_port *port1;
+	bool initialized;
 
 	spinlock_t	irq_lock; /* Locks IRQ-related registers */
 	unsigned int	freeq_order;
@@ -2303,6 +2304,14 @@ static void gemini_port_remove(struct gemini_ethernet_port *port)
 
 static void gemini_ethernet_init(struct gemini_ethernet *geth)
 {
+	/* Only do this once both ports are online */
+	if (geth->initialized)
+		return;
+	if (geth->port0 && geth->port1)
+		geth->initialized = true;
+	else
+		return;
+
 	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_0_REG);
 	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_1_REG);
 	writel(0, geth->base + GLOBAL_INTERRUPT_ENABLE_2_REG);
@@ -2450,6 +2459,10 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 		geth->port0 = port;
 	else
 		geth->port1 = port;
+
+	/* This will just be done once both ports are up and reset */
+	gemini_ethernet_init(geth);
+
 	platform_set_drvdata(pdev, port);
 
 	/* Set up and register the netdev */
@@ -2567,7 +2580,6 @@ static int gemini_ethernet_probe(struct platform_device *pdev)
 
 	spin_lock_init(&geth->irq_lock);
 	spin_lock_init(&geth->freeq_lock);
-	gemini_ethernet_init(geth);
 
 	/* The children will use this */
 	platform_set_drvdata(pdev, geth);
@@ -2580,8 +2592,8 @@ static int gemini_ethernet_remove(struct platform_device *pdev)
 {
 	struct gemini_ethernet *geth = platform_get_drvdata(pdev);
 
-	gemini_ethernet_init(geth);
 	geth_cleanup_freeq(geth);
+	geth->initialized = false;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 430ac34de9693bfe4bea0bab830e0ca0be9ef4b9 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 11 Jul 2018 21:32:45 +0200
Subject: net: gemini: Indicate that we can handle jumboframes

The hardware supposedly handles frames up to 10236 bytes and
implements .ndo_change_mtu() so accept 10236 minus the ethernet
header for a VLAN tagged frame on the netdevices. Use
ETH_MIN_MTU as minimum MTU.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cortina/gemini.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 050fffb77d11..1c9ad3630c77 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -2476,6 +2476,11 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev)
 
 	netdev->hw_features = GMAC_OFFLOAD_FEATURES;
 	netdev->features |= GMAC_OFFLOAD_FEATURES | NETIF_F_GRO;
+	/* We can handle jumbo frames up to 10236 bytes so, let's accept
+	 * payloads of 10236 bytes minus VLAN and ethernet header
+	 */
+	netdev->min_mtu = ETH_MIN_MTU;
+	netdev->max_mtu = 10236 - VLAN_ETH_HLEN;
 
 	port->freeq_refill = 0;
 	netif_napi_add(netdev, &port->napi, gmac_napi_poll,
-- 
cgit v1.2.3


From c3d433617d2048f5fc3ee1135bce1a9bc2375662 Mon Sep 17 00:00:00 2001
From: Tarun Vyas <tarun.vyas@intel.com>
Date: Wed, 11 Jul 2018 22:33:23 -0700
Subject: drm/i915: Use crtc_state->has_psr instead of CAN_PSR for pipe update

In commit "drm/i915: Wait for PSR exit before checking for vblank
evasion", the idea was to limit the PSR IDLE checks when PSR is
actually supported. While CAN_PSR does do that check, it doesn't
applies on a per-crtc basis. crtc_state->has_psr is a more granular
check that only applies to pipe(s) that have PSR enabled.

Without the has_psr check, we end up waiting on the eDP transcoder's
PSR_STATUS register irrespective of whether the pipe being updated is
driving it or not.

v2: Remove unnecessary parantheses, make checkpatch happy.

v3: Move the has_psr check to intel_psr_wait_for_idle and commit
    message changes (DK).

v4: Derive dev_priv from intel_crtc_state (DK)

v5: Commit message changes to reflect the HW behavior (DK)

Fixes: a608987970b9 ("drm/i915: Wait for PSR exit before checking for vblank evasion")
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Tarun Vyas <tarun.vyas@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712053323.26266-1-tarun.vyas@intel.com
---
 drivers/gpu/drm/i915/intel_drv.h    | 2 +-
 drivers/gpu/drm/i915/intel_psr.c    | 7 ++++++-
 drivers/gpu/drm/i915/intel_sprite.c | 2 +-
 3 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index e283e9e901c2..1375cad8bf83 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1922,7 +1922,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
 void intel_psr_irq_control(struct drm_i915_private *dev_priv, bool debug);
 void intel_psr_irq_handler(struct drm_i915_private *dev_priv, u32 psr_iir);
 void intel_psr_short_pulse(struct intel_dp *intel_dp);
-int intel_psr_wait_for_idle(struct drm_i915_private *dev_priv);
+int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state);
 
 /* intel_runtime_pm.c */
 int intel_power_domains_init(struct drm_i915_private *);
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index 23acc9ac8d4d..e97db5dd75b1 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -717,11 +717,16 @@ void intel_psr_disable(struct intel_dp *intel_dp,
 	cancel_work_sync(&dev_priv->psr.work);
 }
 
-int intel_psr_wait_for_idle(struct drm_i915_private *dev_priv)
+int intel_psr_wait_for_idle(const struct intel_crtc_state *new_crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(new_crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	i915_reg_t reg;
 	u32 mask;
 
+	if (!new_crtc_state->has_psr)
+		return 0;
+
 	/*
 	 * The sole user right now is intel_pipe_update_start(),
 	 * which won't race with psr_enable/disable, which is
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index e2328d0402d8..3a4a26dd770f 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -118,7 +118,7 @@ void intel_pipe_update_start(const struct intel_crtc_state *new_crtc_state)
 	 * VBL interrupts will start the PSR exit and prevent a PSR
 	 * re-entry as well.
 	 */
-	if (CAN_PSR(dev_priv) && intel_psr_wait_for_idle(dev_priv))
+	if (intel_psr_wait_for_idle(new_crtc_state))
 		DRM_ERROR("PSR idle timed out, atomic update may fail\n");
 
 	local_irq_disable();
-- 
cgit v1.2.3


From 5b7b30864d1d18605e9ad81f2cd1eee6927399df Mon Sep 17 00:00:00 2001
From: Dhinakaran Pandiyan <dhinakaran.pandiyan@gmail.com>
Date: Wed, 4 Jul 2018 17:31:21 -0700
Subject: drm/i915/psr: Split sink status into a separate debugfs node
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows to read i915_edp_psr_status from tests without triggering
any AUX communication. Take this opportunity to move this under the
eDP-1 connector directory as the status we print is of the sink.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Suggested-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705003121.2478-1-dhinakaran.pandiyan@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c | 69 +++++++++++++++++++++----------------
 1 file changed, 39 insertions(+), 30 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 099f97ef2303..54509e44a856 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2592,6 +2592,41 @@ static const struct file_operations i915_guc_log_relay_fops = {
 	.release = i915_guc_log_relay_release,
 };
 
+static int i915_psr_sink_status_show(struct seq_file *m, void *data)
+{
+	u8 val;
+	static const char * const sink_status[] = {
+		"inactive",
+		"transition to active, capture and display",
+		"active, display from RFB",
+		"active, capture and display on sink device timings",
+		"transition to inactive, capture and display, timing re-sync",
+		"reserved",
+		"reserved",
+		"sink internal error",
+	};
+	struct drm_connector *connector = m->private;
+	struct intel_dp *intel_dp =
+		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+
+	if (connector->status != connector_status_connected)
+		return -ENODEV;
+
+	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) == 1) {
+		const char *str = "unknown";
+
+		val &= DP_PSR_SINK_STATE_MASK;
+		if (val < ARRAY_SIZE(sink_status))
+			str = sink_status[val];
+		seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, str);
+	} else {
+		DRM_ERROR("dpcd read (at %u) failed\n", DP_PSR_STATUS);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(i915_psr_sink_status);
+
 static void
 psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
 {
@@ -2643,26 +2678,6 @@ psr_source_status(struct drm_i915_private *dev_priv, struct seq_file *m)
 	seq_printf(m, "Source PSR status: 0x%x [%s]\n", psr_status, "unknown");
 }
 
-static const char *psr_sink_status(u8 val)
-{
-	static const char * const sink_status[] = {
-		"inactive",
-		"transition to active, capture and display",
-		"active, display from RFB",
-		"active, capture and display on sink device timings",
-		"transition to inactive, capture and display, timing re-sync",
-		"reserved",
-		"reserved",
-		"sink internal error"
-	};
-
-	val &= DP_PSR_SINK_STATE_MASK;
-	if (val < ARRAY_SIZE(sink_status))
-		return sink_status[val];
-
-	return "unknown";
-}
-
 static int i915_edp_psr_status(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -2706,15 +2721,6 @@ static int i915_edp_psr_status(struct seq_file *m, void *data)
 	}
 
 	psr_source_status(dev_priv, m);
-
-	if (dev_priv->psr.enabled) {
-		struct drm_dp_aux *aux = &dev_priv->psr.enabled->aux;
-		u8 val;
-
-		if (drm_dp_dpcd_readb(aux, DP_PSR_STATUS, &val) == 1)
-			seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val,
-				   psr_sink_status(val));
-	}
 	mutex_unlock(&dev_priv->psr.lock);
 
 	if (READ_ONCE(dev_priv->psr.debug)) {
@@ -4968,9 +4974,12 @@ int i915_debugfs_connector_add(struct drm_connector *connector)
 		debugfs_create_file("i915_dpcd", S_IRUGO, root,
 				    connector, &i915_dpcd_fops);
 
-	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP)
+	if (connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
 		debugfs_create_file("i915_panel_timings", S_IRUGO, root,
 				    connector, &i915_panel_fops);
+		debugfs_create_file("i915_psr_sink_status", S_IRUGO, root,
+				    connector, &i915_psr_sink_status_fops);
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 97fe222524f8fdbcc528b44d160d1df71d96af86 Mon Sep 17 00:00:00 2001
From: Ching Huang <ching2048@areca.com.tw>
Date: Mon, 9 Jul 2018 18:24:53 +0800
Subject: scsi: arcmsr: Fix error of resuming from hibernation for adapter type
 E

Fix error of resuming from hibernation for adapter type E.

Signed-off-by: Ching Huang <ching2048@areca.com.tw>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/arcmsr/arcmsr_hba.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/scsi/arcmsr/arcmsr_hba.c b/drivers/scsi/arcmsr/arcmsr_hba.c
index 732b5d9242f1..12316ef4c893 100644
--- a/drivers/scsi/arcmsr/arcmsr_hba.c
+++ b/drivers/scsi/arcmsr/arcmsr_hba.c
@@ -1061,6 +1061,13 @@ static int arcmsr_resume(struct pci_dev *pdev)
 	pci_set_master(pdev);
 	if (arcmsr_request_irq(pdev, acb) == FAILED)
 		goto controller_stop;
+	if (acb->adapter_type == ACB_ADAPTER_TYPE_E) {
+		writel(0, &acb->pmuE->host_int_status);
+		writel(ARCMSR_HBEMU_DOORBELL_SYNC, &acb->pmuE->iobound_doorbell);
+		acb->in_doorbell = 0;
+		acb->out_doorbell = 0;
+		acb->doneq_index = 0;
+	}
 	arcmsr_iop_init(acb);
 	arcmsr_init_get_devmap_timer(acb);
 	if (set_date_time)
-- 
cgit v1.2.3


From cb12ba356ce2a00cafd9e3f0c14d96fa9471ca44 Mon Sep 17 00:00:00 2001
From: Ching Huang <ching2048@areca.com.tw>
Date: Mon, 9 Jul 2018 18:28:02 +0800
Subject: scsi: arcmsr: Update driver version to v1.40.00.09-20180709

Update driver version to v1.40.00.09-20180709

Signed-off-by: Ching Huang <ching2048@areca.com.tw>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/arcmsr/arcmsr.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/arcmsr/arcmsr.h b/drivers/scsi/arcmsr/arcmsr.h
index 2e51ccc510e8..9c397a2794d6 100644
--- a/drivers/scsi/arcmsr/arcmsr.h
+++ b/drivers/scsi/arcmsr/arcmsr.h
@@ -49,7 +49,7 @@ struct device_attribute;
 #define ARCMSR_MAX_OUTSTANDING_CMD	1024
 #define ARCMSR_DEFAULT_OUTSTANDING_CMD	128
 #define ARCMSR_MIN_OUTSTANDING_CMD	32
-#define ARCMSR_DRIVER_VERSION		"v1.40.00.05-20180309"
+#define ARCMSR_DRIVER_VERSION		"v1.40.00.09-20180709"
 #define ARCMSR_SCSI_INITIATOR_ID	255
 #define ARCMSR_MAX_XFER_SECTORS		512
 #define ARCMSR_MAX_XFER_SECTORS_B	4096
-- 
cgit v1.2.3


From b15c9fd8bb38cc9a50d9b0a953c866c6091be08b Mon Sep 17 00:00:00 2001
From: Chaitra P B <chaitra.basappa@broadcom.com>
Date: Fri, 29 Jun 2018 10:58:10 -0400
Subject: scsi: mpt3sas: Fix for regression caused by sparse cleanups

Commit cf6bf9710cab ("scsi: mpt3sas: Bug fix for big endian systems") was
merged to address sparse warnings. However, the patch introduced a
regression on big endian since the code accidentally mixed I/O memory
accessors, which do endian swaps, and regular CPU loads and stores.

Do a partial revert of the offending commit.

[mkp: replaced commit message]

Signed-off-by: Chaitra P B <chaitra.basappa@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index dc41bd3de08a..17b6b0a3455f 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3321,7 +3321,7 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 					spinlock_t *writeq_lock)
 {
 	unsigned long flags;
-	__u64 data_out = b;
+	__u64 data_out = cpu_to_le64(b);
 
 	spin_lock_irqsave(writeq_lock, flags);
 	writel((u32)(data_out), addr);
@@ -3344,7 +3344,7 @@ _base_mpi_ep_writeq(__u64 b, volatile void __iomem *addr,
 static inline void
 _base_writeq(__u64 b, volatile void __iomem *addr, spinlock_t *writeq_lock)
 {
-	writeq(b, addr);
+	writeq(cpu_to_le64(b), addr);
 }
 #else
 static inline void
@@ -5215,7 +5215,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 
 	/* send message 32-bits at a time */
 	for (i = 0, failed = 0; i < request_bytes/4 && !failed; i++) {
-		writel((u32)(request[i]), &ioc->chip->Doorbell);
+		writel(cpu_to_le32(request[i]), &ioc->chip->Doorbell);
 		if ((_base_wait_for_doorbell_ack(ioc, 5)))
 			failed = 1;
 	}
@@ -5236,7 +5236,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 	}
 
 	/* read the first two 16-bits, it gives the total length of the reply */
-	reply[0] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[0] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 	if ((_base_wait_for_doorbell_int(ioc, 5))) {
@@ -5245,7 +5245,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 			ioc->name, __LINE__);
 		return -EFAULT;
 	}
-	reply[1] = (u16)(readl(&ioc->chip->Doorbell)
+	reply[1] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 	    & MPI2_DOORBELL_DATA_MASK);
 	writel(0, &ioc->chip->HostInterruptStatus);
 
@@ -5259,7 +5259,7 @@ _base_handshake_req_reply_wait(struct MPT3SAS_ADAPTER *ioc, int request_bytes,
 		if (i >=  reply_bytes/2) /* overflow case */
 			readl(&ioc->chip->Doorbell);
 		else
-			reply[i] = (u16)(readl(&ioc->chip->Doorbell)
+			reply[i] = le16_to_cpu(readl(&ioc->chip->Doorbell)
 			    & MPI2_DOORBELL_DATA_MASK);
 		writel(0, &ioc->chip->HostInterruptStatus);
 	}
-- 
cgit v1.2.3


From 9a26653b9525c08bc3d0a2c5c65721e4de3a5f6d Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 11 Jul 2018 10:09:27 +0200
Subject: scsi: libfc: fixup lockdep annotations

fc_rport_recv_plogi_req() needs the lport mutex to be held; the rport mutex
will be acquired in the function itself.

Fixes: ee35624e1e4e ("scsi: libfc: Add lockdep annotations")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libfc/fc_rport.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 6aff9303251a..3d51a936f6d5 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -1835,7 +1835,7 @@ static void fc_rport_recv_plogi_req(struct fc_lport *lport,
 	struct fc_seq_els_data rjt_data;
 	u32 sid;
 
-	lockdep_assert_held(&rdata->rp_mutex);
+	lockdep_assert_held(&lport->lp_mutex);
 
 	sid = fc_frame_sid(fp);
 
-- 
cgit v1.2.3


From bc3d12b75491c0e844a8a7ce05e84de8f7d94822 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 11 Jul 2018 10:09:28 +0200
Subject: scsi: libfc: hold disc_mutex in fc_disc_stop_rports()

fc_disc_stop_rports() is calling fc_rport_logoff(), which in turn is
acquiring the rport mutex. So we cannot use RCU list traversal here, but
rather need to hold the disc mutex to avoid list corruption while
traversing.

Fixes: a407c593398c ("scsi: libfc: Fixup disc_mutex handling")
Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libfc/fc_disc.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/libfc/fc_disc.c b/drivers/scsi/libfc/fc_disc.c
index c1756b9b3ea5..f969a71348ef 100644
--- a/drivers/scsi/libfc/fc_disc.c
+++ b/drivers/scsi/libfc/fc_disc.c
@@ -62,20 +62,16 @@ static void fc_disc_restart(struct fc_disc *);
  */
 static void fc_disc_stop_rports(struct fc_disc *disc)
 {
-	struct fc_lport *lport;
 	struct fc_rport_priv *rdata;
 
-	lport = fc_disc_lport(disc);
-	lockdep_assert_held(&lport->lp_mutex);
+	lockdep_assert_held(&disc->disc_mutex);
 
-	rcu_read_lock();
-	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
+	list_for_each_entry(rdata, &disc->rports, peers) {
 		if (kref_get_unless_zero(&rdata->kref)) {
 			fc_rport_logoff(rdata);
 			kref_put(&rdata->kref, fc_rport_destroy);
 		}
 	}
-	rcu_read_unlock();
 }
 
 /**
@@ -699,7 +695,9 @@ static void fc_disc_stop(struct fc_lport *lport)
 
 	if (disc->pending)
 		cancel_delayed_work_sync(&disc->disc_work);
+	mutex_lock(&disc->disc_mutex);
 	fc_disc_stop_rports(disc);
+	mutex_unlock(&disc->disc_mutex);
 }
 
 /**
-- 
cgit v1.2.3


From bbc0f8bd88abefb0f27998f40a073634a3a2db89 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 11 Jul 2018 10:09:29 +0200
Subject: scsi: libfc: Add WARN_ON() when deleting rports

The discovery rport list handling is quite odd; the list traversal is
independent from the lifetime of the rport itself. This makes auditing
quite tricky, and the chance remains that we've missed something.  So this
patch adds a WARN_ON() statement when freeing an rport which is still part
of a list.

Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libfc/fc_rport.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/libfc/fc_rport.c b/drivers/scsi/libfc/fc_rport.c
index 3d51a936f6d5..d69531ab2db8 100644
--- a/drivers/scsi/libfc/fc_rport.c
+++ b/drivers/scsi/libfc/fc_rport.c
@@ -184,6 +184,7 @@ void fc_rport_destroy(struct kref *kref)
 	struct fc_rport_priv *rdata;
 
 	rdata = container_of(kref, struct fc_rport_priv, kref);
+	WARN_ON(!list_empty(&rdata->peers));
 	kfree_rcu(rdata, rcu);
 }
 EXPORT_SYMBOL(fc_rport_destroy);
-- 
cgit v1.2.3


From 0993ed922a3e62a66fcad41633985b127ecf71b0 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Wed, 11 Jul 2018 10:09:30 +0200
Subject: scsi: fcoe: hold disc_mutex when traversing rport lists

When calling either fc_rport_logon() or fc_rport_logoff() during rport list
traversal we cannot use the RCU list traversal, as either of these
functions will be taking a mutex.  So we need to partially revert commit
a407c593398c to take the disc mutex during traversal.  We should, however,
continue to use krefs to ensure that the rport object will not be freed
from under us.

Fixes: a407c593398c ("scsi: libfc: Fixup disc_mutex handling")
Signed-off-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/fcoe/fcoe_ctlr.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index ea23c8dffc25..b42bfc790e04 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -2175,15 +2175,13 @@ static void fcoe_ctlr_disc_stop_locked(struct fc_lport *lport)
 {
 	struct fc_rport_priv *rdata;
 
-	rcu_read_lock();
+	mutex_lock(&lport->disc.disc_mutex);
 	list_for_each_entry_rcu(rdata, &lport->disc.rports, peers) {
 		if (kref_get_unless_zero(&rdata->kref)) {
 			fc_rport_logoff(rdata);
 			kref_put(&rdata->kref, fc_rport_destroy);
 		}
 	}
-	rcu_read_unlock();
-	mutex_lock(&lport->disc.disc_mutex);
 	lport->disc.disc_callback = NULL;
 	mutex_unlock(&lport->disc.disc_mutex);
 }
@@ -2712,7 +2710,7 @@ static unsigned long fcoe_ctlr_vn_age(struct fcoe_ctlr *fip)
 	unsigned long deadline;
 
 	next_time = jiffies + msecs_to_jiffies(FIP_VN_BEACON_INT * 10);
-	rcu_read_lock();
+	mutex_lock(&lport->disc.disc_mutex);
 	list_for_each_entry_rcu(rdata, &lport->disc.rports, peers) {
 		if (!kref_get_unless_zero(&rdata->kref))
 			continue;
@@ -2733,7 +2731,7 @@ static unsigned long fcoe_ctlr_vn_age(struct fcoe_ctlr *fip)
 			next_time = deadline;
 		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	rcu_read_unlock();
+	mutex_unlock(&lport->disc.disc_mutex);
 	return next_time;
 }
 
@@ -3080,8 +3078,6 @@ static void fcoe_ctlr_vn_disc(struct fcoe_ctlr *fip)
 	mutex_lock(&disc->disc_mutex);
 	callback = disc->pending ? disc->disc_callback : NULL;
 	disc->pending = 0;
-	mutex_unlock(&disc->disc_mutex);
-	rcu_read_lock();
 	list_for_each_entry_rcu(rdata, &disc->rports, peers) {
 		if (!kref_get_unless_zero(&rdata->kref))
 			continue;
@@ -3090,7 +3086,7 @@ static void fcoe_ctlr_vn_disc(struct fcoe_ctlr *fip)
 			fc_rport_login(rdata);
 		kref_put(&rdata->kref, fc_rport_destroy);
 	}
-	rcu_read_unlock();
+	mutex_unlock(&disc->disc_mutex);
 	if (callback)
 		callback(lport, DISC_EV_SUCCESS);
 }
-- 
cgit v1.2.3


From 920447f138917d8d5b830b752cff5e5f747f67e8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 14:37:37 +0200
Subject: scsi: snic: fix printing time intervals

We don't want to use 'struct timespec' because of the y2038 overflow
problem. The overflow is not actually an issue here, but it's easy to
replace with 'timespec64' for consistency. However, it's worth pointing out
that nanosecond values have nine digits, not eight or ten, so I'm fixing
the format strings accordingly as well.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/snic/snic_debugfs.c | 10 +++++-----
 drivers/scsi/snic/snic_trc.c     |  6 +++---
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/snic/snic_debugfs.c b/drivers/scsi/snic/snic_debugfs.c
index 269ddf791a73..0abe17c1a73b 100644
--- a/drivers/scsi/snic/snic_debugfs.c
+++ b/drivers/scsi/snic/snic_debugfs.c
@@ -200,7 +200,7 @@ snic_stats_show(struct seq_file *sfp, void *data)
 {
 	struct snic *snic = (struct snic *) sfp->private;
 	struct snic_stats *stats = &snic->s_stats;
-	struct timespec last_isr_tms, last_ack_tms;
+	struct timespec64 last_isr_tms, last_ack_tms;
 	u64 maxio_tm;
 	int i;
 
@@ -312,12 +312,12 @@ snic_stats_show(struct seq_file *sfp, void *data)
 		   "\t\t Other Statistics\n"
 		   "\n---------------------------------------------\n");
 
-	jiffies_to_timespec(stats->misc.last_isr_time, &last_isr_tms);
-	jiffies_to_timespec(stats->misc.last_ack_time, &last_ack_tms);
+	jiffies_to_timespec64(stats->misc.last_isr_time, &last_isr_tms);
+	jiffies_to_timespec64(stats->misc.last_ack_time, &last_ack_tms);
 
 	seq_printf(sfp,
-		   "Last ISR Time               : %llu (%8lu.%8lu)\n"
-		   "Last Ack Time               : %llu (%8lu.%8lu)\n"
+		   "Last ISR Time               : %llu (%8llu.%09lu)\n"
+		   "Last Ack Time               : %llu (%8llu.%09lu)\n"
 		   "Ack ISRs                    : %llu\n"
 		   "IO Cmpl ISRs                : %llu\n"
 		   "Err Notify ISRs             : %llu\n"
diff --git a/drivers/scsi/snic/snic_trc.c b/drivers/scsi/snic/snic_trc.c
index f00ebf4717e0..fc60c933d6c0 100644
--- a/drivers/scsi/snic/snic_trc.c
+++ b/drivers/scsi/snic/snic_trc.c
@@ -65,12 +65,12 @@ static int
 snic_fmt_trc_data(struct snic_trc_data *td, char *buf, int buf_sz)
 {
 	int len = 0;
-	struct timespec tmspec;
+	struct timespec64 tmspec;
 
-	jiffies_to_timespec(td->ts, &tmspec);
+	jiffies_to_timespec64(td->ts, &tmspec);
 
 	len += snprintf(buf, buf_sz,
-			"%lu.%10lu %-25s %3d %4x %16llx %16llx %16llx %16llx %16llx\n",
+			"%llu.%09lu %-25s %3d %4x %16llx %16llx %16llx %16llx %16llx\n",
 			tmspec.tv_sec,
 			tmspec.tv_nsec,
 			td->fn,
-- 
cgit v1.2.3


From 75aa3209c945fc711163ff1ecbc031bd13962a9d Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Thu, 12 Jul 2018 13:35:42 -0400
Subject: scsi: scsi_debug: skip long delays when ndelay small

A test program's runtime became impractically long since any non zero
ndelay (e.g. 1 nanosec) caused Start Stop Unit to delay over 8 magnitudes
greater than other commands. This patch skips long delays (on Start Stop
Unit and Synchronize Cache) if ndelay is less than or equal to 10
microsecs.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_debug.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 24d7496cd9e2..4dda192b8fba 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -5790,11 +5790,13 @@ static int scsi_debug_queuecommand(struct Scsi_Host *shost,
 fini:
 	if (F_DELAY_OVERR & flags)
 		return schedule_resp(scp, devip, errsts, pfp, 0, 0);
-	else if ((sdebug_jdelay || sdebug_ndelay) && (flags & F_LONG_DELAY)) {
+	else if ((flags & F_LONG_DELAY) && (sdebug_jdelay > 0 ||
+					    sdebug_ndelay > 10000)) {
 		/*
-		 * If any delay is active, for F_SSU_DELAY want at least 1
-		 * second and if sdebug_jdelay>0 want a long delay of that
-		 * many seconds; for F_SYNC_DELAY want 1/20 of that.
+		 * Skip long delays if ndelay <= 10 microseconds. Otherwise
+		 * for Start Stop Unit (SSU) want at least 1 second delay and
+		 * if sdebug_jdelay>1 want a long delay of that many seconds.
+		 * For Synchronize Cache want 1/20 of SSU's delay.
 		 */
 		int jdelay = (sdebug_jdelay < 2) ? 1 : sdebug_jdelay;
 		int denom = (flags & F_SYNC_DELAY) ? 20 : 1;
-- 
cgit v1.2.3


From 521715f903783e324b0067c521baf4f9776d7561 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Wed, 11 Jul 2018 15:00:50 -0700
Subject: drm/i915/psr: Remove useless function calls.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PSR is no longer supported on VLV/CHV so this is just dead code.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711220050.21809-1-rodrigo.vivi@intel.com
---
 drivers/gpu/drm/i915/intel_dp.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 5be07e1d816d..7d40bfcb1bbb 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -2830,10 +2830,6 @@ static void vlv_disable_dp(struct intel_encoder *encoder,
 			   const struct intel_crtc_state *old_crtc_state,
 			   const struct drm_connector_state *old_conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-
-	intel_psr_disable(intel_dp, old_crtc_state);
-
 	intel_disable_dp(encoder, old_crtc_state, old_conn_state);
 }
 
@@ -3046,10 +3042,7 @@ static void vlv_enable_dp(struct intel_encoder *encoder,
 			  const struct intel_crtc_state *pipe_config,
 			  const struct drm_connector_state *conn_state)
 {
-	struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
-
 	intel_edp_backlight_on(pipe_config, conn_state);
-	intel_psr_enable(intel_dp, pipe_config);
 }
 
 static void g4x_pre_enable_dp(struct intel_encoder *encoder,
-- 
cgit v1.2.3


From 9306b62b43c460923ba4a32b66aeb7d0e4c02adf Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Wed, 11 Jul 2018 22:27:15 -0700
Subject: drm/i915/psr: Remove few mod parameters option.

Reduce the module parameter to enable or disable.

The link stand by vs full link off was used only once.

And it was actually masking another bug fixed by commit
'84bb2916a683 ("drm/i915/psr: Check for SET_POWER_CAPABLE
bit at PSR init time.")'

So, let's remove these options for now. End goal is to
fully remove the mod param, moving it to a debugfs
interface in upcoming patches.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Tarun Vyas <tarun.vyas@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712052715.8177-1-rodrigo.vivi@intel.com
---
 drivers/gpu/drm/i915/i915_params.c |  2 +-
 drivers/gpu/drm/i915/intel_psr.c   | 10 ----------
 2 files changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 49fcc4679db6..817576701ed7 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -92,7 +92,7 @@ i915_param_named_unsafe(enable_ppgtt, int, 0400,
 
 i915_param_named_unsafe(enable_psr, int, 0600,
 	"Enable PSR "
-	"(0=disabled, 1=enabled - link mode chosen per-platform, 2=force link-standby mode, 3=force link-off mode) "
+	"(0=disabled, 1=enabled) "
 	"Default: -1 (use per-chip default)");
 
 i915_param_named_unsafe(alpha_support, bool, 0400,
diff --git a/drivers/gpu/drm/i915/intel_psr.c b/drivers/gpu/drm/i915/intel_psr.c
index e97db5dd75b1..4bd5768731ee 100644
--- a/drivers/gpu/drm/i915/intel_psr.c
+++ b/drivers/gpu/drm/i915/intel_psr.c
@@ -971,16 +971,6 @@ void intel_psr_init(struct drm_i915_private *dev_priv)
 		/* For new platforms let's respect VBT back again */
 		dev_priv->psr.link_standby = dev_priv->vbt.psr.full_link;
 
-	/* Override link_standby x link_off defaults */
-	if (i915_modparams.enable_psr == 2 && !dev_priv->psr.link_standby) {
-		DRM_DEBUG_KMS("PSR: Forcing link standby\n");
-		dev_priv->psr.link_standby = true;
-	}
-	if (i915_modparams.enable_psr == 3 && dev_priv->psr.link_standby) {
-		DRM_DEBUG_KMS("PSR: Forcing main link off\n");
-		dev_priv->psr.link_standby = false;
-	}
-
 	INIT_WORK(&dev_priv->psr.work, intel_psr_work);
 	mutex_init(&dev_priv->psr.lock);
 }
-- 
cgit v1.2.3


From f7cf1a1829f9ff776fb5504c9c5ffa0e9d2baf79 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Thu, 12 Jul 2018 23:54:26 -0700
Subject: drm/i915: Update DRIVER_DATE to 20180712

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index a6c6decd0546..1616e994b9a5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -86,8 +86,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180709"
-#define DRIVER_TIMESTAMP	1531175967
+#define DRIVER_DATE		"20180712"
+#define DRIVER_TIMESTAMP	1531464866
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
-- 
cgit v1.2.3


From b23ec59926faf05b0c43680d05671c484e810ac4 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 9 Jul 2018 21:47:27 +0300
Subject: gpiolib: Mark gpio_suffixes array with __maybe_unused
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since we put static variable to a header file it's copied to each module
that includes the header. But not all of them are actually used it.

Mark gpio_suffixes array with __maybe_unused to hide a compiler warning:

In file included from
drivers/gpio/gpiolib-legacy.c:6:0:
drivers/gpio/gpiolib.h:95:27: warning: ‘gpio_suffixes’ defined but not used [-Wunused-const-variable=]
 static const char * const gpio_suffixes[] = { "gpios", "gpio" };
                           ^~~~~~~~~~~~~
In file included from drivers/gpio/gpiolib-devprop.c:17:0:
drivers/gpio/gpiolib.h:95:27: warning: ‘gpio_suffixes’ defined but not used [-Wunused-const-variable=]
 static const char * const gpio_suffixes[] = { "gpios", "gpio" };
                           ^~~~~~~~~~~~~

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 1a8e20363861..a7e49fef73d4 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -92,7 +92,7 @@ struct acpi_gpio_info {
 };
 
 /* gpio suffixes used for ACPI and device tree lookup */
-static const char * const gpio_suffixes[] = { "gpios", "gpio" };
+static __maybe_unused const char * const gpio_suffixes[] = { "gpios", "gpio" };
 
 #ifdef CONFIG_OF_GPIO
 struct gpio_desc *of_find_gpio(struct device *dev,
-- 
cgit v1.2.3


From 809567905b5f10f73828b3fab3024bfaaf967f32 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 9 Jul 2018 21:47:21 +0300
Subject: gpiolib: Consistent use of ->get_direction() inside gpiolib

Two out of three calls to ->get_direction (excluding, of course,
gpiod_get_direction() itself) are using gpiod_get_direction() and
one is still open coded.

Replace the latter one to use same API for sake of consistency.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index a9a290999990..cbc071423f30 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3260,18 +3260,13 @@ int gpiochip_lock_as_irq(struct gpio_chip *chip, unsigned int offset)
 	 * behind our back
 	 */
 	if (!chip->can_sleep && chip->get_direction) {
-		int dir = chip->get_direction(chip, offset);
+		int dir = gpiod_get_direction(desc);
 
 		if (dir < 0) {
 			chip_err(chip, "%s: cannot get GPIO direction\n",
 				 __func__);
 			return dir;
 		}
-
-		if (dir)
-			clear_bit(FLAG_IS_OUT, &desc->flags);
-		else
-			set_bit(FLAG_IS_OUT, &desc->flags);
 	}
 
 	if (test_bit(FLAG_IS_OUT, &desc->flags)) {
-- 
cgit v1.2.3


From c29677312d2532f7a7d49623539e435df6d64d22 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 9 Jul 2018 16:56:03 +0200
Subject: gpio: aspeed: fix compile testing warning

Gcc cannot always see that BUG_ON(1) is guaranteed to not
return, so we get a warning message in some configurations:

drivers/gpio/gpio-aspeed.c: In function 'bank_reg':
drivers/gpio/gpio-aspeed.c:244:1: error: control reaches end of non-void function [-Werror=return-type]

Using a plain BUG() is easier here and avoids the problem.

Fixes: 44ddf559d579 ("gpio: aspeed: Rework register type accessors")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-aspeed.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index 1e00f4045f9d..2342e154029b 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -240,7 +240,7 @@ static inline void __iomem *bank_reg(struct aspeed_gpio *gpio,
 	case reg_cmdsrc1:
 		return gpio->base + bank->cmdsrc_regs + GPIO_CMDSRC_1;
 	}
-	BUG_ON(1);
+	BUG();
 }
 
 #define GPIO_BANK(x)	((x) >> 5)
-- 
cgit v1.2.3


From 9dcc7570b06836a9aa497bb921ff73c6b319d94c Mon Sep 17 00:00:00 2001
From: Dong Jia Shi <bjsdjshi@linux.ibm.com>
Date: Fri, 6 Jul 2018 08:35:24 +0200
Subject: MAINTAINERS: Remove myself as maintainer

I am leaving IBM and will move on to other working area,
so remove myself as a vfio-ccw maintainer.

Signed-off-by: Dong Jia Shi <bjsdjshi@linux.ibm.com>

Message-Id: <20180706015743.41810-1-bjsdjshi@linux.ibm.com>
Signed-off-by: Cornelia Huck <cohuck@redhat.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 6cfd16790add..6f690fa7bd8a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12384,7 +12384,6 @@ F:	drivers/pci/hotplug/s390_pci_hpc.c
 
 S390 VFIO-CCW DRIVER
 M:	Cornelia Huck <cohuck@redhat.com>
-M:	Dong Jia Shi <bjsdjshi@linux.ibm.com>
 M:	Halil Pasic <pasic@linux.ibm.com>
 L:	linux-s390@vger.kernel.org
 L:	kvm@vger.kernel.org
-- 
cgit v1.2.3


From 7a9a5df0a54e4b2a36a7984800d0a064b39fb3f8 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jul 2018 17:18:47 +0200
Subject: gpio: mt7621: add OF_GPIO dependency

Compile-testing the driver fails unless OF_GPIO is enabled:

drivers/gpio/gpio-mt7621.c: In function 'mediatek_gpio_bank_probe':
drivers/gpio/gpio-mt7621.c:228:10: error: 'struct gpio_chip' has no member named 'of_node'

Fixes: 4ba9c3afda41 ("gpio: mt7621: Add a driver for MT7621")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 836aa2173e44..7429b30e61b0 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -362,6 +362,7 @@ config GPIO_MPC8XXX
 config GPIO_MT7621
 	bool "Mediatek MT7621 GPIO Support"
 	depends on SOC_MT7620 || SOC_MT7621 || COMPILE_TEST
+	depends on OF_GPIO
 	select GPIO_GENERIC
 	select GPIOLIB_IRQCHIP
 	help
-- 
cgit v1.2.3


From 55fe0768f53ecc6c0a1bbfa3b0c688090cfa0360 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Jul 2018 21:20:27 +0100
Subject: drm/i915/guc: Protect against NULL client dereference in error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After aborting a module load, we may try and disable guc before we have
finished setting it. Long term plan is to ensure perfect onion unwind,
but in the short term we want to fix the oops to re-enable
drv_module_reload.

[  317.401239] BUG: unable to handle kernel NULL pointer dereference at 0000000000000030
[  317.401279] Oops: 0000 [#1] PREEMPT SMP PTI
[  317.401294] CPU: 5 PID: 4275 Comm: drv_module_relo Tainted: G     U            4.18.0-rc4-CI-CI_DRM_4476+ #1
[  317.401317] Hardware name: System manufacturer System Product Name/Z170M-PLUS, BIOS 3610 03/29/2018
[  317.401440] RIP: 0010:unreserve_doorbell+0x0/0x80 [i915]
[  317.401454] Code: bb e0 48 8b 35 21 4d 18 00 49 c7 c0 a8 e5 62 a0 b9 cc 00 00 00 48 c7 c2 d8 41 5f a0 48 c7 c7 c9 f6 53 a0 e8 a2 3d c2 e0 0f 0b <0f> b7 47 30 66 3d 00 01 74 20 48 8b 57 18 48 0f a3 82 40 05 00 00
[  317.401602] RSP: 0018:ffffc900003d3da0 EFLAGS: 00010246
[  317.401619] RAX: ffffffff8223b300 RBX: 0000000000000000 RCX: 0000000000000000
[  317.401636] RDX: 0000001fffffffc0 RSI: ffff880219f115f0 RDI: 0000000000000000
[  317.401654] RBP: ffff880219f11838 R08: 0000000000000000 R09: 0000000000000000
[  317.401671] R10: 0000000000000000 R11: 0000000000000000 R12: ffff880219f11300
[  317.401689] R13: ffff880219f17770 R14: ffff88022c1daef8 R15: ffffffffa06ae950
[  317.401707] FS:  00007febf77a9980(0000) GS:ffff880236d40000(0000) knlGS:0000000000000000
[  317.401727] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  317.401743] CR2: 0000000000000030 CR3: 0000000222072003 CR4: 00000000003606e0
[  317.401761] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  317.401779] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  317.401796] Call Trace:
[  317.401894]  guc_client_free+0x9/0x130 [i915]
[  317.401993]  intel_guc_submission_fini+0x50/0x90 [i915]
[  317.402092]  intel_uc_fini+0x34/0xd0 [i915]
[  317.402179]  i915_gem_fini+0x5c/0x100 [i915]
[  317.402249]  i915_driver_unload+0xd2/0x110 [i915]
[  317.402321]  i915_pci_remove+0x10/0x20 [i915]
[  317.402341]  pci_device_remove+0x36/0xb0
[  317.402357]  device_release_driver_internal+0x185/0x250
[  317.402374]  driver_detach+0x35/0x70
[  317.402390]  bus_remove_driver+0x53/0xd0
[  317.402404]  pci_unregister_driver+0x25/0xa0
[  317.402423]  __se_sys_delete_module+0x162/0x210
[  317.402439]  ? do_syscall_64+0xd/0x190
[  317.402454]  do_syscall_64+0x55/0x190
[  317.402470]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  317.402485] RIP: 0033:0x7febf6e5d1b7
[  317.402496] Code: 73 01 c3 48 8b 0d d1 8c 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d a1 8c 2c 00 f7 d8 64 89 01 48
[  317.402646] RSP: 002b:00007fffb5e72798 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0
[  317.402667] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007febf6e5d1b7
[  317.402686] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 0000562da1addd98
[  317.402703] RBP: 0000562da1addd30 R08: 0000562da1addd9c R09: 00007fffb5e727d8
[  317.402721] R10: 00007fffb5e71794 R11: 0000000000000206 R12: 0000562da0ff6470

Testcase: igt/drv_module_reload/basic-reload-inject
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712202027.19801-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index cd51be8ff025..22367131d6a1 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -1128,7 +1128,8 @@ static void guc_clients_destroy(struct intel_guc *guc)
 		guc_client_free(client);
 
 	client = fetch_and_zero(&guc->execbuf_client);
-	guc_client_free(client);
+	if (client)
+		guc_client_free(client);
 }
 
 /*
-- 
cgit v1.2.3


From 9506755633d0b32ef76f67c345000178e9b0dfc4 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 11 Jul 2018 13:19:38 +0000
Subject: gpio: pxa: Fix potential NULL dereference

platform_get_resource() may fail and return NULL, so we should
better check it's return value to avoid a NULL pointer dereference
a bit later in the code.

This is detected by Coccinelle semantic patch.

@@
expression pdev, res, n, t, e, e1, e2;
@@

res = platform_get_resource(pdev, t, n);
+ if (!res)
+   return -EINVAL;
... when != res == NULL
e = devm_ioremap(e1, res->start, e2);

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-pxa.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index 1e66f808051c..0d09a4fcef49 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -646,6 +646,8 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	pchip->irq0 = irq0;
 	pchip->irq1 = irq1;
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
 	gpio_reg_base = devm_ioremap(&pdev->dev, res->start,
 				     resource_size(res));
 	if (!gpio_reg_base)
-- 
cgit v1.2.3


From a1a6fa3dcda11d068f5e629c7a18ef7282bf0c7d Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Fri, 13 Jul 2018 10:06:25 +0200
Subject: drm/stm: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Philippe Cornu <philippe.cornu@st.com>
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180713080625.18256-1-tzimmermann@suse.de
---
 drivers/gpu/drm/stm/drv.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c
index 8698e08313e1..f2021b23554d 100644
--- a/drivers/gpu/drm/stm/drv.c
+++ b/drivers/gpu/drm/stm/drv.c
@@ -148,16 +148,16 @@ static int stm_drm_platform_probe(struct platform_device *pdev)
 
 	ret = drv_load(ddev);
 	if (ret)
-		goto err_unref;
+		goto err_put;
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
-		goto err_unref;
+		goto err_put;
 
 	return 0;
 
-err_unref:
-	drm_dev_unref(ddev);
+err_put:
+	drm_dev_put(ddev);
 
 	return ret;
 }
@@ -170,7 +170,7 @@ static int stm_drm_platform_remove(struct platform_device *pdev)
 
 	drm_dev_unregister(ddev);
 	drv_unload(ddev);
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 
 	return 0;
 }
-- 
cgit v1.2.3


From a08eac479b4e6de3700d8d1c7c664d4ffc0535c7 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Thu, 12 Jul 2018 17:26:39 +0200
Subject: drm/sti: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Acked-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712152639.30934-1-tzimmermann@suse.de
---
 drivers/gpu/drm/sti/sti_drv.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/sti/sti_drv.c b/drivers/gpu/drm/sti/sti_drv.c
index 90c46b49c931..832fc43960ee 100644
--- a/drivers/gpu/drm/sti/sti_drv.c
+++ b/drivers/gpu/drm/sti/sti_drv.c
@@ -224,7 +224,7 @@ static int sti_bind(struct device *dev)
 
 	ret = sti_init(ddev);
 	if (ret)
-		goto err_drm_dev_unref;
+		goto err_drm_dev_put;
 
 	ret = component_bind_all(ddev->dev, ddev);
 	if (ret)
@@ -248,8 +248,8 @@ err_register:
 	drm_mode_config_cleanup(ddev);
 err_cleanup:
 	sti_cleanup(ddev);
-err_drm_dev_unref:
-	drm_dev_unref(ddev);
+err_drm_dev_put:
+	drm_dev_put(ddev);
 	return ret;
 }
 
@@ -259,7 +259,7 @@ static void sti_unbind(struct device *dev)
 
 	drm_dev_unregister(ddev);
 	sti_cleanup(ddev);
-	drm_dev_unref(ddev);
+	drm_dev_put(ddev);
 }
 
 static const struct component_master_ops sti_ops = {
-- 
cgit v1.2.3


From 1c22a252b3ded10d06acecdf8fb71f9dd8005c4f Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 12 Jul 2018 20:36:42 +0300
Subject: gpiolib: Join one line back for better readability

One line in gpiolib_dbg_show() still fits 80 characters, so,
join it to be like that in order to increase readability.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index cbc071423f30..2e2a6f8db405 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -4278,9 +4278,7 @@ static void gpiolib_dbg_show(struct seq_file *s, struct gpio_device *gdev)
 		seq_printf(s, " gpio-%-3d (%-20.20s|%-20.20s) %s %s %s",
 			gpio, gdesc->name ? gdesc->name : "", gdesc->label,
 			is_out ? "out" : "in ",
-			chip->get
-				? (chip->get(chip, i) ? "hi" : "lo")
-				: "?  ",
+			chip->get ? (chip->get(chip, i) ? "hi" : "lo") : "?  ",
 			is_irq ? "IRQ" : "   ");
 		seq_printf(s, "\n");
 	}
-- 
cgit v1.2.3


From ad817297418539b8895bbbf1d05ee3e5a211a117 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 12 Jul 2018 11:15:01 +0200
Subject: gpio: rcar: Implement .get_direction() callback

Allow gpiolib to read back the current I/O direction configuration by
implementing the .get_direction() callback.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Tested-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-rcar.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 2c9a4fc92dc6..55cc61086d99 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -278,6 +278,13 @@ static void gpio_rcar_free(struct gpio_chip *chip, unsigned offset)
 	pm_runtime_put(&p->pdev->dev);
 }
 
+static int gpio_rcar_get_direction(struct gpio_chip *chip, unsigned int offset)
+{
+	struct gpio_rcar_priv *p = gpiochip_get_data(chip);
+
+	return !(gpio_rcar_read(p, INOUTSEL) & BIT(offset));
+}
+
 static int gpio_rcar_direction_input(struct gpio_chip *chip, unsigned offset)
 {
 	gpio_rcar_config_general_input_output_mode(chip, offset, false);
@@ -461,6 +468,7 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 	gpio_chip = &p->gpio_chip;
 	gpio_chip->request = gpio_rcar_request;
 	gpio_chip->free = gpio_rcar_free;
+	gpio_chip->get_direction = gpio_rcar_get_direction;
 	gpio_chip->direction_input = gpio_rcar_direction_input;
 	gpio_chip->get = gpio_rcar_get;
 	gpio_chip->direction_output = gpio_rcar_direction_output;
-- 
cgit v1.2.3


From cf19fa2cfa4e9b5458b6f3503c5317dd1a2bfbae Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Thu, 12 Jul 2018 17:04:14 +0200
Subject: drm/client: Fix double free in error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes a static checker warning:

	drivers/gpu/drm/drm_client.c:289 drm_client_buffer_create()
	error: double free of 'buffer'

Extend drm_client_buffer_delete() to handle the case when there's no
dumb buffer attached and drop the extra kfree.

Fixes: c76f0f7cb546 ("drm: Begin an API for in-kernel clients")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712150414.46908-1-noralf@tronnes.org
---
 drivers/gpu/drm/drm_client.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
index 9b142f58d489..baff50a4c234 100644
--- a/drivers/gpu/drm/drm_client.c
+++ b/drivers/gpu/drm/drm_client.c
@@ -218,7 +218,9 @@ static void drm_client_buffer_delete(struct drm_client_buffer *buffer)
 	if (buffer->gem)
 		drm_gem_object_put_unlocked(buffer->gem);
 
-	drm_mode_destroy_dumb(dev, buffer->handle, buffer->client->file);
+	if (buffer->handle)
+		drm_mode_destroy_dumb(dev, buffer->handle, buffer->client->file);
+
 	kfree(buffer);
 }
 
@@ -243,7 +245,7 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u
 	dumb_args.bpp = drm_format_plane_cpp(format, 0) * 8;
 	ret = drm_mode_create_dumb(dev, &dumb_args, client->file);
 	if (ret)
-		goto err_free;
+		goto err_delete;
 
 	buffer->handle = dumb_args.handle;
 	buffer->pitch = dumb_args.pitch;
@@ -276,8 +278,6 @@ drm_client_buffer_create(struct drm_client_dev *client, u32 width, u32 height, u
 
 err_delete:
 	drm_client_buffer_delete(buffer);
-err_free:
-	kfree(buffer);
 
 	return ERR_PTR(ret);
 }
-- 
cgit v1.2.3


From f426d2b20f1cd63818873593031593e15c3db20b Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 3 Jul 2018 12:11:33 -0500
Subject: crypto: ccp - Fix command completion detection race

The wait_event() function is used to detect command completion.  The
interrupt handler will set the wait condition variable when the interrupt
is triggered.  However, the variable used for wait_event() is initialized
after the command has been submitted, which can create a race condition
with the interrupt handler and result in the wait_event() never returning.
Move the initialization of the wait condition variable to just before
command submission.

Fixes: 200664d5237f ("crypto: ccp: Add Secure Encrypted Virtualization (SEV) command support")
Cc: <stable@vger.kernel.org> # 4.16.x-
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Brijesh Singh <brijesh.singh@amd.com>
Acked-by: Gary R Hook <gary.hook@amd.com>
Acked-by: Gary R Hook <gary.hook@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/psp-dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index ff478d826d7d..973d683f80ee 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -84,8 +84,6 @@ done:
 
 static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg)
 {
-	psp->sev_int_rcvd = 0;
-
 	wait_event(psp->sev_int_queue, psp->sev_int_rcvd);
 	*reg = ioread32(psp->io_regs + PSP_CMDRESP);
 }
@@ -148,6 +146,8 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 	iowrite32(phys_lsb, psp->io_regs + PSP_CMDBUFF_ADDR_LO);
 	iowrite32(phys_msb, psp->io_regs + PSP_CMDBUFF_ADDR_HI);
 
+	psp->sev_int_rcvd = 0;
+
 	reg = cmd;
 	reg <<= PSP_CMDRESP_CMD_SHIFT;
 	reg |= PSP_CMDRESP_IOC;
-- 
cgit v1.2.3


From 015c8c85b721e93bcd6a3f4b5be63112ecb331c4 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 3 Jul 2018 12:11:42 -0500
Subject: crypto: ccp - Add psp enabled message when initialization succeeds

Add a dev_notice() message to the PSP initialization to report when the
PSP initialization has succeeded and the PSP is enabled.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Acked-by: Gary R Hook <gary.hook@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/psp-dev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index 973d683f80ee..91ef6ed2fea2 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -840,6 +840,8 @@ int psp_dev_init(struct sp_device *sp)
 	/* Enable interrupt */
 	iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTEN);
 
+	dev_notice(dev, "psp enabled\n");
+
 	return 0;
 
 e_irq:
-- 
cgit v1.2.3


From 03af91242c36f225c6fa79e143fad5f4c3624a46 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 3 Jul 2018 12:11:52 -0500
Subject: crypto: ccp - Remove unused #defines

Remove some unused #defines for register offsets that are not used. This
will lessen the changes required when register offsets change between
versions of the device.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Acked-by: Gary R Hook <gary.hook@amd.com>
Reviewed-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/psp-dev.c |  2 +-
 drivers/crypto/ccp/psp-dev.h | 10 +---------
 2 files changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index 91ef6ed2fea2..875756dd9024 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -65,7 +65,7 @@ static irqreturn_t psp_irq_handler(int irq, void *data)
 	status = ioread32(psp->io_regs + PSP_P2CMSG_INTSTS);
 
 	/* Check if it is command completion: */
-	if (!(status & BIT(PSP_CMD_COMPLETE_REG)))
+	if (!(status & PSP_CMD_COMPLETE))
 		goto done;
 
 	/* Check if it is SEV command completion: */
diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h
index c7e9098a233c..5d46a2bebfd1 100644
--- a/drivers/crypto/ccp/psp-dev.h
+++ b/drivers/crypto/ccp/psp-dev.h
@@ -36,19 +36,11 @@
 #define PSP_CMDBUFF_ADDR_HI             PSP_C2PMSG(57)
 #define PSP_FEATURE_REG			PSP_C2PMSG(63)
 
-#define PSP_P2CMSG(_num)		((_num) << 2)
-#define PSP_CMD_COMPLETE_REG		1
-#define PSP_CMD_COMPLETE		PSP_P2CMSG(PSP_CMD_COMPLETE_REG)
+#define PSP_CMD_COMPLETE		BIT(1)
 
 #define PSP_P2CMSG_INTEN		0x0110
 #define PSP_P2CMSG_INTSTS		0x0114
 
-#define PSP_C2PMSG_ATTR_0		0x0118
-#define PSP_C2PMSG_ATTR_1		0x011c
-#define PSP_C2PMSG_ATTR_2		0x0120
-#define PSP_C2PMSG_ATTR_3		0x0124
-#define PSP_P2CMSG_ATTR_0		0x0128
-
 #define PSP_CMDRESP_CMD_SHIFT		16
 #define PSP_CMDRESP_IOC			BIT(0)
 #define PSP_CMDRESP_RESP		BIT(31)
-- 
cgit v1.2.3


From ad01a984f512c42c9f4fe79d36b9cddbc6156a3f Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 3 Jul 2018 12:12:03 -0500
Subject: crypto: ccp - Support register differences between PSP devices

In preparation for adding a new PSP device ID that uses different register
offsets, add support to the PSP version data for register offset values.
And then update the code to use these new register offset values.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Acked-by: Gary R Hook <gary.hook@amd.com>
Reviewed-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/psp-dev.c | 24 ++++++++++++------------
 drivers/crypto/ccp/psp-dev.h |  9 ---------
 drivers/crypto/ccp/sp-dev.h  |  7 ++++++-
 drivers/crypto/ccp/sp-pci.c  |  7 ++++++-
 4 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index 875756dd9024..9b596387a09f 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -62,14 +62,14 @@ static irqreturn_t psp_irq_handler(int irq, void *data)
 	int reg;
 
 	/* Read the interrupt status: */
-	status = ioread32(psp->io_regs + PSP_P2CMSG_INTSTS);
+	status = ioread32(psp->io_regs + psp->vdata->intsts_reg);
 
 	/* Check if it is command completion: */
 	if (!(status & PSP_CMD_COMPLETE))
 		goto done;
 
 	/* Check if it is SEV command completion: */
-	reg = ioread32(psp->io_regs + PSP_CMDRESP);
+	reg = ioread32(psp->io_regs + psp->vdata->cmdresp_reg);
 	if (reg & PSP_CMDRESP_RESP) {
 		psp->sev_int_rcvd = 1;
 		wake_up(&psp->sev_int_queue);
@@ -77,7 +77,7 @@ static irqreturn_t psp_irq_handler(int irq, void *data)
 
 done:
 	/* Clear the interrupt status by writing the same value we read. */
-	iowrite32(status, psp->io_regs + PSP_P2CMSG_INTSTS);
+	iowrite32(status, psp->io_regs + psp->vdata->intsts_reg);
 
 	return IRQ_HANDLED;
 }
@@ -85,7 +85,7 @@ done:
 static void sev_wait_cmd_ioc(struct psp_device *psp, unsigned int *reg)
 {
 	wait_event(psp->sev_int_queue, psp->sev_int_rcvd);
-	*reg = ioread32(psp->io_regs + PSP_CMDRESP);
+	*reg = ioread32(psp->io_regs + psp->vdata->cmdresp_reg);
 }
 
 static int sev_cmd_buffer_len(int cmd)
@@ -143,15 +143,15 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
 	print_hex_dump_debug("(in):  ", DUMP_PREFIX_OFFSET, 16, 2, data,
 			     sev_cmd_buffer_len(cmd), false);
 
-	iowrite32(phys_lsb, psp->io_regs + PSP_CMDBUFF_ADDR_LO);
-	iowrite32(phys_msb, psp->io_regs + PSP_CMDBUFF_ADDR_HI);
+	iowrite32(phys_lsb, psp->io_regs + psp->vdata->cmdbuff_addr_lo_reg);
+	iowrite32(phys_msb, psp->io_regs + psp->vdata->cmdbuff_addr_hi_reg);
 
 	psp->sev_int_rcvd = 0;
 
 	reg = cmd;
 	reg <<= PSP_CMDRESP_CMD_SHIFT;
 	reg |= PSP_CMDRESP_IOC;
-	iowrite32(reg, psp->io_regs + PSP_CMDRESP);
+	iowrite32(reg, psp->io_regs + psp->vdata->cmdresp_reg);
 
 	/* wait for command completion */
 	sev_wait_cmd_ioc(psp, &reg);
@@ -789,7 +789,7 @@ static int sev_misc_init(struct psp_device *psp)
 static int sev_init(struct psp_device *psp)
 {
 	/* Check if device supports SEV feature */
-	if (!(ioread32(psp->io_regs + PSP_FEATURE_REG) & 1)) {
+	if (!(ioread32(psp->io_regs + psp->vdata->feature_reg) & 1)) {
 		dev_dbg(psp->dev, "device does not support SEV\n");
 		return 1;
 	}
@@ -817,11 +817,11 @@ int psp_dev_init(struct sp_device *sp)
 		goto e_err;
 	}
 
-	psp->io_regs = sp->io_map + psp->vdata->offset;
+	psp->io_regs = sp->io_map;
 
 	/* Disable and clear interrupts until ready */
-	iowrite32(0, psp->io_regs + PSP_P2CMSG_INTEN);
-	iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTSTS);
+	iowrite32(0, psp->io_regs + psp->vdata->inten_reg);
+	iowrite32(-1, psp->io_regs + psp->vdata->intsts_reg);
 
 	/* Request an irq */
 	ret = sp_request_psp_irq(psp->sp, psp_irq_handler, psp->name, psp);
@@ -838,7 +838,7 @@ int psp_dev_init(struct sp_device *sp)
 		sp->set_psp_master_device(sp);
 
 	/* Enable interrupt */
-	iowrite32(-1, psp->io_regs + PSP_P2CMSG_INTEN);
+	iowrite32(-1, psp->io_regs + psp->vdata->inten_reg);
 
 	dev_notice(dev, "psp enabled\n");
 
diff --git a/drivers/crypto/ccp/psp-dev.h b/drivers/crypto/ccp/psp-dev.h
index 5d46a2bebfd1..8b53a9674ecb 100644
--- a/drivers/crypto/ccp/psp-dev.h
+++ b/drivers/crypto/ccp/psp-dev.h
@@ -30,17 +30,8 @@
 
 #include "sp-dev.h"
 
-#define PSP_C2PMSG(_num)		((_num) << 2)
-#define PSP_CMDRESP			PSP_C2PMSG(32)
-#define PSP_CMDBUFF_ADDR_LO		PSP_C2PMSG(56)
-#define PSP_CMDBUFF_ADDR_HI             PSP_C2PMSG(57)
-#define PSP_FEATURE_REG			PSP_C2PMSG(63)
-
 #define PSP_CMD_COMPLETE		BIT(1)
 
-#define PSP_P2CMSG_INTEN		0x0110
-#define PSP_P2CMSG_INTSTS		0x0114
-
 #define PSP_CMDRESP_CMD_SHIFT		16
 #define PSP_CMDRESP_IOC			BIT(0)
 #define PSP_CMDRESP_RESP		BIT(31)
diff --git a/drivers/crypto/ccp/sp-dev.h b/drivers/crypto/ccp/sp-dev.h
index acb197b66ced..14398cad1625 100644
--- a/drivers/crypto/ccp/sp-dev.h
+++ b/drivers/crypto/ccp/sp-dev.h
@@ -44,7 +44,12 @@ struct ccp_vdata {
 };
 
 struct psp_vdata {
-	const unsigned int offset;
+	const unsigned int cmdresp_reg;
+	const unsigned int cmdbuff_addr_lo_reg;
+	const unsigned int cmdbuff_addr_hi_reg;
+	const unsigned int feature_reg;
+	const unsigned int inten_reg;
+	const unsigned int intsts_reg;
 };
 
 /* Structure to hold SP device data */
diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c
index f5f43c50698a..78c1e9d606c9 100644
--- a/drivers/crypto/ccp/sp-pci.c
+++ b/drivers/crypto/ccp/sp-pci.c
@@ -270,7 +270,12 @@ static int sp_pci_resume(struct pci_dev *pdev)
 
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
 static const struct psp_vdata psp_entry = {
-	.offset = 0x10500,
+	.cmdresp_reg		= 0x10580,
+	.cmdbuff_addr_lo_reg	= 0x105e0,
+	.cmdbuff_addr_hi_reg	= 0x105e4,
+	.feature_reg		= 0x105fc,
+	.inten_reg		= 0x10610,
+	.intsts_reg		= 0x10614,
 };
 #endif
 
-- 
cgit v1.2.3


From dcbc0c6e4aa1ef269179351ac615fd08ddefc849 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Tue, 3 Jul 2018 12:12:14 -0500
Subject: crypto: ccp - Add support for new CCP/PSP device ID

Add a new CCP/PSP PCI device ID and new PSP register offsets.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Acked-by: Gary R Hook <gary.hook@amd.com>
Reviewed-by: Brijesh Singh <brijesh.singh@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/sp-pci.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/crypto/ccp/sp-pci.c b/drivers/crypto/ccp/sp-pci.c
index 78c1e9d606c9..7da93e9bebed 100644
--- a/drivers/crypto/ccp/sp-pci.c
+++ b/drivers/crypto/ccp/sp-pci.c
@@ -269,7 +269,7 @@ static int sp_pci_resume(struct pci_dev *pdev)
 #endif
 
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
-static const struct psp_vdata psp_entry = {
+static const struct psp_vdata pspv1 = {
 	.cmdresp_reg		= 0x10580,
 	.cmdbuff_addr_lo_reg	= 0x105e0,
 	.cmdbuff_addr_hi_reg	= 0x105e4,
@@ -277,28 +277,46 @@ static const struct psp_vdata psp_entry = {
 	.inten_reg		= 0x10610,
 	.intsts_reg		= 0x10614,
 };
+
+static const struct psp_vdata pspv2 = {
+	.cmdresp_reg		= 0x10980,
+	.cmdbuff_addr_lo_reg	= 0x109e0,
+	.cmdbuff_addr_hi_reg	= 0x109e4,
+	.feature_reg		= 0x109fc,
+	.inten_reg		= 0x10690,
+	.intsts_reg		= 0x10694,
+};
 #endif
 
 static const struct sp_dev_vdata dev_vdata[] = {
-	{
+	{	/* 0 */
 		.bar = 2,
 #ifdef CONFIG_CRYPTO_DEV_SP_CCP
 		.ccp_vdata = &ccpv3,
 #endif
 	},
-	{
+	{	/* 1 */
 		.bar = 2,
 #ifdef CONFIG_CRYPTO_DEV_SP_CCP
 		.ccp_vdata = &ccpv5a,
 #endif
 #ifdef CONFIG_CRYPTO_DEV_SP_PSP
-		.psp_vdata = &psp_entry
+		.psp_vdata = &pspv1,
 #endif
 	},
-	{
+	{	/* 2 */
 		.bar = 2,
 #ifdef CONFIG_CRYPTO_DEV_SP_CCP
 		.ccp_vdata = &ccpv5b,
+#endif
+	},
+	{	/* 3 */
+		.bar = 2,
+#ifdef CONFIG_CRYPTO_DEV_SP_CCP
+		.ccp_vdata = &ccpv5a,
+#endif
+#ifdef CONFIG_CRYPTO_DEV_SP_PSP
+		.psp_vdata = &pspv2,
 #endif
 	},
 };
@@ -306,6 +324,7 @@ static const struct pci_device_id sp_pci_table[] = {
 	{ PCI_VDEVICE(AMD, 0x1537), (kernel_ulong_t)&dev_vdata[0] },
 	{ PCI_VDEVICE(AMD, 0x1456), (kernel_ulong_t)&dev_vdata[1] },
 	{ PCI_VDEVICE(AMD, 0x1468), (kernel_ulong_t)&dev_vdata[2] },
+	{ PCI_VDEVICE(AMD, 0x1486), (kernel_ulong_t)&dev_vdata[3] },
 	/* Last entry must be zero */
 	{ 0, }
 };
-- 
cgit v1.2.3


From d6be72ee2c77469d4fb391ccccc2ebc1b167a242 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 11:37:20 -0500
Subject: crypto: chtls - use 64-bit arithmetic instead of 32-bit

Cast *val* to u64 in order to give the compiler complete
information about the proper arithmetic to use.

Notice that such variable is used in a context that expects an
expression of type u64 (64 bits, unsigned) and the following
expression is currently being evaluated using 32-bit arithmetic:

val << bit_pos

Addresses-Coverity-ID: 1467425 ("Unintentional integer overflow")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/chelsio/chtls/chtls_hw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/chelsio/chtls/chtls_hw.c b/drivers/crypto/chelsio/chtls/chtls_hw.c
index 55d50140f9e5..490960755864 100644
--- a/drivers/crypto/chelsio/chtls/chtls_hw.c
+++ b/drivers/crypto/chelsio/chtls/chtls_hw.c
@@ -97,7 +97,7 @@ static int chtls_set_tcb_field(struct sock *sk, u16 word, u64 mask, u64 val)
 int chtls_set_tcb_tflag(struct sock *sk, unsigned int bit_pos, int val)
 {
 	return chtls_set_tcb_field(sk, 1, 1ULL << bit_pos,
-				   val << bit_pos);
+				   (u64)val << bit_pos);
 }
 
 static int chtls_set_tcb_keyid(struct sock *sk, int keyid)
-- 
cgit v1.2.3


From 90c3e2198777aaa355b6994a31a79c636c8d4306 Mon Sep 17 00:00:00 2001
From: Clint Taylor <clinton.a.taylor@intel.com>
Date: Tue, 10 Jul 2018 13:02:05 -0700
Subject: drm/i915/glk: Add Quirk for GLK NUC HDMI port issues.

On GLK NUC platforms the HDMI retiming buffer needs additional disabled
time to correctly sync to a faster incoming signal.

When measured on a scope the highspeed lines of the HDMI clock turn off
 for ~400uS during a normal resolution change. The HDMI retimer on the
 GLK NUC appears to require at least a full frame of quiet time before a
new faster clock can be correctly sync'd. Wait 100ms due to msleep
inaccuracies while waiting for a completed frame. Add a quirk to the
driver for GLK boards that use ITE66317 HDMI retimers.

V2: Add more devices to the quirk list
V3: Delay increased to 100ms, check to confirm crtc type is HDMI.
V4: crtc type check extended to include _DDI and whitespace fixes
v5: Fix white spaces, remove the macro for delay. Revert the crtc type
    check introduced in v4.

Cc: Imre Deak <imre.deak@intel.com>
Cc: <stable@vger.kernel.org> # v4.14+
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105887
Signed-off-by: Clint Taylor <clinton.a.taylor@intel.com>
Tested-by: Daniel Scheller <d.scheller.oss@gmail.com>
Signed-off-by: Radhakrishna Sripada <radhakrishna.sripada@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180710200205.1478-1-radhakrishna.sripada@intel.com
---
 drivers/gpu/drm/i915/i915_drv.h      |  1 +
 drivers/gpu/drm/i915/intel_ddi.c     | 13 +++++++++++--
 drivers/gpu/drm/i915/intel_display.c | 21 ++++++++++++++++++++-
 drivers/gpu/drm/i915/intel_drv.h     |  3 +--
 4 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1616e994b9a5..f519485fcd73 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -650,6 +650,7 @@ enum intel_sbi_destination {
 #define QUIRK_BACKLIGHT_PRESENT (1<<3)
 #define QUIRK_PIN_SWIZZLED_PAGES (1<<5)
 #define QUIRK_INCREASE_T12_DELAY (1<<6)
+#define QUIRK_INCREASE_DDI_DISABLED_TIME (1<<7)
 
 struct intel_fbdev;
 struct intel_fbc_work;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 32838ed89ee7..e4caa902d88e 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1808,15 +1808,24 @@ void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state)
 	I915_WRITE(TRANS_DDI_FUNC_CTL(cpu_transcoder), temp);
 }
 
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder)
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state)
 {
+	struct intel_crtc *crtc = to_intel_crtc(crtc_state->base.crtc);
+	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
+	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
 	i915_reg_t reg = TRANS_DDI_FUNC_CTL(cpu_transcoder);
 	uint32_t val = I915_READ(reg);
 
 	val &= ~(TRANS_DDI_FUNC_ENABLE | TRANS_DDI_PORT_MASK | TRANS_DDI_DP_VC_PAYLOAD_ALLOC);
 	val |= TRANS_DDI_PORT_NONE;
 	I915_WRITE(reg, val);
+
+	if (dev_priv->quirks & QUIRK_INCREASE_DDI_DISABLED_TIME &&
+	    intel_crtc_has_type(crtc_state, INTEL_OUTPUT_HDMI)) {
+		DRM_DEBUG_KMS("Quirk Increase DDI disabled time\n");
+		/* Quirk time at 100ms for reliable operation */
+		msleep(100);
+	}
 }
 
 int intel_ddi_toggle_hdcp_signalling(struct intel_encoder *intel_encoder,
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 694975afe394..8bd9080fce34 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -5838,7 +5838,7 @@ static void haswell_crtc_disable(struct intel_crtc_state *old_crtc_state,
 		intel_ddi_set_vc_payload_alloc(old_crtc_state, false);
 
 	if (!transcoder_is_dsi(cpu_transcoder))
-		intel_ddi_disable_transcoder_func(dev_priv, cpu_transcoder);
+		intel_ddi_disable_transcoder_func(old_crtc_state);
 
 	if (INTEL_GEN(dev_priv) >= 9)
 		skylake_scaler_disable(intel_crtc);
@@ -14806,6 +14806,18 @@ static void quirk_increase_t12_delay(struct drm_device *dev)
 	DRM_INFO("Applying T12 delay quirk\n");
 }
 
+/*
+ * GeminiLake NUC HDMI outputs require additional off time
+ * this allows the onboard retimer to correctly sync to signal
+ */
+static void quirk_increase_ddi_disabled_time(struct drm_device *dev)
+{
+	struct drm_i915_private *dev_priv = to_i915(dev);
+
+	dev_priv->quirks |= QUIRK_INCREASE_DDI_DISABLED_TIME;
+	DRM_INFO("Applying Increase DDI Disabled quirk\n");
+}
+
 struct intel_quirk {
 	int device;
 	int subsystem_vendor;
@@ -14892,6 +14904,13 @@ static struct intel_quirk intel_quirks[] = {
 
 	/* Toshiba Satellite P50-C-18C */
 	{ 0x191B, 0x1179, 0xF840, quirk_increase_t12_delay },
+
+	/* GeminiLake NUC */
+	{ 0x3185, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x8086, 0x2072, quirk_increase_ddi_disabled_time },
+	/* ASRock ITX*/
+	{ 0x3185, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
+	{ 0x3184, 0x1849, 0x2212, quirk_increase_ddi_disabled_time },
 };
 
 static void intel_init_quirks(struct drm_device *dev)
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 1375cad8bf83..a0e9a35b5658 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1384,8 +1384,7 @@ void hsw_fdi_link_train(struct intel_crtc *crtc,
 void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port);
 bool intel_ddi_get_hw_state(struct intel_encoder *encoder, enum pipe *pipe);
 void intel_ddi_enable_transcoder_func(const struct intel_crtc_state *crtc_state);
-void intel_ddi_disable_transcoder_func(struct drm_i915_private *dev_priv,
-				       enum transcoder cpu_transcoder);
+void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state);
 void intel_ddi_enable_pipe_clock(const struct intel_crtc_state *crtc_state);
 void intel_ddi_disable_pipe_clock(const  struct intel_crtc_state *crtc_state);
 void intel_ddi_set_pipe_settings(const struct intel_crtc_state *crtc_state);
-- 
cgit v1.2.3


From b95e2cd021938d2c3455fd2fce69b4845de0b85f Mon Sep 17 00:00:00 2001
From: Ray Jui <ray.jui@broadcom.com>
Date: Mon, 11 Jun 2018 17:21:03 -0700
Subject: PCI: iproc: Activate PAXC bridge quirk for more devices

Activate PAXC bridge quirk for more PAXC based PCIe root complex with
the following PCIe device ID:
0xd750, 0xd802, 0xd804

Signed-off-by: Ray Jui <ray.jui@broadcom.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f439de848658..8bf68e62d280 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2352,6 +2352,9 @@ static void quirk_paxc_bridge(struct pci_dev *pdev)
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge);
 #endif
 
 /*
-- 
cgit v1.2.3


From 3bc70825e4361eaedffeb4e85e1b2774547e66a0 Mon Sep 17 00:00:00 2001
From: Ray Jui <ray.jui@broadcom.com>
Date: Mon, 11 Jun 2018 17:21:04 -0700
Subject: PCI: iproc: Fix up corrupted PAXC root complex config registers

On certain versions of Broadcom PAXC based root complexes, certain
regions of the configuration space are corrupted. As a result, it
prevents the Linux PCIe stack from traversing the linked list of the
capability registers completely and therefore the root complex is
not advertised as "PCIe capable". This prevents the correct PCIe RID
from being parsed in the kernel PCIe stack. A correct RID is required
for mapping to a stream ID from the SMMU or the device ID from the
GICv3 ITS.

This patch fixes up the issue by manually populating the related
PCIe capabilities.

Signed-off-by: Ray Jui <rjui@broadcom.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/controller/pcie-iproc.c | 65 +++++++++++++++++++++++++++++++++----
 drivers/pci/controller/pcie-iproc.h |  3 ++
 2 files changed, 62 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index 3c76c5fa4f32..680f6b170845 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -85,6 +85,8 @@
 #define IMAP_VALID_SHIFT		0
 #define IMAP_VALID			BIT(IMAP_VALID_SHIFT)
 
+#define IPROC_PCI_PM_CAP		0x48
+#define IPROC_PCI_PM_CAP_MASK		0xffff
 #define IPROC_PCI_EXP_CAP		0xac
 
 #define IPROC_PCIE_REG_INVALID		0xffff
@@ -375,6 +377,17 @@ static const u16 iproc_pcie_reg_paxc_v2[] = {
 	[IPROC_PCIE_CFG_DATA]		= 0x1fc,
 };
 
+/*
+ * List of device IDs of controllers that have corrupted capability list that
+ * require SW fixup
+ */
+static const u16 iproc_pcie_corrupt_cap_did[] = {
+	0x16cd,
+	0x16f0,
+	0xd802,
+	0xd804
+};
+
 static inline struct iproc_pcie *iproc_data(struct pci_bus *bus)
 {
 	struct iproc_pcie *pcie = bus->sysdata;
@@ -495,6 +508,49 @@ static unsigned int iproc_pcie_cfg_retry(void __iomem *cfg_data_p)
 	return data;
 }
 
+static void iproc_pcie_fix_cap(struct iproc_pcie *pcie, int where, u32 *val)
+{
+	u32 i, dev_id;
+
+	switch (where & ~0x3) {
+	case PCI_VENDOR_ID:
+		dev_id = *val >> 16;
+
+		/*
+		 * Activate fixup for those controllers that have corrupted
+		 * capability list registers
+		 */
+		for (i = 0; i < ARRAY_SIZE(iproc_pcie_corrupt_cap_did); i++)
+			if (dev_id == iproc_pcie_corrupt_cap_did[i])
+				pcie->fix_paxc_cap = true;
+		break;
+
+	case IPROC_PCI_PM_CAP:
+		if (pcie->fix_paxc_cap) {
+			/* advertise PM, force next capability to PCIe */
+			*val &= ~IPROC_PCI_PM_CAP_MASK;
+			*val |= IPROC_PCI_EXP_CAP << 8 | PCI_CAP_ID_PM;
+		}
+		break;
+
+	case IPROC_PCI_EXP_CAP:
+		if (pcie->fix_paxc_cap) {
+			/* advertise root port, version 2, terminate here */
+			*val = (PCI_EXP_TYPE_ROOT_PORT << 4 | 2) << 16 |
+				PCI_CAP_ID_EXP;
+		}
+		break;
+
+	case IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL:
+		/* Don't advertise CRS SV support */
+		*val &= ~(PCI_EXP_RTCAP_CRSVIS << 16);
+		break;
+
+	default:
+		break;
+	}
+}
+
 static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
 				  int where, int size, u32 *val)
 {
@@ -509,13 +565,10 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
 	/* root complex access */
 	if (busno == 0) {
 		ret = pci_generic_config_read32(bus, devfn, where, size, val);
-		if (ret != PCIBIOS_SUCCESSFUL)
-			return ret;
+		if (ret == PCIBIOS_SUCCESSFUL)
+			iproc_pcie_fix_cap(pcie, where, val);
 
-		/* Don't advertise CRS SV support */
-		if ((where & ~0x3) == IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL)
-			*val &= ~(PCI_EXP_RTCAP_CRSVIS << 16);
-		return PCIBIOS_SUCCESSFUL;
+		return ret;
 	}
 
 	cfg_data_p = iproc_pcie_map_ep_cfg_reg(pcie, busno, slot, fn, where);
diff --git a/drivers/pci/controller/pcie-iproc.h b/drivers/pci/controller/pcie-iproc.h
index 814b600b383a..9d5cfeea3046 100644
--- a/drivers/pci/controller/pcie-iproc.h
+++ b/drivers/pci/controller/pcie-iproc.h
@@ -60,6 +60,8 @@ struct iproc_msi;
  * @ep_is_internal: indicates an internal emulated endpoint device is connected
  * @has_apb_err_disable: indicates the controller can be configured to prevent
  * unsupported request from being forwarded as an APB bus error
+ * @fix_paxc_cap: indicates the controller has corrupted capability list in its
+ * config space registers and requires SW based fixup
  *
  * @need_ob_cfg: indicates SW needs to configure the outbound mapping window
  * @ob: outbound mapping related parameters
@@ -85,6 +87,7 @@ struct iproc_pcie {
 	int (*map_irq)(const struct pci_dev *, u8, u8);
 	bool ep_is_internal;
 	bool has_apb_err_disable;
+	bool fix_paxc_cap;
 
 	bool need_ob_cfg;
 	struct iproc_pcie_ob ob;
-- 
cgit v1.2.3


From 1e5748c27ad6669ec4a377f44ef40898c28184e5 Mon Sep 17 00:00:00 2001
From: Ray Jui <ray.jui@broadcom.com>
Date: Mon, 11 Jun 2018 17:21:05 -0700
Subject: PCI: iproc: Disable MSI parsing in certain PAXC blocks

The internal MSI parsing logic in certain revisions of PAXC root
complexes does not work properly and can cause corruptions on the
writes transactions so they need to be disabled.

Signed-off-by: Ray Jui <ray.jui@broadcom.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Scott Branden <scott.branden@broadcom.com>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/controller/pcie-iproc.c | 34 ++++++++++++++++++++++++++++++++--
 1 file changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index 680f6b170845..0804aa284b87 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -1197,10 +1197,22 @@ static int iproc_pcie_paxb_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr)
 	return ret;
 }
 
-static void iproc_pcie_paxc_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr)
+static void iproc_pcie_paxc_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr,
+					 bool enable)
 {
 	u32 val;
 
+	if (!enable) {
+		/*
+		 * Disable PAXC MSI steering. All write transfers will be
+		 * treated as non-MSI transfers
+		 */
+		val = iproc_pcie_read_reg(pcie, IPROC_PCIE_MSI_EN_CFG);
+		val &= ~MSI_ENABLE_CFG;
+		iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_EN_CFG, val);
+		return;
+	}
+
 	/*
 	 * Program bits [43:13] of address of GITS_TRANSLATER register into
 	 * bits [30:0] of the MSI base address register.  In fact, in all iProc
@@ -1254,7 +1266,7 @@ static int iproc_pcie_msi_steer(struct iproc_pcie *pcie,
 			return ret;
 		break;
 	case IPROC_PCIE_PAXC_V2:
-		iproc_pcie_paxc_v2_msi_steer(pcie, msi_addr);
+		iproc_pcie_paxc_v2_msi_steer(pcie, msi_addr, true);
 		break;
 	default:
 		return -EINVAL;
@@ -1480,6 +1492,24 @@ int iproc_pcie_remove(struct iproc_pcie *pcie)
 }
 EXPORT_SYMBOL(iproc_pcie_remove);
 
+/*
+ * The MSI parsing logic in certain revisions of Broadcom PAXC based root
+ * complex does not work and needs to be disabled
+ */
+static void quirk_paxc_disable_msi_parsing(struct pci_dev *pdev)
+{
+	struct iproc_pcie *pcie = iproc_data(pdev->bus);
+
+	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
+		iproc_pcie_paxc_v2_msi_steer(pcie, 0, false);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0,
+			quirk_paxc_disable_msi_parsing);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802,
+			quirk_paxc_disable_msi_parsing);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804,
+			quirk_paxc_disable_msi_parsing);
+
 MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>");
 MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver");
 MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From f78e60a29d4ff27531770cf2c6eee89292379209 Mon Sep 17 00:00:00 2001
From: Ray Jui <ray.jui@broadcom.com>
Date: Mon, 11 Jun 2018 17:21:06 -0700
Subject: PCI: iproc: Reject unconfigured physical functions from PAXC

PAXC is an emulated PCIe root complex internally in various Broadcom
based SoCs. PAXC internally connects to the embedded network processor
within these SoCs, with the embedeed network processor exposed as an
endpoint device.

The number of physical functions from the embedded network processor
that can be accessed depends on the firmware configuration.

Unfortunately, due to an ASIC bug, unconfigured physical functions cannot
be properly hidden from the root complex during enumerattion. As a
result, config write access to these unconfigured physical functions
during enumeration will cause a bus lock up on the embedded network
processor.

Fortunately, these unconfigured physical functions contain a very
specific, staled PCIe device ID 0x168e. By making use of this device ID,
one is able to terminate the enumeration early in the vendor/device ID
config read.

Signed-off-by: Ray Jui <ray.jui@broadcom.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Scott Branden <scott.branden@broadcom.com>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/controller/pcie-iproc.c | 26 +++++++++++++++++++++++++-
 drivers/pci/controller/pcie-iproc.h |  5 +++++
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index 0804aa284b87..59be1e02ba65 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -582,6 +582,25 @@ static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
 	if (size <= 2)
 		*val = (data >> (8 * (where & 3))) & ((1 << (size * 8)) - 1);
 
+	/*
+	 * For PAXC and PAXCv2, the total number of PFs that one can enumerate
+	 * depends on the firmware configuration. Unfortunately, due to an ASIC
+	 * bug, unconfigured PFs cannot be properly hidden from the root
+	 * complex. As a result, write access to these PFs will cause bus lock
+	 * up on the embedded processor
+	 *
+	 * Since all unconfigured PFs are left with an incorrect, staled device
+	 * ID of 0x168e (PCI_DEVICE_ID_NX2_57810), we try to catch those access
+	 * early here and reject them all
+	 */
+#define DEVICE_ID_MASK     0xffff0000
+#define DEVICE_ID_SHIFT    16
+	if (pcie->rej_unconfig_pf &&
+	    (where & CFG_ADDR_REG_NUM_MASK) == PCI_VENDOR_ID)
+		if ((*val & DEVICE_ID_MASK) ==
+		    (PCI_DEVICE_ID_NX2_57810 << DEVICE_ID_SHIFT))
+			return PCIBIOS_FUNC_NOT_SUPPORTED;
+
 	return PCIBIOS_SUCCESSFUL;
 }
 
@@ -681,7 +700,7 @@ static int iproc_pcie_config_read32(struct pci_bus *bus, unsigned int devfn,
 	struct iproc_pcie *pcie = iproc_data(bus);
 
 	iproc_pcie_apb_err_disable(bus, true);
-	if (pcie->type == IPROC_PCIE_PAXB_V2)
+	if (pcie->iproc_cfg_read)
 		ret = iproc_pcie_config_read(bus, devfn, where, size, val);
 	else
 		ret = pci_generic_config_read32(bus, devfn, where, size, val);
@@ -1336,6 +1355,7 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie)
 		break;
 	case IPROC_PCIE_PAXB:
 		regs = iproc_pcie_reg_paxb;
+		pcie->iproc_cfg_read = true;
 		pcie->has_apb_err_disable = true;
 		if (pcie->need_ob_cfg) {
 			pcie->ob_map = paxb_ob_map;
@@ -1358,10 +1378,14 @@ static int iproc_pcie_rev_init(struct iproc_pcie *pcie)
 	case IPROC_PCIE_PAXC:
 		regs = iproc_pcie_reg_paxc;
 		pcie->ep_is_internal = true;
+		pcie->iproc_cfg_read = true;
+		pcie->rej_unconfig_pf = true;
 		break;
 	case IPROC_PCIE_PAXC_V2:
 		regs = iproc_pcie_reg_paxc_v2;
 		pcie->ep_is_internal = true;
+		pcie->iproc_cfg_read = true;
+		pcie->rej_unconfig_pf = true;
 		pcie->need_msi_steer = true;
 		break;
 	default:
diff --git a/drivers/pci/controller/pcie-iproc.h b/drivers/pci/controller/pcie-iproc.h
index 9d5cfeea3046..4f03ea539805 100644
--- a/drivers/pci/controller/pcie-iproc.h
+++ b/drivers/pci/controller/pcie-iproc.h
@@ -58,6 +58,9 @@ struct iproc_msi;
  * @phy: optional PHY device that controls the Serdes
  * @map_irq: function callback to map interrupts
  * @ep_is_internal: indicates an internal emulated endpoint device is connected
+ * @iproc_cfg_read: indicates the iProc config read function should be used
+ * @rej_unconfig_pf: indicates the root complex needs to detect and reject
+ * enumeration against unconfigured physical functions emulated in the ASIC
  * @has_apb_err_disable: indicates the controller can be configured to prevent
  * unsupported request from being forwarded as an APB bus error
  * @fix_paxc_cap: indicates the controller has corrupted capability list in its
@@ -86,6 +89,8 @@ struct iproc_pcie {
 	struct phy *phy;
 	int (*map_irq)(const struct pci_dev *, u8, u8);
 	bool ep_is_internal;
+	bool iproc_cfg_read;
+	bool rej_unconfig_pf;
 	bool has_apb_err_disable;
 	bool fix_paxc_cap;
 
-- 
cgit v1.2.3


From 0043d4ae812e474d4edd28b60f203bfbb4edc93b Mon Sep 17 00:00:00 2001
From: Ray Jui <ray.jui@broadcom.com>
Date: Mon, 11 Jun 2018 17:21:07 -0700
Subject: PCI: iproc: Reduce inbound/outbound mapping print level

Reduce inbound/outbound mapping print level from dev_info() to
dev_dbg(). This reduces the console logs during Linux boot process.

Signed-off-by: Ray Jui <ray.jui@broadcom.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Scott Branden <scott.branden@broadcom.com>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/controller/pcie-iproc.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index 59be1e02ba65..3160e9342a2f 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -880,14 +880,14 @@ static inline int iproc_pcie_ob_write(struct iproc_pcie *pcie, int window_idx,
 	writel(lower_32_bits(pci_addr), pcie->base + omap_offset);
 	writel(upper_32_bits(pci_addr), pcie->base + omap_offset + 4);
 
-	dev_info(dev, "ob window [%d]: offset 0x%x axi %pap pci %pap\n",
-		 window_idx, oarr_offset, &axi_addr, &pci_addr);
-	dev_info(dev, "oarr lo 0x%x oarr hi 0x%x\n",
-		 readl(pcie->base + oarr_offset),
-		 readl(pcie->base + oarr_offset + 4));
-	dev_info(dev, "omap lo 0x%x omap hi 0x%x\n",
-		 readl(pcie->base + omap_offset),
-		 readl(pcie->base + omap_offset + 4));
+	dev_dbg(dev, "ob window [%d]: offset 0x%x axi %pap pci %pap\n",
+		window_idx, oarr_offset, &axi_addr, &pci_addr);
+	dev_dbg(dev, "oarr lo 0x%x oarr hi 0x%x\n",
+		readl(pcie->base + oarr_offset),
+		readl(pcie->base + oarr_offset + 4));
+	dev_dbg(dev, "omap lo 0x%x omap hi 0x%x\n",
+		readl(pcie->base + omap_offset),
+		readl(pcie->base + omap_offset + 4));
 
 	return 0;
 }
@@ -1054,8 +1054,8 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx,
 	    iproc_pcie_reg_is_invalid(imap_offset))
 		return -EINVAL;
 
-	dev_info(dev, "ib region [%d]: offset 0x%x axi %pap pci %pap\n",
-		 region_idx, iarr_offset, &axi_addr, &pci_addr);
+	dev_dbg(dev, "ib region [%d]: offset 0x%x axi %pap pci %pap\n",
+		region_idx, iarr_offset, &axi_addr, &pci_addr);
 
 	/*
 	 * Program the IARR registers.  The upper 32-bit IARR register is
@@ -1065,9 +1065,9 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx,
 	       pcie->base + iarr_offset);
 	writel(upper_32_bits(pci_addr), pcie->base + iarr_offset + 4);
 
-	dev_info(dev, "iarr lo 0x%x iarr hi 0x%x\n",
-		 readl(pcie->base + iarr_offset),
-		 readl(pcie->base + iarr_offset + 4));
+	dev_dbg(dev, "iarr lo 0x%x iarr hi 0x%x\n",
+		readl(pcie->base + iarr_offset),
+		readl(pcie->base + iarr_offset + 4));
 
 	/*
 	 * Now program the IMAP registers.  Each IARR region may have one or
@@ -1081,10 +1081,10 @@ static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx,
 		writel(upper_32_bits(axi_addr),
 		       pcie->base + imap_offset + ib_map->imap_addr_offset);
 
-		dev_info(dev, "imap window [%d] lo 0x%x hi 0x%x\n",
-			 window_idx, readl(pcie->base + imap_offset),
-			 readl(pcie->base + imap_offset +
-			       ib_map->imap_addr_offset));
+		dev_dbg(dev, "imap window [%d] lo 0x%x hi 0x%x\n",
+			window_idx, readl(pcie->base + imap_offset),
+			readl(pcie->base + imap_offset +
+			      ib_map->imap_addr_offset));
 
 		imap_offset += ib_map->imap_window_offset;
 		axi_addr += size;
-- 
cgit v1.2.3


From a0476b3a678b4145a993f56071989af39d5718fb Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:43 +0800
Subject: PCI: exynos: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Jingoo Han <jingoohan1@gmail.com>
---
 drivers/pci/controller/dwc/pci-exynos.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 4cc1e5df8c79..cee5f2f590e2 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -421,7 +421,6 @@ static int __init exynos_add_pcie_port(struct exynos_pcie *ep,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &exynos_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
-- 
cgit v1.2.3


From 39f712e989c5e591c58b65b62981b85027ba3103 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:44 +0800
Subject: PCI: imx6: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Cc: Richard Zhu <hongxing.zhu@nxp.com>
Cc: Lucas Stach <l.stach@pengutronix.de>
---
 drivers/pci/controller/dwc/pci-imx6.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 80f604602783..4a9a673b4777 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -667,7 +667,6 @@ static int imx6_add_pcie_port(struct imx6_pcie *imx6_pcie,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &imx6_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
-- 
cgit v1.2.3


From 8519bc8fe88fbe5c1e448ae1dd1ba215a1723abe Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:45 +0800
Subject: PCI: keystone: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Murali Karicheri <m-karicheri2@ti.com>
---
 drivers/pci/controller/dwc/pci-keystone.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 3722a5f31e5e..e88bd221fffe 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -347,7 +347,6 @@ static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &keystone_pcie_host_ops;
 	ret = ks_dw_pcie_host_init(ks_pcie, ks_pcie->msi_intc_np);
 	if (ret) {
-- 
cgit v1.2.3


From 53b801fd020d4d00a1eebbab9f042a8b9fe03b78 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:46 +0800
Subject: PCI: armada8k: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
---
 drivers/pci/controller/dwc/pcie-armada8k.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index 072fd7ecc29f..0c389a30ef5d 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -172,7 +172,6 @@ static int armada8k_add_pcie_port(struct armada8k_pcie *pcie,
 	struct device *dev = &pdev->dev;
 	int ret;
 
-	pp->root_bus_nr = -1;
 	pp->ops = &armada8k_pcie_host_ops;
 
 	pp->irq = platform_get_irq(pdev, 0);
-- 
cgit v1.2.3


From 84b88219553af870a47e28d6ba288bd6fbd129f7 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:47 +0800
Subject: PCI: artpec6: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Cc: Jesper Nilsson <jesper.nilsson@axis.com>
---
 drivers/pci/controller/dwc/pcie-artpec6.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 321b56cfd5d0..128b182648b3 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -399,7 +399,6 @@ static int artpec6_add_pcie_port(struct artpec6_pcie *artpec6_pcie,
 		}
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &artpec6_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
-- 
cgit v1.2.3


From 3513f81816ef085c0068c8aea04b78b0a06a8720 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:48 +0800
Subject: PCI: designware-plat: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Cc: Joao Pinto <Joao.Pinto@synopsys.com>
---
 drivers/pci/controller/dwc/pcie-designware-plat.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index 5937fed4c938..6e048c0b67f2 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -118,7 +118,6 @@ static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie,
 			return pp->msi_irq;
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &dw_plat_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
-- 
cgit v1.2.3


From 73fb9924d26b835f67acedacfe032343c9ed4f06 Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:49 +0800
Subject: PCI: histb: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Jianguo Sun <sunjianguo1@huawei.com>
---
 drivers/pci/controller/dwc/pcie-histb.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index 3611d6ce9a92..7b32e619b959 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -420,7 +420,6 @@ static int histb_pcie_probe(struct platform_device *pdev)
 		phy_init(hipcie->phy);
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &histb_pcie_host_ops;
 
 	platform_set_drvdata(pdev, hipcie);
-- 
cgit v1.2.3


From 739cd35918b7cf495ea2d7abb2ff6ee97605f41d Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:50 +0800
Subject: PCI: qcom: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Stanimir Varbanov <svarbanov@mm-sol.com>
---
 drivers/pci/controller/dwc/pcie-qcom.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index a1d0198081a6..4352c1cb926d 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -1251,7 +1251,6 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	pp->root_bus_nr = -1;
 	pp->ops = &qcom_pcie_dw_ops;
 
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
-- 
cgit v1.2.3


From 53dd0c51f16be5f215d3ecad435062df99ee29ae Mon Sep 17 00:00:00 2001
From: Shawn Guo <shawn.guo@linaro.org>
Date: Sun, 1 Jul 2018 11:54:51 +0800
Subject: PCI: spear13xx: Drop unnecessary root_bus_nr setting

Function dw_pcie_host_init() already initializes the root_bus_nr field
of 'struct pcie_port', so the -1 assignment prior to calling
dw_pcie_host_init() in platform specific driver is not really needed.
Drop it.

Signed-off-by: Shawn Guo <shawn.guo@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Pratyush Anand <pratyush.anand@gmail.com>
---
 drivers/pci/controller/dwc/pcie-spear13xx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c
index ecb58f7b7566..7d0cdfd8138b 100644
--- a/drivers/pci/controller/dwc/pcie-spear13xx.c
+++ b/drivers/pci/controller/dwc/pcie-spear13xx.c
@@ -210,7 +210,6 @@ static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie,
 		return ret;
 	}
 
-	pp->root_bus_nr = -1;
 	pp->ops = &spear13xx_pcie_host_ops;
 
 	ret = dw_pcie_host_init(pp);
-- 
cgit v1.2.3


From afed7bcf9487bb28e2e2b016a195085c07416c0b Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Wed, 11 Jul 2018 10:36:07 +0100
Subject: locking/refcount: Always allow checked forms

In many cases, it would be useful to be able to use the full
sanity-checked refcount helpers regardless of CONFIG_REFCOUNT_FULL,
as this would help to avoid duplicate warnings where callers try to
sanity-check refcount manipulation.

This patch refactors things such that the full refcount helpers were
always built, as refcount_${op}_checked(), such that they can be used
regardless of CONFIG_REFCOUNT_FULL. This will allow code which *always*
wants a checked refcount to opt-in, avoiding the need to duplicate the
logic for warnings.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Acked-by: Kees Cook <keescook@chromium.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20180711093607.1644-1-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/refcount.h | 27 +++++++++++++++++-------
 lib/refcount.c           | 53 +++++++++++++++++++++++-------------------------
 2 files changed, 45 insertions(+), 35 deletions(-)

diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index c36addd27dd5..53c5eca24d83 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -43,17 +43,30 @@ static inline unsigned int refcount_read(const refcount_t *r)
 	return atomic_read(&r->refs);
 }
 
+extern __must_check bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r);
+extern void refcount_add_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_inc_not_zero_checked(refcount_t *r);
+extern void refcount_inc_checked(refcount_t *r);
+
+extern __must_check bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r);
+
+extern __must_check bool refcount_dec_and_test_checked(refcount_t *r);
+extern void refcount_dec_checked(refcount_t *r);
+
 #ifdef CONFIG_REFCOUNT_FULL
-extern __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r);
-extern void refcount_add(unsigned int i, refcount_t *r);
 
-extern __must_check bool refcount_inc_not_zero(refcount_t *r);
-extern void refcount_inc(refcount_t *r);
+#define refcount_add_not_zero	refcount_add_not_zero_checked
+#define refcount_add		refcount_add_checked
+
+#define refcount_inc_not_zero	refcount_inc_not_zero_checked
+#define refcount_inc		refcount_inc_checked
+
+#define refcount_sub_and_test	refcount_sub_and_test_checked
 
-extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r);
+#define refcount_dec_and_test	refcount_dec_and_test_checked
+#define refcount_dec		refcount_dec_checked
 
-extern __must_check bool refcount_dec_and_test(refcount_t *r);
-extern void refcount_dec(refcount_t *r);
 #else
 # ifdef CONFIG_ARCH_HAS_REFCOUNT
 #  include <asm/refcount.h>
diff --git a/lib/refcount.c b/lib/refcount.c
index 4bd842f20749..5c4aaefc0682 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -40,10 +40,8 @@
 #include <linux/spinlock.h>
 #include <linux/bug.h>
 
-#ifdef CONFIG_REFCOUNT_FULL
-
 /**
- * refcount_add_not_zero - add a value to a refcount unless it is 0
+ * refcount_add_not_zero_checked - add a value to a refcount unless it is 0
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -60,7 +58,7 @@
  *
  * Return: false if the passed refcount is 0, true otherwise
  */
-bool refcount_add_not_zero(unsigned int i, refcount_t *r)
+bool refcount_add_not_zero_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -81,10 +79,10 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_add_not_zero);
+EXPORT_SYMBOL(refcount_add_not_zero_checked);
 
 /**
- * refcount_add - add a value to a refcount
+ * refcount_add_checked - add a value to a refcount
  * @i: the value to add to the refcount
  * @r: the refcount
  *
@@ -99,14 +97,14 @@ EXPORT_SYMBOL(refcount_add_not_zero);
  * cases, refcount_inc(), or one of its variants, should instead be used to
  * increment a reference count.
  */
-void refcount_add(unsigned int i, refcount_t *r)
+void refcount_add_checked(unsigned int i, refcount_t *r)
 {
-	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_add_not_zero_checked(i, r), "refcount_t: addition on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_add);
+EXPORT_SYMBOL(refcount_add_checked);
 
 /**
- * refcount_inc_not_zero - increment a refcount unless it is 0
+ * refcount_inc_not_zero_checked - increment a refcount unless it is 0
  * @r: the refcount to increment
  *
  * Similar to atomic_inc_not_zero(), but will saturate at UINT_MAX and WARN.
@@ -117,7 +115,7 @@ EXPORT_SYMBOL(refcount_add);
  *
  * Return: true if the increment was successful, false otherwise
  */
-bool refcount_inc_not_zero(refcount_t *r)
+bool refcount_inc_not_zero_checked(refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -136,10 +134,10 @@ bool refcount_inc_not_zero(refcount_t *r)
 
 	return true;
 }
-EXPORT_SYMBOL(refcount_inc_not_zero);
+EXPORT_SYMBOL(refcount_inc_not_zero_checked);
 
 /**
- * refcount_inc - increment a refcount
+ * refcount_inc_checked - increment a refcount
  * @r: the refcount to increment
  *
  * Similar to atomic_inc(), but will saturate at UINT_MAX and WARN.
@@ -150,14 +148,14 @@ EXPORT_SYMBOL(refcount_inc_not_zero);
  * Will WARN if the refcount is 0, as this represents a possible use-after-free
  * condition.
  */
-void refcount_inc(refcount_t *r)
+void refcount_inc_checked(refcount_t *r)
 {
-	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_inc_not_zero_checked(r), "refcount_t: increment on 0; use-after-free.\n");
 }
-EXPORT_SYMBOL(refcount_inc);
+EXPORT_SYMBOL(refcount_inc_checked);
 
 /**
- * refcount_sub_and_test - subtract from a refcount and test if it is 0
+ * refcount_sub_and_test_checked - subtract from a refcount and test if it is 0
  * @i: amount to subtract from the refcount
  * @r: the refcount
  *
@@ -176,7 +174,7 @@ EXPORT_SYMBOL(refcount_inc);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_sub_and_test(unsigned int i, refcount_t *r)
+bool refcount_sub_and_test_checked(unsigned int i, refcount_t *r)
 {
 	unsigned int new, val = atomic_read(&r->refs);
 
@@ -194,10 +192,10 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 
 	return !new;
 }
-EXPORT_SYMBOL(refcount_sub_and_test);
+EXPORT_SYMBOL(refcount_sub_and_test_checked);
 
 /**
- * refcount_dec_and_test - decrement a refcount and test if it is 0
+ * refcount_dec_and_test_checked - decrement a refcount and test if it is 0
  * @r: the refcount
  *
  * Similar to atomic_dec_and_test(), it will WARN on underflow and fail to
@@ -209,14 +207,14 @@ EXPORT_SYMBOL(refcount_sub_and_test);
  *
  * Return: true if the resulting refcount is 0, false otherwise
  */
-bool refcount_dec_and_test(refcount_t *r)
+bool refcount_dec_and_test_checked(refcount_t *r)
 {
-	return refcount_sub_and_test(1, r);
+	return refcount_sub_and_test_checked(1, r);
 }
-EXPORT_SYMBOL(refcount_dec_and_test);
+EXPORT_SYMBOL(refcount_dec_and_test_checked);
 
 /**
- * refcount_dec - decrement a refcount
+ * refcount_dec_checked - decrement a refcount
  * @r: the refcount
  *
  * Similar to atomic_dec(), it will WARN on underflow and fail to decrement
@@ -225,12 +223,11 @@ EXPORT_SYMBOL(refcount_dec_and_test);
  * Provides release memory ordering, such that prior loads and stores are done
  * before.
  */
-void refcount_dec(refcount_t *r)
+void refcount_dec_checked(refcount_t *r)
 {
-	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+	WARN_ONCE(refcount_dec_and_test_checked(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
-EXPORT_SYMBOL(refcount_dec);
-#endif /* CONFIG_REFCOUNT_FULL */
+EXPORT_SYMBOL(refcount_dec_checked);
 
 /**
  * refcount_dec_if_one - decrement a refcount if it is 1
-- 
cgit v1.2.3


From f9ff5018c13b4918c98178ee81d41372b455201e Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 12 Jul 2018 21:50:41 +0100
Subject: ARM: net: bpf: improve 64-bit load immediate implementation

Rather than writing each 32-bit half of the 64-bit immediate value
separately when the register is on the stack:

  movw    r6, #45056      ; 0xb000
  movt    r6, #60979      ; 0xee33
  str     r6, [fp, #-44]  ; 0xffffffd4
  mov     r6, #0
  str     r6, [fp, #-40]  ; 0xffffffd8

arrange to use the double-word store when available instead:

  movw    r6, #45056      ; 0xb000
  movt    r6, #60979      ; 0xee33
  mov     r7, #0
  strd    r6, [fp, #-44]  ; 0xffffffd4

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index a9f68a924800..6558bd73bbb9 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -599,9 +599,20 @@ static inline void emit_a32_mov_i(const s8 dst, const u32 val,
 	}
 }
 
+static void emit_a32_mov_i64(const s8 dst[], u64 val, struct jit_ctx *ctx)
+{
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *rd = is_stacked(dst_lo) ? tmp : dst;
+
+	emit_mov_i(rd[1], (u32)val, ctx);
+	emit_mov_i(rd[0], val >> 32, ctx);
+
+	arm_bpf_put_reg64(dst, rd, ctx);
+}
+
 /* Sign extended move */
-static inline void emit_a32_mov_i64(const bool is64, const s8 dst[],
-				  const u32 val, struct jit_ctx *ctx) {
+static inline void emit_a32_mov_se_i64(const bool is64, const s8 dst[],
+				       const u32 val, struct jit_ctx *ctx) {
 	u32 hi = 0;
 
 	if (is64 && (val & (1<<31)))
@@ -1309,7 +1320,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			break;
 		case BPF_K:
 			/* Sign-extend immediate value to destination reg */
-			emit_a32_mov_i64(is64, dst, imm, ctx);
+			emit_a32_mov_se_i64(is64, dst, imm, ctx);
 			break;
 		}
 		break;
@@ -1358,7 +1369,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			 * value into temporary reg and then it would be
 			 * safe to do the operation on it.
 			 */
-			emit_a32_mov_i64(is64, tmp2, imm, ctx);
+			emit_a32_mov_se_i64(is64, tmp2, imm, ctx);
 			emit_a32_alu_r64(is64, dst, tmp2, ctx, BPF_OP(code));
 			break;
 		}
@@ -1454,7 +1465,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx)
 			 * reg then it would be safe to do the operation
 			 * on it.
 			 */
-			emit_a32_mov_i64(is64, tmp2, imm, ctx);
+			emit_a32_mov_se_i64(is64, tmp2, imm, ctx);
 			emit_a32_mul_r64(dst, tmp2, ctx);
 			break;
 		}
@@ -1506,12 +1517,9 @@ exit:
 	/* dst = imm64 */
 	case BPF_LD | BPF_IMM | BPF_DW:
 	{
-		const struct bpf_insn insn1 = insn[1];
-		u32 hi, lo = imm;
+		u64 val = (u32)imm | (u64)insn[1].imm << 32;
 
-		hi = insn1.imm;
-		emit_a32_mov_i(dst_lo, lo, ctx);
-		emit_a32_mov_i(dst_hi, hi, ctx);
+		emit_a32_mov_i64(dst, val, ctx);
 
 		return 1;
 	}
@@ -1531,7 +1539,7 @@ exit:
 		switch (BPF_SIZE(code)) {
 		case BPF_DW:
 			/* Sign-extend immediate value into temp reg */
-			emit_a32_mov_i64(true, tmp2, imm, ctx);
+			emit_a32_mov_se_i64(true, tmp2, imm, ctx);
 			emit_str_r(dst_lo, tmp2[1], off, ctx, BPF_W);
 			emit_str_r(dst_lo, tmp2[0], off+4, ctx, BPF_W);
 			break;
@@ -1620,7 +1628,7 @@ exit:
 		rm = tmp2[0];
 		rn = tmp2[1];
 		/* Sign-extend immediate value */
-		emit_a32_mov_i64(true, tmp2, imm, ctx);
+		emit_a32_mov_se_i64(true, tmp2, imm, ctx);
 go_jmp:
 		/* Setup destination register */
 		rd = arm_bpf_get_reg64(dst, tmp, ctx);
-- 
cgit v1.2.3


From 077513b89424ba814432b1cd7d7f793958059ed8 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 12 Jul 2018 21:50:46 +0100
Subject: ARM: net: bpf: improve 64-bit sign-extended immediate load

Improve the 64-bit sign-extended immediate from:

  mov     r6, #1
  str     r6, [fp, #-52]  ; 0xffffffcc
  mov     r6, #0
  str     r6, [fp, #-48]  ; 0xffffffd0

to:

  mov     r6, #1
  mov     r7, #0
  strd    r6, [fp, #-52]  ; 0xffffffcc

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 6558bd73bbb9..3a182e618441 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -613,12 +613,11 @@ static void emit_a32_mov_i64(const s8 dst[], u64 val, struct jit_ctx *ctx)
 /* Sign extended move */
 static inline void emit_a32_mov_se_i64(const bool is64, const s8 dst[],
 				       const u32 val, struct jit_ctx *ctx) {
-	u32 hi = 0;
+	u64 val64 = val;
 
 	if (is64 && (val & (1<<31)))
-		hi = (u32)~0;
-	emit_a32_mov_i(dst_lo, val, ctx);
-	emit_a32_mov_i(dst_hi, hi, ctx);
+		val64 |= 0xffffffff00000000ULL;
+	emit_a32_mov_i64(dst, val64, ctx);
 }
 
 static inline void emit_a32_add_r(const u8 dst, const u8 src,
-- 
cgit v1.2.3


From c5eae692571d6c44efeb27fe78a5ed8b5ded9b4a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 12 Jul 2018 21:50:51 +0100
Subject: ARM: net: bpf: improve 64-bit store implementation

Improve the 64-bit store implementation from:

  ldr     r6, [fp, #-8]
  str     r8, [r6]
  ldr     r6, [fp, #-8]
  mov     r7, #4
  add     r7, r6, r7
  str     r9, [r7]

to:

  ldr     r6, [fp, #-8]
  str     r8, [r6]
  str     r9, [r6, #4]

We leave the store as two separate STR instructions rather than using
STRD as the store may not be aligned, and STR can handle misalignment.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 52 +++++++++++++++++++++++------------------------
 1 file changed, 26 insertions(+), 26 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 3a182e618441..026612ee8151 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -975,29 +975,42 @@ static inline void emit_a32_mul_r64(const s8 dst[], const s8 src[],
 }
 
 /* *(size *)(dst + off) = src */
-static inline void emit_str_r(const s8 dst, const s8 src,
-			      const s32 off, struct jit_ctx *ctx, const u8 sz){
+static inline void emit_str_r(const s8 dst, const s8 src[],
+			      s32 off, struct jit_ctx *ctx, const u8 sz){
 	const s8 *tmp = bpf2a32[TMP_REG_1];
+	s32 off_max;
 	s8 rd;
 
 	rd = arm_bpf_get_reg32(dst, tmp[1], ctx);
-	if (off) {
+
+	if (sz == BPF_H)
+		off_max = 0xff;
+	else
+		off_max = 0xfff;
+
+	if (off < 0 || off > off_max) {
 		emit_a32_mov_i(tmp[0], off, ctx);
-		emit(ARM_ADD_R(tmp[0], rd, tmp[0]), ctx);
+		emit(ARM_ADD_R(tmp[0], tmp[0], rd), ctx);
 		rd = tmp[0];
+		off = 0;
 	}
 	switch (sz) {
-	case BPF_W:
-		/* Store a Word */
-		emit(ARM_STR_I(src, rd, 0), ctx);
+	case BPF_B:
+		/* Store a Byte */
+		emit(ARM_STRB_I(src_lo, rd, off), ctx);
 		break;
 	case BPF_H:
 		/* Store a HalfWord */
-		emit(ARM_STRH_I(src, rd, 0), ctx);
+		emit(ARM_STRH_I(src_lo, rd, off), ctx);
 		break;
-	case BPF_B:
-		/* Store a Byte */
-		emit(ARM_STRB_I(src, rd, 0), ctx);
+	case BPF_W:
+		/* Store a Word */
+		emit(ARM_STR_I(src_lo, rd, off), ctx);
+		break;
+	case BPF_DW:
+		/* Store a Double Word */
+		emit(ARM_STR_I(src_lo, rd, off), ctx);
+		emit(ARM_STR_I(src_hi, rd, off + 4), ctx);
 		break;
 	}
 }
@@ -1539,16 +1552,14 @@ exit:
 		case BPF_DW:
 			/* Sign-extend immediate value into temp reg */
 			emit_a32_mov_se_i64(true, tmp2, imm, ctx);
-			emit_str_r(dst_lo, tmp2[1], off, ctx, BPF_W);
-			emit_str_r(dst_lo, tmp2[0], off+4, ctx, BPF_W);
 			break;
 		case BPF_W:
 		case BPF_H:
 		case BPF_B:
 			emit_a32_mov_i(tmp2[1], imm, ctx);
-			emit_str_r(dst_lo, tmp2[1], off, ctx, BPF_SIZE(code));
 			break;
 		}
+		emit_str_r(dst_lo, tmp2, off, ctx, BPF_SIZE(code));
 		break;
 	/* STX XADD: lock *(u32 *)(dst + off) += src */
 	case BPF_STX | BPF_XADD | BPF_W:
@@ -1560,20 +1571,9 @@ exit:
 	case BPF_STX | BPF_MEM | BPF_H:
 	case BPF_STX | BPF_MEM | BPF_B:
 	case BPF_STX | BPF_MEM | BPF_DW:
-	{
-		u8 sz = BPF_SIZE(code);
-
 		rs = arm_bpf_get_reg64(src, tmp2, ctx);
-
-		/* Store the value */
-		if (BPF_SIZE(code) == BPF_DW) {
-			emit_str_r(dst_lo, rs[1], off, ctx, BPF_W);
-			emit_str_r(dst_lo, rs[0], off+4, ctx, BPF_W);
-		} else {
-			emit_str_r(dst_lo, rs[1], off, ctx, sz);
-		}
+		emit_str_r(dst_lo, rs, off, ctx, BPF_SIZE(code));
 		break;
-	}
 	/* PC += off if dst == src */
 	/* PC += off if dst > src */
 	/* PC += off if dst >= src */
-- 
cgit v1.2.3


From b18bea2a45b136c4da7ff75305b54d66cf57de81 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 12 Jul 2018 21:50:56 +0100
Subject: ARM: net: bpf: improve 64-bit ALU implementation

Improbe the 64-bit ALU implementation from:

  movw    r8, #65532
  movt    r8, #65535
  movw    r9, #65535
  movt    r9, #65535
  ldr     r7, [fp, #-44]
  adds    r7, r7, r8
  str     r7, [fp, #-44]
  ldr     r7, [fp, #-40]
  adc     r7, r7, r9
  str     r7, [fp, #-40]

to:

  movw    r8, #65532
  movt    r8, #65535
  movw    r9, #65535
  movt    r9, #65535
  ldrd    r6, [fp, #-44]
  adds    r6, r6, r8
  adc     r7, r7, r9
  strd    r6, [fp, #-44]

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 arch/arm/net/bpf_jit_32.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c
index 026612ee8151..25b3ee85066e 100644
--- a/arch/arm/net/bpf_jit_32.c
+++ b/arch/arm/net/bpf_jit_32.c
@@ -716,11 +716,30 @@ static inline void emit_a32_alu_r(const s8 dst, const s8 src,
 static inline void emit_a32_alu_r64(const bool is64, const s8 dst[],
 				  const s8 src[], struct jit_ctx *ctx,
 				  const u8 op) {
-	emit_a32_alu_r(dst_lo, src_lo, ctx, is64, false, op);
-	if (is64)
-		emit_a32_alu_r(dst_hi, src_hi, ctx, is64, true, op);
-	else
-		emit_a32_mov_i(dst_hi, 0, ctx);
+	const s8 *tmp = bpf2a32[TMP_REG_1];
+	const s8 *tmp2 = bpf2a32[TMP_REG_2];
+	const s8 *rd;
+
+	rd = arm_bpf_get_reg64(dst, tmp, ctx);
+	if (is64) {
+		const s8 *rs;
+
+		rs = arm_bpf_get_reg64(src, tmp2, ctx);
+
+		/* ALU operation */
+		emit_alu_r(rd[1], rs[1], true, false, op, ctx);
+		emit_alu_r(rd[0], rs[0], true, true, op, ctx);
+	} else {
+		s8 rs;
+
+		rs = arm_bpf_get_reg32(src_lo, tmp2[1], ctx);
+
+		/* ALU operation */
+		emit_alu_r(rd[1], rs, true, false, op, ctx);
+		emit_a32_mov_i(rd[0], 0, ctx);
+	}
+
+	arm_bpf_put_reg64(dst, rd, ctx);
 }
 
 /* dst = src (4 bytes)*/
-- 
cgit v1.2.3


From eb1e39f784e83321353314da1b2e8cbb2fceaba9 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 11 Jul 2018 09:01:03 +0100
Subject: PCI: pcie-cadence-ep: Remove redundant variable mmc

Variable mmc is being assigned but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: variable 'mmc' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
[lorenzo.pieralisi@arm.com: reworked commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Alan Douglas <adouglas@cadence.com>
---
 drivers/pci/controller/pcie-cadence-ep.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c
index 3eabd99a1233..04fe76c3d59d 100644
--- a/drivers/pci/controller/pcie-cadence-ep.c
+++ b/drivers/pci/controller/pcie-cadence-ep.c
@@ -238,7 +238,7 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn)
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
 	u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET;
-	u16 flags, mmc, mme;
+	u16 flags, mme;
 
 	/* Validate that the MSI feature is actually enabled. */
 	flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS);
@@ -249,7 +249,6 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn)
 	 * Get the Multiple Message Enable bitfield from the Message Control
 	 * register.
 	 */
-	mmc = (flags & PCI_MSI_FLAGS_QMASK) >> 1;
 	mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4;
 
 	return mme;
-- 
cgit v1.2.3


From 05814a10370b3252fe2b0898b6adac3cdd531096 Mon Sep 17 00:00:00 2001
From: Vladimir Zapolskiy <vz@mleia.com>
Date: Fri, 13 Jul 2018 17:07:26 +0300
Subject: block: remove blkdev_entry_to_request() macro

Remove blkdev_entry_to_request() macro, which remained unused through
the observable history, also note that it repeats list_entry_rq() macro
verbatim.

Signed-off-by: Vladimir Zapolskiy <vz@mleia.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 137759862f07..1939ed95f936 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1436,8 +1436,6 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
-
 static inline unsigned long queue_segment_boundary(struct request_queue *q)
 {
 	return q->limits.seg_boundary_mask;
-- 
cgit v1.2.3


From ffc03fb7a52a88f87910d2b2418fd4e3069698e1 Mon Sep 17 00:00:00 2001
From: Marcin Dziegielewski <marcin.dziegielewski@intel.com>
Date: Fri, 13 Jul 2018 10:48:36 +0200
Subject: lightnvm: pblk: handle case when mw_cunits equals to 0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some devices can expose mw_cunits equal to 0, it can cause the
creation of too small write buffer and cause performance to drop
on write workloads.

Additionally, write buffer size must cover write data requirements,
such as WS_MIN and MW_CUNITS - it must be greater than or equal to
the larger one multiplied by the number of PUs. However, for
performance reasons, use the WS_OPT value to calculation instead of
WS_MIN.

Because the place where buffer size is calculated was changed, this
patch also removes pgs_in_buffer filed in pblk structure.

Signed-off-by: Marcin Dziegielewski <marcin.dziegielewski@intel.com>
Signed-off-by: Igor Konopko <igor.j.konopko@intel.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-init.c | 9 +++++----
 drivers/lightnvm/pblk.h      | 3 ---
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index b57f764d6a16..ef8d8dea7b6b 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -179,11 +179,14 @@ static int pblk_rwb_init(struct pblk *pblk)
 	struct pblk_rb_entry *entries;
 	unsigned long nr_entries, buffer_size;
 	unsigned int power_size, power_seg_sz;
+	int pgs_in_buffer;
 
-	if (write_buffer_size && (write_buffer_size > pblk->pgs_in_buffer))
+	pgs_in_buffer = max(geo->mw_cunits, geo->ws_opt) * geo->all_luns;
+
+	if (write_buffer_size && (write_buffer_size > pgs_in_buffer))
 		buffer_size = write_buffer_size;
 	else
-		buffer_size = pblk->pgs_in_buffer;
+		buffer_size = pgs_in_buffer;
 
 	nr_entries = pblk_rb_calculate_size(buffer_size);
 
@@ -366,8 +369,6 @@ static int pblk_core_init(struct pblk *pblk)
 	atomic64_set(&pblk->nr_flush, 0);
 	pblk->nr_flush_rst = 0;
 
-	pblk->pgs_in_buffer = geo->mw_cunits * geo->all_luns;
-
 	pblk->min_write_pgs = geo->ws_opt * (geo->csecs / PAGE_SIZE);
 	max_write_ppas = pblk->min_write_pgs * geo->all_luns;
 	pblk->max_write_pgs = min_t(int, max_write_ppas, NVM_MAX_VLBA);
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 34cc1d64a9d4..9d1a0e86e082 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -608,9 +608,6 @@ struct pblk {
 
 	int min_write_pgs; /* Minimum amount of pages required by controller */
 	int max_write_pgs; /* Maximum amount of pages supported by controller */
-	int pgs_in_buffer; /* Number of pages that need to be held in buffer to
-			    * guarantee successful reads.
-			    */
 
 	sector_t capacity; /* Device capacity when bad blocks are subtracted */
 
-- 
cgit v1.2.3


From 880eda544097a525b669df84533f439fb031684b Mon Sep 17 00:00:00 2001
From: Matias Bjørling <mb@lightnvm.io>
Date: Fri, 13 Jul 2018 10:48:37 +0200
Subject: lightnvm: move NVM_DEBUG to pblk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no users of CONFIG_NVM_DEBUG in the LightNVM subsystem. All
users are in pblk. Rename NVM_DEBUG to NVM_PBLK_DEBUG and enable
only for pblk.

Also fix up the CONFIG_NVM_PBLK entry to follow the code style for
Kconfig files.

Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/Kconfig      | 30 ++++++++++++++++--------------
 drivers/lightnvm/pblk-cache.c |  4 ++--
 drivers/lightnvm/pblk-core.c  | 26 +++++++++++++-------------
 drivers/lightnvm/pblk-gc.c    |  2 +-
 drivers/lightnvm/pblk-init.c  |  8 ++++----
 drivers/lightnvm/pblk-rb.c    | 16 ++++++++--------
 drivers/lightnvm/pblk-read.c  | 28 ++++++++++++++--------------
 drivers/lightnvm/pblk-sysfs.c |  8 ++++----
 drivers/lightnvm/pblk-write.c | 14 +++++++-------
 drivers/lightnvm/pblk.h       |  6 +++---
 10 files changed, 72 insertions(+), 70 deletions(-)

diff --git a/drivers/lightnvm/Kconfig b/drivers/lightnvm/Kconfig
index 9c03f35d9df1..439bf90d084d 100644
--- a/drivers/lightnvm/Kconfig
+++ b/drivers/lightnvm/Kconfig
@@ -17,23 +17,25 @@ menuconfig NVM
 
 if NVM
 
-config NVM_DEBUG
-	bool "Open-Channel SSD debugging support"
-	default n
-	---help---
-	Exposes a debug management interface to create/remove targets at:
+config NVM_PBLK
+	tristate "Physical Block Device Open-Channel SSD target"
+	help
+	  Allows an open-channel SSD to be exposed as a block device to the
+	  host. The target assumes the device exposes raw flash and must be
+	  explicitly managed by the host.
 
-	  /sys/module/lnvm/parameters/configure_debug
+	  Please note the disk format is considered EXPERIMENTAL for now.
 
-	It is required to create/remove targets without IOCTLs.
+if NVM_PBLK
 
-config NVM_PBLK
-	tristate "Physical Block Device Open-Channel SSD target"
-	---help---
-	Allows an open-channel SSD to be exposed as a block device to the
-	host. The target assumes the device exposes raw flash and must be
-	explicitly managed by the host.
+config NVM_PBLK_DEBUG
+	bool "PBlk Debug Support"
+	default n
+	help
+	  Enables debug support for pblk. This includes extra checks, more
+	  vocal error messages, and extra tracking fields in the pblk sysfs
+	  entries.
 
-	Please note the disk format is considered EXPERIMENTAL for now.
+endif # NVM_PBLK_DEBUG
 
 endif # NVM
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index b1c6d7eb6115..77d811962818 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -67,7 +67,7 @@ retry:
 
 	atomic64_add(nr_entries, &pblk->user_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_entries, &pblk->inflight_writes);
 	atomic_long_add(nr_entries, &pblk->req_writes);
 #endif
@@ -123,7 +123,7 @@ retry:
 
 	atomic64_add(valid_entries, &pblk->gc_wa);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_entries, &pblk->inflight_writes);
 	atomic_long_add(valid_entries, &pblk->recov_gc_writes);
 #endif
diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index ed9cc977c8b3..66ab1036f2fb 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -194,7 +194,7 @@ void pblk_map_invalidate(struct pblk *pblk, struct ppa_addr ppa)
 	u64 paddr;
 	int line_id;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_ppa_empty(ppa));
@@ -430,7 +430,7 @@ void pblk_discard(struct pblk *pblk, struct bio *bio)
 void pblk_log_write_err(struct pblk *pblk, struct nvm_rq *rqd)
 {
 	atomic_long_inc(&pblk->write_failed);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -454,7 +454,7 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
 	default:
 		pr_err("pblk: unknown read error:%d\n", rqd->error);
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 }
@@ -470,7 +470,7 @@ int pblk_submit_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -484,7 +484,7 @@ int pblk_submit_io_sync(struct pblk *pblk, struct nvm_rq *rqd)
 
 	atomic_inc(&pblk->inflight_io);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (pblk_check_io(pblk, rqd))
 		return NVM_IO_ERR;
 #endif
@@ -1726,7 +1726,7 @@ void pblk_line_close(struct pblk *pblk, struct pblk_line *line)
 	struct list_head *move_list;
 	int i;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN(!bitmap_full(line->map_bitmap, lm->sec_per_line),
 				"pblk: corrupt closed line %d\n", line->id);
 #endif
@@ -1856,7 +1856,7 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 	 * Only send one inflight I/O per LUN. Since we map at a page
 	 * granurality, all ppas in the I/O will map to the same LUN
 	 */
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1901,7 +1901,7 @@ void pblk_up_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
 	struct pblk_lun *rlun;
 	int pos = pblk_ppa_to_pos(geo, ppa_list[0]);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	int i;
 
 	for (i = 1; i < nr_ppas; i++)
@@ -1951,7 +1951,7 @@ void pblk_update_map(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 void pblk_update_map_cache(struct pblk *pblk, sector_t lba, struct ppa_addr ppa)
 {
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa)));
@@ -1966,7 +1966,7 @@ int pblk_update_map_gc(struct pblk *pblk, sector_t lba, struct ppa_addr ppa_new,
 	struct ppa_addr ppa_l2p, ppa_gc;
 	int ret = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(!pblk_addr_in_cache(ppa_new));
 	BUG_ON(pblk_rb_pos_oob(&pblk->rwb, pblk_addr_to_cacheline(ppa_new)));
@@ -2003,14 +2003,14 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 {
 	struct ppa_addr ppa_l2p;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a device address */
 	BUG_ON(pblk_addr_in_cache(ppa_mapped));
 #endif
 	/* Invalidate and discard padded entries */
 	if (lba == ADDR_EMPTY) {
 		atomic64_inc(&pblk->pad_wa);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->padded_wb);
 #endif
 		if (!pblk_ppa_empty(ppa_mapped))
@@ -2036,7 +2036,7 @@ void pblk_update_map_dev(struct pblk *pblk, sector_t lba,
 		goto out;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ON(!pblk_addr_in_cache(ppa_l2p) && !pblk_ppa_empty(ppa_l2p));
 #endif
 
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 080469d90b40..40d2dcb4f2bd 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -522,7 +522,7 @@ static int pblk_gc_reader_ts(void *data)
 		io_schedule();
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pr_info("pblk: flushing gc pipeline, %d lines left\n",
 		atomic_read(&gc->pipeline_gc));
 #endif
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index ef8d8dea7b6b..9ea30102f61c 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -91,7 +91,7 @@ static size_t pblk_trans_map_size(struct pblk *pblk)
 	return entry_size * pblk->rl.nr_secs;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static u32 pblk_l2p_crc(struct pblk *pblk)
 {
 	size_t map_size;
@@ -122,7 +122,7 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
 		}
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pr_info("pblk init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
@@ -1166,7 +1166,7 @@ static void pblk_exit(void *private, bool graceful)
 	pblk_gc_exit(pblk, graceful);
 	pblk_tear_down(pblk, graceful);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	pr_info("pblk exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
@@ -1217,7 +1217,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	spin_lock_init(&pblk->trans_lock);
 	spin_lock_init(&pblk->lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_set(&pblk->inflight_writes, 0);
 	atomic_long_set(&pblk->padded_writes, 0);
 	atomic_long_set(&pblk->padded_wb, 0);
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 55e9442a99e2..529def80966b 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -111,7 +111,7 @@ int pblk_rb_init(struct pblk_rb *rb, struct pblk_rb_entry *rb_entry_base,
 	} while (iter > 0);
 	up_write(&pblk_rb_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_set(&rb->inflight_flush_point, 0);
 #endif
 
@@ -308,7 +308,7 @@ void pblk_rb_write_entry_user(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -332,7 +332,7 @@ void pblk_rb_write_entry_gc(struct pblk_rb *rb, void *data,
 
 	entry = &rb->entries[ring_pos];
 	flags = READ_ONCE(entry->w_ctx.flags);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must guarantee that the entry is free */
 	BUG_ON(!(flags & PBLK_WRITABLE_ENTRY));
 #endif
@@ -362,7 +362,7 @@ static int pblk_rb_flush_point_set(struct pblk_rb *rb, struct bio *bio,
 		return 0;
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_inc(&rb->inflight_flush_point);
 #endif
 
@@ -588,7 +588,7 @@ try:
 		atomic64_add(pad, &pblk->pad_wa);
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(pad, &pblk->padded_writes);
 #endif
 
@@ -613,7 +613,7 @@ int pblk_rb_copy_to_bio(struct pblk_rb *rb, struct bio *bio, sector_t lba,
 	int ret = 1;
 
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Caller must ensure that the access will not cause an overflow */
 	BUG_ON(pos >= rb->nr_entries);
 #endif
@@ -820,7 +820,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
@@ -838,7 +838,7 @@ ssize_t pblk_rb_sysfs(struct pblk_rb *rb, char *buf)
 			rb->subm,
 			rb->sync,
 			rb->l2p_update,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_read(&rb->inflight_flush_point),
 #else
 			0,
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 18694694e5f0..6e93c489ce57 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -28,7 +28,7 @@ static int pblk_read_from_cache(struct pblk *pblk, struct bio *bio,
 				sector_t lba, struct ppa_addr ppa,
 				int bio_iter, bool advanced_bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Callers must ensure that the ppa points to a cache address */
 	BUG_ON(pblk_ppa_empty(ppa));
 	BUG_ON(!pblk_addr_in_cache(ppa));
@@ -79,7 +79,7 @@ retry:
 			WARN_ON(test_and_set_bit(i, read_bitmap));
 			meta_list[i].lba = cpu_to_le64(lba);
 			advanced_bio = true;
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_long_inc(&pblk->cache_reads);
 #endif
 		} else {
@@ -97,7 +97,7 @@ next:
 	else
 		rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(nr_secs, &pblk->inflight_reads);
 #endif
 }
@@ -117,7 +117,7 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 			continue;
 
 		if (lba != blba + i) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 
 			p = (nr_lbas == 1) ? &rqd->ppa_list[i] : &rqd->ppa_addr;
@@ -149,7 +149,7 @@ static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_lba = le64_to_cpu(meta_lba_list[j].lba);
 
 		if (lba != meta_lba) {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			struct ppa_addr *p;
 			int nr_ppas = rqd->nr_ppas;
 
@@ -185,7 +185,7 @@ static void pblk_read_put_rqd_kref(struct pblk *pblk, struct nvm_rq *rqd)
 
 static void pblk_end_user_read(struct bio *bio)
 {
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	WARN_ONCE(bio->bi_status, "pblk: corrupted read bio\n");
 #endif
 	bio_endio(bio);
@@ -212,7 +212,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	if (put_line)
 		pblk_read_put_rqd_kref(pblk, rqd);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_reads);
 	atomic_long_sub(rqd->nr_ppas, &pblk->inflight_reads);
 #endif
@@ -285,7 +285,7 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 
 	if (rqd->error) {
 		atomic_long_inc(&pblk->read_failed);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		pblk_print_failed_rqd(pblk, rqd, rqd->error);
 #endif
 	}
@@ -359,7 +359,7 @@ static void pblk_read_rq(struct pblk *pblk, struct nvm_rq *rqd, struct bio *bio,
 
 	pblk_lookup_l2p_seq(pblk, &ppa, lba, 1);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -382,7 +382,7 @@ retry:
 		WARN_ON(test_and_set_bit(0, read_bitmap));
 		meta_list[0].lba = cpu_to_le64(lba);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		atomic_long_inc(&pblk->cache_reads);
 #endif
 	} else {
@@ -514,7 +514,7 @@ static int read_ppalist_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 		rqd->ppa_list[valid_secs++] = ppa_list_l2p[i];
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(valid_secs, &pblk->inflight_reads);
 #endif
 
@@ -548,7 +548,7 @@ static int read_rq_gc(struct pblk *pblk, struct nvm_rq *rqd,
 	rqd->ppa_addr = ppa_l2p;
 	valid_secs = 1;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_inc(&pblk->inflight_reads);
 #endif
 
@@ -619,12 +619,12 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (rqd.error) {
 		atomic_long_inc(&pblk->read_failed_gc);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 		pblk_print_failed_rqd(pblk, &rqd, rqd.error);
 #endif
 	}
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->sync_reads);
 	atomic_long_add(gc_rq->secs_to_gc, &pblk->recov_gc_reads);
 	atomic_long_sub(gc_rq->secs_to_gc, &pblk->inflight_reads);
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index 88a0a7c407aa..b0e5e93a9d5f 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -421,7 +421,7 @@ static ssize_t pblk_sysfs_get_padding_dist(struct pblk *pblk, char *page)
 	return sz;
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static ssize_t pblk_sysfs_stats_debug(struct pblk *pblk, char *page)
 {
 	return snprintf(page, PAGE_SIZE,
@@ -598,7 +598,7 @@ static struct attribute sys_padding_dist = {
 	.mode = 0644,
 };
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static struct attribute sys_stats_debug_attr = {
 	.name = "stats",
 	.mode = 0444,
@@ -619,7 +619,7 @@ static struct attribute *pblk_attrs[] = {
 	&sys_write_amp_mileage,
 	&sys_write_amp_trip,
 	&sys_padding_dist,
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	&sys_stats_debug_attr,
 #endif
 	NULL,
@@ -654,7 +654,7 @@ static ssize_t pblk_sysfs_show(struct kobject *kobj, struct attribute *attr,
 		return pblk_sysfs_get_write_amp_trip(pblk, buf);
 	else if (strcmp(attr->name, "padding_dist") == 0)
 		return pblk_sysfs_get_padding_dist(pblk, buf);
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else if (strcmp(attr->name, "stats") == 0)
 		return pblk_sysfs_stats_debug(pblk, buf);
 #endif
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index f353e52941f5..5f44df999aed 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -38,7 +38,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 			/* Release flags on context. Protect from writes */
 			smp_store_release(&w_ctx->flags, flags);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 			atomic_dec(&rwb->inflight_flush_point);
 #endif
 		}
@@ -51,7 +51,7 @@ static unsigned long pblk_end_w_bio(struct pblk *pblk, struct nvm_rq *rqd,
 		pblk_bio_free_pages(pblk, rqd->bio, c_ctx->nr_valid,
 							c_ctx->nr_padded);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(rqd->nr_ppas, &pblk->sync_writes);
 #endif
 
@@ -78,7 +78,7 @@ static void pblk_complete_write(struct pblk *pblk, struct nvm_rq *rqd,
 	unsigned long flags;
 	unsigned long pos;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_sub(c_ctx->nr_valid, &pblk->inflight_writes);
 #endif
 
@@ -196,7 +196,7 @@ static void pblk_queue_resubmit(struct pblk *pblk, struct pblk_c_ctx *c_ctx)
 	list_add_tail(&r_ctx->list, &pblk->resubmit_list);
 	spin_unlock(&pblk->resubmit_lock);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(c_ctx->nr_valid, &pblk->recov_writes);
 #endif
 }
@@ -258,7 +258,7 @@ static void pblk_end_io_write(struct nvm_rq *rqd)
 		pblk_end_w_fail(pblk, rqd);
 		return;
 	}
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	else
 		WARN_ONCE(rqd->bio->bi_status, "pblk: corrupted write error\n");
 #endif
@@ -356,7 +356,7 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 
 	secs_to_sync = pblk_calc_secs(pblk, secs_avail, secs_to_flush);
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if ((!secs_to_sync && secs_to_flush)
 			|| (secs_to_sync < 0)
 			|| (secs_to_sync > secs_avail && !secs_to_flush)) {
@@ -640,7 +640,7 @@ static int pblk_submit_write(struct pblk *pblk)
 	if (pblk_submit_io_set(pblk, rqd))
 		goto fail_free_bio;
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_long_add(secs_to_sync, &pblk->sub_writes);
 #endif
 
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 9d1a0e86e082..c072955d72c2 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -193,7 +193,7 @@ struct pblk_rb {
 	spinlock_t w_lock;		/* Write lock */
 	spinlock_t s_lock;		/* Sync lock */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	atomic_t inflight_flush_point;	/* Not served REQ_FLUSH | REQ_FUA */
 #endif
 };
@@ -636,7 +636,7 @@ struct pblk {
 	u64 nr_flush_rst;		/* Flushes reset value for pad dist.*/
 	atomic64_t nr_flush;		/* Number of flush/fua I/O */
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	/* Non-persistent debug counters, 4kb sector I/Os */
 	atomic_long_t inflight_writes;	/* Inflight writes (user and gc) */
 	atomic_long_t padded_writes;	/* Sectors padded due to flush/fua */
@@ -1279,7 +1279,7 @@ static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs)
 	return !(nr_secs % pblk->min_write_pgs);
 }
 
-#ifdef CONFIG_NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 static inline void print_ppa(struct nvm_geo *geo, struct ppa_addr *p,
 			     char *msg, int error)
 {
-- 
cgit v1.2.3


From 99b8dad1b6e52721904220322a947f7b75056303 Mon Sep 17 00:00:00 2001
From: Matias Bjørling <mb@lightnvm.io>
Date: Fri, 13 Jul 2018 10:48:38 +0200
Subject: lightnvm: pblk: enable line minor version detection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When recovering a line, an extra check was added when debugging was
active, such that minor version where also checked. Unfortunately,
this used the ifdef NVM_DEBUG, which is not correct.

Instead use the proper DEBUG def, and now that it compiles, also fix
the variable.

Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Fixes: d0ab0b1ab991f ("lightnvm: pblk: check data lines version on recovery")
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-recovery.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index 3a5069183859..d83466b3821b 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -742,9 +742,10 @@ static int pblk_recov_check_line_version(struct pblk *pblk,
 		return 1;
 	}
 
-#ifdef NVM_DEBUG
+#ifdef CONFIG_NVM_PBLK_DEBUG
 	if (header->version_minor > EMETA_VERSION_MINOR)
-		pr_info("pblk: newer line minor version found: %d\n", line_v);
+		pr_info("pblk: newer line minor version found: %d\n",
+				header->version_minor);
 #endif
 
 	return 0;
-- 
cgit v1.2.3


From 242e461fb628bb63763e0bb2788d52ea054f8721 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 13 Jul 2018 10:48:39 +0200
Subject: lightnvm: Remove redundant rq->__data_len initialization
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since both blk_old_get_request() and blk_mq_alloc_request() initialize
rq->__data_len to zero, it is not necessary to initialize that member
in nvme_nvm_alloc_request(). Hence remove the rq->__data_len
initialization from nvme_nvm_alloc_request().

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/lightnvm.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 41279da799ed..a76db8820f1c 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -662,12 +662,10 @@ static struct request *nvme_nvm_alloc_request(struct request_queue *q,
 
 	rq->cmd_flags &= ~REQ_FAILFAST_DRIVER;
 
-	if (rqd->bio) {
+	if (rqd->bio)
 		blk_init_request_from_bio(rq, rqd->bio);
-	} else {
+	else
 		rq->ioprio = IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, IOPRIO_NORM);
-		rq->__data_len = 0;
-	}
 
 	return rq;
 }
-- 
cgit v1.2.3


From 921aebfac0871e8212913039d5241c0b3527eddb Mon Sep 17 00:00:00 2001
From: Matias Bjørling <mb@lightnvm.io>
Date: Fri, 13 Jul 2018 10:48:40 +0200
Subject: lightnvm: pblk: fix read_bitmap for 32bit archs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If using pblk on a 32bit architecture, and there is a need to
perform a partial read, the partial read bitmap will only have
allocated 32 entries, where as 64 are needed.

Make sure that the read_bitmap is initialized to 64bits on 32bit
architectures as well.

Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Igor Konopko <igor.j.konopko@intel.com>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-read.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 6e93c489ce57..bcfc6ea86e9d 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -401,7 +401,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	struct pblk_g_ctx *r_ctx;
 	struct nvm_rq *rqd;
 	unsigned int bio_init_idx;
-	unsigned long read_bitmap; /* Max 64 ppas per request */
+	DECLARE_BITMAP(read_bitmap, NVM_MAX_VLBA);
 	int ret = NVM_IO_ERR;
 
 	/* logic error: lba out-of-bounds. Ignore read request */
@@ -413,7 +413,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 
 	generic_start_io_acct(q, READ, bio_sectors(bio), &pblk->disk->part0);
 
-	bitmap_zero(&read_bitmap, nr_secs);
+	bitmap_zero(read_bitmap, nr_secs);
 
 	rqd = pblk_alloc_rqd(pblk, PBLK_READ);
 
@@ -444,19 +444,19 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		rqd->ppa_list = rqd->meta_list + pblk_dma_meta_size;
 		rqd->dma_ppa_list = rqd->dma_meta_list + pblk_dma_meta_size;
 
-		pblk_read_ppalist_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_ppalist_rq(pblk, rqd, bio, blba, read_bitmap);
 	} else {
-		pblk_read_rq(pblk, rqd, bio, blba, &read_bitmap);
+		pblk_read_rq(pblk, rqd, bio, blba, read_bitmap);
 	}
 
-	if (bitmap_full(&read_bitmap, nr_secs)) {
+	if (bitmap_full(read_bitmap, nr_secs)) {
 		atomic_inc(&pblk->inflight_io);
 		__pblk_end_io_read(pblk, rqd, false);
 		return NVM_IO_DONE;
 	}
 
 	/* All sectors are to be read from the device */
-	if (bitmap_empty(&read_bitmap, rqd->nr_ppas)) {
+	if (bitmap_empty(read_bitmap, rqd->nr_ppas)) {
 		struct bio *int_bio = NULL;
 
 		/* Clone read bio to deal with read errors internally */
@@ -480,7 +480,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	/* The read bio request could be partially filled by the write buffer,
 	 * but there are some holes that need to be read from the drive.
 	 */
-	return pblk_partial_read(pblk, rqd, bio, bio_init_idx, &read_bitmap);
+	return pblk_partial_read(pblk, rqd, bio, bio_init_idx, read_bitmap);
 
 fail_rqd_free:
 	pblk_free_rqd(pblk, rqd, PBLK_READ);
-- 
cgit v1.2.3


From 59a8f43b6341b6964a9956640bb0f21b083ccd66 Mon Sep 17 00:00:00 2001
From: Matias Bjørling <mb@lightnvm.io>
Date: Fri, 13 Jul 2018 10:48:41 +0200
Subject: lightnvm: limit get chunk meta request size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For devices that does not specify a limit on its transfer size, the
get_chk_meta command may send down a single I/O retrieving the full
chunk metadata table. Resulting in large 2-4MB I/O requests. Instead,
split up the I/Os to a maximum of 256KB and issue them separately to
reduce memory requirements.

Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/lightnvm.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index a76db8820f1c..d9e4cccd5b66 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -583,7 +583,13 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	struct ppa_addr ppa;
 	size_t left = nchks * sizeof(struct nvme_nvm_chk_meta);
 	size_t log_pos, offset, len;
-	int ret, i;
+	int ret, i, max_len;
+
+	/*
+	 * limit requests to maximum 256K to avoid issuing arbitrary large
+	 * requests when the device does not specific a maximum transfer size.
+	 */
+	max_len = min_t(unsigned int, ctrl->max_hw_sectors << 9, 256 * 1024);
 
 	/* Normalize lba address space to obtain log offset */
 	ppa.ppa = slba;
@@ -596,7 +602,7 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	offset = log_pos * sizeof(struct nvme_nvm_chk_meta);
 
 	while (left) {
-		len = min_t(unsigned int, left, ctrl->max_hw_sectors << 9);
+		len = min_t(unsigned int, left, max_len);
 
 		ret = nvme_get_log_ext(ctrl, ns, NVME_NVM_LOG_REPORT_CHUNK,
 				dev_meta, len, offset);
-- 
cgit v1.2.3


From 4e495a46b1039252f4af0c883e2cb31cc5f44145 Mon Sep 17 00:00:00 2001
From: Matias Bjørling <mb@lightnvm.io>
Date: Fri, 13 Jul 2018 10:48:42 +0200
Subject: lightnvm: pblk: expose generic disk name on pr_* msgs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The error messages in pblk does not say which pblk instance that
a message occurred from. Update each error message to reflect the
instance it belongs to, and also prefix it with pblk, so we know
the message comes from the pblk module.

Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c     | 51 ++++++++++++++-------------
 drivers/lightnvm/pblk-gc.c       | 32 ++++++++---------
 drivers/lightnvm/pblk-init.c     | 76 +++++++++++++++++++++-------------------
 drivers/lightnvm/pblk-rb.c       |  8 ++---
 drivers/lightnvm/pblk-read.c     | 25 ++++++-------
 drivers/lightnvm/pblk-recovery.c | 44 +++++++++++------------
 drivers/lightnvm/pblk-sysfs.c    |  5 ++-
 drivers/lightnvm/pblk-write.c    | 21 +++++------
 drivers/lightnvm/pblk.h          | 29 ++++++++++-----
 9 files changed, 153 insertions(+), 138 deletions(-)

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index 66ab1036f2fb..b829460fe827 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -35,7 +35,7 @@ static void pblk_line_mark_bb(struct work_struct *work)
 		line = &pblk->lines[pblk_ppa_to_line(*ppa)];
 		pos = pblk_ppa_to_pos(&dev->geo, *ppa);
 
-		pr_err("pblk: failed to mark bb, line:%d, pos:%d\n",
+		pblk_err(pblk, "failed to mark bb, line:%d, pos:%d\n",
 				line->id, pos);
 	}
 
@@ -51,12 +51,12 @@ static void pblk_mark_bb(struct pblk *pblk, struct pblk_line *line,
 	struct ppa_addr *ppa;
 	int pos = pblk_ppa_to_pos(geo, ppa_addr);
 
-	pr_debug("pblk: erase failed: line:%d, pos:%d\n", line->id, pos);
+	pblk_debug(pblk, "erase failed: line:%d, pos:%d\n", line->id, pos);
 	atomic_long_inc(&pblk->erase_failed);
 
 	atomic_dec(&line->blk_in_line);
 	if (test_and_set_bit(pos, line->blk_bitmap))
-		pr_err("pblk: attempted to erase bb: line:%d, pos:%d\n",
+		pblk_err(pblk, "attempted to erase bb: line:%d, pos:%d\n",
 							line->id, pos);
 
 	/* Not necessary to mark bad blocks on 2.0 spec. */
@@ -274,7 +274,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 		pool = &pblk->e_rq_pool;
 		break;
 	default:
-		pr_err("pblk: trying to free unknown rqd type\n");
+		pblk_err(pblk, "trying to free unknown rqd type\n");
 		return;
 	}
 
@@ -310,7 +310,7 @@ int pblk_bio_add_pages(struct pblk *pblk, struct bio *bio, gfp_t flags,
 
 		ret = bio_add_pc_page(q, bio, page, PBLK_EXPOSED_PAGE_SIZE, 0);
 		if (ret != PBLK_EXPOSED_PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			mempool_free(page, &pblk->page_bio_pool);
 			goto err;
 		}
@@ -410,7 +410,7 @@ struct list_head *pblk_line_gc_list(struct pblk *pblk, struct pblk_line *line)
 		line->state = PBLK_LINESTATE_CORRUPT;
 		line->gc_group = PBLK_LINEGC_NONE;
 		move_list =  &l_mg->corrupt_list;
-		pr_err("pblk: corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
+		pblk_err(pblk, "corrupted vsc for line %d, vsc:%d (%d/%d/%d)\n",
 						line->id, vsc,
 						line->sec_in_line,
 						lm->high_thrs, lm->mid_thrs);
@@ -452,7 +452,7 @@ void pblk_log_read_err(struct pblk *pblk, struct nvm_rq *rqd)
 		atomic_long_inc(&pblk->read_failed);
 		break;
 	default:
-		pr_err("pblk: unknown read error:%d\n", rqd->error);
+		pblk_err(pblk, "unknown read error:%d\n", rqd->error);
 	}
 #ifdef CONFIG_NVM_PBLK_DEBUG
 	pblk_print_failed_rqd(pblk, rqd, rqd->error);
@@ -517,7 +517,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 	for (i = 0; i < nr_secs; i++) {
 		page = vmalloc_to_page(kaddr);
 		if (!page) {
-			pr_err("pblk: could not map vmalloc bio\n");
+			pblk_err(pblk, "could not map vmalloc bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -525,7 +525,7 @@ struct bio *pblk_bio_map_addr(struct pblk *pblk, void *data,
 
 		ret = bio_add_pc_page(dev->q, bio, page, PAGE_SIZE, 0);
 		if (ret != PAGE_SIZE) {
-			pr_err("pblk: could not add page to bio\n");
+			pblk_err(pblk, "could not add page to bio\n");
 			bio_put(bio);
 			bio = ERR_PTR(-ENOMEM);
 			goto out;
@@ -711,7 +711,7 @@ next_rq:
 			while (test_bit(pos, line->blk_bitmap)) {
 				paddr += min;
 				if (pblk_boundary_paddr_checks(pblk, paddr)) {
-					pr_err("pblk: corrupt emeta line:%d\n",
+					pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 					bio_put(bio);
 					ret = -EINTR;
@@ -723,7 +723,7 @@ next_rq:
 			}
 
 			if (pblk_boundary_paddr_checks(pblk, paddr + min)) {
-				pr_err("pblk: corrupt emeta line:%d\n",
+				pblk_err(pblk, "corrupt emeta line:%d\n",
 								line->id);
 				bio_put(bio);
 				ret = -EINTR;
@@ -738,7 +738,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_rqd_dma;
 	}
@@ -843,7 +843,7 @@ static int pblk_line_submit_smeta_io(struct pblk *pblk, struct pblk_line *line,
 	 */
 	ret = pblk_submit_io_sync(pblk, &rqd);
 	if (ret) {
-		pr_err("pblk: smeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "smeta I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		goto free_ppa_list;
 	}
@@ -905,7 +905,7 @@ static int pblk_blk_erase_sync(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not sync erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not sync erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 
@@ -945,7 +945,7 @@ int pblk_line_erase(struct pblk *pblk, struct pblk_line *line)
 
 		ret = pblk_blk_erase_sync(pblk, ppa);
 		if (ret) {
-			pr_err("pblk: failed to erase line %d\n", line->id);
+			pblk_err(pblk, "failed to erase line %d\n", line->id);
 			return ret;
 		}
 	} while (1);
@@ -1012,7 +1012,7 @@ static int pblk_line_init_metadata(struct pblk *pblk, struct pblk_line *line,
 		list_add_tail(&line->list, &l_mg->bad_list);
 		spin_unlock(&l_mg->free_lock);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1122,7 +1122,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 	line->cur_sec = off + lm->smeta_sec;
 
 	if (init && pblk_line_submit_smeta_io(pblk, line, off, PBLK_WRITE)) {
-		pr_debug("pblk: line smeta I/O failed. Retry\n");
+		pblk_debug(pblk, "line smeta I/O failed. Retry\n");
 		return 0;
 	}
 
@@ -1154,7 +1154,7 @@ static int pblk_line_init_bb(struct pblk *pblk, struct pblk_line *line,
 		spin_unlock(&line->lock);
 
 		list_add_tail(&line->list, &l_mg->bad_list);
-		pr_err("pblk: unexpected line %d is bad\n", line->id);
+		pblk_err(pblk, "unexpected line %d is bad\n", line->id);
 
 		return 0;
 	}
@@ -1299,7 +1299,7 @@ struct pblk_line *pblk_line_get(struct pblk *pblk)
 
 retry:
 	if (list_empty(&l_mg->free_list)) {
-		pr_err("pblk: no free lines\n");
+		pblk_err(pblk, "no free lines\n");
 		return NULL;
 	}
 
@@ -1315,7 +1315,7 @@ retry:
 
 		list_add_tail(&line->list, &l_mg->bad_list);
 
-		pr_debug("pblk: line %d is bad\n", line->id);
+		pblk_debug(pblk, "line %d is bad\n", line->id);
 		goto retry;
 	}
 
@@ -1329,7 +1329,7 @@ retry:
 			list_add(&line->list, &l_mg->corrupt_list);
 			goto retry;
 		default:
-			pr_err("pblk: failed to prepare line %d\n", line->id);
+			pblk_err(pblk, "failed to prepare line %d\n", line->id);
 			list_add(&line->list, &l_mg->free_list);
 			l_mg->nr_free_lines++;
 			return NULL;
@@ -1477,7 +1477,7 @@ static void pblk_line_close_meta_sync(struct pblk *pblk)
 
 			ret = pblk_submit_meta_io(pblk, line);
 			if (ret) {
-				pr_err("pblk: sync meta line %d failed (%d)\n",
+				pblk_err(pblk, "sync meta line %d failed (%d)\n",
 							line->id, ret);
 				return;
 			}
@@ -1507,7 +1507,7 @@ void __pblk_pipeline_flush(struct pblk *pblk)
 
 	ret = pblk_recov_pad(pblk);
 	if (ret) {
-		pr_err("pblk: could not close data on teardown(%d)\n", ret);
+		pblk_err(pblk, "could not close data on teardown(%d)\n", ret);
 		return;
 	}
 
@@ -1687,7 +1687,7 @@ int pblk_blk_erase_async(struct pblk *pblk, struct ppa_addr ppa)
 		struct nvm_tgt_dev *dev = pblk->dev;
 		struct nvm_geo *geo = &dev->geo;
 
-		pr_err("pblk: could not async erase line:%d,blk:%d\n",
+		pblk_err(pblk, "could not async erase line:%d,blk:%d\n",
 					pblk_ppa_to_line(ppa),
 					pblk_ppa_to_pos(geo, ppa));
 	}
@@ -1866,7 +1866,8 @@ static void __pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list,
 
 	ret = down_timeout(&rlun->wr_sem, msecs_to_jiffies(30000));
 	if (ret == -ETIME || ret == -EINTR)
-		pr_err("pblk: taking lun semaphore timed out: err %d\n", -ret);
+		pblk_err(pblk, "taking lun semaphore timed out: err %d\n",
+				-ret);
 }
 
 void pblk_down_page(struct pblk *pblk, struct ppa_addr *ppa_list, int nr_ppas)
diff --git a/drivers/lightnvm/pblk-gc.c b/drivers/lightnvm/pblk-gc.c
index 40d2dcb4f2bd..157c2567c9e8 100644
--- a/drivers/lightnvm/pblk-gc.c
+++ b/drivers/lightnvm/pblk-gc.c
@@ -90,7 +90,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 
 	gc_rq->data = vmalloc(array_size(gc_rq->nr_secs, geo->csecs));
 	if (!gc_rq->data) {
-		pr_err("pblk: could not GC line:%d (%d/%d)\n",
+		pblk_err(pblk, "could not GC line:%d (%d/%d)\n",
 					line->id, *line->vsc, gc_rq->nr_secs);
 		goto out;
 	}
@@ -98,7 +98,7 @@ static void pblk_gc_line_ws(struct work_struct *work)
 	/* Read from GC victim block */
 	ret = pblk_submit_read_gc(pblk, gc_rq);
 	if (ret) {
-		pr_err("pblk: failed GC read in line:%d (err:%d)\n",
+		pblk_err(pblk, "failed GC read in line:%d (err:%d)\n",
 								line->id, ret);
 		goto out;
 	}
@@ -146,7 +146,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_line_read_emeta(pblk, line, emeta_buf);
 	if (ret) {
-		pr_err("pblk: line %d read emeta failed (%d)\n",
+		pblk_err(pblk, "line %d read emeta failed (%d)\n",
 				line->id, ret);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -160,7 +160,7 @@ static __le64 *get_lba_list_from_emeta(struct pblk *pblk,
 
 	ret = pblk_recov_check_emeta(pblk, emeta_buf);
 	if (ret) {
-		pr_err("pblk: inconsistent emeta (line %d)\n",
+		pblk_err(pblk, "inconsistent emeta (line %d)\n",
 				line->id);
 		pblk_mfree(emeta_buf, l_mg->emeta_alloc_type);
 		return NULL;
@@ -201,7 +201,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	} else {
 		lba_list = get_lba_list_from_emeta(pblk, line);
 		if (!lba_list) {
-			pr_err("pblk: could not interpret emeta (line %d)\n",
+			pblk_err(pblk, "could not interpret emeta (line %d)\n",
 					line->id);
 			goto fail_free_invalid_bitmap;
 		}
@@ -213,7 +213,7 @@ static void pblk_gc_line_prepare_ws(struct work_struct *work)
 	spin_unlock(&line->lock);
 
 	if (sec_left < 0) {
-		pr_err("pblk: corrupted GC line (%d)\n", line->id);
+		pblk_err(pblk, "corrupted GC line (%d)\n", line->id);
 		goto fail_free_lba_list;
 	}
 
@@ -289,7 +289,7 @@ fail_free_ws:
 	kref_put(&line->ref, pblk_line_put);
 	atomic_dec(&gc->read_inflight_gc);
 
-	pr_err("pblk: Failed to GC line %d\n", line->id);
+	pblk_err(pblk, "failed to GC line %d\n", line->id);
 }
 
 static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
@@ -297,7 +297,7 @@ static int pblk_gc_line(struct pblk *pblk, struct pblk_line *line)
 	struct pblk_gc *gc = &pblk->gc;
 	struct pblk_line_ws *line_ws;
 
-	pr_debug("pblk: line '%d' being reclaimed for GC\n", line->id);
+	pblk_debug(pblk, "line '%d' being reclaimed for GC\n", line->id);
 
 	line_ws = kmalloc(sizeof(struct pblk_line_ws), GFP_KERNEL);
 	if (!line_ws)
@@ -351,7 +351,7 @@ static int pblk_gc_read(struct pblk *pblk)
 	pblk_gc_kick(pblk);
 
 	if (pblk_gc_line(pblk, line))
-		pr_err("pblk: failed to GC line %d\n", line->id);
+		pblk_err(pblk, "failed to GC line %d\n", line->id);
 
 	return 0;
 }
@@ -523,7 +523,7 @@ static int pblk_gc_reader_ts(void *data)
 	}
 
 #ifdef CONFIG_NVM_PBLK_DEBUG
-	pr_info("pblk: flushing gc pipeline, %d lines left\n",
+	pblk_info(pblk, "flushing gc pipeline, %d lines left\n",
 		atomic_read(&gc->pipeline_gc));
 #endif
 
@@ -540,7 +540,7 @@ static int pblk_gc_reader_ts(void *data)
 static void pblk_gc_start(struct pblk *pblk)
 {
 	pblk->gc.gc_active = 1;
-	pr_debug("pblk: gc start\n");
+	pblk_debug(pblk, "gc start\n");
 }
 
 void pblk_gc_should_start(struct pblk *pblk)
@@ -605,14 +605,14 @@ int pblk_gc_init(struct pblk *pblk)
 
 	gc->gc_ts = kthread_create(pblk_gc_ts, pblk, "pblk-gc-ts");
 	if (IS_ERR(gc->gc_ts)) {
-		pr_err("pblk: could not allocate GC main kthread\n");
+		pblk_err(pblk, "could not allocate GC main kthread\n");
 		return PTR_ERR(gc->gc_ts);
 	}
 
 	gc->gc_writer_ts = kthread_create(pblk_gc_writer_ts, pblk,
 							"pblk-gc-writer-ts");
 	if (IS_ERR(gc->gc_writer_ts)) {
-		pr_err("pblk: could not allocate GC writer kthread\n");
+		pblk_err(pblk, "could not allocate GC writer kthread\n");
 		ret = PTR_ERR(gc->gc_writer_ts);
 		goto fail_free_main_kthread;
 	}
@@ -620,7 +620,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_ts = kthread_create(pblk_gc_reader_ts, pblk,
 							"pblk-gc-reader-ts");
 	if (IS_ERR(gc->gc_reader_ts)) {
-		pr_err("pblk: could not allocate GC reader kthread\n");
+		pblk_err(pblk, "could not allocate GC reader kthread\n");
 		ret = PTR_ERR(gc->gc_reader_ts);
 		goto fail_free_writer_kthread;
 	}
@@ -641,7 +641,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_line_reader_wq = alloc_workqueue("pblk-gc-line-reader-wq",
 			WQ_MEM_RECLAIM | WQ_UNBOUND, PBLK_GC_MAX_READERS);
 	if (!gc->gc_line_reader_wq) {
-		pr_err("pblk: could not allocate GC line reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC line reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_kthread;
 	}
@@ -650,7 +650,7 @@ int pblk_gc_init(struct pblk *pblk)
 	gc->gc_reader_wq = alloc_workqueue("pblk-gc-line_wq",
 					WQ_MEM_RECLAIM | WQ_UNBOUND, 1);
 	if (!gc->gc_reader_wq) {
-		pr_err("pblk: could not allocate GC reader workqueue\n");
+		pblk_err(pblk, "could not allocate GC reader workqueue\n");
 		ret = -ENOMEM;
 		goto fail_free_reader_line_wq;
 	}
diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index 9ea30102f61c..d023ea6116bc 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -117,13 +117,13 @@ static int pblk_l2p_recover(struct pblk *pblk, bool factory_init)
 	} else {
 		line = pblk_recov_l2p(pblk);
 		if (IS_ERR(line)) {
-			pr_err("pblk: could not recover l2p table\n");
+			pblk_err(pblk, "could not recover l2p table\n");
 			return -EFAULT;
 		}
 	}
 
 #ifdef CONFIG_NVM_PBLK_DEBUG
-	pr_info("pblk init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+	pblk_info(pblk, "init: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	/* Free full lines directly as GC has not been started yet */
@@ -166,7 +166,7 @@ static int pblk_l2p_init(struct pblk *pblk, bool factory_init)
 static void pblk_rwb_free(struct pblk *pblk)
 {
 	if (pblk_rb_tear_down_check(&pblk->rwb))
-		pr_err("pblk: write buffer error on tear down\n");
+		pblk_err(pblk, "write buffer error on tear down\n");
 
 	pblk_rb_data_free(&pblk->rwb);
 	vfree(pblk_rb_entries_ref(&pblk->rwb));
@@ -203,7 +203,8 @@ static int pblk_rwb_init(struct pblk *pblk)
 /* Minimum pages needed within a lun */
 #define ADDR_POOL_SIZE 64
 
-static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
+static int pblk_set_addrf_12(struct pblk *pblk, struct nvm_geo *geo,
+			     struct nvm_addrf_12 *dst)
 {
 	struct nvm_addrf_12 *src = (struct nvm_addrf_12 *)&geo->addrf;
 	int power_len;
@@ -211,14 +212,14 @@ static int pblk_set_addrf_12(struct nvm_geo *geo, struct nvm_addrf_12 *dst)
 	/* Re-calculate channel and lun format to adapt to configuration */
 	power_len = get_count_order(geo->num_ch);
 	if (1 << power_len != geo->num_ch) {
-		pr_err("pblk: supports only power-of-two channel config.\n");
+		pblk_err(pblk, "supports only power-of-two channel config.\n");
 		return -EINVAL;
 	}
 	dst->ch_len = power_len;
 
 	power_len = get_count_order(geo->num_lun);
 	if (1 << power_len != geo->num_lun) {
-		pr_err("pblk: supports only power-of-two LUN config.\n");
+		pblk_err(pblk, "supports only power-of-two LUN config.\n");
 		return -EINVAL;
 	}
 	dst->lun_len = power_len;
@@ -285,18 +286,19 @@ static int pblk_set_addrf(struct pblk *pblk)
 	case NVM_OCSSD_SPEC_12:
 		div_u64_rem(geo->clba, pblk->min_write_pgs, &mod);
 		if (mod) {
-			pr_err("pblk: bad configuration of sectors/pages\n");
+			pblk_err(pblk, "bad configuration of sectors/pages\n");
 			return -EINVAL;
 		}
 
-		pblk->addrf_len = pblk_set_addrf_12(geo, (void *)&pblk->addrf);
+		pblk->addrf_len = pblk_set_addrf_12(pblk, geo,
+							(void *)&pblk->addrf);
 		break;
 	case NVM_OCSSD_SPEC_20:
 		pblk->addrf_len = pblk_set_addrf_20(geo, (void *)&pblk->addrf,
-								&pblk->uaddrf);
+							&pblk->uaddrf);
 		break;
 	default:
-		pr_err("pblk: OCSSD revision not supported (%d)\n",
+		pblk_err(pblk, "OCSSD revision not supported (%d)\n",
 								geo->version);
 		return -EINVAL;
 	}
@@ -375,7 +377,7 @@ static int pblk_core_init(struct pblk *pblk)
 	pblk_set_sec_per_write(pblk, pblk->min_write_pgs);
 
 	if (pblk->max_write_pgs > PBLK_MAX_REQ_ADDRS) {
-		pr_err("pblk: vector list too big(%u > %u)\n",
+		pblk_err(pblk, "vector list too big(%u > %u)\n",
 				pblk->max_write_pgs, PBLK_MAX_REQ_ADDRS);
 		return -EINVAL;
 	}
@@ -608,7 +610,7 @@ static int pblk_luns_init(struct pblk *pblk)
 
 	/* TODO: Implement unbalanced LUN support */
 	if (geo->num_lun < 0) {
-		pr_err("pblk: unbalanced LUN config.\n");
+		pblk_err(pblk, "unbalanced LUN config.\n");
 		return -EINVAL;
 	}
 
@@ -1027,7 +1029,7 @@ add_emeta_page:
 					lm->emeta_sec[0], geo->clba);
 
 	if (lm->min_blk_line > lm->blk_per_line) {
-		pr_err("pblk: config. not supported. Min. LUN in line:%d\n",
+		pblk_err(pblk, "config. not supported. Min. LUN in line:%d\n",
 							lm->blk_per_line);
 		return -EINVAL;
 	}
@@ -1079,7 +1081,7 @@ static int pblk_lines_init(struct pblk *pblk)
 	}
 
 	if (!nr_free_chks) {
-		pr_err("pblk: too many bad blocks prevent for sane instance\n");
+		pblk_err(pblk, "too many bad blocks prevent for sane instance\n");
 		return -EINTR;
 	}
 
@@ -1109,7 +1111,7 @@ static int pblk_writer_init(struct pblk *pblk)
 		int err = PTR_ERR(pblk->writer_ts);
 
 		if (err != -EINTR)
-			pr_err("pblk: could not allocate writer kthread (%d)\n",
+			pblk_err(pblk, "could not allocate writer kthread (%d)\n",
 					err);
 		return err;
 	}
@@ -1155,7 +1157,7 @@ static void pblk_tear_down(struct pblk *pblk, bool graceful)
 	pblk_rb_sync_l2p(&pblk->rwb);
 	pblk_rl_free(&pblk->rl);
 
-	pr_debug("pblk: consistent tear down (graceful:%d)\n", graceful);
+	pblk_debug(pblk, "consistent tear down (graceful:%d)\n", graceful);
 }
 
 static void pblk_exit(void *private, bool graceful)
@@ -1167,7 +1169,7 @@ static void pblk_exit(void *private, bool graceful)
 	pblk_tear_down(pblk, graceful);
 
 #ifdef CONFIG_NVM_PBLK_DEBUG
-	pr_info("pblk exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
+	pblk_info(pblk, "exit: L2P CRC: %x\n", pblk_l2p_crc(pblk));
 #endif
 
 	pblk_free(pblk);
@@ -1190,29 +1192,30 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	struct pblk *pblk;
 	int ret;
 
-	/* pblk supports 1.2 and 2.0 versions */
+	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
+	if (!pblk)
+		return ERR_PTR(-ENOMEM);
+
+	pblk->dev = dev;
+	pblk->disk = tdisk;
+	pblk->state = PBLK_STATE_RUNNING;
+	pblk->gc.gc_enabled = 0;
+
 	if (!(geo->version == NVM_OCSSD_SPEC_12 ||
 					geo->version == NVM_OCSSD_SPEC_20)) {
-		pr_err("pblk: OCSSD version not supported (%u)\n",
+		pblk_err(pblk, "OCSSD version not supported (%u)\n",
 							geo->version);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
 	if (geo->version == NVM_OCSSD_SPEC_12 && geo->dom & NVM_RSP_L2P) {
-		pr_err("pblk: host-side L2P table not supported. (%x)\n",
+		pblk_err(pblk, "host-side L2P table not supported. (%x)\n",
 							geo->dom);
+		kfree(pblk);
 		return ERR_PTR(-EINVAL);
 	}
 
-	pblk = kzalloc(sizeof(struct pblk), GFP_KERNEL);
-	if (!pblk)
-		return ERR_PTR(-ENOMEM);
-
-	pblk->dev = dev;
-	pblk->disk = tdisk;
-	pblk->state = PBLK_STATE_RUNNING;
-	pblk->gc.gc_enabled = 0;
-
 	spin_lock_init(&pblk->resubmit_lock);
 	spin_lock_init(&pblk->trans_lock);
 	spin_lock_init(&pblk->lock);
@@ -1242,38 +1245,38 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 
 	ret = pblk_core_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize core\n");
+		pblk_err(pblk, "could not initialize core\n");
 		goto fail;
 	}
 
 	ret = pblk_lines_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize lines\n");
+		pblk_err(pblk, "could not initialize lines\n");
 		goto fail_free_core;
 	}
 
 	ret = pblk_rwb_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize write buffer\n");
+		pblk_err(pblk, "could not initialize write buffer\n");
 		goto fail_free_lines;
 	}
 
 	ret = pblk_l2p_init(pblk, flags & NVM_TARGET_FACTORY);
 	if (ret) {
-		pr_err("pblk: could not initialize maps\n");
+		pblk_err(pblk, "could not initialize maps\n");
 		goto fail_free_rwb;
 	}
 
 	ret = pblk_writer_init(pblk);
 	if (ret) {
 		if (ret != -EINTR)
-			pr_err("pblk: could not initialize write thread\n");
+			pblk_err(pblk, "could not initialize write thread\n");
 		goto fail_free_l2p;
 	}
 
 	ret = pblk_gc_init(pblk);
 	if (ret) {
-		pr_err("pblk: could not initialize gc\n");
+		pblk_err(pblk, "could not initialize gc\n");
 		goto fail_stop_writer;
 	}
 
@@ -1288,8 +1291,7 @@ static void *pblk_init(struct nvm_tgt_dev *dev, struct gendisk *tdisk,
 	blk_queue_max_discard_sectors(tqueue, UINT_MAX >> 9);
 	blk_queue_flag_set(QUEUE_FLAG_DISCARD, tqueue);
 
-	pr_info("pblk(%s): luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
-			tdisk->disk_name,
+	pblk_info(pblk, "luns:%u, lines:%d, secs:%llu, buf entries:%u\n",
 			geo->all_luns, pblk->l_mg.nr_lines,
 			(unsigned long long)pblk->rl.nr_secs,
 			pblk->rwb.nr_entries);
diff --git a/drivers/lightnvm/pblk-rb.c b/drivers/lightnvm/pblk-rb.c
index 529def80966b..f6eec0212dfc 100644
--- a/drivers/lightnvm/pblk-rb.c
+++ b/drivers/lightnvm/pblk-rb.c
@@ -547,7 +547,7 @@ try:
 
 		page = virt_to_page(entry->data);
 		if (!page) {
-			pr_err("pblk: could not allocate write bio page\n");
+			pblk_err(pblk, "could not allocate write bio page\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -557,7 +557,7 @@ try:
 
 		if (bio_add_pc_page(q, bio, page, rb->seg_size, 0) !=
 								rb->seg_size) {
-			pr_err("pblk: could not add page to write bio\n");
+			pblk_err(pblk, "could not add page to write bio\n");
 			flags &= ~PBLK_WRITTEN_DATA;
 			flags |= PBLK_SUBMITTED_ENTRY;
 			/* Release flags on context. Protect from writes */
@@ -576,14 +576,14 @@ try:
 
 	if (pad) {
 		if (pblk_bio_add_pages(pblk, bio, GFP_KERNEL, pad)) {
-			pr_err("pblk: could not pad page in write bio\n");
+			pblk_err(pblk, "could not pad page in write bio\n");
 			return NVM_IO_ERR;
 		}
 
 		if (pad < pblk->min_write_pgs)
 			atomic64_inc(&pblk->pad_dist[pad - 1]);
 		else
-			pr_warn("pblk: padding more than min. sectors\n");
+			pblk_warn(pblk, "padding more than min. sectors\n");
 
 		atomic64_add(pad, &pblk->pad_wa);
 	}
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index bcfc6ea86e9d..9c9362b20861 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -121,9 +121,9 @@ static void pblk_read_check_seq(struct pblk *pblk, struct nvm_rq *rqd,
 			struct ppa_addr *p;
 
 			p = (nr_lbas == 1) ? &rqd->ppa_list[i] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", i);
+			print_ppa(pblk, p, "seq", i);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 							lba, (u64)blba + i);
 			WARN_ON(1);
 		}
@@ -154,9 +154,9 @@ static void pblk_read_check_rand(struct pblk *pblk, struct nvm_rq *rqd,
 			int nr_ppas = rqd->nr_ppas;
 
 			p = (nr_ppas == 1) ? &rqd->ppa_list[j] : &rqd->ppa_addr;
-			print_ppa(&pblk->dev->geo, p, "seq", j);
+			print_ppa(pblk, p, "seq", j);
 #endif
-			pr_err("pblk: corrupted read LBA (%llu/%llu)\n",
+			pblk_err(pblk, "corrupted read LBA (%llu/%llu)\n",
 								lba, meta_lba);
 			WARN_ON(1);
 		}
@@ -256,7 +256,7 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 		goto fail_add_pages;
 
 	if (nr_holes != new_bio->bi_vcnt) {
-		pr_err("pblk: malformed bio\n");
+		pblk_err(pblk, "malformed bio\n");
 		goto fail;
 	}
 
@@ -279,7 +279,7 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
 		bio_put(rqd->bio);
-		pr_err("pblk: sync read IO submission failed\n");
+		pblk_err(pblk, "sync read IO submission failed\n");
 		goto fail;
 	}
 
@@ -346,7 +346,7 @@ fail:
 	/* Free allocated pages in new bio */
 	pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt);
 fail_add_pages:
-	pr_err("pblk: failed to perform partial read\n");
+	pblk_err(pblk, "failed to perform partial read\n");
 	__pblk_end_io_read(pblk, rqd, false);
 	return NVM_IO_ERR;
 }
@@ -436,7 +436,7 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	rqd->meta_list = nvm_dev_dma_alloc(dev->parent, GFP_KERNEL,
 							&rqd->dma_meta_list);
 	if (!rqd->meta_list) {
-		pr_err("pblk: not able to allocate ppa list\n");
+		pblk_err(pblk, "not able to allocate ppa list\n");
 		goto fail_rqd_free;
 	}
 
@@ -462,14 +462,14 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		/* Clone read bio to deal with read errors internally */
 		int_bio = bio_clone_fast(bio, GFP_KERNEL, &pblk_bio_set);
 		if (!int_bio) {
-			pr_err("pblk: could not clone read bio\n");
+			pblk_err(pblk, "could not clone read bio\n");
 			goto fail_end_io;
 		}
 
 		rqd->bio = int_bio;
 
 		if (pblk_submit_io(pblk, rqd)) {
-			pr_err("pblk: read IO submission failed\n");
+			pblk_err(pblk, "read IO submission failed\n");
 			ret = NVM_IO_ERR;
 			goto fail_end_io;
 		}
@@ -595,7 +595,8 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 	bio = pblk_bio_map_addr(pblk, gc_rq->data, gc_rq->secs_to_gc, data_len,
 						PBLK_VMALLOC_META, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: could not allocate GC bio (%lu)\n", PTR_ERR(bio));
+		pblk_err(pblk, "could not allocate GC bio (%lu)\n",
+				PTR_ERR(bio));
 		goto err_free_dma;
 	}
 
@@ -609,7 +610,7 @@ int pblk_submit_read_gc(struct pblk *pblk, struct pblk_gc_rq *gc_rq)
 
 	if (pblk_submit_io_sync(pblk, &rqd)) {
 		ret = -EIO;
-		pr_err("pblk: GC read request failed\n");
+		pblk_err(pblk, "GC read request failed\n");
 		goto err_free_bio;
 	}
 
diff --git a/drivers/lightnvm/pblk-recovery.c b/drivers/lightnvm/pblk-recovery.c
index d83466b3821b..e232e47e1353 100644
--- a/drivers/lightnvm/pblk-recovery.c
+++ b/drivers/lightnvm/pblk-recovery.c
@@ -77,7 +77,7 @@ static int pblk_recov_l2p_from_emeta(struct pblk *pblk, struct pblk_line *line)
 	}
 
 	if (nr_valid_lbas != nr_lbas)
-		pr_err("pblk: line %d - inconsistent lba list(%llu/%llu)\n",
+		pblk_err(pblk, "line %d - inconsistent lba list(%llu/%llu)\n",
 				line->id, nr_valid_lbas, nr_lbas);
 
 	line->left_msecs = 0;
@@ -184,7 +184,7 @@ next_read_rq:
 	/* If read fails, more padding is needed */
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -194,7 +194,7 @@ next_read_rq:
 	 * we cannot recover from here. Need FTL log.
 	 */
 	if (rqd->error && rqd->error != NVM_RSP_WARN_HIGHECC) {
-		pr_err("pblk: L2P recovery failed (%d)\n", rqd->error);
+		pblk_err(pblk, "L2P recovery failed (%d)\n", rqd->error);
 		return -EINTR;
 	}
 
@@ -273,7 +273,7 @@ static int pblk_recov_pad_oob(struct pblk *pblk, struct pblk_line *line,
 next_pad_rq:
 	rq_ppas = pblk_calc_secs(pblk, left_ppas, 0);
 	if (rq_ppas < pblk->min_write_pgs) {
-		pr_err("pblk: corrupted pad line %d\n", line->id);
+		pblk_err(pblk, "corrupted pad line %d\n", line->id);
 		goto fail_free_pad;
 	}
 
@@ -342,7 +342,7 @@ next_pad_rq:
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		pblk_up_page(pblk, rqd->ppa_list, rqd->nr_ppas);
 		goto fail_free_bio;
 	}
@@ -356,12 +356,12 @@ next_pad_rq:
 
 	if (!wait_for_completion_io_timeout(&pad_rq->wait,
 				msecs_to_jiffies(PBLK_COMMAND_TIMEOUT_MS))) {
-		pr_err("pblk: pad write timed out\n");
+		pblk_err(pblk, "pad write timed out\n");
 		ret = -ETIME;
 	}
 
 	if (!pblk_line_is_full(line))
-		pr_err("pblk: corrupted padded line: %d\n", line->id);
+		pblk_err(pblk, "corrupted padded line: %d\n", line->id);
 
 	vfree(data);
 free_rq:
@@ -461,7 +461,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		return ret;
 	}
 
@@ -501,11 +501,11 @@ next_rq:
 
 		ret = pblk_recov_pad_oob(pblk, line, pad_secs);
 		if (ret)
-			pr_err("pblk: OOB padding failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB padding failed (err:%d)\n", ret);
 
 		ret = pblk_recov_read_oob(pblk, line, p, r_ptr);
 		if (ret)
-			pr_err("pblk: OOB read failed (err:%d)\n", ret);
+			pblk_err(pblk, "OOB read failed (err:%d)\n", ret);
 
 		left_ppas = 0;
 	}
@@ -592,7 +592,7 @@ next_rq:
 
 	ret = pblk_submit_io_sync(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "I/O submission failed: %d\n", ret);
 		bio_put(bio);
 		return ret;
 	}
@@ -671,14 +671,14 @@ static int pblk_recov_l2p_from_oob(struct pblk *pblk, struct pblk_line *line)
 
 	ret = pblk_recov_scan_oob(pblk, line, p, &done);
 	if (ret) {
-		pr_err("pblk: could not recover L2P from OOB\n");
+		pblk_err(pblk, "could not recover L2P from OOB\n");
 		goto out;
 	}
 
 	if (!done) {
 		ret = pblk_recov_scan_all_oob(pblk, line, p);
 		if (ret) {
-			pr_err("pblk: could not recover L2P from OOB\n");
+			pblk_err(pblk, "could not recover L2P from OOB\n");
 			goto out;
 		}
 	}
@@ -737,14 +737,14 @@ static int pblk_recov_check_line_version(struct pblk *pblk,
 	struct line_header *header = &emeta->header;
 
 	if (header->version_major != EMETA_VERSION_MAJOR) {
-		pr_err("pblk: line major version mismatch: %d, expected: %d\n",
-		       header->version_major, EMETA_VERSION_MAJOR);
+		pblk_err(pblk, "line major version mismatch: %d, expected: %d\n",
+			 header->version_major, EMETA_VERSION_MAJOR);
 		return 1;
 	}
 
 #ifdef CONFIG_NVM_PBLK_DEBUG
 	if (header->version_minor > EMETA_VERSION_MINOR)
-		pr_info("pblk: newer line minor version found: %d\n",
+		pblk_info(pblk, "newer line minor version found: %d\n",
 				header->version_minor);
 #endif
 
@@ -852,7 +852,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 			continue;
 
 		if (smeta_buf->header.version_major != SMETA_VERSION_MAJOR) {
-			pr_err("pblk: found incompatible line version %u\n",
+			pblk_err(pblk, "found incompatible line version %u\n",
 					smeta_buf->header.version_major);
 			return ERR_PTR(-EINVAL);
 		}
@@ -864,7 +864,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 		}
 
 		if (memcmp(pblk->instance_uuid, smeta_buf->header.uuid, 16)) {
-			pr_debug("pblk: ignore line %u due to uuid mismatch\n",
+			pblk_debug(pblk, "ignore line %u due to uuid mismatch\n",
 					i);
 			continue;
 		}
@@ -888,7 +888,7 @@ struct pblk_line *pblk_recov_l2p(struct pblk *pblk)
 
 		pblk_recov_line_add_ordered(&recov_list, line);
 		found_lines++;
-		pr_debug("pblk: recovering data line %d, seq:%llu\n",
+		pblk_debug(pblk, "recovering data line %d, seq:%llu\n",
 						line->id, smeta_buf->seq_nr);
 	}
 
@@ -948,7 +948,7 @@ next:
 			line->emeta = NULL;
 		} else {
 			if (open_lines > 1)
-				pr_err("pblk: failed to recover L2P\n");
+				pblk_err(pblk, "failed to recover L2P\n");
 
 			open_lines++;
 			line->meta_line = meta_line;
@@ -977,7 +977,7 @@ next:
 
 out:
 	if (found_lines != recovered_lines)
-		pr_err("pblk: failed to recover all found lines %d/%d\n",
+		pblk_err(pblk, "failed to recover all found lines %d/%d\n",
 						found_lines, recovered_lines);
 
 	return data_line;
@@ -1000,7 +1000,7 @@ int pblk_recov_pad(struct pblk *pblk)
 
 	ret = pblk_recov_pad_oob(pblk, line, left_msecs);
 	if (ret) {
-		pr_err("pblk: Tear down padding failed (%d)\n", ret);
+		pblk_err(pblk, "tear down padding failed (%d)\n", ret);
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-sysfs.c b/drivers/lightnvm/pblk-sysfs.c
index b0e5e93a9d5f..9fc3dfa168b4 100644
--- a/drivers/lightnvm/pblk-sysfs.c
+++ b/drivers/lightnvm/pblk-sysfs.c
@@ -268,7 +268,7 @@ static ssize_t pblk_sysfs_lines(struct pblk *pblk, char *page)
 	spin_unlock(&l_mg->free_lock);
 
 	if (nr_free_lines != free_line_cnt)
-		pr_err("pblk: corrupted free line list:%d/%d\n",
+		pblk_err(pblk, "corrupted free line list:%d/%d\n",
 						nr_free_lines, free_line_cnt);
 
 	sz = snprintf(page, PAGE_SIZE - sz,
@@ -697,8 +697,7 @@ int pblk_sysfs_init(struct gendisk *tdisk)
 					kobject_get(&parent_dev->kobj),
 					"%s", "pblk");
 	if (ret) {
-		pr_err("pblk: could not register %s/pblk\n",
-						tdisk->disk_name);
+		pblk_err(pblk, "could not register\n");
 		return ret;
 	}
 
diff --git a/drivers/lightnvm/pblk-write.c b/drivers/lightnvm/pblk-write.c
index 5f44df999aed..ee774a86cf1e 100644
--- a/drivers/lightnvm/pblk-write.c
+++ b/drivers/lightnvm/pblk-write.c
@@ -238,7 +238,7 @@ static void pblk_end_w_fail(struct pblk *pblk, struct nvm_rq *rqd)
 
 	recovery = mempool_alloc(&pblk->rec_pool, GFP_ATOMIC);
 	if (!recovery) {
-		pr_err("pblk: could not allocate recovery work\n");
+		pblk_err(pblk, "could not allocate recovery work\n");
 		return;
 	}
 
@@ -279,7 +279,7 @@ static void pblk_end_io_write_meta(struct nvm_rq *rqd)
 
 	if (rqd->error) {
 		pblk_log_write_err(pblk, rqd);
-		pr_err("pblk: metadata I/O failed. Line %d\n", line->id);
+		pblk_err(pblk, "metadata I/O failed. Line %d\n", line->id);
 		line->w_err_gc->has_write_err = 1;
 	}
 
@@ -360,7 +360,7 @@ static int pblk_calc_secs_to_sync(struct pblk *pblk, unsigned int secs_avail,
 	if ((!secs_to_sync && secs_to_flush)
 			|| (secs_to_sync < 0)
 			|| (secs_to_sync > secs_avail && !secs_to_flush)) {
-		pr_err("pblk: bad sector calculation (a:%d,s:%d,f:%d)\n",
+		pblk_err(pblk, "bad sector calculation (a:%d,s:%d,f:%d)\n",
 				secs_avail, secs_to_sync, secs_to_flush);
 	}
 #endif
@@ -397,7 +397,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 	bio = pblk_bio_map_addr(pblk, data, rq_ppas, rq_len,
 					l_mg->emeta_alloc_type, GFP_KERNEL);
 	if (IS_ERR(bio)) {
-		pr_err("pblk: failed to map emeta io");
+		pblk_err(pblk, "failed to map emeta io");
 		ret = PTR_ERR(bio);
 		goto fail_free_rqd;
 	}
@@ -428,7 +428,7 @@ int pblk_submit_meta_io(struct pblk *pblk, struct pblk_line *meta_line)
 
 	ret = pblk_submit_io(pblk, rqd);
 	if (ret) {
-		pr_err("pblk: emeta I/O submission failed: %d\n", ret);
+		pblk_err(pblk, "emeta I/O submission failed: %d\n", ret);
 		goto fail_rollback;
 	}
 
@@ -518,7 +518,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Assign lbas to ppas and populate request structure */
 	err = pblk_setup_w_rq(pblk, rqd, &erase_ppa);
 	if (err) {
-		pr_err("pblk: could not setup write request: %d\n", err);
+		pblk_err(pblk, "could not setup write request: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -527,7 +527,7 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 	/* Submit data write for current data line */
 	err = pblk_submit_io(pblk, rqd);
 	if (err) {
-		pr_err("pblk: data I/O submission failed: %d\n", err);
+		pblk_err(pblk, "data I/O submission failed: %d\n", err);
 		return NVM_IO_ERR;
 	}
 
@@ -549,7 +549,8 @@ static int pblk_submit_io_set(struct pblk *pblk, struct nvm_rq *rqd)
 		/* Submit metadata write for previous data line */
 		err = pblk_submit_meta_io(pblk, meta_line);
 		if (err) {
-			pr_err("pblk: metadata I/O submission failed: %d", err);
+			pblk_err(pblk, "metadata I/O submission failed: %d",
+					err);
 			return NVM_IO_ERR;
 		}
 	}
@@ -614,7 +615,7 @@ static int pblk_submit_write(struct pblk *pblk)
 		secs_to_sync = pblk_calc_secs_to_sync(pblk, secs_avail,
 					secs_to_flush);
 		if (secs_to_sync > pblk->max_write_pgs) {
-			pr_err("pblk: bad buffer sync calculation\n");
+			pblk_err(pblk, "bad buffer sync calculation\n");
 			return 1;
 		}
 
@@ -633,7 +634,7 @@ static int pblk_submit_write(struct pblk *pblk)
 
 	if (pblk_rb_read_to_bio(&pblk->rwb, rqd, pos, secs_to_sync,
 								secs_avail)) {
-		pr_err("pblk: corrupted write bio\n");
+		pblk_err(pblk, "corrupted write bio\n");
 		goto fail_put_bio;
 	}
 
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index c072955d72c2..5c6904eb8557 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -703,6 +703,15 @@ struct pblk_line_ws {
 #define pblk_g_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_g_ctx))
 #define pblk_w_rq_size (sizeof(struct nvm_rq) + sizeof(struct pblk_c_ctx))
 
+#define pblk_err(pblk, fmt, ...)			\
+	pr_err("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_info(pblk, fmt, ...)			\
+	pr_info("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_warn(pblk, fmt, ...)			\
+	pr_warn("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+#define pblk_debug(pblk, fmt, ...)			\
+	pr_debug("pblk %s: " fmt, pblk->disk->disk_name, ##__VA_ARGS__)
+
 /*
  * pblk ring buffer operations
  */
@@ -1280,19 +1289,21 @@ static inline int pblk_io_aligned(struct pblk *pblk, int nr_secs)
 }
 
 #ifdef CONFIG_NVM_PBLK_DEBUG
-static inline void print_ppa(struct nvm_geo *geo, struct ppa_addr *p,
+static inline void print_ppa(struct pblk *pblk, struct ppa_addr *p,
 			     char *msg, int error)
 {
+	struct nvm_geo *geo = &pblk->dev->geo;
+
 	if (p->c.is_cached) {
-		pr_err("ppa: (%s: %x) cache line: %llu\n",
+		pblk_err(pblk, "ppa: (%s: %x) cache line: %llu\n",
 				msg, error, (u64)p->c.line);
 	} else if (geo->version == NVM_OCSSD_SPEC_12) {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,blk:%d,pg:%d,pl:%d,sec:%d\n",
 			msg, error,
 			p->g.ch, p->g.lun, p->g.blk,
 			p->g.pg, p->g.pl, p->g.sec);
 	} else {
-		pr_err("ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
+		pblk_err(pblk, "ppa: (%s: %x):ch:%d,lun:%d,chk:%d,sec:%d\n",
 			msg, error,
 			p->m.grp, p->m.pu, p->m.chk, p->m.sec);
 	}
@@ -1304,16 +1315,16 @@ static inline void pblk_print_failed_rqd(struct pblk *pblk, struct nvm_rq *rqd,
 	int bit = -1;
 
 	if (rqd->nr_ppas ==  1) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_addr, "rqd", error);
+		print_ppa(pblk, &rqd->ppa_addr, "rqd", error);
 		return;
 	}
 
 	while ((bit = find_next_bit((void *)&rqd->ppa_status, rqd->nr_ppas,
 						bit + 1)) < rqd->nr_ppas) {
-		print_ppa(&pblk->dev->geo, &rqd->ppa_list[bit], "rqd", error);
+		print_ppa(pblk, &rqd->ppa_list[bit], "rqd", error);
 	}
 
-	pr_err("error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
+	pblk_err(pblk, "error:%d, ppa_status:%llx\n", error, rqd->ppa_status);
 }
 
 static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
@@ -1344,7 +1355,7 @@ static inline int pblk_boundary_ppa_checks(struct nvm_tgt_dev *tgt_dev,
 				continue;
 		}
 
-		print_ppa(geo, ppa, "boundary", i);
+		print_ppa(tgt_dev->q->queuedata, ppa, "boundary", i);
 
 		return 1;
 	}
@@ -1374,7 +1385,7 @@ static inline int pblk_check_io(struct pblk *pblk, struct nvm_rq *rqd)
 
 			spin_lock(&line->lock);
 			if (line->state != PBLK_LINESTATE_OPEN) {
-				pr_err("pblk: bad ppa: line:%d,state:%d\n",
+				pblk_err(pblk, "bad ppa: line:%d,state:%d\n",
 							line->id, line->state);
 				WARN_ON(1);
 				spin_unlock(&line->lock);
-- 
cgit v1.2.3


From 884b031b288bae15397dd07b084a41ffb44f99e4 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 13 Jul 2018 10:48:43 +0200
Subject: lightnvm: pblk: mark expected switch fall-through
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/lightnvm/pblk-core.c b/drivers/lightnvm/pblk-core.c
index b829460fe827..00984b486fea 100644
--- a/drivers/lightnvm/pblk-core.c
+++ b/drivers/lightnvm/pblk-core.c
@@ -264,6 +264,7 @@ void pblk_free_rqd(struct pblk *pblk, struct nvm_rq *rqd, int type)
 	switch (type) {
 	case PBLK_WRITE:
 		kfree(((struct pblk_c_ctx *)nvm_rq_to_pdu(rqd))->lun_bitmap);
+		/* fall through */
 	case PBLK_WRITE_INT:
 		pool = &pblk->w_rq_pool;
 		break;
-- 
cgit v1.2.3


From 11f6ad699a32f3be1232741e4bfa34abf6677cb8 Mon Sep 17 00:00:00 2001
From: Heiner Litz <hlitz@ucsc.edu>
Date: Fri, 13 Jul 2018 10:48:44 +0200
Subject: lightnvm: pblk: add asynchronous partial read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the read path, partial reads are currently performed synchronously
which affects performance for workloads that generate many partial
reads. This patch adds an asynchronous partial read path as well as
the required partial read ctx.

Signed-off-by: Heiner Litz <hlitz@ucsc.edu>
Reviewed-by: Igor Konopko <igor.j.konopko@intel.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-read.c | 183 ++++++++++++++++++++++++++++---------------
 drivers/lightnvm/pblk.h      |  10 +++
 2 files changed, 130 insertions(+), 63 deletions(-)

diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 9c9362b20861..26d414ae25b6 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -231,74 +231,36 @@ static void pblk_end_io_read(struct nvm_rq *rqd)
 	__pblk_end_io_read(pblk, rqd, true);
 }
 
-static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
-			     struct bio *orig_bio, unsigned int bio_init_idx,
-			     unsigned long *read_bitmap)
+static void pblk_end_partial_read(struct nvm_rq *rqd)
 {
-	struct pblk_sec_meta *meta_list = rqd->meta_list;
-	struct bio *new_bio;
+	struct pblk *pblk = rqd->private;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx = r_ctx->private;
+	struct bio *new_bio = rqd->bio;
+	struct bio *bio = pr_ctx->orig_bio;
 	struct bio_vec src_bv, dst_bv;
-	void *ppa_ptr = NULL;
-	void *src_p, *dst_p;
-	dma_addr_t dma_ppa_list = 0;
-	__le64 *lba_list_mem, *lba_list_media;
-	int nr_secs = rqd->nr_ppas;
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	int bio_init_idx = pr_ctx->bio_init_idx;
+	unsigned long *read_bitmap = pr_ctx->bitmap;
+	int nr_secs = pr_ctx->orig_nr_secs;
 	int nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
-	int i, ret, hole;
-
-	/* Re-use allocated memory for intermediate lbas */
-	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
-	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
-
-	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
-
-	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
-		goto fail_add_pages;
-
-	if (nr_holes != new_bio->bi_vcnt) {
-		pblk_err(pblk, "malformed bio\n");
-		goto fail;
-	}
-
-	for (i = 0; i < nr_secs; i++)
-		lba_list_mem[i] = meta_list[i].lba;
-
-	new_bio->bi_iter.bi_sector = 0; /* internal bio */
-	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
-
-	rqd->bio = new_bio;
-	rqd->nr_ppas = nr_holes;
-	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
-
-	if (unlikely(nr_holes == 1)) {
-		ppa_ptr = rqd->ppa_list;
-		dma_ppa_list = rqd->dma_ppa_list;
-		rqd->ppa_addr = rqd->ppa_list[0];
-	}
-
-	ret = pblk_submit_io_sync(pblk, rqd);
-	if (ret) {
-		bio_put(rqd->bio);
-		pblk_err(pblk, "sync read IO submission failed\n");
-		goto fail;
-	}
-
-	if (rqd->error) {
-		atomic_long_inc(&pblk->read_failed);
-#ifdef CONFIG_NVM_PBLK_DEBUG
-		pblk_print_failed_rqd(pblk, rqd, rqd->error);
-#endif
-	}
+	__le64 *lba_list_mem, *lba_list_media;
+	void *src_p, *dst_p;
+	int hole, i;
 
 	if (unlikely(nr_holes == 1)) {
 		struct ppa_addr ppa;
 
 		ppa = rqd->ppa_addr;
-		rqd->ppa_list = ppa_ptr;
-		rqd->dma_ppa_list = dma_ppa_list;
+		rqd->ppa_list = pr_ctx->ppa_ptr;
+		rqd->dma_ppa_list = pr_ctx->dma_ppa_list;
 		rqd->ppa_list[0] = ppa;
 	}
 
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+	lba_list_media = (((void *)rqd->ppa_list) + 2 * pblk_dma_ppa_size);
+
 	for (i = 0; i < nr_secs; i++) {
 		lba_list_media[i] = meta_list[i].lba;
 		meta_list[i].lba = lba_list_mem[i];
@@ -316,7 +278,7 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 		meta_list[hole].lba = lba_list_media[i];
 
 		src_bv = new_bio->bi_io_vec[i++];
-		dst_bv = orig_bio->bi_io_vec[bio_init_idx + hole];
+		dst_bv = bio->bi_io_vec[bio_init_idx + hole];
 
 		src_p = kmap_atomic(src_bv.bv_page);
 		dst_p = kmap_atomic(dst_bv.bv_page);
@@ -334,19 +296,107 @@ static int pblk_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
 	} while (hole < nr_secs);
 
 	bio_put(new_bio);
+	kfree(pr_ctx);
 
 	/* restore original request */
 	rqd->bio = NULL;
 	rqd->nr_ppas = nr_secs;
 
+	bio_endio(bio);
 	__pblk_end_io_read(pblk, rqd, false);
-	return NVM_IO_DONE;
+}
 
-fail:
-	/* Free allocated pages in new bio */
+static int pblk_setup_partial_read(struct pblk *pblk, struct nvm_rq *rqd,
+			    unsigned int bio_init_idx,
+			    unsigned long *read_bitmap,
+			    int nr_holes)
+{
+	struct pblk_sec_meta *meta_list = rqd->meta_list;
+	struct pblk_g_ctx *r_ctx = nvm_rq_to_pdu(rqd);
+	struct pblk_pr_ctx *pr_ctx;
+	struct bio *new_bio, *bio = r_ctx->private;
+	__le64 *lba_list_mem;
+	int nr_secs = rqd->nr_ppas;
+	int i;
+
+	/* Re-use allocated memory for intermediate lbas */
+	lba_list_mem = (((void *)rqd->ppa_list) + pblk_dma_ppa_size);
+
+	new_bio = bio_alloc(GFP_KERNEL, nr_holes);
+
+	if (pblk_bio_add_pages(pblk, new_bio, GFP_KERNEL, nr_holes))
+		goto fail_bio_put;
+
+	if (nr_holes != new_bio->bi_vcnt) {
+		WARN_ONCE(1, "pblk: malformed bio\n");
+		goto fail_free_pages;
+	}
+
+	pr_ctx = kmalloc(sizeof(struct pblk_pr_ctx), GFP_KERNEL);
+	if (!pr_ctx)
+		goto fail_free_pages;
+
+	for (i = 0; i < nr_secs; i++)
+		lba_list_mem[i] = meta_list[i].lba;
+
+	new_bio->bi_iter.bi_sector = 0; /* internal bio */
+	bio_set_op_attrs(new_bio, REQ_OP_READ, 0);
+
+	rqd->bio = new_bio;
+	rqd->nr_ppas = nr_holes;
+	rqd->flags = pblk_set_read_mode(pblk, PBLK_READ_RANDOM);
+
+	pr_ctx->ppa_ptr = NULL;
+	pr_ctx->orig_bio = bio;
+	bitmap_copy(pr_ctx->bitmap, read_bitmap, NVM_MAX_VLBA);
+	pr_ctx->bio_init_idx = bio_init_idx;
+	pr_ctx->orig_nr_secs = nr_secs;
+	r_ctx->private = pr_ctx;
+
+	if (unlikely(nr_holes == 1)) {
+		pr_ctx->ppa_ptr = rqd->ppa_list;
+		pr_ctx->dma_ppa_list = rqd->dma_ppa_list;
+		rqd->ppa_addr = rqd->ppa_list[0];
+	}
+	return 0;
+
+fail_free_pages:
 	pblk_bio_free_pages(pblk, new_bio, 0, new_bio->bi_vcnt);
-fail_add_pages:
+fail_bio_put:
+	bio_put(new_bio);
+
+	return -ENOMEM;
+}
+
+static int pblk_partial_read_bio(struct pblk *pblk, struct nvm_rq *rqd,
+				 unsigned int bio_init_idx,
+				 unsigned long *read_bitmap, int nr_secs)
+{
+	int nr_holes;
+	int ret;
+
+	nr_holes = nr_secs - bitmap_weight(read_bitmap, nr_secs);
+
+	if (pblk_setup_partial_read(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_holes))
+		return NVM_IO_ERR;
+
+	rqd->end_io = pblk_end_partial_read;
+
+	ret = pblk_submit_io(pblk, rqd);
+	if (ret) {
+		bio_put(rqd->bio);
+		pblk_err(pblk, "partial read IO submission failed\n");
+		goto err;
+	}
+
+	return NVM_IO_OK;
+
+err:
 	pblk_err(pblk, "failed to perform partial read\n");
+
+	/* Free allocated pages in new bio */
+	pblk_bio_free_pages(pblk, rqd->bio, 0, rqd->bio->bi_vcnt);
 	__pblk_end_io_read(pblk, rqd, false);
 	return NVM_IO_ERR;
 }
@@ -480,8 +530,15 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 	/* The read bio request could be partially filled by the write buffer,
 	 * but there are some holes that need to be read from the drive.
 	 */
-	return pblk_partial_read(pblk, rqd, bio, bio_init_idx, read_bitmap);
+	ret = pblk_partial_read_bio(pblk, rqd, bio_init_idx, read_bitmap,
+				    nr_secs);
+	if (ret)
+		goto fail_meta_free;
+
+	return NVM_IO_OK;
 
+fail_meta_free:
+	nvm_dev_dma_free(dev->parent, rqd->meta_list, rqd->dma_meta_list);
 fail_rqd_free:
 	pblk_free_rqd(pblk, rqd, PBLK_READ);
 	return ret;
diff --git a/drivers/lightnvm/pblk.h b/drivers/lightnvm/pblk.h
index 5c6904eb8557..4760af7b6499 100644
--- a/drivers/lightnvm/pblk.h
+++ b/drivers/lightnvm/pblk.h
@@ -119,6 +119,16 @@ struct pblk_g_ctx {
 	u64 lba;
 };
 
+/* partial read context */
+struct pblk_pr_ctx {
+	struct bio *orig_bio;
+	DECLARE_BITMAP(bitmap, NVM_MAX_VLBA);
+	unsigned int orig_nr_secs;
+	unsigned int bio_init_idx;
+	void *ppa_ptr;
+	dma_addr_t dma_ppa_list;
+};
+
 /* Pad context */
 struct pblk_pad_rq {
 	struct pblk *pblk;
-- 
cgit v1.2.3


From f6352103d2e0ad2d2066725eb19bfdfb8763239b Mon Sep 17 00:00:00 2001
From: Hans Holmberg <hans.holmberg@cnexlabs.com>
Date: Fri, 13 Jul 2018 10:48:45 +0200
Subject: lightnvm: pblk: assume that chunks are closed on 1.2 devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can't know if a block is closed or not on 1.2 devices, so assume
closed state to make sure that blocks are erased before writing.

Fixes: 32ef9412c114 ("lightnvm: pblk: implement get log report chunk")
Signed-off-by: Hans Holmberg <hans.holmberg@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/lightnvm/pblk-init.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/lightnvm/pblk-init.c b/drivers/lightnvm/pblk-init.c
index d023ea6116bc..537e98f2b24a 100644
--- a/drivers/lightnvm/pblk-init.c
+++ b/drivers/lightnvm/pblk-init.c
@@ -719,10 +719,11 @@ static int pblk_setup_line_meta_12(struct pblk *pblk, struct pblk_line *line,
 
 		/*
 		 * In 1.2 spec. chunk state is not persisted by the device. Thus
-		 * some of the values are reset each time pblk is instantiated.
+		 * some of the values are reset each time pblk is instantiated,
+		 * so we have to assume that the block is closed.
 		 */
 		if (lun_bb_meta[line->id] == NVM_BLK_T_FREE)
-			chunk->state =  NVM_CHK_ST_FREE;
+			chunk->state =  NVM_CHK_ST_CLOSED;
 		else
 			chunk->state = NVM_CHK_ST_OFFLINE;
 
-- 
cgit v1.2.3


From 72c6d2db64fa18c996ece8f06e499509e6c9a37e Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:16 +0200
Subject: x86/litf: Introduce vmx status variable

Store the effective mitigation of VMX in a status variable and use it to
report the VMX state in the l1tf sysfs file.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142322.433098358@linutronix.de
---
 arch/x86/include/asm/vmx.h |  9 +++++++++
 arch/x86/kernel/cpu/bugs.c | 36 ++++++++++++++++++++++++++++++++++--
 arch/x86/kvm/vmx.c         | 22 +++++++++++-----------
 3 files changed, 54 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 425e6b8b9547..c98aa9aed056 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -573,4 +573,13 @@ enum vm_instruction_error_number {
 	VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID = 28,
 };
 
+enum vmx_l1d_flush_state {
+	VMENTER_L1D_FLUSH_AUTO,
+	VMENTER_L1D_FLUSH_NEVER,
+	VMENTER_L1D_FLUSH_COND,
+	VMENTER_L1D_FLUSH_ALWAYS,
+};
+
+extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
+
 #endif
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 50500cea6eba..8aba7d3abccb 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -22,6 +22,7 @@
 #include <asm/processor-flags.h>
 #include <asm/fpu/internal.h>
 #include <asm/msr.h>
+#include <asm/vmx.h>
 #include <asm/paravirt.h>
 #include <asm/alternative.h>
 #include <asm/pgtable.h>
@@ -657,6 +658,12 @@ void x86_spec_ctrl_setup_ap(void)
 
 #undef pr_fmt
 #define pr_fmt(fmt)	"L1TF: " fmt
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+enum vmx_l1d_flush_state l1tf_vmx_mitigation __ro_after_init = VMENTER_L1D_FLUSH_AUTO;
+EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
+#endif
+
 static void __init l1tf_select_mitigation(void)
 {
 	u64 half_pa;
@@ -686,6 +693,32 @@ static void __init l1tf_select_mitigation(void)
 
 #ifdef CONFIG_SYSFS
 
+#define L1TF_DEFAULT_MSG "Mitigation: PTE Inversion"
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+static const char *l1tf_vmx_states[] = {
+	[VMENTER_L1D_FLUSH_AUTO]	= "auto",
+	[VMENTER_L1D_FLUSH_NEVER]	= "vulnerable",
+	[VMENTER_L1D_FLUSH_COND]	= "conditional cache flushes",
+	[VMENTER_L1D_FLUSH_ALWAYS]	= "cache flushes",
+};
+
+static ssize_t l1tf_show_state(char *buf)
+{
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO)
+		return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+
+	return sprintf(buf, "%s; VMX: SMT %s, L1D %s\n", L1TF_DEFAULT_MSG,
+		       cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled",
+		       l1tf_vmx_states[l1tf_vmx_mitigation]);
+}
+#else
+static ssize_t l1tf_show_state(char *buf)
+{
+	return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
+}
+#endif
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -713,9 +746,8 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 
 	case X86_BUG_L1TF:
 		if (boot_cpu_has(X86_FEATURE_L1TF_PTEINV))
-			return sprintf(buf, "Mitigation: Page Table Inversion\n");
+			return l1tf_show_state(buf);
 		break;
-
 	default:
 		break;
 	}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index eb7c207a3bc3..385cbfaa3c71 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -193,19 +193,13 @@ extern const ulong vmx_return;
 
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
 
-/* These MUST be in sync with vmentry_l1d_param order. */
-enum vmx_l1d_flush_state {
-	VMENTER_L1D_FLUSH_NEVER,
-	VMENTER_L1D_FLUSH_COND,
-	VMENTER_L1D_FLUSH_ALWAYS,
-};
-
 static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND;
 
 static const struct {
 	const char *option;
 	enum vmx_l1d_flush_state cmd;
 } vmentry_l1d_param[] = {
+	{"auto",	VMENTER_L1D_FLUSH_AUTO},
 	{"never",	VMENTER_L1D_FLUSH_NEVER},
 	{"cond",	VMENTER_L1D_FLUSH_COND},
 	{"always",	VMENTER_L1D_FLUSH_ALWAYS},
@@ -13235,8 +13229,12 @@ static int __init vmx_setup_l1d_flush(void)
 {
 	struct page *page;
 
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return 0;
+
+	l1tf_vmx_mitigation = vmentry_l1d_flush;
+
 	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
-	    !boot_cpu_has_bug(X86_BUG_L1TF) ||
 	    vmx_l1d_use_msr_save_list())
 		return 0;
 
@@ -13251,12 +13249,14 @@ static int __init vmx_setup_l1d_flush(void)
 	return 0;
 }
 
-static void vmx_free_l1d_flush_pages(void)
+static void vmx_cleanup_l1d_flush(void)
 {
 	if (vmx_l1d_flush_pages) {
 		free_pages((unsigned long)vmx_l1d_flush_pages, L1D_CACHE_ORDER);
 		vmx_l1d_flush_pages = NULL;
 	}
+	/* Restore state so sysfs ignores VMX */
+	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 }
 
 static int __init vmx_init(void)
@@ -13299,7 +13299,7 @@ static int __init vmx_init(void)
 	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
 		     __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r) {
-		vmx_free_l1d_flush_pages();
+		vmx_cleanup_l1d_flush();
 		return r;
 	}
 
@@ -13343,7 +13343,7 @@ static void __exit vmx_exit(void)
 		static_branch_disable(&enable_evmcs);
 	}
 #endif
-	vmx_free_l1d_flush_pages();
+	vmx_cleanup_l1d_flush();
 }
 
 module_init(vmx_init)
-- 
cgit v1.2.3


From 2f055947ae5e2741fb2dc5bba1033c417ccf4faa Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:17 +0200
Subject: x86/kvm: Drop L1TF MSR list approach

The VMX module parameter to control the L1D flush should become
writeable.

The MSR list is set up at VM init per guest VCPU, but the run time
switching is based on a static key which is global. Toggling the MSR list
at run time might be feasible, but for now drop this optimization and use
the regular MSR write to make run-time switching possible.

The default mitigation is the conditional flush anyway, so for extra
paranoid setups this will add some small overhead, but the extra code
executed is in the noise compared to the flush itself.

Aside of that the EPT disabled case is not handled correctly at the moment
and the MSR list magic is in the way for fixing that as well.

If it's really providing a significant advantage, then this needs to be
revisited after the code is correct and the control is writable.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142322.516940445@linutronix.de
---
 arch/x86/kvm/vmx.c | 43 +++++++------------------------------------
 1 file changed, 7 insertions(+), 36 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 385cbfaa3c71..e553e43a114c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6231,16 +6231,6 @@ static void ept_set_mmio_spte_mask(void)
 				   VMX_EPT_MISCONFIG_WX_VALUE);
 }
 
-static bool vmx_l1d_use_msr_save_list(void)
-{
-	if (!enable_ept || !boot_cpu_has_bug(X86_BUG_L1TF) ||
-	    static_cpu_has(X86_FEATURE_HYPERVISOR) ||
-	    !static_cpu_has(X86_FEATURE_FLUSH_L1D))
-		return false;
-
-	return vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
-}
-
 #define VMX_XSS_EXIT_BITMAP 0
 /*
  * Sets up the vmcs for emulated real mode.
@@ -6362,12 +6352,6 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		vmcs_write64(PML_ADDRESS, page_to_phys(vmx->pml_pg));
 		vmcs_write16(GUEST_PML_INDEX, PML_ENTITY_NUM - 1);
 	}
-	/*
-	 * If flushing the L1D cache on every VMENTER is enforced and the
-	 * MSR is available, use the MSR save list.
-	 */
-	if (vmx_l1d_use_msr_save_list())
-		add_atomic_switch_msr(vmx, MSR_IA32_FLUSH_CMD, L1D_FLUSH, 0, true);
 }
 
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -9617,26 +9601,14 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	bool always;
 
 	/*
-	 * This code is only executed when:
-	 * - the flush mode is 'cond'
-	 * - the flush mode is 'always' and the flush MSR is not
-	 *   available
-	 *
-	 * If the CPU has the flush MSR then clear the flush bit because
-	 * 'always' mode is handled via the MSR save list.
-	 *
-	 * If the MSR is not avaibable then act depending on the mitigation
-	 * mode: If 'flush always', keep the flush bit set, otherwise clear
-	 * it.
+	 * This code is only executed when the the flush mode is 'cond' or
+	 * 'always'
 	 *
-	 * The flush bit gets set again either from vcpu_run() or from one
-	 * of the unsafe VMEXIT handlers.
+	 * If 'flush always', keep the flush bit set, otherwise clear
+	 * it. The flush bit gets set again either from vcpu_run() or from
+	 * one of the unsafe VMEXIT handlers.
 	 */
-	if (static_cpu_has(X86_FEATURE_FLUSH_L1D))
-		always = false;
-	else
-		always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
-
+	always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
 	vcpu->arch.l1tf_flush_l1d = always;
 
 	vcpu->stat.l1d_flush++;
@@ -13234,8 +13206,7 @@ static int __init vmx_setup_l1d_flush(void)
 
 	l1tf_vmx_mitigation = vmentry_l1d_flush;
 
-	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER ||
-	    vmx_l1d_use_msr_save_list())
+	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER)
 		return 0;
 
 	if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
-- 
cgit v1.2.3


From a7b9020b06ec6d7c3f3b0d4ef1a9eba12654f4f7 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:18 +0200
Subject: x86/l1tf: Handle EPT disabled state proper

If Extended Page Tables (EPT) are disabled or not supported, no L1D
flushing is required. The setup function can just avoid setting up the L1D
flush for the EPT=n case.

Invoke it after the hardware setup has be done and enable_ept has the
correct state and expose the EPT disabled state in the mitigation status as
well.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142322.612160168@linutronix.de
---
 arch/x86/include/asm/vmx.h |  1 +
 arch/x86/kernel/cpu/bugs.c |  9 ++---
 arch/x86/kvm/vmx.c         | 89 +++++++++++++++++++++++++---------------------
 3 files changed, 54 insertions(+), 45 deletions(-)

diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index c98aa9aed056..94a8547d915b 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -578,6 +578,7 @@ enum vmx_l1d_flush_state {
 	VMENTER_L1D_FLUSH_NEVER,
 	VMENTER_L1D_FLUSH_COND,
 	VMENTER_L1D_FLUSH_ALWAYS,
+	VMENTER_L1D_FLUSH_EPT_DISABLED,
 };
 
 extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 8aba7d3abccb..1b3dc586d29d 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -697,10 +697,11 @@ static void __init l1tf_select_mitigation(void)
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 static const char *l1tf_vmx_states[] = {
-	[VMENTER_L1D_FLUSH_AUTO]	= "auto",
-	[VMENTER_L1D_FLUSH_NEVER]	= "vulnerable",
-	[VMENTER_L1D_FLUSH_COND]	= "conditional cache flushes",
-	[VMENTER_L1D_FLUSH_ALWAYS]	= "cache flushes",
+	[VMENTER_L1D_FLUSH_AUTO]		= "auto",
+	[VMENTER_L1D_FLUSH_NEVER]		= "vulnerable",
+	[VMENTER_L1D_FLUSH_COND]		= "conditional cache flushes",
+	[VMENTER_L1D_FLUSH_ALWAYS]		= "cache flushes",
+	[VMENTER_L1D_FLUSH_EPT_DISABLED]	= "EPT disabled",
 };
 
 static ssize_t l1tf_show_state(char *buf)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index e553e43a114c..78593550059b 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -13204,6 +13204,11 @@ static int __init vmx_setup_l1d_flush(void)
 	if (!boot_cpu_has_bug(X86_BUG_L1TF))
 		return 0;
 
+	if (!enable_ept) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
+		return 0;
+	}
+
 	l1tf_vmx_mitigation = vmentry_l1d_flush;
 
 	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER)
@@ -13230,6 +13235,41 @@ static void vmx_cleanup_l1d_flush(void)
 	l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 }
 
+static void vmx_exit(void)
+{
+#ifdef CONFIG_KEXEC_CORE
+	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
+	synchronize_rcu();
+#endif
+
+	kvm_exit();
+
+#if IS_ENABLED(CONFIG_HYPERV)
+	if (static_branch_unlikely(&enable_evmcs)) {
+		int cpu;
+		struct hv_vp_assist_page *vp_ap;
+		/*
+		 * Reset everything to support using non-enlightened VMCS
+		 * access later (e.g. when we reload the module with
+		 * enlightened_vmcs=0)
+		 */
+		for_each_online_cpu(cpu) {
+			vp_ap =	hv_get_vp_assist_page(cpu);
+
+			if (!vp_ap)
+				continue;
+
+			vp_ap->current_nested_vmcs = 0;
+			vp_ap->enlighten_vmentry = 0;
+		}
+
+		static_branch_disable(&enable_evmcs);
+	}
+#endif
+	vmx_cleanup_l1d_flush();
+}
+module_exit(vmx_exit);
+
 static int __init vmx_init(void)
 {
 	int r;
@@ -13263,14 +13303,17 @@ static int __init vmx_init(void)
 	}
 #endif
 
-	r = vmx_setup_l1d_flush();
+	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
+		     __alignof__(struct vcpu_vmx), THIS_MODULE);
 	if (r)
 		return r;
 
-	r = kvm_init(&vmx_x86_ops, sizeof(struct vcpu_vmx),
-		     __alignof__(struct vcpu_vmx), THIS_MODULE);
+	/*
+	 * Must be called after kvm_init() so enable_ept is properly set up
+	 */
+	r = vmx_setup_l1d_flush();
 	if (r) {
-		vmx_cleanup_l1d_flush();
+		vmx_exit();
 		return r;
 	}
 
@@ -13282,40 +13325,4 @@ static int __init vmx_init(void)
 
 	return 0;
 }
-
-static void __exit vmx_exit(void)
-{
-#ifdef CONFIG_KEXEC_CORE
-	RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL);
-	synchronize_rcu();
-#endif
-
-	kvm_exit();
-
-#if IS_ENABLED(CONFIG_HYPERV)
-	if (static_branch_unlikely(&enable_evmcs)) {
-		int cpu;
-		struct hv_vp_assist_page *vp_ap;
-		/*
-		 * Reset everything to support using non-enlightened VMCS
-		 * access later (e.g. when we reload the module with
-		 * enlightened_vmcs=0)
-		 */
-		for_each_online_cpu(cpu) {
-			vp_ap =	hv_get_vp_assist_page(cpu);
-
-			if (!vp_ap)
-				continue;
-
-			vp_ap->current_nested_vmcs = 0;
-			vp_ap->enlighten_vmentry = 0;
-		}
-
-		static_branch_disable(&enable_evmcs);
-	}
-#endif
-	vmx_cleanup_l1d_flush();
-}
-
-module_init(vmx_init)
-module_exit(vmx_exit)
+module_init(vmx_init);
-- 
cgit v1.2.3


From 7db92e165ac814487264632ab2624e832f20ae38 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:19 +0200
Subject: x86/kvm: Move l1tf setup function

In preparation of allowing run time control for L1D flushing, move the
setup code to the module parameter handler.

In case of pre module init parsing, just store the value and let vmx_init()
do the actual setup after running kvm_init() so that enable_ept is having
the correct state.

During run-time invoke it directly from the parameter setter to prepare for
run-time control.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142322.694063239@linutronix.de
---
 arch/x86/kvm/vmx.c | 125 +++++++++++++++++++++++++++++++++--------------------
 1 file changed, 78 insertions(+), 47 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 78593550059b..ce06701916ae 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -193,7 +193,8 @@ extern const ulong vmx_return;
 
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
 
-static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush = VMENTER_L1D_FLUSH_COND;
+/* Storage for pre module init parameter parsing */
+static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
 
 static const struct {
 	const char *option;
@@ -205,33 +206,85 @@ static const struct {
 	{"always",	VMENTER_L1D_FLUSH_ALWAYS},
 };
 
-static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+#define L1D_CACHE_ORDER 4
+static void *vmx_l1d_flush_pages;
+
+static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
-	unsigned int i;
+	struct page *page;
 
-	if (!s)
-		return -EINVAL;
+	/* If set to 'auto' select 'cond' */
+	if (l1tf == VMENTER_L1D_FLUSH_AUTO)
+		l1tf = VMENTER_L1D_FLUSH_COND;
 
-	for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
-		if (!strcmp(s, vmentry_l1d_param[i].option)) {
-			vmentry_l1d_flush = vmentry_l1d_param[i].cmd;
-			return 0;
-		}
+	if (!enable_ept) {
+		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
+		return 0;
 	}
 
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
+	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
+		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
+		if (!page)
+			return -ENOMEM;
+		vmx_l1d_flush_pages = page_address(page);
+	}
+
+	l1tf_vmx_mitigation = l1tf;
+
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
+		static_branch_enable(&vmx_l1d_should_flush);
+	return 0;
+}
+
+static int vmentry_l1d_flush_parse(const char *s)
+{
+	unsigned int i;
+
+	if (s) {
+		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
+			if (!strcmp(s, vmentry_l1d_param[i].option))
+				return vmentry_l1d_param[i].cmd;
+		}
+	}
 	return -EINVAL;
 }
 
+static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
+{
+	int l1tf;
+
+	if (!boot_cpu_has(X86_BUG_L1TF))
+		return 0;
+
+	l1tf = vmentry_l1d_flush_parse(s);
+	if (l1tf < 0)
+		return l1tf;
+
+	/*
+	 * Has vmx_init() run already? If not then this is the pre init
+	 * parameter parsing. In that case just store the value and let
+	 * vmx_init() do the proper setup after enable_ept has been
+	 * established.
+	 */
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO) {
+		vmentry_l1d_flush_param = l1tf;
+		return 0;
+	}
+
+	return vmx_setup_l1d_flush(l1tf);
+}
+
 static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
 {
-	return sprintf(s, "%s\n", vmentry_l1d_param[vmentry_l1d_flush].option);
+	return sprintf(s, "%s\n", vmentry_l1d_param[l1tf_vmx_mitigation].option);
 }
 
 static const struct kernel_param_ops vmentry_l1d_flush_ops = {
 	.set = vmentry_l1d_flush_set,
 	.get = vmentry_l1d_flush_get,
 };
-module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, &vmentry_l1d_flush, S_IRUGO);
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, S_IRUGO);
 
 struct kvm_vmx {
 	struct kvm kvm;
@@ -9608,7 +9661,7 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	 * it. The flush bit gets set again either from vcpu_run() or from
 	 * one of the unsafe VMEXIT handlers.
 	 */
-	always = vmentry_l1d_flush == VMENTER_L1D_FLUSH_ALWAYS;
+	always = l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_ALWAYS;
 	vcpu->arch.l1tf_flush_l1d = always;
 
 	vcpu->stat.l1d_flush++;
@@ -13197,34 +13250,6 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
 	.enable_smi_window = enable_smi_window,
 };
 
-static int __init vmx_setup_l1d_flush(void)
-{
-	struct page *page;
-
-	if (!boot_cpu_has_bug(X86_BUG_L1TF))
-		return 0;
-
-	if (!enable_ept) {
-		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
-		return 0;
-	}
-
-	l1tf_vmx_mitigation = vmentry_l1d_flush;
-
-	if (vmentry_l1d_flush == VMENTER_L1D_FLUSH_NEVER)
-		return 0;
-
-	if (!boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
-		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
-		if (!page)
-			return -ENOMEM;
-		vmx_l1d_flush_pages = page_address(page);
-	}
-
-	static_branch_enable(&vmx_l1d_should_flush);
-	return 0;
-}
-
 static void vmx_cleanup_l1d_flush(void)
 {
 	if (vmx_l1d_flush_pages) {
@@ -13309,12 +13334,18 @@ static int __init vmx_init(void)
 		return r;
 
 	/*
-	 * Must be called after kvm_init() so enable_ept is properly set up
-	 */
-	r = vmx_setup_l1d_flush();
-	if (r) {
-		vmx_exit();
-		return r;
+	 * Must be called after kvm_init() so enable_ept is properly set
+	 * up. Hand the parameter mitigation value in which was stored in
+	 * the pre module init parser. If no parameter was given, it will
+	 * contain 'auto' which will be turned into the default 'cond'
+	 * mitigation mode.
+	 */
+	if (boot_cpu_has(X86_BUG_L1TF)) {
+		r = vmx_setup_l1d_flush(vmentry_l1d_flush_param);
+		if (r) {
+			vmx_exit();
+			return r;
+		}
 	}
 
 #ifdef CONFIG_KEXEC_CORE
-- 
cgit v1.2.3


From 4c6523ec59fe895ea352a650218a6be0653910b1 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:20 +0200
Subject: x86/kvm: Add static key for flush always

Avoid the conditional in the L1D flush control path.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142322.790914912@linutronix.de
---
 arch/x86/kvm/vmx.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ce06701916ae..37c7ff581184 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -192,6 +192,7 @@ module_param(ple_window_max, uint, 0444);
 extern const ulong vmx_return;
 
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_always);
 
 /* Storage for pre module init parameter parsing */
 static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
@@ -232,8 +233,12 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 
 	l1tf_vmx_mitigation = l1tf;
 
-	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
-		static_branch_enable(&vmx_l1d_should_flush);
+	if (l1tf == VMENTER_L1D_FLUSH_NEVER)
+		return 0;
+
+	static_branch_enable(&vmx_l1d_should_flush);
+	if (l1tf == VMENTER_L1D_FLUSH_ALWAYS)
+		static_branch_enable(&vmx_l1d_flush_always);
 	return 0;
 }
 
@@ -9651,7 +9656,6 @@ static void *vmx_l1d_flush_pages;
 static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 {
 	int size = PAGE_SIZE << L1D_CACHE_ORDER;
-	bool always;
 
 	/*
 	 * This code is only executed when the the flush mode is 'cond' or
@@ -9661,8 +9665,10 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	 * it. The flush bit gets set again either from vcpu_run() or from
 	 * one of the unsafe VMEXIT handlers.
 	 */
-	always = l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_ALWAYS;
-	vcpu->arch.l1tf_flush_l1d = always;
+	if (static_branch_unlikely(&vmx_l1d_flush_always))
+		vcpu->arch.l1tf_flush_l1d = true;
+	else
+		vcpu->arch.l1tf_flush_l1d = false;
 
 	vcpu->stat.l1d_flush++;
 
-- 
cgit v1.2.3


From dd4bfa739a72508b75760b393d129ed7b431daab Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:21 +0200
Subject: x86/kvm: Serialize L1D flush parameter setter

Writes to the parameter files are not serialized at the sysfs core
level, so local serialization is required.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142322.873642605@linutronix.de
---
 arch/x86/kvm/vmx.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 37c7ff581184..12b1a5dae767 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -193,6 +193,7 @@ extern const ulong vmx_return;
 
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_always);
+static DEFINE_MUTEX(vmx_l1d_flush_mutex);
 
 /* Storage for pre module init parameter parsing */
 static enum vmx_l1d_flush_state __read_mostly vmentry_l1d_flush_param = VMENTER_L1D_FLUSH_AUTO;
@@ -257,7 +258,7 @@ static int vmentry_l1d_flush_parse(const char *s)
 
 static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
 {
-	int l1tf;
+	int l1tf, ret;
 
 	if (!boot_cpu_has(X86_BUG_L1TF))
 		return 0;
@@ -277,7 +278,10 @@ static int vmentry_l1d_flush_set(const char *s, const struct kernel_param *kp)
 		return 0;
 	}
 
-	return vmx_setup_l1d_flush(l1tf);
+	mutex_lock(&vmx_l1d_flush_mutex);
+	ret = vmx_setup_l1d_flush(l1tf);
+	mutex_unlock(&vmx_l1d_flush_mutex);
+	return ret;
 }
 
 static int vmentry_l1d_flush_get(char *s, const struct kernel_param *kp)
-- 
cgit v1.2.3


From 895ae47f9918833c3a880fbccd41e0692b37e7d9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:22 +0200
Subject: x86/kvm: Allow runtime control of L1D flush

All mitigation modes can be switched at run time with a static key now:

 - Use sysfs_streq() instead of strcmp() to handle the trailing new line
   from sysfs writes correctly.
 - Make the static key management handle multiple invocations properly.
 - Set the module parameter file to RW

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142322.954525119@linutronix.de
---
 arch/x86/kernel/cpu/bugs.c |  2 +-
 arch/x86/kvm/vmx.c         | 13 ++++++++-----
 2 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 1b3dc586d29d..7df7df9a2753 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -660,7 +660,7 @@ void x86_spec_ctrl_setup_ap(void)
 #define pr_fmt(fmt)	"L1TF: " fmt
 
 #if IS_ENABLED(CONFIG_KVM_INTEL)
-enum vmx_l1d_flush_state l1tf_vmx_mitigation __ro_after_init = VMENTER_L1D_FLUSH_AUTO;
+enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
 #endif
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 12b1a5dae767..08fcd59342ed 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -234,12 +234,15 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 
 	l1tf_vmx_mitigation = l1tf;
 
-	if (l1tf == VMENTER_L1D_FLUSH_NEVER)
-		return 0;
+	if (l1tf != VMENTER_L1D_FLUSH_NEVER)
+		static_branch_enable(&vmx_l1d_should_flush);
+	else
+		static_branch_disable(&vmx_l1d_should_flush);
 
-	static_branch_enable(&vmx_l1d_should_flush);
 	if (l1tf == VMENTER_L1D_FLUSH_ALWAYS)
 		static_branch_enable(&vmx_l1d_flush_always);
+	else
+		static_branch_disable(&vmx_l1d_flush_always);
 	return 0;
 }
 
@@ -249,7 +252,7 @@ static int vmentry_l1d_flush_parse(const char *s)
 
 	if (s) {
 		for (i = 0; i < ARRAY_SIZE(vmentry_l1d_param); i++) {
-			if (!strcmp(s, vmentry_l1d_param[i].option))
+			if (sysfs_streq(s, vmentry_l1d_param[i].option))
 				return vmentry_l1d_param[i].cmd;
 		}
 	}
@@ -293,7 +296,7 @@ static const struct kernel_param_ops vmentry_l1d_flush_ops = {
 	.set = vmentry_l1d_flush_set,
 	.get = vmentry_l1d_flush_get,
 };
-module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, S_IRUGO);
+module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
 
 struct kvm_vmx {
 	struct kvm kvm;
-- 
cgit v1.2.3


From 8e1b706b6e819bed215c0db16345568864660393 Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Fri, 13 Jul 2018 16:23:23 +0200
Subject: cpu/hotplug: Expose SMT control init function

The L1TF mitigation will gain a commend line parameter which allows to set
a combination of hypervisor mitigation and SMT control.

Expose cpu_smt_disable() so the command line parser can tweak SMT settings.

[ tglx: Split out of larger patch and made it preserve an already existing
  	force off state ]

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142323.039715135@linutronix.de
---
 include/linux/cpu.h |  2 ++
 kernel/cpu.c        | 16 +++++++++++++---
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 7532cbf27b1d..c9b23ad27b38 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -177,8 +177,10 @@ enum cpuhp_smt_control {
 
 #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
 extern enum cpuhp_smt_control cpu_smt_control;
+extern void cpu_smt_disable(bool force);
 #else
 # define cpu_smt_control		(CPU_SMT_ENABLED)
+static inline void cpu_smt_disable(bool force) { }
 #endif
 
 #endif /* _LINUX_CPU_H_ */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index d79e24df2420..8453e31f2d1a 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -347,13 +347,23 @@ EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
 EXPORT_SYMBOL_GPL(cpu_smt_control);
 
-static int __init smt_cmdline_disable(char *str)
+void __init cpu_smt_disable(bool force)
 {
-	cpu_smt_control = CPU_SMT_DISABLED;
-	if (str && !strcmp(str, "force")) {
+	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
+		cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+		return;
+
+	if (force) {
 		pr_info("SMT: Force disabled\n");
 		cpu_smt_control = CPU_SMT_FORCE_DISABLED;
+	} else {
+		cpu_smt_control = CPU_SMT_DISABLED;
 	}
+}
+
+static int __init smt_cmdline_disable(char *str)
+{
+	cpu_smt_disable(str && !strcmp(str, "force"));
 	return 0;
 }
 early_param("nosmt", smt_cmdline_disable);
-- 
cgit v1.2.3


From fee0aede6f4739c87179eca76136f83210953b86 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:24 +0200
Subject: cpu/hotplug: Set CPU_SMT_NOT_SUPPORTED early

The CPU_SMT_NOT_SUPPORTED state is set (if the processor does not support
SMT) when the sysfs SMT control file is initialized.

That was fine so far as this was only required to make the output of the
control file correct and to prevent writes in that case.

With the upcoming l1tf command line parameter, this needs to be set up
before the L1TF mitigation selection and command line parsing happens.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142323.121795971@linutronix.de
---
 arch/x86/kernel/cpu/bugs.c |  6 ++++++
 include/linux/cpu.h        |  2 ++
 kernel/cpu.c               | 13 ++++++++++---
 3 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 7df7df9a2753..4be69a7bef0b 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -58,6 +58,12 @@ void __init check_bugs(void)
 {
 	identify_boot_cpu();
 
+	/*
+	 * identify_boot_cpu() initialized SMT support information, let the
+	 * core code know.
+	 */
+	cpu_smt_check_topology();
+
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
 		print_cpu_info(&boot_cpu_data);
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index c9b23ad27b38..ccdf3a67ce56 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -178,9 +178,11 @@ enum cpuhp_smt_control {
 #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
 extern enum cpuhp_smt_control cpu_smt_control;
 extern void cpu_smt_disable(bool force);
+extern void cpu_smt_check_topology(void);
 #else
 # define cpu_smt_control		(CPU_SMT_ENABLED)
 static inline void cpu_smt_disable(bool force) { }
+static inline void cpu_smt_check_topology(void) { }
 #endif
 
 #endif /* _LINUX_CPU_H_ */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8453e31f2d1a..37eec872042b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -361,6 +361,16 @@ void __init cpu_smt_disable(bool force)
 	}
 }
 
+/*
+ * The decision whether SMT is supported can only be done after the full
+ * CPU identification. Called from architecture code.
+ */
+void __init cpu_smt_check_topology(void)
+{
+	if (!topology_smt_supported())
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
 static int __init smt_cmdline_disable(char *str)
 {
 	cpu_smt_disable(str && !strcmp(str, "force"));
@@ -2115,9 +2125,6 @@ static const struct attribute_group cpuhp_smt_attr_group = {
 
 static int __init cpu_smt_state_init(void)
 {
-	if (!topology_smt_supported())
-		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
-
 	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				  &cpuhp_smt_attr_group);
 }
-- 
cgit v1.2.3


From d90a7a0ec83fb86622cd7dae23255d3c50a99ec8 Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Fri, 13 Jul 2018 16:23:25 +0200
Subject: x86/bugs, kvm: Introduce boot-time control of L1TF mitigations

Introduce the 'l1tf=' kernel command line option to allow for boot-time
switching of mitigation that is used on processors affected by L1TF.

The possible values are:

  full
	Provides all available mitigations for the L1TF vulnerability. Disables
	SMT and enables all mitigations in the hypervisors. SMT control via
	/sys/devices/system/cpu/smt/control is still possible after boot.
	Hypervisors will issue a warning when the first VM is started in
	a potentially insecure configuration, i.e. SMT enabled or L1D flush
	disabled.

  full,force
	Same as 'full', but disables SMT control. Implies the 'nosmt=force'
	command line option. sysfs control of SMT and the hypervisor flush
	control is disabled.

  flush
	Leaves SMT enabled and enables the conditional hypervisor mitigation.
	Hypervisors will issue a warning when the first VM is started in a
	potentially insecure configuration, i.e. SMT enabled or L1D flush
	disabled.

  flush,nosmt
	Disables SMT and enables the conditional hypervisor mitigation. SMT
	control via /sys/devices/system/cpu/smt/control is still possible
	after boot. If SMT is reenabled or flushing disabled at runtime
	hypervisors will issue a warning.

  flush,nowarn
	Same as 'flush', but hypervisors will not warn when
	a VM is started in a potentially insecure configuration.

  off
	Disables hypervisor mitigations and doesn't emit any warnings.

Default is 'flush'.

Let KVM adhere to these semantics, which means:

  - 'lt1f=full,force'	: Performe L1D flushes. No runtime control
    			  possible.

  - 'l1tf=full'
  - 'l1tf-flush'
  - 'l1tf=flush,nosmt'	: Perform L1D flushes and warn on VM start if
			  SMT has been runtime enabled or L1D flushing
			  has been run-time enabled

  - 'l1tf=flush,nowarn'	: Perform L1D flushes and no warnings are emitted.

  - 'l1tf=off'		: L1D flushes are not performed and no warnings
			  are emitted.

KVM can always override the L1D flushing behavior using its 'vmentry_l1d_flush'
module parameter except when lt1f=full,force is set.

This makes KVM's private 'nosmt' option redundant, and as it is a bit
non-systematic anyway (this is something to control globally, not on
hypervisor level), remove that option.

Add the missing Documentation entry for the l1tf vulnerability sysfs file
while at it.

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lkml.kernel.org/r/20180713142323.202758176@linutronix.de
---
 Documentation/ABI/testing/sysfs-devices-system-cpu |  4 ++
 Documentation/admin-guide/kernel-parameters.txt    | 68 ++++++++++++++++++++--
 arch/x86/include/asm/processor.h                   | 12 ++++
 arch/x86/kernel/cpu/bugs.c                         | 44 ++++++++++++++
 arch/x86/kvm/vmx.c                                 | 56 +++++++++++++-----
 5 files changed, 165 insertions(+), 19 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 65d9b844ecfd..73318225a368 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -476,6 +476,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/spec_store_bypass
+		/sys/devices/system/cpu/vulnerabilities/l1tf
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
 Description:	Information about CPU vulnerabilities
@@ -488,6 +489,9 @@ Description:	Information about CPU vulnerabilities
 		"Vulnerable"	  CPU is affected and no mitigation in effect
 		"Mitigation: $M"  CPU is affected and mitigation $M is in effect
 
+		Details about the l1tf file can be found in
+		Documentation/admin-guide/l1tf.rst
+
 What:		/sys/devices/system/cpu/smt
 		/sys/devices/system/cpu/smt/active
 		/sys/devices/system/cpu/smt/control
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 4f790566ad91..9a08a7aa2bc3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1946,12 +1946,6 @@
 			[KVM,ARM] Allow use of GICv4 for direct injection of
 			LPIs.
 
-	kvm-intel.nosmt=[KVM,Intel] If the L1TF CPU bug is present (CVE-2018-3620)
-			and the system has SMT (aka Hyper-Threading) enabled then
-			don't allow guests to be created.
-
-			Default is 0 (allow guests to be created).
-
 	kvm-intel.ept=	[KVM,Intel] Disable extended page tables
 			(virtualized MMU) support on capable Intel chips.
 			Default is 1 (enabled)
@@ -1989,6 +1983,68 @@
 			feature (tagged TLBs) on capable Intel chips.
 			Default is 1 (enabled)
 
+	l1tf=           [X86] Control mitigation of the L1TF vulnerability on
+			      affected CPUs
+
+			The kernel PTE inversion protection is unconditionally
+			enabled and cannot be disabled.
+
+			full
+				Provides all available mitigations for the
+				L1TF vulnerability. Disables SMT and
+				enables all mitigations in the
+				hypervisors, i.e. unconditional L1D flush.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			full,force
+				Same as 'full', but disables SMT and L1D
+				flush runtime control. Implies the
+				'nosmt=force' command line option.
+				(i.e. sysfs control of SMT is disabled.)
+
+			flush
+				Leaves SMT enabled and enables the default
+				hypervisor mitigation, i.e. conditional
+				L1D flush.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			flush,nosmt
+
+				Disables SMT and enables the default
+				hypervisor mitigation.
+
+				SMT control and L1D flush control via the
+				sysfs interface is still possible after
+				boot.  Hypervisors will issue a warning
+				when the first VM is started in a
+				potentially insecure configuration,
+				i.e. SMT enabled or L1D flush disabled.
+
+			flush,nowarn
+				Same as 'flush', but hypervisors will not
+				warn when a VM is started in a potentially
+				insecure configuration.
+
+			off
+				Disables hypervisor mitigations and doesn't
+				emit any warnings.
+
+			Default is 'flush'.
+
+			For details see: Documentation/admin-guide/l1tf.rst
+
 	l2cr=		[PPC]
 
 	l3cr=		[PPC]
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7e3ac5eedcd6..79e409974ccc 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -982,4 +982,16 @@ bool xen_set_default_idle(void);
 void stop_this_cpu(void *dummy);
 void df_debug(struct pt_regs *regs, long error_code);
 void microcode_check(void);
+
+enum l1tf_mitigations {
+	L1TF_MITIGATION_OFF,
+	L1TF_MITIGATION_FLUSH_NOWARN,
+	L1TF_MITIGATION_FLUSH,
+	L1TF_MITIGATION_FLUSH_NOSMT,
+	L1TF_MITIGATION_FULL,
+	L1TF_MITIGATION_FULL_FORCE
+};
+
+extern enum l1tf_mitigations l1tf_mitigation;
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 4be69a7bef0b..fa6123bdd032 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -665,7 +665,11 @@ void x86_spec_ctrl_setup_ap(void)
 #undef pr_fmt
 #define pr_fmt(fmt)	"L1TF: " fmt
 
+/* Default mitigation for L1TF-affected CPUs */
+enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH;
 #if IS_ENABLED(CONFIG_KVM_INTEL)
+EXPORT_SYMBOL_GPL(l1tf_mitigation);
+
 enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
 #endif
@@ -677,6 +681,20 @@ static void __init l1tf_select_mitigation(void)
 	if (!boot_cpu_has_bug(X86_BUG_L1TF))
 		return;
 
+	switch (l1tf_mitigation) {
+	case L1TF_MITIGATION_OFF:
+	case L1TF_MITIGATION_FLUSH_NOWARN:
+	case L1TF_MITIGATION_FLUSH:
+		break;
+	case L1TF_MITIGATION_FLUSH_NOSMT:
+	case L1TF_MITIGATION_FULL:
+		cpu_smt_disable(false);
+		break;
+	case L1TF_MITIGATION_FULL_FORCE:
+		cpu_smt_disable(true);
+		break;
+	}
+
 #if CONFIG_PGTABLE_LEVELS == 2
 	pr_warn("Kernel not compiled for PAE. No mitigation for L1TF\n");
 	return;
@@ -695,6 +713,32 @@ static void __init l1tf_select_mitigation(void)
 
 	setup_force_cpu_cap(X86_FEATURE_L1TF_PTEINV);
 }
+
+static int __init l1tf_cmdline(char *str)
+{
+	if (!boot_cpu_has_bug(X86_BUG_L1TF))
+		return 0;
+
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		l1tf_mitigation = L1TF_MITIGATION_OFF;
+	else if (!strcmp(str, "flush,nowarn"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOWARN;
+	else if (!strcmp(str, "flush"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH;
+	else if (!strcmp(str, "flush,nosmt"))
+		l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+	else if (!strcmp(str, "full"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL;
+	else if (!strcmp(str, "full,force"))
+		l1tf_mitigation = L1TF_MITIGATION_FULL_FORCE;
+
+	return 0;
+}
+early_param("l1tf", l1tf_cmdline);
+
 #undef pr_fmt
 
 #ifdef CONFIG_SYSFS
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 08fcd59342ed..c5c0118b126d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -71,9 +71,6 @@ static const struct x86_cpu_id vmx_cpu_id[] = {
 };
 MODULE_DEVICE_TABLE(x86cpu, vmx_cpu_id);
 
-static bool __read_mostly nosmt;
-module_param(nosmt, bool, S_IRUGO);
-
 static bool __read_mostly enable_vpid = 1;
 module_param_named(vpid, enable_vpid, bool, 0444);
 
@@ -215,15 +212,31 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
 	struct page *page;
 
-	/* If set to 'auto' select 'cond' */
-	if (l1tf == VMENTER_L1D_FLUSH_AUTO)
-		l1tf = VMENTER_L1D_FLUSH_COND;
-
 	if (!enable_ept) {
 		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
 		return 0;
 	}
 
+	/* If set to auto use the default l1tf mitigation method */
+	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+			l1tf = VMENTER_L1D_FLUSH_NEVER;
+			break;
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+			l1tf = VMENTER_L1D_FLUSH_COND;
+			break;
+		case L1TF_MITIGATION_FULL:
+		case L1TF_MITIGATION_FULL_FORCE:
+			l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+			break;
+		}
+	} else if (l1tf_mitigation == L1TF_MITIGATION_FULL_FORCE) {
+		l1tf = VMENTER_L1D_FLUSH_ALWAYS;
+	}
+
 	if (l1tf != VMENTER_L1D_FLUSH_NEVER && !vmx_l1d_flush_pages &&
 	    !boot_cpu_has(X86_FEATURE_FLUSH_L1D)) {
 		page = alloc_pages(GFP_KERNEL, L1D_CACHE_ORDER);
@@ -10571,19 +10584,36 @@ free_vcpu:
 	return ERR_PTR(err);
 }
 
-#define L1TF_MSG "SMT enabled with L1TF CPU bug present. Refer to CVE-2018-3620 for details.\n"
+#define L1TF_MSG_SMT "L1TF CPU bug present and SMT on, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
+#define L1TF_MSG_L1D "L1TF CPU bug present and virtualization mitigation disabled, data leak possible. See CVE-2018-3646 and https://www.kernel.org/doc/html/latest/admin-guide/l1tf.html for details.\n"
 
 static int vmx_vm_init(struct kvm *kvm)
 {
 	if (!ple_gap)
 		kvm->arch.pause_in_guest = true;
 
-	if (boot_cpu_has(X86_BUG_L1TF) && cpu_smt_control == CPU_SMT_ENABLED) {
-		if (nosmt) {
-			pr_err(L1TF_MSG);
-			return -EOPNOTSUPP;
+	if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
+		switch (l1tf_mitigation) {
+		case L1TF_MITIGATION_OFF:
+		case L1TF_MITIGATION_FLUSH_NOWARN:
+			/* 'I explicitly don't care' is set */
+			break;
+		case L1TF_MITIGATION_FLUSH:
+		case L1TF_MITIGATION_FLUSH_NOSMT:
+		case L1TF_MITIGATION_FULL:
+			/*
+			 * Warn upon starting the first VM in a potentially
+			 * insecure environment.
+			 */
+			if (cpu_smt_control == CPU_SMT_ENABLED)
+				pr_warn_once(L1TF_MSG_SMT);
+			if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER)
+				pr_warn_once(L1TF_MSG_L1D);
+			break;
+		case L1TF_MITIGATION_FULL_FORCE:
+			/* Flush is enforced */
+			break;
 		}
-		pr_warn(L1TF_MSG);
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 3ec8ce5d866ec6a08a9cfab82b62acf4a830b35f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 13 Jul 2018 16:23:26 +0200
Subject: Documentation: Add section about CPU vulnerabilities

Add documentation for the L1TF vulnerability and the mitigation mechanisms:

  - Explain the problem and risks
  - Document the mitigation mechanisms
  - Document the command line controls
  - Document the sysfs files

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20180713142323.287429944@linutronix.de
---
 Documentation/admin-guide/index.rst |   9 +
 Documentation/admin-guide/l1tf.rst  | 591 ++++++++++++++++++++++++++++++++++++
 2 files changed, 600 insertions(+)
 create mode 100644 Documentation/admin-guide/l1tf.rst

diff --git a/Documentation/admin-guide/index.rst b/Documentation/admin-guide/index.rst
index 48d70af11652..0873685bab0f 100644
--- a/Documentation/admin-guide/index.rst
+++ b/Documentation/admin-guide/index.rst
@@ -17,6 +17,15 @@ etc.
    kernel-parameters
    devices
 
+This section describes CPU vulnerabilities and provides an overview of the
+possible mitigations along with guidance for selecting mitigations if they
+are configurable at compile, boot or run time.
+
+.. toctree::
+   :maxdepth: 1
+
+   l1tf
+
 Here is a set of documents aimed at users who are trying to track down
 problems and bugs in particular.
 
diff --git a/Documentation/admin-guide/l1tf.rst b/Documentation/admin-guide/l1tf.rst
new file mode 100644
index 000000000000..f2bb28cff439
--- /dev/null
+++ b/Documentation/admin-guide/l1tf.rst
@@ -0,0 +1,591 @@
+L1TF - L1 Terminal Fault
+========================
+
+L1 Terminal Fault is a hardware vulnerability which allows unprivileged
+speculative access to data which is available in the Level 1 Data Cache
+when the page table entry controlling the virtual address, which is used
+for the access, has the Present bit cleared or other reserved bits set.
+
+Affected processors
+-------------------
+
+This vulnerability affects a wide range of Intel processors. The
+vulnerability is not present on:
+
+   - Processors from AMD, Centaur and other non Intel vendors
+
+   - Older processor models, where the CPU family is < 6
+
+   - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft,
+     Penwell, Pineview, Slivermont, Airmont, Merrifield)
+
+   - The Intel Core Duo Yonah variants (2006 - 2008)
+
+   - The Intel XEON PHI family
+
+   - Intel processors which have the ARCH_CAP_RDCL_NO bit set in the
+     IA32_ARCH_CAPABILITIES MSR. If the bit is set the CPU is not affected
+     by the Meltdown vulnerability either. These CPUs should become
+     available by end of 2018.
+
+Whether a processor is affected or not can be read out from the L1TF
+vulnerability file in sysfs. See :ref:`l1tf_sys_info`.
+
+Related CVEs
+------------
+
+The following CVE entries are related to the L1TF vulnerability:
+
+   =============  =================  ==============================
+   CVE-2018-3615  L1 Terminal Fault  SGX related aspects
+   CVE-2018-3620  L1 Terminal Fault  OS, SMM related aspects
+   CVE-2018-3646  L1 Terminal Fault  Virtualization related aspects
+   =============  =================  ==============================
+
+Problem
+-------
+
+If an instruction accesses a virtual address for which the relevant page
+table entry (PTE) has the Present bit cleared or other reserved bits set,
+then speculative execution ignores the invalid PTE and loads the referenced
+data if it is present in the Level 1 Data Cache, as if the page referenced
+by the address bits in the PTE was still present and accessible.
+
+While this is a purely speculative mechanism and the instruction will raise
+a page fault when it is retired eventually, the pure act of loading the
+data and making it available to other speculative instructions opens up the
+opportunity for side channel attacks to unprivileged malicious code,
+similar to the Meltdown attack.
+
+While Meltdown breaks the user space to kernel space protection, L1TF
+allows to attack any physical memory address in the system and the attack
+works across all protection domains. It allows an attack of SGX and also
+works from inside virtual machines because the speculation bypasses the
+extended page table (EPT) protection mechanism.
+
+
+Attack scenarios
+----------------
+
+1. Malicious user space
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   Operating Systems store arbitrary information in the address bits of a
+   PTE which is marked non present. This allows a malicious user space
+   application to attack the physical memory to which these PTEs resolve.
+   In some cases user-space can maliciously influence the information
+   encoded in the address bits of the PTE, thus making attacks more
+   deterministic and more practical.
+
+   The Linux kernel contains a mitigation for this attack vector, PTE
+   inversion, which is permanently enabled and has no performance
+   impact. The kernel ensures that the address bits of PTEs, which are not
+   marked present, never point to cacheable physical memory space.
+
+   A system with an up to date kernel is protected against attacks from
+   malicious user space applications.
+
+2. Malicious guest in a virtual machine
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The fact that L1TF breaks all domain protections allows malicious guest
+   OSes, which can control the PTEs directly, and malicious guest user
+   space applications, which run on an unprotected guest kernel lacking the
+   PTE inversion mitigation for L1TF, to attack physical host memory.
+
+   A special aspect of L1TF in the context of virtualization is symmetric
+   multi threading (SMT). The Intel implementation of SMT is called
+   HyperThreading. The fact that Hyperthreads on the affected processors
+   share the L1 Data Cache (L1D) is important for this. As the flaw allows
+   only to attack data which is present in L1D, a malicious guest running
+   on one Hyperthread can attack the data which is brought into the L1D by
+   the context which runs on the sibling Hyperthread of the same physical
+   core. This context can be host OS, host user space or a different guest.
+
+   If the processor does not support Extended Page Tables, the attack is
+   only possible, when the hypervisor does not sanitize the content of the
+   effective (shadow) page tables.
+
+   While solutions exist to mitigate these attack vectors fully, these
+   mitigations are not enabled by default in the Linux kernel because they
+   can affect performance significantly. The kernel provides several
+   mechanisms which can be utilized to address the problem depending on the
+   deployment scenario. The mitigations, their protection scope and impact
+   are described in the next sections.
+
+   The default mitigations and the rationale for chosing them are explained
+   at the end of this document. See :ref:`default_mitigations`.
+
+.. _l1tf_sys_info:
+
+L1TF system information
+-----------------------
+
+The Linux kernel provides a sysfs interface to enumerate the current L1TF
+status of the system: whether the system is vulnerable, and which
+mitigations are active. The relevant sysfs file is:
+
+/sys/devices/system/cpu/vulnerabilities/l1tf
+
+The possible values in this file are:
+
+  ===========================   ===============================
+  'Not affected'		The processor is not vulnerable
+  'Mitigation: PTE Inversion'	The host protection is active
+  ===========================   ===============================
+
+If KVM/VMX is enabled and the processor is vulnerable then the following
+information is appended to the 'Mitigation: PTE Inversion' part:
+
+  - SMT status:
+
+    =====================  ================
+    'VMX: SMT vulnerable'  SMT is enabled
+    'VMX: SMT disabled'    SMT is disabled
+    =====================  ================
+
+  - L1D Flush mode:
+
+    ================================  ====================================
+    'L1D vulnerable'		      L1D flushing is disabled
+
+    'L1D conditional cache flushes'   L1D flush is conditionally enabled
+
+    'L1D cache flushes'		      L1D flush is unconditionally enabled
+    ================================  ====================================
+
+The resulting grade of protection is discussed in the following sections.
+
+
+Host mitigation mechanism
+-------------------------
+
+The kernel is unconditionally protected against L1TF attacks from malicious
+user space running on the host.
+
+
+Guest mitigation mechanisms
+---------------------------
+
+.. _l1d_flush:
+
+1. L1D flush on VMENTER
+^^^^^^^^^^^^^^^^^^^^^^^
+
+   To make sure that a guest cannot attack data which is present in the L1D
+   the hypervisor flushes the L1D before entering the guest.
+
+   Flushing the L1D evicts not only the data which should not be accessed
+   by a potentially malicious guest, it also flushes the guest
+   data. Flushing the L1D has a performance impact as the processor has to
+   bring the flushed guest data back into the L1D. Depending on the
+   frequency of VMEXIT/VMENTER and the type of computations in the guest
+   performance degradation in the range of 1% to 50% has been observed. For
+   scenarios where guest VMEXIT/VMENTER are rare the performance impact is
+   minimal. Virtio and mechanisms like posted interrupts are designed to
+   confine the VMEXITs to a bare minimum, but specific configurations and
+   application scenarios might still suffer from a high VMEXIT rate.
+
+   The kernel provides two L1D flush modes:
+    - conditional ('cond')
+    - unconditional ('always')
+
+   The conditional mode avoids L1D flushing after VMEXITs which execute
+   only audited code pathes before the corresponding VMENTER. These code
+   pathes have beed verified that they cannot expose secrets or other
+   interesting data to an attacker, but they can leak information about the
+   address space layout of the hypervisor.
+
+   Unconditional mode flushes L1D on all VMENTER invocations and provides
+   maximum protection. It has a higher overhead than the conditional
+   mode. The overhead cannot be quantified correctly as it depends on the
+   work load scenario and the resulting number of VMEXITs.
+
+   The general recommendation is to enable L1D flush on VMENTER. The kernel
+   defaults to conditional mode on affected processors.
+
+   **Note**, that L1D flush does not prevent the SMT problem because the
+   sibling thread will also bring back its data into the L1D which makes it
+   attackable again.
+
+   L1D flush can be controlled by the administrator via the kernel command
+   line and sysfs control files. See :ref:`mitigation_control_command_line`
+   and :ref:`mitigation_control_kvm`.
+
+.. _guest_confinement:
+
+2. Guest VCPU confinement to dedicated physical cores
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   To address the SMT problem, it is possible to make a guest or a group of
+   guests affine to one or more physical cores. The proper mechanism for
+   that is to utilize exclusive cpusets to ensure that no other guest or
+   host tasks can run on these cores.
+
+   If only a single guest or related guests run on sibling SMT threads on
+   the same physical core then they can only attack their own memory and
+   restricted parts of the host memory.
+
+   Host memory is attackable, when one of the sibling SMT threads runs in
+   host OS (hypervisor) context and the other in guest context. The amount
+   of valuable information from the host OS context depends on the context
+   which the host OS executes, i.e. interrupts, soft interrupts and kernel
+   threads. The amount of valuable data from these contexts cannot be
+   declared as non-interesting for an attacker without deep inspection of
+   the code.
+
+   **Note**, that assigning guests to a fixed set of physical cores affects
+   the ability of the scheduler to do load balancing and might have
+   negative effects on CPU utilization depending on the hosting
+   scenario. Disabling SMT might be a viable alternative for particular
+   scenarios.
+
+   For further information about confining guests to a single or to a group
+   of cores consult the cpusets documentation:
+
+   https://www.kernel.org/doc/Documentation/cgroup-v1/cpusets.txt
+
+.. _interrupt_isolation:
+
+3. Interrupt affinity
+^^^^^^^^^^^^^^^^^^^^^
+
+   Interrupts can be made affine to logical CPUs. This is not universally
+   true because there are types of interrupts which are truly per CPU
+   interrupts, e.g. the local timer interrupt. Aside of that multi queue
+   devices affine their interrupts to single CPUs or groups of CPUs per
+   queue without allowing the administrator to control the affinities.
+
+   Moving the interrupts, which can be affinity controlled, away from CPUs
+   which run untrusted guests, reduces the attack vector space.
+
+   Whether the interrupts with are affine to CPUs, which run untrusted
+   guests, provide interesting data for an attacker depends on the system
+   configuration and the scenarios which run on the system. While for some
+   of the interrupts it can be assumed that they wont expose interesting
+   information beyond exposing hints about the host OS memory layout, there
+   is no way to make general assumptions.
+
+   Interrupt affinity can be controlled by the administrator via the
+   /proc/irq/$NR/smp_affinity[_list] files. Limited documentation is
+   available at:
+
+   https://www.kernel.org/doc/Documentation/IRQ-affinity.txt
+
+.. _smt_control:
+
+4. SMT control
+^^^^^^^^^^^^^^
+
+   To prevent the SMT issues of L1TF it might be necessary to disable SMT
+   completely. Disabling SMT can have a significant performance impact, but
+   the impact depends on the hosting scenario and the type of workloads.
+   The impact of disabling SMT needs also to be weighted against the impact
+   of other mitigation solutions like confining guests to dedicated cores.
+
+   The kernel provides a sysfs interface to retrieve the status of SMT and
+   to control it. It also provides a kernel command line interface to
+   control SMT.
+
+   The kernel command line interface consists of the following options:
+
+     =========== ==========================================================
+     nosmt	 Affects the bring up of the secondary CPUs during boot. The
+		 kernel tries to bring all present CPUs online during the
+		 boot process. "nosmt" makes sure that from each physical
+		 core only one - the so called primary (hyper) thread is
+		 activated. Due to a design flaw of Intel processors related
+		 to Machine Check Exceptions the non primary siblings have
+		 to be brought up at least partially and are then shut down
+		 again.  "nosmt" can be undone via the sysfs interface.
+
+     nosmt=force Has the same effect as "nosmt' but it does not allow to
+		 undo the SMT disable via the sysfs interface.
+     =========== ==========================================================
+
+   The sysfs interface provides two files:
+
+   - /sys/devices/system/cpu/smt/control
+   - /sys/devices/system/cpu/smt/active
+
+   /sys/devices/system/cpu/smt/control:
+
+     This file allows to read out the SMT control state and provides the
+     ability to disable or (re)enable SMT. The possible states are:
+
+	==============  ===================================================
+	on		SMT is supported by the CPU and enabled. All
+			logical CPUs can be onlined and offlined without
+			restrictions.
+
+	off		SMT is supported by the CPU and disabled. Only
+			the so called primary SMT threads can be onlined
+			and offlined without restrictions. An attempt to
+			online a non-primary sibling is rejected
+
+	forceoff	Same as 'off' but the state cannot be controlled.
+			Attempts to write to the control file are rejected.
+
+	notsupported	The processor does not support SMT. It's therefore
+			not affected by the SMT implications of L1TF.
+			Attempts to write to the control file are rejected.
+	==============  ===================================================
+
+     The possible states which can be written into this file to control SMT
+     state are:
+
+     - on
+     - off
+     - forceoff
+
+   /sys/devices/system/cpu/smt/active:
+
+     This file reports whether SMT is enabled and active, i.e. if on any
+     physical core two or more sibling threads are online.
+
+   SMT control is also possible at boot time via the l1tf kernel command
+   line parameter in combination with L1D flush control. See
+   :ref:`mitigation_control_command_line`.
+
+5. Disabling EPT
+^^^^^^^^^^^^^^^^
+
+  Disabling EPT for virtual machines provides full mitigation for L1TF even
+  with SMT enabled, because the effective page tables for guests are
+  managed and sanitized by the hypervisor. Though disabling EPT has a
+  significant performance impact especially when the Meltdown mitigation
+  KPTI is enabled.
+
+  EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+There is ongoing research and development for new mitigation mechanisms to
+address the performance impact of disabling SMT or EPT.
+
+.. _mitigation_control_command_line:
+
+Mitigation control on the kernel command line
+---------------------------------------------
+
+The kernel command line allows to control the L1TF mitigations at boot
+time with the option "l1tf=". The valid arguments for this option are:
+
+  ============  =============================================================
+  full		Provides all available mitigations for the L1TF
+		vulnerability. Disables SMT and enables all mitigations in
+		the hypervisors, i.e. unconditional L1D flushing
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  full,force	Same as 'full', but disables SMT and L1D flush runtime
+		control. Implies the 'nosmt=force' command line option.
+		(i.e. sysfs control of SMT is disabled.)
+
+  flush		Leaves SMT enabled and enables the default hypervisor
+		mitigation, i.e. conditional L1D flushing
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  flush,nosmt	Disables SMT and enables the default hypervisor mitigation,
+		i.e. conditional L1D flushing.
+
+		SMT control and L1D flush control via the sysfs interface
+		is still possible after boot.  Hypervisors will issue a
+		warning when the first VM is started in a potentially
+		insecure configuration, i.e. SMT enabled or L1D flush
+		disabled.
+
+  flush,nowarn	Same as 'flush', but hypervisors will not warn when a VM is
+		started in a potentially insecure configuration.
+
+  off		Disables hypervisor mitigations and doesn't emit any
+		warnings.
+  ============  =============================================================
+
+The default is 'flush'. For details about L1D flushing see :ref:`l1d_flush`.
+
+
+.. _mitigation_control_kvm:
+
+Mitigation control for KVM - module parameter
+-------------------------------------------------------------
+
+The KVM hypervisor mitigation mechanism, flushing the L1D cache when
+entering a guest, can be controlled with a module parameter.
+
+The option/parameter is "kvm-intel.vmentry_l1d_flush=". It takes the
+following arguments:
+
+  ============  ==============================================================
+  always	L1D cache flush on every VMENTER.
+
+  cond		Flush L1D on VMENTER only when the code between VMEXIT and
+		VMENTER can leak host memory which is considered
+		interesting for an attacker. This still can leak host memory
+		which allows e.g. to determine the hosts address space layout.
+
+  never		Disables the mitigation
+  ============  ==============================================================
+
+The parameter can be provided on the kernel command line, as a module
+parameter when loading the modules and at runtime modified via the sysfs
+file:
+
+/sys/module/kvm_intel/parameters/vmentry_l1d_flush
+
+The default is 'cond'. If 'l1tf=full,force' is given on the kernel command
+line, then 'always' is enforced and the kvm-intel.vmentry_l1d_flush
+module parameter is ignored and writes to the sysfs file are rejected.
+
+
+Mitigation selection guide
+--------------------------
+
+1. No virtualization in use
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   The system is protected by the kernel unconditionally and no further
+   action is required.
+
+2. Virtualization with trusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+   If the guest comes from a trusted source and the guest OS kernel is
+   guaranteed to have the L1TF mitigations in place the system is fully
+   protected against L1TF and no further action is required.
+
+   To avoid the overhead of the default L1D flushing on VMENTER the
+   administrator can disable the flushing via the kernel command line and
+   sysfs control files. See :ref:`mitigation_control_command_line` and
+   :ref:`mitigation_control_kvm`.
+
+
+3. Virtualization with untrusted guests
+^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
+
+3.1. SMT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+  If SMT is not supported by the processor or disabled in the BIOS or by
+  the kernel, it's only required to enforce L1D flushing on VMENTER.
+
+  Conditional L1D flushing is the default behaviour and can be tuned. See
+  :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+3.2. EPT not supported or disabled
+""""""""""""""""""""""""""""""""""
+
+  If EPT is not supported by the processor or disabled in the hypervisor,
+  the system is fully protected. SMT can stay enabled and L1D flushing on
+  VMENTER is not required.
+
+  EPT can be disabled in the hypervisor via the 'kvm-intel.ept' parameter.
+
+3.3. SMT and EPT supported and active
+"""""""""""""""""""""""""""""""""""""
+
+  If SMT and EPT are supported and active then various degrees of
+  mitigations can be employed:
+
+  - L1D flushing on VMENTER:
+
+    L1D flushing on VMENTER is the minimal protection requirement, but it
+    is only potent in combination with other mitigation methods.
+
+    Conditional L1D flushing is the default behaviour and can be tuned. See
+    :ref:`mitigation_control_command_line` and :ref:`mitigation_control_kvm`.
+
+  - Guest confinement:
+
+    Confinement of guests to a single or a group of physical cores which
+    are not running any other processes, can reduce the attack surface
+    significantly, but interrupts, soft interrupts and kernel threads can
+    still expose valuable data to a potential attacker. See
+    :ref:`guest_confinement`.
+
+  - Interrupt isolation:
+
+    Isolating the guest CPUs from interrupts can reduce the attack surface
+    further, but still allows a malicious guest to explore a limited amount
+    of host physical memory. This can at least be used to gain knowledge
+    about the host address space layout. The interrupts which have a fixed
+    affinity to the CPUs which run the untrusted guests can depending on
+    the scenario still trigger soft interrupts and schedule kernel threads
+    which might expose valuable information. See
+    :ref:`interrupt_isolation`.
+
+The above three mitigation methods combined can provide protection to a
+certain degree, but the risk of the remaining attack surface has to be
+carefully analyzed. For full protection the following methods are
+available:
+
+  - Disabling SMT:
+
+    Disabling SMT and enforcing the L1D flushing provides the maximum
+    amount of protection. This mitigation is not depending on any of the
+    above mitigation methods.
+
+    SMT control and L1D flushing can be tuned by the command line
+    parameters 'nosmt', 'l1tf', 'kvm-intel.vmentry_l1d_flush' and at run
+    time with the matching sysfs control files. See :ref:`smt_control`,
+    :ref:`mitigation_control_command_line` and
+    :ref:`mitigation_control_kvm`.
+
+  - Disabling EPT:
+
+    Disabling EPT provides the maximum amount of protection as well. It is
+    not depending on any of the above mitigation methods. SMT can stay
+    enabled and L1D flushing is not required, but the performance impact is
+    significant.
+
+    EPT can be disabled in the hypervisor via the 'kvm-intel.ept'
+    parameter.
+
+
+.. _default_mitigations:
+
+Default mitigations
+-------------------
+
+  The kernel default mitigations for vulnerable processors are:
+
+  - PTE inversion to protect against malicious user space. This is done
+    unconditionally and cannot be controlled.
+
+  - L1D conditional flushing on VMENTER when EPT is enabled for
+    a guest.
+
+  The kernel does not by default enforce the disabling of SMT, which leaves
+  SMT systems vulnerable when running untrusted guests with EPT enabled.
+
+  The rationale for this choice is:
+
+  - Force disabling SMT can break existing setups, especially with
+    unattended updates.
+
+  - If regular users run untrusted guests on their machine, then L1TF is
+    just an add on to other malware which might be embedded in an untrusted
+    guest, e.g. spam-bots or attacks on the local network.
+
+    There is no technical way to prevent a user from running untrusted code
+    on their machines blindly.
+
+  - It's technically extremely unlikely and from today's knowledge even
+    impossible that L1TF can be exploited via the most popular attack
+    mechanisms like JavaScript because these mechanisms have no way to
+    control PTEs. If this would be possible and not other mitigation would
+    be possible, then the default might be different.
+
+  - The administrators of cloud and hosting setups have to carefully
+    analyze the risk for their scenarios and make the appropriate
+    mitigation choices, which might even vary across their deployed
+    machines and also result in other changes of their overall setup.
+    There is no way for the kernel to provide a sensible default for this
+    kind of scenarios.
-- 
cgit v1.2.3


From 2c6d1fffa1d9b0a5b5ac1a23be9ad64abe60910d Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Wed, 11 Jul 2018 15:29:07 +0200
Subject: drm: add support for DisplayPort CEC-Tunneling-over-AUX
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds support for the DisplayPort CEC-Tunneling-over-AUX
feature that is part of the DisplayPort 1.3 standard.

Unfortunately, not all DisplayPort/USB-C to HDMI adapters with a
chip that has this capability actually hook up the CEC pin, so
even though a CEC device is created, it may not actually work.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711132909.25409-2-hverkuil@xs4all.nl
---
 drivers/gpu/drm/Kconfig         |  10 +
 drivers/gpu/drm/Makefile        |   1 +
 drivers/gpu/drm/drm_dp_cec.c    | 428 ++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/drm_dp_helper.c |   1 +
 include/drm/drm_dp_helper.h     |  56 ++++++
 5 files changed, 496 insertions(+)
 create mode 100644 drivers/gpu/drm/drm_dp_cec.c

diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index a8054dde49b5..cb88528e7b10 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -122,6 +122,16 @@ config DRM_LOAD_EDID_FIRMWARE
 	  default case is N. Details and instructions how to build your own
 	  EDID data are given in Documentation/EDID/HOWTO.txt.
 
+config DRM_DP_CEC
+	bool "Enable DisplayPort CEC-Tunneling-over-AUX HDMI support"
+	select CEC_CORE
+	help
+	  Choose this option if you want to enable HDMI CEC support for
+	  DisplayPort/USB-C to HDMI adapters.
+
+	  Note: not all adapters support this feature, and even for those
+	  that do support this they often do not hook up the CEC pin.
+
 config DRM_TTM
 	tristate
 	depends on DRM && MMU
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 0e0a3ef1abad..a6771cef85e2 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -41,6 +41,7 @@ drm_kms_helper-$(CONFIG_DRM_PANEL_BRIDGE) += bridge/panel.o
 drm_kms_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fb_helper.o
 drm_kms_helper-$(CONFIG_DRM_KMS_CMA_HELPER) += drm_fb_cma_helper.o
 drm_kms_helper-$(CONFIG_DRM_DP_AUX_CHARDEV) += drm_dp_aux_dev.o
+drm_kms_helper-$(CONFIG_DRM_DP_CEC) += drm_dp_cec.o
 
 obj-$(CONFIG_DRM_KMS_HELPER) += drm_kms_helper.o
 obj-$(CONFIG_DRM_DEBUG_SELFTEST) += selftests/
diff --git a/drivers/gpu/drm/drm_dp_cec.c b/drivers/gpu/drm/drm_dp_cec.c
new file mode 100644
index 000000000000..ddb1c5adebb9
--- /dev/null
+++ b/drivers/gpu/drm/drm_dp_cec.c
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DisplayPort CEC-Tunneling-over-AUX support
+ *
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <drm/drm_dp_helper.h>
+#include <media/cec.h>
+
+/*
+ * Unfortunately it turns out that we have a chicken-and-egg situation
+ * here. Quite a few active (mini-)DP-to-HDMI or USB-C-to-HDMI adapters
+ * have a converter chip that supports CEC-Tunneling-over-AUX (usually the
+ * Parade PS176), but they do not wire up the CEC pin, thus making CEC
+ * useless.
+ *
+ * Sadly there is no way for this driver to know this. What happens is
+ * that a /dev/cecX device is created that is isolated and unable to see
+ * any of the other CEC devices. Quite literally the CEC wire is cut
+ * (or in this case, never connected in the first place).
+ *
+ * The reason so few adapters support this is that this tunneling protocol
+ * was never supported by any OS. So there was no easy way of testing it,
+ * and no incentive to correctly wire up the CEC pin.
+ *
+ * Hopefully by creating this driver it will be easier for vendors to
+ * finally fix their adapters and test the CEC functionality.
+ *
+ * I keep a list of known working adapters here:
+ *
+ * https://hverkuil.home.xs4all.nl/cec-status.txt
+ *
+ * Please mail me (hverkuil@xs4all.nl) if you find an adapter that works
+ * and is not yet listed there.
+ *
+ * Note that the current implementation does not support CEC over an MST hub.
+ * As far as I can see there is no mechanism defined in the DisplayPort
+ * standard to transport CEC interrupts over an MST device. It might be
+ * possible to do this through polling, but I have not been able to get that
+ * to work.
+ */
+
+/**
+ * DOC: dp cec helpers
+ *
+ * These functions take care of supporting the CEC-Tunneling-over-AUX
+ * feature of DisplayPort-to-HDMI adapters.
+ */
+
+/*
+ * When the EDID is unset because the HPD went low, then the CEC DPCD registers
+ * typically can no longer be read (true for a DP-to-HDMI adapter since it is
+ * powered by the HPD). However, some displays toggle the HPD off and on for a
+ * short period for one reason or another, and that would cause the CEC adapter
+ * to be removed and added again, even though nothing else changed.
+ *
+ * This module parameter sets a delay in seconds before the CEC adapter is
+ * actually unregistered. Only if the HPD does not return within that time will
+ * the CEC adapter be unregistered.
+ *
+ * If it is set to a value >= NEVER_UNREG_DELAY, then the CEC adapter will never
+ * be unregistered for as long as the connector remains registered.
+ *
+ * If it is set to 0, then the CEC adapter will be unregistered immediately as
+ * soon as the HPD disappears.
+ *
+ * The default is one second to prevent short HPD glitches from unregistering
+ * the CEC adapter.
+ *
+ * Note that for integrated HDMI branch devices that support CEC the DPCD
+ * registers remain available even if the HPD goes low since it is not powered
+ * by the HPD. In that case the CEC adapter will never be unregistered during
+ * the life time of the connector. At least, this is the theory since I do not
+ * have hardware with an integrated HDMI branch device that supports CEC.
+ */
+#define NEVER_UNREG_DELAY 1000
+static unsigned int drm_dp_cec_unregister_delay = 1;
+module_param(drm_dp_cec_unregister_delay, uint, 0600);
+MODULE_PARM_DESC(drm_dp_cec_unregister_delay,
+		 "CEC unregister delay in seconds, 0: no delay, >= 1000: never unregister");
+
+static int drm_dp_cec_adap_enable(struct cec_adapter *adap, bool enable)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	u32 val = enable ? DP_CEC_TUNNELING_ENABLE : 0;
+	ssize_t err = 0;
+
+	err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val);
+	return (enable && err < 0) ? err : 0;
+}
+
+static int drm_dp_cec_adap_log_addr(struct cec_adapter *adap, u8 addr)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	/* Bit 15 (logical address 15) should always be set */
+	u16 la_mask = 1 << CEC_LOG_ADDR_BROADCAST;
+	u8 mask[2];
+	ssize_t err;
+
+	if (addr != CEC_LOG_ADDR_INVALID)
+		la_mask |= adap->log_addrs.log_addr_mask | (1 << addr);
+	mask[0] = la_mask & 0xff;
+	mask[1] = la_mask >> 8;
+	err = drm_dp_dpcd_write(aux, DP_CEC_LOGICAL_ADDRESS_MASK, mask, 2);
+	return (addr != CEC_LOG_ADDR_INVALID && err < 0) ? err : 0;
+}
+
+static int drm_dp_cec_adap_transmit(struct cec_adapter *adap, u8 attempts,
+				    u32 signal_free_time, struct cec_msg *msg)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	unsigned int retries = min(5, attempts - 1);
+	ssize_t err;
+
+	err = drm_dp_dpcd_write(aux, DP_CEC_TX_MESSAGE_BUFFER,
+				msg->msg, msg->len);
+	if (err < 0)
+		return err;
+
+	err = drm_dp_dpcd_writeb(aux, DP_CEC_TX_MESSAGE_INFO,
+				 (msg->len - 1) | (retries << 4) |
+				 DP_CEC_TX_MESSAGE_SEND);
+	return err < 0 ? err : 0;
+}
+
+static int drm_dp_cec_adap_monitor_all_enable(struct cec_adapter *adap,
+					      bool enable)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	ssize_t err;
+	u8 val;
+
+	if (!(adap->capabilities & CEC_CAP_MONITOR_ALL))
+		return 0;
+
+	err = drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CONTROL, &val);
+	if (err >= 0) {
+		if (enable)
+			val |= DP_CEC_SNOOPING_ENABLE;
+		else
+			val &= ~DP_CEC_SNOOPING_ENABLE;
+		err = drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_CONTROL, val);
+	}
+	return (enable && err < 0) ? err : 0;
+}
+
+static void drm_dp_cec_adap_status(struct cec_adapter *adap,
+				   struct seq_file *file)
+{
+	struct drm_dp_aux *aux = cec_get_drvdata(adap);
+	struct drm_dp_desc desc;
+	struct drm_dp_dpcd_ident *id = &desc.ident;
+
+	if (drm_dp_read_desc(aux, &desc, true))
+		return;
+	seq_printf(file, "OUI: %*pdH\n",
+		   (int)sizeof(id->oui), id->oui);
+	seq_printf(file, "ID: %*pE\n",
+		   (int)strnlen(id->device_id, sizeof(id->device_id)),
+		   id->device_id);
+	seq_printf(file, "HW Rev: %d.%d\n", id->hw_rev >> 4, id->hw_rev & 0xf);
+	/*
+	 * Show this both in decimal and hex: at least one vendor
+	 * always reports this in hex.
+	 */
+	seq_printf(file, "FW/SW Rev: %d.%d (0x%02x.0x%02x)\n",
+		   id->sw_major_rev, id->sw_minor_rev,
+		   id->sw_major_rev, id->sw_minor_rev);
+}
+
+static const struct cec_adap_ops drm_dp_cec_adap_ops = {
+	.adap_enable = drm_dp_cec_adap_enable,
+	.adap_log_addr = drm_dp_cec_adap_log_addr,
+	.adap_transmit = drm_dp_cec_adap_transmit,
+	.adap_monitor_all_enable = drm_dp_cec_adap_monitor_all_enable,
+	.adap_status = drm_dp_cec_adap_status,
+};
+
+static int drm_dp_cec_received(struct drm_dp_aux *aux)
+{
+	struct cec_adapter *adap = aux->cec.adap;
+	struct cec_msg msg;
+	u8 rx_msg_info;
+	ssize_t err;
+
+	err = drm_dp_dpcd_readb(aux, DP_CEC_RX_MESSAGE_INFO, &rx_msg_info);
+	if (err < 0)
+		return err;
+
+	if (!(rx_msg_info & DP_CEC_RX_MESSAGE_ENDED))
+		return 0;
+
+	msg.len = (rx_msg_info & DP_CEC_RX_MESSAGE_LEN_MASK) + 1;
+	err = drm_dp_dpcd_read(aux, DP_CEC_RX_MESSAGE_BUFFER, msg.msg, msg.len);
+	if (err < 0)
+		return err;
+
+	cec_received_msg(adap, &msg);
+	return 0;
+}
+
+static void drm_dp_cec_handle_irq(struct drm_dp_aux *aux)
+{
+	struct cec_adapter *adap = aux->cec.adap;
+	u8 flags;
+
+	if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, &flags) < 0)
+		return;
+
+	if (flags & DP_CEC_RX_MESSAGE_INFO_VALID)
+		drm_dp_cec_received(aux);
+
+	if (flags & DP_CEC_TX_MESSAGE_SENT)
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_OK);
+	else if (flags & DP_CEC_TX_LINE_ERROR)
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_ERROR |
+						CEC_TX_STATUS_MAX_RETRIES);
+	else if (flags &
+		 (DP_CEC_TX_ADDRESS_NACK_ERROR | DP_CEC_TX_DATA_NACK_ERROR))
+		cec_transmit_attempt_done(adap, CEC_TX_STATUS_NACK |
+						CEC_TX_STATUS_MAX_RETRIES);
+	drm_dp_dpcd_writeb(aux, DP_CEC_TUNNELING_IRQ_FLAGS, flags);
+}
+
+/**
+ * drm_dp_cec_irq() - handle CEC interrupt, if any
+ * @aux: DisplayPort AUX channel
+ *
+ * Should be called when handling an IRQ_HPD request. If CEC-tunneling-over-AUX
+ * is present, then it will check for a CEC_IRQ and handle it accordingly.
+ */
+void drm_dp_cec_irq(struct drm_dp_aux *aux)
+{
+	u8 cec_irq;
+	int ret;
+
+	mutex_lock(&aux->cec.lock);
+	if (!aux->cec.adap)
+		goto unlock;
+
+	ret = drm_dp_dpcd_readb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1,
+				&cec_irq);
+	if (ret < 0 || !(cec_irq & DP_CEC_IRQ))
+		goto unlock;
+
+	drm_dp_cec_handle_irq(aux);
+	drm_dp_dpcd_writeb(aux, DP_DEVICE_SERVICE_IRQ_VECTOR_ESI1, DP_CEC_IRQ);
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_irq);
+
+static bool drm_dp_cec_cap(struct drm_dp_aux *aux, u8 *cec_cap)
+{
+	u8 cap = 0;
+
+	if (drm_dp_dpcd_readb(aux, DP_CEC_TUNNELING_CAPABILITY, &cap) != 1 ||
+	    !(cap & DP_CEC_TUNNELING_CAPABLE))
+		return false;
+	if (cec_cap)
+		*cec_cap = cap;
+	return true;
+}
+
+/*
+ * Called if the HPD was low for more than drm_dp_cec_unregister_delay
+ * seconds. This unregisters the CEC adapter.
+ */
+static void drm_dp_cec_unregister_work(struct work_struct *work)
+{
+	struct drm_dp_aux *aux = container_of(work, struct drm_dp_aux,
+					      cec.unregister_work.work);
+
+	mutex_lock(&aux->cec.lock);
+	cec_unregister_adapter(aux->cec.adap);
+	aux->cec.adap = NULL;
+	mutex_unlock(&aux->cec.lock);
+}
+
+/*
+ * A new EDID is set. If there is no CEC adapter, then create one. If
+ * there was a CEC adapter, then check if the CEC adapter properties
+ * were unchanged and just update the CEC physical address. Otherwise
+ * unregister the old CEC adapter and create a new one.
+ */
+void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid)
+{
+	u32 cec_caps = CEC_CAP_DEFAULTS | CEC_CAP_NEEDS_HPD;
+	unsigned int num_las = 1;
+	u8 cap;
+
+#ifndef CONFIG_MEDIA_CEC_RC
+	/*
+	 * CEC_CAP_RC is part of CEC_CAP_DEFAULTS, but it is stripped by
+	 * cec_allocate_adapter() if CONFIG_MEDIA_CEC_RC is undefined.
+	 *
+	 * Do this here as well to ensure the tests against cec_caps are
+	 * correct.
+	 */
+	cec_caps &= ~CEC_CAP_RC;
+#endif
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+
+	mutex_lock(&aux->cec.lock);
+	if (!drm_dp_cec_cap(aux, &cap)) {
+		/* CEC is not supported, unregister any existing adapter */
+		cec_unregister_adapter(aux->cec.adap);
+		aux->cec.adap = NULL;
+		goto unlock;
+	}
+
+	if (cap & DP_CEC_SNOOPING_CAPABLE)
+		cec_caps |= CEC_CAP_MONITOR_ALL;
+	if (cap & DP_CEC_MULTIPLE_LA_CAPABLE)
+		num_las = CEC_MAX_LOG_ADDRS;
+
+	if (aux->cec.adap) {
+		if (aux->cec.adap->capabilities == cec_caps &&
+		    aux->cec.adap->available_log_addrs == num_las) {
+			/* Unchanged, so just set the phys addr */
+			cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+			goto unlock;
+		}
+		/*
+		 * The capabilities changed, so unregister the old
+		 * adapter first.
+		 */
+		cec_unregister_adapter(aux->cec.adap);
+	}
+
+	/* Create a new adapter */
+	aux->cec.adap = cec_allocate_adapter(&drm_dp_cec_adap_ops,
+					     aux, aux->cec.name, cec_caps,
+					     num_las);
+	if (IS_ERR(aux->cec.adap)) {
+		aux->cec.adap = NULL;
+		goto unlock;
+	}
+	if (cec_register_adapter(aux->cec.adap, aux->cec.parent)) {
+		cec_delete_adapter(aux->cec.adap);
+		aux->cec.adap = NULL;
+	} else {
+		/*
+		 * Update the phys addr for the new CEC adapter. When called
+		 * from drm_dp_cec_register_connector() edid == NULL, so in
+		 * that case the phys addr is just invalidated.
+		 */
+		cec_s_phys_addr_from_edid(aux->cec.adap, edid);
+	}
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_set_edid);
+
+/*
+ * The EDID disappeared (likely because of the HPD going down).
+ */
+void drm_dp_cec_unset_edid(struct drm_dp_aux *aux)
+{
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+
+	mutex_lock(&aux->cec.lock);
+	if (!aux->cec.adap)
+		goto unlock;
+
+	cec_phys_addr_invalidate(aux->cec.adap);
+	/*
+	 * We're done if we want to keep the CEC device
+	 * (drm_dp_cec_unregister_delay is >= NEVER_UNREG_DELAY) or if the
+	 * DPCD still indicates the CEC capability (expected for an integrated
+	 * HDMI branch device).
+	 */
+	if (drm_dp_cec_unregister_delay < NEVER_UNREG_DELAY &&
+	    !drm_dp_cec_cap(aux, NULL)) {
+		/*
+		 * Unregister the CEC adapter after drm_dp_cec_unregister_delay
+		 * seconds. This to debounce short HPD off-and-on cycles from
+		 * displays.
+		 */
+		schedule_delayed_work(&aux->cec.unregister_work,
+				      drm_dp_cec_unregister_delay * HZ);
+	}
+unlock:
+	mutex_unlock(&aux->cec.lock);
+}
+EXPORT_SYMBOL(drm_dp_cec_unset_edid);
+
+/**
+ * drm_dp_cec_register_connector() - register a new connector
+ * @aux: DisplayPort AUX channel
+ * @name: name of the CEC device
+ * @parent: parent device
+ *
+ * A new connector was registered with associated CEC adapter name and
+ * CEC adapter parent device. After registering the name and parent
+ * drm_dp_cec_set_edid() is called to check if the connector supports
+ * CEC and to register a CEC adapter if that is the case.
+ */
+void drm_dp_cec_register_connector(struct drm_dp_aux *aux, const char *name,
+				   struct device *parent)
+{
+	WARN_ON(aux->cec.adap);
+	aux->cec.name = name;
+	aux->cec.parent = parent;
+	INIT_DELAYED_WORK(&aux->cec.unregister_work,
+			  drm_dp_cec_unregister_work);
+
+	drm_dp_cec_set_edid(aux, NULL);
+}
+EXPORT_SYMBOL(drm_dp_cec_register_connector);
+
+/**
+ * drm_dp_cec_unregister_connector() - unregister the CEC adapter, if any
+ * @aux: DisplayPort AUX channel
+ */
+void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux)
+{
+	if (!aux->cec.adap)
+		return;
+	cancel_delayed_work_sync(&aux->cec.unregister_work);
+	cec_unregister_adapter(aux->cec.adap);
+	aux->cec.adap = NULL;
+}
+EXPORT_SYMBOL(drm_dp_cec_unregister_connector);
diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index a7ba602a43a8..f4a06b54aa7d 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -1087,6 +1087,7 @@ static void drm_dp_aux_crc_work(struct work_struct *work)
 void drm_dp_aux_init(struct drm_dp_aux *aux)
 {
 	mutex_init(&aux->hw_mutex);
+	mutex_init(&aux->cec.lock);
 	INIT_WORK(&aux->crc_work, drm_dp_aux_crc_work);
 
 	aux->ddc.algo = &drm_dp_i2c_algo;
diff --git a/include/drm/drm_dp_helper.h b/include/drm/drm_dp_helper.h
index c01564991a9f..05cc31b5db16 100644
--- a/include/drm/drm_dp_helper.h
+++ b/include/drm/drm_dp_helper.h
@@ -1078,6 +1078,25 @@ struct drm_dp_aux_msg {
 	size_t size;
 };
 
+struct cec_adapter;
+struct edid;
+
+/**
+ * struct drm_dp_aux_cec - DisplayPort CEC-Tunneling-over-AUX
+ * @lock: mutex protecting this struct
+ * @adap: the CEC adapter for CEC-Tunneling-over-AUX support.
+ * @name: name of the CEC adapter
+ * @parent: parent device of the CEC adapter
+ * @unregister_work: unregister the CEC adapter
+ */
+struct drm_dp_aux_cec {
+	struct mutex lock;
+	struct cec_adapter *adap;
+	const char *name;
+	struct device *parent;
+	struct delayed_work unregister_work;
+};
+
 /**
  * struct drm_dp_aux - DisplayPort AUX channel
  * @name: user-visible name of this AUX channel and the I2C-over-AUX adapter
@@ -1136,6 +1155,10 @@ struct drm_dp_aux {
 	 * @i2c_defer_count: Counts I2C DEFERs, used for DP validation.
 	 */
 	unsigned i2c_defer_count;
+	/**
+	 * @cec: struct containing fields used for CEC-Tunneling-over-AUX.
+	 */
+	struct drm_dp_aux_cec cec;
 };
 
 ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
@@ -1258,4 +1281,37 @@ drm_dp_has_quirk(const struct drm_dp_desc *desc, enum drm_dp_quirk quirk)
 	return desc->quirks & BIT(quirk);
 }
 
+#ifdef CONFIG_DRM_DP_CEC
+void drm_dp_cec_irq(struct drm_dp_aux *aux);
+void drm_dp_cec_register_connector(struct drm_dp_aux *aux, const char *name,
+				   struct device *parent);
+void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux);
+void drm_dp_cec_set_edid(struct drm_dp_aux *aux, const struct edid *edid);
+void drm_dp_cec_unset_edid(struct drm_dp_aux *aux);
+#else
+static inline void drm_dp_cec_irq(struct drm_dp_aux *aux)
+{
+}
+
+static inline void drm_dp_cec_register_connector(struct drm_dp_aux *aux,
+						 const char *name,
+						 struct device *parent)
+{
+}
+
+static inline void drm_dp_cec_unregister_connector(struct drm_dp_aux *aux)
+{
+}
+
+static inline void drm_dp_cec_set_edid(struct drm_dp_aux *aux,
+				       const struct edid *edid)
+{
+}
+
+static inline void drm_dp_cec_unset_edid(struct drm_dp_aux *aux)
+{
+}
+
+#endif
+
 #endif /* _DRM_DP_HELPER_H_ */
-- 
cgit v1.2.3


From d2e2d265211cdb423406dd693c8f6fa4ca62674f Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Wed, 11 Jul 2018 15:29:08 +0200
Subject: drm-kms-helpers.rst: document the DP CEC helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Document the Display Port CEC helper functions.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711132909.25409-3-hverkuil@xs4all.nl
---
 Documentation/gpu/drm-kms-helpers.rst | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst
index e37557b30f62..62de583e9efe 100644
--- a/Documentation/gpu/drm-kms-helpers.rst
+++ b/Documentation/gpu/drm-kms-helpers.rst
@@ -169,6 +169,15 @@ Display Port Helper Functions Reference
 .. kernel-doc:: drivers/gpu/drm/drm_dp_helper.c
    :export:
 
+Display Port CEC Helper Functions Reference
+===========================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_cec.c
+   :doc: dp cec helpers
+
+.. kernel-doc:: drivers/gpu/drm/drm_dp_cec.c
+   :export:
+
 Display Port Dual Mode Adaptor Helper Functions Reference
 =========================================================
 
-- 
cgit v1.2.3


From 82e00d113639ac810568060b060462e0a7583c9d Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Wed, 11 Jul 2018 15:29:09 +0200
Subject: drm/i915: add DisplayPort CEC-Tunneling-over-AUX support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement support for this DisplayPort feature.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180711132909.25409-4-hverkuil@xs4all.nl
---
 drivers/gpu/drm/i915/intel_dp.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 6ac6c8787dcf..b021801dbd48 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -4495,6 +4495,9 @@ intel_dp_short_pulse(struct intel_dp *intel_dp)
 			DRM_DEBUG_DRIVER("CP or sink specific irq unhandled\n");
 	}
 
+	/* Handle CEC interrupts, if any */
+	drm_dp_cec_irq(&intel_dp->aux);
+
 	/* defer to the hotplug work for link retraining if needed */
 	if (intel_dp_needs_link_retrain(intel_dp))
 		return false;
@@ -4809,6 +4812,7 @@ intel_dp_set_edid(struct intel_dp *intel_dp)
 	intel_connector->detect_edid = edid;
 
 	intel_dp->has_audio = drm_detect_monitor_audio(edid);
+	drm_dp_cec_set_edid(&intel_dp->aux, edid);
 }
 
 static void
@@ -4816,6 +4820,7 @@ intel_dp_unset_edid(struct intel_dp *intel_dp)
 {
 	struct intel_connector *intel_connector = intel_dp->attached_connector;
 
+	drm_dp_cec_unset_edid(&intel_dp->aux);
 	kfree(intel_connector->detect_edid);
 	intel_connector->detect_edid = NULL;
 
@@ -5004,6 +5009,7 @@ static int
 intel_dp_connector_register(struct drm_connector *connector)
 {
 	struct intel_dp *intel_dp = intel_attached_dp(connector);
+	struct drm_device *dev = connector->dev;
 	int ret;
 
 	ret = intel_connector_register(connector);
@@ -5016,13 +5022,20 @@ intel_dp_connector_register(struct drm_connector *connector)
 		      intel_dp->aux.name, connector->kdev->kobj.name);
 
 	intel_dp->aux.dev = connector->kdev;
-	return drm_dp_aux_register(&intel_dp->aux);
+	ret = drm_dp_aux_register(&intel_dp->aux);
+	if (!ret)
+		drm_dp_cec_register_connector(&intel_dp->aux,
+					      connector->name, dev->dev);
+	return ret;
 }
 
 static void
 intel_dp_connector_unregister(struct drm_connector *connector)
 {
-	drm_dp_aux_unregister(&intel_attached_dp(connector)->aux);
+	struct intel_dp *intel_dp = intel_attached_dp(connector);
+
+	drm_dp_cec_unregister_connector(&intel_dp->aux);
+	drm_dp_aux_unregister(&intel_dp->aux);
 	intel_connector_unregister(connector);
 }
 
-- 
cgit v1.2.3


From 4dd4677c2d3d34a2bcd511c088da4535ea58e360 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 28 Jun 2018 16:54:55 +0300
Subject: drm: Extract __setplane_check()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pull all the error checking out from __set_plane_internal() to a helper
function. We'll have another user of this soon.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628135457.14647-1-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
---
 drivers/gpu/drm/drm_plane.c | 80 +++++++++++++++++++++++++++------------------
 1 file changed, 49 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index df0b4ebbedbf..5c97a0131484 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -583,6 +583,52 @@ int drm_plane_check_pixel_format(struct drm_plane *plane,
 	return 0;
 }
 
+static int __setplane_check(struct drm_plane *plane,
+			    struct drm_crtc *crtc,
+			    struct drm_framebuffer *fb,
+			    int32_t crtc_x, int32_t crtc_y,
+			    uint32_t crtc_w, uint32_t crtc_h,
+			    uint32_t src_x, uint32_t src_y,
+			    uint32_t src_w, uint32_t src_h)
+{
+	int ret;
+
+	/* Check whether this plane is usable on this CRTC */
+	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
+		DRM_DEBUG_KMS("Invalid crtc for plane\n");
+		return -EINVAL;
+	}
+
+	/* Check whether this plane supports the fb pixel format. */
+	ret = drm_plane_check_pixel_format(plane, fb->format->format,
+					   fb->modifier);
+	if (ret) {
+		struct drm_format_name_buf format_name;
+
+		DRM_DEBUG_KMS("Invalid pixel format %s, modifier 0x%llx\n",
+			      drm_get_format_name(fb->format->format,
+						  &format_name),
+			      fb->modifier);
+		return ret;
+	}
+
+	/* Give drivers some help against integer overflows */
+	if (crtc_w > INT_MAX ||
+	    crtc_x > INT_MAX - (int32_t) crtc_w ||
+	    crtc_h > INT_MAX ||
+	    crtc_y > INT_MAX - (int32_t) crtc_h) {
+		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
+			      crtc_w, crtc_h, crtc_x, crtc_y);
+		return -ERANGE;
+	}
+
+	ret = drm_framebuffer_check_src_coords(src_x, src_y, src_w, src_h, fb);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 /*
  * __setplane_internal - setplane handler for internal callers
  *
@@ -616,37 +662,9 @@ static int __setplane_internal(struct drm_plane *plane,
 		goto out;
 	}
 
-	/* Check whether this plane is usable on this CRTC */
-	if (!(plane->possible_crtcs & drm_crtc_mask(crtc))) {
-		DRM_DEBUG_KMS("Invalid crtc for plane\n");
-		ret = -EINVAL;
-		goto out;
-	}
-
-	/* Check whether this plane supports the fb pixel format. */
-	ret = drm_plane_check_pixel_format(plane, fb->format->format,
-					   fb->modifier);
-	if (ret) {
-		struct drm_format_name_buf format_name;
-		DRM_DEBUG_KMS("Invalid pixel format %s, modifier 0x%llx\n",
-			      drm_get_format_name(fb->format->format,
-						  &format_name),
-			      fb->modifier);
-		goto out;
-	}
-
-	/* Give drivers some help against integer overflows */
-	if (crtc_w > INT_MAX ||
-	    crtc_x > INT_MAX - (int32_t) crtc_w ||
-	    crtc_h > INT_MAX ||
-	    crtc_y > INT_MAX - (int32_t) crtc_h) {
-		DRM_DEBUG_KMS("Invalid CRTC coordinates %ux%u+%d+%d\n",
-			      crtc_w, crtc_h, crtc_x, crtc_y);
-		ret = -ERANGE;
-		goto out;
-	}
-
-	ret = drm_framebuffer_check_src_coords(src_x, src_y, src_w, src_h, fb);
+	ret = __setplane_check(plane, crtc, fb,
+			       crtc_x, crtc_y, crtc_w, crtc_h,
+			       src_x, src_y, src_w, src_h);
 	if (ret)
 		goto out;
 
-- 
cgit v1.2.3


From e7695eb6ea70ed143fafbcd12ce69886be3aa03d Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 21:59:07 +0300
Subject: drm: Introduce __setplane_atomic()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All the plane->fb/old_fb/crtc dance of __setplane_internal() is
pointless on atomic drivers. So let's just introduce a simpler
version that skips all that.

Ideally we could also skip the __setplane_check() as
drm_atomic_plane_check() already checks for everything, but the
legacy cursor/"async" .update_plane() tricks bypass that so
we still need to call __setplane_check(). Toss in a FIXME to
remind someone to clean this up later.

v2: Use drm_drv_uses_atomic_modeset() (Daniel)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705185907.9524-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/drm_plane.c | 68 +++++++++++++++++++++++++++++++++++++--------
 1 file changed, 57 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/drm_plane.c b/drivers/gpu/drm/drm_plane.c
index 5c97a0131484..6153cbda239f 100644
--- a/drivers/gpu/drm/drm_plane.c
+++ b/drivers/gpu/drm/drm_plane.c
@@ -649,6 +649,8 @@ static int __setplane_internal(struct drm_plane *plane,
 {
 	int ret = 0;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(plane->dev));
+
 	/* No fb means shut it down */
 	if (!fb) {
 		plane->old_fb = plane->fb;
@@ -673,11 +675,9 @@ static int __setplane_internal(struct drm_plane *plane,
 					 crtc_x, crtc_y, crtc_w, crtc_h,
 					 src_x, src_y, src_w, src_h, ctx);
 	if (!ret) {
-		if (!plane->state) {
-			plane->crtc = crtc;
-			plane->fb = fb;
-			drm_framebuffer_get(plane->fb);
-		}
+		plane->crtc = crtc;
+		plane->fb = fb;
+		drm_framebuffer_get(plane->fb);
 	} else {
 		plane->old_fb = NULL;
 	}
@@ -690,6 +690,41 @@ out:
 	return ret;
 }
 
+static int __setplane_atomic(struct drm_plane *plane,
+			     struct drm_crtc *crtc,
+			     struct drm_framebuffer *fb,
+			     int32_t crtc_x, int32_t crtc_y,
+			     uint32_t crtc_w, uint32_t crtc_h,
+			     uint32_t src_x, uint32_t src_y,
+			     uint32_t src_w, uint32_t src_h,
+			     struct drm_modeset_acquire_ctx *ctx)
+{
+	int ret;
+
+	WARN_ON(!drm_drv_uses_atomic_modeset(plane->dev));
+
+	/* No fb means shut it down */
+	if (!fb)
+		return plane->funcs->disable_plane(plane, ctx);
+
+	/*
+	 * FIXME: This is redundant with drm_atomic_plane_check(),
+	 * but the legacy cursor/"async" .update_plane() tricks
+	 * don't call that so we still need this here. Should remove
+	 * this when all .update_plane() implementations have been
+	 * fixed to call drm_atomic_plane_check().
+	 */
+	ret = __setplane_check(plane, crtc, fb,
+			       crtc_x, crtc_y, crtc_w, crtc_h,
+			       src_x, src_y, src_w, src_h);
+	if (ret)
+		return ret;
+
+	return plane->funcs->update_plane(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  src_x, src_y, src_w, src_h, ctx);
+}
+
 static int setplane_internal(struct drm_plane *plane,
 			     struct drm_crtc *crtc,
 			     struct drm_framebuffer *fb,
@@ -707,9 +742,15 @@ retry:
 	ret = drm_modeset_lock_all_ctx(plane->dev, &ctx);
 	if (ret)
 		goto fail;
-	ret = __setplane_internal(plane, crtc, fb,
-				  crtc_x, crtc_y, crtc_w, crtc_h,
-				  src_x, src_y, src_w, src_h, &ctx);
+
+	if (drm_drv_uses_atomic_modeset(plane->dev))
+		ret = __setplane_atomic(plane, crtc, fb,
+					crtc_x, crtc_y, crtc_w, crtc_h,
+					src_x, src_y, src_w, src_h, &ctx);
+	else
+		ret = __setplane_internal(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  src_x, src_y, src_w, src_h, &ctx);
 
 fail:
 	if (ret == -EDEADLK) {
@@ -841,9 +882,14 @@ static int drm_mode_cursor_universal(struct drm_crtc *crtc,
 		src_h = fb->height << 16;
 	}
 
-	ret = __setplane_internal(plane, crtc, fb,
-				  crtc_x, crtc_y, crtc_w, crtc_h,
-				  0, 0, src_w, src_h, ctx);
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = __setplane_atomic(plane, crtc, fb,
+					crtc_x, crtc_y, crtc_w, crtc_h,
+					0, 0, src_w, src_h, ctx);
+	else
+		ret = __setplane_internal(plane, crtc, fb,
+					  crtc_x, crtc_y, crtc_w, crtc_h,
+					  0, 0, src_w, src_h, ctx);
 
 	if (fb)
 		drm_framebuffer_put(fb);
-- 
cgit v1.2.3


From 69a8a1961c7bf59b70ec958f8a408ba448fe62a9 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 22:00:10 +0300
Subject: drm: Skip __drm_mode_set_config_internal() on atomic drivers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Everything (apart from the actual ->set_config() call)
__drm_mode_set_config_internal() does is now useless on
atomic drivers. So let's just skip all the foreplay.

v2: Use drm_drv_uses_atomic_modeset() (Daniel)

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705190010.19836-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/drm_crtc.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/drm_crtc.c b/drivers/gpu/drm/drm_crtc.c
index a6906c4ab880..bae43938c8f6 100644
--- a/drivers/gpu/drm/drm_crtc.c
+++ b/drivers/gpu/drm/drm_crtc.c
@@ -461,6 +461,8 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 	struct drm_crtc *tmp;
 	int ret;
 
+	WARN_ON(drm_drv_uses_atomic_modeset(crtc->dev));
+
 	/*
 	 * NOTE: ->set_config can also disable other crtcs (if we steal all
 	 * connectors from it), hence we need to refcount the fbs across all
@@ -478,10 +480,8 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 	if (ret == 0) {
 		struct drm_plane *plane = crtc->primary;
 
-		if (!plane->state) {
-			plane->crtc = fb ? crtc : NULL;
-			plane->fb = fb;
-		}
+		plane->crtc = fb ? crtc : NULL;
+		plane->fb = fb;
 	}
 
 	drm_for_each_crtc(tmp, crtc->dev) {
@@ -496,6 +496,7 @@ static int __drm_mode_set_config_internal(struct drm_mode_set *set,
 
 	return ret;
 }
+
 /**
  * drm_mode_set_config_internal - helper to call &drm_mode_config_funcs.set_config
  * @set: modeset config to set
@@ -740,7 +741,11 @@ retry:
 	set.connectors = connector_set;
 	set.num_connectors = crtc_req->count_connectors;
 	set.fb = fb;
-	ret = __drm_mode_set_config_internal(&set, &ctx);
+
+	if (drm_drv_uses_atomic_modeset(dev))
+		ret = crtc->funcs->set_config(&set, &ctx);
+	else
+		ret = __drm_mode_set_config_internal(&set, &ctx);
 
 out:
 	if (fb)
-- 
cgit v1.2.3


From d5418ae3f9443f911d4324c0cade988ced39cfbe Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Fri, 13 Jul 2018 14:50:42 +0200
Subject: ASoC: add DT documentation for the sound-name-prefix property

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/name-prefix.txt      | 24 ++++++++++++++++++++++
 1 file changed, 24 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/name-prefix.txt

diff --git a/Documentation/devicetree/bindings/sound/name-prefix.txt b/Documentation/devicetree/bindings/sound/name-prefix.txt
new file mode 100644
index 000000000000..645775908657
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/name-prefix.txt
@@ -0,0 +1,24 @@
+Name prefix:
+
+Card implementing the routing property define the connection between
+audio components as list of string pair. Component using the same
+sink/source names may use the name prefix property to prepend the
+name of their sinks/sources with the provided string.
+
+Optional name prefix property:
+- sound-name-prefix : string using as prefix for the sink/source names of
+		      the component.
+
+Example: Two instances of the same component.
+
+amp0: analog-amplifier@0 {
+	compatible = "simple-audio-amplifier";
+	enable-gpios = <&gpio GPIOH_3 0>;
+	sound-name-prefix = "FRONT";
+};
+
+amp1: analog-amplifier@1 {
+	compatible = "simple-audio-amplifier";
+	enable-gpios = <&gpio GPIOH_4 0>;
+	sound-name-prefix = "BACK";
+};
-- 
cgit v1.2.3


From aefba45539bc4868c1fae336410aec907ee0882a Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Fri, 13 Jul 2018 14:50:43 +0200
Subject: ASoC: allow soc-core to pick up name prefixes from component nodes

When the component does not match the configuration table provided
by the card, let soc-core check the component node for a name prefix

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 00bd58d167dd..3be0310d5c81 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -1193,15 +1193,27 @@ void snd_soc_remove_dai_link(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(snd_soc_remove_dai_link);
 
+static void soc_set_of_name_prefix(struct snd_soc_component *component)
+{
+	struct device_node *component_of_node = component->dev->of_node;
+	const char *str;
+	int ret;
+
+	if (!component_of_node && component->dev->parent)
+		component_of_node = component->dev->parent->of_node;
+
+	ret = of_property_read_string(component_of_node, "sound-name-prefix",
+				      &str);
+	if (!ret)
+		component->name_prefix = str;
+}
+
 static void soc_set_name_prefix(struct snd_soc_card *card,
 				struct snd_soc_component *component)
 {
 	int i;
 
-	if (card->codec_conf == NULL)
-		return;
-
-	for (i = 0; i < card->num_configs; i++) {
+	for (i = 0; i < card->num_configs && card->codec_conf; i++) {
 		struct snd_soc_codec_conf *map = &card->codec_conf[i];
 		struct device_node *component_of_node = component->dev->of_node;
 
@@ -1213,8 +1225,14 @@ static void soc_set_name_prefix(struct snd_soc_card *card,
 		if (map->dev_name && strcmp(component->name, map->dev_name))
 			continue;
 		component->name_prefix = map->name_prefix;
-		break;
+		return;
 	}
+
+	/*
+	 * If there is no configuration table or no match in the table,
+	 * check if a prefix is provided in the node
+	 */
+	soc_set_of_name_prefix(component);
 }
 
 static int soc_probe_component(struct snd_soc_card *card,
-- 
cgit v1.2.3


From 39fbb88165b2bbbc77ea7acab5f10632a31526e6 Mon Sep 17 00:00:00 2001
From: Sean Young <sean@mess.org>
Date: Wed, 4 Jul 2018 10:57:58 -0400
Subject: media: bpf: ensure bpf program is freed on detach

Currently we are leaking bpf programs when they are detached from the
lirc device; the refcount never reaches zero.

Signed-off-by: Sean Young <sean@mess.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/rc/bpf-lirc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index 40826bba06b6..55400317ec53 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -174,6 +174,7 @@ static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog)
 
 	rcu_assign_pointer(raw->progs, new_array);
 	bpf_prog_array_free(old_array);
+	bpf_prog_put(prog);
 unlock:
 	mutex_unlock(&ir_raw_handler_lock);
 	return ret;
-- 
cgit v1.2.3


From 25dda4dabeeb12af5209b0183c788ef2a88dabbe Mon Sep 17 00:00:00 2001
From: Jon Bloomfield <jon.bloomfield@intel.com>
Date: Thu, 12 Jul 2018 19:53:10 +0100
Subject: drm/i915/gtt: Add read only pages to gen8_pte_encode

We can set a bit inside the ppGTT PTE to indicate a page is read-only;
writes from the GPU will be discarded. We can use this to protect pages
and in particular support read-only userptr mappings (necessary for
importing PROT_READ vma).

Signed-off-by: Jon Bloomfield <jon.bloomfield@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 25 ++++++++++++++-----------
 1 file changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 502353b9bf84..b74f1ed03bae 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -244,10 +244,13 @@ static void clear_pages(struct i915_vma *vma)
 }
 
 static gen8_pte_t gen8_pte_encode(dma_addr_t addr,
-				  enum i915_cache_level level)
+				  enum i915_cache_level level,
+				  u32 flags)
 {
-	gen8_pte_t pte = _PAGE_PRESENT | _PAGE_RW;
-	pte |= addr;
+	gen8_pte_t pte = addr | _PAGE_PRESENT | _PAGE_RW;
+
+	if (unlikely(flags & PTE_READ_ONLY))
+		pte &= ~_PAGE_RW;
 
 	switch (level) {
 	case I915_CACHE_NONE:
@@ -721,7 +724,7 @@ static void gen8_initialize_pt(struct i915_address_space *vm,
 			       struct i915_page_table *pt)
 {
 	fill_px(vm, pt,
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC));
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0));
 }
 
 static void gen6_initialize_pt(struct gen6_hw_ppgtt *ppgtt,
@@ -869,7 +872,7 @@ static bool gen8_ppgtt_clear_pt(struct i915_address_space *vm,
 	unsigned int pte = gen8_pte_index(start);
 	unsigned int pte_end = pte + num_entries;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	gen8_pte_t *vaddr;
 
 	GEM_BUG_ON(num_entries > pt->used_ptes);
@@ -1044,7 +1047,7 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 			      enum i915_cache_level cache_level)
 {
 	struct i915_page_directory *pd;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, 0);
 	gen8_pte_t *vaddr;
 	bool ret;
 
@@ -1112,7 +1115,7 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 					   struct sgt_dma *iter,
 					   enum i915_cache_level cache_level)
 {
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, 0);
 	u64 start = vma->node.start;
 	dma_addr_t rem = iter->sg->length;
 
@@ -1578,7 +1581,7 @@ static void gen8_dump_ppgtt(struct i915_hw_ppgtt *ppgtt, struct seq_file *m)
 {
 	struct i915_address_space *vm = &ppgtt->vm;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	u64 start = 0, length = ppgtt->vm.total;
 
 	if (use_4lvl(vm)) {
@@ -2461,7 +2464,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 	gen8_pte_t __iomem *pte =
 		(gen8_pte_t __iomem *)ggtt->gsm + (offset >> PAGE_SHIFT);
 
-	gen8_set_pte(pte, gen8_pte_encode(addr, level));
+	gen8_set_pte(pte, gen8_pte_encode(addr, level, 0));
 
 	ggtt->invalidate(vm->i915);
 }
@@ -2474,7 +2477,7 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	struct sgt_iter sgt_iter;
 	gen8_pte_t __iomem *gtt_entries;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, level);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
 	dma_addr_t addr;
 
 	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
@@ -2542,7 +2545,7 @@ static void gen8_ggtt_clear_range(struct i915_address_space *vm,
 	unsigned first_entry = start >> PAGE_SHIFT;
 	unsigned num_entries = length >> PAGE_SHIFT;
 	const gen8_pte_t scratch_pte =
-		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC);
+		gen8_pte_encode(vm->scratch_page.daddr, I915_CACHE_LLC, 0);
 	gen8_pte_t __iomem *gtt_base =
 		(gen8_pte_t __iomem *)ggtt->gsm + first_entry;
 	const int max_entries = ggtt_total_entries(ggtt) - first_entry;
-- 
cgit v1.2.3


From 250f8c8140ac0a5e5acb91891d6813f12778b224 Mon Sep 17 00:00:00 2001
From: Jon Bloomfield <jon.bloomfield@intel.com>
Date: Thu, 12 Jul 2018 19:53:11 +0100
Subject: drm/i915/gtt: Read-only pages for insert_entries on bdw+

Hook up the flags to allow read-only ppGTT mappings for gen8+

v2: Include a selftest to check that writes to a readonly PTE are
dropped
v3: Don't duplicate cpu_check() as we can just reuse it, and even worse
don't wholesale copy the theory-of-operation comment from igt_ctx_exec
without changing it to explain the intention behind the new test!
v4: Joonas really likes magic mystery values

Signed-off-by: Jon Bloomfield <jon.bloomfield@intel.com>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c               |  45 ++++++---
 drivers/gpu/drm/i915/i915_gem_gtt.h               |   7 +-
 drivers/gpu/drm/i915/intel_ringbuffer.c           |  11 ++-
 drivers/gpu/drm/i915/selftests/i915_gem_context.c | 112 +++++++++++++++++++++-
 4 files changed, 153 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index b74f1ed03bae..734b67f7853c 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -204,7 +204,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 			return err;
 	}
 
-	/* Currently applicable only to VLV */
+	/* Applicable to VLV, and gen8+ */
 	pte_flags = 0;
 	if (vma->obj->gt_ro)
 		pte_flags |= PTE_READ_ONLY;
@@ -1044,10 +1044,11 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 			      struct i915_page_directory_pointer *pdp,
 			      struct sgt_dma *iter,
 			      struct gen8_insert_pte *idx,
-			      enum i915_cache_level cache_level)
+			      enum i915_cache_level cache_level,
+			      u32 flags)
 {
 	struct i915_page_directory *pd;
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, 0);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
 	gen8_pte_t *vaddr;
 	bool ret;
 
@@ -1098,14 +1099,14 @@ gen8_ppgtt_insert_pte_entries(struct i915_hw_ppgtt *ppgtt,
 static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
 				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
-				   u32 unused)
+				   u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = sgt_dma(vma);
 	struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 	gen8_ppgtt_insert_pte_entries(ppgtt, &ppgtt->pdp, &iter, &idx,
-				      cache_level);
+				      cache_level, flags);
 
 	vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
 }
@@ -1113,9 +1114,10 @@ static void gen8_ppgtt_insert_3lvl(struct i915_address_space *vm,
 static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 					   struct i915_page_directory_pointer **pdps,
 					   struct sgt_dma *iter,
-					   enum i915_cache_level cache_level)
+					   enum i915_cache_level cache_level,
+					   u32 flags)
 {
-	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, 0);
+	const gen8_pte_t pte_encode = gen8_pte_encode(0, cache_level, flags);
 	u64 start = vma->node.start;
 	dma_addr_t rem = iter->sg->length;
 
@@ -1231,19 +1233,21 @@ static void gen8_ppgtt_insert_huge_entries(struct i915_vma *vma,
 static void gen8_ppgtt_insert_4lvl(struct i915_address_space *vm,
 				   struct i915_vma *vma,
 				   enum i915_cache_level cache_level,
-				   u32 unused)
+				   u32 flags)
 {
 	struct i915_hw_ppgtt *ppgtt = i915_vm_to_ppgtt(vm);
 	struct sgt_dma iter = sgt_dma(vma);
 	struct i915_page_directory_pointer **pdps = ppgtt->pml4.pdps;
 
 	if (vma->page_sizes.sg > I915_GTT_PAGE_SIZE) {
-		gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level);
+		gen8_ppgtt_insert_huge_entries(vma, pdps, &iter, cache_level,
+					       flags);
 	} else {
 		struct gen8_insert_pte idx = gen8_insert_pte(vma->node.start);
 
 		while (gen8_ppgtt_insert_pte_entries(ppgtt, pdps[idx.pml4e++],
-						     &iter, &idx, cache_level))
+						     &iter, &idx, cache_level,
+						     flags))
 			GEM_BUG_ON(idx.pml4e >= GEN8_PML4ES_PER_PML4);
 
 		vma->page_sizes.gtt = I915_GTT_PAGE_SIZE;
@@ -1658,6 +1662,9 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 		1ULL << 48 :
 		1ULL << 32;
 
+	/* From bdw, there is support for read-only pages in the PPGTT */
+	ppgtt->vm.has_read_only = true;
+
 	i915_address_space_init(&ppgtt->vm, i915);
 
 	/* There are only few exceptions for gen >=6. chv and bxt.
@@ -2472,7 +2479,7 @@ static void gen8_ggtt_insert_page(struct i915_address_space *vm,
 static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 				     struct i915_vma *vma,
 				     enum i915_cache_level level,
-				     u32 unused)
+				     u32 flags)
 {
 	struct i915_ggtt *ggtt = i915_vm_to_ggtt(vm);
 	struct sgt_iter sgt_iter;
@@ -2480,6 +2487,9 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
 	dma_addr_t addr;
 
+	/* The GTT does not support read-only mappings */
+	GEM_BUG_ON(flags & PTE_READ_ONLY);
+
 	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
 	gtt_entries += vma->node.start >> PAGE_SHIFT;
 	for_each_sgt_dma(addr, sgt_iter, vma->pages)
@@ -2606,13 +2616,14 @@ struct insert_entries {
 	struct i915_address_space *vm;
 	struct i915_vma *vma;
 	enum i915_cache_level level;
+	u32 flags;
 };
 
 static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 {
 	struct insert_entries *arg = _arg;
 
-	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, 0);
+	gen8_ggtt_insert_entries(arg->vm, arg->vma, arg->level, arg->flags);
 	bxt_vtd_ggtt_wa(arg->vm);
 
 	return 0;
@@ -2621,9 +2632,9 @@ static int bxt_vtd_ggtt_insert_entries__cb(void *_arg)
 static void bxt_vtd_ggtt_insert_entries__BKL(struct i915_address_space *vm,
 					     struct i915_vma *vma,
 					     enum i915_cache_level level,
-					     u32 unused)
+					     u32 flags)
 {
-	struct insert_entries arg = { vm, vma, level };
+	struct insert_entries arg = { vm, vma, level, flags };
 
 	stop_machine(bxt_vtd_ggtt_insert_entries__cb, &arg, NULL);
 }
@@ -2714,7 +2725,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 	struct drm_i915_gem_object *obj = vma->obj;
 	u32 pte_flags;
 
-	/* Currently applicable only to VLV */
+	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
 	pte_flags = 0;
 	if (obj->gt_ro)
 		pte_flags |= PTE_READ_ONLY;
@@ -3594,6 +3605,10 @@ int i915_ggtt_init_hw(struct drm_i915_private *dev_priv)
 	 */
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	i915_address_space_init(&ggtt->vm, dev_priv);
+
+	/* Only VLV supports read-only GGTT mappings */
+	ggtt->vm.has_read_only = IS_VALLEYVIEW(dev_priv);
+
 	if (!HAS_LLC(dev_priv) && !USES_PPGTT(dev_priv))
 		ggtt->vm.mm.color_adjust = i915_gtt_color_adjust;
 	mutex_unlock(&dev_priv->drm.struct_mutex);
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.h b/drivers/gpu/drm/i915/i915_gem_gtt.h
index 14e62651010b..2a116a91420b 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.h
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.h
@@ -331,7 +331,12 @@ struct i915_address_space {
 	struct list_head unbound_list;
 
 	struct pagestash free_pages;
-	bool pt_kmap_wc;
+
+	/* Some systems require uncached updates of the page directories */
+	bool pt_kmap_wc:1;
+
+	/* Some systems support read-only mappings for GGTT and/or PPGTT */
+	bool has_read_only:1;
 
 	/* FIXME: Need a more generic return type */
 	gen6_pte_t (*pte_encode)(dma_addr_t addr,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index fab83e3c1502..6de88add508a 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1085,6 +1085,7 @@ void intel_ring_unpin(struct intel_ring *ring)
 static struct i915_vma *
 intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 {
+	struct i915_address_space *vm = &dev_priv->ggtt.vm;
 	struct drm_i915_gem_object *obj;
 	struct i915_vma *vma;
 
@@ -1094,10 +1095,14 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 	if (IS_ERR(obj))
 		return ERR_CAST(obj);
 
-	/* mark ring buffers as read-only from GPU side by default */
-	obj->gt_ro = 1;
+	/*
+	 * Mark ring buffers as read-only from GPU side (so no stray overwrites)
+	 * if supported by the platform's GGTT.
+	 */
+	if (vm->has_read_only)
+		obj->gt_ro = 1;
 
-	vma = i915_vma_instance(obj, &dev_priv->ggtt.vm, NULL);
+	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma))
 		goto err;
 
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index ab2590242033..2e2a3c44b8e9 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -23,6 +23,7 @@
  */
 
 #include "../i915_selftest.h"
+#include "i915_random.h"
 #include "igt_flush_test.h"
 
 #include "mock_drm.h"
@@ -252,9 +253,9 @@ static int cpu_check(struct drm_i915_gem_object *obj, unsigned int max)
 		}
 
 		for (; m < DW_PER_PAGE; m++) {
-			if (map[m] != 0xdeadbeef) {
+			if (map[m] != STACK_MAGIC) {
 				pr_err("Invalid value at page %d, offset %d: found %x expected %x\n",
-				       n, m, map[m], 0xdeadbeef);
+				       n, m, map[m], STACK_MAGIC);
 				err = -EINVAL;
 				goto out_unmap;
 			}
@@ -310,7 +311,7 @@ create_test_object(struct i915_gem_context *ctx,
 	if (err)
 		return ERR_PTR(err);
 
-	err = cpu_fill(obj, 0xdeadbeef);
+	err = cpu_fill(obj, STACK_MAGIC);
 	if (err) {
 		pr_err("Failed to fill object with cpu, err=%d\n",
 		       err);
@@ -432,6 +433,110 @@ out_unlock:
 	return err;
 }
 
+static int igt_ctx_readonly(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct drm_i915_gem_object *obj = NULL;
+	struct drm_file *file;
+	I915_RND_STATE(prng);
+	IGT_TIMEOUT(end_time);
+	LIST_HEAD(objects);
+	struct i915_gem_context *ctx;
+	struct i915_hw_ppgtt *ppgtt;
+	unsigned long ndwords, dw;
+	int err = -ENODEV;
+
+	/*
+	 * Create a few read-only objects (with the occasional writable object)
+	 * and try to write into these object checking that the GPU discards
+	 * any write to a read-only object.
+	 */
+
+	file = mock_file(i915);
+	if (IS_ERR(file))
+		return PTR_ERR(file);
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	ctx = i915_gem_create_context(i915, file->driver_priv);
+	if (IS_ERR(ctx)) {
+		err = PTR_ERR(ctx);
+		goto out_unlock;
+	}
+
+	ppgtt = ctx->ppgtt ?: i915->mm.aliasing_ppgtt;
+	if (!ppgtt || !ppgtt->vm.has_read_only) {
+		err = 0;
+		goto out_unlock;
+	}
+
+	ndwords = 0;
+	dw = 0;
+	while (!time_after(jiffies, end_time)) {
+		struct intel_engine_cs *engine;
+		unsigned int id;
+
+		for_each_engine(engine, i915, id) {
+			if (!intel_engine_can_store_dword(engine))
+				continue;
+
+			if (!obj) {
+				obj = create_test_object(ctx, file, &objects);
+				if (IS_ERR(obj)) {
+					err = PTR_ERR(obj);
+					goto out_unlock;
+				}
+
+				obj->gt_ro = prandom_u32_state(&prng);
+			}
+
+			intel_runtime_pm_get(i915);
+			err = gpu_fill(obj, ctx, engine, dw);
+			intel_runtime_pm_put(i915);
+			if (err) {
+				pr_err("Failed to fill dword %lu [%lu/%lu] with gpu (%s) in ctx %u [full-ppgtt? %s], err=%d\n",
+				       ndwords, dw, max_dwords(obj),
+				       engine->name, ctx->hw_id,
+				       yesno(!!ctx->ppgtt), err);
+				goto out_unlock;
+			}
+
+			if (++dw == max_dwords(obj)) {
+				obj = NULL;
+				dw = 0;
+			}
+			ndwords++;
+		}
+	}
+	pr_info("Submitted %lu dwords (across %u engines)\n",
+		ndwords, INTEL_INFO(i915)->num_rings);
+
+	dw = 0;
+	list_for_each_entry(obj, &objects, st_link) {
+		unsigned int rem =
+			min_t(unsigned int, ndwords - dw, max_dwords(obj));
+		unsigned int num_writes;
+
+		num_writes = rem;
+		if (obj->gt_ro)
+			num_writes = 0;
+
+		err = cpu_check(obj, num_writes);
+		if (err)
+			break;
+
+		dw += rem;
+	}
+
+out_unlock:
+	if (igt_flush_test(i915, I915_WAIT_LOCKED))
+		err = -EIO;
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	mock_file_free(i915, file);
+	return err;
+}
+
 static __maybe_unused const char *
 __engine_name(struct drm_i915_private *i915, unsigned int engines)
 {
@@ -608,6 +713,7 @@ int i915_gem_context_live_selftests(struct drm_i915_private *dev_priv)
 	static const struct i915_subtest tests[] = {
 		SUBTEST(igt_switch_to_kernel_context),
 		SUBTEST(igt_ctx_exec),
+		SUBTEST(igt_ctx_readonly),
 	};
 	bool fake_alias = false;
 	int err;
-- 
cgit v1.2.3


From c9e666880de5a1fed04dc412b046916d542b72dd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Jul 2018 19:53:12 +0100
Subject: drm/i915/gtt: Disable read-only support under GVT

GVT is not propagating the PTE bits, and is always setting the
read-write bit, thus breaking read-only support.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_gtt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 734b67f7853c..86a9618bab24 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1662,8 +1662,12 @@ static struct i915_hw_ppgtt *gen8_ppgtt_create(struct drm_i915_private *i915)
 		1ULL << 48 :
 		1ULL << 32;
 
-	/* From bdw, there is support for read-only pages in the PPGTT */
-	ppgtt->vm.has_read_only = true;
+	/*
+	 * From bdw, there is support for read-only pages in the PPGTT.
+	 *
+	 * XXX GVT is not honouring the lack of RW in the PTE bits.
+	 */
+	ppgtt->vm.has_read_only = !intel_vgpu_active(i915);
 
 	i915_address_space_init(&ppgtt->vm, i915);
 
-- 
cgit v1.2.3


From 3e977ac6179b39faa3c0eda5fce4f00663ae298d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Jul 2018 19:53:13 +0100
Subject: drm/i915: Prevent writing into a read-only object via a GGTT mmap

If the user has created a read-only object, they should not be allowed
to circumvent the write protection by using a GGTT mmapping. Deny it.

Also most machines do not support read-only GGTT PTEs, so again we have
to reject attempted writes. Fortunately, this is known a priori, so we
can at least reject in the call to create the mmap (with a sanity check
in the fault handler).

v2: Check the vma->vm_flags during mmap() to allow readonly access.
v3: Remove VM_MAYWRITE to curtail mprotect()

Testcase: igt/gem_userptr_blits/readonly_mmap*
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Cc: David Herrmann <dh.herrmann@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com> #v1
Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/drm_gem.c                         |  9 +++++++++
 drivers/gpu/drm/i915/i915_gem.c                   |  4 ++++
 drivers/gpu/drm/i915/i915_gem_gtt.c               | 12 +++++++-----
 drivers/gpu/drm/i915/i915_gem_object.h            | 13 ++++++++++++-
 drivers/gpu/drm/i915/intel_ringbuffer.c           |  2 +-
 drivers/gpu/drm/i915/selftests/i915_gem_context.c |  5 +++--
 include/drm/drm_vma_manager.h                     |  1 +
 7 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index 4a16d7b26c89..bf90625df3c5 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -1036,6 +1036,15 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 		return -EACCES;
 	}
 
+	if (node->readonly) {
+		if (vma->vm_flags & VM_WRITE) {
+			drm_gem_object_put_unlocked(obj);
+			return -EINVAL;
+		}
+
+		vma->vm_flags &= ~VM_MAYWRITE;
+	}
+
 	ret = drm_gem_mmap_obj(obj, drm_vma_node_size(node) << PAGE_SHIFT,
 			       vma);
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ed2be33ec58a..1910c66f48e2 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -2012,6 +2012,10 @@ vm_fault_t i915_gem_fault(struct vm_fault *vmf)
 	pgoff_t page_offset;
 	int ret;
 
+	/* Sanity check that we allow writing into this object */
+	if (i915_gem_object_is_readonly(obj) && write)
+		return VM_FAULT_SIGBUS;
+
 	/* We don't use vmf->pgoff since that has the fake offset */
 	page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT;
 
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 86a9618bab24..3d75f2bb5623 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -206,7 +206,7 @@ static int ppgtt_bind_vma(struct i915_vma *vma,
 
 	/* Applicable to VLV, and gen8+ */
 	pte_flags = 0;
-	if (vma->obj->gt_ro)
+	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	vma->vm->insert_entries(vma->vm, vma, cache_level, pte_flags);
@@ -2491,8 +2491,10 @@ static void gen8_ggtt_insert_entries(struct i915_address_space *vm,
 	const gen8_pte_t pte_encode = gen8_pte_encode(0, level, 0);
 	dma_addr_t addr;
 
-	/* The GTT does not support read-only mappings */
-	GEM_BUG_ON(flags & PTE_READ_ONLY);
+	/*
+	 * Note that we ignore PTE_READ_ONLY here. The caller must be careful
+	 * not to allow the user to override access to a read only page.
+	 */
 
 	gtt_entries = (gen8_pte_t __iomem *)ggtt->gsm;
 	gtt_entries += vma->node.start >> PAGE_SHIFT;
@@ -2731,7 +2733,7 @@ static int ggtt_bind_vma(struct i915_vma *vma,
 
 	/* Applicable to VLV (gen8+ do not support RO in the GGTT) */
 	pte_flags = 0;
-	if (obj->gt_ro)
+	if (i915_gem_object_is_readonly(obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	intel_runtime_pm_get(i915);
@@ -2769,7 +2771,7 @@ static int aliasing_gtt_bind_vma(struct i915_vma *vma,
 
 	/* Currently applicable only to VLV */
 	pte_flags = 0;
-	if (vma->obj->gt_ro)
+	if (i915_gem_object_is_readonly(vma->obj))
 		pte_flags |= PTE_READ_ONLY;
 
 	if (flags & I915_VMA_LOCAL_BIND) {
diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index c3c6f2e588fb..56e9f00d2c4c 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -141,7 +141,6 @@ struct drm_i915_gem_object {
 	 * Is the object to be mapped as read-only to the GPU
 	 * Only honoured if hardware has relevant pte bit
 	 */
-	unsigned long gt_ro:1;
 	unsigned int cache_level:3;
 	unsigned int cache_coherent:2;
 #define I915_BO_CACHE_COHERENT_FOR_READ BIT(0)
@@ -358,6 +357,18 @@ static inline void i915_gem_object_unlock(struct drm_i915_gem_object *obj)
 	reservation_object_unlock(obj->resv);
 }
 
+static inline void
+i915_gem_object_set_readonly(struct drm_i915_gem_object *obj)
+{
+	obj->base.vma_node.readonly = true;
+}
+
+static inline bool
+i915_gem_object_is_readonly(const struct drm_i915_gem_object *obj)
+{
+	return obj->base.vma_node.readonly;
+}
+
 static inline bool
 i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
 {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 6de88add508a..69bd7f697f6d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1100,7 +1100,7 @@ intel_ring_create_vma(struct drm_i915_private *dev_priv, int size)
 	 * if supported by the platform's GGTT.
 	 */
 	if (vm->has_read_only)
-		obj->gt_ro = 1;
+		i915_gem_object_set_readonly(obj);
 
 	vma = i915_vma_instance(obj, vm, NULL);
 	if (IS_ERR(vma))
diff --git a/drivers/gpu/drm/i915/selftests/i915_gem_context.c b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
index 2e2a3c44b8e9..1c92560d35da 100644
--- a/drivers/gpu/drm/i915/selftests/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/selftests/i915_gem_context.c
@@ -487,7 +487,8 @@ static int igt_ctx_readonly(void *arg)
 					goto out_unlock;
 				}
 
-				obj->gt_ro = prandom_u32_state(&prng);
+				if (prandom_u32_state(&prng) & 1)
+					i915_gem_object_set_readonly(obj);
 			}
 
 			intel_runtime_pm_get(i915);
@@ -518,7 +519,7 @@ static int igt_ctx_readonly(void *arg)
 		unsigned int num_writes;
 
 		num_writes = rem;
-		if (obj->gt_ro)
+		if (i915_gem_object_is_readonly(obj))
 			num_writes = 0;
 
 		err = cpu_check(obj, num_writes);
diff --git a/include/drm/drm_vma_manager.h b/include/drm/drm_vma_manager.h
index 8758df94e9a0..c7987daeaed0 100644
--- a/include/drm/drm_vma_manager.h
+++ b/include/drm/drm_vma_manager.h
@@ -41,6 +41,7 @@ struct drm_vma_offset_node {
 	rwlock_t vm_lock;
 	struct drm_mm_node vm_node;
 	struct rb_root vm_files;
+	bool readonly:1;
 };
 
 struct drm_vma_offset_manager {
-- 
cgit v1.2.3


From f8c1cce36ccb21b5e5ecc87fac65de0e29693f01 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Jul 2018 19:53:14 +0100
Subject: drm/i915: Reject attempted pwrites into a read-only object

If the user created a read-only object, they should not be allowed to
circumvent the write protection using the pwrite ioctl.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712185315.3288-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1910c66f48e2..42d24410a98c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1627,6 +1627,12 @@ i915_gem_pwrite_ioctl(struct drm_device *dev, void *data,
 		goto err;
 	}
 
+	/* Writes not allowed into this read-only object */
+	if (i915_gem_object_is_readonly(obj)) {
+		ret = -EINVAL;
+		goto err;
+	}
+
 	trace_i915_gem_object_pwrite(obj, args->offset, args->size);
 
 	ret = -ENODEV;
-- 
cgit v1.2.3


From 0b100760e3e8cbb2b5d09c1c2bcb01d50201c142 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 12 Jul 2018 20:14:30 +0100
Subject: drm/i915/userptr: Enable read-only support on gen8+

On gen8 and onwards, we can mark GPU accesses through the ppGTT as being
read-only, that is cause any GPU write onto that page to be discarded
(not triggering a fault). This is all that we need to finally support
the read-only flag for userptr!

v2: Check default address space for read only support as a proxy for the
user context/ppgtt.

Testcase: igt/gem_userptr_blits/readonly*
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jon Bloomfield <jon.bloomfield@intel.com>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Jon Bloomfield <jon.bloomfield@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712191430.9269-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem_object.h  |  1 -
 drivers/gpu/drm/i915/i915_gem_userptr.c | 18 ++++++++++++------
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem_object.h b/drivers/gpu/drm/i915/i915_gem_object.h
index 56e9f00d2c4c..83e5e01fa9ea 100644
--- a/drivers/gpu/drm/i915/i915_gem_object.h
+++ b/drivers/gpu/drm/i915/i915_gem_object.h
@@ -267,7 +267,6 @@ struct drm_i915_gem_object {
 	union {
 		struct i915_gem_userptr {
 			uintptr_t ptr;
-			unsigned read_only :1;
 
 			struct i915_mm_struct *mm;
 			struct i915_mmu_object *mmu_object;
diff --git a/drivers/gpu/drm/i915/i915_gem_userptr.c b/drivers/gpu/drm/i915/i915_gem_userptr.c
index 854bd51b9478..dcd6e230d16a 100644
--- a/drivers/gpu/drm/i915/i915_gem_userptr.c
+++ b/drivers/gpu/drm/i915/i915_gem_userptr.c
@@ -507,7 +507,7 @@ __i915_gem_userptr_get_pages_worker(struct work_struct *_work)
 		struct mm_struct *mm = obj->userptr.mm->mm;
 		unsigned int flags = 0;
 
-		if (!obj->userptr.read_only)
+		if (!i915_gem_object_is_readonly(obj))
 			flags |= FOLL_WRITE;
 
 		ret = -EFAULT;
@@ -643,7 +643,7 @@ static int i915_gem_userptr_get_pages(struct drm_i915_gem_object *obj)
 		if (pvec) /* defer to worker if malloc fails */
 			pinned = __get_user_pages_fast(obj->userptr.ptr,
 						       num_pages,
-						       !obj->userptr.read_only,
+						       !i915_gem_object_is_readonly(obj),
 						       pvec);
 	}
 
@@ -789,10 +789,15 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 		return -EFAULT;
 
 	if (args->flags & I915_USERPTR_READ_ONLY) {
-		/* On almost all of the current hw, we cannot tell the GPU that a
-		 * page is readonly, so this is just a placeholder in the uAPI.
+		struct i915_hw_ppgtt *ppgtt;
+
+		/*
+		 * On almost all of the older hw, we cannot tell the GPU that
+		 * a page is readonly.
 		 */
-		return -ENODEV;
+		ppgtt = dev_priv->kernel_context->ppgtt;
+		if (!ppgtt || !ppgtt->vm.has_read_only)
+			return -ENODEV;
 	}
 
 	obj = i915_gem_object_alloc(dev_priv);
@@ -806,7 +811,8 @@ i915_gem_userptr_ioctl(struct drm_device *dev,
 	i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC);
 
 	obj->userptr.ptr = args->user_ptr;
-	obj->userptr.read_only = !!(args->flags & I915_USERPTR_READ_ONLY);
+	if (args->flags & I915_USERPTR_READ_ONLY)
+		i915_gem_object_set_readonly(obj);
 
 	/* And keep a pointer to the current->mm for resolving the user pages
 	 * at binding. This means that we need to hook into the mmu_notifier
-- 
cgit v1.2.3


From 14aa521c5eb615c802d51e9e8884f2dbd35993a2 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 19:43:50 +0300
Subject: drm/i915: Introduce for_each_intel_dp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a convenience macro for iterating DP encoders.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705164357.28512-2-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/intel_display.h |  4 ++++
 drivers/gpu/drm/i915/intel_dp.c      | 38 +++++++-----------------------------
 drivers/gpu/drm/i915/intel_drv.h     | 14 +++++++++++++
 3 files changed, 25 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.h b/drivers/gpu/drm/i915/intel_display.h
index a77dd29db2ec..7559dfc235a2 100644
--- a/drivers/gpu/drm/i915/intel_display.h
+++ b/drivers/gpu/drm/i915/intel_display.h
@@ -289,6 +289,10 @@ struct intel_link_m_n {
 			    &(dev)->mode_config.encoder_list,	\
 			    base.head)
 
+#define for_each_intel_dp(dev, intel_encoder)			\
+	for_each_intel_encoder(dev, intel_encoder)		\
+		for_each_if(intel_encoder_is_dp(intel_encoder))
+
 #define for_each_intel_connector_iter(intel_connector, iter) \
 	while ((intel_connector = to_intel_connector(drm_connector_list_iter_next(iter))))
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 7d40bfcb1bbb..f4662b2fb7ab 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -600,14 +600,8 @@ static enum pipe vlv_find_free_pps(struct drm_i915_private *dev_priv)
 	 * We don't have power sequencer currently.
 	 * Pick one that's not used by other ports.
 	 */
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 
 		if (encoder->type == INTEL_OUTPUT_EDP) {
 			WARN_ON(intel_dp->active_pipe != INVALID_PIPE &&
@@ -799,19 +793,8 @@ void intel_power_sequencer_reset(struct drm_i915_private *dev_priv)
 	 * should use them always.
 	 */
 
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP &&
-		    encoder->type != INTEL_OUTPUT_DDI)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
-
-		/* Skip pure DVI/HDMI DDI encoders */
-		if (!i915_mmio_reg_valid(intel_dp->output_reg))
-			continue;
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
 
 		WARN_ON(intel_dp->active_pipe != INVALID_PIPE);
 
@@ -3097,16 +3080,9 @@ static void vlv_steal_power_sequencer(struct drm_i915_private *dev_priv,
 
 	lockdep_assert_held(&dev_priv->pps_mutex);
 
-	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		struct intel_dp *intel_dp;
-		enum port port;
-
-		if (encoder->type != INTEL_OUTPUT_DP &&
-		    encoder->type != INTEL_OUTPUT_EDP)
-			continue;
-
-		intel_dp = enc_to_intel_dp(&encoder->base);
-		port = dp_to_dig_port(intel_dp)->base.port;
+	for_each_intel_dp(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp = enc_to_intel_dp(&encoder->base);
+		enum port port = encoder->port;
 
 		WARN(intel_dp->active_pipe == pipe,
 		     "stealing pipe %c power sequencer from active (e)DP port %c\n",
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a0e9a35b5658..2740a0ef3f49 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1275,6 +1275,20 @@ static inline struct intel_dp *enc_to_intel_dp(struct drm_encoder *encoder)
 	return &enc_to_dig_port(encoder)->dp;
 }
 
+static inline bool intel_encoder_is_dp(struct intel_encoder *encoder)
+{
+	switch (encoder->type) {
+	case INTEL_OUTPUT_DP:
+	case INTEL_OUTPUT_EDP:
+		return true;
+	case INTEL_OUTPUT_DDI:
+		/* Skip pure HDMI/DVI DDI encoders */
+		return i915_mmio_reg_valid(enc_to_intel_dp(&encoder->base)->output_reg);
+	default:
+		return false;
+	}
+}
+
 static inline struct intel_digital_port *
 dp_to_dig_port(struct intel_dp *intel_dp)
 {
-- 
cgit v1.2.3


From 4ef03f8354f592b237cff1774cc50e4e4eb63652 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 19:43:51 +0300
Subject: drm/i915: Introduce intel_encoder_is_dig_port()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add intel_encoder_is_dig_port() to match intel_encoder_is_dp().

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705164357.28512-3-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/intel_drv.h | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 2740a0ef3f49..987fbb2ef911 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1245,23 +1245,29 @@ intel_attached_encoder(struct drm_connector *connector)
 	return to_intel_connector(connector)->encoder;
 }
 
-static inline struct intel_digital_port *
-enc_to_dig_port(struct drm_encoder *encoder)
+static inline bool intel_encoder_is_dig_port(struct intel_encoder *encoder)
 {
-	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
-
-	switch (intel_encoder->type) {
+	switch (encoder->type) {
 	case INTEL_OUTPUT_DDI:
-		WARN_ON(!HAS_DDI(to_i915(encoder->dev)));
-		/* fall through */
 	case INTEL_OUTPUT_DP:
 	case INTEL_OUTPUT_EDP:
 	case INTEL_OUTPUT_HDMI:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static inline struct intel_digital_port *
+enc_to_dig_port(struct drm_encoder *encoder)
+{
+	struct intel_encoder *intel_encoder = to_intel_encoder(encoder);
+
+	if (intel_encoder_is_dig_port(intel_encoder))
 		return container_of(encoder, struct intel_digital_port,
 				    base.base);
-	default:
+	else
 		return NULL;
-	}
 }
 
 static inline struct intel_dp_mst_encoder *
-- 
cgit v1.2.3


From 1a4313d13b69318d11e3418b7193be6add511f69 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 19:43:52 +0300
Subject: drm/i915: Rewrite mst suspend/resume in terms of encoders
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather than looping over all the ports and picking the encoder based on
the port, let's just loop over all the encoders instead. Gets rid of
some irq_port[] usage, which is a bit of an eye sore.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705164357.28512-4-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c  |  4 ++--
 drivers/gpu/drm/i915/intel_dp.c  | 41 +++++++++++++++++++++++-----------------
 drivers/gpu/drm/i915/intel_drv.h |  4 ++--
 3 files changed, 28 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index f059aa332323..cfa7583cf408 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1586,7 +1586,7 @@ static int i915_drm_suspend(struct drm_device *dev)
 
 	intel_display_suspend(dev);
 
-	intel_dp_mst_suspend(dev);
+	intel_dp_mst_suspend(dev_priv);
 
 	intel_runtime_pm_disable_interrupts(dev_priv);
 	intel_hpd_cancel_work(dev_priv);
@@ -1751,7 +1751,7 @@ static int i915_drm_resume(struct drm_device *dev)
 		dev_priv->display.hpd_irq_setup(dev_priv);
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	intel_dp_mst_resume(dev);
+	intel_dp_mst_resume(dev_priv);
 
 	intel_display_resume(dev);
 
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index f4662b2fb7ab..18bcdab24baa 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -6483,37 +6483,44 @@ err_connector_alloc:
 	return false;
 }
 
-void intel_dp_mst_suspend(struct drm_device *dev)
+void intel_dp_mst_suspend(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int i;
+	struct intel_encoder *encoder;
+
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp;
+
+		if (encoder->type != INTEL_OUTPUT_DDI)
+			continue;
 
-	/* disable MST */
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
+		intel_dp = enc_to_intel_dp(&encoder->base);
 
-		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
+		if (!intel_dp->can_mst)
 			continue;
 
-		if (intel_dig_port->dp.is_mst)
-			drm_dp_mst_topology_mgr_suspend(&intel_dig_port->dp.mst_mgr);
+		if (intel_dp->is_mst)
+			drm_dp_mst_topology_mgr_suspend(&intel_dp->mst_mgr);
 	}
 }
 
-void intel_dp_mst_resume(struct drm_device *dev)
+void intel_dp_mst_resume(struct drm_i915_private *dev_priv)
 {
-	struct drm_i915_private *dev_priv = to_i915(dev);
-	int i;
+	struct intel_encoder *encoder;
 
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		struct intel_digital_port *intel_dig_port = dev_priv->hotplug.irq_port[i];
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_dp *intel_dp;
 		int ret;
 
-		if (!intel_dig_port || !intel_dig_port->dp.can_mst)
+		if (encoder->type != INTEL_OUTPUT_DDI)
+			continue;
+
+		intel_dp = enc_to_intel_dp(&encoder->base);
+
+		if (!intel_dp->can_mst)
 			continue;
 
-		ret = drm_dp_mst_topology_mgr_resume(&intel_dig_port->dp.mst_mgr);
+		ret = drm_dp_mst_topology_mgr_resume(&intel_dp->mst_mgr);
 		if (ret)
-			intel_dp_check_mst_status(&intel_dig_port->dp);
+			intel_dp_check_mst_status(intel_dp);
 	}
 }
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 987fbb2ef911..33c15fbc9cc1 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1698,8 +1698,8 @@ void intel_edp_backlight_off(const struct drm_connector_state *conn_state);
 void intel_edp_panel_vdd_on(struct intel_dp *intel_dp);
 void intel_edp_panel_on(struct intel_dp *intel_dp);
 void intel_edp_panel_off(struct intel_dp *intel_dp);
-void intel_dp_mst_suspend(struct drm_device *dev);
-void intel_dp_mst_resume(struct drm_device *dev);
+void intel_dp_mst_suspend(struct drm_i915_private *dev_priv);
+void intel_dp_mst_resume(struct drm_i915_private *dev_priv);
 int intel_dp_max_link_rate(struct intel_dp *intel_dp);
 int intel_dp_max_lane_count(struct intel_dp *intel_dp);
 int intel_dp_rate_select(struct intel_dp *intel_dp, int rate);
-- 
cgit v1.2.3


From b6ca3eee18ba1ec97cad54b7f476bcfaca50c17c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 19:43:53 +0300
Subject: drm/i915: Nuke dev_priv->irq_port[]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of looping over ports and hpd_pins, let's loop over
the encoders when doing hotplug processing. And instead of
depending on dev_priv->irq_port[] to tell us whether the
encoder has the ->hpd_pulse() hook or not, we can just
check for that directly. So we can just nuke irq_port[] entirely.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705164357.28512-5-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h      |  1 -
 drivers/gpu/drm/i915/intel_ddi.c     |  1 -
 drivers/gpu/drm/i915/intel_dp.c      |  1 -
 drivers/gpu/drm/i915/intel_drv.h     |  2 ++
 drivers/gpu/drm/i915/intel_hotplug.c | 61 +++++++++++++++++++-----------------
 5 files changed, 34 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index f519485fcd73..059cef73eb28 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -299,7 +299,6 @@ struct i915_hotplug {
 	u32 event_bits;
 	struct delayed_work reenable_work;
 
-	struct intel_digital_port *irq_port[I915_MAX_PORTS];
 	u32 long_port_mask;
 	u32 short_port_mask;
 	struct work_struct dig_port_work;
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index e4caa902d88e..39d66f8493fa 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -3639,7 +3639,6 @@ void intel_ddi_init(struct drm_i915_private *dev_priv, enum port port)
 			goto err;
 
 		intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
-		dev_priv->hotplug.irq_port[port] = intel_dig_port;
 	}
 
 	/* In theory we don't need the encoder->type check, but leave it just in
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 18bcdab24baa..fc05c8226551 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -6464,7 +6464,6 @@ bool intel_dp_init(struct drm_i915_private *dev_priv,
 	intel_encoder->port = port;
 
 	intel_dig_port->hpd_pulse = intel_dp_hpd_pulse;
-	dev_priv->hotplug.irq_port[port] = intel_dig_port;
 
 	if (port != PORT_A)
 		intel_infoframe_init(intel_dig_port);
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 33c15fbc9cc1..a45f6324dd9b 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -304,6 +304,8 @@ struct intel_panel {
 	} backlight;
 };
 
+struct intel_digital_port;
+
 /*
  * This structure serves as a translation layer between the generic HDCP code
  * and the bus-specific code. What that means is that HDCP over HDMI differs
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index 43aa92beff2a..f862441158e1 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -301,13 +301,18 @@ bool intel_encoder_hotplug(struct intel_encoder *encoder,
 	return true;
 }
 
+static bool intel_encoder_has_hpd_pulse(struct intel_encoder *encoder)
+{
+	return intel_encoder_is_dig_port(encoder) &&
+		enc_to_dig_port(&encoder->base)->hpd_pulse != NULL;
+}
+
 static void i915_digport_work_func(struct work_struct *work)
 {
 	struct drm_i915_private *dev_priv =
 		container_of(work, struct drm_i915_private, hotplug.dig_port_work);
 	u32 long_port_mask, short_port_mask;
-	struct intel_digital_port *intel_dig_port;
-	int i;
+	struct intel_encoder *encoder;
 	u32 old_bits = 0;
 
 	spin_lock_irq(&dev_priv->irq_lock);
@@ -317,27 +322,27 @@ static void i915_digport_work_func(struct work_struct *work)
 	dev_priv->hotplug.short_port_mask = 0;
 	spin_unlock_irq(&dev_priv->irq_lock);
 
-	for (i = 0; i < I915_MAX_PORTS; i++) {
-		bool valid = false;
-		bool long_hpd = false;
-		intel_dig_port = dev_priv->hotplug.irq_port[i];
-		if (!intel_dig_port || !intel_dig_port->hpd_pulse)
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		struct intel_digital_port *dig_port;
+		enum port port = encoder->port;
+		bool long_hpd, short_hpd;
+		enum irqreturn ret;
+
+		if (!intel_encoder_has_hpd_pulse(encoder))
 			continue;
 
-		if (long_port_mask & (1 << i))  {
-			valid = true;
-			long_hpd = true;
-		} else if (short_port_mask & (1 << i))
-			valid = true;
+		long_hpd = long_port_mask & BIT(port);
+		short_hpd = short_port_mask & BIT(port);
+
+		if (!long_hpd && !short_hpd)
+			continue;
 
-		if (valid) {
-			enum irqreturn ret;
+		dig_port = enc_to_dig_port(&encoder->base);
 
-			ret = intel_dig_port->hpd_pulse(intel_dig_port, long_hpd);
-			if (ret == IRQ_NONE) {
-				/* fall back to old school hpd */
-				old_bits |= (1 << intel_dig_port->base.hpd_pin);
-			}
+		ret = dig_port->hpd_pulse(dig_port, long_hpd);
+		if (ret == IRQ_NONE) {
+			/* fall back to old school hpd */
+			old_bits |= BIT(encoder->hpd_pin);
 		}
 	}
 
@@ -418,26 +423,24 @@ static void i915_hotplug_work_func(struct work_struct *work)
 void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			   u32 pin_mask, u32 long_mask)
 {
-	int i;
-	enum port port;
+	struct intel_encoder *encoder;
 	bool storm_detected = false;
 	bool queue_dig = false, queue_hp = false;
-	bool is_dig_port;
 
 	if (!pin_mask)
 		return;
 
 	spin_lock(&dev_priv->irq_lock);
-	for_each_hpd_pin(i) {
+	for_each_intel_encoder(&dev_priv->drm, encoder) {
+		enum hpd_pin i = encoder->hpd_pin;
+		bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder);
+
 		if (!(BIT(i) & pin_mask))
 			continue;
 
-		port = intel_hpd_pin_to_port(dev_priv, i);
-		is_dig_port = port != PORT_NONE &&
-			dev_priv->hotplug.irq_port[port];
-
-		if (is_dig_port) {
+		if (has_hpd_pulse) {
 			bool long_hpd = long_mask & BIT(i);
+			enum port port = encoder->port;
 
 			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port),
 					 long_hpd ? "long" : "short");
@@ -470,7 +473,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 		if (dev_priv->hotplug.stats[i].state != HPD_ENABLED)
 			continue;
 
-		if (!is_dig_port) {
+		if (!has_hpd_pulse) {
 			dev_priv->hotplug.event_bits |= BIT(i);
 			queue_hp = true;
 		}
-- 
cgit v1.2.3


From e9be285051e1ff447f43d09da4102aa30d8645d7 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 19:43:54 +0300
Subject: drm/i915: s/int i/enum hpd_pin pin/
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use the enum hpd_pin type when talking about HPD pins, and rename the
variable from a very nondescript 'i' to 'pin', a name we already
use in other parts of the code.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705164357.28512-6-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_irq.c      | 12 ++++++------
 drivers/gpu/drm/i915/intel_hotplug.c | 28 ++++++++++++++--------------
 2 files changed, 20 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 495b9d27990e..bd9c77c804ab 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1712,20 +1712,20 @@ static void intel_get_hpd_pins(struct drm_i915_private *dev_priv,
 			       bool long_pulse_detect(enum port port, u32 val))
 {
 	enum port port;
-	int i;
+	enum hpd_pin pin;
 
-	for_each_hpd_pin(i) {
-		if ((hpd[i] & hotplug_trigger) == 0)
+	for_each_hpd_pin(pin) {
+		if ((hpd[pin] & hotplug_trigger) == 0)
 			continue;
 
-		*pin_mask |= BIT(i);
+		*pin_mask |= BIT(pin);
 
-		port = intel_hpd_pin_to_port(dev_priv, i);
+		port = intel_hpd_pin_to_port(dev_priv, pin);
 		if (port == PORT_NONE)
 			continue;
 
 		if (long_pulse_detect(port, dig_hotplug_reg))
-			*long_mask |= BIT(i);
+			*long_mask |= BIT(pin);
 	}
 
 	DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x\n",
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index f862441158e1..d9d61d11dd2b 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -241,25 +241,25 @@ static void intel_hpd_irq_storm_reenable_work(struct work_struct *work)
 		container_of(work, typeof(*dev_priv),
 			     hotplug.reenable_work.work);
 	struct drm_device *dev = &dev_priv->drm;
-	int i;
+	enum hpd_pin pin;
 
 	intel_runtime_pm_get(dev_priv);
 
 	spin_lock_irq(&dev_priv->irq_lock);
-	for_each_hpd_pin(i) {
+	for_each_hpd_pin(pin) {
 		struct drm_connector *connector;
 		struct drm_connector_list_iter conn_iter;
 
-		if (dev_priv->hotplug.stats[i].state != HPD_DISABLED)
+		if (dev_priv->hotplug.stats[pin].state != HPD_DISABLED)
 			continue;
 
-		dev_priv->hotplug.stats[i].state = HPD_ENABLED;
+		dev_priv->hotplug.stats[pin].state = HPD_ENABLED;
 
 		drm_connector_list_iter_begin(dev, &conn_iter);
 		drm_for_each_connector_iter(connector, &conn_iter) {
 			struct intel_connector *intel_connector = to_intel_connector(connector);
 
-			if (intel_connector->encoder->hpd_pin == i) {
+			if (intel_connector->encoder->hpd_pin == pin) {
 				if (connector->polled != intel_connector->polled)
 					DRM_DEBUG_DRIVER("Reenabling HPD on connector %s\n",
 							 connector->name);
@@ -432,14 +432,14 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 
 	spin_lock(&dev_priv->irq_lock);
 	for_each_intel_encoder(&dev_priv->drm, encoder) {
-		enum hpd_pin i = encoder->hpd_pin;
+		enum hpd_pin pin = encoder->hpd_pin;
 		bool has_hpd_pulse = intel_encoder_has_hpd_pulse(encoder);
 
-		if (!(BIT(i) & pin_mask))
+		if (!(BIT(pin) & pin_mask))
 			continue;
 
 		if (has_hpd_pulse) {
-			bool long_hpd = long_mask & BIT(i);
+			bool long_hpd = long_mask & BIT(pin);
 			enum port port = encoder->port;
 
 			DRM_DEBUG_DRIVER("digital hpd port %c - %s\n", port_name(port),
@@ -458,7 +458,7 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			}
 		}
 
-		if (dev_priv->hotplug.stats[i].state == HPD_DISABLED) {
+		if (dev_priv->hotplug.stats[pin].state == HPD_DISABLED) {
 			/*
 			 * On GMCH platforms the interrupt mask bits only
 			 * prevent irq generation, not the setting of the
@@ -466,20 +466,20 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 			 * interrupts on saner platforms.
 			 */
 			WARN_ONCE(!HAS_GMCH_DISPLAY(dev_priv),
-				  "Received HPD interrupt on pin %d although disabled\n", i);
+				  "Received HPD interrupt on pin %d although disabled\n", pin);
 			continue;
 		}
 
-		if (dev_priv->hotplug.stats[i].state != HPD_ENABLED)
+		if (dev_priv->hotplug.stats[pin].state != HPD_ENABLED)
 			continue;
 
 		if (!has_hpd_pulse) {
-			dev_priv->hotplug.event_bits |= BIT(i);
+			dev_priv->hotplug.event_bits |= BIT(pin);
 			queue_hp = true;
 		}
 
-		if (intel_hpd_irq_storm_detect(dev_priv, i)) {
-			dev_priv->hotplug.event_bits &= ~BIT(i);
+		if (intel_hpd_irq_storm_detect(dev_priv, pin)) {
+			dev_priv->hotplug.event_bits &= ~BIT(pin);
 			storm_detected = true;
 		}
 	}
-- 
cgit v1.2.3


From af92058ff021d5d8b0523baf76e709fe2fc3aa0c Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 19:43:55 +0300
Subject: drm/i915: Pass hpd_pin to long_pulse_detect()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're doing a pointless translation from hpd_pin to port simply for
passing the thing to long_pulse_detect(). Let's pass the hpd_pin
directly instead.

This removes the assumption that the hpd_pin and port always
match. The only other place where we make that assumption anymore
is intel_hpd_pin_default() and that's fine as it's what determines
the relationship between the two. If we ever get hardware where
the hpd pins are wired in more interesting ways it should be
trivial to handle from now on.

This should also fix the IS_CNL_WITH_PORT_F() case as that mapped
pin E back to port F and passed that to
spt_port_hotplug2_long_detect() which would always return false
for port F. Now that we pass in pin E directly it'll actually
do the right thing.

Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Fixes: cf53902f48c3 ("drm/i915/cnl: Add HPD support for Port F.")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705164357.28512-7-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h      |  2 -
 drivers/gpu/drm/i915/i915_irq.c      | 95 +++++++++++++++++-------------------
 drivers/gpu/drm/i915/intel_hotplug.c | 31 ------------
 3 files changed, 45 insertions(+), 83 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 059cef73eb28..08d4303abb14 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2745,8 +2745,6 @@ void intel_hpd_irq_handler(struct drm_i915_private *dev_priv,
 void intel_hpd_init(struct drm_i915_private *dev_priv);
 void intel_hpd_init_work(struct drm_i915_private *dev_priv);
 void intel_hpd_cancel_work(struct drm_i915_private *dev_priv);
-enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
-				enum hpd_pin pin);
 enum hpd_pin intel_hpd_pin_default(struct drm_i915_private *dev_priv,
 				   enum port port);
 bool intel_hpd_disable(struct drm_i915_private *dev_priv, enum hpd_pin pin);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index bd9c77c804ab..6d80eb6b8998 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1576,122 +1576,122 @@ static void gen8_gt_irq_handler(struct drm_i915_private *i915,
 	}
 }
 
-static bool gen11_port_hotplug_long_detect(enum port port, u32 val)
+static bool gen11_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_C:
+	switch (pin) {
+	case HPD_PORT_C:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC1);
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC2);
-	case PORT_E:
+	case HPD_PORT_E:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC3);
-	case PORT_F:
+	case HPD_PORT_F:
 		return val & GEN11_HOTPLUG_CTL_LONG_DETECT(PORT_TC4);
 	default:
 		return false;
 	}
 }
 
-static bool bxt_port_hotplug_long_detect(enum port port, u32 val)
+static bool bxt_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & PORTA_HOTPLUG_LONG_DETECT;
-	case PORT_B:
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool icp_ddi_port_hotplug_long_detect(enum port port, u32 val)
+static bool icp_ddi_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & ICP_DDIA_HPD_LONG_DETECT;
-	case PORT_B:
+	case HPD_PORT_B:
 		return val & ICP_DDIB_HPD_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool icp_tc_port_hotplug_long_detect(enum port port, u32 val)
+static bool icp_tc_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_C:
+	switch (pin) {
+	case HPD_PORT_C:
 		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC1);
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC2);
-	case PORT_E:
+	case HPD_PORT_E:
 		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC3);
-	case PORT_F:
+	case HPD_PORT_F:
 		return val & ICP_TC_HPD_LONG_DETECT(PORT_TC4);
 	default:
 		return false;
 	}
 }
 
-static bool spt_port_hotplug2_long_detect(enum port port, u32 val)
+static bool spt_port_hotplug2_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_E:
+	switch (pin) {
+	case HPD_PORT_E:
 		return val & PORTE_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool spt_port_hotplug_long_detect(enum port port, u32 val)
+static bool spt_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & PORTA_HOTPLUG_LONG_DETECT;
-	case PORT_B:
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool ilk_port_hotplug_long_detect(enum port port, u32 val)
+static bool ilk_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_A:
+	switch (pin) {
+	case HPD_PORT_A:
 		return val & DIGITAL_PORTA_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool pch_port_hotplug_long_detect(enum port port, u32 val)
+static bool pch_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_B:
+	switch (pin) {
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_LONG_DETECT;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_LONG_DETECT;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_LONG_DETECT;
 	default:
 		return false;
 	}
 }
 
-static bool i9xx_port_hotplug_long_detect(enum port port, u32 val)
+static bool i9xx_port_hotplug_long_detect(enum hpd_pin pin, u32 val)
 {
-	switch (port) {
-	case PORT_B:
+	switch (pin) {
+	case HPD_PORT_B:
 		return val & PORTB_HOTPLUG_INT_LONG_PULSE;
-	case PORT_C:
+	case HPD_PORT_C:
 		return val & PORTC_HOTPLUG_INT_LONG_PULSE;
-	case PORT_D:
+	case HPD_PORT_D:
 		return val & PORTD_HOTPLUG_INT_LONG_PULSE;
 	default:
 		return false;
@@ -1709,9 +1709,8 @@ static void intel_get_hpd_pins(struct drm_i915_private *dev_priv,
 			       u32 *pin_mask, u32 *long_mask,
 			       u32 hotplug_trigger, u32 dig_hotplug_reg,
 			       const u32 hpd[HPD_NUM_PINS],
-			       bool long_pulse_detect(enum port port, u32 val))
+			       bool long_pulse_detect(enum hpd_pin pin, u32 val))
 {
-	enum port port;
 	enum hpd_pin pin;
 
 	for_each_hpd_pin(pin) {
@@ -1720,11 +1719,7 @@ static void intel_get_hpd_pins(struct drm_i915_private *dev_priv,
 
 		*pin_mask |= BIT(pin);
 
-		port = intel_hpd_pin_to_port(dev_priv, pin);
-		if (port == PORT_NONE)
-			continue;
-
-		if (long_pulse_detect(port, dig_hotplug_reg))
+		if (long_pulse_detect(pin, dig_hotplug_reg))
 			*long_mask |= BIT(pin);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_hotplug.c b/drivers/gpu/drm/i915/intel_hotplug.c
index d9d61d11dd2b..648a13c6043c 100644
--- a/drivers/gpu/drm/i915/intel_hotplug.c
+++ b/drivers/gpu/drm/i915/intel_hotplug.c
@@ -76,37 +76,6 @@
  * it will use i915_hotplug_work_func where this logic is handled.
  */
 
-/**
- * intel_hpd_port - return port hard associated with certain pin.
- * @dev_priv: private driver data pointer
- * @pin: the hpd pin to get associated port
- *
- * Return port that is associatade with @pin and PORT_NONE if no port is
- * hard associated with that @pin.
- */
-enum port intel_hpd_pin_to_port(struct drm_i915_private *dev_priv,
-				enum hpd_pin pin)
-{
-	switch (pin) {
-	case HPD_PORT_A:
-		return PORT_A;
-	case HPD_PORT_B:
-		return PORT_B;
-	case HPD_PORT_C:
-		return PORT_C;
-	case HPD_PORT_D:
-		return PORT_D;
-	case HPD_PORT_E:
-		if (IS_CNL_WITH_PORT_F(dev_priv))
-			return PORT_F;
-		return PORT_E;
-	case HPD_PORT_F:
-		return PORT_F;
-	default:
-		return PORT_NONE; /* no port for this pin */
-	}
-}
-
 /**
  * intel_hpd_pin_default - return default pin associated with certain port.
  * @dev_priv: private driver data pointer
-- 
cgit v1.2.3


From f88f047812c5977636a5c2ebb9c0b05fe788acf3 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Thu, 5 Jul 2018 19:43:57 +0300
Subject: drm/i915: Print the long_mask alongside the pin_mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're printing out which pins got a hotplug, so why not also print
out which pins detected the long pulse as opposed to a short pulse.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705164357.28512-9-ville.syrjala@linux.intel.com
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/i915_irq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6d80eb6b8998..6975a169c4e4 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1723,8 +1723,8 @@ static void intel_get_hpd_pins(struct drm_i915_private *dev_priv,
 			*long_mask |= BIT(pin);
 	}
 
-	DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x\n",
-			 hotplug_trigger, dig_hotplug_reg, *pin_mask);
+	DRM_DEBUG_DRIVER("hotplug event received, stat 0x%08x, dig 0x%08x, pins 0x%08x, long 0x%08x\n",
+			 hotplug_trigger, dig_hotplug_reg, *pin_mask, *long_mask);
 
 }
 
-- 
cgit v1.2.3


From b8110a87b75f948d978c06e130cc68026645c4a1 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 13 Jul 2018 18:05:57 +0300
Subject: ASoC: qdsp6: q6afe-dai: fix a range check in
 of_q6afe_parse_dai_data()

The main thing is that the data->priv[] array has AFE_PORT_MAX elements
so the > condition should be >=.  But we may as well check for negative
values as well just to be safe.

Fixes: 24c4cbcfac09 ("ASoC: qdsp6: q6afe: Add q6afe dai driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe-dai.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index a373ca5523ff..9ba95956ada8 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -1183,7 +1183,7 @@ static void of_q6afe_parse_dai_data(struct device *dev,
 		int id, i, num_lines;
 
 		ret = of_property_read_u32(node, "reg", &id);
-		if (ret || id > AFE_PORT_MAX) {
+		if (ret || id < 0 || id >= AFE_PORT_MAX) {
 			dev_err(dev, "valid dai id not found:%d\n", ret);
 			continue;
 		}
-- 
cgit v1.2.3


From 090345ce7265dd111299e3a63cdc79c3ef924481 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 13 Jul 2018 18:11:04 +0300
Subject: ASoC: qdsp6: q6routing: off by one in routing_hw_params()

The data->port_data[] array has AFE_MAX_PORTS elements so the check
should be >= instead of > or we write one element beyond the end of the
array.

Fixes: e3a33673e845 ("ASoC: qdsp6: q6routing: Add q6routing driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6routing.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index 593f66b8622f..7a19d6278406 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -899,7 +899,7 @@ static int routing_hw_params(struct snd_pcm_substream *substream,
 	else
 		path_type = ADM_PATH_LIVE_REC;
 
-	if (be_id > AFE_MAX_PORTS)
+	if (be_id >= AFE_MAX_PORTS)
 		return -EINVAL;
 
 	session = &data->port_data[be_id];
-- 
cgit v1.2.3


From 90a460d5dd205b1b39dae3dad041a37cf7c4241d Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Fri, 13 Jul 2018 11:34:44 -0400
Subject: drm: Fix kerneldoc for DRM_MODE_PROP_IMMUTABLE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Noticed this while browsing the docs.

Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180713153444.95466-1-seanpaul@chromium.org
---
 include/drm/drm_property.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/drm/drm_property.h b/include/drm/drm_property.h
index 1d5c0b2a8956..c030f6ccab99 100644
--- a/include/drm/drm_property.h
+++ b/include/drm/drm_property.h
@@ -147,10 +147,10 @@ struct drm_property {
 	 *     properties are not exposed to legacy userspace.
 	 *
 	 * DRM_MODE_PROP_IMMUTABLE
-	 *     Set for properties where userspace cannot be changed by
+	 *     Set for properties whose values cannot be changed by
 	 *     userspace. The kernel is allowed to update the value of these
 	 *     properties. This is generally used to expose probe state to
-	 *     usersapce, e.g. the EDID, or the connector path property on DP
+	 *     userspace, e.g. the EDID, or the connector path property on DP
 	 *     MST sinks.
 	 */
 	uint32_t flags;
-- 
cgit v1.2.3


From 811e299f4645588cc7a1b78d97b6847c155324b9 Mon Sep 17 00:00:00 2001
From: Romuald CARI <romuald.cari@devialet.com>
Date: Thu, 7 Jun 2018 16:08:02 +0200
Subject: ieee802154: add rx LQI from userspace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Link Quality Indication data exposed by drivers could not be accessed from
userspace. Since this data is per-datagram received, it makes sense to make it
available to userspace application through the ancillary data mechanism in
recvmsg rather than through ioctls. This can be activated using the socket
option WPAN_WANTLQI under SOL_IEEE802154 protocol.

This LQI data is available in the ancillary data buffer under the SOL_IEEE802154
level as the type WPAN_LQI. The value is an unsigned byte indicating the link
quality with values ranging 0-255.

Signed-off-by: Romuald Cari <romuald.cari@devialet.com>
Signed-off-by: Clément Peron <clement.peron@devialet.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 include/net/af_ieee802154.h |  1 +
 net/ieee802154/socket.c     | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/net/af_ieee802154.h b/include/net/af_ieee802154.h
index a5563d27a3eb..8003a9f6eb43 100644
--- a/include/net/af_ieee802154.h
+++ b/include/net/af_ieee802154.h
@@ -56,6 +56,7 @@ struct sockaddr_ieee802154 {
 #define WPAN_WANTACK		0
 #define WPAN_SECURITY		1
 #define WPAN_SECURITY_LEVEL	2
+#define WPAN_WANTLQI		3
 
 #define WPAN_SECURITY_DEFAULT	0
 #define WPAN_SECURITY_OFF	1
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index a60658c85a9a..bc6b912603f1 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -25,6 +25,7 @@
 #include <linux/termios.h>	/* For TIOCOUTQ/INQ */
 #include <linux/list.h>
 #include <linux/slab.h>
+#include <linux/socket.h>
 #include <net/datalink.h>
 #include <net/psnap.h>
 #include <net/sock.h>
@@ -452,6 +453,7 @@ struct dgram_sock {
 	unsigned int bound:1;
 	unsigned int connected:1;
 	unsigned int want_ack:1;
+	unsigned int want_lqi:1;
 	unsigned int secen:1;
 	unsigned int secen_override:1;
 	unsigned int seclevel:3;
@@ -486,6 +488,7 @@ static int dgram_init(struct sock *sk)
 	struct dgram_sock *ro = dgram_sk(sk);
 
 	ro->want_ack = 1;
+	ro->want_lqi = 0;
 	return 0;
 }
 
@@ -713,6 +716,7 @@ static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	size_t copied = 0;
 	int err = -EOPNOTSUPP;
 	struct sk_buff *skb;
+	struct dgram_sock *ro = dgram_sk(sk);
 	DECLARE_SOCKADDR(struct sockaddr_ieee802154 *, saddr, msg->msg_name);
 
 	skb = skb_recv_datagram(sk, flags, noblock, &err);
@@ -744,6 +748,13 @@ static int dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		*addr_len = sizeof(*saddr);
 	}
 
+	if (ro->want_lqi) {
+		err = put_cmsg(msg, SOL_IEEE802154, WPAN_WANTLQI,
+			       sizeof(uint8_t), &(mac_cb(skb)->lqi));
+		if (err)
+			goto done;
+	}
+
 	if (flags & MSG_TRUNC)
 		copied = skb->len;
 done:
@@ -847,6 +858,9 @@ static int dgram_getsockopt(struct sock *sk, int level, int optname,
 	case WPAN_WANTACK:
 		val = ro->want_ack;
 		break;
+	case WPAN_WANTLQI:
+		val = ro->want_lqi;
+		break;
 	case WPAN_SECURITY:
 		if (!ro->secen_override)
 			val = WPAN_SECURITY_DEFAULT;
@@ -892,6 +906,9 @@ static int dgram_setsockopt(struct sock *sk, int level, int optname,
 	case WPAN_WANTACK:
 		ro->want_ack = !!val;
 		break;
+	case WPAN_WANTLQI:
+		ro->want_lqi = !!val;
+		break;
 	case WPAN_SECURITY:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN) &&
 		    !ns_capable(net->user_ns, CAP_NET_RAW)) {
-- 
cgit v1.2.3


From ce6058039bca7f1f11f1723549eec1bc069dcb28 Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 10 Jul 2018 14:18:54 +0100
Subject: drm/arm/malidp: Add modifier definitions for describing Arm
 Framebuffer Compression (AFBC).

AFBC is a proprietary lossless image compression protocol and format.
It provides fine-grained random access and minimizes the amount of data
transferred between IP blocks.
AFBC has several features which may be supported and/or used, which are
represented using bits in the modifier. Not all combinations are valid,
and different devices or use-cases may support different combinations.

Changes from v2:-
- Added ack by Maarten Lankhorst

Signed-off-by: Rosen Zhelev <rosen.zhelev@arm.com>
Signed-off-by: Ayan Kumar halder <ayan.halder@arm.com>
Reviewed-by: Brian Starkey <brian.starkey@arm.com>
Reviewed-by: Liviu Dudau <liviu.dudau@arm.com>
Reviewed-by: James (Qian) Wang <james.qian.wang@arm.com>
Acked-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://lkml.org/lkml/2018/7/10/360
---
 include/uapi/drm/drm_fourcc.h | 83 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)

diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index d5e52350a3aa..d43949b5bb3e 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -183,6 +183,7 @@ extern "C" {
 #define DRM_FORMAT_MOD_VENDOR_QCOM    0x05
 #define DRM_FORMAT_MOD_VENDOR_VIVANTE 0x06
 #define DRM_FORMAT_MOD_VENDOR_BROADCOM 0x07
+#define DRM_FORMAT_MOD_VENDOR_ARM     0x08
 /* add more to the end as needed */
 
 #define DRM_FORMAT_RESERVED	      ((1ULL << 56) - 1)
@@ -485,6 +486,88 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_BROADCOM_UIF fourcc_mod_code(BROADCOM, 6)
 
+/*
+ * Arm Framebuffer Compression (AFBC) modifiers
+ *
+ * AFBC is a proprietary lossless image compression protocol and format.
+ * It provides fine-grained random access and minimizes the amount of data
+ * transferred between IP blocks.
+ *
+ * AFBC has several features which may be supported and/or used, which are
+ * represented using bits in the modifier. Not all combinations are valid,
+ * and different devices or use-cases may support different combinations.
+ */
+#define DRM_FORMAT_MOD_ARM_AFBC(__afbc_mode)	fourcc_mod_code(ARM, __afbc_mode)
+
+/*
+ * AFBC superblock size
+ *
+ * Indicates the superblock size(s) used for the AFBC buffer. The buffer
+ * size (in pixels) must be aligned to a multiple of the superblock size.
+ * Four lowest significant bits(LSBs) are reserved for block size.
+ */
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_MASK      0xf
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_16x16     (1ULL)
+#define AFBC_FORMAT_MOD_BLOCK_SIZE_32x8      (2ULL)
+
+/*
+ * AFBC lossless colorspace transform
+ *
+ * Indicates that the buffer makes use of the AFBC lossless colorspace
+ * transform.
+ */
+#define AFBC_FORMAT_MOD_YTR     (1ULL <<  4)
+
+/*
+ * AFBC block-split
+ *
+ * Indicates that the payload of each superblock is split. The second
+ * half of the payload is positioned at a predefined offset from the start
+ * of the superblock payload.
+ */
+#define AFBC_FORMAT_MOD_SPLIT   (1ULL <<  5)
+
+/*
+ * AFBC sparse layout
+ *
+ * This flag indicates that the payload of each superblock must be stored at a
+ * predefined position relative to the other superblocks in the same AFBC
+ * buffer. This order is the same order used by the header buffer. In this mode
+ * each superblock is given the same amount of space as an uncompressed
+ * superblock of the particular format would require, rounding up to the next
+ * multiple of 128 bytes in size.
+ */
+#define AFBC_FORMAT_MOD_SPARSE  (1ULL <<  6)
+
+/*
+ * AFBC copy-block restrict
+ *
+ * Buffers with this flag must obey the copy-block restriction. The restriction
+ * is such that there are no copy-blocks referring across the border of 8x8
+ * blocks. For the subsampled data the 8x8 limitation is also subsampled.
+ */
+#define AFBC_FORMAT_MOD_CBR     (1ULL <<  7)
+
+/*
+ * AFBC tiled layout
+ *
+ * The tiled layout groups superblocks in 8x8 or 4x4 tiles, where all
+ * superblocks inside a tile are stored together in memory. 8x8 tiles are used
+ * for pixel formats up to and including 32 bpp while 4x4 tiles are used for
+ * larger bpp formats. The order between the tiles is scan line.
+ * When the tiled layout is used, the buffer size (in pixels) must be aligned
+ * to the tile size.
+ */
+#define AFBC_FORMAT_MOD_TILED   (1ULL <<  8)
+
+/*
+ * AFBC solid color blocks
+ *
+ * Indicates that the buffer makes use of solid-color blocks, whereby bandwidth
+ * can be reduced if a whole superblock is a single color.
+ */
+#define AFBC_FORMAT_MOD_SC      (1ULL <<  9)
+
 #if defined(__cplusplus)
 }
 #endif
-- 
cgit v1.2.3


From 3479fc248bf383549ff629c607df0486813e14fd Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:02 +0200
Subject: drm: move drv test macros out of drmP.h

Last bit the prevented us from starting to delete the drmP.h monster
includes from source files!

Also add kernel-doc while moving them.

A nice consistent drm_dev_ prefix would be cute for these, but since
they're used everywhere I've figured I'll leave this bikeshed aside
for now.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-2-daniel.vetter@ffwll.ch
---
 include/drm/drmP.h    | 19 -------------------
 include/drm/drm_drv.h | 29 +++++++++++++++++++++++++++++
 2 files changed, 29 insertions(+), 19 deletions(-)

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index c5dfbdb7271d..f7a19c2a7a80 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -102,25 +102,6 @@ struct pci_controller;
 #define DRM_SWITCH_POWER_CHANGING 2
 #define DRM_SWITCH_POWER_DYNAMIC_OFF 3
 
-static inline bool drm_core_check_feature(struct drm_device *dev, int feature)
-{
-	return dev->driver->driver_features & feature;
-}
-
-/**
- * drm_drv_uses_atomic_modeset - check if the driver implements
- * atomic_commit()
- * @dev: DRM device
- *
- * This check is useful if drivers do not have DRIVER_ATOMIC set but
- * have atomic modesetting internally implemented.
- */
-static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev)
-{
-	return drm_core_check_feature(dev, DRIVER_ATOMIC) ||
-		dev->mode_config.funcs->atomic_commit != NULL;
-}
-
 /* returns true if currently okay to sleep */
 static inline bool drm_can_sleep(void)
 {
diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
index 7e545f5f94d3..46a8009784df 100644
--- a/include/drm/drm_drv.h
+++ b/include/drm/drm_drv.h
@@ -649,6 +649,35 @@ static inline bool drm_dev_is_unplugged(struct drm_device *dev)
 	return true;
 }
 
+/**
+ * drm_core_check_feature - check driver feature flags
+ * @dev: DRM device to check
+ * @feature: feature flag
+ *
+ * This checks @dev for driver features, see &drm_driver.driver_features and the
+ * various DRIVER_\* flags.
+ *
+ * Returns true if the @feature is supported, false otherwise.
+ */
+static inline bool drm_core_check_feature(struct drm_device *dev, int feature)
+{
+	return dev->driver->driver_features & feature;
+}
+
+/**
+ * drm_drv_uses_atomic_modeset - check if the driver implements
+ * atomic_commit()
+ * @dev: DRM device
+ *
+ * This check is useful if drivers do not have DRIVER_ATOMIC set but
+ * have atomic modesetting internally implemented.
+ */
+static inline bool drm_drv_uses_atomic_modeset(struct drm_device *dev)
+{
+	return drm_core_check_feature(dev, DRIVER_ATOMIC) ||
+		dev->mode_config.funcs->atomic_commit != NULL;
+}
+
 
 int drm_dev_set_unique(struct drm_device *dev, const char *name);
 
-- 
cgit v1.2.3


From aab999a66e4bc448a439733d60c83c86bee4c2be Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:04 +0200
Subject: drm/doc: switch drm_connector_state to inline comments

For consistency. Also spelled out the docs for ->best_encoder a bit
more while at it.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-4-daniel.vetter@ffwll.ch
---
 include/drm/drm_connector.h | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index a5179eb9e56f..99fd75d7a3a9 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -378,12 +378,9 @@ struct drm_tv_connector_state {
 
 /**
  * struct drm_connector_state - mutable connector state
- * @connector: backpointer to the connector
- * @best_encoder: can be used by helpers and drivers to select the encoder
- * @state: backpointer to global drm_atomic_state
- * @tv: TV connector state
  */
 struct drm_connector_state {
+	/** @connector: backpointer to the connector */
 	struct drm_connector *connector;
 
 	/**
@@ -394,6 +391,13 @@ struct drm_connector_state {
 	 */
 	struct drm_crtc *crtc;
 
+	/**
+	 * @best_encoder:
+	 *
+	 * Used by the atomic helpers to select the encoder, through the
+	 * &drm_connector_helper_funcs.atomic_best_encoder or
+	 * &drm_connector_helper_funcs.best_encoder callbacks.
+	 */
 	struct drm_encoder *best_encoder;
 
 	/**
@@ -402,6 +406,7 @@ struct drm_connector_state {
 	 */
 	enum drm_link_status link_status;
 
+	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
 
 	/**
@@ -411,6 +416,7 @@ struct drm_connector_state {
 	 */
 	struct drm_crtc_commit *commit;
 
+	/** @tv: TV connector state */
 	struct drm_tv_connector_state tv;
 
 	/**
-- 
cgit v1.2.3


From 92e1d26324e095252f3baf2c953615715c7c2a89 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:05 +0200
Subject: drm/doc: polish for sturct drm_connector

- switch everything over to inline comments
- add notes about locking, links to functions and other related stuff
- also include a note about Ville's soon-to-be-merged
  drm_connector_for_each_possible_encoder().

Also check that all the hyperlinks in drm_connector.h work and fix
them as needed.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-5-daniel.vetter@ffwll.ch
---
 include/drm/drm_connector.h | 191 ++++++++++++++++++++++++++++----------------
 1 file changed, 120 insertions(+), 71 deletions(-)

diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index 99fd75d7a3a9..e09e16b3e054 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -561,8 +561,7 @@ struct drm_connector_funcs {
 	 * received for this output connector->edid must be NULL.
 	 *
 	 * Drivers using the probe helpers should use
-	 * drm_helper_probe_single_connector_modes() or
-	 * drm_helper_probe_single_connector_modes_nomerge() to implement this
+	 * drm_helper_probe_single_connector_modes() to implement this
 	 * function.
 	 *
 	 * RETURNS:
@@ -773,45 +772,6 @@ struct drm_cmdline_mode {
 
 /**
  * struct drm_connector - central DRM connector control structure
- * @dev: parent DRM device
- * @kdev: kernel device for sysfs attributes
- * @attr: sysfs attributes
- * @head: list management
- * @base: base KMS object
- * @name: human readable name, can be overwritten by the driver
- * @connector_type: one of the DRM_MODE_CONNECTOR_<foo> types from drm_mode.h
- * @connector_type_id: index into connector type enum
- * @interlace_allowed: can this connector handle interlaced modes?
- * @doublescan_allowed: can this connector handle doublescan?
- * @stereo_allowed: can this connector handle stereo modes?
- * @funcs: connector control functions
- * @edid_blob_ptr: DRM property containing EDID if present
- * @properties: property tracking for this connector
- * @dpms: current dpms state
- * @helper_private: mid-layer private data
- * @cmdline_mode: mode line parsed from the kernel cmdline for this connector
- * @force: a DRM_FORCE_<foo> state for forced mode sets
- * @override_edid: has the EDID been overwritten through debugfs for testing?
- * @encoder_ids: valid encoders for this connector
- * @eld: EDID-like data, if present
- * @latency_present: AV delay info from ELD, if found
- * @video_latency: video latency info from ELD, if found
- * @audio_latency: audio latency info from ELD, if found
- * @null_edid_counter: track sinks that give us all zeros for the EDID
- * @bad_edid_counter: track sinks that give us an EDID with invalid checksum
- * @edid_corrupt: indicates whether the last read EDID was corrupt
- * @debugfs_entry: debugfs directory for this connector
- * @has_tile: is this connector connected to a tiled monitor
- * @tile_group: tile group for the connected monitor
- * @tile_is_single_monitor: whether the tile is one monitor housing
- * @num_h_tile: number of horizontal tiles in the tile group
- * @num_v_tile: number of vertical tiles in the tile group
- * @tile_h_loc: horizontal location of this tile
- * @tile_v_loc: vertical location of this tile
- * @tile_h_size: horizontal size of this tile.
- * @tile_v_size: vertical size of this tile.
- * @scaling_mode_property:  Optional atomic property to control the upscaling.
- * @content_protection_property: Optional property to control content protection
  *
  * Each connector may be connected to one or more CRTCs, or may be clonable by
  * another connector if they can share a CRTC.  Each connector also has a specific
@@ -819,13 +779,27 @@ struct drm_cmdline_mode {
  * span multiple monitors).
  */
 struct drm_connector {
+	/** @dev: parent DRM device */
 	struct drm_device *dev;
+	/** @kdev: kernel device for sysfs attributes */
 	struct device *kdev;
+	/** @attr: sysfs attributes */
 	struct device_attribute *attr;
+
+	/**
+	 * @head:
+	 *
+	 * List of all connectors on a @dev, linked from
+	 * &drm_mode_config.connector_list. Protected by
+	 * &drm_mode_config.connector_list_lock, but please only use
+	 * &drm_connector_list_iter to walk this list.
+	 */
 	struct list_head head;
 
+	/** @base: base KMS object */
 	struct drm_mode_object base;
 
+	/** @name: human readable name, can be overwritten by the driver */
 	char *name;
 
 	/**
@@ -843,10 +817,30 @@ struct drm_connector {
 	 */
 	unsigned index;
 
+	/**
+	 * @connector_type:
+	 * one of the DRM_MODE_CONNECTOR_<foo> types from drm_mode.h
+	 */
 	int connector_type;
+	/** @connector_type_id: index into connector type enum */
 	int connector_type_id;
+	/**
+	 * @interlace_allowed:
+	 * Can this connector handle interlaced modes? Only used by
+	 * drm_helper_probe_single_connector_modes() for mode filtering.
+	 */
 	bool interlace_allowed;
+	/**
+	 * @doublescan_allowed:
+	 * Can this connector handle doublescan? Only used by
+	 * drm_helper_probe_single_connector_modes() for mode filtering.
+	 */
 	bool doublescan_allowed;
+	/**
+	 * @stereo_allowed:
+	 * Can this connector handle stereo modes? Only used by
+	 * drm_helper_probe_single_connector_modes() for mode filtering.
+	 */
 	bool stereo_allowed;
 
 	/**
@@ -895,45 +889,42 @@ struct drm_connector {
 	 * Protected by &drm_mode_config.mutex.
 	 */
 	struct drm_display_info display_info;
+
+	/** @funcs: connector control functions */
 	const struct drm_connector_funcs *funcs;
 
+	/**
+	 * @edid_blob_ptr: DRM property containing EDID if present. Protected by
+	 * &drm_mode_config.mutex. This should be updated only by calling
+	 * drm_mode_connector_update_edid_property().
+	 */
 	struct drm_property_blob *edid_blob_ptr;
+
+	/** @properties: property tracking for this connector */
 	struct drm_object_properties properties;
 
+	/**
+	 * @scaling_mode_property: Optional atomic property to control the
+	 * upscaling. See drm_connector_attach_content_protection_property().
+	 */
 	struct drm_property *scaling_mode_property;
 
 	/**
 	 * @content_protection_property: DRM ENUM property for content
-	 * protection
+	 * protection. See drm_connector_attach_content_protection_property().
 	 */
 	struct drm_property *content_protection_property;
 
 	/**
 	 * @path_blob_ptr:
 	 *
-	 * DRM blob property data for the DP MST path property.
+	 * DRM blob property data for the DP MST path property. This should only
+	 * be updated by calling drm_mode_connector_set_path_property().
 	 */
 	struct drm_property_blob *path_blob_ptr;
 
-	/**
-	 * @tile_blob_ptr:
-	 *
-	 * DRM blob property data for the tile property (used mostly by DP MST).
-	 * This is meant for screens which are driven through separate display
-	 * pipelines represented by &drm_crtc, which might not be running with
-	 * genlocked clocks. For tiled panels which are genlocked, like
-	 * dual-link LVDS or dual-link DSI, the driver should try to not expose
-	 * the tiling and virtualize both &drm_crtc and &drm_plane if needed.
-	 */
-	struct drm_property_blob *tile_blob_ptr;
-
-/* should we poll this connector for connects and disconnects */
-/* hot plug detectable */
 #define DRM_CONNECTOR_POLL_HPD (1 << 0)
-/* poll for connections */
 #define DRM_CONNECTOR_POLL_CONNECT (1 << 1)
-/* can cleanly poll for disconnections without flickering the screen */
-/* DACs should rarely do this without a lot of testing */
 #define DRM_CONNECTOR_POLL_DISCONNECT (1 << 2)
 
 	/**
@@ -950,25 +941,40 @@ struct drm_connector {
 	 *     Periodically poll the connector for connection.
 	 *
 	 * DRM_CONNECTOR_POLL_DISCONNECT
-	 *     Periodically poll the connector for disconnection.
+	 *     Periodically poll the connector for disconnection, without
+	 *     causing flickering even when the connector is in use. DACs should
+	 *     rarely do this without a lot of testing.
 	 *
 	 * Set to 0 for connectors that don't support connection status
 	 * discovery.
 	 */
 	uint8_t polled;
 
-	/* requested DPMS state */
+	/**
+	 * @dpms: Current dpms state. For legacy drivers the
+	 * &drm_connector_funcs.dpms callback must update this. For atomic
+	 * drivers, this is handled by the core atomic code, and drivers must
+	 * only take &drm_crtc_state.active into account.
+	 */
 	int dpms;
 
+	/** @helper_private: mid-layer private data */
 	const struct drm_connector_helper_funcs *helper_private;
 
-	/* forced on connector */
+	/** @cmdline_mode: mode line parsed from the kernel cmdline for this connector */
 	struct drm_cmdline_mode cmdline_mode;
+	/** @force: a DRM_FORCE_<foo> state for forced mode sets */
 	enum drm_connector_force force;
+	/** @override_edid: has the EDID been overwritten through debugfs for testing? */
 	bool override_edid;
 
 #define DRM_CONNECTOR_MAX_ENCODER 3
+	/**
+	 * @encoder_ids: Valid encoders for this connector. Please only use
+	 * drm_connector_for_each_possible_encoder() to enumerate these.
+	 */
 	uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER];
+
 	/**
 	 * @encoder: Currently bound encoder driving this connector, if any.
 	 * Only really meaningful for non-atomic drivers. Atomic drivers should
@@ -978,19 +984,37 @@ struct drm_connector {
 	struct drm_encoder *encoder;
 
 #define MAX_ELD_BYTES	128
-	/* EDID bits */
+	/** @eld: EDID-like data, if present */
 	uint8_t eld[MAX_ELD_BYTES];
+	/** @latency_present: AV delay info from ELD, if found */
 	bool latency_present[2];
-	int video_latency[2];	/* [0]: progressive, [1]: interlaced */
+	/**
+	 * @video_latency: Video latency info from ELD, if found.
+	 * [0]: progressive, [1]: interlaced
+	 */
+	int video_latency[2];
+	/**
+	 * @audio_latency: audio latency info from ELD, if found
+	 * [0]: progressive, [1]: interlaced
+	 */
 	int audio_latency[2];
-	int null_edid_counter; /* needed to workaround some HW bugs where we get all 0s */
+	/**
+	 * @null_edid_counter: track sinks that give us all zeros for the EDID.
+	 * Needed to workaround some HW bugs where we get all 0s
+	 */
+	int null_edid_counter;
+
+	/** @bad_edid_counter: track sinks that give us an EDID with invalid checksum */
 	unsigned bad_edid_counter;
 
-	/* Flag for raw EDID header corruption - used in Displayport
-	 * compliance testing - * Displayport Link CTS Core 1.2 rev1.1 4.2.2.6
+	/**
+	 * @edid_corrupt: Indicates whether the last read EDID was corrupt. Used
+	 * in Displayport compliance testing - Displayport Link CTS Core 1.2
+	 * rev1.1 4.2.2.6
 	 */
 	bool edid_corrupt;
 
+	/** @debugfs_entry: debugfs directory for this connector */
 	struct dentry *debugfs_entry;
 
 	/**
@@ -998,7 +1022,7 @@ struct drm_connector {
 	 *
 	 * Current atomic state for this connector.
 	 *
-	 * This is protected by @drm_mode_config.connection_mutex. Note that
+	 * This is protected by &drm_mode_config.connection_mutex. Note that
 	 * nonblocking atomic commits access the current connector state without
 	 * taking locks. Either by going through the &struct drm_atomic_state
 	 * pointers, see for_each_oldnew_connector_in_state(),
@@ -1009,19 +1033,44 @@ struct drm_connector {
 	 */
 	struct drm_connector_state *state;
 
-	/* DisplayID bits */
+	/* DisplayID bits. FIXME: Extract into a substruct? */
+
+	/**
+	 * @tile_blob_ptr:
+	 *
+	 * DRM blob property data for the tile property (used mostly by DP MST).
+	 * This is meant for screens which are driven through separate display
+	 * pipelines represented by &drm_crtc, which might not be running with
+	 * genlocked clocks. For tiled panels which are genlocked, like
+	 * dual-link LVDS or dual-link DSI, the driver should try to not expose
+	 * the tiling and virtualize both &drm_crtc and &drm_plane if needed.
+	 *
+	 * This should only be updated by calling
+	 * drm_mode_connector_set_tile_property().
+	 */
+	struct drm_property_blob *tile_blob_ptr;
+
+	/** @has_tile: is this connector connected to a tiled monitor */
 	bool has_tile;
+	/** @tile_group: tile group for the connected monitor */
 	struct drm_tile_group *tile_group;
+	/** @tile_is_single_monitor: whether the tile is one monitor housing */
 	bool tile_is_single_monitor;
 
+	/** @num_h_tile: number of horizontal tiles in the tile group */
+	/** @num_v_tile: number of vertical tiles in the tile group */
 	uint8_t num_h_tile, num_v_tile;
+	/** @tile_h_loc: horizontal location of this tile */
+	/** @tile_v_loc: vertical location of this tile */
 	uint8_t tile_h_loc, tile_v_loc;
+	/** @tile_h_size: horizontal size of this tile. */
+	/** @tile_v_size: vertical size of this tile. */
 	uint16_t tile_h_size, tile_v_size;
 
 	/**
 	 * @free_node:
 	 *
-	 * List used only by &drm_connector_iter to be able to clean up a
+	 * List used only by &drm_connector_list_iter to be able to clean up a
 	 * connector from any context, in conjunction with
 	 * &drm_mode_config.connector_free_work.
 	 */
-- 
cgit v1.2.3


From c555f02371c338b06752577aebf738dbdb6907bd Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:06 +0200
Subject: drm: drop _mode_ from update_edit_property()

Just makes it longer, and for most things in drm_connector.[hc] we
just use the drm_connector_ prefix. Done with sed + a bit of manual
fixup for the indenting.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-6-daniel.vetter@ffwll.ch
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c              | 4 ++--
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c           | 4 ++--
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c | 4 ++--
 drivers/gpu/drm/ast/ast_mode.c                              | 4 ++--
 drivers/gpu/drm/bridge/adv7511/adv7511_drv.c                | 2 +-
 drivers/gpu/drm/bridge/analogix-anx78xx.c                   | 4 ++--
 drivers/gpu/drm/bridge/analogix/analogix_dp_core.c          | 4 ++--
 drivers/gpu/drm/bridge/dumb-vga-dac.c                       | 2 +-
 drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c    | 2 +-
 drivers/gpu/drm/bridge/nxp-ptn3460.c                        | 2 +-
 drivers/gpu/drm/bridge/sii902x.c                            | 2 +-
 drivers/gpu/drm/bridge/synopsys/dw-hdmi.c                   | 2 +-
 drivers/gpu/drm/bridge/tc358767.c                           | 2 +-
 drivers/gpu/drm/bridge/ti-tfp410.c                          | 2 +-
 drivers/gpu/drm/drm_connector.c                             | 8 ++++----
 drivers/gpu/drm/drm_debugfs.c                               | 4 ++--
 drivers/gpu/drm/drm_probe_helper.c                          | 2 +-
 drivers/gpu/drm/exynos/exynos_drm_vidi.c                    | 2 +-
 drivers/gpu/drm/exynos/exynos_hdmi.c                        | 2 +-
 drivers/gpu/drm/gma500/cdv_intel_dp.c                       | 2 +-
 drivers/gpu/drm/gma500/cdv_intel_hdmi.c                     | 2 +-
 drivers/gpu/drm/gma500/oaktrail_hdmi.c                      | 2 +-
 drivers/gpu/drm/gma500/oaktrail_lvds.c                      | 2 +-
 drivers/gpu/drm/gma500/psb_intel_modes.c                    | 2 +-
 drivers/gpu/drm/gma500/psb_intel_sdvo.c                     | 2 +-
 drivers/gpu/drm/i2c/tda998x_drv.c                           | 2 +-
 drivers/gpu/drm/i915/intel_dp.c                             | 2 +-
 drivers/gpu/drm/i915/intel_lvds.c                           | 2 +-
 drivers/gpu/drm/i915/intel_modes.c                          | 2 +-
 drivers/gpu/drm/i915/intel_sdvo.c                           | 2 +-
 drivers/gpu/drm/imx/imx-ldb.c                               | 2 +-
 drivers/gpu/drm/imx/imx-tve.c                               | 2 +-
 drivers/gpu/drm/imx/parallel-display.c                      | 2 +-
 drivers/gpu/drm/mediatek/mtk_hdmi.c                         | 2 +-
 drivers/gpu/drm/mgag200/mgag200_mode.c                      | 2 +-
 drivers/gpu/drm/msm/edp/edp_connector.c                     | 2 +-
 drivers/gpu/drm/msm/hdmi/hdmi_connector.c                   | 2 +-
 drivers/gpu/drm/nouveau/dispnv50/disp.c                     | 2 +-
 drivers/gpu/drm/nouveau/nouveau_connector.c                 | 8 ++++----
 drivers/gpu/drm/omapdrm/omap_connector.c                    | 4 ++--
 drivers/gpu/drm/panel/panel-simple.c                        | 2 +-
 drivers/gpu/drm/radeon/radeon_connectors.c                  | 4 ++--
 drivers/gpu/drm/radeon/radeon_dp_mst.c                      | 4 ++--
 drivers/gpu/drm/rockchip/cdn-dp-core.c                      | 2 +-
 drivers/gpu/drm/rockchip/inno_hdmi.c                        | 2 +-
 drivers/gpu/drm/sti/sti_hdmi.c                              | 2 +-
 drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c                      | 2 +-
 drivers/gpu/drm/tegra/output.c                              | 2 +-
 drivers/gpu/drm/tilcdc/tilcdc_tfp410.c                      | 2 +-
 drivers/gpu/drm/udl/udl_connector.c                         | 2 +-
 drivers/gpu/drm/vc4/vc4_hdmi.c                              | 2 +-
 drivers/gpu/drm/zte/zx_hdmi.c                               | 2 +-
 drivers/gpu/drm/zte/zx_vga.c                                | 2 +-
 drivers/staging/vboxvideo/vbox_mode.c                       | 2 +-
 include/drm/drm_connector.h                                 | 6 +++---
 include/drm/drm_modeset_helper_vtables.h                    | 2 +-
 56 files changed, 74 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
index 881f7cb7ae6e..c770d73352a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_connectors.c
@@ -334,11 +334,11 @@ static int amdgpu_connector_ddc_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (amdgpu_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, amdgpu_connector->edid);
+		drm_connector_update_edid_property(connector, amdgpu_connector->edid);
 		ret = drm_add_edid_modes(connector, amdgpu_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(connector, NULL);
+	drm_connector_update_edid_property(connector, NULL);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 66bd3cc3e387..c4ab19831344 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -900,14 +900,14 @@ amdgpu_dm_update_connector_after_detect(struct amdgpu_dm_connector *aconnector)
 				(struct edid *) sink->dc_edid.raw_edid;
 
 
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 					aconnector->edid);
 		}
 		amdgpu_dm_add_sink_to_freesync_module(connector, aconnector->edid);
 
 	} else {
 		amdgpu_dm_remove_sink_from_freesync_module(connector);
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		aconnector->num_modes = 0;
 		aconnector->dc_sink = NULL;
 		aconnector->edid = NULL;
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 4304d9e408b8..581bb75d08eb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -233,7 +233,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 		edid = drm_dp_mst_get_edid(connector, &aconnector->mst_port->mst_mgr, aconnector->port);
 
 		if (!edid) {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 				&aconnector->base,
 				NULL);
 			return ret;
@@ -261,7 +261,7 @@ static int dm_dp_mst_get_modes(struct drm_connector *connector)
 					connector, aconnector->edid);
 	}
 
-	drm_mode_connector_update_edid_property(
+	drm_connector_update_edid_property(
 					&aconnector->base, aconnector->edid);
 
 	ret = drm_add_edid_modes(connector, aconnector->edid);
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 036dff8a1f33..1bb8174ad155 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -790,12 +790,12 @@ static int ast_get_modes(struct drm_connector *connector)
 	if (!flags)
 		edid = drm_get_edid(connector, &ast_connector->i2c->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(&ast_connector->base, edid);
+		drm_connector_update_edid_property(&ast_connector->base, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 		return ret;
 	} else
-		drm_mode_connector_update_edid_property(&ast_connector->base, NULL);
+		drm_connector_update_edid_property(&ast_connector->base, NULL);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 73021b388e12..1f4745953aca 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -601,7 +601,7 @@ static int adv7511_get_modes(struct adv7511 *adv7511,
 		__adv7511_power_off(adv7511);
 
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	count = drm_add_edid_modes(connector, edid);
 
 	adv7511_set_config_csc(adv7511, connector, adv7511->rgb,
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c
index b49043866be6..37f947dcadec 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c
@@ -969,8 +969,8 @@ static int anx78xx_get_modes(struct drm_connector *connector)
 		goto unlock;
 	}
 
-	err = drm_mode_connector_update_edid_property(connector,
-						      anx78xx->edid);
+	err = drm_connector_update_edid_property(connector,
+						 anx78xx->edid);
 	if (err) {
 		DRM_ERROR("Failed to update EDID property: %d\n", err);
 		goto unlock;
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 2bcbfadb6ac5..288c015f7460 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1119,8 +1119,8 @@ static int analogix_dp_get_modes(struct drm_connector *connector)
 		edid = drm_get_edid(connector, &dp->aux.ddc);
 		pm_runtime_put(dp->dev);
 		if (edid) {
-			drm_mode_connector_update_edid_property(&dp->connector,
-								edid);
+			drm_connector_update_edid_property(&dp->connector,
+							   edid);
 			num_modes += drm_add_edid_modes(&dp->connector, edid);
 			kfree(edid);
 		}
diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c
index 9837c8d69e69..da99b8ba4ee1 100644
--- a/drivers/gpu/drm/bridge/dumb-vga-dac.c
+++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c
@@ -55,7 +55,7 @@ static int dumb_vga_get_modes(struct drm_connector *connector)
 		goto fallback;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 	return ret;
diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
index 7ccadba7c98c..b49b543bd1f6 100644
--- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
+++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
@@ -152,7 +152,7 @@ static int ge_b850v3_lvds_get_modes(struct drm_connector *connector)
 	ge_b850v3_lvds_ptr->edid = (struct edid *)stdp2690_get_edid(client);
 
 	if (ge_b850v3_lvds_ptr->edid) {
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 						      ge_b850v3_lvds_ptr->edid);
 		num_modes = drm_add_edid_modes(connector,
 					       ge_b850v3_lvds_ptr->edid);
diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c
index d64a3283822a..bd5c191858cb 100644
--- a/drivers/gpu/drm/bridge/nxp-ptn3460.c
+++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c
@@ -222,7 +222,7 @@ static int ptn3460_get_modes(struct drm_connector *connector)
 	}
 
 	ptn_bridge->edid = (struct edid *)edid;
-	drm_mode_connector_update_edid_property(connector, ptn_bridge->edid);
+	drm_connector_update_edid_property(connector, ptn_bridge->edid);
 
 	num_modes = drm_add_edid_modes(connector, ptn_bridge->edid);
 
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index 60373d7eb220..cd331933c230 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -170,7 +170,7 @@ static int sii902x_get_modes(struct drm_connector *connector)
 		return ret;
 
 	edid = drm_get_edid(connector, sii902x->i2c->adapter);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	if (edid) {
 		num = drm_add_edid_modes(connector, edid);
 		kfree(edid);
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index 3c136f2b954f..ab32aceb6f24 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1922,7 +1922,7 @@ static int dw_hdmi_connector_get_modes(struct drm_connector *connector)
 
 		hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 		hdmi->sink_has_audio = drm_detect_monitor_audio(edid);
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		cec_notifier_set_phys_addr_from_edid(hdmi->cec_notifier, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index 0fd9cf27542c..ee2fd0a349b3 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1140,7 +1140,7 @@ static int tc_connector_get_modes(struct drm_connector *connector)
 	if (!edid)
 		return 0;
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	count = drm_add_edid_modes(connector, edid);
 
 	return count;
diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c
index acb857030951..c81bf7910bbe 100644
--- a/drivers/gpu/drm/bridge/ti-tfp410.c
+++ b/drivers/gpu/drm/bridge/ti-tfp410.c
@@ -62,7 +62,7 @@ static int tfp410_get_modes(struct drm_connector *connector)
 		goto fallback;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	return drm_add_edid_modes(connector, edid);
 fallback:
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 5ada0640de5a..b2b182ffdbe9 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -814,7 +814,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * 	Blob property which contains the current EDID read from the sink. This
  * 	is useful to parse sink identification information like vendor, model
  * 	and serial. Drivers should update this property by calling
- * 	drm_mode_connector_update_edid_property(), usually after having parsed
+ * 	drm_connector_update_edid_property(), usually after having parsed
  * 	the EDID using drm_add_edid_modes(). Userspace cannot change this
  * 	property.
  * DPMS:
@@ -1497,7 +1497,7 @@ int drm_mode_connector_set_tile_property(struct drm_connector *connector)
 EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
 
 /**
- * drm_mode_connector_update_edid_property - update the edid property of a connector
+ * drm_connector_update_edid_property - update the edid property of a connector
  * @connector: drm connector
  * @edid: new value of the edid property
  *
@@ -1507,7 +1507,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_update_edid_property(struct drm_connector *connector,
+int drm_connector_update_edid_property(struct drm_connector *connector,
 					    const struct edid *edid)
 {
 	struct drm_device *dev = connector->dev;
@@ -1546,7 +1546,7 @@ int drm_mode_connector_update_edid_property(struct drm_connector *connector,
 	                                       dev->mode_config.edid_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_update_edid_property);
+EXPORT_SYMBOL(drm_connector_update_edid_property);
 
 /**
  * drm_mode_connector_set_link_status_property - Set link status property of a connector
diff --git a/drivers/gpu/drm/drm_debugfs.c b/drivers/gpu/drm/drm_debugfs.c
index 50a20bfc07ea..6f28fe58f169 100644
--- a/drivers/gpu/drm/drm_debugfs.c
+++ b/drivers/gpu/drm/drm_debugfs.c
@@ -314,13 +314,13 @@ static ssize_t edid_write(struct file *file, const char __user *ubuf,
 
 	if (len == 5 && !strncmp(buf, "reset", 5)) {
 		connector->override_edid = false;
-		ret = drm_mode_connector_update_edid_property(connector, NULL);
+		ret = drm_connector_update_edid_property(connector, NULL);
 	} else if (len < EDID_LENGTH ||
 		   EDID_LENGTH * (1 + edid->extensions) > len)
 		ret = -EINVAL;
 	else {
 		connector->override_edid = false;
-		ret = drm_mode_connector_update_edid_property(connector, edid);
+		ret = drm_connector_update_edid_property(connector, edid);
 		if (!ret)
 			connector->override_edid = true;
 	}
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 34fe2704a31c..3d58e0eb26a4 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -472,7 +472,7 @@ retry:
 	if (connector->status == connector_status_disconnected) {
 		DRM_DEBUG_KMS("[CONNECTOR:%d:%s] disconnected\n",
 			connector->base.id, connector->name);
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		verbose_prune = false;
 		goto prune;
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index e6b0940b1ac2..dfea61edba4a 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -319,7 +319,7 @@ static int vidi_get_modes(struct drm_connector *connector)
 		return -ENOMEM;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	return drm_add_edid_modes(connector, edid);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index db91932550cf..6672d0ff0423 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -888,7 +888,7 @@ static int hdmi_get_modes(struct drm_connector *connector)
 		(hdata->dvi_mode ? "dvi monitor" : "hdmi monitor"),
 		edid->width_cm, edid->height_cm);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	cec_notifier_set_phys_addr_from_edid(hdata->notifier, edid);
 
 	ret = drm_add_edid_modes(connector, edid);
diff --git a/drivers/gpu/drm/gma500/cdv_intel_dp.c b/drivers/gpu/drm/gma500/cdv_intel_dp.c
index 5ea785f07ba8..90ed20083009 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_dp.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_dp.c
@@ -1770,7 +1770,7 @@ static int cdv_intel_dp_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &intel_dp->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
index f0878998526a..4e4e4a66eaee 100644
--- a/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
+++ b/drivers/gpu/drm/gma500/cdv_intel_hdmi.c
@@ -216,7 +216,7 @@ static int cdv_hdmi_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &gma_encoder->i2c_bus->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/oaktrail_hdmi.c b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
index 78566a80ad25..c6d72de1c054 100644
--- a/drivers/gpu/drm/gma500/oaktrail_hdmi.c
+++ b/drivers/gpu/drm/gma500/oaktrail_hdmi.c
@@ -578,7 +578,7 @@ static int oaktrail_hdmi_get_modes(struct drm_connector *connector)
 	}
 
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 	}
 	return ret;
diff --git a/drivers/gpu/drm/gma500/oaktrail_lvds.c b/drivers/gpu/drm/gma500/oaktrail_lvds.c
index e6943fef0611..83babb815a5d 100644
--- a/drivers/gpu/drm/gma500/oaktrail_lvds.c
+++ b/drivers/gpu/drm/gma500/oaktrail_lvds.c
@@ -376,7 +376,7 @@ void oaktrail_lvds_init(struct drm_device *dev,
 	 * preferred mode is the right one.
 	 */
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		drm_add_edid_modes(connector, edid);
 		kfree(edid);
 
diff --git a/drivers/gpu/drm/gma500/psb_intel_modes.c b/drivers/gpu/drm/gma500/psb_intel_modes.c
index e5360726d80b..fb4da3cd6681 100644
--- a/drivers/gpu/drm/gma500/psb_intel_modes.c
+++ b/drivers/gpu/drm/gma500/psb_intel_modes.c
@@ -66,7 +66,7 @@ int psb_intel_ddc_get_modes(struct drm_connector *connector,
 
 	edid = drm_get_edid(connector, adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/gma500/psb_intel_sdvo.c b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
index 1d40746ab625..dd3cec0e3190 100644
--- a/drivers/gpu/drm/gma500/psb_intel_sdvo.c
+++ b/drivers/gpu/drm/gma500/psb_intel_sdvo.c
@@ -1472,7 +1472,7 @@ static void psb_intel_sdvo_get_ddc_modes(struct drm_connector *connector)
 		bool connector_is_digital = !!IS_TMDS(psb_intel_sdvo_connector);
 
 		if (connector_is_digital == monitor_is_digital) {
-			drm_mode_connector_update_edid_property(connector, edid);
+			drm_connector_update_edid_property(connector, edid);
 			drm_add_edid_modes(connector, edid);
 		}
 
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 0038c976536a..d434f576e6b2 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1243,7 +1243,7 @@ static int tda998x_connector_get_modes(struct drm_connector *connector)
 		return 0;
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	n = drm_add_edid_modes(connector, edid);
 
 	kfree(edid);
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index b021801dbd48..c8268f377602 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -6231,7 +6231,7 @@ static bool intel_edp_init_connector(struct intel_dp *intel_dp,
 	edid = drm_get_edid(connector, &intel_dp->aux.ddc);
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 		} else {
 			kfree(edid);
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index bb06744d28a4..ca55b0a82ba6 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -1131,7 +1131,7 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 				    intel_gmbus_get_adapter(dev_priv, pin));
 	if (edid) {
 		if (drm_add_edid_modes(connector, edid)) {
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 		} else {
 			kfree(edid);
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index b39846613e3c..ca44bf368e24 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -40,7 +40,7 @@ int intel_connector_update_modes(struct drm_connector *connector,
 {
 	int ret;
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 
 	return ret;
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index e6a64b3ecd91..a88611a73b03 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -1913,7 +1913,7 @@ static void intel_sdvo_get_ddc_modes(struct drm_connector *connector)
 	if (edid != NULL) {
 		if (intel_sdvo_connector_matches_edid(to_intel_sdvo_connector(connector),
 						      edid)) {
-			drm_mode_connector_update_edid_property(connector, edid);
+			drm_connector_update_edid_property(connector, edid);
 			drm_add_edid_modes(connector, edid);
 		}
 
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index 56dd7a9a8e25..ae81cbb75f51 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -143,7 +143,7 @@ static int imx_ldb_connector_get_modes(struct drm_connector *connector)
 		imx_ldb_ch->edid = drm_get_edid(connector, imx_ldb_ch->ddc);
 
 	if (imx_ldb_ch->edid) {
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 							imx_ldb_ch->edid);
 		num_modes = drm_add_edid_modes(connector, imx_ldb_ch->edid);
 	}
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index bc27c2699464..1a4ced5c09b5 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -235,7 +235,7 @@ static int imx_tve_connector_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, tve->ddc);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index aedecda9728a..4fc1cf583435 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -63,7 +63,7 @@ static int imx_pd_connector_get_modes(struct drm_connector *connector)
 	}
 
 	if (imxpd->edid) {
-		drm_mode_connector_update_edid_property(connector, imxpd->edid);
+		drm_connector_update_edid_property(connector, imxpd->edid);
 		num_modes = drm_add_edid_modes(connector, imxpd->edid);
 	}
 
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 59a11026dceb..835313940395 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1220,7 +1220,7 @@ static int mtk_hdmi_conn_get_modes(struct drm_connector *conn)
 
 	hdmi->dvi_mode = !drm_detect_monitor_audio(edid);
 
-	drm_mode_connector_update_edid_property(conn, edid);
+	drm_connector_update_edid_property(conn, edid);
 
 	ret = drm_add_edid_modes(conn, edid);
 	kfree(edid);
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 8918539a19aa..5f104f139197 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1553,7 +1553,7 @@ static int mga_vga_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, &mga_connector->i2c->adapter);
 	if (edid) {
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c
index 6f3fc6b0f0a3..0b5eac054195 100644
--- a/drivers/gpu/drm/msm/edp/edp_connector.c
+++ b/drivers/gpu/drm/msm/edp/edp_connector.c
@@ -56,7 +56,7 @@ static int edp_connector_get_modes(struct drm_connector *connector)
 	if (ret)
 		return ret;
 
-	drm_mode_connector_update_edid_property(connector, drm_edid);
+	drm_connector_update_edid_property(connector, drm_edid);
 	if (drm_edid)
 		ret = drm_add_edid_modes(connector, drm_edid);
 
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index c0848dfedd50..07feacc5a441 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -392,7 +392,7 @@ static int msm_hdmi_connector_get_modes(struct drm_connector *connector)
 	hdmi_write(hdmi, REG_HDMI_CTRL, hdmi_ctrl);
 
 	hdmi->hdmi_mode = drm_detect_hdmi_monitor(edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		ret = drm_add_edid_modes(connector, edid);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index b83465ae7c1b..2fabb69e452b 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -850,7 +850,7 @@ nv50_mstc_get_modes(struct drm_connector *connector)
 	int ret = 0;
 
 	mstc->edid = drm_dp_mst_get_edid(&mstc->connector, mstc->port->mgr, mstc->port);
-	drm_mode_connector_update_edid_property(&mstc->connector, mstc->edid);
+	drm_connector_update_edid_property(&mstc->connector, mstc->edid);
 	if (mstc->edid)
 		ret = drm_add_edid_modes(&mstc->connector, mstc->edid);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index bb46c1d489cf..22a15478d23d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -550,7 +550,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 
 	/* Cleanup the previous EDID block. */
 	if (nv_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		kfree(nv_connector->edid);
 		nv_connector->edid = NULL;
 	}
@@ -575,7 +575,7 @@ nouveau_connector_detect(struct drm_connector *connector, bool force)
 		else
 			nv_connector->edid = drm_get_edid(connector, i2c);
 
-		drm_mode_connector_update_edid_property(connector,
+		drm_connector_update_edid_property(connector,
 							nv_connector->edid);
 		if (!nv_connector->edid) {
 			NV_ERROR(drm, "DDC responded, but no EDID for %s\n",
@@ -657,7 +657,7 @@ nouveau_connector_detect_lvds(struct drm_connector *connector, bool force)
 
 	/* Cleanup the previous EDID block. */
 	if (nv_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, NULL);
+		drm_connector_update_edid_property(connector, NULL);
 		kfree(nv_connector->edid);
 		nv_connector->edid = NULL;
 	}
@@ -721,7 +721,7 @@ out:
 		status = connector_status_unknown;
 #endif
 
-	drm_mode_connector_update_edid_property(connector, nv_connector->edid);
+	drm_connector_update_edid_property(connector, nv_connector->edid);
 	nouveau_connector_set_encoder(connector, nv_encoder);
 	return status;
 }
diff --git a/drivers/gpu/drm/omapdrm/omap_connector.c b/drivers/gpu/drm/omapdrm/omap_connector.c
index 5cde26ac937b..2ddb856666c4 100644
--- a/drivers/gpu/drm/omapdrm/omap_connector.c
+++ b/drivers/gpu/drm/omapdrm/omap_connector.c
@@ -126,14 +126,14 @@ static int omap_connector_get_modes(struct drm_connector *connector)
 
 		if ((dssdrv->read_edid(dssdev, edid, MAX_EDID) > 0) &&
 				drm_edid_is_valid(edid)) {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 					connector, edid);
 			n = drm_add_edid_modes(connector, edid);
 
 			omap_connector->hdmi_mode =
 				drm_detect_hdmi_monitor(edid);
 		} else {
-			drm_mode_connector_update_edid_property(
+			drm_connector_update_edid_property(
 					connector, NULL);
 		}
 
diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c
index 86fec03dd260..5b5d0a24e713 100644
--- a/drivers/gpu/drm/panel/panel-simple.c
+++ b/drivers/gpu/drm/panel/panel-simple.c
@@ -252,7 +252,7 @@ static int panel_simple_get_modes(struct drm_panel *panel)
 	/* probe EDID if a DDC bus is available */
 	if (p->ddc) {
 		struct edid *edid = drm_get_edid(panel->connector, p->ddc);
-		drm_mode_connector_update_edid_property(panel->connector, edid);
+		drm_connector_update_edid_property(panel->connector, edid);
 		if (edid) {
 			num += drm_add_edid_modes(panel->connector, edid);
 			kfree(edid);
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index 0655698f2956..414642e5b7a3 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -368,11 +368,11 @@ static int radeon_ddc_get_modes(struct drm_connector *connector)
 	int ret;
 
 	if (radeon_connector->edid) {
-		drm_mode_connector_update_edid_property(connector, radeon_connector->edid);
+		drm_connector_update_edid_property(connector, radeon_connector->edid);
 		ret = drm_add_edid_modes(connector, radeon_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(connector, NULL);
+	drm_connector_update_edid_property(connector, NULL);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index cd8a3ee16649..37956cfc0b6d 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -195,11 +195,11 @@ static int radeon_dp_mst_get_ddc_modes(struct drm_connector *connector)
 	radeon_connector->edid = edid;
 	DRM_DEBUG_KMS("edid retrieved %p\n", edid);
 	if (radeon_connector->edid) {
-		drm_mode_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
+		drm_connector_update_edid_property(&radeon_connector->base, radeon_connector->edid);
 		ret = drm_add_edid_modes(&radeon_connector->base, radeon_connector->edid);
 		return ret;
 	}
-	drm_mode_connector_update_edid_property(&radeon_connector->base, NULL);
+	drm_connector_update_edid_property(&radeon_connector->base, NULL);
 
 	return ret;
 }
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index c6fbdcd87c16..a40cb2be50e1 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -275,7 +275,7 @@ static int cdn_dp_connector_get_modes(struct drm_connector *connector)
 		dp->sink_has_audio = drm_detect_monitor_audio(edid);
 		ret = drm_add_edid_modes(connector, edid);
 		if (ret)
-			drm_mode_connector_update_edid_property(connector,
+			drm_connector_update_edid_property(connector,
 								edid);
 	}
 	mutex_unlock(&dp->lock);
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index 88d0774c97bd..510fcb33e31d 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -565,7 +565,7 @@ static int inno_hdmi_connector_get_modes(struct drm_connector *connector)
 	if (edid) {
 		hdmi->hdmi_data.sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 		hdmi->hdmi_data.sink_has_audio = drm_detect_monitor_audio(edid);
-		drm_mode_connector_update_edid_property(connector, edid);
+		drm_connector_update_edid_property(connector, edid);
 		ret = drm_add_edid_modes(connector, edid);
 		kfree(edid);
 	}
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 58f431102512..0c3008356ab8 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -977,7 +977,7 @@ static int sti_hdmi_connector_get_modes(struct drm_connector *connector)
 	cec_notifier_set_phys_addr_from_edid(hdmi->notifier, edid);
 
 	count = drm_add_edid_modes(connector, edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	kfree(edid);
 	return count;
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index fa4bcd092eaf..9b4b1d015423 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -220,7 +220,7 @@ static int sun4i_hdmi_get_modes(struct drm_connector *connector)
 	DRM_DEBUG_DRIVER("Monitor is %s monitor\n",
 			 hdmi->hdmi_monitor ? "an HDMI" : "a DVI");
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	cec_s_phys_addr_from_edid(hdmi->cec_adap, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
diff --git a/drivers/gpu/drm/tegra/output.c b/drivers/gpu/drm/tegra/output.c
index 0c0936511bb4..c662efc7e413 100644
--- a/drivers/gpu/drm/tegra/output.c
+++ b/drivers/gpu/drm/tegra/output.c
@@ -37,7 +37,7 @@ int tegra_output_connector_get_modes(struct drm_connector *connector)
 		edid = drm_get_edid(connector, output->ddc);
 
 	cec_notifier_set_phys_addr_from_edid(output->notifier, edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		err = drm_add_edid_modes(connector, edid);
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index c45cabb38db0..46dacca3cce8 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -173,7 +173,7 @@ static int tfp410_connector_get_modes(struct drm_connector *connector)
 
 	edid = drm_get_edid(connector, tfp410_connector->mod->i2c);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 
 	if (edid) {
 		ret = drm_add_edid_modes(connector, edid);
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index 09dc585aa46f..8fac12e1a1a4 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -99,7 +99,7 @@ static int udl_get_modes(struct drm_connector *connector)
 					struct udl_drm_connector,
 					connector);
 
-	drm_mode_connector_update_edid_property(connector, udl_connector->edid);
+	drm_connector_update_edid_property(connector, udl_connector->edid);
 	if (udl_connector->edid)
 		return drm_add_edid_modes(connector, udl_connector->edid);
 	return 0;
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index b8d50533e2bb..91f284e1b908 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -285,7 +285,7 @@ static int vc4_hdmi_connector_get_modes(struct drm_connector *connector)
 			drm_rgb_quant_range_selectable(edid);
 	}
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c
index 13ea90f7a185..d073c6737500 100644
--- a/drivers/gpu/drm/zte/zx_hdmi.c
+++ b/drivers/gpu/drm/zte/zx_hdmi.c
@@ -272,7 +272,7 @@ static int zx_hdmi_connector_get_modes(struct drm_connector *connector)
 
 	hdmi->sink_is_hdmi = drm_detect_hdmi_monitor(edid);
 	hdmi->sink_has_audio = drm_detect_monitor_audio(edid);
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
diff --git a/drivers/gpu/drm/zte/zx_vga.c b/drivers/gpu/drm/zte/zx_vga.c
index 3e7e33cd3dfa..3e78ee21b8d0 100644
--- a/drivers/gpu/drm/zte/zx_vga.c
+++ b/drivers/gpu/drm/zte/zx_vga.c
@@ -109,7 +109,7 @@ static int zx_vga_connector_get_modes(struct drm_connector *connector)
 	 */
 	zx_writel(vga->mmio + VGA_AUTO_DETECT_SEL, VGA_DETECT_SEL_HAS_DEVICE);
 
-	drm_mode_connector_update_edid_property(connector, edid);
+	drm_connector_update_edid_property(connector, edid);
 	ret = drm_add_edid_modes(connector, edid);
 	kfree(edid);
 
diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c
index 5c7ea237893e..a943d2f683ed 100644
--- a/drivers/staging/vboxvideo/vbox_mode.c
+++ b/drivers/staging/vboxvideo/vbox_mode.c
@@ -504,7 +504,7 @@ static void vbox_set_edid(struct drm_connector *connector, int width,
 	for (i = 0; i < EDID_SIZE - 1; ++i)
 		sum += edid[i];
 	edid[EDID_SIZE - 1] = (0x100 - (sum & 0xFF)) & 0xFF;
-	drm_mode_connector_update_edid_property(connector, (struct edid *)edid);
+	drm_connector_update_edid_property(connector, (struct edid *)edid);
 }
 
 static int vbox_get_modes(struct drm_connector *connector)
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index e09e16b3e054..4411c0542871 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -896,7 +896,7 @@ struct drm_connector {
 	/**
 	 * @edid_blob_ptr: DRM property containing EDID if present. Protected by
 	 * &drm_mode_config.mutex. This should be updated only by calling
-	 * drm_mode_connector_update_edid_property().
+	 * drm_connector_update_edid_property().
 	 */
 	struct drm_property_blob *edid_blob_ptr;
 
@@ -1194,8 +1194,8 @@ int drm_mode_create_suggested_offset_properties(struct drm_device *dev);
 int drm_mode_connector_set_path_property(struct drm_connector *connector,
 					 const char *path);
 int drm_mode_connector_set_tile_property(struct drm_connector *connector);
-int drm_mode_connector_update_edid_property(struct drm_connector *connector,
-					    const struct edid *edid);
+int drm_connector_update_edid_property(struct drm_connector *connector,
+				       const struct edid *edid);
 void drm_mode_connector_set_link_status_property(struct drm_connector *connector,
 						 uint64_t link_status);
 int drm_connector_init_panel_orientation_property(
diff --git a/include/drm/drm_modeset_helper_vtables.h b/include/drm/drm_modeset_helper_vtables.h
index d0eb76c4b309..61142aa0ab23 100644
--- a/include/drm/drm_modeset_helper_vtables.h
+++ b/include/drm/drm_modeset_helper_vtables.h
@@ -785,7 +785,7 @@ struct drm_connector_helper_funcs {
 	 *
 	 * This function should fill in all modes currently valid for the sink
 	 * into the &drm_connector.probed_modes list. It should also update the
-	 * EDID property by calling drm_mode_connector_update_edid_property().
+	 * EDID property by calling drm_connector_update_edid_property().
 	 *
 	 * The usual way to implement this is to cache the EDID retrieved in the
 	 * probe callback somewhere in the driver-private connector structure.
-- 
cgit v1.2.3


From cde4c44d8769c1be16074c097592c46c7d64092b Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:07 +0200
Subject: drm: drop _mode_ from drm_mode_connector_attach_encoder

Again to align with the usual prefix of just drm_connector_. Again
done with sed + manual fixup for indent issues.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-7-daniel.vetter@ffwll.ch
---
 Documentation/gpu/drm-kms.rst                            |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c             |  2 +-
 drivers/gpu/drm/amd/amdgpu/dce_virtual.c                 |  2 +-
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c        |  2 +-
 drivers/gpu/drm/arc/arcpgu_sim.c                         |  2 +-
 drivers/gpu/drm/ast/ast_mode.c                           |  2 +-
 drivers/gpu/drm/bochs/bochs_kms.c                        |  2 +-
 drivers/gpu/drm/bridge/adv7511/adv7511_drv.c             |  2 +-
 drivers/gpu/drm/bridge/analogix-anx78xx.c                |  4 ++--
 drivers/gpu/drm/bridge/analogix/analogix_dp_core.c       |  2 +-
 drivers/gpu/drm/bridge/dumb-vga-dac.c                    |  2 +-
 drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c |  2 +-
 drivers/gpu/drm/bridge/nxp-ptn3460.c                     |  2 +-
 drivers/gpu/drm/bridge/panel.c                           |  2 +-
 drivers/gpu/drm/bridge/parade-ps8622.c                   |  2 +-
 drivers/gpu/drm/bridge/sii902x.c                         |  2 +-
 drivers/gpu/drm/bridge/synopsys/dw-hdmi.c                |  2 +-
 drivers/gpu/drm/bridge/tc358767.c                        |  2 +-
 drivers/gpu/drm/bridge/ti-tfp410.c                       |  2 +-
 drivers/gpu/drm/cirrus/cirrus_mode.c                     |  2 +-
 drivers/gpu/drm/drm_connector.c                          | 10 +++++-----
 drivers/gpu/drm/drm_simple_kms_helper.c                  |  2 +-
 drivers/gpu/drm/drm_writeback.c                          |  2 +-
 drivers/gpu/drm/exynos/exynos_drm_dpi.c                  |  2 +-
 drivers/gpu/drm/exynos/exynos_drm_dsi.c                  |  2 +-
 drivers/gpu/drm/exynos/exynos_drm_vidi.c                 |  2 +-
 drivers/gpu/drm/exynos/exynos_hdmi.c                     |  2 +-
 drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c                |  2 +-
 drivers/gpu/drm/gma500/gma_display.c                     |  2 +-
 drivers/gpu/drm/gma500/mdfld_dsi_dpi.c                   |  2 +-
 drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c         |  2 +-
 drivers/gpu/drm/i2c/tda998x_drv.c                        |  2 +-
 drivers/gpu/drm/i915/intel_display.c                     |  3 +--
 drivers/gpu/drm/i915/intel_dp_mst.c                      |  3 +--
 drivers/gpu/drm/imx/imx-ldb.c                            |  3 +--
 drivers/gpu/drm/imx/imx-tve.c                            |  2 +-
 drivers/gpu/drm/imx/parallel-display.c                   |  2 +-
 drivers/gpu/drm/mediatek/mtk_dsi.c                       |  2 +-
 drivers/gpu/drm/mediatek/mtk_hdmi.c                      |  2 +-
 drivers/gpu/drm/meson/meson_venc_cvbs.c                  |  2 +-
 drivers/gpu/drm/mgag200/mgag200_mode.c                   |  2 +-
 drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c      |  2 +-
 drivers/gpu/drm/msm/dsi/dsi_manager.c                    |  2 +-
 drivers/gpu/drm/msm/edp/edp_connector.c                  |  2 +-
 drivers/gpu/drm/msm/hdmi/hdmi_connector.c                |  2 +-
 drivers/gpu/drm/nouveau/dispnv04/dac.c                   |  2 +-
 drivers/gpu/drm/nouveau/dispnv04/dfp.c                   |  2 +-
 drivers/gpu/drm/nouveau/dispnv04/tvnv04.c                |  2 +-
 drivers/gpu/drm/nouveau/dispnv04/tvnv17.c                |  2 +-
 drivers/gpu/drm/nouveau/dispnv50/disp.c                  |  8 ++++----
 drivers/gpu/drm/omapdrm/omap_drv.c                       |  2 +-
 drivers/gpu/drm/qxl/qxl_display.c                        |  2 +-
 drivers/gpu/drm/radeon/radeon_encoders.c                 |  2 +-
 drivers/gpu/drm/rcar-du/rcar_lvds.c                      |  2 +-
 drivers/gpu/drm/rockchip/cdn-dp-core.c                   |  2 +-
 drivers/gpu/drm/rockchip/dw-mipi-dsi.c                   |  2 +-
 drivers/gpu/drm/rockchip/inno_hdmi.c                     |  2 +-
 drivers/gpu/drm/rockchip/rockchip_lvds.c                 |  2 +-
 drivers/gpu/drm/shmobile/shmob_drm_crtc.c                |  2 +-
 drivers/gpu/drm/sti/sti_dvo.c                            |  2 +-
 drivers/gpu/drm/sti/sti_hda.c                            |  2 +-
 drivers/gpu/drm/sti/sti_hdmi.c                           |  2 +-
 drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c                   |  2 +-
 drivers/gpu/drm/sun4i/sun4i_lvds.c                       |  2 +-
 drivers/gpu/drm/sun4i/sun4i_rgb.c                        |  2 +-
 drivers/gpu/drm/sun4i/sun4i_tv.c                         |  2 +-
 drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c                   |  2 +-
 drivers/gpu/drm/tegra/dsi.c                              |  2 +-
 drivers/gpu/drm/tegra/hdmi.c                             |  2 +-
 drivers/gpu/drm/tegra/rgb.c                              |  2 +-
 drivers/gpu/drm/tegra/sor.c                              |  2 +-
 drivers/gpu/drm/tilcdc/tilcdc_panel.c                    |  2 +-
 drivers/gpu/drm/tilcdc/tilcdc_tfp410.c                   |  2 +-
 drivers/gpu/drm/udl/udl_connector.c                      |  2 +-
 drivers/gpu/drm/vc4/vc4_hdmi.c                           |  2 +-
 drivers/gpu/drm/vc4/vc4_vec.c                            |  2 +-
 drivers/gpu/drm/virtio/virtgpu_display.c                 |  2 +-
 drivers/gpu/drm/vkms/vkms_output.c                       |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c                      |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c                     |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c                     |  2 +-
 drivers/gpu/drm/zte/zx_hdmi.c                            |  2 +-
 drivers/gpu/drm/zte/zx_tvenc.c                           |  2 +-
 drivers/gpu/drm/zte/zx_vga.c                             |  2 +-
 drivers/staging/vboxvideo/vbox_mode.c                    |  2 +-
 include/drm/drm_connector.h                              |  2 +-
 86 files changed, 94 insertions(+), 97 deletions(-)

diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 514939433004..58eed08fbe31 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -466,7 +466,7 @@ Output discovery and initialization example
         drm_encoder_init(dev, &intel_output->enc, &intel_crt_enc_funcs,
                  DRM_MODE_ENCODER_DAC);
 
-        drm_mode_connector_attach_encoder(&intel_output->base,
+        drm_connector_attach_encoder(&intel_output->base,
                           &intel_output->enc);
 
         /* Set up the DDC bus. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
index 94138abe093b..ae8fac34f7a5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_encoders.c
@@ -46,7 +46,7 @@ amdgpu_link_encoder_connector(struct drm_device *dev)
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			amdgpu_encoder = to_amdgpu_encoder(encoder);
 			if (amdgpu_encoder->devices & amdgpu_connector->devices) {
-				drm_mode_connector_attach_encoder(connector, encoder);
+				drm_connector_attach_encoder(connector, encoder);
 				if (amdgpu_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT)) {
 					amdgpu_atombios_encoder_init_backlight(amdgpu_encoder, connector);
 					adev->mode_info.bl_encoder = amdgpu_encoder;
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index 016f15093173..677e96a56330 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -627,7 +627,7 @@ static int dce_virtual_connector_encoder_init(struct amdgpu_device *adev,
 	drm_connector_register(connector);
 
 	/* link them */
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index c4ab19831344..ae09331eed00 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3615,7 +3615,7 @@ static int amdgpu_dm_connector_init(struct amdgpu_display_manager *dm,
 		link,
 		link_index);
 
-	drm_mode_connector_attach_encoder(
+	drm_connector_attach_encoder(
 		&aconnector->base, &aencoder->base);
 
 	drm_connector_register(&aconnector->base);
diff --git a/drivers/gpu/drm/arc/arcpgu_sim.c b/drivers/gpu/drm/arc/arcpgu_sim.c
index b8f6f9a5dfbe..68629e614990 100644
--- a/drivers/gpu/drm/arc/arcpgu_sim.c
+++ b/drivers/gpu/drm/arc/arcpgu_sim.c
@@ -99,7 +99,7 @@ int arcpgu_drm_sim_init(struct drm_device *drm, struct device_node *np)
 		goto error_encoder_cleanup;
 	}
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0) {
 		dev_err(drm->dev, "could not attach connector to encoder\n");
 		drm_connector_unregister(connector);
diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
index 1bb8174ad155..5e77d456d9bb 100644
--- a/drivers/gpu/drm/ast/ast_mode.c
+++ b/drivers/gpu/drm/ast/ast_mode.c
@@ -900,7 +900,7 @@ static int ast_connector_init(struct drm_device *dev)
 	connector->polled = DRM_CONNECTOR_POLL_CONNECT;
 
 	encoder = list_first_entry(&dev->mode_config.encoder_list, struct drm_encoder, head);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ast_connector->i2c = ast_i2c_create(dev);
 	if (!ast_connector->i2c)
diff --git a/drivers/gpu/drm/bochs/bochs_kms.c b/drivers/gpu/drm/bochs/bochs_kms.c
index 233980a78591..ca5a9afdd5cf 100644
--- a/drivers/gpu/drm/bochs/bochs_kms.c
+++ b/drivers/gpu/drm/bochs/bochs_kms.c
@@ -259,7 +259,7 @@ int bochs_kms_init(struct bochs_device *bochs)
 	bochs_crtc_init(bochs->dev);
 	bochs_encoder_init(bochs->dev);
 	bochs_connector_init(bochs->dev);
-	drm_mode_connector_attach_encoder(&bochs->connector,
+	drm_connector_attach_encoder(&bochs->connector,
 					  &bochs->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
index 1f4745953aca..6437b878724a 100644
--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
@@ -860,7 +860,7 @@ static int adv7511_bridge_attach(struct drm_bridge *bridge)
 	}
 	drm_connector_helper_add(&adv->connector,
 				 &adv7511_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(&adv->connector, bridge->encoder);
+	drm_connector_attach_encoder(&adv->connector, bridge->encoder);
 
 	if (adv->type == ADV7533)
 		ret = adv7533_attach_dsi(adv);
diff --git a/drivers/gpu/drm/bridge/analogix-anx78xx.c b/drivers/gpu/drm/bridge/analogix-anx78xx.c
index 37f947dcadec..f8433c93f463 100644
--- a/drivers/gpu/drm/bridge/analogix-anx78xx.c
+++ b/drivers/gpu/drm/bridge/analogix-anx78xx.c
@@ -1048,8 +1048,8 @@ static int anx78xx_bridge_attach(struct drm_bridge *bridge)
 
 	anx78xx->connector.polled = DRM_CONNECTOR_POLL_HPD;
 
-	err = drm_mode_connector_attach_encoder(&anx78xx->connector,
-						bridge->encoder);
+	err = drm_connector_attach_encoder(&anx78xx->connector,
+					   bridge->encoder);
 	if (err) {
 		DRM_ERROR("Failed to link up connector to encoder: %d\n", err);
 		return err;
diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
index 288c015f7460..d68986cea132 100644
--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
+++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_core.c
@@ -1210,7 +1210,7 @@ static int analogix_dp_bridge_attach(struct drm_bridge *bridge)
 
 		drm_connector_helper_add(connector,
 					 &analogix_dp_connector_helper_funcs);
-		drm_mode_connector_attach_encoder(connector, encoder);
+		drm_connector_attach_encoder(connector, encoder);
 	}
 
 	/*
diff --git a/drivers/gpu/drm/bridge/dumb-vga-dac.c b/drivers/gpu/drm/bridge/dumb-vga-dac.c
index da99b8ba4ee1..9b706789a341 100644
--- a/drivers/gpu/drm/bridge/dumb-vga-dac.c
+++ b/drivers/gpu/drm/bridge/dumb-vga-dac.c
@@ -122,7 +122,7 @@ static int dumb_vga_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&vga->connector,
+	drm_connector_attach_encoder(&vga->connector,
 					  bridge->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
index b49b543bd1f6..2136c97aeb8e 100644
--- a/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
+++ b/drivers/gpu/drm/bridge/megachips-stdpxxxx-ge-b850v3-fw.c
@@ -241,7 +241,7 @@ static int ge_b850v3_lvds_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	ret = drm_mode_connector_attach_encoder(connector, bridge->encoder);
+	ret = drm_connector_attach_encoder(connector, bridge->encoder);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/bridge/nxp-ptn3460.c b/drivers/gpu/drm/bridge/nxp-ptn3460.c
index bd5c191858cb..a3e817abace1 100644
--- a/drivers/gpu/drm/bridge/nxp-ptn3460.c
+++ b/drivers/gpu/drm/bridge/nxp-ptn3460.c
@@ -265,7 +265,7 @@ static int ptn3460_bridge_attach(struct drm_bridge *bridge)
 	drm_connector_helper_add(&ptn_bridge->connector,
 					&ptn3460_connector_helper_funcs);
 	drm_connector_register(&ptn_bridge->connector);
-	drm_mode_connector_attach_encoder(&ptn_bridge->connector,
+	drm_connector_attach_encoder(&ptn_bridge->connector,
 							bridge->encoder);
 
 	if (ptn_bridge->panel)
diff --git a/drivers/gpu/drm/bridge/panel.c b/drivers/gpu/drm/bridge/panel.c
index 6d99d4a3beb3..7cbaba213ef6 100644
--- a/drivers/gpu/drm/bridge/panel.c
+++ b/drivers/gpu/drm/bridge/panel.c
@@ -79,7 +79,7 @@ static int panel_bridge_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&panel_bridge->connector,
+	drm_connector_attach_encoder(&panel_bridge->connector,
 					  bridge->encoder);
 
 	ret = drm_panel_attach(panel_bridge->panel, &panel_bridge->connector);
diff --git a/drivers/gpu/drm/bridge/parade-ps8622.c b/drivers/gpu/drm/bridge/parade-ps8622.c
index 81198f5e9afa..7334d1b62b71 100644
--- a/drivers/gpu/drm/bridge/parade-ps8622.c
+++ b/drivers/gpu/drm/bridge/parade-ps8622.c
@@ -503,7 +503,7 @@ static int ps8622_attach(struct drm_bridge *bridge)
 	drm_connector_helper_add(&ps8622->connector,
 					&ps8622_connector_helper_funcs);
 	drm_connector_register(&ps8622->connector);
-	drm_mode_connector_attach_encoder(&ps8622->connector,
+	drm_connector_attach_encoder(&ps8622->connector,
 							bridge->encoder);
 
 	if (ps8622->panel)
diff --git a/drivers/gpu/drm/bridge/sii902x.c b/drivers/gpu/drm/bridge/sii902x.c
index cd331933c230..e59a13542333 100644
--- a/drivers/gpu/drm/bridge/sii902x.c
+++ b/drivers/gpu/drm/bridge/sii902x.c
@@ -324,7 +324,7 @@ static int sii902x_bridge_attach(struct drm_bridge *bridge)
 	else
 		sii902x->connector.polled = DRM_CONNECTOR_POLL_CONNECT;
 
-	drm_mode_connector_attach_encoder(&sii902x->connector, bridge->encoder);
+	drm_connector_attach_encoder(&sii902x->connector, bridge->encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
index ab32aceb6f24..5971976284bf 100644
--- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
+++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c
@@ -1974,7 +1974,7 @@ static int dw_hdmi_bridge_attach(struct drm_bridge *bridge)
 	drm_connector_init(bridge->dev, connector, &dw_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
index ee2fd0a349b3..8e28e738cb52 100644
--- a/drivers/gpu/drm/bridge/tc358767.c
+++ b/drivers/gpu/drm/bridge/tc358767.c
@@ -1195,7 +1195,7 @@ static int tc_bridge_attach(struct drm_bridge *bridge)
 
 	drm_display_info_set_bus_formats(&tc->connector.display_info,
 					 &bus_format, 1);
-	drm_mode_connector_attach_encoder(&tc->connector, tc->bridge.encoder);
+	drm_connector_attach_encoder(&tc->connector, tc->bridge.encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/bridge/ti-tfp410.c b/drivers/gpu/drm/bridge/ti-tfp410.c
index c81bf7910bbe..c3e32138c6bb 100644
--- a/drivers/gpu/drm/bridge/ti-tfp410.c
+++ b/drivers/gpu/drm/bridge/ti-tfp410.c
@@ -132,7 +132,7 @@ static int tfp410_attach(struct drm_bridge *bridge)
 		return ret;
 	}
 
-	drm_mode_connector_attach_encoder(&dvi->connector,
+	drm_connector_attach_encoder(&dvi->connector,
 					  bridge->encoder);
 
 	return 0;
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index b529f8c8e2a6..336bfda40125 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -530,7 +530,7 @@ int cirrus_modeset_init(struct cirrus_device *cdev)
 		return -1;
 	}
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ret = cirrus_fbdev_init(cdev);
 	if (ret) {
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index b2b182ffdbe9..8997792e2e23 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -48,7 +48,7 @@
  *
  * Connectors must be attached to an encoder to be used. For devices that map
  * connectors to encoders 1:1, the connector should be attached at
- * initialization time with a call to drm_mode_connector_attach_encoder(). The
+ * initialization time with a call to drm_connector_attach_encoder(). The
  * driver must also set the &drm_connector.encoder field to point to the
  * attached encoder.
  *
@@ -291,7 +291,7 @@ out_put:
 EXPORT_SYMBOL(drm_connector_init);
 
 /**
- * drm_mode_connector_attach_encoder - attach a connector to an encoder
+ * drm_connector_attach_encoder - attach a connector to an encoder
  * @connector: connector to attach
  * @encoder: encoder to attach @connector to
  *
@@ -302,8 +302,8 @@ EXPORT_SYMBOL(drm_connector_init);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_attach_encoder(struct drm_connector *connector,
-				      struct drm_encoder *encoder)
+int drm_connector_attach_encoder(struct drm_connector *connector,
+				 struct drm_encoder *encoder)
 {
 	int i;
 
@@ -329,7 +329,7 @@ int drm_mode_connector_attach_encoder(struct drm_connector *connector,
 	}
 	return -ENOMEM;
 }
-EXPORT_SYMBOL(drm_mode_connector_attach_encoder);
+EXPORT_SYMBOL(drm_connector_attach_encoder);
 
 /**
  * drm_connector_has_possible_encoder - check if the connector and encoder are assosicated with each other
diff --git a/drivers/gpu/drm/drm_simple_kms_helper.c b/drivers/gpu/drm/drm_simple_kms_helper.c
index b72fcf1e9605..51fa978f0d23 100644
--- a/drivers/gpu/drm/drm_simple_kms_helper.c
+++ b/drivers/gpu/drm/drm_simple_kms_helper.c
@@ -287,7 +287,7 @@ int drm_simple_display_pipe_init(struct drm_device *dev,
 	if (ret || !connector)
 		return ret;
 
-	return drm_mode_connector_attach_encoder(connector, encoder);
+	return drm_connector_attach_encoder(connector, encoder);
 }
 EXPORT_SYMBOL(drm_simple_display_pipe_init);
 
diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index 69e7a63cfcc3..169746f6b567 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -202,7 +202,7 @@ int drm_writeback_connector_init(struct drm_device *dev,
 	if (ret)
 		goto connector_fail;
 
-	ret = drm_mode_connector_attach_encoder(connector,
+	ret = drm_connector_attach_encoder(connector,
 						&wb_connector->encoder);
 	if (ret)
 		goto attach_fail;
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dpi.c b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
index 5887e8522b70..2f0babb67c51 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dpi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dpi.c
@@ -113,7 +113,7 @@ static int exynos_dpi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &exynos_dpi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index 809e1e0447df..a1ed6146a3b5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1479,7 +1479,7 @@ static int exynos_dsi_create_connector(struct drm_encoder *encoder)
 
 	connector->status = connector_status_disconnected;
 	drm_connector_helper_add(connector, &exynos_dsi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_vidi.c b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
index dfea61edba4a..19697c1362d8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_vidi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_vidi.c
@@ -344,7 +344,7 @@ static int vidi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &vidi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 6672d0ff0423..3a11c719a580 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -951,7 +951,7 @@ static int hdmi_create_connector(struct drm_encoder *encoder)
 	}
 
 	drm_connector_helper_add(connector, &hdmi_connector_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	if (hdata->bridge) {
 		ret = drm_bridge_attach(encoder, hdata->bridge, NULL);
diff --git a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
index 681e2a07d03b..2298ed2a9e1c 100644
--- a/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
+++ b/drivers/gpu/drm/fsl-dcu/fsl_dcu_drm_rgb.c
@@ -117,7 +117,7 @@ static int fsl_dcu_attach_panel(struct fsl_dcu_drm_device *fsl_dev,
 	if (ret < 0)
 		goto err_cleanup;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		goto err_sysfs;
 
diff --git a/drivers/gpu/drm/gma500/gma_display.c b/drivers/gpu/drm/gma500/gma_display.c
index 08f17f85b801..09c1161a7ac6 100644
--- a/drivers/gpu/drm/gma500/gma_display.c
+++ b/drivers/gpu/drm/gma500/gma_display.c
@@ -665,7 +665,7 @@ void gma_connector_attach_encoder(struct gma_connector *connector,
 				  struct gma_encoder *encoder)
 {
 	connector->encoder = encoder;
-	drm_mode_connector_attach_encoder(&connector->base,
+	drm_connector_attach_encoder(&connector->base,
 					  &encoder->base);
 }
 
diff --git a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
index a05c020602bd..d0bf5a1e94e8 100644
--- a/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
+++ b/drivers/gpu/drm/gma500/mdfld_dsi_dpi.c
@@ -999,7 +999,7 @@ struct mdfld_dsi_encoder *mdfld_dsi_dpi_init(struct drm_device *dev,
 				p_funcs->encoder_helper_funcs);
 
 	/*attach to given connector*/
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	/*set possible crtcs and clones*/
 	if (dsi_connector->pipe) {
diff --git a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
index d2f4749ebf8d..744956cea749 100644
--- a/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
+++ b/drivers/gpu/drm/hisilicon/hibmc/hibmc_drm_vdac.c
@@ -133,7 +133,7 @@ int hibmc_vdac_init(struct hibmc_drm_private *priv)
 	}
 
 	drm_encoder_helper_add(encoder, &hibmc_encoder_helper_funcs);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index d434f576e6b2..eecdc327b9f8 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1301,7 +1301,7 @@ static int tda998x_connector_init(struct tda998x_priv *priv,
 	if (ret)
 		return ret;
 
-	drm_mode_connector_attach_encoder(&priv->connector, &priv->encoder);
+	drm_connector_attach_encoder(&priv->connector, &priv->encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 694a4703042f..fbe5a6572d7d 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15899,8 +15899,7 @@ void intel_connector_attach_encoder(struct intel_connector *connector,
 				    struct intel_encoder *encoder)
 {
 	connector->encoder = encoder;
-	drm_mode_connector_attach_encoder(&connector->base,
-					  &encoder->base);
+	drm_connector_attach_encoder(&connector->base, &encoder->base);
 }
 
 /*
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 0f012fbe34eb..364330fc5d6a 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -466,8 +466,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 		struct drm_encoder *enc =
 			&intel_dp->mst_encoders[pipe]->base.base;
 
-		ret = drm_mode_connector_attach_encoder(&intel_connector->base,
-							enc);
+		ret = drm_connector_attach_encoder(&intel_connector->base, enc);
 		if (ret)
 			goto err;
 	}
diff --git a/drivers/gpu/drm/imx/imx-ldb.c b/drivers/gpu/drm/imx/imx-ldb.c
index ae81cbb75f51..7312beb6f1fc 100644
--- a/drivers/gpu/drm/imx/imx-ldb.c
+++ b/drivers/gpu/drm/imx/imx-ldb.c
@@ -471,8 +471,7 @@ static int imx_ldb_register(struct drm_device *drm,
 		drm_connector_init(drm, &imx_ldb_ch->connector,
 				&imx_ldb_connector_funcs,
 				DRM_MODE_CONNECTOR_LVDS);
-		drm_mode_connector_attach_encoder(&imx_ldb_ch->connector,
-				encoder);
+		drm_connector_attach_encoder(&imx_ldb_ch->connector, encoder);
 	}
 
 	if (imx_ldb_ch->panel) {
diff --git a/drivers/gpu/drm/imx/imx-tve.c b/drivers/gpu/drm/imx/imx-tve.c
index 1a4ced5c09b5..cffd3310240e 100644
--- a/drivers/gpu/drm/imx/imx-tve.c
+++ b/drivers/gpu/drm/imx/imx-tve.c
@@ -493,7 +493,7 @@ static int imx_tve_register(struct drm_device *drm, struct imx_tve *tve)
 	drm_connector_init(drm, &tve->connector, &imx_tve_connector_funcs,
 			   DRM_MODE_CONNECTOR_VGA);
 
-	drm_mode_connector_attach_encoder(&tve->connector, &tve->encoder);
+	drm_connector_attach_encoder(&tve->connector, &tve->encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/imx/parallel-display.c b/drivers/gpu/drm/imx/parallel-display.c
index 4fc1cf583435..aefd04e18f93 100644
--- a/drivers/gpu/drm/imx/parallel-display.c
+++ b/drivers/gpu/drm/imx/parallel-display.c
@@ -197,7 +197,7 @@ static int imx_pd_register(struct drm_device *drm,
 			return ret;
 		}
 	} else {
-		drm_mode_connector_attach_encoder(&imxpd->connector, encoder);
+		drm_connector_attach_encoder(&imxpd->connector, encoder);
 	}
 
 	return 0;
diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
index aa0943ec32b0..66df1b177959 100644
--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
+++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
@@ -782,7 +782,7 @@ static int mtk_dsi_create_connector(struct drm_device *drm, struct mtk_dsi *dsi)
 	drm_connector_helper_add(&dsi->conn, &mtk_dsi_connector_helper_funcs);
 
 	dsi->conn.dpms = DRM_MODE_DPMS_OFF;
-	drm_mode_connector_attach_encoder(&dsi->conn, &dsi->encoder);
+	drm_connector_attach_encoder(&dsi->conn, &dsi->encoder);
 
 	if (dsi->panel) {
 		ret = drm_panel_attach(dsi->panel, &dsi->conn);
diff --git a/drivers/gpu/drm/mediatek/mtk_hdmi.c b/drivers/gpu/drm/mediatek/mtk_hdmi.c
index 835313940395..2d45d1dd9554 100644
--- a/drivers/gpu/drm/mediatek/mtk_hdmi.c
+++ b/drivers/gpu/drm/mediatek/mtk_hdmi.c
@@ -1306,7 +1306,7 @@ static int mtk_hdmi_bridge_attach(struct drm_bridge *bridge)
 	hdmi->conn.interlace_allowed = true;
 	hdmi->conn.doublescan_allowed = false;
 
-	ret = drm_mode_connector_attach_encoder(&hdmi->conn,
+	ret = drm_connector_attach_encoder(&hdmi->conn,
 						bridge->encoder);
 	if (ret) {
 		dev_err(hdmi->dev,
diff --git a/drivers/gpu/drm/meson/meson_venc_cvbs.c b/drivers/gpu/drm/meson/meson_venc_cvbs.c
index 79d95ca8a0c0..f7945bae3b4a 100644
--- a/drivers/gpu/drm/meson/meson_venc_cvbs.c
+++ b/drivers/gpu/drm/meson/meson_venc_cvbs.c
@@ -282,7 +282,7 @@ int meson_venc_cvbs_create(struct meson_drm *priv)
 
 	encoder->possible_crtcs = BIT(0);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index 5f104f139197..acf7bfe68454 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1747,7 +1747,7 @@ int mgag200_modeset_init(struct mga_device *mdev)
 		return -1;
 	}
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	ret = mgag200_fbdev_init(mdev);
 	if (ret) {
diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
index 32fba5664b0e..5368e621999c 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_lvds_connector.c
@@ -132,7 +132,7 @@ struct drm_connector *mdp4_lvds_connector_init(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 4beba3f7d067..21e0dc51531d 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -684,7 +684,7 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id)
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, msm_dsi->encoder);
+	drm_connector_attach_encoder(connector, msm_dsi->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/edp/edp_connector.c b/drivers/gpu/drm/msm/edp/edp_connector.c
index 0b5eac054195..058ff92a0207 100644
--- a/drivers/gpu/drm/msm/edp/edp_connector.c
+++ b/drivers/gpu/drm/msm/edp/edp_connector.c
@@ -134,7 +134,7 @@ struct drm_connector *msm_edp_connector_init(struct msm_edp *edp)
 	connector->interlace_allowed = false;
 	connector->doublescan_allowed = false;
 
-	drm_mode_connector_attach_encoder(connector, edp->encoder);
+	drm_connector_attach_encoder(connector, edp->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
index 07feacc5a441..e9c9a0af508e 100644
--- a/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
+++ b/drivers/gpu/drm/msm/hdmi/hdmi_connector.c
@@ -477,7 +477,7 @@ struct drm_connector *msm_hdmi_connector_init(struct hdmi *hdmi)
 		return ERR_PTR(ret);
 	}
 
-	drm_mode_connector_attach_encoder(connector, hdmi->encoder);
+	drm_connector_attach_encoder(connector, hdmi->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dac.c b/drivers/gpu/drm/nouveau/dispnv04/dac.c
index 4feab0a5419d..e7af95d37ddb 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dac.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dac.c
@@ -556,6 +556,6 @@ nv04_dac_create(struct drm_connector *connector, struct dcb_output *entry)
 	encoder->possible_crtcs = entry->heads;
 	encoder->possible_clones = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/dfp.c b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
index 9805d2cdc1a1..73d41abbb510 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/dfp.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/dfp.c
@@ -716,6 +716,6 @@ nv04_dfp_create(struct drm_connector *connector, struct dcb_output *entry)
 	    entry->location != DCB_LOC_ON_CHIP)
 		nv04_tmds_slave_init(encoder);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
index 01664357d3e1..de4490b4ed30 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv04.c
@@ -244,7 +244,7 @@ nv04_tv_create(struct drm_connector *connector, struct dcb_output *entry)
 
 	/* Attach it to the specified connector. */
 	get_slave_funcs(encoder)->create_resources(encoder, connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
index 6d99f11fee4e..6a4ca139cf5d 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/tvnv17.c
@@ -821,6 +821,6 @@ nv17_tv_create(struct drm_connector *connector, struct dcb_output *entry)
 	encoder->possible_clones = 0;
 
 	nv17_tv_create_resources(encoder, connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 2fabb69e452b..475456c19b76 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -424,7 +424,7 @@ nv50_dac_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "dac-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_dac_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
 
@@ -927,7 +927,7 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 	nouveau_conn_attach_properties(&mstc->connector);
 
 	for (i = 0; i < ARRAY_SIZE(mstm->msto) && mstm->msto[i]; i++)
-		drm_mode_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
+		drm_connector_attach_encoder(&mstc->connector, &mstm->msto[i]->encoder);
 
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0);
@@ -1418,7 +1418,7 @@ nv50_sor_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "sor-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_sor_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	if (dcbe->type == DCB_OUTPUT_DP) {
 		struct nv50_disp *disp = nv50_disp(encoder->dev);
@@ -1576,7 +1576,7 @@ nv50_pior_create(struct drm_connector *connector, struct dcb_output *dcbe)
 			 "pior-%04x-%04x", dcbe->hasht, dcbe->hashm);
 	drm_encoder_helper_add(encoder, &nv50_pior_help);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/omapdrm/omap_drv.c b/drivers/gpu/drm/omapdrm/omap_drv.c
index 5005ecc284d2..1b6601e9b107 100644
--- a/drivers/gpu/drm/omapdrm/omap_drv.c
+++ b/drivers/gpu/drm/omapdrm/omap_drv.c
@@ -274,7 +274,7 @@ static int omap_modeset_init(struct drm_device *dev)
 		if (IS_ERR(crtc))
 			return PTR_ERR(crtc);
 
-		drm_mode_connector_attach_encoder(connector, encoder);
+		drm_connector_attach_encoder(connector, encoder);
 		encoder->possible_crtcs = (1 << crtc_idx);
 
 		priv->crtcs[priv->num_crtcs++] = crtc;
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 768207fbbae3..0570c6826bff 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -1086,7 +1086,7 @@ static int qdev_output_init(struct drm_device *dev, int num_output)
 	/* we get HPD via client monitors config */
 	connector->polled = DRM_CONNECTOR_POLL_HPD;
 	encoder->possible_crtcs = 1 << num_output;
-	drm_mode_connector_attach_encoder(&qxl_output->base,
+	drm_connector_attach_encoder(&qxl_output->base,
 					  &qxl_output->enc);
 	drm_encoder_helper_add(encoder, &qxl_enc_helper_funcs);
 	drm_connector_helper_add(connector, &qxl_connector_helper_funcs);
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index c6ee80216cf4..c341fb2a5b56 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -211,7 +211,7 @@ radeon_link_encoder_connector(struct drm_device *dev)
 		list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
 			radeon_encoder = to_radeon_encoder(encoder);
 			if (radeon_encoder->devices & radeon_connector->devices) {
-				drm_mode_connector_attach_encoder(connector, encoder);
+				drm_connector_attach_encoder(connector, encoder);
 				if (radeon_encoder->devices & (ATOM_DEVICE_LCD_SUPPORT))
 					radeon_encoder_add_backlight(radeon_encoder, connector);
 			}
diff --git a/drivers/gpu/drm/rcar-du/rcar_lvds.c b/drivers/gpu/drm/rcar-du/rcar_lvds.c
index 5d8e391e75f4..4c39de3f4f0f 100644
--- a/drivers/gpu/drm/rcar-du/rcar_lvds.c
+++ b/drivers/gpu/drm/rcar-du/rcar_lvds.c
@@ -353,7 +353,7 @@ static int rcar_lvds_attach(struct drm_bridge *bridge)
 
 	drm_connector_helper_add(connector, &rcar_lvds_conn_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/gpu/drm/rockchip/cdn-dp-core.c b/drivers/gpu/drm/rockchip/cdn-dp-core.c
index a40cb2be50e1..8ad0d773dc33 100644
--- a/drivers/gpu/drm/rockchip/cdn-dp-core.c
+++ b/drivers/gpu/drm/rockchip/cdn-dp-core.c
@@ -1062,7 +1062,7 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
 
 	drm_connector_helper_add(connector, &cdn_dp_connector_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret) {
 		DRM_ERROR("failed to attach connector and encoder\n");
 		goto err_free_connector;
diff --git a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
index 01642aaf6127..662b6cb5d3f0 100644
--- a/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
+++ b/drivers/gpu/drm/rockchip/dw-mipi-dsi.c
@@ -1129,7 +1129,7 @@ static int dw_mipi_dsi_register(struct drm_device *drm,
 			   &dw_mipi_dsi_atomic_connector_funcs,
 			   DRM_MODE_CONNECTOR_DSI);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/inno_hdmi.c b/drivers/gpu/drm/rockchip/inno_hdmi.c
index 510fcb33e31d..1c02b3e61299 100644
--- a/drivers/gpu/drm/rockchip/inno_hdmi.c
+++ b/drivers/gpu/drm/rockchip/inno_hdmi.c
@@ -634,7 +634,7 @@ static int inno_hdmi_register(struct drm_device *drm, struct inno_hdmi *hdmi)
 	drm_connector_init(drm, &hdmi->connector, &inno_hdmi_connector_funcs,
 			   DRM_MODE_CONNECTOR_HDMIA);
 
-	drm_mode_connector_attach_encoder(&hdmi->connector, encoder);
+	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/rockchip/rockchip_lvds.c b/drivers/gpu/drm/rockchip/rockchip_lvds.c
index b3f6f524b402..456bd9f13bae 100644
--- a/drivers/gpu/drm/rockchip/rockchip_lvds.c
+++ b/drivers/gpu/drm/rockchip/rockchip_lvds.c
@@ -434,7 +434,7 @@ static int rockchip_lvds_bind(struct device *dev, struct device *master,
 		drm_connector_helper_add(connector,
 					 &rockchip_lvds_connector_helper_funcs);
 
-		ret = drm_mode_connector_attach_encoder(connector, encoder);
+		ret = drm_connector_attach_encoder(connector, encoder);
 		if (ret < 0) {
 			DRM_DEV_ERROR(drm_dev->dev,
 				      "failed to attach encoder: %d\n", ret);
diff --git a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
index 40df8887fc17..fc66167b0641 100644
--- a/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
+++ b/drivers/gpu/drm/shmobile/shmob_drm_crtc.c
@@ -675,7 +675,7 @@ int shmob_drm_connector_create(struct shmob_drm_device *sdev,
 	if (ret < 0)
 		goto err_cleanup;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret < 0)
 		goto err_backlight;
 
diff --git a/drivers/gpu/drm/sti/sti_dvo.c b/drivers/gpu/drm/sti/sti_dvo.c
index 030da55a8d30..b08376b7611b 100644
--- a/drivers/gpu/drm/sti/sti_dvo.c
+++ b/drivers/gpu/drm/sti/sti_dvo.c
@@ -486,7 +486,7 @@ static int sti_dvo_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 				 &sti_dvo_connector_helper_funcs);
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sti/sti_hda.c b/drivers/gpu/drm/sti/sti_hda.c
index 67bbdb49fffc..49438337f70d 100644
--- a/drivers/gpu/drm/sti/sti_hda.c
+++ b/drivers/gpu/drm/sti/sti_hda.c
@@ -709,7 +709,7 @@ static int sti_hda_bind(struct device *dev, struct device *master, void *data)
 	drm_connector_helper_add(drm_connector,
 			&sti_hda_connector_helper_funcs);
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sti/sti_hdmi.c b/drivers/gpu/drm/sti/sti_hdmi.c
index 0c3008356ab8..34cdc4644435 100644
--- a/drivers/gpu/drm/sti/sti_hdmi.c
+++ b/drivers/gpu/drm/sti/sti_hdmi.c
@@ -1290,7 +1290,7 @@ static int sti_hdmi_bind(struct device *dev, struct device *master, void *data)
 
 	hdmi->drm_connector = drm_connector;
 
-	err = drm_mode_connector_attach_encoder(drm_connector, encoder);
+	err = drm_connector_attach_encoder(drm_connector, encoder);
 	if (err) {
 		DRM_ERROR("Failed to attach a connector to a encoder\n");
 		goto err_sysfs;
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index 9b4b1d015423..061d2e0d9011 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -623,7 +623,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 	ret = cec_register_adapter(hdmi->cec_adap, dev);
 	if (ret < 0)
 		goto err_cleanup_connector;
-	drm_mode_connector_attach_encoder(&hdmi->connector, &hdmi->encoder);
+	drm_connector_attach_encoder(&hdmi->connector, &hdmi->encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/sun4i/sun4i_lvds.c b/drivers/gpu/drm/sun4i/sun4i_lvds.c
index a69fe2e1f9d1..af7dcb6da351 100644
--- a/drivers/gpu/drm/sun4i/sun4i_lvds.c
+++ b/drivers/gpu/drm/sun4i/sun4i_lvds.c
@@ -149,7 +149,7 @@ int sun4i_lvds_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 			goto err_cleanup_connector;
 		}
 
-		drm_mode_connector_attach_encoder(&lvds->connector,
+		drm_connector_attach_encoder(&lvds->connector,
 						  &lvds->encoder);
 
 		ret = drm_panel_attach(tcon->panel, &lvds->connector);
diff --git a/drivers/gpu/drm/sun4i/sun4i_rgb.c b/drivers/gpu/drm/sun4i/sun4i_rgb.c
index 96d21b07f8fc..bf068da6b12e 100644
--- a/drivers/gpu/drm/sun4i/sun4i_rgb.c
+++ b/drivers/gpu/drm/sun4i/sun4i_rgb.c
@@ -215,7 +215,7 @@ int sun4i_rgb_init(struct drm_device *drm, struct sun4i_tcon *tcon)
 			goto err_cleanup_connector;
 		}
 
-		drm_mode_connector_attach_encoder(&rgb->connector,
+		drm_connector_attach_encoder(&rgb->connector,
 						  &rgb->encoder);
 
 		ret = drm_panel_attach(tcon->panel, &rgb->connector);
diff --git a/drivers/gpu/drm/sun4i/sun4i_tv.c b/drivers/gpu/drm/sun4i/sun4i_tv.c
index b070d522ed8d..1a838d208211 100644
--- a/drivers/gpu/drm/sun4i/sun4i_tv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_tv.c
@@ -623,7 +623,7 @@ static int sun4i_tv_bind(struct device *dev, struct device *master,
 	}
 	tv->connector.interlace_allowed = true;
 
-	drm_mode_connector_attach_encoder(&tv->connector, &tv->encoder);
+	drm_connector_attach_encoder(&tv->connector, &tv->encoder);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
index 2b40d1f6aee8..e3b34a345546 100644
--- a/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
+++ b/drivers/gpu/drm/sun4i/sun6i_mipi_dsi.c
@@ -941,7 +941,7 @@ static int sun6i_dsi_bind(struct device *dev, struct device *master,
 		goto err_cleanup_connector;
 	}
 
-	drm_mode_connector_attach_encoder(&dsi->connector, &dsi->encoder);
+	drm_connector_attach_encoder(&dsi->connector, &dsi->encoder);
 	drm_panel_attach(dsi->panel, &dsi->connector);
 
 	return 0;
diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c
index ad88ec230329..ee6ca8fa1c65 100644
--- a/drivers/gpu/drm/tegra/dsi.c
+++ b/drivers/gpu/drm/tegra/dsi.c
@@ -1052,7 +1052,7 @@ static int tegra_dsi_init(struct host1x_client *client)
 		drm_encoder_helper_add(&dsi->output.encoder,
 				       &tegra_dsi_encoder_helper_funcs);
 
-		drm_mode_connector_attach_encoder(&dsi->output.connector,
+		drm_connector_attach_encoder(&dsi->output.connector,
 						  &dsi->output.encoder);
 		drm_connector_register(&dsi->output.connector);
 
diff --git a/drivers/gpu/drm/tegra/hdmi.c b/drivers/gpu/drm/tegra/hdmi.c
index 784739a9f497..0082468f703c 100644
--- a/drivers/gpu/drm/tegra/hdmi.c
+++ b/drivers/gpu/drm/tegra/hdmi.c
@@ -1488,7 +1488,7 @@ static int tegra_hdmi_init(struct host1x_client *client)
 	drm_encoder_helper_add(&hdmi->output.encoder,
 			       &tegra_hdmi_encoder_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&hdmi->output.connector,
+	drm_connector_attach_encoder(&hdmi->output.connector,
 					  &hdmi->output.encoder);
 	drm_connector_register(&hdmi->output.connector);
 
diff --git a/drivers/gpu/drm/tegra/rgb.c b/drivers/gpu/drm/tegra/rgb.c
index 78ec5193741d..28a78d3120bc 100644
--- a/drivers/gpu/drm/tegra/rgb.c
+++ b/drivers/gpu/drm/tegra/rgb.c
@@ -289,7 +289,7 @@ int tegra_dc_rgb_init(struct drm_device *drm, struct tegra_dc *dc)
 	drm_encoder_helper_add(&output->encoder,
 			       &tegra_rgb_encoder_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&output->connector,
+	drm_connector_attach_encoder(&output->connector,
 					  &output->encoder);
 	drm_connector_register(&output->connector);
 
diff --git a/drivers/gpu/drm/tegra/sor.c b/drivers/gpu/drm/tegra/sor.c
index 7d2a955fc515..d7fe9f15def1 100644
--- a/drivers/gpu/drm/tegra/sor.c
+++ b/drivers/gpu/drm/tegra/sor.c
@@ -2622,7 +2622,7 @@ static int tegra_sor_init(struct host1x_client *client)
 			 encoder, NULL);
 	drm_encoder_helper_add(&sor->output.encoder, helpers);
 
-	drm_mode_connector_attach_encoder(&sor->output.connector,
+	drm_connector_attach_encoder(&sor->output.connector,
 					  &sor->output.encoder);
 	drm_connector_register(&sor->output.connector);
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_panel.c b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
index d616d64a6725..a1acab39d87f 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_panel.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_panel.c
@@ -223,7 +223,7 @@ static struct drm_connector *panel_connector_create(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
index 46dacca3cce8..daebf1aa6b0a 100644
--- a/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
+++ b/drivers/gpu/drm/tilcdc/tilcdc_tfp410.c
@@ -240,7 +240,7 @@ static struct drm_connector *tfp410_connector_create(struct drm_device *dev,
 	connector->interlace_allowed = 0;
 	connector->doublescan_allowed = 0;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret)
 		goto fail;
 
diff --git a/drivers/gpu/drm/udl/udl_connector.c b/drivers/gpu/drm/udl/udl_connector.c
index 8fac12e1a1a4..68e88bed77ca 100644
--- a/drivers/gpu/drm/udl/udl_connector.c
+++ b/drivers/gpu/drm/udl/udl_connector.c
@@ -200,7 +200,7 @@ int udl_connector_init(struct drm_device *dev, struct drm_encoder *encoder)
 	drm_connector_helper_add(connector, &udl_connector_helper_funcs);
 
 	drm_connector_register(connector);
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	connector->polled = DRM_CONNECTOR_POLL_HPD |
 		DRM_CONNECTOR_POLL_CONNECT | DRM_CONNECTOR_POLL_DISCONNECT;
 
diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
index 91f284e1b908..fd5522fd179e 100644
--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
+++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
@@ -329,7 +329,7 @@ static struct drm_connector *vc4_hdmi_connector_init(struct drm_device *dev,
 	connector->interlace_allowed = 1;
 	connector->doublescan_allowed = 0;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/vc4/vc4_vec.c b/drivers/gpu/drm/vc4/vc4_vec.c
index 3a9a302247a2..8e7facb6514e 100644
--- a/drivers/gpu/drm/vc4/vc4_vec.c
+++ b/drivers/gpu/drm/vc4/vc4_vec.c
@@ -404,7 +404,7 @@ static struct drm_connector *vc4_vec_connector_init(struct drm_device *dev,
 				   VC4_VEC_TV_MODE_NTSC);
 	vec->tv_mode = &vc4_vec_tv_modes[VC4_VEC_TV_MODE_NTSC];
 
-	drm_mode_connector_attach_encoder(connector, vec->encoder);
+	drm_connector_attach_encoder(connector, vec->encoder);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/virtio/virtgpu_display.c b/drivers/gpu/drm/virtio/virtgpu_display.c
index ff9933e79416..25503b933599 100644
--- a/drivers/gpu/drm/virtio/virtgpu_display.c
+++ b/drivers/gpu/drm/virtio/virtgpu_display.c
@@ -292,7 +292,7 @@ static int vgdev_output_init(struct virtio_gpu_device *vgdev, int index)
 	drm_encoder_helper_add(encoder, &virtio_gpu_enc_helper_funcs);
 	encoder->possible_crtcs = 1 << index;
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 	drm_connector_register(connector);
 	return 0;
 }
diff --git a/drivers/gpu/drm/vkms/vkms_output.c b/drivers/gpu/drm/vkms/vkms_output.c
index a7c0ec9b643f..901012cb1af1 100644
--- a/drivers/gpu/drm/vkms/vkms_output.c
+++ b/drivers/gpu/drm/vkms/vkms_output.c
@@ -83,7 +83,7 @@ int vkms_output_init(struct vkms_device *vkmsdev)
 	}
 	encoder->possible_crtcs = 1;
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret) {
 		DRM_ERROR("Failed to attach connector to encoder\n");
 		goto err_attach;
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
index dc0cfda26b1b..a234fe0e1061 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
@@ -438,7 +438,7 @@ static int vmw_ldu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
index 73cf3c6e1591..dd417eb74524 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
@@ -695,7 +695,7 @@ static int vmw_sou_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
index a474d87b1af3..4cca78cab03f 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
@@ -1486,7 +1486,7 @@ static int vmw_stdu_init(struct vmw_private *dev_priv, unsigned unit)
 		goto err_free_connector;
 	}
 
-	(void) drm_mode_connector_attach_encoder(connector, encoder);
+	(void) drm_connector_attach_encoder(connector, encoder);
 	encoder->possible_crtcs = (1 << unit);
 	encoder->possible_clones = 0;
 
diff --git a/drivers/gpu/drm/zte/zx_hdmi.c b/drivers/gpu/drm/zte/zx_hdmi.c
index d073c6737500..78655269d843 100644
--- a/drivers/gpu/drm/zte/zx_hdmi.c
+++ b/drivers/gpu/drm/zte/zx_hdmi.c
@@ -326,7 +326,7 @@ static int zx_hdmi_register(struct drm_device *drm, struct zx_hdmi *hdmi)
 	drm_connector_helper_add(&hdmi->connector,
 				 &zx_hdmi_connector_helper_funcs);
 
-	drm_mode_connector_attach_encoder(&hdmi->connector, encoder);
+	drm_connector_attach_encoder(&hdmi->connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/zte/zx_tvenc.c b/drivers/gpu/drm/zte/zx_tvenc.c
index 0de1a71ca4e0..b73afb212fb2 100644
--- a/drivers/gpu/drm/zte/zx_tvenc.c
+++ b/drivers/gpu/drm/zte/zx_tvenc.c
@@ -297,7 +297,7 @@ static int zx_tvenc_register(struct drm_device *drm, struct zx_tvenc *tvenc)
 			   DRM_MODE_CONNECTOR_Composite);
 	drm_connector_helper_add(connector, &zx_tvenc_connector_helper_funcs);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/zte/zx_vga.c b/drivers/gpu/drm/zte/zx_vga.c
index 3e78ee21b8d0..23d1ff4355a0 100644
--- a/drivers/gpu/drm/zte/zx_vga.c
+++ b/drivers/gpu/drm/zte/zx_vga.c
@@ -175,7 +175,7 @@ static int zx_vga_register(struct drm_device *drm, struct zx_vga *vga)
 
 	drm_connector_helper_add(connector, &zx_vga_connector_helper_funcs);
 
-	ret = drm_mode_connector_attach_encoder(connector, encoder);
+	ret = drm_connector_attach_encoder(connector, encoder);
 	if (ret) {
 		DRM_DEV_ERROR(dev, "failed to attach encoder: %d\n", ret);
 		goto clean_connector;
diff --git a/drivers/staging/vboxvideo/vbox_mode.c b/drivers/staging/vboxvideo/vbox_mode.c
index a943d2f683ed..da4a93df8d75 100644
--- a/drivers/staging/vboxvideo/vbox_mode.c
+++ b/drivers/staging/vboxvideo/vbox_mode.c
@@ -655,7 +655,7 @@ static int vbox_connector_init(struct drm_device *dev,
 				   dev->mode_config.suggested_y_property, 0);
 	drm_connector_register(connector);
 
-	drm_mode_connector_attach_encoder(connector, encoder);
+	drm_connector_attach_encoder(connector, encoder);
 
 	return 0;
 }
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index 4411c0542871..f9a78a53bd9f 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -1085,7 +1085,7 @@ int drm_connector_init(struct drm_device *dev,
 		       int connector_type);
 int drm_connector_register(struct drm_connector *connector);
 void drm_connector_unregister(struct drm_connector *connector);
-int drm_mode_connector_attach_encoder(struct drm_connector *connector,
+int drm_connector_attach_encoder(struct drm_connector *connector,
 				      struct drm_encoder *encoder);
 
 void drm_connector_cleanup(struct drm_connector *connector);
-- 
cgit v1.2.3


From 97e14fbeb53fe060c5f6a7a07e37fd24c087ed0c Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:08 +0200
Subject: drm: drop _mode_ from remaining connector functions

Since there's very few callers of these I've decided to do them all in
one patch. With this the unecessarily long drm_mode_connector_ prefix
is gone from the codebase! The only exception being struct
drm_mode_connector_set_property, which is part of the uapi so can't be
renamed.

Again done with sed+some manual fixups for indent issues.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-8-daniel.vetter@ffwll.ch
---
 .../amd/display/amdgpu_dm/amdgpu_dm_mst_types.c    |  6 ++--
 drivers/gpu/drm/drm_atomic_helper.c                |  2 +-
 drivers/gpu/drm/drm_connector.c                    | 36 +++++++++++-----------
 drivers/gpu/drm/drm_crtc_internal.h                |  6 ++--
 drivers/gpu/drm/drm_dp_mst_topology.c              |  4 +--
 drivers/gpu/drm/drm_ioctl.c                        |  2 +-
 drivers/gpu/drm/drm_mode_object.c                  |  3 +-
 drivers/gpu/drm/drm_modes.c                        |  6 ++--
 drivers/gpu/drm/drm_probe_helper.c                 |  4 +--
 drivers/gpu/drm/i915/intel_dp.c                    |  4 +--
 drivers/gpu/drm/i915/intel_dp_mst.c                |  2 +-
 drivers/gpu/drm/msm/dsi/dsi_manager.c              |  2 +-
 drivers/gpu/drm/nouveau/dispnv50/disp.c            |  2 +-
 drivers/gpu/drm/radeon/radeon_dp_mst.c             |  2 +-
 drivers/gpu/drm/vmwgfx/vmwgfx_kms.c                |  2 +-
 include/drm/drm_connector.h                        | 14 ++++-----
 include/drm/drm_modes.h                            |  2 +-
 17 files changed, 49 insertions(+), 50 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 581bb75d08eb..65f210d3497b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -345,7 +345,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 						aconnector, connector->base.id, aconnector->mst_port);
 
 			aconnector->port = port;
-			drm_mode_connector_set_path_property(connector, pathprop);
+			drm_connector_set_path_property(connector, pathprop);
 
 			drm_connector_list_iter_end(&conn_iter);
 			aconnector->mst_connected = true;
@@ -393,7 +393,7 @@ dm_dp_add_mst_connector(struct drm_dp_mst_topology_mgr *mgr,
 		dev->mode_config.tile_property,
 		0);
 
-	drm_mode_connector_set_path_property(connector, pathprop);
+	drm_connector_set_path_property(connector, pathprop);
 
 	/*
 	 * Initialize connector state before adding the connectror to drm and
@@ -441,7 +441,7 @@ static void dm_dp_mst_hotplug(struct drm_dp_mst_topology_mgr *mgr)
 static void dm_dp_mst_link_status_reset(struct drm_connector *connector)
 {
 	mutex_lock(&connector->dev->mode_config.mutex);
-	drm_mode_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
+	drm_connector_set_link_status_property(connector, DRM_MODE_LINK_STATUS_BAD);
 	mutex_unlock(&connector->dev->mode_config.mutex);
 }
 
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 91fda6b8926e..866a2cc72ef6 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -2867,7 +2867,7 @@ static int update_output_state(struct drm_atomic_state *state,
  * resets the "link-status" property to GOOD, to force any link
  * re-training. The SETCRTC ioctl does not define whether an update does
  * need a full modeset or just a plane update, hence we're allowed to do
- * that. See also drm_mode_connector_set_link_status_property().
+ * that. See also drm_connector_set_link_status_property().
  *
  * Returns:
  * Returns 0 on success, negative errno numbers on failure.
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 8997792e2e23..8f3f672a47b0 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -852,7 +852,7 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * PATH:
  * 	Connector path property to identify how this sink is physically
  * 	connected. Used by DP MST. This should be set by calling
- * 	drm_mode_connector_set_path_property(), in the case of DP MST with the
+ * 	drm_connector_set_path_property(), in the case of DP MST with the
  * 	path property the MST manager created. Userspace cannot change this
  * 	property.
  * TILE:
@@ -863,14 +863,14 @@ DRM_ENUM_NAME_FN(drm_get_content_protection_name, drm_cp_enum_list)
  * 	are not gen-locked. Note that for tiled panels which are genlocked, like
  * 	dual-link LVDS or dual-link DSI, the driver should try to not expose the
  * 	tiling and virtualize both &drm_crtc and &drm_plane if needed. Drivers
- * 	should update this value using drm_mode_connector_set_tile_property().
+ * 	should update this value using drm_connector_set_tile_property().
  * 	Userspace cannot change this property.
  * link-status:
  *      Connector link-status property to indicate the status of link. The
  *      default value of link-status is "GOOD". If something fails during or
  *      after modeset, the kernel driver may set this to "BAD" and issue a
  *      hotplug uevent. Drivers should update this value using
- *      drm_mode_connector_set_link_status_property().
+ *      drm_connector_set_link_status_property().
  * non_desktop:
  * 	Indicates the output should be ignored for purposes of displaying a
  * 	standard desktop environment or console. This is most likely because
@@ -1425,7 +1425,7 @@ int drm_mode_create_suggested_offset_properties(struct drm_device *dev)
 EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties);
 
 /**
- * drm_mode_connector_set_path_property - set tile property on connector
+ * drm_connector_set_path_property - set tile property on connector
  * @connector: connector to set property on.
  * @path: path to use for property; must not be NULL.
  *
@@ -1437,8 +1437,8 @@ EXPORT_SYMBOL(drm_mode_create_suggested_offset_properties);
  * Returns:
  * Zero on success, negative errno on failure.
  */
-int drm_mode_connector_set_path_property(struct drm_connector *connector,
-					 const char *path)
+int drm_connector_set_path_property(struct drm_connector *connector,
+				    const char *path)
 {
 	struct drm_device *dev = connector->dev;
 	int ret;
@@ -1451,10 +1451,10 @@ int drm_mode_connector_set_path_property(struct drm_connector *connector,
 	                                       dev->mode_config.path_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_set_path_property);
+EXPORT_SYMBOL(drm_connector_set_path_property);
 
 /**
- * drm_mode_connector_set_tile_property - set tile property on connector
+ * drm_connector_set_tile_property - set tile property on connector
  * @connector: connector to set property on.
  *
  * This looks up the tile information for a connector, and creates a
@@ -1464,7 +1464,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_path_property);
  * Returns:
  * Zero on success, errno on failure.
  */
-int drm_mode_connector_set_tile_property(struct drm_connector *connector)
+int drm_connector_set_tile_property(struct drm_connector *connector)
 {
 	struct drm_device *dev = connector->dev;
 	char tile[256];
@@ -1494,7 +1494,7 @@ int drm_mode_connector_set_tile_property(struct drm_connector *connector)
 	                                       dev->mode_config.tile_property);
 	return ret;
 }
-EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
+EXPORT_SYMBOL(drm_connector_set_tile_property);
 
 /**
  * drm_connector_update_edid_property - update the edid property of a connector
@@ -1508,7 +1508,7 @@ EXPORT_SYMBOL(drm_mode_connector_set_tile_property);
  * Zero on success, negative errno on failure.
  */
 int drm_connector_update_edid_property(struct drm_connector *connector,
-					    const struct edid *edid)
+				       const struct edid *edid)
 {
 	struct drm_device *dev = connector->dev;
 	size_t size = 0;
@@ -1549,7 +1549,7 @@ int drm_connector_update_edid_property(struct drm_connector *connector,
 EXPORT_SYMBOL(drm_connector_update_edid_property);
 
 /**
- * drm_mode_connector_set_link_status_property - Set link status property of a connector
+ * drm_connector_set_link_status_property - Set link status property of a connector
  * @connector: drm connector
  * @link_status: new value of link status property (0: Good, 1: Bad)
  *
@@ -1567,8 +1567,8 @@ EXPORT_SYMBOL(drm_connector_update_edid_property);
  * it is not limited to DP or link training. For example, if we implement
  * asynchronous setcrtc, this property can be used to report any failures in that.
  */
-void drm_mode_connector_set_link_status_property(struct drm_connector *connector,
-						 uint64_t link_status)
+void drm_connector_set_link_status_property(struct drm_connector *connector,
+					    uint64_t link_status)
 {
 	struct drm_device *dev = connector->dev;
 
@@ -1576,7 +1576,7 @@ void drm_mode_connector_set_link_status_property(struct drm_connector *connector
 	connector->state->link_status = link_status;
 	drm_modeset_unlock(&dev->mode_config.connection_mutex);
 }
-EXPORT_SYMBOL(drm_mode_connector_set_link_status_property);
+EXPORT_SYMBOL(drm_connector_set_link_status_property);
 
 /**
  * drm_connector_init_panel_orientation_property -
@@ -1629,7 +1629,7 @@ int drm_connector_init_panel_orientation_property(
 }
 EXPORT_SYMBOL(drm_connector_init_panel_orientation_property);
 
-int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
+int drm_connector_set_obj_prop(struct drm_mode_object *obj,
 				    struct drm_property *property,
 				    uint64_t value)
 {
@@ -1647,8 +1647,8 @@ int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
 	return ret;
 }
 
-int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
-				       void *data, struct drm_file *file_priv)
+int drm_connector_property_set_ioctl(struct drm_device *dev,
+				     void *data, struct drm_file *file_priv)
 {
 	struct drm_mode_connector_set_property *conn_set_prop = data;
 	struct drm_mode_obj_set_property obj_set_prop = {
diff --git a/drivers/gpu/drm/drm_crtc_internal.h b/drivers/gpu/drm/drm_crtc_internal.h
index 235d40fce8b5..b61322763394 100644
--- a/drivers/gpu/drm/drm_crtc_internal.h
+++ b/drivers/gpu/drm/drm_crtc_internal.h
@@ -148,7 +148,7 @@ void drm_connector_ida_init(void);
 void drm_connector_ida_destroy(void);
 void drm_connector_unregister_all(struct drm_device *dev);
 int drm_connector_register_all(struct drm_device *dev);
-int drm_mode_connector_set_obj_prop(struct drm_mode_object *obj,
+int drm_connector_set_obj_prop(struct drm_mode_object *obj,
 				    struct drm_property *property,
 				    uint64_t value);
 int drm_connector_create_standard_properties(struct drm_device *dev);
@@ -156,8 +156,8 @@ const char *drm_get_connector_force_name(enum drm_connector_force force);
 void drm_connector_free_work_fn(struct work_struct *work);
 
 /* IOCTL */
-int drm_mode_connector_property_set_ioctl(struct drm_device *dev,
-					  void *data, struct drm_file *file_priv);
+int drm_connector_property_set_ioctl(struct drm_device *dev,
+				     void *data, struct drm_file *file_priv);
 int drm_mode_getconnector(struct drm_device *dev,
 			  void *data, struct drm_file *file_priv);
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 658830620ca3..7780567aa669 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1215,7 +1215,7 @@ static void drm_dp_add_port(struct drm_dp_mst_branch *mstb,
 		     port->pdt == DP_PEER_DEVICE_SST_SINK) &&
 		    port->port_num >= DP_MST_LOGICAL_PORT_0) {
 			port->cached_edid = drm_get_edid(port->connector, &port->aux.ddc);
-			drm_mode_connector_set_tile_property(port->connector);
+			drm_connector_set_tile_property(port->connector);
 		}
 		(*mstb->mgr->cbs->register_connector)(port->connector);
 	}
@@ -2559,7 +2559,7 @@ struct edid *drm_dp_mst_get_edid(struct drm_connector *connector, struct drm_dp_
 		edid = drm_edid_duplicate(port->cached_edid);
 	else {
 		edid = drm_get_edid(connector, &port->aux.ddc);
-		drm_mode_connector_set_tile_property(connector);
+		drm_connector_set_tile_property(connector);
 	}
 	port->has_audio = drm_detect_monitor_audio(edid);
 	drm_dp_put_port(port);
diff --git a/drivers/gpu/drm/drm_ioctl.c b/drivers/gpu/drm/drm_ioctl.c
index 3c125041a597..ea10e9a26aad 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -641,7 +641,7 @@ static const struct drm_ioctl_desc drm_ioctls[] = {
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ATTACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_DETACHMODE, drm_noop, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPERTY, drm_mode_getproperty_ioctl, DRM_UNLOCKED),
-	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_mode_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
+	DRM_IOCTL_DEF(DRM_IOCTL_MODE_SETPROPERTY, drm_connector_property_set_ioctl, DRM_MASTER|DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETPROPBLOB, drm_mode_getblob_ioctl, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_GETFB, drm_mode_getfb, DRM_UNLOCKED),
 	DRM_IOCTL_DEF(DRM_IOCTL_MODE_ADDFB, drm_mode_addfb_ioctl, DRM_UNLOCKED),
diff --git a/drivers/gpu/drm/drm_mode_object.c b/drivers/gpu/drm/drm_mode_object.c
index ce4d2fb32810..fcb0ab0abb75 100644
--- a/drivers/gpu/drm/drm_mode_object.c
+++ b/drivers/gpu/drm/drm_mode_object.c
@@ -433,8 +433,7 @@ static int set_property_legacy(struct drm_mode_object *obj,
 	drm_modeset_lock_all(dev);
 	switch (obj->type) {
 	case DRM_MODE_OBJECT_CONNECTOR:
-		ret = drm_mode_connector_set_obj_prop(obj, prop,
-						      prop_value);
+		ret = drm_connector_set_obj_prop(obj, prop, prop_value);
 		break;
 	case DRM_MODE_OBJECT_CRTC:
 		ret = drm_mode_crtc_set_obj_prop(obj, prop, prop_value);
diff --git a/drivers/gpu/drm/drm_modes.c b/drivers/gpu/drm/drm_modes.c
index f8f7eae738ab..02db9ac82d7a 100644
--- a/drivers/gpu/drm/drm_modes.c
+++ b/drivers/gpu/drm/drm_modes.c
@@ -1353,7 +1353,7 @@ void drm_mode_sort(struct list_head *mode_list)
 EXPORT_SYMBOL(drm_mode_sort);
 
 /**
- * drm_mode_connector_list_update - update the mode list for the connector
+ * drm_connector_list_update - update the mode list for the connector
  * @connector: the connector to update
  *
  * This moves the modes from the @connector probed_modes list
@@ -1363,7 +1363,7 @@ EXPORT_SYMBOL(drm_mode_sort);
  * This is just a helper functions doesn't validate any modes itself and also
  * doesn't prune any invalid modes. Callers need to do that themselves.
  */
-void drm_mode_connector_list_update(struct drm_connector *connector)
+void drm_connector_list_update(struct drm_connector *connector)
 {
 	struct drm_display_mode *pmode, *pt;
 
@@ -1412,7 +1412,7 @@ void drm_mode_connector_list_update(struct drm_connector *connector)
 		}
 	}
 }
-EXPORT_SYMBOL(drm_mode_connector_list_update);
+EXPORT_SYMBOL(drm_connector_list_update);
 
 /**
  * drm_mode_parse_command_line_for_connector - parse command line modeline for connector
diff --git a/drivers/gpu/drm/drm_probe_helper.c b/drivers/gpu/drm/drm_probe_helper.c
index 3d58e0eb26a4..a1bb157bfdfa 100644
--- a/drivers/gpu/drm/drm_probe_helper.c
+++ b/drivers/gpu/drm/drm_probe_helper.c
@@ -360,7 +360,7 @@ EXPORT_SYMBOL(drm_helper_probe_detect);
  *    using the VESA GTF/CVT formulas.
  *
  * 3. Modes are moved from the probed_modes list to the modes list. Potential
- *    duplicates are merged together (see drm_mode_connector_list_update()).
+ *    duplicates are merged together (see drm_connector_list_update()).
  *    After this step the probed_modes list will be empty again.
  *
  * 4. Any non-stale mode on the modes list then undergoes validation
@@ -485,7 +485,7 @@ retry:
 	if (count == 0)
 		goto prune;
 
-	drm_mode_connector_list_update(connector);
+	drm_connector_list_update(connector);
 
 	if (connector->interlace_allowed)
 		mode_flags |= DRM_MODE_FLAG_INTERLACE;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index c8268f377602..8caf20fb6587 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -6320,8 +6320,8 @@ static void intel_dp_modeset_retry_work_fn(struct work_struct *work)
 	/* Set connector link status to BAD and send a Uevent to notify
 	 * userspace to do a modeset.
 	 */
-	drm_mode_connector_set_link_status_property(connector,
-						    DRM_MODE_LINK_STATUS_BAD);
+	drm_connector_set_link_status_property(connector,
+					       DRM_MODE_LINK_STATUS_BAD);
 	mutex_unlock(&connector->dev->mode_config.mutex);
 	/* Send Hotplug uevent so userspace can reprobe */
 	drm_kms_helper_hotplug_event(connector->dev);
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 364330fc5d6a..0095c197f155 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -474,7 +474,7 @@ static struct drm_connector *intel_dp_add_mst_connector(struct drm_dp_mst_topolo
 	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
 
-	ret = drm_mode_connector_set_path_property(connector, pathprop);
+	ret = drm_connector_set_path_property(connector, pathprop);
 	if (ret)
 		goto err;
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 21e0dc51531d..d5006d6923e0 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -393,7 +393,7 @@ static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 		ret = dsi_dual_connector_tile_init(connector, id);
 		if (ret)
 			return ret;
-		ret = drm_mode_connector_set_tile_property(connector);
+		ret = drm_connector_set_tile_property(connector);
 		if (ret) {
 			pr_err("%s: set tile property failed, %d\n",
 					__func__, ret);
diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 475456c19b76..5a247eb71899 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -931,7 +931,7 @@ nv50_mstc_new(struct nv50_mstm *mstm, struct drm_dp_mst_port *port,
 
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&mstc->connector.base, dev->mode_config.tile_property, 0);
-	drm_mode_connector_set_path_property(&mstc->connector, path);
+	drm_connector_set_path_property(&mstc->connector, path);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_dp_mst.c b/drivers/gpu/drm/radeon/radeon_dp_mst.c
index 37956cfc0b6d..f920be236cc9 100644
--- a/drivers/gpu/drm/radeon/radeon_dp_mst.c
+++ b/drivers/gpu/drm/radeon/radeon_dp_mst.c
@@ -290,7 +290,7 @@ static struct drm_connector *radeon_dp_add_mst_connector(struct drm_dp_mst_topol
 
 	drm_object_attach_property(&connector->base, dev->mode_config.path_property, 0);
 	drm_object_attach_property(&connector->base, dev->mode_config.tile_property, 0);
-	drm_mode_connector_set_path_property(connector, pathprop);
+	drm_connector_set_path_property(connector, pathprop);
 
 	return connector;
 }
diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
index bc5fbd39cf9a..4a0f0f41afa1 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -2114,7 +2114,7 @@ int vmw_du_connector_fill_modes(struct drm_connector *connector,
 		drm_mode_probed_add(connector, mode);
 	}
 
-	drm_mode_connector_list_update(connector);
+	drm_connector_list_update(connector);
 	/* Move the prefered mode first, help apps pick the right mode. */
 	drm_mode_sort(&connector->modes);
 
diff --git a/include/drm/drm_connector.h b/include/drm/drm_connector.h
index f9a78a53bd9f..97ea41dc678f 100644
--- a/include/drm/drm_connector.h
+++ b/include/drm/drm_connector.h
@@ -919,7 +919,7 @@ struct drm_connector {
 	 * @path_blob_ptr:
 	 *
 	 * DRM blob property data for the DP MST path property. This should only
-	 * be updated by calling drm_mode_connector_set_path_property().
+	 * be updated by calling drm_connector_set_path_property().
 	 */
 	struct drm_property_blob *path_blob_ptr;
 
@@ -1046,7 +1046,7 @@ struct drm_connector {
 	 * the tiling and virtualize both &drm_crtc and &drm_plane if needed.
 	 *
 	 * This should only be updated by calling
-	 * drm_mode_connector_set_tile_property().
+	 * drm_connector_set_tile_property().
 	 */
 	struct drm_property_blob *tile_blob_ptr;
 
@@ -1191,13 +1191,13 @@ void drm_hdmi_avi_infoframe_content_type(struct hdmi_avi_infoframe *frame,
 
 int drm_mode_create_suggested_offset_properties(struct drm_device *dev);
 
-int drm_mode_connector_set_path_property(struct drm_connector *connector,
-					 const char *path);
-int drm_mode_connector_set_tile_property(struct drm_connector *connector);
+int drm_connector_set_path_property(struct drm_connector *connector,
+				    const char *path);
+int drm_connector_set_tile_property(struct drm_connector *connector);
 int drm_connector_update_edid_property(struct drm_connector *connector,
 				       const struct edid *edid);
-void drm_mode_connector_set_link_status_property(struct drm_connector *connector,
-						 uint64_t link_status);
+void drm_connector_set_link_status_property(struct drm_connector *connector,
+					    uint64_t link_status);
 int drm_connector_init_panel_orientation_property(
 	struct drm_connector *connector, int width, int height);
 
diff --git a/include/drm/drm_modes.h b/include/drm/drm_modes.h
index b159fe07fcf9..baded6514456 100644
--- a/include/drm/drm_modes.h
+++ b/include/drm/drm_modes.h
@@ -530,7 +530,7 @@ drm_mode_validate_ycbcr420(const struct drm_display_mode *mode,
 void drm_mode_prune_invalid(struct drm_device *dev,
 			    struct list_head *mode_list, bool verbose);
 void drm_mode_sort(struct list_head *mode_list);
-void drm_mode_connector_list_update(struct drm_connector *connector);
+void drm_connector_list_update(struct drm_connector *connector);
 
 /* parsing cmdline modes */
 bool
-- 
cgit v1.2.3


From 2e784a91424892cc8c75853dd40b63c0d5855af9 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:09 +0200
Subject: drm: Switch drm_plane_state to inline kerneldoc style

For consistency and to encourage more detailed documentation. While
doing this also beefed up a few of the comments, linking at least to
the setup function. Plus fixed all the hyperlinks.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-9-daniel.vetter@ffwll.ch
---
 include/drm/drm_plane.h | 86 ++++++++++++++++++++++++++++++++-----------------
 1 file changed, 56 insertions(+), 30 deletions(-)

diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index cee9dfaaa740..1a647f8f5661 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -34,31 +34,15 @@ struct drm_modeset_acquire_ctx;
 
 /**
  * struct drm_plane_state - mutable plane state
- * @plane: backpointer to the plane
- * @crtc_w: width of visible portion of plane on crtc
- * @crtc_h: height of visible portion of plane on crtc
- * @src_x: left position of visible portion of plane within
- *	plane (in 16.16)
- * @src_y: upper position of visible portion of plane within
- *	plane (in 16.16)
- * @src_w: width of visible portion of plane (in 16.16)
- * @src_h: height of visible portion of plane (in 16.16)
- * @alpha: opacity of the plane
- * @rotation: rotation of the plane
- * @zpos: priority of the given plane on crtc (optional)
- *	Note that multiple active planes on the same crtc can have an identical
- *	zpos value. The rule to solving the conflict is to compare the plane
- *	object IDs; the plane with a higher ID must be stacked on top of a
- *	plane with a lower ID.
- * @normalized_zpos: normalized value of zpos: unique, range from 0 to N-1
- *	where N is the number of active planes for given crtc. Note that
- *	the driver must set drm_mode_config.normalize_zpos or call
- *	drm_atomic_normalize_zpos() to update this before it can be trusted.
- * @src: clipped source coordinates of the plane (in 16.16)
- * @dst: clipped destination coordinates of the plane
- * @state: backpointer to global drm_atomic_state
+ *
+ * Please not that the destination coordinates @crtc_x, @crtc_y, @crtc_h and
+ * @crtc_w and the source coordinates @src_x, @src_y, @src_h and @src_w are the
+ * raw coordinates provided by userspace. Drivers should use
+ * drm_atomic_helper_check_plane_state() and only use the derived rectangles in
+ * @src and @dst to program the hardware.
  */
 struct drm_plane_state {
+	/** @plane: backpointer to the plane */
 	struct drm_plane *plane;
 
 	/**
@@ -87,7 +71,7 @@ struct drm_plane_state {
 	 * preserved.
 	 *
 	 * Drivers should store any implicit fence in this from their
-	 * &drm_plane_helper.prepare_fb callback. See drm_gem_fb_prepare_fb()
+	 * &drm_plane_helper_funcs.prepare_fb callback. See drm_gem_fb_prepare_fb()
 	 * and drm_gem_fb_simple_display_pipe_prepare_fb() for suitable helpers.
 	 */
 	struct dma_fence *fence;
@@ -108,20 +92,60 @@ struct drm_plane_state {
 	 */
 	int32_t crtc_y;
 
+	/** @crtc_w: width of visible portion of plane on crtc */
+	/** @crtc_h: height of visible portion of plane on crtc */
 	uint32_t crtc_w, crtc_h;
 
-	/* Source values are 16.16 fixed point */
-	uint32_t src_x, src_y;
+	/**
+	 * @src_x: left position of visible portion of plane within plane (in
+	 * 16.16 fixed point).
+	 */
+	uint32_t src_x;
+	/**
+	 * @src_y: upper position of visible portion of plane within plane (in
+	 * 16.16 fixed point).
+	 */
+	uint32_t src_y;
+	/** @src_w: width of visible portion of plane (in 16.16) */
+	/** @src_h: height of visible portion of plane (in 16.16) */
 	uint32_t src_h, src_w;
 
-	/* Plane opacity */
+	/**
+	 * @alpha:
+	 * Opacity of the plane with 0 as completely transparent and 0xffff as
+	 * completely opaque. See drm_plane_create_alpha_property() for more
+	 * details.
+	 */
 	u16 alpha;
 
-	/* Plane rotation */
+	/**
+	 * @rotation:
+	 * Rotation of the plane. See drm_plane_create_rotation_property() for
+	 * more details.
+	 */
 	unsigned int rotation;
 
-	/* Plane zpos */
+	/**
+	 * @zpos:
+	 * Priority of the given plane on crtc (optional).
+	 *
+	 * Note that multiple active planes on the same crtc can have an
+	 * identical zpos value. The rule to solving the conflict is to compare
+	 * the plane object IDs; the plane with a higher ID must be stacked on
+	 * top of a plane with a lower ID.
+	 *
+	 * See drm_plane_create_zpos_property() and
+	 * drm_plane_create_zpos_immutable_property() for more details.
+	 */
 	unsigned int zpos;
+
+	/**
+	 * @normalized_zpos:
+	 * Normalized value of zpos: unique, range from 0 to N-1 where N is the
+	 * number of active planes for given crtc. Note that the driver must set
+	 * &drm_mode_config.normalize_zpos or call drm_atomic_normalize_zpos() to
+	 * update this before it can be trusted.
+	 */
 	unsigned int normalized_zpos;
 
 	/**
@@ -138,7 +162,8 @@ struct drm_plane_state {
 	 */
 	enum drm_color_range color_range;
 
-	/* Clipped coordinates */
+	/** @src: clipped source coordinates of the plane (in 16.16) */
+	/** @dst: clipped destination coordinates of the plane */
 	struct drm_rect src, dst;
 
 	/**
@@ -157,6 +182,7 @@ struct drm_plane_state {
 	 */
 	struct drm_crtc_commit *commit;
 
+	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
 };
 
-- 
cgit v1.2.3


From 268bc24e861efd6892d2911bf25a3d1192aa51f5 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:10 +0200
Subject: drm: switch drm_plane to inline comments

And use that opportunity to polish the kernel doc all around:
- Beef up some of the documentation.
- Intro text for drm_plane and better links
- Fix all the hyperlinks!

v2: Fix linebreaks.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-10-daniel.vetter@ffwll.ch
---
 Documentation/gpu/drm-kms.rst | 11 +++---
 include/drm/drm_crtc.h        |  4 +-
 include/drm/drm_plane.h       | 88 +++++++++++++++++++++++++++++++------------
 3 files changed, 72 insertions(+), 31 deletions(-)

diff --git a/Documentation/gpu/drm-kms.rst b/Documentation/gpu/drm-kms.rst
index 58eed08fbe31..5dee6b8a4c12 100644
--- a/Documentation/gpu/drm-kms.rst
+++ b/Documentation/gpu/drm-kms.rst
@@ -56,11 +56,12 @@ Overview
 
 The basic object structure KMS presents to userspace is fairly simple.
 Framebuffers (represented by :c:type:`struct drm_framebuffer <drm_framebuffer>`,
-see `Frame Buffer Abstraction`_) feed into planes. One or more (or even no)
-planes feed their pixel data into a CRTC (represented by :c:type:`struct
-drm_crtc <drm_crtc>`, see `CRTC Abstraction`_) for blending. The precise
-blending step is explained in more detail in `Plane Composition Properties`_ and
-related chapters.
+see `Frame Buffer Abstraction`_) feed into planes. Planes are represented by
+:c:type:`struct drm_plane <drm_plane>`, see `Plane Abstraction`_ for more
+details. One or more (or even no) planes feed their pixel data into a CRTC
+(represented by :c:type:`struct drm_crtc <drm_crtc>`, see `CRTC Abstraction`_)
+for blending. The precise blending step is explained in more detail in `Plane
+Composition Properties`_ and related chapters.
 
 For the output routing the first step is encoders (represented by
 :c:type:`struct drm_encoder <drm_encoder>`, see `Encoder Abstraction`_). Those
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 17f4f93340b8..71b276a05e36 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -965,8 +965,8 @@ static inline unsigned int drm_crtc_index(const struct drm_crtc *crtc)
  * drm_crtc_mask - find the mask of a registered CRTC
  * @crtc: CRTC to find mask for
  *
- * Given a registered CRTC, return the mask bit of that CRTC for an
- * encoder's possible_crtcs field.
+ * Given a registered CRTC, return the mask bit of that CRTC for the
+ * &drm_encoder.possible_crtcs and &drm_plane.possible_crtcs fields.
  */
 static inline uint32_t drm_crtc_mask(const struct drm_crtc *crtc)
 {
diff --git a/include/drm/drm_plane.h b/include/drm/drm_plane.h
index 1a647f8f5661..8a152dc16ea5 100644
--- a/include/drm/drm_plane.h
+++ b/include/drm/drm_plane.h
@@ -525,30 +525,27 @@ enum drm_plane_type {
 
 /**
  * struct drm_plane - central DRM plane control structure
- * @dev: DRM device this plane belongs to
- * @head: for list management
- * @name: human readable name, can be overwritten by the driver
- * @base: base mode object
- * @possible_crtcs: pipes this plane can be bound to
- * @format_types: array of formats supported by this plane
- * @format_count: number of formats supported
- * @format_default: driver hasn't supplied supported formats for the plane
- * @modifiers: array of modifiers supported by this plane
- * @modifier_count: number of modifiers supported
- * @old_fb: Temporary tracking of the old fb while a modeset is ongoing. Used by
- * 	drm_mode_set_config_internal() to implement correct refcounting.
- * @funcs: helper functions
- * @properties: property tracking for this plane
- * @type: type of plane (overlay, primary, cursor)
- * @alpha_property: alpha property for this plane
- * @zpos_property: zpos property for this plane
- * @rotation_property: rotation property for this plane
- * @helper_private: mid-layer private data
+ *
+ * Planes represent the scanout hardware of a display block. They receive their
+ * input data from a &drm_framebuffer and feed it to a &drm_crtc. Planes control
+ * the color conversion, see `Plane Composition Properties`_ for more details,
+ * and are also involved in the color conversion of input pixels, see `Color
+ * Management Properties`_ for details on that.
  */
 struct drm_plane {
+	/** @dev: DRM device this plane belongs to */
 	struct drm_device *dev;
+
+	/**
+	 * @head:
+	 *
+	 * List of all planes on @dev, linked from &drm_mode_config.plane_list.
+	 * Invariant over the lifetime of @dev and therefore does not need
+	 * locking.
+	 */
 	struct list_head head;
 
+	/** @name: human readable name, can be overwritten by the driver */
 	char *name;
 
 	/**
@@ -562,35 +559,62 @@ struct drm_plane {
 	 */
 	struct drm_modeset_lock mutex;
 
+	/** @base: base mode object */
 	struct drm_mode_object base;
 
+	/**
+	 * @possible_crtcs: pipes this plane can be bound to constructed from
+	 * drm_crtc_mask()
+	 */
 	uint32_t possible_crtcs;
+	/** @format_types: array of formats supported by this plane */
 	uint32_t *format_types;
+	/** @format_count: Size of the array pointed at by @format_types. */
 	unsigned int format_count;
+	/**
+	 * @format_default: driver hasn't supplied supported formats for the
+	 * plane. Used by the drm_plane_init compatibility wrapper only.
+	 */
 	bool format_default;
 
+	/** @modifiers: array of modifiers supported by this plane */
 	uint64_t *modifiers;
+	/** @modifier_count: Size of the array pointed at by @modifier_count. */
 	unsigned int modifier_count;
 
 	/**
-	 * @crtc: Currently bound CRTC, only really meaningful for non-atomic
-	 * drivers.  Atomic drivers should instead check &drm_plane_state.crtc.
+	 * @crtc:
+	 *
+	 * Currently bound CRTC, only meaningful for non-atomic drivers. For
+	 * atomic drivers this is forced to be NULL, atomic drivers should
+	 * instead check &drm_plane_state.crtc.
 	 */
 	struct drm_crtc *crtc;
 
 	/**
-	 * @fb: Currently bound framebuffer, only really meaningful for
-	 * non-atomic drivers.  Atomic drivers should instead check
-	 * &drm_plane_state.fb.
+	 * @fb:
+	 *
+	 * Currently bound framebuffer, only meaningful for non-atomic drivers.
+	 * For atomic drivers this is forced to be NULL, atomic drivers should
+	 * instead check &drm_plane_state.fb.
 	 */
 	struct drm_framebuffer *fb;
 
+	/**
+	 * @old_fb:
+	 *
+	 * Temporary tracking of the old fb while a modeset is ongoing. Only
+	 * used by non-atomic drivers, forced to be NULL for atomic drivers.
+	 */
 	struct drm_framebuffer *old_fb;
 
+	/** @funcs: plane control functions */
 	const struct drm_plane_funcs *funcs;
 
+	/** @properties: property tracking for this plane */
 	struct drm_object_properties properties;
 
+	/** @type: Type of plane, see &enum drm_plane_type for details. */
 	enum drm_plane_type type;
 
 	/**
@@ -599,6 +623,7 @@ struct drm_plane {
 	 */
 	unsigned index;
 
+	/** @helper_private: mid-layer private data */
 	const struct drm_plane_helper_funcs *helper_private;
 
 	/**
@@ -616,8 +641,23 @@ struct drm_plane {
 	 */
 	struct drm_plane_state *state;
 
+	/**
+	 * @alpha_property:
+	 * Optional alpha property for this plane. See
+	 * drm_plane_create_alpha_property().
+	 */
 	struct drm_property *alpha_property;
+	/**
+	 * @zpos_property:
+	 * Optional zpos property for this plane. See
+	 * drm_plane_create_zpos_property().
+	 */
 	struct drm_property *zpos_property;
+	/**
+	 * @rotation_property:
+	 * Optional rotation property for this plane. See
+	 * drm_plane_create_rotation_property().
+	 */
 	struct drm_property *rotation_property;
 
 	/**
-- 
cgit v1.2.3


From 15185aa20cbdf4404198b74f86a1ce9f6fe0fad7 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:12 +0200
Subject: drm/doc: move struct drm_crtc to in-line comments

And clean them up a bit, as usual.

v2: Fix nits (Sean).

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-12-daniel.vetter@ffwll.ch
---
 include/drm/drm_crtc.h | 126 +++++++++++++++++++++++++++++++++++++------------
 1 file changed, 97 insertions(+), 29 deletions(-)

diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 71b276a05e36..7fe06ad6e5f0 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -747,35 +747,25 @@ struct drm_crtc_funcs {
 
 /**
  * struct drm_crtc - central CRTC control structure
- * @dev: parent DRM device
- * @port: OF node used by drm_of_find_possible_crtcs()
- * @head: list management
- * @name: human readable name, can be overwritten by the driver
- * @mutex: per-CRTC locking
- * @base: base KMS object for ID tracking etc.
- * @primary: primary plane for this CRTC
- * @cursor: cursor plane for this CRTC
- * @cursor_x: current x position of the cursor, used for universal cursor planes
- * @cursor_y: current y position of the cursor, used for universal cursor planes
- * @enabled: is this CRTC enabled?
- * @mode: current mode timings
- * @hwmode: mode timings as programmed to hw regs
- * @x: x position on screen
- * @y: y position on screen
- * @funcs: CRTC control functions
- * @gamma_size: size of gamma ramp
- * @gamma_store: gamma ramp values
- * @helper_private: mid-layer private data
- * @properties: property tracking for this CRTC
  *
  * Each CRTC may have one or more connectors associated with it.  This structure
  * allows the CRTC to be controlled.
  */
 struct drm_crtc {
+	/** @dev: parent DRM device */
 	struct drm_device *dev;
+	/** @port: OF node used by drm_of_find_possible_crtcs(). */
 	struct device_node *port;
+	/**
+	 * @head:
+	 *
+	 * List of all CRTCs on @dev, linked from &drm_mode_config.crtc_list.
+	 * Invariant over the lifetime of @dev and therefore does not need
+	 * locking.
+	 */
 	struct list_head head;
 
+	/** @name: human readable name, can be overwritten by the driver */
 	char *name;
 
 	/**
@@ -790,10 +780,25 @@ struct drm_crtc {
 	 */
 	struct drm_modeset_lock mutex;
 
+	/** @base: base KMS object for ID tracking etc. */
 	struct drm_mode_object base;
 
-	/* primary and cursor planes for CRTC */
+	/**
+	 * @primary:
+	 * Primary plane for this CRTC. Note that this is only
+	 * relevant for legacy IOCTL, it specifies the plane implicitly used by
+	 * the SETCRTC and PAGE_FLIP IOCTLs. It does not have any significance
+	 * beyond that.
+	 */
 	struct drm_plane *primary;
+
+	/**
+	 * @cursor:
+	 * Cursor plane for this CRTC. Note that this is only relevant for
+	 * legacy IOCTL, it specifies the plane implicitly used by the SETCURSOR
+	 * and SETCURSOR2 IOCTLs. It does not have any significance
+	 * beyond that.
+	 */
 	struct drm_plane *cursor;
 
 	/**
@@ -802,30 +807,94 @@ struct drm_crtc {
 	 */
 	unsigned index;
 
-	/* position of cursor plane on crtc */
+	/**
+	 * @cursor_x: Current x position of the cursor, used for universal
+	 * cursor planes because the SETCURSOR IOCTL only can update the
+	 * framebuffer without supplying the coordinates. Drivers should not use
+	 * this directly, atomic drivers should look at &drm_plane_state.crtc_x
+	 * of the cursor plane instead.
+	 */
 	int cursor_x;
+	/**
+	 * @cursor_y: Current y position of the cursor, used for universal
+	 * cursor planes because the SETCURSOR IOCTL only can update the
+	 * framebuffer without supplying the coordinates. Drivers should not use
+	 * this directly, atomic drivers should look at &drm_plane_state.crtc_y
+	 * of the cursor plane instead.
+	 */
 	int cursor_y;
 
+	/**
+	 * @enabled:
+	 *
+	 * Is this CRTC enabled? Should only be used by legacy drivers, atomic
+	 * drivers should instead consult &drm_crtc_state.enable and
+	 * &drm_crtc_state.active. Atomic drivers can update this by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
 	bool enabled;
 
-	/* Requested mode from modesetting. */
+	/**
+	 * @mode:
+	 *
+	 * Current mode timings. Should only be used by legacy drivers, atomic
+	 * drivers should instead consult &drm_crtc_state.mode. Atomic drivers
+	 * can update this by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
 	struct drm_display_mode mode;
 
-	/* Programmed mode in hw, after adjustments for encoders,
-	 * crtc, panel scaling etc. Needed for timestamping etc.
+	/**
+	 * @hwmode:
+	 *
+	 * Programmed mode in hw, after adjustments for encoders, crtc, panel
+	 * scaling etc. Should only be used by legacy drivers, for high
+	 * precision vblank timestamps in
+	 * drm_calc_vbltimestamp_from_scanoutpos().
+	 *
+	 * Note that atomic drivers should not use this, but instead use
+	 * &drm_crtc_state.adjusted_mode. And for high-precision timestamps
+	 * drm_calc_vbltimestamp_from_scanoutpos() used &drm_vblank_crtc.hwmode,
+	 * which is filled out by calling drm_calc_timestamping_constants().
 	 */
 	struct drm_display_mode hwmode;
 
-	int x, y;
+	/**
+	 * @x:
+	 * x position on screen. Should only be used by legacy drivers, atomic
+	 * drivers should look at &drm_plane_state.crtc_x of the primary plane
+	 * instead. Updated by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
+	int x;
+	/**
+	 * @y:
+	 * y position on screen. Should only be used by legacy drivers, atomic
+	 * drivers should look at &drm_plane_state.crtc_y of the primary plane
+	 * instead. Updated by calling
+	 * drm_atomic_helper_update_legacy_modeset_state().
+	 */
+	int y;
+
+	/** @funcs: CRTC control functions */
 	const struct drm_crtc_funcs *funcs;
 
-	/* Legacy FB CRTC gamma size for reporting to userspace */
+	/**
+	 * @gamma_size: Size of legacy gamma ramp reported to userspace. Set up
+	 * by calling drm_mode_crtc_set_gamma_size().
+	 */
 	uint32_t gamma_size;
+
+	/**
+	 * @gamma_store: Gamma ramp values used by the legacy SETGAMMA and
+	 * GETGAMMA IOCTls. Set up by calling drm_mode_crtc_set_gamma_size().
+	 */
 	uint16_t *gamma_store;
 
-	/* if you are using the helper */
+	/** @helper_private: mid-layer private data */
 	const struct drm_crtc_helper_funcs *helper_private;
 
+	/** @properties: property tracking for this CRTC */
 	struct drm_object_properties properties;
 
 	/**
@@ -895,7 +964,6 @@ struct drm_crtc {
 	 *
 	 * spinlock to protect the fences in the fence_context.
 	 */
-
 	spinlock_t fence_lock;
 	/**
 	 * @fence_seqno:
-- 
cgit v1.2.3


From 9bea6dd081d1f1411a37da8ff066caf4aeb5ab31 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:13 +0200
Subject: drm/doc: Group the fb gem helpers better
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of spreading them all over the place.

Cc: Noralf Trønnes <noralf@tronnes.org>
Acked-by: Noralf Trønnes <noralf@tronnes.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-13-daniel.vetter@ffwll.ch
---
 Documentation/gpu/drm-kms-helpers.rst | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst
index 62de583e9efe..a0a75342d732 100644
--- a/Documentation/gpu/drm-kms-helpers.rst
+++ b/Documentation/gpu/drm-kms-helpers.rst
@@ -109,6 +109,15 @@ Framebuffer CMA Helper Functions Reference
 
 .. _drm_bridges:
 
+Framebuffer GEM Helper Reference
+================================
+
+.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
+   :doc: overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
+   :export:
+
 Bridges
 =======
 
@@ -291,15 +300,6 @@ Auxiliary Modeset Helpers
 .. kernel-doc:: drivers/gpu/drm/drm_modeset_helper.c
    :export:
 
-Framebuffer GEM Helper Reference
-================================
-
-.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
-   :doc: overview
-
-.. kernel-doc:: drivers/gpu/drm/drm_gem_framebuffer_helper.c
-   :export:
-
 Legacy Plane Helper Reference
 =============================
 
-- 
cgit v1.2.3


From 7f9e7ec92be93e73ef552e6185a3ada72a90e1a9 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:14 +0200
Subject: drm/doc: Include drm_of.c helpers

Fixes a dead link I spotted in the struct drm_crtc docs. Comments
themselves are in a surprisingly good state.

v2: Fix subject typo (Sean).

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-14-daniel.vetter@ffwll.ch
---
 Documentation/gpu/drm-kms-helpers.rst | 9 +++++++++
 drivers/gpu/drm/drm_of.c              | 9 ++++++++-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/Documentation/gpu/drm-kms-helpers.rst b/Documentation/gpu/drm-kms-helpers.rst
index a0a75342d732..f9cfcdcdf024 100644
--- a/Documentation/gpu/drm-kms-helpers.rst
+++ b/Documentation/gpu/drm-kms-helpers.rst
@@ -300,6 +300,15 @@ Auxiliary Modeset Helpers
 .. kernel-doc:: drivers/gpu/drm/drm_modeset_helper.c
    :export:
 
+OF/DT Helpers
+=============
+
+.. kernel-doc:: drivers/gpu/drm/drm_of.c
+   :doc: overview
+
+.. kernel-doc:: drivers/gpu/drm/drm_of.c
+   :export:
+
 Legacy Plane Helper Reference
 =============================
 
diff --git a/drivers/gpu/drm/drm_of.c b/drivers/gpu/drm/drm_of.c
index 260612958cbe..2763a5ec845b 100644
--- a/drivers/gpu/drm/drm_of.c
+++ b/drivers/gpu/drm/drm_of.c
@@ -9,6 +9,13 @@
 #include <drm/drm_panel.h>
 #include <drm/drm_of.h>
 
+/**
+ * DOC: overview
+ *
+ * A set of helper functions to aid DRM drivers in parsing standard DT
+ * properties.
+ */
+
 static void drm_release_of(struct device *dev, void *data)
 {
 	of_node_put(data);
@@ -94,7 +101,7 @@ EXPORT_SYMBOL_GPL(drm_of_component_match_add);
  * drm_of_component_probe - Generic probe function for a component based master
  * @dev: master device containing the OF node
  * @compare_of: compare function used for matching components
- * @master_ops: component master ops to be used
+ * @m_ops: component master ops to be used
  *
  * Parse the platform device OF node and bind all the components associated
  * with the master. Interface ports are added before the encoders in order to
-- 
cgit v1.2.3


From 620eec75f35ce470cb59410b2ed91ad750b867a2 Mon Sep 17 00:00:00 2001
From: Daniel Vetter <daniel.vetter@ffwll.ch>
Date: Mon, 9 Jul 2018 10:40:15 +0200
Subject: drm/doc: use inline kerneldoc style for drm_crtc_state

Lots of added text here since I think the various control flow bits
are worth explaining a bit better.

v2: Fix conflict with Boris' no_vblank addition.

Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Daniel Vetter <daniel.vetter@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180709084016.23750-15-daniel.vetter@ffwll.ch
---
 include/drm/drm_crtc.h | 110 ++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 86 insertions(+), 24 deletions(-)

diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 7fe06ad6e5f0..92e7fc7f05a4 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -77,21 +77,6 @@ struct drm_plane_helper_funcs;
 
 /**
  * struct drm_crtc_state - mutable CRTC state
- * @crtc: backpointer to the CRTC
- * @enable: whether the CRTC should be enabled, gates all other state
- * @active: whether the CRTC is actively displaying (used for DPMS)
- * @planes_changed: planes on this crtc are updated
- * @mode_changed: @mode or @enable has been changed
- * @active_changed: @active has been toggled.
- * @connectors_changed: connectors to this crtc have been updated
- * @zpos_changed: zpos values of planes on this crtc have been updated
- * @color_mgmt_changed: color management properties have changed (degamma or
- *	gamma LUT or CSC matrix)
- * @plane_mask: bitmask of (1 << drm_plane_index(plane)) of attached planes
- * @connector_mask: bitmask of (1 << drm_connector_index(connector)) of attached connectors
- * @encoder_mask: bitmask of (1 << drm_encoder_index(encoder)) of attached encoders
- * @mode_blob: &drm_property_blob for @mode
- * @state: backpointer to global drm_atomic_state
  *
  * Note that the distinction between @enable and @active is rather subtile:
  * Flipping @active while @enable is set without changing anything else may
@@ -102,21 +87,86 @@ struct drm_plane_helper_funcs;
  *
  * The three booleans active_changed, connectors_changed and mode_changed are
  * intended to indicate whether a full modeset is needed, rather than strictly
- * describing what has changed in a commit.
- * See also: drm_atomic_crtc_needs_modeset()
+ * describing what has changed in a commit. See also:
+ * drm_atomic_crtc_needs_modeset()
+ *
+ * WARNING: Transitional helpers (like drm_helper_crtc_mode_set() or
+ * drm_helper_crtc_mode_set_base()) do not maintain many of the derived control
+ * state like @plane_mask so drivers not converted over to atomic helpers should
+ * not rely on these being accurate!
  */
 struct drm_crtc_state {
+	/** @crtc: backpointer to the CRTC */
 	struct drm_crtc *crtc;
 
+	/**
+	 * @enable: Whether the CRTC should be enabled, gates all other state.
+	 * This controls reservations of shared resources. Actual hardware state
+	 * is controlled by @active.
+	 */
 	bool enable;
+
+	/**
+	 * @active: Whether the CRTC is actively displaying (used for DPMS).
+	 * Implies that @enable is set. The driver must not release any shared
+	 * resources if @active is set to false but @enable still true, because
+	 * userspace expects that a DPMS ON always succeeds.
+	 *
+	 * Hence drivers must not consult @active in their various
+	 * &drm_mode_config_funcs.atomic_check callback to reject an atomic
+	 * commit. They can consult it to aid in the computation of derived
+	 * hardware state, since even in the DPMS OFF state the display hardware
+	 * should be as much powered down as when the CRTC is completely
+	 * disabled through setting @enable to false.
+	 */
 	bool active;
 
-	/* computed state bits used by helpers and drivers */
+	/**
+	 * @planes_changed: Planes on this crtc are updated. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow.
+	 */
 	bool planes_changed : 1;
+
+	/**
+	 * @mode_changed: @mode or @enable has been changed. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow. See also
+	 * drm_atomic_crtc_needs_modeset().
+	 *
+	 * Drivers are supposed to set this for any CRTC state changes that
+	 * require a full modeset. They can also reset it to false if e.g. a
+	 * @mode change can be done without a full modeset by only changing
+	 * scaler settings.
+	 */
 	bool mode_changed : 1;
+
+	/**
+	 * @active_changed: @active has been toggled. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow. See also
+	 * drm_atomic_crtc_needs_modeset().
+	 */
 	bool active_changed : 1;
+
+	/**
+	 * @connectors_changed: Connectors to this crtc have been updated,
+	 * either in their state or routing. Used by the atomic
+	 * helpers and drivers to steer the atomic commit control flow. See also
+	 * drm_atomic_crtc_needs_modeset().
+	 *
+	 * Drivers are supposed to set this as-needed from their own atomic
+	 * check code, e.g. from &drm_encoder_helper_funcs.atomic_check
+	 */
 	bool connectors_changed : 1;
+	/**
+	 * @zpos_changed: zpos values of planes on this crtc have been updated.
+	 * Used by the atomic helpers and drivers to steer the atomic commit
+	 * control flow.
+	 */
 	bool zpos_changed : 1;
+	/**
+	 * @color_mgmt_changed: Color management properties have changed
+	 * (@gamma_lut, @degamma_lut or @ctm). Used by the atomic helpers and
+	 * drivers to steer the atomic commit control flow.
+	 */
 	bool color_mgmt_changed : 1;
 
 	/**
@@ -142,14 +192,22 @@ struct drm_crtc_state {
 	 */
 	bool no_vblank : 1;
 
-	/* attached planes bitmask:
-	 * WARNING: transitional helpers do not maintain plane_mask so
-	 * drivers not converted over to atomic helpers should not rely
-	 * on plane_mask being accurate!
+	/**
+	 * @plane_mask: Bitmask of drm_plane_mask(plane) of planes attached to
+	 * this CRTC.
 	 */
 	u32 plane_mask;
 
+	/**
+	 * @connector_mask: Bitmask of drm_connector_mask(connector) of
+	 * connectors attached to this CRTC.
+	 */
 	u32 connector_mask;
+
+	/**
+	 * @encoder_mask: Bitmask of drm_encoder_mask(encoder) of encoders
+	 * attached to this CRTC.
+	 */
 	u32 encoder_mask;
 
 	/**
@@ -159,7 +217,7 @@ struct drm_crtc_state {
 	 * differences between the mode requested by userspace in @mode and what
 	 * is actually programmed into the hardware.
 	 *
-	 * For drivers using drm_bridge, this stores hardware display timings
+	 * For drivers using &drm_bridge, this stores hardware display timings
 	 * used between the CRTC and the first bridge. For other drivers, the
 	 * meaning of the adjusted_mode field is purely driver implementation
 	 * defined information, and will usually be used to store the hardware
@@ -184,7 +242,10 @@ struct drm_crtc_state {
 	 */
 	struct drm_display_mode mode;
 
-	/* blob property to expose current mode to atomic userspace */
+	/**
+	 * @mode_blob: &drm_property_blob for @mode, for exposing the mode to
+	 * atomic userspace.
+	 */
 	struct drm_property_blob *mode_blob;
 
 	/**
@@ -288,6 +349,7 @@ struct drm_crtc_state {
 	 */
 	struct drm_crtc_commit *commit;
 
+	/** @state: backpointer to global drm_atomic_state */
 	struct drm_atomic_state *state;
 };
 
-- 
cgit v1.2.3


From 6710fcfca5ccb690e02d72376950c61b19570525 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 13 Jul 2018 18:26:58 +0100
Subject: drm/i915/guc: Protect against no desc-pool on premature shutdown
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Hopefully the final hack to get guc fault-injection happy before we can
clean it up again, starting from a known good baseline...

[  383.017530] BUG: unable to handle kernel NULL pointer dereference at 00000000000000a0
[  383.017556] Oops: 0000 [#1] PREEMPT SMP PTI
[  383.017566] CPU: 7 PID: 4725 Comm: drv_module_relo Tainted: G     U            4.18.0-rc4-CI-CI_DRM_4485+ #1
[  383.017581] Hardware name: Micro-Star International Co., Ltd. MS-7B54/Z370M MORTAR (MS-7B54), BIOS 1.10 12/28/2017
[  383.017664] RIP: 0010:guc_stage_desc_pool_destroy+0x17/0xe0 [i915]
[  383.017674] Code: 59 a0 c6 05 02 59 18 00 01 e8 5e 01 c3 e0 eb b1 0f 1f 00 53 48 89 fb 48 81 c7 90 02 00 00 e8 60 64 45 e1 48 8b 83 80 02 00 00 <48> 8b 80 a0 00 00 00 48 8b 90 68 02 00 00 48 83 ea 01 48 81 fa ff
[  383.017771] RSP: 0018:ffffc900004bbdd0 EFLAGS: 00010282
[  383.017782] RAX: 0000000000000000 RBX: ffff88012ff41300 RCX: 0000000000000000
[  383.017794] RDX: 0000000000000000 RSI: ffffc900004bbd80 RDI: 0000000000000000
[  383.017805] RBP: ffff88012ff40000 R08: 00000000d876ee11 R09: 0000000000000000
[  383.017817] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88012ff47770
[  383.017828] R13: ffff88012ff40068 R14: ffff880264392ef8 R15: ffffffffa0639950
[  383.017840] FS:  00007fb9c18c8980(0000) GS:ffff8802663c0000(0000) knlGS:0000000000000000
[  383.017853] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  383.017864] CR2: 00000000000000a0 CR3: 00000001df6cc003 CR4: 00000000003606e0
[  383.017875] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  383.017887] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[  383.017898] Call Trace:
[  383.017962]  intel_uc_fini+0x34/0xd0 [i915]
[  383.018020]  i915_gem_fini+0x5c/0x100 [i915]
[  383.018093]  i915_driver_unload+0xd2/0x110 [i915]
[  383.018150]  i915_pci_remove+0x10/0x20 [i915]
[  383.018165]  pci_device_remove+0x36/0xb0
[  383.018179]  device_release_driver_internal+0x185/0x250
[  383.018193]  driver_detach+0x35/0x70
[  383.018205]  bus_remove_driver+0x53/0xd0
[  383.018217]  pci_unregister_driver+0x25/0xa0
[  383.018232]  __se_sys_delete_module+0x162/0x210
[  383.018245]  ? do_syscall_64+0xd/0x190
[  383.018257]  do_syscall_64+0x55/0x190
[  383.018270]  entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  383.018282] RIP: 0033:0x7fb9c0f7c1b7
[  383.018290] Code: 73 01 c3 48 8b 0d d1 8c 2c 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 b8 b0 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d a1 8c 2c 00 f7 d8 64 89 01 48
[  383.018408] RSP: 002b:00007fffa01c2aa8 EFLAGS: 00000206 ORIG_RAX: 00000000000000b0
[  383.018425] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007fb9c0f7c1b7
[  383.018440] RDX: 0000000000000000 RSI: 0000000000000800 RDI: 0000560b96856d48
[  383.018454] RBP: 0000560b96856ce0 R08: 0000560b96856d4c R09: 00007fffa01c2ae8
[  383.018468] R10: 00007fffa01c1aa4 R11: 0000000000000206 R12: 0000560b954f7470

Testcase: igt/drv_module_reload/basic-reload-inject
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180713172658.14070-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 22367131d6a1..cc444dc5f3ad 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -1184,7 +1184,8 @@ void intel_guc_submission_fini(struct intel_guc *guc)
 	guc_clients_destroy(guc);
 	WARN_ON(!guc_verify_doorbells(guc));
 
-	guc_stage_desc_pool_destroy(guc);
+	if (guc->stage_desc_pool)
+		guc_stage_desc_pool_destroy(guc);
 }
 
 static void guc_interrupts_capture(struct drm_i915_private *dev_priv)
-- 
cgit v1.2.3


From 4f91da26c81145f255cb153152ffed70014b1c41 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 11 Jul 2018 20:36:38 -0700
Subject: xdp: add per mode attributes for attached programs

In preparation for support of simultaneous driver and hardware XDP
support add per-mode attributes.  The catch-all IFLA_XDP_PROG_ID
will still be reported, but user space can now also access the
program ID in a new IFLA_XDP_<mode>_PROG_ID attribute.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/if_link.h |  3 +++
 net/core/rtnetlink.c         | 30 ++++++++++++++++++++++++++----
 2 files changed, 29 insertions(+), 4 deletions(-)

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index cf01b6824244..bc86c2b105ec 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -928,6 +928,9 @@ enum {
 	IFLA_XDP_ATTACHED,
 	IFLA_XDP_FLAGS,
 	IFLA_XDP_PROG_ID,
+	IFLA_XDP_DRV_PROG_ID,
+	IFLA_XDP_SKB_PROG_ID,
+	IFLA_XDP_HW_PROG_ID,
 	__IFLA_XDP_MAX,
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5ef61222fdef..b40242459907 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -964,7 +964,8 @@ static size_t rtnl_xdp_size(void)
 {
 	size_t xdp_size = nla_total_size(0) +	/* nest IFLA_XDP */
 			  nla_total_size(1) +	/* XDP_ATTACHED */
-			  nla_total_size(4);	/* XDP_PROG_ID */
+			  nla_total_size(4) +	/* XDP_PROG_ID */
+			  nla_total_size(4);	/* XDP_<mode>_PROG_ID */
 
 	return xdp_size;
 }
@@ -1378,16 +1379,17 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 {
+	u32 prog_attr, prog_id;
 	struct nlattr *xdp;
-	u32 prog_id;
 	int err;
+	u8 mode;
 
 	xdp = nla_nest_start(skb, IFLA_XDP);
 	if (!xdp)
 		return -EMSGSIZE;
 
-	err = nla_put_u8(skb, IFLA_XDP_ATTACHED,
-			 rtnl_xdp_attached_mode(dev, &prog_id));
+	mode = rtnl_xdp_attached_mode(dev, &prog_id);
+	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode);
 	if (err)
 		goto err_cancel;
 
@@ -1395,6 +1397,26 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 		err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
 		if (err)
 			goto err_cancel;
+
+		switch (mode) {
+		case XDP_ATTACHED_DRV:
+			prog_attr = IFLA_XDP_DRV_PROG_ID;
+			break;
+		case XDP_ATTACHED_SKB:
+			prog_attr = IFLA_XDP_SKB_PROG_ID;
+			break;
+		case XDP_ATTACHED_HW:
+			prog_attr = IFLA_XDP_HW_PROG_ID;
+			break;
+		case XDP_ATTACHED_NONE:
+		default:
+			err = -EINVAL;
+			goto err_cancel;
+		}
+
+		err = nla_put_u32(skb, prog_attr, prog_id);
+		if (err)
+			goto err_cancel;
 	}
 
 	nla_nest_end(skb, xdp);
-- 
cgit v1.2.3


From 6b8675897338f874c41612655a85d8e10cdb23d8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 11 Jul 2018 20:36:39 -0700
Subject: xdp: don't make drivers report attachment mode

prog_attached of struct netdev_bpf should have been superseded
by simply setting prog_id long time ago, but we kept it around
to allow offloading drivers to communicate attachment mode (drv
vs hw).  Subsequently drivers were also allowed to report back
attachment flags (prog_flags), and since nowadays only programs
attached will XDP_FLAGS_HW_MODE can get offloaded, we can tell
the attachment mode from the flags driver reports.  Remove
prog_attached member.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c       | 1 -
 drivers/net/ethernet/cavium/thunder/nicvf_main.c    | 1 -
 drivers/net/ethernet/intel/i40e/i40e_main.c         | 1 -
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c       | 1 -
 drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c   | 1 -
 drivers/net/ethernet/mellanox/mlx4/en_netdev.c      | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c   | 1 -
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 3 ---
 drivers/net/ethernet/qlogic/qede/qede_filter.c      | 1 -
 drivers/net/netdevsim/bpf.c                         | 1 -
 drivers/net/tun.c                                   | 1 -
 drivers/net/virtio_net.c                            | 1 -
 include/linux/netdevice.h                           | 5 -----
 net/core/dev.c                                      | 7 +++----
 net/core/rtnetlink.c                                | 8 ++++++--
 15 files changed, 9 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 1f0e872d0667..0584d07c8c33 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -219,7 +219,6 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		rc = bnxt_xdp_set(bp, xdp->prog);
 		break;
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!bp->xdp_prog;
 		xdp->prog_id = bp->xdp_prog ? bp->xdp_prog->aux->id : 0;
 		rc = 0;
 		break;
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 135766c4296b..768f584f8392 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -1848,7 +1848,6 @@ static int nicvf_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return nicvf_xdp_setup(nic, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nic->xdp_prog;
 		xdp->prog_id = nic->xdp_prog ? nic->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 426b0ccb1fc6..51762428b40e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -11841,7 +11841,6 @@ static int i40e_xdp(struct net_device *dev,
 	case XDP_SETUP_PROG:
 		return i40e_xdp_setup(vsi, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = i40e_enabled_xdp_vsi(vsi);
 		xdp->prog_id = vsi->xdp_prog ? vsi->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index a8e21becb619..3862fea1c923 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -9966,7 +9966,6 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbe_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			adapter->xdp_prog->aux->id : 0;
 		return 0;
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 59416eddd840..d86446d202d5 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -4462,7 +4462,6 @@ static int ixgbevf_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return ixgbevf_xdp_setup(dev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!(adapter->xdp_prog);
 		xdp->prog_id = adapter->xdp_prog ?
 			       adapter->xdp_prog->aux->id : 0;
 		return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
index 65eb06e017e4..6785661d1a72 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c
@@ -2926,7 +2926,6 @@ static int mlx4_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx4_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx4_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index bbd2fd0b2e06..e4a9a0768a81 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4192,7 +4192,6 @@ static int mlx5e_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return mlx5e_xdp_set(dev, xdp->prog);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = mlx5e_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 7df5ca37bfb8..d20714598613 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3459,9 +3459,6 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 		return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags,
 					 xdp->extack);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!nn->xdp_prog;
-		if (nn->dp.bpf_offload_xdp)
-			xdp->prog_attached = XDP_ATTACHED_HW;
 		xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
 		xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0;
 		return 0;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index b823bfe2ea4d..f9a327c821eb 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1116,7 +1116,6 @@ int qede_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG:
 		return qede_xdp_set(edev, xdp->prog);
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!edev->xdp_prog;
 		xdp->prog_id = edev->xdp_prog ? edev->xdp_prog->aux->id : 0;
 		return 0;
 	default:
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 75c25306d234..712e6f918065 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -567,7 +567,6 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
 	case XDP_QUERY_PROG:
-		bpf->prog_attached = ns->xdp_prog_mode;
 		bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0;
 		bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0;
 		return 0;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index a192a017cc68..49a50219d0da 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1268,7 +1268,6 @@ static int tun_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return tun_xdp_set(dev, xdp->prog, xdp->extack);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = tun_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 53085c63277b..2ff08bc103a9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2343,7 +2343,6 @@ static int virtnet_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 		return virtnet_xdp_set(dev, xdp->prog, xdp->extack);
 	case XDP_QUERY_PROG:
 		xdp->prog_id = virtnet_xdp_query(dev);
-		xdp->prog_attached = !!xdp->prog_id;
 		return 0;
 	default:
 		return -EINVAL;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b683971e500d..69a664789b33 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -819,10 +819,6 @@ enum bpf_netdev_command {
 	 */
 	XDP_SETUP_PROG,
 	XDP_SETUP_PROG_HW,
-	/* Check if a bpf program is set on the device.  The callee should
-	 * set @prog_attached to one of XDP_ATTACHED_* values, note that "true"
-	 * is equivalent to XDP_ATTACHED_DRV.
-	 */
 	XDP_QUERY_PROG,
 	/* BPF program for offload callbacks, invoked at program load time. */
 	BPF_OFFLOAD_VERIFIER_PREP,
@@ -849,7 +845,6 @@ struct netdev_bpf {
 		};
 		/* XDP_QUERY_PROG */
 		struct {
-			u8 prog_attached;
 			u32 prog_id;
 			/* flags with which program was installed */
 			u32 prog_flags;
diff --git a/net/core/dev.c b/net/core/dev.c
index 89825c1eccdc..9fa3b3705a8e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4926,7 +4926,6 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 		break;
 
 	case XDP_QUERY_PROG:
-		xdp->prog_attached = !!old;
 		xdp->prog_id = old ? old->aux->id : 0;
 		break;
 
@@ -7593,13 +7592,13 @@ void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
 	WARN_ON(bpf_op(dev, xdp) < 0);
 }
 
-static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op)
+static bool __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op)
 {
 	struct netdev_bpf xdp;
 
 	__dev_xdp_query(dev, bpf_op, &xdp);
 
-	return xdp.prog_attached;
+	return xdp.prog_id;
 }
 
 static int dev_xdp_install(struct net_device *dev, bpf_op_t bpf_op,
@@ -7634,7 +7633,7 @@ static void dev_xdp_uninstall(struct net_device *dev)
 		return;
 
 	__dev_xdp_query(dev, ndo_bpf, &xdp);
-	if (xdp.prog_attached == XDP_ATTACHED_NONE)
+	if (!xdp.prog_id)
 		return;
 
 	/* Program removal should always succeed */
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b40242459907..02ebc056a688 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1372,9 +1372,13 @@ static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
 		return XDP_ATTACHED_NONE;
 
 	__dev_xdp_query(dev, ops->ndo_bpf, &xdp);
-	*prog_id = xdp.prog_id;
+	if (!xdp.prog_id)
+		return XDP_ATTACHED_NONE;
 
-	return xdp.prog_attached;
+	*prog_id = xdp.prog_id;
+	if (xdp.prog_flags & XDP_FLAGS_HW_MODE)
+		return XDP_ATTACHED_HW;
+	return XDP_ATTACHED_DRV;
 }
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
-- 
cgit v1.2.3


From 05296620f6d14dce0030b87e1e57891a770fb65c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 11 Jul 2018 20:36:40 -0700
Subject: xdp: factor out common program/flags handling from drivers

Basic operations drivers perform during xdp setup and query can
be moved to helpers in the core.  Encapsulate program and flags
into a structure and add helpers.  Note that the structure is
intended as the "main" program information source in the driver.
Most drivers will additionally place the program pointer in their
fast path or ring structures.

The helpers don't have a huge impact now, but they will
decrease the code duplication when programs can be installed
in HW and driver at the same time.  Encapsulating the basic
operations in helpers will hopefully also reduce the number
of changes to drivers which adopt them.

Helpers could really be static inline, but they depend on
definition of struct netdev_bpf which means they'd have
to be placed in netdevice.h, an already 4500 line header.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h       |  6 ++--
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 28 +++++++-----------
 drivers/net/netdevsim/bpf.c                        | 16 +++-------
 drivers/net/netdevsim/netdevsim.h                  |  4 +--
 include/net/xdp.h                                  | 13 +++++++++
 net/core/xdp.c                                     | 34 ++++++++++++++++++++++
 tools/testing/selftests/bpf/test_offload.py        |  4 +--
 7 files changed, 67 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 2a71a9ffd095..2021dda595b7 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -553,8 +553,7 @@ struct nfp_net_dp {
  * @rss_cfg:            RSS configuration
  * @rss_key:            RSS secret key
  * @rss_itbl:           RSS indirection table
- * @xdp_flags:		Flags with which XDP prog was loaded
- * @xdp_prog:		XDP prog (for ctrl path, both DRV and HW modes)
+ * @xdp:		Information about the attached XDP program
  * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
@@ -610,8 +609,7 @@ struct nfp_net {
 	u8 rss_key[NFP_NET_CFG_RSS_KEY_SZ];
 	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
 
-	u32 xdp_flags;
-	struct bpf_prog *xdp_prog;
+	struct xdp_attachment_info xdp;
 
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index d20714598613..4bb589dbffbc 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3417,34 +3417,29 @@ nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
 	return nfp_net_ring_reconfig(nn, dp, extack);
 }
 
-static int
-nfp_net_xdp_setup(struct nfp_net *nn, struct bpf_prog *prog, u32 flags,
-		  struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
 	struct bpf_prog *drv_prog, *offload_prog;
 	int err;
 
-	if (nn->xdp_prog && (flags ^ nn->xdp_flags) & XDP_FLAGS_MODES)
+	if (!xdp_attachment_flags_ok(&nn->xdp, bpf))
 		return -EBUSY;
 
 	/* Load both when no flags set to allow easy activation of driver path
 	 * when program is replaced by one which can't be offloaded.
 	 */
-	drv_prog     = flags & XDP_FLAGS_HW_MODE  ? NULL : prog;
-	offload_prog = flags & XDP_FLAGS_DRV_MODE ? NULL : prog;
+	drv_prog     = bpf->flags & XDP_FLAGS_HW_MODE  ? NULL : bpf->prog;
+	offload_prog = bpf->flags & XDP_FLAGS_DRV_MODE ? NULL : bpf->prog;
 
-	err = nfp_net_xdp_setup_drv(nn, drv_prog, extack);
+	err = nfp_net_xdp_setup_drv(nn, drv_prog, bpf->extack);
 	if (err)
 		return err;
 
-	err = nfp_app_xdp_offload(nn->app, nn, offload_prog, extack);
-	if (err && flags & XDP_FLAGS_HW_MODE)
+	err = nfp_app_xdp_offload(nn->app, nn, offload_prog, bpf->extack);
+	if (err && bpf->flags & XDP_FLAGS_HW_MODE)
 		return err;
 
-	if (nn->xdp_prog)
-		bpf_prog_put(nn->xdp_prog);
-	nn->xdp_prog = prog;
-	nn->xdp_flags = flags;
+	xdp_attachment_setup(&nn->xdp, bpf);
 
 	return 0;
 }
@@ -3456,12 +3451,9 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 	case XDP_SETUP_PROG_HW:
-		return nfp_net_xdp_setup(nn, xdp->prog, xdp->flags,
-					 xdp->extack);
+		return nfp_net_xdp_setup(nn, xdp);
 	case XDP_QUERY_PROG:
-		xdp->prog_id = nn->xdp_prog ? nn->xdp_prog->aux->id : 0;
-		xdp->prog_flags = nn->xdp_prog ? nn->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&nn->xdp, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
 	}
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 712e6f918065..c485d97b5df4 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -199,10 +199,8 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 {
 	int err;
 
-	if (ns->xdp_prog && (bpf->flags ^ ns->xdp_flags) & XDP_FLAGS_MODES) {
-		NSIM_EA(bpf->extack, "program loaded with different flags");
+	if (!xdp_attachment_flags_ok(&ns->xdp, bpf))
 		return -EBUSY;
-	}
 
 	if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
 		NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS");
@@ -219,11 +217,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 			return err;
 	}
 
-	if (ns->xdp_prog)
-		bpf_prog_put(ns->xdp_prog);
-
-	ns->xdp_prog = bpf->prog;
-	ns->xdp_flags = bpf->flags;
+	xdp_attachment_setup(&ns->xdp, bpf);
 
 	if (!bpf->prog)
 		ns->xdp_prog_mode = XDP_ATTACHED_NONE;
@@ -567,9 +561,7 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
 	case XDP_QUERY_PROG:
-		bpf->prog_id = ns->xdp_prog ? ns->xdp_prog->aux->id : 0;
-		bpf->prog_flags = ns->xdp_prog ? ns->xdp_flags : 0;
-		return 0;
+		return xdp_attachment_query(&ns->xdp, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
 		if (err)
@@ -636,6 +628,6 @@ void nsim_bpf_uninit(struct netdevsim *ns)
 {
 	WARN_ON(!list_empty(&ns->bpf_bound_progs));
 	WARN_ON(!list_empty(&ns->bpf_bound_maps));
-	WARN_ON(ns->xdp_prog);
+	WARN_ON(ns->xdp.prog);
 	WARN_ON(ns->bpf_offloaded);
 }
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index d8a7cc995e88..69ffb4a2d14b 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -18,6 +18,7 @@
 #include <linux/list.h>
 #include <linux/netdevice.h>
 #include <linux/u64_stats_sync.h>
+#include <net/xdp.h>
 
 #define DRV_NAME	"netdevsim"
 
@@ -67,9 +68,8 @@ struct netdevsim {
 	struct bpf_prog	*bpf_offloaded;
 	u32 bpf_offloaded_id;
 
-	u32 xdp_flags;
+	struct xdp_attachment_info xdp;
 	int xdp_prog_mode;
-	struct bpf_prog	*xdp_prog;
 
 	u32 prog_id_gen;
 
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 2deea7166a34..fcb033f51d8c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -144,4 +144,17 @@ xdp_data_meta_unsupported(const struct xdp_buff *xdp)
 	return unlikely(xdp->data_meta > xdp->data);
 }
 
+struct xdp_attachment_info {
+	struct bpf_prog *prog;
+	u32 flags;
+};
+
+struct netdev_bpf;
+int xdp_attachment_query(struct xdp_attachment_info *info,
+			 struct netdev_bpf *bpf);
+bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
+			     struct netdev_bpf *bpf);
+void xdp_attachment_setup(struct xdp_attachment_info *info,
+			  struct netdev_bpf *bpf);
+
 #endif /* __LINUX_NET_XDP_H__ */
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 31c58719b5a9..57285383ed00 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -3,8 +3,11 @@
  * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
  * Released under terms in GPL version 2.  See COPYING.
  */
+#include <linux/bpf.h>
+#include <linux/filter.h>
 #include <linux/types.h>
 #include <linux/mm.h>
+#include <linux/netdevice.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/rhashtable.h>
@@ -370,3 +373,34 @@ void xdp_return_buff(struct xdp_buff *xdp)
 	__xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle);
 }
 EXPORT_SYMBOL_GPL(xdp_return_buff);
+
+int xdp_attachment_query(struct xdp_attachment_info *info,
+			 struct netdev_bpf *bpf)
+{
+	bpf->prog_id = info->prog ? info->prog->aux->id : 0;
+	bpf->prog_flags = info->prog ? info->flags : 0;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_query);
+
+bool xdp_attachment_flags_ok(struct xdp_attachment_info *info,
+			     struct netdev_bpf *bpf)
+{
+	if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) {
+		NL_SET_ERR_MSG(bpf->extack,
+			       "program loaded with different flags");
+		return false;
+	}
+	return true;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok);
+
+void xdp_attachment_setup(struct xdp_attachment_info *info,
+			  struct netdev_bpf *bpf)
+{
+	if (info->prog)
+		bpf_prog_put(info->prog);
+	info->prog = bpf->prog;
+	info->flags = bpf->flags;
+}
+EXPORT_SYMBOL_GPL(xdp_attachment_setup);
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index f8d9bd81d9a4..40401e9e9351 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -821,7 +821,7 @@ try:
     ret, _, err = sim.set_xdp(obj, "", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test XDP prog remove with bad flags...")
     ret, _, err = sim.unset_xdp("offload", force=True,
@@ -831,7 +831,7 @@ try:
     ret, _, err = sim.unset_xdp("", force=True,
                                 fail=False, include_stderr=True)
     fail(ret == 0, "Removed program with a bad mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
+    check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test MTU restrictions...")
     ret, _ = sim.set_mtu(9000, fail=False)
-- 
cgit v1.2.3


From a25717d2b604347d9af8da81deea7b08e8c94220 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 11 Jul 2018 20:36:41 -0700
Subject: xdp: support simultaneous driver and hw XDP attachment

Split the query of HW-attached program from the software one.
Introduce new .ndo_bpf command to query HW-attached program.
This will allow drivers to install different programs in HW
and SW at the same time.  Netlink can now also carry multiple
programs on dump (in which case mode will be set to
XDP_ATTACHED_MULTI and user has to check per-attachment point
attributes, IFLA_XDP_PROG_ID will not be present).  We reuse
IFLA_XDP_PROG_ID skb space for second mode, so rtnl_xdp_size()
doesn't need to be updated.

Note that the installation side is still not there, since all
drivers currently reject installing more than one program at
the time.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    |  6 ++
 drivers/net/netdevsim/bpf.c                        |  6 ++
 include/linux/netdevice.h                          |  7 +-
 include/uapi/linux/if_link.h                       |  1 +
 net/core/dev.c                                     | 45 ++++++-----
 net/core/rtnetlink.c                               | 93 ++++++++++++----------
 6 files changed, 96 insertions(+), 62 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 4bb589dbffbc..bb1e72e8dbc2 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3453,6 +3453,12 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	case XDP_SETUP_PROG_HW:
 		return nfp_net_xdp_setup(nn, xdp);
 	case XDP_QUERY_PROG:
+		if (nn->dp.bpf_offload_xdp)
+			return 0;
+		return xdp_attachment_query(&nn->xdp, xdp);
+	case XDP_QUERY_PROG_HW:
+		if (!nn->dp.bpf_offload_xdp)
+			return 0;
 		return xdp_attachment_query(&nn->xdp, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index c485d97b5df4..5544c9b51173 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -561,6 +561,12 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
 	case XDP_QUERY_PROG:
+		if (ns->xdp_prog_mode != XDP_ATTACHED_DRV)
+			return 0;
+		return xdp_attachment_query(&ns->xdp, bpf);
+	case XDP_QUERY_PROG_HW:
+		if (ns->xdp_prog_mode != XDP_ATTACHED_HW)
+			return 0;
 		return xdp_attachment_query(&ns->xdp, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 69a664789b33..2422c0e88f5c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -820,6 +820,7 @@ enum bpf_netdev_command {
 	XDP_SETUP_PROG,
 	XDP_SETUP_PROG_HW,
 	XDP_QUERY_PROG,
+	XDP_QUERY_PROG_HW,
 	/* BPF program for offload callbacks, invoked at program load time. */
 	BPF_OFFLOAD_VERIFIER_PREP,
 	BPF_OFFLOAD_TRANSLATE,
@@ -843,7 +844,7 @@ struct netdev_bpf {
 			struct bpf_prog *prog;
 			struct netlink_ext_ack *extack;
 		};
-		/* XDP_QUERY_PROG */
+		/* XDP_QUERY_PROG, XDP_QUERY_PROG_HW */
 		struct {
 			u32 prog_id;
 			/* flags with which program was installed */
@@ -3533,8 +3534,8 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, u32 flags);
-void __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
-		     struct netdev_bpf *xdp);
+u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
+		    enum bpf_netdev_command cmd);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index bc86c2b105ec..8759cfb8aa2e 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -920,6 +920,7 @@ enum {
 	XDP_ATTACHED_DRV,
 	XDP_ATTACHED_SKB,
 	XDP_ATTACHED_HW,
+	XDP_ATTACHED_MULTI,
 };
 
 enum {
diff --git a/net/core/dev.c b/net/core/dev.c
index 9fa3b3705a8e..993cdc3cd086 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7582,21 +7582,19 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
 }
 EXPORT_SYMBOL(dev_change_proto_down);
 
-void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
-		     struct netdev_bpf *xdp)
+u32 __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op,
+		    enum bpf_netdev_command cmd)
 {
-	memset(xdp, 0, sizeof(*xdp));
-	xdp->command = XDP_QUERY_PROG;
+	struct netdev_bpf xdp;
 
-	/* Query must always succeed. */
-	WARN_ON(bpf_op(dev, xdp) < 0);
-}
+	if (!bpf_op)
+		return 0;
 
-static bool __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op)
-{
-	struct netdev_bpf xdp;
+	memset(&xdp, 0, sizeof(xdp));
+	xdp.command = cmd;
 
-	__dev_xdp_query(dev, bpf_op, &xdp);
+	/* Query must always succeed. */
+	WARN_ON(bpf_op(dev, &xdp) < 0 && cmd == XDP_QUERY_PROG);
 
 	return xdp.prog_id;
 }
@@ -7632,12 +7630,19 @@ static void dev_xdp_uninstall(struct net_device *dev)
 	if (!ndo_bpf)
 		return;
 
-	__dev_xdp_query(dev, ndo_bpf, &xdp);
-	if (!xdp.prog_id)
-		return;
+	memset(&xdp, 0, sizeof(xdp));
+	xdp.command = XDP_QUERY_PROG;
+	WARN_ON(ndo_bpf(dev, &xdp));
+	if (xdp.prog_id)
+		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
+					NULL));
 
-	/* Program removal should always succeed */
-	WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL));
+	/* Remove HW offload */
+	memset(&xdp, 0, sizeof(xdp));
+	xdp.command = XDP_QUERY_PROG_HW;
+	if (!ndo_bpf(dev, &xdp) && xdp.prog_id)
+		WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags,
+					NULL));
 }
 
 /**
@@ -7653,12 +7658,15 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, u32 flags)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
+	enum bpf_netdev_command query;
 	struct bpf_prog *prog = NULL;
 	bpf_op_t bpf_op, bpf_chk;
 	int err;
 
 	ASSERT_RTNL();
 
+	query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG;
+
 	bpf_op = bpf_chk = ops->ndo_bpf;
 	if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE)))
 		return -EOPNOTSUPP;
@@ -7668,10 +7676,11 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		bpf_chk = generic_xdp_install;
 
 	if (fd >= 0) {
-		if (bpf_chk && __dev_xdp_attached(dev, bpf_chk))
+		if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) ||
+		    __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW))
 			return -EEXIST;
 		if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) &&
-		    __dev_xdp_attached(dev, bpf_op))
+		    __dev_xdp_query(dev, bpf_op, query))
 			return -EBUSY;
 
 		prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP,
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 02ebc056a688..c9929ef17539 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -964,7 +964,7 @@ static size_t rtnl_xdp_size(void)
 {
 	size_t xdp_size = nla_total_size(0) +	/* nest IFLA_XDP */
 			  nla_total_size(1) +	/* XDP_ATTACHED */
-			  nla_total_size(4) +	/* XDP_PROG_ID */
+			  nla_total_size(4) +	/* XDP_PROG_ID (or 1st mode) */
 			  nla_total_size(4);	/* XDP_<mode>_PROG_ID */
 
 	return xdp_size;
@@ -1354,37 +1354,57 @@ static int rtnl_fill_link_ifmap(struct sk_buff *skb, struct net_device *dev)
 	return 0;
 }
 
-static u8 rtnl_xdp_attached_mode(struct net_device *dev, u32 *prog_id)
+static u32 rtnl_xdp_prog_skb(struct net_device *dev)
 {
-	const struct net_device_ops *ops = dev->netdev_ops;
 	const struct bpf_prog *generic_xdp_prog;
-	struct netdev_bpf xdp;
 
 	ASSERT_RTNL();
 
-	*prog_id = 0;
 	generic_xdp_prog = rtnl_dereference(dev->xdp_prog);
-	if (generic_xdp_prog) {
-		*prog_id = generic_xdp_prog->aux->id;
-		return XDP_ATTACHED_SKB;
-	}
-	if (!ops->ndo_bpf)
-		return XDP_ATTACHED_NONE;
+	if (!generic_xdp_prog)
+		return 0;
+	return generic_xdp_prog->aux->id;
+}
+
+static u32 rtnl_xdp_prog_drv(struct net_device *dev)
+{
+	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf, XDP_QUERY_PROG);
+}
+
+static u32 rtnl_xdp_prog_hw(struct net_device *dev)
+{
+	return __dev_xdp_query(dev, dev->netdev_ops->ndo_bpf,
+			       XDP_QUERY_PROG_HW);
+}
+
+static int rtnl_xdp_report_one(struct sk_buff *skb, struct net_device *dev,
+			       u32 *prog_id, u8 *mode, u8 tgt_mode, u32 attr,
+			       u32 (*get_prog_id)(struct net_device *dev))
+{
+	u32 curr_id;
+	int err;
+
+	curr_id = get_prog_id(dev);
+	if (!curr_id)
+		return 0;
+
+	*prog_id = curr_id;
+	err = nla_put_u32(skb, attr, curr_id);
+	if (err)
+		return err;
 
-	__dev_xdp_query(dev, ops->ndo_bpf, &xdp);
-	if (!xdp.prog_id)
-		return XDP_ATTACHED_NONE;
+	if (*mode != XDP_ATTACHED_NONE)
+		*mode = XDP_ATTACHED_MULTI;
+	else
+		*mode = tgt_mode;
 
-	*prog_id = xdp.prog_id;
-	if (xdp.prog_flags & XDP_FLAGS_HW_MODE)
-		return XDP_ATTACHED_HW;
-	return XDP_ATTACHED_DRV;
+	return 0;
 }
 
 static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 {
-	u32 prog_attr, prog_id;
 	struct nlattr *xdp;
+	u32 prog_id;
 	int err;
 	u8 mode;
 
@@ -1392,35 +1412,26 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 	if (!xdp)
 		return -EMSGSIZE;
 
-	mode = rtnl_xdp_attached_mode(dev, &prog_id);
+	prog_id = 0;
+	mode = XDP_ATTACHED_NONE;
+	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_SKB,
+				IFLA_XDP_SKB_PROG_ID, rtnl_xdp_prog_skb))
+		goto err_cancel;
+	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_DRV,
+				IFLA_XDP_DRV_PROG_ID, rtnl_xdp_prog_drv))
+		goto err_cancel;
+	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_HW,
+				IFLA_XDP_HW_PROG_ID, rtnl_xdp_prog_hw))
+		goto err_cancel;
+
 	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode);
 	if (err)
 		goto err_cancel;
 
-	if (prog_id) {
+	if (prog_id && mode != XDP_ATTACHED_MULTI) {
 		err = nla_put_u32(skb, IFLA_XDP_PROG_ID, prog_id);
 		if (err)
 			goto err_cancel;
-
-		switch (mode) {
-		case XDP_ATTACHED_DRV:
-			prog_attr = IFLA_XDP_DRV_PROG_ID;
-			break;
-		case XDP_ATTACHED_SKB:
-			prog_attr = IFLA_XDP_SKB_PROG_ID;
-			break;
-		case XDP_ATTACHED_HW:
-			prog_attr = IFLA_XDP_HW_PROG_ID;
-			break;
-		case XDP_ATTACHED_NONE:
-		default:
-			err = -EINVAL;
-			goto err_cancel;
-		}
-
-		err = nla_put_u32(skb, prog_attr, prog_id);
-		if (err)
-			goto err_cancel;
 	}
 
 	nla_nest_end(skb, xdp);
-- 
cgit v1.2.3


From 799e173d7125155c00e9492c8212c5e41333049f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 11 Jul 2018 20:36:42 -0700
Subject: netdevsim: add support for simultaneous driver and hw XDP

Allow netdevsim to accept driver and offload attachment of XDP
BPF programs at the same time.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/netdevsim/bpf.c                 | 32 +++++++++--------------------
 drivers/net/netdevsim/netdev.c              |  3 +--
 drivers/net/netdevsim/netdevsim.h           |  2 +-
 tools/testing/selftests/bpf/test_offload.py |  8 --------
 4 files changed, 12 insertions(+), 33 deletions(-)

diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 5544c9b51173..c36d2a768202 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -92,7 +92,7 @@ static const struct bpf_prog_offload_ops nsim_bpf_analyzer_ops = {
 
 static bool nsim_xdp_offload_active(struct netdevsim *ns)
 {
-	return ns->xdp_prog_mode == XDP_ATTACHED_HW;
+	return ns->xdp_hw.prog;
 }
 
 static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded)
@@ -195,11 +195,13 @@ static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 	return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns));
 }
 
-static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
+static int
+nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf,
+		  struct xdp_attachment_info *xdp)
 {
 	int err;
 
-	if (!xdp_attachment_flags_ok(&ns->xdp, bpf))
+	if (!xdp_attachment_flags_ok(xdp, bpf))
 		return -EBUSY;
 
 	if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) {
@@ -217,14 +219,7 @@ static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf)
 			return err;
 	}
 
-	xdp_attachment_setup(&ns->xdp, bpf);
-
-	if (!bpf->prog)
-		ns->xdp_prog_mode = XDP_ATTACHED_NONE;
-	else if (bpf->command == XDP_SETUP_PROG)
-		ns->xdp_prog_mode = XDP_ATTACHED_DRV;
-	else
-		ns->xdp_prog_mode = XDP_ATTACHED_HW;
+	xdp_attachment_setup(xdp, bpf);
 
 	return 0;
 }
@@ -284,10 +279,6 @@ static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
 		return -EINVAL;
 	}
-	if (nsim_xdp_offload_active(ns)) {
-		NSIM_EA(bpf->extack, "xdp offload active, can't load drv prog");
-		return -EBUSY;
-	}
 	return 0;
 }
 
@@ -561,25 +552,21 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 		nsim_bpf_destroy_prog(bpf->offload.prog);
 		return 0;
 	case XDP_QUERY_PROG:
-		if (ns->xdp_prog_mode != XDP_ATTACHED_DRV)
-			return 0;
 		return xdp_attachment_query(&ns->xdp, bpf);
 	case XDP_QUERY_PROG_HW:
-		if (ns->xdp_prog_mode != XDP_ATTACHED_HW)
-			return 0;
-		return xdp_attachment_query(&ns->xdp, bpf);
+		return xdp_attachment_query(&ns->xdp_hw, bpf);
 	case XDP_SETUP_PROG:
 		err = nsim_setup_prog_checks(ns, bpf);
 		if (err)
 			return err;
 
-		return nsim_xdp_set_prog(ns, bpf);
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp);
 	case XDP_SETUP_PROG_HW:
 		err = nsim_setup_prog_hw_checks(ns, bpf);
 		if (err)
 			return err;
 
-		return nsim_xdp_set_prog(ns, bpf);
+		return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw);
 	case BPF_OFFLOAD_MAP_ALLOC:
 		if (!ns->bpf_map_accept)
 			return -EOPNOTSUPP;
@@ -635,5 +622,6 @@ void nsim_bpf_uninit(struct netdevsim *ns)
 	WARN_ON(!list_empty(&ns->bpf_bound_progs));
 	WARN_ON(!list_empty(&ns->bpf_bound_maps));
 	WARN_ON(ns->xdp.prog);
+	WARN_ON(ns->xdp_hw.prog);
 	WARN_ON(ns->bpf_offloaded);
 }
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index b2f9d0df93b0..a7b179f0d954 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -228,8 +228,7 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
-	if (ns->xdp_prog_mode == XDP_ATTACHED_DRV &&
-	    new_mtu > NSIM_XDP_MAX_MTU)
+	if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
 		return -EBUSY;
 
 	dev->mtu = new_mtu;
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 69ffb4a2d14b..0aeabbe81cc6 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -69,7 +69,7 @@ struct netdevsim {
 	u32 bpf_offloaded_id;
 
 	struct xdp_attachment_info xdp;
-	int xdp_prog_mode;
+	struct xdp_attachment_info xdp_hw;
 
 	u32 prog_id_gen;
 
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 40401e9e9351..4f982a0255c2 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -814,20 +814,12 @@ try:
          "Device parameters reported for non-offloaded program")
 
     start_test("Test XDP prog replace with bad flags...")
-    ret, _, err = sim.set_xdp(obj, "offload", force=True,
-                              fail=False, include_stderr=True)
-    fail(ret == 0, "Replaced XDP program with a program in different mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
     ret, _, err = sim.set_xdp(obj, "", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
     check_extack(err, "program loaded with different flags.", args)
 
     start_test("Test XDP prog remove with bad flags...")
-    ret, _, err = sim.unset_xdp("offload", force=True,
-                                fail=False, include_stderr=True)
-    fail(ret == 0, "Removed program with a bad mode mode")
-    check_extack_nsim(err, "program loaded with different flags.", args)
     ret, _, err = sim.unset_xdp("", force=True,
                                 fail=False, include_stderr=True)
     fail(ret == 0, "Removed program with a bad mode")
-- 
cgit v1.2.3


From 99dadb6e3ec130800d199ec42fff03242b1be1eb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 11 Jul 2018 20:36:43 -0700
Subject: selftests/bpf: add test for multiple programs

Add tests for having an XDP program attached in the driver and
another one attached in HW simultaneously.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_offload.py | 63 +++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index 4f982a0255c2..b746227eaff2 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -339,6 +339,11 @@ class NetdevSim:
         self.dfs = DebugfsDir(self.dfs_dir)
         return self.dfs
 
+    def dfs_read(self, f):
+        path = os.path.join(self.dfs_dir, f)
+        _, data = cmd('cat %s' % (path))
+        return data.strip()
+
     def dfs_num_bound_progs(self):
         path = os.path.join(self.dfs_dir, "bpf_bound_progs")
         _, progs = cmd('ls %s' % (path))
@@ -814,6 +819,10 @@ try:
          "Device parameters reported for non-offloaded program")
 
     start_test("Test XDP prog replace with bad flags...")
+    ret, _, err = sim.set_xdp(obj, "generic", force=True,
+                              fail=False, include_stderr=True)
+    fail(ret == 0, "Replaced XDP program with a program in different mode")
+    fail(err.count("File exists") != 1, "Replaced driver XDP with generic")
     ret, _, err = sim.set_xdp(obj, "", force=True,
                               fail=False, include_stderr=True)
     fail(ret == 0, "Replaced XDP program with a program in different mode")
@@ -883,6 +892,60 @@ try:
     rm(pin_file)
     bpftool_prog_list_wait(expected=0)
 
+    start_test("Test multi-attachment XDP - attach...")
+    sim.set_xdp(obj, "offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+    fail("prog" not in xdp, "Base program not reported in single program mode")
+    fail(len(ipl["xdp"]["attached"]) != 1,
+         "Wrong attached program count with one program")
+
+    sim.set_xdp(obj, "")
+    two_xdps = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded2 = sim.dfs_read("bpf_offloaded_id")
+
+    fail(two_xdps["mode"] != 4, "Bad mode reported with multiple programs")
+    fail("prog" in two_xdps, "Base program reported in multi program mode")
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after driver activated")
+    fail(len(two_xdps["attached"]) != 2,
+         "Wrong attached program count with two programs")
+    fail(two_xdps["attached"][0]["prog"]["id"] ==
+         two_xdps["attached"][1]["prog"]["id"],
+         "offloaded and drv programs have the same id")
+    fail(offloaded != offloaded2,
+         "offload ID changed after loading driver program")
+
+    start_test("Test multi-attachment XDP - replace...")
+    ret, _, err = sim.set_xdp(obj, "offload", fail=False, include_stderr=True)
+    fail(err.count("busy") != 1, "Replaced one of programs without -force")
+
+    start_test("Test multi-attachment XDP - detach...")
+    ret, _, err = sim.unset_xdp("drv", force=True,
+                                fail=False, include_stderr=True)
+    fail(ret == 0, "Removed program with a bad mode")
+    check_extack(err, "program loaded with different flags.", args)
+
+    sim.unset_xdp("offload")
+    xdp = sim.ip_link_show(xdp=True)["xdp"]
+    offloaded = sim.dfs_read("bpf_offloaded_id")
+
+    fail(xdp["mode"] != 1, "Bad mode reported after multiple programs")
+    fail("prog" not in xdp,
+         "Base program not reported after multi program mode")
+    fail(xdp["attached"][0] not in two_xdps["attached"],
+         "Offload program not reported after driver activated")
+    fail(len(ipl["xdp"]["attached"]) != 1,
+         "Wrong attached program count with remaining programs")
+    fail(offloaded != "0", "offload ID reported with only driver program left")
+
+    start_test("Test multi-attachment XDP - device remove...")
+    sim.set_xdp(obj, "offload")
+    sim.remove()
+
+    sim = NetdevSim()
+    sim.set_ethtool_tc_offloads(True)
+
     start_test("Test mixing of TC and XDP...")
     sim.tc_add_ingress()
     sim.set_xdp(obj, "offload")
-- 
cgit v1.2.3


From 5f4284015e29c2de501d83eb647c8ec8802b58ac Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 11 Jul 2018 20:36:44 -0700
Subject: nfp: add support for simultaneous driver and hw XDP

Split handling of offloaded and driver programs completely.  Since
offloaded programs always come with XDP_FLAGS_HW_MODE set in reality
there could be no sharing, anyway, programs would only be installed
in driver or in hardware.  Splitting the handling allows us to install
programs in HW and in driver at the same time.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.c      | 11 +----
 drivers/net/ethernet/netronome/nfp/nfp_net.h       |  6 +--
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 49 ++++++++++------------
 3 files changed, 26 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 4dbf7cba6377..b95b94d008cf 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -66,26 +66,19 @@ nfp_bpf_xdp_offload(struct nfp_app *app, struct nfp_net *nn,
 		    struct bpf_prog *prog, struct netlink_ext_ack *extack)
 {
 	bool running, xdp_running;
-	int ret;
 
 	if (!nfp_net_ebpf_capable(nn))
 		return -EINVAL;
 
 	running = nn->dp.ctrl & NFP_NET_CFG_CTRL_BPF;
-	xdp_running = running && nn->dp.bpf_offload_xdp;
+	xdp_running = running && nn->xdp_hw.prog;
 
 	if (!prog && !xdp_running)
 		return 0;
 	if (prog && running && !xdp_running)
 		return -EBUSY;
 
-	ret = nfp_net_bpf_offload(nn, prog, running, extack);
-	/* Stop offload if replace not possible */
-	if (ret)
-		return ret;
-
-	nn->dp.bpf_offload_xdp = !!prog;
-	return ret;
+	return nfp_net_bpf_offload(nn, prog, running, extack);
 }
 
 static const char *nfp_bpf_extra_cap(struct nfp_app *app, struct nfp_net *nn)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 2021dda595b7..8970ec981e11 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -485,7 +485,6 @@ struct nfp_stat_pair {
  * @dev:		Backpointer to struct device
  * @netdev:		Backpointer to net_device structure
  * @is_vf:		Is the driver attached to a VF?
- * @bpf_offload_xdp:	Offloaded BPF program is XDP
  * @chained_metadata_format:  Firemware will use new metadata format
  * @rx_dma_dir:		Mapping direction for RX buffers
  * @rx_dma_off:		Offset at which DMA packets (for XDP headroom)
@@ -510,7 +509,6 @@ struct nfp_net_dp {
 	struct net_device *netdev;
 
 	u8 is_vf:1;
-	u8 bpf_offload_xdp:1;
 	u8 chained_metadata_format:1;
 
 	u8 rx_dma_dir;
@@ -553,7 +551,8 @@ struct nfp_net_dp {
  * @rss_cfg:            RSS configuration
  * @rss_key:            RSS secret key
  * @rss_itbl:           RSS indirection table
- * @xdp:		Information about the attached XDP program
+ * @xdp:		Information about the driver XDP program
+ * @xdp_hw:		Information about the HW XDP program
  * @max_r_vecs:		Number of allocated interrupt vectors for RX/TX
  * @max_tx_rings:       Maximum number of TX rings supported by the Firmware
  * @max_rx_rings:       Maximum number of RX rings supported by the Firmware
@@ -610,6 +609,7 @@ struct nfp_net {
 	u8 rss_itbl[NFP_NET_CFG_RSS_ITBL_SZ];
 
 	struct xdp_attachment_info xdp;
+	struct xdp_attachment_info xdp_hw;
 
 	unsigned int max_tx_rings;
 	unsigned int max_rx_rings;
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index bb1e72e8dbc2..a712e83c3f0f 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1710,8 +1710,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			}
 		}
 
-		if (xdp_prog && !(rxd->rxd.flags & PCIE_DESC_RX_BPF &&
-				  dp->bpf_offload_xdp) && !meta.portid) {
+		if (xdp_prog && !meta.portid) {
 			void *orig_data = rxbuf->frag + pkt_off;
 			unsigned int dma_off;
 			int act;
@@ -3393,14 +3392,18 @@ static void nfp_net_del_vxlan_port(struct net_device *netdev,
 		nfp_net_set_vxlan_port(nn, idx, 0);
 }
 
-static int
-nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
-		      struct netlink_ext_ack *extack)
+static int nfp_net_xdp_setup_drv(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
+	struct bpf_prog *prog = bpf->prog;
 	struct nfp_net_dp *dp;
+	int err;
+
+	if (!xdp_attachment_flags_ok(&nn->xdp, bpf))
+		return -EBUSY;
 
 	if (!prog == !nn->dp.xdp_prog) {
 		WRITE_ONCE(nn->dp.xdp_prog, prog);
+		xdp_attachment_setup(&nn->xdp, bpf);
 		return 0;
 	}
 
@@ -3414,33 +3417,26 @@ nfp_net_xdp_setup_drv(struct nfp_net *nn, struct bpf_prog *prog,
 	dp->rx_dma_off = prog ? XDP_PACKET_HEADROOM - nn->dp.rx_offset : 0;
 
 	/* We need RX reconfig to remap the buffers (BIDIR vs FROM_DEV) */
-	return nfp_net_ring_reconfig(nn, dp, extack);
+	err = nfp_net_ring_reconfig(nn, dp, bpf->extack);
+	if (err)
+		return err;
+
+	xdp_attachment_setup(&nn->xdp, bpf);
+	return 0;
 }
 
-static int nfp_net_xdp_setup(struct nfp_net *nn, struct netdev_bpf *bpf)
+static int nfp_net_xdp_setup_hw(struct nfp_net *nn, struct netdev_bpf *bpf)
 {
-	struct bpf_prog *drv_prog, *offload_prog;
 	int err;
 
-	if (!xdp_attachment_flags_ok(&nn->xdp, bpf))
+	if (!xdp_attachment_flags_ok(&nn->xdp_hw, bpf))
 		return -EBUSY;
 
-	/* Load both when no flags set to allow easy activation of driver path
-	 * when program is replaced by one which can't be offloaded.
-	 */
-	drv_prog     = bpf->flags & XDP_FLAGS_HW_MODE  ? NULL : bpf->prog;
-	offload_prog = bpf->flags & XDP_FLAGS_DRV_MODE ? NULL : bpf->prog;
-
-	err = nfp_net_xdp_setup_drv(nn, drv_prog, bpf->extack);
+	err = nfp_app_xdp_offload(nn->app, nn, bpf->prog, bpf->extack);
 	if (err)
 		return err;
 
-	err = nfp_app_xdp_offload(nn->app, nn, offload_prog, bpf->extack);
-	if (err && bpf->flags & XDP_FLAGS_HW_MODE)
-		return err;
-
-	xdp_attachment_setup(&nn->xdp, bpf);
-
+	xdp_attachment_setup(&nn->xdp_hw, bpf);
 	return 0;
 }
 
@@ -3450,16 +3446,13 @@ static int nfp_net_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
+		return nfp_net_xdp_setup_drv(nn, xdp);
 	case XDP_SETUP_PROG_HW:
-		return nfp_net_xdp_setup(nn, xdp);
+		return nfp_net_xdp_setup_hw(nn, xdp);
 	case XDP_QUERY_PROG:
-		if (nn->dp.bpf_offload_xdp)
-			return 0;
 		return xdp_attachment_query(&nn->xdp, xdp);
 	case XDP_QUERY_PROG_HW:
-		if (!nn->dp.bpf_offload_xdp)
-			return 0;
-		return xdp_attachment_query(&nn->xdp, xdp);
+		return xdp_attachment_query(&nn->xdp_hw, xdp);
 	default:
 		return nfp_app_bpf(nn->app, nn, xdp);
 	}
-- 
cgit v1.2.3


From 137dc4b9060e99a22dce59b42ca71912cf0180f3 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Wed, 4 Jul 2018 16:21:52 +0800
Subject: drm/amdgpu: pin the csb buffer on hw init v2

Without this pin, the csb buffer will be filled with inconsistent
data after S3 resume. And that will causes gfx hang on gfxoff
exit since this csb will be executed then.

v2: fit amdgpu_bo_pin change(take one less argument)

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 40 +++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index ac46eabe3bcd..82f457a061fe 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -943,6 +943,7 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 		dst_ptr = adev->gfx.rlc.cs_ptr;
 		gfx_v9_0_get_csb_buffer(adev, dst_ptr);
 		amdgpu_bo_kunmap(adev->gfx.rlc.clear_state_obj);
+		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
 		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
 	}
 
@@ -971,6 +972,39 @@ static int gfx_v9_0_rlc_init(struct amdgpu_device *adev)
 	return 0;
 }
 
+static int gfx_v9_0_csb_vram_pin(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, false);
+	if (unlikely(r != 0))
+		return r;
+
+	r = amdgpu_bo_pin(adev->gfx.rlc.clear_state_obj,
+			AMDGPU_GEM_DOMAIN_VRAM);
+	if (!r)
+		adev->gfx.rlc.clear_state_gpu_addr =
+			amdgpu_bo_gpu_offset(adev->gfx.rlc.clear_state_obj);
+
+	amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+
+	return r;
+}
+
+static void gfx_v9_0_csb_vram_unpin(struct amdgpu_device *adev)
+{
+	int r;
+
+	if (!adev->gfx.rlc.clear_state_obj)
+		return;
+
+	r = amdgpu_bo_reserve(adev->gfx.rlc.clear_state_obj, true);
+	if (likely(r == 0)) {
+		amdgpu_bo_unpin(adev->gfx.rlc.clear_state_obj);
+		amdgpu_bo_unreserve(adev->gfx.rlc.clear_state_obj);
+	}
+}
+
 static void gfx_v9_0_mec_fini(struct amdgpu_device *adev)
 {
 	amdgpu_bo_free_kernel(&adev->gfx.mec.hpd_eop_obj, NULL, NULL);
@@ -3116,6 +3150,10 @@ static int gfx_v9_0_hw_init(void *handle)
 
 	gfx_v9_0_gpu_init(adev);
 
+	r = gfx_v9_0_csb_vram_pin(adev);
+	if (r)
+		return r;
+
 	r = gfx_v9_0_rlc_resume(adev);
 	if (r)
 		return r;
@@ -3224,6 +3262,8 @@ static int gfx_v9_0_hw_fini(void *handle)
 	gfx_v9_0_cp_enable(adev, false);
 	gfx_v9_0_rlc_stop(adev);
 
+	gfx_v9_0_csb_vram_unpin(adev);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From af356b6d32c8dd065393e4c8cd5576c15e48df4d Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Thu, 5 Jul 2018 11:17:48 +0800
Subject: drm/amdgpu: init CSIB regardless of rlc version and pg status

CSIB init has no relation with rlc version and pg status. It should be
needed regardless of them.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 82f457a061fe..e4ae92618b62 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2182,6 +2182,8 @@ static void gfx_v9_0_enable_gfx_dynamic_mg_power_gating(struct amdgpu_device *ad
 
 static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 {
+	gfx_v9_0_init_csb(adev);
+
 	if (!adev->gfx.rlc.is_rlc_v2_1)
 		return;
 
@@ -2191,7 +2193,6 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 			      AMD_PG_SUPPORT_CP |
 			      AMD_PG_SUPPORT_GDS |
 			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
-		gfx_v9_0_init_csb(adev);
 		gfx_v9_1_init_rlc_save_restore_list(adev);
 		gfx_v9_0_enable_save_restore_machine(adev);
 
-- 
cgit v1.2.3


From b58b65cf7ac09b3d9a979a6a9bbe41abfc425a2a Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Thu, 5 Jul 2018 11:24:20 +0800
Subject: drm/amdgpu: correct rlc save restore list initialization for v2_1

The save restore list initialization does not have to be pg guarded.
And for some asic(e.g. Vega12), it does not have cntl/gpm/srm lists.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e4ae92618b62..5e92002e72e2 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -648,7 +648,10 @@ static int gfx_v9_0_init_microcode(struct amdgpu_device *adev)
 		adev->firmware.fw_size +=
 			ALIGN(le32_to_cpu(header->ucode_size_bytes), PAGE_SIZE);
 
-		if (adev->gfx.rlc.is_rlc_v2_1) {
+		if (adev->gfx.rlc.is_rlc_v2_1 &&
+		    adev->gfx.rlc.save_restore_list_cntl_size_bytes &&
+		    adev->gfx.rlc.save_restore_list_gpm_size_bytes &&
+		    adev->gfx.rlc.save_restore_list_srm_size_bytes) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL];
 			info->ucode_id = AMDGPU_UCODE_ID_RLC_RESTORE_LIST_CNTL;
 			info->fw = adev->gfx.rlc_fw;
@@ -2184,8 +2187,14 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 {
 	gfx_v9_0_init_csb(adev);
 
-	if (!adev->gfx.rlc.is_rlc_v2_1)
-		return;
+	/*
+	 * Rlc save restore list is workable since v2_1.
+	 * And it's needed by gfxoff feature.
+	 */
+	if (adev->gfx.rlc.is_rlc_v2_1) {
+		gfx_v9_1_init_rlc_save_restore_list(adev);
+		gfx_v9_0_enable_save_restore_machine(adev);
+	}
 
 	if (adev->pg_flags & (AMD_PG_SUPPORT_GFX_PG |
 			      AMD_PG_SUPPORT_GFX_SMG |
@@ -2193,9 +2202,6 @@ static void gfx_v9_0_init_pg(struct amdgpu_device *adev)
 			      AMD_PG_SUPPORT_CP |
 			      AMD_PG_SUPPORT_GDS |
 			      AMD_PG_SUPPORT_RLC_SMU_HS)) {
-		gfx_v9_1_init_rlc_save_restore_list(adev);
-		gfx_v9_0_enable_save_restore_machine(adev);
-
 		WREG32(mmRLC_JUMP_TABLE_RESTORE,
 		       adev->gfx.rlc.cp_table_gpu_addr >> 8);
 		gfx_v9_0_init_gfx_power_gating(adev);
-- 
cgit v1.2.3


From d26031c113acf8289d118bae9a8a293b2f9f6a34 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Wed, 4 Jul 2018 17:06:38 +0800
Subject: drm/amdgpu: drop mmRLC_PG_CNTL clear v2

SMU owns this register so the driver should not set it
to avoid breaking gfxoff.

v2: update description

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher at amd.com>
Reviewed-by: Huang Rui <ray.huang at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 5e92002e72e2..6439e65af55b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -2293,9 +2293,6 @@ static int gfx_v9_0_rlc_resume(struct amdgpu_device *adev)
 	/* disable CG */
 	WREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL, 0);
 
-	/* disable PG */
-	WREG32_SOC15(GC, 0, mmRLC_PG_CNTL, 0);
-
 	gfx_v9_0_rlc_reset(adev);
 
 	gfx_v9_0_init_pg(adev);
-- 
cgit v1.2.3


From c3693768174e90481b1b074fcc1dc68d36dd98d4 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Thu, 5 Jul 2018 10:26:48 +0800
Subject: drm/amdgpu: no touch for the reserved bit of RLC_CGTT_MGCG_OVERRIDE

On vega12, the bit0 of RLC_CGTT_MGCG_OVERRIDE is reserved.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 6439e65af55b..1f88eb2566bf 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3554,8 +3554,11 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev
 	if (enable && (adev->cg_flags & AMD_CG_SUPPORT_GFX_MGCG)) {
 		/* 1 - RLC_CGTT_MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
-		data &= ~(RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK |
-			  RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
+
+		if (adev->asic_type != CHIP_VEGA12)
+			data &= ~RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK;
+
+		data &= ~(RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			  RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
 
@@ -3585,11 +3588,15 @@ static void gfx_v9_0_update_medium_grain_clock_gating(struct amdgpu_device *adev
 	} else {
 		/* 1 - MGCG_OVERRIDE */
 		def = data = RREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE);
-		data |= (RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK |
-			 RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
+
+		if (adev->asic_type != CHIP_VEGA12)
+			data |= RLC_CGTT_MGCG_OVERRIDE__CPF_CGTT_SCLK_OVERRIDE_MASK;
+
+		data |= (RLC_CGTT_MGCG_OVERRIDE__RLC_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GRBM_CGTT_SCLK_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGCG_OVERRIDE_MASK |
 			 RLC_CGTT_MGCG_OVERRIDE__GFXIP_MGLS_OVERRIDE_MASK);
+
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
-- 
cgit v1.2.3


From a5aedc2d18bcb33816545f39f13a37a0c86b3b3d Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Thu, 5 Jul 2018 10:30:36 +0800
Subject: drm/amdgpu: reduce the idle period that RLC has to wait before
 request CGCG

Gfxoff feature may depends on the CGCG(on vega12, that's the case). This
change will help to enable gfxoff feature more frequently.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 1f88eb2566bf..ff754bf1875c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3632,9 +3632,11 @@ static void gfx_v9_0_update_3d_clock_gating(struct amdgpu_device *adev,
 		/* update CGCG and CGLS override bits */
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
-		/* enable 3Dcgcg FSM(0x0020003f) */
+
+		/* enable 3Dcgcg FSM(0x0000363f) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL_3D);
-		data = (0x2000 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+
+		data = (0x36 << RLC_CGCG_CGLS_CTRL_3D__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
 			RLC_CGCG_CGLS_CTRL_3D__CGCG_EN_MASK;
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_3D_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL_3D__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
@@ -3681,9 +3683,10 @@ static void gfx_v9_0_update_coarse_grain_clock_gating(struct amdgpu_device *adev
 		if (def != data)
 			WREG32_SOC15(GC, 0, mmRLC_CGTT_MGCG_OVERRIDE, data);
 
-		/* enable cgcg FSM(0x0020003F) */
+		/* enable cgcg FSM(0x0000363F) */
 		def = RREG32_SOC15(GC, 0, mmRLC_CGCG_CGLS_CTRL);
-		data = (0x2000 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
+
+		data = (0x36 << RLC_CGCG_CGLS_CTRL__CGCG_GFX_IDLE_THRESHOLD__SHIFT) |
 			RLC_CGCG_CGLS_CTRL__CGCG_EN_MASK;
 		if (adev->cg_flags & AMD_CG_SUPPORT_GFX_CGLS)
 			data |= (0x000F << RLC_CGCG_CGLS_CTRL__CGLS_REP_COMPANSAT_DELAY__SHIFT) |
-- 
cgit v1.2.3


From 991a6b32ce647e9827acc0c72a998e4ffed1d753 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Wed, 4 Jul 2018 16:44:07 +0800
Subject: drm/amd/powerplay: add vega12 SMU gfxoff support v3

Export apis for enabling/disabling SMU gfxoff support.

v2: fit the latest gfxoff support framework
v3: add feature_mask control

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Huang Rui <ray.huang at amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c              |  5 +++
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 38 ++++++++++++++++++++++
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h |  3 ++
 3 files changed, 46 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index ff754bf1875c..e6d19e7fbfbd 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3769,6 +3769,11 @@ static int gfx_v9_0_set_powergating_state(void *handle,
 		/* update mgcg state */
 		gfx_v9_0_update_gfx_mg_power_gating(adev, enable);
 
+		/* set gfx off through smu */
+		if (enable && adev->powerplay.pp_funcs->set_powergating_by_smu)
+			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true);
+		break;
+	case CHIP_VEGA12:
 		/* set gfx off through smu */
 		if (enable && adev->powerplay.pp_funcs->set_powergating_by_smu)
 			amdgpu_dpm_set_powergating_by_smu(adev, AMD_IP_BLOCK_TYPE_GFX, true);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index ed17c560b5ef..cae76fe65881 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -423,6 +423,11 @@ static int vega12_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
 			hwmgr->thermal_controller.advanceFanControlParameters.usFanPWMMinLimit *
 			hwmgr->thermal_controller.fanInfo.ulMaxRPM / 100;
 
+	if (hwmgr->feature_mask & PP_GFXOFF_MASK)
+		data->gfxoff_controlled_by_driver = true;
+	else
+		data->gfxoff_controlled_by_driver = false;
+
 	return result;
 }
 
@@ -2328,6 +2333,38 @@ static int vega12_get_thermal_temperature_range(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
+static int vega12_enable_gfx_off(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->gfxoff_controlled_by_driver)
+		ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_AllowGfxOff);
+
+	return ret;
+}
+
+static int vega12_disable_gfx_off(struct pp_hwmgr *hwmgr)
+{
+	struct vega12_hwmgr *data =
+			(struct vega12_hwmgr *)(hwmgr->backend);
+	int ret = 0;
+
+	if (data->gfxoff_controlled_by_driver)
+		ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_DisallowGfxOff);
+
+	return ret;
+}
+
+static int vega12_gfx_off_control(struct pp_hwmgr *hwmgr, bool enable)
+{
+	if (enable)
+		return vega12_enable_gfx_off(hwmgr);
+	else
+		return vega12_disable_gfx_off(hwmgr);
+}
+
 static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.backend_init = vega12_hwmgr_backend_init,
 	.backend_fini = vega12_hwmgr_backend_fini,
@@ -2377,6 +2414,7 @@ static const struct pp_hwmgr_func vega12_hwmgr_funcs = {
 	.get_thermal_temperature_range = vega12_get_thermal_temperature_range,
 	.register_irq_handlers = smu9_register_irq_handlers,
 	.start_thermal_controller = vega12_start_thermal_controller,
+	.powergate_gfx = vega12_gfx_off_control,
 };
 
 int vega12_hwmgr_init(struct pp_hwmgr *hwmgr)
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
index e17237c90eea..b3e424d28994 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.h
@@ -393,6 +393,9 @@ struct vega12_hwmgr {
 	struct vega12_smc_state_table  smc_state_table;
 
 	struct vega12_clock_range      clk_range[PPCLK_COUNT];
+
+	/* ---- Gfxoff ---- */
+	bool                           gfxoff_controlled_by_driver;
 };
 
 #define VEGA12_DPM2_NEAR_TDP_DEC                      10
-- 
cgit v1.2.3


From 3f2e6bf89cab5f7c84dafc62f478874fdc08d161 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Thu, 5 Jul 2018 10:44:33 +0800
Subject: drm/amd/powerplay: no need to mask workable gfxoff feature for vega12

Gfxoff feature for vega12 is workable. So, there is no need to
mask it any more.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
index 9b675d9bd162..8994aa5c8cf8 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/hwmgr.c
@@ -147,10 +147,10 @@ int hwmgr_early_init(struct pp_hwmgr *hwmgr)
 		smu7_init_function_pointers(hwmgr);
 		break;
 	case AMDGPU_FAMILY_AI:
-		hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 		switch (hwmgr->chip_id) {
 		case CHIP_VEGA10:
 		case CHIP_VEGA20:
+			hwmgr->feature_mask &= ~PP_GFXOFF_MASK;
 			hwmgr->smumgr_funcs = &vega10_smu_funcs;
 			vega10_hwmgr_init(hwmgr);
 			break;
-- 
cgit v1.2.3


From ed515ce2748007385347d70ec2779d6aef2cf5f0 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Tue, 10 Jul 2018 11:35:16 +0800
Subject: drm/amd/powerplay: convert the sclk/mclk into Mhz for comparation

Convert the clocks into right Mhz unit. Otherwise, it will miss
the equal situation.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index cae76fe65881..c0ceb69a23b0 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1881,7 +1881,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
-				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
+				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
 
 	case PP_MCLK:
@@ -1897,7 +1897,7 @@ static int vega12_print_clock_levels(struct pp_hwmgr *hwmgr,
 		for (i = 0; i < clocks.num_levels; i++)
 			size += sprintf(buf + size, "%d: %uMhz %s\n",
 				i, clocks.data[i].clocks_in_khz / 1000,
-				(clocks.data[i].clocks_in_khz / 1000 == now) ? "*" : "");
+				(clocks.data[i].clocks_in_khz / 1000 == now / 100) ? "*" : "");
 		break;
 
 	case PP_PCIE:
-- 
cgit v1.2.3


From 530e7a660fb795452357b36cce26b839a9a187a9 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Wed, 11 Jul 2018 17:34:35 -0400
Subject: drm/amd: Add interrupt source definitions for VI v3.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Stop using 'magic numbers' when registering interrupt sources.

v2:
Clean redundant comments.
Switch to kernel style comments.

v3:
Add CP_ECC_ERROR define

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/include/ivsrcid/ivsrcid_vislands30.h   | 98 ++++++++++++++++++++++
 1 file changed, 98 insertions(+)

diff --git a/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h b/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
index c6b6f97de9de..aaed7f59e0e2 100644
--- a/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
+++ b/drivers/gpu/drm/amd/include/ivsrcid/ivsrcid_vislands30.h
@@ -198,4 +198,102 @@
 #define VISLANDS30_IV_SRCID_HPD_RX_F		                    42	    // 0x2a		
 #define VISLANDS30_IV_EXTID_HPD_RX_F                         11
 
+#define VISLANDS30_IV_SRCID_GPIO_19                            0x00000053  /* 83 */
+
+#define VISLANDS30_IV_SRCID_SRBM_READ_TIMEOUT_ERR              0x00000060  /* 96 */
+#define VISLANDS30_IV_SRCID_SRBM_CTX_SWITCH                    0x00000061  /* 97 */
+
+#define VISLANDS30_IV_SRBM_REG_ACCESS_ERROR                    0x00000062  /* 98 */
+
+
+#define VISLANDS30_IV_SRCID_UVD_ENC_GEN_PURP                   0x00000077  /* 119 */
+#define VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE                 0x0000007c  /* 124 */
+
+#define VISLANDS30_IV_SRCID_BIF_PF_VF_MSGBUF_VALID             0x00000087  /* 135 */
+
+#define VISLANDS30_IV_SRCID_BIF_VF_PF_MSGBUF_ACK               0x0000008a  /* 138 */
+
+#define VISLANDS30_IV_SRCID_SYS_PAGE_INV_FAULT                 0x0000008c  /* 140 */
+#define VISLANDS30_IV_SRCID_SYS_MEM_PROT_FAULT                 0x0000008d  /* 141 */
+
+#define VISLANDS30_IV_SRCID_SEM_PAGE_INV_FAULT                 0x00000090  /* 144 */
+#define VISLANDS30_IV_SRCID_SEM_MEM_PROT_FAULT                 0x00000091  /* 145 */
+
+#define VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT                 0x00000092  /* 146 */
+#define VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT                 0x00000093  /* 147 */
+
+#define VISLANDS30_IV_SRCID_ACP                                0x000000a2  /* 162 */
+
+#define VISLANDS30_IV_SRCID_VCE_TRAP                           0x000000a7  /* 167 */
+#define VISLANDS30_IV_EXTID_VCE_TRAP_GENERAL_PURPOSE           0
+#define VISLANDS30_IV_EXTID_VCE_TRAP_LOW_LATENCY               1
+#define VISLANDS30_IV_EXTID_VCE_TRAP_REAL_TIME                 2
+
+#define VISLANDS30_IV_SRCID_CP_INT_RB                          0x000000b0  /* 176 */
+#define VISLANDS30_IV_SRCID_CP_INT_IB1                         0x000000b1  /* 177 */
+#define VISLANDS30_IV_SRCID_CP_INT_IB2                         0x000000b2  /* 178 */
+#define VISLANDS30_IV_SRCID_CP_PM4_RES_BITS_ERR                0x000000b4  /* 180 */
+#define VISLANDS30_IV_SRCID_CP_END_OF_PIPE                     0x000000b5  /* 181 */
+#define VISLANDS30_IV_SRCID_CP_BAD_OPCODE                      0x000000b7  /* 183 */
+#define VISLANDS30_IV_SRCID_CP_PRIV_REG_FAULT                  0x000000b8  /* 184 */
+#define VISLANDS30_IV_SRCID_CP_PRIV_INSTR_FAULT                0x000000b9  /* 185 */
+#define VISLANDS30_IV_SRCID_CP_WAIT_MEM_SEM_FAULT              0x000000ba  /* 186 */
+#define VISLANDS30_IV_SRCID_CP_GUI_IDLE                        0x000000bb  /* 187 */
+#define VISLANDS30_IV_SRCID_CP_GUI_BUSY                        0x000000bc  /* 188 */
+
+#define VISLANDS30_IV_SRCID_CP_COMPUTE_QUERY_STATUS            0x000000bf  /* 191 */
+#define VISLANDS30_IV_SRCID_CP_ECC_ERROR                       0x000000c5  /* 197 */
+
+#define CARRIZO_IV_SRCID_CP_COMPUTE_QUERY_STATUS               0x000000c7  /* 199 */
+
+#define VISLANDS30_IV_SRCID_CP_WAIT_REG_MEM_POLL_TIMEOUT       0x000000c0  /* 192 */
+#define VISLANDS30_IV_SRCID_CP_SEM_SIG_INCOMPL                 0x000000c1  /* 193 */
+#define VISLANDS30_IV_SRCID_CP_PREEMPT_ACK                     0x000000c2  /* 194 */
+#define VISLANDS30_IV_SRCID_CP_GENERAL_PROT_FAULT              0x000000c3  /* 195 */
+#define VISLANDS30_IV_SRCID_CP_GDS_ALLOC_ERROR                 0x000000c4  /* 196 */
+#define VISLANDS30_IV_SRCID_CP_ECC_ERROR                       0x000000c5  /* 197 */
+
+#define VISLANDS30_IV_SRCID_RLC_STRM_PERF_MONITOR              0x000000ca  /* 202 */
+
+#define VISLANDS30_IV_SDMA_ATOMIC_SRC_ID                       0x000000da  /* 218 */
+
+#define VISLANDS30_IV_SRCID_SDMA_ECC_ERROR                     0x000000dc  /* 220 */
+
+#define VISLANDS30_IV_SRCID_SDMA_TRAP          	               0x000000e0  /* 224 */
+#define VISLANDS30_IV_SRCID_SDMA_SEM_INCOMPLETE                0x000000e1  /* 225 */
+#define VISLANDS30_IV_SRCID_SDMA_SEM_WAIT                      0x000000e2  /* 226 */
+
+
+#define VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER            0x000000e5  /* 229 */
+
+#define VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH         0x000000e6  /* 230 */
+#define VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW         0x000000e7  /* 231 */
+
+#define VISLANDS30_IV_SRCID_GRBM_READ_TIMEOUT_ERR              0x000000e8  /* 232 */
+#define VISLANDS30_IV_SRCID_GRBM_REG_GUI_IDLE                  0x000000e9  /* 233 */
+
+#define VISLANDS30_IV_SRCID_SQ_INTERRUPT_MSG                   0x000000ef  /* 239 */
+
+#define VISLANDS30_IV_SRCID_SDMA_PREEMPT                       0x000000f0  /* 240 */
+#define VISLANDS30_IV_SRCID_SDMA_VM_HOLE                       0x000000f2  /* 242 */
+#define VISLANDS30_IV_SRCID_SDMA_CTXEMPTY                      0x000000f3  /* 243 */
+#define VISLANDS30_IV_SRCID_SDMA_DOORBELL_INVALID              0x000000f4  /* 244 */
+#define VISLANDS30_IV_SRCID_SDMA_FROZEN                        0x000000f5  /* 245 */
+#define VISLANDS30_IV_SRCID_SDMA_POLL_TIMEOUT                  0x000000f6  /* 246 */
+#define VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE                    0x000000f7  /* 247 */
+
+#define VISLANDS30_IV_SRCID_CG_THERMAL_TRIG                    0x000000f8  /* 248 */
+
+#define VISLANDS30_IV_SRCID_SMU_DISP_TIMER_TRIGGER             0x000000fd  /* 253 */
+
+/* These are not "real" source ids defined by HW */
+#define VISLANDS30_IV_SRCID_VM_CONTEXT_ALL                     0x00000100  /* 256 */
+#define VISLANDS30_IV_EXTID_VM_CONTEXT0_ALL                    0
+#define VISLANDS30_IV_EXTID_VM_CONTEXT1_ALL                    1
+
+
+/* IV Extended IDs */
+#define VISLANDS30_IV_EXTID_NONE                               0x00000000
+#define VISLANDS30_IV_EXTID_INVALID                            0xffffffff
+
 #endif // _IVSRCID_VISLANDS30_H_
-- 
cgit v1.2.3


From 091aec0b4e26c8d31b6c211b57a2ea2c5b985ca9 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Fri, 25 May 2018 10:06:52 -0400
Subject: drm/amd: Use newly added interrupt source defs for VI v3.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

v2: Rebase
v3: Use defines for CP_SQ and CP_ECC_ERROR interrupts.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/dce_v10_0.c           |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/dce_v11_0.c           |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/dce_virtual.c         |  3 ++-
 drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c            | 14 ++++++++------
 drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c            |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c            |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c           |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c           |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c            |  3 ++-
 drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c            |  5 +++--
 drivers/gpu/drm/amd/amdgpu/vce_v3_0.c            |  3 ++-
 drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c |  8 +++++---
 12 files changed, 46 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
index ab043228d8da..308f9f238bc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v10_0.c
@@ -41,6 +41,8 @@
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void dce_v10_0_set_display_funcs(struct amdgpu_device *adev);
 static void dce_v10_0_set_irq_funcs(struct amdgpu_device *adev);
 
@@ -2737,14 +2739,14 @@ static int dce_v10_0_sw_init(void *handle)
 			return r;
 	}
 
-	for (i = 8; i < 20; i += 2) {
+	for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP; i < 20; i += 2) {
 		r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i, &adev->pageflip_irq);
 		if (r)
 			return r;
 	}
 
 	/* HPD hotplug */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 42, &adev->hpd_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
index 177851264754..76dfb76f7900 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_v11_0.c
@@ -41,6 +41,8 @@
 #include "gmc/gmc_8_1_d.h"
 #include "gmc/gmc_8_1_sh_mask.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void dce_v11_0_set_display_funcs(struct amdgpu_device *adev);
 static void dce_v11_0_set_irq_funcs(struct amdgpu_device *adev);
 
@@ -2858,14 +2860,14 @@ static int dce_v11_0_sw_init(void *handle)
 			return r;
 	}
 
-	for (i = 8; i < 20; i += 2) {
+	for (i = VISLANDS30_IV_SRCID_D1_GRPH_PFLIP; i < 20; i += 2) {
 		r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i, &adev->pageflip_irq);
 		if (r)
 			return r;
 	}
 
 	/* HPD hotplug */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 42, &adev->hpd_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_HOTPLUG_DETECT_A, &adev->hpd_irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
index dbf2ccd0c744..aea8b89765c6 100644
--- a/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
+++ b/drivers/gpu/drm/amd/amdgpu/dce_virtual.c
@@ -36,6 +36,7 @@
 #include "dce_v10_0.h"
 #include "dce_v11_0.h"
 #include "dce_virtual.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 #define DCE_VIRTUAL_VBLANK_PERIOD 16666666
 
@@ -378,7 +379,7 @@ static int dce_virtual_sw_init(void *handle)
 	int r, i;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 229, &adev->crtc_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SMU_DISP_TIMER2_TRIGGER, &adev->crtc_irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 551f21bad6d3..5cd45210113f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -51,6 +51,8 @@
 
 #include "smu/smu_7_1_3_d.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 #define GFX8_NUM_GFX_RINGS     1
 #define GFX8_MEC_HPD_SIZE 2048
 
@@ -2047,35 +2049,35 @@ static int gfx_v8_0_sw_init(void *handle)
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
 	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 178, &adev->gfx.kiq.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_INT_IB2, &adev->gfx.kiq.irq);
 	if (r)
 		return r;
 
 	/* EOP Event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 181, &adev->gfx.eop_irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_END_OF_PIPE, &adev->gfx.eop_irq);
 	if (r)
 		return r;
 
 	/* Privileged reg */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 184,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_PRIV_REG_FAULT,
 			      &adev->gfx.priv_reg_irq);
 	if (r)
 		return r;
 
 	/* Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 185,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_PRIV_INSTR_FAULT,
 			      &adev->gfx.priv_inst_irq);
 	if (r)
 		return r;
 
 	/* Add CP EDC/ECC irq  */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 197,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_CP_ECC_ERROR,
 			      &adev->gfx.cp_ecc_error_irq);
 	if (r)
 		return r;
 
 	/* SQ interrupts. */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 239,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SQ_INTERRUPT_MSG,
 			      &adev->gfx.sq_irq);
 	if (r) {
 		DRM_ERROR("amdgpu_irq_add() for SQ failed: %d\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
index 78339309a00c..10920f0bd85f 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v7_0.c
@@ -43,6 +43,8 @@
 
 #include "amdgpu_atombios.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void gmc_v7_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v7_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v7_0_wait_for_idle(void *handle);
@@ -996,11 +998,11 @@ static int gmc_v7_0_sw_init(void *handle)
 		adev->gmc.vram_type = gmc_v7_0_convert_vram_type(tmp);
 	}
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 146, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 147, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
index a86332f36c3e..75f3ffb2891e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v8_0.c
@@ -44,6 +44,8 @@
 
 #include "amdgpu_atombios.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void gmc_v8_0_set_gmc_funcs(struct amdgpu_device *adev);
 static void gmc_v8_0_set_irq_funcs(struct amdgpu_device *adev);
 static int gmc_v8_0_wait_for_idle(void *handle);
@@ -1100,11 +1102,11 @@ static int gmc_v8_0_sw_init(void *handle)
 		adev->gmc.vram_type = gmc_v8_0_convert_vram_type(tmp);
 	}
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 146, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_PAGE_INV_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 147, &adev->gmc.vm_fault);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_GFX_MEM_PROT_FAULT, &adev->gmc.vm_fault);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index cee4fae76d20..15ae4bc9c072 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -44,6 +44,8 @@
 
 #include "iceland_sdma_pkt_open.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void sdma_v2_4_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v2_4_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v2_4_set_vm_pte_funcs(struct amdgpu_device *adev);
@@ -896,7 +898,7 @@ static int sdma_v2_4_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 224,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -908,7 +910,7 @@ static int sdma_v2_4_sw_init(void *handle)
 		return r;
 
 	/* SDMA Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 247,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
 			      &adev->sdma.illegal_inst_irq);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 99616dd9594f..1e07ff274d73 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -44,6 +44,8 @@
 
 #include "tonga_sdma_pkt_open.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 static void sdma_v3_0_set_ring_funcs(struct amdgpu_device *adev);
 static void sdma_v3_0_set_buffer_funcs(struct amdgpu_device *adev);
 static void sdma_v3_0_set_vm_pte_funcs(struct amdgpu_device *adev);
@@ -1175,7 +1177,7 @@ static int sdma_v3_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 224,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
@@ -1187,7 +1189,7 @@ static int sdma_v3_0_sw_init(void *handle)
 		return r;
 
 	/* SDMA Privileged inst */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 247,
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_SDMA_SRBM_WRITE,
 			      &adev->sdma.illegal_inst_irq);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
index 341ee6d55ce8..aeaa1ca46a99 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v5_0.c
@@ -35,6 +35,7 @@
 #include "vi.h"
 #include "smu/smu_7_1_2_d.h"
 #include "smu/smu_7_1_2_sh_mask.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 static void uvd_v5_0_set_ring_funcs(struct amdgpu_device *adev);
 static void uvd_v5_0_set_irq_funcs(struct amdgpu_device *adev);
@@ -104,7 +105,7 @@ static int uvd_v5_0_sw_init(void *handle)
 	int r;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 8ee1c2eaaa14..2623f249cb7a 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -36,6 +36,7 @@
 #include "bif/bif_5_1_d.h"
 #include "gmc/gmc_8_1_d.h"
 #include "vi.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 /* Polaris10/11/12 firmware version */
 #define FW_1_130_16 ((1 << 24) | (130 << 16) | (16 << 8))
@@ -400,14 +401,14 @@ static int uvd_v6_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* UVD TRAP */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 124, &adev->uvd.inst->irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_UVD_SYSTEM_MESSAGE, &adev->uvd.inst->irq);
 	if (r)
 		return r;
 
 	/* UVD ENC TRAP */
 	if (uvd_v6_0_enc_support(adev)) {
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + 119, &adev->uvd.inst->irq);
+			r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, i + VISLANDS30_IV_SRCID_UVD_ENC_GEN_PURP, &adev->uvd.inst->irq);
 			if (r)
 				return r;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
index 99604d0262ad..cc6ce6cc03f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v3_0.c
@@ -39,6 +39,7 @@
 #include "smu/smu_7_1_2_sh_mask.h"
 #include "gca/gfx_8_0_d.h"
 #include "gca/gfx_8_0_sh_mask.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 
 #define GRBM_GFX_INDEX__VCE_INSTANCE__SHIFT	0x04
@@ -422,7 +423,7 @@ static int vce_v3_0_sw_init(void *handle)
 	int r, i;
 
 	/* VCE */
-	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, 167, &adev->vce.irq);
+	r = amdgpu_irq_add_id(adev, AMDGPU_IH_CLIENTID_LEGACY, VISLANDS30_IV_SRCID_VCE_TRAP, &adev->vce.irq);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
index 2f7e70730e3c..052e60dfaf9f 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_hwmgr.c
@@ -48,6 +48,8 @@
 #include "processpptables.h"
 #include "pp_thermal.h"
 
+#include "ivsrcid/ivsrcid_vislands30.h"
+
 #define MC_CG_ARB_FREQ_F0           0x0a
 #define MC_CG_ARB_FREQ_F1           0x0b
 #define MC_CG_ARB_FREQ_F2           0x0c
@@ -4105,17 +4107,17 @@ static int smu7_register_irq_handlers(struct pp_hwmgr *hwmgr)
 
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			230,
+			VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH,
 			source);
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			231,
+			VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW,
 			source);
 
 	/* Register CTF(GPIO_19) interrupt */
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			AMDGPU_IH_CLIENTID_LEGACY,
-			83,
+			VISLANDS30_IV_SRCID_GPIO_19,
 			source);
 
 	return 0;
-- 
cgit v1.2.3


From ba61bb17496d1664bf7c5c2fd650d5fd78bd0a92 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Fri, 25 May 2018 10:44:12 -0400
Subject: drm/amd: Add interrupt source definitions for SOC15 v3.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Stop using 'magic numbers' when registering interrupt sources.

v2: Switch to kernel style comments.

v3:
Rebase.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h  | 55 ++++++++++++++++++++++
 .../amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h  | 50 ++++++++++++++++++++
 .../amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h  | 50 ++++++++++++++++++++
 .../amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h  | 32 +++++++++++++
 .../drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h  | 33 +++++++++++++
 .../drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h  | 34 +++++++++++++
 .../drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h  | 34 +++++++++++++
 .../drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h  | 34 +++++++++++++
 .../drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h  | 37 +++++++++++++++
 9 files changed, 359 insertions(+)
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h
 create mode 100644 drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h

diff --git a/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h b/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h
new file mode 100644
index 000000000000..36306c57a2b4
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/gfx/irqsrcs_gfx_9_0.h
@@ -0,0 +1,55 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_GFX_9_0_H__
+#define __IRQSRCS_GFX_9_0_H__
+
+
+#define GFX_9_0__SRCID__CP_RB_INTERRUPT_PKT					176		/* B0 CP_INTERRUPT pkt in RB */
+#define GFX_9_0__SRCID__CP_IB1_INTERRUPT_PKT				177		/* B1 CP_INTERRUPT pkt in IB1 */
+#define GFX_9_0__SRCID__CP_IB2_INTERRUPT_PKT				178		/* B2 CP_INTERRUPT pkt in IB2 */
+#define GFX_9_0__SRCID__CP_PM4_PKT_RSVD_BIT_ERROR			180		/* B4 PM4 Pkt Rsvd Bits Error */
+#define GFX_9_0__SRCID__CP_EOP_INTERRUPT					181		/* B5 End-of-Pipe Interrupt */
+#define GFX_9_0__SRCID__CP_BAD_OPCODE_ERROR					183		/* B7 Bad Opcode Error */
+#define GFX_9_0__SRCID__CP_PRIV_REG_FAULT					184		/* B8 Privileged Register Fault */
+#define GFX_9_0__SRCID__CP_PRIV_INSTR_FAULT					185		/* B9 Privileged Instr Fault */
+#define GFX_9_0__SRCID__CP_WAIT_MEM_SEM_FAULT				186		/* BA Wait Memory Semaphore Fault (Synchronization Object Fault) */
+#define GFX_9_0__SRCID__CP_CTX_EMPTY_INTERRUPT				187		/* BB Context Empty Interrupt */
+#define GFX_9_0__SRCID__CP_CTX_BUSY_INTERRUPT				188		/* BC Context Busy Interrupt */
+#define GFX_9_0__SRCID__CP_ME_WAIT_REG_MEM_POLL_TIMEOUT		192		/* C0 CP.ME Wait_Reg_Mem Poll Timeout */
+#define GFX_9_0__SRCID__CP_SIG_INCOMPLETE					193		/* C1 "Surface Probe Fault Signal Incomplete" */
+#define GFX_9_0__SRCID__CP_PREEMPT_ACK					    194		/* C2 Preemption Ack-wledge */
+#define GFX_9_0__SRCID__CP_GPF					            195		/* C3 General Protection Fault (GPF) */
+#define GFX_9_0__SRCID__CP_GDS_ALLOC_ERROR					196		/* C4 GDS Alloc Error */
+#define GFX_9_0__SRCID__CP_ECC_ERROR					    197		/* C5 ECC  Error */
+#define GFX_9_0__SRCID__CP_COMPUTE_QUERY_STATUS             199     /* C7 Compute query status */
+#define GFX_9_0__SRCID__CP_VM_DOORBELL					    200		/* C8 Unattached VM Doorbell Received */
+#define GFX_9_0__SRCID__CP_FUE_ERROR					    201		/* C9 ECC FUE Error */
+#define GFX_9_0__SRCID__RLC_STRM_PERF_MONITOR_INTERRUPT		202		/* CA Streaming Perf Monitor Interrupt */
+#define GFX_9_0__SRCID__GRBM_RD_TIMEOUT_ERROR				232		/* E8 CRead timeout error */
+#define GFX_9_0__SRCID__GRBM_REG_GUI_IDLE					233		/* E9 Register GUI Idle */
+#define GFX_9_0__SRCID__SQ_INTERRUPT_ID					    239		/* EF SQ Interrupt (ttrace wrap, errors) */
+
+#endif /* __IRQSRCS_GFX_9_0_H__ */
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h
new file mode 100644
index 000000000000..802413832fe8
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/sdma0/irqsrcs_sdma0_4_0.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_SDMA0_4_0_H__
+#define __IRQSRCS_SDMA0_4_0_H__
+
+#define SDMA0_4_0__SRCID__SDMA_ATOMIC_RTN_DONE                         217             /* 0xD9 SDMA atomic*_rtn ops complete  */
+#define SDMA0_4_0__SRCID__SDMA_ATOMIC_TIMEOUT                          218             /* 0xDA SDMA atomic CMPSWAP loop timeout  */
+#define SDMA0_4_0__SRCID__SDMA_IB_PREEMPT                                      219             /* 0xDB sdma mid-command buffer preempt interrupt  */
+#define SDMA0_4_0__SRCID__SDMA_ECC                                             220             /* 0xDC ECC  Error  */
+#define SDMA0_4_0__SRCID__SDMA_PAGE_FAULT                                      221             /* 0xDD Page Fault Error from UTCL2 when nack=3  */
+#define SDMA0_4_0__SRCID__SDMA_PAGE_NULL                                       222             /* 0xDE Page Null from UTCL2 when nack=2  */
+#define SDMA0_4_0__SRCID__SDMA_XNACK                                       223         /* 0xDF Page retry  timeout after UTCL2 return nack=1  */
+#define SDMA0_4_0__SRCID__SDMA_TRAP                                            224             /* 0xE0 Trap  */
+#define SDMA0_4_0__SRCID__SDMA_SEM_INCOMPLETE_TIMEOUT          225             /* 0xE1 0xDAGPF (Sem incomplete timeout)  */
+#define SDMA0_4_0__SRCID__SDMA_SEM_WAIT_FAIL_TIMEOUT           226             /* 0xE2 Semaphore wait fail timeout  */
+#define SDMA0_4_0__SRCID__SDMA_SRAM_ECC                                            228         /* 0xE4 SRAM ECC Error  */
+#define SDMA0_4_0__SRCID__SDMA_PREEMPT                                     240         /* 0xF0 SDMA New Run List  */
+#define SDMA0_4_0__SRCID__SDMA_VM_HOLE                                     242         /* 0xF2 MC or SEM address in VM hole  */
+#define SDMA0_4_0__SRCID__SDMA_CTXEMPTY                                            243         /* 0xF3 Context Empty  */
+#define SDMA0_4_0__SRCID__SDMA_DOORBELL_INVALID                                244             /* 0xF4 Doorbell BE invalid  */
+#define SDMA0_4_0__SRCID__SDMA_FROZEN                                      245         /* 0xF5 SDMA Frozen  */
+#define SDMA0_4_0__SRCID__SDMA_POLL_TIMEOUT                                    246             /* 0xF6 SRBM read poll timeout  */
+#define SDMA0_4_0__SRCID__SDMA_SRBMWRITE                                       247             /* 0xF7 SRBM write Protection  */
+
+#endif /* __IRQSRCS_SDMA_4_0_H__ */
+
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h
new file mode 100644
index 000000000000..d12a35619f9a
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/sdma1/irqsrcs_sdma1_4_0.h
@@ -0,0 +1,50 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_SDMA1_4_0_H__
+#define __IRQSRCS_SDMA1_4_0_H__
+
+#define SDMA1_4_0__SRCID__SDMA_ATOMIC_RTN_DONE                         217             /* 0xD9 SDMA atomic*_rtn ops complete  */
+#define SDMA1_4_0__SRCID__SDMA_ATOMIC_TIMEOUT                          218             /* 0xDA SDMA atomic CMPSWAP loop timeout  */
+#define SDMA1_4_0__SRCID__SDMA_IB_PREEMPT                                      219             /* 0xDB sdma mid-command buffer preempt interrupt  */
+#define SDMA1_4_0__SRCID__SDMA_ECC                                             220             /* 0xDC ECC  Error  */
+#define SDMA1_4_0__SRCID__SDMA_PAGE_FAULT                                      221             /* 0xDD Page Fault Error from UTCL2 when nack=3  */
+#define SDMA1_4_0__SRCID__SDMA_PAGE_NULL                                       222             /* 0xDE Page Null from UTCL2 when nack=2  */
+#define SDMA1_4_0__SRCID__SDMA_XNACK                                       223         /* 0xDF Page retry  timeout after UTCL2 return nack=1  */
+#define SDMA1_4_0__SRCID__SDMA_TRAP                                            224             /* 0xE0 Trap  */
+#define SDMA1_4_0__SRCID__SDMA_SEM_INCOMPLETE_TIMEOUT          225             /* 0xE1 0xDAGPF (Sem incomplete timeout)  */
+#define SDMA1_4_0__SRCID__SDMA_SEM_WAIT_FAIL_TIMEOUT           226             /* 0xE2 Semaphore wait fail timeout  */
+#define SDMA1_4_0__SRCID__SDMA_SRAM_ECC                                            228         /* 0xE4 SRAM ECC Error  */
+#define SDMA1_4_0__SRCID__SDMA_PREEMPT                                     240         /* 0xF0 SDMA New Run List  */
+#define SDMA1_4_0__SRCID__SDMA_VM_HOLE                                     242         /* 0xF2 MC or SEM address in VM hole  */
+#define SDMA1_4_0__SRCID__SDMA_CTXEMPTY                                            243         /* 0xF3 Context Empty  */
+#define SDMA1_4_0__SRCID__SDMA_DOORBELL_INVALID                                244             /* 0xF4 Doorbell BE invalid  */
+#define SDMA1_4_0__SRCID__SDMA_FROZEN                                      245         /* 0xF5 SDMA Frozen  */
+#define SDMA1_4_0__SRCID__SDMA_POLL_TIMEOUT                                    246             /* 0xF6 SRBM read poll timeout  */
+#define SDMA1_4_0__SRCID__SDMA_SRBMWRITE                                       247             /* 0xF7 SRBM write Protection  */
+
+#endif /* __IRQSRCS_SDMA1_4_0_H__ */
+
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h b/drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h
new file mode 100644
index 000000000000..02bab4673cd4
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/smuio/irqsrcs_smuio_9_0.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_SMUIO_9_0_H__
+#define __IRQSRCS_SMUIO_9_0_H__
+
+#define SMUIO_9_0__SRCID__SMUIO_GPIO19			83		/* GPIO19 interrupt  */
+
+#endif /* __IRQSRCS_SMUIO_9_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h b/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h
new file mode 100644
index 000000000000..5218bc53fb2d
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/thm/irqsrcs_thm_9_0.h
@@ -0,0 +1,33 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_THM_9_0_H__
+#define __IRQSRCS_THM_9_0_H__
+
+#define THM_9_0__SRCID__THM_DIG_THERM_L2H		0		/* ASIC_TEMP > CG_THERMAL_INT.DIG_THERM_INTH  */
+#define THM_9_0__SRCID__THM_DIG_THERM_H2L		1		/* ASIC_TEMP < CG_THERMAL_INT.DIG_THERM_INTL  */
+
+#endif /* __IRQSRCS_THM_9_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h b/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h
new file mode 100644
index 000000000000..fb041aee6c66
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/uvd/irqsrcs_uvd_7_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_UVD_7_0_H__
+#define __IRQSRCS_UVD_7_0_H__
+
+#define UVD_7_0__SRCID__UVD_ENC_GEN_PURP                119
+#define UVD_7_0__SRCID__UVD_ENC_LOW_LATENCY             120
+#define UVD_7_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT	124		/* UVD system message interrupt  */
+
+#endif /* __IRQSRCS_UVD_7_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h
new file mode 100644
index 000000000000..3440bab565af
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vce/irqsrcs_vce_4_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_VCE_4_0_H__
+#define __IRQSRCS_VCE_4_0_H__
+
+#define VCE_4_0__CTXID__VCE_TRAP_GENERAL_PURPOSE               0
+#define VCE_4_0__CTXID__VCE_TRAP_LOW_LATENCY                   1
+#define VCE_4_0__CTXID__VCE_TRAP_REAL_TIME                     2
+
+#endif /* __IRQSRCS_VCE_4_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h
new file mode 100644
index 000000000000..e5951709bfc3
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vcn/irqsrcs_vcn_1_0.h
@@ -0,0 +1,34 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_VCN_1_0_H__
+#define __IRQSRCS_VCN_1_0_H__
+
+#define VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE                 119     /* 0x77 Encoder General Purpose  */
+#define VCN_1_0__SRCID__UVD_ENC_LOW_LATENCY                     120     /* 0x78 Encoder Low Latency  */
+#define VCN_1_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT	        124		/* 0x7c UVD system message interrupt  */
+
+#endif /* __IRQSRCS_VCN_1_0_H__ */
+
diff --git a/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h b/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h
new file mode 100644
index 000000000000..d130936c9989
--- /dev/null
+++ b/drivers/gpu/drm/amd/include/ivsrcid/vmc/irqsrcs_vmc_1_0.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright 2017 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __IRQSRCS_VMC_1_0_H__
+#define __IRQSRCS_VMC_1_0_H__
+
+
+#define VMC_1_0__SRCID__VM_FAULT                            0
+#define VMC_1_0__SRCID__VM_CONTEXT0_ALL                     256
+#define VMC_1_0__SRCID__VM_CONTEXT1_ALL                     257
+
+#define UTCL2_1_0__SRCID__FAULT                             0       /* UTC L2 has encountered a fault or retry scenario */
+
+
+#endif /* __IRQSRCS_VMC_1_0_H__ */
-- 
cgit v1.2.3


From 44a99b65fc27474b66f7173b971bfbd67ca6ba74 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Fri, 25 May 2018 10:45:34 -0400
Subject: drm/amd: Use newly added interrupt source defs for SOC15.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c            | 10 ++++++----
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c            |  6 ++++--
 drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c           |  7 +++++--
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c            |  5 +++--
 drivers/gpu/drm/amd/amdgpu/vce_v4_0.c            |  2 ++
 drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c            |  6 ++++--
 drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c |  8 +++++---
 7 files changed, 29 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index e6d19e7fbfbd..a12da4a66b01 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -38,6 +38,8 @@
 #include "clearstate_gfx9.h"
 #include "v9_structs.h"
 
+#include "ivsrcid/gfx/irqsrcs_gfx_9_0.h"
+
 #define GFX9_NUM_GFX_RINGS     1
 #define GFX9_MEC_HPD_SIZE 2048
 #define RLCG_UCODE_LOADING_START_ADDRESS 0x00002000L
@@ -1488,23 +1490,23 @@ static int gfx_v9_0_sw_init(void *handle)
 	adev->gfx.mec.num_queue_per_pipe = 8;
 
 	/* KIQ event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 178, &adev->gfx.kiq.irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_IB2_INTERRUPT_PKT, &adev->gfx.kiq.irq);
 	if (r)
 		return r;
 
 	/* EOP Event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 181, &adev->gfx.eop_irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_EOP_INTERRUPT, &adev->gfx.eop_irq);
 	if (r)
 		return r;
 
 	/* Privileged reg */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 184,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_PRIV_REG_FAULT,
 			      &adev->gfx.priv_reg_irq);
 	if (r)
 		return r;
 
 	/* Privileged inst */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, 185,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_GRBM_CP, GFX_9_0__SRCID__CP_PRIV_INSTR_FAULT,
 			      &adev->gfx.priv_inst_irq);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 7f238149ba54..9df94b45d17d 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -43,6 +43,8 @@
 #include "gfxhub_v1_0.h"
 #include "mmhub_v1_0.h"
 
+#include "ivsrcid/vmc/irqsrcs_vmc_1_0.h"
+
 /* add these here since we already include dce12 headers and these are for DCN */
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION                                                          0x055d
 #define mmHUBP0_DCSURF_PRI_VIEWPORT_DIMENSION_BASE_IDX                                                 2
@@ -877,9 +879,9 @@ static int gmc_v9_0_sw_init(void *handle)
 	}
 
 	/* This interrupt is VMC page fault.*/
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, 0,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VMC, VMC_1_0__SRCID__VM_FAULT,
 				&adev->gmc.vm_fault);
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, 0,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_UTCL2, UTCL2_1_0__SRCID__FAULT,
 				&adev->gmc.vm_fault);
 
 	if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
index 572ca63cf676..e7ca4623cfb9 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
@@ -38,6 +38,9 @@
 #include "soc15.h"
 #include "vega10_sdma_pkt_open.h"
 
+#include "ivsrcid/sdma0/irqsrcs_sdma0_4_0.h"
+#include "ivsrcid/sdma1/irqsrcs_sdma1_4_0.h"
+
 MODULE_FIRMWARE("amdgpu/vega10_sdma.bin");
 MODULE_FIRMWARE("amdgpu/vega10_sdma1.bin");
 MODULE_FIRMWARE("amdgpu/vega12_sdma.bin");
@@ -1225,13 +1228,13 @@ static int sdma_v4_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA0, 224,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA0, SDMA0_4_0__SRCID__SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
 
 	/* SDMA trap event */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA1, 224,
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_SDMA1, SDMA1_4_0__SRCID__SDMA_TRAP,
 			      &adev->sdma.trap_irq);
 	if (r)
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index ba244d3b74db..ce360ad16856 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -39,6 +39,7 @@
 #include "hdp/hdp_4_0_offset.h"
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
+#include "ivsrcid/uvd/irqsrcs_uvd_7_0.h"
 
 #define UVD7_MAX_HW_INSTANCES_VEGA20			2
 
@@ -402,13 +403,13 @@ static int uvd_v7_0_sw_init(void *handle)
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
 		/* UVD TRAP */
-		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], 124, &adev->uvd.inst[j].irq);
+		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], UVD_7_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->uvd.inst[j].irq);
 		if (r)
 			return r;
 
 		/* UVD ENC TRAP */
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
-			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], i + 119, &adev->uvd.inst[j].irq);
+			r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], i + UVD_7_0__SRCID__UVD_ENC_GEN_PURP, &adev->uvd.inst[j].irq);
 			if (r)
 				return r;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
index 575bf9709389..65f8860169e9 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v4_0.c
@@ -39,6 +39,8 @@
 #include "mmhub/mmhub_1_0_offset.h"
 #include "mmhub/mmhub_1_0_sh_mask.h"
 
+#include "ivsrcid/vce/irqsrcs_vce_4_0.h"
+
 #define VCE_STATUS_VCPU_REPORT_FW_LOADED_MASK	0x02
 
 #define VCE_V4_0_FW_SIZE	(384 * 1024)
diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
index ca4265bc10b9..2ce91a748c40 100644
--- a/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vcn_v1_0.c
@@ -35,6 +35,8 @@
 #include "mmhub/mmhub_9_1_offset.h"
 #include "mmhub/mmhub_9_1_sh_mask.h"
 
+#include "ivsrcid/vcn/irqsrcs_vcn_1_0.h"
+
 static int vcn_v1_0_stop(struct amdgpu_device *adev);
 static void vcn_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
 static void vcn_v1_0_set_enc_ring_funcs(struct amdgpu_device *adev);
@@ -77,13 +79,13 @@ static int vcn_v1_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	/* VCN DEC TRAP */
-	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, 124, &adev->vcn.irq);
+	r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, VCN_1_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->vcn.irq);
 	if (r)
 		return r;
 
 	/* VCN ENC TRAP */
 	for (i = 0; i < adev->vcn.num_enc_rings; ++i) {
-		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + 119,
+		r = amdgpu_irq_add_id(adev, SOC15_IH_CLIENTID_VCN, i + VCN_1_0__SRCID__UVD_ENC_GENERAL_PURPOSE,
 					&adev->vcn.irq);
 		if (r)
 			return r;
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 3effb5583d1f..8eea49e4c74d 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -25,6 +25,8 @@
 #include "ppatomctrl.h"
 #include "ppsmc.h"
 #include "atom.h"
+#include "ivsrcid/thm/irqsrcs_thm_9_0.h"
+#include "ivsrcid/smuio/irqsrcs_smuio_9_0.h"
 
 uint8_t convert_to_vid(uint16_t vddc)
 {
@@ -594,17 +596,17 @@ int smu9_register_irq_handlers(struct pp_hwmgr *hwmgr)
 
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
-			0,
+			THM_9_0__SRCID__THM_DIG_THERM_L2H,
 			source);
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_THM,
-			1,
+			THM_9_0__SRCID__THM_DIG_THERM_H2L,
 			source);
 
 	/* Register CTF(GPIO_19) interrupt */
 	amdgpu_irq_add_id((struct amdgpu_device *)(hwmgr->adev),
 			SOC15_IH_CLIENTID_ROM_SMUIO,
-			83,
+			SMUIO_9_0__SRCID__SMUIO_GPIO19,
 			source);
 
 	return 0;
-- 
cgit v1.2.3


From b7d85e1db32ea85b09f58f416da48f44285ff41f Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 12 Jul 2018 14:31:25 +0200
Subject: drm/amdgpu: fix TTM move entity init order
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We are initializing the entity before the scheduler is actually
initialized.

This can lead to all kind of problem, but especially NULL pointer deref
because of Nayan's scheduler work.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 37 +++++++++++++++++++--------------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 0e47f15b0f97..6a3fead5c1f0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -104,8 +104,6 @@ static void amdgpu_ttm_mem_global_release(struct drm_global_reference *ref)
 static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 {
 	struct drm_global_reference *global_ref;
-	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
 	int r;
 
 	/* ensure reference is false in case init fails */
@@ -138,21 +136,10 @@ static int amdgpu_ttm_global_init(struct amdgpu_device *adev)
 
 	mutex_init(&adev->mman.gtt_window_lock);
 
-	ring = adev->mman.buffer_funcs_ring;
-	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-	r = drm_sched_entity_init(&ring->sched, &adev->mman.entity,
-				  rq, NULL);
-	if (r) {
-		DRM_ERROR("Failed setting up TTM BO move run queue.\n");
-		goto error_entity;
-	}
-
 	adev->mman.mem_global_referenced = true;
 
 	return 0;
 
-error_entity:
-	drm_global_item_unref(&adev->mman.bo_global_ref.ref);
 error_bo:
 	drm_global_item_unref(&adev->mman.mem_global_ref);
 error_mem:
@@ -162,8 +149,6 @@ error_mem:
 static void amdgpu_ttm_global_fini(struct amdgpu_device *adev)
 {
 	if (adev->mman.mem_global_referenced) {
-		drm_sched_entity_destroy(adev->mman.entity.sched,
-				      &adev->mman.entity);
 		mutex_destroy(&adev->mman.gtt_window_lock);
 		drm_global_item_unref(&adev->mman.bo_global_ref.ref);
 		drm_global_item_unref(&adev->mman.mem_global_ref);
@@ -1921,10 +1906,30 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 {
 	struct ttm_mem_type_manager *man = &adev->mman.bdev.man[TTM_PL_VRAM];
 	uint64_t size;
+	int r;
 
-	if (!adev->mman.initialized || adev->in_gpu_reset)
+	if (!adev->mman.initialized || adev->in_gpu_reset ||
+	    adev->mman.buffer_funcs_enabled == enable)
 		return;
 
+	if (enable) {
+		struct amdgpu_ring *ring;
+		struct drm_sched_rq *rq;
+
+		ring = adev->mman.buffer_funcs_ring;
+		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
+		r = drm_sched_entity_init(&ring->sched, &adev->mman.entity,
+					  rq, NULL);
+		if (r) {
+			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
+				  r);
+			return;
+		}
+	} else {
+		drm_sched_entity_destroy(adev->mman.entity.sched,
+					 &adev->mman.entity);
+	}
+
 	/* this just adjusts TTM size idea, which sets lpfn to the correct value */
 	if (enable)
 		size = adev->gmc.real_vram_size;
-- 
cgit v1.2.3


From 8dc9fbbf274b7b2a647e06141aee70ffabf6dbc0 Mon Sep 17 00:00:00 2001
From: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Date: Fri, 13 Jul 2018 15:21:13 +0530
Subject: drm/scheduler: add a pointer to scheduler in the rq
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch is in preparation for a better load balancing in
scheduler. It allows us to associate entities with the
run queues instead of binding them to a scheduler.

Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 ++++--
 include/drm/gpu_scheduler.h               | 2 ++
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 7d2560699b84..429b1328653a 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -69,11 +69,13 @@ static void drm_sched_process_job(struct dma_fence *f, struct dma_fence_cb *cb);
  *
  * Initializes a scheduler runqueue.
  */
-static void drm_sched_rq_init(struct drm_sched_rq *rq)
+static void drm_sched_rq_init(struct drm_gpu_scheduler *sched,
+			      struct drm_sched_rq *rq)
 {
 	spin_lock_init(&rq->lock);
 	INIT_LIST_HEAD(&rq->entities);
 	rq->current_entity = NULL;
+	rq->sched = sched;
 }
 
 /**
@@ -926,7 +928,7 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 	sched->timeout = timeout;
 	sched->hang_limit = hang_limit;
 	for (i = DRM_SCHED_PRIORITY_MIN; i < DRM_SCHED_PRIORITY_MAX; i++)
-		drm_sched_rq_init(&sched->sched_rq[i]);
+		drm_sched_rq_init(sched, &sched->sched_rq[i]);
 
 	init_waitqueue_head(&sched->wake_up_worker);
 	init_waitqueue_head(&sched->job_scheduled);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 4214ceb71c05..43e93d6077cf 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -93,6 +93,7 @@ struct drm_sched_entity {
  * struct drm_sched_rq - queue of entities to be scheduled.
  *
  * @lock: to modify the entities list.
+ * @sched: the scheduler to which this rq belongs to.
  * @entities: list of the entities to be scheduled.
  * @current_entity: the entity which is to be scheduled.
  *
@@ -102,6 +103,7 @@ struct drm_sched_entity {
  */
 struct drm_sched_rq {
 	spinlock_t			lock;
+	struct drm_gpu_scheduler	*sched;
 	struct list_head		entities;
 	struct drm_sched_entity		*current_entity;
 };
-- 
cgit v1.2.3


From aa16b6c6b4d979234f830a48add47d02c12bb569 Mon Sep 17 00:00:00 2001
From: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Date: Fri, 13 Jul 2018 15:21:14 +0530
Subject: drm/scheduler: modify args of drm_sched_entity_init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

replace run queue by a list of run queues and remove the
sched arg as that is part of run queue itself

Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c   |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c   |  3 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c   |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c   |  3 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c    |  3 +--
 drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c     |  4 ++--
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c     |  4 ++--
 drivers/gpu/drm/etnaviv/etnaviv_drv.c     |  8 ++++----
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 20 ++++++++++++--------
 drivers/gpu/drm/v3d/v3d_drv.c             |  7 +++----
 include/drm/gpu_scheduler.h               |  6 +++---
 11 files changed, 33 insertions(+), 33 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 0120b24fae1b..83e3b320a793 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -90,8 +90,8 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 		if (ring == &adev->gfx.kiq.ring)
 			continue;
 
-		r = drm_sched_entity_init(&ring->sched, &ctx->rings[i].entity,
-					  rq, &ctx->guilty);
+		r = drm_sched_entity_init(&ctx->rings[i].entity,
+					  &rq, 1, &ctx->guilty);
 		if (r)
 			goto failed;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6a3fead5c1f0..11a12483c995 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1918,8 +1918,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 
 		ring = adev->mman.buffer_funcs_ring;
 		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-		r = drm_sched_entity_init(&ring->sched, &adev->mman.entity,
-					  rq, NULL);
+		r = drm_sched_entity_init(&adev->mman.entity, &rq, 1, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up TTM BO move entity (%d)\n",
 				  r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 3e70eb61a960..a6c2cace4b9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -266,8 +266,8 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 
 		ring = &adev->uvd.inst[j].ring;
 		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity,
-					  rq, NULL);
+		r = drm_sched_entity_init(&adev->uvd.inst[j].entity, &rq,
+					  1, NULL);
 		if (r != 0) {
 			DRM_ERROR("Failed setting up UVD(%d) run queue.\n", j);
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 6ae1ad7e83b3..ffb0fcc9707e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -190,8 +190,7 @@ int amdgpu_vce_sw_init(struct amdgpu_device *adev, unsigned long size)
 
 	ring = &adev->vce.ring[0];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-	r = drm_sched_entity_init(&ring->sched, &adev->vce.entity,
-				  rq, NULL);
+	r = drm_sched_entity_init(&adev->vce.entity, &rq, 1, NULL);
 	if (r != 0) {
 		DRM_ERROR("Failed setting up VCE run queue.\n");
 		return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 0fd0a718763b..484e2c19c027 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2564,8 +2564,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
 	ring_instance %= adev->vm_manager.vm_pte_num_rings;
 	ring = adev->vm_manager.vm_pte_rings[ring_instance];
 	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_KERNEL];
-	r = drm_sched_entity_init(&ring->sched, &vm->entity,
-				  rq, NULL);
+	r = drm_sched_entity_init(&vm->entity, &rq, 1, NULL);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 2623f249cb7a..1c118c02e8cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -430,8 +430,8 @@ static int uvd_v6_0_sw_init(void *handle)
 		struct drm_sched_rq *rq;
 		ring = &adev->uvd.inst->ring_enc[0];
 		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst->entity_enc,
-					  rq, NULL);
+		r = drm_sched_entity_init(&adev->uvd.inst->entity_enc,
+					  &rq, 1, NULL);
 		if (r) {
 			DRM_ERROR("Failed setting up UVD ENC run queue.\n");
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index ce360ad16856..d48bc3393545 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -432,8 +432,8 @@ static int uvd_v7_0_sw_init(void *handle)
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
 		ring = &adev->uvd.inst[j].ring_enc[0];
 		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&ring->sched, &adev->uvd.inst[j].entity_enc,
-					  rq, NULL);
+		r = drm_sched_entity_init(&adev->uvd.inst[j].entity_enc,
+					  &rq, 1, NULL);
 		if (r) {
 			DRM_ERROR("(%d)Failed setting up UVD ENC run queue.\n", j);
 			return r;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index 45bfdf4cc107..36414ba56b22 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -49,12 +49,12 @@ static int etnaviv_open(struct drm_device *dev, struct drm_file *file)
 
 	for (i = 0; i < ETNA_MAX_PIPES; i++) {
 		struct etnaviv_gpu *gpu = priv->gpu[i];
+		struct drm_sched_rq *rq;
 
 		if (gpu) {
-			drm_sched_entity_init(&gpu->sched,
-				&ctx->sched_entity[i],
-				&gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
-				NULL);
+			rq = &gpu->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+			drm_sched_entity_init(&ctx->sched_entity[i],
+					      &rq, 1, NULL);
 			}
 	}
 
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 429b1328653a..16bf446aa6b3 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -162,26 +162,30 @@ drm_sched_rq_select_entity(struct drm_sched_rq *rq)
  * drm_sched_entity_init - Init a context entity used by scheduler when
  * submit to HW ring.
  *
- * @sched: scheduler instance
  * @entity: scheduler entity to init
- * @rq: the run queue this entity belongs
+ * @rq_list: the list of run queue on which jobs from this
+ *           entity can be submitted
+ * @num_rq_list: number of run queue in rq_list
  * @guilty: atomic_t set to 1 when a job on this queue
  *          is found to be guilty causing a timeout
  *
+ * Note: the rq_list should have atleast one element to schedule
+ *       the entity
+ *
  * Returns 0 on success or a negative error code on failure.
 */
-int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
-			  struct drm_sched_entity *entity,
-			  struct drm_sched_rq *rq,
+int drm_sched_entity_init(struct drm_sched_entity *entity,
+			  struct drm_sched_rq **rq_list,
+			  unsigned int num_rq_list,
 			  atomic_t *guilty)
 {
-	if (!(sched && entity && rq))
+	if (!(entity && rq_list && num_rq_list > 0 && rq_list[0]))
 		return -EINVAL;
 
 	memset(entity, 0, sizeof(struct drm_sched_entity));
 	INIT_LIST_HEAD(&entity->list);
-	entity->rq = rq;
-	entity->sched = sched;
+	entity->rq = rq_list[0];
+	entity->sched = rq_list[0]->sched;
 	entity->guilty = guilty;
 	entity->last_scheduled = NULL;
 
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index 567f7d46d912..1dceba2b42fd 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -123,6 +123,7 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 {
 	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv;
+	struct drm_sched_rq *rq;
 	int i;
 
 	v3d_priv = kzalloc(sizeof(*v3d_priv), GFP_KERNEL);
@@ -132,10 +133,8 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 	v3d_priv->v3d = v3d;
 
 	for (i = 0; i < V3D_MAX_QUEUES; i++) {
-		drm_sched_entity_init(&v3d->queue[i].sched,
-				      &v3d_priv->sched_entity[i],
-				      &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL],
-				      NULL);
+		rq = &v3d->queue[i].sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+		drm_sched_entity_init(&v3d_priv->sched_entity[i], &rq, 1, NULL);
 	}
 
 	file->driver_priv = v3d_priv;
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 43e93d6077cf..2205e89722f6 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -282,9 +282,9 @@ int drm_sched_init(struct drm_gpu_scheduler *sched,
 		   const char *name);
 void drm_sched_fini(struct drm_gpu_scheduler *sched);
 
-int drm_sched_entity_init(struct drm_gpu_scheduler *sched,
-			  struct drm_sched_entity *entity,
-			  struct drm_sched_rq *rq,
+int drm_sched_entity_init(struct drm_sched_entity *entity,
+			  struct drm_sched_rq **rq_list,
+			  unsigned int num_rq_list,
 			  atomic_t *guilty);
 long drm_sched_entity_flush(struct drm_gpu_scheduler *sched,
 			   struct drm_sched_entity *entity, long timeout);
-- 
cgit v1.2.3


From ddc21af4d0f37f42b33c54cb69b215997fe5b082 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Wed, 11 Jul 2018 12:06:31 +0200
Subject: drm/amdgpu: Keep track of amount of pinned CPU visible VRAM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of CPU invisible VRAM. Preparation for the following, no
functional change intended.

v2:
* Also change amdgpu_vram_mgr_bo_invisible_size to
  amdgpu_vram_mgr_bo_visible_size, allowing further simplification
  (Christian König)

Cc: stable@vger.kernel.org
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h          |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c      |  5 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c   |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h      |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 20 ++++++++------------
 5 files changed, 14 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index b38c170fb95c..51b16de008bb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1590,7 +1590,7 @@ struct amdgpu_device {
 
 	/* tracking pinned memory */
 	u64 vram_pin_size;
-	u64 invisible_pin_size;
+	u64 visible_pin_size;
 	u64 gart_pin_size;
 
 	/* amdkfd interface */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 2060f208e60b..c00bd9591dad 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -504,7 +504,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		vram_gtt.vram_size = adev->gmc.real_vram_size;
 		vram_gtt.vram_size -= adev->vram_pin_size;
 		vram_gtt.vram_cpu_accessible_size = adev->gmc.visible_vram_size;
-		vram_gtt.vram_cpu_accessible_size -= (adev->vram_pin_size - adev->invisible_pin_size);
+		vram_gtt.vram_cpu_accessible_size -= adev->visible_pin_size;
 		vram_gtt.gtt_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		vram_gtt.gtt_size *= PAGE_SIZE;
 		vram_gtt.gtt_size -= adev->gart_pin_size;
@@ -525,8 +525,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		mem.cpu_accessible_vram.total_heap_size =
 			adev->gmc.visible_vram_size;
 		mem.cpu_accessible_vram.usable_heap_size =
-			adev->gmc.visible_vram_size -
-			(adev->vram_pin_size - adev->invisible_pin_size);
+			adev->gmc.visible_vram_size - adev->visible_pin_size;
 		mem.cpu_accessible_vram.heap_usage =
 			amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 		mem.cpu_accessible_vram.max_allocation =
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 9ee678d63890..f0239feceab4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -917,7 +917,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
 		adev->vram_pin_size += amdgpu_bo_size(bo);
-		adev->invisible_pin_size += amdgpu_vram_mgr_bo_invisible_size(bo);
+		adev->visible_pin_size += amdgpu_vram_mgr_bo_visible_size(bo);
 	} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
 		adev->gart_pin_size += amdgpu_bo_size(bo);
 	}
@@ -969,7 +969,7 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 
 	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
 		adev->vram_pin_size -= amdgpu_bo_size(bo);
-		adev->invisible_pin_size -= amdgpu_vram_mgr_bo_invisible_size(bo);
+		adev->visible_pin_size -= amdgpu_vram_mgr_bo_visible_size(bo);
 	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
 		adev->gart_pin_size -= amdgpu_bo_size(bo);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
index e5da4654b630..8b3cc6687769 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.h
@@ -73,7 +73,7 @@ bool amdgpu_gtt_mgr_has_gart_addr(struct ttm_mem_reg *mem);
 uint64_t amdgpu_gtt_mgr_usage(struct ttm_mem_type_manager *man);
 int amdgpu_gtt_mgr_recover(struct ttm_mem_type_manager *man);
 
-u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo);
+u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo);
 uint64_t amdgpu_vram_mgr_usage(struct ttm_mem_type_manager *man);
 uint64_t amdgpu_vram_mgr_vis_usage(struct ttm_mem_type_manager *man);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index f7a4bd5885a3..9cfa8a9ada92 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -97,33 +97,29 @@ static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
 }
 
 /**
- * amdgpu_vram_mgr_bo_invisible_size - CPU invisible BO size
+ * amdgpu_vram_mgr_bo_visible_size - CPU visible BO size
  *
  * @bo: &amdgpu_bo buffer object (must be in VRAM)
  *
  * Returns:
- * How much of the given &amdgpu_bo buffer object lies in CPU invisible VRAM.
+ * How much of the given &amdgpu_bo buffer object lies in CPU visible VRAM.
  */
-u64 amdgpu_vram_mgr_bo_invisible_size(struct amdgpu_bo *bo)
+u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	struct ttm_mem_reg *mem = &bo->tbo.mem;
 	struct drm_mm_node *nodes = mem->mm_node;
 	unsigned pages = mem->num_pages;
-	u64 usage = 0;
+	u64 usage;
 
 	if (amdgpu_gmc_vram_full_visible(&adev->gmc))
-		return 0;
+		return amdgpu_bo_size(bo);
 
 	if (mem->start >= adev->gmc.visible_vram_size >> PAGE_SHIFT)
-		return amdgpu_bo_size(bo);
+		return 0;
 
-	while (nodes && pages) {
-		usage += nodes->size << PAGE_SHIFT;
-		usage -= amdgpu_vram_mgr_vis_size(adev, nodes);
-		pages -= nodes->size;
-		++nodes;
-	}
+	for (usage = 0; nodes && pages; pages -= nodes->size, nodes++)
+		usage += amdgpu_vram_mgr_vis_size(adev, nodes);
 
 	return usage;
 }
-- 
cgit v1.2.3


From a5ccfe5c20740f2fbf00291490cdf8d2373ec255 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Wed, 11 Jul 2018 12:00:40 +0200
Subject: drm/amdgpu: Make pin_size values atomic
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Concurrent execution of the non-atomic arithmetic could result in
completely bogus values.

v2:
* Rebased on v2 of the previous patch

Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/106872
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c     |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    | 22 +++++++++++-----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 14 ++++++++------
 4 files changed, 23 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 51b16de008bb..53435da158c2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1589,9 +1589,9 @@ struct amdgpu_device {
 	DECLARE_HASHTABLE(mn_hash, 7);
 
 	/* tracking pinned memory */
-	u64 vram_pin_size;
-	u64 visible_pin_size;
-	u64 gart_pin_size;
+	atomic64_t vram_pin_size;
+	atomic64_t visible_pin_size;
+	atomic64_t gart_pin_size;
 
 	/* amdkfd interface */
 	struct kfd_dev          *kfd;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 9881a1e55df3..5a2a5ba29f9a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -262,7 +262,7 @@ static void amdgpu_cs_get_threshold_for_moves(struct amdgpu_device *adev,
 		return;
 	}
 
-	total_vram = adev->gmc.real_vram_size - adev->vram_pin_size;
+	total_vram = adev->gmc.real_vram_size - atomic64_read(&adev->vram_pin_size);
 	used_vram = amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 	free_vram = used_vram >= total_vram ? 0 : total_vram - used_vram;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index c00bd9591dad..207f238649b4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -501,13 +501,13 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	case AMDGPU_INFO_VRAM_GTT: {
 		struct drm_amdgpu_info_vram_gtt vram_gtt;
 
-		vram_gtt.vram_size = adev->gmc.real_vram_size;
-		vram_gtt.vram_size -= adev->vram_pin_size;
-		vram_gtt.vram_cpu_accessible_size = adev->gmc.visible_vram_size;
-		vram_gtt.vram_cpu_accessible_size -= adev->visible_pin_size;
+		vram_gtt.vram_size = adev->gmc.real_vram_size -
+			atomic64_read(&adev->vram_pin_size);
+		vram_gtt.vram_cpu_accessible_size = adev->gmc.visible_vram_size -
+			atomic64_read(&adev->visible_pin_size);
 		vram_gtt.gtt_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		vram_gtt.gtt_size *= PAGE_SIZE;
-		vram_gtt.gtt_size -= adev->gart_pin_size;
+		vram_gtt.gtt_size -= atomic64_read(&adev->gart_pin_size);
 		return copy_to_user(out, &vram_gtt,
 				    min((size_t)size, sizeof(vram_gtt))) ? -EFAULT : 0;
 	}
@@ -516,16 +516,16 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		memset(&mem, 0, sizeof(mem));
 		mem.vram.total_heap_size = adev->gmc.real_vram_size;
-		mem.vram.usable_heap_size =
-			adev->gmc.real_vram_size - adev->vram_pin_size;
+		mem.vram.usable_heap_size = adev->gmc.real_vram_size -
+			atomic64_read(&adev->vram_pin_size);
 		mem.vram.heap_usage =
 			amdgpu_vram_mgr_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 		mem.vram.max_allocation = mem.vram.usable_heap_size * 3 / 4;
 
 		mem.cpu_accessible_vram.total_heap_size =
 			adev->gmc.visible_vram_size;
-		mem.cpu_accessible_vram.usable_heap_size =
-			adev->gmc.visible_vram_size - adev->visible_pin_size;
+		mem.cpu_accessible_vram.usable_heap_size = adev->gmc.visible_vram_size -
+			atomic64_read(&adev->visible_pin_size);
 		mem.cpu_accessible_vram.heap_usage =
 			amdgpu_vram_mgr_vis_usage(&adev->mman.bdev.man[TTM_PL_VRAM]);
 		mem.cpu_accessible_vram.max_allocation =
@@ -533,8 +533,8 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 
 		mem.gtt.total_heap_size = adev->mman.bdev.man[TTM_PL_TT].size;
 		mem.gtt.total_heap_size *= PAGE_SIZE;
-		mem.gtt.usable_heap_size = mem.gtt.total_heap_size
-			- adev->gart_pin_size;
+		mem.gtt.usable_heap_size = mem.gtt.total_heap_size -
+			atomic64_read(&adev->gart_pin_size);
 		mem.gtt.heap_usage =
 			amdgpu_gtt_mgr_usage(&adev->mman.bdev.man[TTM_PL_TT]);
 		mem.gtt.max_allocation = mem.gtt.usable_heap_size * 3 / 4;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index f0239feceab4..1fd83ed175fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -916,10 +916,11 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 
 	domain = amdgpu_mem_type_to_domain(bo->tbo.mem.mem_type);
 	if (domain == AMDGPU_GEM_DOMAIN_VRAM) {
-		adev->vram_pin_size += amdgpu_bo_size(bo);
-		adev->visible_pin_size += amdgpu_vram_mgr_bo_visible_size(bo);
+		atomic64_add(amdgpu_bo_size(bo), &adev->vram_pin_size);
+		atomic64_add(amdgpu_vram_mgr_bo_visible_size(bo),
+			     &adev->visible_pin_size);
 	} else if (domain == AMDGPU_GEM_DOMAIN_GTT) {
-		adev->gart_pin_size += amdgpu_bo_size(bo);
+		atomic64_add(amdgpu_bo_size(bo), &adev->gart_pin_size);
 	}
 
 error:
@@ -968,10 +969,11 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 		return 0;
 
 	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
-		adev->vram_pin_size -= amdgpu_bo_size(bo);
-		adev->visible_pin_size -= amdgpu_vram_mgr_bo_visible_size(bo);
+		atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size);
+		atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo),
+			     &adev->visible_pin_size);
 	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
-		adev->gart_pin_size -= amdgpu_bo_size(bo);
+		atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size);
 	}
 
 	for (i = 0; i < bo->placement.num_placement; i++) {
-- 
cgit v1.2.3


From 15e6b76880e65be24250e30986084b5569b7a06f Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Wed, 11 Jul 2018 12:42:55 +0200
Subject: drm/amdgpu: Warn and update pin_size values when destroying a pinned
 BO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This shouldn't happen, but if it does, we'll get a backtrace of the
caller, and update the pin_size values as needed.

v2:
* Check bo->pin_count instead of placement flags (Christian König)

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 32 +++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 1fd83ed175fa..b12526ce1a9d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -63,11 +63,35 @@ static bool amdgpu_need_backup(struct amdgpu_device *adev)
 	return true;
 }
 
+/**
+ * amdgpu_bo_subtract_pin_size - Remove BO from pin_size accounting
+ *
+ * @bo: &amdgpu_bo buffer object
+ *
+ * This function is called when a BO stops being pinned, and updates the
+ * &amdgpu_device pin_size values accordingly.
+ */
+static void amdgpu_bo_subtract_pin_size(struct amdgpu_bo *bo)
+{
+	struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
+
+	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
+		atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size);
+		atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo),
+			     &adev->visible_pin_size);
+	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
+		atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size);
+	}
+}
+
 static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
 	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
 
+	if (WARN_ON_ONCE(bo->pin_count > 0))
+		amdgpu_bo_subtract_pin_size(bo);
+
 	if (bo->kfd_bo)
 		amdgpu_amdkfd_unreserve_system_memory_limit(bo);
 
@@ -968,13 +992,7 @@ int amdgpu_bo_unpin(struct amdgpu_bo *bo)
 	if (bo->pin_count)
 		return 0;
 
-	if (bo->tbo.mem.mem_type == TTM_PL_VRAM) {
-		atomic64_sub(amdgpu_bo_size(bo), &adev->vram_pin_size);
-		atomic64_sub(amdgpu_vram_mgr_bo_visible_size(bo),
-			     &adev->visible_pin_size);
-	} else if (bo->tbo.mem.mem_type == TTM_PL_TT) {
-		atomic64_sub(amdgpu_bo_size(bo), &adev->gart_pin_size);
-	}
+	amdgpu_bo_subtract_pin_size(bo);
 
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		bo->placements[i].lpfn = 0;
-- 
cgit v1.2.3


From 37b5fcfde879652bac7fc4b18c5f242f2544e9ea Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Fri, 6 Jul 2018 10:54:18 -0400
Subject: Revert "drm/amd/display: Don't return ddc result and read_bytes in
 same return value"

This reverts commit 8a61bc085ffab3071c59efcbeff4044c034e7490.

Need to revert "make dm_dp_aux_transfer return payload bytes instead of
size", which this commit is based on. That commit was problematic on
other OSes. The real solution is to leave all the error checking to DRM
and don't do it in DC, which is addressed by "Return aux replies
directly to DRM" later in this patchset.

v2: Add reason for revert.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c  | 20 ++++++++------------
 drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c    | 10 +++-------
 drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h     |  5 ++---
 3 files changed, 13 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index 4304d9e408b8..ace9ad578ca0 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -83,22 +83,21 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
 		I2C_MOT_TRUE : I2C_MOT_FALSE;
 	enum ddc_result res;
-	uint32_t read_bytes = msg->size;
+	ssize_t read_bytes;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
 
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_READ:
-		res = dal_ddc_service_read_dpcd_data(
+		read_bytes = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				false,
 				I2C_MOT_UNDEF,
 				msg->address,
 				msg->buffer,
-				msg->size,
-				&read_bytes);
-		break;
+				msg->size);
+		return read_bytes;
 	case DP_AUX_NATIVE_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
@@ -109,15 +108,14 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				msg->size);
 		break;
 	case DP_AUX_I2C_READ:
-		res = dal_ddc_service_read_dpcd_data(
+		read_bytes = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				true,
 				mot,
 				msg->address,
 				msg->buffer,
-				msg->size,
-				&read_bytes);
-		break;
+				msg->size);
+		return read_bytes;
 	case DP_AUX_I2C_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
@@ -139,9 +137,7 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 		 r == DDC_RESULT_SUCESSFULL);
 #endif
 
-	if (res != DDC_RESULT_SUCESSFULL)
-		return -EIO;
-	return read_bytes;
+	return msg->size;
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index ae48d603ebd6..49c2face1e7a 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -629,14 +629,13 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
+ssize_t dal_ddc_service_read_dpcd_data(
 	struct ddc_service *ddc,
 	bool i2c,
 	enum i2c_mot_mode mot,
 	uint32_t address,
 	uint8_t *data,
-	uint32_t len,
-	uint32_t *read)
+	uint32_t len)
 {
 	struct aux_payload read_payload = {
 		.i2c_over_aux = i2c,
@@ -653,8 +652,6 @@ enum ddc_result dal_ddc_service_read_dpcd_data(
 		.mot = mot
 	};
 
-	*read = 0;
-
 	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
 		BREAK_TO_DEBUGGER();
 		return DDC_RESULT_FAILED_INVALID_OPERATION;
@@ -664,8 +661,7 @@ enum ddc_result dal_ddc_service_read_dpcd_data(
 		ddc->ctx->i2caux,
 		ddc->ddc_pin,
 		&command)) {
-		*read = command.payloads->length;
-		return DDC_RESULT_SUCESSFULL;
+		return (ssize_t)command.payloads->length;
 	}
 
 	return DDC_RESULT_FAILED_OPERATION;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 30b3a08b91be..090b7a8dd67b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -102,14 +102,13 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
+ssize_t dal_ddc_service_read_dpcd_data(
 		struct ddc_service *ddc,
 		bool i2c,
 		enum i2c_mot_mode mot,
 		uint32_t address,
 		uint8_t *data,
-		uint32_t len,
-		uint32_t *read);
+		uint32_t len);
 
 enum ddc_result dal_ddc_service_write_dpcd_data(
 		struct ddc_service *ddc,
-- 
cgit v1.2.3


From 013fc06ea4260574755541773ece1a76a8017de6 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Fri, 6 Jul 2018 10:54:33 -0400
Subject: Revert "drm/amd/display: make dm_dp_aux_transfer return payload bytes
 instead of size"

This reverts commit cc195141133ac3e767d930bedd8294ceebf1f10b.

This commit was problematic on other OSes. The real solution is to
leave all the error checking to DRM and don't do it in DC, which is
addressed by "Return aux replies directly to DRM" later in this patchset.

v2: Add reason for revert.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c   |  9 ++++-----
 drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c         |  7 +++----
 drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c        | 15 +++++++++++++--
 drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c            |  1 -
 drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h          |  2 +-
 5 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index ace9ad578ca0..c74105758815 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -83,21 +83,20 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 	enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
 		I2C_MOT_TRUE : I2C_MOT_FALSE;
 	enum ddc_result res;
-	ssize_t read_bytes;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
 
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_READ:
-		read_bytes = dal_ddc_service_read_dpcd_data(
+		res = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				false,
 				I2C_MOT_UNDEF,
 				msg->address,
 				msg->buffer,
 				msg->size);
-		return read_bytes;
+		break;
 	case DP_AUX_NATIVE_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
@@ -108,14 +107,14 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				msg->size);
 		break;
 	case DP_AUX_I2C_READ:
-		read_bytes = dal_ddc_service_read_dpcd_data(
+		res = dal_ddc_service_read_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
 				true,
 				mot,
 				msg->address,
 				msg->buffer,
 				msg->size);
-		return read_bytes;
+		break;
 	case DP_AUX_I2C_WRITE:
 		res = dal_ddc_service_write_dpcd_data(
 				TO_DM_AUX(aux)->ddc_service,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 49c2face1e7a..d5294798b0a5 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -629,7 +629,7 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
 	struct ddc_service *ddc,
 	bool i2c,
 	enum i2c_mot_mode mot,
@@ -660,9 +660,8 @@ ssize_t dal_ddc_service_read_dpcd_data(
 	if (dal_i2caux_submit_aux_command(
 		ddc->ctx->i2caux,
 		ddc->ddc_pin,
-		&command)) {
-		return (ssize_t)command.payloads->length;
-	}
+		&command))
+		return DDC_RESULT_SUCESSFULL;
 
 	return DDC_RESULT_FAILED_OPERATION;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
index 1d7309611978..0afd2fa57bbe 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.c
@@ -128,8 +128,20 @@ static void process_read_reply(
 			ctx->status =
 				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
 			ctx->operation_succeeded = false;
+		} else if (ctx->returned_byte < ctx->current_read_length) {
+			ctx->current_read_length -= ctx->returned_byte;
+
+			ctx->offset += ctx->returned_byte;
+
+			++ctx->invalid_reply_retry_aux_on_ack;
+
+			if (ctx->invalid_reply_retry_aux_on_ack >
+				AUX_INVALID_REPLY_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+				ctx->operation_succeeded = false;
+			}
 		} else {
-			ctx->current_read_length = ctx->returned_byte;
 			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
 			ctx->transaction_complete = true;
 			ctx->operation_succeeded = true;
@@ -290,7 +302,6 @@ static bool read_command(
 				ctx.operation_succeeded);
 	}
 
-	request->payload.length = ctx.reply.length;
 	return ctx.operation_succeeded;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
index 14dc8c94d862..9b0bcc6b769b 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
@@ -254,7 +254,6 @@ bool dal_i2caux_submit_aux_command(
 			break;
 		}
 
-		cmd->payloads->length = request.payload.length;
 		++index_of_payload;
 	}
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 090b7a8dd67b..0bf73b742f1f 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -102,7 +102,7 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
-ssize_t dal_ddc_service_read_dpcd_data(
+enum ddc_result dal_ddc_service_read_dpcd_data(
 		struct ddc_service *ddc,
 		bool i2c,
 		enum i2c_mot_mode mot,
-- 
cgit v1.2.3


From a9962fb8e53aad86bc5c4147ecc209a214345f56 Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Fri, 8 Jun 2018 15:01:59 -0400
Subject: drm/amd/display: Separate HUBP surface size and rotation/mirror
 programming

Separate HUBP surface size and rotation/mirror programming so that
HUBP revision without mirror/rotation do not access those register
fields.

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c | 23 +++++++++++++++--------
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h | 13 ++++++++-----
 2 files changed, 23 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index a281bed9b413..ec8e833a07bd 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -152,16 +152,14 @@ void hubp1_program_tiling(
 			PIPE_ALIGNED, info->gfx9.pipe_aligned);
 }
 
-void hubp1_program_size_and_rotation(
+void hubp1_program_size(
 	struct hubp *hubp,
-	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
-	struct dc_plane_dcc_param *dcc,
-	bool horizontal_mirror)
+	struct dc_plane_dcc_param *dcc)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	uint32_t pitch, meta_pitch, pitch_c, meta_pitch_c, mirror;
+	uint32_t pitch, meta_pitch, pitch_c, meta_pitch_c;
 
 	/* Program data and meta surface pitch (calculation from addrlib)
 	 * 444 or 420 luma
@@ -192,13 +190,22 @@ void hubp1_program_size_and_rotation(
 	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
 		REG_UPDATE_2(DCSURF_SURFACE_PITCH_C,
 			PITCH_C, pitch_c, META_PITCH_C, meta_pitch_c);
+}
+
+void hubp1_program_rotation(
+	struct hubp *hubp,
+	enum dc_rotation_angle rotation,
+	bool horizontal_mirror)
+{
+	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
+	uint32_t mirror;
+
 
 	if (horizontal_mirror)
 		mirror = 1;
 	else
 		mirror = 0;
 
-
 	/* Program rotation angle and horz mirror - no mirror */
 	if (rotation == ROTATION_ANGLE_0)
 		REG_UPDATE_2(DCSURF_SURFACE_CONFIG,
@@ -481,8 +488,8 @@ void hubp1_program_surface_config(
 {
 	hubp1_dcc_control(hubp, dcc->enable, dcc->grph.independent_64b_blks);
 	hubp1_program_tiling(hubp, tiling_info, format);
-	hubp1_program_size_and_rotation(
-			hubp, rotation, format, plane_size, dcc, horizontal_mirror);
+	hubp1_program_size(hubp, format, plane_size, dcc);
+	hubp1_program_rotation(hubp, rotation, horizontal_mirror);
 	hubp1_program_pixel_format(hubp, format);
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index d901d5092969..f689feace82d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -268,8 +268,6 @@
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH, META_PITCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, PITCH_C, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_SURFACE_PITCH_C, META_PITCH_C, mask_sh),\
-	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
-	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
 	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, SURFACE_PIXEL_FORMAT, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_TYPE, mask_sh),\
 	HUBP_SF(HUBPREQ0_DCSURF_FLIP_CONTROL, SURFACE_FLIP_PENDING, mask_sh),\
@@ -388,6 +386,8 @@
 #define HUBP_MASK_SH_LIST_DCN10(mask_sh)\
 	HUBP_MASK_SH_LIST_DCN(mask_sh),\
 	HUBP_MASK_SH_LIST_DCN_VM(mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, ROTATION_ANGLE, mask_sh),\
+	HUBP_SF(HUBP0_DCSURF_SURFACE_CONFIG, H_MIRROR_EN, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, DST_Y_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS, VRATIO_PREFETCH, mask_sh),\
 	HUBP_SF(HUBPREQ0_PREFETCH_SETTINS_C, VRATIO_PREFETCH_C, mask_sh),\
@@ -679,12 +679,15 @@ void hubp1_program_pixel_format(
 	struct hubp *hubp,
 	enum surface_pixel_format format);
 
-void hubp1_program_size_and_rotation(
+void hubp1_program_size(
 	struct hubp *hubp,
-	enum dc_rotation_angle rotation,
 	enum surface_pixel_format format,
 	const union plane_size *plane_size,
-	struct dc_plane_dcc_param *dcc,
+	struct dc_plane_dcc_param *dcc);
+
+void hubp1_program_rotation(
+	struct hubp *hubp,
+	enum dc_rotation_angle rotation,
 	bool horizontal_mirror);
 
 void hubp1_program_tiling(
-- 
cgit v1.2.3


From 91f191c74e8da29360109acb97a20240bedbc355 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Thu, 14 Jun 2018 16:06:10 -0400
Subject: drm/amd/display: Add avoid_vbios_exec_table debug bit

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 0cb7e10d2505..59985baac11e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -249,6 +249,7 @@ struct dc_debug {
 	bool always_use_regamma;
 	bool p010_mpo_support;
 	bool recovery_enabled;
+	bool avoid_vbios_exec_table;
 
 };
 struct dc_state;
-- 
cgit v1.2.3


From 0a14544661fad1606cc96aece30b2950fd9c4c81 Mon Sep 17 00:00:00 2001
From: Eric Yang <Eric.Yang2@amd.com>
Date: Tue, 12 Jun 2018 18:37:12 -0400
Subject: drm/amd/display: support access ddc for mst branch

[Why]
Megachip dockings accesses ddc line through display driver when
installing FW. Previously, we would fail every transaction because
link attached to mst branch did not have their ddc transaction type
set.

[How]
Set ddc transaction type when mst branch is connected.

Signed-off-by: Eric Yang <Eric.Yang2@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index fa56c0fc02bf..a4180ba63d82 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -498,6 +498,10 @@ static bool detect_dp(
 			sink_caps->signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
 			link->type = dc_connection_mst_branch;
 
+			dal_ddc_service_set_transaction_type(
+							link->ddc,
+							sink_caps->transaction_type);
+
 			/*
 			 * This call will initiate MST topology discovery. Which
 			 * will detect MST ports and add new DRM connector DRM
-- 
cgit v1.2.3


From 1811a51f6a04adbaa4dba1e7bfe13201c04b9f94 Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Thu, 14 Jun 2018 15:08:58 -0400
Subject: drm/amd/display: Implement cursor multiplier

DCN allows cursor multiplier when blending FP16 surface.

Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h      |  1 +
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c | 15 +++++++++++++++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h | 12 ++++++++----
 3 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 14afbc5c0a62..00afd07a852e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -490,6 +490,7 @@ struct dc_cursor_attributes {
 	uint32_t height;
 
 	enum dc_cursor_color_format color_format;
+	uint32_t sdr_white_level; // for boosting (SDR) cursor in HDR mode
 
 	/* In case we support HW Cursor rotation in the future */
 	enum dc_rotation_angle rotation_angle;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index ec8e833a07bd..9eb60a013f4c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -27,6 +27,7 @@
 #include "reg_helper.h"
 #include "basics/conversion.h"
 #include "dcn10_hubp.h"
+#include "custom_float.h"
 
 #define REG(reg)\
 	hubp1->hubp_regs->reg
@@ -1038,6 +1039,18 @@ void hubp1_cursor_set_attributes(
 	enum cursor_pitch hw_pitch = hubp1_get_cursor_pitch(attr->pitch);
 	enum cursor_lines_per_chunk lpc = hubp1_get_lines_per_chunk(
 			attr->width, attr->color_format);
+	struct fixed31_32 multiplier;
+	uint32_t hw_mult = 0x3c00; // 1.0 default multiplier
+	struct custom_float_format fmt;
+
+	fmt.exponenta_bits = 5;
+	fmt.mantissa_bits = 10;
+	fmt.sign = true;
+
+	if (attr->sdr_white_level > 80) {
+		multiplier = dc_fixpt_from_fraction(attr->sdr_white_level, 80);
+		convert_to_custom_float_format(multiplier, &fmt, &hw_mult);
+	}
 
 	hubp->curs_attr = *attr;
 
@@ -1060,6 +1073,8 @@ void hubp1_cursor_set_attributes(
 			CURSOR0_DST_Y_OFFSET, 0,
 			 /* used to shift the cursor chunk request deadline */
 			CURSOR0_CHUNK_HDL_ADJUST, 3);
+
+	REG_UPDATE(CURSOR0_FP_SCALE_BIAS, CUR0_FP_SCALE, hw_mult);
 }
 
 void hubp1_cursor_set_position(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index f689feace82d..9991da50bf29 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -133,7 +133,8 @@
 	SRI(CURSOR_CONTROL, CURSOR, id), \
 	SRI(CURSOR_POSITION, CURSOR, id), \
 	SRI(CURSOR_HOT_SPOT, CURSOR, id), \
-	SRI(CURSOR_DST_OFFSET, CURSOR, id)
+	SRI(CURSOR_DST_OFFSET, CURSOR, id), \
+	SRI(CURSOR0_FP_SCALE_BIAS, CNVC_CUR, id)
 
 #define HUBP_COMMON_REG_VARIABLE_LIST \
 	uint32_t DCHUBP_CNTL; \
@@ -241,7 +242,8 @@
 	uint32_t CURSOR_POSITION; \
 	uint32_t CURSOR_HOT_SPOT; \
 	uint32_t CURSOR_DST_OFFSET; \
-	uint32_t HUBP_CLK_CNTL
+	uint32_t HUBP_CLK_CNTL; \
+	uint32_t CURSOR0_FP_SCALE_BIAS
 
 #define HUBP_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
@@ -424,7 +426,8 @@
 	HUBP_SF(CURSOR0_CURSOR_POSITION, CURSOR_Y_POSITION, mask_sh), \
 	HUBP_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_X, mask_sh), \
 	HUBP_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_Y, mask_sh), \
-	HUBP_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh)
+	HUBP_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh), \
+	HUBP_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_SCALE, mask_sh)
 
 #define DCN_HUBP_REG_FIELD_LIST(type) \
 	type HUBP_BLANK_EN;\
@@ -615,7 +618,8 @@
 	type CURSOR_HOT_SPOT_X; \
 	type CURSOR_HOT_SPOT_Y; \
 	type CURSOR_DST_X_OFFSET; \
-	type OUTPUT_FP
+	type OUTPUT_FP; \
+	type CUR0_FP_SCALE
 
 struct dcn_mi_registers {
 	HUBP_COMMON_REG_VARIABLE_LIST;
-- 
cgit v1.2.3


From 40dd6bd376a4b8617d7cfb1402bafd84bbd79bbd Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Fri, 15 Jun 2018 09:28:34 -0400
Subject: drm/amd/display: Linux Set/Read link rate and lane count through
 debugfs

expose dc function to be called by linux dm

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Sun peng Li <Sunpeng.Li@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc.c | 65 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/dc_link.h | 17 +++++++++
 2 files changed, 82 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 2a785bbf2b8f..815656a5b6bd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -384,6 +384,71 @@ void dc_stream_set_static_screen_events(struct dc *dc,
 	dc->hwss.set_static_screen_control(pipes_affected, num_pipes_affected, events);
 }
 
+void dc_link_set_drive_settings(struct dc *dc,
+				struct link_training_settings *lt_settings,
+				const struct dc_link *link)
+{
+
+	int i;
+
+	for (i = 0; i < dc->link_count; i++) {
+		if (dc->links[i] == link)
+			break;
+	}
+
+	if (i >= dc->link_count)
+		ASSERT_CRITICAL(false);
+
+	dc_link_dp_set_drive_settings(dc->links[i], lt_settings);
+}
+
+void dc_link_perform_link_training(struct dc *dc,
+				   struct dc_link_settings *link_setting,
+				   bool skip_video_pattern)
+{
+	int i;
+
+	for (i = 0; i < dc->link_count; i++)
+		dc_link_dp_perform_link_training(
+			dc->links[i],
+			link_setting,
+			skip_video_pattern);
+}
+
+void dc_link_set_preferred_link_settings(struct dc *dc,
+					 struct dc_link_settings *link_setting,
+					 struct dc_link *link)
+{
+	link->preferred_link_setting = *link_setting;
+	dp_retrain_link_dp_test(link, link_setting, false);
+}
+
+void dc_link_enable_hpd(const struct dc_link *link)
+{
+	dc_link_dp_enable_hpd(link);
+}
+
+void dc_link_disable_hpd(const struct dc_link *link)
+{
+	dc_link_dp_disable_hpd(link);
+}
+
+
+void dc_link_set_test_pattern(struct dc_link *link,
+			      enum dp_test_pattern test_pattern,
+			      const struct link_training_settings *p_link_settings,
+			      const unsigned char *p_custom_pattern,
+			      unsigned int cust_pattern_size)
+{
+	if (link != NULL)
+		dc_link_dp_set_test_pattern(
+			link,
+			test_pattern,
+			p_link_settings,
+			p_custom_pattern,
+			cust_pattern_size);
+}
+
 static void destruct(struct dc *dc)
 {
 	dc_release_state(dc->current_state);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 8a716baa1203..83eea42452b5 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -214,6 +214,23 @@ void dc_link_enable_hpd_filter(struct dc_link *link, bool enable);
  * DPCD access interfaces
  */
 
+void dc_link_set_drive_settings(struct dc *dc,
+				struct link_training_settings *lt_settings,
+				const struct dc_link *link);
+void dc_link_perform_link_training(struct dc *dc,
+				   struct dc_link_settings *link_setting,
+				   bool skip_video_pattern);
+void dc_link_set_preferred_link_settings(struct dc *dc,
+					 struct dc_link_settings *link_setting,
+					 struct dc_link *link);
+void dc_link_enable_hpd(const struct dc_link *link);
+void dc_link_disable_hpd(const struct dc_link *link);
+void dc_link_set_test_pattern(struct dc_link *link,
+			enum dp_test_pattern test_pattern,
+			const struct link_training_settings *p_link_settings,
+			const unsigned char *p_custom_pattern,
+			unsigned int cust_pattern_size);
+
 bool dc_submit_i2c(
 		struct dc *dc,
 		uint32_t link_index,
-- 
cgit v1.2.3


From b81e5aa39f66fa159beb449c47220cfb483f0d5f Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Fri, 15 Jun 2018 12:19:00 -0400
Subject: drm/amd/display: Move common GPIO registers into a common define

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
index 9c4a56c738c0..bf40725f982f 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
+++ b/drivers/gpu/drm/amd/display/dc/gpio/ddc_regs.h
@@ -82,13 +82,16 @@
 	DDC_GPIO_I2C_REG_LIST(cd),\
 	.ddc_setup = 0
 
-#define DDC_MASK_SH_LIST(mask_sh) \
+#define DDC_MASK_SH_LIST_COMMON(mask_sh) \
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE, mask_sh),\
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_EDID_DETECT_ENABLE, mask_sh),\
 		SF_DDC(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_EDID_DETECT_MODE, mask_sh),\
 		SF_DDC(DC_GPIO_DDC1_MASK, DC_GPIO_DDC1DATA_PD_EN, mask_sh),\
 		SF_DDC(DC_GPIO_DDC1_MASK, DC_GPIO_DDC1CLK_PD_EN, mask_sh),\
-		SF_DDC(DC_GPIO_DDC1_MASK, AUX_PAD1_MODE, mask_sh),\
+		SF_DDC(DC_GPIO_DDC1_MASK, AUX_PAD1_MODE, mask_sh)
+
+#define DDC_MASK_SH_LIST(mask_sh) \
+		DDC_MASK_SH_LIST_COMMON(mask_sh),\
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SDA_PD_DIS, mask_sh),\
 		SF_DDC(DC_GPIO_I2CPAD_MASK, DC_GPIO_SCL_PD_DIS, mask_sh)
 
-- 
cgit v1.2.3


From 4981a66144fa1e05c54164ea2ef4255451b62d78 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Fri, 15 Jun 2018 17:53:35 -0400
Subject: drm/amd/display: fix bug where we are creating bogus i2c aux

[WHY]
we were using  6 instances based on i2caux_dce110.c

[HOW]
pass in how many instances to ctor

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c | 1 +
 drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c | 6 ++++--
 drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h | 1 +
 drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c | 1 +
 drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c | 1 +
 drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c   | 1 +
 6 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
index e8d3781deaed..8b704ab0471c 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce100/i2caux_dce100.c
@@ -97,6 +97,7 @@ struct i2caux *dal_i2caux_dce100_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce100_aux_regs),
 				    dce100_aux_regs,
 				    dce100_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
index 2a047f8ca0e9..e0557d353818 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
@@ -199,6 +199,7 @@ static const struct dce110_i2c_hw_engine_mask i2c_mask = {
 void dal_i2caux_dce110_construct(
 	struct i2caux_dce110 *i2caux_dce110,
 	struct dc_context *ctx,
+	unsigned int num_i2caux_inst,
 	const struct dce110_aux_registers aux_regs[],
 	const struct dce110_i2c_hw_engine_registers i2c_hw_engine_regs[],
 	const struct dce110_i2c_hw_engine_shift *i2c_shift,
@@ -251,7 +252,7 @@ void dal_i2caux_dce110_construct(
 			dal_i2c_hw_engine_dce110_create(&hw_arg_dce110);
 
 		++i;
-	} while (i < ARRAY_SIZE(hw_ddc_lines));
+	} while (i < num_i2caux_inst);
 
 	/* Create AUX engines for all lines which has assisted HW AUX
 	 * 'i' (loop counter) used as DDC/AUX engine_id */
@@ -272,7 +273,7 @@ void dal_i2caux_dce110_construct(
 			dal_aux_engine_dce110_create(&aux_init_data);
 
 		++i;
-	} while (i < ARRAY_SIZE(hw_aux_lines));
+	} while (i < num_i2caux_inst);
 
 	/*TODO Generic I2C SW and HW*/
 }
@@ -303,6 +304,7 @@ struct i2caux *dal_i2caux_dce110_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce110_aux_regs),
 				    dce110_aux_regs,
 				    i2c_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
index 1b1f71c60ac9..d3d8cc58666a 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.h
@@ -45,6 +45,7 @@ struct i2caux *dal_i2caux_dce110_create(
 void dal_i2caux_dce110_construct(
 	struct i2caux_dce110 *i2caux_dce110,
 	struct dc_context *ctx,
+	unsigned int num_i2caux_inst,
 	const struct dce110_aux_registers *aux_regs,
 	const struct dce110_i2c_hw_engine_registers *i2c_hw_engine_regs,
 	const struct dce110_i2c_hw_engine_shift *i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
index dafc1a727f7f..a9db04738724 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce112/i2caux_dce112.c
@@ -93,6 +93,7 @@ static void construct(
 {
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce112_aux_regs),
 				    dce112_aux_regs,
 				    dce112_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
index 0e7b18260027..6a4f344c1db4 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce120/i2caux_dce120.c
@@ -111,6 +111,7 @@ struct i2caux *dal_i2caux_dce120_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dce120_aux_regs),
 				    dce120_aux_regs,
 				    dce120_hw_engine_regs,
 				    &i2c_shift,
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
index e44a8901f38b..a59c1f50c1e8 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dcn10/i2caux_dcn10.c
@@ -111,6 +111,7 @@ struct i2caux *dal_i2caux_dcn10_create(
 
 	dal_i2caux_dce110_construct(i2caux_dce110,
 				    ctx,
+				    ARRAY_SIZE(dcn10_aux_regs),
 				    dcn10_aux_regs,
 				    dcn10_hw_engine_regs,
 				    &i2c_shift,
-- 
cgit v1.2.3


From 16aecfd4bf546907a6d7d06b4edfdbeea75b1839 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Sat, 16 Jun 2018 19:43:41 -0400
Subject: drm/amd/display: generic indirect register access

add generic indirect register access following our register access pattern

this will make it easier to review code and programming sequence,
with all the complexity hidden in macro

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_helper.c      | 51 +++++++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/inc/reg_helper.h | 46 ++++++++++++++++++++++
 2 files changed, 97 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index bd0fda0ceb91..e68077e65565 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -255,3 +255,54 @@ uint32_t generic_reg_wait(const struct dc_context *ctx,
 
 	return reg_val;
 }
+
+void generic_write_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t data)
+{
+	dm_write_reg(ctx, addr_index, index);
+	dm_write_reg(ctx, addr_data, data);
+}
+
+uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index)
+{
+	uint32_t value = 0;
+
+	dm_write_reg(ctx, addr_index, index);
+	value = dm_read_reg(ctx, addr_data);
+
+	return value;
+}
+
+
+uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t reg_val, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...)
+{
+	uint32_t shift, mask, field_value;
+	int i = 1;
+
+	va_list ap;
+
+	va_start(ap, field_value1);
+
+	reg_val = set_reg_field_value_ex(reg_val, field_value1, mask1, shift1);
+
+	while (i < n) {
+		shift = va_arg(ap, uint32_t);
+		mask = va_arg(ap, uint32_t);
+		field_value = va_arg(ap, uint32_t);
+
+		reg_val = set_reg_field_value_ex(reg_val, field_value, mask, shift);
+		i++;
+	}
+
+	generic_write_indirect_reg(ctx, addr_index, addr_data, index, reg_val);
+	va_end(ap);
+
+	return reg_val;
+}
diff --git a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
index 3306e7b0b3e3..cf5a84b9e27c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/reg_helper.h
@@ -445,4 +445,50 @@ uint32_t generic_reg_get8(const struct dc_context *ctx, uint32_t addr,
 		uint8_t shift6, uint32_t mask6, uint32_t *field_value6,
 		uint8_t shift7, uint32_t mask7, uint32_t *field_value7,
 		uint8_t shift8, uint32_t mask8, uint32_t *field_value8);
+
+
+/* indirect register access */
+
+#define IX_REG_SET_N(index_reg_name, data_reg_name, index, n, initial_val, ...)	\
+		generic_indirect_reg_update_ex(CTX, \
+				REG(index_reg_name), REG(data_reg_name), IND_REG(index), \
+				initial_val, \
+				n, __VA_ARGS__)
+
+#define IX_REG_SET_2(index_reg_name, data_reg_name, index, init_value, f1, v1, f2, v2)	\
+		IX_REG_SET_N(index_reg_name, data_reg_name, index, 2, init_value, \
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+
+#define IX_REG_READ(index_reg_name, data_reg_name, index) \
+		generic_read_indirect_reg(CTX, REG(index_reg_name), REG(data_reg_name), IND_REG(index))
+
+
+
+#define IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, n, ...)	\
+		generic_indirect_reg_update_ex(CTX, \
+				REG(index_reg_name), REG(data_reg_name), IND_REG(index), \
+				IX_REG_READ(index_reg_name, data_reg_name, index), \
+				n, __VA_ARGS__)
+
+#define IX_REG_UPDATE_2(index_reg_name, data_reg_name, index, f1, v1, f2, v2)	\
+		IX_REG_UPDATE_N(index_reg_name, data_reg_name, index, 2,\
+				FN(reg, f1), v1,\
+				FN(reg, f2), v2)
+
+void generic_write_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t data);
+
+uint32_t generic_read_indirect_reg(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index);
+
+uint32_t generic_indirect_reg_update_ex(const struct dc_context *ctx,
+		uint32_t addr_index, uint32_t addr_data,
+		uint32_t index, uint32_t reg_val, int n,
+		uint8_t shift1, uint32_t mask1, uint32_t field_value1,
+		...);
+
 #endif /* DRIVERS_GPU_DRM_AMD_DC_DEV_DC_INC_REG_HELPER_H_ */
-- 
cgit v1.2.3


From 7a34057cb5ceb20756e30abc36c58c34be62eff9 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Sun, 17 Jun 2018 13:26:27 -0400
Subject: drm/amd/display: fix incorrect check for atom table size

in case we have very few pins in the table, check fails and we can't boot

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Yongqiang Sun <yongqiang.sun@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
index aeb56e402ccc..eab007e1793c 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
@@ -678,7 +678,7 @@ static enum bp_result bios_parser_get_gpio_pin_info(
 		return BP_RESULT_BADBIOSTABLE;
 
 	if (sizeof(struct atom_common_table_header) +
-			sizeof(struct atom_gpio_pin_lut_v2_1)
+			sizeof(struct atom_gpio_pin_assignment)
 			> le16_to_cpu(header->table_header.structuresize))
 		return BP_RESULT_BADBIOSTABLE;
 
-- 
cgit v1.2.3


From 41db5f1931ec73f2d909752e09ffb691fecdaaa1 Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Fri, 15 Jun 2018 14:25:48 -0400
Subject: drm/amd/display: set-read link rate and lane count through debugfs

 function description
 get/ set DP configuration: lane_count, link_rate, spread_spectrum

  valid lane count value: 1, 2, 4
  valid link rate value:
  06h = 1.62Gbps per lane
  0Ah = 2.7Gbps per lane
  0Ch = 3.24Gbps per lane
  14h = 5.4Gbps per lane
  1Eh = 8.1Gbps per lane

  debugfs is located at /sys/kernel/debug/dri/0/DP-x/link_settings

  --- to get dp configuration

  xxd -l 300 phy_settings

  It will list current, verified, reported, preferred dp configuration.
  current -- for current video mode
  verified --- maximum configuration which pass link training
  reported --- DP rx report caps (DPCD register offset 0, 1 2)
  preferred --- user force settings

  --- set (or force) dp configuration

  echo <lane_count>  <link_rate>

  for example, to force to  2 lane, 2.7GHz,
  echo 4 0xa > link_settings

  spread_spectrum could not be changed dynamically.

  in case invalid lane count, link rate are force, no hw programming will be
  done. please check link settings after force operation to see if HW get
  programming.

  xxd -l 300 link_settings

  check current and preferred settings.

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Hersen Wu <hersenxs.wu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c  | 227 ++++++++++++++++++---
 1 file changed, 196 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index cf5ea69e46ad..9ff8833b52c4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -26,38 +26,211 @@
 #include <linux/debugfs.h>
 
 #include "dc.h"
-#include "dc_link.h"
 
 #include "amdgpu.h"
 #include "amdgpu_dm.h"
 #include "amdgpu_dm_debugfs.h"
 
-static ssize_t dp_link_rate_debugfs_read(struct file *f, char __user *buf,
+/* function description
+ * get/ set DP configuration: lane_count, link_rate, spread_spectrum
+ *
+ * valid lane count value: 1, 2, 4
+ * valid link rate value:
+ * 06h = 1.62Gbps per lane
+ * 0Ah = 2.7Gbps per lane
+ * 0Ch = 3.24Gbps per lane
+ * 14h = 5.4Gbps per lane
+ * 1Eh = 8.1Gbps per lane
+ *
+ * debugfs is located at /sys/kernel/debug/dri/0/DP-x/link_settings
+ *
+ * --- to get dp configuration
+ *
+ * xxd -l 300 phy_settings
+ *
+ * It will list current, verified, reported, preferred dp configuration.
+ * current -- for current video mode
+ * verified --- maximum configuration which pass link training
+ * reported --- DP rx report caps (DPCD register offset 0, 1 2)
+ * preferred --- user force settings
+ *
+ * --- set (or force) dp configuration
+ *
+ * echo <lane_count>  <link_rate>
+ *
+ * for example, to force to  2 lane, 2.7GHz,
+ * echo 4 0xa > link_settings
+ *
+ * spread_spectrum could not be changed dynamically.
+ *
+ * in case invalid lane count, link rate are force, no hw programming will be
+ * done. please check link settings after force operation to see if HW get
+ * programming.
+ *
+ * xxd -l 300 link_settings
+ *
+ * check current and preferred settings.
+ *
+ */
+static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
 				 size_t size, loff_t *pos)
 {
-	/* TODO: create method to read link rate */
-	return 1;
-}
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *rd_buf = NULL;
+	char *rd_buf_ptr = NULL;
+	uint32_t rd_buf_size = 320;
+	int bytes_to_user;
+	uint8_t str_len = 0;
+	int r;
 
-static ssize_t dp_link_rate_debugfs_write(struct file *f, const char __user *buf,
-				 size_t size, loff_t *pos)
-{
-	/* TODO: create method to write link rate */
-	return 1;
-}
+	if (size == 0)
+		return 0;
 
-static ssize_t dp_lane_count_debugfs_read(struct file *f, char __user *buf,
-				 size_t size, loff_t *pos)
-{
-	/* TODO: create method to read lane count */
-	return 1;
+	rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
+	if (!rd_buf)
+		return 0;
+
+	rd_buf_ptr = rd_buf;
+
+	str_len = strlen("Current:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Current:  %d  %d  %d  ",
+			link->cur_link_settings.lane_count,
+			link->cur_link_settings.link_rate,
+			link->cur_link_settings.link_spread);
+	rd_buf_ptr = rd_buf_ptr + str_len;
+
+	str_len = strlen("Verified:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
+			link->verified_link_cap.lane_count,
+			link->verified_link_cap.link_rate,
+			link->verified_link_cap.link_spread);
+	rd_buf_ptr = rd_buf_ptr + str_len;
+
+	str_len = strlen("Reported:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
+			link->reported_link_cap.lane_count,
+			link->reported_link_cap.link_rate,
+			link->reported_link_cap.link_spread);
+	rd_buf_ptr = rd_buf_ptr + str_len;
+
+	str_len = strlen("Preferred:  %d  %d  %d  ");
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d  ",
+			link->preferred_link_setting.lane_count,
+			link->preferred_link_setting.link_rate,
+			link->preferred_link_setting.link_spread);
+
+	r = copy_to_user(buf, rd_buf, rd_buf_size);
+
+	bytes_to_user = rd_buf_size - r;
+
+	if (r > rd_buf_size) {
+		bytes_to_user = 0;
+		DRM_DEBUG_DRIVER("data not copy to user");
+	}
+
+	kfree(rd_buf);
+	return bytes_to_user;
 }
 
-static ssize_t dp_lane_count_debugfs_write(struct file *f, const char __user *buf,
+static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 				 size_t size, loff_t *pos)
 {
-	/* TODO: create method to write lane count */
-	return 1;
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	struct dc *dc = (struct dc *)link->dc;
+	struct dc_link_settings prefer_link_settings;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	uint32_t wr_buf_size = 40;
+	int r;
+	int bytes_from_user;
+	char *sub_str;
+	/* 0: lane_count; 1: link_rate */
+	uint8_t param_index = 0;
+	long param[2];
+	const char delimiter[3] = {' ', '\n', '\0'};
+	bool valid_input = false;
+
+	if (size == 0)
+		return 0;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return 0;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not read\n");
+		return 0;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	while (isspace(*wr_buf_ptr))
+		wr_buf_ptr++;
+
+	while ((*wr_buf_ptr != '\0') && (param_index < 2)) {
+
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER(" -EINVAL convert error happens!\n");
+
+		param_index++;
+		while (isspace(*wr_buf_ptr))
+			wr_buf_ptr++;
+	}
+
+	DRM_DEBUG_DRIVER("Lane_count:  %lx\n", param[0]);
+	DRM_DEBUG_DRIVER("link_rate:  %lx\n", param[1]);
+
+	switch (param[0]) {
+	case LANE_COUNT_ONE:
+	case LANE_COUNT_TWO:
+	case LANE_COUNT_FOUR:
+		valid_input = true;
+		break;
+	default:
+		break;
+	}
+
+	switch (param[1]) {
+	case LINK_RATE_LOW:
+	case LINK_RATE_HIGH:
+	case LINK_RATE_RBR2:
+	case LINK_RATE_HIGH2:
+	case LINK_RATE_HIGH3:
+		valid_input = true;
+		break;
+	default:
+		break;
+	}
+
+	if (!valid_input) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Input value  exceed  No HW will be programmed\n");
+		return bytes_from_user;
+	}
+
+	/* save user force lane_count, link_rate to preferred settings
+	 * spread spectrum will not be changed
+	 */
+	prefer_link_settings.link_spread = link->cur_link_settings.link_spread;
+	prefer_link_settings.lane_count = param[0];
+	prefer_link_settings.link_rate = param[1];
+
+	dc_link_set_preferred_link_settings(dc, &prefer_link_settings, link);
+
+	kfree(wr_buf);
+
+	return bytes_from_user;
 }
 
 static ssize_t dp_voltage_swing_debugfs_read(struct file *f, char __user *buf,
@@ -102,17 +275,10 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 	return 1;
 }
 
-static const struct file_operations dp_link_rate_fops = {
-	.owner = THIS_MODULE,
-	.read = dp_link_rate_debugfs_read,
-	.write = dp_link_rate_debugfs_write,
-	.llseek = default_llseek
-};
-
-static const struct file_operations dp_lane_count_fops = {
+static const struct file_operations dp_link_settings_debugfs_fops = {
 	.owner = THIS_MODULE,
-	.read = dp_lane_count_debugfs_read,
-	.write = dp_lane_count_debugfs_write,
+	.read = dp_link_settings_read,
+	.write = dp_link_settings_write,
 	.llseek = default_llseek
 };
 
@@ -141,8 +307,7 @@ static const struct {
 	char *name;
 	const struct file_operations *fops;
 } dp_debugfs_entries[] = {
-		{"link_rate", &dp_link_rate_fops},
-		{"lane_count", &dp_lane_count_fops},
+		{"link_settings", &dp_link_settings_debugfs_fops},
 		{"voltage_swing", &dp_voltage_swing_fops},
 		{"pre_emphasis", &dp_pre_emphasis_fops},
 		{"phy_test_pattern", &dp_phy_test_pattern_fops}
-- 
cgit v1.2.3


From c9ff778b291b95f6f7c0aa764c714ca88cc49f7b Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 5 Jun 2018 09:14:56 -0400
Subject: drm/amd/display: dal 3.1.53

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 59985baac11e..85533619440a 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.52"
+#define DC_VER "3.1.53"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 93ed1814c668fb13f3b23b629528e90a2b0d5ea3 Mon Sep 17 00:00:00 2001
From: Hugo Hu <hugo.hu@amd.com>
Date: Mon, 18 Jun 2018 15:27:58 -0400
Subject: drm/amd/display: Correct calculation of duration time.

Signed-off-by: Hugo Hu <hugo.hu@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 9cbd5036db07..bf4df34bc1df 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -864,10 +864,10 @@ void hwss_edp_power_control(
 		if (power_up) {
 			unsigned long long current_ts = dm_get_timestamp(ctx);
 			unsigned long long duration_in_ms =
-					dm_get_elapse_time_in_ns(
+					div64_u64(dm_get_elapse_time_in_ns(
 							ctx,
 							current_ts,
-							div64_u64(link->link_trace.time_stamp.edp_poweroff, 1000000));
+							link->link_trace.time_stamp.edp_poweroff), 1000000);
 			unsigned long long wait_time_ms = 0;
 
 			/* max 500ms from LCDVDD off to on */
-- 
cgit v1.2.3


From 0252c9425f20ade8bfcb5ad4f1e150940acbe39c Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Mon, 18 Jun 2018 15:45:07 -0400
Subject: drm/amd/display: Add Azalia registers to HW sequencer

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index 057407892618..f091d87f8f8b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -275,6 +275,8 @@ struct dce_hwseq_registers {
 	uint32_t MC_VM_SYSTEM_APERTURE_DEFAULT_ADDR_LSB;
 	uint32_t MC_VM_SYSTEM_APERTURE_LOW_ADDR;
 	uint32_t MC_VM_SYSTEM_APERTURE_HIGH_ADDR;
+	uint32_t AZALIA_AUDIO_DTO;
+	uint32_t AZALIA_CONTROLLER_CLOCK_GATING;
 };
  /* set field name */
 #define HWS_SF(blk_name, reg_name, field_name, post_fix)\
@@ -500,7 +502,8 @@ struct dce_hwseq_registers {
 	type D1VGA_MODE_ENABLE; \
 	type D2VGA_MODE_ENABLE; \
 	type D3VGA_MODE_ENABLE; \
-	type D4VGA_MODE_ENABLE;
+	type D4VGA_MODE_ENABLE; \
+	type AZALIA_AUDIO_DTO_MODULE;
 
 struct dce_hwseq_shift {
 	HWSEQ_REG_FIELD_LIST(uint8_t)
-- 
cgit v1.2.3


From 8e8539c2fcdf65b6a2e6ceb93e56034896e47dd0 Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Mon, 18 Jun 2018 19:50:07 -0400
Subject: drm/amd/display: Define couple extra DCN registers

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h            | 1 +
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h | 9 +++++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index f091d87f8f8b..df3203a1d278 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -147,6 +147,7 @@
 	SR(DCCG_GATE_DISABLE_CNTL2), \
 	SR(DCFCLK_CNTL),\
 	SR(DCFCLK_CNTL), \
+	SR(DC_MEM_GLOBAL_PWR_REQ_CNTL), \
 	/* todo:  get these from GVM instead of reading registers ourselves */\
 	MMHUB_SR(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_HI32),\
 	MMHUB_SR(VM_CONTEXT0_PAGE_TABLE_BASE_ADDR_LO32),\
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index 2a97cdb2cfbb..d8ef30bed9ff 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -42,6 +42,7 @@
 #define LE_DCN_COMMON_REG_LIST(id) \
 	SRI(DIG_BE_CNTL, DIG, id), \
 	SRI(DIG_BE_EN_CNTL, DIG, id), \
+	SRI(TMDS_CTL_BITS, DIG, id), \
 	SRI(DP_CONFIG, DP, id), \
 	SRI(DP_DPHY_CNTL, DP, id), \
 	SRI(DP_DPHY_PRBS_CNTL, DP, id), \
@@ -64,6 +65,7 @@
 	SRI(DP_DPHY_INTERNAL_CTRL, DP, id), \
 	SRI(DP_DPHY_HBR2_PATTERN_CONTROL, DP, id)
 
+
 #define LE_DCN10_REG_LIST(id)\
 	LE_DCN_COMMON_REG_LIST(id)
 
@@ -100,6 +102,7 @@ struct dcn10_link_enc_registers {
 	uint32_t DP_DPHY_BS_SR_SWAP_CNTL;
 	uint32_t DP_DPHY_HBR2_PATTERN_CONTROL;
 	uint32_t DP_SEC_CNTL1;
+	uint32_t TMDS_CTL_BITS;
 };
 
 #define LE_SF(reg_name, field_name, post_fix)\
@@ -110,6 +113,7 @@ struct dcn10_link_enc_registers {
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_HPD_SELECT, mask_sh),\
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_MODE, mask_sh),\
 	LE_SF(DIG0_DIG_BE_CNTL, DIG_FE_SOURCE_SELECT, mask_sh),\
+	LE_SF(DIG0_TMDS_CTL_BITS, TMDS_CTL0, mask_sh), \
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_BYPASS, mask_sh),\
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE0, mask_sh),\
 	LE_SF(DP0_DP_DPHY_CNTL, DPHY_ATEST_SEL_LANE1, mask_sh),\
@@ -198,10 +202,11 @@ struct dcn10_link_enc_registers {
 	type DP_MSE_SAT_SLOT_COUNT3;\
 	type DP_MSE_SAT_UPDATE;\
 	type DP_MSE_16_MTP_KEEPOUT;\
+	type DC_HPD_EN;\
+	type TMDS_CTL0;\
 	type AUX_HPD_SEL;\
 	type AUX_LS_READ_EN;\
-	type AUX_RX_RECEIVE_WINDOW;\
-	type DC_HPD_EN
+	type AUX_RX_RECEIVE_WINDOW
 
 struct dcn10_link_enc_shift {
 	DCN_LINK_ENCODER_REG_FIELD_LIST(uint8_t);
-- 
cgit v1.2.3


From 1bd493e37807c4bf7ee8c4809d2d83545379c04d Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Mon, 18 Jun 2018 18:32:43 -0400
Subject: drm/amd/display: Expose configure_encoder for link_encoder

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c | 3 +--
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h | 4 ++++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index fd9dc70190a8..18a7cac4f6e3 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -445,12 +445,11 @@ static uint8_t get_frontend_source(
 	}
 }
 
-static void configure_encoder(
+void configure_encoder(
 	struct dcn10_link_encoder *enc10,
 	const struct dc_link_settings *link_settings)
 {
 	/* set number of lanes */
-
 	REG_SET(DP_CONFIG, 0,
 			DP_UDI_LANES, link_settings->lane_count - LANE_COUNT_ONE);
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index d8ef30bed9ff..cd3bb5d40579 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -271,6 +271,10 @@ void dcn10_link_encoder_setup(
 	struct link_encoder *enc,
 	enum signal_type signal);
 
+void configure_encoder(
+	struct dcn10_link_encoder *enc10,
+	const struct dc_link_settings *link_settings);
+
 /* enables TMDS PHY output */
 /* TODO: still need depth or just pass in adjusted pixel clock? */
 void dcn10_link_encoder_enable_tmds_output(
-- 
cgit v1.2.3


From aac5db824d6f5997344101ae0e71fbb003b9692b Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Tue, 29 May 2018 13:11:55 -0400
Subject: drm/amd/display: Serialize is_dp_sink_present

Access to GPIO needs to be serialized. Aux transactions are already
serialized in DRM but we also need to serialize access to the GPIO pin
for purposes of DP dongle detection.

Call is_dp_sink_present through DM so we can lock correctly. This
follows the same pattern used for DPCD transactions.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c    | 16 ++++++++++++++++
 drivers/gpu/drm/amd/display/dc/core/dc_link.c            |  4 ++--
 drivers/gpu/drm/amd/display/dc/dc_link.h                 |  2 ++
 drivers/gpu/drm/amd/display/dc/dm_helpers.h              |  3 +++
 4 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index b19dc4cfc030..7b51b8fde3fe 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -454,6 +454,22 @@ bool dm_helpers_submit_i2c(
 	return result;
 }
 
+bool dm_helpers_is_dp_sink_present(struct dc_link *link)
+{
+	bool dp_sink_present;
+	struct amdgpu_dm_connector *aconnector = link->priv;
+
+	if (!aconnector) {
+		BUG_ON("Failed to found connector for link!");
+		return true;
+	}
+
+	mutex_lock(&aconnector->dm_dp_aux.aux.hw_mutex);
+	dp_sink_present = dc_link_is_dp_sink_present(link);
+	mutex_unlock(&aconnector->dm_dp_aux.aux.hw_mutex);
+	return dp_sink_present;
+}
+
 enum dc_edid_status dm_helpers_read_local_edid(
 		struct dc_context *ctx,
 		struct dc_link *link,
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index a4180ba63d82..fe29a398b703 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -313,7 +313,7 @@ static enum signal_type get_basic_signal_type(
  * @brief
  * Check whether there is a dongle on DP connector
  */
-static bool is_dp_sink_present(struct dc_link *link)
+bool dc_link_is_dp_sink_present(struct dc_link *link)
 {
 	enum gpio_result gpio_result;
 	uint32_t clock_pin = 0;
@@ -406,7 +406,7 @@ static enum signal_type link_detect_sink(
 			 * we assume signal is DVI; it could be corrected
 			 * to HDMI after dongle detection
 			 */
-			if (!is_dp_sink_present(link))
+			if (!dm_helpers_is_dp_sink_present(link))
 				result = SIGNAL_TYPE_DVI_SINGLE_LINK;
 		}
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 83eea42452b5..eda4a5d3ff1c 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -210,6 +210,8 @@ bool dc_link_dp_set_test_pattern(
 
 void dc_link_enable_hpd_filter(struct dc_link *link, bool enable);
 
+bool dc_link_is_dp_sink_present(struct dc_link *link);
+
 /*
  * DPCD access interfaces
  */
diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
index 034369fbb9e2..7e6b9f5b8906 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
@@ -103,6 +103,9 @@ bool dm_helpers_submit_i2c(
 		const struct dc_link *link,
 		struct i2c_command *cmd);
 
+bool dm_helpers_is_dp_sink_present(
+		struct dc_link *link);
+
 enum dc_edid_status dm_helpers_read_local_edid(
 		struct dc_context *ctx,
 		struct dc_link *link,
-- 
cgit v1.2.3


From 899e2aaddbfa0ff96fbaf31f0d9e91427e87dd88 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Tue, 8 May 2018 16:28:31 -0400
Subject: drm/amd/display: Break out function to simply read aux reply

DRM's DP helpers take care of dealing with the error code for us. In
order not to step on each other's toes we'll need to be able to simply
read auch channel replies without further logic based on return values.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Sun peng Li <Sunpeng.Li@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h |   6 ++
 .../display/dc/i2caux/dce110/aux_engine_dce110.c   | 119 ++++++++++++---------
 2 files changed, 76 insertions(+), 49 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
index b01488f710d5..c33a2898d967 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/aux_engine.h
@@ -44,6 +44,12 @@ struct aux_engine_funcs {
 	void (*process_channel_reply)(
 		struct aux_engine *engine,
 		struct aux_reply_transaction_data *reply);
+	int (*read_channel_reply)(
+		struct aux_engine *engine,
+		uint32_t size,
+		uint8_t *buffer,
+		uint8_t *reply_result,
+		uint32_t *sw_status);
 	enum aux_channel_operation_result (*get_channel_status)(
 		struct aux_engine *engine,
 		uint8_t *returned_bytes);
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
index 2b927f25937b..1f3940644a5b 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
@@ -275,61 +275,92 @@ static void submit_channel_request(
 	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
 }
 
-static void process_channel_reply(
-	struct aux_engine *engine,
-	struct aux_reply_transaction_data *reply)
+static int read_channel_reply(struct aux_engine *engine, uint32_t size,
+			      uint8_t *buffer, uint8_t *reply_result,
+			      uint32_t *sw_status)
 {
 	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t bytes_replied;
+	uint32_t reply_result_32;
 
-	/* Need to do a read to get the number of bytes to process
-	 * Alternatively, this information can be passed -
-	 * but that causes coupling which isn't good either. */
+	*sw_status = REG_GET(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT,
+			     &bytes_replied);
 
-	uint32_t bytes_replied;
-	uint32_t value;
+	/* In case HPD is LOW, exit AUX transaction */
+	if ((*sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return -1;
 
-	value = REG_GET(AUX_SW_STATUS,
-			AUX_SW_REPLY_BYTE_COUNT, &bytes_replied);
+	/* Need at least the status byte */
+	if (!bytes_replied)
+		return -1;
 
-	/* in case HPD is LOW, exit AUX transaction */
-	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
-		reply->status = AUX_TRANSACTION_REPLY_HPD_DISCON;
-		return;
-	}
+	REG_UPDATE_1BY1_3(AUX_SW_DATA,
+			  AUX_SW_INDEX, 0,
+			  AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			  AUX_SW_DATA_RW, 1);
+
+	REG_GET(AUX_SW_DATA, AUX_SW_DATA, &reply_result_32);
+	*reply_result = (uint8_t)reply_result_32;
 
-	if (bytes_replied) {
-		uint32_t reply_result;
+	if (reply_result_32 >> 4 == 0) { /* ACK */
+		uint32_t i = 0;
 
-		REG_UPDATE_1BY1_3(AUX_SW_DATA,
-				AUX_SW_INDEX, 0,
-				AUX_SW_AUTOINCREMENT_DISABLE, 1,
-				AUX_SW_DATA_RW, 1);
+		/* First byte was already used to get the command status */
+		--bytes_replied;
 
-		REG_GET(AUX_SW_DATA,
-				AUX_SW_DATA, &reply_result);
+		/* Do not overflow buffer */
+		if (bytes_replied > size)
+			return -1;
 
-		reply_result = reply_result >> 4;
+		while (i < bytes_replied) {
+			uint32_t aux_sw_data_val;
 
-		switch (reply_result) {
-		case 0: /* ACK */ {
-			uint32_t i = 0;
+			REG_GET(AUX_SW_DATA, AUX_SW_DATA, &aux_sw_data_val);
+			buffer[i] = aux_sw_data_val;
+			++i;
+		}
 
-			/* first byte was already used
-			 * to get the command status */
-			--bytes_replied;
+		return i;
+	}
+
+	return 0;
+}
+
+static void process_channel_reply(
+	struct aux_engine *engine,
+	struct aux_reply_transaction_data *reply)
+{
+	int bytes_replied;
+	uint8_t reply_result;
+	uint32_t sw_status;
 
-			while (i < bytes_replied) {
-				uint32_t aux_sw_data_val;
+	bytes_replied = read_channel_reply(engine, reply->length, reply->data,
+					   &reply_result, &sw_status);
 
-				REG_GET(AUX_SW_DATA,
-						AUX_SW_DATA, &aux_sw_data_val);
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		return;
+	}
 
-				reply->data[i] = aux_sw_data_val;
-				++i;
-			}
+	if (bytes_replied < 0) {
+		/* Need to handle an error case...
+		 * Hopefully, upper layer function won't call this function if
+		 * the number of bytes in the reply was 0, because there was
+		 * surely an error that was asserted that should have been
+		 * handled for hot plug case, this could happens
+		 */
+		if (!(sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+			ASSERT_CRITICAL(false);
+			return;
+		}
+	} else {
+		reply_result = reply_result >> 4;
 
+		switch (reply_result) {
+		case 0: /* ACK */
 			reply->status = AUX_TRANSACTION_REPLY_AUX_ACK;
-		}
 		break;
 		case 1: /* NACK */
 			reply->status = AUX_TRANSACTION_REPLY_AUX_NACK;
@@ -346,17 +377,6 @@ static void process_channel_reply(
 		default:
 			reply->status = AUX_TRANSACTION_REPLY_INVALID;
 		}
-	} else {
-		/* Need to handle an error case...
-		 * hopefully, upper layer function won't call this function
-		 * if the number of bytes in the reply was 0
-		 * because there was surely an error that was asserted
-		 * that should have been handled
-		 * for hot plug case, this could happens*/
-		if (!(value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
-			reply->status = AUX_TRANSACTION_REPLY_INVALID;
-			ASSERT_CRITICAL(false);
-		}
 	}
 }
 
@@ -427,6 +447,7 @@ static const struct aux_engine_funcs aux_engine_funcs = {
 	.acquire_engine = acquire_engine,
 	.submit_channel_request = submit_channel_request,
 	.process_channel_reply = process_channel_reply,
+	.read_channel_reply = read_channel_reply,
 	.get_channel_status = get_channel_status,
 	.is_engine_available = is_engine_available,
 };
-- 
cgit v1.2.3


From 084b3765ec4baf8b7de57e7dc1e1ba1b6905e9d9 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Wed, 9 May 2018 16:26:17 -0400
Subject: drm/amd/display: Return aux replies directly to DRM

Currently we still go through DC code that does error checking, retries,
etc. There's no need for that since DRM already does that for us. This
simplifies the code a bit and makes it easier to debug.

This also ensures we correctly tell DRM how many bytes have actually
been read, as we should. This allows DRM to correctly read the EDID on
the Chamelium DP port.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../amd/display/amdgpu_dm/amdgpu_dm_mst_types.c    |  89 +++++++++------
 drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c  | 120 ++++++++++-----------
 drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h   |  22 ++--
 3 files changed, 117 insertions(+), 114 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
index c74105758815..8348d4d46b30 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
@@ -80,52 +80,72 @@ static void log_dpcd(uint8_t type,
 static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 				  struct drm_dp_aux_msg *msg)
 {
-	enum i2c_mot_mode mot = (msg->request & DP_AUX_I2C_MOT) ?
-		I2C_MOT_TRUE : I2C_MOT_FALSE;
-	enum ddc_result res;
+	ssize_t result = 0;
+	enum i2caux_transaction_action action;
+	enum aux_transaction_type type;
 
 	if (WARN_ON(msg->size > 16))
 		return -E2BIG;
 
 	switch (msg->request & ~DP_AUX_I2C_MOT) {
 	case DP_AUX_NATIVE_READ:
-		res = dal_ddc_service_read_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				false,
-				I2C_MOT_UNDEF,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_DP;
+		action = I2CAUX_TRANSACTION_ACTION_DP_READ;
+
+		result = dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+					      msg->address,
+					      &msg->reply,
+					      msg->buffer,
+					      msg->size,
+					      type,
+					      action);
 		break;
 	case DP_AUX_NATIVE_WRITE:
-		res = dal_ddc_service_write_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				false,
-				I2C_MOT_UNDEF,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_DP;
+		action = I2CAUX_TRANSACTION_ACTION_DP_WRITE;
+
+		dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+				     msg->address,
+				     &msg->reply,
+				     msg->buffer,
+				     msg->size,
+				     type,
+				     action);
+		result = msg->size;
 		break;
 	case DP_AUX_I2C_READ:
-		res = dal_ddc_service_read_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				true,
-				mot,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_I2C;
+		if (msg->request & DP_AUX_I2C_MOT)
+			action = I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT;
+		else
+			action = I2CAUX_TRANSACTION_ACTION_I2C_READ;
+
+		result = dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+					      msg->address,
+					      &msg->reply,
+					      msg->buffer,
+					      msg->size,
+					      type,
+					      action);
 		break;
 	case DP_AUX_I2C_WRITE:
-		res = dal_ddc_service_write_dpcd_data(
-				TO_DM_AUX(aux)->ddc_service,
-				true,
-				mot,
-				msg->address,
-				msg->buffer,
-				msg->size);
+		type = AUX_TRANSACTION_TYPE_I2C;
+		if (msg->request & DP_AUX_I2C_MOT)
+			action = I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT;
+		else
+			action = I2CAUX_TRANSACTION_ACTION_I2C_WRITE;
+
+		dc_link_aux_transfer(TO_DM_AUX(aux)->ddc_service,
+				     msg->address,
+				     &msg->reply,
+				     msg->buffer,
+				     msg->size,
+				     type,
+				     action);
+		result = msg->size;
 		break;
 	default:
-		return 0;
+		return -EINVAL;
 	}
 
 #ifdef TRACE_DPCD
@@ -136,7 +156,10 @@ static ssize_t dm_dp_aux_transfer(struct drm_dp_aux *aux,
 		 r == DDC_RESULT_SUCESSFULL);
 #endif
 
-	return msg->size;
+	if (result < 0) /* DC doesn't know about kernel error codes */
+		result = -EIO;
+
+	return result;
 }
 
 static enum drm_connector_status
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index d5294798b0a5..d108ccfc5cf9 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -33,6 +33,10 @@
 #include "include/vector.h"
 #include "core_types.h"
 #include "dc_link_ddc.h"
+#include "i2caux/engine.h"
+#include "i2caux/i2c_engine.h"
+#include "i2caux/aux_engine.h"
+#include "i2caux/i2caux.h"
 
 #define AUX_POWER_UP_WA_DELAY 500
 #define I2C_OVER_AUX_DEFER_WA_DELAY 70
@@ -629,78 +633,62 @@ bool dal_ddc_service_query_ddc_data(
 	return ret;
 }
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
-	struct ddc_service *ddc,
-	bool i2c,
-	enum i2c_mot_mode mot,
-	uint32_t address,
-	uint8_t *data,
-	uint32_t len)
+int dc_link_aux_transfer(struct ddc_service *ddc,
+			     unsigned int address,
+			     uint8_t *reply,
+			     void *buffer,
+			     unsigned int size,
+			     enum aux_transaction_type type,
+			     enum i2caux_transaction_action action)
 {
-	struct aux_payload read_payload = {
-		.i2c_over_aux = i2c,
-		.write = false,
-		.address = address,
-		.length = len,
-		.data = data,
-	};
-	struct aux_command command = {
-		.payloads = &read_payload,
-		.number_of_payloads = 1,
-		.defer_delay = 0,
-		.max_defer_write_retry = 0,
-		.mot = mot
-	};
-
-	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
-		BREAK_TO_DEBUGGER();
-		return DDC_RESULT_FAILED_INVALID_OPERATION;
-	}
+	struct i2caux *i2caux = ddc->ctx->i2caux;
+	struct ddc *ddc_pin = ddc->ddc_pin;
+	struct aux_engine *engine;
+	enum aux_channel_operation_result operation_result;
+	struct aux_request_transaction_data aux_req;
+	struct aux_reply_transaction_data aux_rep;
+	uint8_t returned_bytes = 0;
+	int res = -1;
+	uint32_t status;
 
-	if (dal_i2caux_submit_aux_command(
-		ddc->ctx->i2caux,
-		ddc->ddc_pin,
-		&command))
-		return DDC_RESULT_SUCESSFULL;
+	memset(&aux_req, 0, sizeof(aux_req));
+	memset(&aux_rep, 0, sizeof(aux_rep));
 
-	return DDC_RESULT_FAILED_OPERATION;
-}
+	engine = i2caux->funcs->acquire_aux_engine(i2caux, ddc_pin);
 
-enum ddc_result dal_ddc_service_write_dpcd_data(
-	struct ddc_service *ddc,
-	bool i2c,
-	enum i2c_mot_mode mot,
-	uint32_t address,
-	const uint8_t *data,
-	uint32_t len)
-{
-	struct aux_payload write_payload = {
-		.i2c_over_aux = i2c,
-		.write = true,
-		.address = address,
-		.length = len,
-		.data = (uint8_t *)data,
-	};
-	struct aux_command command = {
-		.payloads = &write_payload,
-		.number_of_payloads = 1,
-		.defer_delay = 0,
-		.max_defer_write_retry = 0,
-		.mot = mot
-	};
-
-	if (len > DEFAULT_AUX_MAX_DATA_SIZE) {
-		BREAK_TO_DEBUGGER();
-		return DDC_RESULT_FAILED_INVALID_OPERATION;
-	}
+	aux_req.type = type;
+	aux_req.action = action;
+
+	aux_req.address = address;
+	aux_req.delay = 0;
+	aux_req.length = size;
+	aux_req.data = buffer;
+
+	engine->funcs->submit_channel_request(engine, &aux_req);
+	operation_result = engine->funcs->get_channel_status(engine, &returned_bytes);
 
-	if (dal_i2caux_submit_aux_command(
-		ddc->ctx->i2caux,
-		ddc->ddc_pin,
-		&command))
-		return DDC_RESULT_SUCESSFULL;
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		res = returned_bytes;
+
+		if (res <= size && res > 0)
+			res = engine->funcs->read_channel_reply(engine, size,
+								buffer, reply,
+								&status);
+
+		break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		res = 0;
+		break;
+	case AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN:
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		res = -1;
+		break;
+	}
 
-	return DDC_RESULT_FAILED_OPERATION;
+	i2caux->funcs->release_engine(i2caux, &engine->base);
+	return res;
 }
 
 /*test only function*/
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
index 0bf73b742f1f..538b83303b86 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_ddc.h
@@ -102,21 +102,13 @@ bool dal_ddc_service_query_ddc_data(
 		uint8_t *read_buf,
 		uint32_t read_size);
 
-enum ddc_result dal_ddc_service_read_dpcd_data(
-		struct ddc_service *ddc,
-		bool i2c,
-		enum i2c_mot_mode mot,
-		uint32_t address,
-		uint8_t *data,
-		uint32_t len);
-
-enum ddc_result dal_ddc_service_write_dpcd_data(
-		struct ddc_service *ddc,
-		bool i2c,
-		enum i2c_mot_mode mot,
-		uint32_t address,
-		const uint8_t *data,
-		uint32_t len);
+int dc_link_aux_transfer(struct ddc_service *ddc,
+			     unsigned int address,
+			     uint8_t *reply,
+			     void *buffer,
+			     unsigned int size,
+			     enum aux_transaction_type type,
+			     enum i2caux_transaction_action action);
 
 void dal_ddc_service_write_scdc_data(
 		struct ddc_service *ddc_service,
-- 
cgit v1.2.3


From e1cb3e4801e6896ba93d63222b1052199d2a8c9b Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Tue, 19 Jun 2018 09:58:24 -0400
Subject: drm/amd/display: Convert remaining loggers off dc_logger

- Removed dal/dm/dc loggers from linux, switched to kernel prints
- Modified functions that used these directly to use macros
- dc_logger support is completely dropped from Linux

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/TODO                   |   8 +-
 drivers/gpu/drm/amd/display/dc/basics/Makefile     |   2 +-
 .../gpu/drm/amd/display/dc/basics/log_helpers.c    |  71 +---
 drivers/gpu/drm/amd/display/dc/basics/logger.c     | 406 ---------------------
 .../gpu/drm/amd/display/dc/calcs/calcs_logger.h    |   9 +-
 drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c   |   6 +-
 drivers/gpu/drm/amd/display/dc/core/dc.c           |  15 +-
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c    |  23 +-
 drivers/gpu/drm/amd/display/dc/dc_stream.h         |   5 +-
 drivers/gpu/drm/amd/display/dc/dc_types.h          |   2 -
 .../drm/amd/display/dc/dce110/dce110_resource.c    |  34 +-
 .../drm/amd/display/dc/dce112/dce112_resource.c    |  34 +-
 .../gpu/drm/amd/display/include/logger_interface.h | 138 +++----
 drivers/gpu/drm/amd/display/include/logger_types.h |  59 ---
 14 files changed, 99 insertions(+), 713 deletions(-)
 delete mode 100644 drivers/gpu/drm/amd/display/dc/basics/logger.c

diff --git a/drivers/gpu/drm/amd/display/TODO b/drivers/gpu/drm/amd/display/TODO
index 357d59648401..a8a6c106e8c7 100644
--- a/drivers/gpu/drm/amd/display/TODO
+++ b/drivers/gpu/drm/amd/display/TODO
@@ -97,10 +97,10 @@ share it with drivers. But that's a very long term goal, and by far not just an
 issue with DC - other drivers, especially around DP sink handling, are equally
 guilty.
 
-19. The DC logger is still a rather sore thing, but I know that the DRM_DEBUG
-stuff just isn't up to the challenges either. We need to figure out something
-that integrates better with DRM and linux debug printing, while not being
-useless with filtering output. dynamic debug printing might be an option.
+19. DONE - The DC logger is still a rather sore thing, but I know that the
+DRM_DEBUG stuff just isn't up to the challenges either. We need to figure out
+something that integrates better with DRM and linux debug printing, while not
+being useless with filtering output. dynamic debug printing might be an option.
 
 20. Use kernel i2c device to program HDMI retimer. Some boards have an HDMI
 retimer that we need to program to pass PHY compliance. Currently that's
diff --git a/drivers/gpu/drm/amd/display/dc/basics/Makefile b/drivers/gpu/drm/amd/display/dc/basics/Makefile
index b49ea96b5dae..a50a76471107 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/basics/Makefile
@@ -25,7 +25,7 @@
 # subcomponents.
 
 BASICS = conversion.o fixpt31_32.o \
-	logger.o log_helpers.o vector.o
+	log_helpers.o vector.o
 
 AMD_DAL_BASICS = $(addprefix $(AMDDALPATH)/dc/basics/,$(BASICS))
 
diff --git a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
index f6c00a51d51a..26583f346c39 100644
--- a/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
+++ b/drivers/gpu/drm/amd/display/dc/basics/log_helpers.c
@@ -28,77 +28,12 @@
 #include "include/logger_interface.h"
 #include "dm_helpers.h"
 
-#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
-
-struct dc_signal_type_info {
-	enum signal_type type;
-	char name[MAX_NAME_LEN];
-};
-
-static const struct dc_signal_type_info signal_type_info_tbl[] = {
-		{SIGNAL_TYPE_NONE,             "NC"},
-		{SIGNAL_TYPE_DVI_SINGLE_LINK,  "DVI"},
-		{SIGNAL_TYPE_DVI_DUAL_LINK,    "DDVI"},
-		{SIGNAL_TYPE_HDMI_TYPE_A,      "HDMIA"},
-		{SIGNAL_TYPE_LVDS,             "LVDS"},
-		{SIGNAL_TYPE_RGB,              "VGA"},
-		{SIGNAL_TYPE_DISPLAY_PORT,     "DP"},
-		{SIGNAL_TYPE_DISPLAY_PORT_MST, "MST"},
-		{SIGNAL_TYPE_EDP,              "eDP"},
-		{SIGNAL_TYPE_VIRTUAL,          "Virtual"}
-};
-
-void dc_conn_log(struct dc_context *ctx,
-		const struct dc_link *link,
-		uint8_t *hex_data,
-		int hex_data_count,
-		enum dc_log_type event,
-		const char *msg,
-		...)
+void dc_conn_log_hex_linux(const uint8_t *hex_data, int hex_data_count)
 {
 	int i;
-	va_list args;
-	struct log_entry entry = { 0 };
-	enum signal_type signal;
-
-	if (link->local_sink)
-		signal = link->local_sink->sink_signal;
-	else
-		signal = link->connector_signal;
-
-	if (link->type == dc_connection_mst_branch)
-		signal = SIGNAL_TYPE_DISPLAY_PORT_MST;
-
-	dm_logger_open(ctx->logger, &entry, event);
-
-	for (i = 0; i < NUM_ELEMENTS(signal_type_info_tbl); i++)
-		if (signal == signal_type_info_tbl[i].type)
-			break;
-
-	if (i == NUM_ELEMENTS(signal_type_info_tbl))
-		goto fail;
-
-	dm_logger_append_heading(&entry);
-
-	dm_logger_append(&entry, "[%s][ConnIdx:%d] ",
-			signal_type_info_tbl[i].name,
-			link->link_index);
-
-	va_start(args, msg);
-	dm_logger_append_va(&entry, msg, args);
-
-	if (entry.buf_offset > 0 &&
-	    entry.buf[entry.buf_offset - 1] == '\n')
-		entry.buf_offset--;
 
 	if (hex_data)
 		for (i = 0; i < hex_data_count; i++)
-			dm_logger_append(&entry, "%2.2X ", hex_data[i]);
-
-	dm_logger_append(&entry, "^\n");
-
-fail:
-	dm_logger_close(&entry);
-
-	va_end(args);
+			DC_LOG_DEBUG("%2.2X ", hex_data[i]);
 }
+
diff --git a/drivers/gpu/drm/amd/display/dc/basics/logger.c b/drivers/gpu/drm/amd/display/dc/basics/logger.c
deleted file mode 100644
index a3c56cd8b396..000000000000
--- a/drivers/gpu/drm/amd/display/dc/basics/logger.c
+++ /dev/null
@@ -1,406 +0,0 @@
-/*
- * Copyright 2012-15 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-#include "dm_services.h"
-#include "include/logger_interface.h"
-#include "logger.h"
-
-
-#define NUM_ELEMENTS(a) (sizeof(a) / sizeof((a)[0]))
-
-static const struct dc_log_type_info log_type_info_tbl[] = {
-		{LOG_ERROR,                 "Error"},
-		{LOG_WARNING,               "Warning"},
-		{LOG_DEBUG,                 "Debug"},
-		{LOG_DC,                    "DC_Interface"},
-		{LOG_DTN,                   "DTN"},
-		{LOG_SURFACE,               "Surface"},
-		{LOG_HW_HOTPLUG,            "HW_Hotplug"},
-		{LOG_HW_LINK_TRAINING,      "HW_LKTN"},
-		{LOG_HW_SET_MODE,           "HW_Mode"},
-		{LOG_HW_RESUME_S3,          "HW_Resume"},
-		{LOG_HW_AUDIO,              "HW_Audio"},
-		{LOG_HW_HPD_IRQ,            "HW_HPDIRQ"},
-		{LOG_MST,                   "MST"},
-		{LOG_SCALER,                "Scaler"},
-		{LOG_BIOS,                  "BIOS"},
-		{LOG_BANDWIDTH_CALCS,       "BWCalcs"},
-		{LOG_BANDWIDTH_VALIDATION,  "BWValidation"},
-		{LOG_I2C_AUX,               "I2C_AUX"},
-		{LOG_SYNC,                  "Sync"},
-		{LOG_BACKLIGHT,             "Backlight"},
-		{LOG_FEATURE_OVERRIDE,      "Override"},
-		{LOG_DETECTION_EDID_PARSER, "Edid"},
-		{LOG_DETECTION_DP_CAPS,     "DP_Caps"},
-		{LOG_RESOURCE,              "Resource"},
-		{LOG_DML,                   "DML"},
-		{LOG_EVENT_MODE_SET,        "Mode"},
-		{LOG_EVENT_DETECTION,       "Detect"},
-		{LOG_EVENT_LINK_TRAINING,   "LKTN"},
-		{LOG_EVENT_LINK_LOSS,       "LinkLoss"},
-		{LOG_EVENT_UNDERFLOW,       "Underflow"},
-		{LOG_IF_TRACE,              "InterfaceTrace"},
-		{LOG_PERF_TRACE,            "PerfTrace"},
-		{LOG_DISPLAYSTATS,          "DisplayStats"}
-};
-
-
-/* ----------- Object init and destruction ----------- */
-static bool construct(struct dc_context *ctx, struct dal_logger *logger,
-		      uint32_t log_mask)
-{
-	/* malloc buffer and init offsets */
-	logger->log_buffer_size = DAL_LOGGER_BUFFER_MAX_SIZE;
-	logger->log_buffer = kcalloc(logger->log_buffer_size, sizeof(char),
-				     GFP_KERNEL);
-	if (!logger->log_buffer)
-		return false;
-
-	/* Initialize both offsets to start of buffer (empty) */
-	logger->buffer_read_offset = 0;
-	logger->buffer_write_offset = 0;
-
-	logger->open_count = 0;
-
-	logger->flags.bits.ENABLE_CONSOLE = 1;
-	logger->flags.bits.ENABLE_BUFFER = 0;
-
-	logger->ctx = ctx;
-
-	logger->mask = log_mask;
-
-	return true;
-}
-
-static void destruct(struct dal_logger *logger)
-{
-	if (logger->log_buffer) {
-		kfree(logger->log_buffer);
-		logger->log_buffer = NULL;
-	}
-}
-
-struct dal_logger *dal_logger_create(struct dc_context *ctx, uint32_t log_mask)
-{
-	/* malloc struct */
-	struct dal_logger *logger = kzalloc(sizeof(struct dal_logger),
-					    GFP_KERNEL);
-
-	if (!logger)
-		return NULL;
-	if (!construct(ctx, logger, log_mask)) {
-		kfree(logger);
-		return NULL;
-	}
-
-	return logger;
-}
-
-uint32_t dal_logger_destroy(struct dal_logger **logger)
-{
-	if (logger == NULL || *logger == NULL)
-		return 1;
-	destruct(*logger);
-	kfree(*logger);
-	*logger = NULL;
-
-	return 0;
-}
-
-/* ------------------------------------------------------------------------ */
-void dm_logger_append_heading(struct log_entry *entry)
-{
-	int j;
-
-	for (j = 0; j < NUM_ELEMENTS(log_type_info_tbl); j++) {
-
-		const struct dc_log_type_info *info = &log_type_info_tbl[j];
-
-		if (info->type == entry->type)
-			dm_logger_append(entry, "[%s]\t", info->name);
-	}
-}
-
-
-/* Print everything unread existing in log_buffer to debug console*/
-void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn)
-{
-	char *string_start = &logger->log_buffer[logger->buffer_read_offset];
-
-	if (should_warn)
-		dm_output_to_console(
-			"---------------- FLUSHING LOG BUFFER ----------------\n");
-	while (logger->buffer_read_offset < logger->buffer_write_offset) {
-
-		if (logger->log_buffer[logger->buffer_read_offset] == '\0') {
-			dm_output_to_console("%s", string_start);
-			string_start = logger->log_buffer + logger->buffer_read_offset + 1;
-		}
-		logger->buffer_read_offset++;
-	}
-	if (should_warn)
-		dm_output_to_console(
-			"-------------- END FLUSHING LOG BUFFER --------------\n\n");
-}
-/* ------------------------------------------------------------------------ */
-
-/* Warning: Be careful that 'msg' is null terminated and the total size is
- * less than DAL_LOGGER_BUFFER_MAX_LOG_LINE_SIZE (256) including '\0'
- */
-static bool dal_logger_should_log(
-	struct dal_logger *logger,
-	enum dc_log_type log_type)
-{
-	if (logger->mask & (1 << log_type))
-		return true;
-
-	return false;
-}
-
-static void log_to_debug_console(struct log_entry *entry)
-{
-	struct dal_logger *logger = entry->logger;
-
-	if (logger->flags.bits.ENABLE_CONSOLE == 0)
-		return;
-
-	if (entry->buf_offset) {
-		switch (entry->type) {
-		case LOG_ERROR:
-			dm_error("%s", entry->buf);
-			break;
-		default:
-			dm_output_to_console("%s", entry->buf);
-			break;
-		}
-	}
-}
-
-
-static void log_to_internal_buffer(struct log_entry *entry)
-{
-
-	uint32_t size = entry->buf_offset;
-	struct dal_logger *logger = entry->logger;
-
-	if (logger->flags.bits.ENABLE_BUFFER == 0)
-		return;
-
-	if (logger->log_buffer == NULL)
-		return;
-
-	if (size > 0 && size < logger->log_buffer_size) {
-
-		int buffer_space = logger->log_buffer_size -
-				logger->buffer_write_offset;
-
-		if (logger->buffer_write_offset == logger->buffer_read_offset) {
-			/* Buffer is empty, start writing at beginning */
-			buffer_space = logger->log_buffer_size;
-			logger->buffer_write_offset = 0;
-			logger->buffer_read_offset = 0;
-		}
-
-		if (buffer_space > size) {
-			/* No wrap around, copy 'size' bytes
-			 * from 'entry->buf' to 'log_buffer'
-			 */
-			memmove(logger->log_buffer +
-					logger->buffer_write_offset,
-					entry->buf, size);
-			logger->buffer_write_offset += size;
-
-		} else {
-			/* Not enough room remaining, we should flush
-			 * existing logs */
-
-			/* Flush existing unread logs to console */
-			dm_logger_flush_buffer(logger, true);
-
-			/* Start writing to beginning of buffer */
-			memmove(logger->log_buffer, entry->buf, size);
-			logger->buffer_write_offset = size;
-			logger->buffer_read_offset = 0;
-		}
-
-	}
-}
-
-static void append_entry(
-		struct log_entry *entry,
-		char *buffer,
-		uint32_t buf_size)
-{
-	if (!entry->buf ||
-		entry->buf_offset + buf_size > entry->max_buf_bytes
-	) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	/* Todo: check if off by 1 byte due to \0 anywhere */
-	memmove(entry->buf + entry->buf_offset, buffer, buf_size);
-	entry->buf_offset += buf_size;
-}
-
-
-void dm_logger_write(
-	struct dal_logger *logger,
-	enum dc_log_type log_type,
-	const char *msg,
-	...)
-{
-	if (logger && dal_logger_should_log(logger, log_type)) {
-		uint32_t size;
-		va_list args;
-		char buffer[LOG_MAX_LINE_SIZE];
-		struct log_entry entry;
-
-		va_start(args, msg);
-
-		entry.logger = logger;
-
-		entry.buf = buffer;
-
-		entry.buf_offset = 0;
-		entry.max_buf_bytes = DAL_LOGGER_BUFFER_MAX_SIZE * sizeof(char);
-
-		entry.type = log_type;
-
-		dm_logger_append_heading(&entry);
-
-		size = dm_log_to_buffer(
-			buffer, LOG_MAX_LINE_SIZE - 1, msg, args);
-
-		buffer[entry.buf_offset + size] = '\0';
-		entry.buf_offset += size + 1;
-
-		/* --Flush log_entry buffer-- */
-		/* print to kernel console */
-		log_to_debug_console(&entry);
-		/* log internally for dsat */
-		log_to_internal_buffer(&entry);
-
-		va_end(args);
-	}
-}
-
-/* Same as dm_logger_write, except without open() and close(), which must
- * be done separately.
- */
-void dm_logger_append(
-	struct log_entry *entry,
-	const char *msg,
-	...)
-{
-	va_list args;
-
-	va_start(args, msg);
-	dm_logger_append_va(entry, msg, args);
-	va_end(args);
-}
-
-void dm_logger_append_va(
-	struct log_entry *entry,
-	const char *msg,
-	va_list args)
-{
-	struct dal_logger *logger;
-
-	if (!entry) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	logger = entry->logger;
-
-	if (logger && logger->open_count > 0 &&
-		dal_logger_should_log(logger, entry->type)) {
-
-		uint32_t size;
-		char buffer[LOG_MAX_LINE_SIZE];
-
-		size = dm_log_to_buffer(
-			buffer, LOG_MAX_LINE_SIZE, msg, args);
-
-		if (size < LOG_MAX_LINE_SIZE - 1) {
-			append_entry(entry, buffer, size);
-		} else {
-			append_entry(entry, "LOG_ERROR, line too long\n", 27);
-		}
-	}
-}
-
-void dm_logger_open(
-		struct dal_logger *logger,
-		struct log_entry *entry, /* out */
-		enum dc_log_type log_type)
-{
-	if (!entry) {
-		BREAK_TO_DEBUGGER();
-		return;
-	}
-
-	entry->type = log_type;
-	entry->logger = logger;
-
-	entry->buf = kzalloc(DAL_LOGGER_BUFFER_MAX_SIZE,
-			     GFP_KERNEL);
-
-	entry->buf_offset = 0;
-	entry->max_buf_bytes = DAL_LOGGER_BUFFER_MAX_SIZE * sizeof(char);
-
-	logger->open_count++;
-
-	dm_logger_append_heading(entry);
-}
-
-void dm_logger_close(struct log_entry *entry)
-{
-	struct dal_logger *logger = entry->logger;
-
-	if (logger && logger->open_count > 0) {
-		logger->open_count--;
-	} else {
-		BREAK_TO_DEBUGGER();
-		goto cleanup;
-	}
-
-	/* --Flush log_entry buffer-- */
-	/* print to kernel console */
-	log_to_debug_console(entry);
-	/* log internally for dsat */
-	log_to_internal_buffer(entry);
-
-	/* TODO: Write end heading */
-
-cleanup:
-	if (entry->buf) {
-		kfree(entry->buf);
-		entry->buf = NULL;
-		entry->buf_offset = 0;
-		entry->max_buf_bytes = 0;
-	}
-}
-
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
index fc3f98fb09ea..62435bfc274d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
+++ b/drivers/gpu/drm/amd/display/dc/calcs/calcs_logger.h
@@ -25,10 +25,9 @@
 
 #ifndef _CALCS_CALCS_LOGGER_H_
 #define _CALCS_CALCS_LOGGER_H_
-#define DC_LOGGER \
-	logger
+#define DC_LOGGER ctx->logger
 
-static void print_bw_calcs_dceip(struct dal_logger *logger, const struct bw_calcs_dceip *dceip)
+static void print_bw_calcs_dceip(struct dc_context *ctx, const struct bw_calcs_dceip *dceip)
 {
 
 	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
@@ -122,7 +121,7 @@ static void print_bw_calcs_dceip(struct dal_logger *logger, const struct bw_calc
 
 }
 
-static void print_bw_calcs_vbios(struct dal_logger *logger, const struct bw_calcs_vbios *vbios)
+static void print_bw_calcs_vbios(struct dc_context *ctx, const struct bw_calcs_vbios *vbios)
 {
 
 	DC_LOG_BANDWIDTH_CALCS("#####################################################################");
@@ -181,7 +180,7 @@ static void print_bw_calcs_vbios(struct dal_logger *logger, const struct bw_calc
 
 }
 
-static void print_bw_calcs_data(struct dal_logger *logger, struct bw_calcs_data *data)
+static void print_bw_calcs_data(struct dc_context *ctx, struct bw_calcs_data *data)
 {
 
 	int i, j, k;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
index 2c4e8f0cb2dc..160d11a15eac 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dce_calcs.c
@@ -3010,9 +3010,9 @@ bool bw_calcs(struct dc_context *ctx,
 		struct bw_fixed low_yclk = vbios->low_yclk;
 
 		if (ctx->dc->debug.bandwidth_calcs_trace) {
-			print_bw_calcs_dceip(ctx->logger, dceip);
-			print_bw_calcs_vbios(ctx->logger, vbios);
-			print_bw_calcs_data(ctx->logger, data);
+			print_bw_calcs_dceip(ctx, dceip);
+			print_bw_calcs_vbios(ctx, vbios);
+			print_bw_calcs_data(ctx, data);
 		}
 		calculate_bandwidth(dceip, vbios, data);
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index 815656a5b6bd..cb0be7f6994c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -467,9 +467,6 @@ static void destruct(struct dc *dc)
 	if (dc->ctx->created_bios)
 		dal_bios_parser_destroy(&dc->ctx->dc_bios);
 
-	if (dc->ctx->logger)
-		dal_logger_destroy(&dc->ctx->logger);
-
 	kfree(dc->ctx);
 	dc->ctx = NULL;
 
@@ -492,7 +489,6 @@ static void destruct(struct dc *dc)
 static bool construct(struct dc *dc,
 		const struct dc_init_data *init_params)
 {
-	struct dal_logger *logger;
 	struct dc_context *dc_ctx;
 	struct bw_calcs_dceip *dc_dceip;
 	struct bw_calcs_vbios *dc_vbios;
@@ -557,14 +553,7 @@ static bool construct(struct dc *dc,
 	}
 
 	/* Create logger */
-	logger = dal_logger_create(dc_ctx, init_params->log_mask);
 
-	if (!logger) {
-		/* can *not* call logger. call base driver 'print error' */
-		dm_error("%s: failed to create Logger!\n", __func__);
-		goto fail;
-	}
-	dc_ctx->logger = logger;
 	dc_ctx->dce_environment = init_params->dce_environment;
 
 	dc_version = resource_parse_asic_id(init_params->asic_id);
@@ -983,9 +972,7 @@ bool dc_commit_state(struct dc *dc, struct dc_state *context)
 	for (i = 0; i < context->stream_count; i++) {
 		struct dc_stream_state *stream = context->streams[i];
 
-		dc_stream_log(stream,
-				dc->ctx->logger,
-				LOG_DC);
+		dc_stream_log(dc, stream);
 	}
 
 	result = dc_commit_state_no_check(dc, context);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 3732a1de9d6c..0223f4867e8d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -30,6 +30,8 @@
 #include "ipp.h"
 #include "timing_generator.h"
 
+#define DC_LOGGER dc->ctx->logger
+
 /*******************************************************************************
  * Private functions
  ******************************************************************************/
@@ -317,16 +319,10 @@ bool dc_stream_get_scanoutpos(const struct dc_stream_state *stream,
 	return ret;
 }
 
-
-void dc_stream_log(
-	const struct dc_stream_state *stream,
-	struct dal_logger *dm_logger,
-	enum dc_log_type log_type)
+void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream)
 {
-
-	dm_logger_write(dm_logger,
-			log_type,
-			"core_stream 0x%x: src: %d, %d, %d, %d; dst: %d, %d, %d, %d, colorSpace:%d\n",
+	DC_LOG_DC(
+			"core_stream 0x%p: src: %d, %d, %d, %d; dst: %d, %d, %d, %d, colorSpace:%d\n",
 			stream,
 			stream->src.x,
 			stream->src.y,
@@ -337,21 +333,18 @@ void dc_stream_log(
 			stream->dst.width,
 			stream->dst.height,
 			stream->output_color_space);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tpix_clk_khz: %d, h_total: %d, v_total: %d, pixelencoder:%d, displaycolorDepth:%d\n",
 			stream->timing.pix_clk_khz,
 			stream->timing.h_total,
 			stream->timing.v_total,
 			stream->timing.pixel_encoding,
 			stream->timing.display_color_depth);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tsink name: %s, serial: %d\n",
 			stream->sink->edid_caps.display_name,
 			stream->sink->edid_caps.serial_number);
-	dm_logger_write(dm_logger,
-			log_type,
+	DC_LOG_DC(
 			"\tlink: %d\n",
 			stream->sink->link->link_index);
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index af503e0286a7..64eeb440e3d3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -147,10 +147,7 @@ void dc_commit_updates_for_stream(struct dc *dc,
 /*
  * Log the current stream state.
  */
-void dc_stream_log(
-	const struct dc_stream_state *stream,
-	struct dal_logger *dc_logger,
-	enum dc_log_type log_type);
+void dc_stream_log(const struct dc *dc, const struct dc_stream_state *stream);
 
 uint8_t dc_get_current_stream_count(struct dc *dc);
 struct dc_stream_state *dc_get_stream_at_index(struct dc *dc, uint8_t i);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index c96e526d07bb..03bf9eee9a04 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -77,8 +77,6 @@ struct dc_context {
 	struct dc *dc;
 
 	void *driver_context; /* e.g. amdgpu_device */
-
-	struct dal_logger *logger;
 	void *cgs_device;
 
 	enum dce_environment dce_environment;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 3edaa006bd57..1c902e49a712 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -794,43 +794,38 @@ static bool dce110_validate_bandwidth(
 
 	if (memcmp(&dc->current_state->bw.dce,
 			&context->bw.dce, sizeof(context->bw.dce))) {
-		struct log_entry log_entry;
-		dm_logger_open(
-			dc->ctx->logger,
-			&log_entry,
-			LOG_BANDWIDTH_CALCS);
-		dm_logger_append(&log_entry, "%s: finish,\n"
+
+		DC_LOG_BANDWIDTH_CALCS(
+			"%s: finish,\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d\n"
 			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			"stutMark_b: %d stutMark_a: %d\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n"
+			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
+			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n"
+			,
 			__func__,
 			context->bw.dce.nbp_state_change_wm_ns[0].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[0].a_mark,
 			context->bw.dce.urgent_wm_ns[0].b_mark,
 			context->bw.dce.urgent_wm_ns[0].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[0].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[0].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[0].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].a_mark,
 			context->bw.dce.urgent_wm_ns[1].b_mark,
 			context->bw.dce.urgent_wm_ns[1].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[1].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[1].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[1].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].a_mark,
 			context->bw.dce.urgent_wm_ns[2].b_mark,
 			context->bw.dce.urgent_wm_ns[2].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].b_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].a_mark,
-			context->bw.dce.stutter_mode_enable);
-		dm_logger_append(&log_entry,
-			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
-			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n",
+			context->bw.dce.stutter_mode_enable,
 			context->bw.dce.cpuc_state_change_enable,
 			context->bw.dce.cpup_state_change_enable,
 			context->bw.dce.nbp_state_change_enable,
@@ -840,7 +835,6 @@ static bool dce110_validate_bandwidth(
 			context->bw.dce.sclk_deep_sleep_khz,
 			context->bw.dce.yclk_khz,
 			context->bw.dce.blackout_recovery_time_us);
-		dm_logger_close(&log_entry);
 	}
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 9e1afb11e6ad..30d5b32892d6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -744,43 +744,38 @@ bool dce112_validate_bandwidth(
 
 	if (memcmp(&dc->current_state->bw.dce,
 			&context->bw.dce, sizeof(context->bw.dce))) {
-		struct log_entry log_entry;
-		dm_logger_open(
-			dc->ctx->logger,
-			&log_entry,
-			LOG_BANDWIDTH_CALCS);
-		dm_logger_append(&log_entry, "%s: finish,\n"
+
+		DC_LOG_BANDWIDTH_CALCS(
+			"%s: finish,\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d\n"
 			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			"stutMark_b: %d stutMark_a: %d\n"
+			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
+			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n"
+			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
+			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n"
+			,
 			__func__,
 			context->bw.dce.nbp_state_change_wm_ns[0].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[0].a_mark,
 			context->bw.dce.urgent_wm_ns[0].b_mark,
 			context->bw.dce.urgent_wm_ns[0].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[0].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[0].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[0].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[1].a_mark,
 			context->bw.dce.urgent_wm_ns[1].b_mark,
 			context->bw.dce.urgent_wm_ns[1].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[1].b_mark,
-			context->bw.dce.stutter_exit_wm_ns[1].a_mark);
-		dm_logger_append(&log_entry,
-			"nbpMark_b: %d nbpMark_a: %d urgentMark_b: %d urgentMark_a: %d\n"
-			"stutMark_b: %d stutMark_a: %d stutter_mode_enable: %d\n",
+			context->bw.dce.stutter_exit_wm_ns[1].a_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].b_mark,
 			context->bw.dce.nbp_state_change_wm_ns[2].a_mark,
 			context->bw.dce.urgent_wm_ns[2].b_mark,
 			context->bw.dce.urgent_wm_ns[2].a_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].b_mark,
 			context->bw.dce.stutter_exit_wm_ns[2].a_mark,
-			context->bw.dce.stutter_mode_enable);
-		dm_logger_append(&log_entry,
-			"cstate: %d pstate: %d nbpstate: %d sync: %d dispclk: %d\n"
-			"sclk: %d sclk_sleep: %d yclk: %d blackout_recovery_time_us: %d\n",
+			context->bw.dce.stutter_mode_enable,
 			context->bw.dce.cpuc_state_change_enable,
 			context->bw.dce.cpup_state_change_enable,
 			context->bw.dce.nbp_state_change_enable,
@@ -790,7 +785,6 @@ bool dce112_validate_bandwidth(
 			context->bw.dce.sclk_deep_sleep_khz,
 			context->bw.dce.yclk_khz,
 			context->bw.dce.blackout_recovery_time_us);
-		dm_logger_close(&log_entry);
 	}
 	return result;
 }
diff --git a/drivers/gpu/drm/amd/display/include/logger_interface.h b/drivers/gpu/drm/amd/display/include/logger_interface.h
index 0f10ed710e0d..e3c79616682d 100644
--- a/drivers/gpu/drm/amd/display/include/logger_interface.h
+++ b/drivers/gpu/drm/amd/display/include/logger_interface.h
@@ -40,49 +40,7 @@ struct dc_state;
  *
  */
 
-struct dal_logger *dal_logger_create(struct dc_context *ctx, uint32_t log_mask);
-
-uint32_t dal_logger_destroy(struct dal_logger **logger);
-
-void dm_logger_flush_buffer(struct dal_logger *logger, bool should_warn);
-
-void dm_logger_write(
-		struct dal_logger *logger,
-		enum dc_log_type log_type,
-		const char *msg,
-		...);
-
-void dm_logger_append(
-		struct log_entry *entry,
-		const char *msg,
-		...);
-
-void dm_logger_append_va(
-		struct log_entry *entry,
-		const char *msg,
-		va_list args);
-
-void dm_logger_append_heading(struct log_entry *entry);
-
-void dm_logger_open(
-		struct dal_logger *logger,
-		struct log_entry *entry,
-		enum dc_log_type log_type);
-
-void dm_logger_close(struct log_entry *entry);
-
-void dc_conn_log(struct dc_context *ctx,
-		const struct dc_link *link,
-		uint8_t *hex_data,
-		int hex_data_count,
-		enum dc_log_type event,
-		const char *msg,
-		...);
-
-void logger_write(struct dal_logger *logger,
-		enum dc_log_type log_type,
-		const char *msg,
-		void *paralist);
+void dc_conn_log_hex_linux(const uint8_t *hex_data, int hex_data_count);
 
 void pre_surface_trace(
 		struct dc *dc,
@@ -108,28 +66,31 @@ void context_clock_trace(
  * marked by this macro.
  * Note that the message will be printed exactly once for every function
  * it is used in order to avoid repeating of the same message. */
+
 #define DAL_LOGGER_NOT_IMPL(fmt, ...) \
-{ \
-	static bool print_not_impl = true; \
-\
-	if (print_not_impl == true) { \
-		print_not_impl = false; \
-		dm_logger_write(ctx->logger, LOG_WARNING, \
-		"DAL_NOT_IMPL: " fmt, ##__VA_ARGS__); \
-	} \
-}
+	do { \
+		static bool print_not_impl = true; \
+		if (print_not_impl == true) { \
+			print_not_impl = false; \
+			DRM_WARN("DAL_NOT_IMPL: " fmt, ##__VA_ARGS__); \
+		} \
+	} while (0)
 
 /******************************************************************************
  * Convenience macros to save on typing.
  *****************************************************************************/
 
 #define DC_ERROR(...) \
-	dm_logger_write(dc_ctx->logger, LOG_ERROR, \
-		__VA_ARGS__)
+		do { \
+			(void)(dc_ctx); \
+			DC_LOG_ERROR(__VA_ARGS__); \
+		} while (0)
 
 #define DC_SYNC_INFO(...) \
-	dm_logger_write(dc_ctx->logger, LOG_SYNC, \
-		__VA_ARGS__)
+		do { \
+			(void)(dc_ctx); \
+			DC_LOG_SYNC(__VA_ARGS__); \
+		} while (0)
 
 /* Connectivity log format:
  * [time stamp]   [drm] [Major_minor] [connector name] message.....
@@ -139,20 +100,30 @@ void context_clock_trace(
  */
 
 #define CONN_DATA_DETECT(link, hex_data, hex_len, ...) \
-		dc_conn_log(link->ctx, link, hex_data, hex_len, \
-				LOG_EVENT_DETECTION, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			dc_conn_log_hex_linux(hex_data, hex_len); \
+			DC_LOG_EVENT_DETECTION(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_DATA_LINK_LOSS(link, hex_data, hex_len, ...) \
-		dc_conn_log(link->ctx, link, hex_data, hex_len, \
-				LOG_EVENT_LINK_LOSS, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			dc_conn_log_hex_linux(hex_data, hex_len); \
+			DC_LOG_EVENT_LINK_LOSS(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_MSG_LT(link, ...) \
-		dc_conn_log(link->ctx, link, NULL, 0, \
-				LOG_EVENT_LINK_TRAINING, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			DC_LOG_EVENT_LINK_TRAINING(__VA_ARGS__); \
+		} while (0)
 
 #define CONN_MSG_MODE(link, ...) \
-		dc_conn_log(link->ctx, link, NULL, 0, \
-				LOG_EVENT_MODE_SET, ##__VA_ARGS__)
+		do { \
+			(void)(link); \
+			DC_LOG_EVENT_MODE_SET(__VA_ARGS__); \
+		} while (0)
 
 /*
  * Display Test Next logging
@@ -167,38 +138,21 @@ void context_clock_trace(
 	dm_dtn_log_end(dc_ctx)
 
 #define PERFORMANCE_TRACE_START() \
-	unsigned long long perf_trc_start_stmp = dm_get_timestamp(dc->ctx); \
-	unsigned long long perf_trc_start_log_msk = dc->ctx->logger->mask; \
-	unsigned int perf_trc_start_log_flags = dc->ctx->logger->flags.value; \
-	if (dc->debug.performance_trace) {\
-		dm_logger_flush_buffer(dc->ctx->logger, false);\
-		dc->ctx->logger->mask = 1<<LOG_PERF_TRACE;\
-		dc->ctx->logger->flags.bits.ENABLE_CONSOLE = 0;\
-		dc->ctx->logger->flags.bits.ENABLE_BUFFER = 1;\
-	}
-
-#define PERFORMANCE_TRACE_END() do {\
-	unsigned long long perf_trc_end_stmp = dm_get_timestamp(dc->ctx);\
-	if (dc->debug.performance_trace) {\
-		dm_logger_write(dc->ctx->logger, \
-				LOG_PERF_TRACE, \
-				"%s duration: %d ticks\n", __func__,\
+	unsigned long long perf_trc_start_stmp = dm_get_timestamp(dc->ctx)
+
+#define PERFORMANCE_TRACE_END() \
+	do { \
+		unsigned long long perf_trc_end_stmp = dm_get_timestamp(dc->ctx); \
+		if (dc->debug.performance_trace) { \
+			DC_LOG_PERF_TRACE("%s duration: %lld ticks\n", __func__, \
 				perf_trc_end_stmp - perf_trc_start_stmp); \
-		if (perf_trc_start_log_msk != 1<<LOG_PERF_TRACE) {\
-			dc->ctx->logger->mask = perf_trc_start_log_msk;\
-			dc->ctx->logger->flags.value = perf_trc_start_log_flags;\
-			dm_logger_flush_buffer(dc->ctx->logger, false);\
 		} \
-	} \
-} while (0)
+	} while (0)
 
-#define DISPLAY_STATS_BEGIN(entry) \
-	dm_logger_open(dc->ctx->logger, &entry, LOG_DISPLAYSTATS)
+#define DISPLAY_STATS_BEGIN(entry) (void)(entry)
 
-#define DISPLAY_STATS(msg, ...) \
-	dm_logger_append(&log_entry, msg, ##__VA_ARGS__)
+#define DISPLAY_STATS(msg, ...) DC_LOG_PERF_TRACE(msg, __VA_ARGS__)
 
-#define DISPLAY_STATS_END(entry) \
-	dm_logger_close(&entry)
+#define DISPLAY_STATS_END(entry) (void)(entry)
 
 #endif /* __DAL_LOGGER_INTERFACE_H__ */
diff --git a/drivers/gpu/drm/amd/display/include/logger_types.h b/drivers/gpu/drm/amd/display/include/logger_types.h
index 0a540b9897a6..ad3695e67b76 100644
--- a/drivers/gpu/drm/amd/display/include/logger_types.h
+++ b/drivers/gpu/drm/amd/display/include/logger_types.h
@@ -138,63 +138,4 @@ enum dc_log_type {
 		(1 << LOG_HW_AUDIO)| \
 		(1 << LOG_BANDWIDTH_CALCS)*/
 
-union logger_flags {
-	struct {
-		uint32_t ENABLE_CONSOLE:1; /* Print to console */
-		uint32_t ENABLE_BUFFER:1; /* Print to buffer */
-		uint32_t RESERVED:30;
-	} bits;
-	uint32_t value;
-};
-
-struct log_entry {
-	struct dal_logger *logger;
-	enum dc_log_type type;
-
-	char *buf;
-	uint32_t buf_offset;
-	uint32_t max_buf_bytes;
-};
-
-/**
-* Structure for enumerating log types
-*/
-struct dc_log_type_info {
-	enum dc_log_type type;
-	char name[MAX_NAME_LEN];
-};
-
-/* Structure for keeping track of offsets, buffer, etc */
-
-#define DAL_LOGGER_BUFFER_MAX_SIZE 2048
-
-/*Connectivity log needs to output EDID, which needs at lease 256x3 bytes,
- * change log line size to 896 to meet the request.
- */
-#define LOG_MAX_LINE_SIZE 896
-
-struct dal_logger {
-
-	/* How far into the circular buffer has been read by dsat
-	 * Read offset should never cross write offset. Write \0's to
-	 * read data just to be sure?
-	 */
-	uint32_t buffer_read_offset;
-
-	/* How far into the circular buffer we have written
-	 * Write offset should never cross read offset
-	 */
-	uint32_t buffer_write_offset;
-
-	uint32_t open_count;
-
-	char *log_buffer;	/* Pointer to malloc'ed buffer */
-	uint32_t log_buffer_size; /* Size of circular buffer */
-
-	uint32_t mask; /*array of masks for major elements*/
-
-	union logger_flags flags;
-	struct dc_context *ctx;
-};
-
 #endif /* __DAL_LOGGER_TYPES_H__ */
-- 
cgit v1.2.3


From 4b99affbb30027c8414a9d583777ad5c6439ae12 Mon Sep 17 00:00:00 2001
From: Alvin lee <alvin.lee3@amd.com>
Date: Tue, 19 Jun 2018 15:40:09 -0400
Subject: drm/amd/display: read DP sink and DP branch hardware and firmware
 revision from DPCD

- define new dpcd address in drm
- implement new members in dpcd_caps to store values read from new dpcd address

Signed-off-by: Alvin lee <alvin.lee3@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 25 ++++++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/dc.h              |  5 +++++
 drivers/gpu/drm/amd/display/include/dpcd_defs.h  |  3 +++
 3 files changed, 33 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 84586b679d73..6d4642bf395d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -2262,6 +2262,11 @@ static void get_active_converter_info(
 
 		link->dpcd_caps.branch_hw_revision =
 			dp_hw_fw_revision.ieee_hw_rev;
+
+		memmove(
+			link->dpcd_caps.branch_fw_revision,
+			dp_hw_fw_revision.ieee_fw_rev,
+			sizeof(dp_hw_fw_revision.ieee_fw_rev));
 	}
 }
 
@@ -2317,6 +2322,7 @@ static bool retrieve_link_cap(struct dc_link *link)
 	enum dc_status status = DC_ERROR_UNEXPECTED;
 	uint32_t read_dpcd_retry_cnt = 3;
 	int i;
+	struct dp_sink_hw_fw_revision dp_hw_fw_revision;
 
 	memset(dpcd_data, '\0', sizeof(dpcd_data));
 	memset(&down_strm_port_count,
@@ -2408,6 +2414,25 @@ static bool retrieve_link_cap(struct dc_link *link)
 			(sink_id.ieee_oui[1] << 8) +
 			(sink_id.ieee_oui[2]);
 
+	memmove(
+		link->dpcd_caps.sink_dev_id_str,
+		sink_id.ieee_device_id,
+		sizeof(sink_id.ieee_device_id));
+
+	core_link_read_dpcd(
+		link,
+		DP_SINK_HW_REVISION_START,
+		(uint8_t *)&dp_hw_fw_revision,
+		sizeof(dp_hw_fw_revision));
+
+	link->dpcd_caps.sink_hw_revision =
+		dp_hw_fw_revision.ieee_hw_rev;
+
+	memmove(
+		link->dpcd_caps.sink_fw_revision,
+		dp_hw_fw_revision.ieee_fw_rev,
+		sizeof(dp_hw_fw_revision.ieee_fw_rev));
+
 	/* Connectivity log: detection */
 	CONN_DATA_DETECT(link, dpcd_data, sizeof(dpcd_data), "Rx Caps: ");
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 85533619440a..1b36e763f3b0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -628,9 +628,14 @@ struct dpcd_caps {
 	struct dc_dongle_caps dongle_caps;
 
 	uint32_t sink_dev_id;
+	int8_t sink_dev_id_str[6];
+	int8_t sink_hw_revision;
+	int8_t sink_fw_revision[2];
+
 	uint32_t branch_dev_id;
 	int8_t branch_dev_name[6];
 	int8_t branch_hw_revision;
+	int8_t branch_fw_revision[2];
 
 	bool allow_invalid_MSA_timing_param;
 	bool panel_mode_edp;
diff --git a/drivers/gpu/drm/amd/display/include/dpcd_defs.h b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
index d8e52e3b8e3c..1c66166d0a94 100644
--- a/drivers/gpu/drm/amd/display/include/dpcd_defs.h
+++ b/drivers/gpu/drm/amd/display/include/dpcd_defs.h
@@ -27,6 +27,9 @@
 #define __DAL_DPCD_DEFS_H__
 
 #include <drm/drm_dp_helper.h>
+#ifndef DP_SINK_HW_REVISION_START // can remove this once the define gets into linux drm_dp_helper.h
+#define DP_SINK_HW_REVISION_START 0x409
+#endif
 
 enum dpcd_revision {
 	DPCD_REV_10 = 0x10,
-- 
cgit v1.2.3


From 30cdbfaa6aa469347db7fcda5949f1ccf7559ecf Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 13 Jun 2018 13:58:14 -0400
Subject: drm/amd/display: dcc always on for bw calculations on raven

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c | 19 ++++++++++++++++++-
 1 file changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index e44b8d3d6891..080f777d705e 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -250,7 +250,24 @@ static void pipe_ctx_to_e2e_pipe_params (
 	else if (pipe->bottom_pipe != NULL && pipe->bottom_pipe->plane_state == pipe->plane_state)
 		input->src.is_hsplit = true;
 
-	input->src.dcc                 = pipe->plane_state->dcc.enable;
+	if (pipe->plane_res.dpp->ctx->dc->debug.optimized_watermark) {
+		/*
+		 * this method requires us to always re-calculate watermark when dcc change
+		 * between flip.
+		 */
+		input->src.dcc = pipe->plane_state->dcc.enable ? 1 : 0;
+	} else {
+		/*
+		 * allow us to disable dcc on the fly without re-calculating WM
+		 *
+		 * extra overhead for DCC is quite small.  for 1080p WM without
+		 * DCC is only 0.417us lower (urgent goes from 6.979us to 6.562us)
+		 */
+		unsigned int bpe;
+
+		input->src.dcc = pipe->plane_res.dpp->ctx->dc->res_pool->hubbub->funcs->
+			dcc_support_pixel_format(pipe->plane_state->format, &bpe) ? 1 : 0;
+	}
 	input->src.dcc_rate            = 1;
 	input->src.meta_pitch          = pipe->plane_state->dcc.grph.meta_pitch;
 	input->src.source_scan         = dm_horz;
-- 
cgit v1.2.3


From 0a1d56599b9bb58464a8bf1243191eb32b36b694 Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Tue, 19 Jun 2018 12:14:29 -0400
Subject: drm/amd/display: hook dp test pattern through debugfs

 set PHY layer or Link layer test pattern
 PHY test pattern is used for PHY SI check.
 Link layer test will not affect PHY SI.

 - normal video mode
  0 = DP_TEST_PATTERN_VIDEO_MODE

 - PHY test pattern supported
  1 = DP_TEST_PATTERN_D102
  2 = DP_TEST_PATTERN_SYMBOL_ERROR
  3 = DP_TEST_PATTERN_PRBS7
  4 = DP_TEST_PATTERN_80BIT_CUSTOM
  5 = DP_TEST_PATTERN_CP2520_1
  6 = DP_TEST_PATTERN_CP2520_2 = DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE
  7 = DP_TEST_PATTERN_CP2520_3

 - DP PHY Link Training Patterns
  8 = DP_TEST_PATTERN_TRAINING_PATTERN1
  9 = DP_TEST_PATTERN_TRAINING_PATTERN2
  0xa = DP_TEST_PATTERN_TRAINING_PATTERN3
  0xb = DP_TEST_PATTERN_TRAINING_PATTERN4

 - DP Link Layer Test pattern
  0xc = DP_TEST_PATTERN_COLOR_SQUARES
  0xd = DP_TEST_PATTERN_COLOR_SQUARES_CEA
  0xe = DP_TEST_PATTERN_VERTICAL_BARS
  0xf = DP_TEST_PATTERN_HORIZONTAL_BARS
  0x10= DP_TEST_PATTERN_COLOR_RAMP

 debugfs phy_test_pattern is located at /syskernel/debug/dri/0/DP-x

 --- set test pattern
  echo <test pattern #> > test_pattern

 - custom test pattern
  If test pattern # is not supported, NO HW programming will be done
  for DP_TEST_PATTERN_80BIT_CUSTOM, it needs extra 10 bytes of data
  for the user pattern. input 10 bytes data are separated by space

  echo 0x4 0x11 0x22 0x33 0x44 0x55 0x66 0x77 0x88 0x99 0xaa >
  test_pattern

 --- reset test pattern
  echo 0 > test_pattern

 --- HPD detection is disabled when set PHY test pattern

  when PHY test pattern (pattern # within [1,7]) is set, HPD pin of
  HW ASIC is disable. User could unplug DP display from DP connected
  and plug scope to check test pattern PHY SI.
  If there is need unplug scope and plug DP display back, do steps
  below:
  echo 0 > phy_test_pattern
  unplug scope
  plug DP display.

  "echo 0 > phy_test_pattern" will re-enable HPD pin again so that
  video sw driver could detect "unplug scope" and "plug DP display"

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c  | 222 ++++++++++++++++++++-
 1 file changed, 211 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 9ff8833b52c4..8ddbf219dd23 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -261,18 +261,219 @@ static ssize_t dp_pre_emphasis_debugfs_write(struct file *f, const char __user *
 	return 1;
 }
 
-static ssize_t dp_phy_test_pattern_debugfs_read(struct file *f, char __user *buf,
-				 size_t size, loff_t *pos)
-{
-	/* TODO: create method to read PHY test pattern */
-	return 1;
-}
-
+/* function description
+ *
+ * set PHY layer or Link layer test pattern
+ * PHY test pattern is used for PHY SI check.
+ * Link layer test will not affect PHY SI.
+ *
+ * Reset Test Pattern:
+ * 0 = DP_TEST_PATTERN_VIDEO_MODE
+ *
+ * PHY test pattern supported:
+ * 1 = DP_TEST_PATTERN_D102
+ * 2 = DP_TEST_PATTERN_SYMBOL_ERROR
+ * 3 = DP_TEST_PATTERN_PRBS7
+ * 4 = DP_TEST_PATTERN_80BIT_CUSTOM
+ * 5 = DP_TEST_PATTERN_CP2520_1
+ * 6 = DP_TEST_PATTERN_CP2520_2 = DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE
+ * 7 = DP_TEST_PATTERN_CP2520_3
+ *
+ * DP PHY Link Training Patterns
+ * 8 = DP_TEST_PATTERN_TRAINING_PATTERN1
+ * 9 = DP_TEST_PATTERN_TRAINING_PATTERN2
+ * a = DP_TEST_PATTERN_TRAINING_PATTERN3
+ * b = DP_TEST_PATTERN_TRAINING_PATTERN4
+ *
+ * DP Link Layer Test pattern
+ * c = DP_TEST_PATTERN_COLOR_SQUARES
+ * d = DP_TEST_PATTERN_COLOR_SQUARES_CEA
+ * e = DP_TEST_PATTERN_VERTICAL_BARS
+ * f = DP_TEST_PATTERN_HORIZONTAL_BARS
+ * 10= DP_TEST_PATTERN_COLOR_RAMP
+ *
+ * debugfs phy_test_pattern is located at /syskernel/debug/dri/0/DP-x
+ *
+ * --- set test pattern
+ * echo <test pattern #> > test_pattern
+ *
+ * If test pattern # is not supported, NO HW programming will be done.
+ * for DP_TEST_PATTERN_80BIT_CUSTOM, it needs extra 10 bytes of data
+ * for the user pattern. input 10 bytes data are separated by space
+ *
+ * echo 0x4 0x11 0x22 0x33 0x44 0x55 0x66 0x77 0x88 0x99 0xaa > test_pattern
+ *
+ * --- reset test pattern
+ * echo 0 > test_pattern
+ *
+ * --- HPD detection is disabled when set PHY test pattern
+ *
+ * when PHY test pattern (pattern # within [1,7]) is set, HPD pin of HW ASIC
+ * is disable. User could unplug DP display from DP connected and plug scope to
+ * check test pattern PHY SI.
+ * If there is need unplug scope and plug DP display back, do steps below:
+ * echo 0 > phy_test_pattern
+ * unplug scope
+ * plug DP display.
+ *
+ * "echo 0 > phy_test_pattern" will re-enable HPD pin again so that video sw
+ * driver could detect "unplug scope" and "plug DP display"
+ */
 static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __user *buf,
 				 size_t size, loff_t *pos)
 {
-	/* TODO: create method to write PHY test pattern */
-	return 1;
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	uint32_t wr_buf_size = 100;
+	int r;
+	int bytes_from_user;
+	char *sub_str;
+	uint8_t param_index = 0;
+	long param[11];
+	const char delimiter[3] = {' ', '\n', '\0'};
+	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
+	bool disable_hpd = false;
+	bool valid_test_pattern = false;
+	uint8_t custom_pattern[10] = {0};
+	struct dc_link_settings prefer_link_settings = {LANE_COUNT_UNKNOWN,
+			LINK_RATE_UNKNOWN, LINK_SPREAD_DISABLED};
+	struct dc_link_settings cur_link_settings = {LANE_COUNT_UNKNOWN,
+			LINK_RATE_UNKNOWN, LINK_SPREAD_DISABLED};
+	struct link_training_settings link_training_settings;
+	int i;
+
+	if (size == 0)
+		return 0;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return 0;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		return 0;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	while (isspace(*wr_buf_ptr))
+		wr_buf_ptr++;
+
+	while ((*wr_buf_ptr != '\0') && (param_index < 1)) {
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+		while (isspace(*wr_buf_ptr))
+			wr_buf_ptr++;
+
+		/* DP_TEST_PATTERN_80BIT_CUSTOM need extra 80 bits
+		 * whci are 10 bytes separte by space
+		 */
+		if (param[0] != 0x4)
+			break;
+	}
+
+	test_pattern = param[0];
+
+	switch (test_pattern) {
+	case DP_TEST_PATTERN_VIDEO_MODE:
+	case DP_TEST_PATTERN_COLOR_SQUARES:
+	case DP_TEST_PATTERN_COLOR_SQUARES_CEA:
+	case DP_TEST_PATTERN_VERTICAL_BARS:
+	case DP_TEST_PATTERN_HORIZONTAL_BARS:
+	case DP_TEST_PATTERN_COLOR_RAMP:
+		valid_test_pattern = true;
+		break;
+
+	case DP_TEST_PATTERN_D102:
+	case DP_TEST_PATTERN_SYMBOL_ERROR:
+	case DP_TEST_PATTERN_PRBS7:
+	case DP_TEST_PATTERN_80BIT_CUSTOM:
+	case DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE:
+	case DP_TEST_PATTERN_TRAINING_PATTERN4:
+		disable_hpd = true;
+		valid_test_pattern = true;
+		break;
+
+	default:
+		valid_test_pattern = false;
+		test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
+		break;
+	}
+
+	if (!valid_test_pattern) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Test Pattern Parameters\n");
+		return bytes_from_user;
+	}
+
+	if (test_pattern == DP_TEST_PATTERN_80BIT_CUSTOM) {
+		for (i = 0; i < 10; i++)
+			custom_pattern[i] = (uint8_t) param[i + 1];
+	}
+
+	/* Usage: set DP physical test pattern using debugfs with normal DP
+	 * panel. Then plug out DP panel and connect a scope to measure
+	 * For normal video mode and test pattern generated from CRCT,
+	 * they are visibile to user. So do not disable HPD.
+	 * Video Mode is also set to clear the test pattern, so enable HPD
+	 * because it might have been disabled after a test pattern was set.
+	 * AUX depends on HPD * sequence dependent, do not move!
+	 */
+	if (!disable_hpd)
+		dc_link_enable_hpd(link);
+
+	prefer_link_settings.lane_count = link->verified_link_cap.lane_count;
+	prefer_link_settings.link_rate = link->verified_link_cap.link_rate;
+	prefer_link_settings.link_spread = link->verified_link_cap.link_spread;
+
+	cur_link_settings.lane_count = link->cur_link_settings.lane_count;
+	cur_link_settings.link_rate = link->cur_link_settings.link_rate;
+	cur_link_settings.link_spread = link->cur_link_settings.link_spread;
+
+	link_training_settings.link_settings = cur_link_settings;
+
+
+	if (test_pattern != DP_TEST_PATTERN_VIDEO_MODE) {
+		if (prefer_link_settings.lane_count != LANE_COUNT_UNKNOWN &&
+			prefer_link_settings.link_rate !=  LINK_RATE_UNKNOWN &&
+			(prefer_link_settings.lane_count != cur_link_settings.lane_count ||
+			prefer_link_settings.link_rate != cur_link_settings.link_rate))
+			link_training_settings.link_settings = prefer_link_settings;
+	}
+
+	for (i = 0; i < (unsigned int)(link_training_settings.link_settings.lane_count); i++)
+		link_training_settings.lane_settings[i] = link->cur_lane_setting;
+
+	dc_link_set_test_pattern(
+		link,
+		test_pattern,
+		&link_training_settings,
+		custom_pattern,
+		10);
+
+	/* Usage: Set DP physical test pattern using AMDDP with normal DP panel
+	 * Then plug out DP panel and connect a scope to measure DP PHY signal.
+	 * Need disable interrupt to avoid SW driver disable DP output. This is
+	 * done after the test pattern is set.
+	 */
+	if (valid_test_pattern && disable_hpd)
+		dc_link_disable_hpd(link);
+
+	kfree(wr_buf);
+
+	return bytes_from_user;
 }
 
 static const struct file_operations dp_link_settings_debugfs_fops = {
@@ -298,7 +499,6 @@ static const struct file_operations dp_pre_emphasis_fops = {
 
 static const struct file_operations dp_phy_test_pattern_fops = {
 	.owner = THIS_MODULE,
-	.read = dp_phy_test_pattern_debugfs_read,
 	.write = dp_phy_test_pattern_debugfs_write,
 	.llseek = default_llseek
 };
@@ -310,7 +510,7 @@ static const struct {
 		{"link_settings", &dp_link_settings_debugfs_fops},
 		{"voltage_swing", &dp_voltage_swing_fops},
 		{"pre_emphasis", &dp_pre_emphasis_fops},
-		{"phy_test_pattern", &dp_phy_test_pattern_fops}
+		{"test_pattern", &dp_phy_test_pattern_fops}
 };
 
 int connector_debugfs_init(struct amdgpu_dm_connector *connector)
-- 
cgit v1.2.3


From 05541913a97053e58669ea5817fa5000b836f834 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 13 Jun 2018 13:52:53 -0400
Subject: drm/amd/display: remove dentist_vco_freq from resource_pool

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/inc/core_types.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 00d728e629fa..1db26bc0bec3 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -148,7 +148,6 @@ struct resource_pool {
 	unsigned int underlay_pipe_index;
 	unsigned int stream_enc_count;
 	unsigned int ref_clock_inKhz;
-	unsigned int dentist_vco_freq_khz;
 	unsigned int timing_generator_count;
 
 	/*
-- 
cgit v1.2.3


From 793d4d087f9ff365031a62b30d6578686ae1765b Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 20 Jun 2018 11:40:15 -0400
Subject: drm/amd/display: drop unused register defines

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 7ce0a54e548f..8a6b2d328467 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -44,18 +44,14 @@
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPREFCLK_WDIVIDER, mask_sh)
 
 #define CLK_COMMON_MASK_SH_LIST_DCN_COMMON_BASE(mask_sh) \
-	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_WDIVIDER, mask_sh),\
 	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_WDIVIDER, mask_sh),\
-	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh),\
-	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DPPCLK_CHG_DONE, mask_sh)
+	CLK_SF(DENTIST_DISPCLK_CNTL, DENTIST_DISPCLK_CHG_DONE, mask_sh)
 
 #define CLK_REG_FIELD_LIST(type) \
 	type DPREFCLK_SRC_SEL; \
 	type DENTIST_DPREFCLK_WDIVIDER; \
 	type DENTIST_DISPCLK_WDIVIDER; \
-	type DENTIST_DPPCLK_WDIVIDER; \
-	type DENTIST_DISPCLK_CHG_DONE; \
-	type DENTIST_DPPCLK_CHG_DONE;
+	type DENTIST_DISPCLK_CHG_DONE;
 
 struct dccg_shift {
 	CLK_REG_FIELD_LIST(uint8_t)
-- 
cgit v1.2.3


From 39a9f4d89e123b62c8a5cc26696ea8afa98e0e88 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Tue, 19 Jun 2018 15:49:02 -0400
Subject: drm/amd/display: add additional info for cursor position programming

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h                | 5 +++--
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 7 ++++---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c            | 4 ++--
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c           | 4 ++--
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c   | 7 ++++---
 5 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 00afd07a852e..5e80bc1a88c4 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -404,9 +404,10 @@ struct dc_cursor_position {
 struct dc_cursor_mi_param {
 	unsigned int pixel_clk_khz;
 	unsigned int ref_clk_khz;
-	unsigned int viewport_x_start;
-	unsigned int viewport_width;
+	struct rect viewport;
 	struct fixed31_32 h_scale_ratio;
+	struct fixed31_32 v_scale_ratio;
+	enum dc_rotation_angle rotation;
 };
 
 /* IPP related types */
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index bf4df34bc1df..5b41cbe06f59 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2801,9 +2801,10 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	struct dc_cursor_mi_param param = {
 		.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz,
 		.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz,
-		.viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x,
-		.viewport_width = pipe_ctx->plane_res.scl_data.viewport.width,
-		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz
+		.viewport = pipe_ctx->plane_res.scl_data.viewport,
+		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
+		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
+		.rotation = pipe_ctx->plane_state->rotation
 	};
 
 	if (pipe_ctx->plane_state->address.type
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index 742fd497ed00..a558efa9b34a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -445,10 +445,10 @@ void dpp1_set_cursor_position(
 		uint32_t width)
 {
 	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
-	int src_x_offset = pos->x - pos->x_hotspot - param->viewport_x_start;
+	int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x;
 	uint32_t cur_en = pos->enable ? 1 : 0;
 
-	if (src_x_offset >= (int)param->viewport_width)
+	if (src_x_offset >= (int)param->viewport.width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
 	if (src_x_offset + (int)width <= 0)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 9eb60a013f4c..617fd30b1161 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -1083,7 +1083,7 @@ void hubp1_cursor_set_position(
 		const struct dc_cursor_mi_param *param)
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
-	int src_x_offset = pos->x - pos->x_hotspot - param->viewport_x_start;
+	int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x;
 	uint32_t cur_en = pos->enable ? 1 : 0;
 	uint32_t dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0;
 
@@ -1107,7 +1107,7 @@ void hubp1_cursor_set_position(
 				dc_fixpt_from_int(dst_x_offset),
 				param->h_scale_ratio));
 
-	if (src_x_offset >= (int)param->viewport_width)
+	if (src_x_offset >= (int)param->viewport.width)
 		cur_en = 0;  /* not visible beyond right edge*/
 
 	if (src_x_offset + (int)hubp->curs_attr.width <= 0)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 3b2cb2d3b8a6..2938364fd2f0 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2520,9 +2520,10 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 	struct dc_cursor_mi_param param = {
 		.pixel_clk_khz = pipe_ctx->stream->timing.pix_clk_khz,
 		.ref_clk_khz = pipe_ctx->stream->ctx->dc->res_pool->ref_clock_inKhz,
-		.viewport_x_start = pipe_ctx->plane_res.scl_data.viewport.x,
-		.viewport_width = pipe_ctx->plane_res.scl_data.viewport.width,
-		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz
+		.viewport = pipe_ctx->plane_res.scl_data.viewport,
+		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
+		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
+		.rotation = pipe_ctx->plane_state->rotation
 	};
 
 	if (pipe_ctx->plane_state->address.type
-- 
cgit v1.2.3


From ff58798725ba9c747cd934e2623f7a0610b3f0dd Mon Sep 17 00:00:00 2001
From: Hugo Hu <hugo.hu@amd.com>
Date: Fri, 15 Jun 2018 15:49:55 -0400
Subject: drm/amd/display: Patch for extend time to panel poweron.

[WHY]
In eDP spec, the min duration in LCDVDD on-off-on sequence should be
500ms, some BOE panels need 700ms to pass.
[HOW]
Add patch to wait more time when eDP power on.

Signed-off-by: Hugo Hu <hugo.hu@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_types.h                   | 1 +
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 9 ++++++---
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_types.h b/drivers/gpu/drm/amd/display/dc/dc_types.h
index 03bf9eee9a04..8c6eb78b0c3b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_types.h
@@ -192,6 +192,7 @@ union display_content_support {
 
 struct dc_panel_patch {
 	unsigned int dppowerup_delay;
+	unsigned int extra_t12_ms;
 };
 
 struct dc_edid_caps {
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 5b41cbe06f59..7227cfddb352 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -871,10 +871,13 @@ void hwss_edp_power_control(
 			unsigned long long wait_time_ms = 0;
 
 			/* max 500ms from LCDVDD off to on */
+			unsigned long long edp_poweroff_time_ms =
+					500 + link->local_sink->edid_caps.panel_patch.extra_t12_ms;
+
 			if (link->link_trace.time_stamp.edp_poweroff == 0)
-				wait_time_ms = 500;
-			else if (duration_in_ms < 500)
-				wait_time_ms = 500 - duration_in_ms;
+				wait_time_ms = edp_poweroff_time_ms;
+			else if (duration_in_ms < edp_poweroff_time_ms)
+				wait_time_ms = edp_poweroff_time_ms - duration_in_ms;
 
 			if (wait_time_ms) {
 				msleep(wait_time_ms);
-- 
cgit v1.2.3


From f8ac2cf78f276b4d9fc0bc6b90f5e3560caa11de Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Fri, 15 Jun 2018 10:32:50 -0400
Subject: drm/amd/display: Linux set/read lane settings through debugfs

 function: get current DP PHY settings: voltage swing, pre-emphasis,
 post-cursor2 (defined by VESA DP specification)

 valid values:  voltage swing: 0,1,2,3  pre-emphasis : 0,1,2,3
 post cursor2 : 0,1,2,3

 debugfs file phy_setings is located at  /sys/kernel/debug/dri/0/DP-x

 there will be directories, like DP-1, DP-2,DP-3, etc. for DP display

 --- to figure out which DP-x is the display for DP to be check,
 cd DP-x
 ls -ll
 There should be debugfs file, like link_settings, phy_settings.
 cat link_settings
 from lane_count, link_rate to figure which DP-x is for display to be
 worked on

 --- to get current DP PHY settings,
 cat phy_settings

 --- to change DP PHY settings,
 echo <voltage_swing> <pre-emphasis> <post_cursor2> > phy_settings

 for examle, to change voltage swing to 2, pre-emphasis to 3,
 post_cursor2 to 0,
 echo 2 3 0 > phy_settings

 ---  to check if change be applied, get current phy settings by
 cat phy_settings

 ---  in case invalid values are set by user, like
 echo 1 4 0 > phy_settings

 HW will NOT be programmed by these settings.

cat phy_settings will show the previous valid settings.

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Reviewed-by: Hersen Wu <hersenxs.wu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c  | 266 ++++++++++++++++-----
 1 file changed, 207 insertions(+), 59 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 8ddbf219dd23..f20ba9d1c9e2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -26,7 +26,6 @@
 #include <linux/debugfs.h>
 
 #include "dc.h"
-
 #include "amdgpu.h"
 #include "amdgpu_dm.h"
 #include "amdgpu_dm_debugfs.h"
@@ -46,7 +45,7 @@
  *
  * --- to get dp configuration
  *
- * xxd -l 300 phy_settings
+ * cat link_settings
  *
  * It will list current, verified, reported, preferred dp configuration.
  * current -- for current video mode
@@ -56,7 +55,7 @@
  *
  * --- set (or force) dp configuration
  *
- * echo <lane_count>  <link_rate>
+ * echo <lane_count>  <link_rate> > link_settings
  *
  * for example, to force to  2 lane, 2.7GHz,
  * echo 4 0xa > link_settings
@@ -67,7 +66,7 @@
  * done. please check link settings after force operation to see if HW get
  * programming.
  *
- * xxd -l 300 link_settings
+ * cat link_settings
  *
  * check current and preferred settings.
  *
@@ -79,13 +78,13 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
 	struct dc_link *link = connector->dc_link;
 	char *rd_buf = NULL;
 	char *rd_buf_ptr = NULL;
-	uint32_t rd_buf_size = 320;
-	int bytes_to_user;
+	const uint32_t rd_buf_size = 100;
+	uint32_t result = 0;
 	uint8_t str_len = 0;
 	int r;
 
-	if (size == 0)
-		return 0;
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
 
 	rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
 	if (!rd_buf)
@@ -98,39 +97,44 @@ static ssize_t dp_link_settings_read(struct file *f, char __user *buf,
 			link->cur_link_settings.lane_count,
 			link->cur_link_settings.link_rate,
 			link->cur_link_settings.link_spread);
-	rd_buf_ptr = rd_buf_ptr + str_len;
+	rd_buf_ptr += str_len;
 
 	str_len = strlen("Verified:  %d  %d  %d  ");
 	snprintf(rd_buf_ptr, str_len, "Verified:  %d  %d  %d  ",
 			link->verified_link_cap.lane_count,
 			link->verified_link_cap.link_rate,
 			link->verified_link_cap.link_spread);
-	rd_buf_ptr = rd_buf_ptr + str_len;
+	rd_buf_ptr += str_len;
 
 	str_len = strlen("Reported:  %d  %d  %d  ");
 	snprintf(rd_buf_ptr, str_len, "Reported:  %d  %d  %d  ",
 			link->reported_link_cap.lane_count,
 			link->reported_link_cap.link_rate,
 			link->reported_link_cap.link_spread);
-	rd_buf_ptr = rd_buf_ptr + str_len;
+	rd_buf_ptr += str_len;
 
 	str_len = strlen("Preferred:  %d  %d  %d  ");
-	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d  ",
+	snprintf(rd_buf_ptr, str_len, "Preferred:  %d  %d  %d\n",
 			link->preferred_link_setting.lane_count,
 			link->preferred_link_setting.link_rate,
 			link->preferred_link_setting.link_spread);
 
-	r = copy_to_user(buf, rd_buf, rd_buf_size);
+	while (size) {
+		if (*pos >= rd_buf_size)
+			break;
 
-	bytes_to_user = rd_buf_size - r;
+		r = put_user(*(rd_buf + result), buf);
+		if (r)
+			return r; /* r = -EFAULT */
 
-	if (r > rd_buf_size) {
-		bytes_to_user = 0;
-		DRM_DEBUG_DRIVER("data not copy to user");
+		buf += 1;
+		size -= 1;
+		*pos += 1;
+		result += 1;
 	}
 
 	kfree(rd_buf);
-	return bytes_to_user;
+	return result;
 }
 
 static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
@@ -142,7 +146,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 	struct dc_link_settings prefer_link_settings;
 	char *wr_buf = NULL;
 	char *wr_buf_ptr = NULL;
-	uint32_t wr_buf_size = 40;
+	const uint32_t wr_buf_size = 40;
 	int r;
 	int bytes_from_user;
 	char *sub_str;
@@ -153,11 +157,11 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 	bool valid_input = false;
 
 	if (size == 0)
-		return 0;
+		return -EINVAL;
 
 	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
 	if (!wr_buf)
-		return 0;
+		return -EINVAL;
 	wr_buf_ptr = wr_buf;
 
 	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
@@ -166,7 +170,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 	if (r >= wr_buf_size) {
 		kfree(wr_buf);
 		DRM_DEBUG_DRIVER("user data not read\n");
-		return 0;
+		return -EINVAL;
 	}
 
 	bytes_from_user = wr_buf_size - r;
@@ -181,16 +185,13 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 		r = kstrtol(sub_str, 16, &param[param_index]);
 
 		if (r)
-			DRM_DEBUG_DRIVER(" -EINVAL convert error happens!\n");
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
 
 		param_index++;
 		while (isspace(*wr_buf_ptr))
 			wr_buf_ptr++;
 	}
 
-	DRM_DEBUG_DRIVER("Lane_count:  %lx\n", param[0]);
-	DRM_DEBUG_DRIVER("link_rate:  %lx\n", param[1]);
-
 	switch (param[0]) {
 	case LANE_COUNT_ONE:
 	case LANE_COUNT_TWO:
@@ -213,9 +214,10 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 		break;
 	}
 
-	if (!valid_input) {
+	if (!valid_input || (param[0] > link->reported_link_cap.lane_count) ||
+			(param[1] > link->reported_link_cap.link_rate)) {
 		kfree(wr_buf);
-		DRM_DEBUG_DRIVER("Invalid Input value  exceed  No HW will be programmed\n");
+		DRM_DEBUG_DRIVER("Invalid Input value No HW will be programmed\n");
 		return bytes_from_user;
 	}
 
@@ -229,36 +231,190 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 	dc_link_set_preferred_link_settings(dc, &prefer_link_settings, link);
 
 	kfree(wr_buf);
-
 	return bytes_from_user;
 }
 
-static ssize_t dp_voltage_swing_debugfs_read(struct file *f, char __user *buf,
+/* function: get current DP PHY settings: voltage swing, pre-emphasis,
+ * post-cursor2 (defined by VESA DP specification)
+ *
+ * valid values
+ * voltage swing: 0,1,2,3
+ * pre-emphasis : 0,1,2,3
+ * post cursor2 : 0,1,2,3
+ *
+ *
+ * how to use this debugfs
+ *
+ * debugfs is located at /sys/kernel/debug/dri/0/DP-x
+ *
+ * there will be directories, like DP-1, DP-2,DP-3, etc. for DP display
+ *
+ * To figure out which DP-x is the display for DP to be check,
+ * cd DP-x
+ * ls -ll
+ * There should be debugfs file, like link_settings, phy_settings.
+ * cat link_settings
+ * from lane_count, link_rate to figure which DP-x is for display to be worked
+ * on
+ *
+ * To get current DP PHY settings,
+ * cat phy_settings
+ *
+ * To change DP PHY settings,
+ * echo <voltage_swing> <pre-emphasis> <post_cursor2> > phy_settings
+ * for examle, to change voltage swing to 2, pre-emphasis to 3, post_cursor2 to
+ * 0,
+ * echo 2 3 0 > phy_settings
+ *
+ * To check if change be applied, get current phy settings by
+ * cat phy_settings
+ *
+ * In case invalid values are set by user, like
+ * echo 1 4 0 > phy_settings
+ *
+ * HW will NOT be programmed by these settings.
+ * cat phy_settings will show the previous valid settings.
+ */
+static ssize_t dp_phy_settings_read(struct file *f, char __user *buf,
 				 size_t size, loff_t *pos)
 {
-	/* TODO: create method to read voltage swing */
-	return 1;
-}
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	char *rd_buf = NULL;
+	const uint32_t rd_buf_size = 20;
+	uint32_t result = 0;
+	int r;
 
-static ssize_t dp_voltage_swing_debugfs_write(struct file *f, const char __user *buf,
-				 size_t size, loff_t *pos)
-{
-	/* TODO: create method to write voltage swing */
-	return 1;
-}
+	if (*pos & 3 || size & 3)
+		return -EINVAL;
 
-static ssize_t dp_pre_emphasis_debugfs_read(struct file *f, char __user *buf,
-				 size_t size, loff_t *pos)
-{
-	/* TODO: create method to read pre-emphasis */
-	return 1;
+	rd_buf = kcalloc(rd_buf_size, sizeof(char), GFP_KERNEL);
+	if (!rd_buf)
+		return -EINVAL;
+
+	snprintf(rd_buf, rd_buf_size, "  %d  %d  %d  ",
+			link->cur_lane_setting.VOLTAGE_SWING,
+			link->cur_lane_setting.PRE_EMPHASIS,
+			link->cur_lane_setting.POST_CURSOR2);
+
+	while (size) {
+		if (*pos >= rd_buf_size)
+			break;
+
+		r = put_user((*(rd_buf + result)), buf);
+		if (r)
+			return r; /* r = -EFAULT */
+
+		buf += 1;
+		size -= 1;
+		*pos += 1;
+		result += 1;
+	}
+
+	kfree(rd_buf);
+	return result;
 }
 
-static ssize_t dp_pre_emphasis_debugfs_write(struct file *f, const char __user *buf,
+static ssize_t dp_phy_settings_write(struct file *f, const char __user *buf,
 				 size_t size, loff_t *pos)
 {
-	/* TODO: create method to write pre-emphasis */
-	return 1;
+	struct amdgpu_dm_connector *connector = file_inode(f)->i_private;
+	struct dc_link *link = connector->dc_link;
+	struct dc *dc = (struct dc *)link->dc;
+	char *wr_buf = NULL;
+	char *wr_buf_ptr = NULL;
+	uint32_t wr_buf_size = 40;
+	int r;
+	int bytes_from_user;
+	char *sub_str;
+	uint8_t param_index = 0;
+	long param[3];
+	const char delimiter[3] = {' ', '\n', '\0'};
+	bool use_prefer_link_setting;
+	struct link_training_settings link_lane_settings;
+
+	if (size == 0)
+		return 0;
+
+	wr_buf = kcalloc(wr_buf_size, sizeof(char), GFP_KERNEL);
+	if (!wr_buf)
+		return 0;
+	wr_buf_ptr = wr_buf;
+
+	r = copy_from_user(wr_buf_ptr, buf, wr_buf_size);
+
+	/* r is bytes not be copied */
+	if (r >= wr_buf_size) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("user data not be read\n");
+		return 0;
+	}
+
+	bytes_from_user = wr_buf_size - r;
+
+	while (isspace(*wr_buf_ptr))
+		wr_buf_ptr++;
+
+	while ((*wr_buf_ptr != '\0') && (param_index < 3)) {
+
+		sub_str = strsep(&wr_buf_ptr, delimiter);
+
+		r = kstrtol(sub_str, 16, &param[param_index]);
+
+		if (r)
+			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
+
+		param_index++;
+		while (isspace(*wr_buf_ptr))
+			wr_buf_ptr++;
+	}
+
+	if ((param[0] > VOLTAGE_SWING_MAX_LEVEL) ||
+			(param[1] > PRE_EMPHASIS_MAX_LEVEL) ||
+			(param[2] > POST_CURSOR2_MAX_LEVEL)) {
+		kfree(wr_buf);
+		DRM_DEBUG_DRIVER("Invalid Input No HW will be programmed\n");
+		return bytes_from_user;
+	}
+
+	/* get link settings: lane count, link rate */
+	use_prefer_link_setting =
+		((link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN) &&
+		(link->test_pattern_enabled));
+
+	memset(&link_lane_settings, 0, sizeof(link_lane_settings));
+
+	if (use_prefer_link_setting) {
+		link_lane_settings.link_settings.lane_count =
+				link->preferred_link_setting.lane_count;
+		link_lane_settings.link_settings.link_rate =
+				link->preferred_link_setting.link_rate;
+		link_lane_settings.link_settings.link_spread =
+				link->preferred_link_setting.link_spread;
+	} else {
+		link_lane_settings.link_settings.lane_count =
+				link->cur_link_settings.lane_count;
+		link_lane_settings.link_settings.link_rate =
+				link->cur_link_settings.link_rate;
+		link_lane_settings.link_settings.link_spread =
+				link->cur_link_settings.link_spread;
+	}
+
+	/* apply phy settings from user */
+	for (r = 0; r < link_lane_settings.link_settings.lane_count; r++) {
+		link_lane_settings.lane_settings[r].VOLTAGE_SWING =
+				(enum dc_voltage_swing) (param[0]);
+		link_lane_settings.lane_settings[r].PRE_EMPHASIS =
+				(enum dc_pre_emphasis) (param[1]);
+		link_lane_settings.lane_settings[r].POST_CURSOR2 =
+				(enum dc_post_cursor2) (param[2]);
+	}
+
+	/* program ASIC registers and DPCD registers */
+	dc_link_set_drive_settings(dc, &link_lane_settings, link);
+
+	kfree(wr_buf);
+	return bytes_from_user;
 }
 
 /* function description
@@ -483,17 +639,10 @@ static const struct file_operations dp_link_settings_debugfs_fops = {
 	.llseek = default_llseek
 };
 
-static const struct file_operations dp_voltage_swing_fops = {
-	.owner = THIS_MODULE,
-	.read = dp_voltage_swing_debugfs_read,
-	.write = dp_voltage_swing_debugfs_write,
-	.llseek = default_llseek
-};
-
-static const struct file_operations dp_pre_emphasis_fops = {
+static const struct file_operations dp_phy_settings_debugfs_fop = {
 	.owner = THIS_MODULE,
-	.read = dp_pre_emphasis_debugfs_read,
-	.write = dp_pre_emphasis_debugfs_write,
+	.read = dp_phy_settings_read,
+	.write = dp_phy_settings_write,
 	.llseek = default_llseek
 };
 
@@ -508,8 +657,7 @@ static const struct {
 	const struct file_operations *fops;
 } dp_debugfs_entries[] = {
 		{"link_settings", &dp_link_settings_debugfs_fops},
-		{"voltage_swing", &dp_voltage_swing_fops},
-		{"pre_emphasis", &dp_pre_emphasis_fops},
+		{"phy_settings", &dp_phy_settings_debugfs_fop},
 		{"test_pattern", &dp_phy_test_pattern_fops}
 };
 
-- 
cgit v1.2.3


From 1a2eaed80a0bd19f69da880d87f037f5829fb664 Mon Sep 17 00:00:00 2001
From: "Leo (Sunpeng) Li" <sunpeng.li@amd.com>
Date: Mon, 18 Jun 2018 12:23:03 -0400
Subject: drm/amd/display: Fix compile error on older GCC versions

GCC 4.9 reports a 'missing braces around initializer' error. This is a
bug, documented here:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=53119

Fix it by adding another brace.

Signed-off-by: Leo (Sunpeng) Li <sunpeng.li@amd.com>
Reviewed-by: Mikita Lipski <Mikita.Lipski@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 7b51b8fde3fe..59b113d11f66 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -514,8 +514,8 @@ enum dc_edid_status dm_helpers_read_local_edid(
 				edid_status,
 				aconnector->base.name);
 	if (link->aux_mode) {
-		union test_request test_request = {0};
-		union test_response test_response = {0};
+		union test_request test_request = { {0} };
+		union test_response test_response = { {0} };
 
 		dm_helpers_dp_read_dpcd(ctx,
 					link,
-- 
cgit v1.2.3


From abfa99f4d2f1d1a0018f8f39fc1958eda6a48dde Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Thu, 21 Jun 2018 17:57:51 -0400
Subject: drm/amd/display: add missing mask for dcn

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Wesley Chalmers <Wesley.Chalmers@amd.com>
Reviewed-by: Duke Du <Duke.Du@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
index df3203a1d278..64dc75378541 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_hwseq.h
@@ -364,7 +364,8 @@ struct dce_hwseq_registers {
 	HWSEQ_PIXEL_RATE_MASK_SH_LIST(mask_sh, OTG0_),\
 	HWS_SF1(OTG0_, PHYPLL_PIXEL_RATE_CNTL, PHYPLL_PIXEL_RATE_SOURCE, mask_sh), \
 	HWS_SF(, DCHUBBUB_GLOBAL_TIMER_CNTL, DCHUBBUB_GLOBAL_TIMER_ENABLE, mask_sh), \
-	HWS_SF(, DCFCLK_CNTL, DCFCLK_GATE_DIS, mask_sh)
+	HWS_SF(, DCFCLK_CNTL, DCFCLK_GATE_DIS, mask_sh), \
+	HWS_SF(, DC_MEM_GLOBAL_PWR_REQ_CNTL, DC_MEM_GLOBAL_PWR_REQ_DIS, mask_sh)
 
 #define HWSEQ_DCN1_MASK_SH_LIST(mask_sh)\
 	HWSEQ_DCN_MASK_SH_LIST(mask_sh), \
-- 
cgit v1.2.3


From 613cb725dc6cb6039b37d2b71c90a70d49780ce5 Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Thu, 21 Jun 2018 21:32:36 -0400
Subject: drm/amd/display: set default GPIO_ID_HPD

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
index ab5483c0c502..f20161c5706d 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
@@ -375,6 +375,7 @@ struct gpio *dal_gpio_create_irq(
 	case GPIO_ID_GPIO_PAD:
 	break;
 	default:
+		id = GPIO_ID_HPD;
 		ASSERT_CRITICAL(false);
 		return NULL;
 	}
-- 
cgit v1.2.3


From 08ed681c8453c2934136bcc3b30bca4dee8a5fca Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 21 Jun 2018 13:33:41 -0400
Subject: drm/amd/display: add dcn cursor hotsport rotation and mirror support

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h         |  1 +
 .../drm/amd/display/dc/dce110/dce110_hw_sequencer.c  |  3 ++-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c    | 20 +++++++++++++++++---
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c    |  3 ++-
 4 files changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 5e80bc1a88c4..da787e279319 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -408,6 +408,7 @@ struct dc_cursor_mi_param {
 	struct fixed31_32 h_scale_ratio;
 	struct fixed31_32 v_scale_ratio;
 	enum dc_rotation_angle rotation;
+	bool mirror;
 };
 
 /* IPP related types */
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 7227cfddb352..109d4103d10d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2807,7 +2807,8 @@ void dce110_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		.viewport = pipe_ctx->plane_res.scl_data.viewport,
 		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
 		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
-		.rotation = pipe_ctx->plane_state->rotation
+		.rotation = pipe_ctx->plane_state->rotation,
+		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
 
 	if (pipe_ctx->plane_state->address.type
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 617fd30b1161..5c4ad8a67e62 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -1084,8 +1084,10 @@ void hubp1_cursor_set_position(
 {
 	struct dcn10_hubp *hubp1 = TO_DCN10_HUBP(hubp);
 	int src_x_offset = pos->x - pos->x_hotspot - param->viewport.x;
+	int x_hotspot = pos->x_hotspot;
+	int y_hotspot = pos->y_hotspot;
+	uint32_t dst_x_offset;
 	uint32_t cur_en = pos->enable ? 1 : 0;
-	uint32_t dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0;
 
 	/*
 	 * Guard aganst cursor_set_position() from being called with invalid
@@ -1097,6 +1099,18 @@ void hubp1_cursor_set_position(
 	if (hubp->curs_attr.address.quad_part == 0)
 		return;
 
+	if (param->rotation == ROTATION_ANGLE_90 || param->rotation == ROTATION_ANGLE_270) {
+		src_x_offset = pos->y - pos->y_hotspot - param->viewport.x;
+		y_hotspot = pos->x_hotspot;
+		x_hotspot = pos->y_hotspot;
+	}
+
+	if (param->mirror) {
+		x_hotspot = param->viewport.width - x_hotspot;
+		src_x_offset = param->viewport.x + param->viewport.width - src_x_offset;
+	}
+
+	dst_x_offset = (src_x_offset >= 0) ? src_x_offset : 0;
 	dst_x_offset *= param->ref_clk_khz;
 	dst_x_offset /= param->pixel_clk_khz;
 
@@ -1124,8 +1138,8 @@ void hubp1_cursor_set_position(
 			CURSOR_Y_POSITION, pos->y);
 
 	REG_SET_2(CURSOR_HOT_SPOT, 0,
-			CURSOR_HOT_SPOT_X, pos->x_hotspot,
-			CURSOR_HOT_SPOT_Y, pos->y_hotspot);
+			CURSOR_HOT_SPOT_X, x_hotspot,
+			CURSOR_HOT_SPOT_Y, y_hotspot);
 
 	REG_SET(CURSOR_DST_OFFSET, 0,
 			CURSOR_DST_X_OFFSET, dst_x_offset);
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 2938364fd2f0..944275a50c0a 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2523,7 +2523,8 @@ static void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
 		.viewport = pipe_ctx->plane_res.scl_data.viewport,
 		.h_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.horz,
 		.v_scale_ratio = pipe_ctx->plane_res.scl_data.ratios.vert,
-		.rotation = pipe_ctx->plane_state->rotation
+		.rotation = pipe_ctx->plane_state->rotation,
+		.mirror = pipe_ctx->plane_state->horizontal_mirror
 	};
 
 	if (pipe_ctx->plane_state->address.type
-- 
cgit v1.2.3


From ac99243c8db70c9b5497a9c75c53f6bfd19b572a Mon Sep 17 00:00:00 2001
From: Yongqiang Sun <yongqiang.sun@amd.com>
Date: Mon, 25 Jun 2018 00:18:54 +0800
Subject: drm/amd/display: expose dcn10_aux_initialize in header

Signed-off-by: Yongqiang Sun <yongqiang.sun@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c | 10 ++--------
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h |  2 ++
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index 18a7cac4f6e3..be78ccb439e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -65,11 +65,6 @@ enum {
 	DP_MST_UPDATE_MAX_RETRY = 50
 };
 
-
-
-static void aux_initialize(struct dcn10_link_encoder *enc10);
-
-
 static const struct link_encoder_funcs dcn10_lnk_enc_funcs = {
 	.validate_output_with_stream =
 		dcn10_link_encoder_validate_output_with_stream,
@@ -811,7 +806,7 @@ void dcn10_link_encoder_hw_init(
 		ASSERT(result == BP_RESULT_OK);
 
 	}
-	aux_initialize(enc10);
+	dcn10_aux_initialize(enc10);
 
 	/* reinitialize HPD.
 	 * hpd_initialize() will pass DIG_FE id to HW context.
@@ -1348,8 +1343,7 @@ void dcn10_link_encoder_disable_hpd(struct link_encoder *enc)
 				FN(reg, f1), v1,\
 				FN(reg, f2), v2)
 
-static void aux_initialize(
-	struct dcn10_link_encoder *enc10)
+void dcn10_aux_initialize(struct dcn10_link_encoder *enc10)
 {
 	enum hpd_source_id hpd_source = enc10->base.hpd_source;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
index cd3bb5d40579..49ead12b2532 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.h
@@ -336,4 +336,6 @@ void dcn10_psr_program_secondary_packet(struct link_encoder *enc,
 
 bool dcn10_is_dig_enabled(struct link_encoder *enc);
 
+void dcn10_aux_initialize(struct dcn10_link_encoder *enc10);
+
 #endif /* __DC_LINK_ENCODER__DCN10_H__ */
-- 
cgit v1.2.3


From 53a599de5560b95bf76bc12d17b93406c33e9f75 Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Fri, 22 Jun 2018 13:06:01 -0400
Subject: drm/amd/display: Linux hook test pattern through debufs

bug fix: phy test PLTAT is special 80bit test pattern. The 80bit
data should be hard coded within driver so that user does not
need input the deata. previous driver does not have hard coded
80 bits pattern data for PLTPAT. Other than this PLTPAT, user
has to input 80 bits pattern data. In case user input less than
10 bytes data, un-input data byte will be filled by 0x00.

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c  | 70 +++++++++++++++++-----
 1 file changed, 55 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index f20ba9d1c9e2..0276e09d0b82 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -483,16 +483,22 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 	char *wr_buf = NULL;
 	char *wr_buf_ptr = NULL;
 	uint32_t wr_buf_size = 100;
+	uint32_t wr_buf_count = 0;
 	int r;
 	int bytes_from_user;
-	char *sub_str;
+	char *sub_str = NULL;
 	uint8_t param_index = 0;
-	long param[11];
+	uint8_t param_nums = 0;
+	long param[11] = {0x0};
 	const char delimiter[3] = {' ', '\n', '\0'};
 	enum dp_test_pattern test_pattern = DP_TEST_PATTERN_UNSUPPORTED;
 	bool disable_hpd = false;
 	bool valid_test_pattern = false;
-	uint8_t custom_pattern[10] = {0};
+	/* init with defalut 80bit custom pattern */
+	uint8_t custom_pattern[10] = {
+			0x1f, 0x7c, 0xf0, 0xc1, 0x07,
+			0x1f, 0x7c, 0xf0, 0xc1, 0x07
+			};
 	struct dc_link_settings prefer_link_settings = {LANE_COUNT_UNKNOWN,
 			LINK_RATE_UNKNOWN, LINK_SPREAD_DISABLED};
 	struct dc_link_settings cur_link_settings = {LANE_COUNT_UNKNOWN,
@@ -519,25 +525,51 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 
 	bytes_from_user = wr_buf_size - r;
 
-	while (isspace(*wr_buf_ptr))
+	/* check number of parameters. isspace could not differ space and \n */
+	while ((*wr_buf_ptr != 0xa) && (wr_buf_count < wr_buf_size)) {
+		/* skip space*/
+		while (isspace(*wr_buf_ptr) && (wr_buf_count < wr_buf_size)) {
+			wr_buf_ptr++;
+			wr_buf_count++;
+			}
+
+		if (wr_buf_count == wr_buf_size)
+			break;
+
+		/* skip non-space*/
+		while ((!isspace(*wr_buf_ptr)) && (wr_buf_count < wr_buf_size)) {
+			wr_buf_ptr++;
+			wr_buf_count++;
+			}
+
+		param_nums++;
+
+		if (wr_buf_count == wr_buf_size)
+			break;
+	}
+
+	/* max 11 parameters */
+	if (param_nums > 11)
+		param_nums = 11;
+
+	wr_buf_ptr = wr_buf; /* reset buf pinter */
+	wr_buf_count = 0; /* number of char already checked */
+
+	while (isspace(*wr_buf_ptr) && (wr_buf_count < wr_buf_size)) {
 		wr_buf_ptr++;
+		wr_buf_count++;
+	}
 
-	while ((*wr_buf_ptr != '\0') && (param_index < 1)) {
+	while (param_index < param_nums) {
+		/* after strsep, wr_buf_ptr will be moved to after space */
 		sub_str = strsep(&wr_buf_ptr, delimiter);
+
 		r = kstrtol(sub_str, 16, &param[param_index]);
 
 		if (r)
 			DRM_DEBUG_DRIVER("string to int convert error code: %d\n", r);
 
 		param_index++;
-		while (isspace(*wr_buf_ptr))
-			wr_buf_ptr++;
-
-		/* DP_TEST_PATTERN_80BIT_CUSTOM need extra 80 bits
-		 * whci are 10 bytes separte by space
-		 */
-		if (param[0] != 0x4)
-			break;
 	}
 
 	test_pattern = param[0];
@@ -575,8 +607,16 @@ static ssize_t dp_phy_test_pattern_debugfs_write(struct file *f, const char __us
 	}
 
 	if (test_pattern == DP_TEST_PATTERN_80BIT_CUSTOM) {
-		for (i = 0; i < 10; i++)
-			custom_pattern[i] = (uint8_t) param[i + 1];
+		for (i = 0; i < 10; i++) {
+			if ((uint8_t) param[i + 1] != 0x0)
+				break;
+		}
+
+		if (i < 10) {
+			/* not use default value */
+			for (i = 0; i < 10; i++)
+				custom_pattern[i] = (uint8_t) param[i + 1];
+		}
 	}
 
 	/* Usage: set DP physical test pattern using debugfs with normal DP
-- 
cgit v1.2.3


From 76fbdc63daaa216bdbd294e4d7ac6a35e1470126 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 5 Jun 2018 09:15:15 -0400
Subject: drm/amd/display: dal 3.1.54

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 1b36e763f3b0..6074680ecee1 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.53"
+#define DC_VER "3.1.54"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From e7baae1cfb7fd1a31fa8c968403cbc761cf999ff Mon Sep 17 00:00:00 2001
From: "Jerry (Fangzhi) Zuo" <Jerry.Zuo@amd.com>
Date: Fri, 22 Jun 2018 17:12:47 -0400
Subject: drm/amd/display: Add YCbCr420 only support for HDMI 4K@60

[Why]
Some monitors mark 4K@60 capable HDMI port only have 300MHz TMDS
maximum, but the edid includes 4K@60 mode in cea extension block.

[How]
To enable 4K@60, need to limit BW by allowing YCbCr420 ONLY mode.
Add YCbCr420 only support for monitors that do not fully support
HDMI2.0, e.g., ASUS PA328. The YCbCr420 only support applies to
DCN, DCE112 or higher.

Signed-off-by: Jerry (Fangzhi) Zuo <Jerry.Zuo@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index d2cc32add5f7..88854982171c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3509,7 +3509,6 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 	aconnector->base.stereo_allowed = false;
 	aconnector->base.dpms = DRM_MODE_DPMS_OFF;
 	aconnector->hpd.hpd = AMDGPU_HPD_NONE; /* not used */
-
 	mutex_init(&aconnector->hpd_lock);
 
 	/* configure support HPD hot plug connector_>polled default value is 0
@@ -3518,9 +3517,13 @@ void amdgpu_dm_connector_init_helper(struct amdgpu_display_manager *dm,
 	switch (connector_type) {
 	case DRM_MODE_CONNECTOR_HDMIA:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
+		aconnector->base.ycbcr_420_allowed =
+			link->link_enc->features.ycbcr420_supported ? true : false;
 		break;
 	case DRM_MODE_CONNECTOR_DisplayPort:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
+		aconnector->base.ycbcr_420_allowed =
+			link->link_enc->features.ycbcr420_supported ? true : false;
 		break;
 	case DRM_MODE_CONNECTOR_DVID:
 		aconnector->base.polled = DRM_CONNECTOR_POLL_HPD;
-- 
cgit v1.2.3


From c2437b1f16d9b136c88b2c7c0254919a0e1311f6 Mon Sep 17 00:00:00 2001
From: Eric Bernstein <eric.bernstein@amd.com>
Date: Wed, 16 May 2018 16:19:50 -0400
Subject: drm/amd/display: Expose bunch of functions from dcn10_hw_sequencer

v2: Remove spurious newline changes

Signed-off-by: Eric Bernstein <eric.bernstein@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 59 +++++++++++++---------
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h  |  7 +++
 drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h  |  8 +++
 3 files changed, 49 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 944275a50c0a..a9942fd5f34e 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -834,7 +834,7 @@ static bool dcn10_hw_wa_force_recovery(struct dc *dc)
 }
 
 
-static void dcn10_verify_allow_pstate_change_high(struct dc *dc)
+void dcn10_verify_allow_pstate_change_high(struct dc *dc)
 {
 	static bool should_log_hw_state; /* prevent hw state log by default */
 
@@ -1848,8 +1848,7 @@ static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 		dpp->funcs->dpp_program_bias_and_scale(dpp, &bns_params);
 }
 
-
-static void update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
+static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
 	struct mpcc_blnd_cfg blnd_cfg;
@@ -1994,7 +1993,7 @@ static void update_dchubp_dpp(
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change)
-		update_mpcc(dc, pipe_ctx);
+		dc->hwss.update_mpcc(dc, pipe_ctx);
 
 	if (plane_state->update_flags.bits.full_update ||
 		plane_state->update_flags.bits.per_pixel_alpha_change ||
@@ -2104,6 +2103,33 @@ static void set_hdr_multiplier(struct pipe_ctx *pipe_ctx)
 			pipe_ctx->plane_res.dpp, hw_mult);
 }
 
+void dcn10_program_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context)
+{
+	if (pipe_ctx->plane_state->update_flags.bits.full_update)
+		dcn10_enable_plane(dc, pipe_ctx, context);
+
+	update_dchubp_dpp(dc, pipe_ctx, context);
+
+	set_hdr_multiplier(pipe_ctx);
+
+	if (pipe_ctx->plane_state->update_flags.bits.full_update ||
+			pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
+			pipe_ctx->plane_state->update_flags.bits.gamma_change)
+		dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
+
+	/* dcn10_translate_regamma_to_hw_format takes 750us to finish
+	 * only do gamma programming for full update.
+	 * TODO: This can be further optimized/cleaned up
+	 * Always call this for now since it does memcmp inside before
+	 * doing heavy calculation and programming
+	 */
+	if (pipe_ctx->plane_state->update_flags.bits.full_update)
+		dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+}
+
 static void program_all_pipe_in_tree(
 		struct dc *dc,
 		struct pipe_ctx *pipe_ctx,
@@ -2125,26 +2151,7 @@ static void program_all_pipe_in_tree(
 	}
 
 	if (pipe_ctx->plane_state != NULL) {
-		if (pipe_ctx->plane_state->update_flags.bits.full_update)
-			dcn10_enable_plane(dc, pipe_ctx, context);
-
-		update_dchubp_dpp(dc, pipe_ctx, context);
-
-		set_hdr_multiplier(pipe_ctx);
-
-		if (pipe_ctx->plane_state->update_flags.bits.full_update ||
-				pipe_ctx->plane_state->update_flags.bits.in_transfer_func_change ||
-				pipe_ctx->plane_state->update_flags.bits.gamma_change)
-			dc->hwss.set_input_transfer_func(pipe_ctx, pipe_ctx->plane_state);
-
-		/* dcn10_translate_regamma_to_hw_format takes 750us to finish
-		 * only do gamma programming for full update.
-		 * TODO: This can be further optimized/cleaned up
-		 * Always call this for now since it does memcmp inside before
-		 * doing heavy calculation and programming
-		 */
-		if (pipe_ctx->plane_state->update_flags.bits.full_update)
-			dc->hwss.set_output_transfer_func(pipe_ctx, pipe_ctx->stream);
+		dcn10_program_pipe(dc, pipe_ctx, context);
 	}
 
 	if (pipe_ctx->bottom_pipe != NULL && pipe_ctx->bottom_pipe != pipe_ctx) {
@@ -2269,7 +2276,7 @@ static void dcn10_apply_ctx_for_surface(
 			old_pipe_ctx->plane_state &&
 			old_pipe_ctx->stream_res.tg == tg) {
 
-			hwss1_plane_atomic_disconnect(dc, old_pipe_ctx);
+			dc->hwss.plane_atomic_disconnect(dc, old_pipe_ctx);
 			removed_pipe[i] = true;
 
 			DC_LOG_DC("Reset mpcc for pipe %d\n",
@@ -2555,7 +2562,9 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.apply_ctx_to_hw = dce110_apply_ctx_to_hw,
 	.apply_ctx_for_surface = dcn10_apply_ctx_for_surface,
 	.update_plane_addr = dcn10_update_plane_addr,
+	.plane_atomic_disconnect = hwss1_plane_atomic_disconnect,
 	.update_dchub = dcn10_update_dchub,
+	.update_mpcc = dcn10_update_mpcc,
 	.update_pending_status = dcn10_update_pending_status,
 	.set_input_transfer_func = dcn10_set_input_transfer_func,
 	.set_output_transfer_func = dcn10_set_output_transfer_func,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
index 44f734b73f9e..7139fb73e966 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.h
@@ -39,4 +39,11 @@ bool is_rgb_cspace(enum dc_color_space output_color_space);
 
 void hwss1_plane_atomic_disconnect(struct dc *dc, struct pipe_ctx *pipe_ctx);
 
+void dcn10_verify_allow_pstate_change_high(struct dc *dc);
+
+void dcn10_program_pipe(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx,
+		struct dc_state *context);
+
 #endif /* __DC_HWSS_DCN10_H__ */
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index 2506601120af..c2277d1e195b 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -102,10 +102,18 @@ struct hw_sequencer_funcs {
 		const struct dc *dc,
 		struct pipe_ctx *pipe_ctx);
 
+	void (*plane_atomic_disconnect)(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx);
+
 	void (*update_dchub)(
 		struct dce_hwseq *hws,
 		struct dchub_init_data *dh_data);
 
+	void (*update_mpcc)(
+		struct dc *dc,
+		struct pipe_ctx *pipe_ctx);
+
 	void (*update_pending_status)(
 			struct pipe_ctx *pipe_ctx);
 
-- 
cgit v1.2.3


From 3092108904461dd50b1502f3a2977a4259d91044 Mon Sep 17 00:00:00 2001
From: "Leo (Sunpeng) Li" <sunpeng.li@amd.com>
Date: Tue, 26 Jun 2018 10:44:05 -0400
Subject: drm/amd/display: Right shift AUX reply value sooner than later

[Why]
There is no point in keeping the AUX reply value in the raw format as
returned from reading the AUX_SW_DATA register.

[How]
Shift it within read_channel_reply(), where the register is read, before
returning it.

Signed-off-by: Leo (Sunpeng) Li <sunpeng.li@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
index 1f3940644a5b..ae5caa97caca 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/aux_engine_dce110.c
@@ -300,9 +300,10 @@ static int read_channel_reply(struct aux_engine *engine, uint32_t size,
 			  AUX_SW_DATA_RW, 1);
 
 	REG_GET(AUX_SW_DATA, AUX_SW_DATA, &reply_result_32);
+	reply_result_32 = reply_result_32 >> 4;
 	*reply_result = (uint8_t)reply_result_32;
 
-	if (reply_result_32 >> 4 == 0) { /* ACK */
+	if (reply_result_32 == 0) { /* ACK */
 		uint32_t i = 0;
 
 		/* First byte was already used to get the command status */
@@ -356,7 +357,6 @@ static void process_channel_reply(
 			return;
 		}
 	} else {
-		reply_result = reply_result >> 4;
 
 		switch (reply_result) {
 		case 0: /* ACK */
-- 
cgit v1.2.3


From edf6ffe4f47e6749cfd45c1489feea2dbb0041c7 Mon Sep 17 00:00:00 2001
From: "Leo (Sunpeng) Li" <sunpeng.li@amd.com>
Date: Tue, 26 Jun 2018 10:50:16 -0400
Subject: drm/amd/display: Read AUX channel even if only status byte is
 returned

[Why]
get_channel_status() can return 0 in returned_bytes, and report a
successful operation result. This is because it prunes the first status
byte out. This was preventing read_channel_reply() from being called
(due to the faulty condition), and consequently preventing the AUX
reply status from being set.

[How]
Fix the conditional so that it accounts for when get_channel_status()
returns 0 bytes read.

[Fixes]
Fixes possible edid read failures during S3 resume, where we are now
relying on DRM's DP AUX handling. This was an regression introduced by:

    Author: Harry Wentland <harry.wentland@amd.com>
        drm/amd/display: Return aux replies directly to DRM

Signed-off-by: Leo (Sunpeng) Li <sunpeng.li@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index d108ccfc5cf9..08c9d73b9ab7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -671,7 +671,7 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 	case AUX_CHANNEL_OPERATION_SUCCEEDED:
 		res = returned_bytes;
 
-		if (res <= size && res > 0)
+		if (res <= size && res >= 0)
 			res = engine->funcs->read_channel_reply(engine, size,
 								buffer, reply,
 								&status);
-- 
cgit v1.2.3


From e0d85b20c74fc078862262da64b36e8e7b6663e7 Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Mon, 25 Jun 2018 19:28:54 -0400
Subject: drm/amd/display: introduce concept of send_reset_length for i2c
 engines

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                |  1 +
 .../dc/i2caux/dce110/i2c_hw_engine_dce110.c        | 26 +++++++++++++---------
 .../dc/i2caux/dce110/i2c_hw_engine_dce110.h        |  8 +++++++
 .../amd/display/dc/i2caux/dce110/i2caux_dce110.c   | 18 ++++++++++++++-
 drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h |  2 ++
 5 files changed, 43 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 6074680ecee1..ede3489b4f37 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -250,6 +250,7 @@ struct dc_debug {
 	bool p010_mpo_support;
 	bool recovery_enabled;
 	bool avoid_vbios_exec_table;
+	bool scl_reset_length10;
 
 };
 struct dc_state;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
index b7256f595052..9cbe1a7a6bcb 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.c
@@ -62,12 +62,7 @@ enum dc_i2c_arbitration {
 	DC_I2C_ARBITRATION__DC_I2C_SW_PRIORITY_HIGH
 };
 
-enum {
-	/* No timeout in HW
-	 * (timeout implemented in SW by querying status) */
-	I2C_SETUP_TIME_LIMIT = 255,
-	I2C_HW_BUFFER_SIZE = 538
-};
+
 
 /*
  * @brief
@@ -152,6 +147,11 @@ static bool setup_engine(
 	struct i2c_engine *i2c_engine)
 {
 	struct i2c_hw_engine_dce110 *hw_engine = FROM_I2C_ENGINE(i2c_engine);
+	uint32_t i2c_setup_limit = I2C_SETUP_TIME_LIMIT_DCE;
+	uint32_t  reset_length = 0;
+
+	if (hw_engine->base.base.setup_limit != 0)
+		i2c_setup_limit = hw_engine->base.base.setup_limit;
 
 	/* Program pin select */
 	REG_UPDATE_6(
@@ -164,11 +164,15 @@ static bool setup_engine(
 			DC_I2C_DDC_SELECT, hw_engine->engine_id);
 
 	/* Program time limit */
-	REG_UPDATE_N(
-			SETUP, 2,
-			FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), I2C_SETUP_TIME_LIMIT,
-			FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
-
+	if (hw_engine->base.base.send_reset_length == 0) {
+		/*pre-dcn*/
+		REG_UPDATE_N(
+				SETUP, 2,
+				FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_TIME_LIMIT), i2c_setup_limit,
+				FN(DC_I2C_DDC1_SETUP, DC_I2C_DDC1_ENABLE), 1);
+	} else {
+		reset_length = hw_engine->base.base.send_reset_length;
+	}
 	/* Program HW priority
 	 * set to High - interrupt software I2C at any time
 	 * Enable restart of SW I2C that was interrupted by HW
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
index 5bb04085f670..fea2946906ed 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2c_hw_engine_dce110.h
@@ -192,6 +192,7 @@ struct i2c_hw_engine_dce110 {
 	/* number of pending transactions (before GO) */
 	uint32_t transaction_count;
 	uint32_t engine_keep_power_up_count;
+	uint32_t i2_setup_time_limit;
 };
 
 struct i2c_hw_engine_dce110_create_arg {
@@ -207,4 +208,11 @@ struct i2c_hw_engine_dce110_create_arg {
 struct i2c_engine *dal_i2c_hw_engine_dce110_create(
 	const struct i2c_hw_engine_dce110_create_arg *arg);
 
+enum {
+	I2C_SETUP_TIME_LIMIT_DCE = 255,
+	I2C_SETUP_TIME_LIMIT_DCN = 3,
+	I2C_HW_BUFFER_SIZE = 538,
+	I2C_SEND_RESET_LENGTH_9 = 9,
+	I2C_SEND_RESET_LENGTH_10 = 10,
+};
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
index e0557d353818..1d748ac1d6d6 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/dce110/i2caux_dce110.c
@@ -43,6 +43,9 @@
 #include "i2c_sw_engine_dce110.h"
 #include "i2c_hw_engine_dce110.h"
 #include "aux_engine_dce110.h"
+#include "../../dc.h"
+#include "dc_types.h"
+
 
 /*
  * Post-requisites: headers required by this unit
@@ -250,7 +253,20 @@ void dal_i2caux_dce110_construct(
 
 		base->i2c_hw_engines[line_id] =
 			dal_i2c_hw_engine_dce110_create(&hw_arg_dce110);
-
+		if (base->i2c_hw_engines[line_id] != NULL) {
+			switch (ctx->dce_version) {
+			case DCN_VERSION_1_0:
+				base->i2c_hw_engines[line_id]->setup_limit =
+					I2C_SETUP_TIME_LIMIT_DCN;
+				base->i2c_hw_engines[line_id]->send_reset_length  = 0;
+			break;
+			default:
+				base->i2c_hw_engines[line_id]->setup_limit =
+					I2C_SETUP_TIME_LIMIT_DCE;
+				base->i2c_hw_engines[line_id]->send_reset_length  = 0;
+				break;
+			}
+		}
 		++i;
 	} while (i < num_i2caux_inst);
 
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
index 58fc0f25eceb..ded6ea34b714 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2c_engine.h
@@ -86,6 +86,8 @@ struct i2c_engine {
 	struct engine base;
 	const struct i2c_engine_funcs *funcs;
 	uint32_t timeout_delay;
+	uint32_t setup_limit;
+	uint32_t send_reset_length;
 };
 
 void dal_i2c_engine_construct(
-- 
cgit v1.2.3


From 8fc0a0d4a0a49ed148db2e484539516ad67b6321 Mon Sep 17 00:00:00 2001
From: Charlene Liu <charlene.liu@amd.com>
Date: Tue, 26 Jun 2018 18:49:32 -0400
Subject: drm/amd/display: add DalEnableHDMI20 key support

[why]
"DalEnableHDMI20" set to 0, disallow HDMI YCbCr420 and  pixel clock > 340Mhz
Default is enabled.

Signed-off-by: Charlene Liu <charlene.liu@amd.com>
Reviewed-by: Jun Lei <Jun.Lei@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                       | 1 +
 drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c     | 6 ++++++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c | 6 ++++++
 3 files changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index ede3489b4f37..721c5cdff38f 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -251,6 +251,7 @@ struct dc_debug {
 	bool recovery_enabled;
 	bool avoid_vbios_exec_table;
 	bool scl_reset_length10;
+	bool hdmi20_disable;
 
 };
 struct dc_state;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index dbe3b26b6d9e..60e3c6a73d37 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -646,6 +646,9 @@ static bool dce110_link_encoder_validate_hdmi_output(
 	if (!enc110->base.features.flags.bits.HDMI_6GB_EN &&
 		adjusted_pix_clk_khz >= 300000)
 		return false;
+	if (enc110->base.ctx->dc->debug.hdmi20_disable &&
+		crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 	return true;
 }
 
@@ -773,6 +776,9 @@ void dce110_link_encoder_construct(
 				__func__,
 				result);
 	}
+	if (enc110->base.ctx->dc->debug.hdmi20_disable) {
+		enc110->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
 }
 
 bool dce110_link_encoder_validate_output_with_stream(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
index be78ccb439e9..6f675206a136 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_link_encoder.c
@@ -596,6 +596,9 @@ static bool dcn10_link_encoder_validate_hdmi_output(
 	if (!enc10->base.features.flags.bits.HDMI_6GB_EN &&
 		adjusted_pix_clk_khz >= 300000)
 		return false;
+	if (enc10->base.ctx->dc->debug.hdmi20_disable &&
+		crtc_timing->pixel_encoding == PIXEL_ENCODING_YCBCR420)
+		return false;
 	return true;
 }
 
@@ -728,6 +731,9 @@ void dcn10_link_encoder_construct(
 				__func__,
 				result);
 	}
+	if (enc10->base.ctx->dc->debug.hdmi20_disable) {
+		enc10->base.features.flags.bits.HDMI_6GB_EN = 0;
+	}
 }
 
 bool dcn10_link_encoder_validate_output_with_stream(
-- 
cgit v1.2.3


From c2c09ed5cd1b7423b2d2bf372e4c62394264324d Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Tue, 26 Jun 2018 09:52:29 -0400
Subject: drm/amd/display: add pp to dc powerlevel enum translator

[why]
Add a switch statement to translate pp's powerlevel enum
to dc powerlevel statement enum
[how]
Add a translator function

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Sun peng Li <Sunpeng.Li@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c   | 29 +++++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index 50e863024f58..c69ae78d82b2 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -192,6 +192,33 @@ static enum amd_pp_clock_type dc_to_pp_clock_type(
 	return amd_pp_clk_type;
 }
 
+static enum dm_pp_clocks_state pp_to_dc_powerlevel_state(
+			enum PP_DAL_POWERLEVEL max_clocks_state)
+{
+	switch (max_clocks_state) {
+	case PP_DAL_POWERLEVEL_0:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_0;
+	case PP_DAL_POWERLEVEL_1:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_1;
+	case PP_DAL_POWERLEVEL_2:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_2;
+	case PP_DAL_POWERLEVEL_3:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_3;
+	case PP_DAL_POWERLEVEL_4:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_4;
+	case PP_DAL_POWERLEVEL_5:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_5;
+	case PP_DAL_POWERLEVEL_6:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_6;
+	case PP_DAL_POWERLEVEL_7:
+		return DM_PP_CLOCKS_DPM_STATE_LEVEL_7;
+	default:
+		DRM_ERROR("DM_PPLIB: invalid powerlevel state: %d!\n",
+				max_clocks_state);
+		return DM_PP_CLOCKS_STATE_INVALID;
+	}
+}
+
 static void pp_to_dc_clock_levels(
 		const struct amd_pp_clocks *pp_clks,
 		struct dm_pp_clock_levels *dc_clks,
@@ -441,7 +468,7 @@ bool dm_pp_get_static_clocks(
 	if (ret)
 		return false;
 
-	static_clk_info->max_clocks_state = pp_clk_info.max_clocks_state;
+	static_clk_info->max_clocks_state = pp_to_dc_powerlevel_state(pp_clk_info.max_clocks_state);
 	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock;
 	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock;
 
-- 
cgit v1.2.3


From 6c4fff068f7940993b3ec74a9996f4b514089d1a Mon Sep 17 00:00:00 2001
From: Yue Hin Lau <Yuehin.Lau@amd.com>
Date: Wed, 27 Jun 2018 13:49:20 -0400
Subject: drm/amd/display: Add NULL check for local sink in edp_power_control

[WHY]
PNP cause bsod regression fix

[HOW]
Add NULL check

Signed-off-by: Yue Hin Lau <Yuehin.Lau@amd.com>
Reviewed-by: Hugo Hu <Hugo.Hu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 109d4103d10d..e48eb3056af5 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -871,9 +871,11 @@ void hwss_edp_power_control(
 			unsigned long long wait_time_ms = 0;
 
 			/* max 500ms from LCDVDD off to on */
-			unsigned long long edp_poweroff_time_ms =
-					500 + link->local_sink->edid_caps.panel_patch.extra_t12_ms;
+			unsigned long long edp_poweroff_time_ms = 500;
 
+			if (link->local_sink != NULL)
+				edp_poweroff_time_ms =
+						500 + link->local_sink->edid_caps.panel_patch.extra_t12_ms;
 			if (link->link_trace.time_stamp.edp_poweroff == 0)
 				wait_time_ms = edp_poweroff_time_ms;
 			else if (duration_in_ms < edp_poweroff_time_ms)
-- 
cgit v1.2.3


From 4e18814eeec946fa864723423c9a607815ede5cb Mon Sep 17 00:00:00 2001
From: Fatemeh Darbehani <fatemeh.darbehani@amd.com>
Date: Tue, 26 Jun 2018 16:40:55 -0400
Subject: drm/amd/display: Return out_link_loss from interrupt handler

Signed-off-by: Fatemeh Darbehani <fatemeh.darbehani@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c  | 8 +++++++-
 drivers/gpu/drm/amd/display/dc/dc_link.h          | 2 +-
 3 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 88854982171c..e0cf54ccc9f4 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1041,7 +1041,7 @@ static void handle_hpd_rx_irq(void *param)
 	if (dc_link->type != dc_connection_mst_branch)
 		mutex_lock(&aconnector->hpd_lock);
 
-	if (dc_link_handle_hpd_rx_irq(dc_link, NULL) &&
+	if (dc_link_handle_hpd_rx_irq(dc_link, NULL, NULL) &&
 			!is_mst_root_connector) {
 		/* Downstream Port status changed. */
 		if (dc_link_detect(dc_link, DETECT_REASON_HPDRX)) {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 6d4642bf395d..54e396452345 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1996,12 +1996,16 @@ static void handle_automated_test(struct dc_link *link)
 			sizeof(test_response));
 }
 
-bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data)
+bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data, bool *out_link_loss)
 {
 	union hpd_irq_data hpd_irq_dpcd_data = {{{{0}}}};
 	union device_service_irq device_service_clear = { { 0 } };
 	enum dc_status result;
+
 	bool status = false;
+
+	if (out_link_loss)
+		*out_link_loss = false;
 	/* For use cases related to down stream connection status change,
 	 * PSR and device auto test, refer to function handle_sst_hpd_irq
 	 * in DAL2.1*/
@@ -2076,6 +2080,8 @@ bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd
 			true, LINK_TRAINING_ATTEMPTS);
 
 		status = false;
+		if (out_link_loss)
+			*out_link_loss = true;
 	}
 
 	if (link->type == dc_connection_active_dongle &&
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index eda4a5d3ff1c..070a56926308 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -172,7 +172,7 @@ bool dc_link_detect(struct dc_link *dc_link, enum dc_detect_reason reason);
  * false - no change in Downstream port status. No further action required
  * from DM. */
 bool dc_link_handle_hpd_rx_irq(struct dc_link *dc_link,
-		union hpd_irq_data *hpd_irq_dpcd_data);
+		union hpd_irq_data *hpd_irq_dpcd_data, bool *out_link_loss);
 
 struct dc_sink_init_data;
 
-- 
cgit v1.2.3


From 99a100ae327c2d9c89740bd556cc128f666ba71b Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Tue, 26 Jun 2018 14:58:15 -0400
Subject: drm/amd/display: Add CRC support for DCN

[Why]
Regamma/CTM tests require CRC support

[How]
The CRC registers that were used in DCE exist under different
names in DCN.  The code was copied from DCE (in
dc/dce110/dce110_timing_generator.c) into DCN, and changed to
use the DCN register access helper functions.

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c | 68 +++++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h | 49 +++++++++++++++-
 2 files changed, 114 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
index e6a3ade154b9..411f89218e01 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.c
@@ -1324,6 +1324,72 @@ bool optc1_is_optc_underflow_occurred(struct timing_generator *optc)
 	return (underflow_occurred == 1);
 }
 
+bool optc1_configure_crc(struct timing_generator *optc,
+			  const struct crc_params *params)
+{
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	/* Cannot configure crc on a CRTC that is disabled */
+	if (!optc1_is_tg_enabled(optc))
+		return false;
+
+	REG_WRITE(OTG_CRC_CNTL, 0);
+
+	if (!params->enable)
+		return true;
+
+	/* Program frame boundaries */
+	/* Window A x axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWA_X_CONTROL,
+			OTG_CRC0_WINDOWA_X_START, params->windowa_x_start,
+			OTG_CRC0_WINDOWA_X_END, params->windowa_x_end);
+
+	/* Window A y axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWA_Y_CONTROL,
+			OTG_CRC0_WINDOWA_Y_START, params->windowa_y_start,
+			OTG_CRC0_WINDOWA_Y_END, params->windowa_y_end);
+
+	/* Window B x axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWB_X_CONTROL,
+			OTG_CRC0_WINDOWB_X_START, params->windowb_x_start,
+			OTG_CRC0_WINDOWB_X_END, params->windowb_x_end);
+
+	/* Window B y axis start and end. */
+	REG_UPDATE_2(OTG_CRC0_WINDOWB_Y_CONTROL,
+			OTG_CRC0_WINDOWB_Y_START, params->windowb_y_start,
+			OTG_CRC0_WINDOWB_Y_END, params->windowb_y_end);
+
+	/* Set crc mode and selection, and enable. Only using CRC0*/
+	REG_UPDATE_3(OTG_CRC_CNTL,
+			OTG_CRC_CONT_EN, params->continuous_mode ? 1 : 0,
+			OTG_CRC0_SELECT, params->selection,
+			OTG_CRC_EN, 1);
+
+	return true;
+}
+
+bool optc1_get_crc(struct timing_generator *optc,
+		    uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb)
+{
+	uint32_t field = 0;
+	struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
+	REG_GET(OTG_CRC_CNTL, OTG_CRC_EN, &field);
+
+	/* Early return if CRC is not enabled for this CRTC */
+	if (!field)
+		return false;
+
+	REG_GET_2(OTG_CRC0_DATA_RG,
+			CRC0_R_CR, r_cr,
+			CRC0_G_Y, g_y);
+
+	REG_GET(OTG_CRC0_DATA_B,
+			CRC0_B_CB, b_cb);
+
+	return true;
+}
+
 static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.validate_timing = optc1_validate_timing,
 		.program_timing = optc1_program_timing,
@@ -1360,6 +1426,8 @@ static const struct timing_generator_funcs dcn10_tg_funcs = {
 		.is_tg_enabled = optc1_is_tg_enabled,
 		.is_optc_underflow_occurred = optc1_is_optc_underflow_occurred,
 		.clear_optc_underflow = optc1_clear_optc_underflow,
+		.get_crc = optc1_get_crc,
+		.configure_crc = optc1_configure_crc,
 };
 
 void dcn10_timing_generator_init(struct optc *optc1)
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index 59ed272e0c49..1df510f57377 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -75,7 +75,14 @@
 	SRI(CONTROL, VTG, inst),\
 	SRI(OTG_VERT_SYNC_CONTROL, OTG, inst),\
 	SRI(OTG_MASTER_UPDATE_MODE, OTG, inst),\
-	SRI(OTG_GSL_CONTROL, OTG, inst)
+	SRI(OTG_GSL_CONTROL, OTG, inst),\
+	SRI(OTG_CRC_CNTL, OTG, inst),\
+	SRI(OTG_CRC0_DATA_RG, OTG, inst),\
+	SRI(OTG_CRC0_DATA_B, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWA_X_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWA_Y_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWB_X_CONTROL, OTG, inst),\
+	SRI(OTG_CRC0_WINDOWB_Y_CONTROL, OTG, inst)
 
 #define TG_COMMON_REG_LIST_DCN1_0(inst) \
 	TG_COMMON_REG_LIST_DCN(inst),\
@@ -138,6 +145,13 @@ struct dcn_optc_registers {
 	uint32_t OTG_GSL_WINDOW_X;
 	uint32_t OTG_GSL_WINDOW_Y;
 	uint32_t OTG_VUPDATE_KEEPOUT;
+	uint32_t OTG_CRC_CNTL;
+	uint32_t OTG_CRC0_DATA_RG;
+	uint32_t OTG_CRC0_DATA_B;
+	uint32_t OTG_CRC0_WINDOWA_X_CONTROL;
+	uint32_t OTG_CRC0_WINDOWA_Y_CONTROL;
+	uint32_t OTG_CRC0_WINDOWB_X_CONTROL;
+	uint32_t OTG_CRC0_WINDOWB_Y_CONTROL;
 };
 
 #define TG_COMMON_MASK_SH_LIST_DCN(mask_sh)\
@@ -232,7 +246,21 @@ struct dcn_optc_registers {
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL2_EN, mask_sh),\
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_MASTER_EN, mask_sh),\
 	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_FORCE_DELAY, mask_sh),\
-	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh)
+	SF(OTG0_OTG_GSL_CONTROL, OTG_GSL_CHECK_ALL_FIELDS, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC_CONT_EN, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC0_SELECT, mask_sh),\
+	SF(OTG0_OTG_CRC_CNTL, OTG_CRC_EN, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_RG, CRC0_R_CR, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_RG, CRC0_G_Y, mask_sh),\
+	SF(OTG0_OTG_CRC0_DATA_B, CRC0_B_CB, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_X_CONTROL, OTG_CRC0_WINDOWA_X_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_X_CONTROL, OTG_CRC0_WINDOWA_X_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_Y_CONTROL, OTG_CRC0_WINDOWA_Y_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWA_Y_CONTROL, OTG_CRC0_WINDOWA_Y_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_X_CONTROL, OTG_CRC0_WINDOWB_X_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_X_CONTROL, OTG_CRC0_WINDOWB_X_END, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_START, mask_sh),\
+	SF(OTG0_OTG_CRC0_WINDOWB_Y_CONTROL, OTG_CRC0_WINDOWB_Y_END, mask_sh)
 
 
 #define TG_COMMON_MASK_SH_LIST_DCN1_0(mask_sh)\
@@ -363,7 +391,22 @@ struct dcn_optc_registers {
 	type OTG_MASTER_UPDATE_LOCK_GSL_EN;\
 	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_START_OFFSET;\
 	type MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_END_OFFSET;\
-	type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;
+	type OTG_MASTER_UPDATE_LOCK_VUPDATE_KEEPOUT_EN;\
+	type OTG_CRC_CONT_EN;\
+	type OTG_CRC0_SELECT;\
+	type OTG_CRC_EN;\
+	type CRC0_R_CR;\
+	type CRC0_G_Y;\
+	type CRC0_B_CB;\
+	type OTG_CRC0_WINDOWA_X_START;\
+	type OTG_CRC0_WINDOWA_X_END;\
+	type OTG_CRC0_WINDOWA_Y_START;\
+	type OTG_CRC0_WINDOWA_Y_END;\
+	type OTG_CRC0_WINDOWB_X_START;\
+	type OTG_CRC0_WINDOWB_X_END;\
+	type OTG_CRC0_WINDOWB_Y_START;\
+	type OTG_CRC0_WINDOWB_Y_END;
+
 
 #define TG_REG_FIELD_LIST(type) \
 	TG_REG_FIELD_LIST_DCN1_0(type)
-- 
cgit v1.2.3


From aca3e9a49b200d56e4dd0a21bbb443e96a482fd9 Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Wed, 27 Jun 2018 15:55:57 -0400
Subject: drm/amd/display: Expose couple OPTC functions through header

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
index 1df510f57377..c1b114209fe8 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_optc.h
@@ -554,4 +554,15 @@ bool optc1_get_otg_active_size(struct timing_generator *optc,
 		uint32_t *otg_active_width,
 		uint32_t *otg_active_height);
 
+void optc1_enable_crtc_reset(
+		struct timing_generator *optc,
+		int source_tg_inst,
+		struct crtc_trigger_info *crtc_tp);
+
+bool optc1_configure_crc(struct timing_generator *optc,
+			  const struct crc_params *params);
+
+bool optc1_get_crc(struct timing_generator *optc,
+		    uint32_t *r_cr, uint32_t *g_y, uint32_t *b_cb);
+
 #endif /* __DC_TIMING_GENERATOR_DCN10_H__ */
-- 
cgit v1.2.3


From 245524d9b827e184de1a23aff24c7872fed04cdb Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Wed, 27 Jun 2018 13:03:04 -0400
Subject: drm/amd/display: dp debugfs allow link rate lane count greater than
 dp rx reported caps

[Why]
when hw team does phy parameters tuning, there is need to force dp
link rate or lane count grater than the values from dp receiver to
check dp tx. current debufs limit link rate, lane count no more
than rx caps.

[How] remove force settings less than rx caps check

v2: Fix typo in title

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
index 0276e09d0b82..0d9e410ca01e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_debugfs.c
@@ -214,8 +214,7 @@ static ssize_t dp_link_settings_write(struct file *f, const char __user *buf,
 		break;
 	}
 
-	if (!valid_input || (param[0] > link->reported_link_cap.lane_count) ||
-			(param[1] > link->reported_link_cap.link_rate)) {
+	if (!valid_input) {
 		kfree(wr_buf);
 		DRM_DEBUG_DRIVER("Invalid Input value No HW will be programmed\n");
 		return bytes_from_user;
-- 
cgit v1.2.3


From ece4147fea152fe0761d67b825fb4b4b9f94349b Mon Sep 17 00:00:00 2001
From: Ken Chalmers <ken.chalmers@amd.com>
Date: Wed, 27 Jun 2018 12:48:21 -0400
Subject: drm/amd/display: Fix new stream count check in dc_add_stream_to_ctx

[Why]
The previous code could allow through attempts to enable more streams
than there are timing generators, in designs where the number of pipes
is greater than the number of timing generators.

[How]
Compare the new stream count to the resource pool's timing generator
count, instead of its pipe count.  Also correct a typo in the error
message.

Signed-off-by: Ken Chalmers <ken.chalmers@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index c5fc5250e2bf..9abe5481e40c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1705,8 +1705,8 @@ enum dc_status dc_add_stream_to_ctx(
 	struct dc_context *dc_ctx = dc->ctx;
 	enum dc_status res;
 
-	if (new_ctx->stream_count >= dc->res_pool->pipe_count) {
-		DC_ERROR("Max streams reached, can add stream %p !\n", stream);
+	if (new_ctx->stream_count >= dc->res_pool->timing_generator_count) {
+		DC_ERROR("Max streams reached, can't add stream %p !\n", stream);
 		return DC_ERROR_UNEXPECTED;
 	}
 
-- 
cgit v1.2.3


From dbcac9c8abb117b11728da44fcaffcdc0d2fcc81 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 28 Jun 2018 12:28:00 -0400
Subject: drm/amd/display: add max scl ratio to soc bounding box

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index 6943801c5fd3..c43d68bc9d5c 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -111,6 +111,8 @@ struct _vcs_dpi_soc_bounding_box_st {
 	double xfc_bus_transport_time_us;
 	double xfc_xbuf_latency_tolerance_us;
 	int use_urgent_burst_bw;
+	double max_hscl_ratio;
+	double max_vscl_ratio;
 	struct _vcs_dpi_voltage_scaling_st clock_limits[7];
 };
 
-- 
cgit v1.2.3


From 5fbac0a5ff99071919976a5434b19e9cc792a2ca Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 28 Jun 2018 11:31:13 -0400
Subject: drm/amd/display: update dml to match DV dml

DV updated their dml with an option to use max vstartup,
this updates dc dml with the same option

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
index c43d68bc9d5c..cbafce649e33 100644
--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
+++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_structs.h
@@ -305,6 +305,7 @@ struct _vcs_dpi_display_pipe_dest_params_st {
 	unsigned char otg_inst;
 	unsigned char odm_split_cnt;
 	unsigned char odm_combine;
+	unsigned char use_maximum_vstartup;
 };
 
 struct _vcs_dpi_display_pipe_params_st {
-- 
cgit v1.2.3


From cc034fed70d2d41ac7726d1c9872a80f035f8692 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Tue, 5 Jun 2018 09:15:41 -0400
Subject: drm/amd/display: dal 3.1.55

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Anthony Koo <Anthony.Koo@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 721c5cdff38f..208578301d59 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.54"
+#define DC_VER "3.1.55"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 522e6b434a61f8be910560969386a2b3ce113c1b Mon Sep 17 00:00:00 2001
From: Hugo Hu <hugo.hu@amd.com>
Date: Tue, 3 Jul 2018 15:59:15 -0400
Subject: drm/amd/display: Initialize data structure for DalMpVisualConfirm.

[Why] Prevent unexpected color shows if DalMpVisualConfirm enable.
[How] Zero out color configuration data for DalMpVisualConfirm when initiating.

Signed-off-by: Hugo Hu <hugo.hu@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index a9942fd5f34e..2e145aa663a4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1851,7 +1851,7 @@ static void update_dpp(struct dpp *dpp, struct dc_plane_state *plane_state)
 static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 {
 	struct hubp *hubp = pipe_ctx->plane_res.hubp;
-	struct mpcc_blnd_cfg blnd_cfg;
+	struct mpcc_blnd_cfg blnd_cfg = {0};
 	bool per_pixel_alpha = pipe_ctx->plane_state->per_pixel_alpha && pipe_ctx->bottom_pipe;
 	int mpcc_id;
 	struct mpcc *new_mpcc;
-- 
cgit v1.2.3


From ec95213112dca6111eb7561ae6384f77017dfd1f Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 4 Jul 2018 11:31:40 -0400
Subject: drm/amd/display: properly turn autocal off

[why]
Currently we do not turn off autocal when scaling is in bypass.
In case vbios enalbes auto scale and our first mode set is a non-scaled
mode we have autocal on causing screen corruption.

[how]
moves turning autocal off to be first thing done during scaler setup

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index f862fd148cca..f0cc97518c49 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -655,6 +655,12 @@ void dpp1_dscl_set_scaler_manual_scale(
 
 	dpp->scl_data = *scl_data;
 
+	/* Autocal off */
+	REG_SET_3(DSCL_AUTOCAL, 0,
+		AUTOCAL_MODE, AUTOCAL_MODE_OFF,
+		AUTOCAL_NUM_PIPE, 0,
+		AUTOCAL_PIPE_ID, 0);
+
 	/* Recout */
 	dpp1_dscl_set_recout(dpp, &scl_data->recout);
 
@@ -678,12 +684,6 @@ void dpp1_dscl_set_scaler_manual_scale(
 	if (dscl_mode == DSCL_MODE_SCALING_444_BYPASS)
 		return;
 
-	/* Autocal off */
-	REG_SET_3(DSCL_AUTOCAL, 0,
-		AUTOCAL_MODE, AUTOCAL_MODE_OFF,
-		AUTOCAL_NUM_PIPE, 0,
-		AUTOCAL_PIPE_ID, 0);
-
 	/* Black offsets */
 	if (ycbcr)
 		REG_SET_2(SCL_BLACK_OFFSET, 0,
-- 
cgit v1.2.3


From 3f2ddfa8875ce71a8c12723d1841647af8cbb0ba Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 10 Jul 2018 16:51:22 -0500
Subject: drm/amdgpu/vi: fix mixed up state in smu clockgating setup

Use the PP_STATE_SUPPORT_* rather than AMD_CG_SUPPORT_*
when communicating with the SMU.

Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/vi.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vi.c b/drivers/gpu/drm/amd/amdgpu/vi.c
index 4ac1288ab7df..42c8ad105b05 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1363,11 +1363,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_MC_LS | AMD_CG_SUPPORT_MC_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_MC_LS) {
-			pp_support_state = AMD_CG_SUPPORT_MC_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_MC_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_MC_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
@@ -1382,11 +1382,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_SDMA_LS | AMD_CG_SUPPORT_SDMA_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_LS) {
-			pp_support_state = AMD_CG_SUPPORT_SDMA_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_SDMA_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_SDMA_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
@@ -1401,11 +1401,11 @@ static int vi_common_set_clockgating_state_by_smu(void *handle,
 
 	if (adev->cg_flags & (AMD_CG_SUPPORT_HDP_LS | AMD_CG_SUPPORT_HDP_MGCG)) {
 		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_LS) {
-			pp_support_state = AMD_CG_SUPPORT_HDP_LS;
+			pp_support_state = PP_STATE_SUPPORT_LS;
 			pp_state = PP_STATE_LS;
 		}
 		if (adev->cg_flags & AMD_CG_SUPPORT_HDP_MGCG) {
-			pp_support_state |= AMD_CG_SUPPORT_HDP_MGCG;
+			pp_support_state |= PP_STATE_SUPPORT_CG;
 			pp_state |= PP_STATE_CG;
 		}
 		if (state == AMD_CG_STATE_UNGATE)
-- 
cgit v1.2.3


From 3d75a8b689af2824dabe79d250b1ec535341109d Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 12 Jul 2018 08:38:09 -0500
Subject: drm/amdgpu/pp/smu7: use a local variable for toc indexing
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather than using the index variable stored in vram.  If
the device fails to come back online after a resume cycle,
reads from vram will return all 1s which will cause a
segfault. Based on a patch from Thomas Martitz <kugel@rockbox.org>.
This avoids the segfault, but we still need to sort out
why the GPU does not come back online after a resume.

Bug: https://bugs.freedesktop.org/show_bug.cgi?id=105760
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c | 23 +++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index d644a9bb9078..9f407c48d4f0 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -381,6 +381,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	uint32_t fw_to_load;
 	int result = 0;
 	struct SMU_DRAMData_TOC *toc;
+	uint32_t num_entries = 0;
 
 	if (!hwmgr->reload_fw) {
 		pr_info("skip reloading...\n");
@@ -422,41 +423,41 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 	}
 
 	toc = (struct SMU_DRAMData_TOC *)smu_data->header;
-	toc->num_entries = 0;
 	toc->structure_version = 1;
 
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_RLC_G, &toc->entry[toc->num_entries++]),
+				UCODE_ID_RLC_G, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_CE, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_CE, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_PFP, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_PFP, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_ME, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_ME, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_MEC, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT1, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_MEC_JT1, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT2, &toc->entry[toc->num_entries++]),
+				UCODE_ID_CP_MEC_JT2, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA0, &toc->entry[toc->num_entries++]),
+				UCODE_ID_SDMA0, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
+				UCODE_ID_SDMA1, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 	if (!hwmgr->not_vf)
 		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]),
+				UCODE_ID_MEC_STORAGE, &toc->entry[num_entries++]),
 				"Failed to Get Firmware Entry.", return -EINVAL);
 
+	toc->num_entries = num_entries;
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr));
 
-- 
cgit v1.2.3


From 2bce4be03738bc679c61f74fd42dd9e45c9a9959 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 11 Jul 2018 13:24:53 -0500
Subject: drm/amdgpu/pp/smu7: drop unused values in smu data structure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

use kaddr directly rather than secondary variable.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c | 3 +--
 drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h | 2 --
 2 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index 9f407c48d4f0..0f11c5341c49 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -422,7 +422,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 			   + UCODE_ID_CP_MEC_JT2_MASK;
 	}
 
-	toc = (struct SMU_DRAMData_TOC *)smu_data->header;
+	toc = (struct SMU_DRAMData_TOC *)smu_data->header_buffer.kaddr;
 	toc->structure_version = 1;
 
 	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
@@ -591,7 +591,6 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 	if (r)
 		return -EINVAL;
 
-	smu_data->header = smu_data->header_buffer.kaddr;
 	smu_data->header_buffer.mc_addr = mc_addr;
 
 	if (!hwmgr->not_vf)
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
index 39c9bfda0ab4..e6def283b731 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
@@ -37,8 +37,6 @@ struct smu7_buffer_entry {
 };
 
 struct smu7_smumgr {
-	uint8_t *header;
-	uint8_t *mec_image;
 	struct smu7_buffer_entry smu_buffer;
 	struct smu7_buffer_entry header_buffer;
 
-- 
cgit v1.2.3


From 82088d5d7de1ef3575206cc3284dc219d0bd8fab Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 11 Jul 2018 13:43:40 -0500
Subject: drm/amdgpu/pp/smu7: remove local mc_addr variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

use the structure member directly.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index 0f11c5341c49..cb5da61f214b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -571,7 +571,6 @@ int smu7_setup_pwr_virus(struct pp_hwmgr *hwmgr)
 int smu7_init(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_smumgr *smu_data;
-	uint64_t mc_addr = 0;
 	int r;
 	/* Allocate memory for backend private data */
 	smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
@@ -585,14 +584,12 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 		PAGE_SIZE,
 		AMDGPU_GEM_DOMAIN_VRAM,
 		&smu_data->header_buffer.handle,
-		&mc_addr,
+		&smu_data->header_buffer.mc_addr,
 		&smu_data->header_buffer.kaddr);
 
 	if (r)
 		return -EINVAL;
 
-	smu_data->header_buffer.mc_addr = mc_addr;
-
 	if (!hwmgr->not_vf)
 		return 0;
 
@@ -602,7 +599,7 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 		PAGE_SIZE,
 		AMDGPU_GEM_DOMAIN_VRAM,
 		&smu_data->smu_buffer.handle,
-		&mc_addr,
+		&smu_data->smu_buffer.mc_addr,
 		&smu_data->smu_buffer.kaddr);
 
 	if (r) {
@@ -611,7 +608,6 @@ int smu7_init(struct pp_hwmgr *hwmgr)
 					&smu_data->header_buffer.kaddr);
 		return -EINVAL;
 	}
-	smu_data->smu_buffer.mc_addr = mc_addr;
 
 	if (smum_is_hw_avfs_present(hwmgr))
 		hwmgr->avfs_supported = true;
-- 
cgit v1.2.3


From d92867122cd952485a4d209829bfa935689b14fe Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 12 Jul 2018 00:38:23 -0500
Subject: drm/amdgpu/pp/smu7: cache smu firmware toc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rather than calculating it everytime we rebuild the toc
buffer, calculate it once initially and then just copy
the cached results to the vram buffer.

Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c | 92 +++++++++++++---------
 drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h |  1 +
 2 files changed, 54 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
index cb5da61f214b..a029e47c2319 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.c
@@ -379,9 +379,7 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 {
 	struct smu7_smumgr *smu_data = (struct smu7_smumgr *)(hwmgr->smu_backend);
 	uint32_t fw_to_load;
-	int result = 0;
-	struct SMU_DRAMData_TOC *toc;
-	uint32_t num_entries = 0;
+	int r = 0;
 
 	if (!hwmgr->reload_fw) {
 		pr_info("skip reloading...\n");
@@ -422,49 +420,62 @@ int smu7_request_smu_load_fw(struct pp_hwmgr *hwmgr)
 			   + UCODE_ID_CP_MEC_JT2_MASK;
 	}
 
-	toc = (struct SMU_DRAMData_TOC *)smu_data->header_buffer.kaddr;
-	toc->structure_version = 1;
-
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_RLC_G, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_CE, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_PFP, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_ME, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT1, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_CP_MEC_JT2, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA0, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_SDMA1, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
-	if (!hwmgr->not_vf)
-		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
-				UCODE_ID_MEC_STORAGE, &toc->entry[num_entries++]),
-				"Failed to Get Firmware Entry.", return -EINVAL);
+	if (!smu_data->toc) {
+		struct SMU_DRAMData_TOC *toc;
 
-	toc->num_entries = num_entries;
+		smu_data->toc = kzalloc(sizeof(struct SMU_DRAMData_TOC), GFP_KERNEL);
+		if (!smu_data->toc)
+			return -ENOMEM;
+		toc = smu_data->toc;
+		toc->num_entries = 0;
+		toc->structure_version = 1;
+
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_RLC_G, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_CE, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_PFP, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_ME, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_MEC, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_MEC_JT1, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_CP_MEC_JT2, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_SDMA0, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_SDMA1, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+		if (!hwmgr->not_vf)
+			PP_ASSERT_WITH_CODE(0 == smu7_populate_single_firmware_entry(hwmgr,
+				UCODE_ID_MEC_STORAGE, &toc->entry[toc->num_entries++]),
+				"Failed to Get Firmware Entry.", r = -EINVAL; goto failed);
+	}
+	memcpy_toio(smu_data->header_buffer.kaddr, smu_data->toc,
+		    sizeof(struct SMU_DRAMData_TOC));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_HI, upper_32_bits(smu_data->header_buffer.mc_addr));
 	smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_DRV_DRAM_ADDR_LO, lower_32_bits(smu_data->header_buffer.mc_addr));
 
 	if (smu7_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_LoadUcodes, fw_to_load))
 		pr_err("Fail to Request SMU Load uCode");
 
-	return result;
+	return r;
+
+failed:
+	kfree(smu_data->toc);
+	smu_data->toc = NULL;
+	return r;
 }
 
 /* Check if the FW has been loaded, SMU will not return if loading has not finished. */
@@ -629,6 +640,9 @@ int smu7_smu_fini(struct pp_hwmgr *hwmgr)
 					&smu_data->smu_buffer.mc_addr,
 					&smu_data->smu_buffer.kaddr);
 
+
+	kfree(smu_data->toc);
+	smu_data->toc = NULL;
 	kfree(hwmgr->smu_backend);
 	hwmgr->smu_backend = NULL;
 	return 0;
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
index e6def283b731..01f0538fba6b 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu7_smumgr.h
@@ -39,6 +39,7 @@ struct smu7_buffer_entry {
 struct smu7_smumgr {
 	struct smu7_buffer_entry smu_buffer;
 	struct smu7_buffer_entry header_buffer;
+	struct SMU_DRAMData_TOC *toc;
 
 	uint32_t                             soft_regs_start;
 	uint32_t                             dpm_table_start;
-- 
cgit v1.2.3


From f3ed5df84c268235fb1d489ab8979af423da02de Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Fri, 13 Jul 2018 16:17:43 -0400
Subject: drm/amdkfd: Consolidate duplicate memory banks info in topology

If there are several memory banks that has the same properties in CRAT,
we aggregate them into one memory bank. This cleans up memory banks on
APUs (e.g. Raven) where the CRAT reports each memory channel as a
separate bank. This only confuses user mode, which only deals with
virtual memory.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_crat.c | 57 ++++++++++++++++++++++++++++-------
 1 file changed, 46 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
index 296b3f230280..ee4996029a86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.c
@@ -189,6 +189,21 @@ static int kfd_parse_subtype_cu(struct crat_subtype_computeunit *cu,
 	return 0;
 }
 
+static struct kfd_mem_properties *
+find_subtype_mem(uint32_t heap_type, uint32_t flags, uint32_t width,
+		struct kfd_topology_device *dev)
+{
+	struct kfd_mem_properties *props;
+
+	list_for_each_entry(props, &dev->mem_props, list) {
+		if (props->heap_type == heap_type
+				&& props->flags == flags
+				&& props->width == width)
+			return props;
+	}
+
+	return NULL;
+}
 /* kfd_parse_subtype_mem - parse memory subtypes and attach it to correct
  * topology device present in the device_list
  */
@@ -197,36 +212,56 @@ static int kfd_parse_subtype_mem(struct crat_subtype_memory *mem,
 {
 	struct kfd_mem_properties *props;
 	struct kfd_topology_device *dev;
+	uint32_t heap_type;
+	uint64_t size_in_bytes;
+	uint32_t flags = 0;
+	uint32_t width;
 
 	pr_debug("Found memory entry in CRAT table with proximity_domain=%d\n",
 			mem->proximity_domain);
 	list_for_each_entry(dev, device_list, list) {
 		if (mem->proximity_domain == dev->proximity_domain) {
-			props = kfd_alloc_struct(props);
-			if (!props)
-				return -ENOMEM;
-
 			/* We're on GPU node */
 			if (dev->node_props.cpu_cores_count == 0) {
 				/* APU */
 				if (mem->visibility_type == 0)
-					props->heap_type =
+					heap_type =
 						HSA_MEM_HEAP_TYPE_FB_PRIVATE;
 				/* dGPU */
 				else
-					props->heap_type = mem->visibility_type;
+					heap_type = mem->visibility_type;
 			} else
-				props->heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
+				heap_type = HSA_MEM_HEAP_TYPE_SYSTEM;
 
 			if (mem->flags & CRAT_MEM_FLAGS_HOT_PLUGGABLE)
-				props->flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
+				flags |= HSA_MEM_FLAGS_HOT_PLUGGABLE;
 			if (mem->flags & CRAT_MEM_FLAGS_NON_VOLATILE)
-				props->flags |= HSA_MEM_FLAGS_NON_VOLATILE;
+				flags |= HSA_MEM_FLAGS_NON_VOLATILE;
 
-			props->size_in_bytes =
+			size_in_bytes =
 				((uint64_t)mem->length_high << 32) +
 							mem->length_low;
-			props->width = mem->width;
+			width = mem->width;
+
+			/* Multiple banks of the same type are aggregated into
+			 * one. User mode doesn't care about multiple physical
+			 * memory segments. It's managed as a single virtual
+			 * heap for user mode.
+			 */
+			props = find_subtype_mem(heap_type, flags, width, dev);
+			if (props) {
+				props->size_in_bytes += size_in_bytes;
+				break;
+			}
+
+			props = kfd_alloc_struct(props);
+			if (!props)
+				return -ENOMEM;
+
+			props->heap_type = heap_type;
+			props->flags = flags;
+			props->size_in_bytes = size_in_bytes;
+			props->width = width;
 
 			dev->node_props.mem_banks_count++;
 			list_add_tail(&props->list, &dev->mem_props);
-- 
cgit v1.2.3


From 98bb92222eef6ac022f352aa4224f4c94a119199 Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Fri, 13 Jul 2018 16:17:44 -0400
Subject: drm/amdkfd: Make SDMA engine number an ASIC-dependent variable

On Raven there is only one SDMA engine instead of previously assumed two,
so we need to adapt our code to this new scenario.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c            | 12 +++++++++
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.c  | 29 +++++++++++++++-------
 .../gpu/drm/amd/amdkfd/kfd_device_queue_manager.h  |  6 ++---
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              |  1 +
 .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c |  3 +--
 5 files changed, 36 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 8faa8db3eba5..572235cdd061 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -52,6 +52,7 @@ static const struct kfd_device_info kaveri_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info carrizo_device_info = {
@@ -67,6 +68,7 @@ static const struct kfd_device_info carrizo_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = true,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 #endif
 
@@ -83,6 +85,7 @@ static const struct kfd_device_info hawaii_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_device_info = {
@@ -97,6 +100,7 @@ static const struct kfd_device_info tonga_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info tonga_vf_device_info = {
@@ -111,6 +115,7 @@ static const struct kfd_device_info tonga_vf_device_info = {
 	.supports_cwsr = false,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_device_info = {
@@ -125,6 +130,7 @@ static const struct kfd_device_info fiji_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info fiji_vf_device_info = {
@@ -139,6 +145,7 @@ static const struct kfd_device_info fiji_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
@@ -154,6 +161,7 @@ static const struct kfd_device_info polaris10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris10_vf_device_info = {
@@ -168,6 +176,7 @@ static const struct kfd_device_info polaris10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info polaris11_device_info = {
@@ -182,6 +191,7 @@ static const struct kfd_device_info polaris11_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = true,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_device_info = {
@@ -196,6 +206,7 @@ static const struct kfd_device_info vega10_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 static const struct kfd_device_info vega10_vf_device_info = {
@@ -210,6 +221,7 @@ static const struct kfd_device_info vega10_vf_device_info = {
 	.supports_cwsr = true,
 	.needs_iommu_device = false,
 	.needs_pci_atomics = false,
+	.num_sdma_engines = 2,
 };
 
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 97c9f10ff473..ace94d6e54cf 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -101,6 +101,17 @@ unsigned int get_pipes_per_mec(struct device_queue_manager *dqm)
 	return dqm->dev->shared_resources.num_pipe_per_mec;
 }
 
+static unsigned int get_num_sdma_engines(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines;
+}
+
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm)
+{
+	return dqm->dev->device_info->num_sdma_engines
+			* KFD_SDMA_QUEUES_PER_ENGINE;
+}
+
 void program_sh_mem_settings(struct device_queue_manager *dqm,
 					struct qcm_process_device *qpd)
 {
@@ -855,7 +866,7 @@ static int initialize_nocpsch(struct device_queue_manager *dqm)
 	}
 
 	dqm->vmid_bitmap = (1 << dqm->dev->vm_info.vmid_num_kfd) - 1;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
 
 	return 0;
 }
@@ -903,7 +914,7 @@ static int allocate_sdma_queue(struct device_queue_manager *dqm,
 static void deallocate_sdma_queue(struct device_queue_manager *dqm,
 				unsigned int sdma_queue_id)
 {
-	if (sdma_queue_id >= CIK_SDMA_QUEUES)
+	if (sdma_queue_id >= get_num_sdma_queues(dqm))
 		return;
 	dqm->sdma_bitmap |= (1 << sdma_queue_id);
 }
@@ -923,8 +934,8 @@ static int create_sdma_queue_nocpsch(struct device_queue_manager *dqm,
 	if (retval)
 		return retval;
 
-	q->properties.sdma_queue_id = q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
-	q->properties.sdma_engine_id = q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+	q->properties.sdma_queue_id = q->sdma_id / get_num_sdma_engines(dqm);
+	q->properties.sdma_engine_id = q->sdma_id % get_num_sdma_engines(dqm);
 
 	retval = allocate_doorbell(qpd, q);
 	if (retval)
@@ -1011,7 +1022,7 @@ static int initialize_cpsch(struct device_queue_manager *dqm)
 	dqm->queue_count = dqm->processes_count = 0;
 	dqm->sdma_queue_count = 0;
 	dqm->active_runlist = false;
-	dqm->sdma_bitmap = (1 << CIK_SDMA_QUEUES) - 1;
+	dqm->sdma_bitmap = (1 << get_num_sdma_queues(dqm)) - 1;
 
 	INIT_WORK(&dqm->hw_exception_work, kfd_process_hw_exception);
 
@@ -1142,9 +1153,9 @@ static int create_queue_cpsch(struct device_queue_manager *dqm, struct queue *q,
 		if (retval)
 			goto out_unlock;
 		q->properties.sdma_queue_id =
-			q->sdma_id / CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id / get_num_sdma_engines(dqm);
 		q->properties.sdma_engine_id =
-			q->sdma_id % CIK_SDMA_QUEUES_PER_ENGINE;
+			q->sdma_id % get_num_sdma_engines(dqm);
 	}
 
 	retval = allocate_doorbell(qpd, q);
@@ -1791,8 +1802,8 @@ int dqm_debugfs_hqds(struct seq_file *m, void *data)
 		}
 	}
 
-	for (pipe = 0; pipe < CIK_SDMA_ENGINE_NUM; pipe++) {
-		for (queue = 0; queue < CIK_SDMA_QUEUES_PER_ENGINE; queue++) {
+	for (pipe = 0; pipe < get_num_sdma_engines(dqm); pipe++) {
+		for (queue = 0; queue < KFD_SDMA_QUEUES_PER_ENGINE; queue++) {
 			r = dqm->dev->kfd2kgd->hqd_sdma_dump(
 				dqm->dev->kgd, pipe, queue, &dump, &n_regs);
 			if (r)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
index 52e708c4f9a5..00da3169a004 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h
@@ -33,10 +33,7 @@
 
 #define KFD_UNMAP_LATENCY_MS			(4000)
 #define QUEUE_PREEMPT_DEFAULT_TIMEOUT_MS (2 * KFD_UNMAP_LATENCY_MS + 1000)
-
-#define CIK_SDMA_QUEUES				(4)
-#define CIK_SDMA_QUEUES_PER_ENGINE		(2)
-#define CIK_SDMA_ENGINE_NUM			(2)
+#define KFD_SDMA_QUEUES_PER_ENGINE		(2)
 
 struct device_process_node {
 	struct qcm_process_device *qpd;
@@ -214,6 +211,7 @@ void program_sh_mem_settings(struct device_queue_manager *dqm,
 unsigned int get_queues_num(struct device_queue_manager *dqm);
 unsigned int get_queues_per_pipe(struct device_queue_manager *dqm);
 unsigned int get_pipes_per_mec(struct device_queue_manager *dqm);
+unsigned int get_num_sdma_queues(struct device_queue_manager *dqm);
 
 static inline unsigned int get_sh_mem_bases_32(struct kfd_process_device *pdd)
 {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index 37d179ed51dc..ca83254719fc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -203,6 +203,7 @@ struct kfd_device_info {
 	bool supports_cwsr;
 	bool needs_iommu_device;
 	bool needs_pci_atomics;
+	unsigned int num_sdma_engines;
 };
 
 struct kfd_mem_obj {
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index 1303b1457950..eb4e5fb4f2f2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -186,8 +186,7 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 
 	switch (type) {
 	case KFD_QUEUE_TYPE_SDMA:
-		if (dev->dqm->queue_count >=
-			CIK_SDMA_QUEUES_PER_ENGINE * CIK_SDMA_ENGINE_NUM) {
+		if (dev->dqm->queue_count >= get_num_sdma_queues(dev->dqm)) {
 			pr_err("Over-subscription is not allowed for SDMA.\n");
 			retval = -EPERM;
 			goto err_create_queue;
-- 
cgit v1.2.3


From eab69801cf4388aeba2c730ce4db746ae164eada Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Fri, 13 Jul 2018 16:17:45 -0400
Subject: drm/amdkfd: Avoid flooding dmesg on Raven due to IOMMU issues

On Raven Invalid PPRs (peripheral page requests) can be reported
because multiple PPRs can be still queued when memory is freed.
Apply a rate limit to avoid flooding the log in this case.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_iommu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
index c71817963eea..7a61f38c09e6 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_iommu.c
@@ -190,7 +190,7 @@ static int iommu_invalid_ppr_cb(struct pci_dev *pdev, int pasid,
 {
 	struct kfd_dev *dev;
 
-	dev_warn(kfd_device,
+	dev_warn_ratelimited(kfd_device,
 			"Invalid PPR device %x:%x.%x pasid %d address 0x%lX flags 0x%X",
 			PCI_BUS_NUM(pdev->devfn),
 			PCI_SLOT(pdev->devfn),
-- 
cgit v1.2.3


From 8725aecac331954e0827d6bed7be02eb7b8f1e9e Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Fri, 13 Jul 2018 16:17:46 -0400
Subject: drm/amdkfd: Workaround to accommodate Raven too many PPR issue

On Raven multiple PPRs can be queued up by the hardware. When the
first of those requests is handled by the IOMMU driver, the memory
access succeeds. After that the application may be done with the
memory and unmap it. At that point the page table entries are
invalidated, but there are still outstanding duplicate PPRs for those
addresses. When the IOMMU driver processes those duplicate requests,
it finds invalid page table entries and triggers an invalid PPR fault.

As a workaround, don't signal invalid PPR faults on Raven to avoid
segfaulting applications that haven't done anything wrong. As a side
effect, real GPU memory access faults may go unnoticed by the
application.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_events.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 820133cdef83..4dcacce2db86 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -932,13 +932,24 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	up_read(&mm->mmap_sem);
 	mmput(mm);
 
-	mutex_lock(&p->event_mutex);
+	pr_debug("notpresent %d, noexecute %d, readonly %d\n",
+			memory_exception_data.failure.NotPresent,
+			memory_exception_data.failure.NoExecute,
+			memory_exception_data.failure.ReadOnly);
 
-	/* Lookup events by type and signal them */
-	lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
-			&memory_exception_data);
+	/* Workaround on Raven to not kill the process when memory is freed
+	 * before IOMMU is able to finish processing all the excessive PPRs
+	 */
+	if (dev->device_info->asic_family != CHIP_RAVEN) {
+		mutex_lock(&p->event_mutex);
+
+		/* Lookup events by type and signal them */
+		lookup_events_by_type_and_signal(p, KFD_EVENT_TYPE_MEMORY,
+				&memory_exception_data);
+
+		mutex_unlock(&p->event_mutex);
+	}
 
-	mutex_unlock(&p->event_mutex);
 	kfd_unref_process(p);
 }
 #endif /* KFD_SUPPORT_IOMMU_V2 */
-- 
cgit v1.2.3


From 359cecdd499783abcf4ba6589066db8d8cb58e88 Mon Sep 17 00:00:00 2001
From: Yong Zhao <yong.zhao@amd.com>
Date: Fri, 13 Jul 2018 16:17:47 -0400
Subject: drm/amdkfd: Optimize out some duplicated code in
 kfd_signal_iommu_event()

memory_exception_data is already initialized for not-present faults.
It only needs to be overridden for permission faults.

Signed-off-by: Yong Zhao <yong.zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_events.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_events.c b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
index 4dcacce2db86..e9f0e0a1b41c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_events.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_events.c
@@ -911,22 +911,18 @@ void kfd_signal_iommu_event(struct kfd_dev *dev, unsigned int pasid,
 	memory_exception_data.failure.NotPresent = 1;
 	memory_exception_data.failure.NoExecute = 0;
 	memory_exception_data.failure.ReadOnly = 0;
-	if (vma) {
-		if (vma->vm_start > address) {
-			memory_exception_data.failure.NotPresent = 1;
-			memory_exception_data.failure.NoExecute = 0;
+	if (vma && address >= vma->vm_start) {
+		memory_exception_data.failure.NotPresent = 0;
+
+		if (is_write_requested && !(vma->vm_flags & VM_WRITE))
+			memory_exception_data.failure.ReadOnly = 1;
+		else
 			memory_exception_data.failure.ReadOnly = 0;
-		} else {
-			memory_exception_data.failure.NotPresent = 0;
-			if (is_write_requested && !(vma->vm_flags & VM_WRITE))
-				memory_exception_data.failure.ReadOnly = 1;
-			else
-				memory_exception_data.failure.ReadOnly = 0;
-			if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
-				memory_exception_data.failure.NoExecute = 1;
-			else
-				memory_exception_data.failure.NoExecute = 0;
-		}
+
+		if (is_execute_requested && !(vma->vm_flags & VM_EXEC))
+			memory_exception_data.failure.NoExecute = 1;
+		else
+			memory_exception_data.failure.NoExecute = 0;
 	}
 
 	up_read(&mm->mmap_sem);
-- 
cgit v1.2.3


From 4d663df6588709e8763b976310117aa0f9825bc6 Mon Sep 17 00:00:00 2001
From: Yong Zhao <Yong.Zhao@amd.com>
Date: Fri, 13 Jul 2018 16:17:48 -0400
Subject: drm/amdkfd: Enable Raven for KFD

Add DID and kfd_device_info for Raven.

Signed-off-by: Yong Zhao <Yong.Zhao@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
index 572235cdd061..1b048715ab8a 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c
@@ -70,6 +70,21 @@ static const struct kfd_device_info carrizo_device_info = {
 	.needs_pci_atomics = false,
 	.num_sdma_engines = 2,
 };
+
+static const struct kfd_device_info raven_device_info = {
+	.asic_family = CHIP_RAVEN,
+	.max_pasid_bits = 16,
+	.max_no_of_hqd  = 24,
+	.doorbell_size  = 8,
+	.ih_ring_entry_size = 8 * sizeof(uint32_t),
+	.event_interrupt_class = &event_interrupt_class_v9,
+	.num_of_watch_points = 4,
+	.mqd_size_aligned = MQD_SIZE_ALIGNED,
+	.supports_cwsr = true,
+	.needs_iommu_device = true,
+	.needs_pci_atomics = true,
+	.num_sdma_engines = 1,
+};
 #endif
 
 static const struct kfd_device_info hawaii_device_info = {
@@ -259,6 +274,7 @@ static const struct kfd_deviceid supported_devices[] = {
 	{ 0x9875, &carrizo_device_info },	/* Carrizo */
 	{ 0x9876, &carrizo_device_info },	/* Carrizo */
 	{ 0x9877, &carrizo_device_info },	/* Carrizo */
+	{ 0x15DD, &raven_device_info },		/* Raven */
 #endif
 	{ 0x67A0, &hawaii_device_info },	/* Hawaii */
 	{ 0x67A1, &hawaii_device_info },	/* Hawaii */
-- 
cgit v1.2.3


From c921c2077b32081617789a645120148bc8b60c98 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Fri, 13 Jul 2018 12:16:43 +0300
Subject: net: ipmr: add support for passing full packet on wrong vif

This patch adds support for IGMPMSG_WRVIFWHOLE which is used to pass
full packet and real vif id when the incoming interface is wrong.
While the RP and FHR are setting up state we need to be sending the
registers encapsulated with all the data inside otherwise we lose it.
The RP then decapsulates it and forwards it to the interested parties.
Currently with WRONGVIF we can only be sending empty register packets
and will lose that data.
This behaviour can be enabled by using MRT_PIM with
val == IGMPMSG_WRVIFWHOLE. This doesn't prevent IGMPMSG_WRONGVIF from
happening, it happens in addition to it, also it is controlled by the same
throttling parameters as WRONGVIF (i.e. 1 packet per 3 seconds currently).
Both messages are generated to keep backwards compatibily and avoid
breaking someone who was enabling MRT_PIM with val == 4, since any
positive val is accepted and treated the same.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/mroute_base.h |  1 +
 include/uapi/linux/mroute.h |  2 ++
 net/ipv4/ipmr.c             | 21 ++++++++++++++++-----
 3 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index fd436cdd4725..6675b9f81979 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -254,6 +254,7 @@ struct mr_table {
 	atomic_t		cache_resolve_queue_len;
 	bool			mroute_do_assert;
 	bool			mroute_do_pim;
+	bool			mroute_do_wrvifwhole;
 	int			mroute_reg_vif_num;
 };
 
diff --git a/include/uapi/linux/mroute.h b/include/uapi/linux/mroute.h
index 10f9ff9426a2..5d37a9ccce63 100644
--- a/include/uapi/linux/mroute.h
+++ b/include/uapi/linux/mroute.h
@@ -120,6 +120,7 @@ enum {
 	IPMRA_TABLE_MROUTE_DO_ASSERT,
 	IPMRA_TABLE_MROUTE_DO_PIM,
 	IPMRA_TABLE_VIFS,
+	IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE,
 	__IPMRA_TABLE_MAX
 };
 #define IPMRA_TABLE_MAX (__IPMRA_TABLE_MAX - 1)
@@ -173,5 +174,6 @@ enum {
 #define IGMPMSG_NOCACHE		1		/* Kern cache fill request to mrouted */
 #define IGMPMSG_WRONGVIF	2		/* For PIM assert processing (unused) */
 #define IGMPMSG_WHOLEPKT	3		/* For PIM Register processing */
+#define IGMPMSG_WRVIFWHOLE	4		/* For PIM Register and assert processing */
 
 #endif /* _UAPI__LINUX_MROUTE_H */
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 82f914122f1b..5660adcf7a04 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1052,7 +1052,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
 	struct sk_buff *skb;
 	int ret;
 
-	if (assert == IGMPMSG_WHOLEPKT)
+	if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE)
 		skb = skb_realloc_headroom(pkt, sizeof(struct iphdr));
 	else
 		skb = alloc_skb(128, GFP_ATOMIC);
@@ -1060,7 +1060,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
 	if (!skb)
 		return -ENOBUFS;
 
-	if (assert == IGMPMSG_WHOLEPKT) {
+	if (assert == IGMPMSG_WHOLEPKT || assert == IGMPMSG_WRVIFWHOLE) {
 		/* Ugly, but we have no choice with this interface.
 		 * Duplicate old header, fix ihl, length etc.
 		 * And all this only to mangle msg->im_msgtype and
@@ -1071,9 +1071,12 @@ static int ipmr_cache_report(struct mr_table *mrt,
 		skb_reset_transport_header(skb);
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		memcpy(msg, skb_network_header(pkt), sizeof(struct iphdr));
-		msg->im_msgtype = IGMPMSG_WHOLEPKT;
+		msg->im_msgtype = assert;
 		msg->im_mbz = 0;
-		msg->im_vif = mrt->mroute_reg_vif_num;
+		if (assert == IGMPMSG_WRVIFWHOLE)
+			msg->im_vif = vifi;
+		else
+			msg->im_vif = mrt->mroute_reg_vif_num;
 		ip_hdr(skb)->ihl = sizeof(struct iphdr) >> 2;
 		ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(pkt)->tot_len) +
 					     sizeof(struct iphdr));
@@ -1372,6 +1375,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 	struct mr_table *mrt;
 	struct vifctl vif;
 	struct mfcctl mfc;
+	bool do_wrvifwhole;
 	u32 uval;
 
 	/* There's one exception to the lock - MRT_DONE which needs to unlock */
@@ -1502,10 +1506,12 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval,
 			break;
 		}
 
+		do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE);
 		val = !!val;
 		if (val != mrt->mroute_do_pim) {
 			mrt->mroute_do_pim = val;
 			mrt->mroute_do_assert = val;
+			mrt->mroute_do_wrvifwhole = do_wrvifwhole;
 		}
 		break;
 	case MRT_TABLE:
@@ -1983,6 +1989,9 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
 			       MFC_ASSERT_THRESH)) {
 			c->_c.mfc_un.res.last_assert = jiffies;
 			ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF);
+			if (mrt->mroute_do_wrvifwhole)
+				ipmr_cache_report(mrt, skb, true_vifi,
+						  IGMPMSG_WRVIFWHOLE);
 		}
 		goto dont_forward;
 	}
@@ -2659,7 +2668,9 @@ static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb)
 			mrt->mroute_reg_vif_num) ||
 	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT,
 		       mrt->mroute_do_assert) ||
-	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim))
+	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) ||
+	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE,
+		       mrt->mroute_do_wrvifwhole))
 		return false;
 
 	return true;
-- 
cgit v1.2.3


From 9dd1a981a22a6c5416e9a179912fb1215225235f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 13 Jul 2018 21:35:27 +0100
Subject: drm/i915/selftests: Include the start of each subtest in the GEM
 trace

Knowing the boundary of each subtest can be instrumental in digesting
the voluminous trace output and finding the critical piece of
information.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180713203529.1973-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/i915_selftest.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/i915_selftest.c b/drivers/gpu/drm/i915/selftests/i915_selftest.c
index addc5a599c4a..86c54ea37f48 100644
--- a/drivers/gpu/drm/i915/selftests/i915_selftest.c
+++ b/drivers/gpu/drm/i915/selftests/i915_selftest.c
@@ -210,6 +210,8 @@ int __i915_subtests(const char *caller,
 			return -EINTR;
 
 		pr_debug(DRIVER_NAME ": Running %s/%s\n", caller, st->name);
+		GEM_TRACE("Running %s/%s\n", caller, st->name);
+
 		err = st->func(data);
 		if (err && err != -EINTR) {
 			pr_err(DRIVER_NAME "/%s: %s failed with error %d\n",
-- 
cgit v1.2.3


From 9701975e851082d179faaab9c6306a7800d86c0f Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 13 Jul 2018 21:35:28 +0100
Subject: drm/i915: Do not short-circuit tasklets during reset

Inside intel_engine_is_idle(), we flush the tasklet to ensure that is
being run in a timely fashion (ksoftirqd has taught us to expect the
worst). However, if we are in the middle of reset, the HW may not yet be
ready to execute the submission tasklet and so we must respect the
disable flag.

Fixes: dd0cf235d81f ("drm/i915: Speed up idle detection by kicking the tasklets")
Testcase: igt/drv_selftest/live_hangcheck
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180713203529.1973-2-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_engine_cs.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c
index 220050107c48..2d1952849d69 100644
--- a/drivers/gpu/drm/i915/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/intel_engine_cs.c
@@ -989,16 +989,18 @@ bool intel_engine_is_idle(struct intel_engine_cs *engine)
 
 	/* Waiting to drain ELSP? */
 	if (READ_ONCE(engine->execlists.active)) {
-		struct intel_engine_execlists *execlists = &engine->execlists;
+		struct tasklet_struct *t = &engine->execlists.tasklet;
 
 		local_bh_disable();
-		if (tasklet_trylock(&execlists->tasklet)) {
-			execlists->tasklet.func(execlists->tasklet.data);
-			tasklet_unlock(&execlists->tasklet);
+		if (tasklet_trylock(t)) {
+			/* Must wait for any GPU reset in progress. */
+			if (__tasklet_is_enabled(t))
+				t->func(t->data);
+			tasklet_unlock(t);
 		}
 		local_bh_enable();
 
-		if (READ_ONCE(execlists->active))
+		if (READ_ONCE(engine->execlists.active))
 			return false;
 	}
 
-- 
cgit v1.2.3


From 60a94324541361542f1ffb12844f4cb737695ba5 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Fri, 13 Jul 2018 21:35:29 +0100
Subject: drm/i915/execlists: Drop clear_gtiir() on GPU reset

With the new CSB processing code, we are not vulnerable to delayed
delivery of a pre-reset interrupt as we use the CSB status pointers in
the HWSP to decide if we need to parse any CSB events and no longer need
to wait for the first post-reset interrupt to be assured that the CSB
mmio registers are valid.

The new icl code to clear registers has a nasty lock inversion:
[   57.409776] ======================================================
[   57.409779] WARNING: possible circular locking dependency detected
[   57.409783] 4.18.0-rc4-CI-CI_DII_1137+ #1 Tainted: G     U  W
[   57.409785] ------------------------------------------------------
[   57.409788] swapper/6/0 is trying to acquire lock:
[   57.409790] 000000004f304ee5 (&engine->timeline.lock/1){-.-.}, at: execlists_submit_request+0x2b/0x1a0 [i915]
[   57.409841]
               but task is already holding lock:
[   57.409844] 00000000aad89594 (&(&rq->lock)->rlock#2){-.-.}, at: notify_ring+0x2b2/0x480 [i915]
[   57.409869]
               which lock already depends on the new lock.

[   57.409872]
               the existing dependency chain (in reverse order) is:
[   57.409876]
               -> #2 (&(&rq->lock)->rlock#2){-.-.}:
[   57.409900]        notify_ring+0x2b2/0x480 [i915]
[   57.409922]        gen8_cs_irq_handler+0x39/0xa0 [i915]
[   57.409943]        gen11_irq_handler+0x2f0/0x420 [i915]
[   57.409949]        __handle_irq_event_percpu+0x42/0x370
[   57.409952]        handle_irq_event_percpu+0x2b/0x70
[   57.409956]        handle_irq_event+0x2f/0x50
[   57.409959]        handle_edge_irq+0xe7/0x190
[   57.409964]        handle_irq+0x67/0x160
[   57.409967]        do_IRQ+0x5e/0x120
[   57.409971]        ret_from_intr+0x0/0x1d
[   57.409974]        _raw_spin_unlock_irqrestore+0x4e/0x60
[   57.409979]        tasklet_action_common.isra.5+0x47/0xb0
[   57.409982]        __do_softirq+0xd9/0x505
[   57.409985]        irq_exit+0xa9/0xc0
[   57.409988]        do_IRQ+0x9a/0x120
[   57.409991]        ret_from_intr+0x0/0x1d
[   57.409995]        cpuidle_enter_state+0xac/0x360
[   57.409999]        do_idle+0x1f3/0x250
[   57.410004]        cpu_startup_entry+0x6a/0x70
[   57.410010]        start_secondary+0x19d/0x1f0
[   57.410015]        secondary_startup_64+0xa5/0xb0
[   57.410018]
               -> #1 (&(&dev_priv->irq_lock)->rlock){-.-.}:
[   57.410081]        clear_gtiir+0x30/0x200 [i915]
[   57.410116]        execlists_reset+0x6e/0x2b0 [i915]
[   57.410140]        i915_reset_engine+0x111/0x190 [i915]
[   57.410165]        i915_handle_error+0x11a/0x4a0 [i915]
[   57.410198]        i915_hangcheck_elapsed+0x378/0x530 [i915]
[   57.410204]        process_one_work+0x248/0x6c0
[   57.410207]        worker_thread+0x37/0x380
[   57.410211]        kthread+0x119/0x130
[   57.410215]        ret_from_fork+0x3a/0x50
[   57.410217]
               -> #0 (&engine->timeline.lock/1){-.-.}:
[   57.410224]        _raw_spin_lock_irqsave+0x33/0x50
[   57.410256]        execlists_submit_request+0x2b/0x1a0 [i915]
[   57.410289]        submit_notify+0x8d/0x124 [i915]
[   57.410314]        __i915_sw_fence_complete+0x81/0x250 [i915]
[   57.410339]        dma_i915_sw_fence_wake+0xd/0x20 [i915]
[   57.410344]        dma_fence_signal_locked+0x79/0x200
[   57.410368]        notify_ring+0x2ba/0x480 [i915]
[   57.410392]        gen8_cs_irq_handler+0x39/0xa0 [i915]
[   57.410416]        gen11_irq_handler+0x2f0/0x420 [i915]
[   57.410421]        __handle_irq_event_percpu+0x42/0x370
[   57.410425]        handle_irq_event_percpu+0x2b/0x70
[   57.410428]        handle_irq_event+0x2f/0x50
[   57.410432]        handle_edge_irq+0xe7/0x190
[   57.410436]        handle_irq+0x67/0x160
[   57.410439]        do_IRQ+0x5e/0x120
[   57.410445]        ret_from_intr+0x0/0x1d
[   57.410449]        cpuidle_enter_state+0xac/0x360
[   57.410453]        do_idle+0x1f3/0x250
[   57.410456]        cpu_startup_entry+0x6a/0x70
[   57.410460]        start_secondary+0x19d/0x1f0
[   57.410464]        secondary_startup_64+0xa5/0xb0
[   57.410466]
               other info that might help us debug this:

[   57.410471] Chain exists of:
                 &engine->timeline.lock/1 --> &(&dev_priv->irq_lock)->rlock --> &(&rq->lock)->rlock#2

[   57.410481]  Possible unsafe locking scenario:

[   57.410485]        CPU0                    CPU1
[   57.410487]        ----                    ----
[   57.410490]   lock(&(&rq->lock)->rlock#2);
[   57.410494]                                lock(&(&dev_priv->irq_lock)->rlock);
[   57.410498]                                lock(&(&rq->lock)->rlock#2);
[   57.410503]   lock(&engine->timeline.lock/1);
[   57.410506]
                *** DEADLOCK ***

[   57.410511] 4 locks held by swapper/6/0:
[   57.410514]  #0: 0000000074575789 (&(&dev_priv->irq_lock)->rlock){-.-.}, at: gen11_irq_handler+0x8a/0x420 [i915]
[   57.410542]  #1: 000000009b29b30e (rcu_read_lock){....}, at: notify_ring+0x1a/0x480 [i915]
[   57.410573]  #2: 00000000aad89594 (&(&rq->lock)->rlock#2){-.-.}, at: notify_ring+0x2b2/0x480 [i915]
[   57.410601]  #3: 000000009b29b30e (rcu_read_lock){....}, at: submit_notify+0x35/0x124 [i915]
[   57.410635]
               stack backtrace:
[   57.410640] CPU: 6 PID: 0 Comm: swapper/6 Tainted: G     U  W         4.18.0-rc4-CI-CI_DII_1137+ #1
[   57.410644] Hardware name: Intel Corporation Ice Lake Client Platform/IceLake U DDR4 SODIMM PD RVP, BIOS ICLSFWR1.R00.2222.A01.1805300339 05/30/2018
[   57.410650] Call Trace:
[   57.410652]  <IRQ>
[   57.410657]  dump_stack+0x67/0x9b
[   57.410662]  print_circular_bug.isra.16+0x1c8/0x2b0
[   57.410666]  __lock_acquire+0x1897/0x1b50
[   57.410671]  ? lock_acquire+0xa6/0x210
[   57.410674]  lock_acquire+0xa6/0x210
[   57.410706]  ? execlists_submit_request+0x2b/0x1a0 [i915]
[   57.410711]  _raw_spin_lock_irqsave+0x33/0x50
[   57.410741]  ? execlists_submit_request+0x2b/0x1a0 [i915]
[   57.410769]  execlists_submit_request+0x2b/0x1a0 [i915]
[   57.410774]  ? _raw_spin_unlock_irqrestore+0x39/0x60
[   57.410804]  submit_notify+0x8d/0x124 [i915]
[   57.410828]  __i915_sw_fence_complete+0x81/0x250 [i915]
[   57.410854]  dma_i915_sw_fence_wake+0xd/0x20 [i915]
[   57.410858]  dma_fence_signal_locked+0x79/0x200
[   57.410882]  notify_ring+0x2ba/0x480 [i915]
[   57.410907]  gen8_cs_irq_handler+0x39/0xa0 [i915]
[   57.410933]  gen11_irq_handler+0x2f0/0x420 [i915]
[   57.410938]  __handle_irq_event_percpu+0x42/0x370
[   57.410943]  handle_irq_event_percpu+0x2b/0x70
[   57.410947]  handle_irq_event+0x2f/0x50
[   57.410951]  handle_edge_irq+0xe7/0x190
[   57.410955]  handle_irq+0x67/0x160
[   57.410958]  do_IRQ+0x5e/0x120
[   57.410962]  common_interrupt+0xf/0xf
[   57.410965]  </IRQ>
[   57.410969] RIP: 0010:cpuidle_enter_state+0xac/0x360
[   57.410972] Code: 44 00 00 31 ff e8 84 93 91 ff 45 84 f6 74 12 9c 58 f6 c4 02 0f 85 31 02 00 00 31 ff e8 7d 30 98 ff e8 e8 0e 94 ff fb 4c 29 fb <48> ba cf f7 53 e3 a5 9b c4 20 48 89 d8 48 c1 fb 3f 48 f7 ea b8 ff
[   57.411015] RSP: 0018:ffffc90000133e90 EFLAGS: 00000216 ORIG_RAX: ffffffffffffffdd
[   57.411023] RAX: ffff8804ae748040 RBX: 000000000002a97d RCX: 0000000000000000
[   57.411029] RDX: 0000000000000046 RSI: ffffffff82141263 RDI: ffffffff820f05a7
[   57.411035] RBP: 0000000000000001 R08: 0000000000000001 R09: 0000000000000000
[   57.411041] R10: 0000000000000000 R11: 0000000000000000 R12: ffffffff8229f078
[   57.411045] R13: ffff8804ab2adfa8 R14: 0000000000000000 R15: 0000000d5de092e3
[   57.411052]  do_idle+0x1f3/0x250
[   57.411055]  cpu_startup_entry+0x6a/0x70
[   57.411059]  start_secondary+0x19d/0x1f0
[   57.411064]  secondary_startup_64+0xa5/0xb0

The easiest remedy is to remove the defunct code.

Fixes: ff047a87cfac ("drm/i915/icl: Correctly clear lost ctx-switch interrupts across reset for Gen11")
References: fd8526e50902 ("drm/i915/execlists: Trust the CSB")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michel Thierry <michel.thierry@intel.com>
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Reviewed-by: Michel Thierry <michel.thierry@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180713203529.1973-3-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_irq.c  |  6 ++--
 drivers/gpu/drm/i915/intel_drv.h |  3 --
 drivers/gpu/drm/i915/intel_lrc.c | 68 ----------------------------------------
 3 files changed, 3 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 6975a169c4e4..5dadefca2ad2 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -263,9 +263,9 @@ static u32
 gen11_gt_engine_identity(struct drm_i915_private * const i915,
 			 const unsigned int bank, const unsigned int bit);
 
-bool gen11_reset_one_iir(struct drm_i915_private * const i915,
-			 const unsigned int bank,
-			 const unsigned int bit)
+static bool gen11_reset_one_iir(struct drm_i915_private * const i915,
+				const unsigned int bank,
+				const unsigned int bit)
 {
 	void __iomem * const regs = i915->regs;
 	u32 dw;
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index a45f6324dd9b..f8d5fafe1f1a 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1353,9 +1353,6 @@ void intel_check_cpu_fifo_underruns(struct drm_i915_private *dev_priv);
 void intel_check_pch_fifo_underruns(struct drm_i915_private *dev_priv);
 
 /* i915_irq.c */
-bool gen11_reset_one_iir(struct drm_i915_private * const i915,
-			 const unsigned int bank,
-			 const unsigned int bit);
 void gen5_enable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen5_disable_gt_irq(struct drm_i915_private *dev_priv, uint32_t mask);
 void gen6_mask_pm_irq(struct drm_i915_private *dev_priv, u32 mask);
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ad436d200758..05567e30efe0 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -796,72 +796,6 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
 	execlists_user_end(execlists);
 }
 
-static void clear_gtiir(struct intel_engine_cs *engine)
-{
-	struct drm_i915_private *dev_priv = engine->i915;
-	int i;
-
-	/*
-	 * Clear any pending interrupt state.
-	 *
-	 * We do it twice out of paranoia that some of the IIR are
-	 * double buffered, and so if we only reset it once there may
-	 * still be an interrupt pending.
-	 */
-	if (INTEL_GEN(dev_priv) >= 11) {
-		static const struct {
-			u8 bank;
-			u8 bit;
-		} gen11_gtiir[] = {
-			[RCS] = {0, GEN11_RCS0},
-			[BCS] = {0, GEN11_BCS},
-			[_VCS(0)] = {1, GEN11_VCS(0)},
-			[_VCS(1)] = {1, GEN11_VCS(1)},
-			[_VCS(2)] = {1, GEN11_VCS(2)},
-			[_VCS(3)] = {1, GEN11_VCS(3)},
-			[_VECS(0)] = {1, GEN11_VECS(0)},
-			[_VECS(1)] = {1, GEN11_VECS(1)},
-		};
-		unsigned long irqflags;
-
-		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gen11_gtiir));
-
-		spin_lock_irqsave(&dev_priv->irq_lock, irqflags);
-		for (i = 0; i < 2; i++) {
-			gen11_reset_one_iir(dev_priv,
-					    gen11_gtiir[engine->id].bank,
-					    gen11_gtiir[engine->id].bit);
-		}
-		spin_unlock_irqrestore(&dev_priv->irq_lock, irqflags);
-	} else {
-		static const u8 gtiir[] = {
-			[RCS]  = 0,
-			[BCS]  = 0,
-			[VCS]  = 1,
-			[VCS2] = 1,
-			[VECS] = 3,
-		};
-
-		GEM_BUG_ON(engine->id >= ARRAY_SIZE(gtiir));
-
-		for (i = 0; i < 2; i++) {
-			I915_WRITE(GEN8_GT_IIR(gtiir[engine->id]),
-				   engine->irq_keep_mask);
-			POSTING_READ(GEN8_GT_IIR(gtiir[engine->id]));
-		}
-		GEM_BUG_ON(I915_READ(GEN8_GT_IIR(gtiir[engine->id])) &
-			   engine->irq_keep_mask);
-	}
-}
-
-static void reset_irq(struct intel_engine_cs *engine)
-{
-	/* Mark all CS interrupts as complete */
-	smp_store_mb(engine->execlists.active, 0);
-
-	clear_gtiir(engine);
-}
-
 static void reset_csb_pointers(struct intel_engine_execlists *execlists)
 {
 	/*
@@ -905,7 +839,6 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 
 	/* Cancel the requests on the HW and clear the ELSP tracker. */
 	execlists_cancel_port_requests(execlists);
-	reset_irq(engine);
 
 	/* Mark all executing requests as skipped. */
 	list_for_each_entry(rq, &engine->timeline.requests, link) {
@@ -1976,7 +1909,6 @@ static void execlists_reset(struct intel_engine_cs *engine,
 	 * requests were completed.
 	 */
 	execlists_cancel_port_requests(execlists);
-	reset_irq(engine);
 
 	/* Push back any incomplete requests for replay after the reset. */
 	__unwind_incomplete_requests(engine);
-- 
cgit v1.2.3


From d23b27c02f03438ac1867b4b6a484b92f536bd28 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 13 Jul 2018 16:35:14 +0200
Subject: samples/bpf: xdp_redirect_cpu handle parsing of double VLAN tagged
 packets

People noticed that the code match on IEEE 802.1ad (ETH_P_8021AD) ethertype,
and this implies Q-in-Q or double tagged VLANs.  Thus, we better parse
the next VLAN header too.  It is even marked as a TODO.

This is relevant for real world use-cases, as XDP cpumap redirect can be
used when the NIC RSS hashing is broken.  E.g. the ixgbe driver HW cannot
handle double tagged VLAN packets, and places everything into a single
RX queue.  Using cpumap redirect, users can redistribute traffic across
CPUs to solve this, which is faster than the network stacks RPS solution.

It is left as an exerise how to distribute the packets across CPUs.  It
would be convenient to use the RX hash, but that is not _yet_ exposed
to XDP programs. For now, users can code their own hash, as I've demonstrated
in the Suricata code (where Q-in-Q is handled correctly).

Reported-by: Florian Maury <florian.maury-cv@x-cli.eu>
Reported-by: Marek Majkowski <marek@cloudflare.com>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/xdp_redirect_cpu_kern.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index 303e9e7161f3..8cb703671b04 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -134,7 +134,16 @@ bool parse_eth(struct ethhdr *eth, void *data_end,
 			return false;
 		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
 	}
-	/* TODO: Handle double VLAN tagged packet */
+	/* Handle double VLAN tagged packet */
+	if (eth_type == htons(ETH_P_8021Q) || eth_type == htons(ETH_P_8021AD)) {
+		struct vlan_hdr *vlan_hdr;
+
+		vlan_hdr = (void *)eth + offset;
+		offset += sizeof(*vlan_hdr);
+		if ((void *)eth + offset > data_end)
+			return false;
+		eth_type = vlan_hdr->h_vlan_encapsulated_proto;
+	}
 
 	*eth_proto = ntohs(eth_type);
 	*l3_offset = offset;
-- 
cgit v1.2.3


From 01683a1469995cc7aaf833d6f8b3f1c1d2fc3b92 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Mon, 9 Jul 2018 13:29:11 +0300
Subject: net: sched: refactor flower walk to iterate over idr

Extend struct tcf_walker with additional 'cookie' field. It is intended to
be used by classifier walk implementations to continue iteration directly
from particular filter, instead of iterating 'skip' number of times.

Change flower walk implementation to save filter handle in 'cookie'. Each
time flower walk is called, it looks up filter with saved handle directly
with idr, instead of iterating over filter linked list 'skip' number of
times. This change improves complexity of dumping flower classifier from
quadratic to linearithmic. (assuming idr lookup has logarithmic complexity)

Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Reported-by: Simon Horman <simon.horman@netronome.com>
Reviewed-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h  |  1 +
 net/sched/cls_api.c    |  2 ++
 net/sched/cls_flower.c | 20 +++++++++-----------
 3 files changed, 12 insertions(+), 11 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 2081e4219f81..e4252a176eec 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -13,6 +13,7 @@ struct tcf_walker {
 	int	stop;
 	int	skip;
 	int	count;
+	unsigned long cookie;
 	int	(*fn)(struct tcf_proto *, void *node, struct tcf_walker *);
 };
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 73d9967c3739..c51b1b12450d 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1508,7 +1508,9 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent,
 		arg.w.stop = 0;
 		arg.w.skip = cb->args[1] - 1;
 		arg.w.count = 0;
+		arg.w.cookie = cb->args[2];
 		tp->ops->walk(tp, &arg.w);
+		cb->args[2] = arg.w.cookie;
 		cb->args[1] = arg.w.count + 1;
 		if (arg.w.stop)
 			return false;
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 8b2474293db1..c53fdd411f90 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1099,19 +1099,17 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 {
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *f;
-	struct fl_flow_mask *mask;
 
-	list_for_each_entry_rcu(mask, &head->masks, list) {
-		list_for_each_entry_rcu(f, &mask->filters, list) {
-			if (arg->count < arg->skip)
-				goto skip;
-			if (arg->fn(tp, f, arg) < 0) {
-				arg->stop = 1;
-				break;
-			}
-skip:
-			arg->count++;
+	arg->count = arg->skip;
+
+	while ((f = idr_get_next_ul(&head->handle_idr,
+				    &arg->cookie)) != NULL) {
+		if (arg->fn(tp, f, arg) < 0) {
+			arg->stop = 1;
+			break;
 		}
+		arg->cookie = f->handle + 1;
+		arg->count++;
 	}
 }
 
-- 
cgit v1.2.3


From 6eb9c9dafd02b6a0236074e3ee7acee9e2271308 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 11 Jul 2018 19:45:11 +0200
Subject: of: mdio: Support fixed links in of_phy_get_and_connect()

By a simple extension of of_phy_get_and_connect() drivers
that have a fixed link on e.g. RGMII can support also
fixed links, so in addition to:

ethernet-port {
	phy-mode = "rgmii";
	phy-handle = <&foo>;
};

This setup with a fixed-link node and no phy-handle will
now also work just fine:

ethernet-port {
	phy-mode = "rgmii";
	fixed-link {
		speed = <1000>;
		full-duplex;
		pause;
	};
};

This is very helpful for connecting random ethernet ports
to e.g. DSA switches that typically reside on fixed links.

The phy-mode is still there as the fixes link in this case
is still an RGMII link.

Tested on the Cortina Gemini driver with the Vitesse DSA
router chip on a fixed 1Gbit link.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/of/of_mdio.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index d963baf8e53a..e92391d6d1bd 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -367,14 +367,23 @@ struct phy_device *of_phy_get_and_connect(struct net_device *dev,
 	phy_interface_t iface;
 	struct device_node *phy_np;
 	struct phy_device *phy;
+	int ret;
 
 	iface = of_get_phy_mode(np);
 	if (iface < 0)
 		return NULL;
-
-	phy_np = of_parse_phandle(np, "phy-handle", 0);
-	if (!phy_np)
-		return NULL;
+	if (of_phy_is_fixed_link(np)) {
+		ret = of_phy_register_fixed_link(np);
+		if (ret < 0) {
+			netdev_err(dev, "broken fixed-link specification\n");
+			return NULL;
+		}
+		phy_np = of_node_get(np);
+	} else {
+		phy_np = of_parse_phandle(np, "phy-handle", 0);
+		if (!phy_np)
+			return NULL;
+	}
 
 	phy = of_phy_connect(dev, phy_np, hndlr, 0, iface);
 
-- 
cgit v1.2.3


From 9cee8c4375431d5087466eacf6f8f436210e56ea Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Sat, 14 Jul 2018 09:27:35 +0800
Subject: net: mvpp2: mvpp2_cls_flow_get() can be static

Fixes: f9358e12a0af ("net: mvpp2: split ingress traffic into multiple flows")
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index dc7dfa9a6606..723d0ba6f78d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -557,7 +557,7 @@ static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
 	return 0;
 }
 
-struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
+static struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
 {
 	if (flow >= MVPP2_N_FLOWS)
 		return NULL;
-- 
cgit v1.2.3


From db42a21a1e8d11a30a06050281c2723ec78b63a7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 13 Jul 2018 19:08:59 -0700
Subject: tools: include reallocarray feature test in FEATURE_TESTS_BASIC

perf propagates its feature check results to libbpf.  This means
features for which perf probes must be a superset of libbpf's
required features.  perf depends on FEATURE_TESTS_BASIC for its list
of features.

commit 531b014e7a2f ("tools: bpf: make use of reallocarray") added
reallocarray use to libbpf, make perf also perform the reallocarray
feature check.

Fixes: 531b014e7a2f ("tools: bpf: make use of reallocarray")
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/build/Makefile.feature | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 5b6dda3b1ca8..f216b2f5c3d7 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -57,6 +57,7 @@ FEATURE_TESTS_BASIC :=                  \
         libunwind-aarch64               \
         pthread-attr-setaffinity-np     \
         pthread-barrier     		\
+        reallocarray                    \
         stackprotector-all              \
         timerfd                         \
         libdw-dwarf-unwind              \
-- 
cgit v1.2.3


From 92b57121ca79b286bef4f304e887272f3f2d86bb Mon Sep 17 00:00:00 2001
From: Okash Khawaja <osk@fb.com>
Date: Fri, 13 Jul 2018 21:57:02 -0700
Subject: bpf: btf: export btf types and name by offset from lib

This patch introduces btf__resolve_type() function and exports two
existing functions from libbpf. btf__resolve_type follows modifier
types like const and typedef until it hits a type which actually takes
up memory, and then returns it. This function follows similar pattern
to btf__resolve_size but instead of computing size, it just returns
the type.

These  functions will be used in the followig patch which parses
information inside array of `struct btf_type *`. btf_name_by_offset is
used for printing variable names.

Signed-off-by: Okash Khawaja <osk@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/btf.c | 65 ++++++++++++++++++++++++++++++++++++-----------------
 tools/lib/bpf/btf.h |  3 +++
 2 files changed, 48 insertions(+), 20 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 8c54a4b6f187..03161be094b4 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -17,6 +17,11 @@
 
 #define BTF_MAX_NR_TYPES 65535
 
+#define IS_MODIFIER(k) (((k) == BTF_KIND_TYPEDEF) || \
+		((k) == BTF_KIND_VOLATILE) || \
+		((k) == BTF_KIND_CONST) || \
+		((k) == BTF_KIND_RESTRICT))
+
 static struct btf_type btf_void;
 
 struct btf {
@@ -33,14 +38,6 @@ struct btf {
 	int fd;
 };
 
-static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset)
-{
-	if (offset < btf->hdr->str_len)
-		return &btf->strings[offset];
-	else
-		return NULL;
-}
-
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
@@ -190,15 +187,6 @@ static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log)
 	return 0;
 }
 
-static const struct btf_type *btf_type_by_id(const struct btf *btf,
-					     uint32_t type_id)
-{
-	if (type_id > btf->nr_types)
-		return NULL;
-
-	return btf->types[type_id];
-}
-
 static bool btf_type_is_void(const struct btf_type *t)
 {
 	return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
@@ -234,7 +222,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 	int64_t size = -1;
 	int i;
 
-	t = btf_type_by_id(btf, type_id);
+	t = btf__type_by_id(btf, type_id);
 	for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t);
 	     i++) {
 		size = btf_type_size(t);
@@ -259,7 +247,7 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 			return -EINVAL;
 		}
 
-		t = btf_type_by_id(btf, type_id);
+		t = btf__type_by_id(btf, type_id);
 	}
 
 	if (size < 0)
@@ -271,6 +259,26 @@ int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id)
 	return nelems * size;
 }
 
+int btf__resolve_type(const struct btf *btf, __u32 type_id)
+{
+	const struct btf_type *t;
+	int depth = 0;
+
+	t = btf__type_by_id(btf, type_id);
+	while (depth < MAX_RESOLVE_DEPTH &&
+	       !btf_type_is_void_or_null(t) &&
+	       IS_MODIFIER(BTF_INFO_KIND(t->info))) {
+		type_id = t->type;
+		t = btf__type_by_id(btf, type_id);
+		depth++;
+	}
+
+	if (depth == MAX_RESOLVE_DEPTH || btf_type_is_void_or_null(t))
+		return -EINVAL;
+
+	return type_id;
+}
+
 int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
 {
 	uint32_t i;
@@ -280,7 +288,7 @@ int32_t btf__find_by_name(const struct btf *btf, const char *type_name)
 
 	for (i = 1; i <= btf->nr_types; i++) {
 		const struct btf_type *t = btf->types[i];
-		const char *name = btf_name_by_offset(btf, t->name_off);
+		const char *name = btf__name_by_offset(btf, t->name_off);
 
 		if (name && !strcmp(type_name, name))
 			return i;
@@ -371,3 +379,20 @@ int btf__fd(const struct btf *btf)
 {
 	return btf->fd;
 }
+
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
+{
+	if (offset < btf->hdr->str_len)
+		return &btf->strings[offset];
+	else
+		return NULL;
+}
+
+const struct btf_type *btf__type_by_id(const struct btf *btf,
+				       __u32 type_id)
+{
+	if (type_id > btf->nr_types)
+		return NULL;
+
+	return btf->types[type_id];
+}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index 74bb344035bb..24f361d99a5e 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -17,6 +17,9 @@ void btf__free(struct btf *btf);
 struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log);
 int32_t btf__find_by_name(const struct btf *btf, const char *type_name);
 int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id);
+int btf__resolve_type(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
+const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
+const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id);
 
 #endif
-- 
cgit v1.2.3


From b12d6ec09730b2646e85c348e599b592348dd0e3 Mon Sep 17 00:00:00 2001
From: Okash Khawaja <osk@fb.com>
Date: Fri, 13 Jul 2018 21:57:03 -0700
Subject: bpf: btf: add btf print functionality

This consumes functionality exported in the previous patch. It does the
main job of printing with BTF data. This is used in the following patch
to provide a more readable output of a map's dump. It relies on
json_writer to do json printing. Below is sample output where map keys
are ints and values are of type struct A:

typedef int int_type;
enum E {
        E0,
        E1,
};

struct B {
        int x;
        int y;
};

struct A {
        int m;
        unsigned long long n;
        char o;
        int p[8];
        int q[4][8];
        enum E r;
        void *s;
        struct B t;
        const int u;
        int_type v;
        unsigned int w1: 3;
        unsigned int w2: 3;
};

$ sudo bpftool map dump id 14
[{
        "key": 0,
        "value": {
            "m": 1,
            "n": 2,
            "o": "c",
            "p": [15,16,17,18,15,16,17,18
            ],
            "q": [[25,26,27,28,25,26,27,28
                ],[35,36,37,38,35,36,37,38
                ],[45,46,47,48,45,46,47,48
                ],[55,56,57,58,55,56,57,58
                ]
            ],
            "r": 1,
            "s": 0x7ffd80531cf8,
            "t": {
                "x": 5,
                "y": 10
            },
            "u": 100,
            "v": 20,
            "w1": 0x7,
            "w2": 0x3
        }
    }
]

This patch uses json's {} and [] to imply struct/union and array. More
explicit information can be added later. For example, a command line
option can be introduced to print whether a key or value is struct
or union, name of a struct etc. This will however come at the expense
of duplicating info when, for example, printing an array of structs.
enums are printed as ints without their names.

Signed-off-by: Okash Khawaja <osk@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/btf_dumper.c | 251 +++++++++++++++++++++++++++++++++++++++++
 tools/bpf/bpftool/main.h       |  15 +++
 2 files changed, 266 insertions(+)
 create mode 100644 tools/bpf/bpftool/btf_dumper.c

diff --git a/tools/bpf/bpftool/btf_dumper.c b/tools/bpf/bpftool/btf_dumper.c
new file mode 100644
index 000000000000..55bc512a1831
--- /dev/null
+++ b/tools/bpf/bpftool/btf_dumper.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <ctype.h>
+#include <stdio.h> /* for (FILE *) used by json_writer */
+#include <string.h>
+#include <asm/byteorder.h>
+#include <linux/bitops.h>
+#include <linux/btf.h>
+#include <linux/err.h>
+
+#include "btf.h"
+#include "json_writer.h"
+#include "main.h"
+
+#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1)
+#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK)
+#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3)
+#define BITS_ROUNDUP_BYTES(bits) \
+	(BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits))
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+			      __u8 bit_offset, const void *data);
+
+static void btf_dumper_ptr(const void *data, json_writer_t *jw,
+			   bool is_plain_text)
+{
+	if (is_plain_text)
+		jsonw_printf(jw, "%p", *(unsigned long *)data);
+	else
+		jsonw_printf(jw, "%u", *(unsigned long *)data);
+}
+
+static int btf_dumper_modifier(const struct btf_dumper *d, __u32 type_id,
+			       const void *data)
+{
+	int actual_type_id;
+
+	actual_type_id = btf__resolve_type(d->btf, type_id);
+	if (actual_type_id < 0)
+		return actual_type_id;
+
+	return btf_dumper_do_type(d, actual_type_id, 0, data);
+}
+
+static void btf_dumper_enum(const void *data, json_writer_t *jw)
+{
+	jsonw_printf(jw, "%d", *(int *)data);
+}
+
+static int btf_dumper_array(const struct btf_dumper *d, __u32 type_id,
+			    const void *data)
+{
+	const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+	struct btf_array *arr = (struct btf_array *)(t + 1);
+	long long elem_size;
+	int ret = 0;
+	__u32 i;
+
+	elem_size = btf__resolve_size(d->btf, arr->type);
+	if (elem_size < 0)
+		return elem_size;
+
+	jsonw_start_array(d->jw);
+	for (i = 0; i < arr->nelems; i++) {
+		ret = btf_dumper_do_type(d, arr->type, 0,
+					 data + i * elem_size);
+		if (ret)
+			break;
+	}
+
+	jsonw_end_array(d->jw);
+	return ret;
+}
+
+static void btf_dumper_int_bits(__u32 int_type, __u8 bit_offset,
+				const void *data, json_writer_t *jw,
+				bool is_plain_text)
+{
+	int left_shift_bits, right_shift_bits;
+	int nr_bits = BTF_INT_BITS(int_type);
+	int total_bits_offset;
+	int bytes_to_copy;
+	int bits_to_copy;
+	__u64 print_num;
+
+	total_bits_offset = bit_offset + BTF_INT_OFFSET(int_type);
+	data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
+	bit_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
+	bits_to_copy = bit_offset + nr_bits;
+	bytes_to_copy = BITS_ROUNDUP_BYTES(bits_to_copy);
+
+	print_num = 0;
+	memcpy(&print_num, data, bytes_to_copy);
+#if defined(__BIG_ENDIAN_BITFIELD)
+	left_shift_bits = bit_offset;
+#elif defined(__LITTLE_ENDIAN_BITFIELD)
+	left_shift_bits = 64 - bits_to_copy;
+#else
+#error neither big nor little endian
+#endif
+	right_shift_bits = 64 - nr_bits;
+
+	print_num <<= left_shift_bits;
+	print_num >>= right_shift_bits;
+	if (is_plain_text)
+		jsonw_printf(jw, "0x%llx", print_num);
+	else
+		jsonw_printf(jw, "%llu", print_num);
+}
+
+static int btf_dumper_int(const struct btf_type *t, __u8 bit_offset,
+			  const void *data, json_writer_t *jw,
+			  bool is_plain_text)
+{
+	__u32 *int_type;
+	__u32 nr_bits;
+
+	int_type = (__u32 *)(t + 1);
+	nr_bits = BTF_INT_BITS(*int_type);
+	/* if this is bit field */
+	if (bit_offset || BTF_INT_OFFSET(*int_type) ||
+	    BITS_PER_BYTE_MASKED(nr_bits)) {
+		btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+				    is_plain_text);
+		return 0;
+	}
+
+	switch (BTF_INT_ENCODING(*int_type)) {
+	case 0:
+		if (BTF_INT_BITS(*int_type) == 64)
+			jsonw_printf(jw, "%lu", *(__u64 *)data);
+		else if (BTF_INT_BITS(*int_type) == 32)
+			jsonw_printf(jw, "%u", *(__u32 *)data);
+		else if (BTF_INT_BITS(*int_type) == 16)
+			jsonw_printf(jw, "%hu", *(__u16 *)data);
+		else if (BTF_INT_BITS(*int_type) == 8)
+			jsonw_printf(jw, "%hhu", *(__u8 *)data);
+		else
+			btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+					    is_plain_text);
+		break;
+	case BTF_INT_SIGNED:
+		if (BTF_INT_BITS(*int_type) == 64)
+			jsonw_printf(jw, "%ld", *(long long *)data);
+		else if (BTF_INT_BITS(*int_type) == 32)
+			jsonw_printf(jw, "%d", *(int *)data);
+		else if (BTF_INT_BITS(*int_type) == 16)
+			jsonw_printf(jw, "%hd", *(short *)data);
+		else if (BTF_INT_BITS(*int_type) == 8)
+			jsonw_printf(jw, "%hhd", *(char *)data);
+		else
+			btf_dumper_int_bits(*int_type, bit_offset, data, jw,
+					    is_plain_text);
+		break;
+	case BTF_INT_CHAR:
+		if (isprint(*(char *)data))
+			jsonw_printf(jw, "\"%c\"", *(char *)data);
+		else
+			if (is_plain_text)
+				jsonw_printf(jw, "0x%hhx", *(char *)data);
+			else
+				jsonw_printf(jw, "\"\\u00%02hhx\"",
+					     *(char *)data);
+		break;
+	case BTF_INT_BOOL:
+		jsonw_bool(jw, *(int *)data);
+		break;
+	default:
+		/* shouldn't happen */
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int btf_dumper_struct(const struct btf_dumper *d, __u32 type_id,
+			     const void *data)
+{
+	const struct btf_type *t;
+	struct btf_member *m;
+	const void *data_off;
+	int ret = 0;
+	int i, vlen;
+
+	t = btf__type_by_id(d->btf, type_id);
+	if (!t)
+		return -EINVAL;
+
+	vlen = BTF_INFO_VLEN(t->info);
+	jsonw_start_object(d->jw);
+	m = (struct btf_member *)(t + 1);
+
+	for (i = 0; i < vlen; i++) {
+		data_off = data + BITS_ROUNDDOWN_BYTES(m[i].offset);
+		jsonw_name(d->jw, btf__name_by_offset(d->btf, m[i].name_off));
+		ret = btf_dumper_do_type(d, m[i].type,
+					 BITS_PER_BYTE_MASKED(m[i].offset),
+					 data_off);
+		if (ret)
+			break;
+	}
+
+	jsonw_end_object(d->jw);
+
+	return ret;
+}
+
+static int btf_dumper_do_type(const struct btf_dumper *d, __u32 type_id,
+			      __u8 bit_offset, const void *data)
+{
+	const struct btf_type *t = btf__type_by_id(d->btf, type_id);
+
+	switch (BTF_INFO_KIND(t->info)) {
+	case BTF_KIND_INT:
+		return btf_dumper_int(t, bit_offset, data, d->jw,
+				     d->is_plain_text);
+	case BTF_KIND_STRUCT:
+	case BTF_KIND_UNION:
+		return btf_dumper_struct(d, type_id, data);
+	case BTF_KIND_ARRAY:
+		return btf_dumper_array(d, type_id, data);
+	case BTF_KIND_ENUM:
+		btf_dumper_enum(data, d->jw);
+		return 0;
+	case BTF_KIND_PTR:
+		btf_dumper_ptr(data, d->jw, d->is_plain_text);
+		return 0;
+	case BTF_KIND_UNKN:
+		jsonw_printf(d->jw, "(unknown)");
+		return 0;
+	case BTF_KIND_FWD:
+		/* map key or value can't be forward */
+		jsonw_printf(d->jw, "(fwd-kind-invalid)");
+		return -EINVAL;
+	case BTF_KIND_TYPEDEF:
+	case BTF_KIND_VOLATILE:
+	case BTF_KIND_CONST:
+	case BTF_KIND_RESTRICT:
+		return btf_dumper_modifier(d, type_id, data);
+	default:
+		jsonw_printf(d->jw, "(unsupported-kind");
+		return -EINVAL;
+	}
+}
+
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+		    const void *data)
+{
+	return btf_dumper_do_type(d, type_id, 0, data);
+}
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 41004bb2644a..238e734d75b3 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -150,4 +150,19 @@ unsigned int get_page_size(void);
 unsigned int get_possible_cpus(void);
 const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino);
 
+struct btf_dumper {
+	const struct btf *btf;
+	json_writer_t *jw;
+	bool is_plain_text;
+};
+
+/* btf_dumper_type - print data along with type information
+ * @d: an instance containing context for dumping types
+ * @type_id: index in btf->types array. this points to the type to be dumped
+ * @data: pointer the actual data, i.e. the values to be printed
+ *
+ * Returns zero on success and negative error code otherwise
+ */
+int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
+		    const void *data);
 #endif
-- 
cgit v1.2.3


From 2d3feca8c44f315624b7c0f5b8361e2f54405c12 Mon Sep 17 00:00:00 2001
From: Okash Khawaja <osk@fb.com>
Date: Fri, 13 Jul 2018 21:57:04 -0700
Subject: bpf: btf: print map dump and lookup with btf info

This patch augments the output of bpftool's map dump and map lookup
commands to print data along side btf info, if the correspondin btf
info is available. The outputs for each of  map dump and map lookup
commands are augmented in two ways:

1. when neither of -j and -p are supplied, btf-ful map data is printed
whose aim is human readability. This means no commitments for json- or
backward- compatibility.

2. when either -j or -p are supplied, a new json object named
"formatted" is added for each key-value pair. This object contains the
same data as the key-value pair, but with btf info. "formatted" object
promises json- and backward- compatibility. Below is a sample output.

$ bpftool map dump -p id 8
[{
        "key": ["0x0f","0x00","0x00","0x00"
        ],
        "value": ["0x03", "0x00", "0x00", "0x00", ...
        ],
        "formatted": {
                "key": 15,
                "value": {
                        "int_field":  3,
                        ...
                }
        }
}
]

This patch calls btf_dumper introduced in previous patch to accomplish
the above. Indeed, btf-ful info is only displayed if btf data for the
given map is available. Otherwise existing output is displayed as-is.

Signed-off-by: Okash Khawaja <osk@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 217 ++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 201 insertions(+), 16 deletions(-)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index e2baec1122fb..9c8191845585 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -34,6 +34,7 @@
 #include <assert.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <linux/err.h>
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -44,6 +45,8 @@
 
 #include <bpf.h>
 
+#include "btf.h"
+#include "json_writer.h"
 #include "main.h"
 
 static const char * const map_type_name[] = {
@@ -148,8 +151,109 @@ int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len)
 	return fd;
 }
 
+static int do_dump_btf(const struct btf_dumper *d,
+		       struct bpf_map_info *map_info, void *key,
+		       void *value)
+{
+	int ret;
+
+	/* start of key-value pair */
+	jsonw_start_object(d->jw);
+
+	jsonw_name(d->jw, "key");
+
+	ret = btf_dumper_type(d, map_info->btf_key_type_id, key);
+	if (ret)
+		goto err_end_obj;
+
+	jsonw_name(d->jw, "value");
+
+	ret = btf_dumper_type(d, map_info->btf_value_type_id, value);
+
+err_end_obj:
+	/* end of key-value pair */
+	jsonw_end_object(d->jw);
+
+	return ret;
+}
+
+static int get_btf(struct bpf_map_info *map_info, struct btf **btf)
+{
+	struct bpf_btf_info btf_info = { 0 };
+	__u32 len = sizeof(btf_info);
+	__u32 last_size;
+	int btf_fd;
+	void *ptr;
+	int err;
+
+	err = 0;
+	*btf = NULL;
+	btf_fd = bpf_btf_get_fd_by_id(map_info->btf_id);
+	if (btf_fd < 0)
+		return 0;
+
+	/* we won't know btf_size until we call bpf_obj_get_info_by_fd(). so
+	 * let's start with a sane default - 4KiB here - and resize it only if
+	 * bpf_obj_get_info_by_fd() needs a bigger buffer.
+	 */
+	btf_info.btf_size = 4096;
+	last_size = btf_info.btf_size;
+	ptr = malloc(last_size);
+	if (!ptr) {
+		err = -ENOMEM;
+		goto exit_free;
+	}
+
+	bzero(ptr, last_size);
+	btf_info.btf = ptr_to_u64(ptr);
+	err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+
+	if (!err && btf_info.btf_size > last_size) {
+		void *temp_ptr;
+
+		last_size = btf_info.btf_size;
+		temp_ptr = realloc(ptr, last_size);
+		if (!temp_ptr) {
+			err = -ENOMEM;
+			goto exit_free;
+		}
+		ptr = temp_ptr;
+		bzero(ptr, last_size);
+		btf_info.btf = ptr_to_u64(ptr);
+		err = bpf_obj_get_info_by_fd(btf_fd, &btf_info, &len);
+	}
+
+	if (err || btf_info.btf_size > last_size) {
+		err = errno;
+		goto exit_free;
+	}
+
+	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
+	if (IS_ERR(*btf)) {
+		err = PTR_ERR(btf);
+		*btf = NULL;
+	}
+
+exit_free:
+	close(btf_fd);
+	free(ptr);
+
+	return err;
+}
+
+static json_writer_t *get_btf_writer(void)
+{
+	json_writer_t *jw = jsonw_new(stdout);
+
+	if (!jw)
+		return NULL;
+	jsonw_pretty(jw, true);
+
+	return jw;
+}
+
 static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
-			     unsigned char *value)
+			     unsigned char *value, struct btf *btf)
 {
 	jsonw_start_object(json_wtr);
 
@@ -158,6 +262,16 @@ static void print_entry_json(struct bpf_map_info *info, unsigned char *key,
 		print_hex_data_json(key, info->key_size);
 		jsonw_name(json_wtr, "value");
 		print_hex_data_json(value, info->value_size);
+		if (btf) {
+			struct btf_dumper d = {
+				.btf = btf,
+				.jw = json_wtr,
+				.is_plain_text = false,
+			};
+
+			jsonw_name(json_wtr, "formatted");
+			do_dump_btf(&d, info, key, value);
+		}
 	} else {
 		unsigned int i, n;
 
@@ -508,10 +622,12 @@ static int do_show(int argc, char **argv)
 
 static int do_dump(int argc, char **argv)
 {
+	struct bpf_map_info info = {};
 	void *key, *value, *prev_key;
 	unsigned int num_elems = 0;
-	struct bpf_map_info info = {};
 	__u32 len = sizeof(info);
+	json_writer_t *btf_wtr;
+	struct btf *btf = NULL;
 	int err;
 	int fd;
 
@@ -537,8 +653,27 @@ static int do_dump(int argc, char **argv)
 	}
 
 	prev_key = NULL;
+
+	err = get_btf(&info, &btf);
+	if (err) {
+		p_err("failed to get btf");
+		goto exit_free;
+	}
+
 	if (json_output)
 		jsonw_start_array(json_wtr);
+	else
+		if (btf) {
+			btf_wtr = get_btf_writer();
+			if (!btf_wtr) {
+				p_info("failed to create json writer for btf. falling back to plain output");
+				btf__free(btf);
+				btf = NULL;
+			} else {
+				jsonw_start_array(btf_wtr);
+			}
+		}
+
 	while (true) {
 		err = bpf_map_get_next_key(fd, prev_key, key);
 		if (err) {
@@ -549,9 +684,19 @@ static int do_dump(int argc, char **argv)
 
 		if (!bpf_map_lookup_elem(fd, key, value)) {
 			if (json_output)
-				print_entry_json(&info, key, value);
+				print_entry_json(&info, key, value, btf);
 			else
-				print_entry_plain(&info, key, value);
+				if (btf) {
+					struct btf_dumper d = {
+						.btf = btf,
+						.jw = btf_wtr,
+						.is_plain_text = true,
+					};
+
+					do_dump_btf(&d, &info, key, value);
+				} else {
+					print_entry_plain(&info, key, value);
+				}
 		} else {
 			if (json_output) {
 				jsonw_name(json_wtr, "key");
@@ -574,14 +719,19 @@ static int do_dump(int argc, char **argv)
 
 	if (json_output)
 		jsonw_end_array(json_wtr);
-	else
+	else if (btf) {
+		jsonw_end_array(btf_wtr);
+		jsonw_destroy(&btf_wtr);
+	} else {
 		printf("Found %u element%s\n", num_elems,
 		       num_elems != 1 ? "s" : "");
+	}
 
 exit_free:
 	free(key);
 	free(value);
 	close(fd);
+	btf__free(btf);
 
 	return err;
 }
@@ -637,6 +787,8 @@ static int do_lookup(int argc, char **argv)
 {
 	struct bpf_map_info info = {};
 	__u32 len = sizeof(info);
+	json_writer_t *btf_wtr;
+	struct btf *btf = NULL;
 	void *key, *value;
 	int err;
 	int fd;
@@ -661,27 +813,60 @@ static int do_lookup(int argc, char **argv)
 		goto exit_free;
 
 	err = bpf_map_lookup_elem(fd, key, value);
-	if (!err) {
-		if (json_output)
-			print_entry_json(&info, key, value);
-		else
+	if (err) {
+		if (errno == ENOENT) {
+			if (json_output) {
+				jsonw_null(json_wtr);
+			} else {
+				printf("key:\n");
+				fprint_hex(stdout, key, info.key_size, " ");
+				printf("\n\nNot found\n");
+			}
+		} else {
+			p_err("lookup failed: %s", strerror(errno));
+		}
+
+		goto exit_free;
+	}
+
+	/* here means bpf_map_lookup_elem() succeeded */
+	err = get_btf(&info, &btf);
+	if (err) {
+		p_err("failed to get btf");
+		goto exit_free;
+	}
+
+	if (json_output) {
+		print_entry_json(&info, key, value, btf);
+	} else if (btf) {
+		/* if here json_wtr wouldn't have been initialised,
+		 * so let's create separate writer for btf
+		 */
+		btf_wtr = get_btf_writer();
+		if (!btf_wtr) {
+			p_info("failed to create json writer for btf. falling back to plain output");
+			btf__free(btf);
+			btf = NULL;
 			print_entry_plain(&info, key, value);
-	} else if (errno == ENOENT) {
-		if (json_output) {
-			jsonw_null(json_wtr);
 		} else {
-			printf("key:\n");
-			fprint_hex(stdout, key, info.key_size, " ");
-			printf("\n\nNot found\n");
+			struct btf_dumper d = {
+				.btf = btf,
+				.jw = btf_wtr,
+				.is_plain_text = true,
+			};
+
+			do_dump_btf(&d, &info, key, value);
+			jsonw_destroy(&btf_wtr);
 		}
 	} else {
-		p_err("lookup failed: %s", strerror(errno));
+		print_entry_plain(&info, key, value);
 	}
 
 exit_free:
 	free(key);
 	free(value);
 	close(fd);
+	btf__free(btf);
 
 	return err;
 }
-- 
cgit v1.2.3


From 14459ce2bd980f74bc9c36f3ef42e7ba645e5dfe Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 29 Mar 2018 11:27:31 +0100
Subject: ARM: tcm: ensure inline stub functions are marked static

Ensure that the stubbed out tcm_init() is marked static, so we don't
end up emitting the stub each time the header is included.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/mm/tcm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm/mm/tcm.h b/arch/arm/mm/tcm.h
index 8015ad434a40..24101925fe64 100644
--- a/arch/arm/mm/tcm.h
+++ b/arch/arm/mm/tcm.h
@@ -11,7 +11,7 @@
 void __init tcm_init(void);
 #else
 /* No TCM support, just blank inlines to be optimized out */
-inline void tcm_init(void)
+static inline void tcm_init(void)
 {
 }
 #endif
-- 
cgit v1.2.3


From e5cae659597811f8bacc4abc70135dffb48711d5 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Sat, 14 Jul 2018 18:37:03 +0100
Subject: drm/i915/guc: Disable rpm wakeref asserts in GuC irq handler
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We're seeing "RPM wakelock ref not held during HW access" warning
otherwise. Since IRQs are synced for runtime suspend we can just disable
the wakeref asserts.

Reported-by: Marta Löfstedt <marta.lofstedt@intel.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105710
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180714173703.7894-1-chris@chris-wilson.co.uk
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/intel_guc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_guc.c b/drivers/gpu/drm/i915/intel_guc.c
index e12bd259df17..560c7406ae40 100644
--- a/drivers/gpu/drm/i915/intel_guc.c
+++ b/drivers/gpu/drm/i915/intel_guc.c
@@ -466,11 +466,13 @@ void intel_guc_to_host_event_handler_mmio(struct intel_guc *guc)
 	 * could happen that GuC sets the bit for 2nd interrupt but Host
 	 * clears out the bit on handling the 1st interrupt.
 	 */
+	disable_rpm_wakeref_asserts(dev_priv);
 	spin_lock(&guc->irq_lock);
 	val = I915_READ(SOFT_SCRATCH(15));
 	msg = val & guc->msg_enabled_mask;
 	I915_WRITE(SOFT_SCRATCH(15), val & ~msg);
 	spin_unlock(&guc->irq_lock);
+	enable_rpm_wakeref_asserts(dev_priv);
 
 	intel_guc_to_host_process_recv_msg(guc, msg);
 }
-- 
cgit v1.2.3


From ff0432e5a8025df895813408325b2afdfa21f946 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Sat, 14 Jul 2018 16:36:29 +0800
Subject: tcp: remove redundant rcv_nxt update

tcp_rcv_nxt_update() is already executed in tcp_data_queue().
This line is redundant.

See bellow,
	tcp_queue_rcv
		tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
	tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq); <<<< redundant

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d3b6390ecf23..fac5d03d4528 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4695,7 +4695,6 @@ queue_and_out:
 		}
 
 		eaten = tcp_queue_rcv(sk, skb, 0, &fragstolen);
-		tcp_rcv_nxt_update(tp, TCP_SKB_CB(skb)->end_seq);
 		if (skb->len)
 			tcp_event_data_recv(sk, skb);
 		if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
-- 
cgit v1.2.3


From c55161852fe852edd9e615768835e59059695990 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sat, 14 Jul 2018 11:39:51 +0300
Subject: mlxsw: spectrum: Enable macvlan upper devices

In order to allow more unicast MAC addresses (e.g., VRRP virtual MAC) to
be directed to the router we need to enable macvlan uppers on top of
mlxsw netdevs.

Allow macvlan upper devices on top of mlxsw netdevs and sanitize
configurations that can't work. For example, a macvlan can't be enslaved
to a bridge as without ACLs the device doesn't take the destination MAC
into account when classifying a packet to a bridge instance (i.e., a
FID).

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 75 +++++++++++++++++++++-
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  |  5 +-
 2 files changed, 76 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 5b2f4c6f5e57..b9d0cab3ada5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4420,7 +4420,8 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 		if (!is_vlan_dev(upper_dev) &&
 		    !netif_is_lag_master(upper_dev) &&
 		    !netif_is_bridge_master(upper_dev) &&
-		    !netif_is_ovs_master(upper_dev)) {
+		    !netif_is_ovs_master(upper_dev) &&
+		    !netif_is_macvlan(upper_dev)) {
 			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
 			return -EINVAL;
 		}
@@ -4446,6 +4447,11 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Can not put a VLAN on a LAG port");
 			return -EINVAL;
 		}
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, lower_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
 		if (netif_is_ovs_master(upper_dev) && vlan_uses_dev(dev)) {
 			NL_SET_ERR_MSG_MOD(extack, "Master device is an OVS master and this device has a VLAN");
 			return -EINVAL;
@@ -4568,8 +4574,9 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 	switch (event) {
 	case NETDEV_PRECHANGEUPPER:
 		upper_dev = info->upper_dev;
-		if (!netif_is_bridge_master(upper_dev)) {
-			NL_SET_ERR_MSG_MOD(extack, "VLAN devices only support bridge and VRF uppers");
+		if (!netif_is_bridge_master(upper_dev) &&
+		    !netif_is_macvlan(upper_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
 			return -EINVAL;
 		}
 		if (!info->linking)
@@ -4581,6 +4588,11 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 			NL_SET_ERR_MSG_MOD(extack, "Enslaving a port to a device that already has an upper device is not supported");
 			return -EINVAL;
 		}
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
 		break;
 	case NETDEV_CHANGEUPPER:
 		upper_dev = info->upper_dev;
@@ -4643,6 +4655,59 @@ static int mlxsw_sp_netdevice_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
+					   unsigned long event, void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(br_dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+	struct net_device *upper_dev;
+
+	if (!mlxsw_sp)
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	switch (event) {
+	case NETDEV_PRECHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (!is_vlan_dev(upper_dev) && !netif_is_macvlan(upper_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+			return -EOPNOTSUPP;
+		}
+		if (!info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev) &&
+		    !mlxsw_sp_rif_find_by_dev(mlxsw_sp, br_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+			return -EOPNOTSUPP;
+		}
+		break;
+	case NETDEV_CHANGEUPPER:
+		break;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_netdevice_macvlan_event(struct net_device *macvlan_dev,
+					    unsigned long event, void *ptr)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
+	struct netdev_notifier_changeupper_info *info = ptr;
+	struct netlink_ext_ack *extack;
+
+	if (!mlxsw_sp || event != NETDEV_PRECHANGEUPPER)
+		return 0;
+
+	extack = netdev_notifier_info_to_extack(&info->info);
+
+	/* VRF enslavement is handled in mlxsw_sp_netdevice_vrf_event() */
+	NL_SET_ERR_MSG_MOD(extack, "Unknown upper device type");
+
+	return -EOPNOTSUPP;
+}
+
 static bool mlxsw_sp_is_vrf_event(unsigned long event, void *ptr)
 {
 	struct netdev_notifier_changeupper_info *info = ptr;
@@ -4684,6 +4749,10 @@ static int mlxsw_sp_netdevice_event(struct notifier_block *nb,
 		err = mlxsw_sp_netdevice_lag_event(dev, event, ptr);
 	else if (is_vlan_dev(dev))
 		err = mlxsw_sp_netdevice_vlan_event(dev, event, ptr);
+	else if (netif_is_bridge_master(dev))
+		err = mlxsw_sp_netdevice_bridge_event(dev, event, ptr);
+	else if (netif_is_macvlan(dev))
+		err = mlxsw_sp_netdevice_macvlan_event(dev, event, ptr);
 
 	return notifier_from_errno(err);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index b4126db695dd..3fc521db1528 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6692,7 +6692,10 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_lower_get(l3_dev);
 	int err = 0;
 
-	if (!mlxsw_sp)
+	/* We do not create a RIF for a macvlan, but only use it to
+	 * direct more MAC addresses to the router.
+	 */
+	if (!mlxsw_sp || netif_is_macvlan(l3_dev))
 		return 0;
 
 	switch (event) {
-- 
cgit v1.2.3


From 2db9937804ac23dc45e35f47dbf93ded516e8b58 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sat, 14 Jul 2018 11:39:52 +0300
Subject: mlxsw: spectrum_router: Direct macvlans' MACs to router

An IP packet received on a netdev with a macvlan upper whose MAC matches
the packet's destination MAC will be re-injected to the Rx path as if it
was received by the macvlan, and perform an L3 lookup.

Reflect this functionality to the ASIC by programming FDB entries that
will direct MACs of macvlan uppers to the router.

In a similar fashion to router interfaces (RIFs) that are programmed
upon the addition of the first IP address on an interface and destroyed
upon the removal of the last IP address, the FDB entries for the macvlan
are added and destroyed based on the addition of the first and removal
of the last IP address on the macvlan.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  11 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   2 +
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 133 +++++++++++++++++++++
 3 files changed, 146 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index b9d0cab3ada5..526c8c61ce2d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -4490,6 +4490,9 @@ static int mlxsw_sp_netdevice_port_upper_event(struct net_device *lower_dev,
 				err = mlxsw_sp_port_ovs_join(mlxsw_sp_port);
 			else
 				mlxsw_sp_port_ovs_leave(mlxsw_sp_port);
+		} else if (netif_is_macvlan(upper_dev)) {
+			if (!info->linking)
+				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
 		}
 		break;
 	}
@@ -4606,6 +4609,9 @@ static int mlxsw_sp_netdevice_port_vlan_event(struct net_device *vlan_dev,
 				mlxsw_sp_port_bridge_leave(mlxsw_sp_port,
 							   vlan_dev,
 							   upper_dev);
+		} else if (netif_is_macvlan(upper_dev)) {
+			if (!info->linking)
+				mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
 		} else {
 			err = -EINVAL;
 			WARN_ON(1);
@@ -4684,6 +4690,11 @@ static int mlxsw_sp_netdevice_bridge_event(struct net_device *br_dev,
 		}
 		break;
 	case NETDEV_CHANGEUPPER:
+		upper_dev = info->upper_dev;
+		if (info->linking)
+			break;
+		if (netif_is_macvlan(upper_dev))
+			mlxsw_sp_rif_macvlan_del(mlxsw_sp, upper_dev);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index eb3d3c0bdb03..8aa717a7d11c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -417,6 +417,8 @@ static inline void mlxsw_sp_port_dcb_fini(struct mlxsw_sp_port *mlxsw_sp_port)
 int mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
 void mlxsw_sp_router_fini(struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_netdevice_router_port_event(struct net_device *dev);
+void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
+			      const struct net_device *macvlan_dev);
 int mlxsw_sp_inetaddr_event(struct notifier_block *unused,
 			    unsigned long event, void *ptr);
 int mlxsw_sp_inetaddr_valid_event(struct notifier_block *unused,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 3fc521db1528..867d3db2c127 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -48,6 +48,7 @@
 #include <linux/route.h>
 #include <linux/gcd.h>
 #include <linux/random.h>
+#include <linux/if_macvlan.h>
 #include <net/netevent.h>
 #include <net/neighbour.h>
 #include <net/arp.h>
@@ -60,6 +61,7 @@
 #include <net/ndisc.h>
 #include <net/ipv6.h>
 #include <net/fib_notifier.h>
+#include <net/switchdev.h>
 
 #include "spectrum.h"
 #include "core.h"
@@ -165,6 +167,7 @@ struct mlxsw_sp_rif_ops {
 	void (*deconfigure)(struct mlxsw_sp_rif *rif);
 	struct mlxsw_sp_fid * (*fid_get)(struct mlxsw_sp_rif *rif,
 					 struct netlink_ext_ack *extack);
+	void (*fdb_del)(struct mlxsw_sp_rif *rif, const char *mac);
 };
 
 static void mlxsw_sp_lpm_tree_hold(struct mlxsw_sp_lpm_tree *lpm_tree);
@@ -6027,6 +6030,12 @@ mlxsw_sp_rif_should_config(struct mlxsw_sp_rif *rif, struct net_device *dev,
 		    !list_empty(&inet6_dev->addr_list))
 			addr_list_empty = false;
 
+		/* macvlans do not have a RIF, but rather piggy back on the
+		 * RIF of their lower device.
+		 */
+		if (netif_is_macvlan(dev) && addr_list_empty)
+			return true;
+
 		if (rif && addr_list_empty &&
 		    !netif_is_l3_slave(rif->dev))
 			return true;
@@ -6440,6 +6449,71 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static int mlxsw_sp_rif_macvlan_add(struct mlxsw_sp *mlxsw_sp,
+				    const struct net_device *macvlan_dev,
+				    struct netlink_ext_ack *extack)
+{
+	struct macvlan_dev *vlan = netdev_priv(macvlan_dev);
+	struct mlxsw_sp_rif *rif;
+	int err;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan->lowerdev);
+	if (!rif) {
+		NL_SET_ERR_MSG_MOD(extack, "macvlan is only supported on top of router interfaces");
+		return -EOPNOTSUPP;
+	}
+
+	err = mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+				  mlxsw_sp_fid_index(rif->fid), true);
+	if (err)
+		return err;
+
+	/* Make sure the bridge driver does not have this MAC pointing at
+	 * some other port.
+	 */
+	if (rif->ops->fdb_del)
+		rif->ops->fdb_del(rif, macvlan_dev->dev_addr);
+
+	return 0;
+}
+
+void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
+			      const struct net_device *macvlan_dev)
+{
+	struct macvlan_dev *vlan = netdev_priv(macvlan_dev);
+	struct mlxsw_sp_rif *rif;
+
+	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, vlan->lowerdev);
+	/* If we do not have a RIF, then we already took care of
+	 * removing the macvlan's MAC during RIF deletion.
+	 */
+	if (!rif)
+		return;
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+			    mlxsw_sp_fid_index(rif->fid), false);
+}
+
+static int mlxsw_sp_inetaddr_macvlan_event(struct net_device *macvlan_dev,
+					   unsigned long event,
+					   struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp *mlxsw_sp;
+
+	mlxsw_sp = mlxsw_sp_lower_get(macvlan_dev);
+	if (!mlxsw_sp)
+		return 0;
+
+	switch (event) {
+	case NETDEV_UP:
+		return mlxsw_sp_rif_macvlan_add(mlxsw_sp, macvlan_dev, extack);
+	case NETDEV_DOWN:
+		mlxsw_sp_rif_macvlan_del(mlxsw_sp, macvlan_dev);
+		break;
+	}
+
+	return 0;
+}
+
 static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 				     unsigned long event,
 				     struct netlink_ext_ack *extack)
@@ -6452,6 +6526,8 @@ static int __mlxsw_sp_inetaddr_event(struct net_device *dev,
 		return mlxsw_sp_inetaddr_bridge_event(dev, event, extack);
 	else if (is_vlan_dev(dev))
 		return mlxsw_sp_inetaddr_vlan_event(dev, event, extack);
+	else if (netif_is_macvlan(dev))
+		return mlxsw_sp_inetaddr_macvlan_event(dev, event, extack);
 	else
 		return 0;
 }
@@ -6716,6 +6792,27 @@ int mlxsw_sp_netdevice_vrf_event(struct net_device *l3_dev, unsigned long event,
 	return err;
 }
 
+static int __mlxsw_sp_rif_macvlan_flush(struct net_device *dev, void *data)
+{
+	struct mlxsw_sp_rif *rif = data;
+
+	if (!netif_is_macvlan(dev))
+		return 0;
+
+	return mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, dev->dev_addr,
+				   mlxsw_sp_fid_index(rif->fid), false);
+}
+
+static int mlxsw_sp_rif_macvlan_flush(struct mlxsw_sp_rif *rif)
+{
+	if (!netif_is_macvlan_port(rif->dev))
+		return 0;
+
+	netdev_warn(rif->dev, "Router interface is deleted. Upper macvlans will not work\n");
+	return netdev_walk_all_upper_dev_rcu(rif->dev,
+					     __mlxsw_sp_rif_macvlan_flush, rif);
+}
+
 static struct mlxsw_sp_rif_subport *
 mlxsw_sp_rif_subport_rif(const struct mlxsw_sp_rif *rif)
 {
@@ -6782,6 +6879,7 @@ static void mlxsw_sp_rif_subport_deconfigure(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_fid_rif_set(fid, NULL);
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
 			    mlxsw_sp_fid_index(fid), false);
+	mlxsw_sp_rif_macvlan_flush(rif);
 	mlxsw_sp_rif_subport_op(rif, false);
 }
 
@@ -6869,6 +6967,7 @@ static void mlxsw_sp_rif_vlan_deconfigure(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_fid_rif_set(fid, NULL);
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
 			    mlxsw_sp_fid_index(fid), false);
+	mlxsw_sp_rif_macvlan_flush(rif);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
 			       mlxsw_sp_router_port(mlxsw_sp), false);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
@@ -6896,12 +6995,30 @@ mlxsw_sp_rif_vlan_fid_get(struct mlxsw_sp_rif *rif,
 	return mlxsw_sp_fid_8021q_get(rif->mlxsw_sp, vid);
 }
 
+static void mlxsw_sp_rif_vlan_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
+{
+	u16 vid = mlxsw_sp_fid_8021q_vid(rif->fid);
+	struct switchdev_notifier_fdb_info info;
+	struct net_device *br_dev;
+	struct net_device *dev;
+
+	br_dev = is_vlan_dev(rif->dev) ? vlan_dev_real_dev(rif->dev) : rif->dev;
+	dev = br_fdb_find_port(br_dev, mac, vid);
+	if (!dev)
+		return;
+
+	info.addr = mac;
+	info.vid = vid;
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+}
+
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_vlan_ops = {
 	.type			= MLXSW_SP_RIF_TYPE_VLAN,
 	.rif_size		= sizeof(struct mlxsw_sp_rif),
 	.configure		= mlxsw_sp_rif_vlan_configure,
 	.deconfigure		= mlxsw_sp_rif_vlan_deconfigure,
 	.fid_get		= mlxsw_sp_rif_vlan_fid_get,
+	.fdb_del		= mlxsw_sp_rif_vlan_fdb_del,
 };
 
 static int mlxsw_sp_rif_fid_configure(struct mlxsw_sp_rif *rif)
@@ -6953,6 +7070,7 @@ static void mlxsw_sp_rif_fid_deconfigure(struct mlxsw_sp_rif *rif)
 	mlxsw_sp_fid_rif_set(fid, NULL);
 	mlxsw_sp_rif_fdb_op(rif->mlxsw_sp, rif->dev->dev_addr,
 			    mlxsw_sp_fid_index(fid), false);
+	mlxsw_sp_rif_macvlan_flush(rif);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_BC,
 			       mlxsw_sp_router_port(mlxsw_sp), false);
 	mlxsw_sp_fid_flood_set(rif->fid, MLXSW_SP_FLOOD_TYPE_MC,
@@ -6967,12 +7085,27 @@ mlxsw_sp_rif_fid_fid_get(struct mlxsw_sp_rif *rif,
 	return mlxsw_sp_fid_8021d_get(rif->mlxsw_sp, rif->dev->ifindex);
 }
 
+static void mlxsw_sp_rif_fid_fdb_del(struct mlxsw_sp_rif *rif, const char *mac)
+{
+	struct switchdev_notifier_fdb_info info;
+	struct net_device *dev;
+
+	dev = br_fdb_find_port(rif->dev, mac, 0);
+	if (!dev)
+		return;
+
+	info.addr = mac;
+	info.vid = 0;
+	call_switchdev_notifiers(SWITCHDEV_FDB_DEL_TO_BRIDGE, dev, &info.info);
+}
+
 static const struct mlxsw_sp_rif_ops mlxsw_sp_rif_fid_ops = {
 	.type			= MLXSW_SP_RIF_TYPE_FID,
 	.rif_size		= sizeof(struct mlxsw_sp_rif),
 	.configure		= mlxsw_sp_rif_fid_configure,
 	.deconfigure		= mlxsw_sp_rif_fid_deconfigure,
 	.fid_get		= mlxsw_sp_rif_fid_fid_get,
+	.fdb_del		= mlxsw_sp_rif_fid_fdb_del,
 };
 
 static struct mlxsw_sp_rif_ipip_lb *
-- 
cgit v1.2.3


From 11566d34f8952a780d86e8a6e734006ed035aa6b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sat, 14 Jul 2018 11:39:53 +0300
Subject: mlxsw: spectrum: Add VRRP traps

Virtual Router Redundancy Protocol packets are used to communicate the
state of the Master router associated with the virtual router ID (VRID).

These are link-local multicast packets sent with IP protocol 112 that
are trapped in the router block in the ASIC.

Add a trap for these packets and mark the trapped packets to prevent
them from potentially being re-flooded by the bridge driver.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/trap.h     | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 526c8c61ce2d..6ec0f91a93cc 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -3386,6 +3386,8 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV4, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
 	/* PKT Sample trap */
 	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
 		  false, SP_IP2ME, DISCARD),
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 399e9d6993f7..eb437f59640d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -63,6 +63,7 @@ enum {
 	MLXSW_TRAP_ID_LBERROR = 0x54,
 	MLXSW_TRAP_ID_IPV4_OSPF = 0x55,
 	MLXSW_TRAP_ID_IPV4_PIM = 0x58,
+	MLXSW_TRAP_ID_IPV4_VRRP = 0x59,
 	MLXSW_TRAP_ID_RPF = 0x5C,
 	MLXSW_TRAP_ID_IP2ME = 0x5F,
 	MLXSW_TRAP_ID_IPV6_UNSPECIFIED_ADDRESS = 0x60,
@@ -78,6 +79,7 @@ enum {
 	MLXSW_TRAP_ID_IPV6_ALL_ROUTERS_LINK = 0x6F,
 	MLXSW_TRAP_ID_RTR_INGRESS0 = 0x70,
 	MLXSW_TRAP_ID_IPV6_PIM = 0x79,
+	MLXSW_TRAP_ID_IPV6_VRRP = 0x7A,
 	MLXSW_TRAP_ID_IPV4_BGP = 0x88,
 	MLXSW_TRAP_ID_IPV6_BGP = 0x89,
 	MLXSW_TRAP_ID_L3_IPV6_ROUTER_SOLICITATION = 0x8A,
-- 
cgit v1.2.3


From c3a495409adeb677fa8b53f4cfe37cf9cfb7c751 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Sat, 14 Jul 2018 11:39:54 +0300
Subject: mlxsw: spectrum_router: Optimize processing of VRRP MACs

Hosts using a VRRP router send their packets with a destination MAC of
the VRRP router which is of the following form [1]:

IPv4 - 00-00-5E-00-01-{VRID}
IPv6 - 00-00-5E-00-02-{VRID}

Where VRID is the ID of the virtual router. Such packets are directed to
the router block in the ASIC by an FDB entry that was added in the
previous patch.

However, in certain cases it is possible to skip this FDB lookup and
send such packets directly to the router. This is accomplished by adding
these special MAC addresses to the RIF cache. If the cache is hit, the
packet will skip the L2 lookup and ingress the router with the RIF
specified in the cache entry.

1. https://tools.ietf.org/html/rfc5798#section-7.3

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          | 14 ++++++
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 52 ++++++++++++++++++++++
 2 files changed, 66 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index ccf4aae91630..6f98a43e75f5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -4353,6 +4353,20 @@ MLXSW_ITEM32(reg, ritr, if_swid, 0x08, 24, 8);
  */
 MLXSW_ITEM_BUF(reg, ritr, if_mac, 0x12, 6);
 
+/* reg_ritr_if_vrrp_id_ipv6
+ * VRRP ID for IPv6
+ * Note: Reserved for RIF types other than VLAN, FID and Sub-port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, if_vrrp_id_ipv6, 0x1C, 8, 8);
+
+/* reg_ritr_if_vrrp_id_ipv4
+ * VRRP ID for IPv4
+ * Note: Reserved for RIF types other than VLAN, FID and Sub-port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ritr, if_vrrp_id_ipv4, 0x1C, 0, 8);
+
 /* VLAN Interface */
 
 /* reg_ritr_vlan_if_vid
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 867d3db2c127..e51c8dc52f37 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -6449,6 +6449,46 @@ static int mlxsw_sp_inetaddr_vlan_event(struct net_device *vlan_dev,
 	return 0;
 }
 
+static bool mlxsw_sp_rif_macvlan_is_vrrp4(const u8 *mac)
+{
+	u8 vrrp4[ETH_ALEN] = { 0x00, 0x00, 0x5e, 0x00, 0x01, 0x00 };
+	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 };
+
+	return ether_addr_equal_masked(mac, vrrp4, mask);
+}
+
+static bool mlxsw_sp_rif_macvlan_is_vrrp6(const u8 *mac)
+{
+	u8 vrrp6[ETH_ALEN] = { 0x00, 0x00, 0x5e, 0x00, 0x02, 0x00 };
+	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x00 };
+
+	return ether_addr_equal_masked(mac, vrrp6, mask);
+}
+
+static int mlxsw_sp_rif_vrrp_op(struct mlxsw_sp *mlxsw_sp, u16 rif_index,
+				const u8 *mac, bool adding)
+{
+	char ritr_pl[MLXSW_REG_RITR_LEN];
+	u8 vrrp_id = adding ? mac[5] : 0;
+	int err;
+
+	if (!mlxsw_sp_rif_macvlan_is_vrrp4(mac) &&
+	    !mlxsw_sp_rif_macvlan_is_vrrp6(mac))
+		return 0;
+
+	mlxsw_reg_ritr_rif_pack(ritr_pl, rif_index);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+	if (err)
+		return err;
+
+	if (mlxsw_sp_rif_macvlan_is_vrrp4(mac))
+		mlxsw_reg_ritr_if_vrrp_id_ipv4_set(ritr_pl, vrrp_id);
+	else
+		mlxsw_reg_ritr_if_vrrp_id_ipv6_set(ritr_pl, vrrp_id);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ritr), ritr_pl);
+}
+
 static int mlxsw_sp_rif_macvlan_add(struct mlxsw_sp *mlxsw_sp,
 				    const struct net_device *macvlan_dev,
 				    struct netlink_ext_ack *extack)
@@ -6468,6 +6508,11 @@ static int mlxsw_sp_rif_macvlan_add(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
+	err = mlxsw_sp_rif_vrrp_op(mlxsw_sp, rif->rif_index,
+				   macvlan_dev->dev_addr, true);
+	if (err)
+		goto err_rif_vrrp_add;
+
 	/* Make sure the bridge driver does not have this MAC pointing at
 	 * some other port.
 	 */
@@ -6475,6 +6520,11 @@ static int mlxsw_sp_rif_macvlan_add(struct mlxsw_sp *mlxsw_sp,
 		rif->ops->fdb_del(rif, macvlan_dev->dev_addr);
 
 	return 0;
+
+err_rif_vrrp_add:
+	mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
+			    mlxsw_sp_fid_index(rif->fid), false);
+	return err;
 }
 
 void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
@@ -6489,6 +6539,8 @@ void mlxsw_sp_rif_macvlan_del(struct mlxsw_sp *mlxsw_sp,
 	 */
 	if (!rif)
 		return;
+	mlxsw_sp_rif_vrrp_op(mlxsw_sp, rif->rif_index, macvlan_dev->dev_addr,
+			     false);
 	mlxsw_sp_rif_fdb_op(mlxsw_sp, macvlan_dev->dev_addr,
 			    mlxsw_sp_fid_index(rif->fid), false);
 }
-- 
cgit v1.2.3


From f333ee0cdb27ba201e6cc0c99c76b1364aa29b86 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 11 Jul 2018 17:33:32 -0700
Subject: bpf: Add BPF_SOCK_OPS_TCP_LISTEN_CB

Add new TCP-BPF callback that is called on listen(2) right after socket
transition to TCP_LISTEN state.

It fills the gap for listening sockets in TCP-BPF. For example BPF
program can set BPF_SOCK_OPS_STATE_CB_FLAG when socket becomes listening
and track later transition from TCP_LISTEN to TCP_CLOSE with
BPF_SOCK_OPS_STATE_CB callback.

Before there was no way to do it with TCP-BPF and other options were
much harder to work with. E.g. socket state tracking can be done with
tracepoints (either raw or regular) but they can't be attached to cgroup
and their lifetime has to be managed separately.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h | 3 +++
 net/ipv4/af_inet.c       | 1 +
 2 files changed, 4 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 6bcb287a888d..870113916cac 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2555,6 +2555,9 @@ enum {
 					 * Arg1: old_state
 					 * Arg2: new_state
 					 */
+	BPF_SOCK_OPS_TCP_LISTEN_CB,	/* Called on listen(2), right after
+					 * socket transition to LISTEN state.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index c716be13d58c..f2a0a3bab6b5 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -229,6 +229,7 @@ int inet_listen(struct socket *sock, int backlog)
 		err = inet_csk_listen_start(sk, backlog);
 		if (err)
 			goto out;
+		tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_LISTEN_CB, 0, NULL);
 	}
 	sk->sk_max_ack_backlog = backlog;
 	err = 0;
-- 
cgit v1.2.3


From 060a7fccd394f1600be86536b1d3e8cdd66637c2 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 11 Jul 2018 17:33:33 -0700
Subject: bpf: Sync bpf.h to tools/

Sync BPF_SOCK_OPS_TCP_LISTEN_CB related UAPI changes to tools/.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 6bcb287a888d..870113916cac 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2555,6 +2555,9 @@ enum {
 					 * Arg1: old_state
 					 * Arg2: new_state
 					 */
+	BPF_SOCK_OPS_TCP_LISTEN_CB,	/* Called on listen(2), right after
+					 * socket transition to LISTEN state.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
-- 
cgit v1.2.3


From 04c13411151c220b41998020c32ac97f33b58683 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 11 Jul 2018 17:33:34 -0700
Subject: selftests/bpf: Fix const'ness in cgroup_helpers

Lack of const in cgroup helpers signatures forces to write ugly client
code. Fix it.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/cgroup_helpers.c | 6 +++---
 tools/testing/selftests/bpf/cgroup_helpers.h | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/cgroup_helpers.c b/tools/testing/selftests/bpf/cgroup_helpers.c
index c87b4e052ce9..cf16948aad4a 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.c
+++ b/tools/testing/selftests/bpf/cgroup_helpers.c
@@ -118,7 +118,7 @@ static int join_cgroup_from_top(char *cgroup_path)
  *
  * On success, it returns 0, otherwise on failure it returns 1.
  */
-int join_cgroup(char *path)
+int join_cgroup(const char *path)
 {
 	char cgroup_path[PATH_MAX + 1];
 
@@ -158,7 +158,7 @@ void cleanup_cgroup_environment(void)
  * On success, it returns the file descriptor. On failure it returns 0.
  * If there is a failure, it prints the error to stderr.
  */
-int create_and_get_cgroup(char *path)
+int create_and_get_cgroup(const char *path)
 {
 	char cgroup_path[PATH_MAX + 1];
 	int fd;
@@ -186,7 +186,7 @@ int create_and_get_cgroup(char *path)
  * which is an invalid cgroup id.
  * If there is a failure, it prints the error to stderr.
  */
-unsigned long long get_cgroup_id(char *path)
+unsigned long long get_cgroup_id(const char *path)
 {
 	int dirfd, err, flags, mount_id, fhsize;
 	union {
diff --git a/tools/testing/selftests/bpf/cgroup_helpers.h b/tools/testing/selftests/bpf/cgroup_helpers.h
index 20a4a5dcd469..d64bb8957090 100644
--- a/tools/testing/selftests/bpf/cgroup_helpers.h
+++ b/tools/testing/selftests/bpf/cgroup_helpers.h
@@ -9,10 +9,10 @@
 	__FILE__, __LINE__, clean_errno(), ##__VA_ARGS__)
 
 
-int create_and_get_cgroup(char *path);
-int join_cgroup(char *path);
+int create_and_get_cgroup(const char *path);
+int join_cgroup(const char *path);
 int setup_cgroup_environment(void);
 void cleanup_cgroup_environment(void);
-unsigned long long get_cgroup_id(char *path);
+unsigned long long get_cgroup_id(const char *path);
 
 #endif
-- 
cgit v1.2.3


From c65267e5ff418c81d7fea7025850ed4f190a1289 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 11 Jul 2018 17:33:35 -0700
Subject: selftests/bpf: Switch test_tcpbpf_user to cgroup_helpers

Switch to cgroup_helpers to simplify the code and fix cgroup cleanup:
before cgroup was not cleaned up after the test.

It also removes SYSTEM macro, that only printed error, but didn't
terminate the test.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile           |  1 +
 tools/testing/selftests/bpf/test_tcpbpf_user.c | 55 ++++++++++----------------
 2 files changed, 22 insertions(+), 34 deletions(-)

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 7a6214e9ae58..478bf1bcbbf5 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -61,6 +61,7 @@ $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
+$(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index 84ab5163c828..fa97ec6428de 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -1,25 +1,18 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
 #include <stdlib.h>
-#include <stdio.h>
 #include <unistd.h>
 #include <errno.h>
-#include <signal.h>
 #include <string.h>
-#include <assert.h>
-#include <linux/perf_event.h>
-#include <linux/ptrace.h>
 #include <linux/bpf.h>
-#include <sys/ioctl.h>
-#include <sys/time.h>
 #include <sys/types.h>
-#include <sys/stat.h>
-#include <fcntl.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
-#include "bpf_util.h"
+
 #include "bpf_rlimit.h"
-#include <linux/perf_event.h>
+#include "bpf_util.h"
+#include "cgroup_helpers.h"
+
 #include "test_tcpbpf.h"
 
 static int bpf_find_map(const char *test, struct bpf_object *obj,
@@ -35,42 +28,32 @@ static int bpf_find_map(const char *test, struct bpf_object *obj,
 	return bpf_map__fd(map);
 }
 
-#define SYSTEM(CMD)						\
-	do {							\
-		if (system(CMD)) {				\
-			printf("system(%s) FAILS!\n", CMD);	\
-		}						\
-	} while (0)
-
 int main(int argc, char **argv)
 {
 	const char *file = "test_tcpbpf_kern.o";
 	struct tcpbpf_globals g = {0};
-	int cg_fd, prog_fd, map_fd;
+	const char *cg_path = "/foo";
 	bool debug_flag = false;
 	int error = EXIT_FAILURE;
 	struct bpf_object *obj;
-	char cmd[100], *dir;
-	struct stat buffer;
+	int prog_fd, map_fd;
+	int cg_fd = -1;
 	__u32 key = 0;
-	int pid;
 	int rv;
 
 	if (argc > 1 && strcmp(argv[1], "-d") == 0)
 		debug_flag = true;
 
-	dir = "/tmp/cgroupv2/foo";
+	if (setup_cgroup_environment())
+		goto err;
+
+	cg_fd = create_and_get_cgroup(cg_path);
+	if (!cg_fd)
+		goto err;
 
-	if (stat(dir, &buffer) != 0) {
-		SYSTEM("mkdir -p /tmp/cgroupv2");
-		SYSTEM("mount -t cgroup2 none /tmp/cgroupv2");
-		SYSTEM("mkdir -p /tmp/cgroupv2/foo");
-	}
-	pid = (int) getpid();
-	sprintf(cmd, "echo %d >> /tmp/cgroupv2/foo/cgroup.procs", pid);
-	SYSTEM(cmd);
+	if (join_cgroup(cg_path))
+		goto err;
 
-	cg_fd = open(dir, O_DIRECTORY, O_RDONLY);
 	if (bpf_prog_load(file, BPF_PROG_TYPE_SOCK_OPS, &obj, &prog_fd)) {
 		printf("FAILED: load_bpf_file failed for: %s\n", file);
 		goto err;
@@ -83,7 +66,10 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	SYSTEM("./tcp_server.py");
+	if (system("./tcp_server.py")) {
+		printf("FAILED: TCP server\n");
+		goto err;
+	}
 
 	map_fd = bpf_find_map(__func__, obj, "global_map");
 	if (map_fd < 0)
@@ -123,6 +109,7 @@ int main(int argc, char **argv)
 	error = 0;
 err:
 	bpf_prog_detach(cg_fd, BPF_CGROUP_SOCK_OPS);
+	close(cg_fd);
+	cleanup_cgroup_environment();
 	return error;
-
 }
-- 
cgit v1.2.3


From 2044e4ef0be29f0154b078a956a3d8331315298a Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 11 Jul 2018 17:33:36 -0700
Subject: selftests/bpf: Better verification in test_tcpbpf

Reduce amount of copy/paste for debug info when result is verified in
the test and keep that info together with values being checked so that
they won't get out of sync.

It also improves debug experience: instead of checking manually what
doesn't match in debug output for all fields, only unexpected field is
printed.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_tcpbpf_user.c | 64 ++++++++++++++++----------
 1 file changed, 39 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index fa97ec6428de..971f1644b9c7 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <unistd.h>
@@ -15,6 +16,42 @@
 
 #include "test_tcpbpf.h"
 
+#define EXPECT_EQ(expected, actual, fmt)			\
+	do {							\
+		if ((expected) != (actual)) {			\
+			printf("  Value of: " #actual "\n"	\
+			       "    Actual: %" fmt "\n"		\
+			       "  Expected: %" fmt "\n",	\
+			       (actual), (expected));		\
+			goto err;				\
+		}						\
+	} while (0)
+
+int verify_result(const struct tcpbpf_globals *result)
+{
+	__u32 expected_events;
+
+	expected_events = ((1 << BPF_SOCK_OPS_TIMEOUT_INIT) |
+			   (1 << BPF_SOCK_OPS_RWND_INIT) |
+			   (1 << BPF_SOCK_OPS_TCP_CONNECT_CB) |
+			   (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
+			   (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
+			   (1 << BPF_SOCK_OPS_NEEDS_ECN) |
+			   (1 << BPF_SOCK_OPS_STATE_CB));
+
+	EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
+	EXPECT_EQ(501ULL, result->bytes_received, "llu");
+	EXPECT_EQ(1002ULL, result->bytes_acked, "llu");
+	EXPECT_EQ(1, result->data_segs_in, PRIu32);
+	EXPECT_EQ(1, result->data_segs_out, PRIu32);
+	EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
+	EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
+
+	return 0;
+err:
+	return -1;
+}
+
 static int bpf_find_map(const char *test, struct bpf_object *obj,
 			const char *name)
 {
@@ -33,7 +70,6 @@ int main(int argc, char **argv)
 	const char *file = "test_tcpbpf_kern.o";
 	struct tcpbpf_globals g = {0};
 	const char *cg_path = "/foo";
-	bool debug_flag = false;
 	int error = EXIT_FAILURE;
 	struct bpf_object *obj;
 	int prog_fd, map_fd;
@@ -41,9 +77,6 @@ int main(int argc, char **argv)
 	__u32 key = 0;
 	int rv;
 
-	if (argc > 1 && strcmp(argv[1], "-d") == 0)
-		debug_flag = true;
-
 	if (setup_cgroup_environment())
 		goto err;
 
@@ -81,30 +114,11 @@ int main(int argc, char **argv)
 		goto err;
 	}
 
-	if (g.bytes_received != 501 || g.bytes_acked != 1002 ||
-	    g.data_segs_in != 1 || g.data_segs_out != 1 ||
-	    (g.event_map ^ 0x47e) != 0 || g.bad_cb_test_rv != 0x80 ||
-		g.good_cb_test_rv != 0) {
+	if (verify_result(&g)) {
 		printf("FAILED: Wrong stats\n");
-		if (debug_flag) {
-			printf("\n");
-			printf("bytes_received: %d (expecting 501)\n",
-			       (int)g.bytes_received);
-			printf("bytes_acked:    %d (expecting 1002)\n",
-			       (int)g.bytes_acked);
-			printf("data_segs_in:   %d (expecting 1)\n",
-			       g.data_segs_in);
-			printf("data_segs_out:  %d (expecting 1)\n",
-			       g.data_segs_out);
-			printf("event_map:      0x%x (at least 0x47e)\n",
-			       g.event_map);
-			printf("bad_cb_test_rv: 0x%x (expecting 0x80)\n",
-			       g.bad_cb_test_rv);
-			printf("good_cb_test_rv:0x%x (expecting 0)\n",
-			       g.good_cb_test_rv);
-		}
 		goto err;
 	}
+
 	printf("PASSED!\n");
 	error = 0;
 err:
-- 
cgit v1.2.3


From 78d8e26d46bc2ed73ab6a0e369a342478fda4ce0 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Wed, 11 Jul 2018 17:33:37 -0700
Subject: selftests/bpf: Test case for BPF_SOCK_OPS_TCP_LISTEN_CB

Cover new TCP-BPF callback in test_tcpbpf: when listen() is called on
socket, set BPF_SOCK_OPS_STATE_CB_FLAG so that BPF_SOCK_OPS_STATE_CB
callback can be called on future state transition, and when such a
transition happens (TCP_LISTEN -> TCP_CLOSE), track it in the map and
verify it in user space later.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_tcpbpf.h      |  1 +
 tools/testing/selftests/bpf/test_tcpbpf_kern.c | 17 ++++++++++++-----
 tools/testing/selftests/bpf/test_tcpbpf_user.c |  4 +++-
 3 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_tcpbpf.h b/tools/testing/selftests/bpf/test_tcpbpf.h
index 2fe43289943c..7bcfa6207005 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf.h
+++ b/tools/testing/selftests/bpf/test_tcpbpf.h
@@ -12,5 +12,6 @@ struct tcpbpf_globals {
 	__u32 good_cb_test_rv;
 	__u64 bytes_received;
 	__u64 bytes_acked;
+	__u32 num_listen;
 };
 #endif
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 3e645ee41ed5..4b7fd540cea9 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -96,15 +96,22 @@ int bpf_testcb(struct bpf_sock_ops *skops)
 			if (!gp)
 				break;
 			g = *gp;
-			g.total_retrans = skops->total_retrans;
-			g.data_segs_in = skops->data_segs_in;
-			g.data_segs_out = skops->data_segs_out;
-			g.bytes_received = skops->bytes_received;
-			g.bytes_acked = skops->bytes_acked;
+			if (skops->args[0] == BPF_TCP_LISTEN) {
+				g.num_listen++;
+			} else {
+				g.total_retrans = skops->total_retrans;
+				g.data_segs_in = skops->data_segs_in;
+				g.data_segs_out = skops->data_segs_out;
+				g.bytes_received = skops->bytes_received;
+				g.bytes_acked = skops->bytes_acked;
+			}
 			bpf_map_update_elem(&global_map, &key, &g,
 					    BPF_ANY);
 		}
 		break;
+	case BPF_SOCK_OPS_TCP_LISTEN_CB:
+		bpf_sock_ops_cb_flags_set(skops, BPF_SOCK_OPS_STATE_CB_FLAG);
+		break;
 	default:
 		rv = -1;
 	}
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_user.c b/tools/testing/selftests/bpf/test_tcpbpf_user.c
index 971f1644b9c7..a275c2971376 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_user.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_user.c
@@ -37,7 +37,8 @@ int verify_result(const struct tcpbpf_globals *result)
 			   (1 << BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB) |
 			   (1 << BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB) |
 			   (1 << BPF_SOCK_OPS_NEEDS_ECN) |
-			   (1 << BPF_SOCK_OPS_STATE_CB));
+			   (1 << BPF_SOCK_OPS_STATE_CB) |
+			   (1 << BPF_SOCK_OPS_TCP_LISTEN_CB));
 
 	EXPECT_EQ(expected_events, result->event_map, "#" PRIx32);
 	EXPECT_EQ(501ULL, result->bytes_received, "llu");
@@ -46,6 +47,7 @@ int verify_result(const struct tcpbpf_globals *result)
 	EXPECT_EQ(1, result->data_segs_out, PRIu32);
 	EXPECT_EQ(0x80, result->bad_cb_test_rv, PRIu32);
 	EXPECT_EQ(0, result->good_cb_test_rv, PRIu32);
+	EXPECT_EQ(1, result->num_listen, PRIu32);
 
 	return 0;
 err:
-- 
cgit v1.2.3


From a7fe68a1e8e4bce007505f729bc33e427c540386 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Sat, 14 Jul 2018 19:05:58 -0400
Subject: drm/amd: Add CU-masking ioctl definition to kfd_ioctl.h

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 include/uapi/linux/kfd_ioctl.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/kfd_ioctl.h b/include/uapi/linux/kfd_ioctl.h
index 88d17c39dbf9..01674b56e14f 100644
--- a/include/uapi/linux/kfd_ioctl.h
+++ b/include/uapi/linux/kfd_ioctl.h
@@ -76,6 +76,12 @@ struct kfd_ioctl_update_queue_args {
 	__u32 queue_priority;	/* to KFD */
 };
 
+struct kfd_ioctl_set_cu_mask_args {
+	__u32 queue_id;		/* to KFD */
+	__u32 num_cu_mask;		/* to KFD */
+	__u64 cu_mask_ptr;		/* to KFD */
+};
+
 /* For kfd_ioctl_set_memory_policy_args.default_policy and alternate_policy */
 #define KFD_IOC_CACHE_POLICY_COHERENT 0
 #define KFD_IOC_CACHE_POLICY_NONCOHERENT 1
@@ -466,7 +472,10 @@ struct kfd_ioctl_unmap_memory_from_gpu_args {
 #define AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU	\
 		AMDKFD_IOWR(0x19, struct kfd_ioctl_unmap_memory_from_gpu_args)
 
+#define AMDKFD_IOC_SET_CU_MASK		\
+		AMDKFD_IOW(0x1A, struct kfd_ioctl_set_cu_mask_args)
+
 #define AMDKFD_COMMAND_START		0x01
-#define AMDKFD_COMMAND_END		0x1A
+#define AMDKFD_COMMAND_END		0x1B
 
 #endif
-- 
cgit v1.2.3


From 39e7f331864d2b9e30d5f3fd2121e182b2c9c8a9 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Sat, 14 Jul 2018 19:05:59 -0400
Subject: drm/amdkfd: Add CU-masking ioctl to KFD

CU-masking allows a KFD client to control the set of CUs used by a
user mode queue for executing compute dispatches. This can be used
for optimizing the partitioning of the GPU and minimize conflicts
between concurrent tasks.

Signed-off-by: Flora Cui <flora.cui@amd.com>
Signed-off-by: Kent Russell <kent.russell@amd.com>
Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Acked-by: Oded Gabbay <oded.gabbay@gmail.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_chardev.c           | 58 ++++++++++++++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c      |  1 +
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c       | 41 ++++++++++++++-
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h       |  4 ++
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c   | 27 ++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c    | 27 ++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c    | 27 ++++++++++
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h              |  5 ++
 .../gpu/drm/amd/amdkfd/kfd_process_queue_manager.c | 30 +++++++++++
 9 files changed, 219 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
index b5338bff8cef..297b36c26a05 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_chardev.c
@@ -392,6 +392,61 @@ static int kfd_ioctl_update_queue(struct file *filp, struct kfd_process *p,
 	return retval;
 }
 
+static int kfd_ioctl_set_cu_mask(struct file *filp, struct kfd_process *p,
+					void *data)
+{
+	int retval;
+	const int max_num_cus = 1024;
+	struct kfd_ioctl_set_cu_mask_args *args = data;
+	struct queue_properties properties;
+	uint32_t __user *cu_mask_ptr = (uint32_t __user *)args->cu_mask_ptr;
+	size_t cu_mask_size = sizeof(uint32_t) * (args->num_cu_mask / 32);
+
+	if ((args->num_cu_mask % 32) != 0) {
+		pr_debug("num_cu_mask 0x%x must be a multiple of 32",
+				args->num_cu_mask);
+		return -EINVAL;
+	}
+
+	properties.cu_mask_count = args->num_cu_mask;
+	if (properties.cu_mask_count == 0) {
+		pr_debug("CU mask cannot be 0");
+		return -EINVAL;
+	}
+
+	/* To prevent an unreasonably large CU mask size, set an arbitrary
+	 * limit of max_num_cus bits.  We can then just drop any CU mask bits
+	 * past max_num_cus bits and just use the first max_num_cus bits.
+	 */
+	if (properties.cu_mask_count > max_num_cus) {
+		pr_debug("CU mask cannot be greater than 1024 bits");
+		properties.cu_mask_count = max_num_cus;
+		cu_mask_size = sizeof(uint32_t) * (max_num_cus/32);
+	}
+
+	properties.cu_mask = kzalloc(cu_mask_size, GFP_KERNEL);
+	if (!properties.cu_mask)
+		return -ENOMEM;
+
+	retval = copy_from_user(properties.cu_mask, cu_mask_ptr, cu_mask_size);
+	if (retval) {
+		pr_debug("Could not copy CU mask from userspace");
+		kfree(properties.cu_mask);
+		return -EFAULT;
+	}
+
+	mutex_lock(&p->mutex);
+
+	retval = pqm_set_cu_mask(&p->pqm, args->queue_id, &properties);
+
+	mutex_unlock(&p->mutex);
+
+	if (retval)
+		kfree(properties.cu_mask);
+
+	return retval;
+}
+
 static int kfd_ioctl_set_memory_policy(struct file *filep,
 					struct kfd_process *p, void *data)
 {
@@ -1557,6 +1612,9 @@ static const struct amdkfd_ioctl_desc amdkfd_ioctls[] = {
 	AMDKFD_IOCTL_DEF(AMDKFD_IOC_UNMAP_MEMORY_FROM_GPU,
 			kfd_ioctl_unmap_memory_from_gpu, 0),
 
+	AMDKFD_IOCTL_DEF(AMDKFD_IOC_SET_CU_MASK,
+			kfd_ioctl_set_cu_mask, 0),
+
 };
 
 #define AMDKFD_CORE_IOCTL_COUNT	ARRAY_SIZE(amdkfd_ioctls)
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
index 2c8897e9073d..9f84b4d9fb88 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_kernel_queue.c
@@ -123,6 +123,7 @@ static bool initialize(struct kernel_queue *kq, struct kfd_dev *dev,
 	prop.write_ptr = (uint32_t *) kq->wptr_gpu_addr;
 	prop.eop_ring_buffer_address = kq->eop_gpu_addr;
 	prop.eop_ring_buffer_size = PAGE_SIZE;
+	prop.cu_mask = NULL;
 
 	if (init_queue(&kq->queue, &prop) != 0)
 		goto err_init_queue;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
index 4b8eb506642b..3bc25ab84f34 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.c
@@ -21,7 +21,7 @@
  *
  */
 
-#include "kfd_priv.h"
+#include "kfd_mqd_manager.h"
 
 struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 					struct kfd_dev *dev)
@@ -48,3 +48,42 @@ struct mqd_manager *mqd_manager_init(enum KFD_MQD_TYPE type,
 
 	return NULL;
 }
+
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask)
+{
+	struct kfd_cu_info cu_info;
+	uint32_t cu_per_sh[4] = {0};
+	int i, se, cu = 0;
+
+	mm->dev->kfd2kgd->get_cu_info(mm->dev->kgd, &cu_info);
+
+	if (cu_mask_count > cu_info.cu_active_number)
+		cu_mask_count = cu_info.cu_active_number;
+
+	for (se = 0; se < cu_info.num_shader_engines; se++)
+		for (i = 0; i < 4; i++)
+			cu_per_sh[se] += hweight32(cu_info.cu_bitmap[se][i]);
+
+	/* Symmetrically map cu_mask to all SEs:
+	 * cu_mask[0] bit0 -> se_mask[0] bit0;
+	 * cu_mask[0] bit1 -> se_mask[1] bit0;
+	 * ... (if # SE is 4)
+	 * cu_mask[0] bit4 -> se_mask[0] bit1;
+	 * ...
+	 */
+	se = 0;
+	for (i = 0; i < cu_mask_count; i++) {
+		if (cu_mask[i / 32] & (1 << (i % 32)))
+			se_mask[se] |= 1 << cu;
+
+		do {
+			se++;
+			if (se == cu_info.num_shader_engines) {
+				se = 0;
+				cu++;
+			}
+		} while (cu >= cu_per_sh[se] && cu < 32);
+	}
+}
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
index 8972bcfbf701..4e84052d4e21 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager.h
@@ -93,4 +93,8 @@ struct mqd_manager {
 	struct kfd_dev	*dev;
 };
 
+void mqd_symmetrically_map_cu_mask(struct mqd_manager *mm,
+		const uint32_t *cu_mask, uint32_t cu_mask_count,
+		uint32_t *se_mask);
+
 #endif /* KFD_MQD_MANAGER_H_ */
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
index 4872574f7a04..47243165a082 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_cik.c
@@ -41,6 +41,31 @@ static inline struct cik_sdma_rlc_registers *get_sdma_mqd(void *mqd)
 	return (struct cik_sdma_rlc_registers *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct cik_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 		struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 		struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 	if (q->format == KFD_QUEUE_FORMAT_AQL)
 		m->cp_hqd_pq_control |= NO_UPDATE_RPTR;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index ad5c9f80cccd..f5fc3675f21e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -41,6 +41,31 @@ static inline struct v9_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct v9_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct v9_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -198,6 +223,8 @@ static int update_mqd(struct mqd_manager *mm, void *mqd,
 	if (mm->dev->cwsr_enabled && q->ctx_save_restore_area_address)
 		m->cp_hqd_ctx_save_control = 0;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
index 89e4242e43e7..b81fda3754da 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_vi.c
@@ -43,6 +43,31 @@ static inline struct vi_sdma_mqd *get_sdma_mqd(void *mqd)
 	return (struct vi_sdma_mqd *)mqd;
 }
 
+static void update_cu_mask(struct mqd_manager *mm, void *mqd,
+			struct queue_properties *q)
+{
+	struct vi_mqd *m;
+	uint32_t se_mask[4] = {0}; /* 4 is the max # of SEs */
+
+	if (q->cu_mask_count == 0)
+		return;
+
+	mqd_symmetrically_map_cu_mask(mm,
+		q->cu_mask, q->cu_mask_count, se_mask);
+
+	m = get_mqd(mqd);
+	m->compute_static_thread_mgmt_se0 = se_mask[0];
+	m->compute_static_thread_mgmt_se1 = se_mask[1];
+	m->compute_static_thread_mgmt_se2 = se_mask[2];
+	m->compute_static_thread_mgmt_se3 = se_mask[3];
+
+	pr_debug("Update cu mask to %#x %#x %#x %#x\n",
+		m->compute_static_thread_mgmt_se0,
+		m->compute_static_thread_mgmt_se1,
+		m->compute_static_thread_mgmt_se2,
+		m->compute_static_thread_mgmt_se3);
+}
+
 static int init_mqd(struct mqd_manager *mm, void **mqd,
 			struct kfd_mem_obj **mqd_mem_obj, uint64_t *gart_addr,
 			struct queue_properties *q)
@@ -196,6 +221,8 @@ static int __update_mqd(struct mqd_manager *mm, void *mqd,
 			atc_bit << CP_HQD_CTX_SAVE_CONTROL__ATC__SHIFT |
 			mtype << CP_HQD_CTX_SAVE_CONTROL__MTYPE__SHIFT;
 
+	update_cu_mask(mm, mqd, q);
+
 	q->is_active = (q->queue_size > 0 &&
 			q->queue_address != 0 &&
 			q->queue_percent > 0 &&
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
index ca83254719fc..f971710f1c91 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_priv.h
@@ -422,6 +422,9 @@ struct queue_properties {
 	uint32_t ctl_stack_size;
 	uint64_t tba_addr;
 	uint64_t tma_addr;
+	/* Relevant for CU */
+	uint32_t cu_mask_count; /* Must be a multiple of 32 */
+	uint32_t *cu_mask;
 };
 
 /**
@@ -872,6 +875,8 @@ int pqm_create_queue(struct process_queue_manager *pqm,
 int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid);
 int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 			struct queue_properties *p);
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p);
 struct kernel_queue *pqm_get_kernel_queue(struct process_queue_manager *pqm,
 						unsigned int qid);
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index eb4e5fb4f2f2..c8cad9c078ae 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -325,6 +325,8 @@ int pqm_destroy_queue(struct process_queue_manager *pqm, unsigned int qid)
 			if (retval != -ETIME)
 				goto err_destroy_queue;
 		}
+		kfree(pqn->q->properties.cu_mask);
+		pqn->q->properties.cu_mask = NULL;
 		uninit_queue(pqn->q);
 	}
 
@@ -365,6 +367,34 @@ int pqm_update_queue(struct process_queue_manager *pqm, unsigned int qid,
 	return 0;
 }
 
+int pqm_set_cu_mask(struct process_queue_manager *pqm, unsigned int qid,
+			struct queue_properties *p)
+{
+	int retval;
+	struct process_queue_node *pqn;
+
+	pqn = get_queue_by_qid(pqm, qid);
+	if (!pqn) {
+		pr_debug("No queue %d exists for update operation\n", qid);
+		return -EFAULT;
+	}
+
+	/* Free the old CU mask memory if it is already allocated, then
+	 * allocate memory for the new CU mask.
+	 */
+	kfree(pqn->q->properties.cu_mask);
+
+	pqn->q->properties.cu_mask_count = p->cu_mask_count;
+	pqn->q->properties.cu_mask = p->cu_mask;
+
+	retval = pqn->q->device->dqm->ops.update_queue(pqn->q->device->dqm,
+							pqn->q);
+	if (retval != 0)
+		return retval;
+
+	return 0;
+}
+
 struct kernel_queue *pqm_get_kernel_queue(
 					struct process_queue_manager *pqm,
 					unsigned int qid)
-- 
cgit v1.2.3


From 6c26fcd2abfe0a56bbd95271fce02df2896cfd24 Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Sat, 14 Jul 2018 21:56:13 +0200
Subject: x86/speculation/l1tf: Unbreak !__HAVE_ARCH_PFN_MODIFY_ALLOWED
 architectures

pfn_modify_allowed() and arch_has_pfn_modify_check() are outside of the
!__ASSEMBLY__ section in include/asm-generic/pgtable.h, which confuses
assembler on archs that don't have __HAVE_ARCH_PFN_MODIFY_ALLOWED (e.g.
ia64) and breaks build:

    include/asm-generic/pgtable.h: Assembler messages:
    include/asm-generic/pgtable.h:538: Error: Unknown opcode `static inline bool pfn_modify_allowed(unsigned long pfn,pgprot_t prot)'
    include/asm-generic/pgtable.h:540: Error: Unknown opcode `return true'
    include/asm-generic/pgtable.h:543: Error: Unknown opcode `static inline bool arch_has_pfn_modify_check(void)'
    include/asm-generic/pgtable.h:545: Error: Unknown opcode `return false'
    arch/ia64/kernel/entry.S:69: Error: `mov' does not fit into bundle

Move those two static inlines into the !__ASSEMBLY__ section so that they
don't confuse the asm build pass.

Fixes: 42e4089c7890 ("x86/speculation/l1tf: Disallow non privileged high MMIO PROT_NONE mappings")
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 include/asm-generic/pgtable.h | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 0ecc1197084b..26ca0276b503 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -1083,6 +1083,18 @@ int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
 static inline void init_espfix_bsp(void) { }
 #endif
 
+#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
+static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
+{
+	return true;
+}
+
+static inline bool arch_has_pfn_modify_check(void)
+{
+	return false;
+}
+#endif /* !_HAVE_ARCH_PFN_MODIFY_ALLOWED */
+
 #endif /* !__ASSEMBLY__ */
 
 #ifndef io_remap_pfn_range
@@ -1097,16 +1109,4 @@ static inline void init_espfix_bsp(void) { }
 #endif
 #endif
 
-#ifndef __HAVE_ARCH_PFN_MODIFY_ALLOWED
-static inline bool pfn_modify_allowed(unsigned long pfn, pgprot_t prot)
-{
-	return true;
-}
-
-static inline bool arch_has_pfn_modify_check(void)
-{
-	return false;
-}
-#endif
-
 #endif /* _ASM_GENERIC_PGTABLE_H */
-- 
cgit v1.2.3


From be45bf5395e0886a93fc816bbe41a008ec2e42e2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 13 Jul 2018 12:42:08 +0200
Subject: watchdog/softlockup: Fix cpu_stop_queue_work() double-queue bug

When scheduling is delayed for longer than the softlockup interrupt
period it is possible to double-queue the cpu_stop_work, causing list
corruption.

Cure this by adding a completion to track the cpu_stop_work's
progress.

Reported-by: kernel test robot <lkp@intel.com>
Tested-by: Rong Chen <rong.a.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Fixes: 9cf57731b63e ("watchdog/softlockup: Replace "watchdog/%u" threads with cpu_stop_work")
Link: http://lkml.kernel.org/r/20180713104208.GW2494@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/watchdog.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index b81f777838d5..5470dce212c0 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -330,6 +330,9 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
+static DEFINE_PER_CPU(struct completion, softlockup_completion);
+static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
+
 /*
  * The watchdog thread function - touches the timestamp.
  *
@@ -343,12 +346,11 @@ static int softlockup_fn(void *data)
 	__this_cpu_write(soft_lockup_hrtimer_cnt,
 			 __this_cpu_read(hrtimer_interrupts));
 	__touch_watchdog();
+	complete(this_cpu_ptr(&softlockup_completion));
 
 	return 0;
 }
 
-static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work);
-
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -364,9 +366,12 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	watchdog_interrupt_count();
 
 	/* kick the softlockup detector */
-	stop_one_cpu_nowait(smp_processor_id(),
-			softlockup_fn, NULL,
-			this_cpu_ptr(&softlockup_stop_work));
+	if (completion_done(this_cpu_ptr(&softlockup_completion))) {
+		reinit_completion(this_cpu_ptr(&softlockup_completion));
+		stop_one_cpu_nowait(smp_processor_id(),
+				softlockup_fn, NULL,
+				this_cpu_ptr(&softlockup_stop_work));
+	}
 
 	/* .. and repeat */
 	hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period));
@@ -467,9 +472,13 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 static void watchdog_enable(unsigned int cpu)
 {
 	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
+	struct completion *done = this_cpu_ptr(&softlockup_completion);
 
 	WARN_ON_ONCE(cpu != smp_processor_id());
 
+	init_completion(done);
+	complete(done);
+
 	/*
 	 * Start the timer first to prevent the NMI watchdog triggering
 	 * before the timer has a chance to fire.
@@ -499,6 +508,7 @@ static void watchdog_disable(unsigned int cpu)
 	 */
 	watchdog_nmi_disable(cpu);
 	hrtimer_cancel(hrtimer);
+	wait_for_completion(this_cpu_ptr(&softlockup_completion));
 }
 
 static int softlockup_stop_fn(void *data)
-- 
cgit v1.2.3


From 8fe5c5a937d0f4e84221631833a2718afde52285 Mon Sep 17 00:00:00 2001
From: Quentin Perret <quentin.perret@arm.com>
Date: Tue, 12 Jun 2018 12:22:15 +0100
Subject: sched/fair: Fix util_avg of new tasks for asymmetric systems

When a new task wakes-up for the first time, its initial utilization
is set to half of the spare capacity of its CPU. The current
implementation of post_init_entity_util_avg() uses SCHED_CAPACITY_SCALE
directly as a capacity reference. As a result, on a big.LITTLE system, a
new task waking up on an idle little CPU will be given ~512 of util_avg,
even if the CPU's capacity is significantly less than that.

Fix this by computing the spare capacity with arch_scale_cpu_capacity().

Signed-off-by: Quentin Perret <quentin.perret@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dietmar.eggemann@arm.com
Cc: morten.rasmussen@arm.com
Cc: patrick.bellasi@arm.com
Link: http://lkml.kernel.org/r/20180612112215.25448-1-quentin.perret@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 321cd5dcf2e8..08b89ae34233 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -735,11 +735,12 @@ static void attach_entity_cfs_rq(struct sched_entity *se);
  * To solve this problem, we also cap the util_avg of successive tasks to
  * only 1/2 of the left utilization budget:
  *
- *   util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ *   util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
  *
- * where n denotes the nth task.
+ * where n denotes the nth task and cpu_scale the CPU capacity.
  *
- * For example, a simplest series from the beginning would be like:
+ * For example, for a CPU with 1024 of capacity, a simplest series from
+ * the beginning would be like:
  *
  *  task  util_avg: 512, 256, 128,  64,  32,   16,    8, ...
  * cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
@@ -751,7 +752,8 @@ void post_init_entity_util_avg(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 	struct sched_avg *sa = &se->avg;
-	long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+	long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+	long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
 
 	if (cap > 0) {
 		if (cfs_rq->avg.util_avg != 0) {
-- 
cgit v1.2.3


From c079629862b20c101e8336362a8b042ec7d942fe Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:04 +0200
Subject: sched/pelt: Move PELT related code in a dedicated file

We want to track rt_rq's utilization as a part of the estimation of the
whole rq's utilization. This is necessary because rt tasks can steal
utilization to cfs tasks and make them lighter than they are.
As we want to use the same load tracking mecanism for both and prevent
useless dependency between cfs and rt code, PELT code is moved in a
dedicated file.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-2-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/Makefile |   2 +-
 kernel/sched/fair.c   | 333 +-------------------------------------------------
 kernel/sched/pelt.c   | 311 ++++++++++++++++++++++++++++++++++++++++++++++
 kernel/sched/pelt.h   |  43 +++++++
 kernel/sched/sched.h  |  19 +++
 5 files changed, 375 insertions(+), 333 deletions(-)
 create mode 100644 kernel/sched/pelt.c
 create mode 100644 kernel/sched/pelt.h

diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index d9a02b318108..7fe183404c38 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -20,7 +20,7 @@ obj-y += core.o loadavg.o clock.o cputime.o
 obj-y += idle.o fair.o rt.o deadline.o
 obj-y += wait.o wait_bit.o swait.o completion.o
 
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o
+obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
 obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
 obj-$(CONFIG_SCHEDSTATS) += stats.o
 obj-$(CONFIG_SCHED_DEBUG) += debug.o
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 08b89ae34233..39ab46cea6c5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -255,9 +255,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 	return cfs_rq->rq;
 }
 
-/* An entity is a task if it doesn't "own" a runqueue */
-#define entity_is_task(se)	(!se->my_q)
-
 static inline struct task_struct *task_of(struct sched_entity *se)
 {
 	SCHED_WARN_ON(!entity_is_task(se));
@@ -419,7 +416,6 @@ static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
 	return container_of(cfs_rq, struct rq, cfs);
 }
 
-#define entity_is_task(se)	1
 
 #define for_each_sched_entity(se) \
 		for (; se; se = NULL)
@@ -692,7 +688,7 @@ static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
 }
 
 #ifdef CONFIG_SMP
-
+#include "pelt.h"
 #include "sched-pelt.h"
 
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
@@ -2751,19 +2747,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 } while (0)
 
 #ifdef CONFIG_SMP
-/*
- * XXX we want to get rid of these helpers and use the full load resolution.
- */
-static inline long se_weight(struct sched_entity *se)
-{
-	return scale_load_down(se->load.weight);
-}
-
-static inline long se_runnable(struct sched_entity *se)
-{
-	return scale_load_down(se->runnable_weight);
-}
-
 static inline void
 enqueue_runnable_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -3064,314 +3047,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 }
 
 #ifdef CONFIG_SMP
-/*
- * Approximate:
- *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
- */
-static u64 decay_load(u64 val, u64 n)
-{
-	unsigned int local_n;
-
-	if (unlikely(n > LOAD_AVG_PERIOD * 63))
-		return 0;
-
-	/* after bounds checking we can collapse to 32-bit */
-	local_n = n;
-
-	/*
-	 * As y^PERIOD = 1/2, we can combine
-	 *    y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
-	 * With a look-up table which covers y^n (n<PERIOD)
-	 *
-	 * To achieve constant time decay_load.
-	 */
-	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
-		val >>= local_n / LOAD_AVG_PERIOD;
-		local_n %= LOAD_AVG_PERIOD;
-	}
-
-	val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
-	return val;
-}
-
-static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
-{
-	u32 c1, c2, c3 = d3; /* y^0 == 1 */
-
-	/*
-	 * c1 = d1 y^p
-	 */
-	c1 = decay_load((u64)d1, periods);
-
-	/*
-	 *            p-1
-	 * c2 = 1024 \Sum y^n
-	 *            n=1
-	 *
-	 *              inf        inf
-	 *    = 1024 ( \Sum y^n - \Sum y^n - y^0 )
-	 *              n=0        n=p
-	 */
-	c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
-
-	return c1 + c2 + c3;
-}
-
-/*
- * Accumulate the three separate parts of the sum; d1 the remainder
- * of the last (incomplete) period, d2 the span of full periods and d3
- * the remainder of the (incomplete) current period.
- *
- *           d1          d2           d3
- *           ^           ^            ^
- *           |           |            |
- *         |<->|<----------------->|<--->|
- * ... |---x---|------| ... |------|-----x (now)
- *
- *                           p-1
- * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
- *                           n=1
- *
- *    = u y^p +					(Step 1)
- *
- *                     p-1
- *      d1 y^p + 1024 \Sum y^n + d3 y^0		(Step 2)
- *                     n=1
- */
-static __always_inline u32
-accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
-	       unsigned long load, unsigned long runnable, int running)
-{
-	unsigned long scale_freq, scale_cpu;
-	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
-	u64 periods;
-
-	scale_freq = arch_scale_freq_capacity(cpu);
-	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
-
-	delta += sa->period_contrib;
-	periods = delta / 1024; /* A period is 1024us (~1ms) */
-
-	/*
-	 * Step 1: decay old *_sum if we crossed period boundaries.
-	 */
-	if (periods) {
-		sa->load_sum = decay_load(sa->load_sum, periods);
-		sa->runnable_load_sum =
-			decay_load(sa->runnable_load_sum, periods);
-		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
-
-		/*
-		 * Step 2
-		 */
-		delta %= 1024;
-		contrib = __accumulate_pelt_segments(periods,
-				1024 - sa->period_contrib, delta);
-	}
-	sa->period_contrib = delta;
-
-	contrib = cap_scale(contrib, scale_freq);
-	if (load)
-		sa->load_sum += load * contrib;
-	if (runnable)
-		sa->runnable_load_sum += runnable * contrib;
-	if (running)
-		sa->util_sum += contrib * scale_cpu;
-
-	return periods;
-}
-
-/*
- * We can represent the historical contribution to runnable average as the
- * coefficients of a geometric series.  To do this we sub-divide our runnable
- * history into segments of approximately 1ms (1024us); label the segment that
- * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
- *
- * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
- *      p0            p1           p2
- *     (now)       (~1ms ago)  (~2ms ago)
- *
- * Let u_i denote the fraction of p_i that the entity was runnable.
- *
- * We then designate the fractions u_i as our co-efficients, yielding the
- * following representation of historical load:
- *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
- *
- * We choose y based on the with of a reasonably scheduling period, fixing:
- *   y^32 = 0.5
- *
- * This means that the contribution to load ~32ms ago (u_32) will be weighted
- * approximately half as much as the contribution to load within the last ms
- * (u_0).
- *
- * When a period "rolls over" and we have new u_0`, multiplying the previous
- * sum again by y is sufficient to update:
- *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
- *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
- */
-static __always_inline int
-___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
-		  unsigned long load, unsigned long runnable, int running)
-{
-	u64 delta;
-
-	delta = now - sa->last_update_time;
-	/*
-	 * This should only happen when time goes backwards, which it
-	 * unfortunately does during sched clock init when we swap over to TSC.
-	 */
-	if ((s64)delta < 0) {
-		sa->last_update_time = now;
-		return 0;
-	}
-
-	/*
-	 * Use 1024ns as the unit of measurement since it's a reasonable
-	 * approximation of 1us and fast to compute.
-	 */
-	delta >>= 10;
-	if (!delta)
-		return 0;
-
-	sa->last_update_time += delta << 10;
-
-	/*
-	 * running is a subset of runnable (weight) so running can't be set if
-	 * runnable is clear. But there are some corner cases where the current
-	 * se has been already dequeued but cfs_rq->curr still points to it.
-	 * This means that weight will be 0 but not running for a sched_entity
-	 * but also for a cfs_rq if the latter becomes idle. As an example,
-	 * this happens during idle_balance() which calls
-	 * update_blocked_averages()
-	 */
-	if (!load)
-		runnable = running = 0;
-
-	/*
-	 * Now we know we crossed measurement unit boundaries. The *_avg
-	 * accrues by two steps:
-	 *
-	 * Step 1: accumulate *_sum since last_update_time. If we haven't
-	 * crossed period boundaries, finish.
-	 */
-	if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
-		return 0;
-
-	return 1;
-}
-
-static __always_inline void
-___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
-{
-	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
-
-	/*
-	 * Step 2: update *_avg.
-	 */
-	sa->load_avg = div_u64(load * sa->load_sum, divider);
-	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
-	sa->util_avg = sa->util_sum / divider;
-}
-
-/*
- * When a task is dequeued, its estimated utilization should not be update if
- * its util_avg has not been updated at least once.
- * This flag is used to synchronize util_avg updates with util_est updates.
- * We map this information into the LSB bit of the utilization saved at
- * dequeue time (i.e. util_est.dequeued).
- */
-#define UTIL_AVG_UNCHANGED 0x1
-
-static inline void cfs_se_util_change(struct sched_avg *avg)
-{
-	unsigned int enqueued;
-
-	if (!sched_feat(UTIL_EST))
-		return;
-
-	/* Avoid store if the flag has been already set */
-	enqueued = avg->util_est.enqueued;
-	if (!(enqueued & UTIL_AVG_UNCHANGED))
-		return;
-
-	/* Reset flag to report util_avg has been updated */
-	enqueued &= ~UTIL_AVG_UNCHANGED;
-	WRITE_ONCE(avg->util_est.enqueued, enqueued);
-}
-
-/*
- * sched_entity:
- *
- *   task:
- *     se_runnable() == se_weight()
- *
- *   group: [ see update_cfs_group() ]
- *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
- *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
- *
- *   load_sum := runnable_sum
- *   load_avg = se_weight(se) * runnable_avg
- *
- *   runnable_load_sum := runnable_sum
- *   runnable_load_avg = se_runnable(se) * runnable_avg
- *
- * XXX collapse load_sum and runnable_load_sum
- *
- * cfq_rs:
- *
- *   load_sum = \Sum se_weight(se) * se->avg.load_sum
- *   load_avg = \Sum se->avg.load_avg
- *
- *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
- *   runnable_load_avg = \Sum se->avg.runable_load_avg
- */
-
-static int
-__update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
-{
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
-	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
-		return 1;
-	}
-
-	return 0;
-}
-
-static int
-__update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
-	if (entity_is_task(se))
-		se->runnable_weight = se->load.weight;
-
-	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
-				cfs_rq->curr == se)) {
-
-		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
-		cfs_se_util_change(&se->avg);
-		return 1;
-	}
-
-	return 0;
-}
-
-static int
-__update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
-{
-	if (___update_load_sum(now, cpu, &cfs_rq->avg,
-				scale_load_down(cfs_rq->load.weight),
-				scale_load_down(cfs_rq->runnable_weight),
-				cfs_rq->curr != NULL)) {
-
-		___update_load_avg(&cfs_rq->avg, 1, 1);
-		return 1;
-	}
-
-	return 0;
-}
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 /**
  * update_tg_load_avg - update the tg's load avg
@@ -4039,12 +3714,6 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
 
 #else /* CONFIG_SMP */
 
-static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
-{
-	return 0;
-}
-
 #define UPDATE_TG	0x0
 #define SKIP_AGE_LOAD	0x0
 #define DO_ATTACH	0x0
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
new file mode 100644
index 000000000000..e6ecbb2b8698
--- /dev/null
+++ b/kernel/sched/pelt.c
@@ -0,0 +1,311 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Per Entity Load Tracking
+ *
+ *  Copyright (C) 2007 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *
+ *  Interactivity improvements by Mike Galbraith
+ *  (C) 2007 Mike Galbraith <efault@gmx.de>
+ *
+ *  Various enhancements by Dmitry Adamushko.
+ *  (C) 2007 Dmitry Adamushko <dmitry.adamushko@gmail.com>
+ *
+ *  Group scheduling enhancements by Srivatsa Vaddagiri
+ *  Copyright IBM Corporation, 2007
+ *  Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
+ *
+ *  Scaled math optimizations by Thomas Gleixner
+ *  Copyright (C) 2007, Thomas Gleixner <tglx@linutronix.de>
+ *
+ *  Adaptive scheduling granularity, math enhancements by Peter Zijlstra
+ *  Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra
+ *
+ *  Move PELT related code from fair.c into this pelt.c file
+ *  Author: Vincent Guittot <vincent.guittot@linaro.org>
+ */
+
+#include <linux/sched.h>
+#include "sched.h"
+#include "sched-pelt.h"
+#include "pelt.h"
+
+/*
+ * Approximate:
+ *   val * y^n,    where y^32 ~= 0.5 (~1 scheduling period)
+ */
+static u64 decay_load(u64 val, u64 n)
+{
+	unsigned int local_n;
+
+	if (unlikely(n > LOAD_AVG_PERIOD * 63))
+		return 0;
+
+	/* after bounds checking we can collapse to 32-bit */
+	local_n = n;
+
+	/*
+	 * As y^PERIOD = 1/2, we can combine
+	 *    y^n = 1/2^(n/PERIOD) * y^(n%PERIOD)
+	 * With a look-up table which covers y^n (n<PERIOD)
+	 *
+	 * To achieve constant time decay_load.
+	 */
+	if (unlikely(local_n >= LOAD_AVG_PERIOD)) {
+		val >>= local_n / LOAD_AVG_PERIOD;
+		local_n %= LOAD_AVG_PERIOD;
+	}
+
+	val = mul_u64_u32_shr(val, runnable_avg_yN_inv[local_n], 32);
+	return val;
+}
+
+static u32 __accumulate_pelt_segments(u64 periods, u32 d1, u32 d3)
+{
+	u32 c1, c2, c3 = d3; /* y^0 == 1 */
+
+	/*
+	 * c1 = d1 y^p
+	 */
+	c1 = decay_load((u64)d1, periods);
+
+	/*
+	 *            p-1
+	 * c2 = 1024 \Sum y^n
+	 *            n=1
+	 *
+	 *              inf        inf
+	 *    = 1024 ( \Sum y^n - \Sum y^n - y^0 )
+	 *              n=0        n=p
+	 */
+	c2 = LOAD_AVG_MAX - decay_load(LOAD_AVG_MAX, periods) - 1024;
+
+	return c1 + c2 + c3;
+}
+
+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
+
+/*
+ * Accumulate the three separate parts of the sum; d1 the remainder
+ * of the last (incomplete) period, d2 the span of full periods and d3
+ * the remainder of the (incomplete) current period.
+ *
+ *           d1          d2           d3
+ *           ^           ^            ^
+ *           |           |            |
+ *         |<->|<----------------->|<--->|
+ * ... |---x---|------| ... |------|-----x (now)
+ *
+ *                           p-1
+ * u' = (u + d1) y^p + 1024 \Sum y^n + d3 y^0
+ *                           n=1
+ *
+ *    = u y^p +					(Step 1)
+ *
+ *                     p-1
+ *      d1 y^p + 1024 \Sum y^n + d3 y^0		(Step 2)
+ *                     n=1
+ */
+static __always_inline u32
+accumulate_sum(u64 delta, int cpu, struct sched_avg *sa,
+	       unsigned long load, unsigned long runnable, int running)
+{
+	unsigned long scale_freq, scale_cpu;
+	u32 contrib = (u32)delta; /* p == 0 -> delta < 1024 */
+	u64 periods;
+
+	scale_freq = arch_scale_freq_capacity(cpu);
+	scale_cpu = arch_scale_cpu_capacity(NULL, cpu);
+
+	delta += sa->period_contrib;
+	periods = delta / 1024; /* A period is 1024us (~1ms) */
+
+	/*
+	 * Step 1: decay old *_sum if we crossed period boundaries.
+	 */
+	if (periods) {
+		sa->load_sum = decay_load(sa->load_sum, periods);
+		sa->runnable_load_sum =
+			decay_load(sa->runnable_load_sum, periods);
+		sa->util_sum = decay_load((u64)(sa->util_sum), periods);
+
+		/*
+		 * Step 2
+		 */
+		delta %= 1024;
+		contrib = __accumulate_pelt_segments(periods,
+				1024 - sa->period_contrib, delta);
+	}
+	sa->period_contrib = delta;
+
+	contrib = cap_scale(contrib, scale_freq);
+	if (load)
+		sa->load_sum += load * contrib;
+	if (runnable)
+		sa->runnable_load_sum += runnable * contrib;
+	if (running)
+		sa->util_sum += contrib * scale_cpu;
+
+	return periods;
+}
+
+/*
+ * We can represent the historical contribution to runnable average as the
+ * coefficients of a geometric series.  To do this we sub-divide our runnable
+ * history into segments of approximately 1ms (1024us); label the segment that
+ * occurred N-ms ago p_N, with p_0 corresponding to the current period, e.g.
+ *
+ * [<- 1024us ->|<- 1024us ->|<- 1024us ->| ...
+ *      p0            p1           p2
+ *     (now)       (~1ms ago)  (~2ms ago)
+ *
+ * Let u_i denote the fraction of p_i that the entity was runnable.
+ *
+ * We then designate the fractions u_i as our co-efficients, yielding the
+ * following representation of historical load:
+ *   u_0 + u_1*y + u_2*y^2 + u_3*y^3 + ...
+ *
+ * We choose y based on the with of a reasonably scheduling period, fixing:
+ *   y^32 = 0.5
+ *
+ * This means that the contribution to load ~32ms ago (u_32) will be weighted
+ * approximately half as much as the contribution to load within the last ms
+ * (u_0).
+ *
+ * When a period "rolls over" and we have new u_0`, multiplying the previous
+ * sum again by y is sufficient to update:
+ *   load_avg = u_0` + y*(u_0 + u_1*y + u_2*y^2 + ... )
+ *            = u_0 + u_1*y + u_2*y^2 + ... [re-labeling u_i --> u_{i+1}]
+ */
+static __always_inline int
+___update_load_sum(u64 now, int cpu, struct sched_avg *sa,
+		  unsigned long load, unsigned long runnable, int running)
+{
+	u64 delta;
+
+	delta = now - sa->last_update_time;
+	/*
+	 * This should only happen when time goes backwards, which it
+	 * unfortunately does during sched clock init when we swap over to TSC.
+	 */
+	if ((s64)delta < 0) {
+		sa->last_update_time = now;
+		return 0;
+	}
+
+	/*
+	 * Use 1024ns as the unit of measurement since it's a reasonable
+	 * approximation of 1us and fast to compute.
+	 */
+	delta >>= 10;
+	if (!delta)
+		return 0;
+
+	sa->last_update_time += delta << 10;
+
+	/*
+	 * running is a subset of runnable (weight) so running can't be set if
+	 * runnable is clear. But there are some corner cases where the current
+	 * se has been already dequeued but cfs_rq->curr still points to it.
+	 * This means that weight will be 0 but not running for a sched_entity
+	 * but also for a cfs_rq if the latter becomes idle. As an example,
+	 * this happens during idle_balance() which calls
+	 * update_blocked_averages()
+	 */
+	if (!load)
+		runnable = running = 0;
+
+	/*
+	 * Now we know we crossed measurement unit boundaries. The *_avg
+	 * accrues by two steps:
+	 *
+	 * Step 1: accumulate *_sum since last_update_time. If we haven't
+	 * crossed period boundaries, finish.
+	 */
+	if (!accumulate_sum(delta, cpu, sa, load, runnable, running))
+		return 0;
+
+	return 1;
+}
+
+static __always_inline void
+___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runnable)
+{
+	u32 divider = LOAD_AVG_MAX - 1024 + sa->period_contrib;
+
+	/*
+	 * Step 2: update *_avg.
+	 */
+	sa->load_avg = div_u64(load * sa->load_sum, divider);
+	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
+	sa->util_avg = sa->util_sum / divider;
+}
+
+/*
+ * sched_entity:
+ *
+ *   task:
+ *     se_runnable() == se_weight()
+ *
+ *   group: [ see update_cfs_group() ]
+ *     se_weight()   = tg->weight * grq->load_avg / tg->load_avg
+ *     se_runnable() = se_weight(se) * grq->runnable_load_avg / grq->load_avg
+ *
+ *   load_sum := runnable_sum
+ *   load_avg = se_weight(se) * runnable_avg
+ *
+ *   runnable_load_sum := runnable_sum
+ *   runnable_load_avg = se_runnable(se) * runnable_avg
+ *
+ * XXX collapse load_sum and runnable_load_sum
+ *
+ * cfq_rq:
+ *
+ *   load_sum = \Sum se_weight(se) * se->avg.load_sum
+ *   load_avg = \Sum se->avg.load_avg
+ *
+ *   runnable_load_sum = \Sum se_runnable(se) * se->avg.runnable_load_sum
+ *   runnable_load_avg = \Sum se->avg.runable_load_avg
+ */
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, 0, 0, 0)) {
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		return 1;
+	}
+
+	return 0;
+}
+
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+	if (entity_is_task(se))
+		se->runnable_weight = se->load.weight;
+
+	if (___update_load_sum(now, cpu, &se->avg, !!se->on_rq, !!se->on_rq,
+				cfs_rq->curr == se)) {
+
+		___update_load_avg(&se->avg, se_weight(se), se_runnable(se));
+		cfs_se_util_change(&se->avg);
+		return 1;
+	}
+
+	return 0;
+}
+
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
+{
+	if (___update_load_sum(now, cpu, &cfs_rq->avg,
+				scale_load_down(cfs_rq->load.weight),
+				scale_load_down(cfs_rq->runnable_weight),
+				cfs_rq->curr != NULL)) {
+
+		___update_load_avg(&cfs_rq->avg, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
new file mode 100644
index 000000000000..9cac73efd64a
--- /dev/null
+++ b/kernel/sched/pelt.h
@@ -0,0 +1,43 @@
+#ifdef CONFIG_SMP
+
+int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
+int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
+int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
+
+/*
+ * When a task is dequeued, its estimated utilization should not be update if
+ * its util_avg has not been updated at least once.
+ * This flag is used to synchronize util_avg updates with util_est updates.
+ * We map this information into the LSB bit of the utilization saved at
+ * dequeue time (i.e. util_est.dequeued).
+ */
+#define UTIL_AVG_UNCHANGED 0x1
+
+static inline void cfs_se_util_change(struct sched_avg *avg)
+{
+	unsigned int enqueued;
+
+	if (!sched_feat(UTIL_EST))
+		return;
+
+	/* Avoid store if the flag has been already set */
+	enqueued = avg->util_est.enqueued;
+	if (!(enqueued & UTIL_AVG_UNCHANGED))
+		return;
+
+	/* Reset flag to report util_avg has been updated */
+	enqueued &= ~UTIL_AVG_UNCHANGED;
+	WRITE_ONCE(avg->util_est.enqueued, enqueued);
+}
+
+#else
+
+static inline int
+update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+{
+	return 0;
+}
+
+#endif
+
+
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c7742dcc136c..00d6f2594c4e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -673,7 +673,26 @@ struct dl_rq {
 	u64			bw_ratio;
 };
 
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* An entity is a task if it doesn't "own" a runqueue */
+#define entity_is_task(se)	(!se->my_q)
+#else
+#define entity_is_task(se)	1
+#endif
+
 #ifdef CONFIG_SMP
+/*
+ * XXX we want to get rid of these helpers and use the full load resolution.
+ */
+static inline long se_weight(struct sched_entity *se)
+{
+	return scale_load_down(se->load.weight);
+}
+
+static inline long se_runnable(struct sched_entity *se)
+{
+	return scale_load_down(se->runnable_weight);
+}
 
 static inline bool sched_asym_prefer(int a, int b)
 {
-- 
cgit v1.2.3


From 371bf42732694d142b0de026e152266c039b97d3 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:05 +0200
Subject: sched/rt: Add rt_rq utilization tracking

schedutil governor relies on cfs_rq's util_avg to choose the OPP when CFS
tasks are running. When the CPU is overloaded by CFS and RT tasks, CFS tasks
are preempted by RT tasks and in this case util_avg reflects the remaining
capacity but not what CFS want to use. In such case, schedutil can select a
lower OPP whereas the CPU is overloaded. In order to have a more accurate
view of the utilization of the CPU, we track the utilization of RT tasks.
Only util_avg is correctly tracked but not load_avg and runnable_load_avg
which are useless for rt_rq.

rt_rq uses rq_clock_task and cfs_rq uses cfs_rq_clock_task but they are
the same at the root group level, so the PELT windows of the util_sum are
aligned.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-3-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c  | 15 ++++++++++++++-
 kernel/sched/pelt.c  | 25 +++++++++++++++++++++++++
 kernel/sched/pelt.h  |  7 +++++++
 kernel/sched/rt.c    | 13 +++++++++++++
 kernel/sched/sched.h |  7 +++++++
 5 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 39ab46cea6c5..5b453213cd18 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7290,6 +7290,14 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 	return false;
 }
 
+static inline bool rt_rq_has_blocked(struct rq *rq)
+{
+	if (READ_ONCE(rq->avg_rt.util_avg))
+		return true;
+
+	return false;
+}
+
 #ifdef CONFIG_FAIR_GROUP_SCHED
 
 static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7349,6 +7357,10 @@ static void update_blocked_averages(int cpu)
 		if (cfs_rq_has_blocked(cfs_rq))
 			done = false;
 	}
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+	/* Don't need periodic decay once load/util_avg are null */
+	if (rt_rq_has_blocked(rq))
+		done = false;
 
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
@@ -7414,9 +7426,10 @@ static inline void update_blocked_averages(int cpu)
 	rq_lock_irqsave(rq, &rf);
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
-	if (!cfs_rq_has_blocked(cfs_rq))
+	if (!cfs_rq_has_blocked(cfs_rq) && !rt_rq_has_blocked(rq))
 		rq->has_blocked_load = 0;
 #endif
 	rq_unlock_irqrestore(rq, &rf);
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index e6ecbb2b8698..a00b1ba3dd5b 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -309,3 +309,28 @@ int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq)
 
 	return 0;
 }
+
+/*
+ * rt_rq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ *   load_avg and runnable_load_avg are not supported and meaningless.
+ *
+ */
+
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	if (___update_load_sum(now, rq->cpu, &rq->avg_rt,
+				running,
+				running,
+				running)) {
+
+		___update_load_avg(&rq->avg_rt, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 9cac73efd64a..b2983b741d57 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -3,6 +3,7 @@
 int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
 int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
 int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
+int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 
 /*
  * When a task is dequeued, its estimated utilization should not be update if
@@ -38,6 +39,12 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
 	return 0;
 }
 
+static inline int
+update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
+
 #endif
 
 
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 572567078b60..0dc8ad1915e6 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -5,6 +5,8 @@
  */
 #include "sched.h"
 
+#include "pelt.h"
+
 int sched_rr_timeslice = RR_TIMESLICE;
 int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
 
@@ -1576,6 +1578,14 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	rt_queue_push_tasks(rq);
 
+	/*
+	 * If prev task was rt, put_prev_task() has already updated the
+	 * utilization. We only care of the case where we start to schedule a
+	 * rt task
+	 */
+	if (rq->curr->sched_class != &rt_sched_class)
+		update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1583,6 +1593,8 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
 {
 	update_curr_rt(rq);
 
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
+
 	/*
 	 * The previous task needs to be made eligible for pushing
 	 * if it is still active
@@ -2312,6 +2324,7 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	struct sched_rt_entity *rt_se = &p->rt;
 
 	update_curr_rt(rq);
+	update_rt_rq_load_avg(rq_clock_task(rq), rq, 1);
 
 	watchdog(rq, p);
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 00d6f2594c4e..405dd9ba6b39 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -594,6 +594,7 @@ struct rt_rq {
 	unsigned long		rt_nr_total;
 	int			overloaded;
 	struct plist_head	pushable_tasks;
+
 #endif /* CONFIG_SMP */
 	int			rt_queued;
 
@@ -854,6 +855,7 @@ struct rq {
 
 	u64			rt_avg;
 	u64			age_stamp;
+	struct sched_avg	avg_rt;
 	u64			idle_stamp;
 	u64			avg_idle;
 
@@ -2212,4 +2214,9 @@ static inline unsigned long cpu_util_cfs(struct rq *rq)
 
 	return util;
 }
+
+static inline unsigned long cpu_util_rt(struct rq *rq)
+{
+	return rq->avg_rt.util_avg;
+}
 #endif
-- 
cgit v1.2.3


From 3ae117c6cd7c4783819a0766aa97b9493a8a0f62 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:06 +0200
Subject: cpufreq/schedutil: Use RT utilization tracking

Add both CFS and RT utilization when selecting an OPP for CFS tasks as RT
can preempt and steal CFS's running time.

RT util_avg is used to take into account the utilization of RT tasks
on the CPU when selecting OPP. If a RT task migrate, the RT utilization
will not migrate but will decay over time. On an overloaded CPU, CFS
utilization reflects the remaining utilization avialable on CPU. When RT
task migrates, the CFS utilization will increase when tasks will start to
use the newly available capacity. At the same pace, RT utilization will
decay and both variations will compensate each other to keep unchanged
overall utilization and will prevent any OPP drop.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Link: http://lkml.kernel.org/r/1530200714-4504-4-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cpufreq_schedutil.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c907fde01eaa..da29b5a33adb 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -56,6 +56,7 @@ struct sugov_cpu {
 	/* The fields below are only needed when sharing a policy: */
 	unsigned long		util_cfs;
 	unsigned long		util_dl;
+	unsigned long		util_rt;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -186,15 +187,21 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
 	sg_cpu->util_cfs = cpu_util_cfs(rq);
 	sg_cpu->util_dl  = cpu_util_dl(rq);
+	sg_cpu->util_rt  = cpu_util_rt(rq);
 }
 
 static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util;
 
 	if (rt_rq_is_runnable(&rq->rt))
 		return sg_cpu->max;
 
+	util = sg_cpu->util_dl;
+	util += sg_cpu->util_cfs;
+	util += sg_cpu->util_rt;
+
 	/*
 	 * Utilization required by DEADLINE must always be granted while, for
 	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
@@ -205,7 +212,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
 	 * ready for such an interface. So, we only do the latter for now.
 	 */
-	return min(sg_cpu->max, (sg_cpu->util_dl + sg_cpu->util_cfs));
+	return min(sg_cpu->max, util);
 }
 
 /**
-- 
cgit v1.2.3


From 3727e0e16340cbdf83818f5bf0113505c6876057 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:07 +0200
Subject: sched/dl: Add dl_rq utilization tracking

Similarly to what happens with RT tasks, CFS tasks can be preempted by DL
tasks and the CFS's utilization might no longer describes the real
utilization level.

Current DL bandwidth reflects the requirements to meet deadline when tasks are
enqueued but not the current utilization of the DL sched class. We track
DL class utilization to estimate the system utilization.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-5-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/deadline.c |  6 ++++++
 kernel/sched/fair.c     | 11 ++++++++---
 kernel/sched/pelt.c     | 23 +++++++++++++++++++++++
 kernel/sched/pelt.h     |  6 ++++++
 kernel/sched/sched.h    |  1 +
 5 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fbfc3f1d368a..f4de26982d80 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -16,6 +16,7 @@
  *                    Fabio Checconi <fchecconi@gmail.com>
  */
 #include "sched.h"
+#include "pelt.h"
 
 struct dl_bandwidth def_dl_bandwidth;
 
@@ -1761,6 +1762,9 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	deadline_queue_push_tasks(rq);
 
+	if (rq->curr->sched_class != &dl_sched_class)
+		update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+
 	return p;
 }
 
@@ -1768,6 +1772,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1)
 		enqueue_pushable_dl_task(rq, p);
 }
@@ -1784,6 +1789,7 @@ static void task_tick_dl(struct rq *rq, struct task_struct *p, int queued)
 {
 	update_curr_dl(rq);
 
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 1);
 	/*
 	 * Even when we have runtime, update_curr_dl() might have resulted in us
 	 * not being the leftmost task anymore. In that case NEED_RESCHED will
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5b453213cd18..f096275c7df2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7290,11 +7290,14 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 	return false;
 }
 
-static inline bool rt_rq_has_blocked(struct rq *rq)
+static inline bool others_rqs_have_blocked(struct rq *rq)
 {
 	if (READ_ONCE(rq->avg_rt.util_avg))
 		return true;
 
+	if (READ_ONCE(rq->avg_dl.util_avg))
+		return true;
+
 	return false;
 }
 
@@ -7358,8 +7361,9 @@ static void update_blocked_averages(int cpu)
 			done = false;
 	}
 	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
 	/* Don't need periodic decay once load/util_avg are null */
-	if (rt_rq_has_blocked(rq))
+	if (others_rqs_have_blocked(rq))
 		done = false;
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -7427,9 +7431,10 @@ static inline void update_blocked_averages(int cpu)
 	update_rq_clock(rq);
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
 	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
-	if (!cfs_rq_has_blocked(cfs_rq) && !rt_rq_has_blocked(rq))
+	if (!cfs_rq_has_blocked(cfs_rq) && !others_rqs_have_blocked(rq))
 		rq->has_blocked_load = 0;
 #endif
 	rq_unlock_irqrestore(rq, &rf);
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a00b1ba3dd5b..8b78b6320cda 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -334,3 +334,26 @@ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
 
 	return 0;
 }
+
+/*
+ * dl_rq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ */
+
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	if (___update_load_sum(now, rq->cpu, &rq->avg_dl,
+				running,
+				running,
+				running)) {
+
+		___update_load_avg(&rq->avg_dl, 1, 1);
+		return 1;
+	}
+
+	return 0;
+}
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index b2983b741d57..0e4f912461ad 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -4,6 +4,7 @@ int __update_load_avg_blocked_se(u64 now, int cpu, struct sched_entity *se);
 int __update_load_avg_se(u64 now, int cpu, struct cfs_rq *cfs_rq, struct sched_entity *se);
 int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
 
 /*
  * When a task is dequeued, its estimated utilization should not be update if
@@ -45,6 +46,11 @@ update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
 	return 0;
 }
 
+static inline int
+update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+{
+	return 0;
+}
 #endif
 
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 405dd9ba6b39..ab8b5296b5f6 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -856,6 +856,7 @@ struct rq {
 	u64			rt_avg;
 	u64			age_stamp;
 	struct sched_avg	avg_rt;
+	struct sched_avg	avg_dl;
 	u64			idle_stamp;
 	u64			avg_idle;
 
-- 
cgit v1.2.3


From 8cc90515a4fa419ccfc4703ff127699cdcb96839 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:08 +0200
Subject: cpufreq/schedutil: Use DL utilization tracking

Now that we have both the DL class bandwidth requirement and the DL class
utilization, we can detect when CPU is fully used so we should run at max.
Otherwise, we keep using the DL bandwidth requirement to define the
utilization of the CPU.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Link: http://lkml.kernel.org/r/1530200714-4504-6-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cpufreq_schedutil.c | 23 +++++++++++++++++------
 kernel/sched/sched.h             |  7 ++++++-
 2 files changed, 23 insertions(+), 7 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index da29b5a33adb..07760bc7f69a 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -56,6 +56,7 @@ struct sugov_cpu {
 	/* The fields below are only needed when sharing a policy: */
 	unsigned long		util_cfs;
 	unsigned long		util_dl;
+	unsigned long		bw_dl;
 	unsigned long		util_rt;
 	unsigned long		max;
 
@@ -187,6 +188,7 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
 	sg_cpu->util_cfs = cpu_util_cfs(rq);
 	sg_cpu->util_dl  = cpu_util_dl(rq);
+	sg_cpu->bw_dl    = cpu_bw_dl(rq);
 	sg_cpu->util_rt  = cpu_util_rt(rq);
 }
 
@@ -198,20 +200,29 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 	if (rt_rq_is_runnable(&rq->rt))
 		return sg_cpu->max;
 
-	util = sg_cpu->util_dl;
-	util += sg_cpu->util_cfs;
+	util = sg_cpu->util_cfs;
 	util += sg_cpu->util_rt;
 
+	if ((util + sg_cpu->util_dl) >= sg_cpu->max)
+		return sg_cpu->max;
+
 	/*
-	 * Utilization required by DEADLINE must always be granted while, for
-	 * FAIR, we use blocked utilization of IDLE CPUs as a mechanism to
-	 * gracefully reduce the frequency when no tasks show up for longer
+	 * As there is still idle time on the CPU, we need to compute the
+	 * utilization level of the CPU.
+	 *
+	 * Bandwidth required by DEADLINE must always be granted while, for
+	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
+	 * to gracefully reduce the frequency when no tasks show up for longer
 	 * periods of time.
 	 *
 	 * Ideally we would like to set util_dl as min/guaranteed freq and
 	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
 	 * ready for such an interface. So, we only do the latter for now.
 	 */
+
+	/* Add DL bandwidth requirement */
+	util += sg_cpu->bw_dl;
+
 	return min(sg_cpu->max, util);
 }
 
@@ -367,7 +378,7 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
  */
 static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
 {
-	if (cpu_util_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->util_dl)
+	if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
 		sg_policy->need_freq_update = true;
 }
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ab8b5296b5f6..9028f268f867 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2199,11 +2199,16 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
-static inline unsigned long cpu_util_dl(struct rq *rq)
+static inline unsigned long cpu_bw_dl(struct rq *rq)
 {
 	return (rq->dl.running_bw * SCHED_CAPACITY_SCALE) >> BW_SHIFT;
 }
 
+static inline unsigned long cpu_util_dl(struct rq *rq)
+{
+	return READ_ONCE(rq->avg_dl.util_avg);
+}
+
 static inline unsigned long cpu_util_cfs(struct rq *rq)
 {
 	unsigned long util = READ_ONCE(rq->cfs.avg.util_avg);
-- 
cgit v1.2.3


From 91c27493e78df6849baaa21a9d66e26de8b875c0 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:09 +0200
Subject: sched/irq: Add IRQ utilization tracking

interrupt and steal time are the only remaining activities tracked by
rt_avg. Like for sched classes, we can use PELT to track their average
utilization of the CPU. But unlike sched class, we don't track when
entering/leaving interrupt; Instead, we take into account the time spent
under interrupt context when we update rqs' clock (rq_clock_task).
This also means that we have to decay the normal context time and account
for interrupt time during the update.

That's also important to note that because:

  rq_clock == rq_clock_task + interrupt time

and rq_clock_task is used by a sched class to compute its utilization, the
util_avg of a sched class only reflects the utilization of the time spent
in normal context and not of the whole time of the CPU. The utilization of
interrupt gives an more accurate level of utilization of CPU.

The CPU utilization is:

  avg_irq + (1 - avg_irq / max capacity) * /Sum avg_rq

Most of the time, avg_irq is small and neglictible so the use of the
approximation CPU utilization = /Sum avg_rq was enough.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-7-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  |  4 +++-
 kernel/sched/fair.c  | 13 ++++++++++---
 kernel/sched/pelt.c  | 40 ++++++++++++++++++++++++++++++++++++++++
 kernel/sched/pelt.h  | 16 ++++++++++++++++
 kernel/sched/sched.h |  3 +++
 5 files changed, 72 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe365c9a08e9..38107a95baca 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -17,6 +17,8 @@
 #include "../workqueue_internal.h"
 #include "../smpboot.h"
 
+#include "pelt.h"
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/sched.h>
 
@@ -185,7 +187,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
-		sched_rt_avg_update(rq, irq_delta + steal);
+		update_irq_load_avg(rq, irq_delta + steal);
 #endif
 }
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f096275c7df2..c2782b29c79f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7290,7 +7290,7 @@ static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
 	return false;
 }
 
-static inline bool others_rqs_have_blocked(struct rq *rq)
+static inline bool others_have_blocked(struct rq *rq)
 {
 	if (READ_ONCE(rq->avg_rt.util_avg))
 		return true;
@@ -7298,6 +7298,11 @@ static inline bool others_rqs_have_blocked(struct rq *rq)
 	if (READ_ONCE(rq->avg_dl.util_avg))
 		return true;
 
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	if (READ_ONCE(rq->avg_irq.util_avg))
+		return true;
+#endif
+
 	return false;
 }
 
@@ -7362,8 +7367,9 @@ static void update_blocked_averages(int cpu)
 	}
 	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
 	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_irq_load_avg(rq, 0);
 	/* Don't need periodic decay once load/util_avg are null */
-	if (others_rqs_have_blocked(rq))
+	if (others_have_blocked(rq))
 		done = false;
 
 #ifdef CONFIG_NO_HZ_COMMON
@@ -7432,9 +7438,10 @@ static inline void update_blocked_averages(int cpu)
 	update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq);
 	update_rt_rq_load_avg(rq_clock_task(rq), rq, 0);
 	update_dl_rq_load_avg(rq_clock_task(rq), rq, 0);
+	update_irq_load_avg(rq, 0);
 #ifdef CONFIG_NO_HZ_COMMON
 	rq->last_blocked_load_update_tick = jiffies;
-	if (!cfs_rq_has_blocked(cfs_rq) && !others_rqs_have_blocked(rq))
+	if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
 		rq->has_blocked_load = 0;
 #endif
 	rq_unlock_irqrestore(rq, &rf);
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index 8b78b6320cda..ead6d8b4a8b8 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -357,3 +357,43 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 
 	return 0;
 }
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+/*
+ * irq:
+ *
+ *   util_sum = \Sum se->avg.util_sum but se->avg.util_sum is not tracked
+ *   util_sum = cpu_scale * load_sum
+ *   runnable_load_sum = load_sum
+ *
+ */
+
+int update_irq_load_avg(struct rq *rq, u64 running)
+{
+	int ret = 0;
+	/*
+	 * We know the time that has been used by interrupt since last update
+	 * but we don't when. Let be pessimistic and assume that interrupt has
+	 * happened just before the update. This is not so far from reality
+	 * because interrupt will most probably wake up task and trig an update
+	 * of rq clock during which the metric si updated.
+	 * We start to decay with normal context time and then we add the
+	 * interrupt context time.
+	 * We can safely remove running from rq->clock because
+	 * rq->clock += delta with delta >= running
+	 */
+	ret = ___update_load_sum(rq->clock - running, rq->cpu, &rq->avg_irq,
+				0,
+				0,
+				0);
+	ret += ___update_load_sum(rq->clock, rq->cpu, &rq->avg_irq,
+				1,
+				1,
+				1);
+
+	if (ret)
+		___update_load_avg(&rq->avg_irq, 1, 1);
+
+	return ret;
+}
+#endif
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index 0e4f912461ad..d2894db28955 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -6,6 +6,16 @@ int __update_load_avg_cfs_rq(u64 now, int cpu, struct cfs_rq *cfs_rq);
 int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
 int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
 
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+int update_irq_load_avg(struct rq *rq, u64 running);
+#else
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
+#endif
+
 /*
  * When a task is dequeued, its estimated utilization should not be update if
  * its util_avg has not been updated at least once.
@@ -51,6 +61,12 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
 {
 	return 0;
 }
+
+static inline int
+update_irq_load_avg(struct rq *rq, u64 running)
+{
+	return 0;
+}
 #endif
 
 
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9028f268f867..b26d0c9948dd 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -857,6 +857,9 @@ struct rq {
 	u64			age_stamp;
 	struct sched_avg	avg_rt;
 	struct sched_avg	avg_dl;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	struct sched_avg	avg_irq;
+#endif
 	u64			idle_stamp;
 	u64			avg_idle;
 
-- 
cgit v1.2.3


From 9033ea11889f88f243445495f72441e22256d5e9 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:10 +0200
Subject: cpufreq/schedutil: Take time spent in interrupts into account

The time spent executing IRQ handlers can be significant but it is not reflected
in the utilization of CPU when deciding to choose an OPP. Now that we have
access to this metric, schedutil can take it into account when selecting
the OPP for a CPU.

RQS utilization don't see the time spend under interrupt context and report
their value in the normal context time window. We need to compensate this when
adding interrupt utilization

The CPU utilization is:

  IRQ util_avg + (1 - IRQ util_avg / max capacity ) * /Sum rq util_avg

A test with iperf on hikey (octo arm64) gives the following speedup:

 iperf -c server_address -r -t 5

 w/o patch		w/ patch
 Tx 276 Mbits/sec	304 Mbits/sec +10%
 Rx 299 Mbits/sec	328 Mbits/sec  +9%

 8 iterations
 stdev is lower than 1%

Only WFI idle state is enabled (shallowest idle state).

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Link: http://lkml.kernel.org/r/1530200714-4504-8-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cpufreq_schedutil.c | 25 +++++++++++++++++++++----
 kernel/sched/sched.h             | 13 +++++++++++++
 2 files changed, 34 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 07760bc7f69a..7016bde9d194 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -58,6 +58,7 @@ struct sugov_cpu {
 	unsigned long		util_dl;
 	unsigned long		bw_dl;
 	unsigned long		util_rt;
+	unsigned long		util_irq;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -190,21 +191,30 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
 	sg_cpu->util_dl  = cpu_util_dl(rq);
 	sg_cpu->bw_dl    = cpu_bw_dl(rq);
 	sg_cpu->util_rt  = cpu_util_rt(rq);
+	sg_cpu->util_irq = cpu_util_irq(rq);
 }
 
 static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util;
+	unsigned long util, max = sg_cpu->max;
 
 	if (rt_rq_is_runnable(&rq->rt))
 		return sg_cpu->max;
 
+	if (unlikely(sg_cpu->util_irq >= max))
+		return max;
+
+	/* Sum rq utilization */
 	util = sg_cpu->util_cfs;
 	util += sg_cpu->util_rt;
 
-	if ((util + sg_cpu->util_dl) >= sg_cpu->max)
-		return sg_cpu->max;
+	/*
+	 * Interrupt time is not seen by RQS utilization so we can compare
+	 * them with the CPU capacity
+	 */
+	if ((util + sg_cpu->util_dl) >= max)
+		return max;
 
 	/*
 	 * As there is still idle time on the CPU, we need to compute the
@@ -220,10 +230,17 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 	 * ready for such an interface. So, we only do the latter for now.
 	 */
 
+	/* Weight RQS utilization to normal context window */
+	util *= (max - sg_cpu->util_irq);
+	util /= max;
+
+	/* Add interrupt utilization */
+	util += sg_cpu->util_irq;
+
 	/* Add DL bandwidth requirement */
 	util += sg_cpu->bw_dl;
 
-	return min(sg_cpu->max, util);
+	return min(max, util);
 }
 
 /**
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b26d0c9948dd..b2833e2b4b6a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2228,4 +2228,17 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 {
 	return rq->avg_rt.util_avg;
 }
+
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return rq->avg_irq.util_avg;
+}
+#else
+static inline unsigned long cpu_util_irq(struct rq *rq)
+{
+	return 0;
+}
+
+#endif
 #endif
-- 
cgit v1.2.3


From dfa444dc2ff62edbaf1ff95ed22dd2ce8a5715da Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:11 +0200
Subject: sched/cpufreq: Remove sugov_aggregate_util()

There is no reason why sugov_get_util() and sugov_aggregate_util()
were in fact separate functions.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
[ Rebased after adding irq tracking and fixed some compilation errors. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Link: http://lkml.kernel.org/r/1530200714-4504-9-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cpufreq_schedutil.c | 44 ++++++++++++++--------------------------
 kernel/sched/sched.h             |  2 +-
 2 files changed, 16 insertions(+), 30 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 7016bde9d194..c9622b3f183d 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -53,12 +53,7 @@ struct sugov_cpu {
 	unsigned int		iowait_boost_max;
 	u64			last_update;
 
-	/* The fields below are only needed when sharing a policy: */
-	unsigned long		util_cfs;
-	unsigned long		util_dl;
 	unsigned long		bw_dl;
-	unsigned long		util_rt;
-	unsigned long		util_irq;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -182,38 +177,31 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
-static void sugov_get_util(struct sugov_cpu *sg_cpu)
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
+	unsigned long util, irq, max;
 
-	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
-	sg_cpu->util_cfs = cpu_util_cfs(rq);
-	sg_cpu->util_dl  = cpu_util_dl(rq);
-	sg_cpu->bw_dl    = cpu_bw_dl(rq);
-	sg_cpu->util_rt  = cpu_util_rt(rq);
-	sg_cpu->util_irq = cpu_util_irq(rq);
-}
-
-static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
-{
-	struct rq *rq = cpu_rq(sg_cpu->cpu);
-	unsigned long util, max = sg_cpu->max;
+	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
+	sg_cpu->bw_dl = cpu_bw_dl(rq);
 
 	if (rt_rq_is_runnable(&rq->rt))
-		return sg_cpu->max;
+		return max;
+
+	irq = cpu_util_irq(rq);
 
-	if (unlikely(sg_cpu->util_irq >= max))
+	if (unlikely(irq >= max))
 		return max;
 
 	/* Sum rq utilization */
-	util = sg_cpu->util_cfs;
-	util += sg_cpu->util_rt;
+	util = cpu_util_cfs(rq);
+	util += cpu_util_rt(rq);
 
 	/*
 	 * Interrupt time is not seen by RQS utilization so we can compare
 	 * them with the CPU capacity
 	 */
-	if ((util + sg_cpu->util_dl) >= max)
+	if ((util + cpu_util_dl(rq)) >= max)
 		return max;
 
 	/*
@@ -231,11 +219,11 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
 	 */
 
 	/* Weight RQS utilization to normal context window */
-	util *= (max - sg_cpu->util_irq);
+	util *= (max - irq);
 	util /= max;
 
 	/* Add interrupt utilization */
-	util += sg_cpu->util_irq;
+	util += irq;
 
 	/* Add DL bandwidth requirement */
 	util += sg_cpu->bw_dl;
@@ -418,9 +406,8 @@ static void sugov_update_single(struct update_util_data *hook, u64 time,
 
 	busy = sugov_cpu_is_busy(sg_cpu);
 
-	sugov_get_util(sg_cpu);
+	util = sugov_get_util(sg_cpu);
 	max = sg_cpu->max;
-	util = sugov_aggregate_util(sg_cpu);
 	sugov_iowait_apply(sg_cpu, time, &util, &max);
 	next_f = get_next_freq(sg_policy, util, max);
 	/*
@@ -459,9 +446,8 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
 		struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
 		unsigned long j_util, j_max;
 
-		sugov_get_util(j_sg_cpu);
+		j_util = sugov_get_util(j_sg_cpu);
 		j_max = j_sg_cpu->max;
-		j_util = sugov_aggregate_util(j_sg_cpu);
 		sugov_iowait_apply(j_sg_cpu, time, &j_util, &j_max);
 
 		if (j_util * max > j_max * util) {
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b2833e2b4b6a..061d51fb5b44 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2226,7 +2226,7 @@ static inline unsigned long cpu_util_cfs(struct rq *rq)
 
 static inline unsigned long cpu_util_rt(struct rq *rq)
 {
-	return rq->avg_rt.util_avg;
+	return READ_ONCE(rq->avg_rt.util_avg);
 }
 
 #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-- 
cgit v1.2.3


From 523e979d31648112bad07f427c183525c0258c75 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:12 +0200
Subject: sched/core: Use PELT for scale_rt_capacity()

The utilization of the CPU by RT, DL and IRQs are now tracked with
PELT so we can use these metrics instead of rt_avg to evaluate the remaining
capacity available for CFS class.

scale_rt_capacity() behavior has been changed and now returns the remaining
capacity available for CFS instead of a scaling factor because RT, DL and
IRQ provide now absolute utilization value.

The same formula as schedutil is used:

  IRQ util_avg + (1 - IRQ util_avg / max capacity ) * /Sum rq util_avg

but the implementation is different because it doesn't return the same value
and doesn't benefit of the same optimization.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-10-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/deadline.c |  2 --
 kernel/sched/fair.c     | 44 ++++++++++++++++++++++----------------------
 kernel/sched/pelt.c     |  2 +-
 kernel/sched/rt.c       |  2 --
 4 files changed, 23 insertions(+), 27 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f4de26982d80..68b8a9f1c9ca 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1180,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c2782b29c79f..d265fa9756a2 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7551,39 +7551,39 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, used, age_stamp, avg;
-	s64 delta;
-
-	/*
-	 * Since we're reading these variables without serialization make sure
-	 * we read them once before doing sanity checks on them.
-	 */
-	age_stamp = READ_ONCE(rq->age_stamp);
-	avg = READ_ONCE(rq->rt_avg);
-	delta = __rq_clock_broken(rq) - age_stamp;
+	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long used, free;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	unsigned long irq;
+#endif
 
-	if (unlikely(delta < 0))
-		delta = 0;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	irq = READ_ONCE(rq->avg_irq.util_avg);
 
-	total = sched_avg_period() + delta;
+	if (unlikely(irq >= max))
+		return 1;
+#endif
 
-	used = div_u64(avg, total);
+	used = READ_ONCE(rq->avg_rt.util_avg);
+	used += READ_ONCE(rq->avg_dl.util_avg);
 
-	if (likely(used < SCHED_CAPACITY_SCALE))
-		return SCHED_CAPACITY_SCALE - used;
+	if (unlikely(used >= max))
+		return 1;
 
-	return 1;
+	free = max - used;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	free *= (max - irq);
+	free /= max;
+#endif
+	return free;
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
-	cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
-	capacity *= scale_rt_capacity(cpu);
-	capacity >>= SCHED_CAPACITY_SHIFT;
+	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
 
 	if (!capacity)
 		capacity = 1;
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index ead6d8b4a8b8..35475c0c5419 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -237,7 +237,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna
 	 */
 	sa->load_avg = div_u64(load * sa->load_sum, divider);
 	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
-	sa->util_avg = sa->util_sum / divider;
+	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
 }
 
 /*
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0dc8ad1915e6..2df72abfa24a 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -973,8 +973,6 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
-- 
cgit v1.2.3


From bbb62c0b024a1c721232667fa1d625cf6b3a555b Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:13 +0200
Subject: sched/core: Remove the rt_avg code

rt_avg is not used anywhere anymore, so we can remove all related code.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-11-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  | 26 --------------------------
 kernel/sched/fair.c  |  2 --
 kernel/sched/sched.h | 17 -----------------
 3 files changed, 45 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 38107a95baca..a691b07390ab 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -651,23 +651,6 @@ bool sched_can_stop_tick(struct rq *rq)
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
-
-void sched_avg_update(struct rq *rq)
-{
-	s64 period = sched_avg_period();
-
-	while ((s64)(rq_clock(rq) - rq->age_stamp) > period) {
-		/*
-		 * Inline assembly required to prevent the compiler
-		 * optimising this loop into a divmod call.
-		 * See __iter_div_u64_rem() for another example of this.
-		 */
-		asm("" : "+rm" (rq->age_stamp));
-		rq->age_stamp += period;
-		rq->rt_avg /= 2;
-	}
-}
-
 #endif /* CONFIG_SMP */
 
 #if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
@@ -5716,13 +5699,6 @@ void set_rq_offline(struct rq *rq)
 	}
 }
 
-static void set_cpu_rq_start_time(unsigned int cpu)
-{
-	struct rq *rq = cpu_rq(cpu);
-
-	rq->age_stamp = sched_clock_cpu(cpu);
-}
-
 /*
  * used to mark begin/end of suspend/resume:
  */
@@ -5840,7 +5816,6 @@ static void sched_rq_cpu_starting(unsigned int cpu)
 
 int sched_cpu_starting(unsigned int cpu)
 {
-	set_cpu_rq_start_time(cpu);
 	sched_rq_cpu_starting(cpu);
 	sched_tick_start(cpu);
 	return 0;
@@ -6108,7 +6083,6 @@ void __init sched_init(void)
 
 #ifdef CONFIG_SMP
 	idle_thread_set_boot_cpu();
-	set_cpu_rq_start_time(smp_processor_id());
 #endif
 	init_sched_fair_class();
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d265fa9756a2..d5f7d521e448 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5323,8 +5323,6 @@ static void cpu_load_update(struct rq *this_rq, unsigned long this_load,
 
 		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
 	}
-
-	sched_avg_update(this_rq);
 }
 
 /* Used instead of source_load when we know the type == 0 */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 061d51fb5b44..14aac2d2de80 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -853,8 +853,6 @@ struct rq {
 
 	struct list_head cfs_tasks;
 
-	u64			rt_avg;
-	u64			age_stamp;
 	struct sched_avg	avg_rt;
 	struct sched_avg	avg_dl;
 #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
@@ -1719,11 +1717,6 @@ extern const_debug unsigned int sysctl_sched_time_avg;
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
-static inline u64 sched_avg_period(void)
-{
-	return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2;
-}
-
 #ifdef CONFIG_SCHED_HRTICK
 
 /*
@@ -1760,8 +1753,6 @@ unsigned long arch_scale_freq_capacity(int cpu)
 #endif
 
 #ifdef CONFIG_SMP
-extern void sched_avg_update(struct rq *rq);
-
 #ifndef arch_scale_cpu_capacity
 static __always_inline
 unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
@@ -1772,12 +1763,6 @@ unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
-{
-	rq->rt_avg += rt_delta * arch_scale_freq_capacity(cpu_of(rq));
-	sched_avg_update(rq);
-}
 #else
 #ifndef arch_scale_cpu_capacity
 static __always_inline
@@ -1786,8 +1771,6 @@ unsigned long arch_scale_cpu_capacity(void __always_unused *sd, int cpu)
 	return SCHED_CAPACITY_SCALE;
 }
 #endif
-static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { }
-static inline void sched_avg_update(struct rq *rq) { }
 #endif
 
 struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-- 
cgit v1.2.3


From 5fd778915ad29184a5ff8eb82d1118f6916b79e4 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 28 Jun 2018 17:45:14 +0200
Subject: sched/sysctl: Remove unused sched_time_avg_ms sysctl

/proc/sys/kernel/sched_time_avg_ms entry is not used anywhere,
remove it.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Cc: viresh.kumar@linaro.org
Link: http://lkml.kernel.org/r/1530200714-4504-12-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched/sysctl.h | 1 -
 kernel/sched/core.c          | 8 --------
 kernel/sched/sched.h         | 1 -
 kernel/sysctl.c              | 8 --------
 4 files changed, 18 deletions(-)

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 1c1a1512ec55..913488d828cb 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -40,7 +40,6 @@ extern unsigned int sysctl_numa_balancing_scan_size;
 #ifdef CONFIG_SCHED_DEBUG
 extern __read_mostly unsigned int sysctl_sched_migration_cost;
 extern __read_mostly unsigned int sysctl_sched_nr_migrate;
-extern __read_mostly unsigned int sysctl_sched_time_avg;
 
 int sched_proc_update_handler(struct ctl_table *table, int write,
 		void __user *buffer, size_t *length,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index a691b07390ab..ba6bb805693a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -46,14 +46,6 @@ const_debug unsigned int sysctl_sched_features =
  */
 const_debug unsigned int sysctl_sched_nr_migrate = 32;
 
-/*
- * period over which we average the RT time consumption, measured
- * in ms.
- *
- * default: 1s
- */
-const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
-
 /*
  * period over which we measure -rt task CPU usage in us.
  * default: 1s
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 14aac2d2de80..ebb4b3c3ece7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1713,7 +1713,6 @@ extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
 extern void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags);
 
-extern const_debug unsigned int sysctl_sched_time_avg;
 extern const_debug unsigned int sysctl_sched_nr_migrate;
 extern const_debug unsigned int sysctl_sched_migration_cost;
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2d9837c0aff4..f22f76b7a138 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -368,14 +368,6 @@ static struct ctl_table kern_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
-	{
-		.procname	= "sched_time_avg_ms",
-		.data		= &sysctl_sched_time_avg,
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= &one,
-	},
 #ifdef CONFIG_SCHEDSTATS
 	{
 		.procname	= "sched_schedstats",
-- 
cgit v1.2.3


From 45f5519ec55e75af3565dd737586d3b041834f71 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 5 Jul 2018 14:36:17 +0200
Subject: sched/cpufreq: Clarify sugov_get_util()

Add a few comments to (hopefully) clarifying some of the magic in
sugov_get_util().

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Morten.Rasmussen@arm.com
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: claudio@evidence.eu.com
Cc: daniel.lezcano@linaro.org
Cc: dietmar.eggemann@arm.com
Cc: joel@joelfernandes.org
Cc: juri.lelli@redhat.com
Cc: luca.abeni@santannapisa.it
Cc: patrick.bellasi@arm.com
Cc: quentin.perret@arm.com
Cc: rjw@rjwysocki.net
Cc: valentin.schneider@arm.com
Link: http://lkml.kernel.org/r/20180705123617.GM2458@hirez.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/cpufreq_schedutil.c | 75 +++++++++++++++++++++++++++++-----------
 1 file changed, 54 insertions(+), 21 deletions(-)

diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index c9622b3f183d..97dcd4472a0e 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -177,6 +177,26 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
 	return cpufreq_driver_resolve_freq(policy, freq);
 }
 
+/*
+ * This function computes an effective utilization for the given CPU, to be
+ * used for frequency selection given the linear relation: f = u * f_max.
+ *
+ * The scheduler tracks the following metrics:
+ *
+ *   cpu_util_{cfs,rt,dl,irq}()
+ *   cpu_bw_dl()
+ *
+ * Where the cfs,rt and dl util numbers are tracked with the same metric and
+ * synchronized windows and are thus directly comparable.
+ *
+ * The cfs,rt,dl utilization are the running times measured with rq->clock_task
+ * which excludes things like IRQ and steal-time. These latter are then accrued
+ * in the irq utilization.
+ *
+ * The DL bandwidth number otoh is not a measured metric but a value computed
+ * based on the task model parameters and gives the minimal utilization
+ * required to meet deadlines.
+ */
 static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 {
 	struct rq *rq = cpu_rq(sg_cpu->cpu);
@@ -188,47 +208,60 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 	if (rt_rq_is_runnable(&rq->rt))
 		return max;
 
+	/*
+	 * Early check to see if IRQ/steal time saturates the CPU, can be
+	 * because of inaccuracies in how we track these -- see
+	 * update_irq_load_avg().
+	 */
 	irq = cpu_util_irq(rq);
-
 	if (unlikely(irq >= max))
 		return max;
 
-	/* Sum rq utilization */
+	/*
+	 * Because the time spend on RT/DL tasks is visible as 'lost' time to
+	 * CFS tasks and we use the same metric to track the effective
+	 * utilization (PELT windows are synchronized) we can directly add them
+	 * to obtain the CPU's actual utilization.
+	 */
 	util = cpu_util_cfs(rq);
 	util += cpu_util_rt(rq);
 
 	/*
-	 * Interrupt time is not seen by RQS utilization so we can compare
-	 * them with the CPU capacity
+	 * We do not make cpu_util_dl() a permanent part of this sum because we
+	 * want to use cpu_bw_dl() later on, but we need to check if the
+	 * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
+	 * f_max when there is no idle time.
+	 *
+	 * NOTE: numerical errors or stop class might cause us to not quite hit
+	 * saturation when we should -- something for later.
 	 */
 	if ((util + cpu_util_dl(rq)) >= max)
 		return max;
 
 	/*
-	 * As there is still idle time on the CPU, we need to compute the
-	 * utilization level of the CPU.
+	 * There is still idle time; further improve the number by using the
+	 * irq metric. Because IRQ/steal time is hidden from the task clock we
+	 * need to scale the task numbers:
 	 *
+	 *              1 - irq
+	 *   U' = irq + ------- * U
+	 *                max
+	 */
+	util *= (max - irq);
+	util /= max;
+	util += irq;
+
+	/*
 	 * Bandwidth required by DEADLINE must always be granted while, for
 	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a mechanism
 	 * to gracefully reduce the frequency when no tasks show up for longer
 	 * periods of time.
 	 *
-	 * Ideally we would like to set util_dl as min/guaranteed freq and
-	 * util_cfs + util_dl as requested freq. However, cpufreq is not yet
-	 * ready for such an interface. So, we only do the latter for now.
+	 * Ideally we would like to set bw_dl as min/guaranteed freq and util +
+	 * bw_dl as requested freq. However, cpufreq is not yet ready for such
+	 * an interface. So, we only do the latter for now.
 	 */
-
-	/* Weight RQS utilization to normal context window */
-	util *= (max - irq);
-	util /= max;
-
-	/* Add interrupt utilization */
-	util += irq;
-
-	/* Add DL bandwidth requirement */
-	util += sg_cpu->bw_dl;
-
-	return min(max, util);
+	return min(max, util + sg_cpu->bw_dl);
 }
 
 /**
-- 
cgit v1.2.3


From af0fffd9300b97d8875aa745bc78e2f6fdb3c1f0 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Fri, 6 Jul 2018 15:06:15 +0200
Subject: sched/core: Remove get_cpu() from sched_fork()

get_cpu() disables preemption for the entire sched_fork() function.
This get_cpu() was introduced in commit:

  dd41f596cda0 ("sched: cfs core code")

... which also invoked sched_balance_self() and this function
required preemption do be off.

Today, sched_balance_self() seems to be moved to ->task_fork callback
which is invoked while the ->pi_lock is held.

set_load_weight() could invoke reweight_task() which then via $callchain
might end up in smp_processor_id() but since `update_load' is false
this won't happen.

I didn't find any this_cpu*() or similar usage during the initialisation
of the task_struct.

The `cpu' value (from get_cpu()) is only used later in __set_task_cpu()
while the ->pi_lock lock is held.

Based on this it is possible to remove get_cpu() and use
smp_processor_id() for the `cpu' variable without breaking anything.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20180706130615.g2ex2kmfu5kcvlq6@linutronix.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ba6bb805693a..c3cf7d992159 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2294,7 +2294,6 @@ static inline void init_schedstats(void) {}
 int sched_fork(unsigned long clone_flags, struct task_struct *p)
 {
 	unsigned long flags;
-	int cpu = get_cpu();
 
 	__sched_fork(clone_flags, p);
 	/*
@@ -2330,14 +2329,12 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 		p->sched_reset_on_fork = 0;
 	}
 
-	if (dl_prio(p->prio)) {
-		put_cpu();
+	if (dl_prio(p->prio))
 		return -EAGAIN;
-	} else if (rt_prio(p->prio)) {
+	else if (rt_prio(p->prio))
 		p->sched_class = &rt_sched_class;
-	} else {
+	else
 		p->sched_class = &fair_sched_class;
-	}
 
 	init_entity_runnable_average(&p->se);
 
@@ -2353,7 +2350,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	 * We're setting the CPU for the first time, we don't migrate,
 	 * so use __set_task_cpu().
 	 */
-	__set_task_cpu(p, cpu);
+	__set_task_cpu(p, smp_processor_id());
 	if (p->sched_class->task_fork)
 		p->sched_class->task_fork(p);
 	raw_spin_unlock_irqrestore(&p->pi_lock, flags);
@@ -2370,8 +2367,6 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 	RB_CLEAR_NODE(&p->pushable_dl_tasks);
 #endif
-
-	put_cpu();
 	return 0;
 }
 
-- 
cgit v1.2.3


From 788faab70d5a882693286b8d5022779559c79904 Mon Sep 17 00:00:00 2001
From: Tobias Tefke <tobias.tefke@gmail.com>
Date: Mon, 9 Jul 2018 12:57:15 +0200
Subject: perf, tools: Use correct articles in comments

Some of the comments in the perf events code use articles incorrectly,
using 'a' for words beginning with a vowel sound, where 'an' should be
used.

Signed-off-by: Tobias Tefke <tobias.tefke@tutanota.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: acme@kernel.org
Cc: alexander.shishkin@linux.intel.com
Cc: jolsa@redhat.com
Cc: namhyung@kernel.org
Link: http://lkml.kernel.org/r/20180709105715.22938-1-tobias.tefke@tutanota.com
[ Fix a few more perf related 'a event' typo fixes from all around the kernel and tooling tree. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/powerpc/perf/core-book3s.c          |  6 +++---
 include/linux/perf_event.h               |  2 +-
 kernel/events/core.c                     | 16 ++++++++--------
 kernel/events/uprobes.c                  |  6 +++---
 tools/perf/Documentation/perf-list.txt   |  2 +-
 tools/perf/Documentation/perf-record.txt |  4 ++--
 6 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 3f66fcf8ad99..19d8ab49d1bd 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -1469,7 +1469,7 @@ static int collect_events(struct perf_event *group, int max_count,
 }
 
 /*
- * Add a event to the PMU.
+ * Add an event to the PMU.
  * If all events are not already frozen, then we disable and
  * re-enable the PMU in order to get hw_perf_enable to do the
  * actual work of reconfiguring the PMU.
@@ -1548,7 +1548,7 @@ nocheck:
 }
 
 /*
- * Remove a event from the PMU.
+ * Remove an event from the PMU.
  */
 static void power_pmu_del(struct perf_event *event, int ef_flags)
 {
@@ -1742,7 +1742,7 @@ static int power_pmu_commit_txn(struct pmu *pmu)
 /*
  * Return 1 if we might be able to put event on a limited PMC,
  * or 0 if not.
- * A event can only go on a limited PMC if it counts something
+ * An event can only go on a limited PMC if it counts something
  * that a limited PMC can count, doesn't require interrupts, and
  * doesn't exclude any processor mode.
  */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 1fa12887ec02..e6dd3a2f8ec4 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -490,7 +490,7 @@ struct perf_addr_filters_head {
 };
 
 /**
- * enum perf_event_state - the states of a event
+ * enum perf_event_state - the states of an event:
  */
 enum perf_event_state {
 	PERF_EVENT_STATE_DEAD		= -4,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a4d5ac6d74af..86b31e5a5a9a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1656,7 +1656,7 @@ perf_event_groups_next(struct perf_event *event)
 				typeof(*event), group_node))
 
 /*
- * Add a event from the lists for its context.
+ * Add an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -1844,7 +1844,7 @@ static void perf_group_attach(struct perf_event *event)
 }
 
 /*
- * Remove a event from the lists for its context.
+ * Remove an event from the lists for its context.
  * Must be called with ctx->mutex and ctx->lock held.
  */
 static void
@@ -2148,7 +2148,7 @@ static void __perf_event_disable(struct perf_event *event,
 }
 
 /*
- * Disable a event.
+ * Disable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2677,7 +2677,7 @@ static void __perf_event_enable(struct perf_event *event,
 }
 
 /*
- * Enable a event.
+ * Enable an event.
  *
  * If event->ctx is a cloned context, callers must make sure that
  * every task struct that event->ctx->task could possibly point to
@@ -2755,7 +2755,7 @@ static int __perf_event_stop(void *info)
 	 * events will refuse to restart because of rb::aux_mmap_count==0,
 	 * see comments in perf_aux_output_begin().
 	 *
-	 * Since this is happening on a event-local CPU, no trace is lost
+	 * Since this is happening on an event-local CPU, no trace is lost
 	 * while restarting.
 	 */
 	if (sd->restart)
@@ -4827,7 +4827,7 @@ __perf_read(struct perf_event *event, char __user *buf, size_t count)
 	int ret;
 
 	/*
-	 * Return end-of-file for a read on a event that is in
+	 * Return end-of-file for a read on an event that is in
 	 * error state (i.e. because it was pinned but it couldn't be
 	 * scheduled on to the CPU at some point).
 	 */
@@ -9898,7 +9898,7 @@ enabled:
 }
 
 /*
- * Allocate and initialize a event structure
+ * Allocate and initialize an event structure
  */
 static struct perf_event *
 perf_event_alloc(struct perf_event_attr *attr, int cpu,
@@ -11229,7 +11229,7 @@ const struct perf_event_attr *perf_event_attrs(struct perf_event *event)
 }
 
 /*
- * Inherit a event from parent task to child task.
+ * Inherit an event from parent task to child task.
  *
  * Returns:
  *  - valid pointer on success
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index ccc579a7d32e..aed1ba569954 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -918,7 +918,7 @@ int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *
 EXPORT_SYMBOL_GPL(uprobe_register);
 
 /*
- * uprobe_apply - unregister a already registered probe.
+ * uprobe_apply - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: consumer which wants to add more or remove some breakpoints
@@ -947,7 +947,7 @@ int uprobe_apply(struct inode *inode, loff_t offset,
 }
 
 /*
- * uprobe_unregister - unregister a already registered probe.
+ * uprobe_unregister - unregister an already registered probe.
  * @inode: the file in which the probe has to be removed.
  * @offset: offset from the start of the file.
  * @uc: identify which probe if multiple probes are colocated.
@@ -1403,7 +1403,7 @@ static struct return_instance *free_ret_instance(struct return_instance *ri)
 
 /*
  * Called with no locks held.
- * Called in context of a exiting or a exec-ing thread.
+ * Called in context of an exiting or an exec-ing thread.
  */
 void uprobe_free_utask(struct task_struct *t)
 {
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 11300dbe35c5..14e13512c05f 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -234,7 +234,7 @@ perf also supports group leader sampling using the :S specifier.
   perf record -e '{cycles,instructions}:S' ...
   perf report --group
 
-Normally all events in a event group sample, but with :S only
+Normally all events in an event group sample, but with :S only
 the first event (the leader) samples, and it only reads the values of the
 other events in the group.
 
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 04168da4268e..246dee081efd 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -94,7 +94,7 @@ OPTIONS
 	  "perf report" to view group events together.
 
 --filter=<filter>::
-        Event filter. This option should follow a event selector (-e) which
+        Event filter. This option should follow an event selector (-e) which
 	selects either tracepoint event(s) or a hardware trace PMU
 	(e.g. Intel PT or CoreSight).
 
@@ -153,7 +153,7 @@ OPTIONS
 
 --exclude-perf::
 	Don't record events issued by perf itself. This option should follow
-	a event selector (-e) which selects tracepoint event(s). It adds a
+	an event selector (-e) which selects tracepoint event(s). It adds a
 	filter expression 'common_pid != $PERFPID' to filters. If other
 	'--filter' exists, the new filter expression will be combined with
 	them by '&&'.
-- 
cgit v1.2.3


From bdc9c3e5ed953441a46ef3acd81c783d591c9a96 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Mon, 9 Jul 2018 21:07:21 +0900
Subject: x86/build: Remove old -funit-at-a-time GCC quirk

The following commit:

  e501ce957a78 ("x86: Force asm-goto")

... bumped the minimum GCC version to 4.5 for building the x86 kernel.

arch/x86/Makefile no longer needs to take care of older GCC versions,
such as this pre-4.0 -funit-at-a-time quirk.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1531138041-24200-1-git-send-email-yamada.masahiro@socionext.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/Makefile | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index a08e82856563..7e3c07d6ad42 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -80,11 +80,6 @@ ifeq ($(CONFIG_X86_32),y)
         # alignment instructions.
         KBUILD_CFLAGS += $(call cc-option,$(cc_stack_align4))
 
-        # Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
-        # a lot more stack due to the lack of sharing of stacklots:
-        KBUILD_CFLAGS += $(call cc-ifversion, -lt, 0400, \
-				$(call cc-option,-fno-unit-at-a-time))
-
         # CPU-specific tuning. Anything which can be shared with UML should go here.
         include arch/x86/Makefile_32.cpu
         KBUILD_CFLAGS += $(cflags-y)
-- 
cgit v1.2.3


From 90a2186b7df183c2fd35f724d0d16a0c10fac9b2 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 11 Jul 2018 11:40:33 +0200
Subject: efi/x86: Clean up the eboot code

Various small cleanups:

 - Standardize printk messages:

     'alloc' => 'allocate'
     'mem'   => 'memory'

   also put variable names in printk messages between quotes.

 - Align mass-assignments vertically for better readability

 - Break multi-line function prototypes at the name where possible,
   not in the middle of the parameter list

 - Use a newline before return statements consistently.

 - Use curly braces in a balanced fashion.

 - Remove stray newlines.

No change in functionality.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Matt Fleming <matt@codeblueprint.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-2-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/eboot.c | 245 ++++++++++++++++++++-------------------
 1 file changed, 125 insertions(+), 120 deletions(-)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index e98522ea6f09..9f6813493945 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -34,9 +34,9 @@ static void setup_boot_services##bits(struct efi_config *c)		\
 									\
 	table = (typeof(table))sys_table;				\
 									\
-	c->runtime_services = table->runtime;				\
-	c->boot_services = table->boottime;				\
-	c->text_output = table->con_out;				\
+	c->runtime_services	= table->runtime;			\
+	c->boot_services	= table->boottime;			\
+	c->text_output		= table->con_out;			\
 }
 BOOT_SERVICES(32);
 BOOT_SERVICES(64);
@@ -64,6 +64,7 @@ static inline efi_status_t __open_volume32(void *__image, void **__fh)
 		efi_printk(sys_table, "Failed to open volume\n");
 
 	*__fh = fh;
+
 	return status;
 }
 
@@ -90,6 +91,7 @@ static inline efi_status_t __open_volume64(void *__image, void **__fh)
 		efi_printk(sys_table, "Failed to open volume\n");
 
 	*__fh = fh;
+
 	return status;
 }
 
@@ -134,16 +136,16 @@ __setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA, size, &rom);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for rom\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'rom'\n");
 		return status;
 	}
 
 	memset(rom, 0, sizeof(*rom));
 
-	rom->data.type = SETUP_PCI;
-	rom->data.len = size - sizeof(struct setup_data);
-	rom->data.next = 0;
-	rom->pcilen = pci->romsize;
+	rom->data.type	= SETUP_PCI;
+	rom->data.len	= size - sizeof(struct setup_data);
+	rom->data.next	= 0;
+	rom->pcilen	= pci->romsize;
 	*__rom = rom;
 
 	status = efi_call_proto(efi_pci_io_protocol, pci.read, pci,
@@ -180,8 +182,7 @@ free_struct:
 }
 
 static void
-setup_efi_pci32(struct boot_params *params, void **pci_handle,
-		unsigned long size)
+setup_efi_pci32(struct boot_params *params, void **pci_handle, unsigned long size)
 {
 	efi_pci_io_protocol_t *pci = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
@@ -220,13 +221,11 @@ setup_efi_pci32(struct boot_params *params, void **pci_handle,
 			params->hdr.setup_data = (unsigned long)rom;
 
 		data = (struct setup_data *)rom;
-
 	}
 }
 
 static void
-setup_efi_pci64(struct boot_params *params, void **pci_handle,
-		unsigned long size)
+setup_efi_pci64(struct boot_params *params, void **pci_handle, unsigned long size)
 {
 	efi_pci_io_protocol_t *pci = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
@@ -265,7 +264,6 @@ setup_efi_pci64(struct boot_params *params, void **pci_handle,
 			params->hdr.setup_data = (unsigned long)rom;
 
 		data = (struct setup_data *)rom;
-
 	}
 }
 
@@ -295,7 +293,7 @@ static void setup_efi_pci(struct boot_params *params)
 					size, (void **)&pci_handle);
 
 		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table, "Failed to alloc mem for pci_handle\n");
+			efi_printk(sys_table, "Failed to allocate memory for 'pci_handle'\n");
 			return;
 		}
 
@@ -341,8 +339,7 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 		status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
 					size + sizeof(struct setup_data), &new);
 		if (status != EFI_SUCCESS) {
-			efi_printk(sys_table,
-					"Failed to alloc mem for properties\n");
+			efi_printk(sys_table, "Failed to allocate memory for 'properties'\n");
 			return;
 		}
 
@@ -358,9 +355,9 @@ static void retrieve_apple_device_properties(struct boot_params *boot_params)
 	new->next = 0;
 
 	data = (struct setup_data *)(unsigned long)boot_params->hdr.setup_data;
-	if (!data)
+	if (!data) {
 		boot_params->hdr.setup_data = (unsigned long)new;
-	else {
+	} else {
 		while (data->next)
 			data = (struct setup_data *)(unsigned long)data->next;
 		data->next = (unsigned long)new;
@@ -473,8 +470,8 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 /*
  * See if we have Universal Graphics Adapter (UGA) protocol
  */
-static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
-			      unsigned long size)
+static efi_status_t
+setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size)
 {
 	efi_status_t status;
 	u32 width, height;
@@ -503,23 +500,24 @@ static efi_status_t setup_uga(struct screen_info *si, efi_guid_t *uga_proto,
 		goto free_handle;
 
 	/* EFI framebuffer */
-	si->orig_video_isVGA = VIDEO_TYPE_EFI;
+	si->orig_video_isVGA	= VIDEO_TYPE_EFI;
 
-	si->lfb_depth = 32;
-	si->lfb_width = width;
-	si->lfb_height = height;
+	si->lfb_depth		= 32;
+	si->lfb_width		= width;
+	si->lfb_height		= height;
 
-	si->red_size = 8;
-	si->red_pos = 16;
-	si->green_size = 8;
-	si->green_pos = 8;
-	si->blue_size = 8;
-	si->blue_pos = 0;
-	si->rsvd_size = 8;
-	si->rsvd_pos = 24;
+	si->red_size		= 8;
+	si->red_pos		= 16;
+	si->green_size		= 8;
+	si->green_pos		= 8;
+	si->blue_size		= 8;
+	si->blue_pos		= 0;
+	si->rsvd_size		= 8;
+	si->rsvd_pos		= 24;
 
 free_handle:
 	efi_call_early(free_pool, uga_handle);
+
 	return status;
 }
 
@@ -601,7 +599,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	status = efi_low_alloc(sys_table, 0x4000, 1,
 			       (unsigned long *)&boot_params);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc lowmem for boot params\n");
+		efi_printk(sys_table, "Failed to allocate lowmem for boot params\n");
 		return NULL;
 	}
 
@@ -617,9 +615,9 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	 * Fill out some of the header fields ourselves because the
 	 * EFI firmware loader doesn't load the first sector.
 	 */
-	hdr->root_flags = 1;
-	hdr->vid_mode = 0xffff;
-	hdr->boot_flag = 0xAA55;
+	hdr->root_flags	= 1;
+	hdr->vid_mode	= 0xffff;
+	hdr->boot_flag	= 0xAA55;
 
 	hdr->type_of_loader = 0x21;
 
@@ -627,6 +625,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	cmdline_ptr = efi_convert_cmdline(sys_table, image, &options_size);
 	if (!cmdline_ptr)
 		goto fail;
+
 	hdr->cmd_line_ptr = (unsigned long)cmdline_ptr;
 	/* Fill in upper bits of command line address, NOP on 32 bit  */
 	boot_params->ext_cmd_line_ptr = (u64)(unsigned long)cmdline_ptr >> 32;
@@ -663,10 +662,12 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	boot_params->ext_ramdisk_size  = (u64)ramdisk_size >> 32;
 
 	return boot_params;
+
 fail2:
 	efi_free(sys_table, options_size, hdr->cmd_line_ptr);
 fail:
 	efi_free(sys_table, 0x4000, (unsigned long)boot_params);
+
 	return NULL;
 }
 
@@ -678,7 +679,7 @@ static void add_e820ext(struct boot_params *params,
 	unsigned long size;
 
 	e820ext->type = SETUP_E820_EXT;
-	e820ext->len = nr_entries * sizeof(struct boot_e820_entry);
+	e820ext->len  = nr_entries * sizeof(struct boot_e820_entry);
 	e820ext->next = 0;
 
 	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
@@ -692,8 +693,8 @@ static void add_e820ext(struct boot_params *params,
 		params->hdr.setup_data = (unsigned long)e820ext;
 }
 
-static efi_status_t setup_e820(struct boot_params *params,
-			       struct setup_data *e820ext, u32 e820ext_size)
+static efi_status_t
+setup_e820(struct boot_params *params, struct setup_data *e820ext, u32 e820ext_size)
 {
 	struct boot_e820_entry *entry = params->e820_table;
 	struct efi_info *efi = &params->efi_info;
@@ -814,11 +815,11 @@ static efi_status_t alloc_e820ext(u32 nr_desc, struct setup_data **e820ext,
 }
 
 struct exit_boot_struct {
-	struct boot_params *boot_params;
-	struct efi_info *efi;
-	struct setup_data *e820ext;
-	__u32 e820ext_size;
-	bool is64;
+	struct boot_params	*boot_params;
+	struct efi_info		*efi;
+	struct setup_data	*e820ext;
+	__u32			e820ext_size;
+	bool			is64;
 };
 
 static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
@@ -848,15 +849,15 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 	signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
 	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
-	p->efi->efi_systab = (unsigned long)sys_table_arg;
-	p->efi->efi_memdesc_size = *map->desc_size;
-	p->efi->efi_memdesc_version = *map->desc_ver;
-	p->efi->efi_memmap = (unsigned long)*map->map;
-	p->efi->efi_memmap_size = *map->map_size;
+	p->efi->efi_systab		= (unsigned long)sys_table_arg;
+	p->efi->efi_memdesc_size	= *map->desc_size;
+	p->efi->efi_memdesc_version	= *map->desc_ver;
+	p->efi->efi_memmap		= (unsigned long)*map->map;
+	p->efi->efi_memmap_size		= *map->map_size;
 
 #ifdef CONFIG_X86_64
-	p->efi->efi_systab_hi = (unsigned long)sys_table_arg >> 32;
-	p->efi->efi_memmap_hi = (unsigned long)*map->map >> 32;
+	p->efi->efi_systab_hi		= (unsigned long)sys_table_arg >> 32;
+	p->efi->efi_memmap_hi		= (unsigned long)*map->map >> 32;
 #endif
 
 	return EFI_SUCCESS;
@@ -874,17 +875,17 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	struct efi_boot_memmap map;
 	struct exit_boot_struct priv;
 
-	map.map =		&mem_map;
-	map.map_size =		&map_sz;
-	map.desc_size =		&desc_size;
-	map.desc_ver =		&desc_version;
-	map.key_ptr =		&key;
-	map.buff_size =		&buff_size;
-	priv.boot_params =	boot_params;
-	priv.efi =		&boot_params->efi_info;
-	priv.e820ext =		NULL;
-	priv.e820ext_size =	0;
-	priv.is64 =		is64;
+	map.map			= &mem_map;
+	map.map_size		= &map_sz;
+	map.desc_size		= &desc_size;
+	map.desc_ver		= &desc_version;
+	map.key_ptr		= &key;
+	map.buff_size		= &buff_size;
+	priv.boot_params	= boot_params;
+	priv.efi		= &boot_params->efi_info;
+	priv.e820ext		= NULL;
+	priv.e820ext_size	= 0;
+	priv.is64		= is64;
 
 	/* Might as well exit boot services now */
 	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
@@ -892,10 +893,11 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	if (status != EFI_SUCCESS)
 		return status;
 
-	e820ext = priv.e820ext;
-	e820ext_size = priv.e820ext_size;
+	e820ext			= priv.e820ext;
+	e820ext_size		= priv.e820ext_size;
+
 	/* Historic? */
-	boot_params->alt_mem_k = 32 * 1024;
+	boot_params->alt_mem_k	= 32 * 1024;
 
 	status = setup_e820(boot_params, e820ext, e820ext_size);
 	if (status != EFI_SUCCESS)
@@ -908,8 +910,8 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
  * On success we return a pointer to a boot_params structure, and NULL
  * on failure.
  */
-struct boot_params *efi_main(struct efi_config *c,
-			     struct boot_params *boot_params)
+struct boot_params *
+efi_main(struct efi_config *c, struct boot_params *boot_params)
 {
 	struct desc_ptr *gdt = NULL;
 	efi_loaded_image_t *image;
@@ -957,7 +959,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
 				sizeof(*gdt), (void **)&gdt);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for gdt structure\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'gdt' structure\n");
 		goto fail;
 	}
 
@@ -965,7 +967,7 @@ struct boot_params *efi_main(struct efi_config *c,
 	status = efi_low_alloc(sys_table, gdt->size, 8,
 			   (unsigned long *)&gdt->address);
 	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to alloc mem for gdt\n");
+		efi_printk(sys_table, "Failed to allocate memory for 'gdt'\n");
 		goto fail;
 	}
 
@@ -1002,19 +1004,20 @@ struct boot_params *efi_main(struct efi_config *c,
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		/* __KERNEL32_CS */
-		desc->limit0 = 0xffff;
-		desc->base0 = 0x0000;
-		desc->base1 = 0x0000;
-		desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
-		desc->s = DESC_TYPE_CODE_DATA;
-		desc->dpl = 0;
-		desc->p = 1;
-		desc->limit1 = 0xf;
-		desc->avl = 0;
-		desc->l = 0;
-		desc->d = SEG_OP_SIZE_32BIT;
-		desc->g = SEG_GRANULARITY_4KB;
-		desc->base2 = 0x00;
+		desc->limit0	= 0xffff;
+		desc->base0	= 0x0000;
+		desc->base1	= 0x0000;
+		desc->type	= SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+		desc->s		= DESC_TYPE_CODE_DATA;
+		desc->dpl	= 0;
+		desc->p		= 1;
+		desc->limit1	= 0xf;
+		desc->avl	= 0;
+		desc->l		= 0;
+		desc->d		= SEG_OP_SIZE_32BIT;
+		desc->g		= SEG_GRANULARITY_4KB;
+		desc->base2	= 0x00;
+
 		desc++;
 	} else {
 		/* Second entry is unused on 32-bit */
@@ -1022,15 +1025,16 @@ struct boot_params *efi_main(struct efi_config *c,
 	}
 
 	/* __KERNEL_CS */
-	desc->limit0 = 0xffff;
-	desc->base0 = 0x0000;
-	desc->base1 = 0x0000;
-	desc->type = SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
-	desc->s = DESC_TYPE_CODE_DATA;
-	desc->dpl = 0;
-	desc->p = 1;
-	desc->limit1 = 0xf;
-	desc->avl = 0;
+	desc->limit0	= 0xffff;
+	desc->base0	= 0x0000;
+	desc->base1	= 0x0000;
+	desc->type	= SEG_TYPE_CODE | SEG_TYPE_EXEC_READ;
+	desc->s		= DESC_TYPE_CODE_DATA;
+	desc->dpl	= 0;
+	desc->p		= 1;
+	desc->limit1	= 0xf;
+	desc->avl	= 0;
+
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		desc->l = 1;
 		desc->d = 0;
@@ -1038,41 +1042,41 @@ struct boot_params *efi_main(struct efi_config *c,
 		desc->l = 0;
 		desc->d = SEG_OP_SIZE_32BIT;
 	}
-	desc->g = SEG_GRANULARITY_4KB;
-	desc->base2 = 0x00;
+	desc->g		= SEG_GRANULARITY_4KB;
+	desc->base2	= 0x00;
 	desc++;
 
 	/* __KERNEL_DS */
-	desc->limit0 = 0xffff;
-	desc->base0 = 0x0000;
-	desc->base1 = 0x0000;
-	desc->type = SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
-	desc->s = DESC_TYPE_CODE_DATA;
-	desc->dpl = 0;
-	desc->p = 1;
-	desc->limit1 = 0xf;
-	desc->avl = 0;
-	desc->l = 0;
-	desc->d = SEG_OP_SIZE_32BIT;
-	desc->g = SEG_GRANULARITY_4KB;
-	desc->base2 = 0x00;
+	desc->limit0	= 0xffff;
+	desc->base0	= 0x0000;
+	desc->base1	= 0x0000;
+	desc->type	= SEG_TYPE_DATA | SEG_TYPE_READ_WRITE;
+	desc->s		= DESC_TYPE_CODE_DATA;
+	desc->dpl	= 0;
+	desc->p		= 1;
+	desc->limit1	= 0xf;
+	desc->avl	= 0;
+	desc->l		= 0;
+	desc->d		= SEG_OP_SIZE_32BIT;
+	desc->g		= SEG_GRANULARITY_4KB;
+	desc->base2	= 0x00;
 	desc++;
 
 	if (IS_ENABLED(CONFIG_X86_64)) {
 		/* Task segment value */
-		desc->limit0 = 0x0000;
-		desc->base0 = 0x0000;
-		desc->base1 = 0x0000;
-		desc->type = SEG_TYPE_TSS;
-		desc->s = 0;
-		desc->dpl = 0;
-		desc->p = 1;
-		desc->limit1 = 0x0;
-		desc->avl = 0;
-		desc->l = 0;
-		desc->d = 0;
-		desc->g = SEG_GRANULARITY_4KB;
-		desc->base2 = 0x00;
+		desc->limit0	= 0x0000;
+		desc->base0	= 0x0000;
+		desc->base1	= 0x0000;
+		desc->type	= SEG_TYPE_TSS;
+		desc->s		= 0;
+		desc->dpl	= 0;
+		desc->p		= 1;
+		desc->limit1	= 0x0;
+		desc->avl	= 0;
+		desc->l		= 0;
+		desc->d		= 0;
+		desc->g		= SEG_GRANULARITY_4KB;
+		desc->base2	= 0x00;
 		desc++;
 	}
 
@@ -1082,5 +1086,6 @@ struct boot_params *efi_main(struct efi_config *c,
 	return boot_params;
 fail:
 	efi_printk(sys_table, "efi_main() failed!\n");
+
 	return NULL;
 }
-- 
cgit v1.2.3


From 5a58bc1b1edc18a9edff606ec99e6f6b723975f4 Mon Sep 17 00:00:00 2001
From: Sai Praneeth <sai.praneeth.prakhya@intel.com>
Date: Wed, 11 Jul 2018 11:40:34 +0200
Subject: efi/x86: Use non-blocking SetVariable() for
 efi_delete_dummy_variable()

Presently, efi_delete_dummy_variable() uses set_variable() which might
block, which the scheduler is rightfully upset about when used from
the idle thread, producing this splat:

  "bad: scheduling from the idle thread!"

So, make efi_delete_dummy_variable() use set_variable_nonblocking(),
which, as the name suggests, doesn't block.

Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-3-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/platform/efi/quirks.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 36c1f8b9f7e0..6af39dc40325 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -105,12 +105,11 @@ early_param("efi_no_storage_paranoia", setup_storage_paranoia);
 */
 void efi_delete_dummy_variable(void)
 {
-	efi.set_variable((efi_char16_t *)efi_dummy_name,
-			 &EFI_DUMMY_GUID,
-			 EFI_VARIABLE_NON_VOLATILE |
-			 EFI_VARIABLE_BOOTSERVICE_ACCESS |
-			 EFI_VARIABLE_RUNTIME_ACCESS,
-			 0, NULL);
+	efi.set_variable_nonblocking((efi_char16_t *)efi_dummy_name,
+				     &EFI_DUMMY_GUID,
+				     EFI_VARIABLE_NON_VOLATILE |
+				     EFI_VARIABLE_BOOTSERVICE_ACCESS |
+				     EFI_VARIABLE_RUNTIME_ACCESS, 0, NULL);
 }
 
 /*
-- 
cgit v1.2.3


From 3eb420e70d879ce0e6bf752accf5cdedb0a59de8 Mon Sep 17 00:00:00 2001
From: Sai Praneeth <sai.praneeth.prakhya@intel.com>
Date: Wed, 11 Jul 2018 11:40:35 +0200
Subject: efi: Use a work queue to invoke EFI Runtime Services

Presently, when a user process requests the kernel to execute any
UEFI runtime service, the kernel temporarily switches to a separate
set of page tables that describe the virtual mapping of the UEFI
runtime services regions in memory. Since UEFI runtime services are
typically invoked with interrupts enabled, any code that may be called
during this time, will have an incorrect view of the process's address
space. Although it is unusual for code running in interrupt context to
make assumptions about the process context it runs in, there are cases
(such as the perf subsystem taking samples) where this causes problems.

So let's set up a work queue for calling UEFI runtime services, so that
the actual calls are made when the work queue items are dispatched by a
work queue worker running in a separate kernel thread. Such threads are
not expected to have userland mappings in the first place, and so the
additional mappings created for the UEFI runtime services can never
clash with any.

The ResetSystem() runtime service is not covered by the work queue
handling, since it is not expected to return, and may be called at a
time when the kernel is torn down to the point where we cannot expect
work queues to still be operational.

The non-blocking variants of SetVariable() and QueryVariableInfo()
are also excluded: these are intended to be used from atomic context,
which obviously rules out waiting for a completion to be signalled by
another thread. Note that these variants are currently only used for
UEFI runtime services calls that occur very early in the boot, and
for ones that occur in critical conditions, e.g., to flush kernel logs
to UEFI variables via efi-pstore.

Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
[ardb: exclude ResetSystem() from the workqueue treatment
       merge from 2 separate patches and rewrite commit log]
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-4-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/efi.c              |  14 +++
 drivers/firmware/efi/runtime-wrappers.c | 202 +++++++++++++++++++++++++++++---
 include/linux/efi.h                     |   3 +
 3 files changed, 204 insertions(+), 15 deletions(-)

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 232f4915223b..1379a375dfa8 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -84,6 +84,8 @@ struct mm_struct efi_mm = {
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
 };
 
+struct workqueue_struct *efi_rts_wq;
+
 static bool disable_runtime;
 static int __init setup_noefi(char *arg)
 {
@@ -337,6 +339,18 @@ static int __init efisubsys_init(void)
 	if (!efi_enabled(EFI_BOOT))
 		return 0;
 
+	/*
+	 * Since we process only one efi_runtime_service() at a time, an
+	 * ordered workqueue (which creates only one execution context)
+	 * should suffice all our needs.
+	 */
+	efi_rts_wq = alloc_ordered_workqueue("efi_rts_wq", 0);
+	if (!efi_rts_wq) {
+		pr_err("Creating efi_rts_wq failed, EFI runtime services disabled.\n");
+		clear_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+		return 0;
+	}
+
 	/* We register the efi directory at /sys/firmware/efi */
 	efi_kobj = kobject_create_and_add("efi", firmware_kobj);
 	if (!efi_kobj) {
diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
index ae54870b2788..aa66cbf23512 100644
--- a/drivers/firmware/efi/runtime-wrappers.c
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -1,6 +1,15 @@
 /*
  * runtime-wrappers.c - Runtime Services function call wrappers
  *
+ * Implementation summary:
+ * -----------------------
+ * 1. When user/kernel thread requests to execute efi_runtime_service(),
+ * enqueue work to efi_rts_wq.
+ * 2. Caller thread waits for completion until the work is finished
+ * because it's dependent on the return status and execution of
+ * efi_runtime_service().
+ * For instance, get_variable() and get_next_variable().
+ *
  * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * Split off from arch/x86/platform/efi/efi.c
@@ -22,6 +31,9 @@
 #include <linux/mutex.h>
 #include <linux/semaphore.h>
 #include <linux/stringify.h>
+#include <linux/workqueue.h>
+#include <linux/completion.h>
+
 #include <asm/efi.h>
 
 /*
@@ -33,6 +45,76 @@
 #define __efi_call_virt(f, args...) \
 	__efi_call_virt_pointer(efi.systab->runtime, f, args)
 
+/* efi_runtime_service() function identifiers */
+enum efi_rts_ids {
+	GET_TIME,
+	SET_TIME,
+	GET_WAKEUP_TIME,
+	SET_WAKEUP_TIME,
+	GET_VARIABLE,
+	GET_NEXT_VARIABLE,
+	SET_VARIABLE,
+	QUERY_VARIABLE_INFO,
+	GET_NEXT_HIGH_MONO_COUNT,
+	UPDATE_CAPSULE,
+	QUERY_CAPSULE_CAPS,
+};
+
+/*
+ * efi_runtime_work:	Details of EFI Runtime Service work
+ * @arg<1-5>:		EFI Runtime Service function arguments
+ * @status:		Status of executing EFI Runtime Service
+ * @efi_rts_id:		EFI Runtime Service function identifier
+ * @efi_rts_comp:	Struct used for handling completions
+ */
+struct efi_runtime_work {
+	void *arg1;
+	void *arg2;
+	void *arg3;
+	void *arg4;
+	void *arg5;
+	efi_status_t status;
+	struct work_struct work;
+	enum efi_rts_ids efi_rts_id;
+	struct completion efi_rts_comp;
+};
+
+/*
+ * efi_queue_work:	Queue efi_runtime_service() and wait until it's done
+ * @rts:		efi_runtime_service() function identifier
+ * @rts_arg<1-5>:	efi_runtime_service() function arguments
+ *
+ * Accesses to efi_runtime_services() are serialized by a binary
+ * semaphore (efi_runtime_lock) and caller waits until the work is
+ * finished, hence _only_ one work is queued at a time and the caller
+ * thread waits for completion.
+ */
+#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5)		\
+({									\
+	struct efi_runtime_work efi_rts_work;				\
+	efi_rts_work.status = EFI_ABORTED;				\
+									\
+	init_completion(&efi_rts_work.efi_rts_comp);			\
+	INIT_WORK_ONSTACK(&efi_rts_work.work, efi_call_rts);		\
+	efi_rts_work.arg1 = _arg1;					\
+	efi_rts_work.arg2 = _arg2;					\
+	efi_rts_work.arg3 = _arg3;					\
+	efi_rts_work.arg4 = _arg4;					\
+	efi_rts_work.arg5 = _arg5;					\
+	efi_rts_work.efi_rts_id = _rts;					\
+									\
+	/*								\
+	 * queue_work() returns 0 if work was already on queue,         \
+	 * _ideally_ this should never happen.                          \
+	 */								\
+	if (queue_work(efi_rts_wq, &efi_rts_work.work))			\
+		wait_for_completion(&efi_rts_work.efi_rts_comp);	\
+	else								\
+		pr_err("Failed to queue work to efi_rts_wq.\n");	\
+									\
+	efi_rts_work.status;						\
+})
+
 void efi_call_virt_check_flags(unsigned long flags, const char *call)
 {
 	unsigned long cur_flags, mismatch;
@@ -90,13 +172,98 @@ void efi_call_virt_check_flags(unsigned long flags, const char *call)
  */
 static DEFINE_SEMAPHORE(efi_runtime_lock);
 
+/*
+ * Calls the appropriate efi_runtime_service() with the appropriate
+ * arguments.
+ *
+ * Semantics followed by efi_call_rts() to understand efi_runtime_work:
+ * 1. If argument was a pointer, recast it from void pointer to original
+ * pointer type.
+ * 2. If argument was a value, recast it from void pointer to original
+ * pointer type and dereference it.
+ */
+static void efi_call_rts(struct work_struct *work)
+{
+	struct efi_runtime_work *efi_rts_work;
+	void *arg1, *arg2, *arg3, *arg4, *arg5;
+	efi_status_t status = EFI_NOT_FOUND;
+
+	efi_rts_work = container_of(work, struct efi_runtime_work, work);
+	arg1 = efi_rts_work->arg1;
+	arg2 = efi_rts_work->arg2;
+	arg3 = efi_rts_work->arg3;
+	arg4 = efi_rts_work->arg4;
+	arg5 = efi_rts_work->arg5;
+
+	switch (efi_rts_work->efi_rts_id) {
+	case GET_TIME:
+		status = efi_call_virt(get_time, (efi_time_t *)arg1,
+				       (efi_time_cap_t *)arg2);
+		break;
+	case SET_TIME:
+		status = efi_call_virt(set_time, (efi_time_t *)arg1);
+		break;
+	case GET_WAKEUP_TIME:
+		status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1,
+				       (efi_bool_t *)arg2, (efi_time_t *)arg3);
+		break;
+	case SET_WAKEUP_TIME:
+		status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1,
+				       (efi_time_t *)arg2);
+		break;
+	case GET_VARIABLE:
+		status = efi_call_virt(get_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, (u32 *)arg3,
+				       (unsigned long *)arg4, (void *)arg5);
+		break;
+	case GET_NEXT_VARIABLE:
+		status = efi_call_virt(get_next_variable, (unsigned long *)arg1,
+				       (efi_char16_t *)arg2,
+				       (efi_guid_t *)arg3);
+		break;
+	case SET_VARIABLE:
+		status = efi_call_virt(set_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, *(u32 *)arg3,
+				       *(unsigned long *)arg4, (void *)arg5);
+		break;
+	case QUERY_VARIABLE_INFO:
+		status = efi_call_virt(query_variable_info, *(u32 *)arg1,
+				       (u64 *)arg2, (u64 *)arg3, (u64 *)arg4);
+		break;
+	case GET_NEXT_HIGH_MONO_COUNT:
+		status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1);
+		break;
+	case UPDATE_CAPSULE:
+		status = efi_call_virt(update_capsule,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2,
+				       *(unsigned long *)arg3);
+		break;
+	case QUERY_CAPSULE_CAPS:
+		status = efi_call_virt(query_capsule_caps,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2, (u64 *)arg3,
+				       (int *)arg4);
+		break;
+	default:
+		/*
+		 * Ideally, we should never reach here because a caller of this
+		 * function should have put the right efi_runtime_service()
+		 * function identifier into efi_rts_work->efi_rts_id
+		 */
+		pr_err("Requested executing invalid EFI Runtime Service.\n");
+	}
+	efi_rts_work->status = status;
+	complete(&efi_rts_work->efi_rts_comp);
+}
+
 static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_time, tm, tc);
+	status = efi_queue_work(GET_TIME, tm, tc, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -107,7 +274,7 @@ static efi_status_t virt_efi_set_time(efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_time, tm);
+	status = efi_queue_work(SET_TIME, tm, NULL, NULL, NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -120,7 +287,8 @@ static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_wakeup_time, enabled, pending, tm);
+	status = efi_queue_work(GET_WAKEUP_TIME, enabled, pending, tm, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -131,7 +299,8 @@ static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_wakeup_time, enabled, tm);
+	status = efi_queue_work(SET_WAKEUP_TIME, &enabled, tm, NULL, NULL,
+				NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -146,8 +315,8 @@ static efi_status_t virt_efi_get_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(GET_VARIABLE, name, vendor, attr, data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -160,7 +329,8 @@ static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_variable, name_size, name, vendor);
+	status = efi_queue_work(GET_NEXT_VARIABLE, name_size, name, vendor,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -175,8 +345,8 @@ static efi_status_t virt_efi_set_variable(efi_char16_t *name,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
-			       data);
+	status = efi_queue_work(SET_VARIABLE, name, vendor, &attr, &data_size,
+				data);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -210,8 +380,8 @@ static efi_status_t virt_efi_query_variable_info(u32 attr,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_variable_info, attr, storage_space,
-			       remaining_space, max_variable_size);
+	status = efi_queue_work(QUERY_VARIABLE_INFO, &attr, storage_space,
+				remaining_space, max_variable_size, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -242,7 +412,8 @@ static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(get_next_high_mono_count, count);
+	status = efi_queue_work(GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -272,7 +443,8 @@ static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(update_capsule, capsules, count, sg_list);
+	status = efi_queue_work(UPDATE_CAPSULE, capsules, &count, &sg_list,
+				NULL, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
@@ -289,8 +461,8 @@ static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
 
 	if (down_interruptible(&efi_runtime_lock))
 		return EFI_ABORTED;
-	status = efi_call_virt(query_capsule_caps, capsules, count, max_size,
-			       reset_type);
+	status = efi_queue_work(QUERY_CAPSULE_CAPS, capsules, &count,
+				max_size, reset_type, NULL);
 	up(&efi_runtime_lock);
 	return status;
 }
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 56add823f190..8ba0cdd244b2 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1651,4 +1651,7 @@ struct linux_efi_tpm_eventlog {
 
 extern int efi_tpm_eventlog_init(void);
 
+/* Workqueue to queue EFI Runtime Services */
+extern struct workqueue_struct *efi_rts_wq;
+
 #endif /* _LINUX_EFI_H */
-- 
cgit v1.2.3


From 7bb497092a34a2bbb16bad5385a0487dee18a769 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 11:40:36 +0200
Subject: efi/cper: Avoid using get_seconds()

get_seconds() is deprecated because of the 32-bit time overflow
in y2038/y2106 on 32-bit architectures. The way it is used in
cper_next_record_id() causes an overflow in 2106 when unsigned UTC
seconds overflow, even on 64-bit architectures.

This starts using ktime_get_real_seconds() to give us more than 32 bits
of timestamp on all architectures, and then changes the algorithm to use
39 bits for the timestamp after the y2038 wrap date, plus an always-1
bit at the top. This gives us another 127 epochs of 136 years, with
strictly monotonically increasing sequence numbers across boots.

This is almost certainly overkill, but seems better than just extending
the deadline from 2038 to 2106.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-5-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/cper.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index 3bf0dca378a6..b73fc4cab083 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -48,8 +48,21 @@ u64 cper_next_record_id(void)
 {
 	static atomic64_t seq;
 
-	if (!atomic64_read(&seq))
-		atomic64_set(&seq, ((u64)get_seconds()) << 32);
+	if (!atomic64_read(&seq)) {
+		time64_t time = ktime_get_real_seconds();
+
+		/*
+		 * This code is unlikely to still be needed in year 2106,
+		 * but just in case, let's use a few more bits for timestamps
+		 * after y2038 to be sure they keep increasing monotonically
+		 * for the next few hundred years...
+		 */
+		if (time < 0x80000000)
+			atomic64_set(&seq, (ktime_get_real_seconds()) << 32);
+		else
+			atomic64_set(&seq, 0x8000000000000000ull |
+					   ktime_get_real_seconds() << 24);
+	}
 
 	return atomic64_inc_return(&seq);
 }
-- 
cgit v1.2.3


From f5dcc214aae29a68b37b2b4183f7171724e7b02d Mon Sep 17 00:00:00 2001
From: Sai Praneeth <sai.praneeth.prakhya@intel.com>
Date: Wed, 11 Jul 2018 11:40:37 +0200
Subject: efi: Remove the declaration of efi_late_init() as the function is
 unused

The following commit:

  7b0a911478c74 ("efi/x86: Move the EFI BGRT init code to early init code")

... removed the implementation and all the references to
efi_late_init() but the function is still declared at
include/linux/efi.h.

Hence, remove the unnecessary declaration.

Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-6-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/efi.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/efi.h b/include/linux/efi.h
index 8ba0cdd244b2..e190652f5ef9 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -988,14 +988,12 @@ extern void efi_memmap_walk (efi_freemem_callback_t callback, void *arg);
 extern void efi_gettimeofday (struct timespec64 *ts);
 extern void efi_enter_virtual_mode (void);	/* switch EFI to virtual mode, if possible */
 #ifdef CONFIG_X86
-extern void efi_late_init(void);
 extern void efi_free_boot_services(void);
 extern efi_status_t efi_query_variable_store(u32 attributes,
 					     unsigned long size,
 					     bool nonblocking);
 extern void efi_find_mirror(void);
 #else
-static inline void efi_late_init(void) {}
 static inline void efi_free_boot_services(void) {}
 
 static inline efi_status_t efi_query_variable_store(u32 attributes,
-- 
cgit v1.2.3


From 3d7ee348aa4127a7893c11261da9b76371a970e6 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Wed, 11 Jul 2018 11:40:38 +0200
Subject: efi/libstub/arm: Add opt-in Kconfig option for the DTB loader

There are various ways a platform can provide a device tree binary
to the kernel, with different levels of sophistication:

- ideally, the UEFI firmware, which is tightly coupled with the
  platform, provides a device tree image directly as a UEFI
  configuration table, and typically permits the contents to be
  manipulated either via menu options or via UEFI environment
  variables that specify a replacement image,

- GRUB for ARM has a 'devicetree' directive which allows a device
  tree image to be loaded from any location accessible to GRUB, and
  supersede the one provided by the firmware,

- the EFI stub implements a dtb= command line option that allows a
  device tree image to be loaded from a file residing in the same
  file system as the one the kernel image was loaded from.

The dtb= command line option was never intended to be more than a
development feature, to allow the other options to be implemented
in parallel. So let's make it an opt-in feature that is disabled
by default, but can be re-enabled at will.

Note that we already disable the dtb= command line option when we
detect that we are running with UEFI Secure Boot enabled.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Alexander Graf <agraf@suse.de>
Acked-by: Leif Lindholm <leif.lindholm@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-7-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/Kconfig            | 12 ++++++++++++
 drivers/firmware/efi/libstub/arm-stub.c |  7 ++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index 781a4a337557..d8e159feb573 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -87,6 +87,18 @@ config EFI_RUNTIME_WRAPPERS
 config EFI_ARMSTUB
 	bool
 
+config EFI_ARMSTUB_DTB_LOADER
+	bool "Enable the DTB loader"
+	depends on EFI_ARMSTUB
+	help
+	  Select this config option to add support for the dtb= command
+	  line parameter, allowing a device tree blob to be loaded into
+	  memory from the EFI System Partition by the stub.
+
+	  The device tree is typically provided by the platform or by
+	  the bootloader, so this option is mostly for development
+	  purposes only.
+
 config EFI_BOOTLOADER_CONTROL
 	tristate "EFI Bootloader Control"
 	depends on EFI_VARS
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index 01a9d78ee415..c98b1856fc3d 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -202,9 +202,10 @@ unsigned long efi_entry(void *handle, efi_system_table_t *sys_table,
 	 * 'dtb=' unless UEFI Secure Boot is disabled.  We assume that secure
 	 * boot is enabled if we can't determine its state.
 	 */
-	if (secure_boot != efi_secureboot_mode_disabled &&
-	    strstr(cmdline_ptr, "dtb=")) {
-		pr_efi(sys_table, "Ignoring DTB from command line.\n");
+	if (!IS_ENABLED(CONFIG_EFI_ARMSTUB_DTB_LOADER) ||
+	     secure_boot != efi_secureboot_mode_disabled) {
+		if (strstr(cmdline_ptr, "dtb="))
+			pr_efi(sys_table, "Ignoring DTB from command line.\n");
 	} else {
 		status = handle_cmdline_files(sys_table, image, cmdline_ptr,
 					      "dtb=",
-- 
cgit v1.2.3


From 7e1550b8f2081cccdfa9f1cf1e54cbc4d720af7f Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Wed, 11 Jul 2018 11:40:39 +0200
Subject: efi: Drop type and attribute checks in efi_mem_desc_lookup()

The current implementation of efi_mem_desc_lookup() includes the
following check on the memory descriptor it returns:

    if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
        md->type != EFI_BOOT_SERVICES_DATA &&
        md->type != EFI_RUNTIME_SERVICES_DATA) {
            continue;
    }

This means that only EfiBootServicesData or EfiRuntimeServicesData
regions are considered, or any other region type provided that it
has the EFI_MEMORY_RUNTIME attribute set.

Given what the name of the function implies, and the fact that any
physical address can be described in the UEFI memory map only a single
time, it does not make sense to impose this condition in the body of the
loop, but instead, should be imposed by the caller depending on the value
that is returned to it.

Two such callers exist at the moment:

- The BGRT code when running on x86, via efi_mem_reserve() and
  efi_arch_mem_reserve(). In this case, the region is already known to
  be EfiBootServicesData, and so the check is redundant.

- The ESRT handling code which introduced this function, which calls it
  both directly from efi_esrt_init() and again via efi_mem_reserve() and
  efi_arch_mem_reserve() [on x86].

So let's move this check into the callers instead. This preserves the
current behavior both for BGRT and ESRT handling, and allows the lookup
routine to be reused by other [upcoming] users that don't have this
limitation.

In the ESRT case, keep the entire condition, so that platforms that
deviate from the UEFI spec and use something other than
EfiBootServicesData for the ESRT table will keep working as before.

For x86's efi_arch_mem_reserve() implementation, limit the type to
EfiBootServicesData, since it is the only type the reservation code
expects to operate on in the first place.

While we're at it, drop the __init annotation so that drivers can use it
as well.

Tested-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-8-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/platform/efi/quirks.c | 3 ++-
 drivers/firmware/efi/efi.c     | 8 +-------
 drivers/firmware/efi/esrt.c    | 5 ++++-
 3 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c
index 6af39dc40325..844d31cb8a0c 100644
--- a/arch/x86/platform/efi/quirks.c
+++ b/arch/x86/platform/efi/quirks.c
@@ -248,7 +248,8 @@ void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size)
 	int num_entries;
 	void *new;
 
-	if (efi_mem_desc_lookup(addr, &md)) {
+	if (efi_mem_desc_lookup(addr, &md) ||
+	    md.type != EFI_BOOT_SERVICES_DATA) {
 		pr_err("Failed to lookup EFI memory descriptor for %pa\n", &addr);
 		return;
 	}
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 1379a375dfa8..d8a33a781a57 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -402,7 +402,7 @@ subsys_initcall(efisubsys_init);
  * and if so, populate the supplied memory descriptor with the appropriate
  * data.
  */
-int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
+int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 {
 	efi_memory_desc_t *md;
 
@@ -420,12 +420,6 @@ int __init efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md)
 		u64 size;
 		u64 end;
 
-		if (!(md->attribute & EFI_MEMORY_RUNTIME) &&
-		    md->type != EFI_BOOT_SERVICES_DATA &&
-		    md->type != EFI_RUNTIME_SERVICES_DATA) {
-			continue;
-		}
-
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
 		if (phys_addr >= md->phys_addr && phys_addr < end) {
diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 1ab80e06e7c5..375a77c1c6e5 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -250,7 +250,10 @@ void __init efi_esrt_init(void)
 		return;
 
 	rc = efi_mem_desc_lookup(efi.esrt, &md);
-	if (rc < 0) {
+	if (rc < 0 ||
+	    (!(md.attribute & EFI_MEMORY_RUNTIME) &&
+	     md.type != EFI_BOOT_SERVICES_DATA &&
+	     md.type != EFI_RUNTIME_SERVICES_DATA)) {
 		pr_warn("ESRT header is not in the memory map.\n");
 		return;
 	}
-- 
cgit v1.2.3


From 38ac0287b7f4f3922e25fd8f81db67f2c13d16bb Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Wed, 11 Jul 2018 11:40:40 +0200
Subject: fbdev/efifb: Honour UEFI memory map attributes when mapping the FB

If the framebuffer address provided by the Graphics Output Protocol
(GOP) is covered by the UEFI memory map, it will tell us which memory
attributes are permitted when mapping this region. In some cases,
(KVM guest on ARM), violating this will result in loss of coherency,
which means that updates sent to the framebuffer by the guest will
not be observeable by the host, and the emulated display simply does
not work.

So if the memory map contains such a description, take the attributes
field into account, and add support for creating WT or WB mappings of
the framebuffer region.

Tested-by: Laszlo Ersek <lersek@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180711094040.12506-9-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/video/fbdev/efifb.c | 51 ++++++++++++++++++++++++++++++++++++---------
 1 file changed, 41 insertions(+), 10 deletions(-)

diff --git a/drivers/video/fbdev/efifb.c b/drivers/video/fbdev/efifb.c
index 46a4484e3da7..c6f78d27947b 100644
--- a/drivers/video/fbdev/efifb.c
+++ b/drivers/video/fbdev/efifb.c
@@ -20,7 +20,7 @@
 #include <drm/drm_connector.h>  /* For DRM_MODE_PANEL_ORIENTATION_* */
 
 static bool request_mem_succeeded = false;
-static bool nowc = false;
+static u64 mem_flags = EFI_MEMORY_WC | EFI_MEMORY_UC;
 
 static struct fb_var_screeninfo efifb_defined = {
 	.activate		= FB_ACTIVATE_NOW,
@@ -68,8 +68,12 @@ static int efifb_setcolreg(unsigned regno, unsigned red, unsigned green,
 
 static void efifb_destroy(struct fb_info *info)
 {
-	if (info->screen_base)
-		iounmap(info->screen_base);
+	if (info->screen_base) {
+		if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+			iounmap(info->screen_base);
+		else
+			memunmap(info->screen_base);
+	}
 	if (request_mem_succeeded)
 		release_mem_region(info->apertures->ranges[0].base,
 				   info->apertures->ranges[0].size);
@@ -104,7 +108,7 @@ static int efifb_setup(char *options)
 			else if (!strncmp(this_opt, "width:", 6))
 				screen_info.lfb_width = simple_strtoul(this_opt+6, NULL, 0);
 			else if (!strcmp(this_opt, "nowc"))
-				nowc = true;
+				mem_flags &= ~EFI_MEMORY_WC;
 		}
 	}
 
@@ -164,6 +168,7 @@ static int efifb_probe(struct platform_device *dev)
 	unsigned int size_remap;
 	unsigned int size_total;
 	char *option = NULL;
+	efi_memory_desc_t md;
 
 	if (screen_info.orig_video_isVGA != VIDEO_TYPE_EFI || pci_dev_disabled)
 		return -ENODEV;
@@ -272,12 +277,35 @@ static int efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	if (nowc)
-		info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
-	else
-		info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
+	if (!efi_mem_desc_lookup(efifb_fix.smem_start, &md)) {
+		if ((efifb_fix.smem_start + efifb_fix.smem_len) >
+		    (md.phys_addr + (md.num_pages << EFI_PAGE_SHIFT))) {
+			pr_err("efifb: video memory @ 0x%lx spans multiple EFI memory regions\n",
+			       efifb_fix.smem_start);
+			err = -EIO;
+			goto err_release_fb;
+		}
+		/*
+		 * If the UEFI memory map covers the efifb region, we may only
+		 * remap it using the attributes the memory map prescribes.
+		 */
+		mem_flags |= EFI_MEMORY_WT | EFI_MEMORY_WB;
+		mem_flags &= md.attribute;
+	}
+	if (mem_flags & EFI_MEMORY_WC)
+		info->screen_base = ioremap_wc(efifb_fix.smem_start,
+					       efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_UC)
+		info->screen_base = ioremap(efifb_fix.smem_start,
+					    efifb_fix.smem_len);
+	else if (mem_flags & EFI_MEMORY_WT)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WT);
+	else if (mem_flags & EFI_MEMORY_WB)
+		info->screen_base = memremap(efifb_fix.smem_start,
+					     efifb_fix.smem_len, MEMREMAP_WB);
 	if (!info->screen_base) {
-		pr_err("efifb: abort, cannot ioremap video memory 0x%x @ 0x%lx\n",
+		pr_err("efifb: abort, cannot remap video memory 0x%x @ 0x%lx\n",
 			efifb_fix.smem_len, efifb_fix.smem_start);
 		err = -EIO;
 		goto err_release_fb;
@@ -371,7 +399,10 @@ err_fb_dealoc:
 err_groups:
 	sysfs_remove_groups(&dev->dev.kobj, efifb_groups);
 err_unmap:
-	iounmap(info->screen_base);
+	if (mem_flags & (EFI_MEMORY_UC | EFI_MEMORY_WC))
+		iounmap(info->screen_base);
+	else
+		memunmap(info->screen_base);
 err_release_fb:
 	framebuffer_release(info);
 err_release_mem:
-- 
cgit v1.2.3


From f1e37e3101ee74006a05a290af58a065a838549f Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Sat, 14 Jul 2018 13:29:24 +0200
Subject: net: mvpp2: switch to SPDX identifiers

Use the appropriate SPDX license identifiers and drop the license text.
This patch is only cosmetic.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h      | 5 +----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c  | 5 +----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h  | 5 +----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 5 +----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c  | 5 +----
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h  | 5 +----
 6 files changed, 6 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 749d9720bf5e..3e470d6fcf64 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Definitions for Marvell PPv2 network controller for Armada 375 SoC.
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 #ifndef _MVPP2_H_
 #define _MVPP2_H_
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 723d0ba6f78d..125466c66f1a 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * RSS and Classifier helpers for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include "mvpp2.h"
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 151d791a91b6..e159489a20ea 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * RSS and Classifier definitions for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #ifndef _MVPP2_CLS_H_
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 2283be12d700..2d690b082b89 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Driver for Marvell PPv2 network controller for Armada 375 SoC.
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/acpi.h>
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index acf9f78d5f80..2a8d25139a8f 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Header Parser helpers for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index 368e90b54477..eb81db1a301f 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Header Parser definitions for Marvell PPv2 Network Controller
  *
  * Copyright (C) 2014 Marvell
  *
  * Marcin Wojtas <mw@semihalf.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 #ifndef _MVPP2_PRS_H_
 #define _MVPP2_PRS_H_
-- 
cgit v1.2.3


From 21da57a23125a072e6ab2bb6c9bea5e02e01d1f5 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 14 Jul 2018 13:29:25 +0200
Subject: net: mvpp2: add a debugfs interface for the Header Parser

Marvell PPv2 Packer Header Parser has a TCAM based filter, that is not
trivial to configure and debug. Being able to dump TCAM entries from
userspace can be really helpful to help development of new features
and debug existing ones.

This commit adds a basic debugfs interface for the PPv2 driver, focusing
on TCAM related features.

<mnt>/mvpp2/ --- f2000000.ethernet
              \- f4000000.ethernet --- parser --- 000 ...
                                    |          \- 001
                                    |          \- ...
                                    |          \- 255 --- ai
                                    |                  \- header_data
                                    |                  \- lookup_id
                                    |                  \- sram
                                    |                  \- valid
                                    \- eth1 ...
                                    \- eth2 --- mac_filter
                                             \- parser_entries
                                             \- vid_filter

There's one directory per PPv2 instance, named after pdev->name to make
sure names are uniques. In each of these directories, there's :

 - one directory per interface on the controller, each containing :

   - "mac_filter", which lists all filtered addresses for this port
     (based on TCAM, not on the kernel's uc / mc lists)

   - "parser_entries", which lists the indices of all valid TCAM
      entries that have this port in their port map

   - "vid_filter", which lists the vids allowed on this port, based on
     TCAM

 - one "parser" directory (the parser is common to all ports), containing :

   - one directory per TCAM entry (256 of them, from 0 to 255), each
     containing :

     - "ai" : Contains the 1 byte Additional Info field from TCAM, and

     - "header_data" : Contains the 8 bytes Header Data extracted from
       the packet

     - "lookup_id" : Contains the 4 bits LU_ID

     - "sram" : contains the raw SRAM data, which is the result of the TCAM
		lookup. This readonly at the moment.

     - "valid" : Indicates if the entry is valid of not.

All entries are read-only, and everything is output in hex form.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/Makefile        |   2 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h         |   7 +
 drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 344 +++++++++++++++++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c    |   4 +
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c     |  12 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h     |   9 +
 6 files changed, 371 insertions(+), 7 deletions(-)
 create mode 100644 drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c

diff --git a/drivers/net/ethernet/marvell/mvpp2/Makefile b/drivers/net/ethernet/marvell/mvpp2/Makefile
index 4d11dd9e3246..51f65a202c6e 100644
--- a/drivers/net/ethernet/marvell/mvpp2/Makefile
+++ b/drivers/net/ethernet/marvell/mvpp2/Makefile
@@ -4,4 +4,4 @@
 #
 obj-$(CONFIG_MVPP2) := mvpp2.o
 
-mvpp2-objs := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o
+mvpp2-objs := mvpp2_main.o mvpp2_prs.o mvpp2_cls.o mvpp2_debugfs.o
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 3e470d6fcf64..439f14192b08 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -746,6 +746,9 @@ struct mvpp2 {
 	/* Workqueue to gather hardware statistics */
 	char queue_name[30];
 	struct workqueue_struct *stats_queue;
+
+	/* Debugfs root entry */
+	struct dentry *dbgfs_dir;
 };
 
 struct mvpp2_pcpu_stats {
@@ -1089,4 +1092,8 @@ u32 mvpp2_percpu_read(struct mvpp2 *priv, int cpu, u32 offset);
 void mvpp2_percpu_write_relaxed(struct mvpp2 *priv, int cpu, u32 offset,
 				u32 data);
 
+void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name);
+
+void mvpp2_dbgfs_cleanup(struct mvpp2 *priv);
+
 #endif
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
new file mode 100644
index 000000000000..e8a242b56519
--- /dev/null
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for Marvell PPv2 network controller for Armada 375 SoC.
+ *
+ * Copyright (C) 2018 Marvell
+ */
+
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/debugfs.h>
+
+#include "mvpp2.h"
+#include "mvpp2_prs.h"
+
+struct mvpp2_dbgfs_prs_entry {
+	int tid;
+	struct mvpp2 *priv;
+};
+
+static int mvpp2_dbgfs_port_vid_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	unsigned char byte[2], enable[2];
+	struct mvpp2 *priv = port->priv;
+	struct mvpp2_prs_entry pe;
+	unsigned long pmap;
+	u16 rvid;
+	int tid;
+
+	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
+	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
+		mvpp2_prs_init_from_hw(priv, &pe, tid);
+
+		pmap = mvpp2_prs_tcam_port_map_get(&pe);
+
+		if (!priv->prs_shadow[tid].valid)
+			continue;
+
+		if (!test_bit(port->id, &pmap))
+			continue;
+
+		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
+		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
+
+		rvid = ((byte[0] & 0xf) << 8) + byte[1];
+
+		seq_printf(s, "%u\n", rvid);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_vid);
+
+static int mvpp2_dbgfs_port_parser_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2 *priv = port->priv;
+	struct mvpp2_prs_entry pe;
+	unsigned long pmap;
+	int i;
+
+	for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) {
+		mvpp2_prs_init_from_hw(port->priv, &pe, i);
+
+		pmap = mvpp2_prs_tcam_port_map_get(&pe);
+		if (priv->prs_shadow[i].valid && test_bit(port->id, &pmap))
+			seq_printf(s, "%03d\n", i);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_parser);
+
+static int mvpp2_dbgfs_filter_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2 *priv = port->priv;
+	struct mvpp2_prs_entry pe;
+	unsigned long pmap;
+	int index, tid;
+
+	for (tid = MVPP2_PE_MAC_RANGE_START;
+	     tid <= MVPP2_PE_MAC_RANGE_END; tid++) {
+		unsigned char da[ETH_ALEN], da_mask[ETH_ALEN];
+
+		if (!priv->prs_shadow[tid].valid ||
+		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_MAC ||
+		    priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF)
+			continue;
+
+		mvpp2_prs_init_from_hw(priv, &pe, tid);
+
+		pmap = mvpp2_prs_tcam_port_map_get(&pe);
+
+		/* We only want entries active on this port */
+		if (!test_bit(port->id, &pmap))
+			continue;
+
+		/* Read mac addr from entry */
+		for (index = 0; index < ETH_ALEN; index++)
+			mvpp2_prs_tcam_data_byte_get(&pe, index, &da[index],
+						     &da_mask[index]);
+
+		seq_printf(s, "%pM\n", da);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_filter);
+
+static int mvpp2_dbgfs_prs_lu_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2 *priv = entry->priv;
+
+	seq_printf(s, "%x\n", priv->prs_shadow[entry->tid].lu);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_lu);
+
+static int mvpp2_dbgfs_prs_pmap_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+	unsigned int pmap;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	pmap = mvpp2_prs_tcam_port_map_get(&pe);
+	pmap &= MVPP2_PRS_PORT_MASK;
+
+	seq_printf(s, "%02x\n", pmap);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_pmap);
+
+static int mvpp2_dbgfs_prs_ai_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+	unsigned char ai, ai_mask;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	ai = pe.tcam[MVPP2_PRS_TCAM_AI_WORD] & MVPP2_PRS_AI_MASK;
+	ai_mask = (pe.tcam[MVPP2_PRS_TCAM_AI_WORD] >> 16) & MVPP2_PRS_AI_MASK;
+
+	seq_printf(s, "%02x %02x\n", ai, ai_mask);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_ai);
+
+static int mvpp2_dbgfs_prs_hdata_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+	unsigned char data[8], mask[8];
+	int i;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	for (i = 0; i < 8; i++)
+		mvpp2_prs_tcam_data_byte_get(&pe, i, &data[i], &mask[i]);
+
+	seq_printf(s, "%*phN %*phN\n", 8, data, 8, mask);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_hdata);
+
+static int mvpp2_dbgfs_prs_sram_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2_prs_entry pe;
+
+	mvpp2_prs_init_from_hw(entry->priv, &pe, entry->tid);
+
+	seq_printf(s, "%*phN\n", 14, pe.sram);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_sram);
+
+static int mvpp2_dbgfs_prs_valid_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	struct mvpp2 *priv = entry->priv;
+	int tid = entry->tid;
+
+	seq_printf(s, "%d\n", priv->prs_shadow[tid].valid ? 1 : 0);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_prs_valid_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mvpp2_dbgfs_prs_valid_show, inode->i_private);
+}
+
+static int mvpp2_dbgfs_prs_valid_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct mvpp2_dbgfs_prs_entry *entry = seq->private;
+
+	kfree(entry);
+	return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_prs_valid_fops = {
+	.open = mvpp2_dbgfs_prs_valid_open,
+	.read = seq_read,
+	.release = mvpp2_dbgfs_prs_valid_release,
+};
+
+static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent,
+				      struct mvpp2 *priv, int tid)
+{
+	struct mvpp2_dbgfs_prs_entry *entry;
+	struct dentry *prs_entry_dir;
+	char prs_entry_name[10];
+
+	if (tid >= MVPP2_PRS_TCAM_SRAM_SIZE)
+		return -EINVAL;
+
+	sprintf(prs_entry_name, "%03d", tid);
+
+	prs_entry_dir = debugfs_create_dir(prs_entry_name, parent);
+	if (!prs_entry_dir)
+		return -ENOMEM;
+
+	/* The 'valid' entry's ops will free that */
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->tid = tid;
+	entry->priv = priv;
+
+	/* Create each attr */
+	debugfs_create_file("sram", 0444, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_sram_fops);
+
+	debugfs_create_file("valid", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_valid_fops);
+
+	debugfs_create_file("lookup_id", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_lu_fops);
+
+	debugfs_create_file("ai", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_ai_fops);
+
+	debugfs_create_file("header_data", 0644, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_hdata_fops);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_prs_init(struct dentry *parent, struct mvpp2 *priv)
+{
+	struct dentry *prs_dir;
+	int i, ret;
+
+	prs_dir = debugfs_create_dir("parser", parent);
+	if (!prs_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) {
+		ret = mvpp2_dbgfs_prs_entry_init(prs_dir, priv, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_port_init(struct dentry *parent,
+				 struct mvpp2_port *port)
+{
+	struct dentry *port_dir;
+
+	port_dir = debugfs_create_dir(port->dev->name, parent);
+	if (IS_ERR(port_dir))
+		return PTR_ERR(port_dir);
+
+	debugfs_create_file("parser_entries", 0444, port_dir, port,
+			    &mvpp2_dbgfs_port_parser_fops);
+
+	debugfs_create_file("mac_filter", 0444, port_dir, port,
+			    &mvpp2_dbgfs_filter_fops);
+
+	debugfs_create_file("vid_filter", 0444, port_dir, port,
+			    &mvpp2_dbgfs_port_vid_fops);
+
+	return 0;
+}
+
+void mvpp2_dbgfs_cleanup(struct mvpp2 *priv)
+{
+	debugfs_remove_recursive(priv->dbgfs_dir);
+}
+
+void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name)
+{
+	struct dentry *mvpp2_dir, *mvpp2_root;
+	int ret, i;
+
+	mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL);
+	if (!mvpp2_root) {
+		mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL);
+		if (IS_ERR(mvpp2_root))
+			return;
+	}
+
+	mvpp2_dir = debugfs_create_dir(name, mvpp2_root);
+	if (IS_ERR(mvpp2_dir))
+		return;
+
+	priv->dbgfs_dir = mvpp2_dir;
+
+	ret = mvpp2_dbgfs_prs_init(mvpp2_dir, priv);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < priv->port_count; i++) {
+		ret = mvpp2_dbgfs_port_init(mvpp2_dir, priv->port_list[i]);
+		if (ret)
+			goto err;
+	}
+
+	return;
+err:
+	mvpp2_dbgfs_cleanup(priv);
+}
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 2d690b082b89..32d785b616e1 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -5289,6 +5289,8 @@ static int mvpp2_probe(struct platform_device *pdev)
 		goto err_port_probe;
 	}
 
+	mvpp2_dbgfs_init(priv, pdev->name);
+
 	platform_set_drvdata(pdev, priv);
 	return 0;
 
@@ -5322,6 +5324,8 @@ static int mvpp2_remove(struct platform_device *pdev)
 	struct fwnode_handle *port_fwnode;
 	int i = 0;
 
+	mvpp2_dbgfs_cleanup(priv);
+
 	flush_workqueue(priv->stats_queue);
 	destroy_workqueue(priv->stats_queue);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 2a8d25139a8f..f133d820f0fa 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -43,8 +43,8 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 }
 
 /* Initialize tcam entry from hw */
-static int mvpp2_prs_init_from_hw(struct mvpp2 *priv,
-				  struct mvpp2_prs_entry *pe, int tid)
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid)
 {
 	int i;
 
@@ -126,7 +126,7 @@ static void mvpp2_prs_tcam_port_map_set(struct mvpp2_prs_entry *pe,
 }
 
 /* Obtain port map from tcam sw entry */
-static unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
+unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe)
 {
 	return (~pe->tcam[MVPP2_PRS_TCAM_PORT_WORD] >> 24) & MVPP2_PRS_PORT_MASK;
 }
@@ -145,9 +145,9 @@ static void mvpp2_prs_tcam_data_byte_set(struct mvpp2_prs_entry *pe,
 }
 
 /* Get byte of data and its enable bits from tcam sw entry */
-static void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
-					 unsigned int offs, unsigned char *byte,
-					 unsigned char *enable)
+void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
+				  unsigned int offs, unsigned char *byte,
+				  unsigned char *enable)
 {
 	int pos = MVPP2_PRS_BYTE_IN_WORD(offs) * BITS_PER_BYTE;
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index eb81db1a301f..67b67ccb387d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -294,6 +294,15 @@ struct mvpp2_prs_shadow {
 
 int mvpp2_prs_default_init(struct platform_device *pdev, struct mvpp2 *priv);
 
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid);
+
+unsigned int mvpp2_prs_tcam_port_map_get(struct mvpp2_prs_entry *pe);
+
+void mvpp2_prs_tcam_data_byte_get(struct mvpp2_prs_entry *pe,
+				  unsigned int offs, unsigned char *byte,
+				  unsigned char *enable);
+
 int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add);
 
 int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type);
-- 
cgit v1.2.3


From 1203341cc9e858376241b65c17cf6b414b6a0837 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 14 Jul 2018 13:29:26 +0200
Subject: net: mvpp2: debugfs: add hit counter stats for Header Parser entries

One helpful feature to help debug the Header Parser TCAM filter in PPv2
is to be able to see if the entries did match something when a packet
comes in. This can be done by using the built-in hit counter for TCAM
entries.

This commit implements reading the counter, and exposing its value on
debugfs for each filter entry.

The counter is a 16-bits clear-on-read value, located at:
 .../mvpp2/<controller>/parser/XXX/hits

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h         |  3 +++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 19 +++++++++++++++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c     | 16 ++++++++++++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h     |  2 ++
 4 files changed, 40 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 439f14192b08..70b3e9cd0d84 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -64,6 +64,9 @@
 #define MVPP2_PRS_SRAM_DATA_REG(idx)		(0x1204 + (idx) * 4)
 #define MVPP2_PRS_TCAM_CTRL_REG			0x1230
 #define     MVPP2_PRS_TCAM_EN_MASK		BIT(0)
+#define MVPP2_PRS_TCAM_HIT_IDX_REG		0x1240
+#define MVPP2_PRS_TCAM_HIT_CNT_REG		0x1244
+#define     MVPP2_PRS_TCAM_HIT_CNT_MASK		GENMASK(15, 0)
 
 /* RSS Registers */
 #define MVPP22_RSS_INDEX			0x1500
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
index e8a242b56519..af8fb93a8ae2 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -192,6 +192,22 @@ static int mvpp2_dbgfs_prs_sram_show(struct seq_file *s, void *unused)
 
 DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_sram);
 
+static int mvpp2_dbgfs_prs_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_prs_entry *entry = s->private;
+	int val;
+
+	val = mvpp2_prs_hits(entry->priv, entry->tid);
+	if (val < 0)
+		return val;
+
+	seq_printf(s, "%d\n", val);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_prs_hits);
+
 static int mvpp2_dbgfs_prs_valid_show(struct seq_file *s, void *unused)
 {
 	struct mvpp2_dbgfs_prs_entry *entry = s->private;
@@ -263,6 +279,9 @@ static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent,
 	debugfs_create_file("header_data", 0644, prs_entry_dir, entry,
 			    &mvpp2_dbgfs_prs_hdata_fops);
 
+	debugfs_create_file("hits", 0444, prs_entry_dir, entry,
+			    &mvpp2_dbgfs_prs_hits_fops);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index f133d820f0fa..392fd895f278 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -2478,3 +2478,19 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 
 	return 0;
 }
+
+int mvpp2_prs_hits(struct mvpp2 *priv, int index)
+{
+	u32 val;
+
+	if (index > MVPP2_PRS_TCAM_SRAM_SIZE)
+		return -EINVAL;
+
+	mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index);
+
+	val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG);
+
+	val &= MVPP2_PRS_TCAM_HIT_CNT_MASK;
+
+	return val;
+}
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
index 67b67ccb387d..e22f6c85d380 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.h
@@ -328,4 +328,6 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port);
 
 int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da);
 
+int mvpp2_prs_hits(struct mvpp2 *priv, int index);
+
 #endif
-- 
cgit v1.2.3


From dba1d918da025bf48f3aa004058e565db4d09886 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 14 Jul 2018 13:29:27 +0200
Subject: net: mvpp2: debugfs: add entries for classifier flows

The classifier configuration for RSS is quite complex, with several
lookup tables being used. This commit adds useful info in debugfs to
see how the different tables are configured :

Added 2 new entries in the per-port directory :

  - .../eth0/default_rxq : The default rx queue on that port
  - .../eth0/rss_enable : Indicates if RSS is enabled in the C2 entry

Added the 'flows' directory :

  It contains one entry per sub-flow. a 'sub-flow' is a unique path from
  Header Parser to the flow table. Multiple sub-flows can point to the
  same 'flow' (each flow has an id from 8 to 29, which is its index in the
  Lookup Id table) :

  - .../flows/00/...
             /01/...
             ...
             /51/id : The flow id. There are 21 unique flows. There's one
                       flow per combination of the following parameters :
                       - L4 protocol (TCP, UDP, none)
                       - L3 protocol (IPv4, IPv6)
                       - L3 parameters (Fragmented or not)
                       - L2 parameters (Vlan tag presence or not)
              .../type : The flow type. This is an even higher level flow,
                         that we manipulate with ethtool. It can be :
                         "udp4" "tcp4" "udp6" "tcp6" "ipv4" "ipv6" "other".
              .../eth0/...
              .../eth1/engine : The hash generation engine used for this
	                        flow on the given port
                  .../hash_opts : The hash generation options indicating on
                                  what data we base the hash (vlan tag, src
                                  IP, src port, etc.)

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h         |   2 +
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c     |  28 +-
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h     |  15 ++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 289 +++++++++++++++++++++
 4 files changed, 329 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 70b3e9cd0d84..af4968d7c007 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -132,8 +132,10 @@
 #define MVPP22_CLS_C2_ATTR0			0x1b64
 #define     MVPP22_CLS_C2_ATTR0_QHIGH(qh)	(((qh) & 0x1f) << 24)
 #define     MVPP22_CLS_C2_ATTR0_QHIGH_MASK	0x1f
+#define     MVPP22_CLS_C2_ATTR0_QHIGH_OFFS	24
 #define     MVPP22_CLS_C2_ATTR0_QLOW(ql)	(((ql) & 0x7) << 21)
 #define     MVPP22_CLS_C2_ATTR0_QLOW_MASK	0x7
+#define     MVPP22_CLS_C2_ATTR0_QLOW_OFFS	21
 #define MVPP22_CLS_C2_ATTR1			0x1b68
 #define MVPP22_CLS_C2_ATTR2			0x1b6c
 #define     MVPP22_CLS_C2_ATTR2_RSS_EN		BIT(30)
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 125466c66f1a..c5012fa390c8 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -322,8 +322,8 @@ static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
 		       0, 0),
 };
 
-static void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
-				struct mvpp2_cls_flow_entry *fe)
+void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+			 struct mvpp2_cls_flow_entry *fe)
 {
 	fe->index = index;
 	mvpp2_write(priv, MVPP2_CLS_FLOW_INDEX_REG, index);
@@ -342,6 +342,18 @@ static void mvpp2_cls_flow_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL2_REG,  fe->data[2]);
 }
 
+void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
+			   struct mvpp2_cls_lookup_entry *le)
+{
+	u32 val;
+
+	val = (way << MVPP2_CLS_LKP_INDEX_WAY_OFFS) | lkpid;
+	mvpp2_write(priv, MVPP2_CLS_LKP_INDEX_REG, val);
+	le->way = way;
+	le->lkpid = lkpid;
+	le->data = mvpp2_read(priv, MVPP2_CLS_LKP_TBL_REG);
+}
+
 /* Update classification lookup table register */
 static void mvpp2_cls_lookup_write(struct mvpp2 *priv,
 				   struct mvpp2_cls_lookup_entry *le)
@@ -388,6 +400,12 @@ static void mvpp2_cls_flow_eng_set(struct mvpp2_cls_flow_entry *fe,
 	fe->data[0] |= MVPP2_CLS_FLOW_TBL0_ENG(engine);
 }
 
+int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe)
+{
+	return (fe->data[0] >> MVPP2_CLS_FLOW_TBL0_OFFS) &
+		MVPP2_CLS_FLOW_TBL0_ENG_MASK;
+}
+
 static void mvpp2_cls_flow_port_id_sel(struct mvpp2_cls_flow_entry *fe,
 				       bool from_packet)
 {
@@ -554,7 +572,7 @@ static int mvpp2_flow_set_hek_fields(struct mvpp2_cls_flow_entry *fe,
 	return 0;
 }
 
-static struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
+struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow)
 {
 	if (flow >= MVPP2_N_FLOWS)
 		return NULL;
@@ -725,8 +743,8 @@ static void mvpp2_cls_c2_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP22_CLS_C2_ATTR3, c2->attr[3]);
 }
 
-static void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
-			      struct mvpp2_cls_c2_entry *c2)
+void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+		       struct mvpp2_cls_c2_entry *c2)
 {
 	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, index);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index e159489a20ea..13eae2d1b4bf 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -209,4 +209,19 @@ void mvpp2_cls_port_config(struct mvpp2_port *port);
 
 void mvpp2_cls_oversize_rxq_set(struct mvpp2_port *port);
 
+int mvpp2_cls_flow_eng_get(struct mvpp2_cls_flow_entry *fe);
+
+u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe);
+
+struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow);
+
+void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
+			 struct mvpp2_cls_flow_entry *fe);
+
+void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
+			   struct mvpp2_cls_lookup_entry *le);
+
+void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
+		       struct mvpp2_cls_c2_entry *c2);
+
 #endif
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
index af8fb93a8ae2..fc46ec81249b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -11,12 +11,207 @@
 
 #include "mvpp2.h"
 #include "mvpp2_prs.h"
+#include "mvpp2_cls.h"
 
 struct mvpp2_dbgfs_prs_entry {
 	int tid;
 	struct mvpp2 *priv;
 };
 
+struct mvpp2_dbgfs_flow_entry {
+	int flow;
+	struct mvpp2 *priv;
+};
+
+struct mvpp2_dbgfs_port_flow_entry {
+	struct mvpp2_port *port;
+	struct mvpp2_dbgfs_flow_entry *dbg_fe;
+};
+
+static int mvpp2_dbgfs_flow_type_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+	struct mvpp2_cls_flow *f;
+	const char *flow_name;
+
+	f = mvpp2_cls_flow_get(entry->flow);
+	if (!f)
+		return -EINVAL;
+
+	switch (f->flow_type) {
+	case IPV4_FLOW:
+		flow_name = "ipv4";
+		break;
+	case IPV6_FLOW:
+		flow_name = "ipv6";
+		break;
+	case TCP_V4_FLOW:
+		flow_name = "tcp4";
+		break;
+	case TCP_V6_FLOW:
+		flow_name = "tcp6";
+		break;
+	case UDP_V4_FLOW:
+		flow_name = "udp4";
+		break;
+	case UDP_V6_FLOW:
+		flow_name = "udp6";
+		break;
+	default:
+		flow_name = "other";
+	}
+
+	seq_printf(s, "%s\n", flow_name);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_flow_type_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mvpp2_dbgfs_flow_type_show, inode->i_private);
+}
+
+static int mvpp2_dbgfs_flow_type_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct mvpp2_dbgfs_flow_entry *flow_entry = seq->private;
+
+	kfree(flow_entry);
+	return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_flow_type_fops = {
+	.open = mvpp2_dbgfs_flow_type_open,
+	.read = seq_read,
+	.release = mvpp2_dbgfs_flow_type_release,
+};
+
+static int mvpp2_dbgfs_flow_id_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+	struct mvpp2_cls_flow *f;
+
+	f = mvpp2_cls_flow_get(entry->flow);
+	if (!f)
+		return -EINVAL;
+
+	seq_printf(s, "%d\n", f->flow_id);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_id);
+
+static int mvpp2_dbgfs_port_flow_hash_opt_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
+	struct mvpp2_port *port = entry->port;
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *f;
+	int flow_index;
+	u16 hash_opts;
+
+	f = mvpp2_cls_flow_get(entry->dbg_fe->flow);
+	if (!f)
+		return -EINVAL;
+
+	flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+
+	mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+	hash_opts = mvpp2_flow_get_hek_fields(&fe);
+
+	seq_printf(s, "0x%04x\n", hash_opts);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_port_flow_hash_opt_open(struct inode *inode,
+					       struct file *file)
+{
+	return single_open(file, mvpp2_dbgfs_port_flow_hash_opt_show,
+			   inode->i_private);
+}
+
+static int mvpp2_dbgfs_port_flow_hash_opt_release(struct inode *inode,
+						  struct file *file)
+{
+	struct seq_file *seq = file->private_data;
+	struct mvpp2_dbgfs_port_flow_entry *flow_entry = seq->private;
+
+	kfree(flow_entry);
+	return single_release(inode, file);
+}
+
+static const struct file_operations mvpp2_dbgfs_port_flow_hash_opt_fops = {
+	.open = mvpp2_dbgfs_port_flow_hash_opt_open,
+	.read = seq_read,
+	.release = mvpp2_dbgfs_port_flow_hash_opt_release,
+};
+
+static int mvpp2_dbgfs_port_flow_engine_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_port_flow_entry *entry = s->private;
+	struct mvpp2_port *port = entry->port;
+	struct mvpp2_cls_flow_entry fe;
+	struct mvpp2_cls_flow *f;
+	int flow_index, engine;
+
+	f = mvpp2_cls_flow_get(entry->dbg_fe->flow);
+	if (!f)
+		return -EINVAL;
+
+	flow_index = MVPP2_PORT_FLOW_HASH_ENTRY(entry->port->id, f->flow_id);
+
+	mvpp2_cls_flow_read(port->priv, flow_index, &fe);
+
+	engine = mvpp2_cls_flow_eng_get(&fe);
+
+	seq_printf(s, "%d\n", engine);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_flow_engine);
+
+static int mvpp2_dbgfs_flow_c2_rxq_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2_cls_c2_entry c2;
+	u8 qh, ql;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	qh = (c2.attr[0] >> MVPP22_CLS_C2_ATTR0_QHIGH_OFFS) &
+	     MVPP22_CLS_C2_ATTR0_QHIGH_MASK;
+
+	ql = (c2.attr[0] >> MVPP22_CLS_C2_ATTR0_QLOW_OFFS) &
+	     MVPP22_CLS_C2_ATTR0_QLOW_MASK;
+
+	seq_printf(s, "%d\n", (qh << 3 | ql));
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_rxq);
+
+static int mvpp2_dbgfs_flow_c2_enable_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	struct mvpp2_cls_c2_entry c2;
+	int enabled;
+
+	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
+
+	enabled = !!(c2.attr[2] | MVPP22_CLS_C2_ATTR2_RSS_EN);
+
+	seq_printf(s, "%d\n", enabled);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_enable);
+
 static int mvpp2_dbgfs_port_vid_show(struct seq_file *s, void *unused)
 {
 	struct mvpp2_port *port = s->private;
@@ -239,6 +434,90 @@ static const struct file_operations mvpp2_dbgfs_prs_valid_fops = {
 	.release = mvpp2_dbgfs_prs_valid_release,
 };
 
+static int mvpp2_dbgfs_flow_port_init(struct dentry *parent,
+				      struct mvpp2_port *port,
+				      struct mvpp2_dbgfs_flow_entry *entry)
+{
+	struct mvpp2_dbgfs_port_flow_entry *port_entry;
+	struct dentry *port_dir;
+
+	port_dir = debugfs_create_dir(port->dev->name, parent);
+	if (IS_ERR(port_dir))
+		return PTR_ERR(port_dir);
+
+	/* This will be freed by 'hash_opts' release op */
+	port_entry = kmalloc(sizeof(*port_entry), GFP_KERNEL);
+	if (!port_entry)
+		return -ENOMEM;
+
+	port_entry->port = port;
+	port_entry->dbg_fe = entry;
+
+	debugfs_create_file("hash_opts", 0444, port_dir, port_entry,
+			    &mvpp2_dbgfs_port_flow_hash_opt_fops);
+
+	debugfs_create_file("engine", 0444, port_dir, port_entry,
+			    &mvpp2_dbgfs_port_flow_engine_fops);
+
+	return 0;
+}
+
+static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent,
+				       struct mvpp2 *priv, int flow)
+{
+	struct mvpp2_dbgfs_flow_entry *entry;
+	struct dentry *flow_entry_dir;
+	char flow_entry_name[10];
+	int i, ret;
+
+	sprintf(flow_entry_name, "%02d", flow);
+
+	flow_entry_dir = debugfs_create_dir(flow_entry_name, parent);
+	if (!flow_entry_dir)
+		return -ENOMEM;
+
+	/* This will be freed by 'type' release op */
+	entry = kmalloc(sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->flow = flow;
+	entry->priv = priv;
+
+	debugfs_create_file("type", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_type_fops);
+
+	debugfs_create_file("id", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_id_fops);
+
+	/* Create entry for each port */
+	for (i = 0; i < priv->port_count; i++) {
+		ret = mvpp2_dbgfs_flow_port_init(flow_entry_dir,
+						 priv->port_list[i], entry);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int mvpp2_dbgfs_flow_init(struct dentry *parent, struct mvpp2 *priv)
+{
+	struct dentry *flow_dir;
+	int i, ret;
+
+	flow_dir = debugfs_create_dir("flows", parent);
+	if (!flow_dir)
+		return -ENOMEM;
+
+	for (i = 0; i < MVPP2_N_FLOWS; i++) {
+		ret = mvpp2_dbgfs_flow_entry_init(flow_dir, priv, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent,
 				      struct mvpp2 *priv, int tid)
 {
@@ -321,6 +600,12 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent,
 	debugfs_create_file("vid_filter", 0444, port_dir, port,
 			    &mvpp2_dbgfs_port_vid_fops);
 
+	debugfs_create_file("default_rxq", 0444, port_dir, port,
+			    &mvpp2_dbgfs_flow_c2_rxq_fops);
+
+	debugfs_create_file("rss_enable", 0444, port_dir, port,
+			    &mvpp2_dbgfs_flow_c2_enable_fops);
+
 	return 0;
 }
 
@@ -357,6 +642,10 @@ void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name)
 			goto err;
 	}
 
+	ret = mvpp2_dbgfs_flow_init(mvpp2_dir, priv);
+	if (ret)
+		goto err;
+
 	return;
 err:
 	mvpp2_dbgfs_cleanup(priv);
-- 
cgit v1.2.3


From f9d30d5bd57e6451345b3e021b789f629719923b Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 14 Jul 2018 13:29:28 +0200
Subject: net: mvpp2: debugfs: add classifier hit counters

The classification operations that are used for RSS make use of several
lookup tables. Having hit counters for these tables is really helpful
to determine what flows were matched by ingress traffic, and see the
path of packets among all the classifier tables.

This commit adds hit counters for the 3 tables used at the moment :

 - The decoding table (also called lookup_id table), that links flows
   identified by the Header Parser to the flow table.

   There's one entry per flow, located at :
   .../mvpp2/<controller>/flows/XX/dec_hits

   Note that there are 21 flows in the decoding table, whereas there are
   52 flows in the Header Parser. That's because there are several kind
   of traffic that will match a given flow. Reading the hit counter from
   one sub-flow will clear all hit counter that have the same flow_id.

   This also applies to the flow_hits.

 - The flow table, that contains all the different lookups to be
   performed by the classifier for each packet of a given flow. The match
   is done on the first entry of the flow sequence.

 - The C2 engine entries, that are used to assign the default rx queue,
   and enable or disable RSS for a given port.

   There's one entry per flow, located at:
   .../mvpp2/<controller>/flows/XX/flow_hits

   There is one C2 entry per port, so the c2 hit counter is located at :
   .../mvpp2/<controller>/ethX/c2_hits

All hit counter values are 16-bits clear-on-read values.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h         |  6 +++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c     | 21 +++++++++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h     |  6 +++
 drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 51 ++++++++++++++++++++++
 4 files changed, 84 insertions(+)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index af4968d7c007..67b9e81b7c02 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -124,6 +124,7 @@
 #define MVPP22_CLS_C2_TCAM_DATA3		0x1b1c
 #define MVPP22_CLS_C2_TCAM_DATA4		0x1b20
 #define     MVPP22_CLS_C2_PORT_ID(port)		((port) << 8)
+#define MVPP22_CLS_C2_HIT_CTR			0x1b50
 #define MVPP22_CLS_C2_ACT			0x1b60
 #define     MVPP22_CLS_C2_ACT_RSS_EN(act)	(((act) & 0x3) << 19)
 #define     MVPP22_CLS_C2_ACT_FWD(act)		(((act) & 0x7) << 13)
@@ -318,6 +319,11 @@
 #define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_MASK	0xff00
 #define     MVPP22_BM_ADDR_HIGH_VIRT_RLS_SHIFT	8
 
+/* Hit counters registers */
+#define MVPP2_CTRS_IDX				0x7040
+#define MVPP2_CLS_DEC_TBL_HIT_CTR		0x7700
+#define MVPP2_CLS_FLOW_TBL_HIT_CTR		0x7704
+
 /* TX Scheduler registers */
 #define MVPP2_TXP_SCHED_PORT_INDEX_REG		0x8000
 #define MVPP2_TXP_SCHED_Q_CMD_REG		0x8004
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index c5012fa390c8..efdb7a656835 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -322,6 +322,13 @@ static struct mvpp2_cls_flow cls_flows[MVPP2_N_FLOWS] = {
 		       0, 0),
 };
 
+u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index)
+{
+	mvpp2_write(priv, MVPP2_CTRS_IDX, index);
+
+	return mvpp2_read(priv, MVPP2_CLS_FLOW_TBL_HIT_CTR);
+}
+
 void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
 			 struct mvpp2_cls_flow_entry *fe)
 {
@@ -342,6 +349,13 @@ static void mvpp2_cls_flow_write(struct mvpp2 *priv,
 	mvpp2_write(priv, MVPP2_CLS_FLOW_TBL2_REG,  fe->data[2]);
 }
 
+u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index)
+{
+	mvpp2_write(priv, MVPP2_CTRS_IDX, index);
+
+	return mvpp2_read(priv, MVPP2_CLS_DEC_TBL_HIT_CTR);
+}
+
 void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
 			   struct mvpp2_cls_lookup_entry *le)
 {
@@ -859,6 +873,13 @@ void mvpp2_cls_port_config(struct mvpp2_port *port)
 	mvpp2_port_c2_cls_init(port);
 }
 
+u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index)
+{
+	mvpp2_write(priv, MVPP22_CLS_C2_TCAM_IDX, c2_index);
+
+	return mvpp2_read(priv, MVPP22_CLS_C2_HIT_CTR);
+}
+
 static void mvpp2_rss_port_c2_enable(struct mvpp2_port *port)
 {
 	struct mvpp2_cls_c2_entry c2;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
index 13eae2d1b4bf..089f05f29891 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.h
@@ -215,12 +215,18 @@ u16 mvpp2_flow_get_hek_fields(struct mvpp2_cls_flow_entry *fe);
 
 struct mvpp2_cls_flow *mvpp2_cls_flow_get(int flow);
 
+u32 mvpp2_cls_flow_hits(struct mvpp2 *priv, int index);
+
 void mvpp2_cls_flow_read(struct mvpp2 *priv, int index,
 			 struct mvpp2_cls_flow_entry *fe);
 
+u32 mvpp2_cls_lookup_hits(struct mvpp2 *priv, int index);
+
 void mvpp2_cls_lookup_read(struct mvpp2 *priv, int lkpid, int way,
 			   struct mvpp2_cls_lookup_entry *le);
 
+u32 mvpp2_cls_c2_hit_count(struct mvpp2 *priv, int c2_index);
+
 void mvpp2_cls_c2_read(struct mvpp2 *priv, int index,
 		       struct mvpp2_cls_c2_entry *c2);
 
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
index fc46ec81249b..02dfef13cccd 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -28,6 +28,33 @@ struct mvpp2_dbgfs_port_flow_entry {
 	struct mvpp2_dbgfs_flow_entry *dbg_fe;
 };
 
+static int mvpp2_dbgfs_flow_flt_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+	int id = MVPP2_FLOW_C2_ENTRY(entry->flow);
+
+	u32 hits = mvpp2_cls_flow_hits(entry->priv, id);
+
+	seq_printf(s, "%u\n", hits);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_flt_hits);
+
+static int mvpp2_dbgfs_flow_dec_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_dbgfs_flow_entry *entry = s->private;
+
+	u32 hits = mvpp2_cls_lookup_hits(entry->priv, entry->flow);
+
+	seq_printf(s, "%u\n", hits);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_dec_hits);
+
 static int mvpp2_dbgfs_flow_type_show(struct seq_file *s, void *unused)
 {
 	struct mvpp2_dbgfs_flow_entry *entry = s->private;
@@ -174,6 +201,21 @@ static int mvpp2_dbgfs_port_flow_engine_show(struct seq_file *s, void *unused)
 
 DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_port_flow_engine);
 
+static int mvpp2_dbgfs_flow_c2_hits_show(struct seq_file *s, void *unused)
+{
+	struct mvpp2_port *port = s->private;
+	u32 hits;
+
+	hits = mvpp2_cls_c2_hit_count(port->priv,
+				      MVPP22_CLS_C2_RSS_ENTRY(port->id));
+
+	seq_printf(s, "%u\n", hits);
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(mvpp2_dbgfs_flow_c2_hits);
+
 static int mvpp2_dbgfs_flow_c2_rxq_show(struct seq_file *s, void *unused)
 {
 	struct mvpp2_port *port = s->private;
@@ -484,6 +526,12 @@ static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent,
 	entry->flow = flow;
 	entry->priv = priv;
 
+	debugfs_create_file("flow_hits", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_flt_hits_fops);
+
+	debugfs_create_file("dec_hits", 0444, flow_entry_dir, entry,
+			    &mvpp2_dbgfs_flow_dec_hits_fops);
+
 	debugfs_create_file("type", 0444, flow_entry_dir, entry,
 			    &mvpp2_dbgfs_flow_type_fops);
 
@@ -600,6 +648,9 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent,
 	debugfs_create_file("vid_filter", 0444, port_dir, port,
 			    &mvpp2_dbgfs_port_vid_fops);
 
+	debugfs_create_file("c2_hits", 0444, port_dir, port,
+			    &mvpp2_dbgfs_flow_c2_hits_fops);
+
 	debugfs_create_file("default_rxq", 0444, port_dir, port,
 			    &mvpp2_dbgfs_flow_c2_rxq_fops);
 
-- 
cgit v1.2.3


From 784abe24c903b093af04cf1a043140faa556cad7 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:35 +0300
Subject: net: Add decrypted field to skb

The decrypted bit is propogated to cloned/copied skbs.
This will be used later by the inline crypto receive side offload
of tls.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 7 ++++++-
 net/core/skbuff.c      | 6 ++++++
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7601838c2513..3ceb8dcc54da 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -630,6 +630,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
+ *	@decrypted: Decrypted SKB
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -736,7 +737,11 @@ struct sk_buff {
 				peeked:1,
 				head_frag:1,
 				xmit_more:1,
-				__unused:1; /* one bit hole */
+#ifdef CONFIG_TLS_DEVICE
+				decrypted:1;
+#else
+				__unused:1;
+#endif
 
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c4e24ac27464..cfd6c6f35f9c 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -805,6 +805,9 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	 * It is not yet because we do not want to have a 16 bit hole
 	 */
 	new->queue_mapping = old->queue_mapping;
+#ifdef CONFIG_TLS_DEVICE
+	new->decrypted = old->decrypted;
+#endif
 
 	memcpy(&new->headers_start, &old->headers_start,
 	       offsetof(struct sk_buff, headers_end) -
@@ -865,6 +868,9 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	C(head_frag);
 	C(data);
 	C(truesize);
+#ifdef CONFIG_TLS_DEVICE
+	C(decrypted);
+#endif
 	refcount_set(&n->users, 1);
 
 	atomic_inc(&(skb_shinfo(skb)->dataref));
-- 
cgit v1.2.3


From 14136564c8ee94566945e85014019cbdb1716dca Mon Sep 17 00:00:00 2001
From: Ilya Lesokhin <ilyal@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:36 +0300
Subject: net: Add TLS RX offload feature

This patch adds a netdev feature to configure TLS RX inline crypto offload.

Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 2 ++
 net/core/ethtool.c              | 1 +
 2 files changed, 3 insertions(+)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 623bb8ced060..2b2a6dce1630 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -79,6 +79,7 @@ enum {
 	NETIF_F_HW_ESP_TX_CSUM_BIT,	/* ESP with TX checksum offload */
 	NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */
 	NETIF_F_HW_TLS_TX_BIT,		/* Hardware TLS TX offload */
+	NETIF_F_HW_TLS_RX_BIT,		/* Hardware TLS RX offload */
 
 	NETIF_F_GRO_HW_BIT,		/* Hardware Generic receive offload */
 	NETIF_F_HW_TLS_RECORD_BIT,	/* Offload TLS record */
@@ -151,6 +152,7 @@ enum {
 #define NETIF_F_HW_TLS_RECORD	__NETIF_F(HW_TLS_RECORD)
 #define NETIF_F_GSO_UDP_L4	__NETIF_F(GSO_UDP_L4)
 #define NETIF_F_HW_TLS_TX	__NETIF_F(HW_TLS_TX)
+#define NETIF_F_HW_TLS_RX	__NETIF_F(HW_TLS_RX)
 
 #define for_each_netdev_feature(mask_addr, bit)	\
 	for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT)
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index e677a20180cf..c9993c6c2fd4 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -111,6 +111,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN]
 	[NETIF_F_RX_UDP_TUNNEL_PORT_BIT] =	 "rx-udp_tunnel-port-offload",
 	[NETIF_F_HW_TLS_RECORD_BIT] =	"tls-hw-record",
 	[NETIF_F_HW_TLS_TX_BIT] =	 "tls-hw-tx-offload",
+	[NETIF_F_HW_TLS_RX_BIT] =	 "tls-hw-rx-offload",
 };
 
 static const char
-- 
cgit v1.2.3


From 16e4edc297ffc9b643b8dd3da6b0d579753ea2b3 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:37 +0300
Subject: net: Add TLS rx resync NDO

Add new netdev tls op for resynchronizing HW tls context

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4fa7f7a3f8b3..3514d67112b3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -903,6 +903,8 @@ struct tlsdev_ops {
 	void (*tls_dev_del)(struct net_device *netdev,
 			    struct tls_context *ctx,
 			    enum tls_offload_ctx_dir direction);
+	void (*tls_dev_resync_rx)(struct net_device *netdev,
+				  struct sock *sk, u32 seq, u64 rcd_sn);
 };
 #endif
 
-- 
cgit v1.2.3


From 41ed9c04aac2f8c6ee922e29ce5e69f185c5125b Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:38 +0300
Subject: tcp: Don't coalesce decrypted and encrypted SKBs

Prevent coalescing of decrypted and encrypted SKBs in GRO
and TCP layer.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c   | 12 ++++++++++++
 net/ipv4/tcp_offload.c |  3 +++
 2 files changed, 15 insertions(+)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fac5d03d4528..91dbb9afb950 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4343,6 +4343,11 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
 		return false;
 
+#ifdef CONFIG_TLS_DEVICE
+	if (from->decrypted != to->decrypted)
+		return false;
+#endif
+
 	if (!skb_try_coalesce(to, from, fragstolen, &delta))
 		return false;
 
@@ -4871,6 +4876,9 @@ restart:
 			break;
 
 		memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
+#ifdef CONFIG_TLS_DEVICE
+		nskb->decrypted = skb->decrypted;
+#endif
 		TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
 		if (list)
 			__skb_queue_before(list, skb, nskb);
@@ -4898,6 +4906,10 @@ restart:
 				    skb == tail ||
 				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					goto end;
+#ifdef CONFIG_TLS_DEVICE
+				if (skb->decrypted != nskb->decrypted)
+					goto end;
+#endif
 			}
 		}
 	}
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index f5aee641f825..870b0a335061 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -262,6 +262,9 @@ found:
 
 	flush |= (len - 1) >= mss;
 	flush |= (ntohl(th2->seq) + skb_gro_len(p)) ^ ntohl(th->seq);
+#ifdef CONFIG_TLS_DEVICE
+	flush |= p->decrypted ^ skb->decrypted;
+#endif
 
 	if (flush || skb_gro_receive(p, skb)) {
 		mss = 1;
-- 
cgit v1.2.3


From d80a1b9d186057ddb0d384ba601cf2b7d214539c Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:39 +0300
Subject: tls: Refactor tls_offload variable names

For symmetry, we rename tls_offload_context to
tls_offload_context_tx before we add tls_offload_context_rx.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls.h |  6 +++---
 include/net/tls.h                                  | 16 +++++++-------
 net/tls/tls_device.c                               | 25 +++++++++++-----------
 net/tls/tls_device_fallback.c                      |  8 +++----
 4 files changed, 27 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index b6162178f621..b82f4deaa398 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -50,7 +50,7 @@ struct mlx5e_tls {
 };
 
 struct mlx5e_tls_offload_context {
-	struct tls_offload_context base;
+	struct tls_offload_context_tx base;
 	u32 expected_seq;
 	__be32 swid;
 };
@@ -59,8 +59,8 @@ static inline struct mlx5e_tls_offload_context *
 mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
 {
 	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) >
-		     TLS_OFFLOAD_CONTEXT_SIZE);
-	return container_of(tls_offload_ctx(tls_ctx),
+		     TLS_OFFLOAD_CONTEXT_SIZE_TX);
+	return container_of(tls_offload_ctx_tx(tls_ctx),
 			    struct mlx5e_tls_offload_context,
 			    base);
 }
diff --git a/include/net/tls.h b/include/net/tls.h
index 70c273777fe9..5dcd808236a7 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -128,7 +128,7 @@ struct tls_record_info {
 	skb_frag_t frags[MAX_SKB_FRAGS];
 };
 
-struct tls_offload_context {
+struct tls_offload_context_tx {
 	struct crypto_aead *aead_send;
 	spinlock_t lock;	/* protects records list */
 	struct list_head records_list;
@@ -147,8 +147,8 @@ struct tls_offload_context {
 #define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *)))
 };
 
-#define TLS_OFFLOAD_CONTEXT_SIZE                                               \
-	(ALIGN(sizeof(struct tls_offload_context), sizeof(void *)) +           \
+#define TLS_OFFLOAD_CONTEXT_SIZE_TX                                            \
+	(ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) +        \
 	 TLS_DRIVER_STATE_SIZE)
 
 enum {
@@ -239,7 +239,7 @@ void tls_device_sk_destruct(struct sock *sk);
 void tls_device_init(void);
 void tls_device_cleanup(void);
 
-struct tls_record_info *tls_get_record(struct tls_offload_context *context,
+struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 				       u32 seq, u64 *p_record_sn);
 
 static inline bool tls_record_is_start_marker(struct tls_record_info *rec)
@@ -380,10 +380,10 @@ static inline struct tls_sw_context_tx *tls_sw_ctx_tx(
 	return (struct tls_sw_context_tx *)tls_ctx->priv_ctx_tx;
 }
 
-static inline struct tls_offload_context *tls_offload_ctx(
-		const struct tls_context *tls_ctx)
+static inline struct tls_offload_context_tx *
+tls_offload_ctx_tx(const struct tls_context *tls_ctx)
 {
-	return (struct tls_offload_context *)tls_ctx->priv_ctx_tx;
+	return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx;
 }
 
 int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
@@ -396,7 +396,7 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
 				      struct sk_buff *skb);
 
 int tls_sw_fallback_init(struct sock *sk,
-			 struct tls_offload_context *offload_ctx,
+			 struct tls_offload_context_tx *offload_ctx,
 			 struct tls_crypto_info *crypto_info);
 
 #endif /* _TLS_OFFLOAD_H */
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index a7a8f8e20ff3..332a5d1459b6 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -52,9 +52,8 @@ static DEFINE_SPINLOCK(tls_device_lock);
 
 static void tls_device_free_ctx(struct tls_context *ctx)
 {
-	struct tls_offload_context *offload_ctx = tls_offload_ctx(ctx);
+	kfree(tls_offload_ctx_tx(ctx));
 
-	kfree(offload_ctx);
 	kfree(ctx);
 }
 
@@ -125,7 +124,7 @@ static void destroy_record(struct tls_record_info *record)
 	kfree(record);
 }
 
-static void delete_all_records(struct tls_offload_context *offload_ctx)
+static void delete_all_records(struct tls_offload_context_tx *offload_ctx)
 {
 	struct tls_record_info *info, *temp;
 
@@ -141,14 +140,14 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_record_info *info, *temp;
-	struct tls_offload_context *ctx;
+	struct tls_offload_context_tx *ctx;
 	u64 deleted_records = 0;
 	unsigned long flags;
 
 	if (!tls_ctx)
 		return;
 
-	ctx = tls_offload_ctx(tls_ctx);
+	ctx = tls_offload_ctx_tx(tls_ctx);
 
 	spin_lock_irqsave(&ctx->lock, flags);
 	info = ctx->retransmit_hint;
@@ -179,7 +178,7 @@ static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq)
 void tls_device_sk_destruct(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
 
 	if (ctx->open_record)
 		destroy_record(ctx->open_record);
@@ -219,7 +218,7 @@ static void tls_append_frag(struct tls_record_info *record,
 
 static int tls_push_record(struct sock *sk,
 			   struct tls_context *ctx,
-			   struct tls_offload_context *offload_ctx,
+			   struct tls_offload_context_tx *offload_ctx,
 			   struct tls_record_info *record,
 			   struct page_frag *pfrag,
 			   int flags,
@@ -264,7 +263,7 @@ static int tls_push_record(struct sock *sk,
 	return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags);
 }
 
-static int tls_create_new_record(struct tls_offload_context *offload_ctx,
+static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
 				 struct page_frag *pfrag,
 				 size_t prepend_size)
 {
@@ -290,7 +289,7 @@ static int tls_create_new_record(struct tls_offload_context *offload_ctx,
 }
 
 static int tls_do_allocation(struct sock *sk,
-			     struct tls_offload_context *offload_ctx,
+			     struct tls_offload_context_tx *offload_ctx,
 			     struct page_frag *pfrag,
 			     size_t prepend_size)
 {
@@ -324,7 +323,7 @@ static int tls_push_data(struct sock *sk,
 			 unsigned char record_type)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
 	int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;
 	int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
 	struct tls_record_info *record = ctx->open_record;
@@ -477,7 +476,7 @@ out:
 	return rc;
 }
 
-struct tls_record_info *tls_get_record(struct tls_offload_context *context,
+struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
 				       u32 seq, u64 *p_record_sn)
 {
 	u64 record_sn = context->hint_record_sn;
@@ -524,7 +523,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 {
 	u16 nonce_size, tag_size, iv_size, rec_seq_size;
 	struct tls_record_info *start_marker_record;
-	struct tls_offload_context *offload_ctx;
+	struct tls_offload_context_tx *offload_ctx;
 	struct tls_crypto_info *crypto_info;
 	struct net_device *netdev;
 	char *iv, *rec_seq;
@@ -546,7 +545,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 		goto out;
 	}
 
-	offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE, GFP_KERNEL);
+	offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_TX, GFP_KERNEL);
 	if (!offload_ctx) {
 		rc = -ENOMEM;
 		goto free_marker_record;
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 748914abdb60..d1d7dce38e0b 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -214,7 +214,7 @@ static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln)
 
 static int fill_sg_in(struct scatterlist *sg_in,
 		      struct sk_buff *skb,
-		      struct tls_offload_context *ctx,
+		      struct tls_offload_context_tx *ctx,
 		      u64 *rcd_sn,
 		      s32 *sync_size,
 		      int *resync_sgs)
@@ -299,7 +299,7 @@ static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx,
 				   s32 sync_size, u64 rcd_sn)
 {
 	int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
-	struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
 	int payload_len = skb->len - tcp_payload_offset;
 	void *buf, *iv, *aad, *dummy_buf;
 	struct aead_request *aead_req;
@@ -361,7 +361,7 @@ static struct sk_buff *tls_sw_fallback(struct sock *sk, struct sk_buff *skb)
 {
 	int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb);
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx);
+	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
 	int payload_len = skb->len - tcp_payload_offset;
 	struct scatterlist *sg_in, sg_out[3];
 	struct sk_buff *nskb = NULL;
@@ -415,7 +415,7 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
 }
 
 int tls_sw_fallback_init(struct sock *sk,
-			 struct tls_offload_context *offload_ctx,
+			 struct tls_offload_context_tx *offload_ctx,
 			 struct tls_crypto_info *crypto_info)
 {
 	const u8 *key;
-- 
cgit v1.2.3


From dafb67f3bb4a58a45fe92c1e362ea6429831688a Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:40 +0300
Subject: tls: Split decrypt_skb to two functions

Previously, decrypt_skb also updated the TLS context.
Now, decrypt_skb only decrypts the payload using the current context,
while decrypt_skb_update also updates the state.

Later, in the tls_device Rx flow, we will use decrypt_skb directly.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h |  2 ++
 net/tls/tls_sw.c  | 44 ++++++++++++++++++++++++++------------------
 2 files changed, 28 insertions(+), 18 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 5dcd808236a7..49b89221db43 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -390,6 +390,8 @@ int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
 		      unsigned char *record_type);
 void tls_register_device(struct tls_device *device);
 void tls_unregister_device(struct tls_device *device);
+int decrypt_skb(struct sock *sk, struct sk_buff *skb,
+		struct scatterlist *sgout);
 
 struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
 				      struct net_device *dev,
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 7453f5ae0819..1d2271736717 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -53,7 +53,6 @@ static int tls_do_decryption(struct sock *sk,
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
-	struct strp_msg *rxm = strp_msg(skb);
 	struct aead_request *aead_req;
 
 	int ret;
@@ -71,18 +70,6 @@ static int tls_do_decryption(struct sock *sk,
 
 	ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait);
 
-	if (ret < 0)
-		goto out;
-
-	rxm->offset += tls_ctx->rx.prepend_size;
-	rxm->full_len -= tls_ctx->rx.overhead_size;
-	tls_advance_record_sn(sk, &tls_ctx->rx);
-
-	ctx->decrypted = true;
-
-	ctx->saved_data_ready(sk);
-
-out:
 	aead_request_free(aead_req);
 	return ret;
 }
@@ -666,8 +653,29 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
 	return skb;
 }
 
-static int decrypt_skb(struct sock *sk, struct sk_buff *skb,
-		       struct scatterlist *sgout)
+static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
+			      struct scatterlist *sgout)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+	struct strp_msg *rxm = strp_msg(skb);
+	int err = 0;
+
+	err = decrypt_skb(sk, skb, sgout);
+	if (err < 0)
+		return err;
+
+	rxm->offset += tls_ctx->rx.prepend_size;
+	rxm->full_len -= tls_ctx->rx.overhead_size;
+	tls_advance_record_sn(sk, &tls_ctx->rx);
+	ctx->decrypted = true;
+	ctx->saved_data_ready(sk);
+
+	return err;
+}
+
+int decrypt_skb(struct sock *sk, struct sk_buff *skb,
+		struct scatterlist *sgout)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
@@ -812,7 +820,7 @@ int tls_sw_recvmsg(struct sock *sk,
 				if (err < 0)
 					goto fallback_to_reg_recv;
 
-				err = decrypt_skb(sk, skb, sgin);
+				err = decrypt_skb_update(sk, skb, sgin);
 				for (; pages > 0; pages--)
 					put_page(sg_page(&sgin[pages]));
 				if (err < 0) {
@@ -821,7 +829,7 @@ int tls_sw_recvmsg(struct sock *sk,
 				}
 			} else {
 fallback_to_reg_recv:
-				err = decrypt_skb(sk, skb, NULL);
+				err = decrypt_skb_update(sk, skb, NULL);
 				if (err < 0) {
 					tls_err_abort(sk, EBADMSG);
 					goto recv_end;
@@ -892,7 +900,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	}
 
 	if (!ctx->decrypted) {
-		err = decrypt_skb(sk, skb, NULL);
+		err = decrypt_skb_update(sk, skb, NULL);
 
 		if (err < 0) {
 			tls_err_abort(sk, EBADMSG);
-- 
cgit v1.2.3


From 39f56e1a78d647316db330c3b6f4c5637a895e3b Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:41 +0300
Subject: tls: Split tls_sw_release_resources_rx

This patch splits tls_sw_release_resources_rx into two functions one
which releases all inner software tls structures and another that also
frees the containing structure.

In TLS_DEVICE we will need to release the software structures without
freeeing the containing structure, which contains other information.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h |  1 +
 net/tls/tls_sw.c  | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 49b89221db43..7a485de25646 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -223,6 +223,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page,
 void tls_sw_close(struct sock *sk, long timeout);
 void tls_sw_free_resources_tx(struct sock *sk);
 void tls_sw_free_resources_rx(struct sock *sk);
+void tls_sw_release_resources_rx(struct sock *sk);
 int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		   int nonblock, int flags, int *addr_len);
 unsigned int tls_sw_poll(struct file *file, struct socket *sock,
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 1d2271736717..694d26589dcc 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1030,7 +1030,7 @@ void tls_sw_free_resources_tx(struct sock *sk)
 	kfree(ctx);
 }
 
-void tls_sw_free_resources_rx(struct sock *sk)
+void tls_sw_release_resources_rx(struct sock *sk)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
@@ -1049,6 +1049,14 @@ void tls_sw_free_resources_rx(struct sock *sk)
 		strp_done(&ctx->strp);
 		lock_sock(sk);
 	}
+}
+
+void tls_sw_free_resources_rx(struct sock *sk)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+
+	tls_sw_release_resources_rx(sk);
 
 	kfree(ctx);
 }
-- 
cgit v1.2.3


From b190a587c634a8559e4ceabeb0468e93db49789a Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:42 +0300
Subject: tls: Fill software context without allocation

This patch allows tls_set_sw_offload to fill the context in case it was
already allocated previously.

We will use it in TLS_DEVICE to fill the RX software context.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 34 ++++++++++++++++++++++------------
 1 file changed, 22 insertions(+), 12 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 694d26589dcc..5f7d70b24be6 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1081,28 +1081,38 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	}
 
 	if (tx) {
-		sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL);
-		if (!sw_ctx_tx) {
-			rc = -ENOMEM;
-			goto out;
+		if (!ctx->priv_ctx_tx) {
+			sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL);
+			if (!sw_ctx_tx) {
+				rc = -ENOMEM;
+				goto out;
+			}
+			ctx->priv_ctx_tx = sw_ctx_tx;
+		} else {
+			sw_ctx_tx =
+				(struct tls_sw_context_tx *)ctx->priv_ctx_tx;
 		}
-		crypto_init_wait(&sw_ctx_tx->async_wait);
-		ctx->priv_ctx_tx = sw_ctx_tx;
 	} else {
-		sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL);
-		if (!sw_ctx_rx) {
-			rc = -ENOMEM;
-			goto out;
+		if (!ctx->priv_ctx_rx) {
+			sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL);
+			if (!sw_ctx_rx) {
+				rc = -ENOMEM;
+				goto out;
+			}
+			ctx->priv_ctx_rx = sw_ctx_rx;
+		} else {
+			sw_ctx_rx =
+				(struct tls_sw_context_rx *)ctx->priv_ctx_rx;
 		}
-		crypto_init_wait(&sw_ctx_rx->async_wait);
-		ctx->priv_ctx_rx = sw_ctx_rx;
 	}
 
 	if (tx) {
+		crypto_init_wait(&sw_ctx_tx->async_wait);
 		crypto_info = &ctx->crypto_send;
 		cctx = &ctx->tx;
 		aead = &sw_ctx_tx->aead_send;
 	} else {
+		crypto_init_wait(&sw_ctx_rx->async_wait);
 		crypto_info = &ctx->crypto_recv;
 		cctx = &ctx->rx;
 		aead = &sw_ctx_rx->aead_recv;
-- 
cgit v1.2.3


From 4799ac81e52a72a6404827bf2738337bb581a174 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:43 +0300
Subject: tls: Add rx inline crypto offload

This patch completes the generic infrastructure to offload TLS crypto to a
network device. It enables the kernel to skip decryption and
authentication of some skbs marked as decrypted by the NIC. In the fast
path, all packets received are decrypted by the NIC and the performance
is comparable to plain TCP.

This infrastructure doesn't require a TCP offload engine. Instead, the
NIC only decrypts packets that contain the expected TCP sequence number.
Out-Of-Order TCP packets are provided unmodified. As a result, at the
worst case a received TLS record consists of both plaintext and ciphertext
packets. These partially decrypted records must be reencrypted,
only to be decrypted.

The notable differences between SW KTLS Rx and this offload are as
follows:
1. Partial decryption - Software must handle the case of a TLS record
that was only partially decrypted by HW. This can happen due to packet
reordering.
2. Resynchronization - tls_read_size calls the device driver to
resynchronize HW after HW lost track of TLS record framing in
the TCP stream.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h             |  63 +++++++++-
 net/tls/tls_device.c          | 278 ++++++++++++++++++++++++++++++++++++++----
 net/tls/tls_device_fallback.c |   1 +
 net/tls/tls_main.c            |  32 +++--
 net/tls/tls_sw.c              |  24 +++-
 5 files changed, 355 insertions(+), 43 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index 7a485de25646..d8b3b6578c01 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -83,6 +83,16 @@ struct tls_device {
 	void (*unhash)(struct tls_device *device, struct sock *sk);
 };
 
+enum {
+	TLS_BASE,
+	TLS_SW,
+#ifdef CONFIG_TLS_DEVICE
+	TLS_HW,
+#endif
+	TLS_HW_RECORD,
+	TLS_NUM_CONFIG,
+};
+
 struct tls_sw_context_tx {
 	struct crypto_aead *aead_send;
 	struct crypto_wait async_wait;
@@ -197,6 +207,7 @@ struct tls_context {
 	int (*push_pending_record)(struct sock *sk, int flags);
 
 	void (*sk_write_space)(struct sock *sk);
+	void (*sk_destruct)(struct sock *sk);
 	void (*sk_proto_close)(struct sock *sk, long timeout);
 
 	int  (*setsockopt)(struct sock *sk, int level,
@@ -209,13 +220,27 @@ struct tls_context {
 	void (*unhash)(struct sock *sk);
 };
 
+struct tls_offload_context_rx {
+	/* sw must be the first member of tls_offload_context_rx */
+	struct tls_sw_context_rx sw;
+	atomic64_t resync_req;
+	u8 driver_state[];
+	/* The TLS layer reserves room for driver specific state
+	 * Currently the belief is that there is not enough
+	 * driver specific state to justify another layer of indirection
+	 */
+};
+
+#define TLS_OFFLOAD_CONTEXT_SIZE_RX					\
+	(ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \
+	 TLS_DRIVER_STATE_SIZE)
+
 int wait_on_pending_writer(struct sock *sk, long *timeo);
 int tls_sk_query(struct sock *sk, int optname, char __user *optval,
 		int __user *optlen);
 int tls_sk_attach(struct sock *sk, int optname, char __user *optval,
 		  unsigned int optlen);
 
-
 int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx);
 int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tls_sw_sendpage(struct sock *sk, struct page *page,
@@ -290,11 +315,19 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx)
 	return tls_ctx->pending_open_record_frags;
 }
 
+struct sk_buff *
+tls_validate_xmit_skb(struct sock *sk, struct net_device *dev,
+		      struct sk_buff *skb);
+
 static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk)
 {
-	return sk_fullsock(sk) &&
-	       /* matches smp_store_release in tls_set_device_offload */
-	       smp_load_acquire(&sk->sk_destruct) == &tls_device_sk_destruct;
+#ifdef CONFIG_SOCK_VALIDATE_XMIT
+	return sk_fullsock(sk) &
+	       (smp_load_acquire(&sk->sk_validate_xmit_skb) ==
+	       &tls_validate_xmit_skb);
+#else
+	return false;
+#endif
 }
 
 static inline void tls_err_abort(struct sock *sk, int err)
@@ -387,10 +420,27 @@ tls_offload_ctx_tx(const struct tls_context *tls_ctx)
 	return (struct tls_offload_context_tx *)tls_ctx->priv_ctx_tx;
 }
 
+static inline struct tls_offload_context_rx *
+tls_offload_ctx_rx(const struct tls_context *tls_ctx)
+{
+	return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx;
+}
+
+/* The TLS context is valid until sk_destruct is called */
+static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
+
+	atomic64_set(&rx_ctx->resync_req, ((((uint64_t)seq) << 32) | 1));
+}
+
+
 int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg,
 		      unsigned char *record_type);
 void tls_register_device(struct tls_device *device);
 void tls_unregister_device(struct tls_device *device);
+int tls_device_decrypted(struct sock *sk, struct sk_buff *skb);
 int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 		struct scatterlist *sgout);
 
@@ -402,4 +452,9 @@ int tls_sw_fallback_init(struct sock *sk,
 			 struct tls_offload_context_tx *offload_ctx,
 			 struct tls_crypto_info *crypto_info);
 
+int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx);
+
+void tls_device_offload_cleanup_rx(struct sock *sk);
+void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn);
+
 #endif /* _TLS_OFFLOAD_H */
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 332a5d1459b6..4995d84d228d 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -52,7 +52,11 @@ static DEFINE_SPINLOCK(tls_device_lock);
 
 static void tls_device_free_ctx(struct tls_context *ctx)
 {
-	kfree(tls_offload_ctx_tx(ctx));
+	if (ctx->tx_conf == TLS_HW)
+		kfree(tls_offload_ctx_tx(ctx));
+
+	if (ctx->rx_conf == TLS_HW)
+		kfree(tls_offload_ctx_rx(ctx));
 
 	kfree(ctx);
 }
@@ -70,10 +74,11 @@ static void tls_device_gc_task(struct work_struct *work)
 	list_for_each_entry_safe(ctx, tmp, &gc_list, list) {
 		struct net_device *netdev = ctx->netdev;
 
-		if (netdev) {
+		if (netdev && ctx->tx_conf == TLS_HW) {
 			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
 							TLS_OFFLOAD_CTX_DIR_TX);
 			dev_put(netdev);
+			ctx->netdev = NULL;
 		}
 
 		list_del(&ctx->list);
@@ -81,6 +86,22 @@ static void tls_device_gc_task(struct work_struct *work)
 	}
 }
 
+static void tls_device_attach(struct tls_context *ctx, struct sock *sk,
+			      struct net_device *netdev)
+{
+	if (sk->sk_destruct != tls_device_sk_destruct) {
+		refcount_set(&ctx->refcount, 1);
+		dev_hold(netdev);
+		ctx->netdev = netdev;
+		spin_lock_irq(&tls_device_lock);
+		list_add_tail(&ctx->list, &tls_device_list);
+		spin_unlock_irq(&tls_device_lock);
+
+		ctx->sk_destruct = sk->sk_destruct;
+		sk->sk_destruct = tls_device_sk_destruct;
+	}
+}
+
 static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
 {
 	unsigned long flags;
@@ -180,13 +201,15 @@ void tls_device_sk_destruct(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
 
-	if (ctx->open_record)
-		destroy_record(ctx->open_record);
+	tls_ctx->sk_destruct(sk);
 
-	delete_all_records(ctx);
-	crypto_free_aead(ctx->aead_send);
-	ctx->sk_destruct(sk);
-	clean_acked_data_disable(inet_csk(sk));
+	if (tls_ctx->tx_conf == TLS_HW) {
+		if (ctx->open_record)
+			destroy_record(ctx->open_record);
+		delete_all_records(ctx);
+		crypto_free_aead(ctx->aead_send);
+		clean_acked_data_disable(inet_csk(sk));
+	}
 
 	if (refcount_dec_and_test(&tls_ctx->refcount))
 		tls_device_queue_ctx_destruction(tls_ctx);
@@ -519,6 +542,118 @@ static int tls_device_push_pending_record(struct sock *sk, int flags)
 	return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
 }
 
+void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct net_device *netdev = tls_ctx->netdev;
+	struct tls_offload_context_rx *rx_ctx;
+	u32 is_req_pending;
+	s64 resync_req;
+	u32 req_seq;
+
+	if (tls_ctx->rx_conf != TLS_HW)
+		return;
+
+	rx_ctx = tls_offload_ctx_rx(tls_ctx);
+	resync_req = atomic64_read(&rx_ctx->resync_req);
+	req_seq = ntohl(resync_req >> 32) - ((u32)TLS_HEADER_SIZE - 1);
+	is_req_pending = resync_req;
+
+	if (unlikely(is_req_pending) && req_seq == seq &&
+	    atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0))
+		netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk,
+						      seq + TLS_HEADER_SIZE - 1,
+						      rcd_sn);
+}
+
+static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
+{
+	struct strp_msg *rxm = strp_msg(skb);
+	int err = 0, offset = rxm->offset, copy, nsg;
+	struct sk_buff *skb_iter, *unused;
+	struct scatterlist sg[1];
+	char *orig_buf, *buf;
+
+	orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE +
+			   TLS_CIPHER_AES_GCM_128_IV_SIZE, sk->sk_allocation);
+	if (!orig_buf)
+		return -ENOMEM;
+	buf = orig_buf;
+
+	nsg = skb_cow_data(skb, 0, &unused);
+	if (unlikely(nsg < 0)) {
+		err = nsg;
+		goto free_buf;
+	}
+
+	sg_init_table(sg, 1);
+	sg_set_buf(&sg[0], buf,
+		   rxm->full_len + TLS_HEADER_SIZE +
+		   TLS_CIPHER_AES_GCM_128_IV_SIZE);
+	skb_copy_bits(skb, offset, buf,
+		      TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE);
+
+	/* We are interested only in the decrypted data not the auth */
+	err = decrypt_skb(sk, skb, sg);
+	if (err != -EBADMSG)
+		goto free_buf;
+	else
+		err = 0;
+
+	copy = min_t(int, skb_pagelen(skb) - offset,
+		     rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+
+	if (skb->decrypted)
+		skb_store_bits(skb, offset, buf, copy);
+
+	offset += copy;
+	buf += copy;
+
+	skb_walk_frags(skb, skb_iter) {
+		copy = min_t(int, skb_iter->len,
+			     rxm->full_len - offset + rxm->offset -
+			     TLS_CIPHER_AES_GCM_128_TAG_SIZE);
+
+		if (skb_iter->decrypted)
+			skb_store_bits(skb, offset, buf, copy);
+
+		offset += copy;
+		buf += copy;
+	}
+
+free_buf:
+	kfree(orig_buf);
+	return err;
+}
+
+int tls_device_decrypted(struct sock *sk, struct sk_buff *skb)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_offload_context_rx *ctx = tls_offload_ctx_rx(tls_ctx);
+	int is_decrypted = skb->decrypted;
+	int is_encrypted = !is_decrypted;
+	struct sk_buff *skb_iter;
+
+	/* Skip if it is already decrypted */
+	if (ctx->sw.decrypted)
+		return 0;
+
+	/* Check if all the data is decrypted already */
+	skb_walk_frags(skb, skb_iter) {
+		is_decrypted &= skb_iter->decrypted;
+		is_encrypted &= !skb_iter->decrypted;
+	}
+
+	ctx->sw.decrypted |= is_decrypted;
+
+	/* Return immedeatly if the record is either entirely plaintext or
+	 * entirely ciphertext. Otherwise handle reencrypt partially decrypted
+	 * record.
+	 */
+	return (is_encrypted || is_decrypted) ? 0 :
+		tls_device_reencrypt(sk, skb);
+}
+
 int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 {
 	u16 nonce_size, tag_size, iv_size, rec_seq_size;
@@ -608,7 +743,6 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 
 	clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked);
 	ctx->push_pending_record = tls_device_push_pending_record;
-	offload_ctx->sk_destruct = sk->sk_destruct;
 
 	/* TLS offload is greatly simplified if we don't send
 	 * SKBs where only part of the payload needs to be encrypted.
@@ -618,8 +752,6 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	if (skb)
 		TCP_SKB_CB(skb)->eor = 1;
 
-	refcount_set(&ctx->refcount, 1);
-
 	/* We support starting offload on multiple sockets
 	 * concurrently, so we only need a read lock here.
 	 * This lock must precede get_netdev_for_sock to prevent races between
@@ -654,19 +786,14 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	if (rc)
 		goto release_netdev;
 
-	ctx->netdev = netdev;
+	tls_device_attach(ctx, sk, netdev);
 
-	spin_lock_irq(&tls_device_lock);
-	list_add_tail(&ctx->list, &tls_device_list);
-	spin_unlock_irq(&tls_device_lock);
-
-	sk->sk_validate_xmit_skb = tls_validate_xmit_skb;
 	/* following this assignment tls_is_sk_tx_device_offloaded
 	 * will return true and the context might be accessed
 	 * by the netdev's xmit function.
 	 */
-	smp_store_release(&sk->sk_destruct,
-			  &tls_device_sk_destruct);
+	smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb);
+	dev_put(netdev);
 	up_read(&device_offload_lock);
 	goto out;
 
@@ -689,6 +816,105 @@ out:
 	return rc;
 }
 
+int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
+{
+	struct tls_offload_context_rx *context;
+	struct net_device *netdev;
+	int rc = 0;
+
+	/* We support starting offload on multiple sockets
+	 * concurrently, so we only need a read lock here.
+	 * This lock must precede get_netdev_for_sock to prevent races between
+	 * NETDEV_DOWN and setsockopt.
+	 */
+	down_read(&device_offload_lock);
+	netdev = get_netdev_for_sock(sk);
+	if (!netdev) {
+		pr_err_ratelimited("%s: netdev not found\n", __func__);
+		rc = -EINVAL;
+		goto release_lock;
+	}
+
+	if (!(netdev->features & NETIF_F_HW_TLS_RX)) {
+		pr_err_ratelimited("%s: netdev %s with no TLS offload\n",
+				   __func__, netdev->name);
+		rc = -ENOTSUPP;
+		goto release_netdev;
+	}
+
+	/* Avoid offloading if the device is down
+	 * We don't want to offload new flows after
+	 * the NETDEV_DOWN event
+	 */
+	if (!(netdev->flags & IFF_UP)) {
+		rc = -EINVAL;
+		goto release_netdev;
+	}
+
+	context = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_RX, GFP_KERNEL);
+	if (!context) {
+		rc = -ENOMEM;
+		goto release_netdev;
+	}
+
+	ctx->priv_ctx_rx = context;
+	rc = tls_set_sw_offload(sk, ctx, 0);
+	if (rc)
+		goto release_ctx;
+
+	rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX,
+					     &ctx->crypto_recv,
+					     tcp_sk(sk)->copied_seq);
+	if (rc) {
+		pr_err_ratelimited("%s: The netdev has refused to offload this socket\n",
+				   __func__);
+		goto free_sw_resources;
+	}
+
+	tls_device_attach(ctx, sk, netdev);
+	goto release_netdev;
+
+free_sw_resources:
+	tls_sw_free_resources_rx(sk);
+release_ctx:
+	ctx->priv_ctx_rx = NULL;
+release_netdev:
+	dev_put(netdev);
+release_lock:
+	up_read(&device_offload_lock);
+	return rc;
+}
+
+void tls_device_offload_cleanup_rx(struct sock *sk)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct net_device *netdev;
+
+	down_read(&device_offload_lock);
+	netdev = tls_ctx->netdev;
+	if (!netdev)
+		goto out;
+
+	if (!(netdev->features & NETIF_F_HW_TLS_RX)) {
+		pr_err_ratelimited("%s: device is missing NETIF_F_HW_TLS_RX cap\n",
+				   __func__);
+		goto out;
+	}
+
+	netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx,
+					TLS_OFFLOAD_CTX_DIR_RX);
+
+	if (tls_ctx->tx_conf != TLS_HW) {
+		dev_put(netdev);
+		tls_ctx->netdev = NULL;
+	}
+out:
+	up_read(&device_offload_lock);
+	kfree(tls_ctx->rx.rec_seq);
+	kfree(tls_ctx->rx.iv);
+	tls_sw_release_resources_rx(sk);
+}
+
 static int tls_device_down(struct net_device *netdev)
 {
 	struct tls_context *ctx, *tmp;
@@ -709,8 +935,12 @@ static int tls_device_down(struct net_device *netdev)
 	spin_unlock_irqrestore(&tls_device_lock, flags);
 
 	list_for_each_entry_safe(ctx, tmp, &list, list)	{
-		netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
-						TLS_OFFLOAD_CTX_DIR_TX);
+		if (ctx->tx_conf == TLS_HW)
+			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
+							TLS_OFFLOAD_CTX_DIR_TX);
+		if (ctx->rx_conf == TLS_HW)
+			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
+							TLS_OFFLOAD_CTX_DIR_RX);
 		ctx->netdev = NULL;
 		dev_put(netdev);
 		list_del_init(&ctx->list);
@@ -731,12 +961,16 @@ static int tls_dev_event(struct notifier_block *this, unsigned long event,
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 
-	if (!(dev->features & NETIF_F_HW_TLS_TX))
+	if (!(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX)))
 		return NOTIFY_DONE;
 
 	switch (event) {
 	case NETDEV_REGISTER:
 	case NETDEV_FEAT_CHANGE:
+		if ((dev->features & NETIF_F_HW_TLS_RX) &&
+		    !dev->tlsdev_ops->tls_dev_resync_rx)
+			return NOTIFY_BAD;
+
 		if  (dev->tlsdev_ops &&
 		     dev->tlsdev_ops->tls_dev_add &&
 		     dev->tlsdev_ops->tls_dev_del)
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index d1d7dce38e0b..e3313c45663f 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -413,6 +413,7 @@ struct sk_buff *tls_validate_xmit_skb(struct sock *sk,
 
 	return tls_sw_fallback(sk, skb);
 }
+EXPORT_SYMBOL_GPL(tls_validate_xmit_skb);
 
 int tls_sw_fallback_init(struct sock *sk,
 			 struct tls_offload_context_tx *offload_ctx,
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 301f22430469..b09867c8b817 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -51,15 +51,6 @@ enum {
 	TLSV6,
 	TLS_NUM_PROTS,
 };
-enum {
-	TLS_BASE,
-	TLS_SW,
-#ifdef CONFIG_TLS_DEVICE
-	TLS_HW,
-#endif
-	TLS_HW_RECORD,
-	TLS_NUM_CONFIG,
-};
 
 static struct proto *saved_tcpv6_prot;
 static DEFINE_MUTEX(tcpv6_prot_mutex);
@@ -290,7 +281,10 @@ static void tls_sk_proto_close(struct sock *sk, long timeout)
 	}
 
 #ifdef CONFIG_TLS_DEVICE
-	if (ctx->tx_conf != TLS_HW) {
+	if (ctx->rx_conf == TLS_HW)
+		tls_device_offload_cleanup_rx(sk);
+
+	if (ctx->tx_conf != TLS_HW && ctx->rx_conf != TLS_HW) {
 #else
 	{
 #endif
@@ -470,8 +464,16 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval,
 			conf = TLS_SW;
 		}
 	} else {
-		rc = tls_set_sw_offload(sk, ctx, 0);
-		conf = TLS_SW;
+#ifdef CONFIG_TLS_DEVICE
+		rc = tls_set_device_offload_rx(sk, ctx);
+		conf = TLS_HW;
+		if (rc) {
+#else
+		{
+#endif
+			rc = tls_set_sw_offload(sk, ctx, 0);
+			conf = TLS_SW;
+		}
 	}
 
 	if (rc)
@@ -629,6 +631,12 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG],
 	prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW];
 	prot[TLS_HW][TLS_SW].sendmsg		= tls_device_sendmsg;
 	prot[TLS_HW][TLS_SW].sendpage		= tls_device_sendpage;
+
+	prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW];
+
+	prot[TLS_SW][TLS_HW] = prot[TLS_SW][TLS_SW];
+
+	prot[TLS_HW][TLS_HW] = prot[TLS_HW][TLS_SW];
 #endif
 
 	prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base;
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 5f7d70b24be6..fe5735c57774 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -654,16 +654,25 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
 }
 
 static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
-			      struct scatterlist *sgout)
+			      struct scatterlist *sgout, bool *zc)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 	struct strp_msg *rxm = strp_msg(skb);
 	int err = 0;
 
-	err = decrypt_skb(sk, skb, sgout);
+#ifdef CONFIG_TLS_DEVICE
+	err = tls_device_decrypted(sk, skb);
 	if (err < 0)
 		return err;
+#endif
+	if (!ctx->decrypted) {
+		err = decrypt_skb(sk, skb, sgout);
+		if (err < 0)
+			return err;
+	} else {
+		*zc = false;
+	}
 
 	rxm->offset += tls_ctx->rx.prepend_size;
 	rxm->full_len -= tls_ctx->rx.overhead_size;
@@ -820,7 +829,7 @@ int tls_sw_recvmsg(struct sock *sk,
 				if (err < 0)
 					goto fallback_to_reg_recv;
 
-				err = decrypt_skb_update(sk, skb, sgin);
+				err = decrypt_skb_update(sk, skb, sgin, &zc);
 				for (; pages > 0; pages--)
 					put_page(sg_page(&sgin[pages]));
 				if (err < 0) {
@@ -829,7 +838,7 @@ int tls_sw_recvmsg(struct sock *sk,
 				}
 			} else {
 fallback_to_reg_recv:
-				err = decrypt_skb_update(sk, skb, NULL);
+				err = decrypt_skb_update(sk, skb, NULL, &zc);
 				if (err < 0) {
 					tls_err_abort(sk, EBADMSG);
 					goto recv_end;
@@ -884,6 +893,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	int err = 0;
 	long timeo;
 	int chunk;
+	bool zc;
 
 	lock_sock(sk);
 
@@ -900,7 +910,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	}
 
 	if (!ctx->decrypted) {
-		err = decrypt_skb_update(sk, skb, NULL);
+		err = decrypt_skb_update(sk, skb, NULL, &zc);
 
 		if (err < 0) {
 			tls_err_abort(sk, EBADMSG);
@@ -989,6 +999,10 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb)
 		goto read_failure;
 	}
 
+#ifdef CONFIG_TLS_DEVICE
+	handle_device_resync(strp->sk, TCP_SKB_CB(skb)->seq + rxm->offset,
+			     *(u64*)tls_ctx->rx.rec_seq);
+#endif
 	return data_len + TLS_HEADER_SIZE;
 
 read_failure:
-- 
cgit v1.2.3


From 4718799817c5a30ae723eda21f3a6c7d8701b1a4 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:44 +0300
Subject: tls: Fix zerocopy_from_iter iov handling

zerocopy_from_iter iterates over the message, but it doesn't revert the
updates made by the iov iteration. This patch fixes it. Now, the iov can
be used after calling zerocopy_from_iter.

Fixes: 3c4d75591 ("tls: kernel TLS support")
Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index fe5735c57774..7d194c0cd6cf 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -263,7 +263,7 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 			      int length, int *pages_used,
 			      unsigned int *size_used,
 			      struct scatterlist *to, int to_max_pages,
-			      bool charge)
+			      bool charge, bool revert)
 {
 	struct page *pages[MAX_SKB_FRAGS];
 
@@ -314,6 +314,8 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 out:
 	*size_used = size;
 	*pages_used = num_elem;
+	if (revert)
+		iov_iter_revert(from, size);
 
 	return rc;
 }
@@ -415,7 +417,7 @@ alloc_encrypted:
 				&ctx->sg_plaintext_size,
 				ctx->sg_plaintext_data,
 				ARRAY_SIZE(ctx->sg_plaintext_data),
-				true);
+				true, false);
 			if (ret)
 				goto fallback_to_reg_send;
 
@@ -825,7 +827,7 @@ int tls_sw_recvmsg(struct sock *sk,
 				err = zerocopy_from_iter(sk, &msg->msg_iter,
 							 to_copy, &pages,
 							 &chunk, &sgin[1],
-							 MAX_SKB_FRAGS,	false);
+							 MAX_SKB_FRAGS,	false, true);
 				if (err < 0)
 					goto fallback_to_reg_recv;
 
-- 
cgit v1.2.3


From 0aadb2fc092910b6db0038b377e130b905ba17e0 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:45 +0300
Subject: net/mlx5e: TLS, refactor variable names

For symmetry, we rename mlx5e_tls_offload_context to
mlx5e_tls_offload_context_tx before we add mlx5e_tls_offload_context_rx.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Reviewed-by: Aviad Yehezkel <aviadye@mellanox.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c      | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h      | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c | 6 +++---
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index d167845271c3..7fb9c750326e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -123,7 +123,7 @@ static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
 		goto free_flow;
 
 	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
-		struct mlx5e_tls_offload_context *tx_ctx =
+		struct mlx5e_tls_offload_context_tx *tx_ctx =
 		    mlx5e_get_tls_tx_context(tls_ctx);
 		u32 swid;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index b82f4deaa398..e26222ab26a6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -49,19 +49,19 @@ struct mlx5e_tls {
 	struct mlx5e_tls_sw_stats sw_stats;
 };
 
-struct mlx5e_tls_offload_context {
+struct mlx5e_tls_offload_context_tx {
 	struct tls_offload_context_tx base;
 	u32 expected_seq;
 	__be32 swid;
 };
 
-static inline struct mlx5e_tls_offload_context *
+static inline struct mlx5e_tls_offload_context_tx *
 mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
 {
-	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) >
+	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_tx) >
 		     TLS_OFFLOAD_CONTEXT_SIZE_TX);
 	return container_of(tls_offload_ctx_tx(tls_ctx),
-			    struct mlx5e_tls_offload_context,
+			    struct mlx5e_tls_offload_context_tx,
 			    base);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 15aef71d1957..c96196f900d7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -73,7 +73,7 @@ static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid)
 	return 0;
 }
 
-static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context *context,
+static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context_tx *context,
 				   u32 tcp_seq, struct sync_info *info)
 {
 	int remaining, i = 0, ret = -EINVAL;
@@ -161,7 +161,7 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 }
 
 static struct sk_buff *
-mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context *context,
+mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context_tx *context,
 		     struct mlx5e_txqsq *sq, struct sk_buff *skb,
 		     struct mlx5e_tx_wqe **wqe,
 		     u16 *pi,
@@ -239,7 +239,7 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 					u16 *pi)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	struct mlx5e_tls_offload_context *context;
+	struct mlx5e_tls_offload_context_tx *context;
 	struct tls_context *tls_ctx;
 	u32 expected_seq;
 	int datalen;
-- 
cgit v1.2.3


From ab412e1dd7db132c2abeb9385b4bf0dc8e6c5a65 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:46 +0300
Subject: net/mlx5: Accel, add TLS rx offload routines

In Innova TLS, TLS contexts are added or deleted
via a command message over the SBU connection.
The HW then sends a response message over the same connection.

Complete the implementation for Innova TLS (FPGA-based) hardware by
adding support for rx inline crypto offload.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/accel/tls.c    |  23 +++--
 .../net/ethernet/mellanox/mlx5/core/accel/tls.h    |  26 +++--
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c | 113 ++++++++++++++++-----
 drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h |  18 ++--
 include/linux/mlx5/mlx5_ifc_fpga.h                 |   1 +
 5 files changed, 135 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
index 77ac19f38cbe..da7bd26368f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c
@@ -37,17 +37,26 @@
 #include "mlx5_core.h"
 #include "fpga/tls.h"
 
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			       struct tls_crypto_info *crypto_info,
-			       u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			    struct tls_crypto_info *crypto_info,
+			    u32 start_offload_tcp_sn, u32 *p_swid,
+			    bool direction_sx)
 {
-	return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info,
-					 start_offload_tcp_sn, p_swid);
+	return mlx5_fpga_tls_add_flow(mdev, flow, crypto_info,
+				      start_offload_tcp_sn, p_swid,
+				      direction_sx);
 }
 
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid)
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			     bool direction_sx)
 {
-	mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL);
+	mlx5_fpga_tls_del_flow(mdev, swid, GFP_KERNEL, direction_sx);
+}
+
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			     u64 rcd_sn)
+{
+	return mlx5_fpga_tls_resync_rx(mdev, handle, seq, rcd_sn);
 }
 
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index 6f9c9f446ecc..2228c1083528 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -60,10 +60,14 @@ struct mlx5_ifc_tls_flow_bits {
 	u8         reserved_at_2[0x1e];
 };
 
-int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			       struct tls_crypto_info *crypto_info,
-			       u32 start_offload_tcp_sn, u32 *p_swid);
-void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid);
+int mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			    struct tls_crypto_info *crypto_info,
+			    u32 start_offload_tcp_sn, u32 *p_swid,
+			    bool direction_sx);
+void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			     bool direction_sx);
+int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			     u64 rcd_sn);
 bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev);
 u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev);
 int mlx5_accel_tls_init(struct mlx5_core_dev *mdev);
@@ -71,11 +75,15 @@ void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev);
 
 #else
 
-static inline int
-mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			   struct tls_crypto_info *crypto_info,
-			   u32 start_offload_tcp_sn, u32 *p_swid) { return 0; }
-static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { }
+static int
+mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			struct tls_crypto_info *crypto_info,
+			u32 start_offload_tcp_sn, u32 *p_swid,
+			bool direction_sx) { return -ENOTSUPP; }
+static inline void mlx5_accel_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+					   bool direction_sx) { }
+static inline int mlx5_accel_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle,
+					   u32 seq, u64 rcd_sn) { return 0; }
 static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; }
 static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; }
 static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
index c9736238604a..5cf5f2a9d51f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c
@@ -129,6 +129,7 @@ static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev,
 static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 				    void *ptr)
 {
+	unsigned long flags;
 	int ret;
 
 	/* TLS metadata format is 1 byte for syndrome followed
@@ -139,9 +140,9 @@ static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock,
 	BUILD_BUG_ON((SWID_END - 1) & 0xFF000000);
 
 	idr_preload(GFP_KERNEL);
-	spin_lock_irq(idr_spinlock);
+	spin_lock_irqsave(idr_spinlock, flags);
 	ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC);
-	spin_unlock_irq(idr_spinlock);
+	spin_unlock_irqrestore(idr_spinlock, flags);
 	idr_preload_end();
 
 	return ret;
@@ -157,6 +158,13 @@ static void mlx5_fpga_tls_release_swid(struct idr *idr,
 	spin_unlock_irqrestore(idr_spinlock, flags);
 }
 
+static void mlx_tls_kfree_complete(struct mlx5_fpga_conn *conn,
+				   struct mlx5_fpga_device *fdev,
+				   struct mlx5_fpga_dma_buf *buf, u8 status)
+{
+	kfree(buf);
+}
+
 struct mlx5_teardown_stream_context {
 	struct mlx5_fpga_tls_command_context cmd;
 	u32 swid;
@@ -178,9 +186,13 @@ mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn,
 			mlx5_fpga_err(fdev,
 				      "Teardown stream failed with syndrome = %d",
 				      syndrome);
-		else
+		else if (MLX5_GET(tls_cmd, cmd->buf.sg[0].data, direction_sx))
 			mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr,
-						   &fdev->tls->idr_spinlock,
+						   &fdev->tls->tx_idr_spinlock,
+						   ctx->swid);
+		else
+			mlx5_fpga_tls_release_swid(&fdev->tls->rx_idr,
+						   &fdev->tls->rx_idr_spinlock,
 						   ctx->swid);
 	}
 	mlx5_fpga_tls_put_command_ctx(cmd);
@@ -196,6 +208,40 @@ static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd)
 		 MLX5_GET(tls_flow, flow, direction_sx));
 }
 
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			    u64 rcd_sn)
+{
+	struct mlx5_fpga_dma_buf *buf;
+	int size = sizeof(*buf) + MLX5_TLS_COMMAND_SIZE;
+	void *flow;
+	void *cmd;
+	int ret;
+
+	buf = kzalloc(size, GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+
+	cmd = (buf + 1);
+
+	rcu_read_lock();
+	flow = idr_find(&mdev->fpga->tls->rx_idr, ntohl(handle));
+	rcu_read_unlock();
+	mlx5_fpga_tls_flow_to_cmd(flow, cmd);
+
+	MLX5_SET(tls_cmd, cmd, swid, ntohl(handle));
+	MLX5_SET64(tls_cmd, cmd, tls_rcd_sn, be64_to_cpu(rcd_sn));
+	MLX5_SET(tls_cmd, cmd, tcp_sn, seq);
+	MLX5_SET(tls_cmd, cmd, command_type, CMD_RESYNC_RX);
+
+	buf->sg[0].data = cmd;
+	buf->sg[0].size = MLX5_TLS_COMMAND_SIZE;
+	buf->complete = mlx_tls_kfree_complete;
+
+	ret = mlx5_fpga_sbu_conn_sendmsg(mdev->fpga->tls->conn, buf);
+
+	return ret;
+}
+
 static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 					    void *flow, u32 swid, gfp_t flags)
 {
@@ -223,14 +269,18 @@ static void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev,
 			       mlx5_fpga_tls_teardown_completion);
 }
 
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
-			       gfp_t flags)
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			    gfp_t flags, bool direction_sx)
 {
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	void *flow;
 
 	rcu_read_lock();
-	flow = idr_find(&tls->tx_idr, swid);
+	if (direction_sx)
+		flow = idr_find(&tls->tx_idr, swid);
+	else
+		flow = idr_find(&tls->rx_idr, swid);
+
 	rcu_read_unlock();
 
 	if (!flow) {
@@ -289,9 +339,11 @@ mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn,
 		 * the command context because we might not have received
 		 * the tx completion yet.
 		 */
-		mlx5_fpga_tls_del_tx_flow(fdev->mdev,
-					  MLX5_GET(tls_cmd, tls_cmd, swid),
-					  GFP_ATOMIC);
+		mlx5_fpga_tls_del_flow(fdev->mdev,
+				       MLX5_GET(tls_cmd, tls_cmd, swid),
+				       GFP_ATOMIC,
+				       MLX5_GET(tls_cmd, tls_cmd,
+						direction_sx));
 	}
 
 	mlx5_fpga_tls_put_command_ctx(cmd);
@@ -415,8 +467,7 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
 	if (err)
 		goto error;
 
-	if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 |
-				 MLX5_ACCEL_TLS_AES_GCM128))) {
+	if (!(tls->caps & (MLX5_ACCEL_TLS_V12 | MLX5_ACCEL_TLS_AES_GCM128))) {
 		err = -ENOTSUPP;
 		goto error;
 	}
@@ -438,7 +489,9 @@ int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev)
 	INIT_LIST_HEAD(&tls->pending_cmds);
 
 	idr_init(&tls->tx_idr);
-	spin_lock_init(&tls->idr_spinlock);
+	idr_init(&tls->rx_idr);
+	spin_lock_init(&tls->tx_idr_spinlock);
+	spin_lock_init(&tls->rx_idr_spinlock);
 	fdev->tls = tls;
 	return 0;
 
@@ -500,9 +553,9 @@ static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps,
 	return 0;
 }
 
-static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
-				  struct tls_crypto_info *crypto_info, u32 swid,
-				  u32 tcp_sn)
+static int _mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+				   struct tls_crypto_info *crypto_info,
+				   u32 swid, u32 tcp_sn)
 {
 	u32 caps = mlx5_fpga_tls_device_caps(mdev);
 	struct mlx5_setup_stream_context *ctx;
@@ -533,30 +586,42 @@ out:
 	return ret;
 }
 
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			      struct tls_crypto_info *crypto_info,
-			      u32 start_offload_tcp_sn, u32 *p_swid)
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			   struct tls_crypto_info *crypto_info,
+			   u32 start_offload_tcp_sn, u32 *p_swid,
+			   bool direction_sx)
 {
 	struct mlx5_fpga_tls *tls = mdev->fpga->tls;
 	int ret = -ENOMEM;
 	u32 swid;
 
-	ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow);
+	if (direction_sx)
+		ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr,
+					       &tls->tx_idr_spinlock, flow);
+	else
+		ret = mlx5_fpga_tls_alloc_swid(&tls->rx_idr,
+					       &tls->rx_idr_spinlock, flow);
+
 	if (ret < 0)
 		return ret;
 
 	swid = ret;
-	MLX5_SET(tls_flow, flow, direction_sx, 1);
+	MLX5_SET(tls_flow, flow, direction_sx, direction_sx ? 1 : 0);
 
-	ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
-				     start_offload_tcp_sn);
+	ret = _mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid,
+				      start_offload_tcp_sn);
 	if (ret && ret != -EINTR)
 		goto free_swid;
 
 	*p_swid = swid;
 	return 0;
 free_swid:
-	mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid);
+	if (direction_sx)
+		mlx5_fpga_tls_release_swid(&tls->tx_idr,
+					   &tls->tx_idr_spinlock, swid);
+	else
+		mlx5_fpga_tls_release_swid(&tls->rx_idr,
+					   &tls->rx_idr_spinlock, swid);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
index 800a214e4e49..3b2e37bf76fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h
@@ -46,15 +46,18 @@ struct mlx5_fpga_tls {
 	struct mlx5_fpga_conn *conn;
 
 	struct idr tx_idr;
-	spinlock_t idr_spinlock; /* protects the IDR */
+	struct idr rx_idr;
+	spinlock_t tx_idr_spinlock; /* protects the IDR */
+	spinlock_t rx_idr_spinlock; /* protects the IDR */
 };
 
-int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow,
-			      struct tls_crypto_info *crypto_info,
-			      u32 start_offload_tcp_sn, u32 *p_swid);
+int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
+			   struct tls_crypto_info *crypto_info,
+			   u32 start_offload_tcp_sn, u32 *p_swid,
+			   bool direction_sx);
 
-void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid,
-			       gfp_t flags);
+void mlx5_fpga_tls_del_flow(struct mlx5_core_dev *mdev, u32 swid,
+			    gfp_t flags, bool direction_sx);
 
 bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev);
 int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev);
@@ -65,4 +68,7 @@ static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev)
 	return mdev->fpga->tls->caps;
 }
 
+int mlx5_fpga_tls_resync_rx(struct mlx5_core_dev *mdev, u32 handle, u32 seq,
+			    u64 rcd_sn);
+
 #endif /* __MLX5_FPGA_TLS_H__ */
diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h
index 64d0f40d4cc3..37e065a80a43 100644
--- a/include/linux/mlx5/mlx5_ifc_fpga.h
+++ b/include/linux/mlx5/mlx5_ifc_fpga.h
@@ -576,6 +576,7 @@ struct mlx5_ifc_fpga_ipsec_sa {
 enum fpga_tls_cmds {
 	CMD_SETUP_STREAM		= 0x1001,
 	CMD_TEARDOWN_STREAM		= 0x1002,
+	CMD_RESYNC_RX			= 0x1003,
 };
 
 #define MLX5_TLS_1_2 (0)
-- 
cgit v1.2.3


From ca942c78f3237e09567d80ac19dffe9690c74d79 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:47 +0300
Subject: net/mlx5e: TLS, add innova rx support

Add the mlx5 implementation of the TLS Rx routines to add/del TLS
contexts, also add the tls_dev_resync_rx routine
to work with the TLS inline Rx crypto offload infrastructure.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 46 +++++++++++++++-------
 .../net/ethernet/mellanox/mlx5/core/en_accel/tls.h | 15 +++++++
 2 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index 7fb9c750326e..68368c965295 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -110,9 +110,7 @@ static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
 	u32 caps = mlx5_accel_tls_device_caps(mdev);
 	int ret = -ENOMEM;
 	void *flow;
-
-	if (direction != TLS_OFFLOAD_CTX_DIR_TX)
-		return -EINVAL;
+	u32 swid;
 
 	flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL);
 	if (!flow)
@@ -122,18 +120,23 @@ static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk,
 	if (ret)
 		goto free_flow;
 
+	ret = mlx5_accel_tls_add_flow(mdev, flow, crypto_info,
+				      start_offload_tcp_sn, &swid,
+				      direction == TLS_OFFLOAD_CTX_DIR_TX);
+	if (ret < 0)
+		goto free_flow;
+
 	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
 		struct mlx5e_tls_offload_context_tx *tx_ctx =
 		    mlx5e_get_tls_tx_context(tls_ctx);
-		u32 swid;
-
-		ret = mlx5_accel_tls_add_tx_flow(mdev, flow, crypto_info,
-						 start_offload_tcp_sn, &swid);
-		if (ret < 0)
-			goto free_flow;
 
 		tx_ctx->swid = htonl(swid);
 		tx_ctx->expected_seq = start_offload_tcp_sn;
+	} else {
+		struct mlx5e_tls_offload_context_rx *rx_ctx =
+		    mlx5e_get_tls_rx_context(tls_ctx);
+
+		rx_ctx->handle = htonl(swid);
 	}
 
 	return 0;
@@ -147,19 +150,32 @@ static void mlx5e_tls_del(struct net_device *netdev,
 			  enum tls_offload_ctx_dir direction)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
+	unsigned int handle;
 
-	if (direction == TLS_OFFLOAD_CTX_DIR_TX) {
-		u32 swid = ntohl(mlx5e_get_tls_tx_context(tls_ctx)->swid);
+	handle = ntohl((direction == TLS_OFFLOAD_CTX_DIR_TX) ?
+		       mlx5e_get_tls_tx_context(tls_ctx)->swid :
+		       mlx5e_get_tls_rx_context(tls_ctx)->handle);
 
-		mlx5_accel_tls_del_tx_flow(priv->mdev, swid);
-	} else {
-		netdev_err(netdev, "unsupported direction %d\n", direction);
-	}
+	mlx5_accel_tls_del_flow(priv->mdev, handle,
+				direction == TLS_OFFLOAD_CTX_DIR_TX);
+}
+
+static void mlx5e_tls_resync_rx(struct net_device *netdev, struct sock *sk,
+				u32 seq, u64 rcd_sn)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct mlx5e_priv *priv = netdev_priv(netdev);
+	struct mlx5e_tls_offload_context_rx *rx_ctx;
+
+	rx_ctx = mlx5e_get_tls_rx_context(tls_ctx);
+
+	mlx5_accel_tls_resync_rx(priv->mdev, rx_ctx->handle, seq, rcd_sn);
 }
 
 static const struct tlsdev_ops mlx5e_tls_ops = {
 	.tls_dev_add = mlx5e_tls_add,
 	.tls_dev_del = mlx5e_tls_del,
+	.tls_dev_resync_rx = mlx5e_tls_resync_rx,
 };
 
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index e26222ab26a6..2d40eded2bbb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -65,6 +65,21 @@ mlx5e_get_tls_tx_context(struct tls_context *tls_ctx)
 			    base);
 }
 
+struct mlx5e_tls_offload_context_rx {
+	struct tls_offload_context_rx base;
+	__be32 handle;
+};
+
+static inline struct mlx5e_tls_offload_context_rx *
+mlx5e_get_tls_rx_context(struct tls_context *tls_ctx)
+{
+	BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context_rx) >
+		     TLS_OFFLOAD_CONTEXT_SIZE_RX);
+	return container_of(tls_offload_ctx_rx(tls_ctx),
+			    struct mlx5e_tls_offload_context_rx,
+			    base);
+}
+
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv);
 int mlx5e_tls_init(struct mlx5e_priv *priv);
 void mlx5e_tls_cleanup(struct mlx5e_priv *priv);
-- 
cgit v1.2.3


From 00aebab27c8752c7420dce286270ccedc70ac39a Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:48 +0300
Subject: net/mlx5e: TLS, add Innova TLS rx data path

Implement the TLS rx offload data path according to the
requirements of the TLS generic NIC offload infrastructure.

Special metadata ethertype is used to pass information to
the hardware.

When hardware loses synchronization a special resync request
metadata message is used to request resync.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Ilya Lesokhin <ilyal@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlx5/core/en_accel/tls_rxtx.c         | 112 ++++++++++++++++++++-
 .../mellanox/mlx5/core/en_accel/tls_rxtx.h         |   3 +
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |   6 ++
 3 files changed, 118 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index c96196f900d7..d460fda68f00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -33,6 +33,12 @@
 
 #include "en_accel/tls.h"
 #include "en_accel/tls_rxtx.h"
+#include <net/inet6_hashtables.h>
+#include <linux/ipv6.h>
+
+#define SYNDROM_DECRYPTED  0x30
+#define SYNDROM_RESYNC_REQUEST 0x31
+#define SYNDROM_AUTH_FAILED 0x32
 
 #define SYNDROME_OFFLOAD_REQUIRED 32
 #define SYNDROME_SYNC 33
@@ -44,10 +50,26 @@ struct sync_info {
 	skb_frag_t frags[MAX_SKB_FRAGS];
 };
 
-struct mlx5e_tls_metadata {
+struct recv_metadata_content {
+	u8 syndrome;
+	u8 reserved;
+	__be32 sync_seq;
+} __packed;
+
+struct send_metadata_content {
 	/* One byte of syndrome followed by 3 bytes of swid */
 	__be32 syndrome_swid;
 	__be16 first_seq;
+} __packed;
+
+struct mlx5e_tls_metadata {
+	union {
+		/* from fpga to host */
+		struct recv_metadata_content recv;
+		/* from host to fpga */
+		struct send_metadata_content send;
+		unsigned char raw[6];
+	} __packed content;
 	/* packet type ID field	*/
 	__be16 ethertype;
 } __packed;
@@ -68,7 +90,8 @@ static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid)
 		2 * ETH_ALEN);
 
 	eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE);
-	pet->syndrome_swid = htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
+	pet->content.send.syndrome_swid =
+		htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid;
 
 	return 0;
 }
@@ -149,7 +172,7 @@ static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb,
 
 	pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr));
 	memcpy(pet, &syndrome, sizeof(syndrome));
-	pet->first_seq = htons(tcp_seq);
+	pet->content.send.first_seq = htons(tcp_seq);
 
 	/* MLX5 devices don't care about the checksum partial start, offset
 	 * and pseudo header
@@ -276,3 +299,86 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 out:
 	return skb;
 }
+
+static int tls_update_resync_sn(struct net_device *netdev,
+				struct sk_buff *skb,
+				struct mlx5e_tls_metadata *mdata)
+{
+	struct sock *sk = NULL;
+	struct iphdr *iph;
+	struct tcphdr *th;
+	__be32 seq;
+
+	if (mdata->ethertype != htons(ETH_P_IP))
+		return -EINVAL;
+
+	iph = (struct iphdr *)(mdata + 1);
+
+	th = ((void *)iph) + iph->ihl * 4;
+
+	if (iph->version == 4) {
+		sk = inet_lookup_established(dev_net(netdev), &tcp_hashinfo,
+					     iph->saddr, th->source, iph->daddr,
+					     th->dest, netdev->ifindex);
+#if IS_ENABLED(CONFIG_IPV6)
+	} else {
+		struct ipv6hdr *ipv6h = (struct ipv6hdr *)iph;
+
+		sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
+						&ipv6h->saddr, th->source,
+						&ipv6h->daddr, th->dest,
+						netdev->ifindex, 0);
+#endif
+	}
+	if (!sk || sk->sk_state == TCP_TIME_WAIT)
+		goto out;
+
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+
+	memcpy(&seq, &mdata->content.recv.sync_seq, sizeof(seq));
+	tls_offload_rx_resync_request(sk, seq);
+out:
+	return 0;
+}
+
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     u32 *cqe_bcnt)
+{
+	struct mlx5e_tls_metadata *mdata;
+	struct ethhdr *old_eth;
+	struct ethhdr *new_eth;
+	__be16 *ethtype;
+
+	/* Detect inline metadata */
+	if (skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN)
+		return;
+	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
+	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+		return;
+
+	/* Use the metadata */
+	mdata = (struct mlx5e_tls_metadata *)(skb->data + ETH_HLEN);
+	switch (mdata->content.recv.syndrome) {
+	case SYNDROM_DECRYPTED:
+		skb->decrypted = 1;
+		break;
+	case SYNDROM_RESYNC_REQUEST:
+		tls_update_resync_sn(netdev, skb, mdata);
+		break;
+	case SYNDROM_AUTH_FAILED:
+		/* Authentication failure will be observed and verified by kTLS */
+		break;
+	default:
+		/* Bypass the metadata header to others */
+		return;
+	}
+
+	/* Remove the metadata from the buffer */
+	old_eth = (struct ethhdr *)skb->data;
+	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
+	memmove(new_eth, old_eth, 2 * ETH_ALEN);
+	/* Ethertype is already in its new place */
+	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
index 405dfd302225..311667ec71b8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h
@@ -45,6 +45,9 @@ struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev,
 					struct mlx5e_tx_wqe **wqe,
 					u16 *pi);
 
+void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
+			     u32 *cqe_bcnt);
+
 #endif /* CONFIG_MLX5_EN_TLS */
 
 #endif /* __MLX5E_TLS_RXTX_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index f763a6aebc2d..0f2bcc243235 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -44,6 +44,7 @@
 #include "en_rep.h"
 #include "ipoib/ipoib.h"
 #include "en_accel/ipsec_rxtx.h"
+#include "en_accel/tls_rxtx.h"
 #include "lib/clock.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
@@ -797,6 +798,11 @@ static inline void mlx5e_build_rx_skb(struct mlx5_cqe64 *cqe,
 	struct net_device *netdev = rq->netdev;
 
 	skb->mac_len = ETH_HLEN;
+
+#ifdef CONFIG_MLX5_EN_TLS
+	mlx5e_tls_handle_rx_skb(netdev, skb, &cqe_bcnt);
+#endif
+
 	if (lro_num_seg > 1) {
 		mlx5e_lro_update_hdr(skb, cqe, cqe_bcnt);
 		skb_shinfo(skb)->gso_size = DIV_ROUND_UP(cqe_bcnt, lro_num_seg);
-- 
cgit v1.2.3


From afd3baaa938ce85dc738cd9279716cdb684cc707 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:49 +0300
Subject: net/mlx5e: TLS, add software statistics

This patch adds software statistics for TLS to count important
events.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c      |  3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h      |  4 ++++
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c | 11 ++++++++++-
 3 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index 68368c965295..541e6f4fe9e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -169,7 +169,10 @@ static void mlx5e_tls_resync_rx(struct net_device *netdev, struct sock *sk,
 
 	rx_ctx = mlx5e_get_tls_rx_context(tls_ctx);
 
+	netdev_info(netdev, "resyncing seq %d rcd %lld\n", seq,
+		    be64_to_cpu(rcd_sn));
 	mlx5_accel_tls_resync_rx(priv->mdev, rx_ctx->handle, seq, rcd_sn);
+	atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_reply);
 }
 
 static const struct tlsdev_ops mlx5e_tls_ops = {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
index 2d40eded2bbb..3f5d72163b56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h
@@ -43,6 +43,10 @@ struct mlx5e_tls_sw_stats {
 	atomic64_t tx_tls_drop_resync_alloc;
 	atomic64_t tx_tls_drop_no_sync_data;
 	atomic64_t tx_tls_drop_bypass_required;
+	atomic64_t rx_tls_drop_resync_request;
+	atomic64_t rx_tls_resync_request;
+	atomic64_t rx_tls_resync_reply;
+	atomic64_t rx_tls_auth_fail;
 };
 
 struct mlx5e_tls {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index d460fda68f00..ecfc764c0712 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -330,8 +330,12 @@ static int tls_update_resync_sn(struct net_device *netdev,
 						netdev->ifindex, 0);
 #endif
 	}
-	if (!sk || sk->sk_state == TCP_TIME_WAIT)
+	if (!sk || sk->sk_state == TCP_TIME_WAIT) {
+		struct mlx5e_priv *priv = netdev_priv(netdev);
+
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_drop_resync_request);
 		goto out;
+	}
 
 	skb->sk = sk;
 	skb->destructor = sock_edemux;
@@ -349,6 +353,7 @@ void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 	struct ethhdr *old_eth;
 	struct ethhdr *new_eth;
 	__be16 *ethtype;
+	struct mlx5e_priv *priv;
 
 	/* Detect inline metadata */
 	if (skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN)
@@ -365,9 +370,13 @@ void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 		break;
 	case SYNDROM_RESYNC_REQUEST:
 		tls_update_resync_sn(netdev, skb, mdata);
+		priv = netdev_priv(netdev);
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_resync_request);
 		break;
 	case SYNDROM_AUTH_FAILED:
 		/* Authentication failure will be observed and verified by kTLS */
+		priv = netdev_priv(netdev);
+		atomic64_inc(&priv->tls->sw_stats.rx_tls_auth_fail);
 		break;
 	default:
 		/* Bypass the metadata header to others */
-- 
cgit v1.2.3


From 790af90c00d277b7fc8bd2ba18fcfa40941bf134 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:50 +0300
Subject: net/mlx5e: TLS, build TLS netdev from capabilities

This patch enables TLS Rx based on available HW capabilities.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
index 541e6f4fe9e7..eddd7702680b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c
@@ -183,13 +183,27 @@ static const struct tlsdev_ops mlx5e_tls_ops = {
 
 void mlx5e_tls_build_netdev(struct mlx5e_priv *priv)
 {
+	u32 caps = mlx5_accel_tls_device_caps(priv->mdev);
 	struct net_device *netdev = priv->netdev;
 
 	if (!mlx5_accel_is_tls_device(priv->mdev))
 		return;
 
-	netdev->features |= NETIF_F_HW_TLS_TX;
-	netdev->hw_features |= NETIF_F_HW_TLS_TX;
+	if (caps & MLX5_ACCEL_TLS_TX) {
+		netdev->features          |= NETIF_F_HW_TLS_TX;
+		netdev->hw_features       |= NETIF_F_HW_TLS_TX;
+	}
+
+	if (caps & MLX5_ACCEL_TLS_RX) {
+		netdev->features          |= NETIF_F_HW_TLS_RX;
+		netdev->hw_features       |= NETIF_F_HW_TLS_RX;
+	}
+
+	if (!(caps & MLX5_ACCEL_TLS_LRO)) {
+		netdev->features          &= ~NETIF_F_LRO;
+		netdev->hw_features       &= ~NETIF_F_LRO;
+	}
+
 	netdev->tlsdev_ops = &mlx5e_tls_ops;
 }
 
-- 
cgit v1.2.3


From 10e71acca28262a9db47ce9b0a10dcd8b38bbdeb Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:51 +0300
Subject: net/mlx5: Accel, add common metadata functions

This patch adds common functions to handle mellanox metadata headers.
These functions are used by IPsec and TLS to process FPGA metadata.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlx5/core/accel/accel.h  | 37 ++++++++++++++++++++++
 .../mellanox/mlx5/core/en_accel/ipsec_rxtx.c       | 19 +++--------
 .../mellanox/mlx5/core/en_accel/tls_rxtx.c         | 18 +++--------
 3 files changed, 45 insertions(+), 29 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
new file mode 100644
index 000000000000..c13260467750
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/accel.h
@@ -0,0 +1,37 @@
+#ifndef __MLX5E_ACCEL_H__
+#define __MLX5E_ACCEL_H__
+
+#ifdef CONFIG_MLX5_ACCEL
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include "en.h"
+
+static inline bool is_metadata_hdr_valid(struct sk_buff *skb)
+{
+	__be16 *ethtype;
+
+	if (unlikely(skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN))
+		return false;
+	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
+	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+		return false;
+	return true;
+}
+
+static inline void remove_metadata_hdr(struct sk_buff *skb)
+{
+	struct ethhdr *old_eth;
+	struct ethhdr *new_eth;
+
+	/* Remove the metadata from the buffer */
+	old_eth = (struct ethhdr *)skb->data;
+	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
+	memmove(new_eth, old_eth, 2 * ETH_ALEN);
+	/* Ethertype is already in its new place */
+	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+}
+
+#endif /* CONFIG_MLX5_ACCEL */
+
+#endif /* __MLX5E_EN_ACCEL_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index c245d8e78509..fda7929de9d6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -37,6 +37,7 @@
 
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/ipsec.h"
+#include "accel/accel.h"
 #include "en.h"
 
 enum {
@@ -346,19 +347,12 @@ mlx5e_ipsec_build_sp(struct net_device *netdev, struct sk_buff *skb,
 }
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
-					  struct sk_buff *skb)
+					  struct sk_buff *skb, u32 *cqe_bcnt)
 {
 	struct mlx5e_ipsec_metadata *mdata;
-	struct ethhdr *old_eth;
-	struct ethhdr *new_eth;
 	struct xfrm_state *xs;
-	__be16 *ethtype;
 
-	/* Detect inline metadata */
-	if (skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN)
-		return skb;
-	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
-	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+	if (!is_metadata_hdr_valid(skb))
 		return skb;
 
 	/* Use the metadata */
@@ -369,12 +363,7 @@ struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 		return NULL;
 	}
 
-	/* Remove the metadata from the buffer */
-	old_eth = (struct ethhdr *)skb->data;
-	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
-	memmove(new_eth, old_eth, 2 * ETH_ALEN);
-	/* Ethertype is already in its new place */
-	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+	remove_metadata_hdr(skb);
 
 	return skb;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index ecfc764c0712..92d37459850e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -33,6 +33,8 @@
 
 #include "en_accel/tls.h"
 #include "en_accel/tls_rxtx.h"
+#include "accel/accel.h"
+
 #include <net/inet6_hashtables.h>
 #include <linux/ipv6.h>
 
@@ -350,16 +352,9 @@ void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 			     u32 *cqe_bcnt)
 {
 	struct mlx5e_tls_metadata *mdata;
-	struct ethhdr *old_eth;
-	struct ethhdr *new_eth;
-	__be16 *ethtype;
 	struct mlx5e_priv *priv;
 
-	/* Detect inline metadata */
-	if (skb->len < ETH_HLEN + MLX5E_METADATA_ETHER_LEN)
-		return;
-	ethtype = (__be16 *)(skb->data + ETH_ALEN * 2);
-	if (*ethtype != cpu_to_be16(MLX5E_METADATA_ETHER_TYPE))
+	if (!is_metadata_hdr_valid(skb))
 		return;
 
 	/* Use the metadata */
@@ -383,11 +378,6 @@ void mlx5e_tls_handle_rx_skb(struct net_device *netdev, struct sk_buff *skb,
 		return;
 	}
 
-	/* Remove the metadata from the buffer */
-	old_eth = (struct ethhdr *)skb->data;
-	new_eth = (struct ethhdr *)(skb->data + MLX5E_METADATA_ETHER_LEN);
-	memmove(new_eth, old_eth, 2 * ETH_ALEN);
-	/* Ethertype is already in its new place */
-	skb_pull_inline(skb, MLX5E_METADATA_ETHER_LEN);
+	remove_metadata_hdr(skb);
 	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
 }
-- 
cgit v1.2.3


From b3ccf978132ed7d0add45ca56e810a36ce7febf3 Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Fri, 13 Jul 2018 14:33:52 +0300
Subject: net/mlx5e: IPsec, fix byte count in CQE

This patch fixes the byte count indication in CQE for processed IPsec
packets that contain a metadata header.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c               | 2 +-
 3 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
index fda7929de9d6..128a82b1dbfc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.c
@@ -364,6 +364,7 @@ struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
 	}
 
 	remove_metadata_hdr(skb);
+	*cqe_bcnt -= MLX5E_METADATA_ETHER_LEN;
 
 	return skb;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
index 2bfbbef1b054..ca47c0540904 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_rxtx.h
@@ -41,7 +41,7 @@
 #include "en.h"
 
 struct sk_buff *mlx5e_ipsec_handle_rx_skb(struct net_device *netdev,
-					  struct sk_buff *skb);
+					  struct sk_buff *skb, u32 *cqe_bcnt);
 void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 
 void mlx5e_ipsec_inverse_table_init(void);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 0f2bcc243235..1d5295ee863c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1547,7 +1547,7 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 		mlx5e_free_rx_wqe(rq, wi);
 		goto wq_cyc_pop;
 	}
-	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb);
+	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
 	if (unlikely(!skb)) {
 		mlx5e_free_rx_wqe(rq, wi);
 		goto wq_cyc_pop;
-- 
cgit v1.2.3


From bdf4424dc3b180e40718034a30eced5c1eac8588 Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Wed, 30 May 2018 15:36:42 +1000
Subject: drm/nouveau/gr/gv100: handle multiple SM-per-TPC for shader
 exceptions

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
index 19173ea19096..3b3327789ae7 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gv100.c
@@ -25,24 +25,31 @@
 #include <nvif/class.h>
 
 static void
-gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
+gv100_gr_trap_sm(struct gf100_gr *gr, int gpc, int tpc, int sm)
 {
 	struct nvkm_subdev *subdev = &gr->base.engine.subdev;
 	struct nvkm_device *device = subdev->device;
-	u32 werr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x730));
-	u32 gerr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x734));
+	u32 werr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x730 + (sm * 0x80)));
+	u32 gerr = nvkm_rd32(device, TPC_UNIT(gpc, tpc, 0x734 + (sm * 0x80)));
 	const struct nvkm_enum *warp;
 	char glob[128];
 
 	nvkm_snprintbf(glob, sizeof(glob), gf100_mp_global_error, gerr);
 	warp = nvkm_enum_find(gf100_mp_warp_error, werr & 0xffff);
 
-	nvkm_error(subdev, "GPC%i/TPC%i/MP trap: "
+	nvkm_error(subdev, "GPC%i/TPC%i/SM%d trap: "
 			   "global %08x [%s] warp %04x [%s]\n",
-		   gpc, tpc, gerr, glob, werr, warp ? warp->name : "");
+		   gpc, tpc, sm, gerr, glob, werr, warp ? warp->name : "");
+
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x730 + sm * 0x80), 0x00000000);
+	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734 + sm * 0x80), gerr);
+}
 
-	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x730), 0x00000000);
-	nvkm_wr32(device, TPC_UNIT(gpc, tpc, 0x734), gerr);
+static void
+gv100_gr_trap_mp(struct gf100_gr *gr, int gpc, int tpc)
+{
+	gv100_gr_trap_sm(gr, gpc, tpc, 0);
+	gv100_gr_trap_sm(gr, gpc, tpc, 1);
 }
 
 static void
-- 
cgit v1.2.3


From 60cda665724a33af1486d0a84190b384f180bb0e Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Wed, 13 Jun 2018 15:33:16 +1000
Subject: drm/nouveau/fault/gv100: fix fault buffer initialisation

Not sure how this happened, it worked last time I tested it!

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c  | 10 ++++++++--
 drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c | 21 ++++++++++-----------
 drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h  |  1 +
 3 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
index 007bf4af33b9..16ad91c91a7b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/base.c
@@ -133,8 +133,14 @@ nvkm_fault_oneinit(struct nvkm_subdev *subdev)
 		}
 	}
 
-	return nvkm_event_init(&nvkm_fault_ntfy, 1, fault->buffer_nr,
-			       &fault->event);
+	ret = nvkm_event_init(&nvkm_fault_ntfy, 1, fault->buffer_nr,
+			      &fault->event);
+	if (ret)
+		return ret;
+
+	if (fault->func->oneinit)
+		ret = fault->func->oneinit(fault);
+	return ret;
 }
 
 static void *
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
index 73c7728b5969..3cd610d7deb5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/gv100.c
@@ -176,8 +176,17 @@ gv100_fault_init(struct nvkm_fault *fault)
 	nvkm_notify_get(&fault->nrpfb);
 }
 
+static int
+gv100_fault_oneinit(struct nvkm_fault *fault)
+{
+	return nvkm_notify_init(&fault->buffer[0]->object, &fault->event,
+				gv100_fault_ntfy_nrpfb, false, NULL, 0, 0,
+				&fault->nrpfb);
+}
+
 static const struct nvkm_fault_func
 gv100_fault = {
+	.oneinit = gv100_fault_oneinit,
 	.init = gv100_fault_init,
 	.fini = gv100_fault_fini,
 	.intr = gv100_fault_intr,
@@ -192,15 +201,5 @@ int
 gv100_fault_new(struct nvkm_device *device, int index,
 		struct nvkm_fault **pfault)
 {
-	struct nvkm_fault *fault;
-	int ret;
-
-	ret = nvkm_fault_new_(&gv100_fault, device, index, &fault);
-	*pfault = fault;
-	if (ret)
-		return ret;
-
-	return nvkm_notify_init(&fault->buffer[0]->object, &fault->event,
-				gv100_fault_ntfy_nrpfb, false, NULL, 0, 0,
-				&fault->nrpfb);
+	return nvkm_fault_new_(&gv100_fault, device, index, pfault);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
index 44843ecf12b0..e4d2f5234fd1 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fault/priv.h
@@ -20,6 +20,7 @@ int nvkm_fault_new_(const struct nvkm_fault_func *, struct nvkm_device *,
 		    int index, struct nvkm_fault **);
 
 struct nvkm_fault_func {
+	int (*oneinit)(struct nvkm_fault *);
 	void (*init)(struct nvkm_fault *);
 	void (*fini)(struct nvkm_fault *);
 	void (*intr)(struct nvkm_fault *);
-- 
cgit v1.2.3


From 3c9f27eeedb76fb65fc572adbb58d7f4ca154536 Mon Sep 17 00:00:00 2001
From: Nicolas Chauvet <kwizart@gmail.com>
Date: Sun, 10 Jun 2018 13:01:31 +0200
Subject: drm/nouveau/secboot/tegra: Enable gp20b/gp10b firmware tag when
 relevant

This allows to have the related MODULE_FIRMWARE tag only
on relevant arch (arm64).
This will saves about 400k on initramfs when not relevant

Signed-off-by: Nicolas Chauvet <kwizart@gmail.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c | 2 ++
 drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
index 30491d132d59..df8b919dcf09 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gm20b.c
@@ -129,6 +129,7 @@ gm20b_secboot_new(struct nvkm_device *device, int index,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
 MODULE_FIRMWARE("nvidia/gm20b/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/gm20b/acr/ucode_load.bin");
 MODULE_FIRMWARE("nvidia/gm20b/gr/fecs_bl.bin");
@@ -144,3 +145,4 @@ MODULE_FIRMWARE("nvidia/gm20b/gr/sw_method_init.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gm20b/pmu/sig.bin");
+#endif
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
index 632e9545e292..28ca29d0eeee 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/gp10b.c
@@ -74,6 +74,7 @@ gp10b_secboot_new(struct nvkm_device *device, int index,
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
 MODULE_FIRMWARE("nvidia/gp10b/acr/bl.bin");
 MODULE_FIRMWARE("nvidia/gp10b/acr/ucode_load.bin");
 MODULE_FIRMWARE("nvidia/gp10b/gr/fecs_bl.bin");
@@ -91,3 +92,4 @@ MODULE_FIRMWARE("nvidia/gp10b/gr/sw_method_init.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");
+#endif
-- 
cgit v1.2.3


From f0fffeeb149e6d1fe05f2c8d6e385c5e82814cff Mon Sep 17 00:00:00 2001
From: Jérôme Glisse <jglisse@redhat.com>
Date: Thu, 7 Jun 2018 14:18:24 -0400
Subject: drm/nouveau/mmu/gp10b: remove ghost file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This ghost file have been haunting us.

Signed-off-by: Jérôme Glisse <jglisse@redhat.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b. | 0
 1 file changed, 0 insertions(+), 0 deletions(-)
 delete mode 100644 drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b. b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/gp10b.
deleted file mode 100644
index e69de29bb2d1..000000000000
-- 
cgit v1.2.3


From f7fbbf2ccaa0f557c4615a5cf3e1e5704585628a Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Fri, 15 Jun 2018 07:59:28 +1000
Subject: drm/nouveau/core: ERR_PTR vs NULL bug in nvkm_engine_info()

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/core/engine.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/core/engine.c b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
index d0322ce85172..1a47c40e171b 100644
--- a/drivers/gpu/drm/nouveau/nvkm/core/engine.c
+++ b/drivers/gpu/drm/nouveau/nvkm/core/engine.c
@@ -87,11 +87,12 @@ nvkm_engine_info(struct nvkm_subdev *subdev, u64 mthd, u64 *data)
 {
 	struct nvkm_engine *engine = nvkm_engine(subdev);
 	if (engine->func->info) {
-		if ((engine = nvkm_engine_ref(engine))) {
+		if (!IS_ERR((engine = nvkm_engine_ref(engine)))) {
 			int ret = engine->func->info(engine, mthd, data);
 			nvkm_engine_unref(&engine);
 			return ret;
 		}
+		return PTR_ERR(engine);
 	}
 	return -ENOSYS;
 }
-- 
cgit v1.2.3


From 7a26c92367a7195277bf663eca69c55b863b4d7b Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Fri, 15 Jun 2018 08:02:33 +1000
Subject: drm/nouveau/disp/nv50-gp10x: fix coverity warning

Change values to u32, there's no need for them to be 64-bit.

Reported-by: Colin Ian King <colin.king@canonical.com>
Suggested-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c | 2 +-
 drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c  | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
index 29e6dd58ac48..525f95d06429 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/changf119.c
@@ -52,7 +52,7 @@ void
 gf119_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
 {
 	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
-	const u64 mask = 0x00000001 << chan->chid.user;
+	const u32 mask = 0x00000001 << chan->chid.user;
 	if (!en) {
 		nvkm_mask(device, 0x610090, mask, 0x00000000);
 		nvkm_mask(device, 0x6100a0, mask, 0x00000000);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
index 57719f675eec..bcf32d92ee5a 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/channv50.c
@@ -166,8 +166,8 @@ void
 nv50_disp_chan_intr(struct nv50_disp_chan *chan, bool en)
 {
 	struct nvkm_device *device = chan->disp->base.engine.subdev.device;
-	const u64 mask = 0x00010001 << chan->chid.user;
-	const u64 data = en ? 0x00010000 : 0x00000000;
+	const u32 mask = 0x00010001 << chan->chid.user;
+	const u32 data = en ? 0x00010000 << chan->chid.user : 0x00000000;
 	nvkm_mask(device, 0x610028, mask, data);
 }
 
-- 
cgit v1.2.3


From 01981aeb4745e31e0842b6f9f98be9b99615db3c Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Fri, 18 May 2018 18:51:32 +0200
Subject: drm/nouveau/kms/nv50-: fix drm-get-put.cocci warnings

 Use drm_*_get() and drm_*_put() helpers instead of drm_*_reference() and
 drm_*_unreference() helpers.

Generated by: scripts/coccinelle/api/drm-get-put.cocci

Fixes: 30ed49b55b6e ("drm/nouveau/kms/nv50-: move code underneath dispnv50/")
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/dispnv50/disp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index b83465ae7c1b..1f8bba8f6528 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -1007,7 +1007,7 @@ nv50_mstm_destroy_connector(struct drm_dp_mst_topology_mgr *mgr,
 	mstc->port = NULL;
 	drm_modeset_unlock(&drm->dev->mode_config.connection_mutex);
 
-	drm_connector_unreference(&mstc->connector);
+	drm_connector_put(&mstc->connector);
 }
 
 static void
-- 
cgit v1.2.3


From 6ec7aecf1f1080d058943d4c44edff470c67679b Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Mon, 18 Jun 2018 17:53:12 +1000
Subject: drm/nouveau/kms/nv50-: remove duplicate assignment

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/dispnv50/wndw.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/dispnv50/wndw.c b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
index c5a9bc1af5af..2187922e8dc2 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/wndw.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/wndw.c
@@ -586,7 +586,6 @@ nv50_wndw_new_(const struct nv50_wndw_func *func, struct drm_device *dev,
 	wndw->id = index;
 	wndw->interlock.type = interlock_type;
 	wndw->interlock.data = interlock_data;
-	wndw->ctxdma.parent = &wndw->wndw.base.user;
 
 	wndw->ctxdma.parent = &wndw->wndw.base.user;
 	INIT_LIST_HEAD(&wndw->ctxdma.list);
-- 
cgit v1.2.3


From 2ae4c5f6ff7310e4dcaca4378ddadd881d176693 Mon Sep 17 00:00:00 2001
From: Mario Kleiner <mario.kleiner.de@gmail.com>
Date: Mon, 16 Jul 2018 16:47:50 +1000
Subject: drm/nouveau/kms/nv50-: Allow vblank_disable_immediate

With instantaneous high precision vblank timestamping
that updates at leading edge of vblank, the emulated
"hw vblank counter" from vblank timestamping, which
increments at leading edge of vblank, and reliable
page flip execution and completion at leading edge of
vblank, we should meet the requirements for fast/
immediate vblank irq disable/enable.

This is only allowed on nv50+ gpu's, ie. the ones with
atomic modesetting. One requirement for immediate vblank
disable is that high precision vblank timestamping works
reliably all the time on all connectors. This is not the
case on all pre-nv50 parts for analog VGA outputs, where we
currently don't always have support for scanout position
queries and therefore fall back to vblank interrupt
timestamping. The implementation in nv04_head_state() does
not return valid values for vblanks, vtotal, hblanks, htotal
for VGA outputs on all cards, but those are needed for scanout
position queries.

Testing on Linux-4.12-rc5 + drm-next on a GeForce 9500 GT
(NV G96) with timing measurement equipment indicates this
works fine, so allow immediate vblank disable for power
saving.

For debugging in case of unexpected trouble, booting
with kernel cmdline option drm.vblankoffdelay=0
(or echo 0 > /sys/module/drm/parameters/vblankoffdelay)
would keep vblank irqs permanently on to approximate old
behavior.

Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/dispnv50/disp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 1f8bba8f6528..7d00d833bbe5 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -2231,6 +2231,9 @@ nv50_display_create(struct drm_device *dev)
 		connector->funcs->destroy(connector);
 	}
 
+	/* Disable vblank irqs aggressively for power-saving, safe on nv50+ */
+	dev->vblank_disable_immediate = true;
+
 out:
 	if (ret)
 		nv50_display_destroy(dev);
-- 
cgit v1.2.3


From f706037c4e135d322160e201872ee3567435035a Mon Sep 17 00:00:00 2001
From: Karol Herbst <karolherbst@gmail.com>
Date: Sat, 14 Jul 2018 12:52:08 +0200
Subject: drm/nouveau/bios/vpstate: There are some fermi vbios with no boost or
 tdp entry

If the entry size is too small, default to invalid values for both
boost_id and tdp_id, so as to default to the base clock in both cases.

Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
index 20b6fc8243e0..71524548de32 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/vpstate.c
@@ -58,8 +58,14 @@ nvbios_vpstate_parse(struct nvkm_bios *b, struct nvbios_vpstate_header *h)
 		h->ecount   = nvbios_rd08(b, h->offset + 0x5);
 
 		h->base_id  = nvbios_rd08(b, h->offset + 0x0f);
-		h->boost_id = nvbios_rd08(b, h->offset + 0x10);
-		h->tdp_id   = nvbios_rd08(b, h->offset + 0x11);
+		if (h->hlen > 0x10)
+			h->boost_id = nvbios_rd08(b, h->offset + 0x10);
+		else
+			h->boost_id = 0xff;
+		if (h->hlen > 0x11)
+			h->tdp_id = nvbios_rd08(b, h->offset + 0x11);
+		else
+			h->tdp_id = 0xff;
 		return 0;
 	default:
 		return -EINVAL;
-- 
cgit v1.2.3


From eaeb9010bb4bcdc20e58254fa42f3fe730a7f908 Mon Sep 17 00:00:00 2001
From: Karol Herbst <karolherbst@gmail.com>
Date: Sat, 14 Jul 2018 12:52:09 +0200
Subject: drm/nouveau/debugfs: Wake up GPU before doing any reclocking

Fixes various reclocking related issues on prime systems.

Signed-off-by: Karol Herbst <karolherbst@gmail.com>
Signed-off-by: Martin Peres <martin.peres@free.fr>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_debugfs.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
index 963a4dba8213..9109b69cd052 100644
--- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c
+++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c
@@ -160,7 +160,11 @@ nouveau_debugfs_pstate_set(struct file *file, const char __user *ubuf,
 		args.ustate = value;
 	}
 
+	ret = pm_runtime_get_sync(drm->dev);
+	if (IS_ERR_VALUE(ret) && ret != -EACCES)
+		return ret;
 	ret = nvif_mthd(ctrl, NVIF_CONTROL_PSTATE_USER, &args, sizeof(args));
+	pm_runtime_put_autosuspend(drm->dev);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 922a8c82fafdec99688bbaea6c5889f562a42cdc Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Thu, 12 Jul 2018 13:02:52 -0400
Subject: drm/nouveau: Fix runtime PM leak in drm_open()

Noticed this as I was skimming through, if we fail to allocate memory
for cli we'll end up returning without dropping the runtime PM ref we
got. Additionally, we'll even return the wrong return code! (ret most
likely will == 0 here, we want -ENOMEM).

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_drm.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 775443c9af94..c779ee3c665b 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -912,8 +912,10 @@ nouveau_drm_open(struct drm_device *dev, struct drm_file *fpriv)
 	get_task_comm(tmpname, current);
 	snprintf(name, sizeof(name), "%s[%d]", tmpname, pid_nr(fpriv->pid));
 
-	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL)))
-		return ret;
+	if (!(cli = kzalloc(sizeof(*cli), GFP_KERNEL))) {
+		ret = -ENOMEM;
+		goto done;
+	}
 
 	ret = nouveau_cli_init(drm, name, cli);
 	if (ret)
-- 
cgit v1.2.3


From da71f0efe714ecf71d450f882b94e2acd8e0c3c0 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 11 Jul 2018 11:02:28 +0300
Subject: drm/nouveau/hwmon: potential uninitialized variables

Smatch complains that "value" can be uninitialized when kstrtol()
returns -ERANGE.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_hwmon.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_hwmon.c b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
index 44178b4c3599..08a1ab6b150d 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hwmon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hwmon.c
@@ -69,8 +69,8 @@ nouveau_hwmon_set_temp1_auto_point1_temp(struct device *d,
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 	long value;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
-		return count;
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
 
 	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST,
 			value / 1000);
@@ -102,8 +102,8 @@ nouveau_hwmon_set_temp1_auto_point1_temp_hyst(struct device *d,
 	struct nvkm_therm *therm = nvxx_therm(&drm->client.device);
 	long value;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
-		return count;
+	if (kstrtol(buf, 10, &value))
+		return -EINVAL;
 
 	therm->attr_set(therm, NVKM_THERM_ATTR_THRS_FAN_BOOST_HYST,
 			value / 1000);
@@ -156,7 +156,7 @@ nouveau_hwmon_set_pwm1_min(struct device *d, struct device_attribute *a,
 	long value;
 	int ret;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
+	if (kstrtol(buf, 10, &value))
 		return -EINVAL;
 
 	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MIN_DUTY, value);
@@ -179,7 +179,7 @@ nouveau_hwmon_set_pwm1_max(struct device *d, struct device_attribute *a,
 	long value;
 	int ret;
 
-	if (kstrtol(buf, 10, &value) == -EINVAL)
+	if (kstrtol(buf, 10, &value))
 		return -EINVAL;
 
 	ret = therm->attr_set(therm, NVKM_THERM_ATTR_FAN_MAX_DUTY, value);
-- 
cgit v1.2.3


From c9fb2cc84c31910e710cdd8d67a01473170ea67d Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Fri, 15 Jun 2018 16:00:42 -0700
Subject: drm/nouveau/nvif: remove const attribute from nvif_mclass

Similar to commit 0bf8bf50eddc ("module: Remove
const attribute from alias for MODULE_DEVICE_TABLE")

Fixes many -Wduplicate-decl-specifier warnings due to the combination of
const typeof() of already const variables.

Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/include/nvif/object.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/include/nvif/object.h b/drivers/gpu/drm/nouveau/include/nvif/object.h
index 20754d9e6883..8407651f6ac6 100644
--- a/drivers/gpu/drm/nouveau/include/nvif/object.h
+++ b/drivers/gpu/drm/nouveau/include/nvif/object.h
@@ -78,7 +78,7 @@ struct nvif_mclass {
 #define nvif_mclass(o,m) ({                                                    \
 	struct nvif_object *object = (o);                                      \
 	struct nvif_sclass *sclass;                                            \
-	const typeof(m[0]) *mclass = (m);                                      \
+	typeof(m[0]) *mclass = (m);                                            \
 	int ret = -ENODEV;                                                     \
 	int cnt, i, j;                                                         \
                                                                                \
-- 
cgit v1.2.3


From f066f7950708d889f59545c6c9f426885dcf3dcb Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 14:53:10 +0200
Subject: drm/nouveau: Replace drm_framebuffer_{un/reference} with put, get
 functions

This patch unifies the naming of DRM functions for reference counting
of struct drm_framebuffer. The resulting code is more aligned with the
rest of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_fbcon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
index 85c1f10bc2b6..844498c4267c 100644
--- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c
@@ -429,7 +429,7 @@ nouveau_fbcon_destroy(struct drm_device *dev, struct nouveau_fbdev *fbcon)
 		nouveau_vma_del(&nouveau_fb->vma);
 		nouveau_bo_unmap(nouveau_fb->nvbo);
 		nouveau_bo_unpin(nouveau_fb->nvbo);
-		drm_framebuffer_unreference(&nouveau_fb->base);
+		drm_framebuffer_put(&nouveau_fb->base);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 743e0f079a38182cb22e663b34e6a45ad3274b9e Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 14:53:11 +0200
Subject: drm/nouveau: Replace drm_gem_object_unreference_unlocked with put
 function

This patch unifies the naming of DRM functions for reference counting
of struct drm_gem_object. The resulting code is more aligned with the
rest of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/dispnv04/crtc.c   |  2 +-
 drivers/gpu/drm/nouveau/nouveau_abi16.c   |  2 +-
 drivers/gpu/drm/nouveau/nouveau_display.c |  8 ++++----
 drivers/gpu/drm/nouveau/nouveau_gem.c     | 14 +++++++-------
 4 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
index 6aa6ee16dcbd..2c569e264df3 100644
--- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c
+++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c
@@ -1017,7 +1017,7 @@ nv04_crtc_cursor_set(struct drm_crtc *crtc, struct drm_file *file_priv,
 	nv_crtc->cursor.set_offset(nv_crtc, nv_crtc->cursor.offset);
 	nv_crtc->cursor.show(nv_crtc, true);
 out:
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c
index e2211bb2cf79..e67a471331b5 100644
--- a/drivers/gpu/drm/nouveau/nouveau_abi16.c
+++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c
@@ -139,7 +139,7 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16,
 	if (chan->ntfy) {
 		nouveau_vma_del(&chan->ntfy_vma);
 		nouveau_bo_unpin(chan->ntfy);
-		drm_gem_object_unreference_unlocked(&chan->ntfy->gem);
+		drm_gem_object_put_unlocked(&chan->ntfy->gem);
 	}
 
 	if (chan->heap.block_size)
diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c
index 774b429142bc..dfa236370726 100644
--- a/drivers/gpu/drm/nouveau/nouveau_display.c
+++ b/drivers/gpu/drm/nouveau/nouveau_display.c
@@ -205,7 +205,7 @@ nouveau_user_framebuffer_destroy(struct drm_framebuffer *drm_fb)
 	struct nouveau_framebuffer *fb = nouveau_framebuffer(drm_fb);
 
 	if (fb->nvbo)
-		drm_gem_object_unreference_unlocked(&fb->nvbo->gem);
+		drm_gem_object_put_unlocked(&fb->nvbo->gem);
 
 	drm_framebuffer_cleanup(drm_fb);
 	kfree(fb);
@@ -287,7 +287,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev,
 	if (ret == 0)
 		return &fb->base;
 
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ERR_PTR(ret);
 }
 
@@ -939,7 +939,7 @@ nouveau_display_dumb_create(struct drm_file *file_priv, struct drm_device *dev,
 		return ret;
 
 	ret = drm_gem_handle_create(file_priv, &bo->gem, &args->handle);
-	drm_gem_object_unreference_unlocked(&bo->gem);
+	drm_gem_object_put_unlocked(&bo->gem);
 	return ret;
 }
 
@@ -954,7 +954,7 @@ nouveau_display_dumb_map_offset(struct drm_file *file_priv,
 	if (gem) {
 		struct nouveau_bo *bo = nouveau_gem_object(gem);
 		*poffset = drm_vma_node_offset_addr(&bo->bo.vma_node);
-		drm_gem_object_unreference_unlocked(gem);
+		drm_gem_object_put_unlocked(gem);
 		return 0;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c
index 300daee74209..df73bec354e8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_gem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_gem.c
@@ -274,7 +274,7 @@ nouveau_gem_ioctl_new(struct drm_device *dev, void *data,
 	}
 
 	/* drop reference from allocate - handle holds it now */
-	drm_gem_object_unreference_unlocked(&nvbo->gem);
+	drm_gem_object_put_unlocked(&nvbo->gem);
 	return ret;
 }
 
@@ -354,7 +354,7 @@ validate_fini_no_ticket(struct validate_op *op, struct nouveau_fence *fence,
 		list_del(&nvbo->entry);
 		nvbo->reserved_by = NULL;
 		ttm_bo_unreserve(&nvbo->bo);
-		drm_gem_object_unreference_unlocked(&nvbo->gem);
+		drm_gem_object_put_unlocked(&nvbo->gem);
 	}
 }
 
@@ -400,14 +400,14 @@ retry:
 		nvbo = nouveau_gem_object(gem);
 		if (nvbo == res_bo) {
 			res_bo = NULL;
-			drm_gem_object_unreference_unlocked(gem);
+			drm_gem_object_put_unlocked(gem);
 			continue;
 		}
 
 		if (nvbo->reserved_by && nvbo->reserved_by == file_priv) {
 			NV_PRINTK(err, cli, "multiple instances of buffer %d on "
 				      "validation list\n", b->handle);
-			drm_gem_object_unreference_unlocked(gem);
+			drm_gem_object_put_unlocked(gem);
 			ret = -EINVAL;
 			break;
 		}
@@ -894,7 +894,7 @@ nouveau_gem_ioctl_cpu_prep(struct drm_device *dev, void *data,
 		ret = lret;
 
 	nouveau_bo_sync_for_cpu(nvbo);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 
 	return ret;
 }
@@ -913,7 +913,7 @@ nouveau_gem_ioctl_cpu_fini(struct drm_device *dev, void *data,
 	nvbo = nouveau_gem_object(gem);
 
 	nouveau_bo_sync_for_device(nvbo);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return 0;
 }
 
@@ -930,7 +930,7 @@ nouveau_gem_ioctl_info(struct drm_device *dev, void *data,
 		return -ENOENT;
 
 	ret = nouveau_gem_info(file_priv, gem, req);
-	drm_gem_object_unreference_unlocked(gem);
+	drm_gem_object_put_unlocked(gem);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 94a0b8634f4ccb0a512702f96df67914b615d556 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 18 Jun 2018 14:53:12 +0200
Subject: drm/nouveau: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nouveau_platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 1ada186fab77..039e23548e08 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -36,7 +36,7 @@ static int nouveau_platform_probe(struct platform_device *pdev)
 
 	ret = drm_dev_register(drm, 0);
 	if (ret < 0) {
-		drm_dev_unref(drm);
+		drm_dev_put(drm);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From 0d466901552a8b4e80cb3c0968e344751c2c9ac3 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 24 May 2018 10:24:36 -0700
Subject: drm/nouveau/secboot/acr: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], this
allocates the working buffers before starting the writing so it won't
abort in the middle. This needs an initial walk of the lists to figure
out how large the buffer should be.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 .../gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c | 25 +++++++++++++++++++---
 .../gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c | 16 +++++++++++++-
 2 files changed, 37 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
index a721354249ce..d02e183717dc 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r352.c
@@ -414,6 +414,20 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 {
 	struct ls_ucode_img *_img;
 	u32 pos = 0;
+	u32 max_desc_size = 0;
+	u8 *gdesc;
+
+	/* Figure out how large we need gdesc to be. */
+	list_for_each_entry(_img, imgs, node) {
+		const struct acr_r352_ls_func *ls_func =
+					    acr->func->ls_func[_img->falcon_id];
+
+		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
+	}
+
+	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
+	if (!gdesc)
+		return -ENOMEM;
 
 	nvkm_kmap(wpr_blob);
 
@@ -421,7 +435,6 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 		struct ls_ucode_img_r352 *img = ls_ucode_img_r352(_img);
 		const struct acr_r352_ls_func *ls_func =
 					    acr->func->ls_func[_img->falcon_id];
-		u8 gdesc[ls_func->bl_desc_size];
 
 		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
 				      sizeof(img->wpr_header));
@@ -447,6 +460,8 @@ acr_r352_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 
 	nvkm_done(wpr_blob);
 
+	kfree(gdesc);
+
 	return 0;
 }
 
@@ -771,7 +786,11 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 	struct fw_bl_desc *hsbl_desc;
 	void *bl, *blob_data, *hsbl_code, *hsbl_data;
 	u32 code_size;
-	u8 bl_desc[bl_desc_size];
+	u8 *bl_desc;
+
+	bl_desc = kzalloc(bl_desc_size, GFP_KERNEL);
+	if (!bl_desc)
+		return -ENOMEM;
 
 	/* Find the bootloader descriptor for our blob and copy it */
 	if (blob == acr->load_blob) {
@@ -802,7 +821,6 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 			      code_size, hsbl_desc->start_tag, 0, false);
 
 	/* Generate the BL header */
-	memset(bl_desc, 0, bl_desc_size);
 	acr->func->generate_hs_bl_desc(load_hdr, bl_desc, offset);
 
 	/*
@@ -811,6 +829,7 @@ acr_r352_load(struct nvkm_acr *_acr, struct nvkm_falcon *falcon,
 	nvkm_falcon_load_dmem(falcon, bl_desc, hsbl_desc->dmem_load_off,
 			      bl_desc_size, 0);
 
+	kfree(bl_desc);
 	return hsbl_desc->start_tag << 8;
 }
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
index 866877b88797..978ad0790367 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/secboot/acr_r367.c
@@ -265,6 +265,19 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 {
 	struct ls_ucode_img *_img;
 	u32 pos = 0;
+	u32 max_desc_size = 0;
+	u8 *gdesc;
+
+	list_for_each_entry(_img, imgs, node) {
+		const struct acr_r352_ls_func *ls_func =
+					    acr->func->ls_func[_img->falcon_id];
+
+		max_desc_size = max(max_desc_size, ls_func->bl_desc_size);
+	}
+
+	gdesc = kmalloc(max_desc_size, GFP_KERNEL);
+	if (!gdesc)
+		return -ENOMEM;
 
 	nvkm_kmap(wpr_blob);
 
@@ -272,7 +285,6 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 		struct ls_ucode_img_r367 *img = ls_ucode_img_r367(_img);
 		const struct acr_r352_ls_func *ls_func =
 					    acr->func->ls_func[_img->falcon_id];
-		u8 gdesc[ls_func->bl_desc_size];
 
 		nvkm_gpuobj_memcpy_to(wpr_blob, pos, &img->wpr_header,
 				      sizeof(img->wpr_header));
@@ -298,6 +310,8 @@ acr_r367_ls_write_wpr(struct acr_r352 *acr, struct list_head *imgs,
 
 	nvkm_done(wpr_blob);
 
+	kfree(gdesc);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 1874619a7df4b14b23b14877e705ae15325773e3 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 30 May 2018 16:06:24 +0200
Subject: ARM: dma-mapping: Set proper DMA ops in arm_iommu_detach_device()

Instead of setting the DMA ops pointer to NULL, set the correct,
non-IOMMU ops depending on the device's coherency setting.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Russell King <rmk+kernel@armlinux.org.uk>
Acked-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 arch/arm/mm/dma-mapping.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index be0fa7e39c26..ba0e786c952e 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1151,6 +1151,11 @@ int arm_dma_supported(struct device *dev, u64 mask)
 	return __dma_supported(dev, mask, false);
 }
 
+static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
+{
+	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
+}
+
 #ifdef CONFIG_ARM_DMA_USE_IOMMU
 
 static int __dma_info_to_prot(enum dma_data_direction dir, unsigned long attrs)
@@ -2296,7 +2301,7 @@ void arm_iommu_detach_device(struct device *dev)
 	iommu_detach_device(mapping->domain, dev);
 	kref_put(&mapping->kref, release_iommu_mapping);
 	to_dma_iommu_mapping(dev) = NULL;
-	set_dma_ops(dev, NULL);
+	set_dma_ops(dev, arm_get_dma_map_ops(dev->archdata.dma_coherent));
 
 	pr_debug("Detached IOMMU controller from %s device.\n", dev_name(dev));
 }
@@ -2357,11 +2362,6 @@ static void arm_teardown_iommu_dma_ops(struct device *dev) { }
 
 #endif	/* CONFIG_ARM_DMA_USE_IOMMU */
 
-static const struct dma_map_ops *arm_get_dma_map_ops(bool coherent)
-{
-	return coherent ? &arm_coherent_dma_ops : &arm_dma_ops;
-}
-
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			const struct iommu_ops *iommu, bool coherent)
 {
-- 
cgit v1.2.3


From b59fb482b52269977ee5de205308e5b236a03917 Mon Sep 17 00:00:00 2001
From: Thierry Reding <treding@nvidia.com>
Date: Wed, 30 May 2018 16:06:25 +0200
Subject: drm/nouveau: tegra: Detach from ARM DMA/IOMMU mapping

Depending on the kernel configuration, early ARM architecture setup code
may have attached the GPU to a DMA/IOMMU mapping that transparently uses
the IOMMU to back the DMA API. Tegra requires special handling for IOMMU
backed buffers (a special bit in the GPU's MMU page tables indicates the
memory path to take: via the SMMU or directly to the memory controller).
Transparently backing DMA memory with an IOMMU prevents Nouveau from
properly handling such memory accesses and causes memory access faults.

As a side-note: buffers other than those allocated in instance memory
don't need to be physically contiguous from the GPU's perspective since
the GPU can map them into contiguous buffers using its own MMU. Mapping
these buffers through the IOMMU is unnecessary and will even lead to
performance degradation because of the additional translation. One
exception to this are compressible buffers which need large pages. In
order to enable these large pages, multiple small pages will have to be
combined into one large (I/O virtually contiguous) mapping via the
IOMMU. However, that is a topic outside the scope of this fix and isn't
currently supported. An implementation will want to explicitly create
these large pages in the Nouveau driver, so detaching from a DMA/IOMMU
mapping would still be required.

Signed-off-by: Thierry Reding <treding@nvidia.com>
Acked-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Tested-by: Nicolas Chauvet <kwizart@gmail.com>
Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
index 78597da6313a..0e372a190d3f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/device/tegra.c
@@ -23,6 +23,10 @@
 #ifdef CONFIG_NOUVEAU_PLATFORM_DRIVER
 #include "priv.h"
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+#include <asm/dma-iommu.h>
+#endif
+
 static int
 nvkm_device_tegra_power_up(struct nvkm_device_tegra *tdev)
 {
@@ -105,6 +109,15 @@ nvkm_device_tegra_probe_iommu(struct nvkm_device_tegra *tdev)
 	unsigned long pgsize_bitmap;
 	int ret;
 
+#if IS_ENABLED(CONFIG_ARM_DMA_USE_IOMMU)
+	if (dev->archdata.mapping) {
+		struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
+
+		arm_iommu_detach_device(dev);
+		arm_iommu_release_mapping(mapping);
+	}
+#endif
+
 	if (!tdev->func->iommu_bit)
 		return;
 
-- 
cgit v1.2.3


From 3273fc63e1ed4866fe10a582f4203f2aa142b216 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Mon, 16 Jul 2018 09:40:14 +0200
Subject: drm/meson: Make DMT timings parameters and pixel clock generic

Remove the modes timings tables for DMT modes and calculate the HW
paremeters from the modes timings.

Switch the DMT modes pixel clock calculation out of the static frequency
list to a generic calculation from a range of possible PLL dividers.

This patch is an intermediate step towards usage of the Common Clock
Framwework for PLL setup, by reworking the code to have common
sel_pll() function called by the CEA (HDMI) freq setup and the generic
DMT frequencies setup, we should be able to simply call clk_set_rate()
on the PLL clock handle in a near future.

The CEA (HDMI) and CVBS modes needs very specific clock paths that CCF will
never be able to determine by itself, so there is still some work to do for
a full handoff to CCF handling the clocks.

This setup permits setting non-CEA modes like :
- 1600x900-60Hz
- 1280x1024-75Hz
- 1280x1024-60Hz
- 1440x900-60Hz
- 1366x768-60Hz
- 1280x800-60Hz
- 1152x864-75Hz
- 1024x768-75Hz
- 1024x768-70Hz
- 1024x768-60Hz
- 832x624-75Hz
- 800x600-75Hz
- 800x600-72Hz
- 800x600-60Hz
- 640x480-75Hz
- 640x480-73Hz
- 640x480-67Hz

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Acked-by: Jerome Brunet <jbrunet@baylibre.com>
[narmstrong: fixed trivial checkpatch issues]
Link: https://patchwork.freedesktop.org/patch/msgid/1531726814-14638-1-git-send-email-narmstrong@baylibre.com
---
 drivers/gpu/drm/meson/meson_dw_hdmi.c |  22 +-
 drivers/gpu/drm/meson/meson_vclk.c    | 656 +++++++++++++++-------------------
 drivers/gpu/drm/meson/meson_vclk.h    |   4 +
 drivers/gpu/drm/meson/meson_venc.c    | 378 +++-----------------
 drivers/gpu/drm/meson/meson_venc.h    |   3 +-
 5 files changed, 350 insertions(+), 713 deletions(-)

diff --git a/drivers/gpu/drm/meson/meson_dw_hdmi.c b/drivers/gpu/drm/meson/meson_dw_hdmi.c
index c9ad45686e7a..df7247cd93f9 100644
--- a/drivers/gpu/drm/meson/meson_dw_hdmi.c
+++ b/drivers/gpu/drm/meson/meson_dw_hdmi.c
@@ -329,6 +329,12 @@ static void dw_hdmi_set_vclk(struct meson_dw_hdmi *dw_hdmi,
 
 	vclk_freq = mode->clock;
 
+	if (!vic) {
+		meson_vclk_setup(priv, MESON_VCLK_TARGET_DMT, vclk_freq,
+				 vclk_freq, vclk_freq, false);
+		return;
+	}
+
 	if (mode->flags & DRM_MODE_FLAG_DBLCLK)
 		vclk_freq *= 2;
 
@@ -542,10 +548,12 @@ static enum drm_mode_status
 dw_hdmi_mode_valid(struct drm_connector *connector,
 		   const struct drm_display_mode *mode)
 {
+	struct meson_drm *priv = connector->dev->dev_private;
 	unsigned int vclk_freq;
 	unsigned int venc_freq;
 	unsigned int hdmi_freq;
 	int vic = drm_match_cea_mode(mode);
+	enum drm_mode_status status;
 
 	DRM_DEBUG_DRIVER("Modeline %d:\"%s\" %d %d %d %d %d %d %d %d %d %d 0x%x 0x%x\n",
 		mode->base.id, mode->name, mode->vrefresh, mode->clock,
@@ -556,8 +564,11 @@ dw_hdmi_mode_valid(struct drm_connector *connector,
 
 	/* Check against non-VIC supported modes */
 	if (!vic) {
-		if (!meson_venc_hdmi_supported_mode(mode))
-			return MODE_BAD;
+		status = meson_venc_hdmi_supported_mode(mode);
+		if (status != MODE_OK)
+			return status;
+
+		return meson_vclk_dmt_supported_freq(priv, mode->clock);
 	/* Check against supported VIC modes */
 	} else if (!meson_venc_hdmi_supported_vic(vic))
 		return MODE_BAD;
@@ -583,16 +594,11 @@ dw_hdmi_mode_valid(struct drm_connector *connector,
 	dev_dbg(connector->dev->dev, "%s: vclk:%d venc=%d hdmi=%d\n", __func__,
 		vclk_freq, venc_freq, hdmi_freq);
 
-	/* Finally filter by configurable vclk frequencies */
+	/* Finally filter by configurable vclk frequencies for VIC modes */
 	switch (vclk_freq) {
-	case 25175:
-	case 40000:
 	case 54000:
-	case 65000:
 	case 74250:
-	case 108000:
 	case 148500:
-	case 162000:
 	case 297000:
 	case 594000:
 		return MODE_OK;
diff --git a/drivers/gpu/drm/meson/meson_vclk.c b/drivers/gpu/drm/meson/meson_vclk.c
index f0511220317f..ae5473257f72 100644
--- a/drivers/gpu/drm/meson/meson_vclk.c
+++ b/drivers/gpu/drm/meson/meson_vclk.c
@@ -320,32 +320,23 @@ static void meson_venci_cvbs_clock_config(struct meson_drm *priv)
 				CTS_VDAC_EN, CTS_VDAC_EN);
 }
 
-
+enum {
 /* PLL	O1 O2 O3 VP DV     EN TX */
 /* 4320 /4 /4 /1 /5 /1  => /2 /2 */
-#define MESON_VCLK_HDMI_ENCI_54000	1
+	MESON_VCLK_HDMI_ENCI_54000 = 1,
 /* 4320 /4 /4 /1 /5 /1  => /1 /2 */
-#define MESON_VCLK_HDMI_DDR_54000	2
+	MESON_VCLK_HDMI_DDR_54000,
 /* 2970 /4 /1 /1 /5 /1  => /1 /2 */
-#define MESON_VCLK_HDMI_DDR_148500	3
-/* 4028 /4 /4 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_25175		4
-/* 3200 /4 /2 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_40000		5
-/* 5200 /4 /2 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_65000		6
+	MESON_VCLK_HDMI_DDR_148500,
 /* 2970 /2 /2 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_74250		7
-/* 4320 /4 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_108000		8
+	MESON_VCLK_HDMI_74250,
 /* 2970 /1 /2 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_148500		9
-/* 3240 /2 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_162000		10
+	MESON_VCLK_HDMI_148500,
 /* 2970 /1 /1 /1 /5 /2  => /1 /1 */
-#define MESON_VCLK_HDMI_297000		11
+	MESON_VCLK_HDMI_297000,
 /* 5940 /1 /1 /2 /5 /1  => /1 /1 */
-#define MESON_VCLK_HDMI_594000		12
+	MESON_VCLK_HDMI_594000
+};
 
 struct meson_vclk_params {
 	unsigned int pll_base_freq;
@@ -411,46 +402,6 @@ struct meson_vclk_params {
 		.vid_pll_div = VID_PLL_DIV_5,
 		.vclk_div = 1,
 	},
-	[MESON_VCLK_HDMI_25175] = {
-		.pll_base_freq = 4028000,
-		.pll_od1 = 4,
-		.pll_od2 = 4,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_40000] = {
-		.pll_base_freq = 3200000,
-		.pll_od1 = 4,
-		.pll_od2 = 2,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_65000] = {
-		.pll_base_freq = 5200000,
-		.pll_od1 = 4,
-		.pll_od2 = 2,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_108000] = {
-		.pll_base_freq = 4320000,
-		.pll_od1 = 4,
-		.pll_od2 = 1,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
-	[MESON_VCLK_HDMI_162000] = {
-		.pll_base_freq = 3240000,
-		.pll_od1 = 2,
-		.pll_od2 = 1,
-		.pll_od3 = 1,
-		.vid_pll_div = VID_PLL_DIV_5,
-		.vclk_div = 2,
-	},
 };
 
 static inline unsigned int pll_od_to_reg(unsigned int od)
@@ -470,358 +421,217 @@ static inline unsigned int pll_od_to_reg(unsigned int od)
 	return 0;
 }
 
-void meson_hdmi_pll_set(struct meson_drm *priv,
-			unsigned int base,
-			unsigned int od1,
-			unsigned int od2,
-			unsigned int od3)
+void meson_hdmi_pll_set_params(struct meson_drm *priv, unsigned int m,
+			       unsigned int frac, unsigned int od1,
+			       unsigned int od2, unsigned int od3)
 {
 	unsigned int val;
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
-		switch (base) {
-		case 2970000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800023d);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* Enable and unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						0x7 << 28, 0x4 << 28);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4e00);
-			break;
-
-		case 3200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000242);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4aab);
-			break;
-
-		case 3240000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000243);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4800);
-			break;
-
-		case 3865000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000250);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4855);
-			break;
-
-		case 4028000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000253);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-
-			/* div_frac */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4eab);
-			break;
-
-		case 4320000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800025a);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x58000200 | m);
+		if (frac)
+			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2,
+				     0x00004000 | frac);
+		else
+			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2,
+				     0x00000000);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x0d5c5091);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
 
-		case 5940000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800027b);
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-						0xFFFF,  0x4c00);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x135c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
+		/* Enable and unreset */
+		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
+				   0x7 << 28, 0x4 << 28);
 
-		case 5200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x5800026c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x00000000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x135c5091);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x801da72c);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x71486980);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x00000e55);
-
-			/* unreset */
-			regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-						BIT(28), 0);
-
-			/* Poll for lock bit */
-			regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
-					val, (val & HDMI_PLL_LOCK), 10, 0);
-			break;
-		};
+		/* Poll for lock bit */
+		regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL,
+					 val, (val & HDMI_PLL_LOCK), 10, 0);
 	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
 		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
-		switch (base) {
-		case 2970000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x4000027b);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb300);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000285);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb155);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3240000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000287);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 3865000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002a1);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb02b);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 4028000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002a7);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb355);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 4320000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002b4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 5940000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002f7);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb200);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		case 5200000:
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x400002d8);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb2ab);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
-			regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
-			break;
-
-		};
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL, 0x40000200 | m);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL2, 0x800cb000 | frac);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL3, 0x860f30c4);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL4, 0x0c8e0000);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL5, 0x001fa729);
+		regmap_write(priv->hhi, HHI_HDMI_PLL_CNTL6, 0x01a31500);
 
 		/* Reset PLL */
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-					HDMI_PLL_RESET, HDMI_PLL_RESET);
+				HDMI_PLL_RESET, HDMI_PLL_RESET);
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL,
-					HDMI_PLL_RESET, 0);
+				HDMI_PLL_RESET, 0);
 
 		/* Poll for lock bit */
 		regmap_read_poll_timeout(priv->hhi, HHI_HDMI_PLL_CNTL, val,
 				(val & HDMI_PLL_LOCK), 10, 0);
-	};
+	}
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 16, pll_od_to_reg(od1) << 16);
+				3 << 16, pll_od_to_reg(od1) << 16);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 21, pll_od_to_reg(od1) << 21);
+				3 << 21, pll_od_to_reg(od1) << 21);
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 22, pll_od_to_reg(od2) << 22);
+				3 << 22, pll_od_to_reg(od2) << 22);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 23, pll_od_to_reg(od2) << 23);
+				3 << 23, pll_od_to_reg(od2) << 23);
 
 	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL2,
-				   3 << 18, pll_od_to_reg(od3) << 18);
+				3 << 18, pll_od_to_reg(od3) << 18);
 	else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
-		 meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
+			meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu"))
 		regmap_update_bits(priv->hhi, HHI_HDMI_PLL_CNTL3,
-				   3 << 19, pll_od_to_reg(od3) << 19);
+				3 << 19, pll_od_to_reg(od3) << 19);
+
 }
 
-void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
-		      unsigned int vclk_freq, unsigned int venc_freq,
-		      unsigned int dac_freq, bool hdmi_use_enci)
+#define XTAL_FREQ 24000
+
+static unsigned int meson_hdmi_pll_get_m(struct meson_drm *priv,
+					 unsigned int pll_freq)
 {
-	unsigned int freq;
-	unsigned int hdmi_tx_div;
-	unsigned int venc_div;
+	/* The GXBB PLL has a /2 pre-multiplier */
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu"))
+		pll_freq /= 2;
 
-	if (target == MESON_VCLK_TARGET_CVBS) {
-		meson_venci_cvbs_clock_config(priv);
-		return;
+	return pll_freq / XTAL_FREQ;
+}
+
+#define HDMI_FRAC_MAX_GXBB	4096
+#define HDMI_FRAC_MAX_GXL	1024
+
+static unsigned int meson_hdmi_pll_get_frac(struct meson_drm *priv,
+					    unsigned int m,
+					    unsigned int pll_freq)
+{
+	unsigned int parent_freq = XTAL_FREQ;
+	unsigned int frac_max = HDMI_FRAC_MAX_GXL;
+	unsigned int frac_m;
+	unsigned int frac;
+
+	/* The GXBB PLL has a /2 pre-multiplier and a larger FRAC width */
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		frac_max = HDMI_FRAC_MAX_GXBB;
+		parent_freq *= 2;
 	}
 
-	hdmi_tx_div = vclk_freq / dac_freq;
+	/* We can have a perfect match !*/
+	if (pll_freq / m == parent_freq &&
+	    pll_freq % m == 0)
+		return 0;
 
-	if (hdmi_tx_div == 0) {
-		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
-				dac_freq);
-		return;
+	frac = div_u64((u64)pll_freq * (u64)frac_max, parent_freq);
+	frac_m = m * frac_max;
+	if (frac_m > frac)
+		return frac_max;
+	frac -= frac_m;
+
+	return min((u16)frac, (u16)(frac_max - 1));
+}
+
+static bool meson_hdmi_pll_validate_params(struct meson_drm *priv,
+					   unsigned int m,
+					   unsigned int frac)
+{
+	if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		/* Empiric supported min/max dividers */
+		if (m < 53 || m > 123)
+			return false;
+		if (frac >= HDMI_FRAC_MAX_GXBB)
+			return false;
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
+		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
+		/* Empiric supported min/max dividers */
+		if (m < 106 || m > 247)
+			return false;
+		if (frac >= HDMI_FRAC_MAX_GXL)
+			return false;
 	}
 
-	venc_div = vclk_freq / venc_freq;
+	return true;
+}
 
-	if (venc_div == 0) {
-		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
-				venc_freq);
-		return;
+static bool meson_hdmi_pll_find_params(struct meson_drm *priv,
+				       unsigned int freq,
+				       unsigned int *m,
+				       unsigned int *frac,
+				       unsigned int *od)
+{
+	/* Cycle from /16 to /2 */
+	for (*od = 16 ; *od > 1 ; *od >>= 1) {
+		*m = meson_hdmi_pll_get_m(priv, freq * *od);
+		if (!*m)
+			continue;
+		*frac = meson_hdmi_pll_get_frac(priv, *m, freq * *od);
+
+		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d\n",
+				 freq, *m, *frac, *od);
+
+		if (meson_hdmi_pll_validate_params(priv, *m, *frac))
+			return true;
 	}
 
-	switch (vclk_freq) {
-	case 54000:
-		if (hdmi_use_enci)
-			freq = MESON_VCLK_HDMI_ENCI_54000;
-		else
-			freq = MESON_VCLK_HDMI_DDR_54000;
-		break;
-	case 25175:
-		freq = MESON_VCLK_HDMI_25175;
-		break;
-	case 40000:
-		freq = MESON_VCLK_HDMI_40000;
-		break;
-	case 65000:
-		freq = MESON_VCLK_HDMI_65000;
-		break;
-	case 74250:
-		freq = MESON_VCLK_HDMI_74250;
-		break;
-	case 108000:
-		freq = MESON_VCLK_HDMI_108000;
-		break;
-	case 148500:
-		if (dac_freq != 148500)
-			freq = MESON_VCLK_HDMI_DDR_148500;
-		else
-			freq = MESON_VCLK_HDMI_148500;
-		break;
-	case 162000:
-		freq = MESON_VCLK_HDMI_162000;
-		break;
-	case 297000:
-		freq = MESON_VCLK_HDMI_297000;
-		break;
-	case 594000:
-		freq = MESON_VCLK_HDMI_594000;
-		break;
-	default:
-		pr_err("Fatal Error, invalid HDMI vclk freq %d\n",
-			vclk_freq);
+	return false;
+}
+
+/* pll_freq is the frequency after the OD dividers */
+enum drm_mode_status
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq)
+{
+	unsigned int od, m, frac;
+
+	/* In DMT mode, path after PLL is always /10 */
+	freq *= 10;
+
+	if (meson_hdmi_pll_find_params(priv, freq, &m, &frac, &od))
+		return MODE_OK;
+
+	return MODE_CLOCK_RANGE;
+}
+EXPORT_SYMBOL_GPL(meson_vclk_dmt_supported_freq);
+
+/* pll_freq is the frequency after the OD dividers */
+static void meson_hdmi_pll_generic_set(struct meson_drm *priv,
+				       unsigned int pll_freq)
+{
+	unsigned int od, m, frac, od1, od2, od3;
+
+	if (meson_hdmi_pll_find_params(priv, pll_freq, &m, &frac, &od)) {
+		od3 = 1;
+		if (od < 4) {
+			od1 = 2;
+			od2 = 1;
+		} else {
+			od2 = od / 4;
+			od1 = od / od2;
+		}
+
+		DRM_DEBUG_DRIVER("PLL params for %dkHz: m=%x frac=%x od=%d/%d/%d\n",
+				 pll_freq, m, frac, od1, od2, od3);
+
+		meson_hdmi_pll_set_params(priv, m, frac, od1, od2, od3);
+
 		return;
 	}
 
+	DRM_ERROR("Fatal, unable to find parameters for PLL freq %d\n",
+		  pll_freq);
+}
+
+static void meson_vclk_set(struct meson_drm *priv, unsigned int pll_base_freq,
+			   unsigned int od1, unsigned int od2, unsigned int od3,
+			   unsigned int vid_pll_div, unsigned int vclk_div,
+			   unsigned int hdmi_tx_div, unsigned int venc_div,
+			   bool hdmi_use_enci)
+{
 	/* Set HDMI-TX sys clock */
 	regmap_update_bits(priv->hhi, HHI_HDMI_CLK_CNTL,
 			   CTS_HDMI_SYS_SEL_MASK, 0);
@@ -831,19 +641,49 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 			   CTS_HDMI_SYS_EN, CTS_HDMI_SYS_EN);
 
 	/* Set HDMI PLL rate */
-	meson_hdmi_pll_set(priv, params[freq].pll_base_freq,
-			   params[freq].pll_od1,
-			   params[freq].pll_od2,
-			   params[freq].pll_od3);
+	if (!od1 && !od2 && !od3) {
+		meson_hdmi_pll_generic_set(priv, pll_base_freq);
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxbb-vpu")) {
+		switch (pll_base_freq) {
+		case 2970000:
+			meson_hdmi_pll_set_params(priv, 0x3d, 0xe00,
+						  od1, od2, od3);
+			break;
+		case 4320000:
+			meson_hdmi_pll_set_params(priv, 0x5a, 0,
+						  od1, od2, od3);
+			break;
+		case 5940000:
+			meson_hdmi_pll_set_params(priv, 0x7b, 0xc00,
+						  od1, od2, od3);
+			break;
+		}
+	} else if (meson_vpu_is_compatible(priv, "amlogic,meson-gxm-vpu") ||
+		   meson_vpu_is_compatible(priv, "amlogic,meson-gxl-vpu")) {
+		switch (pll_base_freq) {
+		case 2970000:
+			meson_hdmi_pll_set_params(priv, 0x7b, 0x300,
+						  od1, od2, od3);
+			break;
+		case 4320000:
+			meson_hdmi_pll_set_params(priv, 0xb4, 0,
+						  od1, od2, od3);
+			break;
+		case 5940000:
+			meson_hdmi_pll_set_params(priv, 0xf7, 0x200,
+						  od1, od2, od3);
+			break;
+		}
+	}
 
 	/* Setup vid_pll divider */
-	meson_vid_pll_set(priv, params[freq].vid_pll_div);
+	meson_vid_pll_set(priv, vid_pll_div);
 
 	/* Set VCLK div */
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_CNTL,
 			   VCLK_SEL_MASK, 0);
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_DIV,
-			   VCLK_DIV_MASK, params[freq].vclk_div - 1);
+			   VCLK_DIV_MASK, vclk_div - 1);
 
 	/* Set HDMI-TX source */
 	switch (hdmi_tx_div) {
@@ -981,4 +821,80 @@ void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 
 	regmap_update_bits(priv->hhi, HHI_VID_CLK_CNTL, VCLK_EN, VCLK_EN);
 }
+
+void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
+		      unsigned int vclk_freq, unsigned int venc_freq,
+		      unsigned int dac_freq, bool hdmi_use_enci)
+{
+	unsigned int freq;
+	unsigned int hdmi_tx_div;
+	unsigned int venc_div;
+
+	if (target == MESON_VCLK_TARGET_CVBS) {
+		meson_venci_cvbs_clock_config(priv);
+		return;
+	} else if (target == MESON_VCLK_TARGET_DMT) {
+		/* The DMT clock path is fixed after the PLL:
+		 * - automatic PLL freq + OD management
+		 * - vid_pll_div = VID_PLL_DIV_5
+		 * - vclk_div = 2
+		 * - hdmi_tx_div = 1
+		 * - venc_div = 1
+		 * - encp encoder
+		 */
+		meson_vclk_set(priv, vclk_freq * 10, 0, 0, 0,
+			       VID_PLL_DIV_5, 2, 1, 1, false);
+		return;
+	}
+
+	hdmi_tx_div = vclk_freq / dac_freq;
+
+	if (hdmi_tx_div == 0) {
+		pr_err("Fatal Error, invalid HDMI-TX freq %d\n",
+		       dac_freq);
+		return;
+	}
+
+	venc_div = vclk_freq / venc_freq;
+
+	if (venc_div == 0) {
+		pr_err("Fatal Error, invalid HDMI venc freq %d\n",
+		       venc_freq);
+		return;
+	}
+
+	switch (vclk_freq) {
+	case 54000:
+		if (hdmi_use_enci)
+			freq = MESON_VCLK_HDMI_ENCI_54000;
+		else
+			freq = MESON_VCLK_HDMI_DDR_54000;
+		break;
+	case 74250:
+		freq = MESON_VCLK_HDMI_74250;
+		break;
+	case 148500:
+		if (dac_freq != 148500)
+			freq = MESON_VCLK_HDMI_DDR_148500;
+		else
+			freq = MESON_VCLK_HDMI_148500;
+		break;
+	case 297000:
+		freq = MESON_VCLK_HDMI_297000;
+		break;
+	case 594000:
+		freq = MESON_VCLK_HDMI_594000;
+		break;
+	default:
+		pr_err("Fatal Error, invalid HDMI vclk freq %d\n",
+		       vclk_freq);
+		return;
+	}
+
+	meson_vclk_set(priv, params[freq].pll_base_freq,
+		       params[freq].pll_od1, params[freq].pll_od2,
+		       params[freq].pll_od3, params[freq].vid_pll_div,
+		       params[freq].vclk_div, hdmi_tx_div, venc_div,
+		       hdmi_use_enci);
+}
 EXPORT_SYMBOL_GPL(meson_vclk_setup);
diff --git a/drivers/gpu/drm/meson/meson_vclk.h b/drivers/gpu/drm/meson/meson_vclk.h
index 0401b5213471..869fa3a3073e 100644
--- a/drivers/gpu/drm/meson/meson_vclk.h
+++ b/drivers/gpu/drm/meson/meson_vclk.h
@@ -24,11 +24,15 @@
 enum {
 	MESON_VCLK_TARGET_CVBS = 0,
 	MESON_VCLK_TARGET_HDMI = 1,
+	MESON_VCLK_TARGET_DMT = 2,
 };
 
 /* 27MHz is the CVBS Pixel Clock */
 #define MESON_VCLK_CVBS			27000
 
+enum drm_mode_status
+meson_vclk_dmt_supported_freq(struct meson_drm *priv, unsigned int freq);
+
 void meson_vclk_setup(struct meson_drm *priv, unsigned int target,
 		      unsigned int vclk_freq, unsigned int venc_freq,
 		      unsigned int dac_freq, bool hdmi_use_enci);
diff --git a/drivers/gpu/drm/meson/meson_venc.c b/drivers/gpu/drm/meson/meson_venc.c
index 6e2701389801..514245e69b38 100644
--- a/drivers/gpu/drm/meson/meson_venc.c
+++ b/drivers/gpu/drm/meson/meson_venc.c
@@ -697,314 +697,6 @@ union meson_hdmi_venc_mode meson_hdmi_encp_mode_1080p60 = {
 	},
 };
 
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_640x480_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x31f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x90,
-		.havon_end = 0x30f,
-		.vavon_bline = 0x23,
-		.vavon_eline = 0x202,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x60,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 2,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x20c,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_800x600_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x41f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0xD8,
-		.havon_end = 0x3f7,
-		.vavon_bline = 0x1b,
-		.vavon_eline = 0x272,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x80,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 4,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x273,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1024x768_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 1343,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 296,
-		.havon_end = 1319,
-		.vavon_bline = 35,
-		.vavon_eline = 802,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 136,
-		.vso_begin = 30,
-		.vso_end = 50,
-		.vso_bline = 0,
-		.vso_eline = 6,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 805,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1152x864_75 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x63f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x180,
-		.havon_end = 0x5ff,
-		.vavon_bline = 0x23,
-		.vavon_eline = 0x382,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x80,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x383,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1280x1024_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x697,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x168,
-		.havon_end = 0x667,
-		.vavon_bline = 0x29,
-		.vavon_eline = 0x428,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0x70,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x429,
-	},
-};
-
-union meson_hdmi_venc_mode meson_hdmi_encp_mode_1600x1200_60 = {
-	.encp = {
-		.dvi_settings = 0x21,
-		.video_mode = 0x4040,
-		.video_mode_adv = 0x18,
-		/* video_prog_mode */
-		/* video_sync_mode */
-		/* video_yc_dly */
-		/* video_rgb_ctrl */
-		/* video_filt_ctrl */
-		/* video_ofld_voav_ofst */
-		/* yfp1_htime */
-		/* yfp2_htime */
-		.max_pxcnt = 0x86f,
-		/* hspuls_begin */
-		/* hspuls_end */
-		/* hspuls_switch */
-		/* vspuls_begin */
-		/* vspuls_end */
-		/* vspuls_bline */
-		/* vspuls_eline */
-		.havon_begin = 0x1f0,
-		.havon_end = 0x82f,
-		.vavon_bline = 0x31,
-		.vavon_eline = 0x4e0,
-		/* eqpuls_begin */
-		/* eqpuls_end */
-		/* eqpuls_bline */
-		/* eqpuls_eline */
-		.hso_begin = 0,
-		.hso_end = 0xc0,
-		.vso_begin = 0x1e,
-		.vso_end = 0x32,
-		.vso_bline = 0,
-		.vso_eline = 3,
-		.vso_eline_present = true,
-		/* sy_val */
-		/* sy2_val */
-		.max_lncnt = 0x4e1,
-	},
-};
-
-struct meson_hdmi_venc_dmt_mode {
-	struct drm_display_mode drm_mode;
-	union meson_hdmi_venc_mode *mode;
-} meson_hdmi_venc_dmt_modes[] = {
-	/* 640x480@60Hz */
-	{
-		{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 25175, 640, 656,
-		  752, 800, 0, 480, 490, 492, 525, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_640x480_60,
-	},
-	/* 800x600@60Hz */
-	{
-		{ DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 40000, 800, 840,
-		  968, 1056, 0, 600, 601, 605, 628, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_800x600_60,
-	},
-	/* 1024x768@60Hz */
-	{
-		{ DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 65000, 1024,
-		  1048, 1184, 1344, 0, 768, 771, 777, 806, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_1024x768_60,
-	},
-	/* 1152x864@75Hz */
-	{
-		{ DRM_MODE("1152x864", DRM_MODE_TYPE_DRIVER, 108000, 1152,
-		  1216, 1344, 1600, 0, 864, 865, 868, 900, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1152x864_75,
-	},
-	/* 1280x1024@60Hz */
-	{
-		{ DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 108000, 1280,
-		  1328, 1440, 1688, 0, 1024, 1025, 1028, 1066, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1280x1024_60,
-	},
-	/* 1600x1200@60Hz */
-	{
-		{ DRM_MODE("1600x1200", DRM_MODE_TYPE_DRIVER, 162000, 1600,
-		  1664, 1856, 2160, 0, 1200, 1201, 1204, 1250, 0,
-		  DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-		&meson_hdmi_encp_mode_1600x1200_60,
-	},
-	/* 1920x1080@60Hz */
-	{
-		{ DRM_MODE("1920x1080", DRM_MODE_TYPE_DRIVER, 148500, 1920,
-		  2008, 2052, 2200, 0, 1080, 1084, 1089, 1125, 0,
-		  DRM_MODE_FLAG_NHSYNC | DRM_MODE_FLAG_NVSYNC) },
-		&meson_hdmi_encp_mode_1080p60
-	},
-	{ }, /* sentinel */
-};
-
 struct meson_hdmi_venc_vic_mode {
 	unsigned int vic;
 	union meson_hdmi_venc_mode *mode;
@@ -1044,17 +736,20 @@ static unsigned long modulo(unsigned long a, unsigned long b)
 		return a;
 }
 
-bool meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode)
+enum drm_mode_status
+meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode)
 {
-	struct meson_hdmi_venc_dmt_mode *vmode = meson_hdmi_venc_dmt_modes;
+	if (mode->flags & ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_NHSYNC |
+			    DRM_MODE_FLAG_PVSYNC | DRM_MODE_FLAG_NVSYNC))
+		return MODE_BAD;
 
-	while (vmode->mode) {
-		if (drm_mode_equal(&vmode->drm_mode, mode))
-			return true;
-		vmode++;
-	}
+	if (mode->hdisplay < 640 || mode->hdisplay > 1920)
+		return MODE_BAD_HVALUE;
 
-	return false;
+	if (mode->vdisplay < 480 || mode->vdisplay > 1200)
+		return MODE_BAD_VVALUE;
+
+	return MODE_OK;
 }
 EXPORT_SYMBOL_GPL(meson_venc_hdmi_supported_mode);
 
@@ -1072,18 +767,29 @@ bool meson_venc_hdmi_supported_vic(int vic)
 }
 EXPORT_SYMBOL_GPL(meson_venc_hdmi_supported_vic);
 
-static union meson_hdmi_venc_mode
-*meson_venc_hdmi_get_dmt_vmode(const struct drm_display_mode *mode)
+void meson_venc_hdmi_get_dmt_vmode(const struct drm_display_mode *mode,
+				   union meson_hdmi_venc_mode *dmt_mode)
 {
-	struct meson_hdmi_venc_dmt_mode *vmode = meson_hdmi_venc_dmt_modes;
-
-	while (vmode->mode) {
-		if (drm_mode_equal(&vmode->drm_mode, mode))
-			return vmode->mode;
-		vmode++;
-	}
-
-	return NULL;
+	memset(dmt_mode, 0, sizeof(*dmt_mode));
+
+	dmt_mode->encp.dvi_settings = 0x21;
+	dmt_mode->encp.video_mode = 0x4040;
+	dmt_mode->encp.video_mode_adv = 0x18;
+	dmt_mode->encp.max_pxcnt = mode->htotal - 1;
+	dmt_mode->encp.havon_begin = mode->htotal - mode->hsync_start;
+	dmt_mode->encp.havon_end = dmt_mode->encp.havon_begin +
+				   mode->hdisplay - 1;
+	dmt_mode->encp.vavon_bline = mode->vtotal - mode->vsync_start;
+	dmt_mode->encp.vavon_eline = dmt_mode->encp.vavon_bline +
+				     mode->vdisplay - 1;
+	dmt_mode->encp.hso_begin = 0;
+	dmt_mode->encp.hso_end = mode->hsync_end - mode->hsync_start;
+	dmt_mode->encp.vso_begin = 30;
+	dmt_mode->encp.vso_end = 50;
+	dmt_mode->encp.vso_bline = 0;
+	dmt_mode->encp.vso_eline = mode->vsync_end - mode->vsync_start;
+	dmt_mode->encp.vso_eline_present = true;
+	dmt_mode->encp.max_lncnt = mode->vtotal - 1;
 }
 
 static union meson_hdmi_venc_mode *meson_venc_hdmi_get_vic_vmode(int vic)
@@ -1120,6 +826,7 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 			      struct drm_display_mode *mode)
 {
 	union meson_hdmi_venc_mode *vmode = NULL;
+	union meson_hdmi_venc_mode vmode_dmt;
 	bool use_enci = false;
 	bool venc_repeat = false;
 	bool hdmi_repeat = false;
@@ -1147,14 +854,17 @@ void meson_venc_hdmi_mode_set(struct meson_drm *priv, int vic,
 	unsigned int sof_lines;
 	unsigned int vsync_lines;
 
-	if (meson_venc_hdmi_supported_vic(vic))
+	if (meson_venc_hdmi_supported_vic(vic)) {
 		vmode = meson_venc_hdmi_get_vic_vmode(vic);
-	else
-		vmode = meson_venc_hdmi_get_dmt_vmode(mode);
-	if (!vmode) {
-		dev_err(priv->dev, "%s: Fatal Error, unsupported mode "
-			DRM_MODE_FMT "\n", __func__, DRM_MODE_ARG(mode));
-		return;
+		if (!vmode) {
+			dev_err(priv->dev, "%s: Fatal Error, unsupported mode "
+				DRM_MODE_FMT "\n", __func__,
+				DRM_MODE_ARG(mode));
+			return;
+		}
+	} else {
+		meson_venc_hdmi_get_dmt_vmode(mode, &vmode_dmt);
+		vmode = &vmode_dmt;
 	}
 
 	/* Use VENCI for 480i and 576i and double HDMI pixels */
diff --git a/drivers/gpu/drm/meson/meson_venc.h b/drivers/gpu/drm/meson/meson_venc.h
index 7c18a36a0dd0..97eaebbfa0c4 100644
--- a/drivers/gpu/drm/meson/meson_venc.h
+++ b/drivers/gpu/drm/meson/meson_venc.h
@@ -58,7 +58,8 @@ struct meson_cvbs_enci_mode {
 };
 
 /* HDMI Clock parameters */
-bool meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode);
+enum drm_mode_status
+meson_venc_hdmi_supported_mode(const struct drm_display_mode *mode);
 bool meson_venc_hdmi_supported_vic(int vic);
 bool meson_venc_hdmi_venc_repeat(int vic);
 
-- 
cgit v1.2.3


From 0f0caa52cd4a48a44f6cdc77bf83272bbb450727 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Mon, 9 Jul 2018 19:40:11 +0200
Subject: x86/hyper-v: Check cpumask_to_vpset() return value in
 hyperv_flush_tlb_others_ex()

Commit 1268ed0c474a ("x86/hyper-v: Fix the circular dependency in IPI
enlightenment") made cpumask_to_vpset() return '-1' when there is a CPU
with unknown VP index in the supplied set. This needs to be checked before
we pass 'nr_bank' to hypercall.

Fixes: 1268ed0c474a ("x86/hyper-v: Fix the circular dependency in IPI enlightenment")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Cc: devel@linuxdriverproject.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lkml.kernel.org/r/20180709174012.17429-2-vkuznets@redhat.com
---
 arch/x86/hyperv/mmu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 0d90e515ec98..453d2355cd61 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -186,6 +186,8 @@ static u64 hyperv_flush_tlb_others_ex(const struct cpumask *cpus,
 
 	flush->hv_vp_set.format = HV_GENERIC_SET_SPARSE_4K;
 	nr_bank = cpumask_to_vpset(&(flush->hv_vp_set), cpus);
+	if (nr_bank < 0)
+		return U64_MAX;
 
 	/*
 	 * We can flush not more than max_gvas with one hypercall. Flush the
-- 
cgit v1.2.3


From 110d2a7fc39725d2c29d2fede4f34a35a4f98882 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Mon, 9 Jul 2018 19:40:12 +0200
Subject: x86/hyper-v: Check for VP_INVAL in hyperv_flush_tlb_others()

Commit 1268ed0c474a ("x86/hyper-v: Fix the circular dependency in IPI
 enlightenment") pre-filled hv_vp_index with VP_INVAL so it is now
(theoretically) possible to observe hv_cpu_number_to_vp_number()
returning VP_INVAL. We need to check for that in hyperv_flush_tlb_others().

Not checking for VP_INVAL on the first call site where we do

 if (hv_cpu_number_to_vp_number(cpumask_last(cpus)) >= 64)
                        goto do_ex_hypercall;

is OK, in case we're eligible for non-ex hypercall we'll catch the
issue later in for_each_cpu() cycle and in case we'll be doing ex-
hypercall cpumask_to_vpset() will fail.

It would be nice to change hv_cpu_number_to_vp_number() return
value's type to 'u32' but this will likely be a bigger change as
all call sites need to be checked first.

Fixes: 1268ed0c474a ("x86/hyper-v: Fix the circular dependency in IPI enlightenment")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Cc: devel@linuxdriverproject.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lkml.kernel.org/r/20180709174012.17429-3-vkuznets@redhat.com
---
 arch/x86/hyperv/mmu.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 453d2355cd61..1147e1fed7ff 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -111,6 +111,11 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 
 		for_each_cpu(cpu, cpus) {
 			vcpu = hv_cpu_number_to_vp_number(cpu);
+			if (vcpu == VP_INVAL) {
+				local_irq_restore(flags);
+				goto do_native;
+			}
+
 			if (vcpu >= 64)
 				goto do_ex_hypercall;
 
-- 
cgit v1.2.3


From 55e4b859a2e1952d3feb2e2ec1c520952cc8b660 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 16 Jul 2018 09:03:32 +0100
Subject: drm/i915/selftests: Downgrade igt_timeout message

Give in, since CI continues to incorrectly insist that KERN_NOTICE is a
warning and flags the timeout message as unwanted spam. At first, the
intention was to use the message to indicate which tests might warrant
an extended run, but virtually all tests require a timeout so it is
simply not as interesting as first thought.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=103667
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716080332.32283-6-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_selftest.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_selftest.h b/drivers/gpu/drm/i915/i915_selftest.h
index 9766e806dce6..a73472dd12fd 100644
--- a/drivers/gpu/drm/i915/i915_selftest.h
+++ b/drivers/gpu/drm/i915/i915_selftest.h
@@ -99,6 +99,6 @@ __printf(2, 3)
 bool __igt_timeout(unsigned long timeout, const char *fmt, ...);
 
 #define igt_timeout(t, fmt, ...) \
-	__igt_timeout((t), KERN_NOTICE pr_fmt(fmt), ##__VA_ARGS__)
+	__igt_timeout((t), KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 
 #endif /* !__I915_SELFTEST_H__ */
-- 
cgit v1.2.3


From 159b69bc0dcdb88ea5126a8f98e4caa31789326b Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 16 Jul 2018 09:03:31 +0100
Subject: drm/i915: Remove pci private pointer after destroying the device
 private

On an aborted module load, we unwind and free our device private - but
we left a dangling pointer to our privates inside the pci_device. After
the attempted aborted unload, we may still get a call to i915_pci_remove()
when the module is removed, potentially chasing stale data.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716080332.32283-5-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_drv.c |  1 +
 drivers/gpu/drm/i915/i915_pci.c | 13 ++++++++++++-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index cfa7583cf408..337b1aad5212 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -1424,6 +1424,7 @@ out_fini:
 	drm_dev_fini(&dev_priv->drm);
 out_free:
 	kfree(dev_priv);
+	pci_set_drvdata(pdev, NULL);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_pci.c b/drivers/gpu/drm/i915/i915_pci.c
index 55543f1b0236..6a4d1388ad2d 100644
--- a/drivers/gpu/drm/i915/i915_pci.c
+++ b/drivers/gpu/drm/i915/i915_pci.c
@@ -674,10 +674,16 @@ MODULE_DEVICE_TABLE(pci, pciidlist);
 
 static void i915_pci_remove(struct pci_dev *pdev)
 {
-	struct drm_device *dev = pci_get_drvdata(pdev);
+	struct drm_device *dev;
+
+	dev = pci_get_drvdata(pdev);
+	if (!dev) /* driver load aborted, nothing to cleanup */
+		return;
 
 	i915_driver_unload(dev);
 	drm_dev_put(dev);
+
+	pci_set_drvdata(pdev, NULL);
 }
 
 static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
@@ -712,6 +718,11 @@ static int i915_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		return err;
 
+	if (i915_inject_load_failure()) {
+		i915_pci_remove(pdev);
+		return -ENODEV;
+	}
+
 	err = i915_live_selftests(pdev);
 	if (err) {
 		i915_pci_remove(pdev);
-- 
cgit v1.2.3


From f1a498fa549e8e86895cda37e3fca867aae955b7 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 16 Jul 2018 09:03:30 +0100
Subject: drm/i915/execlists: Disable submission tasklet upon wedging

If we declare the driver wedged before the GPU truly is, then we may see
the GPU complete some CS events following our cancellation. This leaves
us quite confused as we deleted all the bookkeeping and thus complain
about the inconsistent state.

We can just ignore the remaining events and let the GPU idle by not
feeding it, and so avoid trying to racily overwrite shared state. We
rely on there being a full GPU reset before unwedging, giving us the
opportunity to reset the shared state.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107188
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716080332.32283-4-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 05567e30efe0..629127e03577 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -811,6 +811,11 @@ static void reset_csb_pointers(struct intel_engine_execlists *execlists)
 	WRITE_ONCE(*execlists->csb_write, execlists->csb_write_reset);
 }
 
+static void nop_submission_tasklet(unsigned long data)
+{
+	/* The driver is wedged; don't process any more events. */
+}
+
 static void execlists_cancel_requests(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
@@ -870,6 +875,9 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 	execlists->queue = RB_ROOT_CACHED;
 	GEM_BUG_ON(port_isset(execlists->port));
 
+	GEM_BUG_ON(__tasklet_is_enabled(&execlists->tasklet));
+	execlists->tasklet.func = nop_submission_tasklet;
+
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
-- 
cgit v1.2.3


From eeef847de593e2de4ddbf7ae3439c9fc9ebc8e84 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 16 Jul 2018 09:34:51 +0100
Subject: ALSA: opl3: remove redundant pointer opl3

Variable opl3 is being assigned but is never used hence it is
redundant and can be removed.

Cleans up several clang warnings:
warning: variable 'opl3' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/drivers/opl3/opl3_midi.c | 12 ------------
 sound/drivers/opl3/opl3_oss.c  |  6 ------
 2 files changed, 18 deletions(-)

diff --git a/sound/drivers/opl3/opl3_midi.c b/sound/drivers/opl3/opl3_midi.c
index bb3f3a5a6951..71cd5a2fbe82 100644
--- a/sound/drivers/opl3/opl3_midi.c
+++ b/sound/drivers/opl3/opl3_midi.c
@@ -721,9 +721,6 @@ void snd_opl3_note_off(void *p, int note, int vel,
  */
 void snd_opl3_key_press(void *p, int note, int vel, struct snd_midi_channel *chan)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "Key pressure, ch#: %i, inst#: %i\n",
 		   chan->number, chan->midi_program);
@@ -735,9 +732,6 @@ void snd_opl3_key_press(void *p, int note, int vel, struct snd_midi_channel *cha
  */
 void snd_opl3_terminate_note(void *p, int note, struct snd_midi_channel *chan)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "Terminate note, ch#: %i, inst#: %i\n",
 		   chan->number, chan->midi_program);
@@ -861,9 +855,6 @@ void snd_opl3_control(void *p, int type, struct snd_midi_channel *chan)
 void snd_opl3_nrpn(void *p, struct snd_midi_channel *chan,
 		   struct snd_midi_channel_set *chset)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "NRPN, ch#: %i, inst#: %i\n",
 		   chan->number, chan->midi_program);
@@ -876,9 +867,6 @@ void snd_opl3_nrpn(void *p, struct snd_midi_channel *chan,
 void snd_opl3_sysex(void *p, unsigned char *buf, int len,
 		    int parsed, struct snd_midi_channel_set *chset)
 {
-  	struct snd_opl3 *opl3;
-
-	opl3 = p;
 #ifdef DEBUG_MIDI
 	snd_printk(KERN_DEBUG "SYSEX\n");
 #endif
diff --git a/sound/drivers/opl3/opl3_oss.c b/sound/drivers/opl3/opl3_oss.c
index 22c3e4bca220..8a0ce3f43f42 100644
--- a/sound/drivers/opl3/opl3_oss.c
+++ b/sound/drivers/opl3/opl3_oss.c
@@ -233,11 +233,8 @@ static int snd_opl3_load_patch_seq_oss(struct snd_seq_oss_arg *arg, int format,
 static int snd_opl3_ioctl_seq_oss(struct snd_seq_oss_arg *arg, unsigned int cmd,
 				  unsigned long ioarg)
 {
-	struct snd_opl3 *opl3;
-
 	if (snd_BUG_ON(!arg))
 		return -ENXIO;
-	opl3 = arg->private_data;
 	switch (cmd) {
 		case SNDCTL_FM_LOAD_INSTR:
 			snd_printk(KERN_ERR "OPL3: "
@@ -261,11 +258,8 @@ static int snd_opl3_ioctl_seq_oss(struct snd_seq_oss_arg *arg, unsigned int cmd,
 /* reset device */
 static int snd_opl3_reset_seq_oss(struct snd_seq_oss_arg *arg)
 {
-	struct snd_opl3 *opl3;
-
 	if (snd_BUG_ON(!arg))
 		return -ENXIO;
-	opl3 = arg->private_data;
 
 	return 0;
 }
-- 
cgit v1.2.3


From a34e8aac49e6d2e3438998edba5f753bd5d5210f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 16 Jul 2018 09:43:08 +0100
Subject: ALSA: es1688: remove redundant pointer chip

Pointer chip is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'chip' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/es1688/es1688.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/isa/es1688/es1688.c b/sound/isa/es1688/es1688.c
index a826c138e7f5..3dfe7e592c25 100644
--- a/sound/isa/es1688/es1688.c
+++ b/sound/isa/es1688/es1688.c
@@ -260,7 +260,6 @@ static int snd_es968_pnp_detect(struct pnp_card_link *pcard,
 	struct snd_card *card;
 	static unsigned int dev;
 	int error;
-	struct snd_es1688 *chip;
 
 	if (snd_es968_pnp_is_probed)
 		return -EBUSY;
@@ -276,7 +275,6 @@ static int snd_es968_pnp_detect(struct pnp_card_link *pcard,
 			     sizeof(struct snd_es1688), &card);
 	if (error < 0)
 		return error;
-	chip = card->private_data;
 
 	error = snd_card_es968_pnp(card, dev, pcard, pid);
 	if (error < 0) {
-- 
cgit v1.2.3


From 29fba9230de237312337fb7372a6ee2d5f2f893c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 16 Jul 2018 09:49:38 +0100
Subject: ALSA: gus: remove redundant pointer private_data

Pointer private_data is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'private_data' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/gus/gus_reset.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/isa/gus/gus_reset.c b/sound/isa/gus/gus_reset.c
index 3d1fed0c2620..59b3f683d49b 100644
--- a/sound/isa/gus/gus_reset.c
+++ b/sound/isa/gus/gus_reset.c
@@ -292,7 +292,6 @@ void snd_gf1_free_voice(struct snd_gus_card * gus, struct snd_gus_voice *voice)
 {
 	unsigned long flags;
 	void (*private_free)(struct snd_gus_voice *voice);
-	void *private_data;
 
 	if (voice == NULL || !voice->use)
 		return;
@@ -300,7 +299,6 @@ void snd_gf1_free_voice(struct snd_gus_card * gus, struct snd_gus_voice *voice)
 	snd_gf1_clear_voices(gus, voice->number, voice->number);
 	spin_lock_irqsave(&gus->voice_alloc, flags);
 	private_free = voice->private_free;
-	private_data = voice->private_data;
 	voice->private_free = NULL;
 	voice->private_data = NULL;
 	if (voice->pcm)
-- 
cgit v1.2.3


From 7527cd209eb88ed03aeab9f4f9bde0923fd6b5d5 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 16 Jul 2018 09:52:56 +0100
Subject: ALSA: sb8: remove redundant pointer runtime

Pointer runtime is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'runtime' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/sb8_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/sound/isa/sb/sb8_main.c b/sound/isa/sb/sb8_main.c
index d45df5c54423..80e7dcaa551f 100644
--- a/sound/isa/sb/sb8_main.c
+++ b/sound/isa/sb/sb8_main.c
@@ -381,7 +381,6 @@ static int snd_sb8_capture_trigger(struct snd_pcm_substream *substream,
 irqreturn_t snd_sb8dsp_interrupt(struct snd_sb *chip)
 {
 	struct snd_pcm_substream *substream;
-	struct snd_pcm_runtime *runtime;
 
 	snd_sb_ack_8bit(chip);
 	switch (chip->mode) {
@@ -391,7 +390,6 @@ irqreturn_t snd_sb8dsp_interrupt(struct snd_sb *chip)
 		/* fallthru */
 	case SB_MODE_PLAYBACK_8:
 		substream = chip->playback_substream;
-		runtime = substream->runtime;
 		if (chip->playback_format == SB_DSP_OUTPUT)
 		    	snd_sb8_playback_trigger(substream, SNDRV_PCM_TRIGGER_START);
 		snd_pcm_period_elapsed(substream);
@@ -402,7 +400,6 @@ irqreturn_t snd_sb8dsp_interrupt(struct snd_sb *chip)
 		/* fallthru */
 	case SB_MODE_CAPTURE_8:
 		substream = chip->capture_substream;
-		runtime = substream->runtime;
 		if (chip->capture_format == SB_DSP_INPUT)
 		    	snd_sb8_capture_trigger(substream, SNDRV_PCM_TRIGGER_START);
 		snd_pcm_period_elapsed(substream);
-- 
cgit v1.2.3


From c888443951949530b2eb9075cb24f6db00b8118d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 16 Jul 2018 09:57:38 +0100
Subject: ALSA: ali5451: remove redundant pointer 'codec'

Pointer 'codec' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'codec' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ali5451/ali5451.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/sound/pci/ali5451/ali5451.c b/sound/pci/ali5451/ali5451.c
index 39547e32e584..9f569379b77e 100644
--- a/sound/pci/ali5451/ali5451.c
+++ b/sound/pci/ali5451/ali5451.c
@@ -1484,12 +1484,9 @@ static struct snd_pcm_hardware snd_ali_capture =
 static void snd_ali_pcm_free_substream(struct snd_pcm_runtime *runtime)
 {
 	struct snd_ali_voice *pvoice = runtime->private_data;
-	struct snd_ali *codec;
 
-	if (pvoice) {
-		codec = pvoice->codec;
+	if (pvoice)
 		snd_ali_free_voice(pvoice->codec, pvoice);
-	}
 }
 
 static int snd_ali_open(struct snd_pcm_substream *substream, int rec,
-- 
cgit v1.2.3


From d6e08c7eabefc9b027d31d56024810eba76ce113 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 16 Jul 2018 10:03:15 +0100
Subject: ALSA: cs46xx: remove redundant pointer 'ins'

Pointer 'ins' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'ins' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/cs46xx/dsp_spos_scb_lib.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/sound/pci/cs46xx/dsp_spos_scb_lib.c b/sound/pci/cs46xx/dsp_spos_scb_lib.c
index abb01ce66983..8d0a3d357345 100644
--- a/sound/pci/cs46xx/dsp_spos_scb_lib.c
+++ b/sound/pci/cs46xx/dsp_spos_scb_lib.c
@@ -73,13 +73,10 @@ static void cs46xx_dsp_proc_scb_info_read (struct snd_info_entry *entry,
 {
 	struct proc_scb_info * scb_info  = entry->private_data;
 	struct dsp_scb_descriptor * scb = scb_info->scb_desc;
-	struct dsp_spos_instance * ins;
 	struct snd_cs46xx *chip = scb_info->chip;
 	int j,col;
 	void __iomem *dst = chip->region.idx[1].remap_addr + DSP_PARAMETER_BYTE_OFFSET;
 
-	ins = chip->dsp_spos_instance;
-
 	mutex_lock(&chip->spos_mutex);
 	snd_iprintf(buffer,"%04x %s:\n",scb->address,scb->scb_name);
 
-- 
cgit v1.2.3


From 7628fa811b8af57192e02a52574412af316d60a9 Mon Sep 17 00:00:00 2001
From: Takeshi Kihara <takeshi.kihara.df@renesas.com>
Date: Thu, 14 Dec 2017 13:04:55 +0900
Subject: pinctrl: sh-pfc: r8a77965: Add HSCIF pins, groups, and functions

This patch adds HSCIF{0,1,2,3,4} pins, groups and functions to
the R8A77965 SoC.

Signed-off-by: Takeshi Kihara <takeshi.kihara.df@renesas.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/sh-pfc/pfc-r8a77965.c | 333 ++++++++++++++++++++++++++++++++++
 1 file changed, 333 insertions(+)

diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
index d2bbee656381..cfd7de67e3e3 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77965.c
@@ -1758,6 +1758,263 @@ static const unsigned int du_disp_mux[] = {
 	DU_DISP_MARK,
 };
 
+/* - HSCIF0 ----------------------------------------------------------------- */
+static const unsigned int hscif0_data_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 13), RCAR_GP_PIN(5, 14),
+};
+
+static const unsigned int hscif0_data_mux[] = {
+	HRX0_MARK, HTX0_MARK,
+};
+
+static const unsigned int hscif0_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 12),
+};
+
+static const unsigned int hscif0_clk_mux[] = {
+	HSCK0_MARK,
+};
+
+static const unsigned int hscif0_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 16), RCAR_GP_PIN(5, 15),
+};
+
+static const unsigned int hscif0_ctrl_mux[] = {
+	HRTS0_N_MARK, HCTS0_N_MARK,
+};
+
+/* - HSCIF1 ----------------------------------------------------------------- */
+static const unsigned int hscif1_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 5), RCAR_GP_PIN(5, 6),
+};
+
+static const unsigned int hscif1_data_a_mux[] = {
+	HRX1_A_MARK, HTX1_A_MARK,
+};
+
+static const unsigned int hscif1_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+
+static const unsigned int hscif1_clk_a_mux[] = {
+	HSCK1_A_MARK,
+};
+
+static const unsigned int hscif1_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 8), RCAR_GP_PIN(5, 7),
+};
+
+static const unsigned int hscif1_ctrl_a_mux[] = {
+	HRTS1_N_A_MARK, HCTS1_N_A_MARK,
+};
+
+static const unsigned int hscif1_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(5, 1), RCAR_GP_PIN(5, 2),
+};
+
+static const unsigned int hscif1_data_b_mux[] = {
+	HRX1_B_MARK, HTX1_B_MARK,
+};
+
+static const unsigned int hscif1_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(5, 0),
+};
+
+static const unsigned int hscif1_clk_b_mux[] = {
+	HSCK1_B_MARK,
+};
+
+static const unsigned int hscif1_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(5, 4), RCAR_GP_PIN(5, 3),
+};
+
+static const unsigned int hscif1_ctrl_b_mux[] = {
+	HRTS1_N_B_MARK, HCTS1_N_B_MARK,
+};
+
+/* - HSCIF2 ----------------------------------------------------------------- */
+static const unsigned int hscif2_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 8), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int hscif2_data_a_mux[] = {
+	HRX2_A_MARK, HTX2_A_MARK,
+};
+
+static const unsigned int hscif2_clk_a_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 10),
+};
+
+static const unsigned int hscif2_clk_a_mux[] = {
+	HSCK2_A_MARK,
+};
+
+static const unsigned int hscif2_ctrl_a_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 7), RCAR_GP_PIN(6, 6),
+};
+
+static const unsigned int hscif2_ctrl_a_mux[] = {
+	HRTS2_N_A_MARK, HCTS2_N_A_MARK,
+};
+
+static const unsigned int hscif2_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 18),
+};
+
+static const unsigned int hscif2_data_b_mux[] = {
+	HRX2_B_MARK, HTX2_B_MARK,
+};
+
+static const unsigned int hscif2_clk_b_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 21),
+};
+
+static const unsigned int hscif2_clk_b_mux[] = {
+	HSCK2_B_MARK,
+};
+
+static const unsigned int hscif2_ctrl_b_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 20), RCAR_GP_PIN(6, 19),
+};
+
+static const unsigned int hscif2_ctrl_b_mux[] = {
+	HRTS2_N_B_MARK, HCTS2_N_B_MARK,
+};
+
+static const unsigned int hscif2_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(6, 25), RCAR_GP_PIN(6, 26),
+};
+
+static const unsigned int hscif2_data_c_mux[] = {
+	HRX2_C_MARK, HTX2_C_MARK,
+};
+
+static const unsigned int hscif2_clk_c_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(6, 24),
+};
+
+static const unsigned int hscif2_clk_c_mux[] = {
+	HSCK2_C_MARK,
+};
+
+static const unsigned int hscif2_ctrl_c_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(6, 28), RCAR_GP_PIN(6, 27),
+};
+
+static const unsigned int hscif2_ctrl_c_mux[] = {
+	HRTS2_N_C_MARK, HCTS2_N_C_MARK,
+};
+
+/* - HSCIF3 ----------------------------------------------------------------- */
+static const unsigned int hscif3_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 23), RCAR_GP_PIN(1, 24),
+};
+
+static const unsigned int hscif3_data_a_mux[] = {
+	HRX3_A_MARK, HTX3_A_MARK,
+};
+
+static const unsigned int hscif3_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 22),
+};
+
+static const unsigned int hscif3_clk_mux[] = {
+	HSCK3_MARK,
+};
+
+static const unsigned int hscif3_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 25),
+};
+
+static const unsigned int hscif3_ctrl_mux[] = {
+	HRTS3_N_MARK, HCTS3_N_MARK,
+};
+
+static const unsigned int hscif3_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 10), RCAR_GP_PIN(0, 11),
+};
+
+static const unsigned int hscif3_data_b_mux[] = {
+	HRX3_B_MARK, HTX3_B_MARK,
+};
+
+static const unsigned int hscif3_data_c_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(0, 14), RCAR_GP_PIN(0, 15),
+};
+
+static const unsigned int hscif3_data_c_mux[] = {
+	HRX3_C_MARK, HTX3_C_MARK,
+};
+
+static const unsigned int hscif3_data_d_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(2, 7), RCAR_GP_PIN(2, 8),
+};
+
+static const unsigned int hscif3_data_d_mux[] = {
+	HRX3_D_MARK, HTX3_D_MARK,
+};
+
+/* - HSCIF4 ----------------------------------------------------------------- */
+static const unsigned int hscif4_data_a_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 12), RCAR_GP_PIN(1, 13),
+};
+
+static const unsigned int hscif4_data_a_mux[] = {
+	HRX4_A_MARK, HTX4_A_MARK,
+};
+
+static const unsigned int hscif4_clk_pins[] = {
+	/* SCK */
+	RCAR_GP_PIN(1, 11),
+};
+
+static const unsigned int hscif4_clk_mux[] = {
+	HSCK4_MARK,
+};
+
+static const unsigned int hscif4_ctrl_pins[] = {
+	/* RTS, CTS */
+	RCAR_GP_PIN(1, 15), RCAR_GP_PIN(1, 14),
+};
+
+static const unsigned int hscif4_ctrl_mux[] = {
+	HRTS4_N_MARK, HCTS4_N_MARK,
+};
+
+static const unsigned int hscif4_data_b_pins[] = {
+	/* RX, TX */
+	RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 11),
+};
+
+static const unsigned int hscif4_data_b_mux[] = {
+	HRX4_B_MARK, HTX4_B_MARK,
+};
+
 /* - I2C -------------------------------------------------------------------- */
 static const unsigned int i2c1_a_pins[] = {
 	/* SDA, SCL */
@@ -3169,6 +3426,34 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(du_oddf),
 	SH_PFC_PIN_GROUP(du_cde),
 	SH_PFC_PIN_GROUP(du_disp),
+	SH_PFC_PIN_GROUP(hscif0_data),
+	SH_PFC_PIN_GROUP(hscif0_clk),
+	SH_PFC_PIN_GROUP(hscif0_ctrl),
+	SH_PFC_PIN_GROUP(hscif1_data_a),
+	SH_PFC_PIN_GROUP(hscif1_clk_a),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif1_data_b),
+	SH_PFC_PIN_GROUP(hscif1_clk_b),
+	SH_PFC_PIN_GROUP(hscif1_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_a),
+	SH_PFC_PIN_GROUP(hscif2_clk_a),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_a),
+	SH_PFC_PIN_GROUP(hscif2_data_b),
+	SH_PFC_PIN_GROUP(hscif2_clk_b),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_b),
+	SH_PFC_PIN_GROUP(hscif2_data_c),
+	SH_PFC_PIN_GROUP(hscif2_clk_c),
+	SH_PFC_PIN_GROUP(hscif2_ctrl_c),
+	SH_PFC_PIN_GROUP(hscif3_data_a),
+	SH_PFC_PIN_GROUP(hscif3_clk),
+	SH_PFC_PIN_GROUP(hscif3_ctrl),
+	SH_PFC_PIN_GROUP(hscif3_data_b),
+	SH_PFC_PIN_GROUP(hscif3_data_c),
+	SH_PFC_PIN_GROUP(hscif3_data_d),
+	SH_PFC_PIN_GROUP(hscif4_data_a),
+	SH_PFC_PIN_GROUP(hscif4_clk),
+	SH_PFC_PIN_GROUP(hscif4_ctrl),
+	SH_PFC_PIN_GROUP(hscif4_data_b),
 	SH_PFC_PIN_GROUP(i2c1_a),
 	SH_PFC_PIN_GROUP(i2c1_b),
 	SH_PFC_PIN_GROUP(i2c2_a),
@@ -3379,6 +3664,49 @@ static const char * const du_groups[] = {
 	"du_disp",
 };
 
+static const char * const hscif0_groups[] = {
+	"hscif0_data",
+	"hscif0_clk",
+	"hscif0_ctrl",
+};
+
+static const char * const hscif1_groups[] = {
+	"hscif1_data_a",
+	"hscif1_clk_a",
+	"hscif1_ctrl_a",
+	"hscif1_data_b",
+	"hscif1_clk_b",
+	"hscif1_ctrl_b",
+};
+
+static const char * const hscif2_groups[] = {
+	"hscif2_data_a",
+	"hscif2_clk_a",
+	"hscif2_ctrl_a",
+	"hscif2_data_b",
+	"hscif2_clk_b",
+	"hscif2_ctrl_b",
+	"hscif2_data_c",
+	"hscif2_clk_c",
+	"hscif2_ctrl_c",
+};
+
+static const char * const hscif3_groups[] = {
+	"hscif3_data_a",
+	"hscif3_clk",
+	"hscif3_ctrl",
+	"hscif3_data_b",
+	"hscif3_data_c",
+	"hscif3_data_d",
+};
+
+static const char * const hscif4_groups[] = {
+	"hscif4_data_a",
+	"hscif4_clk",
+	"hscif4_ctrl",
+	"hscif4_data_b",
+};
+
 static const char * const i2c1_groups[] = {
 	"i2c1_a",
 	"i2c1_b",
@@ -3651,6 +3979,11 @@ static const char * const usb30_groups[] = {
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(du),
+	SH_PFC_FUNCTION(hscif0),
+	SH_PFC_FUNCTION(hscif1),
+	SH_PFC_FUNCTION(hscif2),
+	SH_PFC_FUNCTION(hscif3),
+	SH_PFC_FUNCTION(hscif4),
 	SH_PFC_FUNCTION(i2c1),
 	SH_PFC_FUNCTION(i2c2),
 	SH_PFC_FUNCTION(i2c6),
-- 
cgit v1.2.3


From 747c5417823d58aa494b04d4c329bb23c93bef92 Mon Sep 17 00:00:00 2001
From: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Date: Wed, 6 Jun 2018 15:43:04 +0900
Subject: pinctrl: sh-pfc: r8a77990: Revise USB ID pin name

Since the datasheet Rev.1.00 has an error about the USB ID pin name,
this patch revises it.

Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/sh-pfc/pfc-r8a77990.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
index a68fd658aada..dc4a957e1241 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
@@ -277,7 +277,7 @@
 #define IP11_15_12	FM(TX0_A)		FM(HTX1_A)		FM(SSI_WS2_A)		FM(RIF1_D0)		F_(0, 0)		F_(0, 0)	F_(0, 0)	FM(TS_SDAT1)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_19_16	FM(CTS0_N_A)		FM(NFDATA14_A)		FM(AUDIO_CLKOUT_A)	FM(RIF1_D1)		FM(SCIF_CLK_A)		FM(FMCLK_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_23_20	FM(RTS0_N_TANS_A)	FM(NFDATA15_A)		FM(AUDIO_CLKOUT1_A)	FM(RIF1_CLK)		FM(SCL2_A)		FM(FMIN_A)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
-#define IP11_27_24	FM(SCK0_A)		FM(HSCK1_A)		FM(USB3HS0_ID)		FM(RTS1_N_TANS)		FM(SDA2_A)		FM(FMCLK_C)	F_(0, 0)	F_(0, 0)	FM(USB1_ID)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+#define IP11_27_24	FM(SCK0_A)		FM(HSCK1_A)		FM(USB3HS0_ID)		FM(RTS1_N_TANS)		FM(SDA2_A)		FM(FMCLK_C)	F_(0, 0)	F_(0, 0)	FM(USB0_ID)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 #define IP11_31_28	FM(RX1)			FM(HRX2_B)		FM(SSI_SCK9_B)		FM(AUDIO_CLKOUT1_B)	F_(0, 0)		F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0)	F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
 
 /* IPSRx */		/* 0 */			/* 1 */			/* 2 */			/* 3 */			/* 4 */			/* 5 */		/* 6 */		/* 7 */		/* 8 */		/* 9 - F */
@@ -1082,7 +1082,7 @@ static const u16 pinmux_data[] = {
 	PINMUX_IPSR_GPSR(IP11_27_24,		RTS1_N_TANS),
 	PINMUX_IPSR_MSEL(IP11_27_24,		SDA2_A,		SEL_I2C2_0),
 	PINMUX_IPSR_MSEL(IP11_27_24,		FMCLK_C,	SEL_FM_2),
-	PINMUX_IPSR_GPSR(IP11_27_24,		USB1_ID),
+	PINMUX_IPSR_GPSR(IP11_27_24,		USB0_ID),
 
 	PINMUX_IPSR_GPSR(IP11_31_28,		RX1),
 	PINMUX_IPSR_MSEL(IP11_31_28,		HRX2_B,		SEL_HSCIF2_1),
-- 
cgit v1.2.3


From d7b535f99b39c808aa70faf23c4cfcee47b4abed Mon Sep 17 00:00:00 2001
From: Takeshi Kihara <takeshi.kihara.df@renesas.com>
Date: Wed, 6 Jun 2018 15:43:05 +0900
Subject: pinctrl: sh-pfc: r8a77990: Add USB2.0 pins, groups and functions

This patch adds USB0_{PWEN,OVC}_{A,B} and USB0_ID pins, groups and
functions to the R8A77990 SoC.

Signed-off-by: Takeshi Kihara <takeshi.kihara.df@renesas.com>
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/sh-pfc/pfc-r8a77990.c | 38 +++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
index dc4a957e1241..edefcc375f8b 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
@@ -1784,6 +1784,34 @@ static const unsigned int scif_clk_b_mux[] = {
 	SCIF_CLK_B_MARK,
 };
 
+/* - USB0 ------------------------------------------------------------------- */
+static const unsigned int usb0_a_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int usb0_a_mux[] = {
+	USB0_PWEN_A_MARK, USB0_OVC_A_MARK,
+};
+
+static const unsigned int usb0_b_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 11), RCAR_GP_PIN(6, 12),
+};
+
+static const unsigned int usb0_b_mux[] = {
+	USB0_PWEN_B_MARK, USB0_OVC_B_MARK,
+};
+
+static const unsigned int usb0_id_pins[] = {
+	/* ID */
+	RCAR_GP_PIN(5, 0)
+};
+
+static const unsigned int usb0_id_mux[] = {
+	USB0_ID_MARK,
+};
+
 static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(avb_link),
 	SH_PFC_PIN_GROUP(avb_magic),
@@ -1837,6 +1865,9 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(scif5_data_c),
 	SH_PFC_PIN_GROUP(scif_clk_a),
 	SH_PFC_PIN_GROUP(scif_clk_b),
+	SH_PFC_PIN_GROUP(usb0_a),
+	SH_PFC_PIN_GROUP(usb0_b),
+	SH_PFC_PIN_GROUP(usb0_id),
 };
 
 static const char * const avb_groups[] = {
@@ -1933,6 +1964,12 @@ static const char * const scif_clk_groups[] = {
 	"scif_clk_b",
 };
 
+static const char * const usb0_groups[] = {
+	"usb0_a",
+	"usb0_b",
+	"usb0_id",
+};
+
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(i2c1),
@@ -1948,6 +1985,7 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(scif4),
 	SH_PFC_FUNCTION(scif5),
 	SH_PFC_FUNCTION(scif_clk),
+	SH_PFC_FUNCTION(usb0),
 };
 
 static const struct pinmux_cfg_reg pinmux_config_regs[] = {
-- 
cgit v1.2.3


From a35f5c1ac2d4bdd777ffb8883961c10248da2aae Mon Sep 17 00:00:00 2001
From: Takeshi Kihara <takeshi.kihara.df@renesas.com>
Date: Tue, 3 Jul 2018 19:53:28 +0900
Subject: pinctrl: sh-pfc: r8a77990: Add USB3.0 pins, groups and functions

This patch adds USB30_{PWEN,OVC} and USB3HS0_ID pins, groups and functions
to the R8A77990 SoC.

Signed-off-by: Takeshi Kihara <takeshi.kihara.df@renesas.com>
Signed-off-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/sh-pfc/pfc-r8a77990.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
index edefcc375f8b..b81c807ac54d 100644
--- a/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
+++ b/drivers/pinctrl/sh-pfc/pfc-r8a77990.c
@@ -1812,6 +1812,25 @@ static const unsigned int usb0_id_mux[] = {
 	USB0_ID_MARK,
 };
 
+/* - USB30 ------------------------------------------------------------------ */
+static const unsigned int usb30_pins[] = {
+	/* PWEN, OVC */
+	RCAR_GP_PIN(6, 17), RCAR_GP_PIN(6, 9),
+};
+
+static const unsigned int usb30_mux[] = {
+	USB30_PWEN_MARK, USB30_OVC_MARK,
+};
+
+static const unsigned int usb30_id_pins[] = {
+	/* ID */
+	RCAR_GP_PIN(5, 0),
+};
+
+static const unsigned int usb30_id_mux[] = {
+	USB3HS0_ID_MARK,
+};
+
 static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(avb_link),
 	SH_PFC_PIN_GROUP(avb_magic),
@@ -1868,6 +1887,8 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
 	SH_PFC_PIN_GROUP(usb0_a),
 	SH_PFC_PIN_GROUP(usb0_b),
 	SH_PFC_PIN_GROUP(usb0_id),
+	SH_PFC_PIN_GROUP(usb30),
+	SH_PFC_PIN_GROUP(usb30_id),
 };
 
 static const char * const avb_groups[] = {
@@ -1970,6 +1991,11 @@ static const char * const usb0_groups[] = {
 	"usb0_id",
 };
 
+static const char * const usb30_groups[] = {
+	"usb30",
+	"usb30_id",
+};
+
 static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(avb),
 	SH_PFC_FUNCTION(i2c1),
@@ -1986,6 +2012,7 @@ static const struct sh_pfc_function pinmux_functions[] = {
 	SH_PFC_FUNCTION(scif5),
 	SH_PFC_FUNCTION(scif_clk),
 	SH_PFC_FUNCTION(usb0),
+	SH_PFC_FUNCTION(usb30),
 };
 
 static const struct pinmux_cfg_reg pinmux_config_regs[] = {
-- 
cgit v1.2.3


From a130af0162409fc8a118930255979d8be4adde5a Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Wed, 4 Jul 2018 18:57:24 +0200
Subject: pinctrl: meson: add gen_clk pins

Add the pinctrl configuration for gen_clk on gxbb and axg.
gen_clk allows to output and devide several internal clocks of SoC,
including most of the plls.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/meson/pinctrl-meson-axg.c  | 9 +++++++++
 drivers/pinctrl/meson/pinctrl-meson-gxbb.c | 8 ++++++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/pinctrl/meson/pinctrl-meson-axg.c b/drivers/pinctrl/meson/pinctrl-meson-axg.c
index 46a0918bd284..ad502eda4afa 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-axg.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-axg.c
@@ -672,6 +672,9 @@ static const unsigned int jtag_ao_tdo_pins[] = {GPIOAO_4};
 static const unsigned int jtag_ao_clk_pins[] = {GPIOAO_5};
 static const unsigned int jtag_ao_tms_pins[] = {GPIOAO_7};
 
+/* gen_clk */
+static const unsigned int gen_clk_ee_pins[] = {GPIOAO_13};
+
 static struct meson_pmx_group meson_axg_aobus_groups[] = {
 	GPIO_GROUP(GPIOAO_0),
 	GPIO_GROUP(GPIOAO_1),
@@ -718,6 +721,7 @@ static struct meson_pmx_group meson_axg_aobus_groups[] = {
 	GROUP(jtag_ao_tdo, 4),
 	GROUP(jtag_ao_clk, 4),
 	GROUP(jtag_ao_tms, 4),
+	GROUP(gen_clk_ee, 4),
 };
 
 static const char * const gpio_periphs_groups[] = {
@@ -947,6 +951,10 @@ static const char * const tdmb_groups[] = {
 	"tdmb_din2", "tdmb_dout2", "tdmb_din3",	"tdmb_dout3",
 };
 
+static const char * const gen_clk_ee_groups[] = {
+	"gen_clk_ee",
+};
+
 static struct meson_pmx_func meson_axg_periphs_functions[] = {
 	FUNCTION(gpio_periphs),
 	FUNCTION(emmc),
@@ -992,6 +1000,7 @@ static struct meson_pmx_func meson_axg_aobus_functions[] = {
 	FUNCTION(pwm_ao_c),
 	FUNCTION(pwm_ao_d),
 	FUNCTION(jtag_ao),
+	FUNCTION(gen_clk_ee),
 };
 
 static struct meson_bank meson_axg_periphs_banks[] = {
diff --git a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
index 2c97a2e07a5f..4ceb06f8a33c 100644
--- a/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
+++ b/drivers/pinctrl/meson/pinctrl-meson-gxbb.c
@@ -243,6 +243,8 @@ static const unsigned int i2s_out_ch67_y_pins[]	= { GPIOY_10 };
 
 static const unsigned int spdif_out_y_pins[]	= { GPIOY_12 };
 
+static const unsigned int gen_clk_out_pins[]	= { GPIOY_15 };
+
 static const struct pinctrl_pin_desc meson_gxbb_aobus_pins[] = {
 	MESON_PIN(GPIOAO_0),
 	MESON_PIN(GPIOAO_1),
@@ -453,6 +455,7 @@ static struct meson_pmx_group meson_gxbb_periphs_groups[] = {
 	GROUP(i2s_out_ch45_y,	1,	6),
 	GROUP(i2s_out_ch67_y,	1,	7),
 	GROUP(spdif_out_y,	1,	9),
+	GROUP(gen_clk_out,	6,	15),
 
 	/* Bank Z */
 	GROUP(eth_mdio,		6,	1),
@@ -706,6 +709,10 @@ static const char * const spdif_out_groups[] = {
 	"spdif_out_y",
 };
 
+static const char * const gen_clk_out_groups[] = {
+	"gen_clk_out",
+};
+
 static const char * const gpio_aobus_groups[] = {
 	"GPIOAO_0", "GPIOAO_1", "GPIOAO_2", "GPIOAO_3", "GPIOAO_4",
 	"GPIOAO_5", "GPIOAO_6", "GPIOAO_7", "GPIOAO_8", "GPIOAO_9",
@@ -790,6 +797,7 @@ static struct meson_pmx_func meson_gxbb_periphs_functions[] = {
 	FUNCTION(hdmi_i2c),
 	FUNCTION(i2s_out),
 	FUNCTION(spdif_out),
+	FUNCTION(gen_clk_out),
 };
 
 static struct meson_pmx_func meson_gxbb_aobus_functions[] = {
-- 
cgit v1.2.3


From e12fa73c97a4c5fbc77b28e6436277fdc4f9b3b5 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 5 Jul 2018 10:44:52 -0500
Subject: pinctrl: mt7622: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Warning level 2 was used: -Wimplicit-fallthrough=2

Addresses-Coverity-ID: 1463284 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/pinctrl-mt7622.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
index ad6da1184c9f..b8df7ad87cf4 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
@@ -1263,6 +1263,7 @@ static int mtk_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin,
 					       MTK_DISABLE);
 			if (err)
 				goto err;
+			/* else: fall through */
 		case PIN_CONFIG_INPUT_ENABLE:
 		case PIN_CONFIG_SLEW_RATE:
 			reg = (param == PIN_CONFIG_SLEW_RATE) ?
-- 
cgit v1.2.3


From ff10e353a4c0c83a28c89c182462b3c8dc7f70cc Mon Sep 17 00:00:00 2001
From: Ludovic Desroches <ludovic.desroches@microchip.com>
Date: Fri, 29 Jun 2018 10:15:33 +0200
Subject: pinctrl: at91-pio4: add support for drive strength

Add support for the drive strength configuration. Usually, this value is
expressed in mA. Since the numeric value depends on VDDIOP voltage, a
value we can't retrieve at runtime, the controller uses low, medium and
high to define the drive strength.

The PIO controller accepts two values for the low drive configuration: 0
and 1. Most of the time, we don't care about the drive strength. So we
keep the default value which is 0. The drive strength is advertised
through the sysfs only when it has been explicitly set in the device
tree i.e. if its value is different from 0.

Signed-off-by: Ludovic Desroches <ludovic.desroches@microchip.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/atmel,at91-pio4-pinctrl.txt   |  3 ++
 drivers/pinctrl/pinctrl-at91-pio4.c                | 42 ++++++++++++++++++++++
 include/dt-bindings/pinctrl/at91.h                 |  4 +++
 3 files changed, 49 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt
index 61ac75706cc9..04d16fb69eb7 100644
--- a/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/atmel,at91-pio4-pinctrl.txt
@@ -36,6 +36,8 @@ Optional properties:
 - GENERIC_PINCONFIG: generic pinconfig options to use, bias-disable,
 bias-pull-down, bias-pull-up, drive-open-drain, input-schmitt-enable,
 input-debounce, output-low, output-high.
+- atmel,drive-strength: 0 or 1 for low drive, 2 for medium drive and 3 for
+high drive. The default value is low drive.
 
 Example:
 
@@ -66,6 +68,7 @@ Example:
 			pinmux = <PIN_PB0>,
 				 <PIN_PB5>;
 			bias-pull-up;
+			atmel,drive-strength = <ATMEL_PIO_DRVSTR_ME>;
 		};
 
 		pinctrl_sdmmc1_default: sdmmc1_default {
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 67e4d9ffa6b1..8f061971a7d1 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -14,6 +14,7 @@
  * GNU General Public License for more details.
  */
 
+#include <dt-bindings/pinctrl/at91.h>
 #include <linux/clk.h>
 #include <linux/gpio/driver.h>
 /* FIXME: needed for gpio_to_irq(), get rid of this */
@@ -49,6 +50,8 @@
 #define		ATMEL_PIO_IFSCEN_MASK		BIT(13)
 #define		ATMEL_PIO_OPD_MASK		BIT(14)
 #define		ATMEL_PIO_SCHMITT_MASK		BIT(15)
+#define		ATMEL_PIO_DRVSTR_MASK		GENMASK(17, 16)
+#define		ATMEL_PIO_DRVSTR_OFFSET		16
 #define		ATMEL_PIO_CFGR_EVTSEL_MASK	GENMASK(26, 24)
 #define		ATMEL_PIO_CFGR_EVTSEL_FALLING	(0 << 24)
 #define		ATMEL_PIO_CFGR_EVTSEL_RISING	(1 << 24)
@@ -75,6 +78,9 @@
 #define ATMEL_GET_PIN_FUNC(pinfunc)	((pinfunc >> 16) & 0xf)
 #define ATMEL_GET_PIN_IOSET(pinfunc)	((pinfunc >> 20) & 0xf)
 
+/* Custom pinconf parameters */
+#define ATMEL_PIN_CONFIG_DRIVE_STRENGTH	(PIN_CONFIG_END + 1)
+
 struct atmel_pioctrl_data {
 	unsigned nbanks;
 };
@@ -139,6 +145,10 @@ static const char * const atmel_functions[] = {
 	"GPIO", "A", "B", "C", "D", "E", "F", "G"
 };
 
+static const struct pinconf_generic_params atmel_custom_bindings[] = {
+	{"atmel,drive-strength", ATMEL_PIN_CONFIG_DRIVE_STRENGTH, 0},
+};
+
 /* --- GPIO --- */
 static unsigned int atmel_gpio_read(struct atmel_pioctrl *atmel_pioctrl,
 				    unsigned int bank, unsigned int reg)
@@ -692,6 +702,11 @@ static int atmel_conf_pin_config_group_get(struct pinctrl_dev *pctldev,
 			return -EINVAL;
 		arg = 1;
 		break;
+	case ATMEL_PIN_CONFIG_DRIVE_STRENGTH:
+		if (!(res & ATMEL_PIO_DRVSTR_MASK))
+			return -EINVAL;
+		arg = (res & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET;
+		break;
 	default:
 		return -ENOTSUPP;
 	}
@@ -777,6 +792,18 @@ static int atmel_conf_pin_config_group_set(struct pinctrl_dev *pctldev,
 					ATMEL_PIO_SODR);
 			}
 			break;
+		case ATMEL_PIN_CONFIG_DRIVE_STRENGTH:
+			switch (arg) {
+			case ATMEL_PIO_DRVSTR_LO:
+			case ATMEL_PIO_DRVSTR_ME:
+			case ATMEL_PIO_DRVSTR_HI:
+				conf &= (~ATMEL_PIO_DRVSTR_MASK);
+				conf |= arg << ATMEL_PIO_DRVSTR_OFFSET;
+				break;
+			default:
+				dev_warn(pctldev->dev, "drive strength not updated (incorrect value)\n");
+			}
+			break;
 		default:
 			dev_warn(pctldev->dev,
 				 "unsupported configuration parameter: %u\n",
@@ -816,6 +843,19 @@ static void atmel_conf_pin_config_dbg_show(struct pinctrl_dev *pctldev,
 		seq_printf(s, "%s ", "open-drain");
 	if (conf & ATMEL_PIO_SCHMITT_MASK)
 		seq_printf(s, "%s ", "schmitt");
+	if (conf & ATMEL_PIO_DRVSTR_MASK) {
+		switch ((conf & ATMEL_PIO_DRVSTR_MASK) >> ATMEL_PIO_DRVSTR_OFFSET) {
+		case ATMEL_PIO_DRVSTR_ME:
+			seq_printf(s, "%s ", "medium-drive");
+			break;
+		case ATMEL_PIO_DRVSTR_HI:
+			seq_printf(s, "%s ", "high-drive");
+			break;
+		/* ATMEL_PIO_DRVSTR_LO and 0 which is the default value at reset */
+		default:
+			seq_printf(s, "%s ", "low-drive");
+		}
+	}
 }
 
 static const struct pinconf_ops atmel_confops = {
@@ -958,6 +998,8 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	atmel_pinctrl_desc.pins = pin_desc;
 	atmel_pinctrl_desc.npins = atmel_pioctrl->npins;
+	atmel_pinctrl_desc.num_custom_params = ARRAY_SIZE(atmel_custom_bindings);
+	atmel_pinctrl_desc.custom_params = atmel_custom_bindings;
 
 	/* One pin is one group since a pin can achieve all functions. */
 	group_names = devm_kcalloc(dev,
diff --git a/include/dt-bindings/pinctrl/at91.h b/include/dt-bindings/pinctrl/at91.h
index 2732d6c0fb39..eb81867eac77 100644
--- a/include/dt-bindings/pinctrl/at91.h
+++ b/include/dt-bindings/pinctrl/at91.h
@@ -39,4 +39,8 @@
 #define AT91_PERIPH_C		3
 #define AT91_PERIPH_D		4
 
+#define ATMEL_PIO_DRVSTR_LO	1
+#define ATMEL_PIO_DRVSTR_ME	2
+#define ATMEL_PIO_DRVSTR_HI	3
+
 #endif /* __DT_BINDINGS_AT91_PINCTRL_H__ */
-- 
cgit v1.2.3


From 399476bd40a5f3518d9ca8e809ca042028c41cea Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 5 Jul 2018 10:51:27 -0500
Subject: pinctrl: baytrail: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1292308 ("Missing break in switch")
Addresses-Coverity-ID: 1292309 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/pinctrl-baytrail.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 153187919d02..003ad48a607f 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1534,11 +1534,13 @@ static void byt_irq_unmask(struct irq_data *d)
 	switch (irqd_get_trigger_type(d)) {
 	case IRQ_TYPE_LEVEL_HIGH:
 		value |= BYT_TRIG_LVL;
+		/* fall through */
 	case IRQ_TYPE_EDGE_RISING:
 		value |= BYT_TRIG_POS;
 		break;
 	case IRQ_TYPE_LEVEL_LOW:
 		value |= BYT_TRIG_LVL;
+		/* fall through */
 	case IRQ_TYPE_EDGE_FALLING:
 		value |= BYT_TRIG_NEG;
 		break;
-- 
cgit v1.2.3


From 95e7618b7ba1a0ddb05643712e21b3df413ffb8f Mon Sep 17 00:00:00 2001
From: Abel Vesa <abel.vesa@nxp.com>
Date: Mon, 2 Jul 2018 14:59:05 +0300
Subject: pinctrl: imx: Add DT binding for i.MX8MQ IOMUXC

This adds the binding for the i.MX8MQ pin controller, in the same
fashion as earlier i.MX SoCs.

Signed-off-by: Abel Vesa <abel.vesa@nxp.com>
Acked-by: Dong Aisheng <aisheng.dong@nxp.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/pinctrl/fsl,imx8mq-pinctrl.txt        | 36 ++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/pinctrl/fsl,imx8mq-pinctrl.txt

diff --git a/Documentation/devicetree/bindings/pinctrl/fsl,imx8mq-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/fsl,imx8mq-pinctrl.txt
new file mode 100644
index 000000000000..66de75090458
--- /dev/null
+++ b/Documentation/devicetree/bindings/pinctrl/fsl,imx8mq-pinctrl.txt
@@ -0,0 +1,36 @@
+* Freescale IMX8MQ IOMUX Controller
+
+Please refer to fsl,imx-pinctrl.txt and pinctrl-bindings.txt in this directory
+for common binding part and usage.
+
+Required properties:
+- compatible: "fsl,imx8mq-iomuxc"
+- reg: should contain the base physical address and size of the iomuxc
+  registers.
+
+Required properties in sub-nodes:
+- fsl,pins: each entry consists of 6 integers and represents the mux and config
+  setting for one pin.  The first 5 integers <mux_reg conf_reg input_reg mux_val
+  input_val> are specified using a PIN_FUNC_ID macro, which can be found in
+  imx8mq-pinfunc.h under device tree source folder.  The last integer CONFIG is
+  the pad setting value like pull-up on this pin.  Please refer to i.MX8M Quad
+  Reference Manual for detailed CONFIG settings.
+
+Examples:
+
+&uart1 {
+       pinctrl-names = "default";
+       pinctrl-0 = <&pinctrl_uart1>;
+};
+
+iomuxc: pinctrl@30330000 {
+        compatible = "fsl,imx8mq-iomuxc";
+        reg = <0x0 0x30330000 0x0 0x10000>;
+
+        pinctrl_uart1: uart1grp {
+                fsl,pins = <
+                        MX8MQ_IOMUXC_UART1_RXD_UART1_DCE_RX             0x49
+                        MX8MQ_IOMUXC_UART1_TXD_UART1_DCE_TX             0x49
+                >;
+        };
+};
-- 
cgit v1.2.3


From 45b85fca4598e4d4b881df1a482919d1df909016 Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Mon, 2 Jul 2018 14:59:06 +0300
Subject: pinctrl: imx: add driver for i.MX8MQ

The i.MX8MQ pincontrol works in a similar way to the earlier i.MX SoCs.
This driver builds on top of the imx specific pinconf handling.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Signed-off-by: Abel Vesa <abel.vesa@nxp.com>
Acked-by: Dong Aisheng <aisheng.dong@nxp.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/Kconfig          |   7 +
 drivers/pinctrl/freescale/Makefile         |   1 +
 drivers/pinctrl/freescale/pinctrl-imx8mq.c | 351 +++++++++++++++++++++++++++++
 3 files changed, 359 insertions(+)
 create mode 100644 drivers/pinctrl/freescale/pinctrl-imx8mq.c

diff --git a/drivers/pinctrl/freescale/Kconfig b/drivers/pinctrl/freescale/Kconfig
index 0d8ba1ef5329..dccf64c55498 100644
--- a/drivers/pinctrl/freescale/Kconfig
+++ b/drivers/pinctrl/freescale/Kconfig
@@ -117,6 +117,13 @@ config PINCTRL_IMX7ULP
 	help
 	  Say Y here to enable the imx7ulp pinctrl driver
 
+config PINCTRL_IMX8MQ
+	bool "IMX8MQ pinctrl driver"
+	depends on SOC_IMX8MQ
+	select PINCTRL_IMX
+	help
+	  Say Y here to enable the imx8mq pinctrl driver
+
 config PINCTRL_VF610
 	bool "Freescale Vybrid VF610 pinctrl driver"
 	depends on SOC_VF610
diff --git a/drivers/pinctrl/freescale/Makefile b/drivers/pinctrl/freescale/Makefile
index 368be8cfc9b1..73175b3e7c9c 100644
--- a/drivers/pinctrl/freescale/Makefile
+++ b/drivers/pinctrl/freescale/Makefile
@@ -17,6 +17,7 @@ obj-$(CONFIG_PINCTRL_IMX6SX)	+= pinctrl-imx6sx.o
 obj-$(CONFIG_PINCTRL_IMX6UL)	+= pinctrl-imx6ul.o
 obj-$(CONFIG_PINCTRL_IMX7D)	+= pinctrl-imx7d.o
 obj-$(CONFIG_PINCTRL_IMX7ULP)	+= pinctrl-imx7ulp.o
+obj-$(CONFIG_PINCTRL_IMX8MQ)	+= pinctrl-imx8mq.o
 obj-$(CONFIG_PINCTRL_VF610)	+= pinctrl-vf610.o
 obj-$(CONFIG_PINCTRL_MXS)	+= pinctrl-mxs.o
 obj-$(CONFIG_PINCTRL_IMX23)	+= pinctrl-imx23.o
diff --git a/drivers/pinctrl/freescale/pinctrl-imx8mq.c b/drivers/pinctrl/freescale/pinctrl-imx8mq.c
new file mode 100644
index 000000000000..8d39af541d5f
--- /dev/null
+++ b/drivers/pinctrl/freescale/pinctrl-imx8mq.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ * Copyright 2017-2018 NXP
+ * Copyright (C) 2018 Pengutronix, Lucas Stach <kernel@pengutronix.de>
+ */
+
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/pinctrl/pinctrl.h>
+
+#include "pinctrl-imx.h"
+
+enum imx8mq_pads {
+	MX8MQ_PAD_RESERVE0 = 0,
+	MX8MQ_PAD_RESERVE1 = 1,
+	MX8MQ_PAD_RESERVE2 = 2,
+	MX8MQ_PAD_RESERVE3 = 3,
+	MX8MQ_PAD_RESERVE4 = 4,
+	MX8MQ_IOMUXC_PMIC_STBY_REQ_CCMSRCGPCMIX = 5,
+	MX8MQ_IOMUXC_PMIC_ON_REQ_SNVSMIX = 6,
+	MX8MQ_IOMUXC_ONOFF_SNVSMIX = 7,
+	MX8MQ_IOMUXC_POR_B_SNVSMIX = 8,
+	MX8MQ_IOMUXC_RTC_RESET_B_SNVSMIX = 9,
+	MX8MQ_IOMUXC_GPIO1_IO00 = 10,
+	MX8MQ_IOMUXC_GPIO1_IO01 = 11,
+	MX8MQ_IOMUXC_GPIO1_IO02 = 12,
+	MX8MQ_IOMUXC_GPIO1_IO03 = 13,
+	MX8MQ_IOMUXC_GPIO1_IO04 = 14,
+	MX8MQ_IOMUXC_GPIO1_IO05 = 15,
+	MX8MQ_IOMUXC_GPIO1_IO06 = 16,
+	MX8MQ_IOMUXC_GPIO1_IO07 = 17,
+	MX8MQ_IOMUXC_GPIO1_IO08 = 18,
+	MX8MQ_IOMUXC_GPIO1_IO09 = 19,
+	MX8MQ_IOMUXC_GPIO1_IO10 = 20,
+	MX8MQ_IOMUXC_GPIO1_IO11 = 21,
+	MX8MQ_IOMUXC_GPIO1_IO12 = 22,
+	MX8MQ_IOMUXC_GPIO1_IO13 = 23,
+	MX8MQ_IOMUXC_GPIO1_IO14 = 24,
+	MX8MQ_IOMUXC_GPIO1_IO15 = 25,
+	MX8MQ_IOMUXC_ENET_MDC = 26,
+	MX8MQ_IOMUXC_ENET_MDIO = 27,
+	MX8MQ_IOMUXC_ENET_TD3 = 28,
+	MX8MQ_IOMUXC_ENET_TD2 = 29,
+	MX8MQ_IOMUXC_ENET_TD1 = 30,
+	MX8MQ_IOMUXC_ENET_TD0 = 31,
+	MX8MQ_IOMUXC_ENET_TX_CTL = 32,
+	MX8MQ_IOMUXC_ENET_TXC = 33,
+	MX8MQ_IOMUXC_ENET_RX_CTL = 34,
+	MX8MQ_IOMUXC_ENET_RXC = 35,
+	MX8MQ_IOMUXC_ENET_RD0 = 36,
+	MX8MQ_IOMUXC_ENET_RD1 = 37,
+	MX8MQ_IOMUXC_ENET_RD2 = 38,
+	MX8MQ_IOMUXC_ENET_RD3 = 39,
+	MX8MQ_IOMUXC_SD1_CLK = 40,
+	MX8MQ_IOMUXC_SD1_CMD = 41,
+	MX8MQ_IOMUXC_SD1_DATA0 = 42,
+	MX8MQ_IOMUXC_SD1_DATA1 = 43,
+	MX8MQ_IOMUXC_SD1_DATA2 = 44,
+	MX8MQ_IOMUXC_SD1_DATA3 = 45,
+	MX8MQ_IOMUXC_SD1_DATA4 = 46,
+	MX8MQ_IOMUXC_SD1_DATA5 = 47,
+	MX8MQ_IOMUXC_SD1_DATA6 = 48,
+	MX8MQ_IOMUXC_SD1_DATA7 = 49,
+	MX8MQ_IOMUXC_SD1_RESET_B = 50,
+	MX8MQ_IOMUXC_SD1_STROBE = 51,
+	MX8MQ_IOMUXC_SD2_CD_B = 52,
+	MX8MQ_IOMUXC_SD2_CLK = 53,
+	MX8MQ_IOMUXC_SD2_CMD = 54,
+	MX8MQ_IOMUXC_SD2_DATA0 = 55,
+	MX8MQ_IOMUXC_SD2_DATA1 = 56,
+	MX8MQ_IOMUXC_SD2_DATA2 = 57,
+	MX8MQ_IOMUXC_SD2_DATA3 = 58,
+	MX8MQ_IOMUXC_SD2_RESET_B = 59,
+	MX8MQ_IOMUXC_SD2_WP = 60,
+	MX8MQ_IOMUXC_NAND_ALE = 61,
+	MX8MQ_IOMUXC_NAND_CE0_B = 62,
+	MX8MQ_IOMUXC_NAND_CE1_B = 63,
+	MX8MQ_IOMUXC_NAND_CE2_B = 64,
+	MX8MQ_IOMUXC_NAND_CE3_B = 65,
+	MX8MQ_IOMUXC_NAND_CLE = 66,
+	MX8MQ_IOMUXC_NAND_DATA00 = 67,
+	MX8MQ_IOMUXC_NAND_DATA01 = 68,
+	MX8MQ_IOMUXC_NAND_DATA02 = 69,
+	MX8MQ_IOMUXC_NAND_DATA03 = 70,
+	MX8MQ_IOMUXC_NAND_DATA04 = 71,
+	MX8MQ_IOMUXC_NAND_DATA05 = 72,
+	MX8MQ_IOMUXC_NAND_DATA06 = 73,
+	MX8MQ_IOMUXC_NAND_DATA07 = 74,
+	MX8MQ_IOMUXC_NAND_DQS = 75,
+	MX8MQ_IOMUXC_NAND_RE_B = 76,
+	MX8MQ_IOMUXC_NAND_READY_B = 77,
+	MX8MQ_IOMUXC_NAND_WE_B = 78,
+	MX8MQ_IOMUXC_NAND_WP_B = 79,
+	MX8MQ_IOMUXC_SAI5_RXFS = 80,
+	MX8MQ_IOMUXC_SAI5_RXC = 81,
+	MX8MQ_IOMUXC_SAI5_RXD0 = 82,
+	MX8MQ_IOMUXC_SAI5_RXD1 = 83,
+	MX8MQ_IOMUXC_SAI5_RXD2 = 84,
+	MX8MQ_IOMUXC_SAI5_RXD3 = 85,
+	MX8MQ_IOMUXC_SAI5_MCLK = 86,
+	MX8MQ_IOMUXC_SAI1_RXFS = 87,
+	MX8MQ_IOMUXC_SAI1_RXC = 88,
+	MX8MQ_IOMUXC_SAI1_RXD0 = 89,
+	MX8MQ_IOMUXC_SAI1_RXD1 = 90,
+	MX8MQ_IOMUXC_SAI1_RXD2 = 91,
+	MX8MQ_IOMUXC_SAI1_RXD3 = 92,
+	MX8MQ_IOMUXC_SAI1_RXD4 = 93,
+	MX8MQ_IOMUXC_SAI1_RXD5 = 94,
+	MX8MQ_IOMUXC_SAI1_RXD6 = 95,
+	MX8MQ_IOMUXC_SAI1_RXD7 = 96,
+	MX8MQ_IOMUXC_SAI1_TXFS = 97,
+	MX8MQ_IOMUXC_SAI1_TXC = 98,
+	MX8MQ_IOMUXC_SAI1_TXD0 = 99,
+	MX8MQ_IOMUXC_SAI1_TXD1 = 100,
+	MX8MQ_IOMUXC_SAI1_TXD2 = 101,
+	MX8MQ_IOMUXC_SAI1_TXD3 = 102,
+	MX8MQ_IOMUXC_SAI1_TXD4 = 103,
+	MX8MQ_IOMUXC_SAI1_TXD5 = 104,
+	MX8MQ_IOMUXC_SAI1_TXD6 = 105,
+	MX8MQ_IOMUXC_SAI1_TXD7 = 106,
+	MX8MQ_IOMUXC_SAI1_MCLK = 107,
+	MX8MQ_IOMUXC_SAI2_RXFS = 108,
+	MX8MQ_IOMUXC_SAI2_RXC = 109,
+	MX8MQ_IOMUXC_SAI2_RXD0 = 110,
+	MX8MQ_IOMUXC_SAI2_TXFS = 111,
+	MX8MQ_IOMUXC_SAI2_TXC = 112,
+	MX8MQ_IOMUXC_SAI2_TXD0 = 113,
+	MX8MQ_IOMUXC_SAI2_MCLK = 114,
+	MX8MQ_IOMUXC_SAI3_RXFS = 115,
+	MX8MQ_IOMUXC_SAI3_RXC = 116,
+	MX8MQ_IOMUXC_SAI3_RXD = 117,
+	MX8MQ_IOMUXC_SAI3_TXFS = 118,
+	MX8MQ_IOMUXC_SAI3_TXC = 119,
+	MX8MQ_IOMUXC_SAI3_TXD = 120,
+	MX8MQ_IOMUXC_SAI3_MCLK = 121,
+	MX8MQ_IOMUXC_SPDIF_TX = 122,
+	MX8MQ_IOMUXC_SPDIF_RX = 123,
+	MX8MQ_IOMUXC_SPDIF_EXT_CLK = 124,
+	MX8MQ_IOMUXC_ECSPI1_SCLK = 125,
+	MX8MQ_IOMUXC_ECSPI1_MOSI = 126,
+	MX8MQ_IOMUXC_ECSPI1_MISO = 127,
+	MX8MQ_IOMUXC_ECSPI1_SS0 = 128,
+	MX8MQ_IOMUXC_ECSPI2_SCLK = 129,
+	MX8MQ_IOMUXC_ECSPI2_MOSI = 130,
+	MX8MQ_IOMUXC_ECSPI2_MISO = 131,
+	MX8MQ_IOMUXC_ECSPI2_SS0 = 132,
+	MX8MQ_IOMUXC_I2C1_SCL = 133,
+	MX8MQ_IOMUXC_I2C1_SDA = 134,
+	MX8MQ_IOMUXC_I2C2_SCL = 135,
+	MX8MQ_IOMUXC_I2C2_SDA = 136,
+	MX8MQ_IOMUXC_I2C3_SCL = 137,
+	MX8MQ_IOMUXC_I2C3_SDA = 138,
+	MX8MQ_IOMUXC_I2C4_SCL = 139,
+	MX8MQ_IOMUXC_I2C4_SDA = 140,
+	MX8MQ_IOMUXC_UART1_RXD = 141,
+	MX8MQ_IOMUXC_UART1_TXD = 142,
+	MX8MQ_IOMUXC_UART2_RXD = 143,
+	MX8MQ_IOMUXC_UART2_TXD = 144,
+	MX8MQ_IOMUXC_UART3_RXD = 145,
+	MX8MQ_IOMUXC_UART3_TXD = 146,
+	MX8MQ_IOMUXC_UART4_RXD = 147,
+	MX8MQ_IOMUXC_UART4_TXD = 148,
+};
+
+/* Pad names for the pinmux subsystem */
+static const struct pinctrl_pin_desc imx8mq_pinctrl_pads[] = {
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE0),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE1),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE2),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE3),
+	IMX_PINCTRL_PIN(MX8MQ_PAD_RESERVE4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_PMIC_STBY_REQ_CCMSRCGPCMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_PMIC_ON_REQ_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ONOFF_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_POR_B_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_RTC_RESET_B_SNVSMIX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO00),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO01),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO02),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO03),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO04),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO05),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO06),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO07),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO08),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO09),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO10),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO11),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO12),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO13),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO14),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_GPIO1_IO15),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_MDC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_MDIO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TX_CTL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RX_CTL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ENET_RD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_CMD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_DATA7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_RESET_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD1_STROBE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CD_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_CMD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_DATA3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_RESET_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SD2_WP),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_ALE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE0_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE1_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE2_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CE3_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_CLE),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA00),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA01),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA02),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA03),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA04),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA05),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA06),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DATA07),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_DQS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_RE_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_READY_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_WE_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_NAND_WP_B),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_RXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI5_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_RXD7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD1),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD2),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD3),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD4),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD5),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD6),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_TXD7),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI1_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_RXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_TXD0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI2_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXFS),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXC),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SAI3_MCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_TX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_RX),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_SPDIF_EXT_CLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_SCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_MOSI),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_MISO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI1_SS0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_SCLK),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_MOSI),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_MISO),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_ECSPI2_SS0),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C1_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C1_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C2_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C2_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C3_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C3_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C4_SCL),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_I2C4_SDA),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART1_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART1_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART2_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART2_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART3_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART3_TXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART4_RXD),
+	IMX_PINCTRL_PIN(MX8MQ_IOMUXC_UART4_TXD),
+};
+
+static const struct imx_pinctrl_soc_info imx8mq_pinctrl_info = {
+	.pins = imx8mq_pinctrl_pads,
+	.npins = ARRAY_SIZE(imx8mq_pinctrl_pads),
+	.gpr_compatible = "fsl,imx8mq-iomuxc-gpr",
+};
+
+static const struct of_device_id imx8mq_pinctrl_of_match[] = {
+	{ .compatible = "fsl,imx8mq-iomuxc", .data = &imx8mq_pinctrl_info, },
+	{ /* sentinel */ }
+};
+
+static int imx8mq_pinctrl_probe(struct platform_device *pdev)
+{
+	return imx_pinctrl_probe(pdev, &imx8mq_pinctrl_info);
+}
+
+static struct platform_driver imx8mq_pinctrl_driver = {
+	.driver = {
+		.name = "imx8mq-pinctrl",
+		.of_match_table = of_match_ptr(imx8mq_pinctrl_of_match),
+		.suppress_bind_attrs = true,
+	},
+	.probe = imx8mq_pinctrl_probe,
+};
+
+static int __init imx8mq_pinctrl_init(void)
+{
+	return platform_driver_register(&imx8mq_pinctrl_driver);
+}
+arch_initcall(imx8mq_pinctrl_init);
-- 
cgit v1.2.3


From 17f790843cd77d69927ccd2f01a3bbd55067069e Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Wed, 11 Jul 2018 15:01:26 +0200
Subject: pinctrl: ocelot: fix gpio4 twi function

the TWI function on GPIO4 is actually a multiplexed SCL, not an original
TWI SDA or SCL. Fix it.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-ocelot.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index 15bb1cb8729b..e93669f4d1c8 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -132,7 +132,7 @@ OCELOT_P(0,  SG0,       NONE,      NONE);
 OCELOT_P(1,  SG0,       NONE,      NONE);
 OCELOT_P(2,  SG0,       NONE,      NONE);
 OCELOT_P(3,  SG0,       NONE,      NONE);
-OCELOT_P(4,  IRQ0_IN,   IRQ0_OUT,  TWI);
+OCELOT_P(4,  IRQ0_IN,   IRQ0_OUT,  TWI_SCL_M);
 OCELOT_P(5,  IRQ1_IN,   IRQ1_OUT,  PCI_WAKE);
 OCELOT_P(6,  UART,      TWI_SCL_M, NONE);
 OCELOT_P(7,  UART,      TWI_SCL_M, NONE);
-- 
cgit v1.2.3


From aa0d8bda510865e06b56effc14c913b5af8142d8 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 11 Jul 2018 12:34:07 +0000
Subject: pinctrl: at91-pio4: Remove redundant return value check

Remove unneeded error handling on the result of a call
to platform_get_resource() when the value is passed to
devm_ioremap_resource().

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Acked-by: Ludovic Desroches <ludovic.desroches@microchip.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-at91-pio4.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 8f061971a7d1..ef7ab208b951 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -971,10 +971,6 @@ static int atmel_pinctrl_probe(struct platform_device *pdev)
 	atmel_pioctrl->npins = atmel_pioctrl->nbanks * ATMEL_PIO_NPINS_PER_BANK;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res) {
-		dev_err(dev, "unable to get atmel pinctrl resource\n");
-		return -EINVAL;
-	}
 	atmel_pioctrl->reg_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(atmel_pioctrl->reg_base))
 		return -EINVAL;
-- 
cgit v1.2.3


From 4e1a720d0312fd510699032c7694a362a010170f Mon Sep 17 00:00:00 2001
From: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Date: Sun, 15 Jul 2018 20:36:50 +0100
Subject: Bluetooth: avoid killing an already killed socket

slub debug reported:

[  440.648642] =============================================================================
[  440.648649] BUG kmalloc-1024 (Tainted: G    BU     O   ): Poison overwritten
[  440.648651] -----------------------------------------------------------------------------

[  440.648655] INFO: 0xe70f4bec-0xe70f4bec. First byte 0x6a instead of 0x6b
[  440.648665] INFO: Allocated in sk_prot_alloc+0x6b/0xc6 age=33155 cpu=1 pid=1047
[  440.648671] 	___slab_alloc.constprop.24+0x1fc/0x292
[  440.648675] 	__slab_alloc.isra.18.constprop.23+0x1c/0x25
[  440.648677] 	__kmalloc+0xb6/0x17f
[  440.648680] 	sk_prot_alloc+0x6b/0xc6
[  440.648683] 	sk_alloc+0x1e/0xa1
[  440.648700] 	sco_sock_alloc.constprop.6+0x26/0xaf [bluetooth]
[  440.648716] 	sco_connect_cfm+0x166/0x281 [bluetooth]
[  440.648731] 	hci_conn_request_evt.isra.53+0x258/0x281 [bluetooth]
[  440.648746] 	hci_event_packet+0x28b/0x2326 [bluetooth]
[  440.648759] 	hci_rx_work+0x161/0x291 [bluetooth]
[  440.648764] 	process_one_work+0x163/0x2b2
[  440.648767] 	worker_thread+0x1a9/0x25c
[  440.648770] 	kthread+0xf8/0xfd
[  440.648774] 	ret_from_fork+0x2e/0x38
[  440.648779] INFO: Freed in __sk_destruct+0xd3/0xdf age=3815 cpu=1 pid=1047
[  440.648782] 	__slab_free+0x4b/0x27a
[  440.648784] 	kfree+0x12e/0x155
[  440.648787] 	__sk_destruct+0xd3/0xdf
[  440.648790] 	sk_destruct+0x27/0x29
[  440.648793] 	__sk_free+0x75/0x91
[  440.648795] 	sk_free+0x1c/0x1e
[  440.648810] 	sco_sock_kill+0x5a/0x5f [bluetooth]
[  440.648825] 	sco_conn_del+0x8e/0xba [bluetooth]
[  440.648840] 	sco_disconn_cfm+0x3a/0x41 [bluetooth]
[  440.648855] 	hci_event_packet+0x45e/0x2326 [bluetooth]
[  440.648868] 	hci_rx_work+0x161/0x291 [bluetooth]
[  440.648872] 	process_one_work+0x163/0x2b2
[  440.648875] 	worker_thread+0x1a9/0x25c
[  440.648877] 	kthread+0xf8/0xfd
[  440.648880] 	ret_from_fork+0x2e/0x38
[  440.648884] INFO: Slab 0xf4718580 objects=27 used=27 fp=0x  (null) flags=0x40008100
[  440.648886] INFO: Object 0xe70f4b88 @offset=19336 fp=0xe70f54f8

When KASAN was enabled, it reported:

[  210.096613] ==================================================================
[  210.096634] BUG: KASAN: use-after-free in ex_handler_refcount+0x5b/0x127
[  210.096641] Write of size 4 at addr ffff880107e17160 by task kworker/u9:1/2040

[  210.096651] CPU: 1 PID: 2040 Comm: kworker/u9:1 Tainted: G     U     O    4.14.47-20180606+ #2
[  210.096654] Hardware name: , BIOS 2017.01-00087-g43e04de 08/30/2017
[  210.096693] Workqueue: hci0 hci_rx_work [bluetooth]
[  210.096698] Call Trace:
[  210.096711]  dump_stack+0x46/0x59
[  210.096722]  print_address_description+0x6b/0x23b
[  210.096729]  ? ex_handler_refcount+0x5b/0x127
[  210.096736]  kasan_report+0x220/0x246
[  210.096744]  ex_handler_refcount+0x5b/0x127
[  210.096751]  ? ex_handler_clear_fs+0x85/0x85
[  210.096757]  fixup_exception+0x8c/0x96
[  210.096766]  do_trap+0x66/0x2c1
[  210.096773]  do_error_trap+0x152/0x180
[  210.096781]  ? fixup_bug+0x78/0x78
[  210.096817]  ? hci_debugfs_create_conn+0x244/0x26a [bluetooth]
[  210.096824]  ? __schedule+0x113b/0x1453
[  210.096830]  ? sysctl_net_exit+0xe/0xe
[  210.096837]  ? __wake_up_common+0x343/0x343
[  210.096843]  ? insert_work+0x107/0x163
[  210.096850]  invalid_op+0x1b/0x40
[  210.096888] RIP: 0010:hci_debugfs_create_conn+0x244/0x26a [bluetooth]
[  210.096892] RSP: 0018:ffff880094a0f970 EFLAGS: 00010296
[  210.096898] RAX: 0000000000000000 RBX: ffff880107e170e8 RCX: ffff880107e17160
[  210.096902] RDX: 000000000000002f RSI: ffff88013b80ed40 RDI: ffffffffa058b940
[  210.096906] RBP: ffff88011b2b0578 R08: 00000000852f0ec9 R09: ffffffff81cfcf9b
[  210.096909] R10: 00000000d21bdad7 R11: 0000000000000001 R12: ffff8800967b0488
[  210.096913] R13: ffff880107e17168 R14: 0000000000000068 R15: ffff8800949c0008
[  210.096920]  ? __sk_destruct+0x2c6/0x2d4
[  210.096959]  hci_event_packet+0xff5/0x7de2 [bluetooth]
[  210.096969]  ? __local_bh_enable_ip+0x43/0x5b
[  210.097004]  ? l2cap_sock_recv_cb+0x158/0x166 [bluetooth]
[  210.097039]  ? hci_le_meta_evt+0x2bb3/0x2bb3 [bluetooth]
[  210.097075]  ? l2cap_ertm_init+0x94e/0x94e [bluetooth]
[  210.097093]  ? xhci_urb_enqueue+0xbd8/0xcf5 [xhci_hcd]
[  210.097102]  ? __accumulate_pelt_segments+0x24/0x33
[  210.097109]  ? __accumulate_pelt_segments+0x24/0x33
[  210.097115]  ? __update_load_avg_se.isra.2+0x217/0x3a4
[  210.097122]  ? set_next_entity+0x7c3/0x12cd
[  210.097128]  ? pick_next_entity+0x25e/0x26c
[  210.097135]  ? pick_next_task_fair+0x2ca/0xc1a
[  210.097141]  ? switch_mm_irqs_off+0x346/0xb4f
[  210.097147]  ? __switch_to+0x769/0xbc4
[  210.097153]  ? compat_start_thread+0x66/0x66
[  210.097188]  ? hci_conn_check_link_mode+0x1cd/0x1cd [bluetooth]
[  210.097195]  ? finish_task_switch+0x392/0x431
[  210.097228]  ? hci_rx_work+0x154/0x487 [bluetooth]
[  210.097260]  hci_rx_work+0x154/0x487 [bluetooth]
[  210.097269]  process_one_work+0x579/0x9e9
[  210.097277]  worker_thread+0x68f/0x804
[  210.097285]  kthread+0x31c/0x32b
[  210.097292]  ? rescuer_thread+0x70c/0x70c
[  210.097299]  ? kthread_create_on_node+0xa3/0xa3
[  210.097306]  ret_from_fork+0x35/0x40

[  210.097314] Allocated by task 2040:
[  210.097323]  kasan_kmalloc.part.1+0x51/0xc7
[  210.097328]  __kmalloc+0x17f/0x1b6
[  210.097335]  sk_prot_alloc+0xf2/0x1a3
[  210.097340]  sk_alloc+0x22/0x297
[  210.097375]  sco_sock_alloc.constprop.7+0x23/0x202 [bluetooth]
[  210.097410]  sco_connect_cfm+0x2d0/0x566 [bluetooth]
[  210.097443]  hci_conn_request_evt.isra.53+0x6d3/0x762 [bluetooth]
[  210.097476]  hci_event_packet+0x85e/0x7de2 [bluetooth]
[  210.097507]  hci_rx_work+0x154/0x487 [bluetooth]
[  210.097512]  process_one_work+0x579/0x9e9
[  210.097517]  worker_thread+0x68f/0x804
[  210.097523]  kthread+0x31c/0x32b
[  210.097529]  ret_from_fork+0x35/0x40

[  210.097533] Freed by task 2040:
[  210.097539]  kasan_slab_free+0xb3/0x15e
[  210.097544]  kfree+0x103/0x1a9
[  210.097549]  __sk_destruct+0x2c6/0x2d4
[  210.097584]  sco_conn_del.isra.1+0xba/0x10e [bluetooth]
[  210.097617]  hci_event_packet+0xff5/0x7de2 [bluetooth]
[  210.097648]  hci_rx_work+0x154/0x487 [bluetooth]
[  210.097653]  process_one_work+0x579/0x9e9
[  210.097658]  worker_thread+0x68f/0x804
[  210.097663]  kthread+0x31c/0x32b
[  210.097670]  ret_from_fork+0x35/0x40

[  210.097676] The buggy address belongs to the object at ffff880107e170e8
 which belongs to the cache kmalloc-1024 of size 1024
[  210.097681] The buggy address is located 120 bytes inside of
 1024-byte region [ffff880107e170e8, ffff880107e174e8)
[  210.097683] The buggy address belongs to the page:
[  210.097689] page:ffffea00041f8400 count:1 mapcount:0 mapping:          (null) index:0xffff880107e15b68 compound_mapcount: 0
[  210.110194] flags: 0x8000000000008100(slab|head)
[  210.115441] raw: 8000000000008100 0000000000000000 ffff880107e15b68 0000000100170016
[  210.115448] raw: ffffea0004a47620 ffffea0004b48e20 ffff88013b80ed40 0000000000000000
[  210.115451] page dumped because: kasan: bad access detected

[  210.115454] Memory state around the buggy address:
[  210.115460]  ffff880107e17000: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
[  210.115465]  ffff880107e17080: fc fc fc fc fc fc fc fc fc fc fc fc fc fb fb fb
[  210.115469] >ffff880107e17100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  210.115472]                                                        ^
[  210.115477]  ffff880107e17180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  210.115481]  ffff880107e17200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
[  210.115483] ==================================================================

And finally when BT_DBG() and ftrace was enabled it showed:

       <...>-14979 [001] ....   186.104191: sco_sock_kill <-sco_sock_close
       <...>-14979 [001] ....   186.104191: sco_sock_kill <-sco_sock_release
       <...>-14979 [001] ....   186.104192: sco_sock_kill: sk ef0497a0 state 9
       <...>-14979 [001] ....   186.104193: bt_sock_unlink <-sco_sock_kill
kworker/u9:2-792   [001] ....   186.104246: sco_sock_kill <-sco_conn_del
kworker/u9:2-792   [001] ....   186.104248: sco_sock_kill: sk ef0497a0 state 9
kworker/u9:2-792   [001] ....   186.104249: bt_sock_unlink <-sco_sock_kill
kworker/u9:2-792   [001] ....   186.104250: sco_sock_destruct <-__sk_destruct
kworker/u9:2-792   [001] ....   186.104250: sco_sock_destruct: sk ef0497a0
kworker/u9:2-792   [001] ....   186.104860: hci_conn_del <-hci_event_packet
kworker/u9:2-792   [001] ....   186.104864: hci_conn_del: hci0 hcon ef0484c0 handle 266

Only in the failed case, sco_sock_kill() gets called with the same sock
pointer two times. Add a check for SOCK_DEAD to avoid continue killing
a socket which has already been killed.

Signed-off-by: Sudip Mukherjee <sudipm.mukherjee@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/sco.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 413b8ee49fec..8f0f9279eac9 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -393,7 +393,8 @@ static void sco_sock_cleanup_listen(struct sock *parent)
  */
 static void sco_sock_kill(struct sock *sk)
 {
-	if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket)
+	if (!sock_flag(sk, SOCK_ZAPPED) || sk->sk_socket ||
+	    sock_flag(sk, SOCK_DEAD))
 		return;
 
 	BT_DBG("sk %p state %d", sk, sk->sk_state);
-- 
cgit v1.2.3


From 880cb3cddd164128522146d1c087fbd1811ed0cc Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Sun, 27 May 2018 16:14:15 +0100
Subject: irqchip/gic-v3-its: Refactor LPI allocator

Our current LPI allocator relies on a bitmap, each bit representing
a chunk of 32 LPIs, meaning that each device gets allocated LPIs
in multiple of 32. It served us well so far, but new use cases now
require much more finer grain allocations, down the the individual
LPI.

Given the size of the IntID space (up to 32bit), it isn't practical
to continue using a bitmap, so let's use a different data structure
altogether.

We switch to a list, where each element represent a contiguous range
of LPIs. On allocation, we simply grab the first group big enough to
satisfy the allocation, and substract what we need from it. If the
group becomes empty, we just remove it. On freeing interrupts, we
insert a new group of interrupt in the list, sort it and fuse the
adjacent groups.

This makes freeing interrupt much more expensive than allocating
them (an unusual behaviour), but that's fine as long as we consider
that freeing interrupts is an extremely rare event.

We still allocate interrupts in blocks of 32 for the time being,
but subsequent patches will relax this.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its.c | 191 ++++++++++++++++++++++++++-------------
 1 file changed, 129 insertions(+), 62 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index d7842d312d3e..9084a7e5a4b2 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -23,6 +23,8 @@
 #include <linux/dma-iommu.h>
 #include <linux/interrupt.h>
 #include <linux/irqdomain.h>
+#include <linux/list.h>
+#include <linux/list_sort.h>
 #include <linux/log2.h>
 #include <linux/mm.h>
 #include <linux/msi.h>
@@ -1421,112 +1423,177 @@ static struct irq_chip its_irq_chip = {
 	.irq_set_vcpu_affinity	= its_irq_set_vcpu_affinity,
 };
 
+
 /*
  * How we allocate LPIs:
  *
- * The GIC has id_bits bits for interrupt identifiers. From there, we
- * must subtract 8192 which are reserved for SGIs/PPIs/SPIs. Then, as
- * we allocate LPIs by chunks of 32, we can shift the whole thing by 5
- * bits to the right.
+ * lpi_range_list contains ranges of LPIs that are to available to
+ * allocate from. To allocate LPIs, just pick the first range that
+ * fits the required allocation, and reduce it by the required
+ * amount. Once empty, remove the range from the list.
+ *
+ * To free a range of LPIs, add a free range to the list, sort it and
+ * merge the result if the new range happens to be adjacent to an
+ * already free block.
  *
- * This gives us (((1UL << id_bits) - 8192) >> 5) possible allocations.
+ * The consequence of the above is that allocation is cost is low, but
+ * freeing is expensive. We assumes that freeing rarely occurs.
+ */
+
+/*
+ * Compatibility defines until we fully refactor the allocator
  */
 #define IRQS_PER_CHUNK_SHIFT	5
 #define IRQS_PER_CHUNK		(1UL << IRQS_PER_CHUNK_SHIFT)
 #define ITS_MAX_LPI_NRBITS	16 /* 64K LPIs */
 
-static unsigned long *lpi_bitmap;
-static u32 lpi_chunks;
-static DEFINE_SPINLOCK(lpi_lock);
+static DEFINE_MUTEX(lpi_range_lock);
+static LIST_HEAD(lpi_range_list);
 
-static int its_lpi_to_chunk(int lpi)
+struct lpi_range {
+	struct list_head	entry;
+	u32			base_id;
+	u32			span;
+};
+
+static struct lpi_range *mk_lpi_range(u32 base, u32 span)
 {
-	return (lpi - 8192) >> IRQS_PER_CHUNK_SHIFT;
+	struct lpi_range *range;
+
+	range = kzalloc(sizeof(*range), GFP_KERNEL);
+	if (range) {
+		INIT_LIST_HEAD(&range->entry);
+		range->base_id = base;
+		range->span = span;
+	}
+
+	return range;
 }
 
-static int its_chunk_to_lpi(int chunk)
+static int lpi_range_cmp(void *priv, struct list_head *a, struct list_head *b)
 {
-	return (chunk << IRQS_PER_CHUNK_SHIFT) + 8192;
+	struct lpi_range *ra, *rb;
+
+	ra = container_of(a, struct lpi_range, entry);
+	rb = container_of(b, struct lpi_range, entry);
+
+	return rb->base_id - ra->base_id;
 }
 
-static int __init its_lpi_init(u32 id_bits)
+static void merge_lpi_ranges(void)
 {
-	lpi_chunks = its_lpi_to_chunk(1UL << id_bits);
+	struct lpi_range *range, *tmp;
 
-	lpi_bitmap = kcalloc(BITS_TO_LONGS(lpi_chunks), sizeof(long),
-			     GFP_KERNEL);
-	if (!lpi_bitmap) {
-		lpi_chunks = 0;
-		return -ENOMEM;
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (!list_is_last(&range->entry, &lpi_range_list) &&
+		    (tmp->base_id == (range->base_id + range->span))) {
+			tmp->base_id = range->base_id;
+			tmp->span += range->span;
+			list_del(&range->entry);
+			kfree(range);
+		}
 	}
+}
 
-	pr_info("ITS: Allocated %d chunks for LPIs\n", (int)lpi_chunks);
-	return 0;
+static int alloc_lpi_range(u32 nr_lpis, u32 *base)
+{
+	struct lpi_range *range, *tmp;
+	int err = -ENOSPC;
+
+	mutex_lock(&lpi_range_lock);
+
+	list_for_each_entry_safe(range, tmp, &lpi_range_list, entry) {
+		if (range->span >= nr_lpis) {
+			*base = range->base_id;
+			range->base_id += nr_lpis;
+			range->span -= nr_lpis;
+
+			if (range->span == 0) {
+				list_del(&range->entry);
+				kfree(range);
+			}
+
+			err = 0;
+			break;
+		}
+	}
+
+	mutex_unlock(&lpi_range_lock);
+
+	pr_debug("ITS: alloc %u:%u\n", *base, nr_lpis);
+	return err;
 }
 
-static unsigned long *its_lpi_alloc_chunks(int nr_irqs, int *base, int *nr_ids)
+static int free_lpi_range(u32 base, u32 nr_lpis)
 {
-	unsigned long *bitmap = NULL;
-	int chunk_id;
-	int nr_chunks;
-	int i;
+	struct lpi_range *new;
+	int err = 0;
 
-	nr_chunks = DIV_ROUND_UP(nr_irqs, IRQS_PER_CHUNK);
+	mutex_lock(&lpi_range_lock);
 
-	spin_lock(&lpi_lock);
+	new = mk_lpi_range(base, nr_lpis);
+	if (!new) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	list_add(&new->entry, &lpi_range_list);
+	list_sort(NULL, &lpi_range_list, lpi_range_cmp);
+	merge_lpi_ranges();
+out:
+	mutex_unlock(&lpi_range_lock);
+	return err;
+}
+
+static int __init its_lpi_init(u32 id_bits)
+{
+	u32 lpis = (1UL << id_bits) - 8192;
+	int err;
+
+	/*
+	 * Initializing the allocator is just the same as freeing the
+	 * full range of LPIs.
+	 */
+	err = free_lpi_range(8192, lpis);
+	pr_debug("ITS: Allocator initialized for %u LPIs\n", lpis);
+	return err;
+}
+
+static unsigned long *its_lpi_alloc_chunks(int nr_irqs, u32 *base, int *nr_ids)
+{
+	unsigned long *bitmap = NULL;
+	int err = 0;
+	int nr_lpis;
+
+	nr_lpis = round_up(nr_irqs, IRQS_PER_CHUNK);
 
 	do {
-		chunk_id = bitmap_find_next_zero_area(lpi_bitmap, lpi_chunks,
-						      0, nr_chunks, 0);
-		if (chunk_id < lpi_chunks)
+		err = alloc_lpi_range(nr_lpis, base);
+		if (!err)
 			break;
 
-		nr_chunks--;
-	} while (nr_chunks > 0);
+		nr_lpis -= IRQS_PER_CHUNK;
+	} while (nr_lpis > 0);
 
-	if (!nr_chunks)
+	if (err)
 		goto out;
 
-	bitmap = kcalloc(BITS_TO_LONGS(nr_chunks * IRQS_PER_CHUNK),
-			 sizeof(long),
-			 GFP_ATOMIC);
+	bitmap = kcalloc(BITS_TO_LONGS(nr_lpis), sizeof (long), GFP_ATOMIC);
 	if (!bitmap)
 		goto out;
 
-	for (i = 0; i < nr_chunks; i++)
-		set_bit(chunk_id + i, lpi_bitmap);
-
-	*base = its_chunk_to_lpi(chunk_id);
-	*nr_ids = nr_chunks * IRQS_PER_CHUNK;
+	*nr_ids = nr_lpis;
 
 out:
-	spin_unlock(&lpi_lock);
-
 	if (!bitmap)
 		*base = *nr_ids = 0;
 
 	return bitmap;
 }
 
-static void its_lpi_free_chunks(unsigned long *bitmap, int base, int nr_ids)
+static void its_lpi_free_chunks(unsigned long *bitmap, u32 base, u32 nr_ids)
 {
-	int lpi;
-
-	spin_lock(&lpi_lock);
-
-	for (lpi = base; lpi < (base + nr_ids); lpi += IRQS_PER_CHUNK) {
-		int chunk = its_lpi_to_chunk(lpi);
-
-		BUG_ON(chunk > lpi_chunks);
-		if (test_bit(chunk, lpi_bitmap)) {
-			clear_bit(chunk, lpi_bitmap);
-		} else {
-			pr_err("Bad LPI chunk %d\n", chunk);
-		}
-	}
-
-	spin_unlock(&lpi_lock);
-
+	WARN_ON(free_lpi_range(base, nr_ids));
 	kfree(bitmap);
 }
 
-- 
cgit v1.2.3


From fe8e93504ce870cb60b5dca97d13d861a53d7353 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Sun, 27 May 2018 16:15:22 +0100
Subject: irqchip/gic-v3-its: Use full range of LPIs

As we used to represent the LPI range using a bitmap, we were reducing
the number of LPIs to at most 64k in order to preserve memory.

With our new allocator, there is no such need, as dealing with 2^16
or 2^32 LPIs takes the same amount of memory.

So let's use the number of IntID bits reported by the GIC instead of
an arbitrary limit.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 9084a7e5a4b2..20244006cd82 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1445,7 +1445,6 @@ static struct irq_chip its_irq_chip = {
  */
 #define IRQS_PER_CHUNK_SHIFT	5
 #define IRQS_PER_CHUNK		(1UL << IRQS_PER_CHUNK_SHIFT)
-#define ITS_MAX_LPI_NRBITS	16 /* 64K LPIs */
 
 static DEFINE_MUTEX(lpi_range_lock);
 static LIST_HEAD(lpi_range_list);
@@ -1626,7 +1625,7 @@ static int __init its_alloc_lpi_tables(void)
 {
 	phys_addr_t paddr;
 
-	lpi_id_bits = min_t(u32, gic_rdists->id_bits, ITS_MAX_LPI_NRBITS);
+	lpi_id_bits = gic_rdists->id_bits;
 	gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
 	if (!gic_rdists->prop_page) {
 		pr_err("Failed to allocate PROPBASE\n");
-- 
cgit v1.2.3


From 147c8f376e5526ebfaf2827734916414db52a3c4 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Sun, 27 May 2018 16:39:55 +0100
Subject: irqchip/gic-v3-its: Move minimum LPI requirements to individual
 busses

At the moment, the core ITS driver imposes the allocation to be
in chunks of 32. As we want to relax this on a per bus basis, let's
move the the the allocation constraints to each bus.

No functionnal change.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c   |  3 +++
 drivers/irqchip/irq-gic-v3-its-pci-msi.c      |  6 ++++--
 drivers/irqchip/irq-gic-v3-its-platform-msi.c |  2 ++
 drivers/irqchip/irq-gic-v3-its.c              | 11 +++++++----
 4 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
index 4eca5c763766..606efa64adff 100644
--- a/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-fsl-mc-msi.c
@@ -45,6 +45,9 @@ static int its_fsl_mc_msi_prepare(struct irq_domain *msi_domain,
 	 */
 	info->scratchpad[0].ul = mc_bus_dev->icid;
 	msi_info = msi_get_domain_info(msi_domain->parent);
+
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(msi_domain->parent, dev, nvec, info);
 }
 
diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index 25a98de5cfb2..75c3cafabc6a 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -86,8 +86,10 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
 
-	return msi_info->ops->msi_prepare(domain->parent,
-					  dev, max(nvec, alias_count), info);
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max(nvec, alias_count);
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
 }
 
 static struct msi_domain_ops its_pci_msi_ops = {
diff --git a/drivers/irqchip/irq-gic-v3-its-platform-msi.c b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
index 8881a053c173..7b8e87b493fe 100644
--- a/drivers/irqchip/irq-gic-v3-its-platform-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-platform-msi.c
@@ -73,6 +73,8 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = dev_id;
 
+	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(domain->parent,
 					  dev, nvec, info);
 }
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 20244006cd82..03ac8d05279d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -2200,12 +2200,15 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	if (!its_alloc_device_table(its, dev_id))
 		return NULL;
 
+	if (WARN_ON(!is_power_of_2(nvecs)))
+		nvecs = roundup_pow_of_two(nvecs);
+
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	/*
-	 * We allocate at least one chunk worth of LPIs bet device,
-	 * and thus that many ITEs. The device may require less though.
+	 * Even if the device wants a single LPI, the ITT must be
+	 * sized as a power of two (and you need at least one bit...).
 	 */
-	nr_ites = max(IRQS_PER_CHUNK, roundup_pow_of_two(nvecs));
+	nr_ites = max(2, nvecs);
 	sz = nr_ites * its->ite_size;
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc(sz, GFP_KERNEL);
@@ -2861,7 +2864,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 
 	BUG_ON(!vm);
 
-	bitmap = its_lpi_alloc_chunks(nr_irqs, &base, &nr_ids);
+	bitmap = its_lpi_alloc_chunks(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
 	if (!bitmap)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 38dd7c494cf604879e187e9b56690d25f876cf69 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Sun, 27 May 2018 17:03:03 +0100
Subject: irqchip/gic-v3-its: Drop chunk allocation compatibility

The chunk allocation system is now officially dead, so let's
remove it.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its.c | 41 ++++++++++++++++------------------------
 1 file changed, 16 insertions(+), 25 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 03ac8d05279d..9c5b85577053 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1440,12 +1440,6 @@ static struct irq_chip its_irq_chip = {
  * freeing is expensive. We assumes that freeing rarely occurs.
  */
 
-/*
- * Compatibility defines until we fully refactor the allocator
- */
-#define IRQS_PER_CHUNK_SHIFT	5
-#define IRQS_PER_CHUNK		(1UL << IRQS_PER_CHUNK_SHIFT)
-
 static DEFINE_MUTEX(lpi_range_lock);
 static LIST_HEAD(lpi_range_list);
 
@@ -1558,30 +1552,27 @@ static int __init its_lpi_init(u32 id_bits)
 	return err;
 }
 
-static unsigned long *its_lpi_alloc_chunks(int nr_irqs, u32 *base, int *nr_ids)
+static unsigned long *its_lpi_alloc(int nr_irqs, u32 *base, int *nr_ids)
 {
 	unsigned long *bitmap = NULL;
 	int err = 0;
-	int nr_lpis;
-
-	nr_lpis = round_up(nr_irqs, IRQS_PER_CHUNK);
 
 	do {
-		err = alloc_lpi_range(nr_lpis, base);
+		err = alloc_lpi_range(nr_irqs, base);
 		if (!err)
 			break;
 
-		nr_lpis -= IRQS_PER_CHUNK;
-	} while (nr_lpis > 0);
+		nr_irqs /= 2;
+	} while (nr_irqs > 0);
 
 	if (err)
 		goto out;
 
-	bitmap = kcalloc(BITS_TO_LONGS(nr_lpis), sizeof (long), GFP_ATOMIC);
+	bitmap = kcalloc(BITS_TO_LONGS(nr_irqs), sizeof (long), GFP_ATOMIC);
 	if (!bitmap)
 		goto out;
 
-	*nr_ids = nr_lpis;
+	*nr_ids = nr_irqs;
 
 out:
 	if (!bitmap)
@@ -1590,7 +1581,7 @@ out:
 	return bitmap;
 }
 
-static void its_lpi_free_chunks(unsigned long *bitmap, u32 base, u32 nr_ids)
+static void its_lpi_free(unsigned long *bitmap, u32 base, u32 nr_ids)
 {
 	WARN_ON(free_lpi_range(base, nr_ids));
 	kfree(bitmap);
@@ -2213,7 +2204,7 @@ static struct its_device *its_create_device(struct its_node *its, u32 dev_id,
 	sz = max(sz, ITS_ITT_ALIGN) + ITS_ITT_ALIGN - 1;
 	itt = kzalloc(sz, GFP_KERNEL);
 	if (alloc_lpis) {
-		lpi_map = its_lpi_alloc_chunks(nvecs, &lpi_base, &nr_lpis);
+		lpi_map = its_lpi_alloc(nvecs, &lpi_base, &nr_lpis);
 		if (lpi_map)
 			col_map = kcalloc(nr_lpis, sizeof(*col_map),
 					  GFP_KERNEL);
@@ -2448,9 +2439,9 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	/* If all interrupts have been freed, start mopping the floor */
 	if (bitmap_empty(its_dev->event_map.lpi_map,
 			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free_chunks(its_dev->event_map.lpi_map,
-				    its_dev->event_map.lpi_base,
-				    its_dev->event_map.nr_lpis);
+		its_lpi_free(its_dev->event_map.lpi_map,
+			     its_dev->event_map.lpi_base,
+			     its_dev->event_map.nr_lpis);
 		kfree(its_dev->event_map.col_map);
 
 		/* Unmap device/itt */
@@ -2849,7 +2840,7 @@ static void its_vpe_irq_domain_free(struct irq_domain *domain,
 	}
 
 	if (bitmap_empty(vm->db_bitmap, vm->nr_db_lpis)) {
-		its_lpi_free_chunks(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
+		its_lpi_free(vm->db_bitmap, vm->db_lpi_base, vm->nr_db_lpis);
 		its_free_prop_table(vm->vprop_page);
 	}
 }
@@ -2864,18 +2855,18 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 
 	BUG_ON(!vm);
 
-	bitmap = its_lpi_alloc_chunks(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
+	bitmap = its_lpi_alloc(roundup_pow_of_two(nr_irqs), &base, &nr_ids);
 	if (!bitmap)
 		return -ENOMEM;
 
 	if (nr_ids < nr_irqs) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
 	vprop_page = its_allocate_prop_table(GFP_KERNEL);
 	if (!vprop_page) {
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		return -ENOMEM;
 	}
 
@@ -2902,7 +2893,7 @@ static int its_vpe_irq_domain_alloc(struct irq_domain *domain, unsigned int virq
 		if (i > 0)
 			its_vpe_irq_domain_free(domain, virq, i - 1);
 
-		its_lpi_free_chunks(bitmap, base, nr_ids);
+		its_lpi_free(bitmap, base, nr_ids);
 		its_free_prop_table(vprop_page);
 	}
 
-- 
cgit v1.2.3


From a4f9edb29d9c19f9f8dcd2df7ddfe4eb7ad58996 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Wed, 30 May 2018 17:29:52 +0100
Subject: irqchip/gic-v3: Expose GICD_TYPER in the rdist structure

Instead of exposing the GIC distributor IntID field in the rdist
structure that is passed to the ITS, let's replace it with a
copy of the whole GICD_TYPER register. We are going to need
some of this information at a later time.

No functionnal change.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its.c   | 2 +-
 drivers/irqchip/irq-gic-v3.c       | 4 ++--
 include/linux/irqchip/arm-gic-v3.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 9c5b85577053..efe6d1a6c32e 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1616,7 +1616,7 @@ static int __init its_alloc_lpi_tables(void)
 {
 	phys_addr_t paddr;
 
-	lpi_id_bits = gic_rdists->id_bits;
+	lpi_id_bits = GICD_TYPER_ID_BITS(gic_rdists->gicd_typer);
 	gic_rdists->prop_page = its_allocate_prop_table(GFP_NOWAIT);
 	if (!gic_rdists->prop_page) {
 		pr_err("Failed to allocate PROPBASE\n");
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 76ea56d779a1..e214181b77b7 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -877,7 +877,7 @@ static struct irq_chip gic_eoimode1_chip = {
 	.flags			= IRQCHIP_SET_TYPE_MASKED,
 };
 
-#define GIC_ID_NR		(1U << gic_data.rdists.id_bits)
+#define GIC_ID_NR	(1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer))
 
 static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq,
 			      irq_hw_number_t hw)
@@ -1091,7 +1091,7 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)
 	 */
 	typer = readl_relaxed(gic_data.dist_base + GICD_TYPER);
-	gic_data.rdists.id_bits = GICD_TYPER_ID_BITS(typer);
+	gic_data.rdists.gicd_typer = typer;
 	gic_irqs = GICD_TYPER_IRQS(typer);
 	if (gic_irqs > 1020)
 		gic_irqs = 1020;
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index cbb872c1b607..396cd99af02f 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -576,8 +576,8 @@ struct rdists {
 		phys_addr_t	phys_base;
 	} __percpu		*rdist;
 	struct page		*prop_page;
-	int			id_bits;
 	u64			flags;
+	u32			gicd_typer;
 	bool			has_vlpis;
 	bool			has_direct_lpi;
 };
-- 
cgit v1.2.3


From 12b2905af183c931bedcab4292c81d3a415e080f Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Thu, 31 May 2018 09:01:59 +0100
Subject: irqchip/gic-v3-its: Honor hypervisor enforced LPI range

A recent extension to the GIC architecture allows a hypervisor to
arbitrarily reduce the number of LPIs available to a guest, no
matter what the GIC says about the valid range of IntIDs.

Let's factor in this information when computing the number of
available LPIs

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its.c   | 9 +++++++++
 include/linux/irqchip/arm-gic-v3.h | 1 +
 2 files changed, 10 insertions(+)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index efe6d1a6c32e..f56c84977241 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -1541,8 +1541,17 @@ out:
 static int __init its_lpi_init(u32 id_bits)
 {
 	u32 lpis = (1UL << id_bits) - 8192;
+	u32 numlpis;
 	int err;
 
+	numlpis = 1UL << GICD_TYPER_NUM_LPIS(gic_rdists->gicd_typer);
+
+	if (numlpis > 2 && !WARN_ON(numlpis > lpis)) {
+		lpis = numlpis;
+		pr_info("ITS: Using hypervisor restricted LPI range [%u]\n",
+			lpis);
+	}
+
 	/*
 	 * Initializing the allocator is just the same as freeing the
 	 * full range of LPIs.
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 396cd99af02f..9d2ea3e907d0 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -73,6 +73,7 @@
 #define GICD_TYPER_MBIS			(1U << 16)
 
 #define GICD_TYPER_ID_BITS(typer)	((((typer) >> 19) & 0x1f) + 1)
+#define GICD_TYPER_NUM_LPIS(typer)	((((typer) >> 11) & 0x1f) + 1)
 #define GICD_TYPER_IRQS(typer)		((((typer) & 0x1f) + 1) * 32)
 
 #define GICD_IROUTER_SPI_MODE_ONE	(0U << 31)
-- 
cgit v1.2.3


From e5332d5437764f775cf4e3b8ca3bf592af063a02 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <brgl@bgdev.pl>
Date: Mon, 16 Jul 2018 10:34:23 +0200
Subject: gpiolib: don't allow userspace to set values of input lines

User space can currently both read and set values of input lines using
the character device. This was not allowed by the old sysfs interface
nor is it a correct behavior.

Check the first descriptor in the set for the OUT flag when asked to
set values and return -EPERM if the line is input.

Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 2e2a6f8db405..c507cd3d01c0 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -449,7 +449,13 @@ static long linehandle_ioctl(struct file *filep, unsigned int cmd,
 
 		return 0;
 	} else if (cmd == GPIOHANDLE_SET_LINE_VALUES_IOCTL) {
-		/* TODO: check if descriptors are really output */
+		/*
+		 * All line descriptors were created at once with the same
+		 * flags so just check if the first one is really output.
+		 */
+		if (!test_bit(FLAG_IS_OUT, &lh->descs[0]->flags))
+			return -EPERM;
+
 		if (copy_from_user(&ghd, ip, sizeof(ghd)))
 			return -EFAULT;
 
-- 
cgit v1.2.3


From 2b955b34c268af57e3002ece9fd2da70d19b1d5b Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <brgl@bgdev.pl>
Date: Mon, 16 Jul 2018 10:34:24 +0200
Subject: gpiolib: remove an unnecessary TODO

It's actually fine to read values of output lines. This was also
allowed by the legacy sysfs interface.

Signed-off-by: Bartosz Golaszewski <brgl@bgdev.pl>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index c507cd3d01c0..464d5ba79f96 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -431,7 +431,7 @@ static long linehandle_ioctl(struct file *filep, unsigned int cmd,
 	int i;
 
 	if (cmd == GPIOHANDLE_GET_LINE_VALUES_IOCTL) {
-		/* TODO: check if descriptors are really input */
+		/* NOTE: It's ok to read values of output lines. */
 		int ret = gpiod_get_array_value_complex(false,
 							true,
 							lh->numdescs,
-- 
cgit v1.2.3


From d0ec2e9c10341001d648afdff0f42a22dafb044d Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Fri, 13 Jul 2018 17:46:38 +0800
Subject: dt-binding: pinctrl: berlin: document AS370 SoC pinctrl

Add as370 to existing berlin pinctrl device tree binding.

Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt
index f8fa28ce163e..0a2d5516e1f3 100644
--- a/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/berlin,pinctrl.txt
@@ -23,7 +23,8 @@ Required properties:
 	"marvell,berlin2q-system-pinctrl",
 	"marvell,berlin4ct-avio-pinctrl",
 	"marvell,berlin4ct-soc-pinctrl",
-	"marvell,berlin4ct-system-pinctrl"
+	"marvell,berlin4ct-system-pinctrl",
+	"syna,as370-soc-pinctrl"
 
 Required subnode-properties:
 - groups: a list of strings describing the group names.
-- 
cgit v1.2.3


From a09baa9543ef1ced2cc7c171a055712ec8af62a3 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Thu, 28 Jun 2018 13:33:35 +0200
Subject: s390/crypto: fix gcc 8 stringop-truncation warning

Replace strncpy which is used to deliberately avoid string NUL-termination
with memcpy. This allows to get rid of gcc 8 stringop-truncation warning:

    inlined from 'query_crypto_facility.constprop' at
    drivers/s390/crypto/pkey_api.c:702:2:
./include/linux/string.h:246:9: warning: '__builtin_strncpy' output
truncated before terminating nul copying 8 bytes from a string of the
same length [-Wstringop-truncation]

Reviewed-by: Harald Freudenberger <freude@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/crypto/pkey_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/crypto/pkey_api.c b/drivers/s390/crypto/pkey_api.c
index 3929c8be8098..e663432395c1 100644
--- a/drivers/s390/crypto/pkey_api.c
+++ b/drivers/s390/crypto/pkey_api.c
@@ -699,7 +699,7 @@ static int query_crypto_facility(u16 cardnr, u16 domain,
 	/* fill request cprb param block with FQ request */
 	preqparm = (struct fqreqparm *) preqcblk->req_parmb;
 	memcpy(preqparm->subfunc_code, "FQ", 2);
-	strncpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
+	memcpy(preqparm->rule_array, keyword, sizeof(preqparm->rule_array));
 	preqparm->rule_array_len =
 		sizeof(preqparm->rule_array_len) + sizeof(preqparm->rule_array);
 	preqparm->lv1.len = sizeof(preqparm->lv1);
-- 
cgit v1.2.3


From ac4c4fc87d6beb6dd8287f24670e5e81c24b1de7 Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Fri, 13 Jul 2018 08:13:13 +0200
Subject: s390/cmm: avoid add_timer on concurrently used timer

cmm_set_timer could be called concurrently from cmm_thread, cmm proc
handler, upon cmm smsg receive and timer function itself. To avoid
potential race condition and hitting BUG_ON in add_timer on already
pending timer simply reuse mod_timer which is according to
documentation "the only safe way to modify the timeout" with multiple
unserialized concurrent users. mod_timer can handle both active and
inactive timers which allows to carry out minor code simplification as
well.

Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/cmm.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/s390/mm/cmm.c b/arch/s390/mm/cmm.c
index 50d8d1c887a4..510a18299196 100644
--- a/arch/s390/mm/cmm.c
+++ b/arch/s390/mm/cmm.c
@@ -191,12 +191,7 @@ static void cmm_set_timer(void)
 			del_timer(&cmm_timer);
 		return;
 	}
-	if (timer_pending(&cmm_timer)) {
-		if (mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds*HZ))
-			return;
-	}
-	cmm_timer.expires = jiffies + cmm_timeout_seconds*HZ;
-	add_timer(&cmm_timer);
+	mod_timer(&cmm_timer, jiffies + cmm_timeout_seconds * HZ);
 }
 
 static void cmm_timer_fn(struct timer_list *unused)
-- 
cgit v1.2.3


From 306d6c49ac9ded11114cb53b0925da52f2c2ada1 Mon Sep 17 00:00:00 2001
From: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Date: Mon, 16 Jul 2018 10:38:57 +0200
Subject: s390/kvm: fix deadlock when killed by oom

When the oom killer kills a userspace process in the page fault handler
while in guest context, the fault handler fails to release the mm_sem
if the FAULT_FLAG_RETRY_NOWAIT option is set. This leads to a deadlock
when tearing down the mm when the process terminates. This bug can only
happen when pfault is enabled, so only KVM clients are affected.

The problem arises in the rare cases in which handle_mm_fault does not
release the mm_sem. This patch fixes the issue by manually releasing
the mm_sem when needed.

Fixes: 24eb3a824c4f3 ("KVM: s390: Add FAULT_FLAG_RETRY_NOWAIT for guest fault")
Cc: <stable@vger.kernel.org> # 3.15+
Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/fault.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
index e074480d3598..4cc3f06b0ab3 100644
--- a/arch/s390/mm/fault.c
+++ b/arch/s390/mm/fault.c
@@ -502,6 +502,8 @@ retry:
 	/* No reason to continue if interrupted by SIGKILL. */
 	if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
 		fault = VM_FAULT_SIGNAL;
+		if (flags & FAULT_FLAG_RETRY_NOWAIT)
+			goto out_up;
 		goto out;
 	}
 	if (unlikely(fault & VM_FAULT_ERROR))
-- 
cgit v1.2.3


From d30e23d69981a4b665f5ce8711335df986576389 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Sat, 14 Jul 2018 16:01:06 +0100
Subject: ASoC: hdmi-codec: fix routing

Commit 943fa0228252 ("ASoC: hdmi-codec: Use different name for playback
streams") broke hdmi-codec's routing between it's output "TX" widget
and the S/PDIF or I2S streams by renaming the streams.

Whether an error occurs or not is dependent on whether there is another
widget called "Playback" registered by some other component - if there
is, that widget will be (incorrectly) bound to the HDMI codec's "TX"
output widget.  If we end up connecting "TX" incorrectly, it can result
in components not being started, causing no audio output.

Since the I2S and S/PDIF streams now have different names, we can't
use a static route at component level to describe the relationship, so
arrange to dynamically create the route when the DAI driver is probed.

Fixes: 943fa0228252 ("ASoC: hdmi-codec: Use different name for playback streams")
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/hdmi-codec.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/sound/soc/codecs/hdmi-codec.c b/sound/soc/codecs/hdmi-codec.c
index 6fa11888672d..3e5b12de71bb 100644
--- a/sound/soc/codecs/hdmi-codec.c
+++ b/sound/soc/codecs/hdmi-codec.c
@@ -291,10 +291,6 @@ static const struct snd_soc_dapm_widget hdmi_widgets[] = {
 	SND_SOC_DAPM_OUTPUT("TX"),
 };
 
-static const struct snd_soc_dapm_route hdmi_routes[] = {
-	{ "TX", NULL, "Playback" },
-};
-
 enum {
 	DAI_ID_I2S = 0,
 	DAI_ID_SPDIF,
@@ -689,9 +685,23 @@ static int hdmi_codec_pcm_new(struct snd_soc_pcm_runtime *rtd,
 	return snd_ctl_add(rtd->card->snd_card, kctl);
 }
 
+static int hdmi_dai_probe(struct snd_soc_dai *dai)
+{
+	struct snd_soc_dapm_context *dapm;
+	struct snd_soc_dapm_route route = {
+		.sink = "TX",
+		.source = dai->driver->playback.stream_name,
+	};
+
+	dapm = snd_soc_component_get_dapm(dai->component);
+
+	return snd_soc_dapm_add_routes(dapm, &route, 1);
+}
+
 static const struct snd_soc_dai_driver hdmi_i2s_dai = {
 	.name = "i2s-hifi",
 	.id = DAI_ID_I2S,
+	.probe = hdmi_dai_probe,
 	.playback = {
 		.stream_name = "I2S Playback",
 		.channels_min = 2,
@@ -707,6 +717,7 @@ static const struct snd_soc_dai_driver hdmi_i2s_dai = {
 static const struct snd_soc_dai_driver hdmi_spdif_dai = {
 	.name = "spdif-hifi",
 	.id = DAI_ID_SPDIF,
+	.probe = hdmi_dai_probe,
 	.playback = {
 		.stream_name = "SPDIF Playback",
 		.channels_min = 2,
@@ -733,8 +744,6 @@ static int hdmi_of_xlate_dai_id(struct snd_soc_component *component,
 static const struct snd_soc_component_driver hdmi_driver = {
 	.dapm_widgets		= hdmi_widgets,
 	.num_dapm_widgets	= ARRAY_SIZE(hdmi_widgets),
-	.dapm_routes		= hdmi_routes,
-	.num_dapm_routes	= ARRAY_SIZE(hdmi_routes),
 	.of_xlate_dai_id	= hdmi_of_xlate_dai_id,
 	.idle_bias_on		= 1,
 	.use_pmdown_time	= 1,
-- 
cgit v1.2.3


From 8452112baac67c3235d15de67fb190d29bbba98f Mon Sep 17 00:00:00 2001
From: Naveen Manohar <naveen.m@intel.com>
Date: Wed, 11 Jul 2018 16:05:36 +0530
Subject: ASoC: Intel: Boards: Add GLK Realtek Maxim I2S machine driver

Patch adds Geminilake I2S machine driver which uses following codecs:
RT5682 and MAX98357A.

Signed-off-by: Naveen Manohar <naveen.m@intel.com>
Signed-off-by: Harsha Priya <harshapriya.n@intel.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/Kconfig                |  14 +
 sound/soc/intel/boards/Makefile               |   2 +
 sound/soc/intel/boards/glk_rt5682_max98357a.c | 643 ++++++++++++++++++++++++++
 3 files changed, 659 insertions(+)
 create mode 100644 sound/soc/intel/boards/glk_rt5682_max98357a.c

diff --git a/sound/soc/intel/boards/Kconfig b/sound/soc/intel/boards/Kconfig
index 24797482a3d2..cccda87f4b34 100644
--- a/sound/soc/intel/boards/Kconfig
+++ b/sound/soc/intel/boards/Kconfig
@@ -281,6 +281,20 @@ config SND_SOC_INTEL_KBL_DA7219_MAX98357A_MACH
 	  Say Y if you have such a device.
 	  If unsure select "N".
 
+config SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH
+	tristate "GLK with RT5682 and MAX98357A in I2S Mode"
+	depends on MFD_INTEL_LPSS && I2C && ACPI
+	select SND_SOC_RT5682
+	select SND_SOC_MAX98357A
+	select SND_SOC_DMIC
+	select SND_SOC_HDAC_HDMI
+	select SND_HDA_DSP_LOADER
+	help
+	   This adds support for ASoC machine driver for Geminilake platforms
+	   with RT5682 + MAX98357A I2S audio codec.
+	   Say Y if you have such a device.
+	   If unsure select "N".
+
 endif ## SND_SOC_INTEL_SKYLAKE
 
 endif ## SND_SOC_INTEL_MACH
diff --git a/sound/soc/intel/boards/Makefile b/sound/soc/intel/boards/Makefile
index 92b5507291af..87ef8b4058e5 100644
--- a/sound/soc/intel/boards/Makefile
+++ b/sound/soc/intel/boards/Makefile
@@ -6,6 +6,7 @@ snd-soc-sst-bdw-rt5677-mach-objs := bdw-rt5677.o
 snd-soc-sst-broadwell-objs := broadwell.o
 snd-soc-sst-bxt-da7219_max98357a-objs := bxt_da7219_max98357a.o
 snd-soc-sst-bxt-rt298-objs := bxt_rt298.o
+snd-soc-sst-glk-rt5682_max98357a-objs := glk_rt5682_max98357a.o
 snd-soc-sst-bytcr-rt5640-objs := bytcr_rt5640.o
 snd-soc-sst-bytcr-rt5651-objs := bytcr_rt5651.o
 snd-soc-sst-cht-bsw-rt5672-objs := cht_bsw_rt5672.o
@@ -27,6 +28,7 @@ obj-$(CONFIG_SND_SOC_INTEL_BYT_RT5640_MACH) += snd-soc-sst-byt-rt5640-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BYT_MAX98090_MACH) += snd-soc-sst-byt-max98090-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_DA7219_MAX98357A_MACH) += snd-soc-sst-bxt-da7219_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BXT_RT298_MACH) += snd-soc-sst-bxt-rt298.o
+obj-$(CONFIG_SND_SOC_INTEL_GLK_RT5682_MAX98357A_MACH) += snd-soc-sst-glk-rt5682_max98357a.o
 obj-$(CONFIG_SND_SOC_INTEL_BROADWELL_MACH) += snd-soc-sst-broadwell.o
 obj-$(CONFIG_SND_SOC_INTEL_BDW_RT5677_MACH) += snd-soc-sst-bdw-rt5677-mach.o
 obj-$(CONFIG_SND_SOC_INTEL_BYTCR_RT5640_MACH) += snd-soc-sst-bytcr-rt5640.o
diff --git a/sound/soc/intel/boards/glk_rt5682_max98357a.c b/sound/soc/intel/boards/glk_rt5682_max98357a.c
new file mode 100644
index 000000000000..c4b94e2617c5
--- /dev/null
+++ b/sound/soc/intel/boards/glk_rt5682_max98357a.c
@@ -0,0 +1,643 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright(c) 2018 Intel Corporation.
+
+/*
+ * Intel Geminilake I2S Machine Driver with MAX98357A & RT5682 Codecs
+ *
+ * Modified from:
+ *   Intel Apollolake I2S Machine driver
+ */
+
+#include <linux/input.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <sound/core.h>
+#include <sound/jack.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include "../skylake/skl.h"
+#include "../../codecs/rt5682.h"
+#include "../../codecs/hdac_hdmi.h"
+
+/* The platform clock outputs 19.2Mhz clock to codec as I2S MCLK */
+#define GLK_PLAT_CLK_FREQ 19200000
+#define RT5682_PLL_FREQ (48000 * 512)
+#define GLK_REALTEK_CODEC_DAI "rt5682-aif1"
+#define GLK_MAXIM_CODEC_DAI "HiFi"
+#define MAXIM_DEV0_NAME "MX98357A:00"
+#define DUAL_CHANNEL 2
+#define QUAD_CHANNEL 4
+#define NAME_SIZE 32
+
+static struct snd_soc_jack geminilake_hdmi[3];
+
+struct glk_hdmi_pcm {
+	struct list_head head;
+	struct snd_soc_dai *codec_dai;
+	int device;
+};
+
+struct glk_card_private {
+	struct snd_soc_jack geminilake_headset;
+	struct list_head hdmi_pcm_list;
+};
+
+enum {
+	GLK_DPCM_AUDIO_PB = 0,
+	GLK_DPCM_AUDIO_CP,
+	GLK_DPCM_AUDIO_HS_PB,
+	GLK_DPCM_AUDIO_ECHO_REF_CP,
+	GLK_DPCM_AUDIO_REF_CP,
+	GLK_DPCM_AUDIO_DMIC_CP,
+	GLK_DPCM_AUDIO_HDMI1_PB,
+	GLK_DPCM_AUDIO_HDMI2_PB,
+	GLK_DPCM_AUDIO_HDMI3_PB,
+};
+
+static int platform_clock_control(struct snd_soc_dapm_widget *w,
+					struct snd_kcontrol *k, int  event)
+{
+	struct snd_soc_dapm_context *dapm = w->dapm;
+	struct snd_soc_card *card = dapm->card;
+	struct snd_soc_dai *codec_dai;
+	int ret = 0;
+
+	codec_dai = snd_soc_card_get_codec_dai(card, GLK_REALTEK_CODEC_DAI);
+	if (!codec_dai) {
+		dev_err(card->dev, "Codec dai not found; Unable to set/unset codec pll\n");
+		return -EIO;
+	}
+
+	if (SND_SOC_DAPM_EVENT_OFF(event)) {
+		ret = snd_soc_dai_set_sysclk(codec_dai, 0, 0, 0);
+		if (ret)
+			dev_err(card->dev, "failed to stop sysclk: %d\n", ret);
+	} else if (SND_SOC_DAPM_EVENT_ON(event)) {
+		ret = snd_soc_dai_set_pll(codec_dai, 0, RT5682_PLL1_S_MCLK,
+					GLK_PLAT_CLK_FREQ, RT5682_PLL_FREQ);
+		if (ret < 0) {
+			dev_err(card->dev, "can't set codec pll: %d\n", ret);
+			return ret;
+		}
+	}
+
+	if (ret)
+		dev_err(card->dev, "failed to start internal clk: %d\n", ret);
+
+	return ret;
+}
+
+static const struct snd_kcontrol_new geminilake_controls[] = {
+	SOC_DAPM_PIN_SWITCH("Headphone Jack"),
+	SOC_DAPM_PIN_SWITCH("Headset Mic"),
+	SOC_DAPM_PIN_SWITCH("Spk"),
+};
+
+static const struct snd_soc_dapm_widget geminilake_widgets[] = {
+	SND_SOC_DAPM_HP("Headphone Jack", NULL),
+	SND_SOC_DAPM_MIC("Headset Mic", NULL),
+	SND_SOC_DAPM_SPK("Spk", NULL),
+	SND_SOC_DAPM_MIC("SoC DMIC", NULL),
+	SND_SOC_DAPM_SPK("HDMI1", NULL),
+	SND_SOC_DAPM_SPK("HDMI2", NULL),
+	SND_SOC_DAPM_SPK("HDMI3", NULL),
+	SND_SOC_DAPM_SUPPLY("Platform Clock", SND_SOC_NOPM, 0, 0,
+			platform_clock_control, SND_SOC_DAPM_PRE_PMU |
+			SND_SOC_DAPM_POST_PMD),
+};
+
+static const struct snd_soc_dapm_route geminilake_map[] = {
+	/* HP jack connectors - unknown if we have jack detection */
+	{ "Headphone Jack", NULL, "Platform Clock" },
+	{ "Headphone Jack", NULL, "HPOL" },
+	{ "Headphone Jack", NULL, "HPOR" },
+
+	/* speaker */
+	{ "Spk", NULL, "Speaker" },
+
+	/* other jacks */
+	{ "Headset Mic", NULL, "Platform Clock" },
+	{ "IN1P", NULL, "Headset Mic" },
+
+	/* digital mics */
+	{ "DMic", NULL, "SoC DMIC" },
+
+	/* CODEC BE connections */
+	{ "HiFi Playback", NULL, "ssp1 Tx" },
+	{ "ssp1 Tx", NULL, "codec0_out" },
+
+	{ "AIF1 Playback", NULL, "ssp2 Tx" },
+	{ "ssp2 Tx", NULL, "codec1_out" },
+
+	{ "codec0_in", NULL, "ssp2 Rx" },
+	{ "ssp2 Rx", NULL, "AIF1 Capture" },
+
+	{ "HDMI1", NULL, "hif5-0 Output" },
+	{ "HDMI2", NULL, "hif6-0 Output" },
+	{ "HDMI2", NULL, "hif7-0 Output" },
+
+	{ "hifi3", NULL, "iDisp3 Tx" },
+	{ "iDisp3 Tx", NULL, "iDisp3_out" },
+	{ "hifi2", NULL, "iDisp2 Tx" },
+	{ "iDisp2 Tx", NULL, "iDisp2_out" },
+	{ "hifi1", NULL, "iDisp1 Tx" },
+	{ "iDisp1 Tx", NULL, "iDisp1_out" },
+
+	/* DMIC */
+	{ "dmic01_hifi", NULL, "DMIC01 Rx" },
+	{ "DMIC01 Rx", NULL, "DMIC AIF" },
+};
+
+static int geminilake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
+			struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *rate = hw_param_interval(params,
+			SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *channels = hw_param_interval(params,
+			SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+
+	/* The ADSP will convert the FE rate to 48k, stereo */
+	rate->min = rate->max = 48000;
+	channels->min = channels->max = DUAL_CHANNEL;
+
+	/* set SSP to 24 bit */
+	snd_mask_none(fmt);
+	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+
+	return 0;
+}
+
+static int geminilake_rt5682_codec_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct glk_card_private *ctx = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_component *component = rtd->codec_dai->component;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	struct snd_soc_jack *jack;
+	int ret;
+
+	/* Configure sysclk for codec */
+	ret = snd_soc_dai_set_sysclk(codec_dai, RT5682_SCLK_S_PLL1,
+					RT5682_PLL_FREQ, SND_SOC_CLOCK_IN);
+	if (ret < 0)
+		dev_err(rtd->dev, "snd_soc_dai_set_sysclk err = %d\n", ret);
+
+	/*
+	 * Headset buttons map to the google Reference headset.
+	 * These can be configured by userspace.
+	 */
+	ret = snd_soc_card_jack_new(rtd->card, "Headset Jack",
+			SND_JACK_HEADSET | SND_JACK_BTN_0 | SND_JACK_BTN_1 |
+			SND_JACK_BTN_2 | SND_JACK_BTN_3 | SND_JACK_LINEOUT,
+			&ctx->geminilake_headset, NULL, 0);
+	if (ret) {
+		dev_err(rtd->dev, "Headset Jack creation failed: %d\n", ret);
+		return ret;
+	}
+
+	jack = &ctx->geminilake_headset;
+
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_1, KEY_VOLUMEUP);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEDOWN);
+	snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOICECOMMAND);
+	ret = snd_soc_component_set_jack(component, jack, NULL);
+
+	if (ret) {
+		dev_err(rtd->dev, "Headset Jack call-back failed: %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+};
+
+static int geminilake_rt5682_hw_params(struct snd_pcm_substream *substream,
+	struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *codec_dai = rtd->codec_dai;
+	int ret;
+
+	/* Set valid bitmask & configuration for I2S in 24 bit */
+	ret = snd_soc_dai_set_tdm_slot(codec_dai, 0x0, 0x0, 2, 24);
+	if (ret < 0) {
+		dev_err(rtd->dev, "set TDM slot err:%d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static struct snd_soc_ops geminilake_rt5682_ops = {
+	.hw_params = geminilake_rt5682_hw_params,
+};
+
+static int geminilake_hdmi_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct glk_card_private *ctx = snd_soc_card_get_drvdata(rtd->card);
+	struct snd_soc_dai *dai = rtd->codec_dai;
+	struct glk_hdmi_pcm *pcm;
+
+	pcm = devm_kzalloc(rtd->card->dev, sizeof(*pcm), GFP_KERNEL);
+	if (!pcm)
+		return -ENOMEM;
+
+	pcm->device = GLK_DPCM_AUDIO_HDMI1_PB + dai->id;
+	pcm->codec_dai = dai;
+
+	list_add_tail(&pcm->head, &ctx->hdmi_pcm_list);
+
+	return 0;
+}
+
+static int geminilake_rt5682_fe_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct snd_soc_component *component = rtd->cpu_dai->component;
+	struct snd_soc_dapm_context *dapm;
+	int ret;
+
+	dapm = snd_soc_component_get_dapm(component);
+	ret = snd_soc_dapm_ignore_suspend(dapm, "Reference Capture");
+	if (ret) {
+		dev_err(rtd->dev, "Ref Cap ignore suspend failed %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static const unsigned int rates[] = {
+	48000,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_rates = {
+	.count = ARRAY_SIZE(rates),
+	.list  = rates,
+	.mask = 0,
+};
+
+static const unsigned int channels[] = {
+	DUAL_CHANNEL,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_channels = {
+	.count = ARRAY_SIZE(channels),
+	.list = channels,
+	.mask = 0,
+};
+
+static unsigned int channels_quad[] = {
+	QUAD_CHANNEL,
+};
+
+static struct snd_pcm_hw_constraint_list constraints_channels_quad = {
+	.count = ARRAY_SIZE(channels_quad),
+	.list = channels_quad,
+	.mask = 0,
+};
+
+static int geminilake_dmic_fixup(struct snd_soc_pcm_runtime *rtd,
+		struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *channels = hw_param_interval(params,
+				SNDRV_PCM_HW_PARAM_CHANNELS);
+
+	/*
+	 * set BE channel constraint as user FE channels
+	 */
+	channels->min = channels->max = 4;
+
+	return 0;
+}
+
+static int geminilake_dmic_startup(struct snd_pcm_substream *substream)
+{
+	struct snd_pcm_runtime *runtime = substream->runtime;
+
+	runtime->hw.channels_min = runtime->hw.channels_max = QUAD_CHANNEL;
+	snd_pcm_hw_constraint_list(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
+			&constraints_channels_quad);
+
+	return snd_pcm_hw_constraint_list(substream->runtime, 0,
+			SNDRV_PCM_HW_PARAM_RATE, &constraints_rates);
+}
+
+static const struct snd_soc_ops geminilake_dmic_ops = {
+	.startup = geminilake_dmic_startup,
+};
+
+static const unsigned int rates_16000[] = {
+	16000,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_16000 = {
+	.count = ARRAY_SIZE(rates_16000),
+	.list  = rates_16000,
+};
+
+static int geminilake_refcap_startup(struct snd_pcm_substream *substream)
+{
+	return snd_pcm_hw_constraint_list(substream->runtime, 0,
+				SNDRV_PCM_HW_PARAM_RATE,
+				&constraints_16000);
+};
+
+static const struct snd_soc_ops geminilake_refcap_ops = {
+	.startup = geminilake_refcap_startup,
+};
+
+/* geminilake digital audio interface glue - connects codec <--> CPU */
+static struct snd_soc_dai_link geminilake_dais[] = {
+	/* Front End DAI links */
+	[GLK_DPCM_AUDIO_PB] = {
+		.name = "Glk Audio Port",
+		.stream_name = "Audio",
+		.cpu_dai_name = "System Pin",
+		.platform_name = "0000:00:0e.0",
+		.dynamic = 1,
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.nonatomic = 1,
+		.init = geminilake_rt5682_fe_init,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_playback = 1,
+	},
+	[GLK_DPCM_AUDIO_CP] = {
+		.name = "Glk Audio Capture Port",
+		.stream_name = "Audio Record",
+		.cpu_dai_name = "System Pin",
+		.platform_name = "0000:00:0e.0",
+		.dynamic = 1,
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.nonatomic = 1,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_capture = 1,
+	},
+	[GLK_DPCM_AUDIO_HS_PB] = {
+		.name = "Glk Audio Headset Playback",
+		.stream_name = "Headset Audio",
+		.cpu_dai_name = "System Pin2",
+		.platform_name = "0000:00:0e.0",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.dpcm_playback = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[GLK_DPCM_AUDIO_ECHO_REF_CP] = {
+		.name = "Glk Audio Echo Reference cap",
+		.stream_name = "Echoreference Capture",
+		.cpu_dai_name = "Echoref Pin",
+		.platform_name = "0000:00:0e.0",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.init = NULL,
+		.capture_only = 1,
+		.nonatomic = 1,
+	},
+	[GLK_DPCM_AUDIO_REF_CP] = {
+		.name = "Glk Audio Reference cap",
+		.stream_name = "Refcap",
+		.cpu_dai_name = "Reference Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.init = NULL,
+		.dpcm_capture = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+		.ops = &geminilake_refcap_ops,
+	},
+	[GLK_DPCM_AUDIO_DMIC_CP] = {
+		.name = "Glk Audio DMIC cap",
+		.stream_name = "dmiccap",
+		.cpu_dai_name = "DMIC Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.init = NULL,
+		.dpcm_capture = 1,
+		.nonatomic = 1,
+		.dynamic = 1,
+		.ops = &geminilake_dmic_ops,
+	},
+	[GLK_DPCM_AUDIO_HDMI1_PB] = {
+		.name = "Glk HDMI Port1",
+		.stream_name = "Hdmi1",
+		.cpu_dai_name = "HDMI1 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.dpcm_playback = 1,
+		.init = NULL,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[GLK_DPCM_AUDIO_HDMI2_PB] =	{
+		.name = "Glk HDMI Port2",
+		.stream_name = "Hdmi2",
+		.cpu_dai_name = "HDMI2 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.dpcm_playback = 1,
+		.init = NULL,
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	[GLK_DPCM_AUDIO_HDMI3_PB] =	{
+		.name = "Glk HDMI Port3",
+		.stream_name = "Hdmi3",
+		.cpu_dai_name = "HDMI3 Pin",
+		.codec_name = "snd-soc-dummy",
+		.codec_dai_name = "snd-soc-dummy-dai",
+		.platform_name = "0000:00:0e.0",
+		.trigger = {
+			SND_SOC_DPCM_TRIGGER_POST, SND_SOC_DPCM_TRIGGER_POST},
+		.dpcm_playback = 1,
+		.init = NULL,
+		.nonatomic = 1,
+		.dynamic = 1,
+	},
+	/* Back End DAI links */
+	{
+		/* SSP1 - Codec */
+		.name = "SSP1-Codec",
+		.id = 0,
+		.cpu_dai_name = "SSP1 Pin",
+		.platform_name = "0000:00:0e.0",
+		.no_pcm = 1,
+		.codec_name = MAXIM_DEV0_NAME,
+		.codec_dai_name = GLK_MAXIM_CODEC_DAI,
+		.dai_fmt = SND_SOC_DAIFMT_I2S |
+			SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		.ignore_pmdown_time = 1,
+		.be_hw_params_fixup = geminilake_ssp_fixup,
+		.dpcm_playback = 1,
+	},
+	{
+		/* SSP2 - Codec */
+		.name = "SSP2-Codec",
+		.id = 1,
+		.cpu_dai_name = "SSP2 Pin",
+		.platform_name = "0000:00:0e.0",
+		.no_pcm = 1,
+		.codec_name = "i2c-10EC5682:00",
+		.codec_dai_name = GLK_REALTEK_CODEC_DAI,
+		.init = geminilake_rt5682_codec_init,
+		.dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF |
+			SND_SOC_DAIFMT_CBS_CFS,
+		.ignore_pmdown_time = 1,
+		.be_hw_params_fixup = geminilake_ssp_fixup,
+		.ops = &geminilake_rt5682_ops,
+		.dpcm_playback = 1,
+		.dpcm_capture = 1,
+	},
+	{
+		.name = "dmic01",
+		.id = 2,
+		.cpu_dai_name = "DMIC01 Pin",
+		.codec_name = "dmic-codec",
+		.codec_dai_name = "dmic-hifi",
+		.platform_name = "0000:00:0e.0",
+		.ignore_suspend = 1,
+		.be_hw_params_fixup = geminilake_dmic_fixup,
+		.dpcm_capture = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp1",
+		.id = 3,
+		.cpu_dai_name = "iDisp1 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi1",
+		.platform_name = "0000:00:0e.0",
+		.init = geminilake_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp2",
+		.id = 4,
+		.cpu_dai_name = "iDisp2 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi2",
+		.platform_name = "0000:00:0e.0",
+		.init = geminilake_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+	{
+		.name = "iDisp3",
+		.id = 5,
+		.cpu_dai_name = "iDisp3 Pin",
+		.codec_name = "ehdaudio0D2",
+		.codec_dai_name = "intel-hdmi-hifi3",
+		.platform_name = "0000:00:0e.0",
+		.init = geminilake_hdmi_init,
+		.dpcm_playback = 1,
+		.no_pcm = 1,
+	},
+};
+
+static int glk_card_late_probe(struct snd_soc_card *card)
+{
+	struct glk_card_private *ctx = snd_soc_card_get_drvdata(card);
+	struct snd_soc_component *component = NULL;
+	char jack_name[NAME_SIZE];
+	struct glk_hdmi_pcm *pcm;
+	int err = 0;
+	int i = 0;
+
+	list_for_each_entry(pcm, &ctx->hdmi_pcm_list, head) {
+		component = pcm->codec_dai->component;
+		snprintf(jack_name, sizeof(jack_name),
+			"HDMI/DP, pcm=%d Jack", pcm->device);
+		err = snd_soc_card_jack_new(card, jack_name,
+					SND_JACK_AVOUT, &geminilake_hdmi[i],
+					NULL, 0);
+
+		if (err)
+			return err;
+
+		err = hdac_hdmi_jack_init(pcm->codec_dai, pcm->device,
+						&geminilake_hdmi[i]);
+		if (err < 0)
+			return err;
+
+		i++;
+	}
+
+	if (!component)
+		return -EINVAL;
+
+	return hdac_hdmi_jack_port_init(component, &card->dapm);
+}
+
+/* geminilake audio machine driver for SPT + RT5682 */
+static struct snd_soc_card glk_audio_card_rt5682_m98357a = {
+	.name = "glkrt5682max",
+	.owner = THIS_MODULE,
+	.dai_link = geminilake_dais,
+	.num_links = ARRAY_SIZE(geminilake_dais),
+	.controls = geminilake_controls,
+	.num_controls = ARRAY_SIZE(geminilake_controls),
+	.dapm_widgets = geminilake_widgets,
+	.num_dapm_widgets = ARRAY_SIZE(geminilake_widgets),
+	.dapm_routes = geminilake_map,
+	.num_dapm_routes = ARRAY_SIZE(geminilake_map),
+	.fully_routed = true,
+	.late_probe = glk_card_late_probe,
+};
+
+static int geminilake_audio_probe(struct platform_device *pdev)
+{
+	struct glk_card_private *ctx;
+
+	ctx = devm_kzalloc(&pdev->dev, sizeof(*ctx), GFP_ATOMIC);
+	if (!ctx)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&ctx->hdmi_pcm_list);
+
+	glk_audio_card_rt5682_m98357a.dev = &pdev->dev;
+	snd_soc_card_set_drvdata(&glk_audio_card_rt5682_m98357a, ctx);
+
+	return devm_snd_soc_register_card(&pdev->dev,
+					&glk_audio_card_rt5682_m98357a);
+}
+
+static const struct platform_device_id glk_board_ids[] = {
+	{
+		.name = "glk_rt5682_max98357a",
+		.driver_data =
+			(kernel_ulong_t)&glk_audio_card_rt5682_m98357a,
+	},
+	{ }
+};
+
+static struct platform_driver geminilake_audio = {
+	.probe = geminilake_audio_probe,
+	.driver = {
+		.name = "glk_rt5682_max98357a",
+		.pm = &snd_soc_pm_ops,
+	},
+	.id_table = glk_board_ids,
+};
+module_platform_driver(geminilake_audio)
+
+/* Module information */
+MODULE_DESCRIPTION("Geminilake Audio Machine driver-RT5682 & MAX98357A in I2S mode");
+MODULE_AUTHOR("Naveen Manohar <naveen.m@intel.com>");
+MODULE_AUTHOR("Harsha Priya <harshapriya.n@intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS("platform:glk_rt5682_max98357a");
-- 
cgit v1.2.3


From fa9d2f17c23fb3ea6b659b1bfe4ca10551a19e56 Mon Sep 17 00:00:00 2001
From: "Agrawal, Akshu" <Akshu.Agrawal@amd.com>
Date: Mon, 16 Jul 2018 15:02:40 +0800
Subject: ASoC: AMD: Send correct channel for configuring DMA descriptors

Earlier, ch1 was used to define ACP-SYSMEM transfer and ch2 for
ACP-I2S transfer. With recent patches ch1 is used to define channel
order number 1 and ch2 as channel order number 2. Thus,
Playback:
ch1:SYSMEM->ACP
ch2:ACP->I2S
Capture:
ch1:I2S->ACP
ch1:ACP->SYSMEM

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 26 ++++++++++++++++++++++----
 1 file changed, 22 insertions(+), 4 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 65c1033bd51c..eeb867767252 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -322,17 +322,27 @@ static void config_acp_dma(void __iomem *acp_mmio,
 			   struct audio_substream_data *rtd,
 			   u32 asic_type)
 {
+	u16 ch_acp_sysmem, ch_acp_i2s;
+
 	acp_pte_config(acp_mmio, rtd->pg, rtd->num_of_pages,
 		       rtd->pte_offset);
+
+	if (rtd->direction == SNDRV_PCM_STREAM_PLAYBACK) {
+		ch_acp_sysmem = rtd->ch1;
+		ch_acp_i2s = rtd->ch2;
+	} else {
+		ch_acp_i2s = rtd->ch1;
+		ch_acp_sysmem = rtd->ch2;
+	}
 	/* Configure System memory <-> ACP SRAM DMA descriptors */
 	set_acp_sysmem_dma_descriptors(acp_mmio, rtd->size,
 				       rtd->direction, rtd->pte_offset,
-				       rtd->ch1, rtd->sram_bank,
+				       ch_acp_sysmem, rtd->sram_bank,
 				       rtd->dma_dscr_idx_1, asic_type);
 	/* Configure ACP SRAM <-> I2S DMA descriptors */
 	set_acp_to_i2s_dma_descriptors(acp_mmio, rtd->size,
 				       rtd->direction, rtd->sram_bank,
-				       rtd->destination, rtd->ch2,
+				       rtd->destination, ch_acp_i2s,
 				       rtd->dma_dscr_idx_2, asic_type);
 }
 
@@ -995,16 +1005,24 @@ static int acp_dma_prepare(struct snd_pcm_substream *substream)
 {
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
+	u16 ch_acp_sysmem, ch_acp_i2s;
 
 	if (!rtd)
 		return -EINVAL;
 
+	if (rtd->direction == SNDRV_PCM_STREAM_PLAYBACK) {
+		ch_acp_sysmem = rtd->ch1;
+		ch_acp_i2s = rtd->ch2;
+	} else {
+		ch_acp_i2s = rtd->ch1;
+		ch_acp_sysmem = rtd->ch2;
+	}
 	config_acp_dma_channel(rtd->acp_mmio,
-			       rtd->ch1,
+			       ch_acp_sysmem,
 			       rtd->dma_dscr_idx_1,
 			       NUM_DSCRS_PER_CHANNEL, 0);
 	config_acp_dma_channel(rtd->acp_mmio,
-			       rtd->ch2,
+			       ch_acp_i2s,
 			       rtd->dma_dscr_idx_2,
 			       NUM_DSCRS_PER_CHANNEL, 0);
 	return 0;
-- 
cgit v1.2.3


From 19e023e3befb4cb64b4a81b47a92a0c687672661 Mon Sep 17 00:00:00 2001
From: "Agrawal, Akshu" <Akshu.Agrawal@amd.com>
Date: Mon, 16 Jul 2018 15:02:41 +0800
Subject: ASoC: AMD: For capture have interrupts on I2S->ACP channel

Having interrupts enabled for ACP<->SYSMEM DMA transfer, we are in
for an interrupt storm.
For both playback and capture interrupts should be enabled for
I2S<->ACP DMA.

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index eeb867767252..94bcf69008df 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -224,13 +224,11 @@ static void set_acp_sysmem_dma_descriptors(void __iomem *acp_mmio,
 			switch (asic_type) {
 			case CHIP_STONEY:
 				dmadscr[i].xfer_val |=
-				BIT(22) |
 				(ACP_DMA_ATTR_SHARED_MEM_TO_DAGB_GARLIC << 16) |
 				(size / 2);
 				break;
 			default:
 				dmadscr[i].xfer_val |=
-				BIT(22) |
 				(ACP_DMA_ATTR_SHAREDMEM_TO_DAGB_ONION << 16) |
 				(size / 2);
 			}
@@ -421,9 +419,9 @@ static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
 
 	switch (ch_num) {
 	case ACP_TO_I2S_DMA_CH_NUM:
-	case ACP_TO_SYSRAM_CH_NUM:
+	case I2S_TO_ACP_DMA_CH_NUM:
 	case ACP_TO_I2S_DMA_BT_INSTANCE_CH_NUM:
-	case ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM:
+	case I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM:
 		dma_ctrl |= ACP_DMA_CNTL_0__DMAChIOCEn_MASK;
 		break;
 	default:
@@ -705,18 +703,18 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) != 0) {
+	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
 		valid_irq = true;
 		snd_pcm_period_elapsed(irq_data->capture_i2ssp_stream);
-		acp_reg_write((intr_flag & BIT(ACP_TO_SYSRAM_CH_NUM)) << 16,
+		acp_reg_write((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-	if ((intr_flag & BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) != 0) {
+	if ((intr_flag & BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) != 0) {
 		valid_irq = true;
 		snd_pcm_period_elapsed(irq_data->capture_i2sbt_stream);
 		acp_reg_write((intr_flag &
-			      BIT(ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM)) << 16,
+			      BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
 	}
 
-- 
cgit v1.2.3


From c77e1ef1cdf74dba09edfa706fecc9fddd7bd084 Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Wed, 11 Jul 2018 13:37:51 +0100
Subject: ALSA: usb-audio: Add support for Selector Units in UAC3

This patch add support for Selector Units and Clock Selector Units
defined in the new UAC3 spec.

Selector Units play a really important role in the new UAC3 spec as
Processing Units do not define an on/off switch control anymore.
This forces topology designers to add bypass paths in the topology
to enable/dissable the Processing Units.

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer.c | 54 ++++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 44 insertions(+), 10 deletions(-)

diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index ca963e94ec03..a51f2320a3dd 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -940,6 +940,19 @@ static int check_input_term(struct mixer_build *state, int id,
 
 				return 0;
 			}
+			case UAC3_SELECTOR_UNIT:
+			case UAC3_CLOCK_SELECTOR: {
+				struct uac_selector_unit_descriptor *d = p1;
+				/* call recursively to retrieve the channel info */
+				err = check_input_term(state, d->baSourceID[0], term);
+				if (err < 0)
+					return err;
+				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->id = id;
+				term->name = 0; /* TODO: UAC3 Class-specific strings */
+
+				return 0;
+			}
 			default:
 				return -ENODEV;
 			}
@@ -2509,11 +2522,20 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 	cval->res = 1;
 	cval->initialized = 1;
 
-	if (state->mixer->protocol == UAC_VERSION_1)
+	switch (state->mixer->protocol) {
+	case UAC_VERSION_1:
+	default:
 		cval->control = 0;
-	else /* UAC_VERSION_2 */
-		cval->control = (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR) ?
-			UAC2_CX_CLOCK_SELECTOR : UAC2_SU_SELECTOR;
+		break;
+	case UAC_VERSION_2:
+	case UAC_VERSION_3:
+		if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR ||
+		    desc->bDescriptorSubtype == UAC3_CLOCK_SELECTOR)
+			cval->control = UAC2_CX_CLOCK_SELECTOR;
+		else /* UAC2/3_SELECTOR_UNIT */
+			cval->control = UAC2_SU_SELECTOR;
+		break;
+	}
 
 	namelist = kmalloc_array(desc->bNrInPins, sizeof(char *), GFP_KERNEL);
 	if (!namelist) {
@@ -2555,12 +2577,22 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 	len = check_mapped_name(map, kctl->id.name, sizeof(kctl->id.name));
 	if (!len) {
 		/* no mapping ? */
+		switch (state->mixer->protocol) {
+		case UAC_VERSION_1:
+		case UAC_VERSION_2:
+		default:
 		/* if iSelector is given, use it */
-		nameid = uac_selector_unit_iSelector(desc);
-		if (nameid)
-			len = snd_usb_copy_string_desc(state->chip, nameid,
-						       kctl->id.name,
-						       sizeof(kctl->id.name));
+			nameid = uac_selector_unit_iSelector(desc);
+			if (nameid)
+				len = snd_usb_copy_string_desc(state->chip,
+							nameid, kctl->id.name,
+							sizeof(kctl->id.name));
+			break;
+		case UAC_VERSION_3:
+			/* TODO: Class-Specific strings not yet supported */
+			break;
+		}
+
 		/* ... or pick up the terminal name at next */
 		if (!len)
 			len = get_term_name(state->chip, &state->oterm,
@@ -2570,7 +2602,8 @@ static int parse_audio_selector_unit(struct mixer_build *state, int unitid,
 			strlcpy(kctl->id.name, "USB", sizeof(kctl->id.name));
 
 		/* and add the proper suffix */
-		if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR)
+		if (desc->bDescriptorSubtype == UAC2_CLOCK_SELECTOR ||
+		    desc->bDescriptorSubtype == UAC3_CLOCK_SELECTOR)
 			append_ctl_name(kctl, " Clock Source");
 		else if ((state->oterm.type & 0xff00) == 0x0100)
 			append_ctl_name(kctl, " Capture Source");
@@ -2641,6 +2674,7 @@ static int parse_audio_unit(struct mixer_build *state, int unitid)
 			return parse_audio_mixer_unit(state, unitid, p1);
 		case UAC3_CLOCK_SOURCE:
 			return parse_clock_source_unit(state, unitid, p1);
+		case UAC3_SELECTOR_UNIT:
 		case UAC3_CLOCK_SELECTOR:
 			return parse_audio_selector_unit(state, unitid, p1);
 		case UAC3_FEATURE_UNIT:
-- 
cgit v1.2.3


From 4e887af31cedec0d3b24521a5c3c14c3a190422b Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Wed, 11 Jul 2018 13:37:52 +0100
Subject: ALSA: usb-audio: Processing Unit controls parsing in UAC2

Current support for UAC2 Processing Units does the parsing
as one control per bit in the bitmap. However, the UAC2 spec
defines the controls as bit pairs where b01 means read-only
and b11 means read/write control.

This patch fixes that and uses the helper functions for checking
controls readability/writability when the control is defined as
bit pairs (UAC2 and UAC3).

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index a51f2320a3dd..bfb3484096a6 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -2300,8 +2300,16 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 	for (valinfo = info->values; valinfo->control; valinfo++) {
 		__u8 *controls = uac_processing_unit_bmControls(desc, state->mixer->protocol);
 
-		if (!(controls[valinfo->control / 8] & (1 << ((valinfo->control % 8) - 1))))
-			continue;
+		if (state->mixer->protocol == UAC_VERSION_1) {
+			if (!(controls[valinfo->control / 8] &
+					(1 << ((valinfo->control % 8) - 1))))
+				continue;
+		} else { /* UAC_VERSION_2/3 */
+			if (!uac_v2v3_control_is_readable(controls[valinfo->control / 8],
+							  valinfo->control))
+				continue;
+		}
+
 		map = find_map(state->map, unitid, valinfo->control);
 		if (check_ignored_ctl(map))
 			continue;
@@ -2313,6 +2321,11 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 		cval->val_type = valinfo->val_type;
 		cval->channels = 1;
 
+		if (state->mixer->protocol > UAC_VERSION_1 &&
+		    !uac_v2v3_control_is_writeable(controls[valinfo->control / 8],
+						   valinfo->control))
+			cval->master_readonly = 1;
+
 		/* get min/max values */
 		if (type == UAC_PROCESS_UP_DOWNMIX && cval->control == UAC_UD_MODE_SELECT) {
 			__u8 *control_spec = uac_processing_unit_specific(desc, state->mixer->protocol);
-- 
cgit v1.2.3


From 0f292f023ffcc67ec49d63dcb7fe388711cbb83a Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Wed, 11 Jul 2018 13:37:53 +0100
Subject: ALSA: usb-audio: Add support for Processing Units in UAC3

This patch adds support for the Processig Units defined in
the UAC3 spec. The main difference with the previous specs
is the lack of on/off switches in the controls for these
units and the addiction of the new Multi Function Processing
Unit.

The current version of the UAC3 spec doesn't define any
useful controls for the new Multi Function Processing Unit
so no control will get created once this unit is parsed.

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/linux/usb/audio-v3.h   | 15 +++++++++++++
 include/uapi/linux/usb/audio.h | 49 ++++++++++++++++++++++++++++++++--------
 sound/usb/mixer.c              | 51 ++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 104 insertions(+), 11 deletions(-)

diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h
index a710e28b5215..334bfa6dfb47 100644
--- a/include/linux/usb/audio-v3.h
+++ b/include/linux/usb/audio-v3.h
@@ -387,6 +387,12 @@ struct uac3_interrupt_data_msg {
 #define UAC3_CONNECTORS			0x0f
 #define UAC3_POWER_DOMAIN		0x10
 
+/* A.20 PROCESSING UNIT PROCESS TYPES */
+#define UAC3_PROCESS_UNDEFINED		0x00
+#define UAC3_PROCESS_UP_DOWNMIX		0x01
+#define UAC3_PROCESS_STEREO_EXTENDER	0x02
+#define UAC3_PROCESS_MULTI_FUNCTION	0x03
+
 /* A.22 AUDIO CLASS-SPECIFIC REQUEST CODES */
 /* see audio-v2.h for the rest, which is identical to v2 */
 #define UAC3_CS_REQ_INTEN			0x04
@@ -406,6 +412,15 @@ struct uac3_interrupt_data_msg {
 #define UAC3_TE_OVERFLOW			0x04
 #define UAC3_TE_LATENCY 			0x05
 
+/* A.23.10 PROCESSING UNITS CONTROL SELECTROS */
+
+/* Up/Down Mixer */
+#define UAC3_UD_MODE_SELECT			0x01
+
+/* Stereo Extender */
+#define UAC3_EXT_WIDTH_CONTROL			0x01
+
+
 /* BADD predefined Unit/Terminal values */
 #define UAC3_BADD_IT_ID1	1  /* Input Terminal ID1: bTerminalID = 1 */
 #define UAC3_BADD_FU_ID2	2  /* Feature Unit ID2: bUnitID = 2 */
diff --git a/include/uapi/linux/usb/audio.h b/include/uapi/linux/usb/audio.h
index 74e520fb944f..ddc5396800aa 100644
--- a/include/uapi/linux/usb/audio.h
+++ b/include/uapi/linux/usb/audio.h
@@ -390,33 +390,64 @@ static inline __u8 uac_processing_unit_iChannelNames(struct uac_processing_unit_
 static inline __u8 uac_processing_unit_bControlSize(struct uac_processing_unit_descriptor *desc,
 						    int protocol)
 {
-	return (protocol == UAC_VERSION_1) ?
-		desc->baSourceID[desc->bNrInPins + 4] :
-		2; /* in UAC2, this value is constant */
+	switch (protocol) {
+	case UAC_VERSION_1:
+		return desc->baSourceID[desc->bNrInPins + 4];
+	case UAC_VERSION_2:
+		return 2; /* in UAC2, this value is constant */
+	case UAC_VERSION_3:
+		return 4; /* in UAC3, this value is constant */
+	default:
+		return 1;
+	}
 }
 
 static inline __u8 *uac_processing_unit_bmControls(struct uac_processing_unit_descriptor *desc,
 						   int protocol)
 {
-	return (protocol == UAC_VERSION_1) ?
-		&desc->baSourceID[desc->bNrInPins + 5] :
-		&desc->baSourceID[desc->bNrInPins + 6];
+	switch (protocol) {
+	case UAC_VERSION_1:
+		return &desc->baSourceID[desc->bNrInPins + 5];
+	case UAC_VERSION_2:
+		return &desc->baSourceID[desc->bNrInPins + 6];
+	case UAC_VERSION_3:
+		return &desc->baSourceID[desc->bNrInPins + 2];
+	default:
+		return NULL;
+	}
 }
 
 static inline __u8 uac_processing_unit_iProcessing(struct uac_processing_unit_descriptor *desc,
 						   int protocol)
 {
 	__u8 control_size = uac_processing_unit_bControlSize(desc, protocol);
-	return *(uac_processing_unit_bmControls(desc, protocol)
-			+ control_size);
+
+	switch (protocol) {
+	case UAC_VERSION_1:
+	case UAC_VERSION_2:
+	default:
+		return *(uac_processing_unit_bmControls(desc, protocol)
+			 + control_size);
+	case UAC_VERSION_3:
+		return 0; /* UAC3 does not have this field */
+	}
 }
 
 static inline __u8 *uac_processing_unit_specific(struct uac_processing_unit_descriptor *desc,
 						 int protocol)
 {
 	__u8 control_size = uac_processing_unit_bControlSize(desc, protocol);
-	return uac_processing_unit_bmControls(desc, protocol)
+
+	switch (protocol) {
+	case UAC_VERSION_1:
+	case UAC_VERSION_2:
+	default:
+		return uac_processing_unit_bmControls(desc, protocol)
 			+ control_size + 1;
+	case UAC_VERSION_3:
+		return uac_processing_unit_bmControls(desc, protocol)
+			+ control_size;
+	}
 }
 
 /* 4.5.2 Class-Specific AS Interface Descriptor */
diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index bfb3484096a6..39fde49e8749 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -953,6 +953,23 @@ static int check_input_term(struct mixer_build *state, int id,
 
 				return 0;
 			}
+			case UAC3_PROCESSING_UNIT: {
+				struct uac_processing_unit_descriptor *d = p1;
+
+				if (!d->bNrInPins)
+					return -EINVAL;
+
+				/* call recursively to retrieve the channel info */
+				err = check_input_term(state, d->baSourceID[0], term);
+				if (err < 0)
+					return err;
+
+				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->id = id;
+				term->name = 0; /* TODO: UAC3 Class-specific strings */
+
+				return 0;
+			}
 			default:
 				return -ENODEV;
 			}
@@ -2180,6 +2197,11 @@ struct procunit_info {
 	struct procunit_value_info *values;
 };
 
+static struct procunit_value_info undefined_proc_info[] = {
+	{ 0x00, "Control Undefined", 0 },
+	{ 0 }
+};
+
 static struct procunit_value_info updown_proc_info[] = {
 	{ UAC_UD_ENABLE, "Switch", USB_MIXER_BOOLEAN },
 	{ UAC_UD_MODE_SELECT, "Mode Select", USB_MIXER_U8, 1 },
@@ -2228,6 +2250,23 @@ static struct procunit_info procunits[] = {
 	{ UAC_PROCESS_DYN_RANGE_COMP, "DCR", dcr_proc_info },
 	{ 0 },
 };
+
+static struct procunit_value_info uac3_updown_proc_info[] = {
+	{ UAC3_UD_MODE_SELECT, "Mode Select", USB_MIXER_U8, 1 },
+	{ 0 }
+};
+static struct procunit_value_info uac3_stereo_ext_proc_info[] = {
+	{ UAC3_EXT_WIDTH_CONTROL, "Width Control", USB_MIXER_U8 },
+	{ 0 }
+};
+
+static struct procunit_info uac3_procunits[] = {
+	{ UAC3_PROCESS_UP_DOWNMIX, "Up Down", uac3_updown_proc_info },
+	{ UAC3_PROCESS_STEREO_EXTENDER, "3D Stereo Extender", uac3_stereo_ext_proc_info },
+	{ UAC3_PROCESS_MULTI_FUNCTION, "Multi-Function", undefined_proc_info },
+	{ 0 },
+};
+
 /*
  * predefined data for extension units
  */
@@ -2388,8 +2427,16 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 static int parse_audio_processing_unit(struct mixer_build *state, int unitid,
 				       void *raw_desc)
 {
-	return build_audio_procunit(state, unitid, raw_desc,
-				    procunits, "Processing Unit");
+	switch (state->mixer->protocol) {
+	case UAC_VERSION_1:
+	case UAC_VERSION_2:
+	default:
+		return build_audio_procunit(state, unitid, raw_desc,
+				procunits, "Processing Unit");
+	case UAC_VERSION_3:
+		return build_audio_procunit(state, unitid, raw_desc,
+				uac3_procunits, "Processing Unit");
+	}
 }
 
 static int parse_audio_extension_unit(struct mixer_build *state, int unitid,
-- 
cgit v1.2.3


From 8b3a087f7f6580e685a4f1ac980d07f96ad250a5 Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Wed, 11 Jul 2018 13:37:54 +0100
Subject: ALSA: usb-audio: Unify virtual type units type to UAC3 values

The Audio Control interface descriptor subtypes do not match
across all the UAC versions. That makes reusability of the
"virtual type" (Mixer, Processors, Selectors, etc) terminals
difficult. It also makes the mixer get the default names for
the virtual terminals wrong due to the overlap.

This patch proposes an unified approach by always using the most
comprehensive spec version to define them all (in this case UAC3).

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer.c | 36 +++++++++++++++++++++++-------------
 1 file changed, 23 insertions(+), 13 deletions(-)

diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 39fde49e8749..87f18cb74ca3 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -675,16 +675,16 @@ static int get_term_name(struct snd_usb_audio *chip, struct usb_audio_term *iter
 		if (term_only)
 			return 0;
 		switch (iterm->type >> 16) {
-		case UAC_SELECTOR_UNIT:
+		case UAC3_SELECTOR_UNIT:
 			strcpy(name, "Selector");
 			return 8;
-		case UAC1_PROCESSING_UNIT:
+		case UAC3_PROCESSING_UNIT:
 			strcpy(name, "Process Unit");
 			return 12;
-		case UAC1_EXTENSION_UNIT:
+		case UAC3_EXTENSION_UNIT:
 			strcpy(name, "Ext Unit");
 			return 8;
-		case UAC_MIXER_UNIT:
+		case UAC3_MIXER_UNIT:
 			strcpy(name, "Mixer");
 			return 5;
 		default:
@@ -832,7 +832,7 @@ static int check_input_term(struct mixer_build *state, int id,
 			case UAC_MIXER_UNIT: {
 				struct uac_mixer_unit_descriptor *d = p1;
 
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_MIXER_UNIT << 16; /* virtual type */
 				term->channels = uac_mixer_unit_bNrChannels(d);
 				term->chconfig = uac_mixer_unit_wChannelConfig(d, protocol);
 				term->name = uac_mixer_unit_iMixer(d);
@@ -845,15 +845,23 @@ static int check_input_term(struct mixer_build *state, int id,
 				err = check_input_term(state, d->baSourceID[0], term);
 				if (err < 0)
 					return err;
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */
 				term->id = id;
 				term->name = uac_selector_unit_iSelector(d);
 				return 0;
 			}
 			case UAC1_PROCESSING_UNIT:
+			/* UAC2_EFFECT_UNIT */
+				if (protocol == UAC_VERSION_1)
+					term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
+				else /* UAC_VERSION_2 */
+					term->type = UAC3_EFFECT_UNIT << 16; /* virtual type */
 			case UAC1_EXTENSION_UNIT:
 			/* UAC2_PROCESSING_UNIT_V2 */
-			/* UAC2_EFFECT_UNIT */
+				if (protocol == UAC_VERSION_1 && !term->type)
+					term->type = UAC3_EXTENSION_UNIT << 16; /* virtual type */
+				else if (protocol == UAC_VERSION_2 && !term->type)
+					term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
 			case UAC2_EXTENSION_UNIT_V2: {
 				struct uac_processing_unit_descriptor *d = p1;
 
@@ -869,7 +877,9 @@ static int check_input_term(struct mixer_build *state, int id,
 					id = d->baSourceID[0];
 					break; /* continue to parse */
 				}
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				if (!term->type)
+					term->type = UAC3_EXTENSION_UNIT << 16; /* virtual type */
+
 				term->channels = uac_processing_unit_bNrChannels(d);
 				term->chconfig = uac_processing_unit_wChannelConfig(d, protocol);
 				term->name = uac_processing_unit_iProcessing(d, protocol);
@@ -878,7 +888,7 @@ static int check_input_term(struct mixer_build *state, int id,
 			case UAC2_CLOCK_SOURCE: {
 				struct uac_clock_source_descriptor *d = p1;
 
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_CLOCK_SOURCE << 16; /* virtual type */
 				term->id = id;
 				term->name = d->iClockSource;
 				return 0;
@@ -923,7 +933,7 @@ static int check_input_term(struct mixer_build *state, int id,
 			case UAC3_CLOCK_SOURCE: {
 				struct uac3_clock_source_descriptor *d = p1;
 
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_CLOCK_SOURCE << 16; /* virtual type */
 				term->id = id;
 				term->name = le16_to_cpu(d->wClockSourceStr);
 				return 0;
@@ -936,7 +946,7 @@ static int check_input_term(struct mixer_build *state, int id,
 					return err;
 
 				term->channels = err;
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_MIXER_UNIT << 16; /* virtual type */
 
 				return 0;
 			}
@@ -947,7 +957,7 @@ static int check_input_term(struct mixer_build *state, int id,
 				err = check_input_term(state, d->baSourceID[0], term);
 				if (err < 0)
 					return err;
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_SELECTOR_UNIT << 16; /* virtual type */
 				term->id = id;
 				term->name = 0; /* TODO: UAC3 Class-specific strings */
 
@@ -964,7 +974,7 @@ static int check_input_term(struct mixer_build *state, int id,
 				if (err < 0)
 					return err;
 
-				term->type = d->bDescriptorSubtype << 16; /* virtual type */
+				term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
 				term->id = id;
 				term->name = 0; /* TODO: UAC3 Class-specific strings */
 
-- 
cgit v1.2.3


From 55b8cb46a71137aa19eba2ae5a4be384500db89e Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Wed, 11 Jul 2018 13:37:55 +0100
Subject: ALSA: usb-audio: Tidy up logic for Processing Unit min/max values

This patch refactors the processing units min/max calculation logic
for the mixer controls and fixes an issue where the Mode Select
checking of the Up/Down mixers doesn't differentiate between the
UAC1 and UAC2 Control Selector (0x02) and the UAC3 one which is
different (0x01).

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer.c | 58 +++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 17 deletions(-)

diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 87f18cb74ca3..73e811f86a95 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -2376,25 +2376,49 @@ static int build_audio_procunit(struct mixer_build *state, int unitid,
 			cval->master_readonly = 1;
 
 		/* get min/max values */
-		if (type == UAC_PROCESS_UP_DOWNMIX && cval->control == UAC_UD_MODE_SELECT) {
-			__u8 *control_spec = uac_processing_unit_specific(desc, state->mixer->protocol);
-			/* FIXME: hard-coded */
-			cval->min = 1;
-			cval->max = control_spec[0];
-			cval->res = 1;
-			cval->initialized = 1;
-		} else {
-			if (type == USB_XU_CLOCK_RATE) {
-				/*
-				 * E-Mu USB 0404/0202/TrackerPre/0204
-				 * samplerate control quirk
-				 */
-				cval->min = 0;
-				cval->max = 5;
+		switch (type) {
+		case UAC_PROCESS_UP_DOWNMIX: {
+			bool mode_sel = false;
+
+			switch (state->mixer->protocol) {
+			case UAC_VERSION_1:
+			case UAC_VERSION_2:
+			default:
+				if (cval->control == UAC_UD_MODE_SELECT)
+					mode_sel = true;
+				break;
+			case UAC_VERSION_3:
+				if (cval->control == UAC3_UD_MODE_SELECT)
+					mode_sel = true;
+				break;
+			}
+
+			if (mode_sel) {
+				__u8 *control_spec = uac_processing_unit_specific(desc,
+								state->mixer->protocol);
+				cval->min = 1;
+				cval->max = control_spec[0];
 				cval->res = 1;
 				cval->initialized = 1;
-			} else
-				get_min_max(cval, valinfo->min_value);
+				break;
+			}
+
+			get_min_max(cval, valinfo->min_value);
+			break;
+		}
+		case USB_XU_CLOCK_RATE:
+			/*
+			 * E-Mu USB 0404/0202/TrackerPre/0204
+			 * samplerate control quirk
+			 */
+			cval->min = 0;
+			cval->max = 5;
+			cval->res = 1;
+			cval->initialized = 1;
+			break;
+		default:
+			get_min_max(cval, valinfo->min_value);
+			break;
 		}
 
 		kctl = snd_ctl_new1(&mixer_procunit_ctl, cval);
-- 
cgit v1.2.3


From b6d7b3622b6e7685767a616bb663aed40d04fdc6 Mon Sep 17 00:00:00 2001
From: Jim Qu <Jim.Qu@amd.com>
Date: Mon, 16 Jul 2018 14:06:34 +0800
Subject: ALSA: hda: use PCI_BASE_CLASS_DISPLAY to replace
 PCI_CLASS_DISPLAY_VGA

Except PCI_CLASS_DISPLAY_VGA, some PCI class is sometimes
PCI_CLASS_DISPLAY_3D or PCI_CLASS_DISPLAY_OTHER.

Signed-off-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index a9b55d65f2bd..daedf662b940 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1429,7 +1429,7 @@ static struct pci_dev *get_bound_vga(struct pci_dev *pci)
 			p = pci_get_domain_bus_and_slot(pci_domain_nr(pci->bus),
 							pci->bus->number, 0);
 			if (p) {
-				if ((p->class >> 8) == PCI_CLASS_DISPLAY_VGA)
+				if ((p->class >> 16) == PCI_BASE_CLASS_DISPLAY)
 					return p;
 				pci_dev_put(p);
 			}
-- 
cgit v1.2.3


From 7f43ef9f0d98abbc0eb5e697628ec06756bf60a9 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Wed, 4 Jul 2018 17:14:05 +0200
Subject: dma-buf: Move BUG_ON from _add_shared_fence to _add_shared_inplace
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fixes the BUG_ON spuriously triggering under the following
circumstances:

* reservation_object_reserve_shared is called with shared_count ==
  shared_max - 1, so obj->staged is freed in preparation of an in-place
  update.

* reservation_object_add_shared_fence is called with the first fence,
  after which shared_count == shared_max.

* reservation_object_add_shared_fence is called with a follow-up fence
  from the same context.

In the second reservation_object_add_shared_fence call, the BUG_ON
triggers. However, nothing bad would happen in
reservation_object_add_shared_inplace, since both fences are from the
same context, so they only occupy a single slot.

Prevent this by moving the BUG_ON to where an overflow would actually
happen (e.g. if a buggy caller didn't call
reservation_object_reserve_shared before).

v2:
* Fix description of breaking scenario (Christian König)
* Add bugzilla reference

Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/106418
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> # v1
Reviewed-by: Christian König <christian.koenig@amd.com> # v1
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20180704151405.10357-1-michel@daenzer.net
---
 drivers/dma-buf/reservation.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c
index 20bf90f4ee63..6c95f61a32e7 100644
--- a/drivers/dma-buf/reservation.c
+++ b/drivers/dma-buf/reservation.c
@@ -141,6 +141,7 @@ reservation_object_add_shared_inplace(struct reservation_object *obj,
 	if (signaled) {
 		RCU_INIT_POINTER(fobj->shared[signaled_idx], fence);
 	} else {
+		BUG_ON(fobj->shared_count >= fobj->shared_max);
 		RCU_INIT_POINTER(fobj->shared[fobj->shared_count], fence);
 		fobj->shared_count++;
 	}
@@ -230,10 +231,9 @@ void reservation_object_add_shared_fence(struct reservation_object *obj,
 	old = reservation_object_get_list(obj);
 	obj->staged = NULL;
 
-	if (!fobj) {
-		BUG_ON(old->shared_count >= old->shared_max);
+	if (!fobj)
 		reservation_object_add_shared_inplace(obj, old, fence);
-	} else
+	else
 		reservation_object_add_shared_replace(obj, old, fobj, fence);
 }
 EXPORT_SYMBOL(reservation_object_add_shared_fence);
-- 
cgit v1.2.3


From 3cdba8018fd54a418480ded9c14df5436a5b743d Mon Sep 17 00:00:00 2001
From: Leonard Crestez <leonard.crestez@nxp.com>
Date: Wed, 28 Mar 2018 00:39:47 +0300
Subject: drm/imx: Remove last traces of struct imx_drm_crtc

When the definition of this struct was removed a forward declaration and an
unused struct member were still left around. Remove them because they serve
no purpose.

Fixes 44b460cfe554 ("drm: imx: remove struct imx_drm_crtc and imx_drm_crtc_helper_funcs")

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/imx-drm.h    | 1 -
 drivers/gpu/drm/imx/ipuv3-crtc.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/imx/imx-drm.h b/drivers/gpu/drm/imx/imx-drm.h
index 15c2bec47a04..ab9c6f706eb3 100644
--- a/drivers/gpu/drm/imx/imx-drm.h
+++ b/drivers/gpu/drm/imx/imx-drm.h
@@ -10,7 +10,6 @@ struct drm_display_mode;
 struct drm_encoder;
 struct drm_framebuffer;
 struct drm_plane;
-struct imx_drm_crtc;
 struct platform_device;
 
 struct imx_crtc_state {
diff --git a/drivers/gpu/drm/imx/ipuv3-crtc.c b/drivers/gpu/drm/imx/ipuv3-crtc.c
index e83af0f2be86..50d9f2bbe348 100644
--- a/drivers/gpu/drm/imx/ipuv3-crtc.c
+++ b/drivers/gpu/drm/imx/ipuv3-crtc.c
@@ -35,7 +35,6 @@
 struct ipu_crtc {
 	struct device		*dev;
 	struct drm_crtc		base;
-	struct imx_drm_crtc	*imx_crtc;
 
 	/* plane[0] is the full plane, plane[1] is the partial plane */
 	struct ipu_plane	*plane[2];
-- 
cgit v1.2.3


From 7cc3bf3f08b5645d1d08439fea36e4148dc6d7d3 Mon Sep 17 00:00:00 2001
From: Michael Grzeschik <m.grzeschik@pengutronix.de>
Date: Wed, 2 May 2018 14:52:26 +0200
Subject: gpu: ipu-csi: add rgb/bgr888 24bit support to mbus_code_to_bus_cfg

The 24bit RGB format configuration is currently missing, we add
it now.

Signed-off-by: Michael Grzeschik <m.grzeschik@pengutronix.de>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-csi.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
index 5450a2db1219..813a3199aa84 100644
--- a/drivers/gpu/ipu-v3/ipu-csi.c
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -247,6 +247,12 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
 		cfg->mipi_dt = MIPI_DT_RGB555;
 		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
 		break;
+	case MEDIA_BUS_FMT_RGB888_1X24:
+	case MEDIA_BUS_FMT_BGR888_1X24:
+		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB_YUV444;
+		cfg->mipi_dt = MIPI_DT_RGB888;
+		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
+		break;
 	case MEDIA_BUS_FMT_UYVY8_2X8:
 		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_YUV422_UYVY;
 		cfg->mipi_dt = MIPI_DT_YUV422;
-- 
cgit v1.2.3


From d36d0e6309dd8137cf438cbb680e72eb63c81425 Mon Sep 17 00:00:00 2001
From: Enrico Scholz <enrico.scholz@sigma-chemnitz.de>
Date: Thu, 3 May 2018 18:29:36 +0200
Subject: gpu: ipu-v3: csi: pass back mbus_code_to_bus_cfg error codes

mbus_code_to_bus_cfg() can fail on unknown mbus codes; pass back the
error to the caller.

Signed-off-by: Enrico Scholz <enrico.scholz@sigma-chemnitz.de>
Signed-off-by: Jan Luebbe <jlu@pengutronix.de>
[p.zabel@pengutronix.de - renamed rc to ret for consistency]
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-csi.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
index 813a3199aa84..27262748a549 100644
--- a/drivers/gpu/ipu-v3/ipu-csi.c
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -324,13 +324,17 @@ static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
 /*
  * Fill a CSI bus config struct from mbus_config and mbus_framefmt.
  */
-static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
+static int fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 				 struct v4l2_mbus_config *mbus_cfg,
 				 struct v4l2_mbus_framefmt *mbus_fmt)
 {
+	int ret;
+
 	memset(csicfg, 0, sizeof(*csicfg));
 
-	mbus_code_to_bus_cfg(csicfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(csicfg, mbus_fmt->code);
+	if (ret < 0)
+		return ret;
 
 	switch (mbus_cfg->type) {
 	case V4L2_MBUS_PARALLEL:
@@ -362,6 +366,8 @@ static void fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 		/* will never get here, keep compiler quiet */
 		break;
 	}
+
+	return 0;
 }
 
 int ipu_csi_init_interface(struct ipu_csi *csi,
@@ -371,8 +377,11 @@ int ipu_csi_init_interface(struct ipu_csi *csi,
 	struct ipu_csi_bus_config cfg;
 	unsigned long flags;
 	u32 width, height, data = 0;
+	int ret;
 
-	fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+	ret = fill_csi_bus_cfg(&cfg, mbus_cfg, mbus_fmt);
+	if (ret < 0)
+		return ret;
 
 	/* set default sensor frame width and height */
 	width = mbus_fmt->width;
@@ -593,11 +602,14 @@ int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
 	struct ipu_csi_bus_config cfg;
 	unsigned long flags;
 	u32 temp;
+	int ret;
 
 	if (vc > 3)
 		return -EINVAL;
 
-	mbus_code_to_bus_cfg(&cfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(&cfg, mbus_fmt->code);
+	if (ret < 0)
+		return ret;
 
 	spin_lock_irqsave(&csi->lock, flags);
 
-- 
cgit v1.2.3


From 1e6a1495c66947b289de9ba92b569b62ce68a979 Mon Sep 17 00:00:00 2001
From: Jan Luebbe <jlu@pengutronix.de>
Date: Thu, 3 May 2018 18:29:37 +0200
Subject: gpu: ipu-v3: csi: support RGB565 on parallel bus

The CSI_SENS_CONF_DATA_FMT_RGB565 configuration only works for MIPI
CSI-2 sources. On the parallel bus, we need to use bayer (generic) mode
instead. To handle this difference, we pass the mbus_type to
mbus_code_to_bus_cfg().

Signed-off-by: Jan Luebbe <jlu@pengutronix.de>
[p.zabel@pengutronix.de - renamed rc to ret for consistency]
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-csi.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/ipu-v3/ipu-csi.c b/drivers/gpu/ipu-v3/ipu-csi.c
index 27262748a549..954eefe144e2 100644
--- a/drivers/gpu/ipu-v3/ipu-csi.c
+++ b/drivers/gpu/ipu-v3/ipu-csi.c
@@ -224,14 +224,18 @@ static int ipu_csi_set_testgen_mclk(struct ipu_csi *csi, u32 pixel_clk,
  * Find the CSI data format and data width for the given V4L2 media
  * bus pixel format code.
  */
-static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code)
+static int mbus_code_to_bus_cfg(struct ipu_csi_bus_config *cfg, u32 mbus_code,
+				enum v4l2_mbus_type mbus_type)
 {
 	switch (mbus_code) {
 	case MEDIA_BUS_FMT_BGR565_2X8_BE:
 	case MEDIA_BUS_FMT_BGR565_2X8_LE:
 	case MEDIA_BUS_FMT_RGB565_2X8_BE:
 	case MEDIA_BUS_FMT_RGB565_2X8_LE:
-		cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		if (mbus_type == V4L2_MBUS_CSI2)
+			cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_RGB565;
+		else
+			cfg->data_fmt = CSI_SENS_CONF_DATA_FMT_BAYER;
 		cfg->mipi_dt = MIPI_DT_RGB565;
 		cfg->data_width = IPU_CSI_DATA_WIDTH_8;
 		break;
@@ -332,7 +336,7 @@ static int fill_csi_bus_cfg(struct ipu_csi_bus_config *csicfg,
 
 	memset(csicfg, 0, sizeof(*csicfg));
 
-	ret = mbus_code_to_bus_cfg(csicfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(csicfg, mbus_fmt->code, mbus_cfg->type);
 	if (ret < 0)
 		return ret;
 
@@ -607,7 +611,7 @@ int ipu_csi_set_mipi_datatype(struct ipu_csi *csi, u32 vc,
 	if (vc > 3)
 		return -EINVAL;
 
-	ret = mbus_code_to_bus_cfg(&cfg, mbus_fmt->code);
+	ret = mbus_code_to_bus_cfg(&cfg, mbus_fmt->code, V4L2_MBUS_CSI2);
 	if (ret < 0)
 		return ret;
 
-- 
cgit v1.2.3


From 4e3c5d7e05be6c9c6de4f4da9116511428924997 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Fri, 1 Jun 2018 15:13:16 +0200
Subject: gpu: ipu-v3: Allow negative offsets for interlaced scanning

The IPU also supports interlaced buffers that start with the bottom field.
To achieve this, the the base address EBA has to be increased by a stride
length and the interlace offset ILO has to be set to the negative stride.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
---
 drivers/gpu/ipu-v3/ipu-cpmem.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 9f2d9ec42add..125721a7f8b6 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -269,9 +269,20 @@ EXPORT_SYMBOL_GPL(ipu_cpmem_set_uv_offset);
 
 void ipu_cpmem_interlaced_scan(struct ipuv3_channel *ch, int stride)
 {
+	u32 ilo, sly;
+
+	if (stride < 0) {
+		stride = -stride;
+		ilo = 0x100000 - (stride / 8);
+	} else {
+		ilo = stride / 8;
+	}
+
+	sly = (stride * 2) - 1;
+
 	ipu_ch_param_write_field(ch, IPU_FIELD_SO, 1);
-	ipu_ch_param_write_field(ch, IPU_FIELD_ILO, stride / 8);
-	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, (stride * 2) - 1);
+	ipu_ch_param_write_field(ch, IPU_FIELD_ILO, ilo);
+	ipu_ch_param_write_field(ch, IPU_FIELD_SLY, sly);
 };
 EXPORT_SYMBOL_GPL(ipu_cpmem_interlaced_scan);
 
-- 
cgit v1.2.3


From 71a5cb3eb758b5b3735709c7fca577522eda43d4 Mon Sep 17 00:00:00 2001
From: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Date: Fri, 13 Jul 2018 16:10:58 +0100
Subject: drm: writeback: Fix doc that says connector should be disconnected

During iteration process one of the proposed mechanism for not
breaking existing userspace was to report writeback connectors as
disconnected, however the final version used
DRM_CLIENT_CAP_WRITEBACK_CONNECTORS for that purpose.

Change-Id: I2319d099f7669094c8530f1521abdbca08e76486
Signed-off-by: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Link: https://patchwork.freedesktop.org/patch/238399/
---
 drivers/gpu/drm/drm_writeback.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_writeback.c b/drivers/gpu/drm/drm_writeback.c
index 169746f6b567..c20e6fe00cb3 100644
--- a/drivers/gpu/drm/drm_writeback.c
+++ b/drivers/gpu/drm/drm_writeback.c
@@ -25,8 +25,8 @@
  *
  * * Writeback connectors don't provide a way to output visually to the user.
  *
- * * Writeback connectors should always report as "disconnected" (so that
- *   clients which don't understand them will ignore them).
+ * * Writeback connectors are visible to userspace only when the client sets
+ *   DRM_CLIENT_CAP_WRITEBACK_CONNECTORS.
  *
  * * Writeback connectors don't have EDID.
  *
-- 
cgit v1.2.3


From a18b21929453af70390e14f8dee40acf00d428cb Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Mon, 16 Jul 2018 11:44:32 -0400
Subject: drm/dp_helper: Add DP aux channel tracing

This is something we've needed for a very long time now, as it makes
debugging issues with faulty MST hubs along with debugging issues
regarding us interfacing with hubs correctly vastly easier to debug.
Currently this can actually be done if you trace the i2c devices for DP
using ftrace but that's significantly less useful for a couple of
reasons:

- Tracing the i2c devices through ftrace means all of the traces are
  going to contain a lot of "garbage" output that we're sending over the
  i2c line. Most of this garbage comes from retrying transactions, DRM's
  helper library adding extra transactions to work around bad hubs, etc.
- Having a user set up ftrace so that they can provide debugging
  information is a lot more difficult then being able to say "just boot
  with drm.debug=0x100"
- We can potentially expand upon this tracing in the future to print
  debugging information in regards to other DP transactions like MST
  sideband transactions

This is inspired by a patch Rob Clark sent to do this a long time back.
Neither of us could find the patch however, so we both assumed it would
probably just be easier to rewrite it anyway.

Cc: Rob Clark <robdclark@gmail.com>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716154432.13433-1-lyude@redhat.com
---
 drivers/gpu/drm/drm_dp_helper.c | 32 +++++++++++++++++++++++++++-----
 drivers/gpu/drm/drm_drv.c       | 15 ++++++++-------
 include/drm/drm_print.h         |  6 ++++++
 3 files changed, 41 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/drm_dp_helper.c b/drivers/gpu/drm/drm_dp_helper.c
index f4a06b54aa7d..0cccbcb2d03e 100644
--- a/drivers/gpu/drm/drm_dp_helper.c
+++ b/drivers/gpu/drm/drm_dp_helper.c
@@ -185,6 +185,20 @@ EXPORT_SYMBOL(drm_dp_bw_code_to_link_rate);
 
 #define AUX_RETRY_INTERVAL 500 /* us */
 
+static inline void
+drm_dp_dump_access(const struct drm_dp_aux *aux,
+		   u8 request, uint offset, void *buffer, int ret)
+{
+	const char *arrow = request == DP_AUX_NATIVE_READ ? "->" : "<-";
+
+	if (ret > 0)
+		drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d) %*ph\n",
+			aux->name, offset, arrow, ret, min(ret, 20), buffer);
+	else
+		drm_dbg(DRM_UT_DP, "%s: 0x%05x AUX %s (ret=%3d)\n",
+			aux->name, offset, arrow, ret);
+}
+
 /**
  * DOC: dp helpers
  *
@@ -288,10 +302,14 @@ ssize_t drm_dp_dpcd_read(struct drm_dp_aux *aux, unsigned int offset,
 	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, DP_DPCD_REV, buffer,
 				 1);
 	if (ret != 1)
-		return ret;
+		goto out;
 
-	return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer,
-				  size);
+	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_READ, offset, buffer,
+				 size);
+
+out:
+	drm_dp_dump_access(aux, DP_AUX_NATIVE_READ, offset, buffer, ret);
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_dpcd_read);
 
@@ -312,8 +330,12 @@ EXPORT_SYMBOL(drm_dp_dpcd_read);
 ssize_t drm_dp_dpcd_write(struct drm_dp_aux *aux, unsigned int offset,
 			  void *buffer, size_t size)
 {
-	return drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer,
-				  size);
+	int ret;
+
+	ret = drm_dp_dpcd_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer,
+				 size);
+	drm_dp_dump_access(aux, DP_AUX_NATIVE_WRITE, offset, buffer, ret);
+	return ret;
 }
 EXPORT_SYMBOL(drm_dp_dpcd_write);
 
diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
index 6eb935bb2f92..ea4941da9b27 100644
--- a/drivers/gpu/drm/drm_drv.c
+++ b/drivers/gpu/drm/drm_drv.c
@@ -54,13 +54,14 @@ MODULE_AUTHOR("Gareth Hughes, Leif Delgass, José Fonseca, Jon Smirl");
 MODULE_DESCRIPTION("DRM shared core routines");
 MODULE_LICENSE("GPL and additional rights");
 MODULE_PARM_DESC(debug, "Enable debug output, where each bit enables a debug category.\n"
-"\t\tBit 0 (0x01) will enable CORE messages (drm core code)\n"
-"\t\tBit 1 (0x02) will enable DRIVER messages (drm controller code)\n"
-"\t\tBit 2 (0x04) will enable KMS messages (modesetting code)\n"
-"\t\tBit 3 (0x08) will enable PRIME messages (prime code)\n"
-"\t\tBit 4 (0x10) will enable ATOMIC messages (atomic code)\n"
-"\t\tBit 5 (0x20) will enable VBL messages (vblank code)\n"
-"\t\tBit 7 (0x80) will enable LEASE messages (leasing code)");
+"\t\tBit 0 (0x01)  will enable CORE messages (drm core code)\n"
+"\t\tBit 1 (0x02)  will enable DRIVER messages (drm controller code)\n"
+"\t\tBit 2 (0x04)  will enable KMS messages (modesetting code)\n"
+"\t\tBit 3 (0x08)  will enable PRIME messages (prime code)\n"
+"\t\tBit 4 (0x10)  will enable ATOMIC messages (atomic code)\n"
+"\t\tBit 5 (0x20)  will enable VBL messages (vblank code)\n"
+"\t\tBit 7 (0x80)  will enable LEASE messages (leasing code)\n"
+"\t\tBit 8 (0x100) will enable DP messages (displayport code)");
 module_param_named(debug, drm_debug, int, 0600);
 
 static DEFINE_SPINLOCK(drm_minor_lock);
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index e1a46e9991cc..767c90b654c5 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -195,6 +195,7 @@ static inline struct drm_printer drm_debug_printer(const char *prefix)
 #define DRM_UT_VBL		0x20
 #define DRM_UT_STATE		0x40
 #define DRM_UT_LEASE		0x80
+#define DRM_UT_DP		0x100
 
 __printf(3, 4)
 void drm_dev_printk(const struct device *dev, const char *level,
@@ -307,6 +308,11 @@ void drm_err(const char *format, ...);
 #define DRM_DEBUG_LEASE(fmt, ...)					\
 	drm_dbg(DRM_UT_LEASE, fmt, ##__VA_ARGS__)
 
+#define	DRM_DEV_DEBUG_DP(dev, fmt, ...)					\
+	drm_dev_dbg(dev, DRM_UT_DP, fmt, ## __VA_ARGS__)
+#define DRM_DEBUG_DP(dev, fmt, ...)					\
+	drm_dbg(DRM_UT_DP, fmt, ## __VA_ARGS__)
+
 #define _DRM_DEV_DEFINE_DEBUG_RATELIMITED(dev, category, fmt, ...)	\
 ({									\
 	static DEFINE_RATELIMIT_STATE(_rs,				\
-- 
cgit v1.2.3


From 6542df2f8412a8a065e987aac940130884028715 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Tue, 12 Jun 2018 01:54:47 +0900
Subject: netfilter: nft_reject_bridge: remove unnecessary ttl set

In the nft_reject_br_send_v4_tcp_reset(), a ttl is set by the
nf_reject_iphdr_put(). so, below code is unnecessary.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/bridge/netfilter/nft_reject_bridge.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index 6de981270566..08cbed7d940e 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -89,8 +89,7 @@ static void nft_reject_br_send_v4_tcp_reset(struct net *net,
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
 				   net->ipv4.sysctl_ip_default_ttl);
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
-	niph->ttl	= net->ipv4.sysctl_ip_default_ttl;
-	niph->tot_len	= htons(nskb->len);
+	niph->tot_len = htons(nskb->len);
 	ip_send_check(niph);
 
 	nft_reject_br_push_etherhdr(oldskb, nskb);
-- 
cgit v1.2.3


From e97d9404d5e8aea1f91f4c00dbe7854008f3a1e1 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 15 Jun 2018 23:46:42 +0200
Subject: netfilter: flowtables: use fixed renew timeout on teardown

This is one of the very few external callers of ->get_timeouts(),

We can use a fixed timeout instead, conntrack core will refresh this in
case a new packet comes within this period.

Use of ESTABLISHED timeout seems way too huge anyway.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_core.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index eb0d1658ac05..d8125616edc7 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -107,11 +107,12 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp)
 	tcp->seen[1].td_maxwin = 0;
 }
 
+#define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT	(120 * HZ)
+#define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT	(30 * HZ)
+
 static void flow_offload_fixup_ct_state(struct nf_conn *ct)
 {
 	const struct nf_conntrack_l4proto *l4proto;
-	struct net *net = nf_ct_net(ct);
-	unsigned int *timeouts;
 	unsigned int timeout;
 	int l4num;
 
@@ -123,14 +124,10 @@ static void flow_offload_fixup_ct_state(struct nf_conn *ct)
 	if (!l4proto)
 		return;
 
-	timeouts = l4proto->get_timeouts(net);
-	if (!timeouts)
-		return;
-
 	if (l4num == IPPROTO_TCP)
-		timeout = timeouts[TCP_CONNTRACK_ESTABLISHED];
+		timeout = NF_FLOWTABLE_TCP_PICKUP_TIMEOUT;
 	else if (l4num == IPPROTO_UDP)
-		timeout = timeouts[UDP_CT_REPLIED];
+		timeout = NF_FLOWTABLE_UDP_PICKUP_TIMEOUT;
 	else
 		return;
 
-- 
cgit v1.2.3


From f286586df68e7733a8e651098401f139dc2e17f4 Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Mon, 18 Jun 2018 15:12:52 +0200
Subject: netfilter: nft_tproxy: Move nf_tproxy_assign_sock() to nf_tproxy.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This function is also necessary to implement nft tproxy support

Fixes: 45ca4e0cf273 ("netfilter: Libify xt_TPROXY")
Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tproxy.h | 8 ++++++++
 net/netfilter/xt_TPROXY.c         | 9 ---------
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/include/net/netfilter/nf_tproxy.h b/include/net/netfilter/nf_tproxy.h
index 9754a50ecde9..d5a80888cbe4 100644
--- a/include/net/netfilter/nf_tproxy.h
+++ b/include/net/netfilter/nf_tproxy.h
@@ -17,6 +17,14 @@ static inline bool nf_tproxy_sk_is_transparent(struct sock *sk)
 	return false;
 }
 
+/* assign a socket to the skb -- consumes sk */
+static inline void nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
+{
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+}
+
 __be32 nf_tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr);
 
 /**
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 58fce4e749a9..35df0827e2ca 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -36,15 +36,6 @@
 #include <net/netfilter/nf_tproxy.h>
 #include <linux/netfilter/xt_TPROXY.h>
 
-/* assign a socket to the skb -- consumes sk */
-static void
-nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
-{
-	skb_orphan(skb);
-	skb->sk = sk;
-	skb->destructor = sock_edemux;
-}
-
 static unsigned int
 tproxy_tg4(struct net *net, struct sk_buff *skb, __be32 laddr, __be16 lport,
 	   u_int32_t mark_mask, u_int32_t mark_value)
-- 
cgit v1.2.3


From d7e5a9a50245b91f016c814b0f076f7e55cbb980 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 25 Jun 2018 17:49:43 +0200
Subject: netfilter: utils: move nf_ip_checksum* from ipv4 to utils

allows to make nf_ip_checksum_partial static, it no longer
has an external caller.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_ipv4.h | 11 ---------
 net/ipv4/netfilter.c           | 53 ----------------------------------------
 net/netfilter/utils.c          | 55 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 55 insertions(+), 64 deletions(-)

diff --git a/include/linux/netfilter_ipv4.h b/include/linux/netfilter_ipv4.h
index b31dabfdb453..95ab5cc64422 100644
--- a/include/linux/netfilter_ipv4.h
+++ b/include/linux/netfilter_ipv4.h
@@ -23,9 +23,6 @@ struct nf_queue_entry;
 #ifdef CONFIG_INET
 __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 		       unsigned int dataoff, u_int8_t protocol);
-__sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
-			       unsigned int dataoff, unsigned int len,
-			       u_int8_t protocol);
 int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
 		bool strict);
 int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry);
@@ -35,14 +32,6 @@ static inline __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
 {
 	return 0;
 }
-static inline __sum16 nf_ip_checksum_partial(struct sk_buff *skb,
-					     unsigned int hook,
-					     unsigned int dataoff,
-					     unsigned int len,
-					     u_int8_t protocol)
-{
-	return 0;
-}
 static inline int nf_ip_route(struct net *net, struct dst_entry **dst,
 			      struct flowi *fl, bool strict)
 {
diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c
index e6774ccb7731..8d2e5dc9a827 100644
--- a/net/ipv4/netfilter.c
+++ b/net/ipv4/netfilter.c
@@ -98,59 +98,6 @@ int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry)
 }
 EXPORT_SYMBOL_GPL(nf_ip_reroute);
 
-__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
-			    unsigned int dataoff, u_int8_t protocol)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
-			break;
-		if ((protocol == 0 && !csum_fold(skb->csum)) ||
-		    !csum_tcpudp_magic(iph->saddr, iph->daddr,
-				       skb->len - dataoff, protocol,
-				       skb->csum)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			break;
-		}
-		/* fall through */
-	case CHECKSUM_NONE:
-		if (protocol == 0)
-			skb->csum = 0;
-		else
-			skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
-						       skb->len - dataoff,
-						       protocol, 0);
-		csum = __skb_checksum_complete(skb);
-	}
-	return csum;
-}
-EXPORT_SYMBOL(nf_ip_checksum);
-
-__sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
-			       unsigned int dataoff, unsigned int len,
-			       u_int8_t protocol)
-{
-	const struct iphdr *iph = ip_hdr(skb);
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (len == skb->len - dataoff)
-			return nf_ip_checksum(skb, hook, dataoff, protocol);
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol,
-					       skb->len - dataoff, 0);
-		skb->ip_summed = CHECKSUM_NONE;
-		return __skb_checksum_complete_head(skb, dataoff + len);
-	}
-	return csum;
-}
-EXPORT_SYMBOL_GPL(nf_ip_checksum_partial);
-
 int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
 		bool strict __always_unused)
 {
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index 0b660c568156..8980c8a0fe5c 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -1,9 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/kernel.h>
 #include <linux/netfilter.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_ipv6.h>
 #include <net/netfilter/nf_queue.h>
 
+#ifdef CONFIG_INET
+__sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
+		       unsigned int dataoff, u8 protocol)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	__sum16 csum = 0;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
+			break;
+		if ((protocol == 0 && !csum_fold(skb->csum)) ||
+		    !csum_tcpudp_magic(iph->saddr, iph->daddr,
+				       skb->len - dataoff, protocol,
+				       skb->csum)) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			break;
+		}
+		/* fall through */
+	case CHECKSUM_NONE:
+		if (protocol == 0)
+			skb->csum = 0;
+		else
+			skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
+						       skb->len - dataoff,
+						       protocol, 0);
+		csum = __skb_checksum_complete(skb);
+	}
+	return csum;
+}
+EXPORT_SYMBOL(nf_ip_checksum);
+#endif
+
+static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
+				      unsigned int dataoff, unsigned int len,
+				      u8 protocol)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	__sum16 csum = 0;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (len == skb->len - dataoff)
+			return nf_ip_checksum(skb, hook, dataoff, protocol);
+		/* fall through */
+	case CHECKSUM_NONE:
+		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, protocol,
+					       skb->len - dataoff, 0);
+		skb->ip_summed = CHECKSUM_NONE;
+		return __skb_checksum_complete_head(skb, dataoff + len);
+	}
+	return csum;
+}
+
 __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook,
 		    unsigned int dataoff, u_int8_t protocol,
 		    unsigned short family)
-- 
cgit v1.2.3


From ebee5a50d0b7cdc576aa8081f05b86971880054d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 25 Jun 2018 17:49:59 +0200
Subject: netfilter: utils: move nf_ip6_checksum* from ipv6 to utils

similar to previous change, this also allows to remove it
from nf_ipv6_ops and avoid the indirection.

It also removes the bogus dependency of nf_conntrack_ipv6 on ipv6 module:
ipv6 checksum functions are built into kernel even if CONFIG_IPV6=m,
but ipv6/netfilter.o isn't.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_ipv6.h |  5 ---
 net/ipv6/netfilter.c           | 62 ----------------------------------
 net/netfilter/utils.c          | 76 ++++++++++++++++++++++++++++++++++++------
 3 files changed, 65 insertions(+), 78 deletions(-)

diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 288c597e75b3..c0dc4dd78887 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -30,11 +30,6 @@ struct nf_ipv6_ops {
 	void (*route_input)(struct sk_buff *skb);
 	int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
 			int (*output)(struct net *, struct sock *, struct sk_buff *));
-	__sum16 (*checksum)(struct sk_buff *skb, unsigned int hook,
-			    unsigned int dataoff, u_int8_t protocol);
-	__sum16 (*checksum_partial)(struct sk_buff *skb, unsigned int hook,
-				    unsigned int dataoff, unsigned int len,
-				    u_int8_t protocol);
 	int (*route)(struct net *net, struct dst_entry **dst, struct flowi *fl,
 		     bool strict);
 	int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry);
diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c
index 531d6957af36..5ae8e1c51079 100644
--- a/net/ipv6/netfilter.c
+++ b/net/ipv6/netfilter.c
@@ -15,7 +15,6 @@
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/xfrm.h>
-#include <net/ip6_checksum.h>
 #include <net/netfilter/nf_queue.h>
 
 int ip6_route_me_harder(struct net *net, struct sk_buff *skb)
@@ -106,71 +105,10 @@ static int nf_ip6_route(struct net *net, struct dst_entry **dst,
 	return err;
 }
 
-__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
-			     unsigned int dataoff, u_int8_t protocol)
-{
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
-			break;
-		if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-				     skb->len - dataoff, protocol,
-				     csum_sub(skb->csum,
-					      skb_checksum(skb, 0,
-							   dataoff, 0)))) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			break;
-		}
-		/* fall through */
-	case CHECKSUM_NONE:
-		skb->csum = ~csum_unfold(
-				csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
-					     skb->len - dataoff,
-					     protocol,
-					     csum_sub(0,
-						      skb_checksum(skb, 0,
-								   dataoff, 0))));
-		csum = __skb_checksum_complete(skb);
-	}
-	return csum;
-}
-EXPORT_SYMBOL(nf_ip6_checksum);
-
-static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
-				       unsigned int dataoff, unsigned int len,
-				       u_int8_t protocol)
-{
-	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
-	__wsum hsum;
-	__sum16 csum = 0;
-
-	switch (skb->ip_summed) {
-	case CHECKSUM_COMPLETE:
-		if (len == skb->len - dataoff)
-			return nf_ip6_checksum(skb, hook, dataoff, protocol);
-		/* fall through */
-	case CHECKSUM_NONE:
-		hsum = skb_checksum(skb, 0, dataoff, 0);
-		skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
-							 &ip6h->daddr,
-							 skb->len - dataoff,
-							 protocol,
-							 csum_sub(0, hsum)));
-		skb->ip_summed = CHECKSUM_NONE;
-		return __skb_checksum_complete_head(skb, dataoff + len);
-	}
-	return csum;
-};
-
 static const struct nf_ipv6_ops ipv6ops = {
 	.chk_addr		= ipv6_chk_addr,
 	.route_input    	= ip6_route_input,
 	.fragment		= ip6_fragment,
-	.checksum		= nf_ip6_checksum,
-	.checksum_partial	= nf_ip6_checksum_partial,
 	.route			= nf_ip6_route,
 	.reroute		= nf_ip6_reroute,
 };
diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c
index 8980c8a0fe5c..e8da9a9bba73 100644
--- a/net/netfilter/utils.c
+++ b/net/netfilter/utils.c
@@ -4,6 +4,7 @@
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_ipv6.h>
 #include <net/netfilter/nf_queue.h>
+#include <net/ip6_checksum.h>
 
 #ifdef CONFIG_INET
 __sum16 nf_ip_checksum(struct sk_buff *skb, unsigned int hook,
@@ -59,11 +60,69 @@ static __sum16 nf_ip_checksum_partial(struct sk_buff *skb, unsigned int hook,
 	return csum;
 }
 
+__sum16 nf_ip6_checksum(struct sk_buff *skb, unsigned int hook,
+			unsigned int dataoff, u8 protocol)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	__sum16 csum = 0;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (hook != NF_INET_PRE_ROUTING && hook != NF_INET_LOCAL_IN)
+			break;
+		if (!csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+				     skb->len - dataoff, protocol,
+				     csum_sub(skb->csum,
+					      skb_checksum(skb, 0,
+							   dataoff, 0)))) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			break;
+		}
+		/* fall through */
+	case CHECKSUM_NONE:
+		skb->csum = ~csum_unfold(
+				csum_ipv6_magic(&ip6h->saddr, &ip6h->daddr,
+					     skb->len - dataoff,
+					     protocol,
+					     csum_sub(0,
+						      skb_checksum(skb, 0,
+								   dataoff, 0))));
+		csum = __skb_checksum_complete(skb);
+	}
+	return csum;
+}
+EXPORT_SYMBOL(nf_ip6_checksum);
+
+static __sum16 nf_ip6_checksum_partial(struct sk_buff *skb, unsigned int hook,
+				       unsigned int dataoff, unsigned int len,
+				       u8 protocol)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	__wsum hsum;
+	__sum16 csum = 0;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_COMPLETE:
+		if (len == skb->len - dataoff)
+			return nf_ip6_checksum(skb, hook, dataoff, protocol);
+		/* fall through */
+	case CHECKSUM_NONE:
+		hsum = skb_checksum(skb, 0, dataoff, 0);
+		skb->csum = ~csum_unfold(csum_ipv6_magic(&ip6h->saddr,
+							 &ip6h->daddr,
+							 skb->len - dataoff,
+							 protocol,
+							 csum_sub(0, hsum)));
+		skb->ip_summed = CHECKSUM_NONE;
+		return __skb_checksum_complete_head(skb, dataoff + len);
+	}
+	return csum;
+};
+
 __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook,
-		    unsigned int dataoff, u_int8_t protocol,
+		    unsigned int dataoff, u8 protocol,
 		    unsigned short family)
 {
-	const struct nf_ipv6_ops *v6ops;
 	__sum16 csum = 0;
 
 	switch (family) {
@@ -71,9 +130,7 @@ __sum16 nf_checksum(struct sk_buff *skb, unsigned int hook,
 		csum = nf_ip_checksum(skb, hook, dataoff, protocol);
 		break;
 	case AF_INET6:
-		v6ops = rcu_dereference(nf_ipv6_ops);
-		if (v6ops)
-			csum = v6ops->checksum(skb, hook, dataoff, protocol);
+		csum = nf_ip6_checksum(skb, hook, dataoff, protocol);
 		break;
 	}
 
@@ -83,9 +140,8 @@ EXPORT_SYMBOL_GPL(nf_checksum);
 
 __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook,
 			    unsigned int dataoff, unsigned int len,
-			    u_int8_t protocol, unsigned short family)
+			    u8 protocol, unsigned short family)
 {
-	const struct nf_ipv6_ops *v6ops;
 	__sum16 csum = 0;
 
 	switch (family) {
@@ -94,10 +150,8 @@ __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook,
 					      protocol);
 		break;
 	case AF_INET6:
-		v6ops = rcu_dereference(nf_ipv6_ops);
-		if (v6ops)
-			csum = v6ops->checksum_partial(skb, hook, dataoff, len,
-						       protocol);
+		csum = nf_ip6_checksum_partial(skb, hook, dataoff, len,
+					       protocol);
 		break;
 	}
 
-- 
cgit v1.2.3


From 60e3be94e6a1c5162a0763c9aafb5190b2b1fdce Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 25 Jun 2018 17:55:32 +0200
Subject: openvswitch: use nf_ct_get_tuplepr, invert_tuplepr

These versions deal with the l3proto/l4proto details internally.
It removes only caller of nf_ct_get_tuple, so make it static.

After this, l3proto->get_l4proto() can be removed in a followup patch.

Signed-off-by: Florian Westphal <fw@strlen.de>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_core.h |  7 -------
 net/netfilter/nf_conntrack_core.c         |  3 +--
 net/openvswitch/conntrack.c               | 17 +++--------------
 3 files changed, 4 insertions(+), 23 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 9b5e7634713e..90df45022c51 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -40,13 +40,6 @@ void nf_conntrack_cleanup_start(void);
 void nf_conntrack_init_end(void);
 void nf_conntrack_cleanup_end(void);
 
-bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff,
-		     unsigned int dataoff, u_int16_t l3num, u_int8_t protonum,
-		     struct net *net,
-		     struct nf_conntrack_tuple *tuple,
-		     const struct nf_conntrack_l3proto *l3proto,
-		     const struct nf_conntrack_l4proto *l4proto);
-
 bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 			const struct nf_conntrack_tuple *orig,
 			const struct nf_conntrack_l3proto *l3proto,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 85ab2fd6a665..be0ab81e6b2c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -222,7 +222,7 @@ static u32 hash_conntrack(const struct net *net,
 	return scale_hash(hash_conntrack_raw(tuple, net));
 }
 
-bool
+static bool
 nf_ct_get_tuple(const struct sk_buff *skb,
 		unsigned int nhoff,
 		unsigned int dataoff,
@@ -244,7 +244,6 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 
 	return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
 }
-EXPORT_SYMBOL_GPL(nf_ct_get_tuple);
 
 bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 		       u_int16_t l3num,
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 284aca2a252d..e05bd3e53f0f 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -607,23 +607,12 @@ static struct nf_conn *
 ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
 		     u8 l3num, struct sk_buff *skb, bool natted)
 {
-	const struct nf_conntrack_l3proto *l3proto;
-	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conn *ct;
-	unsigned int dataoff;
-	u8 protonum;
 
-	l3proto = __nf_ct_l3proto_find(l3num);
-	if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff,
-				 &protonum) <= 0) {
-		pr_debug("ovs_ct_find_existing: Can't get protonum\n");
-		return NULL;
-	}
-	l4proto = __nf_ct_l4proto_find(l3num, protonum);
-	if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
-			     protonum, net, &tuple, l3proto, l4proto)) {
+	if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), l3num,
+			       net, &tuple)) {
 		pr_debug("ovs_ct_find_existing: Can't get tuple\n");
 		return NULL;
 	}
@@ -632,7 +621,7 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone,
 	if (natted) {
 		struct nf_conntrack_tuple inverse;
 
-		if (!nf_ct_invert_tuple(&inverse, &tuple, l3proto, l4proto)) {
+		if (!nf_ct_invert_tuplepr(&inverse, &tuple)) {
 			pr_debug("ovs_ct_find_existing: Inversion failed!\n");
 			return NULL;
 		}
-- 
cgit v1.2.3


From 7414d929bc35b9a7c3eab98ef7bd32d5ae4c2981 Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Thu, 28 Jun 2018 20:01:02 +0200
Subject: netfilter: Kconfig: Make NETFILTER_XT_MATCH_SOCKET select
 NF_SOCKET_IPV4/6
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of depending on it.

Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index dbd7d1fad277..3ce657fbca67 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -1492,8 +1492,8 @@ config NETFILTER_XT_MATCH_SOCKET
 	depends on NETFILTER_ADVANCED
 	depends on IPV6 || IPV6=n
 	depends on IP6_NF_IPTABLES || IP6_NF_IPTABLES=n
-	depends on NF_SOCKET_IPV4
-	depends on NF_SOCKET_IPV6
+	select NF_SOCKET_IPV4
+	select NF_SOCKET_IPV6 if IP6_NF_IPTABLES
 	select NF_DEFRAG_IPV4
 	select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES != n
 	help
-- 
cgit v1.2.3


From f957be9d349a3800940f823b16e12b0405cc305b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:44 +0200
Subject: netfilter: conntrack: remove ctnetlink callbacks from l3 protocol
 trackers

handle everything from ctnetlink directly.

After all these years we still only support ipv4 and ipv6, so it
seems reasonable to remove l3 protocol tracker support and instead
handle ipv4/ipv6 from a common, always builtin inet tracker.

Step 1: Get rid of all the l3proto->func() calls.

Start with ctnetlink, then move on to packet-path ones.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_core.h      |  6 +-
 include/net/netfilter/nf_conntrack_l3proto.h   |  8 ---
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 47 -------------
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 48 -------------
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c      |  1 -
 net/netfilter/nf_conntrack_expect.c            |  1 -
 net/netfilter/nf_conntrack_helper.c            |  1 -
 net/netfilter/nf_conntrack_netlink.c           | 96 +++++++++++++++++++-------
 net/netfilter/nf_conntrack_proto.c             |  5 +-
 net/netfilter/nf_conntrack_standalone.c        | 14 ++--
 net/netfilter/nfnetlink_cttimeout.c            |  1 -
 11 files changed, 79 insertions(+), 149 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 90df45022c51..d454a53ba646 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -68,10 +68,8 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
 	return ret;
 }
 
-void
-print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
-            const struct nf_conntrack_l3proto *l3proto,
-            const struct nf_conntrack_l4proto *proto);
+void print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
+		 const struct nf_conntrack_l4proto *proto);
 
 #define CONNTRACK_LOCKS 1024
 
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index d5808f3e2715..d07b5216a925 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -46,14 +46,6 @@ struct nf_conntrack_l3proto {
 	int (*get_l4proto)(const struct sk_buff *skb, unsigned int nhoff,
 			   unsigned int *dataoff, u_int8_t *protonum);
 
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	int (*tuple_to_nlattr)(struct sk_buff *skb,
-			       const struct nf_conntrack_tuple *t);
-	int (*nlattr_to_tuple)(struct nlattr *tb[],
-			       struct nf_conntrack_tuple *t);
-	const struct nla_policy *nla_policy;
-#endif
-
 	/* Called when netns wants to use connection tracking */
 	int (*net_ns_get)(struct net *);
 	void (*net_ns_put)(struct net *);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 9db988f9a4d7..98ed12858c52 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -274,41 +274,6 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 	return -ENOENT;
 }
 
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nfnetlink_conntrack.h>
-
-static int ipv4_tuple_to_nlattr(struct sk_buff *skb,
-				const struct nf_conntrack_tuple *tuple)
-{
-	if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) ||
-	    nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static const struct nla_policy ipv4_nla_policy[CTA_IP_MAX+1] = {
-	[CTA_IP_V4_SRC]	= { .type = NLA_U32 },
-	[CTA_IP_V4_DST]	= { .type = NLA_U32 },
-};
-
-static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *t)
-{
-	if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST])
-		return -EINVAL;
-
-	t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
-	t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);
-
-	return 0;
-}
-#endif
-
 static struct nf_sockopt_ops so_getorigdst = {
 	.pf		= PF_INET,
 	.get_optmin	= SO_ORIGINAL_DST,
@@ -360,13 +325,6 @@ const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.pkt_to_tuple	 = ipv4_pkt_to_tuple,
 	.invert_tuple	 = ipv4_invert_tuple,
 	.get_l4proto	 = ipv4_get_l4proto,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.tuple_to_nlattr = ipv4_tuple_to_nlattr,
-	.nlattr_to_tuple = ipv4_nlattr_to_tuple,
-	.nla_policy	 = ipv4_nla_policy,
-	.nla_size	 = NLA_ALIGN(NLA_HDRLEN + sizeof(u32)) + /* CTA_IP_V4_SRC */
-			   NLA_ALIGN(NLA_HDRLEN + sizeof(u32)),  /* CTA_IP_V4_DST */
-#endif
 	.net_ns_get	 = ipv4_hooks_register,
 	.net_ns_put	 = ipv4_hooks_unregister,
 	.me		 = THIS_MODULE,
@@ -419,11 +377,6 @@ static int __init nf_conntrack_l3proto_ipv4_init(void)
 
 	need_conntrack();
 
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	if (WARN_ON(nla_policy_len(ipv4_nla_policy, CTA_IP_MAX + 1) !=
-	    nf_conntrack_l3proto_ipv4.nla_size))
-		return -EINVAL;
-#endif
 	ret = nf_register_sockopt(&so_getorigdst);
 	if (ret < 0) {
 		pr_err("Unable to register netfilter socket option\n");
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 663827ee3cf8..13a660ae5799 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -269,41 +269,6 @@ ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 	return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
 }
 
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nfnetlink_conntrack.h>
-
-static int ipv6_tuple_to_nlattr(struct sk_buff *skb,
-				const struct nf_conntrack_tuple *tuple)
-{
-	if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) ||
-	    nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static const struct nla_policy ipv6_nla_policy[CTA_IP_MAX+1] = {
-	[CTA_IP_V6_SRC]	= { .len = sizeof(u_int32_t)*4 },
-	[CTA_IP_V6_DST]	= { .len = sizeof(u_int32_t)*4 },
-};
-
-static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *t)
-{
-	if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST])
-		return -EINVAL;
-
-	t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]);
-	t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]);
-
-	return 0;
-}
-#endif
-
 static int ipv6_hooks_register(struct net *net)
 {
 	struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
@@ -345,13 +310,6 @@ const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
 	.pkt_to_tuple		= ipv6_pkt_to_tuple,
 	.invert_tuple		= ipv6_invert_tuple,
 	.get_l4proto		= ipv6_get_l4proto,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.tuple_to_nlattr	= ipv6_tuple_to_nlattr,
-	.nlattr_to_tuple	= ipv6_nlattr_to_tuple,
-	.nla_policy		= ipv6_nla_policy,
-	.nla_size		= NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])) +
-				  NLA_ALIGN(NLA_HDRLEN + sizeof(u32[4])),
-#endif
 	.net_ns_get		= ipv6_hooks_register,
 	.net_ns_put		= ipv6_hooks_unregister,
 	.me			= THIS_MODULE,
@@ -409,12 +367,6 @@ static int __init nf_conntrack_l3proto_ipv6_init(void)
 
 	need_conntrack();
 
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	if (WARN_ON(nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1) !=
-	    nf_conntrack_l3proto_ipv6.nla_size))
-		return -EINVAL;
-#endif
-
 	ret = nf_register_sockopt(&so_getorigdst6);
 	if (ret < 0) {
 		pr_err("Unable to register netfilter socket option\n");
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index c87b48359e8f..e631be25337e 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -23,7 +23,6 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 #endif
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 853b23206bb7..3f586ba23d92 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -610,7 +610,6 @@ static int exp_seq_show(struct seq_file *s, void *v)
 		   expect->tuple.src.l3num,
 		   expect->tuple.dst.protonum);
 	print_tuple(s, &expect->tuple,
-		    __nf_ct_l3proto_find(expect->tuple.src.l3num),
 		    __nf_ct_l4proto_find(expect->tuple.src.l3num,
 				       expect->tuple.dst.protonum));
 
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index a75b11c39312..a55a58c706a9 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -24,7 +24,6 @@
 #include <linux/rtnetlink.h>
 
 #include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_core.h>
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 20a2e37c76d1..40152b9ad772 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -38,7 +38,6 @@
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_acct.h>
@@ -81,9 +80,26 @@ nla_put_failure:
 	return -1;
 }
 
+static int ipv4_tuple_to_nlattr(struct sk_buff *skb,
+				const struct nf_conntrack_tuple *tuple)
+{
+	if (nla_put_in_addr(skb, CTA_IP_V4_SRC, tuple->src.u3.ip) ||
+	    nla_put_in_addr(skb, CTA_IP_V4_DST, tuple->dst.u3.ip))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int ipv6_tuple_to_nlattr(struct sk_buff *skb,
+				const struct nf_conntrack_tuple *tuple)
+{
+	if (nla_put_in6_addr(skb, CTA_IP_V6_SRC, &tuple->src.u3.in6) ||
+	    nla_put_in6_addr(skb, CTA_IP_V6_DST, &tuple->dst.u3.in6))
+		return -EMSGSIZE;
+	return 0;
+}
+
 static int ctnetlink_dump_tuples_ip(struct sk_buff *skb,
-				    const struct nf_conntrack_tuple *tuple,
-				    const struct nf_conntrack_l3proto *l3proto)
+				    const struct nf_conntrack_tuple *tuple)
 {
 	int ret = 0;
 	struct nlattr *nest_parms;
@@ -92,8 +108,14 @@ static int ctnetlink_dump_tuples_ip(struct sk_buff *skb,
 	if (!nest_parms)
 		goto nla_put_failure;
 
-	if (likely(l3proto->tuple_to_nlattr))
-		ret = l3proto->tuple_to_nlattr(skb, tuple);
+	switch (tuple->src.l3num) {
+	case NFPROTO_IPV4:
+		ret = ipv4_tuple_to_nlattr(skb, tuple);
+		break;
+	case NFPROTO_IPV6:
+		ret = ipv6_tuple_to_nlattr(skb, tuple);
+		break;
+	}
 
 	nla_nest_end(skb, nest_parms);
 
@@ -106,13 +128,11 @@ nla_put_failure:
 static int ctnetlink_dump_tuples(struct sk_buff *skb,
 				 const struct nf_conntrack_tuple *tuple)
 {
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
 	int ret;
 
 	rcu_read_lock();
-	l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
-	ret = ctnetlink_dump_tuples_ip(skb, tuple, l3proto);
+	ret = ctnetlink_dump_tuples_ip(skb, tuple);
 
 	if (ret >= 0) {
 		l4proto = __nf_ct_l4proto_find(tuple->src.l3num,
@@ -556,15 +576,20 @@ nla_put_failure:
 	return -1;
 }
 
+static const struct nla_policy cta_ip_nla_policy[CTA_IP_MAX + 1] = {
+	[CTA_IP_V4_SRC]	= { .type = NLA_U32 },
+	[CTA_IP_V4_DST]	= { .type = NLA_U32 },
+	[CTA_IP_V6_SRC]	= { .len = sizeof(__be32) * 4 },
+	[CTA_IP_V6_DST]	= { .len = sizeof(__be32) * 4 },
+};
+
 #if defined(CONFIG_NETFILTER_NETLINK_GLUE_CT) || defined(CONFIG_NF_CONNTRACK_EVENTS)
 static size_t ctnetlink_proto_size(const struct nf_conn *ct)
 {
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
 	size_t len, len4 = 0;
 
-	l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
-	len = l3proto->nla_size;
+	len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1);
 	len *= 3u; /* ORIG, REPLY, MASTER */
 
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
@@ -936,29 +961,54 @@ out:
 	return skb->len;
 }
 
+static int ipv4_nlattr_to_tuple(struct nlattr *tb[],
+				struct nf_conntrack_tuple *t)
+{
+	if (!tb[CTA_IP_V4_SRC] || !tb[CTA_IP_V4_DST])
+		return -EINVAL;
+
+	t->src.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_SRC]);
+	t->dst.u3.ip = nla_get_in_addr(tb[CTA_IP_V4_DST]);
+
+	return 0;
+}
+
+static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
+				struct nf_conntrack_tuple *t)
+{
+	if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST])
+		return -EINVAL;
+
+	t->src.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_SRC]);
+	t->dst.u3.in6 = nla_get_in6_addr(tb[CTA_IP_V6_DST]);
+
+	return 0;
+}
+
 static int ctnetlink_parse_tuple_ip(struct nlattr *attr,
 				    struct nf_conntrack_tuple *tuple)
 {
 	struct nlattr *tb[CTA_IP_MAX+1];
-	struct nf_conntrack_l3proto *l3proto;
 	int ret = 0;
 
 	ret = nla_parse_nested(tb, CTA_IP_MAX, attr, NULL, NULL);
 	if (ret < 0)
 		return ret;
 
-	rcu_read_lock();
-	l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
+	ret = nla_validate_nested(attr, CTA_IP_MAX,
+				  cta_ip_nla_policy, NULL);
+	if (ret)
+		return ret;
 
-	if (likely(l3proto->nlattr_to_tuple)) {
-		ret = nla_validate_nested(attr, CTA_IP_MAX,
-					  l3proto->nla_policy, NULL);
-		if (ret == 0)
-			ret = l3proto->nlattr_to_tuple(tb, tuple);
+	switch (tuple->src.l3num) {
+	case NFPROTO_IPV4:
+		ret = ipv4_nlattr_to_tuple(tb, tuple);
+		break;
+	case NFPROTO_IPV6:
+		ret = ipv6_nlattr_to_tuple(tb, tuple);
+		break;
 	}
 
-	rcu_read_unlock();
-
 	return ret;
 }
 
@@ -2581,7 +2631,6 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb,
 				   const struct nf_conntrack_tuple *tuple,
 				   const struct nf_conntrack_tuple_mask *mask)
 {
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conntrack_tuple m;
 	struct nlattr *nest_parms;
@@ -2597,8 +2646,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb,
 		goto nla_put_failure;
 
 	rcu_read_lock();
-	l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
-	ret = ctnetlink_dump_tuples_ip(skb, &m, l3proto);
+	ret = ctnetlink_dump_tuples_ip(skb, &m);
 	if (ret >= 0) {
 		l4proto = __nf_ct_l4proto_find(tuple->src.l3num,
 					       tuple->dst.protonum);
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index d88841fbc560..859cb303bb91 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -294,10 +294,7 @@ int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto)
 
 	if (proto->l3proto >= NFPROTO_NUMPROTO)
 		return -EBUSY;
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	if (proto->tuple_to_nlattr && proto->nla_size == 0)
-		return -EINVAL;
-#endif
+
 	mutex_lock(&nf_ct_proto_mutex);
 	old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
 					lockdep_is_held(&nf_ct_proto_mutex));
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index b642c0b2495c..47b80fd0d2c3 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -24,7 +24,6 @@
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
@@ -38,10 +37,9 @@ MODULE_LICENSE("GPL");
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 void
 print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
-            const struct nf_conntrack_l3proto *l3proto,
             const struct nf_conntrack_l4proto *l4proto)
 {
-	switch (l3proto->l3proto) {
+	switch (tuple->src.l3num) {
 	case NFPROTO_IPV4:
 		seq_printf(s, "src=%pI4 dst=%pI4 ",
 			   &tuple->src.u3.ip, &tuple->dst.u3.ip);
@@ -282,7 +280,6 @@ static int ct_seq_show(struct seq_file *s, void *v)
 {
 	struct nf_conntrack_tuple_hash *hash = v;
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
 	struct net *net = seq_file_net(s);
 	int ret = 0;
@@ -303,14 +300,12 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (!net_eq(nf_ct_net(ct), net))
 		goto release;
 
-	l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
-	WARN_ON(!l3proto);
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	WARN_ON(!l4proto);
 
 	ret = -ENOSPC;
 	seq_printf(s, "%-8s %u %-8s %u ",
-		   l3proto_name(l3proto->l3proto), nf_ct_l3num(ct),
+		   l3proto_name(nf_ct_l3num(ct)), nf_ct_l3num(ct),
 		   l4proto_name(l4proto->l4proto), nf_ct_protonum(ct));
 
 	if (!test_bit(IPS_OFFLOAD_BIT, &ct->status))
@@ -320,7 +315,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 		l4proto->print_conntrack(s, ct);
 
 	print_tuple(s, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
-		    l3proto, l4proto);
+		    l4proto);
 
 	ct_show_zone(s, ct, NF_CT_ZONE_DIR_ORIG);
 
@@ -333,8 +328,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (!(test_bit(IPS_SEEN_REPLY_BIT, &ct->status)))
 		seq_puts(s, "[UNREPLIED] ");
 
-	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,
-		    l3proto, l4proto);
+	print_tuple(s, &ct->tuplehash[IP_CT_DIR_REPLY].tuple, l4proto);
 
 	ct_show_zone(s, ct, NF_CT_ZONE_DIR_REPL);
 
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 9ee5fa551fa6..9da4b8462004 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -26,7 +26,6 @@
 #include <net/sock.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_timeout.h>
-- 
cgit v1.2.3


From 47a91b14de62e35d1466820cbb4c024b6c02dff1 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:45 +0200
Subject: netfilter: conntrack: remove pkt_to_tuple indirection from l3
 protocol trackers

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_l3proto.h   |  7 -----
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 17 -----------
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 18 ------------
 net/netfilter/nf_conntrack_core.c              | 39 ++++++++++++++++++++++----
 net/netfilter/nf_conntrack_l3proto_generic.c   | 10 -------
 5 files changed, 33 insertions(+), 58 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index d07b5216a925..ece231450f30 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -24,13 +24,6 @@ struct nf_conntrack_l3proto {
 	/* size of tuple nlattr, fills a hole */
 	u16 nla_size;
 
-	/*
-	 * Try to fill in the third arg: nhoff is offset of l3 proto
-         * hdr.  Return true if possible.
-	 */
-	bool (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int nhoff,
-			     struct nf_conntrack_tuple *tuple);
-
 	/*
 	 * Invert the per-proto part of the tuple: ie. turn xmit into reply.
 	 * Some packets can't be inverted: return 0 in that case.
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 98ed12858c52..7ed56f61798b 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -38,22 +38,6 @@ struct conntrack4_net {
 	unsigned int users;
 };
 
-static bool ipv4_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
-			      struct nf_conntrack_tuple *tuple)
-{
-	const __be32 *ap;
-	__be32 _addrs[2];
-	ap = skb_header_pointer(skb, nhoff + offsetof(struct iphdr, saddr),
-				sizeof(u_int32_t) * 2, _addrs);
-	if (ap == NULL)
-		return false;
-
-	tuple->src.u3.ip = ap[0];
-	tuple->dst.u3.ip = ap[1];
-
-	return true;
-}
-
 static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
 			      const struct nf_conntrack_tuple *orig)
 {
@@ -322,7 +306,6 @@ static void ipv4_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
-	.pkt_to_tuple	 = ipv4_pkt_to_tuple,
 	.invert_tuple	 = ipv4_invert_tuple,
 	.get_l4proto	 = ipv4_get_l4proto,
 	.net_ns_get	 = ipv4_hooks_register,
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 13a660ae5799..bdb1709bb951 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -41,23 +41,6 @@ struct conntrack6_net {
 	unsigned int users;
 };
 
-static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
-			      struct nf_conntrack_tuple *tuple)
-{
-	const u_int32_t *ap;
-	u_int32_t _addrs[8];
-
-	ap = skb_header_pointer(skb, nhoff + offsetof(struct ipv6hdr, saddr),
-				sizeof(_addrs), _addrs);
-	if (ap == NULL)
-		return false;
-
-	memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
-	memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
-
-	return true;
-}
-
 static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
 			      const struct nf_conntrack_tuple *orig)
 {
@@ -307,7 +290,6 @@ static void ipv6_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
 	.l3proto		= PF_INET6,
-	.pkt_to_tuple		= ipv6_pkt_to_tuple,
 	.invert_tuple		= ipv6_invert_tuple,
 	.get_l4proto		= ipv6_get_l4proto,
 	.net_ns_get		= ipv6_hooks_register,
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index be0ab81e6b2c..66b2ebae2747 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -230,15 +230,43 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 		u_int8_t protonum,
 		struct net *net,
 		struct nf_conntrack_tuple *tuple,
-		const struct nf_conntrack_l3proto *l3proto,
 		const struct nf_conntrack_l4proto *l4proto)
 {
+	unsigned int size;
+	const __be32 *ap;
+	__be32 _addrs[8];
+
 	memset(tuple, 0, sizeof(*tuple));
 
 	tuple->src.l3num = l3num;
-	if (l3proto->pkt_to_tuple(skb, nhoff, tuple) == 0)
+	switch (l3num) {
+	case NFPROTO_IPV4:
+		nhoff += offsetof(struct iphdr, saddr);
+		size = 2 * sizeof(__be32);
+		break;
+	case NFPROTO_IPV6:
+		nhoff += offsetof(struct ipv6hdr, saddr);
+		size = sizeof(_addrs);
+		break;
+	default:
+		return true;
+	}
+
+	ap = skb_header_pointer(skb, nhoff, size, _addrs);
+	if (!ap)
 		return false;
 
+	switch (l3num) {
+	case NFPROTO_IPV4:
+		tuple->src.u3.ip = ap[0];
+		tuple->dst.u3.ip = ap[1];
+		break;
+	case NFPROTO_IPV6:
+		memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
+		memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
+		break;
+	}
+
 	tuple->dst.protonum = protonum;
 	tuple->dst.dir = IP_CT_DIR_ORIGINAL;
 
@@ -267,7 +295,7 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 	l4proto = __nf_ct_l4proto_find(l3num, protonum);
 
 	ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple,
-			      l3proto, l4proto);
+			      l4proto);
 
 	rcu_read_unlock();
 	return ret;
@@ -1318,8 +1346,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	u32 hash;
 
 	if (!nf_ct_get_tuple(skb, skb_network_offset(skb),
-			     dataoff, l3num, protonum, net, &tuple, l3proto,
-			     l4proto)) {
+			     dataoff, l3num, protonum, net, &tuple, l4proto)) {
 		pr_debug("Can't get tuple\n");
 		return 0;
 	}
@@ -1633,7 +1660,7 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 	l4proto = nf_ct_l4proto_find_get(l3num, l4num);
 
 	if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num,
-			     l4num, net, &tuple, l3proto, l4proto))
+			     l4num, net, &tuple, l4proto))
 		return -1;
 
 	if (ct->status & IPS_SRC_NAT) {
diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c
index 397e6911214f..0b01c9970e99 100644
--- a/net/netfilter/nf_conntrack_l3proto_generic.c
+++ b/net/netfilter/nf_conntrack_l3proto_generic.c
@@ -31,15 +31,6 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 
-static bool generic_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
-				 struct nf_conntrack_tuple *tuple)
-{
-	memset(&tuple->src.u3, 0, sizeof(tuple->src.u3));
-	memset(&tuple->dst.u3, 0, sizeof(tuple->dst.u3));
-
-	return true;
-}
-
 static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_tuple *orig)
 {
@@ -59,7 +50,6 @@ static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 
 struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
 	.l3proto	 = PF_UNSPEC,
-	.pkt_to_tuple	 = generic_pkt_to_tuple,
 	.invert_tuple	 = generic_invert_tuple,
 	.get_l4proto	 = generic_get_l4proto,
 };
-- 
cgit v1.2.3


From d1b6fe94941f43e4743d5fea953d16b0a001c2c6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:46 +0200
Subject: netfilter: conntrack: remove invert_tuple indirection from l3
 protocol trackers

Its simpler to just handle it directly in nf_ct_invert_tuple().
Also gets rid of need to pass l3proto pointer to resolve_conntrack().

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_core.h      |  1 -
 include/net/netfilter/nf_conntrack_l3proto.h   |  7 -------
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 10 ----------
 net/ipv4/netfilter/nf_conntrack_proto_icmp.c   |  3 +--
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 10 ----------
 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c |  3 +--
 net/netfilter/nf_conntrack_core.c              | 26 ++++++++++++++++----------
 net/netfilter/nf_conntrack_l3proto_generic.c   | 10 ----------
 8 files changed, 18 insertions(+), 52 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index d454a53ba646..35461b2d3462 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -42,7 +42,6 @@ void nf_conntrack_cleanup_end(void);
 
 bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 			const struct nf_conntrack_tuple *orig,
-			const struct nf_conntrack_l3proto *l3proto,
 			const struct nf_conntrack_l4proto *l4proto);
 
 /* Find a connection corresponding to a tuple. */
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index ece231450f30..164641c743a5 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -24,13 +24,6 @@ struct nf_conntrack_l3proto {
 	/* size of tuple nlattr, fills a hole */
 	u16 nla_size;
 
-	/*
-	 * Invert the per-proto part of the tuple: ie. turn xmit into reply.
-	 * Some packets can't be inverted: return 0 in that case.
-	 */
-	bool (*invert_tuple)(struct nf_conntrack_tuple *inverse,
-			     const struct nf_conntrack_tuple *orig);
-
 	/*
 	 * Called before tracking. 
 	 *	*dataoff: offset of protocol header (TCP, UDP,...) in skb
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 7ed56f61798b..e10e38c443ab 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -38,15 +38,6 @@ struct conntrack4_net {
 	unsigned int users;
 };
 
-static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u3.ip = orig->dst.u3.ip;
-	tuple->dst.u3.ip = orig->src.u3.ip;
-
-	return true;
-}
-
 static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    unsigned int *dataoff, u_int8_t *protonum)
 {
@@ -306,7 +297,6 @@ static void ipv4_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
-	.invert_tuple	 = ipv4_invert_tuple,
 	.get_l4proto	 = ipv4_get_l4proto,
 	.net_ns_get	 = ipv4_hooks_register,
 	.net_ns_put	 = ipv4_hooks_unregister,
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 5c15beafa711..34095949a003 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -142,8 +142,7 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
 	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&innertuple, &origtuple,
-				&nf_conntrack_l3proto_ipv4, innerproto)) {
+	if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) {
 		pr_debug("icmp_error_message: no match\n");
 		return -NF_ACCEPT;
 	}
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index bdb1709bb951..f8051fe20489 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -41,15 +41,6 @@ struct conntrack6_net {
 	unsigned int users;
 };
 
-static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_tuple *orig)
-{
-	memcpy(tuple->src.u3.ip6, orig->dst.u3.ip6, sizeof(tuple->src.u3.ip6));
-	memcpy(tuple->dst.u3.ip6, orig->src.u3.ip6, sizeof(tuple->dst.u3.ip6));
-
-	return true;
-}
-
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    unsigned int *dataoff, u_int8_t *protonum)
 {
@@ -290,7 +281,6 @@ static void ipv6_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
 	.l3proto		= PF_INET6,
-	.invert_tuple		= ipv6_invert_tuple,
 	.get_l4proto		= ipv6_get_l4proto,
 	.net_ns_get		= ipv6_hooks_register,
 	.net_ns_put		= ipv6_hooks_unregister,
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 2548e2c8aedd..8bcbc2f15bd5 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -152,8 +152,7 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
 
 	/* Ordinarily, we'd expect the inverted tupleproto, but it's
 	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&intuple, &origtuple,
-				&nf_conntrack_l3proto_ipv6, inproto)) {
+	if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) {
 		pr_debug("icmpv6_error: Can't invert tuple\n");
 		return -NF_ACCEPT;
 	}
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 66b2ebae2747..14c040805b32 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -305,14 +305,24 @@ EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr);
 bool
 nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 		   const struct nf_conntrack_tuple *orig,
-		   const struct nf_conntrack_l3proto *l3proto,
 		   const struct nf_conntrack_l4proto *l4proto)
 {
 	memset(inverse, 0, sizeof(*inverse));
 
 	inverse->src.l3num = orig->src.l3num;
-	if (l3proto->invert_tuple(inverse, orig) == 0)
-		return false;
+
+	switch (orig->src.l3num) {
+	case NFPROTO_IPV4:
+		inverse->src.u3.ip = orig->dst.u3.ip;
+		inverse->dst.u3.ip = orig->src.u3.ip;
+		break;
+	case NFPROTO_IPV6:
+		inverse->src.u3.in6 = orig->dst.u3.in6;
+		inverse->dst.u3.in6 = orig->src.u3.in6;
+		break;
+	default:
+		break;
+	}
 
 	inverse->dst.dir = !orig->dst.dir;
 
@@ -1222,7 +1232,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free);
 static noinline struct nf_conntrack_tuple_hash *
 init_conntrack(struct net *net, struct nf_conn *tmpl,
 	       const struct nf_conntrack_tuple *tuple,
-	       const struct nf_conntrack_l3proto *l3proto,
 	       const struct nf_conntrack_l4proto *l4proto,
 	       struct sk_buff *skb,
 	       unsigned int dataoff, u32 hash)
@@ -1237,7 +1246,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	struct nf_conntrack_zone tmp;
 	unsigned int *timeouts;
 
-	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l3proto, l4proto)) {
+	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) {
 		pr_debug("Can't invert tuple.\n");
 		return NULL;
 	}
@@ -1334,7 +1343,6 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 		  unsigned int dataoff,
 		  u_int16_t l3num,
 		  u_int8_t protonum,
-		  const struct nf_conntrack_l3proto *l3proto,
 		  const struct nf_conntrack_l4proto *l4proto)
 {
 	const struct nf_conntrack_zone *zone;
@@ -1356,7 +1364,7 @@ resolve_normal_ct(struct net *net, struct nf_conn *tmpl,
 	hash = hash_conntrack_raw(&tuple, net);
 	h = __nf_conntrack_find_get(net, zone, &tuple, hash);
 	if (!h) {
-		h = init_conntrack(net, tmpl, &tuple, l3proto, l4proto,
+		h = init_conntrack(net, tmpl, &tuple, l4proto,
 				   skb, dataoff, hash);
 		if (!h)
 			return 0;
@@ -1439,8 +1447,7 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 			goto out;
 	}
 repeat:
-	ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum,
-				l3proto, l4proto);
+	ret = resolve_normal_ct(net, tmpl, skb, dataoff, pf, protonum, l4proto);
 	if (ret < 0) {
 		/* Too stressed to deal. */
 		NF_CT_STAT_INC_ATOMIC(net, drop);
@@ -1497,7 +1504,6 @@ bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
 
 	rcu_read_lock();
 	ret = nf_ct_invert_tuple(inverse, orig,
-				 __nf_ct_l3proto_find(orig->src.l3num),
 				 __nf_ct_l4proto_find(orig->src.l3num,
 						      orig->dst.protonum));
 	rcu_read_unlock();
diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c
index 0b01c9970e99..d6a8fe591ccc 100644
--- a/net/netfilter/nf_conntrack_l3proto_generic.c
+++ b/net/netfilter/nf_conntrack_l3proto_generic.c
@@ -31,15 +31,6 @@
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 
-static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_tuple *orig)
-{
-	memset(&tuple->src.u3, 0, sizeof(tuple->src.u3));
-	memset(&tuple->dst.u3, 0, sizeof(tuple->dst.u3));
-
-	return true;
-}
-
 static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			       unsigned int *dataoff, u_int8_t *protonum)
 {
@@ -50,7 +41,6 @@ static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 
 struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
 	.l3proto	 = PF_UNSPEC,
-	.invert_tuple	 = generic_invert_tuple,
 	.get_l4proto	 = generic_get_l4proto,
 };
 EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic);
-- 
cgit v1.2.3


From 6816d931cab009024b68c11c4cf752f8bf9a1e32 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:47 +0200
Subject: netfilter: conntrack: remove get_l4proto indirection from l3 protocol
 trackers

Handle it in the core instead.

ipv6_skip_exthdr() is built-in even if ipv6 is a module, i.e. this
doesn't create an ipv6 dependency.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_l3proto.h   |   8 --
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c |  30 -------
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c |  29 -------
 net/netfilter/Makefile                         |   2 +-
 net/netfilter/nf_conntrack_core.c              | 108 ++++++++++++++++++++-----
 net/netfilter/nf_conntrack_l3proto_generic.c   |  46 -----------
 net/netfilter/nf_conntrack_proto.c             |   5 ++
 7 files changed, 94 insertions(+), 134 deletions(-)
 delete mode 100644 net/netfilter/nf_conntrack_l3proto_generic.c

diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
index 164641c743a5..5f160375c93a 100644
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ b/include/net/netfilter/nf_conntrack_l3proto.h
@@ -24,14 +24,6 @@ struct nf_conntrack_l3proto {
 	/* size of tuple nlattr, fills a hole */
 	u16 nla_size;
 
-	/*
-	 * Called before tracking. 
-	 *	*dataoff: offset of protocol header (TCP, UDP,...) in skb
-	 *	*protonum: protocol number
-	 */
-	int (*get_l4proto)(const struct sk_buff *skb, unsigned int nhoff,
-			   unsigned int *dataoff, u_int8_t *protonum);
-
 	/* Called when netns wants to use connection tracking */
 	int (*net_ns_get)(struct net *);
 	void (*net_ns_put)(struct net *);
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index e10e38c443ab..9fbf6c7f8ece 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -38,35 +38,6 @@ struct conntrack4_net {
 	unsigned int users;
 };
 
-static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
-			    unsigned int *dataoff, u_int8_t *protonum)
-{
-	const struct iphdr *iph;
-	struct iphdr _iph;
-
-	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
-	if (iph == NULL)
-		return -NF_ACCEPT;
-
-	/* Conntrack defragments packets, we might still see fragments
-	 * inside ICMP packets though. */
-	if (iph->frag_off & htons(IP_OFFSET))
-		return -NF_ACCEPT;
-
-	*dataoff = nhoff + (iph->ihl << 2);
-	*protonum = iph->protocol;
-
-	/* Check bogus IP headers */
-	if (*dataoff > skb->len) {
-		pr_debug("nf_conntrack_ipv4: bogus IPv4 packet: "
-			 "nhoff %u, ihl %u, skblen %u\n",
-			 nhoff, iph->ihl << 2, skb->len);
-		return -NF_ACCEPT;
-	}
-
-	return NF_ACCEPT;
-}
-
 static unsigned int ipv4_helper(void *priv,
 				struct sk_buff *skb,
 				const struct nf_hook_state *state)
@@ -297,7 +268,6 @@ static void ipv4_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
 	.l3proto	 = PF_INET,
-	.get_l4proto	 = ipv4_get_l4proto,
 	.net_ns_get	 = ipv4_hooks_register,
 	.net_ns_put	 = ipv4_hooks_unregister,
 	.me		 = THIS_MODULE,
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index f8051fe20489..37ab25645cf2 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -41,34 +41,6 @@ struct conntrack6_net {
 	unsigned int users;
 };
 
-static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
-			    unsigned int *dataoff, u_int8_t *protonum)
-{
-	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
-	__be16 frag_off;
-	int protoff;
-	u8 nexthdr;
-
-	if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
-			  &nexthdr, sizeof(nexthdr)) != 0) {
-		pr_debug("ip6_conntrack_core: can't get nexthdr\n");
-		return -NF_ACCEPT;
-	}
-	protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
-	/*
-	 * (protoff == skb->len) means the packet has not data, just
-	 * IPv6 and possibly extensions headers, but it is tracked anyway
-	 */
-	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
-		pr_debug("ip6_conntrack_core: can't find proto in pkt\n");
-		return -NF_ACCEPT;
-	}
-
-	*dataoff = protoff;
-	*protonum = nexthdr;
-	return NF_ACCEPT;
-}
-
 static unsigned int ipv6_helper(void *priv,
 				struct sk_buff *skb,
 				const struct nf_hook_state *state)
@@ -281,7 +253,6 @@ static void ipv6_hooks_unregister(struct net *net)
 
 const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
 	.l3proto		= PF_INET6,
-	.get_l4proto		= ipv6_get_l4proto,
 	.net_ns_get		= ipv6_hooks_register,
 	.net_ns_put		= ipv6_hooks_unregister,
 	.me			= THIS_MODULE,
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 44449389e527..f132ea850778 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o utils.o
 
-nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
+nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 14c040805b32..0674c6e5bfed 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -37,7 +37,6 @@
 #include <linux/rculist_nulls.h>
 
 #include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 #include <net/netfilter/nf_conntrack_helper.h>
@@ -55,6 +54,7 @@
 #include <net/netfilter/nf_nat_core.h>
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netns/hash.h>
+#include <net/ip.h>
 
 #include "nf_internals.h"
 
@@ -273,21 +273,94 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 	return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
 }
 
+static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
+			    u_int8_t *protonum)
+{
+	int dataoff = -1;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
+	const struct iphdr *iph;
+	struct iphdr _iph;
+
+	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
+	if (!iph)
+		return -1;
+
+	/* Conntrack defragments packets, we might still see fragments
+	 * inside ICMP packets though.
+	 */
+	if (iph->frag_off & htons(IP_OFFSET))
+		return -1;
+
+	dataoff = nhoff + (iph->ihl << 2);
+	*protonum = iph->protocol;
+
+	/* Check bogus IP headers */
+	if (dataoff > skb->len) {
+		pr_debug("bogus IPv4 packet: nhoff %u, ihl %u, skblen %u\n",
+			 nhoff, iph->ihl << 2, skb->len);
+		return -1;
+	}
+#endif
+	return dataoff;
+}
+
+static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
+			    u8 *protonum)
+{
+	int protoff = -1;
+#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
+	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
+	__be16 frag_off;
+	u8 nexthdr;
+
+	if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
+			  &nexthdr, sizeof(nexthdr)) != 0) {
+		pr_debug("can't get nexthdr\n");
+		return -1;
+	}
+	protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
+	/*
+	 * (protoff == skb->len) means the packet has not data, just
+	 * IPv6 and possibly extensions headers, but it is tracked anyway
+	 */
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		pr_debug("can't find proto in pkt\n");
+		return -1;
+	}
+
+	*protonum = nexthdr;
+#endif
+	return protoff;
+}
+
+static int get_l4proto(const struct sk_buff *skb,
+		       unsigned int nhoff, u8 pf, u8 *l4num)
+{
+	switch (pf) {
+	case NFPROTO_IPV4:
+		return ipv4_get_l4proto(skb, nhoff, l4num);
+	case NFPROTO_IPV6:
+		return ipv6_get_l4proto(skb, nhoff, l4num);
+	default:
+		*l4num = 0;
+		break;
+	}
+	return -1;
+}
+
 bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,
 		       u_int16_t l3num,
 		       struct net *net, struct nf_conntrack_tuple *tuple)
 {
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
-	unsigned int protoff;
-	u_int8_t protonum;
+	u8 protonum;
+	int protoff;
 	int ret;
 
 	rcu_read_lock();
 
-	l3proto = __nf_ct_l3proto_find(l3num);
-	ret = l3proto->get_l4proto(skb, nhoff, &protoff, &protonum);
-	if (ret != NF_ACCEPT) {
+	protoff = get_l4proto(skb, nhoff, l3num, &protonum);
+	if (protoff <= 0) {
 		rcu_read_unlock();
 		return false;
 	}
@@ -1397,14 +1470,12 @@ unsigned int
 nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 		struct sk_buff *skb)
 {
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conn *ct, *tmpl;
 	enum ip_conntrack_info ctinfo;
 	unsigned int *timeouts;
-	unsigned int dataoff;
 	u_int8_t protonum;
-	int ret;
+	int dataoff, ret;
 
 	tmpl = nf_ct_get(skb, &ctinfo);
 	if (tmpl || ctinfo == IP_CT_UNTRACKED) {
@@ -1418,14 +1489,12 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	}
 
 	/* rcu_read_lock()ed by nf_hook_thresh */
-	l3proto = __nf_ct_l3proto_find(pf);
-	ret = l3proto->get_l4proto(skb, skb_network_offset(skb),
-				   &dataoff, &protonum);
-	if (ret <= 0) {
+	dataoff = get_l4proto(skb, skb_network_offset(skb), pf, &protonum);
+	if (dataoff <= 0) {
 		pr_debug("not prepared to track yet or error occurred\n");
 		NF_CT_STAT_INC_ATOMIC(net, error);
 		NF_CT_STAT_INC_ATOMIC(net, invalid);
-		ret = -ret;
+		ret = NF_ACCEPT;
 		goto out;
 	}
 
@@ -1641,14 +1710,14 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
 
 static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 {
-	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
 	enum ip_conntrack_info ctinfo;
 	struct nf_nat_hook *nat_hook;
-	unsigned int dataoff, status;
+	unsigned int status;
 	struct nf_conn *ct;
+	int dataoff;
 	u16 l3num;
 	u8 l4num;
 
@@ -1657,10 +1726,9 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb)
 		return 0;
 
 	l3num = nf_ct_l3num(ct);
-	l3proto = nf_ct_l3proto_find_get(l3num);
 
-	if (l3proto->get_l4proto(skb, skb_network_offset(skb), &dataoff,
-				 &l4num) <= 0)
+	dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num);
+	if (dataoff <= 0)
 		return -1;
 
 	l4proto = nf_ct_l4proto_find_get(l3num, l4num);
diff --git a/net/netfilter/nf_conntrack_l3proto_generic.c b/net/netfilter/nf_conntrack_l3proto_generic.c
deleted file mode 100644
index d6a8fe591ccc..000000000000
--- a/net/netfilter/nf_conntrack_l3proto_generic.c
+++ /dev/null
@@ -1,46 +0,0 @@
-/*
- * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
- *
- * Based largely upon the original ip_conntrack code which
- * had the following copyright information:
- *
- * (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Author:
- *	Yasuyuki Kozakai @USAGI	<yasuyuki.kozakai@toshiba.co.jp>
- */
-
-#include <linux/types.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/icmp.h>
-#include <linux/sysctl.h>
-#include <net/ip.h>
-
-#include <linux/netfilter_ipv4.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
-#include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
-
-static int generic_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
-			       unsigned int *dataoff, u_int8_t *protonum)
-{
-	/* Never track !!! */
-	return -NF_ACCEPT;
-}
-
-
-struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
-	.l3proto	 = PF_UNSPEC,
-	.get_l4proto	 = generic_get_l4proto,
-};
-EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic);
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 859cb303bb91..39df72bb9d56 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -35,6 +35,11 @@ EXPORT_SYMBOL_GPL(nf_ct_l3protos);
 
 static DEFINE_MUTEX(nf_ct_proto_mutex);
 
+struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
+	.l3proto	 = PF_UNSPEC,
+};
+EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic);
+
 #ifdef CONFIG_SYSCTL
 static int
 nf_ct_register_sysctl(struct net *net,
-- 
cgit v1.2.3


From 8b3892ea8718920d29432328fe9544d89a429614 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:48 +0200
Subject: netfilter: conntrack: avoid calls to l4proto invert_tuple

Handle the common cases (tcp, udp, etc). in the core and only
do the indirect call for the protocols that need it (GRE for instance).

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_l4proto.h |  2 +-
 net/netfilter/nf_conntrack_core.c            |  8 +++++++-
 net/netfilter/nf_conntrack_proto_dccp.c      | 10 ----------
 net/netfilter/nf_conntrack_proto_generic.c   | 10 ----------
 net/netfilter/nf_conntrack_proto_gre.c       | 10 ----------
 net/netfilter/nf_conntrack_proto_sctp.c      | 10 ----------
 net/netfilter/nf_conntrack_proto_tcp.c       | 10 ----------
 net/netfilter/nf_conntrack_proto_udp.c       | 12 ------------
 8 files changed, 8 insertions(+), 64 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index a7220eef9aee..6a55e337a161 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -36,7 +36,7 @@ struct nf_conntrack_l4proto {
 			     struct net *net, struct nf_conntrack_tuple *tuple);
 
 	/* Invert the per-proto part of the tuple: ie. turn xmit into reply.
-	 * Some packets can't be inverted: return 0 in that case.
+	 * Only used by icmp, most protocols use a generic version.
 	 */
 	bool (*invert_tuple)(struct nf_conntrack_tuple *inverse,
 			     const struct nf_conntrack_tuple *orig);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 0674c6e5bfed..92efce69b690 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -400,7 +400,13 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
 	inverse->dst.dir = !orig->dst.dir;
 
 	inverse->dst.protonum = orig->dst.protonum;
-	return l4proto->invert_tuple(inverse, orig);
+
+	if (unlikely(l4proto->invert_tuple))
+		return l4proto->invert_tuple(inverse, orig);
+
+	inverse->src.u.all = orig->dst.u.all;
+	inverse->dst.u.all = orig->src.u.all;
+	return true;
 }
 EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);
 
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index abe647d5b8c6..05620c03f138 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -403,14 +403,6 @@ static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 	return true;
 }
 
-static bool dccp_invert_tuple(struct nf_conntrack_tuple *inv,
-			      const struct nf_conntrack_tuple *tuple)
-{
-	inv->src.u.dccp.port = tuple->dst.u.dccp.port;
-	inv->dst.u.dccp.port = tuple->src.u.dccp.port;
-	return true;
-}
-
 static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		     unsigned int dataoff, unsigned int *timeouts)
 {
@@ -865,7 +857,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = {
 	.l3proto		= AF_INET,
 	.l4proto		= IPPROTO_DCCP,
 	.pkt_to_tuple		= dccp_pkt_to_tuple,
-	.invert_tuple		= dccp_invert_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,
@@ -901,7 +892,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = {
 	.l3proto		= AF_INET6,
 	.l4proto		= IPPROTO_DCCP,
 	.pkt_to_tuple		= dccp_pkt_to_tuple,
-	.invert_tuple		= dccp_invert_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index 6c6896d21cd7..4dfe40aa9446 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -41,15 +41,6 @@ static bool generic_pkt_to_tuple(const struct sk_buff *skb,
 	return true;
 }
 
-static bool generic_invert_tuple(struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.all = 0;
-	tuple->dst.u.all = 0;
-
-	return true;
-}
-
 static unsigned int *generic_get_timeouts(struct net *net)
 {
 	return &(generic_pernet(net)->timeout);
@@ -168,7 +159,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic =
 	.l3proto		= PF_UNSPEC,
 	.l4proto		= 255,
 	.pkt_to_tuple		= generic_pkt_to_tuple,
-	.invert_tuple		= generic_invert_tuple,
 	.packet			= generic_packet,
 	.get_timeouts		= generic_get_timeouts,
 	.new			= generic_new,
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index d049ea5a3770..0bd40eb06b55 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -179,15 +179,6 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy);
 
 /* PUBLIC CONNTRACK PROTO HELPER FUNCTIONS */
 
-/* invert gre part of tuple */
-static bool gre_invert_tuple(struct nf_conntrack_tuple *tuple,
-			     const struct nf_conntrack_tuple *orig)
-{
-	tuple->dst.u.gre.key = orig->src.u.gre.key;
-	tuple->src.u.gre.key = orig->dst.u.gre.key;
-	return true;
-}
-
 /* gre hdr info to tuple */
 static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 			     struct net *net, struct nf_conntrack_tuple *tuple)
@@ -356,7 +347,6 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = {
 	.l3proto	 = AF_INET,
 	.l4proto	 = IPPROTO_GRE,
 	.pkt_to_tuple	 = gre_pkt_to_tuple,
-	.invert_tuple	 = gre_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack = gre_print_conntrack,
 #endif
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index fb9a35d16069..148957a5cf3e 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -166,14 +166,6 @@ static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 	return true;
 }
 
-static bool sctp_invert_tuple(struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.sctp.port = orig->dst.u.sctp.port;
-	tuple->dst.u.sctp.port = orig->src.u.sctp.port;
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
@@ -781,7 +773,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = {
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_SCTP,
 	.pkt_to_tuple 		= sctp_pkt_to_tuple,
-	.invert_tuple 		= sctp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif
@@ -818,7 +809,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = {
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_SCTP,
 	.pkt_to_tuple 		= sctp_pkt_to_tuple,
-	.invert_tuple 		= sctp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 8e67910185a0..03cff1e3066a 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -293,14 +293,6 @@ static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 	return true;
 }
 
-static bool tcp_invert_tuple(struct nf_conntrack_tuple *tuple,
-			     const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.tcp.port = orig->dst.u.tcp.port;
-	tuple->dst.u.tcp.port = orig->src.u.tcp.port;
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
@@ -1560,7 +1552,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_TCP,
 	.pkt_to_tuple 		= tcp_pkt_to_tuple,
-	.invert_tuple 		= tcp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
@@ -1598,7 +1589,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_TCP,
 	.pkt_to_tuple 		= tcp_pkt_to_tuple,
-	.invert_tuple 		= tcp_invert_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index fe7243970aa4..6fe2233c323a 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -55,14 +55,6 @@ static bool udp_pkt_to_tuple(const struct sk_buff *skb,
 	return true;
 }
 
-static bool udp_invert_tuple(struct nf_conntrack_tuple *tuple,
-			     const struct nf_conntrack_tuple *orig)
-{
-	tuple->src.u.udp.port = orig->dst.u.udp.port;
-	tuple->dst.u.udp.port = orig->src.u.udp.port;
-	return true;
-}
-
 static unsigned int *udp_get_timeouts(struct net *net)
 {
 	return udp_pernet(net)->timeouts;
@@ -302,7 +294,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
@@ -334,7 +325,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
@@ -366,7 +356,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
@@ -398,7 +387,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.pkt_to_tuple		= udp_pkt_to_tuple,
-	.invert_tuple		= udp_invert_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
-- 
cgit v1.2.3


From 97e08caec33a0923385b1215c3386c9ee1d07982 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:49 +0200
Subject: netfilter: conntrack: avoid l4proto pkt_to_tuple calls

Handle common protocols (udp, tcp, ..), in the core and only
do the call if needed by the l4proto tracker.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_core.c       | 16 +++++++++++++++-
 net/netfilter/nf_conntrack_proto_dccp.c | 17 -----------------
 net/netfilter/nf_conntrack_proto_sctp.c | 18 ------------------
 net/netfilter/nf_conntrack_proto_tcp.c  | 19 -------------------
 net/netfilter/nf_conntrack_proto_udp.c  | 23 -----------------------
 5 files changed, 15 insertions(+), 78 deletions(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 92efce69b690..994591fd9b96 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -235,6 +235,10 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 	unsigned int size;
 	const __be32 *ap;
 	__be32 _addrs[8];
+	struct {
+		__be16 sport;
+		__be16 dport;
+	} _inet_hdr, *inet_hdr;
 
 	memset(tuple, 0, sizeof(*tuple));
 
@@ -270,7 +274,17 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 	tuple->dst.protonum = protonum;
 	tuple->dst.dir = IP_CT_DIR_ORIGINAL;
 
-	return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
+	if (unlikely(l4proto->pkt_to_tuple))
+		return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
+
+	/* Actually only need first 4 bytes to get ports. */
+	inet_hdr = skb_header_pointer(skb, dataoff, sizeof(_inet_hdr), &_inet_hdr);
+	if (!inet_hdr)
+		return false;
+
+	tuple->src.u.udp.port = inet_hdr->sport;
+	tuple->dst.u.udp.port = inet_hdr->dport;
+	return true;
 }
 
 static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 05620c03f138..abfdce7baed5 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -388,21 +388,6 @@ static inline struct nf_dccp_net *dccp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.dccp;
 }
 
-static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			      struct net *net, struct nf_conntrack_tuple *tuple)
-{
-	struct dccp_hdr _hdr, *dh;
-
-	/* Actually only need first 4 bytes to get ports. */
-	dh = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (dh == NULL)
-		return false;
-
-	tuple->src.u.dccp.port = dh->dccph_sport;
-	tuple->dst.u.dccp.port = dh->dccph_dport;
-	return true;
-}
-
 static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		     unsigned int dataoff, unsigned int *timeouts)
 {
@@ -856,7 +841,6 @@ static struct nf_proto_net *dccp_get_net_proto(struct net *net)
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = {
 	.l3proto		= AF_INET,
 	.l4proto		= IPPROTO_DCCP,
-	.pkt_to_tuple		= dccp_pkt_to_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,
@@ -891,7 +875,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_dccp4);
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = {
 	.l3proto		= AF_INET6,
 	.l4proto		= IPPROTO_DCCP,
-	.pkt_to_tuple		= dccp_pkt_to_tuple,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
 	.get_timeouts		= dccp_get_timeouts,
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index 148957a5cf3e..b4126a842bfd 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -150,22 +150,6 @@ static inline struct nf_sctp_net *sctp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.sctp;
 }
 
-static bool sctp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			      struct net *net, struct nf_conntrack_tuple *tuple)
-{
-	const struct sctphdr *hp;
-	struct sctphdr _hdr;
-
-	/* Actually only need first 4 bytes to get ports. */
-	hp = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (hp == NULL)
-		return false;
-
-	tuple->src.u.sctp.port = hp->source;
-	tuple->dst.u.sctp.port = hp->dest;
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
@@ -772,7 +756,6 @@ static struct nf_proto_net *sctp_get_net_proto(struct net *net)
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = {
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_SCTP,
-	.pkt_to_tuple 		= sctp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif
@@ -808,7 +791,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_sctp4);
 const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = {
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_SCTP,
-	.pkt_to_tuple 		= sctp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack	= sctp_print_conntrack,
 #endif
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 03cff1e3066a..13c89fd107b2 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -276,23 +276,6 @@ static inline struct nf_tcp_net *tcp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.tcp;
 }
 
-static bool tcp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			     struct net *net, struct nf_conntrack_tuple *tuple)
-{
-	const struct tcphdr *hp;
-	struct tcphdr _hdr;
-
-	/* Actually only need first 4 bytes to get ports. */
-	hp = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (hp == NULL)
-		return false;
-
-	tuple->src.u.tcp.port = hp->source;
-	tuple->dst.u.tcp.port = hp->dest;
-
-	return true;
-}
-
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 /* Print out the private part of the conntrack. */
 static void tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
@@ -1551,7 +1534,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
 {
 	.l3proto		= PF_INET,
 	.l4proto 		= IPPROTO_TCP,
-	.pkt_to_tuple 		= tcp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
@@ -1588,7 +1570,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
 {
 	.l3proto		= PF_INET6,
 	.l4proto 		= IPPROTO_TCP,
-	.pkt_to_tuple 		= tcp_pkt_to_tuple,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 6fe2233c323a..8b435d70ffe3 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -36,25 +36,6 @@ static inline struct nf_udp_net *udp_pernet(struct net *net)
 	return &net->ct.nf_ct_proto.udp;
 }
 
-static bool udp_pkt_to_tuple(const struct sk_buff *skb,
-			     unsigned int dataoff,
-			     struct net *net,
-			     struct nf_conntrack_tuple *tuple)
-{
-	const struct udphdr *hp;
-	struct udphdr _hdr;
-
-	/* Actually only need first 4 bytes to get ports. */
-	hp = skb_header_pointer(skb, dataoff, 4, &_hdr);
-	if (hp == NULL)
-		return false;
-
-	tuple->src.u.udp.port = hp->source;
-	tuple->dst.u.udp.port = hp->dest;
-
-	return true;
-}
-
 static unsigned int *udp_get_timeouts(struct net *net)
 {
 	return udp_pernet(net)->timeouts;
@@ -293,7 +274,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 =
 	.l3proto		= PF_INET,
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
@@ -324,7 +304,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 =
 	.l3proto		= PF_INET,
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
@@ -355,7 +334,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 =
 	.l3proto		= PF_INET6,
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
@@ -386,7 +364,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 	.l3proto		= PF_INET6,
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
-	.pkt_to_tuple		= udp_pkt_to_tuple,
 	.packet			= udp_packet,
 	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
-- 
cgit v1.2.3


From c779e849608a875448f6ffc2a5c2a15523bdcd00 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:50 +0200
Subject: netfilter: conntrack: remove get_timeout() indirection

Not needed, we can have the l4trackers fetch it themselvs.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_l4proto.h   |  8 ++------
 include/net/netfilter/nf_conntrack_timeout.h   | 18 ++++--------------
 net/ipv4/netfilter/nf_conntrack_proto_icmp.c   | 16 +++++++++++-----
 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 14 ++++++++++----
 net/netfilter/nf_conntrack_core.c              | 16 ++--------------
 net/netfilter/nf_conntrack_proto_dccp.c        | 17 +++++++----------
 net/netfilter/nf_conntrack_proto_generic.c     | 22 ++++++++++++----------
 net/netfilter/nf_conntrack_proto_gre.c         | 14 ++++++++++----
 net/netfilter/nf_conntrack_proto_sctp.c        | 18 ++++++++----------
 net/netfilter/nf_conntrack_proto_tcp.c         | 23 +++++++++++------------
 net/netfilter/nf_conntrack_proto_udp.c         | 20 +++++++++++++-------
 net/netfilter/nfnetlink_cttimeout.c            | 12 ++++--------
 12 files changed, 94 insertions(+), 104 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 6a55e337a161..c7a0075d96df 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -45,13 +45,12 @@ struct nf_conntrack_l4proto {
 	int (*packet)(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts);
+		      enum ip_conntrack_info ctinfo);
 
 	/* Called when a new connection for this protocol found;
 	 * returns TRUE if it's OK.  If so, packet() called next. */
 	bool (*new)(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts);
+		    unsigned int dataoff);
 
 	/* Called when a conntrack entry is destroyed */
 	void (*destroy)(struct nf_conn *ct);
@@ -63,9 +62,6 @@ struct nf_conntrack_l4proto {
 	/* called by gc worker if table is full */
 	bool (*can_early_drop)(const struct nf_conn *ct);
 
-	/* Return the array of timeouts for this protocol. */
-	unsigned int *(*get_timeouts)(struct net *net);
-
 	/* convert protoinfo to nfnetink attributes */
 	int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla,
 			 struct nf_conn *ct);
diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 9468ab4ad12d..80ceb3d0291d 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -67,27 +67,17 @@ struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct,
 #endif
 };
 
-static inline unsigned int *
-nf_ct_timeout_lookup(struct net *net, struct nf_conn *ct,
-		     const struct nf_conntrack_l4proto *l4proto)
+static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct)
 {
+	unsigned int *timeouts = NULL;
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	struct nf_conn_timeout *timeout_ext;
-	unsigned int *timeouts;
 
 	timeout_ext = nf_ct_timeout_find(ct);
-	if (timeout_ext) {
+	if (timeout_ext)
 		timeouts = nf_ct_timeout_data(timeout_ext);
-		if (unlikely(!timeouts))
-			timeouts = l4proto->get_timeouts(net);
-	} else {
-		timeouts = l4proto->get_timeouts(net);
-	}
-
-	return timeouts;
-#else
-	return l4proto->get_timeouts(net);
 #endif
+	return timeouts;
 }
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 34095949a003..036670b38282 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -19,6 +19,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/nf_log.h>
 
@@ -80,12 +81,16 @@ static unsigned int *icmp_get_timeouts(struct net *net)
 static int icmp_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo,
-		       unsigned int *timeout)
+		       enum ip_conntrack_info ctinfo)
 {
 	/* Do not immediately delete the connection after the first
 	   successful reply to avoid excessive conntrackd traffic
 	   and also to handle correctly ICMP echo reply duplicates. */
+	unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = icmp_get_timeouts(nf_ct_net(ct));
+
 	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
 
 	return NF_ACCEPT;
@@ -93,7 +98,7 @@ static int icmp_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		     unsigned int dataoff, unsigned int *timeouts)
+		     unsigned int dataoff)
 {
 	static const u_int8_t valid_new[] = {
 		[ICMP_ECHO] = 1,
@@ -280,9 +285,11 @@ static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[],
 	struct nf_icmp_net *in = icmp_pernet(net);
 
 	if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) {
+		if (!timeout)
+			timeout = &in->timeout;
 		*timeout =
 			ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ;
-	} else {
+	} else if (timeout) {
 		/* Set default ICMP timeout. */
 		*timeout = in->timeout;
 	}
@@ -357,7 +364,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp =
 	.pkt_to_tuple		= icmp_pkt_to_tuple,
 	.invert_tuple		= icmp_invert_tuple,
 	.packet			= icmp_packet,
-	.get_timeouts		= icmp_get_timeouts,
 	.new			= icmp_new,
 	.error			= icmp_error,
 	.destroy		= NULL,
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
index 8bcbc2f15bd5..bed07b998a10 100644
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
@@ -23,6 +23,7 @@
 #include <net/netfilter/nf_conntrack_tuple.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
 #include <net/netfilter/nf_log.h>
@@ -93,9 +94,13 @@ static unsigned int *icmpv6_get_timeouts(struct net *net)
 static int icmpv6_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo,
-		       unsigned int *timeout)
+		       enum ip_conntrack_info ctinfo)
 {
+	unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = icmpv6_get_timeouts(nf_ct_net(ct));
+
 	/* Do not immediately delete the connection after the first
 	   successful reply to avoid excessive conntrackd traffic
 	   and also to handle correctly ICMP echo reply duplicates. */
@@ -106,7 +111,7 @@ static int icmpv6_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
-		       unsigned int dataoff, unsigned int *timeouts)
+		       unsigned int dataoff)
 {
 	static const u_int8_t valid_new[] = {
 		[ICMPV6_ECHO_REQUEST - 128] = 1,
@@ -280,6 +285,8 @@ static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[],
 	unsigned int *timeout = data;
 	struct nf_icmp_net *in = icmpv6_pernet(net);
 
+	if (!timeout)
+		timeout = icmpv6_get_timeouts(net);
 	if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) {
 		*timeout =
 		    ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ;
@@ -358,7 +365,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 =
 	.pkt_to_tuple		= icmpv6_pkt_to_tuple,
 	.invert_tuple		= icmpv6_invert_tuple,
 	.packet			= icmpv6_packet,
-	.get_timeouts		= icmpv6_get_timeouts,
 	.new			= icmpv6_new,
 	.error			= icmpv6_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 994591fd9b96..c069f2faff4c 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1337,7 +1337,6 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	const struct nf_conntrack_zone *zone;
 	struct nf_conn_timeout *timeout_ext;
 	struct nf_conntrack_zone tmp;
-	unsigned int *timeouts;
 
 	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) {
 		pr_debug("Can't invert tuple.\n");
@@ -1356,15 +1355,8 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 	}
 
 	timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;
-	if (timeout_ext) {
-		timeouts = nf_ct_timeout_data(timeout_ext);
-		if (unlikely(!timeouts))
-			timeouts = l4proto->get_timeouts(net);
-	} else {
-		timeouts = l4proto->get_timeouts(net);
-	}
 
-	if (!l4proto->new(ct, skb, dataoff, timeouts)) {
+	if (!l4proto->new(ct, skb, dataoff)) {
 		nf_conntrack_free(ct);
 		pr_debug("can't track with proto module\n");
 		return NULL;
@@ -1493,7 +1485,6 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 	const struct nf_conntrack_l4proto *l4proto;
 	struct nf_conn *ct, *tmpl;
 	enum ip_conntrack_info ctinfo;
-	unsigned int *timeouts;
 	u_int8_t protonum;
 	int dataoff, ret;
 
@@ -1552,10 +1543,7 @@ repeat:
 		goto out;
 	}
 
-	/* Decide what timeout policy we want to apply to this flow. */
-	timeouts = nf_ct_timeout_lookup(net, ct, l4proto);
-
-	ret = l4proto->packet(ct, skb, dataoff, ctinfo, timeouts);
+	ret = l4proto->packet(ct, skb, dataoff, ctinfo);
 	if (ret <= 0) {
 		/* Invalid: inverse of the return code tells
 		 * the netfilter core what to do */
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index abfdce7baed5..f476d116c816 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -23,6 +23,7 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_log.h>
 
 /* Timeouts are based on values from RFC4340:
@@ -389,7 +390,7 @@ static inline struct nf_dccp_net *dccp_pernet(struct net *net)
 }
 
 static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		     unsigned int dataoff, unsigned int *timeouts)
+		     unsigned int dataoff)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_dccp_net *dn;
@@ -437,19 +438,14 @@ static u64 dccp_ack_seq(const struct dccp_hdr *dh)
 		     ntohl(dhack->dccph_ack_nr_low);
 }
 
-static unsigned int *dccp_get_timeouts(struct net *net)
-{
-	return dccp_pernet(net)->dccp_timeout;
-}
-
 static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
-		       unsigned int dataoff, enum ip_conntrack_info ctinfo,
-		       unsigned int *timeouts)
+		       unsigned int dataoff, enum ip_conntrack_info ctinfo)
 {
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
 	struct dccp_hdr _dh, *dh;
 	u_int8_t type, old_state, new_state;
 	enum ct_dccp_roles role;
+	unsigned int *timeouts;
 
 	dh = skb_header_pointer(skb, dataoff, sizeof(_dh), &_dh);
 	BUG_ON(dh == NULL);
@@ -523,6 +519,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 	if (new_state != old_state)
 		nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
 
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = dccp_pernet(nf_ct_net(ct))->dccp_timeout;
 	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
 
 	return NF_ACCEPT;
@@ -843,7 +842,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp4 = {
 	.l4proto		= IPPROTO_DCCP,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
-	.get_timeouts		= dccp_get_timeouts,
 	.error			= dccp_error,
 	.can_early_drop		= dccp_can_early_drop,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
@@ -877,7 +875,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp6 = {
 	.l4proto		= IPPROTO_DCCP,
 	.new			= dccp_new,
 	.packet			= dccp_packet,
-	.get_timeouts		= dccp_get_timeouts,
 	.error			= dccp_error,
 	.can_early_drop		= dccp_can_early_drop,
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c
index 4dfe40aa9446..ac4a0b296dcd 100644
--- a/net/netfilter/nf_conntrack_proto_generic.c
+++ b/net/netfilter/nf_conntrack_proto_generic.c
@@ -11,6 +11,7 @@
 #include <linux/timer.h>
 #include <linux/netfilter.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 
 static const unsigned int nf_ct_generic_timeout = 600*HZ;
 
@@ -41,25 +42,24 @@ static bool generic_pkt_to_tuple(const struct sk_buff *skb,
 	return true;
 }
 
-static unsigned int *generic_get_timeouts(struct net *net)
-{
-	return &(generic_pernet(net)->timeout);
-}
-
 /* Returns verdict for packet, or -1 for invalid. */
 static int generic_packet(struct nf_conn *ct,
 			  const struct sk_buff *skb,
 			  unsigned int dataoff,
-			  enum ip_conntrack_info ctinfo,
-			  unsigned int *timeout)
+			  enum ip_conntrack_info ctinfo)
 {
+	const unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = &generic_pernet(nf_ct_net(ct))->timeout;
+
 	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
 	return NF_ACCEPT;
 }
 
 /* Called when a new connection for this protocol found. */
 static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb,
-			unsigned int dataoff, unsigned int *timeouts)
+			unsigned int dataoff)
 {
 	bool ret;
 
@@ -78,8 +78,11 @@ static bool generic_new(struct nf_conn *ct, const struct sk_buff *skb,
 static int generic_timeout_nlattr_to_obj(struct nlattr *tb[],
 					 struct net *net, void *data)
 {
-	unsigned int *timeout = data;
 	struct nf_generic_net *gn = generic_pernet(net);
+	unsigned int *timeout = data;
+
+	if (!timeout)
+		timeout = &gn->timeout;
 
 	if (tb[CTA_TIMEOUT_GENERIC_TIMEOUT])
 		*timeout =
@@ -160,7 +163,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic =
 	.l4proto		= 255,
 	.pkt_to_tuple		= generic_pkt_to_tuple,
 	.packet			= generic_packet,
-	.get_timeouts		= generic_get_timeouts,
 	.new			= generic_new,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
 	.ctnl_timeout		= {
diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c
index 0bd40eb06b55..d1632252bf5b 100644
--- a/net/netfilter/nf_conntrack_proto_gre.c
+++ b/net/netfilter/nf_conntrack_proto_gre.c
@@ -39,6 +39,7 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 #include <linux/netfilter/nf_conntrack_pptp.h>
 
@@ -234,8 +235,7 @@ static unsigned int *gre_get_timeouts(struct net *net)
 static int gre_packet(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts)
+		      enum ip_conntrack_info ctinfo)
 {
 	/* If we've seen traffic both ways, this is a GRE connection.
 	 * Extend timeout. */
@@ -254,8 +254,13 @@ static int gre_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool gre_new(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts)
+		    unsigned int dataoff)
 {
+	unsigned int *timeouts = nf_ct_timeout_lookup(ct);
+
+	if (!timeouts)
+		timeouts = gre_get_timeouts(nf_ct_net(ct));
+
 	pr_debug(": ");
 	nf_ct_dump_tuple(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 
@@ -291,6 +296,8 @@ static int gre_timeout_nlattr_to_obj(struct nlattr *tb[],
 	unsigned int *timeouts = data;
 	struct netns_proto_gre *net_gre = gre_pernet(net);
 
+	if (!timeouts)
+		timeouts = gre_get_timeouts(net);
 	/* set default timeouts for GRE. */
 	timeouts[GRE_CT_UNREPLIED] = net_gre->gre_timeouts[GRE_CT_UNREPLIED];
 	timeouts[GRE_CT_REPLIED] = net_gre->gre_timeouts[GRE_CT_REPLIED];
@@ -350,7 +357,6 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = {
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	.print_conntrack = gre_print_conntrack,
 #endif
-	.get_timeouts    = gre_get_timeouts,
 	.packet		 = gre_packet,
 	.new		 = gre_new,
 	.destroy	 = gre_destroy,
diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c
index b4126a842bfd..8d1e085fc14a 100644
--- a/net/netfilter/nf_conntrack_proto_sctp.c
+++ b/net/netfilter/nf_conntrack_proto_sctp.c
@@ -28,6 +28,7 @@
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 
 /* FIXME: Examine ipfilter's timeouts and conntrack transitions more
    closely.  They're more complex. --RR
@@ -272,17 +273,11 @@ static int sctp_new_state(enum ip_conntrack_dir dir,
 	return sctp_conntracks[dir][i][cur_state];
 }
 
-static unsigned int *sctp_get_timeouts(struct net *net)
-{
-	return sctp_pernet(net)->timeouts;
-}
-
 /* Returns verdict for packet, or -NF_ACCEPT for invalid. */
 static int sctp_packet(struct nf_conn *ct,
 		       const struct sk_buff *skb,
 		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo,
-		       unsigned int *timeouts)
+		       enum ip_conntrack_info ctinfo)
 {
 	enum sctp_conntrack new_state, old_state;
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -291,6 +286,7 @@ static int sctp_packet(struct nf_conn *ct,
 	const struct sctp_chunkhdr *sch;
 	struct sctp_chunkhdr _sch;
 	u_int32_t offset, count;
+	unsigned int *timeouts;
 	unsigned long map[256 / sizeof(unsigned long)] = { 0 };
 
 	sh = skb_header_pointer(skb, dataoff, sizeof(_sctph), &_sctph);
@@ -379,6 +375,10 @@ static int sctp_packet(struct nf_conn *ct,
 	}
 	spin_unlock_bh(&ct->lock);
 
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = sctp_pernet(nf_ct_net(ct))->timeouts;
+
 	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
 
 	if (old_state == SCTP_CONNTRACK_COOKIE_ECHOED &&
@@ -399,7 +399,7 @@ out:
 
 /* Called when a new connection for this protocol found. */
 static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		     unsigned int dataoff, unsigned int *timeouts)
+		     unsigned int dataoff)
 {
 	enum sctp_conntrack new_state;
 	const struct sctphdr *sh;
@@ -760,7 +760,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp4 = {
 	.print_conntrack	= sctp_print_conntrack,
 #endif
 	.packet 		= sctp_packet,
-	.get_timeouts		= sctp_get_timeouts,
 	.new 			= sctp_new,
 	.error			= sctp_error,
 	.can_early_drop		= sctp_can_early_drop,
@@ -795,7 +794,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp6 = {
 	.print_conntrack	= sctp_print_conntrack,
 #endif
 	.packet 		= sctp_packet,
-	.get_timeouts		= sctp_get_timeouts,
 	.new 			= sctp_new,
 	.error			= sctp_error,
 	.can_early_drop		= sctp_can_early_drop,
diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c
index 13c89fd107b2..d80d322b9d8b 100644
--- a/net/netfilter/nf_conntrack_proto_tcp.c
+++ b/net/netfilter/nf_conntrack_proto_tcp.c
@@ -29,6 +29,7 @@
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/nf_conntrack_synproxy.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_log.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
@@ -768,27 +769,21 @@ static int tcp_error(struct net *net, struct nf_conn *tmpl,
 	return NF_ACCEPT;
 }
 
-static unsigned int *tcp_get_timeouts(struct net *net)
-{
-	return tcp_pernet(net)->timeouts;
-}
-
 /* Returns verdict for packet, or -1 for invalid. */
 static int tcp_packet(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts)
+		      enum ip_conntrack_info ctinfo)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_tcp_net *tn = tcp_pernet(net);
 	struct nf_conntrack_tuple *tuple;
 	enum tcp_conntrack new_state, old_state;
+	unsigned int index, *timeouts;
 	enum ip_conntrack_dir dir;
 	const struct tcphdr *th;
 	struct tcphdr _tcph;
 	unsigned long timeout;
-	unsigned int index;
 
 	th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
 	BUG_ON(th == NULL);
@@ -1021,6 +1016,10 @@ static int tcp_packet(struct nf_conn *ct,
 	    && new_state == TCP_CONNTRACK_FIN_WAIT)
 		ct->proto.tcp.seen[dir].flags |= IP_CT_TCP_FLAG_CLOSE_INIT;
 
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = tn->timeouts;
+
 	if (ct->proto.tcp.retrans >= tn->tcp_max_retrans &&
 	    timeouts[new_state] > timeouts[TCP_CONNTRACK_RETRANS])
 		timeout = timeouts[TCP_CONNTRACK_RETRANS];
@@ -1070,7 +1069,7 @@ static int tcp_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts)
+		    unsigned int dataoff)
 {
 	enum tcp_conntrack new_state;
 	const struct tcphdr *th;
@@ -1288,10 +1287,12 @@ static unsigned int tcp_nlattr_tuple_size(void)
 static int tcp_timeout_nlattr_to_obj(struct nlattr *tb[],
 				     struct net *net, void *data)
 {
-	unsigned int *timeouts = data;
 	struct nf_tcp_net *tn = tcp_pernet(net);
+	unsigned int *timeouts = data;
 	int i;
 
+	if (!timeouts)
+		timeouts = tn->timeouts;
 	/* set default TCP timeouts. */
 	for (i=0; i<TCP_CONNTRACK_TIMEOUT_MAX; i++)
 		timeouts[i] = tn->timeouts[i];
@@ -1538,7 +1539,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4 =
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
 	.packet 		= tcp_packet,
-	.get_timeouts		= tcp_get_timeouts,
 	.new 			= tcp_new,
 	.error			= tcp_error,
 	.can_early_drop		= tcp_can_early_drop,
@@ -1574,7 +1574,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp6 =
 	.print_conntrack 	= tcp_print_conntrack,
 #endif
 	.packet 		= tcp_packet,
-	.get_timeouts		= tcp_get_timeouts,
 	.new 			= tcp_new,
 	.error			= tcp_error,
 	.can_early_drop		= tcp_can_early_drop,
diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c
index 8b435d70ffe3..7a1b8988a931 100644
--- a/net/netfilter/nf_conntrack_proto_udp.c
+++ b/net/netfilter/nf_conntrack_proto_udp.c
@@ -22,6 +22,7 @@
 #include <linux/netfilter_ipv6.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
 #include <net/netfilter/nf_log.h>
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
@@ -45,9 +46,14 @@ static unsigned int *udp_get_timeouts(struct net *net)
 static int udp_packet(struct nf_conn *ct,
 		      const struct sk_buff *skb,
 		      unsigned int dataoff,
-		      enum ip_conntrack_info ctinfo,
-		      unsigned int *timeouts)
+		      enum ip_conntrack_info ctinfo)
 {
+	unsigned int *timeouts;
+
+	timeouts = nf_ct_timeout_lookup(ct);
+	if (!timeouts)
+		timeouts = udp_get_timeouts(nf_ct_net(ct));
+
 	/* If we've seen traffic both ways, this is some kind of UDP
 	   stream.  Extend timeout. */
 	if (test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
@@ -65,7 +71,7 @@ static int udp_packet(struct nf_conn *ct,
 
 /* Called when a new connection for this protocol found. */
 static bool udp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		    unsigned int dataoff, unsigned int *timeouts)
+		    unsigned int dataoff)
 {
 	return true;
 }
@@ -176,6 +182,9 @@ static int udp_timeout_nlattr_to_obj(struct nlattr *tb[],
 	unsigned int *timeouts = data;
 	struct nf_udp_net *un = udp_pernet(net);
 
+	if (!timeouts)
+		timeouts = un->timeouts;
+
 	/* set default timeouts for UDP. */
 	timeouts[UDP_CT_UNREPLIED] = un->timeouts[UDP_CT_UNREPLIED];
 	timeouts[UDP_CT_REPLIED] = un->timeouts[UDP_CT_REPLIED];
@@ -275,7 +284,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udp_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
@@ -305,7 +313,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite4 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udplite_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
@@ -335,7 +342,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp6 =
 	.l4proto		= IPPROTO_UDP,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udp_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
@@ -365,7 +371,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 	.l4proto		= IPPROTO_UDPLITE,
 	.allow_clash		= true,
 	.packet			= udp_packet,
-	.get_timeouts		= udp_get_timeouts,
 	.new			= udp_new,
 	.error			= udplite_error,
 #if IS_ENABLED(CONFIG_NF_CT_NETLINK)
@@ -388,3 +393,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite6 =
 };
 EXPORT_SYMBOL_GPL(nf_conntrack_l4proto_udplite6);
 #endif
+#include <net/netfilter/nf_conntrack_timeout.h>
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 9da4b8462004..d9d952fad3e0 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -46,7 +46,7 @@ static const struct nla_policy cttimeout_nla_policy[CTA_TIMEOUT_MAX+1] = {
 };
 
 static int
-ctnl_timeout_parse_policy(void *timeouts,
+ctnl_timeout_parse_policy(void *timeout,
 			  const struct nf_conntrack_l4proto *l4proto,
 			  struct net *net, const struct nlattr *attr)
 {
@@ -67,7 +67,7 @@ ctnl_timeout_parse_policy(void *timeouts,
 	if (ret < 0)
 		goto err;
 
-	ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeouts);
+	ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeout);
 
 err:
 	kfree(tb);
@@ -372,7 +372,6 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl,
 				 struct netlink_ext_ack *extack)
 {
 	const struct nf_conntrack_l4proto *l4proto;
-	unsigned int *timeouts;
 	__u16 l3num;
 	__u8 l4num;
 	int ret;
@@ -392,9 +391,7 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl,
 		goto err;
 	}
 
-	timeouts = l4proto->get_timeouts(net);
-
-	ret = ctnl_timeout_parse_policy(timeouts, l4proto, net,
+	ret = ctnl_timeout_parse_policy(NULL, l4proto, net,
 					cda[CTA_TIMEOUT_DATA]);
 	if (ret < 0)
 		goto err;
@@ -431,7 +428,6 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 
 	if (likely(l4proto->ctnl_timeout.obj_to_nlattr)) {
 		struct nlattr *nest_parms;
-		unsigned int *timeouts = l4proto->get_timeouts(net);
 		int ret;
 
 		nest_parms = nla_nest_start(skb,
@@ -439,7 +435,7 @@ cttimeout_default_fill_info(struct net *net, struct sk_buff *skb, u32 portid,
 		if (!nest_parms)
 			goto nla_put_failure;
 
-		ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, timeouts);
+		ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, NULL);
 		if (ret < 0)
 			goto nla_put_failure;
 
-- 
cgit v1.2.3


From 21279157efffe5e7258483809942d576cb802768 Mon Sep 17 00:00:00 2001
From: Jiang Biao <jiang.biao2@zte.com.cn>
Date: Mon, 16 Jul 2018 12:03:38 +0800
Subject: x86/pti: Make pti_set_kernel_image_nonglobal() static

pti_set_kernel_image_nonglobal() is only used in pti.c, make it static.

Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: luto@kernel.org
Cc: hpa@zytor.com
Cc: albcamus@gmail.com
Cc: zhong.weidong@zte.com.cn
Link: https://lkml.kernel.org/r/1531713820-24544-4-git-send-email-jiang.biao2@zte.com.cn
---
 arch/x86/mm/pti.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 4d418e705878..9277e9ba92b5 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -466,7 +466,7 @@ void pti_clone_kernel_text(void)
  * the other set_memory.h functions.  Just extern it.
  */
 extern int set_memory_nonglobal(unsigned long addr, int numpages);
-void pti_set_kernel_image_nonglobal(void)
+static void pti_set_kernel_image_nonglobal(void)
 {
 	/*
 	 * The identity map is created with PMDs, regardless of the
-- 
cgit v1.2.3


From d607eefa3b55c7b8cd9902e9209fc1235f88ccd9 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Mon, 16 Jul 2018 12:12:22 -0400
Subject: blk-iolatency: don't change the latency window

Early versions of these patches had us waiting for seconds at a time
during submission, so we had to adjust the timing window we monitored
for latency.  Now we don't do things like that so this is unnecessary
code.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iolatency.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index b59e5451680b..893f888eebb1 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -468,16 +468,6 @@ static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
 	}
 	preempt_enable();
 
-	/*
-	 * Our average exceeded our window, scale up our window so we are more
-	 * accurate, but not more than the global timer.
-	 */
-	if (stat.mean > iolat->cur_win_nsec) {
-		iolat->cur_win_nsec <<= 1;
-		iolat->cur_win_nsec =
-			max_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC);
-	}
-
 	parent = blkg_to_lat(blkg->parent);
 	if (!parent)
 		return;
-- 
cgit v1.2.3


From 71e9690b59e7349156025a514c29c29ef55b0175 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Mon, 16 Jul 2018 12:12:23 -0400
Subject: blk-iolatency: truncate our current time

In our longer tests we noticed that some boxes would degrade to the
point of uselessness.  This is because we truncate the current time when
saving it in our bio, but I was using the raw current time to subtract
from.  So once the box had been up a certain amount of time it would
appear as if our IO's were taking several years to complete.  Fix this
by truncating the current time so it matches the issue time.  Verified
this worked by running with this patch for a week on our test tier.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iolatency.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index 893f888eebb1..bb59b2929e0d 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -425,6 +425,12 @@ static void iolatency_record_time(struct iolatency_grp *iolat,
 	u64 start = bio_issue_time(issue);
 	u64 req_time;
 
+	/*
+	 * Have to do this so we are truncated to the correct time that our
+	 * issue is truncated to.
+	 */
+	now = __bio_issue_time(now);
+
 	if (now <= start)
 		return;
 
-- 
cgit v1.2.3


From 0051163ab3d8090a08ea2ea5edbb738c0920000a Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 16 Jul 2018 13:54:24 +0100
Subject: drm/i915/execlists: Always clear preempt status on cancelling all

On reset/wedging, we cancel all pending replies from the HW and we also
want to cancel an outstanding preemption event. Since we use the same
function to cancel the pending replies for reset and for a preemption
event, we can simply clear the active tracking for all.

v2: Keep execlists_user_end() markup for wedging
v3: Move assignment to inline to hide the bare assignment.

Fixes: 60a943245413 ("drm/i915/execlists: Drop clear_gtiir() on GPU reset")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716125424.5715-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 2 --
 drivers/gpu/drm/i915/intel_lrc.c            | 6 ++----
 drivers/gpu/drm/i915/intel_ringbuffer.h     | 6 ++++++
 3 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index cc444dc5f3ad..94d0674ea3c6 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -633,8 +633,6 @@ static void complete_preempt_context(struct intel_engine_cs *engine)
 
 	wait_for_guc_preempt_report(engine);
 	intel_write_status_page(engine, I915_GEM_HWS_PREEMPT_INDEX, 0);
-
-	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index 629127e03577..c0ee14f86754 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -563,8 +563,6 @@ static void complete_preempt_context(struct intel_engine_execlists *execlists)
 	__unwind_incomplete_requests(container_of(execlists,
 						  struct intel_engine_cs,
 						  execlists));
-
-	execlists_clear_active(execlists, EXECLISTS_ACTIVE_PREEMPT);
 }
 
 static void execlists_dequeue(struct intel_engine_cs *engine)
@@ -792,8 +790,7 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
 		port++;
 	}
 
-	execlists_clear_active(execlists, EXECLISTS_ACTIVE_USER);
-	execlists_user_end(execlists);
+	execlists_clear_all_active(execlists);
 }
 
 static void reset_csb_pointers(struct intel_engine_execlists *execlists)
@@ -844,6 +841,7 @@ static void execlists_cancel_requests(struct intel_engine_cs *engine)
 
 	/* Cancel the requests on the HW and clear the ELSP tracker. */
 	execlists_cancel_port_requests(execlists);
+	execlists_user_end(execlists);
 
 	/* Mark all executing requests as skipped. */
 	list_for_each_entry(rq, &engine->timeline.requests, link) {
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index d1eee08e5f6b..665b59ba1f45 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -683,6 +683,12 @@ execlists_clear_active(struct intel_engine_execlists *execlists,
 	__clear_bit(bit, (unsigned long *)&execlists->active);
 }
 
+static inline void
+execlists_clear_all_active(struct intel_engine_execlists *execlists)
+{
+	execlists->active = 0;
+}
+
 static inline bool
 execlists_is_active(const struct intel_engine_execlists *execlists,
 		    unsigned int bit)
-- 
cgit v1.2.3


From 0f6b79fa138d781b978bcff22680662fd351cd2d Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 16 Jul 2018 14:21:54 +0100
Subject: drm/i915/selftests: Force a preemption hang

Inject a failure into preemption completion to pretend as if the HW
didn't successfully handle preemption and we are forced to do a reset in
the middle.

v2: Wait for preemption, to force testing with the missed preemption.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716132154.12539-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c |   3 +
 drivers/gpu/drm/i915/intel_lrc.c            |   3 +
 drivers/gpu/drm/i915/intel_ringbuffer.h     |  27 +++++++
 drivers/gpu/drm/i915/selftests/intel_lrc.c  | 115 ++++++++++++++++++++++++++++
 4 files changed, 148 insertions(+)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 94d0674ea3c6..0fa1eb0bfff5 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -628,6 +628,9 @@ static void complete_preempt_context(struct intel_engine_cs *engine)
 
 	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
 
+	if (inject_preempt_hang(execlists))
+		return;
+
 	execlists_cancel_port_requests(execlists);
 	execlists_unwind_incomplete_requests(execlists);
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c0ee14f86754..db5351e6a3a5 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -559,6 +559,9 @@ static void complete_preempt_context(struct intel_engine_execlists *execlists)
 {
 	GEM_BUG_ON(!execlists_is_active(execlists, EXECLISTS_ACTIVE_PREEMPT));
 
+	if (inject_preempt_hang(execlists))
+		return;
+
 	execlists_cancel_port_requests(execlists);
 	__unwind_incomplete_requests(container_of(execlists,
 						  struct intel_engine_cs,
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 665b59ba1f45..f5ffa6d31e82 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -193,6 +193,11 @@ struct i915_priolist {
 	int priority;
 };
 
+struct st_preempt_hang {
+	struct completion completion;
+	bool inject_hang;
+};
+
 /**
  * struct intel_engine_execlists - execlist submission queue and port state
  *
@@ -333,6 +338,8 @@ struct intel_engine_execlists {
 	 * @csb_head: context status buffer head
 	 */
 	u8 csb_head;
+
+	I915_SELFTEST_DECLARE(struct st_preempt_hang preempt_hang;)
 };
 
 #define INTEL_ENGINE_CS_MAX_NAME 8
@@ -1155,4 +1162,24 @@ void intel_disable_engine_stats(struct intel_engine_cs *engine);
 
 ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine);
 
+#if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
+
+static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
+{
+	if (!execlists->preempt_hang.inject_hang)
+		return false;
+
+	complete(&execlists->preempt_hang.completion);
+	return true;
+}
+
+#else
+
+static inline bool inject_preempt_hang(struct intel_engine_execlists *execlists)
+{
+	return false;
+}
+
+#endif
+
 #endif /* _INTEL_RINGBUFFER_H_ */
diff --git a/drivers/gpu/drm/i915/selftests/intel_lrc.c b/drivers/gpu/drm/i915/selftests/intel_lrc.c
index 636cb68191e3..582566faef09 100644
--- a/drivers/gpu/drm/i915/selftests/intel_lrc.c
+++ b/drivers/gpu/drm/i915/selftests/intel_lrc.c
@@ -451,12 +451,127 @@ err_wedged:
 	goto err_ctx_lo;
 }
 
+static int live_preempt_hang(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx_hi, *ctx_lo;
+	struct spinner spin_hi, spin_lo;
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+	int err = -ENOMEM;
+
+	if (!HAS_LOGICAL_RING_PREEMPTION(i915))
+		return 0;
+
+	if (!intel_has_reset_engine(i915))
+		return 0;
+
+	mutex_lock(&i915->drm.struct_mutex);
+
+	if (spinner_init(&spin_hi, i915))
+		goto err_unlock;
+
+	if (spinner_init(&spin_lo, i915))
+		goto err_spin_hi;
+
+	ctx_hi = kernel_context(i915);
+	if (!ctx_hi)
+		goto err_spin_lo;
+	ctx_hi->sched.priority = I915_CONTEXT_MAX_USER_PRIORITY;
+
+	ctx_lo = kernel_context(i915);
+	if (!ctx_lo)
+		goto err_ctx_hi;
+	ctx_lo->sched.priority = I915_CONTEXT_MIN_USER_PRIORITY;
+
+	for_each_engine(engine, i915, id) {
+		struct i915_request *rq;
+
+		if (!intel_engine_has_preemption(engine))
+			continue;
+
+		rq = spinner_create_request(&spin_lo, ctx_lo, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		i915_request_add(rq);
+		if (!wait_for_spinner(&spin_lo, rq)) {
+			GEM_TRACE("lo spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		rq = spinner_create_request(&spin_hi, ctx_hi, engine,
+					    MI_ARB_CHECK);
+		if (IS_ERR(rq)) {
+			spinner_end(&spin_lo);
+			err = PTR_ERR(rq);
+			goto err_ctx_lo;
+		}
+
+		init_completion(&engine->execlists.preempt_hang.completion);
+		engine->execlists.preempt_hang.inject_hang = true;
+
+		i915_request_add(rq);
+
+		if (!wait_for_completion_timeout(&engine->execlists.preempt_hang.completion,
+						 HZ / 10)) {
+			pr_err("Preemption did not occur within timeout!");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		set_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+		i915_reset_engine(engine, NULL);
+		clear_bit(I915_RESET_ENGINE + id, &i915->gpu_error.flags);
+
+		engine->execlists.preempt_hang.inject_hang = false;
+
+		if (!wait_for_spinner(&spin_hi, rq)) {
+			GEM_TRACE("hi spinner failed to start\n");
+			GEM_TRACE_DUMP();
+			i915_gem_set_wedged(i915);
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+
+		spinner_end(&spin_hi);
+		spinner_end(&spin_lo);
+		if (igt_flush_test(i915, I915_WAIT_LOCKED)) {
+			err = -EIO;
+			goto err_ctx_lo;
+		}
+	}
+
+	err = 0;
+err_ctx_lo:
+	kernel_context_close(ctx_lo);
+err_ctx_hi:
+	kernel_context_close(ctx_hi);
+err_spin_lo:
+	spinner_fini(&spin_lo);
+err_spin_hi:
+	spinner_fini(&spin_hi);
+err_unlock:
+	igt_flush_test(i915, I915_WAIT_LOCKED);
+	mutex_unlock(&i915->drm.struct_mutex);
+	return err;
+}
+
 int intel_execlists_live_selftests(struct drm_i915_private *i915)
 {
 	static const struct i915_subtest tests[] = {
 		SUBTEST(live_sanitycheck),
 		SUBTEST(live_preempt),
 		SUBTEST(live_late_preempt),
+		SUBTEST(live_preempt_hang),
 	};
 
 	if (!HAS_EXECLISTS(i915))
-- 
cgit v1.2.3


From 2d4bc57348e157dbb0a76f37a398ab32f60c2586 Mon Sep 17 00:00:00 2001
From: Anthony Brandon <anthony@amarulasolutions.com>
Date: Mon, 9 Jul 2018 19:46:43 +0200
Subject: dt-bindings: sound: wm8994: document wlf,spkmode-pu property

Add the wlf,spkmode-pu property to control the Speaker Mode pull-up from
the device tree.

Signed-off-by: Anthony Brandon <anthony@amarulasolutions.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/sound/wm8994.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index 4a9dead1b7d3..b74a221455f7 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -57,6 +57,9 @@ Optional properties:
 
   - wlf,ldoena-always-driven : If present LDOENA is always driven.
 
+  - wlf,spkmode-pu : If present enable the internal pull-up resistor on
+    the SPKMODE pin.
+
 Example:
 
 wm8994: codec@1a {
-- 
cgit v1.2.3


From 3a6372daddebbc34ef8dd51771da8f08f060b19d Mon Sep 17 00:00:00 2001
From: Anthony Brandon <anthony@amarulasolutions.com>
Date: Mon, 9 Jul 2018 19:46:45 +0200
Subject: dt-bindings: sound: wm8994: document wlf,csnaddr-pd property

Add the wlf,csnaddr-pd property to allow the CS/Addr pull-down to be
controlled from the device tree.

Signed-off-by: Anthony Brandon <anthony@amarulasolutions.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/sound/wm8994.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index b74a221455f7..0795931c38a2 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -60,6 +60,9 @@ Optional properties:
   - wlf,spkmode-pu : If present enable the internal pull-up resistor on
     the SPKMODE pin.
 
+  - wlf,csnaddr-pd : If present enable the internal pull-down resistor on
+    the CS/ADDR pin.
+
 Example:
 
 wm8994: codec@1a {
-- 
cgit v1.2.3


From 26094c02934e9aceee8f7386a8e28190262a69d3 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 11 Jul 2018 17:30:25 -0500
Subject: drm/amdgpu/pp: remove dead vega12 code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commented out.

Reviewed-by: Rex Zhu <rezhu@amd.com>
Acked-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c   | 29 ----------------------
 1 file changed, 29 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index 7d9b40e8b1bf..508a262fb328 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -343,29 +343,6 @@ static int vega12_set_tools_address(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-#if 0 /* tentatively remove */
-static int vega12_verify_smc_interface(struct pp_hwmgr *hwmgr)
-{
-	uint32_t smc_driver_if_version;
-
-	PP_ASSERT_WITH_CODE(!vega12_send_msg_to_smc(hwmgr,
-			PPSMC_MSG_GetDriverIfVersion),
-			"Attempt to get SMC IF Version Number Failed!",
-			return -EINVAL);
-	vega12_read_arg_from_smc(hwmgr, &smc_driver_if_version);
-
-	if (smc_driver_if_version != SMU9_DRIVER_IF_VERSION) {
-		pr_err("Your firmware(0x%x) doesn't match \
-			SMU9_DRIVER_IF_VERSION(0x%x). \
-			Please update your firmware!\n",
-			smc_driver_if_version, SMU9_DRIVER_IF_VERSION);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-#endif
-
 static int vega12_smu_init(struct pp_hwmgr *hwmgr)
 {
 	struct vega12_smumgr *priv;
@@ -517,12 +494,6 @@ static int vega12_start_smu(struct pp_hwmgr *hwmgr)
 			"SMC is not running!",
 			return -EINVAL);
 
-#if 0 /* tentatively remove */
-	PP_ASSERT_WITH_CODE(!vega12_verify_smc_interface(hwmgr),
-			"Failed to verify SMC interface!",
-			return -EINVAL);
-#endif
-
 	vega12_set_tools_address(hwmgr);
 
 	return 0;
-- 
cgit v1.2.3


From ce7577a2194b58bf7faf303612a24b7cd5210afc Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 12 Jul 2018 14:47:30 -0500
Subject: drm/amdgpu/pp: split out common smumgr smu9 code

Split out the shared smumgr code for vega10 and 12
so we don't have duplicate code for both.

Reviewed-by: Rex Zhu <rezhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c |  44 ++---
 .../gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c   |   8 +-
 drivers/gpu/drm/amd/powerplay/smumgr/Makefile      |   2 +-
 drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c | 150 ++++++++++++++++
 drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h |  32 ++++
 .../gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c   | 168 ++----------------
 .../gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c   | 191 +++------------------
 .../gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h   |   1 -
 8 files changed, 242 insertions(+), 354 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
 create mode 100644 drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index c0ceb69a23b0..912d0d6cf476 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -477,7 +477,7 @@ static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
 			"[GetNumOfDpmLevel] failed to get dpm levels!",
 			return ret);
 
-	vega12_read_arg_from_smc(hwmgr, num_of_levels);
+	*num_of_levels = smum_get_argument(hwmgr);
 	PP_ASSERT_WITH_CODE(*num_of_levels > 0,
 			"[GetNumOfDpmLevel] number of clk levels is invalid!",
 			return -EINVAL);
@@ -499,11 +499,7 @@ static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		"[GetDpmFrequencyByIndex] Failed to get dpm frequency from SMU!",
 		return -EINVAL);
 
-	result = vega12_read_arg_from_smc(hwmgr, clock);
-
-	PP_ASSERT_WITH_CODE(*clock != 0,
-		"[GetDPMFrequencyByIndex] Failed to get dpm frequency by index.!",
-		return -EINVAL);
+	*clock = smum_get_argument(hwmgr);
 
 	return result;
 }
@@ -884,21 +880,21 @@ static int vega12_get_all_clock_ranges_helper(struct pp_hwmgr *hwmgr,
 		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMaxDpmFreq, (clkid << 16)) == 0,
 		"[GetClockRanges] Failed to get max ac clock from SMC!",
 		return -EINVAL);
-	vega12_read_arg_from_smc(hwmgr, &(clock->ACMax));
+	clock->ACMax = smum_get_argument(hwmgr);
 
 	/* AC Min */
 	PP_ASSERT_WITH_CODE(
 		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetMinDpmFreq, (clkid << 16)) == 0,
 		"[GetClockRanges] Failed to get min ac clock from SMC!",
 		return -EINVAL);
-	vega12_read_arg_from_smc(hwmgr, &(clock->ACMin));
+	clock->ACMin = smum_get_argument(hwmgr);
 
 	/* DC Max */
 	PP_ASSERT_WITH_CODE(
 		smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDcModeMaxDpmFreq, (clkid << 16)) == 0,
 		"[GetClockRanges] Failed to get max dc clock from SMC!",
 		return -EINVAL);
-	vega12_read_arg_from_smc(hwmgr, &(clock->DCMax));
+	clock->DCMax = smum_get_argument(hwmgr);
 
 	return 0;
 }
@@ -1219,7 +1215,7 @@ static int vega12_get_gpu_power(struct pp_hwmgr *hwmgr, uint32_t *query)
 			"Failed to get current package power!",
 			return -EINVAL);
 
-	vega12_read_arg_from_smc(hwmgr, &value);
+	value = smum_get_argument(hwmgr);
 	/* power value is an integer */
 	*query = value << 8;
 #endif
@@ -1235,11 +1231,8 @@ static int vega12_get_current_gfx_clk_freq(struct pp_hwmgr *hwmgr, uint32_t *gfx
 	PP_ASSERT_WITH_CODE(smum_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_GetDpmClockFreq, (PPCLK_GFXCLK << 16)) == 0,
 			"[GetCurrentGfxClkFreq] Attempt to get Current GFXCLK Frequency Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(
-			vega12_read_arg_from_smc(hwmgr, &gfx_clk) == 0,
-			"[GetCurrentGfxClkFreq] Attempt to read arg from SMC Failed",
-			return -1);
+			return -EINVAL);
+	gfx_clk = smum_get_argument(hwmgr);
 
 	*gfx_freq = gfx_clk * 100;
 
@@ -1255,11 +1248,8 @@ static int vega12_get_current_mclk_freq(struct pp_hwmgr *hwmgr, uint32_t *mclk_f
 	PP_ASSERT_WITH_CODE(
 			smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetDpmClockFreq, (PPCLK_UCLK << 16)) == 0,
 			"[GetCurrentMClkFreq] Attempt to get Current MCLK Frequency Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(
-			vega12_read_arg_from_smc(hwmgr, &mem_clk) == 0,
-			"[GetCurrentMClkFreq] Attempt to read arg from SMC Failed",
-			return -1);
+			return -EINVAL);
+	mem_clk = smum_get_argument(hwmgr);
 
 	*mclk_freq = mem_clk * 100;
 
@@ -1276,16 +1266,12 @@ static int vega12_get_current_activity_percent(
 #if 0
 	ret = smum_send_msg_to_smc_with_parameter(hwmgr, PPSMC_MSG_GetAverageGfxActivity, 0);
 	if (!ret) {
-		ret = vega12_read_arg_from_smc(hwmgr, &current_activity);
-		if (!ret) {
-			if (current_activity > 100) {
-				PP_ASSERT(false,
-					"[GetCurrentActivityPercent] Activity Percentage Exceeds 100!");
-				current_activity = 100;
-			}
-		} else
+		current_activity = smum_get_argument(hwmgr);
+		if (current_activity > 100) {
 			PP_ASSERT(false,
-				"[GetCurrentActivityPercent] Attempt To Read Average Graphics Activity from SMU Failed!");
+				  "[GetCurrentActivityPercent] Activity Percentage Exceeds 100!");
+			current_activity = 100;
+		}
 	} else
 		PP_ASSERT(false,
 			"[GetCurrentActivityPercent] Attempt To Send Get Average Graphics Activity to SMU Failed!");
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
index cfd9e6ccb790..904eb2c9155b 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_thermal.c
@@ -34,11 +34,9 @@ static int vega12_get_current_rpm(struct pp_hwmgr *hwmgr, uint32_t *current_rpm)
 	PP_ASSERT_WITH_CODE(!smum_send_msg_to_smc(hwmgr,
 				PPSMC_MSG_GetCurrentRpm),
 			"Attempt to get current RPM from SMC Failed!",
-			return -1);
-	PP_ASSERT_WITH_CODE(!vega12_read_arg_from_smc(hwmgr,
-			current_rpm),
-			"Attempt to read current RPM from SMC Failed!",
-			return -1);
+			return -EINVAL);
+	*current_rpm = smum_get_argument(hwmgr);
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
index 0a200406a1ec..8d557accaef2 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/Makefile
@@ -26,7 +26,7 @@
 SMU_MGR = smumgr.o smu8_smumgr.o tonga_smumgr.o fiji_smumgr.o \
 	  polaris10_smumgr.o iceland_smumgr.o \
 	  smu7_smumgr.o vega10_smumgr.o smu10_smumgr.o ci_smumgr.o \
-	  vega12_smumgr.o vegam_smumgr.o
+	  vega12_smumgr.o vegam_smumgr.o smu9_smumgr.o
 
 AMD_PP_SMUMGR = $(addprefix $(AMD_PP_PATH)/smumgr/,$(SMU_MGR))
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
new file mode 100644
index 000000000000..aad8f077f33c
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
@@ -0,0 +1,150 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+
+#include "smumgr.h"
+#include "vega10_inc.h"
+#include "soc15_common.h"
+#include "pp_debug.h"
+
+
+/* MP Apertures */
+#define MP0_Public                  0x03800000
+#define MP0_SRAM                    0x03900000
+#define MP1_Public                  0x03b00000
+#define MP1_SRAM                    0x03c00004
+
+#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
+
+bool smu9_is_smc_ram_running(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t mp1_fw_flags;
+
+	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
+			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
+
+	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
+
+	if (mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK)
+		return true;
+
+	return false;
+}
+
+/*
+ * Check if SMC has responded to previous message.
+ *
+ * @param    smumgr  the address of the powerplay hardware manager.
+ * @return   TRUE    SMC has responded, FALSE otherwise.
+ */
+static uint32_t smu9_wait_for_response(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t reg;
+	uint32_t ret;
+
+	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
+
+	ret = phm_wait_for_register_unequal(hwmgr, reg,
+			0, MP1_C2PMSG_90__CONTENT_MASK);
+
+	if (ret)
+		pr_err("No response from smu\n");
+
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
+}
+
+/*
+ * Send a message to the SMC, and do not wait for its response.
+ * @param    smumgr  the address of the powerplay hardware manager.
+ * @param    msg the message to send.
+ * @return   Always return 0.
+ */
+static int smu9_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
+						uint16_t msg)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
+
+	return 0;
+}
+
+/*
+ * Send a message to the SMC, and wait for its response.
+ * @param    hwmgr  the address of the powerplay hardware manager.
+ * @param    msg the message to send.
+ * @return   Always return 0.
+ */
+int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t ret;
+
+	smu9_wait_for_response(hwmgr);
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+
+	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
+
+	ret = smu9_wait_for_response(hwmgr);
+	if (ret != 1)
+		pr_err("Failed to send message: 0x%x, ret value: 0x%x\n", msg, ret);
+
+	return 0;
+}
+
+/*
+ * Send a message to the SMC with parameter
+ * @param    hwmgr:  the address of the powerplay hardware manager.
+ * @param    msg: the message to send.
+ * @param    parameter: the parameter to send
+ * @return   Always return 0.
+ */
+int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
+					uint16_t msg, uint32_t parameter)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+	uint32_t ret;
+
+	smu9_wait_for_response(hwmgr);
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
+
+	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
+
+	smu9_send_msg_to_smc_without_waiting(hwmgr, msg);
+
+	ret = smu9_wait_for_response(hwmgr);
+	if (ret != 1)
+		pr_err("Failed message: 0x%x, input parameter: 0x%x, error code: 0x%x\n", msg, parameter, ret);
+
+	return 0;
+}
+
+int smu9_get_argument(struct pp_hwmgr *hwmgr)
+{
+	struct amdgpu_device *adev = hwmgr->adev;
+
+	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
+}
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
new file mode 100644
index 000000000000..a8da2815bd89
--- /dev/null
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
@@ -0,0 +1,32 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef _SMU9_SMUMANAGER_H_
+#define _SMU9_SMUMANAGER_H_
+
+bool smu9_is_smc_ram_running(struct pp_hwmgr *hwmgr);
+int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg);
+int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
+					uint16_t msg, uint32_t parameter);
+int smu9_get_argument(struct pp_hwmgr *hwmgr);
+
+#endif
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
index e84669c448a3..5d19115f410c 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega10_smumgr.c
@@ -28,142 +28,11 @@
 #include "vega10_hwmgr.h"
 #include "vega10_ppsmc.h"
 #include "smu9_driver_if.h"
+#include "smu9_smumgr.h"
 #include "ppatomctrl.h"
 #include "pp_debug.h"
 
 
-#define AVFS_EN_MSB		1568
-#define AVFS_EN_LSB		1568
-
-/* Microcode file is stored in this buffer */
-#define BUFFER_SIZE                 80000
-#define MAX_STRING_SIZE             15
-#define BUFFER_SIZETWO              131072 /* 128 *1024 */
-
-/* MP Apertures */
-#define MP0_Public                  0x03800000
-#define MP0_SRAM                    0x03900000
-#define MP1_Public                  0x03b00000
-#define MP1_SRAM                    0x03c00004
-
-#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
-#define smnMP0_FW_INTF                                                                                  0x3010104
-#define smnMP1_PUB_CTRL                                                                                 0x3010b14
-
-static bool vega10_is_smc_ram_running(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t mp1_fw_flags;
-
-	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
-			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
-
-	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
-
-	if (mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK)
-		return true;
-
-	return false;
-}
-
-/*
- * Check if SMC has responded to previous message.
- *
- * @param    smumgr  the address of the powerplay hardware manager.
- * @return   TRUE    SMC has responded, FALSE otherwise.
- */
-static uint32_t vega10_wait_for_response(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
-	uint32_t ret;
-
-	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
-
-	ret = phm_wait_for_register_unequal(hwmgr, reg,
-			0, MP1_C2PMSG_90__CONTENT_MASK);
-
-	if (ret)
-		pr_err("No response from smu\n");
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
-}
-
-/*
- * Send a message to the SMC, and do not wait for its response.
- * @param    smumgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
-		uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC, and wait for its response.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t ret;
-
-	vega10_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	ret = vega10_wait_for_response(hwmgr);
-	if (ret != 1)
-		pr_err("Failed to send message: 0x%x, ret value: 0x%x\n", msg, ret);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC with parameter
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   Always return 0.
- */
-static int vega10_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
-		uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t ret;
-
-	vega10_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
-
-	vega10_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	ret = vega10_wait_for_response(hwmgr);
-	if (ret != 1)
-		pr_err("Failed message: 0x%x, input parameter: 0x%x, error code: 0x%x\n", msg, parameter, ret);
-
-	return 0;
-}
-
-static int vega10_get_argument(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
-}
-
 static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id)
 {
@@ -175,13 +44,13 @@ static int vega10_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			"Invalid SMU Table version!", return -EINVAL);
 	PP_ASSERT_WITH_CODE(priv->smu_tables.entry[table_id].size != 0,
 			"Invalid SMU Table Length!", return -EINVAL);
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableSmu2Dram,
 			priv->smu_tables.entry[table_id].table_id);
 
@@ -206,13 +75,13 @@ static int vega10_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr));
-	vega10_send_msg_to_smc_with_parameter(hwmgr,
+	smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableDram2Smu,
 			priv->smu_tables.entry[table_id].table_id);
 
@@ -225,8 +94,8 @@ static int vega10_get_smc_features(struct pp_hwmgr *hwmgr,
 	if (features_enabled == NULL)
 		return -EINVAL;
 
-	vega10_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures);
-	*features_enabled = vega10_get_argument(hwmgr);
+	smu9_send_msg_to_smc(hwmgr, PPSMC_MSG_GetEnabledSmuFeatures);
+	*features_enabled = smu9_get_argument(hwmgr);
 
 	return 0;
 }
@@ -248,10 +117,10 @@ static int vega10_set_tools_address(struct pp_hwmgr *hwmgr)
 	struct vega10_smumgr *priv = hwmgr->smu_backend;
 
 	if (priv->smu_tables.entry[TOOLSTABLE].mc_addr) {
-		vega10_send_msg_to_smc_with_parameter(hwmgr,
+		smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrHigh,
 				upper_32_bits(priv->smu_tables.entry[TOOLSTABLE].mc_addr));
-		vega10_send_msg_to_smc_with_parameter(hwmgr,
+		smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrLow,
 				lower_32_bits(priv->smu_tables.entry[TOOLSTABLE].mc_addr));
 	}
@@ -265,11 +134,11 @@ static int vega10_verify_smc_interface(struct pp_hwmgr *hwmgr)
 	uint32_t dev_id;
 	uint32_t rev_id;
 
-	PP_ASSERT_WITH_CODE(!vega10_send_msg_to_smc(hwmgr,
+	PP_ASSERT_WITH_CODE(!smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetDriverIfVersion),
 			"Attempt to get SMC IF Version Number Failed!",
 			return -EINVAL);
-	smc_driver_if_version = vega10_get_argument(hwmgr);
+	smc_driver_if_version = smu9_get_argument(hwmgr);
 
 	dev_id = adev->pdev->device;
 	rev_id = adev->pdev->revision;
@@ -441,7 +310,7 @@ static int vega10_smu_fini(struct pp_hwmgr *hwmgr)
 
 static int vega10_start_smu(struct pp_hwmgr *hwmgr)
 {
-	if (!vega10_is_smc_ram_running(hwmgr))
+	if (!smu9_is_smc_ram_running(hwmgr))
 		return -EINVAL;
 
 	PP_ASSERT_WITH_CODE(!vega10_verify_smc_interface(hwmgr),
@@ -453,7 +322,8 @@ static int vega10_start_smu(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-static int vega10_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table, uint16_t table_id, bool rw)
+static int vega10_smc_table_manager(struct pp_hwmgr *hwmgr, uint8_t *table,
+				    uint16_t table_id, bool rw)
 {
 	int ret;
 
@@ -470,11 +340,11 @@ const struct pp_smumgr_func vega10_smu_funcs = {
 	.smu_fini = &vega10_smu_fini,
 	.start_smu = &vega10_start_smu,
 	.request_smu_load_specific_fw = NULL,
-	.send_msg_to_smc = &vega10_send_msg_to_smc,
-	.send_msg_to_smc_with_parameter = &vega10_send_msg_to_smc_with_parameter,
+	.send_msg_to_smc = &smu9_send_msg_to_smc,
+	.send_msg_to_smc_with_parameter = &smu9_send_msg_to_smc_with_parameter,
 	.download_pptable_settings = NULL,
 	.upload_pptable_settings = NULL,
 	.is_dpm_running = vega10_is_dpm_running,
-	.get_argument = vega10_get_argument,
+	.get_argument = smu9_get_argument,
 	.smc_table_manager = vega10_smc_table_manager,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
index 508a262fb328..7f0e2109f40d 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.c
@@ -24,157 +24,14 @@
 #include "smumgr.h"
 #include "vega12_inc.h"
 #include "soc15_common.h"
+#include "smu9_smumgr.h"
 #include "vega12_smumgr.h"
 #include "vega12_ppsmc.h"
 #include "vega12/smu9_driver_if.h"
-
 #include "ppatomctrl.h"
 #include "pp_debug.h"
 
 
-/* MP Apertures */
-#define MP0_Public                  0x03800000
-#define MP0_SRAM                    0x03900000
-#define MP1_Public                  0x03b00000
-#define MP1_SRAM                    0x03c00004
-
-#define smnMP1_FIRMWARE_FLAGS                                                                           0x3010028
-#define smnMP0_FW_INTF                                                                                  0x3010104
-#define smnMP1_PUB_CTRL                                                                                 0x3010b14
-
-static bool vega12_is_smc_ram_running(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t mp1_fw_flags;
-
-	WREG32_SOC15(NBIF, 0, mmPCIE_INDEX2,
-			(MP1_Public | (smnMP1_FIRMWARE_FLAGS & 0xffffffff)));
-
-	mp1_fw_flags = RREG32_SOC15(NBIF, 0, mmPCIE_DATA2);
-
-	if ((mp1_fw_flags & MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED_MASK) >>
-				MP1_FIRMWARE_FLAGS__INTERRUPTS_ENABLED__SHIFT)
-		return true;
-
-	return false;
-}
-
-/*
- * Check if SMC has responded to previous message.
- *
- * @param    smumgr  the address of the powerplay hardware manager.
- * @return   TRUE    SMC has responded, FALSE otherwise.
- */
-static uint32_t vega12_wait_for_response(struct pp_hwmgr *hwmgr)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-	uint32_t reg;
-
-	reg = SOC15_REG_OFFSET(MP1, 0, mmMP1_SMN_C2PMSG_90);
-
-	phm_wait_for_register_unequal(hwmgr, reg,
-			0, MP1_C2PMSG_90__CONTENT_MASK);
-
-	return RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90);
-}
-
-/*
- * Send a message to the SMC, and do not wait for its response.
- * @param    smumgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
-		uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC, and wait for its response.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    msg the message to send.
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	vega12_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	if (vega12_wait_for_response(hwmgr) != 1)
-		pr_err("Failed to send message: 0x%x\n", msg);
-
-	return 0;
-}
-
-/*
- * Send a message to the SMC with parameter
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   Always return 0.
- */
-int vega12_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
-		uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	vega12_wait_for_response(hwmgr);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_90, 0);
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82, parameter);
-
-	vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-
-	if (vega12_wait_for_response(hwmgr) != 1)
-		pr_err("Failed to send message: 0x%x\n", msg);
-
-	return 0;
-}
-
-
-/*
- * Send a message to the SMC with parameter, do not wait for response
- * @param    hwmgr:  the address of the powerplay hardware manager.
- * @param    msg: the message to send.
- * @param    parameter: the parameter to send
- * @return   The response that came from the SMC.
- */
-int vega12_send_msg_to_smc_with_parameter_without_waiting(
-		struct pp_hwmgr *hwmgr, uint16_t msg, uint32_t parameter)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	WREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_66, parameter);
-
-	return vega12_send_msg_to_smc_without_waiting(hwmgr, msg);
-}
-
-/*
- * Retrieve an argument from SMC.
- * @param    hwmgr  the address of the powerplay hardware manager.
- * @param    arg     pointer to store the argument from SMC.
- * @return   Always return 0.
- */
-int vega12_read_arg_from_smc(struct pp_hwmgr *hwmgr, uint32_t *arg)
-{
-	struct amdgpu_device *adev = hwmgr->adev;
-
-	*arg = RREG32_SOC15(MP1, 0, mmMP1_SMN_C2PMSG_82);
-
-	return 0;
-}
-
 /*
  * Copy table from SMC into driver FB
  * @param   hwmgr    the address of the HW manager
@@ -192,16 +49,16 @@ int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 			"Invalid SMU Table version!", return -EINVAL);
 	PP_ASSERT_WITH_CODE(priv->smu_tables.entry[table_id].size != 0,
 			"Invalid SMU Table Length!", return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableFromSMC] Attempt to Set Dram Addr High Failed!", return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableFromSMC] Attempt to Set Dram Addr Low Failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableSmu2Dram,
 			table_id) == 0,
 			"[CopyTableFromSMC] Attempt to Transfer Table From SMU Failed!",
@@ -234,17 +91,17 @@ int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
 	memcpy(priv->smu_tables.entry[table_id].table, table,
 			priv->smu_tables.entry[table_id].size);
 
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrHigh,
 			upper_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableToSMC] Attempt to Set Dram Addr High Failed!",
 			return -EINVAL;);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetDriverDramAddrLow,
 			lower_32_bits(priv->smu_tables.entry[table_id].mc_addr)) == 0,
 			"[CopyTableToSMC] Attempt to Set Dram Addr Low Failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_TransferTableDram2Smu,
 			table_id) == 0,
 			"[CopyTableToSMC] Attempt to Transfer Table To SMU Failed!",
@@ -262,20 +119,20 @@ int vega12_enable_smc_features(struct pp_hwmgr *hwmgr,
 	smu_features_high = (uint32_t)((feature_mask & SMU_FEATURES_HIGH_MASK) >> SMU_FEATURES_HIGH_SHIFT);
 
 	if (enable) {
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_EnableSmuFeaturesLow, smu_features_low) == 0,
 				"[EnableDisableSMCFeatures] Attemp to enable SMU features Low failed!",
 				return -EINVAL);
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_EnableSmuFeaturesHigh, smu_features_high) == 0,
 				"[EnableDisableSMCFeatures] Attemp to enable SMU features High failed!",
 				return -EINVAL);
 	} else {
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_DisableSmuFeaturesLow, smu_features_low) == 0,
 				"[EnableDisableSMCFeatures] Attemp to disable SMU features Low failed!",
 				return -EINVAL);
-		PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc_with_parameter(hwmgr,
+		PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_DisableSmuFeaturesHigh, smu_features_high) == 0,
 				"[EnableDisableSMCFeatures] Attemp to disable SMU features High failed!",
 				return -EINVAL);
@@ -292,22 +149,17 @@ int vega12_get_enabled_smc_features(struct pp_hwmgr *hwmgr,
 	if (features_enabled == NULL)
 		return -EINVAL;
 
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc(hwmgr,
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetEnabledSmuFeaturesLow) == 0,
 			"[GetEnabledSMCFeatures] Attemp to get SMU features Low failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_read_arg_from_smc(hwmgr,
-			&smc_features_low) == 0,
-			"[GetEnabledSMCFeatures] Attemp to read SMU features Low argument failed!",
-			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_send_msg_to_smc(hwmgr,
+	smc_features_low = smu9_get_argument(hwmgr);
+
+	PP_ASSERT_WITH_CODE(smu9_send_msg_to_smc(hwmgr,
 			PPSMC_MSG_GetEnabledSmuFeaturesHigh) == 0,
 			"[GetEnabledSMCFeatures] Attemp to get SMU features High failed!",
 			return -EINVAL);
-	PP_ASSERT_WITH_CODE(vega12_read_arg_from_smc(hwmgr,
-			&smc_features_high) == 0,
-			"[GetEnabledSMCFeatures] Attemp to read SMU features High argument failed!",
-			return -EINVAL);
+	smc_features_high = smu9_get_argument(hwmgr);
 
 	*features_enabled = ((((uint64_t)smc_features_low << SMU_FEATURES_LOW_SHIFT) & SMU_FEATURES_LOW_MASK) |
 			(((uint64_t)smc_features_high << SMU_FEATURES_HIGH_SHIFT) & SMU_FEATURES_HIGH_MASK));
@@ -333,10 +185,10 @@ static int vega12_set_tools_address(struct pp_hwmgr *hwmgr)
 			(struct vega12_smumgr *)(hwmgr->smu_backend);
 
 	if (priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr) {
-		if (!vega12_send_msg_to_smc_with_parameter(hwmgr,
+		if (!smu9_send_msg_to_smc_with_parameter(hwmgr,
 				PPSMC_MSG_SetToolsDramAddrHigh,
 				upper_32_bits(priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr)))
-			vega12_send_msg_to_smc_with_parameter(hwmgr,
+			smu9_send_msg_to_smc_with_parameter(hwmgr,
 					PPSMC_MSG_SetToolsDramAddrLow,
 					lower_32_bits(priv->smu_tables.entry[TABLE_PMSTATUSLOG].mc_addr));
 	}
@@ -490,7 +342,7 @@ static int vega12_smu_fini(struct pp_hwmgr *hwmgr)
 
 static int vega12_start_smu(struct pp_hwmgr *hwmgr)
 {
-	PP_ASSERT_WITH_CODE(vega12_is_smc_ram_running(hwmgr),
+	PP_ASSERT_WITH_CODE(smu9_is_smc_ram_running(hwmgr),
 			"SMC is not running!",
 			return -EINVAL);
 
@@ -504,9 +356,10 @@ const struct pp_smumgr_func vega12_smu_funcs = {
 	.smu_fini = &vega12_smu_fini,
 	.start_smu = &vega12_start_smu,
 	.request_smu_load_specific_fw = NULL,
-	.send_msg_to_smc = &vega12_send_msg_to_smc,
-	.send_msg_to_smc_with_parameter = &vega12_send_msg_to_smc_with_parameter,
+	.send_msg_to_smc = &smu9_send_msg_to_smc,
+	.send_msg_to_smc_with_parameter = &smu9_send_msg_to_smc_with_parameter,
 	.download_pptable_settings = NULL,
 	.upload_pptable_settings = NULL,
 	.is_dpm_running = vega12_is_dpm_running,
+	.get_argument = smu9_get_argument,
 };
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
index 2810d387b611..b285cbc04019 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega12_smumgr.h
@@ -48,7 +48,6 @@ struct vega12_smumgr {
 #define SMU_FEATURES_HIGH_MASK       0xFFFFFFFF00000000
 #define SMU_FEATURES_HIGH_SHIFT      32
 
-int vega12_read_arg_from_smc(struct pp_hwmgr *hwmgr, uint32_t *arg);
 int vega12_copy_table_from_smc(struct pp_hwmgr *hwmgr,
 		uint8_t *table, int16_t table_id);
 int vega12_copy_table_to_smc(struct pp_hwmgr *hwmgr,
-- 
cgit v1.2.3


From 59f20f5a0c9767a8b66688b84e72a345b4dc1bc1 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 12 Jul 2018 14:59:22 -0500
Subject: drm/amdgpu/pp: switch smu callback type for get_argument()

return a uint32_t rather than an int to properly reflect
what the function does.

Reviewed-by: Rex Zhu <rezhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/inc/hwmgr.h           | 2 +-
 drivers/gpu/drm/amd/powerplay/inc/smumgr.h          | 2 +-
 drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c | 2 +-
 drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c  | 4 ++--
 drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c  | 2 +-
 drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h  | 2 +-
 drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c       | 2 +-
 7 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
index b3363f26039a..d3d96260f440 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/hwmgr.h
@@ -194,7 +194,7 @@ struct pp_smumgr_func {
 	int (*request_smu_load_fw)(struct pp_hwmgr  *hwmgr);
 	int (*request_smu_load_specific_fw)(struct pp_hwmgr  *hwmgr,
 					    uint32_t firmware);
-	int (*get_argument)(struct pp_hwmgr  *hwmgr);
+	uint32_t (*get_argument)(struct pp_hwmgr  *hwmgr);
 	int (*send_msg_to_smc)(struct pp_hwmgr  *hwmgr, uint16_t msg);
 	int (*send_msg_to_smc_with_parameter)(struct pp_hwmgr  *hwmgr,
 					  uint16_t msg, uint32_t parameter);
diff --git a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
index 89dfbf53c7e6..82550a8a3a3f 100644
--- a/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/inc/smumgr.h
@@ -80,7 +80,7 @@ enum SMU10_TABLE_ID {
 	SMU10_CLOCKTABLE,
 };
 
-extern int smum_get_argument(struct pp_hwmgr *hwmgr);
+extern uint32_t smum_get_argument(struct pp_hwmgr *hwmgr);
 
 extern int smum_download_powerplay_table(struct pp_hwmgr *hwmgr, void **table);
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
index 0a563f6fe9ea..bb07d43f3874 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu10_smumgr.c
@@ -68,7 +68,7 @@ static int smu10_send_msg_to_smc_without_waiting(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-static int smu10_read_arg_from_smc(struct pp_hwmgr *hwmgr)
+static uint32_t smu10_read_arg_from_smc(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
index c861d3023474..f7e3bc22bb93 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu8_smumgr.c
@@ -52,10 +52,10 @@ static const enum smu8_scratch_entry firmware_list[] = {
 	SMU8_SCRATCH_ENTRY_UCODE_ID_RLC_G,
 };
 
-static int smu8_get_argument(struct pp_hwmgr *hwmgr)
+static uint32_t smu8_get_argument(struct pp_hwmgr *hwmgr)
 {
 	if (hwmgr == NULL || hwmgr->device == NULL)
-		return -EINVAL;
+		return 0;
 
 	return cgs_read_register(hwmgr->device,
 					mmSMU_MP1_SRBM2P_ARG_0);
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
index aad8f077f33c..079fc8e8f709 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.c
@@ -142,7 +142,7 @@ int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 	return 0;
 }
 
-int smu9_get_argument(struct pp_hwmgr *hwmgr)
+uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr)
 {
 	struct amdgpu_device *adev = hwmgr->adev;
 
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
index a8da2815bd89..1462279ca128 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smu9_smumgr.h
@@ -27,6 +27,6 @@ bool smu9_is_smc_ram_running(struct pp_hwmgr *hwmgr);
 int smu9_send_msg_to_smc(struct pp_hwmgr *hwmgr, uint16_t msg);
 int smu9_send_msg_to_smc_with_parameter(struct pp_hwmgr *hwmgr,
 					uint16_t msg, uint32_t parameter);
-int smu9_get_argument(struct pp_hwmgr *hwmgr);
+uint32_t smu9_get_argument(struct pp_hwmgr *hwmgr);
 
 #endif
diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
index c9837935f0f5..99d5e4f98f49 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c
@@ -96,7 +96,7 @@ int smum_process_firmware_header(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
-int smum_get_argument(struct pp_hwmgr *hwmgr)
+uint32_t smum_get_argument(struct pp_hwmgr *hwmgr)
 {
 	if (NULL != hwmgr->smumgr_funcs->get_argument)
 		return hwmgr->smumgr_funcs->get_argument(hwmgr);
-- 
cgit v1.2.3


From 4f45c778352eff878757a21566d87fbbedd104fc Mon Sep 17 00:00:00 2001
From: Lyude Paul <lyude@redhat.com>
Date: Mon, 16 Jul 2018 13:17:11 -0400
Subject: drm/connector: Fix typo in drm_connector_list_iter_next()

Signed-off-by: Lyude Paul <lyude@redhat.com>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716171711.413-1-lyude@redhat.com
---
 drivers/gpu/drm/drm_connector.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 8f3f672a47b0..6011d769d50b 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -606,7 +606,7 @@ __drm_connector_put_safe(struct drm_connector *conn)
 
 /**
  * drm_connector_list_iter_next - return next connector
- * @iter: connectr_list iterator
+ * @iter: connector_list iterator
  *
  * Returns the next connector for @iter, or NULL when the list walk has
  * completed.
-- 
cgit v1.2.3


From 9c7e47025a6b9a2800eec127996ad58946e0cad4 Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Wed, 9 May 2018 11:26:07 +0530
Subject: clk: qcom: clk-rpmh: Add QCOM RPMh clock driver

Add the RPMh clock driver to control the RPMh managed clock resources on
some of the Qualcomm Technologies, Inc. SoCs.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
[sboyd@kernel.org: Clean up whitespace, indentation, remove
cmd_db_ready check]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/Kconfig    |   9 ++
 drivers/clk/qcom/Makefile   |   1 +
 drivers/clk/qcom/clk-rpmh.c | 329 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 339 insertions(+)
 create mode 100644 drivers/clk/qcom/clk-rpmh.c

diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 9c3480dcc38a..2b69cf22b323 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -59,6 +59,15 @@ config QCOM_CLK_SMD_RPM
 	  Say Y if you want to support the clocks exposed by the RPM on
 	  platforms such as apq8016, apq8084, msm8974 etc.
 
+config QCOM_CLK_RPMH
+	tristate "RPMh Clock Driver"
+	depends on COMMON_CLK_QCOM && QCOM_RPMH
+	help
+	 RPMh manages shared resources on some Qualcomm Technologies, Inc.
+	 SoCs. It accepts requests from other hardware subsystems via RSC.
+	 Say Y if you want to support the clocks exposed by RPMh on
+	 platforms such as SDM845.
+
 config APQ_GCC_8084
 	tristate "APQ8084 Global Clock Controller"
 	select QCOM_GDSC
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 762c01137c2f..599ab9154480 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -37,6 +37,7 @@ obj-$(CONFIG_MSM_MMCC_8996) += mmcc-msm8996.o
 obj-$(CONFIG_QCOM_A53PLL) += a53-pll.o
 obj-$(CONFIG_QCOM_CLK_APCS_MSM8916) += apcs-msm8916.o
 obj-$(CONFIG_QCOM_CLK_RPM) += clk-rpm.o
+obj-$(CONFIG_QCOM_CLK_RPMH) += clk-rpmh.o
 obj-$(CONFIG_QCOM_CLK_SMD_RPM) += clk-smd-rpm.o
 obj-$(CONFIG_SDM_GCC_845) += gcc-sdm845.o
 obj-$(CONFIG_SDM_VIDEOCC_845) += videocc-sdm845.o
diff --git a/drivers/clk/qcom/clk-rpmh.c b/drivers/clk/qcom/clk-rpmh.c
new file mode 100644
index 000000000000..9f4fc7773fb2
--- /dev/null
+++ b/drivers/clk/qcom/clk-rpmh.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/rpmh.h>
+
+#include <dt-bindings/clock/qcom,rpmh.h>
+
+#define CLK_RPMH_ARC_EN_OFFSET		0
+#define CLK_RPMH_VRM_EN_OFFSET		4
+
+/**
+ * struct clk_rpmh - individual rpmh clock data structure
+ * @hw:			handle between common and hardware-specific interfaces
+ * @res_name:		resource name for the rpmh clock
+ * @div:		clock divider to compute the clock rate
+ * @res_addr:		base address of the rpmh resource within the RPMh
+ * @res_on_val:		rpmh clock enable value
+ * @state:		rpmh clock requested state
+ * @aggr_state:		rpmh clock aggregated state
+ * @last_sent_aggr_state: rpmh clock last aggr state sent to RPMh
+ * @valid_state_mask:	mask to determine the state of the rpmh clock
+ * @dev:		device to which it is attached
+ * @peer:		pointer to the clock rpmh sibling
+ */
+struct clk_rpmh {
+	struct clk_hw hw;
+	const char *res_name;
+	u8 div;
+	u32 res_addr;
+	u32 res_on_val;
+	u32 state;
+	u32 aggr_state;
+	u32 last_sent_aggr_state;
+	u32 valid_state_mask;
+	struct device *dev;
+	struct clk_rpmh *peer;
+};
+
+struct clk_rpmh_desc {
+	struct clk_hw **clks;
+	size_t num_clks;
+};
+
+static DEFINE_MUTEX(rpmh_clk_lock);
+
+#define __DEFINE_CLK_RPMH(_platform, _name, _name_active, _res_name,	\
+			  _res_en_offset, _res_on, _div)		\
+	static struct clk_rpmh _platform##_##_name_active;		\
+	static struct clk_rpmh _platform##_##_name = {			\
+		.res_name = _res_name,					\
+		.res_addr = _res_en_offset,				\
+		.res_on_val = _res_on,					\
+		.div = _div,						\
+		.peer = &_platform##_##_name_active,			\
+		.valid_state_mask = (BIT(RPMH_WAKE_ONLY_STATE) |	\
+				      BIT(RPMH_ACTIVE_ONLY_STATE) |	\
+				      BIT(RPMH_SLEEP_STATE)),		\
+		.hw.init = &(struct clk_init_data){			\
+			.ops = &clk_rpmh_ops,				\
+			.name = #_name,					\
+			.parent_names = (const char *[]){ "xo_board" },	\
+			.num_parents = 1,				\
+		},							\
+	};								\
+	static struct clk_rpmh _platform##_##_name_active = {		\
+		.res_name = _res_name,					\
+		.res_addr = _res_en_offset,				\
+		.res_on_val = _res_on,					\
+		.div = _div,						\
+		.peer = &_platform##_##_name,				\
+		.valid_state_mask = (BIT(RPMH_WAKE_ONLY_STATE) |	\
+					BIT(RPMH_ACTIVE_ONLY_STATE)),	\
+		.hw.init = &(struct clk_init_data){			\
+			.ops = &clk_rpmh_ops,				\
+			.name = #_name_active,				\
+			.parent_names = (const char *[]){ "xo_board" },	\
+			.num_parents = 1,				\
+		},							\
+	}
+
+#define DEFINE_CLK_RPMH_ARC(_platform, _name, _name_active, _res_name,	\
+			    _res_on, _div)				\
+	__DEFINE_CLK_RPMH(_platform, _name, _name_active, _res_name,	\
+			  CLK_RPMH_ARC_EN_OFFSET, _res_on, _div)
+
+#define DEFINE_CLK_RPMH_VRM(_platform, _name, _name_active, _res_name,	\
+				_div)					\
+	__DEFINE_CLK_RPMH(_platform, _name, _name_active, _res_name,	\
+			  CLK_RPMH_VRM_EN_OFFSET, 1, _div)
+
+static inline struct clk_rpmh *to_clk_rpmh(struct clk_hw *_hw)
+{
+	return container_of(_hw, struct clk_rpmh, hw);
+}
+
+static inline bool has_state_changed(struct clk_rpmh *c, u32 state)
+{
+	return (c->last_sent_aggr_state & BIT(state))
+		!= (c->aggr_state & BIT(state));
+}
+
+static int clk_rpmh_send_aggregate_command(struct clk_rpmh *c)
+{
+	struct tcs_cmd cmd = { 0 };
+	u32 cmd_state, on_val;
+	enum rpmh_state state = RPMH_SLEEP_STATE;
+	int ret;
+
+	cmd.addr = c->res_addr;
+	cmd_state = c->aggr_state;
+	on_val = c->res_on_val;
+
+	for (; state <= RPMH_ACTIVE_ONLY_STATE; state++) {
+		if (has_state_changed(c, state)) {
+			if (cmd_state & BIT(state))
+				cmd.data = on_val;
+
+			ret = rpmh_write_async(c->dev, state, &cmd, 1);
+			if (ret) {
+				dev_err(c->dev, "set %s state of %s failed: (%d)\n",
+					!state ? "sleep" :
+					state == RPMH_WAKE_ONLY_STATE	?
+					"wake" : "active", c->res_name, ret);
+				return ret;
+			}
+		}
+	}
+
+	c->last_sent_aggr_state = c->aggr_state;
+	c->peer->last_sent_aggr_state =  c->last_sent_aggr_state;
+
+	return 0;
+}
+
+/*
+ * Update state and aggregate state values based on enable value.
+ */
+static int clk_rpmh_aggregate_state_send_command(struct clk_rpmh *c,
+						bool enable)
+{
+	int ret;
+
+	/* Nothing required to be done if already off or on */
+	if (enable == c->state)
+		return 0;
+
+	c->state = enable ? c->valid_state_mask : 0;
+	c->aggr_state = c->state | c->peer->state;
+	c->peer->aggr_state = c->aggr_state;
+
+	ret = clk_rpmh_send_aggregate_command(c);
+	if (!ret)
+		return 0;
+
+	if (ret && enable)
+		c->state = 0;
+	else if (ret)
+		c->state = c->valid_state_mask;
+
+	WARN(1, "clk: %s failed to %s\n", c->res_name,
+	     enable ? "enable" : "disable");
+	return ret;
+}
+
+static int clk_rpmh_prepare(struct clk_hw *hw)
+{
+	struct clk_rpmh *c = to_clk_rpmh(hw);
+	int ret = 0;
+
+	mutex_lock(&rpmh_clk_lock);
+	ret = clk_rpmh_aggregate_state_send_command(c, true);
+	mutex_unlock(&rpmh_clk_lock);
+
+	return ret;
+};
+
+static void clk_rpmh_unprepare(struct clk_hw *hw)
+{
+	struct clk_rpmh *c = to_clk_rpmh(hw);
+
+	mutex_lock(&rpmh_clk_lock);
+	clk_rpmh_aggregate_state_send_command(c, false);
+	mutex_unlock(&rpmh_clk_lock);
+};
+
+static unsigned long clk_rpmh_recalc_rate(struct clk_hw *hw,
+					unsigned long prate)
+{
+	struct clk_rpmh *r = to_clk_rpmh(hw);
+
+	/*
+	 * RPMh clocks have a fixed rate. Return static rate.
+	 */
+	return prate / r->div;
+}
+
+static const struct clk_ops clk_rpmh_ops = {
+	.prepare	= clk_rpmh_prepare,
+	.unprepare	= clk_rpmh_unprepare,
+	.recalc_rate	= clk_rpmh_recalc_rate,
+};
+
+/* Resource name must match resource id present in cmd-db. */
+DEFINE_CLK_RPMH_ARC(sdm845, bi_tcxo, bi_tcxo_ao, "xo.lvl", 0x3, 2);
+DEFINE_CLK_RPMH_VRM(sdm845, ln_bb_clk2, ln_bb_clk2_ao, "lnbclka2", 2);
+DEFINE_CLK_RPMH_VRM(sdm845, ln_bb_clk3, ln_bb_clk3_ao, "lnbclka3", 2);
+DEFINE_CLK_RPMH_VRM(sdm845, rf_clk1, rf_clk1_ao, "rfclka1", 1);
+DEFINE_CLK_RPMH_VRM(sdm845, rf_clk2, rf_clk2_ao, "rfclka2", 1);
+DEFINE_CLK_RPMH_VRM(sdm845, rf_clk3, rf_clk3_ao, "rfclka3", 1);
+
+static struct clk_hw *sdm845_rpmh_clocks[] = {
+	[RPMH_CXO_CLK]		= &sdm845_bi_tcxo.hw,
+	[RPMH_CXO_CLK_A]	= &sdm845_bi_tcxo_ao.hw,
+	[RPMH_LN_BB_CLK2]	= &sdm845_ln_bb_clk2.hw,
+	[RPMH_LN_BB_CLK2_A]	= &sdm845_ln_bb_clk2_ao.hw,
+	[RPMH_LN_BB_CLK3]	= &sdm845_ln_bb_clk3.hw,
+	[RPMH_LN_BB_CLK3_A]	= &sdm845_ln_bb_clk3_ao.hw,
+	[RPMH_RF_CLK1]		= &sdm845_rf_clk1.hw,
+	[RPMH_RF_CLK1_A]	= &sdm845_rf_clk1_ao.hw,
+	[RPMH_RF_CLK2]		= &sdm845_rf_clk2.hw,
+	[RPMH_RF_CLK2_A]	= &sdm845_rf_clk2_ao.hw,
+	[RPMH_RF_CLK3]		= &sdm845_rf_clk3.hw,
+	[RPMH_RF_CLK3_A]	= &sdm845_rf_clk3_ao.hw,
+};
+
+static const struct clk_rpmh_desc clk_rpmh_sdm845 = {
+	.clks = sdm845_rpmh_clocks,
+	.num_clks = ARRAY_SIZE(sdm845_rpmh_clocks),
+};
+
+static struct clk_hw *of_clk_rpmh_hw_get(struct of_phandle_args *clkspec,
+					 void *data)
+{
+	struct clk_rpmh_desc *rpmh = data;
+	unsigned int idx = clkspec->args[0];
+
+	if (idx >= rpmh->num_clks) {
+		pr_err("%s: invalid index %u\n", __func__, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return rpmh->clks[idx];
+}
+
+static int clk_rpmh_probe(struct platform_device *pdev)
+{
+	struct clk_hw **hw_clks;
+	struct clk_rpmh *rpmh_clk;
+	const struct clk_rpmh_desc *desc;
+	int ret, i;
+
+	desc = of_device_get_match_data(&pdev->dev);
+	if (!desc)
+		return -ENODEV;
+
+	hw_clks = desc->clks;
+
+	for (i = 0; i < desc->num_clks; i++) {
+		u32 res_addr;
+
+		rpmh_clk = to_clk_rpmh(hw_clks[i]);
+		res_addr = cmd_db_read_addr(rpmh_clk->res_name);
+		if (!res_addr) {
+			dev_err(&pdev->dev, "missing RPMh resource address for %s\n",
+				rpmh_clk->res_name);
+			return -ENODEV;
+		}
+		rpmh_clk->res_addr += res_addr;
+		rpmh_clk->dev = &pdev->dev;
+
+		ret = devm_clk_hw_register(&pdev->dev, hw_clks[i]);
+		if (ret) {
+			dev_err(&pdev->dev, "failed to register %s\n",
+				hw_clks[i]->init->name);
+			return ret;
+		}
+	}
+
+	/* typecast to silence compiler warning */
+	ret = devm_of_clk_add_hw_provider(&pdev->dev, of_clk_rpmh_hw_get,
+					  (void *)desc);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed to add clock provider\n");
+		return ret;
+	}
+
+	dev_dbg(&pdev->dev, "Registered RPMh clocks\n");
+
+	return 0;
+}
+
+static const struct of_device_id clk_rpmh_match_table[] = {
+	{ .compatible = "qcom,sdm845-rpmh-clk", .data = &clk_rpmh_sdm845},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, clk_rpmh_match_table);
+
+static struct platform_driver clk_rpmh_driver = {
+	.probe		= clk_rpmh_probe,
+	.driver		= {
+		.name	= "clk-rpmh",
+		.of_match_table = clk_rpmh_match_table,
+	},
+};
+
+static int __init clk_rpmh_init(void)
+{
+	return platform_driver_register(&clk_rpmh_driver);
+}
+subsys_initcall(clk_rpmh_init);
+
+static void __exit clk_rpmh_exit(void)
+{
+	platform_driver_unregister(&clk_rpmh_driver);
+}
+module_exit(clk_rpmh_exit);
+
+MODULE_DESCRIPTION("QCOM RPMh Clock Driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 1b3725781a07f754d1b81065926495c79c2183e6 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 16 Jul 2018 16:36:19 +0100
Subject: net: hns3: Modify the order of initializing command queue register

According to hardware's description, the head pointer register should
be written before the tail pointer register while doing command queue
initialization.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index eca4b23fd0a8..cf40afca66db 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -119,8 +119,8 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG,
 				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
 				HCLGE_NIC_CMQ_ENABLE);
-		hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0);
+		hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0);
 	} else {
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_BASEADDR_L_REG,
 				lower_32_bits(dma));
@@ -129,8 +129,8 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_DEPTH_REG,
 				(ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S) |
 				HCLGE_NIC_CMQ_ENABLE);
-		hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
 		hclge_write_dev(hw, HCLGE_NIC_CRQ_HEAD_REG, 0);
+		hclge_write_dev(hw, HCLGE_NIC_CRQ_TAIL_REG, 0);
 	}
 }
 
-- 
cgit v1.2.3


From 6d4fab39533f1bcd933d82d1667ceea93e4de260 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 16 Jul 2018 16:36:20 +0100
Subject: net: hns3: Reset net device with rtnl_lock

Since current locking was not covering certain code where
netdev was being accessed or manipulated, this patch fixes
it.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 8bbf4e5c0032..3886290ae63e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2820,15 +2820,13 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 static void hclge_reset(struct hclge_dev *hdev)
 {
 	/* perform reset of the stack & ae device for a client */
-
+	rtnl_lock();
 	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 
 	if (!hclge_reset_wait(hdev)) {
-		rtnl_lock();
 		hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT);
 		hclge_reset_ae_dev(hdev->ae_dev);
 		hclge_notify_client(hdev, HNAE3_INIT_CLIENT);
-		rtnl_unlock();
 
 		hclge_clear_reset_cause(hdev);
 	} else {
@@ -2838,6 +2836,7 @@ static void hclge_reset(struct hclge_dev *hdev)
 	}
 
 	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	rtnl_unlock();
 }
 
 static void hclge_reset_event(struct hnae3_handle *handle)
-- 
cgit v1.2.3


From 9de0b86f64444e5bddc0c4687e23c36ab52d1fcf Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 16 Jul 2018 16:36:21 +0100
Subject: net: hns3: Prevent to request reset frequently

Netdevice reset should not be requested frequently, a new one
must wait a moment since there may be some work not completed.

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3886290ae63e..a1886a3c18d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2819,7 +2819,10 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev)
 
 static void hclge_reset(struct hclge_dev *hdev)
 {
+	struct hnae3_handle *handle;
+
 	/* perform reset of the stack & ae device for a client */
+	handle = &hdev->vport[0].nic;
 	rtnl_lock();
 	hclge_notify_client(hdev, HNAE3_DOWN_CLIENT);
 
@@ -2836,6 +2839,7 @@ static void hclge_reset(struct hclge_dev *hdev)
 	}
 
 	hclge_notify_client(hdev, HNAE3_UP_CLIENT);
+	handle->last_reset_time = jiffies;
 	rtnl_unlock();
 }
 
@@ -2849,8 +2853,13 @@ static void hclge_reset_event(struct hnae3_handle *handle)
 	 * know this if last reset request did not occur very recently (watchdog
 	 * timer = 5*HZ, let us check after sufficiently large time, say 4*5*Hz)
 	 * In case of new request we reset the "reset level" to PF reset.
+	 * And if it is a repeat reset request of the most recent one then we
+	 * want to make sure we throttle the reset request. Therefore, we will
+	 * not allow it again before 3*HZ times.
 	 */
-	if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
+	if (time_before(jiffies, (handle->last_reset_time + 3 * HZ)))
+		return;
+	else if (time_after(jiffies, (handle->last_reset_time + 4 * 5 * HZ)))
 		handle->reset_level = HNAE3_FUNC_RESET;
 
 	dev_info(&hdev->pdev->dev, "received reset event , reset type is %d",
@@ -2862,8 +2871,6 @@ static void hclge_reset_event(struct hnae3_handle *handle)
 
 	if (handle->reset_level < HNAE3_GLOBAL_RESET)
 		handle->reset_level++;
-
-	handle->last_reset_time = jiffies;
 }
 
 static void hclge_reset_subtask(struct hclge_dev *hdev)
-- 
cgit v1.2.3


From 9ca8d1a73c373c0f54e7ab6eaa37aea8de28cd3a Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 16 Jul 2018 16:36:22 +0100
Subject: net: hns3: Correct reset event status register

According to hardware's description, driver should get reset event
from VECTOR0_PF_OTHER_INT_ST(0x20800) instead of
VECTOR0_PF_OTHER_INT_SRC(0x20700).

Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a1886a3c18d9..266c68607e53 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2495,7 +2495,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	u32 cmdq_src_reg;
 
 	/* fetch the events from their corresponding regs */
-	rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG);
+	rst_src_reg = hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS);
 	cmdq_src_reg = hclge_read_dev(&hdev->hw, HCLGE_VECTOR0_CMDQ_SRC_REG);
 
 	/* Assumption: If by any chance reset and mailbox events are reported
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 20abe828e30b..a5abf8ee9b96 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -89,6 +89,7 @@
 
 /* Reset related Registers */
 #define HCLGE_MISC_RESET_STS_REG	0x20700
+#define HCLGE_MISC_VECTOR_INT_STS	0x20800
 #define HCLGE_GLOBAL_RESET_REG		0x20A00
 #define HCLGE_GLOBAL_RESET_BIT		0x0
 #define HCLGE_CORE_RESET_BIT		0x1
-- 
cgit v1.2.3


From 6b1385cc251ae9f26b720fa5c8c00bf19af336ae Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 16 Jul 2018 16:36:23 +0100
Subject: net: hns3: Fix return value error in hns3_reset_notify_down_enet

When doing reset, netdev has not been brought up is not an error,
it means that we do not need do the stop operation, so just return
zero.

Fixes: 76ad4f0ee747 ("net: hns3: Add support of HNS3 Ethernet Driver for hip08 SoC")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index c211450bfd78..829644665aa8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3396,7 +3396,7 @@ static int hns3_reset_notify_down_enet(struct hnae3_handle *handle)
 	struct net_device *ndev = kinfo->netdev;
 
 	if (!netif_running(ndev))
-		return -EIO;
+		return 0;
 
 	return hns3_nic_net_stop(ndev);
 }
-- 
cgit v1.2.3


From d62eccaed41db5d231c597e1b019b13d7c760d6e Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Mon, 16 Jul 2018 16:36:24 +0100
Subject: net: hns3: remove unnecessary ring configuration operation while
 resetting

The configuration of the ring will be used to reinitialize the
ring after the hardware reset is completed. So we should not
release and reacquire this configuration during reset.

Fixes: bb6b94a896d4 ("net: hns3: Add reset interface implementation in client")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 829644665aa8..24f82b774d7e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3436,10 +3436,6 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle)
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
-	ret = hns3_get_ring_config(priv);
-	if (ret)
-		return ret;
-
 	ret = hns3_nic_init_vector_data(priv);
 	if (ret)
 		return ret;
@@ -3471,10 +3467,6 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
 	if (ret)
 		netdev_err(netdev, "uninit ring error\n");
 
-	hns3_put_ring_config(priv);
-
-	priv->ring_data = NULL;
-
 	hns3_uninit_mac_addr(netdev);
 
 	return ret;
-- 
cgit v1.2.3


From 82b5321460005ac5d34996e17f5a51a4004a1e14 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Mon, 16 Jul 2018 16:36:25 +0100
Subject: net: hns3: Fix for reset_level default assignment probelm

handle->reset_level is assigned to HNAE3_NONE_RESET when client is
initialized, if a tx timeout happens right after initialization,
then handle->reset_level is not resetted to HNAE3_FUNC_RESET in
hclge_reset_event, which will cause reset event not properly
handled problem.

This patch fixes it by setting handle->reset_level properly when
client is initialized.

Fixes: 6d4c3981a8d8 ("net: hns3: Changes to make enet watchdog timeout func common for PF/VF")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 24f82b774d7e..29be96e5cc47 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -3085,7 +3085,6 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->dev = &pdev->dev;
 	priv->netdev = netdev;
 	priv->ae_handle = handle;
-	priv->ae_handle->reset_level = HNAE3_NONE_RESET;
 	priv->ae_handle->last_reset_time = jiffies;
 	priv->tx_timeout_count = 0;
 
@@ -3106,6 +3105,11 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	/* Carrier off reporting is important to ethtool even BEFORE open */
 	netif_carrier_off(netdev);
 
+	if (handle->flags & HNAE3_SUPPORT_VF)
+		handle->reset_level = HNAE3_VF_RESET;
+	else
+		handle->reset_level = HNAE3_FUNC_RESET;
+
 	ret = hns3_get_ring_config(priv);
 	if (ret) {
 		ret = -ENOMEM;
-- 
cgit v1.2.3


From cf4103c699c2b3dd88bea169f47ad75d872b4a80 Mon Sep 17 00:00:00 2001
From: Fuyun Liang <liangfuyun1@huawei.com>
Date: Mon, 16 Jul 2018 16:36:26 +0100
Subject: net: hns3: Fix for using wrong mask and shift in
 hclge_get_ring_chain_from_mbx

HCLGE_INT_GL_IDX_M and HCLGE_INT_GL_IDX_S are used to set fireware
cmd. When getting int_gl value from mailbox message, we should use
HNAE3_RING_GL_IDX_M and HNAE3_RING_GL_IDX_S.

Fixes: 79eee4108541 ("net: hns3: add int_gl_idx setup for VF")
Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 50ae2f8f188d..9d36bccde31b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -131,8 +131,8 @@ static int hclge_get_ring_chain_from_mbx(
 	hnae3_set_bit(ring_chain->flag, HNAE3_RING_TYPE_B, req->msg[3]);
 	ring_chain->tqp_index =
 			hclge_get_queue_id(vport->nic.kinfo.tqp[req->msg[4]]);
-	hnae3_set_field(ring_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
-			HCLGE_INT_GL_IDX_S,
+	hnae3_set_field(ring_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+			HNAE3_RING_GL_IDX_S,
 			req->msg[5]);
 
 	cur_chain = ring_chain;
@@ -151,8 +151,8 @@ static int hclge_get_ring_chain_from_mbx(
 			[req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
 			HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 1]]);
 
-		hnae3_set_field(new_chain->int_gl_idx, HCLGE_INT_GL_IDX_M,
-				HCLGE_INT_GL_IDX_S,
+		hnae3_set_field(new_chain->int_gl_idx, HNAE3_RING_GL_IDX_M,
+				HNAE3_RING_GL_IDX_S,
 				req->msg[HCLGE_MBX_RING_NODE_VARIABLE_NUM * i +
 				HCLGE_MBX_RING_MAP_BASIC_MSG_NUM + 2]);
 
-- 
cgit v1.2.3


From 5550aa4d4771f61f5119b45e8de7dd6f66060817 Mon Sep 17 00:00:00 2001
From: Fuyun Liang <liangfuyun1@huawei.com>
Date: Mon, 16 Jul 2018 16:36:27 +0100
Subject: net: hns3: Fix comments for hclge_get_ring_chain_from_mbx

Actually, hclge_get_ring_chain_from_mbx is used to get ring type, tqp id,
and int_gl index from mailbox message. So the comments is incorrect. This
patch fixes it.

Fixes: dde1a86e93ca ("net: hns3: Add mailbox support to PF driver")
Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
index 9d36bccde31b..f34851c91eb3 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c
@@ -104,13 +104,15 @@ static void hclge_free_vector_ring_chain(struct hnae3_ring_chain_node *head)
 	}
 }
 
-/* hclge_get_ring_chain_from_mbx: get ring type & tqpid from mailbox message
+/* hclge_get_ring_chain_from_mbx: get ring type & tqp id & int_gl idx
+ * from mailbox message
  * msg[0]: opcode
  * msg[1]: <not relevant to this function>
  * msg[2]: ring_num
  * msg[3]: first ring type (TX|RX)
  * msg[4]: first tqp id
- * msg[5] ~ msg[14]: other ring type and tqp id
+ * msg[5]: first int_gl idx
+ * msg[6] ~ msg[14]: other ring type, tqp id and int_gl idx
  */
 static int hclge_get_ring_chain_from_mbx(
 			struct hclge_mbx_vf_to_pf_cmd *req,
-- 
cgit v1.2.3


From d95768d3cccd0bfb258f04e0fa21768332b153a0 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 12 Jul 2018 07:42:49 +1000
Subject: docs: networking: Add failover docs to index

Currently we have rst format docs for the failover and net_failover
modules however these docs are not linked to within the index.

Add `failover` and `net_failover` to the networking documentation index.

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/index.rst | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index fec8588a588e..6123a7e9e1da 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -15,6 +15,8 @@ Contents:
    kapi
    z8530book
    msg_zerocopy
+   failover
+   net_failover
 
 .. only::  subproject
 
-- 
cgit v1.2.3


From 2880984970ddf3f3a4600f1725621792352b8627 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 12 Jul 2018 07:42:50 +1000
Subject: docs: networking: Fix failover build warnings

Currently building the net_failover docs causes a bunch of warnings to
be emitted.  These warnings are all related to indentation and correctly
highlight missing '::' (for code sections).  It looks, from other rst
files in Documentation, that the first column should be indented 2
spaces.

Add '::' before code snippets and indent all snippets uniformly starting
with 2 spaces.

Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/net_failover.rst | 111 +++++++++++++++---------------
 1 file changed, 57 insertions(+), 54 deletions(-)

diff --git a/Documentation/networking/net_failover.rst b/Documentation/networking/net_failover.rst
index 70ca2f5800c4..06c97dcb57ca 100644
--- a/Documentation/networking/net_failover.rst
+++ b/Documentation/networking/net_failover.rst
@@ -36,37 +36,39 @@ feature on the virtio-net interface and assign the same MAC address to both
 virtio-net and VF interfaces.
 
 Here is an example XML snippet that shows such configuration.
-
- <interface type='network'>
-   <mac address='52:54:00:00:12:53'/>
-   <source network='enp66s0f0_br'/>
-   <target dev='tap01'/>
-   <model type='virtio'/>
-   <driver name='vhost' queues='4'/>
-   <link state='down'/>
-   <address type='pci' domain='0x0000' bus='0x00' slot='0x0a' function='0x0'/>
- </interface>
- <interface type='hostdev' managed='yes'>
-   <mac address='52:54:00:00:12:53'/>
-   <source>
-     <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
-   </source>
-   <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
- </interface>
+::
+
+  <interface type='network'>
+    <mac address='52:54:00:00:12:53'/>
+    <source network='enp66s0f0_br'/>
+    <target dev='tap01'/>
+    <model type='virtio'/>
+    <driver name='vhost' queues='4'/>
+    <link state='down'/>
+    <address type='pci' domain='0x0000' bus='0x00' slot='0x0a' function='0x0'/>
+  </interface>
+  <interface type='hostdev' managed='yes'>
+    <mac address='52:54:00:00:12:53'/>
+    <source>
+      <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
+    </source>
+    <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
+  </interface>
 
 Booting a VM with the above configuration will result in the following 3
 netdevs created in the VM.
-
-4: ens10: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
-    link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
-    inet 192.168.12.53/24 brd 192.168.12.255 scope global dynamic ens10
-       valid_lft 42482sec preferred_lft 42482sec
-    inet6 fe80::97d8:db2:8c10:b6d6/64 scope link
-       valid_lft forever preferred_lft forever
-5: ens10nsby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel master ens10 state UP group default qlen 1000
-    link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
-7: ens11: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq master ens10 state UP group default qlen 1000
-    link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+::
+
+  4: ens10: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc noqueue state UP group default qlen 1000
+      link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+      inet 192.168.12.53/24 brd 192.168.12.255 scope global dynamic ens10
+         valid_lft 42482sec preferred_lft 42482sec
+      inet6 fe80::97d8:db2:8c10:b6d6/64 scope link
+         valid_lft forever preferred_lft forever
+  5: ens10nsby: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc fq_codel master ens10 state UP group default qlen 1000
+      link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
+  7: ens11: <BROADCAST,MULTICAST,UP,LOWER_UP> mtu 1500 qdisc mq master ens10 state UP group default qlen 1000
+      link/ether 52:54:00:00:12:53 brd ff:ff:ff:ff:ff:ff
 
 ens10 is the 'failover' master netdev, ens10nsby and ens11 are the slave
 'standby' and 'primary' netdevs respectively.
@@ -80,37 +82,38 @@ the paravirtual datapath when the VF is unplugged.
 
 Here is a sample script that shows the steps to initiate live migration on
 the source hypervisor.
+::
 
-# cat vf_xml
-<interface type='hostdev' managed='yes'>
-  <mac address='52:54:00:00:12:53'/>
-  <source>
-    <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
-  </source>
-  <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
-</interface>
+  # cat vf_xml
+  <interface type='hostdev' managed='yes'>
+    <mac address='52:54:00:00:12:53'/>
+    <source>
+      <address type='pci' domain='0x0000' bus='0x42' slot='0x02' function='0x5'/>
+    </source>
+    <address type='pci' domain='0x0000' bus='0x00' slot='0x0b' function='0x0'/>
+  </interface>
 
-# Source Hypervisor
-#!/bin/bash
+  # Source Hypervisor
+  #!/bin/bash
 
-DOMAIN=fedora27-tap01
-PF=enp66s0f0
-VF_NUM=5
-TAP_IF=tap01
-VF_XML=
+  DOMAIN=fedora27-tap01
+  PF=enp66s0f0
+  VF_NUM=5
+  TAP_IF=tap01
+  VF_XML=
 
-MAC=52:54:00:00:12:53
-ZERO_MAC=00:00:00:00:00:00
+  MAC=52:54:00:00:12:53
+  ZERO_MAC=00:00:00:00:00:00
 
-virsh domif-setlink $DOMAIN $TAP_IF up
-bridge fdb del $MAC dev $PF master
-virsh detach-device $DOMAIN $VF_XML
-ip link set $PF vf $VF_NUM mac $ZERO_MAC
+  virsh domif-setlink $DOMAIN $TAP_IF up
+  bridge fdb del $MAC dev $PF master
+  virsh detach-device $DOMAIN $VF_XML
+  ip link set $PF vf $VF_NUM mac $ZERO_MAC
 
-virsh migrate --live $DOMAIN qemu+ssh://$REMOTE_HOST/system
+  virsh migrate --live $DOMAIN qemu+ssh://$REMOTE_HOST/system
 
-# Destination Hypervisor
-#!/bin/bash
+  # Destination Hypervisor
+  #!/bin/bash
 
-virsh attach-device $DOMAIN $VF_XML
-virsh domif-setlink $DOMAIN $TAP_IF down
+  virsh attach-device $DOMAIN $VF_XML
+  virsh domif-setlink $DOMAIN $TAP_IF down
-- 
cgit v1.2.3


From eb5f43d45b3b3c239b9ca0fde6eee11244a57346 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Mon, 16 Jul 2018 14:40:09 +0100
Subject: drm/i915/selftests: Exercise reset to break stuck GTT eviction

We must be able to reset the GPU while we are waiting on it to perform
an eviction (unbinding an active vma). So attach a spinning request to a
target vma and try and it evict it from a thread to see if that blocks
indefinitely.

v2: Add a wait for the thread to start just in case that takes more than
10ms...
v3: complete() not completion_done() to signal the completion.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180716134009.13143-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/intel_hangcheck.c | 171 ++++++++++++++++++++++-
 1 file changed, 169 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
index 73462a65a330..65d66cdedd26 100644
--- a/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
+++ b/drivers/gpu/drm/i915/selftests/intel_hangcheck.c
@@ -27,6 +27,7 @@
 #include "../i915_selftest.h"
 #include "i915_random.h"
 #include "igt_flush_test.h"
+#include "igt_wedge_me.h"
 
 #include "mock_context.h"
 #include "mock_drm.h"
@@ -921,7 +922,7 @@ static u32 fake_hangcheck(struct i915_request *rq, u32 mask)
 	return reset_count;
 }
 
-static int igt_wait_reset(void *arg)
+static int igt_reset_wait(void *arg)
 {
 	struct drm_i915_private *i915 = arg;
 	struct i915_request *rq;
@@ -995,6 +996,170 @@ unlock:
 	return err;
 }
 
+struct evict_vma {
+	struct completion completion;
+	struct i915_vma *vma;
+};
+
+static int evict_vma(void *data)
+{
+	struct evict_vma *arg = data;
+	struct i915_address_space *vm = arg->vma->vm;
+	struct drm_i915_private *i915 = vm->i915;
+	struct drm_mm_node evict = arg->vma->node;
+	int err;
+
+	complete(&arg->completion);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = i915_gem_evict_for_node(vm, &evict, 0);
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	return err;
+}
+
+static int __igt_reset_evict_vma(struct drm_i915_private *i915,
+				 struct i915_address_space *vm)
+{
+	struct drm_i915_gem_object *obj;
+	struct task_struct *tsk = NULL;
+	struct i915_request *rq;
+	struct evict_vma arg;
+	struct hang h;
+	int err;
+
+	if (!intel_engine_can_store_dword(i915->engine[RCS]))
+		return 0;
+
+	/* Check that we can recover an unbind stuck on a hanging request */
+
+	global_reset_lock(i915);
+
+	mutex_lock(&i915->drm.struct_mutex);
+	err = hang_init(&h, i915);
+	if (err)
+		goto unlock;
+
+	obj = i915_gem_object_create_internal(i915, PAGE_SIZE);
+	if (IS_ERR(obj)) {
+		err = PTR_ERR(obj);
+		goto fini;
+	}
+
+	arg.vma = i915_vma_instance(obj, vm, NULL);
+	if (IS_ERR(arg.vma)) {
+		err = PTR_ERR(arg.vma);
+		goto out_obj;
+	}
+
+	rq = hang_create_request(&h, i915->engine[RCS]);
+	if (IS_ERR(rq)) {
+		err = PTR_ERR(rq);
+		goto out_obj;
+	}
+
+	err = i915_vma_pin(arg.vma, 0, 0,
+			   i915_vma_is_ggtt(arg.vma) ? PIN_GLOBAL : PIN_USER);
+	if (err)
+		goto out_obj;
+
+	err = i915_vma_move_to_active(arg.vma, rq, EXEC_OBJECT_WRITE);
+	i915_vma_unpin(arg.vma);
+
+	i915_request_get(rq);
+	i915_request_add(rq);
+	if (err)
+		goto out_rq;
+
+	mutex_unlock(&i915->drm.struct_mutex);
+
+	if (!wait_until_running(&h, rq)) {
+		struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+		pr_err("%s: Failed to start request %x, at %x\n",
+		       __func__, rq->fence.seqno, hws_seqno(&h, rq));
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
+
+		i915_gem_set_wedged(i915);
+		goto out_reset;
+	}
+
+	init_completion(&arg.completion);
+
+	tsk = kthread_run(evict_vma, &arg, "igt/evict_vma");
+	if (IS_ERR(tsk)) {
+		err = PTR_ERR(tsk);
+		tsk = NULL;
+		goto out_reset;
+	}
+
+	wait_for_completion(&arg.completion);
+
+	if (wait_for(waitqueue_active(&rq->execute), 10)) {
+		struct drm_printer p = drm_info_printer(i915->drm.dev);
+
+		pr_err("igt/evict_vma kthread did not wait\n");
+		intel_engine_dump(rq->engine, &p, "%s\n", rq->engine->name);
+
+		i915_gem_set_wedged(i915);
+		goto out_reset;
+	}
+
+out_reset:
+	fake_hangcheck(rq, intel_engine_flag(rq->engine));
+
+	if (tsk) {
+		struct igt_wedge_me w;
+
+		/* The reset, even indirectly, should take less than 10ms. */
+		igt_wedge_on_timeout(&w, i915, HZ / 10 /* 100ms timeout*/)
+			err = kthread_stop(tsk);
+	}
+
+	mutex_lock(&i915->drm.struct_mutex);
+out_rq:
+	i915_request_put(rq);
+out_obj:
+	i915_gem_object_put(obj);
+fini:
+	hang_fini(&h);
+unlock:
+	mutex_unlock(&i915->drm.struct_mutex);
+	global_reset_unlock(i915);
+
+	if (i915_terminally_wedged(&i915->gpu_error))
+		return -EIO;
+
+	return err;
+}
+
+static int igt_reset_evict_ggtt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+
+	return __igt_reset_evict_vma(i915, &i915->ggtt.vm);
+}
+
+static int igt_reset_evict_ppgtt(void *arg)
+{
+	struct drm_i915_private *i915 = arg;
+	struct i915_gem_context *ctx;
+	int err;
+
+	mutex_lock(&i915->drm.struct_mutex);
+	ctx = kernel_context(i915);
+	mutex_unlock(&i915->drm.struct_mutex);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	err = 0;
+	if (ctx->ppgtt) /* aliasing == global gtt locking, covered above */
+		err = __igt_reset_evict_vma(i915, &ctx->ppgtt->vm);
+
+	kernel_context_close(ctx);
+	return err;
+}
+
 static int wait_for_others(struct drm_i915_private *i915,
 			   struct intel_engine_cs *exclude)
 {
@@ -1240,8 +1405,10 @@ int intel_hangcheck_live_selftests(struct drm_i915_private *i915)
 		SUBTEST(igt_reset_idle_engine),
 		SUBTEST(igt_reset_active_engine),
 		SUBTEST(igt_reset_engines),
-		SUBTEST(igt_wait_reset),
 		SUBTEST(igt_reset_queue),
+		SUBTEST(igt_reset_wait),
+		SUBTEST(igt_reset_evict_ggtt),
+		SUBTEST(igt_reset_evict_ppgtt),
 		SUBTEST(igt_handle_error),
 	};
 	bool saved_hangcheck;
-- 
cgit v1.2.3


From 377179cd28cd417dcfb4396edb824533431e607e Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:05:56 -0400
Subject: security: define new LSM hook named security_kernel_load_data

Differentiate between the kernel reading a file specified by userspace
from the kernel loading a buffer containing data provided by userspace.
This patch defines a new LSM hook named security_kernel_load_data().

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Luis R. Rodriguez <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 include/linux/lsm_hooks.h |  6 ++++++
 include/linux/security.h  | 27 +++++++++++++++++++++++++++
 security/security.c       |  5 +++++
 3 files changed, 38 insertions(+)

diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index 8f1131c8dd54..a08bc2587b96 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -576,6 +576,10 @@
  *	userspace to load a kernel module with the given name.
  *	@kmod_name name of the module requested by the kernel
  *	Return 0 if successful.
+ * @kernel_load_data:
+ *	Load data provided by userspace.
+ *	@id kernel load data identifier
+ *	Return 0 if permission is granted.
  * @kernel_read_file:
  *	Read a file specified by userspace.
  *	@file contains the file structure pointing to the file being read
@@ -1582,6 +1586,7 @@ union security_list_options {
 	int (*kernel_act_as)(struct cred *new, u32 secid);
 	int (*kernel_create_files_as)(struct cred *new, struct inode *inode);
 	int (*kernel_module_request)(char *kmod_name);
+	int (*kernel_load_data)(enum kernel_load_data_id id);
 	int (*kernel_read_file)(struct file *file, enum kernel_read_file_id id);
 	int (*kernel_post_read_file)(struct file *file, char *buf, loff_t size,
 				     enum kernel_read_file_id id);
@@ -1872,6 +1877,7 @@ struct security_hook_heads {
 	struct hlist_head cred_getsecid;
 	struct hlist_head kernel_act_as;
 	struct hlist_head kernel_create_files_as;
+	struct hlist_head kernel_load_data;
 	struct hlist_head kernel_read_file;
 	struct hlist_head kernel_post_read_file;
 	struct hlist_head kernel_module_request;
diff --git a/include/linux/security.h b/include/linux/security.h
index 63030c85ee19..3410acfe139c 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -159,6 +159,27 @@ extern int mmap_min_addr_handler(struct ctl_table *table, int write,
 typedef int (*initxattrs) (struct inode *inode,
 			   const struct xattr *xattr_array, void *fs_data);
 
+
+/* Keep the kernel_load_data_id enum in sync with kernel_read_file_id */
+#define __data_id_enumify(ENUM, dummy) LOADING_ ## ENUM,
+#define __data_id_stringify(dummy, str) #str,
+
+enum kernel_load_data_id {
+	__kernel_read_file_id(__data_id_enumify)
+};
+
+static const char * const kernel_load_data_str[] = {
+	__kernel_read_file_id(__data_id_stringify)
+};
+
+static inline const char *kernel_load_data_id_str(enum kernel_load_data_id id)
+{
+	if ((unsigned)id >= LOADING_MAX_ID)
+		return kernel_load_data_str[LOADING_UNKNOWN];
+
+	return kernel_load_data_str[id];
+}
+
 #ifdef CONFIG_SECURITY
 
 struct security_mnt_opts {
@@ -320,6 +341,7 @@ void security_cred_getsecid(const struct cred *c, u32 *secid);
 int security_kernel_act_as(struct cred *new, u32 secid);
 int security_kernel_create_files_as(struct cred *new, struct inode *inode);
 int security_kernel_module_request(char *kmod_name);
+int security_kernel_load_data(enum kernel_load_data_id id);
 int security_kernel_read_file(struct file *file, enum kernel_read_file_id id);
 int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 				   enum kernel_read_file_id id);
@@ -909,6 +931,11 @@ static inline int security_kernel_module_request(char *kmod_name)
 	return 0;
 }
 
+static inline int security_kernel_load_data(enum kernel_load_data_id id)
+{
+	return 0;
+}
+
 static inline int security_kernel_read_file(struct file *file,
 					    enum kernel_read_file_id id)
 {
diff --git a/security/security.c b/security/security.c
index 68f46d849abe..c2de2f134854 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1056,6 +1056,11 @@ int security_kernel_post_read_file(struct file *file, char *buf, loff_t size,
 }
 EXPORT_SYMBOL_GPL(security_kernel_post_read_file);
 
+int security_kernel_load_data(enum kernel_load_data_id id)
+{
+	return call_int_hook(kernel_load_data, 0, id);
+}
+
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
 			     int flags)
 {
-- 
cgit v1.2.3


From a210fd32a46bae6d05b43860fe3b47732501d63b Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:05:57 -0400
Subject: kexec: add call to LSM hook in original kexec_load syscall

In order for LSMs and IMA-appraisal to differentiate between kexec_load
and kexec_file_load syscalls, both the original and new syscalls must
call an LSM hook.  This patch adds a call to security_kernel_load_data()
in the original kexec_load syscall.

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Acked-by: Serge Hallyn <serge@hallyn.com>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 kernel/kexec.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/kernel/kexec.c b/kernel/kexec.c
index aed8fb2564b3..68559808fdfa 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -11,6 +11,7 @@
 #include <linux/capability.h>
 #include <linux/mm.h>
 #include <linux/file.h>
+#include <linux/security.h>
 #include <linux/kexec.h>
 #include <linux/mutex.h>
 #include <linux/list.h>
@@ -195,10 +196,17 @@ out:
 static inline int kexec_load_check(unsigned long nr_segments,
 				   unsigned long flags)
 {
+	int result;
+
 	/* We only trust the superuser with rebooting the system. */
 	if (!capable(CAP_SYS_BOOT) || kexec_load_disabled)
 		return -EPERM;
 
+	/* Permit LSMs and IMA to fail the kexec */
+	result = security_kernel_load_data(LOADING_KEXEC_IMAGE);
+	if (result < 0)
+		return result;
+
 	/*
 	 * Verify we have a legal set of flags
 	 * This leaves us room for future extensions.
-- 
cgit v1.2.3


From 16c267aac86b463b1fcccd43c89f4c8e5c5c86fa Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:05:58 -0400
Subject: ima: based on policy require signed kexec kernel images

The original kexec_load syscall can not verify file signatures, nor can
the kexec image be measured.  Based on policy, deny the kexec_load
syscall.

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Kees Cook <keescook@chromium.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 include/linux/ima.h                 |  7 +++++++
 security/integrity/ima/ima.h        |  1 +
 security/integrity/ima/ima_main.c   | 27 +++++++++++++++++++++++++++
 security/integrity/ima/ima_policy.c |  2 ++
 security/security.c                 |  7 ++++++-
 5 files changed, 43 insertions(+), 1 deletion(-)

diff --git a/include/linux/ima.h b/include/linux/ima.h
index 0e4647e0eb60..84806b54b50a 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -11,6 +11,7 @@
 #define _LINUX_IMA_H
 
 #include <linux/fs.h>
+#include <linux/security.h>
 #include <linux/kexec.h>
 struct linux_binprm;
 
@@ -19,6 +20,7 @@ extern int ima_bprm_check(struct linux_binprm *bprm);
 extern int ima_file_check(struct file *file, int mask, int opened);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
+extern int ima_load_data(enum kernel_load_data_id id);
 extern int ima_read_file(struct file *file, enum kernel_read_file_id id);
 extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
@@ -49,6 +51,11 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot)
 	return 0;
 }
 
+static inline int ima_load_data(enum kernel_load_data_id id)
+{
+	return 0;
+}
+
 static inline int ima_read_file(struct file *file, enum kernel_read_file_id id)
 {
 	return 0;
diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 354bb5716ce3..78c15264b17b 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -232,6 +232,7 @@ int ima_policy_show(struct seq_file *m, void *v);
 #define IMA_APPRAISE_MODULES	0x08
 #define IMA_APPRAISE_FIRMWARE	0x10
 #define IMA_APPRAISE_POLICY	0x20
+#define IMA_APPRAISE_KEXEC	0x40
 
 #ifdef CONFIG_IMA_APPRAISE
 int ima_appraise_measurement(enum ima_hooks func,
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index dca44cf7838e..71fecfef0939 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -496,6 +496,33 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 				   MAY_READ, func, 0);
 }
 
+/**
+ * ima_load_data - appraise decision based on policy
+ * @id: kernel load data caller identifier
+ *
+ * Callers of this LSM hook can not measure, appraise, or audit the
+ * data provided by userspace.  Enforce policy rules requring a file
+ * signature (eg. kexec'ed kernel image).
+ *
+ * For permission return 0, otherwise return -EACCES.
+ */
+int ima_load_data(enum kernel_load_data_id id)
+{
+	if ((ima_appraise & IMA_APPRAISE_ENFORCE) != IMA_APPRAISE_ENFORCE)
+		return 0;
+
+	switch (id) {
+	case LOADING_KEXEC_IMAGE:
+		if (ima_appraise & IMA_APPRAISE_KEXEC) {
+			pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n");
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		}
+	default:
+		break;
+	}
+	return 0;
+}
+
 static int __init init_ima(void)
 {
 	int error;
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index cdcc9a7b4e24..d5b4958decc5 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -448,6 +448,8 @@ static int ima_appraise_flag(enum ima_hooks func)
 		return IMA_APPRAISE_FIRMWARE;
 	else if (func == POLICY_CHECK)
 		return IMA_APPRAISE_POLICY;
+	else if (func == KEXEC_KERNEL_CHECK)
+		return IMA_APPRAISE_KEXEC;
 	return 0;
 }
 
diff --git a/security/security.c b/security/security.c
index c2de2f134854..4927e7cc7d96 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1058,7 +1058,12 @@ EXPORT_SYMBOL_GPL(security_kernel_post_read_file);
 
 int security_kernel_load_data(enum kernel_load_data_id id)
 {
-	return call_int_hook(kernel_load_data, 0, id);
+	int ret;
+
+	ret = call_int_hook(kernel_load_data, 0, id);
+	if (ret)
+		return ret;
+	return ima_load_data(id);
 }
 
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
-- 
cgit v1.2.3


From 6e852651f28eee851069c7d40989281fae4bf9d2 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:05:59 -0400
Subject: firmware: add call to LSM hook before firmware sysfs fallback

Add an LSM hook prior to allowing firmware sysfs fallback loading.

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Acked-by: Luis R. Rodriguez <mcgrof@kernel.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 drivers/base/firmware_loader/fallback.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/base/firmware_loader/fallback.c b/drivers/base/firmware_loader/fallback.c
index 7f732744f0d3..202324291542 100644
--- a/drivers/base/firmware_loader/fallback.c
+++ b/drivers/base/firmware_loader/fallback.c
@@ -651,6 +651,8 @@ static bool fw_force_sysfs_fallback(enum fw_opt opt_flags)
 
 static bool fw_run_sysfs_fallback(enum fw_opt opt_flags)
 {
+	int ret;
+
 	if (fw_fallback_config.ignore_sysfs_fallback) {
 		pr_info_once("Ignoring firmware sysfs fallback due to sysctl knob\n");
 		return false;
@@ -659,6 +661,11 @@ static bool fw_run_sysfs_fallback(enum fw_opt opt_flags)
 	if ((opt_flags & FW_OPT_NOFALLBACK))
 		return false;
 
+	/* Also permit LSMs and IMA to fail firmware sysfs fallback */
+	ret = security_kernel_load_data(LOADING_FIRMWARE);
+	if (ret < 0)
+		return ret;
+
 	return fw_force_sysfs_fallback(opt_flags);
 }
 
-- 
cgit v1.2.3


From fed2512a7ccc8fc4b8e1de22925d127e4caac300 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:06:00 -0400
Subject: ima: based on policy require signed firmware (sysfs fallback)

With an IMA policy requiring signed firmware, this patch prevents
the sysfs fallback method of loading firmware.

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Matthew Garrett <mjg59@google.com>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 security/integrity/ima/ima_main.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 71fecfef0939..e467664965e7 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -472,8 +472,10 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 
 	if (!file && read_id == READING_FIRMWARE) {
 		if ((ima_appraise & IMA_APPRAISE_FIRMWARE) &&
-		    (ima_appraise & IMA_APPRAISE_ENFORCE))
+		    (ima_appraise & IMA_APPRAISE_ENFORCE)) {
+			pr_err("Prevent firmware loading_store.\n");
 			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		}
 		return 0;
 	}
 
@@ -517,6 +519,12 @@ int ima_load_data(enum kernel_load_data_id id)
 			pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n");
 			return -EACCES;	/* INTEGRITY_UNKNOWN */
 		}
+		break;
+	case LOADING_FIRMWARE:
+		if (ima_appraise & IMA_APPRAISE_FIRMWARE) {
+			pr_err("Prevent firmware sysfs fallback loading.\n");
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		}
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From ef96837b0de4af47732e2a8ebf5c18e8a885ded6 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:06:01 -0400
Subject: ima: add build time policy

IMA by default does not measure, appraise or audit files, but can be
enabled at runtime by specifying a builtin policy on the boot command line
or by loading a custom policy.

This patch defines a build time policy, which verifies kernel modules,
firmware, kexec image, and/or the IMA policy signatures.  This build time
policy is automatically enabled at runtime and persists after loading a
custom policy.

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 security/integrity/ima/Kconfig      | 58 +++++++++++++++++++++++++++++++++++++
 security/integrity/ima/ima_policy.c | 46 +++++++++++++++++++++++++++--
 2 files changed, 101 insertions(+), 3 deletions(-)

diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 6a8f67714c83..004919d9bf09 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -156,6 +156,64 @@ config IMA_APPRAISE
 	  <http://linux-ima.sourceforge.net>
 	  If unsure, say N.
 
+config IMA_APPRAISE_BUILD_POLICY
+	bool "IMA build time configured policy rules"
+	depends on IMA_APPRAISE && INTEGRITY_ASYMMETRIC_KEYS
+	default n
+	help
+	  This option defines an IMA appraisal policy at build time, which
+	  is enforced at run time without having to specify a builtin
+	  policy name on the boot command line.  The build time appraisal
+	  policy rules persist after loading a custom policy.
+
+	  Depending on the rules configured, this policy may require kernel
+	  modules, firmware, the kexec kernel image, and/or the IMA policy
+	  to be signed.  Unsigned files might prevent the system from
+	  booting or applications from working properly.
+
+config IMA_APPRAISE_REQUIRE_FIRMWARE_SIGS
+	bool "Appraise firmware signatures"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  This option defines a policy requiring all firmware to be signed,
+	  including the regulatory.db.  If both this option and
+	  CFG80211_REQUIRE_SIGNED_REGDB are enabled, then both signature
+	  verification methods are necessary.
+
+config IMA_APPRAISE_REQUIRE_KEXEC_SIGS
+	bool "Appraise kexec kernel image signatures"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  Enabling this rule will require all kexec'ed kernel images to
+	  be signed and verified by a public key on the trusted IMA
+	  keyring.
+
+	  Kernel image signatures can not be verified by the original
+	  kexec_load syscall.  Enabling this rule will prevent its
+	  usage.
+
+config IMA_APPRAISE_REQUIRE_MODULE_SIGS
+	bool "Appraise kernel modules signatures"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  Enabling this rule will require all kernel modules to be signed
+	  and verified by a public key on the trusted IMA keyring.
+
+	  Kernel module signatures can only be verified by IMA-appraisal,
+	  via the finit_module syscall. Enabling this rule will prevent
+	  the usage of the init_module syscall.
+
+config IMA_APPRAISE_REQUIRE_POLICY_SIGS
+	bool "Appraise IMA policy signature"
+	depends on IMA_APPRAISE_BUILD_POLICY
+	default n
+	help
+	  Enabling this rule will require the IMA policy to be signed and
+	  and verified by a key on the trusted IMA keyring.
+
 config IMA_APPRAISE_BOOTPARAM
 	bool "ima_appraise boot parameter"
 	depends on IMA_APPRAISE
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index d5b4958decc5..1659abb344f9 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -49,6 +49,7 @@
 
 int ima_policy_flag;
 static int temp_ima_appraise;
+static int build_ima_appraise __ro_after_init;
 
 #define MAX_LSM_RULES 6
 enum lsm_rule_types { LSM_OBJ_USER, LSM_OBJ_ROLE, LSM_OBJ_TYPE,
@@ -162,6 +163,25 @@ static struct ima_rule_entry default_appraise_rules[] __ro_after_init = {
 #endif
 };
 
+static struct ima_rule_entry build_appraise_rules[] __ro_after_init = {
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_MODULE_SIGS
+	{.action = APPRAISE, .func = MODULE_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_FIRMWARE_SIGS
+	{.action = APPRAISE, .func = FIRMWARE_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_KEXEC_SIGS
+	{.action = APPRAISE, .func = KEXEC_KERNEL_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+#ifdef CONFIG_IMA_APPRAISE_REQUIRE_POLICY_SIGS
+	{.action = APPRAISE, .func = POLICY_CHECK,
+	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
+#endif
+};
+
 static struct ima_rule_entry secure_boot_rules[] __ro_after_init = {
 	{.action = APPRAISE, .func = MODULE_CHECK,
 	 .flags = IMA_FUNC | IMA_DIGSIG_REQUIRED},
@@ -435,7 +455,7 @@ void ima_update_policy_flag(void)
 			ima_policy_flag |= entry->action;
 	}
 
-	ima_appraise |= temp_ima_appraise;
+	ima_appraise |= (build_ima_appraise | temp_ima_appraise);
 	if (!ima_appraise)
 		ima_policy_flag &= ~IMA_APPRAISE;
 }
@@ -488,8 +508,8 @@ void __init ima_init_policy(void)
 	}
 
 	/*
-	 * Insert the appraise rules requiring file signatures, prior to
-	 * any other appraise rules.
+	 * Insert the builtin "secure_boot" policy rules requiring file
+	 * signatures, prior to any other appraise rules.
 	 */
 	for (i = 0; i < secure_boot_entries; i++) {
 		list_add_tail(&secure_boot_rules[i].list, &ima_default_rules);
@@ -497,6 +517,26 @@ void __init ima_init_policy(void)
 		    ima_appraise_flag(secure_boot_rules[i].func);
 	}
 
+	/*
+	 * Insert the build time appraise rules requiring file signatures
+	 * for both the initial and custom policies, prior to other appraise
+	 * rules.
+	 */
+	for (i = 0; i < ARRAY_SIZE(build_appraise_rules); i++) {
+		struct ima_rule_entry *entry;
+
+		if (!secure_boot_entries)
+			list_add_tail(&build_appraise_rules[i].list,
+				      &ima_default_rules);
+
+		entry = kmemdup(&build_appraise_rules[i], sizeof(*entry),
+				GFP_KERNEL);
+		if (entry)
+			list_add_tail(&entry->list, &ima_policy_rules);
+		build_ima_appraise |=
+			ima_appraise_flag(build_appraise_rules[i].func);
+	}
+
 	for (i = 0; i < appraise_entries; i++) {
 		list_add_tail(&default_appraise_rules[i].list,
 			      &ima_default_rules);
-- 
cgit v1.2.3


From c77b8cdf745d91eca138e7bfa430dc6640b604a0 Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:06:02 -0400
Subject: module: replace the existing LSM hook in init_module

Both the init_module and finit_module syscalls call either directly
or indirectly the security_kernel_read_file LSM hook.  This patch
replaces the direct call in init_module with a call to the new
security_kernel_load_data hook and makes the corresponding changes
in SELinux, LoadPin, and IMA.

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: Jeff Vander Stoep <jeffv@google.com>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Cc: Kees Cook <keescook@chromium.org>
Acked-by: Jessica Yu <jeyu@kernel.org>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 kernel/module.c                   |  2 +-
 security/integrity/ima/ima_main.c | 23 ++++++++++-------------
 security/loadpin/loadpin.c        |  6 ++++++
 security/selinux/hooks.c          | 15 +++++++++++++++
 4 files changed, 32 insertions(+), 14 deletions(-)

diff --git a/kernel/module.c b/kernel/module.c
index f475f30eed8c..a7615d661910 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -2876,7 +2876,7 @@ static int copy_module_from_user(const void __user *umod, unsigned long len,
 	if (info->len < sizeof(*(info->hdr)))
 		return -ENOEXEC;
 
-	err = security_kernel_read_file(NULL, READING_MODULE);
+	err = security_kernel_load_data(LOADING_MODULE);
 	if (err)
 		return err;
 
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index e467664965e7..ef349a761609 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -429,16 +429,6 @@ void ima_post_path_mknod(struct dentry *dentry)
  */
 int ima_read_file(struct file *file, enum kernel_read_file_id read_id)
 {
-	bool sig_enforce = is_module_sig_enforced();
-
-	if (!file && read_id == READING_MODULE) {
-		if (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES) &&
-		    (ima_appraise & IMA_APPRAISE_ENFORCE)) {
-			pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n");
-			return -EACCES;	/* INTEGRITY_UNKNOWN */
-		}
-		return 0;	/* We rely on module signature checking */
-	}
 	return 0;
 }
 
@@ -479,9 +469,6 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
 		return 0;
 	}
 
-	if (!file && read_id == READING_MODULE) /* MODULE_SIG_FORCE enabled */
-		return 0;
-
 	/* permit signed certs */
 	if (!file && read_id == READING_X509_CERTIFICATE)
 		return 0;
@@ -510,6 +497,8 @@ int ima_post_read_file(struct file *file, void *buf, loff_t size,
  */
 int ima_load_data(enum kernel_load_data_id id)
 {
+	bool sig_enforce;
+
 	if ((ima_appraise & IMA_APPRAISE_ENFORCE) != IMA_APPRAISE_ENFORCE)
 		return 0;
 
@@ -525,6 +514,14 @@ int ima_load_data(enum kernel_load_data_id id)
 			pr_err("Prevent firmware sysfs fallback loading.\n");
 			return -EACCES;	/* INTEGRITY_UNKNOWN */
 		}
+		break;
+	case LOADING_MODULE:
+		sig_enforce = is_module_sig_enforced();
+
+		if (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES)) {
+			pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n");
+			return -EACCES;	/* INTEGRITY_UNKNOWN */
+		}
 	default:
 		break;
 	}
diff --git a/security/loadpin/loadpin.c b/security/loadpin/loadpin.c
index 5fa191252c8f..0716af28808a 100644
--- a/security/loadpin/loadpin.c
+++ b/security/loadpin/loadpin.c
@@ -173,9 +173,15 @@ static int loadpin_read_file(struct file *file, enum kernel_read_file_id id)
 	return 0;
 }
 
+static int loadpin_load_data(enum kernel_load_data_id id)
+{
+	return loadpin_read_file(NULL, (enum kernel_read_file_id) id);
+}
+
 static struct security_hook_list loadpin_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(sb_free_security, loadpin_sb_free_security),
 	LSM_HOOK_INIT(kernel_read_file, loadpin_read_file),
+	LSM_HOOK_INIT(kernel_load_data, loadpin_load_data),
 };
 
 void __init loadpin_add_hooks(void)
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index 2b5ee5fbd652..a8bf324130f5 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -4073,6 +4073,20 @@ static int selinux_kernel_read_file(struct file *file,
 	return rc;
 }
 
+static int selinux_kernel_load_data(enum kernel_load_data_id id)
+{
+	int rc = 0;
+
+	switch (id) {
+	case LOADING_MODULE:
+		rc = selinux_kernel_module_from_file(NULL);
+	default:
+		break;
+	}
+
+	return rc;
+}
+
 static int selinux_task_setpgid(struct task_struct *p, pid_t pgid)
 {
 	return avc_has_perm(&selinux_state,
@@ -6972,6 +6986,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = {
 	LSM_HOOK_INIT(kernel_act_as, selinux_kernel_act_as),
 	LSM_HOOK_INIT(kernel_create_files_as, selinux_kernel_create_files_as),
 	LSM_HOOK_INIT(kernel_module_request, selinux_kernel_module_request),
+	LSM_HOOK_INIT(kernel_load_data, selinux_kernel_load_data),
 	LSM_HOOK_INIT(kernel_read_file, selinux_kernel_read_file),
 	LSM_HOOK_INIT(task_setpgid, selinux_task_setpgid),
 	LSM_HOOK_INIT(task_getpgid, selinux_task_getpgid),
-- 
cgit v1.2.3


From 4f0496d8ffa3ed5956a2ddee5d84f0246977799d Mon Sep 17 00:00:00 2001
From: Mimi Zohar <zohar@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 14:06:03 -0400
Subject: ima: based on policy warn about loading firmware (pre-allocated
 buffer)

Some systems are memory constrained but they need to load very large
firmwares.  The firmware subsystem allows drivers to request this
firmware be loaded from the filesystem, but this requires that the
entire firmware be loaded into kernel memory first before it's provided
to the driver.  This can lead to a situation where we map the firmware
twice, once to load the firmware into kernel memory and once to copy the
firmware into the final resting place.

To resolve this problem, commit a098ecd2fa7d ("firmware: support loading
into a pre-allocated buffer") introduced request_firmware_into_buf() API
that allows drivers to request firmware be loaded directly into a
pre-allocated buffer.

Do devices using pre-allocated memory run the risk of the firmware being
accessible to the device prior to the completion of IMA's signature
verification any more than when using two buffers? (Refer to mailing list
discussion[1]).

Only on systems with an IOMMU can the access be prevented.  As long as
the signature verification completes prior to the DMA map is performed,
the device can not access the buffer.  This implies that the same buffer
can not be re-used.  Can we ensure the buffer has not been DMA mapped
before using the pre-allocated buffer?

[1] https://lkml.org/lkml/2018/7/10/56

Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 security/integrity/ima/ima_main.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index ef349a761609..dce0a8a217bb 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -429,6 +429,14 @@ void ima_post_path_mknod(struct dentry *dentry)
  */
 int ima_read_file(struct file *file, enum kernel_read_file_id read_id)
 {
+	/*
+	 * READING_FIRMWARE_PREALLOC_BUFFER
+	 *
+	 * Do devices using pre-allocated memory run the risk of the
+	 * firmware being accessible to the device prior to the completion
+	 * of IMA's signature verification any more than when using two
+	 * buffers?
+	 */
 	return 0;
 }
 
-- 
cgit v1.2.3


From 8415afbd86ddd8a268a8450286bc58b2bb3b83d1 Mon Sep 17 00:00:00 2001
From: Eric Huang <JinhuiEric.Huang@amd.com>
Date: Fri, 13 Jul 2018 15:05:10 -0400
Subject: Revert "drm/amd/powerplay: fix performance drop on Vega10"

This reverts commit b87079ec7b4d38efee015367315958ce5495ba93.

SMU FW team ask to remove this version specific code.

Signed-off-by: Eric Huang <JinHuiEric.Huang@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index eb37316cfbf7..1a0dccb3fac1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -2896,11 +2896,6 @@ static int vega10_enable_dpm_tasks(struct pp_hwmgr *hwmgr)
 
 	vega10_enable_disable_PCC_limit_feature(hwmgr, true);
 
-	if ((hwmgr->smu_version == 0x001c2c00) ||
-			(hwmgr->smu_version == 0x001c2d00))
-		smum_send_msg_to_smc_with_parameter(hwmgr,
-				PPSMC_MSG_UpdatePkgPwrPidAlpha, 1);
-
 	smum_send_msg_to_smc_with_parameter(hwmgr,
 		PPSMC_MSG_ConfigureTelemetry, data->config_telemetry);
 
-- 
cgit v1.2.3


From 964d0fbf6301d3dc8dfad19ffab5a06d002d27f1 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Fri, 6 Jul 2018 14:16:54 -0400
Subject: drm/amdgpu: Allow to create BO lists in CS ioctl v3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This change is to support MESA performace optimization.
Modify CS IOCTL to allow its input as command buffer and an array of
buffer handles to create a temporay bo list and then destroy it
when IOCTL completes.
This saves on calling for BO_LIST create and destry IOCTLs in MESA
and by this improves performance.

v2: Avoid inserting the temp list into idr struct.

v3:
Remove idr alloation from amdgpu_bo_list_create.
Remove useless argument from amdgpu_cs_parser_fini
Minor cosmetic stuff.

v4: Revert amdgpu_bo_list_destroy back to static

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h         |  8 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 88 +++++++++++++++++------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c      | 48 +++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c     |  3 +-
 include/uapi/drm/amdgpu_drm.h               |  1 +
 5 files changed, 108 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 53435da158c2..c6c1e8dc919f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -732,6 +732,14 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 			     struct list_head *validated);
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
 void amdgpu_bo_list_free(struct amdgpu_bo_list *list);
+int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
+				      struct drm_amdgpu_bo_list_entry **info_param);
+
+int amdgpu_bo_list_create(struct amdgpu_device *adev,
+				 struct drm_file *filp,
+				 struct drm_amdgpu_bo_list_entry *info,
+				 unsigned num_entries,
+				 struct amdgpu_bo_list **list);
 
 /*
  * GFX stuff
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 92be7f6de197..7679c068c89a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -55,15 +55,15 @@ static void amdgpu_bo_list_release_rcu(struct kref *ref)
 	kfree_rcu(list, rhead);
 }
 
-static int amdgpu_bo_list_create(struct amdgpu_device *adev,
+int amdgpu_bo_list_create(struct amdgpu_device *adev,
 				 struct drm_file *filp,
 				 struct drm_amdgpu_bo_list_entry *info,
 				 unsigned num_entries,
-				 int *id)
+				 struct amdgpu_bo_list **list_out)
 {
-	int r;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
 	struct amdgpu_bo_list *list;
+	int r;
+
 
 	list = kzalloc(sizeof(struct amdgpu_bo_list), GFP_KERNEL);
 	if (!list)
@@ -78,16 +78,7 @@ static int amdgpu_bo_list_create(struct amdgpu_device *adev,
 		return r;
 	}
 
-	/* idr alloc should be called only after initialization of bo list. */
-	mutex_lock(&fpriv->bo_list_lock);
-	r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
-	mutex_unlock(&fpriv->bo_list_lock);
-	if (r < 0) {
-		amdgpu_bo_list_free(list);
-		return r;
-	}
-	*id = r;
-
+	*list_out = list;
 	return 0;
 }
 
@@ -263,55 +254,79 @@ void amdgpu_bo_list_free(struct amdgpu_bo_list *list)
 	kfree(list);
 }
 
-int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
-				struct drm_file *filp)
+int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
+				      struct drm_amdgpu_bo_list_entry **info_param)
 {
+	const void __user *uptr = u64_to_user_ptr(in->bo_info_ptr);
 	const uint32_t info_size = sizeof(struct drm_amdgpu_bo_list_entry);
-
-	struct amdgpu_device *adev = dev->dev_private;
-	struct amdgpu_fpriv *fpriv = filp->driver_priv;
-	union drm_amdgpu_bo_list *args = data;
-	uint32_t handle = args->in.list_handle;
-	const void __user *uptr = u64_to_user_ptr(args->in.bo_info_ptr);
-
 	struct drm_amdgpu_bo_list_entry *info;
-	struct amdgpu_bo_list *list;
-
 	int r;
 
-	info = kvmalloc_array(args->in.bo_number,
-			     sizeof(struct drm_amdgpu_bo_list_entry), GFP_KERNEL);
+	info = kvmalloc_array(in->bo_number, info_size, GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;
 
 	/* copy the handle array from userspace to a kernel buffer */
 	r = -EFAULT;
-	if (likely(info_size == args->in.bo_info_size)) {
-		unsigned long bytes = args->in.bo_number *
-			args->in.bo_info_size;
+	if (likely(info_size == in->bo_info_size)) {
+		unsigned long bytes = in->bo_number *
+			in->bo_info_size;
 
 		if (copy_from_user(info, uptr, bytes))
 			goto error_free;
 
 	} else {
-		unsigned long bytes = min(args->in.bo_info_size, info_size);
+		unsigned long bytes = min(in->bo_info_size, info_size);
 		unsigned i;
 
-		memset(info, 0, args->in.bo_number * info_size);
-		for (i = 0; i < args->in.bo_number; ++i) {
+		memset(info, 0, in->bo_number * info_size);
+		for (i = 0; i < in->bo_number; ++i) {
 			if (copy_from_user(&info[i], uptr, bytes))
 				goto error_free;
 
-			uptr += args->in.bo_info_size;
+			uptr += in->bo_info_size;
 		}
 	}
 
+	*info_param = info;
+	return 0;
+
+error_free:
+	kvfree(info);
+	return r;
+}
+
+int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
+				struct drm_file *filp)
+{
+	struct amdgpu_device *adev = dev->dev_private;
+	struct amdgpu_fpriv *fpriv = filp->driver_priv;
+	union drm_amdgpu_bo_list *args = data;
+	uint32_t handle = args->in.list_handle;
+	struct drm_amdgpu_bo_list_entry *info = NULL;
+	struct amdgpu_bo_list *list;
+	int r;
+
+	r = amdgpu_bo_create_list_entry_array(&args->in, &info);
+	if (r)
+		goto error_free;
+
 	switch (args->in.operation) {
 	case AMDGPU_BO_LIST_OP_CREATE:
 		r = amdgpu_bo_list_create(adev, filp, info, args->in.bo_number,
-					  &handle);
+					  &list);
 		if (r)
 			goto error_free;
+
+		mutex_lock(&fpriv->bo_list_lock);
+		r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
+		mutex_unlock(&fpriv->bo_list_lock);
+		if (r < 0) {
+			amdgpu_bo_list_free(list);
+			return r;
+		}
+
+		handle = r;
 		break;
 
 	case AMDGPU_BO_LIST_OP_DESTROY:
@@ -345,6 +360,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 	return 0;
 
 error_free:
-	kvfree(info);
+	if (info)
+		kvfree(info);
 	return r;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 5a2a5ba29f9a..6d8df76b5a5d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -66,11 +66,35 @@ static int amdgpu_cs_user_fence_chunk(struct amdgpu_cs_parser *p,
 	return 0;
 }
 
-static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
+static int amdgpu_cs_bo_handles_chunk(struct amdgpu_cs_parser *p,
+				      struct drm_amdgpu_bo_list_in *data)
+{
+	int r;
+	struct drm_amdgpu_bo_list_entry *info = NULL;
+
+	r = amdgpu_bo_create_list_entry_array(data, &info);
+	if (r)
+		return r;
+
+	r = amdgpu_bo_list_create(p->adev, p->filp, info, data->bo_number,
+				  &p->bo_list);
+	if (r)
+		goto error_free;
+
+	kvfree(info);
+	return 0;
+
+error_free:
+	if (info)
+		kvfree(info);
+
+	return r;
+}
+
+static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_vm *vm = &fpriv->vm;
-	union drm_amdgpu_cs *cs = data;
 	uint64_t *chunk_array_user;
 	uint64_t *chunk_array;
 	unsigned size, num_ibs = 0;
@@ -164,6 +188,19 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, void *data)
 
 			break;
 
+		case AMDGPU_CHUNK_ID_BO_HANDLES:
+			size = sizeof(struct drm_amdgpu_bo_list_in);
+			if (p->chunks[i].length_dw * sizeof(uint32_t) < size) {
+				ret = -EINVAL;
+				goto free_partial_kdata;
+			}
+
+			ret = amdgpu_cs_bo_handles_chunk(p, p->chunks[i].kdata);
+			if (ret)
+				goto free_partial_kdata;
+
+			break;
+
 		case AMDGPU_CHUNK_ID_DEPENDENCIES:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_IN:
 		case AMDGPU_CHUNK_ID_SYNCOBJ_OUT:
@@ -534,7 +571,12 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	INIT_LIST_HEAD(&p->validated);
 
-	p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
+	/* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */
+	if (!p->bo_list)
+		p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
+	else
+		mutex_lock(&p->bo_list->lock);
+
 	if (p->bo_list) {
 		amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 		if (p->bo_list->first_userptr != p->bo_list->num_entries)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 06aede194bf8..529500c94675 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -69,9 +69,10 @@
  * - 3.24.0 - Add high priority compute support for gfx9
  * - 3.25.0 - Add support for sensor query info (stable pstate sclk/mclk).
  * - 3.26.0 - GFX9: Process AMDGPU_IB_FLAG_TC_WB_NOT_INVALIDATE.
+ * - 3.27.0 - Add new chunk to to AMDGPU_CS to enable BO_LIST creation.
  */
 #define KMS_DRIVER_MAJOR	3
-#define KMS_DRIVER_MINOR	26
+#define KMS_DRIVER_MINOR	27
 #define KMS_DRIVER_PATCHLEVEL	0
 
 int amdgpu_vram_limit = 0;
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index 784b0fe470ee..1ceec56de015 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -516,6 +516,7 @@ struct drm_amdgpu_gem_va {
 #define AMDGPU_CHUNK_ID_DEPENDENCIES	0x03
 #define AMDGPU_CHUNK_ID_SYNCOBJ_IN      0x04
 #define AMDGPU_CHUNK_ID_SYNCOBJ_OUT     0x05
+#define AMDGPU_CHUNK_ID_BO_HANDLES      0x06
 
 struct drm_amdgpu_cs_chunk {
 	__u32		chunk_id;
-- 
cgit v1.2.3


From 7f657d5bf507be0f059405306e860c4b3e40854b Mon Sep 17 00:00:00 2001
From: Dave Watson <davejwatson@fb.com>
Date: Thu, 12 Jul 2018 10:59:20 -0700
Subject: selftests: tls: add selftests for TLS sockets

Add selftests for tls socket.  Tests various iov and message options,
poll blocking and nonblocking behavior, partial message sends / receives,
 and control message data.  Tests should pass regardless of if TLS
is enabled in the kernel or not, and print a warning message if not.

Signed-off-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/Makefile |   2 +-
 tools/testing/selftests/net/tls.c    | 692 +++++++++++++++++++++++++++++++++++
 2 files changed, 693 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/net/tls.c

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 663e11e85727..9cca68e440a0 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -13,7 +13,7 @@ TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd
 TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx
 TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa
-TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict
+TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c
new file mode 100644
index 000000000000..b3ebf2646e52
--- /dev/null
+++ b/tools/testing/selftests/net/tls.c
@@ -0,0 +1,692 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define _GNU_SOURCE
+
+#include <arpa/inet.h>
+#include <errno.h>
+#include <error.h>
+#include <fcntl.h>
+#include <poll.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/tls.h>
+#include <linux/tcp.h>
+#include <linux/socket.h>
+
+#include <sys/types.h>
+#include <sys/sendfile.h>
+#include <sys/socket.h>
+#include <sys/stat.h>
+
+#include "../kselftest_harness.h"
+
+#define TLS_PAYLOAD_MAX_LEN 16384
+#define SOL_TLS 282
+
+FIXTURE(tls)
+{
+	int fd, cfd;
+	bool notls;
+};
+
+FIXTURE_SETUP(tls)
+{
+	struct tls12_crypto_info_aes_gcm_128 tls12;
+	struct sockaddr_in addr;
+	socklen_t len;
+	int sfd, ret;
+
+	self->notls = false;
+	len = sizeof(addr);
+
+	memset(&tls12, 0, sizeof(tls12));
+	tls12.info.version = TLS_1_2_VERSION;
+	tls12.info.cipher_type = TLS_CIPHER_AES_GCM_128;
+
+	addr.sin_family = AF_INET;
+	addr.sin_addr.s_addr = htonl(INADDR_ANY);
+	addr.sin_port = 0;
+
+	self->fd = socket(AF_INET, SOCK_STREAM, 0);
+	sfd = socket(AF_INET, SOCK_STREAM, 0);
+
+	ret = bind(sfd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+	ret = listen(sfd, 10);
+	ASSERT_EQ(ret, 0);
+
+	ret = getsockname(sfd, &addr, &len);
+	ASSERT_EQ(ret, 0);
+
+	ret = connect(self->fd, &addr, sizeof(addr));
+	ASSERT_EQ(ret, 0);
+
+	ret = setsockopt(self->fd, IPPROTO_TCP, TCP_ULP, "tls", sizeof("tls"));
+	if (ret != 0) {
+		self->notls = true;
+		printf("Failure setting TCP_ULP, testing without tls\n");
+	}
+
+	if (!self->notls) {
+		ret = setsockopt(self->fd, SOL_TLS, TLS_TX, &tls12,
+				 sizeof(tls12));
+		ASSERT_EQ(ret, 0);
+	}
+
+	self->cfd = accept(sfd, &addr, &len);
+	ASSERT_GE(self->cfd, 0);
+
+	if (!self->notls) {
+		ret = setsockopt(self->cfd, IPPROTO_TCP, TCP_ULP, "tls",
+				 sizeof("tls"));
+		ASSERT_EQ(ret, 0);
+
+		ret = setsockopt(self->cfd, SOL_TLS, TLS_RX, &tls12,
+				 sizeof(tls12));
+		ASSERT_EQ(ret, 0);
+	}
+
+	close(sfd);
+}
+
+FIXTURE_TEARDOWN(tls)
+{
+	close(self->fd);
+	close(self->cfd);
+}
+
+TEST_F(tls, sendfile)
+{
+	int filefd = open("/proc/self/exe", O_RDONLY);
+	struct stat st;
+
+	EXPECT_GE(filefd, 0);
+	fstat(filefd, &st);
+	EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
+}
+
+TEST_F(tls, send_then_sendfile)
+{
+	int filefd = open("/proc/self/exe", O_RDONLY);
+	char const *test_str = "test_send";
+	int to_send = strlen(test_str) + 1;
+	char recv_buf[10];
+	struct stat st;
+	char *buf;
+
+	EXPECT_GE(filefd, 0);
+	fstat(filefd, &st);
+	buf = (char *)malloc(st.st_size);
+
+	EXPECT_EQ(send(self->fd, test_str, to_send, 0), to_send);
+	EXPECT_EQ(recv(self->cfd, recv_buf, to_send, 0), to_send);
+	EXPECT_EQ(memcmp(test_str, recv_buf, to_send), 0);
+
+	EXPECT_GE(sendfile(self->fd, filefd, 0, st.st_size), 0);
+	EXPECT_EQ(recv(self->cfd, buf, st.st_size, 0), st.st_size);
+}
+
+TEST_F(tls, recv_max)
+{
+	unsigned int send_len = TLS_PAYLOAD_MAX_LEN;
+	char recv_mem[TLS_PAYLOAD_MAX_LEN];
+	char buf[TLS_PAYLOAD_MAX_LEN];
+
+	EXPECT_GE(send(self->fd, buf, send_len, 0), 0);
+	EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, recv_mem, send_len), 0);
+}
+
+TEST_F(tls, recv_small)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10];
+
+	send_len = strlen(test_str) + 1;
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, msg_more)
+{
+	char const *test_str = "test_read";
+	int send_len = 10;
+	char buf[10 * 2];
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, MSG_MORE), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, MSG_DONTWAIT), -1);
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len * 2, MSG_DONTWAIT),
+		  send_len * 2);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, sendmsg_single)
+{
+	struct msghdr msg;
+
+	char const *test_str = "test_sendmsg";
+	size_t send_len = 13;
+	struct iovec vec;
+	char buf[13];
+
+	vec.iov_base = (char *)test_str;
+	vec.iov_len = send_len;
+	memset(&msg, 0, sizeof(struct msghdr));
+	msg.msg_iov = &vec;
+	msg.msg_iovlen = 1;
+	EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_F(tls, sendmsg_large)
+{
+	void *mem = malloc(16384);
+	size_t send_len = 16384;
+	size_t sends = 128;
+	struct msghdr msg;
+	size_t recvs = 0;
+	size_t sent = 0;
+
+	memset(&msg, 0, sizeof(struct msghdr));
+	while (sent++ < sends) {
+		struct iovec vec = { (void *)mem, send_len };
+
+		msg.msg_iov = &vec;
+		msg.msg_iovlen = 1;
+		EXPECT_EQ(sendmsg(self->cfd, &msg, 0), send_len);
+	}
+
+	while (recvs++ < sends)
+		EXPECT_NE(recv(self->fd, mem, send_len, 0), -1);
+
+	free(mem);
+}
+
+TEST_F(tls, sendmsg_multiple)
+{
+	char const *test_str = "test_sendmsg_multiple";
+	struct iovec vec[5];
+	char *test_strs[5];
+	struct msghdr msg;
+	int total_len = 0;
+	int len_cmp = 0;
+	int iov_len = 5;
+	char *buf;
+	int i;
+
+	memset(&msg, 0, sizeof(struct msghdr));
+	for (i = 0; i < iov_len; i++) {
+		test_strs[i] = (char *)malloc(strlen(test_str) + 1);
+		snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str);
+		vec[i].iov_base = (void *)test_strs[i];
+		vec[i].iov_len = strlen(test_strs[i]) + 1;
+		total_len += vec[i].iov_len;
+	}
+	msg.msg_iov = vec;
+	msg.msg_iovlen = iov_len;
+
+	EXPECT_EQ(sendmsg(self->cfd, &msg, 0), total_len);
+	buf = malloc(total_len);
+	EXPECT_NE(recv(self->fd, buf, total_len, 0), -1);
+	for (i = 0; i < iov_len; i++) {
+		EXPECT_EQ(memcmp(test_strs[i], buf + len_cmp,
+				 strlen(test_strs[i])),
+			  0);
+		len_cmp += strlen(buf + len_cmp) + 1;
+	}
+	for (i = 0; i < iov_len; i++)
+		free(test_strs[i]);
+	free(buf);
+}
+
+TEST_F(tls, sendmsg_multiple_stress)
+{
+	char const *test_str = "abcdefghijklmno";
+	struct iovec vec[1024];
+	char *test_strs[1024];
+	int iov_len = 1024;
+	int total_len = 0;
+	char buf[1 << 14];
+	struct msghdr msg;
+	int len_cmp = 0;
+	int i;
+
+	memset(&msg, 0, sizeof(struct msghdr));
+	for (i = 0; i < iov_len; i++) {
+		test_strs[i] = (char *)malloc(strlen(test_str) + 1);
+		snprintf(test_strs[i], strlen(test_str) + 1, "%s", test_str);
+		vec[i].iov_base = (void *)test_strs[i];
+		vec[i].iov_len = strlen(test_strs[i]) + 1;
+		total_len += vec[i].iov_len;
+	}
+	msg.msg_iov = vec;
+	msg.msg_iovlen = iov_len;
+
+	EXPECT_EQ(sendmsg(self->fd, &msg, 0), total_len);
+	EXPECT_NE(recv(self->cfd, buf, total_len, 0), -1);
+
+	for (i = 0; i < iov_len; i++)
+		len_cmp += strlen(buf + len_cmp) + 1;
+
+	for (i = 0; i < iov_len; i++)
+		free(test_strs[i]);
+}
+
+TEST_F(tls, splice_from_pipe)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_GE(write(p[1], mem_send, send_len), 0);
+	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), 0);
+	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, splice_from_pipe2)
+{
+	int send_len = 16000;
+	char mem_send[16000];
+	char mem_recv[16000];
+	int p2[2];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	ASSERT_GE(pipe(p2), 0);
+	EXPECT_GE(write(p[1], mem_send, 8000), 0);
+	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, 8000, 0), 0);
+	EXPECT_GE(write(p2[1], mem_send + 8000, 8000), 0);
+	EXPECT_GE(splice(p2[0], NULL, self->fd, NULL, 8000, 0), 0);
+	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, send_and_splice)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	char const *test_str = "test_read";
+	int send_len2 = 10;
+	char buf[10];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_EQ(send(self->fd, test_str, send_len2, 0), send_len2);
+	EXPECT_NE(recv(self->cfd, buf, send_len2, 0), -1);
+	EXPECT_EQ(memcmp(test_str, buf, send_len2), 0);
+
+	EXPECT_GE(write(p[1], mem_send, send_len), send_len);
+	EXPECT_GE(splice(p[0], NULL, self->fd, NULL, send_len, 0), send_len);
+
+	EXPECT_GE(recv(self->cfd, mem_recv, send_len, 0), 0);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, splice_to_pipe)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char mem_send[TLS_PAYLOAD_MAX_LEN];
+	char mem_recv[TLS_PAYLOAD_MAX_LEN];
+	int p[2];
+
+	ASSERT_GE(pipe(p), 0);
+	EXPECT_GE(send(self->fd, mem_send, send_len, 0), 0);
+	EXPECT_GE(splice(self->cfd, NULL, p[1], NULL, send_len, 0), 0);
+	EXPECT_GE(read(p[0], mem_recv, send_len), 0);
+	EXPECT_EQ(memcmp(mem_send, mem_recv, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_single)
+{
+	char const *test_str = "test_recvmsg_single";
+	int send_len = strlen(test_str) + 1;
+	char buf[20];
+	struct msghdr hdr;
+	struct iovec vec;
+
+	memset(&hdr, 0, sizeof(hdr));
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	vec.iov_base = (char *)buf;
+	vec.iov_len = send_len;
+	hdr.msg_iovlen = 1;
+	hdr.msg_iov = &vec;
+	EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_single_max)
+{
+	int send_len = TLS_PAYLOAD_MAX_LEN;
+	char send_mem[TLS_PAYLOAD_MAX_LEN];
+	char recv_mem[TLS_PAYLOAD_MAX_LEN];
+	struct iovec vec;
+	struct msghdr hdr;
+
+	EXPECT_EQ(send(self->fd, send_mem, send_len, 0), send_len);
+	vec.iov_base = (char *)recv_mem;
+	vec.iov_len = TLS_PAYLOAD_MAX_LEN;
+
+	hdr.msg_iovlen = 1;
+	hdr.msg_iov = &vec;
+	EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+	EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
+}
+
+TEST_F(tls, recvmsg_multiple)
+{
+	unsigned int msg_iovlen = 1024;
+	unsigned int len_compared = 0;
+	struct iovec vec[1024];
+	char *iov_base[1024];
+	unsigned int iov_len = 16;
+	int send_len = 1 << 14;
+	char buf[1 << 14];
+	struct msghdr hdr;
+	int i;
+
+	EXPECT_EQ(send(self->fd, buf, send_len, 0), send_len);
+	for (i = 0; i < msg_iovlen; i++) {
+		iov_base[i] = (char *)malloc(iov_len);
+		vec[i].iov_base = iov_base[i];
+		vec[i].iov_len = iov_len;
+	}
+
+	hdr.msg_iovlen = msg_iovlen;
+	hdr.msg_iov = vec;
+	EXPECT_NE(recvmsg(self->cfd, &hdr, 0), -1);
+	for (i = 0; i < msg_iovlen; i++)
+		len_compared += iov_len;
+
+	for (i = 0; i < msg_iovlen; i++)
+		free(iov_base[i]);
+}
+
+TEST_F(tls, single_send_multiple_recv)
+{
+	unsigned int total_len = TLS_PAYLOAD_MAX_LEN * 2;
+	unsigned int send_len = TLS_PAYLOAD_MAX_LEN;
+	char send_mem[TLS_PAYLOAD_MAX_LEN * 2];
+	char recv_mem[TLS_PAYLOAD_MAX_LEN * 2];
+
+	EXPECT_GE(send(self->fd, send_mem, total_len, 0), 0);
+	memset(recv_mem, 0, total_len);
+
+	EXPECT_NE(recv(self->cfd, recv_mem, send_len, 0), -1);
+	EXPECT_NE(recv(self->cfd, recv_mem + send_len, send_len, 0), -1);
+	EXPECT_EQ(memcmp(send_mem, recv_mem, total_len), 0);
+}
+
+TEST_F(tls, multiple_send_single_recv)
+{
+	unsigned int total_len = 2 * 10;
+	unsigned int send_len = 10;
+	char recv_mem[2 * 10];
+	char send_mem[10];
+
+	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
+	EXPECT_GE(send(self->fd, send_mem, send_len, 0), 0);
+	memset(recv_mem, 0, total_len);
+	EXPECT_EQ(recv(self->cfd, recv_mem, total_len, 0), total_len);
+
+	EXPECT_EQ(memcmp(send_mem, recv_mem, send_len), 0);
+	EXPECT_EQ(memcmp(send_mem, recv_mem + send_len, send_len), 0);
+}
+
+TEST_F(tls, recv_partial)
+{
+	char const *test_str = "test_read_partial";
+	char const *test_str_first = "test_read";
+	char const *test_str_second = "_partial";
+	int send_len = strlen(test_str) + 1;
+	char recv_mem[18];
+
+	memset(recv_mem, 0, sizeof(recv_mem));
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_first), 0), -1);
+	EXPECT_EQ(memcmp(test_str_first, recv_mem, strlen(test_str_first)), 0);
+	memset(recv_mem, 0, sizeof(recv_mem));
+	EXPECT_NE(recv(self->cfd, recv_mem, strlen(test_str_second), 0), -1);
+	EXPECT_EQ(memcmp(test_str_second, recv_mem, strlen(test_str_second)),
+		  0);
+}
+
+TEST_F(tls, recv_nonblock)
+{
+	char buf[4096];
+	bool err;
+
+	EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_DONTWAIT), -1);
+	err = (errno == EAGAIN || errno == EWOULDBLOCK);
+	EXPECT_EQ(err, true);
+}
+
+TEST_F(tls, recv_peek)
+{
+	char const *test_str = "test_read_peek";
+	int send_len = strlen(test_str) + 1;
+	char buf[15];
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+	memset(buf, 0, sizeof(buf));
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, recv_peek_multiple)
+{
+	char const *test_str = "test_read_peek";
+	int send_len = strlen(test_str) + 1;
+	unsigned int num_peeks = 100;
+	char buf[15];
+	int i;
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	for (i = 0; i < num_peeks; i++) {
+		EXPECT_NE(recv(self->cfd, buf, send_len, MSG_PEEK), -1);
+		EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+		memset(buf, 0, sizeof(buf));
+	}
+	EXPECT_NE(recv(self->cfd, buf, send_len, 0), -1);
+	EXPECT_EQ(memcmp(test_str, buf, send_len), 0);
+}
+
+TEST_F(tls, pollin)
+{
+	char const *test_str = "test_poll";
+	struct pollfd fd = { 0, 0, 0 };
+	char buf[10];
+	int send_len = 10;
+
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	fd.fd = self->cfd;
+	fd.events = POLLIN;
+
+	EXPECT_EQ(poll(&fd, 1, 20), 1);
+	EXPECT_EQ(fd.revents & POLLIN, 1);
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), send_len);
+	/* Test timing out */
+	EXPECT_EQ(poll(&fd, 1, 20), 0);
+}
+
+TEST_F(tls, poll_wait)
+{
+	char const *test_str = "test_poll_wait";
+	int send_len = strlen(test_str) + 1;
+	struct pollfd fd = { 0, 0, 0 };
+	char recv_mem[15];
+
+	fd.fd = self->cfd;
+	fd.events = POLLIN;
+	EXPECT_EQ(send(self->fd, test_str, send_len, 0), send_len);
+	/* Set timeout to inf. secs */
+	EXPECT_EQ(poll(&fd, 1, -1), 1);
+	EXPECT_EQ(fd.revents & POLLIN, 1);
+	EXPECT_EQ(recv(self->cfd, recv_mem, send_len, 0), send_len);
+}
+
+TEST_F(tls, blocking)
+{
+	size_t data = 100000;
+	int res = fork();
+
+	EXPECT_NE(res, -1);
+
+	if (res) {
+		/* parent */
+		size_t left = data;
+		char buf[16384];
+		int status;
+		int pid2;
+
+		while (left) {
+			int res = send(self->fd, buf,
+				       left > 16384 ? 16384 : left, 0);
+
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+
+		pid2 = wait(&status);
+		EXPECT_EQ(status, 0);
+		EXPECT_EQ(res, pid2);
+	} else {
+		/* child */
+		size_t left = data;
+		char buf[16384];
+
+		while (left) {
+			int res = recv(self->cfd, buf,
+				       left > 16384 ? 16384 : left, 0);
+
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+	}
+}
+
+TEST_F(tls, nonblocking)
+{
+	size_t data = 100000;
+	int sendbuf = 100;
+	int flags;
+	int res;
+
+	flags = fcntl(self->fd, F_GETFL, 0);
+	fcntl(self->fd, F_SETFL, flags | O_NONBLOCK);
+	fcntl(self->cfd, F_SETFL, flags | O_NONBLOCK);
+
+	/* Ensure nonblocking behavior by imposing a small send
+	 * buffer.
+	 */
+	EXPECT_EQ(setsockopt(self->fd, SOL_SOCKET, SO_SNDBUF,
+			     &sendbuf, sizeof(sendbuf)), 0);
+
+	res = fork();
+	EXPECT_NE(res, -1);
+
+	if (res) {
+		/* parent */
+		bool eagain = false;
+		size_t left = data;
+		char buf[16384];
+		int status;
+		int pid2;
+
+		while (left) {
+			int res = send(self->fd, buf,
+				       left > 16384 ? 16384 : left, 0);
+
+			if (res == -1 && errno == EAGAIN) {
+				eagain = true;
+				usleep(10000);
+				continue;
+			}
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+
+		EXPECT_TRUE(eagain);
+		pid2 = wait(&status);
+
+		EXPECT_EQ(status, 0);
+		EXPECT_EQ(res, pid2);
+	} else {
+		/* child */
+		bool eagain = false;
+		size_t left = data;
+		char buf[16384];
+
+		while (left) {
+			int res = recv(self->cfd, buf,
+				       left > 16384 ? 16384 : left, 0);
+
+			if (res == -1 && errno == EAGAIN) {
+				eagain = true;
+				usleep(10000);
+				continue;
+			}
+			EXPECT_GE(res, 0);
+			left -= res;
+		}
+		EXPECT_TRUE(eagain);
+	}
+}
+
+TEST_F(tls, control_msg)
+{
+	if (self->notls)
+		return;
+
+	char cbuf[CMSG_SPACE(sizeof(char))];
+	char const *test_str = "test_read";
+	int cmsg_len = sizeof(char);
+	char record_type = 100;
+	struct cmsghdr *cmsg;
+	struct msghdr msg;
+	int send_len = 10;
+	struct iovec vec;
+	char buf[10];
+
+	vec.iov_base = (char *)test_str;
+	vec.iov_len = 10;
+	memset(&msg, 0, sizeof(struct msghdr));
+	msg.msg_iov = &vec;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+	cmsg = CMSG_FIRSTHDR(&msg);
+	cmsg->cmsg_level = SOL_TLS;
+	/* test sending non-record types. */
+	cmsg->cmsg_type = TLS_SET_RECORD_TYPE;
+	cmsg->cmsg_len = CMSG_LEN(cmsg_len);
+	*CMSG_DATA(cmsg) = record_type;
+	msg.msg_controllen = cmsg->cmsg_len;
+
+	EXPECT_EQ(sendmsg(self->fd, &msg, 0), send_len);
+	/* Should fail because we didn't provide a control message */
+	EXPECT_EQ(recv(self->cfd, buf, send_len, 0), -1);
+
+	vec.iov_base = buf;
+	EXPECT_EQ(recvmsg(self->cfd, &msg, 0), send_len);
+	cmsg = CMSG_FIRSTHDR(&msg);
+	EXPECT_NE(cmsg, NULL);
+	EXPECT_EQ(cmsg->cmsg_level, SOL_TLS);
+	EXPECT_EQ(cmsg->cmsg_type, TLS_GET_RECORD_TYPE);
+	record_type = *((unsigned char *)CMSG_DATA(cmsg));
+	EXPECT_EQ(record_type, 100);
+	EXPECT_EQ(memcmp(buf, test_str, send_len), 0);
+}
+
+TEST_HARNESS_MAIN
-- 
cgit v1.2.3


From 762995807059dec20c926617415e0cdd52fd44e9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 12 Jul 2018 21:31:54 +0200
Subject: net: phy: add helper phy_config_aneg

This functionality will also be needed in subsequent patches of this
series, therefore factor it out to a helper.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 537297d2b4b4..c4aa360dedff 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -467,6 +467,14 @@ int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd)
 }
 EXPORT_SYMBOL(phy_mii_ioctl);
 
+static int phy_config_aneg(struct phy_device *phydev)
+{
+	if (phydev->drv->config_aneg)
+		return phydev->drv->config_aneg(phydev);
+	else
+		return genphy_config_aneg(phydev);
+}
+
 /**
  * phy_start_aneg_priv - start auto-negotiation for this PHY device
  * @phydev: the phy_device struct
@@ -493,10 +501,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	/* Invalidate LP advertising flags */
 	phydev->lp_advertising = 0;
 
-	if (phydev->drv->config_aneg)
-		err = phydev->drv->config_aneg(phydev);
-	else
-		err = genphy_config_aneg(phydev);
+	err = phy_config_aneg(phydev);
 	if (err < 0)
 		goto out_unlock;
 
-- 
cgit v1.2.3


From 2b9672ddb6f347467d7b33b86c5dfc4d5c0501a8 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 12 Jul 2018 21:32:53 +0200
Subject: net: phy: add phy_speed_down and phy_speed_up

Some network drivers include functionality to speed down the PHY when
suspending and just waiting for a WoL packet because this saves energy.
This functionality is quite generic, therefore let's factor it out to
phylib.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/phy.h   |  2 ++
 2 files changed, 80 insertions(+)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index c4aa360dedff..d2baedc4ea91 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -551,6 +551,84 @@ int phy_start_aneg(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_start_aneg);
 
+static int phy_poll_aneg_done(struct phy_device *phydev)
+{
+	unsigned int retries = 100;
+	int ret;
+
+	do {
+		msleep(100);
+		ret = phy_aneg_done(phydev);
+	} while (!ret && --retries);
+
+	if (!ret)
+		return -ETIMEDOUT;
+
+	return ret < 0 ? ret : 0;
+}
+
+/**
+ * phy_speed_down - set speed to lowest speed supported by both link partners
+ * @phydev: the phy_device struct
+ * @sync: perform action synchronously
+ *
+ * Description: Typically used to save energy when waiting for a WoL packet
+ *
+ * WARNING: Setting sync to false may cause the system being unable to suspend
+ * in case the PHY generates an interrupt when finishing the autonegotiation.
+ * This interrupt may wake up the system immediately after suspend.
+ * Therefore use sync = false only if you're sure it's safe with the respective
+ * network chip.
+ */
+int phy_speed_down(struct phy_device *phydev, bool sync)
+{
+	u32 adv = phydev->lp_advertising & phydev->supported;
+	u32 adv_old = phydev->advertising;
+	int ret;
+
+	if (phydev->autoneg != AUTONEG_ENABLE)
+		return 0;
+
+	if (adv & PHY_10BT_FEATURES)
+		phydev->advertising &= ~(PHY_100BT_FEATURES |
+					 PHY_1000BT_FEATURES);
+	else if (adv & PHY_100BT_FEATURES)
+		phydev->advertising &= ~PHY_1000BT_FEATURES;
+
+	if (phydev->advertising == adv_old)
+		return 0;
+
+	ret = phy_config_aneg(phydev);
+	if (ret)
+		return ret;
+
+	return sync ? phy_poll_aneg_done(phydev) : 0;
+}
+EXPORT_SYMBOL_GPL(phy_speed_down);
+
+/**
+ * phy_speed_up - (re)set advertised speeds to all supported speeds
+ * @phydev: the phy_device struct
+ *
+ * Description: Used to revert the effect of phy_speed_down
+ */
+int phy_speed_up(struct phy_device *phydev)
+{
+	u32 mask = PHY_10BT_FEATURES | PHY_100BT_FEATURES | PHY_1000BT_FEATURES;
+	u32 adv_old = phydev->advertising;
+
+	if (phydev->autoneg != AUTONEG_ENABLE)
+		return 0;
+
+	phydev->advertising = (adv_old & ~mask) | (phydev->supported & mask);
+
+	if (phydev->advertising == adv_old)
+		return 0;
+
+	return phy_config_aneg(phydev);
+}
+EXPORT_SYMBOL_GPL(phy_speed_up);
+
 /**
  * phy_start_machine - start PHY state machine tracking
  * @phydev: the phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 6cd09098427c..075c2f770d3e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -942,6 +942,8 @@ void phy_start(struct phy_device *phydev);
 void phy_stop(struct phy_device *phydev);
 int phy_start_aneg(struct phy_device *phydev);
 int phy_aneg_done(struct phy_device *phydev);
+int phy_speed_down(struct phy_device *phydev, bool sync);
+int phy_speed_up(struct phy_device *phydev);
 
 int phy_stop_interrupts(struct phy_device *phydev);
 int phy_restart_aneg(struct phy_device *phydev);
-- 
cgit v1.2.3


From ae85467cccba9b255bd91b583effb17a5b57a12f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 12 Jul 2018 14:43:20 -0500
Subject: net: usb: hso: use swap macro in hso_kick_transmit

Make use of the swap macro and remove unnecessary variable *temp*.
This makes the code easier to read and maintain. Also, slightly
refactor some code due to the removal of *temp*.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/hso.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index de305ead32e6..184c24baca15 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -1732,7 +1732,6 @@ static int hso_serial_ioctl(struct tty_struct *tty,
 /* starts a transmit */
 static void hso_kick_transmit(struct hso_serial *serial)
 {
-	u8 *temp;
 	unsigned long flags;
 	int res;
 
@@ -1748,14 +1747,12 @@ static void hso_kick_transmit(struct hso_serial *serial)
 		goto out;
 
 	/* Switch pointers around to avoid memcpy */
-	temp = serial->tx_buffer;
-	serial->tx_buffer = serial->tx_data;
-	serial->tx_data = temp;
+	swap(serial->tx_buffer, serial->tx_data);
 	serial->tx_data_count = serial->tx_buffer_count;
 	serial->tx_buffer_count = 0;
 
-	/* If temp is set, it means we switched buffers */
-	if (temp && serial->write_data) {
+	/* If serial->tx_data is set, it means we switched buffers */
+	if (serial->tx_data && serial->write_data) {
 		res = serial->write_data(serial);
 		if (res >= 0)
 			serial->tx_urb_used = 1;
-- 
cgit v1.2.3


From 04ecac8c12cdab87c44a98f0679079dd13d95a78 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 12 Jul 2018 21:45:08 +0200
Subject: net: phy: realtek: add missing entry for RTL8211C to mdio_device_id
 table

Add missing entry for RTL8211C to mdio_device_id table.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Fixes: cf87915cb9f8 ("net: phy: realtek: add support for RTL8211C")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index f8f127831a92..0610148cc1ff 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -279,6 +279,7 @@ static struct mdio_device_id __maybe_unused realtek_tbl[] = {
 	{ 0x001cc816, 0x001fffff },
 	{ 0x001cc910, 0x001fffff },
 	{ 0x001cc912, 0x001fffff },
+	{ 0x001cc913, 0x001fffff },
 	{ 0x001cc914, 0x001fffff },
 	{ 0x001cc915, 0x001fffff },
 	{ 0x001cc916, 0x001fffff },
-- 
cgit v1.2.3


From 6e85d7a8bc6543fcf81b1b2af0901e5f3332d113 Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Thu, 12 Jul 2018 22:36:29 +0200
Subject: liquidio: Use %pad printk format for dma_addr_t values

Use the existing %pad printk format to print dma_addr_t values.
This avoids the following warnings when compiling on the parisc platform:

warning: format '%llx' expects argument of type 'long long unsigned int', but argument 2 has type 'dma_addr_t {aka unsigned int}' [-Wformat=]

Signed-off-by: Helge Deller <deller@gmx.de>
Acked-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/request_manager.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index 1f2e75da28f8..d5d9e47daa4b 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -110,8 +110,8 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	memset(iq->request_list, 0, sizeof(*iq->request_list) * num_descs);
 
-	dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %llx count: %d\n",
-		iq_no, iq->base_addr, iq->base_addr_dma, iq->max_count);
+	dev_dbg(&oct->pci_dev->dev, "IQ[%d]: base: %p basedma: %pad count: %d\n",
+		iq_no, iq->base_addr, &iq->base_addr_dma, iq->max_count);
 
 	iq->txpciq.u64 = txpciq.u64;
 	iq->fill_threshold = (u32)conf->db_min;
-- 
cgit v1.2.3


From 48559af3454c262543fe28d4730a92234f887881 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 13 Jul 2018 11:02:04 +0800
Subject: bnxt_en: remove redundant debug register dma mem allocation

hwrm_dbg_resp_addr and hwrm_dbg_resp_dma_addr are never used
and can be removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 13 -------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  3 ---
 2 files changed, 16 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d2dadade1d0e..2cf726e31461 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3012,13 +3012,6 @@ static void bnxt_free_hwrm_resources(struct bnxt *bp)
 			  bp->hwrm_cmd_resp_dma_addr);
 
 	bp->hwrm_cmd_resp_addr = NULL;
-	if (bp->hwrm_dbg_resp_addr) {
-		dma_free_coherent(&pdev->dev, HWRM_DBG_REG_BUF_SIZE,
-				  bp->hwrm_dbg_resp_addr,
-				  bp->hwrm_dbg_resp_dma_addr);
-
-		bp->hwrm_dbg_resp_addr = NULL;
-	}
 }
 
 static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
@@ -3030,12 +3023,6 @@ static int bnxt_alloc_hwrm_resources(struct bnxt *bp)
 						   GFP_KERNEL);
 	if (!bp->hwrm_cmd_resp_addr)
 		return -ENOMEM;
-	bp->hwrm_dbg_resp_addr = dma_alloc_coherent(&pdev->dev,
-						    HWRM_DBG_REG_BUF_SIZE,
-						    &bp->hwrm_dbg_resp_dma_addr,
-						    GFP_KERNEL);
-	if (!bp->hwrm_dbg_resp_addr)
-		netdev_warn(bp->dev, "fail to alloc debug register dma mem\n");
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 9b14eb610b9f..709ba86d3a02 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1287,9 +1287,6 @@ struct bnxt {
 	dma_addr_t		hwrm_short_cmd_req_dma_addr;
 	void			*hwrm_cmd_resp_addr;
 	dma_addr_t		hwrm_cmd_resp_dma_addr;
-	void			*hwrm_dbg_resp_addr;
-	dma_addr_t		hwrm_dbg_resp_dma_addr;
-#define HWRM_DBG_REG_BUF_SIZE	128
 
 	struct rx_port_stats	*hw_rx_port_stats;
 	struct tx_port_stats	*hw_tx_port_stats;
-- 
cgit v1.2.3


From d9f37d01e294e5338aa3e9d3b2eda61b59b619df Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 13 Jul 2018 14:41:36 +0800
Subject: net: convert gro_count to bitmask

gro_hash size is 192 bytes, and uses 3 cache lines, if there is few
flows, gro_hash may be not fully used, so it is unnecessary to iterate
all gro_hash in napi_gro_flush(), to occupy unnecessary cacheline.

convert gro_count to a bitmask, and rename it as gro_bitmask, each bit
represents a element of gro_hash, only flush a gro_hash element if the
related bit is set, to speed up napi_gro_flush().

and update gro_bitmask only if it will be changed, to reduce cache
update

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Cc: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  9 +++++++--
 net/core/dev.c            | 36 ++++++++++++++++++++++++------------
 2 files changed, 31 insertions(+), 14 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3514d67112b3..c1295c7a452e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -308,9 +308,14 @@ struct gro_list {
 };
 
 /*
- * Structure for NAPI scheduling similar to tasklet but with weighting
+ * size of gro hash buckets, must less than bit number of
+ * napi_struct::gro_bitmask
  */
 #define GRO_HASH_BUCKETS	8
+
+/*
+ * Structure for NAPI scheduling similar to tasklet but with weighting
+ */
 struct napi_struct {
 	/* The poll_list must only be managed by the entity which
 	 * changes the state of the NAPI_STATE_SCHED bit.  This means
@@ -322,7 +327,7 @@ struct napi_struct {
 
 	unsigned long		state;
 	int			weight;
-	unsigned int		gro_count;
+	unsigned long		gro_bitmask;
 	int			(*poll)(struct napi_struct *, int);
 #ifdef CONFIG_NETPOLL
 	int			poll_owner;
diff --git a/net/core/dev.c b/net/core/dev.c
index 0df1771a12f9..c883b17ee0fe 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5282,9 +5282,11 @@ static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
 		list_del(&skb->list);
 		skb->next = NULL;
 		napi_gro_complete(skb);
-		napi->gro_count--;
 		napi->gro_hash[index].count--;
 	}
+
+	if (!napi->gro_hash[index].count)
+		__clear_bit(index, &napi->gro_bitmask);
 }
 
 /* napi->gro_hash[].list contains packets ordered by age.
@@ -5295,8 +5297,10 @@ void napi_gro_flush(struct napi_struct *napi, bool flush_old)
 {
 	u32 i;
 
-	for (i = 0; i < GRO_HASH_BUCKETS; i++)
-		__napi_gro_flush_chain(napi, i, flush_old);
+	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
+		if (test_bit(i, &napi->gro_bitmask))
+			__napi_gro_flush_chain(napi, i, flush_old);
+	}
 }
 EXPORT_SYMBOL(napi_gro_flush);
 
@@ -5388,8 +5392,8 @@ static void gro_flush_oldest(struct list_head *head)
 	if (WARN_ON_ONCE(!oldest))
 		return;
 
-	/* Do not adjust napi->gro_count, caller is adding a new SKB to
-	 * the chain.
+	/* Do not adjust napi->gro_hash[].count, caller is adding a new
+	 * SKB to the chain.
 	 */
 	list_del(&oldest->list);
 	napi_gro_complete(oldest);
@@ -5464,7 +5468,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		list_del(&pp->list);
 		pp->next = NULL;
 		napi_gro_complete(pp);
-		napi->gro_count--;
 		napi->gro_hash[hash].count--;
 	}
 
@@ -5477,7 +5480,6 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	if (unlikely(napi->gro_hash[hash].count >= MAX_GRO_SKBS)) {
 		gro_flush_oldest(gro_head);
 	} else {
-		napi->gro_count++;
 		napi->gro_hash[hash].count++;
 	}
 	NAPI_GRO_CB(skb)->count = 1;
@@ -5492,6 +5494,13 @@ pull:
 	if (grow > 0)
 		gro_pull_from_frag0(skb, grow);
 ok:
+	if (napi->gro_hash[hash].count) {
+		if (!test_bit(hash, &napi->gro_bitmask))
+			__set_bit(hash, &napi->gro_bitmask);
+	} else if (test_bit(hash, &napi->gro_bitmask)) {
+		__clear_bit(hash, &napi->gro_bitmask);
+	}
+
 	return ret;
 
 normal:
@@ -5890,7 +5899,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 				 NAPIF_STATE_IN_BUSY_POLL)))
 		return false;
 
-	if (n->gro_count) {
+	if (n->gro_bitmask) {
 		unsigned long timeout = 0;
 
 		if (work_done)
@@ -6099,7 +6108,7 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	/* Note : we use a relaxed variant of napi_schedule_prep() not setting
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
-	if (napi->gro_count && !napi_disable_pending(napi) &&
+	if (napi->gro_bitmask && !napi_disable_pending(napi) &&
 	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
 		__napi_schedule_irqoff(napi);
 
@@ -6114,7 +6123,7 @@ void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 	INIT_LIST_HEAD(&napi->poll_list);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
-	napi->gro_count = 0;
+	napi->gro_bitmask = 0;
 	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
 		INIT_LIST_HEAD(&napi->gro_hash[i].list);
 		napi->gro_hash[i].count = 0;
@@ -6174,7 +6183,7 @@ void netif_napi_del(struct napi_struct *napi)
 	napi_free_frags(napi);
 
 	flush_gro_hash(napi);
-	napi->gro_count = 0;
+	napi->gro_bitmask = 0;
 }
 EXPORT_SYMBOL(netif_napi_del);
 
@@ -6216,7 +6225,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
-	if (n->gro_count) {
+	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
 		 */
@@ -9272,6 +9281,9 @@ static struct hlist_head * __net_init netdev_create_hash(void)
 /* Initialize per network namespace state */
 static int __net_init netdev_init(struct net *net)
 {
+	BUILD_BUG_ON(GRO_HASH_BUCKETS >
+			FIELD_SIZEOF(struct napi_struct, gro_bitmask));
+
 	if (net != &init_net)
 		INIT_LIST_HEAD(&net->dev_base_head);
 
-- 
cgit v1.2.3


From bc1b50309ce19bb2ccb1340fa83ab56ca6da8f96 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Fri, 13 Jul 2018 17:56:55 +0530
Subject: cxgb4: do not return DUPLEX_UNKNOWN when link is down

We were returning DUPLEX_UNKNOWN in get_link_ksettings() when
the link was down.  Unfortunately, this causes a problem when
"ethtool -s autoneg on" is issued for a link which is down because
the ethtool code first reads the settings and then reapplies them
with only the changes provided on the command line. Which results
in us diving into set_link_ksettings() with DUPLEX_UNKNOWN which is
not DUPLEX_FULL, so set_link_ksettings() throws an -EINVAL error.
do not return DUPLEX_UNKNOWN to fix the issue.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
index a14a290a56ee..d07230c892a5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_ethtool.c
@@ -628,13 +628,10 @@ static int get_link_ksettings(struct net_device *dev,
 	fw_caps_to_lmm(pi->port_type, pi->link_cfg.lpacaps,
 		       link_ksettings->link_modes.lp_advertising);
 
-	if (netif_carrier_ok(dev)) {
-		base->speed = pi->link_cfg.speed;
-		base->duplex = DUPLEX_FULL;
-	} else {
-		base->speed = SPEED_UNKNOWN;
-		base->duplex = DUPLEX_UNKNOWN;
-	}
+	base->speed = (netif_carrier_ok(dev)
+		       ? pi->link_cfg.speed
+		       : SPEED_UNKNOWN);
+	base->duplex = DUPLEX_FULL;
 
 	if (pi->link_cfg.fc & PAUSE_RX) {
 		if (pi->link_cfg.fc & PAUSE_TX) {
-- 
cgit v1.2.3


From 495083807f2007af7a29ea72768866f747021a98 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Fri, 13 Jul 2018 16:57:57 +0200
Subject: net: mscc: simplify retrieving the tag type from the frame header

The tag type in the frame extraction header is only a bit wide. There's
no need to use GENMASK when retrieving the information. This patch
simplify the code by dropping GENMASK and using BIT instead.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot_board.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c
index 18df7d934e81..26bb3b18f3be 100644
--- a/drivers/net/ethernet/mscc/ocelot_board.c
+++ b/drivers/net/ethernet/mscc/ocelot_board.c
@@ -29,7 +29,7 @@ static int ocelot_parse_ifh(u32 *ifh, struct frame_info *info)
 	info->port = (ifh[2] & GENMASK(14, 11)) >> 11;
 
 	info->cpuq = (ifh[3] & GENMASK(27, 20)) >> 20;
-	info->tag_type = (ifh[3] & GENMASK(16, 16)) >> 16;
+	info->tag_type = (ifh[3] & BIT(16)) >> 16;
 	info->vid = ifh[3] & GENMASK(11, 0);
 
 	return 0;
-- 
cgit v1.2.3


From 7e2bc7fb65d544bb8598a0ab64e40ee9c60ded6e Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Fri, 13 Jul 2018 17:04:28 +0200
Subject: net: cavium: Drop dependency of NET_VENDOR_CAVIUM on PCI

Octeon Ethernet drivers work perfectly without PCI.

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 043e3c11c42b..4c3a5c354497 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -4,7 +4,6 @@
 
 config NET_VENDOR_CAVIUM
 	bool "Cavium ethernet drivers"
-	depends on PCI
 	default y
 	---help---
 	  Select this option if you want enable Cavium network support.
-- 
cgit v1.2.3


From ac13d6d8eaded15c67265eafc32f439ea3a0ac4a Mon Sep 17 00:00:00 2001
From: Rick Farrington <ricardo.farrington@cavium.com>
Date: Fri, 13 Jul 2018 12:50:21 -0700
Subject: liquidio: fix hang when re-binding VF host drv after running DPDK VF
 driver

When configuring SLI_PKTn_OUTPUT_CONTROL, VF driver was assuming that IPTR
mode was disabled by reset, which was not true.  Since DPDK driver had
set IPTR mode previously, the VF driver (which uses buf-ptr-only mode) was
not properly handling DROQ packets (i.e. it saw zero-length packets).

This represented an invalid hardware configuration which the driver could
not handle.

Signed-off-by: Rick Farrington <ricardo.farrington@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c | 3 +++
 drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 929d485a3a2f..e088dedc1747 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -493,6 +493,9 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 	for (q_no = srn; q_no < ern; q_no++) {
 		reg_val = octeon_read_csr(oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no));
 
+		/* clear IPTR */
+		reg_val &= ~CN23XX_PKT_OUTPUT_CTL_IPTR;
+
 		/* set DPTR */
 		reg_val |= CN23XX_PKT_OUTPUT_CTL_DPTR;
 
diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
index 9338a0008378..1f8b7f651254 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
@@ -165,6 +165,9 @@ static void cn23xx_vf_setup_global_output_regs(struct octeon_device *oct)
 		reg_val =
 		    octeon_read_csr(oct, CN23XX_VF_SLI_OQ_PKT_CONTROL(q_no));
 
+		/* clear IPTR */
+		reg_val &= ~CN23XX_PKT_OUTPUT_CTL_IPTR;
+
 		/* set DPTR */
 		reg_val |= CN23XX_PKT_OUTPUT_CTL_DPTR;
 
-- 
cgit v1.2.3


From 1222d15a01c7a3a76a5988df341998a647ff462c Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Sun, 15 Jul 2018 10:45:42 +0300
Subject: mlxsw: spectrum: Expose counters for various packet sizes

Expose counters ASIC has in the group of RFC 2819 counters that count
number of packets within specific size range.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h      | 63 ++++++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 62 ++++++++++++++++++++++++-
 2 files changed, 124 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 6f98a43e75f5..f76c17308a51 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3365,6 +3365,7 @@ MLXSW_ITEM32(reg, ppcnt, pnat, 0x00, 14, 2);
 
 enum mlxsw_reg_ppcnt_grp {
 	MLXSW_REG_PPCNT_IEEE_8023_CNT = 0x0,
+	MLXSW_REG_PPCNT_RFC_2819_CNT = 0x2,
 	MLXSW_REG_PPCNT_EXT_CNT = 0x5,
 	MLXSW_REG_PPCNT_PRIO_CNT = 0x10,
 	MLXSW_REG_PPCNT_TC_CNT = 0x11,
@@ -3523,6 +3524,68 @@ MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_received,
 MLXSW_ITEM64(reg, ppcnt, a_pause_mac_ctrl_frames_transmitted,
 	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
 
+/* Ethernet RFC 2819 Counter Group */
+
+/* reg_ppcnt_ether_stats_pkts64octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts64octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x58, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts65to127octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts65to127octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x60, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts128to255octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts128to255octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x68, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts256to511octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts256to511octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x70, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts512to1023octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts512to1023octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x78, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts1024to1518octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts1024to1518octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x80, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts1519to2047octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts1519to2047octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x88, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts2048to4095octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts2048to4095octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x90, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts4096to8191octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts4096to8191octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0x98, 0, 64);
+
+/* reg_ppcnt_ether_stats_pkts8192to10239octets
+ * Access: RO
+ */
+MLXSW_ITEM64(reg, ppcnt, ether_stats_pkts8192to10239octets,
+	     MLXSW_REG_PPCNT_COUNTERS_OFFSET + 0xA0, 0, 64);
+
 /* Ethernet Extended Counter Group Counters */
 
 /* reg_ppcnt_ecn_marked
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 6ec0f91a93cc..62c5f1c5bf62 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1888,6 +1888,52 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_stats[] = {
 
 #define MLXSW_SP_PORT_HW_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_stats)
 
+static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_rfc_2819_stats[] = {
+	{
+		.str = "ether_pkts64octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts64octets_get,
+	},
+	{
+		.str = "ether_pkts65to127octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts65to127octets_get,
+	},
+	{
+		.str = "ether_pkts128to255octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts128to255octets_get,
+	},
+	{
+		.str = "ether_pkts256to511octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts256to511octets_get,
+	},
+	{
+		.str = "ether_pkts512to1023octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts512to1023octets_get,
+	},
+	{
+		.str = "ether_pkts1024to1518octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts1024to1518octets_get,
+	},
+	{
+		.str = "ether_pkts1519to2047octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts1519to2047octets_get,
+	},
+	{
+		.str = "ether_pkts2048to4095octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts2048to4095octets_get,
+	},
+	{
+		.str = "ether_pkts4096to8191octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts4096to8191octets_get,
+	},
+	{
+		.str = "ether_pkts8192to10239octets",
+		.getter = mlxsw_reg_ppcnt_ether_stats_pkts8192to10239octets_get,
+	},
+};
+
+#define MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN \
+	ARRAY_SIZE(mlxsw_sp_port_hw_rfc_2819_stats)
+
 static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_prio_stats[] = {
 	{
 		.str = "rx_octets_prio",
@@ -1979,6 +2025,11 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev,
 			       ETH_GSTRING_LEN);
 			p += ETH_GSTRING_LEN;
 		}
+		for (i = 0; i < MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN; i++) {
+			memcpy(p, mlxsw_sp_port_hw_rfc_2819_stats[i].str,
+			       ETH_GSTRING_LEN);
+			p += ETH_GSTRING_LEN;
+		}
 
 		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
 			mlxsw_sp_port_get_prio_strings(&p, i);
@@ -2018,10 +2069,14 @@ mlxsw_sp_get_hw_stats_by_group(struct mlxsw_sp_port_hw_stats **p_hw_stats,
 			       int *p_len, enum mlxsw_reg_ppcnt_grp grp)
 {
 	switch (grp) {
-	case  MLXSW_REG_PPCNT_IEEE_8023_CNT:
+	case MLXSW_REG_PPCNT_IEEE_8023_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_stats;
 		*p_len = MLXSW_SP_PORT_HW_STATS_LEN;
 		break;
+	case MLXSW_REG_PPCNT_RFC_2819_CNT:
+		*p_hw_stats = mlxsw_sp_port_hw_rfc_2819_stats;
+		*p_len = MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
+		break;
 	case MLXSW_REG_PPCNT_PRIO_CNT:
 		*p_hw_stats = mlxsw_sp_port_hw_prio_stats;
 		*p_len = MLXSW_SP_PORT_HW_PRIO_STATS_LEN;
@@ -2071,6 +2126,11 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 				  data, data_index);
 	data_index = MLXSW_SP_PORT_HW_STATS_LEN;
 
+	/* RFC 2819 Counters */
+	__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_RFC_2819_CNT, 0,
+				  data, data_index);
+	data_index += MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN;
+
 	/* Per-Priority Counters */
 	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
 		__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_PRIO_CNT, i,
-- 
cgit v1.2.3


From a6da48caf92b4b6119cae146259528bec0e48545 Mon Sep 17 00:00:00 2001
From: Junwei Zhang <Jerry.Zhang@amd.com>
Date: Mon, 16 Jul 2018 10:53:43 +0800
Subject: drm/scheduler: add NULL pointer check for run queue (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To check rq pointer before adding entity into it.
That avoids NULL pointer access in some case.

v2: move the check to caller

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 16bf446aa6b3..dac71e3b4514 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -547,6 +547,11 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 	if (first) {
 		/* Add the entity to the run queue */
 		spin_lock(&entity->rq_lock);
+		if (!entity->rq) {
+			DRM_ERROR("Trying to push to a killed entity\n");
+			spin_unlock(&entity->rq_lock);
+			return;
+		}
 		drm_sched_rq_add_entity(entity->rq, entity);
 		spin_unlock(&entity->rq_lock);
 		drm_sched_wakeup(sched);
-- 
cgit v1.2.3


From 8d2bbe54d18906e456c1ba0e1b0aa9fd175cae97 Mon Sep 17 00:00:00 2001
From: Vitaly Prosyak <vitaly.prosyak@amd.com>
Date: Fri, 15 Jun 2018 08:34:10 -0500
Subject: drm/amd/display: Add headers for hardcoded 1d luts.

Hard-coded luts are needed since complex algorithms are used for
color and tone mapping. Add the headers for future use.

Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/modules/color/luts_1d.h    | 51 ++++++++++++++++++++++
 1 file changed, 51 insertions(+)
 create mode 100644 drivers/gpu/drm/amd/display/modules/color/luts_1d.h

diff --git a/drivers/gpu/drm/amd/display/modules/color/luts_1d.h b/drivers/gpu/drm/amd/display/modules/color/luts_1d.h
new file mode 100644
index 000000000000..66b1fad572ac
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/modules/color/luts_1d.h
@@ -0,0 +1,51 @@
+/*
+ * Copyright 2016 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+#ifndef LUTS_1D_H
+#define LUTS_1D_H
+
+#include "hw_shared.h"
+
+struct point_config {
+	uint32_t custom_float_x;
+	uint32_t custom_float_y;
+	uint32_t custom_float_slope;
+};
+
+struct lut_point {
+	uint32_t red;
+	uint32_t green;
+	uint32_t blue;
+	uint32_t delta_red;
+	uint32_t delta_green;
+	uint32_t delta_blue;
+};
+
+struct pwl_1dlut_parameter {
+	struct gamma_curve	arr_curve_points[34];
+	struct point_config	arr_points[2];
+	struct lut_point rgb_resulted[256];
+	uint32_t hw_points_num;
+};
+#endif // LUTS_1D_H
-- 
cgit v1.2.3


From 6d92b5c2d5bea1b1d0859bd8f3080344e5e3960e Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Wed, 27 Jun 2018 18:23:37 -0400
Subject: drm/amd/display: Refactor SDR cursor boosting in HDR mode

[Why]
Cursor boosting is done via CNVC_CUR register which is DPP, not HUBP
Previous commit was implementing it in HUBP functions,
and also breaking diags tests.

[How]
1. Undo original commit as well as Eric's diags test fix, almost completely
2. Move programming to DPP and call via new dc_stream function
3. Also removing cur_rom_en from dpp_cursor_attributes and programming
as part of normal cursor attributes as it depends on cursor color format

Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c    |  1 +
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h       |  5 ++++
 drivers/gpu/drm/amd/display/dc/dc_stream.h         |  2 ++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c   | 13 ++++++++++
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h   | 14 ++++++++--
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c  | 15 -----------
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h  | 12 +++------
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 30 +++++++++++++++++++++-
 drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h        |  3 +++
 drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h  |  1 +
 10 files changed, 70 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 0223f4867e8d..4717330a42f4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -214,6 +214,7 @@ bool dc_stream_set_cursor_attributes(
 		}
 
 		core_dc->hwss.set_cursor_attribute(pipe_ctx);
+		core_dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
 	}
 
 	if (pipe_to_program)
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index da787e279319..9cfd7ea845e3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -500,6 +500,11 @@ struct dc_cursor_attributes {
 	union dc_cursor_attribute_flags attribute_flags;
 };
 
+struct dpp_cursor_attributes {
+	int bias;
+	int scale;
+};
+
 /* OPP */
 
 enum dc_color_space {
diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
index 64eeb440e3d3..cbfe418006cb 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
@@ -100,6 +100,7 @@ struct dc_stream_state {
 
 	struct dc_cursor_attributes cursor_attributes;
 	struct dc_cursor_position cursor_position;
+	uint32_t sdr_white_level; // for boosting (SDR) cursor in HDR mode
 
 	/* from stream struct */
 	struct kref refcount;
@@ -255,6 +256,7 @@ bool dc_stream_set_cursor_position(
 	struct dc_stream_state *stream,
 	const struct dc_cursor_position *position);
 
+
 bool dc_stream_adjust_vmin_vmax(struct dc *dc,
 				struct dc_stream_state **stream,
 				int num_streams,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
index a558efa9b34a..bf8b68f8db4f 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.c
@@ -459,6 +459,18 @@ void dpp1_set_cursor_position(
 
 }
 
+void dpp1_cnv_set_optional_cursor_attributes(
+		struct dpp *dpp_base,
+		struct dpp_cursor_attributes *attr)
+{
+	struct dcn10_dpp *dpp = TO_DCN10_DPP(dpp_base);
+
+	if (attr) {
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_BIAS,  attr->bias);
+		REG_UPDATE(CURSOR0_FP_SCALE_BIAS,  CUR0_FP_SCALE, attr->scale);
+	}
+}
+
 void dpp1_dppclk_control(
 		struct dpp *dpp_base,
 		bool dppclk_div,
@@ -499,6 +511,7 @@ static const struct dpp_funcs dcn10_dpp_funcs = {
 		.dpp_full_bypass		= dpp1_full_bypass,
 		.set_cursor_attributes = dpp1_set_cursor_attributes,
 		.set_cursor_position = dpp1_set_cursor_position,
+		.set_optional_cursor_attributes = dpp1_cnv_set_optional_cursor_attributes,
 		.dpp_dppclk_control = dpp1_dppclk_control,
 		.dpp_set_hdr_multiplier = dpp1_set_hdr_multiplier,
 };
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
index e862cafa6501..e2889e61b18c 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp.h
@@ -119,6 +119,7 @@
 	SRI(CURSOR0_CONTROL, CNVC_CUR, id), \
 	SRI(CURSOR0_COLOR0, CNVC_CUR, id), \
 	SRI(CURSOR0_COLOR1, CNVC_CUR, id), \
+	SRI(CURSOR0_FP_SCALE_BIAS, CNVC_CUR, id), \
 	SRI(DPP_CONTROL, DPP_TOP, id), \
 	SRI(CM_HDR_MULT_COEF, CM, id)
 
@@ -324,6 +325,8 @@
 	TF_SF(CNVC_CUR0_CURSOR0_CONTROL, CUR0_ENABLE, mask_sh), \
 	TF_SF(CNVC_CUR0_CURSOR0_COLOR0, CUR0_COLOR0, mask_sh), \
 	TF_SF(CNVC_CUR0_CURSOR0_COLOR1, CUR0_COLOR1, mask_sh), \
+	TF_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_BIAS, mask_sh), \
+	TF_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_SCALE, mask_sh), \
 	TF_SF(DPP_TOP0_DPP_CONTROL, DPP_CLOCK_ENABLE, mask_sh), \
 	TF_SF(CM0_CM_HDR_MULT_COEF, CM_HDR_MULT_COEF, mask_sh)
 
@@ -1076,7 +1079,9 @@
 	type CUR0_COLOR1; \
 	type DPPCLK_RATE_CONTROL; \
 	type DPP_CLOCK_ENABLE; \
-	type CM_HDR_MULT_COEF;
+	type CM_HDR_MULT_COEF; \
+	type CUR0_FP_BIAS; \
+	type CUR0_FP_SCALE;
 
 struct dcn_dpp_shift {
 	TF_REG_FIELD_LIST(uint8_t)
@@ -1329,7 +1334,8 @@ struct dcn_dpp_mask {
 	uint32_t CURSOR0_COLOR0; \
 	uint32_t CURSOR0_COLOR1; \
 	uint32_t DPP_CONTROL; \
-	uint32_t CM_HDR_MULT_COEF;
+	uint32_t CM_HDR_MULT_COEF; \
+	uint32_t CURSOR0_FP_SCALE_BIAS;
 
 struct dcn_dpp_registers {
 	DPP_COMMON_REG_VARIABLE_LIST
@@ -1370,6 +1376,10 @@ void dpp1_set_cursor_position(
 		const struct dc_cursor_mi_param *param,
 		uint32_t width);
 
+void dpp1_cnv_set_optional_cursor_attributes(
+			struct dpp *dpp_base,
+			struct dpp_cursor_attributes *attr);
+
 bool dpp1_dscl_is_lb_conf_valid(
 		int ceil_vratio,
 		int num_partitions,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 5c4ad8a67e62..d6dc61ecf4a1 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -27,7 +27,6 @@
 #include "reg_helper.h"
 #include "basics/conversion.h"
 #include "dcn10_hubp.h"
-#include "custom_float.h"
 
 #define REG(reg)\
 	hubp1->hubp_regs->reg
@@ -1039,18 +1038,6 @@ void hubp1_cursor_set_attributes(
 	enum cursor_pitch hw_pitch = hubp1_get_cursor_pitch(attr->pitch);
 	enum cursor_lines_per_chunk lpc = hubp1_get_lines_per_chunk(
 			attr->width, attr->color_format);
-	struct fixed31_32 multiplier;
-	uint32_t hw_mult = 0x3c00; // 1.0 default multiplier
-	struct custom_float_format fmt;
-
-	fmt.exponenta_bits = 5;
-	fmt.mantissa_bits = 10;
-	fmt.sign = true;
-
-	if (attr->sdr_white_level > 80) {
-		multiplier = dc_fixpt_from_fraction(attr->sdr_white_level, 80);
-		convert_to_custom_float_format(multiplier, &fmt, &hw_mult);
-	}
 
 	hubp->curs_attr = *attr;
 
@@ -1073,8 +1060,6 @@ void hubp1_cursor_set_attributes(
 			CURSOR0_DST_Y_OFFSET, 0,
 			 /* used to shift the cursor chunk request deadline */
 			CURSOR0_CHUNK_HDL_ADJUST, 3);
-
-	REG_UPDATE(CURSOR0_FP_SCALE_BIAS, CUR0_FP_SCALE, hw_mult);
 }
 
 void hubp1_cursor_set_position(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
index 9991da50bf29..f689feace82d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.h
@@ -133,8 +133,7 @@
 	SRI(CURSOR_CONTROL, CURSOR, id), \
 	SRI(CURSOR_POSITION, CURSOR, id), \
 	SRI(CURSOR_HOT_SPOT, CURSOR, id), \
-	SRI(CURSOR_DST_OFFSET, CURSOR, id), \
-	SRI(CURSOR0_FP_SCALE_BIAS, CNVC_CUR, id)
+	SRI(CURSOR_DST_OFFSET, CURSOR, id)
 
 #define HUBP_COMMON_REG_VARIABLE_LIST \
 	uint32_t DCHUBP_CNTL; \
@@ -242,8 +241,7 @@
 	uint32_t CURSOR_POSITION; \
 	uint32_t CURSOR_HOT_SPOT; \
 	uint32_t CURSOR_DST_OFFSET; \
-	uint32_t HUBP_CLK_CNTL; \
-	uint32_t CURSOR0_FP_SCALE_BIAS
+	uint32_t HUBP_CLK_CNTL
 
 #define HUBP_SF(reg_name, field_name, post_fix)\
 	.field_name = reg_name ## __ ## field_name ## post_fix
@@ -426,8 +424,7 @@
 	HUBP_SF(CURSOR0_CURSOR_POSITION, CURSOR_Y_POSITION, mask_sh), \
 	HUBP_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_X, mask_sh), \
 	HUBP_SF(CURSOR0_CURSOR_HOT_SPOT, CURSOR_HOT_SPOT_Y, mask_sh), \
-	HUBP_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh), \
-	HUBP_SF(CNVC_CUR0_CURSOR0_FP_SCALE_BIAS, CUR0_FP_SCALE, mask_sh)
+	HUBP_SF(CURSOR0_CURSOR_DST_OFFSET, CURSOR_DST_X_OFFSET, mask_sh)
 
 #define DCN_HUBP_REG_FIELD_LIST(type) \
 	type HUBP_BLANK_EN;\
@@ -618,8 +615,7 @@
 	type CURSOR_HOT_SPOT_X; \
 	type CURSOR_HOT_SPOT_Y; \
 	type CURSOR_DST_X_OFFSET; \
-	type OUTPUT_FP; \
-	type CUR0_FP_SCALE
+	type OUTPUT_FP
 
 struct dcn_mi_registers {
 	HUBP_COMMON_REG_VARIABLE_LIST;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 2e145aa663a4..6e8127cb2e56 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -2555,6 +2555,33 @@ static void dcn10_set_cursor_attribute(struct pipe_ctx *pipe_ctx)
 		pipe_ctx->plane_res.dpp, attributes->color_format);
 }
 
+static void dcn10_set_cursor_sdr_white_level(struct pipe_ctx *pipe_ctx)
+{
+	uint32_t sdr_white_level = pipe_ctx->stream->cursor_attributes.sdr_white_level;
+	struct fixed31_32 multiplier;
+	struct dpp_cursor_attributes opt_attr = { 0 };
+	uint32_t hw_scale = 0x3c00; // 1.0 default multiplier
+	struct custom_float_format fmt;
+
+	if (!pipe_ctx->plane_res.dpp->funcs->set_optional_cursor_attributes)
+		return;
+
+	fmt.exponenta_bits = 5;
+	fmt.mantissa_bits = 10;
+	fmt.sign = true;
+
+	if (sdr_white_level > 80) {
+		multiplier = dc_fixpt_from_fraction(sdr_white_level, 80);
+		convert_to_custom_float_format(multiplier, &fmt, &hw_scale);
+	}
+
+	opt_attr.scale = hw_scale;
+	opt_attr.bias = 0;
+
+	pipe_ctx->plane_res.dpp->funcs->set_optional_cursor_attributes(
+			pipe_ctx->plane_res.dpp, &opt_attr);
+}
+
 static const struct hw_sequencer_funcs dcn10_funcs = {
 	.program_gamut_remap = program_gamut_remap,
 	.program_csc_matrix = program_csc_matrix,
@@ -2602,7 +2629,8 @@ static const struct hw_sequencer_funcs dcn10_funcs = {
 	.edp_power_control = hwss_edp_power_control,
 	.edp_wait_for_hpd_ready = hwss_edp_wait_for_hpd_ready,
 	.set_cursor_position = dcn10_set_cursor_position,
-	.set_cursor_attribute = dcn10_set_cursor_attribute
+	.set_cursor_attribute = dcn10_set_cursor_attribute,
+	.set_cursor_sdr_white_level = dcn10_set_cursor_sdr_white_level
 };
 
 
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
index 582458f028f8..74ad94b0e4f0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dpp.h
@@ -151,6 +151,9 @@ struct dpp_funcs {
 	void (*dpp_set_hdr_multiplier)(
 			struct dpp *dpp_base,
 			uint32_t multiplier);
+	void (*set_optional_cursor_attributes)(
+			struct dpp *dpp_base,
+			struct dpp_cursor_attributes *attr);
 
 	void (*dpp_dppclk_control)(
 			struct dpp *dpp_base,
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
index c2277d1e195b..a14ce4de80b2 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw_sequencer.h
@@ -223,6 +223,7 @@ struct hw_sequencer_funcs {
 
 	void (*set_cursor_position)(struct pipe_ctx *pipe);
 	void (*set_cursor_attribute)(struct pipe_ctx *pipe);
+	void (*set_cursor_sdr_white_level)(struct pipe_ctx *pipe);
 
 };
 
-- 
cgit v1.2.3


From bf53769d9fc95c89d2f1588463c268c3af987748 Mon Sep 17 00:00:00 2001
From: Gloria Li <geling.li@amd.com>
Date: Tue, 3 Jul 2018 14:39:22 -0400
Subject: drm/amd/display: add HDR visual confirm

[Why]
Testing team wants a way to tell if HDR is on or not

[How]
Program the overscan color to visually indicate the HDR state of the top-most plane

Signed-off-by: Gloria Li <geling.li@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                | 11 ++++-
 drivers/gpu/drm/amd/display/dc/dce/dce_transform.c |  2 +-
 .../amd/display/dc/dce110/dce110_hw_sequencer.c    |  2 +-
 .../drm/amd/display/dc/dce110/dce110_transform_v.c |  2 +-
 .../gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c  |  7 ++-
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  | 50 ++++++++++++++++++++--
 6 files changed, 63 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 208578301d59..85f5ddded418 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -169,6 +169,12 @@ struct dc_config {
 	bool disable_disp_pll_sharing;
 };
 
+enum visual_confirm {
+	VISUAL_CONFIRM_DISABLE = 0,
+	VISUAL_CONFIRM_SURFACE = 1,
+	VISUAL_CONFIRM_HDR = 2,
+};
+
 enum dcc_option {
 	DCC_ENABLE = 0,
 	DCC_DISABLE = 1,
@@ -202,7 +208,7 @@ struct dc_clocks {
 };
 
 struct dc_debug {
-	bool surface_visual_confirm;
+	enum visual_confirm visual_confirm;
 	bool sanity_checks;
 	bool max_disp_clk;
 	bool surface_trace;
@@ -387,7 +393,8 @@ enum dc_transfer_func_predefined {
 	TRANSFER_FUNCTION_LINEAR,
 	TRANSFER_FUNCTION_UNITY,
 	TRANSFER_FUNCTION_HLG,
-	TRANSFER_FUNCTION_HLG12
+	TRANSFER_FUNCTION_HLG12,
+	TRANSFER_FUNCTION_GAMMA22
 };
 
 struct dc_transfer_func {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
index a02e719d7794..ab63d0d0304c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_transform.c
@@ -155,7 +155,7 @@ static void program_overscan(
 	int overscan_bottom = data->v_active
 			- data->recout.y - data->recout.height;
 
-	if (xfm_dce->base.ctx->dc->debug.surface_visual_confirm) {
+	if (xfm_dce->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 		overscan_bottom += 2;
 		overscan_right += 2;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index e48eb3056af5..45388bff2c7d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1256,7 +1256,7 @@ static void program_scaler(const struct dc *dc,
 		return;
 #endif
 
-	if (dc->debug.surface_visual_confirm)
+	if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE)
 		get_surface_visual_confirm_color(pipe_ctx, &color);
 	else
 		color_space_to_black_color(dc,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
index a7dce060204f..aa8d6b10d2c3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_transform_v.c
@@ -235,7 +235,7 @@ static void program_overscan(
 	int overscan_right = data->h_active - data->recout.x - data->recout.width;
 	int overscan_bottom = data->v_active - data->recout.y - data->recout.height;
 
-	if (xfm_dce->base.ctx->dc->debug.surface_visual_confirm) {
+	if (xfm_dce->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE) {
 		overscan_bottom += 2;
 		overscan_right += 2;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
index f0cc97518c49..4a863a5dab41 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_dpp_dscl.c
@@ -621,6 +621,10 @@ static void dpp1_dscl_set_manual_ratio_init(
 static void dpp1_dscl_set_recout(
 			struct dcn10_dpp *dpp, const struct rect *recout)
 {
+	int visual_confirm_on = 0;
+	if (dpp->base.ctx->dc->debug.visual_confirm != VISUAL_CONFIRM_DISABLE)
+		visual_confirm_on = 1;
+
 	REG_SET_2(RECOUT_START, 0,
 		/* First pixel of RECOUT */
 			 RECOUT_START_X, recout->x,
@@ -632,8 +636,7 @@ static void dpp1_dscl_set_recout(
 			 RECOUT_WIDTH, recout->width,
 		/* Number of RECOUT vertical lines */
 			 RECOUT_HEIGHT, recout->height
-			 - dpp->base.ctx->dc->debug.surface_visual_confirm * 4 *
-			 (dpp->base.inst + 1));
+			 - visual_confirm_on * 4 * (dpp->base.inst + 1));
 }
 
 /* Main function to program scaler and line buffer in manual scaling mode */
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index 6e8127cb2e56..ade74c821831 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1768,6 +1768,43 @@ static void dcn10_get_surface_visual_confirm_color(
 	}
 }
 
+static void dcn10_get_hdr_visual_confirm_color(
+		struct pipe_ctx *pipe_ctx,
+		struct tg_color *color)
+{
+	uint32_t color_value = MAX_TG_COLOR_VALUE;
+
+	// Determine the overscan color based on the top-most (desktop) plane's context
+	struct pipe_ctx *top_pipe_ctx  = pipe_ctx;
+
+	while (top_pipe_ctx->top_pipe != NULL)
+		top_pipe_ctx = top_pipe_ctx->top_pipe;
+
+	switch (top_pipe_ctx->plane_res.scl_data.format) {
+	case PIXEL_FORMAT_ARGB2101010:
+		if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_UNITY) {
+			/* HDR10, ARGB2101010 - set boarder color to red */
+			color->color_r_cr = color_value;
+		}
+		break;
+	case PIXEL_FORMAT_FP16:
+		if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_PQ) {
+			/* HDR10, FP16 - set boarder color to blue */
+			color->color_b_cb = color_value;
+		} else if (top_pipe_ctx->stream->out_transfer_func->tf == TRANSFER_FUNCTION_GAMMA22) {
+			/* FreeSync 2 HDR - set boarder color to green */
+			color->color_g_y = color_value;
+		}
+		break;
+	default:
+		/* SDR - set boarder color to Gray */
+		color->color_r_cr = color_value/2;
+		color->color_b_cb = color_value/2;
+		color->color_g_y = color_value/2;
+		break;
+	}
+}
+
 static uint16_t fixed_point_to_int_frac(
 	struct fixed31_32 arg,
 	uint8_t integer_bits,
@@ -1862,13 +1899,17 @@ static void dcn10_update_mpcc(struct dc *dc, struct pipe_ctx *pipe_ctx)
 
 	/* TODO: proper fix once fpga works */
 
-	if (dc->debug.surface_visual_confirm)
+	if (dc->debug.visual_confirm == VISUAL_CONFIRM_HDR) {
+		dcn10_get_hdr_visual_confirm_color(
+				pipe_ctx, &blnd_cfg.black_color);
+	} else if (dc->debug.visual_confirm == VISUAL_CONFIRM_SURFACE) {
 		dcn10_get_surface_visual_confirm_color(
 				pipe_ctx, &blnd_cfg.black_color);
-	else
+	} else {
 		color_space_to_black_color(
-			dc, pipe_ctx->stream->output_color_space,
-			&blnd_cfg.black_color);
+				dc, pipe_ctx->stream->output_color_space,
+				&blnd_cfg.black_color);
+	}
 
 	if (per_pixel_alpha)
 		blnd_cfg.alpha_mode = MPCC_ALPHA_BLEND_MODE_PER_PIXEL_ALPHA;
@@ -2148,6 +2189,7 @@ static void program_all_pipe_in_tree(
 				pipe_ctx->stream_res.tg);
 
 		dc->hwss.blank_pixel_data(dc, pipe_ctx, blank);
+
 	}
 
 	if (pipe_ctx->plane_state != NULL) {
-- 
cgit v1.2.3


From 2068afe649ae36f422ced4ecf0efee79e2ff5154 Mon Sep 17 00:00:00 2001
From: Nikola Cornij <nikola.cornij@amd.com>
Date: Wed, 4 Jul 2018 19:05:16 -0400
Subject: drm/amd/display: Add hook for MST root branch info

This allows DM to do any necessary updates before MST discovery starts.

Signed-off-by: Nikola Cornij <nikola.cornij@amd.com>
Reviewed-by: Nikola Cornij <Nikola.Cornij@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c | 5 +++++
 drivers/gpu/drm/amd/display/dc/core/dc_link.c             | 4 ++++
 drivers/gpu/drm/amd/display/dc/dm_helpers.h               | 8 ++++++++
 3 files changed, 17 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
index 59b113d11f66..8403b6a9a77b 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_helpers.c
@@ -169,6 +169,11 @@ static void get_payload_table(
 	mutex_unlock(&mst_mgr->payload_lock);
 }
 
+void dm_helpers_dp_update_branch_info(
+	struct dc_context *ctx,
+	const struct dc_link *link)
+{}
+
 /*
  * Writes payload allocation table in immediate downstream device.
  */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index fe29a398b703..a4429c90c60c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -529,6 +529,10 @@ static bool detect_dp(
 			if (reason == DETECT_REASON_BOOT)
 				boot = true;
 
+			dm_helpers_dp_update_branch_info(
+				link->ctx,
+				link);
+
 			if (!dm_helpers_dp_mst_start_top_mgr(
 				link->ctx,
 				link, boot)) {
diff --git a/drivers/gpu/drm/amd/display/dc/dm_helpers.h b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
index 7e6b9f5b8906..5d4527d03045 100644
--- a/drivers/gpu/drm/amd/display/dc/dm_helpers.h
+++ b/drivers/gpu/drm/amd/display/dc/dm_helpers.h
@@ -40,6 +40,14 @@ enum dc_edid_status dm_helpers_parse_edid_caps(
 	const struct dc_edid *edid,
 	struct dc_edid_caps *edid_caps);
 
+
+/*
+ * Update DP branch info
+ */
+void dm_helpers_dp_update_branch_info(
+		struct dc_context *ctx,
+		const struct dc_link *link);
+
 /*
  * Writes payload allocation table in immediate downstream device.
  */
-- 
cgit v1.2.3


From 68199bd16cb56d121ade83918d5858933d07ae8a Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Sat, 7 Jul 2018 15:43:07 -0400
Subject: drm/amd/display: Move address tracking out of HUBP

[Why]
We sometime require remapping of FB address space to UMA

[How]
Move address tracking up a layer before we apply address translation

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c     |  4 ----
 .../gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 19 +++++++++++++++----
 drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h          |  1 -
 3 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index d6dc61ecf4a1..332354ca6529 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -457,9 +457,6 @@ bool hubp1_program_surface_flip_and_addr(
 
 	hubp->request_address = *address;
 
-	if (flip_immediate)
-		hubp->current_address = *address;
-
 	return true;
 }
 
@@ -695,7 +692,6 @@ bool hubp1_is_flip_pending(struct hubp *hubp)
 	if (earliest_inuse_address.grph.addr.quad_part != hubp->request_address.grph.addr.quad_part)
 		return true;
 
-	hubp->current_address = hubp->request_address;
 	return false;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index ade74c821831..c87f6e603055 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1157,12 +1157,19 @@ static void dcn10_update_plane_addr(const struct dc *dc, struct pipe_ctx *pipe_c
 
 	if (plane_state == NULL)
 		return;
+
 	addr_patched = patch_address_for_sbs_tb_stereo(pipe_ctx, &addr);
+
 	pipe_ctx->plane_res.hubp->funcs->hubp_program_surface_flip_and_addr(
 			pipe_ctx->plane_res.hubp,
 			&plane_state->address,
 			plane_state->flip_immediate);
+
 	plane_state->status.requested_address = plane_state->address;
+
+	if (plane_state->flip_immediate)
+		plane_state->status.current_address = plane_state->address;
+
 	if (addr_patched)
 		pipe_ctx->plane_state->address.grph_stereo.left_addr = addr;
 }
@@ -2533,16 +2540,20 @@ static void dcn10_update_pending_status(struct pipe_ctx *pipe_ctx)
 {
 	struct dc_plane_state *plane_state = pipe_ctx->plane_state;
 	struct timing_generator *tg = pipe_ctx->stream_res.tg;
+	bool flip_pending;
 
 	if (plane_state == NULL)
 		return;
 
-	plane_state->status.is_flip_pending =
-			pipe_ctx->plane_res.hubp->funcs->hubp_is_flip_pending(
+	flip_pending = pipe_ctx->plane_res.hubp->funcs->hubp_is_flip_pending(
 					pipe_ctx->plane_res.hubp);
 
-	plane_state->status.current_address = pipe_ctx->plane_res.hubp->current_address;
-	if (pipe_ctx->plane_res.hubp->current_address.type == PLN_ADDR_TYPE_GRPH_STEREO &&
+	plane_state->status.is_flip_pending = flip_pending;
+
+	if (!flip_pending)
+		plane_state->status.current_address = plane_state->status.requested_address;
+
+	if (plane_state->status.current_address.type == PLN_ADDR_TYPE_GRPH_STEREO &&
 			tg->funcs->is_stereo_left_eye) {
 		plane_state->status.is_right_eye =
 				!tg->funcs->is_stereo_left_eye(pipe_ctx->stream_res.tg);
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
index 5b7976f6861a..4f3f9e68ccfa 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/hubp.h
@@ -46,7 +46,6 @@ struct hubp {
 	const struct hubp_funcs *funcs;
 	struct dc_context *ctx;
 	struct dc_plane_address request_address;
-	struct dc_plane_address current_address;
 	int inst;
 
 	/* run time states */
-- 
cgit v1.2.3


From d6e75df4e5e10362a140c5c6ce8ced3612296ae3 Mon Sep 17 00:00:00 2001
From: Jun Lei <Jun.Lei@amd.com>
Date: Fri, 22 Jun 2018 16:51:47 -0400
Subject: drm/amd/display: add new dc debug structure to track debug data

[why]
Some DTN tests still failing @ 2%  Need to reduce.

[how]
add instrumentation code to driver so we can get more information from failed runs.

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 3 +++
 drivers/gpu/drm/amd/display/dc/dc.h              | 5 +++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 54e396452345..701a882505e9 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1028,6 +1028,9 @@ enum link_training_result dc_link_dp_perform_link_training(
 			lt_settings.lane_settings[0].VOLTAGE_SWING,
 			lt_settings.lane_settings[0].PRE_EMPHASIS);
 
+	if (status != LINK_TRAINING_SUCCESS)
+		link->ctx->dc->debug.debug_data.ltFailCount++;
+
 	return status;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 85f5ddded418..f74ad8e3fd4e 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -259,6 +259,11 @@ struct dc_debug {
 	bool scl_reset_length10;
 	bool hdmi20_disable;
 
+	struct {
+		uint32_t ltFailCount;
+		uint32_t i2cErrorCount;
+		uint32_t auxErrorCount;
+	} debug_data;
 };
 struct dc_state;
 struct resource_pool;
-- 
cgit v1.2.3


From 4a7d1d123ddb8c0b57e9beacee03ffcc9b55555a Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Mon, 9 Jul 2018 17:25:15 -0400
Subject: drm/amd/display: dal 3.1.56

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Steven Chiu <Steven.Chiu@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index f74ad8e3fd4e..b10dc177ad61 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.55"
+#define DC_VER "3.1.56"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From ddb85fcd839cab0ac46a44d47c4f345dad4c2cb1 Mon Sep 17 00:00:00 2001
From: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Date: Tue, 10 Jul 2018 16:04:05 -0400
Subject: drm/amd/display: Null ptr check for set_sdr_white_level

[Why&How]
Cursor boosting can only be done on DCN+
Check for nullptr since DCE doesn't implement it.

Signed-off-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Sivapiriyan Kumarasamy <Sivapiriyan.Kumarasamy@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_stream.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
index 4717330a42f4..fdcc8ab19bf3 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
@@ -214,7 +214,8 @@ bool dc_stream_set_cursor_attributes(
 		}
 
 		core_dc->hwss.set_cursor_attribute(pipe_ctx);
-		core_dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
+		if (core_dc->hwss.set_cursor_sdr_white_level)
+			core_dc->hwss.set_cursor_sdr_white_level(pipe_ctx);
 	}
 
 	if (pipe_to_program)
-- 
cgit v1.2.3


From 9a6a8075bd439115b41468eaccdcb5e463196fb5 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Fri, 6 Jul 2018 13:40:33 -0400
Subject: drm/amd/display: Fix some checkpatch.pl errors and warnings in
 dc_link_dp.c

[Why]
Any Linux kernel code should pass checkpatch.pl with no errors and
little, if any, warning.

[How]
Fixing some spacing errors and warnings.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 35 ++++++++++++------------
 1 file changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 701a882505e9..474cd3e01752 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -39,7 +39,7 @@ static bool decide_fallback_link_setting(
 		struct dc_link_settings initial_link_settings,
 		struct dc_link_settings *current_link_setting,
 		enum link_training_result training_result);
-static struct dc_link_settings get_common_supported_link_settings (
+static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b);
 
@@ -94,8 +94,8 @@ static void dpcd_set_link_settings(
 	uint8_t rate = (uint8_t)
 	(lt_settings->link_settings.link_rate);
 
-	union down_spread_ctrl downspread = {{0}};
-	union lane_count_set lane_count_set = {{0}};
+	union down_spread_ctrl downspread = { {0} };
+	union lane_count_set lane_count_set = { {0} };
 	uint8_t link_set_buffer[2];
 
 	downspread.raw = (uint8_t)
@@ -165,11 +165,11 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 	const struct link_training_settings *lt_settings,
 	enum hw_dp_training_pattern pattern)
 {
-	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = {{{0}}};
+	union dpcd_training_lane dpcd_lane[LANE_COUNT_DP_MAX] = { { {0} } };
 	const uint32_t dpcd_base_lt_offset =
 	DP_TRAINING_PATTERN_SET;
 	uint8_t dpcd_lt_buffer[5] = {0};
-	union dpcd_training_pattern dpcd_pattern = {{0}};
+	union dpcd_training_pattern dpcd_pattern = { {0} };
 	uint32_t lane;
 	uint32_t size_in_bytes;
 	bool edp_workaround = false; /* TODO link_prop.INTERNAL */
@@ -233,7 +233,7 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 			link,
 			DP_TRAINING_PATTERN_SET,
 			&dpcd_pattern.raw,
-			sizeof(dpcd_pattern.raw) );
+			sizeof(dpcd_pattern.raw));
 
 		core_link_write_dpcd(
 			link,
@@ -247,7 +247,7 @@ static void dpcd_set_lt_pattern_and_lane_settings(
 				link,
 				dpcd_base_lt_offset,
 				dpcd_lt_buffer,
-				size_in_bytes + sizeof(dpcd_pattern.raw) );
+				size_in_bytes + sizeof(dpcd_pattern.raw));
 
 	link->cur_lane_setting = lt_settings->lane_settings[0];
 }
@@ -429,8 +429,8 @@ static void get_lane_status_and_drive_settings(
 	struct link_training_settings *req_settings)
 {
 	uint8_t dpcd_buf[6] = {0};
-	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = {{{0}}};
-	struct link_training_settings request_settings = {{0}};
+	union lane_adjust dpcd_lane_adjust[LANE_COUNT_DP_MAX] = { { {0} } };
+	struct link_training_settings request_settings = { {0} };
 	uint32_t lane;
 
 	memset(req_settings, '\0', sizeof(struct link_training_settings));
@@ -652,7 +652,7 @@ static bool perform_post_lt_adj_req_sequence(
 
 			if (req_drv_setting_changed) {
 				update_drive_settings(
-					lt_settings,req_settings);
+					lt_settings, req_settings);
 
 				dc_link_dp_set_drive_settings(link,
 						lt_settings);
@@ -725,8 +725,8 @@ static enum link_training_result perform_channel_equalization_sequence(
 	enum hw_dp_training_pattern hw_tr_pattern;
 	uint32_t retries_ch_eq;
 	enum dc_lane_count lane_count = lt_settings->link_settings.lane_count;
-	union lane_align_status_updated dpcd_lane_status_updated = {{0}};
-	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = {{{0}}};
+	union lane_align_status_updated dpcd_lane_status_updated = { {0} };
+	union lane_status dpcd_lane_status[LANE_COUNT_DP_MAX] = { { {0} } };
 
 	hw_tr_pattern = get_supported_tp(link);
 
@@ -1186,7 +1186,7 @@ bool dp_hbr_verify_link_cap(
 	return success;
 }
 
-static struct dc_link_settings get_common_supported_link_settings (
+static struct dc_link_settings get_common_supported_link_settings(
 		struct dc_link_settings link_setting_a,
 		struct dc_link_settings link_setting_b)
 {
@@ -1432,6 +1432,7 @@ static uint32_t bandwidth_in_kbps_from_link_settings(
 
 	uint32_t lane_count  = link_setting->lane_count;
 	uint32_t kbps = link_rate_in_kbps;
+
 	kbps *= lane_count;
 	kbps *= 8;   /* 8 bits per byte*/
 
@@ -1449,9 +1450,9 @@ bool dp_validate_mode_timing(
 	const struct dc_link_settings *link_setting;
 
 	/*always DP fail safe mode*/
-	if (timing->pix_clk_khz == (uint32_t)25175 &&
-		timing->h_addressable == (uint32_t)640 &&
-		timing->v_addressable == (uint32_t)480)
+	if (timing->pix_clk_khz == (uint32_t) 25175 &&
+		timing->h_addressable == (uint32_t) 640 &&
+		timing->v_addressable == (uint32_t) 480)
 		return true;
 
 	/* We always use verified link settings */
@@ -2001,7 +2002,7 @@ static void handle_automated_test(struct dc_link *link)
 
 bool dc_link_handle_hpd_rx_irq(struct dc_link *link, union hpd_irq_data *out_hpd_irq_dpcd_data, bool *out_link_loss)
 {
-	union hpd_irq_data hpd_irq_dpcd_data = {{{{0}}}};
+	union hpd_irq_data hpd_irq_dpcd_data = { { { {0} } } };
 	union device_service_irq device_service_clear = { { 0 } };
 	enum dc_status result;
 
-- 
cgit v1.2.3


From 050d9d43a7d3847fd9726a675bf644b124518425 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 13 Jul 2018 09:50:08 +0200
Subject: drm/amdgpu: cleanup job header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move job related defines, structure and function declarations to
amdgpu_job.h

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     | 46 +-------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 74 +++++++++++++++++++++++++++++++++
 2 files changed, 75 insertions(+), 45 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index c6c1e8dc919f..e0cc9f878e80 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -73,6 +73,7 @@
 #include "amdgpu_virt.h"
 #include "amdgpu_gart.h"
 #include "amdgpu_debugfs.h"
+#include "amdgpu_job.h"
 
 /*
  * Modules parameters.
@@ -600,17 +601,6 @@ struct amdgpu_ib {
 
 extern const struct drm_sched_backend_ops amdgpu_sched_ops;
 
-int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
-		     struct amdgpu_job **job, struct amdgpu_vm *vm);
-int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
-			     struct amdgpu_job **job);
-
-void amdgpu_job_free_resources(struct amdgpu_job *job);
-void amdgpu_job_free(struct amdgpu_job *job);
-int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct drm_sched_entity *entity, void *owner,
-		      struct dma_fence **f);
-
 /*
  * Queue manager
  */
@@ -1058,40 +1048,6 @@ struct amdgpu_cs_parser {
 	struct drm_syncobj **post_dep_syncobjs;
 };
 
-#define AMDGPU_PREAMBLE_IB_PRESENT          (1 << 0) /* bit set means command submit involves a preamble IB */
-#define AMDGPU_PREAMBLE_IB_PRESENT_FIRST    (1 << 1) /* bit set means preamble IB is first presented in belonging context */
-#define AMDGPU_HAVE_CTX_SWITCH              (1 << 2) /* bit set means context switch occured */
-
-struct amdgpu_job {
-	struct drm_sched_job    base;
-	struct amdgpu_device	*adev;
-	struct amdgpu_vm	*vm;
-	struct amdgpu_ring	*ring;
-	struct amdgpu_sync	sync;
-	struct amdgpu_sync	sched_sync;
-	struct amdgpu_ib	*ibs;
-	struct dma_fence	*fence; /* the hw fence */
-	uint32_t		preamble_status;
-	uint32_t		num_ibs;
-	void			*owner;
-	uint64_t		fence_ctx; /* the fence_context this job uses */
-	bool                    vm_needs_flush;
-	uint64_t		vm_pd_addr;
-	unsigned		vmid;
-	unsigned		pasid;
-	uint32_t		gds_base, gds_size;
-	uint32_t		gws_base, gws_size;
-	uint32_t		oa_base, oa_size;
-	uint32_t		vram_lost_counter;
-
-	/* user fence handling */
-	uint64_t		uf_addr;
-	uint64_t		uf_sequence;
-
-};
-#define to_amdgpu_job(sched_job)		\
-		container_of((sched_job), struct amdgpu_job, base)
-
 static inline u32 amdgpu_get_ib_value(struct amdgpu_cs_parser *p,
 				      uint32_t ib_idx, int idx)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
new file mode 100644
index 000000000000..35bb93254eb2
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -0,0 +1,74 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __AMDGPU_JOB_H__
+#define __AMDGPU_JOB_H__
+
+/* bit set means command submit involves a preamble IB */
+#define AMDGPU_PREAMBLE_IB_PRESENT          (1 << 0)
+/* bit set means preamble IB is first presented in belonging context */
+#define AMDGPU_PREAMBLE_IB_PRESENT_FIRST    (1 << 1)
+/* bit set means context switch occured */
+#define AMDGPU_HAVE_CTX_SWITCH              (1 << 2)
+
+#define to_amdgpu_job(sched_job)		\
+		container_of((sched_job), struct amdgpu_job, base)
+
+struct amdgpu_job {
+	struct drm_sched_job    base;
+	struct amdgpu_device	*adev;
+	struct amdgpu_vm	*vm;
+	struct amdgpu_ring	*ring;
+	struct amdgpu_sync	sync;
+	struct amdgpu_sync	sched_sync;
+	struct amdgpu_ib	*ibs;
+	struct dma_fence	*fence; /* the hw fence */
+	uint32_t		preamble_status;
+	uint32_t		num_ibs;
+	void			*owner;
+	uint64_t		fence_ctx; /* the fence_context this job uses */
+	bool                    vm_needs_flush;
+	uint64_t		vm_pd_addr;
+	unsigned		vmid;
+	unsigned		pasid;
+	uint32_t		gds_base, gds_size;
+	uint32_t		gws_base, gws_size;
+	uint32_t		oa_base, oa_size;
+	uint32_t		vram_lost_counter;
+
+	/* user fence handling */
+	uint64_t		uf_addr;
+	uint64_t		uf_sequence;
+
+};
+
+int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
+		     struct amdgpu_job **job, struct amdgpu_vm *vm);
+int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
+			     struct amdgpu_job **job);
+
+void amdgpu_job_free_resources(struct amdgpu_job *job);
+void amdgpu_job_free(struct amdgpu_job *job);
+int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
+		      struct drm_sched_entity *entity, void *owner,
+		      struct dma_fence **f);
+#endif
-- 
cgit v1.2.3


From eb3961a57424a5c3dae44576d1c88e64a818d871 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 13 Jul 2018 09:58:49 +0200
Subject: drm/amdgpu: remove fence context from the job
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Can be obtained directly from the fence as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  | 1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c  | 2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h | 1 -
 4 files changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 6d8df76b5a5d..6eb7ee859ffd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1239,7 +1239,6 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	}
 
 	job->owner = p->filp;
-	job->fence_ctx = entity->fence_context;
 	p->fence = dma_fence_get(&job->base.s_fence->finished);
 
 	r = amdgpu_ctx_add_fence(p->ctx, ring, p->fence, &seq);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index ce7739832d29..5518e623fed2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -139,7 +139,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
 	/* ring tests don't use a job */
 	if (job) {
 		vm = job->vm;
-		fence_ctx = job->fence_ctx;
+		fence_ctx = job->base.s_fence->scheduled.context;
 	} else {
 		vm = NULL;
 		fence_ctx = 0;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 2bd56760c744..10e0a97c7c03 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -132,7 +132,6 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
 		return r;
 
 	job->owner = owner;
-	job->fence_ctx = entity->fence_context;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
 	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 35bb93254eb2..3151692312bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -45,7 +45,6 @@ struct amdgpu_job {
 	uint32_t		preamble_status;
 	uint32_t		num_ibs;
 	void			*owner;
-	uint64_t		fence_ctx; /* the fence_context this job uses */
 	bool                    vm_needs_flush;
 	uint64_t		vm_pd_addr;
 	unsigned		vmid;
-- 
cgit v1.2.3


From 0e28b10ff1b8e65788040b51c30c9cc984060dcd Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 13 Jul 2018 13:54:56 +0200
Subject: drm/amdgpu: remove ring parameter from amdgpu_job_submit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We know the ring through the entity anyway.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c  |  9 ++++-----
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h  |  5 ++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c  |  6 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c  |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c   | 11 +++++------
 drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c    |  2 +-
 9 files changed, 20 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 10e0a97c7c03..51ff751e093b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -117,21 +117,20 @@ void amdgpu_job_free(struct amdgpu_job *job)
 	kfree(job);
 }
 
-int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct drm_sched_entity *entity, void *owner,
-		      struct dma_fence **f)
+int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
+		      void *owner, struct dma_fence **f)
 {
 	int r;
-	job->ring = ring;
 
 	if (!f)
 		return -EINVAL;
 
-	r = drm_sched_job_init(&job->base, &ring->sched, entity, owner);
+	r = drm_sched_job_init(&job->base, entity->sched, entity, owner);
 	if (r)
 		return r;
 
 	job->owner = owner;
+	job->ring = to_amdgpu_ring(entity->sched);
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
 	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 3151692312bd..39f4230e1d37 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -67,7 +67,6 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 
 void amdgpu_job_free_resources(struct amdgpu_job *job);
 void amdgpu_job_free(struct amdgpu_job *job);
-int amdgpu_job_submit(struct amdgpu_job *job, struct amdgpu_ring *ring,
-		      struct drm_sched_entity *entity, void *owner,
-		      struct dma_fence **f);
+int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
+		      void *owner, struct dma_fence **f);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index a293f4e6760d..5018c0b6bf1a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -44,6 +44,8 @@
 #define AMDGPU_FENCE_FLAG_INT           (1 << 1)
 #define AMDGPU_FENCE_FLAG_TC_WB_ONLY    (1 << 2)
 
+#define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
+
 enum amdgpu_ring_type {
 	AMDGPU_RING_TYPE_GFX,
 	AMDGPU_RING_TYPE_COMPUTE,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 11a12483c995..9958e76d1c78 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2006,7 +2006,7 @@ static int amdgpu_map_buffer(struct ttm_buffer_object *bo,
 	if (r)
 		goto error_free;
 
-	r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
 	if (r)
 		goto error_free;
@@ -2083,7 +2083,7 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
 			DRM_ERROR("Error scheduling IBs (%d)\n", r);
 		amdgpu_job_free(job);
 	} else {
-		r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+		r = amdgpu_job_submit(job, &adev->mman.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
 		if (r)
 			goto error_free;
@@ -2175,7 +2175,7 @@ int amdgpu_fill_buffer(struct amdgpu_bo *bo,
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
-	r = amdgpu_job_submit(job, ring, &adev->mman.entity,
+	r = amdgpu_job_submit(job, &adev->mman.entity,
 			      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
 	if (r)
 		goto error_free;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index a6c2cace4b9d..848b2e898818 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -1074,7 +1074,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		if (r)
 			goto err_free;
 
-		r = amdgpu_job_submit(job, ring, &adev->uvd.inst[ring->me].entity,
+		r = amdgpu_job_submit(job, &adev->uvd.inst[ring->me].entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err_free;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index ffb0fcc9707e..7dfb4c4b19c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -539,7 +539,7 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 		amdgpu_job_free(job);
 	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 484e2c19c027..5d3d783f2d72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -425,8 +425,8 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 	if (r)
 		goto error_free;
 
-	r = amdgpu_job_submit(job, ring, &vm->entity,
-			      AMDGPU_FENCE_OWNER_UNDEFINED, &fence);
+	r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_UNDEFINED,
+			      &fence);
 	if (r)
 		goto error_free;
 
@@ -1120,8 +1120,8 @@ restart:
 		amdgpu_sync_resv(adev, &job->sync, root->tbo.resv,
 				 AMDGPU_FENCE_OWNER_VM, false);
 		WARN_ON(params.ib->length_dw > ndw);
-		r = amdgpu_job_submit(job, ring, &vm->entity,
-				      AMDGPU_FENCE_OWNER_VM, &fence);
+		r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_VM,
+				      &fence);
 		if (r)
 			goto error;
 
@@ -1485,8 +1485,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 
 	amdgpu_ring_pad_ib(ring, params.ib);
 	WARN_ON(params.ib->length_dw > ndw);
-	r = amdgpu_job_submit(job, ring, &vm->entity,
-			      AMDGPU_FENCE_OWNER_VM, &f);
+	r = amdgpu_job_submit(job, &vm->entity, AMDGPU_FENCE_OWNER_VM, &f);
 	if (r)
 		goto error_free;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 1c118c02e8cb..591d1f211823 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -320,7 +320,7 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 
 		amdgpu_job_free(job);
 	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err;
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index d48bc3393545..ceb0a7037897 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -321,7 +321,7 @@ int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 
 		amdgpu_job_free(job);
 	} else {
-		r = amdgpu_job_submit(job, ring, &ring->adev->vce.entity,
+		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err;
-- 
cgit v1.2.3


From 3320b8d2acd3d480d0dd4835d970067354eac915 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 13 Jul 2018 15:08:44 +0200
Subject: drm/amdgpu: remove job->ring
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can easily get that from the scheduler.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c     | 18 +++++++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c    | 23 ++++++++++++-----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h    |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h  |  8 ++++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c    |  2 +-
 7 files changed, 29 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e0cc9f878e80..90780b0f0ce5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1027,6 +1027,7 @@ struct amdgpu_cs_parser {
 
 	/* scheduler job object */
 	struct amdgpu_job	*job;
+	struct amdgpu_ring	*ring;
 
 	/* buffer objects */
 	struct ww_acquire_ctx		ticket;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 6eb7ee859ffd..72dc9b36b937 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -912,11 +912,11 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_vm *vm = &fpriv->vm;
-	struct amdgpu_ring *ring = p->job->ring;
+	struct amdgpu_ring *ring = p->ring;
 	int r;
 
 	/* Only for UVD/VCE VM emulation */
-	if (p->job->ring->funcs->parse_cs) {
+	if (p->ring->funcs->parse_cs) {
 		unsigned i, j;
 
 		for (i = 0, j = 0; i < p->nchunks && j < p->job->num_ibs; i++) {
@@ -1030,10 +1030,10 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 			}
 		}
 
-		if (parser->job->ring && parser->job->ring != ring)
+		if (parser->ring && parser->ring != ring)
 			return -EINVAL;
 
-		parser->job->ring = ring;
+		parser->ring = ring;
 
 		r =  amdgpu_ib_get(adev, vm,
 					ring->funcs->parse_cs ? chunk_ib->ib_bytes : 0,
@@ -1052,11 +1052,11 @@ static int amdgpu_cs_ib_fill(struct amdgpu_device *adev,
 
 	/* UVD & VCE fw doesn't support user fences */
 	if (parser->job->uf_addr && (
-	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
-	    parser->job->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
+	    parser->ring->funcs->type == AMDGPU_RING_TYPE_UVD ||
+	    parser->ring->funcs->type == AMDGPU_RING_TYPE_VCE))
 		return -EINVAL;
 
-	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->job->ring->idx);
+	return amdgpu_ctx_wait_prev_fence(parser->ctx, parser->ring->idx);
 }
 
 static int amdgpu_cs_process_fence_dep(struct amdgpu_cs_parser *p,
@@ -1207,7 +1207,7 @@ static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
-	struct amdgpu_ring *ring = p->job->ring;
+	struct amdgpu_ring *ring = p->ring;
 	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	struct amdgpu_job *job;
 	unsigned i;
@@ -1256,7 +1256,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job->uf_sequence = seq;
 
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
+	amdgpu_ring_priority_get(p->ring, job->base.s_priority);
 
 	trace_amdgpu_cs_ioctl(job);
 	drm_sched_entity_push_job(&job->base, entity);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2720444ff23a..2b2de5f3e6e3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3253,7 +3253,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 
 		kthread_park(ring->sched.thread);
 
-		if (job && job->ring->idx != i)
+		if (job && job->base.sched == &ring->sched)
 			continue;
 
 		drm_sched_hw_job_reset(&ring->sched, &job->base);
@@ -3277,7 +3277,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		 * or all rings (in the case @job is NULL)
 		 * after above amdgpu_reset accomplished
 		 */
-		if ((!job || job->ring->idx == i) && !r)
+		if ((!job || job->base.sched == &ring->sched) && !r)
 			drm_sched_job_recovery(&ring->sched);
 
 		kthread_unpark(ring->sched.thread);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 51ff751e093b..2496f2269bcb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -30,12 +30,12 @@
 
 static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 {
-	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
+	struct amdgpu_job *job = to_amdgpu_job(s_job);
 
 	DRM_ERROR("ring %s timeout, last signaled seq=%u, last emitted seq=%u\n",
-		  job->base.sched->name,
-		  atomic_read(&job->ring->fence_drv.last_seq),
-		  job->ring->fence_drv.sync_seq);
+		  job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
+		  ring->fence_drv.sync_seq);
 
 	amdgpu_device_gpu_recover(job->adev, job, false);
 }
@@ -98,9 +98,10 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 
 static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
 {
-	struct amdgpu_job *job = container_of(s_job, struct amdgpu_job, base);
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
+	struct amdgpu_job *job = to_amdgpu_job(s_job);
 
-	amdgpu_ring_priority_put(job->ring, s_job->s_priority);
+	amdgpu_ring_priority_put(ring, s_job->s_priority);
 	dma_fence_put(job->fence);
 	amdgpu_sync_free(&job->sync);
 	amdgpu_sync_free(&job->sched_sync);
@@ -120,6 +121,7 @@ void amdgpu_job_free(struct amdgpu_job *job)
 int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 		      void *owner, struct dma_fence **f)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(entity->sched);
 	int r;
 
 	if (!f)
@@ -130,10 +132,9 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 		return r;
 
 	job->owner = owner;
-	job->ring = to_amdgpu_ring(entity->sched);
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(job->ring, job->base.s_priority);
+	amdgpu_ring_priority_get(ring, job->base.s_priority);
 	drm_sched_entity_push_job(&job->base, entity);
 
 	return 0;
@@ -142,6 +143,7 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 					       struct drm_sched_entity *s_entity)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->sched);
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
 	struct amdgpu_vm *vm = job->vm;
 	bool explicit = false;
@@ -157,8 +159,6 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 	}
 
 	while (fence == NULL && vm && !job->vmid) {
-		struct amdgpu_ring *ring = job->ring;
-
 		r = amdgpu_vmid_grab(vm, ring, &job->sync,
 				     &job->base.s_fence->finished,
 				     job);
@@ -173,6 +173,7 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 
 static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
 	struct dma_fence *fence = NULL, *finished;
 	struct amdgpu_device *adev;
 	struct amdgpu_job *job;
@@ -196,7 +197,7 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	if (finished->error < 0) {
 		DRM_INFO("Skip scheduling IBs!\n");
 	} else {
-		r = amdgpu_ib_schedule(job->ring, job->num_ibs, job->ibs, job,
+		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, job,
 				       &fence);
 		if (r)
 			DRM_ERROR("Error scheduling IBs (%d)\n", r);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index 39f4230e1d37..c663c1925f91 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -37,7 +37,6 @@ struct amdgpu_job {
 	struct drm_sched_job    base;
 	struct amdgpu_device	*adev;
 	struct amdgpu_vm	*vm;
-	struct amdgpu_ring	*ring;
 	struct amdgpu_sync	sync;
 	struct amdgpu_sync	sched_sync;
 	struct amdgpu_ib	*ibs;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index e96e26d3f3b0..76920035eb22 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -150,10 +150,10 @@ TRACE_EVENT(amdgpu_cs,
 
 	    TP_fast_assign(
 			   __entry->bo_list = p->bo_list;
-			   __entry->ring = p->job->ring->idx;
+			   __entry->ring = p->ring->idx;
 			   __entry->dw = p->job->ibs[i].length_dw;
 			   __entry->fences = amdgpu_fence_count_emitted(
-				p->job->ring);
+				p->ring);
 			   ),
 	    TP_printk("bo_list=%p, ring=%u, dw=%u, fences=%u",
 		      __entry->bo_list, __entry->ring, __entry->dw,
@@ -178,7 +178,7 @@ TRACE_EVENT(amdgpu_cs_ioctl,
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = job->ring->name;
+			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
@@ -203,7 +203,7 @@ TRACE_EVENT(amdgpu_sched_run_job,
 			   __assign_str(timeline, AMDGPU_JOB_GET_TIMELINE_NAME(job))
 			   __entry->context = job->base.s_fence->finished.context;
 			   __entry->seqno = job->base.s_fence->finished.seqno;
-			   __entry->ring_name = job->ring->name;
+			   __entry->ring_name = to_amdgpu_ring(job->base.sched)->name;
 			   __entry->num_ibs = job->num_ibs;
 			   ),
 	    TP_printk("sched_job=%llu, timeline=%s, context=%u, seqno=%u, ring_name=%s, num_ibs=%u",
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 848b2e898818..7738d2b90dae 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -692,11 +692,11 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 			     struct amdgpu_bo *bo, unsigned offset)
 {
 	struct amdgpu_device *adev = ctx->parser->adev;
+	uint32_t ip_instance = ctx->parser->ring->me;
 	int32_t *msg, msg_type, handle;
 	void *ptr;
 	long r;
 	int i;
-	uint32_t ip_instance = ctx->parser->job->ring->me;
 
 	if (offset & 0x3F) {
 		DRM_ERROR("UVD(%d) messages must be 64 byte aligned!\n", ip_instance);
-- 
cgit v1.2.3


From ee913fd9e166384aacc0aa70ffd4e93ca41d54b0 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 13 Jul 2018 16:29:10 +0200
Subject: drm/amdgpu: add amdgpu_job_submit_direct helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make sure that we properly initialize at least the sched member.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 15 +++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h |  4 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 17 ++++++-----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c |  5 +----
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c | 20 ++++++--------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c | 17 ++++-------------
 drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c   | 20 ++++++--------------
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c   | 20 ++++++--------------
 8 files changed, 48 insertions(+), 70 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 2496f2269bcb..0e2b18ccdf2e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -140,6 +140,21 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 	return 0;
 }
 
+int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
+			     struct dma_fence **fence)
+{
+	int r;
+
+	job->base.sched = &ring->sched;
+	r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs, NULL, fence);
+	job->fence = dma_fence_get(*fence);
+	if (r)
+		return r;
+
+	amdgpu_job_free(job);
+	return 0;
+}
+
 static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 					       struct drm_sched_entity *s_entity)
 {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index c663c1925f91..d77fd232f7ce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -33,6 +33,8 @@
 #define to_amdgpu_job(sched_job)		\
 		container_of((sched_job), struct amdgpu_job, base)
 
+struct amdgpu_fence;
+
 struct amdgpu_job {
 	struct drm_sched_job    base;
 	struct amdgpu_device	*adev;
@@ -68,4 +70,6 @@ void amdgpu_job_free_resources(struct amdgpu_job *job);
 void amdgpu_job_free(struct amdgpu_job *job);
 int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 		      void *owner, struct dma_fence **f);
+int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
+			     struct dma_fence **fence);
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 9958e76d1c78..13977ea6a097 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2075,24 +2075,19 @@ int amdgpu_copy_buffer(struct amdgpu_ring *ring, uint64_t src_offset,
 
 	amdgpu_ring_pad_ib(ring, &job->ibs[0]);
 	WARN_ON(job->ibs[0].length_dw > num_dw);
-	if (direct_submit) {
-		r = amdgpu_ib_schedule(ring, job->num_ibs, job->ibs,
-				       NULL, fence);
-		job->fence = dma_fence_get(*fence);
-		if (r)
-			DRM_ERROR("Error scheduling IBs (%d)\n", r);
-		amdgpu_job_free(job);
-	} else {
+	if (direct_submit)
+		r = amdgpu_job_submit_direct(job, ring, fence);
+	else
 		r = amdgpu_job_submit(job, &adev->mman.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, fence);
-		if (r)
-			goto error_free;
-	}
+	if (r)
+		goto error_free;
 
 	return r;
 
 error_free:
 	amdgpu_job_free(job);
+	DRM_ERROR("Error scheduling IBs (%d)\n", r);
 	return r;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 7738d2b90dae..d708970244eb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -1062,12 +1062,9 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		if (r < 0)
 			goto err_free;
 
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
+		r = amdgpu_job_submit_direct(job, ring, &f);
 		if (r)
 			goto err_free;
-
-		amdgpu_job_free(job);
 	} else {
 		r = amdgpu_sync_resv(adev, &job->sync, bo->tbo.resv,
 				     AMDGPU_FENCE_OWNER_UNDEFINED, false);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 7dfb4c4b19c5..86182c966ed6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -469,12 +469,10 @@ int amdgpu_vce_get_create_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -531,19 +529,13 @@ int amdgpu_vce_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
 		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
index 769c6723c9ca..798648a19710 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
@@ -308,13 +308,10 @@ static int amdgpu_vcn_dec_send_msg(struct amdgpu_ring *ring,
 	}
 	ib->length_dw = 16;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err_free;
 
-	amdgpu_job_free(job);
-
 	amdgpu_bo_fence(bo, f, false);
 	amdgpu_bo_unreserve(bo);
 	amdgpu_bo_unref(&bo);
@@ -499,12 +496,10 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -553,12 +548,10 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -666,12 +659,10 @@ static int amdgpu_vcn_jpeg_set_reg(struct amdgpu_ring *ring, uint32_t handle,
 	}
 	ib->length_dw = 16;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index 591d1f211823..b796dc8375cd 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -248,12 +248,10 @@ static int uvd_v6_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -312,19 +310,13 @@ static int uvd_v6_0_enc_get_destroy_msg(struct amdgpu_ring *ring,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
 		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index ceb0a7037897..831bb995b0ed 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -250,12 +250,10 @@ static int uvd_v7_0_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t handle
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-	job->fence = dma_fence_get(f);
+	r = amdgpu_job_submit_direct(job, ring, &f);
 	if (r)
 		goto err;
 
-	amdgpu_job_free(job);
 	if (fence)
 		*fence = dma_fence_get(f);
 	dma_fence_put(f);
@@ -313,19 +311,13 @@ int uvd_v7_0_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t handle,
 	for (i = ib->length_dw; i < ib_size_dw; ++i)
 		ib->ptr[i] = 0x0;
 
-	if (direct) {
-		r = amdgpu_ib_schedule(ring, 1, ib, NULL, &f);
-		job->fence = dma_fence_get(f);
-		if (r)
-			goto err;
-
-		amdgpu_job_free(job);
-	} else {
+	if (direct)
+		r = amdgpu_job_submit_direct(job, ring, &f);
+	else
 		r = amdgpu_job_submit(job, &ring->adev->vce.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
-		if (r)
-			goto err;
-	}
+	if (r)
+		goto err;
 
 	if (fence)
 		*fence = dma_fence_get(f);
-- 
cgit v1.2.3


From 1eb94d441f1c6aff4a594662d11c183520ffe4f3 Mon Sep 17 00:00:00 2001
From: Surendra Mobiya <surendra@chelsio.com>
Date: Mon, 16 Jul 2018 19:40:54 +0530
Subject: cxgb4: collect ASIC LA dumps from ULP TX

Signed-off-by: Surendra Mobiya <surendra@chelsio.com>
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h |  6 +++++
 drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c    | 32 +++++++++++++++++++++--
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c  |  3 ++-
 drivers/net/ethernet/chelsio/cxgb4/t4_regs.h      | 10 +++++++
 4 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
index 3c5057868ab3..aaf7985aef4c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -281,12 +281,18 @@ struct cudbg_tid_data {
 
 #define CUDBG_NUM_ULPTX 11
 #define CUDBG_NUM_ULPTX_READ 512
+#define CUDBG_NUM_ULPTX_ASIC 6
+#define CUDBG_NUM_ULPTX_ASIC_READ 128
+
+#define CUDBG_ULPTX_LA_REV 1
 
 struct cudbg_ulptx_la {
 	u32 rdptr[CUDBG_NUM_ULPTX];
 	u32 wrptr[CUDBG_NUM_ULPTX];
 	u32 rddata[CUDBG_NUM_ULPTX];
 	u32 rd_data[CUDBG_NUM_ULPTX][CUDBG_NUM_ULPTX_READ];
+	u32 rdptr_asic[CUDBG_NUM_ULPTX_ASIC_READ];
+	u32 rddata_asic[CUDBG_NUM_ULPTX_ASIC_READ][CUDBG_NUM_ULPTX_ASIC];
 };
 
 #define CUDBG_CHAC_PBT_ADDR 0x2800
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index 0afcfe99bff3..b1eb843035ee 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -2586,15 +2586,24 @@ int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_buffer temp_buff = { 0 };
 	struct cudbg_ulptx_la *ulptx_la_buff;
+	struct cudbg_ver_hdr *ver_hdr;
 	u32 i, j;
 	int rc;
 
-	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_ulptx_la),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff,
+			    sizeof(struct cudbg_ver_hdr) +
+			    sizeof(struct cudbg_ulptx_la),
 			    &temp_buff);
 	if (rc)
 		return rc;
 
-	ulptx_la_buff = (struct cudbg_ulptx_la *)temp_buff.data;
+	ver_hdr = (struct cudbg_ver_hdr *)temp_buff.data;
+	ver_hdr->signature = CUDBG_ENTITY_SIGNATURE;
+	ver_hdr->revision = CUDBG_ULPTX_LA_REV;
+	ver_hdr->size = sizeof(struct cudbg_ulptx_la);
+
+	ulptx_la_buff = (struct cudbg_ulptx_la *)(temp_buff.data +
+						  sizeof(*ver_hdr));
 	for (i = 0; i < CUDBG_NUM_ULPTX; i++) {
 		ulptx_la_buff->rdptr[i] = t4_read_reg(padap,
 						      ULP_TX_LA_RDPTR_0_A +
@@ -2610,6 +2619,25 @@ int cudbg_collect_ulptx_la(struct cudbg_init *pdbg_init,
 				t4_read_reg(padap,
 					    ULP_TX_LA_RDDATA_0_A + 0x10 * i);
 	}
+
+	for (i = 0; i < CUDBG_NUM_ULPTX_ASIC_READ; i++) {
+		t4_write_reg(padap, ULP_TX_ASIC_DEBUG_CTRL_A, 0x1);
+		ulptx_la_buff->rdptr_asic[i] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_CTRL_A);
+		ulptx_la_buff->rddata_asic[i][0] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_0_A);
+		ulptx_la_buff->rddata_asic[i][1] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_1_A);
+		ulptx_la_buff->rddata_asic[i][2] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_2_A);
+		ulptx_la_buff->rddata_asic[i][3] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_3_A);
+		ulptx_la_buff->rddata_asic[i][4] =
+				t4_read_reg(padap, ULP_TX_ASIC_DEBUG_4_A);
+		ulptx_la_buff->rddata_asic[i][5] =
+				t4_read_reg(padap, PM_RX_BASE_ADDR);
+	}
+
 	return cudbg_write_and_release_buff(pdbg_init, &temp_buff, dbg_buff);
 }
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
index 8d751efcb90e..55b46592af28 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -273,7 +273,8 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 		}
 		break;
 	case CUDBG_ULPTX_LA:
-		len = sizeof(struct cudbg_ulptx_la);
+		len = sizeof(struct cudbg_ver_hdr) +
+		      sizeof(struct cudbg_ulptx_la);
 		break;
 	case CUDBG_UP_CIM_INDIRECT:
 		n = 0;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 6b55aa2eb2a5..446aaff15bae 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1683,6 +1683,16 @@
 #define ULP_TX_LA_RDPTR_0_A 0x8ec0
 #define ULP_TX_LA_RDDATA_0_A 0x8ec4
 #define ULP_TX_LA_WRPTR_0_A 0x8ec8
+#define ULP_TX_ASIC_DEBUG_CTRL_A 0x8f70
+
+#define ULP_TX_ASIC_DEBUG_0_A 0x8f74
+#define ULP_TX_ASIC_DEBUG_1_A 0x8f78
+#define ULP_TX_ASIC_DEBUG_2_A 0x8f7c
+#define ULP_TX_ASIC_DEBUG_3_A 0x8f80
+#define ULP_TX_ASIC_DEBUG_4_A 0x8f84
+
+/* registers for module PM_RX */
+#define PM_RX_BASE_ADDR 0x8fc0
 
 #define PMRX_E_PCMD_PAR_ERROR_S    0
 #define PMRX_E_PCMD_PAR_ERROR_V(x) ((x) << PMRX_E_PCMD_PAR_ERROR_S)
-- 
cgit v1.2.3


From 301f935be9e09a1bf188bd8262a4db0aeeac2b50 Mon Sep 17 00:00:00 2001
From: Toke Høiland-Jørgensen <toke@toke.dk>
Date: Mon, 16 Jul 2018 16:45:09 +0200
Subject: sch_cake: Fix tin order when set through skb->priority
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In diffserv mode, CAKE stores tins in a different order internally than
the logical order exposed to userspace. The order remapping was missing
in the handling of 'tc filter' priority mappings through skb->priority,
resulting in bulk and best effort mappings being reversed relative to
how they are displayed.

Fix this by adding the missing mapping when reading skb->priority.

Fixes: 83f8fd69af4f ("sch_cake: Add DiffServ handling")
Signed-off-by: Toke Høiland-Jørgensen <toke@toke.dk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 30695691e9ff..539c9490c308 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -1546,7 +1546,7 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch,
 	if (TC_H_MAJ(skb->priority) == sch->handle &&
 	    TC_H_MIN(skb->priority) > 0 &&
 	    TC_H_MIN(skb->priority) <= q->tin_cnt) {
-		tin = TC_H_MIN(skb->priority) - 1;
+		tin = q->tin_order[TC_H_MIN(skb->priority) - 1];
 
 		if (q->rate_flags & CAKE_FLAG_WASH)
 			cake_wash_diffserv(skb);
-- 
cgit v1.2.3


From b0294bc1ad19e9d2dd03df5faa1ccc395d4ddd4b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 13 Jul 2018 18:11:39 +0300
Subject: samples: bpf: ensure that we don't load over MAX_PROGS programs

I can't see that we check prog_cnt to ensure it doesn't go over
MAX_PROGS.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/bpf_load.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 89161c9ed466..904e775d1a44 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -107,6 +107,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		return -1;
 	}
 
+	if (prog_cnt == MAX_PROGS)
+		return -1;
+
 	fd = bpf_load_program(prog_type, prog, insns_cnt, license, kern_version,
 			      bpf_log_buf, BPF_LOG_BUF_SIZE);
 	if (fd < 0) {
-- 
cgit v1.2.3


From ee583014a9d8cc48cb4969f87cc02c12b966fabc Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 13 Jul 2018 18:05:37 +0300
Subject: samples/bpf: test_cgrp2_sock2: fix an off by one

"prog_cnt" is the number of elements which are filled out in prog_fd[]
so the test should be >= instead of >.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 samples/bpf/test_cgrp2_sock2.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c
index 3b5be2364975..a9277b118c33 100644
--- a/samples/bpf/test_cgrp2_sock2.c
+++ b/samples/bpf/test_cgrp2_sock2.c
@@ -51,7 +51,7 @@ int main(int argc, char **argv)
 	if (argc > 3)
 		filter_id = atoi(argv[3]);
 
-	if (filter_id > prog_cnt) {
+	if (filter_id >= prog_cnt) {
 		printf("Invalid program id; program not found in file\n");
 		return EXIT_FAILURE;
 	}
-- 
cgit v1.2.3


From 01c097dbfc03ac1357b9c8a1f52fd43d636bc7f7 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Mon, 16 Jul 2018 19:10:36 -0400
Subject: drm/amdgpu: Add kfd2kgd.set_compute_idle interface

This allows automatic switching to the compute power profile depending
on compute activity.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Eric Huang <JinHuiEric.Huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c        | 8 ++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h        | 1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c | 3 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c | 3 ++-
 drivers/gpu/drm/amd/include/kgd_kfd_interface.h   | 5 +++++
 6 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
index 454c22c722c2..f8bbbb3a9504 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -488,6 +488,14 @@ err:
 	return ret;
 }
 
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle)
+{
+	struct amdgpu_device *adev = (struct amdgpu_device *)kgd;
+
+	amdgpu_dpm_switch_power_profile(adev,
+					PP_SMC_POWER_PROFILE_COMPUTE, !idle);
+}
+
 bool amdgpu_amdkfd_is_kfd_vmid(struct amdgpu_device *adev, u32 vmid)
 {
 	if (adev->kfd) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
index 60207ea48bf5..2f379c183ed2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h
@@ -119,6 +119,7 @@ int amdgpu_amdkfd_evict_userptr(struct kgd_mem *mem, struct mm_struct *mm);
 int amdgpu_amdkfd_submit_ib(struct kgd_dev *kgd, enum kgd_engine_type engine,
 				uint32_t vmid, uint64_t gpu_addr,
 				uint32_t *ib_cmd, uint32_t ib_len);
+void amdgpu_amdkfd_set_compute_idle(struct kgd_dev *kgd, bool idle);
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void);
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
index 98eac00e5d32..ea3f698aef5e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v7.c
@@ -219,7 +219,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.submit_ib = amdgpu_amdkfd_submit_ib,
 	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
 	.read_vmid_from_vmfault_reg = read_vmid_from_vmfault_reg,
-	.gpu_recover = amdgpu_amdkfd_gpu_reset
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_7_get_functions(void)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
index ad563b1ee547..f6e53e9352bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v8.c
@@ -177,7 +177,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
 	.get_vm_fault_info = amdgpu_amdkfd_gpuvm_get_vm_fault_info,
-	.gpu_recover = amdgpu_amdkfd_gpu_reset
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_8_0_get_functions(void)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
index 3b07d37b6fd4..8efedfcb9dfc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c
@@ -213,7 +213,8 @@ static const struct kfd2kgd_calls kfd2kgd = {
 	.invalidate_tlbs = invalidate_tlbs,
 	.invalidate_tlbs_vmid = invalidate_tlbs_vmid,
 	.submit_ib = amdgpu_amdkfd_submit_ib,
-	.gpu_recover = amdgpu_amdkfd_gpu_reset
+	.gpu_recover = amdgpu_amdkfd_gpu_reset,
+	.set_compute_idle = amdgpu_amdkfd_set_compute_idle
 };
 
 struct kfd2kgd_calls *amdgpu_amdkfd_gfx_9_0_get_functions(void)
diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
index 7df5e4ab839f..14391b06080c 100644
--- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
+++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
@@ -282,6 +282,9 @@ struct tile_config {
  *
  * @gpu_recover: let kgd reset gpu after kfd detect CPC hang
  *
+ * @set_compute_idle: Indicates that compute is idle on a device. This
+ * can be used to change power profiles depending on compute activity.
+ *
  * This structure contains function pointers to services that the kgd driver
  * provides to amdkfd driver.
  *
@@ -403,6 +406,8 @@ struct kfd2kgd_calls {
 	uint32_t (*read_vmid_from_vmfault_reg)(struct kgd_dev *kgd);
 
 	void (*gpu_recover)(struct kgd_dev *kgd);
+
+	void (*set_compute_idle)(struct kgd_dev *kgd, bool idle);
 };
 
 /**
-- 
cgit v1.2.3


From b5aa3f4aef724e9c0f626dcf69948b22efcc5176 Mon Sep 17 00:00:00 2001
From: Felix Kuehling <Felix.Kuehling@amd.com>
Date: Mon, 16 Jul 2018 19:10:37 -0400
Subject: drm/amdkfd: Call kfd2kgd.set_compute_idle

User mode queue submissions don't go through KFD. Therefore we don't
know exactly when compute is idle or not idle. We use the existence
of user mode queues on a device as an approximation.

register_process is called when the first queue of a process is
created. Conversely unregister_process is called when the last queue
is destroyed. The first process that is registered takes compute
out of idle. The last process that is unregisters sets compute back
to idle.

Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Eric Huang <JinHuiEric.Huang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Oded Gabbay <oded.gabbay@gmail.com>
---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index ace94d6e54cf..ec0d62a16e53 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -782,7 +782,8 @@ static int register_process(struct device_queue_manager *dqm,
 
 	retval = dqm->asic_ops.update_qpd(dqm, qpd);
 
-	dqm->processes_count++;
+	if (dqm->processes_count++ == 0)
+		dqm->dev->kfd2kgd->set_compute_idle(dqm->dev->kgd, false);
 
 	dqm_unlock(dqm);
 
@@ -805,7 +806,9 @@ static int unregister_process(struct device_queue_manager *dqm,
 		if (qpd == cur->qpd) {
 			list_del(&cur->list);
 			kfree(cur);
-			dqm->processes_count--;
+			if (--dqm->processes_count == 0)
+				dqm->dev->kfd2kgd->set_compute_idle(
+					dqm->dev->kgd, true);
 			goto out;
 		}
 	}
-- 
cgit v1.2.3


From b4b5bffd6c19b1005d2e4c90971bf562b8b4a55b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 16 Jul 2018 10:57:15 -0700
Subject: tools: libbpf: remove libelf-getphdrnum feature detection

libbpf does not depend on libelf-getphdrnum feature, don't check it.

$ git grep HAVE_ELF_GETPHDRNUM_SUPPORT
tools/perf/Makefile.config:    CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
tools/perf/util/symbol-elf.c:#ifndef HAVE_ELF_GETPHDRNUM_SUPPORT

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/lib/bpf/Makefile | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 7a8e4c98ef1a..d49902e818b5 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -66,7 +66,7 @@ ifndef VERBOSE
 endif
 
 FEATURE_USER = .libbpf
-FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf reallocarray
+FEATURE_TESTS = libelf libelf-mmap bpf reallocarray
 FEATURE_DISPLAY = libelf bpf
 
 INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf
@@ -116,10 +116,6 @@ ifeq ($(feature-libelf-mmap), 1)
   override CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
 endif
 
-ifeq ($(feature-libelf-getphdrnum), 1)
-  override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT
-endif
-
 ifeq ($(feature-reallocarray), 0)
   override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY
 endif
-- 
cgit v1.2.3


From dc989d2ce2c2bc4b5cdc92a9d2c8a5c857448475 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 16 Jul 2018 10:57:16 -0700
Subject: tools: bpftool: don't pass FEATURES_DUMP to libbpf

bpftool does not export features it probed for, i.e.
FEATURE_DUMP_EXPORT is always empty, so don't try to communicate
the features to libbpf.  It has no effect.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 tools/bpf/bpftool/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index 6c4830e18879..74288a2197ab 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -26,7 +26,7 @@ LIBBPF = $(BPF_PATH)libbpf.a
 BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion)
 
 $(LIBBPF): FORCE
-	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT)
+	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a
 
 $(LIBBPF)-clean:
 	$(call QUIET_CLEAN, libbpf)
-- 
cgit v1.2.3


From ccdb51717ba3bdc9585998e4ffd41d70c04dedea Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Mon, 16 Jul 2018 17:02:04 -0700
Subject: net: Fix GRO_HASH_BUCKETS assertion.

FIELD_SIZEOF() is in bytes, but we want bits.

Fixes: d9f37d01e294 ("net: convert gro_count to bitmask")
Suggested-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index c883b17ee0fe..4f8b92d81d10 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9282,7 +9282,7 @@ static struct hlist_head * __net_init netdev_create_hash(void)
 static int __net_init netdev_init(struct net *net)
 {
 	BUILD_BUG_ON(GRO_HASH_BUCKETS >
-			FIELD_SIZEOF(struct napi_struct, gro_bitmask));
+		     8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask));
 
 	if (net != &init_net)
 		INIT_LIST_HEAD(&net->dev_base_head);
-- 
cgit v1.2.3


From 87dc8a01281a4543ed25c367dace6e0f267e0dd1 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.ibm.com>
Date: Wed, 13 Jun 2018 16:26:23 +0200
Subject: s390/cio: ensure that a chpid is registered only once

Improve locking in chp_new to make sure that we don't register
the same chpid twice. Chpid registration was synchronized via
the machine check handler thread but we also have codepaths to
look for new chpids triggered independent of that thread (during
IPL or resume from hibernate).

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/chp.c | 21 +++++++++++----------
 drivers/s390/cio/css.c |  3 +--
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/s390/cio/chp.c b/drivers/s390/cio/chp.c
index afbdee74147d..51038ec309c1 100644
--- a/drivers/s390/cio/chp.c
+++ b/drivers/s390/cio/chp.c
@@ -471,14 +471,17 @@ int chp_new(struct chp_id chpid)
 {
 	struct channel_subsystem *css = css_by_id(chpid.cssid);
 	struct channel_path *chp;
-	int ret;
+	int ret = 0;
 
+	mutex_lock(&css->mutex);
 	if (chp_is_registered(chpid))
-		return 0;
-	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
-	if (!chp)
-		return -ENOMEM;
+		goto out;
 
+	chp = kzalloc(sizeof(struct channel_path), GFP_KERNEL);
+	if (!chp) {
+		ret = -ENOMEM;
+		goto out;
+	}
 	/* fill in status, etc. */
 	chp->chpid = chpid;
 	chp->state = 1;
@@ -505,21 +508,20 @@ int chp_new(struct chp_id chpid)
 		put_device(&chp->dev);
 		goto out;
 	}
-	mutex_lock(&css->mutex);
+
 	if (css->cm_enabled) {
 		ret = chp_add_cmg_attr(chp);
 		if (ret) {
 			device_unregister(&chp->dev);
-			mutex_unlock(&css->mutex);
 			goto out;
 		}
 	}
 	css->chps[chpid.id] = chp;
-	mutex_unlock(&css->mutex);
 	goto out;
 out_free:
 	kfree(chp);
 out:
+	mutex_unlock(&css->mutex);
 	return ret;
 }
 
@@ -585,8 +587,7 @@ static void chp_process_crw(struct crw *crw0, struct crw *crw1,
 	switch (crw0->erc) {
 	case CRW_ERC_IPARM: /* Path has come. */
 	case CRW_ERC_INIT:
-		if (!chp_is_registered(chpid))
-			chp_new(chpid);
+		chp_new(chpid);
 		chsc_chp_online(chpid);
 		break;
 	case CRW_ERC_PERRI: /* Path has gone. */
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 9263a0fb3858..830a83ec4987 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -244,8 +244,7 @@ static void ssd_register_chpids(struct chsc_ssd_info *ssd)
 	for (i = 0; i < 8; i++) {
 		mask = 0x80 >> i;
 		if (ssd->path_mask & mask)
-			if (!chp_is_registered(ssd->chpid[i]))
-				chp_new(ssd->chpid[i]);
+			chp_new(ssd->chpid[i]);
 	}
 }
 
-- 
cgit v1.2.3


From 71aa11a40d1a1d80196b55d8dd95be2bc4c1649e Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.ibm.com>
Date: Tue, 12 Jun 2018 13:56:21 +0200
Subject: s390/css: start the subchannel evaluation earlier

The css bus code uses 2 initcalls: channel_subsystem_init to
initialize internal data and channel_subsystem_init_sync to
start scanning for devices and wait for it to finish.

The start scanning for devices part is moved to the first
initcall such that more work happens in parallel.

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/css.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index 830a83ec4987..e608e8cad88e 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -1080,6 +1080,11 @@ static int __init channel_subsystem_init(void)
 	if (ret)
 		goto out_wq;
 
+	/* Register subchannels which are already in use. */
+	cio_register_early_subchannels();
+	/* Start initial subchannel evaluation. */
+	css_schedule_eval_all();
+
 	return ret;
 out_wq:
 	destroy_workqueue(cio_work_q);
@@ -1119,10 +1124,6 @@ int css_complete_work(void)
  */
 static int __init channel_subsystem_init_sync(void)
 {
-	/* Register subchannels which are already in use. */
-	cio_register_early_subchannels();
-	/* Start initial subchannel evaluation. */
-	css_schedule_eval_all();
 	css_complete_work();
 	return 0;
 }
-- 
cgit v1.2.3


From 05b217f4c5573f34f6799698f7d4162c702132bc Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.ibm.com>
Date: Mon, 25 Jun 2018 11:23:26 +0200
Subject: s390/css: validate subchannel prior to allocation

In css_alloc_subchannel we allocate the subchannel and do a
validation of the subchannel (to decide if we should look for
devices via this subchannel). On a typical LPAR we find lots
of subchannels to be invalid (because there is no device
attached or the device is blacklisted) leading to lots of
useless kmalloc and kfree calls.

This patch changes the order to only allocate the subchannels
that have been found valid.

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/cio.c | 40 ++++++++++++++--------------------------
 drivers/s390/cio/cio.h |  2 +-
 drivers/s390/cio/css.c | 11 ++++++++---
 3 files changed, 23 insertions(+), 30 deletions(-)

diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 5130d7c67239..4b8f29f83421 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -526,34 +526,19 @@ int cio_disable_subchannel(struct subchannel *sch)
 }
 EXPORT_SYMBOL_GPL(cio_disable_subchannel);
 
-static int cio_check_devno_blacklisted(struct subchannel *sch)
-{
-	if (is_blacklisted(sch->schid.ssid, sch->schib.pmcw.dev)) {
-		/*
-		 * This device must not be known to Linux. So we simply
-		 * say that there is no device and return ENODEV.
-		 */
-		CIO_MSG_EVENT(6, "Blacklisted device detected "
-			      "at devno %04X, subchannel set %x\n",
-			      sch->schib.pmcw.dev, sch->schid.ssid);
-		return -ENODEV;
-	}
-	return 0;
-}
-
 /**
  * cio_validate_subchannel - basic validation of subchannel
- * @sch: subchannel structure to be filled out
  * @schid: subchannel id
+ * @schib: subchannel information block to be filled out
  *
- * Find out subchannel type and initialize struct subchannel.
+ * Check if subchannel is valid and should be used.
  * Return codes:
  *   0 on success
  *   -ENXIO for non-defined subchannels
  *   -ENODEV for invalid subchannels or blacklisted devices
  *   -EIO for subchannels in an invalid subchannel set
  */
-int cio_validate_subchannel(struct subchannel *sch, struct subchannel_id schid)
+int cio_validate_subchannel(struct subchannel_id schid, struct schib *schib)
 {
 	char dbf_txt[15];
 	int ccode;
@@ -568,21 +553,24 @@ int cio_validate_subchannel(struct subchannel *sch, struct subchannel_id schid)
 	 * If stsch gets an exception, it means the current subchannel set
 	 * is not valid.
 	 */
-	ccode = stsch(schid, &sch->schib);
+	ccode = stsch(schid, schib);
 	if (ccode) {
 		err = (ccode == 3) ? -ENXIO : ccode;
 		goto out;
 	}
-	sch->st = sch->schib.pmcw.st;
-	sch->schid = schid;
 
-	switch (sch->st) {
+	switch (schib->pmcw.st) {
 	case SUBCHANNEL_TYPE_IO:
 	case SUBCHANNEL_TYPE_MSG:
-		if (!css_sch_is_valid(&sch->schib))
+		if (!css_sch_is_valid(schib))
 			err = -ENODEV;
-		else
-			err = cio_check_devno_blacklisted(sch);
+		else if (is_blacklisted(schid.ssid, schib->pmcw.dev)) {
+			CIO_MSG_EVENT(6, "Blacklisted device detected "
+				      "at devno %04X, subchannel set %x\n",
+				      schib->pmcw.dev, schid.ssid);
+			err = -ENODEV;
+		} else
+			err = 0;
 		break;
 	default:
 		err = 0;
@@ -591,7 +579,7 @@ int cio_validate_subchannel(struct subchannel *sch, struct subchannel_id schid)
 		goto out;
 
 	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
-		      sch->schid.ssid, sch->schid.sch_no, sch->st);
+		      schid.ssid, schid.sch_no, schib->pmcw.st);
 out:
 	return err;
 }
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 94cd813bdcfe..234aa068dd8f 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -119,7 +119,7 @@ DECLARE_PER_CPU(struct irb, cio_irb);
 
 #define to_subchannel(n) container_of(n, struct subchannel, dev)
 
-extern int cio_validate_subchannel (struct subchannel *, struct subchannel_id);
+extern int cio_validate_subchannel(struct subchannel_id, struct schib *);
 extern int cio_enable_subchannel(struct subchannel *, u32);
 extern int cio_disable_subchannel (struct subchannel *);
 extern int cio_cancel (struct subchannel *);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index e608e8cad88e..e4d6537cdd87 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -171,15 +171,20 @@ static void css_subchannel_release(struct device *dev)
 struct subchannel *css_alloc_subchannel(struct subchannel_id schid)
 {
 	struct subchannel *sch;
+	struct schib schib;
 	int ret;
 
+	ret = cio_validate_subchannel(schid, &schib);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
 	sch = kzalloc(sizeof(*sch), GFP_KERNEL | GFP_DMA);
 	if (!sch)
 		return ERR_PTR(-ENOMEM);
 
-	ret = cio_validate_subchannel(sch, schid);
-	if (ret < 0)
-		goto err;
+	sch->schid = schid;
+	sch->schib = schib;
+	sch->st = schib.pmcw.st;
 
 	ret = css_sch_create_locks(sch);
 	if (ret)
-- 
cgit v1.2.3


From d4f5d79e97ca6e903700d3d9455afb5694cc4833 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.ibm.com>
Date: Tue, 26 Jun 2018 15:09:32 +0200
Subject: s390/css: reduce stsch calls

Both css_evaluate_new_subchannel and cio_validate_subchannel used
stsch and css_sch_is_valid to check for a valid device.

Reduce stsch calls during subchannel evaluation by re-using schib
data. Also the type/devno valid information is only checked once.

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/cio.c | 65 +++++-------------------------------------------
 drivers/s390/cio/cio.h |  1 -
 drivers/s390/cio/css.c | 67 ++++++++++++++++++++++++++++++++++++--------------
 drivers/s390/cio/css.h |  3 ++-
 4 files changed, 57 insertions(+), 79 deletions(-)

diff --git a/drivers/s390/cio/cio.c b/drivers/s390/cio/cio.c
index 4b8f29f83421..de744ca158fd 100644
--- a/drivers/s390/cio/cio.c
+++ b/drivers/s390/cio/cio.c
@@ -526,64 +526,6 @@ int cio_disable_subchannel(struct subchannel *sch)
 }
 EXPORT_SYMBOL_GPL(cio_disable_subchannel);
 
-/**
- * cio_validate_subchannel - basic validation of subchannel
- * @schid: subchannel id
- * @schib: subchannel information block to be filled out
- *
- * Check if subchannel is valid and should be used.
- * Return codes:
- *   0 on success
- *   -ENXIO for non-defined subchannels
- *   -ENODEV for invalid subchannels or blacklisted devices
- *   -EIO for subchannels in an invalid subchannel set
- */
-int cio_validate_subchannel(struct subchannel_id schid, struct schib *schib)
-{
-	char dbf_txt[15];
-	int ccode;
-	int err;
-
-	sprintf(dbf_txt, "valsch%x", schid.sch_no);
-	CIO_TRACE_EVENT(4, dbf_txt);
-
-	/*
-	 * The first subchannel that is not-operational (ccode==3)
-	 * indicates that there aren't any more devices available.
-	 * If stsch gets an exception, it means the current subchannel set
-	 * is not valid.
-	 */
-	ccode = stsch(schid, schib);
-	if (ccode) {
-		err = (ccode == 3) ? -ENXIO : ccode;
-		goto out;
-	}
-
-	switch (schib->pmcw.st) {
-	case SUBCHANNEL_TYPE_IO:
-	case SUBCHANNEL_TYPE_MSG:
-		if (!css_sch_is_valid(schib))
-			err = -ENODEV;
-		else if (is_blacklisted(schid.ssid, schib->pmcw.dev)) {
-			CIO_MSG_EVENT(6, "Blacklisted device detected "
-				      "at devno %04X, subchannel set %x\n",
-				      schib->pmcw.dev, schid.ssid);
-			err = -ENODEV;
-		} else
-			err = 0;
-		break;
-	default:
-		err = 0;
-	}
-	if (err)
-		goto out;
-
-	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
-		      schid.ssid, schid.sch_no, schib->pmcw.st);
-out:
-	return err;
-}
-
 /*
  * do_cio_interrupt() handles all normal I/O device IRQ's
  */
@@ -707,6 +649,7 @@ struct subchannel *cio_probe_console(void)
 {
 	struct subchannel_id schid;
 	struct subchannel *sch;
+	struct schib schib;
 	int sch_no, ret;
 
 	sch_no = cio_get_console_sch_no();
@@ -716,7 +659,11 @@ struct subchannel *cio_probe_console(void)
 	}
 	init_subchannel_id(&schid);
 	schid.sch_no = sch_no;
-	sch = css_alloc_subchannel(schid);
+	ret = stsch(schid, &schib);
+	if (ret)
+		return ERR_PTR(-ENODEV);
+
+	sch = css_alloc_subchannel(schid, &schib);
 	if (IS_ERR(sch))
 		return sch;
 
diff --git a/drivers/s390/cio/cio.h b/drivers/s390/cio/cio.h
index 234aa068dd8f..9811fd8a0c73 100644
--- a/drivers/s390/cio/cio.h
+++ b/drivers/s390/cio/cio.h
@@ -119,7 +119,6 @@ DECLARE_PER_CPU(struct irb, cio_irb);
 
 #define to_subchannel(n) container_of(n, struct subchannel, dev)
 
-extern int cio_validate_subchannel(struct subchannel_id, struct schib *);
 extern int cio_enable_subchannel(struct subchannel *, u32);
 extern int cio_disable_subchannel (struct subchannel *);
 extern int cio_cancel (struct subchannel *);
diff --git a/drivers/s390/cio/css.c b/drivers/s390/cio/css.c
index e4d6537cdd87..aea502922646 100644
--- a/drivers/s390/cio/css.c
+++ b/drivers/s390/cio/css.c
@@ -25,6 +25,7 @@
 
 #include "css.h"
 #include "cio.h"
+#include "blacklist.h"
 #include "cio_debug.h"
 #include "ioasm.h"
 #include "chsc.h"
@@ -168,13 +169,43 @@ static void css_subchannel_release(struct device *dev)
 	kfree(sch);
 }
 
-struct subchannel *css_alloc_subchannel(struct subchannel_id schid)
+static int css_validate_subchannel(struct subchannel_id schid,
+				   struct schib *schib)
+{
+	int err;
+
+	switch (schib->pmcw.st) {
+	case SUBCHANNEL_TYPE_IO:
+	case SUBCHANNEL_TYPE_MSG:
+		if (!css_sch_is_valid(schib))
+			err = -ENODEV;
+		else if (is_blacklisted(schid.ssid, schib->pmcw.dev)) {
+			CIO_MSG_EVENT(6, "Blacklisted device detected "
+				      "at devno %04X, subchannel set %x\n",
+				      schib->pmcw.dev, schid.ssid);
+			err = -ENODEV;
+		} else
+			err = 0;
+		break;
+	default:
+		err = 0;
+	}
+	if (err)
+		goto out;
+
+	CIO_MSG_EVENT(4, "Subchannel 0.%x.%04x reports subchannel type %04X\n",
+		      schid.ssid, schid.sch_no, schib->pmcw.st);
+out:
+	return err;
+}
+
+struct subchannel *css_alloc_subchannel(struct subchannel_id schid,
+					struct schib *schib)
 {
 	struct subchannel *sch;
-	struct schib schib;
 	int ret;
 
-	ret = cio_validate_subchannel(schid, &schib);
+	ret = css_validate_subchannel(schid, schib);
 	if (ret < 0)
 		return ERR_PTR(ret);
 
@@ -183,8 +214,8 @@ struct subchannel *css_alloc_subchannel(struct subchannel_id schid)
 		return ERR_PTR(-ENOMEM);
 
 	sch->schid = schid;
-	sch->schib = schib;
-	sch->st = schib.pmcw.st;
+	sch->schib = *schib;
+	sch->st = schib->pmcw.st;
 
 	ret = css_sch_create_locks(sch);
 	if (ret)
@@ -386,12 +417,12 @@ int css_register_subchannel(struct subchannel *sch)
 	return ret;
 }
 
-static int css_probe_device(struct subchannel_id schid)
+static int css_probe_device(struct subchannel_id schid, struct schib *schib)
 {
 	struct subchannel *sch;
 	int ret;
 
-	sch = css_alloc_subchannel(schid);
+	sch = css_alloc_subchannel(schid, schib);
 	if (IS_ERR(sch))
 		return PTR_ERR(sch);
 
@@ -440,23 +471,23 @@ EXPORT_SYMBOL_GPL(css_sch_is_valid);
 static int css_evaluate_new_subchannel(struct subchannel_id schid, int slow)
 {
 	struct schib schib;
+	int ccode;
 
 	if (!slow) {
 		/* Will be done on the slow path. */
 		return -EAGAIN;
 	}
-	if (stsch(schid, &schib)) {
-		/* Subchannel is not provided. */
-		return -ENXIO;
-	}
-	if (!css_sch_is_valid(&schib)) {
-		/* Unusable - ignore. */
-		return 0;
-	}
-	CIO_MSG_EVENT(4, "event: sch 0.%x.%04x, new\n", schid.ssid,
-		      schid.sch_no);
+	/*
+	 * The first subchannel that is not-operational (ccode==3)
+	 * indicates that there aren't any more devices available.
+	 * If stsch gets an exception, it means the current subchannel set
+	 * is not valid.
+	 */
+	ccode = stsch(schid, &schib);
+	if (ccode)
+		return (ccode == 3) ? -ENXIO : ccode;
 
-	return css_probe_device(schid);
+	return css_probe_device(schid, &schib);
 }
 
 static int css_evaluate_known_subchannel(struct subchannel *sch, int slow)
diff --git a/drivers/s390/cio/css.h b/drivers/s390/cio/css.h
index 30357cbf350a..8d832900a63d 100644
--- a/drivers/s390/cio/css.h
+++ b/drivers/s390/cio/css.h
@@ -103,7 +103,8 @@ extern void css_driver_unregister(struct css_driver *);
 
 extern void css_sch_device_unregister(struct subchannel *);
 extern int css_register_subchannel(struct subchannel *);
-extern struct subchannel *css_alloc_subchannel(struct subchannel_id);
+extern struct subchannel *css_alloc_subchannel(struct subchannel_id,
+					       struct schib *schib);
 extern struct subchannel *get_subchannel_by_schid(struct subchannel_id);
 extern int css_init_done;
 extern int max_ssid;
-- 
cgit v1.2.3


From ccaabeea02026e1fbf9274800e43d9135914cd72 Mon Sep 17 00:00:00 2001
From: Sebastian Ott <sebott@linux.ibm.com>
Date: Mon, 25 Jun 2018 14:25:59 +0200
Subject: s390/chsc: fix packed-not-aligned warnings

Remove attribute packed where possible failing this add proper alignment
information to fix warnings like the one below:

drivers/s390/cio/chsc.c: In function 'chsc_siosl':
drivers/s390/cio/chsc.c:1287:2: warning: alignment 1 of 'struct <anonymous>' is less than 4 [-Wpacked-not-aligned]
  } __attribute__ ((packed)) *siosl_area;

Note: this patch should be a nop since non of these structs use auto
storage but allocated pages. However there are changes to the generated
code because of additional padding at the end of some of the structs due
to alignment when memset(foo, 0, sizeof(*foo)) is used.

Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/uapi/asm/chsc.h | 10 +++++-----
 drivers/s390/cio/chsc.c           | 18 +++++++++---------
 drivers/s390/cio/chsc.h           | 18 +++++++++---------
 3 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/arch/s390/include/uapi/asm/chsc.h b/arch/s390/include/uapi/asm/chsc.h
index dc329aa03f76..83a574e95b3a 100644
--- a/arch/s390/include/uapi/asm/chsc.h
+++ b/arch/s390/include/uapi/asm/chsc.h
@@ -23,29 +23,29 @@ struct chsc_async_header {
 	__u32 key : 4;
 	__u32 : 28;
 	struct subchannel_id sid;
-} __attribute__ ((packed));
+};
 
 struct chsc_async_area {
 	struct chsc_async_header header;
 	__u8 data[CHSC_SIZE - sizeof(struct chsc_async_header)];
-} __attribute__ ((packed));
+};
 
 struct chsc_header {
 	__u16 length;
 	__u16 code;
-} __attribute__ ((packed));
+};
 
 struct chsc_sync_area {
 	struct chsc_header header;
 	__u8 data[CHSC_SIZE - sizeof(struct chsc_header)];
-} __attribute__ ((packed));
+};
 
 struct chsc_response_struct {
 	__u16 length;
 	__u16 code;
 	__u32 parms;
 	__u8 data[CHSC_SIZE - 2 * sizeof(__u16) - sizeof(__u32)];
-} __attribute__ ((packed));
+};
 
 struct chsc_chp_cd {
 	struct chp_id chpid;
diff --git a/drivers/s390/cio/chsc.c b/drivers/s390/cio/chsc.c
index 9029804dcd22..a0baee25134c 100644
--- a/drivers/s390/cio/chsc.c
+++ b/drivers/s390/cio/chsc.c
@@ -91,7 +91,7 @@ struct chsc_ssd_area {
 	u16 sch;	  /* subchannel */
 	u8 chpid[8];	  /* chpids 0-7 */
 	u16 fla[8];	  /* full link addresses 0-7 */
-} __attribute__ ((packed));
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_get_ssd_info(struct subchannel_id schid, struct chsc_ssd_info *ssd)
 {
@@ -319,7 +319,7 @@ struct chsc_sei {
 		struct chsc_sei_nt2_area nt2_area;
 		u8 nt_area[PAGE_SIZE - 24];
 	} u;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 /*
  * Node Descriptor as defined in SA22-7204, "Common I/O-Device Commands"
@@ -841,7 +841,7 @@ int __chsc_do_secm(struct channel_subsystem *css, int enable)
 		u32 : 4;
 		u32 fmt : 4;
 		u32 : 16;
-	} __attribute__ ((packed)) *secm_area;
+	} *secm_area;
 	unsigned long flags;
 	int ret, ccode;
 
@@ -1014,7 +1014,7 @@ int chsc_get_channel_measurement_chars(struct channel_path *chp)
 		u32 cmg : 8;
 		u32 zeroes3;
 		u32 data[NR_MEASUREMENT_CHARS];
-	} __attribute__ ((packed)) *scmc_area;
+	} *scmc_area;
 
 	chp->shared = -1;
 	chp->cmg = -1;
@@ -1142,7 +1142,7 @@ int __init chsc_get_cssid(int idx)
 			u8 cssid;
 			u32 : 24;
 		} list[0];
-	} __packed *sdcal_area;
+	} *sdcal_area;
 	int ret;
 
 	spin_lock_irq(&chsc_page_lock);
@@ -1192,7 +1192,7 @@ chsc_determine_css_characteristics(void)
 		u32 reserved4;
 		u32 general_char[510];
 		u32 chsc_char[508];
-	} __attribute__ ((packed)) *scsc_area;
+	} *scsc_area;
 
 	spin_lock_irqsave(&chsc_page_lock, flags);
 	memset(chsc_page, 0, PAGE_SIZE);
@@ -1236,7 +1236,7 @@ int chsc_sstpc(void *page, unsigned int op, u16 ctrl, u64 *clock_delta)
 		unsigned int rsvd3[3];
 		u64 clock_delta;
 		unsigned int rsvd4[2];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1261,7 +1261,7 @@ int chsc_sstpi(void *page, void *result, size_t size)
 		unsigned int rsvd0[3];
 		struct chsc_header response;
 		char data[];
-	} __attribute__ ((packed)) *rr;
+	} *rr;
 	int rc;
 
 	memset(page, 0, PAGE_SIZE);
@@ -1284,7 +1284,7 @@ int chsc_siosl(struct subchannel_id schid)
 		u32 word3;
 		struct chsc_header response;
 		u32 word[11];
-	} __attribute__ ((packed)) *siosl_area;
+	} *siosl_area;
 	unsigned long flags;
 	int ccode;
 	int rc;
diff --git a/drivers/s390/cio/chsc.h b/drivers/s390/cio/chsc.h
index 5c9f0dd33f4e..78aba8d94eec 100644
--- a/drivers/s390/cio/chsc.h
+++ b/drivers/s390/cio/chsc.h
@@ -15,12 +15,12 @@
 #define NR_MEASUREMENT_CHARS 5
 struct cmg_chars {
 	u32 values[NR_MEASUREMENT_CHARS];
-} __attribute__ ((packed));
+};
 
 #define NR_MEASUREMENT_ENTRIES 8
 struct cmg_entry {
 	u32 values[NR_MEASUREMENT_ENTRIES];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt1 {
 	u8 flags;
@@ -38,7 +38,7 @@ struct channel_path_desc_fmt1 {
 	u8 s:1;
 	u8 f:1;
 	u32 zeros[2];
-} __attribute__ ((packed));
+};
 
 struct channel_path_desc_fmt3 {
 	struct channel_path_desc_fmt1 fmt1_desc;
@@ -59,7 +59,7 @@ struct css_chsc_char {
 	u32:7;
 	u32 pnso:1; /* bit 116 */
 	u32:11;
-}__attribute__((packed));
+} __packed;
 
 extern struct css_chsc_char css_chsc_characteristics;
 
@@ -82,7 +82,7 @@ struct chsc_ssqd_area {
 	struct chsc_header response;
 	u32:32;
 	struct qdio_ssqd_desc qdio_ssqd;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scssc_area {
 	struct chsc_header request;
@@ -102,7 +102,7 @@ struct chsc_scssc_area {
 	u32 reserved[1004];
 	struct chsc_header response;
 	u32:32;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_scpd {
 	struct chsc_header request;
@@ -120,7 +120,7 @@ struct chsc_scpd {
 	struct chsc_header response;
 	u32:32;
 	u8 data[0];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 struct chsc_sda_area {
 	struct chsc_header request;
@@ -199,7 +199,7 @@ struct chsc_scm_info {
 	u32 reserved2[10];
 	u64 restok;
 	struct sale scmal[248];
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_scm_info(struct chsc_scm_info *scm_area, u64 token);
 
@@ -243,7 +243,7 @@ struct chsc_pnso_area {
 		struct qdio_brinfo_entry_l3_ipv4 l3_ipv4[0];
 		struct qdio_brinfo_entry_l2	 l2[0];
 	} entries;
-} __packed;
+} __packed __aligned(PAGE_SIZE);
 
 int chsc_pnso_brinfo(struct subchannel_id schid,
 		struct chsc_pnso_area *brinfo_area,
-- 
cgit v1.2.3


From fcaccc829382aafaab640933e526b786791ae8e7 Mon Sep 17 00:00:00 2001
From: Rick Farrington <ricardo.farrington@cavium.com>
Date: Mon, 16 Jul 2018 18:06:07 -0700
Subject: liquidio: correct error msg text when removing VLAN ID

Signed-off-by: Rick Farrington <ricardo.farrington@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/lio_main.c    | 2 +-
 drivers/net/ethernet/cavium/liquidio/lio_vf_main.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index a60d5afeac28..4edb1584b32f 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2628,7 +2628,7 @@ static int liquidio_vlan_rx_kill_vid(struct net_device *netdev,
 
 	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
-		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+		dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
 			ret);
 	}
 	return ret;
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
index 7fa0212873ac..b77835724dc8 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c
@@ -1693,7 +1693,7 @@ liquidio_vlan_rx_kill_vid(struct net_device *netdev,
 
 	ret = octnet_send_nic_ctrl_pkt(lio->oct_dev, &nctrl);
 	if (ret < 0) {
-		dev_err(&oct->pci_dev->dev, "Add VLAN filter failed in core (ret: 0x%x)\n",
+		dev_err(&oct->pci_dev->dev, "Del VLAN filter failed in core (ret: 0x%x)\n",
 			ret);
 	}
 	return ret;
-- 
cgit v1.2.3


From 61f0d55569463a1af897117ff47d202b0ccb2e24 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 16 Jul 2018 23:25:07 +0800
Subject: efi/esrt: Only call efi_mem_reserve() for boot services memory

The following commit:

  7e1550b8f208 ("efi: Drop type and attribute checks in efi_mem_desc_lookup()")

refactored the implementation of efi_mem_desc_lookup() so that the type
check is moved to the callers, one of which is the x86 version of
efi_arch_mem_reserve(), where we added a modified check that only takes
EFI_BOOT_SERVICES_DATA regions into account.

This is reasonable, since it is the only memory type that requires this,
but doing so uncovered some unexpected behavior in the ESRT code, which
permits the ESRT table to reside in other types of memory than what the
UEFI spec mandates (i.e., EFI_BOOT_SERVICES_DATA), and unconditionally
calls efi_mem_reserve() on the region in question. This may result in
errors such as

  esrt: Reserving ESRT space from 0x000000009c810318 to 0x000000009c810350.
  efi: Failed to lookup EFI memory descriptor for 0x000000009c810318

when the ESRT table is not in EFI_BOOT_SERVICES_DATA memory, but we try
to reserve it nonetheless.

So make the call to efi_mem_reserve() conditional on the memory type.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Jones <pjones@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/esrt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/esrt.c b/drivers/firmware/efi/esrt.c
index 375a77c1c6e5..5d06bd247d07 100644
--- a/drivers/firmware/efi/esrt.c
+++ b/drivers/firmware/efi/esrt.c
@@ -329,7 +329,8 @@ void __init efi_esrt_init(void)
 
 	end = esrt_data + size;
 	pr_info("Reserving ESRT space from %pa to %pa.\n", &esrt_data, &end);
-	efi_mem_reserve(esrt_data, esrt_data_size);
+	if (md.type == EFI_BOOT_SERVICES_DATA)
+		efi_mem_reserve(esrt_data, esrt_data_size);
 
 	pr_debug("esrt-init: loaded.\n");
 }
-- 
cgit v1.2.3


From b464818978d45cd4d78c8f13207891142c68bea9 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 16 Jul 2018 11:05:52 -0700
Subject: tools/memory-model: Add litmus test for full multicopy atomicity

This commit adds a litmus test suggested by Alan Stern that is forbidden
on fully multicopy atomic systems, but allowed on other-multicopy and
on non-multicopy atomic systems.  For reference, s390 is fully multicopy
atomic, x86 and ARMv8 are other-multicopy atomic, and ARMv7 and powerpc
are non-multicopy atomic.

Suggested-by: Alan Stern <stern@rowland.harvard.edu>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Acked-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-1-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/litmus-tests/README             |  9 ++++++
 .../litmus-tests/SB+rfionceonce-poonceonces.litmus | 32 ++++++++++++++++++++++
 2 files changed, 41 insertions(+)
 create mode 100644 tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus

diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 17eb9a8c222d..00140aaf58b7 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -111,6 +111,15 @@ SB+mbonceonces.litmus
 SB+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
+SB+rfionceonce-poonceonces.litmus
+	This litmus test demonstrates that LKMM is not fully multicopy
+	atomic.  (Neither is it other multicopy atomic.)  This litmus test
+	also demonstrates the "locations" debugging aid, which designates
+	additional registers and locations to be printed out in the dump
+	of final states in the herd7 output.  Without the "locations"
+	statement, only those registers and locations mentioned in the
+	"exists" clause will be printed.
+
 S+poonceonces.litmus
 	As below, but without the smp_wmb() and acquire load.
 
diff --git a/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
new file mode 100644
index 000000000000..04a16603660b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+rfionceonce-poonceonces.litmus
@@ -0,0 +1,32 @@
+C SB+rfionceonce-poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates that LKMM is not fully multicopy atomic.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	int r1;
+	int r2;
+
+	WRITE_ONCE(*x, 1);
+	r1 = READ_ONCE(*x);
+	r2 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+	int r3;
+	int r4;
+
+	WRITE_ONCE(*y, 1);
+	r3 = READ_ONCE(*y);
+	r4 = READ_ONCE(*x);
+}
+
+locations [0:r1; 1:r3; x; y] (* Debug aid: Print things not in "exists". *)
+exists (0:r2=0 /\ 1:r4=0)
-- 
cgit v1.2.3


From acb6c96c52ac0da6bb464173ad2cf5ada9049ad4 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 16 Jul 2018 11:05:53 -0700
Subject: tools/memory-model: Fix ISA2+pooncelock+pooncelock+pombonce name

The names on the first line of the litmus tests are arbitrary,
but the convention is that they be the filename without the trailing
".litmus".  This commit therefore removes the stray trailing ".litmus"
from ISA2+pooncelock+pooncelock+pombonce.litmus's name.

Reported-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-2-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 .../litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus             | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
index 7a39a0aaa976..0f749e419b34 100644
--- a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -1,4 +1,4 @@
-C ISA2+pooncelock+pooncelock+pombonce.litmus
+C ISA2+pooncelock+pooncelock+pombonce
 
 (*
  * Result: Sometimes
-- 
cgit v1.2.3


From 2caf412dc46149b8714e0f52c8337e8eda035a83 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@sifive.com>
Date: Mon, 16 Jul 2018 11:05:54 -0700
Subject: MAINTAINERS: Add Daniel Lustig as an LKMM reviewer

Dan runs the RISC-V memory model working group.  I've been forwarding
him LKMM emails that end up in my inbox, but I'm far from an expert in
this stuff.  He requested to be added as a reviewer, which seems sane to
me as it'll take a human out of the loop.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Daniel Lustig <dlustig@nvidia.com>
Acked-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-3-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 192d7f73fd01..eb427596f3e0 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8316,6 +8316,7 @@ M:	Jade Alglave <j.alglave@ucl.ac.uk>
 M:	Luc Maranget <luc.maranget@inria.fr>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 R:	Akira Yokosawa <akiyks@gmail.com>
+R:	Daniel Lustig <dlustig@nvidia.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
-- 
cgit v1.2.3


From 68ec3444b32158541f4bbd47ed9345634c56399d Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj38.park@gmail.com>
Date: Mon, 16 Jul 2018 11:05:55 -0700
Subject: locking/memory-barriers.txt/kokr: Update Korean translation to fix
 broken DMA vs. MMIO ordering example

Translate this commit to Korean:

  5846581e3563 ("locking/memory-barriers.txt: Fix broken DMA vs. MMIO ordering example")

[ paulmck: Updated based on feedback from Byungchul Park. ]
Signed-off-by: SeongJae Park <sj38.park@gmail.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Byungchul Park <byungchul.park@lge.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-4-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 .../translations/ko_KR/memory-barriers.txt         | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/Documentation/translations/ko_KR/memory-barriers.txt b/Documentation/translations/ko_KR/memory-barriers.txt
index 921739d00f69..7f01fb1c1084 100644
--- a/Documentation/translations/ko_KR/memory-barriers.txt
+++ b/Documentation/translations/ko_KR/memory-barriers.txt
@@ -1891,22 +1891,22 @@ Mandatory 배리어들은 SMP 시스템에서도 UP 시스템에서도 SMP 효
 		/* 소유권을 수정 */
 		desc->status = DEVICE_OWN;
 
-		/* MMIO 를 통해 디바이스에 공지를 하기 전에 메모리를 동기화 */
-		wmb();
-
 		/* 업데이트된 디스크립터의 디바이스에 공지 */
 		writel(DESC_NOTIFY, doorbell);
 	}
 
      dma_rmb() 는 디스크립터로부터 데이터를 읽어오기 전에 디바이스가 소유권을
-     내놓았음을 보장하게 하고, dma_wmb() 는 디바이스가 자신이 소유권을 다시
-     가졌음을 보기 전에 디스크립터에 데이터가 쓰였음을 보장합니다.  wmb() 는
-     캐시 일관성이 없는 (cache incoherent) MMIO 영역에 쓰기를 시도하기 전에
-     캐시 일관성이 있는 메모리 (cache coherent memory) 쓰기가 완료되었음을
-     보장해주기 위해 필요합니다.
-
-     consistent memory 에 대한 자세한 내용을 위해선 Documentation/DMA-API.txt
-     문서를 참고하세요.
+     내려놓았을 것을 보장하고, dma_wmb() 는 디바이스가 자신이 소유권을 다시
+     가졌음을 보기 전에 디스크립터에 데이터가 쓰였을 것을 보장합니다.  참고로,
+     writel() 을 사용하면 캐시 일관성이 있는 메모리 (cache coherent memory)
+     쓰기가 MMIO 영역에의 쓰기 전에 완료되었을 것을 보장하므로 writel() 앞에
+     wmb() 를 실행할 필요가 없음을 알아두시기 바랍니다.  writel() 보다 비용이
+     저렴한 writel_relaxed() 는 이런 보장을 제공하지 않으므로 여기선 사용되지
+     않아야 합니다.
+
+     writel_relaxed() 와 같은 완화된 I/O 접근자들에 대한 자세한 내용을 위해서는
+     "커널 I/O 배리어의 효과" 섹션을, consistent memory 에 대한 자세한 내용을
+     위해선 Documentation/DMA-API.txt 문서를 참고하세요.
 
 
 MMIO 쓰기 배리어
-- 
cgit v1.2.3


From 5bde06b63af2af8c2326270aae041067eef89245 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 16 Jul 2018 11:05:56 -0700
Subject: tools/memory-model: Remove ACCESS_ONCE() from recipes

Since commit:

  b899a850431e2dd0 ("compiler.h: Remove ACCESS_ONCE()")

... there has been no definition of ACCESS_ONCE() in the kernel tree,
and it has been necessary to use READ_ONCE() or WRITE_ONCE() instead.

Let's update the exmaples in recipes.txt likewise for consistency, using
READ_ONCE() for reads.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: parri.andrea@gmail.com
Link: http://lkml.kernel.org/r/20180716180605.16115-5-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/Documentation/recipes.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
index ee4309a87fc4..1fea8ef2b184 100644
--- a/tools/memory-model/Documentation/recipes.txt
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -322,9 +322,9 @@ the following write-side code fragment:
 And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains
 the corresponding read-side code fragment:
 
-	cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+	cur_cycle = READ_ONCE(log->l_curr_cycle);
 	smp_rmb();
-	cur_block = ACCESS_ONCE(log->l_curr_block);
+	cur_block = READ_ONCE(log->l_curr_block);
 
 Alternatively, consider the following comment in function
 perf_output_put_handle() in kernel/events/ring_buffer.c:
-- 
cgit v1.2.3


From af41db5ef7c7cf0fee860f65cab59d0d188098d2 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 16 Jul 2018 11:05:57 -0700
Subject: tools/memory-model: Remove ACCESS_ONCE() from model

Since commit:

  b899a850431e2dd0 ("compiler.h: Remove ACCESS_ONCE()")

... there has been no definition of ACCESS_ONCE() in the kernel tree,
and it has been necessary to use READ_ONCE() or WRITE_ONCE() instead.

Correspondingly, let's remove ACCESS_ONCE() from the kernel memory
model.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: parri.andrea@gmail.com
Link: http://lkml.kernel.org/r/20180716180605.16115-6-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/linux-kernel.bell | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
index 64f5740e0e75..b84fb2f67109 100644
--- a/tools/memory-model/linux-kernel.bell
+++ b/tools/memory-model/linux-kernel.bell
@@ -13,7 +13,7 @@
 
 "Linux-kernel memory consistency model"
 
-enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) ||
+enum Accesses = 'once (*READ_ONCE,WRITE_ONCE*) ||
 		'release (*smp_store_release*) ||
 		'acquire (*smp_load_acquire*) ||
 		'noreturn (* R of non-return RMW *)
-- 
cgit v1.2.3


From 24675bb554f9e3d0e2bd61f6a7d8da50d224c8ff Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 16 Jul 2018 11:05:58 -0700
Subject: tools/memory-model: Make scripts executable

This commit makes the scripts executable to avoid the need for everyone
to do so manually in their archive.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Akira Yokosawa <akiyks@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-7-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/scripts/checkalllitmus.sh | 2 +-
 tools/memory-model/scripts/checklitmus.sh    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
 mode change 100644 => 100755 tools/memory-model/scripts/checkalllitmus.sh
 mode change 100644 => 100755 tools/memory-model/scripts/checklitmus.sh

diff --git a/tools/memory-model/scripts/checkalllitmus.sh b/tools/memory-model/scripts/checkalllitmus.sh
old mode 100644
new mode 100755
index af0aa15ab84e..ca528f9a24d4
--- a/tools/memory-model/scripts/checkalllitmus.sh
+++ b/tools/memory-model/scripts/checkalllitmus.sh
@@ -9,7 +9,7 @@
 # appended.
 #
 # Usage:
-#	sh checkalllitmus.sh [ directory ]
+#	checkalllitmus.sh [ directory ]
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, whose default is defined by the checklitmus.sh script.
diff --git a/tools/memory-model/scripts/checklitmus.sh b/tools/memory-model/scripts/checklitmus.sh
old mode 100644
new mode 100755
index e2e477472844..bf12a75c0719
--- a/tools/memory-model/scripts/checklitmus.sh
+++ b/tools/memory-model/scripts/checklitmus.sh
@@ -8,7 +8,7 @@
 # with ".out" appended.
 #
 # Usage:
-#	sh checklitmus.sh file.litmus
+#	checklitmus.sh file.litmus
 #
 # The LINUX_HERD_OPTIONS environment variable may be used to specify
 # arguments to herd, which default to "-conf linux-kernel.cfg".  Thus,
-- 
cgit v1.2.3


From c4081a46f38fd9917e0beb58de72391f27138d57 Mon Sep 17 00:00:00 2001
From: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Date: Mon, 16 Jul 2018 11:05:59 -0700
Subject: locking/atomics/Documentation: Describe atomic_set() as a write
 operation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The atomic_set() and ATOMIC_INIT() operations are writes, so this
commit changes their description from "reads" to "writes".

Signed-off-by: Jonathan Neuschäfer <j.neuschaefer@gmx.net>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Reviewed-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-8-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/core-api/atomic_ops.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/core-api/atomic_ops.rst b/Documentation/core-api/atomic_ops.rst
index 2e7165f86f55..724583453e1f 100644
--- a/Documentation/core-api/atomic_ops.rst
+++ b/Documentation/core-api/atomic_ops.rst
@@ -29,7 +29,7 @@ updated by one CPU, local_t is probably more appropriate. Please see
 local_t.
 
 The first operations to implement for atomic_t's are the initializers and
-plain reads. ::
+plain writes. ::
 
 	#define ATOMIC_INIT(i)		{ (i) }
 	#define atomic_set(v, i)	((v)->counter = (i))
-- 
cgit v1.2.3


From 70b83069f70d185356beba3202b9d167ee39f051 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Date: Mon, 16 Jul 2018 11:06:00 -0700
Subject: tools/memory-model: Add informal LKMM documentation to MAINTAINERS

The Linux-kernel memory model has been informal, with a number of
text files documenting it.  It would be good to make sure that these
informal descriptions are kept up to date and/or pruned appropriately.
This commit therefore brings more of those text files into the LKMM
MAINTAINERS file entry.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: David Howells <dhowells@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: parri.andrea@gmail.com
Link: http://lkml.kernel.org/r/20180716180605.16115-9-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 MAINTAINERS | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index eb427596f3e0..900889a47627 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8318,9 +8318,14 @@ M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 R:	Akira Yokosawa <akiyks@gmail.com>
 R:	Daniel Lustig <dlustig@nvidia.com>
 L:	linux-kernel@vger.kernel.org
+L:	linux-arch@vger.kernel.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.git
 F:	tools/memory-model/
+F:	Documentation/atomic_bitops.txt
+F:	Documentation/atomic_t.txt
+F:	Documentation/core-api/atomic_ops.rst
+F:	Documentation/core-api/refcount-vs-atomic.rst
 F:	Documentation/memory-barriers.txt
 
 LINUX SECURITY MODULE (LSM) FRAMEWORK
-- 
cgit v1.2.3


From 76e079fefc8f62bd9b2cd2950814d1ee806e31a5 Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Mon, 16 Jul 2018 11:06:01 -0700
Subject: sched/core: Use smp_mb() in wake_woken_function()

wake_woken_function() synchronizes with wait_woken() as follows:

  [wait_woken]                       [wake_woken_function]

  entry->flags &= ~wq_flag_woken;    condition = true;
  smp_mb();                          smp_wmb();
  if (condition)                     wq_entry->flags |= wq_flag_woken;
     break;

This commit replaces the above smp_wmb() with an smp_mb() in order to
guarantee that either wait_woken() sees the wait condition being true
or the store to wq_entry->flags in woken_wake_function() follows the
store in wait_woken() in the coherence order (so that the former can
eventually be observed by wait_woken()).

The commit also fixes a comment associated to set_current_state() in
wait_woken(): the comment pairs the barrier in set_current_state() to
the above smp_wmb(), while the actual pairing involves the barrier in
set_current_state() and the barrier executed by the try_to_wake_up()
in wake_woken_function().

Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-10-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/wait.c | 47 +++++++++++++++++++++--------------------------
 1 file changed, 21 insertions(+), 26 deletions(-)

diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 928be527477e..a7a2aaa3026a 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -392,35 +392,36 @@ static inline bool is_kthread_should_stop(void)
  *     if (condition)
  *         break;
  *
- *     p->state = mode;				condition = true;
- *     smp_mb(); // A				smp_wmb(); // C
- *     if (!wq_entry->flags & WQ_FLAG_WOKEN)	wq_entry->flags |= WQ_FLAG_WOKEN;
- *         schedule()				try_to_wake_up();
- *     p->state = TASK_RUNNING;		    ~~~~~~~~~~~~~~~~~~
- *     wq_entry->flags &= ~WQ_FLAG_WOKEN;		condition = true;
- *     smp_mb() // B				smp_wmb(); // C
- *						wq_entry->flags |= WQ_FLAG_WOKEN;
- * }
- * remove_wait_queue(&wq_head, &wait);
+ *     // in wait_woken()			// in woken_wake_function()
  *
+ *     p->state = mode;				wq_entry->flags |= WQ_FLAG_WOKEN;
+ *     smp_mb(); // A				try_to_wake_up():
+ *     if (!(wq_entry->flags & WQ_FLAG_WOKEN))	   <full barrier>
+ *         schedule()				   if (p->state & mode)
+ *     p->state = TASK_RUNNING;			      p->state = TASK_RUNNING;
+ *     wq_entry->flags &= ~WQ_FLAG_WOKEN;	~~~~~~~~~~~~~~~~~~
+ *     smp_mb(); // B				condition = true;
+ * }						smp_mb(); // C
+ * remove_wait_queue(&wq_head, &wait);		wq_entry->flags |= WQ_FLAG_WOKEN;
  */
 long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
 {
-	set_current_state(mode); /* A */
 	/*
-	 * The above implies an smp_mb(), which matches with the smp_wmb() from
-	 * woken_wake_function() such that if we observe WQ_FLAG_WOKEN we must
-	 * also observe all state before the wakeup.
+	 * The below executes an smp_mb(), which matches with the full barrier
+	 * executed by the try_to_wake_up() in woken_wake_function() such that
+	 * either we see the store to wq_entry->flags in woken_wake_function()
+	 * or woken_wake_function() sees our store to current->state.
 	 */
+	set_current_state(mode); /* A */
 	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
 		timeout = schedule_timeout(timeout);
 	__set_current_state(TASK_RUNNING);
 
 	/*
-	 * The below implies an smp_mb(), it too pairs with the smp_wmb() from
-	 * woken_wake_function() such that we must either observe the wait
-	 * condition being true _OR_ WQ_FLAG_WOKEN such that we will not miss
-	 * an event.
+	 * The below executes an smp_mb(), which matches with the smp_mb() (C)
+	 * in woken_wake_function() such that either we see the wait condition
+	 * being true or the store to wq_entry->flags in woken_wake_function()
+	 * follows ours in the coherence order.
 	 */
 	smp_store_mb(wq_entry->flags, wq_entry->flags & ~WQ_FLAG_WOKEN); /* B */
 
@@ -430,14 +431,8 @@ EXPORT_SYMBOL(wait_woken);
 
 int woken_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, int sync, void *key)
 {
-	/*
-	 * Although this function is called under waitqueue lock, LOCK
-	 * doesn't imply write barrier and the users expects write
-	 * barrier semantics on wakeup functions.  The following
-	 * smp_wmb() is equivalent to smp_wmb() in try_to_wake_up()
-	 * and is paired with smp_store_mb() in wait_woken().
-	 */
-	smp_wmb(); /* C */
+	/* Pairs with the smp_store_mb() in wait_woken(). */
+	smp_mb(); /* C */
 	wq_entry->flags |= WQ_FLAG_WOKEN;
 
 	return default_wake_function(wq_entry, mode, sync, key);
-- 
cgit v1.2.3


From 3d85b2703783636366560c94842affd8608ec9d1 Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Mon, 16 Jul 2018 11:06:02 -0700
Subject: locking/spinlock, sched/core: Clarify requirements for
 smp_mb__after_spinlock()

There are 11 interpretations of the requirements described in the header
comment for smp_mb__after_spinlock(): one for each LKMM maintainer, and
one currently encoded in the Cat file. Stick to the latter (until a more
satisfactory solution is available).

This also reworks some snippets related to the barrier to illustrate the
requirements and to link them to the idioms which are relied upon at its
call sites.

Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: akiyks@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: stern@rowland.harvard.edu
Link: http://lkml.kernel.org/r/20180716180605.16115-11-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/spinlock.h | 53 ++++++++++++++++++++++++++++++++----------------
 kernel/sched/core.c      | 41 +++++++++++++++++++------------------
 2 files changed, 57 insertions(+), 37 deletions(-)

diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index fd57888d4942..3190997df9ca 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -114,29 +114,48 @@ do {								\
 #endif /*arch_spin_is_contended*/
 
 /*
- * This barrier must provide two things:
+ * smp_mb__after_spinlock() provides the equivalent of a full memory barrier
+ * between program-order earlier lock acquisitions and program-order later
+ * memory accesses.
  *
- *   - it must guarantee a STORE before the spin_lock() is ordered against a
- *     LOAD after it, see the comments at its two usage sites.
+ * This guarantees that the following two properties hold:
  *
- *   - it must ensure the critical section is RCsc.
+ *   1) Given the snippet:
  *
- * The latter is important for cases where we observe values written by other
- * CPUs in spin-loops, without barriers, while being subject to scheduling.
+ *	  { X = 0;  Y = 0; }
  *
- * CPU0			CPU1			CPU2
+ *	  CPU0				CPU1
  *
- *			for (;;) {
- *			  if (READ_ONCE(X))
- *			    break;
- *			}
- * X=1
- *			<sched-out>
- *						<sched-in>
- *						r = X;
+ *	  WRITE_ONCE(X, 1);		WRITE_ONCE(Y, 1);
+ *	  spin_lock(S);			smp_mb();
+ *	  smp_mb__after_spinlock();	r1 = READ_ONCE(X);
+ *	  r0 = READ_ONCE(Y);
+ *	  spin_unlock(S);
  *
- * without transitivity it could be that CPU1 observes X!=0 breaks the loop,
- * we get migrated and CPU2 sees X==0.
+ *      it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0)
+ *      and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments
+ *      preceding the call to smp_mb__after_spinlock() in __schedule() and in
+ *      try_to_wake_up().
+ *
+ *   2) Given the snippet:
+ *
+ *  { X = 0;  Y = 0; }
+ *
+ *  CPU0		CPU1				CPU2
+ *
+ *  spin_lock(S);	spin_lock(S);			r1 = READ_ONCE(Y);
+ *  WRITE_ONCE(X, 1);	smp_mb__after_spinlock();	smp_rmb();
+ *  spin_unlock(S);	r0 = READ_ONCE(X);		r2 = READ_ONCE(X);
+ *			WRITE_ONCE(Y, 1);
+ *			spin_unlock(S);
+ *
+ *      it is forbidden that CPU0's critical section executes before CPU1's
+ *      critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1)
+ *      and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments
+ *      preceding the calls to smp_rmb() in try_to_wake_up() for similar
+ *      snippets but "projected" onto two CPUs.
+ *
+ * Property (2) upgrades the lock to an RCsc lock.
  *
  * Since most load-store architectures implement ACQUIRE with an smp_mb() after
  * the LL/SC loop, they need no further barriers. Similarly all our TSO
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe365c9a08e9..0c5ec2abdf93 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1998,21 +1998,20 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * be possible to, falsely, observe p->on_rq == 0 and get stuck
 	 * in smp_cond_load_acquire() below.
 	 *
-	 * sched_ttwu_pending()                 try_to_wake_up()
-	 *   [S] p->on_rq = 1;                  [L] P->state
-	 *       UNLOCK rq->lock  -----.
-	 *                              \
-	 *				 +---   RMB
-	 * schedule()                   /
-	 *       LOCK rq->lock    -----'
-	 *       UNLOCK rq->lock
+	 * sched_ttwu_pending()			try_to_wake_up()
+	 *   STORE p->on_rq = 1			  LOAD p->state
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (switch to task 'p')
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   UNLOCK rq->lock
 	 *
 	 * [task p]
-	 *   [S] p->state = UNINTERRUPTIBLE     [L] p->on_rq
+	 *   STORE p->state = UNINTERRUPTIBLE	  LOAD p->on_rq
 	 *
-	 * Pairs with the UNLOCK+LOCK on rq->lock from the
-	 * last wakeup of our task and the schedule that got our task
-	 * current.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 	if (p->on_rq && ttwu_remote(p, wake_flags))
@@ -2026,15 +2025,17 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 	 * One must be running (->on_cpu == 1) in order to remove oneself
 	 * from the runqueue.
 	 *
-	 *  [S] ->on_cpu = 1;	[L] ->on_rq
-	 *      UNLOCK rq->lock
-	 *			RMB
-	 *      LOCK   rq->lock
-	 *  [S] ->on_rq = 0;    [L] ->on_cpu
+	 * __schedule() (switch to task 'p')	try_to_wake_up()
+	 *   STORE p->on_cpu = 1		  LOAD p->on_rq
+	 *   UNLOCK rq->lock
+	 *
+	 * __schedule() (put 'p' to sleep)
+	 *   LOCK rq->lock			  smp_rmb();
+	 *   smp_mb__after_spinlock();
+	 *   STORE p->on_rq = 0			  LOAD p->on_cpu
 	 *
-	 * Pairs with the full barrier implied in the UNLOCK+LOCK on rq->lock
-	 * from the consecutive calls to schedule(); the first switching to our
-	 * task, the second putting it to sleep.
+	 * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+	 * __schedule().  See the comment for smp_mb__after_spinlock().
 	 */
 	smp_rmb();
 
-- 
cgit v1.2.3


From 7696f9910a9a40b8a952f57d3428515fabd2d889 Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Mon, 16 Jul 2018 11:06:03 -0700
Subject: sched/Documentation: Update wake_up() & co. memory-barrier guarantees

Both the implementation and the users' expectation [1] for the various
wakeup primitives have evolved over time, but the documentation has not
kept up with these changes: brings it into 2018.

[1] http://lkml.kernel.org/r/20180424091510.GB4064@hirez.programming.kicks-ass.net

Also applied feedback from Alan Stern.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Daniel Lustig <dlustig@nvidia.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: parri.andrea@gmail.com
Link: http://lkml.kernel.org/r/20180716180605.16115-12-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 Documentation/memory-barriers.txt | 43 ++++++++++++++++++++++++---------------
 include/linux/sched.h             |  4 ++--
 kernel/sched/completion.c         |  8 ++++----
 kernel/sched/core.c               | 30 +++++++++++----------------
 kernel/sched/wait.c               |  8 ++++----
 5 files changed, 49 insertions(+), 44 deletions(-)

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index a02d6bbfc9d0..0d8d7ef131e9 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -2179,32 +2179,41 @@ or:
 	event_indicated = 1;
 	wake_up_process(event_daemon);
 
-A write memory barrier is implied by wake_up() and co.  if and only if they
-wake something up.  The barrier occurs before the task state is cleared, and so
-sits between the STORE to indicate the event and the STORE to set TASK_RUNNING:
+A general memory barrier is executed by wake_up() if it wakes something up.
+If it doesn't wake anything up then a memory barrier may or may not be
+executed; you must not rely on it.  The barrier occurs before the task state
+is accessed, in particular, it sits between the STORE to indicate the event
+and the STORE to set TASK_RUNNING:
 
-	CPU 1				CPU 2
+	CPU 1 (Sleeper)			CPU 2 (Waker)
 	===============================	===============================
 	set_current_state();		STORE event_indicated
 	  smp_store_mb();		wake_up();
-	    STORE current->state	  <write barrier>
-	    <general barrier>		  STORE current->state
-	LOAD event_indicated
+	    STORE current->state	  ...
+	    <general barrier>		  <general barrier>
+	LOAD event_indicated		  if ((LOAD task->state) & TASK_NORMAL)
+					    STORE task->state
 
-To repeat, this write memory barrier is present if and only if something
-is actually awakened.  To see this, consider the following sequence of
-events, where X and Y are both initially zero:
+where "task" is the thread being woken up and it equals CPU 1's "current".
+
+To repeat, a general memory barrier is guaranteed to be executed by wake_up()
+if something is actually awakened, but otherwise there is no such guarantee.
+To see this, consider the following sequence of events, where X and Y are both
+initially zero:
 
 	CPU 1				CPU 2
 	===============================	===============================
-	X = 1;				STORE event_indicated
+	X = 1;				Y = 1;
 	smp_mb();			wake_up();
-	Y = 1;				wait_event(wq, Y == 1);
-	wake_up();			  load from Y sees 1, no memory barrier
-					load from X might see 0
+	LOAD Y				LOAD X
+
+If a wakeup does occur, one (at least) of the two loads must see 1.  If, on
+the other hand, a wakeup does not occur, both loads might see 0.
 
-In contrast, if a wakeup does occur, CPU 2's load from X would be guaranteed
-to see 1.
+wake_up_process() always executes a general memory barrier.  The barrier again
+occurs before the task state is accessed.  In particular, if the wake_up() in
+the previous snippet were replaced by a call to wake_up_process() then one of
+the two loads would be guaranteed to see 1.
 
 The available waker functions include:
 
@@ -2224,6 +2233,8 @@ The available waker functions include:
 	wake_up_poll();
 	wake_up_process();
 
+In terms of memory ordering, these functions all provide the same guarantees of
+a wake_up() (or stronger).
 
 [!] Note that the memory barriers implied by the sleeper and the waker do _not_
 order multiple stores before the wake-up with respect to loads of those stored
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 43731fe51c97..05cd419f962d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -167,8 +167,8 @@ struct task_group;
  *   need_sleep = false;
  *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
- * Where wake_up_state() (and all other wakeup primitives) imply enough
- * barriers to order the store of the variable against wakeup.
+ * where wake_up_state() executes a full memory barrier before accessing the
+ * task state.
  *
  * Wakeup will do: if (@state & p->state) p->state = TASK_RUNNING, that is,
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index e426b0cb9ac6..a1ad5b7d5521 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -22,8 +22,8 @@
  *
  * See also complete_all(), wait_for_completion() and related routines.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void complete(struct completion *x)
 {
@@ -44,8 +44,8 @@ EXPORT_SYMBOL(complete);
  *
  * This will wake up all threads waiting on this particular completion event.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  *
  * Since complete_all() sets the completion of @x permanently to done
  * to allow multiple waiters to finish, a call to reinit_completion()
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0c5ec2abdf93..a0065c84e73f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -412,8 +412,8 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 	 * its already queued (either by us or someone else) and will get the
 	 * wakeup due to that.
 	 *
-	 * This cmpxchg() implies a full barrier, which pairs with the write
-	 * barrier implied by the wakeup in wake_up_q().
+	 * This cmpxchg() executes a full barrier, which pairs with the full
+	 * barrier executed by the wakeup in wake_up_q().
 	 */
 	if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL))
 		return;
@@ -441,8 +441,8 @@ void wake_up_q(struct wake_q_head *head)
 		task->wake_q.next = NULL;
 
 		/*
-		 * wake_up_process() implies a wmb() to pair with the queueing
-		 * in wake_q_add() so as not to miss wakeups.
+		 * wake_up_process() executes a full barrier, which pairs with
+		 * the queueing in wake_q_add() so as not to miss wakeups.
 		 */
 		wake_up_process(task);
 		put_task_struct(task);
@@ -1879,8 +1879,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *     rq(c1)->lock (if not at the same time, then in that order).
  *  C) LOCK of the rq(c1)->lock scheduling in task
  *
- * Transitivity guarantees that B happens after A and C after B.
- * Note: we only require RCpc transitivity.
+ * Release/acquire chaining guarantees that B happens after A and C after B.
  * Note: the CPU doing B need not be c0 or c1
  *
  * Example:
@@ -1942,16 +1941,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  *   UNLOCK rq(0)->lock
  *
  *
- * However; for wakeups there is a second guarantee we must provide, namely we
- * must observe the state that lead to our wakeup. That is, not only must our
- * task observe its own prior state, it must also observe the stores prior to
- * its wakeup.
- *
- * This means that any means of doing remote wakeups must order the CPU doing
- * the wakeup against the CPU the task is going to end up running on. This,
- * however, is already required for the regular Program-Order guarantee above,
- * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
- *
+ * However, for wakeups there is a second guarantee we must provide, namely we
+ * must ensure that CONDITION=1 done by the caller can not be reordered with
+ * accesses to the task state; see try_to_wake_up() and set_current_state().
  */
 
 /**
@@ -1967,6 +1959,9 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
  * Atomic against schedule() which would dequeue a task, also see
  * set_current_state().
  *
+ * This function executes a full memory barrier before accessing the task
+ * state; see set_current_state().
+ *
  * Return: %true if @p->state changes (an actual wakeup was done),
  *	   %false otherwise.
  */
@@ -2141,8 +2136,7 @@ out:
  *
  * Return: 1 if the process was woken up, 0 if it was already running.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * This function executes a full memory barrier before accessing the task state.
  */
 int wake_up_process(struct task_struct *p)
 {
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index a7a2aaa3026a..870f97b313e3 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -134,8 +134,8 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
@@ -180,8 +180,8 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
  *
  * On UP it can prevent extra preemption.
  *
- * It may be assumed that this function implies a write memory barrier before
- * changing the task state if and only if any tasks are woken up.
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
  */
 void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, void *key)
-- 
cgit v1.2.3


From 0fcff1715bec7593a0ba86f3fef46cd89af37a8b Mon Sep 17 00:00:00 2001
From: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Date: Mon, 16 Jul 2018 11:06:04 -0700
Subject: tools/memory-model/Documentation: Fix typo, smb->smp

The tools/memory-model/Documentation/explanation.txt file says
"For each other CPU C', smb_wmb() forces all po-earlier stores"
This commit therefore replaces the "smb_wmb()" with "smp_wmb()".

Signed-off-by: Yauheni Kaliuta <yauheni.kaliuta@redhat.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akiyks@gmail.com
Cc: boqun.feng@gmail.com
Cc: dhowells@redhat.com
Cc: j.alglave@ucl.ac.uk
Cc: linux-arch@vger.kernel.org
Cc: luc.maranget@inria.fr
Cc: npiggin@gmail.com
Cc: parri.andrea@gmail.com
Cc: will.deacon@arm.com
Link: http://lkml.kernel.org/r/20180716180605.16115-13-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/Documentation/explanation.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
index 1b09f3175a1f..0cbd1ef8f86d 100644
--- a/tools/memory-model/Documentation/explanation.txt
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -804,7 +804,7 @@ type of fence:
 Second, some types of fence affect the way the memory subsystem
 propagates stores.  When a fence instruction is executed on CPU C:
 
-	For each other CPU C', smb_wmb() forces all po-earlier stores
+	For each other CPU C', smp_wmb() forces all po-earlier stores
 	on C to propagate to C' before any po-later stores do.
 
 	For each other CPU C', any store which propagates to C before
-- 
cgit v1.2.3


From 71b7ff5ebc9b1d5aa95eb48d6388234f1304fd19 Mon Sep 17 00:00:00 2001
From: Andrea Parri <andrea.parri@amarulasolutions.com>
Date: Mon, 16 Jul 2018 11:06:05 -0700
Subject: tools/memory-model: Rename litmus tests to comply to norm7

norm7 produces the 'normalized' name of a litmus test,  when the test
can be generated from a single cycle that passes through each process
exactly once. The commit renames such tests in order to comply to the
naming scheme implemented by this tool.

Signed-off-by: Andrea Parri <andrea.parri@amarulasolutions.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Acked-by: Alan Stern <stern@rowland.harvard.edu>
Cc: Akira Yokosawa <akiyks@gmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jade Alglave <j.alglave@ucl.ac.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luc Maranget <luc.maranget@inria.fr>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Will Deacon <will.deacon@arm.com>
Cc: linux-arch@vger.kernel.org
Cc: parri.andrea@gmail.com
Link: http://lkml.kernel.org/r/20180716180605.16115-14-paulmck@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 tools/memory-model/Documentation/recipes.txt       |  8 ++--
 tools/memory-model/README                          | 20 +++++-----
 .../IRIW+fencembonceonces+OnceOnce.litmus          | 45 ++++++++++++++++++++++
 .../litmus-tests/IRIW+mbonceonces+OnceOnce.litmus  | 45 ----------------------
 .../litmus-tests/LB+ctrlonceonce+mbonceonce.litmus | 34 ----------------
 .../LB+fencembonceonce+ctrlonceonce.litmus         | 34 ++++++++++++++++
 .../MP+fencewmbonceonce+fencermbonceonce.litmus    | 30 +++++++++++++++
 .../litmus-tests/MP+wmbonceonce+rmbonceonce.litmus | 30 ---------------
 .../litmus-tests/R+fencembonceonces.litmus         | 30 +++++++++++++++
 .../memory-model/litmus-tests/R+mbonceonces.litmus | 30 ---------------
 tools/memory-model/litmus-tests/README             | 16 ++++----
 .../S+fencewmbonceonce+poacquireonce.litmus        | 27 +++++++++++++
 .../S+wmbonceonce+poacquireonce.litmus             | 27 -------------
 .../litmus-tests/SB+fencembonceonces.litmus        | 32 +++++++++++++++
 .../litmus-tests/SB+mbonceonces.litmus             | 32 ---------------
 .../WRC+pooncerelease+fencermbonceonce+Once.litmus | 38 ++++++++++++++++++
 .../WRC+pooncerelease+rmbonceonce+Once.litmus      | 38 ------------------
 ...release+poacquirerelease+fencembonceonce.litmus | 42 ++++++++++++++++++++
 ...ooncerelease+poacquirerelease+mbonceonce.litmus | 42 --------------------
 19 files changed, 300 insertions(+), 300 deletions(-)
 create mode 100644 tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
 delete mode 100644 tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
 delete mode 100644 tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
 create mode 100644 tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
 create mode 100644 tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
 delete mode 100644 tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
 create mode 100644 tools/memory-model/litmus-tests/R+fencembonceonces.litmus
 delete mode 100644 tools/memory-model/litmus-tests/R+mbonceonces.litmus
 create mode 100644 tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
 delete mode 100644 tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
 create mode 100644 tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
 delete mode 100644 tools/memory-model/litmus-tests/SB+mbonceonces.litmus
 create mode 100644 tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
 delete mode 100644 tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
 create mode 100644 tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
 delete mode 100644 tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus

diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
index 1fea8ef2b184..af72700cc20a 100644
--- a/tools/memory-model/Documentation/recipes.txt
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -126,7 +126,7 @@ However, it is not necessarily the case that accesses ordered by
 locking will be seen as ordered by CPUs not holding that lock.
 Consider this example:
 
-	/* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+	/* See Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus. */
 	void CPU0(void)
 	{
 		spin_lock(&mylock);
@@ -292,7 +292,7 @@ and to use smp_load_acquire() instead of smp_rmb().  However, the older
 smp_wmb() and smp_rmb() APIs are still heavily used, so it is important
 to understand their use cases.  The general approach is shown below:
 
-	/* See MP+wmbonceonce+rmbonceonce.litmus. */
+	/* See MP+fencewmbonceonce+fencermbonceonce.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
@@ -360,7 +360,7 @@ can be seen in the LB+poonceonces.litmus litmus test.
 One way of avoiding the counter-intuitive outcome is through the use of a
 control dependency paired with a full memory barrier:
 
-	/* See LB+ctrlonceonce+mbonceonce.litmus. */
+	/* See LB+fencembonceonce+ctrlonceonce.litmus. */
 	void CPU0(void)
 	{
 		r0 = READ_ONCE(x);
@@ -476,7 +476,7 @@ that one CPU first stores to one variable and then loads from a second,
 while another CPU stores to the second variable and then loads from the
 first.  Preserving order requires nothing less than full barriers:
 
-	/* See SB+mbonceonces.litmus. */
+	/* See SB+fencembonceonces.litmus. */
 	void CPU0(void)
 	{
 		WRITE_ONCE(x, 1);
diff --git a/tools/memory-model/README b/tools/memory-model/README
index 734f7feaa5dc..ee987ce20aae 100644
--- a/tools/memory-model/README
+++ b/tools/memory-model/README
@@ -35,13 +35,13 @@ BASIC USAGE: HERD7
 The memory model is used, in conjunction with "herd7", to exhaustively
 explore the state space of small litmus tests.
 
-For example, to run SB+mbonceonces.litmus against the memory model:
+For example, to run SB+fencembonceonces.litmus against the memory model:
 
-  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus
+  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+fencembonceonces.litmus
 
 Here is the corresponding output:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   States 3
   0:r0=0; 1:r0=1;
   0:r0=1; 1:r0=0;
@@ -50,8 +50,8 @@ Here is the corresponding output:
   Witnesses
   Positive: 0 Negative: 3
   Condition exists (0:r0=0 /\ 1:r0=0)
-  Observation SB+mbonceonces Never 0 3
-  Time SB+mbonceonces 0.01
+  Observation SB+fencembonceonces Never 0 3
+  Time SB+fencembonceonces 0.01
   Hash=d66d99523e2cac6b06e66f4c995ebb48
 
 The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that
@@ -67,16 +67,16 @@ BASIC USAGE: KLITMUS7
 The "klitmus7" tool converts a litmus test into a Linux kernel module,
 which may then be loaded and run.
 
-For example, to run SB+mbonceonces.litmus against hardware:
+For example, to run SB+fencembonceonces.litmus against hardware:
 
   $ mkdir mymodules
-  $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus
+  $ klitmus7 -o mymodules litmus-tests/SB+fencembonceonces.litmus
   $ cd mymodules ; make
   $ sudo sh run.sh
 
 The corresponding output includes:
 
-  Test SB+mbonceonces Allowed
+  Test SB+fencembonceonces Allowed
   Histogram (3 states)
   644580  :>0:r0=1; 1:r0=0;
   644328  :>0:r0=0; 1:r0=1;
@@ -86,8 +86,8 @@ The corresponding output includes:
   Positive: 0, Negative: 2000000
   Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated
   Hash=d66d99523e2cac6b06e66f4c995ebb48
-  Observation SB+mbonceonces Never 0 2000000
-  Time SB+mbonceonces 0.16
+  Observation SB+fencembonceonces Never 0 2000000
+  Time SB+fencembonceonces 0.16
 
 The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate
 that during two million trials, the state specified in this litmus
diff --git a/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
new file mode 100644
index 000000000000..e729d2776e89
--- /dev/null
+++ b/tools/memory-model/litmus-tests/IRIW+fencembonceonces+OnceOnce.litmus
@@ -0,0 +1,45 @@
+C IRIW+fencembonceonces+OnceOnce
+
+(*
+ * Result: Never
+ *
+ * Test of independent reads from independent writes with smp_mb()
+ * between each pairs of reads.  In other words, is smp_mb() sufficient to
+ * cause two different reading processes to agree on the order of a pair
+ * of writes, where each write is to a different variable by a different
+ * process?  This litmus test exercises LKMM's "propagation" rule.
+ *)
+
+{}
+
+P0(int *x)
+{
+	WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+	int r0;
+	int r1;
+
+	r0 = READ_ONCE(*x);
+	smp_mb();
+	r1 = READ_ONCE(*y);
+}
+
+P2(int *y)
+{
+	WRITE_ONCE(*y, 1);
+}
+
+P3(int *x, int *y)
+{
+	int r0;
+	int r1;
+
+	r0 = READ_ONCE(*y);
+	smp_mb();
+	r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0 /\ 3:r0=1 /\ 3:r1=0)
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
deleted file mode 100644
index 98a3716efa37..000000000000
--- a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
+++ /dev/null
@@ -1,45 +0,0 @@
-C IRIW+mbonceonces+OnceOnce
-
-(*
- * Result: Never
- *
- * Test of independent reads from independent writes with smp_mb()
- * between each pairs of reads.  In other words, is smp_mb() sufficient to
- * cause two different reading processes to agree on the order of a pair
- * of writes, where each write is to a different variable by a different
- * process?  This litmus test exercises LKMM's "propagation" rule.
- *)
-
-{}
-
-P0(int *x)
-{
-	WRITE_ONCE(*x, 1);
-}
-
-P1(int *x, int *y)
-{
-	int r0;
-	int r1;
-
-	r0 = READ_ONCE(*x);
-	smp_mb();
-	r1 = READ_ONCE(*y);
-}
-
-P2(int *y)
-{
-	WRITE_ONCE(*y, 1);
-}
-
-P3(int *x, int *y)
-{
-	int r0;
-	int r1;
-
-	r0 = READ_ONCE(*y);
-	smp_mb();
-	r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ 1:r1=0 /\ 3:r0=1 /\ 3:r1=0)
diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
deleted file mode 100644
index de6708229dd1..000000000000
--- a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
+++ /dev/null
@@ -1,34 +0,0 @@
-C LB+ctrlonceonce+mbonceonce
-
-(*
- * Result: Never
- *
- * This litmus test demonstrates that lightweight ordering suffices for
- * the load-buffering pattern, in other words, preventing all processes
- * reading from the preceding process's write.  In this example, the
- * combination of a control dependency and a full memory barrier are enough
- * to do the trick.  (But the full memory barrier could be replaced with
- * another control dependency and order would still be maintained.)
- *)
-
-{}
-
-P0(int *x, int *y)
-{
-	int r0;
-
-	r0 = READ_ONCE(*x);
-	if (r0)
-		WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
-	int r0;
-
-	r0 = READ_ONCE(*y);
-	smp_mb();
-	WRITE_ONCE(*x, 1);
-}
-
-exists (0:r0=1 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
new file mode 100644
index 000000000000..4727f5aaf03b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/LB+fencembonceonce+ctrlonceonce.litmus
@@ -0,0 +1,34 @@
+C LB+fencembonceonce+ctrlonceonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that lightweight ordering suffices for
+ * the load-buffering pattern, in other words, preventing all processes
+ * reading from the preceding process's write.  In this example, the
+ * combination of a control dependency and a full memory barrier are enough
+ * to do the trick.  (But the full memory barrier could be replaced with
+ * another control dependency and order would still be maintained.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	int r0;
+
+	r0 = READ_ONCE(*x);
+	if (r0)
+		WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+	int r0;
+
+	r0 = READ_ONCE(*y);
+	smp_mb();
+	WRITE_ONCE(*x, 1);
+}
+
+exists (0:r0=1 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
new file mode 100644
index 000000000000..a273da9faa6d
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+fencewmbonceonce+fencermbonceonce.litmus
@@ -0,0 +1,30 @@
+C MP+fencewmbonceonce+fencermbonceonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that smp_wmb() and smp_rmb() provide
+ * sufficient ordering for the message-passing pattern.  However, it
+ * is usually better to use smp_store_release() and smp_load_acquire().
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	WRITE_ONCE(*x, 1);
+	smp_wmb();
+	WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+	int r0;
+	int r1;
+
+	r0 = READ_ONCE(*y);
+	smp_rmb();
+	r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
deleted file mode 100644
index c078f38ff27a..000000000000
--- a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
+++ /dev/null
@@ -1,30 +0,0 @@
-C MP+wmbonceonce+rmbonceonce
-
-(*
- * Result: Never
- *
- * This litmus test demonstrates that smp_wmb() and smp_rmb() provide
- * sufficient ordering for the message-passing pattern.  However, it
- * is usually better to use smp_store_release() and smp_load_acquire().
- *)
-
-{}
-
-P0(int *x, int *y)
-{
-	WRITE_ONCE(*x, 1);
-	smp_wmb();
-	WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
-	int r0;
-	int r1;
-
-	r0 = READ_ONCE(*y);
-	smp_rmb();
-	r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/R+fencembonceonces.litmus b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
new file mode 100644
index 000000000000..222a0b850b4a
--- /dev/null
+++ b/tools/memory-model/litmus-tests/R+fencembonceonces.litmus
@@ -0,0 +1,30 @@
+C R+fencembonceonces
+
+(*
+ * Result: Never
+ *
+ * This is the fully ordered (via smp_mb()) version of one of the classic
+ * counterintuitive litmus tests that illustrates the effects of store
+ * propagation delays.  Note that weakening either of the barriers would
+ * cause the resulting test to be allowed.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	WRITE_ONCE(*x, 1);
+	smp_mb();
+	WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+	int r0;
+
+	WRITE_ONCE(*y, 2);
+	smp_mb();
+	r0 = READ_ONCE(*x);
+}
+
+exists (y=2 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+mbonceonces.litmus
deleted file mode 100644
index a0e884ad2132..000000000000
--- a/tools/memory-model/litmus-tests/R+mbonceonces.litmus
+++ /dev/null
@@ -1,30 +0,0 @@
-C R+mbonceonces
-
-(*
- * Result: Never
- *
- * This is the fully ordered (via smp_mb()) version of one of the classic
- * counterintuitive litmus tests that illustrates the effects of store
- * propagation delays.  Note that weakening either of the barriers would
- * cause the resulting test to be allowed.
- *)
-
-{}
-
-P0(int *x, int *y)
-{
-	WRITE_ONCE(*x, 1);
-	smp_mb();
-	WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
-	int r0;
-
-	WRITE_ONCE(*y, 2);
-	smp_mb();
-	r0 = READ_ONCE(*x);
-}
-
-exists (y=2 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
index 00140aaf58b7..4581ec2d3c57 100644
--- a/tools/memory-model/litmus-tests/README
+++ b/tools/memory-model/litmus-tests/README
@@ -18,7 +18,7 @@ CoWW+poonceonce.litmus
 	Test of write-write coherence, that is, whether or not two
 	successive writes to the same variable are ordered.
 
-IRIW+mbonceonces+OnceOnce.litmus
+IRIW+fencembonceonces+OnceOnce.litmus
 	Test of independent reads from independent writes with smp_mb()
 	between each pairs of reads.  In other words, is smp_mb()
 	sufficient to cause two different reading processes to agree on
@@ -47,7 +47,7 @@ ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
 	Can a release-acquire chain order a prior store against
 	a later load?
 
-LB+ctrlonceonce+mbonceonce.litmus
+LB+fencembonceonce+ctrlonceonce.litmus
 	Does a control dependency and an smp_mb() suffice for the
 	load-buffering litmus test, where each process reads from one
 	of two variables then writes to the other?
@@ -88,14 +88,14 @@ MP+porevlocks.litmus
 	As below, but with the first access of the writer process
 	and the second access of reader process protected by a lock.
 
-MP+wmbonceonce+rmbonceonce.litmus
+MP+fencewmbonceonce+fencermbonceonce.litmus
 	Does a smp_wmb() (between the stores) and an smp_rmb() (between
 	the loads) suffice for the message-passing litmus test, where one
 	process writes data and then a flag, and the other process reads
 	the flag and then the data.  (This is similar to the ISA2 tests,
 	but with two processes instead of three.)
 
-R+mbonceonces.litmus
+R+fencembonceonces.litmus
 	This is the fully ordered (via smp_mb()) version of one of
 	the classic counterintuitive litmus tests that illustrates the
 	effects of store propagation delays.
@@ -103,7 +103,7 @@ R+mbonceonces.litmus
 R+poonceonces.litmus
 	As above, but without the smp_mb() invocations.
 
-SB+mbonceonces.litmus
+SB+fencembonceonces.litmus
 	This is the fully ordered (again, via smp_mb() version of store
 	buffering, which forms the core of Dekker's mutual-exclusion
 	algorithm.
@@ -123,12 +123,12 @@ SB+rfionceonce-poonceonces.litmus
 S+poonceonces.litmus
 	As below, but without the smp_wmb() and acquire load.
 
-S+wmbonceonce+poacquireonce.litmus
+S+fencewmbonceonce+poacquireonce.litmus
 	Can a smp_wmb(), instead of a release, and an acquire order
 	a prior store against a subsequent store?
 
 WRC+poonceonces+Once.litmus
-WRC+pooncerelease+rmbonceonce+Once.litmus
+WRC+pooncerelease+fencermbonceonce+Once.litmus
 	These two are members of an extension of the MP litmus-test
 	class in which the first write is moved to a separate process.
 	The second is forbidden because smp_store_release() is
@@ -143,7 +143,7 @@ Z6.0+pooncelock+poonceLock+pombonce.litmus
 	As above, but with smp_mb__after_spinlock() immediately
 	following the spin_lock().
 
-Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
 	Is the ordering provided by a release-acquire chain sufficient
 	to make ordering apparent to accesses by a process that does
 	not participate in that release-acquire chain?
diff --git a/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
new file mode 100644
index 000000000000..18479823cd6c
--- /dev/null
+++ b/tools/memory-model/litmus-tests/S+fencewmbonceonce+poacquireonce.litmus
@@ -0,0 +1,27 @@
+C S+fencewmbonceonce+poacquireonce
+
+(*
+ * Result: Never
+ *
+ * Can a smp_wmb(), instead of a release, and an acquire order a prior
+ * store against a subsequent store?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	WRITE_ONCE(*x, 2);
+	smp_wmb();
+	WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+	int r0;
+
+	r0 = smp_load_acquire(y);
+	WRITE_ONCE(*x, 1);
+}
+
+exists (x=2 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
deleted file mode 100644
index c53350205d28..000000000000
--- a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
+++ /dev/null
@@ -1,27 +0,0 @@
-C S+wmbonceonce+poacquireonce
-
-(*
- * Result: Never
- *
- * Can a smp_wmb(), instead of a release, and an acquire order a prior
- * store against a subsequent store?
- *)
-
-{}
-
-P0(int *x, int *y)
-{
-	WRITE_ONCE(*x, 2);
-	smp_wmb();
-	WRITE_ONCE(*y, 1);
-}
-
-P1(int *x, int *y)
-{
-	int r0;
-
-	r0 = smp_load_acquire(y);
-	WRITE_ONCE(*x, 1);
-}
-
-exists (x=2 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
new file mode 100644
index 000000000000..ed5fff18d223
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+fencembonceonces.litmus
@@ -0,0 +1,32 @@
+C SB+fencembonceonces
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that full memory barriers suffice to
+ * order the store-buffering pattern, where each process writes to the
+ * variable that the preceding process reads.  (Locking and RCU can also
+ * suffice, but not much else.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	int r0;
+
+	WRITE_ONCE(*x, 1);
+	smp_mb();
+	r0 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+	int r0;
+
+	WRITE_ONCE(*y, 1);
+	smp_mb();
+	r0 = READ_ONCE(*x);
+}
+
+exists (0:r0=0 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
deleted file mode 100644
index 74b874ffa8da..000000000000
--- a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
+++ /dev/null
@@ -1,32 +0,0 @@
-C SB+mbonceonces
-
-(*
- * Result: Never
- *
- * This litmus test demonstrates that full memory barriers suffice to
- * order the store-buffering pattern, where each process writes to the
- * variable that the preceding process reads.  (Locking and RCU can also
- * suffice, but not much else.)
- *)
-
-{}
-
-P0(int *x, int *y)
-{
-	int r0;
-
-	WRITE_ONCE(*x, 1);
-	smp_mb();
-	r0 = READ_ONCE(*y);
-}
-
-P1(int *x, int *y)
-{
-	int r0;
-
-	WRITE_ONCE(*y, 1);
-	smp_mb();
-	r0 = READ_ONCE(*x);
-}
-
-exists (0:r0=0 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
new file mode 100644
index 000000000000..e9947250d7de
--- /dev/null
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+fencermbonceonce+Once.litmus
@@ -0,0 +1,38 @@
+C WRC+pooncerelease+fencermbonceonce+Once
+
+(*
+ * Result: Never
+ *
+ * This litmus test is an extension of the message-passing pattern, where
+ * the first write is moved to a separate process.  Because it features
+ * a release and a read memory barrier, it should be forbidden.  More
+ * specifically, this litmus test is forbidden because smp_store_release()
+ * is A-cumulative in LKMM.
+ *)
+
+{}
+
+P0(int *x)
+{
+	WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+	int r0;
+
+	r0 = READ_ONCE(*x);
+	smp_store_release(y, 1);
+}
+
+P2(int *x, int *y)
+{
+	int r0;
+	int r1;
+
+	r0 = READ_ONCE(*y);
+	smp_rmb();
+	r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
deleted file mode 100644
index ad3448b941e6..000000000000
--- a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
+++ /dev/null
@@ -1,38 +0,0 @@
-C WRC+pooncerelease+rmbonceonce+Once
-
-(*
- * Result: Never
- *
- * This litmus test is an extension of the message-passing pattern, where
- * the first write is moved to a separate process.  Because it features
- * a release and a read memory barrier, it should be forbidden.  More
- * specifically, this litmus test is forbidden because smp_store_release()
- * is A-cumulative in LKMM.
- *)
-
-{}
-
-P0(int *x)
-{
-	WRITE_ONCE(*x, 1);
-}
-
-P1(int *x, int *y)
-{
-	int r0;
-
-	r0 = READ_ONCE(*x);
-	smp_store_release(y, 1);
-}
-
-P2(int *x, int *y)
-{
-	int r0;
-	int r1;
-
-	r0 = READ_ONCE(*y);
-	smp_rmb();
-	r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
new file mode 100644
index 000000000000..88e70b87a683
--- /dev/null
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+fencembonceonce.litmus
@@ -0,0 +1,42 @@
+C Z6.0+pooncerelease+poacquirerelease+fencembonceonce
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test shows that a release-acquire chain, while sufficient
+ * when there is but one non-reads-from (AKA non-rf) link, does not suffice
+ * if there is more than one.  Of the three processes, only P1() reads from
+ * P0's write, which means that there are two non-rf links: P1() to P2()
+ * is a write-to-write link (AKA a "coherence" or just "co" link) and P2()
+ * to P0() is a read-to-write link (AKA a "from-reads" or just "fr" link).
+ * When there are two or more non-rf links, you typically will need one
+ * full barrier for each non-rf link.  (Exceptions include some cases
+ * involving locking.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+	WRITE_ONCE(*x, 1);
+	smp_store_release(y, 1);
+}
+
+P1(int *y, int *z)
+{
+	int r0;
+
+	r0 = smp_load_acquire(y);
+	smp_store_release(z, 1);
+}
+
+P2(int *x, int *z)
+{
+	int r1;
+
+	WRITE_ONCE(*z, 2);
+	smp_mb();
+	r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ z=2 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
deleted file mode 100644
index a20fc3fafb53..000000000000
--- a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+++ /dev/null
@@ -1,42 +0,0 @@
-C Z6.0+pooncerelease+poacquirerelease+mbonceonce
-
-(*
- * Result: Sometimes
- *
- * This litmus test shows that a release-acquire chain, while sufficient
- * when there is but one non-reads-from (AKA non-rf) link, does not suffice
- * if there is more than one.  Of the three processes, only P1() reads from
- * P0's write, which means that there are two non-rf links: P1() to P2()
- * is a write-to-write link (AKA a "coherence" or just "co" link) and P2()
- * to P0() is a read-to-write link (AKA a "from-reads" or just "fr" link).
- * When there are two or more non-rf links, you typically will need one
- * full barrier for each non-rf link.  (Exceptions include some cases
- * involving locking.)
- *)
-
-{}
-
-P0(int *x, int *y)
-{
-	WRITE_ONCE(*x, 1);
-	smp_store_release(y, 1);
-}
-
-P1(int *y, int *z)
-{
-	int r0;
-
-	r0 = smp_load_acquire(y);
-	smp_store_release(z, 1);
-}
-
-P2(int *x, int *z)
-{
-	int r1;
-
-	WRITE_ONCE(*z, 2);
-	smp_mb();
-	r1 = READ_ONCE(*x);
-}
-
-exists (1:r0=1 /\ z=2 /\ 2:r1=0)
-- 
cgit v1.2.3


From c1a2f7f0c06454387c2cd7b93ff1491c715a8c69 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Mon, 16 Jul 2018 15:03:31 -0400
Subject: mm: Allocate the mm_cpumask (mm->cpu_bitmap[]) dynamically based on
 nr_cpu_ids

The mm_struct always contains a cpumask bitmap, regardless of
CONFIG_CPUMASK_OFFSTACK. That means the first step can be to
simplify things, and simply have one bitmask at the end of the
mm_struct for the mm_cpumask.

This does necessitate moving everything else in mm_struct into
an anonymous sub-structure, which can be randomized when struct
randomization is enabled.

The second step is to determine the correct size for the
mm_struct slab object from the size of the mm_struct
(excluding the CPU bitmap) and the size the cpumask.

For init_mm we can simply allocate the maximum size this
kernel is compiled for, since we only have one init_mm
in the system, anyway.

Pointer magic by Mike Galbraith, to evade -Wstringop-overflow
getting confused by the dynamically sized array.

Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-team@fb.com
Cc: luto@kernel.org
Link: http://lkml.kernel.org/r/20180716190337.26133-2-riel@surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/efi.c |   1 +
 include/linux/mm_types.h   | 241 +++++++++++++++++++++++----------------------
 kernel/fork.c              |  15 +--
 mm/init-mm.c               |  11 +++
 4 files changed, 145 insertions(+), 123 deletions(-)

diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 232f4915223b..7f0b19410a95 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -82,6 +82,7 @@ struct mm_struct efi_mm = {
 	.mmap_sem		= __RWSEM_INITIALIZER(efi_mm.mmap_sem),
 	.page_table_lock	= __SPIN_LOCK_UNLOCKED(efi_mm.page_table_lock),
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
+	.cpu_bitmap		= { [BITS_TO_LONGS(NR_CPUS)] = 0},
 };
 
 static bool disable_runtime;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 99ce070e7dcb..efdc24dd9e97 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -335,176 +335,183 @@ struct core_state {
 
 struct kioctx_table;
 struct mm_struct {
-	struct vm_area_struct *mmap;		/* list of VMAs */
-	struct rb_root mm_rb;
-	u32 vmacache_seqnum;                   /* per-thread vmacache */
+	struct {
+		struct vm_area_struct *mmap;		/* list of VMAs */
+		struct rb_root mm_rb;
+		u32 vmacache_seqnum;                   /* per-thread vmacache */
 #ifdef CONFIG_MMU
-	unsigned long (*get_unmapped_area) (struct file *filp,
+		unsigned long (*get_unmapped_area) (struct file *filp,
 				unsigned long addr, unsigned long len,
 				unsigned long pgoff, unsigned long flags);
 #endif
-	unsigned long mmap_base;		/* base of mmap area */
-	unsigned long mmap_legacy_base;         /* base of mmap area in bottom-up allocations */
+		unsigned long mmap_base;	/* base of mmap area */
+		unsigned long mmap_legacy_base;	/* base of mmap area in bottom-up allocations */
 #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
-	/* Base adresses for compatible mmap() */
-	unsigned long mmap_compat_base;
-	unsigned long mmap_compat_legacy_base;
+		/* Base adresses for compatible mmap() */
+		unsigned long mmap_compat_base;
+		unsigned long mmap_compat_legacy_base;
 #endif
-	unsigned long task_size;		/* size of task vm space */
-	unsigned long highest_vm_end;		/* highest vma end address */
-	pgd_t * pgd;
-
-	/**
-	 * @mm_users: The number of users including userspace.
-	 *
-	 * Use mmget()/mmget_not_zero()/mmput() to modify. When this drops
-	 * to 0 (i.e. when the task exits and there are no other temporary
-	 * reference holders), we also release a reference on @mm_count
-	 * (which may then free the &struct mm_struct if @mm_count also
-	 * drops to 0).
-	 */
-	atomic_t mm_users;
-
-	/**
-	 * @mm_count: The number of references to &struct mm_struct
-	 * (@mm_users count as 1).
-	 *
-	 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
-	 * &struct mm_struct is freed.
-	 */
-	atomic_t mm_count;
+		unsigned long task_size;	/* size of task vm space */
+		unsigned long highest_vm_end;	/* highest vma end address */
+		pgd_t * pgd;
+
+		/**
+		 * @mm_users: The number of users including userspace.
+		 *
+		 * Use mmget()/mmget_not_zero()/mmput() to modify. When this
+		 * drops to 0 (i.e. when the task exits and there are no other
+		 * temporary reference holders), we also release a reference on
+		 * @mm_count (which may then free the &struct mm_struct if
+		 * @mm_count also drops to 0).
+		 */
+		atomic_t mm_users;
+
+		/**
+		 * @mm_count: The number of references to &struct mm_struct
+		 * (@mm_users count as 1).
+		 *
+		 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
+		 * &struct mm_struct is freed.
+		 */
+		atomic_t mm_count;
 
 #ifdef CONFIG_MMU
-	atomic_long_t pgtables_bytes;		/* PTE page table pages */
+		atomic_long_t pgtables_bytes;	/* PTE page table pages */
 #endif
-	int map_count;				/* number of VMAs */
+		int map_count;			/* number of VMAs */
 
-	spinlock_t page_table_lock;		/* Protects page tables and some counters */
-	struct rw_semaphore mmap_sem;
+		spinlock_t page_table_lock; /* Protects page tables and some
+					     * counters
+					     */
+		struct rw_semaphore mmap_sem;
 
-	struct list_head mmlist;		/* List of maybe swapped mm's.	These are globally strung
-						 * together off init_mm.mmlist, and are protected
-						 * by mmlist_lock
-						 */
+		struct list_head mmlist; /* List of maybe swapped mm's.	These
+					  * are globally strung together off
+					  * init_mm.mmlist, and are protected
+					  * by mmlist_lock
+					  */
 
 
-	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
-	unsigned long hiwater_vm;	/* High-water virtual memory usage */
+		unsigned long hiwater_rss; /* High-watermark of RSS usage */
+		unsigned long hiwater_vm;  /* High-water virtual memory usage */
 
-	unsigned long total_vm;		/* Total pages mapped */
-	unsigned long locked_vm;	/* Pages that have PG_mlocked set */
-	unsigned long pinned_vm;	/* Refcount permanently increased */
-	unsigned long data_vm;		/* VM_WRITE & ~VM_SHARED & ~VM_STACK */
-	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE & ~VM_STACK */
-	unsigned long stack_vm;		/* VM_STACK */
-	unsigned long def_flags;
+		unsigned long total_vm;	   /* Total pages mapped */
+		unsigned long locked_vm;   /* Pages that have PG_mlocked set */
+		unsigned long pinned_vm;   /* Refcount permanently increased */
+		unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
+		unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
+		unsigned long stack_vm;	   /* VM_STACK */
+		unsigned long def_flags;
 
-	spinlock_t arg_lock; /* protect the below fields */
-	unsigned long start_code, end_code, start_data, end_data;
-	unsigned long start_brk, brk, start_stack;
-	unsigned long arg_start, arg_end, env_start, env_end;
+		spinlock_t arg_lock; /* protect the below fields */
+		unsigned long start_code, end_code, start_data, end_data;
+		unsigned long start_brk, brk, start_stack;
+		unsigned long arg_start, arg_end, env_start, env_end;
 
-	unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
+		unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
 
-	/*
-	 * Special counters, in some configurations protected by the
-	 * page_table_lock, in other configurations by being atomic.
-	 */
-	struct mm_rss_stat rss_stat;
-
-	struct linux_binfmt *binfmt;
+		/*
+		 * Special counters, in some configurations protected by the
+		 * page_table_lock, in other configurations by being atomic.
+		 */
+		struct mm_rss_stat rss_stat;
 
-	cpumask_var_t cpu_vm_mask_var;
+		struct linux_binfmt *binfmt;
 
-	/* Architecture-specific MM context */
-	mm_context_t context;
+		/* Architecture-specific MM context */
+		mm_context_t context;
 
-	unsigned long flags; /* Must use atomic bitops to access the bits */
+		unsigned long flags; /* Must use atomic bitops to access */
 
-	struct core_state *core_state; /* coredumping support */
+		struct core_state *core_state; /* coredumping support */
 #ifdef CONFIG_MEMBARRIER
-	atomic_t membarrier_state;
+		atomic_t membarrier_state;
 #endif
 #ifdef CONFIG_AIO
-	spinlock_t			ioctx_lock;
-	struct kioctx_table __rcu	*ioctx_table;
+		spinlock_t			ioctx_lock;
+		struct kioctx_table __rcu	*ioctx_table;
 #endif
 #ifdef CONFIG_MEMCG
-	/*
-	 * "owner" points to a task that is regarded as the canonical
-	 * user/owner of this mm. All of the following must be true in
-	 * order for it to be changed:
-	 *
-	 * current == mm->owner
-	 * current->mm != mm
-	 * new_owner->mm == mm
-	 * new_owner->alloc_lock is held
-	 */
-	struct task_struct __rcu *owner;
+		/*
+		 * "owner" points to a task that is regarded as the canonical
+		 * user/owner of this mm. All of the following must be true in
+		 * order for it to be changed:
+		 *
+		 * current == mm->owner
+		 * current->mm != mm
+		 * new_owner->mm == mm
+		 * new_owner->alloc_lock is held
+		 */
+		struct task_struct __rcu *owner;
 #endif
-	struct user_namespace *user_ns;
+		struct user_namespace *user_ns;
 
-	/* store ref to file /proc/<pid>/exe symlink points to */
-	struct file __rcu *exe_file;
+		/* store ref to file /proc/<pid>/exe symlink points to */
+		struct file __rcu *exe_file;
 #ifdef CONFIG_MMU_NOTIFIER
-	struct mmu_notifier_mm *mmu_notifier_mm;
+		struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
-	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
-#endif
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	struct cpumask cpumask_allocation;
+		pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
 #ifdef CONFIG_NUMA_BALANCING
-	/*
-	 * numa_next_scan is the next time that the PTEs will be marked
-	 * pte_numa. NUMA hinting faults will gather statistics and migrate
-	 * pages to new nodes if necessary.
-	 */
-	unsigned long numa_next_scan;
+		/*
+		 * numa_next_scan is the next time that the PTEs will be marked
+		 * pte_numa. NUMA hinting faults will gather statistics and
+		 * migrate pages to new nodes if necessary.
+		 */
+		unsigned long numa_next_scan;
 
-	/* Restart point for scanning and setting pte_numa */
-	unsigned long numa_scan_offset;
+		/* Restart point for scanning and setting pte_numa */
+		unsigned long numa_scan_offset;
 
-	/* numa_scan_seq prevents two threads setting pte_numa */
-	int numa_scan_seq;
+		/* numa_scan_seq prevents two threads setting pte_numa */
+		int numa_scan_seq;
 #endif
-	/*
-	 * An operation with batched TLB flushing is going on. Anything that
-	 * can move process memory needs to flush the TLB when moving a
-	 * PROT_NONE or PROT_NUMA mapped page.
-	 */
-	atomic_t tlb_flush_pending;
+		/*
+		 * An operation with batched TLB flushing is going on. Anything
+		 * that can move process memory needs to flush the TLB when
+		 * moving a PROT_NONE or PROT_NUMA mapped page.
+		 */
+		atomic_t tlb_flush_pending;
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
-	/* See flush_tlb_batched_pending() */
-	bool tlb_flush_batched;
+		/* See flush_tlb_batched_pending() */
+		bool tlb_flush_batched;
 #endif
-	struct uprobes_state uprobes_state;
+		struct uprobes_state uprobes_state;
 #ifdef CONFIG_HUGETLB_PAGE
-	atomic_long_t hugetlb_usage;
+		atomic_long_t hugetlb_usage;
 #endif
-	struct work_struct async_put_work;
+		struct work_struct async_put_work;
 
 #if IS_ENABLED(CONFIG_HMM)
-	/* HMM needs to track a few things per mm */
-	struct hmm *hmm;
+		/* HMM needs to track a few things per mm */
+		struct hmm *hmm;
 #endif
-} __randomize_layout;
+	} __randomize_layout;
+
+	/*
+	 * The mm_cpumask needs to be at the end of mm_struct, because it
+	 * is dynamically sized based on nr_cpu_ids.
+	 */
+	unsigned long cpu_bitmap[];
+};
 
 extern struct mm_struct init_mm;
 
+/* Pointer magic because the dynamic array size confuses some compilers. */
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	mm->cpu_vm_mask_var = &mm->cpumask_allocation;
-#endif
-	cpumask_clear(mm->cpu_vm_mask_var);
+	unsigned long cpu_bitmap = (unsigned long)mm;
+
+	cpu_bitmap += offsetof(struct mm_struct, cpu_bitmap);
+	cpumask_clear((struct cpumask *)cpu_bitmap);
 }
 
 /* Future-safe accessor for struct mm_struct's cpu_vm_mask. */
 static inline cpumask_t *mm_cpumask(struct mm_struct *mm)
 {
-	return mm->cpu_vm_mask_var;
+	return (struct cpumask *)&mm->cpu_bitmap;
 }
 
 struct mmu_gather;
diff --git a/kernel/fork.c b/kernel/fork.c
index 9440d61b925c..5b64c1b8461e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2253,6 +2253,8 @@ static void sighand_ctor(void *data)
 
 void __init proc_caches_init(void)
 {
+	unsigned int mm_size;
+
 	sighand_cachep = kmem_cache_create("sighand_cache",
 			sizeof(struct sighand_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_TYPESAFE_BY_RCU|
@@ -2269,15 +2271,16 @@ void __init proc_caches_init(void)
 			sizeof(struct fs_struct), 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			NULL);
+
 	/*
-	 * FIXME! The "sizeof(struct mm_struct)" currently includes the
-	 * whole struct cpumask for the OFFSTACK case. We could change
-	 * this to *only* allocate as much of it as required by the
-	 * maximum number of CPU's we can ever have.  The cpumask_allocation
-	 * is at the end of the structure, exactly for that reason.
+	 * The mm_cpumask is located at the end of mm_struct, and is
+	 * dynamically sized based on the maximum CPU number this system
+	 * can have, taking hotplug into account (nr_cpu_ids).
 	 */
+	mm_size = sizeof(struct mm_struct) + cpumask_size();
+
 	mm_cachep = kmem_cache_create_usercopy("mm_struct",
-			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
+			mm_size, ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT,
 			offsetof(struct mm_struct, saved_auxv),
 			sizeof_field(struct mm_struct, saved_auxv),
diff --git a/mm/init-mm.c b/mm/init-mm.c
index f0179c9c04c2..a787a319211e 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -15,6 +15,16 @@
 #define INIT_MM_CONTEXT(name)
 #endif
 
+/*
+ * For dynamically allocated mm_structs, there is a dynamically sized cpumask
+ * at the end of the structure, the size of which depends on the maximum CPU
+ * number the system can see. That way we allocate only as much memory for
+ * mm_cpumask() as needed for the hundreds, or thousands of processes that
+ * a system typically runs.
+ *
+ * Since there is only one init_mm in the entire system, keep it simple
+ * and size this cpu_bitmask to NR_CPUS.
+ */
 struct mm_struct init_mm = {
 	.mm_rb		= RB_ROOT,
 	.pgd		= swapper_pg_dir,
@@ -25,5 +35,6 @@ struct mm_struct init_mm = {
 	.arg_lock	=  __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
 	.mmlist		= LIST_HEAD_INIT(init_mm.mmlist),
 	.user_ns	= &init_user_ns,
+	.cpu_bitmap	= { [BITS_TO_LONGS(NR_CPUS)] = 0},
 	INIT_MM_CONTEXT(init_mm)
 };
-- 
cgit v1.2.3


From 2ff6ddf19c0ec40633bd14d8fe28a289816bd98d Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Mon, 16 Jul 2018 15:03:32 -0400
Subject: x86/mm/tlb: Leave lazy TLB mode at page table free time

Andy discovered that speculative memory accesses while in lazy
TLB mode can crash a system, when a CPU tries to dereference a
speculative access using memory contents that used to be valid
page table memory, but have since been reused for something else
and point into la-la land.

The latter problem can be prevented in two ways. The first is to
always send a TLB shootdown IPI to CPUs in lazy TLB mode, while
the second one is to only send the TLB shootdown at page table
freeing time.

The second should result in fewer IPIs, since operationgs like
mprotect and madvise are very common with some workloads, but
do not involve page table freeing. Also, on munmap, batching
of page table freeing covers much larger ranges of virtual
memory than the batching of unmapped user pages.

Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: efault@gmx.de
Cc: kernel-team@fb.com
Cc: luto@kernel.org
Link: http://lkml.kernel.org/r/20180716190337.26133-3-riel@surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/tlbflush.h |  5 +++++
 arch/x86/mm/tlb.c               | 27 +++++++++++++++++++++++++++
 include/asm-generic/tlb.h       | 10 ++++++++++
 mm/memory.c                     | 22 ++++++++++++++--------
 4 files changed, 56 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 6690cd3fc8b1..3aa3204b5dc0 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -554,4 +554,9 @@ extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
 	native_flush_tlb_others(mask, info)
 #endif
 
+extern void tlb_flush_remove_tables(struct mm_struct *mm);
+extern void tlb_flush_remove_tables_local(void *arg);
+
+#define HAVE_TLB_FLUSH_REMOVE_TABLES
+
 #endif /* _ASM_X86_TLBFLUSH_H */
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 6eb1f34c3c85..9a893673c56b 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -646,6 +646,33 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
 	put_cpu();
 }
 
+void tlb_flush_remove_tables_local(void *arg)
+{
+	struct mm_struct *mm = arg;
+
+	if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm &&
+			this_cpu_read(cpu_tlbstate.is_lazy)) {
+		/*
+		 * We're in lazy mode.  We need to at least flush our
+		 * paging-structure cache to avoid speculatively reading
+		 * garbage into our TLB.  Since switching to init_mm is barely
+		 * slower than a minimal flush, just switch to init_mm.
+		 */
+		switch_mm_irqs_off(NULL, &init_mm, NULL);
+	}
+}
+
+void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+	int cpu = get_cpu();
+	/*
+	 * XXX: this really only needs to be called for CPUs in lazy TLB mode.
+	 */
+	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
+		smp_call_function_many(mm_cpumask(mm), tlb_flush_remove_tables_local, (void *)mm, 1);
+
+	put_cpu();
+}
 
 static void do_flush_tlb_all(void *info)
 {
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 3063125197ad..e811ef7b8350 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -303,4 +303,14 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 
 #define tlb_migrate_finish(mm) do {} while (0)
 
+/*
+ * Used to flush the TLB when page tables are removed, when lazy
+ * TLB mode may cause a CPU to retain intermediate translations
+ * pointing to about-to-be-freed page table memory.
+ */
+#ifndef HAVE_TLB_FLUSH_REMOVE_TABLES
+#define tlb_flush_remove_tables(mm) do {} while (0)
+#define tlb_flush_remove_tables_local(mm) do {} while (0)
+#endif
+
 #endif /* _ASM_GENERIC__TLB_H */
diff --git a/mm/memory.c b/mm/memory.c
index 7206a634270b..18355e0b971a 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -326,16 +326,20 @@ bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_
 
 #ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
-/*
- * See the comment near struct mmu_table_batch.
- */
-
 static void tlb_remove_table_smp_sync(void *arg)
 {
-	/* Simply deliver the interrupt */
+	struct mm_struct __maybe_unused *mm = arg;
+	/*
+	 * On most architectures this does nothing. Simply delivering the
+	 * interrupt is enough to prevent races with software page table
+	 * walking like that done in get_user_pages_fast.
+	 *
+	 * See the comment near struct mmu_table_batch.
+	 */
+	tlb_flush_remove_tables_local(mm);
 }
 
-static void tlb_remove_table_one(void *table)
+static void tlb_remove_table_one(void *table, struct mmu_gather *tlb)
 {
 	/*
 	 * This isn't an RCU grace period and hence the page-tables cannot be
@@ -344,7 +348,7 @@ static void tlb_remove_table_one(void *table)
 	 * It is however sufficient for software page-table walkers that rely on
 	 * IRQ disabling. See the comment near struct mmu_table_batch.
 	 */
-	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
+	smp_call_function(tlb_remove_table_smp_sync, tlb->mm, 1);
 	__tlb_remove_table(table);
 }
 
@@ -365,6 +369,8 @@ void tlb_table_flush(struct mmu_gather *tlb)
 {
 	struct mmu_table_batch **batch = &tlb->batch;
 
+	tlb_flush_remove_tables(tlb->mm);
+
 	if (*batch) {
 		call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu);
 		*batch = NULL;
@@ -387,7 +393,7 @@ void tlb_remove_table(struct mmu_gather *tlb, void *table)
 	if (*batch == NULL) {
 		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
 		if (*batch == NULL) {
-			tlb_remove_table_one(table);
+			tlb_remove_table_one(table, tlb);
 			return;
 		}
 		(*batch)->nr = 0;
-- 
cgit v1.2.3


From 61d0beb5796ab11f7f3bf38cb2eccc6579aaa70b Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Mon, 16 Jul 2018 15:03:33 -0400
Subject: x86/mm/tlb: Restructure switch_mm_irqs_off()

Move some code that will be needed for the lazy -> !lazy state
transition when a lazy TLB CPU has gotten out of date.

No functional changes, since the if (real_prev == next) branch
always returns.

Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: efault@gmx.de
Cc: kernel-team@fb.com
Link: http://lkml.kernel.org/r/20180716190337.26133-4-riel@surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/mm/tlb.c | 60 +++++++++++++++++++++++++++----------------------------
 1 file changed, 30 insertions(+), 30 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 9a893673c56b..4b73fe835c95 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -187,6 +187,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
 	unsigned cpu = smp_processor_id();
 	u64 next_tlb_gen;
+	bool need_flush;
+	u16 new_asid;
 
 	/*
 	 * NB: The scheduler will call us with prev == next when switching
@@ -252,8 +254,6 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 
 		return;
 	} else {
-		u16 new_asid;
-		bool need_flush;
 		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
 
 		/*
@@ -297,41 +297,41 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+	}
 
-		if (need_flush) {
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
-			this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
-			load_new_mm_cr3(next->pgd, new_asid, true);
-
-			/*
-			 * NB: This gets called via leave_mm() in the idle path
-			 * where RCU functions differently.  Tracing normally
-			 * uses RCU, so we need to use the _rcuidle variant.
-			 *
-			 * (There is no good reason for this.  The idle code should
-			 *  be rearranged to call this before rcu_idle_enter().)
-			 */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
-		} else {
-			/* The new ASID is already up to date. */
-			load_new_mm_cr3(next->pgd, new_asid, false);
-
-			/* See above wrt _rcuidle. */
-			trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
-		}
+	if (need_flush) {
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
+		this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
+		load_new_mm_cr3(next->pgd, new_asid, true);
 
 		/*
-		 * Record last user mm's context id, so we can avoid
-		 * flushing branch buffer with IBPB if we switch back
-		 * to the same user.
+		 * NB: This gets called via leave_mm() in the idle path
+		 * where RCU functions differently.  Tracing normally
+		 * uses RCU, so we need to use the _rcuidle variant.
+		 *
+		 * (There is no good reason for this.  The idle code should
+		 *  be rearranged to call this before rcu_idle_enter().)
 		 */
-		if (next != &init_mm)
-			this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
+	} else {
+		/* The new ASID is already up to date. */
+		load_new_mm_cr3(next->pgd, new_asid, false);
 
-		this_cpu_write(cpu_tlbstate.loaded_mm, next);
-		this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+		/* See above wrt _rcuidle. */
+		trace_tlb_flush_rcuidle(TLB_FLUSH_ON_TASK_SWITCH, 0);
 	}
 
+	/*
+	 * Record last user mm's context id, so we can avoid
+	 * flushing branch buffer with IBPB if we switch back
+	 * to the same user.
+	 */
+	if (next != &init_mm)
+		this_cpu_write(cpu_tlbstate.last_ctx_id, next->context.ctx_id);
+
+	this_cpu_write(cpu_tlbstate.loaded_mm, next);
+	this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+
 	load_mm_cr4(next);
 	switch_ldt(real_prev, next);
 }
-- 
cgit v1.2.3


From ac0315896970d8589291e9d8a1569fc65967b7f1 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Mon, 16 Jul 2018 15:03:34 -0400
Subject: x86/mm/tlb: Make lazy TLB mode lazier

Lazy TLB mode can result in an idle CPU being woken up by a TLB flush,
when all it really needs to do is reload %CR3 at the next context switch,
assuming no page table pages got freed.

Memory ordering is used to prevent race conditions between switch_mm_irqs_off,
which checks whether .tlb_gen changed, and the TLB invalidation code, which
increments .tlb_gen whenever page table entries get invalidated.

The atomic increment in inc_mm_tlb_gen is its own barrier; the context
switch code adds an explicit barrier between reading tlbstate.is_lazy and
next->context.tlb_gen.

Unlike the 2016 version of this patch, CPUs with cpu_tlbstate.is_lazy set
are not removed from the mm_cpumask(mm), since that would prevent the TLB
flush IPIs at page table free time from being sent to all the CPUs
that need them.

This patch reduces total CPU use in the system by about 1-2% for a
memcache workload on two socket systems, and by about 1% for a heavily
multi-process netperf between two systems.

Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: efault@gmx.de
Cc: kernel-team@fb.com
Cc: luto@kernel.org
Link: http://lkml.kernel.org/r/20180716190337.26133-5-riel@surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/mm/tlb.c | 68 +++++++++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 59 insertions(+), 9 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 4b73fe835c95..26542cc17043 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/cpu.h>
 #include <linux/debugfs.h>
+#include <linux/gfp.h>
 
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
@@ -185,6 +186,7 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 {
 	struct mm_struct *real_prev = this_cpu_read(cpu_tlbstate.loaded_mm);
 	u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+	bool was_lazy = this_cpu_read(cpu_tlbstate.is_lazy);
 	unsigned cpu = smp_processor_id();
 	u64 next_tlb_gen;
 	bool need_flush;
@@ -242,17 +244,40 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			   next->context.ctx_id);
 
 		/*
-		 * We don't currently support having a real mm loaded without
-		 * our cpu set in mm_cpumask().  We have all the bookkeeping
-		 * in place to figure out whether we would need to flush
-		 * if our cpu were cleared in mm_cpumask(), but we don't
-		 * currently use it.
+		 * Even in lazy TLB mode, the CPU should stay set in the
+		 * mm_cpumask. The TLB shootdown code can figure out from
+		 * from cpu_tlbstate.is_lazy whether or not to send an IPI.
 		 */
 		if (WARN_ON_ONCE(real_prev != &init_mm &&
 				 !cpumask_test_cpu(cpu, mm_cpumask(next))))
 			cpumask_set_cpu(cpu, mm_cpumask(next));
 
-		return;
+		/*
+		 * If the CPU is not in lazy TLB mode, we are just switching
+		 * from one thread in a process to another thread in the same
+		 * process. No TLB flush required.
+		 */
+		if (!was_lazy)
+			return;
+
+		/*
+		 * Read the tlb_gen to check whether a flush is needed.
+		 * If the TLB is up to date, just use it.
+		 * The barrier synchronizes with the tlb_gen increment in
+		 * the TLB shootdown code.
+		 */
+		smp_mb();
+		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+		if (this_cpu_read(cpu_tlbstate.ctxs[prev_asid].tlb_gen) ==
+				next_tlb_gen)
+			return;
+
+		/*
+		 * TLB contents went out of date while we were in lazy
+		 * mode. Fall through to the TLB switching code below.
+		 */
+		new_asid = prev_asid;
+		need_flush = true;
 	} else {
 		u64 last_ctx_id = this_cpu_read(cpu_tlbstate.last_ctx_id);
 
@@ -454,6 +479,9 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f,
 		 * paging-structure cache to avoid speculatively reading
 		 * garbage into our TLB.  Since switching to init_mm is barely
 		 * slower than a minimal flush, just switch to init_mm.
+		 *
+		 * This should be rare, with native_flush_tlb_others skipping
+		 * IPIs to lazy TLB mode CPUs.
 		 */
 		switch_mm_irqs_off(NULL, &init_mm, NULL);
 		return;
@@ -560,6 +588,9 @@ static void flush_tlb_func_remote(void *info)
 void native_flush_tlb_others(const struct cpumask *cpumask,
 			     const struct flush_tlb_info *info)
 {
+	cpumask_var_t lazymask;
+	unsigned int cpu;
+
 	count_vm_tlb_event(NR_TLB_REMOTE_FLUSH);
 	if (info->end == TLB_FLUSH_ALL)
 		trace_tlb_flush(TLB_REMOTE_SEND_IPI, TLB_FLUSH_ALL);
@@ -583,8 +614,6 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 		 * that UV should be updated so that smp_call_function_many(),
 		 * etc, are optimal on UV.
 		 */
-		unsigned int cpu;
-
 		cpu = smp_processor_id();
 		cpumask = uv_flush_tlb_others(cpumask, info);
 		if (cpumask)
@@ -592,8 +621,29 @@ void native_flush_tlb_others(const struct cpumask *cpumask,
 					       (void *)info, 1);
 		return;
 	}
-	smp_call_function_many(cpumask, flush_tlb_func_remote,
+
+	/*
+	 * A temporary cpumask is used in order to skip sending IPIs
+	 * to CPUs in lazy TLB state, while keeping them in mm_cpumask(mm).
+	 * If the allocation fails, simply IPI every CPU in mm_cpumask.
+	 */
+	if (!alloc_cpumask_var(&lazymask, GFP_ATOMIC)) {
+		smp_call_function_many(cpumask, flush_tlb_func_remote,
+			       (void *)info, 1);
+		return;
+	}
+
+	cpumask_copy(lazymask, cpumask);
+
+	for_each_cpu(cpu, lazymask) {
+		if (per_cpu(cpu_tlbstate.is_lazy, cpu))
+			cpumask_clear_cpu(cpu, lazymask);
+	}
+
+	smp_call_function_many(lazymask, flush_tlb_func_remote,
 			       (void *)info, 1);
+
+	free_cpumask_var(lazymask);
 }
 
 /*
-- 
cgit v1.2.3


From 64482aafe55fc7e84d0741c356f8176ee7bde357 Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Mon, 16 Jul 2018 15:03:35 -0400
Subject: x86/mm/tlb: Only send page table free TLB flush to lazy TLB CPUs

CPUs in !is_lazy have either received TLB flush IPIs earlier on during
the munmap (when the user memory was unmapped), or have context switched
and reloaded during that stage of the munmap.

Page table free TLB flushes only need to be sent to CPUs in lazy TLB
mode, which TLB contents might not yet be up to date yet.

Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: efault@gmx.de
Cc: kernel-team@fb.com
Cc: luto@kernel.org
Link: http://lkml.kernel.org/r/20180716190337.26133-6-riel@surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/mm/tlb.c | 43 +++++++++++++++++++++++++++++++++++++++----
 1 file changed, 39 insertions(+), 4 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 26542cc17043..e4156e37aa71 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -712,15 +712,50 @@ void tlb_flush_remove_tables_local(void *arg)
 	}
 }
 
+static void mm_fill_lazy_tlb_cpu_mask(struct mm_struct *mm,
+				      struct cpumask *lazy_cpus)
+{
+	int cpu;
+
+	for_each_cpu(cpu, mm_cpumask(mm)) {
+		if (!per_cpu(cpu_tlbstate.is_lazy, cpu))
+			cpumask_set_cpu(cpu, lazy_cpus);
+	}
+}
+
 void tlb_flush_remove_tables(struct mm_struct *mm)
 {
 	int cpu = get_cpu();
+	cpumask_var_t lazy_cpus;
+
+	if (cpumask_any_but(mm_cpumask(mm), cpu) >= nr_cpu_ids) {
+		put_cpu();
+		return;
+	}
+
+	if (!zalloc_cpumask_var(&lazy_cpus, GFP_ATOMIC)) {
+		/*
+		 * If the cpumask allocation fails, do a brute force flush
+		 * on all the CPUs that have this mm loaded.
+		 */
+		smp_call_function_many(mm_cpumask(mm),
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+		put_cpu();
+		return;
+	}
+
 	/*
-	 * XXX: this really only needs to be called for CPUs in lazy TLB mode.
+	 * CPUs with !is_lazy either received a TLB flush IPI while the user
+	 * pages in this address range were unmapped, or have context switched
+	 * and reloaded %CR3 since then.
+	 *
+	 * Shootdown IPIs at page table freeing time only need to be sent to
+	 * CPUs that may have out of date TLB contents.
 	 */
-	if (cpumask_any_but(mm_cpumask(mm), cpu) < nr_cpu_ids)
-		smp_call_function_many(mm_cpumask(mm), tlb_flush_remove_tables_local, (void *)mm, 1);
-
+	mm_fill_lazy_tlb_cpu_mask(mm, lazy_cpus);
+	smp_call_function_many(lazy_cpus,
+				tlb_flush_remove_tables_local, (void *)mm, 1);
+	free_cpumask_var(lazy_cpus);
 	put_cpu();
 }
 
-- 
cgit v1.2.3


From 95b0e6357d3e4e05349668940d7ff8f3b7e7e11e Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Mon, 16 Jul 2018 15:03:36 -0400
Subject: x86/mm/tlb: Always use lazy TLB mode

Now that CPUs in lazy TLB mode no longer receive TLB shootdown IPIs, except
at page table freeing time, and idle CPUs will no longer get shootdown IPIs
for things like mprotect and madvise, we can always use lazy TLB mode.

Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: efault@gmx.de
Cc: kernel-team@fb.com
Cc: luto@kernel.org
Link: http://lkml.kernel.org/r/20180716190337.26133-7-riel@surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/tlbflush.h | 16 ----------------
 arch/x86/mm/tlb.c               | 15 +--------------
 2 files changed, 1 insertion(+), 30 deletions(-)

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 3aa3204b5dc0..511bf5fae8b8 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -148,22 +148,6 @@ static inline unsigned long build_cr3_noflush(pgd_t *pgd, u16 asid)
 #define __flush_tlb_one_user(addr) __native_flush_tlb_one_user(addr)
 #endif
 
-static inline bool tlb_defer_switch_to_init_mm(void)
-{
-	/*
-	 * If we have PCID, then switching to init_mm is reasonably
-	 * fast.  If we don't have PCID, then switching to init_mm is
-	 * quite slow, so we try to defer it in the hopes that we can
-	 * avoid it entirely.  The latter approach runs the risk of
-	 * receiving otherwise unnecessary IPIs.
-	 *
-	 * This choice is just a heuristic.  The tlb code can handle this
-	 * function returning true or false regardless of whether we have
-	 * PCID.
-	 */
-	return !static_cpu_has(X86_FEATURE_PCID);
-}
-
 struct tlb_context {
 	u64 ctx_id;
 	u64 tlb_gen;
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index e4156e37aa71..493559cae2d5 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -379,20 +379,7 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 	if (this_cpu_read(cpu_tlbstate.loaded_mm) == &init_mm)
 		return;
 
-	if (tlb_defer_switch_to_init_mm()) {
-		/*
-		 * There's a significant optimization that may be possible
-		 * here.  We have accurate enough TLB flush tracking that we
-		 * don't need to maintain coherence of TLB per se when we're
-		 * lazy.  We do, however, need to maintain coherence of
-		 * paging-structure caches.  We could, in principle, leave our
-		 * old mm loaded and only switch to init_mm when
-		 * tlb_remove_page() happens.
-		 */
-		this_cpu_write(cpu_tlbstate.is_lazy, true);
-	} else {
-		switch_mm(NULL, &init_mm, NULL);
-	}
+	this_cpu_write(cpu_tlbstate.is_lazy, true);
 }
 
 /*
-- 
cgit v1.2.3


From e9d8c61557687b7126101e9550bdf243223f0d8f Mon Sep 17 00:00:00 2001
From: Rik van Riel <riel@surriel.com>
Date: Mon, 16 Jul 2018 15:03:37 -0400
Subject: x86/mm/tlb: Skip atomic operations for 'init_mm' in
 switch_mm_irqs_off()

Song Liu noticed switch_mm_irqs_off() taking a lot of CPU time in recent
kernels,using 1.8% of a 48 CPU system during a netperf to localhost run.
Digging into the profile, we noticed that cpumask_clear_cpu and
cpumask_set_cpu together take about half of the CPU time taken by
switch_mm_irqs_off().

However, the CPUs running netperf end up switching back and forth
between netperf and the idle task, which does not require changes
to the mm_cpumask. Furthermore, the init_mm cpumask ends up being
the most heavily contended one in the system.

Simply skipping changes to mm_cpumask(&init_mm) reduces overhead.

Reported-and-tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Rik van Riel <riel@surriel.com>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: efault@gmx.de
Cc: kernel-team@fb.com
Cc: luto@kernel.org
Link: http://lkml.kernel.org/r/20180716190337.26133-8-riel@surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/mm/tlb.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 493559cae2d5..f086195f644c 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -310,15 +310,22 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
 			sync_current_stack_to_mm(next);
 		}
 
-		/* Stop remote flushes for the previous mm */
-		VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu, mm_cpumask(real_prev)) &&
-				real_prev != &init_mm);
-		cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+		/*
+		 * Stop remote flushes for the previous mm.
+		 * Skip kernel threads; we never send init_mm TLB flushing IPIs,
+		 * but the bitmap manipulation can cause cache line contention.
+		 */
+		if (real_prev != &init_mm) {
+			VM_WARN_ON_ONCE(!cpumask_test_cpu(cpu,
+						mm_cpumask(real_prev)));
+			cpumask_clear_cpu(cpu, mm_cpumask(real_prev));
+		}
 
 		/*
 		 * Start remote flushes and then read tlb_gen.
 		 */
-		cpumask_set_cpu(cpu, mm_cpumask(next));
+		if (next != &init_mm)
+			cpumask_set_cpu(cpu, mm_cpumask(next));
 		next_tlb_gen = atomic64_read(&next->context.tlb_gen);
 
 		choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
-- 
cgit v1.2.3


From a203728ac6bbbed2fdcf0a2e807c5473efcfdb30 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 5 Jul 2018 02:10:14 -0700
Subject: pinctrl: core: Return selector to the pinctrl driver

We must return the selector from pinctrl_generic_add_group() so
pin controller device drivers can remove the right group if needed
for deferred probe for example. And we now must make sure that a
proper name is passed so we can use it to check if the entry already
exists.

Note that fixes are also needed for the pin controller drivers to
use the selector value.

Fixes: c7059c5ac70a ("pinctrl: core: Add generic pinctrl functions
for managing groups")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Cc: Christ van Willegen <cvwillegen@gmail.com>
Cc: Haojian Zhuang <haojian.zhuang@linaro.org>
Cc: Jacopo Mondi <jacopo+renesas@jmondi.org>
Cc: Paul Cercueil <paul@crapouillou.net>
Cc: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Tested-By: H. Nikolaus Schaller <hns@goldelico.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c | 35 ++++++++++++++++++++++++++++++++---
 1 file changed, 32 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 9fa6c1608b80..a3dd777e3ce8 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -616,6 +616,26 @@ struct group_desc *pinctrl_generic_get_group(struct pinctrl_dev *pctldev,
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_get_group);
 
+static int pinctrl_generic_group_name_to_selector(struct pinctrl_dev *pctldev,
+						  const char *function)
+{
+	const struct pinctrl_ops *ops = pctldev->desc->pctlops;
+	int ngroups = ops->get_groups_count(pctldev);
+	int selector = 0;
+
+	/* See if this pctldev has this group */
+	while (selector < ngroups) {
+		const char *gname = ops->get_group_name(pctldev, selector);
+
+		if (!strcmp(function, gname))
+			return selector;
+
+		selector++;
+	}
+
+	return -EINVAL;
+}
+
 /**
  * pinctrl_generic_add_group() - adds a new pin group
  * @pctldev: pin controller device
@@ -630,6 +650,16 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 			      int *pins, int num_pins, void *data)
 {
 	struct group_desc *group;
+	int selector;
+
+	if (!name)
+		return -EINVAL;
+
+	selector = pinctrl_generic_group_name_to_selector(pctldev, name);
+	if (selector >= 0)
+		return selector;
+
+	selector = pctldev->num_groups;
 
 	group = devm_kzalloc(pctldev->dev, sizeof(*group), GFP_KERNEL);
 	if (!group)
@@ -640,12 +670,11 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 	group->num_pins = num_pins;
 	group->data = data;
 
-	radix_tree_insert(&pctldev->pin_group_tree, pctldev->num_groups,
-			  group);
+	radix_tree_insert(&pctldev->pin_group_tree, selector, group);
 
 	pctldev->num_groups++;
 
-	return 0;
+	return selector;
 }
 EXPORT_SYMBOL_GPL(pinctrl_generic_add_group);
 
-- 
cgit v1.2.3


From f913cfce4ee49a3382a9ff95696f49a46e56e974 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 5 Jul 2018 02:10:15 -0700
Subject: pinctrl: pinmux: Return selector to the pinctrl driver

We must return the selector from pinmux_generic_add_function() so
pin controller device drivers can remove the right group if needed
for deferred probe for example. And we now must make sure that a
proper name is passed so we can use it to check if the entry already
exists.

Note that fixes are also needed for the pin controller drivers to
use the selector value.

Fixes: a76edc89b100 ("pinctrl: core: Add generic pinctrl functions for
managing groups")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Cc: Christ van Willegen <cvwillegen@gmail.com>
Cc: Haojian Zhuang <haojian.zhuang@linaro.org>
Cc: Jacopo Mondi <jacopo+renesas@jmondi.org>
Cc: Paul Cercueil <paul@crapouillou.net>
Cc: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Tested-By: H. Nikolaus Schaller <hns@goldelico.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinmux.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index d7c5b4abd741..5780442c068b 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -307,7 +307,6 @@ static int pinmux_func_name_to_selector(struct pinctrl_dev *pctldev,
 		selector++;
 	}
 
-	dev_err(pctldev->dev, "function '%s' not supported\n", function);
 	return -EINVAL;
 }
 
@@ -774,6 +773,16 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 				void *data)
 {
 	struct function_desc *function;
+	int selector;
+
+	if (!name)
+		return -EINVAL;
+
+	selector = pinmux_func_name_to_selector(pctldev, name);
+	if (selector >= 0)
+		return selector;
+
+	selector = pctldev->num_functions;
 
 	function = devm_kzalloc(pctldev->dev, sizeof(*function), GFP_KERNEL);
 	if (!function)
@@ -784,12 +793,11 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 	function->num_group_names = num_groups;
 	function->data = data;
 
-	radix_tree_insert(&pctldev->pin_function_tree, pctldev->num_functions,
-			  function);
+	radix_tree_insert(&pctldev->pin_function_tree, selector, function);
 
 	pctldev->num_functions++;
 
-	return 0;
+	return selector;
 }
 EXPORT_SYMBOL_GPL(pinmux_generic_add_function);
 
-- 
cgit v1.2.3


From a4ab1086072365235864151bca57230afa8bcc93 Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 5 Jul 2018 02:10:16 -0700
Subject: pinctrl: single: Fix group and function selector use

We must use a mutex around the generic_add functions and save the
function and group selector in case we need to remove them. Otherwise
the selector use will be racy for deferred probe at least.

Note that struct device_node *np is unused in pcs_add_function() we
remove that too and fix a checkpatch warning for bare unsigned while
at it.

Fixes: 571aec4df5b7 ("pinctrl: single: Use generic pinmux helpers for
managing functions")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Cc: Christ van Willegen <cvwillegen@gmail.com>
Cc: Haojian Zhuang <haojian.zhuang@linaro.org>
Cc: Jacopo Mondi <jacopo+renesas@jmondi.org>
Cc: Paul Cercueil <paul@crapouillou.net>
Cc: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Tested-By: H. Nikolaus Schaller <hns@goldelico.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-single.c | 91 ++++++++++++++++++++++++----------------
 1 file changed, 55 insertions(+), 36 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 92b694675a56..42d7e76baccf 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -747,38 +747,44 @@ static int pcs_allocate_pin_table(struct pcs_device *pcs)
 /**
  * pcs_add_function() - adds a new function to the function list
  * @pcs: pcs driver instance
- * @np: device node of the mux entry
+ * @fcn: new function allocated
  * @name: name of the function
  * @vals: array of mux register value pairs used by the function
  * @nvals: number of mux register value pairs
  * @pgnames: array of pingroup names for the function
  * @npgnames: number of pingroup names
+ *
+ * Caller must take care of locking.
  */
-static struct pcs_function *pcs_add_function(struct pcs_device *pcs,
-					struct device_node *np,
-					const char *name,
-					struct pcs_func_vals *vals,
-					unsigned nvals,
-					const char **pgnames,
-					unsigned npgnames)
+static int pcs_add_function(struct pcs_device *pcs,
+			    struct pcs_function **fcn,
+			    const char *name,
+			    struct pcs_func_vals *vals,
+			    unsigned int nvals,
+			    const char **pgnames,
+			    unsigned int npgnames)
 {
 	struct pcs_function *function;
-	int res;
+	int selector;
 
 	function = devm_kzalloc(pcs->dev, sizeof(*function), GFP_KERNEL);
 	if (!function)
-		return NULL;
+		return -ENOMEM;
 
 	function->vals = vals;
 	function->nvals = nvals;
 
-	res = pinmux_generic_add_function(pcs->pctl, name,
-					  pgnames, npgnames,
-					  function);
-	if (res)
-		return NULL;
+	selector = pinmux_generic_add_function(pcs->pctl, name,
+					       pgnames, npgnames,
+					       function);
+	if (selector < 0) {
+		devm_kfree(pcs->dev, function);
+		*fcn = NULL;
+	} else {
+		*fcn = function;
+	}
 
-	return function;
+	return selector;
 }
 
 /**
@@ -979,8 +985,8 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 {
 	const char *name = "pinctrl-single,pins";
 	struct pcs_func_vals *vals;
-	int rows, *pins, found = 0, res = -ENOMEM, i;
-	struct pcs_function *function;
+	int rows, *pins, found = 0, res = -ENOMEM, i, fsel, gsel;
+	struct pcs_function *function = NULL;
 
 	rows = pinctrl_count_index_with_args(np, name);
 	if (rows <= 0) {
@@ -1030,21 +1036,25 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	pgnames[0] = np->name;
-	function = pcs_add_function(pcs, np, np->name, vals, found, pgnames, 1);
-	if (!function) {
-		res = -ENOMEM;
+	mutex_lock(&pcs->mutex);
+	fsel = pcs_add_function(pcs, &function, np->name, vals, found,
+				pgnames, 1);
+	if (fsel < 0) {
+		res = fsel;
 		goto free_pins;
 	}
 
-	res = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
-	if (res < 0)
+	gsel = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
+	if (gsel < 0) {
+		res = gsel;
 		goto free_function;
+	}
 
 	(*map)->type = PIN_MAP_TYPE_MUX_GROUP;
 	(*map)->data.mux.group = np->name;
 	(*map)->data.mux.function = np->name;
 
-	if (PCS_HAS_PINCONF) {
+	if (PCS_HAS_PINCONF && function) {
 		res = pcs_parse_pinconf(pcs, np, function, map);
 		if (res)
 			goto free_pingroups;
@@ -1052,14 +1062,16 @@ static int pcs_parse_one_pinctrl_entry(struct pcs_device *pcs,
 	} else {
 		*num_maps = 1;
 	}
+	mutex_unlock(&pcs->mutex);
+
 	return 0;
 
 free_pingroups:
-	pinctrl_generic_remove_last_group(pcs->pctl);
+	pinctrl_generic_remove_group(pcs->pctl, gsel);
 	*num_maps = 1;
 free_function:
-	pinmux_generic_remove_last_function(pcs->pctl);
-
+	pinmux_generic_remove_function(pcs->pctl, fsel);
+	mutex_unlock(&pcs->mutex);
 free_pins:
 	devm_kfree(pcs->dev, pins);
 
@@ -1077,9 +1089,9 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 {
 	const char *name = "pinctrl-single,bits";
 	struct pcs_func_vals *vals;
-	int rows, *pins, found = 0, res = -ENOMEM, i;
+	int rows, *pins, found = 0, res = -ENOMEM, i, fsel, gsel;
 	int npins_in_row;
-	struct pcs_function *function;
+	struct pcs_function *function = NULL;
 
 	rows = pinctrl_count_index_with_args(np, name);
 	if (rows <= 0) {
@@ -1166,15 +1178,19 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	pgnames[0] = np->name;
-	function = pcs_add_function(pcs, np, np->name, vals, found, pgnames, 1);
-	if (!function) {
-		res = -ENOMEM;
+	mutex_lock(&pcs->mutex);
+	fsel = pcs_add_function(pcs, &function, np->name, vals, found,
+				pgnames, 1);
+	if (fsel < 0) {
+		res = fsel;
 		goto free_pins;
 	}
 
-	res = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
-	if (res < 0)
+	gsel = pinctrl_generic_add_group(pcs->pctl, np->name, pins, found, pcs);
+	if (gsel < 0) {
+		res = gsel;
 		goto free_function;
+	}
 
 	(*map)->type = PIN_MAP_TYPE_MUX_GROUP;
 	(*map)->data.mux.group = np->name;
@@ -1186,13 +1202,16 @@ static int pcs_parse_bits_in_pinctrl_entry(struct pcs_device *pcs,
 	}
 
 	*num_maps = 1;
+	mutex_unlock(&pcs->mutex);
+
 	return 0;
 
 free_pingroups:
-	pinctrl_generic_remove_last_group(pcs->pctl);
+	pinctrl_generic_remove_group(pcs->pctl, gsel);
 	*num_maps = 1;
 free_function:
-	pinmux_generic_remove_last_function(pcs->pctl);
+	pinmux_generic_remove_function(pcs->pctl, fsel);
+	mutex_unlock(&pcs->mutex);
 free_pins:
 	devm_kfree(pcs->dev, pins);
 
-- 
cgit v1.2.3


From dc4003d260594aa300028c3c5d040c5719abd19b Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 5 Jul 2018 02:10:17 -0700
Subject: pinctrl: rza1: Fix selector use for groups and functions

We must use a mutex around the generic_add functions and save the
function and group selector in case we need to remove them. Otherwise
the selector use will be racy for deferred probe at least.

Fixes: 5a49b644b307 ("pinctrl: Renesas RZ/A1 pin and gpio controller")
Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Cc: Christ van Willegen <cvwillegen@gmail.com>
Cc: Haojian Zhuang <haojian.zhuang@linaro.org>
Cc: Paul Cercueil <paul@crapouillou.net>
Cc: Sean Wang <sean.wang@mediatek.com>
Acked-by: Jacopo Mondi <jacopo@jmondi.org>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Tested-By: H. Nikolaus Schaller <hns@goldelico.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-rza1.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-rza1.c b/drivers/pinctrl/pinctrl-rza1.c
index 717c0f4449a0..f76edf664539 100644
--- a/drivers/pinctrl/pinctrl-rza1.c
+++ b/drivers/pinctrl/pinctrl-rza1.c
@@ -1006,6 +1006,7 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	const char *grpname;
 	const char **fngrps;
 	int ret, npins;
+	int gsel, fsel;
 
 	npins = rza1_dt_node_pin_count(np);
 	if (npins < 0) {
@@ -1055,18 +1056,19 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	fngrps[0] = grpname;
 
 	mutex_lock(&rza1_pctl->mutex);
-	ret = pinctrl_generic_add_group(pctldev, grpname, grpins, npins,
-					NULL);
-	if (ret) {
+	gsel = pinctrl_generic_add_group(pctldev, grpname, grpins, npins,
+					 NULL);
+	if (gsel < 0) {
 		mutex_unlock(&rza1_pctl->mutex);
-		return ret;
+		return gsel;
 	}
 
-	ret = pinmux_generic_add_function(pctldev, grpname, fngrps, 1,
-					  mux_confs);
-	if (ret)
+	fsel = pinmux_generic_add_function(pctldev, grpname, fngrps, 1,
+					   mux_confs);
+	if (fsel < 0) {
+		ret = fsel;
 		goto remove_group;
-	mutex_unlock(&rza1_pctl->mutex);
+	}
 
 	dev_info(rza1_pctl->dev, "Parsed function and group %s with %d pins\n",
 				 grpname, npins);
@@ -1083,15 +1085,15 @@ static int rza1_dt_node_to_map(struct pinctrl_dev *pctldev,
 	(*map)->data.mux.group = np->name;
 	(*map)->data.mux.function = np->name;
 	*num_maps = 1;
+	mutex_unlock(&rza1_pctl->mutex);
 
 	return 0;
 
 remove_function:
-	mutex_lock(&rza1_pctl->mutex);
-	pinmux_generic_remove_last_function(pctldev);
+	pinmux_generic_remove_function(pctldev, fsel);
 
 remove_group:
-	pinctrl_generic_remove_last_group(pctldev);
+	pinctrl_generic_remove_group(pctldev, gsel);
 	mutex_unlock(&rza1_pctl->mutex);
 
 	dev_info(rza1_pctl->dev, "Unable to parse function and group %s\n",
-- 
cgit v1.2.3


From 93639058b2af462a9871159be1afe60eab59431e Mon Sep 17 00:00:00 2001
From: Tony Lindgren <tony@atomide.com>
Date: Thu, 5 Jul 2018 02:10:18 -0700
Subject: pinctrl: core: Remove broken remove_last group and pinmux functions

With no users left for these functions let's remove them.

Reported-by: H. Nikolaus Schaller <hns@goldelico.com>
Cc: Christ van Willegen <cvwillegen@gmail.com>
Cc: Haojian Zhuang <haojian.zhuang@linaro.org>
Cc: Jacopo Mondi <jacopo+renesas@jmondi.org>
Cc: Paul Cercueil <paul@crapouillou.net>
Cc: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Tony Lindgren <tony@atomide.com>
Tested-By: H. Nikolaus Schaller <hns@goldelico.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.h   | 6 ------
 drivers/pinctrl/pinmux.h | 7 -------
 2 files changed, 13 deletions(-)

diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index 8cf2eba17c8c..4a0526e567df 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -218,12 +218,6 @@ int pinctrl_generic_add_group(struct pinctrl_dev *pctldev, const char *name,
 int pinctrl_generic_remove_group(struct pinctrl_dev *pctldev,
 				 unsigned int group_selector);
 
-static inline int
-pinctrl_generic_remove_last_group(struct pinctrl_dev *pctldev)
-{
-	return pinctrl_generic_remove_group(pctldev, pctldev->num_groups - 1);
-}
-
 #endif	/* CONFIG_GENERIC_PINCTRL_GROUPS */
 
 struct pinctrl_dev *get_pinctrl_dev_from_devname(const char *dev_name);
diff --git a/drivers/pinctrl/pinmux.h b/drivers/pinctrl/pinmux.h
index a331fcdbedd9..3319535c76cb 100644
--- a/drivers/pinctrl/pinmux.h
+++ b/drivers/pinctrl/pinmux.h
@@ -150,13 +150,6 @@ int pinmux_generic_add_function(struct pinctrl_dev *pctldev,
 int pinmux_generic_remove_function(struct pinctrl_dev *pctldev,
 				   unsigned int selector);
 
-static inline int
-pinmux_generic_remove_last_function(struct pinctrl_dev *pctldev)
-{
-	return pinmux_generic_remove_function(pctldev,
-					      pctldev->num_functions - 1);
-}
-
 void pinmux_generic_free_functions(struct pinctrl_dev *pctldev);
 
 #else
-- 
cgit v1.2.3


From 673ba5a05ca14c2ddef038044768a4acd0ae0a53 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 11 Jul 2018 12:33:31 +0000
Subject: pinctrl: single: Fix missing unlock on error path

Add the missing unlock before return from function
in the error handling case.

Fixes: 0f5972033509 ("pinctrl: single: Fix group and function selector use")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Tony Lindgren <tony@atomide.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-single.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index 42d7e76baccf..9fa2f54bb1a3 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1071,8 +1071,8 @@ free_pingroups:
 	*num_maps = 1;
 free_function:
 	pinmux_generic_remove_function(pcs->pctl, fsel);
-	mutex_unlock(&pcs->mutex);
 free_pins:
+	mutex_unlock(&pcs->mutex);
 	devm_kfree(pcs->dev, pins);
 
 free_vals:
@@ -1211,8 +1211,8 @@ free_pingroups:
 	*num_maps = 1;
 free_function:
 	pinmux_generic_remove_function(pcs->pctl, fsel);
-	mutex_unlock(&pcs->mutex);
 free_pins:
+	mutex_unlock(&pcs->mutex);
 	devm_kfree(pcs->dev, pins);
 
 free_vals:
-- 
cgit v1.2.3


From 238262af08a20e5f1932fcf606b8b84370ac8b77 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Thu, 12 Jul 2018 13:50:00 +0800
Subject: pinctrl: mt7622: Fix probe fail by misuse the selector

After the commit acf137951367 ("pinctrl: core: Return selector to the
pinctrl driver") and the commit 47f1242d19c3 ("pinctrl: pinmux: Return
selector to the pinctrl driver"), it's necessary to add the fixes
needed for the pin controller drivers to use the appropriate returned
selector for a negative error number returned in case of the fail at
these functions. Otherwise, the driver would have a failed probe and
that causes boot message cannot correctly output and devices fail
to acquire their own pins.

Cc: Kevin Hilman <khilman@baylibre.com>
Fixes: acf137951367 ("pinctrl: core: Return selector to the pinctrl driver")
Fixes: 47f1242d19c3 ("pinctrl: pinmux: Return selector to the pinctrl driver")
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/pinctrl-mt7622.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/mediatek/pinctrl-mt7622.c b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
index b8df7ad87cf4..26bc13bda09b 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mt7622.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mt7622.c
@@ -1525,7 +1525,7 @@ static int mtk_build_groups(struct mtk_pinctrl *hw)
 		err = pinctrl_generic_add_group(hw->pctrl, group->name,
 						group->pins, group->num_pins,
 						group->data);
-		if (err) {
+		if (err < 0) {
 			dev_err(hw->dev, "Failed to register group %s\n",
 				group->name);
 			return err;
@@ -1546,7 +1546,7 @@ static int mtk_build_functions(struct mtk_pinctrl *hw)
 						  func->group_names,
 						  func->num_group_names,
 						  func->data);
-		if (err) {
+		if (err < 0) {
 			dev_err(hw->dev, "Failed to register function %s\n",
 				func->name);
 			return err;
-- 
cgit v1.2.3


From 4aaf448fa9754e2d5ee188d32327b24ffc15ca4d Mon Sep 17 00:00:00 2001
From: Jim Qu <Jim.Qu@amd.com>
Date: Tue, 17 Jul 2018 16:20:50 +0800
Subject: vga_switcheroo: set audio client id according to bound GPU id

On modern laptop, there are more and more platforms
have two GPUs, and each of them maybe have audio codec
for HDMP/DP output. For some dGPU which is no output,
audio codec usually is disabled.

In currect HDA audio driver, it will set all codec as
VGA_SWITCHEROO_DIS, the audio which is binded to UMA
will be suspended if user use debugfs to contorl power

In HDA driver side, it is difficult to know which GPU
the audio has binded to. So set the bound gpu pci dev
to vga_switcheroo.

if the audio client is not the third registration, audio
id will set in vga_switcheroo enable function. if the
audio client is the last registration when vga_switcheroo
_ready() get true, we should get audio client id from bound
GPU directly.

Signed-off-by: Jim Qu <Jim.Qu@amd.com>
Reviewed-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 drivers/gpu/vga/vga_switcheroo.c | 63 +++++++++++++++++++++++++++++++++-------
 include/linux/vga_switcheroo.h   |  8 ++---
 sound/pci/hda/hda_intel.c        | 11 +++----
 3 files changed, 62 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/vga/vga_switcheroo.c b/drivers/gpu/vga/vga_switcheroo.c
index fc4adf3d34e8..a96bf46bc483 100644
--- a/drivers/gpu/vga/vga_switcheroo.c
+++ b/drivers/gpu/vga/vga_switcheroo.c
@@ -103,9 +103,11 @@
  *	runtime pm. If true, writing ON and OFF to the vga_switcheroo debugfs
  *	interface is a no-op so as not to interfere with runtime pm
  * @list: client list
+ * @vga_dev: pci device, indicate which GPU is bound to current audio client
  *
  * Registered client. A client can be either a GPU or an audio device on a GPU.
- * For audio clients, the @fb_info and @active members are bogus.
+ * For audio clients, the @fb_info and @active members are bogus. For GPU
+ * clients, the @vga_dev is bogus.
  */
 struct vga_switcheroo_client {
 	struct pci_dev *pdev;
@@ -116,6 +118,7 @@ struct vga_switcheroo_client {
 	bool active;
 	bool driver_power_control;
 	struct list_head list;
+	struct pci_dev *vga_dev;
 };
 
 /*
@@ -161,9 +164,8 @@ struct vgasr_priv {
 };
 
 #define ID_BIT_AUDIO		0x100
-#define client_is_audio(c)	((c)->id & ID_BIT_AUDIO)
-#define client_is_vga(c)	((c)->id == VGA_SWITCHEROO_UNKNOWN_ID || \
-				 !client_is_audio(c))
+#define client_is_audio(c)		((c)->id & ID_BIT_AUDIO)
+#define client_is_vga(c)		(!client_is_audio(c))
 #define client_id(c)		((c)->id & ~ID_BIT_AUDIO)
 
 static int vga_switcheroo_debugfs_init(struct vgasr_priv *priv);
@@ -192,14 +194,29 @@ static void vga_switcheroo_enable(void)
 		vgasr_priv.handler->init();
 
 	list_for_each_entry(client, &vgasr_priv.clients, list) {
-		if (client->id != VGA_SWITCHEROO_UNKNOWN_ID)
+		if (!client_is_vga(client) ||
+		     client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID)
 			continue;
+
 		ret = vgasr_priv.handler->get_client_id(client->pdev);
 		if (ret < 0)
 			return;
 
 		client->id = ret;
 	}
+
+	list_for_each_entry(client, &vgasr_priv.clients, list) {
+		if (!client_is_audio(client) ||
+		     client_id(client) != VGA_SWITCHEROO_UNKNOWN_ID)
+			continue;
+
+		ret = vgasr_priv.handler->get_client_id(client->vga_dev);
+		if (ret < 0)
+			return;
+
+		client->id = ret | ID_BIT_AUDIO;
+	}
+
 	vga_switcheroo_debugfs_init(&vgasr_priv);
 	vgasr_priv.active = true;
 }
@@ -272,7 +289,9 @@ EXPORT_SYMBOL(vga_switcheroo_handler_flags);
 
 static int register_client(struct pci_dev *pdev,
 			   const struct vga_switcheroo_client_ops *ops,
-			   enum vga_switcheroo_client_id id, bool active,
+			   enum vga_switcheroo_client_id id,
+			   struct pci_dev *vga_dev,
+			   bool active,
 			   bool driver_power_control)
 {
 	struct vga_switcheroo_client *client;
@@ -287,6 +306,7 @@ static int register_client(struct pci_dev *pdev,
 	client->id = id;
 	client->active = active;
 	client->driver_power_control = driver_power_control;
+	client->vga_dev = vga_dev;
 
 	mutex_lock(&vgasr_mutex);
 	list_add_tail(&client->list, &vgasr_priv.clients);
@@ -319,7 +339,7 @@ int vga_switcheroo_register_client(struct pci_dev *pdev,
 				   const struct vga_switcheroo_client_ops *ops,
 				   bool driver_power_control)
 {
-	return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID,
+	return register_client(pdev, ops, VGA_SWITCHEROO_UNKNOWN_ID, NULL,
 			       pdev == vga_default_device(),
 			       driver_power_control);
 }
@@ -329,19 +349,40 @@ EXPORT_SYMBOL(vga_switcheroo_register_client);
  * vga_switcheroo_register_audio_client - register audio client
  * @pdev: client pci device
  * @ops: client callbacks
- * @id: client identifier
+ * @vga_dev:  pci device which is bound to current audio client
  *
  * Register audio client (audio device on a GPU). The client is assumed
  * to use runtime PM. Beforehand, vga_switcheroo_client_probe_defer()
  * shall be called to ensure that all prerequisites are met.
  *
- * Return: 0 on success, -ENOMEM on memory allocation error.
+ * Return: 0 on success, -ENOMEM on memory allocation error, -EINVAL on getting
+ * client id error.
  */
 int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 			const struct vga_switcheroo_client_ops *ops,
-			enum vga_switcheroo_client_id id)
+			struct pci_dev *vga_dev)
 {
-	return register_client(pdev, ops, id | ID_BIT_AUDIO, false, true);
+	enum vga_switcheroo_client_id id = VGA_SWITCHEROO_UNKNOWN_ID;
+
+	/*
+	 * if vga_switcheroo has enabled, that mean two GPU clients and also
+	 * handler are registered. Get audio client id from bound GPU client
+	 * id directly, otherwise, set it as VGA_SWITCHEROO_UNKNOWN_ID,
+	 * it will set to correct id in later when vga_switcheroo_enable()
+	 * is called.
+	 */
+	mutex_lock(&vgasr_mutex);
+	if (vgasr_priv.active) {
+		id = vgasr_priv.handler->get_client_id(vga_dev);
+		if (id < 0) {
+			mutex_unlock(&vgasr_mutex);
+			return -EINVAL;
+		}
+	}
+	mutex_unlock(&vgasr_mutex);
+
+	return register_client(pdev, ops, id | ID_BIT_AUDIO, vga_dev,
+			       false, true);
 }
 EXPORT_SYMBOL(vga_switcheroo_register_audio_client);
 
diff --git a/include/linux/vga_switcheroo.h b/include/linux/vga_switcheroo.h
index 77f0f0af3a71..a34539b7f750 100644
--- a/include/linux/vga_switcheroo.h
+++ b/include/linux/vga_switcheroo.h
@@ -84,8 +84,8 @@ enum vga_switcheroo_state {
  * Client identifier. Audio clients use the same identifier & 0x100.
  */
 enum vga_switcheroo_client_id {
-	VGA_SWITCHEROO_UNKNOWN_ID = -1,
-	VGA_SWITCHEROO_IGD,
+	VGA_SWITCHEROO_UNKNOWN_ID = 0x1000,
+	VGA_SWITCHEROO_IGD = 0,
 	VGA_SWITCHEROO_DIS,
 	VGA_SWITCHEROO_MAX_CLIENTS,
 };
@@ -151,7 +151,7 @@ int vga_switcheroo_register_client(struct pci_dev *dev,
 				   bool driver_power_control);
 int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 					 const struct vga_switcheroo_client_ops *ops,
-					 enum vga_switcheroo_client_id id);
+					 struct pci_dev *vga_dev);
 
 void vga_switcheroo_client_fb_set(struct pci_dev *dev,
 				  struct fb_info *info);
@@ -180,7 +180,7 @@ static inline int vga_switcheroo_register_handler(const struct vga_switcheroo_ha
 		enum vga_switcheroo_handler_flags_t handler_flags) { return 0; }
 static inline int vga_switcheroo_register_audio_client(struct pci_dev *pdev,
 	const struct vga_switcheroo_client_ops *ops,
-	enum vga_switcheroo_client_id id) { return 0; }
+	struct pci_dev *vga_dev) { return 0; }
 static inline void vga_switcheroo_unregister_handler(void) {}
 static inline enum vga_switcheroo_handler_flags_t vga_switcheroo_handler_flags(void) { return 0; }
 static inline int vga_switcheroo_lock_ddc(struct pci_dev *pdev) { return -ENODEV; }
diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 1ae1850b3bfd..1967a5537d68 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1319,15 +1319,16 @@ static const struct vga_switcheroo_client_ops azx_vs_ops = {
 static int register_vga_switcheroo(struct azx *chip)
 {
 	struct hda_intel *hda = container_of(chip, struct hda_intel, chip);
+	struct pci_dev *p;
 	int err;
 
 	if (!hda->use_vga_switcheroo)
 		return 0;
-	/* FIXME: currently only handling DIS controller
-	 * is there any machine with two switchable HDMI audio controllers?
-	 */
-	err = vga_switcheroo_register_audio_client(chip->pci, &azx_vs_ops,
-						   VGA_SWITCHEROO_DIS);
+
+	p = get_bound_vga(chip->pci);
+	err = vga_switcheroo_register_audio_client(chip->pci, &azx_vs_ops, p);
+	pci_dev_put(p);
+
 	if (err < 0)
 		return err;
 	hda->vga_switcheroo_registered = 1;
-- 
cgit v1.2.3


From d778847208c016f66a44d4c40baa74ca3bf724fd Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Jul 2018 09:23:34 +0100
Subject: drm/i915/selftests: Free the backing store between iterations

In the huge pages tests, we may have lots of objects being trapped on
the freelist as we hold the struct_mutex allowing the free worker no
opportunity to recover the backing store. We also have stricter
requirements and the desire for large contiguous pages, further
increasing the allocation pressure. To reduce the chance of running out
of memory, we could either drop the mutex and flush the free worker, or
we could release the backing store directly. We do the latter in this
patch for simplicity.

References: https://bugs.freedesktop.org/show_bug.cgi?id=107254
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Matthew Auld <matthew.william.auld@gmail.com>
Reviewed-by: Matthew Auld <matthew.william.auld@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717082334.18774-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/selftests/huge_pages.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/i915/selftests/huge_pages.c b/drivers/gpu/drm/i915/selftests/huge_pages.c
index d9f439f6219f..7efb326badcd 100644
--- a/drivers/gpu/drm/i915/selftests/huge_pages.c
+++ b/drivers/gpu/drm/i915/selftests/huge_pages.c
@@ -570,6 +570,7 @@ static int igt_mock_ppgtt_misaligned_dma(void *arg)
 		i915_vma_close(vma);
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
@@ -597,6 +598,7 @@ static void close_object_list(struct list_head *objects,
 
 		list_del(&obj->st_link);
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 }
@@ -866,6 +868,7 @@ static int igt_mock_ppgtt_64K(void *arg)
 			i915_vma_close(vma);
 
 			i915_gem_object_unpin_pages(obj);
+			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -1265,6 +1268,7 @@ static int igt_ppgtt_exhaust_huge(void *arg)
 			}
 
 			i915_gem_object_unpin_pages(obj);
+			__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 			i915_gem_object_put(obj);
 		}
 	}
@@ -1326,6 +1330,7 @@ static int igt_ppgtt_internal_huge(void *arg)
 		}
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
@@ -1394,6 +1399,7 @@ static int igt_ppgtt_gemfs_huge(void *arg)
 		}
 
 		i915_gem_object_unpin_pages(obj);
+		__i915_gem_object_put_pages(obj, I915_MM_NORMAL);
 		i915_gem_object_put(obj);
 	}
 
-- 
cgit v1.2.3


From 1ef2917d1d9e6cce41c8794b2e3e81552b1668e4 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 17 Jul 2018 10:33:49 +0200
Subject: drm/imx: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/imx-drm-core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index 1d053bbefc02..c895fe78fb48 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -229,7 +229,7 @@ static int imx_drm_bind(struct device *dev)
 	imxdrm = devm_kzalloc(dev, sizeof(*imxdrm), GFP_KERNEL);
 	if (!imxdrm) {
 		ret = -ENOMEM;
-		goto err_unref;
+		goto err_put;
 	}
 
 	imxdrm->drm = drm;
@@ -306,8 +306,8 @@ err_unbind:
 	component_unbind_all(drm->dev, drm);
 err_kms:
 	drm_mode_config_cleanup(drm);
-err_unref:
-	drm_dev_unref(drm);
+err_put:
+	drm_dev_put(drm);
 
 	return ret;
 }
@@ -327,7 +327,7 @@ static void imx_drm_unbind(struct device *dev)
 	component_unbind_all(drm->dev, drm);
 	dev_set_drvdata(dev, NULL);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops imx_drm_ops = {
-- 
cgit v1.2.3


From 504f2565a4f64a3cdd0a4e175a34ffc73297294a Mon Sep 17 00:00:00 2001
From: Liang Chen <cl@rock-chips.com>
Date: Tue, 17 Jul 2018 15:49:03 +0800
Subject: spi: rockchip: add description for px30

Add "rockchip,px30-spi", "rockchip,rk3066-spi" for spi on px30 platform.

Signed-off-by: Liang Chen <cl@rock-chips.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/spi/spi-rockchip.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/spi/spi-rockchip.txt b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
index 6e3ffacbba32..a0edac12d8df 100644
--- a/Documentation/devicetree/bindings/spi/spi-rockchip.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rockchip.txt
@@ -7,6 +7,7 @@ Required Properties:
 
 - compatible: should be one of the following.
     "rockchip,rv1108-spi" for rv1108 SoCs.
+    "rockchip,px30-spi", "rockchip,rk3066-spi" for px30 SoCs.
     "rockchip,rk3036-spi" for rk3036 SoCS.
     "rockchip,rk3066-spi" for rk3066 SoCs.
     "rockchip,rk3188-spi" for rk3188 SoCs.
-- 
cgit v1.2.3


From d91cfeb0aa79445fcfa9f523a5b57c5e9f4113ec Mon Sep 17 00:00:00 2001
From: RAGHU Halharvi <raghuhack78@gmail.com>
Date: Tue, 17 Jul 2018 15:50:09 +0530
Subject: genirq: Remove redundant NULL pointer check in __free_irq()

The NULL pointer check in __free_irq() triggers a 'dereference before NULL
pointer check' warning in static code analysis. It turns out that the check
is redundant because all callers have a NULL pointer check already.

Remove it.

Signed-off-by: RAGHU Halharvi <raghuhack78@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180717102009.7708-1-raghuhack78@gmail.com
---
 kernel/irq/manage.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1f8be33572a7..a66c58f91bff 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1570,9 +1570,6 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
-	if (!desc)
-		return NULL;
-
 	mutex_lock(&desc->request_mutex);
 	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
-- 
cgit v1.2.3


From 5f8f80356eccfaae1db8a827626ae4fc2eb62831 Mon Sep 17 00:00:00 2001
From: Andrey Smirnov <andrew.smirnov@gmail.com>
Date: Mon, 16 Jul 2018 21:33:29 -0700
Subject: spi: spi-fsl-dspi: Fill actual_length when doing DMA transfer

Upper layer users of SPI device drivers may rely on 'actual_length',
so it is important that information is correctly reported. One such
example is spi_mem_exec_op() function that will fail if
'actual_length' of the data transferred is not what was requested. Add
necessary code to populate 'actual_length.

Cc: Mark Brown <broonie@kernel.org>
Cc: Sanchayan Maity <maitysanchayan@gmail.com>
Cc: Stefan Agner <stefan@agner.ch>
Cc: cphealy@gmail.com
Cc: linux-spi@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Andrey Smirnov <andrew.smirnov@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 89a1e7a4fe5d..9e598642ca66 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -358,6 +358,7 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 {
 	struct fsl_dspi_dma *dma = dspi->dma;
 	struct device *dev = &dspi->pdev->dev;
+	struct spi_message *message = dspi->cur_msg;
 	int curr_remaining_bytes;
 	int bytes_per_buffer;
 	int ret = 0;
@@ -377,8 +378,10 @@ static int dspi_dma_xfer(struct fsl_dspi *dspi)
 			goto exit;
 
 		} else {
-			curr_remaining_bytes -= dma->curr_xfer_len
-				* dspi->bytes_per_word;
+			const int len =
+				dma->curr_xfer_len * dspi->bytes_per_word;
+			curr_remaining_bytes -= len;
+			message->actual_length += len;
 			if (curr_remaining_bytes < 0)
 				curr_remaining_bytes = 0;
 		}
-- 
cgit v1.2.3


From 4c2ae34f64c80991501ebd830b13dce5c7dc3621 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 17 Jul 2018 10:48:14 +0200
Subject: drm/sun4i: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717084814.18091-1-tzimmermann@suse.de
---
 drivers/gpu/drm/sun4i/sun4i_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_drv.c b/drivers/gpu/drm/sun4i/sun4i_drv.c
index 03ffbcc98dd0..dd19d674055c 100644
--- a/drivers/gpu/drm/sun4i/sun4i_drv.c
+++ b/drivers/gpu/drm/sun4i/sun4i_drv.c
@@ -144,7 +144,7 @@ cleanup_mode_config:
 	drm_mode_config_cleanup(drm);
 	of_reserved_mem_device_release(dev);
 free_drm:
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 	return ret;
 }
 
@@ -157,7 +157,7 @@ static void sun4i_drv_unbind(struct device *dev)
 	sun4i_framebuffer_free(drm);
 	drm_mode_config_cleanup(drm);
 	of_reserved_mem_device_release(dev);
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops sun4i_drv_master_ops = {
-- 
cgit v1.2.3


From 81f2b25adddeff2fc7fdd1f23f889d018ba65466 Mon Sep 17 00:00:00 2001
From: Leonard Crestez <leonard.crestez@nxp.com>
Date: Tue, 17 Jul 2018 15:11:28 +0300
Subject: drm/imx: Remove unused field imx_drm_device.pipes

This has been unused since commit 44b460cfe554 ("drm: imx: remove struct
imx_drm_crtc and imx_drm_crtc_helper_funcs")

Signed-off-by: Leonard Crestez <leonard.crestez@nxp.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/imx-drm-core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index c895fe78fb48..f0122afcf2a8 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -37,7 +37,6 @@
 
 struct imx_drm_device {
 	struct drm_device			*drm;
-	unsigned int				pipes;
 	struct drm_atomic_state			*state;
 };
 
-- 
cgit v1.2.3


From cc57c07343bd071cdf1915a91a24ab7d40c9b590 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Sun, 15 Jul 2018 18:16:17 -0500
Subject: configfs: fix registered group removal

This patch fixes a bug where configfs_register_group had added
a group in a tree, and userspace has done a rmdir on a dir somewhere
above that group and we hit a kernel crash. The problem is configfs_rmdir
will detach everything under it and unlink groups on the default_groups
list. It will not unlink groups added with configfs_register_group so when
configfs_unregister_group is called to drop its references to the group/items
we crash when we try to access the freed dentrys.

The patch just adds a check for if a rmdir has been done above
us and if so just does the unlink part of unregistration.

Sorry if you are getting this multiple times. I thouhgt I sent
this to some of you and lkml, but I do not see it.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 fs/configfs/dir.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/fs/configfs/dir.c b/fs/configfs/dir.c
index 577cff24707b..39843fa7e11b 100644
--- a/fs/configfs/dir.c
+++ b/fs/configfs/dir.c
@@ -1777,6 +1777,16 @@ void configfs_unregister_group(struct config_group *group)
 	struct dentry *dentry = group->cg_item.ci_dentry;
 	struct dentry *parent = group->cg_item.ci_parent->ci_dentry;
 
+	mutex_lock(&subsys->su_mutex);
+	if (!group->cg_item.ci_parent->ci_group) {
+		/*
+		 * The parent has already been unlinked and detached
+		 * due to a rmdir.
+		 */
+		goto unlink_group;
+	}
+	mutex_unlock(&subsys->su_mutex);
+
 	inode_lock_nested(d_inode(parent), I_MUTEX_PARENT);
 	spin_lock(&configfs_dirent_lock);
 	configfs_detach_prep(dentry, NULL);
@@ -1791,6 +1801,7 @@ void configfs_unregister_group(struct config_group *group)
 	dput(dentry);
 
 	mutex_lock(&subsys->su_mutex);
+unlink_group:
 	unlink_group(group);
 	mutex_unlock(&subsys->su_mutex);
 }
-- 
cgit v1.2.3


From a0ae2562c6c4b2721d9fddba63b7286c13517d9f Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 29 Jun 2018 07:46:51 +0200
Subject: netfilter: conntrack: remove l3proto abstraction

This unifies ipv4 and ipv6 protocol trackers and removes the l3proto
abstraction.

This gets rid of all l3proto indirect calls and the need to do
a lookup on the function to call for l3 demux.

It increases module size by only a small amount (12kbyte), so this reduces
size because nf_conntrack.ko is useless without either nf_conntrack_ipv4
or nf_conntrack_ipv6 module.

before:
   text    data     bss     dec     hex filename
   7357    1088       0    8445    20fd nf_conntrack_ipv4.ko
   7405    1084       4    8493    212d nf_conntrack_ipv6.ko
  72614   13689     236   86539   1520b nf_conntrack.ko
 19K nf_conntrack_ipv4.ko
 19K nf_conntrack_ipv6.ko
179K nf_conntrack.ko

after:
   text    data     bss     dec     hex filename
  79277   13937     236   93450   16d0a nf_conntrack.ko
  191K nf_conntrack.ko

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/ipv4/nf_conntrack_ipv4.h |   3 -
 include/net/netfilter/nf_conntrack.h           |   5 +
 include/net/netfilter/nf_conntrack_core.h      |   1 -
 include/net/netfilter/nf_conntrack_l3proto.h   |  54 --
 include/net/netfilter/nf_conntrack_l4proto.h   |   4 -
 net/ipv4/netfilter/Kconfig                     |  22 +-
 net/ipv4/netfilter/Makefile                    |   6 -
 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c | 368 -----------
 net/ipv4/netfilter/nf_conntrack_proto_icmp.c   | 388 -----------
 net/ipv6/netfilter/Kconfig                     |  27 +-
 net/ipv6/netfilter/Makefile                    |   6 -
 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c | 355 -----------
 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c | 387 -----------
 net/netfilter/Kconfig                          |   2 +
 net/netfilter/Makefile                         |   7 +-
 net/netfilter/nf_conntrack_core.c              |  11 +-
 net/netfilter/nf_conntrack_proto.c             | 847 ++++++++++++++++++-------
 net/netfilter/nf_conntrack_proto_icmp.c        | 388 +++++++++++
 net/netfilter/nf_conntrack_proto_icmpv6.c      | 387 +++++++++++
 net/netfilter/nf_conntrack_standalone.c        |  14 +-
 net/netfilter/nf_nat_core.c                    |   8 -
 21 files changed, 1420 insertions(+), 1870 deletions(-)
 delete mode 100644 include/net/netfilter/nf_conntrack_l3proto.h
 delete mode 100644 net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
 delete mode 100644 net/ipv4/netfilter/nf_conntrack_proto_icmp.c
 delete mode 100644 net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
 delete mode 100644 net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
 create mode 100644 net/netfilter/nf_conntrack_proto_icmp.c
 create mode 100644 net/netfilter/nf_conntrack_proto_icmpv6.c

diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
index 73f825732326..c84b51682f08 100644
--- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
@@ -10,9 +10,6 @@
 #ifndef _NF_CONNTRACK_IPV4_H
 #define _NF_CONNTRACK_IPV4_H
 
-
-const extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
-
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp4;
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp4;
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp;
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 062dc19b5840..a2b0ed025908 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -41,6 +41,11 @@ union nf_conntrack_expect_proto {
 	/* insert expect proto private data here */
 };
 
+struct nf_conntrack_net {
+	unsigned int users4;
+	unsigned int users6;
+};
+
 #include <linux/types.h>
 #include <linux/skbuff.h>
 
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 35461b2d3462..2a3e0974a6af 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -14,7 +14,6 @@
 #define _NF_CONNTRACK_CORE_H
 
 #include <linux/netfilter.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
 
diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h
deleted file mode 100644
index 5f160375c93a..000000000000
--- a/include/net/netfilter/nf_conntrack_l3proto.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Copyright (C)2003,2004 USAGI/WIDE Project
- *
- * Header for use in defining a given L3 protocol for connection tracking.
- *
- * Author:
- *	Yasuyuki Kozakai @USAGI	<yasuyuki.kozakai@toshiba.co.jp>
- *
- * Derived from include/netfilter_ipv4/ip_conntrack_protocol.h
- */
-
-#ifndef _NF_CONNTRACK_L3PROTO_H
-#define _NF_CONNTRACK_L3PROTO_H
-#include <linux/netlink.h>
-#include <net/netlink.h>
-#include <linux/seq_file.h>
-#include <net/netfilter/nf_conntrack.h>
-
-struct nf_conntrack_l3proto {
-	/* L3 Protocol Family number. ex) PF_INET */
-	u_int16_t l3proto;
-
-	/* size of tuple nlattr, fills a hole */
-	u16 nla_size;
-
-	/* Called when netns wants to use connection tracking */
-	int (*net_ns_get)(struct net *);
-	void (*net_ns_put)(struct net *);
-
-	/* Module (if any) which this is connected to. */
-	struct module *me;
-};
-
-extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO];
-
-/* Protocol global registration. */
-int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto);
-void nf_ct_l3proto_unregister(const struct nf_conntrack_l3proto *proto);
-
-const struct nf_conntrack_l3proto *nf_ct_l3proto_find_get(u_int16_t l3proto);
-
-/* Existing built-in protocols */
-extern struct nf_conntrack_l3proto nf_conntrack_l3proto_generic;
-
-static inline struct nf_conntrack_l3proto *
-__nf_ct_l3proto_find(u_int16_t l3proto)
-{
-	if (unlikely(l3proto >= NFPROTO_NUMPROTO))
-		return &nf_conntrack_l3proto_generic;
-	return rcu_dereference(nf_ct_l3protos[l3proto]);
-}
-
-#endif /*_NF_CONNTRACK_L3PROTO_H*/
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index c7a0075d96df..6068c6da3eac 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -130,10 +130,6 @@ void nf_ct_l4proto_pernet_unregister(struct net *net,
 /* Protocol global registration. */
 int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *proto);
 void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *proto);
-int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const proto[],
-			   unsigned int num_proto);
-void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const proto[],
-			      unsigned int num_proto);
 
 /* Generic netlink helpers */
 int nf_ct_port_tuple_to_nlattr(struct sk_buff *skb,
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index bbfc356cb1b5..d9504adc47b3 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -9,22 +9,6 @@ config NF_DEFRAG_IPV4
 	tristate
 	default n
 
-config NF_CONNTRACK_IPV4
-	tristate "IPv4 connection tracking support (required for NAT)"
-	depends on NF_CONNTRACK
-	default m if NETFILTER_ADVANCED=n
-	select NF_DEFRAG_IPV4
-	---help---
-	  Connection tracking keeps a record of what packets have passed
-	  through your machine, in order to figure out how they are related
-	  into connections.
-
-	  This is IPv4 support on Layer 3 independent connection tracking.
-	  Layer 3 independent connection tracking is experimental scheme
-	  which generalize ip_conntrack to support other layer 3 protocols.
-
-	  To compile it as a module, choose M here.  If unsure, say N.
-
 config NF_SOCKET_IPV4
 	tristate "IPv4 socket lookup support"
 	help
@@ -112,7 +96,7 @@ config NF_REJECT_IPV4
 
 config NF_NAT_IPV4
 	tristate "IPv4 NAT"
-	depends on NF_CONNTRACK_IPV4
+	depends on NF_CONNTRACK
 	default m if NETFILTER_ADVANCED=n
 	select NF_NAT
 	help
@@ -279,7 +263,7 @@ config IP_NF_TARGET_SYNPROXY
 # NAT + specific targets: nf_conntrack
 config IP_NF_NAT
 	tristate "iptables NAT support"
-	depends on NF_CONNTRACK_IPV4
+	depends on NF_CONNTRACK
 	default m if NETFILTER_ADVANCED=n
 	select NF_NAT
 	select NF_NAT_IPV4
@@ -340,7 +324,7 @@ config IP_NF_MANGLE
 config IP_NF_TARGET_CLUSTERIP
 	tristate "CLUSTERIP target support"
 	depends on IP_NF_MANGLE
-	depends on NF_CONNTRACK_IPV4
+	depends on NF_CONNTRACK
 	depends on NETFILTER_ADVANCED
 	select NF_CONNTRACK_MARK
 	select NETFILTER_FAMILY_ARP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 8394c17c269f..367993adf4d3 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -3,12 +3,6 @@
 # Makefile for the netfilter modules on top of IPv4.
 #
 
-# objects for l3 independent conntrack
-nf_conntrack_ipv4-y	:=  nf_conntrack_l3proto_ipv4.o nf_conntrack_proto_icmp.o
-
-# connection tracking
-obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o
-
 nf_nat_ipv4-y		:= nf_nat_l3proto_ipv4.o nf_nat_proto_icmp.o
 nf_nat_ipv4-$(CONFIG_NF_NAT_MASQUERADE_IPV4) += nf_nat_masquerade_ipv4.o
 obj-$(CONFIG_NF_NAT_IPV4) += nf_nat_ipv4.o
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
deleted file mode 100644
index 9fbf6c7f8ece..000000000000
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ /dev/null
@@ -1,368 +0,0 @@
-
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
- * (C) 2006-2012 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/icmp.h>
-#include <linux/sysctl.h>
-#include <net/route.h>
-#include <net/ip.h>
-
-#include <linux/netfilter_ipv4.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_helper.h>
-#include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
-#include <net/netfilter/nf_conntrack_zones.h>
-#include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_seqadj.h>
-#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
-#include <net/netfilter/nf_nat_helper.h>
-#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
-#include <net/netfilter/nf_log.h>
-
-static int conntrack4_net_id __read_mostly;
-static DEFINE_MUTEX(register_ipv4_hooks);
-
-struct conntrack4_net {
-	unsigned int users;
-};
-
-static unsigned int ipv4_helper(void *priv,
-				struct sk_buff *skb,
-				const struct nf_hook_state *state)
-{
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	const struct nf_conn_help *help;
-	const struct nf_conntrack_helper *helper;
-
-	/* This is where we call the helper: as the packet goes out. */
-	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
-		return NF_ACCEPT;
-
-	help = nfct_help(ct);
-	if (!help)
-		return NF_ACCEPT;
-
-	/* rcu_read_lock()ed by nf_hook_thresh */
-	helper = rcu_dereference(help->helper);
-	if (!helper)
-		return NF_ACCEPT;
-
-	return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
-			    ct, ctinfo);
-}
-
-static unsigned int ipv4_confirm(void *priv,
-				 struct sk_buff *skb,
-				 const struct nf_hook_state *state)
-{
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
-		goto out;
-
-	/* adjust seqs for loopback traffic only in outgoing direction */
-	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
-	    !nf_is_loopback_packet(skb)) {
-		if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
-			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
-			return NF_DROP;
-		}
-	}
-out:
-	/* We've seen it coming out the other side: confirm it */
-	return nf_conntrack_confirm(skb);
-}
-
-static unsigned int ipv4_conntrack_in(void *priv,
-				      struct sk_buff *skb,
-				      const struct nf_hook_state *state)
-{
-	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
-}
-
-static unsigned int ipv4_conntrack_local(void *priv,
-					 struct sk_buff *skb,
-					 const struct nf_hook_state *state)
-{
-	if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
-		enum ip_conntrack_info ctinfo;
-		struct nf_conn *tmpl;
-
-		tmpl = nf_ct_get(skb, &ctinfo);
-		if (tmpl && nf_ct_is_template(tmpl)) {
-			/* when skipping ct, clear templates to avoid fooling
-			 * later targets/matches
-			 */
-			skb->_nfct = 0;
-			nf_ct_put(tmpl);
-		}
-		return NF_ACCEPT;
-	}
-
-	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
-}
-
-/* Connection tracking may drop packets, but never alters them, so
-   make it the first hook. */
-static const struct nf_hook_ops ipv4_conntrack_ops[] = {
-	{
-		.hook		= ipv4_conntrack_in,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_PRE_ROUTING,
-		.priority	= NF_IP_PRI_CONNTRACK,
-	},
-	{
-		.hook		= ipv4_conntrack_local,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= NF_IP_PRI_CONNTRACK,
-	},
-	{
-		.hook		= ipv4_helper,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP_PRI_CONNTRACK_HELPER,
-	},
-	{
-		.hook		= ipv4_confirm,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
-	},
-	{
-		.hook		= ipv4_helper,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP_PRI_CONNTRACK_HELPER,
-	},
-	{
-		.hook		= ipv4_confirm,
-		.pf		= NFPROTO_IPV4,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
-	},
-};
-
-/* Fast function for those who don't want to parse /proc (and I don't
-   blame them). */
-/* Reversing the socket's dst/src point of view gives us the reply
-   mapping. */
-static int
-getorigdst(struct sock *sk, int optval, void __user *user, int *len)
-{
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct nf_conntrack_tuple_hash *h;
-	struct nf_conntrack_tuple tuple;
-
-	memset(&tuple, 0, sizeof(tuple));
-
-	lock_sock(sk);
-	tuple.src.u3.ip = inet->inet_rcv_saddr;
-	tuple.src.u.tcp.port = inet->inet_sport;
-	tuple.dst.u3.ip = inet->inet_daddr;
-	tuple.dst.u.tcp.port = inet->inet_dport;
-	tuple.src.l3num = PF_INET;
-	tuple.dst.protonum = sk->sk_protocol;
-	release_sock(sk);
-
-	/* We only do TCP and SCTP at the moment: is there a better way? */
-	if (tuple.dst.protonum != IPPROTO_TCP &&
-	    tuple.dst.protonum != IPPROTO_SCTP) {
-		pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n");
-		return -ENOPROTOOPT;
-	}
-
-	if ((unsigned int) *len < sizeof(struct sockaddr_in)) {
-		pr_debug("SO_ORIGINAL_DST: len %d not %zu\n",
-			 *len, sizeof(struct sockaddr_in));
-		return -EINVAL;
-	}
-
-	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
-	if (h) {
-		struct sockaddr_in sin;
-		struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
-
-		sin.sin_family = AF_INET;
-		sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL]
-			.tuple.dst.u.tcp.port;
-		sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL]
-			.tuple.dst.u3.ip;
-		memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
-
-		pr_debug("SO_ORIGINAL_DST: %pI4 %u\n",
-			 &sin.sin_addr.s_addr, ntohs(sin.sin_port));
-		nf_ct_put(ct);
-		if (copy_to_user(user, &sin, sizeof(sin)) != 0)
-			return -EFAULT;
-		else
-			return 0;
-	}
-	pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n",
-		 &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port),
-		 &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port));
-	return -ENOENT;
-}
-
-static struct nf_sockopt_ops so_getorigdst = {
-	.pf		= PF_INET,
-	.get_optmin	= SO_ORIGINAL_DST,
-	.get_optmax	= SO_ORIGINAL_DST+1,
-	.get		= getorigdst,
-	.owner		= THIS_MODULE,
-};
-
-static int ipv4_hooks_register(struct net *net)
-{
-	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
-	int err = 0;
-
-	mutex_lock(&register_ipv4_hooks);
-
-	cnet->users++;
-	if (cnet->users > 1)
-		goto out_unlock;
-
-	err = nf_defrag_ipv4_enable(net);
-	if (err) {
-		cnet->users = 0;
-		goto out_unlock;
-	}
-
-	err = nf_register_net_hooks(net, ipv4_conntrack_ops,
-				    ARRAY_SIZE(ipv4_conntrack_ops));
-
-	if (err)
-		cnet->users = 0;
- out_unlock:
-	mutex_unlock(&register_ipv4_hooks);
-	return err;
-}
-
-static void ipv4_hooks_unregister(struct net *net)
-{
-	struct conntrack4_net *cnet = net_generic(net, conntrack4_net_id);
-
-	mutex_lock(&register_ipv4_hooks);
-	if (cnet->users && (--cnet->users == 0))
-		nf_unregister_net_hooks(net, ipv4_conntrack_ops,
-					ARRAY_SIZE(ipv4_conntrack_ops));
-	mutex_unlock(&register_ipv4_hooks);
-}
-
-const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4 = {
-	.l3proto	 = PF_INET,
-	.net_ns_get	 = ipv4_hooks_register,
-	.net_ns_put	 = ipv4_hooks_unregister,
-	.me		 = THIS_MODULE,
-};
-
-module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
-		  &nf_conntrack_htable_size, 0600);
-
-MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
-MODULE_ALIAS("ip_conntrack");
-MODULE_LICENSE("GPL");
-
-static const struct nf_conntrack_l4proto * const builtin_l4proto4[] = {
-	&nf_conntrack_l4proto_tcp4,
-	&nf_conntrack_l4proto_udp4,
-	&nf_conntrack_l4proto_icmp,
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	&nf_conntrack_l4proto_dccp4,
-#endif
-#ifdef CONFIG_NF_CT_PROTO_SCTP
-	&nf_conntrack_l4proto_sctp4,
-#endif
-#ifdef CONFIG_NF_CT_PROTO_UDPLITE
-	&nf_conntrack_l4proto_udplite4,
-#endif
-};
-
-static int ipv4_net_init(struct net *net)
-{
-	return nf_ct_l4proto_pernet_register(net, builtin_l4proto4,
-					     ARRAY_SIZE(builtin_l4proto4));
-}
-
-static void ipv4_net_exit(struct net *net)
-{
-	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto4,
-					ARRAY_SIZE(builtin_l4proto4));
-}
-
-static struct pernet_operations ipv4_net_ops = {
-	.init = ipv4_net_init,
-	.exit = ipv4_net_exit,
-	.id = &conntrack4_net_id,
-	.size = sizeof(struct conntrack4_net),
-};
-
-static int __init nf_conntrack_l3proto_ipv4_init(void)
-{
-	int ret = 0;
-
-	need_conntrack();
-
-	ret = nf_register_sockopt(&so_getorigdst);
-	if (ret < 0) {
-		pr_err("Unable to register netfilter socket option\n");
-		return ret;
-	}
-
-	ret = register_pernet_subsys(&ipv4_net_ops);
-	if (ret < 0) {
-		pr_err("nf_conntrack_ipv4: can't register pernet ops\n");
-		goto cleanup_sockopt;
-	}
-
-	ret = nf_ct_l4proto_register(builtin_l4proto4,
-				     ARRAY_SIZE(builtin_l4proto4));
-	if (ret < 0)
-		goto cleanup_pernet;
-
-	ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv4);
-	if (ret < 0) {
-		pr_err("nf_conntrack_ipv4: can't register ipv4 proto.\n");
-		goto cleanup_l4proto;
-	}
-
-	return ret;
-cleanup_l4proto:
-	nf_ct_l4proto_unregister(builtin_l4proto4,
-				 ARRAY_SIZE(builtin_l4proto4));
- cleanup_pernet:
-	unregister_pernet_subsys(&ipv4_net_ops);
- cleanup_sockopt:
-	nf_unregister_sockopt(&so_getorigdst);
-	return ret;
-}
-
-static void __exit nf_conntrack_l3proto_ipv4_fini(void)
-{
-	synchronize_net();
-	nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv4);
-	nf_ct_l4proto_unregister(builtin_l4proto4,
-				 ARRAY_SIZE(builtin_l4proto4));
-	unregister_pernet_subsys(&ipv4_net_ops);
-	nf_unregister_sockopt(&so_getorigdst);
-}
-
-module_init(nf_conntrack_l3proto_ipv4_init);
-module_exit(nf_conntrack_l3proto_ipv4_fini);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
deleted file mode 100644
index 036670b38282..000000000000
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ /dev/null
@@ -1,388 +0,0 @@
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
- * (C) 2006-2010 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#include <linux/types.h>
-#include <linux/timer.h>
-#include <linux/netfilter.h>
-#include <linux/in.h>
-#include <linux/icmp.h>
-#include <linux/seq_file.h>
-#include <net/ip.h>
-#include <net/checksum.h>
-#include <linux/netfilter_ipv4.h>
-#include <net/netfilter/nf_conntrack_tuple.h>
-#include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_timeout.h>
-#include <net/netfilter/nf_conntrack_zones.h>
-#include <net/netfilter/nf_log.h>
-
-static const unsigned int nf_ct_icmp_timeout = 30*HZ;
-
-static inline struct nf_icmp_net *icmp_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.icmp;
-}
-
-static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
-			      struct net *net, struct nf_conntrack_tuple *tuple)
-{
-	const struct icmphdr *hp;
-	struct icmphdr _hdr;
-
-	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
-	if (hp == NULL)
-		return false;
-
-	tuple->dst.u.icmp.type = hp->type;
-	tuple->src.u.icmp.id = hp->un.echo.id;
-	tuple->dst.u.icmp.code = hp->code;
-
-	return true;
-}
-
-/* Add 1; spaces filled with 0. */
-static const u_int8_t invmap[] = {
-	[ICMP_ECHO] = ICMP_ECHOREPLY + 1,
-	[ICMP_ECHOREPLY] = ICMP_ECHO + 1,
-	[ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1,
-	[ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1,
-	[ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1,
-	[ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1,
-	[ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1,
-	[ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1
-};
-
-static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple,
-			      const struct nf_conntrack_tuple *orig)
-{
-	if (orig->dst.u.icmp.type >= sizeof(invmap) ||
-	    !invmap[orig->dst.u.icmp.type])
-		return false;
-
-	tuple->src.u.icmp.id = orig->src.u.icmp.id;
-	tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1;
-	tuple->dst.u.icmp.code = orig->dst.u.icmp.code;
-	return true;
-}
-
-static unsigned int *icmp_get_timeouts(struct net *net)
-{
-	return &icmp_pernet(net)->timeout;
-}
-
-/* Returns verdict for packet, or -1 for invalid. */
-static int icmp_packet(struct nf_conn *ct,
-		       const struct sk_buff *skb,
-		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo)
-{
-	/* Do not immediately delete the connection after the first
-	   successful reply to avoid excessive conntrackd traffic
-	   and also to handle correctly ICMP echo reply duplicates. */
-	unsigned int *timeout = nf_ct_timeout_lookup(ct);
-
-	if (!timeout)
-		timeout = icmp_get_timeouts(nf_ct_net(ct));
-
-	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
-
-	return NF_ACCEPT;
-}
-
-/* Called when a new connection for this protocol found. */
-static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
-		     unsigned int dataoff)
-{
-	static const u_int8_t valid_new[] = {
-		[ICMP_ECHO] = 1,
-		[ICMP_TIMESTAMP] = 1,
-		[ICMP_INFO_REQUEST] = 1,
-		[ICMP_ADDRESS] = 1
-	};
-
-	if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) ||
-	    !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) {
-		/* Can't create a new ICMP `conn' with this. */
-		pr_debug("icmp: can't create new conn with type %u\n",
-			 ct->tuplehash[0].tuple.dst.u.icmp.type);
-		nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple);
-		return false;
-	}
-	return true;
-}
-
-/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
-static int
-icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
-		 unsigned int hooknum)
-{
-	struct nf_conntrack_tuple innertuple, origtuple;
-	const struct nf_conntrack_l4proto *innerproto;
-	const struct nf_conntrack_tuple_hash *h;
-	const struct nf_conntrack_zone *zone;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conntrack_zone tmp;
-
-	WARN_ON(skb_nfct(skb));
-	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
-
-	/* Are they talking about one of our connections? */
-	if (!nf_ct_get_tuplepr(skb,
-			       skb_network_offset(skb) + ip_hdrlen(skb)
-						       + sizeof(struct icmphdr),
-			       PF_INET, net, &origtuple)) {
-		pr_debug("icmp_error_message: failed to get tuple\n");
-		return -NF_ACCEPT;
-	}
-
-	/* rcu_read_lock()ed by nf_hook_thresh */
-	innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum);
-
-	/* Ordinarily, we'd expect the inverted tupleproto, but it's
-	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) {
-		pr_debug("icmp_error_message: no match\n");
-		return -NF_ACCEPT;
-	}
-
-	ctinfo = IP_CT_RELATED;
-
-	h = nf_conntrack_find_get(net, zone, &innertuple);
-	if (!h) {
-		pr_debug("icmp_error_message: no match\n");
-		return -NF_ACCEPT;
-	}
-
-	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
-		ctinfo += IP_CT_IS_REPLY;
-
-	/* Update skb to refer to this connection */
-	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
-	return NF_ACCEPT;
-}
-
-static void icmp_error_log(const struct sk_buff *skb, struct net *net,
-			   u8 pf, const char *msg)
-{
-	nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg);
-}
-
-/* Small and modified version of icmp_rcv */
-static int
-icmp_error(struct net *net, struct nf_conn *tmpl,
-	   struct sk_buff *skb, unsigned int dataoff,
-	   u8 pf, unsigned int hooknum)
-{
-	const struct icmphdr *icmph;
-	struct icmphdr _ih;
-
-	/* Not enough header? */
-	icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
-	if (icmph == NULL) {
-		icmp_error_log(skb, net, pf, "short packet");
-		return -NF_ACCEPT;
-	}
-
-	/* See ip_conntrack_proto_tcp.c */
-	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
-	    nf_ip_checksum(skb, hooknum, dataoff, 0)) {
-		icmp_error_log(skb, net, pf, "bad hw icmp checksum");
-		return -NF_ACCEPT;
-	}
-
-	/*
-	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
-	 *
-	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
-	 *		  discarded.
-	 */
-	if (icmph->type > NR_ICMP_TYPES) {
-		icmp_error_log(skb, net, pf, "invalid icmp type");
-		return -NF_ACCEPT;
-	}
-
-	/* Need to track icmp error message? */
-	if (icmph->type != ICMP_DEST_UNREACH &&
-	    icmph->type != ICMP_SOURCE_QUENCH &&
-	    icmph->type != ICMP_TIME_EXCEEDED &&
-	    icmph->type != ICMP_PARAMETERPROB &&
-	    icmph->type != ICMP_REDIRECT)
-		return NF_ACCEPT;
-
-	return icmp_error_message(net, tmpl, skb, hooknum);
-}
-
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nfnetlink_conntrack.h>
-
-static int icmp_tuple_to_nlattr(struct sk_buff *skb,
-				const struct nf_conntrack_tuple *t)
-{
-	if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) ||
-	    nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) ||
-	    nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = {
-	[CTA_PROTO_ICMP_TYPE]	= { .type = NLA_U8 },
-	[CTA_PROTO_ICMP_CODE]	= { .type = NLA_U8 },
-	[CTA_PROTO_ICMP_ID]	= { .type = NLA_U16 },
-};
-
-static int icmp_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *tuple)
-{
-	if (!tb[CTA_PROTO_ICMP_TYPE] ||
-	    !tb[CTA_PROTO_ICMP_CODE] ||
-	    !tb[CTA_PROTO_ICMP_ID])
-		return -EINVAL;
-
-	tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]);
-	tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]);
-	tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]);
-
-	if (tuple->dst.u.icmp.type >= sizeof(invmap) ||
-	    !invmap[tuple->dst.u.icmp.type])
-		return -EINVAL;
-
-	return 0;
-}
-
-static unsigned int icmp_nlattr_tuple_size(void)
-{
-	static unsigned int size __read_mostly;
-
-	if (!size)
-		size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
-
-	return size;
-}
-#endif
-
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nfnetlink_cttimeout.h>
-
-static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[],
-				      struct net *net, void *data)
-{
-	unsigned int *timeout = data;
-	struct nf_icmp_net *in = icmp_pernet(net);
-
-	if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) {
-		if (!timeout)
-			timeout = &in->timeout;
-		*timeout =
-			ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ;
-	} else if (timeout) {
-		/* Set default ICMP timeout. */
-		*timeout = in->timeout;
-	}
-	return 0;
-}
-
-static int
-icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
-{
-	const unsigned int *timeout = data;
-
-	if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ)))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -ENOSPC;
-}
-
-static const struct nla_policy
-icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = {
-	[CTA_TIMEOUT_ICMP_TIMEOUT]	= { .type = NLA_U32 },
-};
-#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
-
-#ifdef CONFIG_SYSCTL
-static struct ctl_table icmp_sysctl_table[] = {
-	{
-		.procname	= "nf_conntrack_icmp_timeout",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{ }
-};
-#endif /* CONFIG_SYSCTL */
-
-static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn,
-				     struct nf_icmp_net *in)
-{
-#ifdef CONFIG_SYSCTL
-	pn->ctl_table = kmemdup(icmp_sysctl_table,
-				sizeof(icmp_sysctl_table),
-				GFP_KERNEL);
-	if (!pn->ctl_table)
-		return -ENOMEM;
-
-	pn->ctl_table[0].data = &in->timeout;
-#endif
-	return 0;
-}
-
-static int icmp_init_net(struct net *net, u_int16_t proto)
-{
-	struct nf_icmp_net *in = icmp_pernet(net);
-	struct nf_proto_net *pn = &in->pn;
-
-	in->timeout = nf_ct_icmp_timeout;
-
-	return icmp_kmemdup_sysctl_table(pn, in);
-}
-
-static struct nf_proto_net *icmp_get_net_proto(struct net *net)
-{
-	return &net->ct.nf_ct_proto.icmp.pn;
-}
-
-const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp =
-{
-	.l3proto		= PF_INET,
-	.l4proto		= IPPROTO_ICMP,
-	.pkt_to_tuple		= icmp_pkt_to_tuple,
-	.invert_tuple		= icmp_invert_tuple,
-	.packet			= icmp_packet,
-	.new			= icmp_new,
-	.error			= icmp_error,
-	.destroy		= NULL,
-	.me			= NULL,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.tuple_to_nlattr	= icmp_tuple_to_nlattr,
-	.nlattr_tuple_size	= icmp_nlattr_tuple_size,
-	.nlattr_to_tuple	= icmp_nlattr_to_tuple,
-	.nla_policy		= icmp_nla_policy,
-#endif
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
-	.ctnl_timeout		= {
-		.nlattr_to_obj	= icmp_timeout_nlattr_to_obj,
-		.obj_to_nlattr	= icmp_timeout_obj_to_nlattr,
-		.nlattr_max	= CTA_TIMEOUT_ICMP_MAX,
-		.obj_size	= sizeof(unsigned int),
-		.nla_policy	= icmp_timeout_nla_policy,
-	},
-#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
-	.init_net		= icmp_init_net,
-	.get_net_proto		= icmp_get_net_proto,
-};
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 37b14dc9d863..339d0762b027 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -5,26 +5,6 @@
 menu "IPv6: Netfilter Configuration"
 	depends on INET && IPV6 && NETFILTER
 
-config NF_DEFRAG_IPV6
-	tristate
-	default n
-
-config NF_CONNTRACK_IPV6
-	tristate "IPv6 connection tracking support"
-	depends on INET && IPV6 && NF_CONNTRACK
-	default m if NETFILTER_ADVANCED=n
-	select NF_DEFRAG_IPV6
-	---help---
-	  Connection tracking keeps a record of what packets have passed
-	  through your machine, in order to figure out how they are related
-	  into connections.
-
-	  This is IPv6 support on Layer 3 independent connection tracking.
-	  Layer 3 independent connection tracking is experimental scheme
-	  which generalize ip_conntrack to support other layer 3 protocols.
-
-	  To compile it as a module, choose M here.  If unsure, say N.
-
 config NF_SOCKET_IPV6
 	tristate "IPv6 socket lookup support"
 	help
@@ -128,7 +108,7 @@ config NF_LOG_IPV6
 
 config NF_NAT_IPV6
 	tristate "IPv6 NAT"
-	depends on NF_CONNTRACK_IPV6
+	depends on NF_CONNTRACK
 	depends on NETFILTER_ADVANCED
 	select NF_NAT
 	help
@@ -328,7 +308,7 @@ config IP6_NF_SECURITY
 
 config IP6_NF_NAT
 	tristate "ip6tables NAT support"
-	depends on NF_CONNTRACK_IPV6
+	depends on NF_CONNTRACK
 	depends on NETFILTER_ADVANCED
 	select NF_NAT
 	select NF_NAT_IPV6
@@ -365,6 +345,7 @@ config IP6_NF_TARGET_NPT
 endif # IP6_NF_NAT
 
 endif # IP6_NF_IPTABLES
-
 endmenu
 
+config NF_DEFRAG_IPV6
+	tristate
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 10a5a1c87320..200c0c235565 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -11,12 +11,6 @@ obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
 obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o
 obj-$(CONFIG_IP6_NF_NAT) += ip6table_nat.o
 
-# objects for l3 independent conntrack
-nf_conntrack_ipv6-y  :=  nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o
-
-# l3 independent conntrack
-obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o
-
 nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
 nf_nat_ipv6-$(CONFIG_NF_NAT_MASQUERADE_IPV6) += nf_nat_masquerade_ipv6.o
 obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
deleted file mode 100644
index 37ab25645cf2..000000000000
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ /dev/null
@@ -1,355 +0,0 @@
-/*
- * Copyright (C)2004 USAGI/WIDE Project
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Author:
- *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
- */
-
-#include <linux/types.h>
-#include <linux/ipv6.h>
-#include <linux/in6.h>
-#include <linux/netfilter.h>
-#include <linux/module.h>
-#include <linux/skbuff.h>
-#include <linux/icmp.h>
-#include <net/ipv6.h>
-#include <net/inet_frag.h>
-
-#include <linux/netfilter_bridge.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter_ipv6/ip6_tables.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_helper.h>
-#include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
-#include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_zones.h>
-#include <net/netfilter/nf_conntrack_seqadj.h>
-#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
-#include <net/netfilter/nf_nat_helper.h>
-#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
-#include <net/netfilter/nf_log.h>
-
-static int conntrack6_net_id;
-static DEFINE_MUTEX(register_ipv6_hooks);
-
-struct conntrack6_net {
-	unsigned int users;
-};
-
-static unsigned int ipv6_helper(void *priv,
-				struct sk_buff *skb,
-				const struct nf_hook_state *state)
-{
-	struct nf_conn *ct;
-	const struct nf_conn_help *help;
-	const struct nf_conntrack_helper *helper;
-	enum ip_conntrack_info ctinfo;
-	__be16 frag_off;
-	int protoff;
-	u8 nexthdr;
-
-	/* This is where we call the helper: as the packet goes out. */
-	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
-		return NF_ACCEPT;
-
-	help = nfct_help(ct);
-	if (!help)
-		return NF_ACCEPT;
-	/* rcu_read_lock()ed by nf_hook_thresh */
-	helper = rcu_dereference(help->helper);
-	if (!helper)
-		return NF_ACCEPT;
-
-	nexthdr = ipv6_hdr(skb)->nexthdr;
-	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
-				   &frag_off);
-	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
-		pr_debug("proto header not found\n");
-		return NF_ACCEPT;
-	}
-
-	return helper->help(skb, protoff, ct, ctinfo);
-}
-
-static unsigned int ipv6_confirm(void *priv,
-				 struct sk_buff *skb,
-				 const struct nf_hook_state *state)
-{
-	struct nf_conn *ct;
-	enum ip_conntrack_info ctinfo;
-	unsigned char pnum = ipv6_hdr(skb)->nexthdr;
-	int protoff;
-	__be16 frag_off;
-
-	ct = nf_ct_get(skb, &ctinfo);
-	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
-		goto out;
-
-	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
-				   &frag_off);
-	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
-		pr_debug("proto header not found\n");
-		goto out;
-	}
-
-	/* adjust seqs for loopback traffic only in outgoing direction */
-	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
-	    !nf_is_loopback_packet(skb)) {
-		if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) {
-			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
-			return NF_DROP;
-		}
-	}
-out:
-	/* We've seen it coming out the other side: confirm it */
-	return nf_conntrack_confirm(skb);
-}
-
-static unsigned int ipv6_conntrack_in(void *priv,
-				      struct sk_buff *skb,
-				      const struct nf_hook_state *state)
-{
-	return nf_conntrack_in(state->net, PF_INET6, state->hook, skb);
-}
-
-static unsigned int ipv6_conntrack_local(void *priv,
-					 struct sk_buff *skb,
-					 const struct nf_hook_state *state)
-{
-	return nf_conntrack_in(state->net, PF_INET6, state->hook, skb);
-}
-
-static const struct nf_hook_ops ipv6_conntrack_ops[] = {
-	{
-		.hook		= ipv6_conntrack_in,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_PRE_ROUTING,
-		.priority	= NF_IP6_PRI_CONNTRACK,
-	},
-	{
-		.hook		= ipv6_conntrack_local,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_LOCAL_OUT,
-		.priority	= NF_IP6_PRI_CONNTRACK,
-	},
-	{
-		.hook		= ipv6_helper,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
-	},
-	{
-		.hook		= ipv6_confirm,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_POST_ROUTING,
-		.priority	= NF_IP6_PRI_LAST,
-	},
-	{
-		.hook		= ipv6_helper,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
-	},
-	{
-		.hook		= ipv6_confirm,
-		.pf		= NFPROTO_IPV6,
-		.hooknum	= NF_INET_LOCAL_IN,
-		.priority	= NF_IP6_PRI_LAST-1,
-	},
-};
-
-static int
-ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
-{
-	struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 };
-	const struct ipv6_pinfo *inet6 = inet6_sk(sk);
-	const struct inet_sock *inet = inet_sk(sk);
-	const struct nf_conntrack_tuple_hash *h;
-	struct sockaddr_in6 sin6;
-	struct nf_conn *ct;
-	__be32 flow_label;
-	int bound_dev_if;
-
-	lock_sock(sk);
-	tuple.src.u3.in6 = sk->sk_v6_rcv_saddr;
-	tuple.src.u.tcp.port = inet->inet_sport;
-	tuple.dst.u3.in6 = sk->sk_v6_daddr;
-	tuple.dst.u.tcp.port = inet->inet_dport;
-	tuple.dst.protonum = sk->sk_protocol;
-	bound_dev_if = sk->sk_bound_dev_if;
-	flow_label = inet6->flow_label;
-	release_sock(sk);
-
-	if (tuple.dst.protonum != IPPROTO_TCP &&
-	    tuple.dst.protonum != IPPROTO_SCTP)
-		return -ENOPROTOOPT;
-
-	if (*len < 0 || (unsigned int) *len < sizeof(sin6))
-		return -EINVAL;
-
-	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
-	if (!h) {
-		pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n",
-			 &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
-			 &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port));
-		return -ENOENT;
-	}
-
-	ct = nf_ct_tuplehash_to_ctrack(h);
-
-	sin6.sin6_family = AF_INET6;
-	sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
-	sin6.sin6_flowinfo = flow_label & IPV6_FLOWINFO_MASK;
-	memcpy(&sin6.sin6_addr,
-		&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6,
-					sizeof(sin6.sin6_addr));
-
-	nf_ct_put(ct);
-	sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, bound_dev_if);
-	return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
-}
-
-static int ipv6_hooks_register(struct net *net)
-{
-	struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
-	int err = 0;
-
-	mutex_lock(&register_ipv6_hooks);
-	cnet->users++;
-	if (cnet->users > 1)
-		goto out_unlock;
-
-	err = nf_defrag_ipv6_enable(net);
-	if (err < 0) {
-		cnet->users = 0;
-		goto out_unlock;
-	}
-
-	err = nf_register_net_hooks(net, ipv6_conntrack_ops,
-				    ARRAY_SIZE(ipv6_conntrack_ops));
-	if (err)
-		cnet->users = 0;
- out_unlock:
-	mutex_unlock(&register_ipv6_hooks);
-	return err;
-}
-
-static void ipv6_hooks_unregister(struct net *net)
-{
-	struct conntrack6_net *cnet = net_generic(net, conntrack6_net_id);
-
-	mutex_lock(&register_ipv6_hooks);
-	if (cnet->users && (--cnet->users == 0))
-		nf_unregister_net_hooks(net, ipv6_conntrack_ops,
-					ARRAY_SIZE(ipv6_conntrack_ops));
-	mutex_unlock(&register_ipv6_hooks);
-}
-
-const struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
-	.l3proto		= PF_INET6,
-	.net_ns_get		= ipv6_hooks_register,
-	.net_ns_put		= ipv6_hooks_unregister,
-	.me			= THIS_MODULE,
-};
-
-MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>");
-
-static struct nf_sockopt_ops so_getorigdst6 = {
-	.pf		= NFPROTO_IPV6,
-	.get_optmin	= IP6T_SO_ORIGINAL_DST,
-	.get_optmax	= IP6T_SO_ORIGINAL_DST + 1,
-	.get		= ipv6_getorigdst,
-	.owner		= THIS_MODULE,
-};
-
-static const struct nf_conntrack_l4proto * const builtin_l4proto6[] = {
-	&nf_conntrack_l4proto_tcp6,
-	&nf_conntrack_l4proto_udp6,
-	&nf_conntrack_l4proto_icmpv6,
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	&nf_conntrack_l4proto_dccp6,
-#endif
-#ifdef CONFIG_NF_CT_PROTO_SCTP
-	&nf_conntrack_l4proto_sctp6,
-#endif
-#ifdef CONFIG_NF_CT_PROTO_UDPLITE
-	&nf_conntrack_l4proto_udplite6,
-#endif
-};
-
-static int ipv6_net_init(struct net *net)
-{
-	return nf_ct_l4proto_pernet_register(net, builtin_l4proto6,
-					     ARRAY_SIZE(builtin_l4proto6));
-}
-
-static void ipv6_net_exit(struct net *net)
-{
-	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto6,
-					ARRAY_SIZE(builtin_l4proto6));
-}
-
-static struct pernet_operations ipv6_net_ops = {
-	.init = ipv6_net_init,
-	.exit = ipv6_net_exit,
-	.id = &conntrack6_net_id,
-	.size = sizeof(struct conntrack6_net),
-};
-
-static int __init nf_conntrack_l3proto_ipv6_init(void)
-{
-	int ret = 0;
-
-	need_conntrack();
-
-	ret = nf_register_sockopt(&so_getorigdst6);
-	if (ret < 0) {
-		pr_err("Unable to register netfilter socket option\n");
-		return ret;
-	}
-
-	ret = register_pernet_subsys(&ipv6_net_ops);
-	if (ret < 0)
-		goto cleanup_sockopt;
-
-	ret = nf_ct_l4proto_register(builtin_l4proto6,
-				     ARRAY_SIZE(builtin_l4proto6));
-	if (ret < 0)
-		goto cleanup_pernet;
-
-	ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6);
-	if (ret < 0) {
-		pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n");
-		goto cleanup_l4proto;
-	}
-	return ret;
-cleanup_l4proto:
-	nf_ct_l4proto_unregister(builtin_l4proto6,
-				 ARRAY_SIZE(builtin_l4proto6));
- cleanup_pernet:
-	unregister_pernet_subsys(&ipv6_net_ops);
- cleanup_sockopt:
-	nf_unregister_sockopt(&so_getorigdst6);
-	return ret;
-}
-
-static void __exit nf_conntrack_l3proto_ipv6_fini(void)
-{
-	synchronize_net();
-	nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
-	nf_ct_l4proto_unregister(builtin_l4proto6,
-				 ARRAY_SIZE(builtin_l4proto6));
-	unregister_pernet_subsys(&ipv6_net_ops);
-	nf_unregister_sockopt(&so_getorigdst6);
-}
-
-module_init(nf_conntrack_l3proto_ipv6_init);
-module_exit(nf_conntrack_l3proto_ipv6_fini);
diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
deleted file mode 100644
index bed07b998a10..000000000000
--- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c
+++ /dev/null
@@ -1,387 +0,0 @@
-/*
- * Copyright (C)2003,2004 USAGI/WIDE Project
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * Author:
- *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
- */
-
-#include <linux/types.h>
-#include <linux/timer.h>
-#include <linux/module.h>
-#include <linux/netfilter.h>
-#include <linux/in6.h>
-#include <linux/icmpv6.h>
-#include <linux/ipv6.h>
-#include <net/ipv6.h>
-#include <net/ip6_checksum.h>
-#include <linux/seq_file.h>
-#include <linux/netfilter_ipv6.h>
-#include <net/netfilter/nf_conntrack_tuple.h>
-#include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_core.h>
-#include <net/netfilter/nf_conntrack_timeout.h>
-#include <net/netfilter/nf_conntrack_zones.h>
-#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
-#include <net/netfilter/nf_log.h>
-
-static const unsigned int nf_ct_icmpv6_timeout = 30*HZ;
-
-static inline struct nf_icmp_net *icmpv6_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.icmpv6;
-}
-
-static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb,
-				unsigned int dataoff,
-				struct net *net,
-				struct nf_conntrack_tuple *tuple)
-{
-	const struct icmp6hdr *hp;
-	struct icmp6hdr _hdr;
-
-	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
-	if (hp == NULL)
-		return false;
-	tuple->dst.u.icmp.type = hp->icmp6_type;
-	tuple->src.u.icmp.id = hp->icmp6_identifier;
-	tuple->dst.u.icmp.code = hp->icmp6_code;
-
-	return true;
-}
-
-/* Add 1; spaces filled with 0. */
-static const u_int8_t invmap[] = {
-	[ICMPV6_ECHO_REQUEST - 128]	= ICMPV6_ECHO_REPLY + 1,
-	[ICMPV6_ECHO_REPLY - 128]	= ICMPV6_ECHO_REQUEST + 1,
-	[ICMPV6_NI_QUERY - 128]		= ICMPV6_NI_REPLY + 1,
-	[ICMPV6_NI_REPLY - 128]		= ICMPV6_NI_QUERY + 1
-};
-
-static const u_int8_t noct_valid_new[] = {
-	[ICMPV6_MGM_QUERY - 130] = 1,
-	[ICMPV6_MGM_REPORT - 130] = 1,
-	[ICMPV6_MGM_REDUCTION - 130] = 1,
-	[NDISC_ROUTER_SOLICITATION - 130] = 1,
-	[NDISC_ROUTER_ADVERTISEMENT - 130] = 1,
-	[NDISC_NEIGHBOUR_SOLICITATION - 130] = 1,
-	[NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1,
-	[ICMPV6_MLD2_REPORT - 130] = 1
-};
-
-static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
-				const struct nf_conntrack_tuple *orig)
-{
-	int type = orig->dst.u.icmp.type - 128;
-	if (type < 0 || type >= sizeof(invmap) || !invmap[type])
-		return false;
-
-	tuple->src.u.icmp.id   = orig->src.u.icmp.id;
-	tuple->dst.u.icmp.type = invmap[type] - 1;
-	tuple->dst.u.icmp.code = orig->dst.u.icmp.code;
-	return true;
-}
-
-static unsigned int *icmpv6_get_timeouts(struct net *net)
-{
-	return &icmpv6_pernet(net)->timeout;
-}
-
-/* Returns verdict for packet, or -1 for invalid. */
-static int icmpv6_packet(struct nf_conn *ct,
-		       const struct sk_buff *skb,
-		       unsigned int dataoff,
-		       enum ip_conntrack_info ctinfo)
-{
-	unsigned int *timeout = nf_ct_timeout_lookup(ct);
-
-	if (!timeout)
-		timeout = icmpv6_get_timeouts(nf_ct_net(ct));
-
-	/* Do not immediately delete the connection after the first
-	   successful reply to avoid excessive conntrackd traffic
-	   and also to handle correctly ICMP echo reply duplicates. */
-	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
-
-	return NF_ACCEPT;
-}
-
-/* Called when a new connection for this protocol found. */
-static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
-		       unsigned int dataoff)
-{
-	static const u_int8_t valid_new[] = {
-		[ICMPV6_ECHO_REQUEST - 128] = 1,
-		[ICMPV6_NI_QUERY - 128] = 1
-	};
-	int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128;
-
-	if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) {
-		/* Can't create a new ICMPv6 `conn' with this. */
-		pr_debug("icmpv6: can't create new conn with type %u\n",
-			 type + 128);
-		nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple);
-		return false;
-	}
-	return true;
-}
-
-static int
-icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
-		     struct sk_buff *skb,
-		     unsigned int icmp6off)
-{
-	struct nf_conntrack_tuple intuple, origtuple;
-	const struct nf_conntrack_tuple_hash *h;
-	const struct nf_conntrack_l4proto *inproto;
-	enum ip_conntrack_info ctinfo;
-	struct nf_conntrack_zone tmp;
-
-	WARN_ON(skb_nfct(skb));
-
-	/* Are they talking about one of our connections? */
-	if (!nf_ct_get_tuplepr(skb,
-			       skb_network_offset(skb)
-				+ sizeof(struct ipv6hdr)
-				+ sizeof(struct icmp6hdr),
-			       PF_INET6, net, &origtuple)) {
-		pr_debug("icmpv6_error: Can't get tuple\n");
-		return -NF_ACCEPT;
-	}
-
-	/* rcu_read_lock()ed by nf_hook_thresh */
-	inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum);
-
-	/* Ordinarily, we'd expect the inverted tupleproto, but it's
-	   been preserved inside the ICMP. */
-	if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) {
-		pr_debug("icmpv6_error: Can't invert tuple\n");
-		return -NF_ACCEPT;
-	}
-
-	ctinfo = IP_CT_RELATED;
-
-	h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
-				  &intuple);
-	if (!h) {
-		pr_debug("icmpv6_error: no match\n");
-		return -NF_ACCEPT;
-	} else {
-		if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
-			ctinfo += IP_CT_IS_REPLY;
-	}
-
-	/* Update skb to refer to this connection */
-	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
-	return NF_ACCEPT;
-}
-
-static void icmpv6_error_log(const struct sk_buff *skb, struct net *net,
-			     u8 pf, const char *msg)
-{
-	nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMPV6, "%s", msg);
-}
-
-static int
-icmpv6_error(struct net *net, struct nf_conn *tmpl,
-	     struct sk_buff *skb, unsigned int dataoff,
-	     u8 pf, unsigned int hooknum)
-{
-	const struct icmp6hdr *icmp6h;
-	struct icmp6hdr _ih;
-	int type;
-
-	icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
-	if (icmp6h == NULL) {
-		icmpv6_error_log(skb, net, pf, "short packet");
-		return -NF_ACCEPT;
-	}
-
-	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
-	    nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
-		icmpv6_error_log(skb, net, pf, "ICMPv6 checksum failed");
-		return -NF_ACCEPT;
-	}
-
-	type = icmp6h->icmp6_type - 130;
-	if (type >= 0 && type < sizeof(noct_valid_new) &&
-	    noct_valid_new[type]) {
-		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
-		return NF_ACCEPT;
-	}
-
-	/* is not error message ? */
-	if (icmp6h->icmp6_type >= 128)
-		return NF_ACCEPT;
-
-	return icmpv6_error_message(net, tmpl, skb, dataoff);
-}
-
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nfnetlink_conntrack.h>
-static int icmpv6_tuple_to_nlattr(struct sk_buff *skb,
-				  const struct nf_conntrack_tuple *t)
-{
-	if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) ||
-	    nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) ||
-	    nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -1;
-}
-
-static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = {
-	[CTA_PROTO_ICMPV6_TYPE]	= { .type = NLA_U8 },
-	[CTA_PROTO_ICMPV6_CODE]	= { .type = NLA_U8 },
-	[CTA_PROTO_ICMPV6_ID]	= { .type = NLA_U16 },
-};
-
-static int icmpv6_nlattr_to_tuple(struct nlattr *tb[],
-				struct nf_conntrack_tuple *tuple)
-{
-	if (!tb[CTA_PROTO_ICMPV6_TYPE] ||
-	    !tb[CTA_PROTO_ICMPV6_CODE] ||
-	    !tb[CTA_PROTO_ICMPV6_ID])
-		return -EINVAL;
-
-	tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]);
-	tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]);
-	tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]);
-
-	if (tuple->dst.u.icmp.type < 128 ||
-	    tuple->dst.u.icmp.type - 128 >= sizeof(invmap) ||
-	    !invmap[tuple->dst.u.icmp.type - 128])
-		return -EINVAL;
-
-	return 0;
-}
-
-static unsigned int icmpv6_nlattr_tuple_size(void)
-{
-	static unsigned int size __read_mostly;
-
-	if (!size)
-		size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1);
-
-	return size;
-}
-#endif
-
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nfnetlink_cttimeout.h>
-
-static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[],
-					struct net *net, void *data)
-{
-	unsigned int *timeout = data;
-	struct nf_icmp_net *in = icmpv6_pernet(net);
-
-	if (!timeout)
-		timeout = icmpv6_get_timeouts(net);
-	if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) {
-		*timeout =
-		    ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ;
-	} else {
-		/* Set default ICMPv6 timeout. */
-		*timeout = in->timeout;
-	}
-	return 0;
-}
-
-static int
-icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
-{
-	const unsigned int *timeout = data;
-
-	if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ)))
-		goto nla_put_failure;
-	return 0;
-
-nla_put_failure:
-	return -ENOSPC;
-}
-
-static const struct nla_policy
-icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = {
-	[CTA_TIMEOUT_ICMPV6_TIMEOUT]	= { .type = NLA_U32 },
-};
-#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
-
-#ifdef CONFIG_SYSCTL
-static struct ctl_table icmpv6_sysctl_table[] = {
-	{
-		.procname	= "nf_conntrack_icmpv6_timeout",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	{ }
-};
-#endif /* CONFIG_SYSCTL */
-
-static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn,
-				       struct nf_icmp_net *in)
-{
-#ifdef CONFIG_SYSCTL
-	pn->ctl_table = kmemdup(icmpv6_sysctl_table,
-				sizeof(icmpv6_sysctl_table),
-				GFP_KERNEL);
-	if (!pn->ctl_table)
-		return -ENOMEM;
-
-	pn->ctl_table[0].data = &in->timeout;
-#endif
-	return 0;
-}
-
-static int icmpv6_init_net(struct net *net, u_int16_t proto)
-{
-	struct nf_icmp_net *in = icmpv6_pernet(net);
-	struct nf_proto_net *pn = &in->pn;
-
-	in->timeout = nf_ct_icmpv6_timeout;
-
-	return icmpv6_kmemdup_sysctl_table(pn, in);
-}
-
-static struct nf_proto_net *icmpv6_get_net_proto(struct net *net)
-{
-	return &net->ct.nf_ct_proto.icmpv6.pn;
-}
-
-const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 =
-{
-	.l3proto		= PF_INET6,
-	.l4proto		= IPPROTO_ICMPV6,
-	.pkt_to_tuple		= icmpv6_pkt_to_tuple,
-	.invert_tuple		= icmpv6_invert_tuple,
-	.packet			= icmpv6_packet,
-	.new			= icmpv6_new,
-	.error			= icmpv6_error,
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.tuple_to_nlattr	= icmpv6_tuple_to_nlattr,
-	.nlattr_tuple_size	= icmpv6_nlattr_tuple_size,
-	.nlattr_to_tuple	= icmpv6_nlattr_to_tuple,
-	.nla_policy		= icmpv6_nla_policy,
-#endif
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
-	.ctnl_timeout		= {
-		.nlattr_to_obj	= icmpv6_timeout_nlattr_to_obj,
-		.obj_to_nlattr	= icmpv6_timeout_obj_to_nlattr,
-		.nlattr_max	= CTA_TIMEOUT_ICMP_MAX,
-		.obj_size	= sizeof(unsigned int),
-		.nla_policy	= icmpv6_timeout_nla_policy,
-	},
-#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
-	.init_net		= icmpv6_init_net,
-	.get_net_proto		= icmpv6_get_net_proto,
-};
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 3ce657fbca67..9eab519b403a 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -49,6 +49,8 @@ config NETFILTER_NETLINK_LOG
 config NF_CONNTRACK
 	tristate "Netfilter connection tracking support"
 	default m if NETFILTER_ADVANCED=n
+	select NF_DEFRAG_IPV4
+	select NF_DEFRAG_IPV6 if IPV6 != n
 	help
 	  Connection tracking keeps a record of what packets have passed
 	  through your machine, in order to figure out how they are related
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index f132ea850778..53bd1ed1228a 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -1,7 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o utils.o
 
-nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
+nf_conntrack-y	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o \
+		   nf_conntrack_proto.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o \
+		   nf_conntrack_proto_icmp.o \
+		   nf_conntrack_extend.o nf_conntrack_acct.o nf_conntrack_seqadj.o
+
+nf_conntrack-$(subst m,y,$(CONFIG_IPV6)) += nf_conntrack_proto_icmpv6.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMEOUT) += nf_conntrack_timeout.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index c069f2faff4c..5123e91b1982 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -291,7 +291,6 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    u_int8_t *protonum)
 {
 	int dataoff = -1;
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV4)
 	const struct iphdr *iph;
 	struct iphdr _iph;
 
@@ -314,15 +313,14 @@ static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			 nhoff, iph->ihl << 2, skb->len);
 		return -1;
 	}
-#endif
 	return dataoff;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 			    u8 *protonum)
 {
 	int protoff = -1;
-#if IS_ENABLED(CONFIG_NF_CONNTRACK_IPV6)
 	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
 	__be16 frag_off;
 	u8 nexthdr;
@@ -343,9 +341,9 @@ static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
 	}
 
 	*protonum = nexthdr;
-#endif
 	return protoff;
 }
+#endif
 
 static int get_l4proto(const struct sk_buff *skb,
 		       unsigned int nhoff, u8 pf, u8 *l4num)
@@ -353,8 +351,10 @@ static int get_l4proto(const struct sk_buff *skb,
 	switch (pf) {
 	case NFPROTO_IPV4:
 		return ipv4_get_l4proto(skb, nhoff, l4num);
+#if IS_ENABLED(CONFIG_IPV6)
 	case NFPROTO_IPV6:
 		return ipv6_get_l4proto(skb, nhoff, l4num);
+#endif
 	default:
 		*l4num = 0;
 		break;
@@ -2197,9 +2197,6 @@ int nf_conntrack_set_hashsize(const char *val, const struct kernel_param *kp)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize);
 
-module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
-		  &nf_conntrack_htable_size, 0600);
-
 static __always_inline unsigned int total_extension_size(void)
 {
 	/* remember to add new extensions below */
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 39df72bb9d56..803607a90102 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -1,14 +1,4 @@
-/* L3/L4 protocol support for nf_conntrack. */
-
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>
- * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>
- * (C) 2006-2012 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
 
 #include <linux/types.h>
 #include <linux/netfilter.h>
@@ -24,22 +14,39 @@
 #include <linux/netdevice.h>
 
 #include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_core.h>
 #include <net/netfilter/nf_log.h>
 
+#include <linux/ip.h>
+#include <linux/icmp.h>
+#include <linux/sysctl.h>
+#include <net/route.h>
+#include <net/ip.h>
+
+#include <linux/netfilter_ipv4.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_conntrack_seqadj.h>
+#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
+#include <net/netfilter/nf_nat_helper.h>
+#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+
+#include <linux/ipv6.h>
+#include <linux/in6.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+extern unsigned int nf_conntrack_net_id;
+
 static struct nf_conntrack_l4proto __rcu **nf_ct_protos[NFPROTO_NUMPROTO] __read_mostly;
-struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[NFPROTO_NUMPROTO] __read_mostly;
-EXPORT_SYMBOL_GPL(nf_ct_l3protos);
 
 static DEFINE_MUTEX(nf_ct_proto_mutex);
 
-struct nf_conntrack_l3proto nf_conntrack_l3proto_generic __read_mostly = {
-	.l3proto	 = PF_UNSPEC,
-};
-EXPORT_SYMBOL_GPL(nf_conntrack_l3proto_generic);
-
 #ifdef CONFIG_SYSCTL
 static int
 nf_ct_register_sysctl(struct net *net,
@@ -127,137 +134,6 @@ __nf_ct_l4proto_find(u_int16_t l3proto, u_int8_t l4proto)
 }
 EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find);
 
-/* this is guaranteed to always return a valid protocol helper, since
- * it falls back to generic_protocol */
-const struct nf_conntrack_l3proto *
-nf_ct_l3proto_find_get(u_int16_t l3proto)
-{
-	struct nf_conntrack_l3proto *p;
-
-	rcu_read_lock();
-	p = __nf_ct_l3proto_find(l3proto);
-	if (!try_module_get(p->me))
-		p = &nf_conntrack_l3proto_generic;
-	rcu_read_unlock();
-
-	return p;
-}
-EXPORT_SYMBOL_GPL(nf_ct_l3proto_find_get);
-
-int
-nf_ct_l3proto_try_module_get(unsigned short l3proto)
-{
-	const struct nf_conntrack_l3proto *p;
-	int ret;
-
-retry:	p = nf_ct_l3proto_find_get(l3proto);
-	if (p == &nf_conntrack_l3proto_generic) {
-		ret = request_module("nf_conntrack-%d", l3proto);
-		if (!ret)
-			goto retry;
-
-		return -EPROTOTYPE;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(nf_ct_l3proto_try_module_get);
-
-void nf_ct_l3proto_module_put(unsigned short l3proto)
-{
-	struct nf_conntrack_l3proto *p;
-
-	/* rcu_read_lock not necessary since the caller holds a reference, but
-	 * taken anyways to avoid lockdep warnings in __nf_ct_l3proto_find()
-	 */
-	rcu_read_lock();
-	p = __nf_ct_l3proto_find(l3proto);
-	module_put(p->me);
-	rcu_read_unlock();
-}
-EXPORT_SYMBOL_GPL(nf_ct_l3proto_module_put);
-
-static int nf_ct_netns_do_get(struct net *net, u8 nfproto)
-{
-	const struct nf_conntrack_l3proto *l3proto;
-	int ret;
-
-	might_sleep();
-
-	ret = nf_ct_l3proto_try_module_get(nfproto);
-	if (ret < 0)
-		return ret;
-
-	/* we already have a reference, can't fail */
-	rcu_read_lock();
-	l3proto = __nf_ct_l3proto_find(nfproto);
-	rcu_read_unlock();
-
-	if (!l3proto->net_ns_get)
-		return 0;
-
-	ret = l3proto->net_ns_get(net);
-	if (ret < 0)
-		nf_ct_l3proto_module_put(nfproto);
-
-	return ret;
-}
-
-int nf_ct_netns_get(struct net *net, u8 nfproto)
-{
-	int err;
-
-	if (nfproto == NFPROTO_INET) {
-		err = nf_ct_netns_do_get(net, NFPROTO_IPV4);
-		if (err < 0)
-			goto err1;
-		err = nf_ct_netns_do_get(net, NFPROTO_IPV6);
-		if (err < 0)
-			goto err2;
-	} else {
-		err = nf_ct_netns_do_get(net, nfproto);
-		if (err < 0)
-			goto err1;
-	}
-	return 0;
-
-err2:
-	nf_ct_netns_put(net, NFPROTO_IPV4);
-err1:
-	return err;
-}
-EXPORT_SYMBOL_GPL(nf_ct_netns_get);
-
-static void nf_ct_netns_do_put(struct net *net, u8 nfproto)
-{
-	const struct nf_conntrack_l3proto *l3proto;
-
-	might_sleep();
-
-	/* same as nf_conntrack_netns_get(), reference assumed */
-	rcu_read_lock();
-	l3proto = __nf_ct_l3proto_find(nfproto);
-	rcu_read_unlock();
-
-	if (WARN_ON(!l3proto))
-		return;
-
-	if (l3proto->net_ns_put)
-		l3proto->net_ns_put(net);
-
-	nf_ct_l3proto_module_put(nfproto);
-}
-
-void nf_ct_netns_put(struct net *net, uint8_t nfproto)
-{
-	if (nfproto == NFPROTO_INET) {
-		nf_ct_netns_do_put(net, NFPROTO_IPV4);
-		nf_ct_netns_do_put(net, NFPROTO_IPV6);
-	} else
-		nf_ct_netns_do_put(net, nfproto);
-}
-EXPORT_SYMBOL_GPL(nf_ct_netns_put);
-
 const struct nf_conntrack_l4proto *
 nf_ct_l4proto_find_get(u_int16_t l3num, u_int8_t l4num)
 {
@@ -279,11 +155,6 @@ void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p)
 }
 EXPORT_SYMBOL_GPL(nf_ct_l4proto_put);
 
-static int kill_l3proto(struct nf_conn *i, void *data)
-{
-	return nf_ct_l3num(i) == ((const struct nf_conntrack_l3proto *)data)->l3proto;
-}
-
 static int kill_l4proto(struct nf_conn *i, void *data)
 {
 	const struct nf_conntrack_l4proto *l4proto;
@@ -292,49 +163,6 @@ static int kill_l4proto(struct nf_conn *i, void *data)
 	       nf_ct_l3num(i) == l4proto->l3proto;
 }
 
-int nf_ct_l3proto_register(const struct nf_conntrack_l3proto *proto)
-{
-	int ret = 0;
-	struct nf_conntrack_l3proto *old;
-
-	if (proto->l3proto >= NFPROTO_NUMPROTO)
-		return -EBUSY;
-
-	mutex_lock(&nf_ct_proto_mutex);
-	old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
-					lockdep_is_held(&nf_ct_proto_mutex));
-	if (old != &nf_conntrack_l3proto_generic) {
-		ret = -EBUSY;
-		goto out_unlock;
-	}
-
-	rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], proto);
-
-out_unlock:
-	mutex_unlock(&nf_ct_proto_mutex);
-	return ret;
-
-}
-EXPORT_SYMBOL_GPL(nf_ct_l3proto_register);
-
-void nf_ct_l3proto_unregister(const struct nf_conntrack_l3proto *proto)
-{
-	BUG_ON(proto->l3proto >= NFPROTO_NUMPROTO);
-
-	mutex_lock(&nf_ct_proto_mutex);
-	BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto],
-					 lockdep_is_held(&nf_ct_proto_mutex)
-					 ) != proto);
-	rcu_assign_pointer(nf_ct_l3protos[proto->l3proto],
-			   &nf_conntrack_l3proto_generic);
-	mutex_unlock(&nf_ct_proto_mutex);
-
-	synchronize_rcu();
-	/* Remove all contrack entries for this protocol */
-	nf_ct_iterate_destroy(kill_l3proto, (void*)proto);
-}
-EXPORT_SYMBOL_GPL(nf_ct_l3proto_unregister);
-
 static struct nf_proto_net *nf_ct_l4proto_net(struct net *net,
 				const struct nf_conntrack_l4proto *l4proto)
 {
@@ -501,8 +329,23 @@ void nf_ct_l4proto_pernet_unregister_one(struct net *net,
 }
 EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one);
 
-int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[],
-			   unsigned int num_proto)
+static void
+nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[],
+			 unsigned int num_proto)
+{
+	mutex_lock(&nf_ct_proto_mutex);
+	while (num_proto-- != 0)
+		__nf_ct_l4proto_unregister_one(l4proto[num_proto]);
+	mutex_unlock(&nf_ct_proto_mutex);
+
+	synchronize_net();
+	/* Remove all contrack entries for this protocol */
+	nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto);
+}
+
+static int
+nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[],
+		       unsigned int num_proto)
 {
 	int ret = -EINVAL, ver;
 	unsigned int i;
@@ -520,7 +363,6 @@ int nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[],
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_register);
 
 int nf_ct_l4proto_pernet_register(struct net *net,
 				  const struct nf_conntrack_l4proto *const l4proto[],
@@ -544,20 +386,6 @@ int nf_ct_l4proto_pernet_register(struct net *net,
 }
 EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register);
 
-void nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[],
-			      unsigned int num_proto)
-{
-	mutex_lock(&nf_ct_proto_mutex);
-	while (num_proto-- != 0)
-		__nf_ct_l4proto_unregister_one(l4proto[num_proto]);
-	mutex_unlock(&nf_ct_proto_mutex);
-
-	synchronize_net();
-	/* Remove all contrack entries for this protocol */
-	nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto);
-}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister);
-
 void nf_ct_l4proto_pernet_unregister(struct net *net,
 				const struct nf_conntrack_l4proto *const l4proto[],
 				unsigned int num_proto)
@@ -567,6 +395,563 @@ void nf_ct_l4proto_pernet_unregister(struct net *net,
 }
 EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister);
 
+static unsigned int ipv4_helper(void *priv,
+				struct sk_buff *skb,
+				const struct nf_hook_state *state)
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	const struct nf_conn_help *help;
+	const struct nf_conntrack_helper *helper;
+
+	/* This is where we call the helper: as the packet goes out. */
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+		return NF_ACCEPT;
+
+	help = nfct_help(ct);
+	if (!help)
+		return NF_ACCEPT;
+
+	/* rcu_read_lock()ed by nf_hook_thresh */
+	helper = rcu_dereference(help->helper);
+	if (!helper)
+		return NF_ACCEPT;
+
+	return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb),
+			    ct, ctinfo);
+}
+
+static unsigned int ipv4_confirm(void *priv,
+				 struct sk_buff *skb,
+				 const struct nf_hook_state *state)
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+		goto out;
+
+	/* adjust seqs for loopback traffic only in outgoing direction */
+	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+	    !nf_is_loopback_packet(skb)) {
+		if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) {
+			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
+			return NF_DROP;
+		}
+	}
+out:
+	/* We've seen it coming out the other side: confirm it */
+	return nf_conntrack_confirm(skb);
+}
+
+static unsigned int ipv4_conntrack_in(void *priv,
+				      struct sk_buff *skb,
+				      const struct nf_hook_state *state)
+{
+	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
+}
+
+static unsigned int ipv4_conntrack_local(void *priv,
+					 struct sk_buff *skb,
+					 const struct nf_hook_state *state)
+{
+	if (ip_is_fragment(ip_hdr(skb))) { /* IP_NODEFRAG setsockopt set */
+		enum ip_conntrack_info ctinfo;
+		struct nf_conn *tmpl;
+
+		tmpl = nf_ct_get(skb, &ctinfo);
+		if (tmpl && nf_ct_is_template(tmpl)) {
+			/* when skipping ct, clear templates to avoid fooling
+			 * later targets/matches
+			 */
+			skb->_nfct = 0;
+			nf_ct_put(tmpl);
+		}
+		return NF_ACCEPT;
+	}
+
+	return nf_conntrack_in(state->net, PF_INET, state->hook, skb);
+}
+
+/* Connection tracking may drop packets, but never alters them, so
+ * make it the first hook.
+ */
+static const struct nf_hook_ops ipv4_conntrack_ops[] = {
+	{
+		.hook		= ipv4_conntrack_in,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP_PRI_CONNTRACK,
+	},
+	{
+		.hook		= ipv4_conntrack_local,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP_PRI_CONNTRACK,
+	},
+	{
+		.hook		= ipv4_helper,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP_PRI_CONNTRACK_HELPER,
+	},
+	{
+		.hook		= ipv4_confirm,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
+	},
+	{
+		.hook		= ipv4_helper,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP_PRI_CONNTRACK_HELPER,
+	},
+	{
+		.hook		= ipv4_confirm,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP_PRI_CONNTRACK_CONFIRM,
+	},
+};
+
+/* Fast function for those who don't want to parse /proc (and I don't
+ * blame them).
+ * Reversing the socket's dst/src point of view gives us the reply
+ * mapping.
+ */
+static int
+getorigdst(struct sock *sk, int optval, void __user *user, int *len)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct nf_conntrack_tuple_hash *h;
+	struct nf_conntrack_tuple tuple;
+
+	memset(&tuple, 0, sizeof(tuple));
+
+	lock_sock(sk);
+	tuple.src.u3.ip = inet->inet_rcv_saddr;
+	tuple.src.u.tcp.port = inet->inet_sport;
+	tuple.dst.u3.ip = inet->inet_daddr;
+	tuple.dst.u.tcp.port = inet->inet_dport;
+	tuple.src.l3num = PF_INET;
+	tuple.dst.protonum = sk->sk_protocol;
+	release_sock(sk);
+
+	/* We only do TCP and SCTP at the moment: is there a better way? */
+	if (tuple.dst.protonum != IPPROTO_TCP &&
+	    tuple.dst.protonum != IPPROTO_SCTP) {
+		pr_debug("SO_ORIGINAL_DST: Not a TCP/SCTP socket\n");
+		return -ENOPROTOOPT;
+	}
+
+	if ((unsigned int)*len < sizeof(struct sockaddr_in)) {
+		pr_debug("SO_ORIGINAL_DST: len %d not %zu\n",
+			 *len, sizeof(struct sockaddr_in));
+		return -EINVAL;
+	}
+
+	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
+	if (h) {
+		struct sockaddr_in sin;
+		struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+		sin.sin_family = AF_INET;
+		sin.sin_port = ct->tuplehash[IP_CT_DIR_ORIGINAL]
+			.tuple.dst.u.tcp.port;
+		sin.sin_addr.s_addr = ct->tuplehash[IP_CT_DIR_ORIGINAL]
+			.tuple.dst.u3.ip;
+		memset(sin.sin_zero, 0, sizeof(sin.sin_zero));
+
+		pr_debug("SO_ORIGINAL_DST: %pI4 %u\n",
+			 &sin.sin_addr.s_addr, ntohs(sin.sin_port));
+		nf_ct_put(ct);
+		if (copy_to_user(user, &sin, sizeof(sin)) != 0)
+			return -EFAULT;
+		else
+			return 0;
+	}
+	pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n",
+		 &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port),
+		 &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port));
+	return -ENOENT;
+}
+
+static struct nf_sockopt_ops so_getorigdst = {
+	.pf		= PF_INET,
+	.get_optmin	= SO_ORIGINAL_DST,
+	.get_optmax	= SO_ORIGINAL_DST + 1,
+	.get		= getorigdst,
+	.owner		= THIS_MODULE,
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int
+ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
+{
+	struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 };
+	const struct ipv6_pinfo *inet6 = inet6_sk(sk);
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct nf_conntrack_tuple_hash *h;
+	struct sockaddr_in6 sin6;
+	struct nf_conn *ct;
+	__be32 flow_label;
+	int bound_dev_if;
+
+	lock_sock(sk);
+	tuple.src.u3.in6 = sk->sk_v6_rcv_saddr;
+	tuple.src.u.tcp.port = inet->inet_sport;
+	tuple.dst.u3.in6 = sk->sk_v6_daddr;
+	tuple.dst.u.tcp.port = inet->inet_dport;
+	tuple.dst.protonum = sk->sk_protocol;
+	bound_dev_if = sk->sk_bound_dev_if;
+	flow_label = inet6->flow_label;
+	release_sock(sk);
+
+	if (tuple.dst.protonum != IPPROTO_TCP &&
+	    tuple.dst.protonum != IPPROTO_SCTP)
+		return -ENOPROTOOPT;
+
+	if (*len < 0 || (unsigned int)*len < sizeof(sin6))
+		return -EINVAL;
+
+	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
+	if (!h) {
+		pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n",
+			 &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
+			 &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port));
+		return -ENOENT;
+	}
+
+	ct = nf_ct_tuplehash_to_ctrack(h);
+
+	sin6.sin6_family = AF_INET6;
+	sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
+	sin6.sin6_flowinfo = flow_label & IPV6_FLOWINFO_MASK;
+	memcpy(&sin6.sin6_addr,
+	       &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6,
+	       sizeof(sin6.sin6_addr));
+
+	nf_ct_put(ct);
+	sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr, bound_dev_if);
+	return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
+}
+
+static struct nf_sockopt_ops so_getorigdst6 = {
+	.pf		= NFPROTO_IPV6,
+	.get_optmin	= IP6T_SO_ORIGINAL_DST,
+	.get_optmax	= IP6T_SO_ORIGINAL_DST + 1,
+	.get		= ipv6_getorigdst,
+	.owner		= THIS_MODULE,
+};
+
+static unsigned int ipv6_confirm(void *priv,
+				 struct sk_buff *skb,
+				 const struct nf_hook_state *state)
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned char pnum = ipv6_hdr(skb)->nexthdr;
+	int protoff;
+	__be16 frag_off;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+		goto out;
+
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
+				   &frag_off);
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		pr_debug("proto header not found\n");
+		goto out;
+	}
+
+	/* adjust seqs for loopback traffic only in outgoing direction */
+	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+	    !nf_is_loopback_packet(skb)) {
+		if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) {
+			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
+			return NF_DROP;
+		}
+	}
+out:
+	/* We've seen it coming out the other side: confirm it */
+	return nf_conntrack_confirm(skb);
+}
+
+static unsigned int ipv6_conntrack_in(void *priv,
+				      struct sk_buff *skb,
+				      const struct nf_hook_state *state)
+{
+	return nf_conntrack_in(state->net, PF_INET6, state->hook, skb);
+}
+
+static unsigned int ipv6_conntrack_local(void *priv,
+					 struct sk_buff *skb,
+					 const struct nf_hook_state *state)
+{
+	return nf_conntrack_in(state->net, PF_INET6, state->hook, skb);
+}
+
+static unsigned int ipv6_helper(void *priv,
+				struct sk_buff *skb,
+				const struct nf_hook_state *state)
+{
+	struct nf_conn *ct;
+	const struct nf_conn_help *help;
+	const struct nf_conntrack_helper *helper;
+	enum ip_conntrack_info ctinfo;
+	__be16 frag_off;
+	int protoff;
+	u8 nexthdr;
+
+	/* This is where we call the helper: as the packet goes out. */
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+		return NF_ACCEPT;
+
+	help = nfct_help(ct);
+	if (!help)
+		return NF_ACCEPT;
+	/* rcu_read_lock()ed by nf_hook_thresh */
+	helper = rcu_dereference(help->helper);
+	if (!helper)
+		return NF_ACCEPT;
+
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				   &frag_off);
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		pr_debug("proto header not found\n");
+		return NF_ACCEPT;
+	}
+
+	return helper->help(skb, protoff, ct, ctinfo);
+}
+
+static const struct nf_hook_ops ipv6_conntrack_ops[] = {
+	{
+		.hook		= ipv6_conntrack_in,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_CONNTRACK,
+	},
+	{
+		.hook		= ipv6_conntrack_local,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_CONNTRACK,
+	},
+	{
+		.hook		= ipv6_helper,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
+	},
+	{
+		.hook		= ipv6_confirm,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP6_PRI_LAST,
+	},
+	{
+		.hook		= ipv6_helper,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
+	},
+	{
+		.hook		= ipv6_confirm,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP6_PRI_LAST - 1,
+	},
+};
+#endif
+
+static int nf_ct_netns_do_get(struct net *net, u8 nfproto)
+{
+	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+	int err = 0;
+
+	mutex_lock(&nf_ct_proto_mutex);
+
+	switch (nfproto) {
+	case NFPROTO_IPV4:
+		cnet->users4++;
+		if (cnet->users4 > 1)
+			goto out_unlock;
+		err = nf_defrag_ipv4_enable(net);
+		if (err) {
+			cnet->users4 = 0;
+			goto out_unlock;
+		}
+
+		err = nf_register_net_hooks(net, ipv4_conntrack_ops,
+					    ARRAY_SIZE(ipv4_conntrack_ops));
+		if (err)
+			cnet->users4 = 0;
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case NFPROTO_IPV6:
+		cnet->users6++;
+		if (cnet->users6 > 1)
+			goto out_unlock;
+		err = nf_defrag_ipv6_enable(net);
+		if (err < 0) {
+			cnet->users6 = 0;
+			goto out_unlock;
+		}
+
+		err = nf_register_net_hooks(net, ipv6_conntrack_ops,
+					    ARRAY_SIZE(ipv6_conntrack_ops));
+		if (err)
+			cnet->users6 = 0;
+		break;
+#endif
+	default:
+		err = -EPROTO;
+		break;
+	}
+ out_unlock:
+	mutex_unlock(&nf_ct_proto_mutex);
+	return err;
+}
+
+static void nf_ct_netns_do_put(struct net *net, u8 nfproto)
+{
+	struct nf_conntrack_net *cnet = net_generic(net, nf_conntrack_net_id);
+
+	mutex_lock(&nf_ct_proto_mutex);
+	switch (nfproto) {
+	case NFPROTO_IPV4:
+		if (cnet->users4 && (--cnet->users4 == 0))
+			nf_unregister_net_hooks(net, ipv4_conntrack_ops,
+						ARRAY_SIZE(ipv4_conntrack_ops));
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case NFPROTO_IPV6:
+		if (cnet->users6 && (--cnet->users6 == 0))
+			nf_unregister_net_hooks(net, ipv6_conntrack_ops,
+						ARRAY_SIZE(ipv6_conntrack_ops));
+		break;
+#endif
+	}
+
+	mutex_unlock(&nf_ct_proto_mutex);
+}
+
+int nf_ct_netns_get(struct net *net, u8 nfproto)
+{
+	int err;
+
+	if (nfproto == NFPROTO_INET) {
+		err = nf_ct_netns_do_get(net, NFPROTO_IPV4);
+		if (err < 0)
+			goto err1;
+		err = nf_ct_netns_do_get(net, NFPROTO_IPV6);
+		if (err < 0)
+			goto err2;
+	} else {
+		err = nf_ct_netns_do_get(net, nfproto);
+		if (err < 0)
+			goto err1;
+	}
+	return 0;
+
+err2:
+	nf_ct_netns_put(net, NFPROTO_IPV4);
+err1:
+	return err;
+}
+EXPORT_SYMBOL_GPL(nf_ct_netns_get);
+
+void nf_ct_netns_put(struct net *net, uint8_t nfproto)
+{
+	if (nfproto == NFPROTO_INET) {
+		nf_ct_netns_do_put(net, NFPROTO_IPV4);
+		nf_ct_netns_do_put(net, NFPROTO_IPV6);
+	} else {
+		nf_ct_netns_do_put(net, nfproto);
+	}
+}
+EXPORT_SYMBOL_GPL(nf_ct_netns_put);
+
+static const struct nf_conntrack_l4proto * const builtin_l4proto[] = {
+	&nf_conntrack_l4proto_tcp4,
+	&nf_conntrack_l4proto_udp4,
+	&nf_conntrack_l4proto_icmp,
+#ifdef CONFIG_NF_CT_PROTO_DCCP
+	&nf_conntrack_l4proto_dccp4,
+#endif
+#ifdef CONFIG_NF_CT_PROTO_SCTP
+	&nf_conntrack_l4proto_sctp4,
+#endif
+#ifdef CONFIG_NF_CT_PROTO_UDPLITE
+	&nf_conntrack_l4proto_udplite4,
+#endif
+#if IS_ENABLED(CONFIG_IPV6)
+	&nf_conntrack_l4proto_tcp6,
+	&nf_conntrack_l4proto_udp6,
+	&nf_conntrack_l4proto_icmpv6,
+#ifdef CONFIG_NF_CT_PROTO_DCCP
+	&nf_conntrack_l4proto_dccp6,
+#endif
+#ifdef CONFIG_NF_CT_PROTO_SCTP
+	&nf_conntrack_l4proto_sctp6,
+#endif
+#ifdef CONFIG_NF_CT_PROTO_UDPLITE
+	&nf_conntrack_l4proto_udplite6,
+#endif
+#endif /* CONFIG_IPV6 */
+};
+
+int nf_conntrack_proto_init(void)
+{
+	int ret = 0;
+
+	ret = nf_register_sockopt(&so_getorigdst);
+	if (ret < 0)
+		return ret;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	ret = nf_register_sockopt(&so_getorigdst6);
+	if (ret < 0)
+		goto cleanup_sockopt;
+#endif
+	ret = nf_ct_l4proto_register(builtin_l4proto,
+				     ARRAY_SIZE(builtin_l4proto));
+	if (ret < 0)
+		goto cleanup_sockopt2;
+
+	return ret;
+cleanup_sockopt2:
+	nf_unregister_sockopt(&so_getorigdst);
+#if IS_ENABLED(CONFIG_IPV6)
+cleanup_sockopt:
+	nf_unregister_sockopt(&so_getorigdst6);
+#endif
+	return ret;
+}
+
+void nf_conntrack_proto_fini(void)
+{
+	unsigned int i;
+
+	nf_ct_l4proto_unregister(builtin_l4proto,
+				 ARRAY_SIZE(builtin_l4proto));
+	nf_unregister_sockopt(&so_getorigdst);
+#if IS_ENABLED(CONFIG_IPV6)
+	nf_unregister_sockopt(&so_getorigdst6);
+#endif
+
+	/* free l3proto protocol tables */
+	for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++)
+		kfree(nf_ct_protos[i]);
+}
+
 int nf_conntrack_proto_pernet_init(struct net *net)
 {
 	int err;
@@ -583,6 +968,14 @@ int nf_conntrack_proto_pernet_init(struct net *net)
 	if (err < 0)
 		return err;
 
+	err = nf_ct_l4proto_pernet_register(net, builtin_l4proto,
+					    ARRAY_SIZE(builtin_l4proto));
+	if (err < 0) {
+		nf_ct_l4proto_unregister_sysctl(net, pn,
+						&nf_conntrack_l4proto_generic);
+		return err;
+	}
+
 	pn->users++;
 	return 0;
 }
@@ -592,25 +985,19 @@ void nf_conntrack_proto_pernet_fini(struct net *net)
 	struct nf_proto_net *pn = nf_ct_l4proto_net(net,
 					&nf_conntrack_l4proto_generic);
 
+	nf_ct_l4proto_pernet_unregister(net, builtin_l4proto,
+					ARRAY_SIZE(builtin_l4proto));
 	pn->users--;
 	nf_ct_l4proto_unregister_sysctl(net,
 					pn,
 					&nf_conntrack_l4proto_generic);
 }
 
-int nf_conntrack_proto_init(void)
-{
-	unsigned int i;
-	for (i = 0; i < NFPROTO_NUMPROTO; i++)
-		rcu_assign_pointer(nf_ct_l3protos[i],
-				   &nf_conntrack_l3proto_generic);
-	return 0;
-}
 
-void nf_conntrack_proto_fini(void)
-{
-	unsigned int i;
-	/* free l3proto protocol tables */
-	for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++)
-		kfree(nf_ct_protos[i]);
-}
+module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint,
+		  &nf_conntrack_htable_size, 0600);
+
+MODULE_ALIAS("ip_conntrack");
+MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET));
+MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
+MODULE_LICENSE("GPL");
diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c
new file mode 100644
index 000000000000..036670b38282
--- /dev/null
+++ b/net/netfilter/nf_conntrack_proto_icmp.c
@@ -0,0 +1,388 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ * (C) 2006-2010 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/netfilter.h>
+#include <linux/in.h>
+#include <linux/icmp.h>
+#include <linux/seq_file.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <linux/netfilter_ipv4.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/nf_log.h>
+
+static const unsigned int nf_ct_icmp_timeout = 30*HZ;
+
+static inline struct nf_icmp_net *icmp_pernet(struct net *net)
+{
+	return &net->ct.nf_ct_proto.icmp;
+}
+
+static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
+			      struct net *net, struct nf_conntrack_tuple *tuple)
+{
+	const struct icmphdr *hp;
+	struct icmphdr _hdr;
+
+	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
+	if (hp == NULL)
+		return false;
+
+	tuple->dst.u.icmp.type = hp->type;
+	tuple->src.u.icmp.id = hp->un.echo.id;
+	tuple->dst.u.icmp.code = hp->code;
+
+	return true;
+}
+
+/* Add 1; spaces filled with 0. */
+static const u_int8_t invmap[] = {
+	[ICMP_ECHO] = ICMP_ECHOREPLY + 1,
+	[ICMP_ECHOREPLY] = ICMP_ECHO + 1,
+	[ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1,
+	[ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1,
+	[ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1,
+	[ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1,
+	[ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1,
+	[ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1
+};
+
+static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple,
+			      const struct nf_conntrack_tuple *orig)
+{
+	if (orig->dst.u.icmp.type >= sizeof(invmap) ||
+	    !invmap[orig->dst.u.icmp.type])
+		return false;
+
+	tuple->src.u.icmp.id = orig->src.u.icmp.id;
+	tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1;
+	tuple->dst.u.icmp.code = orig->dst.u.icmp.code;
+	return true;
+}
+
+static unsigned int *icmp_get_timeouts(struct net *net)
+{
+	return &icmp_pernet(net)->timeout;
+}
+
+/* Returns verdict for packet, or -1 for invalid. */
+static int icmp_packet(struct nf_conn *ct,
+		       const struct sk_buff *skb,
+		       unsigned int dataoff,
+		       enum ip_conntrack_info ctinfo)
+{
+	/* Do not immediately delete the connection after the first
+	   successful reply to avoid excessive conntrackd traffic
+	   and also to handle correctly ICMP echo reply duplicates. */
+	unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = icmp_get_timeouts(nf_ct_net(ct));
+
+	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
+
+	return NF_ACCEPT;
+}
+
+/* Called when a new connection for this protocol found. */
+static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
+		     unsigned int dataoff)
+{
+	static const u_int8_t valid_new[] = {
+		[ICMP_ECHO] = 1,
+		[ICMP_TIMESTAMP] = 1,
+		[ICMP_INFO_REQUEST] = 1,
+		[ICMP_ADDRESS] = 1
+	};
+
+	if (ct->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new) ||
+	    !valid_new[ct->tuplehash[0].tuple.dst.u.icmp.type]) {
+		/* Can't create a new ICMP `conn' with this. */
+		pr_debug("icmp: can't create new conn with type %u\n",
+			 ct->tuplehash[0].tuple.dst.u.icmp.type);
+		nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple);
+		return false;
+	}
+	return true;
+}
+
+/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
+static int
+icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
+		 unsigned int hooknum)
+{
+	struct nf_conntrack_tuple innertuple, origtuple;
+	const struct nf_conntrack_l4proto *innerproto;
+	const struct nf_conntrack_tuple_hash *h;
+	const struct nf_conntrack_zone *zone;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conntrack_zone tmp;
+
+	WARN_ON(skb_nfct(skb));
+	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
+
+	/* Are they talking about one of our connections? */
+	if (!nf_ct_get_tuplepr(skb,
+			       skb_network_offset(skb) + ip_hdrlen(skb)
+						       + sizeof(struct icmphdr),
+			       PF_INET, net, &origtuple)) {
+		pr_debug("icmp_error_message: failed to get tuple\n");
+		return -NF_ACCEPT;
+	}
+
+	/* rcu_read_lock()ed by nf_hook_thresh */
+	innerproto = __nf_ct_l4proto_find(PF_INET, origtuple.dst.protonum);
+
+	/* Ordinarily, we'd expect the inverted tupleproto, but it's
+	   been preserved inside the ICMP. */
+	if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) {
+		pr_debug("icmp_error_message: no match\n");
+		return -NF_ACCEPT;
+	}
+
+	ctinfo = IP_CT_RELATED;
+
+	h = nf_conntrack_find_get(net, zone, &innertuple);
+	if (!h) {
+		pr_debug("icmp_error_message: no match\n");
+		return -NF_ACCEPT;
+	}
+
+	if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+		ctinfo += IP_CT_IS_REPLY;
+
+	/* Update skb to refer to this connection */
+	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
+	return NF_ACCEPT;
+}
+
+static void icmp_error_log(const struct sk_buff *skb, struct net *net,
+			   u8 pf, const char *msg)
+{
+	nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMP, "%s", msg);
+}
+
+/* Small and modified version of icmp_rcv */
+static int
+icmp_error(struct net *net, struct nf_conn *tmpl,
+	   struct sk_buff *skb, unsigned int dataoff,
+	   u8 pf, unsigned int hooknum)
+{
+	const struct icmphdr *icmph;
+	struct icmphdr _ih;
+
+	/* Not enough header? */
+	icmph = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_ih), &_ih);
+	if (icmph == NULL) {
+		icmp_error_log(skb, net, pf, "short packet");
+		return -NF_ACCEPT;
+	}
+
+	/* See ip_conntrack_proto_tcp.c */
+	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
+	    nf_ip_checksum(skb, hooknum, dataoff, 0)) {
+		icmp_error_log(skb, net, pf, "bad hw icmp checksum");
+		return -NF_ACCEPT;
+	}
+
+	/*
+	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
+	 *
+	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
+	 *		  discarded.
+	 */
+	if (icmph->type > NR_ICMP_TYPES) {
+		icmp_error_log(skb, net, pf, "invalid icmp type");
+		return -NF_ACCEPT;
+	}
+
+	/* Need to track icmp error message? */
+	if (icmph->type != ICMP_DEST_UNREACH &&
+	    icmph->type != ICMP_SOURCE_QUENCH &&
+	    icmph->type != ICMP_TIME_EXCEEDED &&
+	    icmph->type != ICMP_PARAMETERPROB &&
+	    icmph->type != ICMP_REDIRECT)
+		return NF_ACCEPT;
+
+	return icmp_error_message(net, tmpl, skb, hooknum);
+}
+
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+
+static int icmp_tuple_to_nlattr(struct sk_buff *skb,
+				const struct nf_conntrack_tuple *t)
+{
+	if (nla_put_be16(skb, CTA_PROTO_ICMP_ID, t->src.u.icmp.id) ||
+	    nla_put_u8(skb, CTA_PROTO_ICMP_TYPE, t->dst.u.icmp.type) ||
+	    nla_put_u8(skb, CTA_PROTO_ICMP_CODE, t->dst.u.icmp.code))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static const struct nla_policy icmp_nla_policy[CTA_PROTO_MAX+1] = {
+	[CTA_PROTO_ICMP_TYPE]	= { .type = NLA_U8 },
+	[CTA_PROTO_ICMP_CODE]	= { .type = NLA_U8 },
+	[CTA_PROTO_ICMP_ID]	= { .type = NLA_U16 },
+};
+
+static int icmp_nlattr_to_tuple(struct nlattr *tb[],
+				struct nf_conntrack_tuple *tuple)
+{
+	if (!tb[CTA_PROTO_ICMP_TYPE] ||
+	    !tb[CTA_PROTO_ICMP_CODE] ||
+	    !tb[CTA_PROTO_ICMP_ID])
+		return -EINVAL;
+
+	tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMP_TYPE]);
+	tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMP_CODE]);
+	tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMP_ID]);
+
+	if (tuple->dst.u.icmp.type >= sizeof(invmap) ||
+	    !invmap[tuple->dst.u.icmp.type])
+		return -EINVAL;
+
+	return 0;
+}
+
+static unsigned int icmp_nlattr_tuple_size(void)
+{
+	static unsigned int size __read_mostly;
+
+	if (!size)
+		size = nla_policy_len(icmp_nla_policy, CTA_PROTO_MAX + 1);
+
+	return size;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_cttimeout.h>
+
+static int icmp_timeout_nlattr_to_obj(struct nlattr *tb[],
+				      struct net *net, void *data)
+{
+	unsigned int *timeout = data;
+	struct nf_icmp_net *in = icmp_pernet(net);
+
+	if (tb[CTA_TIMEOUT_ICMP_TIMEOUT]) {
+		if (!timeout)
+			timeout = &in->timeout;
+		*timeout =
+			ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMP_TIMEOUT])) * HZ;
+	} else if (timeout) {
+		/* Set default ICMP timeout. */
+		*timeout = in->timeout;
+	}
+	return 0;
+}
+
+static int
+icmp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
+{
+	const unsigned int *timeout = data;
+
+	if (nla_put_be32(skb, CTA_TIMEOUT_ICMP_TIMEOUT, htonl(*timeout / HZ)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -ENOSPC;
+}
+
+static const struct nla_policy
+icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = {
+	[CTA_TIMEOUT_ICMP_TIMEOUT]	= { .type = NLA_U32 },
+};
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table icmp_sysctl_table[] = {
+	{
+		.procname	= "nf_conntrack_icmp_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ }
+};
+#endif /* CONFIG_SYSCTL */
+
+static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn,
+				     struct nf_icmp_net *in)
+{
+#ifdef CONFIG_SYSCTL
+	pn->ctl_table = kmemdup(icmp_sysctl_table,
+				sizeof(icmp_sysctl_table),
+				GFP_KERNEL);
+	if (!pn->ctl_table)
+		return -ENOMEM;
+
+	pn->ctl_table[0].data = &in->timeout;
+#endif
+	return 0;
+}
+
+static int icmp_init_net(struct net *net, u_int16_t proto)
+{
+	struct nf_icmp_net *in = icmp_pernet(net);
+	struct nf_proto_net *pn = &in->pn;
+
+	in->timeout = nf_ct_icmp_timeout;
+
+	return icmp_kmemdup_sysctl_table(pn, in);
+}
+
+static struct nf_proto_net *icmp_get_net_proto(struct net *net)
+{
+	return &net->ct.nf_ct_proto.icmp.pn;
+}
+
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp =
+{
+	.l3proto		= PF_INET,
+	.l4proto		= IPPROTO_ICMP,
+	.pkt_to_tuple		= icmp_pkt_to_tuple,
+	.invert_tuple		= icmp_invert_tuple,
+	.packet			= icmp_packet,
+	.new			= icmp_new,
+	.error			= icmp_error,
+	.destroy		= NULL,
+	.me			= NULL,
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+	.tuple_to_nlattr	= icmp_tuple_to_nlattr,
+	.nlattr_tuple_size	= icmp_nlattr_tuple_size,
+	.nlattr_to_tuple	= icmp_nlattr_to_tuple,
+	.nla_policy		= icmp_nla_policy,
+#endif
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+	.ctnl_timeout		= {
+		.nlattr_to_obj	= icmp_timeout_nlattr_to_obj,
+		.obj_to_nlattr	= icmp_timeout_obj_to_nlattr,
+		.nlattr_max	= CTA_TIMEOUT_ICMP_MAX,
+		.obj_size	= sizeof(unsigned int),
+		.nla_policy	= icmp_timeout_nla_policy,
+	},
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+	.init_net		= icmp_init_net,
+	.get_net_proto		= icmp_get_net_proto,
+};
diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c
new file mode 100644
index 000000000000..bed07b998a10
--- /dev/null
+++ b/net/netfilter/nf_conntrack_proto_icmpv6.c
@@ -0,0 +1,387 @@
+/*
+ * Copyright (C)2003,2004 USAGI/WIDE Project
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Author:
+ *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ */
+
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <net/ip6_checksum.h>
+#include <linux/seq_file.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
+#include <net/netfilter/nf_log.h>
+
+static const unsigned int nf_ct_icmpv6_timeout = 30*HZ;
+
+static inline struct nf_icmp_net *icmpv6_pernet(struct net *net)
+{
+	return &net->ct.nf_ct_proto.icmpv6;
+}
+
+static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb,
+				unsigned int dataoff,
+				struct net *net,
+				struct nf_conntrack_tuple *tuple)
+{
+	const struct icmp6hdr *hp;
+	struct icmp6hdr _hdr;
+
+	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
+	if (hp == NULL)
+		return false;
+	tuple->dst.u.icmp.type = hp->icmp6_type;
+	tuple->src.u.icmp.id = hp->icmp6_identifier;
+	tuple->dst.u.icmp.code = hp->icmp6_code;
+
+	return true;
+}
+
+/* Add 1; spaces filled with 0. */
+static const u_int8_t invmap[] = {
+	[ICMPV6_ECHO_REQUEST - 128]	= ICMPV6_ECHO_REPLY + 1,
+	[ICMPV6_ECHO_REPLY - 128]	= ICMPV6_ECHO_REQUEST + 1,
+	[ICMPV6_NI_QUERY - 128]		= ICMPV6_NI_REPLY + 1,
+	[ICMPV6_NI_REPLY - 128]		= ICMPV6_NI_QUERY + 1
+};
+
+static const u_int8_t noct_valid_new[] = {
+	[ICMPV6_MGM_QUERY - 130] = 1,
+	[ICMPV6_MGM_REPORT - 130] = 1,
+	[ICMPV6_MGM_REDUCTION - 130] = 1,
+	[NDISC_ROUTER_SOLICITATION - 130] = 1,
+	[NDISC_ROUTER_ADVERTISEMENT - 130] = 1,
+	[NDISC_NEIGHBOUR_SOLICITATION - 130] = 1,
+	[NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1,
+	[ICMPV6_MLD2_REPORT - 130] = 1
+};
+
+static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
+				const struct nf_conntrack_tuple *orig)
+{
+	int type = orig->dst.u.icmp.type - 128;
+	if (type < 0 || type >= sizeof(invmap) || !invmap[type])
+		return false;
+
+	tuple->src.u.icmp.id   = orig->src.u.icmp.id;
+	tuple->dst.u.icmp.type = invmap[type] - 1;
+	tuple->dst.u.icmp.code = orig->dst.u.icmp.code;
+	return true;
+}
+
+static unsigned int *icmpv6_get_timeouts(struct net *net)
+{
+	return &icmpv6_pernet(net)->timeout;
+}
+
+/* Returns verdict for packet, or -1 for invalid. */
+static int icmpv6_packet(struct nf_conn *ct,
+		       const struct sk_buff *skb,
+		       unsigned int dataoff,
+		       enum ip_conntrack_info ctinfo)
+{
+	unsigned int *timeout = nf_ct_timeout_lookup(ct);
+
+	if (!timeout)
+		timeout = icmpv6_get_timeouts(nf_ct_net(ct));
+
+	/* Do not immediately delete the connection after the first
+	   successful reply to avoid excessive conntrackd traffic
+	   and also to handle correctly ICMP echo reply duplicates. */
+	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
+
+	return NF_ACCEPT;
+}
+
+/* Called when a new connection for this protocol found. */
+static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
+		       unsigned int dataoff)
+{
+	static const u_int8_t valid_new[] = {
+		[ICMPV6_ECHO_REQUEST - 128] = 1,
+		[ICMPV6_NI_QUERY - 128] = 1
+	};
+	int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128;
+
+	if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) {
+		/* Can't create a new ICMPv6 `conn' with this. */
+		pr_debug("icmpv6: can't create new conn with type %u\n",
+			 type + 128);
+		nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple);
+		return false;
+	}
+	return true;
+}
+
+static int
+icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
+		     struct sk_buff *skb,
+		     unsigned int icmp6off)
+{
+	struct nf_conntrack_tuple intuple, origtuple;
+	const struct nf_conntrack_tuple_hash *h;
+	const struct nf_conntrack_l4proto *inproto;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conntrack_zone tmp;
+
+	WARN_ON(skb_nfct(skb));
+
+	/* Are they talking about one of our connections? */
+	if (!nf_ct_get_tuplepr(skb,
+			       skb_network_offset(skb)
+				+ sizeof(struct ipv6hdr)
+				+ sizeof(struct icmp6hdr),
+			       PF_INET6, net, &origtuple)) {
+		pr_debug("icmpv6_error: Can't get tuple\n");
+		return -NF_ACCEPT;
+	}
+
+	/* rcu_read_lock()ed by nf_hook_thresh */
+	inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum);
+
+	/* Ordinarily, we'd expect the inverted tupleproto, but it's
+	   been preserved inside the ICMP. */
+	if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) {
+		pr_debug("icmpv6_error: Can't invert tuple\n");
+		return -NF_ACCEPT;
+	}
+
+	ctinfo = IP_CT_RELATED;
+
+	h = nf_conntrack_find_get(net, nf_ct_zone_tmpl(tmpl, skb, &tmp),
+				  &intuple);
+	if (!h) {
+		pr_debug("icmpv6_error: no match\n");
+		return -NF_ACCEPT;
+	} else {
+		if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+			ctinfo += IP_CT_IS_REPLY;
+	}
+
+	/* Update skb to refer to this connection */
+	nf_ct_set(skb, nf_ct_tuplehash_to_ctrack(h), ctinfo);
+	return NF_ACCEPT;
+}
+
+static void icmpv6_error_log(const struct sk_buff *skb, struct net *net,
+			     u8 pf, const char *msg)
+{
+	nf_l4proto_log_invalid(skb, net, pf, IPPROTO_ICMPV6, "%s", msg);
+}
+
+static int
+icmpv6_error(struct net *net, struct nf_conn *tmpl,
+	     struct sk_buff *skb, unsigned int dataoff,
+	     u8 pf, unsigned int hooknum)
+{
+	const struct icmp6hdr *icmp6h;
+	struct icmp6hdr _ih;
+	int type;
+
+	icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
+	if (icmp6h == NULL) {
+		icmpv6_error_log(skb, net, pf, "short packet");
+		return -NF_ACCEPT;
+	}
+
+	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
+	    nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
+		icmpv6_error_log(skb, net, pf, "ICMPv6 checksum failed");
+		return -NF_ACCEPT;
+	}
+
+	type = icmp6h->icmp6_type - 130;
+	if (type >= 0 && type < sizeof(noct_valid_new) &&
+	    noct_valid_new[type]) {
+		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
+		return NF_ACCEPT;
+	}
+
+	/* is not error message ? */
+	if (icmp6h->icmp6_type >= 128)
+		return NF_ACCEPT;
+
+	return icmpv6_error_message(net, tmpl, skb, dataoff);
+}
+
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+static int icmpv6_tuple_to_nlattr(struct sk_buff *skb,
+				  const struct nf_conntrack_tuple *t)
+{
+	if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) ||
+	    nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) ||
+	    nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = {
+	[CTA_PROTO_ICMPV6_TYPE]	= { .type = NLA_U8 },
+	[CTA_PROTO_ICMPV6_CODE]	= { .type = NLA_U8 },
+	[CTA_PROTO_ICMPV6_ID]	= { .type = NLA_U16 },
+};
+
+static int icmpv6_nlattr_to_tuple(struct nlattr *tb[],
+				struct nf_conntrack_tuple *tuple)
+{
+	if (!tb[CTA_PROTO_ICMPV6_TYPE] ||
+	    !tb[CTA_PROTO_ICMPV6_CODE] ||
+	    !tb[CTA_PROTO_ICMPV6_ID])
+		return -EINVAL;
+
+	tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]);
+	tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]);
+	tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]);
+
+	if (tuple->dst.u.icmp.type < 128 ||
+	    tuple->dst.u.icmp.type - 128 >= sizeof(invmap) ||
+	    !invmap[tuple->dst.u.icmp.type - 128])
+		return -EINVAL;
+
+	return 0;
+}
+
+static unsigned int icmpv6_nlattr_tuple_size(void)
+{
+	static unsigned int size __read_mostly;
+
+	if (!size)
+		size = nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1);
+
+	return size;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_cttimeout.h>
+
+static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[],
+					struct net *net, void *data)
+{
+	unsigned int *timeout = data;
+	struct nf_icmp_net *in = icmpv6_pernet(net);
+
+	if (!timeout)
+		timeout = icmpv6_get_timeouts(net);
+	if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) {
+		*timeout =
+		    ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ;
+	} else {
+		/* Set default ICMPv6 timeout. */
+		*timeout = in->timeout;
+	}
+	return 0;
+}
+
+static int
+icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
+{
+	const unsigned int *timeout = data;
+
+	if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -ENOSPC;
+}
+
+static const struct nla_policy
+icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = {
+	[CTA_TIMEOUT_ICMPV6_TIMEOUT]	= { .type = NLA_U32 },
+};
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table icmpv6_sysctl_table[] = {
+	{
+		.procname	= "nf_conntrack_icmpv6_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ }
+};
+#endif /* CONFIG_SYSCTL */
+
+static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn,
+				       struct nf_icmp_net *in)
+{
+#ifdef CONFIG_SYSCTL
+	pn->ctl_table = kmemdup(icmpv6_sysctl_table,
+				sizeof(icmpv6_sysctl_table),
+				GFP_KERNEL);
+	if (!pn->ctl_table)
+		return -ENOMEM;
+
+	pn->ctl_table[0].data = &in->timeout;
+#endif
+	return 0;
+}
+
+static int icmpv6_init_net(struct net *net, u_int16_t proto)
+{
+	struct nf_icmp_net *in = icmpv6_pernet(net);
+	struct nf_proto_net *pn = &in->pn;
+
+	in->timeout = nf_ct_icmpv6_timeout;
+
+	return icmpv6_kmemdup_sysctl_table(pn, in);
+}
+
+static struct nf_proto_net *icmpv6_get_net_proto(struct net *net)
+{
+	return &net->ct.nf_ct_proto.icmpv6.pn;
+}
+
+const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 =
+{
+	.l3proto		= PF_INET6,
+	.l4proto		= IPPROTO_ICMPV6,
+	.pkt_to_tuple		= icmpv6_pkt_to_tuple,
+	.invert_tuple		= icmpv6_invert_tuple,
+	.packet			= icmpv6_packet,
+	.new			= icmpv6_new,
+	.error			= icmpv6_error,
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+	.tuple_to_nlattr	= icmpv6_tuple_to_nlattr,
+	.nlattr_tuple_size	= icmpv6_nlattr_tuple_size,
+	.nlattr_to_tuple	= icmpv6_nlattr_to_tuple,
+	.nla_policy		= icmpv6_nla_policy,
+#endif
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+	.ctnl_timeout		= {
+		.nlattr_to_obj	= icmpv6_timeout_nlattr_to_obj,
+		.obj_to_nlattr	= icmpv6_timeout_obj_to_nlattr,
+		.nlattr_max	= CTA_TIMEOUT_ICMP_MAX,
+		.obj_size	= sizeof(unsigned int),
+		.nla_policy	= icmpv6_timeout_nla_policy,
+	},
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+	.init_net		= icmpv6_init_net,
+	.get_net_proto		= icmpv6_get_net_proto,
+};
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 47b80fd0d2c3..13279f683da9 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -1,12 +1,4 @@
-/* (C) 1999-2001 Paul `Rusty' Russell
- * (C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
- * (C) 2005-2012 Patrick McHardy <kaber@trash.net>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
+// SPDX-License-Identifier: GPL-2.0
 #include <linux/types.h>
 #include <linux/netfilter.h>
 #include <linux/slab.h>
@@ -32,7 +24,7 @@
 #include <net/netfilter/nf_conntrack_timestamp.h>
 #include <linux/rculist_nulls.h>
 
-MODULE_LICENSE("GPL");
+unsigned int nf_conntrack_net_id __read_mostly;
 
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 void
@@ -674,6 +666,8 @@ static void nf_conntrack_pernet_exit(struct list_head *net_exit_list)
 static struct pernet_operations nf_conntrack_net_ops = {
 	.init		= nf_conntrack_pernet_init,
 	.exit_batch	= nf_conntrack_pernet_exit,
+	.id		= &nf_conntrack_net_id,
+	.size = sizeof(struct nf_conntrack_net),
 };
 
 static int __init nf_conntrack_standalone_init(void)
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 86df2a1666fd..6366f0c0b8c1 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -28,7 +28,6 @@
 #include <net/netfilter/nf_nat_helper.h>
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_seqadj.h>
-#include <net/netfilter/nf_conntrack_l3proto.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <linux/netfilter/nf_nat.h>
 
@@ -743,12 +742,6 @@ EXPORT_SYMBOL_GPL(nf_nat_l4proto_unregister);
 
 int nf_nat_l3proto_register(const struct nf_nat_l3proto *l3proto)
 {
-	int err;
-
-	err = nf_ct_l3proto_try_module_get(l3proto->l3proto);
-	if (err < 0)
-		return err;
-
 	mutex_lock(&nf_nat_proto_mutex);
 	RCU_INIT_POINTER(nf_nat_l4protos[l3proto->l3proto][IPPROTO_TCP],
 			 &nf_nat_l4proto_tcp);
@@ -781,7 +774,6 @@ void nf_nat_l3proto_unregister(const struct nf_nat_l3proto *l3proto)
 	synchronize_rcu();
 
 	nf_nat_l3proto_clean(l3proto->l3proto);
-	nf_ct_l3proto_module_put(l3proto->l3proto);
 }
 EXPORT_SYMBOL_GPL(nf_nat_l3proto_unregister);
 
-- 
cgit v1.2.3


From 5d400a4933e867dbc3706023c8ed55d364c233ed Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Tue, 10 Jul 2018 16:01:28 +0200
Subject: netfilter: Kconfig: Change select IPv6 dependencies
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

... from IPV6 to NF_TABLES_IPV6 and IP6_NF_IPTABLES.

In some cases module selects depend on IPV6, but this means that they
select another module even if eg. NF_TABLES_IPV6 is not set in which
case the selected module is useless due to the lack of IPv6 nf_tables
functionality.

The same applies for IP6_NF_IPTABLES and iptables.

Joint work with: Arnd Bermann <arnd@arndb.de>

Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/Kconfig      | 6 +++---
 net/netfilter/nft_socket.c | 4 ++--
 net/netfilter/xt_TEE.c     | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 9eab519b403a..e0ab50c58dc4 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -628,7 +628,7 @@ config NFT_SOCKET
 	tristate "Netfilter nf_tables socket match support"
 	depends on IPV6 || IPV6=n
 	select NF_SOCKET_IPV4
-	select NF_SOCKET_IPV6 if IPV6
+	select NF_SOCKET_IPV6 if NF_TABLES_IPV6
 	help
 	  This option allows matching for the presence or absence of a
 	  corresponding socket and its attributes.
@@ -894,7 +894,7 @@ config NETFILTER_XT_TARGET_LOG
 	tristate "LOG target support"
 	select NF_LOG_COMMON
 	select NF_LOG_IPV4
-	select NF_LOG_IPV6 if IPV6
+	select NF_LOG_IPV6 if IP6_NF_IPTABLES
 	default m if NETFILTER_ADVANCED=n
 	help
 	  This option adds a `LOG' target, which allows you to create rules in
@@ -986,7 +986,7 @@ config NETFILTER_XT_TARGET_TEE
 	depends on IPV6 || IPV6=n
 	depends on !NF_CONNTRACK || NF_CONNTRACK
 	select NF_DUP_IPV4
-	select NF_DUP_IPV6 if IPV6
+	select NF_DUP_IPV6 if IP6_NF_IPTABLES
 	---help---
 	This option adds a "TEE" target with which a packet can be cloned and
 	this clone be rerouted to another nexthop.
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 998c2b546f6d..e43c1939d25f 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -31,7 +31,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		case NFPROTO_IPV4:
 			sk = nf_sk_lookup_slow_v4(nft_net(pkt), skb, nft_in(pkt));
 			break;
-#if IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
 		case NFPROTO_IPV6:
 			sk = nf_sk_lookup_slow_v6(nft_net(pkt), skb, nft_in(pkt));
 			break;
@@ -77,7 +77,7 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 
 	switch(ctx->family) {
 	case NFPROTO_IPV4:
-#if IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
 	case NFPROTO_IPV6:
 #endif
 	case NFPROTO_INET:
diff --git a/net/netfilter/xt_TEE.c b/net/netfilter/xt_TEE.c
index 475957cfcf50..0d0d68c989df 100644
--- a/net/netfilter/xt_TEE.c
+++ b/net/netfilter/xt_TEE.c
@@ -38,7 +38,7 @@ tee_tg4(struct sk_buff *skb, const struct xt_action_param *par)
 	return XT_CONTINUE;
 }
 
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 static unsigned int
 tee_tg6(struct sk_buff *skb, const struct xt_action_param *par)
 {
@@ -141,7 +141,7 @@ static struct xt_target tee_tg_reg[] __read_mostly = {
 		.destroy    = tee_tg_destroy,
 		.me         = THIS_MODULE,
 	},
-#if IS_ENABLED(CONFIG_IPV6)
+#if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 	{
 		.name       = "TEE",
 		.revision   = 1,
-- 
cgit v1.2.3


From e2d2f240497c63a157f897c87567b93ed43a2213 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 17 Jul 2018 10:00:43 -0500
Subject: ALSA: emu10k1_patch: Use swap macro in snd_emu10k1_sample_new

Make use of the swap macro and remove unnecessary variable *tmp*. This
makes the code easier to read and maintain.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/emu10k1/emu10k1_patch.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/sound/pci/emu10k1/emu10k1_patch.c b/sound/pci/emu10k1/emu10k1_patch.c
index 0e069aeab86d..c32eb7053715 100644
--- a/sound/pci/emu10k1/emu10k1_patch.c
+++ b/sound/pci/emu10k1/emu10k1_patch.c
@@ -70,11 +70,8 @@ snd_emu10k1_sample_new(struct snd_emux *rec, struct snd_sf_sample *sp,
 		loopend = sampleend;
 
 	/* be sure loop points start < end */
-	if (sp->v.loopstart >= sp->v.loopend) {
-		int tmp = sp->v.loopstart;
-		sp->v.loopstart = sp->v.loopend;
-		sp->v.loopend = tmp;
-	}
+	if (sp->v.loopstart >= sp->v.loopend)
+		swap(sp->v.loopstart, sp->v.loopend);
 
 	/* compute true data size to be loaded */
 	truesize = sp->v.size + BLANK_HEAD_SIZE;
-- 
cgit v1.2.3


From 7373c2a99abf2b11b5e8a226071331c0176253ff Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 17 Jul 2018 10:06:10 -0500
Subject: ALSA: emu8000: Use swap macro in snd_emu8000_sample_new

Make use of the swap macro and remove unnecessary variable *tmp*. This
makes the code easier to read and maintain.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/emu8000_patch.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/sound/isa/sb/emu8000_patch.c b/sound/isa/sb/emu8000_patch.c
index c2e41d2762f7..d45a6b9d6437 100644
--- a/sound/isa/sb/emu8000_patch.c
+++ b/sound/isa/sb/emu8000_patch.c
@@ -165,11 +165,8 @@ snd_emu8000_sample_new(struct snd_emux *rec, struct snd_sf_sample *sp,
 		return 0;
 
 	/* be sure loop points start < end */
-	if (sp->v.loopstart > sp->v.loopend) {
-		int tmp = sp->v.loopstart;
-		sp->v.loopstart = sp->v.loopend;
-		sp->v.loopend = tmp;
-	}
+	if (sp->v.loopstart > sp->v.loopend)
+		swap(sp->v.loopstart, sp->v.loopend);
 
 	/* compute true data size to be loaded */
 	truesize = sp->v.size;
-- 
cgit v1.2.3


From d8b3f454dab48bc40528aa5f19f7f27f2a6dc825 Mon Sep 17 00:00:00 2001
From: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Date: Tue, 17 Jul 2018 14:25:22 +0200
Subject: drm/sun4i: sun8i: Avoid clearing blending order at each atomic commit

Blending order is set based on the z position of each DRM plane. The
blending order register is currently cleared at each atomic DRM commit,
with the intent that each committed plane will set the appropriate
bits (based on its z-pos) when enabling the plane.

However, it sometimes happens that a particular plane is left unchanged
by an atomic commit and thus will not be configured again. In that
scenario, blending order is cleared and only the bits relevant for the
planes affected by the commit are set. This leaves the planes that did
not change without their blending order set in the register, leading
to that plane not being displayed.

Instead of clearing the blending order register at every atomic commit,
this change moves the register's initial clear at bind time and only
clears the bits for a specific plane when disabling it or changing its
zpos.

This way, planes that are left untouched by a DRM atomic commit are
no longer disabled.

Signed-off-by: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717122522.11327-1-paul.kocialkowski@bootlin.com
---
 drivers/gpu/drm/sun4i/sun8i_mixer.c    | 15 +++------------
 drivers/gpu/drm/sun4i/sun8i_ui_layer.c | 24 ++++++++++++++++++++----
 drivers/gpu/drm/sun4i/sun8i_vi_layer.c | 24 ++++++++++++++++++++----
 3 files changed, 43 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun8i_mixer.c b/drivers/gpu/drm/sun4i/sun8i_mixer.c
index f76a5576c0e6..fc3713608f78 100644
--- a/drivers/gpu/drm/sun4i/sun8i_mixer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_mixer.c
@@ -261,17 +261,6 @@ const struct de2_fmt_info *sun8i_mixer_format_info(u32 format)
 	return NULL;
 }
 
-static void sun8i_mixer_atomic_begin(struct sunxi_engine *engine,
-				     struct drm_crtc_state *old_state)
-{
-	/*
-	 * Disable all pipes at the beginning. They will be enabled
-	 * again if needed in plane update callback.
-	 */
-	regmap_update_bits(engine->regs, SUN8I_MIXER_BLEND_PIPE_CTL,
-			   SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK, 0);
-}
-
 static void sun8i_mixer_commit(struct sunxi_engine *engine)
 {
 	DRM_DEBUG_DRIVER("Committing changes\n");
@@ -323,7 +312,6 @@ static struct drm_plane **sun8i_layers_init(struct drm_device *drm,
 }
 
 static const struct sunxi_engine_ops sun8i_engine_ops = {
-	.atomic_begin	= sun8i_mixer_atomic_begin,
 	.commit		= sun8i_mixer_commit,
 	.layers_init	= sun8i_layers_init,
 };
@@ -494,6 +482,9 @@ static int sun8i_mixer_bind(struct device *dev, struct device *master,
 		regmap_write(mixer->engine.regs, SUN8I_MIXER_BLEND_MODE(i),
 			     SUN8I_MIXER_BLEND_MODE_DEF);
 
+	regmap_update_bits(mixer->engine.regs, SUN8I_MIXER_BLEND_PIPE_CTL,
+			   SUN8I_MIXER_BLEND_PIPE_CTL_EN_MSK, 0);
+
 	return 0;
 
 err_disable_bus_clk:
diff --git a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
index 518e1921f47e..28c15c6ef1ef 100644
--- a/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_ui_layer.c
@@ -27,7 +27,8 @@
 #include "sun8i_ui_scaler.h"
 
 static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable, unsigned int zpos)
+				  int overlay, bool enable, unsigned int zpos,
+				  unsigned int old_zpos)
 {
 	u32 val;
 
@@ -43,6 +44,18 @@ static void sun8i_ui_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_UI_LAYER_ATTR_EN, val);
 
+	if (!enable || zpos != old_zpos) {
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL,
+				   SUN8I_MIXER_BLEND_PIPE_CTL_EN(old_zpos),
+				   0);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(old_zpos),
+				   0);
+	}
+
 	if (enable) {
 		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
 
@@ -242,9 +255,11 @@ static void sun8i_ui_layer_atomic_disable(struct drm_plane *plane,
 					  struct drm_plane_state *old_state)
 {
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false, 0);
+	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay, false, 0,
+			      old_zpos);
 }
 
 static void sun8i_ui_layer_atomic_update(struct drm_plane *plane,
@@ -252,11 +267,12 @@ static void sun8i_ui_layer_atomic_update(struct drm_plane *plane,
 {
 	struct sun8i_ui_layer *layer = plane_to_sun8i_ui_layer(plane);
 	unsigned int zpos = plane->state->normalized_zpos;
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_ui_layer_enable(mixer, layer->channel,
-				      layer->overlay, false, 0);
+				      layer->overlay, false, 0, old_zpos);
 		return;
 	}
 
@@ -267,7 +283,7 @@ static void sun8i_ui_layer_atomic_update(struct drm_plane *plane,
 	sun8i_ui_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
 	sun8i_ui_layer_enable(mixer, layer->channel, layer->overlay,
-			      true, zpos);
+			      true, zpos, old_zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_ui_layer_helper_funcs = {
diff --git a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
index 17e0d00cfd8a..f4fe97813f94 100644
--- a/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
+++ b/drivers/gpu/drm/sun4i/sun8i_vi_layer.c
@@ -21,7 +21,8 @@
 #include "sun8i_vi_scaler.h"
 
 static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
-				  int overlay, bool enable, unsigned int zpos)
+				  int overlay, bool enable, unsigned int zpos,
+				  unsigned int old_zpos)
 {
 	u32 val;
 
@@ -37,6 +38,18 @@ static void sun8i_vi_layer_enable(struct sun8i_mixer *mixer, int channel,
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR(channel, overlay),
 			   SUN8I_MIXER_CHAN_VI_LAYER_ATTR_EN, val);
 
+	if (!enable || zpos != old_zpos) {
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_PIPE_CTL,
+				   SUN8I_MIXER_BLEND_PIPE_CTL_EN(old_zpos),
+				   0);
+
+		regmap_update_bits(mixer->engine.regs,
+				   SUN8I_MIXER_BLEND_ROUTE,
+				   SUN8I_MIXER_BLEND_ROUTE_PIPE_MSK(old_zpos),
+				   0);
+	}
+
 	if (enable) {
 		val = SUN8I_MIXER_BLEND_PIPE_CTL_EN(zpos);
 
@@ -270,9 +283,11 @@ static void sun8i_vi_layer_atomic_disable(struct drm_plane *plane,
 					  struct drm_plane_state *old_state)
 {
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
-	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false, 0);
+	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay, false, 0,
+			      old_zpos);
 }
 
 static void sun8i_vi_layer_atomic_update(struct drm_plane *plane,
@@ -280,11 +295,12 @@ static void sun8i_vi_layer_atomic_update(struct drm_plane *plane,
 {
 	struct sun8i_vi_layer *layer = plane_to_sun8i_vi_layer(plane);
 	unsigned int zpos = plane->state->normalized_zpos;
+	unsigned int old_zpos = old_state->normalized_zpos;
 	struct sun8i_mixer *mixer = layer->mixer;
 
 	if (!plane->state->visible) {
 		sun8i_vi_layer_enable(mixer, layer->channel,
-				      layer->overlay, false, 0);
+				      layer->overlay, false, 0, old_zpos);
 		return;
 	}
 
@@ -295,7 +311,7 @@ static void sun8i_vi_layer_atomic_update(struct drm_plane *plane,
 	sun8i_vi_layer_update_buffer(mixer, layer->channel,
 				     layer->overlay, plane);
 	sun8i_vi_layer_enable(mixer, layer->channel, layer->overlay,
-			      true, zpos);
+			      true, zpos, old_zpos);
 }
 
 static struct drm_plane_helper_funcs sun8i_vi_layer_helper_funcs = {
-- 
cgit v1.2.3


From b56e5355091d799d58ce8b40fdf62dc9c2159981 Mon Sep 17 00:00:00 2001
From: Elena Reshetova <elena.reshetova@intel.com>
Date: Fri, 1 Sep 2017 12:40:20 +0300
Subject: Coccinelle: add atomic_as_refcounter script

atomic_as_refcounter.cocci script allows detecting
cases when refcount_t type and API should be used
instead of atomic_t.

Signed-off-by: Elena Reshetova <elena.reshetova@intel.com>
Acked-by: Julia Lawall <julia.lawall@lip6.fr>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/coccinelle/api/atomic_as_refcounter.cocci | 129 ++++++++++++++++++++++
 1 file changed, 129 insertions(+)
 create mode 100644 scripts/coccinelle/api/atomic_as_refcounter.cocci

diff --git a/scripts/coccinelle/api/atomic_as_refcounter.cocci b/scripts/coccinelle/api/atomic_as_refcounter.cocci
new file mode 100644
index 000000000000..988120e0fd67
--- /dev/null
+++ b/scripts/coccinelle/api/atomic_as_refcounter.cocci
@@ -0,0 +1,129 @@
+// Check if refcount_t type and API should be used
+// instead of atomic_t type when dealing with refcounters
+//
+// Copyright (c) 2016-2017, Elena Reshetova, Intel Corporation
+//
+// Confidence: Moderate
+// URL: http://coccinelle.lip6.fr/
+// Options: --include-headers --very-quiet
+
+virtual report
+
+@r1 exists@
+identifier a, x;
+position p1, p2;
+identifier fname =~ ".*free.*";
+identifier fname2 =~ ".*destroy.*";
+identifier fname3 =~ ".*del.*";
+identifier fname4 =~ ".*queue_work.*";
+identifier fname5 =~ ".*schedule_work.*";
+identifier fname6 =~ ".*call_rcu.*";
+
+@@
+
+(
+ atomic_dec_and_test@p1(&(a)->x)
+|
+ atomic_dec_and_lock@p1(&(a)->x, ...)
+|
+ atomic_long_dec_and_lock@p1(&(a)->x, ...)
+|
+ atomic_long_dec_and_test@p1(&(a)->x)
+|
+ atomic64_dec_and_test@p1(&(a)->x)
+|
+ local_dec_and_test@p1(&(a)->x)
+)
+...
+(
+ fname@p2(a, ...);
+|
+ fname2@p2(...);
+|
+ fname3@p2(...);
+|
+ fname4@p2(...);
+|
+ fname5@p2(...);
+|
+ fname6@p2(...);
+)
+
+
+@script:python depends on report@
+p1 << r1.p1;
+p2 << r1.p2;
+@@
+msg = "atomic_dec_and_test variation before object free at line %s."
+coccilib.report.print_report(p1[0], msg % (p2[0].line))
+
+@r4 exists@
+identifier a, x, y;
+position p1, p2;
+identifier fname =~ ".*free.*";
+
+@@
+
+(
+ atomic_dec_and_test@p1(&(a)->x)
+|
+ atomic_dec_and_lock@p1(&(a)->x, ...)
+|
+ atomic_long_dec_and_lock@p1(&(a)->x, ...)
+|
+ atomic_long_dec_and_test@p1(&(a)->x)
+|
+ atomic64_dec_and_test@p1(&(a)->x)
+|
+ local_dec_and_test@p1(&(a)->x)
+)
+...
+y=a
+...
+fname@p2(y, ...);
+
+
+@script:python depends on report@
+p1 << r4.p1;
+p2 << r4.p2;
+@@
+msg = "atomic_dec_and_test variation before object free at line %s."
+coccilib.report.print_report(p1[0], msg % (p2[0].line))
+
+@r2 exists@
+identifier a, x;
+position p1;
+@@
+
+(
+atomic_add_unless(&(a)->x,-1,1)@p1
+|
+atomic_long_add_unless(&(a)->x,-1,1)@p1
+|
+atomic64_add_unless(&(a)->x,-1,1)@p1
+)
+
+@script:python depends on report@
+p1 << r2.p1;
+@@
+msg = "atomic_add_unless"
+coccilib.report.print_report(p1[0], msg)
+
+@r3 exists@
+identifier x;
+position p1;
+@@
+
+(
+x = atomic_add_return@p1(-1, ...);
+|
+x = atomic_long_add_return@p1(-1, ...);
+|
+x = atomic64_add_return@p1(-1, ...);
+)
+
+@script:python depends on report@
+p1 << r3.p1;
+@@
+msg = "x = atomic_add_return(-1, ...)"
+coccilib.report.print_report(p1[0], msg)
-- 
cgit v1.2.3


From c417fbce98722ad7e384caa8ba6f2e7c5f8672d9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 26 Jun 2018 01:40:23 +0900
Subject: kbuild: move bin2c back to scripts/ from scripts/basic/

Commit 8370edea81e3 ("bin2c: move bin2c in scripts/basic") moved bin2c
to the scripts/basic/ directory, incorrectly stating "Kexec wants to
use bin2c and it wants to use it really early in the build process.
See arch/x86/purgatory/ code in later patches."

Commit bdab125c9301 ("Revert "kexec/purgatory: Add clean-up for
purgatory directory"") and commit d6605b6bbee8 ("x86/build: Remove
unnecessary preparation for purgatory") removed the redundant
purgatory build magic entirely.

That means that the move of bin2c was unnecessary in the first place.

fixdep is the only host program that deserves to sit in the
scripts/basic/ directory.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/powerpc/purgatory/Makefile |  3 +--
 arch/s390/purgatory/Makefile    |  3 +--
 arch/x86/purgatory/Makefile     |  3 +--
 kernel/Makefile                 |  2 +-
 scripts/.gitignore              |  1 +
 scripts/Makefile                |  1 +
 scripts/basic/.gitignore        |  1 -
 scripts/basic/Makefile          |  1 -
 scripts/basic/bin2c.c           | 36 ------------------------------------
 scripts/bin2c.c                 | 36 ++++++++++++++++++++++++++++++++++++
 security/tomoyo/Makefile        |  2 +-
 11 files changed, 43 insertions(+), 46 deletions(-)
 delete mode 100644 scripts/basic/bin2c.c
 create mode 100644 scripts/bin2c.c

diff --git a/arch/powerpc/purgatory/Makefile b/arch/powerpc/purgatory/Makefile
index 30e05decbb4c..4314ba5baf43 100644
--- a/arch/powerpc/purgatory/Makefile
+++ b/arch/powerpc/purgatory/Makefile
@@ -6,9 +6,8 @@ LDFLAGS_purgatory.ro := -e purgatory_start -r --no-undefined
 $(obj)/purgatory.ro: $(obj)/trampoline.o FORCE
 		$(call if_changed,ld)
 
-CMD_BIN2C = $(objtree)/scripts/basic/bin2c
 quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
+      cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@
 
 $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
 	$(call if_changed,bin2c)
diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index 1ace023cbdce..445c4603ce02 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -27,9 +27,8 @@ KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 		$(call if_changed,ld)
 
-CMD_BIN2C = $(objtree)/scripts/basic/bin2c
 quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
+      cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@
 
 $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
 	$(call if_changed,bin2c)
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index 81a8e33115ad..3cf302b26332 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -28,9 +28,8 @@ $(obj)/purgatory.ro: $(PURGATORY_OBJS) FORCE
 
 targets += kexec-purgatory.c
 
-CMD_BIN2C = $(objtree)/scripts/basic/bin2c
 quiet_cmd_bin2c = BIN2C   $@
-      cmd_bin2c = $(CMD_BIN2C) kexec_purgatory < $< > $@
+      cmd_bin2c = $(objtree)/scripts/bin2c kexec_purgatory < $< > $@
 
 $(obj)/kexec-purgatory.c: $(obj)/purgatory.ro FORCE
 	$(call if_changed,bin2c)
diff --git a/kernel/Makefile b/kernel/Makefile
index 04bc07c2b42a..7a63d567fdb5 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -123,7 +123,7 @@ targets += config_data.gz
 $(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE
 	$(call if_changed,gzip)
 
-      filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/basic/bin2c; echo "MAGIC_END;")
+      filechk_ikconfiggz = (echo "static const char kernel_config_data[] __used = MAGIC_START"; cat $< | scripts/bin2c; echo "MAGIC_END;")
 targets += config_data.h
 $(obj)/config_data.h: $(obj)/config_data.gz FORCE
 	$(call filechk,ikconfiggz)
diff --git a/scripts/.gitignore b/scripts/.gitignore
index 0442c06eefcb..12d302d70128 100644
--- a/scripts/.gitignore
+++ b/scripts/.gitignore
@@ -1,6 +1,7 @@
 #
 # Generated files
 #
+bin2c
 conmakehash
 kallsyms
 pnmtologo
diff --git a/scripts/Makefile b/scripts/Makefile
index 25ab143cbe14..59c21ec49b84 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -10,6 +10,7 @@
 
 HOST_EXTRACFLAGS += -I$(srctree)/tools/include
 
+hostprogs-$(CONFIG_BUILD_BIN2C)  += bin2c
 hostprogs-$(CONFIG_KALLSYMS)     += kallsyms
 hostprogs-$(CONFIG_LOGO)         += pnmtologo
 hostprogs-$(CONFIG_VT)           += conmakehash
diff --git a/scripts/basic/.gitignore b/scripts/basic/.gitignore
index 9528ec9e5adc..a776371a3502 100644
--- a/scripts/basic/.gitignore
+++ b/scripts/basic/.gitignore
@@ -1,2 +1 @@
 fixdep
-bin2c
diff --git a/scripts/basic/Makefile b/scripts/basic/Makefile
index 0372b33febe5..af49b446f17d 100644
--- a/scripts/basic/Makefile
+++ b/scripts/basic/Makefile
@@ -9,7 +9,6 @@
 # fixdep: 	 Used to generate dependency information during build process
 
 hostprogs-y	:= fixdep
-hostprogs-$(CONFIG_BUILD_BIN2C)     += bin2c
 always		:= $(hostprogs-y)
 
 # fixdep is needed to compile other host programs
diff --git a/scripts/basic/bin2c.c b/scripts/basic/bin2c.c
deleted file mode 100644
index c3d7eef3ad06..000000000000
--- a/scripts/basic/bin2c.c
+++ /dev/null
@@ -1,36 +0,0 @@
-/*
- * Unloved program to convert a binary on stdin to a C include on stdout
- *
- * Jan 1999 Matt Mackall <mpm@selenic.com>
- *
- * This software may be used and distributed according to the terms
- * of the GNU General Public License, incorporated herein by reference.
- */
-
-#include <stdio.h>
-
-int main(int argc, char *argv[])
-{
-	int ch, total = 0;
-
-	if (argc > 1)
-		printf("const char %s[] %s=\n",
-			argv[1], argc > 2 ? argv[2] : "");
-
-	do {
-		printf("\t\"");
-		while ((ch = getchar()) != EOF) {
-			total++;
-			printf("\\x%02x", ch);
-			if (total % 16 == 0)
-				break;
-		}
-		printf("\"\n");
-	} while (ch != EOF);
-
-	if (argc > 1)
-		printf("\t;\n\n#include <linux/types.h>\n\nconst size_t %s_size = %d;\n",
-		       argv[1], total);
-
-	return 0;
-}
diff --git a/scripts/bin2c.c b/scripts/bin2c.c
new file mode 100644
index 000000000000..c3d7eef3ad06
--- /dev/null
+++ b/scripts/bin2c.c
@@ -0,0 +1,36 @@
+/*
+ * Unloved program to convert a binary on stdin to a C include on stdout
+ *
+ * Jan 1999 Matt Mackall <mpm@selenic.com>
+ *
+ * This software may be used and distributed according to the terms
+ * of the GNU General Public License, incorporated herein by reference.
+ */
+
+#include <stdio.h>
+
+int main(int argc, char *argv[])
+{
+	int ch, total = 0;
+
+	if (argc > 1)
+		printf("const char %s[] %s=\n",
+			argv[1], argc > 2 ? argv[2] : "");
+
+	do {
+		printf("\t\"");
+		while ((ch = getchar()) != EOF) {
+			total++;
+			printf("\\x%02x", ch);
+			if (total % 16 == 0)
+				break;
+		}
+		printf("\"\n");
+	} while (ch != EOF);
+
+	if (argc > 1)
+		printf("\t;\n\n#include <linux/types.h>\n\nconst size_t %s_size = %d;\n",
+		       argv[1], total);
+
+	return 0;
+}
diff --git a/security/tomoyo/Makefile b/security/tomoyo/Makefile
index b7c6a7ffc058..cca5a3012fee 100644
--- a/security/tomoyo/Makefile
+++ b/security/tomoyo/Makefile
@@ -4,7 +4,7 @@ obj-y = audit.o common.o condition.o domain.o environ.o file.o gc.o group.o load
 targets += builtin-policy.h
 define do_policy
 echo "static char tomoyo_builtin_$(1)[] __initdata ="; \
-$(objtree)/scripts/basic/bin2c <$(firstword $(wildcard $(obj)/policy/$(1).conf $(srctree)/$(src)/policy/$(1).conf.default) /dev/null); \
+$(objtree)/scripts/bin2c <$(firstword $(wildcard $(obj)/policy/$(1).conf $(srctree)/$(src)/policy/$(1).conf.default) /dev/null); \
 echo ";"
 endef
 quiet_cmd_policy  = POLICY  $@
-- 
cgit v1.2.3


From 934193a654c1f4d0643ddbf4b2529b508cae926e Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Sun, 1 Jul 2018 19:46:06 -0700
Subject: kbuild: verify that $DEPMOD is installed

Verify that 'depmod' ($DEPMOD) is installed.
This is a partial revert of commit 620c231c7a7f
("kbuild: do not check for ancient modutils tools").

Also update Documentation/process/changes.rst to refer to
kmod instead of module-init-tools.

Fixes kernel bugzilla #198965:
https://bugzilla.kernel.org/show_bug.cgi?id=198965

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Lucas De Marchi <lucas.demarchi@profusion.mobi>
Cc: Lucas De Marchi <lucas.de.marchi@gmail.com>
Cc: Michal Marek <michal.lkml@markovi.net>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Chih-Wei Huang <cwhuang@linux.org.tw>
Cc: stable@vger.kernel.org # any kernel since 2012
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/process/changes.rst | 19 +++++++------------
 scripts/depmod.sh                 |  8 +++++++-
 2 files changed, 14 insertions(+), 13 deletions(-)

diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index ddc029734b25..005d8842a503 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -35,7 +35,7 @@ binutils               2.20             ld -v
 flex                   2.5.35           flex --version
 bison                  2.0              bison --version
 util-linux             2.10o            fdformat --version
-module-init-tools      0.9.10           depmod -V
+kmod                   13               depmod -V
 e2fsprogs              1.41.4           e2fsck -V
 jfsutils               1.1.3            fsck.jfs -V
 reiserfsprogs          3.6.3            reiserfsck -V
@@ -156,12 +156,6 @@ is not build with ``CONFIG_KALLSYMS`` and you have no way to rebuild and
 reproduce the Oops with that option, then you can still decode that Oops
 with ksymoops.
 
-Module-Init-Tools
------------------
-
-A new module loader is now in the kernel that requires ``module-init-tools``
-to use.  It is backward compatible with the 2.4.x series kernels.
-
 Mkinitrd
 --------
 
@@ -371,16 +365,17 @@ Util-linux
 
 - <https://www.kernel.org/pub/linux/utils/util-linux/>
 
+Kmod
+----
+
+- <https://www.kernel.org/pub/linux/utils/kernel/kmod/>
+- <https://git.kernel.org/pub/scm/utils/kernel/kmod/kmod.git>
+
 Ksymoops
 --------
 
 - <https://www.kernel.org/pub/linux/utils/kernel/ksymoops/v2.4/>
 
-Module-Init-Tools
------------------
-
-- <https://www.kernel.org/pub/linux/utils/kernel/module-init-tools/>
-
 Mkinitrd
 --------
 
diff --git a/scripts/depmod.sh b/scripts/depmod.sh
index 1a6f85e0e6e1..999d585eaa73 100755
--- a/scripts/depmod.sh
+++ b/scripts/depmod.sh
@@ -10,10 +10,16 @@ fi
 DEPMOD=$1
 KERNELRELEASE=$2
 
-if ! test -r System.map -a -x "$DEPMOD"; then
+if ! test -r System.map ; then
 	exit 0
 fi
 
+if [ -z $(command -v $DEPMOD) ]; then
+	echo "'make modules_install' requires $DEPMOD. Please install it." >&2
+	echo "This is probably in the kmod package." >&2
+	exit 1
+fi
+
 # older versions of depmod require the version string to start with three
 # numbers, so we cheat with a symlink here
 depmod_hack_needed=true
-- 
cgit v1.2.3


From 9afb719e7046c4f2462278862ab3db2961cc141c Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Thu, 5 Jul 2018 17:49:37 -0700
Subject: kbuild: Add build salt to the kernel and modules

In Fedora, the debug information is packaged separately (foo-debuginfo) and
can be installed separately. There's been a long standing issue where only
one version of a debuginfo info package can be installed at a time. There's
been an effort for Fedora for parallel debuginfo to rectify this problem.

Part of the requirement to allow parallel debuginfo to work is that build ids
are unique between builds. The existing upstream rpm implementation ensures
this by re-calculating the build-id using the version and release as a
seed. This doesn't work 100% for the kernel because of the vDSO which is
its own binary and doesn't get updated when embedded.

Fix this by adding some data in an ELF note for both the kernel and modules.
The data is controlled via a Kconfig option so distributions can set it
to an appropriate value to ensure uniqueness between builds.

Suggested-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 include/linux/build-salt.h | 20 ++++++++++++++++++++
 init/Kconfig               |  9 +++++++++
 init/version.c             |  3 +++
 scripts/mod/modpost.c      |  3 +++
 4 files changed, 35 insertions(+)
 create mode 100644 include/linux/build-salt.h

diff --git a/include/linux/build-salt.h b/include/linux/build-salt.h
new file mode 100644
index 000000000000..bb007bd05e7a
--- /dev/null
+++ b/include/linux/build-salt.h
@@ -0,0 +1,20 @@
+#ifndef __BUILD_SALT_H
+#define __BUILD_SALT_H
+
+#include <linux/elfnote.h>
+
+#define LINUX_ELFNOTE_BUILD_SALT       0x100
+
+#ifdef __ASSEMBLER__
+
+#define BUILD_SALT \
+       ELFNOTE(Linux, LINUX_ELFNOTE_BUILD_SALT, .asciz CONFIG_BUILD_SALT)
+
+#else
+
+#define BUILD_SALT \
+       ELFNOTE32("Linux", LINUX_ELFNOTE_BUILD_SALT, CONFIG_BUILD_SALT)
+
+#endif
+
+#endif /* __BUILD_SALT_H */
diff --git a/init/Kconfig b/init/Kconfig
index 041f3a022122..d39b31484c52 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -107,6 +107,15 @@ config LOCALVERSION_AUTO
 
 	  which is done within the script "scripts/setlocalversion".)
 
+config BUILD_SALT
+       string "Build ID Salt"
+       default ""
+       help
+          The build ID is used to link binaries and their debug info. Setting
+          this option will use the value in the calculation of the build id.
+          This is mostly useful for distributions which want to ensure the
+          build is unique between builds. It's safe to leave the default.
+
 config HAVE_KERNEL_GZIP
 	bool
 
diff --git a/init/version.c b/init/version.c
index bfb4e3f4955e..ef4012ec4375 100644
--- a/init/version.c
+++ b/init/version.c
@@ -7,6 +7,7 @@
  */
 
 #include <generated/compile.h>
+#include <linux/build-salt.h>
 #include <linux/export.h>
 #include <linux/uts.h>
 #include <linux/utsname.h>
@@ -49,3 +50,5 @@ const char linux_proc_banner[] =
 	"%s version %s"
 	" (" LINUX_COMPILE_BY "@" LINUX_COMPILE_HOST ")"
 	" (" LINUX_COMPILER ") %s\n";
+
+BUILD_SALT;
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 1663fb19343a..dc6d714e4dcb 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -2125,10 +2125,13 @@ static int check_modname_len(struct module *mod)
  **/
 static void add_header(struct buffer *b, struct module *mod)
 {
+	buf_printf(b, "#include <linux/build-salt.h>\n");
 	buf_printf(b, "#include <linux/module.h>\n");
 	buf_printf(b, "#include <linux/vermagic.h>\n");
 	buf_printf(b, "#include <linux/compiler.h>\n");
 	buf_printf(b, "\n");
+	buf_printf(b, "BUILD_SALT;\n");
+	buf_printf(b, "\n");
 	buf_printf(b, "MODULE_INFO(vermagic, VERMAGIC_STRING);\n");
 	buf_printf(b, "MODULE_INFO(name, KBUILD_MODNAME);\n");
 	buf_printf(b, "\n");
-- 
cgit v1.2.3


From d623f60df03a1e44c823ed906ca8ddbd8d3a5983 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Thu, 5 Jul 2018 17:49:38 -0700
Subject: x86: Add build salt to the vDSO

The vDSO needs to have a unique build id in a similar manner
to the kernel and modules. Use the build salt macro.

Acked-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/x86/entry/vdso/vdso-note.S   | 3 +++
 arch/x86/entry/vdso/vdso32/note.S | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/arch/x86/entry/vdso/vdso-note.S b/arch/x86/entry/vdso/vdso-note.S
index 79a071e4357e..79423170118f 100644
--- a/arch/x86/entry/vdso/vdso-note.S
+++ b/arch/x86/entry/vdso/vdso-note.S
@@ -3,6 +3,7 @@
  * Here we can supply some information useful to userland.
  */
 
+#include <linux/build-salt.h>
 #include <linux/uts.h>
 #include <linux/version.h>
 #include <linux/elfnote.h>
@@ -10,3 +11,5 @@
 ELFNOTE_START(Linux, 0, "a")
 	.long LINUX_VERSION_CODE
 ELFNOTE_END
+
+BUILD_SALT
diff --git a/arch/x86/entry/vdso/vdso32/note.S b/arch/x86/entry/vdso/vdso32/note.S
index 9fd51f206314..e78047d119f6 100644
--- a/arch/x86/entry/vdso/vdso32/note.S
+++ b/arch/x86/entry/vdso/vdso32/note.S
@@ -4,6 +4,7 @@
  * Here we can supply some information useful to userland.
  */
 
+#include <linux/build-salt.h>
 #include <linux/version.h>
 #include <linux/elfnote.h>
 
@@ -14,6 +15,8 @@ ELFNOTE_START(Linux, 0, "a")
 	.long LINUX_VERSION_CODE
 ELFNOTE_END
 
+BUILD_SALT
+
 #ifdef CONFIG_XEN
 /*
  * Add a special note telling glibc's dynamic linker a fake hardware
-- 
cgit v1.2.3


From b399baaaf7522750eab0c2a6b9f0dc511d878dd6 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Thu, 5 Jul 2018 17:49:39 -0700
Subject: powerpc: Add build salt to the vDSO

The vDSO needs to have a unique build id in a similar manner
to the kernel and modules. Use the build salt macro.

Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/powerpc/kernel/vdso32/note.S | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/powerpc/kernel/vdso32/note.S b/arch/powerpc/kernel/vdso32/note.S
index d4b5be4f3d5f..227a7327399e 100644
--- a/arch/powerpc/kernel/vdso32/note.S
+++ b/arch/powerpc/kernel/vdso32/note.S
@@ -5,6 +5,7 @@
 
 #include <linux/uts.h>
 #include <linux/version.h>
+#include <linux/build-salt.h>
 
 #define ASM_ELF_NOTE_BEGIN(name, flags, vendor, type)			      \
 	.section name, flags;						      \
@@ -23,3 +24,5 @@
 	ASM_ELF_NOTE_BEGIN(".note.kernel-version", "a", UTS_SYSNAME, 0)
 	.long LINUX_VERSION_CODE
 	ASM_ELF_NOTE_END
+
+BUILD_SALT
-- 
cgit v1.2.3


From efa75c4923be7fedc00b040116657101f20b3678 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Thu, 5 Jul 2018 17:49:40 -0700
Subject: arm64: Add build salt to the vDSO

The vDSO needs to have a unique build id in a similar manner
to the kernel and modules. Use the build salt macro.

Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/arm64/kernel/vdso/note.S | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/arm64/kernel/vdso/note.S b/arch/arm64/kernel/vdso/note.S
index b82c85e5d972..e20483b104d9 100644
--- a/arch/arm64/kernel/vdso/note.S
+++ b/arch/arm64/kernel/vdso/note.S
@@ -22,7 +22,10 @@
 #include <linux/uts.h>
 #include <linux/version.h>
 #include <linux/elfnote.h>
+#include <linux/build-salt.h>
 
 ELFNOTE_START(Linux, 0, "a")
 	.long LINUX_VERSION_CODE
 ELFNOTE_END
+
+BUILD_SALT
-- 
cgit v1.2.3


From 96f14fe738b69dd97a33efe3cc8ab330af5fd1f1 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Mon, 9 Jul 2018 17:45:58 -0700
Subject: kbuild: Rename HOSTCFLAGS to KBUILD_HOSTCFLAGS

In preparation for enabling command line CFLAGS, re-name HOSTCFLAGS to
KBUILD_HOSTCFLAGS as the internal use only flags. This should not have
any visible effects.

Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/kbuild/makefiles.txt |  2 +-
 Makefile                           |  4 ++--
 arch/alpha/boot/Makefile           |  2 +-
 net/bpfilter/Makefile              |  2 +-
 samples/bpf/Makefile               | 10 +++++-----
 scripts/Kbuild.include             |  2 +-
 scripts/Makefile.host              |  2 +-
 tools/build/Build.include          |  2 +-
 tools/objtool/Makefile             |  2 +-
 9 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 048fc39a6b91..63655c1a3ad6 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -661,7 +661,7 @@ Both possibilities are described in the following.
 
 	When compiling host programs, it is possible to set specific flags.
 	The programs will always be compiled utilising $(HOSTCC) passed
-	the options specified in $(HOSTCFLAGS).
+	the options specified in $(KBUILD_HOSTCFLAGS).
 	To set flags that will take effect for all host programs created
 	in that Makefile, use the variable HOST_EXTRACFLAGS.
 
diff --git a/Makefile b/Makefile
index a89d8a0d3ee1..c364e1100ce0 100644
--- a/Makefile
+++ b/Makefile
@@ -359,7 +359,7 @@ HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null)
 
 HOSTCC       = gcc
 HOSTCXX      = g++
-HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \
+KBUILD_HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \
 		-fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS)
 HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS)
 HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS)
@@ -429,7 +429,7 @@ KBUILD_LDFLAGS_MODULE := -T $(srctree)/scripts/module-common.lds
 LDFLAGS :=
 GCC_PLUGINS_CFLAGS :=
 
-export ARCH SRCARCH CONFIG_SHELL HOSTCC HOSTCFLAGS CROSS_COMPILE AS LD CC
+export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
 export CPP AR NM STRIP OBJCOPY OBJDUMP HOSTLDFLAGS HOST_LOADLIBES
 export MAKE LEX YACC AWK GENKSYMS INSTALLKERNEL PERL PYTHON PYTHON2 PYTHON3 UTS_MACHINE
 export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
diff --git a/arch/alpha/boot/Makefile b/arch/alpha/boot/Makefile
index 0cbe4c59d3ce..991e023a6fc4 100644
--- a/arch/alpha/boot/Makefile
+++ b/arch/alpha/boot/Makefile
@@ -14,7 +14,7 @@ targets		:= vmlinux.gz vmlinux \
 		   tools/bootpzh bootloader bootpheader bootpzheader 
 OBJSTRIP	:= $(obj)/tools/objstrip
 
-HOSTCFLAGS	:= -Wall -I$(objtree)/usr/include
+KBUILD_HOSTCFLAGS := -Wall -I$(objtree)/usr/include
 BOOTCFLAGS	+= -I$(objtree)/$(obj) -I$(srctree)/$(obj)
 
 # SRM bootable image.  Copy to offset 512 of a partition.
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
index 39c6980b5d99..70beeb4ad806 100644
--- a/net/bpfilter/Makefile
+++ b/net/bpfilter/Makefile
@@ -5,7 +5,7 @@
 
 hostprogs-y := bpfilter_umh
 bpfilter_umh-objs := main.o
-HOSTCFLAGS += -I. -Itools/include/ -Itools/include/uapi
+KBUILD_HOSTCFLAGS += -I. -Itools/include/ -Itools/include/uapi
 HOSTCC := $(CC)
 
 ifeq ($(CONFIG_BPFILTER_UMH), y)
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 1303af10e54d..494ef04c56cc 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -164,11 +164,11 @@ always += xdpsock_kern.o
 always += xdp_fwd_kern.o
 always += task_fd_query_kern.o
 
-HOSTCFLAGS += -I$(objtree)/usr/include
-HOSTCFLAGS += -I$(srctree)/tools/lib/
-HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
-HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
-HOSTCFLAGS += -I$(srctree)/tools/perf
+KBUILD_HOSTCFLAGS += -I$(objtree)/usr/include
+KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/
+KBUILD_HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/
+KBUILD_HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include
+KBUILD_HOSTCFLAGS += -I$(srctree)/tools/perf
 
 HOSTCFLAGS_bpf_load.o += -I$(objtree)/usr/include -Wno-unused-variable
 HOSTCFLAGS_trace_helpers.o += -I$(srctree)/tools/lib/bpf/
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 86321f06461e..02bb3163cd8d 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -126,7 +126,7 @@ cc-option = $(call __cc-option, $(CC),\
 # hostcc-option
 # Usage: cflags-y += $(call hostcc-option,-march=winchip-c6,-march=i586)
 hostcc-option = $(call __cc-option, $(HOSTCC),\
-	$(HOSTCFLAGS) $(HOST_EXTRACFLAGS),$(1),$(2))
+	$(KBUILD_HOSTCFLAGS) $(HOST_EXTRACFLAGS),$(1),$(2))
 
 # cc-option-yn
 # Usage: flag := $(call cc-option-yn,-march=winchip-c6)
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index aa971cc3f339..09f00dae21fe 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -62,7 +62,7 @@ host-cxxshobjs	:= $(addprefix $(obj)/,$(host-cxxshobjs))
 #####
 # Handle options to gcc. Support building with separate output directory
 
-_hostc_flags   = $(HOSTCFLAGS)   $(HOST_EXTRACFLAGS)   \
+_hostc_flags   = $(KBUILD_HOSTCFLAGS)   $(HOST_EXTRACFLAGS)   \
                  $(HOSTCFLAGS_$(basetarget).o)
 _hostcxx_flags = $(HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \
                  $(HOSTCXXFLAGS_$(basetarget).o)
diff --git a/tools/build/Build.include b/tools/build/Build.include
index 950c1504ca37..9ec01f4454f9 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -98,4 +98,4 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
 ###
 ## HOSTCC C flags
 
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(KBUILD_HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index f76d9914686a..b5d8c2964b52 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -31,7 +31,7 @@ INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/arch/$(HOSTARCH)/include/uapi \
 	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
-CFLAGS   += -Werror $(WARNINGS) $(HOSTCFLAGS) -g $(INCLUDES)
+CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
 LDFLAGS  += -lelf $(LIBSUBCMD) $(HOSTLDFLAGS)
 
 # Allow old libelf to be used:
-- 
cgit v1.2.3


From 10844aebf44851a981ddaa714351ae61c4b29103 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Mon, 9 Jul 2018 17:45:59 -0700
Subject: kbuild: Rename HOSTCXXFLAGS to KBUILD_HOSTCXXFLAGS

In preparation for enabling command line CXXFLAGS, re-name HOSTCXXFLAGS
to KBUILD_HOSTCXXFLAGS as the internal use only flags. This should not
have any visible effects.

Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile              | 4 ++--
 scripts/Makefile.host | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Makefile b/Makefile
index c364e1100ce0..3d2fff178eb6 100644
--- a/Makefile
+++ b/Makefile
@@ -361,7 +361,7 @@ HOSTCC       = gcc
 HOSTCXX      = g++
 KBUILD_HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \
 		-fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS)
-HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS)
+KBUILD_HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS)
 HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS)
 HOST_LOADLIBES := $(HOST_LFS_LIBS)
 
@@ -432,7 +432,7 @@ GCC_PLUGINS_CFLAGS :=
 export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
 export CPP AR NM STRIP OBJCOPY OBJDUMP HOSTLDFLAGS HOST_LOADLIBES
 export MAKE LEX YACC AWK GENKSYMS INSTALLKERNEL PERL PYTHON PYTHON2 PYTHON3 UTS_MACHINE
-export HOSTCXX HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
+export HOSTCXX KBUILD_HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
 
 export KBUILD_CPPFLAGS NOSTDINC_FLAGS LINUXINCLUDE OBJCOPYFLAGS LDFLAGS
 export KBUILD_CFLAGS CFLAGS_KERNEL CFLAGS_MODULE
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 09f00dae21fe..455d85aa1d37 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -64,7 +64,7 @@ host-cxxshobjs	:= $(addprefix $(obj)/,$(host-cxxshobjs))
 
 _hostc_flags   = $(KBUILD_HOSTCFLAGS)   $(HOST_EXTRACFLAGS)   \
                  $(HOSTCFLAGS_$(basetarget).o)
-_hostcxx_flags = $(HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \
+_hostcxx_flags = $(KBUILD_HOSTCXXFLAGS) $(HOST_EXTRACXXFLAGS) \
                  $(HOSTCXXFLAGS_$(basetarget).o)
 
 ifeq ($(KBUILD_SRC),)
-- 
cgit v1.2.3


From b90a368000abe5e015e0b045ca2ff7c2173b94c0 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Mon, 9 Jul 2018 17:46:00 -0700
Subject: kbuild: Rename HOSTLDFLAGS to KBUILD_HOSTLDFLAGS

In preparation for enabling command line LDFLAGS, re-name HOSTLDFLAGS
to KBUILD_HOSTLDFLAGS as the internal use only flags. This should not
have any visible effects.

Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile               |  4 ++--
 net/bpfilter/Makefile  |  2 +-
 scripts/Makefile.host  | 10 +++++-----
 tools/build/Makefile   |  2 +-
 tools/objtool/Makefile |  2 +-
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/Makefile b/Makefile
index 3d2fff178eb6..d8104dcc0b4f 100644
--- a/Makefile
+++ b/Makefile
@@ -362,7 +362,7 @@ HOSTCXX      = g++
 KBUILD_HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \
 		-fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS)
 KBUILD_HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS)
-HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS)
+KBUILD_HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS)
 HOST_LOADLIBES := $(HOST_LFS_LIBS)
 
 # Make variables (CC, etc...)
@@ -430,7 +430,7 @@ LDFLAGS :=
 GCC_PLUGINS_CFLAGS :=
 
 export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP HOSTLDFLAGS HOST_LOADLIBES
+export CPP AR NM STRIP OBJCOPY OBJDUMP KBUILD_HOSTLDFLAGS HOST_LOADLIBES
 export MAKE LEX YACC AWK GENKSYMS INSTALLKERNEL PERL PYTHON PYTHON2 PYTHON3 UTS_MACHINE
 export HOSTCXX KBUILD_HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
 
diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile
index 70beeb4ad806..0947ee7f70d5 100644
--- a/net/bpfilter/Makefile
+++ b/net/bpfilter/Makefile
@@ -12,7 +12,7 @@ ifeq ($(CONFIG_BPFILTER_UMH), y)
 # builtin bpfilter_umh should be compiled with -static
 # since rootfs isn't mounted at the time of __init
 # function is called and do_execv won't find elf interpreter
-HOSTLDFLAGS += -static
+KBUILD_HOSTLDFLAGS += -static
 endif
 
 $(obj)/bpfilter_umh_blob.o: $(obj)/bpfilter_umh
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index 455d85aa1d37..c019d781b2c9 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -84,7 +84,7 @@ hostcxx_flags  = -Wp,-MD,$(depfile) $(__hostcxx_flags)
 # Create executable from a single .c file
 # host-csingle -> Executable
 quiet_cmd_host-csingle 	= HOSTCC  $@
-      cmd_host-csingle	= $(HOSTCC) $(hostc_flags) $(HOSTLDFLAGS) -o $@ $< \
+      cmd_host-csingle	= $(HOSTCC) $(hostc_flags) $(KBUILD_HOSTLDFLAGS) -o $@ $< \
 	  	$(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
 $(host-csingle): $(obj)/%: $(src)/%.c FORCE
 	$(call if_changed_dep,host-csingle)
@@ -92,7 +92,7 @@ $(host-csingle): $(obj)/%: $(src)/%.c FORCE
 # Link an executable based on list of .o files, all plain c
 # host-cmulti -> executable
 quiet_cmd_host-cmulti	= HOSTLD  $@
-      cmd_host-cmulti	= $(HOSTCC) $(HOSTLDFLAGS) -o $@ \
+      cmd_host-cmulti	= $(HOSTCC) $(KBUILD_HOSTLDFLAGS) -o $@ \
 			  $(addprefix $(obj)/,$($(@F)-objs)) \
 			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
 $(host-cmulti): FORCE
@@ -109,7 +109,7 @@ $(host-cobjs): $(obj)/%.o: $(src)/%.c FORCE
 # Link an executable based on list of .o files, a mixture of .c and .cc
 # host-cxxmulti -> executable
 quiet_cmd_host-cxxmulti	= HOSTLD  $@
-      cmd_host-cxxmulti	= $(HOSTCXX) $(HOSTLDFLAGS) -o $@ \
+      cmd_host-cxxmulti	= $(HOSTCXX) $(KBUILD_HOSTLDFLAGS) -o $@ \
 			  $(foreach o,objs cxxobjs,\
 			  $(addprefix $(obj)/,$($(@F)-$(o)))) \
 			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
@@ -143,7 +143,7 @@ $(host-cxxshobjs): $(obj)/%.o: $(src)/%.c FORCE
 # Link a shared library, based on position independent .o files
 # *.o -> .so shared library (host-cshlib)
 quiet_cmd_host-cshlib	= HOSTLLD -shared $@
-      cmd_host-cshlib	= $(HOSTCC) $(HOSTLDFLAGS) -shared -o $@ \
+      cmd_host-cshlib	= $(HOSTCC) $(KBUILD_HOSTLDFLAGS) -shared -o $@ \
 			  $(addprefix $(obj)/,$($(@F:.so=-objs))) \
 			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
 $(host-cshlib): FORCE
@@ -153,7 +153,7 @@ $(call multi_depend, $(host-cshlib), .so, -objs)
 # Link a shared library, based on position independent .o files
 # *.o -> .so shared library (host-cxxshlib)
 quiet_cmd_host-cxxshlib	= HOSTLLD -shared $@
-      cmd_host-cxxshlib	= $(HOSTCXX) $(HOSTLDFLAGS) -shared -o $@ \
+      cmd_host-cxxshlib	= $(HOSTCXX) $(KBUILD_HOSTLDFLAGS) -shared -o $@ \
 			  $(addprefix $(obj)/,$($(@F:.so=-objs))) \
 			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
 $(host-cxxshlib): FORCE
diff --git a/tools/build/Makefile b/tools/build/Makefile
index 5edf65e684ab..727050c40f09 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -43,7 +43,7 @@ $(OUTPUT)fixdep-in.o: FORCE
 	$(Q)$(MAKE) $(build)=fixdep
 
 $(OUTPUT)fixdep: $(OUTPUT)fixdep-in.o
-	$(QUIET_LINK)$(HOSTCC) $(HOSTLDFLAGS) -o $@ $<
+	$(QUIET_LINK)$(HOSTCC) $(KBUILD_HOSTLDFLAGS) -o $@ $<
 
 FORCE:
 
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index b5d8c2964b52..c9d038f91af6 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -32,7 +32,7 @@ INCLUDES := -I$(srctree)/tools/include \
 	    -I$(srctree)/tools/objtool/arch/$(ARCH)/include
 WARNINGS := $(EXTRA_WARNINGS) -Wno-switch-default -Wno-switch-enum -Wno-packed
 CFLAGS   += -Werror $(WARNINGS) $(KBUILD_HOSTCFLAGS) -g $(INCLUDES)
-LDFLAGS  += -lelf $(LIBSUBCMD) $(HOSTLDFLAGS)
+LDFLAGS  += -lelf $(LIBSUBCMD) $(KBUILD_HOSTLDFLAGS)
 
 # Allow old libelf to be used:
 elfshdr := $(shell echo '$(pound)include <libelf.h>' | $(CC) $(CFLAGS) -x c -E - | grep elf_getshdr)
-- 
cgit v1.2.3


From 8377bd2b9ee1be35b39b5523f640a2b75ddd7c4e Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Mon, 9 Jul 2018 17:46:01 -0700
Subject: kbuild: Rename HOST_LOADLIBES to KBUILD_HOSTLDLIBS

In preparation for enabling command line LDLIBS, re-name HOST_LOADLIBES
to KBUILD_HOSTLDLIBS as the internal use only flags. Also rename
existing usage to HOSTLDLIBS for consistency. This should not have any
visible effects.

Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile                 |  4 ++--
 samples/bpf/Makefile     | 12 ++++++------
 samples/seccomp/Makefile |  6 +++---
 scripts/Makefile         |  4 ++--
 scripts/Makefile.host    | 10 +++++-----
 scripts/kconfig/Makefile |  8 ++++----
 6 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/Makefile b/Makefile
index d8104dcc0b4f..caad81c802a4 100644
--- a/Makefile
+++ b/Makefile
@@ -363,7 +363,7 @@ KBUILD_HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \
 		-fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS)
 KBUILD_HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS)
 KBUILD_HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS)
-HOST_LOADLIBES := $(HOST_LFS_LIBS)
+KBUILD_HOSTLDLIBS   := $(HOST_LFS_LIBS)
 
 # Make variables (CC, etc...)
 AS		= $(CROSS_COMPILE)as
@@ -430,7 +430,7 @@ LDFLAGS :=
 GCC_PLUGINS_CFLAGS :=
 
 export ARCH SRCARCH CONFIG_SHELL HOSTCC KBUILD_HOSTCFLAGS CROSS_COMPILE AS LD CC
-export CPP AR NM STRIP OBJCOPY OBJDUMP KBUILD_HOSTLDFLAGS HOST_LOADLIBES
+export CPP AR NM STRIP OBJCOPY OBJDUMP KBUILD_HOSTLDFLAGS KBUILD_HOSTLDLIBS
 export MAKE LEX YACC AWK GENKSYMS INSTALLKERNEL PERL PYTHON PYTHON2 PYTHON3 UTS_MACHINE
 export HOSTCXX KBUILD_HOSTCXXFLAGS LDFLAGS_MODULE CHECK CHECKFLAGS
 
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 494ef04c56cc..bd9f6c2a808e 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -180,12 +180,12 @@ HOSTCFLAGS_trace_event_user.o += -I$(srctree)/tools/lib/bpf/
 HOSTCFLAGS_sampleip_user.o += -I$(srctree)/tools/lib/bpf/
 HOSTCFLAGS_task_fd_query_user.o += -I$(srctree)/tools/lib/bpf/
 
-HOST_LOADLIBES		+= $(LIBBPF) -lelf
-HOSTLOADLIBES_tracex4		+= -lrt
-HOSTLOADLIBES_trace_output	+= -lrt
-HOSTLOADLIBES_map_perf_test	+= -lrt
-HOSTLOADLIBES_test_overhead	+= -lrt
-HOSTLOADLIBES_xdpsock		+= -pthread
+KBUILD_HOSTLDLIBS		+= $(LIBBPF) -lelf
+HOSTLDLIBS_tracex4		+= -lrt
+HOSTLDLIBS_trace_output	+= -lrt
+HOSTLDLIBS_map_perf_test	+= -lrt
+HOSTLDLIBS_test_overhead	+= -lrt
+HOSTLDLIBS_xdpsock		+= -pthread
 
 # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline:
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
diff --git a/samples/seccomp/Makefile b/samples/seccomp/Makefile
index ba942e3ead89..cf34ff6b4065 100644
--- a/samples/seccomp/Makefile
+++ b/samples/seccomp/Makefile
@@ -30,9 +30,9 @@ HOSTCFLAGS_bpf-direct.o += $(MFLAG)
 HOSTCFLAGS_dropper.o += $(MFLAG)
 HOSTCFLAGS_bpf-helper.o += $(MFLAG)
 HOSTCFLAGS_bpf-fancy.o += $(MFLAG)
-HOSTLOADLIBES_bpf-direct += $(MFLAG)
-HOSTLOADLIBES_bpf-fancy += $(MFLAG)
-HOSTLOADLIBES_dropper += $(MFLAG)
+HOSTLDLIBS_bpf-direct += $(MFLAG)
+HOSTLDLIBS_bpf-fancy += $(MFLAG)
+HOSTLDLIBS_dropper += $(MFLAG)
 endif
 always := $(hostprogs-m)
 endif
diff --git a/scripts/Makefile b/scripts/Makefile
index 59c21ec49b84..61affa300d25 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -23,8 +23,8 @@ hostprogs-$(CONFIG_SYSTEM_EXTRA_CERTIFICATE) += insert-sys-cert
 
 HOSTCFLAGS_sortextable.o = -I$(srctree)/tools/include
 HOSTCFLAGS_asn1_compiler.o = -I$(srctree)/include
-HOSTLOADLIBES_sign-file = -lcrypto
-HOSTLOADLIBES_extract-cert = -lcrypto
+HOSTLDLIBS_sign-file = -lcrypto
+HOSTLDLIBS_extract-cert = -lcrypto
 
 always		:= $(hostprogs-y) $(hostprogs-m)
 
diff --git a/scripts/Makefile.host b/scripts/Makefile.host
index c019d781b2c9..0393f75db4d4 100644
--- a/scripts/Makefile.host
+++ b/scripts/Makefile.host
@@ -85,7 +85,7 @@ hostcxx_flags  = -Wp,-MD,$(depfile) $(__hostcxx_flags)
 # host-csingle -> Executable
 quiet_cmd_host-csingle 	= HOSTCC  $@
       cmd_host-csingle	= $(HOSTCC) $(hostc_flags) $(KBUILD_HOSTLDFLAGS) -o $@ $< \
-	  	$(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
+		$(KBUILD_HOSTLDLIBS) $(HOSTLDLIBS_$(@F))
 $(host-csingle): $(obj)/%: $(src)/%.c FORCE
 	$(call if_changed_dep,host-csingle)
 
@@ -94,7 +94,7 @@ $(host-csingle): $(obj)/%: $(src)/%.c FORCE
 quiet_cmd_host-cmulti	= HOSTLD  $@
       cmd_host-cmulti	= $(HOSTCC) $(KBUILD_HOSTLDFLAGS) -o $@ \
 			  $(addprefix $(obj)/,$($(@F)-objs)) \
-			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
+			  $(KBUILD_HOSTLDLIBS) $(HOSTLDLIBS_$(@F))
 $(host-cmulti): FORCE
 	$(call if_changed,host-cmulti)
 $(call multi_depend, $(host-cmulti), , -objs)
@@ -112,7 +112,7 @@ quiet_cmd_host-cxxmulti	= HOSTLD  $@
       cmd_host-cxxmulti	= $(HOSTCXX) $(KBUILD_HOSTLDFLAGS) -o $@ \
 			  $(foreach o,objs cxxobjs,\
 			  $(addprefix $(obj)/,$($(@F)-$(o)))) \
-			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
+			  $(KBUILD_HOSTLDLIBS) $(HOSTLDLIBS_$(@F))
 $(host-cxxmulti): FORCE
 	$(call if_changed,host-cxxmulti)
 $(call multi_depend, $(host-cxxmulti), , -objs -cxxobjs)
@@ -145,7 +145,7 @@ $(host-cxxshobjs): $(obj)/%.o: $(src)/%.c FORCE
 quiet_cmd_host-cshlib	= HOSTLLD -shared $@
       cmd_host-cshlib	= $(HOSTCC) $(KBUILD_HOSTLDFLAGS) -shared -o $@ \
 			  $(addprefix $(obj)/,$($(@F:.so=-objs))) \
-			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
+			  $(KBUILD_HOSTLDLIBS) $(HOSTLDLIBS_$(@F))
 $(host-cshlib): FORCE
 	$(call if_changed,host-cshlib)
 $(call multi_depend, $(host-cshlib), .so, -objs)
@@ -155,7 +155,7 @@ $(call multi_depend, $(host-cshlib), .so, -objs)
 quiet_cmd_host-cxxshlib	= HOSTLLD -shared $@
       cmd_host-cxxshlib	= $(HOSTCXX) $(KBUILD_HOSTLDFLAGS) -shared -o $@ \
 			  $(addprefix $(obj)/,$($(@F:.so=-objs))) \
-			  $(HOST_LOADLIBES) $(HOSTLOADLIBES_$(@F))
+			  $(KBUILD_HOSTLDLIBS) $(HOSTLDLIBS_$(@F))
 $(host-cxxshlib): FORCE
 	$(call if_changed,host-cxxshlib)
 $(call multi_depend, $(host-cxxshlib), .so, -objs)
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index a3ac2c91331c..f3c0e6261e2a 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -169,7 +169,7 @@ HOSTCFLAGS_zconf.tab.o	:= -I$(src)
 hostprogs-y	+= nconf
 nconf-objs	:= nconf.o zconf.tab.o nconf.gui.o
 
-HOSTLOADLIBES_nconf	= $(shell . $(obj)/.nconf-cfg && echo $$libs)
+HOSTLDLIBS_nconf	= $(shell . $(obj)/.nconf-cfg && echo $$libs)
 HOSTCFLAGS_nconf.o	= $(shell . $(obj)/.nconf-cfg && echo $$cflags)
 HOSTCFLAGS_nconf.gui.o	= $(shell . $(obj)/.nconf-cfg && echo $$cflags)
 
@@ -180,7 +180,7 @@ hostprogs-y	+= mconf
 lxdialog	:= checklist.o inputbox.o menubox.o textbox.o util.o yesno.o
 mconf-objs	:= mconf.o zconf.tab.o $(addprefix lxdialog/, $(lxdialog))
 
-HOSTLOADLIBES_mconf = $(shell . $(obj)/.mconf-cfg && echo $$libs)
+HOSTLDLIBS_mconf = $(shell . $(obj)/.mconf-cfg && echo $$libs)
 $(foreach f, mconf.o $(lxdialog), \
   $(eval HOSTCFLAGS_$f = $$(shell . $(obj)/.mconf-cfg && echo $$$$cflags)))
 
@@ -191,7 +191,7 @@ hostprogs-y	+= qconf
 qconf-cxxobjs	:= qconf.o
 qconf-objs	:= zconf.tab.o
 
-HOSTLOADLIBES_qconf	= $(shell . $(obj)/.qconf-cfg && echo $$libs)
+HOSTLDLIBS_qconf	= $(shell . $(obj)/.qconf-cfg && echo $$libs)
 HOSTCXXFLAGS_qconf.o	= $(shell . $(obj)/.qconf-cfg && echo $$cflags)
 
 $(obj)/qconf.o: $(obj)/.qconf-cfg $(obj)/qconf.moc
@@ -206,7 +206,7 @@ $(obj)/%.moc: $(src)/%.h $(obj)/.qconf-cfg
 hostprogs-y	+= gconf
 gconf-objs	:= gconf.o zconf.tab.o
 
-HOSTLOADLIBES_gconf = $(shell . $(obj)/.gconf-cfg && echo $$libs)
+HOSTLDLIBS_gconf    = $(shell . $(obj)/.gconf-cfg && echo $$libs)
 HOSTCFLAGS_gconf.o  = $(shell . $(obj)/.gconf-cfg && echo $$cflags)
 
 $(obj)/gconf.o: $(obj)/.gconf-cfg
-- 
cgit v1.2.3


From f92d19e0ef9bbbb2984845682e740934ad45473b Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Mon, 9 Jul 2018 17:46:02 -0700
Subject: kbuild: Use HOST*FLAGS options from the command line

Now that we have the rename in place, reuse the HOST*FLAGS options as
something that can be set from the command line and included with the
rest of the flags.

Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/kbuild/kbuild.txt | 16 ++++++++++++++++
 Makefile                        |  9 +++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/Documentation/kbuild/kbuild.txt b/Documentation/kbuild/kbuild.txt
index 114c7ce7b58d..8390c360d4b3 100644
--- a/Documentation/kbuild/kbuild.txt
+++ b/Documentation/kbuild/kbuild.txt
@@ -50,6 +50,22 @@ LDFLAGS_MODULE
 --------------------------------------------------
 Additional options used for $(LD) when linking modules.
 
+HOSTCFLAGS
+--------------------------------------------------
+Additional flags to be passed to $(HOSTCC) when building host programs.
+
+HOSTCXXFLAGS
+--------------------------------------------------
+Additional flags to be passed to $(HOSTCXX) when building host programs.
+
+HOSTLDFLAGS
+--------------------------------------------------
+Additional flags to be passed when linking host programs.
+
+HOSTLDLIBS
+--------------------------------------------------
+Additional libraries to link against when building host programs.
+
 KBUILD_KCONFIG
 --------------------------------------------------
 Set the top-level Kconfig file to the value of this environment
diff --git a/Makefile b/Makefile
index caad81c802a4..433f87015c1d 100644
--- a/Makefile
+++ b/Makefile
@@ -360,10 +360,11 @@ HOST_LFS_LIBS := $(shell getconf LFS_LIBS 2>/dev/null)
 HOSTCC       = gcc
 HOSTCXX      = g++
 KBUILD_HOSTCFLAGS   := -Wall -Wmissing-prototypes -Wstrict-prototypes -O2 \
-		-fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS)
-KBUILD_HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS)
-KBUILD_HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS)
-KBUILD_HOSTLDLIBS   := $(HOST_LFS_LIBS)
+		-fomit-frame-pointer -std=gnu89 $(HOST_LFS_CFLAGS) \
+		$(HOSTCFLAGS)
+KBUILD_HOSTCXXFLAGS := -O2 $(HOST_LFS_CFLAGS) $(HOSTCXXFLAGS)
+KBUILD_HOSTLDFLAGS  := $(HOST_LFS_LDFLAGS) $(HOSTLDFLAGS)
+KBUILD_HOSTLDLIBS   := $(HOST_LFS_LIBS) $(HOSTLDLIBS)
 
 # Make variables (CC, etc...)
 AS		= $(CROSS_COMPILE)as
-- 
cgit v1.2.3


From 4ab3b80159d4db63b902ef635d4b5e882911b2da Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Thu, 28 Jun 2018 16:39:50 -0700
Subject: kconfig: check for pkg-config on make {menu,n,g,x}config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Each of 'make {menu,n,g,x}config' uses (needs) pkg-config to make sure
that other required files are present and to determine build flags
settings, but none of these check that pkg-config itself is present.
Add a check for all 4 of these targets and update
Documentation/process/changes.rst to mention 'pkg-config'.

Fixes kernel bugzilla #77511:
https://bugzilla.kernel.org/show_bug.cgi?id=77511

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Bjørn Forsman <bjorn.forsman@gmail.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/process/changes.rst  | 8 ++++++++
 scripts/kconfig/Makefile           | 1 +
 scripts/kconfig/check-pkgconfig.sh | 8 ++++++++
 3 files changed, 17 insertions(+)
 create mode 100644 scripts/kconfig/check-pkgconfig.sh

diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
index ddc029734b25..81930fe75a53 100644
--- a/Documentation/process/changes.rst
+++ b/Documentation/process/changes.rst
@@ -81,6 +81,14 @@ The build system has, as of 4.13, switched to using thin archives (`ar T`)
 rather than incremental linking (`ld -r`) for built-in.a intermediate steps.
 This requires binutils 2.20 or newer.
 
+pkg-config
+----------
+
+The build system, as of 4.18, requires pkg-config to check for installed
+kconfig tools and to determine flags settings for use in
+'make {menu,n,g,x}config'.  Previously pkg-config was being used but not
+verified or documented.
+
 Flex
 ----
 
diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index a3ac2c91331c..49edb9cc9410 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -215,6 +215,7 @@ $(obj)/zconf.tab.o: $(obj)/zconf.lex.c
 
 # check if necessary packages are available, and configure build flags
 define filechk_conf_cfg
+	$(CONFIG_SHELL) $(srctree)/scripts/kconfig/check-pkgconfig.sh; \
 	$(CONFIG_SHELL) $<
 endef
 
diff --git a/scripts/kconfig/check-pkgconfig.sh b/scripts/kconfig/check-pkgconfig.sh
new file mode 100644
index 000000000000..7a1c40bfb58c
--- /dev/null
+++ b/scripts/kconfig/check-pkgconfig.sh
@@ -0,0 +1,8 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Check for pkg-config presence
+
+if [ -z $(command -v pkg-config) ]; then
+	echo "'make *config' requires 'pkg-config'. Please install it." 1>&2
+	exit 1
+fi
-- 
cgit v1.2.3


From 693359f7ac9012778590a370d076b13db704255e Mon Sep 17 00:00:00 2001
From: Dirk Gouders <dirk@gouders.net>
Date: Tue, 3 Jul 2018 14:43:31 +0200
Subject: kconfig: rename SYMBOL_AUTO to SYMBOL_NO_WRITE

Over time, the use of the flag SYMBOL_AUTO changed from initially
marking three automatically generated symbols ARCH, KERNELRELEASE and
UNAME_RELEASE to today's effect of protecting symbols from being
written out.

Currently, only symbols of type CHOICE and those with option
defconf_list set have that flag set.

Reflect that change in semantics in the flag's name.

Signed-off-by: Dirk Gouders <dirk@gouders.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/confdata.c | 4 ++--
 scripts/kconfig/expr.h     | 2 +-
 scripts/kconfig/gconf.c    | 4 ++--
 scripts/kconfig/menu.c     | 2 +-
 scripts/kconfig/symbol.c   | 2 +-
 scripts/kconfig/zconf.y    | 2 +-
 6 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 39e20974f4a3..d1216e4ade2f 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -397,7 +397,7 @@ int conf_read(const char *name)
 
 	for_all_symbols(i, sym) {
 		sym_calc_value(sym);
-		if (sym_is_choice(sym) || (sym->flags & SYMBOL_AUTO))
+		if (sym_is_choice(sym) || (sym->flags & SYMBOL_NO_WRITE))
 			continue;
 		if (sym_has_value(sym) && (sym->flags & SYMBOL_WRITE)) {
 			/* check that calculated value agrees with saved value */
@@ -832,7 +832,7 @@ static int conf_split_config(void)
 	res = 0;
 	for_all_symbols(i, sym) {
 		sym_calc_value(sym);
-		if ((sym->flags & SYMBOL_AUTO) || !sym->name)
+		if ((sym->flags & SYMBOL_NO_WRITE) || !sym->name)
 			continue;
 		if (sym->flags & SYMBOL_WRITE) {
 			if (sym->flags & SYMBOL_DEF_AUTO) {
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index f63b41b0dd49..84a5199bb46b 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -141,7 +141,7 @@ struct symbol {
 #define SYMBOL_OPTIONAL   0x0100  /* choice is optional - values can be 'n' */
 #define SYMBOL_WRITE      0x0200  /* write symbol to file (KCONFIG_CONFIG) */
 #define SYMBOL_CHANGED    0x0400  /* ? */
-#define SYMBOL_AUTO       0x1000  /* value from environment variable */
+#define SYMBOL_NO_WRITE   0x1000  /* Symbol for internal use only; it will not be written */
 #define SYMBOL_CHECKED    0x2000  /* used during dependency checking */
 #define SYMBOL_WARNED     0x8000  /* warning has been issued */
 
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index 610c4ab54d76..a9e48cc7b50a 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -101,8 +101,8 @@ const char *dbg_sym_flags(int val)
 		strcat(buf, "write/");
 	if (val & SYMBOL_CHANGED)
 		strcat(buf, "changed/");
-	if (val & SYMBOL_AUTO)
-		strcat(buf, "auto/");
+	if (val & SYMBOL_NO_WRITE)
+		strcat(buf, "no_write/");
 
 	buf[strlen(buf) - 1] = '\0';
 
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 379a119dcd1e..4cf15d449c05 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -212,7 +212,7 @@ void menu_add_option(int token, char *arg)
 			sym_defconfig_list = current_entry->sym;
 		else if (sym_defconfig_list != current_entry->sym)
 			zconf_error("trying to redefine defconfig symbol");
-		sym_defconfig_list->flags |= SYMBOL_AUTO;
+		sym_defconfig_list->flags |= SYMBOL_NO_WRITE;
 		break;
 	case T_OPT_ALLNOCONFIG_Y:
 		current_entry->sym->flags |= SYMBOL_ALLNOCONFIG_Y;
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 7c9a88e91cfa..869a5e8e87a5 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -463,7 +463,7 @@ void sym_calc_value(struct symbol *sym)
 		}
 	}
 
-	if (sym->flags & SYMBOL_AUTO)
+	if (sym->flags & SYMBOL_NO_WRITE)
 		sym->flags &= ~SYMBOL_WRITE;
 
 	if (sym->flags & SYMBOL_NEED_SET_CHOICE_VALUES)
diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y
index 4b68272ebdb9..96081aa0fef0 100644
--- a/scripts/kconfig/zconf.y
+++ b/scripts/kconfig/zconf.y
@@ -265,7 +265,7 @@ symbol_option_arg:
 choice: T_CHOICE word_opt T_EOL
 {
 	struct symbol *sym = sym_lookup($2, SYMBOL_CHOICE);
-	sym->flags |= SYMBOL_AUTO;
+	sym->flags |= SYMBOL_NO_WRITE;
 	menu_add_entry(sym);
 	menu_add_expr(P_CHOICE, NULL, NULL);
 	free($2);
-- 
cgit v1.2.3


From a8bd3b884dd79dcc9a89dedd0e24b7554de4fe79 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Jul 2018 10:26:55 +0100
Subject: drm/i915: Flush chipset caches after GGTT writes

Our I915g (early gen3, the oldest machine we have in the farm) is still
reporting occasional incoherency performing the following operations:

  1) write through GGTT (indirect write into memory)
  2) write through either CPU or WC (direct write into memory)
  3) read from GGTT (indirect read)

Instead of reporting the value from (2), the read from GGTT reports the
earlier value written via the GGTT. We have made sure that the writes are
flushed from the CPU (commit 3a32497f0dbe ("drm/i915/selftests: Provide
full mb() around clflush") and commit add00e6d896f ("drm/i915: Flush the
WCB following a WC write")), but still see the error, just less
frequently. The only remaining cache that might be affected here is a
chipset cache, so flush that as well.

Testcase: igt/drv_selftest/live_coherency #gdg
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717092655.28417-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 42d24410a98c..08266791801e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -802,7 +802,7 @@ void i915_gem_flush_ggtt_writes(struct drm_i915_private *dev_priv)
 	 * that was!).
 	 */
 
-	wmb();
+	i915_gem_chipset_flush(dev_priv);
 
 	intel_runtime_pm_get(dev_priv);
 	spin_lock_irq(&dev_priv->uncore.lock);
-- 
cgit v1.2.3


From 5c93316c8c2276323af2d98e9676efda7d055bee Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Fri, 13 Jul 2018 17:51:56 +0200
Subject: mips: unify prom_putchar() declarations

prom_putchar() is used centrally in early printk infrastructure therefore
at least MIPS should agree on the function return type.

[paul.burton@mips.com:
  - Include linux/types.h in asm/setup.h to gain the bool typedef before
    we start include asm/setup.h elsewhere.
  - Include asm/setup.h in all files that use or define prom_putchar().
  - Also standardise on signed rather than unsigned char argument.]

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19842/
Cc: linux-mips@linux-mips.org
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Jonas Gorski <jonas.gorski@gmail.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
---
 arch/mips/alchemy/board-gpr.c              |  3 ++-
 arch/mips/alchemy/board-mtx1.c             |  3 ++-
 arch/mips/alchemy/board-xxs1500.c          |  3 ++-
 arch/mips/alchemy/devboards/platform.c     |  3 ++-
 arch/mips/ar7/prom.c                       |  4 ++--
 arch/mips/ath25/early_printk.c             |  5 +++--
 arch/mips/ath79/early_printk.c             | 16 +++++++++-------
 arch/mips/bcm63xx/early_printk.c           |  1 +
 arch/mips/boot/compressed/uart-prom.c      |  3 +--
 arch/mips/cavium-octeon/setup.c            |  4 ++--
 arch/mips/fw/arc/arc_con.c                 |  1 +
 arch/mips/fw/arc/promlib.c                 |  1 +
 arch/mips/fw/sni/sniprom.c                 |  1 +
 arch/mips/include/asm/setup.h              |  2 ++
 arch/mips/include/asm/sgialib.h            |  1 -
 arch/mips/include/asm/txx9/generic.h       |  1 -
 arch/mips/kernel/early_printk.c            |  2 --
 arch/mips/kernel/early_printk_8250.c       |  1 +
 arch/mips/lantiq/early_printk.c            |  1 +
 arch/mips/lasat/prom.c                     |  1 +
 arch/mips/loongson64/common/early_printk.c |  1 +
 arch/mips/netlogic/common/earlycons.c      |  1 +
 arch/mips/paravirt/serial.c                |  5 ++---
 arch/mips/pic32/pic32mzda/early_console.c  |  5 ++---
 arch/mips/ralink/early_printk.c            |  7 ++++---
 arch/mips/sgi-ip27/ip27-console.c          |  1 +
 arch/mips/sibyte/common/cfe.c              |  1 +
 arch/mips/txx9/generic/setup.c             |  1 +
 28 files changed, 47 insertions(+), 32 deletions(-)

diff --git a/arch/mips/alchemy/board-gpr.c b/arch/mips/alchemy/board-gpr.c
index fa75d75b5ba9..ddff9a02513d 100644
--- a/arch/mips/alchemy/board-gpr.c
+++ b/arch/mips/alchemy/board-gpr.c
@@ -34,6 +34,7 @@
 #include <asm/bootinfo.h>
 #include <asm/idle.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/gpio-au1000.h>
 #include <prom.h>
@@ -60,7 +61,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/board-mtx1.c b/arch/mips/alchemy/board-mtx1.c
index aab55aaf3d62..d625e6f99ae7 100644
--- a/arch/mips/alchemy/board-mtx1.c
+++ b/arch/mips/alchemy/board-mtx1.c
@@ -31,6 +31,7 @@
 #include <mtd/mtd-abi.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-au1x00/gpio-au1000.h>
 #include <asm/mach-au1x00/au1xxx_eth.h>
@@ -58,7 +59,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/board-xxs1500.c b/arch/mips/alchemy/board-xxs1500.c
index 0fc53e08a894..5f05b8714385 100644
--- a/arch/mips/alchemy/board-xxs1500.c
+++ b/arch/mips/alchemy/board-xxs1500.c
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <prom.h>
 
@@ -55,7 +56,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	alchemy_uart_putchar(AU1000_UART0_PHYS_ADDR, c);
 }
diff --git a/arch/mips/alchemy/devboards/platform.c b/arch/mips/alchemy/devboards/platform.c
index 203854ddd1bb..8d4b65c3268a 100644
--- a/arch/mips/alchemy/devboards/platform.c
+++ b/arch/mips/alchemy/devboards/platform.c
@@ -14,6 +14,7 @@
 #include <asm/bootinfo.h>
 #include <asm/idle.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/mach-au1x00/au1000.h>
 #include <asm/mach-db1x00/bcsr.h>
 
@@ -36,7 +37,7 @@ void __init prom_init(void)
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
-void prom_putchar(unsigned char c)
+void prom_putchar(char c)
 {
 	if (alchemy_get_cputype() == ALCHEMY_CPU_AU1300)
 		alchemy_uart_putchar(AU1300_UART2_PHYS_ADDR, c);
diff --git a/arch/mips/ar7/prom.c b/arch/mips/ar7/prom.c
index dd53987a690f..2ec8d9ac91ec 100644
--- a/arch/mips/ar7/prom.c
+++ b/arch/mips/ar7/prom.c
@@ -25,6 +25,7 @@
 #include <linux/string.h>
 #include <linux/io.h>
 #include <asm/bootinfo.h>
+#include <asm/setup.h>
 
 #include <asm/mach-ar7/ar7.h>
 #include <asm/mach-ar7/prom.h>
@@ -259,10 +260,9 @@ static inline void serial_out(int offset, int value)
 	writel(value, (void *)PORT(offset));
 }
 
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	while ((serial_in(UART_LSR) & UART_LSR_TEMT) == 0)
 		;
 	serial_out(UART_TX, c);
-	return 1;
 }
diff --git a/arch/mips/ath25/early_printk.c b/arch/mips/ath25/early_printk.c
index 36035b628161..d534761e9cda 100644
--- a/arch/mips/ath25/early_printk.c
+++ b/arch/mips/ath25/early_printk.c
@@ -9,6 +9,7 @@
 #include <linux/mm.h>
 #include <linux/io.h>
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 #include "devices.h"
 #include "ar2315_regs.h"
@@ -25,7 +26,7 @@ static inline unsigned char prom_uart_rr(void __iomem *base, unsigned reg)
 	return __raw_readl(base + 4 * reg);
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	static void __iomem *base;
 
@@ -38,7 +39,7 @@ void prom_putchar(unsigned char ch)
 
 	while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
 		;
-	prom_uart_wr(base, UART_TX, ch);
+	prom_uart_wr(base, UART_TX, (unsigned char)ch);
 	while ((prom_uart_rr(base, UART_LSR) & UART_LSR_THRE) == 0)
 		;
 }
diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c
index d1adc59af5bf..de8c91198ac5 100644
--- a/arch/mips/ath79/early_printk.c
+++ b/arch/mips/ath79/early_printk.c
@@ -13,12 +13,13 @@
 #include <linux/errno.h>
 #include <linux/serial_reg.h>
 #include <asm/addrspace.h>
+#include <asm/setup.h>
 
 #include <asm/mach-ath79/ath79.h>
 #include <asm/mach-ath79/ar71xx_regs.h>
 #include <asm/mach-ath79/ar933x_uart.h>
 
-static void (*_prom_putchar) (unsigned char);
+static void (*_prom_putchar)(char);
 
 static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 {
@@ -33,27 +34,28 @@ static inline void prom_putchar_wait(void __iomem *reg, u32 mask, u32 val)
 
 #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE)
 
-static void prom_putchar_ar71xx(unsigned char ch)
+static void prom_putchar_ar71xx(char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR71XX_UART_BASE));
 
 	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
-	__raw_writel(ch, base + UART_TX * 4);
+	__raw_writel((unsigned char)ch, base + UART_TX * 4);
 	prom_putchar_wait(base + UART_LSR * 4, BOTH_EMPTY, BOTH_EMPTY);
 }
 
-static void prom_putchar_ar933x(unsigned char ch)
+static void prom_putchar_ar933x(char ch)
 {
 	void __iomem *base = (void __iomem *)(KSEG1ADDR(AR933X_UART_BASE));
 
 	prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
 			  AR933X_UART_DATA_TX_CSR);
-	__raw_writel(AR933X_UART_DATA_TX_CSR | ch, base + AR933X_UART_DATA_REG);
+	__raw_writel(AR933X_UART_DATA_TX_CSR | (unsigned char)ch,
+		     base + AR933X_UART_DATA_REG);
 	prom_putchar_wait(base + AR933X_UART_DATA_REG, AR933X_UART_DATA_TX_CSR,
 			  AR933X_UART_DATA_TX_CSR);
 }
 
-static void prom_putchar_dummy(unsigned char ch)
+static void prom_putchar_dummy(char ch)
 {
 	/* nothing to do */
 }
@@ -92,7 +94,7 @@ static void prom_putchar_init(void)
 	}
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	if (!_prom_putchar)
 		prom_putchar_init();
diff --git a/arch/mips/bcm63xx/early_printk.c b/arch/mips/bcm63xx/early_printk.c
index 6092226a6d76..9e9ec27c282f 100644
--- a/arch/mips/bcm63xx/early_printk.c
+++ b/arch/mips/bcm63xx/early_printk.c
@@ -8,6 +8,7 @@
 
 #include <bcm63xx_io.h>
 #include <linux/serial_bcm63xx.h>
+#include <asm/setup.h>
 
 static void wait_xfered(void)
 {
diff --git a/arch/mips/boot/compressed/uart-prom.c b/arch/mips/boot/compressed/uart-prom.c
index d6f0fee0a151..a8a0a32e05d1 100644
--- a/arch/mips/boot/compressed/uart-prom.c
+++ b/arch/mips/boot/compressed/uart-prom.c
@@ -1,6 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
-
-extern void prom_putchar(unsigned char ch);
+#include <asm/setup.h>
 
 void putc(char c)
 {
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index a8034d0dcade..6c437486af39 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -36,6 +36,7 @@
 #include <asm/mipsregs.h>
 #include <asm/bootinfo.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/time.h>
 
 #include <asm/octeon/octeon.h>
@@ -1108,7 +1109,7 @@ void __init plat_mem_setup(void)
  * Emit one character to the boot UART.	 Exported for use by the
  * watchdog timer.
  */
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	uint64_t lsrval;
 
@@ -1119,7 +1120,6 @@ int prom_putchar(char c)
 
 	/* Write the byte */
 	cvmx_write_csr(CVMX_MIO_UARTX_THR(octeon_uart), c & 0xffull);
-	return 1;
 }
 EXPORT_SYMBOL(prom_putchar);
 
diff --git a/arch/mips/fw/arc/arc_con.c b/arch/mips/fw/arc/arc_con.c
index 769d4b9ac82e..365e3913231e 100644
--- a/arch/mips/fw/arc/arc_con.c
+++ b/arch/mips/fw/arc/arc_con.c
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/console.h>
 #include <linux/fs.h>
+#include <asm/setup.h>
 #include <asm/sgialib.h>
 
 static void prom_console_write(struct console *co, const char *s,
diff --git a/arch/mips/fw/arc/promlib.c b/arch/mips/fw/arc/promlib.c
index 7e8ba5ce95be..be381307fbb0 100644
--- a/arch/mips/fw/arc/promlib.c
+++ b/arch/mips/fw/arc/promlib.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <asm/sgialib.h>
 #include <asm/bcache.h>
+#include <asm/setup.h>
 
 /*
  * IP22 boardcache is not compatible with board caches.	 Thus we disable it
diff --git a/arch/mips/fw/sni/sniprom.c b/arch/mips/fw/sni/sniprom.c
index 6aa264b9856a..8772617b64ce 100644
--- a/arch/mips/fw/sni/sniprom.c
+++ b/arch/mips/fw/sni/sniprom.c
@@ -19,6 +19,7 @@
 #include <asm/mipsprom.h>
 #include <asm/mipsregs.h>
 #include <asm/bootinfo.h>
+#include <asm/setup.h>
 
 /* special SNI prom calls */
 /*
diff --git a/arch/mips/include/asm/setup.h b/arch/mips/include/asm/setup.h
index d49d247d48a1..bb36a400203d 100644
--- a/arch/mips/include/asm/setup.h
+++ b/arch/mips/include/asm/setup.h
@@ -2,8 +2,10 @@
 #ifndef _MIPS_SETUP_H
 #define _MIPS_SETUP_H
 
+#include <linux/types.h>
 #include <uapi/asm/setup.h>
 
+extern void prom_putchar(char);
 extern void setup_early_printk(void);
 
 #ifdef CONFIG_EARLY_PRINTK_8250
diff --git a/arch/mips/include/asm/sgialib.h b/arch/mips/include/asm/sgialib.h
index 195db5045ae5..0d9fad5915fe 100644
--- a/arch/mips/include/asm/sgialib.h
+++ b/arch/mips/include/asm/sgialib.h
@@ -31,7 +31,6 @@ extern int prom_flags;
 #define PROM_FLAG_DONT_FREE_TEMP	4
 
 /* Simple char-by-char console I/O. */
-extern void prom_putchar(char c);
 extern char prom_getchar(void);
 
 /* Get next memory descriptor after CURR, returns first descriptor
diff --git a/arch/mips/include/asm/txx9/generic.h b/arch/mips/include/asm/txx9/generic.h
index 64887d3c7ec3..9a2c47bf3c40 100644
--- a/arch/mips/include/asm/txx9/generic.h
+++ b/arch/mips/include/asm/txx9/generic.h
@@ -49,7 +49,6 @@ void txx9_spi_init(int busid, unsigned long base, int irq);
 void txx9_ethaddr_init(unsigned int id, unsigned char *ethaddr);
 void txx9_sio_init(unsigned long baseaddr, int irq,
 		   unsigned int line, unsigned int sclk, int nocts);
-void prom_putchar(char c);
 #ifdef CONFIG_EARLY_PRINTK
 extern void (*txx9_prom_putchar)(char c);
 void txx9_sio_putchar_init(unsigned long baseaddr);
diff --git a/arch/mips/kernel/early_printk.c b/arch/mips/kernel/early_printk.c
index 505cb77d1280..4a1647ddfbd9 100644
--- a/arch/mips/kernel/early_printk.c
+++ b/arch/mips/kernel/early_printk.c
@@ -14,8 +14,6 @@
 
 #include <asm/setup.h>
 
-extern void prom_putchar(char);
-
 static void early_console_write(struct console *con, const char *s, unsigned n)
 {
 	while (n-- && *s) {
diff --git a/arch/mips/kernel/early_printk_8250.c b/arch/mips/kernel/early_printk_8250.c
index 83cea3767556..ea26614afac6 100644
--- a/arch/mips/kernel/early_printk_8250.c
+++ b/arch/mips/kernel/early_printk_8250.c
@@ -20,6 +20,7 @@
 #include <linux/io.h>
 #include <linux/serial_core.h>
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 static void __iomem *serial8250_base;
 static unsigned int serial8250_reg_shift;
diff --git a/arch/mips/lantiq/early_printk.c b/arch/mips/lantiq/early_printk.c
index 44bccaee822b..c4aa140b7c91 100644
--- a/arch/mips/lantiq/early_printk.c
+++ b/arch/mips/lantiq/early_printk.c
@@ -8,6 +8,7 @@
 
 #include <linux/cpu.h>
 #include <lantiq_soc.h>
+#include <asm/setup.h>
 
 #define ASC_BUF		1024
 #define LTQ_ASC_FSTAT	((u32 *)(LTQ_EARLY_ASC + 0x0048))
diff --git a/arch/mips/lasat/prom.c b/arch/mips/lasat/prom.c
index 17e15b50a551..37b8fc5b9ac9 100644
--- a/arch/mips/lasat/prom.c
+++ b/arch/mips/lasat/prom.c
@@ -13,6 +13,7 @@
 #include <asm/bootinfo.h>
 #include <asm/lasat/lasat.h>
 #include <asm/cpu.h>
+#include <asm/setup.h>
 
 #include "at93c.h"
 #include <asm/lasat/eeprom.h>
diff --git a/arch/mips/loongson64/common/early_printk.c b/arch/mips/loongson64/common/early_printk.c
index 6ca632e529dc..a782e2b24747 100644
--- a/arch/mips/loongson64/common/early_printk.c
+++ b/arch/mips/loongson64/common/early_printk.c
@@ -10,6 +10,7 @@
  *  option) any later version.
  */
 #include <linux/serial_reg.h>
+#include <asm/setup.h>
 
 #include <loongson.h>
 
diff --git a/arch/mips/netlogic/common/earlycons.c b/arch/mips/netlogic/common/earlycons.c
index 769f93032c53..8f5bc1597550 100644
--- a/arch/mips/netlogic/common/earlycons.c
+++ b/arch/mips/netlogic/common/earlycons.c
@@ -36,6 +36,7 @@
 #include <linux/serial_reg.h>
 
 #include <asm/mipsregs.h>
+#include <asm/setup.h>
 #include <asm/netlogic/haldefs.h>
 #include <asm/netlogic/common.h>
 
diff --git a/arch/mips/paravirt/serial.c b/arch/mips/paravirt/serial.c
index 02b665c02272..a37b6f9f0ede 100644
--- a/arch/mips/paravirt/serial.c
+++ b/arch/mips/paravirt/serial.c
@@ -9,16 +9,15 @@
 #include <linux/kernel.h>
 #include <linux/virtio_console.h>
 #include <linux/kvm_para.h>
+#include <asm/setup.h>
 
 /*
  * Emit one character to the boot console.
  */
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	kvm_hypercall3(KVM_HC_MIPS_CONSOLE_OUTPUT, 0 /*  port 0 */,
 		(unsigned long)&c, 1 /* len == 1 */);
-
-	return 1;
 }
 
 #ifdef CONFIG_VIRTIO_CONSOLE
diff --git a/arch/mips/pic32/pic32mzda/early_console.c b/arch/mips/pic32/pic32mzda/early_console.c
index d7b783463fac..8ed4961b1271 100644
--- a/arch/mips/pic32/pic32mzda/early_console.c
+++ b/arch/mips/pic32/pic32mzda/early_console.c
@@ -13,6 +13,7 @@
  */
 #include <asm/mach-pic32/pic32.h>
 #include <asm/fw/fw.h>
+#include <asm/setup.h>
 
 #include "pic32mzda.h"
 #include "early_pin.h"
@@ -157,7 +158,7 @@ void __init fw_init_early_console(char port)
 	setup_early_console(port, baud);
 }
 
-int prom_putchar(char c)
+void prom_putchar(char c)
 {
 	if (console_port >= 0) {
 		while (__raw_readl(
@@ -166,6 +167,4 @@ int prom_putchar(char c)
 
 		__raw_writel(c, uart_base + U_TXR(console_port));
 	}
-
-	return 1;
 }
diff --git a/arch/mips/ralink/early_printk.c b/arch/mips/ralink/early_printk.c
index 3c59ffe5f5f5..ecd30ddfb3db 100644
--- a/arch/mips/ralink/early_printk.c
+++ b/arch/mips/ralink/early_printk.c
@@ -10,6 +10,7 @@
 #include <linux/serial_reg.h>
 
 #include <asm/addrspace.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_SOC_RT288X
 #define EARLY_UART_BASE		0x300c00
@@ -68,7 +69,7 @@ static void find_uart_base(void)
 	}
 }
 
-void prom_putchar(unsigned char ch)
+void prom_putchar(char ch)
 {
 	if (!init_complete) {
 		find_uart_base();
@@ -76,13 +77,13 @@ void prom_putchar(unsigned char ch)
 	}
 
 	if (IS_ENABLED(CONFIG_SOC_MT7621) || soc_is_mt7628()) {
-		uart_w32(ch, UART_TX);
+		uart_w32((unsigned char)ch, UART_TX);
 		while ((uart_r32(UART_REG_LSR) & UART_LSR_THRE) == 0)
 			;
 	} else {
 		while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
 			;
-		uart_w32(ch, UART_REG_TX);
+		uart_w32((unsigned char)ch, UART_REG_TX);
 		while ((uart_r32(UART_REG_LSR_RT2880) & UART_LSR_THRE) == 0)
 			;
 	}
diff --git a/arch/mips/sgi-ip27/ip27-console.c b/arch/mips/sgi-ip27/ip27-console.c
index 45fdfbcbd4c6..6bdb48d41276 100644
--- a/arch/mips/sgi-ip27/ip27-console.c
+++ b/arch/mips/sgi-ip27/ip27-console.c
@@ -7,6 +7,7 @@
  */
 
 #include <asm/page.h>
+#include <asm/setup.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/sn0/hub.h>
 #include <asm/sn/klconfig.h>
diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c
index 115399202eab..092fb2a6ec4a 100644
--- a/arch/mips/sibyte/common/cfe.c
+++ b/arch/mips/sibyte/common/cfe.c
@@ -27,6 +27,7 @@
 
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
+#include <asm/setup.h>
 #include <asm/sibyte/board.h>
 #include <asm/smp-ops.h>
 
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 1791a44ee570..dde4dc859f79 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -32,6 +32,7 @@
 #include <asm/reboot.h>
 #include <asm/r4kcache.h>
 #include <asm/sections.h>
+#include <asm/setup.h>
 #include <asm/txx9/generic.h>
 #include <asm/txx9/pci.h>
 #include <asm/txx9tmr.h>
-- 
cgit v1.2.3


From cd87668d601f622e0ebcfea4f78d116d5f572f4d Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 16 Jul 2018 08:26:36 -0700
Subject: MIPS: loongson64: cs5536: Fix PCI_OHCI_INT_REG reads

The PCI_OHCI_INT_REG case in pci_ohci_read_reg() contains the following
if statement:

  if ((lo & 0x00000f00) == CS5536_USB_INTR)

CS5536_USB_INTR expands to the constant 11, which gives us the following
condition which can never evaluate true:

  if ((lo & 0xf00) == 11)

At least when using GCC 8.1.0 this falls foul of the tautoligcal-compare
warning, and since the code is built with the -Werror flag the build
fails.

Fix this by shifting lo right by 8 bits in order to match the
corresponding PCI_OHCI_INT_REG case in pci_ohci_write_reg().

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19861/
Cc: Huacai Chen <chenhc@lemote.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/loongson64/common/cs5536/cs5536_ohci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
index f7c905e50dc4..92dc6bafc127 100644
--- a/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
+++ b/arch/mips/loongson64/common/cs5536/cs5536_ohci.c
@@ -138,7 +138,7 @@ u32 pci_ohci_read_reg(int reg)
 		break;
 	case PCI_OHCI_INT_REG:
 		_rdmsr(DIVIL_MSR_REG(PIC_YSEL_LOW), &hi, &lo);
-		if ((lo & 0x00000f00) == CS5536_USB_INTR)
+		if (((lo >> PIC_YSEL_LOW_USB_SHIFT) & 0xf) == CS5536_USB_INTR)
 			conf_data = 1;
 		break;
 	default:
-- 
cgit v1.2.3


From a708edf13fb0b55d29a003b00251bccbfec74b20 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 17 Jul 2018 10:54:28 +0200
Subject: drm/vc4: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717085428.18500-1-tzimmermann@suse.de
---
 drivers/gpu/drm/vc4/vc4_drv.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_drv.c b/drivers/gpu/drm/vc4/vc4_drv.c
index e42fd5ec41cc..04270a14fcaa 100644
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -288,7 +288,7 @@ static int vc4_drm_bind(struct device *dev)
 
 	ret = vc4_bo_cache_init(drm);
 	if (ret)
-		goto dev_unref;
+		goto dev_put;
 
 	drm_mode_config_init(drm);
 
@@ -313,8 +313,8 @@ unbind_all:
 gem_destroy:
 	vc4_gem_destroy(drm);
 	vc4_bo_cache_destroy(drm);
-dev_unref:
-	drm_dev_unref(drm);
+dev_put:
+	drm_dev_put(drm);
 	return ret;
 }
 
@@ -331,7 +331,7 @@ static void vc4_drm_unbind(struct device *dev)
 
 	drm_atomic_private_obj_fini(&vc4->ctm_manager);
 
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops vc4_drm_ops = {
-- 
cgit v1.2.3


From f9760772d26560ec137fb1c768487c601b93dbc3 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 17 Jul 2018 10:36:57 +0200
Subject: drm/pl111: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717083657.16262-1-tzimmermann@suse.de
---
 drivers/gpu/drm/pl111/pl111_drv.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/pl111/pl111_drv.c b/drivers/gpu/drm/pl111/pl111_drv.c
index 17a38e85ba7d..47fe30223444 100644
--- a/drivers/gpu/drm/pl111/pl111_drv.c
+++ b/drivers/gpu/drm/pl111/pl111_drv.c
@@ -304,13 +304,14 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 	if (IS_ERR(priv->regs)) {
 		dev_err(dev, "%s failed mmio\n", __func__);
 		ret = PTR_ERR(priv->regs);
-		goto dev_unref;
+		goto dev_put;
 	}
 
 	/* This may override some variant settings */
 	ret = pl111_versatile_init(dev, priv);
 	if (ret)
-		goto dev_unref;
+		goto dev_put;
+
 	pl111_nomadik_init(dev);
 
 	/* turn off interrupts before requesting the irq */
@@ -325,16 +326,16 @@ static int pl111_amba_probe(struct amba_device *amba_dev,
 
 	ret = pl111_modeset_init(drm);
 	if (ret != 0)
-		goto dev_unref;
+		goto dev_put;
 
 	ret = drm_dev_register(drm, 0);
 	if (ret < 0)
-		goto dev_unref;
+		goto dev_put;
 
 	return 0;
 
-dev_unref:
-	drm_dev_unref(drm);
+dev_put:
+	drm_dev_put(drm);
 	of_reserved_mem_device_release(dev);
 
 	return ret;
@@ -351,7 +352,7 @@ static int pl111_amba_remove(struct amba_device *amba_dev)
 	if (priv->panel)
 		drm_panel_bridge_remove(priv->bridge);
 	drm_mode_config_cleanup(drm);
-	drm_dev_unref(drm);
+	drm_dev_put(drm);
 	of_reserved_mem_device_release(dev);
 
 	return 0;
-- 
cgit v1.2.3


From 108019a7e6a34df91246365066bea7cf6faf6b02 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 4 Jul 2018 09:22:55 -0500
Subject: drm/pl111: Use 64-bit arithmetic instead of 32-bit

Add suffix ULL to constant 1000 in order to give the compiler complete
information about the proper arithmetic to use.

Notice that such constant is used in a context that expects an
expression of type u64 (64 bits, unsigned) and the following
expression is currently being evaluated using 32-bit arithmetic:

mode->clock * 1000

Addresses-Coverity-ID: 1466139 ("Unintentional integer overflow")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Link: https://patchwork.freedesktop.org/patch/msgid/20180704142255.GA8614@embeddedor.com
---
 drivers/gpu/drm/pl111/pl111_display.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/pl111/pl111_display.c b/drivers/gpu/drm/pl111/pl111_display.c
index a432eb7ad445..754f6b25f265 100644
--- a/drivers/gpu/drm/pl111/pl111_display.c
+++ b/drivers/gpu/drm/pl111/pl111_display.c
@@ -63,7 +63,7 @@ pl111_mode_valid(struct drm_crtc *crtc,
 	 * We use the pixelclock to also account for interlaced modes, the
 	 * resulting bandwidth is in bytes per second.
 	 */
-	bw = mode->clock * 1000; /* In Hz */
+	bw = mode->clock * 1000ULL; /* In Hz */
 	bw = bw * mode->hdisplay * mode->vdisplay * cpp;
 	bw = div_u64(bw, mode->htotal * mode->vtotal);
 
-- 
cgit v1.2.3


From 290e44b7dd116cc61cf37b7ca0be13313bb11e37 Mon Sep 17 00:00:00 2001
From: Paul Moore <paul@paul-moore.com>
Date: Tue, 17 Jul 2018 14:45:08 -0400
Subject: audit: use ktime_get_coarse_real_ts64() for timestamps

Commit c72051d5778a ("audit: use ktime_get_coarse_ts64() for time
access") converted audit's use of current_kernel_time64() to the
new ktime_get_coarse_ts64() function.  Unfortunately this resulted
in incorrect timestamps, e.g. events stamped with the year 1969
despite it being 2018.  This patch corrects this by using
ktime_get_coarse_real_ts64() just like the current_kernel_time64()
wrapper.

Fixes: c72051d5778a ("audit: use ktime_get_coarse_ts64() for time access")
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/audit.c   | 2 +-
 kernel/auditsc.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/audit.c b/kernel/audit.c
index e17bc697d11c..2a8058764aa6 100644
--- a/kernel/audit.c
+++ b/kernel/audit.c
@@ -1721,7 +1721,7 @@ static inline void audit_get_stamp(struct audit_context *ctx,
 				   struct timespec64 *t, unsigned int *serial)
 {
 	if (!ctx || !auditsc_get_stamp(ctx, t, serial)) {
-		ktime_get_coarse_ts64(t);
+		ktime_get_coarse_real_ts64(t);
 		*serial = audit_serial();
 	}
 }
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index f6a0cb32d76e..fb207466e99b 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1543,7 +1543,7 @@ void __audit_syscall_entry(int major, unsigned long a1, unsigned long a2,
 	context->in_syscall = 1;
 	context->current_state  = state;
 	context->ppid       = 0;
-	ktime_get_coarse_ts64(&context->ctime);
+	ktime_get_coarse_real_ts64(&context->ctime);
 }
 
 /**
-- 
cgit v1.2.3


From a1917b73d89e88a6ecdd076b9d6618682f1b0d08 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 13 Jul 2018 17:15:54 +0200
Subject: drm/amdgpu: remove job->adev (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can get that from the ring.

v2: squash in "drm/amdgpu: always initialize job->base.sched" (Alex)

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 18 +++++++++++-------
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.h |  1 -
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 0e2b18ccdf2e..9b1c54ace583 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -37,7 +37,7 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 		  job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
 		  ring->fence_drv.sync_seq);
 
-	amdgpu_device_gpu_recover(job->adev, job, false);
+	amdgpu_device_gpu_recover(ring->adev, job, false);
 }
 
 int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
@@ -54,7 +54,11 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
 	if (!*job)
 		return -ENOMEM;
 
-	(*job)->adev = adev;
+	/*
+	 * Initialize the scheduler to at least some ring so that we always
+	 * have a pointer to adev.
+	 */
+	(*job)->base.sched = &adev->rings[0]->sched;
 	(*job)->vm = vm;
 	(*job)->ibs = (void *)&(*job)[1];
 	(*job)->num_ibs = num_ibs;
@@ -86,6 +90,7 @@ int amdgpu_job_alloc_with_ib(struct amdgpu_device *adev, unsigned size,
 
 void amdgpu_job_free_resources(struct amdgpu_job *job)
 {
+	struct amdgpu_ring *ring = to_amdgpu_ring(job->base.sched);
 	struct dma_fence *f;
 	unsigned i;
 
@@ -93,7 +98,7 @@ void amdgpu_job_free_resources(struct amdgpu_job *job)
 	f = job->base.s_fence ? &job->base.s_fence->finished : job->fence;
 
 	for (i = 0; i < job->num_ibs; ++i)
-		amdgpu_ib_free(job->adev, &job->ibs[i], f);
+		amdgpu_ib_free(ring->adev, &job->ibs[i], f);
 }
 
 static void amdgpu_job_free_cb(struct drm_sched_job *s_job)
@@ -167,7 +172,8 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 
 	if (fence && explicit) {
 		if (drm_sched_dependency_optimized(fence, s_entity)) {
-			r = amdgpu_sync_fence(job->adev, &job->sched_sync, fence, false);
+			r = amdgpu_sync_fence(ring->adev, &job->sched_sync,
+					      fence, false);
 			if (r)
 				DRM_ERROR("Error adding fence to sync (%d)\n", r);
 		}
@@ -190,7 +196,6 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 {
 	struct amdgpu_ring *ring = to_amdgpu_ring(sched_job->sched);
 	struct dma_fence *fence = NULL, *finished;
-	struct amdgpu_device *adev;
 	struct amdgpu_job *job;
 	int r;
 
@@ -200,13 +205,12 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	}
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
-	adev = job->adev;
 
 	BUG_ON(amdgpu_sync_peek_fence(&job->sync, NULL));
 
 	trace_amdgpu_sched_run_job(job);
 
-	if (job->vram_lost_counter != atomic_read(&adev->vram_lost_counter))
+	if (job->vram_lost_counter != atomic_read(&ring->adev->vram_lost_counter))
 		dma_fence_set_error(finished, -ECANCELED);/* skip IB as well if VRAM lost */
 
 	if (finished->error < 0) {
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
index d77fd232f7ce..57cfe78a262b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.h
@@ -37,7 +37,6 @@ struct amdgpu_fence;
 
 struct amdgpu_job {
 	struct drm_sched_job    base;
-	struct amdgpu_device	*adev;
 	struct amdgpu_vm	*vm;
 	struct amdgpu_sync	sync;
 	struct amdgpu_sync	sched_sync;
-- 
cgit v1.2.3


From f024e88343f712941f250f53ddb2652538ea7e95 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 13 Jul 2018 14:01:08 +0200
Subject: drm/amdgpu: minor cleanup in amdgpu_job.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove superflous NULL check, fix coding style a bit, shorten error
messages.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Acked-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 9b1c54ace583..42a4764d728e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -33,7 +33,7 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
 	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
 	struct amdgpu_job *job = to_amdgpu_job(s_job);
 
-	DRM_ERROR("ring %s timeout, last signaled seq=%u, last emitted seq=%u\n",
+	DRM_ERROR("ring %s timeout, signaled seq=%u, emitted seq=%u\n",
 		  job->base.sched->name, atomic_read(&ring->fence_drv.last_seq),
 		  ring->fence_drv.sync_seq);
 
@@ -166,16 +166,17 @@ static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 	struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->sched);
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
 	struct amdgpu_vm *vm = job->vm;
+	struct dma_fence *fence;
 	bool explicit = false;
 	int r;
-	struct dma_fence *fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 
+	fence = amdgpu_sync_get_fence(&job->sync, &explicit);
 	if (fence && explicit) {
 		if (drm_sched_dependency_optimized(fence, s_entity)) {
 			r = amdgpu_sync_fence(ring->adev, &job->sched_sync,
 					      fence, false);
 			if (r)
-				DRM_ERROR("Error adding fence to sync (%d)\n", r);
+				DRM_ERROR("Error adding fence (%d)\n", r);
 		}
 	}
 
@@ -199,10 +200,6 @@ static struct dma_fence *amdgpu_job_run(struct drm_sched_job *sched_job)
 	struct amdgpu_job *job;
 	int r;
 
-	if (!sched_job) {
-		DRM_ERROR("job is null\n");
-		return NULL;
-	}
 	job = to_amdgpu_job(sched_job);
 	finished = &job->base.s_fence->finished;
 
-- 
cgit v1.2.3


From ae891abe7c2ccf75b69ca8330225e37ecc06924e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 11 Jul 2018 15:17:22 +0200
Subject: drm/i915: Split audio component to a generic type

For allowing other drivers to use the DRM audio component, rename the
i915_audio_component_* with drm_audio_component_*, and split the
generic part into drm_audio_component.h.  The i915 specific stuff
remains in struct i915_audio_component, which contains
drm_audio_component as the base.

The license of drm_audio_component.h is kept to MIT as same as the the
original i915_component.h.

This is a preliminary change for further development, and no
functional changes by this patch itself, merely code-split and
renames.

v1->v2: Use SPDX for drm_audio_component.h, fix remaining i915
        argument in drm_audio_component.h

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 drivers/gpu/drm/i915/intel_audio.c | 22 +++++----
 include/drm/drm_audio_component.h  | 95 ++++++++++++++++++++++++++++++++++++++
 include/drm/i915_component.h       | 85 ++--------------------------------
 include/sound/hda_i915.h           |  6 +--
 include/sound/hdaudio.h            |  6 +--
 sound/hda/hdac_i915.c              | 40 ++++++++--------
 sound/pci/hda/patch_hdmi.c         |  8 ++--
 sound/soc/codecs/hdac_hdmi.c       |  2 +-
 8 files changed, 144 insertions(+), 120 deletions(-)
 create mode 100644 include/drm/drm_audio_component.h

diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index 3ea566f99450..7dd5605d94ae 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -639,11 +639,12 @@ void intel_audio_codec_enable(struct intel_encoder *encoder,
 	dev_priv->av_enc_map[pipe] = encoder;
 	mutex_unlock(&dev_priv->av_mutex);
 
-	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) {
+	if (acomp && acomp->base.audio_ops &&
+	    acomp->base.audio_ops->pin_eld_notify) {
 		/* audio drivers expect pipe = -1 to indicate Non-MST cases */
 		if (!intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST))
 			pipe = -1;
-		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+		acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr,
 						 (int) port, (int) pipe);
 	}
 
@@ -681,11 +682,12 @@ void intel_audio_codec_disable(struct intel_encoder *encoder,
 	dev_priv->av_enc_map[pipe] = NULL;
 	mutex_unlock(&dev_priv->av_mutex);
 
-	if (acomp && acomp->audio_ops && acomp->audio_ops->pin_eld_notify) {
+	if (acomp && acomp->base.audio_ops &&
+	    acomp->base.audio_ops->pin_eld_notify) {
 		/* audio drivers expect pipe = -1 to indicate Non-MST cases */
 		if (!intel_crtc_has_type(old_crtc_state, INTEL_OUTPUT_DP_MST))
 			pipe = -1;
-		acomp->audio_ops->pin_eld_notify(acomp->audio_ops->audio_ptr,
+		acomp->base.audio_ops->pin_eld_notify(acomp->base.audio_ops->audio_ptr,
 						 (int) port, (int) pipe);
 	}
 
@@ -880,7 +882,7 @@ static int i915_audio_component_get_eld(struct device *kdev, int port,
 	return ret;
 }
 
-static const struct i915_audio_component_ops i915_audio_component_ops = {
+static const struct drm_audio_component_ops i915_audio_component_ops = {
 	.owner		= THIS_MODULE,
 	.get_power	= i915_audio_component_get_power,
 	.put_power	= i915_audio_component_put_power,
@@ -897,12 +899,12 @@ static int i915_audio_component_bind(struct device *i915_kdev,
 	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
 	int i;
 
-	if (WARN_ON(acomp->ops || acomp->dev))
+	if (WARN_ON(acomp->base.ops || acomp->base.dev))
 		return -EEXIST;
 
 	drm_modeset_lock_all(&dev_priv->drm);
-	acomp->ops = &i915_audio_component_ops;
-	acomp->dev = i915_kdev;
+	acomp->base.ops = &i915_audio_component_ops;
+	acomp->base.dev = i915_kdev;
 	BUILD_BUG_ON(MAX_PORTS != I915_MAX_PORTS);
 	for (i = 0; i < ARRAY_SIZE(acomp->aud_sample_rate); i++)
 		acomp->aud_sample_rate[i] = 0;
@@ -919,8 +921,8 @@ static void i915_audio_component_unbind(struct device *i915_kdev,
 	struct drm_i915_private *dev_priv = kdev_to_i915(i915_kdev);
 
 	drm_modeset_lock_all(&dev_priv->drm);
-	acomp->ops = NULL;
-	acomp->dev = NULL;
+	acomp->base.ops = NULL;
+	acomp->base.dev = NULL;
 	dev_priv->audio_component = NULL;
 	drm_modeset_unlock_all(&dev_priv->drm);
 }
diff --git a/include/drm/drm_audio_component.h b/include/drm/drm_audio_component.h
new file mode 100644
index 000000000000..e85689f212c2
--- /dev/null
+++ b/include/drm/drm_audio_component.h
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: MIT
+// Copyright © 2014 Intel Corporation
+
+#ifndef _DRM_AUDIO_COMPONENT_H_
+#define _DRM_AUDIO_COMPONENT_H_
+
+/**
+ * struct drm_audio_component_ops - Ops implemented by DRM driver, called by hda driver
+ */
+struct drm_audio_component_ops {
+	/**
+	 * @owner: drm module to pin down
+	 */
+	struct module *owner;
+	/**
+	 * @get_power: get the POWER_DOMAIN_AUDIO power well
+	 *
+	 * Request the power well to be turned on.
+	 */
+	void (*get_power)(struct device *);
+	/**
+	 * @put_power: put the POWER_DOMAIN_AUDIO power well
+	 *
+	 * Allow the power well to be turned off.
+	 */
+	void (*put_power)(struct device *);
+	/**
+	 * @codec_wake_override: Enable/disable codec wake signal
+	 */
+	void (*codec_wake_override)(struct device *, bool enable);
+	/**
+	 * @get_cdclk_freq: Get the Core Display Clock in kHz
+	 */
+	int (*get_cdclk_freq)(struct device *);
+	/**
+	 * @sync_audio_rate: set n/cts based on the sample rate
+	 *
+	 * Called from audio driver. After audio driver sets the
+	 * sample rate, it will call this function to set n/cts
+	 */
+	int (*sync_audio_rate)(struct device *, int port, int pipe, int rate);
+	/**
+	 * @get_eld: fill the audio state and ELD bytes for the given port
+	 *
+	 * Called from audio driver to get the HDMI/DP audio state of the given
+	 * digital port, and also fetch ELD bytes to the given pointer.
+	 *
+	 * It returns the byte size of the original ELD (not the actually
+	 * copied size), zero for an invalid ELD, or a negative error code.
+	 *
+	 * Note that the returned size may be over @max_bytes.  Then it
+	 * implies that only a part of ELD has been copied to the buffer.
+	 */
+	int (*get_eld)(struct device *, int port, int pipe, bool *enabled,
+		       unsigned char *buf, int max_bytes);
+};
+
+/**
+ * struct drm_audio_component_audio_ops - Ops implemented by hda driver, called by DRM driver
+ */
+struct drm_audio_component_audio_ops {
+	/**
+	 * @audio_ptr: Pointer to be used in call to pin_eld_notify
+	 */
+	void *audio_ptr;
+	/**
+	 * @pin_eld_notify: Notify the HDA driver that pin sense and/or ELD information has changed
+	 *
+	 * Called when the DRM driver has set up audio pipeline or has just
+	 * begun to tear it down. This allows the HDA driver to update its
+	 * status accordingly (even when the HDA controller is in power save
+	 * mode).
+	 */
+	void (*pin_eld_notify)(void *audio_ptr, int port, int pipe);
+};
+
+/**
+ * struct drm_audio_component - Used for direct communication between DRM and hda drivers
+ */
+struct drm_audio_component {
+	/**
+	 * @dev: DRM device, used as parameter for ops
+	 */
+	struct device *dev;
+	/**
+	 * @ops: Ops implemented by DRM driver, called by hda driver
+	 */
+	const struct drm_audio_component_ops *ops;
+	/**
+	 * @audio_ops: Ops implemented by hda driver, called by DRM driver
+	 */
+	const struct drm_audio_component_audio_ops *audio_ops;
+};
+
+#endif /* _DRM_AUDIO_COMPONENT_H_ */
diff --git a/include/drm/i915_component.h b/include/drm/i915_component.h
index 346b1f5cb180..fca22d463e1b 100644
--- a/include/drm/i915_component.h
+++ b/include/drm/i915_component.h
@@ -24,101 +24,26 @@
 #ifndef _I915_COMPONENT_H_
 #define _I915_COMPONENT_H_
 
+#include "drm_audio_component.h"
+
 /* MAX_PORT is the number of port
  * It must be sync with I915_MAX_PORTS defined i915_drv.h
  */
 #define MAX_PORTS 6
 
-/**
- * struct i915_audio_component_ops - Ops implemented by i915 driver, called by hda driver
- */
-struct i915_audio_component_ops {
-	/**
-	 * @owner: i915 module
-	 */
-	struct module *owner;
-	/**
-	 * @get_power: get the POWER_DOMAIN_AUDIO power well
-	 *
-	 * Request the power well to be turned on.
-	 */
-	void (*get_power)(struct device *);
-	/**
-	 * @put_power: put the POWER_DOMAIN_AUDIO power well
-	 *
-	 * Allow the power well to be turned off.
-	 */
-	void (*put_power)(struct device *);
-	/**
-	 * @codec_wake_override: Enable/disable codec wake signal
-	 */
-	void (*codec_wake_override)(struct device *, bool enable);
-	/**
-	 * @get_cdclk_freq: Get the Core Display Clock in kHz
-	 */
-	int (*get_cdclk_freq)(struct device *);
-	/**
-	 * @sync_audio_rate: set n/cts based on the sample rate
-	 *
-	 * Called from audio driver. After audio driver sets the
-	 * sample rate, it will call this function to set n/cts
-	 */
-	int (*sync_audio_rate)(struct device *, int port, int pipe, int rate);
-	/**
-	 * @get_eld: fill the audio state and ELD bytes for the given port
-	 *
-	 * Called from audio driver to get the HDMI/DP audio state of the given
-	 * digital port, and also fetch ELD bytes to the given pointer.
-	 *
-	 * It returns the byte size of the original ELD (not the actually
-	 * copied size), zero for an invalid ELD, or a negative error code.
-	 *
-	 * Note that the returned size may be over @max_bytes.  Then it
-	 * implies that only a part of ELD has been copied to the buffer.
-	 */
-	int (*get_eld)(struct device *, int port, int pipe, bool *enabled,
-		       unsigned char *buf, int max_bytes);
-};
-
-/**
- * struct i915_audio_component_audio_ops - Ops implemented by hda driver, called by i915 driver
- */
-struct i915_audio_component_audio_ops {
-	/**
-	 * @audio_ptr: Pointer to be used in call to pin_eld_notify
-	 */
-	void *audio_ptr;
-	/**
-	 * @pin_eld_notify: Notify the HDA driver that pin sense and/or ELD information has changed
-	 *
-	 * Called when the i915 driver has set up audio pipeline or has just
-	 * begun to tear it down. This allows the HDA driver to update its
-	 * status accordingly (even when the HDA controller is in power save
-	 * mode).
-	 */
-	void (*pin_eld_notify)(void *audio_ptr, int port, int pipe);
-};
-
 /**
  * struct i915_audio_component - Used for direct communication between i915 and hda drivers
  */
 struct i915_audio_component {
 	/**
-	 * @dev: i915 device, used as parameter for ops
+	 * @base: the drm_audio_component base class
 	 */
-	struct device *dev;
+	struct drm_audio_component	base;
+
 	/**
 	 * @aud_sample_rate: the array of audio sample rate per port
 	 */
 	int aud_sample_rate[MAX_PORTS];
-	/**
-	 * @ops: Ops implemented by i915 driver, called by hda driver
-	 */
-	const struct i915_audio_component_ops *ops;
-	/**
-	 * @audio_ops: Ops implemented by hda driver, called by i915 driver
-	 */
-	const struct i915_audio_component_audio_ops *audio_ops;
 };
 
 #endif /* _I915_COMPONENT_H_ */
diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h
index a94f5b6f92ac..f69ea84e7b65 100644
--- a/include/sound/hda_i915.h
+++ b/include/sound/hda_i915.h
@@ -5,7 +5,7 @@
 #ifndef __SOUND_HDA_I915_H
 #define __SOUND_HDA_I915_H
 
-#include <drm/i915_component.h>
+#include <drm/drm_audio_component.h>
 
 #ifdef CONFIG_SND_HDA_I915
 int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable);
@@ -17,7 +17,7 @@ int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
 			   bool *audio_enabled, char *buffer, int max_bytes);
 int snd_hdac_i915_init(struct hdac_bus *bus);
 int snd_hdac_i915_exit(struct hdac_bus *bus);
-int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *);
+int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *);
 #else
 static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
 {
@@ -49,7 +49,7 @@ static inline int snd_hdac_i915_exit(struct hdac_bus *bus)
 {
 	return 0;
 }
-static inline int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *ops)
+static inline int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *ops)
 {
 	return -ENODEV;
 }
diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index f1baaa88e766..ab5ee3ef2198 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -333,9 +333,9 @@ struct hdac_bus {
 	spinlock_t reg_lock;
 	struct mutex cmd_mutex;
 
-	/* i915 component interface */
-	struct i915_audio_component *audio_component;
-	int i915_power_refcount;
+	/* DRM component interface */
+	struct drm_audio_component *audio_component;
+	int drm_power_refcount;
 
 	/* parameters required for enhanced capabilities */
 	int num_streams;
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index cbe818eda336..1a88c1aaf9bb 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -16,13 +16,13 @@
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/component.h>
-#include <drm/i915_component.h>
+#include <drm/drm_audio_component.h>
 #include <sound/core.h>
 #include <sound/hdaudio.h>
 #include <sound/hda_i915.h>
 #include <sound/hda_register.h>
 
-static struct i915_audio_component *hdac_acomp;
+static struct drm_audio_component *hdac_acomp;
 
 /**
  * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup
@@ -39,7 +39,7 @@ static struct i915_audio_component *hdac_acomp;
  */
 int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
 {
-	struct i915_audio_component *acomp = bus->audio_component;
+	struct drm_audio_component *acomp = bus->audio_component;
 
 	if (!acomp || !acomp->ops)
 		return -ENODEV;
@@ -74,7 +74,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup);
  */
 int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
 {
-	struct i915_audio_component *acomp = bus->audio_component;
+	struct drm_audio_component *acomp = bus->audio_component;
 
 	if (!acomp || !acomp->ops)
 		return -ENODEV;
@@ -83,14 +83,14 @@ int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
 		enable ? "enable" : "disable");
 
 	if (enable) {
-		if (!bus->i915_power_refcount++) {
+		if (!bus->drm_power_refcount++) {
 			acomp->ops->get_power(acomp->dev);
 			snd_hdac_set_codec_wakeup(bus, true);
 			snd_hdac_set_codec_wakeup(bus, false);
 		}
 	} else {
-		WARN_ON(!bus->i915_power_refcount);
-		if (!--bus->i915_power_refcount)
+		WARN_ON(!bus->drm_power_refcount);
+		if (!--bus->drm_power_refcount)
 			acomp->ops->put_power(acomp->dev);
 	}
 
@@ -119,7 +119,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_display_power);
  */
 void snd_hdac_i915_set_bclk(struct hdac_bus *bus)
 {
-	struct i915_audio_component *acomp = bus->audio_component;
+	struct drm_audio_component *acomp = bus->audio_component;
 	struct pci_dev *pci = to_pci_dev(bus->dev);
 	int cdclk_freq;
 	unsigned int bclk_m, bclk_n;
@@ -206,7 +206,7 @@ int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
 			     int dev_id, int rate)
 {
 	struct hdac_bus *bus = codec->bus;
-	struct i915_audio_component *acomp = bus->audio_component;
+	struct drm_audio_component *acomp = bus->audio_component;
 	int port, pipe;
 
 	if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate)
@@ -244,7 +244,7 @@ int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
 			   bool *audio_enabled, char *buffer, int max_bytes)
 {
 	struct hdac_bus *bus = codec->bus;
-	struct i915_audio_component *acomp = bus->audio_component;
+	struct drm_audio_component *acomp = bus->audio_component;
 	int port, pipe;
 
 	if (!acomp || !acomp->ops || !acomp->ops->get_eld)
@@ -262,7 +262,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld);
 
 static int hdac_component_master_bind(struct device *dev)
 {
-	struct i915_audio_component *acomp = hdac_acomp;
+	struct drm_audio_component *acomp = hdac_acomp;
 	int ret;
 
 	ret = component_bind_all(dev, acomp);
@@ -294,7 +294,7 @@ out_unbind:
 
 static void hdac_component_master_unbind(struct device *dev)
 {
-	struct i915_audio_component *acomp = hdac_acomp;
+	struct drm_audio_component *acomp = hdac_acomp;
 
 	module_put(acomp->ops->owner);
 	component_unbind_all(dev, acomp);
@@ -323,7 +323,7 @@ static int hdac_component_master_match(struct device *dev, void *data)
  *
  * Returns zero for success or a negative error code.
  */
-int snd_hdac_i915_register_notifier(const struct i915_audio_component_audio_ops *aops)
+int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *aops)
 {
 	if (!hdac_acomp)
 		return -ENODEV;
@@ -361,7 +361,8 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 {
 	struct component_match *match = NULL;
 	struct device *dev = bus->dev;
-	struct i915_audio_component *acomp;
+	struct i915_audio_component *i915_acomp;
+	struct drm_audio_component *acomp;
 	int ret;
 
 	if (WARN_ON(hdac_acomp))
@@ -370,9 +371,10 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 	if (!i915_gfx_present())
 		return -ENODEV;
 
-	acomp = kzalloc(sizeof(*acomp), GFP_KERNEL);
-	if (!acomp)
+	i915_acomp = kzalloc(sizeof(*i915_acomp), GFP_KERNEL);
+	if (!i915_acomp)
 		return -ENOMEM;
+	acomp = &i915_acomp->base;
 	bus->audio_component = acomp;
 	hdac_acomp = acomp;
 
@@ -421,13 +423,13 @@ EXPORT_SYMBOL_GPL(snd_hdac_i915_init);
 int snd_hdac_i915_exit(struct hdac_bus *bus)
 {
 	struct device *dev = bus->dev;
-	struct i915_audio_component *acomp = bus->audio_component;
+	struct drm_audio_component *acomp = bus->audio_component;
 
 	if (!acomp)
 		return 0;
 
-	WARN_ON(bus->i915_power_refcount);
-	if (bus->i915_power_refcount > 0 && acomp->ops)
+	WARN_ON(bus->drm_power_refcount);
+	if (bus->drm_power_refcount > 0 && acomp->ops)
 		acomp->ops->put_power(acomp->dev);
 
 	component_master_del(dev, &hdac_component_master_ops);
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index 8a49415aebac..c0847017114c 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -177,7 +177,7 @@ struct hdmi_spec {
 
 	/* i915/powerwell (Haswell+/Valleyview+) specific */
 	bool use_acomp_notifier; /* use i915 eld_notify callback for hotplug */
-	struct i915_audio_component_audio_ops i915_audio_ops;
+	struct drm_audio_component_audio_ops drm_audio_ops;
 
 	struct hdac_chmap chmap;
 	hda_nid_t vendor_nid;
@@ -2511,14 +2511,14 @@ static void register_i915_notifier(struct hda_codec *codec)
 	struct hdmi_spec *spec = codec->spec;
 
 	spec->use_acomp_notifier = true;
-	spec->i915_audio_ops.audio_ptr = codec;
+	spec->drm_audio_ops.audio_ptr = codec;
 	/* intel_audio_codec_enable() or intel_audio_codec_disable()
 	 * will call pin_eld_notify with using audio_ptr pointer
 	 * We need make sure audio_ptr is really setup
 	 */
 	wmb();
-	spec->i915_audio_ops.pin_eld_notify = intel_pin_eld_notify;
-	snd_hdac_i915_register_notifier(&spec->i915_audio_ops);
+	spec->drm_audio_ops.pin_eld_notify = intel_pin_eld_notify;
+	snd_hdac_i915_register_notifier(&spec->drm_audio_ops);
 }
 
 /* setup_stream ops override for HSW+ */
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 3e3a2a9ef310..460075475f20 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1583,7 +1583,7 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 
 }
 
-static struct i915_audio_component_audio_ops aops = {
+static struct drm_audio_component_audio_ops aops = {
 	.pin_eld_notify	= hdac_hdmi_eld_notify_cb,
 };
 
-- 
cgit v1.2.3


From 82887c0beb1ee6b33eed8318d8e8d41c5b3eddae Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 11 Jul 2018 15:48:18 +0200
Subject: ALSA: hda/i915: Associate audio component with devres

The HD-audio i915 binding code contains a single pointer, hdac_acomp,
for allowing the access to audio component from the master bind/unbind
callbacks.  This was needed because the callbacks pass only the device
pointer and we can't guarantee the object type assigned to the drvdata
(which is free for each controller driver implementation).
And this implementation will be a problem if we support multiple
components for different DRM drivers, not only i915.

As a solution, allocate the audio component object via devres and
associate it with the given device, so that the component callbacks
can refer to it via devres_find().

The removal of the object is still done half-manually via
devres_destroy() to make the code consistent (although it may work
without the explicit call).

Also, the snd_hda_i915_register_notifier() had the reference to
hdac_acomp as well.  In this patch, the corresponding code is removed
by passing hdac_bus object to the function, too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hda_i915.h     |  6 ++++--
 sound/hda/hdac_i915.c        | 34 +++++++++++++++++++++-------------
 sound/pci/hda/patch_hdmi.c   |  5 +++--
 sound/soc/codecs/hdac_hdmi.c |  2 +-
 4 files changed, 29 insertions(+), 18 deletions(-)

diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h
index f69ea84e7b65..648263791559 100644
--- a/include/sound/hda_i915.h
+++ b/include/sound/hda_i915.h
@@ -17,7 +17,8 @@ int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
 			   bool *audio_enabled, char *buffer, int max_bytes);
 int snd_hdac_i915_init(struct hdac_bus *bus);
 int snd_hdac_i915_exit(struct hdac_bus *bus);
-int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *);
+int snd_hdac_i915_register_notifier(struct hdac_bus *bus,
+				    const struct drm_audio_component_audio_ops *ops);
 #else
 static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
 {
@@ -49,7 +50,8 @@ static inline int snd_hdac_i915_exit(struct hdac_bus *bus)
 {
 	return 0;
 }
-static inline int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *ops)
+static inline int snd_hdac_i915_register_notifier(struct hdac_bus *bus,
+						  const struct drm_audio_component_audio_ops *ops)
 {
 	return -ENODEV;
 }
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 1a88c1aaf9bb..861b77bbc7df 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -22,7 +22,14 @@
 #include <sound/hda_i915.h>
 #include <sound/hda_register.h>
 
-static struct drm_audio_component *hdac_acomp;
+static void hdac_acomp_release(struct device *dev, void *res)
+{
+}
+
+static struct drm_audio_component *hdac_get_acomp(struct device *dev)
+{
+	return devres_find(dev, hdac_acomp_release, NULL, NULL);
+}
 
 /**
  * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup
@@ -262,7 +269,7 @@ EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld);
 
 static int hdac_component_master_bind(struct device *dev)
 {
-	struct drm_audio_component *acomp = hdac_acomp;
+	struct drm_audio_component *acomp = hdac_get_acomp(dev);
 	int ret;
 
 	ret = component_bind_all(dev, acomp);
@@ -294,7 +301,7 @@ out_unbind:
 
 static void hdac_component_master_unbind(struct device *dev)
 {
-	struct drm_audio_component *acomp = hdac_acomp;
+	struct drm_audio_component *acomp = hdac_get_acomp(dev);
 
 	module_put(acomp->ops->owner);
 	component_unbind_all(dev, acomp);
@@ -314,6 +321,7 @@ static int hdac_component_master_match(struct device *dev, void *data)
 
 /**
  * snd_hdac_i915_register_notifier - Register i915 audio component ops
+ * @bus: HDA core bus
  * @aops: i915 audio component ops
  *
  * This function is supposed to be used only by a HD-audio controller
@@ -323,12 +331,13 @@ static int hdac_component_master_match(struct device *dev, void *data)
  *
  * Returns zero for success or a negative error code.
  */
-int snd_hdac_i915_register_notifier(const struct drm_audio_component_audio_ops *aops)
+int snd_hdac_i915_register_notifier(struct hdac_bus *bus,
+				    const struct drm_audio_component_audio_ops *aops)
 {
-	if (!hdac_acomp)
+	if (!bus->audio_component)
 		return -ENODEV;
 
-	hdac_acomp->audio_ops = aops;
+	bus->audio_component->audio_ops = aops;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_i915_register_notifier);
@@ -365,18 +374,19 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 	struct drm_audio_component *acomp;
 	int ret;
 
-	if (WARN_ON(hdac_acomp))
+	if (WARN_ON(hdac_get_acomp(dev)))
 		return -EBUSY;
 
 	if (!i915_gfx_present())
 		return -ENODEV;
 
-	i915_acomp = kzalloc(sizeof(*i915_acomp), GFP_KERNEL);
+	i915_acomp = devres_alloc(hdac_acomp_release, sizeof(*i915_acomp),
+				  GFP_KERNEL);
 	if (!i915_acomp)
 		return -ENOMEM;
 	acomp = &i915_acomp->base;
 	bus->audio_component = acomp;
-	hdac_acomp = acomp;
+	devres_add(dev, acomp);
 
 	component_match_add(dev, &match, hdac_component_master_match, bus);
 	ret = component_master_add_with_match(dev, &hdac_component_master_ops,
@@ -400,9 +410,8 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 out_master_del:
 	component_master_del(dev, &hdac_component_master_ops);
 out_err:
-	kfree(acomp);
 	bus->audio_component = NULL;
-	hdac_acomp = NULL;
+	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
 	dev_info(dev, "failed to add i915 component master (%d)\n", ret);
 
 	return ret;
@@ -434,9 +443,8 @@ int snd_hdac_i915_exit(struct hdac_bus *bus)
 
 	component_master_del(dev, &hdac_component_master_ops);
 
-	kfree(acomp);
 	bus->audio_component = NULL;
-	hdac_acomp = NULL;
+	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
 
 	return 0;
 }
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index c0847017114c..bf174a013f2d 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -2288,7 +2288,7 @@ static void generic_hdmi_free(struct hda_codec *codec)
 	int pin_idx, pcm_idx;
 
 	if (codec_has_acomp(codec))
-		snd_hdac_i915_register_notifier(NULL);
+		snd_hdac_i915_register_notifier(&codec->bus->core, NULL);
 
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
@@ -2518,7 +2518,8 @@ static void register_i915_notifier(struct hda_codec *codec)
 	 */
 	wmb();
 	spec->drm_audio_ops.pin_eld_notify = intel_pin_eld_notify;
-	snd_hdac_i915_register_notifier(&spec->drm_audio_ops);
+	snd_hdac_i915_register_notifier(&codec->bus->core,
+					&spec->drm_audio_ops);
 }
 
 /* setup_stream ops override for HSW+ */
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 460075475f20..2b7c33db4ded 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1812,7 +1812,7 @@ static int hdmi_codec_probe(struct snd_soc_component *component)
 		return ret;
 
 	aops.audio_ptr = hdev;
-	ret = snd_hdac_i915_register_notifier(&aops);
+	ret = snd_hdac_i915_register_notifier(hdev->bus, &aops);
 	if (ret < 0) {
 		dev_err(&hdev->dev, "notifier register failed: err: %d\n", ret);
 		return ret;
-- 
cgit v1.2.3


From a57942bfdd61b46df94021c9c33b8faaae5b65e1 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 11 Jul 2018 16:23:16 +0200
Subject: ALSA: hda: Make audio component support more generic

This is the final step for more generic support of DRM audio
component.  The generic audio component code is now moved to its own
file, and the symbols are renamed from snd_hac_i915_* to
snd_hdac_acomp_*, respectively.  The generic code is enabled via the
new kconfig, CONFIG_SND_HDA_COMPONENT, while CONFIG_SND_HDA_I915 is
kept as the super-class.

Along with the split, three new callbacks are added to audio_ops:
pin2port is for providing the conversion between the pin number and
the widget id, and master_bind/master_unbin are called at binding /
unbinding the master component, respectively.  All these are optional,
but used in i915 implementation and also other later implementations.

A note about the new snd_hdac_acomp_init() function: there is a slight
difference between this and the old snd_hdac_i915_init().  The latter
(still) synchronizes with the master component binding, i.e. it
assures that the relevant DRM component gets bound when it returns, or
gives a negative error.  Meanwhile the new function doesn't
synchronize but just leaves as is.  It's the responsibility by the
caller's side to synchronize, or the caller may accept the
asynchronous binding on the fly.

v1->v2: Fix missing NULL check in master_bind/unbind

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 drivers/gpu/drm/i915/Kconfig      |   1 +
 include/drm/drm_audio_component.h |  23 +++
 include/sound/hda_component.h     |  61 +++++++
 include/sound/hda_i915.h          |  39 +----
 sound/hda/Kconfig                 |   7 +-
 sound/hda/Makefile                |   1 +
 sound/hda/hdac_component.c        | 335 +++++++++++++++++++++++++++++++++++++
 sound/hda/hdac_i915.c             | 343 ++------------------------------------
 sound/pci/hda/patch_hdmi.c        |  50 ++++--
 sound/soc/codecs/hdac_hdmi.c      |   8 +-
 10 files changed, 486 insertions(+), 382 deletions(-)
 create mode 100644 include/sound/hda_component.h
 create mode 100644 sound/hda/hdac_component.c

diff --git a/drivers/gpu/drm/i915/Kconfig b/drivers/gpu/drm/i915/Kconfig
index dfd95889f4b7..5c607f2c707b 100644
--- a/drivers/gpu/drm/i915/Kconfig
+++ b/drivers/gpu/drm/i915/Kconfig
@@ -23,6 +23,7 @@ config DRM_I915
 	select SYNC_FILE
 	select IOSF_MBI
 	select CRC32
+	select SND_HDA_I915 if SND_HDA_CORE
 	help
 	  Choose this option if you have a system that has "Intel Graphics
 	  Media Accelerator" or "HD Graphics" integrated graphics,
diff --git a/include/drm/drm_audio_component.h b/include/drm/drm_audio_component.h
index e85689f212c2..4923b00328c1 100644
--- a/include/drm/drm_audio_component.h
+++ b/include/drm/drm_audio_component.h
@@ -4,6 +4,8 @@
 #ifndef _DRM_AUDIO_COMPONENT_H_
 #define _DRM_AUDIO_COMPONENT_H_
 
+struct drm_audio_component;
+
 /**
  * struct drm_audio_component_ops - Ops implemented by DRM driver, called by hda driver
  */
@@ -72,6 +74,27 @@ struct drm_audio_component_audio_ops {
 	 * mode).
 	 */
 	void (*pin_eld_notify)(void *audio_ptr, int port, int pipe);
+	/**
+	 * @pin2port: Check and convert from pin node to port number
+	 *
+	 * Called by HDA driver to check and convert from the pin widget node
+	 * number to a port number in the graphics side.
+	 */
+	int (*pin2port)(void *audio_ptr, int pin);
+	/**
+	 * @master_bind: (Optional) component master bind callback
+	 *
+	 * Called at binding master component, for HDA codec-specific
+	 * handling of dynamic binding.
+	 */
+	int (*master_bind)(struct device *dev, struct drm_audio_component *);
+	/**
+	 * @master_unbind: (Optional) component master unbind callback
+	 *
+	 * Called at unbinding master component, for HDA codec-specific
+	 * handling of dynamic unbinding.
+	 */
+	void (*master_unbind)(struct device *dev, struct drm_audio_component *);
 };
 
 /**
diff --git a/include/sound/hda_component.h b/include/sound/hda_component.h
new file mode 100644
index 000000000000..78626cde7081
--- /dev/null
+++ b/include/sound/hda_component.h
@@ -0,0 +1,61 @@
+// SPDX-License-Identifier: GPL-2.0
+// HD-Audio helpers to sync with DRM driver
+
+#ifndef __SOUND_HDA_COMPONENT_H
+#define __SOUND_HDA_COMPONENT_H
+
+#include <drm/drm_audio_component.h>
+
+#ifdef CONFIG_SND_HDA_COMPONENT
+int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable);
+int snd_hdac_display_power(struct hdac_bus *bus, bool enable);
+int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
+			     int dev_id, int rate);
+int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
+			   bool *audio_enabled, char *buffer, int max_bytes);
+int snd_hdac_acomp_init(struct hdac_bus *bus,
+			const struct drm_audio_component_audio_ops *aops,
+			int (*match_master)(struct device *, void *),
+			size_t extra_size);
+int snd_hdac_acomp_exit(struct hdac_bus *bus);
+int snd_hdac_acomp_register_notifier(struct hdac_bus *bus,
+				    const struct drm_audio_component_audio_ops *ops);
+#else
+static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
+{
+	return 0;
+}
+static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
+{
+	return 0;
+}
+static inline int snd_hdac_sync_audio_rate(struct hdac_device *codec,
+					   hda_nid_t nid, int dev_id, int rate)
+{
+	return 0;
+}
+static inline int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid,
+					 int dev_id, bool *audio_enabled,
+					 char *buffer, int max_bytes)
+{
+	return -ENODEV;
+}
+static inline int snd_hdac_acomp_init(struct hdac_bus *bus,
+				      const struct drm_audio_component_audio_ops *aops,
+				      int (*match_master)(struct device *, void *),
+				      size_t extra_size)
+{
+	return -ENODEV;
+}
+static inline int snd_hdac_acomp_exit(struct hdac_bus *bus)
+{
+	return 0;
+}
+static inline int snd_hdac_acomp_register_notifier(struct hdac_bus *bus,
+						  const struct drm_audio_component_audio_ops *ops)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif /* __SOUND_HDA_COMPONENT_H */
diff --git a/include/sound/hda_i915.h b/include/sound/hda_i915.h
index 648263791559..6b79614a893b 100644
--- a/include/sound/hda_i915.h
+++ b/include/sound/hda_i915.h
@@ -5,56 +5,23 @@
 #ifndef __SOUND_HDA_I915_H
 #define __SOUND_HDA_I915_H
 
-#include <drm/drm_audio_component.h>
+#include "hda_component.h"
 
 #ifdef CONFIG_SND_HDA_I915
-int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable);
-int snd_hdac_display_power(struct hdac_bus *bus, bool enable);
 void snd_hdac_i915_set_bclk(struct hdac_bus *bus);
-int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
-			     int dev_id, int rate);
-int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
-			   bool *audio_enabled, char *buffer, int max_bytes);
 int snd_hdac_i915_init(struct hdac_bus *bus);
-int snd_hdac_i915_exit(struct hdac_bus *bus);
-int snd_hdac_i915_register_notifier(struct hdac_bus *bus,
-				    const struct drm_audio_component_audio_ops *ops);
 #else
-static inline int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
-{
-	return 0;
-}
-static inline int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
-{
-	return 0;
-}
 static inline void snd_hdac_i915_set_bclk(struct hdac_bus *bus)
 {
 }
-static inline int snd_hdac_sync_audio_rate(struct hdac_device *codec,
-					   hda_nid_t nid, int dev_id, int rate)
-{
-	return 0;
-}
-static inline int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid,
-					 int dev_id, bool *audio_enabled,
-					 char *buffer, int max_bytes)
-{
-	return -ENODEV;
-}
 static inline int snd_hdac_i915_init(struct hdac_bus *bus)
 {
 	return -ENODEV;
 }
+#endif
 static inline int snd_hdac_i915_exit(struct hdac_bus *bus)
 {
-	return 0;
+	return snd_hdac_acomp_exit(bus);
 }
-static inline int snd_hdac_i915_register_notifier(struct hdac_bus *bus,
-						  const struct drm_audio_component_audio_ops *ops)
-{
-	return -ENODEV;
-}
-#endif
 
 #endif /* __SOUND_HDA_I915_H */
diff --git a/sound/hda/Kconfig b/sound/hda/Kconfig
index 3129546398d0..2d90e11b3eaa 100644
--- a/sound/hda/Kconfig
+++ b/sound/hda/Kconfig
@@ -5,11 +5,12 @@ config SND_HDA_CORE
 config SND_HDA_DSP_LOADER
 	bool
 
+config SND_HDA_COMPONENT
+	bool
+
 config SND_HDA_I915
 	bool
-	default y
-	depends on DRM_I915
-	depends on SND_HDA_CORE
+	select SND_HDA_COMPONENT
 
 config SND_HDA_EXT_CORE
        tristate
diff --git a/sound/hda/Makefile b/sound/hda/Makefile
index e4e726f2ce98..2160202e2dc1 100644
--- a/sound/hda/Makefile
+++ b/sound/hda/Makefile
@@ -6,6 +6,7 @@ snd-hda-core-objs += trace.o
 CFLAGS_trace.o := -I$(src)
 
 # for sync with i915 gfx driver
+snd-hda-core-$(CONFIG_SND_HDA_COMPONENT) += hdac_component.o
 snd-hda-core-$(CONFIG_SND_HDA_I915) += hdac_i915.o
 
 obj-$(CONFIG_SND_HDA_CORE) += snd-hda-core.o
diff --git a/sound/hda/hdac_component.c b/sound/hda/hdac_component.c
new file mode 100644
index 000000000000..6e46a9c73aed
--- /dev/null
+++ b/sound/hda/hdac_component.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0
+// hdac_component.c - routines for sync between HD-A core and DRM driver
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/component.h>
+#include <sound/core.h>
+#include <sound/hdaudio.h>
+#include <sound/hda_component.h>
+#include <sound/hda_register.h>
+
+static void hdac_acomp_release(struct device *dev, void *res)
+{
+}
+
+static struct drm_audio_component *hdac_get_acomp(struct device *dev)
+{
+	return devres_find(dev, hdac_acomp_release, NULL, NULL);
+}
+
+/**
+ * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup
+ * @bus: HDA core bus
+ * @enable: enable or disable the wakeup
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function should be called during the chip reset, also called at
+ * resume for updating STATESTS register read.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
+{
+	struct drm_audio_component *acomp = bus->audio_component;
+
+	if (!acomp || !acomp->ops)
+		return -ENODEV;
+
+	if (!acomp->ops->codec_wake_override)
+		return 0;
+
+	dev_dbg(bus->dev, "%s codec wakeup\n",
+		enable ? "enable" : "disable");
+
+	acomp->ops->codec_wake_override(acomp->dev, enable);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup);
+
+/**
+ * snd_hdac_display_power - Power up / down the power refcount
+ * @bus: HDA core bus
+ * @enable: power up or down
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function manages a refcount and calls the get_power() and
+ * put_power() ops accordingly, toggling the codec wakeup, too.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
+{
+	struct drm_audio_component *acomp = bus->audio_component;
+
+	if (!acomp || !acomp->ops)
+		return -ENODEV;
+
+	dev_dbg(bus->dev, "display power %s\n",
+		enable ? "enable" : "disable");
+
+	if (enable) {
+		if (!bus->drm_power_refcount++) {
+			if (acomp->ops->get_power)
+				acomp->ops->get_power(acomp->dev);
+			snd_hdac_set_codec_wakeup(bus, true);
+			snd_hdac_set_codec_wakeup(bus, false);
+		}
+	} else {
+		WARN_ON(!bus->drm_power_refcount);
+		if (!--bus->drm_power_refcount)
+			if (acomp->ops->put_power)
+				acomp->ops->put_power(acomp->dev);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_display_power);
+
+/**
+ * snd_hdac_sync_audio_rate - Set N/CTS based on the sample rate
+ * @codec: HDA codec
+ * @nid: the pin widget NID
+ * @dev_id: device identifier
+ * @rate: the sample rate to set
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function sets N/CTS value based on the given sample rate.
+ * Returns zero for success, or a negative error code.
+ */
+int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
+			     int dev_id, int rate)
+{
+	struct hdac_bus *bus = codec->bus;
+	struct drm_audio_component *acomp = bus->audio_component;
+	int port, pipe;
+
+	if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate)
+		return -ENODEV;
+	port = nid;
+	if (acomp->audio_ops && acomp->audio_ops->pin2port) {
+		port = acomp->audio_ops->pin2port(codec, nid);
+		if (port < 0)
+			return -EINVAL;
+	}
+	pipe = dev_id;
+	return acomp->ops->sync_audio_rate(acomp->dev, port, pipe, rate);
+}
+EXPORT_SYMBOL_GPL(snd_hdac_sync_audio_rate);
+
+/**
+ * snd_hdac_acomp_get_eld - Get the audio state and ELD via component
+ * @codec: HDA codec
+ * @nid: the pin widget NID
+ * @dev_id: device identifier
+ * @audio_enabled: the pointer to store the current audio state
+ * @buffer: the buffer pointer to store ELD bytes
+ * @max_bytes: the max bytes to be stored on @buffer
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function queries the current state of the audio on the given
+ * digital port and fetches the ELD bytes onto the given buffer.
+ * It returns the number of bytes for the total ELD data, zero for
+ * invalid ELD, or a negative error code.
+ *
+ * The return size is the total bytes required for the whole ELD bytes,
+ * thus it may be over @max_bytes.  If it's over @max_bytes, it implies
+ * that only a part of ELD bytes have been fetched.
+ */
+int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
+			   bool *audio_enabled, char *buffer, int max_bytes)
+{
+	struct hdac_bus *bus = codec->bus;
+	struct drm_audio_component *acomp = bus->audio_component;
+	int port, pipe;
+
+	if (!acomp || !acomp->ops || !acomp->ops->get_eld)
+		return -ENODEV;
+
+	port = nid;
+	if (acomp->audio_ops && acomp->audio_ops->pin2port) {
+		port = acomp->audio_ops->pin2port(codec, nid);
+		if (port < 0)
+			return -EINVAL;
+	}
+	pipe = dev_id;
+	return acomp->ops->get_eld(acomp->dev, port, pipe, audio_enabled,
+				   buffer, max_bytes);
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld);
+
+static int hdac_component_master_bind(struct device *dev)
+{
+	struct drm_audio_component *acomp = hdac_get_acomp(dev);
+	int ret;
+
+	if (WARN_ON(!acomp))
+		return -EINVAL;
+
+	ret = component_bind_all(dev, acomp);
+	if (ret < 0)
+		return ret;
+
+	if (WARN_ON(!(acomp->dev && acomp->ops))) {
+		ret = -EINVAL;
+		goto out_unbind;
+	}
+
+	/* pin the module to avoid dynamic unbinding, but only if given */
+	if (!try_module_get(acomp->ops->owner)) {
+		ret = -ENODEV;
+		goto out_unbind;
+	}
+
+	if (acomp->audio_ops && acomp->audio_ops->master_bind) {
+		ret = acomp->audio_ops->master_bind(dev, acomp);
+		if (ret < 0)
+			goto module_put;
+	}
+
+	return 0;
+
+ module_put:
+	module_put(acomp->ops->owner);
+out_unbind:
+	component_unbind_all(dev, acomp);
+
+	return ret;
+}
+
+static void hdac_component_master_unbind(struct device *dev)
+{
+	struct drm_audio_component *acomp = hdac_get_acomp(dev);
+
+	if (acomp->audio_ops && acomp->audio_ops->master_unbind)
+		acomp->audio_ops->master_unbind(dev, acomp);
+	module_put(acomp->ops->owner);
+	component_unbind_all(dev, acomp);
+	WARN_ON(acomp->ops || acomp->dev);
+}
+
+static const struct component_master_ops hdac_component_master_ops = {
+	.bind = hdac_component_master_bind,
+	.unbind = hdac_component_master_unbind,
+};
+
+/**
+ * snd_hdac_acomp_register_notifier - Register audio component ops
+ * @bus: HDA core bus
+ * @aops: audio component ops
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function sets the given ops to be called by the graphics driver.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_acomp_register_notifier(struct hdac_bus *bus,
+				    const struct drm_audio_component_audio_ops *aops)
+{
+	if (!bus->audio_component)
+		return -ENODEV;
+
+	bus->audio_component->audio_ops = aops;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_register_notifier);
+
+/**
+ * snd_hdac_acomp_init - Initialize audio component
+ * @bus: HDA core bus
+ * @match_master: match function for finding components
+ * @extra_size: Extra bytes to allocate
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function initializes and sets up the audio component to communicate
+ * with graphics driver.
+ *
+ * Unlike snd_hdac_i915_init(), this function doesn't synchronize with the
+ * binding with the DRM component.  Each caller needs to sync via master_bind
+ * audio_ops.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_acomp_init(struct hdac_bus *bus,
+			const struct drm_audio_component_audio_ops *aops,
+			int (*match_master)(struct device *, void *),
+			size_t extra_size)
+{
+	struct component_match *match = NULL;
+	struct device *dev = bus->dev;
+	struct drm_audio_component *acomp;
+	int ret;
+
+	if (WARN_ON(hdac_get_acomp(dev)))
+		return -EBUSY;
+
+	acomp = devres_alloc(hdac_acomp_release, sizeof(*acomp) + extra_size,
+			     GFP_KERNEL);
+	if (!acomp)
+		return -ENOMEM;
+	acomp->audio_ops = aops;
+	bus->audio_component = acomp;
+	devres_add(dev, acomp);
+
+	component_match_add(dev, &match, match_master, bus);
+	ret = component_master_add_with_match(dev, &hdac_component_master_ops,
+					      match);
+	if (ret < 0)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	bus->audio_component = NULL;
+	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
+	dev_info(dev, "failed to add audio component master (%d)\n", ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_init);
+
+/**
+ * snd_hdac_acomp_exit - Finalize audio component
+ * @bus: HDA core bus
+ *
+ * This function is supposed to be used only by a HD-audio controller
+ * driver that needs the interaction with graphics driver.
+ *
+ * This function releases the audio component that has been used.
+ *
+ * Returns zero for success or a negative error code.
+ */
+int snd_hdac_acomp_exit(struct hdac_bus *bus)
+{
+	struct device *dev = bus->dev;
+	struct drm_audio_component *acomp = bus->audio_component;
+
+	if (!acomp)
+		return 0;
+
+	WARN_ON(bus->drm_power_refcount);
+	if (bus->drm_power_refcount > 0 && acomp->ops)
+		acomp->ops->put_power(acomp->dev);
+
+	component_master_del(dev, &hdac_component_master_ops);
+
+	bus->audio_component = NULL;
+	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(snd_hdac_acomp_exit);
diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 861b77bbc7df..8f2aa8bc1185 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -15,96 +15,11 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/component.h>
-#include <drm/drm_audio_component.h>
 #include <sound/core.h>
 #include <sound/hdaudio.h>
 #include <sound/hda_i915.h>
 #include <sound/hda_register.h>
 
-static void hdac_acomp_release(struct device *dev, void *res)
-{
-}
-
-static struct drm_audio_component *hdac_get_acomp(struct device *dev)
-{
-	return devres_find(dev, hdac_acomp_release, NULL, NULL);
-}
-
-/**
- * snd_hdac_set_codec_wakeup - Enable / disable HDMI/DP codec wakeup
- * @bus: HDA core bus
- * @enable: enable or disable the wakeup
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function should be called during the chip reset, also called at
- * resume for updating STATESTS register read.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_set_codec_wakeup(struct hdac_bus *bus, bool enable)
-{
-	struct drm_audio_component *acomp = bus->audio_component;
-
-	if (!acomp || !acomp->ops)
-		return -ENODEV;
-
-	if (!acomp->ops->codec_wake_override) {
-		dev_warn(bus->dev,
-			"Invalid codec wake callback\n");
-		return 0;
-	}
-
-	dev_dbg(bus->dev, "%s codec wakeup\n",
-		enable ? "enable" : "disable");
-
-	acomp->ops->codec_wake_override(acomp->dev, enable);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_set_codec_wakeup);
-
-/**
- * snd_hdac_display_power - Power up / down the power refcount
- * @bus: HDA core bus
- * @enable: power up or down
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function manages a refcount and calls the i915 get_power() and
- * put_power() ops accordingly, toggling the codec wakeup, too.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_display_power(struct hdac_bus *bus, bool enable)
-{
-	struct drm_audio_component *acomp = bus->audio_component;
-
-	if (!acomp || !acomp->ops)
-		return -ENODEV;
-
-	dev_dbg(bus->dev, "display power %s\n",
-		enable ? "enable" : "disable");
-
-	if (enable) {
-		if (!bus->drm_power_refcount++) {
-			acomp->ops->get_power(acomp->dev);
-			snd_hdac_set_codec_wakeup(bus, true);
-			snd_hdac_set_codec_wakeup(bus, false);
-		}
-	} else {
-		WARN_ON(!bus->drm_power_refcount);
-		if (!--bus->drm_power_refcount)
-			acomp->ops->put_power(acomp->dev);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_display_power);
-
 #define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \
 				((pci)->device == 0x0c0c) || \
 				((pci)->device == 0x0d0c) || \
@@ -165,183 +80,11 @@ void snd_hdac_i915_set_bclk(struct hdac_bus *bus)
 }
 EXPORT_SYMBOL_GPL(snd_hdac_i915_set_bclk);
 
-/* There is a fixed mapping between audio pin node and display port.
- * on SNB, IVY, HSW, BSW, SKL, BXT, KBL:
- * Pin Widget 5 - PORT B (port = 1 in i915 driver)
- * Pin Widget 6 - PORT C (port = 2 in i915 driver)
- * Pin Widget 7 - PORT D (port = 3 in i915 driver)
- *
- * on VLV, ILK:
- * Pin Widget 4 - PORT B (port = 1 in i915 driver)
- * Pin Widget 5 - PORT C (port = 2 in i915 driver)
- * Pin Widget 6 - PORT D (port = 3 in i915 driver)
- */
-static int pin2port(struct hdac_device *codec, hda_nid_t pin_nid)
-{
-	int base_nid;
-
-	switch (codec->vendor_id) {
-	case 0x80860054: /* ILK */
-	case 0x80862804: /* ILK */
-	case 0x80862882: /* VLV */
-		base_nid = 3;
-		break;
-	default:
-		base_nid = 4;
-		break;
-	}
-
-	if (WARN_ON(pin_nid <= base_nid || pin_nid > base_nid + 3))
-		return -1;
-	return pin_nid - base_nid;
-}
-
-/**
- * snd_hdac_sync_audio_rate - Set N/CTS based on the sample rate
- * @codec: HDA codec
- * @nid: the pin widget NID
- * @dev_id: device identifier
- * @rate: the sample rate to set
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function sets N/CTS value based on the given sample rate.
- * Returns zero for success, or a negative error code.
- */
-int snd_hdac_sync_audio_rate(struct hdac_device *codec, hda_nid_t nid,
-			     int dev_id, int rate)
+static int i915_component_master_match(struct device *dev, void *data)
 {
-	struct hdac_bus *bus = codec->bus;
-	struct drm_audio_component *acomp = bus->audio_component;
-	int port, pipe;
-
-	if (!acomp || !acomp->ops || !acomp->ops->sync_audio_rate)
-		return -ENODEV;
-	port = pin2port(codec, nid);
-	if (port < 0)
-		return -EINVAL;
-	pipe = dev_id;
-	return acomp->ops->sync_audio_rate(acomp->dev, port, pipe, rate);
-}
-EXPORT_SYMBOL_GPL(snd_hdac_sync_audio_rate);
-
-/**
- * snd_hdac_acomp_get_eld - Get the audio state and ELD via component
- * @codec: HDA codec
- * @nid: the pin widget NID
- * @dev_id: device identifier
- * @audio_enabled: the pointer to store the current audio state
- * @buffer: the buffer pointer to store ELD bytes
- * @max_bytes: the max bytes to be stored on @buffer
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function queries the current state of the audio on the given
- * digital port and fetches the ELD bytes onto the given buffer.
- * It returns the number of bytes for the total ELD data, zero for
- * invalid ELD, or a negative error code.
- *
- * The return size is the total bytes required for the whole ELD bytes,
- * thus it may be over @max_bytes.  If it's over @max_bytes, it implies
- * that only a part of ELD bytes have been fetched.
- */
-int snd_hdac_acomp_get_eld(struct hdac_device *codec, hda_nid_t nid, int dev_id,
-			   bool *audio_enabled, char *buffer, int max_bytes)
-{
-	struct hdac_bus *bus = codec->bus;
-	struct drm_audio_component *acomp = bus->audio_component;
-	int port, pipe;
-
-	if (!acomp || !acomp->ops || !acomp->ops->get_eld)
-		return -ENODEV;
-
-	port = pin2port(codec, nid);
-	if (port < 0)
-		return -EINVAL;
-
-	pipe = dev_id;
-	return acomp->ops->get_eld(acomp->dev, port, pipe, audio_enabled,
-				   buffer, max_bytes);
-}
-EXPORT_SYMBOL_GPL(snd_hdac_acomp_get_eld);
-
-static int hdac_component_master_bind(struct device *dev)
-{
-	struct drm_audio_component *acomp = hdac_get_acomp(dev);
-	int ret;
-
-	ret = component_bind_all(dev, acomp);
-	if (ret < 0)
-		return ret;
-
-	if (WARN_ON(!(acomp->dev && acomp->ops && acomp->ops->get_power &&
-		      acomp->ops->put_power && acomp->ops->get_cdclk_freq))) {
-		ret = -EINVAL;
-		goto out_unbind;
-	}
-
-	/*
-	 * Atm, we don't support dynamic unbinding initiated by the child
-	 * component, so pin its containing module until we unbind.
-	 */
-	if (!try_module_get(acomp->ops->owner)) {
-		ret = -ENODEV;
-		goto out_unbind;
-	}
-
-	return 0;
-
-out_unbind:
-	component_unbind_all(dev, acomp);
-
-	return ret;
-}
-
-static void hdac_component_master_unbind(struct device *dev)
-{
-	struct drm_audio_component *acomp = hdac_get_acomp(dev);
-
-	module_put(acomp->ops->owner);
-	component_unbind_all(dev, acomp);
-	WARN_ON(acomp->ops || acomp->dev);
-}
-
-static const struct component_master_ops hdac_component_master_ops = {
-	.bind = hdac_component_master_bind,
-	.unbind = hdac_component_master_unbind,
-};
-
-static int hdac_component_master_match(struct device *dev, void *data)
-{
-	/* i915 is the only supported component */
 	return !strcmp(dev->driver->name, "i915");
 }
 
-/**
- * snd_hdac_i915_register_notifier - Register i915 audio component ops
- * @bus: HDA core bus
- * @aops: i915 audio component ops
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function sets the given ops to be called by the i915 graphics driver.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_i915_register_notifier(struct hdac_bus *bus,
-				    const struct drm_audio_component_audio_ops *aops)
-{
-	if (!bus->audio_component)
-		return -ENODEV;
-
-	bus->audio_component->audio_ops = aops;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_i915_register_notifier);
-
 /* check whether intel graphics is present */
 static bool i915_gfx_present(void)
 {
@@ -368,84 +111,26 @@ static bool i915_gfx_present(void)
  */
 int snd_hdac_i915_init(struct hdac_bus *bus)
 {
-	struct component_match *match = NULL;
-	struct device *dev = bus->dev;
-	struct i915_audio_component *i915_acomp;
 	struct drm_audio_component *acomp;
-	int ret;
-
-	if (WARN_ON(hdac_get_acomp(dev)))
-		return -EBUSY;
+	int err;
 
 	if (!i915_gfx_present())
 		return -ENODEV;
 
-	i915_acomp = devres_alloc(hdac_acomp_release, sizeof(*i915_acomp),
-				  GFP_KERNEL);
-	if (!i915_acomp)
-		return -ENOMEM;
-	acomp = &i915_acomp->base;
-	bus->audio_component = acomp;
-	devres_add(dev, acomp);
-
-	component_match_add(dev, &match, hdac_component_master_match, bus);
-	ret = component_master_add_with_match(dev, &hdac_component_master_ops,
-					      match);
-	if (ret < 0)
-		goto out_err;
-
-	/*
-	 * Atm, we don't support deferring the component binding, so make sure
-	 * i915 is loaded and that the binding successfully completes.
-	 */
-	request_module("i915");
-
+	err = snd_hdac_acomp_init(bus, NULL,
+				  i915_component_master_match,
+				  sizeof(struct i915_audio_component) - sizeof(*acomp));
+	if (err < 0)
+		return err;
+	acomp = bus->audio_component;
+	if (!acomp)
+		return -ENODEV;
+	if (!acomp->ops)
+		request_module("i915");
 	if (!acomp->ops) {
-		ret = -ENODEV;
-		goto out_master_del;
+		snd_hdac_acomp_exit(bus);
+		return -ENODEV;
 	}
-	dev_dbg(dev, "bound to i915 component master\n");
-
 	return 0;
-out_master_del:
-	component_master_del(dev, &hdac_component_master_ops);
-out_err:
-	bus->audio_component = NULL;
-	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
-	dev_info(dev, "failed to add i915 component master (%d)\n", ret);
-
-	return ret;
 }
 EXPORT_SYMBOL_GPL(snd_hdac_i915_init);
-
-/**
- * snd_hdac_i915_exit - Finalize i915 audio component
- * @bus: HDA core bus
- *
- * This function is supposed to be used only by a HD-audio controller
- * driver that needs the interaction with i915 graphics.
- *
- * This function releases the i915 audio component that has been used.
- *
- * Returns zero for success or a negative error code.
- */
-int snd_hdac_i915_exit(struct hdac_bus *bus)
-{
-	struct device *dev = bus->dev;
-	struct drm_audio_component *acomp = bus->audio_component;
-
-	if (!acomp)
-		return 0;
-
-	WARN_ON(bus->drm_power_refcount);
-	if (bus->drm_power_refcount > 0 && acomp->ops)
-		acomp->ops->put_power(acomp->dev);
-
-	component_master_del(dev, &hdac_component_master_ops);
-
-	bus->audio_component = NULL;
-	devres_destroy(dev, hdac_acomp_release, NULL, NULL);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(snd_hdac_i915_exit);
diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index bf174a013f2d..1de5491fb9bf 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -183,7 +183,7 @@ struct hdmi_spec {
 	hda_nid_t vendor_nid;
 };
 
-#ifdef CONFIG_SND_HDA_I915
+#ifdef CONFIG_SND_HDA_COMPONENT
 static inline bool codec_has_acomp(struct hda_codec *codec)
 {
 	struct hdmi_spec *spec = codec->spec;
@@ -2288,7 +2288,7 @@ static void generic_hdmi_free(struct hda_codec *codec)
 	int pin_idx, pcm_idx;
 
 	if (codec_has_acomp(codec))
-		snd_hdac_i915_register_notifier(&codec->bus->core, NULL);
+		snd_hdac_acomp_register_notifier(&codec->bus->core, NULL);
 
 	for (pin_idx = 0; pin_idx < spec->num_pins; pin_idx++) {
 		struct hdmi_spec_per_pin *per_pin = get_pin(spec, pin_idx);
@@ -2471,6 +2471,38 @@ static void haswell_set_power_state(struct hda_codec *codec, hda_nid_t fg,
 	snd_hda_codec_set_power_to_all(codec, fg, power_state);
 }
 
+/* There is a fixed mapping between audio pin node and display port.
+ * on SNB, IVY, HSW, BSW, SKL, BXT, KBL:
+ * Pin Widget 5 - PORT B (port = 1 in i915 driver)
+ * Pin Widget 6 - PORT C (port = 2 in i915 driver)
+ * Pin Widget 7 - PORT D (port = 3 in i915 driver)
+ *
+ * on VLV, ILK:
+ * Pin Widget 4 - PORT B (port = 1 in i915 driver)
+ * Pin Widget 5 - PORT C (port = 2 in i915 driver)
+ * Pin Widget 6 - PORT D (port = 3 in i915 driver)
+ */
+static int intel_base_nid(struct hda_codec *codec)
+{
+	switch (codec->core.vendor_id) {
+	case 0x80860054: /* ILK */
+	case 0x80862804: /* ILK */
+	case 0x80862882: /* VLV */
+		return 4;
+	default:
+		return 5;
+	}
+}
+
+static int intel_pin2port(void *audio_ptr, int pin_nid)
+{
+	int base_nid = intel_base_nid(audio_ptr);
+
+	if (WARN_ON(pin_nid < base_nid || pin_nid >= base_nid + 3))
+		return -1;
+	return pin_nid - base_nid + 1; /* intel port is 1-based */
+}
+
 static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe)
 {
 	struct hda_codec *codec = audio_ptr;
@@ -2481,16 +2513,7 @@ static void intel_pin_eld_notify(void *audio_ptr, int port, int pipe)
 	if (port < 1 || port > 3)
 		return;
 
-	switch (codec->core.vendor_id) {
-	case 0x80860054: /* ILK */
-	case 0x80862804: /* ILK */
-	case 0x80862882: /* VLV */
-		pin_nid = port + 0x03;
-		break;
-	default:
-		pin_nid = port + 0x04;
-		break;
-	}
+	pin_nid = port + intel_base_nid(codec) - 1; /* intel port is 1-based */
 
 	/* skip notification during system suspend (but not in runtime PM);
 	 * the state will be updated at resume
@@ -2517,8 +2540,9 @@ static void register_i915_notifier(struct hda_codec *codec)
 	 * We need make sure audio_ptr is really setup
 	 */
 	wmb();
+	spec->drm_audio_ops.pin2port = intel_pin2port;
 	spec->drm_audio_ops.pin_eld_notify = intel_pin_eld_notify;
-	snd_hdac_i915_register_notifier(&codec->bus->core,
+	snd_hdac_acomp_register_notifier(&codec->bus->core,
 					&spec->drm_audio_ops);
 }
 
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 2b7c33db4ded..4748a9d5de3b 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1530,6 +1530,11 @@ free_widgets:
 	return ret;
 }
 
+static int hdac_hdmi_pin2port(void *aptr, int pin)
+{
+	return pin - 4; /* map NID 0x05 -> port #1 */
+}
+
 static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 {
 	struct hdac_device *hdev = aptr;
@@ -1584,6 +1589,7 @@ static void hdac_hdmi_eld_notify_cb(void *aptr, int port, int pipe)
 }
 
 static struct drm_audio_component_audio_ops aops = {
+	.pin2port	= hdac_hdmi_pin2port,
 	.pin_eld_notify	= hdac_hdmi_eld_notify_cb,
 };
 
@@ -1812,7 +1818,7 @@ static int hdmi_codec_probe(struct snd_soc_component *component)
 		return ret;
 
 	aops.audio_ptr = hdev;
-	ret = snd_hdac_i915_register_notifier(hdev->bus, &aops);
+	ret = snd_hdac_acomp_register_notifier(hdev->bus, &aops);
 	if (ret < 0) {
 		dev_err(&hdev->dev, "notifier register failed: err: %d\n", ret);
 		return ret;
-- 
cgit v1.2.3


From 5bed9139727f3bad06c9444bd092336a59397e9d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 17 Jul 2018 22:32:52 +0200
Subject: ALSA: rawmidi: Tidy up coding styles

Just minor coding style fixes like removal of superfluous white space,
adding missing blank lines, etc.  No actual code changes at all.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/rawmidi.c | 101 ++++++++++++++++++++++++++++++---------------------
 1 file changed, 59 insertions(+), 42 deletions(-)

diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index b53026a72e73..14dec13ecde9 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -88,6 +88,7 @@ static inline unsigned short snd_rawmidi_file_flags(struct file *file)
 static inline int snd_rawmidi_ready(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
+
 	return runtime->avail >= runtime->avail_min;
 }
 
@@ -95,6 +96,7 @@ static inline int snd_rawmidi_ready_append(struct snd_rawmidi_substream *substre
 					   size_t count)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
+
 	return runtime->avail >= runtime->avail_min &&
 	       (!substream->append || runtime->avail >= count);
 }
@@ -103,6 +105,7 @@ static void snd_rawmidi_input_event_work(struct work_struct *work)
 {
 	struct snd_rawmidi_runtime *runtime =
 		container_of(work, struct snd_rawmidi_runtime, event_work);
+
 	if (runtime->event)
 		runtime->event(runtime->substream);
 }
@@ -111,7 +114,8 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime;
 
-	if ((runtime = kzalloc(sizeof(*runtime), GFP_KERNEL)) == NULL)
+	runtime = kzalloc(sizeof(*runtime), GFP_KERNEL);
+	if (!runtime)
 		return -ENOMEM;
 	runtime->substream = substream;
 	spin_lock_init(&runtime->lock);
@@ -124,7 +128,8 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream)
 		runtime->avail = 0;
 	else
 		runtime->avail = runtime->buffer_size;
-	if ((runtime->buffer = kmalloc(runtime->buffer_size, GFP_KERNEL)) == NULL) {
+	runtime->buffer = kmalloc(runtime->buffer_size, GFP_KERNEL);
+	if (!runtime->buffer) {
 		kfree(runtime);
 		return -ENOMEM;
 	}
@@ -143,7 +148,7 @@ static int snd_rawmidi_runtime_free(struct snd_rawmidi_substream *substream)
 	return 0;
 }
 
-static inline void snd_rawmidi_output_trigger(struct snd_rawmidi_substream *substream,int up)
+static inline void snd_rawmidi_output_trigger(struct snd_rawmidi_substream *substream, int up)
 {
 	if (!substream->opened)
 		return;
@@ -330,7 +335,7 @@ static int rawmidi_open_priv(struct snd_rawmidi *rmidi, int subdevice, int mode,
 
 /* called from sound/core/seq/seq_midi.c */
 int snd_rawmidi_kernel_open(struct snd_card *card, int device, int subdevice,
-			    int mode, struct snd_rawmidi_file * rfile)
+			    int mode, struct snd_rawmidi_file *rfile)
 {
 	struct snd_rawmidi *rmidi;
 	int err;
@@ -370,7 +375,7 @@ static int snd_rawmidi_open(struct inode *inode, struct file *file)
 	struct snd_rawmidi_file *rawmidi_file = NULL;
 	wait_queue_entry_t wait;
 
-	if ((file->f_flags & O_APPEND) && !(file->f_flags & O_NONBLOCK)) 
+	if ((file->f_flags & O_APPEND) && !(file->f_flags & O_NONBLOCK))
 		return -EINVAL;		/* invalid combination */
 
 	err = nonseekable_open(inode, file);
@@ -520,7 +525,7 @@ int snd_rawmidi_kernel_release(struct snd_rawmidi_file *rfile)
 
 	if (snd_BUG_ON(!rfile))
 		return -ENXIO;
-	
+
 	rmidi = rfile->rmidi;
 	rawmidi_release_priv(rfile);
 	module_put(rmidi->card->module);
@@ -548,7 +553,7 @@ static int snd_rawmidi_info(struct snd_rawmidi_substream *substream,
 			    struct snd_rawmidi_info *info)
 {
 	struct snd_rawmidi *rmidi;
-	
+
 	if (substream == NULL)
 		return -ENODEV;
 	rmidi = substream->rmidi;
@@ -568,11 +573,13 @@ static int snd_rawmidi_info(struct snd_rawmidi_substream *substream,
 }
 
 static int snd_rawmidi_info_user(struct snd_rawmidi_substream *substream,
-				 struct snd_rawmidi_info __user * _info)
+				 struct snd_rawmidi_info __user *_info)
 {
 	struct snd_rawmidi_info info;
 	int err;
-	if ((err = snd_rawmidi_info(substream, &info)) < 0)
+
+	err = snd_rawmidi_info(substream, &info);
+	if (err < 0)
 		return err;
 	if (copy_to_user(_info, &info, sizeof(struct snd_rawmidi_info)))
 		return -EFAULT;
@@ -619,13 +626,15 @@ static int snd_rawmidi_info_select_user(struct snd_card *card,
 {
 	int err;
 	struct snd_rawmidi_info info;
+
 	if (get_user(info.device, &_info->device))
 		return -EFAULT;
 	if (get_user(info.stream, &_info->stream))
 		return -EFAULT;
 	if (get_user(info.subdevice, &_info->subdevice))
 		return -EFAULT;
-	if ((err = snd_rawmidi_info_select(card, &info)) < 0)
+	err = snd_rawmidi_info_select(card, &info);
+	if (err < 0)
 		return err;
 	if (copy_to_user(_info, &info, sizeof(struct snd_rawmidi_info)))
 		return -EFAULT;
@@ -633,20 +642,18 @@ static int snd_rawmidi_info_select_user(struct snd_card *card,
 }
 
 int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
-			      struct snd_rawmidi_params * params)
+			      struct snd_rawmidi_params *params)
 {
 	char *newbuf, *oldbuf;
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
-	
+
 	if (substream->append && substream->use_count > 1)
 		return -EBUSY;
 	snd_rawmidi_drain_output(substream);
-	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L) {
+	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L)
 		return -EINVAL;
-	}
-	if (params->avail_min < 1 || params->avail_min > params->buffer_size) {
+	if (params->avail_min < 1 || params->avail_min > params->buffer_size)
 		return -EINVAL;
-	}
 	if (params->buffer_size != runtime->buffer_size) {
 		newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
 		if (!newbuf)
@@ -667,18 +674,16 @@ int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
 EXPORT_SYMBOL(snd_rawmidi_output_params);
 
 int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream,
-			     struct snd_rawmidi_params * params)
+			     struct snd_rawmidi_params *params)
 {
 	char *newbuf, *oldbuf;
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
 	snd_rawmidi_drain_input(substream);
-	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L) {
+	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L)
 		return -EINVAL;
-	}
-	if (params->avail_min < 1 || params->avail_min > params->buffer_size) {
+	if (params->avail_min < 1 || params->avail_min > params->buffer_size)
 		return -EINVAL;
-	}
 	if (params->buffer_size != runtime->buffer_size) {
 		newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
 		if (!newbuf)
@@ -697,7 +702,7 @@ int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream,
 EXPORT_SYMBOL(snd_rawmidi_input_params);
 
 static int snd_rawmidi_output_status(struct snd_rawmidi_substream *substream,
-				     struct snd_rawmidi_status * status)
+				     struct snd_rawmidi_status *status)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
@@ -710,7 +715,7 @@ static int snd_rawmidi_output_status(struct snd_rawmidi_substream *substream,
 }
 
 static int snd_rawmidi_input_status(struct snd_rawmidi_substream *substream,
-				    struct snd_rawmidi_status * status)
+				    struct snd_rawmidi_status *status)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
@@ -739,6 +744,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	{
 		int stream;
 		struct snd_rawmidi_info __user *info = argp;
+
 		if (get_user(stream, &info->stream))
 			return -EFAULT;
 		switch (stream) {
@@ -753,6 +759,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	case SNDRV_RAWMIDI_IOCTL_PARAMS:
 	{
 		struct snd_rawmidi_params params;
+
 		if (copy_from_user(&params, argp, sizeof(struct snd_rawmidi_params)))
 			return -EFAULT;
 		switch (params.stream) {
@@ -772,6 +779,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	{
 		int err = 0;
 		struct snd_rawmidi_status status;
+
 		if (copy_from_user(&status, argp, sizeof(struct snd_rawmidi_status)))
 			return -EFAULT;
 		switch (status.stream) {
@@ -797,6 +805,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	case SNDRV_RAWMIDI_IOCTL_DROP:
 	{
 		int val;
+
 		if (get_user(val, (int __user *) argp))
 			return -EFAULT;
 		switch (val) {
@@ -811,6 +820,7 @@ static long snd_rawmidi_ioctl(struct file *file, unsigned int cmd, unsigned long
 	case SNDRV_RAWMIDI_IOCTL_DRAIN:
 	{
 		int val;
+
 		if (get_user(val, (int __user *) argp))
 			return -EFAULT;
 		switch (val) {
@@ -844,7 +854,7 @@ static int snd_rawmidi_control_ioctl(struct snd_card *card,
 	case SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE:
 	{
 		int device;
-		
+
 		if (get_user(device, (int __user *)argp))
 			return -EFAULT;
 		if (device >= SNDRV_RAWMIDI_DEVICES) /* next device is -1 */
@@ -866,7 +876,7 @@ static int snd_rawmidi_control_ioctl(struct snd_card *card,
 	case SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE:
 	{
 		int val;
-		
+
 		if (get_user(val, (int __user *)argp))
 			return -EFAULT;
 		control->preferred_subdevice[SND_CTL_SUBDEV_RAWMIDI] = val;
@@ -1020,6 +1030,7 @@ static ssize_t snd_rawmidi_read(struct file *file, char __user *buf, size_t coun
 		spin_lock_irq(&runtime->lock);
 		while (!snd_rawmidi_ready(substream)) {
 			wait_queue_entry_t wait;
+
 			if ((file->f_flags & O_NONBLOCK) != 0 || result > 0) {
 				spin_unlock_irq(&runtime->lock);
 				return result > 0 ? result : -EAGAIN;
@@ -1072,7 +1083,7 @@ int snd_rawmidi_transmit_empty(struct snd_rawmidi_substream *substream)
 	spin_lock_irqsave(&runtime->lock, flags);
 	result = runtime->avail >= runtime->buffer_size;
 	spin_unlock_irqrestore(&runtime->lock, flags);
-	return result;		
+	return result;
 }
 EXPORT_SYMBOL(snd_rawmidi_transmit_empty);
 
@@ -1210,7 +1221,7 @@ EXPORT_SYMBOL(snd_rawmidi_transmit_ack);
  * @substream: the rawmidi substream
  * @buffer: the buffer pointer
  * @count: the data size to transfer
- * 
+ *
  * Copies data from the buffer to the device and advances the pointer.
  *
  * Return: The copied size if successful, or a negative error code on failure.
@@ -1324,6 +1335,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf,
 		spin_lock_irq(&runtime->lock);
 		while (!snd_rawmidi_ready_append(substream, count)) {
 			wait_queue_entry_t wait;
+
 			if (file->f_flags & O_NONBLOCK) {
 				spin_unlock_irq(&runtime->lock);
 				return result > 0 ? result : -EAGAIN;
@@ -1357,6 +1369,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf,
 		while (runtime->avail != runtime->buffer_size) {
 			wait_queue_entry_t wait;
 			unsigned int last_avail = runtime->avail;
+
 			init_waitqueue_entry(&wait, current);
 			add_wait_queue(&runtime->sleep, &wait);
 			set_current_state(TASK_INTERRUPTIBLE);
@@ -1374,7 +1387,7 @@ static ssize_t snd_rawmidi_write(struct file *file, const char __user *buf,
 	return result;
 }
 
-static __poll_t snd_rawmidi_poll(struct file *file, poll_table * wait)
+static __poll_t snd_rawmidi_poll(struct file *file, poll_table *wait)
 {
 	struct snd_rawmidi_file *rfile;
 	struct snd_rawmidi_runtime *runtime;
@@ -1411,7 +1424,6 @@ static __poll_t snd_rawmidi_poll(struct file *file, poll_table * wait)
 #endif
 
 /*
-
  */
 
 static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry,
@@ -1479,8 +1491,7 @@ static void snd_rawmidi_proc_info_read(struct snd_info_entry *entry,
  *  Register functions
  */
 
-static const struct file_operations snd_rawmidi_f_ops =
-{
+static const struct file_operations snd_rawmidi_f_ops = {
 	.owner =	THIS_MODULE,
 	.read =		snd_rawmidi_read,
 	.write =	snd_rawmidi_write,
@@ -1535,7 +1546,7 @@ static void release_rawmidi_device(struct device *dev)
  */
 int snd_rawmidi_new(struct snd_card *card, char *id, int device,
 		    int output_count, int input_count,
-		    struct snd_rawmidi ** rrawmidi)
+		    struct snd_rawmidi **rrawmidi)
 {
 	struct snd_rawmidi *rmidi;
 	int err;
@@ -1566,21 +1577,24 @@ int snd_rawmidi_new(struct snd_card *card, char *id, int device,
 	rmidi->dev.release = release_rawmidi_device;
 	dev_set_name(&rmidi->dev, "midiC%iD%i", card->number, device);
 
-	if ((err = snd_rawmidi_alloc_substreams(rmidi,
-						&rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT],
-						SNDRV_RAWMIDI_STREAM_INPUT,
-						input_count)) < 0) {
+	err = snd_rawmidi_alloc_substreams(rmidi,
+					   &rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT],
+					   SNDRV_RAWMIDI_STREAM_INPUT,
+					   input_count);
+	if (err < 0) {
 		snd_rawmidi_free(rmidi);
 		return err;
 	}
-	if ((err = snd_rawmidi_alloc_substreams(rmidi,
-						&rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT],
-						SNDRV_RAWMIDI_STREAM_OUTPUT,
-						output_count)) < 0) {
+	err = snd_rawmidi_alloc_substreams(rmidi,
+					   &rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT],
+					   SNDRV_RAWMIDI_STREAM_OUTPUT,
+					   output_count);
+	if (err < 0) {
 		snd_rawmidi_free(rmidi);
 		return err;
 	}
-	if ((err = snd_device_new(card, SNDRV_DEV_RAWMIDI, rmidi, &ops)) < 0) {
+	err = snd_device_new(card, SNDRV_DEV_RAWMIDI, rmidi, &ops);
+	if (err < 0) {
 		snd_rawmidi_free(rmidi);
 		return err;
 	}
@@ -1624,6 +1638,7 @@ static int snd_rawmidi_free(struct snd_rawmidi *rmidi)
 static int snd_rawmidi_dev_free(struct snd_device *device)
 {
 	struct snd_rawmidi *rmidi = device->device_data;
+
 	return snd_rawmidi_free(rmidi);
 }
 
@@ -1631,6 +1646,7 @@ static int snd_rawmidi_dev_free(struct snd_device *device)
 static void snd_rawmidi_dev_seq_free(struct snd_seq_device *device)
 {
 	struct snd_rawmidi *rmidi = device->private_data;
+
 	rmidi->seq_dev = NULL;
 }
 #endif
@@ -1732,6 +1748,7 @@ static int snd_rawmidi_dev_disconnect(struct snd_device *device)
 	list_del_init(&rmidi->list);
 	for (dir = 0; dir < 2; dir++) {
 		struct snd_rawmidi_substream *s;
+
 		list_for_each_entry(s, &rmidi->streams[dir].substreams, list) {
 			if (s->runtime)
 				wake_up(&s->runtime->sleep);
@@ -1769,7 +1786,7 @@ void snd_rawmidi_set_ops(struct snd_rawmidi *rmidi, int stream,
 			 const struct snd_rawmidi_ops *ops)
 {
 	struct snd_rawmidi_substream *substream;
-	
+
 	list_for_each_entry(substream, &rmidi->streams[stream].substreams, list)
 		substream->ops = ops;
 }
-- 
cgit v1.2.3


From 7fdc9b08071b6a3fc85bf90b79e13f6e973a7e5e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 17 Jul 2018 22:45:50 +0200
Subject: ALSA: rawmidi: Simplify error paths

Apply the standard idiom: rewrite the multiple unlocks in error paths
in the goto-error-and-single-unlock way.

Just a code refactoring, and no functional changes.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/rawmidi.c | 76 +++++++++++++++++++++++++++-------------------------
 1 file changed, 39 insertions(+), 37 deletions(-)

diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 14dec13ecde9..6b24c2d2dae6 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -338,22 +338,20 @@ int snd_rawmidi_kernel_open(struct snd_card *card, int device, int subdevice,
 			    int mode, struct snd_rawmidi_file *rfile)
 {
 	struct snd_rawmidi *rmidi;
-	int err;
+	int err = 0;
 
 	if (snd_BUG_ON(!rfile))
 		return -EINVAL;
 
 	mutex_lock(&register_mutex);
 	rmidi = snd_rawmidi_search(card, device);
-	if (rmidi == NULL) {
-		mutex_unlock(&register_mutex);
-		return -ENODEV;
-	}
-	if (!try_module_get(rmidi->card->module)) {
-		mutex_unlock(&register_mutex);
-		return -ENXIO;
-	}
+	if (!rmidi)
+		err = -ENODEV;
+	else if (!try_module_get(rmidi->card->module))
+		err = -ENXIO;
 	mutex_unlock(&register_mutex);
+	if (err < 0)
+		return err;
 
 	mutex_lock(&rmidi->open_mutex);
 	err = rawmidi_open_priv(rmidi, subdevice, mode, rfile);
@@ -1581,26 +1579,25 @@ int snd_rawmidi_new(struct snd_card *card, char *id, int device,
 					   &rmidi->streams[SNDRV_RAWMIDI_STREAM_INPUT],
 					   SNDRV_RAWMIDI_STREAM_INPUT,
 					   input_count);
-	if (err < 0) {
-		snd_rawmidi_free(rmidi);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 	err = snd_rawmidi_alloc_substreams(rmidi,
 					   &rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT],
 					   SNDRV_RAWMIDI_STREAM_OUTPUT,
 					   output_count);
-	if (err < 0) {
-		snd_rawmidi_free(rmidi);
-		return err;
-	}
+	if (err < 0)
+		goto error;
 	err = snd_device_new(card, SNDRV_DEV_RAWMIDI, rmidi, &ops);
-	if (err < 0) {
-		snd_rawmidi_free(rmidi);
-		return err;
-	}
+	if (err < 0)
+		goto error;
+
 	if (rrawmidi)
 		*rrawmidi = rmidi;
 	return 0;
+
+ error:
+	snd_rawmidi_free(rmidi);
+	return err;
 }
 EXPORT_SYMBOL(snd_rawmidi_new);
 
@@ -1660,30 +1657,27 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 
 	if (rmidi->device >= SNDRV_RAWMIDI_DEVICES)
 		return -ENOMEM;
+	err = 0;
 	mutex_lock(&register_mutex);
-	if (snd_rawmidi_search(rmidi->card, rmidi->device)) {
-		mutex_unlock(&register_mutex);
-		return -EBUSY;
-	}
-	list_add_tail(&rmidi->list, &snd_rawmidi_devices);
+	if (snd_rawmidi_search(rmidi->card, rmidi->device))
+		err = -EBUSY;
+	else
+		list_add_tail(&rmidi->list, &snd_rawmidi_devices);
 	mutex_unlock(&register_mutex);
+	if (err < 0)
+		return err;
+
 	err = snd_register_device(SNDRV_DEVICE_TYPE_RAWMIDI,
 				  rmidi->card, rmidi->device,
 				  &snd_rawmidi_f_ops, rmidi, &rmidi->dev);
 	if (err < 0) {
 		rmidi_err(rmidi, "unable to register\n");
-		mutex_lock(&register_mutex);
-		list_del(&rmidi->list);
-		mutex_unlock(&register_mutex);
-		return err;
+		goto error;
 	}
-	if (rmidi->ops && rmidi->ops->dev_register &&
-	    (err = rmidi->ops->dev_register(rmidi)) < 0) {
-		snd_unregister_device(&rmidi->dev);
-		mutex_lock(&register_mutex);
-		list_del(&rmidi->list);
-		mutex_unlock(&register_mutex);
-		return err;
+	if (rmidi->ops && rmidi->ops->dev_register) {
+		err = rmidi->ops->dev_register(rmidi);
+		if (err < 0)
+			goto error_unregister;
 	}
 #ifdef CONFIG_SND_OSSEMUL
 	rmidi->ossreg = 0;
@@ -1735,6 +1729,14 @@ static int snd_rawmidi_dev_register(struct snd_device *device)
 	}
 #endif
 	return 0;
+
+ error_unregister:
+	snd_unregister_device(&rmidi->dev);
+ error:
+	mutex_lock(&register_mutex);
+	list_del(&rmidi->list);
+	mutex_unlock(&register_mutex);
+	return err;
 }
 
 static int snd_rawmidi_dev_disconnect(struct snd_device *device)
-- 
cgit v1.2.3


From 631d2b490569118c5e4d4e35983efe36d9798cb5 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Jul 2018 10:43:56 -0700
Subject: selinux: constify write_op[]

write_op[] is never modified, so make it 'const'.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/selinuxfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index d64a06e84eec..eb7f12ab5c33 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -773,7 +773,7 @@ static ssize_t sel_write_relabel(struct file *file, char *buf, size_t size);
 static ssize_t sel_write_user(struct file *file, char *buf, size_t size);
 static ssize_t sel_write_member(struct file *file, char *buf, size_t size);
 
-static ssize_t (*write_op[])(struct file *, char *, size_t) = {
+static ssize_t (*const write_op[])(struct file *, char *, size_t) = {
 	[SEL_ACCESS] = sel_write_access,
 	[SEL_CREATE] = sel_write_create,
 	[SEL_RELABEL] = sel_write_relabel,
-- 
cgit v1.2.3


From f5beb598b0c4dd023833ae1a7c188ecd987b7125 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 17 Jul 2018 23:07:29 +0200
Subject: ALSA: rawmidi: Minor code refactoring

Unify a few open codes with helper functions to improve the
readability.  Minor behavior changes (rather fixes) are:
- runtime->drain clearance is done within lock
- active_sensing is updated before resizing buffer in
  SNDRV_RAWMIDI_IOCTL_PARAMS ioctl.
Other than that, simply code cleanups.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/rawmidi.c | 77 ++++++++++++++++++++++------------------------------
 1 file changed, 33 insertions(+), 44 deletions(-)

diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index 6b24c2d2dae6..cc944a3637a2 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -164,17 +164,28 @@ static void snd_rawmidi_input_trigger(struct snd_rawmidi_substream *substream, i
 		cancel_work_sync(&substream->runtime->event_work);
 }
 
-int snd_rawmidi_drop_output(struct snd_rawmidi_substream *substream)
+static void __reset_runtime_ptrs(struct snd_rawmidi_runtime *runtime,
+				 bool is_input)
+{
+	runtime->drain = 0;
+	runtime->appl_ptr = runtime->hw_ptr = 0;
+	runtime->avail = is_input ? 0 : runtime->buffer_size;
+}
+
+static void reset_runtime_ptrs(struct snd_rawmidi_runtime *runtime,
+			       bool is_input)
 {
 	unsigned long flags;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
-	snd_rawmidi_output_trigger(substream, 0);
-	runtime->drain = 0;
 	spin_lock_irqsave(&runtime->lock, flags);
-	runtime->appl_ptr = runtime->hw_ptr = 0;
-	runtime->avail = runtime->buffer_size;
+	__reset_runtime_ptrs(runtime, is_input);
 	spin_unlock_irqrestore(&runtime->lock, flags);
+}
+
+int snd_rawmidi_drop_output(struct snd_rawmidi_substream *substream)
+{
+	snd_rawmidi_output_trigger(substream, 0);
+	reset_runtime_ptrs(substream->runtime, false);
 	return 0;
 }
 EXPORT_SYMBOL(snd_rawmidi_drop_output);
@@ -213,15 +224,8 @@ EXPORT_SYMBOL(snd_rawmidi_drain_output);
 
 int snd_rawmidi_drain_input(struct snd_rawmidi_substream *substream)
 {
-	unsigned long flags;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
-
 	snd_rawmidi_input_trigger(substream, 0);
-	runtime->drain = 0;
-	spin_lock_irqsave(&runtime->lock, flags);
-	runtime->appl_ptr = runtime->hw_ptr = 0;
-	runtime->avail = 0;
-	spin_unlock_irqrestore(&runtime->lock, flags);
+	reset_runtime_ptrs(substream->runtime, true);
 	return 0;
 }
 EXPORT_SYMBOL(snd_rawmidi_drain_input);
@@ -639,15 +643,12 @@ static int snd_rawmidi_info_select_user(struct snd_card *card,
 	return 0;
 }
 
-int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
-			      struct snd_rawmidi_params *params)
+static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime,
+				 struct snd_rawmidi_params *params,
+				 bool is_input)
 {
 	char *newbuf, *oldbuf;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
-	if (substream->append && substream->use_count > 1)
-		return -EBUSY;
-	snd_rawmidi_drain_output(substream);
 	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L)
 		return -EINVAL;
 	if (params->avail_min < 1 || params->avail_min > params->buffer_size)
@@ -660,42 +661,30 @@ int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
 		oldbuf = runtime->buffer;
 		runtime->buffer = newbuf;
 		runtime->buffer_size = params->buffer_size;
-		runtime->avail = runtime->buffer_size;
-		runtime->appl_ptr = runtime->hw_ptr = 0;
+		__reset_runtime_ptrs(runtime, is_input);
 		spin_unlock_irq(&runtime->lock);
 		kfree(oldbuf);
 	}
 	runtime->avail_min = params->avail_min;
-	substream->active_sensing = !params->no_active_sensing;
 	return 0;
 }
+
+int snd_rawmidi_output_params(struct snd_rawmidi_substream *substream,
+			      struct snd_rawmidi_params *params)
+{
+	if (substream->append && substream->use_count > 1)
+		return -EBUSY;
+	snd_rawmidi_drain_output(substream);
+	substream->active_sensing = !params->no_active_sensing;
+	return resize_runtime_buffer(substream->runtime, params, false);
+}
 EXPORT_SYMBOL(snd_rawmidi_output_params);
 
 int snd_rawmidi_input_params(struct snd_rawmidi_substream *substream,
 			     struct snd_rawmidi_params *params)
 {
-	char *newbuf, *oldbuf;
-	struct snd_rawmidi_runtime *runtime = substream->runtime;
-
 	snd_rawmidi_drain_input(substream);
-	if (params->buffer_size < 32 || params->buffer_size > 1024L * 1024L)
-		return -EINVAL;
-	if (params->avail_min < 1 || params->avail_min > params->buffer_size)
-		return -EINVAL;
-	if (params->buffer_size != runtime->buffer_size) {
-		newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
-		if (!newbuf)
-			return -ENOMEM;
-		spin_lock_irq(&runtime->lock);
-		oldbuf = runtime->buffer;
-		runtime->buffer = newbuf;
-		runtime->buffer_size = params->buffer_size;
-		runtime->appl_ptr = runtime->hw_ptr = 0;
-		spin_unlock_irq(&runtime->lock);
-		kfree(oldbuf);
-	}
-	runtime->avail_min = params->avail_min;
-	return 0;
+	return resize_runtime_buffer(substream->runtime, params, true);
 }
 EXPORT_SYMBOL(snd_rawmidi_input_params);
 
-- 
cgit v1.2.3


From fa248de98a6beb9ceaec5059041d65f87ac438b4 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 17 Jul 2018 14:24:11 -0700
Subject: xfs: don't assume a left rmap when allocating a new rmap

The original rmap code assumed that there would always be at least one
rmap in the rmapbt (the AG sb/agf/agi) and so errored out if it didn't
find one.  This assumption isn't true for the rmapbt repair function
(and it won't be true for realtime rmap either), so remove the check and
just deal with the situation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
---
 fs/xfs/libxfs/xfs_rmap.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index d4460b0d2d81..8b2a2f81d110 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -753,19 +753,19 @@ xfs_rmap_map(
 			&have_lt);
 	if (error)
 		goto out_error;
-	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
-
-	error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
-	if (error)
-		goto out_error;
-	XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
-	trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
-			cur->bc_private.a.agno, ltrec.rm_startblock,
-			ltrec.rm_blockcount, ltrec.rm_owner,
-			ltrec.rm_offset, ltrec.rm_flags);
+	if (have_lt) {
+		error = xfs_rmap_get_rec(cur, &ltrec, &have_lt);
+		if (error)
+			goto out_error;
+		XFS_WANT_CORRUPTED_GOTO(mp, have_lt == 1, out_error);
+		trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
+				cur->bc_private.a.agno, ltrec.rm_startblock,
+				ltrec.rm_blockcount, ltrec.rm_owner,
+				ltrec.rm_offset, ltrec.rm_flags);
 
-	if (!xfs_rmap_is_mergeable(&ltrec, owner, flags))
-		have_lt = 0;
+		if (!xfs_rmap_is_mergeable(&ltrec, owner, flags))
+			have_lt = 0;
+	}
 
 	XFS_WANT_CORRUPTED_GOTO(mp,
 		have_lt == 0 ||
-- 
cgit v1.2.3


From 1d5bebbafc73d82e5af003cdd2bf8ee5741cd1df Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 11 Jul 2018 22:26:38 -0700
Subject: xfs_attr_leaf: use swap macro in xfs_attr3_leaf_rebalance

Make use of the swap macro and remove some unnecessary variables.
This makes the code easier to read and maintain. Also, reduces the
stack usage.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 251304f3bc5d..8ff287979a8c 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -1566,17 +1566,10 @@ xfs_attr3_leaf_rebalance(
 	 */
 	swap = 0;
 	if (xfs_attr3_leaf_order(blk1->bp, &ichdr1, blk2->bp, &ichdr2)) {
-		struct xfs_da_state_blk	*tmp_blk;
-		struct xfs_attr3_icleaf_hdr tmp_ichdr;
+		swap(blk1, blk2);
 
-		tmp_blk = blk1;
-		blk1 = blk2;
-		blk2 = tmp_blk;
-
-		/* struct copies to swap them rather than reconverting */
-		tmp_ichdr = ichdr1;
-		ichdr1 = ichdr2;
-		ichdr2 = tmp_ichdr;
+		/* swap structures rather than reconverting them */
+		swap(ichdr1, ichdr2);
 
 		leaf1 = blk1->bp->b_addr;
 		leaf2 = blk2->bp->b_addr;
-- 
cgit v1.2.3


From 897992b7e3505659fda57887223bd6bfe163c12f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 11 Jul 2018 22:26:38 -0700
Subject: xfs_bmap_util: use swap macro

Make use of the swap macro and remove some unnecessary variables.
This makes the code easier to read and maintain. Also, reduces the
stack usage.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_util.c | 28 +++++-----------------------
 1 file changed, 5 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d3a314fd721f..1b78c20de7bd 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1688,7 +1688,6 @@ xfs_swap_extent_forks(
 	int			*src_log_flags,
 	int			*target_log_flags)
 {
-	struct xfs_ifork	tempifp, *ifp, *tifp;
 	xfs_filblks_t		aforkblks = 0;
 	xfs_filblks_t		taforkblks = 0;
 	xfs_extnum_t		junk;
@@ -1730,11 +1729,7 @@ xfs_swap_extent_forks(
 	/*
 	 * Swap the data forks of the inodes
 	 */
-	ifp = &ip->i_df;
-	tifp = &tip->i_df;
-	tempifp = *ifp;		/* struct copy */
-	*ifp = *tifp;		/* struct copy */
-	*tifp = tempifp;	/* struct copy */
+	swap(ip->i_df, tip->i_df);
 
 	/*
 	 * Fix the on-disk inode values
@@ -1743,13 +1738,8 @@ xfs_swap_extent_forks(
 	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
 	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
 
-	tmp = (uint64_t) ip->i_d.di_nextents;
-	ip->i_d.di_nextents = tip->i_d.di_nextents;
-	tip->i_d.di_nextents = tmp;
-
-	tmp = (uint64_t) ip->i_d.di_format;
-	ip->i_d.di_format = tip->i_d.di_format;
-	tip->i_d.di_format = tmp;
+	swap(ip->i_d.di_nextents, tip->i_d.di_nextents);
+	swap(ip->i_d.di_format, tip->i_d.di_format);
 
 	/*
 	 * The extents in the source inode could still contain speculative
@@ -1844,7 +1834,6 @@ xfs_swap_extents(
 	int			src_log_flags, target_log_flags;
 	int			error = 0;
 	int			lock_flags;
-	struct xfs_ifork	*cowfp;
 	uint64_t		f;
 	int			resblks = 0;
 
@@ -1986,18 +1975,11 @@ xfs_swap_extents(
 
 	/* Swap the cow forks. */
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
-		xfs_extnum_t	extnum;
-
 		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
 		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
 
-		extnum = ip->i_cnextents;
-		ip->i_cnextents = tip->i_cnextents;
-		tip->i_cnextents = extnum;
-
-		cowfp = ip->i_cowfp;
-		ip->i_cowfp = tip->i_cowfp;
-		tip->i_cowfp = cowfp;
+		swap(ip->i_cnextents, tip->i_cnextents);
+		swap(ip->i_cowfp, tip->i_cowfp);
 
 		if (ip->i_cowfp && ip->i_cowfp->if_bytes)
 			xfs_inode_set_cowblocks_tag(ip);
-- 
cgit v1.2.3


From e4e542a683c16945533d700339a0aec261d39f34 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 17 Jul 2018 14:25:01 -0700
Subject: xfs: use swap macro in xfs_dir2_leafn_rebalance

Make use of the swap macro and remove unnecessary variable *tmp*. This
makes the code easier to read and maintain. Also, slightly refactor some
code.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_dir2_node.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 2daf874969ab..f1bb3434f51c 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -1012,7 +1012,7 @@ xfs_dir2_leafn_rebalance(
 	int			oldstale;	/* old count of stale leaves */
 #endif
 	int			oldsum;		/* old total leaf count */
-	int			swap;		/* swapped leaf blocks */
+	int			swap_blocks;	/* swapped leaf blocks */
 	struct xfs_dir2_leaf_entry *ents1;
 	struct xfs_dir2_leaf_entry *ents2;
 	struct xfs_dir3_icleaf_hdr hdr1;
@@ -1023,13 +1023,10 @@ xfs_dir2_leafn_rebalance(
 	/*
 	 * If the block order is wrong, swap the arguments.
 	 */
-	if ((swap = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp))) {
-		xfs_da_state_blk_t	*tmp;	/* temp for block swap */
+	swap_blocks = xfs_dir2_leafn_order(dp, blk1->bp, blk2->bp);
+	if (swap_blocks)
+		swap(blk1, blk2);
 
-		tmp = blk1;
-		blk1 = blk2;
-		blk2 = tmp;
-	}
 	leaf1 = blk1->bp->b_addr;
 	leaf2 = blk2->bp->b_addr;
 	dp->d_ops->leaf_hdr_from_disk(&hdr1, leaf1);
@@ -1093,11 +1090,11 @@ xfs_dir2_leafn_rebalance(
 	 * Mark whether we're inserting into the old or new leaf.
 	 */
 	if (hdr1.count < hdr2.count)
-		state->inleaf = swap;
+		state->inleaf = swap_blocks;
 	else if (hdr1.count > hdr2.count)
-		state->inleaf = !swap;
+		state->inleaf = !swap_blocks;
 	else
-		state->inleaf = swap ^ (blk1->index <= hdr1.count);
+		state->inleaf = swap_blocks ^ (blk1->index <= hdr1.count);
 	/*
 	 * Adjust the expected index for insertion.
 	 */
-- 
cgit v1.2.3


From 5089eafffba2ed444789e5d25c7c0dfd62595713 Mon Sep 17 00:00:00 2001
From: Carlos Maiolino <cmaiolino@redhat.com>
Date: Tue, 17 Jul 2018 14:25:20 -0700
Subject: libxfs: Fix a couple of sparse complaintis

No significant changes, just silence a couple of sparse errors.

Using cpu_to_be32(NULLAGINO), the NULLAGINO constant will be encoded in
BE as a constant, avoiding a BE -> CPU conversion every iteraction of
the loop, if be32_to_cpu(agi->agi_unlinked[i]) was used instead.

Signed-off-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_ag_resv.h | 2 +-
 fs/xfs/libxfs/xfs_ialloc.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag_resv.h b/fs/xfs/libxfs/xfs_ag_resv.h
index 4619b554ee90..dc953fc84b2f 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.h
+++ b/fs/xfs/libxfs/xfs_ag_resv.h
@@ -28,7 +28,7 @@ xfs_ag_resv_rmapbt_alloc(
 	struct xfs_mount	*mp,
 	xfs_agnumber_t		agno)
 {
-	struct xfs_alloc_arg	args = {0};
+	struct xfs_alloc_arg	args = { NULL };
 	struct xfs_perag	*pag;
 
 	args.len = 1;
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index c38d14106b53..811d36afd024 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2537,7 +2537,7 @@ xfs_agi_verify(
 		return __this_address;
 
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
-		if (agi->agi_unlinked[i] == NULLAGINO)
+		if (agi->agi_unlinked[i] == cpu_to_be32(NULLAGINO))
 			continue;
 		if (!xfs_verify_ino(mp, be32_to_cpu(agi->agi_unlinked[i])))
 			return __this_address;
-- 
cgit v1.2.3


From 6ce3dd6eec114930cf2035a8bcb1e80477ed79a8 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 10 Jul 2018 09:03:31 +0800
Subject: blk-mq: issue directly if hw queue isn't busy in case of 'none'

In case of 'none' io scheduler, when hw queue isn't busy, it isn't
necessary to enqueue request to sw queue and dequeue it from
sw queue because request may be submitted to hw queue asap without
extra cost, meantime there shouldn't be much request in sw queue,
and we don't need to worry about effect on IO merge.

There are still some single hw queue SCSI HBAs(HPSA, megaraid_sas, ...)
which may connect high performance devices, so 'none' is often required
for obtaining good performance.

This patch improves IOPS and decreases CPU unilization on megaraid_sas,
per Kashyap's test.

Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Reported-by: Kashyap Desai <kashyap.desai@broadcom.com>
Tested-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-sched.c | 13 ++++++++++++-
 block/blk-mq.c       | 23 ++++++++++++++++++++++-
 block/blk-mq.h       |  2 ++
 3 files changed, 36 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
index fdc129e64cc4..cf9c66c6d35a 100644
--- a/block/blk-mq-sched.c
+++ b/block/blk-mq-sched.c
@@ -405,8 +405,19 @@ void blk_mq_sched_insert_requests(struct request_queue *q,
 
 	if (e && e->type->ops.mq.insert_requests)
 		e->type->ops.mq.insert_requests(hctx, list, false);
-	else
+	else {
+		/*
+		 * try to issue requests directly if the hw queue isn't
+		 * busy in case of 'none' scheduler, and this way may save
+		 * us one extra enqueue & dequeue to sw queue.
+		 */
+		if (!hctx->dispatch_busy && !e && !run_queue_async) {
+			blk_mq_try_issue_list_directly(hctx, list);
+			if (list_empty(list))
+				return;
+		}
 		blk_mq_insert_requests(hctx, ctx, list);
+	}
 
 	blk_mq_run_hw_queue(hctx, run_queue_async);
 }
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 73a43b81b17d..21f3eda98431 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1691,13 +1691,16 @@ static blk_status_t __blk_mq_issue_directly(struct blk_mq_hw_ctx *hctx,
 	ret = q->mq_ops->queue_rq(hctx, &bd);
 	switch (ret) {
 	case BLK_STS_OK:
+		blk_mq_update_dispatch_busy(hctx, false);
 		*cookie = new_cookie;
 		break;
 	case BLK_STS_RESOURCE:
 	case BLK_STS_DEV_RESOURCE:
+		blk_mq_update_dispatch_busy(hctx, true);
 		__blk_mq_requeue_request(rq);
 		break;
 	default:
+		blk_mq_update_dispatch_busy(hctx, false);
 		*cookie = BLK_QC_T_NONE;
 		break;
 	}
@@ -1780,6 +1783,23 @@ blk_status_t blk_mq_request_issue_directly(struct request *rq)
 	return ret;
 }
 
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+		struct list_head *list)
+{
+	while (!list_empty(list)) {
+		blk_status_t ret;
+		struct request *rq = list_first_entry(list, struct request,
+				queuelist);
+
+		list_del_init(&rq->queuelist);
+		ret = blk_mq_request_issue_directly(rq);
+		if (ret != BLK_STS_OK) {
+			list_add(&rq->queuelist, list);
+			break;
+		}
+	}
+}
+
 static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int is_sync = op_is_sync(bio->bi_opf);
@@ -1880,7 +1900,8 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio)
 			blk_mq_try_issue_directly(data.hctx, same_queue_rq,
 					&cookie);
 		}
-	} else if (q->nr_hw_queues > 1 && is_sync) {
+	} else if ((q->nr_hw_queues > 1 && is_sync) || (!q->elevator &&
+			!data.hctx->dispatch_busy)) {
 		blk_mq_put_ctx(data.ctx);
 		blk_mq_bio_to_request(rq, bio);
 		blk_mq_try_issue_directly(data.hctx, rq, &cookie);
diff --git a/block/blk-mq.h b/block/blk-mq.h
index bc2b24735ed4..9497b47e2526 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -64,6 +64,8 @@ void blk_mq_insert_requests(struct blk_mq_hw_ctx *hctx, struct blk_mq_ctx *ctx,
 
 /* Used by blk_insert_cloned_request() to issue request directly */
 blk_status_t blk_mq_request_issue_directly(struct request *rq);
+void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
+				    struct list_head *list);
 
 /*
  * CPU -> queue mappings
-- 
cgit v1.2.3


From ada94973f15f175283fd3b8f9bfcf9de6f2cc818 Mon Sep 17 00:00:00 2001
From: RAGHU Halharvi <raghuhack78@gmail.com>
Date: Tue, 17 Jul 2018 22:32:12 +0530
Subject: pktcdvd: remove assignment in if condition

* Remove checkpatch errors caused due to assignment operation in if
condition

Signed-off-by: RAGHU Halharvi <raghuhack78@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/pktcdvd.c | 69 ++++++++++++++++++++++++++++++++-----------------
 1 file changed, 46 insertions(+), 23 deletions(-)

diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index b3f83cd96f33..a4b4d524c3af 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -798,7 +798,8 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
 	cgc.cmd[4] = (write_speed >> 8) & 0xff;
 	cgc.cmd[5] = write_speed & 0xff;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 
 	return ret;
@@ -1562,7 +1563,8 @@ static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
 	cgc.cmd[8] = cgc.buflen = 2;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	/* not all drives have the same disc_info length, so requeue
@@ -1591,7 +1593,8 @@ static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type,
 	cgc.cmd[8] = 8;
 	cgc.quiet = 1;
 
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		return ret;
 
 	cgc.buflen = be16_to_cpu(ti->track_information_length) +
@@ -1612,17 +1615,20 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 	__u32 last_track;
 	int ret = -1;
 
-	if ((ret = pkt_get_disc_info(pd, &di)))
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret)
 		return ret;
 
 	last_track = (di.last_track_msb << 8) | di.last_track_lsb;
-	if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+	ret = pkt_get_track_info(pd, last_track, 1, &ti);
+	if (ret)
 		return ret;
 
 	/* if this track is blank, try the previous. */
 	if (ti.blank) {
 		last_track--;
-		if ((ret = pkt_get_track_info(pd, last_track, 1, &ti)))
+		ret = pkt_get_track_info(pd, last_track, 1, &ti);
+		if (ret)
 			return ret;
 	}
 
@@ -1657,7 +1663,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	memset(buffer, 0, sizeof(buffer));
 	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
 	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1672,7 +1679,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	 */
 	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
 	cgc.sense = &sense;
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0))) {
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1714,7 +1722,8 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
 
 	cgc.buflen = cgc.cmd[8] = size;
-	if ((ret = pkt_mode_select(pd, &cgc))) {
+	ret = pkt_mode_select(pd, &cgc);
+	if (ret) {
 		pkt_dump_sense(pd, &cgc);
 		return ret;
 	}
@@ -1819,7 +1828,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	memset(&di, 0, sizeof(disc_information));
 	memset(&ti, 0, sizeof(track_information));
 
-	if ((ret = pkt_get_disc_info(pd, &di))) {
+	ret = pkt_get_disc_info(pd, &di);
+	if (ret) {
 		pkt_err(pd, "failed get_disc\n");
 		return ret;
 	}
@@ -1830,7 +1840,8 @@ static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
 	pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
 
 	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
-	if ((ret = pkt_get_track_info(pd, track, 1, &ti))) {
+	ret = pkt_get_track_info(pd, track, 1, &ti);
+	if (ret) {
 		pkt_err(pd, "failed get_track\n");
 		return ret;
 	}
@@ -1918,7 +1929,8 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 	 */
 	cgc.quiet = 1;
 
-	if ((ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0)))
+	ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
+	if (ret)
 		return ret;
 
 	buf[pd->mode_offset + 10] |= (!!set << 2);
@@ -2093,7 +2105,8 @@ static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
 	cgc.timeout = 60*HZ;
 	cgc.cmd[0] = GPCMD_SEND_OPC;
 	cgc.cmd[1] = 1;
-	if ((ret = pkt_generic_packet(pd, &cgc)))
+	ret = pkt_generic_packet(pd, &cgc);
+	if (ret)
 		pkt_dump_sense(pd, &cgc);
 	return ret;
 }
@@ -2103,19 +2116,22 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	int ret;
 	unsigned int write_speed, media_write_speed, read_speed;
 
-	if ((ret = pkt_probe_settings(pd))) {
+	ret = pkt_probe_settings(pd);
+	if (ret) {
 		pkt_dbg(2, pd, "failed probe\n");
 		return ret;
 	}
 
-	if ((ret = pkt_set_write_settings(pd))) {
+	ret = pkt_set_write_settings(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "failed saving write settings\n");
 		return -EIO;
 	}
 
 	pkt_write_caching(pd, USE_WCACHING);
 
-	if ((ret = pkt_get_max_speed(pd, &write_speed)))
+	ret = pkt_get_max_speed(pd, &write_speed);
+	if (ret)
 		write_speed = 16 * 177;
 	switch (pd->mmc3_profile) {
 		case 0x13: /* DVD-RW */
@@ -2124,7 +2140,8 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 			pkt_dbg(1, pd, "write speed %ukB/s\n", write_speed);
 			break;
 		default:
-			if ((ret = pkt_media_speed(pd, &media_write_speed)))
+			ret = pkt_media_speed(pd, &media_write_speed);
+			if (ret)
 				media_write_speed = 16;
 			write_speed = min(write_speed, media_write_speed * 177);
 			pkt_dbg(1, pd, "write speed %ux\n", write_speed / 176);
@@ -2132,14 +2149,16 @@ static int pkt_open_write(struct pktcdvd_device *pd)
 	}
 	read_speed = write_speed;
 
-	if ((ret = pkt_set_speed(pd, write_speed, read_speed))) {
+	ret = pkt_set_speed(pd, write_speed, read_speed);
+	if (ret) {
 		pkt_dbg(1, pd, "couldn't set write speed\n");
 		return -EIO;
 	}
 	pd->write_speed = write_speed;
 	pd->read_speed = read_speed;
 
-	if ((ret = pkt_perform_opc(pd))) {
+	ret = pkt_perform_opc(pd);
+	if (ret) {
 		pkt_dbg(1, pd, "Optimum Power Calibration failed\n");
 	}
 
@@ -2161,10 +2180,12 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 	 * so bdget() can't fail.
 	 */
 	bdget(pd->bdev->bd_dev);
-	if ((ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd)))
+	ret = blkdev_get(pd->bdev, FMODE_READ | FMODE_EXCL, pd);
+	if (ret)
 		goto out;
 
-	if ((ret = pkt_get_last_written(pd, &lba))) {
+	ret = pkt_get_last_written(pd, &lba);
+	if (ret) {
 		pkt_err(pd, "pkt_get_last_written failed\n");
 		goto out_putdev;
 	}
@@ -2175,7 +2196,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 
 	q = bdev_get_queue(pd->bdev);
 	if (write) {
-		if ((ret = pkt_open_write(pd)))
+		ret = pkt_open_write(pd);
+		if (ret)
 			goto out_putdev;
 		/*
 		 * Some CDRW drives can not handle writes larger than one packet,
@@ -2190,7 +2212,8 @@ static int pkt_open_dev(struct pktcdvd_device *pd, fmode_t write)
 		clear_bit(PACKET_WRITABLE, &pd->flags);
 	}
 
-	if ((ret = pkt_set_segment_merging(pd, q)))
+	ret = pkt_set_segment_merging(pd, q);
+	if (ret)
 		goto out_putdev;
 
 	if (write) {
-- 
cgit v1.2.3


From f1e911d5d0dfde489be38d9702a75964dfb42b28 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:51:26 +0200
Subject: r8169: add basic phylib support

Add basic phylib support to r8169. All now unneeded old PHY handling code
will be removed in subsequent patches.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/Kconfig |   1 +
 drivers/net/ethernet/realtek/r8169.c | 159 ++++++++++++++++++++++++++++-------
 2 files changed, 128 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 7c69f4c8134d..7fb1af1f91ce 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -99,6 +99,7 @@ config R8169
 	depends on PCI
 	select FW_LOADER
 	select CRC32
+	select PHYLIB
 	select MII
 	---help---
 	  Say Y here if you have a Realtek 8169 PCI Gigabit Ethernet adapter.
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index d598fdf0470c..96eb28a7065e 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/ethtool.h>
 #include <linux/mii.h>
+#include <linux/phy.h>
 #include <linux/if_vlan.h>
 #include <linux/crc32.h>
 #include <linux/in.h>
@@ -754,6 +755,7 @@ struct rtl8169_private {
 	} wk;
 
 	struct mii_if_info mii;
+	struct mii_bus *mii_bus;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
 	struct rtl8169_tc_offsets tc_offset;
@@ -1444,11 +1446,6 @@ static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp)
 	return rtl_readphy(tp, MII_BMCR) & BMCR_RESET;
 }
 
-static unsigned int rtl8169_xmii_link_ok(struct rtl8169_private *tp)
-{
-	return RTL_R8(tp, PHYstatus) & LinkStatus;
-}
-
 static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp)
 {
 	unsigned int val;
@@ -1513,25 +1510,6 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 	}
 }
 
-static void rtl8169_check_link_status(struct net_device *dev,
-				      struct rtl8169_private *tp)
-{
-	struct device *d = tp_to_dev(tp);
-
-	if (rtl8169_xmii_link_ok(tp)) {
-		rtl_link_chg_patch(tp);
-		/* This is to cancel a scheduled suspend if there's one. */
-		pm_request_resume(d);
-		netif_carrier_on(dev);
-		if (net_ratelimit())
-			netif_info(tp, ifup, dev, "link up\n");
-	} else {
-		netif_carrier_off(dev);
-		netif_info(tp, ifdown, dev, "link down\n");
-		pm_runtime_idle(d);
-	}
-}
-
 #define WAKE_ANY (WAKE_PHY | WAKE_MAGIC | WAKE_UCAST | WAKE_BCAST | WAKE_MCAST)
 
 static u32 __rtl8169_get_wol(struct rtl8169_private *tp)
@@ -6221,7 +6199,6 @@ static void rtl_reset_work(struct rtl8169_private *tp)
 	napi_enable(&tp->napi);
 	rtl_hw_start(tp);
 	netif_wake_queue(dev);
-	rtl8169_check_link_status(dev, tp);
 }
 
 static void rtl8169_tx_timeout(struct net_device *dev)
@@ -6838,7 +6815,7 @@ static void rtl_slow_event_work(struct rtl8169_private *tp)
 		rtl8169_pcierr_interrupt(dev);
 
 	if (status & LinkChg)
-		rtl8169_check_link_status(dev, tp);
+		phy_mac_interrupt(dev->phydev);
 
 	rtl_irq_enable_all(tp);
 }
@@ -6920,10 +6897,52 @@ static void rtl8169_rx_missed(struct net_device *dev)
 	RTL_W32(tp, RxMissed, 0);
 }
 
+static void r8169_phylink_handler(struct net_device *ndev)
+{
+	struct rtl8169_private *tp = netdev_priv(ndev);
+
+	if (netif_carrier_ok(ndev)) {
+		rtl_link_chg_patch(tp);
+		pm_request_resume(&tp->pci_dev->dev);
+	} else {
+		pm_runtime_idle(&tp->pci_dev->dev);
+	}
+
+	if (net_ratelimit())
+		phy_print_status(ndev->phydev);
+}
+
+static int r8169_phy_connect(struct rtl8169_private *tp)
+{
+	struct phy_device *phydev = mdiobus_get_phy(tp->mii_bus, 0);
+	phy_interface_t phy_mode;
+	int ret;
+
+	phy_mode = tp->mii.supports_gmii ? PHY_INTERFACE_MODE_GMII :
+		   PHY_INTERFACE_MODE_MII;
+
+	ret = phy_connect_direct(tp->dev, phydev, r8169_phylink_handler,
+				 phy_mode);
+	if (ret)
+		return ret;
+
+	if (!tp->mii.supports_gmii)
+		phy_set_max_speed(phydev, SPEED_100);
+
+	/* Ensure to advertise everything, incl. pause */
+	phydev->advertising = phydev->supported;
+
+	phy_attached_info(phydev);
+
+	return 0;
+}
+
 static void rtl8169_down(struct net_device *dev)
 {
 	struct rtl8169_private *tp = netdev_priv(dev);
 
+	phy_stop(dev->phydev);
+
 	napi_disable(&tp->napi);
 	netif_stop_queue(dev);
 
@@ -6963,6 +6982,8 @@ static int rtl8169_close(struct net_device *dev)
 
 	cancel_work_sync(&tp->wk.work);
 
+	phy_disconnect(dev->phydev);
+
 	pci_free_irq(pdev, 0, tp);
 
 	dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray,
@@ -7023,6 +7044,10 @@ static int rtl_open(struct net_device *dev)
 	if (retval < 0)
 		goto err_release_fw_2;
 
+	retval = r8169_phy_connect(tp);
+	if (retval)
+		goto err_free_irq;
+
 	rtl_lock_work(tp);
 
 	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
@@ -7038,16 +7063,17 @@ static int rtl_open(struct net_device *dev)
 	if (!rtl8169_init_counter_offsets(tp))
 		netif_warn(tp, hw, dev, "counter reset/update failed\n");
 
+	phy_start(dev->phydev);
 	netif_start_queue(dev);
 
 	rtl_unlock_work(tp);
 
 	pm_runtime_put_sync(&pdev->dev);
-
-	rtl8169_check_link_status(dev, tp);
 out:
 	return retval;
 
+err_free_irq:
+	pci_free_irq(pdev, 0, tp);
 err_release_fw_2:
 	rtl_release_firmware(tp);
 	rtl8169_rx_clear(tp);
@@ -7126,6 +7152,7 @@ static void rtl8169_net_suspend(struct net_device *dev)
 	if (!netif_running(dev))
 		return;
 
+	phy_stop(dev->phydev);
 	netif_device_detach(dev);
 	netif_stop_queue(dev);
 
@@ -7158,6 +7185,8 @@ static void __rtl8169_resume(struct net_device *dev)
 	rtl_pll_power_up(tp);
 	rtl8169_init_phy(dev, tp);
 
+	phy_start(tp->dev->phydev);
+
 	rtl_lock_work(tp);
 	napi_enable(&tp->napi);
 	set_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags);
@@ -7303,6 +7332,7 @@ static void rtl_remove_one(struct pci_dev *pdev)
 	netif_napi_del(&tp->napi);
 
 	unregister_netdev(dev);
+	mdiobus_unregister(tp->mii_bus);
 
 	rtl_release_firmware(tp);
 
@@ -7388,6 +7418,65 @@ DECLARE_RTL_COND(rtl_rxtx_empty_cond)
 	return (RTL_R8(tp, MCU) & RXTX_EMPTY) == RXTX_EMPTY;
 }
 
+static int r8169_mdio_read_reg(struct mii_bus *mii_bus, int phyaddr, int phyreg)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (phyaddr > 0)
+		return -ENODEV;
+
+	return rtl_readphy(tp, phyreg);
+}
+
+static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr,
+				int phyreg, u16 val)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (phyaddr > 0)
+		return -ENODEV;
+
+	rtl_writephy(tp, phyreg, val);
+
+	return 0;
+}
+
+static int r8169_mdio_register(struct rtl8169_private *tp)
+{
+	struct pci_dev *pdev = tp->pci_dev;
+	struct phy_device *phydev;
+	struct mii_bus *new_bus;
+	int ret;
+
+	new_bus = devm_mdiobus_alloc(&pdev->dev);
+	if (!new_bus)
+		return -ENOMEM;
+
+	new_bus->name = "r8169";
+	new_bus->priv = tp;
+	new_bus->parent = &pdev->dev;
+	new_bus->irq[0] = PHY_IGNORE_INTERRUPT;
+	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x",
+		 PCI_DEVID(pdev->bus->number, pdev->devfn));
+
+	new_bus->read = r8169_mdio_read_reg;
+	new_bus->write = r8169_mdio_write_reg;
+
+	ret = mdiobus_register(new_bus);
+	if (ret)
+		return ret;
+
+	phydev = mdiobus_get_phy(new_bus, 0);
+	if (!phydev) {
+		mdiobus_unregister(new_bus);
+		return -ENODEV;
+	}
+
+	tp->mii_bus = new_bus;
+
+	return 0;
+}
+
 static void rtl_hw_init_8168g(struct rtl8169_private *tp)
 {
 	u32 data;
@@ -7644,10 +7733,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	pci_set_drvdata(pdev, dev);
 
-	rc = register_netdev(dev);
-	if (rc < 0)
+	rc = r8169_mdio_register(tp);
+	if (rc)
 		return rc;
 
+	rc = register_netdev(dev);
+	if (rc)
+		goto err_mdio_unregister;
+
 	netif_info(tp, probe, dev, "%s, %pM, XID %08x, IRQ %d\n",
 		   rtl_chip_infos[chipset].name, dev->dev_addr,
 		   (u32)(RTL_R32(tp, TxConfig) & 0xfcf0f8ff),
@@ -7662,12 +7755,14 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (r8168_check_dash(tp))
 		rtl8168_driver_start(tp);
 
-	netif_carrier_off(dev);
-
 	if (pci_dev_run_wake(pdev))
 		pm_runtime_put_sync(&pdev->dev);
 
 	return 0;
+
+err_mdio_unregister:
+	mdiobus_unregister(tp->mii_bus);
+	return rc;
 }
 
 static struct pci_driver rtl8169_pci_driver = {
-- 
cgit v1.2.3


From 242cd9b5866aa2caf9ff770283b85ddb35d52f90 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:51:33 +0200
Subject: r8169: use phy_resume/phy_suspend

Use phy_resume() / phy_suspend() instead of open coding this functionality.
The chip version specific differences are handled by the respective PHY
drivers.

The call to r8168_phy_power_down() in r8168_pll_power_down() can be
removed because phylib takes care now. The relevant scenarios are:
- rtl8169_close(): phy_disconnect() powers down PHY
- suspend: mdio_bus_phy_suspend() takes care
- runtime-suspend: WoL is active, don't suspend PHY
- rtl_shutdown(): no need to power down PHY

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 50 +++++-------------------------------
 1 file changed, 6 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 96eb28a7065e..15fa08e81660 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4450,47 +4450,6 @@ static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 	return true;
 }
 
-static void r8168_phy_power_up(struct rtl8169_private *tp)
-{
-	rtl_writephy(tp, 0x1f, 0x0000);
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_11:
-	case RTL_GIGA_MAC_VER_12:
-	case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		rtl_writephy(tp, 0x0e, 0x0000);
-		break;
-	default:
-		break;
-	}
-	rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE);
-
-	/* give MAC/PHY some time to resume */
-	msleep(20);
-}
-
-static void r8168_phy_power_down(struct rtl8169_private *tp)
-{
-	rtl_writephy(tp, 0x1f, 0x0000);
-	switch (tp->mac_version) {
-	case RTL_GIGA_MAC_VER_32:
-	case RTL_GIGA_MAC_VER_33:
-	case RTL_GIGA_MAC_VER_40:
-	case RTL_GIGA_MAC_VER_41:
-		rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE | BMCR_PDOWN);
-		break;
-
-	case RTL_GIGA_MAC_VER_11:
-	case RTL_GIGA_MAC_VER_12:
-	case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28:
-	case RTL_GIGA_MAC_VER_31:
-		rtl_writephy(tp, 0x0e, 0x0200);
-	default:
-		rtl_writephy(tp, MII_BMCR, BMCR_PDOWN);
-		break;
-	}
-}
-
 static void r8168_pll_power_down(struct rtl8169_private *tp)
 {
 	if (r8168_check_dash(tp))
@@ -4503,8 +4462,6 @@ static void r8168_pll_power_down(struct rtl8169_private *tp)
 	if (rtl_wol_pll_power_down(tp))
 		return;
 
-	r8168_phy_power_down(tp);
-
 	switch (tp->mac_version) {
 	case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33:
 	case RTL_GIGA_MAC_VER_37:
@@ -4556,7 +4513,9 @@ static void r8168_pll_power_up(struct rtl8169_private *tp)
 		break;
 	}
 
-	r8168_phy_power_up(tp);
+	phy_resume(tp->dev->phydev);
+	/* give MAC/PHY some time to resume */
+	msleep(20);
 }
 
 static void rtl_pll_power_down(struct rtl8169_private *tp)
@@ -7472,6 +7431,9 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 		return -ENODEV;
 	}
 
+	/* PHY will be woken up in rtl_open() */
+	phy_suspend(phydev);
+
 	tp->mii_bus = new_bus;
 
 	return 0;
-- 
cgit v1.2.3


From f75222bce9b5e5a4af01100b949e056f12183c27 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:51:41 +0200
Subject: r8169: replace open-coded PHY soft reset with genphy_soft_reset

Use genphy_soft_reset() instead of open-coding a PHY soft reset. We have
to do an explicit PHY soft reset because some chips use the genphy driver
which uses a no-op as soft_reset callback.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 27 +--------------------------
 1 file changed, 1 insertion(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 15fa08e81660..0ba8588f92c0 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1441,19 +1441,6 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 	RTL_R8(tp, ChipCmd);
 }
 
-static unsigned int rtl8169_xmii_reset_pending(struct rtl8169_private *tp)
-{
-	return rtl_readphy(tp, MII_BMCR) & BMCR_RESET;
-}
-
-static void rtl8169_xmii_reset_enable(struct rtl8169_private *tp)
-{
-	unsigned int val;
-
-	val = rtl_readphy(tp, MII_BMCR) | BMCR_RESET;
-	rtl_writephy(tp, MII_BMCR, val & 0xffff);
-}
-
 static void rtl_link_chg_patch(struct rtl8169_private *tp)
 {
 	struct net_device *dev = tp->dev;
@@ -4252,18 +4239,6 @@ static void rtl_schedule_task(struct rtl8169_private *tp, enum rtl_flag flag)
 		schedule_work(&tp->wk.work);
 }
 
-DECLARE_RTL_COND(rtl_phy_reset_cond)
-{
-	return rtl8169_xmii_reset_pending(tp);
-}
-
-static void rtl8169_phy_reset(struct net_device *dev,
-			      struct rtl8169_private *tp)
-{
-	rtl8169_xmii_reset_enable(tp);
-	rtl_msleep_loop_wait_low(tp, &rtl_phy_reset_cond, 1, 100);
-}
-
 static bool rtl_tbi_enabled(struct rtl8169_private *tp)
 {
 	return (tp->mac_version == RTL_GIGA_MAC_VER_01) &&
@@ -4294,7 +4269,7 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 		rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0
 	}
 
-	rtl8169_phy_reset(dev, tp);
+	genphy_soft_reset(dev->phydev);
 
 	rtl8169_set_speed(dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
 			  ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-- 
cgit v1.2.3


From 4577243392ce36d90290c4101eb6ea6b5617026f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:51:44 +0200
Subject: r8169: use phy_ethtool_(g|s)et_link_ksettings

Use phy_ethtool_(g|s)et_link_ksettings() for the respective ethtool_ops
callbacks.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 35 +++--------------------------------
 1 file changed, 3 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 0ba8588f92c0..a8329f32456b 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1809,35 +1809,6 @@ static void rtl8169_rx_vlan_tag(struct RxDesc *desc, struct sk_buff *skb)
 		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & 0xffff));
 }
 
-static int rtl8169_get_link_ksettings(struct net_device *dev,
-				      struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	mii_ethtool_get_link_ksettings(&tp->mii, cmd);
-
-	return 0;
-}
-
-static int rtl8169_set_link_ksettings(struct net_device *dev,
-				      const struct ethtool_link_ksettings *cmd)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int rc;
-	u32 advertising;
-
-	if (!ethtool_convert_link_mode_to_legacy_u32(&advertising,
-	    cmd->link_modes.advertising))
-		return -EINVAL;
-
-	rtl_lock_work(tp);
-	rc = rtl8169_set_speed(dev, cmd->base.autoneg, cmd->base.speed,
-			       cmd->base.duplex, advertising);
-	rtl_unlock_work(tp);
-
-	return rc;
-}
-
 static void rtl8169_get_regs(struct net_device *dev, struct ethtool_regs *regs,
 			     void *p)
 {
@@ -2092,7 +2063,7 @@ static const struct rtl_coalesce_info *rtl_coalesce_info(struct net_device *dev)
 	const struct rtl_coalesce_info *ci;
 	int rc;
 
-	rc = rtl8169_get_link_ksettings(dev, &ecmd);
+	rc = phy_ethtool_get_link_ksettings(dev, &ecmd);
 	if (rc < 0)
 		return ERR_PTR(rc);
 
@@ -2251,8 +2222,8 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_ethtool_stats	= rtl8169_get_ethtool_stats,
 	.get_ts_info		= ethtool_op_get_ts_info,
 	.nway_reset		= rtl8169_nway_reset,
-	.get_link_ksettings	= rtl8169_get_link_ksettings,
-	.set_link_ksettings	= rtl8169_set_link_ksettings,
+	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
+	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
 
 static void rtl8169_get_mac_version(struct rtl8169_private *tp,
-- 
cgit v1.2.3


From dd84957eeeae61b60c692ff821c958464576604f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:51:48 +0200
Subject: r8169: use phy_ethtool_nway_reset

Switch to using phy_ethtool_nway_reset().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/Kconfig | 1 -
 drivers/net/ethernet/realtek/r8169.c | 9 +--------
 2 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 7fb1af1f91ce..e1cd934c2e4f 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -100,7 +100,6 @@ config R8169
 	select FW_LOADER
 	select CRC32
 	select PHYLIB
-	select MII
 	---help---
 	  Say Y here if you have a Realtek 8169 PCI Gigabit Ethernet adapter.
 
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index a8329f32456b..7c56202f1185 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1984,13 +1984,6 @@ static void rtl8169_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 	}
 }
 
-static int rtl8169_nway_reset(struct net_device *dev)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	return mii_nway_restart(&tp->mii);
-}
-
 /*
  * Interrupt coalescing
  *
@@ -2221,7 +2214,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = {
 	.get_sset_count		= rtl8169_get_sset_count,
 	.get_ethtool_stats	= rtl8169_get_ethtool_stats,
 	.get_ts_info		= ethtool_op_get_ts_info,
-	.nway_reset		= rtl8169_nway_reset,
+	.nway_reset		= phy_ethtool_nway_reset,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
 	.set_link_ksettings	= phy_ethtool_set_link_ksettings,
 };
-- 
cgit v1.2.3


From 69b3c59fe212ff0a90e52bef2073b0c3cc7eff91 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:51:53 +0200
Subject: r8169: use phy_mii_ioctl

Switch to using phy_mii_ioctl().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 25 +++----------------------
 1 file changed, 3 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 7c56202f1185..1937d12a4c2e 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4283,31 +4283,12 @@ static int rtl_set_mac_address(struct net_device *dev, void *p)
 	return 0;
 }
 
-static int rtl_xmii_ioctl(struct rtl8169_private *tp,
-			  struct mii_ioctl_data *data, int cmd)
-{
-	switch (cmd) {
-	case SIOCGMIIPHY:
-		data->phy_id = 32; /* Internal PHY */
-		return 0;
-
-	case SIOCGMIIREG:
-		data->val_out = rtl_readphy(tp, data->reg_num & 0x1f);
-		return 0;
-
-	case SIOCSMIIREG:
-		rtl_writephy(tp, data->reg_num & 0x1f, data->val_in);
-		return 0;
-	}
-	return -EOPNOTSUPP;
-}
-
 static int rtl8169_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
-	struct rtl8169_private *tp = netdev_priv(dev);
-	struct mii_ioctl_data *data = if_mii(ifr);
+	if (!netif_running(dev))
+		return -ENODEV;
 
-	return netif_running(dev) ? rtl_xmii_ioctl(tp, data, cmd) : -ENODEV;
+	return phy_mii_ioctl(dev->phydev, ifr, cmd);
 }
 
 static void rtl_init_mdio_ops(struct rtl8169_private *tp)
-- 
cgit v1.2.3


From 5b7ad4b75d1e89743137857123e67f1b37721264 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:51:57 +0200
Subject: r8169: use phy_speed_down / phy_speed_up

Use new phylib functions phy_speed_down() and phy_speed_up().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 29 ++++-------------------------
 1 file changed, 4 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 1937d12a4c2e..775e5d6dace4 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -4233,6 +4233,9 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 		rtl_writephy(tp, 0x0b, 0x0000); //w 0x0b 15 0 0
 	}
 
+	/* We may have called phy_speed_down before */
+	phy_speed_up(dev->phydev);
+
 	genphy_soft_reset(dev->phydev);
 
 	rtl8169_set_speed(dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
@@ -4316,30 +4319,6 @@ static void rtl_init_mdio_ops(struct rtl8169_private *tp)
 	}
 }
 
-static void rtl_speed_down(struct rtl8169_private *tp)
-{
-	u32 adv;
-	int lpa;
-
-	rtl_writephy(tp, 0x1f, 0x0000);
-	lpa = rtl_readphy(tp, MII_LPA);
-
-	if (lpa & (LPA_10HALF | LPA_10FULL))
-		adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full;
-	else if (lpa & (LPA_100HALF | LPA_100FULL))
-		adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-		      ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full;
-	else
-		adv = ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-		      ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
-		      (tp->mii.supports_gmii ?
-		       ADVERTISED_1000baseT_Half |
-		       ADVERTISED_1000baseT_Full : 0);
-
-	rtl8169_set_speed(tp->dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
-			  adv);
-}
-
 static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 {
 	switch (tp->mac_version) {
@@ -4364,7 +4343,7 @@ static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 	if (!netif_running(tp->dev) || !__rtl8169_get_wol(tp))
 		return false;
 
-	rtl_speed_down(tp);
+	phy_speed_down(tp->dev->phydev, false);
 	rtl_wol_suspend_quirk(tp);
 
 	return true;
-- 
cgit v1.2.3


From a2965f12fde696d3754347bd48a7149b8de45b21 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:52:03 +0200
Subject: r8169: remove rtl8169_set_speed_xmii

We can remove rtl8169_set_speed_xmii() now that phylib handles all this.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 90 ------------------------------------
 1 file changed, 90 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 775e5d6dace4..0924396c5235 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1663,89 +1663,6 @@ static int rtl8169_get_regs_len(struct net_device *dev)
 	return R8169_REGS_SIZE;
 }
 
-static int rtl8169_set_speed_xmii(struct net_device *dev,
-				  u8 autoneg, u16 speed, u8 duplex, u32 adv)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-	int giga_ctrl, bmcr;
-	int rc = -EINVAL;
-
-	rtl_writephy(tp, 0x1f, 0x0000);
-
-	if (autoneg == AUTONEG_ENABLE) {
-		int auto_nego;
-
-		auto_nego = rtl_readphy(tp, MII_ADVERTISE);
-		auto_nego &= ~(ADVERTISE_10HALF | ADVERTISE_10FULL |
-				ADVERTISE_100HALF | ADVERTISE_100FULL);
-
-		if (adv & ADVERTISED_10baseT_Half)
-			auto_nego |= ADVERTISE_10HALF;
-		if (adv & ADVERTISED_10baseT_Full)
-			auto_nego |= ADVERTISE_10FULL;
-		if (adv & ADVERTISED_100baseT_Half)
-			auto_nego |= ADVERTISE_100HALF;
-		if (adv & ADVERTISED_100baseT_Full)
-			auto_nego |= ADVERTISE_100FULL;
-
-		auto_nego |= ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM;
-
-		giga_ctrl = rtl_readphy(tp, MII_CTRL1000);
-		giga_ctrl &= ~(ADVERTISE_1000FULL | ADVERTISE_1000HALF);
-
-		/* The 8100e/8101e/8102e do Fast Ethernet only. */
-		if (tp->mii.supports_gmii) {
-			if (adv & ADVERTISED_1000baseT_Half)
-				giga_ctrl |= ADVERTISE_1000HALF;
-			if (adv & ADVERTISED_1000baseT_Full)
-				giga_ctrl |= ADVERTISE_1000FULL;
-		} else if (adv & (ADVERTISED_1000baseT_Half |
-				  ADVERTISED_1000baseT_Full)) {
-			netif_info(tp, link, dev,
-				   "PHY does not support 1000Mbps\n");
-			goto out;
-		}
-
-		bmcr = BMCR_ANENABLE | BMCR_ANRESTART;
-
-		rtl_writephy(tp, MII_ADVERTISE, auto_nego);
-		rtl_writephy(tp, MII_CTRL1000, giga_ctrl);
-	} else {
-		if (speed == SPEED_10)
-			bmcr = 0;
-		else if (speed == SPEED_100)
-			bmcr = BMCR_SPEED100;
-		else
-			goto out;
-
-		if (duplex == DUPLEX_FULL)
-			bmcr |= BMCR_FULLDPLX;
-	}
-
-	rtl_writephy(tp, MII_BMCR, bmcr);
-
-	if (tp->mac_version == RTL_GIGA_MAC_VER_02 ||
-	    tp->mac_version == RTL_GIGA_MAC_VER_03) {
-		if ((speed == SPEED_100) && (autoneg != AUTONEG_ENABLE)) {
-			rtl_writephy(tp, 0x17, 0x2138);
-			rtl_writephy(tp, 0x0e, 0x0260);
-		} else {
-			rtl_writephy(tp, 0x17, 0x2108);
-			rtl_writephy(tp, 0x0e, 0x0000);
-		}
-	}
-
-	rc = 0;
-out:
-	return rc;
-}
-
-static int rtl8169_set_speed(struct net_device *dev,
-			     u8 autoneg, u16 speed, u8 duplex, u32 advertising)
-{
-	return rtl8169_set_speed_xmii(dev, autoneg, speed, duplex, advertising);
-}
-
 static netdev_features_t rtl8169_fix_features(struct net_device *dev,
 	netdev_features_t features)
 {
@@ -4237,13 +4154,6 @@ static void rtl8169_init_phy(struct net_device *dev, struct rtl8169_private *tp)
 	phy_speed_up(dev->phydev);
 
 	genphy_soft_reset(dev->phydev);
-
-	rtl8169_set_speed(dev, AUTONEG_ENABLE, SPEED_1000, DUPLEX_FULL,
-			  ADVERTISED_10baseT_Half | ADVERTISED_10baseT_Full |
-			  ADVERTISED_100baseT_Half | ADVERTISED_100baseT_Full |
-			  (tp->mii.supports_gmii ?
-			   ADVERTISED_1000baseT_Half |
-			   ADVERTISED_1000baseT_Full : 0));
 }
 
 static void rtl_rar_set(struct rtl8169_private *tp, u8 *addr)
-- 
cgit v1.2.3


From f7ffa9ae2bb90fd948b514e2049ef3a904e66743 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:52:09 +0200
Subject: r8169: remove mii_if_info member from struct rtl8169_private

The only remaining usage of the struct mii_if_info member is to store the
information whether the chip is GMII-capable. So we can replace it with
a simple flag.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 38 +++++++-----------------------------
 1 file changed, 7 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 0924396c5235..724272b78a21 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -15,7 +15,6 @@
 #include <linux/etherdevice.h>
 #include <linux/delay.h>
 #include <linux/ethtool.h>
-#include <linux/mii.h>
 #include <linux/phy.h>
 #include <linux/if_vlan.h>
 #include <linux/crc32.h>
@@ -754,7 +753,7 @@ struct rtl8169_private {
 		struct work_struct work;
 	} wk;
 
-	struct mii_if_info mii;
+	unsigned supports_gmii:1;
 	struct mii_bus *mii_bus;
 	dma_addr_t counters_phys_addr;
 	struct rtl8169_counters *counters;
@@ -1106,21 +1105,6 @@ static void rtl_w0w1_phy(struct rtl8169_private *tp, int reg_addr, int p, int m)
 	rtl_writephy(tp, reg_addr, (val & ~m) | p);
 }
 
-static void rtl_mdio_write(struct net_device *dev, int phy_id, int location,
-			   int val)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	rtl_writephy(tp, location, val);
-}
-
-static int rtl_mdio_read(struct net_device *dev, int phy_id, int location)
-{
-	struct rtl8169_private *tp = netdev_priv(dev);
-
-	return rtl_readphy(tp, location);
-}
-
 DECLARE_RTL_COND(rtl_ephyar_cond)
 {
 	return RTL_R32(tp, EPHYAR) & EPHYAR_FLAG;
@@ -2246,15 +2230,15 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp,
 			   "unknown MAC, using family default\n");
 		tp->mac_version = default_version;
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_42) {
-		tp->mac_version = tp->mii.supports_gmii ?
+		tp->mac_version = tp->supports_gmii ?
 				  RTL_GIGA_MAC_VER_42 :
 				  RTL_GIGA_MAC_VER_43;
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_45) {
-		tp->mac_version = tp->mii.supports_gmii ?
+		tp->mac_version = tp->supports_gmii ?
 				  RTL_GIGA_MAC_VER_45 :
 				  RTL_GIGA_MAC_VER_47;
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_46) {
-		tp->mac_version = tp->mii.supports_gmii ?
+		tp->mac_version = tp->supports_gmii ?
 				  RTL_GIGA_MAC_VER_46 :
 				  RTL_GIGA_MAC_VER_48;
 	}
@@ -6686,7 +6670,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 	phy_interface_t phy_mode;
 	int ret;
 
-	phy_mode = tp->mii.supports_gmii ? PHY_INTERFACE_MODE_GMII :
+	phy_mode = tp->supports_gmii ? PHY_INTERFACE_MODE_GMII :
 		   PHY_INTERFACE_MODE_MII;
 
 	ret = phy_connect_direct(tp->dev, phydev, r8169_phylink_handler,
@@ -6694,7 +6678,7 @@ static int r8169_phy_connect(struct rtl8169_private *tp)
 	if (ret)
 		return ret;
 
-	if (!tp->mii.supports_gmii)
+	if (!tp->supports_gmii)
 		phy_set_max_speed(phydev, SPEED_100);
 
 	/* Ensure to advertise everything, incl. pause */
@@ -7305,7 +7289,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
 	struct rtl8169_private *tp;
-	struct mii_if_info *mii;
 	struct net_device *dev;
 	int chipset, region, i;
 	int rc;
@@ -7325,14 +7308,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	tp->dev = dev;
 	tp->pci_dev = pdev;
 	tp->msg_enable = netif_msg_init(debug.msg_enable, R8169_MSG_DEFAULT);
-
-	mii = &tp->mii;
-	mii->dev = dev;
-	mii->mdio_read = rtl_mdio_read;
-	mii->mdio_write = rtl_mdio_write;
-	mii->phy_id_mask = 0x1f;
-	mii->reg_num_mask = 0x1f;
-	mii->supports_gmii = cfg->has_gmii;
+	tp->supports_gmii = cfg->has_gmii;
 
 	/* enable device (incl. PCI PM wakeup and hotplug setup) */
 	rc = pcim_enable_device(pdev);
-- 
cgit v1.2.3


From 29a12b49536bbf566c1ec4de0d4edfd5da8fe910 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 22:52:14 +0200
Subject: r8169: don't read chip phy status register

Instead of accessing the PHYstatus register we can use the information
phylib stores in the phy_device structure.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 724272b78a21..261fdfad75c2 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -1428,18 +1428,19 @@ static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp)
 static void rtl_link_chg_patch(struct rtl8169_private *tp)
 {
 	struct net_device *dev = tp->dev;
+	struct phy_device *phydev = dev->phydev;
 
 	if (!netif_running(dev))
 		return;
 
 	if (tp->mac_version == RTL_GIGA_MAC_VER_34 ||
 	    tp->mac_version == RTL_GIGA_MAC_VER_38) {
-		if (RTL_R8(tp, PHYstatus) & _1000bpsF) {
+		if (phydev->speed == SPEED_1000) {
 			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
 				      ERIAR_EXGMAC);
-		} else if (RTL_R8(tp, PHYstatus) & _100bps) {
+		} else if (phydev->speed == SPEED_100) {
 			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x0000001f,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
@@ -1457,7 +1458,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 			     ERIAR_EXGMAC);
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_35 ||
 		   tp->mac_version == RTL_GIGA_MAC_VER_36) {
-		if (RTL_R8(tp, PHYstatus) & _1000bpsF) {
+		if (phydev->speed == SPEED_1000) {
 			rtl_eri_write(tp, 0x1bc, ERIAR_MASK_1111, 0x00000011,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_1111, 0x00000005,
@@ -1469,7 +1470,7 @@ static void rtl_link_chg_patch(struct rtl8169_private *tp)
 				      ERIAR_EXGMAC);
 		}
 	} else if (tp->mac_version == RTL_GIGA_MAC_VER_37) {
-		if (RTL_R8(tp, PHYstatus) & _10bps) {
+		if (phydev->speed == SPEED_10) {
 			rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x4d02,
 				      ERIAR_EXGMAC);
 			rtl_eri_write(tp, 0x1dc, ERIAR_MASK_0011, 0x0060,
-- 
cgit v1.2.3


From 2fe31e43124040a67495fa81f7ac67bc4c09ebc8 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 17 Jul 2018 21:48:10 +0200
Subject: hwmon: Add missing HWMON_T_LCRIT_ALARM define

The enum hwmon_temp_lcrit_alarm exists, but the BIT definition is
missing.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/hwmon.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index e5fd2707b6df..1b74ad11a5a4 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -93,6 +93,7 @@ enum hwmon_temp_attributes {
 #define HWMON_T_MIN_ALARM	BIT(hwmon_temp_min_alarm)
 #define HWMON_T_MAX_ALARM	BIT(hwmon_temp_max_alarm)
 #define HWMON_T_CRIT_ALARM	BIT(hwmon_temp_crit_alarm)
+#define HWMON_T_LCRIT_ALARM	BIT(hwmon_temp_lcrit_alarm)
 #define HWMON_T_EMERGENCY_ALARM	BIT(hwmon_temp_emergency_alarm)
 #define HWMON_T_FAULT		BIT(hwmon_temp_fault)
 #define HWMON_T_OFFSET		BIT(hwmon_temp_offset)
-- 
cgit v1.2.3


From aa7f29b07c8702127124d0522e3cd46850cdbc41 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 17 Jul 2018 21:48:11 +0200
Subject: hwmon: Add support for power min, lcrit, min_alarm and lcrit_alarm

Some sensors support reporting minimal and lower critical power, as
well as alarms when these thresholds are reached. Add support for
these attributes to the hwmon core.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/hwmon/hwmon.c | 4 ++++
 include/linux/hwmon.h | 8 ++++++++
 2 files changed, 12 insertions(+)

diff --git a/drivers/hwmon/hwmon.c b/drivers/hwmon/hwmon.c
index e88c01961948..33d51281272b 100644
--- a/drivers/hwmon/hwmon.c
+++ b/drivers/hwmon/hwmon.c
@@ -394,12 +394,16 @@ static const char * const hwmon_power_attr_templates[] = {
 	[hwmon_power_cap_hyst] = "power%d_cap_hyst",
 	[hwmon_power_cap_max] = "power%d_cap_max",
 	[hwmon_power_cap_min] = "power%d_cap_min",
+	[hwmon_power_min] = "power%d_min",
 	[hwmon_power_max] = "power%d_max",
+	[hwmon_power_lcrit] = "power%d_lcrit",
 	[hwmon_power_crit] = "power%d_crit",
 	[hwmon_power_label] = "power%d_label",
 	[hwmon_power_alarm] = "power%d_alarm",
 	[hwmon_power_cap_alarm] = "power%d_cap_alarm",
+	[hwmon_power_min_alarm] = "power%d_min_alarm",
 	[hwmon_power_max_alarm] = "power%d_max_alarm",
+	[hwmon_power_lcrit_alarm] = "power%d_lcrit_alarm",
 	[hwmon_power_crit_alarm] = "power%d_crit_alarm",
 };
 
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 1b74ad11a5a4..b217101ca76e 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -188,12 +188,16 @@ enum hwmon_power_attributes {
 	hwmon_power_cap_hyst,
 	hwmon_power_cap_max,
 	hwmon_power_cap_min,
+	hwmon_power_min,
 	hwmon_power_max,
 	hwmon_power_crit,
+	hwmon_power_lcrit,
 	hwmon_power_label,
 	hwmon_power_alarm,
 	hwmon_power_cap_alarm,
+	hwmon_power_min_alarm,
 	hwmon_power_max_alarm,
+	hwmon_power_lcrit_alarm,
 	hwmon_power_crit_alarm,
 };
 
@@ -214,12 +218,16 @@ enum hwmon_power_attributes {
 #define HWMON_P_CAP_HYST		BIT(hwmon_power_cap_hyst)
 #define HWMON_P_CAP_MAX			BIT(hwmon_power_cap_max)
 #define HWMON_P_CAP_MIN			BIT(hwmon_power_cap_min)
+#define HWMON_P_MIN			BIT(hwmon_power_min)
 #define HWMON_P_MAX			BIT(hwmon_power_max)
+#define HWMON_P_LCRIT			BIT(hwmon_power_lcrit)
 #define HWMON_P_CRIT			BIT(hwmon_power_crit)
 #define HWMON_P_LABEL			BIT(hwmon_power_label)
 #define HWMON_P_ALARM			BIT(hwmon_power_alarm)
 #define HWMON_P_CAP_ALARM		BIT(hwmon_power_cap_alarm)
+#define HWMON_P_MIN_ALARM		BIT(hwmon_power_max_alarm)
 #define HWMON_P_MAX_ALARM		BIT(hwmon_power_max_alarm)
+#define HWMON_P_LCRIT_ALARM		BIT(hwmon_power_lcrit_alarm)
 #define HWMON_P_CRIT_ALARM		BIT(hwmon_power_crit_alarm)
 
 enum hwmon_energy_attributes {
-- 
cgit v1.2.3


From dcb5d0fcaa1ddd0af9c18ef51e6b05e38a6cec71 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 17 Jul 2018 21:48:12 +0200
Subject: hwmon: Add helper to tell if a char is invalid in a name

HWMON device names are not allowed to contain "-* \t\n". Add a helper
which will return true if passed an invalid character. It can be used
to massage a string into a hwmon compatible name by replacing invalid
characters with '_'.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/hwmon.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index b217101ca76e..9493d4a388db 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -398,4 +398,27 @@ devm_hwmon_device_register_with_info(struct device *dev,
 void hwmon_device_unregister(struct device *dev);
 void devm_hwmon_device_unregister(struct device *dev);
 
+/**
+ * hwmon_is_bad_char - Is the char invalid in a hwmon name
+ * @ch: the char to be considered
+ *
+ * hwmon_is_bad_char() can be used to determine if the given character
+ * may not be used in a hwmon name.
+ *
+ * Returns true if the char is invalid, false otherwise.
+ */
+static inline bool hwmon_is_bad_char(const char ch)
+{
+	switch (ch) {
+	case '-':
+	case '*':
+	case ' ':
+	case '\t':
+	case '\n':
+		return true;
+	default:
+		return false;
+	}
+}
+
 #endif
-- 
cgit v1.2.3


From 1323061a018a7514287894a552c4ec2a5f0cb0cd Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Tue, 17 Jul 2018 21:48:13 +0200
Subject: net: phy: sfp: Add HWMON support for module sensors
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

SFP modules can contain a number of sensors. The EEPROM also contains
recommended alarm and critical values for each sensor, and indications
of if these have been exceeded. Export this information via
HWMON. Currently temperature, VCC, bias current, transmit power, and
possibly receiver power is supported.

The sensors in the modules can either return calibrate or uncalibrated
values. Uncalibrated values need to be manipulated, using coefficients
provided in the SFP EEPROM. Uncalibrated receive power values require
floating point maths in order to calibrate them. Performing this in
the kernel is hard. So if the SFP module indicates it uses
uncalibrated values, RX power is not made available.

With this hwmon device, it is possible to view the sensor values using
lm-sensors programs:

in0:          +3.29 V  (crit min =  +2.90 V, min =  +3.00 V)
                       (max =  +3.60 V, crit max =  +3.70 V)
temp1:        +33.0°C  (low  =  -5.0°C, high = +80.0°C)
                       (crit low = -10.0°C, crit = +85.0°C)
power1:      1000.00 nW (max = 794.00 uW, min =  50.00 uW)  ALARM (LCRIT)
                       (lcrit =  40.00 uW, crit = 1000.00 uW)
curr1:        +0.00 A  (crit min =  +0.00 A, min =  +0.00 A)  ALARM (LCRIT, MIN)
                       (max =  +0.01 A, crit max =  +0.01 A)

The scaling sensors performs on the bias current is not particularly
good. The raw values are more useful:

curr1:
  curr1_input: 0.000
  curr1_min: 0.002
  curr1_max: 0.010
  curr1_lcrit: 0.000
  curr1_crit: 0.011
  curr1_min_alarm: 1.000
  curr1_max_alarm: 0.000
  curr1_lcrit_alarm: 1.000
  curr1_crit_alarm: 0.000

In order to keep the I2C overhead to a minimum, the constant values,
such as limits and calibration coefficients are read once at module
insertion time. Thus only reading *_input and *_alarm properties
requires i2c read operations.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Kconfig |   1 +
 drivers/net/phy/sfp.c   | 727 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/sfp.h     |  72 ++++-
 3 files changed, 799 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index ceede09a2845..9beac427f9e8 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -215,6 +215,7 @@ config SFP
 	tristate "SFP cage support"
 	depends on I2C && PHYLINK
 	select MDIO_I2C
+	imply HWMON
 
 config AMD_PHY
 	tristate "AMD PHYs"
diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index c4c92db86dfa..5661226cf75b 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -1,5 +1,7 @@
+#include <linux/ctype.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
+#include <linux/hwmon.h>
 #include <linux/i2c.h>
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
@@ -131,6 +133,12 @@ struct sfp {
 	unsigned int sm_retries;
 
 	struct sfp_eeprom_id id;
+#if IS_ENABLED(CONFIG_HWMON)
+	struct sfp_diag diag;
+	struct device *hwmon_dev;
+	char *hwmon_name;
+#endif
+
 };
 
 static bool sff_module_supported(const struct sfp_eeprom_id *id)
@@ -316,6 +324,719 @@ static unsigned int sfp_check(void *buf, size_t len)
 	return check;
 }
 
+/* hwmon */
+#if IS_ENABLED(CONFIG_HWMON)
+static umode_t sfp_hwmon_is_visible(const void *data,
+				    enum hwmon_sensor_types type,
+				    u32 attr, int channel)
+{
+	const struct sfp *sfp = data;
+
+	switch (type) {
+	case hwmon_temp:
+		switch (attr) {
+		case hwmon_temp_input:
+		case hwmon_temp_min_alarm:
+		case hwmon_temp_max_alarm:
+		case hwmon_temp_lcrit_alarm:
+		case hwmon_temp_crit_alarm:
+		case hwmon_temp_min:
+		case hwmon_temp_max:
+		case hwmon_temp_lcrit:
+		case hwmon_temp_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	case hwmon_in:
+		switch (attr) {
+		case hwmon_in_input:
+		case hwmon_in_min_alarm:
+		case hwmon_in_max_alarm:
+		case hwmon_in_lcrit_alarm:
+		case hwmon_in_crit_alarm:
+		case hwmon_in_min:
+		case hwmon_in_max:
+		case hwmon_in_lcrit:
+		case hwmon_in_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	case hwmon_curr:
+		switch (attr) {
+		case hwmon_curr_input:
+		case hwmon_curr_min_alarm:
+		case hwmon_curr_max_alarm:
+		case hwmon_curr_lcrit_alarm:
+		case hwmon_curr_crit_alarm:
+		case hwmon_curr_min:
+		case hwmon_curr_max:
+		case hwmon_curr_lcrit:
+		case hwmon_curr_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	case hwmon_power:
+		/* External calibration of receive power requires
+		 * floating point arithmetic. Doing that in the kernel
+		 * is not easy, so just skip it. If the module does
+		 * not require external calibration, we can however
+		 * show receiver power, since FP is then not needed.
+		 */
+		if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL &&
+		    channel == 1)
+			return 0;
+		switch (attr) {
+		case hwmon_power_input:
+		case hwmon_power_min_alarm:
+		case hwmon_power_max_alarm:
+		case hwmon_power_lcrit_alarm:
+		case hwmon_power_crit_alarm:
+		case hwmon_power_min:
+		case hwmon_power_max:
+		case hwmon_power_lcrit:
+		case hwmon_power_crit:
+			return 0444;
+		default:
+			return 0;
+		}
+	default:
+		return 0;
+	}
+}
+
+static int sfp_hwmon_read_sensor(struct sfp *sfp, int reg, long *value)
+{
+	__be16 val;
+	int err;
+
+	err = sfp_read(sfp, true, reg, &val, sizeof(val));
+	if (err < 0)
+		return err;
+
+	*value = be16_to_cpu(val);
+
+	return 0;
+}
+
+static void sfp_hwmon_to_rx_power(long *value)
+{
+	*value = DIV_ROUND_CLOSEST(*value, 100);
+}
+
+static void sfp_hwmon_calibrate(struct sfp *sfp, unsigned int slope, int offset,
+				long *value)
+{
+	if (sfp->id.ext.diagmon & SFP_DIAGMON_EXT_CAL)
+		*value = DIV_ROUND_CLOSEST(*value * slope, 256) + offset;
+}
+
+static void sfp_hwmon_calibrate_temp(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_t_slope),
+			    be16_to_cpu(sfp->diag.cal_t_offset), value);
+
+	if (*value >= 0x8000)
+		*value -= 0x10000;
+
+	*value = DIV_ROUND_CLOSEST(*value * 1000, 256);
+}
+
+static void sfp_hwmon_calibrate_vcc(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_v_slope),
+			    be16_to_cpu(sfp->diag.cal_v_offset), value);
+
+	*value = DIV_ROUND_CLOSEST(*value, 10);
+}
+
+static void sfp_hwmon_calibrate_bias(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txi_slope),
+			    be16_to_cpu(sfp->diag.cal_txi_offset), value);
+
+	*value = DIV_ROUND_CLOSEST(*value, 500);
+}
+
+static void sfp_hwmon_calibrate_tx_power(struct sfp *sfp, long *value)
+{
+	sfp_hwmon_calibrate(sfp, be16_to_cpu(sfp->diag.cal_txpwr_slope),
+			    be16_to_cpu(sfp->diag.cal_txpwr_offset), value);
+
+	*value = DIV_ROUND_CLOSEST(*value, 10);
+}
+
+static int sfp_hwmon_read_temp(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_temp(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_vcc(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_vcc(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_bias(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_bias(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_tx_power(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_calibrate_tx_power(sfp, value);
+
+	return 0;
+}
+
+static int sfp_hwmon_read_rx_power(struct sfp *sfp, int reg, long *value)
+{
+	int err;
+
+	err = sfp_hwmon_read_sensor(sfp, reg, value);
+	if (err < 0)
+		return err;
+
+	sfp_hwmon_to_rx_power(value);
+
+	return 0;
+}
+
+static int sfp_hwmon_temp(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_temp_input:
+		return sfp_hwmon_read_temp(sfp, SFP_TEMP, value);
+
+	case hwmon_temp_lcrit:
+		*value = be16_to_cpu(sfp->diag.temp_low_alarm);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+
+	case hwmon_temp_min:
+		*value = be16_to_cpu(sfp->diag.temp_low_warn);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+	case hwmon_temp_max:
+		*value = be16_to_cpu(sfp->diag.temp_high_warn);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+
+	case hwmon_temp_crit:
+		*value = be16_to_cpu(sfp->diag.temp_high_alarm);
+		sfp_hwmon_calibrate_temp(sfp, value);
+		return 0;
+
+	case hwmon_temp_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TEMP_LOW);
+		return 0;
+
+	case hwmon_temp_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TEMP_LOW);
+		return 0;
+
+	case hwmon_temp_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TEMP_HIGH);
+		return 0;
+
+	case hwmon_temp_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TEMP_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_vcc(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_in_input:
+		return sfp_hwmon_read_vcc(sfp, SFP_VCC, value);
+
+	case hwmon_in_lcrit:
+		*value = be16_to_cpu(sfp->diag.volt_low_alarm);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_min:
+		*value = be16_to_cpu(sfp->diag.volt_low_warn);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_max:
+		*value = be16_to_cpu(sfp->diag.volt_high_warn);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_crit:
+		*value = be16_to_cpu(sfp->diag.volt_high_alarm);
+		sfp_hwmon_calibrate_vcc(sfp, value);
+		return 0;
+
+	case hwmon_in_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_VCC_LOW);
+		return 0;
+
+	case hwmon_in_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_VCC_LOW);
+		return 0;
+
+	case hwmon_in_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_VCC_HIGH);
+		return 0;
+
+	case hwmon_in_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_VCC_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_bias(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_curr_input:
+		return sfp_hwmon_read_bias(sfp, SFP_TX_BIAS, value);
+
+	case hwmon_curr_lcrit:
+		*value = be16_to_cpu(sfp->diag.bias_low_alarm);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_min:
+		*value = be16_to_cpu(sfp->diag.bias_low_warn);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_max:
+		*value = be16_to_cpu(sfp->diag.bias_high_warn);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_crit:
+		*value = be16_to_cpu(sfp->diag.bias_high_alarm);
+		sfp_hwmon_calibrate_bias(sfp, value);
+		return 0;
+
+	case hwmon_curr_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TX_BIAS_LOW);
+		return 0;
+
+	case hwmon_curr_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TX_BIAS_LOW);
+		return 0;
+
+	case hwmon_curr_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TX_BIAS_HIGH);
+		return 0;
+
+	case hwmon_curr_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TX_BIAS_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_tx_power(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_power_input:
+		return sfp_hwmon_read_tx_power(sfp, SFP_TX_POWER, value);
+
+	case hwmon_power_lcrit:
+		*value = be16_to_cpu(sfp->diag.txpwr_low_alarm);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_min:
+		*value = be16_to_cpu(sfp->diag.txpwr_low_warn);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_max:
+		*value = be16_to_cpu(sfp->diag.txpwr_high_warn);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_crit:
+		*value = be16_to_cpu(sfp->diag.txpwr_high_alarm);
+		sfp_hwmon_calibrate_tx_power(sfp, value);
+		return 0;
+
+	case hwmon_power_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TXPWR_LOW);
+		return 0;
+
+	case hwmon_power_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TXPWR_LOW);
+		return 0;
+
+	case hwmon_power_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN0_TXPWR_HIGH);
+		return 0;
+
+	case hwmon_power_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM0, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM0_TXPWR_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_rx_power(struct sfp *sfp, u32 attr, long *value)
+{
+	u8 status;
+	int err;
+
+	switch (attr) {
+	case hwmon_power_input:
+		return sfp_hwmon_read_rx_power(sfp, SFP_RX_POWER, value);
+
+	case hwmon_power_lcrit:
+		*value = be16_to_cpu(sfp->diag.rxpwr_low_alarm);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_min:
+		*value = be16_to_cpu(sfp->diag.rxpwr_low_warn);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_max:
+		*value = be16_to_cpu(sfp->diag.rxpwr_high_warn);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_crit:
+		*value = be16_to_cpu(sfp->diag.rxpwr_high_alarm);
+		sfp_hwmon_to_rx_power(value);
+		return 0;
+
+	case hwmon_power_lcrit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM1_RXPWR_LOW);
+		return 0;
+
+	case hwmon_power_min_alarm:
+		err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN1_RXPWR_LOW);
+		return 0;
+
+	case hwmon_power_max_alarm:
+		err = sfp_read(sfp, true, SFP_WARN1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_WARN1_RXPWR_HIGH);
+		return 0;
+
+	case hwmon_power_crit_alarm:
+		err = sfp_read(sfp, true, SFP_ALARM1, &status, sizeof(status));
+		if (err < 0)
+			return err;
+
+		*value = !!(status & SFP_ALARM1_RXPWR_HIGH);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int sfp_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
+			  u32 attr, int channel, long *value)
+{
+	struct sfp *sfp = dev_get_drvdata(dev);
+
+	switch (type) {
+	case hwmon_temp:
+		return sfp_hwmon_temp(sfp, attr, value);
+	case hwmon_in:
+		return sfp_hwmon_vcc(sfp, attr, value);
+	case hwmon_curr:
+		return sfp_hwmon_bias(sfp, attr, value);
+	case hwmon_power:
+		switch (channel) {
+		case 0:
+			return sfp_hwmon_tx_power(sfp, attr, value);
+		case 1:
+			return sfp_hwmon_rx_power(sfp, attr, value);
+		default:
+			return -EOPNOTSUPP;
+		}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct hwmon_ops sfp_hwmon_ops = {
+	.is_visible = sfp_hwmon_is_visible,
+	.read = sfp_hwmon_read,
+};
+
+static u32 sfp_hwmon_chip_config[] = {
+	HWMON_C_REGISTER_TZ,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_chip = {
+	.type = hwmon_chip,
+	.config = sfp_hwmon_chip_config,
+};
+
+static u32 sfp_hwmon_temp_config[] = {
+	HWMON_T_INPUT |
+	HWMON_T_MAX | HWMON_T_MIN |
+	HWMON_T_MAX_ALARM | HWMON_T_MIN_ALARM |
+	HWMON_T_CRIT | HWMON_T_LCRIT |
+	HWMON_T_CRIT_ALARM | HWMON_T_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_temp_channel_info = {
+	.type = hwmon_temp,
+	.config = sfp_hwmon_temp_config,
+};
+
+static u32 sfp_hwmon_vcc_config[] = {
+	HWMON_I_INPUT |
+	HWMON_I_MAX | HWMON_I_MIN |
+	HWMON_I_MAX_ALARM | HWMON_I_MIN_ALARM |
+	HWMON_I_CRIT | HWMON_I_LCRIT |
+	HWMON_I_CRIT_ALARM | HWMON_I_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_vcc_channel_info = {
+	.type = hwmon_in,
+	.config = sfp_hwmon_vcc_config,
+};
+
+static u32 sfp_hwmon_bias_config[] = {
+	HWMON_C_INPUT |
+	HWMON_C_MAX | HWMON_C_MIN |
+	HWMON_C_MAX_ALARM | HWMON_C_MIN_ALARM |
+	HWMON_C_CRIT | HWMON_C_LCRIT |
+	HWMON_C_CRIT_ALARM | HWMON_C_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_bias_channel_info = {
+	.type = hwmon_curr,
+	.config = sfp_hwmon_bias_config,
+};
+
+static u32 sfp_hwmon_power_config[] = {
+	/* Transmit power */
+	HWMON_P_INPUT |
+	HWMON_P_MAX | HWMON_P_MIN |
+	HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM |
+	HWMON_P_CRIT | HWMON_P_LCRIT |
+	HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM,
+	/* Receive power */
+	HWMON_P_INPUT |
+	HWMON_P_MAX | HWMON_P_MIN |
+	HWMON_P_MAX_ALARM | HWMON_P_MIN_ALARM |
+	HWMON_P_CRIT | HWMON_P_LCRIT |
+	HWMON_P_CRIT_ALARM | HWMON_P_LCRIT_ALARM,
+	0,
+};
+
+static const struct hwmon_channel_info sfp_hwmon_power_channel_info = {
+	.type = hwmon_power,
+	.config = sfp_hwmon_power_config,
+};
+
+static const struct hwmon_channel_info *sfp_hwmon_info[] = {
+	&sfp_hwmon_chip,
+	&sfp_hwmon_vcc_channel_info,
+	&sfp_hwmon_temp_channel_info,
+	&sfp_hwmon_bias_channel_info,
+	&sfp_hwmon_power_channel_info,
+	NULL,
+};
+
+static const struct hwmon_chip_info sfp_hwmon_chip_info = {
+	.ops = &sfp_hwmon_ops,
+	.info = sfp_hwmon_info,
+};
+
+static int sfp_hwmon_insert(struct sfp *sfp)
+{
+	int err, i;
+
+	if (sfp->id.ext.sff8472_compliance == SFP_SFF8472_COMPLIANCE_NONE)
+		return 0;
+
+	if (!(sfp->id.ext.diagmon & SFP_DIAGMON_DDM))
+		return 0;
+
+	if (sfp->id.ext.diagmon & SFP_DIAGMON_ADDRMODE)
+		/* This driver in general does not support address
+		 * change.
+		 */
+		return 0;
+
+	err = sfp_read(sfp, true, 0, &sfp->diag, sizeof(sfp->diag));
+	if (err < 0)
+		return err;
+
+	sfp->hwmon_name = kstrdup(dev_name(sfp->dev), GFP_KERNEL);
+	if (!sfp->hwmon_name)
+		return -ENODEV;
+
+	for (i = 0; sfp->hwmon_name[i]; i++)
+		if (hwmon_is_bad_char(sfp->hwmon_name[i]))
+			sfp->hwmon_name[i] = '_';
+
+	sfp->hwmon_dev = hwmon_device_register_with_info(sfp->dev,
+							 sfp->hwmon_name, sfp,
+							 &sfp_hwmon_chip_info,
+							 NULL);
+
+	return PTR_ERR_OR_ZERO(sfp->hwmon_dev);
+}
+
+static void sfp_hwmon_remove(struct sfp *sfp)
+{
+	hwmon_device_unregister(sfp->hwmon_dev);
+	kfree(sfp->hwmon_name);
+}
+#else
+static int sfp_hwmon_insert(struct sfp *sfp)
+{
+	return 0;
+}
+
+static void sfp_hwmon_remove(struct sfp *sfp)
+{
+}
+#endif
+
 /* Helpers */
 static void sfp_module_tx_disable(struct sfp *sfp)
 {
@@ -636,6 +1357,10 @@ static int sfp_sm_mod_probe(struct sfp *sfp)
 		dev_warn(sfp->dev,
 			 "module address swap to access page 0xA2 is not supported.\n");
 
+	ret = sfp_hwmon_insert(sfp);
+	if (ret < 0)
+		return ret;
+
 	ret = sfp_module_insert(sfp->sfp_bus, &sfp->id);
 	if (ret < 0)
 		return ret;
@@ -647,6 +1372,8 @@ static void sfp_sm_mod_remove(struct sfp *sfp)
 {
 	sfp_module_remove(sfp->sfp_bus);
 
+	sfp_hwmon_remove(sfp);
+
 	if (sfp->mod_phy)
 		sfp_sm_phy_detach(sfp);
 
diff --git a/include/linux/sfp.h b/include/linux/sfp.h
index ebce9e24906a..d37518e89db2 100644
--- a/include/linux/sfp.h
+++ b/include/linux/sfp.h
@@ -231,6 +231,50 @@ struct sfp_eeprom_id {
 	struct sfp_eeprom_ext ext;
 } __packed;
 
+struct sfp_diag {
+	__be16 temp_high_alarm;
+	__be16 temp_low_alarm;
+	__be16 temp_high_warn;
+	__be16 temp_low_warn;
+	__be16 volt_high_alarm;
+	__be16 volt_low_alarm;
+	__be16 volt_high_warn;
+	__be16 volt_low_warn;
+	__be16 bias_high_alarm;
+	__be16 bias_low_alarm;
+	__be16 bias_high_warn;
+	__be16 bias_low_warn;
+	__be16 txpwr_high_alarm;
+	__be16 txpwr_low_alarm;
+	__be16 txpwr_high_warn;
+	__be16 txpwr_low_warn;
+	__be16 rxpwr_high_alarm;
+	__be16 rxpwr_low_alarm;
+	__be16 rxpwr_high_warn;
+	__be16 rxpwr_low_warn;
+	__be16 laser_temp_high_alarm;
+	__be16 laser_temp_low_alarm;
+	__be16 laser_temp_high_warn;
+	__be16 laser_temp_low_warn;
+	__be16 tec_cur_high_alarm;
+	__be16 tec_cur_low_alarm;
+	__be16 tec_cur_high_warn;
+	__be16 tec_cur_low_warn;
+	__be32 cal_rxpwr4;
+	__be32 cal_rxpwr3;
+	__be32 cal_rxpwr2;
+	__be32 cal_rxpwr1;
+	__be32 cal_rxpwr0;
+	__be16 cal_txi_slope;
+	__be16 cal_txi_offset;
+	__be16 cal_txpwr_slope;
+	__be16 cal_txpwr_offset;
+	__be16 cal_t_slope;
+	__be16 cal_t_offset;
+	__be16 cal_v_slope;
+	__be16 cal_v_offset;
+} __packed;
+
 /* SFP EEPROM registers */
 enum {
 	SFP_PHYS_ID			= 0x00,
@@ -384,7 +428,33 @@ enum {
 	SFP_TEC_CUR			= 0x6c,
 
 	SFP_STATUS			= 0x6e,
-	SFP_ALARM			= 0x70,
+	SFP_ALARM0			= 0x70,
+	SFP_ALARM0_TEMP_HIGH		= BIT(7),
+	SFP_ALARM0_TEMP_LOW		= BIT(6),
+	SFP_ALARM0_VCC_HIGH		= BIT(5),
+	SFP_ALARM0_VCC_LOW		= BIT(4),
+	SFP_ALARM0_TX_BIAS_HIGH		= BIT(3),
+	SFP_ALARM0_TX_BIAS_LOW		= BIT(2),
+	SFP_ALARM0_TXPWR_HIGH		= BIT(1),
+	SFP_ALARM0_TXPWR_LOW		= BIT(0),
+
+	SFP_ALARM1			= 0x71,
+	SFP_ALARM1_RXPWR_HIGH		= BIT(7),
+	SFP_ALARM1_RXPWR_LOW		= BIT(6),
+
+	SFP_WARN0			= 0x74,
+	SFP_WARN0_TEMP_HIGH		= BIT(7),
+	SFP_WARN0_TEMP_LOW		= BIT(6),
+	SFP_WARN0_VCC_HIGH		= BIT(5),
+	SFP_WARN0_VCC_LOW		= BIT(4),
+	SFP_WARN0_TX_BIAS_HIGH		= BIT(3),
+	SFP_WARN0_TX_BIAS_LOW		= BIT(2),
+	SFP_WARN0_TXPWR_HIGH		= BIT(1),
+	SFP_WARN0_TXPWR_LOW		= BIT(0),
+
+	SFP_WARN1			= 0x75,
+	SFP_WARN1_RXPWR_HIGH		= BIT(7),
+	SFP_WARN1_RXPWR_LOW		= BIT(6),
 
 	SFP_EXT_STATUS			= 0x76,
 	SFP_VSL				= 0x78,
-- 
cgit v1.2.3


From 07df5bd874f05fbbe694b75df12694f51c344311 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 17 Jul 2018 21:21:37 +0200
Subject: r8169: power down chip in probe

The removed code would be called in two situations:
1. interface is brought up never or >10s after driver load
2. after close()

Case 1 we can handle cleaner by ensuring chip is powered down when
leaving probe(). open() callback will power up the chip.

In case 2 we call rtl_pll_power_down() twice currently, from the
close() callback and 10s later when entering runtime-suspend.
This is avoided by this patch.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 261fdfad75c2..3d50378a11d7 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6965,10 +6965,8 @@ static int rtl8169_runtime_suspend(struct device *device)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct rtl8169_private *tp = netdev_priv(dev);
 
-	if (!tp->TxDescArray) {
-		rtl_pll_power_down(tp);
+	if (!tp->TxDescArray)
 		return 0;
-	}
 
 	rtl_lock_work(tp);
 	__rtl8169_set_wol(tp, WAKE_ANY);
@@ -7485,6 +7483,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		return rc;
 
+	/* chip gets powered up in rtl_open() */
+	rtl_pll_power_down(tp);
+
 	rc = register_netdev(dev);
 	if (rc)
 		goto err_mdio_unregister;
-- 
cgit v1.2.3


From 8ddd6efa56c3fe23df9fe4cf5e2b49cc55416ef4 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Fri, 22 Jun 2018 09:15:31 +1000
Subject: random: Fix whitespace pre random-bytes work

There are a couple of whitespace issues around the function
get_random_bytes_arch().  In preparation for patching this function
let's clean them up.

Acked-by: Theodore Ts'o <tytso@mit.edu>
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index bd449ad52442..8e53e9515a1d 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1737,7 +1737,7 @@ void get_random_bytes_arch(void *buf, int nbytes)
 
 		if (!arch_get_random_long(&v))
 			break;
-		
+
 		memcpy(p, &v, chunk);
 		p += chunk;
 		nbytes -= chunk;
@@ -1748,7 +1748,6 @@ void get_random_bytes_arch(void *buf, int nbytes)
 }
 EXPORT_SYMBOL(get_random_bytes_arch);
 
-
 /*
  * init_std_data - initialize pool with system data
  *
-- 
cgit v1.2.3


From 753d433b586d1d43c487e3d660f5778c7c8d58ea Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Fri, 22 Jun 2018 09:15:32 +1000
Subject: random: Return nbytes filled from hw RNG

Currently the function get_random_bytes_arch() has return value 'void'.
If the hw RNG fails we currently fall back to using get_random_bytes().
This defeats the purpose of requesting random material from the hw RNG
in the first place.

There are currently no intree users of get_random_bytes_arch().

Only get random bytes from the hw RNG, make function return the number
of bytes retrieved from the hw RNG.

Acked-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c  | 16 +++++++++-------
 include/linux/random.h |  2 +-
 2 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 8e53e9515a1d..34ddfd57419b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1725,26 +1725,28 @@ EXPORT_SYMBOL(del_random_ready_callback);
  * key known by the NSA).  So it's useful if we need the speed, but
  * only if we're willing to trust the hardware manufacturer not to
  * have put in a back door.
+ *
+ * Return number of bytes filled in.
  */
-void get_random_bytes_arch(void *buf, int nbytes)
+int __must_check get_random_bytes_arch(void *buf, int nbytes)
 {
+	int left = nbytes;
 	char *p = buf;
 
-	trace_get_random_bytes_arch(nbytes, _RET_IP_);
-	while (nbytes) {
+	trace_get_random_bytes_arch(left, _RET_IP_);
+	while (left) {
 		unsigned long v;
-		int chunk = min(nbytes, (int)sizeof(unsigned long));
+		int chunk = min_t(int, left, sizeof(unsigned long));
 
 		if (!arch_get_random_long(&v))
 			break;
 
 		memcpy(p, &v, chunk);
 		p += chunk;
-		nbytes -= chunk;
+		left -= chunk;
 	}
 
-	if (nbytes)
-		get_random_bytes(p, nbytes);
+	return nbytes - left;
 }
 EXPORT_SYMBOL(get_random_bytes_arch);
 
diff --git a/include/linux/random.h b/include/linux/random.h
index 2ddf13b4281e..f1c9bc5cd231 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -38,7 +38,7 @@ extern void get_random_bytes(void *buf, int nbytes);
 extern int wait_for_random_bytes(void);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
 extern void del_random_ready_callback(struct random_ready_callback *rdy);
-extern void get_random_bytes_arch(void *buf, int nbytes);
+extern int __must_check get_random_bytes_arch(void *buf, int nbytes);
 
 #ifndef MODULE
 extern const struct file_operations random_fops, urandom_fops;
-- 
cgit v1.2.3


From 1c4facb846c7f863bc65483394e80acdbacf671b Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Fri, 22 Jun 2018 09:15:33 +1000
Subject: vsprintf: Use hw RNG for ptr_key

Currently we must wait for enough entropy to become available before
hashed pointers can be printed.  We can remove this wait by using the
hw RNG if available.

Use hw RNG to get keying material.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Suggested-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 lib/vsprintf.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index a48aaa79d352..6c1fb395bddf 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1675,8 +1675,16 @@ static struct random_ready_callback random_ready = {
 
 static int __init initialize_ptr_random(void)
 {
-	int ret = add_random_ready_callback(&random_ready);
+	int key_size = sizeof(ptr_key);
+	int ret;
+
+	/* Use hw RNG if available. */
+	if (get_random_bytes_arch(&ptr_key, key_size) == key_size) {
+		static_branch_disable(&not_filled_random_ptr_key);
+		return 0;
+	}
 
+	ret = add_random_ready_callback(&random_ready);
 	if (!ret) {
 		return 0;
 	} else if (ret == -EALREADY) {
-- 
cgit v1.2.3


From 3672476edaa0660eb833f54fa9edeb505417b75c Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Fri, 22 Jun 2018 09:15:34 +1000
Subject: vsprintf: Add command line option debug_boot_weak_hash

Currently printing [hashed] pointers requires enough entropy to be
available.  Early in the boot sequence this may not be the case
resulting in a dummy string '(____ptrval____)' being printed.  This
makes debugging the early boot sequence difficult.  We can relax the
requirement to use cryptographically secure hashing during debugging.
This enables debugging while keeping development/production kernel
behaviour the same.

If new command line option debug_boot_weak_hash is enabled use
cryptographically insecure hashing and hash pointer value immediately.

Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/admin-guide/kernel-parameters.txt |  8 ++++++++
 lib/vsprintf.c                                  | 17 +++++++++++++++++
 2 files changed, 25 insertions(+)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..0c8f7889efa1 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -748,6 +748,14 @@
 
 	debug		[KNL] Enable kernel debugging (events log level).
 
+	debug_boot_weak_hash
+			[KNL] Enable printing [hashed] pointers early in the
+			boot sequence.  If enabled, we use a weak hash instead
+			of siphash to hash pointers.  Use this option if you are
+			seeing instances of '(___ptrval___)') and need to see a
+			value (hashed pointer) instead. Cryptographically
+			insecure, please do not use on production kernels.
+
 	debug_locks_verbose=
 			[KNL] verbose self-tests
 			Format=<0|1>
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 6c1fb395bddf..1ee2829f3b54 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1651,6 +1651,17 @@ char *device_node_string(char *buf, char *end, struct device_node *dn,
 	return widen_string(buf, buf - buf_start, end, spec);
 }
 
+/* Make pointers available for printing early in the boot sequence. */
+static int debug_boot_weak_hash __ro_after_init;
+
+static int __init debug_boot_weak_hash_enable(char *str)
+{
+	debug_boot_weak_hash = 1;
+	pr_info("debug_boot_weak_hash enabled\n");
+	return 0;
+}
+early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable);
+
 static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key);
 static siphash_key_t ptr_key __read_mostly;
 
@@ -1703,6 +1714,12 @@ static char *ptr_to_id(char *buf, char *end, void *ptr, struct printf_spec spec)
 	const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)";
 	unsigned long hashval;
 
+	/* When debugging early boot use non-cryptographically secure hash. */
+	if (unlikely(debug_boot_weak_hash)) {
+		hashval = hash_long((unsigned long)ptr, 32);
+		return pointer_string(buf, end, (const void *)hashval, spec);
+	}
+
 	if (static_branch_unlikely(&not_filled_random_ptr_key)) {
 		spec.field_width = 2 * sizeof(ptr);
 		/* string length must be less than default_width */
-- 
cgit v1.2.3


From 83a68a06795fa47e77ea758f293a5946e9e02e84 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jul 2018 22:23:37 +0200
Subject: security: export security_kernel_load_data function

The firmware_loader can be built as a loadable module, which now
fails when CONFIG_SECURITY is enabled, because a call to the
security_kernel_load_data() function got added, and this is
not exported to modules:

ERROR: "security_kernel_load_data" [drivers/base/firmware_loader/firmware_class.ko] undefined!

Add an EXPORT_SYMBOL_GPL() to make it available here.

Fixes: 6e852651f28e ("firmware: add call to LSM hook before firmware sysfs fallback")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 security/security.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/security/security.c b/security/security.c
index 4927e7cc7d96..6e149d0ffe33 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1065,6 +1065,7 @@ int security_kernel_load_data(enum kernel_load_data_id id)
 		return ret;
 	return ima_load_data(id);
 }
+EXPORT_SYMBOL_GPL(security_kernel_load_data);
 
 int security_task_fix_setuid(struct cred *new, const struct cred *old,
 			     int flags)
-- 
cgit v1.2.3


From 87ea58433208d17295e200d56be5e2a4fe4ce7d6 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Jul 2018 10:36:04 -0700
Subject: security: check for kstrdup() failure in lsm_append()

lsm_append() should return -ENOMEM if memory allocation failed.

Fixes: d69dece5f5b6 ("LSM: Add /sys/kernel/security/lsm")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: James Morris <james.morris@microsoft.com>
---
 security/security.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/security/security.c b/security/security.c
index 6e149d0ffe33..b49ee810371b 100644
--- a/security/security.c
+++ b/security/security.c
@@ -118,6 +118,8 @@ static int lsm_append(char *new, char **result)
 
 	if (*result == NULL) {
 		*result = kstrdup(new, GFP_KERNEL);
+		if (*result == NULL)
+			return -ENOMEM;
 	} else {
 		/* Check if it is the last registered name */
 		if (match_last_lsm(*result, new))
-- 
cgit v1.2.3


From d85458256ad2583df95deb0bb7a3403b74be177a Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 14 Jul 2018 11:45:53 +0200
Subject: net: phy: realtek: Support RTL8366RB variant
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The RTL8366RB is an ASIC with five internal PHYs for
LAN0..LAN3 and WAN. The PHYs are spawn off the main
device so they can be handled in a distributed manner
by the Realtek PHY driver. All that is really needed
is the power save feature enablement and letting the
PHY driver core pick up the IRQ from the switch chip.

Cc: Antti Seppälä <a.seppala@gmail.com>
Cc: Roman Yeryomin <roman@advem.lv>
Cc: Colin Leitner <colin.leitner@googlemail.com>
Cc: Gabor Juhos <juhosg@openwrt.org>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 0610148cc1ff..7fc8508b5231 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -37,6 +37,9 @@
 #define RTL8201F_ISR				0x1e
 #define RTL8201F_IER				0x13
 
+#define RTL8366RB_POWER_SAVE			0x15
+#define RTL8366RB_POWER_SAVE_ON			BIT(12)
+
 MODULE_DESCRIPTION("Realtek PHY driver");
 MODULE_AUTHOR("Johnson Leung");
 MODULE_LICENSE("GPL");
@@ -190,6 +193,24 @@ static int rtl8211b_resume(struct phy_device *phydev)
 	return genphy_resume(phydev);
 }
 
+static int rtl8366rb_config_init(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = genphy_config_init(phydev);
+	if (ret < 0)
+		return ret;
+
+	ret = phy_set_bits(phydev, RTL8366RB_POWER_SAVE,
+			   RTL8366RB_POWER_SAVE_ON);
+	if (ret) {
+		dev_err(&phydev->mdio.dev,
+			"error enabling power management\n");
+	}
+
+	return ret;
+}
+
 static struct phy_driver realtek_drvs[] = {
 	{
 		.phy_id         = 0x00008201,
@@ -270,6 +291,15 @@ static struct phy_driver realtek_drvs[] = {
 		.resume		= genphy_resume,
 		.read_page	= rtl821x_read_page,
 		.write_page	= rtl821x_write_page,
+	}, {
+		.phy_id		= 0x001cc961,
+		.name		= "RTL8366RB Gigabit Ethernet",
+		.phy_id_mask	= 0x001fffff,
+		.features	= PHY_GBIT_FEATURES,
+		.flags		= PHY_HAS_INTERRUPT,
+		.config_init	= &rtl8366rb_config_init,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
 	},
 };
 
@@ -283,6 +313,7 @@ static struct mdio_device_id __maybe_unused realtek_tbl[] = {
 	{ 0x001cc914, 0x001fffff },
 	{ 0x001cc915, 0x001fffff },
 	{ 0x001cc916, 0x001fffff },
+	{ 0x001cc961, 0x001fffff },
 	{ }
 };
 
-- 
cgit v1.2.3


From 3b3b6b460f78101294d7185a3eae8ed6ad920ab3 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 14 Jul 2018 11:45:54 +0200
Subject: net: dsa: Add bindings for Realtek SMI DSAs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The Realtek SMI family is a set of DSA chips that provide
switching in routers. This binding just follows the pattern
set by other switches but with the introduction of an embedded
irqchip to demux and handle the interrupts fired by the single
line from the chip.

This interrupt construction is similar to how we handle
interrupt controllers inside PCI bridges etc.

Cc: Antti Seppälä <a.seppala@gmail.com>
Cc: Roman Yeryomin <roman@advem.lv>
Cc: Colin Leitner <colin.leitner@googlemail.com>
Cc: Gabor Juhos <juhosg@openwrt.org>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: devicetree@vger.kernel.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../devicetree/bindings/net/dsa/realtek-smi.txt    | 153 +++++++++++++++++++++
 1 file changed, 153 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/dsa/realtek-smi.txt

diff --git a/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt b/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt
new file mode 100644
index 000000000000..b6ae8541bd55
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/dsa/realtek-smi.txt
@@ -0,0 +1,153 @@
+Realtek SMI-based Switches
+==========================
+
+The SMI "Simple Management Interface" is a two-wire protocol using
+bit-banged GPIO that while it reuses the MDIO lines MCK and MDIO does
+not use the MDIO protocol. This binding defines how to specify the
+SMI-based Realtek devices.
+
+Required properties:
+
+- compatible: must be exactly one of:
+      "realtek,rtl8366"
+      "realtek,rtl8366rb" (4+1 ports)
+      "realtek,rtl8366s"  (4+1 ports)
+      "realtek,rtl8367"
+      "realtek,rtl8367b"
+      "realtek,rtl8368s"  (8 port)
+      "realtek,rtl8369"
+      "realtek,rtl8370"   (8 port)
+
+Required properties:
+- mdc-gpios: GPIO line for the MDC clock line.
+- mdio-gpios: GPIO line for the MDIO data line.
+- reset-gpios: GPIO line for the reset signal.
+
+Optional properties:
+- realtek,disable-leds: if the LED drivers are not used in the
+  hardware design this will disable them so they are not turned on
+  and wasting power.
+
+Required subnodes:
+
+- interrupt-controller
+
+  This defines an interrupt controller with an IRQ line (typically
+  a GPIO) that will demultiplex and handle the interrupt from the single
+  interrupt line coming out of one of the SMI-based chips. It most
+  importantly provides link up/down interrupts to the PHY blocks inside
+  the ASIC.
+
+Required properties of interrupt-controller:
+
+- interrupt: parent interrupt, see interrupt-controller/interrupts.txt
+- interrupt-controller: see interrupt-controller/interrupts.txt
+- #address-cells: should be <0>
+- #interrupt-cells: should be <1>
+
+- mdio
+
+  This defines the internal MDIO bus of the SMI device, mostly for the
+  purpose of being able to hook the interrupts to the right PHY and
+  the right PHY to the corresponding port.
+
+Required properties of mdio:
+
+- compatible: should be set to "realtek,smi-mdio" for all SMI devices
+
+See net/mdio.txt for additional MDIO bus properties.
+
+See net/dsa/dsa.txt for a list of additional required and optional properties
+and subnodes of DSA switches.
+
+Examples:
+
+switch {
+	compatible = "realtek,rtl8366rb";
+	/* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */
+	mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>;
+	mdio-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>;
+	reset-gpios = <&gpio0 14 GPIO_ACTIVE_LOW>;
+
+	switch_intc: interrupt-controller {
+		/* GPIO 15 provides the interrupt */
+		interrupt-parent = <&gpio0>;
+		interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
+		interrupt-controller;
+		#address-cells = <0>;
+		#interrupt-cells = <1>;
+	};
+
+	ports {
+		#address-cells = <1>;
+		#size-cells = <0>;
+		reg = <0>;
+		port@0 {
+			reg = <0>;
+			label = "lan0";
+			phy-handle = <&phy0>;
+		};
+		port@1 {
+			reg = <1>;
+			label = "lan1";
+			phy-handle = <&phy1>;
+		};
+		port@2 {
+			reg = <2>;
+			label = "lan2";
+			phy-handle = <&phy2>;
+		};
+		port@3 {
+			reg = <3>;
+			label = "lan3";
+			phy-handle = <&phy3>;
+		};
+		port@4 {
+			reg = <4>;
+			label = "wan";
+			phy-handle = <&phy4>;
+		};
+		port@5 {
+			reg = <5>;
+			label = "cpu";
+			ethernet = <&gmac0>;
+			phy-mode = "rgmii";
+			fixed-link {
+				speed = <1000>;
+				full-duplex;
+			};
+		};
+	};
+
+	mdio {
+		compatible = "realtek,smi-mdio", "dsa-mdio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+
+		phy0: phy@0 {
+			reg = <0>;
+			interrupt-parent = <&switch_intc>;
+			interrupts = <0>;
+		};
+		phy1: phy@1 {
+			reg = <1>;
+			interrupt-parent = <&switch_intc>;
+			interrupts = <1>;
+		};
+		phy2: phy@2 {
+			reg = <2>;
+			interrupt-parent = <&switch_intc>;
+			interrupts = <2>;
+		};
+		phy3: phy@3 {
+			reg = <3>;
+			interrupt-parent = <&switch_intc>;
+			interrupts = <3>;
+		};
+		phy4: phy@4 {
+			reg = <4>;
+			interrupt-parent = <&switch_intc>;
+			interrupts = <12>;
+		};
+	};
+};
-- 
cgit v1.2.3


From d8652956cf37c5caa8c19e0b99ce5ca235c6d5de Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 14 Jul 2018 11:45:55 +0200
Subject: net: dsa: realtek-smi: Add Realtek SMI driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This adds a driver core for the Realtek SMI chips and a
subdriver for the RTL8366RB. I just added this chip simply
because it is all I can test.

The code is a massaged variant of the code that has been
sitting out-of-tree in OpenWRT for years in the absence of
a proper switch subsystem. This creates a DSA driver for it.
I have tried to credit the original authors wherever
possible.

The main changes I've done from the OpenWRT code:

- Added an IRQ chip inside the RTL8366RB switch to demux and
  handle the line state IRQs.

- Distributed the phy handling out to the PHY driver.

- Added some RTL8366RB code that was missing in the driver at
  the time, such as setting up "green ethernet" with a funny
  jam table and forcing MAC5 (the CPU port) into 1 GBit.

- Select jam table and add the default jam table from the
  vendor driver, also for ASIC "version 0" if need be.

- Do not store jam tables in the device tree, store them
  in the driver.

- Pick in the "initvals" jam tables from OpenWRT's driver
  and make those get selected per compatible for the
  whole system. It's apparently about electrical settings
  for this system and whatnot, not really configuration
  from device tree.

- Implemented LED control: beware of bugs because there are
  no LEDs on the device I am using!

We do not implement custom DSA tags. This is explained in
a comment in the driver as well: this "tagging protocol" is
not simply a few extra bytes tagged on to the ethernet
frame as DSA is used to. Instead, enabling the CPU tags
will make the switch start talking Realtek RRCP internally.
For example a simple ping will make this kind of packets
appear inside the switch:

0000   ff ff ff ff ff ff bc ae c5 6b a8 3d 88 99 a2 00
0010   08 06 00 01 08 00 06 04 00 01 bc ae c5 6b a8 3d
0020   a9 fe 01 01 00 00 00 00 00 00 a9 fe 01 02 00 00
0030   00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00

As you can see a custom "8899" tagged packet using the
protocol 0xa2. Norm RRCP appears to always have this
protocol set to 0x01 according to OpenRRCP. You can also
see that this is not a ping packet at all, instead the
switch is starting to talk network management issues
with the CPU port.

So for now custom "tagging" is disabled.

This was tested on the D-Link DIR-685 with initramfs and
OpenWRT userspaces and works fine on all the LAN ports
(lan0 .. lan3). The WAN port is yet not working.

Cc: Antti Seppälä <a.seppala@gmail.com>
Cc: Roman Yeryomin <roman@advem.lv>
Cc: Colin Leitner <colin.leitner@googlemail.com>
Cc: Gabor Juhos <juhosg@openwrt.org>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 MAINTAINERS                   |    7 +
 drivers/net/dsa/Kconfig       |   11 +
 drivers/net/dsa/Makefile      |    2 +
 drivers/net/dsa/realtek-smi.c |  487 ++++++++++++++
 drivers/net/dsa/realtek-smi.h |  144 +++++
 drivers/net/dsa/rtl8366.c     |  516 +++++++++++++++
 drivers/net/dsa/rtl8366rb.c   | 1424 +++++++++++++++++++++++++++++++++++++++++
 7 files changed, 2591 insertions(+)
 create mode 100644 drivers/net/dsa/realtek-smi.c
 create mode 100644 drivers/net/dsa/realtek-smi.h
 create mode 100644 drivers/net/dsa/rtl8366.c
 create mode 100644 drivers/net/dsa/rtl8366rb.c

diff --git a/MAINTAINERS b/MAINTAINERS
index b40d702337f2..130ff2f4d33a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12063,6 +12063,13 @@ S:	Maintained
 F:	sound/soc/codecs/rt*
 F:	include/sound/rt*.h
 
+REALTEK RTL83xx SMI DSA ROUTER CHIPS
+M:	Linus Walleij <linus.walleij@linaro.org>
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/dsa/realtek-smi.txt
+F:	drivers/net/dsa/realtek-smi*
+F:	drivers/net/dsa/rtl83*
+
 REGISTER MAP ABSTRACTION
 M:	Mark Brown <broonie@kernel.org>
 L:	linux-kernel@vger.kernel.org
diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 733653d8359a..0b76a3a6977e 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -52,6 +52,17 @@ config NET_DSA_QCA8K
 	  This enables support for the Qualcomm Atheros QCA8K Ethernet
 	  switch chips.
 
+config NET_DSA_REALTEK_SMI
+	tristate "Realtek SMI Ethernet switch family support"
+	depends on NET_DSA
+	select FIXED_PHY
+	select IRQ_DOMAIN
+	select REALTEK_PHY
+	select REGMAP
+	---help---
+	  This enables support for the Realtek SMI-based switch
+	  chips, currently only RTL8366RB.
+
 config NET_DSA_SMSC_LAN9303
 	tristate
 	select NET_DSA_TAG_LAN9303
diff --git a/drivers/net/dsa/Makefile b/drivers/net/dsa/Makefile
index d4f873ae2f6a..46c1cba91ffe 100644
--- a/drivers/net/dsa/Makefile
+++ b/drivers/net/dsa/Makefile
@@ -8,6 +8,8 @@ endif
 obj-$(CONFIG_NET_DSA_MT7530)	+= mt7530.o
 obj-$(CONFIG_NET_DSA_MV88E6060) += mv88e6060.o
 obj-$(CONFIG_NET_DSA_QCA8K)	+= qca8k.o
+obj-$(CONFIG_NET_DSA_REALTEK_SMI) += realtek.o
+realtek-objs			:= realtek-smi.o rtl8366.o rtl8366rb.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303) += lan9303-core.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303_I2C) += lan9303_i2c.o
 obj-$(CONFIG_NET_DSA_SMSC_LAN9303_MDIO) += lan9303_mdio.o
diff --git a/drivers/net/dsa/realtek-smi.c b/drivers/net/dsa/realtek-smi.c
new file mode 100644
index 000000000000..f941f4582825
--- /dev/null
+++ b/drivers/net/dsa/realtek-smi.c
@@ -0,0 +1,487 @@
+// SPDX-License-Identifier: GPL-2.0+
+/* Realtek Simple Management Interface (SMI) driver
+ * It can be discussed how "simple" this interface is.
+ *
+ * The SMI protocol piggy-backs the MDIO MDC and MDIO signals levels
+ * but the protocol is not MDIO at all. Instead it is a Realtek
+ * pecularity that need to bit-bang the lines in a special way to
+ * communicate with the switch.
+ *
+ * ASICs we intend to support with this driver:
+ *
+ * RTL8366   - The original version, apparently
+ * RTL8369   - Similar enough to have the same datsheet as RTL8366
+ * RTL8366RB - Probably reads out "RTL8366 revision B", has a quite
+ *             different register layout from the other two
+ * RTL8366S  - Is this "RTL8366 super"?
+ * RTL8367   - Has an OpenWRT driver as well
+ * RTL8368S  - Seems to be an alternative name for RTL8366RB
+ * RTL8370   - Also uses SMI
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <linux/skbuff.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_mdio.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/bitops.h>
+#include <linux/if_bridge.h>
+
+#include "realtek-smi.h"
+
+#define REALTEK_SMI_ACK_RETRY_COUNT		5
+#define REALTEK_SMI_HW_STOP_DELAY		25	/* msecs */
+#define REALTEK_SMI_HW_START_DELAY		100	/* msecs */
+
+static inline void realtek_smi_clk_delay(struct realtek_smi *smi)
+{
+	ndelay(smi->clk_delay);
+}
+
+static void realtek_smi_start(struct realtek_smi *smi)
+{
+	/* Set GPIO pins to output mode, with initial state:
+	 * SCK = 0, SDA = 1
+	 */
+	gpiod_direction_output(smi->mdc, 0);
+	gpiod_direction_output(smi->mdio, 1);
+	realtek_smi_clk_delay(smi);
+
+	/* CLK 1: 0 -> 1, 1 -> 0 */
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+
+	/* CLK 2: */
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 1);
+}
+
+static void realtek_smi_stop(struct realtek_smi *smi)
+{
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 0);
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdio, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 1);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 1);
+
+	/* Add a click */
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 0);
+	realtek_smi_clk_delay(smi);
+	gpiod_set_value(smi->mdc, 1);
+
+	/* Set GPIO pins to input mode */
+	gpiod_direction_input(smi->mdio);
+	gpiod_direction_input(smi->mdc);
+}
+
+static void realtek_smi_write_bits(struct realtek_smi *smi, u32 data, u32 len)
+{
+	for (; len > 0; len--) {
+		realtek_smi_clk_delay(smi);
+
+		/* Prepare data */
+		gpiod_set_value(smi->mdio, !!(data & (1 << (len - 1))));
+		realtek_smi_clk_delay(smi);
+
+		/* Clocking */
+		gpiod_set_value(smi->mdc, 1);
+		realtek_smi_clk_delay(smi);
+		gpiod_set_value(smi->mdc, 0);
+	}
+}
+
+static void realtek_smi_read_bits(struct realtek_smi *smi, u32 len, u32 *data)
+{
+	gpiod_direction_input(smi->mdio);
+
+	for (*data = 0; len > 0; len--) {
+		u32 u;
+
+		realtek_smi_clk_delay(smi);
+
+		/* Clocking */
+		gpiod_set_value(smi->mdc, 1);
+		realtek_smi_clk_delay(smi);
+		u = !!gpiod_get_value(smi->mdio);
+		gpiod_set_value(smi->mdc, 0);
+
+		*data |= (u << (len - 1));
+	}
+
+	gpiod_direction_output(smi->mdio, 0);
+}
+
+static int realtek_smi_wait_for_ack(struct realtek_smi *smi)
+{
+	int retry_cnt;
+
+	retry_cnt = 0;
+	do {
+		u32 ack;
+
+		realtek_smi_read_bits(smi, 1, &ack);
+		if (ack == 0)
+			break;
+
+		if (++retry_cnt > REALTEK_SMI_ACK_RETRY_COUNT) {
+			dev_err(smi->dev, "ACK timeout\n");
+			return -ETIMEDOUT;
+		}
+	} while (1);
+
+	return 0;
+}
+
+static int realtek_smi_write_byte(struct realtek_smi *smi, u8 data)
+{
+	realtek_smi_write_bits(smi, data, 8);
+	return realtek_smi_wait_for_ack(smi);
+}
+
+static int realtek_smi_write_byte_noack(struct realtek_smi *smi, u8 data)
+{
+	realtek_smi_write_bits(smi, data, 8);
+	return 0;
+}
+
+static int realtek_smi_read_byte0(struct realtek_smi *smi, u8 *data)
+{
+	u32 t;
+
+	/* Read data */
+	realtek_smi_read_bits(smi, 8, &t);
+	*data = (t & 0xff);
+
+	/* Send an ACK */
+	realtek_smi_write_bits(smi, 0x00, 1);
+
+	return 0;
+}
+
+static int realtek_smi_read_byte1(struct realtek_smi *smi, u8 *data)
+{
+	u32 t;
+
+	/* Read data */
+	realtek_smi_read_bits(smi, 8, &t);
+	*data = (t & 0xff);
+
+	/* Send an ACK */
+	realtek_smi_write_bits(smi, 0x01, 1);
+
+	return 0;
+}
+
+static int realtek_smi_read_reg(struct realtek_smi *smi, u32 addr, u32 *data)
+{
+	unsigned long flags;
+	u8 lo = 0;
+	u8 hi = 0;
+	int ret;
+
+	spin_lock_irqsave(&smi->lock, flags);
+
+	realtek_smi_start(smi);
+
+	/* Send READ command */
+	ret = realtek_smi_write_byte(smi, smi->cmd_read);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[7:0] */
+	ret = realtek_smi_write_byte(smi, addr & 0xff);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[15:8] */
+	ret = realtek_smi_write_byte(smi, addr >> 8);
+	if (ret)
+		goto out;
+
+	/* Read DATA[7:0] */
+	realtek_smi_read_byte0(smi, &lo);
+	/* Read DATA[15:8] */
+	realtek_smi_read_byte1(smi, &hi);
+
+	*data = ((u32)lo) | (((u32)hi) << 8);
+
+	ret = 0;
+
+ out:
+	realtek_smi_stop(smi);
+	spin_unlock_irqrestore(&smi->lock, flags);
+
+	return ret;
+}
+
+static int realtek_smi_write_reg(struct realtek_smi *smi,
+				 u32 addr, u32 data, bool ack)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&smi->lock, flags);
+
+	realtek_smi_start(smi);
+
+	/* Send WRITE command */
+	ret = realtek_smi_write_byte(smi, smi->cmd_write);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[7:0] */
+	ret = realtek_smi_write_byte(smi, addr & 0xff);
+	if (ret)
+		goto out;
+
+	/* Set ADDR[15:8] */
+	ret = realtek_smi_write_byte(smi, addr >> 8);
+	if (ret)
+		goto out;
+
+	/* Write DATA[7:0] */
+	ret = realtek_smi_write_byte(smi, data & 0xff);
+	if (ret)
+		goto out;
+
+	/* Write DATA[15:8] */
+	if (ack)
+		ret = realtek_smi_write_byte(smi, data >> 8);
+	else
+		ret = realtek_smi_write_byte_noack(smi, data >> 8);
+	if (ret)
+		goto out;
+
+	ret = 0;
+
+ out:
+	realtek_smi_stop(smi);
+	spin_unlock_irqrestore(&smi->lock, flags);
+
+	return ret;
+}
+
+/* There is one single case when we need to use this accessor and that
+ * is when issueing soft reset. Since the device reset as soon as we write
+ * that bit, no ACK will come back for natural reasons.
+ */
+int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
+				u32 data)
+{
+	return realtek_smi_write_reg(smi, addr, data, false);
+}
+EXPORT_SYMBOL_GPL(realtek_smi_write_reg_noack);
+
+/* Regmap accessors */
+
+static int realtek_smi_write(void *ctx, u32 reg, u32 val)
+{
+	struct realtek_smi *smi = ctx;
+
+	return realtek_smi_write_reg(smi, reg, val, true);
+}
+
+static int realtek_smi_read(void *ctx, u32 reg, u32 *val)
+{
+	struct realtek_smi *smi = ctx;
+
+	return realtek_smi_read_reg(smi, reg, val);
+}
+
+static const struct regmap_config realtek_smi_mdio_regmap_config = {
+	.reg_bits = 10, /* A4..A0 R4..R0 */
+	.val_bits = 16,
+	.reg_stride = 1,
+	/* PHY regs are at 0x8000 */
+	.max_register = 0xffff,
+	.reg_format_endian = REGMAP_ENDIAN_BIG,
+	.reg_read = realtek_smi_read,
+	.reg_write = realtek_smi_write,
+	.cache_type = REGCACHE_NONE,
+};
+
+static int realtek_smi_mdio_read(struct mii_bus *bus, int addr, int regnum)
+{
+	struct realtek_smi *smi = bus->priv;
+
+	return smi->ops->phy_read(smi, addr, regnum);
+}
+
+static int realtek_smi_mdio_write(struct mii_bus *bus, int addr, int regnum,
+				  u16 val)
+{
+	struct realtek_smi *smi = bus->priv;
+
+	return smi->ops->phy_write(smi, addr, regnum, val);
+}
+
+int realtek_smi_setup_mdio(struct realtek_smi *smi)
+{
+	struct device_node *mdio_np;
+	int ret;
+
+	mdio_np = of_find_compatible_node(smi->dev->of_node, NULL,
+					  "realtek,smi-mdio");
+	if (!mdio_np) {
+		dev_err(smi->dev, "no MDIO bus node\n");
+		return -ENODEV;
+	}
+
+	smi->slave_mii_bus = devm_mdiobus_alloc(smi->dev);
+	if (!smi->slave_mii_bus)
+		return -ENOMEM;
+	smi->slave_mii_bus->priv = smi;
+	smi->slave_mii_bus->name = "SMI slave MII";
+	smi->slave_mii_bus->read = realtek_smi_mdio_read;
+	smi->slave_mii_bus->write = realtek_smi_mdio_write;
+	snprintf(smi->slave_mii_bus->id, MII_BUS_ID_SIZE, "SMI-%d",
+		 smi->ds->index);
+	smi->slave_mii_bus->dev.of_node = mdio_np;
+	smi->slave_mii_bus->parent = smi->dev;
+	smi->ds->slave_mii_bus = smi->slave_mii_bus;
+
+	ret = of_mdiobus_register(smi->slave_mii_bus, mdio_np);
+	if (ret) {
+		dev_err(smi->dev, "unable to register MDIO bus %s\n",
+			smi->slave_mii_bus->id);
+		of_node_put(mdio_np);
+	}
+
+	return 0;
+}
+
+static int realtek_smi_probe(struct platform_device *pdev)
+{
+	const struct realtek_smi_variant *var;
+	struct device *dev = &pdev->dev;
+	struct realtek_smi *smi;
+	struct device_node *np;
+	int ret;
+
+	var = of_device_get_match_data(dev);
+	np = dev->of_node;
+
+	smi = devm_kzalloc(dev, sizeof(*smi), GFP_KERNEL);
+	if (!smi)
+		return -ENOMEM;
+	smi->map = devm_regmap_init(dev, NULL, smi,
+				    &realtek_smi_mdio_regmap_config);
+	if (IS_ERR(smi->map)) {
+		ret = PTR_ERR(smi->map);
+		dev_err(dev, "regmap init failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Link forward and backward */
+	smi->dev = dev;
+	smi->clk_delay = var->clk_delay;
+	smi->cmd_read = var->cmd_read;
+	smi->cmd_write = var->cmd_write;
+	smi->ops = var->ops;
+
+	dev_set_drvdata(dev, smi);
+	spin_lock_init(&smi->lock);
+
+	/* TODO: if power is software controlled, set up any regulators here */
+
+	/* Assert then deassert RESET */
+	smi->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH);
+	if (IS_ERR(smi->reset)) {
+		dev_err(dev, "failed to get RESET GPIO\n");
+		return PTR_ERR(smi->reset);
+	}
+	msleep(REALTEK_SMI_HW_STOP_DELAY);
+	gpiod_set_value(smi->reset, 0);
+	msleep(REALTEK_SMI_HW_START_DELAY);
+	dev_info(dev, "deasserted RESET\n");
+
+	/* Fetch MDIO pins */
+	smi->mdc = devm_gpiod_get_optional(dev, "mdc", GPIOD_OUT_LOW);
+	if (IS_ERR(smi->mdc))
+		return PTR_ERR(smi->mdc);
+	smi->mdio = devm_gpiod_get_optional(dev, "mdio", GPIOD_OUT_LOW);
+	if (IS_ERR(smi->mdio))
+		return PTR_ERR(smi->mdio);
+
+	smi->leds_disabled = of_property_read_bool(np, "realtek,disable-leds");
+
+	ret = smi->ops->detect(smi);
+	if (ret) {
+		dev_err(dev, "unable to detect switch\n");
+		return ret;
+	}
+
+	smi->ds = dsa_switch_alloc(dev, smi->num_ports);
+	if (!smi->ds)
+		return -ENOMEM;
+	smi->ds->priv = smi;
+
+	smi->ds->ops = var->ds_ops;
+	ret = dsa_register_switch(smi->ds);
+	if (ret) {
+		dev_err(dev, "unable to register switch ret = %d\n", ret);
+		return ret;
+	}
+	return 0;
+}
+
+static int realtek_smi_remove(struct platform_device *pdev)
+{
+	struct realtek_smi *smi = dev_get_drvdata(&pdev->dev);
+
+	dsa_unregister_switch(smi->ds);
+	gpiod_set_value(smi->reset, 1);
+
+	return 0;
+}
+
+static const struct of_device_id realtek_smi_of_match[] = {
+	{
+		.compatible = "realtek,rtl8366rb",
+		.data = &rtl8366rb_variant,
+	},
+	{
+		/* FIXME: add support for RTL8366S and more */
+		.compatible = "realtek,rtl8366s",
+		.data = NULL,
+	},
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, realtek_smi_of_match);
+
+static struct platform_driver realtek_smi_driver = {
+	.driver = {
+		.name = "realtek-smi",
+		.of_match_table = of_match_ptr(realtek_smi_of_match),
+	},
+	.probe  = realtek_smi_probe,
+	.remove = realtek_smi_remove,
+};
+module_platform_driver(realtek_smi_driver);
diff --git a/drivers/net/dsa/realtek-smi.h b/drivers/net/dsa/realtek-smi.h
new file mode 100644
index 000000000000..9a63b51e1d82
--- /dev/null
+++ b/drivers/net/dsa/realtek-smi.h
@@ -0,0 +1,144 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Realtek SMI interface driver defines
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ */
+
+#ifndef _REALTEK_SMI_H
+#define _REALTEK_SMI_H
+
+#include <linux/phy.h>
+#include <linux/platform_device.h>
+#include <linux/gpio/consumer.h>
+#include <net/dsa.h>
+
+struct realtek_smi_ops;
+struct dentry;
+struct inode;
+struct file;
+
+struct rtl8366_mib_counter {
+	unsigned int	base;
+	unsigned int	offset;
+	unsigned int	length;
+	const char	*name;
+};
+
+struct rtl8366_vlan_mc {
+	u16	vid;
+	u16	untag;
+	u16	member;
+	u8	fid;
+	u8	priority;
+};
+
+struct rtl8366_vlan_4k {
+	u16	vid;
+	u16	untag;
+	u16	member;
+	u8	fid;
+};
+
+struct realtek_smi {
+	struct device		*dev;
+	struct gpio_desc	*reset;
+	struct gpio_desc	*mdc;
+	struct gpio_desc	*mdio;
+	struct regmap		*map;
+	struct mii_bus		*slave_mii_bus;
+
+	unsigned int		clk_delay;
+	u8			cmd_read;
+	u8			cmd_write;
+	spinlock_t		lock; /* Locks around command writes */
+	struct dsa_switch	*ds;
+	struct irq_domain	*irqdomain;
+	bool			leds_disabled;
+
+	unsigned int		cpu_port;
+	unsigned int		num_ports;
+	unsigned int		num_vlan_mc;
+	unsigned int		num_mib_counters;
+	struct rtl8366_mib_counter *mib_counters;
+
+	const struct realtek_smi_ops *ops;
+
+	int			vlan_enabled;
+	int			vlan4k_enabled;
+
+	char			buf[4096];
+};
+
+/**
+ * struct realtek_smi_ops - vtable for the per-SMI-chiptype operations
+ * @detect: detects the chiptype
+ */
+struct realtek_smi_ops {
+	int	(*detect)(struct realtek_smi *smi);
+	int	(*reset_chip)(struct realtek_smi *smi);
+	int	(*setup)(struct realtek_smi *smi);
+	void	(*cleanup)(struct realtek_smi *smi);
+	int	(*get_mib_counter)(struct realtek_smi *smi,
+				   int port,
+				   struct rtl8366_mib_counter *mib,
+				   u64 *mibvalue);
+	int	(*get_vlan_mc)(struct realtek_smi *smi, u32 index,
+			       struct rtl8366_vlan_mc *vlanmc);
+	int	(*set_vlan_mc)(struct realtek_smi *smi, u32 index,
+			       const struct rtl8366_vlan_mc *vlanmc);
+	int	(*get_vlan_4k)(struct realtek_smi *smi, u32 vid,
+			       struct rtl8366_vlan_4k *vlan4k);
+	int	(*set_vlan_4k)(struct realtek_smi *smi,
+			       const struct rtl8366_vlan_4k *vlan4k);
+	int	(*get_mc_index)(struct realtek_smi *smi, int port, int *val);
+	int	(*set_mc_index)(struct realtek_smi *smi, int port, int index);
+	bool	(*is_vlan_valid)(struct realtek_smi *smi, unsigned int vlan);
+	int	(*enable_vlan)(struct realtek_smi *smi, bool enable);
+	int	(*enable_vlan4k)(struct realtek_smi *smi, bool enable);
+	int	(*enable_port)(struct realtek_smi *smi, int port, bool enable);
+	int	(*phy_read)(struct realtek_smi *smi, int phy, int regnum);
+	int	(*phy_write)(struct realtek_smi *smi, int phy, int regnum,
+			     u16 val);
+};
+
+struct realtek_smi_variant {
+	const struct dsa_switch_ops *ds_ops;
+	const struct realtek_smi_ops *ops;
+	unsigned int clk_delay;
+	u8 cmd_read;
+	u8 cmd_write;
+};
+
+/* SMI core calls */
+int realtek_smi_write_reg_noack(struct realtek_smi *smi, u32 addr,
+				u32 data);
+int realtek_smi_setup_mdio(struct realtek_smi *smi);
+
+/* RTL8366 library helpers */
+int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used);
+int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+		     u32 untag, u32 fid);
+int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val);
+int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+		     unsigned int vid);
+int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable);
+int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable);
+int rtl8366_reset_vlan(struct realtek_smi *smi);
+int rtl8366_init_vlan(struct realtek_smi *smi);
+int rtl8366_vlan_filtering(struct dsa_switch *ds, int port,
+			   bool vlan_filtering);
+int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan);
+void rtl8366_vlan_add(struct dsa_switch *ds, int port,
+		      const struct switchdev_obj_port_vlan *vlan);
+int rtl8366_vlan_del(struct dsa_switch *ds, int port,
+		     const struct switchdev_obj_port_vlan *vlan);
+void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+			 uint8_t *data);
+int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset);
+void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data);
+
+extern const struct realtek_smi_variant rtl8366rb_variant;
+
+#endif /*  _REALTEK_SMI_H */
diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
new file mode 100644
index 000000000000..58d8534f7ecb
--- /dev/null
+++ b/drivers/net/dsa/rtl8366.c
@@ -0,0 +1,516 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Realtek SMI library helpers for the RTL8366x variants
+ * RTL8366RB and RTL8366S
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ */
+#include <linux/if_bridge.h>
+#include <net/dsa.h>
+
+#include "realtek-smi.h"
+
+int rtl8366_mc_is_used(struct realtek_smi *smi, int mc_index, int *used)
+{
+	int ret;
+	int i;
+
+	*used = 0;
+	for (i = 0; i < smi->num_ports; i++) {
+		int index = 0;
+
+		ret = smi->ops->get_mc_index(smi, i, &index);
+		if (ret)
+			return ret;
+
+		if (mc_index == index) {
+			*used = 1;
+			break;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_mc_is_used);
+
+int rtl8366_set_vlan(struct realtek_smi *smi, int vid, u32 member,
+		     u32 untag, u32 fid)
+{
+	struct rtl8366_vlan_4k vlan4k;
+	int ret;
+	int i;
+
+	/* Update the 4K table */
+	ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+	if (ret)
+		return ret;
+
+	vlan4k.member = member;
+	vlan4k.untag = untag;
+	vlan4k.fid = fid;
+	ret = smi->ops->set_vlan_4k(smi, &vlan4k);
+	if (ret)
+		return ret;
+
+	/* Try to find an existing MC entry for this VID */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		struct rtl8366_vlan_mc vlanmc;
+
+		ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+
+		if (vid == vlanmc.vid) {
+			/* update the MC entry */
+			vlanmc.member = member;
+			vlanmc.untag = untag;
+			vlanmc.fid = fid;
+
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			break;
+		}
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rtl8366_set_vlan);
+
+int rtl8366_get_pvid(struct realtek_smi *smi, int port, int *val)
+{
+	struct rtl8366_vlan_mc vlanmc;
+	int ret;
+	int index;
+
+	ret = smi->ops->get_mc_index(smi, port, &index);
+	if (ret)
+		return ret;
+
+	ret = smi->ops->get_vlan_mc(smi, index, &vlanmc);
+	if (ret)
+		return ret;
+
+	*val = vlanmc.vid;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_pvid);
+
+int rtl8366_set_pvid(struct realtek_smi *smi, unsigned int port,
+		     unsigned int vid)
+{
+	struct rtl8366_vlan_mc vlanmc;
+	struct rtl8366_vlan_4k vlan4k;
+	int ret;
+	int i;
+
+	/* Try to find an existing MC entry for this VID */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+
+		if (vid == vlanmc.vid) {
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			ret = smi->ops->set_mc_index(smi, port, i);
+			return ret;
+		}
+	}
+
+	/* We have no MC entry for this VID, try to find an empty one */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+
+		if (vlanmc.vid == 0 && vlanmc.member == 0) {
+			/* Update the entry from the 4K table */
+			ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+			if (ret)
+				return ret;
+
+			vlanmc.vid = vid;
+			vlanmc.member = vlan4k.member;
+			vlanmc.untag = vlan4k.untag;
+			vlanmc.fid = vlan4k.fid;
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			ret = smi->ops->set_mc_index(smi, port, i);
+			return ret;
+		}
+	}
+
+	/* MC table is full, try to find an unused entry and replace it */
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		int used;
+
+		ret = rtl8366_mc_is_used(smi, i, &used);
+		if (ret)
+			return ret;
+
+		if (!used) {
+			/* Update the entry from the 4K table */
+			ret = smi->ops->get_vlan_4k(smi, vid, &vlan4k);
+			if (ret)
+				return ret;
+
+			vlanmc.vid = vid;
+			vlanmc.member = vlan4k.member;
+			vlanmc.untag = vlan4k.untag;
+			vlanmc.fid = vlan4k.fid;
+			ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			ret = smi->ops->set_mc_index(smi, port, i);
+			return ret;
+		}
+	}
+
+	dev_err(smi->dev,
+		"all VLAN member configurations are in use\n");
+
+	return -ENOSPC;
+}
+EXPORT_SYMBOL_GPL(rtl8366_set_pvid);
+
+int rtl8366_enable_vlan4k(struct realtek_smi *smi, bool enable)
+{
+	int ret;
+
+	/* To enable 4k VLAN, ordinary VLAN must be enabled first,
+	 * but if we disable 4k VLAN it is fine to leave ordinary
+	 * VLAN enabled.
+	 */
+	if (enable) {
+		/* Make sure VLAN is ON */
+		ret = smi->ops->enable_vlan(smi, true);
+		if (ret)
+			return ret;
+
+		smi->vlan_enabled = true;
+	}
+
+	ret = smi->ops->enable_vlan4k(smi, enable);
+	if (ret)
+		return ret;
+
+	smi->vlan4k_enabled = enable;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_enable_vlan4k);
+
+int rtl8366_enable_vlan(struct realtek_smi *smi, bool enable)
+{
+	int ret;
+
+	ret = smi->ops->enable_vlan(smi, enable);
+	if (ret)
+		return ret;
+
+	smi->vlan_enabled = enable;
+
+	/* If we turn VLAN off, make sure that we turn off
+	 * 4k VLAN as well, if that happened to be on.
+	 */
+	if (!enable) {
+		smi->vlan4k_enabled = false;
+		ret = smi->ops->enable_vlan4k(smi, false);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(rtl8366_enable_vlan);
+
+int rtl8366_reset_vlan(struct realtek_smi *smi)
+{
+	struct rtl8366_vlan_mc vlanmc;
+	struct rtl8366_vlan_4k vlan4k;
+	int ret;
+	int i;
+
+	rtl8366_enable_vlan(smi, false);
+	rtl8366_enable_vlan4k(smi, false);
+
+	/* Clear the 16 VLAN member configurations */
+	vlanmc.vid = 0;
+	vlanmc.priority = 0;
+	vlanmc.member = 0;
+	vlanmc.untag = 0;
+	vlanmc.fid = 0;
+	for (i = 0; i < smi->num_vlan_mc; i++) {
+		ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_reset_vlan);
+
+int rtl8366_init_vlan(struct realtek_smi *smi)
+{
+	int port;
+	int ret;
+
+	ret = rtl8366_reset_vlan(smi);
+	if (ret)
+		return ret;
+
+	/* Loop over the available ports, for each port, associate
+	 * it with the VLAN (port+1)
+	 */
+	for (port = 0; port < smi->num_ports; port++) {
+		u32 mask;
+
+		if (port == smi->cpu_port)
+			/* For the CPU port, make all ports members of this
+			 * VLAN.
+			 */
+			mask = GENMASK(smi->num_ports - 1, 0);
+		else
+			/* For all other ports, enable itself plus the
+			 * CPU port.
+			 */
+			mask = BIT(port) | BIT(smi->cpu_port);
+
+		/* For each port, set the port as member of VLAN (port+1)
+		 * and untagged, except for the CPU port: the CPU port (5) is
+		 * member of VLAN 6 and so are ALL the other ports as well.
+		 * Use filter 0 (no filter).
+		 */
+		dev_info(smi->dev, "VLAN%d port mask for port %d, %08x\n",
+			 (port + 1), port, mask);
+		ret = rtl8366_set_vlan(smi, (port + 1), mask, mask, 0);
+		if (ret)
+			return ret;
+
+		dev_info(smi->dev, "VLAN%d port %d, PVID set to %d\n",
+			 (port + 1), port, (port + 1));
+		ret = rtl8366_set_pvid(smi, port, (port + 1));
+		if (ret)
+			return ret;
+	}
+
+	return rtl8366_enable_vlan(smi, true);
+}
+EXPORT_SYMBOL_GPL(rtl8366_init_vlan);
+
+int rtl8366_vlan_filtering(struct dsa_switch *ds, int port, bool vlan_filtering)
+{
+	struct realtek_smi *smi = ds->priv;
+	struct rtl8366_vlan_4k vlan4k;
+	int ret;
+
+	if (!smi->ops->is_vlan_valid(smi, port))
+		return -EINVAL;
+
+	dev_info(smi->dev, "%s filtering on port %d\n",
+		 vlan_filtering ? "enable" : "disable",
+		 port);
+
+	/* TODO:
+	 * The hardware support filter ID (FID) 0..7, I have no clue how to
+	 * support this in the driver when the callback only says on/off.
+	 */
+	ret = smi->ops->get_vlan_4k(smi, port, &vlan4k);
+	if (ret)
+		return ret;
+
+	/* Just set the filter to FID 1 for now then */
+	ret = rtl8366_set_vlan(smi, port,
+			       vlan4k.member,
+			       vlan4k.untag,
+			       1);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_filtering);
+
+int rtl8366_vlan_prepare(struct dsa_switch *ds, int port,
+			 const struct switchdev_obj_port_vlan *vlan)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	if (!smi->ops->is_vlan_valid(smi, port))
+		return -EINVAL;
+
+	dev_info(smi->dev, "prepare VLANs %04x..%04x\n",
+		 vlan->vid_begin, vlan->vid_end);
+
+	/* Enable VLAN in the hardware
+	 * FIXME: what's with this 4k business?
+	 * Just rtl8366_enable_vlan() seems inconclusive.
+	 */
+	ret = rtl8366_enable_vlan4k(smi, true);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_prepare);
+
+void rtl8366_vlan_add(struct dsa_switch *ds, int port,
+		      const struct switchdev_obj_port_vlan *vlan)
+{
+	bool untagged = !!(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED);
+	bool pvid = !!(vlan->flags & BRIDGE_VLAN_INFO_PVID);
+	struct realtek_smi *smi = ds->priv;
+	u32 member = 0;
+	u32 untag = 0;
+	u16 vid;
+	int ret;
+
+	if (!smi->ops->is_vlan_valid(smi, port))
+		return;
+
+	dev_info(smi->dev, "add VLAN on port %d, %s, %s\n",
+		 port,
+		 untagged ? "untagged" : "tagged",
+		 pvid ? " PVID" : "no PVID");
+
+	if (dsa_is_dsa_port(ds, port) || dsa_is_cpu_port(ds, port))
+		dev_err(smi->dev, "port is DSA or CPU port\n");
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		int pvid_val = 0;
+
+		dev_info(smi->dev, "add VLAN %04x\n", vid);
+		member |= BIT(port);
+
+		if (untagged)
+			untag |= BIT(port);
+
+		/* To ensure that we have a valid MC entry for this VLAN,
+		 * initialize the port VLAN ID here.
+		 */
+		ret = rtl8366_get_pvid(smi, port, &pvid_val);
+		if (ret < 0) {
+			dev_err(smi->dev, "could not lookup PVID for port %d\n",
+				port);
+			return;
+		}
+		if (pvid_val == 0) {
+			ret = rtl8366_set_pvid(smi, port, vid);
+			if (ret < 0)
+				return;
+		}
+	}
+
+	ret = rtl8366_set_vlan(smi, port, member, untag, 0);
+	if (ret)
+		dev_err(smi->dev,
+			"failed to set up VLAN %04x",
+			vid);
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_add);
+
+int rtl8366_vlan_del(struct dsa_switch *ds, int port,
+		     const struct switchdev_obj_port_vlan *vlan)
+{
+	struct realtek_smi *smi = ds->priv;
+	u16 vid;
+	int ret;
+
+	dev_info(smi->dev, "del VLAN on port %d\n", port);
+
+	for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
+		int i;
+
+		dev_info(smi->dev, "del VLAN %04x\n", vid);
+
+		for (i = 0; i < smi->num_vlan_mc; i++) {
+			struct rtl8366_vlan_mc vlanmc;
+
+			ret = smi->ops->get_vlan_mc(smi, i, &vlanmc);
+			if (ret)
+				return ret;
+
+			if (vid == vlanmc.vid) {
+				/* clear VLAN member configurations */
+				vlanmc.vid = 0;
+				vlanmc.priority = 0;
+				vlanmc.member = 0;
+				vlanmc.untag = 0;
+				vlanmc.fid = 0;
+
+				ret = smi->ops->set_vlan_mc(smi, i, &vlanmc);
+				if (ret) {
+					dev_err(smi->dev,
+						"failed to remove VLAN %04x\n",
+						vid);
+					return ret;
+				}
+				break;
+			}
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rtl8366_vlan_del);
+
+void rtl8366_get_strings(struct dsa_switch *ds, int port, u32 stringset,
+			 uint8_t *data)
+{
+	struct realtek_smi *smi = ds->priv;
+	struct rtl8366_mib_counter *mib;
+	int i;
+
+	if (port >= smi->num_ports)
+		return;
+
+	for (i = 0; i < smi->num_mib_counters; i++) {
+		mib = &smi->mib_counters[i];
+		strncpy(data + i * ETH_GSTRING_LEN,
+			mib->name, ETH_GSTRING_LEN);
+	}
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_strings);
+
+int rtl8366_get_sset_count(struct dsa_switch *ds, int port, int sset)
+{
+	struct realtek_smi *smi = ds->priv;
+
+	/* We only support SS_STATS */
+	if (sset != ETH_SS_STATS)
+		return 0;
+	if (port >= smi->num_ports)
+		return -EINVAL;
+
+	return smi->num_mib_counters;
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_sset_count);
+
+void rtl8366_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data)
+{
+	struct realtek_smi *smi = ds->priv;
+	int i;
+	int ret;
+
+	if (port >= smi->num_ports)
+		return;
+
+	for (i = 0; i < smi->num_mib_counters; i++) {
+		struct rtl8366_mib_counter *mib;
+		u64 mibvalue = 0;
+
+		mib = &smi->mib_counters[i];
+		ret = smi->ops->get_mib_counter(smi, port, mib, &mibvalue);
+		if (ret) {
+			dev_err(smi->dev, "error reading MIB counter %s\n",
+				mib->name);
+		}
+		data[i] = mibvalue;
+	}
+}
+EXPORT_SYMBOL_GPL(rtl8366_get_ethtool_stats);
diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c
new file mode 100644
index 000000000000..1e55b9bf8b56
--- /dev/null
+++ b/drivers/net/dsa/rtl8366rb.c
@@ -0,0 +1,1424 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Realtek SMI subdriver for the Realtek RTL8366RB ethernet switch
+ *
+ * This is a sparsely documented chip, the only viable documentation seems
+ * to be a patched up code drop from the vendor that appear in various
+ * GPL source trees.
+ *
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ * Copyright (C) 2009-2010 Gabor Juhos <juhosg@openwrt.org>
+ * Copyright (C) 2010 Antti Seppälä <a.seppala@gmail.com>
+ * Copyright (C) 2010 Roman Yeryomin <roman@advem.lv>
+ * Copyright (C) 2011 Colin Leitner <colin.leitner@googlemail.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/etherdevice.h>
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/of_irq.h>
+#include <linux/regmap.h>
+
+#include "realtek-smi.h"
+
+#define RTL8366RB_PORT_NUM_CPU		5
+#define RTL8366RB_NUM_PORTS		6
+#define RTL8366RB_PHY_NO_MAX		4
+#define RTL8366RB_PHY_ADDR_MAX		31
+
+/* Switch Global Configuration register */
+#define RTL8366RB_SGCR				0x0000
+#define RTL8366RB_SGCR_EN_BC_STORM_CTRL		BIT(0)
+#define RTL8366RB_SGCR_MAX_LENGTH(a)		((a) << 4)
+#define RTL8366RB_SGCR_MAX_LENGTH_MASK		RTL8366RB_SGCR_MAX_LENGTH(0x3)
+#define RTL8366RB_SGCR_MAX_LENGTH_1522		RTL8366RB_SGCR_MAX_LENGTH(0x0)
+#define RTL8366RB_SGCR_MAX_LENGTH_1536		RTL8366RB_SGCR_MAX_LENGTH(0x1)
+#define RTL8366RB_SGCR_MAX_LENGTH_1552		RTL8366RB_SGCR_MAX_LENGTH(0x2)
+#define RTL8366RB_SGCR_MAX_LENGTH_9216		RTL8366RB_SGCR_MAX_LENGTH(0x3)
+#define RTL8366RB_SGCR_EN_VLAN			BIT(13)
+#define RTL8366RB_SGCR_EN_VLAN_4KTB		BIT(14)
+
+/* Port Enable Control register */
+#define RTL8366RB_PECR				0x0001
+
+/* Switch Security Control registers */
+#define RTL8366RB_SSCR0				0x0002
+#define RTL8366RB_SSCR1				0x0003
+#define RTL8366RB_SSCR2				0x0004
+#define RTL8366RB_SSCR2_DROP_UNKNOWN_DA		BIT(0)
+
+/* Port Mirror Control Register */
+#define RTL8366RB_PMCR				0x0007
+#define RTL8366RB_PMCR_SOURCE_PORT(a)		(a)
+#define RTL8366RB_PMCR_SOURCE_PORT_MASK		0x000f
+#define RTL8366RB_PMCR_MONITOR_PORT(a)		((a) << 4)
+#define RTL8366RB_PMCR_MONITOR_PORT_MASK	0x00f0
+#define RTL8366RB_PMCR_MIRROR_RX		BIT(8)
+#define RTL8366RB_PMCR_MIRROR_TX		BIT(9)
+#define RTL8366RB_PMCR_MIRROR_SPC		BIT(10)
+#define RTL8366RB_PMCR_MIRROR_ISO		BIT(11)
+
+/* bits 0..7 = port 0, bits 8..15 = port 1 */
+#define RTL8366RB_PAACR0		0x0010
+/* bits 0..7 = port 2, bits 8..15 = port 3 */
+#define RTL8366RB_PAACR1		0x0011
+/* bits 0..7 = port 4, bits 8..15 = port 5 */
+#define RTL8366RB_PAACR2		0x0012
+#define RTL8366RB_PAACR_SPEED_10M	0
+#define RTL8366RB_PAACR_SPEED_100M	1
+#define RTL8366RB_PAACR_SPEED_1000M	2
+#define RTL8366RB_PAACR_FULL_DUPLEX	BIT(2)
+#define RTL8366RB_PAACR_LINK_UP		BIT(4)
+#define RTL8366RB_PAACR_TX_PAUSE	BIT(5)
+#define RTL8366RB_PAACR_RX_PAUSE	BIT(6)
+#define RTL8366RB_PAACR_AN		BIT(7)
+
+#define RTL8366RB_PAACR_CPU_PORT	(RTL8366RB_PAACR_SPEED_1000M | \
+					 RTL8366RB_PAACR_FULL_DUPLEX | \
+					 RTL8366RB_PAACR_LINK_UP | \
+					 RTL8366RB_PAACR_TX_PAUSE | \
+					 RTL8366RB_PAACR_RX_PAUSE)
+
+/* bits 0..7 = port 0, bits 8..15 = port 1 */
+#define RTL8366RB_PSTAT0		0x0014
+/* bits 0..7 = port 2, bits 8..15 = port 3 */
+#define RTL8366RB_PSTAT1		0x0015
+/* bits 0..7 = port 4, bits 8..15 = port 5 */
+#define RTL8366RB_PSTAT2		0x0016
+
+#define RTL8366RB_POWER_SAVING_REG	0x0021
+
+/* CPU port control reg */
+#define RTL8368RB_CPU_CTRL_REG		0x0061
+#define RTL8368RB_CPU_PORTS_MSK		0x00FF
+/* Enables inserting custom tag length/type 0x8899 */
+#define RTL8368RB_CPU_INSTAG		BIT(15)
+
+#define RTL8366RB_SMAR0			0x0070 /* bits 0..15 */
+#define RTL8366RB_SMAR1			0x0071 /* bits 16..31 */
+#define RTL8366RB_SMAR2			0x0072 /* bits 32..47 */
+
+#define RTL8366RB_RESET_CTRL_REG		0x0100
+#define RTL8366RB_CHIP_CTRL_RESET_HW		BIT(0)
+#define RTL8366RB_CHIP_CTRL_RESET_SW		BIT(1)
+
+#define RTL8366RB_CHIP_ID_REG			0x0509
+#define RTL8366RB_CHIP_ID_8366			0x5937
+#define RTL8366RB_CHIP_VERSION_CTRL_REG		0x050A
+#define RTL8366RB_CHIP_VERSION_MASK		0xf
+
+/* PHY registers control */
+#define RTL8366RB_PHY_ACCESS_CTRL_REG		0x8000
+#define RTL8366RB_PHY_CTRL_READ			BIT(0)
+#define RTL8366RB_PHY_CTRL_WRITE		0
+#define RTL8366RB_PHY_ACCESS_BUSY_REG		0x8001
+#define RTL8366RB_PHY_INT_BUSY			BIT(0)
+#define RTL8366RB_PHY_EXT_BUSY			BIT(4)
+#define RTL8366RB_PHY_ACCESS_DATA_REG		0x8002
+#define RTL8366RB_PHY_EXT_CTRL_REG		0x8010
+#define RTL8366RB_PHY_EXT_WRDATA_REG		0x8011
+#define RTL8366RB_PHY_EXT_RDDATA_REG		0x8012
+
+#define RTL8366RB_PHY_REG_MASK			0x1f
+#define RTL8366RB_PHY_PAGE_OFFSET		5
+#define RTL8366RB_PHY_PAGE_MASK			(0xf << 5)
+#define RTL8366RB_PHY_NO_OFFSET			9
+#define RTL8366RB_PHY_NO_MASK			(0x1f << 9)
+
+#define RTL8366RB_VLAN_INGRESS_CTRL2_REG	0x037f
+
+/* LED control registers */
+#define RTL8366RB_LED_BLINKRATE_REG		0x0430
+#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
+#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
+#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
+#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
+#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
+#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
+#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
+
+#define RTL8366RB_LED_CTRL_REG			0x0431
+#define RTL8366RB_LED_OFF			0x0
+#define RTL8366RB_LED_DUP_COL			0x1
+#define RTL8366RB_LED_LINK_ACT			0x2
+#define RTL8366RB_LED_SPD1000			0x3
+#define RTL8366RB_LED_SPD100			0x4
+#define RTL8366RB_LED_SPD10			0x5
+#define RTL8366RB_LED_SPD1000_ACT		0x6
+#define RTL8366RB_LED_SPD100_ACT		0x7
+#define RTL8366RB_LED_SPD10_ACT			0x8
+#define RTL8366RB_LED_SPD100_10_ACT		0x9
+#define RTL8366RB_LED_FIBER			0xa
+#define RTL8366RB_LED_AN_FAULT			0xb
+#define RTL8366RB_LED_LINK_RX			0xc
+#define RTL8366RB_LED_LINK_TX			0xd
+#define RTL8366RB_LED_MASTER			0xe
+#define RTL8366RB_LED_FORCE			0xf
+#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
+#define RTL8366RB_LED_1_OFFSET			6
+#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
+#define RTL8366RB_LED_3_OFFSET			6
+
+#define RTL8366RB_MIB_COUNT			33
+#define RTL8366RB_GLOBAL_MIB_COUNT		1
+#define RTL8366RB_MIB_COUNTER_PORT_OFFSET	0x0050
+#define RTL8366RB_MIB_COUNTER_BASE		0x1000
+#define RTL8366RB_MIB_CTRL_REG			0x13F0
+#define RTL8366RB_MIB_CTRL_USER_MASK		0x0FFC
+#define RTL8366RB_MIB_CTRL_BUSY_MASK		BIT(0)
+#define RTL8366RB_MIB_CTRL_RESET_MASK		BIT(1)
+#define RTL8366RB_MIB_CTRL_PORT_RESET(_p)	BIT(2 + (_p))
+#define RTL8366RB_MIB_CTRL_GLOBAL_RESET		BIT(11)
+
+#define RTL8366RB_PORT_VLAN_CTRL_BASE		0x0063
+#define RTL8366RB_PORT_VLAN_CTRL_REG(_p)  \
+		(RTL8366RB_PORT_VLAN_CTRL_BASE + (_p) / 4)
+#define RTL8366RB_PORT_VLAN_CTRL_MASK		0xf
+#define RTL8366RB_PORT_VLAN_CTRL_SHIFT(_p)	(4 * ((_p) % 4))
+
+#define RTL8366RB_VLAN_TABLE_READ_BASE		0x018C
+#define RTL8366RB_VLAN_TABLE_WRITE_BASE		0x0185
+
+#define RTL8366RB_TABLE_ACCESS_CTRL_REG		0x0180
+#define RTL8366RB_TABLE_VLAN_READ_CTRL		0x0E01
+#define RTL8366RB_TABLE_VLAN_WRITE_CTRL		0x0F01
+
+#define RTL8366RB_VLAN_MC_BASE(_x)		(0x0020 + (_x) * 3)
+
+#define RTL8366RB_PORT_LINK_STATUS_BASE		0x0014
+#define RTL8366RB_PORT_STATUS_SPEED_MASK	0x0003
+#define RTL8366RB_PORT_STATUS_DUPLEX_MASK	0x0004
+#define RTL8366RB_PORT_STATUS_LINK_MASK		0x0010
+#define RTL8366RB_PORT_STATUS_TXPAUSE_MASK	0x0020
+#define RTL8366RB_PORT_STATUS_RXPAUSE_MASK	0x0040
+#define RTL8366RB_PORT_STATUS_AN_MASK		0x0080
+
+#define RTL8366RB_NUM_VLANS		16
+#define RTL8366RB_NUM_LEDGROUPS		4
+#define RTL8366RB_NUM_VIDS		4096
+#define RTL8366RB_PRIORITYMAX		7
+#define RTL8366RB_FIDMAX		7
+
+#define RTL8366RB_PORT_1		BIT(0) /* In userspace port 0 */
+#define RTL8366RB_PORT_2		BIT(1) /* In userspace port 1 */
+#define RTL8366RB_PORT_3		BIT(2) /* In userspace port 2 */
+#define RTL8366RB_PORT_4		BIT(3) /* In userspace port 3 */
+#define RTL8366RB_PORT_5		BIT(4) /* In userspace port 4 */
+
+#define RTL8366RB_PORT_CPU		BIT(5) /* CPU port */
+
+#define RTL8366RB_PORT_ALL		(RTL8366RB_PORT_1 |	\
+					 RTL8366RB_PORT_2 |	\
+					 RTL8366RB_PORT_3 |	\
+					 RTL8366RB_PORT_4 |	\
+					 RTL8366RB_PORT_5 |	\
+					 RTL8366RB_PORT_CPU)
+
+#define RTL8366RB_PORT_ALL_BUT_CPU	(RTL8366RB_PORT_1 |	\
+					 RTL8366RB_PORT_2 |	\
+					 RTL8366RB_PORT_3 |	\
+					 RTL8366RB_PORT_4 |	\
+					 RTL8366RB_PORT_5)
+
+#define RTL8366RB_PORT_ALL_EXTERNAL	(RTL8366RB_PORT_1 |	\
+					 RTL8366RB_PORT_2 |	\
+					 RTL8366RB_PORT_3 |	\
+					 RTL8366RB_PORT_4)
+
+#define RTL8366RB_PORT_ALL_INTERNAL	 RTL8366RB_PORT_CPU
+
+/* First configuration word per member config, VID and prio */
+#define RTL8366RB_VLAN_VID_MASK		0xfff
+#define RTL8366RB_VLAN_PRIORITY_SHIFT	12
+#define RTL8366RB_VLAN_PRIORITY_MASK	0x7
+/* Second configuration word per member config, member and untagged */
+#define RTL8366RB_VLAN_UNTAG_SHIFT	8
+#define RTL8366RB_VLAN_UNTAG_MASK	0xff
+#define RTL8366RB_VLAN_MEMBER_MASK	0xff
+/* Third config word per member config, STAG currently unused */
+#define RTL8366RB_VLAN_STAG_MBR_MASK	0xff
+#define RTL8366RB_VLAN_STAG_MBR_SHIFT	8
+#define RTL8366RB_VLAN_STAG_IDX_MASK	0x7
+#define RTL8366RB_VLAN_STAG_IDX_SHIFT	5
+#define RTL8366RB_VLAN_FID_MASK		0x7
+
+/* Port ingress bandwidth control */
+#define RTL8366RB_IB_BASE		0x0200
+#define RTL8366RB_IB_REG(pnum)		(RTL8366RB_IB_BASE + (pnum))
+#define RTL8366RB_IB_BDTH_MASK		0x3fff
+#define RTL8366RB_IB_PREIFG		BIT(14)
+
+/* Port egress bandwidth control */
+#define RTL8366RB_EB_BASE		0x02d1
+#define RTL8366RB_EB_REG(pnum)		(RTL8366RB_EB_BASE + (pnum))
+#define RTL8366RB_EB_BDTH_MASK		0x3fff
+#define RTL8366RB_EB_PREIFG_REG		0x02f8
+#define RTL8366RB_EB_PREIFG		BIT(9)
+
+#define RTL8366RB_BDTH_SW_MAX		1048512 /* 1048576? */
+#define RTL8366RB_BDTH_UNIT		64
+#define RTL8366RB_BDTH_REG_DEFAULT	16383
+
+/* QOS */
+#define RTL8366RB_QOS			BIT(15)
+/* Include/Exclude Preamble and IFG (20 bytes). 0:Exclude, 1:Include. */
+#define RTL8366RB_QOS_DEFAULT_PREIFG	1
+
+/* Interrupt handling */
+#define RTL8366RB_INTERRUPT_CONTROL_REG	0x0440
+#define RTL8366RB_INTERRUPT_POLARITY	BIT(0)
+#define RTL8366RB_P4_RGMII_LED		BIT(2)
+#define RTL8366RB_INTERRUPT_MASK_REG	0x0441
+#define RTL8366RB_INTERRUPT_LINK_CHGALL	GENMASK(11, 0)
+#define RTL8366RB_INTERRUPT_ACLEXCEED	BIT(8)
+#define RTL8366RB_INTERRUPT_STORMEXCEED	BIT(9)
+#define RTL8366RB_INTERRUPT_P4_FIBER	BIT(12)
+#define RTL8366RB_INTERRUPT_P4_UTP	BIT(13)
+#define RTL8366RB_INTERRUPT_VALID	(RTL8366RB_INTERRUPT_LINK_CHGALL | \
+					 RTL8366RB_INTERRUPT_ACLEXCEED | \
+					 RTL8366RB_INTERRUPT_STORMEXCEED | \
+					 RTL8366RB_INTERRUPT_P4_FIBER | \
+					 RTL8366RB_INTERRUPT_P4_UTP)
+#define RTL8366RB_INTERRUPT_STATUS_REG	0x0442
+#define RTL8366RB_NUM_INTERRUPT		14 /* 0..13 */
+
+/* bits 0..5 enable force when cleared */
+#define RTL8366RB_MAC_FORCE_CTRL_REG	0x0F11
+
+#define RTL8366RB_OAM_PARSER_REG	0x0F14
+#define RTL8366RB_OAM_MULTIPLEXER_REG	0x0F15
+
+#define RTL8366RB_GREEN_FEATURE_REG	0x0F51
+#define RTL8366RB_GREEN_FEATURE_MSK	0x0007
+#define RTL8366RB_GREEN_FEATURE_TX	BIT(0)
+#define RTL8366RB_GREEN_FEATURE_RX	BIT(2)
+
+static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = {
+	{ 0,  0, 4, "IfInOctets"				},
+	{ 0,  4, 4, "EtherStatsOctets"				},
+	{ 0,  8, 2, "EtherStatsUnderSizePkts"			},
+	{ 0, 10, 2, "EtherFragments"				},
+	{ 0, 12, 2, "EtherStatsPkts64Octets"			},
+	{ 0, 14, 2, "EtherStatsPkts65to127Octets"		},
+	{ 0, 16, 2, "EtherStatsPkts128to255Octets"		},
+	{ 0, 18, 2, "EtherStatsPkts256to511Octets"		},
+	{ 0, 20, 2, "EtherStatsPkts512to1023Octets"		},
+	{ 0, 22, 2, "EtherStatsPkts1024to1518Octets"		},
+	{ 0, 24, 2, "EtherOversizeStats"			},
+	{ 0, 26, 2, "EtherStatsJabbers"				},
+	{ 0, 28, 2, "IfInUcastPkts"				},
+	{ 0, 30, 2, "EtherStatsMulticastPkts"			},
+	{ 0, 32, 2, "EtherStatsBroadcastPkts"			},
+	{ 0, 34, 2, "EtherStatsDropEvents"			},
+	{ 0, 36, 2, "Dot3StatsFCSErrors"			},
+	{ 0, 38, 2, "Dot3StatsSymbolErrors"			},
+	{ 0, 40, 2, "Dot3InPauseFrames"				},
+	{ 0, 42, 2, "Dot3ControlInUnknownOpcodes"		},
+	{ 0, 44, 4, "IfOutOctets"				},
+	{ 0, 48, 2, "Dot3StatsSingleCollisionFrames"		},
+	{ 0, 50, 2, "Dot3StatMultipleCollisionFrames"		},
+	{ 0, 52, 2, "Dot3sDeferredTransmissions"		},
+	{ 0, 54, 2, "Dot3StatsLateCollisions"			},
+	{ 0, 56, 2, "EtherStatsCollisions"			},
+	{ 0, 58, 2, "Dot3StatsExcessiveCollisions"		},
+	{ 0, 60, 2, "Dot3OutPauseFrames"			},
+	{ 0, 62, 2, "Dot1dBasePortDelayExceededDiscards"	},
+	{ 0, 64, 2, "Dot1dTpPortInDiscards"			},
+	{ 0, 66, 2, "IfOutUcastPkts"				},
+	{ 0, 68, 2, "IfOutMulticastPkts"			},
+	{ 0, 70, 2, "IfOutBroadcastPkts"			},
+};
+
+static int rtl8366rb_get_mib_counter(struct realtek_smi *smi,
+				     int port,
+				     struct rtl8366_mib_counter *mib,
+				     u64 *mibvalue)
+{
+	u32 addr, val;
+	int ret;
+	int i;
+
+	addr = RTL8366RB_MIB_COUNTER_BASE +
+		RTL8366RB_MIB_COUNTER_PORT_OFFSET * (port) +
+		mib->offset;
+
+	/* Writing access counter address first
+	 * then ASIC will prepare 64bits counter wait for being retrived
+	 */
+	ret = regmap_write(smi->map, addr, 0); /* Write whatever */
+	if (ret)
+		return ret;
+
+	/* Read MIB control register */
+	ret = regmap_read(smi->map, RTL8366RB_MIB_CTRL_REG, &val);
+	if (ret)
+		return -EIO;
+
+	if (val & RTL8366RB_MIB_CTRL_BUSY_MASK)
+		return -EBUSY;
+
+	if (val & RTL8366RB_MIB_CTRL_RESET_MASK)
+		return -EIO;
+
+	/* Read each individual MIB 16 bits at the time */
+	*mibvalue = 0;
+	for (i = mib->length; i > 0; i--) {
+		ret = regmap_read(smi->map, addr + (i - 1), &val);
+		if (ret)
+			return ret;
+		*mibvalue = (*mibvalue << 16) | (val & 0xFFFF);
+	}
+	return 0;
+}
+
+static u32 rtl8366rb_get_irqmask(struct irq_data *d)
+{
+	int line = irqd_to_hwirq(d);
+	u32 val;
+
+	/* For line interrupts we combine link down in bits
+	 * 6..11 with link up in bits 0..5 into one interrupt.
+	 */
+	if (line < 12)
+		val = BIT(line) | BIT(line + 6);
+	else
+		val = BIT(line);
+	return val;
+}
+
+static void rtl8366rb_mask_irq(struct irq_data *d)
+{
+	struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+	int ret;
+
+	ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+				 rtl8366rb_get_irqmask(d), 0);
+	if (ret)
+		dev_err(smi->dev, "could not mask IRQ\n");
+}
+
+static void rtl8366rb_unmask_irq(struct irq_data *d)
+{
+	struct realtek_smi *smi = irq_data_get_irq_chip_data(d);
+	int ret;
+
+	ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_MASK_REG,
+				 rtl8366rb_get_irqmask(d),
+				 rtl8366rb_get_irqmask(d));
+	if (ret)
+		dev_err(smi->dev, "could not unmask IRQ\n");
+}
+
+static irqreturn_t rtl8366rb_irq(int irq, void *data)
+{
+	struct realtek_smi *smi = data;
+	u32 stat;
+	int ret;
+
+	/* This clears the IRQ status register */
+	ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+			  &stat);
+	if (ret) {
+		dev_err(smi->dev, "can't read interrupt status\n");
+		return IRQ_NONE;
+	}
+	stat &= RTL8366RB_INTERRUPT_VALID;
+	if (!stat)
+		return IRQ_NONE;
+	while (stat) {
+		int line = __ffs(stat);
+		int child_irq;
+
+		stat &= ~BIT(line);
+		/* For line interrupts we combine link down in bits
+		 * 6..11 with link up in bits 0..5 into one interrupt.
+		 */
+		if (line < 12 && line > 5)
+			line -= 5;
+		child_irq = irq_find_mapping(smi->irqdomain, line);
+		handle_nested_irq(child_irq);
+	}
+	return IRQ_HANDLED;
+}
+
+static struct irq_chip rtl8366rb_irq_chip = {
+	.name = "RTL8366RB",
+	.irq_mask = rtl8366rb_mask_irq,
+	.irq_unmask = rtl8366rb_unmask_irq,
+};
+
+static int rtl8366rb_irq_map(struct irq_domain *domain, unsigned int irq,
+			     irq_hw_number_t hwirq)
+{
+	irq_set_chip_data(irq, domain->host_data);
+	irq_set_chip_and_handler(irq, &rtl8366rb_irq_chip, handle_simple_irq);
+	irq_set_nested_thread(irq, 1);
+	irq_set_noprobe(irq);
+
+	return 0;
+}
+
+static void rtl8366rb_irq_unmap(struct irq_domain *d, unsigned int irq)
+{
+	irq_set_nested_thread(irq, 0);
+	irq_set_chip_and_handler(irq, NULL, NULL);
+	irq_set_chip_data(irq, NULL);
+}
+
+static const struct irq_domain_ops rtl8366rb_irqdomain_ops = {
+	.map = rtl8366rb_irq_map,
+	.unmap = rtl8366rb_irq_unmap,
+	.xlate  = irq_domain_xlate_onecell,
+};
+
+static int rtl8366rb_setup_cascaded_irq(struct realtek_smi *smi)
+{
+	struct device_node *intc;
+	unsigned long irq_trig;
+	int irq;
+	int ret;
+	u32 val;
+	int i;
+
+	intc = of_get_child_by_name(smi->dev->of_node, "interrupt-controller");
+	if (!intc) {
+		dev_err(smi->dev, "missing child interrupt-controller node\n");
+		return -EINVAL;
+	}
+	/* RB8366RB IRQs cascade off this one */
+	irq = of_irq_get(intc, 0);
+	if (irq <= 0) {
+		dev_err(smi->dev, "failed to get parent IRQ\n");
+		return irq ? irq : -EINVAL;
+	}
+
+	/* This clears the IRQ status register */
+	ret = regmap_read(smi->map, RTL8366RB_INTERRUPT_STATUS_REG,
+			  &val);
+	if (ret) {
+		dev_err(smi->dev, "can't read interrupt status\n");
+		return ret;
+	}
+
+	/* Fetch IRQ edge information from the descriptor */
+	irq_trig = irqd_get_trigger_type(irq_get_irq_data(irq));
+	switch (irq_trig) {
+	case IRQF_TRIGGER_RISING:
+	case IRQF_TRIGGER_HIGH:
+		dev_info(smi->dev, "active high/rising IRQ\n");
+		val = 0;
+		break;
+	case IRQF_TRIGGER_FALLING:
+	case IRQF_TRIGGER_LOW:
+		dev_info(smi->dev, "active low/falling IRQ\n");
+		val = RTL8366RB_INTERRUPT_POLARITY;
+		break;
+	}
+	ret = regmap_update_bits(smi->map, RTL8366RB_INTERRUPT_CONTROL_REG,
+				 RTL8366RB_INTERRUPT_POLARITY,
+				 val);
+	if (ret) {
+		dev_err(smi->dev, "could not configure IRQ polarity\n");
+		return ret;
+	}
+
+	ret = devm_request_threaded_irq(smi->dev, irq, NULL,
+					rtl8366rb_irq, IRQF_ONESHOT,
+					"RTL8366RB", smi);
+	if (ret) {
+		dev_err(smi->dev, "unable to request irq: %d\n", ret);
+		return ret;
+	}
+	smi->irqdomain = irq_domain_add_linear(intc,
+					       RTL8366RB_NUM_INTERRUPT,
+					       &rtl8366rb_irqdomain_ops,
+					       smi);
+	if (!smi->irqdomain) {
+		dev_err(smi->dev, "failed to create IRQ domain\n");
+		return -EINVAL;
+	}
+	for (i = 0; i < smi->num_ports; i++)
+		irq_set_parent(irq_create_mapping(smi->irqdomain, i), irq);
+
+	return 0;
+}
+
+static int rtl8366rb_set_addr(struct realtek_smi *smi)
+{
+	u8 addr[ETH_ALEN];
+	u16 val;
+	int ret;
+
+	eth_random_addr(addr);
+
+	dev_info(smi->dev, "set MAC: %02X:%02X:%02X:%02X:%02X:%02X\n",
+		 addr[0], addr[1], addr[2], addr[3], addr[4], addr[5]);
+	val = addr[0] << 8 | addr[1];
+	ret = regmap_write(smi->map, RTL8366RB_SMAR0, val);
+	if (ret)
+		return ret;
+	val = addr[2] << 8 | addr[3];
+	ret = regmap_write(smi->map, RTL8366RB_SMAR1, val);
+	if (ret)
+		return ret;
+	val = addr[4] << 8 | addr[5];
+	ret = regmap_write(smi->map, RTL8366RB_SMAR2, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/* Found in a vendor driver */
+
+/* For the "version 0" early silicon, appear in most source releases */
+static const u16 rtl8366rb_init_jam_ver_0[] = {
+	0x000B, 0x0001, 0x03A6, 0x0100, 0x03A7, 0x0001, 0x02D1, 0x3FFF,
+	0x02D2, 0x3FFF, 0x02D3, 0x3FFF, 0x02D4, 0x3FFF, 0x02D5, 0x3FFF,
+	0x02D6, 0x3FFF, 0x02D7, 0x3FFF, 0x02D8, 0x3FFF, 0x022B, 0x0688,
+	0x022C, 0x0FAC, 0x03D0, 0x4688, 0x03D1, 0x01F5, 0x0000, 0x0830,
+	0x02F9, 0x0200, 0x02F7, 0x7FFF, 0x02F8, 0x03FF, 0x0080, 0x03E8,
+	0x0081, 0x00CE, 0x0082, 0x00DA, 0x0083, 0x0230, 0xBE0F, 0x2000,
+	0x0231, 0x422A, 0x0232, 0x422A, 0x0233, 0x422A, 0x0234, 0x422A,
+	0x0235, 0x422A, 0x0236, 0x422A, 0x0237, 0x422A, 0x0238, 0x422A,
+	0x0239, 0x422A, 0x023A, 0x422A, 0x023B, 0x422A, 0x023C, 0x422A,
+	0x023D, 0x422A, 0x023E, 0x422A, 0x023F, 0x422A, 0x0240, 0x422A,
+	0x0241, 0x422A, 0x0242, 0x422A, 0x0243, 0x422A, 0x0244, 0x422A,
+	0x0245, 0x422A, 0x0246, 0x422A, 0x0247, 0x422A, 0x0248, 0x422A,
+	0x0249, 0x0146, 0x024A, 0x0146, 0x024B, 0x0146, 0xBE03, 0xC961,
+	0x024D, 0x0146, 0x024E, 0x0146, 0x024F, 0x0146, 0x0250, 0x0146,
+	0xBE64, 0x0226, 0x0252, 0x0146, 0x0253, 0x0146, 0x024C, 0x0146,
+	0x0251, 0x0146, 0x0254, 0x0146, 0xBE62, 0x3FD0, 0x0084, 0x0320,
+	0x0255, 0x0146, 0x0256, 0x0146, 0x0257, 0x0146, 0x0258, 0x0146,
+	0x0259, 0x0146, 0x025A, 0x0146, 0x025B, 0x0146, 0x025C, 0x0146,
+	0x025D, 0x0146, 0x025E, 0x0146, 0x025F, 0x0146, 0x0260, 0x0146,
+	0x0261, 0xA23F, 0x0262, 0x0294, 0x0263, 0xA23F, 0x0264, 0x0294,
+	0x0265, 0xA23F, 0x0266, 0x0294, 0x0267, 0xA23F, 0x0268, 0x0294,
+	0x0269, 0xA23F, 0x026A, 0x0294, 0x026B, 0xA23F, 0x026C, 0x0294,
+	0x026D, 0xA23F, 0x026E, 0x0294, 0x026F, 0xA23F, 0x0270, 0x0294,
+	0x02F5, 0x0048, 0xBE09, 0x0E00, 0xBE1E, 0x0FA0, 0xBE14, 0x8448,
+	0xBE15, 0x1007, 0xBE4A, 0xA284, 0xC454, 0x3F0B, 0xC474, 0x3F0B,
+	0xBE48, 0x3672, 0xBE4B, 0x17A7, 0xBE4C, 0x0B15, 0xBE52, 0x0EDD,
+	0xBE49, 0x8C00, 0xBE5B, 0x785C, 0xBE5C, 0x785C, 0xBE5D, 0x785C,
+	0xBE61, 0x368A, 0xBE63, 0x9B84, 0xC456, 0xCC13, 0xC476, 0xCC13,
+	0xBE65, 0x307D, 0xBE6D, 0x0005, 0xBE6E, 0xE120, 0xBE2E, 0x7BAF,
+};
+
+/* This v1 init sequence is from Belkin F5D8235 U-Boot release */
+static const u16 rtl8366rb_init_jam_ver_1[] = {
+	0x0000, 0x0830, 0x0001, 0x8000, 0x0400, 0x8130, 0xBE78, 0x3C3C,
+	0x0431, 0x5432, 0xBE37, 0x0CE4, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0,
+	0xC44C, 0x1585, 0xC44C, 0x1185, 0xC44C, 0x1585, 0xC46C, 0x1585,
+	0xC46C, 0x1185, 0xC46C, 0x1585, 0xC451, 0x2135, 0xC471, 0x2135,
+	0xBE10, 0x8140, 0xBE15, 0x0007, 0xBE6E, 0xE120, 0xBE69, 0xD20F,
+	0xBE6B, 0x0320, 0xBE24, 0xB000, 0xBE23, 0xFF51, 0xBE22, 0xDF20,
+	0xBE21, 0x0140, 0xBE20, 0x00BB, 0xBE24, 0xB800, 0xBE24, 0x0000,
+	0xBE24, 0x7000, 0xBE23, 0xFF51, 0xBE22, 0xDF60, 0xBE21, 0x0140,
+	0xBE20, 0x0077, 0xBE24, 0x7800, 0xBE24, 0x0000, 0xBE2E, 0x7B7A,
+	0xBE36, 0x0CE4, 0x02F5, 0x0048, 0xBE77, 0x2940, 0x000A, 0x83E0,
+	0xBE79, 0x3C3C, 0xBE00, 0x1340,
+};
+
+/* This v2 init sequence is from Belkin F5D8235 U-Boot release */
+static const u16 rtl8366rb_init_jam_ver_2[] = {
+	0x0450, 0x0000, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0431, 0x5432,
+	0xC44F, 0x6250, 0xC46F, 0x6250, 0xC456, 0x0C14, 0xC476, 0x0C14,
+	0xC44C, 0x1C85, 0xC44C, 0x1885, 0xC44C, 0x1C85, 0xC46C, 0x1C85,
+	0xC46C, 0x1885, 0xC46C, 0x1C85, 0xC44C, 0x0885, 0xC44C, 0x0881,
+	0xC44C, 0x0885, 0xC46C, 0x0885, 0xC46C, 0x0881, 0xC46C, 0x0885,
+	0xBE2E, 0x7BA7, 0xBE36, 0x1000, 0xBE37, 0x1000, 0x8000, 0x0001,
+	0xBE69, 0xD50F, 0x8000, 0x0000, 0xBE69, 0xD50F, 0xBE6E, 0x0320,
+	0xBE77, 0x2940, 0xBE78, 0x3C3C, 0xBE79, 0x3C3C, 0xBE6E, 0xE120,
+	0x8000, 0x0001, 0xBE15, 0x1007, 0x8000, 0x0000, 0xBE15, 0x1007,
+	0xBE14, 0x0448, 0xBE1E, 0x00A0, 0xBE10, 0x8160, 0xBE10, 0x8140,
+	0xBE00, 0x1340, 0x0F51, 0x0010,
+};
+
+/* Appears in a DDWRT code dump */
+static const u16 rtl8366rb_init_jam_ver_3[] = {
+	0x0000, 0x0830, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0431, 0x5432,
+	0x0F51, 0x0017, 0x02F5, 0x0048, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0,
+	0xC456, 0x0C14, 0xC476, 0x0C14, 0xC454, 0x3F8B, 0xC474, 0x3F8B,
+	0xC450, 0x2071, 0xC470, 0x2071, 0xC451, 0x226B, 0xC471, 0x226B,
+	0xC452, 0xA293, 0xC472, 0xA293, 0xC44C, 0x1585, 0xC44C, 0x1185,
+	0xC44C, 0x1585, 0xC46C, 0x1585, 0xC46C, 0x1185, 0xC46C, 0x1585,
+	0xC44C, 0x0185, 0xC44C, 0x0181, 0xC44C, 0x0185, 0xC46C, 0x0185,
+	0xC46C, 0x0181, 0xC46C, 0x0185, 0xBE24, 0xB000, 0xBE23, 0xFF51,
+	0xBE22, 0xDF20, 0xBE21, 0x0140, 0xBE20, 0x00BB, 0xBE24, 0xB800,
+	0xBE24, 0x0000, 0xBE24, 0x7000, 0xBE23, 0xFF51, 0xBE22, 0xDF60,
+	0xBE21, 0x0140, 0xBE20, 0x0077, 0xBE24, 0x7800, 0xBE24, 0x0000,
+	0xBE2E, 0x7BA7, 0xBE36, 0x1000, 0xBE37, 0x1000, 0x8000, 0x0001,
+	0xBE69, 0xD50F, 0x8000, 0x0000, 0xBE69, 0xD50F, 0xBE6B, 0x0320,
+	0xBE77, 0x2800, 0xBE78, 0x3C3C, 0xBE79, 0x3C3C, 0xBE6E, 0xE120,
+	0x8000, 0x0001, 0xBE10, 0x8140, 0x8000, 0x0000, 0xBE10, 0x8140,
+	0xBE15, 0x1007, 0xBE14, 0x0448, 0xBE1E, 0x00A0, 0xBE10, 0x8160,
+	0xBE10, 0x8140, 0xBE00, 0x1340, 0x0450, 0x0000, 0x0401, 0x0000,
+};
+
+/* Belkin F5D8235 v1, "belkin,f5d8235-v1" */
+static const u16 rtl8366rb_init_jam_f5d8235[] = {
+	0x0242, 0x02BF, 0x0245, 0x02BF, 0x0248, 0x02BF, 0x024B, 0x02BF,
+	0x024E, 0x02BF, 0x0251, 0x02BF, 0x0254, 0x0A3F, 0x0256, 0x0A3F,
+	0x0258, 0x0A3F, 0x025A, 0x0A3F, 0x025C, 0x0A3F, 0x025E, 0x0A3F,
+	0x0263, 0x007C, 0x0100, 0x0004, 0xBE5B, 0x3500, 0x800E, 0x200F,
+	0xBE1D, 0x0F00, 0x8001, 0x5011, 0x800A, 0xA2F4, 0x800B, 0x17A3,
+	0xBE4B, 0x17A3, 0xBE41, 0x5011, 0xBE17, 0x2100, 0x8000, 0x8304,
+	0xBE40, 0x8304, 0xBE4A, 0xA2F4, 0x800C, 0xA8D5, 0x8014, 0x5500,
+	0x8015, 0x0004, 0xBE4C, 0xA8D5, 0xBE59, 0x0008, 0xBE09, 0x0E00,
+	0xBE36, 0x1036, 0xBE37, 0x1036, 0x800D, 0x00FF, 0xBE4D, 0x00FF,
+};
+
+/* DGN3500, "netgear,dgn3500", "netgear,dgn3500b" */
+static const u16 rtl8366rb_init_jam_dgn3500[] = {
+	0x0000, 0x0830, 0x0400, 0x8130, 0x000A, 0x83ED, 0x0F51, 0x0017,
+	0x02F5, 0x0048, 0x02FA, 0xFFDF, 0x02FB, 0xFFE0, 0x0450, 0x0000,
+	0x0401, 0x0000, 0x0431, 0x0960,
+};
+
+/* This jam table activates "green ethernet", which means low power mode
+ * and is claimed to detect the cable length and not use more power than
+ * necessary, and the ports should enter power saving mode 10 seconds after
+ * a cable is disconnected. Seems to always be the same.
+ */
+static const u16 rtl8366rb_green_jam[][2] = {
+	{0xBE78, 0x323C}, {0xBE77, 0x5000}, {0xBE2E, 0x7BA7},
+	{0xBE59, 0x3459}, {0xBE5A, 0x745A}, {0xBE5B, 0x785C},
+	{0xBE5C, 0x785C}, {0xBE6E, 0xE120}, {0xBE79, 0x323C},
+};
+
+static int rtl8366rb_setup(struct dsa_switch *ds)
+{
+	struct realtek_smi *smi = ds->priv;
+	const u16 *jam_table;
+	u32 chip_ver = 0;
+	u32 chip_id = 0;
+	int jam_size;
+	u32 val;
+	int ret;
+	int i;
+
+	ret = regmap_read(smi->map, RTL8366RB_CHIP_ID_REG, &chip_id);
+	if (ret) {
+		dev_err(smi->dev, "unable to read chip id\n");
+		return ret;
+	}
+
+	switch (chip_id) {
+	case RTL8366RB_CHIP_ID_8366:
+		break;
+	default:
+		dev_err(smi->dev, "unknown chip id (%04x)\n", chip_id);
+		return -ENODEV;
+	}
+
+	ret = regmap_read(smi->map, RTL8366RB_CHIP_VERSION_CTRL_REG,
+			  &chip_ver);
+	if (ret) {
+		dev_err(smi->dev, "unable to read chip version\n");
+		return ret;
+	}
+
+	dev_info(smi->dev, "RTL%04x ver %u chip found\n",
+		 chip_id, chip_ver & RTL8366RB_CHIP_VERSION_MASK);
+
+	/* Do the init dance using the right jam table */
+	switch (chip_ver) {
+	case 0:
+		jam_table = rtl8366rb_init_jam_ver_0;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_0);
+		break;
+	case 1:
+		jam_table = rtl8366rb_init_jam_ver_1;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_1);
+		break;
+	case 2:
+		jam_table = rtl8366rb_init_jam_ver_2;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_2);
+		break;
+	default:
+		jam_table = rtl8366rb_init_jam_ver_3;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_ver_3);
+		break;
+	}
+
+	/* Special jam tables for special routers
+	 * TODO: are these necessary? Maintainers, please test
+	 * without them, using just the off-the-shelf tables.
+	 */
+	if (of_machine_is_compatible("belkin,f5d8235-v1")) {
+		jam_table = rtl8366rb_init_jam_f5d8235;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_f5d8235);
+	}
+	if (of_machine_is_compatible("netgear,dgn3500") ||
+	    of_machine_is_compatible("netgear,dgn3500b")) {
+		jam_table = rtl8366rb_init_jam_dgn3500;
+		jam_size = ARRAY_SIZE(rtl8366rb_init_jam_dgn3500);
+	}
+
+	i = 0;
+	while (i < jam_size) {
+		if ((jam_table[i] & 0xBE00) == 0xBE00) {
+			ret = regmap_read(smi->map,
+					  RTL8366RB_PHY_ACCESS_BUSY_REG,
+					  &val);
+			if (ret)
+				return ret;
+			if (!(val & RTL8366RB_PHY_INT_BUSY)) {
+				ret = regmap_write(smi->map,
+						RTL8366RB_PHY_ACCESS_CTRL_REG,
+						RTL8366RB_PHY_CTRL_WRITE);
+				if (ret)
+					return ret;
+			}
+		}
+		dev_dbg(smi->dev, "jam %04x into register %04x\n",
+			jam_table[i + 1],
+			jam_table[i]);
+		ret = regmap_write(smi->map,
+				   jam_table[i],
+				   jam_table[i + 1]);
+		if (ret)
+			return ret;
+		i += 2;
+	}
+
+	/* Set up the "green ethernet" feature */
+	i = 0;
+	while (i < ARRAY_SIZE(rtl8366rb_green_jam)) {
+		ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_BUSY_REG,
+				  &val);
+		if (ret)
+			return ret;
+		if (!(val & RTL8366RB_PHY_INT_BUSY)) {
+			ret = regmap_write(smi->map,
+					   RTL8366RB_PHY_ACCESS_CTRL_REG,
+					   RTL8366RB_PHY_CTRL_WRITE);
+			if (ret)
+				return ret;
+			ret = regmap_write(smi->map,
+					   rtl8366rb_green_jam[i][0],
+					   rtl8366rb_green_jam[i][1]);
+			if (ret)
+				return ret;
+			i++;
+		}
+	}
+	ret = regmap_write(smi->map,
+			   RTL8366RB_GREEN_FEATURE_REG,
+			   (chip_ver == 1) ? 0x0007 : 0x0003);
+	if (ret)
+		return ret;
+
+	/* Vendor driver sets 0x240 in registers 0xc and 0xd (undocumented) */
+	ret = regmap_write(smi->map, 0x0c, 0x240);
+	if (ret)
+		return ret;
+	ret = regmap_write(smi->map, 0x0d, 0x240);
+	if (ret)
+		return ret;
+
+	/* Set some random MAC address */
+	ret = rtl8366rb_set_addr(smi);
+	if (ret)
+		return ret;
+
+	/* Enable CPU port and enable inserting CPU tag
+	 *
+	 * Disabling RTL8368RB_CPU_INSTAG here will change the behaviour
+	 * of the switch totally and it will start talking Realtek RRCP
+	 * internally. It is probably possible to experiment with this,
+	 * but then the kernel needs to understand and handle RRCP first.
+	 */
+	ret = regmap_update_bits(smi->map, RTL8368RB_CPU_CTRL_REG,
+				 0xFFFF,
+				 RTL8368RB_CPU_INSTAG | BIT(smi->cpu_port));
+	if (ret)
+		return ret;
+
+	/* Make sure we default-enable the fixed CPU port */
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR,
+				 BIT(smi->cpu_port),
+				 0);
+	if (ret)
+		return ret;
+
+	/* Set maximum packet length to 1536 bytes */
+	ret = regmap_update_bits(smi->map, RTL8366RB_SGCR,
+				 RTL8366RB_SGCR_MAX_LENGTH_MASK,
+				 RTL8366RB_SGCR_MAX_LENGTH_1536);
+	if (ret)
+		return ret;
+
+	/* Enable learning for all ports */
+	ret = regmap_write(smi->map, RTL8366RB_SSCR0, 0);
+	if (ret)
+		return ret;
+
+	/* Enable auto ageing for all ports */
+	ret = regmap_write(smi->map, RTL8366RB_SSCR1, 0);
+	if (ret)
+		return ret;
+
+	/* Discard VLAN tagged packets if the port is not a member of
+	 * the VLAN with which the packets is associated.
+	 */
+	ret = regmap_write(smi->map, RTL8366RB_VLAN_INGRESS_CTRL2_REG,
+			   RTL8366RB_PORT_ALL);
+	if (ret)
+		return ret;
+
+	/* Don't drop packets whose DA has not been learned */
+	ret = regmap_update_bits(smi->map, RTL8366RB_SSCR2,
+				 RTL8366RB_SSCR2_DROP_UNKNOWN_DA, 0);
+	if (ret)
+		return ret;
+
+	/* Set blinking, TODO: make this configurable */
+	ret = regmap_update_bits(smi->map, RTL8366RB_LED_BLINKRATE_REG,
+				 RTL8366RB_LED_BLINKRATE_MASK,
+				 RTL8366RB_LED_BLINKRATE_56MS);
+	if (ret)
+		return ret;
+
+	/* Set up LED activity:
+	 * Each port has 4 LEDs, we configure all ports to the same
+	 * behaviour (no individual config) but we can set up each
+	 * LED separately.
+	 */
+	if (smi->leds_disabled) {
+		/* Turn everything off */
+		regmap_update_bits(smi->map,
+				   RTL8366RB_LED_0_1_CTRL_REG,
+				   0x0FFF, 0);
+		regmap_update_bits(smi->map,
+				   RTL8366RB_LED_2_3_CTRL_REG,
+				   0x0FFF, 0);
+		regmap_update_bits(smi->map,
+				   RTL8366RB_INTERRUPT_CONTROL_REG,
+				   RTL8366RB_P4_RGMII_LED,
+				   0);
+		val = RTL8366RB_LED_OFF;
+	} else {
+		/* TODO: make this configurable per LED */
+		val = RTL8366RB_LED_FORCE;
+	}
+	for (i = 0; i < 4; i++) {
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_CTRL_REG,
+					 0xf << (i * 4),
+					 val << (i * 4));
+		if (ret)
+			return ret;
+	}
+
+	ret = rtl8366_init_vlan(smi);
+	if (ret)
+		return ret;
+
+	ret = rtl8366rb_setup_cascaded_irq(smi);
+	if (ret)
+		dev_info(smi->dev, "no interrupt support\n");
+
+	ret = realtek_smi_setup_mdio(smi);
+	if (ret) {
+		dev_info(smi->dev, "could not set up MDIO bus\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static enum dsa_tag_protocol rtl8366_get_tag_protocol(struct dsa_switch *ds,
+						      int port)
+{
+	/* For now, the RTL switches are handled without any custom tags.
+	 *
+	 * It is possible to turn on "custom tags" by removing the
+	 * RTL8368RB_CPU_INSTAG flag when enabling the port but what it
+	 * does is unfamiliar to DSA: ethernet frames of type 8899, the Realtek
+	 * Remote Control Protocol (RRCP) start to appear on the CPU port of
+	 * the device. So this is not the ordinary few extra bytes in the
+	 * frame. Instead it appears that the switch starts to talk Realtek
+	 * RRCP internally which means a pretty complex RRCP implementation
+	 * decoding and responding the RRCP protocol is needed to exploit this.
+	 *
+	 * The OpenRRCP project (dormant since 2009) have reverse-egineered
+	 * parts of the protocol.
+	 */
+	return DSA_TAG_PROTO_NONE;
+}
+
+static void rtl8366rb_adjust_link(struct dsa_switch *ds, int port,
+				  struct phy_device *phydev)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	if (port != smi->cpu_port)
+		return;
+
+	dev_info(smi->dev, "adjust link on CPU port (%d)\n", port);
+
+	/* Force the fixed CPU port into 1Gbit mode, no autonegotiation */
+	ret = regmap_update_bits(smi->map, RTL8366RB_MAC_FORCE_CTRL_REG,
+				 BIT(port), BIT(port));
+	if (ret)
+		return;
+
+	ret = regmap_update_bits(smi->map, RTL8366RB_PAACR2,
+				 0xFF00U,
+				 RTL8366RB_PAACR_CPU_PORT << 8);
+	if (ret)
+		return;
+
+	/* Enable the CPU port */
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+				 0);
+	if (ret)
+		return;
+}
+
+static void rb8366rb_set_port_led(struct realtek_smi *smi,
+				  int port, bool enable)
+{
+	u16 val = enable ? 0x3f : 0;
+	int ret;
+
+	if (smi->leds_disabled)
+		return;
+
+	switch (port) {
+	case 0:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_0_1_CTRL_REG,
+					 0x3F, val);
+		break;
+	case 1:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_0_1_CTRL_REG,
+					 0x3F << RTL8366RB_LED_1_OFFSET,
+					 val << RTL8366RB_LED_1_OFFSET);
+		break;
+	case 2:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_2_3_CTRL_REG,
+					 0x3F, val);
+		break;
+	case 3:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_LED_2_3_CTRL_REG,
+					 0x3F << RTL8366RB_LED_3_OFFSET,
+					 val << RTL8366RB_LED_3_OFFSET);
+		break;
+	case 4:
+		ret = regmap_update_bits(smi->map,
+					 RTL8366RB_INTERRUPT_CONTROL_REG,
+					 RTL8366RB_P4_RGMII_LED,
+					 enable ? RTL8366RB_P4_RGMII_LED : 0);
+		break;
+	default:
+		dev_err(smi->dev, "no LED for port %d\n", port);
+		return;
+	}
+	if (ret)
+		dev_err(smi->dev, "error updating LED on port %d\n", port);
+}
+
+static int
+rtl8366rb_port_enable(struct dsa_switch *ds, int port,
+		      struct phy_device *phy)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	dev_dbg(smi->dev, "enable port %d\n", port);
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+				 0);
+	if (ret)
+		return ret;
+
+	rb8366rb_set_port_led(smi, port, true);
+	return 0;
+}
+
+static void
+rtl8366rb_port_disable(struct dsa_switch *ds, int port,
+		       struct phy_device *phy)
+{
+	struct realtek_smi *smi = ds->priv;
+	int ret;
+
+	dev_dbg(smi->dev, "disable port %d\n", port);
+	ret = regmap_update_bits(smi->map, RTL8366RB_PECR, BIT(port),
+				 BIT(port));
+	if (ret)
+		return;
+
+	rb8366rb_set_port_led(smi, port, false);
+}
+
+static int rtl8366rb_get_vlan_4k(struct realtek_smi *smi, u32 vid,
+				 struct rtl8366_vlan_4k *vlan4k)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	memset(vlan4k, '\0', sizeof(struct rtl8366_vlan_4k));
+
+	if (vid >= RTL8366RB_NUM_VIDS)
+		return -EINVAL;
+
+	/* write VID */
+	ret = regmap_write(smi->map, RTL8366RB_VLAN_TABLE_WRITE_BASE,
+			   vid & RTL8366RB_VLAN_VID_MASK);
+	if (ret)
+		return ret;
+
+	/* write table access control word */
+	ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+			   RTL8366RB_TABLE_VLAN_READ_CTRL);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_read(smi->map,
+				  RTL8366RB_VLAN_TABLE_READ_BASE + i,
+				  &data[i]);
+		if (ret)
+			return ret;
+	}
+
+	vlan4k->vid = vid;
+	vlan4k->untag = (data[1] >> RTL8366RB_VLAN_UNTAG_SHIFT) &
+			RTL8366RB_VLAN_UNTAG_MASK;
+	vlan4k->member = data[1] & RTL8366RB_VLAN_MEMBER_MASK;
+	vlan4k->fid = data[2] & RTL8366RB_VLAN_FID_MASK;
+
+	return 0;
+}
+
+static int rtl8366rb_set_vlan_4k(struct realtek_smi *smi,
+				 const struct rtl8366_vlan_4k *vlan4k)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	if (vlan4k->vid >= RTL8366RB_NUM_VIDS ||
+	    vlan4k->member > RTL8366RB_VLAN_MEMBER_MASK ||
+	    vlan4k->untag > RTL8366RB_VLAN_UNTAG_MASK ||
+	    vlan4k->fid > RTL8366RB_FIDMAX)
+		return -EINVAL;
+
+	data[0] = vlan4k->vid & RTL8366RB_VLAN_VID_MASK;
+	data[1] = (vlan4k->member & RTL8366RB_VLAN_MEMBER_MASK) |
+		  ((vlan4k->untag & RTL8366RB_VLAN_UNTAG_MASK) <<
+			RTL8366RB_VLAN_UNTAG_SHIFT);
+	data[2] = vlan4k->fid & RTL8366RB_VLAN_FID_MASK;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_write(smi->map,
+				   RTL8366RB_VLAN_TABLE_WRITE_BASE + i,
+				   data[i]);
+		if (ret)
+			return ret;
+	}
+
+	/* write table access control word */
+	ret = regmap_write(smi->map, RTL8366RB_TABLE_ACCESS_CTRL_REG,
+			   RTL8366RB_TABLE_VLAN_WRITE_CTRL);
+
+	return ret;
+}
+
+static int rtl8366rb_get_vlan_mc(struct realtek_smi *smi, u32 index,
+				 struct rtl8366_vlan_mc *vlanmc)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	memset(vlanmc, '\0', sizeof(struct rtl8366_vlan_mc));
+
+	if (index >= RTL8366RB_NUM_VLANS)
+		return -EINVAL;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_read(smi->map,
+				  RTL8366RB_VLAN_MC_BASE(index) + i,
+				  &data[i]);
+		if (ret)
+			return ret;
+	}
+
+	vlanmc->vid = data[0] & RTL8366RB_VLAN_VID_MASK;
+	vlanmc->priority = (data[0] >> RTL8366RB_VLAN_PRIORITY_SHIFT) &
+		RTL8366RB_VLAN_PRIORITY_MASK;
+	vlanmc->untag = (data[1] >> RTL8366RB_VLAN_UNTAG_SHIFT) &
+		RTL8366RB_VLAN_UNTAG_MASK;
+	vlanmc->member = data[1] & RTL8366RB_VLAN_MEMBER_MASK;
+	vlanmc->fid = data[2] & RTL8366RB_VLAN_FID_MASK;
+
+	return 0;
+}
+
+static int rtl8366rb_set_vlan_mc(struct realtek_smi *smi, u32 index,
+				 const struct rtl8366_vlan_mc *vlanmc)
+{
+	u32 data[3];
+	int ret;
+	int i;
+
+	if (index >= RTL8366RB_NUM_VLANS ||
+	    vlanmc->vid >= RTL8366RB_NUM_VIDS ||
+	    vlanmc->priority > RTL8366RB_PRIORITYMAX ||
+	    vlanmc->member > RTL8366RB_VLAN_MEMBER_MASK ||
+	    vlanmc->untag > RTL8366RB_VLAN_UNTAG_MASK ||
+	    vlanmc->fid > RTL8366RB_FIDMAX)
+		return -EINVAL;
+
+	data[0] = (vlanmc->vid & RTL8366RB_VLAN_VID_MASK) |
+		  ((vlanmc->priority & RTL8366RB_VLAN_PRIORITY_MASK) <<
+			RTL8366RB_VLAN_PRIORITY_SHIFT);
+	data[1] = (vlanmc->member & RTL8366RB_VLAN_MEMBER_MASK) |
+		  ((vlanmc->untag & RTL8366RB_VLAN_UNTAG_MASK) <<
+			RTL8366RB_VLAN_UNTAG_SHIFT);
+	data[2] = vlanmc->fid & RTL8366RB_VLAN_FID_MASK;
+
+	for (i = 0; i < 3; i++) {
+		ret = regmap_write(smi->map,
+				   RTL8366RB_VLAN_MC_BASE(index) + i,
+				   data[i]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int rtl8366rb_get_mc_index(struct realtek_smi *smi, int port, int *val)
+{
+	u32 data;
+	int ret;
+
+	if (port >= smi->num_ports)
+		return -EINVAL;
+
+	ret = regmap_read(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+			  &data);
+	if (ret)
+		return ret;
+
+	*val = (data >> RTL8366RB_PORT_VLAN_CTRL_SHIFT(port)) &
+		RTL8366RB_PORT_VLAN_CTRL_MASK;
+
+	return 0;
+}
+
+static int rtl8366rb_set_mc_index(struct realtek_smi *smi, int port, int index)
+{
+	if (port >= smi->num_ports || index >= RTL8366RB_NUM_VLANS)
+		return -EINVAL;
+
+	return regmap_update_bits(smi->map, RTL8366RB_PORT_VLAN_CTRL_REG(port),
+				RTL8366RB_PORT_VLAN_CTRL_MASK <<
+					RTL8366RB_PORT_VLAN_CTRL_SHIFT(port),
+				(index & RTL8366RB_PORT_VLAN_CTRL_MASK) <<
+					RTL8366RB_PORT_VLAN_CTRL_SHIFT(port));
+}
+
+static bool rtl8366rb_is_vlan_valid(struct realtek_smi *smi, unsigned int vlan)
+{
+	unsigned int max = RTL8366RB_NUM_VLANS;
+
+	if (smi->vlan4k_enabled)
+		max = RTL8366RB_NUM_VIDS - 1;
+
+	if (vlan == 0 || vlan >= max)
+		return false;
+
+	return true;
+}
+
+static int rtl8366rb_enable_vlan(struct realtek_smi *smi, bool enable)
+{
+	dev_dbg(smi->dev, "%s VLAN\n", enable ? "enable" : "disable");
+	return regmap_update_bits(smi->map,
+				  RTL8366RB_SGCR, RTL8366RB_SGCR_EN_VLAN,
+				  enable ? RTL8366RB_SGCR_EN_VLAN : 0);
+}
+
+static int rtl8366rb_enable_vlan4k(struct realtek_smi *smi, bool enable)
+{
+	dev_dbg(smi->dev, "%s VLAN 4k\n", enable ? "enable" : "disable");
+	return regmap_update_bits(smi->map, RTL8366RB_SGCR,
+				  RTL8366RB_SGCR_EN_VLAN_4KTB,
+				  enable ? RTL8366RB_SGCR_EN_VLAN_4KTB : 0);
+}
+
+static int rtl8366rb_phy_read(struct realtek_smi *smi, int phy, int regnum)
+{
+	u32 val;
+	u32 reg;
+	int ret;
+
+	if (phy > RTL8366RB_PHY_NO_MAX)
+		return -EINVAL;
+
+	ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+			   RTL8366RB_PHY_CTRL_READ);
+	if (ret)
+		return ret;
+
+	reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
+
+	ret = regmap_write(smi->map, reg, 0);
+	if (ret) {
+		dev_err(smi->dev,
+			"failed to write PHY%d reg %04x @ %04x, ret %d\n",
+			phy, regnum, reg, ret);
+		return ret;
+	}
+
+	ret = regmap_read(smi->map, RTL8366RB_PHY_ACCESS_DATA_REG, &val);
+	if (ret)
+		return ret;
+
+	dev_dbg(smi->dev, "read PHY%d register 0x%04x @ %08x, val <- %04x\n",
+		phy, regnum, reg, val);
+
+	return val;
+}
+
+static int rtl8366rb_phy_write(struct realtek_smi *smi, int phy, int regnum,
+			       u16 val)
+{
+	u32 reg;
+	int ret;
+
+	if (phy > RTL8366RB_PHY_NO_MAX)
+		return -EINVAL;
+
+	ret = regmap_write(smi->map, RTL8366RB_PHY_ACCESS_CTRL_REG,
+			   RTL8366RB_PHY_CTRL_WRITE);
+	if (ret)
+		return ret;
+
+	reg = 0x8000 | (1 << (phy + RTL8366RB_PHY_NO_OFFSET)) | regnum;
+
+	dev_dbg(smi->dev, "write PHY%d register 0x%04x @ %04x, val -> %04x\n",
+		phy, regnum, reg, val);
+
+	ret = regmap_write(smi->map, reg, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int rtl8366rb_reset_chip(struct realtek_smi *smi)
+{
+	int timeout = 10;
+	u32 val;
+	int ret;
+
+	realtek_smi_write_reg_noack(smi, RTL8366RB_RESET_CTRL_REG,
+				    RTL8366RB_CHIP_CTRL_RESET_HW);
+	do {
+		usleep_range(20000, 25000);
+		ret = regmap_read(smi->map, RTL8366RB_RESET_CTRL_REG, &val);
+		if (ret)
+			return ret;
+
+		if (!(val & RTL8366RB_CHIP_CTRL_RESET_HW))
+			break;
+	} while (--timeout);
+
+	if (!timeout) {
+		dev_err(smi->dev, "timeout waiting for the switch to reset\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int rtl8366rb_detect(struct realtek_smi *smi)
+{
+	struct device *dev = smi->dev;
+	int ret;
+	u32 val;
+
+	/* Detect device */
+	ret = regmap_read(smi->map, 0x5c, &val);
+	if (ret) {
+		dev_err(dev, "can't get chip ID (%d)\n", ret);
+		return ret;
+	}
+
+	switch (val) {
+	case 0x6027:
+		dev_info(dev, "found an RTL8366S switch\n");
+		dev_err(dev, "this switch is not yet supported, submit patches!\n");
+		return -ENODEV;
+	case 0x5937:
+		dev_info(dev, "found an RTL8366RB switch\n");
+		smi->cpu_port = RTL8366RB_PORT_NUM_CPU;
+		smi->num_ports = RTL8366RB_NUM_PORTS;
+		smi->num_vlan_mc = RTL8366RB_NUM_VLANS;
+		smi->mib_counters = rtl8366rb_mib_counters;
+		smi->num_mib_counters = ARRAY_SIZE(rtl8366rb_mib_counters);
+		break;
+	default:
+		dev_info(dev, "found an Unknown Realtek switch (id=0x%04x)\n",
+			 val);
+		break;
+	}
+
+	ret = rtl8366rb_reset_chip(smi);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static const struct dsa_switch_ops rtl8366rb_switch_ops = {
+	.get_tag_protocol = rtl8366_get_tag_protocol,
+	.setup = rtl8366rb_setup,
+	.adjust_link = rtl8366rb_adjust_link,
+	.get_strings = rtl8366_get_strings,
+	.get_ethtool_stats = rtl8366_get_ethtool_stats,
+	.get_sset_count = rtl8366_get_sset_count,
+	.port_vlan_filtering = rtl8366_vlan_filtering,
+	.port_vlan_prepare = rtl8366_vlan_prepare,
+	.port_vlan_add = rtl8366_vlan_add,
+	.port_vlan_del = rtl8366_vlan_del,
+	.port_enable = rtl8366rb_port_enable,
+	.port_disable = rtl8366rb_port_disable,
+};
+
+static const struct realtek_smi_ops rtl8366rb_smi_ops = {
+	.detect		= rtl8366rb_detect,
+	.get_vlan_mc	= rtl8366rb_get_vlan_mc,
+	.set_vlan_mc	= rtl8366rb_set_vlan_mc,
+	.get_vlan_4k	= rtl8366rb_get_vlan_4k,
+	.set_vlan_4k	= rtl8366rb_set_vlan_4k,
+	.get_mc_index	= rtl8366rb_get_mc_index,
+	.set_mc_index	= rtl8366rb_set_mc_index,
+	.get_mib_counter = rtl8366rb_get_mib_counter,
+	.is_vlan_valid	= rtl8366rb_is_vlan_valid,
+	.enable_vlan	= rtl8366rb_enable_vlan,
+	.enable_vlan4k	= rtl8366rb_enable_vlan4k,
+	.phy_read	= rtl8366rb_phy_read,
+	.phy_write	= rtl8366rb_phy_write,
+};
+
+const struct realtek_smi_variant rtl8366rb_variant = {
+	.ds_ops = &rtl8366rb_switch_ops,
+	.ops = &rtl8366rb_smi_ops,
+	.clk_delay = 10,
+	.cmd_read = 0xa9,
+	.cmd_write = 0xa8,
+};
+EXPORT_SYMBOL_GPL(rtl8366rb_variant);
-- 
cgit v1.2.3


From 22a001e8544fa9d89a1d3d7491ca1d8f9466b69d Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Sat, 14 Jul 2018 11:45:56 +0200
Subject: ARM: dts: Add ethernet and switch to D-Link DIR-685

This adds the Ethernet and Realtek switch device to the
D-Link DIR-685 Gemini-based device.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm/boot/dts/gemini-dlink-dir-685.dts | 140 ++++++++++++++++++++++++++++-
 1 file changed, 139 insertions(+), 1 deletion(-)

diff --git a/arch/arm/boot/dts/gemini-dlink-dir-685.dts b/arch/arm/boot/dts/gemini-dlink-dir-685.dts
index fb5c954ab95a..6f258b50eb44 100644
--- a/arch/arm/boot/dts/gemini-dlink-dir-685.dts
+++ b/arch/arm/boot/dts/gemini-dlink-dir-685.dts
@@ -156,6 +156,100 @@
 		};
 	};
 
+	/* This is a RealTek RTL8366RB switch and PHY using SMI over GPIO */
+	switch {
+		compatible = "realtek,rtl8366rb";
+		/* 22 = MDIO (has input reads), 21 = MDC (clock, output only) */
+		mdc-gpios = <&gpio0 21 GPIO_ACTIVE_HIGH>;
+		mdio-gpios = <&gpio0 22 GPIO_ACTIVE_HIGH>;
+		reset-gpios = <&gpio0 14 GPIO_ACTIVE_LOW>;
+		realtek,disable-leds;
+
+		switch_intc: interrupt-controller {
+			/* GPIO 15 provides the interrupt */
+			interrupt-parent = <&gpio0>;
+			interrupts = <15 IRQ_TYPE_LEVEL_LOW>;
+			interrupt-controller;
+			#address-cells = <0>;
+			#interrupt-cells = <1>;
+		};
+
+		ports {
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			port@0 {
+				reg = <0>;
+				label = "lan0";
+				phy-handle = <&phy0>;
+			};
+			port@1 {
+				reg = <1>;
+				label = "lan1";
+				phy-handle = <&phy1>;
+			};
+			port@2 {
+				reg = <2>;
+				label = "lan2";
+				phy-handle = <&phy2>;
+			};
+			port@3 {
+				reg = <3>;
+				label = "lan3";
+				phy-handle = <&phy3>;
+			};
+			port@4 {
+				reg = <4>;
+				label = "wan";
+				phy-handle = <&phy4>;
+			};
+			rtl8366rb_cpu_port: port@5 {
+				reg = <5>;
+				label = "cpu";
+				ethernet = <&gmac0>;
+				phy-mode = "rgmii";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+					pause;
+				};
+			};
+
+		};
+
+		mdio {
+			compatible = "realtek,smi-mdio";
+			#address-cells = <1>;
+			#size-cells = <0>;
+
+			phy0: phy@0 {
+				reg = <0>;
+				interrupt-parent = <&switch_intc>;
+				interrupts = <0>;
+			};
+			phy1: phy@1 {
+				reg = <1>;
+				interrupt-parent = <&switch_intc>;
+				interrupts = <1>;
+			};
+			phy2: phy@2 {
+				reg = <2>;
+				interrupt-parent = <&switch_intc>;
+				interrupts = <2>;
+			};
+			phy3: phy@3 {
+				reg = <3>;
+				interrupt-parent = <&switch_intc>;
+				interrupts = <3>;
+			};
+			phy4: phy@4 {
+				reg = <4>;
+				interrupt-parent = <&switch_intc>;
+				interrupts = <12>;
+			};
+		};
+	};
+
 	soc {
 		flash@30000000 {
 			/*
@@ -223,10 +317,12 @@
 				 * gpio0bgrp cover line 7 used by WPS LED
 				 * gpio0cgrp cover line 8, 13 used by keys
 				 *           and 11, 12 used by the HD LEDs
+				 *           and line 14, 15 used by RTL8366
+				 *           RESET and phy ready
 				 * gpio0egrp cover line 16 used by VDISP
 				 * gpio0fgrp cover line 17 used by TK IRQ
 				 * gpio0ggrp cover line 20 used by panel CS
-				 * gpio0hgrp cover line 21,22 used by RTL8366RB
+				 * gpio0hgrp cover line 21,22 used by RTL8366RB MDIO
 				 */
 				gpio0_default_pins: pinctrl-gpio0 {
 					mux {
@@ -250,6 +346,32 @@
 						groups = "gpio1bgrp";
 					};
 				};
+				pinctrl-gmii {
+					mux {
+						function = "gmii";
+						groups = "gmii_gmac0_grp";
+					};
+					conf0 {
+						pins = "V8 GMAC0 RXDV", "T10 GMAC1 RXDV",
+						     "Y7 GMAC0 RXC", "Y11 GMAC1 RXC",
+						     "T8 GMAC0 TXEN", "W11 GMAC1 TXEN",
+						     "U8 GMAC0 TXC", "V11 GMAC1 TXC",
+						     "W8 GMAC0 RXD0", "V9 GMAC0 RXD1",
+						     "Y8 GMAC0 RXD2", "U9 GMAC0 RXD3",
+						     "T7 GMAC0 TXD0", "U6 GMAC0 TXD1",
+						     "V7 GMAC0 TXD2", "U7 GMAC0 TXD3",
+						     "Y12 GMAC1 RXD0", "V12 GMAC1 RXD1",
+						     "T11 GMAC1 RXD2", "W12 GMAC1 RXD3",
+						     "U10 GMAC1 TXD0", "Y10 GMAC1 TXD1",
+						     "W10 GMAC1 TXD2", "T9 GMAC1 TXD3";
+						skew-delay = <7>;
+					};
+					/* Set up drive strength on GMAC0 to 16 mA */
+					conf1 {
+						groups = "gmii_gmac0_grp";
+						drive-strength = <16>;
+					};
+				};
 			};
 		};
 
@@ -291,6 +413,22 @@
 				<0x6000 0 0 4 &pci_intc 2>;
 		};
 
+		ethernet@60000000 {
+			status = "okay";
+
+			ethernet-port@0 {
+				phy-mode = "rgmii";
+				fixed-link {
+					speed = <1000>;
+					full-duplex;
+					pause;
+				};
+			};
+			ethernet-port@1 {
+				/* Not used in this platform */
+			};
+		};
+
 		ata@63000000 {
 			status = "okay";
 		};
-- 
cgit v1.2.3


From 12ba2c65f9d3d6996d1e909921151487b009dd30 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Tue, 13 Feb 2018 22:10:42 +0100
Subject: PM / devfreq: exynos-ppmu: Delete an error message for a failed
 memory allocation in exynos_ppmu_probe()

Omit an extra message for a memory allocation failure in this function.

This issue was detected by using the Coccinelle software.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Acked-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/event/exynos-ppmu.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index 3cd6a184fe7c..a9c64f0d3284 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -627,11 +627,9 @@ static int exynos_ppmu_probe(struct platform_device *pdev)
 
 	size = sizeof(struct devfreq_event_dev *) * info->num_events;
 	info->edev = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
-	if (!info->edev) {
-		dev_err(&pdev->dev,
-			"failed to allocate memory devfreq-event devices\n");
+	if (!info->edev)
 		return -ENOMEM;
-	}
+
 	edev = info->edev;
 	platform_set_drvdata(pdev, info);
 
-- 
cgit v1.2.3


From 2d803dc8f7a5f622ac47c3b650834ada3a2659b9 Mon Sep 17 00:00:00 2001
From: Arvind Yadav <arvind.yadav.cs@gmail.com>
Date: Fri, 30 Mar 2018 17:14:03 +0530
Subject: PM / devfreq: use put_device() instead of kfree()

Never directly free @dev after calling device_register() or
device_unregister(), even if device_register() returned an error.
Always use put_device() to give up the reference initialized.

Signed-off-by: Arvind Yadav <arvind.yadav.cs@gmail.com>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/devfreq.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 0b5b3abe054e..e26adf67e218 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -625,7 +625,8 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	err = device_register(&devfreq->dev);
 	if (err) {
 		mutex_unlock(&devfreq->lock);
-		goto err_dev;
+		put_device(&devfreq->dev);
+		goto err_out;
 	}
 
 	devfreq->trans_table =
@@ -672,6 +673,7 @@ err_init:
 	mutex_unlock(&devfreq_list_lock);
 
 	device_unregister(&devfreq->dev);
+	devfreq = NULL;
 err_dev:
 	if (devfreq)
 		kfree(devfreq);
-- 
cgit v1.2.3


From 2d2894c94a61930615cd1411cd8e0bf5b804e3a1 Mon Sep 17 00:00:00 2001
From: Nick Milner <nick.milner@collabora.com>
Date: Wed, 9 May 2018 14:57:43 +0200
Subject: dt-bindings: devfreq: rk3399_dmc: improve binding documentation.

There are several typos, references to non existent files, grammar and
punctuation mistakes in the rk3399_dmc.txt binding. This patch tries
to improve the binding documentation and fix these mistakes.

Signed-off-by: Nick Milner <nick.milner@collabora.com>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Rob Herring <robh@kernel.org>
- [1/5] Fix some attributes to match with the code s/_disb/_dis/
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 .../devicetree/bindings/devfreq/rk3399_dmc.txt     | 205 +++++++++++----------
 1 file changed, 104 insertions(+), 101 deletions(-)

diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
index fc2bcbe26b1e..1b93b33c7d38 100644
--- a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
+++ b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
@@ -1,14 +1,14 @@
-* Rockchip rk3399 DMC(Dynamic Memory Controller) device
+* Rockchip rk3399 DMC (Dynamic Memory Controller) device
 
 Required properties:
 - compatible:		 Must be "rockchip,rk3399-dmc".
 - devfreq-events:	 Node to get DDR loading, Refer to
-			 Documentation/devicetree/bindings/devfreq/
+			 Documentation/devicetree/bindings/devfreq/event/
 			 rockchip-dfi.txt
-- interrupts:		 The interrupt number to the CPU. The interrupt
-			 specifier format depends on the interrupt controller.
-			 It should be DCF interrupts, when DDR dvfs finish,
-			 it will happen.
+- interrupts:		 The CPU interrupt number. The interrupt specifier
+			 format depends on the interrupt controller.
+			 It should be a DCF interrupt. When DDR DVFS finishes
+			 a DCF interrupt is triggered.
 - clocks:		 Phandles for clock specified in "clock-names" property
 - clock-names :		 The name of clock used by the DFI, must be
 			 "pclk_ddr_mon";
@@ -17,139 +17,142 @@ Required properties:
 - center-supply:	 DMC supply node.
 - status:		 Marks the node enabled/disabled.
 
-Following properties are ddr timing:
+Following properties relate to DDR timing:
 
 - rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/ddr.h,
-				  it select ddr3 cl-trp-trcd type, default value
-				  "DDR3_DEFAULT".it must selected according to
-				  "Speed Bin" in ddr3 datasheet, DO NOT use
-				  smaller "Speed Bin" than ddr3 exactly is.
-
-- rockchip,pd_idle :		  Config the PD_IDLE value, defined the power-down
-				  idle period, memories are places into power-down
-				  mode if bus is idle for PD_IDLE DFI clocks.
-
-- rockchip,sr_idle :		  Configure the SR_IDLE value, defined the
-				  selfrefresh idle period, memories are places
-				  into self-refresh mode if bus is idle for
-				  SR_IDLE*1024 DFI clocks (DFI clocks freq is
-				  half of dram's clocks), defaule value is "0".
-
-- rockchip,sr_mc_gate_idle :	  Defined the self-refresh with memory and
-				  controller clock gating idle period, memories
-				  are places into self-refresh mode and memory
-				  controller clock arg gating if bus is idle for
-				  sr_mc_gate_idle*1024 DFI clocks.
-
-- rockchip,srpd_lite_idle :	  Defined the self-refresh power down idle
-				  period, memories are places into self-refresh
-				  power down mode if bus is idle for
-				  srpd_lite_idle*1024 DFI clocks. This parameter
-				  is for LPDDR4 only.
-
-- rockchip,standby_idle :	  Defined the standby idle period, memories are
-				  places into self-refresh than controller, pi,
-				  phy and dram clock will gating if bus is idle
-				  for standby_idle * DFI clocks.
-
-- rockchip,dram_dll_disb_freq :  It's defined the DDR3 dll bypass frequency in
-				  MHz, when ddr freq less than DRAM_DLL_DISB_FREQ,
-				  ddr3 dll will bypssed note: if dll was bypassed,
-				  the odt also stop working.
-
-- rockchip,phy_dll_disb_freq :	  Defined the PHY dll bypass frequency in
-				  MHz (Mega Hz), when ddr freq less than
-				  DRAM_DLL_DISB_FREQ, phy dll will bypssed.
-				  note: phy dll and phy odt are independent.
-
-- rockchip,ddr3_odt_disb_freq :  When dram type is DDR3, this parameter defined
-				  the odt disable frequency in MHz (Mega Hz),
-				  when ddr frequency less then ddr3_odt_disb_freq,
-				  the odt on dram side and controller side are
+				  it selects the DDR3 cl-trp-trcd type. It must be
+				  set according to "Speed Bin" in DDR3 datasheet,
+				  DO NOT use a smaller "Speed Bin" than specified
+				  for the DDR3 being used.
+
+- rockchip,pd_idle :		  Configure the PD_IDLE value. Defines the
+				  power-down idle period in which memories are
+				  placed into power-down mode if bus is idle
+				  for PD_IDLE DFI clock cycles.
+
+- rockchip,sr_idle :		  Configure the SR_IDLE value. Defines the
+				  self-refresh idle period in which memories are
+				  placed into self-refresh mode if bus is idle
+				  for SR_IDLE * 1024 DFI clock cycles (DFI
+				  clocks freq is half of DRAM clock), default
+				  value is "0".
+
+- rockchip,sr_mc_gate_idle :	  Defines the memory self-refresh and controller
+				  clock gating idle period. Memories are placed
+				  into self-refresh mode and memory controller
+				  clock arg gating started if bus is idle for
+				  sr_mc_gate_idle*1024 DFI clock cycles.
+
+- rockchip,srpd_lite_idle :	  Defines the self-refresh power down idle
+				  period in which memories are placed into
+				  self-refresh power down mode if bus is idle
+				  for srpd_lite_idle * 1024 DFI clock cycles.
+				  This parameter is for LPDDR4 only.
+
+- rockchip,standby_idle :	  Defines the standby idle period in which
+				  memories are placed into self-refresh mode.
+				  The controller, pi, PHY and DRAM clock will
+				  be gated if bus is idle for standby_idle * DFI
+				  clock cycles.
+
+- rockchip,dram_dll_dis_freq :	  Defines the DDR3 DLL bypass frequency in MHz.
+				  When DDR frequency is less than DRAM_DLL_DISB_FREQ,
+				  DDR3 DLL will be bypassed. Note: if DLL was bypassed,
+				  the odt will also stop working.
+
+- rockchip,phy_dll_dis_freq :	  Defines the PHY dll bypass frequency in
+				  MHz (Mega Hz). When DDR frequency is less than
+				  DRAM_DLL_DISB_FREQ, PHY DLL will be bypassed.
+				  Note: PHY DLL and PHY ODT are independent.
+
+- rockchip,ddr3_odt_dis_freq :	  When the DRAM type is DDR3, this parameter defines
+				  the ODT disable frequency in MHz (Mega Hz).
+				  when the DDR frequency is  less then ddr3_odt_dis_freq,
+				  the ODT on the DRAM side and controller side are
 				  both disabled.
 
-- rockchip,ddr3_drv :		  When dram type is DDR3, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,ddr3_drv :		  When the DRAM type is DDR3, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is DDR3_DS_40ohm.
 
-- rockchip,ddr3_odt :		  When dram type is DDR3, this parameter define
-				  the dram side ODT stength in ohm, default value
+- rockchip,ddr3_odt :		  When the DRAM type is DDR3, this parameter defines
+				  the DRAM side ODT strength in ohms. Default value
 				  is DDR3_ODT_120ohm.
 
-- rockchip,phy_ddr3_ca_drv :	  When dram type is DDR3, this parameter define
-				  the phy side CA line(incluing command line,
+- rockchip,phy_ddr3_ca_drv :	  When the DRAM type is DDR3, this parameter defines
+				  the phy side CA line (incluing command line,
 				  address line and clock line) driver strength.
 				  Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_ddr3_dq_drv :	  When dram type is DDR3, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is PHY_DRV_ODT_40.
+- rockchip,phy_ddr3_dq_drv :	  When the DRAM type is DDR3, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_ddr3_odt : 	  When dram type is DDR3, this parameter define the
-				  phy side odt strength, default value is
+- rockchip,phy_ddr3_odt : 	  When the DRAM type is DDR3, this parameter defines
+				  the PHY side ODT strength. Default value is
 				  PHY_DRV_ODT_240.
 
-- rockchip,lpddr3_odt_disb_freq : When dram type is LPDDR3, this parameter defined
-				  then odt disable frequency in MHz (Mega Hz),
-				  when ddr frequency less then ddr3_odt_disb_freq,
-				  the odt on dram side and controller side are
+- rockchip,lpddr3_odt_dis_freq : When the DRAM type is LPDDR3, this parameter defines
+				  then ODT disable frequency in MHz (Mega Hz).
+				  When DDR frequency is less then ddr3_odt_dis_freq,
+				  the ODT on the DRAM side and controller side are
 				  both disabled.
 
-- rockchip,lpddr3_drv :	  When dram type is LPDDR3, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,lpddr3_drv :		  When the DRAM type is LPDDR3, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is LP3_DS_34ohm.
 
-- rockchip,lpddr3_odt :	  When dram type is LPDDR3, this parameter define
-				  the dram side ODT stength in ohm, default value
+- rockchip,lpddr3_odt :		  When the DRAM type is LPDDR3, this parameter defines
+				  the DRAM side ODT strength in ohms. Default value
 				  is LP3_ODT_240ohm.
 
-- rockchip,phy_lpddr3_ca_drv :	  When dram type is LPDDR3, this parameter define
-				  the phy side CA line(incluing command line,
+- rockchip,phy_lpddr3_ca_drv :	  When the DRAM type is LPDDR3, this parameter defines
+				  the PHY side CA line (including command line,
 				  address line and clock line) driver strength.
-				  default value is PHY_DRV_ODT_40.
+				  Default value is PHY_DRV_ODT_40.
 
-- rockchip,phy_lpddr3_dq_drv :	  When dram type is LPDDR3, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is
+- rockchip,phy_lpddr3_dq_drv :	  When the DRAM type is LPDDR3, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is
 				  PHY_DRV_ODT_40.
 
 - rockchip,phy_lpddr3_odt : 	  When dram type is LPDDR3, this parameter define
 				  the phy side odt strength, default value is
 				  PHY_DRV_ODT_240.
 
-- rockchip,lpddr4_odt_disb_freq : When dram type is LPDDR4, this parameter
-				  defined the odt disable frequency in
-				  MHz (Mega Hz), when ddr frequency less then
-				  ddr3_odt_disb_freq, the odt on dram side and
+- rockchip,lpddr4_odt_dis_freq : When the DRAM type is LPDDR4, this parameter
+				  defines the ODT disable frequency in
+				  MHz (Mega Hz). When the DDR frequency is less then
+				  ddr3_odt_dis_freq, the ODT on the DRAM side and
 				  controller side are both disabled.
 
-- rockchip,lpddr4_drv :	  When dram type is LPDDR4, this parameter define
-				  the dram side driver stength in ohm, default
+- rockchip,lpddr4_drv :		  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side driver strength in ohms. Default
 				  value is LP4_PDDS_60ohm.
 
-- rockchip,lpddr4_dq_odt : 	  When dram type is LPDDR4, this parameter define
-				  the dram side ODT on dqs/dq line stength in ohm,
-				  default value is LP4_DQ_ODT_40ohm.
+- rockchip,lpddr4_dq_odt : 	  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side ODT on DQS/DQ line strength in ohms.
+				  Default value is LP4_DQ_ODT_40ohm.
 
-- rockchip,lpddr4_ca_odt :	  When dram type is LPDDR4, this parameter define
-				  the dram side ODT on ca line stength in ohm,
-				  default value is LP4_CA_ODT_40ohm.
+- rockchip,lpddr4_ca_odt :	  When the DRAM type is LPDDR4, this parameter defines
+				  the DRAM side ODT on CA line strength in ohms.
+				  Default value is LP4_CA_ODT_40ohm.
 
-- rockchip,phy_lpddr4_ca_drv :	  When dram type is LPDDR4, this parameter define
-				  the phy side  CA line(incluing command address
-				  line) driver strength. default value is
+- rockchip,phy_lpddr4_ca_drv :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side CA line (including command address
+				  line) driver strength. Default value is
 				  PHY_DRV_ODT_40.
 
-- rockchip,phy_lpddr4_ck_cs_drv : When dram type is LPDDR4, this parameter define
-				  the phy side clock line and cs line driver
-				  strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_ck_cs_drv : When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side clock line and CS line driver
+				  strength. Default value is PHY_DRV_ODT_80.
 
-- rockchip,phy_lpddr4_dq_drv :	  When dram type is LPDDR4, this parameter define
-				  the phy side DQ line(incluing DQS/DQ/DM line)
-				  driver strength. default value is PHY_DRV_ODT_80.
+- rockchip,phy_lpddr4_dq_drv :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side DQ line (including DQS/DQ/DM line)
+				  driver strength. Default value is PHY_DRV_ODT_80.
 
-- rockchip,phy_lpddr4_odt :	  When dram type is LPDDR4, this parameter define
-				  the phy side odt strength, default value is
+- rockchip,phy_lpddr4_odt :	  When the DRAM type is LPDDR4, this parameter defines
+				  the PHY side ODT strength. Default value is
 				  PHY_DRV_ODT_60.
 
 Example:
-- 
cgit v1.2.3


From 49502b23e0e45b57b776490cfdfd95ea7fecd7c7 Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Wed, 9 May 2018 14:57:44 +0200
Subject: dt-bindings: clock: add rk3399 DDR3 standard speed bins.

DDR3 SDRAM Standard (JESD79-3F) defines some standard speed bins for
DDR3 memories. The rk3399_dmc driver allows you to pass these values via
the device tree. For that purpose the devfreq/rk3399_dmc.txt binding
refers to a ddr.h file which does not exist. This patch adds the missing
defines in a include file called rk3399-ddr.h with the definition of
standard speed bins according to the ARM Trusted Firmware (ATF).

Fixes: c1ceb8f7c167 (Documentation: bindings: add dt documentation for rk3399 dmc)
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 .../devicetree/bindings/devfreq/rk3399_dmc.txt     |  2 +-
 include/dt-bindings/clock/rk3399-ddr.h             | 56 ++++++++++++++++++++++
 2 files changed, 57 insertions(+), 1 deletion(-)
 create mode 100644 include/dt-bindings/clock/rk3399-ddr.h

diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
index 1b93b33c7d38..e0030a139383 100644
--- a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
+++ b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
@@ -19,7 +19,7 @@ Required properties:
 
 Following properties relate to DDR timing:
 
-- rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/ddr.h,
+- rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/rk3399-ddr.h,
 				  it selects the DDR3 cl-trp-trcd type. It must be
 				  set according to "Speed Bin" in DDR3 datasheet,
 				  DO NOT use a smaller "Speed Bin" than specified
diff --git a/include/dt-bindings/clock/rk3399-ddr.h b/include/dt-bindings/clock/rk3399-ddr.h
new file mode 100644
index 000000000000..ed2280844963
--- /dev/null
+++ b/include/dt-bindings/clock/rk3399-ddr.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR MIT) */
+
+#ifndef DT_BINDINGS_DDR_H
+#define DT_BINDINGS_DDR_H
+
+/*
+ * DDR3 SDRAM Standard Speed Bins include tCK, tRCD, tRP, tRAS and tRC for
+ * each corresponding bin.
+ */
+
+/* DDR3-800 (5-5-5) */
+#define DDR3_800D	0
+/* DDR3-800 (6-6-6) */
+#define DDR3_800E	1
+/* DDR3-1066 (6-6-6) */
+#define DDR3_1066E	2
+/* DDR3-1066 (7-7-7) */
+#define DDR3_1066F	3
+/* DDR3-1066 (8-8-8) */
+#define DDR3_1066G	4
+/* DDR3-1333 (7-7-7) */
+#define DDR3_1333F	5
+/* DDR3-1333 (8-8-8) */
+#define DDR3_1333G	6
+/* DDR3-1333 (9-9-9) */
+#define DDR3_1333H	7
+/* DDR3-1333 (10-10-10) */
+#define DDR3_1333J 	8
+/* DDR3-1600 (8-8-8) */
+#define DDR3_1600G	9
+/* DDR3-1600 (9-9-9) */
+#define DDR3_1600H	10
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1600J	11
+/* DDR3-1600 (11-11-11) */
+#define DDR3_1600K	12
+/* DDR3-1600 (10-10-10) */
+#define DDR3_1866J	13
+/* DDR3-1866 (11-11-11) */
+#define DDR3_1866K	14
+/* DDR3-1866 (12-12-12) */
+#define DDR3_1866L	15
+/* DDR3-1866 (13-13-13) */
+#define DDR3_1866M	16
+/* DDR3-2133 (11-11-11) */
+#define DDR3_2133K	17
+/* DDR3-2133 (12-12-12) */
+#define DDR3_2133L	18
+/* DDR3-2133 (13-13-13) */
+#define DDR3_2133M	19
+/* DDR3-2133 (14-14-14) */
+#define DDR3_2133N	20
+/* DDR3 ATF default */
+#define DDR3_DEFAULT	21
+
+#endif
-- 
cgit v1.2.3


From 90dd72e1290dd86c4b6e5c421fcd13e60e625782 Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Wed, 9 May 2018 14:57:45 +0200
Subject: PM / devfreq: rk3399_dmc: remove wait for dcf irq event.

We have already wait dcf done in ATF, so don't need wait dcf irq
in kernel, besides, clear dcf irq in kernel will import competiton
between kernel and ATF, only handle dcf irq in ATF is a better way.

Signed-off-by: Lin Huang <hl@rock-chips.com>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/rk3399_dmc.c | 53 +-------------------------------------------
 1 file changed, 1 insertion(+), 52 deletions(-)

diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 5dfbfa3cc878..44a379657cd5 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -68,15 +68,6 @@ struct rk3399_dmcfreq {
 	struct devfreq_event_dev *edev;
 	struct mutex lock;
 	struct dram_timing timing;
-
-	/*
-	 * DDR Converser of Frequency (DCF) is used to implement DDR frequency
-	 * conversion without the participation of CPU, we will implement and
-	 * control it in arm trust firmware.
-	 */
-	wait_queue_head_t	wait_dcf_queue;
-	int irq;
-	int wait_dcf_flag;
 	struct regulator *vdd_center;
 	unsigned long rate, target_rate;
 	unsigned long volt, target_volt;
@@ -117,7 +108,6 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 			goto out;
 		}
 	}
-	dmcfreq->wait_dcf_flag = 1;
 
 	err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
 	if (err) {
@@ -128,14 +118,6 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		goto out;
 	}
 
-	/*
-	 * Wait until bcf irq happen, it means freq scaling finish in
-	 * arm trust firmware, use 100ms as timeout time.
-	 */
-	if (!wait_event_timeout(dmcfreq->wait_dcf_queue,
-				!dmcfreq->wait_dcf_flag, HZ / 10))
-		dev_warn(dev, "Timeout waiting for dcf interrupt\n");
-
 	/*
 	 * Check the dpll rate,
 	 * There only two result we will get,
@@ -241,22 +223,6 @@ static __maybe_unused int rk3399_dmcfreq_resume(struct device *dev)
 static SIMPLE_DEV_PM_OPS(rk3399_dmcfreq_pm, rk3399_dmcfreq_suspend,
 			 rk3399_dmcfreq_resume);
 
-static irqreturn_t rk3399_dmc_irq(int irq, void *dev_id)
-{
-	struct rk3399_dmcfreq *dmcfreq = dev_id;
-	struct arm_smccc_res res;
-
-	dmcfreq->wait_dcf_flag = 0;
-	wake_up(&dmcfreq->wait_dcf_queue);
-
-	/* Clear the DCF interrupt */
-	arm_smccc_smc(ROCKCHIP_SIP_DRAM_FREQ, 0, 0,
-		      ROCKCHIP_SIP_CONFIG_DRAM_CLR_IRQ,
-		      0, 0, 0, 0, &res);
-
-	return IRQ_HANDLED;
-}
-
 static int of_get_ddr_timings(struct dram_timing *timing,
 			      struct device_node *np)
 {
@@ -330,16 +296,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct device_node *np = pdev->dev.of_node;
 	struct rk3399_dmcfreq *data;
-	int ret, irq, index, size;
+	int ret, index, size;
 	uint32_t *timing;
 	struct dev_pm_opp *opp;
 
-	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(&pdev->dev,
-			"Cannot get the dmc interrupt resource: %d\n", irq);
-		return irq;
-	}
 	data = devm_kzalloc(dev, sizeof(struct rk3399_dmcfreq), GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
@@ -358,17 +318,6 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 		return PTR_ERR(data->dmc_clk);
 	};
 
-	data->irq = irq;
-	ret = devm_request_irq(dev, irq, rk3399_dmc_irq, 0,
-			       dev_name(dev), data);
-	if (ret) {
-		dev_err(dev, "Failed to request dmc irq: %d\n", ret);
-		return ret;
-	}
-
-	init_waitqueue_head(&data->wait_dcf_queue);
-	data->wait_dcf_flag = 0;
-
 	data->edev = devfreq_event_get_edev_by_phandle(dev, 0);
 	if (IS_ERR(data->edev))
 		return -EPROBE_DEFER;
-- 
cgit v1.2.3


From 77f2c2305decda26885f8b2307577267b78c468f Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Wed, 9 May 2018 14:57:46 +0200
Subject: dt-bindings: devfreq: rk3399_dmc: move interrupts to be optional.

In ATF we already wait for DDR DVFS finish, so move the interrupts properties
to be optional.

Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
index e0030a139383..0ec68141f85a 100644
--- a/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
+++ b/Documentation/devicetree/bindings/devfreq/rk3399_dmc.txt
@@ -5,10 +5,6 @@ Required properties:
 - devfreq-events:	 Node to get DDR loading, Refer to
 			 Documentation/devicetree/bindings/devfreq/event/
 			 rockchip-dfi.txt
-- interrupts:		 The CPU interrupt number. The interrupt specifier
-			 format depends on the interrupt controller.
-			 It should be a DCF interrupt. When DDR DVFS finishes
-			 a DCF interrupt is triggered.
 - clocks:		 Phandles for clock specified in "clock-names" property
 - clock-names :		 The name of clock used by the DFI, must be
 			 "pclk_ddr_mon";
@@ -17,6 +13,12 @@ Required properties:
 - center-supply:	 DMC supply node.
 - status:		 Marks the node enabled/disabled.
 
+Optional properties:
+- interrupts:		 The CPU interrupt number. The interrupt specifier
+			 format depends on the interrupt controller.
+			 It should be a DCF interrupt. When DDR DVFS finishes
+			 a DCF interrupt is triggered.
+
 Following properties relate to DDR timing:
 
 - rockchip,dram_speed_bin :	  Value reference include/dt-bindings/clock/rk3399-ddr.h,
-- 
cgit v1.2.3


From 49edc52312c34c981722833b0d9344c2aa83892d Mon Sep 17 00:00:00 2001
From: Lin Huang <hl@rock-chips.com>
Date: Wed, 9 May 2018 14:57:47 +0200
Subject: PM / devfreq: rk3399_dmc: do not print error when get supply and clk
 defer.

We just return -EPROBE_DEFER error code to caller and do not
print error message when try to get center logic regulator
and DMC clock defer.

Signed-off-by: Lin Huang <hl@rock-chips.com>
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/rk3399_dmc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 44a379657cd5..5bfca028eaaf 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -308,12 +308,18 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 
 	data->vdd_center = devm_regulator_get(dev, "center");
 	if (IS_ERR(data->vdd_center)) {
+		if (PTR_ERR(data->vdd_center) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the regulator \"center\"\n");
 		return PTR_ERR(data->vdd_center);
 	}
 
 	data->dmc_clk = devm_clk_get(dev, "dmc_clk");
 	if (IS_ERR(data->dmc_clk)) {
+		if (PTR_ERR(data->dmc_clk) == -EPROBE_DEFER)
+			return -EPROBE_DEFER;
+
 		dev_err(dev, "Cannot get the clk dmc_clk\n");
 		return PTR_ERR(data->dmc_clk);
 	};
-- 
cgit v1.2.3


From dfa7d764caf00b12da276ea473d7f1fd7fd40200 Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Wed, 9 May 2018 14:57:48 +0200
Subject: PM / devfreq: rk3399_dmc: fix spelling mistakes.

Fix some spelling mistakes in error and debug messages.

Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/rk3399_dmc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index 5bfca028eaaf..d5c03e5abe13 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -103,7 +103,7 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 		if (err) {
-			dev_err(dev, "Cannot to set voltage %lu uV\n",
+			dev_err(dev, "Cannot set voltage %lu uV\n",
 				target_volt);
 			goto out;
 		}
@@ -111,8 +111,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 
 	err = clk_set_rate(dmcfreq->dmc_clk, target_rate);
 	if (err) {
-		dev_err(dev, "Cannot to set frequency %lu (%d)\n",
-			target_rate, err);
+		dev_err(dev, "Cannot set frequency %lu (%d)\n", target_rate,
+			err);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
@@ -128,8 +128,8 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 
 	/* If get the incorrect rate, set voltage to old value. */
 	if (dmcfreq->rate != target_rate) {
-		dev_err(dev, "Get wrong ddr frequency, Request frequency %lu,\
-			Current frequency %lu\n", target_rate, dmcfreq->rate);
+		dev_err(dev, "Got wrong frequency, Request %lu, Current %lu\n",
+			target_rate, dmcfreq->rate);
 		regulator_set_voltage(dmcfreq->vdd_center, dmcfreq->volt,
 				      dmcfreq->volt);
 		goto out;
@@ -137,7 +137,7 @@ static int rk3399_dmcfreq_target(struct device *dev, unsigned long *freq,
 		err = regulator_set_voltage(dmcfreq->vdd_center, target_volt,
 					    target_volt);
 	if (err)
-		dev_err(dev, "Cannot to set vol %lu uV\n", target_volt);
+		dev_err(dev, "Cannot set voltage %lu uV\n", target_volt);
 
 	dmcfreq->rate = target_rate;
 	dmcfreq->volt = target_volt;
-- 
cgit v1.2.3


From 2c2cb1e6b05b90d55b4b943646faa3cfbdf78f6e Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Fri, 25 May 2018 13:30:33 -0700
Subject: PM / devfreq: Init user limits from OPP limits, not viceversa

Commit ab8f58ad72c4 ("PM / devfreq: Set min/max_freq when adding
the devfreq device") introduced the initialization of the user
limits min/max_freq from the lowest/highest available OPPs. Later
commit f1d981eaecf8 ("PM / devfreq: Use the available min/max
frequency") added scaling_min/max_freq, which actually represent
the frequencies of the lowest/highest available OPP. scaling_min/
max_freq are initialized with the values from min/max_freq, which
is totally correct in the context, but a bit awkward to read.

Swap the initialization and assign scaling_min/max_freq with the
OPP freqs and then the user limts min/max_freq with scaling_min/
max_freq.

Needless to say that this change is a NOP, intended to improve
readability.

Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Reviewed-by: Brian Norris <briannorris@chromium.org>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/devfreq.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index e26adf67e218..4c49bb1330b5 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -604,21 +604,21 @@ struct devfreq *devfreq_add_device(struct device *dev,
 		mutex_lock(&devfreq->lock);
 	}
 
-	devfreq->min_freq = find_available_min_freq(devfreq);
-	if (!devfreq->min_freq) {
+	devfreq->scaling_min_freq = find_available_min_freq(devfreq);
+	if (!devfreq->scaling_min_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_min_freq = devfreq->min_freq;
+	devfreq->min_freq = devfreq->scaling_min_freq;
 
-	devfreq->max_freq = find_available_max_freq(devfreq);
-	if (!devfreq->max_freq) {
+	devfreq->scaling_max_freq = find_available_max_freq(devfreq);
+	if (!devfreq->scaling_max_freq) {
 		mutex_unlock(&devfreq->lock);
 		err = -EINVAL;
 		goto err_dev;
 	}
-	devfreq->scaling_max_freq = devfreq->max_freq;
+	devfreq->max_freq = devfreq->scaling_max_freq;
 
 	dev_set_name(&devfreq->dev, "devfreq%d",
 				atomic_inc_return(&devfreq_no));
-- 
cgit v1.2.3


From d6e98f3e6d825380b566dc59359917a116090154 Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Fri, 15 Jun 2018 17:12:17 +0200
Subject: PM / devfreq: rk3399_dmc: Fix duplicated opp table on reload.

The opp table is not removed when the driver is unloaded neither when
there is an error within probe, so if the driver is reloaded the opp
core shows the following warning:

  rk3399-dmc-freq dmc: _opp_add: duplicate OPPs detected. Existing: freq:
               200000000, volt: 900000, enabled: 1. New: freq: 200000000,
               volt: 900000, enabled: 1
  rk3399-dmc-freq dmc: _opp_add: duplicate OPPs detected. Existing: freq:
               400000000, volt: 900000, enabled: 1. New: freq: 400000000,
               volt: 900000, enabled: 1
  rk3399-dmc-freq dmc: _opp_add: duplicate OPPs detected. Existing: freq:
               666000000, volt: 900000, enabled: 1. New: freq: 666000000,
               volt: 900000, enabled: 1
  rk3399-dmc-freq dmc: _opp_add: duplicate OPPs detected. Existing: freq:
               800000000, volt: 900000, enabled: 1. New: freq: 800000000,
               volt: 900000, enabled: 1
  rk3399-dmc-freq dmc: _opp_add: duplicate OPPs detected. Existing: freq:
               928000000, volt: 900000, enabled: 1. New: freq: 928000000,
               volt: 900000, enabled: 1

This patch fixes the error path in the probe function and adds a .remove
function to properly cleanup the opp table on unloading.

Fixes: 5a893e31a636c (PM / devfreq: rockchip: add devfreq driver for rk3399 dmc)
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Chanwoo Choi <cw00.choi@samsung.com>
Signed-off-by: MyungJoo Ham <myungjoo.ham@samsung.com>
---
 drivers/devfreq/rk3399_dmc.c | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/drivers/devfreq/rk3399_dmc.c b/drivers/devfreq/rk3399_dmc.c
index d5c03e5abe13..e795ad2b3f6b 100644
--- a/drivers/devfreq/rk3399_dmc.c
+++ b/drivers/devfreq/rk3399_dmc.c
@@ -375,8 +375,10 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 	data->rate = clk_get_rate(data->dmc_clk);
 
 	opp = devfreq_recommended_opp(dev, &data->rate, 0);
-	if (IS_ERR(opp))
-		return PTR_ERR(opp);
+	if (IS_ERR(opp)) {
+		ret = PTR_ERR(opp);
+		goto err_free_opp;
+	}
 
 	data->rate = dev_pm_opp_get_freq(opp);
 	data->volt = dev_pm_opp_get_voltage(opp);
@@ -388,13 +390,33 @@ static int rk3399_dmcfreq_probe(struct platform_device *pdev)
 					   &rk3399_devfreq_dmc_profile,
 					   DEVFREQ_GOV_SIMPLE_ONDEMAND,
 					   &data->ondemand_data);
-	if (IS_ERR(data->devfreq))
-		return PTR_ERR(data->devfreq);
+	if (IS_ERR(data->devfreq)) {
+		ret = PTR_ERR(data->devfreq);
+		goto err_free_opp;
+	}
+
 	devm_devfreq_register_opp_notifier(dev, data->devfreq);
 
 	data->dev = dev;
 	platform_set_drvdata(pdev, data);
 
+	return 0;
+
+err_free_opp:
+	dev_pm_opp_of_remove_table(&pdev->dev);
+	return ret;
+}
+
+static int rk3399_dmcfreq_remove(struct platform_device *pdev)
+{
+	struct rk3399_dmcfreq *dmcfreq = dev_get_drvdata(&pdev->dev);
+
+	/*
+	 * Before remove the opp table we need to unregister the opp notifier.
+	 */
+	devm_devfreq_unregister_opp_notifier(dmcfreq->dev, dmcfreq->devfreq);
+	dev_pm_opp_of_remove_table(dmcfreq->dev);
+
 	return 0;
 }
 
@@ -406,6 +428,7 @@ MODULE_DEVICE_TABLE(of, rk3399dmc_devfreq_of_match);
 
 static struct platform_driver rk3399_dmcfreq_driver = {
 	.probe	= rk3399_dmcfreq_probe,
+	.remove = rk3399_dmcfreq_remove,
 	.driver = {
 		.name	= "rk3399-dmc-freq",
 		.pm	= &rk3399_dmcfreq_pm,
-- 
cgit v1.2.3


From c94f2fc4fc19a0ab29456b652975e08e0362c94a Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Mon, 16 Jul 2018 14:19:25 +0200
Subject: ravb: fix shadowing of symbol 'stats' in ravb_get_ethtool_stats()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Inside a loop in ravb_get_ethtool_stats() a variable 'stats' is declared
resulting in the argument also named 'stats' to be shadowed. Fix this
warning by renaming the unused argument 'stats' to 'estats'.

This fixes the sparse warning:

ravb_main.c:1225:36: originally declared here
ravb_main.c:1233:41: warning: symbol 'stats' shadows an earlier one

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 4a7f54c8e7aa..e5784f0eac3d 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1226,7 +1226,7 @@ static int ravb_get_sset_count(struct net_device *netdev, int sset)
 }
 
 static void ravb_get_ethtool_stats(struct net_device *ndev,
-				   struct ethtool_stats *stats, u64 *data)
+				   struct ethtool_stats *estats, u64 *data)
 {
 	struct ravb_private *priv = netdev_priv(ndev);
 	int i = 0;
-- 
cgit v1.2.3


From 49f3303a6eaa86c64597c33323d03ab0cbdccbe5 Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Mon, 16 Jul 2018 14:19:26 +0200
Subject: ravb: fix warning about memcpy length
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes sparse warning:

ravb_main.c:1257 ravb_get_strings() error: memcpy() '*ravb_gstrings_stats' too small (32 vs 960)

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index e5784f0eac3d..a100bccb3234 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1258,7 +1258,7 @@ static void ravb_get_strings(struct net_device *ndev, u32 stringset, u8 *data)
 {
 	switch (stringset) {
 	case ETH_SS_STATS:
-		memcpy(data, *ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
+		memcpy(data, ravb_gstrings_stats, sizeof(ravb_gstrings_stats));
 		break;
 	}
 }
-- 
cgit v1.2.3


From e49b42faae0eec619ad96d877d5e463efd3ca12f Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Mon, 16 Jul 2018 14:19:27 +0200
Subject: ravb: fix byte order for TX descriptor tag field lower bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The wrong helper is used to swap the bytes when adding the lower bits of
the TX descriptors tag field in the shared ds_tagl variable. The
variable contains the DS[11:0] field and then the TAG[3:0] bits.

The mistake was highlighted by the sparse warning:

ravb_main.c:1622:31:    left side has type restricted __le16
ravb_main.c:1622:31:    right side has type unsigned short
ravb_main.c:1622:31: warning: invalid assignment: |=
ravb_main.c:1622:34: warning: cast to restricted __le16

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/ravb_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index a100bccb3234..f7e649c831ad 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -1623,7 +1623,7 @@ static netdev_tx_t ravb_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		/* TAG and timestamp required flag */
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		desc->tagh_tsr = (ts_skb->tag >> 4) | TX_TSR;
-		desc->ds_tagl |= le16_to_cpu(ts_skb->tag << 12);
+		desc->ds_tagl |= cpu_to_le16(ts_skb->tag << 12);
 	}
 
 	skb_tx_timestamp(skb);
-- 
cgit v1.2.3


From db53770a3eaf37ae732888ba999c223ebb721348 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Wed, 18 Jul 2018 14:42:18 +0900
Subject: dsa: rtl8366: Remove unused variable.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drivers/net/dsa/rtl8366.c: In function ‘rtl8366_reset_vlan’:
drivers/net/dsa/rtl8366.c:234:25: warning: unused variable ‘vlan4k’ [-Wunused-variable]

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/dsa/rtl8366.c b/drivers/net/dsa/rtl8366.c
index 58d8534f7ecb..6dedd43442cc 100644
--- a/drivers/net/dsa/rtl8366.c
+++ b/drivers/net/dsa/rtl8366.c
@@ -231,7 +231,6 @@ EXPORT_SYMBOL_GPL(rtl8366_enable_vlan);
 int rtl8366_reset_vlan(struct realtek_smi *smi)
 {
 	struct rtl8366_vlan_mc vlanmc;
-	struct rtl8366_vlan_4k vlan4k;
 	int ret;
 	int i;
 
-- 
cgit v1.2.3


From bfd4271169176766343026bf324337e529d81fa4 Mon Sep 17 00:00:00 2001
From: Håkon Bugge <Haakon.Bugge@oracle.com>
Date: Mon, 16 Jul 2018 15:00:09 +0200
Subject: net/rds: void function cannot return -1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit b6fb0df12db6 ("RDS/IB: Make ib_recv_refill return void") did
not change the comment accordingly.

Fixes: b6fb0df12db6 ("RDS/IB: Make ib_recv_refill return void")
Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.ccom>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_recv.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index b4e421aa9727..e5ce93419263 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -376,8 +376,6 @@ static void release_refill(struct rds_connection *conn)
  * This tries to allocate and post unused work requests after making sure that
  * they have all the allocations they need to queue received fragments into
  * sockets.
- *
- * -1 is returned if posting fails due to temporary resource exhaustion.
  */
 void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp)
 {
-- 
cgit v1.2.3


From fa52531eb4409a1fc0cc11ac37e249088d3561c7 Mon Sep 17 00:00:00 2001
From: Håkon Bugge <Haakon.Bugge@oracle.com>
Date: Mon, 16 Jul 2018 15:06:39 +0200
Subject: net/rds: Remove unnecessary variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Håkon Bugge <haakon.bugge@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_recv.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index e5ce93419263..1eaf2550a9f8 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -1023,7 +1023,6 @@ int rds_ib_recv_path(struct rds_conn_path *cp)
 {
 	struct rds_connection *conn = cp->cp_conn;
 	struct rds_ib_connection *ic = conn->c_transport_data;
-	int ret = 0;
 
 	rdsdebug("conn %p\n", conn);
 	if (rds_conn_up(conn)) {
@@ -1032,7 +1031,7 @@ int rds_ib_recv_path(struct rds_conn_path *cp)
 		rds_ib_stats_inc(s_ib_rx_refill_from_thread);
 	}
 
-	return ret;
+	return 0;
 }
 
 int rds_ib_recv_init(void)
-- 
cgit v1.2.3


From ef4db239cda2d74f53120e223643b0f5bbf947c1 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 17 Jul 2018 23:12:33 +0200
Subject: ALSA: rawmidi: Use kvmalloc() for buffers

The size of in-kernel rawmidi buffers may be big up to 1MB, and it can
be specified freely by user-space; which implies that user-space may
trigger kmalloc() errors frequently.

This patch replaces the buffer allocation via kvmalloc() for dealing
with bigger buffers gracefully.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/rawmidi.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/sound/core/rawmidi.c b/sound/core/rawmidi.c
index cc944a3637a2..69517e18ef07 100644
--- a/sound/core/rawmidi.c
+++ b/sound/core/rawmidi.c
@@ -29,6 +29,7 @@
 #include <linux/mutex.h>
 #include <linux/module.h>
 #include <linux/delay.h>
+#include <linux/mm.h>
 #include <sound/rawmidi.h>
 #include <sound/info.h>
 #include <sound/control.h>
@@ -128,7 +129,7 @@ static int snd_rawmidi_runtime_create(struct snd_rawmidi_substream *substream)
 		runtime->avail = 0;
 	else
 		runtime->avail = runtime->buffer_size;
-	runtime->buffer = kmalloc(runtime->buffer_size, GFP_KERNEL);
+	runtime->buffer = kvmalloc(runtime->buffer_size, GFP_KERNEL);
 	if (!runtime->buffer) {
 		kfree(runtime);
 		return -ENOMEM;
@@ -142,7 +143,7 @@ static int snd_rawmidi_runtime_free(struct snd_rawmidi_substream *substream)
 {
 	struct snd_rawmidi_runtime *runtime = substream->runtime;
 
-	kfree(runtime->buffer);
+	kvfree(runtime->buffer);
 	kfree(runtime);
 	substream->runtime = NULL;
 	return 0;
@@ -654,7 +655,7 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime,
 	if (params->avail_min < 1 || params->avail_min > params->buffer_size)
 		return -EINVAL;
 	if (params->buffer_size != runtime->buffer_size) {
-		newbuf = kmalloc(params->buffer_size, GFP_KERNEL);
+		newbuf = kvmalloc(params->buffer_size, GFP_KERNEL);
 		if (!newbuf)
 			return -ENOMEM;
 		spin_lock_irq(&runtime->lock);
@@ -663,7 +664,7 @@ static int resize_runtime_buffer(struct snd_rawmidi_runtime *runtime,
 		runtime->buffer_size = params->buffer_size;
 		__reset_runtime_ptrs(runtime, is_input);
 		spin_unlock_irq(&runtime->lock);
-		kfree(oldbuf);
+		kvfree(oldbuf);
 	}
 	runtime->avail_min = params->avail_min;
 	return 0;
-- 
cgit v1.2.3


From fa84cf094ef9667e2b91c104b0a788fd1896f482 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 18 Jul 2018 07:40:53 +0200
Subject: ALSA: pcm: Nuke snd_pcm_lib_mmap_vmalloc()

snd_pcm_lib_mmap_vmalloc() was supposed to be implemented with
somewhat special for vmalloc handling, but in the end, this turned to
just the default handler, i.e. NULL.  As the situation has never
changed over decades, let's rip it off.

Reviewed-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 drivers/staging/most/sound/sound.c       | 1 -
 include/sound/pcm.h                      | 2 --
 sound/drivers/aloop.c                    | 1 -
 sound/drivers/vx/vx_pcm.c                | 2 --
 sound/firewire/bebob/bebob_pcm.c         | 1 -
 sound/firewire/dice/dice-pcm.c           | 2 --
 sound/firewire/digi00x/digi00x-pcm.c     | 1 -
 sound/firewire/fireface/ff-pcm.c         | 1 -
 sound/firewire/fireworks/fireworks_pcm.c | 1 -
 sound/firewire/isight.c                  | 1 -
 sound/firewire/motu/motu-pcm.c           | 2 --
 sound/firewire/oxfw/oxfw-pcm.c           | 2 --
 sound/firewire/tascam/tascam-pcm.c       | 1 -
 sound/mips/sgio2audio.c                  | 3 ---
 sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c   | 1 -
 sound/soc/codecs/rt5514-spi.c            | 1 -
 sound/usb/6fire/pcm.c                    | 1 -
 sound/usb/caiaq/audio.c                  | 1 -
 sound/usb/hiface/pcm.c                   | 1 -
 sound/usb/misc/ua101.c                   | 2 --
 sound/usb/pcm.c                          | 2 --
 21 files changed, 30 deletions(-)

diff --git a/drivers/staging/most/sound/sound.c b/drivers/staging/most/sound/sound.c
index 04c18323c2ea..89b02fc305b8 100644
--- a/drivers/staging/most/sound/sound.c
+++ b/drivers/staging/most/sound/sound.c
@@ -457,7 +457,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.trigger    = pcm_trigger,
 	.pointer    = pcm_pointer,
 	.page       = snd_pcm_lib_get_vmalloc_page,
-	.mmap       = snd_pcm_lib_mmap_vmalloc,
 };
 
 static int split_arg_list(char *buf, char **card_name, u16 *ch_num,
diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index fcdf358a25f0..1206045ccf03 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -1342,8 +1342,6 @@ int snd_pcm_lib_mmap_iomem(struct snd_pcm_substream *substream, struct vm_area_s
 #define snd_pcm_lib_mmap_iomem	NULL
 #endif
 
-#define snd_pcm_lib_mmap_vmalloc NULL
-
 /**
  * snd_pcm_limit_isa_dma_size - Get the max size fitting with ISA DMA transfer
  * @dma: DMA number
diff --git a/sound/drivers/aloop.c b/sound/drivers/aloop.c
index 78a2fdc38531..1e34e6381baa 100644
--- a/sound/drivers/aloop.c
+++ b/sound/drivers/aloop.c
@@ -778,7 +778,6 @@ static const struct snd_pcm_ops loopback_pcm_ops = {
 	.trigger =	loopback_trigger,
 	.pointer =	loopback_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static int loopback_pcm_new(struct loopback *loopback,
diff --git a/sound/drivers/vx/vx_pcm.c b/sound/drivers/vx/vx_pcm.c
index 380a028469c4..ba80f459bdc5 100644
--- a/sound/drivers/vx/vx_pcm.c
+++ b/sound/drivers/vx/vx_pcm.c
@@ -883,7 +883,6 @@ static const struct snd_pcm_ops vx_pcm_playback_ops = {
 	.trigger =	vx_pcm_trigger,
 	.pointer =	vx_pcm_playback_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 
@@ -1105,7 +1104,6 @@ static const struct snd_pcm_ops vx_pcm_capture_ops = {
 	.trigger =	vx_pcm_trigger,
 	.pointer =	vx_pcm_capture_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 
diff --git a/sound/firewire/bebob/bebob_pcm.c b/sound/firewire/bebob/bebob_pcm.c
index e6adab3ef42e..ea9b86450580 100644
--- a/sound/firewire/bebob/bebob_pcm.c
+++ b/sound/firewire/bebob/bebob_pcm.c
@@ -373,7 +373,6 @@ int snd_bebob_create_pcm_devices(struct snd_bebob *bebob)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/dice/dice-pcm.c b/sound/firewire/dice/dice-pcm.c
index 80351b29fe0d..bb3ef5ff3488 100644
--- a/sound/firewire/dice/dice-pcm.c
+++ b/sound/firewire/dice/dice-pcm.c
@@ -412,7 +412,6 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		.pointer   = capture_pointer,
 		.ack       = capture_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -425,7 +424,6 @@ int snd_dice_create_pcm(struct snd_dice *dice)
 		.pointer   = playback_pointer,
 		.ack       = playback_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	unsigned int capture, playback;
diff --git a/sound/firewire/digi00x/digi00x-pcm.c b/sound/firewire/digi00x/digi00x-pcm.c
index 796f4b4645f5..fdcff0460c53 100644
--- a/sound/firewire/digi00x/digi00x-pcm.c
+++ b/sound/firewire/digi00x/digi00x-pcm.c
@@ -352,7 +352,6 @@ int snd_dg00x_create_pcm_devices(struct snd_dg00x *dg00x)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/fireface/ff-pcm.c b/sound/firewire/fireface/ff-pcm.c
index e3c16308363d..bf47f9ec8703 100644
--- a/sound/firewire/fireface/ff-pcm.c
+++ b/sound/firewire/fireface/ff-pcm.c
@@ -383,7 +383,6 @@ int snd_ff_create_pcm_devices(struct snd_ff *ff)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/fireworks/fireworks_pcm.c b/sound/firewire/fireworks/fireworks_pcm.c
index 40faed5e6968..aed566d82726 100644
--- a/sound/firewire/fireworks/fireworks_pcm.c
+++ b/sound/firewire/fireworks/fireworks_pcm.c
@@ -397,7 +397,6 @@ int snd_efw_create_pcm_devices(struct snd_efw *efw)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/isight.c b/sound/firewire/isight.c
index 3919e186a30b..30957477e005 100644
--- a/sound/firewire/isight.c
+++ b/sound/firewire/isight.c
@@ -454,7 +454,6 @@ static int isight_create_pcm(struct isight *isight)
 		.trigger   = isight_trigger,
 		.pointer   = isight_pointer,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/motu/motu-pcm.c b/sound/firewire/motu/motu-pcm.c
index 4330220890e8..ab69d7e6ac05 100644
--- a/sound/firewire/motu/motu-pcm.c
+++ b/sound/firewire/motu/motu-pcm.c
@@ -363,7 +363,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu)
 		.pointer   = capture_pointer,
 		.ack       = capture_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -376,7 +375,6 @@ int snd_motu_create_pcm_devices(struct snd_motu *motu)
 		.pointer   = playback_pointer,
 		.ack       = playback_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/firewire/oxfw/oxfw-pcm.c b/sound/firewire/oxfw/oxfw-pcm.c
index 3dd46285c0e2..b3f6503dd34d 100644
--- a/sound/firewire/oxfw/oxfw-pcm.c
+++ b/sound/firewire/oxfw/oxfw-pcm.c
@@ -389,7 +389,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
 		.pointer   = pcm_capture_pointer,
 		.ack       = pcm_capture_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	static const struct snd_pcm_ops playback_ops = {
 		.open      = pcm_open,
@@ -402,7 +401,6 @@ int snd_oxfw_create_pcm(struct snd_oxfw *oxfw)
 		.pointer   = pcm_playback_pointer,
 		.ack       = pcm_playback_ack,
 		.page      = snd_pcm_lib_get_vmalloc_page,
-		.mmap      = snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	unsigned int cap = 0;
diff --git a/sound/firewire/tascam/tascam-pcm.c b/sound/firewire/tascam/tascam-pcm.c
index 6ec8ec634d4d..e4cc8990e195 100644
--- a/sound/firewire/tascam/tascam-pcm.c
+++ b/sound/firewire/tascam/tascam-pcm.c
@@ -279,7 +279,6 @@ int snd_tscm_create_pcm_devices(struct snd_tscm *tscm)
 		.pointer	= pcm_playback_pointer,
 		.ack		= pcm_playback_ack,
 		.page		= snd_pcm_lib_get_vmalloc_page,
-		.mmap		= snd_pcm_lib_mmap_vmalloc,
 	};
 	struct snd_pcm *pcm;
 	int err;
diff --git a/sound/mips/sgio2audio.c b/sound/mips/sgio2audio.c
index 9fb68b35de5a..3ec9391a4736 100644
--- a/sound/mips/sgio2audio.c
+++ b/sound/mips/sgio2audio.c
@@ -685,7 +685,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback1_ops = {
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
 	.page =        snd_pcm_lib_get_vmalloc_page,
-	.mmap =        snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = {
@@ -698,7 +697,6 @@ static const struct snd_pcm_ops snd_sgio2audio_playback2_ops = {
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
 	.page =        snd_pcm_lib_get_vmalloc_page,
-	.mmap =        snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_sgio2audio_capture_ops = {
@@ -711,7 +709,6 @@ static const struct snd_pcm_ops snd_sgio2audio_capture_ops = {
 	.trigger =     snd_sgio2audio_pcm_trigger,
 	.pointer =     snd_sgio2audio_pcm_pointer,
 	.page =        snd_pcm_lib_get_vmalloc_page,
-	.mmap =        snd_pcm_lib_mmap_vmalloc,
 };
 
 /*
diff --git a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
index 4a2354b5ae00..98a6863e933c 100644
--- a/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
+++ b/sound/pcmcia/pdaudiocf/pdaudiocf_pcm.c
@@ -276,7 +276,6 @@ static const struct snd_pcm_ops pdacf_pcm_capture_ops = {
 	.trigger =	pdacf_pcm_trigger,
 	.pointer =	pdacf_pcm_capture_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 
diff --git a/sound/soc/codecs/rt5514-spi.c b/sound/soc/codecs/rt5514-spi.c
index 18686ffb0cd5..6478d10c4f4a 100644
--- a/sound/soc/codecs/rt5514-spi.c
+++ b/sound/soc/codecs/rt5514-spi.c
@@ -268,7 +268,6 @@ static const struct snd_pcm_ops rt5514_spi_pcm_ops = {
 	.hw_params	= rt5514_spi_hw_params,
 	.hw_free	= rt5514_spi_hw_free,
 	.pointer	= rt5514_spi_pcm_pointer,
-	.mmap		= snd_pcm_lib_mmap_vmalloc,
 	.page		= snd_pcm_lib_get_vmalloc_page,
 };
 
diff --git a/sound/usb/6fire/pcm.c b/sound/usb/6fire/pcm.c
index 2dd2518a71d3..f8ef3e2a8ca0 100644
--- a/sound/usb/6fire/pcm.c
+++ b/sound/usb/6fire/pcm.c
@@ -565,7 +565,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.trigger = usb6fire_pcm_trigger,
 	.pointer = usb6fire_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static void usb6fire_pcm_init_urb(struct pcm_urb *urb,
diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c
index 15344d39a6cd..c6108a3d7f8f 100644
--- a/sound/usb/caiaq/audio.c
+++ b/sound/usb/caiaq/audio.c
@@ -348,7 +348,6 @@ static const struct snd_pcm_ops snd_usb_caiaq_ops = {
 	.trigger =	snd_usb_caiaq_pcm_trigger,
 	.pointer =	snd_usb_caiaq_pcm_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static void check_for_elapsed_periods(struct snd_usb_caiaqdev *cdev,
diff --git a/sound/usb/hiface/pcm.c b/sound/usb/hiface/pcm.c
index 396c317115b1..e1fbb9cc9ea7 100644
--- a/sound/usb/hiface/pcm.c
+++ b/sound/usb/hiface/pcm.c
@@ -523,7 +523,6 @@ static const struct snd_pcm_ops pcm_ops = {
 	.trigger = hiface_pcm_trigger,
 	.pointer = hiface_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static int hiface_pcm_init_urb(struct pcm_urb *urb,
diff --git a/sound/usb/misc/ua101.c b/sound/usb/misc/ua101.c
index 386fbfd5c617..a0b6d039017f 100644
--- a/sound/usb/misc/ua101.c
+++ b/sound/usb/misc/ua101.c
@@ -900,7 +900,6 @@ static const struct snd_pcm_ops capture_pcm_ops = {
 	.trigger = capture_pcm_trigger,
 	.pointer = capture_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops playback_pcm_ops = {
@@ -913,7 +912,6 @@ static const struct snd_pcm_ops playback_pcm_ops = {
 	.trigger = playback_pcm_trigger,
 	.pointer = playback_pcm_pointer,
 	.page = snd_pcm_lib_get_vmalloc_page,
-	.mmap = snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct uac_format_type_i_discrete_descriptor *
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 160f52c4871b..4b930fa47277 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1694,7 +1694,6 @@ static const struct snd_pcm_ops snd_usb_playback_ops = {
 	.trigger =	snd_usb_substream_playback_trigger,
 	.pointer =	snd_usb_pcm_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_usb_capture_ops = {
@@ -1707,7 +1706,6 @@ static const struct snd_pcm_ops snd_usb_capture_ops = {
 	.trigger =	snd_usb_substream_capture_trigger,
 	.pointer =	snd_usb_pcm_pointer,
 	.page =		snd_pcm_lib_get_vmalloc_page,
-	.mmap =		snd_pcm_lib_mmap_vmalloc,
 };
 
 static const struct snd_pcm_ops snd_usb_playback_dev_ops = {
-- 
cgit v1.2.3


From aeaf7002a76c8da60c0f503badcbddc07650678c Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 8 May 2018 15:14:48 +0200
Subject: s390: detect etoken facility

Detect and report the etoken facility. With spectre_v2=auto or
CONFIG_EXPOLINE_AUTO=y automatically disable expolines and use
the full branch prediction mode for the kernel.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/nospec-branch.c | 12 +++++++++++-
 arch/s390/kernel/nospec-sysfs.c  |  2 ++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/nospec-branch.c b/arch/s390/kernel/nospec-branch.c
index 18ae7b9c71d6..bdddaae96559 100644
--- a/arch/s390/kernel/nospec-branch.c
+++ b/arch/s390/kernel/nospec-branch.c
@@ -35,6 +35,8 @@ early_param("nospec", nospec_setup_early);
 
 static int __init nospec_report(void)
 {
+	if (test_facility(156))
+		pr_info("Spectre V2 mitigation: etokens\n");
 	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
 		pr_info("Spectre V2 mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
@@ -56,7 +58,15 @@ early_param("nospectre_v2", nospectre_v2_setup_early);
 
 void __init nospec_auto_detect(void)
 {
-	if (IS_ENABLED(CC_USING_EXPOLINE)) {
+	if (test_facility(156)) {
+		/*
+		 * The machine supports etokens.
+		 * Disable expolines and disable nobp.
+		 */
+		if (IS_ENABLED(CC_USING_EXPOLINE))
+			nospec_disable = 1;
+		__clear_facility(82, S390_lowcore.alt_stfle_fac_list);
+	} else if (IS_ENABLED(CC_USING_EXPOLINE)) {
 		/*
 		 * The kernel has been compiled with expolines.
 		 * Keep expolines enabled and disable nobp.
diff --git a/arch/s390/kernel/nospec-sysfs.c b/arch/s390/kernel/nospec-sysfs.c
index 8affad5f18cb..e30e580ae362 100644
--- a/arch/s390/kernel/nospec-sysfs.c
+++ b/arch/s390/kernel/nospec-sysfs.c
@@ -13,6 +13,8 @@ ssize_t cpu_show_spectre_v1(struct device *dev,
 ssize_t cpu_show_spectre_v2(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
+	if (test_facility(156))
+		return sprintf(buf, "Mitigation: etokens\n");
 	if (IS_ENABLED(CC_USING_EXPOLINE) && !nospec_disable)
 		return sprintf(buf, "Mitigation: execute trampolines\n");
 	if (__test_facility(82, S390_lowcore.alt_stfle_fac_list))
-- 
cgit v1.2.3


From 181ace9e1b2e1c5c2be590bc9603baa65f3a16d8 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:28 +0530
Subject: mtd: rawnand: helper function for setting up ECC configuration

commit 2c8f8afa7f92 ("mtd: nand: add generic helpers to check,
match, maximize ECC settings") provides generic helpers which
drivers can use for setting up ECC parameters.

Since same board can have different ECC strength nand chips so
following is the logic for setting up ECC strength and ECC step
size, which can be used by most of the drivers.

1. If both ECC step size and ECC strength are already set
   (usually by DT) then just check whether this setting
   is supported by NAND controller.
2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength
   supported by NAND controller.
3. Otherwise, try to match the ECC step size and ECC strength closest
   to the chip's requirement. If available OOB size can't fit the chip
   requirement then select maximum ECC strength which can be fit with
   available OOB size.

This patch introduces nand_ecc_choose_conf function which calls the
required helper functions for the above logic. The drivers can use
this single function instead of calling the 3 helper functions
individually.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Reviewed-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 33 +++++++++++++++++++++++++++++++++
 include/linux/mtd/rawnand.h      |  3 +++
 2 files changed, 36 insertions(+)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index dbf6e80e9ab5..2858d0b09c1d 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -6295,6 +6295,39 @@ int nand_maximize_ecc(struct nand_chip *chip,
 }
 EXPORT_SYMBOL_GPL(nand_maximize_ecc);
 
+/**
+ * nand_ecc_choose_conf - Set the ECC strength and ECC step size
+ * @chip: nand chip info structure
+ * @caps: ECC engine caps info structure
+ * @oobavail: OOB size that the ECC engine can use
+ *
+ * Choose the ECC configuration according to following logic
+ *
+ * 1. If both ECC step size and ECC strength are already set (usually by DT)
+ *    then check if it is supported by this controller.
+ * 2. If NAND_ECC_MAXIMIZE is set, then select maximum ECC strength.
+ * 3. Otherwise, try to match the ECC step size and ECC strength closest
+ *    to the chip's requirement. If available OOB size can't fit the chip
+ *    requirement then fallback to the maximum ECC step size and ECC strength.
+ *
+ * On success, the chosen ECC settings are set.
+ */
+int nand_ecc_choose_conf(struct nand_chip *chip,
+			 const struct nand_ecc_caps *caps, int oobavail)
+{
+	if (chip->ecc.size && chip->ecc.strength)
+		return nand_check_ecc_caps(chip, caps, oobavail);
+
+	if (chip->ecc.options & NAND_ECC_MAXIMIZE)
+		return nand_maximize_ecc(chip, caps, oobavail);
+
+	if (!nand_match_ecc_req(chip, caps, oobavail))
+		return 0;
+
+	return nand_maximize_ecc(chip, caps, oobavail);
+}
+EXPORT_SYMBOL_GPL(nand_ecc_choose_conf);
+
 /*
  * Check if the chip configuration meet the datasheet requirements.
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index fbac4741da52..2ce305388471 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1672,6 +1672,9 @@ int nand_match_ecc_req(struct nand_chip *chip,
 int nand_maximize_ecc(struct nand_chip *chip,
 		      const struct nand_ecc_caps *caps, int oobavail);
 
+int nand_ecc_choose_conf(struct nand_chip *chip,
+			 const struct nand_ecc_caps *caps, int oobavail);
+
 /* Default write_oob implementation */
 int nand_write_oob_std(struct mtd_info *mtd, struct nand_chip *chip, int page);
 
-- 
cgit v1.2.3


From f9801fda963ec9d0f6521695d2b0158249d85c94 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:29 +0530
Subject: mtd: rawnand: denali: use helper function for ecc setup

Use the NAND core helper function nand_ecc_choose_conf to tune
the ECC parameters instead of the function locally defined.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/denali.c | 30 ++----------------------------
 1 file changed, 2 insertions(+), 28 deletions(-)

diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 2a302a1d1430..a586a1d8b997 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -1120,33 +1120,6 @@ int denali_calc_ecc_bytes(int step_size, int strength)
 }
 EXPORT_SYMBOL(denali_calc_ecc_bytes);
 
-static int denali_ecc_setup(struct mtd_info *mtd, struct nand_chip *chip,
-			    struct denali_nand_info *denali)
-{
-	int oobavail = mtd->oobsize - denali->oob_skip_bytes;
-	int ret;
-
-	/*
-	 * If .size and .strength are already set (usually by DT),
-	 * check if they are supported by this controller.
-	 */
-	if (chip->ecc.size && chip->ecc.strength)
-		return nand_check_ecc_caps(chip, denali->ecc_caps, oobavail);
-
-	/*
-	 * We want .size and .strength closest to the chip's requirement
-	 * unless NAND_ECC_MAXIMIZE is requested.
-	 */
-	if (!(chip->ecc.options & NAND_ECC_MAXIMIZE)) {
-		ret = nand_match_ecc_req(chip, denali->ecc_caps, oobavail);
-		if (!ret)
-			return 0;
-	}
-
-	/* Max ECC strength is the last thing we can do */
-	return nand_maximize_ecc(chip, denali->ecc_caps, oobavail);
-}
-
 static int denali_ooblayout_ecc(struct mtd_info *mtd, int section,
 				struct mtd_oob_region *oobregion)
 {
@@ -1317,7 +1290,8 @@ int denali_init(struct denali_nand_info *denali)
 	chip->ecc.mode = NAND_ECC_HW_SYNDROME;
 	chip->options |= NAND_NO_SUBPAGE_WRITE;
 
-	ret = denali_ecc_setup(mtd, chip, denali);
+	ret = nand_ecc_choose_conf(chip, denali->ecc_caps,
+				   mtd->oobsize - denali->oob_skip_bytes);
 	if (ret) {
 		dev_err(denali->dev, "Failed to setup ECC settings.\n");
 		goto disable_irq;
-- 
cgit v1.2.3


From c168ac273ce34b8fb181b230544c4eac80f55b9f Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:30 +0530
Subject: dt-bindings: qcom_nandc: update for ECC strength and step size

1. If nand-ecc-strength specified in DT, then controller will use
   this ECC strength otherwise ECC strength will be calculated
   according to chip requirement and available OOB size.

2. QCOM NAND controller supports only one step size (512 bytes) but
   nand-ecc-step-size is required property in DT. This DT property
   can be removed and ecc step size can be assigned in driver with
   512 bytes value.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/qcom_nandc.txt | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/mtd/qcom_nandc.txt b/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
index 73d336befa08..1123cc6d56ef 100644
--- a/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
+++ b/Documentation/devicetree/bindings/mtd/qcom_nandc.txt
@@ -45,11 +45,12 @@ Required properties:
 			number (e.g., 0, 1, 2, etc.)
 - #address-cells:	see partition.txt
 - #size-cells:		see partition.txt
-- nand-ecc-strength:	see nand.txt
-- nand-ecc-step-size:	must be 512. see nand.txt for more details.
 
 Optional properties:
 - nand-bus-width:	see nand.txt
+- nand-ecc-strength:	see nand.txt. If not specified, then ECC strength will
+			be used according to chip requirement and available
+			OOB size.
 
 Each nandcs device node may optionally contain a 'partitions' sub-node, which
 further contains sub-nodes describing the flash partition mapping. See
@@ -77,7 +78,6 @@ nand-controller@1ac00000 {
 		reg = <0>;
 
 		nand-ecc-strength = <4>;
-		nand-ecc-step-size = <512>;
 		nand-bus-width = <8>;
 
 		partitions {
@@ -117,7 +117,6 @@ nand-controller@79b0000 {
 	nand@0 {
 		reg = <0>;
 		nand-ecc-strength = <4>;
-		nand-ecc-step-size = <512>;
 		nand-bus-width = <8>;
 
 		partitions {
-- 
cgit v1.2.3


From 320bdb5fb9c4a6b67ceadab2d7ed74c21c957561 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:31 +0530
Subject: mtd: rawnand: qcom: remove dt property nand-ecc-step-size

QCOM NAND controller supports only one step size (512) so
nand-ecc-step-size DT property is redundant. This property
can be removed and ecc step size can be assigned with 512 value.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 6a5519f0ff25..bf80a61dd941 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2325,15 +2325,8 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	bool wide_bus;
 	int ecc_mode = 1;
 
-	/*
-	 * the controller requires each step consists of 512 bytes of data.
-	 * bail out if DT has populated a wrong step size.
-	 */
-	if (ecc->size != NANDC_STEP_SIZE) {
-		dev_err(nandc->dev, "invalid ecc size\n");
-		return -EINVAL;
-	}
-
+	/* controller only supports 512 bytes data steps */
+	ecc->size = NANDC_STEP_SIZE;
 	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
 
 	if (ecc->strength >= 8) {
-- 
cgit v1.2.3


From 7ddb937f2c1dc79a9d35e6319b96e05ba7b04a8f Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:32 +0530
Subject: mtd: rawnand: qcom: use the ecc strength from device parameter

Currently the driver uses the ECC strength specified in DT.
The QPIC/EBI2 NAND supports 4 or 8-bit ECC correction. The same
kind of board can have different NAND parts so use the ECC
strength from device parameters if it is not specified in DT.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 29 +++++++++++++++++++++--------
 1 file changed, 21 insertions(+), 8 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index bf80a61dd941..237578030a2a 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2315,19 +2315,39 @@ static const struct mtd_ooblayout_ops qcom_nand_ooblayout_ops = {
 	.free = qcom_nand_ooblayout_free,
 };
 
+static int
+qcom_nandc_calc_ecc_bytes(int step_size, int strength)
+{
+	return strength == 4 ? 12 : 16;
+}
+NAND_ECC_CAPS_SINGLE(qcom_nandc_ecc_caps, qcom_nandc_calc_ecc_bytes,
+		     NANDC_STEP_SIZE, 4, 8);
+
 static int qcom_nand_host_setup(struct qcom_nand_host *host)
 {
 	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	int cwperpage, bad_block_byte;
+	int cwperpage, bad_block_byte, ret;
 	bool wide_bus;
 	int ecc_mode = 1;
 
 	/* controller only supports 512 bytes data steps */
 	ecc->size = NANDC_STEP_SIZE;
 	wide_bus = chip->options & NAND_BUSWIDTH_16 ? true : false;
+	cwperpage = mtd->writesize / NANDC_STEP_SIZE;
+
+	/*
+	 * Each CW has 4 available OOB bytes which will be protected with ECC
+	 * so remaining bytes can be used for ECC.
+	 */
+	ret = nand_ecc_choose_conf(chip, &qcom_nandc_ecc_caps,
+				   mtd->oobsize - (cwperpage * 4));
+	if (ret) {
+		dev_err(nandc->dev, "No valid ECC settings possible\n");
+		return ret;
+	}
 
 	if (ecc->strength >= 8) {
 		/* 8 bit ECC defaults to BCH ECC on all platforms */
@@ -2396,7 +2416,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 
 	mtd_set_ooblayout(mtd, &qcom_nand_ooblayout_ops);
 
-	cwperpage = mtd->writesize / ecc->size;
 	nandc->max_cwperpage = max_t(unsigned int, nandc->max_cwperpage,
 				     cwperpage);
 
@@ -2412,12 +2431,6 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	 * for 8 bit ECC
 	 */
 	host->cw_size = host->cw_data + ecc->bytes;
-
-	if (ecc->bytes * (mtd->writesize / ecc->size) > mtd->oobsize) {
-		dev_err(nandc->dev, "ecc data doesn't fit in OOB area\n");
-		return -EINVAL;
-	}
-
 	bad_block_byte = mtd->writesize - host->cw_size * (cwperpage - 1) + 1;
 
 	host->cfg0 = (cwperpage - 1) << CW_PER_PAGE
-- 
cgit v1.2.3


From 6f20070d51a20e489ef117603210264c6bcde8a5 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:33 +0530
Subject: mtd: rawnand: qcom: wait for desc completion in all BAM channels

The BAM has 3 channels - tx, rx and command. command channel
is used for register read/writes, tx channel for data writes
and rx channel for data reads. Currently, the driver assumes the
transfer completion once it gets all the command descriptors
completed. Sometimes, there is race condition between data channel
(tx/rx) and command channel completion. In these cases,
the data present in buffer is not valid during small window
between command descriptor completion and data descriptor
completion.

This patch generates NAND transfer completion when both
(Data and Command) DMA channels have completed all its DMA
descriptors. It assigns completion callback in last
DMA descriptors of that channel and wait for completion.

Fixes: 8d6b6d7e135e ("mtd: nand: qcom: support for command descriptor formation")
Cc: stable@vger.kernel.org
Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 53 ++++++++++++++++++++++++++++++++++++++-
 1 file changed, 52 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 237578030a2a..fc2014997dde 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -213,6 +213,8 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
 #define QPIC_PER_CW_CMD_SGL		32
 #define QPIC_PER_CW_DATA_SGL		8
 
+#define QPIC_NAND_COMPLETION_TIMEOUT	msecs_to_jiffies(2000)
+
 /*
  * Flags used in DMA descriptor preparation helper functions
  * (i.e. read_reg_dma/write_reg_dma/read_data_dma/write_data_dma)
@@ -245,6 +247,11 @@ nandc_set_reg(nandc, NAND_READ_LOCATION_##reg,			\
  * @tx_sgl_start - start index in data sgl for tx.
  * @rx_sgl_pos - current index in data sgl for rx.
  * @rx_sgl_start - start index in data sgl for rx.
+ * @wait_second_completion - wait for second DMA desc completion before making
+ *			     the NAND transfer completion.
+ * @txn_done - completion for NAND transfer.
+ * @last_data_desc - last DMA desc in data channel (tx/rx).
+ * @last_cmd_desc - last DMA desc in command channel.
  */
 struct bam_transaction {
 	struct bam_cmd_element *bam_ce;
@@ -258,6 +265,10 @@ struct bam_transaction {
 	u32 tx_sgl_start;
 	u32 rx_sgl_pos;
 	u32 rx_sgl_start;
+	bool wait_second_completion;
+	struct completion txn_done;
+	struct dma_async_tx_descriptor *last_data_desc;
+	struct dma_async_tx_descriptor *last_cmd_desc;
 };
 
 /*
@@ -504,6 +515,8 @@ alloc_bam_transaction(struct qcom_nand_controller *nandc)
 
 	bam_txn->data_sgl = bam_txn_buf;
 
+	init_completion(&bam_txn->txn_done);
+
 	return bam_txn;
 }
 
@@ -523,11 +536,33 @@ static void clear_bam_transaction(struct qcom_nand_controller *nandc)
 	bam_txn->tx_sgl_start = 0;
 	bam_txn->rx_sgl_pos = 0;
 	bam_txn->rx_sgl_start = 0;
+	bam_txn->last_data_desc = NULL;
+	bam_txn->wait_second_completion = false;
 
 	sg_init_table(bam_txn->cmd_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_CMD_SGL);
 	sg_init_table(bam_txn->data_sgl, nandc->max_cwperpage *
 		      QPIC_PER_CW_DATA_SGL);
+
+	reinit_completion(&bam_txn->txn_done);
+}
+
+/* Callback for DMA descriptor completion */
+static void qpic_bam_dma_done(void *data)
+{
+	struct bam_transaction *bam_txn = data;
+
+	/*
+	 * In case of data transfer with NAND, 2 callbacks will be generated.
+	 * One for command channel and another one for data channel.
+	 * If current transaction has data descriptors
+	 * (i.e. wait_second_completion is true), then set this to false
+	 * and wait for second DMA descriptor completion.
+	 */
+	if (bam_txn->wait_second_completion)
+		bam_txn->wait_second_completion = false;
+	else
+		complete(&bam_txn->txn_done);
 }
 
 static inline struct qcom_nand_host *to_qcom_nand_host(struct nand_chip *chip)
@@ -756,6 +791,12 @@ static int prepare_bam_async_desc(struct qcom_nand_controller *nandc,
 
 	desc->dma_desc = dma_desc;
 
+	/* update last data/command descriptor */
+	if (chan == nandc->cmd_chan)
+		bam_txn->last_cmd_desc = dma_desc;
+	else
+		bam_txn->last_data_desc = dma_desc;
+
 	list_add_tail(&desc->node, &nandc->desc_list);
 
 	return 0;
@@ -1273,10 +1314,20 @@ static int submit_descs(struct qcom_nand_controller *nandc)
 		cookie = dmaengine_submit(desc->dma_desc);
 
 	if (nandc->props->is_bam) {
+		bam_txn->last_cmd_desc->callback = qpic_bam_dma_done;
+		bam_txn->last_cmd_desc->callback_param = bam_txn;
+		if (bam_txn->last_data_desc) {
+			bam_txn->last_data_desc->callback = qpic_bam_dma_done;
+			bam_txn->last_data_desc->callback_param = bam_txn;
+			bam_txn->wait_second_completion = true;
+		}
+
 		dma_async_issue_pending(nandc->tx_chan);
 		dma_async_issue_pending(nandc->rx_chan);
+		dma_async_issue_pending(nandc->cmd_chan);
 
-		if (dma_sync_wait(nandc->cmd_chan, cookie) != DMA_COMPLETE)
+		if (!wait_for_completion_timeout(&bam_txn->txn_done,
+						 QPIC_NAND_COMPLETION_TIMEOUT))
 			return -ETIMEDOUT;
 	} else {
 		if (dma_sync_wait(nandc->chan, cookie) != DMA_COMPLETE)
-- 
cgit v1.2.3


From 8eab72148808a74535c3322f6ca30aba77d2d4a9 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:34 +0530
Subject: mtd: rawnand: qcom: erased page detection for uncorrectable errors
 only

Following is the flow in the HW if controller tries to read erased
page:

1. First ECC uncorrectable error will be generated from ECC engine
   since ECC engine first calculates the ECC with all 0xff and match
   the calculated ECC with ECC code in OOB (which is again all 0xff).
2. After getting ECC error, erased CW detection logic will be
   applied which is different for BCH and RS ECC
    a. For BCH, HW checks if all the bytes in page are 0xff and then
       it updates the status in separate register
       NAND_ERASED_CW_DETECT_STATUS.
    b. For RS ECC, the HW reports the same error when reading an
       erased CW, but it notifies that it is an erased CW by
       placing special characters at certain offsets in the
       buffer.

So the erased CW detect status should be checked only if ECC engine
generated the uncorrectable error.

Currently for all other operational errors also (like TIMEOUT, MPU
errors, etc.), the erased CW detect logic is being applied so fix this
and return EIO for other operational errors.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 67 +++++++++++++++++++++++++--------------
 1 file changed, 44 insertions(+), 23 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index fc2014997dde..0d931d51f85a 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1576,6 +1576,7 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	unsigned int max_bitflips = 0;
 	struct read_stats *buf;
+	bool flash_op_err = false;
 	int i;
 
 	buf = (struct read_stats *)nandc->reg_read_buf;
@@ -1597,8 +1598,18 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 		buffer = le32_to_cpu(buf->buffer);
 		erased_cw = le32_to_cpu(buf->erased_cw);
 
-		if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
+		/*
+		 * Check ECC failure for each codeword. ECC failure can
+		 * happen in either of the following conditions
+		 * 1. If number of bitflips are greater than ECC engine
+		 *    capability.
+		 * 2. If this codeword contains all 0xff for which erased
+		 *    codeword detection check will be done.
+		 */
+		if ((flash & FS_OP_ERR) && (buffer & BS_UNCORRECTABLE_BIT)) {
 			bool erased;
+			int ret, ecclen, extraooblen;
+			void *eccbuf;
 
 			/* ignore erased codeword errors */
 			if (host->bch_enabled) {
@@ -1616,29 +1627,36 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 				continue;
 			}
 
-			if (buffer & BS_UNCORRECTABLE_BIT) {
-				int ret, ecclen, extraooblen;
-				void *eccbuf;
-
-				eccbuf = oob_buf ? oob_buf + oob_len : NULL;
-				ecclen = oob_buf ? host->ecc_bytes_hw : 0;
-				extraooblen = oob_buf ? oob_len : 0;
-
-				/*
-				 * make sure it isn't an erased page reported
-				 * as not-erased by HW because of a few bitflips
-				 */
-				ret = nand_check_erased_ecc_chunk(data_buf,
-					data_len, eccbuf, ecclen, oob_buf,
-					extraooblen, ecc->strength);
-				if (ret < 0) {
-					mtd->ecc_stats.failed++;
-				} else {
-					mtd->ecc_stats.corrected += ret;
-					max_bitflips =
-						max_t(unsigned int, max_bitflips, ret);
-				}
+			eccbuf = oob_buf ? oob_buf + oob_len : NULL;
+			ecclen = oob_buf ? host->ecc_bytes_hw : 0;
+			extraooblen = oob_buf ? oob_len : 0;
+
+			/*
+			 * make sure it isn't an erased page reported
+			 * as not-erased by HW because of a few bitflips
+			 */
+			ret = nand_check_erased_ecc_chunk(data_buf,
+				data_len, eccbuf, ecclen, oob_buf,
+				extraooblen, ecc->strength);
+			if (ret < 0) {
+				mtd->ecc_stats.failed++;
+			} else {
+				mtd->ecc_stats.corrected += ret;
+				max_bitflips =
+					max_t(unsigned int, max_bitflips, ret);
 			}
+		/*
+		 * Check if MPU or any other operational error (timeout,
+		 * device failure, etc.) happened for this codeword and
+		 * make flash_op_err true. If flash_op_err is set, then
+		 * EIO will be returned for page read.
+		 */
+		} else if (flash & (FS_OP_ERR | FS_MPU_ERR)) {
+			flash_op_err = true;
+		/*
+		 * No ECC or operational errors happened. Check the number of
+		 * bits corrected and update the ecc_stats.corrected.
+		 */
 		} else {
 			unsigned int stat;
 
@@ -1652,6 +1670,9 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 			oob_buf += oob_len + ecc->bytes;
 	}
 
+	if (flash_op_err)
+		return -EIO;
+
 	return max_bitflips;
 }
 
-- 
cgit v1.2.3


From 2f610386736d9e5dc69fa06374138f9712690921 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:35 +0530
Subject: mtd: rawnand: qcom: fix null pointer access for erased page detection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

parse_read_errors can be called with only oob_buf in which case
data_buf will be NULL.  If data_buf is NULL, then don’t
treat this page as completely erased in case of ECC uncorrectable
error for RS ECC. For BCH ECC, the controller itself tells
regarding erased page in status register.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 0d931d51f85a..a831f9cb458a 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1611,13 +1611,24 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 			int ret, ecclen, extraooblen;
 			void *eccbuf;
 
-			/* ignore erased codeword errors */
+			/*
+			 * For BCH ECC, ignore erased codeword errors, if
+			 * ERASED_CW bits are set.
+			 */
 			if (host->bch_enabled) {
 				erased = (erased_cw & ERASED_CW) == ERASED_CW ?
 					 true : false;
-			} else {
+			/*
+			 * For RS ECC, HW reports the erased CW by placing
+			 * special characters at certain offsets in the buffer.
+			 * These special characters will be valid only if
+			 * complete page is read i.e. data_buf is not NULL.
+			 */
+			} else if (data_buf) {
 				erased = erased_chunk_check_and_fixup(data_buf,
 								      data_len);
+			} else {
+				erased = false;
 			}
 
 			if (erased) {
@@ -1665,7 +1676,8 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 			max_bitflips = max(max_bitflips, stat);
 		}
 
-		data_buf += data_len;
+		if (data_buf)
+			data_buf += data_len;
 		if (oob_buf)
 			oob_buf += oob_len + ecc->bytes;
 	}
-- 
cgit v1.2.3


From add0cfa3c3e51149c2101765edf05c548ba5f2ee Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:36 +0530
Subject: mtd: rawnand: qcom: parse read errors for read oob also

read_page and read_oob both calls the read_page_ecc function.
The QCOM NAND controller protect the OOB available bytes with
ECC so read errors should be checked for read_oob also.
This patch moves the error checking code inside read_page_ecc
so caller does not have to check explicitly for read errors.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 26 +++++++++-----------------
 1 file changed, 9 insertions(+), 17 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index a831f9cb458a..285b2ad328de 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1698,6 +1698,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 	int i, ret;
 
 	config_nand_page_read(nandc);
@@ -1758,12 +1759,14 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 	}
 
 	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read page/oob\n");
-
 	free_descs(nandc);
 
-	return ret;
+	if (ret) {
+		dev_err(nandc->dev, "failure to read page/oob\n");
+		return ret;
+	}
+
+	return parse_read_errors(host, data_buf_start, oob_buf_start);
 }
 
 /*
@@ -1808,20 +1811,14 @@ static int qcom_nandc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	u8 *data_buf, *oob_buf = NULL;
-	int ret;
 
 	nand_read_page_op(chip, page, 0, NULL, 0);
 	data_buf = buf;
 	oob_buf = oob_required ? chip->oob_poi : NULL;
 
 	clear_bam_transaction(nandc);
-	ret = read_page_ecc(host, data_buf, oob_buf);
-	if (ret) {
-		dev_err(nandc->dev, "failure to read page\n");
-		return ret;
-	}
 
-	return parse_read_errors(host, data_buf, oob_buf);
+	return read_page_ecc(host, data_buf, oob_buf);
 }
 
 /* implements ecc->read_page_raw() */
@@ -1911,7 +1908,6 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int ret;
 
 	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
@@ -1920,11 +1916,7 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	set_address(host, 0, page);
 	update_rw_regs(host, ecc->steps, true);
 
-	ret = read_page_ecc(host, NULL, chip->oob_poi);
-	if (ret)
-		dev_err(nandc->dev, "failure to read oob\n");
-
-	return ret;
+	return read_page_ecc(host, NULL, chip->oob_poi);
 }
 
 /* implements ecc->write_page() */
-- 
cgit v1.2.3


From 28eed9f6cab6ab28cdca4a43df4f8ed51dd5f8f8 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:37 +0530
Subject: mtd: rawnand: qcom: modify write_oob to remove read codeword part

QCOM NAND controller layout protects available OOB data bytes with
ECC also so when ecc->write_oob() is being called then it
can't update just OOB bytes. Currently, it first reads the last
codeword which includes old OOB bytes. Then it updates the old OOB
bytes with new ones and then again writes the codeword back.
The reading codeword is unnecessary since user is responsible to
have these bytes cleared to 0xFF.

This patch removes the read part and updates the OOB bytes with
data area padded with OxFF.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 285b2ad328de..28361b56ac45 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2064,11 +2064,9 @@ static int qcom_nandc_write_page_raw(struct mtd_info *mtd,
 /*
  * implements ecc->write_oob()
  *
- * the NAND controller cannot write only data or only oob within a codeword,
- * since ecc is calculated for the combined codeword. we first copy the
- * entire contents for the last codeword(data + oob), replace the old oob
- * with the new one in chip->oob_poi, and then write the entire codeword.
- * this read-copy-write operation results in a slight performance loss.
+ * the NAND controller cannot write only data or only OOB within a codeword
+ * since ECC is calculated for the combined codeword. So update the OOB from
+ * chip->oob_poi, and pad the data area with OxFF before writing.
  */
 static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 				int page)
@@ -2081,19 +2079,13 @@ static int qcom_nandc_write_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	int ret;
 
 	host->use_ecc = true;
-
-	clear_bam_transaction(nandc);
-	ret = copy_last_cw(host, page);
-	if (ret)
-		return ret;
-
-	clear_read_regs(nandc);
 	clear_bam_transaction(nandc);
 
 	/* calculate the data and oob size for the last codeword/step */
 	data_size = ecc->size - ((ecc->steps - 1) << 2);
 	oob_size = mtd->oobavail;
 
+	memset(nandc->data_buffer, 0xff, host->cw_data);
 	/* override new oob content to last codeword */
 	mtd_ooblayout_get_databytes(mtd, nandc->data_buffer + data_size, oob,
 				    0, mtd->oobavail);
-- 
cgit v1.2.3


From 783b5bf9bd91a59717df38ec3ba7d65b1f441f32 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:38 +0530
Subject: mtd: rawnand: qcom: fix return value for raw page read

Fix value returned by ->read_page_raw() to be the
actual operation status, instead of always 0.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 28361b56ac45..887b1f6aff14 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1898,7 +1898,7 @@ static int qcom_nandc_read_page_raw(struct mtd_info *mtd,
 
 	free_descs(nandc);
 
-	return 0;
+	return ret;
 }
 
 /* implements ecc->read_oob() */
-- 
cgit v1.2.3


From 5bc36b2bf6e2c8bff723ebcd9ae9bd38156d21c0 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:39 +0530
Subject: mtd: rawnand: qcom: check for operation errors in case of raw read
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently there is no error checking for raw read. For raw
reads, there won’t be any ECC failure but the operational
failures are possible, so schedule the NAND_FLASH_STATUS read
after each codeword.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 58 +++++++++++++++++++++++++++------------
 1 file changed, 40 insertions(+), 18 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 887b1f6aff14..5999c397b771 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1096,7 +1096,8 @@ static void config_nand_page_read(struct qcom_nand_controller *nandc)
  * Helper to prepare DMA descriptors for configuring registers
  * before reading each codeword in NAND page.
  */
-static void config_nand_cw_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_cw_read(struct qcom_nand_controller *nandc, bool use_ecc)
 {
 	if (nandc->props->is_bam)
 		write_reg_dma(nandc, NAND_READ_LOCATION_0, 4,
@@ -1105,19 +1106,25 @@ static void config_nand_cw_read(struct qcom_nand_controller *nandc)
 	write_reg_dma(nandc, NAND_FLASH_CMD, 1, NAND_BAM_NEXT_SGL);
 	write_reg_dma(nandc, NAND_EXEC_CMD, 1, NAND_BAM_NEXT_SGL);
 
-	read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
-	read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
-		     NAND_BAM_NEXT_SGL);
+	if (use_ecc) {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 2, 0);
+		read_reg_dma(nandc, NAND_ERASED_CW_DETECT_STATUS, 1,
+			     NAND_BAM_NEXT_SGL);
+	} else {
+		read_reg_dma(nandc, NAND_FLASH_STATUS, 1, NAND_BAM_NEXT_SGL);
+	}
 }
 
 /*
  * Helper to prepare dma descriptors to configure registers needed for reading a
  * single codeword in page
  */
-static void config_nand_single_cw_page_read(struct qcom_nand_controller *nandc)
+static void
+config_nand_single_cw_page_read(struct qcom_nand_controller *nandc,
+				bool use_ecc)
 {
 	config_nand_page_read(nandc);
-	config_nand_cw_read(nandc);
+	config_nand_cw_read(nandc, use_ecc);
 }
 
 /*
@@ -1198,7 +1205,7 @@ static int nandc_param(struct qcom_nand_host *host)
 	nandc->buf_count = 512;
 	memset(nandc->data_buffer, 0xff, nandc->buf_count);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, false);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer,
 		      nandc->buf_count, 0);
@@ -1563,6 +1570,23 @@ struct read_stats {
 	__le32 erased_cw;
 };
 
+/* reads back FLASH_STATUS register set by the controller */
+static int check_flash_errors(struct qcom_nand_host *host, int cw_cnt)
+{
+	struct nand_chip *chip = &host->chip;
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	int i;
+
+	for (i = 0; i < cw_cnt; i++) {
+		u32 flash = le32_to_cpu(nandc->reg_read_buf[i]);
+
+		if (flash & (FS_OP_ERR | FS_MPU_ERR))
+			return -EIO;
+	}
+
+	return 0;
+}
+
 /*
  * reads back status registers set by the controller to notify page read
  * errors. this is equivalent to what 'ecc->correct()' would do.
@@ -1729,7 +1753,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 			}
 		}
 
-		config_nand_cw_read(nandc);
+		config_nand_cw_read(nandc, true);
 
 		if (data_buf)
 			read_data_dma(nandc, FLASH_BUF_ACC, data_buf,
@@ -1791,7 +1815,7 @@ static int copy_last_cw(struct qcom_nand_host *host, int page)
 	set_address(host, host->cw_size * (ecc->steps - 1), page);
 	update_rw_regs(host, 1, true);
 
-	config_nand_single_cw_page_read(nandc);
+	config_nand_single_cw_page_read(nandc, host->use_ecc);
 
 	read_data_dma(nandc, FLASH_BUF_ACC, nandc->data_buffer, size, 0);
 
@@ -1874,7 +1898,7 @@ static int qcom_nandc_read_page_raw(struct mtd_info *mtd,
 			nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
 		}
 
-		config_nand_cw_read(nandc);
+		config_nand_cw_read(nandc, false);
 
 		read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
 		reg_off += data_size1;
@@ -1893,12 +1917,13 @@ static int qcom_nandc_read_page_raw(struct mtd_info *mtd,
 	}
 
 	ret = submit_descs(nandc);
-	if (ret)
-		dev_err(nandc->dev, "failure to read raw page\n");
-
 	free_descs(nandc);
+	if (ret) {
+		dev_err(nandc->dev, "failure to read raw page\n");
+		return ret;
+	}
 
-	return ret;
+	return check_flash_errors(host, ecc->steps);
 }
 
 /* implements ecc->read_oob() */
@@ -2117,7 +2142,6 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	int page, ret, bbpos, bad = 0;
-	u32 flash_status;
 
 	page = (int)(ofs >> chip->page_shift) & chip->pagemask;
 
@@ -2134,9 +2158,7 @@ static int qcom_nandc_block_bad(struct mtd_info *mtd, loff_t ofs)
 	if (ret)
 		goto err;
 
-	flash_status = le32_to_cpu(nandc->reg_read_buf[0]);
-
-	if (flash_status & (FS_OP_ERR | FS_MPU_ERR)) {
+	if (check_flash_errors(host, 1)) {
 		dev_warn(nandc->dev, "error when trying to read BBM\n");
 		goto err;
 	}
-- 
cgit v1.2.3


From 85632c17194e35e00871cfd80713c9acf087ac4f Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:40 +0530
Subject: mtd: rawnand: qcom: code reorganization for raw read

Make separate function to perform raw read for one codeword and
call this function multiple times for each codeword in case of
raw page read. This separate function will help in subsequent
patches related with erased codeword bitflip detection.

It will decrease throughput for raw page read. Raw page read
is used for debug purpose so it won't affect normal flash
operations.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 146 ++++++++++++++++++++------------------
 1 file changed, 78 insertions(+), 68 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 5999c397b771..160acdff7d86 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1587,6 +1587,74 @@ static int check_flash_errors(struct qcom_nand_host *host, int cw_cnt)
 	return 0;
 }
 
+/* performs raw read for one codeword */
+static int
+qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip,
+		       u8 *data_buf, u8 *oob_buf, int page, int cw)
+{
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
+	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	int data_size1, data_size2, oob_size1, oob_size2;
+	int ret, reg_off = FLASH_BUF_ACC, read_loc = 0;
+
+	nand_read_page_op(chip, page, 0, NULL, 0);
+	host->use_ecc = false;
+
+	clear_bam_transaction(nandc);
+	set_address(host, host->cw_size * cw, page);
+	update_rw_regs(host, 1, true);
+	config_nand_page_read(nandc);
+
+	data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
+	oob_size1 = host->bbm_size;
+
+	if (cw == (ecc->steps - 1)) {
+		data_size2 = ecc->size - data_size1 -
+			     ((ecc->steps - 1) * 4);
+		oob_size2 = (ecc->steps * 4) + host->ecc_bytes_hw +
+			    host->spare_bytes;
+	} else {
+		data_size2 = host->cw_data - data_size1;
+		oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
+	}
+
+	if (nandc->props->is_bam) {
+		nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
+		read_loc += data_size1;
+
+		nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
+		read_loc += oob_size1;
+
+		nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
+		read_loc += data_size2;
+
+		nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
+	}
+
+	config_nand_cw_read(nandc, false);
+
+	read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
+	reg_off += data_size1;
+
+	read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
+	reg_off += oob_size1;
+
+	read_data_dma(nandc, reg_off, data_buf + data_size1, data_size2, 0);
+	reg_off += data_size2;
+
+	read_data_dma(nandc, reg_off, oob_buf + oob_size1, oob_size2, 0);
+
+	ret = submit_descs(nandc);
+	free_descs(nandc);
+	if (ret) {
+		dev_err(nandc->dev, "failure to read raw cw %d\n", cw);
+		return ret;
+	}
+
+	return check_flash_errors(host, 1);
+}
+
 /*
  * reads back status registers set by the controller to notify page read
  * errors. this is equivalent to what 'ecc->correct()' would do.
@@ -1851,79 +1919,21 @@ static int qcom_nandc_read_page_raw(struct mtd_info *mtd,
 				    int oob_required, int page)
 {
 	struct qcom_nand_host *host = to_qcom_nand_host(chip);
-	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
-	u8 *data_buf, *oob_buf;
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	int i, ret;
-	int read_loc;
+	int cw, ret;
+	u8 *data_buf = buf, *oob_buf = chip->oob_poi;
 
-	nand_read_page_op(chip, page, 0, NULL, 0);
-	data_buf = buf;
-	oob_buf = chip->oob_poi;
-
-	host->use_ecc = false;
-
-	clear_bam_transaction(nandc);
-	update_rw_regs(host, ecc->steps, true);
-	config_nand_page_read(nandc);
-
-	for (i = 0; i < ecc->steps; i++) {
-		int data_size1, data_size2, oob_size1, oob_size2;
-		int reg_off = FLASH_BUF_ACC;
-
-		data_size1 = mtd->writesize - host->cw_size * (ecc->steps - 1);
-		oob_size1 = host->bbm_size;
-
-		if (i == (ecc->steps - 1)) {
-			data_size2 = ecc->size - data_size1 -
-				     ((ecc->steps - 1) << 2);
-			oob_size2 = (ecc->steps << 2) + host->ecc_bytes_hw +
-				    host->spare_bytes;
-		} else {
-			data_size2 = host->cw_data - data_size1;
-			oob_size2 = host->ecc_bytes_hw + host->spare_bytes;
-		}
-
-		if (nandc->props->is_bam) {
-			read_loc = 0;
-			nandc_set_read_loc(nandc, 0, read_loc, data_size1, 0);
-			read_loc += data_size1;
-
-			nandc_set_read_loc(nandc, 1, read_loc, oob_size1, 0);
-			read_loc += oob_size1;
-
-			nandc_set_read_loc(nandc, 2, read_loc, data_size2, 0);
-			read_loc += data_size2;
-
-			nandc_set_read_loc(nandc, 3, read_loc, oob_size2, 1);
-		}
-
-		config_nand_cw_read(nandc, false);
-
-		read_data_dma(nandc, reg_off, data_buf, data_size1, 0);
-		reg_off += data_size1;
-		data_buf += data_size1;
-
-		read_data_dma(nandc, reg_off, oob_buf, oob_size1, 0);
-		reg_off += oob_size1;
-		oob_buf += oob_size1;
-
-		read_data_dma(nandc, reg_off, data_buf, data_size2, 0);
-		reg_off += data_size2;
-		data_buf += data_size2;
+	for (cw = 0; cw < ecc->steps; cw++) {
+		ret = qcom_nandc_read_cw_raw(mtd, chip, data_buf, oob_buf,
+					     page, cw);
+		if (ret)
+			return ret;
 
-		read_data_dma(nandc, reg_off, oob_buf, oob_size2, 0);
-		oob_buf += oob_size2;
+		data_buf += host->cw_data;
+		oob_buf += ecc->bytes;
 	}
 
-	ret = submit_descs(nandc);
-	free_descs(nandc);
-	if (ret) {
-		dev_err(nandc->dev, "failure to read raw page\n");
-		return ret;
-	}
-
-	return check_flash_errors(host, ecc->steps);
+	return 0;
 }
 
 /* implements ecc->read_oob() */
-- 
cgit v1.2.3


From 0cf5c7dbaa392d11cfae532cedeaad0ac48b2165 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Wed, 20 Jun 2018 12:57:42 +0530
Subject: mtd: rawnand: provide only single helper function for ECC conf

Function nand_ecc_choose_conf() will be help for all the cases, so
other helper functions can be made static.

nand_check_ecc_caps(): Invoke nand_ecc_choose_conf() with
                       both chip->ecc.size and chip->ecc.strength
                       value set.

nand_maximize_ecc(): Invoke nand_ecc_choose_conf() with
                     NAND_ECC_MAXIMIZE flag.

nand_match_ecc_req(): Invoke nand_ecc_choose_conf() with either
                      chip->ecc.size or chip->ecc.strength value
                      set and without NAND_ECC_MAXIMIZE flag.

CC: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 39 +++++++++++++++------------------------
 include/linux/mtd/rawnand.h      |  9 ---------
 2 files changed, 15 insertions(+), 33 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 2858d0b09c1d..faac82b1e058 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -6085,24 +6085,17 @@ static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
  * by the controller and the calculated ECC bytes fit within the chip's OOB.
  * On success, the calculated ECC bytes is set.
  */
-int nand_check_ecc_caps(struct nand_chip *chip,
-			const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_check_ecc_caps(struct nand_chip *chip,
+		    const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
 	int preset_step = chip->ecc.size;
 	int preset_strength = chip->ecc.strength;
-	int nsteps, ecc_bytes;
+	int ecc_bytes, nsteps = mtd->writesize / preset_step;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
-	if (!preset_step || !preset_strength)
-		return -ENODATA;
-
-	nsteps = mtd->writesize / preset_step;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 
@@ -6135,7 +6128,6 @@ int nand_check_ecc_caps(struct nand_chip *chip,
 
 	return -ENOTSUPP;
 }
-EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
 
 /**
  * nand_match_ecc_req - meet the chip's requirement with least ECC bytes
@@ -6147,8 +6139,9 @@ EXPORT_SYMBOL_GPL(nand_check_ecc_caps);
  * number of ECC bytes (i.e. with the largest number of OOB-free bytes).
  * On success, the chosen ECC settings are set.
  */
-int nand_match_ecc_req(struct nand_chip *chip,
-		       const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_match_ecc_req(struct nand_chip *chip,
+		   const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6159,9 +6152,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 	int best_ecc_bytes_total = INT_MAX;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	/* No information provided by the NAND chip */
 	if (!req_step || !req_strength)
 		return -ENOTSUPP;
@@ -6220,7 +6210,6 @@ int nand_match_ecc_req(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_match_ecc_req);
 
 /**
  * nand_maximize_ecc - choose the max ECC strength available
@@ -6231,8 +6220,9 @@ EXPORT_SYMBOL_GPL(nand_match_ecc_req);
  * Choose the max ECC strength that is supported on the controller, and can fit
  * within the chip's OOB.  On success, the chosen ECC settings are set.
  */
-int nand_maximize_ecc(struct nand_chip *chip,
-		      const struct nand_ecc_caps *caps, int oobavail)
+static int
+nand_maximize_ecc(struct nand_chip *chip,
+		  const struct nand_ecc_caps *caps, int oobavail)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	const struct nand_ecc_step_info *stepinfo;
@@ -6242,9 +6232,6 @@ int nand_maximize_ecc(struct nand_chip *chip,
 	int best_strength, best_ecc_bytes;
 	int i, j;
 
-	if (WARN_ON(oobavail < 0))
-		return -EINVAL;
-
 	for (i = 0; i < caps->nstepinfos; i++) {
 		stepinfo = &caps->stepinfos[i];
 		step_size = stepinfo->stepsize;
@@ -6293,7 +6280,6 @@ int nand_maximize_ecc(struct nand_chip *chip,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(nand_maximize_ecc);
 
 /**
  * nand_ecc_choose_conf - Set the ECC strength and ECC step size
@@ -6315,6 +6301,11 @@ EXPORT_SYMBOL_GPL(nand_maximize_ecc);
 int nand_ecc_choose_conf(struct nand_chip *chip,
 			 const struct nand_ecc_caps *caps, int oobavail)
 {
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (WARN_ON(oobavail < 0 || oobavail > mtd->oobsize))
+		return -EINVAL;
+
 	if (chip->ecc.size && chip->ecc.strength)
 		return nand_check_ecc_caps(chip, caps, oobavail);
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 2ce305388471..0c6fb316b409 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1663,15 +1663,6 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 				void *extraoob, int extraooblen,
 				int threshold);
 
-int nand_check_ecc_caps(struct nand_chip *chip,
-			const struct nand_ecc_caps *caps, int oobavail);
-
-int nand_match_ecc_req(struct nand_chip *chip,
-		       const struct nand_ecc_caps *caps,  int oobavail);
-
-int nand_maximize_ecc(struct nand_chip *chip,
-		      const struct nand_ecc_caps *caps, int oobavail);
-
 int nand_ecc_choose_conf(struct nand_chip *chip,
 			 const struct nand_ecc_caps *caps, int oobavail);
 
-- 
cgit v1.2.3


From 7529df4652482c33ae1a99ee8189401146f13cb7 Mon Sep 17 00:00:00 2001
From: Peter Pan <peterpandong@micron.com>
Date: Fri, 22 Jun 2018 14:28:23 +0200
Subject: mtd: nand: Add core infrastructure to support SPI NANDs

Add a SPI NAND framework based on the generic NAND framework and the
spi-mem infrastructure.

In its current state, this framework supports the following features:

- single/dual/quad IO modes
- on-die ECC

Signed-off-by: Peter Pan <peterpandong@micron.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/Kconfig      |    1 +
 drivers/mtd/nand/Makefile     |    1 +
 drivers/mtd/nand/spi/Kconfig  |    7 +
 drivers/mtd/nand/spi/Makefile |    3 +
 drivers/mtd/nand/spi/core.c   | 1136 +++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spinand.h   |  416 +++++++++++++++
 include/linux/spi/spi-mem.h   |    4 +-
 7 files changed, 1567 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mtd/nand/spi/Kconfig
 create mode 100644 drivers/mtd/nand/spi/Makefile
 create mode 100644 drivers/mtd/nand/spi/core.c
 create mode 100644 include/linux/mtd/spinand.h

diff --git a/drivers/mtd/nand/Kconfig b/drivers/mtd/nand/Kconfig
index 88c7d3b4ff8b..9033215e62ea 100644
--- a/drivers/mtd/nand/Kconfig
+++ b/drivers/mtd/nand/Kconfig
@@ -4,3 +4,4 @@ config MTD_NAND_CORE
 source "drivers/mtd/nand/onenand/Kconfig"
 
 source "drivers/mtd/nand/raw/Kconfig"
+source "drivers/mtd/nand/spi/Kconfig"
diff --git a/drivers/mtd/nand/Makefile b/drivers/mtd/nand/Makefile
index 3f0cb87f1a57..7ecd80c0a66e 100644
--- a/drivers/mtd/nand/Makefile
+++ b/drivers/mtd/nand/Makefile
@@ -5,3 +5,4 @@ obj-$(CONFIG_MTD_NAND_CORE) += nandcore.o
 
 obj-y	+= onenand/
 obj-y	+= raw/
+obj-y	+= spi/
diff --git a/drivers/mtd/nand/spi/Kconfig b/drivers/mtd/nand/spi/Kconfig
new file mode 100644
index 000000000000..7c37d2929b68
--- /dev/null
+++ b/drivers/mtd/nand/spi/Kconfig
@@ -0,0 +1,7 @@
+menuconfig MTD_SPI_NAND
+	tristate "SPI NAND device Support"
+	select MTD_NAND_CORE
+	depends on SPI_MASTER
+	select SPI_MEM
+	help
+	  This is the framework for the SPI NAND device drivers.
diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
new file mode 100644
index 000000000000..2c473b765027
--- /dev/null
+++ b/drivers/mtd/nand/spi/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+spinand-objs := core.o
+obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
new file mode 100644
index 000000000000..4efbeb0d85b4
--- /dev/null
+++ b/drivers/mtd/nand/spi/core.c
@@ -0,0 +1,1136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#define pr_fmt(fmt)	"spi-nand: " fmt
+
+#include <linux/device.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mtd/spinand.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+static void spinand_cache_op_adjust_colum(struct spinand_device *spinand,
+					  const struct nand_page_io_req *req,
+					  u16 *column)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int shift;
+
+	if (nand->memorg.planes_per_lun < 2)
+		return;
+
+	/* The plane number is passed in MSB just above the column address */
+	shift = fls(nand->memorg.pagesize);
+	*column |= req->pos.plane << shift;
+}
+
+static int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val)
+{
+	struct spi_mem_op op = SPINAND_GET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	*val = *spinand->scratchbuf;
+	return 0;
+}
+
+static int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val)
+{
+	struct spi_mem_op op = SPINAND_SET_FEATURE_OP(reg,
+						      spinand->scratchbuf);
+
+	*spinand->scratchbuf = val;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_status(struct spinand_device *spinand, u8 *status)
+{
+	return spinand_read_reg_op(spinand, REG_STATUS, status);
+}
+
+static int spinand_get_cfg(struct spinand_device *spinand, u8 *cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	*cfg = spinand->cfg_cache[spinand->cur_target];
+	return 0;
+}
+
+static int spinand_set_cfg(struct spinand_device *spinand, u8 cfg)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(spinand->cur_target < 0 ||
+		    spinand->cur_target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cfg_cache[spinand->cur_target] == cfg)
+		return 0;
+
+	ret = spinand_write_reg_op(spinand, REG_CFG, cfg);
+	if (ret)
+		return ret;
+
+	spinand->cfg_cache[spinand->cur_target] = cfg;
+	return 0;
+}
+
+/**
+ * spinand_upd_cfg() - Update the configuration register
+ * @spinand: the spinand device
+ * @mask: the mask encoding the bits to update in the config reg
+ * @val: the new value to apply
+ *
+ * Update the configuration register.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val)
+{
+	int ret;
+	u8 cfg;
+
+	ret = spinand_get_cfg(spinand, &cfg);
+	if (ret)
+		return ret;
+
+	cfg &= ~mask;
+	cfg |= val;
+
+	return spinand_set_cfg(spinand, cfg);
+}
+
+/**
+ * spinand_select_target() - Select a specific NAND target/die
+ * @spinand: the spinand device
+ * @target: the target/die to select
+ *
+ * Select a new target/die. If chip only has one die, this function is a NOOP.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_select_target(struct spinand_device *spinand, unsigned int target)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	if (WARN_ON(target >= nand->memorg.ntargets))
+		return -EINVAL;
+
+	if (spinand->cur_target == target)
+		return 0;
+
+	if (nand->memorg.ntargets == 1) {
+		spinand->cur_target = target;
+		return 0;
+	}
+
+	ret = spinand->select_target(spinand, target);
+	if (ret)
+		return ret;
+
+	spinand->cur_target = target;
+	return 0;
+}
+
+static int spinand_init_cfg_cache(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct device *dev = &spinand->spimem->spi->dev;
+	unsigned int target;
+	int ret;
+
+	spinand->cfg_cache = devm_kcalloc(dev,
+					  nand->memorg.ntargets,
+					  sizeof(*spinand->cfg_cache),
+					  GFP_KERNEL);
+	if (!spinand->cfg_cache)
+		return -ENOMEM;
+
+	for (target = 0; target < nand->memorg.ntargets; target++) {
+		ret = spinand_select_target(spinand, target);
+		if (ret)
+			return ret;
+
+		/*
+		 * We use spinand_read_reg_op() instead of spinand_get_cfg()
+		 * here to bypass the config cache.
+		 */
+		ret = spinand_read_reg_op(spinand, REG_CFG,
+					  &spinand->cfg_cache[target]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int spinand_init_quad_enable(struct spinand_device *spinand)
+{
+	bool enable = false;
+
+	if (!(spinand->flags & SPINAND_HAS_QE_BIT))
+		return 0;
+
+	if (spinand->op_templates.read_cache->data.buswidth == 4 ||
+	    spinand->op_templates.write_cache->data.buswidth == 4 ||
+	    spinand->op_templates.update_cache->data.buswidth == 4)
+		enable = true;
+
+	return spinand_upd_cfg(spinand, CFG_QUAD_ENABLE,
+			       enable ? CFG_QUAD_ENABLE : 0);
+}
+
+static int spinand_ecc_enable(struct spinand_device *spinand,
+			      bool enable)
+{
+	return spinand_upd_cfg(spinand, CFG_ECC_ENABLE,
+			       enable ? CFG_ECC_ENABLE : 0);
+}
+
+static int spinand_write_enable_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_WR_EN_DIS_OP(true);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_load_page_op(struct spinand_device *spinand,
+				const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PAGE_READ_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_read_from_cache_op(struct spinand_device *spinand,
+				      const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.read_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	if (req->datalen) {
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.dataoffs = 0;
+		adjreq.databuf.in = spinand->databuf;
+		buf = spinand->databuf;
+		nbytes = adjreq.datalen;
+	}
+
+	if (req->ooblen) {
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		adjreq.oobbuf.in = spinand->oobbuf;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max RX data size. In this
+	 * case, just repeat the READ_CACHE operation after updating the
+	 * column.
+	 */
+	while (nbytes) {
+		op.data.buf.in = buf;
+		op.data.nbytes = nbytes;
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+	}
+
+	if (req->datalen)
+		memcpy(req->databuf.in, spinand->databuf + req->dataoffs,
+		       req->datalen);
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_get_databytes(mtd, req->oobbuf.in,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(req->oobbuf.in, spinand->oobbuf + req->ooboffs,
+			       req->ooblen);
+	}
+
+	return 0;
+}
+
+static int spinand_write_to_cache_op(struct spinand_device *spinand,
+				     const struct nand_page_io_req *req)
+{
+	struct spi_mem_op op = *spinand->op_templates.write_cache;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	struct mtd_info *mtd = nanddev_to_mtd(nand);
+	struct nand_page_io_req adjreq = *req;
+	unsigned int nbytes = 0;
+	void *buf = NULL;
+	u16 column = 0;
+	int ret;
+
+	memset(spinand->databuf, 0xff,
+	       nanddev_page_size(nand) +
+	       nanddev_per_page_oobsize(nand));
+
+	if (req->datalen) {
+		memcpy(spinand->databuf + req->dataoffs, req->databuf.out,
+		       req->datalen);
+		adjreq.dataoffs = 0;
+		adjreq.datalen = nanddev_page_size(nand);
+		adjreq.databuf.out = spinand->databuf;
+		nbytes = adjreq.datalen;
+		buf = spinand->databuf;
+	}
+
+	if (req->ooblen) {
+		if (req->mode == MTD_OPS_AUTO_OOB)
+			mtd_ooblayout_set_databytes(mtd, req->oobbuf.out,
+						    spinand->oobbuf,
+						    req->ooboffs,
+						    req->ooblen);
+		else
+			memcpy(spinand->oobbuf + req->ooboffs, req->oobbuf.out,
+			       req->ooblen);
+
+		adjreq.ooblen = nanddev_per_page_oobsize(nand);
+		adjreq.ooboffs = 0;
+		nbytes += nanddev_per_page_oobsize(nand);
+		if (!buf) {
+			buf = spinand->oobbuf;
+			column = nanddev_page_size(nand);
+		}
+	}
+
+	spinand_cache_op_adjust_colum(spinand, &adjreq, &column);
+
+	op = *spinand->op_templates.write_cache;
+	op.addr.val = column;
+
+	/*
+	 * Some controllers are limited in term of max TX data size. In this
+	 * case, split the operation into one LOAD CACHE and one or more
+	 * LOAD RANDOM CACHE.
+	 */
+	while (nbytes) {
+		op.data.buf.out = buf;
+		op.data.nbytes = nbytes;
+
+		ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		ret = spi_mem_exec_op(spinand->spimem, &op);
+		if (ret)
+			return ret;
+
+		buf += op.data.nbytes;
+		nbytes -= op.data.nbytes;
+		op.addr.val += op.data.nbytes;
+
+		/*
+		 * We need to use the RANDOM LOAD CACHE operation if there's
+		 * more than one iteration, because the LOAD operation resets
+		 * the cache to 0xff.
+		 */
+		if (nbytes) {
+			column = op.addr.val;
+			op = *spinand->op_templates.update_cache;
+			op.addr.val = column;
+		}
+	}
+
+	return 0;
+}
+
+static int spinand_program_op(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, &req->pos);
+	struct spi_mem_op op = SPINAND_PROG_EXEC_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_erase_op(struct spinand_device *spinand,
+			    const struct nand_pos *pos)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int row = nanddev_pos_to_row(nand, pos);
+	struct spi_mem_op op = SPINAND_BLK_ERASE_OP(row);
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int spinand_wait(struct spinand_device *spinand, u8 *s)
+{
+	unsigned long timeo =  jiffies + msecs_to_jiffies(400);
+	u8 status;
+	int ret;
+
+	do {
+		ret = spinand_read_status(spinand, &status);
+		if (ret)
+			return ret;
+
+		if (!(status & STATUS_BUSY))
+			goto out;
+	} while (time_before(jiffies, timeo));
+
+	/*
+	 * Extra read, just in case the STATUS_READY bit has changed
+	 * since our last check
+	 */
+	ret = spinand_read_status(spinand, &status);
+	if (ret)
+		return ret;
+
+out:
+	if (s)
+		*s = status;
+
+	return status & STATUS_BUSY ? -ETIMEDOUT : 0;
+}
+
+static int spinand_read_id_op(struct spinand_device *spinand, u8 *buf)
+{
+	struct spi_mem_op op = SPINAND_READID_OP(0, spinand->scratchbuf,
+						 SPINAND_MAX_ID_LEN);
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (!ret)
+		memcpy(buf, spinand->scratchbuf, SPINAND_MAX_ID_LEN);
+
+	return ret;
+}
+
+static int spinand_reset_op(struct spinand_device *spinand)
+{
+	struct spi_mem_op op = SPINAND_RESET_OP;
+	int ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	return spinand_wait(spinand, NULL);
+}
+
+static int spinand_lock_block(struct spinand_device *spinand, u8 lock)
+{
+	return spinand_write_reg_op(spinand, REG_BLOCK_LOCK, lock);
+}
+
+static int spinand_check_ecc_status(struct spinand_device *spinand, u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	if (spinand->eccinfo.get_status)
+		return spinand->eccinfo.get_status(spinand, status);
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * We have no way to know exactly how many bitflips have been
+		 * fixed, so let's return the maximum possible value so that
+		 * wear-leveling layers move the data immediately.
+		 */
+		return nand->eccreq.strength;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static int spinand_read_page(struct spinand_device *spinand,
+			     const struct nand_page_io_req *req,
+			     bool ecc_enabled)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_load_page_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (ret < 0)
+		return ret;
+
+	ret = spinand_read_from_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	if (!ecc_enabled)
+		return 0;
+
+	return spinand_check_ecc_status(spinand, status);
+}
+
+static int spinand_write_page(struct spinand_device *spinand,
+			      const struct nand_page_io_req *req)
+{
+	u8 status;
+	int ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_to_cache_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_program_op(spinand, req);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_PROG_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_read(struct mtd_info *mtd, loff_t from,
+			    struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	unsigned int max_bitflips = 0;
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	bool ecc_failed = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && spinand->eccinfo.ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, from, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_read_page(spinand, &iter.req, enable_ecc);
+		if (ret < 0 && ret != -EBADMSG)
+			break;
+
+		if (ret == -EBADMSG) {
+			ecc_failed = true;
+			mtd->ecc_stats.failed++;
+			ret = 0;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	if (ecc_failed && !ret)
+		ret = -EBADMSG;
+
+	return ret ? ret : max_bitflips;
+}
+
+static int spinand_mtd_write(struct mtd_info *mtd, loff_t to,
+			     struct mtd_oob_ops *ops)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_io_iter iter;
+	bool enable_ecc = false;
+	int ret = 0;
+
+	if (ops->mode != MTD_OPS_RAW && mtd->ooblayout)
+		enable_ecc = true;
+
+	mutex_lock(&spinand->lock);
+
+	nanddev_io_for_each_page(nand, to, ops, &iter) {
+		ret = spinand_select_target(spinand, iter.req.pos.target);
+		if (ret)
+			break;
+
+		ret = spinand_ecc_enable(spinand, enable_ecc);
+		if (ret)
+			break;
+
+		ret = spinand_write_page(spinand, &iter.req);
+		if (ret)
+			break;
+
+		ops->retlen += iter.req.datalen;
+		ops->oobretlen += iter.req.ooblen;
+	}
+
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static bool spinand_isbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooblen = 2,
+		.ooboffs = 0,
+		.oobbuf.in = spinand->oobbuf,
+		.mode = MTD_OPS_RAW,
+	};
+
+	memset(spinand->oobbuf, 0, 2);
+	spinand_select_target(spinand, pos->target);
+	spinand_read_page(spinand, &req, false);
+	if (spinand->oobbuf[0] != 0xff || spinand->oobbuf[1] != 0xff)
+		return true;
+
+	return false;
+}
+
+static int spinand_mtd_block_isbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_markbad(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_page_io_req req = {
+		.pos = *pos,
+		.ooboffs = 0,
+		.ooblen = 2,
+		.oobbuf.out = spinand->oobbuf,
+	};
+	int ret;
+
+	/* Erase block before marking it bad. */
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	spinand_erase_op(spinand, pos);
+
+	memset(spinand->oobbuf, 0, 2);
+	return spinand_write_page(spinand, &req);
+}
+
+static int spinand_mtd_block_markbad(struct mtd_info *mtd, loff_t offs)
+{
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_markbad(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_erase(struct nand_device *nand, const struct nand_pos *pos)
+{
+	struct spinand_device *spinand = nand_to_spinand(nand);
+	u8 status;
+	int ret;
+
+	ret = spinand_select_target(spinand, pos->target);
+	if (ret)
+		return ret;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_erase_op(spinand, pos);
+	if (ret)
+		return ret;
+
+	ret = spinand_wait(spinand, &status);
+	if (!ret && (status & STATUS_ERASE_FAILED))
+		ret = -EIO;
+
+	return ret;
+}
+
+static int spinand_mtd_erase(struct mtd_info *mtd,
+			     struct erase_info *einfo)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	int ret;
+
+	mutex_lock(&spinand->lock);
+	ret = nanddev_mtd_erase(mtd, einfo);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static int spinand_mtd_block_isreserved(struct mtd_info *mtd, loff_t offs)
+{
+	struct spinand_device *spinand = mtd_to_spinand(mtd);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	struct nand_pos pos;
+	int ret;
+
+	nanddev_offs_to_pos(nand, offs, &pos);
+	mutex_lock(&spinand->lock);
+	ret = nanddev_isreserved(nand, &pos);
+	mutex_unlock(&spinand->lock);
+
+	return ret;
+}
+
+static const struct nand_ops spinand_ops = {
+	.erase = spinand_erase,
+	.markbad = spinand_markbad,
+	.isbad = spinand_isbad,
+};
+
+static int spinand_manufacturer_detect(struct spinand_device *spinand)
+{
+	return -ENOTSUPP;
+}
+
+static int spinand_manufacturer_init(struct spinand_device *spinand)
+{
+	if (spinand->manufacturer->ops->init)
+		return spinand->manufacturer->ops->init(spinand);
+
+	return 0;
+}
+
+static void spinand_manufacturer_cleanup(struct spinand_device *spinand)
+{
+	/* Release manufacturer private data */
+	if (spinand->manufacturer->ops->cleanup)
+		return spinand->manufacturer->ops->cleanup(spinand);
+}
+
+static const struct spi_mem_op *
+spinand_select_op_variant(struct spinand_device *spinand,
+			  const struct spinand_op_variants *variants)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < variants->nops; i++) {
+		struct spi_mem_op op = variants->ops[i];
+		unsigned int nbytes;
+		int ret;
+
+		nbytes = nanddev_per_page_oobsize(nand) +
+			 nanddev_page_size(nand);
+
+		while (nbytes) {
+			op.data.nbytes = nbytes;
+			ret = spi_mem_adjust_op_size(spinand->spimem, &op);
+			if (ret)
+				break;
+
+			if (!spi_mem_supports_op(spinand->spimem, &op))
+				break;
+
+			nbytes -= op.data.nbytes;
+		}
+
+		if (!nbytes)
+			return &variants->ops[i];
+	}
+
+	return NULL;
+}
+
+/**
+ * spinand_match_and_init() - Try to find a match between a device ID and an
+ *			      entry in a spinand_info table
+ * @spinand: SPI NAND object
+ * @table: SPI NAND device description table
+ * @table_size: size of the device description table
+ *
+ * Should be used by SPI NAND manufacturer drivers when they want to find a
+ * match between a device ID retrieved through the READ_ID command and an
+ * entry in the SPI NAND description table. If a match is found, the spinand
+ * object will be initialized with information provided by the matching
+ * spinand_info entry.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int spinand_match_and_init(struct spinand_device *spinand,
+			   const struct spinand_info *table,
+			   unsigned int table_size, u8 devid)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	for (i = 0; i < table_size; i++) {
+		const struct spinand_info *info = &table[i];
+		const struct spi_mem_op *op;
+
+		if (devid != info->devid)
+			continue;
+
+		nand->memorg = table[i].memorg;
+		nand->eccreq = table[i].eccreq;
+		spinand->eccinfo = table[i].eccinfo;
+		spinand->flags = table[i].flags;
+		spinand->select_target = table[i].select_target;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.read_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.read_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.write_cache);
+		if (!op)
+			return -ENOTSUPP;
+
+		spinand->op_templates.write_cache = op;
+
+		op = spinand_select_op_variant(spinand,
+					       info->op_variants.update_cache);
+		spinand->op_templates.update_cache = op;
+
+		return 0;
+	}
+
+	return -ENOTSUPP;
+}
+
+static int spinand_detect(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct nand_device *nand = spinand_to_nand(spinand);
+	int ret;
+
+	ret = spinand_reset_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spinand_read_id_op(spinand, spinand->id.data);
+	if (ret)
+		return ret;
+
+	spinand->id.len = SPINAND_MAX_ID_LEN;
+
+	ret = spinand_manufacturer_detect(spinand);
+	if (ret) {
+		dev_err(dev, "unknown raw ID %*phN\n", SPINAND_MAX_ID_LEN,
+			spinand->id.data);
+		return ret;
+	}
+
+	if (nand->memorg.ntargets > 1 && !spinand->select_target) {
+		dev_err(dev,
+			"SPI NANDs with more than one die must implement ->select_target()\n");
+		return -EINVAL;
+	}
+
+	dev_info(&spinand->spimem->spi->dev,
+		 "%s SPI NAND was found.\n", spinand->manufacturer->name);
+	dev_info(&spinand->spimem->spi->dev,
+		 "%llu MiB, block size: %zu KiB, page size: %zu, OOB size: %u\n",
+		 nanddev_size(nand) >> 20, nanddev_eraseblock_size(nand) >> 10,
+		 nanddev_page_size(nand), nanddev_per_page_oobsize(nand));
+
+	return 0;
+}
+
+static int spinand_noecc_ooblayout_ecc(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int spinand_noecc_ooblayout_free(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops spinand_noecc_ooblayout = {
+	.ecc = spinand_noecc_ooblayout_ecc,
+	.free = spinand_noecc_ooblayout_free,
+};
+
+static int spinand_init(struct spinand_device *spinand)
+{
+	struct device *dev = &spinand->spimem->spi->dev;
+	struct mtd_info *mtd = spinand_to_mtd(spinand);
+	struct nand_device *nand = mtd_to_nanddev(mtd);
+	int ret, i;
+
+	/*
+	 * We need a scratch buffer because the spi_mem interface requires that
+	 * buf passed in spi_mem_op->data.buf be DMA-able.
+	 */
+	spinand->scratchbuf = kzalloc(SPINAND_MAX_ID_LEN, GFP_KERNEL);
+	if (!spinand->scratchbuf)
+		return -ENOMEM;
+
+	ret = spinand_detect(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	/*
+	 * Use kzalloc() instead of devm_kzalloc() here, because some drivers
+	 * may use this buffer for DMA access.
+	 * Memory allocated by devm_ does not guarantee DMA-safe alignment.
+	 */
+	spinand->databuf = kzalloc(nanddev_page_size(nand) +
+			       nanddev_per_page_oobsize(nand),
+			       GFP_KERNEL);
+	if (!spinand->databuf) {
+		ret = -ENOMEM;
+		goto err_free_bufs;
+	}
+
+	spinand->oobbuf = spinand->databuf + nanddev_page_size(nand);
+
+	ret = spinand_init_cfg_cache(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_init_quad_enable(spinand);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_upd_cfg(spinand, CFG_OTP_ENABLE, 0);
+	if (ret)
+		goto err_free_bufs;
+
+	ret = spinand_manufacturer_init(spinand);
+	if (ret) {
+		dev_err(dev,
+			"Failed to initialize the SPI NAND chip (err = %d)\n",
+			ret);
+		goto err_free_bufs;
+	}
+
+	/* After power up, all blocks are locked, so unlock them here. */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		ret = spinand_select_target(spinand, i);
+		if (ret)
+			goto err_free_bufs;
+
+		ret = spinand_lock_block(spinand, BL_ALL_UNLOCKED);
+		if (ret)
+			goto err_free_bufs;
+	}
+
+	ret = nanddev_init(nand, &spinand_ops, THIS_MODULE);
+	if (ret)
+		goto err_manuf_cleanup;
+
+	/*
+	 * Right now, we don't support ECC, so let the whole oob
+	 * area is available for user.
+	 */
+	mtd->_read_oob = spinand_mtd_read;
+	mtd->_write_oob = spinand_mtd_write;
+	mtd->_block_isbad = spinand_mtd_block_isbad;
+	mtd->_block_markbad = spinand_mtd_block_markbad;
+	mtd->_block_isreserved = spinand_mtd_block_isreserved;
+	mtd->_erase = spinand_mtd_erase;
+
+	if (spinand->eccinfo.ooblayout)
+		mtd_set_ooblayout(mtd, spinand->eccinfo.ooblayout);
+	else
+		mtd_set_ooblayout(mtd, &spinand_noecc_ooblayout);
+
+	ret = mtd_ooblayout_count_freebytes(mtd);
+	if (ret < 0)
+		goto err_cleanup_nanddev;
+
+	mtd->oobavail = ret;
+
+	return 0;
+
+err_cleanup_nanddev:
+	nanddev_cleanup(nand);
+
+err_manuf_cleanup:
+	spinand_manufacturer_cleanup(spinand);
+
+err_free_bufs:
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+	return ret;
+}
+
+static void spinand_cleanup(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+
+	nanddev_cleanup(nand);
+	spinand_manufacturer_cleanup(spinand);
+	kfree(spinand->databuf);
+	kfree(spinand->scratchbuf);
+}
+
+static int spinand_probe(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = devm_kzalloc(&mem->spi->dev, sizeof(*spinand),
+			       GFP_KERNEL);
+	if (!spinand)
+		return -ENOMEM;
+
+	spinand->spimem = mem;
+	spi_mem_set_drvdata(mem, spinand);
+	spinand_set_of_node(spinand, mem->spi->dev.of_node);
+	mutex_init(&spinand->lock);
+	mtd = spinand_to_mtd(spinand);
+	mtd->dev.parent = &mem->spi->dev;
+
+	ret = spinand_init(spinand);
+	if (ret)
+		return ret;
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		goto err_spinand_cleanup;
+
+	return 0;
+
+err_spinand_cleanup:
+	spinand_cleanup(spinand);
+
+	return ret;
+}
+
+static int spinand_remove(struct spi_mem *mem)
+{
+	struct spinand_device *spinand;
+	struct mtd_info *mtd;
+	int ret;
+
+	spinand = spi_mem_get_drvdata(mem);
+	mtd = spinand_to_mtd(spinand);
+
+	ret = mtd_device_unregister(mtd);
+	if (ret)
+		return ret;
+
+	spinand_cleanup(spinand);
+
+	return 0;
+}
+
+static const struct spi_device_id spinand_ids[] = {
+	{ .name = "spi-nand" },
+	{ /* sentinel */ },
+};
+
+#ifdef CONFIG_OF
+static const struct of_device_id spinand_of_ids[] = {
+	{ .compatible = "spi-nand" },
+	{ /* sentinel */ },
+};
+#endif
+
+static struct spi_mem_driver spinand_drv = {
+	.spidrv = {
+		.id_table = spinand_ids,
+		.driver = {
+			.name = "spi-nand",
+			.of_match_table = of_match_ptr(spinand_of_ids),
+		},
+	},
+	.probe = spinand_probe,
+	.remove = spinand_remove,
+};
+module_spi_mem_driver(spinand_drv);
+
+MODULE_DESCRIPTION("SPI NAND framework");
+MODULE_AUTHOR("Peter Pan<peterpandong@micron.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
new file mode 100644
index 000000000000..d3efe62dc9de
--- /dev/null
+++ b/include/linux/mtd/spinand.h
@@ -0,0 +1,416 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2017 Micron Technology, Inc.
+ *
+ *  Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ */
+#ifndef __LINUX_MTD_SPINAND_H
+#define __LINUX_MTD_SPINAND_H
+
+#include <linux/mutex.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/nand.h>
+#include <linux/spi/spi.h>
+#include <linux/spi/spi-mem.h>
+
+/**
+ * Standard SPI NAND flash operations
+ */
+
+#define SPINAND_RESET_OP						\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xff, 1),				\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_WR_EN_DIS_OP(enable)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD((enable) ? 0x06 : 0x04, 1),		\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_READID_OP(ndummy, buf, len)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x9f, 1),				\
+		   SPI_MEM_OP_NO_ADDR,					\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+
+#define SPINAND_SET_FEATURE_OP(reg, valptr)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x1f, 1),				\
+		   SPI_MEM_OP_ADDR(1, reg, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(1, valptr, 1))
+
+#define SPINAND_GET_FEATURE_OP(reg, valptr)				\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0f, 1),				\
+		   SPI_MEM_OP_ADDR(1, reg, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_IN(1, valptr, 1))
+
+#define SPINAND_BLK_ERASE_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xd8, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PAGE_READ_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x13, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 2),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len)	\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 4),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+
+#define SPINAND_PROG_EXEC_OP(addr)					\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_NO_DATA)
+
+#define SPINAND_PROG_LOAD(reset, addr, buf, len)			\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x02 : 0x84, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 1))
+
+#define SPINAND_PROG_LOAD_X4(reset, addr, buf, len)			\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x32 : 0x34, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 4))
+
+/**
+ * Standard SPI NAND flash commands
+ */
+#define SPINAND_CMD_PROG_LOAD_X4		0x32
+#define SPINAND_CMD_PROG_LOAD_RDM_DATA_X4	0x34
+
+/* feature register */
+#define REG_BLOCK_LOCK		0xa0
+#define BL_ALL_UNLOCKED		0x00
+
+/* configuration register */
+#define REG_CFG			0xb0
+#define CFG_OTP_ENABLE		BIT(6)
+#define CFG_ECC_ENABLE		BIT(4)
+#define CFG_QUAD_ENABLE		BIT(0)
+
+/* status register */
+#define REG_STATUS		0xc0
+#define STATUS_BUSY		BIT(0)
+#define STATUS_ERASE_FAILED	BIT(2)
+#define STATUS_PROG_FAILED	BIT(3)
+#define STATUS_ECC_MASK		GENMASK(5, 4)
+#define STATUS_ECC_NO_BITFLIPS	(0 << 4)
+#define STATUS_ECC_HAS_BITFLIPS	(1 << 4)
+#define STATUS_ECC_UNCOR_ERROR	(2 << 4)
+
+struct spinand_op;
+struct spinand_device;
+
+#define SPINAND_MAX_ID_LEN	4
+
+/**
+ * struct spinand_id - SPI NAND id structure
+ * @data: buffer containing the id bytes. Currently 4 bytes large, but can
+ *	  be extended if required
+ * @len: ID length
+ *
+ * struct_spinand_id->data contains all bytes returned after a READ_ID command,
+ * including dummy bytes if the chip does not emit ID bytes right after the
+ * READ_ID command. The responsibility to extract real ID bytes is left to
+ * struct_manufacurer_ops->detect().
+ */
+struct spinand_id {
+	u8 data[SPINAND_MAX_ID_LEN];
+	int len;
+};
+
+/**
+ * struct manufacurer_ops - SPI NAND manufacturer specific operations
+ * @detect: detect a SPI NAND device. Every time a SPI NAND device is probed
+ *	    the core calls the struct_manufacurer_ops->detect() hook of each
+ *	    registered manufacturer until one of them return 1. Note that
+ *	    the first thing to check in this hook is that the manufacturer ID
+ *	    in struct_spinand_device->id matches the manufacturer whose
+ *	    ->detect() hook has been called. Should return 1 if there's a
+ *	    match, 0 if the manufacturer ID does not match and a negative
+ *	    error code otherwise. When true is returned, the core assumes
+ *	    that properties of the NAND chip (spinand->base.memorg and
+ *	    spinand->base.eccreq) have been filled
+ * @init: initialize a SPI NAND device
+ * @cleanup: cleanup a SPI NAND device
+ *
+ * Each SPI NAND manufacturer driver should implement this interface so that
+ * NAND chips coming from this vendor can be detected and initialized properly.
+ */
+struct spinand_manufacturer_ops {
+	int (*detect)(struct spinand_device *spinand);
+	int (*init)(struct spinand_device *spinand);
+	void (*cleanup)(struct spinand_device *spinand);
+};
+
+/**
+ * struct spinand_manufacturer - SPI NAND manufacturer instance
+ * @id: manufacturer ID
+ * @name: manufacturer name
+ * @ops: manufacturer operations
+ */
+struct spinand_manufacturer {
+	u8 id;
+	char *name;
+	const struct spinand_manufacturer_ops *ops;
+};
+
+/**
+ * struct spinand_op_variants - SPI NAND operation variants
+ * @ops: the list of variants for a given operation
+ * @nops: the number of variants
+ *
+ * Some operations like read-from-cache/write-to-cache have several variants
+ * depending on the number of IO lines you use to transfer data or address
+ * cycles. This structure is a way to describe the different variants supported
+ * by a chip and let the core pick the best one based on the SPI mem controller
+ * capabilities.
+ */
+struct spinand_op_variants {
+	const struct spi_mem_op *ops;
+	unsigned int nops;
+};
+
+#define SPINAND_OP_VARIANTS(name, ...)					\
+	const struct spinand_op_variants name = {			\
+		.ops = (struct spi_mem_op[]) { __VA_ARGS__ },		\
+		.nops = sizeof((struct spi_mem_op[]){ __VA_ARGS__ }) /	\
+			sizeof(struct spi_mem_op),			\
+	}
+
+/**
+ * spinand_ecc_info - description of the on-die ECC implemented by a SPI NAND
+ *		      chip
+ * @get_status: get the ECC status. Should return a positive number encoding
+ *		the number of corrected bitflips if correction was possible or
+ *		-EBADMSG if there are uncorrectable errors. I can also return
+ *		other negative error codes if the error is not caused by
+ *		uncorrectable bitflips
+ * @ooblayout: the OOB layout used by the on-die ECC implementation
+ */
+struct spinand_ecc_info {
+	int (*get_status)(struct spinand_device *spinand, u8 status);
+	const struct mtd_ooblayout_ops *ooblayout;
+};
+
+#define SPINAND_HAS_QE_BIT		BIT(0)
+
+/**
+ * struct spinand_info - Structure used to describe SPI NAND chips
+ * @model: model name
+ * @devid: device ID
+ * @flags: OR-ing of the SPINAND_XXX flags
+ * @memorg: memory organization
+ * @eccreq: ECC requirements
+ * @eccinfo: on-die ECC info
+ * @op_variants: operations variants
+ * @op_variants.read_cache: variants of the read-cache operation
+ * @op_variants.write_cache: variants of the write-cache operation
+ * @op_variants.update_cache: variants of the update-cache operation
+ * @select_target: function used to select a target/die. Required only for
+ *		   multi-die chips
+ *
+ * Each SPI NAND manufacturer driver should have a spinand_info table
+ * describing all the chips supported by the driver.
+ */
+struct spinand_info {
+	const char *model;
+	u8 devid;
+	u32 flags;
+	struct nand_memory_organization memorg;
+	struct nand_ecc_req eccreq;
+	struct spinand_ecc_info eccinfo;
+	struct {
+		const struct spinand_op_variants *read_cache;
+		const struct spinand_op_variants *write_cache;
+		const struct spinand_op_variants *update_cache;
+	} op_variants;
+	int (*select_target)(struct spinand_device *spinand,
+			     unsigned int target);
+};
+
+#define SPINAND_INFO_OP_VARIANTS(__read, __write, __update)		\
+	{								\
+		.read_cache = __read,					\
+		.write_cache = __write,					\
+		.update_cache = __update,				\
+	}
+
+#define SPINAND_ECCINFO(__ooblayout, __get_status)			\
+	.eccinfo = {							\
+		.ooblayout = __ooblayout,				\
+		.get_status = __get_status,				\
+	}
+
+#define SPINAND_SELECT_TARGET(__func)					\
+	.select_target = __func,
+
+#define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants,	\
+		     __flags, ...)					\
+	{								\
+		.model = __model,					\
+		.devid = __id,						\
+		.memorg = __memorg,					\
+		.eccreq = __eccreq,					\
+		.op_variants = __op_variants,				\
+		.flags = __flags,					\
+		__VA_ARGS__						\
+	}
+
+/**
+ * struct spinand_device - SPI NAND device instance
+ * @base: NAND device instance
+ * @spimem: pointer to the SPI mem object
+ * @lock: lock used to serialize accesses to the NAND
+ * @id: NAND ID as returned by READ_ID
+ * @flags: NAND flags
+ * @op_templates: various SPI mem op templates
+ * @op_templates.read_cache: read cache op template
+ * @op_templates.write_cache: write cache op template
+ * @op_templates.update_cache: update cache op template
+ * @select_target: select a specific target/die. Usually called before sending
+ *		   a command addressing a page or an eraseblock embedded in
+ *		   this die. Only required if your chip exposes several dies
+ * @cur_target: currently selected target/die
+ * @eccinfo: on-die ECC information
+ * @cfg_cache: config register cache. One entry per die
+ * @databuf: bounce buffer for data
+ * @oobbuf: bounce buffer for OOB data
+ * @scratchbuf: buffer used for everything but page accesses. This is needed
+ *		because the spi-mem interface explicitly requests that buffers
+ *		passed in spi_mem_op be DMA-able, so we can't based the bufs on
+ *		the stack
+ * @manufacturer: SPI NAND manufacturer information
+ * @priv: manufacturer private data
+ */
+struct spinand_device {
+	struct nand_device base;
+	struct spi_mem *spimem;
+	struct mutex lock;
+	struct spinand_id id;
+	u32 flags;
+
+	struct {
+		const struct spi_mem_op *read_cache;
+		const struct spi_mem_op *write_cache;
+		const struct spi_mem_op *update_cache;
+	} op_templates;
+
+	int (*select_target)(struct spinand_device *spinand,
+			     unsigned int target);
+	unsigned int cur_target;
+
+	struct spinand_ecc_info eccinfo;
+
+	u8 *cfg_cache;
+	u8 *databuf;
+	u8 *oobbuf;
+	u8 *scratchbuf;
+	const struct spinand_manufacturer *manufacturer;
+	void *priv;
+};
+
+/**
+ * mtd_to_spinand() - Get the SPI NAND device attached to an MTD instance
+ * @mtd: MTD instance
+ *
+ * Return: the SPI NAND device attached to @mtd.
+ */
+static inline struct spinand_device *mtd_to_spinand(struct mtd_info *mtd)
+{
+	return container_of(mtd_to_nanddev(mtd), struct spinand_device, base);
+}
+
+/**
+ * spinand_to_mtd() - Get the MTD device embedded in a SPI NAND device
+ * @spinand: SPI NAND device
+ *
+ * Return: the MTD device embedded in @spinand.
+ */
+static inline struct mtd_info *spinand_to_mtd(struct spinand_device *spinand)
+{
+	return nanddev_to_mtd(&spinand->base);
+}
+
+/**
+ * nand_to_spinand() - Get the SPI NAND device embedding an NAND object
+ * @nand: NAND object
+ *
+ * Return: the SPI NAND device embedding @nand.
+ */
+static inline struct spinand_device *nand_to_spinand(struct nand_device *nand)
+{
+	return container_of(nand, struct spinand_device, base);
+}
+
+/**
+ * spinand_to_nand() - Get the NAND device embedded in a SPI NAND object
+ * @spinand: SPI NAND device
+ *
+ * Return: the NAND device embedded in @spinand.
+ */
+static inline struct nand_device *
+spinand_to_nand(struct spinand_device *spinand)
+{
+	return &spinand->base;
+}
+
+/**
+ * spinand_set_of_node - Attach a DT node to a SPI NAND device
+ * @spinand: SPI NAND device
+ * @np: DT node
+ *
+ * Attach a DT node to a SPI NAND device.
+ */
+static inline void spinand_set_of_node(struct spinand_device *spinand,
+				       struct device_node *np)
+{
+	nanddev_set_of_node(&spinand->base, np);
+}
+
+int spinand_match_and_init(struct spinand_device *dev,
+			   const struct spinand_info *table,
+			   unsigned int table_size, u8 devid);
+
+int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val);
+int spinand_select_target(struct spinand_device *spinand, unsigned int target);
+
+#endif /* __LINUX_MTD_SPINAND_H */
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index bb4bd15ae1f6..4fa34a227a0f 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -3,7 +3,9 @@
  * Copyright (C) 2018 Exceet Electronics GmbH
  * Copyright (C) 2018 Bootlin
  *
- * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ * Author:
+ *	Peter Pan <peterpandong@micron.com>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
  */
 
 #ifndef __LINUX_SPI_MEM_H
-- 
cgit v1.2.3


From 5ef5640a27775f533c8c6ad85e06db4f37ead9c0 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 22 Jun 2018 14:28:24 +0200
Subject: dt-bindings: Add bindings for SPI NAND devices

Add bindings for SPI NAND chips.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/spi-nand.txt | 5 +++++
 1 file changed, 5 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mtd/spi-nand.txt

diff --git a/Documentation/devicetree/bindings/mtd/spi-nand.txt b/Documentation/devicetree/bindings/mtd/spi-nand.txt
new file mode 100644
index 000000000000..8b51f3b6d55c
--- /dev/null
+++ b/Documentation/devicetree/bindings/mtd/spi-nand.txt
@@ -0,0 +1,5 @@
+SPI NAND flash
+
+Required properties:
+- compatible: should be "spi-nand"
+- reg: should encode the chip-select line used to access the NAND chip
-- 
cgit v1.2.3


From a508e8875e135d7a1df26d8131b5443cb07005ff Mon Sep 17 00:00:00 2001
From: Peter Pan <peterpandong@micron.com>
Date: Fri, 22 Jun 2018 14:28:25 +0200
Subject: mtd: spinand: Add initial support for Micron MT29F2G01ABAGD

Add a basic driver for Micron SPI NANDs. Only one device is supported
right now, but the driver will be extended to support more devices
afterwards.

Signed-off-by: Peter Pan <peterpandong@micron.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/Makefile |   2 +-
 drivers/mtd/nand/spi/core.c   |  17 ++++++
 drivers/mtd/nand/spi/micron.c | 133 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spinand.h   |   3 +
 4 files changed, 154 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mtd/nand/spi/micron.c

diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
index 2c473b765027..a1df25398f20 100644
--- a/drivers/mtd/nand/spi/Makefile
+++ b/drivers/mtd/nand/spi/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
-spinand-objs := core.o
+spinand-objs := core.o micron.o
 obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 4efbeb0d85b4..9cc502d7e745 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -763,8 +763,25 @@ static const struct nand_ops spinand_ops = {
 	.isbad = spinand_isbad,
 };
 
+static const struct spinand_manufacturer *spinand_manufacturers[] = {
+	&micron_spinand_manufacturer,
+};
+
 static int spinand_manufacturer_detect(struct spinand_device *spinand)
 {
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(spinand_manufacturers); i++) {
+		ret = spinand_manufacturers[i]->ops->detect(spinand);
+		if (ret > 0) {
+			spinand->manufacturer = spinand_manufacturers[i];
+			return 0;
+		} else if (ret < 0) {
+			return ret;
+		}
+	}
+
 	return -ENOTSUPP;
 }
 
diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c
new file mode 100644
index 000000000000..9c4381d6847b
--- /dev/null
+++ b/drivers/mtd/nand/spi/micron.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2017 Micron Technology, Inc.
+ *
+ * Authors:
+ *	Peter Pan <peterpandong@micron.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MICRON		0x2c
+
+#define MICRON_STATUS_ECC_MASK		GENMASK(7, 4)
+#define MICRON_STATUS_ECC_NO_BITFLIPS	(0 << 4)
+#define MICRON_STATUS_ECC_1TO3_BITFLIPS	(1 << 4)
+#define MICRON_STATUS_ECC_4TO6_BITFLIPS	(3 << 4)
+#define MICRON_STATUS_ECC_7TO8_BITFLIPS	(5 << 4)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mt29f2g01abagd_ooblayout_ecc(struct mtd_info *mtd, int section,
+					struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 64;
+	region->length = 64;
+
+	return 0;
+}
+
+static int mt29f2g01abagd_ooblayout_free(struct mtd_info *mtd, int section,
+					 struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	/* Reserve 2 bytes for the BBM. */
+	region->offset = 2;
+	region->length = 62;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mt29f2g01abagd_ooblayout = {
+	.ecc = mt29f2g01abagd_ooblayout_ecc,
+	.free = mt29f2g01abagd_ooblayout_free,
+};
+
+static int mt29f2g01abagd_ecc_get_status(struct spinand_device *spinand,
+					 u8 status)
+{
+	switch (status & MICRON_STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case MICRON_STATUS_ECC_1TO3_BITFLIPS:
+		return 3;
+
+	case MICRON_STATUS_ECC_4TO6_BITFLIPS:
+		return 6;
+
+	case MICRON_STATUS_ECC_7TO8_BITFLIPS:
+		return 8;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info micron_spinand_table[] = {
+	SPINAND_INFO("MT29F2G01ABAGD", 0x24,
+		     NAND_MEMORG(1, 2048, 128, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(8, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&mt29f2g01abagd_ooblayout,
+				     mt29f2g01abagd_ecc_get_status)),
+};
+
+static int micron_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Micron SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_MICRON)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, micron_spinand_table,
+				     ARRAY_SIZE(micron_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops micron_spinand_manuf_ops = {
+	.detect = micron_spinand_detect,
+};
+
+const struct spinand_manufacturer micron_spinand_manufacturer = {
+	.id = SPINAND_MFR_MICRON,
+	.name = "Micron",
+	.ops = &micron_spinand_manuf_ops,
+};
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index d3efe62dc9de..717b272940f1 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -193,6 +193,9 @@ struct spinand_manufacturer {
 	const struct spinand_manufacturer_ops *ops;
 };
 
+/* SPI NAND manufacturers */
+extern const struct spinand_manufacturer micron_spinand_manufacturer;
+
 /**
  * struct spinand_op_variants - SPI NAND operation variants
  * @ops: the list of variants for a given operation
-- 
cgit v1.2.3


From 1075492bb9e26312bc8ddeec1a93e2de5f9c76b4 Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@exceet.de>
Date: Fri, 22 Jun 2018 14:28:26 +0200
Subject: mtd: spinand: Add initial support for Winbond W25M02GV

Add support for the W25M02GV chip.

Signed-off-by: Frieder Schrempf <frieder.schrempf@exceet.de>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/Makefile  |   2 +-
 drivers/mtd/nand/spi/core.c    |   1 +
 drivers/mtd/nand/spi/winbond.c | 141 +++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spinand.h    |   1 +
 4 files changed, 144 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mtd/nand/spi/winbond.c

diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
index a1df25398f20..100008d202ed 100644
--- a/drivers/mtd/nand/spi/Makefile
+++ b/drivers/mtd/nand/spi/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
-spinand-objs := core.o micron.o
+spinand-objs := core.o micron.o winbond.o
 obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 9cc502d7e745..4803a6bfe8ec 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -765,6 +765,7 @@ static const struct nand_ops spinand_ops = {
 
 static const struct spinand_manufacturer *spinand_manufacturers[] = {
 	&micron_spinand_manufacturer,
+	&winbond_spinand_manufacturer,
 };
 
 static int spinand_manufacturer_detect(struct spinand_device *spinand)
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
new file mode 100644
index 000000000000..67baa1b32c00
--- /dev/null
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017 exceet electronics GmbH
+ *
+ * Authors:
+ *	Frieder Schrempf <frieder.schrempf@exceet.de>
+ *	Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_WINBOND		0xEF
+
+#define WINBOND_CFG_BUF_READ		BIT(3)
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int w25m02gv_ooblayout_ecc(struct mtd_info *mtd, int section,
+				  struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 8;
+	region->length = 8;
+
+	return 0;
+}
+
+static int w25m02gv_ooblayout_free(struct mtd_info *mtd, int section,
+				   struct mtd_oob_region *region)
+{
+	if (section > 3)
+		return -ERANGE;
+
+	region->offset = (16 * section) + 2;
+	region->length = 6;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops w25m02gv_ooblayout = {
+	.ecc = w25m02gv_ooblayout_ecc,
+	.free = w25m02gv_ooblayout_free,
+};
+
+static int w25m02gv_select_target(struct spinand_device *spinand,
+				  unsigned int target)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0xc2, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_NO_DUMMY,
+					  SPI_MEM_OP_DATA_OUT(1,
+							spinand->scratchbuf,
+							1));
+
+	*spinand->scratchbuf = target;
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static const struct spinand_info winbond_spinand_table[] = {
+	SPINAND_INFO("W25M02GV", 0xAB,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 2),
+		     NAND_ECCREQ(1, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     0,
+		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL),
+		     SPINAND_SELECT_TARGET(w25m02gv_select_target)),
+};
+
+/**
+ * winbond_spinand_detect - initialize device related part in spinand_device
+ * struct if it is a Winbond device.
+ * @spinand: SPI NAND device structure
+ */
+static int winbond_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Winbond SPI NAND read ID need a dummy byte,
+	 * so the first byte in raw_id is dummy.
+	 */
+	if (id[1] != SPINAND_MFR_WINBOND)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, winbond_spinand_table,
+				     ARRAY_SIZE(winbond_spinand_table), id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static int winbond_spinand_init(struct spinand_device *spinand)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	unsigned int i;
+
+	/*
+	 * Make sure all dies are in buffer read mode and not continuous read
+	 * mode.
+	 */
+	for (i = 0; i < nand->memorg.ntargets; i++) {
+		spinand_select_target(spinand, i);
+		spinand_upd_cfg(spinand, WINBOND_CFG_BUF_READ,
+				WINBOND_CFG_BUF_READ);
+	}
+
+	return 0;
+}
+
+static const struct spinand_manufacturer_ops winbond_spinand_manuf_ops = {
+	.detect = winbond_spinand_detect,
+	.init = winbond_spinand_init,
+};
+
+const struct spinand_manufacturer winbond_spinand_manufacturer = {
+	.id = SPINAND_MFR_WINBOND,
+	.name = "Winbond",
+	.ops = &winbond_spinand_manuf_ops,
+};
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 717b272940f1..f0f16b9029e7 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -195,6 +195,7 @@ struct spinand_manufacturer {
 
 /* SPI NAND manufacturers */
 extern const struct spinand_manufacturer micron_spinand_manufacturer;
+extern const struct spinand_manufacturer winbond_spinand_manufacturer;
 
 /**
  * struct spinand_op_variants - SPI NAND operation variants
-- 
cgit v1.2.3


From b02308af05e62c7d995f4fc75b0bc2ae3c3026f7 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 22 Jun 2018 14:28:27 +0200
Subject: mtd: spinand: Add initial support for the MX35LF1GE4AB chip

Add minimal support for the MX35LF1GE4AB SPI NAND chip.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/Makefile   |   2 +-
 drivers/mtd/nand/spi/core.c     |   1 +
 drivers/mtd/nand/spi/macronix.c | 136 ++++++++++++++++++++++++++++++++++++++++
 include/linux/mtd/spinand.h     |   1 +
 4 files changed, 139 insertions(+), 1 deletion(-)
 create mode 100644 drivers/mtd/nand/spi/macronix.c

diff --git a/drivers/mtd/nand/spi/Makefile b/drivers/mtd/nand/spi/Makefile
index 100008d202ed..b74e074b363a 100644
--- a/drivers/mtd/nand/spi/Makefile
+++ b/drivers/mtd/nand/spi/Makefile
@@ -1,3 +1,3 @@
 # SPDX-License-Identifier: GPL-2.0
-spinand-objs := core.o micron.o winbond.o
+spinand-objs := core.o macronix.o micron.o winbond.o
 obj-$(CONFIG_MTD_SPI_NAND) += spinand.o
diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 4803a6bfe8ec..30f83649c481 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -764,6 +764,7 @@ static const struct nand_ops spinand_ops = {
 };
 
 static const struct spinand_manufacturer *spinand_manufacturers[] = {
+	&macronix_spinand_manufacturer,
 	&micron_spinand_manufacturer,
 	&winbond_spinand_manufacturer,
 };
diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c
new file mode 100644
index 000000000000..8ba3489d332a
--- /dev/null
+++ b/drivers/mtd/nand/spi/macronix.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Macronix
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/mtd/spinand.h>
+
+#define SPINAND_MFR_MACRONIX		0xC2
+
+static SPINAND_OP_VARIANTS(read_cache_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_X4_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_X2_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(true, 0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_OP(false, 0, 1, NULL, 0));
+
+static SPINAND_OP_VARIANTS(write_cache_variants,
+		SPINAND_PROG_LOAD_X4(true, 0, NULL, 0),
+		SPINAND_PROG_LOAD(true, 0, NULL, 0));
+
+static SPINAND_OP_VARIANTS(update_cache_variants,
+		SPINAND_PROG_LOAD_X4(false, 0, NULL, 0),
+		SPINAND_PROG_LOAD(false, 0, NULL, 0));
+
+static int mx35lfxge4ab_ooblayout_ecc(struct mtd_info *mtd, int section,
+				      struct mtd_oob_region *region)
+{
+	return -ERANGE;
+}
+
+static int mx35lfxge4ab_ooblayout_free(struct mtd_info *mtd, int section,
+				       struct mtd_oob_region *region)
+{
+	if (section)
+		return -ERANGE;
+
+	region->offset = 2;
+	region->length = mtd->oobsize - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops mx35lfxge4ab_ooblayout = {
+	.ecc = mx35lfxge4ab_ooblayout_ecc,
+	.free = mx35lfxge4ab_ooblayout_free,
+};
+
+static int mx35lf1ge4ab_get_eccsr(struct spinand_device *spinand, u8 *eccsr)
+{
+	struct spi_mem_op op = SPI_MEM_OP(SPI_MEM_OP_CMD(0x7c, 1),
+					  SPI_MEM_OP_NO_ADDR,
+					  SPI_MEM_OP_DUMMY(1, 1),
+					  SPI_MEM_OP_DATA_IN(1, eccsr, 1));
+
+	return spi_mem_exec_op(spinand->spimem, &op);
+}
+
+static int mx35lf1ge4ab_ecc_get_status(struct spinand_device *spinand,
+				       u8 status)
+{
+	struct nand_device *nand = spinand_to_nand(spinand);
+	u8 eccsr;
+
+	switch (status & STATUS_ECC_MASK) {
+	case STATUS_ECC_NO_BITFLIPS:
+		return 0;
+
+	case STATUS_ECC_UNCOR_ERROR:
+		return -EBADMSG;
+
+	case STATUS_ECC_HAS_BITFLIPS:
+		/*
+		 * Let's try to retrieve the real maximum number of bitflips
+		 * in order to avoid forcing the wear-leveling layer to move
+		 * data around if it's not necessary.
+		 */
+		if (mx35lf1ge4ab_get_eccsr(spinand, &eccsr))
+			return nand->eccreq.strength;
+
+		if (WARN_ON(eccsr > nand->eccreq.strength || !eccsr))
+			return nand->eccreq.strength;
+
+		return eccsr;
+
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct spinand_info macronix_spinand_table[] = {
+	SPINAND_INFO("MX35LF1GE4AB", 0x12,
+		     NAND_MEMORG(1, 2048, 64, 64, 1024, 1, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout,
+				     mx35lf1ge4ab_ecc_get_status)),
+};
+
+static int macronix_spinand_detect(struct spinand_device *spinand)
+{
+	u8 *id = spinand->id.data;
+	int ret;
+
+	/*
+	 * Macronix SPI NAND read ID needs a dummy byte, so the first byte in
+	 * raw_id is garbage.
+	 */
+	if (id[1] != SPINAND_MFR_MACRONIX)
+		return 0;
+
+	ret = spinand_match_and_init(spinand, macronix_spinand_table,
+				     ARRAY_SIZE(macronix_spinand_table),
+				     id[2]);
+	if (ret)
+		return ret;
+
+	return 1;
+}
+
+static const struct spinand_manufacturer_ops macronix_spinand_manuf_ops = {
+	.detect = macronix_spinand_detect,
+};
+
+const struct spinand_manufacturer macronix_spinand_manufacturer = {
+	.id = SPINAND_MFR_MACRONIX,
+	.name = "Macronix",
+	.ops = &macronix_spinand_manuf_ops,
+};
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index f0f16b9029e7..088ff96c3eb6 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -194,6 +194,7 @@ struct spinand_manufacturer {
 };
 
 /* SPI NAND manufacturers */
+extern const struct spinand_manufacturer macronix_spinand_manufacturer;
 extern const struct spinand_manufacturer micron_spinand_manufacturer;
 extern const struct spinand_manufacturer winbond_spinand_manufacturer;
 
-- 
cgit v1.2.3


From 3dfa025f890c4568adc9ba06ecc0da35718f4799 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 22 Jun 2018 14:28:28 +0200
Subject: mtd: spinand: macronix: Add support for MX35LF2GE4AB

MX35LF2GE4AB is almost identical to MX35LF1GE4AB except it has 2 times
more eraseblocks per LUN and exposes 2 planes instead of 1.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/spi/macronix.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c
index 8ba3489d332a..98f6b9c4b684 100644
--- a/drivers/mtd/nand/spi/macronix.c
+++ b/drivers/mtd/nand/spi/macronix.c
@@ -102,6 +102,14 @@ static const struct spinand_info macronix_spinand_table[] = {
 		     SPINAND_HAS_QE_BIT,
 		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout,
 				     mx35lf1ge4ab_ecc_get_status)),
+	SPINAND_INFO("MX35LF2GE4AB", 0x22,
+		     NAND_MEMORG(1, 2048, 64, 64, 2048, 2, 1, 1),
+		     NAND_ECCREQ(4, 512),
+		     SPINAND_INFO_OP_VARIANTS(&read_cache_variants,
+					      &write_cache_variants,
+					      &update_cache_variants),
+		     SPINAND_HAS_QE_BIT,
+		     SPINAND_ECCINFO(&mx35lfxge4ab_ooblayout, NULL)),
 };
 
 static int macronix_spinand_detect(struct spinand_device *spinand)
-- 
cgit v1.2.3


From 24f0ae995deb728076e3ea93fea1949a9775debf Mon Sep 17 00:00:00 2001
From: Martin Kaiser <martin@kaiser.cx>
Date: Wed, 27 Jun 2018 22:47:44 +0200
Subject: mtd: rawnand: mxc: remove __init qualifier from mxcnd_probe_dt

Using the sysfs unbind, bind nodes, mxcnd_probe and mxcnd_probe_dt can
potentially be called at any time. After the __init functions are cleaned,
mxcnd_probe_dt is no longer available. Calling it anyway causes a crash.

mxcnd_probe used to be marked as __init, this was removed years ago.
Remove the __init qualifier from from mxcnd_probe_dt as well.

Fixes: 06f255106923 ("mtd: remove use of __devinit")
Signed-off-by: Martin Kaiser <martin@kaiser.cx>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/mxc_nand.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 26cef218bb43..90cfb5e730aa 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1686,7 +1686,7 @@ static const struct of_device_id mxcnd_dt_ids[] = {
 };
 MODULE_DEVICE_TABLE(of, mxcnd_dt_ids);
 
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	struct device_node *np = host->dev->of_node;
 	const struct of_device_id *of_id =
@@ -1700,7 +1700,7 @@ static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
 	return 0;
 }
 #else
-static int __init mxcnd_probe_dt(struct mxc_nand_host *host)
+static int mxcnd_probe_dt(struct mxc_nand_host *host)
 {
 	return 1;
 }
-- 
cgit v1.2.3


From cd1beffa83f680f3cb33be4e7cadfdf8399cef7e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 23 Jun 2018 01:06:35 +0900
Subject: mtd: rawnand: denali_dt: use dev as a shorthand of &pdev->dev

The probe function references &pdev->dev many times, and I will add
more soon.  Add 'dev' as a shorthand.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Richard Weinberger <richard@nod.at>
Tested-by: Richard Weinberger <richard@nod.at>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/denali_dt.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index 5869e90cc14b..6b4bd16e8bee 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -79,44 +79,45 @@ MODULE_DEVICE_TABLE(of, denali_nand_dt_ids);
 
 static int denali_dt_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct denali_dt *dt;
 	const struct denali_dt_data *data;
 	struct denali_nand_info *denali;
 	int ret;
 
-	dt = devm_kzalloc(&pdev->dev, sizeof(*dt), GFP_KERNEL);
+	dt = devm_kzalloc(dev, sizeof(*dt), GFP_KERNEL);
 	if (!dt)
 		return -ENOMEM;
 	denali = &dt->denali;
 
-	data = of_device_get_match_data(&pdev->dev);
+	data = of_device_get_match_data(dev);
 	if (data) {
 		denali->revision = data->revision;
 		denali->caps = data->caps;
 		denali->ecc_caps = data->ecc_caps;
 	}
 
-	denali->dev = &pdev->dev;
+	denali->dev = dev;
 	denali->irq = platform_get_irq(pdev, 0);
 	if (denali->irq < 0) {
-		dev_err(&pdev->dev, "no irq defined\n");
+		dev_err(dev, "no irq defined\n");
 		return denali->irq;
 	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "denali_reg");
-	denali->reg = devm_ioremap_resource(&pdev->dev, res);
+	denali->reg = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->reg))
 		return PTR_ERR(denali->reg);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "nand_data");
-	denali->host = devm_ioremap_resource(&pdev->dev, res);
+	denali->host = devm_ioremap_resource(dev, res);
 	if (IS_ERR(denali->host))
 		return PTR_ERR(denali->host);
 
-	dt->clk = devm_clk_get(&pdev->dev, NULL);
+	dt->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(dt->clk)) {
-		dev_err(&pdev->dev, "no clk available\n");
+		dev_err(dev, "no clk available\n");
 		return PTR_ERR(dt->clk);
 	}
 	ret = clk_prepare_enable(dt->clk);
-- 
cgit v1.2.3


From d91e8a3eec69a9767a6efa17543a12e1bfcbe099 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 23 Jun 2018 01:06:36 +0900
Subject: dt-binding: mtd: denali_dt: document clock property

Commit 30f9f2fb7ba0 ("mtd: denali: add a DT driver") supported the
clock enablement, but did not document it in the DT binding.

In addition to the existing clock, this commit adds more clocks based
on the IP specification.

According to the Denali User's Guide, this IP needs three clocks:

 - clk: controller core clock

 - clk_x: bus interface clock

 - ecc_clk: clock at which ECC circuitry is run

The driver should accept the current single clock for the backward
compatibility, but the DT binding should represent the real hardware,
and future platforms must follow this.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/denali-nand.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/mtd/denali-nand.txt b/Documentation/devicetree/bindings/mtd/denali-nand.txt
index 0ee8edb60efc..f33da8782741 100644
--- a/Documentation/devicetree/bindings/mtd/denali-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/denali-nand.txt
@@ -8,6 +8,9 @@ Required properties:
   - reg : should contain registers location and length for data and reg.
   - reg-names: Should contain the reg names "nand_data" and "denali_reg"
   - interrupts : The interrupt number.
+  - clocks: should contain phandle of the controller core clock, the bus
+    interface clock, and the ECC circuit clock.
+  - clock-names: should contain "nand", "nand_x", "ecc"
 
 Optional properties:
   - nand-ecc-step-size: see nand.txt for details.  If present, the value must be
@@ -31,5 +34,7 @@ nand: nand@ff900000 {
 	compatible = "altr,socfpga-denali-nand";
 	reg = <0xff900000 0x20>, <0xffb80000 0x1000>;
 	reg-names = "nand_data", "denali_reg";
+	clocks = <&nand_clk>, <&nand_x_clk>, <&nand_ecc_clk>;
+	clock-names = "nand", "nand_x", "ecc";
 	interrupts = <0 144 4>;
 };
-- 
cgit v1.2.3


From 6f1fe97bec349a1fd6c5a8c7c5998d759fe721d5 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 23 Jun 2018 01:06:37 +0900
Subject: mtd: rawnand: denali_dt: add more clocks based on IP datasheet

Currently, denali_dt.c requires a single anonymous clock, but
the Denali User's Guide requires three clocks for this IP:

 - clk: controller core clock

 - clk_x: bus interface clock

 - ecc_clk: clock at which ECC circuitry is run

This commit supports these named clocks to represent the real hardware.

For the backward compatibility, the driver still accepts a single clock
just as before.  The clk_x_rate is taken from the clock driver again if
the named clock "clk_x" is available.  This will happen only for future
DT, hence the existing DT files are not affected.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Richard Weinberger <richard@nod.at>
Tested-by: Richard Weinberger <richard@nod.at>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/denali_dt.c | 53 ++++++++++++++++++++++++++++++++++------
 1 file changed, 45 insertions(+), 8 deletions(-)

diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index 6b4bd16e8bee..afaae378c624 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -27,7 +27,9 @@
 
 struct denali_dt {
 	struct denali_nand_info	denali;
-	struct clk		*clk;
+	struct clk *clk;	/* core clock */
+	struct clk *clk_x;	/* bus interface clock */
+	struct clk *clk_ecc;	/* ECC circuit clock */
 };
 
 struct denali_dt_data {
@@ -115,28 +117,61 @@ static int denali_dt_probe(struct platform_device *pdev)
 	if (IS_ERR(denali->host))
 		return PTR_ERR(denali->host);
 
-	dt->clk = devm_clk_get(dev, NULL);
+	/*
+	 * A single anonymous clock is supported for the backward compatibility.
+	 * New platforms should support all the named clocks.
+	 */
+	dt->clk = devm_clk_get(dev, "nand");
+	if (IS_ERR(dt->clk))
+		dt->clk = devm_clk_get(dev, NULL);
 	if (IS_ERR(dt->clk)) {
 		dev_err(dev, "no clk available\n");
 		return PTR_ERR(dt->clk);
 	}
+
+	dt->clk_x = devm_clk_get(dev, "nand_x");
+	if (IS_ERR(dt->clk_x))
+		dt->clk_x = NULL;
+
+	dt->clk_ecc = devm_clk_get(dev, "ecc");
+	if (IS_ERR(dt->clk_ecc))
+		dt->clk_ecc = NULL;
+
 	ret = clk_prepare_enable(dt->clk);
 	if (ret)
 		return ret;
 
-	/*
-	 * Hardcode the clock rate for the backward compatibility.
-	 * This works for both SOCFPGA and UniPhier.
-	 */
-	denali->clk_x_rate = 200000000;
+	ret = clk_prepare_enable(dt->clk_x);
+	if (ret)
+		goto out_disable_clk;
+
+	ret = clk_prepare_enable(dt->clk_ecc);
+	if (ret)
+		goto out_disable_clk_x;
+
+	if (dt->clk_x) {
+		denali->clk_x_rate = clk_get_rate(dt->clk_x);
+	} else {
+		/*
+		 * Hardcode the clock rates for the backward compatibility.
+		 * This works for both SOCFPGA and UniPhier.
+		 */
+		dev_notice(dev,
+			   "necessary clock is missing. default clock rates are used.\n");
+		denali->clk_x_rate = 200000000;
+	}
 
 	ret = denali_init(denali);
 	if (ret)
-		goto out_disable_clk;
+		goto out_disable_clk_ecc;
 
 	platform_set_drvdata(pdev, dt);
 	return 0;
 
+out_disable_clk_ecc:
+	clk_disable_unprepare(dt->clk_ecc);
+out_disable_clk_x:
+	clk_disable_unprepare(dt->clk_x);
 out_disable_clk:
 	clk_disable_unprepare(dt->clk);
 
@@ -148,6 +183,8 @@ static int denali_dt_remove(struct platform_device *pdev)
 	struct denali_dt *dt = platform_get_drvdata(pdev);
 
 	denali_remove(&dt->denali);
+	clk_disable_unprepare(dt->clk_ecc);
+	clk_disable_unprepare(dt->clk_x);
 	clk_disable_unprepare(dt->clk);
 
 	return 0;
-- 
cgit v1.2.3


From 1dfac31a5a63ac04a9b5fbc3f5105a586560f191 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 23 Jun 2018 01:06:38 +0900
Subject: mtd: rawnand: denali: optimize timing parameters for data interface

This commit improves the ->setup_data_interface() hook.

The denali_setup_data_interface() needs the frequency of clk_x
and the ratio of clk_x / clk.

The latter is currently hardcoded in the driver, like this:

  #define DENALI_CLK_X_MULT       6

The IP datasheet requires that clk_x / clk be 4, 5, or 6.  I just
chose 6 because it is the most defensive value, but it is not optimal.
By getting the clock rate of both "clk" and "clk_x", the driver can
compute the timing values more precisely.

To not break the existing platforms, the fallback value, 50 MHz is
provided.  It is true for all upstreamed platforms.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Richard Weinberger <richard@nod.at>
Tested-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/denali.c     | 49 +++++++++++++++++++--------------------
 drivers/mtd/nand/raw/denali.h     |  1 +
 drivers/mtd/nand/raw/denali_dt.c  |  2 ++
 drivers/mtd/nand/raw/denali_pci.c |  1 +
 4 files changed, 28 insertions(+), 25 deletions(-)

diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index a586a1d8b997..4d53f41ada08 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -51,14 +51,6 @@ MODULE_LICENSE("GPL");
 #define DENALI_INVALID_BANK	-1
 #define DENALI_NR_BANKS		4
 
-/*
- * The bus interface clock, clk_x, is phase aligned with the core clock.  The
- * clk_x is an integral multiple N of the core clk.  The value N is configured
- * at IP delivery time, and its available value is 4, 5, or 6.  We need to align
- * to the largest value to make it work with any possible configuration.
- */
-#define DENALI_CLK_X_MULT	6
-
 static inline struct denali_nand_info *mtd_to_denali(struct mtd_info *mtd)
 {
 	return container_of(mtd_to_nand(mtd), struct denali_nand_info, nand);
@@ -954,7 +946,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 {
 	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	const struct nand_sdr_timings *timings;
-	unsigned long t_clk;
+	unsigned long t_x, mult_x;
 	int acc_clks, re_2_we, re_2_re, we_2_re, addr_2_data;
 	int rdwr_en_lo, rdwr_en_hi, rdwr_en_lo_hi, cs_setup;
 	int addr_2_data_mask;
@@ -965,15 +957,24 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 		return PTR_ERR(timings);
 
 	/* clk_x period in picoseconds */
-	t_clk = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
-	if (!t_clk)
+	t_x = DIV_ROUND_DOWN_ULL(1000000000000ULL, denali->clk_x_rate);
+	if (!t_x)
+		return -EINVAL;
+
+	/*
+	 * The bus interface clock, clk_x, is phase aligned with the core clock.
+	 * The clk_x is an integral multiple N of the core clk.  The value N is
+	 * configured at IP delivery time, and its available value is 4, 5, 6.
+	 */
+	mult_x = DIV_ROUND_CLOSEST_ULL(denali->clk_x_rate, denali->clk_rate);
+	if (mult_x < 4 || mult_x > 6)
 		return -EINVAL;
 
 	if (chipnr == NAND_DATA_IFACE_CHECK_ONLY)
 		return 0;
 
 	/* tREA -> ACC_CLKS */
-	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_clk);
+	acc_clks = DIV_ROUND_UP(timings->tREA_max, t_x);
 	acc_clks = min_t(int, acc_clks, ACC_CLKS__VALUE);
 
 	tmp = ioread32(denali->reg + ACC_CLKS);
@@ -982,7 +983,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + ACC_CLKS);
 
 	/* tRWH -> RE_2_WE */
-	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_clk);
+	re_2_we = DIV_ROUND_UP(timings->tRHW_min, t_x);
 	re_2_we = min_t(int, re_2_we, RE_2_WE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_WE);
@@ -991,7 +992,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RE_2_WE);
 
 	/* tRHZ -> RE_2_RE */
-	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_clk);
+	re_2_re = DIV_ROUND_UP(timings->tRHZ_max, t_x);
 	re_2_re = min_t(int, re_2_re, RE_2_RE__VALUE);
 
 	tmp = ioread32(denali->reg + RE_2_RE);
@@ -1005,8 +1006,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	 * With WE_2_RE properly set, the Denali controller automatically takes
 	 * care of the delay; the driver need not set NAND_WAIT_TCCS.
 	 */
-	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min),
-			       t_clk);
+	we_2_re = DIV_ROUND_UP(max(timings->tCCS_min, timings->tWHR_min), t_x);
 	we_2_re = min_t(int, we_2_re, TWHR2_AND_WE_2_RE__WE_2_RE);
 
 	tmp = ioread32(denali->reg + TWHR2_AND_WE_2_RE);
@@ -1021,7 +1021,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	if (denali->revision < 0x0501)
 		addr_2_data_mask >>= 1;
 
-	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_clk);
+	addr_2_data = DIV_ROUND_UP(timings->tADL_min, t_x);
 	addr_2_data = min_t(int, addr_2_data, addr_2_data_mask);
 
 	tmp = ioread32(denali->reg + TCWAW_AND_ADDR_2_DATA);
@@ -1031,7 +1031,7 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 
 	/* tREH, tWH -> RDWR_EN_HI_CNT */
 	rdwr_en_hi = DIV_ROUND_UP(max(timings->tREH_min, timings->tWH_min),
-				  t_clk);
+				  t_x);
 	rdwr_en_hi = min_t(int, rdwr_en_hi, RDWR_EN_HI_CNT__VALUE);
 
 	tmp = ioread32(denali->reg + RDWR_EN_HI_CNT);
@@ -1040,11 +1040,10 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_HI_CNT);
 
 	/* tRP, tWP -> RDWR_EN_LO_CNT */
-	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min),
-				  t_clk);
+	rdwr_en_lo = DIV_ROUND_UP(max(timings->tRP_min, timings->tWP_min), t_x);
 	rdwr_en_lo_hi = DIV_ROUND_UP(max(timings->tRC_min, timings->tWC_min),
-				     t_clk);
-	rdwr_en_lo_hi = max(rdwr_en_lo_hi, DENALI_CLK_X_MULT);
+				     t_x);
+	rdwr_en_lo_hi = max_t(int, rdwr_en_lo_hi, mult_x);
 	rdwr_en_lo = max(rdwr_en_lo, rdwr_en_lo_hi - rdwr_en_hi);
 	rdwr_en_lo = min_t(int, rdwr_en_lo, RDWR_EN_LO_CNT__VALUE);
 
@@ -1054,8 +1053,8 @@ static int denali_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	iowrite32(tmp, denali->reg + RDWR_EN_LO_CNT);
 
 	/* tCS, tCEA -> CS_SETUP_CNT */
-	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_clk) - rdwr_en_lo,
-			(int)DIV_ROUND_UP(timings->tCEA_max, t_clk) - acc_clks,
+	cs_setup = max3((int)DIV_ROUND_UP(timings->tCS_min, t_x) - rdwr_en_lo,
+			(int)DIV_ROUND_UP(timings->tCEA_max, t_x) - acc_clks,
 			0);
 	cs_setup = min_t(int, cs_setup, CS_SETUP_CNT__VALUE);
 
@@ -1255,7 +1254,7 @@ int denali_init(struct denali_nand_info *denali)
 	}
 
 	/* clk rate info is needed for setup_data_interface */
-	if (denali->clk_x_rate)
+	if (denali->clk_rate && denali->clk_x_rate)
 		chip->setup_data_interface = denali_setup_data_interface;
 
 	ret = nand_scan_ident(mtd, denali->max_banks, NULL);
diff --git a/drivers/mtd/nand/raw/denali.h b/drivers/mtd/nand/raw/denali.h
index 9ad33d237378..1f8feaf924eb 100644
--- a/drivers/mtd/nand/raw/denali.h
+++ b/drivers/mtd/nand/raw/denali.h
@@ -300,6 +300,7 @@
 
 struct denali_nand_info {
 	struct nand_chip nand;
+	unsigned long clk_rate;		/* core clock rate */
 	unsigned long clk_x_rate;	/* bus interface clock rate */
 	int active_bank;		/* currently selected bank */
 	struct device *dev;
diff --git a/drivers/mtd/nand/raw/denali_dt.c b/drivers/mtd/nand/raw/denali_dt.c
index afaae378c624..0faaad032e5f 100644
--- a/drivers/mtd/nand/raw/denali_dt.c
+++ b/drivers/mtd/nand/raw/denali_dt.c
@@ -150,6 +150,7 @@ static int denali_dt_probe(struct platform_device *pdev)
 		goto out_disable_clk_x;
 
 	if (dt->clk_x) {
+		denali->clk_rate = clk_get_rate(dt->clk);
 		denali->clk_x_rate = clk_get_rate(dt->clk_x);
 	} else {
 		/*
@@ -158,6 +159,7 @@ static int denali_dt_probe(struct platform_device *pdev)
 		 */
 		dev_notice(dev,
 			   "necessary clock is missing. default clock rates are used.\n");
+		denali->clk_rate = 50000000;
 		denali->clk_x_rate = 200000000;
 	}
 
diff --git a/drivers/mtd/nand/raw/denali_pci.c b/drivers/mtd/nand/raw/denali_pci.c
index 49cb3e1f8bd0..7c8efc4c7bdf 100644
--- a/drivers/mtd/nand/raw/denali_pci.c
+++ b/drivers/mtd/nand/raw/denali_pci.c
@@ -73,6 +73,7 @@ static int denali_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	denali->irq = dev->irq;
 	denali->ecc_caps = &denali_pci_ecc_caps;
 	denali->nand.ecc.options |= NAND_ECC_MAXIMIZE;
+	denali->clk_rate = 50000000;		/* 50 MHz */
 	denali->clk_x_rate = 200000000;		/* 200 MHz */
 
 	ret = pci_request_regions(dev, DENALI_NAND_NAME);
-- 
cgit v1.2.3


From 8604e6346e8db6dece741881d647606511ddafde Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Sun, 25 Feb 2018 23:09:14 +0100
Subject: mtd: rawnand: docg4: fix the probe function error path

nand_release() should not be called on an MTD device that has not been
registered. While it should work thanks to the checks done in
mtd_device_unregister() it's a bad practice to cleanup/release
something that has not previously been initialized/allocated.

Rework the error path to follow this rule.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/docg4.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c
index 1314aa99b9ab..bb96cb33cd6b 100644
--- a/drivers/mtd/nand/raw/docg4.c
+++ b/drivers/mtd/nand/raw/docg4.c
@@ -1341,7 +1341,7 @@ static int __init probe_docg4(struct platform_device *pdev)
 	nand = kzalloc(len, GFP_KERNEL);
 	if (nand == NULL) {
 		retval = -ENOMEM;
-		goto fail_unmap;
+		goto unmap;
 	}
 
 	mtd = nand_to_mtd(nand);
@@ -1357,7 +1357,7 @@ static int __init probe_docg4(struct platform_device *pdev)
 	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
 	if (doc->bch == NULL) {
 		retval = -EINVAL;
-		goto fail;
+		goto free_nand;
 	}
 
 	platform_set_drvdata(pdev, doc);
@@ -1366,30 +1366,32 @@ static int __init probe_docg4(struct platform_device *pdev)
 	retval = read_id_reg(mtd);
 	if (retval == -ENODEV) {
 		dev_warn(dev, "No diskonchip G4 device found.\n");
-		goto fail;
+		goto free_bch;
 	}
 
 	retval = nand_scan_tail(mtd);
 	if (retval)
-		goto fail;
+		goto free_bch;
 
 	retval = read_factory_bbt(mtd);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	retval = mtd_device_parse_register(mtd, part_probes, NULL, NULL, 0);
 	if (retval)
-		goto fail;
+		goto cleanup_nand;
 
 	doc->mtd = mtd;
+
 	return 0;
 
-fail:
-	nand_release(mtd); /* deletes partitions and mtd devices */
+cleanup_nand:
+	nand_cleanup(nand);
+free_bch:
 	free_bch(doc->bch);
+free_nand:
 	kfree(nand);
-
-fail_unmap:
+unmap:
 	iounmap(virtadr);
 
 	return retval;
-- 
cgit v1.2.3


From da8eb7d227c560a1557a16caee20d7be07b074f8 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 3 Jul 2018 09:12:14 +0100
Subject: mtd: rawnand: gpmi: remove redundant variable payload_virt

Variable payload_virt is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'payload_virt' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index f6aa358a3452..58d4e4a93a93 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -957,7 +957,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 	struct gpmi_nand_data *this = nand_get_controller_data(chip);
 	struct bch_geometry *nfc_geo = &this->bch_geometry;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	void          *payload_virt;
 	dma_addr_t    payload_phys;
 	unsigned int  i;
 	unsigned char *status;
@@ -967,7 +966,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 
 	dev_dbg(this->dev, "page number is : %d\n", page);
 
-	payload_virt = this->payload_virt;
 	payload_phys = this->payload_phys;
 
 	if (virt_addr_valid(buf)) {
@@ -976,7 +974,6 @@ static int gpmi_ecc_read_page_data(struct nand_chip *chip,
 		dest_phys = dma_map_single(this->dev, buf, nfc_geo->payload_size,
 					   DMA_FROM_DEVICE);
 		if (!dma_mapping_error(this->dev, dest_phys)) {
-			payload_virt = buf;
 			payload_phys = dest_phys;
 			direct = true;
 		}
-- 
cgit v1.2.3


From 9f43deee43511c2d70a8220f76854aab89f4e673 Mon Sep 17 00:00:00 2001
From: Abhishek Sahu <absahu@codeaurora.org>
Date: Tue, 3 Jul 2018 17:36:03 +0530
Subject: mtd: rawnand: qcom: erased page bitflips detection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

NAND parts can have bitflips in an erased page due to the
process technology used. In this case, QCOM NAND controller
is not able to identify that page as an erased page.
Currently the driver calls nand_check_erased_ecc_chunk() for
identifying the erased pages but this won’t work always since the
checking is being with ECC engine returned data. In case of
bitflips, the ECC engine tries to correct the data and then it
generates the uncorrectable error. Now, this data is not equal to
original raw data. For erased CW identification, the raw data
should be read again from NAND device and this
nand_check_erased_ecc_chunk function() should be called for raw
data only.

Now following logic is being added to identify the erased
codeword bitflips.

1. In most of the cases, not all the codewords will have bitflips
   and only single CW will have bitflips. So, there is no need to
   read the complete raw page data. The NAND raw read can be
   scheduled for any CW in page. The NAND controller works on CW
   basis and it will update the status register after each CW read.
   Maintain the bitmask for the CW which generated the uncorrectable
   error.
2. Do raw read for all the CW's which generated the uncorrectable
   error.
3. Both DATA and OOB need to be checked for number of 0. The
   top-level API can be called with only data buf or OOB buf so use
   chip->databuf if data buf is null and chip->oob_poi if
   OOB buf is null for copying the raw bytes temporarily.
4. For each CW, check the number of 0 in cw_data and usable
   oob bytes, The bbm and spare (unused) bytes bit flip won’t
   affect the ECC so don’t check the number of bitflips in this area.

Signed-off-by: Abhishek Sahu <absahu@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 126 +++++++++++++++++++++++++++-----------
 1 file changed, 89 insertions(+), 37 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 160acdff7d86..994f980c6d86 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1655,21 +1655,95 @@ qcom_nandc_read_cw_raw(struct mtd_info *mtd, struct nand_chip *chip,
 	return check_flash_errors(host, 1);
 }
 
+/*
+ * Bitflips can happen in erased codewords also so this function counts the
+ * number of 0 in each CW for which ECC engine returns the uncorrectable
+ * error. The page will be assumed as erased if this count is less than or
+ * equal to the ecc->strength for each CW.
+ *
+ * 1. Both DATA and OOB need to be checked for number of 0. The
+ *    top-level API can be called with only data buf or OOB buf so use
+ *    chip->data_buf if data buf is null and chip->oob_poi if oob buf
+ *    is null for copying the raw bytes.
+ * 2. Perform raw read for all the CW which has uncorrectable errors.
+ * 3. For each CW, check the number of 0 in cw_data and usable OOB bytes.
+ *    The BBM and spare bytes bit flip won’t affect the ECC so don’t check
+ *    the number of bitflips in this area.
+ */
+static int
+check_for_erased_page(struct qcom_nand_host *host, u8 *data_buf,
+		      u8 *oob_buf, unsigned long uncorrectable_cws,
+		      int page, unsigned int max_bitflips)
+{
+	struct nand_chip *chip = &host->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+	u8 *cw_data_buf, *cw_oob_buf;
+	int cw, data_size, oob_size, ret = 0;
+
+	if (!data_buf) {
+		data_buf = chip->data_buf;
+		chip->pagebuf = -1;
+	}
+
+	if (!oob_buf) {
+		oob_buf = chip->oob_poi;
+		chip->pagebuf = -1;
+	}
+
+	for_each_set_bit(cw, &uncorrectable_cws, ecc->steps) {
+		if (cw == (ecc->steps - 1)) {
+			data_size = ecc->size - ((ecc->steps - 1) * 4);
+			oob_size = (ecc->steps * 4) + host->ecc_bytes_hw;
+		} else {
+			data_size = host->cw_data;
+			oob_size = host->ecc_bytes_hw;
+		}
+
+		/* determine starting buffer address for current CW */
+		cw_data_buf = data_buf + (cw * host->cw_data);
+		cw_oob_buf = oob_buf + (cw * ecc->bytes);
+
+		ret = qcom_nandc_read_cw_raw(mtd, chip, cw_data_buf,
+					     cw_oob_buf, page, cw);
+		if (ret)
+			return ret;
+
+		/*
+		 * make sure it isn't an erased page reported
+		 * as not-erased by HW because of a few bitflips
+		 */
+		ret = nand_check_erased_ecc_chunk(cw_data_buf, data_size,
+						  cw_oob_buf + host->bbm_size,
+						  oob_size, NULL,
+						  0, ecc->strength);
+		if (ret < 0) {
+			mtd->ecc_stats.failed++;
+		} else {
+			mtd->ecc_stats.corrected += ret;
+			max_bitflips = max_t(unsigned int, max_bitflips, ret);
+		}
+	}
+
+	return max_bitflips;
+}
+
 /*
  * reads back status registers set by the controller to notify page read
  * errors. this is equivalent to what 'ecc->correct()' would do.
  */
 static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
-			     u8 *oob_buf)
+			     u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
-	unsigned int max_bitflips = 0;
+	unsigned int max_bitflips = 0, uncorrectable_cws = 0;
 	struct read_stats *buf;
-	bool flash_op_err = false;
+	bool flash_op_err = false, erased;
 	int i;
+	u8 *data_buf_start = data_buf, *oob_buf_start = oob_buf;
 
 	buf = (struct read_stats *)nandc->reg_read_buf;
 	nandc_read_buffer_sync(nandc, true);
@@ -1699,10 +1773,6 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 		 *    codeword detection check will be done.
 		 */
 		if ((flash & FS_OP_ERR) && (buffer & BS_UNCORRECTABLE_BIT)) {
-			bool erased;
-			int ret, ecclen, extraooblen;
-			void *eccbuf;
-
 			/*
 			 * For BCH ECC, ignore erased codeword errors, if
 			 * ERASED_CW bits are set.
@@ -1723,31 +1793,8 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 				erased = false;
 			}
 
-			if (erased) {
-				data_buf += data_len;
-				if (oob_buf)
-					oob_buf += oob_len + ecc->bytes;
-				continue;
-			}
-
-			eccbuf = oob_buf ? oob_buf + oob_len : NULL;
-			ecclen = oob_buf ? host->ecc_bytes_hw : 0;
-			extraooblen = oob_buf ? oob_len : 0;
-
-			/*
-			 * make sure it isn't an erased page reported
-			 * as not-erased by HW because of a few bitflips
-			 */
-			ret = nand_check_erased_ecc_chunk(data_buf,
-				data_len, eccbuf, ecclen, oob_buf,
-				extraooblen, ecc->strength);
-			if (ret < 0) {
-				mtd->ecc_stats.failed++;
-			} else {
-				mtd->ecc_stats.corrected += ret;
-				max_bitflips =
-					max_t(unsigned int, max_bitflips, ret);
-			}
+			if (!erased)
+				uncorrectable_cws |= BIT(i);
 		/*
 		 * Check if MPU or any other operational error (timeout,
 		 * device failure, etc.) happened for this codeword and
@@ -1777,7 +1824,12 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
 	if (flash_op_err)
 		return -EIO;
 
-	return max_bitflips;
+	if (!uncorrectable_cws)
+		return max_bitflips;
+
+	return check_for_erased_page(host, data_buf_start, oob_buf_start,
+				     uncorrectable_cws, page,
+				     max_bitflips);
 }
 
 /*
@@ -1785,7 +1837,7 @@ static int parse_read_errors(struct qcom_nand_host *host, u8 *data_buf,
  * ecc->read_oob()
  */
 static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
-			 u8 *oob_buf)
+			 u8 *oob_buf, int page)
 {
 	struct nand_chip *chip = &host->chip;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
@@ -1858,7 +1910,7 @@ static int read_page_ecc(struct qcom_nand_host *host, u8 *data_buf,
 		return ret;
 	}
 
-	return parse_read_errors(host, data_buf_start, oob_buf_start);
+	return parse_read_errors(host, data_buf_start, oob_buf_start, page);
 }
 
 /*
@@ -1910,7 +1962,7 @@ static int qcom_nandc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 
 	clear_bam_transaction(nandc);
 
-	return read_page_ecc(host, data_buf, oob_buf);
+	return read_page_ecc(host, data_buf, oob_buf, page);
 }
 
 /* implements ecc->read_page_raw() */
@@ -1951,7 +2003,7 @@ static int qcom_nandc_read_oob(struct mtd_info *mtd, struct nand_chip *chip,
 	set_address(host, 0, page);
 	update_rw_regs(host, ecc->steps, true);
 
-	return read_page_ecc(host, NULL, chip->oob_poi);
+	return read_page_ecc(host, NULL, chip->oob_poi, page);
 }
 
 /* implements ecc->write_page() */
-- 
cgit v1.2.3


From 4d54df433558683236298cc15dbdfee9aa928dee Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:44:56 +0200
Subject: mtd: rawnand: gpmi: Remove useless dependency on MTD_NAND

The MTD_NAND_GPMI_NAND entry is already defined in an 'if MTD_NAND'
block, no need to add an extra "depends on MTD_NAND".

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6074a946708a..58dad80eb174 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -340,7 +340,7 @@ config MTD_NAND_NANDSIM
 
 config MTD_NAND_GPMI_NAND
         tristate "GPMI NAND Flash Controller driver"
-        depends on MTD_NAND && MXS_DMA
+        depends on MXS_DMA
         help
 	 Enables NAND Flash support for IMX23, IMX28 or IMX6.
 	 The GPMI controller is very powerful, with the help of BCH
-- 
cgit v1.2.3


From 45e9f40f466955c9880d59683531f6d1366b97cd Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:44:57 +0200
Subject: mtd: rawnand: Add 'depends on HAS_IOMEM' where missing

When COMPILE_TEST is allowed and the platform needs uses the iomem API
we need to add an explicit dependency on HAS_IOMEM to avoid selection
of these drivers when building for an arch that has no iomem support
(this is the case of arch/um).

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 58dad80eb174..bfd28c1b72a3 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -152,6 +152,7 @@ config MTD_NAND_S3C2410_CLKSTOP
 config MTD_NAND_TANGO
 	tristate "NAND Flash support for Tango chips"
 	depends on ARCH_TANGO || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the NAND Flash controller on Tango chips.
 
@@ -513,6 +514,7 @@ config MTD_NAND_SUNXI
 config MTD_NAND_HISI504
 	tristate "Support for NAND controller on Hisilicon SoC Hip04"
 	depends on ARCH_HISI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on Hisilicon SoC Hip04.
 
@@ -526,6 +528,7 @@ config MTD_NAND_QCOM
 config MTD_NAND_MTK
 	tristate "Support for NAND controller on MTK SoCs"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND controller on MTK SoCs.
 	  This controller is found on mt27xx, mt81xx, mt65xx SoCs.
@@ -533,6 +536,7 @@ config MTD_NAND_MTK
 config MTD_NAND_TEGRA
 	tristate "Support for NAND controller on NVIDIA Tegra"
 	depends on ARCH_TEGRA || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND flash controller on NVIDIA Tegra SoC.
 	  The driver has been developed and tested on a Tegra 2 SoC. DMA
-- 
cgit v1.2.3


From 31ac1a53eb7f4407decbbbe65d8232311705029e Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:44:59 +0200
Subject: mtd: rawnand: omap2: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_OMAP2PLUS or ARCH_KEYSTONE
enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index bfd28c1b72a3..6a406f5b6b7f 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -77,7 +77,8 @@ config MTD_NAND_AMS_DELTA
 
 config MTD_NAND_OMAP2
 	tristate "NAND Flash device on OMAP2, OMAP3, OMAP4 and Keystone"
-	depends on (ARCH_OMAP2PLUS || ARCH_KEYSTONE)
+	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
           Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
 	  and Keystone platforms.
-- 
cgit v1.2.3


From b22a8b075dbc755dd483e1d318c8f2933464583e Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:01 +0200
Subject: mtd: rawnand: sharpsl: Remove inclusion of mach and asm headers

We don't need mach/hardware.h and sm/mach-types.h, and asm/io.h can be
replaced by linux/io.h.

Now that we removed those inclusions, we're ready to allow selection of
this driver when COMPILE_TEST=y.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/sharpsl.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/mtd/nand/raw/sharpsl.c b/drivers/mtd/nand/raw/sharpsl.c
index e93df02c825e..fc171b17a39b 100644
--- a/drivers/mtd/nand/raw/sharpsl.c
+++ b/drivers/mtd/nand/raw/sharpsl.c
@@ -21,10 +21,7 @@
 #include <linux/mtd/sharpsl.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
-
-#include <asm/io.h>
-#include <mach/hardware.h>
-#include <asm/mach-types.h>
+#include <linux/io.h>
 
 struct sharpsl_nand {
 	struct nand_chip	chip;
-- 
cgit v1.2.3


From 18331b98102925f17be13421e153b050b8df01d3 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:02 +0200
Subject: mtd: rawnand: sharpsl: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_PXA enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 6a406f5b6b7f..59bafed9da17 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -249,7 +249,8 @@ config MTD_NAND_DOCG4
 
 config MTD_NAND_SHARPSL
 	tristate "Support for NAND Flash on Sharp SL Series (C7xx + others)"
-	depends on ARCH_PXA
+	depends on ARCH_PXA || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config MTD_NAND_CAFE
 	tristate "NAND support for OLPC CAFÉ chip"
-- 
cgit v1.2.3


From ee70e5e796ff30e486bef4800a633df8e14d6245 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:03 +0200
Subject: mtd: rawnand: lpc32xx: Allow selection of these drivers when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test these drivers without having ARCH_LPC32XX enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 59bafed9da17..22cc19e7586c 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -297,7 +297,8 @@ config MTD_NAND_MARVELL
 
 config MTD_NAND_SLC_LPC32XX
 	tristate "NXP LPC32xx SLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NXP's LPC32XX SLC (i.e. for Single Level Cell
 	  chips) NAND controller. This is the default for the PHYTEC 3250
@@ -308,7 +309,8 @@ config MTD_NAND_SLC_LPC32XX
 
 config MTD_NAND_MLC_LPC32XX
 	tristate "NXP LPC32xx MLC Controller"
-	depends on ARCH_LPC32XX
+	depends on ARCH_LPC32XX || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Uses the LPC32XX MLC (i.e. for Multi Level Cell chips) NAND
 	  controller. This is the default for the WORK92105 controller
-- 
cgit v1.2.3


From 0beb48724120ae13fe87d344a78fb430e077fed9 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:04 +0200
Subject: mtd: rawnand: brcmnand: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARM, ARM64 or MIPS enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 22cc19e7586c..af0b3cd51c82 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -354,7 +354,8 @@ config MTD_NAND_GPMI_NAND
 
 config MTD_NAND_BRCMNAND
 	tristate "Broadcom STB NAND controller"
-	depends on ARM || ARM64 || MIPS
+	depends on ARM || ARM64 || MIPS || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables the Broadcom NAND controller driver. The controller was
 	  originally designed for Set-Top Box but is used on various BCM7xxx,
-- 
cgit v1.2.3


From c03f3cf37e54fee8c04c531dae1c81ebc8f58723 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:07 +0200
Subject: mtd: rawnand: mxc: Avoid inclusion of asm/mach headers

asm/mach/flash.h does not seem to be needed, drop this #include to make
the code completely machine and arch independent and allow one to
compile it when COMPILE_TEST=y.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/mxc_nand.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 90cfb5e730aa..14ec7d975593 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -34,8 +34,6 @@
 #include <linux/completion.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-
-#include <asm/mach/flash.h>
 #include <linux/platform_data/mtd-mxc_nand.h>
 
 #define DRIVER_NAME "mxc_nand"
-- 
cgit v1.2.3


From 434bc2e148aa5a6052cbc038f485fa3284a477d0 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:08 +0200
Subject: mtd: rawnand: mxc: Allow selection of this driver when COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_MXC enabled.

We also need to add a dependency on HAS_IOMEM to make sure the
driver compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index af0b3cd51c82..3565dc06593f 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -443,7 +443,8 @@ config MTD_NAND_VF610_NFC
 
 config MTD_NAND_MXC
 	tristate "MXC NAND support"
-	depends on ARCH_MXC
+	depends on ARCH_MXC || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND flash controller on the
 	  MXC processors.
-- 
cgit v1.2.3


From b2d55fe2ad5a47676292b1ef211fe4f9f14133ec Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:11 +0200
Subject: mtd: rawnand: qcom: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_QCOM enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 3565dc06593f..dd2fc7105ea7 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -526,7 +526,8 @@ config MTD_NAND_HISI504
 
 config MTD_NAND_QCOM
 	tristate "Support for NAND on QCOM SoCs"
-	depends on ARCH_QCOM
+	depends on ARCH_QCOM || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND flash chips on SoCs containing the EBI2 NAND
 	  controller. This controller is found on IPQ806x SoC.
-- 
cgit v1.2.3


From d4de09e5bb08138f06b6d27cd0246d32866b0c68 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:13 +0200
Subject: mtd: rawnand: nuc900: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_W90X900 enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index dd2fc7105ea7..230311fa2cc0 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -478,7 +478,8 @@ config MTD_NAND_SOCRATES
 
 config MTD_NAND_NUC900
 	tristate "Support for NAND on Nuvoton NUC9xx/w90p910 evaluation boards."
-	depends on ARCH_W90X900
+	depends on ARCH_W90X900 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the driver for the NAND Flash on evaluation board based
 	  on w90p910 / NUC9xx.
-- 
cgit v1.2.3


From a58d0b4d512aceb06d8a968c1d19318c77faa6b0 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 11:45:16 +0200
Subject: bcma: Allow selection of this driver when COMPILE_TEST=y

This allows us to increase compile-test coverage without having to build
a kernel for MIPS.  That's particularly interesting for subsystem
maintainers that want to test as many drivers as possible in a single
build.

We also add a dependency on HAS_IOMEM in BCMA_HOST_SOC to make sure the
driver is not selected when the arch does not implement IO accessors.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Kalle Valo <kvalo@codeaurora.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/bcma/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/bcma/Kconfig b/drivers/bcma/Kconfig
index cb0f1aad20b7..b9558ff20830 100644
--- a/drivers/bcma/Kconfig
+++ b/drivers/bcma/Kconfig
@@ -30,6 +30,7 @@ config BCMA_HOST_PCI
 
 config BCMA_HOST_SOC
 	bool "Support for BCMA in a SoC"
+	depends on HAS_IOMEM
 	help
 	  Host interface for a Broadcom AIX bus directly mapped into
 	  the memory. This only works with the Broadcom SoCs from the
@@ -61,7 +62,7 @@ config BCMA_DRIVER_PCI_HOSTMODE
 
 config BCMA_DRIVER_MIPS
 	bool "BCMA Broadcom MIPS core driver"
-	depends on MIPS
+	depends on MIPS || COMPILE_TEST
 	help
 	  Driver for the Broadcom MIPS core attached to Broadcom specific
 	  Advanced Microcontroller Bus.
-- 
cgit v1.2.3


From 5dcddebb1b1f7638a2547d6729ca1ea501fb6834 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:26 +0200
Subject: mtd: rawnand: Kill cafe_nand_bug()

Leaving a function pointer to NULL should be enough to trigger a NULL
pointer exception, and anyway, if we want to BUG() when some missing
hooks are called, this should be done in the core, so let's drop the
cafe_nand_bug() dummy function.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cafe_nand.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index d721f489b38b..ac0be933a490 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -345,11 +345,6 @@ static irqreturn_t cafe_nand_interrupt(int irq, void *id)
 	return IRQ_HANDLED;
 }
 
-static void cafe_nand_bug(struct mtd_info *mtd)
-{
-	BUG();
-}
-
 static int cafe_nand_write_oob(struct mtd_info *mtd,
 			       struct nand_chip *chip, int page)
 {
@@ -760,9 +755,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	cafe->nand.ecc.size = mtd->writesize;
 	cafe->nand.ecc.bytes = 14;
 	cafe->nand.ecc.strength = 4;
-	cafe->nand.ecc.hwctl  = (void *)cafe_nand_bug;
-	cafe->nand.ecc.calculate = (void *)cafe_nand_bug;
-	cafe->nand.ecc.correct  = (void *)cafe_nand_bug;
 	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
 	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
 	cafe->nand.ecc.read_page = cafe_nand_read_page;
-- 
cgit v1.2.3


From a4c025372d9d4756e7be98a98f5dde302c6df562 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:27 +0200
Subject: mtd: rawnand: Remove nand_do_read() prototype from rawnand.h

nand_do_read() is a static function implemented in nand_base.c. There's
no good reason to expose its prototype in rawnand.h.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 include/linux/mtd/rawnand.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 0c6fb316b409..4d7a46c42900 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1545,8 +1545,6 @@ int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs);
 int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt);
 int nand_erase_nand(struct mtd_info *mtd, struct erase_info *instr,
 		    int allowbbt);
-int nand_do_read(struct mtd_info *mtd, loff_t from, size_t len,
-		 size_t *retlen, uint8_t *buf);
 
 /**
  * struct platform_nand_chip - chip level device structure
-- 
cgit v1.2.3


From 707329aca6e0cf5781ca7f62c39bdcb5f87e9c23 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:28 +0200
Subject: mtd: rawnand: Remove forward declaration of mtd_info

struct mtd_info is defined in linux/mtd/mtd.h which is included
at the beginning of nand_base.c, there's thus no need for the
forward declaration of mtd_info.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 include/linux/mtd/rawnand.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 4d7a46c42900..32145b302585 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -23,7 +23,6 @@
 #include <linux/mtd/bbm.h>
 #include <linux/types.h>
 
-struct mtd_info;
 struct nand_flash_dev;
 struct device_node;
 
-- 
cgit v1.2.3


From 1c3ab61ebcf8cfb5308d2e68e03fd4b4df484e62 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:29 +0200
Subject: mtd: rawnand: Remove forward declaration of device_node

struct device_node is defined in linux/of.h. Let's include this file
instead of having a forward declaration of this struct.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 include/linux/mtd/rawnand.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 32145b302585..83ab6779144e 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -21,10 +21,10 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/flashchip.h>
 #include <linux/mtd/bbm.h>
+#include <linux/of.h>
 #include <linux/types.h>
 
 struct nand_flash_dev;
-struct device_node;
 
 /* Scan and identify a NAND device */
 int nand_scan_with_ids(struct mtd_info *mtd, int max_chips,
-- 
cgit v1.2.3


From 44b07b921dea5ec997fb929ceaa82582a7415816 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:30 +0200
Subject: mtd: rawnand: Rename nand_default_bbt() into nand_create_bbt()

Rename nand_default_bbt() into nand_create_bbt() and pass it a nand_chip
object to prepare removal of the chip->scan_bbt() hook.

We add a temporary nand_default_bbt() wrapper which will be dropped
after the removal of ->scan_bbt().

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c |  5 +++++
 drivers/mtd/nand/raw/nand_bbt.c  | 10 +++++-----
 include/linux/mtd/rawnand.h      |  2 +-
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index faac82b1e058..0476e13d47b1 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -4924,6 +4924,11 @@ static void nand_shutdown(struct mtd_info *mtd)
 	nand_get_device(mtd, FL_PM_SUSPENDED);
 }
 
+static int nand_default_bbt(struct mtd_info *mtd)
+{
+	return nand_create_bbt(mtd_to_nand(mtd));
+}
+
 /* Set default functions */
 static void nand_set_defaults(struct nand_chip *chip)
 {
diff --git a/drivers/mtd/nand/raw/nand_bbt.c b/drivers/mtd/nand/raw/nand_bbt.c
index d9f4ceff2568..39db352f8757 100644
--- a/drivers/mtd/nand/raw/nand_bbt.c
+++ b/drivers/mtd/nand/raw/nand_bbt.c
@@ -1349,15 +1349,14 @@ static int nand_create_badblock_pattern(struct nand_chip *this)
 }
 
 /**
- * nand_default_bbt - [NAND Interface] Select a default bad block table for the device
- * @mtd: MTD device structure
+ * nand_create_bbt - [NAND Interface] Select a default bad block table for the device
+ * @this: NAND chip object
  *
  * This function selects the default bad block table support for the device and
  * calls the nand_scan_bbt function.
  */
-int nand_default_bbt(struct mtd_info *mtd)
+int nand_create_bbt(struct nand_chip *this)
 {
-	struct nand_chip *this = mtd_to_nand(mtd);
 	int ret;
 
 	/* Is a flash based bad block table requested? */
@@ -1383,8 +1382,9 @@ int nand_default_bbt(struct mtd_info *mtd)
 			return ret;
 	}
 
-	return nand_scan_bbt(mtd, this->badblock_pattern);
+	return nand_scan_bbt(nand_to_mtd(this), this->badblock_pattern);
 }
+EXPORT_SYMBOL(nand_create_bbt);
 
 /**
  * nand_isreserved_bbt - [NAND Interface] Check if a block is reserved
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 83ab6779144e..186f9fb1e7eb 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1538,7 +1538,7 @@ extern const struct nand_manufacturer_ops micron_nand_manuf_ops;
 extern const struct nand_manufacturer_ops amd_nand_manuf_ops;
 extern const struct nand_manufacturer_ops macronix_nand_manuf_ops;
 
-int nand_default_bbt(struct mtd_info *mtd);
+int nand_create_bbt(struct nand_chip *chip);
 int nand_markbad_bbt(struct mtd_info *mtd, loff_t offs);
 int nand_isreserved_bbt(struct mtd_info *mtd, loff_t offs);
 int nand_isbad_bbt(struct mtd_info *mtd, loff_t offs, int allowbbt);
-- 
cgit v1.2.3


From 2851b907091f2a04d19f50a5fc6a3aeed9e88dd3 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Wed, 4 Jul 2018 15:25:24 +0200
Subject: dt-bindings: marvell: Add documentation for the Armada 3700 AVS
 binding

Extend the documentation of the Armada 37xx SoC with the Adaptive Voltage
Scaling (AVS) registers.

Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 .../devicetree/bindings/arm/marvell/armada-37xx.txt       | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
index 35c3c3460d17..eddde4faef01 100644
--- a/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/armada-37xx.txt
@@ -33,3 +33,18 @@ nb_pm: syscon@14000 {
 	compatible = "marvell,armada-3700-nb-pm", "syscon";
 	reg = <0x14000 0x60>;
 }
+
+AVS
+---
+
+For AVS an other component is needed:
+
+Required properties:
+- compatible     : should contain "marvell,armada-3700-avs", "syscon";
+- reg            : the register start and length for the AVS
+
+Example:
+avs: avs@11500 {
+	compatible = "marvell,armada-3700-avs", "syscon";
+	reg = <0x11500 0x40>;
+}
-- 
cgit v1.2.3


From e80eba7581512625083ba540f120479b935425de Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:31 +0200
Subject: mtd: rawnand: Kill the chip->scan_bbt() hook

None of the existing drivers are overloading the ->scan_bbt() method,
let's get rid of it and replace calls to ->scan_bbt() by
nand_create_bbt() ones.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/diskonchip.c          | 4 ++--
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 2 +-
 drivers/mtd/nand/raw/nand_base.c           | 9 +--------
 drivers/mtd/nand/raw/nandsim.c             | 2 +-
 include/linux/mtd/rawnand.h                | 2 --
 5 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/drivers/mtd/nand/raw/diskonchip.c b/drivers/mtd/nand/raw/diskonchip.c
index 8d10061abb4b..3c46188dd6d2 100644
--- a/drivers/mtd/nand/raw/diskonchip.c
+++ b/drivers/mtd/nand/raw/diskonchip.c
@@ -1291,7 +1291,7 @@ static int __init nftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md = NULL;
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
@@ -1338,7 +1338,7 @@ static int __init inftl_scan_bbt(struct mtd_info *mtd)
 		this->bbt_md->pattern = "TBB_SYSM";
 	}
 
-	ret = this->scan_bbt(mtd);
+	ret = nand_create_bbt(this);
 	if (ret)
 		return ret;
 
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index 58d4e4a93a93..599513321e71 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -1944,7 +1944,7 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
 	ret = nand_boot_init(this);
 	if (ret)
 		goto err_nand_cleanup;
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_cleanup;
 
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 0476e13d47b1..4fa5e20d9690 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -4924,11 +4924,6 @@ static void nand_shutdown(struct mtd_info *mtd)
 	nand_get_device(mtd, FL_PM_SUSPENDED);
 }
 
-static int nand_default_bbt(struct mtd_info *mtd)
-{
-	return nand_create_bbt(mtd_to_nand(mtd));
-}
-
 /* Set default functions */
 static void nand_set_defaults(struct nand_chip *chip)
 {
@@ -4970,8 +4965,6 @@ static void nand_set_defaults(struct nand_chip *chip)
 		chip->write_byte = busw ? nand_write_byte16 : nand_write_byte;
 	if (!chip->read_buf || chip->read_buf == nand_read_buf)
 		chip->read_buf = busw ? nand_read_buf16 : nand_read_buf;
-	if (!chip->scan_bbt)
-		chip->scan_bbt = nand_default_bbt;
 
 	if (!chip->controller) {
 		chip->controller = &chip->hwcontrol;
@@ -6673,7 +6666,7 @@ int nand_scan_tail(struct mtd_info *mtd)
 		return 0;
 
 	/* Build bad block table */
-	ret = chip->scan_bbt(mtd);
+	ret = nand_create_bbt(chip);
 	if (ret)
 		goto err_nand_manuf_cleanup;
 
diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index f8edacde49ab..8a3b36cfe5ea 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2337,7 +2337,7 @@ static int __init ns_init_module(void)
 	if ((retval = init_nandsim(nsmtd)) != 0)
 		goto err_exit;
 
-	if ((retval = chip->scan_bbt(nsmtd)) != 0)
+	if ((retval = nand_create_bbt(chip)) != 0)
 		goto err_exit;
 
 	if ((retval = parse_badblocks(nand, nsmtd)) != 0)
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 186f9fb1e7eb..ac0007ddadf2 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1199,7 +1199,6 @@ int nand_op_parser_exec_op(struct nand_chip *chip,
  * @buf_align:		minimum buffer alignment required by a platform
  * @hwcontrol:		platform-specific hardware control structure
  * @erase:		[REPLACEABLE] erase function
- * @scan_bbt:		[REPLACEABLE] function to scan bad block table
  * @chip_delay:		[BOARDSPECIFIC] chip dependent delay for transferring
  *			data from array to read regs (tR).
  * @state:		[INTERN] the current state of the NAND device
@@ -1292,7 +1291,6 @@ struct nand_chip {
 		       const struct nand_operation *op,
 		       bool check_only);
 	int (*erase)(struct mtd_info *mtd, int page);
-	int (*scan_bbt)(struct mtd_info *mtd);
 	int (*set_features)(struct mtd_info *mtd, struct nand_chip *chip,
 			    int feature_addr, uint8_t *subfeature_para);
 	int (*get_features)(struct mtd_info *mtd, struct nand_chip *chip,
-- 
cgit v1.2.3


From f0f01838f76420988b50b23f315704c9a5cd2fa9 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:32 +0200
Subject: mtd: rawnand: orion_nand: Kill orion_nand_data.dev_ready()

None of the boards seem to overload the ->dev_ready() hook, just drop
this field from orion_nand_data.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/orion_nand.c            | 3 ---
 include/linux/platform_data/mtd-orion_nand.h | 1 -
 2 files changed, 4 deletions(-)

diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 7825fd3ce66b..1a4828442675 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -153,9 +153,6 @@ static int __init orion_nand_probe(struct platform_device *pdev)
 	if (board->width == 16)
 		nc->options |= NAND_BUSWIDTH_16;
 
-	if (board->dev_ready)
-		nc->dev_ready = board->dev_ready;
-
 	platform_set_drvdata(pdev, info);
 
 	/* Not all platforms can gate the clock, so it is not
diff --git a/include/linux/platform_data/mtd-orion_nand.h b/include/linux/platform_data/mtd-orion_nand.h
index a7ce77c7c1a8..34828eb85982 100644
--- a/include/linux/platform_data/mtd-orion_nand.h
+++ b/include/linux/platform_data/mtd-orion_nand.h
@@ -12,7 +12,6 @@
  */
 struct orion_nand_data {
 	struct mtd_partition *parts;
-	int (*dev_ready)(struct mtd_info *mtd);
 	u32 nr_parts;
 	u8 ale;		/* address line number connected to ALE */
 	u8 cle;		/* address line number connected to CLE */
-- 
cgit v1.2.3


From dc2d8856a758627d4f126d17bc113eedd72b2d60 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 5 Jul 2018 12:27:33 +0200
Subject: mtd: rawnand: plat_nand: Kill pdata->ctrl.{hwcontrol, read_byte}()

None of the board files are overloading those hooks, so let's drop them
from struct platform_nand_ctrl.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 arch/arm/mach-pxa/balloon3.c     | 1 -
 arch/arm/mach-pxa/em-x270.c      | 1 -
 drivers/mtd/nand/raw/plat_nand.c | 2 --
 include/linux/mtd/rawnand.h      | 4 ----
 4 files changed, 8 deletions(-)

diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index f4f8f23bda8c..af46d2182533 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -688,7 +688,6 @@ struct platform_nand_data balloon3_nand_pdata = {
 		.chip_delay	= 50,
 	},
 	.ctrl = {
-		.hwcontrol	= 0,
 		.dev_ready	= balloon3_nand_dev_ready,
 		.select_chip	= balloon3_nand_select_chip,
 		.cmd_ctrl	= balloon3_nand_cmd_ctl,
diff --git a/arch/arm/mach-pxa/em-x270.c b/arch/arm/mach-pxa/em-x270.c
index 49022ad338e9..29be04c6cc48 100644
--- a/arch/arm/mach-pxa/em-x270.c
+++ b/arch/arm/mach-pxa/em-x270.c
@@ -346,7 +346,6 @@ struct platform_nand_data em_x270_nand_platdata = {
 		.chip_delay = 20,
 	},
 	.ctrl = {
-		.hwcontrol = 0,
 		.dev_ready = em_x270_nand_device_ready,
 		.select_chip = 0,
 		.cmd_ctrl = em_x270_nand_cmd_ctl,
diff --git a/drivers/mtd/nand/raw/plat_nand.c b/drivers/mtd/nand/raw/plat_nand.c
index 925a1323604d..222626df4b96 100644
--- a/drivers/mtd/nand/raw/plat_nand.c
+++ b/drivers/mtd/nand/raw/plat_nand.c
@@ -67,12 +67,10 @@ static int plat_nand_probe(struct platform_device *pdev)
 	data->chip.select_chip = pdata->ctrl.select_chip;
 	data->chip.write_buf = pdata->ctrl.write_buf;
 	data->chip.read_buf = pdata->ctrl.read_buf;
-	data->chip.read_byte = pdata->ctrl.read_byte;
 	data->chip.chip_delay = pdata->chip.chip_delay;
 	data->chip.options |= pdata->chip.options;
 	data->chip.bbt_options |= pdata->chip.bbt_options;
 
-	data->chip.ecc.hwctl = pdata->ctrl.hwcontrol;
 	data->chip.ecc.mode = NAND_ECC_SOFT;
 	data->chip.ecc.algo = NAND_ECC_HAMMING;
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index ac0007ddadf2..11c2426fc363 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1572,14 +1572,12 @@ struct platform_device;
  * struct platform_nand_ctrl - controller level device structure
  * @probe:		platform specific function to probe/setup hardware
  * @remove:		platform specific function to remove/teardown hardware
- * @hwcontrol:		platform specific hardware control structure
  * @dev_ready:		platform specific function to read ready/busy pin
  * @select_chip:	platform specific chip select function
  * @cmd_ctrl:		platform specific function for controlling
  *			ALE/CLE/nCE. Also used to write command and address
  * @write_buf:		platform specific function for write buffer
  * @read_buf:		platform specific function for read buffer
- * @read_byte:		platform specific function to read one byte from chip
  * @priv:		private data to transport driver specific settings
  *
  * All fields are optional and depend on the hardware driver requirements
@@ -1587,13 +1585,11 @@ struct platform_device;
 struct platform_nand_ctrl {
 	int (*probe)(struct platform_device *pdev);
 	void (*remove)(struct platform_device *pdev);
-	void (*hwcontrol)(struct mtd_info *mtd, int cmd);
 	int (*dev_ready)(struct mtd_info *mtd);
 	void (*select_chip)(struct mtd_info *mtd, int chip);
 	void (*cmd_ctrl)(struct mtd_info *mtd, int dat, unsigned int ctrl);
 	void (*write_buf)(struct mtd_info *mtd, const uint8_t *buf, int len);
 	void (*read_buf)(struct mtd_info *mtd, uint8_t *buf, int len);
-	unsigned char (*read_byte)(struct mtd_info *mtd);
 	void *priv;
 };
 
-- 
cgit v1.2.3


From b04a3fe3143d23e8e450fe8b36868c6e99d5bdd0 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Sat, 7 Jul 2018 14:25:20 -0300
Subject: mtd: rawnand: gpmi: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c  | 15 +--------------
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 15 +--------------
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h | 11 +----------
 3 files changed, 3 insertions(+), 38 deletions(-)

diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
index 83697b8df871..88ea2203e263 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-lib.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2008-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/delay.h>
 #include <linux/clk.h>
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index 599513321e71..6294d018df65 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -1,22 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2015 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
  */
 #include <linux/clk.h>
 #include <linux/slab.h>
diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
index 6aa10d6962d6..69cd0cbde4f2 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.h
@@ -1,18 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Freescale GPMI NAND Flash Driver
  *
  * Copyright (C) 2010-2011 Freescale Semiconductor, Inc.
  * Copyright (C) 2008 Embedded Alley Solutions, Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef __DRIVERS_MTD_NAND_GPMI_NAND_H
 #define __DRIVERS_MTD_NAND_GPMI_NAND_H
-- 
cgit v1.2.3


From c786bbcc1a2c15db29a2acb33d8a53e19a57d20d Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Sat, 7 Jul 2018 14:25:21 -0300
Subject: mtd: rawnand: mxc: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/mxc_nand.c | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index 14ec7d975593..c6eff61e909d 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1,20 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Copyright 2004-2007 Freescale Semiconductor, Inc. All Rights Reserved.
  * Copyright 2008 Sascha Hauer, kernel@pengutronix.de
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version 2
- * of the License, or (at your option) any later version.
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
- * MA 02110-1301, USA.
  */
 
 #include <linux/delay.h>
-- 
cgit v1.2.3


From bd9c3f9b3c00da322b5e784e820533f1598f690a Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Sun, 8 Jul 2018 02:10:06 +0200
Subject: mtd: rawnand: marvell: add suspend and resume hooks

This patch restores the suspend and resume hooks that the old driver used
to have. Apart from stopping and starting the clocks, the resume callback
also nullifies the selected_chip pointer, so the next command that is issued
will re-select the chip and thereby restore the timing registers.

Factor out some code from marvell_nfc_init() into a new function
marvell_nfc_reset() and also call it at resume time to reset some registers
that don't retain their contents during low-power mode.

Without this patch, a PXA3xx based system would cough up an error similar to
the one below after resume.

[   44.660162] marvell-nfc 43100000.nand-controller: Timeout waiting for  RB signal
[   44.671492] ubi0 error: ubi_io_write: error -110 while writing 2048 bytes to PEB 102:38912, written 0 bytes
[   44.682887] CPU: 0 PID: 1417 Comm: remote-control Not tainted 4.18.0-rc2+ #344
[   44.691197] Hardware name: Marvell PXA3xx (Device Tree Support)
[   44.697111] Backtrace:
[   44.699593] [<c0106458>] (dump_backtrace) from [<c0106718>] (show_stack+0x18/0x1c)
[   44.708931]  r7:00000800 r6:00009800 r5:00000066 r4:c6139000
[   44.715833] [<c0106700>] (show_stack) from [<c0678a60>] (dump_stack+0x20/0x28)
[   44.724206] [<c0678a40>] (dump_stack) from [<c0456cbc>] (ubi_io_write+0x3d4/0x630)
[   44.732925] [<c04568e8>] (ubi_io_write) from [<c0454428>] (ubi_eba_write_leb+0x690/0x6fc)
...

Fixes: 02f26ecf8c77 ("mtd: nand: add reworked Marvell NAND controller driver")
Cc: stable@vger.kernel.org
Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/marvell_nand.c | 73 +++++++++++++++++++++++++++++++------
 1 file changed, 62 insertions(+), 11 deletions(-)

diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index ba6889bbe802..96c74bfc5a39 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2678,6 +2678,21 @@ static int marvell_nfc_init_dma(struct marvell_nfc *nfc)
 	return 0;
 }
 
+static void marvell_nfc_reset(struct marvell_nfc *nfc)
+{
+	/*
+	 * ECC operations and interruptions are only enabled when specifically
+	 * needed. ECC shall not be activated in the early stages (fails probe).
+	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
+	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
+	 * offset in the read page and this will fail the protection.
+	 */
+	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
+		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
+	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
+	writel_relaxed(0, nfc->regs + NDECCCTRL);
+}
+
 static int marvell_nfc_init(struct marvell_nfc *nfc)
 {
 	struct device_node *np = nfc->dev->of_node;
@@ -2716,17 +2731,7 @@ static int marvell_nfc_init(struct marvell_nfc *nfc)
 	if (!nfc->caps->is_nfcv2)
 		marvell_nfc_init_dma(nfc);
 
-	/*
-	 * ECC operations and interruptions are only enabled when specifically
-	 * needed. ECC shall not be activated in the early stages (fails probe).
-	 * Arbiter flag, even if marked as "reserved", must be set (empirical).
-	 * SPARE_EN bit must always be set or ECC bytes will not be at the same
-	 * offset in the read page and this will fail the protection.
-	 */
-	writel_relaxed(NDCR_ALL_INT | NDCR_ND_ARB_EN | NDCR_SPARE_EN |
-		       NDCR_RD_ID_CNT(NFCV1_READID_LEN), nfc->regs + NDCR);
-	writel_relaxed(0xFFFFFFFF, nfc->regs + NDSR);
-	writel_relaxed(0, nfc->regs + NDECCCTRL);
+	marvell_nfc_reset(nfc);
 
 	return 0;
 }
@@ -2841,6 +2846,51 @@ static int marvell_nfc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused marvell_nfc_suspend(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	struct marvell_nand_chip *chip;
+
+	list_for_each_entry(chip, &nfc->chips, node)
+		marvell_nfc_wait_ndrun(&chip->chip);
+
+	clk_disable_unprepare(nfc->reg_clk);
+	clk_disable_unprepare(nfc->core_clk);
+
+	return 0;
+}
+
+static int __maybe_unused marvell_nfc_resume(struct device *dev)
+{
+	struct marvell_nfc *nfc = dev_get_drvdata(dev);
+	int ret;
+
+	ret = clk_prepare_enable(nfc->core_clk);
+	if (ret < 0)
+		return ret;
+
+	if (!IS_ERR(nfc->reg_clk)) {
+		ret = clk_prepare_enable(nfc->reg_clk);
+		if (ret < 0)
+			return ret;
+	}
+
+	/*
+	 * Reset nfc->selected_chip so the next command will cause the timing
+	 * registers to be restored in marvell_nfc_select_chip().
+	 */
+	nfc->selected_chip = NULL;
+
+	/* Reset registers that have lost their contents */
+	marvell_nfc_reset(nfc);
+
+	return 0;
+}
+
+static const struct dev_pm_ops marvell_nfc_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(marvell_nfc_suspend, marvell_nfc_resume)
+};
+
 static const struct marvell_nfc_caps marvell_armada_8k_nfc_caps = {
 	.max_cs_nb = 4,
 	.max_rb_nb = 2,
@@ -2925,6 +2975,7 @@ static struct platform_driver marvell_nfc_driver = {
 	.driver	= {
 		.name		= "marvell-nfc",
 		.of_match_table = marvell_nfc_of_ids,
+		.pm		= &marvell_nfc_pm_ops,
 	},
 	.id_table = marvell_nfc_platform_ids,
 	.probe = marvell_nfc_probe,
-- 
cgit v1.2.3


From 7734a275a7eebf11878a923dc102908eff0f0657 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Sun, 8 Jul 2018 02:10:07 +0200
Subject: mtd: rawnand: marvell: remove bogus comment in
 marvell_nfc_select_chip()

The comment in marvell_nfc_select_chip() about ndtr0 and ndtr1 didn't
reflect what the driver was doing.

The values of NDTR0 and NDTR1 are read from the registers at probe time
and a copy is retained in 'struct marvell_nand_chip'. If keep-config is
set in the DT properties, there are no other writers of these timing
variables so they can safely be used when the chip is selected.

As suggested by Miquel Raynal, simply remove the comment.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/marvell_nand.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index 96c74bfc5a39..638a0c8b44b8 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -650,11 +650,6 @@ static void marvell_nfc_select_chip(struct mtd_info *mtd, int die_nr)
 		return;
 	}
 
-	/*
-	 * Do not change the timing registers when using the DT property
-	 * marvell,nand-keep-config; in that case ->ndtr0 and ->ndtr1 from the
-	 * marvell_nand structure are supposedly empty.
-	 */
 	writel_relaxed(marvell_nand->ndtr0, nfc->regs + NDTR0);
 	writel_relaxed(marvell_nand->ndtr1, nfc->regs + NDTR1);
 
-- 
cgit v1.2.3


From f9e64d61042575960ce868fa974d9dbe4937c59a Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Sun, 8 Jul 2018 02:10:08 +0200
Subject: mtd: rawnand: marvell: set reg_clk to NULL if it can't be obtained

Don't keep an error-pointer around in the private struct. If this optional
clock can't be obtained, simply set the pointer to NULL instead so we can
use clk_prepare_enable() on it without further checks,

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/marvell_nand.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index 638a0c8b44b8..80a074cccb82 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2773,17 +2773,19 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return ret;
 
 	nfc->reg_clk = devm_clk_get(&pdev->dev, "reg");
-	if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
-		if (!IS_ERR(nfc->reg_clk)) {
-			ret = clk_prepare_enable(nfc->reg_clk);
-			if (ret)
-				goto unprepare_core_clk;
-		} else {
+	if (IS_ERR(nfc->reg_clk)) {
+		if (PTR_ERR(nfc->reg_clk) != -ENOENT) {
 			ret = PTR_ERR(nfc->reg_clk);
 			goto unprepare_core_clk;
 		}
+
+		nfc->reg_clk = NULL;
 	}
 
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret)
+		goto unprepare_core_clk;
+
 	marvell_nfc_disable_int(nfc, NDCR_ALL_INT);
 	marvell_nfc_clear_int(nfc, NDCR_ALL_INT);
 	ret = devm_request_irq(dev, irq, marvell_nfc_isr,
@@ -2864,11 +2866,9 @@ static int __maybe_unused marvell_nfc_resume(struct device *dev)
 	if (ret < 0)
 		return ret;
 
-	if (!IS_ERR(nfc->reg_clk)) {
-		ret = clk_prepare_enable(nfc->reg_clk);
-		if (ret < 0)
-			return ret;
-	}
+	ret = clk_prepare_enable(nfc->reg_clk);
+	if (ret < 0)
+		return ret;
 
 	/*
 	 * Reset nfc->selected_chip so the next command will cause the timing
-- 
cgit v1.2.3


From 20366e19e28f9954b25580c020d7a4e0db6055c4 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 4 Jul 2018 16:08:58 +0200
Subject: mtd: rawnand: hynix: Use ->exec_op() in hynix_nand_reg_write_op()

Modern NAND controller drivers implement ->exec_op() instead of
->cmdfunc(), make sure we don't end up with a NULL pointer dereference
when hynix_nand_reg_write_op() is called.

Fixes: 8878b126df76 ("mtd: nand: add ->exec_op() implementation")
Cc: <stable@vger.kernel.org>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_hynix.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/mtd/nand/raw/nand_hynix.c b/drivers/mtd/nand/raw/nand_hynix.c
index 8cbe77f447c7..4ffbb26e76d6 100644
--- a/drivers/mtd/nand/raw/nand_hynix.c
+++ b/drivers/mtd/nand/raw/nand_hynix.c
@@ -100,6 +100,16 @@ static int hynix_nand_reg_write_op(struct nand_chip *chip, u8 addr, u8 val)
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	u16 column = ((u16)addr << 8) | addr;
 
+	if (chip->exec_op) {
+		struct nand_op_instr instrs[] = {
+			NAND_OP_ADDR(1, &addr, 0),
+			NAND_OP_8BIT_DATA_OUT(1, &val, 0),
+		};
+		struct nand_operation op = NAND_OPERATION(instrs);
+
+		return nand_exec_op(chip, &op);
+	}
+
 	chip->cmdfunc(mtd, NAND_CMD_NONE, column, -1);
 	chip->write_byte(mtd, val);
 
-- 
cgit v1.2.3


From e6848511d06189cd28f83e5aef580510699fb2b4 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:22 +0200
Subject: mtd: rawnand: atmel: Use uintptr_t casts instead of unsigned int

When casting a pointer to an unsigned int, uintptr_t should be used to
cope with the pointer size differences between 32-bit and 64-bit
architectures.

This is needed if we want to allow compilation of this driver when
COMPILE_TEST=y.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index e686fe73159e..e8f7549d0354 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -2050,7 +2050,7 @@ atmel_smc_nand_controller_init(struct atmel_smc_nand_controller *nc)
 		return ret;
 	}
 
-	nc->ebi_csa_offs = (unsigned int)match->data;
+	nc->ebi_csa_offs = (uintptr_t)match->data;
 
 	/*
 	 * The at91sam9263 has 2 EBIs, if the NAND controller is under EBI1
-- 
cgit v1.2.3


From d28395c9083de4ee03e51b804d7acc591191bb00 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:23 +0200
Subject: mtd: rawnand: atmel: Add an __iomem cast on gen_pool_dma_alloc() call

gen_pool_dma_alloc() return type is void *, while internally, the
memory region exposed by the sram driver has been mapped with
ioremap().

Add a void * to void __iomem * cast to make sparse happy.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index e8f7549d0354..30dae4c9d439 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -2219,9 +2219,9 @@ atmel_hsmc_nand_controller_init(struct atmel_hsmc_nand_controller *nc)
 		return -ENOMEM;
 	}
 
-	nc->sram.virt = gen_pool_dma_alloc(nc->sram.pool,
-					    ATMEL_NFC_SRAM_SIZE,
-					    &nc->sram.dma);
+	nc->sram.virt = (void __iomem *)gen_pool_dma_alloc(nc->sram.pool,
+							   ATMEL_NFC_SRAM_SIZE,
+							   &nc->sram.dma);
 	if (!nc->sram.virt) {
 		dev_err(nc->base.dev,
 			"Could not allocate memory from the NFC SRAM pool\n");
-- 
cgit v1.2.3


From 88a40e7dca00fef96e4396c3e8c0077ab96b15a6 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:24 +0200
Subject: mtd: rawnand: atmel: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_AT91 enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 230311fa2cc0..1488ad0a0199 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -277,7 +277,8 @@ config MTD_NAND_CS553X
 
 config MTD_NAND_ATMEL
 	tristate "Support for NAND Flash / SmartMedia on AT91"
-	depends on ARCH_AT91
+	depends on ARCH_AT91 || COMPILE_TEST
+	depends on HAS_IOMEM
 	select MFD_ATMEL_SMC
 	help
 	  Enables support for NAND Flash / Smart Media Card interface
-- 
cgit v1.2.3


From c5b76d8dd2bf318d9e6b4b3a480b9e96c01b31c8 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:28 +0200
Subject: mtd: rawnand: davinci: Stop doing iomem pointer <-> u32 conversions

There is no point in doing this sort of conversion since we can
replace |= by += operations which are perfectly valid on pointers.

This is done in preparation of COMPILE_TEST addition to the NAND_DAVINCI
Kconfig entry, since building for x86 generates several warnings because
of inappropriate u32 <-> void * conversions (pointers are 64-bit large
on x86_64).

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/davinci_nand.c | 23 ++++++++++-------------
 1 file changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index cd12e5abafde..9cd36a750965 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -60,8 +60,7 @@ struct davinci_nand_info {
 	void __iomem		*base;
 	void __iomem		*vaddr;
 
-	uint32_t		ioaddr;
-	uint32_t		current_cs;
+	void __iomem		*current_cs;
 
 	uint32_t		mask_chipsel;
 	uint32_t		mask_ale;
@@ -102,17 +101,17 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 				   unsigned int ctrl)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->current_cs;
+	void __iomem			*addr = info->current_cs;
 	struct nand_chip		*nand = mtd_to_nand(mtd);
 
 	/* Did the control lines change? */
 	if (ctrl & NAND_CTRL_CHANGE) {
 		if ((ctrl & NAND_CTRL_CLE) == NAND_CTRL_CLE)
-			addr |= info->mask_cle;
+			addr += info->mask_cle;
 		else if ((ctrl & NAND_CTRL_ALE) == NAND_CTRL_ALE)
-			addr |= info->mask_ale;
+			addr += info->mask_ale;
 
-		nand->IO_ADDR_W = (void __iomem __force *)addr;
+		nand->IO_ADDR_W = addr;
 	}
 
 	if (cmd != NAND_CMD_NONE)
@@ -122,14 +121,14 @@ static void nand_davinci_hwcontrol(struct mtd_info *mtd, int cmd,
 static void nand_davinci_select_chip(struct mtd_info *mtd, int chip)
 {
 	struct davinci_nand_info	*info = to_davinci_nand(mtd);
-	uint32_t			addr = info->ioaddr;
+
+	info->current_cs = info->vaddr;
 
 	/* maybe kick in a second chipselect */
 	if (chip > 0)
-		addr |= info->mask_chipsel;
-	info->current_cs = addr;
+		info->current_cs += info->mask_chipsel;
 
-	info->chip.IO_ADDR_W = (void __iomem __force *)addr;
+	info->chip.IO_ADDR_W = info->current_cs;
 	info->chip.IO_ADDR_R = info->chip.IO_ADDR_W;
 }
 
@@ -680,9 +679,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	info->chip.bbt_md	= pdata->bbt_md;
 	info->timing		= pdata->timing;
 
-	info->ioaddr		= (uint32_t __force) vaddr;
-
-	info->current_cs	= info->ioaddr;
+	info->current_cs	= info->vaddr;
 	info->core_chipsel	= pdata->core_chipsel;
 	info->mask_chipsel	= pdata->mask_chipsel;
 
-- 
cgit v1.2.3


From cc53d5ca38c02e05efd20ba8af1759d1005aa454 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:29 +0200
Subject: mtd: rawnand: davinci: Use uintptr_t casts instead of unsigned ones

uintptr_t should be used when casting a pointer to an unsigned int so
that the code compiles without warnings even on 64-bit architectures.

This is needed if we want to allow selection of this driver when
COMPILE_TEST=y.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/davinci_nand.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 9cd36a750965..e79ed0f60ade 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -318,7 +318,7 @@ static int nand_davinci_correct_4bit(struct mtd_info *mtd,
 	/* Unpack ten bytes into eight 10 bit values.  We know we're
 	 * little-endian, and use type punning for less shifting/masking.
 	 */
-	if (WARN_ON(0x01 & (unsigned) ecc_code))
+	if (WARN_ON(0x01 & (uintptr_t)ecc_code))
 		return -EINVAL;
 	ecc16 = (unsigned short *)ecc_code;
 
@@ -440,9 +440,9 @@ static void nand_davinci_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		ioread32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		ioread16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		ioread8_rep(chip->IO_ADDR_R, buf, len);
@@ -453,9 +453,9 @@ static void nand_davinci_write_buf(struct mtd_info *mtd,
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 
-	if ((0x03 & ((unsigned)buf)) == 0 && (0x03 & len) == 0)
+	if ((0x03 & ((uintptr_t)buf)) == 0 && (0x03 & len) == 0)
 		iowrite32_rep(chip->IO_ADDR_R, buf, len >> 2);
-	else if ((0x01 & ((unsigned)buf)) == 0 && (0x01 & len) == 0)
+	else if ((0x01 & ((uintptr_t)buf)) == 0 && (0x01 & len) == 0)
 		iowrite16_rep(chip->IO_ADDR_R, buf, len >> 1);
 	else
 		iowrite8_rep(chip->IO_ADDR_R, buf, len);
-- 
cgit v1.2.3


From d3691813b05c654342fd01dfe3fff9a72828ebe7 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jul 2018 09:04:12 +0200
Subject: mtd: rawnand: fix indentation in Kconfig

Rules about Kconfig are simple but in the raw NAND directory indentation
is somehow archaic. Fix the indentation in the whole file.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 94 ++++++++++++++++++++++----------------------
 1 file changed, 47 insertions(+), 47 deletions(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 1488ad0a0199..2460fc19bfa9 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -44,12 +44,12 @@ config MTD_NAND_DENALI
 	tristate
 
 config MTD_NAND_DENALI_PCI
-        tristate "Support Denali NAND controller on Intel Moorestown"
+	tristate "Support Denali NAND controller on Intel Moorestown"
 	select MTD_NAND_DENALI
 	depends on PCI
-        help
-          Enable the driver for NAND flash on Intel Moorestown, using the
-          Denali NAND controller core.
+	help
+	  Enable the driver for NAND flash on Intel Moorestown, using the
+	  Denali NAND controller core.
 
 config MTD_NAND_DENALI_DT
 	tristate "Support Denali NAND controller as a DT device"
@@ -80,7 +80,7 @@ config MTD_NAND_OMAP2
 	depends on ARCH_OMAP2PLUS || ARCH_KEYSTONE || COMPILE_TEST
 	depends on HAS_IOMEM
 	help
-          Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
+	  Support for NAND flash on Texas Instruments OMAP2, OMAP3, OMAP4
 	  and Keystone platforms.
 
 config MTD_NAND_OMAP_BCH
@@ -138,7 +138,7 @@ config MTD_NAND_NDFC
 	depends on 4xx
 	select MTD_NAND_ECC_SMC
 	help
-	 NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
+	  NDFC Nand Flash Controllers are integrated in IBM/AMCC's 4xx SoCs
 
 config MTD_NAND_S3C2410_CLKSTOP
 	bool "Samsung S3C NAND IDLE clock stop"
@@ -170,40 +170,40 @@ config MTD_NAND_DISKONCHIP
 	  these devices.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        bool "Advanced detection options for DiskOnChip"
-        depends on MTD_NAND_DISKONCHIP
-        help
-          This option allows you to specify nonstandard address at which to
-          probe for a DiskOnChip, or to change the detection options.  You
-          are unlikely to need any of this unless you are using LinuxBIOS.
-          Say 'N'.
+	bool "Advanced detection options for DiskOnChip"
+	depends on MTD_NAND_DISKONCHIP
+	help
+	  This option allows you to specify nonstandard address at which to
+	  probe for a DiskOnChip, or to change the detection options.  You
+	  are unlikely to need any of this unless you are using LinuxBIOS.
+	  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_PROBE_ADDRESS
-        hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        depends on MTD_NAND_DISKONCHIP
-        default "0"
-        ---help---
-        By default, the probe for DiskOnChip devices will look for a
-        DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-        This option allows you to specify a single address at which to probe
-        for the device, which is useful if you have other devices in that
-        range which get upset when they are probed.
-
-        (Note that on PowerPC, the normal probe will only check at
-        0xE4000000.)
-
-        Normally, you should leave this set to zero, to allow the probe at
-        the normal addresses.
+	hex "Physical address of DiskOnChip" if MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	depends on MTD_NAND_DISKONCHIP
+	default "0"
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option allows you to specify a single address at which to probe
+	  for the device, which is useful if you have other devices in that
+	  range which get upset when they are probed.
+
+	  (Note that on PowerPC, the normal probe will only check at
+	  0xE4000000.)
+
+	  Normally, you should leave this set to zero, to allow the probe at
+	  the normal addresses.
 
 config MTD_NAND_DISKONCHIP_PROBE_HIGH
-        bool "Probe high addresses"
-        depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
-        help
-          By default, the probe for DiskOnChip devices will look for a
-          DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
-          This option changes to make it probe between 0xFFFC8000 and
-          0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
-          useful to you.  Say 'N'.
+	bool "Probe high addresses"
+	depends on MTD_NAND_DISKONCHIP_PROBE_ADVANCED
+	help
+	  By default, the probe for DiskOnChip devices will look for a
+	  DiskOnChip at every multiple of 0x2000 between 0xC8000 and 0xEE000.
+	  This option changes to make it probe between 0xFFFC8000 and
+	  0xFFFEE000.  Unless you are using LinuxBIOS, this is unlikely to be
+	  useful to you.  Say 'N'.
 
 config MTD_NAND_DISKONCHIP_BBTWRITE
 	bool "Allow BBT writes on DiskOnChip Millennium and 2000TSOP"
@@ -345,13 +345,13 @@ config MTD_NAND_NANDSIM
 	  MTD nand layer.
 
 config MTD_NAND_GPMI_NAND
-        tristate "GPMI NAND Flash Controller driver"
-        depends on MXS_DMA
-        help
-	 Enables NAND Flash support for IMX23, IMX28 or IMX6.
-	 The GPMI controller is very powerful, with the help of BCH
-	 module, it can do the hardware ECC. The GPMI supports several
-	 NAND flashs at the same time.
+	tristate "GPMI NAND Flash Controller driver"
+	depends on MXS_DMA
+	help
+	  Enables NAND Flash support for IMX23, IMX28 or IMX6.
+	  The GPMI controller is very powerful, with the help of BCH
+	  module, it can do the hardware ECC. The GPMI supports several
+	  NAND flashs at the same time.
 
 config MTD_NAND_BRCMNAND
 	tristate "Broadcom STB NAND controller"
@@ -459,9 +459,9 @@ config MTD_NAND_SH_FLCTL
 	  for NAND Flash using FLCTL.
 
 config MTD_NAND_DAVINCI
-        tristate "Support NAND on DaVinci/Keystone SoC"
-        depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF)
-        help
+	tristate "Support NAND on DaVinci/Keystone SoC"
+	depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF)
+	help
 	  Enable the driver for NAND flash chips on Texas Instruments
 	  DaVinci/Keystone processors.
 
@@ -489,7 +489,7 @@ config MTD_NAND_JZ4740
 	tristate "Support for JZ4740 SoC NAND controller"
 	depends on MACH_JZ4740
 	help
-		Enables support for NAND Flash on JZ4740 SoC based boards.
+	  Enables support for NAND Flash on JZ4740 SoC based boards.
 
 config MTD_NAND_JZ4780
 	tristate "Support for NAND on JZ4780 SoC"
-- 
cgit v1.2.3


From b9221470b081c4dc52de859d47e2431e76b1fac2 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:30 +0200
Subject: mtd: rawnand: davinci: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_DAVINCI or ARCH_KEYSTONE
enabled.

We also need to add a dependency on HAS_IOMEM to make sure the
driver compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 2460fc19bfa9..524684239fdb 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -460,7 +460,8 @@ config MTD_NAND_SH_FLCTL
 
 config MTD_NAND_DAVINCI
 	tristate "Support NAND on DaVinci/Keystone SoC"
-	depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF)
+	depends on ARCH_DAVINCI || (ARCH_KEYSTONE && TI_AEMIF) || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enable the driver for NAND flash chips on Texas Instruments
 	  DaVinci/Keystone processors.
-- 
cgit v1.2.3


From cf3e3fd2e94f4648f17fbd5e0e26409d5d1face9 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:31 +0200
Subject: mtd: rawnand: sunxi: Add an U suffix to NFC_PAGE_OP definition

Fixes the "warning: large integer implicitly truncated to unsigned type
[-Woverflow]" warning when compiled for x86.

This is needed in order to allow compiling this driver when
COMPILE_TEST=y.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/sunxi_nand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index d831a141a196..99043c3a4fa7 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -127,7 +127,7 @@
 #define NFC_CMD_TYPE_MSK	GENMASK(31, 30)
 #define NFC_NORMAL_OP		(0 << 30)
 #define NFC_ECC_OP		(1 << 30)
-#define NFC_PAGE_OP		(2 << 30)
+#define NFC_PAGE_OP		(2U << 30)
 
 /* define bit use in NFC_RCMD_SET */
 #define NFC_READ_CMD_MSK	GENMASK(7, 0)
-- 
cgit v1.2.3


From 06c8b5dc938117866460ee95b79318847dbde209 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:32 +0200
Subject: mtd: rawnand: sunxi: Make sure ret is initialized in
 sunxi_nfc_read_byte()

Fixes the following smatch warning:

drivers/mtd/nand/raw/sunxi_nand.c:551 sunxi_nfc_read_byte() error: uninitialized symbol 'ret'.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/sunxi_nand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 99043c3a4fa7..4b11cd4a79be 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -544,7 +544,7 @@ static void sunxi_nfc_write_buf(struct mtd_info *mtd, const uint8_t *buf,
 
 static uint8_t sunxi_nfc_read_byte(struct mtd_info *mtd)
 {
-	uint8_t ret;
+	uint8_t ret = 0;
 
 	sunxi_nfc_read_buf(mtd, &ret, 1);
 
-- 
cgit v1.2.3


From e37db6df41f5d45e43d5544b2cfadeed1710f086 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:33 +0200
Subject: mtd: rawnand: sunxi: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having ARCH_SUNXI enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 524684239fdb..cd9eb60faff6 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -516,7 +516,8 @@ config MTD_NAND_XWAY
 
 config MTD_NAND_SUNXI
 	tristate "Support for NAND on Allwinner SoCs"
-	depends on ARCH_SUNXI
+	depends on ARCH_SUNXI || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND Flash chips on Allwinner SoCs.
 
-- 
cgit v1.2.3


From 8f3931ed975e1d775b87ce85d65ecacd54138359 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:34 +0200
Subject: mtd: rawnand: fscm: Avoid collision on PC def when compiling for MIPS

We want to allow this driver to be selected when COMPILE_TEST=y, this
means the driver can be compiled for any arch, including MIPS. When
compiling this driver for MIPS, we end up with a collision on the 'PC'
macro definition (also defined in arch/mips/include/asm/ptrace.h).

Prefix the fsmc one with FSMC_ to avoid this problem.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/fsmc_nand.c | 29 +++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index f4a5a317d4ae..d71c49f50e77 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -62,7 +62,7 @@
 						reg)
 
 /* fsmc controller registers for NAND flash */
-#define PC			0x00
+#define FSMC_PC			0x00
 	/* pc register definitions */
 	#define FSMC_RESET		(1 << 0)
 	#define FSMC_WAITON		(1 << 1)
@@ -273,12 +273,13 @@ static void fsmc_nand_setup(struct fsmc_nand_data *host,
 	tset = (tims->tset & FSMC_TSET_MASK) << FSMC_TSET_SHIFT;
 
 	if (host->nand.options & NAND_BUSWIDTH_16)
-		writel_relaxed(value | FSMC_DEVWID_16, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_16,
+			       host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + PC);
+		writel_relaxed(value | FSMC_DEVWID_8, host->regs_va + FSMC_PC);
 
-	writel_relaxed(readl(host->regs_va + PC) | tclr | tar,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | tclr | tar,
+		       host->regs_va + FSMC_PC);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + COMM);
 	writel_relaxed(thiz | thold | twait | tset, host->regs_va + ATTRIB);
 }
@@ -371,12 +372,12 @@ static void fsmc_enable_hwecc(struct mtd_info *mtd, int mode)
 {
 	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
 
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCPLEN_256,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) & ~FSMC_ECCEN,
-		       host->regs_va + PC);
-	writel_relaxed(readl(host->regs_va + PC) | FSMC_ECCEN,
-		       host->regs_va + PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCPLEN_256,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) & ~FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
+	writel_relaxed(readl(host->regs_va + FSMC_PC) | FSMC_ECCEN,
+		       host->regs_va + FSMC_PC);
 }
 
 /*
@@ -618,11 +619,11 @@ static void fsmc_select_chip(struct mtd_info *mtd, int chipnr)
 	if (chipnr > 0)
 		return;
 
-	pc = readl(host->regs_va + PC);
+	pc = readl(host->regs_va + FSMC_PC);
 	if (chipnr < 0)
-		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc & ~FSMC_ENABLE, host->regs_va + FSMC_PC);
 	else
-		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + PC);
+		writel_relaxed(pc | FSMC_ENABLE, host->regs_va + FSMC_PC);
 
 	/* nCE line must be asserted before starting any operation */
 	mb();
-- 
cgit v1.2.3


From f55824c6faef1df97439094a30b9f21fd2ce60a8 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:35 +0200
Subject: mtd: rawnand: fsmc: Use uintptr_t casts instead of unsigned ones

uintptr_t should be used when casting a pointer to an unsigned int so
that the code compiles without warnings even on 64-bit architectures.

This is needed if we want to allow selection of this driver when
COMPILE_TEST=y.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/fsmc_nand.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index d71c49f50e77..527bebc7e6c9 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -547,7 +547,7 @@ static void fsmc_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
@@ -570,7 +570,7 @@ static void fsmc_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct fsmc_nand_data *host  = mtd_to_fsmc(mtd);
 	int i;
 
-	if (IS_ALIGNED((uint32_t)buf, sizeof(uint32_t)) &&
+	if (IS_ALIGNED((uintptr_t)buf, sizeof(uint32_t)) &&
 			IS_ALIGNED(len, sizeof(uint32_t))) {
 		uint32_t *p = (uint32_t *)buf;
 		len = len >> 2;
-- 
cgit v1.2.3


From 17c09ed706de451b7b449fd57198675349b58105 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:36 +0200
Subject: mtd: rawnand: fsmc: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having PLAT_SPEAR, ARCH_NOMADIK,
ARCH_U8500 or MACH_U300 enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index cd9eb60faff6..a47ed653afe5 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -501,8 +501,9 @@ config MTD_NAND_JZ4780
 
 config MTD_NAND_FSMC
 	tristate "Support for NAND on ST Micros FSMC"
-	depends on OF
-	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300
+	depends on OF && HAS_IOMEM
+	depends on PLAT_SPEAR || ARCH_NOMADIK || ARCH_U8500 || MACH_U300 || \
+		   COMPILE_TEST
 	help
 	  Enables support for NAND Flash chips on the ST Microelectronics
 	  Flexible Static Memory Controller (FSMC)
-- 
cgit v1.2.3


From b30a2bd4ee9d3933ce397ab83a0b713e9423ec99 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:37 +0200
Subject: memory: fsl_ifc: Allow selection of this driver when COMPILE_TEST=y

It just makes maintainers' life easier by allowing them to compile-test
this driver without having FSL_SOC, ARCH_LAYERSCAPE or SOC_LS1021A
enabled.

We also need to add a dependency on HAS_IOMEM to make sure the
driver compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/memory/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 8d731d6c3e54..78457ab2cbc4 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -116,7 +116,8 @@ config FSL_CORENET_CF
 
 config FSL_IFC
 	bool
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 
 config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
-- 
cgit v1.2.3


From 62a316088dd07b31587e1874f2f9e4d096ef0da1 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:38 +0200
Subject: mtd: rawnand: fsl_ifc: Add an __iomem specifier on eccstat_regs

The local eccstat_regs variable in fsl_ifc_run_command() is missing an
__iomem specifier, and sparce complains about that.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/fsl_ifc_nand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 382b67e97174..75d3c951f61a 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -225,7 +225,7 @@ static void fsl_ifc_run_command(struct mtd_info *mtd)
 		int bufnum = nctrl->page & priv->bufnum_mask;
 		int sector_start = bufnum * chip->ecc.steps;
 		int sector_end = sector_start + chip->ecc.steps - 1;
-		__be32 *eccstat_regs;
+		__be32 __iomem *eccstat_regs;
 
 		eccstat_regs = ifc->ifc_nand.nand_eccstat;
 		eccstat = ifc_in32(&eccstat_regs[sector_start / 4]);
-- 
cgit v1.2.3


From a6be5051cdca8069abfe016a70ce9243ba1a2c0d Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:39 +0200
Subject: mtd: rawnand: fsl_ifc: Allow selection of this driver when
 COMPILE_TEST=y

It just makes maintainers' life easier by allowing them to compile-test
this driver without having FSL_SOC, ARCH_LAYERSCAPE or SOC_LS1021A
enabled.

We also need to add a dependency on HAS_IOMEM to make sure the
driver compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index a47ed653afe5..30a953aaba3a 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -406,7 +406,8 @@ config MTD_NAND_FSL_ELBC
 
 config MTD_NAND_FSL_IFC
 	tristate "NAND support for Freescale IFC controller"
-	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A
+	depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+	depends on HAS_IOMEM
 	select FSL_IFC
 	select MEMORY
 	help
-- 
cgit v1.2.3


From dc2865ac3527d76fe04ee1f1a3ffc101a60faba0 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:40 +0200
Subject: MIPS: txx9: Move the ndfc.h header to
 include/linux/platform_data/txx9

This way we will be able to compile the ndfmc driver when
COMPILE_TEST=y.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 arch/mips/include/asm/txx9/ndfmc.h       | 30 ------------------------------
 arch/mips/txx9/generic/setup.c           |  2 +-
 arch/mips/txx9/generic/setup_tx4938.c    |  2 +-
 arch/mips/txx9/generic/setup_tx4939.c    |  2 +-
 drivers/mtd/nand/raw/txx9ndfmc.c         |  2 +-
 include/linux/platform_data/txx9/ndfmc.h | 30 ++++++++++++++++++++++++++++++
 6 files changed, 34 insertions(+), 34 deletions(-)
 delete mode 100644 arch/mips/include/asm/txx9/ndfmc.h
 create mode 100644 include/linux/platform_data/txx9/ndfmc.h

diff --git a/arch/mips/include/asm/txx9/ndfmc.h b/arch/mips/include/asm/txx9/ndfmc.h
deleted file mode 100644
index fa67f3df78fc..000000000000
--- a/arch/mips/include/asm/txx9/ndfmc.h
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * (C) Copyright TOSHIBA CORPORATION 2007
- */
-#ifndef __ASM_TXX9_NDFMC_H
-#define __ASM_TXX9_NDFMC_H
-
-#define NDFMC_PLAT_FLAG_USE_BSPRT	0x01
-#define NDFMC_PLAT_FLAG_NO_RSTR		0x02
-#define NDFMC_PLAT_FLAG_HOLDADD		0x04
-#define NDFMC_PLAT_FLAG_DUMMYWRITE	0x08
-
-struct txx9ndfmc_platform_data {
-	unsigned int shift;
-	unsigned int gbus_clock;
-	unsigned int hold;		/* hold time in nanosecond */
-	unsigned int spw;		/* strobe pulse width in nanosecond */
-	unsigned int flags;
-	unsigned char ch_mask;		/* available channel bitmask */
-	unsigned char wp_mask;		/* write-protect bitmask */
-	unsigned char wide_mask;	/* 16bit-nand bitmask */
-};
-
-void txx9_ndfmc_init(unsigned long baseaddr,
-		     const struct txx9ndfmc_platform_data *plat_data);
-
-#endif /* __ASM_TXX9_NDFMC_H */
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 1791a44ee570..aa47932abd28 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -20,6 +20,7 @@
 #include <linux/err.h>
 #include <linux/gpio/driver.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <linux/serial_core.h>
 #include <linux/mtd/physmap.h>
 #include <linux/leds.h>
@@ -35,7 +36,6 @@
 #include <asm/txx9/generic.h>
 #include <asm/txx9/pci.h>
 #include <asm/txx9tmr.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #ifdef CONFIG_CPU_TX49XX
 #include <asm/txx9/tx4938.h>
diff --git a/arch/mips/txx9/generic/setup_tx4938.c b/arch/mips/txx9/generic/setup_tx4938.c
index 85d1795652da..17395d5d15ca 100644
--- a/arch/mips/txx9/generic/setup_tx4938.c
+++ b/arch/mips/txx9/generic/setup_tx4938.c
@@ -17,13 +17,13 @@
 #include <linux/ptrace.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <asm/reboot.h>
 #include <asm/traps.h>
 #include <asm/txx9irq.h>
 #include <asm/txx9tmr.h>
 #include <asm/txx9pio.h>
 #include <asm/txx9/generic.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #include <asm/txx9/tx4938.h>
 
diff --git a/arch/mips/txx9/generic/setup_tx4939.c b/arch/mips/txx9/generic/setup_tx4939.c
index 274928987a21..360c388f4c82 100644
--- a/arch/mips/txx9/generic/setup_tx4939.c
+++ b/arch/mips/txx9/generic/setup_tx4939.c
@@ -21,13 +21,13 @@
 #include <linux/ptrace.h>
 #include <linux/mtd/physmap.h>
 #include <linux/platform_device.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 #include <asm/bootinfo.h>
 #include <asm/reboot.h>
 #include <asm/traps.h>
 #include <asm/txx9irq.h>
 #include <asm/txx9tmr.h>
 #include <asm/txx9/generic.h>
-#include <asm/txx9/ndfmc.h>
 #include <asm/txx9/dmac.h>
 #include <asm/txx9/tx4939.h>
 
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index b567d212fe7d..04d57474ef97 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -20,7 +20,7 @@
 #include <linux/mtd/nand_ecc.h>
 #include <linux/mtd/partitions.h>
 #include <linux/io.h>
-#include <asm/txx9/ndfmc.h>
+#include <linux/platform_data/txx9/ndfmc.h>
 
 /* TXX9 NDFMC Registers */
 #define TXX9_NDFDTR	0x00
diff --git a/include/linux/platform_data/txx9/ndfmc.h b/include/linux/platform_data/txx9/ndfmc.h
new file mode 100644
index 000000000000..fc172627d54e
--- /dev/null
+++ b/include/linux/platform_data/txx9/ndfmc.h
@@ -0,0 +1,30 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * (C) Copyright TOSHIBA CORPORATION 2007
+ */
+#ifndef __TXX9_NDFMC_H
+#define __TXX9_NDFMC_H
+
+#define NDFMC_PLAT_FLAG_USE_BSPRT	0x01
+#define NDFMC_PLAT_FLAG_NO_RSTR		0x02
+#define NDFMC_PLAT_FLAG_HOLDADD		0x04
+#define NDFMC_PLAT_FLAG_DUMMYWRITE	0x08
+
+struct txx9ndfmc_platform_data {
+	unsigned int shift;
+	unsigned int gbus_clock;
+	unsigned int hold;		/* hold time in nanosecond */
+	unsigned int spw;		/* strobe pulse width in nanosecond */
+	unsigned int flags;
+	unsigned char ch_mask;		/* available channel bitmask */
+	unsigned char wp_mask;		/* write-protect bitmask */
+	unsigned char wide_mask;	/* 16bit-nand bitmask */
+};
+
+void txx9_ndfmc_init(unsigned long baseaddr,
+		     const struct txx9ndfmc_platform_data *plat_data);
+
+#endif /* __TXX9_NDFMC_H */
-- 
cgit v1.2.3


From eaea2e7300a23e9e40d15ff9b80c7407e3e7802c Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:41 +0200
Subject: mtd: rawnand: txx9ndfmc: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having SOC_TX4938 or SOC_TX4939
enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 30a953aaba3a..2898016809f0 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -469,7 +469,8 @@ config MTD_NAND_DAVINCI
 
 config MTD_NAND_TXX9NDFMC
 	tristate "NAND Flash support for TXx9 SoC"
-	depends on SOC_TX4938 || SOC_TX4939
+	depends on SOC_TX4938 || SOC_TX4939 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This enables the NAND flash controller on the TXx9 SoCs.
 
-- 
cgit v1.2.3


From e65e3a50702f4e7a01c0b36ff08d6ed8dde7ee7b Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:42 +0200
Subject: MIPS: jz4740: Move jz4740_nand.h header to
 include/linux/platform_data/jz4740

This way we will be able to compile the jz4740_nand driver when
COMPILE_TEST=y.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 arch/mips/include/asm/mach-jz4740/jz4740_nand.h  | 34 ------------------------
 arch/mips/jz4740/board-qi_lb60.c                 |  3 ++-
 drivers/mtd/nand/raw/jz4740_nand.c               |  2 +-
 include/linux/platform_data/jz4740/jz4740_nand.h | 34 ++++++++++++++++++++++++
 4 files changed, 37 insertions(+), 36 deletions(-)
 delete mode 100644 arch/mips/include/asm/mach-jz4740/jz4740_nand.h
 create mode 100644 include/linux/platform_data/jz4740/jz4740_nand.h

diff --git a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h b/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
deleted file mode 100644
index f381d465e768..000000000000
--- a/arch/mips/include/asm/mach-jz4740/jz4740_nand.h
+++ /dev/null
@@ -1,34 +0,0 @@
-/*
- *  Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de>
- *  JZ4740 SoC NAND controller driver
- *
- *  This program is free software; you can redistribute	 it and/or modify it
- *  under  the terms of	 the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the	License, or (at your
- *  option) any later version.
- *
- *  You should have received a copy of the  GNU General Public License along
- *  with this program; if not, write  to the Free Software Foundation, Inc.,
- *  675 Mass Ave, Cambridge, MA 02139, USA.
- *
- */
-
-#ifndef __ASM_MACH_JZ4740_JZ4740_NAND_H__
-#define __ASM_MACH_JZ4740_JZ4740_NAND_H__
-
-#include <linux/mtd/rawnand.h>
-#include <linux/mtd/partitions.h>
-
-#define JZ_NAND_NUM_BANKS 4
-
-struct jz_nand_platform_data {
-	int			num_partitions;
-	struct mtd_partition	*partitions;
-
-	unsigned char banks[JZ_NAND_NUM_BANKS];
-
-	void (*ident_callback)(struct platform_device *, struct mtd_info *,
-				struct mtd_partition **, int *num_partitions);
-};
-
-#endif
diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c
index 60f0767507c6..af0c8ace0141 100644
--- a/arch/mips/jz4740/board-qi_lb60.c
+++ b/arch/mips/jz4740/board-qi_lb60.c
@@ -29,10 +29,11 @@
 #include <linux/power/gpio-charger.h>
 #include <linux/pwm.h>
 
+#include <linux/platform_data/jz4740/jz4740_nand.h>
+
 #include <asm/mach-jz4740/gpio.h>
 #include <asm/mach-jz4740/jz4740_fb.h>
 #include <asm/mach-jz4740/jz4740_mmc.h>
-#include <asm/mach-jz4740/jz4740_nand.h>
 
 #include <linux/regulator/fixed.h>
 #include <linux/regulator/machine.h>
diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index 613b00a9604b..a0254461812d 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -25,7 +25,7 @@
 
 #include <linux/gpio.h>
 
-#include <asm/mach-jz4740/jz4740_nand.h>
+#include <linux/platform_data/jz4740/jz4740_nand.h>
 
 #define JZ_REG_NAND_CTRL	0x50
 #define JZ_REG_NAND_ECC_CTRL	0x100
diff --git a/include/linux/platform_data/jz4740/jz4740_nand.h b/include/linux/platform_data/jz4740/jz4740_nand.h
new file mode 100644
index 000000000000..bc571f6d5ced
--- /dev/null
+++ b/include/linux/platform_data/jz4740/jz4740_nand.h
@@ -0,0 +1,34 @@
+/*
+ *  Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de>
+ *  JZ4740 SoC NAND controller driver
+ *
+ *  This program is free software; you can redistribute	 it and/or modify it
+ *  under  the terms of	 the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the	License, or (at your
+ *  option) any later version.
+ *
+ *  You should have received a copy of the  GNU General Public License along
+ *  with this program; if not, write  to the Free Software Foundation, Inc.,
+ *  675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ */
+
+#ifndef __JZ4740_NAND_H__
+#define __JZ4740_NAND_H__
+
+#include <linux/mtd/rawnand.h>
+#include <linux/mtd/partitions.h>
+
+#define JZ_NAND_NUM_BANKS 4
+
+struct jz_nand_platform_data {
+	int			num_partitions;
+	struct mtd_partition	*partitions;
+
+	unsigned char banks[JZ_NAND_NUM_BANKS];
+
+	void (*ident_callback)(struct platform_device *, struct mtd_info *,
+				struct mtd_partition **, int *num_partitions);
+};
+
+#endif
-- 
cgit v1.2.3


From 6968e07e816906cd4b8150ef2e3af533664f734b Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:43 +0200
Subject: mtd: rawnand: jz4740: Allow selection of this driver when
 COMPILE_TEST=y

It just makes NAND maintainers' life easier by allowing them to
compile-test this driver without having MACH_JZ4740 enabled.

We also need to add a dependency on HAS_IOMEM to make sure the driver
compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 2898016809f0..0711bd714cd5 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -490,7 +490,8 @@ config MTD_NAND_NUC900
 
 config MTD_NAND_JZ4740
 	tristate "Support for JZ4740 SoC NAND controller"
-	depends on MACH_JZ4740
+	depends on MACH_JZ4740 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  Enables support for NAND Flash on JZ4740 SoC based boards.
 
-- 
cgit v1.2.3


From b8f0fadab208d87cab715b7599e0c15b4b2cc55f Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:44 +0200
Subject: mtd: rawnand: jz4780: Drop the dependency on MACH_JZ4780

This MACH_JZ4780 dependency is taken care of by JZ4780_NEMC, no need
to repeat it here.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index 0711bd714cd5..d495759c94ac 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -497,7 +497,7 @@ config MTD_NAND_JZ4740
 
 config MTD_NAND_JZ4780
 	tristate "Support for NAND on JZ4780 SoC"
-	depends on MACH_JZ4780 && JZ4780_NEMC
+	depends on JZ4780_NEMC
 	help
 	  Enables support for NAND Flash connected to the NEMC on JZ4780 SoC
 	  based boards, using the BCH controller for hardware error correction.
-- 
cgit v1.2.3


From 1c3528232f4ba608cc2c31c7a8a55e0dbd6cb200 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Tue, 19 Jun 2018 14:44:01 +0200
Subject: cpufreq: armada-37xx: Add AVS support

Armada 37xx supports Adaptive Voltage Scaling and thanks to this patch a
voltage is associated to each load level.

Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/armada-37xx-cpufreq.c | 163 +++++++++++++++++++++++++++++++++-
 1 file changed, 160 insertions(+), 3 deletions(-)

diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 739da90ff3f6..75491fc841a6 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -51,6 +51,16 @@
 #define  ARMADA_37XX_DVFS_LOAD_2	2
 #define  ARMADA_37XX_DVFS_LOAD_3	3
 
+/* AVS register set */
+#define ARMADA_37XX_AVS_CTL0		0x0
+#define	 ARMADA_37XX_AVS_ENABLE		BIT(30)
+#define	 ARMADA_37XX_AVS_HIGH_VDD_LIMIT	16
+#define	 ARMADA_37XX_AVS_LOW_VDD_LIMIT	22
+#define	 ARMADA_37XX_AVS_VDD_MASK	0x3F
+#define ARMADA_37XX_AVS_CTL2		0x8
+#define	 ARMADA_37XX_AVS_LOW_VDD_EN	BIT(6)
+#define ARMADA_37XX_AVS_VSET(x)	    (0x1C + 4 * (x))
+
 /*
  * On Armada 37xx the Power management manages 4 level of CPU load,
  * each level can be associated with a CPU clock source, a CPU
@@ -58,6 +68,17 @@
  */
 #define LOAD_LEVEL_NR	4
 
+#define MIN_VOLT_MV 1000
+
+/*  AVS value for the corresponding voltage (in mV) */
+static int avs_map[] = {
+	747, 758, 770, 782, 793, 805, 817, 828, 840, 852, 863, 875, 887, 898,
+	910, 922, 933, 945, 957, 968, 980, 992, 1003, 1015, 1027, 1038, 1050,
+	1062, 1073, 1085, 1097, 1108, 1120, 1132, 1143, 1155, 1167, 1178, 1190,
+	1202, 1213, 1225, 1237, 1248, 1260, 1272, 1283, 1295, 1307, 1318, 1330,
+	1342
+};
+
 struct armada37xx_cpufreq_state {
 	struct regmap *regmap;
 	u32 nb_l0l1;
@@ -71,6 +92,7 @@ static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
 struct armada_37xx_dvfs {
 	u32 cpu_freq_max;
 	u8 divider[LOAD_LEVEL_NR];
+	u32 avs[LOAD_LEVEL_NR];
 };
 
 static struct armada_37xx_dvfs armada_37xx_dvfs[] = {
@@ -148,6 +170,128 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 	clk_set_parent(clk, parent);
 }
 
+/*
+ * Find out the armada 37x supported AVS value whose voltage value is
+ * the round-up closest to the target voltage value.
+ */
+static u32 armada_37xx_avs_val_match(int target_vm)
+{
+	u32 avs;
+
+	/* Find out the round-up closest supported voltage value */
+	for (avs = 0; avs < ARRAY_SIZE(avs_map); avs++)
+		if (avs_map[avs] >= target_vm)
+			break;
+
+	/*
+	 * If all supported voltages are smaller than target one,
+	 * choose the largest supported voltage
+	 */
+	if (avs == ARRAY_SIZE(avs_map))
+		avs = ARRAY_SIZE(avs_map) - 1;
+
+	return avs;
+}
+
+/*
+ * For Armada 37xx soc, L0(VSET0) VDD AVS value is set to SVC revision
+ * value or a default value when SVC is not supported.
+ * - L0 can be read out from the register of AVS_CTRL_0 and L0 voltage
+ *   can be got from the mapping table of avs_map.
+ * - L1 voltage should be about 100mv smaller than L0 voltage
+ * - L2 & L3 voltage should be about 150mv smaller than L0 voltage.
+ * This function calculates L1 & L2 & L3 AVS values dynamically based
+ * on L0 voltage and fill all AVS values to the AVS value table.
+ */
+static void __init armada37xx_cpufreq_avs_configure(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int target_vm;
+	int load_level = 0;
+	u32 l0_vdd_min;
+
+	if (base == NULL)
+		return;
+
+	/* Get L0 VDD min value */
+	regmap_read(base, ARMADA_37XX_AVS_CTL0, &l0_vdd_min);
+	l0_vdd_min = (l0_vdd_min >> ARMADA_37XX_AVS_LOW_VDD_LIMIT) &
+		ARMADA_37XX_AVS_VDD_MASK;
+	if (l0_vdd_min >= ARRAY_SIZE(avs_map))  {
+		pr_err("L0 VDD MIN %d is not correct.\n", l0_vdd_min);
+		return;
+	}
+	dvfs->avs[0] = l0_vdd_min;
+
+	if (avs_map[l0_vdd_min] <= MIN_VOLT_MV) {
+		/*
+		 * If L0 voltage is smaller than 1000mv, then all VDD sets
+		 * use L0 voltage;
+		 */
+		u32 avs_min = armada_37xx_avs_val_match(MIN_VOLT_MV);
+
+		for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++)
+			dvfs->avs[load_level] = avs_min;
+
+		return;
+	}
+
+	/*
+	 * L1 voltage is equal to L0 voltage - 100mv and it must be
+	 * larger than 1000mv
+	 */
+
+	target_vm = avs_map[l0_vdd_min] - 100;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[1] = armada_37xx_avs_val_match(target_vm);
+
+	/*
+	 * L2 & L3 voltage is equal to L0 voltage - 150mv and it must
+	 * be larger than 1000mv
+	 */
+	target_vm = avs_map[l0_vdd_min] - 150;
+	target_vm = target_vm > MIN_VOLT_MV ? target_vm : MIN_VOLT_MV;
+	dvfs->avs[2] = dvfs->avs[3] = armada_37xx_avs_val_match(target_vm);
+}
+
+static void __init armada37xx_cpufreq_avs_setup(struct regmap *base,
+						struct armada_37xx_dvfs *dvfs)
+{
+	unsigned int avs_val = 0, freq;
+	int load_level = 0;
+
+	if (base == NULL)
+		return;
+
+	/* Disable AVS before the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE, 0);
+
+
+	/* Enable low voltage mode */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL2,
+			   ARMADA_37XX_AVS_LOW_VDD_EN,
+			   ARMADA_37XX_AVS_LOW_VDD_EN);
+
+
+	for (load_level = 1; load_level < LOAD_LEVEL_NR; load_level++) {
+		freq = dvfs->cpu_freq_max / dvfs->divider[load_level];
+
+		avs_val = dvfs->avs[load_level];
+		regmap_update_bits(base, ARMADA_37XX_AVS_VSET(load_level-1),
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    ARMADA_37XX_AVS_VDD_MASK << ARMADA_37XX_AVS_LOW_VDD_LIMIT,
+		    avs_val << ARMADA_37XX_AVS_HIGH_VDD_LIMIT |
+		    avs_val << ARMADA_37XX_AVS_LOW_VDD_LIMIT);
+	}
+
+	/* Enable AVS after the configuration */
+	regmap_update_bits(base, ARMADA_37XX_AVS_CTL0,
+			   ARMADA_37XX_AVS_ENABLE,
+			   ARMADA_37XX_AVS_ENABLE);
+
+}
+
 static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
 {
 	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
@@ -216,7 +360,7 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	struct platform_device *pdev;
 	unsigned long freq;
 	unsigned int cur_frequency;
-	struct regmap *nb_pm_base;
+	struct regmap *nb_pm_base, *avs_base;
 	struct device *cpu_dev;
 	int load_lvl, ret;
 	struct clk *clk;
@@ -227,6 +371,14 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	if (IS_ERR(nb_pm_base))
 		return -ENODEV;
 
+	avs_base =
+		syscon_regmap_lookup_by_compatible("marvell,armada-3700-avs");
+
+	/* if AVS is not present don't use it but still try to setup dvfs */
+	if (IS_ERR(avs_base)) {
+		pr_info("Syscon failed for Adapting Voltage Scaling: skip it\n");
+		avs_base = NULL;
+	}
 	/* Before doing any configuration on the DVFS first, disable it */
 	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
 
@@ -270,16 +422,21 @@ static int __init armada37xx_cpufreq_driver_init(void)
 
 	armada37xx_cpufreq_state->regmap = nb_pm_base;
 
+	armada37xx_cpufreq_avs_configure(avs_base, dvfs);
+	armada37xx_cpufreq_avs_setup(avs_base, dvfs);
+
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
+		unsigned long u_volt = avs_map[dvfs->avs[load_lvl]] * 1000;
 		freq = cur_frequency / dvfs->divider[load_lvl];
-
-		ret = dev_pm_opp_add(cpu_dev, freq, 0);
+		ret = dev_pm_opp_add(cpu_dev, freq, u_volt);
 		if (ret)
 			goto remove_opp;
+
+
 	}
 
 	/* Now that everything is setup, enable the DVFS at hardware level */
-- 
cgit v1.2.3


From 33477d84c26bbfa626da2c032e567a90dd70a528 Mon Sep 17 00:00:00 2001
From: George Cherian <george.cherian@cavium.com>
Date: Wed, 11 Jul 2018 23:07:55 -0700
Subject: cpufreq / CPPC: Add cpuinfo_cur_freq support for CPPC

Per Section 8.4.7.1.3 of ACPI 6.2, the platform provides performance
feedback via set of performance counters. To determine the actual
performance level delivered over time, OSPM may read a set of
performance counters from the Reference Performance Counter Register
and the Delivered Performance Counter Register.

OSPM calculates the delivered performance over a given time period by
taking a beginning and ending snapshot of both the reference and
delivered performance counters, and calculating:

delivered_perf = reference_perf X (delta of delivered_perf counter / delta of reference_perf counter).

Implement the above and hook this up to the cpufreq->get method.

Signed-off-by: George Cherian <george.cherian@cavium.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Prashanth Prakash <pprakash@codeaurora.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cppc_cpufreq.c | 52 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index a9d3eec32795..30f302149730 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -296,10 +296,62 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	return ret;
 }
 
+static inline u64 get_delta(u64 t1, u64 t0)
+{
+	if (t1 > t0 || t0 > ~(u32)0)
+		return t1 - t0;
+
+	return (u32)t1 - (u32)t0;
+}
+
+static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
+{
+	u64 delta_reference, delta_delivered;
+	u64 reference_perf, delivered_perf;
+
+	reference_perf = fb_ctrs_t0.reference_perf;
+
+	delta_reference = get_delta(fb_ctrs_t1.reference,
+				    fb_ctrs_t0.reference);
+	delta_delivered = get_delta(fb_ctrs_t1.delivered,
+				    fb_ctrs_t0.delivered);
+
+	/* Check to avoid divide-by zero */
+	if (delta_reference || delta_delivered)
+		delivered_perf = (reference_perf * delta_delivered) /
+					delta_reference;
+	else
+		delivered_perf = cpu->perf_ctrls.desired_perf;
+
+	return cppc_cpufreq_perf_to_khz(cpu, delivered_perf);
+}
+
+static unsigned int cppc_cpufreq_get_rate(unsigned int cpunum)
+{
+	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
+	struct cppc_cpudata *cpu = all_cpu_data[cpunum];
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	ret = cppc_get_perf_ctrs(cpunum, &fb_ctrs_t1);
+	if (ret)
+		return ret;
+
+	return cppc_get_rate_from_fbctrs(cpu, fb_ctrs_t0, fb_ctrs_t1);
+}
+
 static struct cpufreq_driver cppc_cpufreq_driver = {
 	.flags = CPUFREQ_CONST_LOOPS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
+	.get = cppc_cpufreq_get_rate,
 	.init = cppc_cpufreq_cpu_init,
 	.stop_cpu = cppc_cpufreq_stop_cpu,
 	.name = "cppc_cpufreq",
-- 
cgit v1.2.3


From f54ab690ad68e4c5a5b4d4b5dbb28a35018546c5 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Tue, 17 Jul 2018 22:48:21 +0200
Subject: cpufreq: qcom-kryo: Silently error out on EPROBE_DEFER

If of_nvmem_cell_get() fails due to probe deferal, we shouldn't print an
error message. Just be silent in this case.

Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/qcom-cpufreq-kryo.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
index 29389accf3e9..b8d1e6875f16 100644
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -109,8 +109,9 @@ static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
 	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
 	of_node_put(np);
 	if (IS_ERR(speedbin_nvmem)) {
-		dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
-			PTR_ERR(speedbin_nvmem));
+		if (PTR_ERR(speedbin_nvmem) != -EPROBE_DEFER)
+			dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
+				PTR_ERR(speedbin_nvmem));
 		return PTR_ERR(speedbin_nvmem);
 	}
 
-- 
cgit v1.2.3


From 4d81b0f9e631f751bf231213893e202a51f76687 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Wed, 18 Jul 2018 10:15:07 +0200
Subject: cpufreq: pcc-cpufreq: Disable dynamic scaling on many-CPU systems

The firmware interface used by the pcc-cpufreq driver is
fundamentally not scalable and using it for dynamic CPU performance
scaling on systems with many CPUs leads to degraded performance.

For this reason, disable dynamic CPU performance scaling on systems
with pcc-cpufreq where the number of CPUs present at the driver init
time is greater than 4.  Also make the driver print corresponding
complaints to the kernel log.

Reported-by: Andreas Herrmann <aherrmann@suse.com>
Tested-by: Andreas Herrmann <aherrmann@suse.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/pcc-cpufreq.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/cpufreq/pcc-cpufreq.c b/drivers/cpufreq/pcc-cpufreq.c
index 3f0ce2ae35ee..ef8d984178a5 100644
--- a/drivers/cpufreq/pcc-cpufreq.c
+++ b/drivers/cpufreq/pcc-cpufreq.c
@@ -589,6 +589,15 @@ static int __init pcc_cpufreq_init(void)
 		return ret;
 	}
 
+	if (num_present_cpus() > 4) {
+		pcc_cpufreq_driver.flags |= CPUFREQ_NO_AUTO_DYNAMIC_SWITCHING;
+		pr_err("%s: Too many CPUs, dynamic performance scaling disabled\n",
+		       __func__);
+		pr_err("%s: Try to enable another scaling driver through BIOS settings\n",
+		       __func__);
+		pr_err("%s: and complain to the system vendor\n", __func__);
+	}
+
 	ret = cpufreq_register_driver(&pcc_cpufreq_driver);
 
 	return ret;
-- 
cgit v1.2.3


From 2a406e8ac7c3e7e96b94d6c0765d5a4641970446 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Mon, 2 Jul 2018 17:33:39 -0700
Subject: netfilter: nf_conncount: Early exit for garbage collection

This patch is originally from Florian Westphal.

We use an extra function with early exit for garbage collection.
It is not necessary to traverse the full list for every node since
it is enough to zap a couple of entries for garbage collection.

Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 39 +++++++++++++++++++++++++++++++++++++--
 1 file changed, 37 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 510039862aa9..81c02185b2e8 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -189,6 +189,42 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 }
 EXPORT_SYMBOL_GPL(nf_conncount_lookup);
 
+static void nf_conncount_gc_list(struct net *net,
+				 struct nf_conncount_rb *rbconn)
+{
+	const struct nf_conntrack_tuple_hash *found;
+	struct nf_conncount_tuple *conn;
+	struct hlist_node *n;
+	struct nf_conn *found_ct;
+	unsigned int collected = 0;
+
+	hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node) {
+		found = find_or_evict(net, conn);
+		if (IS_ERR(found)) {
+			if (PTR_ERR(found) == -ENOENT)
+				collected++;
+			continue;
+		}
+
+		found_ct = nf_ct_tuplehash_to_ctrack(found);
+		if (already_closed(found_ct)) {
+			/*
+			 * we do not care about connections which are
+			 * closed already -> ditch it
+			 */
+			nf_ct_put(found_ct);
+			hlist_del(&conn->node);
+			kmem_cache_free(conncount_conn_cachep, conn);
+			collected++;
+			continue;
+		}
+
+		nf_ct_put(found_ct);
+		if (collected > CONNCOUNT_GC_MAX_NODES)
+			return;
+	}
+}
+
 static void tree_nodes_free(struct rb_root *root,
 			    struct nf_conncount_rb *gc_nodes[],
 			    unsigned int gc_count)
@@ -251,8 +287,7 @@ count_tree(struct net *net, struct rb_root *root,
 		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
 			continue;
 
-		/* only used for GC on hhead, retval and 'addit' ignored */
-		nf_conncount_lookup(net, &rbconn->hhead, tuple, zone, &addit);
+		nf_conncount_gc_list(net, rbconn);
 		if (hlist_empty(&rbconn->hhead))
 			gc_nodes[gc_count++] = rbconn;
 	}
-- 
cgit v1.2.3


From cb2b36f5a97df76f547fcc4ab444a02522fb6c96 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Mon, 2 Jul 2018 17:33:40 -0700
Subject: netfilter: nf_conncount: Switch to plain list

Original patch is from Florian Westphal.

This patch switches from hlist to plain list to store the list of
connections with the same filtering key in nf_conncount. With the
plain list, we can insert new connections at the tail, so over time
the beginning of list holds long-running connections and those are
expired, while the newly creates ones are at the end.

Later on, we could probably move checked ones to the end of the list,
so the next run has higher chance to reclaim stale entries in the front.

Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_count.h | 15 ++++--
 net/netfilter/nf_conncount.c               | 83 ++++++++++++++++++------------
 net/netfilter/nft_connlimit.c              | 24 ++++-----
 3 files changed, 75 insertions(+), 47 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index 3a188a0923a3..e4884e0e4f69 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -1,8 +1,15 @@
 #ifndef _NF_CONNTRACK_COUNT_H
 #define _NF_CONNTRACK_COUNT_H
 
+#include <linux/list.h>
+
 struct nf_conncount_data;
 
+struct nf_conncount_list {
+	struct list_head head;	/* connections with the same filtering key */
+	unsigned int count;	/* length of list */
+};
+
 struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
 					    unsigned int keylen);
 void nf_conncount_destroy(struct net *net, unsigned int family,
@@ -14,15 +21,17 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 
-unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
+unsigned int nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
 				 const struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_zone *zone,
 				 bool *addit);
 
-bool nf_conncount_add(struct hlist_head *head,
+void nf_conncount_list_init(struct nf_conncount_list *list);
+
+bool nf_conncount_add(struct nf_conncount_list *list,
 		      const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conntrack_zone *zone);
 
-void nf_conncount_cache_free(struct hlist_head *hhead);
+void nf_conncount_cache_free(struct nf_conncount_list *list);
 
 #endif
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 81c02185b2e8..81b060adefef 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -44,7 +44,7 @@
 
 /* we will save the tuples of all connections we care about */
 struct nf_conncount_tuple {
-	struct hlist_node		node;
+	struct list_head		node;
 	struct nf_conntrack_tuple	tuple;
 	struct nf_conntrack_zone	zone;
 	int				cpu;
@@ -53,7 +53,7 @@ struct nf_conncount_tuple {
 
 struct nf_conncount_rb {
 	struct rb_node node;
-	struct hlist_head hhead; /* connections/hosts in same subnet */
+	struct nf_conncount_list list;
 	u32 key[MAX_KEYLEN];
 };
 
@@ -82,12 +82,15 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen)
 	return memcmp(a, b, klen * sizeof(u32));
 }
 
-bool nf_conncount_add(struct hlist_head *head,
+bool nf_conncount_add(struct nf_conncount_list *list,
 		      const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conntrack_zone *zone)
 {
 	struct nf_conncount_tuple *conn;
 
+	if (WARN_ON_ONCE(list->count > INT_MAX))
+		return false;
+
 	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
 	if (conn == NULL)
 		return false;
@@ -95,13 +98,26 @@ bool nf_conncount_add(struct hlist_head *head,
 	conn->zone = *zone;
 	conn->cpu = raw_smp_processor_id();
 	conn->jiffies32 = (u32)jiffies;
-	hlist_add_head(&conn->node, head);
+	list_add_tail(&conn->node, &list->head);
+	list->count++;
 	return true;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
 
+static void conn_free(struct nf_conncount_list *list,
+		      struct nf_conncount_tuple *conn)
+{
+	if (WARN_ON_ONCE(list->count == 0))
+		return;
+
+	list->count--;
+	list_del(&conn->node);
+	kmem_cache_free(conncount_conn_cachep, conn);
+}
+
 static const struct nf_conntrack_tuple_hash *
-find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
+find_or_evict(struct net *net, struct nf_conncount_list *list,
+	      struct nf_conncount_tuple *conn)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	unsigned long a, b;
@@ -121,30 +137,29 @@ find_or_evict(struct net *net, struct nf_conncount_tuple *conn)
 	 */
 	age = a - b;
 	if (conn->cpu == cpu || age >= 2) {
-		hlist_del(&conn->node);
-		kmem_cache_free(conncount_conn_cachep, conn);
+		conn_free(list, conn);
 		return ERR_PTR(-ENOENT);
 	}
 
 	return ERR_PTR(-EAGAIN);
 }
 
-unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
+unsigned int nf_conncount_lookup(struct net *net,
+				 struct nf_conncount_list *list,
 				 const struct nf_conntrack_tuple *tuple,
 				 const struct nf_conntrack_zone *zone,
 				 bool *addit)
 {
 	const struct nf_conntrack_tuple_hash *found;
-	struct nf_conncount_tuple *conn;
+	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
-	struct hlist_node *n;
 	unsigned int length = 0;
 
 	*addit = tuple ? true : false;
 
 	/* check the saved connections */
-	hlist_for_each_entry_safe(conn, n, head, node) {
-		found = find_or_evict(net, conn);
+	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
+		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
 			/* Not found, but might be about to be confirmed */
 			if (PTR_ERR(found) == -EAGAIN) {
@@ -157,6 +172,7 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 				    nf_ct_zone_id(zone, zone->dir))
 					*addit = false;
 			}
+
 			continue;
 		}
 
@@ -176,8 +192,7 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 			 * closed already -> ditch it
 			 */
 			nf_ct_put(found_ct);
-			hlist_del(&conn->node);
-			kmem_cache_free(conncount_conn_cachep, conn);
+			conn_free(list, conn);
 			continue;
 		}
 
@@ -189,17 +204,23 @@ unsigned int nf_conncount_lookup(struct net *net, struct hlist_head *head,
 }
 EXPORT_SYMBOL_GPL(nf_conncount_lookup);
 
+void nf_conncount_list_init(struct nf_conncount_list *list)
+{
+	INIT_LIST_HEAD(&list->head);
+	list->count = 1;
+}
+EXPORT_SYMBOL_GPL(nf_conncount_list_init);
+
 static void nf_conncount_gc_list(struct net *net,
-				 struct nf_conncount_rb *rbconn)
+				 struct nf_conncount_list *list)
 {
 	const struct nf_conntrack_tuple_hash *found;
-	struct nf_conncount_tuple *conn;
-	struct hlist_node *n;
+	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
 	unsigned int collected = 0;
 
-	hlist_for_each_entry_safe(conn, n, &rbconn->hhead, node) {
-		found = find_or_evict(net, conn);
+	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
+		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
 			if (PTR_ERR(found) == -ENOENT)
 				collected++;
@@ -213,8 +234,7 @@ static void nf_conncount_gc_list(struct net *net,
 			 * closed already -> ditch it
 			 */
 			nf_ct_put(found_ct);
-			hlist_del(&conn->node);
-			kmem_cache_free(conncount_conn_cachep, conn);
+			conn_free(list, conn);
 			collected++;
 			continue;
 		}
@@ -271,14 +291,14 @@ count_tree(struct net *net, struct rb_root *root,
 			/* same source network -> be counted! */
 			unsigned int count;
 
-			count = nf_conncount_lookup(net, &rbconn->hhead, tuple,
+			count = nf_conncount_lookup(net, &rbconn->list, tuple,
 						    zone, &addit);
 
 			tree_nodes_free(root, gc_nodes, gc_count);
 			if (!addit)
 				return count;
 
-			if (!nf_conncount_add(&rbconn->hhead, tuple, zone))
+			if (!nf_conncount_add(&rbconn->list, tuple, zone))
 				return 0; /* hotdrop */
 
 			return count + 1;
@@ -287,8 +307,8 @@ count_tree(struct net *net, struct rb_root *root,
 		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
 			continue;
 
-		nf_conncount_gc_list(net, rbconn);
-		if (hlist_empty(&rbconn->hhead))
+		nf_conncount_gc_list(net, &rbconn->list);
+		if (list_empty(&rbconn->list.head))
 			gc_nodes[gc_count++] = rbconn;
 	}
 
@@ -322,8 +342,8 @@ count_tree(struct net *net, struct rb_root *root,
 	conn->zone = *zone;
 	memcpy(rbconn->key, key, sizeof(u32) * keylen);
 
-	INIT_HLIST_HEAD(&rbconn->hhead);
-	hlist_add_head(&conn->node, &rbconn->hhead);
+	nf_conncount_list_init(&rbconn->list);
+	list_add(&conn->node, &rbconn->list.head);
 
 	rb_link_node(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);
@@ -388,12 +408,11 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family
 }
 EXPORT_SYMBOL_GPL(nf_conncount_init);
 
-void nf_conncount_cache_free(struct hlist_head *hhead)
+void nf_conncount_cache_free(struct nf_conncount_list *list)
 {
-	struct nf_conncount_tuple *conn;
-	struct hlist_node *n;
+	struct nf_conncount_tuple *conn, *conn_n;
 
-	hlist_for_each_entry_safe(conn, n, hhead, node)
+	list_for_each_entry_safe(conn, conn_n, &list->head, node)
 		kmem_cache_free(conncount_conn_cachep, conn);
 }
 EXPORT_SYMBOL_GPL(nf_conncount_cache_free);
@@ -408,7 +427,7 @@ static void destroy_tree(struct rb_root *r)
 
 		rb_erase(node, r);
 
-		nf_conncount_cache_free(&rbconn->hhead);
+		nf_conncount_cache_free(&rbconn->list);
 
 		kmem_cache_free(conncount_rb_cachep, rbconn);
 	}
diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index a832c59f0a9c..4f0491a36a1d 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -14,10 +14,10 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 
 struct nft_connlimit {
-	spinlock_t		lock;
-	struct hlist_head	hhead;
-	u32			limit;
-	bool			invert;
+	spinlock_t			lock;
+	struct nf_conncount_list	list;
+	u32				limit;
+	bool				invert;
 };
 
 static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
@@ -46,13 +46,13 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	}
 
 	spin_lock_bh(&priv->lock);
-	count = nf_conncount_lookup(nft_net(pkt), &priv->hhead, tuple_ptr, zone,
+	count = nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
 				    &addit);
 
 	if (!addit)
 		goto out;
 
-	if (!nf_conncount_add(&priv->hhead, tuple_ptr, zone)) {
+	if (!nf_conncount_add(&priv->list, tuple_ptr, zone)) {
 		regs->verdict.code = NF_DROP;
 		spin_unlock_bh(&priv->lock);
 		return;
@@ -88,7 +88,7 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx,
 	}
 
 	spin_lock_init(&priv->lock);
-	INIT_HLIST_HEAD(&priv->hhead);
+	nf_conncount_list_init(&priv->list);
 	priv->limit	= limit;
 	priv->invert	= invert;
 
@@ -99,7 +99,7 @@ static void nft_connlimit_do_destroy(const struct nft_ctx *ctx,
 				     struct nft_connlimit *priv)
 {
 	nf_ct_netns_put(ctx->net, ctx->family);
-	nf_conncount_cache_free(&priv->hhead);
+	nf_conncount_cache_free(&priv->list);
 }
 
 static int nft_connlimit_do_dump(struct sk_buff *skb,
@@ -213,7 +213,7 @@ static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src)
 	struct nft_connlimit *priv_src = nft_expr_priv(src);
 
 	spin_lock_init(&priv_dst->lock);
-	INIT_HLIST_HEAD(&priv_dst->hhead);
+	nf_conncount_list_init(&priv_dst->list);
 	priv_dst->limit	 = priv_src->limit;
 	priv_dst->invert = priv_src->invert;
 
@@ -225,7 +225,7 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx,
 {
 	struct nft_connlimit *priv = nft_expr_priv(expr);
 
-	nf_conncount_cache_free(&priv->hhead);
+	nf_conncount_cache_free(&priv->list);
 }
 
 static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
@@ -234,9 +234,9 @@ static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
 	bool addit, ret;
 
 	spin_lock_bh(&priv->lock);
-	nf_conncount_lookup(net, &priv->hhead, NULL, &nf_ct_zone_dflt, &addit);
+	nf_conncount_lookup(net, &priv->list, NULL, &nf_ct_zone_dflt, &addit);
 
-	ret = hlist_empty(&priv->hhead);
+	ret = list_empty(&priv->list.head);
 	spin_unlock_bh(&priv->lock);
 
 	return ret;
-- 
cgit v1.2.3


From 976afca1ceba53df6f4a543014e15d1c7a962571 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Mon, 2 Jul 2018 17:33:41 -0700
Subject: netfilter: nf_conncount: Early exit in nf_conncount_lookup() and
 cleanup

This patch is originally from Florian Westphal.

This patch does the following three tasks.

It applies the same early exit technique for nf_conncount_lookup().

Since now we keep the number of connections in 'struct nf_conncount_list',
we no longer need to return the count in nf_conncount_lookup().

Moreover, we expose the garbage collection function nf_conncount_gc_list()
for nft_connlimit.

Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_count.h | 11 +++++----
 net/netfilter/nf_conncount.c               | 38 +++++++++++++++++-------------
 net/netfilter/nft_connlimit.c              |  9 +++----
 3 files changed, 33 insertions(+), 25 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index e4884e0e4f69..dbec17f674b7 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -21,10 +21,10 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone);
 
-unsigned int nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
-				 const struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_zone *zone,
-				 bool *addit);
+void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
+			 const struct nf_conntrack_tuple *tuple,
+			 const struct nf_conntrack_zone *zone,
+			 bool *addit);
 
 void nf_conncount_list_init(struct nf_conncount_list *list);
 
@@ -32,6 +32,9 @@ bool nf_conncount_add(struct nf_conncount_list *list,
 		      const struct nf_conntrack_tuple *tuple,
 		      const struct nf_conntrack_zone *zone);
 
+void nf_conncount_gc_list(struct net *net,
+			  struct nf_conncount_list *list);
+
 void nf_conncount_cache_free(struct nf_conncount_list *list);
 
 #endif
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 81b060adefef..7dfd9d5e6a3e 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -144,26 +144,29 @@ find_or_evict(struct net *net, struct nf_conncount_list *list,
 	return ERR_PTR(-EAGAIN);
 }
 
-unsigned int nf_conncount_lookup(struct net *net,
-				 struct nf_conncount_list *list,
-				 const struct nf_conntrack_tuple *tuple,
-				 const struct nf_conntrack_zone *zone,
-				 bool *addit)
+void nf_conncount_lookup(struct net *net,
+			 struct nf_conncount_list *list,
+			 const struct nf_conntrack_tuple *tuple,
+			 const struct nf_conntrack_zone *zone,
+			 bool *addit)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
-	unsigned int length = 0;
+	unsigned int collect = 0;
 
+	/* best effort only */
 	*addit = tuple ? true : false;
 
 	/* check the saved connections */
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
+		if (collect > CONNCOUNT_GC_MAX_NODES)
+			break;
+
 		found = find_or_evict(net, list, conn);
 		if (IS_ERR(found)) {
 			/* Not found, but might be about to be confirmed */
 			if (PTR_ERR(found) == -EAGAIN) {
-				length++;
 				if (!tuple)
 					continue;
 
@@ -171,8 +174,8 @@ unsigned int nf_conncount_lookup(struct net *net,
 				    nf_ct_zone_id(&conn->zone, conn->zone.dir) ==
 				    nf_ct_zone_id(zone, zone->dir))
 					*addit = false;
-			}
-
+			} else if (PTR_ERR(found) == -ENOENT)
+				collect++;
 			continue;
 		}
 
@@ -181,9 +184,10 @@ unsigned int nf_conncount_lookup(struct net *net,
 		if (tuple && nf_ct_tuple_equal(&conn->tuple, tuple) &&
 		    nf_ct_zone_equal(found_ct, zone, zone->dir)) {
 			/*
-			 * Just to be sure we have it only once in the list.
 			 * We should not see tuples twice unless someone hooks
 			 * this into a table without "-p tcp --syn".
+			 *
+			 * Attempt to avoid a re-add in this case.
 			 */
 			*addit = false;
 		} else if (already_closed(found_ct)) {
@@ -193,14 +197,12 @@ unsigned int nf_conncount_lookup(struct net *net,
 			 */
 			nf_ct_put(found_ct);
 			conn_free(list, conn);
+			collect++;
 			continue;
 		}
 
 		nf_ct_put(found_ct);
-		length++;
 	}
-
-	return length;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_lookup);
 
@@ -211,8 +213,8 @@ void nf_conncount_list_init(struct nf_conncount_list *list)
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
 
-static void nf_conncount_gc_list(struct net *net,
-				 struct nf_conncount_list *list)
+void nf_conncount_gc_list(struct net *net,
+			  struct nf_conncount_list *list)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn, *conn_n;
@@ -244,6 +246,7 @@ static void nf_conncount_gc_list(struct net *net,
 			return;
 	}
 }
+EXPORT_SYMBOL_GPL(nf_conncount_gc_list);
 
 static void tree_nodes_free(struct rb_root *root,
 			    struct nf_conncount_rb *gc_nodes[],
@@ -291,8 +294,9 @@ count_tree(struct net *net, struct rb_root *root,
 			/* same source network -> be counted! */
 			unsigned int count;
 
-			count = nf_conncount_lookup(net, &rbconn->list, tuple,
-						    zone, &addit);
+			nf_conncount_lookup(net, &rbconn->list, tuple, zone,
+					    &addit);
+			count = rbconn->list.count;
 
 			tree_nodes_free(root, gc_nodes, gc_count);
 			if (!addit)
diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index 4f0491a36a1d..37c52ae06741 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -46,8 +46,9 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	}
 
 	spin_lock_bh(&priv->lock);
-	count = nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
-				    &addit);
+	nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
+			    &addit);
+	count = priv->list.count;
 
 	if (!addit)
 		goto out;
@@ -231,10 +232,10 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx,
 static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
 {
 	struct nft_connlimit *priv = nft_expr_priv(expr);
-	bool addit, ret;
+	bool ret;
 
 	spin_lock_bh(&priv->lock);
-	nf_conncount_lookup(net, &priv->list, NULL, &nf_ct_zone_dflt, &addit);
+	nf_conncount_gc_list(net, &priv->list);
 
 	ret = list_empty(&priv->list.head);
 	spin_unlock_bh(&priv->lock);
-- 
cgit v1.2.3


From 2ba39118c10ae3a7d3411c073485bba9576684cd Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Mon, 2 Jul 2018 17:33:42 -0700
Subject: netfilter: nf_conncount: Move locking into count_tree()

This patch is originally from Florian Westphal.

This is a preparation patch to allow lockless traversal
of the tree via RCU.

Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 52 +++++++++++++++++++++-----------------------
 1 file changed, 25 insertions(+), 27 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 7dfd9d5e6a3e..d1a4fd1c0f81 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -262,18 +262,26 @@ static void tree_nodes_free(struct rb_root *root,
 }
 
 static unsigned int
-count_tree(struct net *net, struct rb_root *root,
-	   const u32 *key, u8 keylen,
+count_tree(struct net *net,
+	   struct nf_conncount_data *data,
+	   const u32 *key,
 	   const struct nf_conntrack_tuple *tuple,
 	   const struct nf_conntrack_zone *zone)
 {
 	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
+	struct rb_root *root;
 	struct rb_node **rbnode, *parent;
 	struct nf_conncount_rb *rbconn;
 	struct nf_conncount_tuple *conn;
-	unsigned int gc_count;
+	unsigned int gc_count, hash;
 	bool no_gc = false;
+	unsigned int count = 0;
+	u8 keylen = data->keylen;
 
+	hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
+	root = &data->root[hash];
+
+	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
  restart:
 	gc_count = 0;
 	parent = NULL;
@@ -292,20 +300,20 @@ count_tree(struct net *net, struct rb_root *root,
 			rbnode = &((*rbnode)->rb_right);
 		} else {
 			/* same source network -> be counted! */
-			unsigned int count;
-
 			nf_conncount_lookup(net, &rbconn->list, tuple, zone,
 					    &addit);
 			count = rbconn->list.count;
 
 			tree_nodes_free(root, gc_nodes, gc_count);
 			if (!addit)
-				return count;
+				goto out_unlock;
 
 			if (!nf_conncount_add(&rbconn->list, tuple, zone))
-				return 0; /* hotdrop */
+				count = 0; /* hotdrop */
+				goto out_unlock;
 
-			return count + 1;
+			count++;
+			goto out_unlock;
 		}
 
 		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
@@ -328,18 +336,18 @@ count_tree(struct net *net, struct rb_root *root,
 		goto restart;
 	}
 
+	count = 0;
 	if (!tuple)
-		return 0;
-
+		goto out_unlock;
 	/* no match, need to insert new node */
 	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
 	if (rbconn == NULL)
-		return 0;
+		goto out_unlock;
 
 	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
 	if (conn == NULL) {
 		kmem_cache_free(conncount_rb_cachep, rbconn);
-		return 0;
+		goto out_unlock;
 	}
 
 	conn->tuple = *tuple;
@@ -348,10 +356,13 @@ count_tree(struct net *net, struct rb_root *root,
 
 	nf_conncount_list_init(&rbconn->list);
 	list_add(&conn->node, &rbconn->list.head);
+	count = 1;
 
 	rb_link_node(&rbconn->node, parent, rbnode);
 	rb_insert_color(&rbconn->node, root);
-	return 1;
+out_unlock:
+	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	return count;
 }
 
 /* Count and return number of conntrack entries in 'net' with particular 'key'.
@@ -363,20 +374,7 @@ unsigned int nf_conncount_count(struct net *net,
 				const struct nf_conntrack_tuple *tuple,
 				const struct nf_conntrack_zone *zone)
 {
-	struct rb_root *root;
-	int count;
-	u32 hash;
-
-	hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
-	root = &data->root[hash];
-
-	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
-
-	count = count_tree(net, root, key, data->keylen, tuple, zone);
-
-	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
-
-	return count;
+	return count_tree(net, data, key, tuple, zone);
 }
 EXPORT_SYMBOL_GPL(nf_conncount_count);
 
-- 
cgit v1.2.3


From 34848d5c896ea1ab4e3c441b9c4fed39928ccbaf Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Mon, 2 Jul 2018 17:33:43 -0700
Subject: netfilter: nf_conncount: Split insert and traversal

This patch is originally from Florian Westphal.

When we have a very coarse grouping, e.g. by large subnets, zone id,
etc, it's likely that we do not need to do tree rotation because
we'll find a node where we can attach new entry.  Based on this
observation, we split tree traversal and insertion.

Later on, we can make traversal lockless (tree protected
by RCU), and add extra lock in the individual nodes to protect list
insertion/deletion, thereby allowing parallel insert/delete in different
tree nodes.

Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 87 ++++++++++++++++++++++++++++++++++----------
 1 file changed, 67 insertions(+), 20 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index d1a4fd1c0f81..3f14806b7271 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -261,6 +261,71 @@ static void tree_nodes_free(struct rb_root *root,
 	}
 }
 
+static unsigned int
+insert_tree(struct rb_root *root,
+	    unsigned int hash,
+	    const u32 *key,
+	    u8 keylen,
+	    const struct nf_conntrack_tuple *tuple,
+	    const struct nf_conntrack_zone *zone)
+{
+	struct rb_node **rbnode, *parent;
+	struct nf_conncount_rb *rbconn;
+	struct nf_conncount_tuple *conn;
+	unsigned int count = 0;
+
+	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+
+	parent = NULL;
+	rbnode = &(root->rb_node);
+	while (*rbnode) {
+		int diff;
+		rbconn = rb_entry(*rbnode, struct nf_conncount_rb, node);
+
+		parent = *rbnode;
+		diff = key_diff(key, rbconn->key, keylen);
+		if (diff < 0) {
+			rbnode = &((*rbnode)->rb_left);
+		} else if (diff > 0) {
+			rbnode = &((*rbnode)->rb_right);
+		} else {
+			/* unlikely: other cpu added node already */
+			if (!nf_conncount_add(&rbconn->list, tuple, zone)) {
+				count = 0; /* hotdrop */
+				goto out_unlock;
+			}
+
+			count = rbconn->list.count;
+			goto out_unlock;
+		}
+	}
+
+	/* expected case: match, insert new node */
+	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
+	if (rbconn == NULL)
+		goto out_unlock;
+
+	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
+	if (conn == NULL) {
+		kmem_cache_free(conncount_rb_cachep, rbconn);
+		goto out_unlock;
+	}
+
+	conn->tuple = *tuple;
+	conn->zone = *zone;
+	memcpy(rbconn->key, key, sizeof(u32) * keylen);
+
+	nf_conncount_list_init(&rbconn->list);
+	list_add(&conn->node, &rbconn->list.head);
+	count = 1;
+
+	rb_link_node(&rbconn->node, parent, rbnode);
+	rb_insert_color(&rbconn->node, root);
+out_unlock:
+	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	return count;
+}
+
 static unsigned int
 count_tree(struct net *net,
 	   struct nf_conncount_data *data,
@@ -272,7 +337,6 @@ count_tree(struct net *net,
 	struct rb_root *root;
 	struct rb_node **rbnode, *parent;
 	struct nf_conncount_rb *rbconn;
-	struct nf_conncount_tuple *conn;
 	unsigned int gc_count, hash;
 	bool no_gc = false;
 	unsigned int count = 0;
@@ -339,27 +403,10 @@ count_tree(struct net *net,
 	count = 0;
 	if (!tuple)
 		goto out_unlock;
-	/* no match, need to insert new node */
-	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
-	if (rbconn == NULL)
-		goto out_unlock;
-
-	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
-	if (conn == NULL) {
-		kmem_cache_free(conncount_rb_cachep, rbconn);
-		goto out_unlock;
-	}
-
-	conn->tuple = *tuple;
-	conn->zone = *zone;
-	memcpy(rbconn->key, key, sizeof(u32) * keylen);
 
-	nf_conncount_list_init(&rbconn->list);
-	list_add(&conn->node, &rbconn->list.head);
-	count = 1;
+	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
+	return insert_tree(root, hash, key, keylen, tuple, zone);
 
-	rb_link_node(&rbconn->node, parent, rbnode);
-	rb_insert_color(&rbconn->node, root);
 out_unlock:
 	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
 	return count;
-- 
cgit v1.2.3


From 5c789e131cbb997a528451564ea4613e812fc718 Mon Sep 17 00:00:00 2001
From: Yi-Hung Wei <yihung.wei@gmail.com>
Date: Mon, 2 Jul 2018 17:33:44 -0700
Subject: netfilter: nf_conncount: Add list lock and gc worker, and RCU for
 init tree search

This patch is originally from Florian Westphal.

This patch does the following 3 main tasks.

1) Add list lock to 'struct nf_conncount_list' so that we can
alter the lists containing the individual connections without holding the
main tree lock.  It would be useful when we only need to add/remove to/from
a list without allocate/remove a node in the tree.  With this change, we
update nft_connlimit accordingly since we longer need to maintain
a list lock in nft_connlimit now.

2) Use RCU for the initial tree search to improve tree look up performance.

3) Add a garbage collection worker. This worker is schedule when there
are excessive tree node that needed to be recycled.

Moreover,the rbnode reclaim logic is moved from search tree to insert tree
to avoid race condition.

Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_count.h |  17 +-
 net/netfilter/nf_conncount.c               | 253 +++++++++++++++++++++--------
 net/netfilter/nft_connlimit.c              |  17 +-
 3 files changed, 196 insertions(+), 91 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_count.h b/include/net/netfilter/nf_conntrack_count.h
index dbec17f674b7..4b2b2baf8ab4 100644
--- a/include/net/netfilter/nf_conntrack_count.h
+++ b/include/net/netfilter/nf_conntrack_count.h
@@ -5,9 +5,17 @@
 
 struct nf_conncount_data;
 
+enum nf_conncount_list_add {
+	NF_CONNCOUNT_ADDED, 	/* list add was ok */
+	NF_CONNCOUNT_ERR,	/* -ENOMEM, must drop skb */
+	NF_CONNCOUNT_SKIP,	/* list is already reclaimed by gc */
+};
+
 struct nf_conncount_list {
+	spinlock_t list_lock;
 	struct list_head head;	/* connections with the same filtering key */
 	unsigned int count;	/* length of list */
+	bool dead;
 };
 
 struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family,
@@ -28,11 +36,12 @@ void nf_conncount_lookup(struct net *net, struct nf_conncount_list *list,
 
 void nf_conncount_list_init(struct nf_conncount_list *list);
 
-bool nf_conncount_add(struct nf_conncount_list *list,
-		      const struct nf_conntrack_tuple *tuple,
-		      const struct nf_conntrack_zone *zone);
+enum nf_conncount_list_add
+nf_conncount_add(struct nf_conncount_list *list,
+		 const struct nf_conntrack_tuple *tuple,
+		 const struct nf_conntrack_zone *zone);
 
-void nf_conncount_gc_list(struct net *net,
+bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list);
 
 void nf_conncount_cache_free(struct nf_conncount_list *list);
diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 3f14806b7271..02ca7df793f5 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -49,12 +49,14 @@ struct nf_conncount_tuple {
 	struct nf_conntrack_zone	zone;
 	int				cpu;
 	u32				jiffies32;
+	struct rcu_head			rcu_head;
 };
 
 struct nf_conncount_rb {
 	struct rb_node node;
 	struct nf_conncount_list list;
 	u32 key[MAX_KEYLEN];
+	struct rcu_head rcu_head;
 };
 
 static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_in_smp;
@@ -62,6 +64,10 @@ static spinlock_t nf_conncount_locks[CONNCOUNT_LOCK_SLOTS] __cacheline_aligned_i
 struct nf_conncount_data {
 	unsigned int keylen;
 	struct rb_root root[CONNCOUNT_SLOTS];
+	struct net *net;
+	struct work_struct gc_work;
+	unsigned long pending_trees[BITS_TO_LONGS(CONNCOUNT_SLOTS)];
+	unsigned int gc_tree;
 };
 
 static u_int32_t conncount_rnd __read_mostly;
@@ -82,42 +88,70 @@ static int key_diff(const u32 *a, const u32 *b, unsigned int klen)
 	return memcmp(a, b, klen * sizeof(u32));
 }
 
-bool nf_conncount_add(struct nf_conncount_list *list,
-		      const struct nf_conntrack_tuple *tuple,
-		      const struct nf_conntrack_zone *zone)
+enum nf_conncount_list_add
+nf_conncount_add(struct nf_conncount_list *list,
+		 const struct nf_conntrack_tuple *tuple,
+		 const struct nf_conntrack_zone *zone)
 {
 	struct nf_conncount_tuple *conn;
 
 	if (WARN_ON_ONCE(list->count > INT_MAX))
-		return false;
+		return NF_CONNCOUNT_ERR;
 
 	conn = kmem_cache_alloc(conncount_conn_cachep, GFP_ATOMIC);
 	if (conn == NULL)
-		return false;
+		return NF_CONNCOUNT_ERR;
+
 	conn->tuple = *tuple;
 	conn->zone = *zone;
 	conn->cpu = raw_smp_processor_id();
 	conn->jiffies32 = (u32)jiffies;
+	spin_lock(&list->list_lock);
+	if (list->dead == true) {
+		kmem_cache_free(conncount_conn_cachep, conn);
+		spin_unlock(&list->list_lock);
+		return NF_CONNCOUNT_SKIP;
+	}
 	list_add_tail(&conn->node, &list->head);
 	list->count++;
-	return true;
+	spin_unlock(&list->list_lock);
+	return NF_CONNCOUNT_ADDED;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_add);
 
-static void conn_free(struct nf_conncount_list *list,
+static void __conn_free(struct rcu_head *h)
+{
+	struct nf_conncount_tuple *conn;
+
+	conn = container_of(h, struct nf_conncount_tuple, rcu_head);
+	kmem_cache_free(conncount_conn_cachep, conn);
+}
+
+static bool conn_free(struct nf_conncount_list *list,
 		      struct nf_conncount_tuple *conn)
 {
-	if (WARN_ON_ONCE(list->count == 0))
-		return;
+	bool free_entry = false;
+
+	spin_lock(&list->list_lock);
+
+	if (list->count == 0) {
+		spin_unlock(&list->list_lock);
+                return free_entry;
+	}
 
 	list->count--;
-	list_del(&conn->node);
-	kmem_cache_free(conncount_conn_cachep, conn);
+	list_del_rcu(&conn->node);
+	if (list->count == 0)
+		free_entry = true;
+
+	spin_unlock(&list->list_lock);
+	call_rcu(&conn->rcu_head, __conn_free);
+	return free_entry;
 }
 
 static const struct nf_conntrack_tuple_hash *
 find_or_evict(struct net *net, struct nf_conncount_list *list,
-	      struct nf_conncount_tuple *conn)
+	      struct nf_conncount_tuple *conn, bool *free_entry)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	unsigned long a, b;
@@ -137,7 +171,7 @@ find_or_evict(struct net *net, struct nf_conncount_list *list,
 	 */
 	age = a - b;
 	if (conn->cpu == cpu || age >= 2) {
-		conn_free(list, conn);
+		*free_entry = conn_free(list, conn);
 		return ERR_PTR(-ENOENT);
 	}
 
@@ -154,6 +188,7 @@ void nf_conncount_lookup(struct net *net,
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
 	unsigned int collect = 0;
+	bool free_entry = false;
 
 	/* best effort only */
 	*addit = tuple ? true : false;
@@ -163,7 +198,7 @@ void nf_conncount_lookup(struct net *net,
 		if (collect > CONNCOUNT_GC_MAX_NODES)
 			break;
 
-		found = find_or_evict(net, list, conn);
+		found = find_or_evict(net, list, conn, &free_entry);
 		if (IS_ERR(found)) {
 			/* Not found, but might be about to be confirmed */
 			if (PTR_ERR(found) == -EAGAIN) {
@@ -208,24 +243,31 @@ EXPORT_SYMBOL_GPL(nf_conncount_lookup);
 
 void nf_conncount_list_init(struct nf_conncount_list *list)
 {
+	spin_lock_init(&list->list_lock);
 	INIT_LIST_HEAD(&list->head);
 	list->count = 1;
+	list->dead = false;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_list_init);
 
-void nf_conncount_gc_list(struct net *net,
+/* Return true if the list is empty */
+bool nf_conncount_gc_list(struct net *net,
 			  struct nf_conncount_list *list)
 {
 	const struct nf_conntrack_tuple_hash *found;
 	struct nf_conncount_tuple *conn, *conn_n;
 	struct nf_conn *found_ct;
 	unsigned int collected = 0;
+	bool free_entry = false;
 
 	list_for_each_entry_safe(conn, conn_n, &list->head, node) {
-		found = find_or_evict(net, list, conn);
+		found = find_or_evict(net, list, conn, &free_entry);
 		if (IS_ERR(found)) {
-			if (PTR_ERR(found) == -ENOENT)
+			if (PTR_ERR(found) == -ENOENT)  {
+				if (free_entry)
+					return true;
 				collected++;
+			}
 			continue;
 		}
 
@@ -236,18 +278,28 @@ void nf_conncount_gc_list(struct net *net,
 			 * closed already -> ditch it
 			 */
 			nf_ct_put(found_ct);
-			conn_free(list, conn);
+			if (conn_free(list, conn))
+				return true;
 			collected++;
 			continue;
 		}
 
 		nf_ct_put(found_ct);
 		if (collected > CONNCOUNT_GC_MAX_NODES)
-			return;
+			return false;
 	}
+	return false;
 }
 EXPORT_SYMBOL_GPL(nf_conncount_gc_list);
 
+static void __tree_nodes_free(struct rcu_head *h)
+{
+	struct nf_conncount_rb *rbconn;
+
+	rbconn = container_of(h, struct nf_conncount_rb, rcu_head);
+	kmem_cache_free(conncount_rb_cachep, rbconn);
+}
+
 static void tree_nodes_free(struct rb_root *root,
 			    struct nf_conncount_rb *gc_nodes[],
 			    unsigned int gc_count)
@@ -256,23 +308,39 @@ static void tree_nodes_free(struct rb_root *root,
 
 	while (gc_count) {
 		rbconn = gc_nodes[--gc_count];
-		rb_erase(&rbconn->node, root);
-		kmem_cache_free(conncount_rb_cachep, rbconn);
+		spin_lock(&rbconn->list.list_lock);
+		if (rbconn->list.count == 0 && rbconn->list.dead == false) {
+			rbconn->list.dead = true;
+			rb_erase(&rbconn->node, root);
+			call_rcu(&rbconn->rcu_head, __tree_nodes_free);
+		}
+		spin_unlock(&rbconn->list.list_lock);
 	}
 }
 
+static void schedule_gc_worker(struct nf_conncount_data *data, int tree)
+{
+	set_bit(tree, data->pending_trees);
+	schedule_work(&data->gc_work);
+}
+
 static unsigned int
-insert_tree(struct rb_root *root,
+insert_tree(struct net *net,
+	    struct nf_conncount_data *data,
+	    struct rb_root *root,
 	    unsigned int hash,
 	    const u32 *key,
 	    u8 keylen,
 	    const struct nf_conntrack_tuple *tuple,
 	    const struct nf_conntrack_zone *zone)
 {
+	enum nf_conncount_list_add ret;
+	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
 	struct rb_node **rbnode, *parent;
 	struct nf_conncount_rb *rbconn;
 	struct nf_conncount_tuple *conn;
-	unsigned int count = 0;
+	unsigned int count = 0, gc_count = 0;
+	bool node_found = false;
 
 	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
 
@@ -290,16 +358,44 @@ insert_tree(struct rb_root *root,
 			rbnode = &((*rbnode)->rb_right);
 		} else {
 			/* unlikely: other cpu added node already */
-			if (!nf_conncount_add(&rbconn->list, tuple, zone)) {
+			node_found = true;
+			ret = nf_conncount_add(&rbconn->list, tuple, zone);
+			if (ret == NF_CONNCOUNT_ERR) {
 				count = 0; /* hotdrop */
-				goto out_unlock;
+			} else if (ret == NF_CONNCOUNT_ADDED) {
+				count = rbconn->list.count;
+			} else {
+				/* NF_CONNCOUNT_SKIP, rbconn is already
+				 * reclaimed by gc, insert a new tree node
+				 */
+				node_found = false;
 			}
-
-			count = rbconn->list.count;
-			goto out_unlock;
+			break;
 		}
+
+		if (gc_count >= ARRAY_SIZE(gc_nodes))
+			continue;
+
+		if (nf_conncount_gc_list(net, &rbconn->list))
+			gc_nodes[gc_count++] = rbconn;
+	}
+
+	if (gc_count) {
+		tree_nodes_free(root, gc_nodes, gc_count);
+		/* tree_node_free before new allocation permits
+		 * allocator to re-use newly free'd object.
+		 *
+		 * This is a rare event; in most cases we will find
+		 * existing node to re-use. (or gc_count is 0).
+		 */
+
+		if (gc_count >= ARRAY_SIZE(gc_nodes))
+			schedule_gc_worker(data, hash);
 	}
 
+	if (node_found)
+		goto out_unlock;
+
 	/* expected case: match, insert new node */
 	rbconn = kmem_cache_alloc(conncount_rb_cachep, GFP_ATOMIC);
 	if (rbconn == NULL)
@@ -333,87 +429,97 @@ count_tree(struct net *net,
 	   const struct nf_conntrack_tuple *tuple,
 	   const struct nf_conntrack_zone *zone)
 {
-	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES];
+	enum nf_conncount_list_add ret;
 	struct rb_root *root;
-	struct rb_node **rbnode, *parent;
+	struct rb_node *parent;
 	struct nf_conncount_rb *rbconn;
-	unsigned int gc_count, hash;
-	bool no_gc = false;
-	unsigned int count = 0;
+	unsigned int hash;
 	u8 keylen = data->keylen;
 
 	hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
 	root = &data->root[hash];
 
-	spin_lock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
- restart:
-	gc_count = 0;
-	parent = NULL;
-	rbnode = &(root->rb_node);
-	while (*rbnode) {
+	parent = rcu_dereference_raw(root->rb_node);
+	while (parent) {
 		int diff;
 		bool addit;
 
-		rbconn = rb_entry(*rbnode, struct nf_conncount_rb, node);
+		rbconn = rb_entry(parent, struct nf_conncount_rb, node);
 
-		parent = *rbnode;
 		diff = key_diff(key, rbconn->key, keylen);
 		if (diff < 0) {
-			rbnode = &((*rbnode)->rb_left);
+			parent = rcu_dereference_raw(parent->rb_left);
 		} else if (diff > 0) {
-			rbnode = &((*rbnode)->rb_right);
+			parent = rcu_dereference_raw(parent->rb_right);
 		} else {
 			/* same source network -> be counted! */
 			nf_conncount_lookup(net, &rbconn->list, tuple, zone,
 					    &addit);
-			count = rbconn->list.count;
 
-			tree_nodes_free(root, gc_nodes, gc_count);
 			if (!addit)
-				goto out_unlock;
+				return rbconn->list.count;
+
+			ret = nf_conncount_add(&rbconn->list, tuple, zone);
+			if (ret == NF_CONNCOUNT_ERR) {
+				return 0; /* hotdrop */
+			} else if (ret == NF_CONNCOUNT_ADDED) {
+				return rbconn->list.count;
+			} else {
+				/* NF_CONNCOUNT_SKIP, rbconn is already
+				 * reclaimed by gc, insert a new tree node
+				 */
+				break;
+			}
+		}
+	}
 
-			if (!nf_conncount_add(&rbconn->list, tuple, zone))
-				count = 0; /* hotdrop */
-				goto out_unlock;
+	if (!tuple)
+		return 0;
 
-			count++;
-			goto out_unlock;
-		}
+	return insert_tree(net, data, root, hash, key, keylen, tuple, zone);
+}
 
-		if (no_gc || gc_count >= ARRAY_SIZE(gc_nodes))
-			continue;
+static void tree_gc_worker(struct work_struct *work)
+{
+	struct nf_conncount_data *data = container_of(work, struct nf_conncount_data, gc_work);
+	struct nf_conncount_rb *gc_nodes[CONNCOUNT_GC_MAX_NODES], *rbconn;
+	struct rb_root *root;
+	struct rb_node *node;
+	unsigned int tree, next_tree, gc_count = 0;
+
+	tree = data->gc_tree % CONNCOUNT_LOCK_SLOTS;
+	root = &data->root[tree];
 
-		nf_conncount_gc_list(net, &rbconn->list);
-		if (list_empty(&rbconn->list.head))
+	rcu_read_lock();
+	for (node = rb_first(root); node != NULL; node = rb_next(node)) {
+		rbconn = rb_entry(node, struct nf_conncount_rb, node);
+		if (nf_conncount_gc_list(data->net, &rbconn->list))
 			gc_nodes[gc_count++] = rbconn;
 	}
+	rcu_read_unlock();
+
+	spin_lock_bh(&nf_conncount_locks[tree]);
 
 	if (gc_count) {
-		no_gc = true;
 		tree_nodes_free(root, gc_nodes, gc_count);
-		/* tree_node_free before new allocation permits
-		 * allocator to re-use newly free'd object.
-		 *
-		 * This is a rare event; in most cases we will find
-		 * existing node to re-use. (or gc_count is 0).
-		 */
-		goto restart;
 	}
 
-	count = 0;
-	if (!tuple)
-		goto out_unlock;
+	clear_bit(tree, data->pending_trees);
 
-	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
-	return insert_tree(root, hash, key, keylen, tuple, zone);
+	next_tree = (tree + 1) % CONNCOUNT_SLOTS;
+	next_tree = find_next_bit(data->pending_trees, next_tree, CONNCOUNT_SLOTS);
 
-out_unlock:
-	spin_unlock_bh(&nf_conncount_locks[hash % CONNCOUNT_LOCK_SLOTS]);
-	return count;
+	if (next_tree < CONNCOUNT_SLOTS) {
+		data->gc_tree = next_tree;
+		schedule_work(work);
+	}
+
+	spin_unlock_bh(&nf_conncount_locks[tree]);
 }
 
 /* Count and return number of conntrack entries in 'net' with particular 'key'.
  * If 'tuple' is not null, insert it into the accounting data structure.
+ * Call with RCU read lock.
  */
 unsigned int nf_conncount_count(struct net *net,
 				struct nf_conncount_data *data,
@@ -452,6 +558,8 @@ struct nf_conncount_data *nf_conncount_init(struct net *net, unsigned int family
 		data->root[i] = RB_ROOT;
 
 	data->keylen = keylen / sizeof(u32);
+	data->net = net;
+	INIT_WORK(&data->gc_work, tree_gc_worker);
 
 	return data;
 }
@@ -487,6 +595,7 @@ void nf_conncount_destroy(struct net *net, unsigned int family,
 {
 	unsigned int i;
 
+	cancel_work_sync(&data->gc_work);
 	nf_ct_netns_put(net, family);
 
 	for (i = 0; i < ARRAY_SIZE(data->root); ++i)
diff --git a/net/netfilter/nft_connlimit.c b/net/netfilter/nft_connlimit.c
index 37c52ae06741..b90d96ba4a12 100644
--- a/net/netfilter/nft_connlimit.c
+++ b/net/netfilter/nft_connlimit.c
@@ -14,7 +14,6 @@
 #include <net/netfilter/nf_conntrack_zones.h>
 
 struct nft_connlimit {
-	spinlock_t			lock;
 	struct nf_conncount_list	list;
 	u32				limit;
 	bool				invert;
@@ -45,7 +44,6 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 		return;
 	}
 
-	spin_lock_bh(&priv->lock);
 	nf_conncount_lookup(nft_net(pkt), &priv->list, tuple_ptr, zone,
 			    &addit);
 	count = priv->list.count;
@@ -53,14 +51,12 @@ static inline void nft_connlimit_do_eval(struct nft_connlimit *priv,
 	if (!addit)
 		goto out;
 
-	if (!nf_conncount_add(&priv->list, tuple_ptr, zone)) {
+	if (nf_conncount_add(&priv->list, tuple_ptr, zone) == NF_CONNCOUNT_ERR) {
 		regs->verdict.code = NF_DROP;
-		spin_unlock_bh(&priv->lock);
 		return;
 	}
 	count++;
 out:
-	spin_unlock_bh(&priv->lock);
 
 	if ((count > priv->limit) ^ priv->invert) {
 		regs->verdict.code = NFT_BREAK;
@@ -88,7 +84,6 @@ static int nft_connlimit_do_init(const struct nft_ctx *ctx,
 			invert = true;
 	}
 
-	spin_lock_init(&priv->lock);
 	nf_conncount_list_init(&priv->list);
 	priv->limit	= limit;
 	priv->invert	= invert;
@@ -213,7 +208,6 @@ static int nft_connlimit_clone(struct nft_expr *dst, const struct nft_expr *src)
 	struct nft_connlimit *priv_dst = nft_expr_priv(dst);
 	struct nft_connlimit *priv_src = nft_expr_priv(src);
 
-	spin_lock_init(&priv_dst->lock);
 	nf_conncount_list_init(&priv_dst->list);
 	priv_dst->limit	 = priv_src->limit;
 	priv_dst->invert = priv_src->invert;
@@ -232,15 +226,8 @@ static void nft_connlimit_destroy_clone(const struct nft_ctx *ctx,
 static bool nft_connlimit_gc(struct net *net, const struct nft_expr *expr)
 {
 	struct nft_connlimit *priv = nft_expr_priv(expr);
-	bool ret;
 
-	spin_lock_bh(&priv->lock);
-	nf_conncount_gc_list(net, &priv->list);
-
-	ret = list_empty(&priv->list.head);
-	spin_unlock_bh(&priv->lock);
-
-	return ret;
+	return nf_conncount_gc_list(net, &priv->list);
 }
 
 static struct nft_expr_type nft_connlimit_type;
-- 
cgit v1.2.3


From ed07d9a021df6da53456663a76999189badc432a Mon Sep 17 00:00:00 2001
From: Martynas Pumputis <martynas@weave.works>
Date: Mon, 2 Jul 2018 16:52:14 +0200
Subject: netfilter: nf_conntrack: resolve clash for matching conntracks

This patch enables the clash resolution for NAT (disabled in
"590b52e10d41") if clashing conntracks match (i.e. both tuples are equal)
and a protocol allows it.

The clash might happen for a connections-less protocol (e.g. UDP) when
two threads in parallel writes to the same socket and consequent calls
to "get_unique_tuple" return the same tuples (incl. reply tuples).

In this case it is safe to perform the resolution, as the losing CT
describes the same mangling as the winning CT, so no modifications to
the packet are needed, and the result of rules traversal for the loser's
packet stays valid.

Signed-off-by: Martynas Pumputis <martynas@weave.works>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_core.c | 30 ++++++++++++++++++++++--------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 5123e91b1982..4ced7c7102b6 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -632,6 +632,18 @@ nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
 	       net_eq(net, nf_ct_net(ct));
 }
 
+static inline bool
+nf_ct_match(const struct nf_conn *ct1, const struct nf_conn *ct2)
+{
+	return nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
+				 &ct2->tuplehash[IP_CT_DIR_ORIGINAL].tuple) &&
+	       nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_REPLY].tuple,
+				 &ct2->tuplehash[IP_CT_DIR_REPLY].tuple) &&
+	       nf_ct_zone_equal(ct1, nf_ct_zone(ct2), IP_CT_DIR_ORIGINAL) &&
+	       nf_ct_zone_equal(ct1, nf_ct_zone(ct2), IP_CT_DIR_REPLY) &&
+	       net_eq(nf_ct_net(ct1), nf_ct_net(ct2));
+}
+
 /* caller must hold rcu readlock and none of the nf_conntrack_locks */
 static void nf_ct_gc_expired(struct nf_conn *ct)
 {
@@ -825,19 +837,21 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
 	/* This is the conntrack entry already in hashes that won race. */
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
 	const struct nf_conntrack_l4proto *l4proto;
+	enum ip_conntrack_info oldinfo;
+	struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo);
 
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto->allow_clash &&
-	    ((ct->status & IPS_NAT_DONE_MASK) == 0) &&
 	    !nf_ct_is_dying(ct) &&
 	    atomic_inc_not_zero(&ct->ct_general.use)) {
-		enum ip_conntrack_info oldinfo;
-		struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo);
-
-		nf_ct_acct_merge(ct, ctinfo, loser_ct);
-		nf_conntrack_put(&loser_ct->ct_general);
-		nf_ct_set(skb, ct, oldinfo);
-		return NF_ACCEPT;
+		if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
+		    nf_ct_match(ct, loser_ct)) {
+			nf_ct_acct_merge(ct, ctinfo, loser_ct);
+			nf_conntrack_put(&loser_ct->ct_general);
+			nf_ct_set(skb, ct, oldinfo);
+			return NF_ACCEPT;
+		}
+		nf_ct_put(ct);
 	}
 	NF_CT_STAT_INC(net, drop);
 	return NF_DROP;
-- 
cgit v1.2.3


From ec1b28ca9674def4a158808a6493bdb87b993d81 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 6 Jul 2018 08:25:52 +0300
Subject: ipvs: provide just conn to ip_vs_state_name

In preparation for followup patches, provide just the cp
ptr to ip_vs_state_name.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h              | 2 +-
 net/netfilter/ipvs/ip_vs_conn.c  | 8 ++++----
 net/netfilter/ipvs/ip_vs_proto.c | 8 ++++----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index a0bec23c6d5e..4d76abcf1c41 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -1221,7 +1221,7 @@ struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, int dest_af,
 				  struct ip_vs_dest *dest, __u32 fwmark);
 void ip_vs_conn_expire_now(struct ip_vs_conn *cp);
 
-const char *ip_vs_state_name(__u16 proto, int state);
+const char *ip_vs_state_name(const struct ip_vs_conn *cp);
 
 void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp);
 int ip_vs_check_template(struct ip_vs_conn *ct, struct ip_vs_dest *cdest);
diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 99e0aa350dc5..de5a64e42ebd 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -1107,7 +1107,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 				&cp->caddr.in6, ntohs(cp->cport),
 				&cp->vaddr.in6, ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
-				ip_vs_state_name(cp->protocol, cp->state),
+				ip_vs_state_name(cp),
 				(cp->timer.expires-jiffies)/HZ, pe_data);
 		else
 #endif
@@ -1118,7 +1118,7 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v)
 				ntohl(cp->caddr.ip), ntohs(cp->cport),
 				ntohl(cp->vaddr.ip), ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
-				ip_vs_state_name(cp->protocol, cp->state),
+				ip_vs_state_name(cp),
 				(cp->timer.expires-jiffies)/HZ, pe_data);
 	}
 	return 0;
@@ -1169,7 +1169,7 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
 				&cp->caddr.in6, ntohs(cp->cport),
 				&cp->vaddr.in6, ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
-				ip_vs_state_name(cp->protocol, cp->state),
+				ip_vs_state_name(cp),
 				ip_vs_origin_name(cp->flags),
 				(cp->timer.expires-jiffies)/HZ);
 		else
@@ -1181,7 +1181,7 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v)
 				ntohl(cp->caddr.ip), ntohs(cp->cport),
 				ntohl(cp->vaddr.ip), ntohs(cp->vport),
 				dbuf, ntohs(cp->dport),
-				ip_vs_state_name(cp->protocol, cp->state),
+				ip_vs_state_name(cp),
 				ip_vs_origin_name(cp->flags),
 				(cp->timer.expires-jiffies)/HZ);
 	}
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index ca880a3ad033..85c446621758 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -193,13 +193,13 @@ ip_vs_create_timeout_table(int *table, int size)
 }
 
 
-const char * ip_vs_state_name(__u16 proto, int state)
+const char *ip_vs_state_name(const struct ip_vs_conn *cp)
 {
-	struct ip_vs_protocol *pp = ip_vs_proto_get(proto);
+	struct ip_vs_protocol *pp = ip_vs_proto_get(cp->protocol);
 
 	if (pp == NULL || pp->state_name == NULL)
-		return (IPPROTO_IP == proto) ? "NONE" : "ERR!";
-	return pp->state_name(state);
+		return (cp->protocol == IPPROTO_IP) ? "NONE" : "ERR!";
+	return pp->state_name(cp->state);
 }
 
 
-- 
cgit v1.2.3


From 275411430f892407b885be1de2548b2e632892c3 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 6 Jul 2018 08:25:53 +0300
Subject: ipvs: add assured state for conn templates

cp->state was not used for templates. Add support for state bits
and for the first "assured" bit which indicates that some
connection controlled by this template was established or assured
by the real server. In a followup patch we will use it to drop
templates under SYN attack.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ip_vs.h                   | 16 ++++++++++++++++
 net/netfilter/ipvs/ip_vs_proto.c      | 17 +++++++++++++++--
 net/netfilter/ipvs/ip_vs_proto_sctp.c |  2 ++
 net/netfilter/ipvs/ip_vs_proto_tcp.c  |  2 ++
 net/netfilter/ipvs/ip_vs_proto_udp.c  |  2 ++
 net/netfilter/ipvs/ip_vs_sync.c       | 18 ++++++------------
 6 files changed, 43 insertions(+), 14 deletions(-)

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 4d76abcf1c41..a0d2e0bb9a94 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -335,6 +335,11 @@ enum ip_vs_sctp_states {
 	IP_VS_SCTP_S_LAST
 };
 
+/* Connection templates use bits from state */
+#define IP_VS_CTPL_S_NONE		0x0000
+#define IP_VS_CTPL_S_ASSURED		0x0001
+#define IP_VS_CTPL_S_LAST		0x0002
+
 /* Delta sequence info structure
  * Each ip_vs_conn has 2 (output AND input seq. changes).
  * Only used in the VS/NAT.
@@ -1289,6 +1294,17 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp)
 	atomic_inc(&ctl_cp->n_control);
 }
 
+/* Mark our template as assured */
+static inline void
+ip_vs_control_assure_ct(struct ip_vs_conn *cp)
+{
+	struct ip_vs_conn *ct = cp->control;
+
+	if (ct && !(ct->state & IP_VS_CTPL_S_ASSURED) &&
+	    (ct->flags & IP_VS_CONN_F_TEMPLATE))
+		ct->state |= IP_VS_CTPL_S_ASSURED;
+}
+
 /* IPVS netns init & cleanup functions */
 int ip_vs_estimator_net_init(struct netns_ipvs *ipvs);
 int ip_vs_control_net_init(struct netns_ipvs *ipvs);
diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c
index 85c446621758..54ee84adf0bd 100644
--- a/net/netfilter/ipvs/ip_vs_proto.c
+++ b/net/netfilter/ipvs/ip_vs_proto.c
@@ -42,6 +42,11 @@
 
 static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE];
 
+/* States for conn templates: NONE or words separated with ",", max 15 chars */
+static const char *ip_vs_ctpl_state_name_table[IP_VS_CTPL_S_LAST] = {
+	[IP_VS_CTPL_S_NONE]			= "NONE",
+	[IP_VS_CTPL_S_ASSURED]			= "ASSURED",
+};
 
 /*
  *	register an ipvs protocol
@@ -195,11 +200,19 @@ ip_vs_create_timeout_table(int *table, int size)
 
 const char *ip_vs_state_name(const struct ip_vs_conn *cp)
 {
-	struct ip_vs_protocol *pp = ip_vs_proto_get(cp->protocol);
+	unsigned int state = cp->state;
+	struct ip_vs_protocol *pp;
+
+	if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
 
+		if (state >= IP_VS_CTPL_S_LAST)
+			return "ERR!";
+		return ip_vs_ctpl_state_name_table[state] ? : "?";
+	}
+	pp = ip_vs_proto_get(cp->protocol);
 	if (pp == NULL || pp->state_name == NULL)
 		return (cp->protocol == IPPROTO_IP) ? "NONE" : "ERR!";
-	return pp->state_name(cp->state);
+	return pp->state_name(state);
 }
 
 
diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index 3250c4a1111e..b0cd7d08f2a7 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -461,6 +461,8 @@ set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 				cp->flags &= ~IP_VS_CONN_F_INACTIVE;
 			}
 		}
+		if (next_state == IP_VS_SCTP_S_ESTABLISHED)
+			ip_vs_control_assure_ct(cp);
 	}
 	if (likely(pd))
 		cp->timeout = pd->timeout_table[cp->state = next_state];
diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c
index 80d10ad12a15..1770fc6ce960 100644
--- a/net/netfilter/ipvs/ip_vs_proto_tcp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c
@@ -569,6 +569,8 @@ set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp,
 				cp->flags &= ~IP_VS_CONN_F_INACTIVE;
 			}
 		}
+		if (new_state == IP_VS_TCP_S_ESTABLISHED)
+			ip_vs_control_assure_ct(cp);
 	}
 
 	if (likely(pd))
diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c
index e0ef11c3691e..0f53c49025f8 100644
--- a/net/netfilter/ipvs/ip_vs_proto_udp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_udp.c
@@ -460,6 +460,8 @@ udp_state_transition(struct ip_vs_conn *cp, int direction,
 	}
 
 	cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL];
+	if (direction == IP_VS_DIR_OUTPUT)
+		ip_vs_control_assure_ct(cp);
 }
 
 static int __udp_init(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd)
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 001501e25625..d4020c5e831d 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1003,12 +1003,9 @@ static void ip_vs_process_message_v0(struct netns_ipvs *ipvs, const char *buffer
 				continue;
 			}
 		} else {
-			/* protocol in templates is not used for state/timeout */
-			if (state > 0) {
-				IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n",
-					state);
-				state = 0;
-			}
+			if (state >= IP_VS_CTPL_S_LAST)
+				IP_VS_DBG(7, "BACKUP v0, Invalid tpl state %u\n",
+					  state);
 		}
 
 		ip_vs_conn_fill_param(ipvs, AF_INET, s->protocol,
@@ -1166,12 +1163,9 @@ static inline int ip_vs_proc_sync_conn(struct netns_ipvs *ipvs, __u8 *p, __u8 *m
 			goto out;
 		}
 	} else {
-		/* protocol in templates is not used for state/timeout */
-		if (state > 0) {
-			IP_VS_DBG(3, "BACKUP, Invalid template state %u\n",
-				state);
-			state = 0;
-		}
+		if (state >= IP_VS_CTPL_S_LAST)
+			IP_VS_DBG(7, "BACKUP, Invalid tpl state %u\n",
+				  state);
 	}
 	if (ip_vs_conn_fill_param_sync(ipvs, af, s, &param, pe_data,
 				       pe_data_len, pe_name, pe_name_len)) {
-- 
cgit v1.2.3


From 762c40076684771c0efbce6490ded26086441ce6 Mon Sep 17 00:00:00 2001
From: Julian Anastasov <ja@ssi.bg>
Date: Fri, 6 Jul 2018 08:25:54 +0300
Subject: ipvs: drop conn templates under attack
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Before now, connection templates were ignored by the random
dropentry procedure. But Michal Koutný suggests that we
should add exception for connections under SYN attack.
He provided patch that implements it for TCP:

<quote>

IPVS includes protection against filling the ip_vs_conn_tab by
dropping 1/32 of feasible entries every second. The template
entries (for persistent services) are never directly deleted by
this mechanism but when a picked TCP connection entry is being
dropped (1), the respective template entry is dropped too (realized
by expiring 60 seconds after the connection entry being dropped).

There is another mechanism that removes connection entries when they
time out (2), in this case the associated template entry is not deleted.
Under SYN flood template entries would accumulate (due to their entry
longer timeout).

The accumulation takes place also with drop_entry being enabled. Roughly
15% ((31/32)^60) of SYN_RECV connections survive the dropping mechanism
(1) and are removed by the timeout mechanism (2)(defaults to 60 seconds
for SYN_RECV), thus template entries would still accumulate.

The patch ensures that when a connection entry times out, we also remove
the template entry from the table. To prevent breaking persistent
services (since the connection may time out in already established state)
we add a new entry flag to protect templates what spawned at least one
established TCP connection.

</quote>

We already added ASSURED flag for the templates in previous patch, so
that we can use it now to decide which connection templates should be
dropped under attack. But we also have some cases that need special
handling.

We modify the dropentry procedure as follows:

- Linux timers currently use LIFO ordering but we can not rely on
this to drop controlling connections. So, set cp->timeout to 0
to indicate that connection was dropped and that on expiration we
should try to drop our controlling connections. As result, we can
now avoid the ip_vs_conn_expire_now call.

- move the cp->n_control check above, so that it avoids restarting
the timer for controlling connections when not needed.

- drop unassured connection templates here if they are not referred
by any connections.

On connection expiration: if connection was dropped (cp->timeout=0)
try to drop our controlling connection except if it is a template
in assured state.

In ip_vs_conn_flush change order of ip_vs_conn_expire_now calls
according to the LIFO timer expiration order. It should work
faster for controlling connections with single controlled one.

Suggested-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipvs/ip_vs_conn.c | 59 +++++++++++++++++++++++++++--------------
 1 file changed, 39 insertions(+), 20 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index de5a64e42ebd..0edc62910ebf 100644
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -825,12 +825,23 @@ static void ip_vs_conn_expire(struct timer_list *t)
 
 	/* Unlink conn if not referenced anymore */
 	if (likely(ip_vs_conn_unlink(cp))) {
+		struct ip_vs_conn *ct = cp->control;
+
 		/* delete the timer if it is activated by other users */
 		del_timer(&cp->timer);
 
 		/* does anybody control me? */
-		if (cp->control)
+		if (ct) {
 			ip_vs_control_del(cp);
+			/* Drop CTL or non-assured TPL if not used anymore */
+			if (!cp->timeout && !atomic_read(&ct->n_control) &&
+			    (!(ct->flags & IP_VS_CONN_F_TEMPLATE) ||
+			     !(ct->state & IP_VS_CTPL_S_ASSURED))) {
+				IP_VS_DBG(4, "drop controlling connection\n");
+				ct->timeout = 0;
+				ip_vs_conn_expire_now(ct);
+			}
+		}
 
 		if ((cp->flags & IP_VS_CONN_F_NFCT) &&
 		    !(cp->flags & IP_VS_CONN_F_ONE_PACKET)) {
@@ -872,6 +883,10 @@ static void ip_vs_conn_expire(struct timer_list *t)
 
 /* Modify timer, so that it expires as soon as possible.
  * Can be called without reference only if under RCU lock.
+ * We can have such chain of conns linked with ->control: DATA->CTL->TPL
+ * - DATA (eg. FTP) and TPL (persistence) can be present depending on setup
+ * - cp->timeout=0 indicates all conns from chain should be dropped but
+ * TPL is not dropped if in assured state
  */
 void ip_vs_conn_expire_now(struct ip_vs_conn *cp)
 {
@@ -1197,8 +1212,11 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = {
 #endif
 
 
-/*
- *      Randomly drop connection entries before running out of memory
+/* Randomly drop connection entries before running out of memory
+ * Can be used for DATA and CTL conns. For TPL conns there are exceptions:
+ * - traffic for services in OPS mode increases ct->in_pkts, so it is supported
+ * - traffic for services not in OPS mode does not increase ct->in_pkts in
+ * all cases, so it is not supported
  */
 static inline int todrop_entry(struct ip_vs_conn *cp)
 {
@@ -1242,7 +1260,7 @@ static inline bool ip_vs_conn_ops_mode(struct ip_vs_conn *cp)
 void ip_vs_random_dropentry(struct netns_ipvs *ipvs)
 {
 	int idx;
-	struct ip_vs_conn *cp, *cp_c;
+	struct ip_vs_conn *cp;
 
 	rcu_read_lock();
 	/*
@@ -1254,13 +1272,15 @@ void ip_vs_random_dropentry(struct netns_ipvs *ipvs)
 		hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[hash], c_list) {
 			if (cp->ipvs != ipvs)
 				continue;
+			if (atomic_read(&cp->n_control))
+				continue;
 			if (cp->flags & IP_VS_CONN_F_TEMPLATE) {
-				if (atomic_read(&cp->n_control) ||
-				    !ip_vs_conn_ops_mode(cp))
-					continue;
-				else
-					/* connection template of OPS */
+				/* connection template of OPS */
+				if (ip_vs_conn_ops_mode(cp))
 					goto try_drop;
+				if (!(cp->state & IP_VS_CTPL_S_ASSURED))
+					goto drop;
+				continue;
 			}
 			if (cp->protocol == IPPROTO_TCP) {
 				switch(cp->state) {
@@ -1294,15 +1314,10 @@ try_drop:
 					continue;
 			}
 
-			IP_VS_DBG(4, "del connection\n");
+drop:
+			IP_VS_DBG(4, "drop connection\n");
+			cp->timeout = 0;
 			ip_vs_conn_expire_now(cp);
-			cp_c = cp->control;
-			/* cp->control is valid only with reference to cp */
-			if (cp_c && __ip_vs_conn_get(cp)) {
-				IP_VS_DBG(4, "del conn template\n");
-				ip_vs_conn_expire_now(cp_c);
-				__ip_vs_conn_put(cp);
-			}
 		}
 		cond_resched_rcu();
 	}
@@ -1325,15 +1340,19 @@ flush_again:
 		hlist_for_each_entry_rcu(cp, &ip_vs_conn_tab[idx], c_list) {
 			if (cp->ipvs != ipvs)
 				continue;
-			IP_VS_DBG(4, "del connection\n");
-			ip_vs_conn_expire_now(cp);
+			/* As timers are expired in LIFO order, restart
+			 * the timer of controlling connection first, so
+			 * that it is expired after us.
+			 */
 			cp_c = cp->control;
 			/* cp->control is valid only with reference to cp */
 			if (cp_c && __ip_vs_conn_get(cp)) {
-				IP_VS_DBG(4, "del conn template\n");
+				IP_VS_DBG(4, "del controlling connection\n");
 				ip_vs_conn_expire_now(cp_c);
 				__ip_vs_conn_put(cp);
 			}
+			IP_VS_DBG(4, "del connection\n");
+			ip_vs_conn_expire_now(cp);
 		}
 		cond_resched_rcu();
 	}
-- 
cgit v1.2.3


From 440534d3c56be04abfb26850ee882d19d223557a Mon Sep 17 00:00:00 2001
From: Gao Feng <gfree.wind@vip.163.com>
Date: Mon, 9 Jul 2018 18:06:33 +0800
Subject: netfilter: Remove useless param helper of nf_ct_helper_ext_add

The param helper of nf_ct_helper_ext_add is useless now, then remove
it now.

Signed-off-by: Gao Feng <gfree.wind@vip.163.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_helper.h | 4 +---
 net/netfilter/nf_conntrack_core.c           | 3 +--
 net/netfilter/nf_conntrack_helper.c         | 5 ++---
 net/netfilter/nf_conntrack_netlink.c        | 2 +-
 net/netfilter/nft_ct.c                      | 2 +-
 net/netfilter/xt_CT.c                       | 2 +-
 net/openvswitch/conntrack.c                 | 2 +-
 7 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h
index 32c2a94a219d..2492120b8097 100644
--- a/include/net/netfilter/nf_conntrack_helper.h
+++ b/include/net/netfilter/nf_conntrack_helper.h
@@ -103,9 +103,7 @@ int nf_conntrack_helpers_register(struct nf_conntrack_helper *, unsigned int);
 void nf_conntrack_helpers_unregister(struct nf_conntrack_helper *,
 				     unsigned int);
 
-struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct,
-					  struct nf_conntrack_helper *helper,
-					  gfp_t gfp);
+struct nf_conn_help *nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp);
 
 int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 			      gfp_t flags);
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 4ced7c7102b6..d97d7e9a9ee7 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1401,8 +1401,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 			/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
 			ct->master = exp->master;
 			if (exp->helper) {
-				help = nf_ct_helper_ext_add(ct, exp->helper,
-							    GFP_ATOMIC);
+				help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 				if (help)
 					rcu_assign_pointer(help->helper, exp->helper);
 			}
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index a55a58c706a9..d557a425289d 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -192,8 +192,7 @@ void nf_conntrack_helper_put(struct nf_conntrack_helper *helper)
 EXPORT_SYMBOL_GPL(nf_conntrack_helper_put);
 
 struct nf_conn_help *
-nf_ct_helper_ext_add(struct nf_conn *ct,
-		     struct nf_conntrack_helper *helper, gfp_t gfp)
+nf_ct_helper_ext_add(struct nf_conn *ct, gfp_t gfp)
 {
 	struct nf_conn_help *help;
 
@@ -262,7 +261,7 @@ int __nf_ct_try_assign_helper(struct nf_conn *ct, struct nf_conn *tmpl,
 	}
 
 	if (help == NULL) {
-		help = nf_ct_helper_ext_add(ct, helper, flags);
+		help = nf_ct_helper_ext_add(ct, flags);
 		if (help == NULL)
 			return -ENOMEM;
 	} else {
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 40152b9ad772..f981bfa8db72 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -1947,7 +1947,7 @@ ctnetlink_create_conntrack(struct net *net,
 		} else {
 			struct nf_conn_help *help;
 
-			help = nf_ct_helper_ext_add(ct, helper, GFP_ATOMIC);
+			help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 			if (help == NULL) {
 				err = -ENOMEM;
 				goto err2;
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 1435ffc5f57e..3bc82ee5464d 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -870,7 +870,7 @@ static void nft_ct_helper_obj_eval(struct nft_object *obj,
 	if (test_bit(IPS_HELPER_BIT, &ct->status))
 		return;
 
-	help = nf_ct_helper_ext_add(ct, to_assign, GFP_ATOMIC);
+	help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 	if (help) {
 		rcu_assign_pointer(help->helper, to_assign);
 		set_bit(IPS_HELPER_BIT, &ct->status);
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 03b9a50ec93b..7ba454e9e3fa 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -93,7 +93,7 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name,
 		return -ENOENT;
 	}
 
-	help = nf_ct_helper_ext_add(ct, helper, GFP_KERNEL);
+	help = nf_ct_helper_ext_add(ct, GFP_KERNEL);
 	if (help == NULL) {
 		nf_conntrack_helper_put(helper);
 		return -ENOMEM;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index e05bd3e53f0f..3e33c382367f 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1303,7 +1303,7 @@ static int ovs_ct_add_helper(struct ovs_conntrack_info *info, const char *name,
 		return -EINVAL;
 	}
 
-	help = nf_ct_helper_ext_add(info->ct, helper, GFP_KERNEL);
+	help = nf_ct_helper_ext_add(info->ct, GFP_KERNEL);
 	if (!help) {
 		nf_conntrack_helper_put(helper);
 		return -ENOMEM;
-- 
cgit v1.2.3


From 452238e8d5ffd8b77f92387519513839d4ca7379 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 11 Jul 2018 13:45:10 +0200
Subject: netfilter: nf_tables: add and use helper for module autoload

module autoload is problematic, it requires dropping the mutex that
protects the transaction.  Once the mutex has been dropped, another
client can start a new transaction before we had a chance to abort
current transaction log.

This helper makes sure we first zap the transaction log, then
drop mutex for module autoload.

In case autload is successful, the caller has to reply entire
message anyway.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 81 +++++++++++++++++++++++++++----------------
 1 file changed, 52 insertions(+), 29 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3f211e1025c1..5e95e92e547b 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -455,8 +455,40 @@ __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family)
 	return NULL;
 }
 
+/*
+ * Loading a module requires dropping mutex that guards the
+ * transaction.
+ * We first need to abort any pending transactions as once
+ * mutex is unlocked a different client could start a new
+ * transaction.  It must not see any 'future generation'
+ * changes * as these changes will never happen.
+ */
+#ifdef CONFIG_MODULES
+static int __nf_tables_abort(struct net *net);
+
+static void nft_request_module(struct net *net, const char *fmt, ...)
+{
+	char module_name[MODULE_NAME_LEN];
+	va_list args;
+	int ret;
+
+	__nf_tables_abort(net);
+
+	va_start(args, fmt);
+	ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args);
+	va_end(args);
+	if (WARN(ret >= MODULE_NAME_LEN, "truncated: '%s' (len %d)", module_name, ret))
+		return;
+
+	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	request_module("%s", module_name);
+	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+}
+#endif
+
 static const struct nft_chain_type *
-nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family, bool autoload)
+nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
+			    u8 family, bool autoload)
 {
 	const struct nft_chain_type *type;
 
@@ -465,10 +497,8 @@ nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family, bool autoload)
 		return type;
 #ifdef CONFIG_MODULES
 	if (autoload) {
-		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nft-chain-%u-%.*s", family,
-			       nla_len(nla), (const char *)nla_data(nla));
-		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		nft_request_module(net, "nft-chain-%u-%.*s", family,
+				   nla_len(nla), (const char *)nla_data(nla));
 		type = __nf_tables_chain_type_lookup(nla, family);
 		if (type != NULL)
 			return ERR_PTR(-EAGAIN);
@@ -1412,7 +1442,7 @@ static int nft_chain_parse_hook(struct net *net,
 
 	type = chain_type[family][NFT_CHAIN_T_DEFAULT];
 	if (nla[NFTA_CHAIN_TYPE]) {
-		type = nf_tables_chain_type_lookup(nla[NFTA_CHAIN_TYPE],
+		type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE],
 						   family, create);
 		if (IS_ERR(type))
 			return PTR_ERR(type);
@@ -1875,7 +1905,8 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family,
 	return NULL;
 }
 
-static const struct nft_expr_type *nft_expr_type_get(u8 family,
+static const struct nft_expr_type *nft_expr_type_get(struct net *net,
+						     u8 family,
 						     struct nlattr *nla)
 {
 	const struct nft_expr_type *type;
@@ -1889,17 +1920,13 @@ static const struct nft_expr_type *nft_expr_type_get(u8 family,
 
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nft-expr-%u-%.*s", family,
-			       nla_len(nla), (char *)nla_data(nla));
-		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		nft_request_module(net, "nft-expr-%u-%.*s", family,
+				   nla_len(nla), (char *)nla_data(nla));
 		if (__nft_expr_type_get(family, nla))
 			return ERR_PTR(-EAGAIN);
 
-		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nft-expr-%.*s",
-			       nla_len(nla), (char *)nla_data(nla));
-		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		nft_request_module(net, "nft-expr-%.*s",
+				   nla_len(nla), (char *)nla_data(nla));
 		if (__nft_expr_type_get(family, nla))
 			return ERR_PTR(-EAGAIN);
 	}
@@ -1968,7 +1995,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 	if (err < 0)
 		return err;
 
-	type = nft_expr_type_get(ctx->family, tb[NFTA_EXPR_NAME]);
+	type = nft_expr_type_get(ctx->net, ctx->family, tb[NFTA_EXPR_NAME]);
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
@@ -2744,9 +2771,7 @@ nft_select_set_ops(const struct nft_ctx *ctx,
 
 #ifdef CONFIG_MODULES
 	if (list_empty(&nf_tables_set_types)) {
-		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nft-set");
-		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		nft_request_module(ctx->net, "nft-set");
 		if (!list_empty(&nf_tables_set_types))
 			return ERR_PTR(-EAGAIN);
 	}
@@ -4779,7 +4804,8 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
 	return NULL;
 }
 
-static const struct nft_object_type *nft_obj_type_get(u32 objtype)
+static const struct nft_object_type *
+nft_obj_type_get(struct net *net, u32 objtype)
 {
 	const struct nft_object_type *type;
 
@@ -4789,9 +4815,7 @@ static const struct nft_object_type *nft_obj_type_get(u32 objtype)
 
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nft-obj-%u", objtype);
-		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		nft_request_module(net, "nft-obj-%u", objtype);
 		if (__nft_obj_type_get(objtype))
 			return ERR_PTR(-EAGAIN);
 	}
@@ -4843,7 +4867,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk,
 
 	nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla);
 
-	type = nft_obj_type_get(objtype);
+	type = nft_obj_type_get(net, objtype);
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
@@ -5339,7 +5363,8 @@ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family)
 	return NULL;
 }
 
-static const struct nf_flowtable_type *nft_flowtable_type_get(u8 family)
+static const struct nf_flowtable_type *
+nft_flowtable_type_get(struct net *net, u8 family)
 {
 	const struct nf_flowtable_type *type;
 
@@ -5349,9 +5374,7 @@ static const struct nf_flowtable_type *nft_flowtable_type_get(u8 family)
 
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
-		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
-		request_module("nf-flowtable-%u", family);
-		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		nft_request_module(net, "nf-flowtable-%u", family);
 		if (__nft_flowtable_type_get(family))
 			return ERR_PTR(-EAGAIN);
 	}
@@ -5431,7 +5454,7 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk,
 		goto err1;
 	}
 
-	type = nft_flowtable_type_get(family);
+	type = nft_flowtable_type_get(net, family);
 	if (IS_ERR(type)) {
 		err = PTR_ERR(type);
 		goto err2;
-- 
cgit v1.2.3


From ca2f18be792fddd0db2bbf6cbe1ec12d1bb32dd7 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 11 Jul 2018 13:45:11 +0200
Subject: netfilter: nf_tables: make valid_genid callback mandatory

always call this function, followup patch can use this to
aquire a per-netns transaction log to guard the entire batch
instead of using the nfnl susbsys mutex (which is shared among all
namespaces).

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 2 +-
 net/netfilter/nfnetlink.c     | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5e95e92e547b..594b395442d6 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6591,7 +6591,7 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb)
 
 static bool nf_tables_valid_genid(struct net *net, u32 genid)
 {
-	return net->nft.base_seq == genid;
+	return genid == 0 || net->nft.base_seq == genid;
 }
 
 static const struct nfnetlink_subsystem nf_tables_subsys = {
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index e1b6be29848d..94f9bcaa0799 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -331,13 +331,13 @@ replay:
 		}
 	}
 
-	if (!ss->commit || !ss->abort) {
+	if (!ss->valid_genid || !ss->commit || !ss->abort) {
 		nfnl_unlock(subsys_id);
 		netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL);
 		return kfree_skb(skb);
 	}
 
-	if (genid && ss->valid_genid && !ss->valid_genid(net, genid)) {
+	if (!ss->valid_genid(net, genid)) {
 		nfnl_unlock(subsys_id);
 		netlink_ack(oskb, nlh, -ERESTART, NULL);
 		return kfree_skb(skb);
-- 
cgit v1.2.3


From be2ab5b4d5c0bf041a34ec2e1397d50afbfb095e Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 11 Jul 2018 13:45:12 +0200
Subject: netfilter: nf_tables: take module reference when starting a batch

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nfnetlink.h | 1 +
 net/netfilter/nf_tables_api.c       | 1 +
 net/netfilter/nfnetlink.c           | 9 +++++++++
 3 files changed, 11 insertions(+)

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 3ecc3050be0e..4a520d3304a2 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -29,6 +29,7 @@ struct nfnetlink_subsystem {
 	__u8 subsys_id;			/* nfnetlink subsystem ID */
 	__u8 cb_count;			/* number of callbacks */
 	const struct nfnl_callback *cb;	/* callback for individual types */
+	struct module *owner;
 	int (*commit)(struct net *net, struct sk_buff *skb);
 	int (*abort)(struct net *net, struct sk_buff *skb);
 	void (*cleanup)(struct net *net);
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 594b395442d6..c16c481fc52a 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -6603,6 +6603,7 @@ static const struct nfnetlink_subsystem nf_tables_subsys = {
 	.abort		= nf_tables_abort,
 	.cleanup	= nf_tables_cleanup,
 	.valid_genid	= nf_tables_valid_genid,
+	.owner		= THIS_MODULE,
 };
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index 94f9bcaa0799..dd1d7bc23b03 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -337,7 +337,14 @@ replay:
 		return kfree_skb(skb);
 	}
 
+	if (!try_module_get(ss->owner)) {
+		nfnl_unlock(subsys_id);
+		netlink_ack(oskb, nlh, -EOPNOTSUPP, NULL);
+		return kfree_skb(skb);
+	}
+
 	if (!ss->valid_genid(net, genid)) {
+		module_put(ss->owner);
 		nfnl_unlock(subsys_id);
 		netlink_ack(oskb, nlh, -ERESTART, NULL);
 		return kfree_skb(skb);
@@ -472,6 +479,7 @@ done:
 		nfnl_err_reset(&err_list);
 		nfnl_unlock(subsys_id);
 		kfree_skb(skb);
+		module_put(ss->owner);
 		goto replay;
 	} else if (status == NFNL_BATCH_DONE) {
 		err = ss->commit(net, oskb);
@@ -491,6 +499,7 @@ done:
 	nfnl_err_deliver(&err_list, oskb);
 	nfnl_unlock(subsys_id);
 	kfree_skb(skb);
+	module_put(ss->owner);
 }
 
 static const struct nla_policy nfnl_batch_policy[NFNL_BATCH_MAX + 1] = {
-- 
cgit v1.2.3


From 2a43ecf96ba6a6eed70dbcd99d0888fc0ad3b82b Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 11 Jul 2018 13:45:13 +0200
Subject: netfilter: nf_tables: avoid global info storage

This works because all accesses are currently serialized by nfnl
nf_tables subsys mutex.

If we want to have per-netns locking, we need to make this scratch
area pernetns or allocate it on demand.

This does the latter, its ~28kbyte but we can fallback to vmalloc
so it should be fine.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 28 ++++++++++++----------------
 1 file changed, 12 insertions(+), 16 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index c16c481fc52a..68436edd9cdf 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -2454,8 +2454,6 @@ static int nft_table_validate(struct net *net, const struct nft_table *table)
 
 #define NFT_RULE_MAXEXPRS	128
 
-static struct nft_expr_info *info;
-
 static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 			     struct sk_buff *skb, const struct nlmsghdr *nlh,
 			     const struct nlattr * const nla[],
@@ -2463,6 +2461,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 {
 	const struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u8 genmask = nft_genmask_next(net);
+	struct nft_expr_info *info = NULL;
 	int family = nfmsg->nfgen_family;
 	struct nft_table *table;
 	struct nft_chain *chain;
@@ -2533,6 +2532,12 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	n = 0;
 	size = 0;
 	if (nla[NFTA_RULE_EXPRESSIONS]) {
+		info = kvmalloc_array(NFT_RULE_MAXEXPRS,
+				      sizeof(struct nft_expr_info),
+				      GFP_KERNEL);
+		if (!info)
+			return -ENOMEM;
+
 		nla_for_each_nested(tmp, nla[NFTA_RULE_EXPRESSIONS], rem) {
 			err = -EINVAL;
 			if (nla_type(tmp) != NFTA_LIST_ELEM)
@@ -2625,6 +2630,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 				list_add_rcu(&rule->list, &chain->rules);
 		}
 	}
+	kvfree(info);
 	chain->use++;
 
 	if (net->nft.validate_state == NFT_VALIDATE_DO)
@@ -2638,6 +2644,7 @@ err1:
 		if (info[i].ops != NULL)
 			module_put(info[i].ops->type->owner);
 	}
+	kvfree(info);
 	return err;
 }
 
@@ -7203,29 +7210,19 @@ static int __init nf_tables_module_init(void)
 
 	nft_chain_filter_init();
 
-	info = kmalloc_array(NFT_RULE_MAXEXPRS, sizeof(struct nft_expr_info),
-			     GFP_KERNEL);
-	if (info == NULL) {
-		err = -ENOMEM;
-		goto err1;
-	}
-
 	err = nf_tables_core_module_init();
 	if (err < 0)
-		goto err2;
+		return err;
 
 	err = nfnetlink_subsys_register(&nf_tables_subsys);
 	if (err < 0)
-		goto err3;
+		goto err;
 
 	register_netdevice_notifier(&nf_tables_flowtable_notifier);
 
 	return register_pernet_subsys(&nf_tables_net_ops);
-err3:
+err:
 	nf_tables_core_module_exit();
-err2:
-	kfree(info);
-err1:
 	return err;
 }
 
@@ -7237,7 +7234,6 @@ static void __exit nf_tables_module_exit(void)
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	rcu_barrier();
 	nf_tables_core_module_exit();
-	kfree(info);
 }
 
 module_init(nf_tables_module_init);
-- 
cgit v1.2.3


From f102d66b335a417d4848da9441f585695a838934 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 11 Jul 2018 13:45:14 +0200
Subject: netfilter: nf_tables: use dedicated mutex to guard transactions

Continue to use nftnl subsys mutex to protect (un)registration of hook types,
expressions and so on, but force batch operations to do their own
locking.

This allows distinct net namespaces to perform transactions in parallel.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netns/nftables.h     |  1 +
 net/netfilter/nf_tables_api.c    | 88 +++++++++++++++++++++++++++++++---------
 net/netfilter/nfnetlink.c        | 10 ++---
 net/netfilter/nft_chain_filter.c |  4 +-
 net/netfilter/nft_dynset.c       |  2 +
 5 files changed, 77 insertions(+), 28 deletions(-)

diff --git a/include/net/netns/nftables.h b/include/net/netns/nftables.h
index 94767ea3a490..286fd960896f 100644
--- a/include/net/netns/nftables.h
+++ b/include/net/netns/nftables.h
@@ -7,6 +7,7 @@
 struct netns_nftables {
 	struct list_head	tables;
 	struct list_head	commit_list;
+	struct mutex		commit_mutex;
 	unsigned int		base_seq;
 	u8			gencursor;
 	u8			validate_state;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 68436edd9cdf..c0fb2bcd30fe 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -480,12 +480,19 @@ static void nft_request_module(struct net *net, const char *fmt, ...)
 	if (WARN(ret >= MODULE_NAME_LEN, "truncated: '%s' (len %d)", module_name, ret))
 		return;
 
-	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	mutex_unlock(&net->nft.commit_mutex);
 	request_module("%s", module_name);
-	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	mutex_lock(&net->nft.commit_mutex);
 }
 #endif
 
+static void lockdep_nfnl_nft_mutex_not_held(void)
+{
+#ifdef CONFIG_PROVE_LOCKING
+	WARN_ON_ONCE(lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
+#endif
+}
+
 static const struct nft_chain_type *
 nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
 			    u8 family, bool autoload)
@@ -495,6 +502,8 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla,
 	type = __nf_tables_chain_type_lookup(nla, family);
 	if (type != NULL)
 		return type;
+
+	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (autoload) {
 		nft_request_module(net, "nft-chain-%u-%.*s", family,
@@ -802,6 +811,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk,
 	struct nft_ctx ctx;
 	int err;
 
+	lockdep_assert_held(&net->nft.commit_mutex);
 	attr = nla[NFTA_TABLE_NAME];
 	table = nft_table_lookup(net, attr, family, genmask);
 	if (IS_ERR(table)) {
@@ -1042,7 +1052,17 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask)
 	return ERR_PTR(-ENOENT);
 }
 
-static struct nft_chain *nft_chain_lookup(struct nft_table *table,
+static bool lockdep_commit_lock_is_held(struct net *net)
+{
+#ifdef CONFIG_PROVE_LOCKING
+	return lockdep_is_held(&net->nft.commit_mutex);
+#else
+	return true;
+#endif
+}
+
+static struct nft_chain *nft_chain_lookup(struct net *net,
+					  struct nft_table *table,
 					  const struct nlattr *nla, u8 genmask)
 {
 	char search[NFT_CHAIN_MAXNAMELEN + 1];
@@ -1055,7 +1075,7 @@ static struct nft_chain *nft_chain_lookup(struct nft_table *table,
 	nla_strlcpy(search, nla, sizeof(search));
 
 	WARN_ON(!rcu_read_lock_held() &&
-		!lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
+		!lockdep_commit_lock_is_held(net));
 
 	chain = ERR_PTR(-ENOENT);
 	rcu_read_lock();
@@ -1295,7 +1315,7 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk,
 		return PTR_ERR(table);
 	}
 
-	chain = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
+	chain = nft_chain_lookup(net, table, nla[NFTA_CHAIN_NAME], genmask);
 	if (IS_ERR(chain)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]);
 		return PTR_ERR(chain);
@@ -1428,6 +1448,9 @@ static int nft_chain_parse_hook(struct net *net,
 	struct net_device *dev;
 	int err;
 
+	lockdep_assert_held(&net->nft.commit_mutex);
+	lockdep_nfnl_nft_mutex_not_held();
+
 	err = nla_parse_nested(ha, NFTA_HOOK_MAX, nla[NFTA_CHAIN_HOOK],
 			       nft_hook_policy, NULL);
 	if (err < 0)
@@ -1662,7 +1685,8 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 	    nla[NFTA_CHAIN_NAME]) {
 		struct nft_chain *chain2;
 
-		chain2 = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask);
+		chain2 = nft_chain_lookup(ctx->net, table,
+					  nla[NFTA_CHAIN_NAME], genmask);
 		if (!IS_ERR(chain2))
 			return -EEXIST;
 	}
@@ -1724,6 +1748,8 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
+	lockdep_assert_held(&net->nft.commit_mutex);
+
 	table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask);
 	if (IS_ERR(table)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]);
@@ -1742,7 +1768,7 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 		}
 		attr = nla[NFTA_CHAIN_HANDLE];
 	} else {
-		chain = nft_chain_lookup(table, attr, genmask);
+		chain = nft_chain_lookup(net, table, attr, genmask);
 		if (IS_ERR(chain)) {
 			if (PTR_ERR(chain) != -ENOENT) {
 				NL_SET_BAD_ATTR(extack, attr);
@@ -1820,7 +1846,7 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk,
 		chain = nft_chain_lookup_byhandle(table, handle, genmask);
 	} else {
 		attr = nla[NFTA_CHAIN_NAME];
-		chain = nft_chain_lookup(table, attr, genmask);
+		chain = nft_chain_lookup(net, table, attr, genmask);
 	}
 	if (IS_ERR(chain)) {
 		NL_SET_BAD_ATTR(extack, attr);
@@ -1918,6 +1944,7 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net,
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
+	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
 		nft_request_module(net, "nft-expr-%u-%.*s", family,
@@ -2352,7 +2379,7 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk,
 		return PTR_ERR(table);
 	}
 
-	chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
+	chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask);
 	if (IS_ERR(chain)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
 		return PTR_ERR(chain);
@@ -2386,6 +2413,7 @@ static void nf_tables_rule_destroy(const struct nft_ctx *ctx,
 {
 	struct nft_expr *expr;
 
+	lockdep_assert_held(&ctx->net->nft.commit_mutex);
 	/*
 	 * Careful: some expressions might not be initialized in case this
 	 * is called on error from nf_tables_newrule().
@@ -2476,6 +2504,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	bool create;
 	u64 handle, pos_handle;
 
+	lockdep_assert_held(&net->nft.commit_mutex);
+
 	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
 	table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
@@ -2484,7 +2514,7 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 		return PTR_ERR(table);
 	}
 
-	chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
+	chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN], genmask);
 	if (IS_ERR(chain)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
 		return PTR_ERR(chain);
@@ -2684,7 +2714,8 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk,
 	}
 
 	if (nla[NFTA_RULE_CHAIN]) {
-		chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask);
+		chain = nft_chain_lookup(net, table, nla[NFTA_RULE_CHAIN],
+					 genmask);
 		if (IS_ERR(chain)) {
 			NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]);
 			return PTR_ERR(chain);
@@ -2776,6 +2807,8 @@ nft_select_set_ops(const struct nft_ctx *ctx,
 	const struct nft_set_type *type;
 	u32 flags = 0;
 
+	lockdep_assert_held(&ctx->net->nft.commit_mutex);
+	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (list_empty(&nf_tables_set_types)) {
 		nft_request_module(ctx->net, "nft-set");
@@ -4820,6 +4853,7 @@ nft_obj_type_get(struct net *net, u32 objtype)
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
+	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
 		nft_request_module(net, "nft-obj-%u", objtype);
@@ -5379,6 +5413,7 @@ nft_flowtable_type_get(struct net *net, u8 family)
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
+	lockdep_nfnl_nft_mutex_not_held();
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
 		nft_request_module(net, "nf-flowtable-%u", family);
@@ -6232,9 +6267,9 @@ static void nf_tables_commit_chain_active(struct net *net, struct nft_chain *cha
 	next_genbit = nft_gencursor_next(net);
 
 	g0 = rcu_dereference_protected(chain->rules_gen_0,
-				       lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
+				       lockdep_commit_lock_is_held(net));
 	g1 = rcu_dereference_protected(chain->rules_gen_1,
-				       lockdep_nfnl_is_held(NFNL_SUBSYS_NFTABLES));
+				       lockdep_commit_lock_is_held(net));
 
 	/* No changes to this chain? */
 	if (chain->rules_next == NULL) {
@@ -6442,6 +6477,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb)
 
 	nf_tables_commit_release(net);
 	nf_tables_gen_notify(net, skb, NFT_MSG_NEWGEN);
+	mutex_unlock(&net->nft.commit_mutex);
 
 	return 0;
 }
@@ -6593,12 +6629,25 @@ static void nf_tables_cleanup(struct net *net)
 
 static int nf_tables_abort(struct net *net, struct sk_buff *skb)
 {
-	return __nf_tables_abort(net);
+	int ret = __nf_tables_abort(net);
+
+	mutex_unlock(&net->nft.commit_mutex);
+
+	return ret;
 }
 
 static bool nf_tables_valid_genid(struct net *net, u32 genid)
 {
-	return genid == 0 || net->nft.base_seq == genid;
+	bool genid_ok;
+
+	mutex_lock(&net->nft.commit_mutex);
+
+	genid_ok = genid == 0 || net->nft.base_seq == genid;
+	if (!genid_ok)
+		mutex_unlock(&net->nft.commit_mutex);
+
+	/* else, commit mutex has to be released by commit or abort function */
+	return genid_ok;
 }
 
 static const struct nfnetlink_subsystem nf_tables_subsys = {
@@ -6937,8 +6986,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data,
 	case NFT_GOTO:
 		if (!tb[NFTA_VERDICT_CHAIN])
 			return -EINVAL;
-		chain = nft_chain_lookup(ctx->table, tb[NFTA_VERDICT_CHAIN],
-					 genmask);
+		chain = nft_chain_lookup(ctx->net, ctx->table,
+					 tb[NFTA_VERDICT_CHAIN], genmask);
 		if (IS_ERR(chain))
 			return PTR_ERR(chain);
 		if (nft_is_base_chain(chain))
@@ -7183,6 +7232,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 {
 	INIT_LIST_HEAD(&net->nft.tables);
 	INIT_LIST_HEAD(&net->nft.commit_list);
+	mutex_init(&net->nft.commit_mutex);
 	net->nft.base_seq = 1;
 	net->nft.validate_state = NFT_VALIDATE_SKIP;
 
@@ -7191,11 +7241,11 @@ static int __net_init nf_tables_init_net(struct net *net)
 
 static void __net_exit nf_tables_exit_net(struct net *net)
 {
-	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	mutex_lock(&net->nft.commit_mutex);
 	if (!list_empty(&net->nft.commit_list))
 		__nf_tables_abort(net);
 	__nft_release_tables(net);
-	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	mutex_unlock(&net->nft.commit_mutex);
 	WARN_ON_ONCE(!list_empty(&net->nft.tables));
 }
 
diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
index dd1d7bc23b03..916913454624 100644
--- a/net/netfilter/nfnetlink.c
+++ b/net/netfilter/nfnetlink.c
@@ -350,6 +350,8 @@ replay:
 		return kfree_skb(skb);
 	}
 
+	nfnl_unlock(subsys_id);
+
 	while (skb->len >= nlmsg_total_size(0)) {
 		int msglen, type;
 
@@ -471,13 +473,8 @@ ack:
 	}
 done:
 	if (status & NFNL_BATCH_REPLAY) {
-		const struct nfnetlink_subsystem *ss2;
-
-		ss2 = nfnl_dereference_protected(subsys_id);
-		if (ss2 == ss)
-			ss->abort(net, oskb);
+		ss->abort(net, oskb);
 		nfnl_err_reset(&err_list);
-		nfnl_unlock(subsys_id);
 		kfree_skb(skb);
 		module_put(ss->owner);
 		goto replay;
@@ -497,7 +494,6 @@ done:
 		ss->cleanup(net);
 
 	nfnl_err_deliver(&err_list, oskb);
-	nfnl_unlock(subsys_id);
 	kfree_skb(skb);
 	module_put(ss->owner);
 }
diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c
index d21834bed805..ea5b7c4944f6 100644
--- a/net/netfilter/nft_chain_filter.c
+++ b/net/netfilter/nft_chain_filter.c
@@ -322,7 +322,7 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 	if (!ctx.net)
 		return NOTIFY_DONE;
 
-	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	mutex_lock(&ctx.net->nft.commit_mutex);
 	list_for_each_entry(table, &ctx.net->nft.tables, list) {
 		if (table->family != NFPROTO_NETDEV)
 			continue;
@@ -337,7 +337,7 @@ static int nf_tables_netdev_event(struct notifier_block *this,
 			nft_netdev_event(event, dev, &ctx);
 		}
 	}
-	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	mutex_unlock(&ctx.net->nft.commit_mutex);
 	put_net(ctx.net);
 
 	return NOTIFY_DONE;
diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
index 27d7e4598ab6..81184c244d1a 100644
--- a/net/netfilter/nft_dynset.c
+++ b/net/netfilter/nft_dynset.c
@@ -118,6 +118,8 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
 	u64 timeout;
 	int err;
 
+	lockdep_assert_held(&ctx->net->nft.commit_mutex);
+
 	if (tb[NFTA_DYNSET_SET_NAME] == NULL ||
 	    tb[NFTA_DYNSET_OP] == NULL ||
 	    tb[NFTA_DYNSET_SREG_KEY] == NULL)
-- 
cgit v1.2.3


From 06ff4aa252303bd2a5d706008210bb49d9889b9d Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 13 Jul 2018 14:54:43 +0200
Subject: netfilter: nf_osf: add nf_osf_match_one()

This new function allows us to check if there is TCP syn packet matching
with a given fingerprint that can be reused from the upcoming new
nf_osf_find() function.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_osf.c | 207 ++++++++++++++++++++++++++-----------------------
 1 file changed, 111 insertions(+), 96 deletions(-)

diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nf_osf.c
index 5ba5c7bef2f9..bd7b34dd7d87 100644
--- a/net/netfilter/nf_osf.c
+++ b/net/netfilter/nf_osf.c
@@ -21,15 +21,14 @@
 #include <linux/netfilter/nf_osf.h>
 
 static inline int nf_osf_ttl(const struct sk_buff *skb,
-			     const struct nf_osf_info *info,
-			     unsigned char f_ttl)
+			     int ttl_check, unsigned char f_ttl)
 {
 	const struct iphdr *ip = ip_hdr(skb);
 
-	if (info->flags & NF_OSF_TTL) {
-		if (info->ttl == NF_OSF_TTL_TRUE)
+	if (ttl_check != -1) {
+		if (ttl_check == NF_OSF_TTL_TRUE)
 			return ip->ttl == f_ttl;
-		if (info->ttl == NF_OSF_TTL_NOCHECK)
+		if (ttl_check == NF_OSF_TTL_NOCHECK)
 			return 1;
 		else if (ip->ttl <= f_ttl)
 			return 1;
@@ -52,6 +51,104 @@ static inline int nf_osf_ttl(const struct sk_buff *skb,
 	return ip->ttl == f_ttl;
 }
 
+static bool nf_osf_match_one(const struct sk_buff *skb,
+			     const struct nf_osf_user_finger *f,
+			     int ttl_check, u16 totlen, u16 window,
+			     const unsigned char *optp,
+			     unsigned int optsize)
+{
+	unsigned int check_WSS = 0;
+	int fmatch = FMATCH_WRONG;
+	int foptsize, optnum;
+	u16 mss = 0;
+
+	if (totlen != f->ss || !nf_osf_ttl(skb, ttl_check, f->ttl))
+		return false;
+
+	/*
+	 * Should not happen if userspace parser was written correctly.
+	 */
+	if (f->wss.wc >= OSF_WSS_MAX)
+		return false;
+
+	/* Check options */
+
+	foptsize = 0;
+	for (optnum = 0; optnum < f->opt_num; ++optnum)
+		foptsize += f->opt[optnum].length;
+
+	if (foptsize > MAX_IPOPTLEN ||
+	    optsize > MAX_IPOPTLEN ||
+	    optsize != foptsize)
+		return false;
+
+	check_WSS = f->wss.wc;
+
+	for (optnum = 0; optnum < f->opt_num; ++optnum) {
+		if (f->opt[optnum].kind == (*optp)) {
+			__u32 len = f->opt[optnum].length;
+			const __u8 *optend = optp + len;
+
+			fmatch = FMATCH_OK;
+
+			switch (*optp) {
+			case OSFOPT_MSS:
+				mss = optp[3];
+				mss <<= 8;
+				mss |= optp[2];
+
+				mss = ntohs((__force __be16)mss);
+				break;
+			case OSFOPT_TS:
+				break;
+			}
+
+			optp = optend;
+		} else
+			fmatch = FMATCH_OPT_WRONG;
+
+		if (fmatch != FMATCH_OK)
+			break;
+	}
+
+	if (fmatch != FMATCH_OPT_WRONG) {
+		fmatch = FMATCH_WRONG;
+
+		switch (check_WSS) {
+		case OSF_WSS_PLAIN:
+			if (f->wss.val == 0 || window == f->wss.val)
+				fmatch = FMATCH_OK;
+			break;
+		case OSF_WSS_MSS:
+			/*
+			 * Some smart modems decrease mangle MSS to
+			 * SMART_MSS_2, so we check standard, decreased
+			 * and the one provided in the fingerprint MSS
+			 * values.
+			 */
+#define SMART_MSS_1	1460
+#define SMART_MSS_2	1448
+			if (window == f->wss.val * mss ||
+			    window == f->wss.val * SMART_MSS_1 ||
+			    window == f->wss.val * SMART_MSS_2)
+				fmatch = FMATCH_OK;
+			break;
+		case OSF_WSS_MTU:
+			if (window == f->wss.val * (mss + 40) ||
+			    window == f->wss.val * (SMART_MSS_1 + 40) ||
+			    window == f->wss.val * (SMART_MSS_2 + 40))
+				fmatch = FMATCH_OK;
+			break;
+		case OSF_WSS_MODULO:
+			if ((window % f->wss.val) == 0)
+				fmatch = FMATCH_OK;
+			break;
+		}
+	}
+
+	return fmatch == FMATCH_OK;
+}
+
 bool
 nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 	     int hooknum, struct net_device *in, struct net_device *out,
@@ -59,15 +156,16 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 	     const struct list_head *nf_osf_fingers)
 {
 	const unsigned char *optp = NULL, *_optp = NULL;
-	unsigned int optsize = 0, check_WSS = 0;
-	int fmatch = FMATCH_WRONG, fcount = 0;
 	const struct iphdr *ip = ip_hdr(skb);
 	const struct nf_osf_user_finger *f;
 	unsigned char opts[MAX_IPOPTLEN];
 	const struct nf_osf_finger *kf;
-	u16 window, totlen, mss = 0;
+	int fcount = 0, ttl_check;
+	int fmatch = FMATCH_WRONG;
+	unsigned int optsize = 0;
 	const struct tcphdr *tcp;
 	struct tcphdr _tcph;
+	u16 window, totlen;
 	bool df;
 
 	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
@@ -88,103 +186,20 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 				sizeof(struct tcphdr), optsize, opts);
 	}
 
+	ttl_check = (info->flags & NF_OSF_TTL) ? info->ttl : -1;
+
 	list_for_each_entry_rcu(kf, &nf_osf_fingers[df], finger_entry) {
-		int foptsize, optnum;
 
 		f = &kf->finger;
 
 		if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre))
 			continue;
 
-		optp = _optp;
-		fmatch = FMATCH_WRONG;
-
-		if (totlen != f->ss || !nf_osf_ttl(skb, info, f->ttl))
-			continue;
-
-		/*
-		 * Should not happen if userspace parser was written correctly.
-		 */
-		if (f->wss.wc >= OSF_WSS_MAX)
+		if (!nf_osf_match_one(skb, f,
+				      ttl_check, totlen, window, optp, optsize))
 			continue;
 
-		/* Check options */
-
-		foptsize = 0;
-		for (optnum = 0; optnum < f->opt_num; ++optnum)
-			foptsize += f->opt[optnum].length;
-
-		if (foptsize > MAX_IPOPTLEN ||
-		    optsize > MAX_IPOPTLEN ||
-		    optsize != foptsize)
-			continue;
-
-		check_WSS = f->wss.wc;
-
-		for (optnum = 0; optnum < f->opt_num; ++optnum) {
-			if (f->opt[optnum].kind == (*optp)) {
-				__u32 len = f->opt[optnum].length;
-				const __u8 *optend = optp + len;
-
-				fmatch = FMATCH_OK;
-
-				switch (*optp) {
-				case OSFOPT_MSS:
-					mss = optp[3];
-					mss <<= 8;
-					mss |= optp[2];
-
-					mss = ntohs((__force __be16)mss);
-					break;
-				case OSFOPT_TS:
-					break;
-				}
-
-				optp = optend;
-			} else
-				fmatch = FMATCH_OPT_WRONG;
-
-			if (fmatch != FMATCH_OK)
-				break;
-		}
-
-		if (fmatch != FMATCH_OPT_WRONG) {
-			fmatch = FMATCH_WRONG;
-
-			switch (check_WSS) {
-			case OSF_WSS_PLAIN:
-				if (f->wss.val == 0 || window == f->wss.val)
-					fmatch = FMATCH_OK;
-				break;
-			case OSF_WSS_MSS:
-				/*
-				 * Some smart modems decrease mangle MSS to
-				 * SMART_MSS_2, so we check standard, decreased
-				 * and the one provided in the fingerprint MSS
-				 * values.
-				 */
-#define SMART_MSS_1	1460
-#define SMART_MSS_2	1448
-				if (window == f->wss.val * mss ||
-				    window == f->wss.val * SMART_MSS_1 ||
-				    window == f->wss.val * SMART_MSS_2)
-					fmatch = FMATCH_OK;
-				break;
-			case OSF_WSS_MTU:
-				if (window == f->wss.val * (mss + 40) ||
-				    window == f->wss.val * (SMART_MSS_1 + 40) ||
-				    window == f->wss.val * (SMART_MSS_2 + 40))
-					fmatch = FMATCH_OK;
-				break;
-			case OSF_WSS_MODULO:
-				if ((window % f->wss.val) == 0)
-					fmatch = FMATCH_OK;
-				break;
-			}
-		}
-
-		if (fmatch != FMATCH_OK)
-			continue;
+		fmatch = FMATCH_OK;
 
 		fcount++;
 
-- 
cgit v1.2.3


From 31a9c29210e2d8129d2e81acb89babb56916c6c9 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 13 Jul 2018 14:54:44 +0200
Subject: netfilter: nf_osf: add struct nf_osf_hdr_ctx

Wrap context that allow us to guess the OS into a structure.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_osf.c | 105 +++++++++++++++++++++++++++++--------------------
 1 file changed, 62 insertions(+), 43 deletions(-)

diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nf_osf.c
index bd7b34dd7d87..b44d62d5d9a9 100644
--- a/net/netfilter/nf_osf.c
+++ b/net/netfilter/nf_osf.c
@@ -51,18 +51,25 @@ static inline int nf_osf_ttl(const struct sk_buff *skb,
 	return ip->ttl == f_ttl;
 }
 
+struct nf_osf_hdr_ctx {
+	bool			df;
+	u16			window;
+	u16			totlen;
+	const unsigned char	*optp;
+	unsigned int		optsize;
+};
+
 static bool nf_osf_match_one(const struct sk_buff *skb,
 			     const struct nf_osf_user_finger *f,
-			     int ttl_check, u16 totlen, u16 window,
-			     const unsigned char *optp,
-			     unsigned int optsize)
+			     int ttl_check,
+			     struct nf_osf_hdr_ctx *ctx)
 {
 	unsigned int check_WSS = 0;
 	int fmatch = FMATCH_WRONG;
 	int foptsize, optnum;
 	u16 mss = 0;
 
-	if (totlen != f->ss || !nf_osf_ttl(skb, ttl_check, f->ttl))
+	if (ctx->totlen != f->ss || !nf_osf_ttl(skb, ttl_check, f->ttl))
 		return false;
 
 	/*
@@ -78,24 +85,24 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 		foptsize += f->opt[optnum].length;
 
 	if (foptsize > MAX_IPOPTLEN ||
-	    optsize > MAX_IPOPTLEN ||
-	    optsize != foptsize)
+	    ctx->optsize > MAX_IPOPTLEN ||
+	    ctx->optsize != foptsize)
 		return false;
 
 	check_WSS = f->wss.wc;
 
 	for (optnum = 0; optnum < f->opt_num; ++optnum) {
-		if (f->opt[optnum].kind == (*optp)) {
+		if (f->opt[optnum].kind == *ctx->optp) {
 			__u32 len = f->opt[optnum].length;
-			const __u8 *optend = optp + len;
+			const __u8 *optend = ctx->optp + len;
 
 			fmatch = FMATCH_OK;
 
-			switch (*optp) {
+			switch (*ctx->optp) {
 			case OSFOPT_MSS:
-				mss = optp[3];
+				mss = ctx->optp[3];
 				mss <<= 8;
-				mss |= optp[2];
+				mss |= ctx->optp[2];
 
 				mss = ntohs((__force __be16)mss);
 				break;
@@ -103,7 +110,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 				break;
 			}
 
-			optp = optend;
+			ctx->optp = optend;
 		} else
 			fmatch = FMATCH_OPT_WRONG;
 
@@ -116,7 +123,7 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 
 		switch (check_WSS) {
 		case OSF_WSS_PLAIN:
-			if (f->wss.val == 0 || window == f->wss.val)
+			if (f->wss.val == 0 || ctx->window == f->wss.val)
 				fmatch = FMATCH_OK;
 			break;
 		case OSF_WSS_MSS:
@@ -128,19 +135,19 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 			 */
 #define SMART_MSS_1	1460
 #define SMART_MSS_2	1448
-			if (window == f->wss.val * mss ||
-			    window == f->wss.val * SMART_MSS_1 ||
-			    window == f->wss.val * SMART_MSS_2)
+			if (ctx->window == f->wss.val * mss ||
+			    ctx->window == f->wss.val * SMART_MSS_1 ||
+			    ctx->window == f->wss.val * SMART_MSS_2)
 				fmatch = FMATCH_OK;
 			break;
 		case OSF_WSS_MTU:
-			if (window == f->wss.val * (mss + 40) ||
-			    window == f->wss.val * (SMART_MSS_1 + 40) ||
-			    window == f->wss.val * (SMART_MSS_2 + 40))
+			if (ctx->window == f->wss.val * (mss + 40) ||
+			    ctx->window == f->wss.val * (SMART_MSS_1 + 40) ||
+			    ctx->window == f->wss.val * (SMART_MSS_2 + 40))
 				fmatch = FMATCH_OK;
 			break;
 		case OSF_WSS_MODULO:
-			if ((window % f->wss.val) == 0)
+			if ((ctx->window % f->wss.val) == 0)
 				fmatch = FMATCH_OK;
 			break;
 		}
@@ -149,54 +156,66 @@ static bool nf_osf_match_one(const struct sk_buff *skb,
 	return fmatch == FMATCH_OK;
 }
 
+static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx,
+						const struct sk_buff *skb,
+						const struct iphdr *ip,
+						unsigned char *opts)
+{
+	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
+
+	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
+	if (!tcp)
+		return NULL;
+
+	if (!tcp->syn)
+		return NULL;
+
+	ctx->totlen = ntohs(ip->tot_len);
+	ctx->df = ntohs(ip->frag_off) & IP_DF;
+	ctx->window = ntohs(tcp->window);
+
+	if (tcp->doff * 4 > sizeof(struct tcphdr)) {
+		ctx->optsize = tcp->doff * 4 - sizeof(struct tcphdr);
+
+		ctx->optp = skb_header_pointer(skb, ip_hdrlen(skb) +
+				sizeof(struct tcphdr), ctx->optsize, opts);
+	}
+
+	return tcp;
+}
+
 bool
 nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 	     int hooknum, struct net_device *in, struct net_device *out,
 	     const struct nf_osf_info *info, struct net *net,
 	     const struct list_head *nf_osf_fingers)
 {
-	const unsigned char *optp = NULL, *_optp = NULL;
 	const struct iphdr *ip = ip_hdr(skb);
 	const struct nf_osf_user_finger *f;
 	unsigned char opts[MAX_IPOPTLEN];
 	const struct nf_osf_finger *kf;
 	int fcount = 0, ttl_check;
 	int fmatch = FMATCH_WRONG;
-	unsigned int optsize = 0;
+	struct nf_osf_hdr_ctx ctx;
 	const struct tcphdr *tcp;
-	struct tcphdr _tcph;
-	u16 window, totlen;
-	bool df;
 
-	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
-	if (!tcp)
-		return false;
+	memset(&ctx, 0, sizeof(ctx));
 
-	if (!tcp->syn)
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	if (!tcp)
 		return false;
 
-	totlen = ntohs(ip->tot_len);
-	df = ntohs(ip->frag_off) & IP_DF;
-	window = ntohs(tcp->window);
-
-	if (tcp->doff * 4 > sizeof(struct tcphdr)) {
-		optsize = tcp->doff * 4 - sizeof(struct tcphdr);
-
-		_optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) +
-				sizeof(struct tcphdr), optsize, opts);
-	}
-
 	ttl_check = (info->flags & NF_OSF_TTL) ? info->ttl : -1;
 
-	list_for_each_entry_rcu(kf, &nf_osf_fingers[df], finger_entry) {
+	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
 
 		f = &kf->finger;
 
 		if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre))
 			continue;
 
-		if (!nf_osf_match_one(skb, f,
-				      ttl_check, totlen, window, optp, optsize))
+		if (!nf_osf_match_one(skb, f, ttl_check, &ctx))
 			continue;
 
 		fmatch = FMATCH_OK;
-- 
cgit v1.2.3


From 365b5a36f352e9884e85c47aa33026fd4df18633 Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Thu, 12 Jul 2018 17:18:46 +0200
Subject: netfilter: nft_socket: Break evaluation if no socket found
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Actual implementation stores 0 in the destination register if no socket
is found by the lookup, but that is not intentional as it is not really
a value of any socket metadata.

This patch fixes this and breaks rule evaluation in this case.

Fixes: 554ced0a6e29 ("netfilter: nf_tables: add support for native socket matching")
Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_socket.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index e43c1939d25f..622ac2012a40 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -43,7 +43,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
 		}
 
 	if (!sk) {
-		nft_reg_store8(dest, 0);
+		regs->verdict.code = NFT_BREAK;
 		return;
 	}
 
-- 
cgit v1.2.3


From 7d25f8851a2c03319bfa8e56bb40bde2c4621392 Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Thu, 12 Jul 2018 17:48:06 +0200
Subject: netfilter: nft_socket: Expose socket mark
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  4 +++-
 net/netfilter/nft_socket.c               | 11 +++++++++++
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 89438e68dc03..f466860bcf75 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -921,10 +921,12 @@ enum nft_socket_attributes {
 /*
  * enum nft_socket_keys - nf_tables socket expression keys
  *
- * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option_
+ * @NFT_SOCKET_TRANSPARENT: Value of the IP(V6)_TRANSPARENT socket option
+ * @NFT_SOCKET_MARK: Value of the socket mark
  */
 enum nft_socket_keys {
 	NFT_SOCKET_TRANSPARENT,
+	NFT_SOCKET_MARK,
 	__NFT_SOCKET_MAX
 };
 #define NFT_SOCKET_MAX	(__NFT_SOCKET_MAX - 1)
diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
index 622ac2012a40..d7f3776dfd71 100644
--- a/net/netfilter/nft_socket.c
+++ b/net/netfilter/nft_socket.c
@@ -54,6 +54,14 @@ static void nft_socket_eval(const struct nft_expr *expr,
 	case NFT_SOCKET_TRANSPARENT:
 		nft_reg_store8(dest, inet_sk_transparent(sk));
 		break;
+	case NFT_SOCKET_MARK:
+		if (sk_fullsock(sk)) {
+			*dest = sk->sk_mark;
+		} else {
+			regs->verdict.code = NFT_BREAK;
+			return;
+		}
+		break;
 	default:
 		WARN_ON(1);
 		regs->verdict.code = NFT_BREAK;
@@ -91,6 +99,9 @@ static int nft_socket_init(const struct nft_ctx *ctx,
 	case NFT_SOCKET_TRANSPARENT:
 		len = sizeof(u8);
 		break;
+	case NFT_SOCKET_MARK:
+		len = sizeof(u32);
+		break;
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 70b095c84326640eeacfd69a411db8fc36e8ab1a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Sat, 14 Jul 2018 01:14:01 +0200
Subject: ipv6: remove dependency of nf_defrag_ipv6 on ipv6 module

IPV6=m
DEFRAG_IPV6=m
CONNTRACK=y yields:

net/netfilter/nf_conntrack_proto.o: In function `nf_ct_netns_do_get':
net/netfilter/nf_conntrack_proto.c:802: undefined reference to `nf_defrag_ipv6_enable'
net/netfilter/nf_conntrack_proto.o:(.rodata+0x640): undefined reference to `nf_conntrack_l4proto_icmpv6'

Setting DEFRAG_IPV6=y causes undefined references to ip6_rhash_params
ip6_frag_init and ip6_expire_frag_queue so it would be needed to force
IPV6=y too.

This patch gets rid of the 'followup linker error' by removing
the dependency of ipv6.ko symbols from netfilter ipv6 defrag.

Shared code is placed into a header, then used from both.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/ipv6.h                        |  28 --------
 include/net/ipv6_frag.h                   | 104 ++++++++++++++++++++++++++++++
 net/ieee802154/6lowpan/reassembly.c       |   2 +-
 net/ipv6/netfilter/nf_conntrack_reasm.c   |  17 +++--
 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c |   3 +-
 net/ipv6/reassembly.c                     |  92 ++------------------------
 net/openvswitch/conntrack.c               |   1 +
 7 files changed, 126 insertions(+), 121 deletions(-)
 create mode 100644 include/net/ipv6_frag.h

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index aa6fd11a887c..3720958cd4e1 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -581,34 +581,6 @@ static inline bool ipv6_prefix_equal(const struct in6_addr *addr1,
 }
 #endif
 
-struct inet_frag_queue;
-
-enum ip6_defrag_users {
-	IP6_DEFRAG_LOCAL_DELIVER,
-	IP6_DEFRAG_CONNTRACK_IN,
-	__IP6_DEFRAG_CONNTRACK_IN	= IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
-	IP6_DEFRAG_CONNTRACK_OUT,
-	__IP6_DEFRAG_CONNTRACK_OUT	= IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
-	IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
-	__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
-};
-
-void ip6_frag_init(struct inet_frag_queue *q, const void *a);
-extern const struct rhashtable_params ip6_rhash_params;
-
-/*
- *	Equivalent of ipv4 struct ip
- */
-struct frag_queue {
-	struct inet_frag_queue	q;
-
-	int			iif;
-	__u16			nhoffset;
-	u8			ecn;
-};
-
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq);
-
 static inline bool ipv6_addr_any(const struct in6_addr *a)
 {
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
new file mode 100644
index 000000000000..6ced1e6899b6
--- /dev/null
+++ b/include/net/ipv6_frag.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _IPV6_FRAG_H
+#define _IPV6_FRAG_H
+#include <linux/kernel.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+enum ip6_defrag_users {
+	IP6_DEFRAG_LOCAL_DELIVER,
+	IP6_DEFRAG_CONNTRACK_IN,
+	__IP6_DEFRAG_CONNTRACK_IN	= IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX,
+	IP6_DEFRAG_CONNTRACK_OUT,
+	__IP6_DEFRAG_CONNTRACK_OUT	= IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX,
+	IP6_DEFRAG_CONNTRACK_BRIDGE_IN,
+	__IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX,
+};
+
+/*
+ *	Equivalent of ipv4 struct ip
+ */
+struct frag_queue {
+	struct inet_frag_queue	q;
+
+	int			iif;
+	__u16			nhoffset;
+	u8			ecn;
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline void ip6frag_init(struct inet_frag_queue *q, const void *a)
+{
+	struct frag_queue *fq = container_of(q, struct frag_queue, q);
+	const struct frag_v6_compare_key *key = a;
+
+	q->key.v6 = *key;
+	fq->ecn = 0;
+}
+
+static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed)
+{
+	return jhash2(data,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed)
+{
+	const struct inet_frag_queue *fq = data;
+
+	return jhash2((const u32 *)&fq->key.v6,
+		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
+}
+
+static inline int
+ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
+{
+	const struct frag_v6_compare_key *key = arg->key;
+	const struct inet_frag_queue *fq = ptr;
+
+	return !!memcmp(&fq->key, key, sizeof(*key));
+}
+
+static inline void
+ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
+{
+	struct net_device *dev = NULL;
+	struct sk_buff *head;
+
+	rcu_read_lock();
+	spin_lock(&fq->q.lock);
+
+	if (fq->q.flags & INET_FRAG_COMPLETE)
+		goto out;
+
+	inet_frag_kill(&fq->q);
+
+	dev = dev_get_by_index_rcu(net, fq->iif);
+	if (!dev)
+		goto out;
+
+	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
+	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
+
+	/* Don't send error if the first segment did not arrive. */
+	head = fq->q.fragments;
+	if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
+		goto out;
+
+	head->dev = dev;
+	skb_get(head);
+	spin_unlock(&fq->q.lock);
+
+	icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
+	kfree_skb(head);
+	goto out_rcu_unlock;
+
+out:
+	spin_unlock(&fq->q.lock);
+out_rcu_unlock:
+	rcu_read_unlock();
+	inet_frag_put(&fq->q);
+}
+#endif
+#endif
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 2cc224106b69..ec7a5da56129 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -25,7 +25,7 @@
 
 #include <net/ieee802154_netdev.h>
 #include <net/6lowpan.h>
-#include <net/ipv6.h>
+#include <net/ipv6_frag.h>
 #include <net/inet_frag.h>
 
 #include "6lowpan_i.h"
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index a452d99c9f52..333ee3256964 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -33,9 +33,8 @@
 
 #include <net/sock.h>
 #include <net/snmp.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
 
-#include <net/ipv6.h>
 #include <net/protocol.h>
 #include <net/transp_v6.h>
 #include <net/rawv6.h>
@@ -151,7 +150,7 @@ static void nf_ct_frag6_expire(struct timer_list *t)
 	fq = container_of(frag, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, nf_frag.frags);
 
-	ip6_expire_frag_queue(net, fq);
+	ip6frag_expire_frag_queue(net, fq);
 }
 
 /* Creation primitives. */
@@ -622,16 +621,24 @@ static struct pernet_operations nf_ct_net_ops = {
 	.exit = nf_ct_net_exit,
 };
 
+static const struct rhashtable_params nfct_rhash_params = {
+	.head_offset		= offsetof(struct inet_frag_queue, node),
+	.hashfn			= ip6frag_key_hashfn,
+	.obj_hashfn		= ip6frag_obj_hashfn,
+	.obj_cmpfn		= ip6frag_obj_cmpfn,
+	.automatic_shrinking	= true,
+};
+
 int nf_ct_frag6_init(void)
 {
 	int ret = 0;
 
-	nf_frags.constructor = ip6_frag_init;
+	nf_frags.constructor = ip6frag_init;
 	nf_frags.destructor = NULL;
 	nf_frags.qsize = sizeof(struct frag_queue);
 	nf_frags.frag_expire = nf_ct_frag6_expire;
 	nf_frags.frags_cache_name = nf_frags_cache_name;
-	nf_frags.rhash_params = ip6_rhash_params;
+	nf_frags.rhash_params = nfct_rhash_params;
 	ret = inet_frags_init(&nf_frags);
 	if (ret)
 		goto out;
diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
index e631be25337e..72dd3e202375 100644
--- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
+++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c
@@ -14,8 +14,7 @@
 #include <linux/skbuff.h>
 #include <linux/icmp.h>
 #include <linux/sysctl.h>
-#include <net/ipv6.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
 
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter_bridge.h>
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index b939b94e7e91..6edd2ac8ae4b 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -57,7 +57,7 @@
 #include <net/rawv6.h>
 #include <net/ndisc.h>
 #include <net/addrconf.h>
-#include <net/inet_frag.h>
+#include <net/ipv6_frag.h>
 #include <net/inet_ecn.h>
 
 static const char ip6_frag_cache_name[] = "ip6-frags";
@@ -72,61 +72,6 @@ static struct inet_frags ip6_frags;
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 			  struct net_device *dev);
 
-void ip6_frag_init(struct inet_frag_queue *q, const void *a)
-{
-	struct frag_queue *fq = container_of(q, struct frag_queue, q);
-	const struct frag_v6_compare_key *key = a;
-
-	q->key.v6 = *key;
-	fq->ecn = 0;
-}
-EXPORT_SYMBOL(ip6_frag_init);
-
-void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq)
-{
-	struct net_device *dev = NULL;
-	struct sk_buff *head;
-
-	rcu_read_lock();
-	spin_lock(&fq->q.lock);
-
-	if (fq->q.flags & INET_FRAG_COMPLETE)
-		goto out;
-
-	inet_frag_kill(&fq->q);
-
-	dev = dev_get_by_index_rcu(net, fq->iif);
-	if (!dev)
-		goto out;
-
-	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
-	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);
-
-	/* Don't send error if the first segment did not arrive. */
-	head = fq->q.fragments;
-	if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head)
-		goto out;
-
-	/* But use as source device on which LAST ARRIVED
-	 * segment was received. And do not use fq->dev
-	 * pointer directly, device might already disappeared.
-	 */
-	head->dev = dev;
-	skb_get(head);
-	spin_unlock(&fq->q.lock);
-
-	icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0);
-	kfree_skb(head);
-	goto out_rcu_unlock;
-
-out:
-	spin_unlock(&fq->q.lock);
-out_rcu_unlock:
-	rcu_read_unlock();
-	inet_frag_put(&fq->q);
-}
-EXPORT_SYMBOL(ip6_expire_frag_queue);
-
 static void ip6_frag_expire(struct timer_list *t)
 {
 	struct inet_frag_queue *frag = from_timer(frag, t, timer);
@@ -136,7 +81,7 @@ static void ip6_frag_expire(struct timer_list *t)
 	fq = container_of(frag, struct frag_queue, q);
 	net = container_of(fq->q.net, struct net, ipv6.frags);
 
-	ip6_expire_frag_queue(net, fq);
+	ip6frag_expire_frag_queue(net, fq);
 }
 
 static struct frag_queue *
@@ -696,42 +641,19 @@ static struct pernet_operations ip6_frags_ops = {
 	.exit = ipv6_frags_exit_net,
 };
 
-static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed)
-{
-	return jhash2(data,
-		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
-}
-
-static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed)
-{
-	const struct inet_frag_queue *fq = data;
-
-	return jhash2((const u32 *)&fq->key.v6,
-		      sizeof(struct frag_v6_compare_key) / sizeof(u32), seed);
-}
-
-static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr)
-{
-	const struct frag_v6_compare_key *key = arg->key;
-	const struct inet_frag_queue *fq = ptr;
-
-	return !!memcmp(&fq->key, key, sizeof(*key));
-}
-
-const struct rhashtable_params ip6_rhash_params = {
+static const struct rhashtable_params ip6_rhash_params = {
 	.head_offset		= offsetof(struct inet_frag_queue, node),
-	.hashfn			= ip6_key_hashfn,
-	.obj_hashfn		= ip6_obj_hashfn,
-	.obj_cmpfn		= ip6_obj_cmpfn,
+	.hashfn			= ip6frag_key_hashfn,
+	.obj_hashfn		= ip6frag_obj_hashfn,
+	.obj_cmpfn		= ip6frag_obj_cmpfn,
 	.automatic_shrinking	= true,
 };
-EXPORT_SYMBOL(ip6_rhash_params);
 
 int __init ipv6_frag_init(void)
 {
 	int ret;
 
-	ip6_frags.constructor = ip6_frag_init;
+	ip6_frags.constructor = ip6frag_init;
 	ip6_frags.destructor = NULL;
 	ip6_frags.qsize = sizeof(struct frag_queue);
 	ip6_frags.frag_expire = ip6_frag_expire;
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 3e33c382367f..86a75105af1a 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -26,6 +26,7 @@
 #include <net/netfilter/nf_conntrack_seqadj.h>
 #include <net/netfilter/nf_conntrack_zones.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/ipv6_frag.h>
 
 #ifdef CONFIG_NF_NAT_NEEDED
 #include <linux/netfilter/nf_nat.h>
-- 
cgit v1.2.3


From 24c458c485c87eef97e91d2e180f222555528b11 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Sat, 14 Jul 2018 16:50:59 +0200
Subject: netfilter: nf_osf: add missing definitions to header file

Add missing definitions from nf_osf.h in order to extract Passive OS
fingerprint infrastructure from xt_osf.

Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_osf.h | 11 +++++++++++
 include/uapi/linux/netfilter/xt_osf.h | 10 ++--------
 2 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h
index 8f2f2f403183..3738116b2bbe 100644
--- a/include/uapi/linux/netfilter/nf_osf.h
+++ b/include/uapi/linux/netfilter/nf_osf.h
@@ -16,9 +16,14 @@
 
 #define NF_OSF_TTL_TRUE			0	/* True ip and fingerprint TTL comparison */
 
+/* Check if ip TTL is less than fingerprint one */
+#define NF_OSF_TTL_LESS			1
+
 /* Do not compare ip and fingerprint TTL at all */
 #define NF_OSF_TTL_NOCHECK		2
 
+#define NF_OSF_FLAGMASK		(NF_OSF_GENRE | NF_OSF_TTL | \
+				 NF_OSF_LOG | NF_OSF_INVERT)
 /* Wildcard MSS (kind of).
  * It is used to implement a state machine for the different wildcard values
  * of the MSS and window sizes.
@@ -83,4 +88,10 @@ enum iana_options {
 	OSFOPT_EMPTY = 255,
 };
 
+enum nf_osf_attr_type {
+	OSF_ATTR_UNSPEC,
+	OSF_ATTR_FINGER,
+	OSF_ATTR_MAX,
+};
+
 #endif /* _NF_OSF_H */
diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h
index 72956eceeb09..b189007f4f28 100644
--- a/include/uapi/linux/netfilter/xt_osf.h
+++ b/include/uapi/linux/netfilter/xt_osf.h
@@ -37,8 +37,7 @@
 
 #define XT_OSF_TTL_TRUE		NF_OSF_TTL_TRUE
 #define XT_OSF_TTL_NOCHECK	NF_OSF_TTL_NOCHECK
-
-#define XT_OSF_TTL_LESS	1	/* Check if ip TTL is less than fingerprint one */
+#define XT_OSF_TTL_LESS		NF_OSF_TTL_LESS
 
 #define xt_osf_wc		nf_osf_wc
 #define xt_osf_opt		nf_osf_opt
@@ -47,6 +46,7 @@
 #define xt_osf_finger		nf_osf_finger
 #define xt_osf_nlmsg		nf_osf_nlmsg
 
+#define xt_osf_attr_type	nf_osf_attr_type
 /*
  * Add/remove fingerprint from the kernel.
  */
@@ -56,10 +56,4 @@ enum xt_osf_msg_types {
 	OSF_MSG_MAX,
 };
 
-enum xt_osf_attr_type {
-	OSF_ATTR_UNSPEC,
-	OSF_ATTR_FINGER,
-	OSF_ATTR_MAX,
-};
-
 #endif				/* _XT_OSF_H */
-- 
cgit v1.2.3


From 8a3bcaf6ecd37fee326cd30732192ef2a09e5b07 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Mon, 4 Jun 2018 16:54:52 -0400
Subject: ima: Call audit_log_string() rather than logging it untrusted

The parameters passed to this logging function are all provided by
a privileged user and therefore we can call audit_log_string()
rather than audit_log_untrustedstring().

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Suggested-by: Steve Grubb <sgrubb@redhat.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima_policy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 1659abb344f9..f45768469003 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -663,7 +663,7 @@ static void ima_log_string_op(struct audit_buffer *ab, char *key, char *value,
 		audit_log_format(ab, "%s<", key);
 	else
 		audit_log_format(ab, "%s=", key);
-	audit_log_untrustedstring(ab, value);
+	audit_log_string(ab, value);
 	audit_log_format(ab, " ");
 }
 static void ima_log_string(struct audit_buffer *ab, char *key, char *value)
-- 
cgit v1.2.3


From 3d2859d5d4c33b12327764b887039bca15a37e57 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Mon, 4 Jun 2018 16:54:53 -0400
Subject: ima: Use audit_log_format() rather than audit_log_string()

Remove the usage of audit_log_string() and replace it with
audit_log_format().

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Suggested-by: Steve Grubb <sgrubb@redhat.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/ima_policy.c  | 3 +--
 security/integrity/integrity_audit.c | 6 +-----
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index f45768469003..50ead724ba23 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -663,8 +663,7 @@ static void ima_log_string_op(struct audit_buffer *ab, char *key, char *value,
 		audit_log_format(ab, "%s<", key);
 	else
 		audit_log_format(ab, "%s=", key);
-	audit_log_string(ab, value);
-	audit_log_format(ab, " ");
+	audit_log_format(ab, "%s ", value);
 }
 static void ima_log_string(struct audit_buffer *ab, char *key, char *value)
 {
diff --git a/security/integrity/integrity_audit.c b/security/integrity/integrity_audit.c
index ab10a25310a1..82c98f7d217e 100644
--- a/security/integrity/integrity_audit.c
+++ b/security/integrity/integrity_audit.c
@@ -45,11 +45,7 @@ void integrity_audit_msg(int audit_msgno, struct inode *inode,
 			 from_kuid(&init_user_ns, audit_get_loginuid(current)),
 			 audit_get_sessionid(current));
 	audit_log_task_context(ab);
-	audit_log_format(ab, " op=");
-	audit_log_string(ab, op);
-	audit_log_format(ab, " cause=");
-	audit_log_string(ab, cause);
-	audit_log_format(ab, " comm=");
+	audit_log_format(ab, " op=%s cause=%s comm=", op, cause);
 	audit_log_untrustedstring(ab, get_task_comm(name, current));
 	if (fname) {
 		audit_log_format(ab, " name=");
-- 
cgit v1.2.3


From 2afd020aaeeefacb7711b47e3afb0cfb50db3f13 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Mon, 4 Jun 2018 16:54:54 -0400
Subject: ima: Do not audit if CONFIG_INTEGRITY_AUDIT is not set

If Integrity is not auditing, IMA shouldn't audit, either.

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/ima/Kconfig      |  1 +
 security/integrity/ima/ima_policy.c |  6 +++++-
 security/integrity/integrity.h      | 15 +++++++++++++++
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/security/integrity/ima/Kconfig b/security/integrity/ima/Kconfig
index 004919d9bf09..13b446328dda 100644
--- a/security/integrity/ima/Kconfig
+++ b/security/integrity/ima/Kconfig
@@ -12,6 +12,7 @@ config IMA
 	select TCG_TIS if TCG_TPM && X86
 	select TCG_CRB if TCG_TPM && ACPI
 	select TCG_IBMVTPM if TCG_TPM && PPC_PSERIES
+	select INTEGRITY_AUDIT if AUDIT
 	help
 	  The Trusted Computing Group(TCG) runtime Integrity
 	  Measurement Architecture(IMA) maintains a list of hash
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 50ead724ba23..0178bdaa40aa 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -657,6 +657,9 @@ static int ima_lsm_rule_init(struct ima_rule_entry *entry,
 static void ima_log_string_op(struct audit_buffer *ab, char *key, char *value,
 			      bool (*rule_operator)(kuid_t, kuid_t))
 {
+	if (!ab)
+		return;
+
 	if (rule_operator == &uid_gt)
 		audit_log_format(ab, "%s>", key);
 	else if (rule_operator == &uid_lt)
@@ -678,7 +681,8 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 	bool uid_token;
 	int result = 0;
 
-	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_INTEGRITY_RULE);
+	ab = integrity_audit_log_start(NULL, GFP_KERNEL,
+				       AUDIT_INTEGRITY_RULE);
 
 	entry->uid = INVALID_UID;
 	entry->fowner = INVALID_UID;
diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
index 0bb372eed62a..e60473b13a8d 100644
--- a/security/integrity/integrity.h
+++ b/security/integrity/integrity.h
@@ -15,6 +15,7 @@
 #include <linux/integrity.h>
 #include <crypto/sha.h>
 #include <linux/key.h>
+#include <linux/audit.h>
 
 /* iint action cache flags */
 #define IMA_MEASURE		0x00000001
@@ -199,6 +200,13 @@ static inline void evm_load_x509(void)
 void integrity_audit_msg(int audit_msgno, struct inode *inode,
 			 const unsigned char *fname, const char *op,
 			 const char *cause, int result, int info);
+
+static inline struct audit_buffer *
+integrity_audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type)
+{
+	return audit_log_start(ctx, gfp_mask, type);
+}
+
 #else
 static inline void integrity_audit_msg(int audit_msgno, struct inode *inode,
 				       const unsigned char *fname,
@@ -206,4 +214,11 @@ static inline void integrity_audit_msg(int audit_msgno, struct inode *inode,
 				       int result, int info)
 {
 }
+
+static inline struct audit_buffer *
+integrity_audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type)
+{
+	return NULL;
+}
+
 #endif
-- 
cgit v1.2.3


From dba31ee759417ef1a952e929524b0cca1751c036 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Mon, 4 Jun 2018 16:54:55 -0400
Subject: ima: Differentiate auditing policy rules from "audit" actions

The AUDIT_INTEGRITY_RULE is used for auditing IMA policy rules and
the IMA "audit" policy action.  This patch defines
AUDIT_INTEGRITY_POLICY_RULE to reflect the IMA policy rules.

Since we defined a new message type we can now also pass the
audit_context and get an associated SYSCALL record. This now produces
the following records when parsing IMA policy's rules:

type=UNKNOWN[1807] msg=audit(1527888965.738:320): action=audit \
  func=MMAP_CHECK mask=MAY_EXEC res=1
type=UNKNOWN[1807] msg=audit(1527888965.738:320): action=audit \
  func=FILE_CHECK mask=MAY_READ res=1
type=SYSCALL msg=audit(1527888965.738:320): arch=c000003e syscall=1 \
  success=yes exit=17 a0=1 a1=55bcfcca9030 a2=11 a3=7fcc1b55fb38 \
  items=0 ppid=1567 pid=1601 auid=0 uid=0 gid=0 euid=0 suid=0 \
  fsuid=0 egid=0 sgid=0 fsgid=0 tty=tty2 ses=2 comm="echo" \
  exe="/usr/bin/echo" \
  subj=unconfined_u:unconfined_r:unconfined_t:s0-s0:c0.c1023 key=(null)

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 include/uapi/linux/audit.h          | 1 +
 security/integrity/ima/ima_policy.c | 4 ++--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/audit.h b/include/uapi/linux/audit.h
index c35aee9ad4a6..cf2bad8d7873 100644
--- a/include/uapi/linux/audit.h
+++ b/include/uapi/linux/audit.h
@@ -148,6 +148,7 @@
 #define AUDIT_INTEGRITY_PCR	    1804 /* PCR invalidation msgs */
 #define AUDIT_INTEGRITY_RULE	    1805 /* policy rule */
 #define AUDIT_INTEGRITY_EVM_XATTR   1806 /* New EVM-covered xattr */
+#define AUDIT_INTEGRITY_POLICY_RULE 1807 /* IMA policy rules */
 
 #define AUDIT_KERNEL		2000	/* Asynchronous audit record. NOT A REQUEST. */
 
diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
index 0178bdaa40aa..8c9499867c91 100644
--- a/security/integrity/ima/ima_policy.c
+++ b/security/integrity/ima/ima_policy.c
@@ -681,8 +681,8 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
 	bool uid_token;
 	int result = 0;
 
-	ab = integrity_audit_log_start(NULL, GFP_KERNEL,
-				       AUDIT_INTEGRITY_RULE);
+	ab = integrity_audit_log_start(audit_context(), GFP_KERNEL,
+				       AUDIT_INTEGRITY_POLICY_RULE);
 
 	entry->uid = INVALID_UID;
 	entry->fowner = INVALID_UID;
-- 
cgit v1.2.3


From ac2409a521f7ec5978fd582567398d19f4a2fdbd Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Tue, 5 Jun 2018 11:25:45 +0100
Subject: integrity: silence warning when CONFIG_SECURITYFS is not enabled

When CONFIG_SECURITYFS is not enabled, securityfs_create_dir returns
-ENODEV which throws the following error:
	"Unable to create integrity sysfs dir: -19"

However, if the feature is disabled, it can't be warning and hence
we need to silence the error. This patch checks for the error -ENODEV
which is returned when CONFIG_SECURITYFS is disabled to stop the error
being thrown.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Acked-by: Matthew Garrett <mjg59@google.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/iint.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/security/integrity/iint.c b/security/integrity/iint.c
index 149faa81f6f0..5a6810041e5c 100644
--- a/security/integrity/iint.c
+++ b/security/integrity/iint.c
@@ -219,10 +219,13 @@ static int __init integrity_fs_init(void)
 {
 	integrity_dir = securityfs_create_dir("integrity", NULL);
 	if (IS_ERR(integrity_dir)) {
-		pr_err("Unable to create integrity sysfs dir: %ld\n",
-		       PTR_ERR(integrity_dir));
+		int ret = PTR_ERR(integrity_dir);
+
+		if (ret != -ENODEV)
+			pr_err("Unable to create integrity sysfs dir: %d\n",
+			       ret);
 		integrity_dir = NULL;
-		return PTR_ERR(integrity_dir);
+		return ret;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From e2861fa71641c6414831d628a1f4f793b6562580 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@google.com>
Date: Fri, 8 Jun 2018 14:57:42 -0700
Subject: evm: Don't deadlock if a crypto algorithm is unavailable

When EVM attempts to appraise a file signed with a crypto algorithm the
kernel doesn't have support for, it will cause the kernel to trigger a
module load. If the EVM policy includes appraisal of kernel modules this
will in turn call back into EVM - since EVM is holding a lock until the
crypto initialisation is complete, this triggers a deadlock. Add a
CRYPTO_NOLOAD flag and skip module loading if it's set, and add that flag
in the EVM case in order to fail gracefully with an error message
instead of deadlocking.

Signed-off-by: Matthew Garrett <mjg59@google.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 crypto/api.c                        | 2 +-
 include/linux/crypto.h              | 5 +++++
 security/integrity/evm/evm_crypto.c | 3 ++-
 3 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/crypto/api.c b/crypto/api.c
index 0ee632bba064..7aca9f86c5f3 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -229,7 +229,7 @@ static struct crypto_alg *crypto_larval_lookup(const char *name, u32 type,
 	mask &= ~(CRYPTO_ALG_LARVAL | CRYPTO_ALG_DEAD);
 
 	alg = crypto_alg_lookup(name, type, mask);
-	if (!alg) {
+	if (!alg && !(mask & CRYPTO_NOLOAD)) {
 		request_module("crypto-%s", name);
 
 		if (!((type ^ CRYPTO_ALG_NEED_FALLBACK) & mask &
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 6eb06101089f..e8839d3a7559 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -112,6 +112,11 @@
  */
 #define CRYPTO_ALG_OPTIONAL_KEY		0x00004000
 
+/*
+ * Don't trigger module loading
+ */
+#define CRYPTO_NOLOAD			0x00008000
+
 /*
  * Transform masks and values (for crt_flags).
  */
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index b60524310855..c20e3142b541 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -97,7 +97,8 @@ static struct shash_desc *init_desc(char type)
 		mutex_lock(&mutex);
 		if (*tfm)
 			goto out;
-		*tfm = crypto_alloc_shash(algo, 0, CRYPTO_ALG_ASYNC);
+		*tfm = crypto_alloc_shash(algo, 0,
+					  CRYPTO_ALG_ASYNC | CRYPTO_NOLOAD);
 		if (IS_ERR(*tfm)) {
 			rc = PTR_ERR(*tfm);
 			pr_err("Can not allocate %s (reason: %ld)\n", algo, rc);
-- 
cgit v1.2.3


From 5feeb61183dde9d4f4026fd0d5801388c21d61a2 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg59@google.com>
Date: Fri, 8 Jun 2018 14:57:43 -0700
Subject: evm: Allow non-SHA1 digital signatures

SHA1 is reasonable in HMAC constructs, but it's desirable to be able to
use stronger hashes in digital signatures. Modify the EVM crypto code so
the hash type is imported from the digital signature and passed down to
the hash calculation code, and return the digest size to higher layers
for validation.

Signed-off-by: Matthew Garrett <mjg59@google.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
---
 security/integrity/evm/Kconfig      |  1 +
 security/integrity/evm/evm.h        | 10 ++++++--
 security/integrity/evm/evm_crypto.c | 47 ++++++++++++++++++++-----------------
 security/integrity/evm/evm_main.c   | 19 +++++++++------
 4 files changed, 46 insertions(+), 31 deletions(-)

diff --git a/security/integrity/evm/Kconfig b/security/integrity/evm/Kconfig
index d593346d0bba..60221852b26a 100644
--- a/security/integrity/evm/Kconfig
+++ b/security/integrity/evm/Kconfig
@@ -4,6 +4,7 @@ config EVM
 	select ENCRYPTED_KEYS
 	select CRYPTO_HMAC
 	select CRYPTO_SHA1
+	select CRYPTO_HASH_INFO
 	default n
 	help
 	  EVM protects a file's security extended attributes against
diff --git a/security/integrity/evm/evm.h b/security/integrity/evm/evm.h
index 1257c3c24723..c3f437f5db10 100644
--- a/security/integrity/evm/evm.h
+++ b/security/integrity/evm/evm.h
@@ -47,6 +47,11 @@ extern struct crypto_shash *hash_tfm;
 /* List of EVM protected security xattrs */
 extern struct list_head evm_config_xattrnames;
 
+struct evm_digest {
+	struct ima_digest_data hdr;
+	char digest[IMA_MAX_DIGEST_SIZE];
+} __packed;
+
 int evm_init_key(void);
 int evm_update_evmxattr(struct dentry *dentry,
 			const char *req_xattr_name,
@@ -54,10 +59,11 @@ int evm_update_evmxattr(struct dentry *dentry,
 			size_t req_xattr_value_len);
 int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name,
 		  const char *req_xattr_value,
-		  size_t req_xattr_value_len, char *digest);
+		  size_t req_xattr_value_len, struct evm_digest *data);
 int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name,
 		  const char *req_xattr_value,
-		  size_t req_xattr_value_len, char type, char *digest);
+		  size_t req_xattr_value_len, char type,
+		  struct evm_digest *data);
 int evm_init_hmac(struct inode *inode, const struct xattr *xattr,
 		  char *hmac_val);
 int evm_init_secfs(void);
diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index c20e3142b541..8a3905bb02c7 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -21,6 +21,7 @@
 #include <linux/evm.h>
 #include <keys/encrypted-type.h>
 #include <crypto/hash.h>
+#include <crypto/hash_info.h>
 #include "evm.h"
 
 #define EVMKEY "evm-key"
@@ -29,7 +30,7 @@ static unsigned char evmkey[MAX_KEY_SIZE];
 static int evmkey_len = MAX_KEY_SIZE;
 
 struct crypto_shash *hmac_tfm;
-struct crypto_shash *hash_tfm;
+static struct crypto_shash *evm_tfm[HASH_ALGO__LAST];
 
 static DEFINE_MUTEX(mutex);
 
@@ -38,7 +39,6 @@ static DEFINE_MUTEX(mutex);
 static unsigned long evm_set_key_flags;
 
 static char * const evm_hmac = "hmac(sha1)";
-static char * const evm_hash = "sha1";
 
 /**
  * evm_set_key() - set EVM HMAC key from the kernel
@@ -74,10 +74,10 @@ busy:
 }
 EXPORT_SYMBOL_GPL(evm_set_key);
 
-static struct shash_desc *init_desc(char type)
+static struct shash_desc *init_desc(char type, uint8_t hash_algo)
 {
 	long rc;
-	char *algo;
+	const char *algo;
 	struct crypto_shash **tfm;
 	struct shash_desc *desc;
 
@@ -89,8 +89,8 @@ static struct shash_desc *init_desc(char type)
 		tfm = &hmac_tfm;
 		algo = evm_hmac;
 	} else {
-		tfm = &hash_tfm;
-		algo = evm_hash;
+		tfm = &evm_tfm[hash_algo];
+		algo = hash_algo_name[hash_algo];
 	}
 
 	if (*tfm == NULL) {
@@ -187,10 +187,10 @@ static void hmac_add_misc(struct shash_desc *desc, struct inode *inode,
  * each xattr, but attempt to re-use the previously allocated memory.
  */
 static int evm_calc_hmac_or_hash(struct dentry *dentry,
-				const char *req_xattr_name,
-				const char *req_xattr_value,
-				size_t req_xattr_value_len,
-				char type, char *digest)
+				 const char *req_xattr_name,
+				 const char *req_xattr_value,
+				 size_t req_xattr_value_len,
+				 uint8_t type, struct evm_digest *data)
 {
 	struct inode *inode = d_backing_inode(dentry);
 	struct xattr_list *xattr;
@@ -205,10 +205,12 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 	    inode->i_sb->s_user_ns != &init_user_ns)
 		return -EOPNOTSUPP;
 
-	desc = init_desc(type);
+	desc = init_desc(type, data->hdr.algo);
 	if (IS_ERR(desc))
 		return PTR_ERR(desc);
 
+	data->hdr.length = crypto_shash_digestsize(desc->tfm);
+
 	error = -ENODATA;
 	list_for_each_entry_rcu(xattr, &evm_config_xattrnames, list) {
 		bool is_ima = false;
@@ -240,7 +242,7 @@ static int evm_calc_hmac_or_hash(struct dentry *dentry,
 		if (is_ima)
 			ima_present = true;
 	}
-	hmac_add_misc(desc, inode, type, digest);
+	hmac_add_misc(desc, inode, type, data->digest);
 
 	/* Portable EVM signatures must include an IMA hash */
 	if (type == EVM_XATTR_PORTABLE_DIGSIG && !ima_present)
@@ -253,18 +255,18 @@ out:
 
 int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name,
 		  const char *req_xattr_value, size_t req_xattr_value_len,
-		  char *digest)
+		  struct evm_digest *data)
 {
 	return evm_calc_hmac_or_hash(dentry, req_xattr_name, req_xattr_value,
-			       req_xattr_value_len, EVM_XATTR_HMAC, digest);
+				    req_xattr_value_len, EVM_XATTR_HMAC, data);
 }
 
 int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name,
 		  const char *req_xattr_value, size_t req_xattr_value_len,
-		  char type, char *digest)
+		  char type, struct evm_digest *data)
 {
 	return evm_calc_hmac_or_hash(dentry, req_xattr_name, req_xattr_value,
-				     req_xattr_value_len, type, digest);
+				     req_xattr_value_len, type, data);
 }
 
 static int evm_is_immutable(struct dentry *dentry, struct inode *inode)
@@ -304,7 +306,7 @@ int evm_update_evmxattr(struct dentry *dentry, const char *xattr_name,
 			const char *xattr_value, size_t xattr_value_len)
 {
 	struct inode *inode = d_backing_inode(dentry);
-	struct evm_ima_xattr_data xattr_data;
+	struct evm_digest data;
 	int rc = 0;
 
 	/*
@@ -317,13 +319,14 @@ int evm_update_evmxattr(struct dentry *dentry, const char *xattr_name,
 	if (rc)
 		return -EPERM;
 
+	data.hdr.algo = HASH_ALGO_SHA1;
 	rc = evm_calc_hmac(dentry, xattr_name, xattr_value,
-			   xattr_value_len, xattr_data.digest);
+			   xattr_value_len, &data);
 	if (rc == 0) {
-		xattr_data.type = EVM_XATTR_HMAC;
+		data.hdr.xattr.sha1.type = EVM_XATTR_HMAC;
 		rc = __vfs_setxattr_noperm(dentry, XATTR_NAME_EVM,
-					   &xattr_data,
-					   sizeof(xattr_data), 0);
+					   &data.hdr.xattr.data[1],
+					   SHA1_DIGEST_SIZE + 1, 0);
 	} else if (rc == -ENODATA && (inode->i_opflags & IOP_XATTR)) {
 		rc = __vfs_removexattr(dentry, XATTR_NAME_EVM);
 	}
@@ -335,7 +338,7 @@ int evm_init_hmac(struct inode *inode, const struct xattr *lsm_xattr,
 {
 	struct shash_desc *desc;
 
-	desc = init_desc(EVM_XATTR_HMAC);
+	desc = init_desc(EVM_XATTR_HMAC, HASH_ALGO_SHA1);
 	if (IS_ERR(desc)) {
 		pr_info("init_desc failed\n");
 		return PTR_ERR(desc);
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index f9eff5041e4c..7f3f54d89a6e 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -25,6 +25,7 @@
 #include <linux/magic.h>
 
 #include <crypto/hash.h>
+#include <crypto/hash_info.h>
 #include <crypto/algapi.h>
 #include "evm.h"
 
@@ -134,8 +135,9 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 					     struct integrity_iint_cache *iint)
 {
 	struct evm_ima_xattr_data *xattr_data = NULL;
-	struct evm_ima_xattr_data calc;
+	struct signature_v2_hdr *hdr;
 	enum integrity_status evm_status = INTEGRITY_PASS;
+	struct evm_digest digest;
 	struct inode *inode;
 	int rc, xattr_len;
 
@@ -171,25 +173,28 @@ static enum integrity_status evm_verify_hmac(struct dentry *dentry,
 			evm_status = INTEGRITY_FAIL;
 			goto out;
 		}
+
+		digest.hdr.algo = HASH_ALGO_SHA1;
 		rc = evm_calc_hmac(dentry, xattr_name, xattr_value,
-				   xattr_value_len, calc.digest);
+				   xattr_value_len, &digest);
 		if (rc)
 			break;
-		rc = crypto_memneq(xattr_data->digest, calc.digest,
-			    sizeof(calc.digest));
+		rc = crypto_memneq(xattr_data->digest, digest.digest,
+				   SHA1_DIGEST_SIZE);
 		if (rc)
 			rc = -EINVAL;
 		break;
 	case EVM_IMA_XATTR_DIGSIG:
 	case EVM_XATTR_PORTABLE_DIGSIG:
+		hdr = (struct signature_v2_hdr *)xattr_data;
+		digest.hdr.algo = hdr->hash_algo;
 		rc = evm_calc_hash(dentry, xattr_name, xattr_value,
-				   xattr_value_len, xattr_data->type,
-				   calc.digest);
+				   xattr_value_len, xattr_data->type, &digest);
 		if (rc)
 			break;
 		rc = integrity_digsig_verify(INTEGRITY_KEYRING_EVM,
 					(const char *)xattr_data, xattr_len,
-					calc.digest, sizeof(calc.digest));
+					digest.digest, digest.hdr.length);
 		if (!rc) {
 			inode = d_backing_inode(dentry);
 
-- 
cgit v1.2.3


From 6eb864c1d9dd1ef32b88e03c3f49d8be0dab7dcf Mon Sep 17 00:00:00 2001
From: Mikhail Kurinnoi <viewizard@viewizard.com>
Date: Wed, 27 Jun 2018 16:33:42 +0300
Subject: integrity: prevent deadlock during digsig verification.

This patch aimed to prevent deadlock during digsig verification.The point
of issue - user space utility modprobe and/or it's dependencies (ld-*.so,
libz.so.*, libc-*.so and /lib/modules/ files) that could be used for
kernel modules load during digsig verification and could be signed by
digsig in the same time.

First at all, look at crypto_alloc_tfm() work algorithm:
crypto_alloc_tfm() will first attempt to locate an already loaded
algorithm. If that fails and the kernel supports dynamically loadable
modules, it will then attempt to load a module of the same name or alias.
If that fails it will send a query to any loaded crypto manager to
construct an algorithm on the fly.

We have situation, when public_key_verify_signature() in case of RSA
algorithm use alg_name to store internal information in order to construct
an algorithm on the fly, but crypto_larval_lookup() will try to use
alg_name in order to load kernel module with same name.

1) we can't do anything with crypto module work, since it designed to work
exactly in this way;
2) we can't globally filter module requests for modprobe, since it
designed to work with any requests.

In this patch, I propose add an exception for "crypto-pkcs1pad(rsa,*)"
module requests only in case of enabled integrity asymmetric keys support.
Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules for
sure, we are safe to fail such module request from crypto_larval_lookup().
In this way we prevent modprobe execution during digsig verification and
avoid possible deadlock if modprobe and/or it's dependencies also signed
with digsig.

Requested "crypto-pkcs1pad(rsa,*)" kernel module name formed by:
1) "pkcs1pad(rsa,%s)" in public_key_verify_signature();
2) "crypto-%s" / "crypto-%s-all" in crypto_larval_lookup().
"crypto-pkcs1pad(rsa," part of request is a constant and unique and could
be used as filter.

Signed-off-by: Mikhail Kurinnoi <viewizard@viewizard.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>

 include/linux/integrity.h              | 13 +++++++++++++
 security/integrity/digsig_asymmetric.c | 23 +++++++++++++++++++++++
 security/security.c                    |  7 ++++++-
 3 files changed, 42 insertions(+), 1 deletion(-)
---
 include/linux/integrity.h              | 13 +++++++++++++
 security/integrity/digsig_asymmetric.c | 23 +++++++++++++++++++++++
 security/security.c                    |  7 ++++++-
 3 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/include/linux/integrity.h b/include/linux/integrity.h
index 858d3f4a2241..54c853ec2fd1 100644
--- a/include/linux/integrity.h
+++ b/include/linux/integrity.h
@@ -44,4 +44,17 @@ static inline void integrity_load_keys(void)
 }
 #endif /* CONFIG_INTEGRITY */
 
+#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
+
+extern int integrity_kernel_module_request(char *kmod_name);
+
+#else
+
+static inline int integrity_kernel_module_request(char *kmod_name)
+{
+	return 0;
+}
+
+#endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */
+
 #endif /* _LINUX_INTEGRITY_H */
diff --git a/security/integrity/digsig_asymmetric.c b/security/integrity/digsig_asymmetric.c
index ab6a029062a1..6dc075144508 100644
--- a/security/integrity/digsig_asymmetric.c
+++ b/security/integrity/digsig_asymmetric.c
@@ -115,3 +115,26 @@ int asymmetric_verify(struct key *keyring, const char *sig,
 	pr_debug("%s() = %d\n", __func__, ret);
 	return ret;
 }
+
+/**
+ * integrity_kernel_module_request - prevent crypto-pkcs1pad(rsa,*) requests
+ * @kmod_name: kernel module name
+ *
+ * We have situation, when public_key_verify_signature() in case of RSA
+ * algorithm use alg_name to store internal information in order to
+ * construct an algorithm on the fly, but crypto_larval_lookup() will try
+ * to use alg_name in order to load kernel module with same name.
+ * Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules,
+ * we are safe to fail such module request from crypto_larval_lookup().
+ *
+ * In this way we prevent modprobe execution during digsig verification
+ * and avoid possible deadlock if modprobe and/or it's dependencies
+ * also signed with digsig.
+ */
+int integrity_kernel_module_request(char *kmod_name)
+{
+	if (strncmp(kmod_name, "crypto-pkcs1pad(rsa,", 20) == 0)
+		return -EINVAL;
+
+	return 0;
+}
diff --git a/security/security.c b/security/security.c
index b49ee810371b..dbca03d3629b 100644
--- a/security/security.c
+++ b/security/security.c
@@ -1032,7 +1032,12 @@ int security_kernel_create_files_as(struct cred *new, struct inode *inode)
 
 int security_kernel_module_request(char *kmod_name)
 {
-	return call_int_hook(kernel_module_request, 0, kmod_name);
+	int ret;
+
+	ret = call_int_hook(kernel_module_request, 0, kmod_name);
+	if (ret)
+		return ret;
+	return integrity_kernel_module_request(kmod_name);
 }
 
 int security_kernel_read_file(struct file *file, enum kernel_read_file_id id)
-- 
cgit v1.2.3


From bb4b894addb09a069c072a0a032f644cc470d17f Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 13 Jul 2018 16:36:28 +0100
Subject: ASoC: core: add support to card re-bind using component framework

This patch aims at achieving dynamic behaviour of audio card when
the dependent components disappear and reappear.

With this patch the card is removed if any of the dependent component
is removed and card is added back if the dependent component comes back.
All this is done using component framework and matching based on
component name.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  7 ++++++
 sound/soc/soc-core.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 69 insertions(+)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index a4915148f739..a23ecdf3eff1 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -17,6 +17,7 @@
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
+#include <linux/component.h>
 #include <linux/regmap.h>
 #include <linux/log2.h>
 #include <sound/core.h>
@@ -1090,6 +1091,12 @@ struct snd_soc_card {
 
 	struct work_struct deferred_resume_work;
 
+	/* component framework related */
+	bool components_added;
+	/* set in machine driver to enable/disable auto re-binding */
+	bool auto_bind;
+	struct component_match *match;
+
 	/* lists of probed devices belonging to this card */
 	struct list_head component_dev_list;
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 3be0310d5c81..08e189485009 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -279,11 +279,28 @@ static inline void snd_soc_debugfs_exit(void)
 
 #endif
 
+static int snd_soc_card_comp_compare(struct device *dev, void *data)
+{
+	struct snd_soc_component *component;
+
+	lockdep_assert_held(&client_mutex);
+	list_for_each_entry(component, &component_list, list) {
+		if (dev == component->dev) {
+			if (!strcmp(component->name, data))
+				return 1;
+			break;
+		}
+	}
+
+	return 0;
+}
+
 static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd,
 			      struct snd_soc_component *component)
 {
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_rtdcom_list *new_rtdcom;
+	char *cname;
 
 	for_each_rtdcom(rtd, rtdcom) {
 		/* already connected */
@@ -300,6 +317,13 @@ static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd,
 
 	list_add_tail(&new_rtdcom->list, &rtd->component_list);
 
+	if (rtd->card->auto_bind && !rtd->card->components_added) {
+		cname = devm_kasprintf(rtd->card->dev, GFP_KERNEL,
+				       "%s", component->name);
+		component_match_add(rtd->card->dev, &rtd->card->match,
+				    snd_soc_card_comp_compare, cname);
+	}
+
 	return 0;
 }
 
@@ -835,6 +859,25 @@ static bool soc_is_dai_link_bound(struct snd_soc_card *card,
 	return false;
 }
 
+static int snd_soc_card_comp_bind(struct device *dev)
+{
+	struct snd_soc_card *card = dev_get_drvdata(dev);
+
+	if (card->instantiated)
+		return 0;
+
+	return snd_soc_register_card(card);
+}
+
+static void snd_soc_card_comp_unbind(struct device *dev)
+{
+}
+
+static const struct component_master_ops snd_soc_card_comp_ops = {
+	.bind = snd_soc_card_comp_bind,
+	.unbind = snd_soc_card_comp_unbind,
+};
+
 static int soc_bind_dai_link(struct snd_soc_card *card,
 	struct snd_soc_dai_link *dai_link)
 {
@@ -2126,6 +2169,12 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 
 	card->instantiated = 1;
 	snd_soc_dapm_sync(&card->dapm);
+	if (card->auto_bind && !card->components_added) {
+		component_master_add_with_match(card->dev,
+						&snd_soc_card_comp_ops,
+						card->match);
+		card->components_added = true;
+	}
 	mutex_unlock(&card->mutex);
 	mutex_unlock(&client_mutex);
 
@@ -2749,6 +2798,9 @@ int snd_soc_unregister_card(struct snd_soc_card *card)
 		dev_dbg(card->dev, "ASoC: Unregistered card '%s'\n", card->name);
 	}
 
+	if (!card->auto_bind && card->components_added)
+		component_master_del(card->dev, &snd_soc_card_comp_ops);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_soc_unregister_card);
@@ -3161,8 +3213,17 @@ int snd_soc_add_component(struct device *dev,
 
 	snd_soc_component_add(component);
 
+	ret = component_add(dev, NULL);
+	if (ret < 0) {
+		dev_err(dev, "ASoC: Failed to add Component: %d\n", ret);
+		goto err_comp;
+	}
+
 	return 0;
 
+err_comp:
+	soc_remove_component(component);
+	snd_soc_unregister_dais(component);
 err_cleanup:
 	snd_soc_component_cleanup(component);
 err_free:
@@ -3210,6 +3271,7 @@ static int __snd_soc_unregister_component(struct device *dev)
 	mutex_unlock(&client_mutex);
 
 	if (found) {
+		component_del(dev, NULL);
 		snd_soc_component_cleanup(component);
 	}
 
-- 
cgit v1.2.3


From 605fcb69918528e1a448cba4d358cbd8ed532146 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 13 Jul 2018 16:36:29 +0100
Subject: ASoC: qdsp6: q6afe-dai: remove component fw related code

Now that the component framework is integrated into the ASoC core,
remove any redundant code in this driver.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe-dai.c | 34 ++++------------------------------
 1 file changed, 4 insertions(+), 30 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index 074582afda85..e988692a3ced 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -4,7 +4,6 @@
 
 #include <linux/err.h>
 #include <linux/init.h>
-#include <linux/component.h>
 #include <linux/module.h>
 #include <linux/device.h>
 #include <linux/platform_device.h>
@@ -1395,11 +1394,12 @@ static void of_q6afe_parse_dai_data(struct device *dev,
 	}
 }
 
-static int q6afe_dai_bind(struct device *dev, struct device *master, void *data)
+static int q6afe_dai_dev_probe(struct platform_device *pdev)
 {
 	struct q6afe_dai_data *dai_data;
+	struct device *dev = &pdev->dev;
 
-	dai_data = kzalloc(sizeof(*dai_data), GFP_KERNEL);
+	dai_data = devm_kzalloc(dev, sizeof(*dai_data), GFP_KERNEL);
 	if (!dai_data)
 		return -ENOMEM;
 
@@ -1407,35 +1407,10 @@ static int q6afe_dai_bind(struct device *dev, struct device *master, void *data)
 
 	of_q6afe_parse_dai_data(dev, dai_data);
 
-	return snd_soc_register_component(dev, &q6afe_dai_component,
+	return devm_snd_soc_register_component(dev, &q6afe_dai_component,
 					  q6afe_dais, ARRAY_SIZE(q6afe_dais));
 }
 
-static void q6afe_dai_unbind(struct device *dev, struct device *master,
-			     void *data)
-{
-	struct q6afe_dai_data *dai_data = dev_get_drvdata(dev);
-
-	snd_soc_unregister_component(dev);
-	kfree(dai_data);
-}
-
-static const struct component_ops q6afe_dai_comp_ops = {
-	.bind   = q6afe_dai_bind,
-	.unbind = q6afe_dai_unbind,
-};
-
-static int q6afe_dai_dev_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &q6afe_dai_comp_ops);
-}
-
-static int q6afe_dai_dev_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &q6afe_dai_comp_ops);
-	return 0;
-}
-
 static const struct of_device_id q6afe_dai_device_id[] = {
 	{ .compatible = "qcom,q6afe-dais" },
 	{},
@@ -1448,7 +1423,6 @@ static struct platform_driver q6afe_dai_platform_driver = {
 		.of_match_table = of_match_ptr(q6afe_dai_device_id),
 	},
 	.probe = q6afe_dai_dev_probe,
-	.remove = q6afe_dai_dev_remove,
 };
 module_platform_driver(q6afe_dai_platform_driver);
 
-- 
cgit v1.2.3


From f924e4fd89659908107a5529f02c21edb4770dba Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 13 Jul 2018 16:36:30 +0100
Subject: ASoC: qdsp6: q6asm-dai: remove component framework related code

Now that the component framework is integrated into the ASoC core,
remove any redundant code in this driver.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6asm-dai.c | 35 ++++-------------------------------
 1 file changed, 4 insertions(+), 31 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6asm-dai.c b/sound/soc/qcom/qdsp6/q6asm-dai.c
index 1196dc7483d2..acf96c6549fc 100644
--- a/sound/soc/qcom/qdsp6/q6asm-dai.c
+++ b/sound/soc/qcom/qdsp6/q6asm-dai.c
@@ -7,7 +7,6 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
-#include <linux/component.h>
 #include <sound/soc.h>
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>
@@ -561,14 +560,15 @@ static struct snd_soc_dai_driver q6asm_fe_dais[] = {
 	Q6ASM_FEDAI_DRIVER(8),
 };
 
-static int q6asm_dai_bind(struct device *dev, struct device *master, void *data)
+static int q6asm_dai_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
 	struct device_node *node = dev->of_node;
 	struct of_phandle_args args;
 	struct q6asm_dai_data *pdata;
 	int rc;
 
-	pdata = kzalloc(sizeof(struct q6asm_dai_data), GFP_KERNEL);
+	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
 	if (!pdata)
 		return -ENOMEM;
 
@@ -580,36 +580,10 @@ static int q6asm_dai_bind(struct device *dev, struct device *master, void *data)
 
 	dev_set_drvdata(dev, pdata);
 
-	return snd_soc_register_component(dev, &q6asm_fe_dai_component,
+	return devm_snd_soc_register_component(dev, &q6asm_fe_dai_component,
 					q6asm_fe_dais,
 					ARRAY_SIZE(q6asm_fe_dais));
 }
-static void q6asm_dai_unbind(struct device *dev, struct device *master,
-			     void *data)
-{
-	struct q6asm_dai_data *pdata = dev_get_drvdata(dev);
-
-	snd_soc_unregister_component(dev);
-
-	kfree(pdata);
-
-}
-
-static const struct component_ops q6asm_dai_comp_ops = {
-	.bind   = q6asm_dai_bind,
-	.unbind = q6asm_dai_unbind,
-};
-
-static int q6asm_dai_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &q6asm_dai_comp_ops);
-}
-
-static int q6asm_dai_dev_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &q6asm_dai_comp_ops);
-	return 0;
-}
 
 static const struct of_device_id q6asm_dai_device_id[] = {
 	{ .compatible = "qcom,q6asm-dais" },
@@ -623,7 +597,6 @@ static struct platform_driver q6asm_dai_platform_driver = {
 		.of_match_table = of_match_ptr(q6asm_dai_device_id),
 	},
 	.probe = q6asm_dai_probe,
-	.remove = q6asm_dai_dev_remove,
 };
 module_platform_driver(q6asm_dai_platform_driver);
 
-- 
cgit v1.2.3


From 791940779d651c2219e97702d2245b5420b0c8ae Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 13 Jul 2018 16:36:31 +0100
Subject: ASoC: qdsp6: q6routing: remove component framework related code

Now that the component framework is integrated into the ASoC core,
remove any redundant code in this driver.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6routing.c | 32 ++++++--------------------------
 1 file changed, 6 insertions(+), 26 deletions(-)

diff --git a/sound/soc/qcom/qdsp6/q6routing.c b/sound/soc/qcom/qdsp6/q6routing.c
index 35269b492761..1d33b00e5b44 100644
--- a/sound/soc/qcom/qdsp6/q6routing.c
+++ b/sound/soc/qcom/qdsp6/q6routing.c
@@ -8,7 +8,6 @@
 #include <linux/platform_device.h>
 #include <linux/of_platform.h>
 #include <linux/bitops.h>
-#include <linux/component.h>
 #include <linux/mutex.h>
 #include <linux/of_device.h>
 #include <linux/slab.h>
@@ -977,9 +976,10 @@ static const struct snd_soc_component_driver msm_soc_routing_component = {
 	.num_dapm_routes = ARRAY_SIZE(intercon),
 };
 
-static int q6routing_dai_bind(struct device *dev, struct device *master,
-			      void *data)
+static int q6pcm_routing_probe(struct platform_device *pdev)
 {
+	struct device *dev = &pdev->dev;
+
 	routing_data = kzalloc(sizeof(*routing_data), GFP_KERNEL);
 	if (!routing_data)
 		return -ENOMEM;
@@ -989,35 +989,15 @@ static int q6routing_dai_bind(struct device *dev, struct device *master,
 	mutex_init(&routing_data->lock);
 	dev_set_drvdata(dev, routing_data);
 
-	return snd_soc_register_component(dev, &msm_soc_routing_component,
+	return devm_snd_soc_register_component(dev, &msm_soc_routing_component,
 					  NULL, 0);
 }
 
-static void q6routing_dai_unbind(struct device *dev, struct device *master,
-				 void *d)
+static int q6pcm_routing_remove(struct platform_device *pdev)
 {
-	struct msm_routing_data *data = dev_get_drvdata(dev);
-
-	snd_soc_unregister_component(dev);
-
-	kfree(data);
-
+	kfree(routing_data);
 	routing_data = NULL;
-}
 
-static const struct component_ops q6routing_dai_comp_ops = {
-	.bind   = q6routing_dai_bind,
-	.unbind = q6routing_dai_unbind,
-};
-
-static int q6pcm_routing_probe(struct platform_device *pdev)
-{
-	return component_add(&pdev->dev, &q6routing_dai_comp_ops);
-}
-
-static int q6pcm_routing_remove(struct platform_device *pdev)
-{
-	component_del(&pdev->dev, &q6routing_dai_comp_ops);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 90ae7105eaf19342bb11e554059d62b84e01da12 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 13 Jul 2018 16:36:32 +0100
Subject: ASoC: qcom: apq8096: remove component framework related code

Now that the component framework is integrated into the ASoC core,
remove any redundant code in this driver.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/apq8096.c | 75 ++++--------------------------------------------
 1 file changed, 6 insertions(+), 69 deletions(-)

diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index cab8c4ff7c00..a56156281c8d 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -129,17 +129,18 @@ err:
 	return ret;
 }
 
-static int apq8096_bind(struct device *dev)
+static int apq8096_platform_probe(struct platform_device *pdev)
 {
 	struct snd_soc_card *card;
+	struct device *dev = &pdev->dev;
 	int ret;
 
 	card = kzalloc(sizeof(*card), GFP_KERNEL);
 	if (!card)
 		return -ENOMEM;
 
-	component_bind_all(dev, card);
 	card->dev = dev;
+	card->auto_bind = true;
 	dev_set_drvdata(dev, card);
 	ret = apq8096_sbc_parse_of(card);
 	if (ret) {
@@ -154,82 +155,18 @@ static int apq8096_bind(struct device *dev)
 	return 0;
 
 err:
-	component_unbind_all(dev, card);
 	kfree(card);
 	return ret;
 }
 
-static void apq8096_unbind(struct device *dev)
+static int apq8096_platform_remove(struct platform_device *pdev)
 {
-	struct snd_soc_card *card = dev_get_drvdata(dev);
+	struct snd_soc_card *card = dev_get_drvdata(&pdev->dev);
 
+	card->auto_bind = false;
 	snd_soc_unregister_card(card);
-	component_unbind_all(dev, card);
 	kfree(card->dai_link);
 	kfree(card);
-}
-
-static const struct component_master_ops apq8096_ops = {
-	.bind = apq8096_bind,
-	.unbind = apq8096_unbind,
-};
-
-static int apq8016_compare_of(struct device *dev, void *data)
-{
-	return dev->of_node == data;
-}
-
-static void apq8016_release_of(struct device *dev, void *data)
-{
-	of_node_put(data);
-}
-
-static int add_audio_components(struct device *dev,
-				struct component_match **matchptr)
-{
-	struct device_node *np, *platform, *cpu, *node, *dai_node;
-
-	node = dev->of_node;
-
-	for_each_child_of_node(node, np) {
-		cpu = of_get_child_by_name(np, "cpu");
-		if (cpu) {
-			dai_node = of_parse_phandle(cpu, "sound-dai", 0);
-			of_node_get(dai_node);
-			component_match_add_release(dev, matchptr,
-						    apq8016_release_of,
-						    apq8016_compare_of,
-						    dai_node);
-		}
-
-		platform = of_get_child_by_name(np, "platform");
-		if (platform) {
-			dai_node = of_parse_phandle(platform, "sound-dai", 0);
-			component_match_add_release(dev, matchptr,
-						    apq8016_release_of,
-						    apq8016_compare_of,
-						    dai_node);
-		}
-	}
-
-	return 0;
-}
-
-static int apq8096_platform_probe(struct platform_device *pdev)
-{
-	struct component_match *match = NULL;
-	int ret;
-
-	ret = add_audio_components(&pdev->dev, &match);
-	if (ret)
-		return ret;
-
-	return component_master_add_with_match(&pdev->dev, &apq8096_ops, match);
-}
-
-static int apq8096_platform_remove(struct platform_device *pdev)
-{
-	component_master_del(&pdev->dev, &apq8096_ops);
 
 	return 0;
 }
-- 
cgit v1.2.3


From bf270262b7b8bb7b48a846c613f74e800abba392 Mon Sep 17 00:00:00 2001
From: Sriram Periyasamy <sriramx.periyasamy@intel.com>
Date: Mon, 16 Jul 2018 15:32:34 +0530
Subject: ASoC: hdac_hdmi: Add documentation for power management

Add documentation for power management of HDAC HDMI codec device for
various scenarios such as S0/S3, probe and playback use case.

Signed-off-by: Sriram Periyasamy <sriramx.periyasamy@intel.com>
Signed-off-by: Sanyog Kale <sanyog.r.kale@intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/hdac_hdmi.c | 69 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 84f7a7a36e4b..30ccc902e5cf 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -2103,6 +2103,75 @@ static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
 }
 
 #ifdef CONFIG_PM
+/*
+ * Power management sequences
+ * ==========================
+ *
+ * The following explains the PM handling of HDAC HDMI with its parent
+ * device SKL and display power usage
+ *
+ * Probe
+ * -----
+ * In SKL probe,
+ * 1. skl_probe_work() powers up the display (refcount++ -> 1)
+ * 2. enumerates the codecs on the link
+ * 3. powers down the display  (refcount-- -> 0)
+ *
+ * In HDAC HDMI probe,
+ * 1. hdac_hdmi_dev_probe() powers up the display (refcount++ -> 1)
+ * 2. probe the codec
+ * 3. put the HDAC HDMI device to runtime suspend
+ * 4. hdac_hdmi_runtime_suspend() powers down the display (refcount-- -> 0)
+ *
+ * Once children are runtime suspended, SKL device also goes to runtime
+ * suspend
+ *
+ * HDMI Playback
+ * -------------
+ * Open HDMI device,
+ * 1. skl_runtime_resume() invoked
+ * 2. hdac_hdmi_runtime_resume() powers up the display (refcount++ -> 1)
+ *
+ * Close HDMI device,
+ * 1. hdac_hdmi_runtime_suspend() powers down the display (refcount-- -> 0)
+ * 2. skl_runtime_suspend() invoked
+ *
+ * S0/S3 Cycle with playback in progress
+ * -------------------------------------
+ * When the device is opened for playback, the device is runtime active
+ * already and the display refcount is 1 as explained above.
+ *
+ * Entering to S3,
+ * 1. hdmi_codec_prepare() invoke the runtime resume of codec which just
+ *    increments the PM runtime usage count of the codec since the device
+ *    is in use already
+ * 2. skl_suspend() powers down the display (refcount-- -> 0)
+ *
+ * Wakeup from S3,
+ * 1. skl_resume() powers up the display (refcount++ -> 1)
+ * 2. hdmi_codec_complete() invokes the runtime suspend of codec which just
+ *    decrements the PM runtime usage count of the codec since the device
+ *    is in use already
+ *
+ * Once playback is stopped, the display refcount is set to 0 as explained
+ * above in the HDMI playback sequence. The PM handlings are designed in
+ * such way that to balance the refcount of display power when the codec
+ * device put to S3 while playback is going on.
+ *
+ * S0/S3 Cycle without playback in progress
+ * ----------------------------------------
+ * Entering to S3,
+ * 1. hdmi_codec_prepare() invoke the runtime resume of codec
+ * 2. skl_runtime_resume() invoked
+ * 3. hdac_hdmi_runtime_resume() powers up the display (refcount++ -> 1)
+ * 4. skl_suspend() powers down the display (refcount-- -> 0)
+ *
+ * Wakeup from S3,
+ * 1. skl_resume() powers up the display (refcount++ -> 1)
+ * 2. hdmi_codec_complete() invokes the runtime suspend of codec
+ * 3. hdac_hdmi_runtime_suspend() powers down the display (refcount-- -> 0)
+ * 4. skl_runtime_suspend() invoked
+ */
 static int hdac_hdmi_runtime_suspend(struct device *dev)
 {
 	struct hdac_ext_device *edev = to_hda_ext_device(dev);
-- 
cgit v1.2.3


From e32d99af6830c9a8f37b4f2637ef0cdc60fa79fb Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:50 +0200
Subject: ASoC: meson: add axg fifos DT binding documentation

Add the DT bindings documentation for axg's FIFOs: TODDR and FRDDR.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/amlogic,axg-fifo.txt | 23 ++++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/amlogic,axg-fifo.txt

diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-fifo.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-fifo.txt
new file mode 100644
index 000000000000..3dfc2515e5c6
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-fifo.txt
@@ -0,0 +1,23 @@
+* Amlogic Audio FIFO controllers
+
+Required properties:
+- compatible: 'amlogic,axg-toddr' or
+	      'amlogic,axg-frddr'
+- reg: physical base address of the controller and length of memory
+       mapped region.
+- interrupts: interrupt specifier for the fifo.
+- clocks: phandle to the fifo peripheral clock provided by the audio
+	  clock controller.
+- resets: phandle to memory ARB line provided by the arb reset controller.
+- #sound-dai-cells: must be 0.
+
+Example of FRDDR A on the A113 SoC:
+
+frddr_a: audio-controller@1c0 {
+	compatible = "amlogic,axg-frddr";
+	reg = <0x0 0x1c0 0x0 0x1c>;
+	#sound-dai-cells = <0>;
+	interrupts = <GIC_SPI 88 IRQ_TYPE_EDGE_RISING>;
+	clocks = <&clkc_audio AUD_CLKID_FRDDR_A>;
+	resets = <&arb AXG_ARB_FRDDR_A>;
+};
-- 
cgit v1.2.3


From 6dc4fa179fb86d2c986b2bc8a8377fe4d8c0428d Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:51 +0200
Subject: ASoC: meson: add axg fifo base driver

Amlogic's axg SoCs have two types of fifos which are the memory
interfaces of the audio subsystem. FRDDR provides the playback
interface while TODDR provides the capture interface.

The way these fifos operate is very similar. Only a few settings
are specific to each.

They implement the same pcm driver here and the specifics of each
will be dealt with the related DAI driver.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/Kconfig          |   1 +
 sound/soc/Makefile         |   1 +
 sound/soc/meson/Kconfig    |   8 ++
 sound/soc/meson/Makefile   |   5 +
 sound/soc/meson/axg-fifo.c | 341 +++++++++++++++++++++++++++++++++++++++++++++
 sound/soc/meson/axg-fifo.h |  80 +++++++++++
 6 files changed, 436 insertions(+)
 create mode 100644 sound/soc/meson/Kconfig
 create mode 100644 sound/soc/meson/Makefile
 create mode 100644 sound/soc/meson/axg-fifo.c
 create mode 100644 sound/soc/meson/axg-fifo.h

diff --git a/sound/soc/Kconfig b/sound/soc/Kconfig
index 41af6b9cc350..1cf11cf51e1d 100644
--- a/sound/soc/Kconfig
+++ b/sound/soc/Kconfig
@@ -57,6 +57,7 @@ source "sound/soc/kirkwood/Kconfig"
 source "sound/soc/img/Kconfig"
 source "sound/soc/intel/Kconfig"
 source "sound/soc/mediatek/Kconfig"
+source "sound/soc/meson/Kconfig"
 source "sound/soc/mxs/Kconfig"
 source "sound/soc/pxa/Kconfig"
 source "sound/soc/qcom/Kconfig"
diff --git a/sound/soc/Makefile b/sound/soc/Makefile
index 06389a5385d7..62a5f87c3cfc 100644
--- a/sound/soc/Makefile
+++ b/sound/soc/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_SND_SOC)	+= jz4740/
 obj-$(CONFIG_SND_SOC)	+= img/
 obj-$(CONFIG_SND_SOC)	+= intel/
 obj-$(CONFIG_SND_SOC)	+= mediatek/
+obj-$(CONFIG_SND_SOC)	+= meson/
 obj-$(CONFIG_SND_SOC)	+= mxs/
 obj-$(CONFIG_SND_SOC)	+= nuc900/
 obj-$(CONFIG_SND_SOC)	+= omap/
diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
new file mode 100644
index 000000000000..c3eb5e050308
--- /dev/null
+++ b/sound/soc/meson/Kconfig
@@ -0,0 +1,8 @@
+menu "ASoC support for Amlogic platforms"
+	depends on ARCH_MESON || COMPILE_TEST
+
+config SND_MESON_AXG_FIFO
+	tristate
+	select REGMAP_MMIO
+
+endmenu
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
new file mode 100644
index 000000000000..75289b6b3ade
--- /dev/null
+++ b/sound/soc/meson/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+snd-soc-meson-axg-fifo-objs := axg-fifo.o
+
+obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c
new file mode 100644
index 000000000000..db367d85290f
--- /dev/null
+++ b/sound/soc/meson/axg-fifo.c
@@ -0,0 +1,341 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/module.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-fifo.h"
+
+/*
+ * This file implements the platform operations common to the playback and
+ * capture frontend DAI. The logic behind this two types of fifo is very
+ * similar but some difference exist.
+ * These differences the respective DAI drivers
+ */
+
+static struct snd_pcm_hardware axg_fifo_hw = {
+	.info = (SNDRV_PCM_INFO_INTERLEAVED |
+		 SNDRV_PCM_INFO_MMAP |
+		 SNDRV_PCM_INFO_MMAP_VALID |
+		 SNDRV_PCM_INFO_BLOCK_TRANSFER |
+		 SNDRV_PCM_INFO_PAUSE),
+
+	.formats = AXG_FIFO_FORMATS,
+	.rate_min = 5512,
+	.rate_max = 192000,
+	.channels_min = 1,
+	.channels_max = AXG_FIFO_CH_MAX,
+	.period_bytes_min = AXG_FIFO_MIN_DEPTH,
+	.period_bytes_max = UINT_MAX,
+	.periods_min = 2,
+	.periods_max = UINT_MAX,
+
+	/* No real justification for this */
+	.buffer_bytes_max = 1 * 1024 * 1024,
+};
+
+static struct snd_soc_dai *axg_fifo_dai(struct snd_pcm_substream *ss)
+{
+	struct snd_soc_pcm_runtime *rtd = ss->private_data;
+
+	return rtd->cpu_dai;
+}
+
+static struct axg_fifo *axg_fifo_data(struct snd_pcm_substream *ss)
+{
+	struct snd_soc_dai *dai = axg_fifo_dai(ss);
+
+	return snd_soc_dai_get_drvdata(dai);
+}
+
+static struct device *axg_fifo_dev(struct snd_pcm_substream *ss)
+{
+	struct snd_soc_dai *dai = axg_fifo_dai(ss);
+
+	return dai->dev;
+}
+
+static void __dma_enable(struct axg_fifo *fifo,  bool enable)
+{
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_DMA_EN,
+			   enable ? CTRL0_DMA_EN : 0);
+}
+
+static int axg_fifo_pcm_trigger(struct snd_pcm_substream *ss, int cmd)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		__dma_enable(fifo, true);
+		break;
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+	case SNDRV_PCM_TRIGGER_STOP:
+		__dma_enable(fifo, false);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static snd_pcm_uframes_t axg_fifo_pcm_pointer(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	struct snd_pcm_runtime *runtime = ss->runtime;
+	unsigned int addr;
+
+	regmap_read(fifo->map, FIFO_STATUS2, &addr);
+
+	return bytes_to_frames(runtime, addr - (unsigned int)runtime->dma_addr);
+}
+
+static int axg_fifo_pcm_hw_params(struct snd_pcm_substream *ss,
+				  struct snd_pcm_hw_params *params)
+{
+	struct snd_pcm_runtime *runtime = ss->runtime;
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	dma_addr_t end_ptr;
+	unsigned int burst_num;
+	int ret;
+
+	ret = snd_pcm_lib_malloc_pages(ss, params_buffer_bytes(params));
+	if (ret < 0)
+		return ret;
+
+	/* Setup dma memory pointers */
+	end_ptr = runtime->dma_addr + runtime->dma_bytes - AXG_FIFO_BURST;
+	regmap_write(fifo->map, FIFO_START_ADDR, runtime->dma_addr);
+	regmap_write(fifo->map, FIFO_FINISH_ADDR, end_ptr);
+
+	/* Setup interrupt periodicity */
+	burst_num = params_period_bytes(params) / AXG_FIFO_BURST;
+	regmap_write(fifo->map, FIFO_INT_ADDR, burst_num);
+
+	/* Enable block count irq */
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT),
+			   CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT));
+
+	return 0;
+}
+
+static int axg_fifo_pcm_hw_free(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+
+	/* Disable the block count irq */
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_INT_EN(FIFO_INT_COUNT_REPEAT), 0);
+
+	return snd_pcm_lib_free_pages(ss);
+}
+
+static void axg_fifo_ack_irq(struct axg_fifo *fifo, u8 mask)
+{
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_INT_CLR(FIFO_INT_MASK),
+			   CTRL1_INT_CLR(mask));
+
+	/* Clear must also be cleared */
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_INT_CLR(FIFO_INT_MASK),
+			   0);
+}
+
+static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id)
+{
+	struct snd_pcm_substream *ss = dev_id;
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	unsigned int status;
+
+	regmap_read(fifo->map, FIFO_STATUS1, &status);
+
+	status = STATUS1_INT_STS(status) & FIFO_INT_MASK;
+	if (status & FIFO_INT_COUNT_REPEAT)
+		snd_pcm_period_elapsed(ss);
+	else
+		dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n",
+			status);
+
+	/* Ack irqs */
+	axg_fifo_ack_irq(fifo, status);
+
+	return !status ? IRQ_NONE : IRQ_HANDLED;
+}
+
+static int axg_fifo_pcm_open(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	struct device *dev = axg_fifo_dev(ss);
+	int ret;
+
+	snd_soc_set_runtime_hwparams(ss, &axg_fifo_hw);
+
+	/*
+	 * Make sure the buffer and period size are multiple of the FIFO
+	 * minimum depth size
+	 */
+	ret = snd_pcm_hw_constraint_step(ss->runtime, 0,
+					 SNDRV_PCM_HW_PARAM_BUFFER_BYTES,
+					 AXG_FIFO_MIN_DEPTH);
+	if (ret)
+		return ret;
+
+	ret = snd_pcm_hw_constraint_step(ss->runtime, 0,
+					 SNDRV_PCM_HW_PARAM_PERIOD_BYTES,
+					 AXG_FIFO_MIN_DEPTH);
+	if (ret)
+		return ret;
+
+	ret = request_irq(fifo->irq, axg_fifo_pcm_irq_block, 0,
+			  dev_name(dev), ss);
+
+	/* Enable pclk to access registers and clock the fifo ip */
+	ret = clk_prepare_enable(fifo->pclk);
+	if (ret)
+		return ret;
+
+	/* Setup status2 so it reports the memory pointer */
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_STATUS2_SEL_MASK,
+			   CTRL1_STATUS2_SEL(STATUS2_SEL_DDR_READ));
+
+	/* Make sure the dma is initially disabled */
+	__dma_enable(fifo, false);
+
+	/* Disable irqs until params are ready */
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_INT_EN(FIFO_INT_MASK), 0);
+
+	/* Clear any pending interrupt */
+	axg_fifo_ack_irq(fifo, FIFO_INT_MASK);
+
+	/* Take memory arbitror out of reset */
+	ret = reset_control_deassert(fifo->arb);
+	if (ret)
+		clk_disable_unprepare(fifo->pclk);
+
+	return ret;
+}
+
+static int axg_fifo_pcm_close(struct snd_pcm_substream *ss)
+{
+	struct axg_fifo *fifo = axg_fifo_data(ss);
+	int ret;
+
+	/* Put the memory arbitror back in reset */
+	ret = reset_control_assert(fifo->arb);
+
+	/* Disable fifo ip and register access */
+	clk_disable_unprepare(fifo->pclk);
+
+	/* remove IRQ */
+	free_irq(fifo->irq, ss);
+
+	return ret;
+}
+
+const struct snd_pcm_ops axg_fifo_pcm_ops = {
+	.open =		axg_fifo_pcm_open,
+	.close =        axg_fifo_pcm_close,
+	.ioctl =	snd_pcm_lib_ioctl,
+	.hw_params =	axg_fifo_pcm_hw_params,
+	.hw_free =      axg_fifo_pcm_hw_free,
+	.pointer =	axg_fifo_pcm_pointer,
+	.trigger =	axg_fifo_pcm_trigger,
+};
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_ops);
+
+int axg_fifo_pcm_new(struct snd_soc_pcm_runtime *rtd, unsigned int type)
+{
+	struct snd_card *card = rtd->card->snd_card;
+	size_t size = axg_fifo_hw.buffer_bytes_max;
+
+	return snd_pcm_lib_preallocate_pages(rtd->pcm->streams[type].substream,
+					     SNDRV_DMA_TYPE_DEV, card->dev,
+					     size, size);
+}
+EXPORT_SYMBOL_GPL(axg_fifo_pcm_new);
+
+static const struct regmap_config axg_fifo_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= FIFO_STATUS2,
+};
+
+int axg_fifo_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct axg_fifo_match_data *data;
+	struct axg_fifo *fifo;
+	struct resource *res;
+	void __iomem *regs;
+
+	data = of_device_get_match_data(dev);
+	if (!data) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
+	fifo = devm_kzalloc(dev, sizeof(*fifo), GFP_KERNEL);
+	if (!fifo)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, fifo);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	fifo->map = devm_regmap_init_mmio(dev, regs, &axg_fifo_regmap_cfg);
+	if (IS_ERR(fifo->map)) {
+		dev_err(dev, "failed to init regmap: %ld\n",
+			PTR_ERR(fifo->map));
+		return PTR_ERR(fifo->map);
+	}
+
+	fifo->pclk = devm_clk_get(dev, NULL);
+	if (IS_ERR(fifo->pclk)) {
+		if (PTR_ERR(fifo->pclk) != -EPROBE_DEFER)
+			dev_err(dev, "failed to get pclk: %ld\n",
+				PTR_ERR(fifo->pclk));
+		return PTR_ERR(fifo->pclk);
+	}
+
+	fifo->arb = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(fifo->arb)) {
+		if (PTR_ERR(fifo->arb) != -EPROBE_DEFER)
+			dev_err(dev, "failed to get arb reset: %ld\n",
+				PTR_ERR(fifo->arb));
+		return PTR_ERR(fifo->arb);
+	}
+
+	fifo->irq = of_irq_get(dev->of_node, 0);
+	if (fifo->irq <= 0) {
+		dev_err(dev, "failed to get irq: %d\n", fifo->irq);
+		return fifo->irq;
+	}
+
+	return devm_snd_soc_register_component(dev, data->component_drv,
+					       data->dai_drv, 1);
+}
+EXPORT_SYMBOL_GPL(axg_fifo_probe);
+
+MODULE_DESCRIPTION("Amlogic AXG fifo driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-fifo.h b/sound/soc/meson/axg-fifo.h
new file mode 100644
index 000000000000..cb6c4013ca33
--- /dev/null
+++ b/sound/soc/meson/axg-fifo.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/*
+ * Copyright (c) 2018 BayLibre, SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef _MESON_AXG_FIFO_H
+#define _MESON_AXG_FIFO_H
+
+struct clk;
+struct platform_device;
+struct regmap;
+struct reset_control;
+
+struct snd_soc_component_driver;
+struct snd_soc_dai;
+struct snd_soc_dai_driver;
+struct snd_pcm_ops;
+struct snd_soc_pcm_runtime;
+
+#define AXG_FIFO_CH_MAX			128
+#define AXG_FIFO_RATES			(SNDRV_PCM_RATE_5512 |		\
+					 SNDRV_PCM_RATE_8000_192000)
+#define AXG_FIFO_FORMATS		(SNDRV_PCM_FMTBIT_S8 |		\
+					 SNDRV_PCM_FMTBIT_S16_LE |	\
+					 SNDRV_PCM_FMTBIT_S20_LE |	\
+					 SNDRV_PCM_FMTBIT_S24_LE |	\
+					 SNDRV_PCM_FMTBIT_S32_LE)
+
+#define AXG_FIFO_BURST			8
+#define AXG_FIFO_MIN_CNT		64
+#define AXG_FIFO_MIN_DEPTH		(AXG_FIFO_BURST * AXG_FIFO_MIN_CNT)
+
+#define FIFO_INT_ADDR_FINISH		BIT(0)
+#define FIFO_INT_ADDR_INT		BIT(1)
+#define FIFO_INT_COUNT_REPEAT		BIT(2)
+#define FIFO_INT_COUNT_ONCE		BIT(3)
+#define FIFO_INT_FIFO_ZERO		BIT(4)
+#define FIFO_INT_FIFO_DEPTH		BIT(5)
+#define FIFO_INT_MASK			GENMASK(7, 0)
+
+#define FIFO_CTRL0			0x00
+#define  CTRL0_DMA_EN			BIT(31)
+#define  CTRL0_INT_EN(x)		((x) << 16)
+#define  CTRL0_SEL_MASK			GENMASK(2, 0)
+#define  CTRL0_SEL_SHIFT		0
+#define FIFO_CTRL1			0x04
+#define  CTRL1_INT_CLR(x)		((x) << 0)
+#define  CTRL1_STATUS2_SEL_MASK		GENMASK(11, 8)
+#define  CTRL1_STATUS2_SEL(x)		((x) << 8)
+#define   STATUS2_SEL_DDR_READ		0
+#define  CTRL1_THRESHOLD_MASK		GENMASK(23, 16)
+#define  CTRL1_THRESHOLD(x)		((x) << 16)
+#define  CTRL1_FRDDR_DEPTH_MASK		GENMASK(31, 24)
+#define  CTRL1_FRDDR_DEPTH(x)		((x) << 24)
+#define FIFO_START_ADDR			0x08
+#define FIFO_FINISH_ADDR		0x0c
+#define FIFO_INT_ADDR			0x10
+#define FIFO_STATUS1			0x14
+#define  STATUS1_INT_STS(x)		((x) << 0)
+#define FIFO_STATUS2			0x18
+
+struct axg_fifo {
+	struct regmap *map;
+	struct clk *pclk;
+	struct reset_control *arb;
+	int irq;
+};
+
+struct axg_fifo_match_data {
+	const struct snd_soc_component_driver *component_drv;
+	struct snd_soc_dai_driver *dai_drv;
+};
+
+extern const struct snd_pcm_ops axg_fifo_pcm_ops;
+
+int axg_fifo_pcm_new(struct snd_soc_pcm_runtime *rtd, unsigned int type);
+int axg_fifo_probe(struct platform_device *pdev);
+
+#endif /* _MESON_AXG_FIFO_H */
-- 
cgit v1.2.3


From 57d552e3ea76003643b2e771042659ce71bac7c2 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:52 +0200
Subject: ASoC: meson: add axg frddr driver

Add the playback memory interface of Amlogic's axg SoCs.
This device pulls data from DDR to an internal FIFO.
This FIFO is then used to feed TDM and SPDIF Output devices.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig     |   7 +++
 sound/soc/meson/Makefile    |   2 +
 sound/soc/meson/axg-frddr.c | 141 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 150 insertions(+)
 create mode 100644 sound/soc/meson/axg-frddr.c

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index c3eb5e050308..cdd78f62e8d7 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -5,4 +5,11 @@ config SND_MESON_AXG_FIFO
 	tristate
 	select REGMAP_MMIO
 
+config SND_MESON_AXG_FRDDR
+	tristate "Amlogic AXG Playback FIFO support"
+	select SND_MESON_AXG_FIFO
+	help
+	  Select Y or M to add support for the frontend playback interfaces
+	  embedded in the Amlogic AXG SoC family
+
 endmenu
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index 75289b6b3ade..9c5d7d4a8e33 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0 OR MIT)
 
 snd-soc-meson-axg-fifo-objs := axg-fifo.o
+snd-soc-meson-axg-frddr-objs := axg-frddr.o
 
 obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
+obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
diff --git a/sound/soc/meson/axg-frddr.c b/sound/soc/meson/axg-frddr.c
new file mode 100644
index 000000000000..a6f6f6a2eca8
--- /dev/null
+++ b/sound/soc/meson/axg-frddr.c
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+/* This driver implements the frontend playback DAI of AXG based SoCs */
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-fifo.h"
+
+#define CTRL0_FRDDR_PP_MODE	BIT(30)
+
+static int axg_frddr_dai_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+	unsigned int fifo_depth, fifo_threshold;
+	int ret;
+
+	/* Enable pclk to access registers and clock the fifo ip */
+	ret = clk_prepare_enable(fifo->pclk);
+	if (ret)
+		return ret;
+
+	/* Apply single buffer mode to the interface */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_FRDDR_PP_MODE, 0);
+
+	/*
+	 * TODO: We could adapt the fifo depth and the fifo threshold
+	 * depending on the expected memory throughput and lantencies
+	 * For now, we'll just use the same values as the vendor kernel
+	 * Depth and threshold are zero based.
+	 */
+	fifo_depth = AXG_FIFO_MIN_CNT - 1;
+	fifo_threshold = (AXG_FIFO_MIN_CNT / 2) - 1;
+	regmap_update_bits(fifo->map, FIFO_CTRL1,
+			   CTRL1_FRDDR_DEPTH_MASK | CTRL1_THRESHOLD_MASK,
+			   CTRL1_FRDDR_DEPTH(fifo_depth) |
+			   CTRL1_THRESHOLD(fifo_threshold));
+
+	return 0;
+}
+
+static void axg_frddr_dai_shutdown(struct snd_pcm_substream *substream,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+
+	clk_disable_unprepare(fifo->pclk);
+}
+
+static int axg_frddr_pcm_new(struct snd_soc_pcm_runtime *rtd,
+			     struct snd_soc_dai *dai)
+{
+	return axg_fifo_pcm_new(rtd, SNDRV_PCM_STREAM_PLAYBACK);
+}
+
+static const struct snd_soc_dai_ops axg_frddr_ops = {
+	.startup	= axg_frddr_dai_startup,
+	.shutdown	= axg_frddr_dai_shutdown,
+};
+
+static struct snd_soc_dai_driver axg_frddr_dai_drv = {
+	.name = "FRDDR",
+	.playback = {
+		.stream_name	= "Playback",
+		.channels_min	= 1,
+		.channels_max	= AXG_FIFO_CH_MAX,
+		.rates		= AXG_FIFO_RATES,
+		.formats	= AXG_FIFO_FORMATS,
+	},
+	.ops		= &axg_frddr_ops,
+	.pcm_new	= axg_frddr_pcm_new,
+};
+
+static const char * const axg_frddr_sel_texts[] = {
+	"OUT 0", "OUT 1", "OUT 2", "OUT 3"
+};
+
+static SOC_ENUM_SINGLE_DECL(axg_frddr_sel_enum, FIFO_CTRL0, CTRL0_SEL_SHIFT,
+			    axg_frddr_sel_texts);
+
+static const struct snd_kcontrol_new axg_frddr_out_demux =
+	SOC_DAPM_ENUM("Output Sink", axg_frddr_sel_enum);
+
+static const struct snd_soc_dapm_widget axg_frddr_dapm_widgets[] = {
+	SND_SOC_DAPM_DEMUX("SINK SEL", SND_SOC_NOPM, 0, 0,
+			   &axg_frddr_out_demux),
+	SND_SOC_DAPM_AIF_OUT("OUT 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("OUT 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("OUT 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_OUT("OUT 3", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_frddr_dapm_routes[] = {
+	{ "SINK SEL", NULL, "Playback" },
+	{ "OUT 0", "OUT 0",  "SINK SEL" },
+	{ "OUT 1", "OUT 1",  "SINK SEL" },
+	{ "OUT 2", "OUT 2",  "SINK SEL" },
+	{ "OUT 3", "OUT 3",  "SINK SEL" },
+};
+
+static const struct snd_soc_component_driver axg_frddr_component_drv = {
+	.dapm_widgets		= axg_frddr_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_frddr_dapm_widgets),
+	.dapm_routes		= axg_frddr_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_frddr_dapm_routes),
+	.ops			= &axg_fifo_pcm_ops
+};
+
+static const struct axg_fifo_match_data axg_frddr_match_data = {
+	.component_drv	= &axg_frddr_component_drv,
+	.dai_drv	= &axg_frddr_dai_drv
+};
+
+static const struct of_device_id axg_frddr_of_match[] = {
+	{
+		.compatible = "amlogic,axg-frddr",
+		.data = &axg_frddr_match_data,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_frddr_of_match);
+
+static struct platform_driver axg_frddr_pdrv = {
+	.probe = axg_fifo_probe,
+	.driver = {
+		.name = "axg-frddr",
+		.of_match_table = axg_frddr_of_match,
+	},
+};
+module_platform_driver(axg_frddr_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG playback fifo driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 7ed4877b403c9343a8e2c7581d9bcfceef0f40cf Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:53 +0200
Subject: ASoC: meson: add axg toddr driver

Add the capture memory interface of Amlogic's axg SoCs.
TDM, SPDIF or PDM input devices place audio samples inside this FIFO.
The FIFO content is then pushed to DDR

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig     |   7 ++
 sound/soc/meson/Makefile    |   2 +
 sound/soc/meson/axg-toddr.c | 199 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 208 insertions(+)
 create mode 100644 sound/soc/meson/axg-toddr.c

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index cdd78f62e8d7..3916060edcae 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -12,4 +12,11 @@ config SND_MESON_AXG_FRDDR
 	  Select Y or M to add support for the frontend playback interfaces
 	  embedded in the Amlogic AXG SoC family
 
+config SND_MESON_AXG_TODDR
+	tristate "Amlogic AXG Capture FIFO support"
+	select SND_MESON_AXG_FIFO
+	help
+	  Select Y or M to add support for the frontend capture interfaces
+	  embedded in the Amlogic AXG SoC family
+
 endmenu
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index 9c5d7d4a8e33..12edf2db2a24 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -2,6 +2,8 @@
 
 snd-soc-meson-axg-fifo-objs := axg-fifo.o
 snd-soc-meson-axg-frddr-objs := axg-frddr.o
+snd-soc-meson-axg-toddr-objs := axg-toddr.o
 
 obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
 obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
+obj-$(CONFIG_SND_MESON_AXG_TODDR) += snd-soc-meson-axg-toddr.o
diff --git a/sound/soc/meson/axg-toddr.c b/sound/soc/meson/axg-toddr.c
new file mode 100644
index 000000000000..c2c9bb312586
--- /dev/null
+++ b/sound/soc/meson/axg-toddr.c
@@ -0,0 +1,199 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+/* This driver implements the frontend capture DAI of AXG based SoCs */
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-fifo.h"
+
+#define CTRL0_TODDR_SEL_RESAMPLE	BIT(30)
+#define CTRL0_TODDR_EXT_SIGNED		BIT(29)
+#define CTRL0_TODDR_PP_MODE		BIT(28)
+#define CTRL0_TODDR_TYPE_MASK		GENMASK(15, 13)
+#define CTRL0_TODDR_TYPE(x)		((x) << 13)
+#define CTRL0_TODDR_MSB_POS_MASK	GENMASK(12, 8)
+#define CTRL0_TODDR_MSB_POS(x)		((x) << 8)
+#define CTRL0_TODDR_LSB_POS_MASK	GENMASK(7, 3)
+#define CTRL0_TODDR_LSB_POS(x)		((x) << 3)
+
+static int axg_toddr_pcm_new(struct snd_soc_pcm_runtime *rtd,
+			     struct snd_soc_dai *dai)
+{
+	return axg_fifo_pcm_new(rtd, SNDRV_PCM_STREAM_CAPTURE);
+}
+
+static int axg_toddr_dai_hw_params(struct snd_pcm_substream *substream,
+				   struct snd_pcm_hw_params *params,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+	unsigned int type, width, msb = 31;
+
+	/*
+	 * NOTE:
+	 * Almost all backend will place the MSB at bit 31, except SPDIF Input
+	 * which will put it at index 28. When adding support for the SPDIF
+	 * Input, we'll need to find which type of backend we are connected to.
+	 */
+
+	switch (params_physical_width(params)) {
+	case 8:
+		type = 0; /* 8 samples of 8 bits */
+		break;
+	case 16:
+		type = 2; /* 4 samples of 16 bits - right justified */
+		break;
+	case 32:
+		type = 4; /* 2 samples of 32 bits - right justified */
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	width = params_width(params);
+
+	regmap_update_bits(fifo->map, FIFO_CTRL0,
+			   CTRL0_TODDR_TYPE_MASK |
+			   CTRL0_TODDR_MSB_POS_MASK |
+			   CTRL0_TODDR_LSB_POS_MASK,
+			   CTRL0_TODDR_TYPE(type) |
+			   CTRL0_TODDR_MSB_POS(msb) |
+			   CTRL0_TODDR_LSB_POS(msb - (width - 1)));
+
+	return 0;
+}
+
+static int axg_toddr_dai_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+	unsigned int fifo_threshold;
+	int ret;
+
+	/* Enable pclk to access registers and clock the fifo ip */
+	ret = clk_prepare_enable(fifo->pclk);
+	if (ret)
+		return ret;
+
+	/* Select orginal data - resampling not supported ATM */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_SEL_RESAMPLE, 0);
+
+	/* Only signed format are supported ATM */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_EXT_SIGNED,
+			   CTRL0_TODDR_EXT_SIGNED);
+
+	/* Apply single buffer mode to the interface */
+	regmap_update_bits(fifo->map, FIFO_CTRL0, CTRL0_TODDR_PP_MODE, 0);
+
+	/* TODDR does not have a configurable fifo depth */
+	fifo_threshold = AXG_FIFO_MIN_CNT - 1;
+	regmap_update_bits(fifo->map, FIFO_CTRL1, CTRL1_THRESHOLD_MASK,
+			   CTRL1_THRESHOLD(fifo_threshold));
+
+	return 0;
+}
+
+static void axg_toddr_dai_shutdown(struct snd_pcm_substream *substream,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_fifo *fifo = snd_soc_dai_get_drvdata(dai);
+
+	clk_disable_unprepare(fifo->pclk);
+}
+
+static const struct snd_soc_dai_ops axg_toddr_ops = {
+	.hw_params	= axg_toddr_dai_hw_params,
+	.startup	= axg_toddr_dai_startup,
+	.shutdown	= axg_toddr_dai_shutdown,
+};
+
+static struct snd_soc_dai_driver axg_toddr_dai_drv = {
+	.name = "TODDR",
+	.capture = {
+		.stream_name	= "Capture",
+		.channels_min	= 1,
+		.channels_max	= AXG_FIFO_CH_MAX,
+		.rates		= AXG_FIFO_RATES,
+		.formats	= AXG_FIFO_FORMATS,
+	},
+	.ops		= &axg_toddr_ops,
+	.pcm_new	= axg_toddr_pcm_new,
+};
+
+static const char * const axg_toddr_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2", "IN 3", "IN 4", "IN 6"
+};
+
+static const unsigned int axg_toddr_sel_values[] = {
+	0, 1, 2, 3, 4, 6
+};
+
+static SOC_VALUE_ENUM_SINGLE_DECL(axg_toddr_sel_enum, FIFO_CTRL0,
+				  CTRL0_SEL_SHIFT, CTRL0_SEL_MASK,
+				  axg_toddr_sel_texts, axg_toddr_sel_values);
+
+static const struct snd_kcontrol_new axg_toddr_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_toddr_sel_enum);
+
+static const struct snd_soc_dapm_widget axg_toddr_dapm_widgets[] = {
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_toddr_in_mux),
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 3", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 4", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 6", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_toddr_dapm_routes[] = {
+	{ "Capture", NULL, "SRC SEL" },
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "SRC SEL", "IN 3", "IN 3" },
+	{ "SRC SEL", "IN 4", "IN 4" },
+	{ "SRC SEL", "IN 6", "IN 6" },
+};
+
+static const struct snd_soc_component_driver axg_toddr_component_drv = {
+	.dapm_widgets		= axg_toddr_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_toddr_dapm_widgets),
+	.dapm_routes		= axg_toddr_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_toddr_dapm_routes),
+	.ops			= &axg_fifo_pcm_ops
+};
+
+static const struct axg_fifo_match_data axg_toddr_match_data = {
+	.component_drv	= &axg_toddr_component_drv,
+	.dai_drv	= &axg_toddr_dai_drv
+};
+
+static const struct of_device_id axg_toddr_of_match[] = {
+	{
+		.compatible = "amlogic,axg-toddr",
+		.data = &axg_toddr_match_data,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_toddr_of_match);
+
+static struct platform_driver axg_toddr_pdrv = {
+	.probe = axg_fifo_probe,
+	.driver = {
+		.name = "axg-toddr",
+		.of_match_table = axg_toddr_of_match,
+	},
+};
+module_platform_driver(axg_toddr_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG capture fifo driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From eb257e6607f96fd70a443750e9eaddbb49ba87ff Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:54 +0200
Subject: ASoC: meson: add axg spdif output DT bindings documentation

Add the DT bindings documentation for axg's SPDIF output.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/sound/amlogic,axg-spdifout.txt          | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/amlogic,axg-spdifout.txt

diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-spdifout.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-spdifout.txt
new file mode 100644
index 000000000000..521c38ad89e7
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-spdifout.txt
@@ -0,0 +1,20 @@
+* Amlogic Audio SPDIF Output
+
+Required properties:
+- compatible: 'amlogic,axg-spdifout'
+- clocks: list of clock phandle, one for each entry clock-names.
+- clock-names: should contain the following:
+  * "pclk" : peripheral clock.
+  * "mclk" : master clock
+- #sound-dai-cells: must be 0.
+
+Example on the A113 SoC:
+
+spdifout: audio-controller@480 {
+	compatible = "amlogic,axg-spdifout";
+	reg = <0x0 0x480 0x0 0x50>;
+	#sound-dai-cells = <0>;
+	clocks = <&clkc_audio AUD_CLKID_SPDIFOUT>,
+		 <&clkc_audio AUD_CLKID_SPDIFOUT_CLK>;
+	clock-names = "pclk", "mclk";
+};
-- 
cgit v1.2.3


From 53eb4b7aaa045e23b6e8edb0ae0d047a4a3612ef Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:55 +0200
Subject: ASoC: meson: add axg spdif output

Add support for the spdif output serializer of the axg SoC family

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig        |   7 +
 sound/soc/meson/Makefile       |   2 +
 sound/soc/meson/axg-spdifout.c | 456 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 465 insertions(+)
 create mode 100644 sound/soc/meson/axg-spdifout.c

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index 3916060edcae..9408214b5854 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -19,4 +19,11 @@ config SND_MESON_AXG_TODDR
 	  Select Y or M to add support for the frontend capture interfaces
 	  embedded in the Amlogic AXG SoC family
 
+config SND_MESON_AXG_SPDIFOUT
+	tristate "Amlogic AXG SPDIF Output Support"
+	imply SND_SOC_SPDIF
+	help
+	  Select Y or M to add support for SPDIF output serializer embedded
+	  in the Amlogic AXG SoC family
+
 endmenu
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index 12edf2db2a24..d51ae045ef08 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -3,7 +3,9 @@
 snd-soc-meson-axg-fifo-objs := axg-fifo.o
 snd-soc-meson-axg-frddr-objs := axg-frddr.o
 snd-soc-meson-axg-toddr-objs := axg-toddr.o
+snd-soc-meson-axg-spdifout-objs := axg-spdifout.o
 
 obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
 obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
 obj-$(CONFIG_SND_MESON_AXG_TODDR) += snd-soc-meson-axg-toddr.o
+obj-$(CONFIG_SND_MESON_AXG_SPDIFOUT) += snd-soc-meson-axg-spdifout.o
diff --git a/sound/soc/meson/axg-spdifout.c b/sound/soc/meson/axg-spdifout.c
new file mode 100644
index 000000000000..9dea528053ad
--- /dev/null
+++ b/sound/soc/meson/axg-spdifout.c
@@ -0,0 +1,456 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+#include <sound/pcm_params.h>
+#include <sound/pcm_iec958.h>
+
+/*
+ * NOTE:
+ * The meaning of bits SPDIFOUT_CTRL0_XXX_SEL is actually the opposite
+ * of what the documentation says. Manual control on V, U and C bits is
+ * applied when the related sel bits are cleared
+ */
+
+#define SPDIFOUT_STAT			0x00
+#define SPDIFOUT_GAIN0			0x04
+#define SPDIFOUT_GAIN1			0x08
+#define SPDIFOUT_CTRL0			0x0c
+#define  SPDIFOUT_CTRL0_EN		BIT(31)
+#define  SPDIFOUT_CTRL0_RST_OUT		BIT(29)
+#define  SPDIFOUT_CTRL0_RST_IN		BIT(28)
+#define  SPDIFOUT_CTRL0_USEL		BIT(26)
+#define  SPDIFOUT_CTRL0_USET		BIT(25)
+#define  SPDIFOUT_CTRL0_CHSTS_SEL	BIT(24)
+#define  SPDIFOUT_CTRL0_DATA_SEL	BIT(20)
+#define  SPDIFOUT_CTRL0_MSB_FIRST	BIT(19)
+#define  SPDIFOUT_CTRL0_VSEL		BIT(18)
+#define  SPDIFOUT_CTRL0_VSET		BIT(17)
+#define  SPDIFOUT_CTRL0_MASK_MASK	GENMASK(11, 4)
+#define  SPDIFOUT_CTRL0_MASK(x)		((x) << 4)
+#define SPDIFOUT_CTRL1			0x10
+#define  SPDIFOUT_CTRL1_MSB_POS_MASK	GENMASK(12, 8)
+#define  SPDIFOUT_CTRL1_MSB_POS(x)	((x) << 8)
+#define  SPDIFOUT_CTRL1_TYPE_MASK	GENMASK(6, 4)
+#define  SPDIFOUT_CTRL1_TYPE(x)		((x) << 4)
+#define SPDIFOUT_PREAMB			0x14
+#define SPDIFOUT_SWAP			0x18
+#define SPDIFOUT_CHSTS0			0x1c
+#define SPDIFOUT_CHSTS1			0x20
+#define SPDIFOUT_CHSTS2			0x24
+#define SPDIFOUT_CHSTS3			0x28
+#define SPDIFOUT_CHSTS4			0x2c
+#define SPDIFOUT_CHSTS5			0x30
+#define SPDIFOUT_CHSTS6			0x34
+#define SPDIFOUT_CHSTS7			0x38
+#define SPDIFOUT_CHSTS8			0x3c
+#define SPDIFOUT_CHSTS9			0x40
+#define SPDIFOUT_CHSTSA			0x44
+#define SPDIFOUT_CHSTSB			0x48
+#define SPDIFOUT_MUTE_VAL		0x4c
+
+struct axg_spdifout {
+	struct regmap *map;
+	struct clk *mclk;
+	struct clk *pclk;
+};
+
+static void axg_spdifout_enable(struct regmap *map)
+{
+	/* Apply both reset */
+	regmap_update_bits(map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_RST_OUT | SPDIFOUT_CTRL0_RST_IN,
+			   0);
+
+	/* Clear out reset before in reset */
+	regmap_update_bits(map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_RST_OUT, SPDIFOUT_CTRL0_RST_OUT);
+	regmap_update_bits(map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_RST_IN,  SPDIFOUT_CTRL0_RST_IN);
+
+	/* Enable spdifout */
+	regmap_update_bits(map, SPDIFOUT_CTRL0, SPDIFOUT_CTRL0_EN,
+			   SPDIFOUT_CTRL0_EN);
+}
+
+static void axg_spdifout_disable(struct regmap *map)
+{
+	regmap_update_bits(map, SPDIFOUT_CTRL0, SPDIFOUT_CTRL0_EN, 0);
+}
+
+static int axg_spdifout_trigger(struct snd_pcm_substream *substream, int cmd,
+				struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+
+	switch (cmd) {
+	case SNDRV_PCM_TRIGGER_START:
+	case SNDRV_PCM_TRIGGER_RESUME:
+	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
+		axg_spdifout_enable(priv->map);
+		return 0;
+
+	case SNDRV_PCM_TRIGGER_STOP:
+	case SNDRV_PCM_TRIGGER_SUSPEND:
+	case SNDRV_PCM_TRIGGER_PAUSE_PUSH:
+		axg_spdifout_disable(priv->map);
+		return 0;
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int axg_spdifout_digital_mute(struct snd_soc_dai *dai, int mute)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+
+	/* Use spdif valid bit to perform digital mute */
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0, SPDIFOUT_CTRL0_VSET,
+			   mute ? SPDIFOUT_CTRL0_VSET : 0);
+
+	return 0;
+}
+
+static int axg_spdifout_sample_fmt(struct snd_pcm_hw_params *params,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int val;
+
+	/* Set the samples spdifout will pull from the FIFO */
+	switch (params_channels(params)) {
+	case 1:
+		val = SPDIFOUT_CTRL0_MASK(0x1);
+		break;
+	case 2:
+		val = SPDIFOUT_CTRL0_MASK(0x3);
+		break;
+	default:
+		dev_err(dai->dev, "too many channels for spdif dai: %u\n",
+			params_channels(params));
+		return -EINVAL;
+	}
+
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_MASK_MASK, val);
+
+	/* FIFO data are arranged in chunks of 64bits */
+	switch (params_physical_width(params)) {
+	case 8:
+		/* 8 samples of 8 bits */
+		val = SPDIFOUT_CTRL1_TYPE(0);
+		break;
+	case 16:
+		/* 4 samples of 16 bits - right justified */
+		val = SPDIFOUT_CTRL1_TYPE(2);
+		break;
+	case 32:
+		/* 2 samples of 32 bits - right justified */
+		val = SPDIFOUT_CTRL1_TYPE(4);
+		break;
+	default:
+		dev_err(dai->dev, "Unsupported physical width: %u\n",
+			params_physical_width(params));
+		return -EINVAL;
+	}
+
+	/* Position of the MSB in FIFO samples */
+	val |= SPDIFOUT_CTRL1_MSB_POS(params_width(params) - 1);
+
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL1,
+			   SPDIFOUT_CTRL1_MSB_POS_MASK |
+			   SPDIFOUT_CTRL1_TYPE_MASK, val);
+
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_MSB_FIRST | SPDIFOUT_CTRL0_DATA_SEL,
+			   0);
+
+	return 0;
+}
+
+static int axg_spdifout_set_chsts(struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int offset;
+	int ret;
+	u8 cs[4];
+	u32 val;
+
+	ret = snd_pcm_create_iec958_consumer_hw_params(params, cs, 4);
+	if (ret < 0) {
+		dev_err(dai->dev, "Creating IEC958 channel status failed %d\n",
+			ret);
+		return ret;
+	}
+	val = cs[0] | cs[1] << 8 | cs[2] << 16 | cs[3] << 24;
+
+	/* Setup channel status A bits [31 - 0]*/
+	regmap_write(priv->map, SPDIFOUT_CHSTS0, val);
+
+	/* Clear channel status A bits [191 - 32] */
+	for (offset = SPDIFOUT_CHSTS1; offset <= SPDIFOUT_CHSTS5;
+	     offset += regmap_get_reg_stride(priv->map))
+		regmap_write(priv->map, offset, 0);
+
+	/* Setup channel status B bits [31 - 0]*/
+	regmap_write(priv->map, SPDIFOUT_CHSTS6, val);
+
+	/* Clear channel status B bits [191 - 32] */
+	for (offset = SPDIFOUT_CHSTS7; offset <= SPDIFOUT_CHSTSB;
+	     offset += regmap_get_reg_stride(priv->map))
+		regmap_write(priv->map, offset, 0);
+
+	return 0;
+}
+
+static int axg_spdifout_hw_params(struct snd_pcm_substream *substream,
+				  struct snd_pcm_hw_params *params,
+				  struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	unsigned int rate = params_rate(params);
+	int ret;
+
+	/* 2 * 32bits per subframe * 2 channels = 128 */
+	ret = clk_set_rate(priv->mclk, rate * 128);
+	if (ret) {
+		dev_err(dai->dev, "failed to set spdif clock\n");
+		return ret;
+	}
+
+	ret = axg_spdifout_sample_fmt(params, dai);
+	if (ret) {
+		dev_err(dai->dev, "failed to setup sample format\n");
+		return ret;
+	}
+
+	ret = axg_spdifout_set_chsts(params, dai);
+	if (ret) {
+		dev_err(dai->dev, "failed to setup channel status words\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_spdifout_startup(struct snd_pcm_substream *substream,
+				struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+	int ret;
+
+	/* Clock the spdif output block */
+	ret = clk_prepare_enable(priv->pclk);
+	if (ret) {
+		dev_err(dai->dev, "failed to enable pclk\n");
+		return ret;
+	}
+
+	/* Make sure the block is initially stopped */
+	axg_spdifout_disable(priv->map);
+
+	/* Insert data from bit 27 lsb first */
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_MSB_FIRST | SPDIFOUT_CTRL0_DATA_SEL,
+			   0);
+
+	/* Manual control of V, C and U, U = 0 */
+	regmap_update_bits(priv->map, SPDIFOUT_CTRL0,
+			   SPDIFOUT_CTRL0_CHSTS_SEL | SPDIFOUT_CTRL0_VSEL |
+			   SPDIFOUT_CTRL0_USEL | SPDIFOUT_CTRL0_USET,
+			   0);
+
+	/* Static SWAP configuration ATM */
+	regmap_write(priv->map, SPDIFOUT_SWAP, 0x10);
+
+	return 0;
+}
+
+static void axg_spdifout_shutdown(struct snd_pcm_substream *substream,
+				  struct snd_soc_dai *dai)
+{
+	struct axg_spdifout *priv = snd_soc_dai_get_drvdata(dai);
+
+	clk_disable_unprepare(priv->pclk);
+}
+
+static const struct snd_soc_dai_ops axg_spdifout_ops = {
+	.trigger	= axg_spdifout_trigger,
+	.digital_mute	= axg_spdifout_digital_mute,
+	.hw_params	= axg_spdifout_hw_params,
+	.startup	= axg_spdifout_startup,
+	.shutdown	= axg_spdifout_shutdown,
+};
+
+static struct snd_soc_dai_driver axg_spdifout_dai_drv[] = {
+	{
+		.name = "SPDIF Output",
+		.playback = {
+			.stream_name	= "Playback",
+			.channels_min	= 1,
+			.channels_max	= 2,
+			.rates		= (SNDRV_PCM_RATE_32000  |
+					   SNDRV_PCM_RATE_44100  |
+					   SNDRV_PCM_RATE_48000  |
+					   SNDRV_PCM_RATE_88200  |
+					   SNDRV_PCM_RATE_96000  |
+					   SNDRV_PCM_RATE_176400 |
+					   SNDRV_PCM_RATE_192000),
+			.formats	= (SNDRV_PCM_FMTBIT_S8     |
+					   SNDRV_PCM_FMTBIT_S16_LE |
+					   SNDRV_PCM_FMTBIT_S20_LE |
+					   SNDRV_PCM_FMTBIT_S24_LE),
+		},
+		.ops = &axg_spdifout_ops,
+	},
+};
+
+static const char * const spdifout_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2",
+};
+
+static SOC_ENUM_SINGLE_DECL(axg_spdifout_sel_enum, SPDIFOUT_CTRL1, 24,
+			    spdifout_sel_texts);
+
+static const struct snd_kcontrol_new axg_spdifout_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_spdifout_sel_enum);
+
+static const struct snd_soc_dapm_widget axg_spdifout_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_spdifout_in_mux),
+};
+
+static const struct snd_soc_dapm_route axg_spdifout_dapm_routes[] = {
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "Playback", NULL, "SRC SEL" },
+};
+
+static const struct snd_kcontrol_new axg_spdifout_controls[] = {
+	SOC_DOUBLE("Playback Volume", SPDIFOUT_GAIN0,  0,  8, 255, 0),
+	SOC_DOUBLE("Playback Switch", SPDIFOUT_CTRL0, 22, 21, 1, 1),
+	SOC_SINGLE("Playback Gain Enable Switch",
+		   SPDIFOUT_CTRL1, 26, 1, 0),
+	SOC_SINGLE("Playback Channels Mix Switch",
+		   SPDIFOUT_CTRL0, 23, 1, 0),
+};
+
+static int axg_spdifout_set_bias_level(struct snd_soc_component *component,
+				       enum snd_soc_bias_level level)
+{
+	struct axg_spdifout *priv = snd_soc_component_get_drvdata(component);
+	enum snd_soc_bias_level now =
+		snd_soc_component_get_bias_level(component);
+	int ret = 0;
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		if (now == SND_SOC_BIAS_STANDBY)
+			ret = clk_prepare_enable(priv->mclk);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		if (now == SND_SOC_BIAS_PREPARE)
+			clk_disable_unprepare(priv->mclk);
+		break;
+
+	case SND_SOC_BIAS_OFF:
+	case SND_SOC_BIAS_ON:
+		break;
+	}
+
+	return ret;
+}
+
+static const struct snd_soc_component_driver axg_spdifout_component_drv = {
+	.controls		= axg_spdifout_controls,
+	.num_controls		= ARRAY_SIZE(axg_spdifout_controls),
+	.dapm_widgets		= axg_spdifout_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_spdifout_dapm_widgets),
+	.dapm_routes		= axg_spdifout_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_spdifout_dapm_routes),
+	.set_bias_level		= axg_spdifout_set_bias_level,
+};
+
+static const struct regmap_config axg_spdifout_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= SPDIFOUT_MUTE_VAL,
+};
+
+static const struct of_device_id axg_spdifout_of_match[] = {
+	{ .compatible = "amlogic,axg-spdifout", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, axg_spdifout_of_match);
+
+static int axg_spdifout_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct axg_spdifout *priv;
+	struct resource *res;
+	void __iomem *regs;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, priv);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	priv->map = devm_regmap_init_mmio(dev, regs, &axg_spdifout_regmap_cfg);
+	if (IS_ERR(priv->map)) {
+		dev_err(dev, "failed to init regmap: %ld\n",
+			PTR_ERR(priv->map));
+		return PTR_ERR(priv->map);
+	}
+
+	priv->pclk = devm_clk_get(dev, "pclk");
+	if (IS_ERR(priv->pclk)) {
+		ret = PTR_ERR(priv->pclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get pclk: %d\n", ret);
+		return ret;
+	}
+
+	priv->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(priv->mclk)) {
+		ret = PTR_ERR(priv->mclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get mclk: %d\n", ret);
+		return ret;
+	}
+
+	return devm_snd_soc_register_component(dev, &axg_spdifout_component_drv,
+			axg_spdifout_dai_drv, ARRAY_SIZE(axg_spdifout_dai_drv));
+}
+
+static struct platform_driver axg_spdifout_pdrv = {
+	.probe = axg_spdifout_probe,
+	.driver = {
+		.name = "axg-spdifout",
+		.of_match_table = axg_spdifout_of_match,
+	},
+};
+module_platform_driver(axg_spdifout_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG SPDIF Output driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 7713a70034f2cb54168d134ac523fdfcdda92a13 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:56 +0200
Subject: ASoC: meson: add axg tdm formatters DT bindings documentation

Add the DT bindings documentation for axg's TDM formatters: TDMIN
and TDMOUT.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/sound/amlogic,axg-tdm-formatters.txt  | 28 ++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/amlogic,axg-tdm-formatters.txt

diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-formatters.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-formatters.txt
new file mode 100644
index 000000000000..1c1b7490554e
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-formatters.txt
@@ -0,0 +1,28 @@
+* Amlogic Audio TDM formatters
+
+Required properties:
+- compatible: 'amlogic,axg-tdmin' or
+	      'amlogic,axg-tdmout'
+- reg: physical base address of the controller and length of memory
+       mapped region.
+- clocks: list of clock phandle, one for each entry clock-names.
+- clock-names: should contain the following:
+  * "pclk"     : peripheral clock.
+  * "sclk"     : bit clock.
+  * "sclk_sel" : bit clock input multiplexer.
+  * "lrclk"    : sample clock
+  * "lrclk_sel": sample clock input multiplexer
+
+Example of TDMOUT_A on the A113 SoC:
+
+tdmout_a: audio-controller@500 {
+	compatible = "amlogic,axg-tdmout";
+	reg = <0x0 0x500 0x0 0x40>;
+	clocks = <&clkc_audio AUD_CLKID_TDMOUT_A>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_SCLK>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_SCLK_SEL>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_LRCLK>,
+		 <&clkc_audio AUD_CLKID_TDMOUT_A_LRCLK>;
+	clock-names = "pclk", "sclk", "sclk_sel",
+		      "lrclk", "lrclk_sel";
+};
-- 
cgit v1.2.3


From 02b3a073c12edc8cbc18e07e8880a32e78c1aee0 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 16 Jul 2018 17:30:50 +0200
Subject: regulator: bd9571mwv: Use "backup_mode" sysfs file instead of
 "wake_up"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently the BD9571MWV PMIC driver uses the standard "wake_up" sysfs
file to control enablement of DDR Backup Mode.

However, configuring DDR Backup Mode is not really equivalent to
configuring the PMIC as a wake-up source.  To avoid confusion, use a
custom "backup_mode" attribute file in sysfs instead.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd9571mwv-regulator.c | 52 +++++++++++++++++++++++++++++----
 1 file changed, 47 insertions(+), 5 deletions(-)

diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index be574eb444eb..1da36a6590c8 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -30,6 +30,7 @@ struct bd9571mwv_reg {
 	/* DDR Backup Power */
 	u8 bkup_mode_cnt_keepon;	/* from "rohm,ddr-backup-power" */
 	u8 bkup_mode_cnt_saved;
+	bool bkup_mode_enabled;
 
 	/* Power switch type */
 	bool rstbmode_level;
@@ -171,13 +172,40 @@ static int bd9571mwv_bkup_mode_write(struct bd9571mwv *bd, unsigned int mode)
 	return 0;
 }
 
+static ssize_t backup_mode_show(struct device *dev,
+				struct device_attribute *attr, char *buf)
+{
+	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
+
+	return sprintf(buf, "%s\n", bdreg->bkup_mode_enabled ? "on" : "off");
+}
+
+static ssize_t backup_mode_store(struct device *dev,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
+	int ret;
+
+	if (!count)
+		return 0;
+
+	ret = kstrtobool(buf, &bdreg->bkup_mode_enabled);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+DEVICE_ATTR_RW(backup_mode);
+
 static int bd9571mwv_suspend(struct device *dev)
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
 	unsigned int mode;
 	int ret;
 
-	if (!device_may_wakeup(dev))
+	if (!bdreg->bkup_mode_enabled)
 		return 0;
 
 	/* Save DDR Backup Mode */
@@ -204,7 +232,7 @@ static int bd9571mwv_resume(struct device *dev)
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
 
-	if (!device_may_wakeup(dev))
+	if (!bdreg->bkup_mode_enabled)
 		return 0;
 
 	/* Restore DDR Backup Mode */
@@ -215,9 +243,15 @@ static const struct dev_pm_ops bd9571mwv_pm  = {
 	SET_SYSTEM_SLEEP_PM_OPS(bd9571mwv_suspend, bd9571mwv_resume)
 };
 
+static int bd9571mwv_regulator_remove(struct platform_device *pdev)
+{
+	device_remove_file(&pdev->dev, &dev_attr_backup_mode);
+	return 0;
+}
 #define DEV_PM_OPS	&bd9571mwv_pm
 #else
 #define DEV_PM_OPS	NULL
+#define bd9571mwv_regulator_remove	NULL
 #endif /* CONFIG_PM_SLEEP */
 
 static int bd9571mwv_regulator_probe(struct platform_device *pdev)
@@ -270,14 +304,21 @@ static int bd9571mwv_regulator_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
+#ifdef CONFIG_PM_SLEEP
 	if (bdreg->bkup_mode_cnt_keepon) {
-		device_set_wakeup_capable(&pdev->dev, true);
+		int ret;
+
 		/*
-		 * Wakeup is enabled by default in pulse mode, but needs
+		 * Backup mode is enabled by default in pulse mode, but needs
 		 * explicit user setup in level mode.
 		 */
-		device_set_wakeup_enable(&pdev->dev, bdreg->rstbmode_pulse);
+		bdreg->bkup_mode_enabled = bdreg->rstbmode_pulse;
+
+		ret = device_create_file(&pdev->dev, &dev_attr_backup_mode);
+		if (ret)
+			return ret;
 	}
+#endif /* CONFIG_PM_SLEEP */
 
 	return 0;
 }
@@ -294,6 +335,7 @@ static struct platform_driver bd9571mwv_regulator_driver = {
 		.pm = DEV_PM_OPS,
 	},
 	.probe = bd9571mwv_regulator_probe,
+	.remove = bd9571mwv_regulator_remove,
 	.id_table = bd9571mwv_regulator_id_table,
 };
 module_platform_driver(bd9571mwv_regulator_driver);
-- 
cgit v1.2.3


From e436875f6f97708613976da75a92974f18998af9 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 16 Jul 2018 17:30:51 +0200
Subject: regulator: bd9571mwv: Add support for toggle power switches
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend the existing support for backup mode to toggle power switches.
With a toggle power switch (or level signal), the following steps must
be followed exactly:
   1. Configure PMIC for backup mode, to change the role of the
      accessory power switch from a power switch to a wake-up switch,
   2. Switch accessory power switch off, to prepare for system suspend,
      which is a manual step not controlled by software,
   3. Suspend system,
   4. Switch accessory power switch on, to resume the system.

Hence the PMIC is configured for backup mode when "on" or "1" is written
to the PMIC's "backup_mode" virtual file in sysfs.  Conversely, writing
"off" or "0" reverts the role of the accessory switch to a power
switch.

Unlike with momentary switches, backup mode is not enabled by default,
as enabling it prevents the board from being powered off using the power
switch, which may confuse the user.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd9571mwv-regulator.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index 1da36a6590c8..c44613b9423b 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -185,6 +185,7 @@ static ssize_t backup_mode_store(struct device *dev,
 				 const char *buf, size_t count)
 {
 	struct bd9571mwv_reg *bdreg = dev_get_drvdata(dev);
+	unsigned int mode;
 	int ret;
 
 	if (!count)
@@ -194,6 +195,25 @@ static ssize_t backup_mode_store(struct device *dev,
 	if (ret)
 		return ret;
 
+	if (!bdreg->rstbmode_level)
+		return count;
+
+	/*
+	 * Configure DDR Backup Mode, to change the role of the accessory power
+	 * switch from a power switch to a wake-up switch, or vice versa
+	 */
+	ret = bd9571mwv_bkup_mode_read(bdreg->bd, &mode);
+	if (ret)
+		return ret;
+
+	mode &= ~BD9571MWV_BKUP_MODE_CNT_KEEPON_MASK;
+	if (bdreg->bkup_mode_enabled)
+		mode |= bdreg->bkup_mode_cnt_keepon;
+
+	ret = bd9571mwv_bkup_mode_write(bdreg->bd, mode);
+	if (ret)
+		return ret;
+
 	return count;
 }
 
-- 
cgit v1.2.3


From cf18fd01466d59263c615165341684a055206dd5 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 16 Jul 2018 17:30:52 +0200
Subject: regulator: bd9571mwv: Document "backup_mode" sysfs file
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../ABI/testing/sysfs-driver-bd9571mwv-regulator   | 27 ++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator

diff --git a/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator
new file mode 100644
index 000000000000..4d63a7904b94
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-driver-bd9571mwv-regulator
@@ -0,0 +1,27 @@
+What:		/sys/bus/i2c/devices/.../bd9571mwv-regulator.*.auto/backup_mode
+Date:		Jul 2018
+KernelVersion:	4.19
+Contact:	Geert Uytterhoeven <geert+renesas@glider.be>
+Description:	Read/write the current state of DDR Backup Mode, which controls
+		if DDR power rails will be kept powered during system suspend.
+		("on"/"1" = enabled, "off"/"0" = disabled).
+		Two types of power switches (or control signals) can be used:
+		  A. With a momentary power switch (or pulse signal), DDR
+		     Backup Mode is enabled by default when available, as the
+		     PMIC will be configured only during system suspend.
+		  B. With a toggle power switch (or level signal), the
+		     following steps must be followed exactly:
+		       1. Configure PMIC for backup mode, to change the role of
+			  the accessory power switch from a power switch to a
+			  wake-up switch,
+		       2. Switch accessory power switch off, to prepare for
+			  system suspend, which is a manual step not controlled
+			  by software,
+		       3. Suspend system,
+		       4. Switch accessory power switch on, to resume the
+			  system.
+		     DDR Backup Mode must be explicitly enabled by the user,
+		     to invoke step 1.
+		See also Documentation/devicetree/bindings/mfd/bd9571mwv.txt.
+Users:		User space applications for embedded boards equipped with a
+		BD9571MWV PMIC.
-- 
cgit v1.2.3


From b71c69c26b4916d11b8d403d8e667bbd191f1b8f Mon Sep 17 00:00:00 2001
From: Philipp Puschmann <pp@emlix.com>
Date: Tue, 17 Jul 2018 13:41:12 +0200
Subject: Bluetooth: Use lock_sock_nested in bt_accept_enqueue

Fixes this warning that was provoked by a pairing:

[60258.016221] WARNING: possible recursive locking detected
[60258.021558] 4.15.0-RD1812-BSP #1 Tainted: G           O
[60258.027146] --------------------------------------------
[60258.032464] kworker/u5:0/70 is trying to acquire lock:
[60258.037609]  (sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP){+.+.}, at: [<87759073>] bt_accept_enqueue+0x3c/0x74
[60258.046863]
[60258.046863] but task is already holding lock:
[60258.052704]  (sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP){+.+.}, at: [<d22d7106>] l2cap_sock_new_connection_cb+0x1c/0x88
[60258.062905]
[60258.062905] other info that might help us debug this:
[60258.069441]  Possible unsafe locking scenario:
[60258.069441]
[60258.075368]        CPU0
[60258.077821]        ----
[60258.080272]   lock(sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP);
[60258.085510]   lock(sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP);
[60258.090748]
[60258.090748]  *** DEADLOCK ***
[60258.090748]
[60258.096676]  May be due to missing lock nesting notation
[60258.096676]
[60258.103472] 5 locks held by kworker/u5:0/70:
[60258.107747]  #0:  ((wq_completion)%shdev->name#2){+.+.}, at: [<9460d092>] process_one_work+0x130/0x4fc
[60258.117263]  #1:  ((work_completion)(&hdev->rx_work)){+.+.}, at: [<9460d092>] process_one_work+0x130/0x4fc
[60258.126942]  #2:  (&conn->chan_lock){+.+.}, at: [<7877c8c3>] l2cap_connect+0x80/0x4f8
[60258.134806]  #3:  (&chan->lock/2){+.+.}, at: [<2e16c724>] l2cap_connect+0x8c/0x4f8
[60258.142410]  #4:  (sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP){+.+.}, at: [<d22d7106>] l2cap_sock_new_connection_cb+0x1c/0x88
[60258.153043]
[60258.153043] stack backtrace:
[60258.157413] CPU: 1 PID: 70 Comm: kworker/u5:0 Tainted: G           O     4.15.0-RD1812-BSP #1
[60258.165945] Hardware name: Freescale i.MX6 Quad/DualLite (Device Tree)
[60258.172485] Workqueue: hci0 hci_rx_work
[60258.176331] Backtrace:
[60258.178797] [<8010c9fc>] (dump_backtrace) from [<8010ccbc>] (show_stack+0x18/0x1c)
[60258.186379]  r7:80e55fe4 r6:80e55fe4 r5:20050093 r4:00000000
[60258.192058] [<8010cca4>] (show_stack) from [<809864e8>] (dump_stack+0xb0/0xdc)
[60258.199301] [<80986438>] (dump_stack) from [<8016ecc8>] (__lock_acquire+0xffc/0x11d4)
[60258.207144]  r9:5e2bb019 r8:630f974c r7:ba8a5940 r6:ba8a5ed8 r5:815b5220 r4:80fa081c
[60258.214901] [<8016dccc>] (__lock_acquire) from [<8016f620>] (lock_acquire+0x78/0x98)
[60258.222655]  r10:00000040 r9:00000040 r8:808729f0 r7:00000001 r6:00000000 r5:60050013
[60258.230491]  r4:00000000
[60258.233045] [<8016f5a8>] (lock_acquire) from [<806ee974>] (lock_sock_nested+0x64/0x88)
[60258.240970]  r7:00000000 r6:b796e870 r5:00000001 r4:b796e800
[60258.246643] [<806ee910>] (lock_sock_nested) from [<808729f0>] (bt_accept_enqueue+0x3c/0x74)
[60258.255004]  r8:00000001 r7:ba7d3c00 r6:ba7d3ea4 r5:ba7d2000 r4:b796e800
[60258.261717] [<808729b4>] (bt_accept_enqueue) from [<808aa39c>] (l2cap_sock_new_connection_cb+0x68/0x88)
[60258.271117]  r5:b796e800 r4:ba7d2000
[60258.274708] [<808aa334>] (l2cap_sock_new_connection_cb) from [<808a294c>] (l2cap_connect+0x190/0x4f8)
[60258.283933]  r5:00000001 r4:ba6dce00
[60258.287524] [<808a27bc>] (l2cap_connect) from [<808a4a14>] (l2cap_recv_frame+0x744/0x2cf8)
[60258.295800]  r10:ba6dcf24 r9:00000004 r8:b78d8014 r7:00000004 r6:bb05d000 r5:00000004
[60258.303635]  r4:bb05d008
[60258.306183] [<808a42d0>] (l2cap_recv_frame) from [<808a7808>] (l2cap_recv_acldata+0x210/0x214)
[60258.314805]  r10:b78e7800 r9:bb05d960 r8:00000001 r7:bb05d000 r6:0000000c r5:b7957a80
[60258.322641]  r4:ba6dce00
[60258.325188] [<808a75f8>] (l2cap_recv_acldata) from [<8087630c>] (hci_rx_work+0x35c/0x4e8)
[60258.333374]  r6:80e5743c r5:bb05d7c8 r4:b7957a80
[60258.338004] [<80875fb0>] (hci_rx_work) from [<8013dc7c>] (process_one_work+0x1a4/0x4fc)
[60258.346018]  r10:00000001 r9:00000000 r8:baabfef8 r7:ba997500 r6:baaba800 r5:baaa5d00
[60258.353853]  r4:bb05d7c8
[60258.356401] [<8013dad8>] (process_one_work) from [<8013e028>] (worker_thread+0x54/0x5cc)
[60258.364503]  r10:baabe038 r9:baaba834 r8:80e05900 r7:00000088 r6:baaa5d18 r5:baaba800
[60258.372338]  r4:baaa5d00
[60258.374888] [<8013dfd4>] (worker_thread) from [<801448f8>] (kthread+0x134/0x160)
[60258.382295]  r10:ba8310b8 r9:bb07dbfc r8:8013dfd4 r7:baaa5d00 r6:00000000 r5:baaa8ac0
[60258.390130]  r4:ba831080
[60258.392682] [<801447c4>] (kthread) from [<801080b4>] (ret_from_fork+0x14/0x20)
[60258.399915]  r10:00000000 r9:00000000 r8:00000000 r7:00000000 r6:00000000 r5:801447c4
[60258.407751]  r4:baaa8ac0 r3:baabe000

Signed-off-by: Philipp Puschmann <pp@emlix.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/af_bluetooth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index 3264e1873219..deacc52d7ff1 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -159,7 +159,7 @@ void bt_accept_enqueue(struct sock *parent, struct sock *sk)
 	BT_DBG("parent %p, sk %p", parent, sk);
 
 	sock_hold(sk);
-	lock_sock(sk);
+	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
 	list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q);
 	bt_sk(sk)->parent = parent;
 	release_sock(sk);
-- 
cgit v1.2.3


From 66b19d762378785d1568b5650935205edfeb0503 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 17 Jul 2018 16:23:10 +0200
Subject: spi: dw: fix possible race condition

It is possible to get an interrupt as soon as it is requested.  dw_spi_irq
does spi_controller_get_devdata(master) and expects it to be different than
NULL. However, spi_controller_set_devdata() is called after request_irq(),
resulting in the following crash:

CPU 0 Unable to handle kernel paging request at virtual address 00000030, epc == 8058e09c, ra == 8018ff90
[...]
Call Trace:
[<8058e09c>] dw_spi_irq+0x8/0x64
[<8018ff90>] __handle_irq_event_percpu+0x70/0x1d4
[<80190128>] handle_irq_event_percpu+0x34/0x8c
[<801901c4>] handle_irq_event+0x44/0x80
[<801951a8>] handle_level_irq+0xdc/0x194
[<8018f580>] generic_handle_irq+0x38/0x50
[<804c6924>] ocelot_irq_handler+0x104/0x1c0

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-dw.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index f693bfe95ab9..a087464efdd7 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -485,6 +485,8 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	dws->dma_inited = 0;
 	dws->dma_addr = (dma_addr_t)(dws->paddr + DW_SPI_DR);
 
+	spi_controller_set_devdata(master, dws);
+
 	ret = request_irq(dws->irq, dw_spi_irq, IRQF_SHARED, dev_name(dev),
 			  master);
 	if (ret < 0) {
@@ -518,7 +520,6 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 		}
 	}
 
-	spi_controller_set_devdata(master, dws);
 	ret = devm_spi_register_controller(dev, master);
 	if (ret) {
 		dev_err(&master->dev, "problem registering spi master\n");
-- 
cgit v1.2.3


From 62dbbae483b6452e688b8e26c4d024d484117697 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 17 Jul 2018 16:23:11 +0200
Subject: spi: dw: allow providing own set_cs callback

Allow platform specific drivers to provide their own set_cs callback when
the IP integration requires it.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-dw.c | 3 +++
 drivers/spi/spi-dw.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index f693bfe95ab9..0d8ccb8be5ec 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -505,6 +505,9 @@ int dw_spi_add_host(struct device *dev, struct dw_spi *dws)
 	master->dev.of_node = dev->of_node;
 	master->flags = SPI_MASTER_GPIO_SS;
 
+	if (dws->set_cs)
+		master->set_cs = dws->set_cs;
+
 	/* Basic HW init */
 	spi_hw_init(dev, dws);
 
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 2cde2473b3e9..446013022849 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -112,6 +112,7 @@ struct dw_spi {
 	u32			reg_io_width;	/* DR I/O width in bytes */
 	u16			bus_num;
 	u16			num_cs;		/* supported slave numbers */
+	void (*set_cs)(struct spi_device *spi, bool enable);
 
 	/* Current message transfer state info */
 	size_t			len;
-- 
cgit v1.2.3


From d29ab6e1fa21ebc2a8a771015dd9e0e5d4e28dc1 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 13 Jul 2018 12:41:10 -0700
Subject: bpf: bpf_prog_array_alloc() should return a generic non-rcu pointer

Currently the return type of the bpf_prog_array_alloc() is
struct bpf_prog_array __rcu *, which is not quite correct.
Obviously, the returned pointer is a generic pointer, which
is valid for an indefinite amount of time and it's not shared
with anyone else, so there is no sense in marking it as __rcu.

This change eliminate the following sparse warnings:
kernel/bpf/core.c:1544:31: warning: incorrect type in return expression (different address spaces)
kernel/bpf/core.c:1544:31:    expected struct bpf_prog_array [noderef] <asn:4>*
kernel/bpf/core.c:1544:31:    got void *
kernel/bpf/core.c:1548:17: warning: incorrect type in return expression (different address spaces)
kernel/bpf/core.c:1548:17:    expected struct bpf_prog_array [noderef] <asn:4>*
kernel/bpf/core.c:1548:17:    got struct bpf_prog_array *<noident>
kernel/bpf/core.c:1681:15: warning: incorrect type in assignment (different address spaces)
kernel/bpf/core.c:1681:15:    expected struct bpf_prog_array *array
kernel/bpf/core.c:1681:15:    got struct bpf_prog_array [noderef] <asn:4>*

Fixes: 324bda9e6c5a ("bpf: multi program support for cgroup+bpf")
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h | 2 +-
 kernel/bpf/core.c   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 8827e797ff97..943fb08d8287 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -352,7 +352,7 @@ struct bpf_prog_array {
 	struct bpf_prog *progs[0];
 };
 
-struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
+struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
 void bpf_prog_array_free(struct bpf_prog_array __rcu *progs);
 int bpf_prog_array_length(struct bpf_prog_array __rcu *progs);
 int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 1e5625d46414..253aa8e79c7b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1538,7 +1538,7 @@ static struct {
 	.null_prog = NULL,
 };
 
-struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
+struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
 {
 	if (prog_cnt)
 		return kzalloc(sizeof(struct bpf_prog_array) +
-- 
cgit v1.2.3


From 3960f4fd6585608e8cc285d9665821985494e147 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Fri, 13 Jul 2018 12:41:11 -0700
Subject: bpf: fix rcu annotations in compute_effective_progs()

The progs local variable in compute_effective_progs() is marked
as __rcu, which is not correct. This is a local pointer, which
is initialized by bpf_prog_array_alloc(), which also now
returns a generic non-rcu pointer.

The real rcu-protected pointer is *array (array is a pointer
to an RCU-protected pointer), so the assignment should be performed
using rcu_assign_pointer().

Fixes: 324bda9e6c5a ("bpf: multi program support for cgroup+bpf")
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/cgroup.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 3d83ee7df381..badabb0b435c 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -95,7 +95,7 @@ static int compute_effective_progs(struct cgroup *cgrp,
 				   enum bpf_attach_type type,
 				   struct bpf_prog_array __rcu **array)
 {
-	struct bpf_prog_array __rcu *progs;
+	struct bpf_prog_array *progs;
 	struct bpf_prog_list *pl;
 	struct cgroup *p = cgrp;
 	int cnt = 0;
@@ -120,13 +120,12 @@ static int compute_effective_progs(struct cgroup *cgrp,
 					    &p->bpf.progs[type], node) {
 				if (!pl->prog)
 					continue;
-				rcu_dereference_protected(progs, 1)->
-					progs[cnt++] = pl->prog;
+				progs->progs[cnt++] = pl->prog;
 			}
 		p = cgroup_parent(p);
 	} while (p);
 
-	*array = progs;
+	rcu_assign_pointer(*array, progs);
 	return 0;
 }
 
-- 
cgit v1.2.3


From c23e014a4ba1a9448cbbd74916377f23a7da2fc2 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 17 Jul 2018 09:38:59 +0100
Subject: bpf: sockmap: remove redundant pointer sg

Pointer sg is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'sg' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/sockmap.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index cf7b6a6dbd1f..3e7a5f622712 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -719,11 +719,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send,
 {
 	bool ingress = !!(md->flags & BPF_F_INGRESS);
 	struct smap_psock *psock;
-	struct scatterlist *sg;
 	int err = 0;
 
-	sg = md->sg_data;
-
 	rcu_read_lock();
 	psock = smap_psock_sk(sk);
 	if (unlikely(!psock))
-- 
cgit v1.2.3


From 5f07655b803eca4c215bac9aa61f4bf19f6ecd5e Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:19 -0700
Subject: netdevsim: add switch_id attribute

Grouping netdevsim devices into "ASICs" will soon be supported.
Add switch_id attribute to all netdevsims.  For now each netdevsim
will have its switch_id matching the device id.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/netdevsim/netdev.c    | 24 ++++++++++++++++++++++++
 drivers/net/netdevsim/netdevsim.h |  1 +
 2 files changed, 25 insertions(+)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index a7b179f0d954..9125637ef5d8 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -22,6 +22,7 @@
 #include <net/netlink.h>
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
+#include <net/switchdev.h>
 
 #include "netdevsim.h"
 
@@ -144,12 +145,34 @@ static struct device_type nsim_dev_type = {
 	.release = nsim_dev_release,
 };
 
+static int
+nsim_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	switch (attr->id) {
+	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
+		attr->u.ppid.id_len = sizeof(ns->switch_id);
+		memcpy(&attr->u.ppid.id, &ns->switch_id,
+		       attr->u.ppid.id_len);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct switchdev_ops nsim_switchdev_ops = {
+	.switchdev_port_attr_get	= nsim_port_attr_get,
+};
+
 static int nsim_init(struct net_device *dev)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
 	ns->netdev = dev;
+	ns->switch_id = nsim_dev_id;
+
 	ns->ddir = debugfs_create_dir(netdev_name(dev), nsim_ddir);
 	if (IS_ERR_OR_NULL(ns->ddir))
 		return -ENOMEM;
@@ -166,6 +189,7 @@ static int nsim_init(struct net_device *dev)
 		goto err_bpf_uninit;
 
 	SET_NETDEV_DEV(dev, &ns->dev);
+	SWITCHDEV_SET_OPS(dev, &nsim_switchdev_ops);
 
 	err = nsim_devlink_setup(ns);
 	if (err)
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 0aeabbe81cc6..e2f232325259 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -59,6 +59,7 @@ struct netdevsim {
 	struct u64_stats_sync syncp;
 
 	struct device dev;
+	u32 switch_id;
 
 	struct dentry *ddir;
 
-- 
cgit v1.2.3


From eeeaaf185eca5790529fa184c89452ead7c8c859 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:20 -0700
Subject: netdevsim: add shared netdevsim devices

Factor out sharable netdevsim sub-object and use IFLA_LINK to link
netdevsims together at creation time.  Sharable object will have
its own DebugFS directory.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/netdevsim/netdev.c    | 87 ++++++++++++++++++++++++++++++++++++---
 drivers/net/netdevsim/netdevsim.h | 10 ++++-
 2 files changed, 90 insertions(+), 7 deletions(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 9125637ef5d8..2d244551298b 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -152,8 +152,8 @@ nsim_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_ID_PORT_PARENT_ID:
-		attr->u.ppid.id_len = sizeof(ns->switch_id);
-		memcpy(&attr->u.ppid.id, &ns->switch_id,
+		attr->u.ppid.id_len = sizeof(ns->sdev->switch_id);
+		memcpy(&attr->u.ppid.id, &ns->sdev->switch_id,
 		       attr->u.ppid.id_len);
 		return 0;
 	default:
@@ -167,19 +167,41 @@ static const struct switchdev_ops nsim_switchdev_ops = {
 
 static int nsim_init(struct net_device *dev)
 {
+	char sdev_ddir_name[10], sdev_link_name[32];
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
 	ns->netdev = dev;
-	ns->switch_id = nsim_dev_id;
-
 	ns->ddir = debugfs_create_dir(netdev_name(dev), nsim_ddir);
 	if (IS_ERR_OR_NULL(ns->ddir))
 		return -ENOMEM;
 
+	if (!ns->sdev) {
+		ns->sdev = kzalloc(sizeof(*ns->sdev), GFP_KERNEL);
+		if (!ns->sdev) {
+			err = -ENOMEM;
+			goto err_debugfs_destroy;
+		}
+		ns->sdev->refcnt = 1;
+		ns->sdev->switch_id = nsim_dev_id;
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->ddir = debugfs_create_dir(sdev_ddir_name,
+						    nsim_sdev_ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir)) {
+			err = PTR_ERR_OR_ZERO(ns->sdev->ddir) ?: -EINVAL;
+			goto err_sdev_free;
+		}
+	} else {
+		sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id);
+		ns->sdev->refcnt++;
+	}
+
+	sprintf(sdev_link_name, "../../" DRV_NAME "_sdev/%s", sdev_ddir_name);
+	debugfs_create_symlink("sdev", ns->ddir, sdev_link_name);
+
 	err = nsim_bpf_init(ns);
 	if (err)
-		goto err_debugfs_destroy;
+		goto err_sdev_destroy;
 
 	ns->dev.id = nsim_dev_id++;
 	ns->dev.bus = &nsim_bus;
@@ -203,6 +225,12 @@ err_unreg_dev:
 	device_unregister(&ns->dev);
 err_bpf_uninit:
 	nsim_bpf_uninit(ns);
+err_sdev_destroy:
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+err_sdev_free:
+		kfree(ns->sdev);
+	}
 err_debugfs_destroy:
 	debugfs_remove_recursive(ns->ddir);
 	return err;
@@ -216,6 +244,10 @@ static void nsim_uninit(struct net_device *dev)
 	nsim_devlink_teardown(ns);
 	debugfs_remove_recursive(ns->ddir);
 	nsim_bpf_uninit(ns);
+	if (!--ns->sdev->refcnt) {
+		debugfs_remove_recursive(ns->sdev->ddir);
+		kfree(ns->sdev);
+	}
 }
 
 static void nsim_free(struct net_device *dev)
@@ -494,14 +526,48 @@ static int nsim_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
+static int nsim_newlink(struct net *src_net, struct net_device *dev,
+			struct nlattr *tb[], struct nlattr *data[],
+			struct netlink_ext_ack *extack)
+{
+	struct netdevsim *ns = netdev_priv(dev);
+
+	if (tb[IFLA_LINK]) {
+		struct net_device *joindev;
+		struct netdevsim *joinns;
+
+		joindev = __dev_get_by_index(src_net,
+					     nla_get_u32(tb[IFLA_LINK]));
+		if (!joindev)
+			return -ENODEV;
+		if (joindev->netdev_ops != &nsim_netdev_ops)
+			return -EINVAL;
+
+		joinns = netdev_priv(joindev);
+		if (!joinns->sdev || !joinns->sdev->refcnt)
+			return -EINVAL;
+		ns->sdev = joinns->sdev;
+	}
+
+	return register_netdevice(dev);
+}
+
+static void nsim_dellink(struct net_device *dev, struct list_head *head)
+{
+	unregister_netdevice_queue(dev, head);
+}
+
 static struct rtnl_link_ops nsim_link_ops __read_mostly = {
 	.kind		= DRV_NAME,
 	.priv_size	= sizeof(struct netdevsim),
 	.setup		= nsim_setup,
 	.validate	= nsim_validate,
+	.newlink	= nsim_newlink,
+	.dellink	= nsim_dellink,
 };
 
 struct dentry *nsim_ddir;
+struct dentry *nsim_sdev_ddir;
 
 static int __init nsim_module_init(void)
 {
@@ -511,9 +577,15 @@ static int __init nsim_module_init(void)
 	if (IS_ERR_OR_NULL(nsim_ddir))
 		return -ENOMEM;
 
+	nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL);
+	if (IS_ERR_OR_NULL(nsim_sdev_ddir)) {
+		err = -ENOMEM;
+		goto err_debugfs_destroy;
+	}
+
 	err = bus_register(&nsim_bus);
 	if (err)
-		goto err_debugfs_destroy;
+		goto err_sdir_destroy;
 
 	err = nsim_devlink_init();
 	if (err)
@@ -529,6 +601,8 @@ err_dl_fini:
 	nsim_devlink_exit();
 err_unreg_bus:
 	bus_unregister(&nsim_bus);
+err_sdir_destroy:
+	debugfs_remove_recursive(nsim_sdev_ddir);
 err_debugfs_destroy:
 	debugfs_remove_recursive(nsim_ddir);
 	return err;
@@ -539,6 +613,7 @@ static void __exit nsim_module_exit(void)
 	rtnl_link_unregister(&nsim_link_ops);
 	nsim_devlink_exit();
 	bus_unregister(&nsim_bus);
+	debugfs_remove_recursive(nsim_sdev_ddir);
 	debugfs_remove_recursive(nsim_ddir);
 }
 
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index e2f232325259..8743ce74d2d9 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -30,6 +30,13 @@ struct bpf_prog;
 struct dentry;
 struct nsim_vf_config;
 
+struct netdevsim_shared_dev {
+	unsigned int refcnt;
+	u32 switch_id;
+
+	struct dentry *ddir;
+};
+
 #define NSIM_IPSEC_MAX_SA_COUNT		33
 #define NSIM_IPSEC_VALID		BIT(31)
 
@@ -59,7 +66,7 @@ struct netdevsim {
 	struct u64_stats_sync syncp;
 
 	struct device dev;
-	u32 switch_id;
+	struct netdevsim_shared_dev *sdev;
 
 	struct dentry *ddir;
 
@@ -93,6 +100,7 @@ struct netdevsim {
 };
 
 extern struct dentry *nsim_ddir;
+extern struct dentry *nsim_sdev_ddir;
 
 #ifdef CONFIG_BPF_SYSCALL
 int nsim_bpf_init(struct netdevsim *ns);
-- 
cgit v1.2.3


From d6d6071388e9fc81e11c6f4392666a9f072befe6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:21 -0700
Subject: netdevsim: associate bound programs with shared dev

Move bound program information from netdevsim to shared sub-object,
as programs will soon be shared between netdevs of the same ASIC.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/netdevsim/bpf.c                 | 30 +++++++++++++++++------------
 drivers/net/netdevsim/netdevsim.h           | 11 ++++++-----
 tools/testing/selftests/bpf/test_offload.py |  5 +++--
 3 files changed, 27 insertions(+), 19 deletions(-)

diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index c36d2a768202..357f9e62f306 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -238,8 +238,8 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 	state->state = "verify";
 
 	/* Program id is not populated yet when we create the state. */
-	sprintf(name, "%u", ns->prog_id_gen++);
-	state->ddir = debugfs_create_dir(name, ns->ddir_bpf_bound_progs);
+	sprintf(name, "%u", ns->sdev->prog_id_gen++);
+	state->ddir = debugfs_create_dir(name, ns->sdev->ddir_bpf_bound_progs);
 	if (IS_ERR_OR_NULL(state->ddir)) {
 		kfree(state);
 		return -ENOMEM;
@@ -250,7 +250,7 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog)
 			    &state->state, &nsim_bpf_string_fops);
 	debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded);
 
-	list_add_tail(&state->l, &ns->bpf_bound_progs);
+	list_add_tail(&state->l, &ns->sdev->bpf_bound_progs);
 
 	prog->aux->offload->dev_priv = state;
 
@@ -497,7 +497,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap)
 	}
 
 	offmap->dev_ops = &nsim_bpf_map_ops;
-	list_add_tail(&nmap->l, &ns->bpf_bound_maps);
+	list_add_tail(&nmap->l, &ns->sdev->bpf_bound_maps);
 
 	return 0;
 
@@ -582,8 +582,15 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 
 int nsim_bpf_init(struct netdevsim *ns)
 {
-	INIT_LIST_HEAD(&ns->bpf_bound_progs);
-	INIT_LIST_HEAD(&ns->bpf_bound_maps);
+	if (ns->sdev->refcnt == 1) {
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs);
+		INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps);
+
+		ns->sdev->ddir_bpf_bound_progs =
+			debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir);
+		if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
+			return -ENOMEM;
+	}
 
 	debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
 			   &ns->bpf_offloaded_id);
@@ -593,10 +600,6 @@ int nsim_bpf_init(struct netdevsim *ns)
 			    &ns->bpf_bind_accept);
 	debugfs_create_u32("bpf_bind_verifier_delay", 0600, ns->ddir,
 			   &ns->bpf_bind_verifier_delay);
-	ns->ddir_bpf_bound_progs =
-		debugfs_create_dir("bpf_bound_progs", ns->ddir);
-	if (IS_ERR_OR_NULL(ns->ddir_bpf_bound_progs))
-		return -ENOMEM;
 
 	ns->bpf_tc_accept = true;
 	debugfs_create_bool("bpf_tc_accept", 0600, ns->ddir,
@@ -619,9 +622,12 @@ int nsim_bpf_init(struct netdevsim *ns)
 
 void nsim_bpf_uninit(struct netdevsim *ns)
 {
-	WARN_ON(!list_empty(&ns->bpf_bound_progs));
-	WARN_ON(!list_empty(&ns->bpf_bound_maps));
 	WARN_ON(ns->xdp.prog);
 	WARN_ON(ns->xdp_hw.prog);
 	WARN_ON(ns->bpf_offloaded);
+
+	if (ns->sdev->refcnt == 1) {
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs));
+		WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps));
+	}
 }
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 8743ce74d2d9..98f26fa1e671 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -35,6 +35,12 @@ struct netdevsim_shared_dev {
 	u32 switch_id;
 
 	struct dentry *ddir;
+
+	struct dentry *ddir_bpf_bound_progs;
+	u32 prog_id_gen;
+
+	struct list_head bpf_bound_progs;
+	struct list_head bpf_bound_maps;
 };
 
 #define NSIM_IPSEC_MAX_SA_COUNT		33
@@ -79,12 +85,8 @@ struct netdevsim {
 	struct xdp_attachment_info xdp;
 	struct xdp_attachment_info xdp_hw;
 
-	u32 prog_id_gen;
-
 	bool bpf_bind_accept;
 	u32 bpf_bind_verifier_delay;
-	struct dentry *ddir_bpf_bound_progs;
-	struct list_head bpf_bound_progs;
 
 	bool bpf_tc_accept;
 	bool bpf_tc_non_bound_accept;
@@ -92,7 +94,6 @@ struct netdevsim {
 	bool bpf_xdpoffload_accept;
 
 	bool bpf_map_accept;
-	struct list_head bpf_bound_maps;
 #if IS_ENABLED(CONFIG_NET_DEVLINK)
 	struct devlink *devlink;
 #endif
diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index b746227eaff2..ee1abef384ea 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -314,6 +314,7 @@ class NetdevSim:
         self.ns = ""
 
         self.dfs_dir = '/sys/kernel/debug/netdevsim/%s' % (self.dev['ifname'])
+        self.sdev_dir = self.dfs_dir + '/sdev/'
         self.dfs_refresh()
 
     def __getitem__(self, key):
@@ -345,12 +346,12 @@ class NetdevSim:
         return data.strip()
 
     def dfs_num_bound_progs(self):
-        path = os.path.join(self.dfs_dir, "bpf_bound_progs")
+        path = os.path.join(self.sdev_dir, "bpf_bound_progs")
         _, progs = cmd('ls %s' % (path))
         return len(progs.split())
 
     def dfs_get_bound_progs(self, expected):
-        progs = DebugfsDir(os.path.join(self.dfs_dir, "bpf_bound_progs"))
+        progs = DebugfsDir(os.path.join(self.sdev_dir, "bpf_bound_progs"))
         if expected is not None:
             if len(progs) != expected:
                 fail(True, "%d BPF programs bound, expected %d" %
-- 
cgit v1.2.3


From 4612bebfa379507a4793ef50846c0059aa75a043 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:22 -0700
Subject: nfp: add .ndo_init() and .ndo_uninit() callbacks

BPF code should unregister the offload capabilities from .ndo_uninit(),
to make sure the operation is atomic with unlist_netdevice().  Plumb
the init/uninit NDOs for vNICs and representors.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_app.c        | 17 +++++++++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_app.h        |  8 ++++++++
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c |  2 ++
 drivers/net/ethernet/netronome/nfp/nfp_net_repr.c   |  2 ++
 4 files changed, 29 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index f28b244f4ee7..69d4ae7a61f3 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -86,6 +86,23 @@ const char *nfp_app_mip_name(struct nfp_app *app)
 	return nfp_mip_name(app->pf->mip);
 }
 
+int nfp_app_ndo_init(struct net_device *netdev)
+{
+	struct nfp_app *app = nfp_app_from_netdev(netdev);
+
+	if (!app || !app->type->ndo_init)
+		return 0;
+	return app->type->ndo_init(app, netdev);
+}
+
+void nfp_app_ndo_uninit(struct net_device *netdev)
+{
+	struct nfp_app *app = nfp_app_from_netdev(netdev);
+
+	if (app && app->type->ndo_uninit)
+		app->type->ndo_uninit(app, netdev);
+}
+
 u64 *nfp_app_port_get_stats(struct nfp_port *port, u64 *data)
 {
 	if (!port || !port->app || !port->app->type->port_get_stats)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index ee74caacb015..afbc19aa66a8 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -78,6 +78,8 @@ extern const struct nfp_app_type app_abm;
  * @init:	perform basic app checks and init
  * @clean:	clean app state
  * @extra_cap:	extra capabilities string
+ * @ndo_init:	vNIC and repr netdev .ndo_init
+ * @ndo_uninit:	vNIC and repr netdev .ndo_unint
  * @vnic_alloc:	allocate vNICs (assign port types, etc.)
  * @vnic_free:	free up app's vNIC state
  * @vnic_init:	vNIC netdev was registered
@@ -117,6 +119,9 @@ struct nfp_app_type {
 
 	const char *(*extra_cap)(struct nfp_app *app, struct nfp_net *nn);
 
+	int (*ndo_init)(struct nfp_app *app, struct net_device *netdev);
+	void (*ndo_uninit)(struct nfp_app *app, struct net_device *netdev);
+
 	int (*vnic_alloc)(struct nfp_app *app, struct nfp_net *nn,
 			  unsigned int id);
 	void (*vnic_free)(struct nfp_app *app, struct nfp_net *nn);
@@ -200,6 +205,9 @@ static inline void nfp_app_clean(struct nfp_app *app)
 		app->type->clean(app);
 }
 
+int nfp_app_ndo_init(struct net_device *netdev);
+void nfp_app_ndo_uninit(struct net_device *netdev);
+
 static inline int nfp_app_vnic_alloc(struct nfp_app *app, struct nfp_net *nn,
 				     unsigned int id)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index a712e83c3f0f..279b8ab8a17b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -3480,6 +3480,8 @@ static int nfp_net_set_mac_address(struct net_device *netdev, void *addr)
 }
 
 const struct net_device_ops nfp_net_netdev_ops = {
+	.ndo_init		= nfp_app_ndo_init,
+	.ndo_uninit		= nfp_app_ndo_uninit,
 	.ndo_open		= nfp_net_netdev_open,
 	.ndo_stop		= nfp_net_netdev_close,
 	.ndo_start_xmit		= nfp_net_tx,
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
index d7b712f6362f..18a09cdcd9c6 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c
@@ -262,6 +262,8 @@ err_port_disable:
 }
 
 const struct net_device_ops nfp_repr_netdev_ops = {
+	.ndo_init		= nfp_app_ndo_init,
+	.ndo_uninit		= nfp_app_ndo_uninit,
 	.ndo_open		= nfp_repr_open,
 	.ndo_stop		= nfp_repr_stop,
 	.ndo_start_xmit		= nfp_repr_xmit,
-- 
cgit v1.2.3


From 09728266b6f99ab57cd4f84f3eead65b7b65dbf7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:23 -0700
Subject: bpf: offload: rename bpf_offload_dev_match() to
 bpf_offload_prog_map_match()

A set of new API functions exported for the drivers will soon use
'bpf_offload_dev_' as a prefix.  Rename the bpf_offload_dev_match()
which is internal to the core (used by the verifier) to avoid any
confusion.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h   | 2 +-
 kernel/bpf/offload.c  | 2 +-
 kernel/bpf/verifier.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 943fb08d8287..9b010d9129f3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -648,7 +648,7 @@ int bpf_map_offload_delete_elem(struct bpf_map *map, void *key);
 int bpf_map_offload_get_next_key(struct bpf_map *map,
 				 void *key, void *next_key);
 
-bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map);
+bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
 
 #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index ac747d5cf7c6..6184e48703f4 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -468,7 +468,7 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map)
 	return 0;
 }
 
-bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map)
+bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
 {
 	struct bpf_offloaded_map *offmap;
 	struct bpf_prog_offload *offload;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..15d69b278277 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5054,7 +5054,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 	}
 
 	if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) &&
-	    !bpf_offload_dev_match(prog, map)) {
+	    !bpf_offload_prog_map_match(prog, map)) {
 		verbose(env, "offload device mismatch between prog and map\n");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 9fd7c5559165f4c679b40c5e6ad442955832dfad Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:24 -0700
Subject: bpf: offload: aggregate offloads per-device

Currently we have two lists of offloaded objects - programs and maps.
Netdevice unregister notifier scans those lists to orphan objects
associated with device being unregistered.  This puts unnecessary
(even if negligible) burden on all netdev unregister calls in BPF-
-enabled kernel.  The lists of objects may potentially get long
making the linear scan even more problematic.  There haven't been
complaints about this mechanisms so far, but it is suboptimal.

Instead of relying on notifiers, make the few BPF-capable drivers
register explicitly for BPF offloads.  The programs and maps will
now be collected per-device not on a global list, and only scanned
for removal when driver unregisters from BPF offloads.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.c |  13 +++
 drivers/net/netdevsim/bpf.c                   |   7 ++
 include/linux/bpf.h                           |   3 +
 kernel/bpf/offload.c                          | 142 +++++++++++++++++---------
 4 files changed, 119 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index b95b94d008cf..dee039ada75c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -404,6 +404,16 @@ err_release_free:
 	return -EINVAL;
 }
 
+static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev)
+{
+	return bpf_offload_dev_netdev_register(netdev);
+}
+
+static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev)
+{
+	bpf_offload_dev_netdev_unregister(netdev);
+}
+
 static int nfp_bpf_init(struct nfp_app *app)
 {
 	struct nfp_app_bpf *bpf;
@@ -466,6 +476,9 @@ const struct nfp_app_type app_bpf = {
 
 	.extra_cap	= nfp_bpf_extra_cap,
 
+	.ndo_init	= nfp_bpf_ndo_init,
+	.ndo_uninit	= nfp_bpf_ndo_uninit,
+
 	.vnic_alloc	= nfp_bpf_vnic_alloc,
 	.vnic_free	= nfp_bpf_vnic_free,
 
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 357f9e62f306..c4a2829e0e1f 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -582,6 +582,8 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf)
 
 int nsim_bpf_init(struct netdevsim *ns)
 {
+	int err;
+
 	if (ns->sdev->refcnt == 1) {
 		INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs);
 		INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps);
@@ -592,6 +594,10 @@ int nsim_bpf_init(struct netdevsim *ns)
 			return -ENOMEM;
 	}
 
+	err = bpf_offload_dev_netdev_register(ns->netdev);
+	if (err)
+		return err;
+
 	debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
 			   &ns->bpf_offloaded_id);
 
@@ -625,6 +631,7 @@ void nsim_bpf_uninit(struct netdevsim *ns)
 	WARN_ON(ns->xdp.prog);
 	WARN_ON(ns->xdp_hw.prog);
 	WARN_ON(ns->bpf_offloaded);
+	bpf_offload_dev_netdev_unregister(ns->netdev);
 
 	if (ns->sdev->refcnt == 1) {
 		WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs));
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9b010d9129f3..aa2e834a122b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -650,6 +650,9 @@ int bpf_map_offload_get_next_key(struct bpf_map *map,
 
 bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
 
+int bpf_offload_dev_netdev_register(struct net_device *netdev);
+void bpf_offload_dev_netdev_unregister(struct net_device *netdev);
+
 #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
 
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 6184e48703f4..cd64a26807aa 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -18,19 +18,37 @@
 #include <linux/bug.h>
 #include <linux/kdev_t.h>
 #include <linux/list.h>
+#include <linux/lockdep.h>
 #include <linux/netdevice.h>
 #include <linux/printk.h>
 #include <linux/proc_ns.h>
+#include <linux/rhashtable.h>
 #include <linux/rtnetlink.h>
 #include <linux/rwsem.h>
 
-/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members
+/* Protects offdevs, members of bpf_offload_netdev and offload members
  * of all progs.
  * RTNL lock cannot be taken when holding this lock.
  */
 static DECLARE_RWSEM(bpf_devs_lock);
-static LIST_HEAD(bpf_prog_offload_devs);
-static LIST_HEAD(bpf_map_offload_devs);
+
+struct bpf_offload_netdev {
+	struct rhash_head l;
+	struct net_device *netdev;
+	struct list_head progs;
+	struct list_head maps;
+};
+
+static const struct rhashtable_params offdevs_params = {
+	.nelem_hint		= 4,
+	.key_len		= sizeof(struct net_device *),
+	.key_offset		= offsetof(struct bpf_offload_netdev, netdev),
+	.head_offset		= offsetof(struct bpf_offload_netdev, l),
+	.automatic_shrinking	= true,
+};
+
+static struct rhashtable offdevs;
+static bool offdevs_inited;
 
 static int bpf_dev_offload_check(struct net_device *netdev)
 {
@@ -41,8 +59,19 @@ static int bpf_dev_offload_check(struct net_device *netdev)
 	return 0;
 }
 
+static struct bpf_offload_netdev *
+bpf_offload_find_netdev(struct net_device *netdev)
+{
+	lockdep_assert_held(&bpf_devs_lock);
+
+	if (!offdevs_inited)
+		return NULL;
+	return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+}
+
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 {
+	struct bpf_offload_netdev *ondev;
 	struct bpf_prog_offload *offload;
 	int err;
 
@@ -66,12 +95,13 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr)
 		goto err_maybe_put;
 
 	down_write(&bpf_devs_lock);
-	if (offload->netdev->reg_state != NETREG_REGISTERED) {
+	ondev = bpf_offload_find_netdev(offload->netdev);
+	if (!ondev) {
 		err = -EINVAL;
 		goto err_unlock;
 	}
 	prog->aux->offload = offload;
-	list_add_tail(&offload->offloads, &bpf_prog_offload_devs);
+	list_add_tail(&offload->offloads, &ondev->progs);
 	dev_put(offload->netdev);
 	up_write(&bpf_devs_lock);
 
@@ -294,6 +324,7 @@ static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap,
 struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 {
 	struct net *net = current->nsproxy->net_ns;
+	struct bpf_offload_netdev *ondev;
 	struct bpf_offloaded_map *offmap;
 	int err;
 
@@ -316,11 +347,17 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 	if (err)
 		goto err_unlock;
 
+	ondev = bpf_offload_find_netdev(offmap->netdev);
+	if (!ondev) {
+		err = -EINVAL;
+		goto err_unlock;
+	}
+
 	err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC);
 	if (err)
 		goto err_unlock;
 
-	list_add_tail(&offmap->offloads, &bpf_map_offload_devs);
+	list_add_tail(&offmap->offloads, &ondev->maps);
 	up_write(&bpf_devs_lock);
 	rtnl_unlock();
 
@@ -489,56 +526,69 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
 	return ret;
 }
 
-static void bpf_offload_orphan_all_progs(struct net_device *netdev)
+int bpf_offload_dev_netdev_register(struct net_device *netdev)
 {
-	struct bpf_prog_offload *offload, *tmp;
+	struct bpf_offload_netdev *ondev;
+	int err;
 
-	list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads)
-		if (offload->netdev == netdev)
-			__bpf_prog_offload_destroy(offload->prog);
-}
+	down_write(&bpf_devs_lock);
+	if (!offdevs_inited) {
+		err = rhashtable_init(&offdevs, &offdevs_params);
+		if (err)
+			return err;
+		offdevs_inited = true;
+	}
+	up_write(&bpf_devs_lock);
 
-static void bpf_offload_orphan_all_maps(struct net_device *netdev)
-{
-	struct bpf_offloaded_map *offmap, *tmp;
+	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
+	if (!ondev)
+		return -ENOMEM;
+
+	ondev->netdev = netdev;
+	INIT_LIST_HEAD(&ondev->progs);
+	INIT_LIST_HEAD(&ondev->maps);
+
+	down_write(&bpf_devs_lock);
+	err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params);
+	if (err) {
+		netdev_warn(netdev, "failed to register for BPF offload\n");
+		goto err_unlock_free;
+	}
 
-	list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads)
-		if (offmap->netdev == netdev)
-			__bpf_map_offload_destroy(offmap);
+	up_write(&bpf_devs_lock);
+	return 0;
+
+err_unlock_free:
+	up_write(&bpf_devs_lock);
+	kfree(ondev);
+	return err;
 }
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
 
-static int bpf_offload_notification(struct notifier_block *notifier,
-				    ulong event, void *ptr)
+void bpf_offload_dev_netdev_unregister(struct net_device *netdev)
 {
-	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+	struct bpf_offloaded_map *offmap, *mtmp;
+	struct bpf_prog_offload *offload, *ptmp;
+	struct bpf_offload_netdev *ondev;
 
 	ASSERT_RTNL();
 
-	switch (event) {
-	case NETDEV_UNREGISTER:
-		/* ignore namespace changes */
-		if (netdev->reg_state != NETREG_UNREGISTERING)
-			break;
-
-		down_write(&bpf_devs_lock);
-		bpf_offload_orphan_all_progs(netdev);
-		bpf_offload_orphan_all_maps(netdev);
-		up_write(&bpf_devs_lock);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
+	down_write(&bpf_devs_lock);
+	ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params);
+	if (WARN_ON(!ondev))
+		goto unlock;
 
-static struct notifier_block bpf_offload_notifier = {
-	.notifier_call = bpf_offload_notification,
-};
+	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
 
-static int __init bpf_offload_init(void)
-{
-	register_netdevice_notifier(&bpf_offload_notifier);
-	return 0;
-}
+	list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+		__bpf_prog_offload_destroy(offload->prog);
+	list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+		__bpf_map_offload_destroy(offmap);
 
-subsys_initcall(bpf_offload_init);
+	WARN_ON(!list_empty(&ondev->progs));
+	WARN_ON(!list_empty(&ondev->maps));
+	kfree(ondev);
+unlock:
+	up_write(&bpf_devs_lock);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
-- 
cgit v1.2.3


From 602144c224604f1cbff02ee2d1cf46825269ecbd Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:25 -0700
Subject: bpf: offload: keep the offload state per-ASIC

Create a higher-level entity to represent a device/ASIC to allow
programs and maps to be shared between device ports.  The extra
work is required to make sure we don't destroy BPF objects as
soon as the netdev for which they were loaded gets destroyed,
as other ports may still be using them.  When netdev goes away
all of its BPF objects will be moved to other netdevs of the
device, and only destroyed when last netdev is unregistered.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.c | 14 ++++-
 drivers/net/ethernet/netronome/nfp/bpf/main.h |  4 ++
 drivers/net/netdevsim/bpf.c                   | 17 +++++-
 drivers/net/netdevsim/netdevsim.h             |  3 +
 include/linux/bpf.h                           |  9 ++-
 kernel/bpf/offload.c                          | 81 +++++++++++++++++++++------
 6 files changed, 104 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index dee039ada75c..458f49235d06 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -406,12 +406,16 @@ err_release_free:
 
 static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev)
 {
-	return bpf_offload_dev_netdev_register(netdev);
+	struct nfp_app_bpf *bpf = app->priv;
+
+	return bpf_offload_dev_netdev_register(bpf->bpf_dev, netdev);
 }
 
 static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev)
 {
-	bpf_offload_dev_netdev_unregister(netdev);
+	struct nfp_app_bpf *bpf = app->priv;
+
+	bpf_offload_dev_netdev_unregister(bpf->bpf_dev, netdev);
 }
 
 static int nfp_bpf_init(struct nfp_app *app)
@@ -437,6 +441,11 @@ static int nfp_bpf_init(struct nfp_app *app)
 	if (err)
 		goto err_free_neutral_maps;
 
+	bpf->bpf_dev = bpf_offload_dev_create();
+	err = PTR_ERR_OR_ZERO(bpf->bpf_dev);
+	if (err)
+		goto err_free_neutral_maps;
+
 	return 0;
 
 err_free_neutral_maps:
@@ -455,6 +464,7 @@ static void nfp_bpf_clean(struct nfp_app *app)
 {
 	struct nfp_app_bpf *bpf = app->priv;
 
+	bpf_offload_dev_destroy(bpf->bpf_dev);
 	WARN_ON(!skb_queue_empty(&bpf->cmsg_replies));
 	WARN_ON(!list_empty(&bpf->map_list));
 	WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use);
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 9845c1a2d4c2..bec935468f90 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -110,6 +110,8 @@ enum pkt_vec {
  * struct nfp_app_bpf - bpf app priv structure
  * @app:		backpointer to the app
  *
+ * @bpf_dev:		BPF offload device handle
+ *
  * @tag_allocator:	bitmap of control message tags in use
  * @tag_alloc_next:	next tag bit to allocate
  * @tag_alloc_last:	next tag bit to be freed
@@ -150,6 +152,8 @@ enum pkt_vec {
 struct nfp_app_bpf {
 	struct nfp_app *app;
 
+	struct bpf_offload_dev *bpf_dev;
+
 	DECLARE_BITMAP(tag_allocator, U16_MAX + 1);
 	u16 tag_alloc_next;
 	u16 tag_alloc_last;
diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index c4a2829e0e1f..9eab29f67a0e 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -592,11 +592,16 @@ int nsim_bpf_init(struct netdevsim *ns)
 			debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir);
 		if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs))
 			return -ENOMEM;
+
+		ns->sdev->bpf_dev = bpf_offload_dev_create();
+		err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev);
+		if (err)
+			return err;
 	}
 
-	err = bpf_offload_dev_netdev_register(ns->netdev);
+	err = bpf_offload_dev_netdev_register(ns->sdev->bpf_dev, ns->netdev);
 	if (err)
-		return err;
+		goto err_destroy_bdev;
 
 	debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir,
 			   &ns->bpf_offloaded_id);
@@ -624,6 +629,11 @@ int nsim_bpf_init(struct netdevsim *ns)
 			    &ns->bpf_map_accept);
 
 	return 0;
+
+err_destroy_bdev:
+	if (ns->sdev->refcnt == 1)
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
+	return err;
 }
 
 void nsim_bpf_uninit(struct netdevsim *ns)
@@ -631,10 +641,11 @@ void nsim_bpf_uninit(struct netdevsim *ns)
 	WARN_ON(ns->xdp.prog);
 	WARN_ON(ns->xdp_hw.prog);
 	WARN_ON(ns->bpf_offloaded);
-	bpf_offload_dev_netdev_unregister(ns->netdev);
+	bpf_offload_dev_netdev_unregister(ns->sdev->bpf_dev, ns->netdev);
 
 	if (ns->sdev->refcnt == 1) {
 		WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs));
 		WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps));
+		bpf_offload_dev_destroy(ns->sdev->bpf_dev);
 	}
 }
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 98f26fa1e671..02be199eb005 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -27,6 +27,7 @@
 #define NSIM_EA(extack, msg)	NL_SET_ERR_MSG_MOD((extack), msg)
 
 struct bpf_prog;
+struct bpf_offload_dev;
 struct dentry;
 struct nsim_vf_config;
 
@@ -36,6 +37,8 @@ struct netdevsim_shared_dev {
 
 	struct dentry *ddir;
 
+	struct bpf_offload_dev *bpf_dev;
+
 	struct dentry *ddir_bpf_bound_progs;
 	u32 prog_id_gen;
 
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index aa2e834a122b..913465e45062 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -85,6 +85,7 @@ struct bpf_map {
 	char name[BPF_OBJ_NAME_LEN];
 };
 
+struct bpf_offload_dev;
 struct bpf_offloaded_map;
 
 struct bpf_map_dev_ops {
@@ -650,8 +651,12 @@ int bpf_map_offload_get_next_key(struct bpf_map *map,
 
 bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
 
-int bpf_offload_dev_netdev_register(struct net_device *netdev);
-void bpf_offload_dev_netdev_unregister(struct net_device *netdev);
+struct bpf_offload_dev *bpf_offload_dev_create(void);
+void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev);
+int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+				    struct net_device *netdev);
+void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+				       struct net_device *netdev);
 
 #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index cd64a26807aa..925575f64ff1 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -32,11 +32,17 @@
  */
 static DECLARE_RWSEM(bpf_devs_lock);
 
+struct bpf_offload_dev {
+	struct list_head netdevs;
+};
+
 struct bpf_offload_netdev {
 	struct rhash_head l;
 	struct net_device *netdev;
+	struct bpf_offload_dev *offdev;
 	struct list_head progs;
 	struct list_head maps;
+	struct list_head offdev_netdevs;
 };
 
 static const struct rhashtable_params offdevs_params = {
@@ -526,25 +532,18 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
 	return ret;
 }
 
-int bpf_offload_dev_netdev_register(struct net_device *netdev)
+int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
+				    struct net_device *netdev)
 {
 	struct bpf_offload_netdev *ondev;
 	int err;
 
-	down_write(&bpf_devs_lock);
-	if (!offdevs_inited) {
-		err = rhashtable_init(&offdevs, &offdevs_params);
-		if (err)
-			return err;
-		offdevs_inited = true;
-	}
-	up_write(&bpf_devs_lock);
-
 	ondev = kzalloc(sizeof(*ondev), GFP_KERNEL);
 	if (!ondev)
 		return -ENOMEM;
 
 	ondev->netdev = netdev;
+	ondev->offdev = offdev;
 	INIT_LIST_HEAD(&ondev->progs);
 	INIT_LIST_HEAD(&ondev->maps);
 
@@ -555,6 +554,7 @@ int bpf_offload_dev_netdev_register(struct net_device *netdev)
 		goto err_unlock_free;
 	}
 
+	list_add(&ondev->offdev_netdevs, &offdev->netdevs);
 	up_write(&bpf_devs_lock);
 	return 0;
 
@@ -565,11 +565,12 @@ err_unlock_free:
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register);
 
-void bpf_offload_dev_netdev_unregister(struct net_device *netdev)
+void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
+				       struct net_device *netdev)
 {
+	struct bpf_offload_netdev *ondev, *altdev;
 	struct bpf_offloaded_map *offmap, *mtmp;
 	struct bpf_prog_offload *offload, *ptmp;
-	struct bpf_offload_netdev *ondev;
 
 	ASSERT_RTNL();
 
@@ -579,11 +580,26 @@ void bpf_offload_dev_netdev_unregister(struct net_device *netdev)
 		goto unlock;
 
 	WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params));
-
-	list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
-		__bpf_prog_offload_destroy(offload->prog);
-	list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
-		__bpf_map_offload_destroy(offmap);
+	list_del(&ondev->offdev_netdevs);
+
+	/* Try to move the objects to another netdev of the device */
+	altdev = list_first_entry_or_null(&offdev->netdevs,
+					  struct bpf_offload_netdev,
+					  offdev_netdevs);
+	if (altdev) {
+		list_for_each_entry(offload, &ondev->progs, offloads)
+			offload->netdev = altdev->netdev;
+		list_splice_init(&ondev->progs, &altdev->progs);
+
+		list_for_each_entry(offmap, &ondev->maps, offloads)
+			offmap->netdev = altdev->netdev;
+		list_splice_init(&ondev->maps, &altdev->maps);
+	} else {
+		list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads)
+			__bpf_prog_offload_destroy(offload->prog);
+		list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads)
+			__bpf_map_offload_destroy(offmap);
+	}
 
 	WARN_ON(!list_empty(&ondev->progs));
 	WARN_ON(!list_empty(&ondev->maps));
@@ -592,3 +608,34 @@ unlock:
 	up_write(&bpf_devs_lock);
 }
 EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister);
+
+struct bpf_offload_dev *bpf_offload_dev_create(void)
+{
+	struct bpf_offload_dev *offdev;
+	int err;
+
+	down_write(&bpf_devs_lock);
+	if (!offdevs_inited) {
+		err = rhashtable_init(&offdevs, &offdevs_params);
+		if (err)
+			return ERR_PTR(err);
+		offdevs_inited = true;
+	}
+	up_write(&bpf_devs_lock);
+
+	offdev = kzalloc(sizeof(*offdev), GFP_KERNEL);
+	if (!offdev)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&offdev->netdevs);
+
+	return offdev;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_create);
+
+void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev)
+{
+	WARN_ON(!list_empty(&offdev->netdevs));
+	kfree(offdev);
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy);
-- 
cgit v1.2.3


From fd4f227dea0f24d89f52f7c4eb3207f84ddcbcbd Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:26 -0700
Subject: bpf: offload: allow program and map sharing per-ASIC

Allow programs and maps to be re-used across different netdevs,
as long as they belong to the same struct bpf_offload_dev.
Update the bpf_offload_prog_map_match() helper for the verifier
and export a new helper for the drivers to use when checking
programs at attachment time.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h  |  1 +
 kernel/bpf/offload.c | 42 +++++++++++++++++++++++++++++++++++-------
 2 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 913465e45062..5b5ad95cf339 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -657,6 +657,7 @@ int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
 				    struct net_device *netdev);
 void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
 				       struct net_device *netdev);
+bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev);
 
 #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
 int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 925575f64ff1..177a52436394 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -511,22 +511,50 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map)
 	return 0;
 }
 
-bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
+static bool __bpf_offload_dev_match(struct bpf_prog *prog,
+				    struct net_device *netdev)
 {
-	struct bpf_offloaded_map *offmap;
+	struct bpf_offload_netdev *ondev1, *ondev2;
 	struct bpf_prog_offload *offload;
-	bool ret;
 
 	if (!bpf_prog_is_dev_bound(prog->aux))
 		return false;
-	if (!bpf_map_is_dev_bound(map))
-		return bpf_map_offload_neutral(map);
 
-	down_read(&bpf_devs_lock);
 	offload = prog->aux->offload;
+	if (!offload)
+		return false;
+	if (offload->netdev == netdev)
+		return true;
+
+	ondev1 = bpf_offload_find_netdev(offload->netdev);
+	ondev2 = bpf_offload_find_netdev(netdev);
+
+	return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev;
+}
+
+bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev)
+{
+	bool ret;
+
+	down_read(&bpf_devs_lock);
+	ret = __bpf_offload_dev_match(prog, netdev);
+	up_read(&bpf_devs_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(bpf_offload_dev_match);
+
+bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map)
+{
+	struct bpf_offloaded_map *offmap;
+	bool ret;
+
+	if (!bpf_map_is_dev_bound(map))
+		return bpf_map_offload_neutral(map);
 	offmap = map_to_offmap(map);
 
-	ret = offload && offload->netdev == offmap->netdev;
+	down_read(&bpf_devs_lock);
+	ret = __bpf_offload_dev_match(prog, offmap->netdev);
 	up_read(&bpf_devs_lock);
 
 	return ret;
-- 
cgit v1.2.3


From 9d1b66b8ae95a0b7c6a12e9d138d41f55e911fde Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:27 -0700
Subject: netdevsim: allow program sharing between devices

Allow program sharing between devices which were linked together.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/netdevsim/bpf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 9eab29f67a0e..81444208b216 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -294,7 +294,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "xdpoffload of non-bound program");
 		return -EINVAL;
 	}
-	if (bpf->prog->aux->offload->netdev != ns->netdev) {
+	if (!bpf_offload_dev_match(bpf->prog, ns->netdev)) {
 		NSIM_EA(bpf->extack, "program bound to different dev");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From b5faa20d6fb28144a71885720a436e2297e26e9b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:28 -0700
Subject: nfp: bpf: allow program sharing within ASIC

Allow program sharing between netdevs of the same NFP ASIC.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 78f44c4d95b4..49b03f7dbf46 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -566,14 +566,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog,
 {
 	int err;
 
-	if (prog) {
-		struct bpf_prog_offload *offload = prog->aux->offload;
-
-		if (!offload)
-			return -EINVAL;
-		if (offload->netdev != nn->dp.netdev)
-			return -EINVAL;
-	}
+	if (prog && !bpf_offload_dev_match(prog, nn->dp.netdev))
+		return -EINVAL;
 
 	if (prog && old_prog) {
 		u8 cap;
-- 
cgit v1.2.3


From 7736b6ed665a8a339f6499f4b0f162386d46fd86 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 10:53:29 -0700
Subject: selftests/bpf: add test for sharing objects between netdevs

Add tests for sharing programs and maps between different netdevs.
Use netdevsim's ability to pretend multiple netdevs belong to the
same "ASIC".

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_offload.py | 146 +++++++++++++++++++++++++++-
 1 file changed, 142 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py
index ee1abef384ea..d59642e70f56 100755
--- a/tools/testing/selftests/bpf/test_offload.py
+++ b/tools/testing/selftests/bpf/test_offload.py
@@ -158,8 +158,9 @@ def tool(name, args, flags, JSON=True, ns="", fail=True, include_stderr=False):
     else:
         return ret, out
 
-def bpftool(args, JSON=True, ns="", fail=True):
-    return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns, fail=fail)
+def bpftool(args, JSON=True, ns="", fail=True, include_stderr=False):
+    return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns,
+                fail=fail, include_stderr=include_stderr)
 
 def bpftool_prog_list(expected=None, ns=""):
     _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True)
@@ -201,6 +202,21 @@ def bpftool_map_list_wait(expected=0, n_retry=20):
         time.sleep(0.05)
     raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
 
+def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None,
+                      fail=True, include_stderr=False):
+    args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name)
+    if prog_type is not None:
+        args += " type " + prog_type
+    if dev is not None:
+        args += " dev " + dev
+    if len(maps):
+        args += " map " + " map ".join(maps)
+
+    res = bpftool(args, fail=fail, include_stderr=include_stderr)
+    if res[0] == 0:
+        files.append(file_name)
+    return res
+
 def ip(args, force=False, JSON=True, ns="", fail=True, include_stderr=False):
     if force:
         args = "-force " + args
@@ -307,7 +323,9 @@ class NetdevSim:
     Class for netdevsim netdevice and its attributes.
     """
 
-    def __init__(self):
+    def __init__(self, link=None):
+        self.link = link
+
         self.dev = self._netdevsim_create()
         devs.append(self)
 
@@ -321,8 +339,9 @@ class NetdevSim:
         return self.dev[key]
 
     def _netdevsim_create(self):
+        link = "" if self.link is None else "link " + self.link.dev['ifname']
         _, old  = ip("link show")
-        ip("link add sim%d type netdevsim")
+        ip("link add sim%d {link} type netdevsim".format(link=link))
         _, new  = ip("link show")
 
         for dev in new:
@@ -848,6 +867,25 @@ try:
     sim.set_mtu(1500)
 
     sim.wait_for_flush()
+    start_test("Test non-offload XDP attaching to HW...")
+    bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/nooffload")
+    nooffload = bpf_pinned("/sys/fs/bpf/nooffload")
+    ret, _, err = sim.set_xdp(nooffload, "offload",
+                              fail=False, include_stderr=True)
+    fail(ret == 0, "attached non-offloaded XDP program to HW")
+    check_extack_nsim(err, "xdpoffload of non-bound program.", args)
+    rm("/sys/fs/bpf/nooffload")
+
+    start_test("Test offload XDP attaching to drv...")
+    bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload",
+                      dev=sim['ifname'])
+    offload = bpf_pinned("/sys/fs/bpf/offload")
+    ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True)
+    fail(ret == 0, "attached offloaded XDP program to drv")
+    check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args)
+    rm("/sys/fs/bpf/offload")
+    sim.wait_for_flush()
+
     start_test("Test XDP offload...")
     _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True)
     ipl = sim.ip_link_show(xdp=True)
@@ -1141,6 +1179,106 @@ try:
     fail(ret == 0,
          "netdevsim didn't refuse to create a map with offload disabled")
 
+    sim.remove()
+
+    start_test("Test multi-dev ASIC program reuse...")
+    simA = NetdevSim()
+    simB1 = NetdevSim()
+    simB2 = NetdevSim(link=simB1)
+    simB3 = NetdevSim(link=simB1)
+    sims = (simA, simB1, simB2, simB3)
+    simB = (simB1, simB2, simB3)
+
+    bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimA",
+                      dev=simA['ifname'])
+    progA = bpf_pinned("/sys/fs/bpf/nsimA")
+    bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB",
+                      dev=simB1['ifname'])
+    progB = bpf_pinned("/sys/fs/bpf/nsimB")
+
+    simA.set_xdp(progA, "offload", JSON=False)
+    for d in simB:
+        d.set_xdp(progB, "offload", JSON=False)
+
+    start_test("Test multi-dev ASIC cross-dev replace...")
+    ret, _ = simA.set_xdp(progB, "offload", force=True, JSON=False, fail=False)
+    fail(ret == 0, "cross-ASIC program allowed")
+    for d in simB:
+        ret, _ = d.set_xdp(progA, "offload", force=True, JSON=False, fail=False)
+        fail(ret == 0, "cross-ASIC program allowed")
+
+    start_test("Test multi-dev ASIC cross-dev install...")
+    for d in sims:
+        d.unset_xdp("offload")
+
+    ret, _, err = simA.set_xdp(progB, "offload", force=True, JSON=False,
+                               fail=False, include_stderr=True)
+    fail(ret == 0, "cross-ASIC program allowed")
+    check_extack_nsim(err, "program bound to different dev.", args)
+    for d in simB:
+        ret, _, err = d.set_xdp(progA, "offload", force=True, JSON=False,
+                                fail=False, include_stderr=True)
+        fail(ret == 0, "cross-ASIC program allowed")
+        check_extack_nsim(err, "program bound to different dev.", args)
+
+    start_test("Test multi-dev ASIC cross-dev map reuse...")
+
+    mapA = bpftool("prog show %s" % (progA))[1]["map_ids"][0]
+    mapB = bpftool("prog show %s" % (progB))[1]["map_ids"][0]
+
+    ret, _ = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB_",
+                               dev=simB3['ifname'],
+                               maps=["idx 0 id %d" % (mapB)],
+                               fail=False)
+    fail(ret != 0, "couldn't reuse a map on the same ASIC")
+    rm("/sys/fs/bpf/nsimB_")
+
+    ret, _, err = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimA_",
+                                    dev=simA['ifname'],
+                                    maps=["idx 0 id %d" % (mapB)],
+                                    fail=False, include_stderr=True)
+    fail(ret == 0, "could reuse a map on a different ASIC")
+    fail(err.count("offload device mismatch between prog and map") == 0,
+         "error message missing for cross-ASIC map")
+
+    ret, _, err = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB_",
+                                    dev=simB1['ifname'],
+                                    maps=["idx 0 id %d" % (mapA)],
+                                    fail=False, include_stderr=True)
+    fail(ret == 0, "could reuse a map on a different ASIC")
+    fail(err.count("offload device mismatch between prog and map") == 0,
+         "error message missing for cross-ASIC map")
+
+    start_test("Test multi-dev ASIC cross-dev destruction...")
+    bpftool_prog_list_wait(expected=2)
+
+    simA.remove()
+    bpftool_prog_list_wait(expected=1)
+
+    ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"]
+    fail(ifnameB != simB1['ifname'], "program not bound to originial device")
+    simB1.remove()
+    bpftool_prog_list_wait(expected=1)
+
+    start_test("Test multi-dev ASIC cross-dev destruction - move...")
+    ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"]
+    fail(ifnameB not in (simB2['ifname'], simB3['ifname']),
+         "program not bound to remaining devices")
+
+    simB2.remove()
+    ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"]
+    fail(ifnameB != simB3['ifname'], "program not bound to remaining device")
+
+    simB3.remove()
+    bpftool_prog_list_wait(expected=0)
+
+    start_test("Test multi-dev ASIC cross-dev destruction - orphaned...")
+    ret, out = bpftool("prog show %s" % (progB), fail=False)
+    fail(ret == 0, "got information about orphaned program")
+    fail("error" not in out, "no error reported for get info on orphaned")
+    fail(out["error"] != "can't get prog info: No such device",
+         "wrong error for get info on orphaned")
+
     print("%s: OK" % (os.path.basename(__file__)))
 
 finally:
-- 
cgit v1.2.3


From 01f8f33e9986aed42a0366704f715cf30e7cb41c Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Jul 2018 09:41:21 +0100
Subject: drm/i915: Always retire residual requests before suspend

If the driver is wedged, we skip idling the GPU. However, we may still
have a few requests still not retired following the wedging (since they
will be waiting for a background worker trying to acquire struct_mutex).
As we hold the struct_mutex, always do a quick request retirement in
order to flush the wedged path.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107257
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717084121.28185-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_gem.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 08266791801e..fcc73a6ab503 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5074,6 +5074,8 @@ int i915_gem_suspend(struct drm_i915_private *i915)
 
 		assert_kernel_context_is_current(i915);
 	}
+	i915_retire_requests(i915); /* ensure we flush after wedging */
+
 	mutex_unlock(&i915->drm.struct_mutex);
 
 	intel_uc_suspend(i915);
-- 
cgit v1.2.3


From 9ea97a7d689c55a5528bfaad499edf1a4ca02e2a Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 13 Jul 2018 10:15:59 +0200
Subject: mtd: powernv_flash: set of_node in mtd's dev
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This enables some features implemented in mtd subsystem like reading
label and partitioning info from DT.

Reported-by: Timothy Pearson <tpearson@raptorengineering.com>
Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/devices/powernv_flash.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
index c1312b141ae0..33593122e49b 100644
--- a/drivers/mtd/devices/powernv_flash.c
+++ b/drivers/mtd/devices/powernv_flash.c
@@ -223,6 +223,7 @@ static int powernv_flash_set_driver_info(struct device *dev,
 	mtd->_read = powernv_flash_read;
 	mtd->_write = powernv_flash_write;
 	mtd->dev.parent = dev;
+	mtd_set_of_node(mtd, dev->of_node);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 4897015d2ffb78c3064eeffa2d4022c5be3ea18f Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 13 Jul 2018 11:27:33 +0200
Subject: mtd: maps: use mtd_device_register() where applicable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If driver doesn't specify parsers it can use that little helper.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/maps/impa7.c            | 5 ++---
 drivers/mtd/maps/intel_vr_nor.c     | 2 +-
 drivers/mtd/maps/latch-addr-flash.c | 5 ++---
 drivers/mtd/maps/rbtx4939-flash.c   | 3 +--
 4 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/mtd/maps/impa7.c b/drivers/mtd/maps/impa7.c
index a0b8fa7849a9..815e2db87955 100644
--- a/drivers/mtd/maps/impa7.c
+++ b/drivers/mtd/maps/impa7.c
@@ -88,9 +88,8 @@ static int __init init_impa7(void)
 		if (impa7_mtd[i]) {
 			impa7_mtd[i]->owner = THIS_MODULE;
 			devicesfound++;
-			mtd_device_parse_register(impa7_mtd[i], NULL, NULL,
-						  partitions,
-						  ARRAY_SIZE(partitions));
+			mtd_device_register(impa7_mtd[i], partitions,
+					    ARRAY_SIZE(partitions));
 		} else {
 			iounmap((void __iomem *)impa7_map[i].virt);
 		}
diff --git a/drivers/mtd/maps/intel_vr_nor.c b/drivers/mtd/maps/intel_vr_nor.c
index dd5d6855f543..69503aef981e 100644
--- a/drivers/mtd/maps/intel_vr_nor.c
+++ b/drivers/mtd/maps/intel_vr_nor.c
@@ -71,7 +71,7 @@ static int vr_nor_init_partitions(struct vr_nor_mtd *p)
 {
 	/* register the flash bank */
 	/* partition the flash bank */
-	return mtd_device_parse_register(p->info, NULL, NULL, NULL, 0);
+	return mtd_device_register(p->info, NULL, 0);
 }
 
 static void vr_nor_destroy_mtd_setup(struct vr_nor_mtd *p)
diff --git a/drivers/mtd/maps/latch-addr-flash.c b/drivers/mtd/maps/latch-addr-flash.c
index 6dc97aa667dc..51db24b7f88d 100644
--- a/drivers/mtd/maps/latch-addr-flash.c
+++ b/drivers/mtd/maps/latch-addr-flash.c
@@ -197,9 +197,8 @@ static int latch_addr_flash_probe(struct platform_device *dev)
 	}
 	info->mtd->dev.parent = &dev->dev;
 
-	mtd_device_parse_register(info->mtd, NULL, NULL,
-				  latch_addr_data->parts,
-				  latch_addr_data->nr_parts);
+	mtd_device_register(info->mtd, latch_addr_data->parts,
+			    latch_addr_data->nr_parts);
 	return 0;
 
 iounmap:
diff --git a/drivers/mtd/maps/rbtx4939-flash.c b/drivers/mtd/maps/rbtx4939-flash.c
index 3a06ecfc55ff..80a187167c92 100644
--- a/drivers/mtd/maps/rbtx4939-flash.c
+++ b/drivers/mtd/maps/rbtx4939-flash.c
@@ -97,8 +97,7 @@ static int rbtx4939_flash_probe(struct platform_device *dev)
 		goto err_out;
 	}
 	info->mtd->dev.parent = &dev->dev;
-	err = mtd_device_parse_register(info->mtd, NULL, NULL, pdata->parts,
-					pdata->nr_parts);
+	err = mtd_device_register(info->mtd, pdata->parts, pdata->nr_parts);
 
 	if (err)
 		goto err_out;
-- 
cgit v1.2.3


From 39675caa06e77547cf0692f854dce015e1b5c36b Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 13 Jul 2018 11:27:34 +0200
Subject: mtd: sst25l: use mtd_device_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This driver doesn't specify parsers so it can use that little helper.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/devices/sst25l.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/devices/sst25l.c b/drivers/mtd/devices/sst25l.c
index 1897f33fe3e7..10d24efb4629 100644
--- a/drivers/mtd/devices/sst25l.c
+++ b/drivers/mtd/devices/sst25l.c
@@ -394,9 +394,8 @@ static int sst25l_probe(struct spi_device *spi)
 	      flash->mtd.numeraseregions);
 
 
-	ret = mtd_device_parse_register(&flash->mtd, NULL, NULL,
-					data ? data->parts : NULL,
-					data ? data->nr_parts : 0);
+	ret = mtd_device_register(&flash->mtd, data ? data->parts : NULL,
+				  data ? data->nr_parts : 0);
 	if (ret)
 		return -ENODEV;
 
-- 
cgit v1.2.3


From c4592b9c37889c2850b0edadcff063d5097f1cb9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 13 Jul 2018 16:47:16 +0200
Subject: jffs2: use 64-bit intermediate timestamps

The VFS now uses timespec64 timestamps consistently, but jffs2 still
converts them to 32-bit numbers on the storage medium. As the helper
functions for the conversion (get_seconds() and timespec_to_timespec64())
are now deprecated, let's change them over to the more modern
replacements.

This keeps the traditional interpretation of those values, where
the on-disk 32-bit numbers are taken to be negative numbers, i.e.
dates before 1970, on 32-bit machines, but future numbers past 2038
on 64-bit machines.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 fs/jffs2/dir.c      | 32 ++++++++++++++++----------------
 fs/jffs2/file.c     |  6 +++---
 fs/jffs2/fs.c       | 12 ++++++------
 fs/jffs2/os-linux.h |  3 ++-
 4 files changed, 27 insertions(+), 26 deletions(-)

diff --git a/fs/jffs2/dir.c b/fs/jffs2/dir.c
index b2944f9218f7..f20cff1194bb 100644
--- a/fs/jffs2/dir.c
+++ b/fs/jffs2/dir.c
@@ -201,7 +201,7 @@ static int jffs2_create(struct inode *dir_i, struct dentry *dentry,
 	if (ret)
 		goto fail;
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(ri->ctime));
 
 	jffs2_free_raw_inode(ri);
 
@@ -227,14 +227,14 @@ static int jffs2_unlink(struct inode *dir_i, struct dentry *dentry)
 	struct jffs2_inode_info *dir_f = JFFS2_INODE_INFO(dir_i);
 	struct jffs2_inode_info *dead_f = JFFS2_INODE_INFO(d_inode(dentry));
 	int ret;
-	uint32_t now = get_seconds();
+	uint32_t now = JFFS2_NOW();
 
 	ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
 			      dentry->d_name.len, dead_f, now);
 	if (dead_f->inocache)
 		set_nlink(d_inode(dentry), dead_f->inocache->pino_nlink);
 	if (!ret)
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 	return ret;
 }
 /***********************************************************************/
@@ -260,7 +260,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 	type = (d_inode(old_dentry)->i_mode & S_IFMT) >> 12;
 	if (!type) type = DT_REG;
 
-	now = get_seconds();
+	now = JFFS2_NOW();
 	ret = jffs2_do_link(c, dir_f, f->inocache->ino, type, dentry->d_name.name, dentry->d_name.len, now);
 
 	if (!ret) {
@@ -268,7 +268,7 @@ static int jffs2_link (struct dentry *old_dentry, struct inode *dir_i, struct de
 		set_nlink(d_inode(old_dentry), ++f->inocache->pino_nlink);
 		mutex_unlock(&f->sem);
 		d_instantiate(dentry, d_inode(old_dentry));
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 		ihold(d_inode(old_dentry));
 	}
 	return ret;
@@ -400,7 +400,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 	rd->type = DT_LNK;
 	rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
@@ -418,7 +418,7 @@ static int jffs2_symlink (struct inode *dir_i, struct dentry *dentry, const char
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 
 	jffs2_free_raw_dirent(rd);
 
@@ -543,7 +543,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 	rd->type = DT_DIR;
 	rd->node_crc = cpu_to_je32(crc32(0, rd, sizeof(*rd)-8));
@@ -561,7 +561,7 @@ static int jffs2_mkdir (struct inode *dir_i, struct dentry *dentry, umode_t mode
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 	inc_nlink(dir_i);
 
 	jffs2_free_raw_dirent(rd);
@@ -588,7 +588,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	struct jffs2_inode_info *f = JFFS2_INODE_INFO(d_inode(dentry));
 	struct jffs2_full_dirent *fd;
 	int ret;
-	uint32_t now = get_seconds();
+	uint32_t now = JFFS2_NOW();
 
 	for (fd = f->dents ; fd; fd = fd->next) {
 		if (fd->ino)
@@ -598,7 +598,7 @@ static int jffs2_rmdir (struct inode *dir_i, struct dentry *dentry)
 	ret = jffs2_do_unlink(c, dir_f, dentry->d_name.name,
 			      dentry->d_name.len, f, now);
 	if (!ret) {
-		dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		dir_i->i_mtime = dir_i->i_ctime = ITIME(now);
 		clear_nlink(d_inode(dentry));
 		drop_nlink(dir_i);
 	}
@@ -712,7 +712,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 	rd->pino = cpu_to_je32(dir_i->i_ino);
 	rd->version = cpu_to_je32(++dir_f->highest_version);
 	rd->ino = cpu_to_je32(inode->i_ino);
-	rd->mctime = cpu_to_je32(get_seconds());
+	rd->mctime = cpu_to_je32(JFFS2_NOW());
 	rd->nsize = namelen;
 
 	/* XXX: This is ugly. */
@@ -733,7 +733,7 @@ static int jffs2_mknod (struct inode *dir_i, struct dentry *dentry, umode_t mode
 		goto fail;
 	}
 
-	dir_i->i_mtime = dir_i->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(rd->mctime)));
+	dir_i->i_mtime = dir_i->i_ctime = ITIME(je32_to_cpu(rd->mctime));
 
 	jffs2_free_raw_dirent(rd);
 
@@ -797,7 +797,7 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 	type = (d_inode(old_dentry)->i_mode & S_IFMT) >> 12;
 	if (!type) type = DT_REG;
 
-	now = get_seconds();
+	now = JFFS2_NOW();
 	ret = jffs2_do_link(c, JFFS2_INODE_INFO(new_dir_i),
 			    d_inode(old_dentry)->i_ino, type,
 			    new_dentry->d_name.name, new_dentry->d_name.len, now);
@@ -853,14 +853,14 @@ static int jffs2_rename (struct inode *old_dir_i, struct dentry *old_dentry,
 		 * caller won't do it on its own since we are returning an error.
 		 */
 		d_invalidate(new_dentry);
-		new_dir_i->i_mtime = new_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+		new_dir_i->i_mtime = new_dir_i->i_ctime = ITIME(now);
 		return ret;
 	}
 
 	if (d_is_dir(old_dentry))
 		drop_nlink(old_dir_i);
 
-	new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = timespec_to_timespec64(ITIME(now));
+	new_dir_i->i_mtime = new_dir_i->i_ctime = old_dir_i->i_mtime = old_dir_i->i_ctime = ITIME(now);
 
 	return 0;
 }
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 481afd4c2e1a..7d8654a1472e 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -175,7 +175,7 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
 		ri.uid = cpu_to_je16(i_uid_read(inode));
 		ri.gid = cpu_to_je16(i_gid_read(inode));
 		ri.isize = cpu_to_je32(max((uint32_t)inode->i_size, pageofs));
-		ri.atime = ri.ctime = ri.mtime = cpu_to_je32(get_seconds());
+		ri.atime = ri.ctime = ri.mtime = cpu_to_je32(JFFS2_NOW());
 		ri.offset = cpu_to_je32(inode->i_size);
 		ri.dsize = cpu_to_je32(pageofs - inode->i_size);
 		ri.csize = cpu_to_je32(0);
@@ -283,7 +283,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 	ri->uid = cpu_to_je16(i_uid_read(inode));
 	ri->gid = cpu_to_je16(i_gid_read(inode));
 	ri->isize = cpu_to_je32((uint32_t)inode->i_size);
-	ri->atime = ri->ctime = ri->mtime = cpu_to_je32(get_seconds());
+	ri->atime = ri->ctime = ri->mtime = cpu_to_je32(JFFS2_NOW());
 
 	/* In 2.4, it was already kmapped by generic_file_write(). Doesn't
 	   hurt to do it again. The alternative is ifdefs, which are ugly. */
@@ -308,7 +308,7 @@ static int jffs2_write_end(struct file *filp, struct address_space *mapping,
 			inode->i_size = pos + writtenlen;
 			inode->i_blocks = (inode->i_size + 511) >> 9;
 
-			inode->i_ctime = inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
+			inode->i_ctime = inode->i_mtime = ITIME(je32_to_cpu(ri->ctime));
 		}
 	}
 
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 0ecfb8ea38cd..eab04eca95a3 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -146,9 +146,9 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr)
 		return PTR_ERR(new_metadata);
 	}
 	/* It worked. Update the inode */
-	inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->atime)));
-	inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->ctime)));
-	inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(ri->mtime)));
+	inode->i_atime = ITIME(je32_to_cpu(ri->atime));
+	inode->i_ctime = ITIME(je32_to_cpu(ri->ctime));
+	inode->i_mtime = ITIME(je32_to_cpu(ri->mtime));
 	inode->i_mode = jemode_to_cpu(ri->mode);
 	i_uid_write(inode, je16_to_cpu(ri->uid));
 	i_gid_write(inode, je16_to_cpu(ri->gid));
@@ -280,9 +280,9 @@ struct inode *jffs2_iget(struct super_block *sb, unsigned long ino)
 	i_uid_write(inode, je16_to_cpu(latest_node.uid));
 	i_gid_write(inode, je16_to_cpu(latest_node.gid));
 	inode->i_size = je32_to_cpu(latest_node.isize);
-	inode->i_atime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.atime)));
-	inode->i_mtime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.mtime)));
-	inode->i_ctime = timespec_to_timespec64(ITIME(je32_to_cpu(latest_node.ctime)));
+	inode->i_atime = ITIME(je32_to_cpu(latest_node.atime));
+	inode->i_mtime = ITIME(je32_to_cpu(latest_node.mtime));
+	inode->i_ctime = ITIME(je32_to_cpu(latest_node.ctime));
 
 	set_nlink(inode, f->inocache->pino_nlink);
 
diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index c2fbec19c616..acbe1f722f2d 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -31,7 +31,8 @@ struct kvec;
 #define JFFS2_F_I_GID(f) (i_gid_read(OFNI_EDONI_2SFFJ(f)))
 #define JFFS2_F_I_RDEV(f) (OFNI_EDONI_2SFFJ(f)->i_rdev)
 
-#define ITIME(sec) ((struct timespec){sec, 0})
+#define ITIME(sec) ((struct timespec64){(int32_t)sec, 0})
+#define JFFS2_NOW() (ktime_get_real_seconds())
 #define I_SEC(tv) ((tv).tv_sec)
 #define JFFS2_F_I_CTIME(f) (OFNI_EDONI_2SFFJ(f)->i_ctime.tv_sec)
 #define JFFS2_F_I_MTIME(f) (OFNI_EDONI_2SFFJ(f)->i_mtime.tv_sec)
-- 
cgit v1.2.3


From 5f7a01e222635cba7e4889ad4ebd891835e8b2eb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 13 Jul 2018 16:47:17 +0200
Subject: jffs2: use unsigned 32-bit timstamps consistently

Most users of jffs2 are 32-bit systems that traditionally only support
timestamps using a 32-bit signed time_t, in the range from years 1902 to
2038. On 64-bit systems, jffs2 however interpreted the same timestamps
as unsigned values, reading back negative times (before 1970) as times
between 2038 and 2106.

Now that Linux supports 64-bit inode timestamps even on 32-bit systems,
let's use the second interpretation everywhere to allow jffs2 to be
used on 32-bit systems beyond 2038 without a fundamental change to the
inode format.

This has a slight risk of regressions, when existing files with timestamps
before 1970 are present in file system images and are now interpreted
as future time stamps. I considered moving the wraparound point a bit,
e.g. to 1960, in order to deal with timestamps that ended up on Dec 31,
1969 due to incorrect timezone handling. However, this would complicate
the implementation unnecessarily, so I went with the simplest possible
method of extending the timestamps.

Writing files with timestamps before 1970 or after 2106 now results
in those times being clamped in the file system.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 fs/jffs2/os-linux.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h
index acbe1f722f2d..a2dbbb3f4c74 100644
--- a/fs/jffs2/os-linux.h
+++ b/fs/jffs2/os-linux.h
@@ -31,13 +31,13 @@ struct kvec;
 #define JFFS2_F_I_GID(f) (i_gid_read(OFNI_EDONI_2SFFJ(f)))
 #define JFFS2_F_I_RDEV(f) (OFNI_EDONI_2SFFJ(f)->i_rdev)
 
-#define ITIME(sec) ((struct timespec64){(int32_t)sec, 0})
-#define JFFS2_NOW() (ktime_get_real_seconds())
-#define I_SEC(tv) ((tv).tv_sec)
-#define JFFS2_F_I_CTIME(f) (OFNI_EDONI_2SFFJ(f)->i_ctime.tv_sec)
-#define JFFS2_F_I_MTIME(f) (OFNI_EDONI_2SFFJ(f)->i_mtime.tv_sec)
-#define JFFS2_F_I_ATIME(f) (OFNI_EDONI_2SFFJ(f)->i_atime.tv_sec)
-
+#define JFFS2_CLAMP_TIME(t) ((uint32_t)clamp_t(time64_t, (t), 0, U32_MAX))
+#define ITIME(sec) ((struct timespec64){sec, 0})
+#define JFFS2_NOW() JFFS2_CLAMP_TIME(ktime_get_real_seconds())
+#define I_SEC(tv) JFFS2_CLAMP_TIME((tv).tv_sec)
+#define JFFS2_F_I_CTIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_ctime)
+#define JFFS2_F_I_MTIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_mtime)
+#define JFFS2_F_I_ATIME(f) I_SEC(OFNI_EDONI_2SFFJ(f)->i_atime)
 #define sleep_on_spinunlock(wq, s)				\
 	do {							\
 		DECLARE_WAITQUEUE(__wait, current);		\
-- 
cgit v1.2.3


From 89fd23efa0d7934ed9ec93c77486a047759d6543 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Sat, 14 Jul 2018 14:42:00 +0200
Subject: mtd: Fallback to ->_read/write() when ->_read/write_oob() is missing

Some MTD sublayers/drivers are implementing ->_read/write() and
not ->_read/write_oob().

While for NAND devices both are usually valid, for NOR devices, using
the _oob variant has no real meaning. But, as the MTD layer is supposed
to hide as much as possible the flash complexity to the user, there is
no reason to error out while it is just a matter of rewritting things
internally.

Add a fallback on mtd->_read() (resp. mtd->_write()) when the user calls
mtd_read_oob() (resp. mtd_write_oob()) while mtd->_read_oob() (resp.
mtd->_write_oob) is not implemented. There is already a fallback on the
_oob variant if the former is used.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/mtdcore.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 42395df06be9..97ac219c082e 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -1155,21 +1155,29 @@ int mtd_read_oob(struct mtd_info *mtd, loff_t from, struct mtd_oob_ops *ops)
 {
 	int ret_code;
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_read_oob)
-		return -EOPNOTSUPP;
 
 	ret_code = mtd_check_oob_ops(mtd, from, ops);
 	if (ret_code)
 		return ret_code;
 
 	ledtrig_mtd_activity();
+
+	/* Check the validity of a potential fallback on mtd->_read */
+	if (!mtd->_read_oob && (!mtd->_read || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_read_oob)
+		ret_code = mtd->_read_oob(mtd, from, ops);
+	else
+		ret_code = mtd->_read(mtd, from, ops->len, &ops->retlen,
+				      ops->datbuf);
+
 	/*
 	 * In cases where ops->datbuf != NULL, mtd->_read_oob() has semantics
 	 * similar to mtd->_read(), returning a non-negative integer
 	 * representing max bitflips. In other cases, mtd->_read_oob() may
 	 * return -EUCLEAN. In all cases, perform similar logic to mtd_read().
 	 */
-	ret_code = mtd->_read_oob(mtd, from, ops);
 	if (unlikely(ret_code < 0))
 		return ret_code;
 	if (mtd->ecc_strength == 0)
@@ -1184,8 +1192,7 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 	int ret;
 
 	ops->retlen = ops->oobretlen = 0;
-	if (!mtd->_write_oob)
-		return -EOPNOTSUPP;
+
 	if (!(mtd->flags & MTD_WRITEABLE))
 		return -EROFS;
 
@@ -1194,7 +1201,16 @@ int mtd_write_oob(struct mtd_info *mtd, loff_t to,
 		return ret;
 
 	ledtrig_mtd_activity();
-	return mtd->_write_oob(mtd, to, ops);
+
+	/* Check the validity of a potential fallback on mtd->_write */
+	if (!mtd->_write_oob && (!mtd->_write || ops->oobbuf))
+		return -EOPNOTSUPP;
+
+	if (mtd->_write_oob)
+		return mtd->_write_oob(mtd, to, ops);
+	else
+		return mtd->_write(mtd, to, ops->len, &ops->retlen,
+				   ops->datbuf);
 }
 EXPORT_SYMBOL_GPL(mtd_write_oob);
 
-- 
cgit v1.2.3


From 3f289dcb4b265416a57ca79cf4a324060bb09060 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 18 Jul 2018 04:47:36 -0700
Subject: block: make bdev_ops->rw_page() take a REQ_OP instead of bool

c11f0c0b5bb9 ("block/mm: make bdev_ops->rw_page() take a bool for
read/write") replaced @op with boolean @is_write, which limited the
amount of information going into ->rw_page() and more importantly
page_endio(), which removed the need to expose block internals to mm.

Unfortunately, we want to track discards separately and @is_write
isn't enough information.  This patch updates bdev_ops->rw_page() to
take REQ_OP instead but leaves page_endio() to take bool @is_write.
This allows the block part of operations to have enough information
while not leaking it to mm.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/brd.c           | 14 +++++++-------
 drivers/block/zram/zram_drv.c | 16 ++++++++--------
 drivers/nvdimm/btt.c          | 12 ++++++------
 drivers/nvdimm/pmem.c         | 13 ++++++-------
 fs/block_dev.c                |  6 ++++--
 fs/mpage.c                    |  4 ++--
 include/linux/blkdev.h        |  2 +-
 7 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index bb976598ee43..df8103dd40ac 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -254,20 +254,20 @@ static void copy_from_brd(void *dst, struct brd_device *brd,
  * Process a single bvec of a bio.
  */
 static int brd_do_bvec(struct brd_device *brd, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	void *mem;
 	int err = 0;
 
-	if (is_write) {
+	if (op_is_write(op)) {
 		err = copy_to_brd_setup(brd, sector, len);
 		if (err)
 			goto out;
 	}
 
 	mem = kmap_atomic(page);
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		copy_from_brd(mem + off, brd, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -296,7 +296,7 @@ static blk_qc_t brd_make_request(struct request_queue *q, struct bio *bio)
 		int err;
 
 		err = brd_do_bvec(brd, bvec.bv_page, len, bvec.bv_offset,
-					op_is_write(bio_op(bio)), sector);
+				  bio_op(bio), sector);
 		if (err)
 			goto io_error;
 		sector += len >> SECTOR_SHIFT;
@@ -310,15 +310,15 @@ io_error:
 }
 
 static int brd_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct brd_device *brd = bdev->bd_disk->private_data;
 	int err;
 
 	if (PageTransHuge(page))
 		return -ENOTSUPP;
-	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, is_write, sector);
-	page_endio(page, is_write, err);
+	err = brd_do_bvec(brd, page, PAGE_SIZE, 0, op, sector);
+	page_endio(page, op_is_write(op), err);
 	return err;
 }
 
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 7436b2d27fa3..78c29044684a 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1274,17 +1274,17 @@ static void zram_bio_discard(struct zram *zram, u32 index,
  * Returns 1 if IO request was successfully submitted.
  */
 static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
-			int offset, bool is_write, struct bio *bio)
+			int offset, unsigned int op, struct bio *bio)
 {
 	unsigned long start_time = jiffies;
-	int rw_acct = is_write ? REQ_OP_WRITE : REQ_OP_READ;
+	int rw_acct = op_is_write(op) ? REQ_OP_WRITE : REQ_OP_READ;
 	struct request_queue *q = zram->disk->queue;
 	int ret;
 
 	generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		atomic64_inc(&zram->stats.num_reads);
 		ret = zram_bvec_read(zram, bvec, index, offset, bio);
 		flush_dcache_page(bvec->bv_page);
@@ -1300,7 +1300,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 	zram_slot_unlock(zram, index);
 
 	if (unlikely(ret < 0)) {
-		if (!is_write)
+		if (!op_is_write(op))
 			atomic64_inc(&zram->stats.failed_reads);
 		else
 			atomic64_inc(&zram->stats.failed_writes);
@@ -1338,7 +1338,7 @@ static void __zram_make_request(struct zram *zram, struct bio *bio)
 			bv.bv_len = min_t(unsigned int, PAGE_SIZE - offset,
 							unwritten);
 			if (zram_bvec_rw(zram, &bv, index, offset,
-					op_is_write(bio_op(bio)), bio) < 0)
+					 bio_op(bio), bio) < 0)
 				goto out;
 
 			bv.bv_offset += bv.bv_len;
@@ -1390,7 +1390,7 @@ static void zram_slot_free_notify(struct block_device *bdev,
 }
 
 static int zram_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	int offset, ret;
 	u32 index;
@@ -1414,7 +1414,7 @@ static int zram_rw_page(struct block_device *bdev, sector_t sector,
 	bv.bv_len = PAGE_SIZE;
 	bv.bv_offset = 0;
 
-	ret = zram_bvec_rw(zram, &bv, index, offset, is_write, NULL);
+	ret = zram_bvec_rw(zram, &bv, index, offset, op, NULL);
 out:
 	/*
 	 * If I/O fails, just return error(ie, non-zero) without
@@ -1429,7 +1429,7 @@ out:
 
 	switch (ret) {
 	case 0:
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 		break;
 	case 1:
 		ret = 0;
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 85de8053aa34..0360c015f658 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1423,11 +1423,11 @@ static int btt_write_pg(struct btt *btt, struct bio_integrity_payload *bip,
 
 static int btt_do_bvec(struct btt *btt, struct bio_integrity_payload *bip,
 			struct page *page, unsigned int len, unsigned int off,
-			bool is_write, sector_t sector)
+			unsigned int op, sector_t sector)
 {
 	int ret;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		ret = btt_read_pg(btt, bip, page, off, sector, len);
 		flush_dcache_page(page);
 	} else {
@@ -1464,7 +1464,7 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 		}
 
 		err = btt_do_bvec(btt, bip, bvec.bv_page, len, bvec.bv_offset,
-				  op_is_write(bio_op(bio)), iter.bi_sector);
+				  bio_op(bio), iter.bi_sector);
 		if (err) {
 			dev_err(&btt->nd_btt->dev,
 					"io error in %s sector %lld, len %d,\n",
@@ -1483,16 +1483,16 @@ static blk_qc_t btt_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int btt_rw_page(struct block_device *bdev, sector_t sector,
-		struct page *page, bool is_write)
+		struct page *page, unsigned int op)
 {
 	struct btt *btt = bdev->bd_disk->private_data;
 	int rc;
 	unsigned int len;
 
 	len = hpage_nr_pages(page) * PAGE_SIZE;
-	rc = btt_do_bvec(btt, NULL, page, len, 0, is_write, sector);
+	rc = btt_do_bvec(btt, NULL, page, len, 0, op, sector);
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return rc;
 }
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index 8b1fd7f1a224..dd17acd8fe68 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -120,7 +120,7 @@ static blk_status_t read_pmem(struct page *page, unsigned int off,
 }
 
 static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
-			unsigned int len, unsigned int off, bool is_write,
+			unsigned int len, unsigned int off, unsigned int op,
 			sector_t sector)
 {
 	blk_status_t rc = BLK_STS_OK;
@@ -131,7 +131,7 @@ static blk_status_t pmem_do_bvec(struct pmem_device *pmem, struct page *page,
 	if (unlikely(is_bad_pmem(&pmem->bb, sector, len)))
 		bad_pmem = true;
 
-	if (!is_write) {
+	if (!op_is_write(op)) {
 		if (unlikely(bad_pmem))
 			rc = BLK_STS_IOERR;
 		else {
@@ -180,8 +180,7 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 	do_acct = nd_iostat_start(bio, &start);
 	bio_for_each_segment(bvec, bio, iter) {
 		rc = pmem_do_bvec(pmem, bvec.bv_page, bvec.bv_len,
-				bvec.bv_offset, op_is_write(bio_op(bio)),
-				iter.bi_sector);
+				bvec.bv_offset, bio_op(bio), iter.bi_sector);
 		if (rc) {
 			bio->bi_status = rc;
 			break;
@@ -198,13 +197,13 @@ static blk_qc_t pmem_make_request(struct request_queue *q, struct bio *bio)
 }
 
 static int pmem_rw_page(struct block_device *bdev, sector_t sector,
-		       struct page *page, bool is_write)
+		       struct page *page, unsigned int op)
 {
 	struct pmem_device *pmem = bdev->bd_queue->queuedata;
 	blk_status_t rc;
 
 	rc = pmem_do_bvec(pmem, page, hpage_nr_pages(page) * PAGE_SIZE,
-			  0, is_write, sector);
+			  0, op, sector);
 
 	/*
 	 * The ->rw_page interface is subtle and tricky.  The core
@@ -213,7 +212,7 @@ static int pmem_rw_page(struct block_device *bdev, sector_t sector,
 	 * caused by double completion.
 	 */
 	if (rc == 0)
-		page_endio(page, is_write, 0);
+		page_endio(page, op_is_write(op), 0);
 
 	return blk_status_to_errno(rc);
 }
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 0dd87aaeb39a..496fb51a1e1a 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -665,7 +665,8 @@ int bdev_read_page(struct block_device *bdev, sector_t sector,
 	result = blk_queue_enter(bdev->bd_queue, 0);
 	if (result)
 		return result;
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, false);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_READ);
 	blk_queue_exit(bdev->bd_queue);
 	return result;
 }
@@ -703,7 +704,8 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 		return result;
 
 	set_page_writeback(page);
-	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page, true);
+	result = ops->rw_page(bdev, sector + get_start_sect(bdev), page,
+			      REQ_OP_WRITE);
 	if (result) {
 		end_page_writeback(page);
 	} else {
diff --git a/fs/mpage.c b/fs/mpage.c
index b7e7f570733a..b73638db9866 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -51,8 +51,8 @@ static void mpage_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, op_is_write(bio_op(bio)),
-				blk_status_to_errno(bio->bi_status));
+		page_endio(page, bio_op(bio),
+			   blk_status_to_errno(bio->bi_status));
 	}
 
 	bio_put(bio);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 1939ed95f936..331a6cb8805f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1943,7 +1943,7 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 struct block_device_operations {
 	int (*open) (struct block_device *, fmode_t);
 	void (*release) (struct gendisk *, fmode_t);
-	int (*rw_page)(struct block_device *, sector_t, struct page *, bool);
+	int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int);
 	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
 	unsigned int (*check_events) (struct gendisk *disk,
-- 
cgit v1.2.3


From 59767fbd49d794b4499d30b314df6c0d4aca584b Mon Sep 17 00:00:00 2001
From: Michael Callahan <michaelcallahan@fb.com>
Date: Wed, 18 Jul 2018 04:47:37 -0700
Subject: block: Add part_stat_read_accum to read across field entries.

Add a part_stat_read_accum macro to genhd.h to read and sum across
field entries.  For example to sum up the number read and write
sectors completed.  In addition to being ar reasonable cleanup by
itself this will make it easier to add new stat fields in the future.

tj: Refreshed on top of v4.17.

Signed-off-by: Michael Callahan <michaelcallahan@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_receiver.c | 3 +--
 drivers/block/drbd/drbd_worker.c   | 4 +---
 drivers/md/md.c                    | 3 +--
 include/linux/genhd.h              | 4 ++++
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index a36a30795c43..75f6b47169e6 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -2674,8 +2674,7 @@ bool drbd_rs_c_min_rate_throttle(struct drbd_device *device)
 	if (c_min_rate == 0)
 		return false;
 
-	curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-		      (int)part_stat_read(&disk->part0, sectors[1]) -
+	curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			atomic_read(&device->rs_sect_ev);
 
 	if (atomic_read(&device->ap_actlog_cnt)
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 5e793dd7adfb..b8f77e83d456 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -1690,9 +1690,7 @@ void drbd_rs_controller_reset(struct drbd_device *device)
 	atomic_set(&device->rs_sect_in, 0);
 	atomic_set(&device->rs_sect_ev, 0);
 	device->rs_in_flight = 0;
-	device->rs_last_events =
-		(int)part_stat_read(&disk->part0, sectors[0]) +
-		(int)part_stat_read(&disk->part0, sectors[1]);
+	device->rs_last_events = (int)part_stat_read_accum(&disk->part0, sectors);
 
 	/* Updating the RCU protected object in place is necessary since
 	   this function gets called from atomic context.
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 994aed2f9dff..dabe36723d60 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -8046,8 +8046,7 @@ static int is_mddev_idle(struct mddev *mddev, int init)
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
-		curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
-			      (int)part_stat_read(&disk->part0, sectors[1]) -
+		curr_events = (int)part_stat_read_accum(&disk->part0, sectors) -
 			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 6cb8a5789668..19f36fa10995 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -353,6 +353,10 @@ static inline void free_part_stats(struct hd_struct *part)
 
 #endif /* CONFIG_SMP */
 
+#define part_stat_read_accum(part, field)				\
+	(part_stat_read(part, field[0]) +				\
+	 part_stat_read(part, field[1]))
+
 #define part_stat_add(cpu, part, field, addnd)	do {			\
 	__part_stat_add((cpu), (part), field, addnd);			\
 	if ((part)->partno)						\
-- 
cgit v1.2.3


From dbae2c551377b6533a00c11fc7ede370100ab404 Mon Sep 17 00:00:00 2001
From: Michael Callahan <michaelcallahan@fb.com>
Date: Wed, 18 Jul 2018 04:47:38 -0700
Subject: block: Define and use STAT_READ and STAT_WRITE

Add defines for STAT_READ and STAT_WRITE for indexing the partition
stat entries. This clarifies some fs/ code which has hardcoded 1 for
STAT_WRITE and will make it easier to extend the stats with additional
fields.

tj: Refreshed on top of v4.17.

Signed-off-by: Michael Callahan <michaelcallahan@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: "Theodore Ts'o" <tytso@mit.edu>
Cc: Jaegeuk Kim <jaegeuk@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/genhd.c             | 16 ++++++++--------
 block/partition-generic.c | 16 ++++++++--------
 fs/ext4/super.c           |  5 +++--
 fs/ext4/sysfs.c           |  6 ++++--
 fs/f2fs/f2fs.h            |  2 +-
 fs/f2fs/super.c           |  3 ++-
 include/linux/blk_types.h |  7 +++++++
 include/linux/genhd.h     | 13 +++++++------
 8 files changed, 40 insertions(+), 28 deletions(-)

diff --git a/block/genhd.c b/block/genhd.c
index f1543a45e73b..0711a800d0d4 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1337,14 +1337,14 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   "%u %lu %lu %lu %u %u %u %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
-			   part_stat_read(hd, ios[READ]),
-			   part_stat_read(hd, merges[READ]),
-			   part_stat_read(hd, sectors[READ]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
-			   part_stat_read(hd, ios[WRITE]),
-			   part_stat_read(hd, merges[WRITE]),
-			   part_stat_read(hd, sectors[WRITE]),
-			   jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
+			   part_stat_read(hd, ios[STAT_READ]),
+			   part_stat_read(hd, merges[STAT_READ]),
+			   part_stat_read(hd, sectors[STAT_READ]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_READ])),
+			   part_stat_read(hd, ios[STAT_WRITE]),
+			   part_stat_read(hd, merges[STAT_WRITE]),
+			   part_stat_read(hd, sectors[STAT_WRITE]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
 			   inflight[0],
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
 			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 3dcfd4ec0e11..0ddb06722162 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -132,14 +132,14 @@ ssize_t part_stat_show(struct device *dev,
 		"%8lu %8lu %8llu %8u "
 		"%8u %8u %8u"
 		"\n",
-		part_stat_read(p, ios[READ]),
-		part_stat_read(p, merges[READ]),
-		(unsigned long long)part_stat_read(p, sectors[READ]),
-		jiffies_to_msecs(part_stat_read(p, ticks[READ])),
-		part_stat_read(p, ios[WRITE]),
-		part_stat_read(p, merges[WRITE]),
-		(unsigned long long)part_stat_read(p, sectors[WRITE]),
-		jiffies_to_msecs(part_stat_read(p, ticks[WRITE])),
+		part_stat_read(p, ios[STAT_READ]),
+		part_stat_read(p, merges[STAT_READ]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_READ]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_READ])),
+		part_stat_read(p, ios[STAT_WRITE]),
+		part_stat_read(p, merges[STAT_WRITE]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_WRITE]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
 		inflight[0],
 		jiffies_to_msecs(part_stat_read(p, io_ticks)),
 		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index ba2396a7bd04..4b8aef989552 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -3514,7 +3514,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_sb_block = sb_block;
 	if (sb->s_bdev->bd_part)
 		sbi->s_sectors_written_start =
-			part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+			part_stat_read(sb->s_bdev->bd_part, sectors[STAT_WRITE]);
 
 	/* Cleanup superblock name */
 	strreplace(sb->s_id, '/', '!');
@@ -4824,7 +4824,8 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	if (sb->s_bdev->bd_part)
 		es->s_kbytes_written =
 			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
-			    ((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			    ((part_stat_read(sb->s_bdev->bd_part,
+					     sectors[STAT_WRITE]) -
 			      EXT4_SB(sb)->s_sectors_written_start) >> 1));
 	else
 		es->s_kbytes_written =
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index f34da0bb8f17..2be9ad790017 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -56,7 +56,8 @@ static ssize_t session_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 	if (!sb->s_bdev->bd_part)
 		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%lu\n",
-			(part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			(part_stat_read(sb->s_bdev->bd_part,
+					sectors[STAT_WRITE]) -
 			 sbi->s_sectors_written_start) >> 1);
 }
 
@@ -68,7 +69,8 @@ static ssize_t lifetime_write_kbytes_show(struct ext4_sb_info *sbi, char *buf)
 		return snprintf(buf, PAGE_SIZE, "0\n");
 	return snprintf(buf, PAGE_SIZE, "%llu\n",
 			(unsigned long long)(sbi->s_kbytes_written +
-			((part_stat_read(sb->s_bdev->bd_part, sectors[1]) -
+			((part_stat_read(sb->s_bdev->bd_part,
+					 sectors[STAT_WRITE]) -
 			  EXT4_SB(sb)->s_sectors_written_start) >> 1)));
 }
 
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 4d8b1de83143..6799c3fc44e3 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1304,7 +1304,7 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
  * and the return value is in kbytes. s is of struct f2fs_sb_info.
  */
 #define BD_PART_WRITTEN(s)						 \
-(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[1]) -		 \
+(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[STAT_WRITE]) -   \
 		(s)->sectors_written_start) >> 1)
 
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 3995e926ba3a..17bcff789c08 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -2882,7 +2882,8 @@ try_onemore:
 	/* For write statistics */
 	if (sb->s_bdev->bd_part)
 		sbi->sectors_written_start =
-			(u64)part_stat_read(sb->s_bdev->bd_part, sectors[1]);
+			(u64)part_stat_read(sb->s_bdev->bd_part,
+					    sectors[STAT_WRITE]);
 
 	/* Read accumulated write IO statistics if exists */
 	seg_i = CURSEG_I(sbi, CURSEG_HOT_NODE);
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index e13449a379a1..d2b44de56bc1 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -357,6 +357,13 @@ enum req_flag_bits {
 #define REQ_NOMERGE_FLAGS \
 	(REQ_NOMERGE | REQ_PREFLUSH | REQ_FUA)
 
+enum stat_group {
+	STAT_READ,
+	STAT_WRITE,
+
+	NR_STAT_GROUPS
+};
+
 #define bio_op(bio) \
 	((bio)->bi_opf & REQ_OP_MASK)
 #define req_op(req) \
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 19f36fa10995..a75445446974 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/percpu-refcount.h>
 #include <linux/uuid.h>
+#include <linux/blk_types.h>
 
 #ifdef CONFIG_BLOCK
 
@@ -82,10 +83,10 @@ struct partition {
 } __attribute__((packed));
 
 struct disk_stats {
-	unsigned long sectors[2];	/* READs and WRITEs */
-	unsigned long ios[2];
-	unsigned long merges[2];
-	unsigned long ticks[2];
+	unsigned long sectors[NR_STAT_GROUPS];
+	unsigned long ios[NR_STAT_GROUPS];
+	unsigned long merges[NR_STAT_GROUPS];
+	unsigned long ticks[NR_STAT_GROUPS];
 	unsigned long io_ticks;
 	unsigned long time_in_queue;
 };
@@ -354,8 +355,8 @@ static inline void free_part_stats(struct hd_struct *part)
 #endif /* CONFIG_SMP */
 
 #define part_stat_read_accum(part, field)				\
-	(part_stat_read(part, field[0]) +				\
-	 part_stat_read(part, field[1]))
+	(part_stat_read(part, field[STAT_READ]) +			\
+	 part_stat_read(part, field[STAT_WRITE]))
 
 #define part_stat_add(cpu, part, field, addnd)	do {			\
 	__part_stat_add((cpu), (part), field, addnd);			\
-- 
cgit v1.2.3


From ddcf35d397976421a4ec1d0d00fbcc027a8cb034 Mon Sep 17 00:00:00 2001
From: Michael Callahan <michaelcallahan@fb.com>
Date: Wed, 18 Jul 2018 04:47:39 -0700
Subject: block: Add and use op_stat_group() for indexing disk_stat fields.

Add and use a new op_stat_group() function for indexing partition stat
fields rather than indexing them by rq_data_dir() or bio_data_dir().
This function works similarly to op_is_sync() in that it takes the
request::cmd_flags or bio::bi_opf flags and determines which stats
should et updated.

In addition, the second parameter to generic_start_io_acct() and
generic_end_io_acct() is now a REQ_OP rather than simply a read or
write bit and it uses op_stat_group() on the parameter to determine
the stat group.

Note that the partition in_flight counts are not part of the per-cpu
statistics and as such are not indexed via this function.  It's now
indexed by op_is_write().

tj: Refreshed on top of v4.17.  Updated to pass around REQ_OP.

Signed-off-by: Michael Callahan <michaelcallahan@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Joshua Morris <josh.h.morris@us.ibm.com>
Cc: Philipp Reisner <philipp.reisner@linbit.com>
Cc: Matias Bjorling <mb@lightnvm.io>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Cc: Alasdair Kergon <agk@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c                   | 16 +++++++++-------
 block/blk-core.c              | 12 ++++++------
 drivers/block/drbd/drbd_req.c |  4 ++--
 drivers/block/rsxx/dev.c      |  6 +++---
 drivers/block/zram/zram_drv.c |  5 ++---
 drivers/lightnvm/pblk-cache.c |  5 +++--
 drivers/lightnvm/pblk-read.c  |  5 +++--
 drivers/md/bcache/request.c   | 13 +++++--------
 drivers/md/dm.c               |  6 ++++--
 drivers/md/md.c               |  5 +++--
 drivers/nvdimm/nd.h           |  7 +++----
 include/linux/bio.h           |  4 ++--
 include/linux/blk_types.h     |  5 +++++
 13 files changed, 50 insertions(+), 43 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index f3536bfc8298..8ecc95615941 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1728,29 +1728,31 @@ void bio_check_pages_dirty(struct bio *bio)
 }
 EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 			   unsigned long sectors, struct hd_struct *part)
 {
+	const int sgrp = op_stat_group(op);
 	int cpu = part_stat_lock();
 
 	part_round_stats(q, cpu, part);
-	part_stat_inc(cpu, part, ios[rw]);
-	part_stat_add(cpu, part, sectors[rw], sectors);
-	part_inc_in_flight(q, part, rw);
+	part_stat_inc(cpu, part, ios[sgrp]);
+	part_stat_add(cpu, part, sectors[sgrp], sectors);
+	part_inc_in_flight(q, part, op_is_write(op));
 
 	part_stat_unlock();
 }
 EXPORT_SYMBOL(generic_start_io_acct);
 
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int req_op,
 			 struct hd_struct *part, unsigned long start_time)
 {
 	unsigned long duration = jiffies - start_time;
+	const int sgrp = op_stat_group(req_op);
 	int cpu = part_stat_lock();
 
-	part_stat_add(cpu, part, ticks[rw], duration);
+	part_stat_add(cpu, part, ticks[sgrp], duration);
 	part_round_stats(q, cpu, part);
-	part_dec_in_flight(q, part, rw);
+	part_dec_in_flight(q, part, op_is_write(req_op));
 
 	part_stat_unlock();
 }
diff --git a/block/blk-core.c b/block/blk-core.c
index c4b57d8806fe..03a4ea93a5f3 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -2702,13 +2702,13 @@ EXPORT_SYMBOL_GPL(blk_rq_err_bytes);
 void blk_account_io_completion(struct request *req, unsigned int bytes)
 {
 	if (blk_do_io_stat(req)) {
-		const int rw = rq_data_dir(req);
+		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 		int cpu;
 
 		cpu = part_stat_lock();
 		part = req->part;
-		part_stat_add(cpu, part, sectors[rw], bytes >> 9);
+		part_stat_add(cpu, part, sectors[sgrp], bytes >> 9);
 		part_stat_unlock();
 	}
 }
@@ -2722,7 +2722,7 @@ void blk_account_io_done(struct request *req, u64 now)
 	 */
 	if (blk_do_io_stat(req) && !(req->rq_flags & RQF_FLUSH_SEQ)) {
 		unsigned long duration;
-		const int rw = rq_data_dir(req);
+		const int sgrp = op_stat_group(req_op(req));
 		struct hd_struct *part;
 		int cpu;
 
@@ -2730,10 +2730,10 @@ void blk_account_io_done(struct request *req, u64 now)
 		cpu = part_stat_lock();
 		part = req->part;
 
-		part_stat_inc(cpu, part, ios[rw]);
-		part_stat_add(cpu, part, ticks[rw], duration);
+		part_stat_inc(cpu, part, ios[sgrp]);
+		part_stat_add(cpu, part, ticks[sgrp], duration);
 		part_round_stats(req->q, cpu, part);
-		part_dec_in_flight(req->q, part, rw);
+		part_dec_in_flight(req->q, part, rq_data_dir(req));
 
 		hd_struct_put(part);
 		part_stat_unlock();
diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c
index d146fedc38bb..19cac36e9737 100644
--- a/drivers/block/drbd/drbd_req.c
+++ b/drivers/block/drbd/drbd_req.c
@@ -38,7 +38,7 @@ static void _drbd_start_io_acct(struct drbd_device *device, struct drbd_request
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_start_io_acct(q, bio_data_dir(req->master_bio),
+	generic_start_io_acct(q, bio_op(req->master_bio),
 				req->i.size >> 9, &device->vdisk->part0);
 }
 
@@ -47,7 +47,7 @@ static void _drbd_end_io_acct(struct drbd_device *device, struct drbd_request *r
 {
 	struct request_queue *q = device->rq_queue;
 
-	generic_end_io_acct(q, bio_data_dir(req->master_bio),
+	generic_end_io_acct(q, bio_op(req->master_bio),
 			    &device->vdisk->part0, req->start_jif);
 }
 
diff --git a/drivers/block/rsxx/dev.c b/drivers/block/rsxx/dev.c
index dddb3f2490b6..1a92f9e65937 100644
--- a/drivers/block/rsxx/dev.c
+++ b/drivers/block/rsxx/dev.c
@@ -112,7 +112,7 @@ static const struct block_device_operations rsxx_fops = {
 
 static void disk_stats_start(struct rsxx_cardinfo *card, struct bio *bio)
 {
-	generic_start_io_acct(card->queue, bio_data_dir(bio), bio_sectors(bio),
+	generic_start_io_acct(card->queue, bio_op(bio), bio_sectors(bio),
 			     &card->gendisk->part0);
 }
 
@@ -120,8 +120,8 @@ static void disk_stats_complete(struct rsxx_cardinfo *card,
 				struct bio *bio,
 				unsigned long start_time)
 {
-	generic_end_io_acct(card->queue, bio_data_dir(bio),
-				&card->gendisk->part0, start_time);
+	generic_end_io_acct(card->queue, bio_op(bio),
+			    &card->gendisk->part0, start_time);
 }
 
 static void bio_dma_done_cb(struct rsxx_cardinfo *card,
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index 78c29044684a..2907a8156aaf 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -1277,11 +1277,10 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 			int offset, unsigned int op, struct bio *bio)
 {
 	unsigned long start_time = jiffies;
-	int rw_acct = op_is_write(op) ? REQ_OP_WRITE : REQ_OP_READ;
 	struct request_queue *q = zram->disk->queue;
 	int ret;
 
-	generic_start_io_acct(q, rw_acct, bvec->bv_len >> SECTOR_SHIFT,
+	generic_start_io_acct(q, op, bvec->bv_len >> SECTOR_SHIFT,
 			&zram->disk->part0);
 
 	if (!op_is_write(op)) {
@@ -1293,7 +1292,7 @@ static int zram_bvec_rw(struct zram *zram, struct bio_vec *bvec, u32 index,
 		ret = zram_bvec_write(zram, bvec, index, offset, bio);
 	}
 
-	generic_end_io_acct(q, rw_acct, &zram->disk->part0, start_time);
+	generic_end_io_acct(q, op, &zram->disk->part0, start_time);
 
 	zram_slot_lock(zram, index);
 	zram_accessed(zram, index);
diff --git a/drivers/lightnvm/pblk-cache.c b/drivers/lightnvm/pblk-cache.c
index 77d811962818..f565a56b898a 100644
--- a/drivers/lightnvm/pblk-cache.c
+++ b/drivers/lightnvm/pblk-cache.c
@@ -27,7 +27,8 @@ int pblk_write_to_cache(struct pblk *pblk, struct bio *bio, unsigned long flags)
 	int nr_entries = pblk_get_secs(bio);
 	int i, ret;
 
-	generic_start_io_acct(q, WRITE, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_WRITE, bio_sectors(bio),
+			      &pblk->disk->part0);
 
 	/* Update the write buffer head (mem) with the entries that we can
 	 * write. The write in itself cannot fail, so there is no need to
@@ -75,7 +76,7 @@ retry:
 	pblk_rl_inserted(&pblk->rl, nr_entries);
 
 out:
-	generic_end_io_acct(q, WRITE, &pblk->disk->part0, start_time);
+	generic_end_io_acct(q, REQ_OP_WRITE, &pblk->disk->part0, start_time);
 	pblk_write_should_kick(pblk);
 	return ret;
 }
diff --git a/drivers/lightnvm/pblk-read.c b/drivers/lightnvm/pblk-read.c
index 26d414ae25b6..5a46d7f9302f 100644
--- a/drivers/lightnvm/pblk-read.c
+++ b/drivers/lightnvm/pblk-read.c
@@ -199,7 +199,7 @@ static void __pblk_end_io_read(struct pblk *pblk, struct nvm_rq *rqd,
 	struct bio *int_bio = rqd->bio;
 	unsigned long start_time = r_ctx->start_time;
 
-	generic_end_io_acct(dev->q, READ, &pblk->disk->part0, start_time);
+	generic_end_io_acct(dev->q, REQ_OP_READ, &pblk->disk->part0, start_time);
 
 	if (rqd->error)
 		pblk_log_read_err(pblk, rqd);
@@ -461,7 +461,8 @@ int pblk_submit_read(struct pblk *pblk, struct bio *bio)
 		return NVM_IO_ERR;
 	}
 
-	generic_start_io_acct(q, READ, bio_sectors(bio), &pblk->disk->part0);
+	generic_start_io_acct(q, REQ_OP_READ, bio_sectors(bio),
+			      &pblk->disk->part0);
 
 	bitmap_zero(read_bitmap, nr_secs);
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index ae67f5fa8047..97707b0c54ce 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -667,8 +667,7 @@ static void backing_request_endio(struct bio *bio)
 static void bio_complete(struct search *s)
 {
 	if (s->orig_bio) {
-		generic_end_io_acct(s->d->disk->queue,
-				    bio_data_dir(s->orig_bio),
+		generic_end_io_acct(s->d->disk->queue, bio_op(s->orig_bio),
 				    &s->d->disk->part0, s->start_time);
 
 		trace_bcache_request_end(s->d, s->orig_bio);
@@ -1062,8 +1061,7 @@ static void detached_dev_end_io(struct bio *bio)
 	bio->bi_end_io = ddip->bi_end_io;
 	bio->bi_private = ddip->bi_private;
 
-	generic_end_io_acct(ddip->d->disk->queue,
-			    bio_data_dir(bio),
+	generic_end_io_acct(ddip->d->disk->queue, bio_op(bio),
 			    &ddip->d->disk->part0, ddip->start_time);
 
 	if (bio->bi_status) {
@@ -1120,7 +1118,7 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 	}
 
 	atomic_set(&dc->backing_idle, 0);
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
 
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
@@ -1229,7 +1227,6 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 	struct search *s;
 	struct closure *cl;
 	struct bcache_device *d = bio->bi_disk->private_data;
-	int rw = bio_data_dir(bio);
 
 	if (unlikely(d->c && test_bit(CACHE_SET_IO_DISABLE, &d->c->flags))) {
 		bio->bi_status = BLK_STS_IOERR;
@@ -1237,7 +1234,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	generic_start_io_acct(q, rw, bio_sectors(bio), &d->disk->part0);
+	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
 
 	s = search_alloc(bio, d);
 	cl = &s->cl;
@@ -1254,7 +1251,7 @@ static blk_qc_t flash_dev_make_request(struct request_queue *q,
 				      flash_dev_nodata,
 				      bcache_wq);
 		return BLK_QC_T_NONE;
-	} else if (rw) {
+	} else if (bio_data_dir(bio)) {
 		bch_keybuf_check_overlapping(&s->iop.c->moving_gc_keys,
 					&KEY(d->id, bio->bi_iter.bi_sector, 0),
 					&KEY(d->id, bio_end_sector(bio), 0));
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index b0dd7027848b..20f7e4ef5342 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -609,7 +609,8 @@ static void start_io_acct(struct dm_io *io)
 
 	io->start_time = jiffies;
 
-	generic_start_io_acct(md->queue, rw, bio_sectors(bio), &dm_disk(md)->part0);
+	generic_start_io_acct(md->queue, bio_op(bio), bio_sectors(bio),
+			      &dm_disk(md)->part0);
 
 	atomic_set(&dm_disk(md)->part0.in_flight[rw],
 		   atomic_inc_return(&md->pending[rw]));
@@ -628,7 +629,8 @@ static void end_io_acct(struct dm_io *io)
 	int pending;
 	int rw = bio_data_dir(bio);
 
-	generic_end_io_acct(md->queue, rw, &dm_disk(md)->part0, io->start_time);
+	generic_end_io_acct(md->queue, bio_op(bio), &dm_disk(md)->part0,
+			    io->start_time);
 
 	if (unlikely(dm_stats_used(&md->stats)))
 		dm_stats_account_io(&md->stats, bio_data_dir(bio),
diff --git a/drivers/md/md.c b/drivers/md/md.c
index dabe36723d60..f6e58dbca0d4 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -335,6 +335,7 @@ EXPORT_SYMBOL(md_handle_request);
 static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 {
 	const int rw = bio_data_dir(bio);
+	const int sgrp = op_stat_group(bio_op(bio));
 	struct mddev *mddev = q->queuedata;
 	unsigned int sectors;
 	int cpu;
@@ -363,8 +364,8 @@ static blk_qc_t md_make_request(struct request_queue *q, struct bio *bio)
 	md_handle_request(mddev, bio);
 
 	cpu = part_stat_lock();
-	part_stat_inc(cpu, &mddev->gendisk->part0, ios[rw]);
-	part_stat_add(cpu, &mddev->gendisk->part0, sectors[rw], sectors);
+	part_stat_inc(cpu, &mddev->gendisk->part0, ios[sgrp]);
+	part_stat_add(cpu, &mddev->gendisk->part0, sectors[sgrp], sectors);
 	part_stat_unlock();
 
 	return BLK_QC_T_NONE;
diff --git a/drivers/nvdimm/nd.h b/drivers/nvdimm/nd.h
index 32e0364b48b9..6ee7fd7e4bbd 100644
--- a/drivers/nvdimm/nd.h
+++ b/drivers/nvdimm/nd.h
@@ -396,16 +396,15 @@ static inline bool nd_iostat_start(struct bio *bio, unsigned long *start)
 		return false;
 
 	*start = jiffies;
-	generic_start_io_acct(disk->queue, bio_data_dir(bio),
-			      bio_sectors(bio), &disk->part0);
+	generic_start_io_acct(disk->queue, bio_op(bio), bio_sectors(bio),
+			      &disk->part0);
 	return true;
 }
 static inline void nd_iostat_end(struct bio *bio, unsigned long start)
 {
 	struct gendisk *disk = bio->bi_disk;
 
-	generic_end_io_acct(disk->queue, bio_data_dir(bio), &disk->part0,
-				start);
+	generic_end_io_acct(disk->queue, bio_op(bio), &disk->part0, start);
 }
 static inline bool is_bad_pmem(struct badblocks *bb, sector_t sector,
 		unsigned int len)
diff --git a/include/linux/bio.h b/include/linux/bio.h
index a00dfff51aa5..ab221c517f4e 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -496,9 +496,9 @@ extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int,
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
 
-void generic_start_io_acct(struct request_queue *q, int rw,
+void generic_start_io_acct(struct request_queue *q, int op,
 				unsigned long sectors, struct hd_struct *part);
-void generic_end_io_acct(struct request_queue *q, int rw,
+void generic_end_io_acct(struct request_queue *q, int op,
 				struct hd_struct *part,
 				unsigned long start_time);
 
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index d2b44de56bc1..2960a96d833c 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -401,6 +401,11 @@ static inline bool op_is_sync(unsigned int op)
 		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
 }
 
+static inline int op_stat_group(unsigned int op)
+{
+	return op_is_write(op);
+}
+
 typedef unsigned int blk_qc_t;
 #define BLK_QC_T_NONE		-1U
 #define BLK_QC_T_SHIFT		16
-- 
cgit v1.2.3


From bdca3c87fb7ad1cc61d231d37eb0d8f90d001e0c Mon Sep 17 00:00:00 2001
From: Michael Callahan <michaelcallahan@fb.com>
Date: Wed, 18 Jul 2018 04:47:40 -0700
Subject: block: Track DISCARD statistics and output them in stat and diskstat

Add tracking of REQ_OP_DISCARD ios to the partition statistics and
append them to the various stat files in /sys as well as
/proc/diskstats.  These are tracked with the same four stats as reads
and writes:

Number of discard ios completed.
Number of discard ios merged
Number of discard sectors completed
Milliseconds spent on discard requests

This is done via adding a new STAT_DISCARD define to genhd.h and then
using it to index that stat field for discard requests.

tj: Refreshed on top of v4.17 and other previous updates.

Signed-off-by: Michael Callahan <michaelcallahan@fb.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Andy Newell <newella@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/ABI/testing/procfs-diskstats | 10 ++++++++++
 Documentation/block/stat.txt               | 28 ++++++++++++++++------------
 Documentation/iostats.txt                  | 15 +++++++++++++++
 block/genhd.c                              | 13 ++++++++++---
 block/partition-generic.c                  |  9 +++++++--
 include/linux/blk_types.h                  |  8 ++++++++
 include/linux/genhd.h                      |  3 ++-
 7 files changed, 68 insertions(+), 18 deletions(-)

diff --git a/Documentation/ABI/testing/procfs-diskstats b/Documentation/ABI/testing/procfs-diskstats
index f91a973a37fe..abac31d216de 100644
--- a/Documentation/ABI/testing/procfs-diskstats
+++ b/Documentation/ABI/testing/procfs-diskstats
@@ -5,6 +5,7 @@ Description:
 		The /proc/diskstats file displays the I/O statistics
 		of block devices. Each line contains the following 14
 		fields:
+
 		 1 - major number
 		 2 - minor mumber
 		 3 - device name
@@ -19,4 +20,13 @@ Description:
 		12 - I/Os currently in progress
 		13 - time spent doing I/Os (ms)
 		14 - weighted time spent doing I/Os (ms)
+
+		Kernel 4.18+ appends four more fields for discard
+		tracking putting the total at 18:
+
+		15 - discards completed successfully
+		16 - discards merged
+		17 - sectors discarded
+		18 - time spent discarding
+
 		For more details refer to Documentation/iostats.txt
diff --git a/Documentation/block/stat.txt b/Documentation/block/stat.txt
index 0dbc946de2ea..0aace9cc536c 100644
--- a/Documentation/block/stat.txt
+++ b/Documentation/block/stat.txt
@@ -31,28 +31,32 @@ write ticks     milliseconds  total wait time for write requests
 in_flight       requests      number of I/Os currently in flight
 io_ticks        milliseconds  total time this block device has been active
 time_in_queue   milliseconds  total wait time for all requests
+discard I/Os    requests      number of discard I/Os processed
+discard merges  requests      number of discard I/Os merged with in-queue I/O
+discard sectors sectors       number of sectors discarded
+discard ticks   milliseconds  total wait time for discard requests
 
-read I/Os, write I/Os
-=====================
+read I/Os, write I/Os, discard I/0s
+===================================
 
 These values increment when an I/O request completes.
 
-read merges, write merges
-=========================
+read merges, write merges, discard merges
+=========================================
 
 These values increment when an I/O request is merged with an
 already-queued I/O request.
 
-read sectors, write sectors
-===========================
+read sectors, write sectors, discard_sectors
+============================================
 
-These values count the number of sectors read from or written to this
-block device.  The "sectors" in question are the standard UNIX 512-byte
-sectors, not any device- or filesystem-specific block size.  The
-counters are incremented when the I/O completes.
+These values count the number of sectors read from, written to, or
+discarded from this block device.  The "sectors" in question are the
+standard UNIX 512-byte sectors, not any device- or filesystem-specific
+block size.  The counters are incremented when the I/O completes.
 
-read ticks, write ticks
-=======================
+read ticks, write ticks, discard ticks
+======================================
 
 These values count the number of milliseconds that I/O requests have
 waited on this block device.  If there are multiple I/O requests waiting,
diff --git a/Documentation/iostats.txt b/Documentation/iostats.txt
index 04d394a2e06c..49df45f90e8a 100644
--- a/Documentation/iostats.txt
+++ b/Documentation/iostats.txt
@@ -31,6 +31,9 @@ Here are examples of these different formats::
       3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160
       3    1   hda1 35486 38030 38030 38030
 
+   4.18+ diskstats:
+      3    0   hda 446216 784926 9550688 4382310 424847 312726 5922052 19310380 0 3376340 23705160 0 0 0 0
+
 On 2.4 you might execute ``grep 'hda ' /proc/partitions``. On 2.6+, you have
 a choice of ``cat /sys/block/hda/stat`` or ``grep 'hda ' /proc/diskstats``.
 
@@ -101,6 +104,18 @@ Field 11 -- weighted # of milliseconds spent doing I/Os
     last update of this field.  This can provide an easy measure of both
     I/O completion time and the backlog that may be accumulating.
 
+Field 12 -- # of discards completed
+    This is the total number of discards completed successfully.
+
+Field 13 -- # of discards merged
+    See the description of field 2
+
+Field 14 -- # of sectors discarded
+    This is the total number of sectors discarded successfully.
+
+Field 15 -- # of milliseconds spent discarding
+    This is the total number of milliseconds spent by all discards (as
+    measured from __make_request() to end_that_request_last()).
 
 To avoid introducing performance bottlenecks, no locks are held while
 modifying these counters.  This implies that minor inaccuracies may be
diff --git a/block/genhd.c b/block/genhd.c
index 0711a800d0d4..8cc719a37b32 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -1333,8 +1333,11 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 		part_round_stats(gp->queue, cpu, hd);
 		part_stat_unlock();
 		part_in_flight(gp->queue, hd, inflight);
-		seq_printf(seqf, "%4d %7d %s %lu %lu %lu "
-			   "%u %lu %lu %lu %u %u %u %u\n",
+		seq_printf(seqf, "%4d %7d %s "
+			   "%lu %lu %lu %u "
+			   "%lu %lu %lu %u "
+			   "%u %u %u "
+			   "%lu %lu %lu %u\n",
 			   MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
 			   disk_name(gp, hd->partno, buf),
 			   part_stat_read(hd, ios[STAT_READ]),
@@ -1347,7 +1350,11 @@ static int diskstats_show(struct seq_file *seqf, void *v)
 			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_WRITE])),
 			   inflight[0],
 			   jiffies_to_msecs(part_stat_read(hd, io_ticks)),
-			   jiffies_to_msecs(part_stat_read(hd, time_in_queue))
+			   jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
+			   part_stat_read(hd, ios[STAT_DISCARD]),
+			   part_stat_read(hd, merges[STAT_DISCARD]),
+			   part_stat_read(hd, sectors[STAT_DISCARD]),
+			   jiffies_to_msecs(part_stat_read(hd, ticks[STAT_DISCARD]))
 			);
 	}
 	disk_part_iter_exit(&piter);
diff --git a/block/partition-generic.c b/block/partition-generic.c
index 0ddb06722162..5a8975a1201c 100644
--- a/block/partition-generic.c
+++ b/block/partition-generic.c
@@ -130,7 +130,8 @@ ssize_t part_stat_show(struct device *dev,
 	return sprintf(buf,
 		"%8lu %8lu %8llu %8u "
 		"%8lu %8lu %8llu %8u "
-		"%8u %8u %8u"
+		"%8u %8u %8u "
+		"%8lu %8lu %8llu %8u"
 		"\n",
 		part_stat_read(p, ios[STAT_READ]),
 		part_stat_read(p, merges[STAT_READ]),
@@ -142,7 +143,11 @@ ssize_t part_stat_show(struct device *dev,
 		jiffies_to_msecs(part_stat_read(p, ticks[STAT_WRITE])),
 		inflight[0],
 		jiffies_to_msecs(part_stat_read(p, io_ticks)),
-		jiffies_to_msecs(part_stat_read(p, time_in_queue)));
+		jiffies_to_msecs(part_stat_read(p, time_in_queue)),
+		part_stat_read(p, ios[STAT_DISCARD]),
+		part_stat_read(p, merges[STAT_DISCARD]),
+		(unsigned long long)part_stat_read(p, sectors[STAT_DISCARD]),
+		jiffies_to_msecs(part_stat_read(p, ticks[STAT_DISCARD])));
 }
 
 ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 2960a96d833c..f6dfb30737d8 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -360,6 +360,7 @@ enum req_flag_bits {
 enum stat_group {
 	STAT_READ,
 	STAT_WRITE,
+	STAT_DISCARD,
 
 	NR_STAT_GROUPS
 };
@@ -401,8 +402,15 @@ static inline bool op_is_sync(unsigned int op)
 		(op & (REQ_SYNC | REQ_FUA | REQ_PREFLUSH));
 }
 
+static inline bool op_is_discard(unsigned int op)
+{
+	return (op & REQ_OP_MASK) == REQ_OP_DISCARD;
+}
+
 static inline int op_stat_group(unsigned int op)
 {
+	if (op_is_discard(op))
+		return STAT_DISCARD;
 	return op_is_write(op);
 }
 
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index a75445446974..57864422a2c8 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -356,7 +356,8 @@ static inline void free_part_stats(struct hd_struct *part)
 
 #define part_stat_read_accum(part, field)				\
 	(part_stat_read(part, field[STAT_READ]) +			\
-	 part_stat_read(part, field[STAT_WRITE]))
+	 part_stat_read(part, field[STAT_WRITE]) +			\
+	 part_stat_read(part, field[STAT_DISCARD]))
 
 #define part_stat_add(cpu, part, field, addnd)	do {			\
 	__part_stat_add((cpu), (part), field, addnd);			\
-- 
cgit v1.2.3


From 636620b66d5d4012c4a9c86206013964d3986c4f Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Wed, 18 Jul 2018 04:47:41 -0700
Subject: blkcg: Track DISCARD statistics and output them in cgroup io.stat

Add tracking of REQ_OP_DISCARD ios to the per-cgroup io.stat.  Two
fields, dbytes and dios, to respectively count the total bytes and
number of discards are added.

Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Andy Newell <newella@fb.com>
Cc: Michael Callahan <michaelcallahan@fb.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/admin-guide/cgroup-v2.rst | 10 ++++++----
 block/blk-cgroup.c                      | 13 +++++++++----
 include/linux/blk-cgroup.h              |  5 ++++-
 3 files changed, 19 insertions(+), 9 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 569ce27b85e5..3afe10fa82bc 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1317,17 +1317,19 @@ IO Interface Files
 	Lines are keyed by $MAJ:$MIN device numbers and not ordered.
 	The following nested keys are defined.
 
-	  ======	===================
+	  ======	=====================
 	  rbytes	Bytes read
 	  wbytes	Bytes written
 	  rios		Number of read IOs
 	  wios		Number of write IOs
-	  ======	===================
+	  dbytes	Bytes discarded
+	  dios		Number of discard IOs
+	  ======	=====================
 
 	An example read output follows:
 
-	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353
-	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252
+	  8:16 rbytes=1459200 wbytes=314773504 rios=192 wios=353 dbytes=0 dios=0
+	  8:0 rbytes=90430464 wbytes=299008000 rios=8950 wios=1252 dbytes=50331648 dios=3021
 
   io.weight
 	A read-write flat-keyed file which exists on non-root cgroups.
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 7e2c19ce1a08..1942357d7165 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -567,6 +567,7 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
 		[BLKG_RWSTAT_WRITE]	= "Write",
 		[BLKG_RWSTAT_SYNC]	= "Sync",
 		[BLKG_RWSTAT_ASYNC]	= "Async",
+		[BLKG_RWSTAT_DISCARD]	= "Discard",
 	};
 	const char *dname = blkg_dev_name(pd->blkg);
 	u64 v;
@@ -580,7 +581,8 @@ u64 __blkg_prfill_rwstat(struct seq_file *sf, struct blkg_policy_data *pd,
 			   (unsigned long long)atomic64_read(&rwstat->aux_cnt[i]));
 
 	v = atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_READ]) +
-		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]);
+		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_WRITE]) +
+		atomic64_read(&rwstat->aux_cnt[BLKG_RWSTAT_DISCARD]);
 	seq_printf(sf, "%s Total %llu\n", dname, (unsigned long long)v);
 	return v;
 }
@@ -959,7 +961,7 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 		const char *dname;
 		char *buf;
 		struct blkg_rwstat rwstat;
-		u64 rbytes, wbytes, rios, wios;
+		u64 rbytes, wbytes, rios, wios, dbytes, dios;
 		size_t size = seq_get_buf(sf, &buf), off = 0;
 		int i;
 		bool has_stats = false;
@@ -982,19 +984,22 @@ static int blkcg_print_stat(struct seq_file *sf, void *v)
 					offsetof(struct blkcg_gq, stat_bytes));
 		rbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
 		wbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+		dbytes = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);
 
 		rwstat = blkg_rwstat_recursive_sum(blkg, NULL,
 					offsetof(struct blkcg_gq, stat_ios));
 		rios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_READ]);
 		wios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_WRITE]);
+		dios = atomic64_read(&rwstat.aux_cnt[BLKG_RWSTAT_DISCARD]);
 
 		spin_unlock_irq(blkg->q->queue_lock);
 
 		if (rbytes || wbytes || rios || wios) {
 			has_stats = true;
 			off += scnprintf(buf+off, size-off,
-					 "rbytes=%llu wbytes=%llu rios=%llu wios=%llu",
-					 rbytes, wbytes, rios, wios);
+					 "rbytes=%llu wbytes=%llu rios=%llu wios=%llu dbytes=%llu dios=%llu",
+					 rbytes, wbytes, rios, wios,
+					 dbytes, dios);
 		}
 
 		if (!blkcg_debug_stats)
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index de57de4831d5..3bed5e02a873 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -35,6 +35,7 @@ enum blkg_rwstat_type {
 	BLKG_RWSTAT_WRITE,
 	BLKG_RWSTAT_SYNC,
 	BLKG_RWSTAT_ASYNC,
+	BLKG_RWSTAT_DISCARD,
 
 	BLKG_RWSTAT_NR,
 	BLKG_RWSTAT_TOTAL = BLKG_RWSTAT_NR,
@@ -649,7 +650,9 @@ static inline void blkg_rwstat_add(struct blkg_rwstat *rwstat,
 {
 	struct percpu_counter *cnt;
 
-	if (op_is_write(op))
+	if (op_is_discard(op))
+		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_DISCARD];
+	else if (op_is_write(op))
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_WRITE];
 	else
 		cnt = &rwstat->cpu_cnt[BLKG_RWSTAT_READ];
-- 
cgit v1.2.3


From bcf7eac3d97f49d8400ba52c71bee5934bf20093 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Tue, 17 Jul 2018 00:47:48 +0900
Subject: regmap: add SCCB support

This adds Serial Camera Control Bus (SCCB) support for regmap API that
is intended to be used by some of Omnivision sensor drivers.

The ov772x and ov9650 drivers are going to use this SCCB regmap API.

The ov772x driver was previously only worked with the i2c controller
drivers that support I2C_FUNC_PROTOCOL_MANGLING, because the ov772x
device doesn't support repeated starts.  After commit 0b964d183cbf
("media: ov772x: allow i2c controllers without
I2C_FUNC_PROTOCOL_MANGLING"), reading ov772x register is replaced with
issuing two separated i2c messages in order to avoid repeated start.
Using this SCCB regmap hides the implementation detail.

The ov9650 driver also issues two separated i2c messages to read the
registers as the device doesn't support repeated start.  So it can
make use of this SCCB regmap.

Cc: Mark Brown <broonie@kernel.org>
Cc: Peter Rosin <peda@axentia.se>
Cc: Sebastian Reichel <sebastian.reichel@collabora.co.uk>
Cc: Wolfram Sang <wsa@the-dreams.de>
Cc: Sylwester Nawrocki <s.nawrocki@samsung.com>
Cc: Jacopo Mondi <jacopo+renesas@jmondi.org>
Cc: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Cc: Hans Verkuil <hans.verkuil@cisco.com>
Cc: Sakari Ailus <sakari.ailus@linux.intel.com>
Cc: Mauro Carvalho Chehab <mchehab@s-opensource.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/Kconfig       |   4 ++
 drivers/base/regmap/Makefile      |   1 +
 drivers/base/regmap/regmap-sccb.c | 128 ++++++++++++++++++++++++++++++++++++++
 include/linux/regmap.h            |  35 +++++++++++
 4 files changed, 168 insertions(+)
 create mode 100644 drivers/base/regmap/regmap-sccb.c

diff --git a/drivers/base/regmap/Kconfig b/drivers/base/regmap/Kconfig
index aff34c0c2a3e..6ad5ef48b61e 100644
--- a/drivers/base/regmap/Kconfig
+++ b/drivers/base/regmap/Kconfig
@@ -45,3 +45,7 @@ config REGMAP_IRQ
 config REGMAP_SOUNDWIRE
 	tristate
 	depends on SOUNDWIRE_BUS
+
+config REGMAP_SCCB
+	tristate
+	depends on I2C
diff --git a/drivers/base/regmap/Makefile b/drivers/base/regmap/Makefile
index 5ed0023fabda..f5b4e8851d00 100644
--- a/drivers/base/regmap/Makefile
+++ b/drivers/base/regmap/Makefile
@@ -15,3 +15,4 @@ obj-$(CONFIG_REGMAP_MMIO) += regmap-mmio.o
 obj-$(CONFIG_REGMAP_IRQ) += regmap-irq.o
 obj-$(CONFIG_REGMAP_W1) += regmap-w1.o
 obj-$(CONFIG_REGMAP_SOUNDWIRE) += regmap-sdw.o
+obj-$(CONFIG_REGMAP_SCCB) += regmap-sccb.o
diff --git a/drivers/base/regmap/regmap-sccb.c b/drivers/base/regmap/regmap-sccb.c
new file mode 100644
index 000000000000..b6eb876ea819
--- /dev/null
+++ b/drivers/base/regmap/regmap-sccb.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+// Register map access API - SCCB support
+
+#include <linux/regmap.h>
+#include <linux/i2c.h>
+#include <linux/module.h>
+
+#include "internal.h"
+
+/**
+ * sccb_is_available - Check if the adapter supports SCCB protocol
+ * @adap: I2C adapter
+ *
+ * Return true if the I2C adapter is capable of using SCCB helper functions,
+ * false otherwise.
+ */
+static bool sccb_is_available(struct i2c_adapter *adap)
+{
+	u32 needed_funcs = I2C_FUNC_SMBUS_BYTE | I2C_FUNC_SMBUS_WRITE_BYTE_DATA;
+
+	/*
+	 * If we ever want support for hardware doing SCCB natively, we will
+	 * introduce a sccb_xfer() callback to struct i2c_algorithm and check
+	 * for it here.
+	 */
+
+	return (i2c_get_functionality(adap) & needed_funcs) == needed_funcs;
+}
+
+/**
+ * regmap_sccb_read - Read data from SCCB slave device
+ * @context: Device that will be interacted wit
+ * @reg: Register to be read from
+ * @val: Pointer to store read value
+ *
+ * This executes the 2-phase write transmission cycle that is followed by a
+ * 2-phase read transmission cycle, returning negative errno else zero on
+ * success.
+ */
+static int regmap_sccb_read(void *context, unsigned int reg, unsigned int *val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+	int ret;
+	union i2c_smbus_data data;
+
+	i2c_lock_bus(i2c->adapter, I2C_LOCK_SEGMENT);
+
+	ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags,
+			       I2C_SMBUS_WRITE, reg, I2C_SMBUS_BYTE, NULL);
+	if (ret < 0)
+		goto out;
+
+	ret = __i2c_smbus_xfer(i2c->adapter, i2c->addr, i2c->flags,
+			       I2C_SMBUS_READ, 0, I2C_SMBUS_BYTE, &data);
+	if (ret < 0)
+		goto out;
+
+	*val = data.byte;
+out:
+	i2c_unlock_bus(i2c->adapter, I2C_LOCK_SEGMENT);
+
+	return ret;
+}
+
+/**
+ * regmap_sccb_write - Write data to SCCB slave device
+ * @context: Device that will be interacted wit
+ * @reg: Register to write to
+ * @val: Value to be written
+ *
+ * This executes the SCCB 3-phase write transmission cycle, returning negative
+ * errno else zero on success.
+ */
+static int regmap_sccb_write(void *context, unsigned int reg, unsigned int val)
+{
+	struct device *dev = context;
+	struct i2c_client *i2c = to_i2c_client(dev);
+
+	return i2c_smbus_write_byte_data(i2c, reg, val);
+}
+
+static struct regmap_bus regmap_sccb_bus = {
+	.reg_write = regmap_sccb_write,
+	.reg_read = regmap_sccb_read,
+};
+
+static const struct regmap_bus *regmap_get_sccb_bus(struct i2c_client *i2c,
+					const struct regmap_config *config)
+{
+	if (config->val_bits == 8 && config->reg_bits == 8 &&
+			sccb_is_available(i2c->adapter))
+		return &regmap_sccb_bus;
+
+	return ERR_PTR(-ENOTSUPP);
+}
+
+struct regmap *__regmap_init_sccb(struct i2c_client *i2c,
+				  const struct regmap_config *config,
+				  struct lock_class_key *lock_key,
+				  const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __regmap_init(&i2c->dev, bus, &i2c->dev, config,
+			     lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__regmap_init_sccb);
+
+struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c,
+				       const struct regmap_config *config,
+				       struct lock_class_key *lock_key,
+				       const char *lock_name)
+{
+	const struct regmap_bus *bus = regmap_get_sccb_bus(i2c, config);
+
+	if (IS_ERR(bus))
+		return ERR_CAST(bus);
+
+	return __devm_regmap_init(&i2c->dev, bus, &i2c->dev, config,
+				  lock_key, lock_name);
+}
+EXPORT_SYMBOL_GPL(__devm_regmap_init_sccb);
+
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4f38068ffb71..52bf358e2c73 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -514,6 +514,10 @@ struct regmap *__regmap_init_i2c(struct i2c_client *i2c,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
 				 const char *lock_name);
+struct regmap *__regmap_init_sccb(struct i2c_client *i2c,
+				  const struct regmap_config *config,
+				  struct lock_class_key *lock_key,
+				  const char *lock_name);
 struct regmap *__regmap_init_slimbus(struct slim_device *slimbus,
 				 const struct regmap_config *config,
 				 struct lock_class_key *lock_key,
@@ -558,6 +562,10 @@ struct regmap *__devm_regmap_init_i2c(struct i2c_client *i2c,
 				      const struct regmap_config *config,
 				      struct lock_class_key *lock_key,
 				      const char *lock_name);
+struct regmap *__devm_regmap_init_sccb(struct i2c_client *i2c,
+				       const struct regmap_config *config,
+				       struct lock_class_key *lock_key,
+				       const char *lock_name);
 struct regmap *__devm_regmap_init_spi(struct spi_device *dev,
 				      const struct regmap_config *config,
 				      struct lock_class_key *lock_key,
@@ -645,6 +653,19 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
 	__regmap_lockdep_wrapper(__regmap_init_i2c, #config,		\
 				i2c, config)
 
+/**
+ * regmap_init_sccb() - Initialise register map
+ *
+ * @i2c: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer to
+ * a struct regmap.
+ */
+#define regmap_init_sccb(i2c, config)					\
+	__regmap_lockdep_wrapper(__regmap_init_sccb, #config,		\
+				i2c, config)
+
 /**
  * regmap_init_slimbus() - Initialise register map
  *
@@ -797,6 +818,20 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
 	__regmap_lockdep_wrapper(__devm_regmap_init_i2c, #config,	\
 				i2c, config)
 
+/**
+ * devm_regmap_init_sccb() - Initialise managed register map
+ *
+ * @i2c: Device that will be interacted with
+ * @config: Configuration for register map
+ *
+ * The return value will be an ERR_PTR() on error or a valid pointer
+ * to a struct regmap.  The regmap will be automatically freed by the
+ * device management code.
+ */
+#define devm_regmap_init_sccb(i2c, config)				\
+	__regmap_lockdep_wrapper(__devm_regmap_init_sccb, #config,	\
+				i2c, config)
+
 /**
  * devm_regmap_init_spi() - Initialise register map
  *
-- 
cgit v1.2.3


From 6c6bc9ea84d0008024606bf5ba10519e20d851bf Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Sat, 7 Jul 2018 05:37:22 +0200
Subject: mtdchar: fix overflows in adjustment of `count`

The first checks in mtdchar_read() and mtdchar_write() attempt to limit
`count` such that `*ppos + count <= mtd->size`. However, they ignore the
possibility of `*ppos > mtd->size`, allowing the calculation of `count` to
wrap around. `mtdchar_lseek()` prevents seeking beyond mtd->size, but the
pread/pwrite syscalls bypass this.

I haven't found any codepath on which this actually causes dangerous
behavior, but it seems like a sensible change anyway.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Jann Horn <jannh@google.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/mtdchar.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index cd67c85cc87d..02389528f622 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -160,8 +160,12 @@ static ssize_t mtdchar_read(struct file *file, char __user *buf, size_t count,
 
 	pr_debug("MTD_read\n");
 
-	if (*ppos + count > mtd->size)
-		count = mtd->size - *ppos;
+	if (*ppos + count > mtd->size) {
+		if (*ppos < mtd->size)
+			count = mtd->size - *ppos;
+		else
+			count = 0;
+	}
 
 	if (!count)
 		return 0;
@@ -246,7 +250,7 @@ static ssize_t mtdchar_write(struct file *file, const char __user *buf, size_t c
 
 	pr_debug("MTD_write\n");
 
-	if (*ppos == mtd->size)
+	if (*ppos >= mtd->size)
 		return -ENOSPC;
 
 	if (*ppos + count > mtd->size)
-- 
cgit v1.2.3


From 7c201ead1bfd19935f689fca69100c335028c047 Mon Sep 17 00:00:00 2001
From: David Lechner <david@lechnology.com>
Date: Mon, 16 Jul 2018 22:20:49 -0500
Subject: spi: spi-bitbang: change flags from u8 to u16

This changes the data type of the flags field in struct spi_bitbang from
u8 to u16. This matches the size of the mode field of struct spi_device
where these flags are also used.

This is done in preparation of adding a new SPI mode flag that will be
used with this field that would otherwise not fit in 8 bits.

Signed-off-by: David Lechner <david@lechnology.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi_bitbang.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h
index 51d8c060e513..c1e61641a7f1 100644
--- a/include/linux/spi/spi_bitbang.h
+++ b/include/linux/spi/spi_bitbang.h
@@ -8,7 +8,7 @@ struct spi_bitbang {
 	struct mutex		lock;
 	u8			busy;
 	u8			use_dma;
-	u8			flags;		/* extra spi->mode support */
+	u16			flags;		/* extra spi->mode support */
 
 	struct spi_master	*master;
 
-- 
cgit v1.2.3


From baa2a4fdd525c8c4b0f704d20457195b29437839 Mon Sep 17 00:00:00 2001
From: Ronny Chevalier <ronny.chevalier@hp.com>
Date: Wed, 11 Jul 2018 14:39:37 +0200
Subject: audit: fix use-after-free in audit_add_watch

audit_add_watch stores locally krule->watch without taking a reference
on watch. Then, it calls audit_add_to_parent, and uses the watch stored
locally.

Unfortunately, it is possible that audit_add_to_parent updates
krule->watch.
When it happens, it also drops a reference of watch which
could free the watch.

How to reproduce (with KASAN enabled):

    auditctl -w /etc/passwd -F success=0 -k test_passwd
    auditctl -w /etc/passwd -F success=1 -k test_passwd2

The second call to auditctl triggers the use-after-free, because
audit_to_parent updates krule->watch to use a previous existing watch
and drops the reference to the newly created watch.

To fix the issue, we grab a reference of watch and we release it at the
end of the function.

Signed-off-by: Ronny Chevalier <ronny.chevalier@hp.com>
Reviewed-by: Richard Guy Briggs <rgb@redhat.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 kernel/audit_watch.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c
index 6f249bdf2d84..787c7afdf829 100644
--- a/kernel/audit_watch.c
+++ b/kernel/audit_watch.c
@@ -420,6 +420,13 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	struct path parent_path;
 	int h, ret = 0;
 
+	/*
+	 * When we will be calling audit_add_to_parent, krule->watch might have
+	 * been updated and watch might have been freed.
+	 * So we need to keep a reference of watch.
+	 */
+	audit_get_watch(watch);
+
 	mutex_unlock(&audit_filter_mutex);
 
 	/* Avoid calling path_lookup under audit_filter_mutex. */
@@ -428,8 +435,10 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	/* caller expects mutex locked */
 	mutex_lock(&audit_filter_mutex);
 
-	if (ret)
+	if (ret) {
+		audit_put_watch(watch);
 		return ret;
+	}
 
 	/* either find an old parent or attach a new one */
 	parent = audit_find_parent(d_backing_inode(parent_path.dentry));
@@ -447,6 +456,7 @@ int audit_add_watch(struct audit_krule *krule, struct list_head **list)
 	*list = &audit_inode_hash[h];
 error:
 	path_put(&parent_path);
+	audit_put_watch(watch);
 	return ret;
 }
 
-- 
cgit v1.2.3


From ce2d54619a10780a0d354e10d4c83ae4fad46f41 Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 17 Jul 2018 18:13:42 +0100
Subject: drm/fourcc: Add is_yuv field to drm_format_info to denote if the
 format is yuv

A lot of drivers duplicate the function to check if a format is yuv or not.
If we add a field (to denote whether the format is yuv or not) in the
drm_format_info table, all the drivers can use this field and it will
prevent duplication of similar logic.

Signed-off-by: Ayan Kumar halder <ayan.halder@arm.com>
Reviewed-by: Ville Syrjala <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531847626-22248-1-git-send-email-ayan.halder@arm.com
---
 drivers/gpu/drm/drm_fourcc.c | 42 +++++++++++++++++++++---------------------
 include/drm/drm_fourcc.h     |  2 ++
 2 files changed, 23 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/drm_fourcc.c b/drivers/gpu/drm/drm_fourcc.c
index 5ca6395cd4d3..35c1e2742c27 100644
--- a/drivers/gpu/drm/drm_fourcc.c
+++ b/drivers/gpu/drm/drm_fourcc.c
@@ -152,27 +152,27 @@ const struct drm_format_info *__drm_format_info(u32 format)
 		{ .format = DRM_FORMAT_XBGR8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_RGBX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
 		{ .format = DRM_FORMAT_BGRX8888_A8,	.depth = 32, .num_planes = 2, .cpp = { 4, 1, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
-		{ .format = DRM_FORMAT_YUV410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
-		{ .format = DRM_FORMAT_YVU410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4 },
-		{ .format = DRM_FORMAT_YUV411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUV420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_YVU420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_YUV422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUV444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVU444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV12,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_NV21,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2 },
-		{ .format = DRM_FORMAT_NV16,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV61,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV24,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_NV42,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1 },
-		{ .format = DRM_FORMAT_YUYV,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_YVYU,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_UYVY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_VYUY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1 },
-		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true },
+		{ .format = DRM_FORMAT_YUV410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU410,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 4, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU411,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 4, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU420,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU422,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUV444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVU444,		.depth = 0,  .num_planes = 3, .cpp = { 1, 1, 1 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV12,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV21,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 2, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV16,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV61,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV24,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_NV42,		.depth = 0,  .num_planes = 2, .cpp = { 1, 2, 0 }, .hsub = 1, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YUYV,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_YVYU,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_UYVY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_VYUY,		.depth = 0,  .num_planes = 1, .cpp = { 2, 0, 0 }, .hsub = 2, .vsub = 1, .is_yuv = true },
+		{ .format = DRM_FORMAT_AYUV,		.depth = 0,  .num_planes = 1, .cpp = { 4, 0, 0 }, .hsub = 1, .vsub = 1, .has_alpha = true, .is_yuv = true },
 	};
 
 	unsigned int i;
diff --git a/include/drm/drm_fourcc.h b/include/drm/drm_fourcc.h
index 3e86408dac9f..f9c15845f465 100644
--- a/include/drm/drm_fourcc.h
+++ b/include/drm/drm_fourcc.h
@@ -39,6 +39,7 @@ struct drm_mode_fb_cmd2;
  * @hsub: Horizontal chroma subsampling factor
  * @vsub: Vertical chroma subsampling factor
  * @has_alpha: Does the format embeds an alpha component?
+ * @is_yuv: Is it a YUV format?
  */
 struct drm_format_info {
 	u32 format;
@@ -48,6 +49,7 @@ struct drm_format_info {
 	u8 hsub;
 	u8 vsub;
 	bool has_alpha;
+	bool is_yuv;
 };
 
 /**
-- 
cgit v1.2.3


From 9bace65934e74d47e467c44765e6a202c302fe7a Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 17 Jul 2018 18:13:43 +0100
Subject: drm/i915: Substitute intel_format_is_yuv() with format->is_yuv

drm_format_info table has a field 'is_yuv' to denote if the format
is yuv or not. The driver is expected to use this instead of
having a function for the same purpose.

Signed-off-by: Ayan Kumar halder <ayan.halder@arm.com>
Reviewed-by: Ville Syrjala <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531847626-22248-2-git-send-email-ayan.halder@arm.com
---
 drivers/gpu/drm/i915/intel_display.c |  2 +-
 drivers/gpu/drm/i915/intel_drv.h     |  2 --
 drivers/gpu/drm/i915/intel_sprite.c  | 20 +++-----------------
 3 files changed, 4 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index fbe5a6572d7d..cf0901240bd1 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3657,7 +3657,7 @@ u32 glk_plane_color_ctl(const struct intel_crtc_state *crtc_state,
 	plane_color_ctl |= PLANE_COLOR_PLANE_GAMMA_DISABLE;
 	plane_color_ctl |= glk_plane_color_ctl_alpha(fb->format->format);
 
-	if (intel_format_is_yuv(fb->format->format)) {
+	if (fb->format->is_yuv) {
 		if (plane_state->base.color_encoding == DRM_COLOR_YCBCR_BT709)
 			plane_color_ctl |= PLANE_COLOR_CSC_MODE_YUV709_TO_RGB709;
 		else
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 0c3ac0eafde0..64111ead4997 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -2069,7 +2069,6 @@ bool intel_sdvo_init(struct drm_i915_private *dev_priv,
 
 
 /* intel_sprite.c */
-bool intel_format_is_yuv(u32 format);
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs);
 struct intel_plane *intel_sprite_plane_create(struct drm_i915_private *dev_priv,
@@ -2085,7 +2084,6 @@ void skl_disable_plane(struct intel_plane *plane, struct intel_crtc *crtc);
 bool skl_plane_get_hw_state(struct intel_plane *plane, enum pipe *pipe);
 bool skl_plane_has_ccs(struct drm_i915_private *dev_priv,
 		       enum pipe pipe, enum plane_id plane_id);
-bool intel_format_is_yuv(uint32_t format);
 bool skl_plane_has_planar(struct drm_i915_private *dev_priv,
 			  enum pipe pipe, enum plane_id plane_id);
 
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 344c0e709b19..1bb7bc3f84fe 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/drivers/gpu/drm/i915/intel_sprite.c
@@ -41,20 +41,6 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 
-bool intel_format_is_yuv(u32 format)
-{
-	switch (format) {
-	case DRM_FORMAT_YUYV:
-	case DRM_FORMAT_UYVY:
-	case DRM_FORMAT_VYUY:
-	case DRM_FORMAT_YVYU:
-	case DRM_FORMAT_NV12:
-		return true;
-	default:
-		return false;
-	}
-}
-
 int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
 			     int usecs)
 {
@@ -404,7 +390,7 @@ chv_update_csc(const struct intel_plane_state *plane_state)
 	const s16 *csc = csc_matrix[plane_state->base.color_encoding];
 
 	/* Seems RGB data bypasses the CSC always */
-	if (!intel_format_is_yuv(fb->format->format))
+	if (!fb->format->is_yuv)
 		return;
 
 	I915_WRITE_FW(SPCSCYGOFF(plane_id), SPCSC_OOFF(0) | SPCSC_IOFF(0));
@@ -439,7 +425,7 @@ vlv_update_clrc(const struct intel_plane_state *plane_state)
 	enum plane_id plane_id = plane->id;
 	int contrast, brightness, sh_scale, sh_sin, sh_cos;
 
-	if (intel_format_is_yuv(fb->format->format) &&
+	if (fb->format->is_yuv &&
 	    plane_state->base.color_range == DRM_COLOR_YCBCR_LIMITED_RANGE) {
 		/*
 		 * Expand limited range to full range:
@@ -1040,7 +1026,7 @@ intel_check_sprite_plane(struct intel_plane *plane,
 		src->y1 = src_y << 16;
 		src->y2 = (src_y + src_h) << 16;
 
-		if (intel_format_is_yuv(fb->format->format) &&
+		if (fb->format->is_yuv &&
     		    fb->format->format != DRM_FORMAT_NV12 &&
 		    (src_x % 2 || src_w % 2)) {
 			DRM_DEBUG_KMS("src x/w (%u, %u) must be a multiple of 2 for YUV planes\n",
-- 
cgit v1.2.3


From d8bd23d9936bea7184a2bce1242ea646f4906d7d Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 17 Jul 2018 18:13:44 +0100
Subject: drm/rockchip: Substitute is_yuv_support() with format->is_yuv

drm_format_info table has a field 'is_yuv' to denote if the format
is yuv or not. The driver is expected to use this instead of
having a function for the same purpose.

Signed-off-by: Ayan Kumar halder <ayan.halder@arm.com>
Reviewed-by: Ville Syrjala <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531847626-22248-3-git-send-email-ayan.halder@arm.com
---
 drivers/gpu/drm/rockchip/rockchip_drm_vop.c | 24 +++++++++---------------
 1 file changed, 9 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
index effecbed2d11..1359e5c773e4 100644
--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
@@ -243,18 +243,6 @@ static enum vop_data_format vop_convert_format(uint32_t format)
 	}
 }
 
-static bool is_yuv_support(uint32_t format)
-{
-	switch (format) {
-	case DRM_FORMAT_NV12:
-	case DRM_FORMAT_NV16:
-	case DRM_FORMAT_NV24:
-		return true;
-	default:
-		return false;
-	}
-}
-
 static uint16_t scl_vop_cal_scale(enum scale_mode mode, uint32_t src,
 				  uint32_t dst, bool is_horizontal,
 				  int vsu_mode, int *vskiplines)
@@ -298,7 +286,8 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
 	uint16_t cbcr_ver_scl_mode = SCALE_NONE;
 	int hsub = drm_format_horz_chroma_subsampling(pixel_format);
 	int vsub = drm_format_vert_chroma_subsampling(pixel_format);
-	bool is_yuv = is_yuv_support(pixel_format);
+	const struct drm_format_info *info;
+	bool is_yuv = false;
 	uint16_t cbcr_src_w = src_w / hsub;
 	uint16_t cbcr_src_h = src_h / vsub;
 	uint16_t vsu_mode;
@@ -306,6 +295,11 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
 	uint32_t val;
 	int vskiplines;
 
+	info = drm_format_info(pixel_format);
+
+	if (info->is_yuv)
+		is_yuv = true;
+
 	if (dst_w > 3840) {
 		DRM_DEV_ERROR(vop->dev, "Maximum dst width (3840) exceeded\n");
 		return;
@@ -680,7 +674,7 @@ static int vop_plane_atomic_check(struct drm_plane *plane,
 	 * Src.x1 can be odd when do clip, but yuv plane start point
 	 * need align with 2 pixel.
 	 */
-	if (is_yuv_support(fb->format->format) && ((state->src.x1 >> 16) % 2)) {
+	if (fb->format->is_yuv && ((state->src.x1 >> 16) % 2)) {
 		DRM_ERROR("Invalid Source: Yuv format not support odd xpos\n");
 		return -EINVAL;
 	}
@@ -767,7 +761,7 @@ static void vop_plane_atomic_update(struct drm_plane *plane,
 	VOP_WIN_SET(vop, win, format, format);
 	VOP_WIN_SET(vop, win, yrgb_vir, DIV_ROUND_UP(fb->pitches[0], 4));
 	VOP_WIN_SET(vop, win, yrgb_mst, dma_addr);
-	if (is_yuv_support(fb->format->format)) {
+	if (fb->format->is_yuv) {
 		int hsub = drm_format_horz_chroma_subsampling(fb->format->format);
 		int vsub = drm_format_vert_chroma_subsampling(fb->format->format);
 		int bpp = fb->format->cpp[1];
-- 
cgit v1.2.3


From 979c11ef39cee79d6f556091a357890962be2580 Mon Sep 17 00:00:00 2001
From: Ayan Kumar Halder <ayan.halder@arm.com>
Date: Tue, 17 Jul 2018 18:13:46 +0100
Subject: drm/sun4i: Substitute sun4i_backend_format_is_yuv() with
 format->is_yuv

drm_format_info table has a field 'is_yuv' to denote if the format
is yuv or not. The driver is expected to use this instead of
having a function for the same purpose.

Signed-off-by: Ayan Kumar halder <ayan.halder@arm.com>
Reviewed-by: Ville Syrjala <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531847626-22248-5-git-send-email-ayan.halder@arm.com
---
 drivers/gpu/drm/sun4i/sun4i_backend.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/sun4i/sun4i_backend.c b/drivers/gpu/drm/sun4i/sun4i_backend.c
index de0a76dfa1a2..d7950b52a1fd 100644
--- a/drivers/gpu/drm/sun4i/sun4i_backend.c
+++ b/drivers/gpu/drm/sun4i/sun4i_backend.c
@@ -86,12 +86,6 @@ static inline bool sun4i_backend_format_is_packed_yuv422(uint32_t format)
 	}
 }
 
-static inline bool sun4i_backend_format_is_yuv(uint32_t format)
-{
-	return sun4i_backend_format_is_planar_yuv(format) ||
-		sun4i_backend_format_is_packed_yuv422(format);
-}
-
 static void sun4i_backend_apply_color_correction(struct sunxi_engine *engine)
 {
 	int i;
@@ -304,7 +298,7 @@ int sun4i_backend_update_layer_formats(struct sun4i_backend *backend,
 			   SUN4I_BACKEND_ATTCTL_REG0_LAY_GLBALPHA_EN,
 			   val);
 
-	if (sun4i_backend_format_is_yuv(fb->format->format))
+	if (fb->format->is_yuv)
 		return sun4i_backend_update_yuv_format(backend, layer, plane);
 
 	ret = sun4i_backend_drm_format_to_layer(fb->format->format, &val);
@@ -384,7 +378,7 @@ int sun4i_backend_update_layer_buffer(struct sun4i_backend *backend,
 	 */
 	paddr -= PHYS_OFFSET;
 
-	if (sun4i_backend_format_is_yuv(fb->format->format))
+	if (fb->format->is_yuv)
 		return sun4i_backend_update_yuv_buffer(backend, fb, paddr);
 
 	/* Write the 32 lower bits of the address (in bits) */
@@ -502,7 +496,7 @@ static int sun4i_backend_atomic_check(struct sunxi_engine *engine,
 		if (fb->format->has_alpha || (plane_state->alpha != DRM_BLEND_ALPHA_OPAQUE))
 			num_alpha_planes++;
 
-		if (sun4i_backend_format_is_yuv(fb->format->format)) {
+		if (fb->format->is_yuv) {
 			DRM_DEBUG_DRIVER("Plane FB format is YUV\n");
 			num_yuv_planes++;
 		}
-- 
cgit v1.2.3


From c33d0cb1922e2914de91a293f3aa253e9f9aa585 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:30 +0300
Subject: mlxsw: reg: Add Infrastructure Entry Delete Register

The IEDR register is used for deleting entries from the entry tables.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 62 +++++++++++++++++++++++++++++++
 1 file changed, 62 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index f76c17308a51..f6bfdca6bfdb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2456,6 +2456,67 @@ static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
 	mlxsw_reg_ptce2_tcam_region_info_memcpy_to(payload, tcam_region_info);
 }
 
+/* IEDR - Infrastructure Entry Delete Register
+ * ----------------------------------------------------
+ * This register is used for deleting entries from the entry tables.
+ * It is legitimate to attempt to delete a nonexisting entry (the device will
+ * respond as a good flow).
+ */
+#define MLXSW_REG_IEDR_ID 0x3804
+#define MLXSW_REG_IEDR_BASE_LEN 0x10 /* base length, without records */
+#define MLXSW_REG_IEDR_REC_LEN 0x8 /* record length */
+#define MLXSW_REG_IEDR_REC_MAX_COUNT 64
+#define MLXSW_REG_IEDR_LEN (MLXSW_REG_IEDR_BASE_LEN +	\
+			    MLXSW_REG_IEDR_REC_LEN *	\
+			    MLXSW_REG_IEDR_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(iedr, MLXSW_REG_IEDR_ID, MLXSW_REG_IEDR_LEN);
+
+/* reg_iedr_num_rec
+ * Number of records.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, iedr, num_rec, 0x00, 0, 8);
+
+/* reg_iedr_rec_type
+ * Resource type.
+ * Access: OP
+ */
+MLXSW_ITEM32_INDEXED(reg, iedr, rec_type, MLXSW_REG_IEDR_BASE_LEN, 24, 8,
+		     MLXSW_REG_IEDR_REC_LEN, 0x00, false);
+
+/* reg_iedr_rec_size
+ * Size of entries do be deleted. The unit is 1 entry, regardless of entry type.
+ * Access: OP
+ */
+MLXSW_ITEM32_INDEXED(reg, iedr, rec_size, MLXSW_REG_IEDR_BASE_LEN, 0, 11,
+		     MLXSW_REG_IEDR_REC_LEN, 0x00, false);
+
+/* reg_iedr_rec_index_start
+ * Resource index start.
+ * Access: OP
+ */
+MLXSW_ITEM32_INDEXED(reg, iedr, rec_index_start, MLXSW_REG_IEDR_BASE_LEN, 0, 24,
+		     MLXSW_REG_IEDR_REC_LEN, 0x04, false);
+
+static inline void mlxsw_reg_iedr_pack(char *payload)
+{
+	MLXSW_REG_ZERO(iedr, payload);
+}
+
+static inline void mlxsw_reg_iedr_rec_pack(char *payload, int rec_index,
+					   u8 rec_type, u16 rec_size,
+					   u32 rec_index_start)
+{
+	u8 num_rec = mlxsw_reg_iedr_num_rec_get(payload);
+
+	if (rec_index >= num_rec)
+		mlxsw_reg_iedr_num_rec_set(payload, rec_index + 1);
+	mlxsw_reg_iedr_rec_type_set(payload, rec_index, rec_type);
+	mlxsw_reg_iedr_rec_size_set(payload, rec_index, rec_size);
+	mlxsw_reg_iedr_rec_index_start_set(payload, rec_index, rec_index_start);
+}
+
 /* QPCR - QoS Policer Configuration Register
  * -----------------------------------------
  * The QPCR register is used to create policers - that limit
@@ -7971,6 +8032,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(prcr),
 	MLXSW_REG(pefa),
 	MLXSW_REG(ptce2),
+	MLXSW_REG(iedr),
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
 	MLXSW_REG(qeec),
-- 
cgit v1.2.3


From 742f75a600cab552482f1b17449ba528584f65de Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:31 +0300
Subject: mlxsw: spectrum: Add KVDL manager implementation for Spectrum-2

In Spectrum-2, KVD linear indexes are hashed into KVD hash. Therefore it
is possible for multiple resource types to use same indexes. There are
multiple index spaces. Also, the index space is bigger than the actual
KVD hash area, which allows to have holes in the index space without any
penalization. The HW has to be told in case the index for particular
resource type is no longer used so it can be freed from KVD hash. IEDR
register is used for that.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   3 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   3 +
 .../net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c   | 302 +++++++++++++++++++++
 3 files changed, 307 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 981e621ef9c2..9fc99c684d68 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -15,7 +15,8 @@ mlxsw_switchx2-objs		:= switchx2.o
 obj-$(CONFIG_MLXSW_SPECTRUM)	+= mlxsw_spectrum.o
 mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_switchdev.o spectrum_router.o \
-				   spectrum1_kvdl.o spectrum_kvdl.o \
+				   spectrum1_kvdl.o spectrum2_kvdl.o \
+				   spectrum_kvdl.o \
 				   spectrum_acl_tcam.o spectrum_acl_ctcam.o \
 				   spectrum1_acl_tcam.o \
 				   spectrum_acl.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 8aa717a7d11c..fa21fd14ef05 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -501,6 +501,9 @@ int mlxsw_sp_kvdl_alloc_count_query(struct mlxsw_sp *mlxsw_sp,
 extern const struct mlxsw_sp_kvdl_ops mlxsw_sp1_kvdl_ops;
 int mlxsw_sp1_kvdl_resources_register(struct mlxsw_core *mlxsw_core);
 
+/* spectrum2_kvdl.c */
+extern const struct mlxsw_sp_kvdl_ops mlxsw_sp2_kvdl_ops;
+
 struct mlxsw_sp_acl_rule_info {
 	unsigned int priority;
 	struct mlxsw_afk_element_values values;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
new file mode 100644
index 000000000000..bacf7483c3fb
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
@@ -0,0 +1,302 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+
+#include "spectrum.h"
+#include "core.h"
+#include "reg.h"
+#include "resources.h"
+
+struct mlxsw_sp2_kvdl_part_info {
+	u8 res_type;
+	/* For each defined partititon we need to know how many
+	 * usage bits we need and how many indexes there are
+	 * represented by a single bit. This could be got from FW
+	 * querying appropriate resources. So have the resource
+	 * ids for for this purpose in partition definition.
+	 */
+	enum mlxsw_res_id usage_bit_count_res_id;
+	enum mlxsw_res_id index_range_res_id;
+};
+
+#define MLXSW_SP2_KVDL_PART_INFO(_entry_type, _res_type,			\
+				 _usage_bit_count_res_id, _index_range_res_id)	\
+[MLXSW_SP_KVDL_ENTRY_TYPE_##_entry_type] = {					\
+	.res_type = _res_type,							\
+	.usage_bit_count_res_id = MLXSW_RES_ID_##_usage_bit_count_res_id,	\
+	.index_range_res_id = MLXSW_RES_ID_##_index_range_res_id,		\
+}
+
+static const struct mlxsw_sp2_kvdl_part_info mlxsw_sp2_kvdl_parts_info[] = {
+	MLXSW_SP2_KVDL_PART_INFO(ADJ, 0x21, KVD_SIZE, MAX_KVD_LINEAR_RANGE),
+	MLXSW_SP2_KVDL_PART_INFO(ACTSET, 0x23, MAX_KVD_ACTION_SETS,
+				 MAX_KVD_ACTION_SETS),
+	MLXSW_SP2_KVDL_PART_INFO(PBS, 0x24, KVD_SIZE, KVD_SIZE),
+	MLXSW_SP2_KVDL_PART_INFO(MCRIGR, 0x26, KVD_SIZE, KVD_SIZE),
+};
+
+#define MLXSW_SP2_KVDL_PARTS_INFO_LEN ARRAY_SIZE(mlxsw_sp2_kvdl_parts_info)
+
+struct mlxsw_sp2_kvdl_part {
+	const struct mlxsw_sp2_kvdl_part_info *info;
+	unsigned int usage_bit_count;
+	unsigned int indexes_per_usage_bit;
+	unsigned int last_allocated_bit;
+	unsigned long usage[0];	/* Usage bits */
+};
+
+struct mlxsw_sp2_kvdl {
+	struct mlxsw_sp2_kvdl_part *parts[MLXSW_SP2_KVDL_PARTS_INFO_LEN];
+};
+
+static int mlxsw_sp2_kvdl_part_find_zero_bits(struct mlxsw_sp2_kvdl_part *part,
+					      unsigned int bit_count,
+					      unsigned int *p_bit)
+{
+	unsigned int start_bit;
+	unsigned int bit;
+	unsigned int i;
+	bool wrap = false;
+
+	start_bit = part->last_allocated_bit + 1;
+	if (start_bit == part->usage_bit_count)
+		start_bit = 0;
+	bit = start_bit;
+again:
+	bit = find_next_zero_bit(part->usage, part->usage_bit_count, bit);
+	if (!wrap && bit + bit_count >= part->usage_bit_count) {
+		wrap = true;
+		bit = 0;
+		goto again;
+	}
+	if (wrap && bit + bit_count >= start_bit)
+		return -ENOBUFS;
+	for (i = 0; i < bit_count; i++) {
+		if (test_bit(bit + i, part->usage)) {
+			bit += bit_count;
+			goto again;
+		}
+	}
+	*p_bit = bit;
+	return 0;
+}
+
+static int mlxsw_sp2_kvdl_part_alloc(struct mlxsw_sp2_kvdl_part *part,
+				     unsigned int size,
+				     u32 *p_kvdl_index)
+{
+	unsigned int bit_count;
+	unsigned int bit;
+	unsigned int i;
+	int err;
+
+	bit_count = DIV_ROUND_UP(size, part->indexes_per_usage_bit);
+	err = mlxsw_sp2_kvdl_part_find_zero_bits(part, bit_count, &bit);
+	if (err)
+		return err;
+	for (i = 0; i < bit_count; i++)
+		__set_bit(bit + i, part->usage);
+	*p_kvdl_index = bit * part->indexes_per_usage_bit;
+	return 0;
+}
+
+static int mlxsw_sp2_kvdl_rec_del(struct mlxsw_sp *mlxsw_sp, u8 res_type,
+				  u16 size, u32 kvdl_index)
+{
+	char *iedr_pl;
+	int err;
+
+	iedr_pl = kmalloc(MLXSW_REG_IEDR_LEN, GFP_KERNEL);
+	if (!iedr_pl)
+		return -ENOMEM;
+
+	mlxsw_reg_iedr_pack(iedr_pl);
+	mlxsw_reg_iedr_rec_pack(iedr_pl, 0, res_type, size, kvdl_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(iedr), iedr_pl);
+	kfree(iedr_pl);
+	return err;
+}
+
+static void mlxsw_sp2_kvdl_part_free(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp2_kvdl_part *part,
+				     unsigned int size, u32 kvdl_index)
+{
+	unsigned int bit_count;
+	unsigned int bit;
+	unsigned int i;
+	int err;
+
+	/* We need to ask FW to delete previously used KVD linear index */
+	err = mlxsw_sp2_kvdl_rec_del(mlxsw_sp, part->info->res_type,
+				     size, kvdl_index);
+	if (err)
+		return;
+
+	bit_count = DIV_ROUND_UP(size, part->indexes_per_usage_bit);
+	bit = kvdl_index / part->indexes_per_usage_bit;
+	for (i = 0; i < bit_count; i++)
+		__clear_bit(bit + i, part->usage);
+}
+
+static int mlxsw_sp2_kvdl_alloc(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
+				unsigned int entry_count,
+				u32 *p_entry_index)
+{
+	unsigned int size = entry_count * mlxsw_sp_kvdl_entry_size(type);
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+	struct mlxsw_sp2_kvdl_part *part = kvdl->parts[type];
+
+	return mlxsw_sp2_kvdl_part_alloc(part, size, p_entry_index);
+}
+
+static void mlxsw_sp2_kvdl_free(struct mlxsw_sp *mlxsw_sp, void *priv,
+				enum mlxsw_sp_kvdl_entry_type type,
+				unsigned int entry_count,
+				int entry_index)
+{
+	unsigned int size = entry_count * mlxsw_sp_kvdl_entry_size(type);
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+	struct mlxsw_sp2_kvdl_part *part = kvdl->parts[type];
+
+	return mlxsw_sp2_kvdl_part_free(mlxsw_sp, part, size, entry_index);
+}
+
+static int mlxsw_sp2_kvdl_alloc_size_query(struct mlxsw_sp *mlxsw_sp,
+					   void *priv,
+					   enum mlxsw_sp_kvdl_entry_type type,
+					   unsigned int entry_count,
+					   unsigned int *p_alloc_count)
+{
+	*p_alloc_count = entry_count;
+	return 0;
+}
+
+static struct mlxsw_sp2_kvdl_part *
+mlxsw_sp2_kvdl_part_init(struct mlxsw_sp *mlxsw_sp,
+			 const struct mlxsw_sp2_kvdl_part_info *info)
+{
+	unsigned int indexes_per_usage_bit;
+	struct mlxsw_sp2_kvdl_part *part;
+	unsigned int index_range;
+	unsigned int usage_bit_count;
+	size_t usage_size;
+
+	if (!mlxsw_core_res_valid(mlxsw_sp->core,
+				  info->usage_bit_count_res_id) ||
+	    !mlxsw_core_res_valid(mlxsw_sp->core,
+				  info->index_range_res_id))
+		return ERR_PTR(-EIO);
+	usage_bit_count = mlxsw_core_res_get(mlxsw_sp->core,
+					     info->usage_bit_count_res_id);
+	index_range = mlxsw_core_res_get(mlxsw_sp->core,
+					 info->index_range_res_id);
+
+	/* For some partitions, one usage bit represents a group of indexes.
+	 * That's why we compute the number of indexes per usage bit here,
+	 * according to queried resources.
+	 */
+	indexes_per_usage_bit = index_range / usage_bit_count;
+
+	usage_size = BITS_TO_LONGS(usage_bit_count) * sizeof(unsigned long);
+	part = kzalloc(sizeof(*part) + usage_size, GFP_KERNEL);
+	if (!part)
+		return ERR_PTR(-ENOMEM);
+	part->info = info;
+	part->usage_bit_count = usage_bit_count;
+	part->indexes_per_usage_bit = indexes_per_usage_bit;
+	part->last_allocated_bit = usage_bit_count - 1;
+	return part;
+}
+
+static void mlxsw_sp2_kvdl_part_fini(struct mlxsw_sp2_kvdl_part *part)
+{
+	kfree(part);
+}
+
+static int mlxsw_sp2_kvdl_parts_init(struct mlxsw_sp *mlxsw_sp,
+				     struct mlxsw_sp2_kvdl *kvdl)
+{
+	const struct mlxsw_sp2_kvdl_part_info *info;
+	int i;
+	int err;
+
+	for (i = 0; i < MLXSW_SP2_KVDL_PARTS_INFO_LEN; i++) {
+		info = &mlxsw_sp2_kvdl_parts_info[i];
+		kvdl->parts[i] = mlxsw_sp2_kvdl_part_init(mlxsw_sp, info);
+		if (IS_ERR(kvdl->parts[i])) {
+			err = PTR_ERR(kvdl->parts[i]);
+			goto err_kvdl_part_init;
+		}
+	}
+	return 0;
+
+err_kvdl_part_init:
+	for (i--; i >= 0; i--)
+		mlxsw_sp2_kvdl_part_fini(kvdl->parts[i]);
+	return err;
+}
+
+static void mlxsw_sp2_kvdl_parts_fini(struct mlxsw_sp2_kvdl *kvdl)
+{
+	int i;
+
+	for (i = 0; i < MLXSW_SP2_KVDL_PARTS_INFO_LEN; i++)
+		mlxsw_sp2_kvdl_part_fini(kvdl->parts[i]);
+}
+
+static int mlxsw_sp2_kvdl_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+
+	return mlxsw_sp2_kvdl_parts_init(mlxsw_sp, kvdl);
+}
+
+static void mlxsw_sp2_kvdl_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp2_kvdl *kvdl = priv;
+
+	mlxsw_sp2_kvdl_parts_fini(kvdl);
+}
+
+const struct mlxsw_sp_kvdl_ops mlxsw_sp2_kvdl_ops = {
+	.priv_size = sizeof(struct mlxsw_sp2_kvdl),
+	.init = mlxsw_sp2_kvdl_init,
+	.fini = mlxsw_sp2_kvdl_fini,
+	.alloc = mlxsw_sp2_kvdl_alloc,
+	.free = mlxsw_sp2_kvdl_free,
+	.alloc_size_query = mlxsw_sp2_kvdl_alloc_size_query,
+};
-- 
cgit v1.2.3


From 18ce0e4e6616d0c8c15aad998e1bda42247e42f1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:32 +0300
Subject: mlxsw: spectrum_mr_tcam: Add Spectrum-2 stubs

Add dummy ops for now. The ops are going to be implemented later on.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  3 +
 .../ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c    | 82 ++++++++++++++++++++++
 3 files changed, 86 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 9fc99c684d68..e1b72e1a0c2a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -24,7 +24,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum_fid.o spectrum_ipip.o \
 				   spectrum_acl_flex_actions.o \
 				   spectrum_acl_flex_keys.o \
-				   spectrum1_mr_tcam.o \
+				   spectrum1_mr_tcam.o spectrum2_mr_tcam.o \
 				   spectrum_mr_tcam.o spectrum_mr.o \
 				   spectrum_qdisc.o spectrum_span.o
 mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB)	+= spectrum_dcb.o
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index fa21fd14ef05..407b3315e210 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -730,4 +730,7 @@ struct mlxsw_sp_mr_tcam_ops {
 /* spectrum1_mr_tcam.c */
 extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp1_mr_tcam_ops;
 
+/* spectrum2_mr_tcam.c */
+extern const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops;
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
new file mode 100644
index 000000000000..53d4ab70da95
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
@@ -0,0 +1,82 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+
+#include "core_acl_flex_actions.h"
+#include "spectrum.h"
+#include "spectrum_mr.h"
+
+static int
+mlxsw_sp2_mr_tcam_route_create(struct mlxsw_sp *mlxsw_sp, void *priv,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block,
+			       enum mlxsw_sp_mr_route_prio prio)
+{
+	return 0;
+}
+
+static void
+mlxsw_sp2_mr_tcam_route_destroy(struct mlxsw_sp *mlxsw_sp, void *priv,
+				void *route_priv,
+				struct mlxsw_sp_mr_route_key *key)
+{
+}
+
+static int
+mlxsw_sp2_mr_tcam_route_update(struct mlxsw_sp *mlxsw_sp,
+			       void *route_priv,
+			       struct mlxsw_sp_mr_route_key *key,
+			       struct mlxsw_afa_block *afa_block)
+{
+	return 0;
+}
+
+static int mlxsw_sp2_mr_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	return 0;
+}
+
+static void mlxsw_sp2_mr_tcam_fini(void *priv)
+{
+}
+
+const struct mlxsw_sp_mr_tcam_ops mlxsw_sp2_mr_tcam_ops = {
+	.init = mlxsw_sp2_mr_tcam_init,
+	.fini = mlxsw_sp2_mr_tcam_fini,
+	.route_create = mlxsw_sp2_mr_tcam_route_create,
+	.route_destroy = mlxsw_sp2_mr_tcam_route_destroy,
+	.route_update = mlxsw_sp2_mr_tcam_route_update,
+};
-- 
cgit v1.2.3


From d55ece4b6e9ec39a9bcac82f1ae29a106c7bbbfb Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:33 +0300
Subject: mlxsw: spectrum: Add Spectrum-2 variant of flex actions ops

In Spectrum-2, no action set is stored directly in TCAM, all are located
in KVD linear. So ask core to treat the first set as dummy empty one,
to be just used for PTCEV2 purposes.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h               |  1 +
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c  | 12 ++++++++++++
 2 files changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 407b3315e210..b09f339329b6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -646,6 +646,7 @@ extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops;
 
 /* spectrum_acl_flex_actions.c */
 extern const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops;
+extern const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops;
 
 /* spectrum_acl_flex_keys.c */
 extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index 6a7c3406b724..7649570f3b76 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -168,6 +168,18 @@ const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
 	.mirror_del		= mlxsw_sp_act_mirror_del,
 };
 
+const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops = {
+	.kvdl_set_add		= mlxsw_sp_act_kvdl_set_add,
+	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
+	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
+	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
+	.counter_index_get	= mlxsw_sp_act_counter_index_get,
+	.counter_index_put	= mlxsw_sp_act_counter_index_put,
+	.mirror_add		= mlxsw_sp_act_mirror_add,
+	.mirror_del		= mlxsw_sp_act_mirror_del,
+	.dummy_first_set	= true,
+};
+
 int mlxsw_sp_afa_init(struct mlxsw_sp *mlxsw_sp)
 {
 	mlxsw_sp->afa = mlxsw_afa_create(MLXSW_CORE_RES_GET(mlxsw_sp->core,
-- 
cgit v1.2.3


From dcdf01028efa4c72d442f029e9bde449d7e7bc4a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:34 +0300
Subject: mlxsw: spectrum: Introduce flex key blocks for Spectrum-2

Introduce key blocks for Spectrum-2 that contains the same elements used
already for Spectrum1. Along with that, introduce encoder stub.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   1 +
 .../mellanox/mlxsw/spectrum_acl_flex_keys.c        | 110 +++++++++++++++++++++
 2 files changed, 111 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index b09f339329b6..dee9c1822727 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -650,6 +650,7 @@ extern const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops;
 
 /* spectrum_acl_flex_keys.c */
 extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
+extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 
 /* spectrum_flower.c */
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 80f22b7c21da..fe46338f0087 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -172,3 +172,113 @@ const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp1_afk_blocks),
 	.encode_one	= mlxsw_sp1_afk_encode_one,
 };
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_0[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_2[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SMAC_32_47, 0x04, 2),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x06, 2),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_3[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x00, 0, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x04, 16, 12),
+	MLXSW_AFK_ELEMENT_INST_BUF(DMAC_32_47, 0x06, 2),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_4[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(PCP, 0x00, 0, 3),
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x04, 16, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(ETHERTYPE, 0x04, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_5[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(VID, 0x04, 16, 12),
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_SYS_PORT, 0x04, 0, 8), /* RX_ACL_SYSTEM_PORT */
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_0[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_0_31, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv4_2[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(IP_DSCP, 0x04, 0, 6),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_ECN, 0x04, 6, 2),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_TTL_, 0x04, 8, 8),
+	MLXSW_AFK_ELEMENT_INST_U32(IP_PROTO, 0x04, 16, 8),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_0[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_32_63, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_1[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_64_95, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_2[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(DST_IP_96_127, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_3[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_32_63, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_4[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_64_95, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_ipv6_5[] = {
+	MLXSW_AFK_ELEMENT_INST_BUF(SRC_IP_96_127, 0x04, 4),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l4_0[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(SRC_L4_PORT, 0x04, 16, 16),
+	MLXSW_AFK_ELEMENT_INST_U32(DST_L4_PORT, 0x04, 0, 16),
+};
+
+static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_l4_2[] = {
+	MLXSW_AFK_ELEMENT_INST_U32(TCP_FLAGS, 0x04, 16, 9), /* TCP_CONTROL + TCP_ECN */
+};
+
+static const struct mlxsw_afk_block mlxsw_sp2_afk_blocks[] = {
+	MLXSW_AFK_BLOCK(0x10, mlxsw_sp_afk_element_info_mac_0),
+	MLXSW_AFK_BLOCK(0x11, mlxsw_sp_afk_element_info_mac_1),
+	MLXSW_AFK_BLOCK(0x12, mlxsw_sp_afk_element_info_mac_2),
+	MLXSW_AFK_BLOCK(0x13, mlxsw_sp_afk_element_info_mac_3),
+	MLXSW_AFK_BLOCK(0x14, mlxsw_sp_afk_element_info_mac_4),
+	MLXSW_AFK_BLOCK(0x15, mlxsw_sp_afk_element_info_mac_5),
+	MLXSW_AFK_BLOCK(0x38, mlxsw_sp_afk_element_info_ipv4_0),
+	MLXSW_AFK_BLOCK(0x39, mlxsw_sp_afk_element_info_ipv4_1),
+	MLXSW_AFK_BLOCK(0x3A, mlxsw_sp_afk_element_info_ipv4_2),
+	MLXSW_AFK_BLOCK(0x40, mlxsw_sp_afk_element_info_ipv6_0),
+	MLXSW_AFK_BLOCK(0x41, mlxsw_sp_afk_element_info_ipv6_1),
+	MLXSW_AFK_BLOCK(0x42, mlxsw_sp_afk_element_info_ipv6_2),
+	MLXSW_AFK_BLOCK(0x43, mlxsw_sp_afk_element_info_ipv6_3),
+	MLXSW_AFK_BLOCK(0x44, mlxsw_sp_afk_element_info_ipv6_4),
+	MLXSW_AFK_BLOCK(0x45, mlxsw_sp_afk_element_info_ipv6_5),
+	MLXSW_AFK_BLOCK(0x90, mlxsw_sp_afk_element_info_l4_0),
+	MLXSW_AFK_BLOCK(0x92, mlxsw_sp_afk_element_info_l4_2),
+};
+
+static void
+mlxsw_sp2_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
+			 int block_index, char *storage, char *output)
+{
+}
+
+const struct mlxsw_afk_ops mlxsw_sp2_afk_ops = {
+	.blocks		= mlxsw_sp2_afk_blocks,
+	.blocks_count	= ARRAY_SIZE(mlxsw_sp2_afk_blocks),
+	.encode_one	= mlxsw_sp2_afk_encode_one,
+};
-- 
cgit v1.2.3


From 2d186ed4ddfd3a20b529d7bec43c30a7a0bbdd3b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:35 +0300
Subject: mlxsw: reg: Add support for activity information from PEFA register

In Spectrum-2, the PEFA register is extend to report if the action set
was hit during processing of packets. Introduce this extension and
adjust the code around this accordingly.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          | 29 ++++++++++++++++++++--
 .../mellanox/mlxsw/spectrum_acl_flex_actions.c     | 22 +++++++++++++---
 2 files changed, 45 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index f6bfdca6bfdb..6d652105dd22 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2332,6 +2332,23 @@ MLXSW_REG_DEFINE(pefa, MLXSW_REG_PEFA_ID, MLXSW_REG_PEFA_LEN);
  */
 MLXSW_ITEM32(reg, pefa, index, 0x00, 0, 24);
 
+/* reg_pefa_a
+ * Index in the KVD Linear Centralized Database.
+ * Activity
+ * For a new entry: set if ca=0, clear if ca=1
+ * Set if a packet lookup has hit on the specific entry
+ * Access: RO
+ */
+MLXSW_ITEM32(reg, pefa, a, 0x04, 29, 1);
+
+/* reg_pefa_ca
+ * Clear activity
+ * When write: activity is according to this field
+ * When read: after reading the activity is cleared according to ca
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, pefa, ca, 0x04, 24, 1);
+
 #define MLXSW_REG_FLEX_ACTION_SET_LEN 0xA8
 
 /* reg_pefa_flex_action_set
@@ -2341,12 +2358,20 @@ MLXSW_ITEM32(reg, pefa, index, 0x00, 0, 24);
  */
 MLXSW_ITEM_BUF(reg, pefa, flex_action_set, 0x08, MLXSW_REG_FLEX_ACTION_SET_LEN);
 
-static inline void mlxsw_reg_pefa_pack(char *payload, u32 index,
+static inline void mlxsw_reg_pefa_pack(char *payload, u32 index, bool ca,
 				       const char *flex_action_set)
 {
 	MLXSW_REG_ZERO(pefa, payload);
 	mlxsw_reg_pefa_index_set(payload, index);
-	mlxsw_reg_pefa_flex_action_set_memcpy_to(payload, flex_action_set);
+	mlxsw_reg_pefa_ca_set(payload, ca);
+	if (flex_action_set)
+		mlxsw_reg_pefa_flex_action_set_memcpy_to(payload,
+							 flex_action_set);
+}
+
+static inline void mlxsw_reg_pefa_unpack(char *payload, bool *p_a)
+{
+	*p_a = mlxsw_reg_pefa_a_get(payload);
 }
 
 /* PTCE-V2 - Policy-Engine TCAM Entry Register Version 2
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index 7649570f3b76..9119a023bc1e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -38,7 +38,7 @@
 #include "spectrum_span.h"
 
 static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
-				     char *enc_actions, bool is_first)
+				     char *enc_actions, bool is_first, bool ca)
 {
 	struct mlxsw_sp *mlxsw_sp = priv;
 	char pefa_pl[MLXSW_REG_PEFA_LEN];
@@ -55,7 +55,7 @@ static int mlxsw_sp_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
 				  1, &kvdl_index);
 	if (err)
 		return err;
-	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, enc_actions);
+	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, ca, enc_actions);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
 	if (err)
 		goto err_pefa_write;
@@ -68,6 +68,20 @@ err_pefa_write:
 	return err;
 }
 
+static int mlxsw_sp1_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
+				      char *enc_actions, bool is_first)
+{
+	return mlxsw_sp_act_kvdl_set_add(priv, p_kvdl_index, enc_actions,
+					 is_first, false);
+}
+
+static int mlxsw_sp2_act_kvdl_set_add(void *priv, u32 *p_kvdl_index,
+				      char *enc_actions, bool is_first)
+{
+	return mlxsw_sp_act_kvdl_set_add(priv, p_kvdl_index, enc_actions,
+					 is_first, true);
+}
+
 static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
 				      bool is_first)
 {
@@ -158,7 +172,7 @@ mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, int span_id, bool ingress)
 }
 
 const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
-	.kvdl_set_add		= mlxsw_sp_act_kvdl_set_add,
+	.kvdl_set_add		= mlxsw_sp1_act_kvdl_set_add,
 	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
 	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
 	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
@@ -169,7 +183,7 @@ const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
 };
 
 const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops = {
-	.kvdl_set_add		= mlxsw_sp_act_kvdl_set_add,
+	.kvdl_set_add		= mlxsw_sp2_act_kvdl_set_add,
 	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
 	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
 	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
-- 
cgit v1.2.3


From 0f27e80aea6e51b69e618ac7d977d55007c13f7d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:36 +0300
Subject: mlxsw: acl: Introduce activity get operation for action block/set

In Spectrum-2, activity cannot be find out by TCAM rule (PTCEv2 register),
but rather by associated action set. For that purpose, extend action ops
to allow query activity from PEFA register. Block activity is decided
according to activity of the first set.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/core_acl_flex_actions.c         |  9 +++++++++
 .../mellanox/mlxsw/core_acl_flex_actions.h         |  3 +++
 .../mellanox/mlxsw/spectrum_acl_flex_actions.c     | 23 ++++++++++++++++++++++
 3 files changed, 35 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 72a6a8a2131e..75ebf5e6b9e1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -441,6 +441,15 @@ u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block)
 }
 EXPORT_SYMBOL(mlxsw_afa_block_first_kvdl_index);
 
+int mlxsw_afa_block_activity_get(struct mlxsw_afa_block *block, bool *activity)
+{
+	u32 kvdl_index = mlxsw_afa_block_first_kvdl_index(block);
+
+	return block->afa->ops->kvdl_set_activity_get(block->afa->ops_priv,
+						      kvdl_index, activity);
+}
+EXPORT_SYMBOL(mlxsw_afa_block_activity_get);
+
 int mlxsw_afa_block_continue(struct mlxsw_afa_block *block)
 {
 	if (block->finished)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index c18249ac28f7..1c7db26e7942 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -45,6 +45,8 @@ struct mlxsw_afa_ops {
 	int (*kvdl_set_add)(void *priv, u32 *p_kvdl_index,
 			    char *enc_actions, bool is_first);
 	void (*kvdl_set_del)(void *priv, u32 kvdl_index, bool is_first);
+	int (*kvdl_set_activity_get)(void *priv, u32 kvdl_index,
+				     bool *activity);
 	int (*kvdl_fwd_entry_add)(void *priv, u32 *p_kvdl_index, u8 local_port);
 	void (*kvdl_fwd_entry_del)(void *priv, u32 kvdl_index);
 	int (*counter_index_get)(void *priv, unsigned int *p_counter_index);
@@ -66,6 +68,7 @@ void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_commit(struct mlxsw_afa_block *block);
 char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block);
 u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block);
+int mlxsw_afa_block_activity_get(struct mlxsw_afa_block *block, bool *activity);
 int mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_jump(struct mlxsw_afa_block *block, u16 group_id);
 int mlxsw_afa_block_terminate(struct mlxsw_afa_block *block);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index 9119a023bc1e..bca0def756cd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -93,6 +93,27 @@ static void mlxsw_sp_act_kvdl_set_del(void *priv, u32 kvdl_index,
 			   1, kvdl_index);
 }
 
+static int mlxsw_sp1_act_kvdl_set_activity_get(void *priv, u32 kvdl_index,
+					       bool *activity)
+{
+	return -EOPNOTSUPP;
+}
+
+static int mlxsw_sp2_act_kvdl_set_activity_get(void *priv, u32 kvdl_index,
+					       bool *activity)
+{
+	struct mlxsw_sp *mlxsw_sp = priv;
+	char pefa_pl[MLXSW_REG_PEFA_LEN];
+	int err;
+
+	mlxsw_reg_pefa_pack(pefa_pl, kvdl_index, true, NULL);
+	err = mlxsw_reg_query(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
+	if (err)
+		return err;
+	mlxsw_reg_pefa_unpack(pefa_pl, activity);
+	return 0;
+}
+
 static int mlxsw_sp_act_kvdl_fwd_entry_add(void *priv, u32 *p_kvdl_index,
 					   u8 local_port)
 {
@@ -174,6 +195,7 @@ mlxsw_sp_act_mirror_del(void *priv, u8 local_in_port, int span_id, bool ingress)
 const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
 	.kvdl_set_add		= mlxsw_sp1_act_kvdl_set_add,
 	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
+	.kvdl_set_activity_get	= mlxsw_sp1_act_kvdl_set_activity_get,
 	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
 	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
 	.counter_index_get	= mlxsw_sp_act_counter_index_get,
@@ -185,6 +207,7 @@ const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops = {
 const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops = {
 	.kvdl_set_add		= mlxsw_sp2_act_kvdl_set_add,
 	.kvdl_set_del		= mlxsw_sp_act_kvdl_set_del,
+	.kvdl_set_activity_get	= mlxsw_sp2_act_kvdl_set_activity_get,
 	.kvdl_fwd_entry_add	= mlxsw_sp_act_kvdl_fwd_entry_add,
 	.kvdl_fwd_entry_del	= mlxsw_sp_act_kvdl_fwd_entry_del,
 	.counter_index_get	= mlxsw_sp_act_counter_index_get,
-- 
cgit v1.2.3


From 3390787b61d85bdc793bd5f42642525dc24684ad Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:37 +0300
Subject: mlxsw: reg: Add Policy-Engine Region Association Register

The PERAR register is used to associate a hw region for region_id's.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 43 +++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 6d652105dd22..c0785476e137 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -39,6 +39,7 @@
 #ifndef _MLXSW_REG_H
 #define _MLXSW_REG_H
 
+#include <linux/kernel.h>
 #include <linux/string.h>
 #include <linux/bitops.h>
 #include <linux/if_vlan.h>
@@ -2481,6 +2482,47 @@ static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
 	mlxsw_reg_ptce2_tcam_region_info_memcpy_to(payload, tcam_region_info);
 }
 
+/* PERAR - Policy-Engine Region Association Register
+ * -------------------------------------------------
+ * This register associates a hw region for region_id's. Changing on the fly
+ * is supported by the device.
+ */
+#define MLXSW_REG_PERAR_ID 0x3026
+#define MLXSW_REG_PERAR_LEN 0x08
+
+MLXSW_REG_DEFINE(perar, MLXSW_REG_PERAR_ID, MLXSW_REG_PERAR_LEN);
+
+/* reg_perar_region_id
+ * Region identifier
+ * Range 0 .. cap_max_regions-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, perar, region_id, 0x00, 0, 16);
+
+static inline unsigned int
+mlxsw_reg_perar_hw_regions_needed(unsigned int block_num)
+{
+	return DIV_ROUND_UP(block_num, 4);
+}
+
+/* reg_perar_hw_region
+ * HW Region
+ * Range 0 .. cap_max_regions-1
+ * Default: hw_region = region_id
+ * For a 8 key block region, 2 consecutive regions are used
+ * For a 12 key block region, 3 consecutive regions are used
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, perar, hw_region, 0x04, 0, 16);
+
+static inline void mlxsw_reg_perar_pack(char *payload, u16 region_id,
+					u16 hw_region)
+{
+	MLXSW_REG_ZERO(perar, payload);
+	mlxsw_reg_perar_region_id_set(payload, region_id);
+	mlxsw_reg_perar_hw_region_set(payload, hw_region);
+}
+
 /* IEDR - Infrastructure Entry Delete Register
  * ----------------------------------------------------
  * This register is used for deleting entries from the entry tables.
@@ -8057,6 +8099,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(prcr),
 	MLXSW_REG(pefa),
 	MLXSW_REG(ptce2),
+	MLXSW_REG(perar),
 	MLXSW_REG(iedr),
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
-- 
cgit v1.2.3


From 481662a8a33645cd0c6568c21759f9ce39266c7f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:38 +0300
Subject: mlxsw: reg: Add Policy-Engine Region Configuration Register

The PERCR register configures the region parameters such as whether to
consult the bloom filter before performing a lookup using a specific
eRP.

For C-TCAM only usage we don't need to accurately set the master mask.
Instead, we can set all of its bits to make sure all the extracted keys
are actually used.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 57 +++++++++++++++++++++++++++++++
 1 file changed, 57 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index c0785476e137..5fa2cdcaecd5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2523,6 +2523,62 @@ static inline void mlxsw_reg_perar_pack(char *payload, u16 region_id,
 	mlxsw_reg_perar_hw_region_set(payload, hw_region);
 }
 
+/* PERCR - Policy-Engine Region Configuration Register
+ * ---------------------------------------------------
+ * This register configures the region parameters. The region_id must be
+ * allocated.
+ */
+#define MLXSW_REG_PERCR_ID 0x302A
+#define MLXSW_REG_PERCR_LEN 0x80
+
+MLXSW_REG_DEFINE(percr, MLXSW_REG_PERCR_ID, MLXSW_REG_PERCR_LEN);
+
+/* reg_percr_region_id
+ * Region identifier.
+ * Range 0..cap_max_regions-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, percr, region_id, 0x00, 0, 16);
+
+/* reg_percr_atcam_ignore_prune
+ * Ignore prune_vector by other A-TCAM rules. Used e.g., for a new rule.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, percr, atcam_ignore_prune, 0x04, 25, 1);
+
+/* reg_percr_ctcam_ignore_prune
+ * Ignore prune_ctcam by other A-TCAM rules. Used e.g., for a new rule.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, percr, ctcam_ignore_prune, 0x04, 24, 1);
+
+/* reg_percr_bf_bypass
+ * Bloom filter bypass.
+ * 0 - Bloom filter is used (default)
+ * 1 - Bloom filter is bypassed. The bypass is an OR condition of
+ * region_id or eRP. See PERPT.bf_bypass
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, percr, bf_bypass, 0x04, 16, 1);
+
+/* reg_percr_master_mask
+ * Master mask. Logical OR mask of all masks of all rules of a region
+ * (both A-TCAM and C-TCAM). When there are no eRPs
+ * (erpt_pointer_valid = 0), then this provides the mask.
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, percr, master_mask, 0x20, 96);
+
+static inline void mlxsw_reg_percr_pack(char *payload, u16 region_id)
+{
+	MLXSW_REG_ZERO(percr, payload);
+	mlxsw_reg_percr_region_id_set(payload, region_id);
+	mlxsw_reg_percr_atcam_ignore_prune_set(payload, false);
+	mlxsw_reg_percr_ctcam_ignore_prune_set(payload, false);
+	mlxsw_reg_percr_bf_bypass_set(payload, true);
+	memset(payload + 0x20, 0xff, 96);
+}
+
 /* IEDR - Infrastructure Entry Delete Register
  * ----------------------------------------------------
  * This register is used for deleting entries from the entry tables.
@@ -8100,6 +8156,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(pefa),
 	MLXSW_REG(ptce2),
 	MLXSW_REG(perar),
+	MLXSW_REG(percr),
 	MLXSW_REG(iedr),
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
-- 
cgit v1.2.3


From f1c7d9cce2a8ec3d6223a2d7b16c6a9c00c52deb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:39 +0300
Subject: mlxsw: reg: Add Policy-Engine Region eRP Register

The PERERP register configures the region eRPs. It can be used, for
example, to enable lookup in the C-TCAM in addition to the A-TCAM.

To be able to perform a lookup in the C-TCAM we need to "use" the eRP
table. This is done by marking the pointer as valid, but zeroing the eRP
table vector.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 71 +++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 5fa2cdcaecd5..6de822bc542b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2579,6 +2579,76 @@ static inline void mlxsw_reg_percr_pack(char *payload, u16 region_id)
 	memset(payload + 0x20, 0xff, 96);
 }
 
+/* PERERP - Policy-Engine Region eRP Register
+ * ------------------------------------------
+ * This register configures the region eRP. The region_id must be
+ * allocated.
+ */
+#define MLXSW_REG_PERERP_ID 0x302B
+#define MLXSW_REG_PERERP_LEN 0x1C
+
+MLXSW_REG_DEFINE(pererp, MLXSW_REG_PERERP_ID, MLXSW_REG_PERERP_LEN);
+
+/* reg_pererp_region_id
+ * Region identifier.
+ * Range 0..cap_max_regions-1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, pererp, region_id, 0x00, 0, 16);
+
+/* reg_pererp_ctcam_le
+ * C-TCAM lookup enable. Reserved when erpt_pointer_valid = 0.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, ctcam_le, 0x04, 28, 1);
+
+/* reg_pererp_erpt_pointer_valid
+ * erpt_pointer is valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, erpt_pointer_valid, 0x10, 31, 1);
+
+/* reg_pererp_erpt_bank_pointer
+ * Pointer to eRP table bank. May be modified at any time.
+ * Range 0..cap_max_erp_table_banks-1
+ * Reserved when erpt_pointer_valid = 0
+ */
+MLXSW_ITEM32(reg, pererp, erpt_bank_pointer, 0x10, 16, 4);
+
+/* reg_pererp_erpt_pointer
+ * Pointer to eRP table within the eRP bank. Can be changed for an
+ * existing region.
+ * Range 0..cap_max_erp_table_size-1
+ * Reserved when erpt_pointer_valid = 0
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, erpt_pointer, 0x10, 0, 8);
+
+/* reg_pererp_erpt_vector
+ * Vector of allowed eRP indexes starting from erpt_pointer within the
+ * erpt_bank_pointer. Next entries will be in next bank.
+ * Note that eRP index is used and not eRP ID.
+ * Reserved when erpt_pointer_valid = 0
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, pererp, erpt_vector, 0x14, 4, 1);
+
+/* reg_pererp_master_rp_id
+ * Master RP ID. When there are no eRPs, then this provides the eRP ID
+ * for the lookup. Can be changed for an existing region.
+ * Reserved when erpt_pointer_valid = 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pererp, master_rp_id, 0x18, 0, 4);
+
+static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id)
+{
+	MLXSW_REG_ZERO(pererp, payload);
+	mlxsw_reg_pererp_region_id_set(payload, region_id);
+	mlxsw_reg_pererp_ctcam_le_set(payload, true);
+	mlxsw_reg_pererp_erpt_pointer_valid_set(payload, true);
+}
+
 /* IEDR - Infrastructure Entry Delete Register
  * ----------------------------------------------------
  * This register is used for deleting entries from the entry tables.
@@ -8157,6 +8227,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(ptce2),
 	MLXSW_REG(perar),
 	MLXSW_REG(percr),
+	MLXSW_REG(pererp),
 	MLXSW_REG(iedr),
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
-- 
cgit v1.2.3


From 7050f439ef6a04daf16f20f8fe5d2d5a4d141992 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:40 +0300
Subject: mlxsw: reg: Add Policy-Engine General Configuration Register

The PGCR register configures general Policy-Engine settings.

Specifically, we are going to use it in order to set the default action
base pointer, which determines where the default action (when there is
no hit) is located for each region.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 6de822bc542b..596fddfb3850 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -1944,6 +1944,28 @@ static inline void mlxsw_reg_cwtpm_pack(char *payload, u8 local_port,
 	mlxsw_reg_cwtpm_ntcp_r_set(payload, profile);
 }
 
+/* PGCR - Policy-Engine General Configuration Register
+ * ---------------------------------------------------
+ * This register configures general Policy-Engine settings.
+ */
+#define MLXSW_REG_PGCR_ID 0x3001
+#define MLXSW_REG_PGCR_LEN 0x20
+
+MLXSW_REG_DEFINE(pgcr, MLXSW_REG_PGCR_ID, MLXSW_REG_PGCR_LEN);
+
+/* reg_pgcr_default_action_pointer_base
+ * Default action pointer base. Each region has a default action pointer
+ * which is equal to default_action_pointer_base + region_id.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, pgcr, default_action_pointer_base, 0x1C, 0, 24);
+
+static inline void mlxsw_reg_pgcr_pack(char *payload, u32 pointer_base)
+{
+	MLXSW_REG_ZERO(pgcr, payload);
+	mlxsw_reg_pgcr_default_action_pointer_base_set(payload, pointer_base);
+}
+
 /* PPBT - Policy-Engine Port Binding Table
  * ---------------------------------------
  * This register is used for configuration of the Port Binding Table.
@@ -8217,6 +8239,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(spvmlr),
 	MLXSW_REG(cwtp),
 	MLXSW_REG(cwtpm),
+	MLXSW_REG(pgcr),
 	MLXSW_REG(ppbt),
 	MLXSW_REG(pacl),
 	MLXSW_REG(pagt),
-- 
cgit v1.2.3


From a6d70a878ed862470e8c0f96f3f3cf41a47077af Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:41 +0300
Subject: mlxsw: spectrum_acl: Prepare for Spectrum-2 block encoding

In Spectrum the key (and mask) block layout is very straight forward and
every block is 16 bytes aligned.

However, in Spectrum-2 the blocks are not even byte aligned, which makes
it difficult to encode them using current method.

Instead, first encode each block and then encode the block in the
general blocks layout.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.c   | 70 ++++++++++++++++++----
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.h   |  3 +-
 .../mellanox/mlxsw/spectrum_acl_flex_keys.c        | 46 ++------------
 3 files changed, 66 insertions(+), 53 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index bf645215f514..5f8485c7640e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -416,24 +416,74 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 }
 EXPORT_SYMBOL(mlxsw_afk_values_add_buf);
 
+static void mlxsw_sp_afk_encode_u32(const struct mlxsw_item *storage_item,
+				    const struct mlxsw_item *output_item,
+				    char *storage, char *output)
+{
+	u32 value;
+
+	value = __mlxsw_item_get32(storage, storage_item, 0);
+	__mlxsw_item_set32(output, output_item, 0, value);
+}
+
+static void mlxsw_sp_afk_encode_buf(const struct mlxsw_item *storage_item,
+				    const struct mlxsw_item *output_item,
+				    char *storage, char *output)
+{
+	char *storage_data = __mlxsw_item_data(storage, storage_item, 0);
+	char *output_data = __mlxsw_item_data(output, output_item, 0);
+	size_t len = output_item->size.bytes;
+
+	memcpy(output_data, storage_data, len);
+}
+
+static void
+mlxsw_sp_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
+			char *output, char *storage)
+{
+	const struct mlxsw_item *storage_item = &elinst->info->item;
+	const struct mlxsw_item *output_item = &elinst->item;
+
+	if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
+		mlxsw_sp_afk_encode_u32(storage_item, output_item,
+					storage, output);
+	else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
+		mlxsw_sp_afk_encode_buf(storage_item, output_item,
+					storage, output);
+}
+
+#define MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE 16
+
 void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
 		      char *key, char *mask)
 {
+	char block_mask[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
+	char block_key[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
 	const struct mlxsw_afk_element_inst *elinst;
 	enum mlxsw_afk_element element;
-	int block_index;
+	int block_index, i;
+
+	for (i = 0; i < key_info->blocks_count; i++) {
+		memset(block_key, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
+		memset(block_mask, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
+
+		mlxsw_afk_element_usage_for_each(element, &values->elusage) {
+			elinst = mlxsw_afk_key_info_elinst_get(key_info,
+							       element,
+							       &block_index);
+			if (!elinst || block_index != i)
+				continue;
+
+			mlxsw_sp_afk_encode_one(elinst, block_key,
+						values->storage.key);
+			mlxsw_sp_afk_encode_one(elinst, block_mask,
+						values->storage.mask);
+		}
 
-	mlxsw_afk_element_usage_for_each(element, &values->elusage) {
-		elinst = mlxsw_afk_key_info_elinst_get(key_info, element,
-						       &block_index);
-		if (!elinst)
-			continue;
-		mlxsw_afk->ops->encode_one(elinst, block_index,
-					   values->storage.key, key);
-		mlxsw_afk->ops->encode_one(elinst, block_index,
-					   values->storage.mask, mask);
+		mlxsw_afk->ops->encode_block(block_key, i, key);
+		mlxsw_afk->ops->encode_block(block_mask, i, mask);
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 441636cd13d8..2ffde915349b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -219,8 +219,7 @@ struct mlxsw_afk;
 struct mlxsw_afk_ops {
 	const struct mlxsw_afk_block *blocks;
 	unsigned int blocks_count;
-	void (*encode_one)(const struct mlxsw_afk_element_inst *elinst,
-			   int block_index, char *storage, char *output);
+	void (*encode_block)(char *block, int block_index, char *output);
 };
 
 struct mlxsw_afk *mlxsw_afk_create(unsigned int max_blocks,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index fe46338f0087..21be0987a93a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -127,50 +127,21 @@ static const struct mlxsw_afk_block mlxsw_sp1_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0xB0, mlxsw_sp_afk_element_info_packet_type),
 };
 
-static void mlxsw_sp1_afk_encode_u32(const struct mlxsw_item *storage_item,
-				     const struct mlxsw_item *output_item,
-				     char *storage, char *output_indexed)
-{
-	u32 value;
-
-	value = __mlxsw_item_get32(storage, storage_item, 0);
-	__mlxsw_item_set32(output_indexed, output_item, 0, value);
-}
-
-static void mlxsw_sp1_afk_encode_buf(const struct mlxsw_item *storage_item,
-				     const struct mlxsw_item *output_item,
-				     char *storage, char *output_indexed)
-{
-	char *storage_data = __mlxsw_item_data(storage, storage_item, 0);
-	char *output_data = __mlxsw_item_data(output_indexed, output_item, 0);
-	size_t len = output_item->size.bytes;
-
-	memcpy(output_data, storage_data, len);
-}
-
 #define MLXSW_SP1_AFK_KEY_BLOCK_SIZE 16
 
-static void
-mlxsw_sp1_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
-			 int block_index, char *storage, char *output)
+static void mlxsw_sp1_afk_encode_block(char *block, int block_index,
+				       char *output)
 {
 	unsigned int offset = block_index * MLXSW_SP1_AFK_KEY_BLOCK_SIZE;
 	char *output_indexed = output + offset;
-	const struct mlxsw_item *storage_item = &elinst->info->item;
-	const struct mlxsw_item *output_item = &elinst->item;
-
-	if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_U32)
-		mlxsw_sp1_afk_encode_u32(storage_item, output_item,
-					 storage, output_indexed);
-	else if (elinst->type == MLXSW_AFK_ELEMENT_TYPE_BUF)
-		mlxsw_sp1_afk_encode_buf(storage_item, output_item,
-					 storage, output_indexed);
+
+	memcpy(output_indexed, block, MLXSW_SP1_AFK_KEY_BLOCK_SIZE);
 }
 
 const struct mlxsw_afk_ops mlxsw_sp1_afk_ops = {
 	.blocks		= mlxsw_sp1_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp1_afk_blocks),
-	.encode_one	= mlxsw_sp1_afk_encode_one,
+	.encode_block	= mlxsw_sp1_afk_encode_block,
 };
 
 static struct mlxsw_afk_element_inst mlxsw_sp_afk_element_info_mac_0[] = {
@@ -271,14 +242,7 @@ static const struct mlxsw_afk_block mlxsw_sp2_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0x92, mlxsw_sp_afk_element_info_l4_2),
 };
 
-static void
-mlxsw_sp2_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
-			 int block_index, char *storage, char *output)
-{
-}
-
 const struct mlxsw_afk_ops mlxsw_sp2_afk_ops = {
 	.blocks		= mlxsw_sp2_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp2_afk_blocks),
-	.encode_one	= mlxsw_sp2_afk_encode_one,
 };
-- 
cgit v1.2.3


From 7a921a1e585a846e039239238aaec0a516477e14 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:42 +0300
Subject: mlxsw: spectrum_acl: Add support for Spectrum-2 block encoding

Encode each flexible key block in the general block scheme according its
block index.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/spectrum_acl_flex_keys.c        | 68 ++++++++++++++++++++++
 1 file changed, 68 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index 21be0987a93a..aa8927cee376 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -242,7 +242,75 @@ static const struct mlxsw_afk_block mlxsw_sp2_afk_blocks[] = {
 	MLXSW_AFK_BLOCK(0x92, mlxsw_sp_afk_element_info_l4_2),
 };
 
+#define MLXSW_SP2_AFK_BITS_PER_BLOCK 36
+
+/* A block in Spectrum-2 is of the following form:
+ *
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ * |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |35|34|33|32|
+ * +-----------------------------------------------------------------------------------------------+
+ * |31|30|29|28|27|26|25|24|23|22|21|20|19|18|17|16|15|14|13|12|11|10| 9| 8| 7| 6| 5| 4| 3| 2| 1| 0|
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ */
+MLXSW_ITEM64(sp2_afk, block, value, 0x00, 0, MLXSW_SP2_AFK_BITS_PER_BLOCK);
+
+/* The key / mask block layout in Spectrum-2 is of the following form:
+ *
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ * |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |  |                block11_high                   |
+ * +-----------------------------------------------------------------------------------------------+
+ * |                    block11_low                               |         block10_high           |
+ * +--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+--+
+ * ...
+ */
+
+struct mlxsw_sp2_afk_block_layout {
+	unsigned short offset;
+	struct mlxsw_item item;
+};
+
+#define MLXSW_SP2_AFK_BLOCK_LAYOUT(_block, _offset, _shift)			\
+	{									\
+		.offset = _offset,						\
+		{								\
+			.shift = _shift,					\
+			.size = {.bits = MLXSW_SP2_AFK_BITS_PER_BLOCK},		\
+			.name = #_block,					\
+		}								\
+	}									\
+
+static const struct mlxsw_sp2_afk_block_layout mlxsw_sp2_afk_blocks_layout[] = {
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block0, 0x30, 0),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block1, 0x2C, 4),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block2, 0x28, 8),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block3, 0x24, 12),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block4, 0x20, 16),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block5, 0x1C, 20),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block6, 0x18, 24),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block7, 0x14, 28),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block8, 0x0C, 0),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block9, 0x08, 4),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block10, 0x04, 8),
+	MLXSW_SP2_AFK_BLOCK_LAYOUT(block11, 0x00, 12),
+};
+
+static void mlxsw_sp2_afk_encode_block(char *block, int block_index,
+				       char *output)
+{
+	u64 block_value = mlxsw_sp2_afk_block_value_get(block);
+	const struct mlxsw_sp2_afk_block_layout *block_layout;
+
+	if (WARN_ON(block_index < 0 ||
+		    block_index >= ARRAY_SIZE(mlxsw_sp2_afk_blocks_layout)))
+		return;
+
+	block_layout = &mlxsw_sp2_afk_blocks_layout[block_index];
+	__mlxsw_item_set64(output + block_layout->offset,
+			   &block_layout->item, 0, block_value);
+}
+
 const struct mlxsw_afk_ops mlxsw_sp2_afk_ops = {
 	.blocks		= mlxsw_sp2_afk_blocks,
 	.blocks_count	= ARRAY_SIZE(mlxsw_sp2_afk_blocks),
+	.encode_block	= mlxsw_sp2_afk_encode_block,
 };
-- 
cgit v1.2.3


From a6b9c87daf5d1de84d915edb9f240276269df1f2 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:43 +0300
Subject: mlxsw: spectrum_acl: Add region association callback

In Spectrum-2, ACL regions that use 8 or 12 key blocks require several
consecutive hardware regions.

In order to allow defragmentation, the device stores a mapping from a
logical region ID to an hardware region ID, which is similar to the page
table that is used to translate virtual addresses to physical addresses.

Add the region association callback to the region create sequence and
implement it as a NOP in Spectrum which does not require it.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c | 8 ++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c  | 5 +++++
 3 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index dee9c1822727..f51831e33757 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -624,6 +624,8 @@ struct mlxsw_sp_acl_tcam_ops {
 	int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			   struct mlxsw_sp_acl_tcam_region *region);
 	void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv);
+	int (*region_associate)(struct mlxsw_sp *mlxsw_sp,
+				struct mlxsw_sp_acl_tcam_region *region);
 	size_t chunk_priv_size;
 	void (*chunk_init)(void *region_priv, void *chunk_priv,
 			   unsigned int priority);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 04f0c9cfae24..d339ec43d79c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -151,6 +151,13 @@ mlxsw_sp1_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv)
 	mlxsw_sp_acl_ctcam_region_fini(&region->cregion);
 }
 
+static int
+mlxsw_sp1_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_acl_tcam_region *region)
+{
+	return 0;
+}
+
 static void mlxsw_sp1_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
 					  unsigned int priority)
 {
@@ -235,6 +242,7 @@ const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops = {
 	.region_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_region),
 	.region_init		= mlxsw_sp1_acl_tcam_region_init,
 	.region_fini		= mlxsw_sp1_acl_tcam_region_fini,
+	.region_associate	= mlxsw_sp1_acl_tcam_region_associate,
 	.chunk_priv_size	= sizeof(struct mlxsw_sp1_acl_tcam_chunk),
 	.chunk_init		= mlxsw_sp1_acl_tcam_chunk_init,
 	.chunk_fini		= mlxsw_sp1_acl_tcam_chunk_fini,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 53fe51a8d720..e06d7d9e5b7f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -547,6 +547,10 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_region_id_get;
 
+	err = ops->region_associate(mlxsw_sp, region);
+	if (err)
+		goto err_tcam_region_associate;
+
 	region->key_type = ops->key_type;
 	err = mlxsw_sp_acl_tcam_region_alloc(mlxsw_sp, region);
 	if (err)
@@ -567,6 +571,7 @@ err_tcam_region_init:
 err_tcam_region_enable:
 	mlxsw_sp_acl_tcam_region_free(mlxsw_sp, region);
 err_tcam_region_alloc:
+err_tcam_region_associate:
 	mlxsw_sp_acl_tcam_region_id_put(tcam, region->id);
 err_region_id_get:
 	mlxsw_afk_key_info_put(region->key_info);
-- 
cgit v1.2.3


From 9912e6b8c256d0f08180e7d4f141c0c39d41f329 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:44 +0300
Subject: mlxsw: spectrum_acl: Add initial Spectrum-2 ACL implementation

Utilize only C-TCAM for now. Do very minimal A-TCAM initialization in
order to make C-TCAM work.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |   3 +-
 .../mellanox/mlxsw/core_acl_flex_actions.c         |   6 +
 .../mellanox/mlxsw/core_acl_flex_actions.h         |   1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   3 +
 .../ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c   | 222 +++++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   |  95 +++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |   5 +
 7 files changed, 334 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index e1b72e1a0c2a..4a1069166119 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -18,7 +18,8 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum1_kvdl.o spectrum2_kvdl.o \
 				   spectrum_kvdl.o \
 				   spectrum_acl_tcam.o spectrum_acl_ctcam.o \
-				   spectrum1_acl_tcam.o \
+				   spectrum_acl_atcam.o \
+				   spectrum1_acl_tcam.o spectrum2_acl_tcam.o \
 				   spectrum_acl.o \
 				   spectrum_flower.o spectrum_cnt.o \
 				   spectrum_fid.o spectrum_ipip.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 75ebf5e6b9e1..9a473628831e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -430,6 +430,12 @@ char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block)
 }
 EXPORT_SYMBOL(mlxsw_afa_block_first_set);
 
+char *mlxsw_afa_block_cur_set(struct mlxsw_afa_block *block)
+{
+	return block->cur_set->ht_key.enc_actions;
+}
+EXPORT_SYMBOL(mlxsw_afa_block_cur_set);
+
 u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block)
 {
 	/* First set is never in KVD linear. So the first set
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index 1c7db26e7942..69628582fb4b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -67,6 +67,7 @@ struct mlxsw_afa_block *mlxsw_afa_block_create(struct mlxsw_afa *mlxsw_afa);
 void mlxsw_afa_block_destroy(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_commit(struct mlxsw_afa_block *block);
 char *mlxsw_afa_block_first_set(struct mlxsw_afa_block *block);
+char *mlxsw_afa_block_cur_set(struct mlxsw_afa_block *block);
 u32 mlxsw_afa_block_first_kvdl_index(struct mlxsw_afa_block *block);
 int mlxsw_afa_block_activity_get(struct mlxsw_afa_block *block, bool *activity);
 int mlxsw_afa_block_continue(struct mlxsw_afa_block *block);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index f51831e33757..016058961542 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -646,6 +646,9 @@ struct mlxsw_sp_acl_tcam_ops {
 /* spectrum1_acl_tcam.c */
 extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp1_acl_tcam_ops;
 
+/* spectrum2_acl_tcam.c */
+extern const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops;
+
 /* spectrum_acl_flex_actions.c */
 extern const struct mlxsw_afa_ops mlxsw_sp1_act_afa_ops;
 extern const struct mlxsw_afa_ops mlxsw_sp2_act_afa_ops;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
new file mode 100644
index 000000000000..d7f1fb35ea2a
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -0,0 +1,222 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+#include "core_acl_flex_actions.h"
+
+struct mlxsw_sp2_acl_tcam {
+	u32 kvdl_index;
+	unsigned int kvdl_count;
+};
+
+struct mlxsw_sp2_acl_tcam_region {
+	struct mlxsw_sp_acl_ctcam_region cregion;
+};
+
+struct mlxsw_sp2_acl_tcam_chunk {
+	struct mlxsw_sp_acl_ctcam_chunk cchunk;
+};
+
+struct mlxsw_sp2_acl_tcam_entry {
+	struct mlxsw_sp_acl_ctcam_entry centry;
+	struct mlxsw_afa_block *act_block;
+};
+
+static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
+				   struct mlxsw_sp_acl_tcam *_tcam)
+{
+	struct mlxsw_sp2_acl_tcam *tcam = priv;
+	struct mlxsw_afa_block *afa_block;
+	char pefa_pl[MLXSW_REG_PEFA_LEN];
+	char pgcr_pl[MLXSW_REG_PGCR_LEN];
+	char *enc_actions;
+	int i;
+	int err;
+
+	tcam->kvdl_count = _tcam->max_regions;
+	err = mlxsw_sp_kvdl_alloc(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+				  tcam->kvdl_count, &tcam->kvdl_index);
+	if (err)
+		return err;
+
+	/* Create flex action block, set default action (continue)
+	 * but don't commit. We need just the current set encoding
+	 * to be written using PEFA register to all indexes for all regions.
+	 */
+	afa_block = mlxsw_afa_block_create(mlxsw_sp->afa);
+	if (!afa_block) {
+		err = -ENOMEM;
+		goto err_afa_block;
+	}
+	err = mlxsw_afa_block_continue(afa_block);
+	if (WARN_ON(err))
+		goto err_afa_block_continue;
+	enc_actions = mlxsw_afa_block_cur_set(afa_block);
+
+	for (i = 0; i < tcam->kvdl_count; i++) {
+		mlxsw_reg_pefa_pack(pefa_pl, tcam->kvdl_index + i,
+				    true, enc_actions);
+		err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pefa), pefa_pl);
+		if (err)
+			goto err_pefa_write;
+	}
+	mlxsw_reg_pgcr_pack(pgcr_pl, tcam->kvdl_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pgcr), pgcr_pl);
+	if (err)
+		goto err_pgcr_write;
+
+	mlxsw_afa_block_destroy(afa_block);
+	return 0;
+
+err_pgcr_write:
+err_pefa_write:
+err_afa_block_continue:
+	mlxsw_afa_block_destroy(afa_block);
+err_afa_block:
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   tcam->kvdl_count, tcam->kvdl_index);
+	return err;
+}
+
+static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
+{
+	struct mlxsw_sp2_acl_tcam *tcam = priv;
+
+	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
+			   tcam->kvdl_count, tcam->kvdl_index);
+}
+
+static int
+mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			       struct mlxsw_sp_acl_tcam_region *_region)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	int err;
+
+	err = mlxsw_sp_acl_atcam_region_init(mlxsw_sp, _region);
+	if (err)
+		return err;
+	return mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &region->cregion,
+					      _region);
+}
+
+static void
+mlxsw_sp2_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+
+	mlxsw_sp_acl_ctcam_region_fini(&region->cregion);
+}
+
+static int
+mlxsw_sp2_acl_tcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_acl_tcam_region *region)
+{
+	return mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id);
+}
+
+static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
+					  unsigned int priority)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion, &chunk->cchunk,
+				      priority);
+}
+
+static void mlxsw_sp2_acl_tcam_chunk_fini(void *chunk_priv)
+{
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+
+	mlxsw_sp_acl_ctcam_chunk_fini(&chunk->cchunk);
+}
+
+static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+					void *region_priv, void *chunk_priv,
+					void *entry_priv,
+					struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	entry->act_block = rulei->act_block;
+	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
+					    &chunk->cchunk, &entry->centry,
+					    rulei, true);
+}
+
+static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+					 void *region_priv, void *chunk_priv,
+					 void *entry_priv)
+{
+	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->cregion,
+				     &chunk->cchunk, &entry->centry);
+}
+
+static int
+mlxsw_sp2_acl_tcam_entry_activity_get(struct mlxsw_sp *mlxsw_sp,
+				      void *region_priv, void *entry_priv,
+				      bool *activity)
+{
+	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
+
+	return mlxsw_afa_block_activity_get(entry->act_block, activity);
+}
+
+const struct mlxsw_sp_acl_tcam_ops mlxsw_sp2_acl_tcam_ops = {
+	.key_type		= MLXSW_REG_PTAR_KEY_TYPE_FLEX2,
+	.priv_size		= sizeof(struct mlxsw_sp2_acl_tcam),
+	.init			= mlxsw_sp2_acl_tcam_init,
+	.fini			= mlxsw_sp2_acl_tcam_fini,
+	.region_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_region),
+	.region_init		= mlxsw_sp2_acl_tcam_region_init,
+	.region_fini		= mlxsw_sp2_acl_tcam_region_fini,
+	.region_associate	= mlxsw_sp2_acl_tcam_region_associate,
+	.chunk_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_chunk),
+	.chunk_init		= mlxsw_sp2_acl_tcam_chunk_init,
+	.chunk_fini		= mlxsw_sp2_acl_tcam_chunk_fini,
+	.entry_priv_size	= sizeof(struct mlxsw_sp2_acl_tcam_entry),
+	.entry_add		= mlxsw_sp2_acl_tcam_entry_add,
+	.entry_del		= mlxsw_sp2_acl_tcam_entry_del,
+	.entry_activity_get	= mlxsw_sp2_acl_tcam_entry_activity_get,
+};
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
new file mode 100644
index 000000000000..b1b3b0e0c00e
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -0,0 +1,95 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
+ * Copyright (c) 2018 Ido Schimmel <idosch@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+#include "reg.h"
+#include "core.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+					u16 region_id)
+{
+	char perar_pl[MLXSW_REG_PERAR_LEN];
+	/* For now, just assume that every region has 12 key blocks */
+	u16 hw_region = region_id * 3;
+	u64 max_regions;
+
+	max_regions = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_REGIONS);
+	if (hw_region >= max_regions)
+		return -ENOBUFS;
+
+	mlxsw_reg_perar_pack(perar_pl, region_id, hw_region);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perar), perar_pl);
+}
+
+static int mlxsw_sp_acl_atcam_region_param_init(struct mlxsw_sp *mlxsw_sp,
+						u16 region_id)
+{
+	char percr_pl[MLXSW_REG_PERCR_LEN];
+
+	mlxsw_reg_percr_pack(percr_pl, region_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl);
+}
+
+static int
+mlxsw_sp_acl_atcam_region_erp_init(struct mlxsw_sp *mlxsw_sp,
+				   u16 region_id)
+{
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, region_id);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_tcam_region *region)
+{
+	int err;
+
+	err = mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id);
+	if (err)
+		return err;
+	err = mlxsw_sp_acl_atcam_region_param_init(mlxsw_sp, region->id);
+	if (err)
+		return err;
+	err = mlxsw_sp_acl_atcam_region_erp_init(mlxsw_sp, region->id);
+	if (err)
+		return err;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index cef769764505..68551da2221d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -143,4 +143,9 @@ mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry)
 	return centry->parman_item.index;
 }
 
+int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
+					u16 region_id);
+int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_tcam_region *region);
+
 #endif
-- 
cgit v1.2.3


From c3ab435466d5109b2c7525a3b90107d4d9e918fc Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 18 Jul 2018 11:14:45 +0300
Subject: mlxsw: spectrum: Extend to support Spectrum-2 ASIC

Extend existing driver for Spectrum ASIC to support Spectrum-2 ASIC.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.h      |   1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 170 ++++++++++++++++++++-----
 2 files changed, 139 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index d65582325cd5..7461f8fe1133 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -39,6 +39,7 @@
 
 #define PCI_DEVICE_ID_MELLANOX_SWITCHX2		0xc738
 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM		0xcb84
+#define PCI_DEVICE_ID_MELLANOX_SPECTRUM2	0xcf6c
 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB		0xcb20
 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB2	0xcf08
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 62c5f1c5bf62..317c92d6496e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -91,7 +91,8 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
 	"." __stringify(MLXSW_SP1_FWREV_MINOR) \
 	"." __stringify(MLXSW_SP1_FWREV_SUBMINOR) ".mfa2"
 
-static const char mlxsw_sp_driver_name[] = "mlxsw_spectrum";
+static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum";
+static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2";
 static const char mlxsw_sp_driver_version[] = "1.0";
 
 /* tx_hdr_version
@@ -1727,7 +1728,8 @@ static void mlxsw_sp_port_get_drvinfo(struct net_device *dev,
 	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
 	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
 
-	strlcpy(drvinfo->driver, mlxsw_sp_driver_name, sizeof(drvinfo->driver));
+	strlcpy(drvinfo->driver, mlxsw_sp->bus_info->device_kind,
+		sizeof(drvinfo->driver));
 	strlcpy(drvinfo->version, mlxsw_sp_driver_version,
 		sizeof(drvinfo->version));
 	snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version),
@@ -3696,14 +3698,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
 	int err;
 
-	mlxsw_sp->req_rev = &mlxsw_sp1_fw_rev;
-	mlxsw_sp->fw_filename = MLXSW_SP1_FW_FILENAME;
-	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
-	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
-	mlxsw_sp->afk_ops = &mlxsw_sp1_afk_ops;
-	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
-	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
-
 	mlxsw_sp->core = mlxsw_core;
 	mlxsw_sp->bus_info = mlxsw_bus_info;
 
@@ -3842,6 +3836,36 @@ err_fids_init:
 	return err;
 }
 
+static int mlxsw_sp1_init(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_bus_info *mlxsw_bus_info)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	mlxsw_sp->req_rev = &mlxsw_sp1_fw_rev;
+	mlxsw_sp->fw_filename = MLXSW_SP1_FW_FILENAME;
+	mlxsw_sp->kvdl_ops = &mlxsw_sp1_kvdl_ops;
+	mlxsw_sp->afa_ops = &mlxsw_sp1_act_afa_ops;
+	mlxsw_sp->afk_ops = &mlxsw_sp1_afk_ops;
+	mlxsw_sp->mr_tcam_ops = &mlxsw_sp1_mr_tcam_ops;
+	mlxsw_sp->acl_tcam_ops = &mlxsw_sp1_acl_tcam_ops;
+
+	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
+}
+
+static int mlxsw_sp2_init(struct mlxsw_core *mlxsw_core,
+			  const struct mlxsw_bus_info *mlxsw_bus_info)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
+
+	mlxsw_sp->kvdl_ops = &mlxsw_sp2_kvdl_ops;
+	mlxsw_sp->afa_ops = &mlxsw_sp2_act_afa_ops;
+	mlxsw_sp->afk_ops = &mlxsw_sp2_afk_ops;
+	mlxsw_sp->mr_tcam_ops = &mlxsw_sp2_mr_tcam_ops;
+	mlxsw_sp->acl_tcam_ops = &mlxsw_sp2_acl_tcam_ops;
+
+	return mlxsw_sp_init(mlxsw_core, mlxsw_bus_info);
+}
+
 static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 {
 	struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core);
@@ -3862,7 +3886,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core)
 	mlxsw_sp_kvdl_fini(mlxsw_sp);
 }
 
-static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
+static const struct mlxsw_config_profile mlxsw_sp1_config_profile = {
 	.used_max_mid			= 1,
 	.max_mid			= MLXSW_SP_MID_MAX,
 	.used_flood_tables		= 1,
@@ -3888,6 +3912,28 @@ static const struct mlxsw_config_profile mlxsw_sp_config_profile = {
 	},
 };
 
+static const struct mlxsw_config_profile mlxsw_sp2_config_profile = {
+	.used_max_mid			= 1,
+	.max_mid			= MLXSW_SP_MID_MAX,
+	.used_flood_tables		= 1,
+	.used_flood_mode		= 1,
+	.flood_mode			= 3,
+	.max_fid_offset_flood_tables	= 3,
+	.fid_offset_flood_table_size	= VLAN_N_VID - 1,
+	.max_fid_flood_tables		= 3,
+	.fid_flood_table_size		= MLXSW_SP_FID_8021D_MAX,
+	.used_max_ib_mc			= 1,
+	.max_ib_mc			= 0,
+	.used_max_pkey			= 1,
+	.max_pkey			= 0,
+	.swid_config			= {
+		{
+			.used_type	= 1,
+			.type		= MLXSW_PORT_SWID_TYPE_ETH,
+		}
+	},
+};
+
 static void
 mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core,
 				      struct devlink_resource_size_params *kvd_size_params,
@@ -3924,7 +3970,7 @@ mlxsw_sp_resource_size_params_prepare(struct mlxsw_core *mlxsw_core,
 					  DEVLINK_RESOURCE_UNIT_ENTRY);
 }
 
-static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
+static int mlxsw_sp1_resources_kvd_register(struct mlxsw_core *mlxsw_core)
 {
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 	struct devlink_resource_size_params hash_single_size_params;
@@ -3935,7 +3981,7 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 	const struct mlxsw_config_profile *profile;
 	int err;
 
-	profile = &mlxsw_sp_config_profile;
+	profile = &mlxsw_sp1_config_profile;
 	if (!MLXSW_CORE_RES_VALID(mlxsw_core, KVD_SIZE))
 		return -EIO;
 
@@ -3990,6 +4036,16 @@ static int mlxsw_sp_resources_register(struct mlxsw_core *mlxsw_core)
 	return 0;
 }
 
+static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core)
+{
+	return mlxsw_sp1_resources_kvd_register(mlxsw_core);
+}
+
+static int mlxsw_sp2_resources_register(struct mlxsw_core *mlxsw_core)
+{
+	return 0;
+}
+
 static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 				  const struct mlxsw_config_profile *profile,
 				  u64 *p_single_size, u64 *p_double_size,
@@ -4045,10 +4101,10 @@ static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core,
 	return 0;
 }
 
-static struct mlxsw_driver mlxsw_sp_driver = {
-	.kind				= mlxsw_sp_driver_name,
+static struct mlxsw_driver mlxsw_sp1_driver = {
+	.kind				= mlxsw_sp1_driver_name,
 	.priv_size			= sizeof(struct mlxsw_sp),
-	.init				= mlxsw_sp_init,
+	.init				= mlxsw_sp1_init,
 	.fini				= mlxsw_sp_fini,
 	.basic_trap_groups_set		= mlxsw_sp_basic_trap_groups_set,
 	.port_split			= mlxsw_sp_port_split,
@@ -4064,10 +4120,35 @@ static struct mlxsw_driver mlxsw_sp_driver = {
 	.sb_occ_port_pool_get		= mlxsw_sp_sb_occ_port_pool_get,
 	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
 	.txhdr_construct		= mlxsw_sp_txhdr_construct,
-	.resources_register		= mlxsw_sp_resources_register,
+	.resources_register		= mlxsw_sp1_resources_register,
 	.kvd_sizes_get			= mlxsw_sp_kvd_sizes_get,
 	.txhdr_len			= MLXSW_TXHDR_LEN,
-	.profile			= &mlxsw_sp_config_profile,
+	.profile			= &mlxsw_sp1_config_profile,
+	.res_query_enabled		= true,
+};
+
+static struct mlxsw_driver mlxsw_sp2_driver = {
+	.kind				= mlxsw_sp2_driver_name,
+	.priv_size			= sizeof(struct mlxsw_sp),
+	.init				= mlxsw_sp2_init,
+	.fini				= mlxsw_sp_fini,
+	.basic_trap_groups_set		= mlxsw_sp_basic_trap_groups_set,
+	.port_split			= mlxsw_sp_port_split,
+	.port_unsplit			= mlxsw_sp_port_unsplit,
+	.sb_pool_get			= mlxsw_sp_sb_pool_get,
+	.sb_pool_set			= mlxsw_sp_sb_pool_set,
+	.sb_port_pool_get		= mlxsw_sp_sb_port_pool_get,
+	.sb_port_pool_set		= mlxsw_sp_sb_port_pool_set,
+	.sb_tc_pool_bind_get		= mlxsw_sp_sb_tc_pool_bind_get,
+	.sb_tc_pool_bind_set		= mlxsw_sp_sb_tc_pool_bind_set,
+	.sb_occ_snapshot		= mlxsw_sp_sb_occ_snapshot,
+	.sb_occ_max_clear		= mlxsw_sp_sb_occ_max_clear,
+	.sb_occ_port_pool_get		= mlxsw_sp_sb_occ_port_pool_get,
+	.sb_occ_tc_port_bind_get	= mlxsw_sp_sb_occ_tc_port_bind_get,
+	.txhdr_construct		= mlxsw_sp_txhdr_construct,
+	.resources_register		= mlxsw_sp2_resources_register,
+	.txhdr_len			= MLXSW_TXHDR_LEN,
+	.profile			= &mlxsw_sp2_config_profile,
 	.res_query_enabled		= true,
 };
 
@@ -4846,14 +4927,24 @@ static struct notifier_block mlxsw_sp_inet6addr_nb __read_mostly = {
 	.notifier_call = mlxsw_sp_inet6addr_event,
 };
 
-static const struct pci_device_id mlxsw_sp_pci_id_table[] = {
+static const struct pci_device_id mlxsw_sp1_pci_id_table[] = {
 	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM), 0},
 	{0, },
 };
 
-static struct pci_driver mlxsw_sp_pci_driver = {
-	.name = mlxsw_sp_driver_name,
-	.id_table = mlxsw_sp_pci_id_table,
+static struct pci_driver mlxsw_sp1_pci_driver = {
+	.name = mlxsw_sp1_driver_name,
+	.id_table = mlxsw_sp1_pci_id_table,
+};
+
+static const struct pci_device_id mlxsw_sp2_pci_id_table[] = {
+	{PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM2), 0},
+	{0, },
+};
+
+static struct pci_driver mlxsw_sp2_pci_driver = {
+	.name = mlxsw_sp2_driver_name,
+	.id_table = mlxsw_sp2_pci_id_table,
 };
 
 static int __init mlxsw_sp_module_init(void)
@@ -4865,19 +4956,31 @@ static int __init mlxsw_sp_module_init(void)
 	register_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	register_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 
-	err = mlxsw_core_driver_register(&mlxsw_sp_driver);
+	err = mlxsw_core_driver_register(&mlxsw_sp1_driver);
+	if (err)
+		goto err_sp1_core_driver_register;
+
+	err = mlxsw_core_driver_register(&mlxsw_sp2_driver);
+	if (err)
+		goto err_sp2_core_driver_register;
+
+	err = mlxsw_pci_driver_register(&mlxsw_sp1_pci_driver);
 	if (err)
-		goto err_core_driver_register;
+		goto err_sp1_pci_driver_register;
 
-	err = mlxsw_pci_driver_register(&mlxsw_sp_pci_driver);
+	err = mlxsw_pci_driver_register(&mlxsw_sp2_pci_driver);
 	if (err)
-		goto err_pci_driver_register;
+		goto err_sp2_pci_driver_register;
 
 	return 0;
 
-err_pci_driver_register:
-	mlxsw_core_driver_unregister(&mlxsw_sp_driver);
-err_core_driver_register:
+err_sp2_pci_driver_register:
+	mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver);
+err_sp1_pci_driver_register:
+	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
+err_sp2_core_driver_register:
+	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
+err_sp1_core_driver_register:
 	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
@@ -4887,8 +4990,10 @@ err_core_driver_register:
 
 static void __exit mlxsw_sp_module_exit(void)
 {
-	mlxsw_pci_driver_unregister(&mlxsw_sp_pci_driver);
-	mlxsw_core_driver_unregister(&mlxsw_sp_driver);
+	mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver);
+	mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver);
+	mlxsw_core_driver_unregister(&mlxsw_sp2_driver);
+	mlxsw_core_driver_unregister(&mlxsw_sp1_driver);
 	unregister_inet6addr_notifier(&mlxsw_sp_inet6addr_nb);
 	unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb);
 	unregister_inetaddr_notifier(&mlxsw_sp_inetaddr_nb);
@@ -4901,5 +5006,6 @@ module_exit(mlxsw_sp_module_exit);
 MODULE_LICENSE("Dual BSD/GPL");
 MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox Spectrum driver");
-MODULE_DEVICE_TABLE(pci, mlxsw_sp_pci_id_table);
+MODULE_DEVICE_TABLE(pci, mlxsw_sp1_pci_id_table);
+MODULE_DEVICE_TABLE(pci, mlxsw_sp2_pci_id_table);
 MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME);
-- 
cgit v1.2.3


From fa145d5dfd612ac318a1eb4b443af55e0f5c8ba7 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Wed, 18 Jul 2018 17:36:12 +0530
Subject: cxgb4: display number of rx and tx pages free

display free rx and tx page count in the meminfo of
an adapter.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 22 +++++++++++++++-------
 drivers/net/ethernet/chelsio/cxgb4/t4_regs.h       | 14 ++++++++++++++
 2 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 511606fd1b20..631b78baedbb 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2858,6 +2858,7 @@ static int meminfo_show(struct seq_file *seq, void *v)
 {
 	static const char * const memory[] = { "EDC0:", "EDC1:", "MC:",
 					       "MC0:", "MC1:", "HMA:"};
+	unsigned int free_rx_cnt, free_tx_cnt;
 	struct adapter *adap = seq->private;
 	struct cudbg_meminfo meminfo;
 	int i, rc;
@@ -2889,13 +2890,20 @@ static int meminfo_show(struct seq_file *seq, void *v)
 	mem_region_show(seq, "uP Extmem2:", meminfo.up_extmem2_lo,
 			meminfo.up_extmem2_hi);
 
-	seq_printf(seq, "\n%u Rx pages of size %uKiB for %u channels\n",
-		   meminfo.rx_pages_data[0], meminfo.rx_pages_data[1],
-		   meminfo.rx_pages_data[2]);
-
-	seq_printf(seq, "%u Tx pages of size %u%ciB for %u channels\n",
-		   meminfo.tx_pages_data[0], meminfo.tx_pages_data[1],
-		   meminfo.tx_pages_data[2], meminfo.tx_pages_data[3]);
+	for (i = 0, free_rx_cnt = 0; i < 2; i++)
+		free_rx_cnt += FREERXPAGECOUNT_G
+				      (t4_read_reg(adap, TP_FLM_FREE_RX_CNT_A));
+	seq_printf(seq, "\n%u Rx pages (%u free) of size %uKiB for %u channels\n",
+		   meminfo.rx_pages_data[0], free_rx_cnt,
+		   meminfo.rx_pages_data[1], meminfo.rx_pages_data[2]);
+
+	for (i = 0, free_tx_cnt = 0; i < 4; i++)
+		free_tx_cnt += FREETXPAGECOUNT_G
+				      (t4_read_reg(adap, TP_FLM_FREE_TX_CNT_A));
+	seq_printf(seq, "%u Tx pages (%u free) of size %u%ciB for %u channels\n",
+		   meminfo.tx_pages_data[0], free_tx_cnt,
+		   meminfo.tx_pages_data[1], meminfo.tx_pages_data[2],
+		   meminfo.tx_pages_data[3]);
 
 	seq_printf(seq, "%u p-structs\n\n", meminfo.p_structs);
 
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index 446aaff15bae..da885881c02f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1502,6 +1502,20 @@
 #define TP_MIB_DATA_A	0x7e54
 #define TP_INT_CAUSE_A	0x7e74
 
+#define TP_FLM_FREE_RX_CNT_A 0x7e84
+
+#define FREERXPAGECOUNT_S    0
+#define FREERXPAGECOUNT_M    0x1fffffU
+#define FREERXPAGECOUNT_V(x) ((x) << FREERXPAGECOUNT_S)
+#define FREERXPAGECOUNT_G(x) (((x) >> FREERXPAGECOUNT_S) & FREERXPAGECOUNT_M)
+
+#define TP_FLM_FREE_TX_CNT_A 0x7e88
+
+#define FREETXPAGECOUNT_S    0
+#define FREETXPAGECOUNT_M    0x1fffffU
+#define FREETXPAGECOUNT_V(x) ((x) << FREETXPAGECOUNT_S)
+#define FREETXPAGECOUNT_G(x) (((x) >> FREETXPAGECOUNT_S) & FREETXPAGECOUNT_M)
+
 #define FLMTXFLSTEMPTY_S    30
 #define FLMTXFLSTEMPTY_V(x) ((x) << FLMTXFLSTEMPTY_S)
 #define FLMTXFLSTEMPTY_F    FLMTXFLSTEMPTY_V(1U)
-- 
cgit v1.2.3


From e146471f588e4b8dcd7994036c1b47cc52325f00 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 08:08:46 -0500
Subject: net: mvpp2: debugfs: fix incorrect bitwise operator

The use of the | operator always leads to true, which looks rather
suspect in this case.

Fix this by using & instead.

Addresses-Coverity-ID: 1471903 ("Wrong operator used")
Fixes: dba1d918da02 ("net: mvpp2: debugfs: add entries for classifier flows")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
index 02dfef13cccd..f9744a61e5dd 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c
@@ -245,7 +245,7 @@ static int mvpp2_dbgfs_flow_c2_enable_show(struct seq_file *s, void *unused)
 
 	mvpp2_cls_c2_read(port->priv, MVPP22_CLS_C2_RSS_ENTRY(port->id), &c2);
 
-	enabled = !!(c2.attr[2] | MVPP22_CLS_C2_ATTR2_RSS_EN);
+	enabled = !!(c2.attr[2] & MVPP22_CLS_C2_ATTR2_RSS_EN);
 
 	seq_printf(s, "%d\n", enabled);
 
-- 
cgit v1.2.3


From 5fd9df6ac6eec9d6c7feaf114690bbeac7f13168 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Thu, 5 Jul 2018 12:25:28 -0700
Subject: drm/i915: Kill sink_crc for good

It was originally introduced following the VESA spec in order to validate PSR.

However we found so many issues around sink_crc that instead of helping PSR
development it only brought another layer of trouble to the table.

So, sink_crc has been a black whole for us in question of time, effort and hope.

First of the problems is that HW statement is clear: "Do not attempt to use
aux communication with PSR enabled". So the main reason behind sink_crc is
already compromised.

For a while we had hope on the aux-mutex could workaround this problem on SKL+
platforms, but that mutex was not reliable, not tested,
and we shouldn't use according to HW engineers.

Also, nor source, nor sink designed and implemented the sink_crc to be used like
we are trying to use here.

Well, the sink side of things is also apparently not prepared for this
case. Each panel that we tried seemed to have a different behavior with same
code and same source.

So, for all the time we lost on trying to ducktape all these different issues
I believe it is now time to move PSR to a more reliable validation.
Maybe not a perfect one as we dreamed for this sink_crc, but at least more
reliable.

Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180705192528.30515-1-rodrigo.vivi@intel.com
---
 drivers/gpu/drm/i915/i915_debugfs.c |  81 ------------------------
 drivers/gpu/drm/i915/intel_dp.c     | 123 ------------------------------------
 drivers/gpu/drm/i915/intel_drv.h    |   2 -
 3 files changed, 206 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 54509e44a856..b3aefd623557 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2767,86 +2767,6 @@ DEFINE_SIMPLE_ATTRIBUTE(i915_edp_psr_debug_fops,
 			i915_edp_psr_debug_get, i915_edp_psr_debug_set,
 			"%llu\n");
 
-static int i915_sink_crc(struct seq_file *m, void *data)
-{
-	struct drm_i915_private *dev_priv = node_to_i915(m->private);
-	struct drm_device *dev = &dev_priv->drm;
-	struct intel_connector *connector;
-	struct drm_connector_list_iter conn_iter;
-	struct intel_dp *intel_dp = NULL;
-	struct drm_modeset_acquire_ctx ctx;
-	int ret;
-	u8 crc[6];
-
-	drm_modeset_acquire_init(&ctx, DRM_MODESET_ACQUIRE_INTERRUPTIBLE);
-
-	drm_connector_list_iter_begin(dev, &conn_iter);
-
-	for_each_intel_connector_iter(connector, &conn_iter) {
-		struct drm_crtc *crtc;
-		struct drm_connector_state *state;
-		struct intel_crtc_state *crtc_state;
-
-		if (connector->base.connector_type != DRM_MODE_CONNECTOR_eDP)
-			continue;
-
-retry:
-		ret = drm_modeset_lock(&dev->mode_config.connection_mutex, &ctx);
-		if (ret)
-			goto err;
-
-		state = connector->base.state;
-		if (!state->best_encoder)
-			continue;
-
-		crtc = state->crtc;
-		ret = drm_modeset_lock(&crtc->mutex, &ctx);
-		if (ret)
-			goto err;
-
-		crtc_state = to_intel_crtc_state(crtc->state);
-		if (!crtc_state->base.active)
-			continue;
-
-		/*
-		 * We need to wait for all crtc updates to complete, to make
-		 * sure any pending modesets and plane updates are completed.
-		 */
-		if (crtc_state->base.commit) {
-			ret = wait_for_completion_interruptible(&crtc_state->base.commit->hw_done);
-
-			if (ret)
-				goto err;
-		}
-
-		intel_dp = enc_to_intel_dp(state->best_encoder);
-
-		ret = intel_dp_sink_crc(intel_dp, crtc_state, crc);
-		if (ret)
-			goto err;
-
-		seq_printf(m, "%02x%02x%02x%02x%02x%02x\n",
-			   crc[0], crc[1], crc[2],
-			   crc[3], crc[4], crc[5]);
-		goto out;
-
-err:
-		if (ret == -EDEADLK) {
-			ret = drm_modeset_backoff(&ctx);
-			if (!ret)
-				goto retry;
-		}
-		goto out;
-	}
-	ret = -ENODEV;
-out:
-	drm_connector_list_iter_end(&conn_iter);
-	drm_modeset_drop_locks(&ctx);
-	drm_modeset_acquire_fini(&ctx);
-
-	return ret;
-}
-
 static int i915_energy_uJ(struct seq_file *m, void *data)
 {
 	struct drm_i915_private *dev_priv = node_to_i915(m->private);
@@ -4792,7 +4712,6 @@ static const struct drm_info_list i915_debugfs_list[] = {
 	{"i915_ppgtt_info", i915_ppgtt_info, 0},
 	{"i915_llc", i915_llc, 0},
 	{"i915_edp_psr_status", i915_edp_psr_status, 0},
-	{"i915_sink_crc_eDP1", i915_sink_crc, 0},
 	{"i915_energy_uJ", i915_energy_uJ, 0},
 	{"i915_runtime_pm_status", i915_runtime_pm_status, 0},
 	{"i915_power_domain_info", i915_power_domain_info, 0},
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index fc05c8226551..5899cadf11e3 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -3874,129 +3874,6 @@ intel_dp_configure_mst(struct intel_dp *intel_dp)
 					intel_dp->is_mst);
 }
 
-static int intel_dp_sink_crc_stop(struct intel_dp *intel_dp,
-				  struct intel_crtc_state *crtc_state, bool disable_wa)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int ret = 0;
-	int count = 0;
-	int attempts = 10;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0) {
-		DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
-			       buf & ~DP_TEST_SINK_START) < 0) {
-		DRM_DEBUG_KMS("Sink CRC couldn't be stopped properly\n");
-		ret = -EIO;
-		goto out;
-	}
-
-	do {
-		intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-
-		if (drm_dp_dpcd_readb(&intel_dp->aux,
-				      DP_TEST_SINK_MISC, &buf) < 0) {
-			ret = -EIO;
-			goto out;
-		}
-		count = buf & DP_TEST_COUNT_MASK;
-	} while (--attempts && count);
-
-	if (attempts == 0) {
-		DRM_DEBUG_KMS("TIMEOUT: Sink CRC counter is not zeroed after calculation is stopped\n");
-		ret = -ETIMEDOUT;
-	}
-
- out:
-	if (disable_wa)
-		hsw_enable_ips(crtc_state);
-	return ret;
-}
-
-static int intel_dp_sink_crc_start(struct intel_dp *intel_dp,
-				   struct intel_crtc_state *crtc_state)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int ret;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK_MISC, &buf) < 0)
-		return -EIO;
-
-	if (!(buf & DP_TEST_CRC_SUPPORTED))
-		return -ENOTTY;
-
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_TEST_SINK, &buf) < 0)
-		return -EIO;
-
-	if (buf & DP_TEST_SINK_START) {
-		ret = intel_dp_sink_crc_stop(intel_dp, crtc_state, false);
-		if (ret)
-			return ret;
-	}
-
-	hsw_disable_ips(crtc_state);
-
-	if (drm_dp_dpcd_writeb(&intel_dp->aux, DP_TEST_SINK,
-			       buf | DP_TEST_SINK_START) < 0) {
-		hsw_enable_ips(crtc_state);
-		return -EIO;
-	}
-
-	intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-	return 0;
-}
-
-int intel_dp_sink_crc(struct intel_dp *intel_dp, struct intel_crtc_state *crtc_state, u8 *crc)
-{
-	struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
-	struct drm_i915_private *dev_priv = to_i915(dig_port->base.base.dev);
-	struct intel_crtc *intel_crtc = to_intel_crtc(crtc_state->base.crtc);
-	u8 buf;
-	int count, ret;
-	int attempts = 6;
-
-	ret = intel_dp_sink_crc_start(intel_dp, crtc_state);
-	if (ret)
-		return ret;
-
-	do {
-		intel_wait_for_vblank(dev_priv, intel_crtc->pipe);
-
-		if (drm_dp_dpcd_readb(&intel_dp->aux,
-				      DP_TEST_SINK_MISC, &buf) < 0) {
-			ret = -EIO;
-			goto stop;
-		}
-		count = buf & DP_TEST_COUNT_MASK;
-
-	} while (--attempts && count == 0);
-
-	if (attempts == 0) {
-		DRM_ERROR("Panel is unable to calculate any CRC after 6 vblanks\n");
-		ret = -ETIMEDOUT;
-		goto stop;
-	}
-
-	if (drm_dp_dpcd_read(&intel_dp->aux, DP_TEST_CRC_R_CR, crc, 6) < 0) {
-		ret = -EIO;
-		goto stop;
-	}
-
-stop:
-	intel_dp_sink_crc_stop(intel_dp, crtc_state, true);
-	return ret;
-}
-
 static bool
 intel_dp_get_sink_irq(struct intel_dp *intel_dp, u8 *sink_irq_vector)
 {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index f8d5fafe1f1a..92b68ebc7413 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1682,8 +1682,6 @@ void intel_dp_sink_dpms(struct intel_dp *intel_dp, int mode);
 void intel_dp_encoder_reset(struct drm_encoder *encoder);
 void intel_dp_encoder_suspend(struct intel_encoder *intel_encoder);
 void intel_dp_encoder_destroy(struct drm_encoder *encoder);
-int intel_dp_sink_crc(struct intel_dp *intel_dp,
-		      struct intel_crtc_state *crtc_state, u8 *crc);
 bool intel_dp_compute_config(struct intel_encoder *encoder,
 			     struct intel_crtc_state *pipe_config,
 			     struct drm_connector_state *conn_state);
-- 
cgit v1.2.3


From 202aabe84a8fd809e8f401bc05e20f35a5102ece Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 16 Jul 2018 19:08:50 -0700
Subject: xdp: fix uninitialized 'err' variable

Smatch caught an uninitialized variable error which GCC seems
to miss.

Fixes: a25717d2b604 ("xdp: support simultaneous driver and hw XDP attachment")
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/rtnetlink.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e03258e954c8..92b6fa5d5f6e 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1414,14 +1414,17 @@ static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev)
 
 	prog_id = 0;
 	mode = XDP_ATTACHED_NONE;
-	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_SKB,
-				IFLA_XDP_SKB_PROG_ID, rtnl_xdp_prog_skb))
+	err = rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_SKB,
+				  IFLA_XDP_SKB_PROG_ID, rtnl_xdp_prog_skb);
+	if (err)
 		goto err_cancel;
-	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_DRV,
-				IFLA_XDP_DRV_PROG_ID, rtnl_xdp_prog_drv))
+	err = rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_DRV,
+				  IFLA_XDP_DRV_PROG_ID, rtnl_xdp_prog_drv);
+	if (err)
 		goto err_cancel;
-	if (rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_HW,
-				IFLA_XDP_HW_PROG_ID, rtnl_xdp_prog_hw))
+	err = rtnl_xdp_report_one(skb, dev, &prog_id, &mode, XDP_ATTACHED_HW,
+				  IFLA_XDP_HW_PROG_ID, rtnl_xdp_prog_hw);
+	if (err)
 		goto err_cancel;
 
 	err = nla_put_u8(skb, IFLA_XDP_ATTACHED, mode);
-- 
cgit v1.2.3


From 6060d9d24e6d7c7959d0db8cd9f511cf43c409d9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jul 2018 15:49:48 +0200
Subject: net/mlx5: fix an unused-function warning

These dummy helpers are all intended to be inline functions,
but one of them by accident came without the 'inline' keyword,
causing a harmless warning:

In file included from drivers/net/ethernet/mellanox/mlx5/core/main.c:63:
drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h:79:1: error: 'mlx5_accel_tls_add_flow' defined but not used [-Werror=unused-function]
 mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,

Fixes: ab412e1dd7db ("net/mlx5: Accel, add TLS rx offload routines")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
index 2228c1083528..def4093ebfae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h
@@ -75,7 +75,7 @@ void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev);
 
 #else
 
-static int
+static inline int
 mlx5_accel_tls_add_flow(struct mlx5_core_dev *mdev, void *flow,
 			struct tls_crypto_info *crypto_info,
 			u32 start_offload_tcp_sn, u32 *p_swid,
-- 
cgit v1.2.3


From bf20a5c1d56043a0ee4263fbd22ca0f70ba4d09a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 17 Jul 2018 17:27:13 +0800
Subject: liquidio: Using NULL instead of plain integer

Fixes the following sparse warnings:

drivers/net/ethernet/cavium/liquidio/lio_main.c:3068:23: warning:
 Using plain integer as NULL pointer
drivers/net/ethernet/cavium/liquidio/lio_main.c:2909:23: warning:
 Using plain integer as NULL pointer
drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c:385:27: warning:
 Using plain integer as NULL pointer

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c | 2 +-
 drivers/net/ethernet/cavium/liquidio/lio_main.c         | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
index 1f8b7f651254..91dce8b8ef7e 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
@@ -382,7 +382,7 @@ void cn23xx_vf_ask_pf_to_do_flr(struct octeon_device *oct)
 	mbox_cmd.recv_len = 0;
 	mbox_cmd.recv_status = 0;
 	mbox_cmd.fn = NULL;
-	mbox_cmd.fn_arg = 0;
+	mbox_cmd.fn_arg = NULL;
 
 	octeon_mbox_write(oct, &mbox_cmd);
 }
diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 4edb1584b32f..4980eca87667 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2906,7 +2906,7 @@ static int liquidio_set_vf_vlan(struct net_device *netdev, int vfidx,
 	    vfidx + 1; /* vfidx is 0 based, but vf_num (param2) is 1 based */
 	nctrl.ncmd.s.more = 0;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.cb_fn = NULL;
 	nctrl.wait_time = LIO_CMD_WAIT_TM;
 
 	octnet_send_nic_ctrl_pkt(oct, &nctrl);
@@ -3065,7 +3065,7 @@ static int liquidio_set_vf_link_state(struct net_device *netdev, int vfidx,
 	nctrl.ncmd.s.param2 = linkstate;
 	nctrl.ncmd.s.more = 0;
 	nctrl.iq_no = lio->linfo.txpciq[0].s.q_no;
-	nctrl.cb_fn = 0;
+	nctrl.cb_fn = NULL;
 	nctrl.wait_time = LIO_CMD_WAIT_TM;
 
 	octnet_send_nic_ctrl_pkt(oct, &nctrl);
-- 
cgit v1.2.3


From a48d189ef53146a8df132a327a637c4182f50a16 Mon Sep 17 00:00:00 2001
From: Stefano Brivio <sbrivio@redhat.com>
Date: Tue, 17 Jul 2018 11:52:57 +0200
Subject: net: Move skb decrypted field, avoid explicity copy

Commit 784abe24c903 ("net: Add decrypted field to skb")
introduced a 'decrypted' field that is explicitly copied on skb
copy and clone.

Move it between headers_start[0] and headers_end[0], so that we
don't need to copy it explicitly as it's copied by the memcpy()
in __copy_skb_header().

While at it, drop the assignment in __skb_clone(), it was
already redundant.

This doesn't change the size of sk_buff or cacheline boundaries.

The 15-bits hole before tc_index becomes a 14-bits hole, and
will be again a 15-bits hole when this change is merged with
commit 8b7008620b84 ("net: Don't copy pfmemalloc flag in
__copy_skb_header()").

v2: as reported by kbuild test robot (oops, I forgot to build
    with CONFIG_TLS_DEVICE it seems), we can't use
    CHECK_SKB_FIELD() on a bit-field member. Just drop the
    check for the moment being, perhaps we could think of some
    magic to also check bit-field members one day.

Fixes: 784abe24c903 ("net: Add decrypted field to skb")
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 9 ++++-----
 net/core/skbuff.c      | 6 ------
 2 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 3ceb8dcc54da..14bc9ebe30f2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -630,7 +630,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@hash: the packet hash
  *	@queue_mapping: Queue mapping for multiqueue devices
  *	@xmit_more: More SKBs are pending for this queue
- *	@decrypted: Decrypted SKB
  *	@ndisc_nodetype: router type (from link layer)
  *	@ooo_okay: allow the mapping of a socket to a queue to be changed
  *	@l4_hash: indicate hash is a canonical 4-tuple hash over transport
@@ -641,6 +640,7 @@ typedef unsigned char *sk_buff_data_t;
  *	@no_fcs:  Request NIC to treat last 4 bytes as Ethernet FCS
  *	@csum_not_inet: use CRC32c to resolve CHECKSUM_PARTIAL
  *	@dst_pending_confirm: need to confirm neighbour
+ *	@decrypted: Decrypted SKB
   *	@napi_id: id of the NAPI struct this skb came from
  *	@secmark: security marking
  *	@mark: Generic packet mark
@@ -737,11 +737,7 @@ struct sk_buff {
 				peeked:1,
 				head_frag:1,
 				xmit_more:1,
-#ifdef CONFIG_TLS_DEVICE
-				decrypted:1;
-#else
 				__unused:1;
-#endif
 
 	/* fields enclosed in headers_start/headers_end are copied
 	 * using a single memcpy() in __copy_skb_header()
@@ -797,6 +793,9 @@ struct sk_buff {
 	__u8			tc_redirected:1;
 	__u8			tc_from_ingress:1;
 #endif
+#ifdef CONFIG_TLS_DEVICE
+	__u8			decrypted:1;
+#endif
 
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index cfd6c6f35f9c..c4e24ac27464 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -805,9 +805,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	 * It is not yet because we do not want to have a 16 bit hole
 	 */
 	new->queue_mapping = old->queue_mapping;
-#ifdef CONFIG_TLS_DEVICE
-	new->decrypted = old->decrypted;
-#endif
 
 	memcpy(&new->headers_start, &old->headers_start,
 	       offsetof(struct sk_buff, headers_end) -
@@ -868,9 +865,6 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
 	C(head_frag);
 	C(data);
 	C(truesize);
-#ifdef CONFIG_TLS_DEVICE
-	C(decrypted);
-#endif
 	refcount_set(&n->users, 1);
 
 	atomic_inc(&(skb_shinfo(skb)->dataref));
-- 
cgit v1.2.3


From 74525cc5f5f7c02f02ed356a37af5c0564ad9565 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jul 2018 15:46:34 +0200
Subject: net: cavium: add missing PCI dependencies

While some of the cavium drivers don't require PCI support, most
others do, as shown by these build failures:

WARNING: unmet direct dependencies detected for MDIO_THUNDER
  Depends on [n]: NETDEVICES [=y] && MDIO_BUS [=y] && 64BIT [=y] && PCI [=n]
  Selected by [y]:
  - THUNDER_NIC_BGX [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_CAVIUM [=y] && 64BIT [=y]
  - THUNDER_NIC_RGX [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_CAVIUM [=y] && 64BIT [=y]
drivers/net/ethernet/cavium/thunder/nicvf_main.c: In function 'nicvf_set_irq_affinity':
drivers/net/ethernet/cavium/thunder/nicvf_main.c:1095:25: error: implicit declaration of function 'pci_irq_vector'; did you mean 'rcu_irq_enter'? [-Werror=implicit-function-declaration]
drivers/net/ethernet/cavium/thunder/nic_main.c: In function 'nic_mbx_intr_handler':
drivers/net/ethernet/cavium/thunder/nic_main.c:1135:13: error: implicit declaration of function 'pci_irq_vector'; did you mean 'rcu_irq_enter'? [-Werror=implicit-function-declaration]
In file included from drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c:27:
drivers/net/ethernet/cavium/liquidio/octeon_main.h: In function 'octeon_unmap_pci_barx':
drivers/net/ethernet/cavium/liquidio/octeon_main.h:97:3: error: implicit declaration of function 'pci_release_region'; did you mean 'pci_release_regions'? [-Werror=implicit-function-declaration]
drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c: In function 'octeon_mbox_process_cmd':
drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c:263:3: error: implicit declaration of function 'pcie_capability_set_word'; did you mean 'has_capability_noaudit'? [-Werror=implicit-function-declaration]
drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c: In function 'setup_cn23xx_octeon_pf_device':
drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c:1315:22: error: 'data32' is used uninitialized in this function [-Werror=uninitialized]
drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c: In function 'cn23xx_dump_vf_iq_regs':
include/linux/dynamic_debug.h:135:3: error: 'regval' may be used uninitialized in this function [-Werror=maybe-uninitialized]
drivers/net/ethernet/cavium/liquidio/lio_core.c: In function 'octeon_setup_interrupt':
drivers/net/ethernet/cavium/liquidio/lio_core.c:1067:17: error: invalid application of 'sizeof' to incomplete type 'struct msix_entry'
drivers/net/ethernet/cavium/liquidio/octeon_main.h: In function 'octeon_unmap_pci_barx':
drivers/net/ethernet/cavium/liquidio/octeon_main.h:97:3: error: implicit declaration of function 'pci_release_region'; did you mean 'pci_release_regions'? [-Werror=implicit-function-declaration]

This adds back the minimum set of dependencies to get everything to
build cleanly again, but leaving the ones that build cleanly.

Fixes: 7e2bc7fb65d5 ("net: cavium: Drop dependency of NET_VENDOR_CAVIUM on PCI")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/Kconfig | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/cavium/Kconfig b/drivers/net/ethernet/cavium/Kconfig
index 4c3a5c354497..80e2e93e4aad 100644
--- a/drivers/net/ethernet/cavium/Kconfig
+++ b/drivers/net/ethernet/cavium/Kconfig
@@ -14,7 +14,7 @@ if NET_VENDOR_CAVIUM
 
 config THUNDER_NIC_PF
 	tristate "Thunder Physical function driver"
-	depends on 64BIT
+	depends on 64BIT && PCI
 	select THUNDER_NIC_BGX
 	---help---
 	  This driver supports Thunder's NIC physical function.
@@ -27,7 +27,7 @@ config THUNDER_NIC_PF
 config THUNDER_NIC_VF
 	tristate "Thunder Virtual function driver"
 	imply CAVIUM_PTP
-	depends on 64BIT
+	depends on 64BIT && PCI
 	---help---
 	  This driver supports Thunder's NIC virtual function
 
@@ -35,7 +35,7 @@ config	THUNDER_NIC_BGX
 	tristate "Thunder MAC interface driver (BGX)"
 	depends on 64BIT
 	select PHYLIB
-	select MDIO_THUNDER
+	select MDIO_THUNDER if PCI
 	select THUNDER_NIC_RGX
 	---help---
 	  This driver supports programming and controlling of MAC
@@ -45,7 +45,7 @@ config	THUNDER_NIC_RGX
 	tristate "Thunder MAC interface driver (RGX)"
 	depends on 64BIT
 	select PHYLIB
-	select MDIO_THUNDER
+	select MDIO_THUNDER if PCI
 	---help---
 	  This driver supports configuring XCV block of RGX interface
 	  present on CN81XX chip.
@@ -53,6 +53,7 @@ config	THUNDER_NIC_RGX
 config CAVIUM_PTP
 	tristate "Cavium PTP coprocessor as PTP clock"
 	depends on 64BIT
+	depends on PCI
 	imply PTP_1588_CLOCK
 	default y
 	---help---
@@ -66,6 +67,7 @@ config LIQUIDIO
 	tristate "Cavium LiquidIO support"
 	depends on 64BIT
 	depends on MAY_USE_DEVLINK
+	depends on PCI
 	imply PTP_1588_CLOCK
 	select FW_LOADER
 	select LIBCRC32C
-- 
cgit v1.2.3


From c94b1ac73244ff7eafb1a5df0b1e9c64f1b46113 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 17 Jul 2018 21:58:46 +0800
Subject: tipc: remove unused tipc_link_is_active

tipc_link_is_active is no longer used and can be removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/link.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index df763be38541..6987ffc8e7a1 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -297,11 +297,6 @@ static bool link_is_bc_rcvlink(struct tipc_link *l)
 	return ((l->bc_rcvlink == l) && !link_is_bc_sndlink(l));
 }
 
-int tipc_link_is_active(struct tipc_link *l)
-{
-	return l->active;
-}
-
 void tipc_link_set_active(struct tipc_link *l, bool active)
 {
 	l->active = active;
-- 
cgit v1.2.3


From d81d25e66a0f218e7d6b6d81b2d57dacf8924195 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 17 Jul 2018 22:11:23 +0800
Subject: tipc: remove unused tipc_group_size

After commit eb929a91b213 ("tipc: improve poll() for group member socket"),
it is no longer used.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/group.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/tipc/group.c b/net/tipc/group.c
index cbe39e8db39c..8f43e7d6046b 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -159,11 +159,6 @@ u32 tipc_group_exclude(struct tipc_group *grp)
 	return 0;
 }
 
-int tipc_group_size(struct tipc_group *grp)
-{
-	return grp->member_cnt;
-}
-
 struct tipc_group *tipc_group_create(struct net *net, u32 portid,
 				     struct tipc_group_req *mreq,
 				     bool *group_is_open)
-- 
cgit v1.2.3


From 8be7d96e5b6caa93bf5ed43e4396c402f7cd282a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 17 Jul 2018 08:42:04 -0700
Subject: net: phy: Drop OF dependency for MDIO_BCM_UNIMAC

The driver builds fine even with CONFIG_OF=n since we now have stubs that are
provided.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 9beac427f9e8..b7ff0af419b4 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -28,7 +28,7 @@ config MDIO_BCM_IPROC
 
 config MDIO_BCM_UNIMAC
 	tristate "Broadcom UniMAC MDIO bus controller"
-	depends on HAS_IOMEM && OF_MDIO
+	depends on HAS_IOMEM
 	help
 	  This module provides a driver for the Broadcom UniMAC MDIO busses.
 	  This hardware can be found in the Broadcom GENET Ethernet MAC
-- 
cgit v1.2.3


From 7f7b7574555e2189135098885208821d0acd4850 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 17 Jul 2018 08:42:05 -0700
Subject: net: ethernet: broadcom: Drop dependency on OF

Both BCMGENET and SYSTEMPORT build just fine with CONFIG_OF=n, we do have a
dependency on HAS_IOMEM that was not being reflected for SYSTEMPORT so add
that.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index 4c3bfde6e8de..b7aa8ad96dfb 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -61,7 +61,7 @@ config BCM63XX_ENET
 
 config BCMGENET
 	tristate "Broadcom GENET internal MAC support"
-	depends on OF && HAS_IOMEM
+	depends on HAS_IOMEM
 	select MII
 	select PHYLIB
 	select FIXED_PHY
@@ -181,7 +181,7 @@ config BGMAC_PLATFORM
 
 config SYSTEMPORT
 	tristate "Broadcom SYSTEMPORT internal MAC support"
-	depends on OF
+	depends on HAS_IOMEM
 	depends on NET_DSA || !NET_DSA
 	select MII
 	select PHYLIB
-- 
cgit v1.2.3


From 9aee398af347a298497f1e686864ee00d97e2d1c Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 17 Jul 2018 08:42:06 -0700
Subject: net: dsa: Drop OF dependency for BCM_SF2

NET_DSA_BCM_SF2 does not need to depend on CONFIG_OF anymore since we have
stubs when that option is disabled.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 0b76a3a6977e..d3ce1e4cb4d3 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -5,7 +5,7 @@ source "drivers/net/dsa/b53/Kconfig"
 
 config NET_DSA_BCM_SF2
 	tristate "Broadcom Starfighter 2 Ethernet switch support"
-	depends on HAS_IOMEM && NET_DSA && OF_MDIO
+	depends on HAS_IOMEM && NET_DSA
 	select NET_DSA_TAG_BRCM
 	select FIXED_PHY
 	select BCM7XXX_PHY
-- 
cgit v1.2.3


From e6d5752080e2d069643d65b0db10c411f6b45412 Mon Sep 17 00:00:00 2001
From: Feifei Xu <Feifei.Xu@amd.com>
Date: Tue, 17 Jul 2018 14:54:23 +0800
Subject: drm/amdgpu/gfx9: Update golden settings for vg10.

Add some UTCL registers' golden settings.

Signed-off-by: Feifei Xu <Feifei.Xu@amd.com>
Tested-by: Kevin Wang <Kevin1.Wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index a12da4a66b01..9ab39117cc4e 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -104,11 +104,22 @@ static const struct soc15_reg_golden golden_settings_gc_9_0_vg10[] =
 {
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL, 0x0000f000, 0x00012107),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCB_HW_CONTROL_3, 0x30000000, 0x10000000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPC_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPF_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmCPG_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG, 0xffff77ff, 0x2a114042),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmGB_ADDR_CONFIG_READ, 0xffff77ff, 0x2a114042),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmIA_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmPA_SC_ENHANCE_1, 0x00008000, 0x00048000),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_0, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_1, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_GPM_UTCL1_CNTL_2, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_PREWALKER_UTCL1_CNTL, 0x08000000, 0x08000080),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRLC_SPM_UTCL1_CNTL, 0x08000000, 0x08000080),
 	SOC15_REG_GOLDEN_VALUE(GC, 0, mmRMI_UTCL1_CNTL2, 0x00030000, 0x00020000),
-	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800)
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmSPI_CONFIG_CNTL_1, 0x0000000f, 0x01000107),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmTD_CNTL, 0x00001800, 0x00000800),
+	SOC15_REG_GOLDEN_VALUE(GC, 0, mmWD_UTCL1_CNTL, 0x08000000, 0x08000080)
 };
 
 static const struct soc15_reg_golden golden_settings_gc_9_0_vg20[] =
-- 
cgit v1.2.3


From 9d46f32bdd3e9d4bf435c5ae50f72fb475bf0620 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 16 Jul 2018 13:47:34 +0200
Subject: drm/amdgpu: allow for more flexible priority handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allow to call amdgpu_ring_priority_get() after pushing the ring to the
scheduler.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
index 19e45a3953e0..93794a85f83d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -211,7 +211,8 @@ void amdgpu_ring_priority_get(struct amdgpu_ring *ring,
 	if (!ring->funcs->set_priority)
 		return;
 
-	atomic_inc(&ring->num_jobs[priority]);
+	if (atomic_inc_return(&ring->num_jobs[priority]) <= 0)
+		return;
 
 	mutex_lock(&ring->priority_mutex);
 	if (priority <= ring->priority)
-- 
cgit v1.2.3


From b5286801705b39e44b824520714d503f882fef1c Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 16 Jul 2018 14:58:48 +0200
Subject: drm/amdgpu: change ring priority after pushing the job (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pushing a job can change the ring assignment of an entity.

v2: squash in:
"drm/amdgpu: fix job priority handling" (Christian)

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c  | 6 +++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c | 8 ++++++--
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 72dc9b36b937..7c5cc33d0cda 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1209,6 +1209,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 {
 	struct amdgpu_ring *ring = p->ring;
 	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
+	enum drm_sched_priority priority;
 	struct amdgpu_job *job;
 	unsigned i;
 	uint64_t seq;
@@ -1256,11 +1257,14 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job->uf_sequence = seq;
 
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(p->ring, job->base.s_priority);
 
 	trace_amdgpu_cs_ioctl(job);
+	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
+	ring = to_amdgpu_ring(entity->sched);
+	amdgpu_ring_priority_get(ring, priority);
+
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
 	amdgpu_mn_unlock(p->mn);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 42a4764d728e..5a2c26a85984 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -126,7 +126,8 @@ void amdgpu_job_free(struct amdgpu_job *job)
 int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 		      void *owner, struct dma_fence **f)
 {
-	struct amdgpu_ring *ring = to_amdgpu_ring(entity->sched);
+	enum drm_sched_priority priority;
+	struct amdgpu_ring *ring;
 	int r;
 
 	if (!f)
@@ -139,9 +140,12 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 	job->owner = owner;
 	*f = dma_fence_get(&job->base.s_fence->finished);
 	amdgpu_job_free_resources(job);
-	amdgpu_ring_priority_get(ring, job->base.s_priority);
+	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
+	ring = to_amdgpu_ring(entity->sched);
+	amdgpu_ring_priority_get(ring, priority);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From f3cdadb6fee9287d81d2dacd830bd5b439cb7331 Mon Sep 17 00:00:00 2001
From: Sonny Jiang <sonny.jiang@amd.com>
Date: Tue, 17 Jul 2018 15:27:20 -0400
Subject: drm/amdgpu: remove internal/unused kernel module parameters

Remove internal/unused kernel module parameters

Signed-off-by: Sonny Jiang <sonny.jiang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h     |  3 ---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 12 ------------
 2 files changed, 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 90780b0f0ce5..44f62fda4022 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -106,11 +106,8 @@ extern int amdgpu_vm_fault_stop;
 extern int amdgpu_vm_debug;
 extern int amdgpu_vm_update_mode;
 extern int amdgpu_dc;
-extern int amdgpu_dc_log;
 extern int amdgpu_sched_jobs;
 extern int amdgpu_sched_hw_submission;
-extern int amdgpu_no_evict;
-extern int amdgpu_direct_gma_size;
 extern uint amdgpu_pcie_gen_cap;
 extern uint amdgpu_pcie_lane_cap;
 extern uint amdgpu_cg_mask;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 529500c94675..8843a06360fa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -104,11 +104,8 @@ int amdgpu_vram_page_split = 512;
 int amdgpu_vm_update_mode = -1;
 int amdgpu_exp_hw_support = 0;
 int amdgpu_dc = -1;
-int amdgpu_dc_log = 0;
 int amdgpu_sched_jobs = 32;
 int amdgpu_sched_hw_submission = 2;
-int amdgpu_no_evict = 0;
-int amdgpu_direct_gma_size = 0;
 uint amdgpu_pcie_gen_cap = 0;
 uint amdgpu_pcie_lane_cap = 0;
 uint amdgpu_cg_mask = 0xffffffff;
@@ -341,9 +338,6 @@ module_param_named(exp_hw_support, amdgpu_exp_hw_support, int, 0444);
 MODULE_PARM_DESC(dc, "Display Core driver (1 = enable, 0 = disable, -1 = auto (default))");
 module_param_named(dc, amdgpu_dc, int, 0444);
 
-MODULE_PARM_DESC(dc_log, "Display Core Log Level (0 = minimal (default), 1 = chatty");
-module_param_named(dc_log, amdgpu_dc_log, int, 0444);
-
 /**
  * DOC: sched_jobs (int)
  * Override the max number of jobs supported in the sw queue. The default is 32.
@@ -366,12 +360,6 @@ module_param_named(sched_hw_submission, amdgpu_sched_hw_submission, int, 0444);
 MODULE_PARM_DESC(ppfeaturemask, "all power features enabled (default))");
 module_param_named(ppfeaturemask, amdgpu_pp_feature_mask, uint, 0444);
 
-MODULE_PARM_DESC(no_evict, "Support pinning request from user space (1 = enable, 0 = disable (default))");
-module_param_named(no_evict, amdgpu_no_evict, int, 0444);
-
-MODULE_PARM_DESC(direct_gma_size, "Direct GMA size in megabytes (max 96MB)");
-module_param_named(direct_gma_size, amdgpu_direct_gma_size, int, 0444);
-
 /**
  * DOC: pcie_gen_cap (uint)
  * Override PCIE gen speed capabilities. See the CAIL flags in drivers/gpu/drm/amd/include/amd_pcie.h.
-- 
cgit v1.2.3


From 7eb80427746175530f03a00ad5281c4222f17238 Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Wed, 4 Jul 2018 18:08:54 +0800
Subject: drm/amdgpu: simplify the bo reference on amdgpu_bo_update
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

BO ptr already be initialized at definition, we needn't use the complicated
reference.

v2: fix typo at subject line

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5d3d783f2d72..098dd1ba751a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -1646,18 +1646,17 @@ int amdgpu_vm_bo_update(struct amdgpu_device *adev,
 	uint64_t flags;
 	int r;
 
-	if (clear || !bo_va->base.bo) {
+	if (clear || !bo) {
 		mem = NULL;
 		nodes = NULL;
 		exclusive = NULL;
 	} else {
 		struct ttm_dma_tt *ttm;
 
-		mem = &bo_va->base.bo->tbo.mem;
+		mem = &bo->tbo.mem;
 		nodes = mem->mm_node;
 		if (mem->mem_type == TTM_PL_TT) {
-			ttm = container_of(bo_va->base.bo->tbo.ttm,
-					   struct ttm_dma_tt, ttm);
+			ttm = container_of(bo->tbo.ttm, struct ttm_dma_tt, ttm);
 			pages_addr = ttm->dma_address;
 		}
 		exclusive = reservation_object_get_excl(bo->tbo.resv);
-- 
cgit v1.2.3


From 4b4bd04898ad8a315b4a8740ff4909ea995f0c65 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 20 Jun 2018 11:26:47 -0700
Subject: drm/amdgpu/pm: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], this
uses the maximum sane buffer size and removes copy/paste code.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Reviewed-by: Rex Zhu <rezhu@amd.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 100 ++++++++++++++-------------------
 1 file changed, 42 insertions(+), 58 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index f1404adc3a90..15a1192c1ec5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -606,40 +606,59 @@ static ssize_t amdgpu_get_pp_dpm_sclk(struct device *dev,
 		return snprintf(buf, PAGE_SIZE, "\n");
 }
 
-static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
-		struct device_attribute *attr,
-		const char *buf,
-		size_t count)
+/*
+ * Worst case: 32 bits individually specified, in octal at 12 characters
+ * per line (+1 for \n).
+ */
+#define AMDGPU_MASK_BUF_MAX	(32 * 13)
+
+static ssize_t amdgpu_read_mask(const char *buf, size_t count, uint32_t *mask)
 {
-	struct drm_device *ddev = dev_get_drvdata(dev);
-	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
 	long level;
-	uint32_t mask = 0;
 	char *sub_str = NULL;
 	char *tmp;
-	char buf_cpy[count];
+	char buf_cpy[AMDGPU_MASK_BUF_MAX + 1];
 	const char delimiter[3] = {' ', '\n', '\0'};
+	size_t bytes;
 
-	memcpy(buf_cpy, buf, count+1);
+	*mask = 0;
+
+	bytes = min(count, sizeof(buf_cpy) - 1);
+	memcpy(buf_cpy, buf, bytes);
+	buf_cpy[bytes] = '\0';
 	tmp = buf_cpy;
 	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
+		sub_str = strsep(&tmp, delimiter);
 		if (strlen(sub_str)) {
 			ret = kstrtol(sub_str, 0, &level);
-
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
+			if (ret)
+				return -EINVAL;
+			*mask |= 1 << level;
 		} else
 			break;
 	}
+
+	return 0;
+}
+
+static ssize_t amdgpu_set_pp_dpm_sclk(struct device *dev,
+		struct device_attribute *attr,
+		const char *buf,
+		size_t count)
+{
+	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = ddev->dev_private;
+	int ret;
+	uint32_t mask = 0;
+
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
+
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_SCLK, mask);
 
-fail:
 	return count;
 }
 
@@ -664,32 +683,15 @@ static ssize_t amdgpu_set_pp_dpm_mclk(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
-	long level;
 	uint32_t mask = 0;
-	char *sub_str = NULL;
-	char *tmp;
-	char buf_cpy[count];
-	const char delimiter[3] = {' ', '\n', '\0'};
 
-	memcpy(buf_cpy, buf, count+1);
-	tmp = buf_cpy;
-	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
-		if (strlen(sub_str)) {
-			ret = kstrtol(sub_str, 0, &level);
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
 
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
-		} else
-			break;
-	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_MCLK, mask);
 
-fail:
 	return count;
 }
 
@@ -714,33 +716,15 @@ static ssize_t amdgpu_set_pp_dpm_pcie(struct device *dev,
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct amdgpu_device *adev = ddev->dev_private;
 	int ret;
-	long level;
 	uint32_t mask = 0;
-	char *sub_str = NULL;
-	char *tmp;
-	char buf_cpy[count];
-	const char delimiter[3] = {' ', '\n', '\0'};
-
-	memcpy(buf_cpy, buf, count+1);
-	tmp = buf_cpy;
 
-	while (tmp[0]) {
-		sub_str =  strsep(&tmp, delimiter);
-		if (strlen(sub_str)) {
-			ret = kstrtol(sub_str, 0, &level);
+	ret = amdgpu_read_mask(buf, count, &mask);
+	if (ret)
+		return ret;
 
-			if (ret) {
-				count = -EINVAL;
-				goto fail;
-			}
-			mask |= 1 << level;
-		} else
-			break;
-	}
 	if (adev->powerplay.pp_funcs->force_clock_level)
 		amdgpu_dpm_force_clock_level(adev, PP_PCIE, mask);
 
-fail:
 	return count;
 }
 
-- 
cgit v1.2.3


From 6d2ac8ee67d335983f1c9106fc8deebb89290505 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:20 +0200
Subject: net: dsa: mv88e6xxx: Abstract PTP operations

The mv88e6165 family supports PTP, but its registers use a different
layout to the currently supported devices. Abstract accessing the PTP
registers into a set of ops, so making space for a second
implementation.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 11 ++++++++
 drivers/net/dsa/mv88e6xxx/chip.h | 14 ++++++++++
 drivers/net/dsa/mv88e6xxx/ptp.c  | 55 +++++++++++++++++++++++++++-------------
 drivers/net/dsa/mv88e6xxx/ptp.h  |  4 +++
 4 files changed, 67 insertions(+), 17 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 437cd6eb4faa..94939a24dd62 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3134,6 +3134,8 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6240_ops = {
@@ -3176,6 +3178,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6290_ops = {
@@ -3215,6 +3218,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.serdes_power = mv88e6390_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
@@ -3253,6 +3257,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6321_ops = {
@@ -3289,6 +3294,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6341_ops = {
@@ -3329,6 +3335,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6350_ops = {
@@ -3402,6 +3409,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6352_ops = {
@@ -3444,6 +3452,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 	.serdes_get_sset_count = mv88e6352_serdes_get_sset_count,
 	.serdes_get_strings = mv88e6352_serdes_get_strings,
 	.serdes_get_stats = mv88e6352_serdes_get_stats,
@@ -3488,6 +3497,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.serdes_power = mv88e6390_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6390x_ops = {
@@ -3529,6 +3539,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.serdes_power = mv88e6390_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
+	.ptp_ops = &mv88e6352_ptp_ops,
 };
 
 static const struct mv88e6xxx_info mv88e6xxx_table[] = {
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 8ac3fbb15352..e12a489c22d4 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -155,6 +155,7 @@ struct mv88e6xxx_bus_ops;
 struct mv88e6xxx_irq_ops;
 struct mv88e6xxx_gpio_ops;
 struct mv88e6xxx_avb_ops;
+struct mv88e6xxx_ptp_ops;
 
 struct mv88e6xxx_irq {
 	u16 masked;
@@ -439,6 +440,9 @@ struct mv88e6xxx_ops {
 
 	/* Remote Management Unit operations */
 	int (*rmu_disable)(struct mv88e6xxx_chip *chip);
+
+	/* Precision Time Protocol operations */
+	const struct mv88e6xxx_ptp_ops *ptp_ops;
 };
 
 struct mv88e6xxx_irq_ops {
@@ -486,6 +490,16 @@ struct mv88e6xxx_avb_ops {
 	int (*tai_write)(struct mv88e6xxx_chip *chip, int addr, u16 data);
 };
 
+struct mv88e6xxx_ptp_ops {
+	u64 (*clock_read)(const struct cyclecounter *cc);
+	int (*ptp_enable)(struct ptp_clock_info *ptp,
+			  struct ptp_clock_request *rq, int on);
+	int (*ptp_verify)(struct ptp_clock_info *ptp, unsigned int pin,
+			  enum ptp_pin_function func, unsigned int chan);
+	void (*event_work)(struct work_struct *ugly);
+	int n_ext_ts;
+};
+
 #define STATS_TYPE_PORT		BIT(0)
 #define STATS_TYPE_BANK0	BIT(1)
 #define STATS_TYPE_BANK1	BIT(2)
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index bd85e2c390e1..aaa8f1b3dc08 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -50,7 +50,7 @@ static int mv88e6xxx_tai_write(struct mv88e6xxx_chip *chip, int addr, u16 data)
 }
 
 /* TODO: places where this are called should be using pinctrl */
-static int mv88e6xxx_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
+static int mv88e6352_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
 				   int func, int input)
 {
 	int err;
@@ -65,7 +65,7 @@ static int mv88e6xxx_set_gpio_func(struct mv88e6xxx_chip *chip, int pin,
 	return chip->info->ops->gpio_ops->set_pctl(chip, pin, func);
 }
 
-static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 	u16 phc_time[2];
@@ -79,13 +79,13 @@ static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
 		return ((u32)phc_time[1] << 16) | phc_time[0];
 }
 
-/* mv88e6xxx_config_eventcap - configure TAI event capture
+/* mv88e6352_config_eventcap - configure TAI event capture
  * @event: PTP_CLOCK_PPS (internal) or PTP_CLOCK_EXTTS (external)
  * @rising: zero for falling-edge trigger, else rising-edge trigger
  *
  * This will also reset the capture sequence counter.
  */
-static int mv88e6xxx_config_eventcap(struct mv88e6xxx_chip *chip, int event,
+static int mv88e6352_config_eventcap(struct mv88e6xxx_chip *chip, int event,
 				     int rising)
 {
 	u16 global_config;
@@ -118,7 +118,7 @@ static int mv88e6xxx_config_eventcap(struct mv88e6xxx_chip *chip, int event,
 	return err;
 }
 
-static void mv88e6xxx_tai_event_work(struct work_struct *ugly)
+static void mv88e6352_tai_event_work(struct work_struct *ugly)
 {
 	struct delayed_work *dw = to_delayed_work(ugly);
 	struct mv88e6xxx_chip *chip = dw_tai_event_to_chip(dw);
@@ -232,7 +232,7 @@ static int mv88e6xxx_ptp_settime(struct ptp_clock_info *ptp,
 	return 0;
 }
 
-static int mv88e6xxx_ptp_enable_extts(struct mv88e6xxx_chip *chip,
+static int mv88e6352_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 				      struct ptp_clock_request *rq, int on)
 {
 	int rising = (rq->extts.flags & PTP_RISING_EDGE);
@@ -250,18 +250,18 @@ static int mv88e6xxx_ptp_enable_extts(struct mv88e6xxx_chip *chip,
 	if (on) {
 		func = MV88E6352_G2_SCRATCH_GPIO_PCTL_EVREQ;
 
-		err = mv88e6xxx_set_gpio_func(chip, pin, func, true);
+		err = mv88e6352_set_gpio_func(chip, pin, func, true);
 		if (err)
 			goto out;
 
 		schedule_delayed_work(&chip->tai_event_work,
 				      TAI_EVENT_WORK_INTERVAL);
 
-		err = mv88e6xxx_config_eventcap(chip, PTP_CLOCK_EXTTS, rising);
+		err = mv88e6352_config_eventcap(chip, PTP_CLOCK_EXTTS, rising);
 	} else {
 		func = MV88E6352_G2_SCRATCH_GPIO_PCTL_GPIO;
 
-		err = mv88e6xxx_set_gpio_func(chip, pin, func, true);
+		err = mv88e6352_set_gpio_func(chip, pin, func, true);
 
 		cancel_delayed_work_sync(&chip->tai_event_work);
 	}
@@ -272,20 +272,20 @@ out:
 	return err;
 }
 
-static int mv88e6xxx_ptp_enable(struct ptp_clock_info *ptp,
+static int mv88e6352_ptp_enable(struct ptp_clock_info *ptp,
 				struct ptp_clock_request *rq, int on)
 {
 	struct mv88e6xxx_chip *chip = ptp_to_chip(ptp);
 
 	switch (rq->type) {
 	case PTP_CLK_REQ_EXTTS:
-		return mv88e6xxx_ptp_enable_extts(chip, rq, on);
+		return mv88e6352_ptp_enable_extts(chip, rq, on);
 	default:
 		return -EOPNOTSUPP;
 	}
 }
 
-static int mv88e6xxx_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
+static int mv88e6352_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
 				enum ptp_pin_function func, unsigned int chan)
 {
 	switch (func) {
@@ -299,6 +299,24 @@ static int mv88e6xxx_ptp_verify(struct ptp_clock_info *ptp, unsigned int pin,
 	return 0;
 }
 
+const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
+	.clock_read = mv88e6352_ptp_clock_read,
+	.ptp_enable = mv88e6352_ptp_enable,
+	.ptp_verify = mv88e6352_ptp_verify,
+	.event_work = mv88e6352_tai_event_work,
+	.n_ext_ts = 1,
+};
+
+static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
+{
+	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
+
+	if (chip->info->ops->ptp_ops->clock_read)
+		return chip->info->ops->ptp_ops->clock_read(cc);
+
+	return 0;
+}
+
 /* With a 125MHz input clock, the 32-bit timestamp counter overflows in ~34.3
  * seconds; this task forces periodic reads so that we don't miss any.
  */
@@ -317,6 +335,7 @@ static void mv88e6xxx_ptp_overflow_check(struct work_struct *work)
 
 int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	int i;
 
 	/* Set up the cycle counter */
@@ -330,14 +349,15 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 			 ktime_to_ns(ktime_get_real()));
 
 	INIT_DELAYED_WORK(&chip->overflow_work, mv88e6xxx_ptp_overflow_check);
-	INIT_DELAYED_WORK(&chip->tai_event_work, mv88e6xxx_tai_event_work);
+	if (ptp_ops->event_work)
+		INIT_DELAYED_WORK(&chip->tai_event_work, ptp_ops->event_work);
 
 	chip->ptp_clock_info.owner = THIS_MODULE;
 	snprintf(chip->ptp_clock_info.name, sizeof(chip->ptp_clock_info.name),
 		 dev_name(chip->dev));
 	chip->ptp_clock_info.max_adj	= 1000000;
 
-	chip->ptp_clock_info.n_ext_ts	= 1;
+	chip->ptp_clock_info.n_ext_ts	= ptp_ops->n_ext_ts;
 	chip->ptp_clock_info.n_per_out	= 0;
 	chip->ptp_clock_info.n_pins	= mv88e6xxx_num_gpio(chip);
 	chip->ptp_clock_info.pps	= 0;
@@ -355,8 +375,8 @@ int mv88e6xxx_ptp_setup(struct mv88e6xxx_chip *chip)
 	chip->ptp_clock_info.adjtime	= mv88e6xxx_ptp_adjtime;
 	chip->ptp_clock_info.gettime64	= mv88e6xxx_ptp_gettime;
 	chip->ptp_clock_info.settime64	= mv88e6xxx_ptp_settime;
-	chip->ptp_clock_info.enable	= mv88e6xxx_ptp_enable;
-	chip->ptp_clock_info.verify	= mv88e6xxx_ptp_verify;
+	chip->ptp_clock_info.enable	= ptp_ops->ptp_enable;
+	chip->ptp_clock_info.verify	= ptp_ops->ptp_verify;
 	chip->ptp_clock_info.do_aux_work = mv88e6xxx_hwtstamp_work;
 
 	chip->ptp_clock = ptp_clock_register(&chip->ptp_clock_info, chip->dev);
@@ -373,7 +393,8 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip)
 {
 	if (chip->ptp_clock) {
 		cancel_delayed_work_sync(&chip->overflow_work);
-		cancel_delayed_work_sync(&chip->tai_event_work);
+		if (chip->info->ops->ptp_ops->event_work)
+			cancel_delayed_work_sync(&chip->tai_event_work);
 
 		ptp_clock_unregister(chip->ptp_clock);
 		chip->ptp_clock = NULL;
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h
index 10f271ab650d..16a310679f12 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.h
+++ b/drivers/net/dsa/mv88e6xxx/ptp.h
@@ -87,6 +87,8 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip);
 #define ptp_to_chip(ptp) container_of(ptp, struct mv88e6xxx_chip,	\
 				      ptp_clock_info)
 
+extern const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops;
+
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
 static inline long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp)
@@ -103,6 +105,8 @@ static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip)
 {
 }
 
+static const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {};
+
 #endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */
 
 #endif /* _MV88E6XXX_PTP_H */
-- 
cgit v1.2.3


From a469a61231e5f67de4289f2a7889f0665528b13b Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:21 +0200
Subject: net: dsa: mv88e6xxx: Add MV88E6165 AVB register access

The MV88E6165 PTP registers are all in AVB bank F, unlike newer
generations which spread them over AVB bank E and F. Implement AVB ops
for the MV88E6165 which hides this difference.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c        |  2 ++
 drivers/net/dsa/mv88e6xxx/global2.h     |  3 +++
 drivers/net/dsa/mv88e6xxx/global2_avb.c | 25 +++++++++++++++++++++++++
 3 files changed, 30 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 94939a24dd62..09b627cc1ca3 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2810,6 +2810,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.avb_ops = &mv88e6165_avb_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6165_ops = {
@@ -2838,6 +2839,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.avb_ops = &mv88e6165_avb_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6171_ops = {
diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h
index 37e8ce2c72a0..194660d8c783 100644
--- a/drivers/net/dsa/mv88e6xxx/global2.h
+++ b/drivers/net/dsa/mv88e6xxx/global2.h
@@ -160,6 +160,7 @@
 #define MV88E6390_G2_AVB_CMD_OP_WRITE		0x6000
 #define MV88E6352_G2_AVB_CMD_PORT_MASK		0x0f00
 #define MV88E6352_G2_AVB_CMD_PORT_TAIGLOBAL	0xe
+#define MV88E6165_G2_AVB_CMD_PORT_PTPGLOBAL	0xf
 #define MV88E6352_G2_AVB_CMD_PORT_PTPGLOBAL	0xf
 #define MV88E6390_G2_AVB_CMD_PORT_MASK		0x1f00
 #define MV88E6390_G2_AVB_CMD_PORT_TAIGLOBAL	0x1e
@@ -335,6 +336,7 @@ int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target,
 extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops;
 extern const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops;
 
+extern const struct mv88e6xxx_avb_ops mv88e6165_avb_ops;
 extern const struct mv88e6xxx_avb_ops mv88e6352_avb_ops;
 extern const struct mv88e6xxx_avb_ops mv88e6390_avb_ops;
 
@@ -484,6 +486,7 @@ static inline int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip)
 static const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops = {};
 static const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops = {};
 
+static const struct mv88e6xxx_avb_ops mv88e6165_avb_ops = {};
 static const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = {};
 static const struct mv88e6xxx_avb_ops mv88e6390_avb_ops = {};
 
diff --git a/drivers/net/dsa/mv88e6xxx/global2_avb.c b/drivers/net/dsa/mv88e6xxx/global2_avb.c
index 2e398ccb88ca..672b503a67e1 100644
--- a/drivers/net/dsa/mv88e6xxx/global2_avb.c
+++ b/drivers/net/dsa/mv88e6xxx/global2_avb.c
@@ -130,6 +130,31 @@ const struct mv88e6xxx_avb_ops mv88e6352_avb_ops = {
 	.tai_write		= mv88e6352_g2_avb_tai_write,
 };
 
+static int mv88e6165_g2_avb_tai_read(struct mv88e6xxx_chip *chip, int addr,
+				     u16 *data, int len)
+{
+	return mv88e6352_g2_avb_port_ptp_read(chip,
+					MV88E6165_G2_AVB_CMD_PORT_PTPGLOBAL,
+					addr, data, len);
+}
+
+static int mv88e6165_g2_avb_tai_write(struct mv88e6xxx_chip *chip, int addr,
+				      u16 data)
+{
+	return mv88e6352_g2_avb_port_ptp_write(chip,
+					MV88E6165_G2_AVB_CMD_PORT_PTPGLOBAL,
+					addr, data);
+}
+
+const struct mv88e6xxx_avb_ops mv88e6165_avb_ops = {
+	.port_ptp_read		= mv88e6352_g2_avb_port_ptp_read,
+	.port_ptp_write		= mv88e6352_g2_avb_port_ptp_write,
+	.ptp_read		= mv88e6352_g2_avb_ptp_read,
+	.ptp_write		= mv88e6352_g2_avb_ptp_write,
+	.tai_read		= mv88e6165_g2_avb_tai_read,
+	.tai_write		= mv88e6165_g2_avb_tai_write,
+};
+
 static int mv88e6390_g2_avb_port_ptp_read(struct mv88e6xxx_chip *chip,
 					  int port, int addr, u16 *data,
 					  int len)
-- 
cgit v1.2.3


From dfa543481034ef57cba55585e35eead113f50030 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:22 +0200
Subject: net: dsa: mv88e6xxx: Add mv88e6165 PTP support

The mv88e6165 family has its global clock in the PTP global
registers. It does not support any form of PTP events. Add a function
to read the clock, fill in an ops structure, and register it with the
two members of the family.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c |  4 ++++
 drivers/net/dsa/mv88e6xxx/ptp.c  | 18 ++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/ptp.h  | 29 +++++++++++++++++++++++++++++
 3 files changed, 51 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 09b627cc1ca3..9dd270978064 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2811,6 +2811,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6165_avb_ops,
+	.ptp_ops = &mv88e6165_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6165_ops = {
@@ -2840,6 +2841,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6165_avb_ops,
+	.ptp_ops = &mv88e6165_ptp_ops,
 };
 
 static const struct mv88e6xxx_ops mv88e6171_ops = {
@@ -3693,6 +3695,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.pvt = true,
 		.multi_chip = true,
 		.tag_protocol = DSA_TAG_PROTO_EDSA,
+		.ptp_support = true,
 		.ops = &mv88e6161_ops,
 	},
 
@@ -3715,6 +3718,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.pvt = true,
 		.multi_chip = true,
 		.tag_protocol = DSA_TAG_PROTO_DSA,
+		.ptp_support = true,
 		.ops = &mv88e6165_ops,
 	},
 
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index aaa8f1b3dc08..485f5676fefb 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -79,6 +79,20 @@ static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
 		return ((u32)phc_time[1] << 16) | phc_time[0];
 }
 
+static u64 mv88e6165_ptp_clock_read(const struct cyclecounter *cc)
+{
+	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
+	u16 phc_time[2];
+	int err;
+
+	err = mv88e6xxx_tai_read(chip, MV88E6XXX_PTP_GC_TIME_LO, phc_time,
+				 ARRAY_SIZE(phc_time));
+	if (err)
+		return 0;
+	else
+		return ((u32)phc_time[1] << 16) | phc_time[0];
+}
+
 /* mv88e6352_config_eventcap - configure TAI event capture
  * @event: PTP_CLOCK_PPS (internal) or PTP_CLOCK_EXTTS (external)
  * @rising: zero for falling-edge trigger, else rising-edge trigger
@@ -307,6 +321,10 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
 	.n_ext_ts = 1,
 };
 
+const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
+	.clock_read = mv88e6165_ptp_clock_read,
+};
+
 static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h
index 16a310679f12..979eecc8ae01 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.h
+++ b/drivers/net/dsa/mv88e6xxx/ptp.h
@@ -78,6 +78,33 @@
 /* Offset 0x12: Lock Status */
 #define MV88E6XXX_TAI_LOCK_STATUS		0x12
 
+/* Offset 0x00: Ether Type */
+#define MV88E6XXX_PTP_GC_ETYPE			0x00
+
+/* Offset 0x01: Message ID */
+#define MV88E6XXX_PTP_GC_MESSAGE_ID		0x01
+
+/* Offset 0x02: Time Stamp Arrive Time */
+#define MV88E6XXX_PTP_GC_TS_ARR_PTR		0x02
+
+/* Offset 0x03: Port Arrival Interrupt Enable */
+#define MV88E6XXX_PTP_GC_PORT_ARR_INT_EN	0x03
+
+/* Offset 0x04: Port Departure Interrupt Enable */
+#define MV88E6XXX_PTP_GC_PORT_DEP_INT_EN	0x04
+
+/* Offset 0x05: Configuration */
+#define MV88E6XXX_PTP_GC_CONFIG			0x05
+#define MV88E6XXX_PTP_GC_CONFIG_DIS_OVERWRITE	BIT(1)
+#define MV88E6XXX_PTP_GC_CONFIG_DIS_TS		BIT(0)
+
+/* Offset 0x8: Interrupt Status */
+#define MV88E6XXX_PTP_GC_INT_STATUS		0x08
+
+/* Offset 0x9/0xa: Global Time */
+#define MV88E6XXX_PTP_GC_TIME_LO		0x09
+#define MV88E6XXX_PTP_GC_TIME_HI		0x0A
+
 #ifdef CONFIG_NET_DSA_MV88E6XXX_PTP
 
 long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp);
@@ -88,6 +115,7 @@ void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip);
 				      ptp_clock_info)
 
 extern const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops;
+extern const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops;
 
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
@@ -106,6 +134,7 @@ static inline void mv88e6xxx_ptp_free(struct mv88e6xxx_chip *chip)
 }
 
 static const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {};
+static const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {};
 
 #endif /* CONFIG_NET_DSA_MV88E6XXX_PTP */
 
-- 
cgit v1.2.3


From ffc705de86e28e7a6e6f8d2e0be73c4181b37b4b Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:23 +0200
Subject: net: dsa: mv88e6xxx: Abstract HW timestamp setup

The 6165 family does not have per port PTP control registers. Also, it
places the timestamp data in different registers. Abstract the current
implementation of 6352 compatible PTP devices so that 6165 can be
added.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.h     |  5 ++++
 drivers/net/dsa/mv88e6xxx/hwtstamp.c | 51 ++++++++++++++++++++----------------
 drivers/net/dsa/mv88e6xxx/hwtstamp.h |  2 ++
 drivers/net/dsa/mv88e6xxx/ptp.c      |  6 +++++
 4 files changed, 42 insertions(+), 22 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index e12a489c22d4..2cc4deb110d6 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -497,7 +497,12 @@ struct mv88e6xxx_ptp_ops {
 	int (*ptp_verify)(struct ptp_clock_info *ptp, unsigned int pin,
 			  enum ptp_pin_function func, unsigned int chan);
 	void (*event_work)(struct work_struct *ugly);
+	int (*port_enable)(struct mv88e6xxx_chip *chip, int port);
+	int (*port_disable)(struct mv88e6xxx_chip *chip, int port);
 	int n_ext_ts;
+	int arr0_sts_reg;
+	int arr1_sts_reg;
+	int dep_sts_reg;
 };
 
 #define STATS_TYPE_PORT		BIT(0)
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index a036c490b7ce..1378c9d102a1 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -92,10 +92,9 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 					 struct hwtstamp_config *config)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
 	bool tstamp_enable = false;
-	u16 port_config0;
-	int err;
 
 	/* Prevent the TX/RX paths from trying to interact with the
 	 * timestamp hardware while we reconfigure it.
@@ -141,24 +140,16 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 		return -ERANGE;
 	}
 
+	mutex_lock(&chip->reg_lock);
 	if (tstamp_enable) {
-		/* Disable transportSpecific value matching, so that packets
-		 * with either 1588 (0) and 802.1AS (1) will be timestamped.
-		 */
-		port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH;
+		if (ptp_ops->port_enable)
+			ptp_ops->port_enable(chip, port);
 	} else {
-		/* Disable PTP. This disables both RX and TX timestamping. */
-		port_config0 = MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP;
+		if (ptp_ops->port_disable)
+			ptp_ops->port_disable(chip, port);
 	}
-
-	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
-				       port_config0);
 	mutex_unlock(&chip->reg_lock);
 
-	if (err < 0)
-		return err;
-
 	/* Once hardware has been configured, enable timestamp checks
 	 * in the RX/TX paths.
 	 */
@@ -338,17 +329,18 @@ static void mv88e6xxx_get_rxts(struct mv88e6xxx_chip *chip,
 static void mv88e6xxx_rxtstamp_work(struct mv88e6xxx_chip *chip,
 				    struct mv88e6xxx_port_hwtstamp *ps)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct sk_buff *skb;
 
 	skb = skb_dequeue(&ps->rx_queue);
 
 	if (skb)
-		mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR0_STS,
+		mv88e6xxx_get_rxts(chip, ps, skb, ptp_ops->arr0_sts_reg,
 				   &ps->rx_queue);
 
 	skb = skb_dequeue(&ps->rx_queue2);
 	if (skb)
-		mv88e6xxx_get_rxts(chip, ps, skb, MV88E6XXX_PORT_PTP_ARR1_STS,
+		mv88e6xxx_get_rxts(chip, ps, skb, ptp_ops->arr1_sts_reg,
 				   &ps->rx_queue2);
 }
 
@@ -389,6 +381,7 @@ bool mv88e6xxx_port_rxtstamp(struct dsa_switch *ds, int port,
 static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip,
 				   struct mv88e6xxx_port_hwtstamp *ps)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct skb_shared_hwtstamps shhwtstamps;
 	u16 departure_block[4], status;
 	struct sk_buff *tmp_skb;
@@ -401,7 +394,7 @@ static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip,
 
 	mutex_lock(&chip->reg_lock);
 	err = mv88e6xxx_port_ptp_read(chip, ps->port_id,
-				      MV88E6XXX_PORT_PTP_DEP_STS,
+				      ptp_ops->dep_sts_reg,
 				      departure_block,
 				      ARRAY_SIZE(departure_block));
 	mutex_unlock(&chip->reg_lock);
@@ -425,8 +418,7 @@ static int mv88e6xxx_txtstamp_work(struct mv88e6xxx_chip *chip,
 
 	/* We have the timestamp; go ahead and clear valid now */
 	mutex_lock(&chip->reg_lock);
-	mv88e6xxx_port_ptp_write(chip, ps->port_id,
-				 MV88E6XXX_PORT_PTP_DEP_STS, 0);
+	mv88e6xxx_port_ptp_write(chip, ps->port_id, ptp_ops->dep_sts_reg, 0);
 	mutex_unlock(&chip->reg_lock);
 
 	status = departure_block[0] & MV88E6XXX_PTP_TS_STATUS_MASK;
@@ -522,8 +514,21 @@ bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port,
 	return true;
 }
 
+int mv88e6352_hwtstamp_port_disable(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
+					MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP);
+}
+
+int mv88e6352_hwtstamp_port_enable(struct mv88e6xxx_chip *chip, int port)
+{
+	return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
+					MV88E6XXX_PORT_PTP_CFG0_DISABLE_TSPEC_MATCH);
+}
+
 static int mv88e6xxx_hwtstamp_port_setup(struct mv88e6xxx_chip *chip, int port)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	struct mv88e6xxx_port_hwtstamp *ps = &chip->port_hwtstamp[port];
 
 	ps->port_id = port;
@@ -531,8 +536,10 @@ static int mv88e6xxx_hwtstamp_port_setup(struct mv88e6xxx_chip *chip, int port)
 	skb_queue_head_init(&ps->rx_queue);
 	skb_queue_head_init(&ps->rx_queue2);
 
-	return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
-					MV88E6XXX_PORT_PTP_CFG0_DISABLE_PTP);
+	if (ptp_ops->port_disable)
+		return ptp_ops->port_disable(chip, port);
+
+	return 0;
 }
 
 int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip)
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.h b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
index bc71c9212a08..3e601051f7c0 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.h
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
@@ -123,6 +123,8 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 
 int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip);
 void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip);
+int mv88e6352_hwtstamp_port_enable(struct mv88e6xxx_chip *chip, int port);
+int mv88e6352_hwtstamp_port_disable(struct mv88e6xxx_chip *chip, int port);
 
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index 485f5676fefb..4963167b9e83 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -16,6 +16,7 @@
 
 #include "chip.h"
 #include "global2.h"
+#include "hwtstamp.h"
 #include "ptp.h"
 
 /* Raw timestamps are in units of 8-ns clock periods. */
@@ -318,7 +319,12 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
 	.ptp_enable = mv88e6352_ptp_enable,
 	.ptp_verify = mv88e6352_ptp_verify,
 	.event_work = mv88e6352_tai_event_work,
+	.port_enable = mv88e6352_hwtstamp_port_enable,
+	.port_disable = mv88e6352_hwtstamp_port_disable,
 	.n_ext_ts = 1,
+	.arr0_sts_reg = MV88E6XXX_PORT_PTP_ARR0_STS,
+	.arr1_sts_reg = MV88E6XXX_PORT_PTP_ARR1_STS,
+	.dep_sts_reg = MV88E6XXX_PORT_PTP_DEP_STS,
 };
 
 const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
-- 
cgit v1.2.3


From 48cb5e03d58b7179dd8e71c1e8e068630b440b1c Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:24 +0200
Subject: net: dsa: mv88e6xxx: Abstract supported PTP filters

The 6165 only supports layer L2 PTP, where as the more modern devices
also support UDP and UDPv6, i.e. L4. Abstract the supported receive
filters.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.h     |  1 +
 drivers/net/dsa/mv88e6xxx/hwtstamp.c | 26 ++++++++++++++------------
 drivers/net/dsa/mv88e6xxx/ptp.c      | 10 ++++++++++
 3 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 2cc4deb110d6..432e7e8e6e3d 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -503,6 +503,7 @@ struct mv88e6xxx_ptp_ops {
 	int arr0_sts_reg;
 	int arr1_sts_reg;
 	int dep_sts_reg;
+	u32 rx_filters;
 };
 
 #define STATS_TYPE_PORT		BIT(0)
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index 1378c9d102a1..0307704e0063 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -61,7 +61,11 @@ static int mv88e6xxx_ptp_write(struct mv88e6xxx_chip *chip, int addr,
 int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 			  struct ethtool_ts_info *info)
 {
-	struct mv88e6xxx_chip *chip = ds->priv;
+	const struct mv88e6xxx_ptp_ops *ptp_ops;
+	struct mv88e6xxx_chip *chip;
+
+	chip = ds->priv;
+	ptp_ops = chip->info->ops->ptp_ops;
 
 	if (!chip->info->ptp_support)
 		return -EOPNOTSUPP;
@@ -74,17 +78,7 @@ int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 	info->tx_types =
 		(1 << HWTSTAMP_TX_OFF) |
 		(1 << HWTSTAMP_TX_ON);
-	info->rx_filters =
-		(1 << HWTSTAMP_FILTER_NONE) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
-		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ);
+	info->rx_filters = ptp_ops->rx_filters;
 
 	return 0;
 }
@@ -119,6 +113,14 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 	/* The switch supports timestamping both L2 and L4; one cannot be
 	 * disabled independently of the other.
 	 */
+
+	if (!(BIT(config->rx_filter) & ptp_ops->rx_filters)) {
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
+		dev_dbg(chip->dev, "Unsupported rx_filter %d\n",
+			config->rx_filter);
+		return -ERANGE;
+	}
+
 	switch (config->rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
 		tstamp_enable = false;
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index 4963167b9e83..bc4efa7d0ac3 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -325,6 +325,16 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
 	.arr0_sts_reg = MV88E6XXX_PORT_PTP_ARR0_STS,
 	.arr1_sts_reg = MV88E6XXX_PORT_PTP_ARR1_STS,
 	.dep_sts_reg = MV88E6XXX_PORT_PTP_DEP_STS,
+	.rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
 };
 
 const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
-- 
cgit v1.2.3


From e2294a8bf52b8bf1bab52b4165ffdceec4a143e0 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:25 +0200
Subject: net: dsa: mv88e6xxx: Add hwtimestamp support for the 6165

The 6165 family supports a more restricted version of hardware time
stamps. Only L2 PTP is supported. All ports have to use the same
EtherType, and transport spec configuration. PTP can only be
enabled/disabled globally, not per port.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.h     |  3 +++
 drivers/net/dsa/mv88e6xxx/hwtstamp.c | 50 ++++++++++++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/hwtstamp.h | 12 +++++++--
 drivers/net/dsa/mv88e6xxx/ptp.c      | 12 +++++++++
 drivers/net/dsa/mv88e6xxx/ptp.h      | 35 +++++++++++++++++++++++++
 5 files changed, 110 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 432e7e8e6e3d..6aa6197ddc10 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -274,6 +274,7 @@ struct mv88e6xxx_chip {
 	struct ptp_pin_desc	pin_config[MV88E6XXX_MAX_GPIO];
 	u16 trig_config;
 	u16 evcap_config;
+	u16 enable_count;
 
 	/* Per-port timestamping resources. */
 	struct mv88e6xxx_port_hwtstamp port_hwtstamp[DSA_MAX_PORTS];
@@ -499,6 +500,8 @@ struct mv88e6xxx_ptp_ops {
 	void (*event_work)(struct work_struct *ugly);
 	int (*port_enable)(struct mv88e6xxx_chip *chip, int port);
 	int (*port_disable)(struct mv88e6xxx_chip *chip, int port);
+	int (*global_enable)(struct mv88e6xxx_chip *chip);
+	int (*global_disable)(struct mv88e6xxx_chip *chip);
 	int n_ext_ts;
 	int arr0_sts_reg;
 	int arr1_sts_reg;
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index 0307704e0063..01e60a8c97fb 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -51,6 +51,15 @@ static int mv88e6xxx_ptp_write(struct mv88e6xxx_chip *chip, int addr,
 	return chip->info->ops->avb_ops->ptp_write(chip, addr, data);
 }
 
+static int mv88e6xxx_ptp_read(struct mv88e6xxx_chip *chip, int addr,
+			      u16 *data)
+{
+	if (!chip->info->ops->avb_ops->ptp_read)
+		return -EOPNOTSUPP;
+
+	return chip->info->ops->avb_ops->ptp_read(chip, addr, data, 1);
+}
+
 /* TX_TSTAMP_TIMEOUT: This limits the time spent polling for a TX
  * timestamp. When working properly, hardware will produce a timestamp
  * within 1ms. Software may enounter delays due to MDIO contention, so
@@ -144,11 +153,17 @@ static int mv88e6xxx_set_hwtstamp_config(struct mv88e6xxx_chip *chip, int port,
 
 	mutex_lock(&chip->reg_lock);
 	if (tstamp_enable) {
+		chip->enable_count += 1;
+		if (chip->enable_count == 1 && ptp_ops->global_enable)
+			ptp_ops->global_enable(chip);
 		if (ptp_ops->port_enable)
 			ptp_ops->port_enable(chip, port);
 	} else {
 		if (ptp_ops->port_disable)
 			ptp_ops->port_disable(chip, port);
+		chip->enable_count -= 1;
+		if (chip->enable_count == 0 && ptp_ops->global_disable)
+			ptp_ops->global_disable(chip);
 	}
 	mutex_unlock(&chip->reg_lock);
 
@@ -516,6 +531,33 @@ bool mv88e6xxx_port_txtstamp(struct dsa_switch *ds, int port,
 	return true;
 }
 
+int mv88e6165_global_disable(struct mv88e6xxx_chip *chip)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_ptp_read(chip, MV88E6165_PTP_CFG, &val);
+	if (err)
+		return err;
+	val |= MV88E6165_PTP_CFG_DISABLE_PTP;
+
+	return mv88e6xxx_ptp_write(chip, MV88E6165_PTP_CFG, val);
+}
+
+int mv88e6165_global_enable(struct mv88e6xxx_chip *chip)
+{
+	u16 val;
+	int err;
+
+	err = mv88e6xxx_ptp_read(chip, MV88E6165_PTP_CFG, &val);
+	if (err)
+		return err;
+
+	val &= ~(MV88E6165_PTP_CFG_DISABLE_PTP | MV88E6165_PTP_CFG_TSPEC_MASK);
+
+	return mv88e6xxx_ptp_write(chip, MV88E6165_PTP_CFG, val);
+}
+
 int mv88e6352_hwtstamp_port_disable(struct mv88e6xxx_chip *chip, int port)
 {
 	return mv88e6xxx_port_ptp_write(chip, port, MV88E6XXX_PORT_PTP_CFG0,
@@ -546,6 +588,7 @@ static int mv88e6xxx_hwtstamp_port_setup(struct mv88e6xxx_chip *chip, int port)
 
 int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip)
 {
+	const struct mv88e6xxx_ptp_ops *ptp_ops = chip->info->ops->ptp_ops;
 	int err;
 	int i;
 
@@ -556,6 +599,13 @@ int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip)
 			return err;
 	}
 
+	/* Disable PTP globally */
+	if (ptp_ops->global_disable) {
+		err = ptp_ops->global_disable(chip);
+		if (err)
+			return err;
+	}
+
 	/* MV88E6XXX_PTP_MSG_TYPE is a mask of PTP message types to
 	 * timestamp. This affects all ports that have timestamping enabled,
 	 * but the timestamp config is per-port; thus we configure all events
diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.h b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
index 3e601051f7c0..b9a72661bcc4 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.h
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.h
@@ -19,7 +19,7 @@
 
 #include "chip.h"
 
-/* Global PTP registers */
+/* Global 6352 PTP registers */
 /* Offset 0x00: PTP EtherType */
 #define MV88E6XXX_PTP_ETHERTYPE	0x00
 
@@ -34,6 +34,12 @@
 /* Offset 0x02: Timestamp Arrival Capture Pointers */
 #define MV88E6XXX_PTP_TS_ARRIVAL_PTR	0x02
 
+/* Offset 0x05: PTP Global Configuration */
+#define MV88E6165_PTP_CFG			0x05
+#define MV88E6165_PTP_CFG_TSPEC_MASK		0xf000
+#define MV88E6165_PTP_CFG_DISABLE_TS_OVERWRITE	BIT(1)
+#define MV88E6165_PTP_CFG_DISABLE_PTP		BIT(0)
+
 /* Offset 0x07: PTP Global Configuration */
 #define MV88E6341_PTP_CFG			0x07
 #define MV88E6341_PTP_CFG_UPDATE		0x8000
@@ -46,7 +52,7 @@
 /* Offset 0x08: PTP Interrupt Status */
 #define MV88E6XXX_PTP_IRQ_STATUS	0x08
 
-/* Per-Port PTP Registers */
+/* Per-Port 6352 PTP Registers */
 /* Offset 0x00: PTP Configuration 0 */
 #define MV88E6XXX_PORT_PTP_CFG0				0x00
 #define MV88E6XXX_PORT_PTP_CFG0_TSPEC_SHIFT		12
@@ -125,6 +131,8 @@ int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip);
 void mv88e6xxx_hwtstamp_free(struct mv88e6xxx_chip *chip);
 int mv88e6352_hwtstamp_port_enable(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_hwtstamp_port_disable(struct mv88e6xxx_chip *chip, int port);
+int mv88e6165_global_enable(struct mv88e6xxx_chip *chip);
+int mv88e6165_global_disable(struct mv88e6xxx_chip *chip);
 
 #else /* !CONFIG_NET_DSA_MV88E6XXX_PTP */
 
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index bc4efa7d0ac3..4b336d8d4c67 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -339,6 +339,18 @@ const struct mv88e6xxx_ptp_ops mv88e6352_ptp_ops = {
 
 const struct mv88e6xxx_ptp_ops mv88e6165_ptp_ops = {
 	.clock_read = mv88e6165_ptp_clock_read,
+	.global_enable = mv88e6165_global_enable,
+	.global_disable = mv88e6165_global_disable,
+	.arr0_sts_reg = MV88E6165_PORT_PTP_ARR0_STS,
+	.arr1_sts_reg = MV88E6165_PORT_PTP_ARR1_STS,
+	.dep_sts_reg = MV88E6165_PORT_PTP_DEP_STS,
+	.rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_EVENT) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_SYNC) |
+		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
 };
 
 static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h
index 979eecc8ae01..747f90bb9393 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.h
+++ b/drivers/net/dsa/mv88e6xxx/ptp.h
@@ -81,6 +81,7 @@
 /* Offset 0x00: Ether Type */
 #define MV88E6XXX_PTP_GC_ETYPE			0x00
 
+/* 6165 Global Control Registers */
 /* Offset 0x01: Message ID */
 #define MV88E6XXX_PTP_GC_MESSAGE_ID		0x01
 
@@ -105,6 +106,40 @@
 #define MV88E6XXX_PTP_GC_TIME_LO		0x09
 #define MV88E6XXX_PTP_GC_TIME_HI		0x0A
 
+/* 6165 Per Port Registers */
+/* Offset 0: Arrival Time 0 Status */
+#define MV88E6165_PORT_PTP_ARR0_STS	0x00
+
+/* Offset 0x01/0x02: PTP Arrival 0 Time */
+#define MV88E6165_PORT_PTP_ARR0_TIME_LO	0x01
+#define MV88E6165_PORT_PTP_ARR0_TIME_HI	0x02
+
+/* Offset 0x03: PTP Arrival 0 Sequence ID */
+#define MV88E6165_PORT_PTP_ARR0_SEQID	0x03
+
+/* Offset 0x04: PTP Arrival 1 Status */
+#define MV88E6165_PORT_PTP_ARR1_STS	0x04
+
+/* Offset 0x05/0x6E: PTP Arrival 1 Time */
+#define MV88E6165_PORT_PTP_ARR1_TIME_LO	0x05
+#define MV88E6165_PORT_PTP_ARR1_TIME_HI	0x06
+
+/* Offset 0x07: PTP Arrival 1 Sequence ID */
+#define MV88E6165_PORT_PTP_ARR1_SEQID	0x07
+
+/* Offset 0x08: PTP Departure Status */
+#define MV88E6165_PORT_PTP_DEP_STS	0x08
+
+/* Offset 0x09/0x0a: PTP Deperture Time */
+#define MV88E6165_PORT_PTP_DEP_TIME_LO	0x09
+#define MV88E6165_PORT_PTP_DEP_TIME_HI	0x0a
+
+/* Offset 0x0b: PTP Departure Sequence ID */
+#define MV88E6165_PORT_PTP_DEP_SEQID	0x0b
+
+/* Offset 0x0d: Port Status */
+#define MV88E6164_PORT_STATUS		0x0d
+
 #ifdef CONFIG_NET_DSA_MV88E6XXX_PTP
 
 long mv88e6xxx_hwtstamp_work(struct ptp_clock_info *ptp);
-- 
cgit v1.2.3


From 2dbed245b408f3e458345b974c862447a73c73c0 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:26 +0200
Subject: net: dsa: mv88e6xxx: Set PTP Ethertype

For the 6352 and newer switches, the PTP Ethertype defaults to
ETH_P_1588. Hence it was not explicitly set. The 6165 however defaults
to 0. So explicitly set the EtherType.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/hwtstamp.c | 5 +++++
 drivers/net/dsa/mv88e6xxx/ptp.h      | 3 +++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index 01e60a8c97fb..ac71910c63c0 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -606,6 +606,11 @@ int mv88e6xxx_hwtstamp_setup(struct mv88e6xxx_chip *chip)
 			return err;
 	}
 
+	/* Set the ethertype of L2 PTP messages */
+	err = mv88e6xxx_ptp_write(chip, MV88E6XXX_PTP_GC_ETYPE, ETH_P_1588);
+	if (err)
+		return err;
+
 	/* MV88E6XXX_PTP_MSG_TYPE is a mask of PTP message types to
 	 * timestamp. This affects all ports that have timestamping enabled,
 	 * but the timestamp config is per-port; thus we configure all events
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.h b/drivers/net/dsa/mv88e6xxx/ptp.h
index 747f90bb9393..28a030840517 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.h
+++ b/drivers/net/dsa/mv88e6xxx/ptp.h
@@ -82,6 +82,9 @@
 #define MV88E6XXX_PTP_GC_ETYPE			0x00
 
 /* 6165 Global Control Registers */
+/* Offset 0x00: Ether Type */
+#define MV88E6XXX_PTP_GC_ETYPE			0x00
+
 /* Offset 0x01: Message ID */
 #define MV88E6XXX_PTP_GC_MESSAGE_ID		0x01
 
-- 
cgit v1.2.3


From df31b74ce132c20d309aaada8b2fb67c35da5fad Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 22:38:27 +0200
Subject: net: dsa: mv88e6xxx: Longer timeout for PTP TX timestamp

For slow processors using bit-banging MDIO, 20ms can be too short a
timeout when waiting for the transmit timestamp to become
available. Double it to 40ms.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/hwtstamp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/hwtstamp.c b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
index ac71910c63c0..a17c16a2ab78 100644
--- a/drivers/net/dsa/mv88e6xxx/hwtstamp.c
+++ b/drivers/net/dsa/mv88e6xxx/hwtstamp.c
@@ -65,7 +65,7 @@ static int mv88e6xxx_ptp_read(struct mv88e6xxx_chip *chip, int addr,
  * within 1ms. Software may enounter delays due to MDIO contention, so
  * the timeout is set accordingly.
  */
-#define TX_TSTAMP_TIMEOUT	msecs_to_jiffies(20)
+#define TX_TSTAMP_TIMEOUT	msecs_to_jiffies(40)
 
 int mv88e6xxx_get_ts_info(struct dsa_switch *ds, int port,
 			  struct ethtool_ts_info *info)
-- 
cgit v1.2.3


From 0015b80abccecca82622d9e9d48eb210572a0c3b Mon Sep 17 00:00:00 2001
From: Salvatore Mesoraca <s.mesoraca16@gmail.com>
Date: Mon, 16 Jul 2018 21:10:34 -0700
Subject: net: dsa: Remove VLA usage

We avoid 2 VLAs by using a pre-allocated field in dsa_switch. We also
try to avoid dynamic allocation whenever possible (when using fewer than
bits-per-long ports, which is the common case).

Link: http://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com
Link: http://lkml.kernel.org/r/20180505185145.GB32630@lunn.ch
Signed-off-by: Salvatore Mesoraca <s.mesoraca16@gmail.com>
[kees: tweak commit subject and message slightly]
Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  3 +++
 net/dsa/dsa2.c    | 14 ++++++++++++++
 net/dsa/switch.c  | 22 ++++++++++------------
 3 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/include/net/dsa.h b/include/net/dsa.h
index fdbd6082945d..461e8a7661b7 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -259,6 +259,9 @@ struct dsa_switch {
 	/* Number of switch port queues */
 	unsigned int		num_tx_queues;
 
+	unsigned long		*bitmap;
+	unsigned long		_bitmap;
+
 	/* Dynamically allocated ports, keep last */
 	size_t num_ports;
 	struct dsa_port ports[];
diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c
index dc5d9af3dc80..a1917025e155 100644
--- a/net/dsa/dsa2.c
+++ b/net/dsa/dsa2.c
@@ -775,6 +775,20 @@ struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n)
 	if (!ds)
 		return NULL;
 
+	/* We avoid allocating memory outside dsa_switch
+	 * if it is not needed.
+	 */
+	if (n <= sizeof(ds->_bitmap) * 8) {
+		ds->bitmap = &ds->_bitmap;
+	} else {
+		ds->bitmap = devm_kcalloc(dev,
+					  BITS_TO_LONGS(n),
+					  sizeof(unsigned long),
+					  GFP_KERNEL);
+		if (unlikely(!ds->bitmap))
+			return NULL;
+	}
+
 	ds->dev = dev;
 	ds->num_ports = n;
 
diff --git a/net/dsa/switch.c b/net/dsa/switch.c
index b93511726069..142b294d3446 100644
--- a/net/dsa/switch.c
+++ b/net/dsa/switch.c
@@ -136,21 +136,20 @@ static int dsa_switch_mdb_add(struct dsa_switch *ds,
 {
 	const struct switchdev_obj_port_mdb *mdb = info->mdb;
 	struct switchdev_trans *trans = info->trans;
-	DECLARE_BITMAP(group, ds->num_ports);
 	int port;
 
 	/* Build a mask of Multicast group members */
-	bitmap_zero(group, ds->num_ports);
+	bitmap_zero(ds->bitmap, ds->num_ports);
 	if (ds->index == info->sw_index)
-		set_bit(info->port, group);
+		set_bit(info->port, ds->bitmap);
 	for (port = 0; port < ds->num_ports; port++)
 		if (dsa_is_dsa_port(ds, port))
-			set_bit(port, group);
+			set_bit(port, ds->bitmap);
 
 	if (switchdev_trans_ph_prepare(trans))
-		return dsa_switch_mdb_prepare_bitmap(ds, mdb, group);
+		return dsa_switch_mdb_prepare_bitmap(ds, mdb, ds->bitmap);
 
-	dsa_switch_mdb_add_bitmap(ds, mdb, group);
+	dsa_switch_mdb_add_bitmap(ds, mdb, ds->bitmap);
 
 	return 0;
 }
@@ -204,21 +203,20 @@ static int dsa_switch_vlan_add(struct dsa_switch *ds,
 {
 	const struct switchdev_obj_port_vlan *vlan = info->vlan;
 	struct switchdev_trans *trans = info->trans;
-	DECLARE_BITMAP(members, ds->num_ports);
 	int port;
 
 	/* Build a mask of VLAN members */
-	bitmap_zero(members, ds->num_ports);
+	bitmap_zero(ds->bitmap, ds->num_ports);
 	if (ds->index == info->sw_index)
-		set_bit(info->port, members);
+		set_bit(info->port, ds->bitmap);
 	for (port = 0; port < ds->num_ports; port++)
 		if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
-			set_bit(port, members);
+			set_bit(port, ds->bitmap);
 
 	if (switchdev_trans_ph_prepare(trans))
-		return dsa_switch_vlan_prepare_bitmap(ds, vlan, members);
+		return dsa_switch_vlan_prepare_bitmap(ds, vlan, ds->bitmap);
 
-	dsa_switch_vlan_add_bitmap(ds, vlan, members);
+	dsa_switch_vlan_add_bitmap(ds, vlan, ds->bitmap);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 088cbac6bea4d383b9e01f042b50fe00898714f5 Mon Sep 17 00:00:00 2001
From: Keara Leibovitz <kleib@mojatatu.com>
Date: Tue, 17 Jul 2018 12:12:54 -0400
Subject: tc-tests: initial version of fw filter unit tests

Create initial unit tests for the tc fw filter.

Signed-off-by: Keara Leibovitz <kleib@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/tc-testing/tc-tests/filters/fw.json  | 1049 ++++++++++++++++++++
 1 file changed, 1049 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/filters/fw.json

diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
new file mode 100644
index 000000000000..3b97cfd7e0f8
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/fw.json
@@ -0,0 +1,1049 @@
+[
+    {
+        "id": "901f",
+        "name": "Add fw filter with prio at 32-bit maxixum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 65535 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 65535 protocol all fw",
+        "matchPattern": "pref 65535 fw.*handle 0x1.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "51e2",
+        "name": "Add fw filter with prio exceeding 32-bit maxixum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 65536 fw action ok",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 65536 protocol all fw",
+        "matchPattern": "pref 65536 fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "d987",
+        "name": "Add fw filter with action ok",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "affe",
+        "name": "Add fw filter with action continue",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action continue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "28bc",
+        "name": "Add fw filter with action pipe",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8da2",
+        "name": "Add fw filter with action drop",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol all prio 1 fw",
+        "matchPattern": "handle 0x1.*gact action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9436",
+        "name": "Add fw filter with action reclassify",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action reclassify",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "95bb",
+        "name": "Add fw filter with action jump 10",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action jump 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action jump 10",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "3d74",
+        "name": "Add fw filter with action goto chain 5",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action goto chain 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action goto chain 5",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "eb8f",
+        "name": "Add fw filter with invalid action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw action pump",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "handle 0x1.*gact action pump",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "6a79",
+        "name": "Add fw filter with missing mandatory action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "filter protocol all pref [0-9]+ fw.*handle 0x1",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8298",
+        "name": "Add fw filter with cookie",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action pipe cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 2 protocol all fw",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action pipe.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "a88c",
+        "name": "Add fw filter with invalid cookie",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action continue cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 2 protocol all fw",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action continue.*cookie aa11bb22cc33dd44ee55ff66aa11b1b2777888",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "10f6",
+        "name": "Add fw filter with handle in hex",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0xa1b2ff prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xa1b2ff prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa1b2ff.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9d51",
+        "name": "Add fw filter with handle at 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967295 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4294967295 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xffffffff.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "d939",
+        "name": "Add fw filter with handle exceeding 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967296 prio 1 fw action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4294967296 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "658c",
+        "name": "Add fw filter with mask in hex",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10/0xa1b2f prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa/0xa1b2f",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "86be",
+        "name": "Add fw filter with mask at 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10/4294967295 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa[^/]",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "e635",
+        "name": "Add fw filter with mask exceeding 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10/4294967296 prio 1 fw action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "6cab",
+        "name": "Add fw filter with handle/mask in hex",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 0xa1b2cdff/0x1a2bffdc prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xa1b2cdff prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xa1b2cdff/0x1a2bffdc",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8700",
+        "name": "Add fw filter with handle/mask at 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967295/4294967295 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 0xffffffff prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0xffffffff[^/]",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "7d62",
+        "name": "Add fw filter with handle/mask exceeding 32-bit maximum",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 4294967296/4294967296 prio 1 fw action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "7b69",
+        "name": "Add fw filter with missing mandatory handle",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 1 fw action ok",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "filter protocol all.*fw.*handle.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "d68b",
+        "name": "Add fw filter with invalid parent",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent aa11b1b2: handle 1 prio 1 fw action ok",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter dev $DEV1 parent aa11b1b2: handle 1 prio 1 protocol all fw",
+        "matchPattern": "filter protocol all pref 1 fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "66e0",
+        "name": "Add fw filter with missing mandatory parent id",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 handle 1 prio 1 fw action ok",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "pref [0-9]+ fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "0ff3",
+        "name": "Add fw filter with classid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid 3 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x1 classid :3.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9849",
+        "name": "Add fw filter with classid at root",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid ffff:ffff action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "pref 1 fw.*handle 0x1 classid root.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "b7ff",
+        "name": "Add fw filter with classid - keeps last 8 (hex) digits",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid 98765fedcb action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x1 classid 765f:edcb.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "2b18",
+        "name": "Add fw filter with invalid classid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 fw classid 6789defg action ok",
+        "expExitCode": "1",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol all fw",
+        "matchPattern": "fw.*handle 0x1 classid 6789:defg.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "fade",
+        "name": "Add fw filter with flowid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 10 prio 1 fw flowid 1:10 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 1 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 1 fw.*handle 0xa classid 1:10.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "33af",
+        "name": "Add fw filter with flowid then classid (same arg, takes second)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 11 prio 1 fw flowid 10 classid 4 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 11 prio 1 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 1 fw.*handle 0xb classid :4.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "8a8c",
+        "name": "Add fw filter with classid then flowid (same arg, takes second)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 11 prio 1 fw classid 4 flowid 10 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 11 prio 1 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 1 fw.*handle 0xb classid :10.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "b50d",
+        "name": "Add fw filter with handle val/mask and flowid 10:1000",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 3 handle 10/0xff fw flowid 10:1000 action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 10 prio 3 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 3 fw.*handle 0xa/0xff classid 10:1000.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "7207",
+        "name": "Add fw filter with protocol ip",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 handle 3 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 3 prio 1 protocol ip fw",
+        "matchPattern": "filter parent ffff: protocol ip pref 1 fw.*handle 0x3.*gact action pass.*index [0-9]+ ref [0-9]+ bind [0-9]+",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "306d",
+        "name": "Add fw filter with protocol ipv6",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ipv6 prio 2 handle 4 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 2 protocol ipv6 fw",
+        "matchPattern": "filter parent ffff: protocol ipv6 pref 2 fw.*handle 0x4.*gact action pass.*index [0-9]+ ref [0-9]+ bind [0-9]+",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "9a78",
+        "name": "Add fw filter with protocol arp",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol arp prio 5 handle 7 fw action drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 7 prio 5 protocol arp fw",
+        "matchPattern": "filter parent ffff: protocol arp pref 5 fw.*handle 0x7.*gact action drop.*index [0-9]+ ref [0-9]+ bind [0-9]+",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "1821",
+        "name": "Add fw filter with protocol 802_3",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol 802_3 handle 1 prio 1 fw action ok",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol 802_3 fw",
+        "matchPattern": "filter parent ffff: protocol 802_3 pref 1 fw.*handle 0x1.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "2260",
+        "name": "Add fw filter with invalid protocol",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol igmp handle 1 prio 1 fw action ok",
+        "expExitCode": "255",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 prio 1 protocol igmp fw",
+        "matchPattern": "filter parent ffff: protocol igmp pref 1 fw.*handle 0x1.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "09d7",
+        "name": "Add fw filters protocol 802_3 and ip with conflicting priorities",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: protocol 802_3 prio 3 handle 7 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 3 handle 8 fw action ok",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 8 prio 3 protocol ip fw",
+        "matchPattern": "filter parent ffff: protocol ip pref 3 fw.*handle 0x8",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "6973",
+        "name": "Add fw filters with same index, same action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: prio 6 handle 2 fw action continue index 5"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 8 handle 4 fw action continue index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 8 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 8 fw.*handle 0x4.*gact action continue.*index 5 ref 2 bind 2",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "fc06",
+        "name": "Add fw filters with action police",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 3 handle 4 fw action police rate 1kbit burst 10k index 5",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 3 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 3 fw.*handle 0x4.*police 0x5 rate 1Kbit burst 10Kb mtu 2Kb action reclassify overhead 0b.*ref 1 bind 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "aac7",
+        "name": "Add fw filters with action police linklayer atm",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress"
+        ],
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: prio 3 handle 4 fw action police rate 2mbit burst 200k linklayer atm index 8",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 3 protocol all fw",
+        "matchPattern": "filter parent ffff: protocol all pref 3 fw.*handle 0x4.*police 0x8 rate 2Mbit burst 200Kb mtu 2Kb action reclassify overhead 0b linklayer atm.*ref 1 bind 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "5339",
+        "name": "Del entire fw filter",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 5 prio 7 fw action pass",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 9 fw action pass"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff:",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "protocol all pref.*handle.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "0e99",
+        "name": "Del single fw filter x1",
+        "__comment__": "First of two tests to check that one filter is there and the other isn't",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 5 prio 7 fw action pass",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 9 fw action pass"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 3 prio 9 fw action pass",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "protocol all pref 7.*handle 0x5.*gact action pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "f54c",
+        "name": "Del single fw filter x2",
+        "__comment__": "Second of two tests to check that one filter is there and the other isn't",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 5 prio 7 fw action pass",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 9 fw action pass"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 3 prio 9 fw action pass",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "protocol all pref 9.*handle 0x3.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "ba94",
+        "name": "Del fw filter by prio",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 4 fw action ok",
+            "$TC filter add dev $DEV1 parent ffff: handle 2 prio 4 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: prio 4",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 4 fw.*gact action pass",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "4acb",
+        "name": "Del fw filter by chain",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 4 prio 2 chain 13 fw action pipe",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 5 chain 13 fw action pipe"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: chain 13",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "fw chain 13 handle.*gact action pipe",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "3424",
+        "name": "Del fw filter by action (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 2 prio 4 fw action drop"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: fw action drop",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 2 prio 4 protocol all fw",
+        "matchPattern": "handle 0x2.*gact action drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "da89",
+        "name": "Del fw filter by handle (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 3 prio 4 fw action continue"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: handle 3 fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 3 prio 4 protocol all fw",
+        "matchPattern": "handle 0x3.*gact action continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "4d95",
+        "name": "Del fw filter by protocol (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 4 prio 2 protocol arp fw action pipe"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: protocol arp fw",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 4 prio 2 protocol arp fw",
+        "matchPattern": "filter parent ffff: protocol arp.*handle 0x4.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "4736",
+        "name": "Del fw filter by flowid (invalid)",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 4 prio 2 fw action pipe flowid 45"
+        ],
+        "cmdUnderTest": "$TC filter del dev $DEV1 parent ffff: fw flowid 45",
+        "expExitCode": "2",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "handle 0x4.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "3dcb",
+        "name": "Replace fw filter action",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: handle 1 prio 2 fw action pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "eb4d",
+        "name": "Replace fw filter classid",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action ok"
+        ],
+        "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: handle 1 prio 2 fw action pipe classid 2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 2 fw.*handle 0x1 classid :2.*gact action pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    },
+    {
+        "id": "67ec",
+        "name": "Replace fw filter index",
+        "category": [
+            "filter",
+            "fw"
+        ],
+        "setup": [
+            "$TC qdisc add dev $DEV1 ingress",
+            "$TC filter add dev $DEV1 parent ffff: handle 1 prio 2 fw action ok index 3"
+        ],
+        "cmdUnderTest": "$TC filter replace dev $DEV1 parent ffff: handle 1 prio 2 fw action ok index 16",
+        "expExitCode": "0",
+        "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
+        "matchPattern": "pref 2 fw.*handle 0x1.*gact action pass.*index 16",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DEV1 ingress"
+        ]
+    }
+]
-- 
cgit v1.2.3


From f15f084ff11519172c67fac4dde61daf4e9ad345 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 17 Jul 2018 14:32:24 -0700
Subject: pktgen: convert safe uses of strncpy() to strcpy() to avoid string
 truncation warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC 8 complains:

net/core/pktgen.c: In function ‘pktgen_if_write’:
net/core/pktgen.c:1419:4: warning: ‘strncpy’ output may be truncated copying between 0 and 31 bytes from a string of length 127 [-Wstringop-truncation]
    strncpy(pkt_dev->src_max, buf, len);
    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
net/core/pktgen.c:1399:4: warning: ‘strncpy’ output may be truncated copying between 0 and 31 bytes from a string of length 127 [-Wstringop-truncation]
    strncpy(pkt_dev->src_min, buf, len);
    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
net/core/pktgen.c:1290:4: warning: ‘strncpy’ output may be truncated copying between 0 and 31 bytes from a string of length 127 [-Wstringop-truncation]
    strncpy(pkt_dev->dst_max, buf, len);
    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
net/core/pktgen.c:1268:4: warning: ‘strncpy’ output may be truncated copying between 0 and 31 bytes from a string of length 127 [-Wstringop-truncation]
    strncpy(pkt_dev->dst_min, buf, len);
    ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

There is no bug here, but the code is not perfect either.  It copies
sizeof(pkt_dev->/member/) - 1 from user space into buf, and then does
a strcmp(pkt_dev->/member/, buf) hence assuming buf will be null-terminated
and shorter than pkt_dev->/member/ (pkt_dev->/member/ is never
explicitly null-terminated, and strncpy() doesn't have to null-terminate
so the assumption must be on buf).  The use of strncpy() without explicit
null-termination looks suspicious.  Convert to use straight strcpy().

strncpy() would also null-pad the output, but that's clearly unnecessary
since the author calls memset(pkt_dev->/member/, 0, sizeof(..)); prior
to strncpy(), anyway.

While at it format the code for "dst_min", "dst_max", "src_min" and
"src_max" in the same way by removing extra new lines in one case.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Jiong Wang <jiong.wang@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/pktgen.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 49368e21d228..308ed04984de 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1265,7 +1265,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->dst_min) != 0) {
 			memset(pkt_dev->dst_min, 0, sizeof(pkt_dev->dst_min));
-			strncpy(pkt_dev->dst_min, buf, len);
+			strcpy(pkt_dev->dst_min, buf);
 			pkt_dev->daddr_min = in_aton(pkt_dev->dst_min);
 			pkt_dev->cur_daddr = pkt_dev->daddr_min;
 		}
@@ -1280,14 +1280,12 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-
 		if (copy_from_user(buf, &user_buffer[i], len))
 			return -EFAULT;
-
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->dst_max) != 0) {
 			memset(pkt_dev->dst_max, 0, sizeof(pkt_dev->dst_max));
-			strncpy(pkt_dev->dst_max, buf, len);
+			strcpy(pkt_dev->dst_max, buf);
 			pkt_dev->daddr_max = in_aton(pkt_dev->dst_max);
 			pkt_dev->cur_daddr = pkt_dev->daddr_max;
 		}
@@ -1396,7 +1394,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->src_min) != 0) {
 			memset(pkt_dev->src_min, 0, sizeof(pkt_dev->src_min));
-			strncpy(pkt_dev->src_min, buf, len);
+			strcpy(pkt_dev->src_min, buf);
 			pkt_dev->saddr_min = in_aton(pkt_dev->src_min);
 			pkt_dev->cur_saddr = pkt_dev->saddr_min;
 		}
@@ -1416,7 +1414,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		buf[len] = 0;
 		if (strcmp(buf, pkt_dev->src_max) != 0) {
 			memset(pkt_dev->src_max, 0, sizeof(pkt_dev->src_max));
-			strncpy(pkt_dev->src_max, buf, len);
+			strcpy(pkt_dev->src_max, buf);
 			pkt_dev->saddr_max = in_aton(pkt_dev->src_max);
 			pkt_dev->cur_saddr = pkt_dev->saddr_max;
 		}
-- 
cgit v1.2.3


From 735dadf894f091bc15c06aedf8c1e99f971d3962 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Wed, 18 Jul 2018 13:27:35 +1000
Subject: docs: networking: Convert alias.txt to rst

The kernel documentation is now restructured text. Convert the IP
aliasing documentation and include it in the toplevel kernel
documentation.

 - Fix heading adornments.
 - Correctly indent code snippets.
 - Limit line length to 72 characters inline with kernel documentation
   standards.
 - Add license identifier.

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/00-INDEX  |  2 --
 Documentation/networking/alias.rst | 49 ++++++++++++++++++++++++++++++++++++++
 Documentation/networking/alias.txt | 40 -------------------------------
 Documentation/networking/index.rst |  1 +
 4 files changed, 50 insertions(+), 42 deletions(-)
 create mode 100644 Documentation/networking/alias.rst
 delete mode 100644 Documentation/networking/alias.txt

diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 2b89d91b376f..1e5153ed8990 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -18,8 +18,6 @@ README.ipw2200
 	- README for the Intel PRO/Wireless 2915ABG and 2200BG driver.
 README.sb1000
 	- info on General Instrument/NextLevel SURFboard1000 cable modem.
-alias.txt
-	- info on using alias network devices.
 altera_tse.txt
 	- Altera Triple-Speed Ethernet controller.
 arcnet-hardware.txt
diff --git a/Documentation/networking/alias.rst b/Documentation/networking/alias.rst
new file mode 100644
index 000000000000..af7c5ee92014
--- /dev/null
+++ b/Documentation/networking/alias.rst
@@ -0,0 +1,49 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+===========
+IP-Aliasing
+===========
+
+IP-aliases are an obsolete way to manage multiple IP-addresses/masks
+per interface. Newer tools such as iproute2 support multiple
+address/prefixes per interface, but aliases are still supported
+for backwards compatibility.
+
+An alias is formed by adding a colon and a string when running ifconfig.
+This string is usually numeric, but this is not a must.
+
+
+Alias creation
+==============
+
+Alias creation is done by 'magic' interface naming: eg. to create a
+200.1.1.1 alias for eth0 ...
+::
+
+  # ifconfig eth0:0 200.1.1.1  etc,etc....
+	~~ -> request alias #0 creation (if not yet exists) for eth0
+
+The corresponding route is also set up by this command.  Please note:
+The route always points to the base interface.
+
+
+Alias deletion
+==============
+
+The alias is removed by shutting the alias down::
+
+  # ifconfig eth0:0 down
+	~~~~~~~~~~ -> will delete alias
+
+
+Alias (re-)configuring
+======================
+
+Aliases are not real devices, but programs should be able to configure
+and refer to them as usual (ifconfig, route, etc).
+
+
+Relationship with main device
+=============================
+
+If the base device is shut down the added aliases will be deleted too.
diff --git a/Documentation/networking/alias.txt b/Documentation/networking/alias.txt
deleted file mode 100644
index 85046f53fcfc..000000000000
--- a/Documentation/networking/alias.txt
+++ /dev/null
@@ -1,40 +0,0 @@
-
-IP-Aliasing:
-============
-
-IP-aliases are an obsolete way to manage multiple IP-addresses/masks
-per interface. Newer tools such as iproute2 support multiple
-address/prefixes per interface, but aliases are still supported
-for backwards compatibility.
-
-An alias is formed by adding a colon and a string when running ifconfig.
-This string is usually numeric, but this is not a must.
-
-o Alias creation.
-  Alias creation is done by 'magic' interface naming: eg. to create a
-  200.1.1.1 alias for eth0 ...
-  
-    # ifconfig eth0:0 200.1.1.1  etc,etc....
-                   ~~ -> request alias #0 creation (if not yet exists) for eth0
-
-    The corresponding route is also set up by this command. 
-    Please note: The route always points to the base interface.
-	
-
-o Alias deletion.
-  The alias is removed by shutting the alias down:
-
-    # ifconfig eth0:0 down
-                 ~~~~~~~~~~ -> will delete alias
-
-  		   		   
-o Alias (re-)configuring
-
-  Aliases are not real devices, but programs should be able to configure and
-  refer to them as usual (ifconfig, route, etc).
-
-
-o Relationship with main device
-
-  If the base device is shut down the added aliases will be deleted 
-  too.
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 6123a7e9e1da..06bdd8232b2a 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -17,6 +17,7 @@ Contents:
    msg_zerocopy
    failover
    net_failover
+   alias
 
 .. only::  subproject
 
-- 
cgit v1.2.3


From 6b335f8205e9d47569ebb2db90ede2c4aa7615ce Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Wed, 18 Jul 2018 13:27:36 +1000
Subject: docs: networking: Convert bridge.txt to rst

The kernel documentation is now restructured text. Convert the Ethernet
Bridge documentation and include it in the toplevel kernel
documentation.

 - Fix heading adornments.
 - Add license identifier.

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/bridge.rst | 21 +++++++++++++++++++++
 Documentation/networking/bridge.txt | 15 ---------------
 Documentation/networking/index.rst  |  1 +
 3 files changed, 22 insertions(+), 15 deletions(-)
 create mode 100644 Documentation/networking/bridge.rst
 delete mode 100644 Documentation/networking/bridge.txt

diff --git a/Documentation/networking/bridge.rst b/Documentation/networking/bridge.rst
new file mode 100644
index 000000000000..4aef9cddde2f
--- /dev/null
+++ b/Documentation/networking/bridge.rst
@@ -0,0 +1,21 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=================
+Ethernet Bridging
+=================
+
+In order to use the Ethernet bridging functionality, you'll need the
+userspace tools.
+
+Documentation for Linux bridging is on:
+   http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge
+
+The bridge-utilities are maintained at:
+   git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/bridge-utils.git
+
+Additionally, the iproute2 utilities can be used to configure
+bridge devices.
+
+If you still have questions, don't hesitate to post to the mailing list 
+(more info https://lists.linux-foundation.org/mailman/listinfo/bridge).
+
diff --git a/Documentation/networking/bridge.txt b/Documentation/networking/bridge.txt
deleted file mode 100644
index a27cb6214ed7..000000000000
--- a/Documentation/networking/bridge.txt
+++ /dev/null
@@ -1,15 +0,0 @@
-In order to use the Ethernet bridging functionality, you'll need the
-userspace tools.
-
-Documentation for Linux bridging is on:
-   http://www.linuxfoundation.org/collaborate/workgroups/networking/bridge
-
-The bridge-utilities are maintained at:
-   git://git.kernel.org/pub/scm/linux/kernel/git/shemminger/bridge-utils.git
-
-Additionally, the iproute2 utilities can be used to configure
-bridge devices.
-
-If you still have questions, don't hesitate to post to the mailing list 
-(more info https://lists.linux-foundation.org/mailman/listinfo/bridge).
-
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 06bdd8232b2a..f0ae9b65dfba 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -18,6 +18,7 @@ Contents:
    failover
    net_failover
    alias
+   bridge
 
 .. only::  subproject
 
-- 
cgit v1.2.3


From 3a477d4efc57adeb3b2bfd6ccedf6f20d275ae1b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 12 Jul 2018 17:01:31 +0900
Subject: um: remove redundant 'export LDFLAGS' in arch/x86/Makefile.um

This is already exported by the top-level Makefile.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/Makefile.um | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 45af19921ebd..5296f8c9e7f0 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -13,8 +13,6 @@ KBUILD_CFLAGS		+= $(call cc-option,-m32)
 KBUILD_AFLAGS		+= $(call cc-option,-m32)
 LINK-y			+= $(call cc-option,-m32)
 
-export LDFLAGS
-
 LDS_EXTRA		:= -Ui386
 export LDS_EXTRA
 
-- 
cgit v1.2.3


From ec33408a2279b7c72fc09eb4c7fba805e3ec5afe Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 12 Jul 2018 17:01:33 +0900
Subject: kbuild: remove redundant LDFLAGS clearing in arch/*/Makefile

Since commit ce99d0bf312d ("kbuild: clear LDFLAGS in the top Makefile"),
the top-level Makefile caters to this.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/arm/Makefile      | 3 ---
 arch/openrisc/Makefile | 1 -
 arch/riscv/Makefile    | 1 -
 3 files changed, 5 deletions(-)

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index fc26c3d7b9b6..0306640602e7 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -10,9 +10,6 @@
 #
 # Copyright (C) 1995-2001 by Russell King
 
-# Ensure linker flags are correct
-LDFLAGS		:=
-
 LDFLAGS_vmlinux	:=-p --no-undefined -X --pic-veneer
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux	+= --be8
diff --git a/arch/openrisc/Makefile b/arch/openrisc/Makefile
index 89076a66eee2..70e06d34006c 100644
--- a/arch/openrisc/Makefile
+++ b/arch/openrisc/Makefile
@@ -19,7 +19,6 @@
 
 KBUILD_DEFCONFIG := or1ksim_defconfig
 
-LDFLAGS         :=
 OBJCOPYFLAGS    := -O binary -R .note -R .comment -S
 LDFLAGS_vmlinux :=
 LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
diff --git a/arch/riscv/Makefile b/arch/riscv/Makefile
index 6d4a5f6c3f4f..2627e4813edf 100644
--- a/arch/riscv/Makefile
+++ b/arch/riscv/Makefile
@@ -8,7 +8,6 @@
 # for more details.
 #
 
-LDFLAGS         :=
 OBJCOPYFLAGS    := -O binary
 LDFLAGS_vmlinux :=
 ifeq ($(CONFIG_DYNAMIC_FTRACE),y)
-- 
cgit v1.2.3


From f60b992e30ffef82fd6cd317c6fba3ccaacbe921 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 12 Jul 2018 17:01:34 +0900
Subject: kbuild: replace $(LDFLAGS) $(ldflags-y) with $(ld_flags)

$(LDFLAGS) $(ldflags-y) is equivalent to $(ld_flags).

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 scripts/Makefile.lib | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 1bb594fcfe12..19155748063b 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -225,8 +225,7 @@ $(obj)/%: $(src)/%_shipped
 # ---------------------------------------------------------------------------
 
 quiet_cmd_ld = LD      $@
-cmd_ld = $(LD) $(LDFLAGS) $(ldflags-y) $(LDFLAGS_$(@F)) \
-	       $(filter-out FORCE,$^) -o $@
+cmd_ld = $(LD) $(ld_flags) $(LDFLAGS_$(@F)) $(filter-out FORCE,$^) -o $@
 
 # Objcopy
 # ---------------------------------------------------------------------------
-- 
cgit v1.2.3


From 2fb9279f2c3e021745d5c461894a0f6c3690db7b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 12 Jul 2018 17:01:35 +0900
Subject: kbuild: change ld_flags to contain LDFLAGS_$(@F)

Put $(LDFLAGS_$(@F)) into ld_flags so that $(LDFLAGS_pcap.o) and
$(LDFLAGS_vde.o) in arch/um/drivers/Makefile are absorbed.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/um/drivers/Makefile | 4 ++--
 scripts/Makefile.lib     | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/um/drivers/Makefile b/arch/um/drivers/Makefile
index 16b3cebddafb..693319839f69 100644
--- a/arch/um/drivers/Makefile
+++ b/arch/um/drivers/Makefile
@@ -25,10 +25,10 @@ LDFLAGS_vde.o := -r $(shell $(CC) $(CFLAGS) -print-file-name=libvdeplug.a)
 targets := pcap_kern.o pcap_user.o vde_kern.o vde_user.o
 
 $(obj)/pcap.o: $(obj)/pcap_kern.o $(obj)/pcap_user.o
-	$(LD) -r -dp -o $@ $^ $(LDFLAGS) $(LDFLAGS_pcap.o)
+	$(LD) -r -dp -o $@ $^ $(ld_flags)
 
 $(obj)/vde.o: $(obj)/vde_kern.o $(obj)/vde_user.o
-	$(LD) -r -dp -o $@ $^ $(LDFLAGS) $(LDFLAGS_vde.o)
+	$(LD) -r -dp -o $@ $^ $(ld_flags)
 
 #XXX: The call below does not work because the flags are added before the
 # object name, so nothing from the library gets linked.
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 19155748063b..f56bb4b8bc60 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -162,7 +162,7 @@ a_flags        = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 cpp_flags      = -Wp,-MD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE)     \
 		 $(__cpp_flags)
 
-ld_flags       = $(LDFLAGS) $(ldflags-y)
+ld_flags       = $(LDFLAGS) $(ldflags-y) $(LDFLAGS_$(@F))
 
 DTC_INCLUDE    := $(srctree)/scripts/dtc/include-prefixes
 
@@ -225,7 +225,7 @@ $(obj)/%: $(src)/%_shipped
 # ---------------------------------------------------------------------------
 
 quiet_cmd_ld = LD      $@
-cmd_ld = $(LD) $(ld_flags) $(LDFLAGS_$(@F)) $(filter-out FORCE,$^) -o $@
+cmd_ld = $(LD) $(ld_flags) $(filter-out FORCE,$^) -o $@
 
 # Objcopy
 # ---------------------------------------------------------------------------
-- 
cgit v1.2.3


From 33c362bbc0748dec3a4d3c119a9a5f4b7f7062a7 Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Fri, 13 Jul 2018 09:24:57 -0700
Subject: kbuild: buildtar: remove crufty vax pieces

ARCH=vax isn't in mainline; it can be added back if/when it shows up.

Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/buildtar | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index e8cc72a51b32..55887ac84ee4 100755
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -84,10 +84,6 @@ case "${ARCH}" in
 		[ -f "${KBUILD_IMAGE}" ] && cp -v -- "${KBUILD_IMAGE}" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
 		[ -f "${objtree}/lifimage" ] && cp -v -- "${objtree}/lifimage" "${tmpdir}/boot/lifimage-${KERNELRELEASE}"
 		;;
-	vax)
-		[ -f "${objtree}/vmlinux.SYS" ] && cp -v -- "${objtree}/vmlinux.SYS" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}.SYS"
-		[ -f "${objtree}/vmlinux.dsk" ] && cp -v -- "${objtree}/vmlinux.dsk" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}.dsk"
-		;;
 	mips)
 		if [ -f "${objtree}/arch/mips/boot/compressed/vmlinux.bin" ]; then
 			cp -v -- "${objtree}/arch/mips/boot/compressed/vmlinux.bin" "${tmpdir}/boot/vmlinuz-${KERNELRELEASE}"
-- 
cgit v1.2.3


From 0df57d90bfd6bb94831e70f4bcb4b7af784066cf Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Fri, 13 Jul 2018 09:24:58 -0700
Subject: kbuild: buildtar: add arm64 support

Make 'make tar-pkg' work on arm64.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/buildtar | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index 55887ac84ee4..d624a07a4e77 100755
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -105,6 +105,14 @@ case "${ARCH}" in
 			cp -v -- "${objtree}/vmlinux" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
 		fi
 		;;
+	arm64)
+		for i in Image.bz2 Image.gz Image.lz4 Image.lzma Image.lzo ; do
+			if [ -f "${objtree}/arch/arm64/boot/${i}" ] ; then
+				cp -v -- "${objtree}/arch/arm64/boot/${i}" "${tmpdir}/boot/vmlinuz-${KERNELRELEASE}"
+				break
+			fi
+		done
+		;;
 	*)
 		[ -f "${KBUILD_IMAGE}" ] && cp -v -- "${KBUILD_IMAGE}" "${tmpdir}/boot/vmlinux-kbuild-${KERNELRELEASE}"
 		echo "" >&2
-- 
cgit v1.2.3


From 7af2be6d54d4eda52603e87fbb99a8fb989ccdf0 Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Tue, 17 Jul 2018 14:10:58 -0700
Subject: drm/i915/icl: Add VIDEO_DIP registers

The Picture Parameter Set metadata for DSC has to be sent
to the panel through secondary data packets. Add the error
correction registers, data registers and control registers
for the same.

The control registers for  transcoders A and B are already
defined and will be reused for Icelake purpose. This patch adds
Control register for EDP and transcoder C apart from adding the
PPS data and error registers.

v2: reuse MMIO_TRANS2 for _PPS_DATA and _PPS_ECC.
The  _MMIO_TRANS2(pipe, reg) macro definition takes care of the eDp case

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531861861-10950-1-git-send-email-anusha.srivatsa@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 1f222af0324d..23e70a40d0cd 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -4605,6 +4605,16 @@ enum {
 #define   VIDEO_DIP_ENABLE_GMP_HSW	(1 << 4)
 #define   VIDEO_DIP_ENABLE_SPD_HSW	(1 << 0)
 
+#define  DRM_DIP_ENABLE			(1 << 28)
+#define  PSR_VSC_BIT_7_SET		(1 << 27)
+#define  VSC_SELECT_MASK		(0x3 << 26)
+#define  VSC_SELECT_SHIFT		26
+#define  VSC_DIP_HW_HEA_DATA		(0 << 26)
+#define  VSC_DIP_HW_HEA_SW_DATA		(1 << 26)
+#define  VSC_DIP_HW_DATA_SW_HEA		(2 << 26)
+#define  VSC_DIP_SW_HEA_DATA		(3 << 26)
+#define  VDIP_ENABLE_PPS		(1 << 24)
+
 /* Panel power sequencing */
 #define PPS_BASE			0x61200
 #define VLV_PPS_BASE			(VLV_DISPLAY_BASE + PPS_BASE)
@@ -7843,12 +7853,25 @@ enum {
 #define _HSW_VIDEO_DIP_VSC_ECC_B	0x61344
 #define _HSW_VIDEO_DIP_GCP_B		0x61210
 
+/* Icelake PPS_DATA and _ECC DIP Registers.
+ * These are available for transcoders B,C and eDP.
+ * Adding the _A so as to reuse the _MMIO_TRANS2
+ * definition, with which it offsets to the right location.
+ */
+
+#define _ICL_VIDEO_DIP_PPS_DATA_A	0x60350
+#define _ICL_VIDEO_DIP_PPS_DATA_B	0x61350
+#define _ICL_VIDEO_DIP_PPS_ECC_A	0x603D4
+#define _ICL_VIDEO_DIP_PPS_ECC_B	0x613D4
+
 #define HSW_TVIDEO_DIP_CTL(trans)		_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_CTL_A)
 #define HSW_TVIDEO_DIP_AVI_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_AVI_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_VS_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VS_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_SPD_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_SPD_DATA_A + (i) * 4)
 #define HSW_TVIDEO_DIP_GCP(trans)		_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_GCP_A)
 #define HSW_TVIDEO_DIP_VSC_DATA(trans, i)	_MMIO_TRANS2(trans, _HSW_VIDEO_DIP_VSC_DATA_A + (i) * 4)
+#define ICL_VIDEO_DIP_PPS_DATA(trans, i)	_MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_DATA_A + (i) * 4)
+#define ICL_VIDEO_DIP_PPS_ECC(trans, i)		_MMIO_TRANS2(trans, _ICL_VIDEO_DIP_PPS_ECC_A + (i) * 4)
 
 #define _HSW_STEREO_3D_CTL_A		0x70020
 #define   S3D_ENABLE			(1 << 31)
-- 
cgit v1.2.3


From 2efbb2f099fb75d95150bf2f4029b641ecbd1503 Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Tue, 17 Jul 2018 14:10:59 -0700
Subject: i915/dp/dsc: Add DSC PPS register definitions

Display Stream Compression(DSC) has a set of Picture
Parameter Set(PPS) components that the encoder must
communicate to the decoder.

This patch adds register definitions to
the PPS parameters for eDP/MIPI case and Display Port.

v2:
- Use _MMIO_PIPE instead of _MMIO(_PICK()). (Manasi)
- Use DSC constants as arguments. (Manasi)

Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531861861-10950-2-git-send-email-anusha.srivatsa@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 255 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 255 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 23e70a40d0cd..e8687b0f906d 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10244,4 +10244,259 @@ enum skl_power_gate {
 						 _ICL_PHY_MISC_B)
 #define  ICL_PHY_MISC_DE_IO_COMP_PWR_DOWN	(1 << 23)
 
+/* Icelake Display Stream Compression Registers */
+#define DSCA_PICTURE_PARAMETER_SET_0		0x6B200
+#define DSCC_PICTURE_PARAMETER_SET_0		0x6BA00
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB	0x78270
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB	0x78370
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC	0x78470
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC	0x78570
+#define ICL_DSC0_PICTURE_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_0_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_0_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_0(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_0_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_0_PC)
+#define  DSC_VBR_ENABLE			(1 << 19)
+#define  DSC_422_ENABLE			(1 << 18)
+#define  DSC_COLOR_SPACE_CONVERSION	(1 << 17)
+#define  DSC_BLOCK_PREDICTION		(1 << 16)
+#define  DSC_LINE_BUF_DEPTH_SHIFT	12
+#define  DSC_BPC_SHIFT			8
+#define  DSC_VER_MIN_SHIFT		4
+#define  DSC_VER_MAJ			(0x1 << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_1		0x6B204
+#define DSCC_PICTURE_PARAMETER_SET_1		0x6BA04
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB	0x78274
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB	0x78374
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC	0x78474
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC	0x78574
+#define ICL_DSC0_PICTURE_PARAMETER_SET_1(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_1_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_1_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_1(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_1_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_1_PC)
+#define  DSC_BPP(bpp)				((bpp) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_2		0x6B208
+#define DSCC_PICTURE_PARAMETER_SET_2		0x6BA08
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB	0x78278
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB	0x78378
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC	0x78478
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC	0x78578
+#define ICL_DSC0_PICTURE_PARAMETER_SET_2(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_2_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_2_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_2(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+					    _ICL_DSC1_PICTURE_PARAMETER_SET_2_PB, \
+					    _ICL_DSC1_PICTURE_PARAMETER_SET_2_PC)
+#define  DSC_PIC_WIDTH(pic_width)	((pic_width) << 16)
+#define  DSC_PIC_HEIGHT(pic_height)	((pic_height) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_3		0x6B20C
+#define DSCC_PICTURE_PARAMETER_SET_3		0x6BA0C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB	0x7827C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB	0x7837C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC	0x7847C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC	0x7857C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_3(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_3_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_3_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_3(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_3_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_3_PC)
+#define  DSC_SLICE_WIDTH(slice_width)   ((slice_width) << 16)
+#define  DSC_SLICE_HEIGHT(slice_height) ((slice_height) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_4		0x6B210
+#define DSCC_PICTURE_PARAMETER_SET_4		0x6BA10
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB	0x78280
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PB	0x78380
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC	0x78480
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC	0x78580
+#define ICL_DSC0_PICTURE_PARAMETER_SET_4(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_4(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_4_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_4_PC)
+#define  DSC_INITIAL_DEC_DELAY(dec_delay)       ((dec_delay) << 16)
+#define  DSC_INITIAL_XMIT_DELAY(xmit_delay)     ((xmit_delay) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_5		0x6B214
+#define DSCC_PICTURE_PARAMETER_SET_5		0x6BA14
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB	0x78284
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PB	0x78384
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC	0x78484
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC	0x78584
+#define ICL_DSC0_PICTURE_PARAMETER_SET_5(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_5_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_5_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_5(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_5_PC)
+#define  DSC_SCALE_DEC_INTINT(scale_dec)	((scale_dec) << 16)
+#define  DSC_SCALE_INC_INT(scale_inc)		((scale_inc) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_6		0x6B218
+#define DSCC_PICTURE_PARAMETER_SET_6		0x6BA18
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB	0x78288
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB	0x78388
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC	0x78488
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC	0x78588
+#define ICL_DSC0_PICTURE_PARAMETER_SET_6(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_6_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_6_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_6(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_6_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_6_PC)
+#define  DSC_FLATNESS_MAX_QP(max_qp)		(qp << 24)
+#define  DSC_FLATNESS_MIN_QP(min_qp)		(qp << 16)
+#define  DSC_FIRST_LINE_BPG_OFFSET(offset)	((offset) << 8)
+#define  DSC_INITIAL_SCALE_VALUE(value)		((value) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_7		0x6B21C
+#define DSCC_PICTURE_PARAMETER_SET_7		0x6BA1C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB	0x7828C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB	0x7838C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC	0x7848C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC	0x7858C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_7(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							    _ICL_DSC0_PICTURE_PARAMETER_SET_7_PB, \
+							    _ICL_DSC0_PICTURE_PARAMETER_SET_7_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_7(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							    _ICL_DSC1_PICTURE_PARAMETER_SET_7_PB, \
+							    _ICL_DSC1_PICTURE_PARAMETER_SET_7_PC)
+#define  DSC_NFL_BPG_OFFSET(bpg_offset)		((bpg_offset) << 16)
+#define  DSC_SLICE_BPG_OFFSET(bpg_offset)	((bpg_offset) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_8		0x6B220
+#define DSCC_PICTURE_PARAMETER_SET_8		0x6BA20
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB	0x78290
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB	0x78390
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC	0x78490
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC	0x78590
+#define ICL_DSC0_PICTURE_PARAMETER_SET_8(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_8_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_8_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_8(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_8_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_8_PC)
+#define  DSC_INITIAL_OFFSET(initial_offset)		((initial_offset) << 16)
+#define  DSC_FINAL_OFFSET(final_offset)			((final_offset) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_9		0x6B224
+#define DSCC_PICTURE_PARAMETER_SET_9		0x6BA24
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB	0x78294
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB	0x78394
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC	0x78494
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC	0x78594
+#define ICL_DSC0_PICTURE_PARAMETER_SET_9(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_9_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_9_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_9(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_9_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_9_PC)
+#define  DSC_RC_EDGE_FACTOR(rc_edge_fact)	((rc_edge_fact) << 16)
+#define  DSC_RC_MODEL_SIZE(rc_model_size)	((rc_model_size) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_10		0x6B228
+#define DSCC_PICTURE_PARAMETER_SET_10		0x6BA28
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB	0x78298
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB	0x78398
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC	0x78498
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC	0x78598
+#define ICL_DSC0_PICTURE_PARAMETER_SET_10(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_10_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_10_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_10(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_10_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_10_PC)
+#define  DSC_RC_TARGET_OFF_LOW(rc_tgt_off_low)		((rc_tgt_off_low) << 20)
+#define  DSC_RC_TARGET_OFF_HIGH(rc_tgt_off_high)	((rc_tgt_off_high) << 16)
+#define  DSC_RC_QUANT_INC_LIMIT1(lim)			((lim) << 8)
+#define  DSC_RC_QUANT_INC_LIMIT0(lim)			((lim) << 0)
+
+#define DSCA_PICTURE_PARAMETER_SET_11		0x6B22C
+#define DSCC_PICTURE_PARAMETER_SET_11		0x6BA2C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB	0x7829C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB	0x7839C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC	0x7849C
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC	0x7859C
+#define ICL_DSC0_PICTURE_PARAMETER_SET_11(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_11_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_11_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_11(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_11_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_11_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_12		0x6B260
+#define DSCC_PICTURE_PARAMETER_SET_12		0x6BA60
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB	0x782A0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB	0x783A0
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC	0x784A0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC	0x785A0
+#define ICL_DSC0_PICTURE_PARAMETER_SET_12(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_12_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_12_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_12(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_12_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_12_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_13		0x6B264
+#define DSCC_PICTURE_PARAMETER_SET_13		0x6BA64
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB	0x782A4
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB	0x783A4
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC	0x784A4
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC	0x785A4
+#define ICL_DSC0_PICTURE_PARAMETER_SET_13(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_13_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_13_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_13(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_13_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_13_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_14		0x6B268
+#define DSCC_PICTURE_PARAMETER_SET_14		0x6BA68
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB	0x782A8
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB	0x783A8
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC	0x784A8
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC	0x785A8
+#define ICL_DSC0_PICTURE_PARAMETER_SET_14(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_14_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_14_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_14(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_14_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_14_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_15		0x6B26C
+#define DSCC_PICTURE_PARAMETER_SET_15		0x6BA6C
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB	0x782AC
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB	0x783AC
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC	0x784AC
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC	0x785AC
+#define ICL_DSC0_PICTURE_PARAMETER_SET_15(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_15_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_15_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_15(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_15_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_15_PC)
+
+#define DSCA_PICTURE_PARAMETER_SET_16		0x6B270
+#define DSCC_PICTURE_PARAMETER_SET_16		0x6BA70
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB	0x782B0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB	0x783B0
+#define _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC	0x784B0
+#define _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC	0x785B0
+#define ICL_DSC0_PICTURE_PARAMETER_SET_16(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_16_PB, \
+							   _ICL_DSC0_PICTURE_PARAMETER_SET_16_PC)
+#define ICL_DSC1_PICTURE_PARAMETER_SET_16(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_16_PB, \
+							   _ICL_DSC1_PICTURE_PARAMETER_SET_16_PC)
+#define  DSC_SLICE_PER_LINE(slice_per_line)		((slice_per_line) << 16)
+#define  DSC_SLICE_CHUNK_SIZE(slice_chunk_aize)		(slice_chunk_size << 0)
+
 #endif /* _I915_REG_H_ */
-- 
cgit v1.2.3


From dbda5111e2d85ff67452e9f8b82fc9eee73a224c Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Tue, 17 Jul 2018 14:11:00 -0700
Subject: i915/dp/dsc: Add Rate Control Buffer Threshold Registers

Add register defines and  shifts that control the RC buffer threshold
between encoder and decoder for eDP/MIPI and DP cases.

The actual values are calculated usung a helper function.
This patch adds the shifts to registers where the value will
be written during atomic commit.

v2:
- Use _MMIO_PIPE() instead of _MMIO_(_PICK()) (Manasi)
- Combine shifts (Manasi)

Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531861861-10950-3-git-send-email-anusha.srivatsa@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 51 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index e8687b0f906d..5825319d4d22 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -10499,4 +10499,55 @@ enum skl_power_gate {
 #define  DSC_SLICE_PER_LINE(slice_per_line)		((slice_per_line) << 16)
 #define  DSC_SLICE_CHUNK_SIZE(slice_chunk_aize)		(slice_chunk_size << 0)
 
+/* Icelake Rate Control Buffer Threshold Registers */
+#define DSCA_RC_BUF_THRESH_0			_MMIO(0x6B230)
+#define DSCA_RC_BUF_THRESH_0_UDW		_MMIO(0x6B230 + 4)
+#define DSCC_RC_BUF_THRESH_0			_MMIO(0x6BA30)
+#define DSCC_RC_BUF_THRESH_0_UDW		_MMIO(0x6BA30 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_0_PB		(0x78254)
+#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PB	(0x78254 + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_0_PB		(0x78354)
+#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PB	(0x78354 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_0_PC		(0x78454)
+#define _ICL_DSC0_RC_BUF_THRESH_0_UDW_PC	(0x78454 + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_0_PC		(0x78554)
+#define _ICL_DSC1_RC_BUF_THRESH_0_UDW_PC	(0x78554 + 4)
+#define ICL_DSC0_RC_BUF_THRESH_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_0_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_0_PC)
+#define ICL_DSC0_RC_BUF_THRESH_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_0_UDW_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_0_UDW_PC)
+#define ICL_DSC1_RC_BUF_THRESH_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_0_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_0_PC)
+#define ICL_DSC1_RC_BUF_THRESH_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_0_UDW_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_0_UDW_PC)
+
+#define DSCA_RC_BUF_THRESH_1			_MMIO(0x6B238)
+#define DSCA_RC_BUF_THRESH_1_UDW		_MMIO(0x6B238 + 4)
+#define DSCC_RC_BUF_THRESH_1			_MMIO(0x6BA38)
+#define DSCC_RC_BUF_THRESH_1_UDW		_MMIO(0x6BA38 + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_1_PB		(0x7825C)
+#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PB	(0x7825C + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_1_PB		(0x7835C)
+#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PB	(0x7835C + 4)
+#define _ICL_DSC0_RC_BUF_THRESH_1_PC		(0x7845C)
+#define _ICL_DSC0_RC_BUF_THRESH_1_UDW_PC	(0x7845C + 4)
+#define _ICL_DSC1_RC_BUF_THRESH_1_PC		(0x7855C)
+#define _ICL_DSC1_RC_BUF_THRESH_1_UDW_PC	(0x7855C + 4)
+#define ICL_DSC0_RC_BUF_THRESH_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_1_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_1_PC)
+#define ICL_DSC0_RC_BUF_THRESH_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC0_RC_BUF_THRESH_1_UDW_PB, \
+						_ICL_DSC0_RC_BUF_THRESH_1_UDW_PC)
+#define ICL_DSC1_RC_BUF_THRESH_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_1_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_1_PC)
+#define ICL_DSC1_RC_BUF_THRESH_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+						_ICL_DSC1_RC_BUF_THRESH_1_UDW_PB, \
+						_ICL_DSC1_RC_BUF_THRESH_1_UDW_PC)
+
 #endif /* _I915_REG_H_ */
-- 
cgit v1.2.3


From c7d2959f032ddb0cb3528df4cc08b6b78acb9a09 Mon Sep 17 00:00:00 2001
From: Anusha Srivatsa <anusha.srivatsa@intel.com>
Date: Tue, 17 Jul 2018 14:11:01 -0700
Subject: i915/dp/dsc: Add Rate Control Range Parameter Registers

RC model has these parameters that correspond with each of
15 ranges of RC buffer threshold value in the RC model.
The three elements are range_min_qp, range_max_qp and
range_bpg_offset.

Add the Rate Control range values for eDP/MIPI and DP case.
The actual values are calculated usung a helper function.
This patch adds the shifts to registers where the value will
be written during atomic commit.

v2:
- Use _MMIO_PIPE() instead of _MMIO(_PICK()) (Manasi)
- Combine shifts (Manasi)

Cc: Jose Souza <jose.souza@intel.com>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Cc: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Anusha Srivatsa <anusha.srivatsa@intel.com>
Reviewed-by: Manasi Navare <manasi.d.navare@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/1531861861-10950-4-git-send-email-anusha.srivatsa@intel.com
---
 drivers/gpu/drm/i915/i915_reg.h | 104 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 104 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 5825319d4d22..8af945d8a995 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -7678,6 +7678,110 @@ enum {
 
 #define SHOTPLUG_CTL_TC				_MMIO(0xc4034)
 #define   ICP_TC_HPD_ENABLE(tc_port)		(8 << (tc_port) * 4)
+/* Icelake DSC Rate Control Range Parameter Registers */
+#define DSCA_RC_RANGE_PARAMETERS_0		_MMIO(0x6B240)
+#define DSCA_RC_RANGE_PARAMETERS_0_UDW		_MMIO(0x6B240 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_0		_MMIO(0x6BA40)
+#define DSCC_RC_RANGE_PARAMETERS_0_UDW		_MMIO(0x6BA40 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PB	(0x78208)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB	(0x78208 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PB	(0x78308)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB	(0x78308 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_PC	(0x78408)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC	(0x78408 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_PC	(0x78508)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC	(0x78508 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_0_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_0(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_0_UDW_PC)
+#define RC_BPG_OFFSET_SHIFT			10
+#define RC_MAX_QP_SHIFT				5
+#define RC_MIN_QP_SHIFT				0
+
+#define DSCA_RC_RANGE_PARAMETERS_1		_MMIO(0x6B248)
+#define DSCA_RC_RANGE_PARAMETERS_1_UDW		_MMIO(0x6B248 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_1		_MMIO(0x6BA48)
+#define DSCC_RC_RANGE_PARAMETERS_1_UDW		_MMIO(0x6BA48 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PB	(0x78210)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB	(0x78210 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PB	(0x78310)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB	(0x78310 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_PC	(0x78410)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC	(0x78410 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_PC	(0x78510)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC	(0x78510 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_1_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_1(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_1_UDW_PC)
+
+#define DSCA_RC_RANGE_PARAMETERS_2		_MMIO(0x6B250)
+#define DSCA_RC_RANGE_PARAMETERS_2_UDW		_MMIO(0x6B250 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_2		_MMIO(0x6BA50)
+#define DSCC_RC_RANGE_PARAMETERS_2_UDW		_MMIO(0x6BA50 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PB	(0x78218)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB	(0x78218 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PB	(0x78318)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB	(0x78318 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_PC	(0x78418)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC	(0x78418 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_PC	(0x78518)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC	(0x78518 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_2(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_2_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_2(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_2_UDW_PC)
+
+#define DSCA_RC_RANGE_PARAMETERS_3		_MMIO(0x6B258)
+#define DSCA_RC_RANGE_PARAMETERS_3_UDW		_MMIO(0x6B258 + 4)
+#define DSCC_RC_RANGE_PARAMETERS_3		_MMIO(0x6BA58)
+#define DSCC_RC_RANGE_PARAMETERS_3_UDW		_MMIO(0x6BA58 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PB	(0x78220)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB	(0x78220 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PB	(0x78320)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB	(0x78320 + 4)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_PC	(0x78420)
+#define _ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC	(0x78420 + 4)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_PC	(0x78520)
+#define _ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC	(0x78520 + 4)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_3(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_PC)
+#define ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PB, \
+							_ICL_DSC0_RC_RANGE_PARAMETERS_3_UDW_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_3(pipe)		_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_PC)
+#define ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW(pipe)	_MMIO_PIPE((pipe) - PIPE_B, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PB, \
+							_ICL_DSC1_RC_RANGE_PARAMETERS_3_UDW_PC)
+
 #define   ICP_TC_HPD_LONG_DETECT(tc_port)	(2 << (tc_port) * 4)
 #define   ICP_TC_HPD_SHORT_DETECT(tc_port)	(1 << (tc_port) * 4)
 
-- 
cgit v1.2.3


From 685dbcaa25becfba864b72ec3f03470833b7f692 Mon Sep 17 00:00:00 2001
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Tue, 3 Jul 2018 22:01:36 +0200
Subject: drivers/md/raid5: Use irqsave variant of atomic_dec_and_lock()

The irqsave variant of atomic_dec_and_lock handles irqsave/restore when
taking/releasing the spin lock. With this variant the call of
local_irq_save is no longer required.

Cc: Shaohua Li <shli@kernel.org>
Cc: linux-raid@vger.kernel.org
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 2031506a0ecd..e933bff9459e 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -409,16 +409,15 @@ void raid5_release_stripe(struct stripe_head *sh)
 		md_wakeup_thread(conf->mddev->thread);
 	return;
 slow_path:
-	local_irq_save(flags);
 	/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
-	if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
+	if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) {
 		INIT_LIST_HEAD(&list);
 		hash = sh->hash_lock_index;
 		do_release_stripe(conf, sh, &list);
 		spin_unlock(&conf->device_lock);
 		release_inactive_stripe_list(conf, &list, hash);
+		local_irq_restore(flags);
 	}
-	local_irq_restore(flags);
 }
 
 static inline void remove_hash(struct stripe_head *sh)
-- 
cgit v1.2.3


From d00ddd9da79a868264997e192f9404aef1e46ba8 Mon Sep 17 00:00:00 2001
From: Ben Skeggs <bskeggs@redhat.com>
Date: Wed, 18 Jul 2018 09:33:39 +1000
Subject: drm/nouveau/kms/nv50-: allocate push buffers in vidmem on pascal

Workaround for issues seen on systems with large amounts of RAM, caused
by display not supporting the same physical address limits as the other
parts of the GPU.

Signed-off-by: Ben Skeggs <bskeggs@redhat.com>
---
 drivers/gpu/drm/nouveau/dispnv50/disp.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c
index 7d00d833bbe5..4a372f805eb9 100644
--- a/drivers/gpu/drm/nouveau/dispnv50/disp.c
+++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c
@@ -136,12 +136,24 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp,
 {
 	struct nouveau_cli *cli = (void *)device->object.client;
 	struct nv50_disp_core_channel_dma_v0 *args = data;
+	u8 type = NVIF_MEM_COHERENT;
 	int ret;
 
 	mutex_init(&dmac->lock);
 
-	ret = nvif_mem_init_map(&cli->mmu, NVIF_MEM_COHERENT, 0x1000,
-				&dmac->push);
+	/* Pascal added support for 47-bit physical addresses, but some
+	 * parts of EVO still only accept 40-bit PAs.
+	 *
+	 * To avoid issues on systems with large amounts of RAM, and on
+	 * systems where an IOMMU maps pages at a high address, we need
+	 * to allocate push buffers in VRAM instead.
+	 *
+	 * This appears to match NVIDIA's behaviour on Pascal.
+	 */
+	if (device->info.family == NV_DEVICE_INFO_V0_PASCAL)
+		type |= NVIF_MEM_VRAM;
+
+	ret = nvif_mem_init_map(&cli->mmu, type, 0x1000, &dmac->push);
 	if (ret)
 		return ret;
 
@@ -216,6 +228,19 @@ void
 evo_kick(u32 *push, struct nv50_dmac *evoc)
 {
 	struct nv50_dmac *dmac = evoc;
+
+	/* Push buffer fetches are not coherent with BAR1, we need to ensure
+	 * writes have been flushed right through to VRAM before writing PUT.
+	 */
+	if (dmac->push.type & NVIF_MEM_VRAM) {
+		struct nvif_device *device = dmac->base.device;
+		nvif_wr32(&device->object, 0x070000, 0x00000001);
+		nvif_msec(device, 2000,
+			if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002))
+				break;
+		);
+	}
+
 	nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2);
 	mutex_unlock(&dmac->lock);
 }
-- 
cgit v1.2.3


From 58cabe8715f20b7fb33431bb1f2c5bd7a438b11b Mon Sep 17 00:00:00 2001
From: Adam Goode <agoode@google.com>
Date: Wed, 18 Jul 2018 16:41:05 -0400
Subject: ALSA: usb-audio: Allow changing from a bad sample rate

If the audio device is externally clocked and set to a rate that does
not match the external clock, the clock will never be valid and we cannot
set the rate successfully. To fix this, allow a rate change even if
the clock is initially invalid, and validate again after the rate is
changed.

This fixes problems with MOTU UltraLite AVB hardware over USB.

Signed-off-by: Adam Goode <agoode@google.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/clock.c | 24 +++++++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/sound/usb/clock.c b/sound/usb/clock.c
index c79749613fa6..db5e39d67a90 100644
--- a/sound/usb/clock.c
+++ b/sound/usb/clock.c
@@ -513,14 +513,28 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface,
 	bool writeable;
 	u32 bmControls;
 
+	/* First, try to find a valid clock. This may trigger
+	 * automatic clock selection if the current clock is not
+	 * valid.
+	 */
 	clock = snd_usb_clock_find_source(chip, fmt->protocol,
 					  fmt->clock, true);
-	if (clock < 0)
-		return clock;
+	if (clock < 0) {
+		/* We did not find a valid clock, but that might be
+		 * because the current sample rate does not match an
+		 * external clock source. Try again without validation
+		 * and we will do another validation after setting the
+		 * rate.
+		 */
+		clock = snd_usb_clock_find_source(chip, fmt->protocol,
+						  fmt->clock, false);
+		if (clock < 0)
+			return clock;
+	}
 
 	prev_rate = get_sample_rate_v2v3(chip, iface, fmt->altsetting, clock);
 	if (prev_rate == rate)
-		return 0;
+		goto validation;
 
 	if (fmt->protocol == UAC_VERSION_3) {
 		struct uac3_clock_source_descriptor *cs_desc;
@@ -577,6 +591,10 @@ static int set_sample_rate_v2v3(struct snd_usb_audio *chip, int iface,
 		snd_usb_set_interface_quirk(dev);
 	}
 
+validation:
+	/* validate clock after rate change */
+	if (!uac_clock_source_is_valid(chip, fmt->protocol, clock))
+		return -ENXIO;
 	return 0;
 }
 
-- 
cgit v1.2.3


From fcb662deeb83bbc6df58b472a3bfe76981a8cc36 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Tue, 26 Jun 2018 14:19:10 -0700
Subject: xfrm: don't check offload_handle for nonzero

The offload_handle should be an opaque data cookie for the driver
to use, much like the data cookie for a timer or alarm callback.
Thus, the XFRM stack should not be checking for non-zero, because
the driver might use that to store an array reference, which could
be zero, or some other zero but meaningful value.

We can remove the checks for non-zero because there are plenty
other attributes also being checked to see if there is an offload
in place for the SA in question.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/ipv4/esp4_offload.c | 6 ++----
 net/ipv6/esp6_offload.c | 6 ++----
 net/xfrm/xfrm_device.c  | 6 +++---
 3 files changed, 7 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 7cf755ef9efb..133589d693a9 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -135,8 +135,7 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
 
 	skb->encap_hdr_csum = 1;
 
-	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
-	    (x->xso.dev != skb->dev))
+	if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev)
 		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
 	else if (!(features & NETIF_F_HW_ESP_TX_CSUM))
 		esp_features = features & ~NETIF_F_CSUM_MASK;
@@ -179,8 +178,7 @@ static int esp_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_
 	if (!xo)
 		return -EINVAL;
 
-	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
-	    (x->xso.dev != skb->dev)) {
+	if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) {
 		xo->flags |= CRYPTO_FALLBACK;
 		hw_offload = false;
 	}
diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
index 27f59b61f70f..96af267835c3 100644
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@ -162,8 +162,7 @@ static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
 
 	skb->encap_hdr_csum = 1;
 
-	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
-	    (x->xso.dev != skb->dev))
+	if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev)
 		esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
 	else if (!(features & NETIF_F_HW_ESP_TX_CSUM))
 		esp_features = features & ~NETIF_F_CSUM_MASK;
@@ -207,8 +206,7 @@ static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features
 	if (!xo)
 		return -EINVAL;
 
-	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
-	    (x->xso.dev != skb->dev)) {
+	if (!(features & NETIF_F_HW_ESP) || x->xso.dev != skb->dev) {
 		xo->flags |= CRYPTO_FALLBACK;
 		hw_offload = false;
 	}
diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c
index 11d56a44e9e8..5611b7521020 100644
--- a/net/xfrm/xfrm_device.c
+++ b/net/xfrm/xfrm_device.c
@@ -56,7 +56,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur
 	if (skb_is_gso(skb)) {
 		struct net_device *dev = skb->dev;
 
-		if (unlikely(!x->xso.offload_handle || (x->xso.dev != dev))) {
+		if (unlikely(x->xso.dev != dev)) {
 			struct sk_buff *segs;
 
 			/* Packet got rerouted, fixup features and segment it. */
@@ -211,8 +211,8 @@ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x)
 	if (!x->type_offload || x->encap)
 		return false;
 
-	if ((!dev || (x->xso.offload_handle && (dev == xfrm_dst_path(dst)->dev))) &&
-	     (!xdst->child->xfrm && x->type->get_mtu)) {
+	if ((!dev || (dev == xfrm_dst_path(dst)->dev)) &&
+	    (!xdst->child->xfrm && x->type->get_mtu)) {
 		mtu = x->type->get_mtu(x, xdst->child_mtu_cached);
 
 		if (skb->len <= mtu)
-- 
cgit v1.2.3


From 209b7955e59e361fe8ba1911fac68f46355ac0cf Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 17 Jul 2018 21:29:32 +0100
Subject: drm/i915/guc: Keep guc submission permanently engaged
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We make a decision at module load whether to use the GuC backend or not,
but lose that setup across set-wedge. Currently, the guc doesn't
override the engine->set_default_submission hook letting execlists sneak
back in temporarily on unwedging leading to an unbalanced park/unpark.

v2: Remove comment about switching back temporarily to execlists on
guc_submission_disable(). We currently only call disable on shutdown,
and plan to also call disable before suspend and reset, in which case we
will either restore guc submission or mark the driver as wedged, making
the reset back to execlists pointless.
v3: Move reset.prepare across

Fixes: 63572937cebf ("drm/i915/execlists: Flush pending preemption events during reset")
Testcase: igt/drv_module_reload/basic-reload-inject
Testcase: igt/gem_eio
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Michał Winiarski <michal.winiarski@intel.com>
Cc: Michal Wajdeczko <michal.wajdeczko@intel.com>
Reviewed-by: Michał Winiarski <michal.winiarski@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717202932.1423-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_guc_submission.c | 41 +++++++++++++++++++----------
 drivers/gpu/drm/i915/intel_lrc.c            |  4 +--
 drivers/gpu/drm/i915/intel_lrc.h            |  2 ++
 3 files changed, 31 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_guc_submission.c b/drivers/gpu/drm/i915/intel_guc_submission.c
index 0fa1eb0bfff5..4aa5e6463e7b 100644
--- a/drivers/gpu/drm/i915/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/intel_guc_submission.c
@@ -1269,6 +1269,31 @@ static void guc_submission_unpark(struct intel_engine_cs *engine)
 	intel_engine_pin_breadcrumbs_irq(engine);
 }
 
+static void guc_set_default_submission(struct intel_engine_cs *engine)
+{
+	/*
+	 * We inherit a bunch of functions from execlists that we'd like
+	 * to keep using:
+	 *
+	 *    engine->submit_request = execlists_submit_request;
+	 *    engine->cancel_requests = execlists_cancel_requests;
+	 *    engine->schedule = execlists_schedule;
+	 *
+	 * But we need to override the actual submission backend in order
+	 * to talk to the GuC.
+	 */
+	intel_execlists_set_default_submission(engine);
+
+	engine->execlists.tasklet.func = guc_submission_tasklet;
+
+	engine->park = guc_submission_park;
+	engine->unpark = guc_submission_unpark;
+
+	engine->reset.prepare = guc_reset_prepare;
+
+	engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
+}
+
 int intel_guc_submission_enable(struct intel_guc *guc)
 {
 	struct drm_i915_private *dev_priv = guc_to_i915(guc);
@@ -1307,17 +1332,8 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 	guc_interrupts_capture(dev_priv);
 
 	for_each_engine(engine, dev_priv, id) {
-		struct intel_engine_execlists * const execlists =
-			&engine->execlists;
-
-		execlists->tasklet.func = guc_submission_tasklet;
-
-		engine->reset.prepare = guc_reset_prepare;
-
-		engine->park = guc_submission_park;
-		engine->unpark = guc_submission_unpark;
-
-		engine->flags &= ~I915_ENGINE_SUPPORTS_STATS;
+		engine->set_default_submission = guc_set_default_submission;
+		engine->set_default_submission(engine);
 	}
 
 	return 0;
@@ -1331,9 +1347,6 @@ void intel_guc_submission_disable(struct intel_guc *guc)
 
 	guc_interrupts_release(dev_priv);
 	guc_clients_doorbell_fini(guc);
-
-	/* Revert back to manual ELSP submission */
-	intel_engines_reset_default_submission(dev_priv);
 }
 
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index db5351e6a3a5..c64ed9090e29 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -2295,7 +2295,7 @@ void intel_logical_ring_cleanup(struct intel_engine_cs *engine)
 	kfree(engine);
 }
 
-static void execlists_set_default_submission(struct intel_engine_cs *engine)
+void intel_execlists_set_default_submission(struct intel_engine_cs *engine)
 {
 	engine->submit_request = execlists_submit_request;
 	engine->cancel_requests = execlists_cancel_requests;
@@ -2335,7 +2335,7 @@ logical_ring_default_vfuncs(struct intel_engine_cs *engine)
 	engine->emit_breadcrumb = gen8_emit_breadcrumb;
 	engine->emit_breadcrumb_sz = gen8_emit_breadcrumb_sz;
 
-	engine->set_default_submission = execlists_set_default_submission;
+	engine->set_default_submission = intel_execlists_set_default_submission;
 
 	if (INTEL_GEN(engine->i915) < 11) {
 		engine->irq_enable = gen8_logical_ring_enable_irq;
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 1593194e930c..4dfb78e3ec7e 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -104,4 +104,6 @@ struct i915_gem_context;
 
 void intel_lr_context_resume(struct drm_i915_private *dev_priv);
 
+void intel_execlists_set_default_submission(struct intel_engine_cs *engine);
+
 #endif /* _INTEL_LRC_H_ */
-- 
cgit v1.2.3


From d9f4426c73002957be5dd39936f44a09498f7560 Mon Sep 17 00:00:00 2001
From: Jiang Biao <jiang.biao2@zte.com.cn>
Date: Wed, 18 Jul 2018 08:03:14 +0800
Subject: x86/speculation: Remove SPECTRE_V2_IBRS in enum spectre_v2_mitigation

SPECTRE_V2_IBRS in enum spectre_v2_mitigation is never used. Remove it.

Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: hpa@zytor.com
Cc: dwmw2@amazon.co.uk
Cc: konrad.wilk@oracle.com
Cc: bp@suse.de
Cc: zhong.weidong@zte.com.cn
Link: https://lkml.kernel.org/r/1531872194-39207-1-git-send-email-jiang.biao2@zte.com.cn
---
 arch/x86/include/asm/nospec-branch.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index f6f6c63da62f..c99082e2ef13 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -214,7 +214,6 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
 	SPECTRE_V2_RETPOLINE_GENERIC,
 	SPECTRE_V2_RETPOLINE_AMD,
-	SPECTRE_V2_IBRS,
 };
 
 /* The Speculative Store Bypass disable variants */
-- 
cgit v1.2.3


From 4e965ede1856ed62c7ac8b7ad905a4a285e4a9f3 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:11 +0200
Subject: PCI: dwc: Fix EP link notification implementation

Move specific features settings from EP shared code
(pcie-designware-ep.c) to the driver (pcie-designware-plat.c).

Previous implementation disables the EP link notification
by default for all SoCs that uses EP DesignWare IP, which affects
directly the dra7xx and artpec6 SoCs.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c   | 14 ++++++--------
 drivers/pci/controller/dwc/pcie-designware-plat.c |  3 +++
 2 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 8650416f6f9e..04092a7aba89 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -386,15 +386,18 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 		return -ENOMEM;
 	ep->outbound_addr = addr;
 
-	if (ep->ops->ep_init)
-		ep->ops->ep_init(ep);
-
 	epc = devm_pci_epc_create(dev, &epc_ops);
 	if (IS_ERR(epc)) {
 		dev_err(dev, "Failed to create epc device\n");
 		return PTR_ERR(epc);
 	}
 
+	ep->epc = epc;
+	epc_set_drvdata(epc, ep);
+
+	if (ep->ops->ep_init)
+		ep->ops->ep_init(ep);
+
 	ret = of_property_read_u8(np, "max-functions", &epc->max_functions);
 	if (ret < 0)
 		epc->max_functions = 1;
@@ -413,11 +416,6 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 		return -ENOMEM;
 	}
 
-	epc->features = EPC_FEATURE_NO_LINKUP_NOTIFIER;
-	EPC_FEATURE_SET_BAR(epc->features, BAR_0);
-
-	ep->epc = epc;
-	epc_set_drvdata(epc, ep);
 	dw_pcie_setup(pci);
 
 	return 0;
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index 6e048c0b67f2..a37dc92a03c7 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -70,10 +70,13 @@ static const struct dw_pcie_ops dw_pcie_ops = {
 static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	struct pci_epc *epc = ep->epc;
 	enum pci_barno bar;
 
 	for (bar = BAR_0; bar <= BAR_5; bar++)
 		dw_pcie_ep_reset_bar(pci, bar);
+
+	epc->features |= EPC_FEATURE_NO_LINKUP_NOTIFIER;
 }
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-- 
cgit v1.2.3


From 8963106eabdc56911e9b65258eb5e9a6b7b3dfda Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:12 +0200
Subject: PCI: endpoint: Add MSI-X interfaces

Add PCI_EPC_IRQ_MSIX type.

Add MSI-X callbacks signatures to the ops structure.

Add sysfs interface for set/get MSI-X capability maximum number.

Update documentation accordingly.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 .../PCI/endpoint/function/binding/pci-test.txt     |  2 +
 drivers/pci/endpoint/pci-ep-cfs.c                  | 24 +++++++++
 drivers/pci/endpoint/pci-epc-core.c                | 57 ++++++++++++++++++++++
 include/linux/pci-epc.h                            |  9 ++++
 include/linux/pci-epf.h                            |  1 +
 5 files changed, 93 insertions(+)

diff --git a/Documentation/PCI/endpoint/function/binding/pci-test.txt b/Documentation/PCI/endpoint/function/binding/pci-test.txt
index 3b68b955fb50..cd76ba47394b 100644
--- a/Documentation/PCI/endpoint/function/binding/pci-test.txt
+++ b/Documentation/PCI/endpoint/function/binding/pci-test.txt
@@ -15,3 +15,5 @@ subsys_id	 : don't care
 interrupt_pin	 : Should be 1 - INTA, 2 - INTB, 3 - INTC, 4 -INTD
 msi_interrupts	 : Should be 1 to 32 depending on the number of MSI interrupts
 		   to test
+msix_interrupts	 : Should be 1 to 2048 depending on the number of MSI-X
+		   interrupts to test
diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c
index 018ea3433cb5..d1288a0bd530 100644
--- a/drivers/pci/endpoint/pci-ep-cfs.c
+++ b/drivers/pci/endpoint/pci-ep-cfs.c
@@ -286,6 +286,28 @@ static ssize_t pci_epf_msi_interrupts_show(struct config_item *item,
 		       to_pci_epf_group(item)->epf->msi_interrupts);
 }
 
+static ssize_t pci_epf_msix_interrupts_store(struct config_item *item,
+					     const char *page, size_t len)
+{
+	u16 val;
+	int ret;
+
+	ret = kstrtou16(page, 0, &val);
+	if (ret)
+		return ret;
+
+	to_pci_epf_group(item)->epf->msix_interrupts = val;
+
+	return len;
+}
+
+static ssize_t pci_epf_msix_interrupts_show(struct config_item *item,
+					    char *page)
+{
+	return sprintf(page, "%d\n",
+		       to_pci_epf_group(item)->epf->msix_interrupts);
+}
+
 PCI_EPF_HEADER_R(vendorid)
 PCI_EPF_HEADER_W_u16(vendorid)
 
@@ -327,6 +349,7 @@ CONFIGFS_ATTR(pci_epf_, subsys_vendor_id);
 CONFIGFS_ATTR(pci_epf_, subsys_id);
 CONFIGFS_ATTR(pci_epf_, interrupt_pin);
 CONFIGFS_ATTR(pci_epf_, msi_interrupts);
+CONFIGFS_ATTR(pci_epf_, msix_interrupts);
 
 static struct configfs_attribute *pci_epf_attrs[] = {
 	&pci_epf_attr_vendorid,
@@ -340,6 +363,7 @@ static struct configfs_attribute *pci_epf_attrs[] = {
 	&pci_epf_attr_subsys_id,
 	&pci_epf_attr_interrupt_pin,
 	&pci_epf_attr_msi_interrupts,
+	&pci_epf_attr_msix_interrupts,
 	NULL,
 };
 
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index b0ee42739c3c..7d77bd0e5d4a 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -217,6 +217,63 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts)
 }
 EXPORT_SYMBOL_GPL(pci_epc_set_msi);
 
+/**
+ * pci_epc_get_msix() - get the number of MSI-X interrupt numbers allocated
+ * @epc: the EPC device to which MSI-X interrupts was requested
+ * @func_no: the endpoint function number in the EPC device
+ *
+ * Invoke to get the number of MSI-X interrupts allocated by the RC
+ */
+int pci_epc_get_msix(struct pci_epc *epc, u8 func_no)
+{
+	int interrupt;
+	unsigned long flags;
+
+	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
+		return 0;
+
+	if (!epc->ops->get_msix)
+		return 0;
+
+	spin_lock_irqsave(&epc->lock, flags);
+	interrupt = epc->ops->get_msix(epc, func_no);
+	spin_unlock_irqrestore(&epc->lock, flags);
+
+	if (interrupt < 0)
+		return 0;
+
+	return interrupt + 1;
+}
+EXPORT_SYMBOL_GPL(pci_epc_get_msix);
+
+/**
+ * pci_epc_set_msix() - set the number of MSI-X interrupt numbers required
+ * @epc: the EPC device on which MSI-X has to be configured
+ * @func_no: the endpoint function number in the EPC device
+ * @interrupts: number of MSI-X interrupts required by the EPF
+ *
+ * Invoke to set the required number of MSI-X interrupts.
+ */
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts)
+{
+	int ret;
+	unsigned long flags;
+
+	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
+	    interrupts < 1 || interrupts > 2048)
+		return -EINVAL;
+
+	if (!epc->ops->set_msix)
+		return 0;
+
+	spin_lock_irqsave(&epc->lock, flags);
+	ret = epc->ops->set_msix(epc, func_no, interrupts - 1);
+	spin_unlock_irqrestore(&epc->lock, flags);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pci_epc_set_msix);
+
 /**
  * pci_epc_unmap_addr() - unmap CPU address from PCI address
  * @epc: the EPC device on which address is allocated
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 243eaa5a66ff..89f079f582df 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -17,6 +17,7 @@ enum pci_epc_irq_type {
 	PCI_EPC_IRQ_UNKNOWN,
 	PCI_EPC_IRQ_LEGACY,
 	PCI_EPC_IRQ_MSI,
+	PCI_EPC_IRQ_MSIX,
 };
 
 /**
@@ -30,6 +31,10 @@ enum pci_epc_irq_type {
  *	     capability register
  * @get_msi: ops to get the number of MSI interrupts allocated by the RC from
  *	     the MSI capability register
+ * @set_msix: ops to set the requested number of MSI-X interrupts in the
+ *	     MSI-X capability register
+ * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC
+ *	     from the MSI-X capability register
  * @raise_irq: ops to raise a legacy or MSI interrupt
  * @start: ops to start the PCI link
  * @stop: ops to stop the PCI link
@@ -48,6 +53,8 @@ struct pci_epc_ops {
 			      phys_addr_t addr);
 	int	(*set_msi)(struct pci_epc *epc, u8 func_no, u8 interrupts);
 	int	(*get_msi)(struct pci_epc *epc, u8 func_no);
+	int	(*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts);
+	int	(*get_msix)(struct pci_epc *epc, u8 func_no);
 	int	(*raise_irq)(struct pci_epc *epc, u8 func_no,
 			     enum pci_epc_irq_type type, u8 interrupt_num);
 	int	(*start)(struct pci_epc *epc);
@@ -144,6 +151,8 @@ void pci_epc_unmap_addr(struct pci_epc *epc, u8 func_no,
 			phys_addr_t phys_addr);
 int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts);
 int pci_epc_get_msi(struct pci_epc *epc, u8 func_no);
+int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts);
+int pci_epc_get_msix(struct pci_epc *epc, u8 func_no);
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no,
 		      enum pci_epc_irq_type type, u8 interrupt_num);
 int pci_epc_start(struct pci_epc *epc);
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 4e7764935fa8..ec02f58758c8 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -119,6 +119,7 @@ struct pci_epf {
 	struct pci_epf_header	*header;
 	struct pci_epf_bar	bar[6];
 	u8			msi_interrupts;
+	u16			msix_interrupts;
 	u8			func_no;
 
 	struct pci_epc		*epc;
-- 
cgit v1.2.3


From 288d152c23dcf3c09da46c5c481903ca10ebfef7 Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Wed, 18 Jul 2018 19:07:38 +0200
Subject: x86/KVM/VMX: Initialize the vmx_l1d_flush_pages' content

The slow path in vmx_l1d_flush() reads from vmx_l1d_flush_pages in order
to evict the L1d cache.

However, these pages are never cleared and, in theory, their data could be
leaked.

More importantly, KSM could merge a nested hypervisor's vmx_l1d_flush_pages
to fewer than 1 << L1D_CACHE_ORDER host physical pages and this would break
the L1d flushing algorithm: L1D on x86_64 is tagged by physical addresses.

Fix this by initializing the individual vmx_l1d_flush_pages with a
different pattern each.

Rename the "empty_zp" asm constraint identifier in vmx_l1d_flush() to
"flush_pages" to reflect this change.

Fixes: a47dd5f06714 ("x86/KVM/VMX: Add L1D flush algorithm")
Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c5c0118b126d..b4b8e8cb4a7e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -211,6 +211,7 @@ static void *vmx_l1d_flush_pages;
 static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 {
 	struct page *page;
+	unsigned int i;
 
 	if (!enable_ept) {
 		l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_EPT_DISABLED;
@@ -243,6 +244,16 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 		if (!page)
 			return -ENOMEM;
 		vmx_l1d_flush_pages = page_address(page);
+
+		/*
+		 * Initialize each page with a different pattern in
+		 * order to protect against KSM in the nested
+		 * virtualization case.
+		 */
+		for (i = 0; i < 1u << L1D_CACHE_ORDER; ++i) {
+			memset(vmx_l1d_flush_pages + i * PAGE_SIZE, i + 1,
+			       PAGE_SIZE);
+		}
 	}
 
 	l1tf_vmx_mitigation = l1tf;
@@ -9701,7 +9712,7 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 		/* First ensure the pages are in the TLB */
 		"xorl	%%eax, %%eax\n"
 		".Lpopulate_tlb:\n\t"
-		"movzbl	(%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
 		"addl	$4096, %%eax\n\t"
 		"cmpl	%%eax, %[size]\n\t"
 		"jne	.Lpopulate_tlb\n\t"
@@ -9710,12 +9721,12 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 		/* Now fill the cache */
 		"xorl	%%eax, %%eax\n"
 		".Lfill_cache:\n"
-		"movzbl	(%[empty_zp], %%" _ASM_AX "), %%ecx\n\t"
+		"movzbl	(%[flush_pages], %%" _ASM_AX "), %%ecx\n\t"
 		"addl	$64, %%eax\n\t"
 		"cmpl	%%eax, %[size]\n\t"
 		"jne	.Lfill_cache\n\t"
 		"lfence\n"
-		:: [empty_zp] "r" (vmx_l1d_flush_pages),
+		:: [flush_pages] "r" (vmx_l1d_flush_pages),
 		    [size] "r" (size)
 		: "eax", "ebx", "ecx", "edx");
 }
-- 
cgit v1.2.3


From d3c70a98d7d63cae02d50ebfafea04264a767401 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:13 +0200
Subject: PCI: Update xxx_pcie_ep_raise_irq() and pci_epc_raise_irq()
 signatures

Change {cdns, dra7xx, artpec6, dw, rockchip}_pcie_ep_raise_irq() and
pci_epc_raise_irq() signature, namely the interrupt_num variable type
from u8 to u16 to accommodate 2048 maximum MSI-X interrupts.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Alan Douglas <adouglas@cadence.com>
Acked-by: Shawn Lin <shawn.lin@rock-chips.com>
Acked-by: Jesper Nilsson <jesper.nilsson@axis.com>
Acked-by: Joao Pinto <jpinto@synopsys.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/pci/controller/dwc/pci-dra7xx.c           | 2 +-
 drivers/pci/controller/dwc/pcie-artpec6.c         | 2 +-
 drivers/pci/controller/dwc/pcie-designware-ep.c   | 2 +-
 drivers/pci/controller/dwc/pcie-designware-plat.c | 2 +-
 drivers/pci/controller/dwc/pcie-designware.h      | 2 +-
 drivers/pci/controller/pcie-cadence-ep.c          | 3 ++-
 drivers/pci/controller/pcie-rockchip-ep.c         | 2 +-
 drivers/pci/endpoint/pci-epc-core.c               | 8 ++++----
 include/linux/pci-epc.h                           | 6 +++---
 9 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index 345aab56ce8b..ce9224a36f62 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -370,7 +370,7 @@ static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx,
 }
 
 static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				 enum pci_epc_irq_type type, u8 interrupt_num)
+				 enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 128b182648b3..dba83abfe764 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -427,7 +427,7 @@ static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep)
 }
 
 static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_epc_irq_type type, u8 interrupt_num)
+				  enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 04092a7aba89..69d039de2af6 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -242,7 +242,7 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 encode_int)
 }
 
 static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no,
-				enum pci_epc_irq_type type, u8 interrupt_num)
+				enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index a37dc92a03c7..cca69ac63319 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -81,7 +81,7 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 				     enum pci_epc_irq_type type,
-				     u8 interrupt_num)
+				     u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index bee4e2535a61..9d581c077329 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -191,7 +191,7 @@ enum dw_pcie_as_type {
 struct dw_pcie_ep_ops {
 	void	(*ep_init)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
-			     enum pci_epc_irq_type type, u8 interrupt_num);
+			     enum pci_epc_irq_type type, u16 interrupt_num);
 };
 
 struct dw_pcie_ep {
diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c
index e3fe4124e3af..208d11f27d5d 100644
--- a/drivers/pci/controller/pcie-cadence-ep.c
+++ b/drivers/pci/controller/pcie-cadence-ep.c
@@ -363,7 +363,8 @@ static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn,
 }
 
 static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn,
-				  enum pci_epc_irq_type type, u8 interrupt_num)
+				  enum pci_epc_irq_type type,
+				  u16 interrupt_num)
 {
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 6beba8ed7b84..b8163c56a142 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -472,7 +472,7 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn,
 
 static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn,
 				      enum pci_epc_irq_type type,
-				      u8 interrupt_num)
+				      u16 interrupt_num)
 {
 	struct rockchip_pcie_ep *ep = epc_get_drvdata(epc);
 
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index 7d77bd0e5d4a..c72e656e7e29 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -131,13 +131,13 @@ EXPORT_SYMBOL_GPL(pci_epc_start);
  * pci_epc_raise_irq() - interrupt the host system
  * @epc: the EPC device which has to interrupt the host
  * @func_no: the endpoint function number in the EPC device
- * @type: specify the type of interrupt; legacy or MSI
- * @interrupt_num: the MSI interrupt number
+ * @type: specify the type of interrupt; legacy, MSI or MSI-X
+ * @interrupt_num: the MSI or MSI-X interrupt number
  *
- * Invoke to raise an MSI or legacy interrupt
+ * Invoke to raise an legacy, MSI or MSI-X interrupt
  */
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no,
-		      enum pci_epc_irq_type type, u8 interrupt_num)
+		      enum pci_epc_irq_type type, u16 interrupt_num)
 {
 	int ret;
 	unsigned long flags;
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index 89f079f582df..bb2395b56f13 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -35,7 +35,7 @@ enum pci_epc_irq_type {
  *	     MSI-X capability register
  * @get_msix: ops to get the number of MSI-X interrupts allocated by the RC
  *	     from the MSI-X capability register
- * @raise_irq: ops to raise a legacy or MSI interrupt
+ * @raise_irq: ops to raise a legacy, MSI or MSI-X interrupt
  * @start: ops to start the PCI link
  * @stop: ops to stop the PCI link
  * @owner: the module owner containing the ops
@@ -56,7 +56,7 @@ struct pci_epc_ops {
 	int	(*set_msix)(struct pci_epc *epc, u8 func_no, u16 interrupts);
 	int	(*get_msix)(struct pci_epc *epc, u8 func_no);
 	int	(*raise_irq)(struct pci_epc *epc, u8 func_no,
-			     enum pci_epc_irq_type type, u8 interrupt_num);
+			     enum pci_epc_irq_type type, u16 interrupt_num);
 	int	(*start)(struct pci_epc *epc);
 	void	(*stop)(struct pci_epc *epc);
 	struct module *owner;
@@ -154,7 +154,7 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no);
 int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts);
 int pci_epc_get_msix(struct pci_epc *epc, u8 func_no);
 int pci_epc_raise_irq(struct pci_epc *epc, u8 func_no,
-		      enum pci_epc_irq_type type, u8 interrupt_num);
+		      enum pci_epc_irq_type type, u16 interrupt_num);
 int pci_epc_start(struct pci_epc *epc);
 void pci_epc_stop(struct pci_epc *epc);
 struct pci_epc *pci_epc_get(const char *epc_name);
-- 
cgit v1.2.3


From beb4641a787df79a1423a8789d185b6b78fcbfea Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:14 +0200
Subject: PCI: dwc: Add MSI-X callbacks handler

Add PCIe config space capability search function.

Add sysfs set/get interface to allow the change of EP MSI-X maximum number.

Add EP MSI-X callback for triggering interruptions.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c   | 137 +++++++++++++++++++++-
 drivers/pci/controller/dwc/pcie-designware-plat.c |   2 +
 drivers/pci/controller/dwc/pcie-designware.h      |  10 ++
 3 files changed, 148 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 69d039de2af6..23be2c0249ee 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -40,6 +40,39 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar)
 	__dw_pcie_ep_reset_bar(pci, bar, 0);
 }
 
+static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie *pci, u8 cap_ptr,
+			      u8 cap)
+{
+	u8 cap_id, next_cap_ptr;
+	u16 reg;
+
+	reg = dw_pcie_readw_dbi(pci, cap_ptr);
+	next_cap_ptr = (reg & 0xff00) >> 8;
+	cap_id = (reg & 0x00ff);
+
+	if (!next_cap_ptr || cap_id > PCI_CAP_ID_MAX)
+		return 0;
+
+	if (cap_id == cap)
+		return cap_ptr;
+
+	return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap);
+}
+
+static u8 dw_pcie_ep_find_capability(struct dw_pcie *pci, u8 cap)
+{
+	u8 next_cap_ptr;
+	u16 reg;
+
+	reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST);
+	next_cap_ptr = (reg & 0x00ff);
+
+	if (!next_cap_ptr)
+		return 0;
+
+	return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap);
+}
+
 static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no,
 				   struct pci_epf_header *hdr)
 {
@@ -241,6 +274,45 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 encode_int)
 	return 0;
 }
 
+static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no)
+{
+	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
+
+	if (!ep->msix_cap)
+		return -EINVAL;
+
+	reg = ep->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	if (!(val & PCI_MSIX_FLAGS_ENABLE))
+		return -EINVAL;
+
+	val &= PCI_MSIX_FLAGS_QSIZE;
+
+	return val;
+}
+
+static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u16 interrupts)
+{
+	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
+
+	if (!ep->msix_cap)
+		return -EINVAL;
+
+	reg = ep->msix_cap + PCI_MSIX_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	val &= ~PCI_MSIX_FLAGS_QSIZE;
+	val |= interrupts;
+	dw_pcie_dbi_ro_wr_en(pci);
+	dw_pcie_writew_dbi(pci, reg, val);
+	dw_pcie_dbi_ro_wr_dis(pci);
+
+	return 0;
+}
+
 static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no,
 				enum pci_epc_irq_type type, u16 interrupt_num)
 {
@@ -282,6 +354,8 @@ static const struct pci_epc_ops epc_ops = {
 	.unmap_addr		= dw_pcie_ep_unmap_addr,
 	.set_msi		= dw_pcie_ep_set_msi,
 	.get_msi		= dw_pcie_ep_get_msi,
+	.set_msix		= dw_pcie_ep_set_msix,
+	.get_msix		= dw_pcie_ep_get_msix,
 	.raise_irq		= dw_pcie_ep_raise_irq,
 	.start			= dw_pcie_ep_start,
 	.stop			= dw_pcie_ep_stop,
@@ -322,6 +396,64 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	return 0;
 }
 
+int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
+			     u16 interrupt_num)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	struct pci_epc *epc = ep->epc;
+	u16 tbl_offset, bir;
+	u32 bar_addr_upper, bar_addr_lower;
+	u32 msg_addr_upper, msg_addr_lower;
+	u32 reg, msg_data, vec_ctrl;
+	u64 tbl_addr, msg_addr, reg_u64;
+	void __iomem *msix_tbl;
+	int ret;
+
+	reg = ep->msix_cap + PCI_MSIX_TABLE;
+	tbl_offset = dw_pcie_readl_dbi(pci, reg);
+	bir = (tbl_offset & PCI_MSIX_TABLE_BIR);
+	tbl_offset &= PCI_MSIX_TABLE_OFFSET;
+	tbl_offset >>= 3;
+
+	reg = PCI_BASE_ADDRESS_0 + (4 * bir);
+	bar_addr_upper = 0;
+	bar_addr_lower = dw_pcie_readl_dbi(pci, reg);
+	reg_u64 = (bar_addr_lower & PCI_BASE_ADDRESS_MEM_TYPE_MASK);
+	if (reg_u64 == PCI_BASE_ADDRESS_MEM_TYPE_64)
+		bar_addr_upper = dw_pcie_readl_dbi(pci, reg + 4);
+
+	tbl_addr = ((u64) bar_addr_upper) << 32 | bar_addr_lower;
+	tbl_addr += (tbl_offset + ((interrupt_num - 1) * PCI_MSIX_ENTRY_SIZE));
+	tbl_addr &= PCI_BASE_ADDRESS_MEM_MASK;
+
+	msix_tbl = ioremap_nocache(ep->phys_base + tbl_addr,
+				   PCI_MSIX_ENTRY_SIZE);
+	if (!msix_tbl)
+		return -EINVAL;
+
+	msg_addr_lower = readl(msix_tbl + PCI_MSIX_ENTRY_LOWER_ADDR);
+	msg_addr_upper = readl(msix_tbl + PCI_MSIX_ENTRY_UPPER_ADDR);
+	msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower;
+	msg_data = readl(msix_tbl + PCI_MSIX_ENTRY_DATA);
+	vec_ctrl = readl(msix_tbl + PCI_MSIX_ENTRY_VECTOR_CTRL);
+
+	iounmap(msix_tbl);
+
+	if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT)
+		return -EPERM;
+
+	ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr,
+				  epc->mem->page_size);
+	if (ret)
+		return ret;
+
+	writel(msg_data, ep->msi_mem);
+
+	dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys);
+
+	return 0;
+}
+
 void dw_pcie_ep_exit(struct dw_pcie_ep *ep)
 {
 	struct pci_epc *epc = ep->epc;
@@ -412,9 +544,12 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 	ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys,
 					     epc->mem->page_size);
 	if (!ep->msi_mem) {
-		dev_err(dev, "Failed to reserve memory for MSI\n");
+		dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n");
 		return -ENOMEM;
 	}
+	ep->msi_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSI);
+
+	ep->msix_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSIX);
 
 	dw_pcie_setup(pci);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index cca69ac63319..35d2291c6ba5 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -91,6 +91,8 @@ static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 		return -EINVAL;
 	case PCI_EPC_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
+	case PCI_EPC_IRQ_MSIX:
+		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
 	default:
 		dev_err(pci->dev, "UNKNOWN IRQ type\n");
 	}
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 9d581c077329..00ac4197c457 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -208,6 +208,8 @@ struct dw_pcie_ep {
 	u32			num_ob_windows;
 	void __iomem		*msi_mem;
 	phys_addr_t		msi_mem_phys;
+	u8			msi_cap;	/* MSI capability offset */
+	u8			msix_cap;	/* MSI-X capability offset */
 };
 
 struct dw_pcie_ops {
@@ -359,6 +361,8 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep);
 void dw_pcie_ep_exit(struct dw_pcie_ep *ep);
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num);
+int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
+			     u16 interrupt_num);
 void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar);
 #else
 static inline void dw_pcie_ep_linkup(struct dw_pcie_ep *ep)
@@ -380,6 +384,12 @@ static inline int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	return 0;
 }
 
+static inline int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
+					   u16 interrupt_num)
+{
+	return 0;
+}
+
 static inline void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar)
 {
 }
-- 
cgit v1.2.3


From 3920a5d7b24dc5229abe6fb8409e4c9de2c8c7a0 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:15 +0200
Subject: PCI: dwc: Rework MSI callbacks handler

Remove duplicate defines located on pcie-designware.h file already
available on /include/uapi/linux/pci-regs.h file.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c | 49 +++++++++++++++++--------
 drivers/pci/controller/dwc/pcie-designware.h    | 11 ------
 2 files changed, 33 insertions(+), 27 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 23be2c0249ee..dd9c36678cba 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -246,29 +246,38 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no,
 
 static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no)
 {
-	int val;
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
+
+	if (!ep->msi_cap)
+		return -EINVAL;
 
-	val = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL);
-	if (!(val & MSI_CAP_MSI_EN_MASK))
+	reg = ep->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	if (!(val & PCI_MSI_FLAGS_ENABLE))
 		return -EINVAL;
 
-	val = (val & MSI_CAP_MME_MASK) >> MSI_CAP_MME_SHIFT;
+	val = (val & PCI_MSI_FLAGS_QSIZE) >> 4;
+
 	return val;
 }
 
-static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 encode_int)
+static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts)
 {
-	int val;
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 val, reg;
 
-	val = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL);
-	val &= ~MSI_CAP_MMC_MASK;
-	val |= (encode_int << MSI_CAP_MMC_SHIFT) & MSI_CAP_MMC_MASK;
+	if (!ep->msi_cap)
+		return -EINVAL;
+
+	reg = ep->msi_cap + PCI_MSI_FLAGS;
+	val = dw_pcie_readw_dbi(pci, reg);
+	val &= ~PCI_MSI_FLAGS_QMASK;
+	val |= (interrupts << 1) & PCI_MSI_FLAGS_QMASK;
 	dw_pcie_dbi_ro_wr_en(pci);
-	dw_pcie_writew_dbi(pci, MSI_MESSAGE_CONTROL, val);
+	dw_pcie_writew_dbi(pci, reg, val);
 	dw_pcie_dbi_ro_wr_dis(pci);
 
 	return 0;
@@ -367,21 +376,29 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct pci_epc *epc = ep->epc;
 	u16 msg_ctrl, msg_data;
-	u32 msg_addr_lower, msg_addr_upper;
+	u32 msg_addr_lower, msg_addr_upper, reg;
 	u64 msg_addr;
 	bool has_upper;
 	int ret;
 
+	if (!ep->msi_cap)
+		return -EINVAL;
+
 	/* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */
-	msg_ctrl = dw_pcie_readw_dbi(pci, MSI_MESSAGE_CONTROL);
+	reg = ep->msi_cap + PCI_MSI_FLAGS;
+	msg_ctrl = dw_pcie_readw_dbi(pci, reg);
 	has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT);
-	msg_addr_lower = dw_pcie_readl_dbi(pci, MSI_MESSAGE_ADDR_L32);
+	reg = ep->msi_cap + PCI_MSI_ADDRESS_LO;
+	msg_addr_lower = dw_pcie_readl_dbi(pci, reg);
 	if (has_upper) {
-		msg_addr_upper = dw_pcie_readl_dbi(pci, MSI_MESSAGE_ADDR_U32);
-		msg_data = dw_pcie_readw_dbi(pci, MSI_MESSAGE_DATA_64);
+		reg = ep->msi_cap + PCI_MSI_ADDRESS_HI;
+		msg_addr_upper = dw_pcie_readl_dbi(pci, reg);
+		reg = ep->msi_cap + PCI_MSI_DATA_64;
+		msg_data = dw_pcie_readw_dbi(pci, reg);
 	} else {
 		msg_addr_upper = 0;
-		msg_data = dw_pcie_readw_dbi(pci, MSI_MESSAGE_DATA_32);
+		reg = ep->msi_cap + PCI_MSI_DATA_32;
+		msg_data = dw_pcie_readw_dbi(pci, reg);
 	}
 	msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower;
 	ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr,
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 00ac4197c457..e8b97f5a64be 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -96,17 +96,6 @@
 #define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region)				\
 			((0x3 << 20) | ((region) << 9) | (0x1 << 8))
 
-#define MSI_MESSAGE_CONTROL		0x52
-#define MSI_CAP_MMC_SHIFT		1
-#define MSI_CAP_MMC_MASK		(7 << MSI_CAP_MMC_SHIFT)
-#define MSI_CAP_MME_SHIFT		4
-#define MSI_CAP_MSI_EN_MASK		0x1
-#define MSI_CAP_MME_MASK		(7 << MSI_CAP_MME_SHIFT)
-#define MSI_MESSAGE_ADDR_L32		0x54
-#define MSI_MESSAGE_ADDR_U32		0x58
-#define MSI_MESSAGE_DATA_32		0x58
-#define MSI_MESSAGE_DATA_64		0x5C
-
 #define MAX_MSI_IRQS			256
 #define MAX_MSI_IRQS_PER_CTRL		32
 #define MAX_MSI_CTRLS			(MAX_MSI_IRQS / MAX_MSI_IRQS_PER_CTRL)
-- 
cgit v1.2.3


From cb22d40b5f2bcf9d374ae92ea504df620daea342 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:16 +0200
Subject: PCI: dwc: Add legacy interrupt callback handler

Currently DesignWare IP does not handle legacy interrupts.
Add a legacy interrupt callback handler.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
[lorenzo.pieralisi@arm.com: updated commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/pci/controller/dwc/pcie-designware-ep.c   | 10 ++++++++++
 drivers/pci/controller/dwc/pcie-designware-plat.c |  3 +--
 drivers/pci/controller/dwc/pcie-designware.h      |  6 ++++++
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index dd9c36678cba..1e7b02221eac 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -370,6 +370,16 @@ static const struct pci_epc_ops epc_ops = {
 	.stop			= dw_pcie_ep_stop,
 };
 
+int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	struct device *dev = pci->dev;
+
+	dev_err(dev, "EP cannot trigger legacy IRQs\n");
+
+	return -EINVAL;
+}
+
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num)
 {
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index 35d2291c6ba5..3f8a3aa3a91e 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -87,8 +87,7 @@ static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
 
 	switch (type) {
 	case PCI_EPC_IRQ_LEGACY:
-		dev_err(pci->dev, "EP cannot trigger legacy IRQs\n");
-		return -EINVAL;
+		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
 	case PCI_EPC_IRQ_MSI:
 		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
 	case PCI_EPC_IRQ_MSIX:
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index e8b97f5a64be..96126fd8403c 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -348,6 +348,7 @@ static inline int dw_pcie_allocate_domains(struct pcie_port *pp)
 void dw_pcie_ep_linkup(struct dw_pcie_ep *ep);
 int dw_pcie_ep_init(struct dw_pcie_ep *ep);
 void dw_pcie_ep_exit(struct dw_pcie_ep *ep);
+int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no);
 int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 			     u8 interrupt_num);
 int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no,
@@ -367,6 +368,11 @@ static inline void dw_pcie_ep_exit(struct dw_pcie_ep *ep)
 {
 }
 
+static inline int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
+{
+	return 0;
+}
+
 static inline int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no,
 					   u8 interrupt_num)
 {
-- 
cgit v1.2.3


From e8817de7fbfca407f4f47da050d12b10fece5706 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:17 +0200
Subject: pci-epf-test/pci_endpoint_test: Cleanup PCI_ENDPOINT_TEST memspace

Cleanup PCI_ENDPOINT_TEST memspace (by moving the interrupt number away
from command section).

Add IRQ_TYPE register to identify the triggered ID interrupt required
for the READ/WRITE/COPY tests and raise IRQ test commands.

Update documentation accordingly.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 Documentation/PCI/endpoint/pci-test-function.txt | 27 ++++++--
 drivers/misc/pci_endpoint_test.c                 | 81 +++++++++++++++---------
 drivers/pci/endpoint/functions/pci-epf-test.c    | 61 ++++++++++++------
 3 files changed, 114 insertions(+), 55 deletions(-)

diff --git a/Documentation/PCI/endpoint/pci-test-function.txt b/Documentation/PCI/endpoint/pci-test-function.txt
index 0c519c9bf94a..bf4b5cf6fee6 100644
--- a/Documentation/PCI/endpoint/pci-test-function.txt
+++ b/Documentation/PCI/endpoint/pci-test-function.txt
@@ -20,6 +20,8 @@ The PCI endpoint test device has the following registers:
 	5) PCI_ENDPOINT_TEST_DST_ADDR
 	6) PCI_ENDPOINT_TEST_SIZE
 	7) PCI_ENDPOINT_TEST_CHECKSUM
+	8) PCI_ENDPOINT_TEST_IRQ_TYPE
+	9) PCI_ENDPOINT_TEST_IRQ_NUMBER
 
 *) PCI_ENDPOINT_TEST_MAGIC
 
@@ -34,10 +36,10 @@ that the endpoint device must perform.
 Bitfield Description:
   Bit 0		: raise legacy IRQ
   Bit 1		: raise MSI IRQ
-  Bit 2 - 7	: MSI interrupt number
-  Bit 8		: read command (read data from RC buffer)
-  Bit 9		: write command (write data to RC buffer)
-  Bit 10	: copy command (copy data from one RC buffer to another
+  Bit 2		: raise MSI-X IRQ (reserved for future implementation)
+  Bit 3		: read command (read data from RC buffer)
+  Bit 4		: write command (write data to RC buffer)
+  Bit 5		: copy command (copy data from one RC buffer to another
 		  RC buffer)
 
 *) PCI_ENDPOINT_TEST_STATUS
@@ -64,3 +66,20 @@ COPY/READ command.
 
 This register contains the destination address (RC buffer address) for
 the COPY/WRITE command.
+
+*) PCI_ENDPOINT_TEST_IRQ_TYPE
+
+This register contains the interrupt type (Legacy/MSI) triggered
+for the READ/WRITE/COPY and raise IRQ (Legacy/MSI) commands.
+
+Possible types:
+ - Legacy	: 0
+ - MSI		: 1
+
+*) PCI_ENDPOINT_TEST_IRQ_NUMBER
+
+This register contains the triggered ID interrupt.
+
+Admissible values:
+ - Legacy	: 0
+ - MSI		: [1 .. 32]
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index 7b370466a227..35fbfbd73a6d 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -35,38 +35,43 @@
 
 #include <uapi/linux/pcitest.h>
 
-#define DRV_MODULE_NAME			"pci-endpoint-test"
-
-#define PCI_ENDPOINT_TEST_MAGIC		0x0
-
-#define PCI_ENDPOINT_TEST_COMMAND	0x4
-#define COMMAND_RAISE_LEGACY_IRQ	BIT(0)
-#define COMMAND_RAISE_MSI_IRQ		BIT(1)
-#define MSI_NUMBER_SHIFT		2
-/* 6 bits for MSI number */
-#define COMMAND_READ                    BIT(8)
-#define COMMAND_WRITE                   BIT(9)
-#define COMMAND_COPY                    BIT(10)
-
-#define PCI_ENDPOINT_TEST_STATUS	0x8
-#define STATUS_READ_SUCCESS             BIT(0)
-#define STATUS_READ_FAIL                BIT(1)
-#define STATUS_WRITE_SUCCESS            BIT(2)
-#define STATUS_WRITE_FAIL               BIT(3)
-#define STATUS_COPY_SUCCESS             BIT(4)
-#define STATUS_COPY_FAIL                BIT(5)
-#define STATUS_IRQ_RAISED               BIT(6)
-#define STATUS_SRC_ADDR_INVALID         BIT(7)
-#define STATUS_DST_ADDR_INVALID         BIT(8)
-
-#define PCI_ENDPOINT_TEST_LOWER_SRC_ADDR	0xc
+#define DRV_MODULE_NAME				"pci-endpoint-test"
+
+#define IRQ_TYPE_LEGACY				0
+#define IRQ_TYPE_MSI				1
+
+#define PCI_ENDPOINT_TEST_MAGIC			0x0
+
+#define PCI_ENDPOINT_TEST_COMMAND		0x4
+#define COMMAND_RAISE_LEGACY_IRQ		BIT(0)
+#define COMMAND_RAISE_MSI_IRQ			BIT(1)
+/* BIT(2) is reserved for raising MSI-X IRQ command */
+#define COMMAND_READ				BIT(3)
+#define COMMAND_WRITE				BIT(4)
+#define COMMAND_COPY				BIT(5)
+
+#define PCI_ENDPOINT_TEST_STATUS		0x8
+#define STATUS_READ_SUCCESS			BIT(0)
+#define STATUS_READ_FAIL			BIT(1)
+#define STATUS_WRITE_SUCCESS			BIT(2)
+#define STATUS_WRITE_FAIL			BIT(3)
+#define STATUS_COPY_SUCCESS			BIT(4)
+#define STATUS_COPY_FAIL			BIT(5)
+#define STATUS_IRQ_RAISED			BIT(6)
+#define STATUS_SRC_ADDR_INVALID			BIT(7)
+#define STATUS_DST_ADDR_INVALID			BIT(8)
+
+#define PCI_ENDPOINT_TEST_LOWER_SRC_ADDR	0x0c
 #define PCI_ENDPOINT_TEST_UPPER_SRC_ADDR	0x10
 
 #define PCI_ENDPOINT_TEST_LOWER_DST_ADDR	0x14
 #define PCI_ENDPOINT_TEST_UPPER_DST_ADDR	0x18
 
-#define PCI_ENDPOINT_TEST_SIZE		0x1c
-#define PCI_ENDPOINT_TEST_CHECKSUM	0x20
+#define PCI_ENDPOINT_TEST_SIZE			0x1c
+#define PCI_ENDPOINT_TEST_CHECKSUM		0x20
+
+#define PCI_ENDPOINT_TEST_IRQ_TYPE		0x24
+#define PCI_ENDPOINT_TEST_IRQ_NUMBER		0x28
 
 static DEFINE_IDA(pci_endpoint_test_ida);
 
@@ -179,6 +184,9 @@ static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test)
 {
 	u32 val;
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
+				 IRQ_TYPE_LEGACY);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 0);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
 				 COMMAND_RAISE_LEGACY_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
@@ -195,8 +203,10 @@ static bool pci_endpoint_test_msi_irq(struct pci_endpoint_test *test,
 	u32 val;
 	struct pci_dev *pdev = test->pdev;
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
+				 IRQ_TYPE_MSI);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, msi_num);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 msi_num << MSI_NUMBER_SHIFT |
 				 COMMAND_RAISE_MSI_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
 					  msecs_to_jiffies(1000));
@@ -281,8 +291,11 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size)
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE,
 				 size);
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
+				 no_msi ? IRQ_TYPE_LEGACY : IRQ_TYPE_MSI);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 1 << MSI_NUMBER_SHIFT | COMMAND_COPY);
+				 COMMAND_COPY);
 
 	wait_for_completion(&test->irq_raised);
 
@@ -348,8 +361,11 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size)
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size);
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
+				 no_msi ? IRQ_TYPE_LEGACY : IRQ_TYPE_MSI);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 1 << MSI_NUMBER_SHIFT | COMMAND_READ);
+				 COMMAND_READ);
 
 	wait_for_completion(&test->irq_raised);
 
@@ -403,8 +419,11 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size)
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size);
 
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
+				 no_msi ? IRQ_TYPE_LEGACY : IRQ_TYPE_MSI);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 1 << MSI_NUMBER_SHIFT | COMMAND_WRITE);
+				 COMMAND_WRITE);
 
 	wait_for_completion(&test->irq_raised);
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 63ed706445b9..db4b23672004 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -18,13 +18,15 @@
 #include <linux/pci-epf.h>
 #include <linux/pci_regs.h>
 
+#define IRQ_TYPE_LEGACY			0
+#define IRQ_TYPE_MSI			1
+
 #define COMMAND_RAISE_LEGACY_IRQ	BIT(0)
 #define COMMAND_RAISE_MSI_IRQ		BIT(1)
-#define MSI_NUMBER_SHIFT		2
-#define MSI_NUMBER_MASK			(0x3f << MSI_NUMBER_SHIFT)
-#define COMMAND_READ			BIT(8)
-#define COMMAND_WRITE			BIT(9)
-#define COMMAND_COPY			BIT(10)
+/* BIT(2) is reserved for raising MSI-X IRQ command */
+#define COMMAND_READ			BIT(3)
+#define COMMAND_WRITE			BIT(4)
+#define COMMAND_COPY			BIT(5)
 
 #define STATUS_READ_SUCCESS		BIT(0)
 #define STATUS_READ_FAIL		BIT(1)
@@ -56,6 +58,8 @@ struct pci_epf_test_reg {
 	u64	dst_addr;
 	u32	size;
 	u32	checksum;
+	u32	irq_type;
+	u32	irq_number;
 } __packed;
 
 static struct pci_epf_header test_header = {
@@ -244,31 +248,39 @@ err:
 	return ret;
 }
 
-static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq)
+static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq_type,
+				   u16 irq)
 {
-	u8 msi_count;
 	struct pci_epf *epf = epf_test->epf;
+	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
 	enum pci_barno test_reg_bar = epf_test->test_reg_bar;
 	struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar];
 
 	reg->status |= STATUS_IRQ_RAISED;
-	msi_count = pci_epc_get_msi(epc, epf->func_no);
-	if (irq > msi_count || msi_count <= 0)
+
+	switch (irq_type) {
+	case IRQ_TYPE_LEGACY:
 		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_LEGACY, 0);
-	else
+		break;
+	case IRQ_TYPE_MSI:
 		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq);
+		break;
+	default:
+		dev_err(dev, "Failed to raise IRQ, unknown type\n");
+		break;
+	}
 }
 
 static void pci_epf_test_cmd_handler(struct work_struct *work)
 {
 	int ret;
-	u8 irq;
-	u8 msi_count;
+	int count;
 	u32 command;
 	struct pci_epf_test *epf_test = container_of(work, struct pci_epf_test,
 						     cmd_handler.work);
 	struct pci_epf *epf = epf_test->epf;
+	struct device *dev = &epf->dev;
 	struct pci_epc *epc = epf->epc;
 	enum pci_barno test_reg_bar = epf_test->test_reg_bar;
 	struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar];
@@ -280,7 +292,10 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 	reg->command = 0;
 	reg->status = 0;
 
-	irq = (command & MSI_NUMBER_MASK) >> MSI_NUMBER_SHIFT;
+	if (reg->irq_type > IRQ_TYPE_MSI) {
+		dev_err(dev, "Failed to detect IRQ type\n");
+		goto reset_handler;
+	}
 
 	if (command & COMMAND_RAISE_LEGACY_IRQ) {
 		reg->status = STATUS_IRQ_RAISED;
@@ -294,7 +309,8 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 			reg->status |= STATUS_WRITE_FAIL;
 		else
 			reg->status |= STATUS_WRITE_SUCCESS;
-		pci_epf_test_raise_irq(epf_test, irq);
+		pci_epf_test_raise_irq(epf_test, reg->irq_type,
+				       reg->irq_number);
 		goto reset_handler;
 	}
 
@@ -304,7 +320,8 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 			reg->status |= STATUS_READ_SUCCESS;
 		else
 			reg->status |= STATUS_READ_FAIL;
-		pci_epf_test_raise_irq(epf_test, irq);
+		pci_epf_test_raise_irq(epf_test, reg->irq_type,
+				       reg->irq_number);
 		goto reset_handler;
 	}
 
@@ -314,16 +331,18 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 			reg->status |= STATUS_COPY_SUCCESS;
 		else
 			reg->status |= STATUS_COPY_FAIL;
-		pci_epf_test_raise_irq(epf_test, irq);
+		pci_epf_test_raise_irq(epf_test, reg->irq_type,
+				       reg->irq_number);
 		goto reset_handler;
 	}
 
 	if (command & COMMAND_RAISE_MSI_IRQ) {
-		msi_count = pci_epc_get_msi(epc, epf->func_no);
-		if (irq > msi_count || msi_count <= 0)
+		count = pci_epc_get_msi(epc, epf->func_no);
+		if (reg->irq_number > count || count <= 0)
 			goto reset_handler;
 		reg->status = STATUS_IRQ_RAISED;
-		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq);
+		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI,
+				  reg->irq_number);
 		goto reset_handler;
 	}
 
@@ -457,8 +476,10 @@ static int pci_epf_test_bind(struct pci_epf *epf)
 		return ret;
 
 	ret = pci_epc_set_msi(epc, epf->func_no, epf->msi_interrupts);
-	if (ret)
+	if (ret) {
+		dev_err(dev, "MSI configuration failed\n");
 		return ret;
+	}
 
 	if (!epf_test->linkup_notifier)
 		queue_work(kpcitest_workqueue, &epf_test->cmd_handler.work);
-- 
cgit v1.2.3


From 9133e394d5ed1c81c1141d611915e09e9f32330d Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:18 +0200
Subject: pci-epf-test/pci_endpoint_test: Use irq_type module parameter

Add new driver parameter to allow interruption type selection.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/misc/pci_endpoint_test.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index 35fbfbd73a6d..349794cbe1f3 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -82,6 +82,10 @@ static bool no_msi;
 module_param(no_msi, bool, 0444);
 MODULE_PARM_DESC(no_msi, "Disable MSI interrupt in pci_endpoint_test");
 
+static int irq_type = IRQ_TYPE_MSI;
+module_param(irq_type, int, 0444);
+MODULE_PARM_DESC(irq_type, "IRQ mode selection in pci_endpoint_test (0 - Legacy, 1 - MSI)");
+
 enum pci_barno {
 	BAR_0,
 	BAR_1,
@@ -108,7 +112,7 @@ struct pci_endpoint_test {
 struct pci_endpoint_test_data {
 	enum pci_barno test_reg_bar;
 	size_t alignment;
-	bool no_msi;
+	int irq_type;
 };
 
 static inline u32 pci_endpoint_test_readl(struct pci_endpoint_test *test,
@@ -291,8 +295,7 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size)
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE,
 				 size);
 
-	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
-				 no_msi ? IRQ_TYPE_LEGACY : IRQ_TYPE_MSI);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
 				 COMMAND_COPY);
@@ -361,8 +364,7 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size)
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size);
 
-	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
-				 no_msi ? IRQ_TYPE_LEGACY : IRQ_TYPE_MSI);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
 				 COMMAND_READ);
@@ -419,8 +421,7 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size)
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_SIZE, size);
 
-	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
-				 no_msi ? IRQ_TYPE_LEGACY : IRQ_TYPE_MSI);
+	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE, irq_type);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, 1);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
 				 COMMAND_WRITE);
@@ -505,11 +506,14 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 	test->alignment = 0;
 	test->pdev = pdev;
 
+	if (no_msi)
+		irq_type = IRQ_TYPE_LEGACY;
+
 	data = (struct pci_endpoint_test_data *)ent->driver_data;
 	if (data) {
 		test_reg_bar = data->test_reg_bar;
 		test->alignment = data->alignment;
-		no_msi = data->no_msi;
+		irq_type = data->irq_type;
 	}
 
 	init_completion(&test->irq_raised);
@@ -529,11 +533,17 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	if (!no_msi) {
+	switch (irq_type) {
+	case IRQ_TYPE_LEGACY:
+		break;
+	case IRQ_TYPE_MSI:
 		irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI);
 		if (irq < 0)
 			dev_err(dev, "Failed to get MSI interrupts\n");
 		test->num_irqs = irq;
+		break;
+	default:
+		dev_err(dev, "Invalid IRQ type selected\n");
 	}
 
 	err = devm_request_irq(dev, pdev->irq, pci_endpoint_test_irqhandler,
-- 
cgit v1.2.3


From c2e00e31087e58f6c49b90b4702fc3df4fad6a83 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:19 +0200
Subject: pci-epf-test/pci_endpoint_test: Add MSI-X support

Add MSI-X support and update driver documentation accordingly.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 Documentation/PCI/endpoint/pci-endpoint.txt       |  4 ++--
 Documentation/PCI/endpoint/pci-test-function.txt  |  4 +++-
 Documentation/PCI/endpoint/pci-test-howto.txt     | 22 ++++++++++++++---
 Documentation/ioctl/ioctl-number.txt              |  1 +
 Documentation/misc-devices/pci-endpoint-test.txt  |  3 +++
 drivers/misc/pci_endpoint_test.c                  | 29 ++++++++++++++++-------
 drivers/pci/controller/dwc/pcie-designware-plat.c |  1 +
 drivers/pci/endpoint/functions/pci-epf-test.c     | 29 +++++++++++++++++++++--
 include/linux/pci-epc.h                           |  1 +
 include/uapi/linux/pcitest.h                      |  1 +
 10 files changed, 79 insertions(+), 16 deletions(-)

diff --git a/Documentation/PCI/endpoint/pci-endpoint.txt b/Documentation/PCI/endpoint/pci-endpoint.txt
index 9b1d66829290..e86a96b66a6a 100644
--- a/Documentation/PCI/endpoint/pci-endpoint.txt
+++ b/Documentation/PCI/endpoint/pci-endpoint.txt
@@ -44,7 +44,7 @@ by the PCI controller driver.
 	 * clear_bar: ops to reset the BAR
 	 * alloc_addr_space: ops to allocate in PCI controller address space
 	 * free_addr_space: ops to free the allocated address space
-	 * raise_irq: ops to raise a legacy or MSI interrupt
+	 * raise_irq: ops to raise a legacy, MSI or MSI-X interrupt
 	 * start: ops to start the PCI link
 	 * stop: ops to stop the PCI link
 
@@ -96,7 +96,7 @@ by the PCI endpoint function driver.
 *) pci_epc_raise_irq()
 
    The PCI endpoint function driver should use pci_epc_raise_irq() to raise
-   Legacy Interrupt or MSI Interrupt.
+   Legacy Interrupt, MSI or MSI-X Interrupt.
 
 *) pci_epc_mem_alloc_addr()
 
diff --git a/Documentation/PCI/endpoint/pci-test-function.txt b/Documentation/PCI/endpoint/pci-test-function.txt
index bf4b5cf6fee6..5916f1f592bb 100644
--- a/Documentation/PCI/endpoint/pci-test-function.txt
+++ b/Documentation/PCI/endpoint/pci-test-function.txt
@@ -36,7 +36,7 @@ that the endpoint device must perform.
 Bitfield Description:
   Bit 0		: raise legacy IRQ
   Bit 1		: raise MSI IRQ
-  Bit 2		: raise MSI-X IRQ (reserved for future implementation)
+  Bit 2		: raise MSI-X IRQ
   Bit 3		: read command (read data from RC buffer)
   Bit 4		: write command (write data to RC buffer)
   Bit 5		: copy command (copy data from one RC buffer to another
@@ -75,6 +75,7 @@ for the READ/WRITE/COPY and raise IRQ (Legacy/MSI) commands.
 Possible types:
  - Legacy	: 0
  - MSI		: 1
+ - MSI-X	: 2
 
 *) PCI_ENDPOINT_TEST_IRQ_NUMBER
 
@@ -83,3 +84,4 @@ This register contains the triggered ID interrupt.
 Admissible values:
  - Legacy	: 0
  - MSI		: [1 .. 32]
+ - MSI-X	: [1 .. 2048]
diff --git a/Documentation/PCI/endpoint/pci-test-howto.txt b/Documentation/PCI/endpoint/pci-test-howto.txt
index 75f48c3bb191..65f1a137e35c 100644
--- a/Documentation/PCI/endpoint/pci-test-howto.txt
+++ b/Documentation/PCI/endpoint/pci-test-howto.txt
@@ -45,9 +45,9 @@ The PCI endpoint framework populates the directory with the following
 configurable fields.
 
 	# ls functions/pci_epf_test/func1
-	  baseclass_code	interrupt_pin	revid		subsys_vendor_id
-	  cache_line_size	msi_interrupts	subclass_code	vendorid
-	  deviceid          	progif_code	subsys_id
+	  baseclass_code	interrupt_pin	progif_code	subsys_id
+	  cache_line_size	msi_interrupts	revid		subsys_vendorid
+	  deviceid          	msix_interrupts	subclass_code	vendorid
 
 The PCI endpoint function driver populates these entries with default values
 when the device is bound to the driver. The pci-epf-test driver populates
@@ -67,6 +67,7 @@ device, the following commands can be used.
 	# echo 0x104c > functions/pci_epf_test/func1/vendorid
 	# echo 0xb500 > functions/pci_epf_test/func1/deviceid
 	# echo 16 > functions/pci_epf_test/func1/msi_interrupts
+	# echo 8 > functions/pci_epf_test/func1/msix_interrupts
 
 1.5 Binding pci-epf-test Device to EP Controller
 
@@ -153,6 +154,21 @@ following commands.
 	MSI30:          NOT OKAY
 	MSI31:          NOT OKAY
 	MSI32:          NOT OKAY
+	MSIX1:          OKAY
+	MSIX2:          OKAY
+	MSIX3:          OKAY
+	MSIX4:          OKAY
+	MSIX5:          OKAY
+	MSIX6:          OKAY
+	MSIX7:          OKAY
+	MSIX8:          OKAY
+	MSIX9:          NOT OKAY
+	MSIX10:         NOT OKAY
+	MSIX11:         NOT OKAY
+	MSIX12:         NOT OKAY
+	MSIX13:         NOT OKAY
+	[...]
+	MSIX2048:       NOT OKAY
 
 	Read Tests
 
diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 480c8609dc58..65259d459fd1 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -166,6 +166,7 @@ Code  Seq#(hex)	Include File		Comments
 'P'	all	linux/soundcard.h	conflict!
 'P'	60-6F	sound/sscape_ioctl.h	conflict!
 'P'	00-0F	drivers/usb/class/usblp.c	conflict!
+'P'	01-07	drivers/misc/pci_endpoint_test.c	conflict!
 'Q'	all	linux/soundcard.h
 'R'	00-1F	linux/random.h		conflict!
 'R'	01	linux/rfkill.h		conflict!
diff --git a/Documentation/misc-devices/pci-endpoint-test.txt b/Documentation/misc-devices/pci-endpoint-test.txt
index 4ebc3594b32c..fdfa0f66d3d0 100644
--- a/Documentation/misc-devices/pci-endpoint-test.txt
+++ b/Documentation/misc-devices/pci-endpoint-test.txt
@@ -10,6 +10,7 @@ The PCI driver for the test device performs the following tests
 	*) verifying addresses programmed in BAR
 	*) raise legacy IRQ
 	*) raise MSI IRQ
+	*) raise MSI-X IRQ
 	*) read data
 	*) write data
 	*) copy data
@@ -25,6 +26,8 @@ ioctl
  PCITEST_LEGACY_IRQ: Tests legacy IRQ
  PCITEST_MSI: Tests message signalled interrupts. The MSI number
 	      to be tested should be passed as argument.
+ PCITEST_MSIX: Tests message signalled interrupts. The MSI-X number
+	      to be tested should be passed as argument.
  PCITEST_WRITE: Perform write tests. The size of the buffer should be passed
 		as argument.
  PCITEST_READ: Perform read tests. The size of the buffer should be passed
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index 349794cbe1f3..f4fef108caff 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -39,13 +39,14 @@
 
 #define IRQ_TYPE_LEGACY				0
 #define IRQ_TYPE_MSI				1
+#define IRQ_TYPE_MSIX				2
 
 #define PCI_ENDPOINT_TEST_MAGIC			0x0
 
 #define PCI_ENDPOINT_TEST_COMMAND		0x4
 #define COMMAND_RAISE_LEGACY_IRQ		BIT(0)
 #define COMMAND_RAISE_MSI_IRQ			BIT(1)
-/* BIT(2) is reserved for raising MSI-X IRQ command */
+#define COMMAND_RAISE_MSIX_IRQ			BIT(2)
 #define COMMAND_READ				BIT(3)
 #define COMMAND_WRITE				BIT(4)
 #define COMMAND_COPY				BIT(5)
@@ -84,7 +85,7 @@ MODULE_PARM_DESC(no_msi, "Disable MSI interrupt in pci_endpoint_test");
 
 static int irq_type = IRQ_TYPE_MSI;
 module_param(irq_type, int, 0444);
-MODULE_PARM_DESC(irq_type, "IRQ mode selection in pci_endpoint_test (0 - Legacy, 1 - MSI)");
+MODULE_PARM_DESC(irq_type, "IRQ mode selection in pci_endpoint_test (0 - Legacy, 1 - MSI, 2 - MSI-X)");
 
 enum pci_barno {
 	BAR_0,
@@ -202,16 +203,18 @@ static bool pci_endpoint_test_legacy_irq(struct pci_endpoint_test *test)
 }
 
 static bool pci_endpoint_test_msi_irq(struct pci_endpoint_test *test,
-				      u8 msi_num)
+				       u16 msi_num, bool msix)
 {
 	u32 val;
 	struct pci_dev *pdev = test->pdev;
 
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_TYPE,
-				 IRQ_TYPE_MSI);
+				 msix == false ? IRQ_TYPE_MSI :
+				 IRQ_TYPE_MSIX);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_IRQ_NUMBER, msi_num);
 	pci_endpoint_test_writel(test, PCI_ENDPOINT_TEST_COMMAND,
-				 COMMAND_RAISE_MSI_IRQ);
+				 msix == false ? COMMAND_RAISE_MSI_IRQ :
+				 COMMAND_RAISE_MSIX_IRQ);
 	val = wait_for_completion_timeout(&test->irq_raised,
 					  msecs_to_jiffies(1000));
 	if (!val)
@@ -456,7 +459,8 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 		ret = pci_endpoint_test_legacy_irq(test);
 		break;
 	case PCITEST_MSI:
-		ret = pci_endpoint_test_msi_irq(test, arg);
+	case PCITEST_MSIX:
+		ret = pci_endpoint_test_msi_irq(test, arg, cmd == PCITEST_MSIX);
 		break;
 	case PCITEST_WRITE:
 		ret = pci_endpoint_test_write(test, arg);
@@ -542,6 +546,12 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 			dev_err(dev, "Failed to get MSI interrupts\n");
 		test->num_irqs = irq;
 		break;
+	case IRQ_TYPE_MSIX:
+		irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX);
+		if (irq < 0)
+			dev_err(dev, "Failed to get MSI-X interrupts\n");
+		test->num_irqs = irq;
+		break;
 	default:
 		dev_err(dev, "Invalid IRQ type selected\n");
 	}
@@ -558,8 +568,9 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 				       pci_endpoint_test_irqhandler,
 				       IRQF_SHARED, DRV_MODULE_NAME, test);
 		if (err)
-			dev_err(dev, "failed to request IRQ %d for MSI %d\n",
-				pci_irq_vector(pdev, i), i + 1);
+			dev_err(dev, "Failed to request IRQ %d for MSI%s %d\n",
+				pci_irq_vector(pdev, i),
+				irq_type == IRQ_TYPE_MSIX ? "-X" : "", i + 1);
 	}
 
 	for (bar = BAR_0; bar <= BAR_5; bar++) {
@@ -625,6 +636,7 @@ err_iounmap:
 
 err_disable_msi:
 	pci_disable_msi(pdev);
+	pci_disable_msix(pdev);
 	pci_release_regions(pdev);
 
 err_disable_pdev:
@@ -656,6 +668,7 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
 	for (i = 0; i < test->num_irqs; i++)
 		devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test);
 	pci_disable_msi(pdev);
+	pci_disable_msix(pdev);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 }
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index 3f8a3aa3a91e..c12bf794d69c 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -77,6 +77,7 @@ static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 		dw_pcie_ep_reset_bar(pci, bar);
 
 	epc->features |= EPC_FEATURE_NO_LINKUP_NOTIFIER;
+	epc->features |= EPC_FEATURE_MSIX_AVAILABLE;
 }
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index db4b23672004..3e86fa3c7da3 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -20,10 +20,11 @@
 
 #define IRQ_TYPE_LEGACY			0
 #define IRQ_TYPE_MSI			1
+#define IRQ_TYPE_MSIX			2
 
 #define COMMAND_RAISE_LEGACY_IRQ	BIT(0)
 #define COMMAND_RAISE_MSI_IRQ		BIT(1)
-/* BIT(2) is reserved for raising MSI-X IRQ command */
+#define COMMAND_RAISE_MSIX_IRQ		BIT(2)
 #define COMMAND_READ			BIT(3)
 #define COMMAND_WRITE			BIT(4)
 #define COMMAND_COPY			BIT(5)
@@ -47,6 +48,7 @@ struct pci_epf_test {
 	struct pci_epf		*epf;
 	enum pci_barno		test_reg_bar;
 	bool			linkup_notifier;
+	bool			msix_available;
 	struct delayed_work	cmd_handler;
 };
 
@@ -266,6 +268,9 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, u8 irq_type,
 	case IRQ_TYPE_MSI:
 		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSI, irq);
 		break;
+	case IRQ_TYPE_MSIX:
+		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX, irq);
+		break;
 	default:
 		dev_err(dev, "Failed to raise IRQ, unknown type\n");
 		break;
@@ -292,7 +297,7 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 	reg->command = 0;
 	reg->status = 0;
 
-	if (reg->irq_type > IRQ_TYPE_MSI) {
+	if (reg->irq_type > IRQ_TYPE_MSIX) {
 		dev_err(dev, "Failed to detect IRQ type\n");
 		goto reset_handler;
 	}
@@ -346,6 +351,16 @@ static void pci_epf_test_cmd_handler(struct work_struct *work)
 		goto reset_handler;
 	}
 
+	if (command & COMMAND_RAISE_MSIX_IRQ) {
+		count = pci_epc_get_msix(epc, epf->func_no);
+		if (reg->irq_number > count || count <= 0)
+			goto reset_handler;
+		reg->status = STATUS_IRQ_RAISED;
+		pci_epc_raise_irq(epc, epf->func_no, PCI_EPC_IRQ_MSIX,
+				  reg->irq_number);
+		goto reset_handler;
+	}
+
 reset_handler:
 	queue_delayed_work(kpcitest_workqueue, &epf_test->cmd_handler,
 			   msecs_to_jiffies(1));
@@ -459,6 +474,8 @@ static int pci_epf_test_bind(struct pci_epf *epf)
 	else
 		epf_test->linkup_notifier = true;
 
+	epf_test->msix_available = epc->features & EPC_FEATURE_MSIX_AVAILABLE;
+
 	epf_test->test_reg_bar = EPC_FEATURE_GET_BAR(epc->features);
 
 	ret = pci_epc_write_header(epc, epf->func_no, header);
@@ -481,6 +498,14 @@ static int pci_epf_test_bind(struct pci_epf *epf)
 		return ret;
 	}
 
+	if (epf_test->msix_available) {
+		ret = pci_epc_set_msix(epc, epf->func_no, epf->msix_interrupts);
+		if (ret) {
+			dev_err(dev, "MSI-X configuration failed\n");
+			return ret;
+		}
+	}
+
 	if (!epf_test->linkup_notifier)
 		queue_work(kpcitest_workqueue, &epf_test->cmd_handler.work);
 
diff --git a/include/linux/pci-epc.h b/include/linux/pci-epc.h
index bb2395b56f13..37dab8116901 100644
--- a/include/linux/pci-epc.h
+++ b/include/linux/pci-epc.h
@@ -102,6 +102,7 @@ struct pci_epc {
 
 #define EPC_FEATURE_NO_LINKUP_NOTIFIER		BIT(0)
 #define EPC_FEATURE_BAR_MASK			(BIT(1) | BIT(2) | BIT(3))
+#define EPC_FEATURE_MSIX_AVAILABLE		BIT(4)
 #define EPC_FEATURE_SET_BAR(features, bar)	\
 		(features |= (EPC_FEATURE_BAR_MASK & (bar << 1)))
 #define EPC_FEATURE_GET_BAR(features)		\
diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h
index 953cf036cb26..d746fb159dcd 100644
--- a/include/uapi/linux/pcitest.h
+++ b/include/uapi/linux/pcitest.h
@@ -16,5 +16,6 @@
 #define PCITEST_WRITE		_IOW('P', 0x4, unsigned long)
 #define PCITEST_READ		_IOW('P', 0x5, unsigned long)
 #define PCITEST_COPY		_IOW('P', 0x6, unsigned long)
+#define PCITEST_MSIX		_IOW('P', 0x7, int)
 
 #endif /* __UAPI_LINUX_PCITEST_H */
-- 
cgit v1.2.3


From e03327122e2c8e6ae4565ef5b3d3cbe4364546a1 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:20 +0200
Subject: pci_endpoint_test: Add 2 ioctl commands

Add MSI-X support and update driver documentation accordingly.

Add 2 new IOCTL commands:
 - Allow to reconfigure driver IRQ type in runtime.
 - Allow to retrieve current driver IRQ type configured.

Add IRQ type validation before executing the READ/WRITE/COPY tests.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 Documentation/ioctl/ioctl-number.txt             |   2 +-
 Documentation/misc-devices/pci-endpoint-test.txt |   3 +
 drivers/misc/pci_endpoint_test.c                 | 206 +++++++++++++++++------
 include/uapi/linux/pcitest.h                     |   2 +
 4 files changed, 165 insertions(+), 48 deletions(-)

diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 65259d459fd1..c15c4f3bdd82 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -166,7 +166,7 @@ Code  Seq#(hex)	Include File		Comments
 'P'	all	linux/soundcard.h	conflict!
 'P'	60-6F	sound/sscape_ioctl.h	conflict!
 'P'	00-0F	drivers/usb/class/usblp.c	conflict!
-'P'	01-07	drivers/misc/pci_endpoint_test.c	conflict!
+'P'	01-09	drivers/misc/pci_endpoint_test.c	conflict!
 'Q'	all	linux/soundcard.h
 'R'	00-1F	linux/random.h		conflict!
 'R'	01	linux/rfkill.h		conflict!
diff --git a/Documentation/misc-devices/pci-endpoint-test.txt b/Documentation/misc-devices/pci-endpoint-test.txt
index fdfa0f66d3d0..58ccca4416b1 100644
--- a/Documentation/misc-devices/pci-endpoint-test.txt
+++ b/Documentation/misc-devices/pci-endpoint-test.txt
@@ -28,6 +28,9 @@ ioctl
 	      to be tested should be passed as argument.
  PCITEST_MSIX: Tests message signalled interrupts. The MSI-X number
 	      to be tested should be passed as argument.
+ PCITEST_SET_IRQTYPE: Changes driver IRQ type configuration. The IRQ type
+	      should be passed as argument (0: Legacy, 1:MSI, 2:MSI-X).
+ PCITEST_GET_IRQTYPE: Gets driver IRQ type configuration.
  PCITEST_WRITE: Perform write tests. The size of the buffer should be passed
 		as argument.
  PCITEST_READ: Perform read tests. The size of the buffer should be passed
diff --git a/drivers/misc/pci_endpoint_test.c b/drivers/misc/pci_endpoint_test.c
index f4fef108caff..896e2df9400f 100644
--- a/drivers/misc/pci_endpoint_test.c
+++ b/drivers/misc/pci_endpoint_test.c
@@ -37,6 +37,7 @@
 
 #define DRV_MODULE_NAME				"pci-endpoint-test"
 
+#define IRQ_TYPE_UNDEFINED			-1
 #define IRQ_TYPE_LEGACY				0
 #define IRQ_TYPE_MSI				1
 #define IRQ_TYPE_MSIX				2
@@ -157,6 +158,100 @@ static irqreturn_t pci_endpoint_test_irqhandler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void pci_endpoint_test_free_irq_vectors(struct pci_endpoint_test *test)
+{
+	struct pci_dev *pdev = test->pdev;
+
+	pci_free_irq_vectors(pdev);
+}
+
+static bool pci_endpoint_test_alloc_irq_vectors(struct pci_endpoint_test *test,
+						int type)
+{
+	int irq = -1;
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+	bool res = true;
+
+	switch (type) {
+	case IRQ_TYPE_LEGACY:
+		irq = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_LEGACY);
+		if (irq < 0)
+			dev_err(dev, "Failed to get Legacy interrupt\n");
+		break;
+	case IRQ_TYPE_MSI:
+		irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI);
+		if (irq < 0)
+			dev_err(dev, "Failed to get MSI interrupts\n");
+		break;
+	case IRQ_TYPE_MSIX:
+		irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX);
+		if (irq < 0)
+			dev_err(dev, "Failed to get MSI-X interrupts\n");
+		break;
+	default:
+		dev_err(dev, "Invalid IRQ type selected\n");
+	}
+
+	if (irq < 0) {
+		irq = 0;
+		res = false;
+	}
+	test->num_irqs = irq;
+
+	return res;
+}
+
+static void pci_endpoint_test_release_irq(struct pci_endpoint_test *test)
+{
+	int i;
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+
+	for (i = 0; i < test->num_irqs; i++)
+		devm_free_irq(dev, pci_irq_vector(pdev, i), test);
+
+	test->num_irqs = 0;
+}
+
+static bool pci_endpoint_test_request_irq(struct pci_endpoint_test *test)
+{
+	int i;
+	int err;
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+
+	for (i = 0; i < test->num_irqs; i++) {
+		err = devm_request_irq(dev, pci_irq_vector(pdev, i),
+				       pci_endpoint_test_irqhandler,
+				       IRQF_SHARED, DRV_MODULE_NAME, test);
+		if (err)
+			goto fail;
+	}
+
+	return true;
+
+fail:
+	switch (irq_type) {
+	case IRQ_TYPE_LEGACY:
+		dev_err(dev, "Failed to request IRQ %d for Legacy\n",
+			pci_irq_vector(pdev, i));
+		break;
+	case IRQ_TYPE_MSI:
+		dev_err(dev, "Failed to request IRQ %d for MSI %d\n",
+			pci_irq_vector(pdev, i),
+			i + 1);
+		break;
+	case IRQ_TYPE_MSIX:
+		dev_err(dev, "Failed to request IRQ %d for MSI-X %d\n",
+			pci_irq_vector(pdev, i),
+			i + 1);
+		break;
+	}
+
+	return false;
+}
+
 static bool pci_endpoint_test_bar(struct pci_endpoint_test *test,
 				  enum pci_barno barno)
 {
@@ -247,6 +342,11 @@ static bool pci_endpoint_test_copy(struct pci_endpoint_test *test, size_t size)
 	if (size > SIZE_MAX - alignment)
 		goto err;
 
+	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		goto err;
+	}
+
 	orig_src_addr = dma_alloc_coherent(dev, size + alignment,
 					   &orig_src_phys_addr, GFP_KERNEL);
 	if (!orig_src_addr) {
@@ -337,6 +437,11 @@ static bool pci_endpoint_test_write(struct pci_endpoint_test *test, size_t size)
 	if (size > SIZE_MAX - alignment)
 		goto err;
 
+	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		goto err;
+	}
+
 	orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr,
 				       GFP_KERNEL);
 	if (!orig_addr) {
@@ -400,6 +505,11 @@ static bool pci_endpoint_test_read(struct pci_endpoint_test *test, size_t size)
 	if (size > SIZE_MAX - alignment)
 		goto err;
 
+	if (irq_type < IRQ_TYPE_LEGACY || irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		goto err;
+	}
+
 	orig_addr = dma_alloc_coherent(dev, size + alignment, &orig_phys_addr,
 				       GFP_KERNEL);
 	if (!orig_addr) {
@@ -440,6 +550,38 @@ err:
 	return ret;
 }
 
+static bool pci_endpoint_test_set_irq(struct pci_endpoint_test *test,
+				      int req_irq_type)
+{
+	struct pci_dev *pdev = test->pdev;
+	struct device *dev = &pdev->dev;
+
+	if (req_irq_type < IRQ_TYPE_LEGACY || req_irq_type > IRQ_TYPE_MSIX) {
+		dev_err(dev, "Invalid IRQ type option\n");
+		return false;
+	}
+
+	if (irq_type == req_irq_type)
+		return true;
+
+	pci_endpoint_test_release_irq(test);
+	pci_endpoint_test_free_irq_vectors(test);
+
+	if (!pci_endpoint_test_alloc_irq_vectors(test, req_irq_type))
+		goto err;
+
+	if (!pci_endpoint_test_request_irq(test))
+		goto err;
+
+	irq_type = req_irq_type;
+	return true;
+
+err:
+	pci_endpoint_test_free_irq_vectors(test);
+	irq_type = IRQ_TYPE_UNDEFINED;
+	return false;
+}
+
 static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 				    unsigned long arg)
 {
@@ -471,6 +613,12 @@ static long pci_endpoint_test_ioctl(struct file *file, unsigned int cmd,
 	case PCITEST_COPY:
 		ret = pci_endpoint_test_copy(test, arg);
 		break;
+	case PCITEST_SET_IRQTYPE:
+		ret = pci_endpoint_test_set_irq(test, arg);
+		break;
+	case PCITEST_GET_IRQTYPE:
+		ret = irq_type;
+		break;
 	}
 
 ret:
@@ -486,9 +634,7 @@ static const struct file_operations pci_endpoint_test_fops = {
 static int pci_endpoint_test_probe(struct pci_dev *pdev,
 				   const struct pci_device_id *ent)
 {
-	int i;
 	int err;
-	int irq = 0;
 	int id;
 	char name[20];
 	enum pci_barno bar;
@@ -537,41 +683,11 @@ static int pci_endpoint_test_probe(struct pci_dev *pdev,
 
 	pci_set_master(pdev);
 
-	switch (irq_type) {
-	case IRQ_TYPE_LEGACY:
-		break;
-	case IRQ_TYPE_MSI:
-		irq = pci_alloc_irq_vectors(pdev, 1, 32, PCI_IRQ_MSI);
-		if (irq < 0)
-			dev_err(dev, "Failed to get MSI interrupts\n");
-		test->num_irqs = irq;
-		break;
-	case IRQ_TYPE_MSIX:
-		irq = pci_alloc_irq_vectors(pdev, 1, 2048, PCI_IRQ_MSIX);
-		if (irq < 0)
-			dev_err(dev, "Failed to get MSI-X interrupts\n");
-		test->num_irqs = irq;
-		break;
-	default:
-		dev_err(dev, "Invalid IRQ type selected\n");
-	}
+	if (!pci_endpoint_test_alloc_irq_vectors(test, irq_type))
+		goto err_disable_irq;
 
-	err = devm_request_irq(dev, pdev->irq, pci_endpoint_test_irqhandler,
-			       IRQF_SHARED, DRV_MODULE_NAME, test);
-	if (err) {
-		dev_err(dev, "Failed to request IRQ %d\n", pdev->irq);
-		goto err_disable_msi;
-	}
-
-	for (i = 1; i < irq; i++) {
-		err = devm_request_irq(dev, pci_irq_vector(pdev, i),
-				       pci_endpoint_test_irqhandler,
-				       IRQF_SHARED, DRV_MODULE_NAME, test);
-		if (err)
-			dev_err(dev, "Failed to request IRQ %d for MSI%s %d\n",
-				pci_irq_vector(pdev, i),
-				irq_type == IRQ_TYPE_MSIX ? "-X" : "", i + 1);
-	}
+	if (!pci_endpoint_test_request_irq(test))
+		goto err_disable_irq;
 
 	for (bar = BAR_0; bar <= BAR_5; bar++) {
 		if (pci_resource_flags(pdev, bar) & IORESOURCE_MEM) {
@@ -630,13 +746,10 @@ err_iounmap:
 		if (test->bar[bar])
 			pci_iounmap(pdev, test->bar[bar]);
 	}
+	pci_endpoint_test_release_irq(test);
 
-	for (i = 0; i < irq; i++)
-		devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test);
-
-err_disable_msi:
-	pci_disable_msi(pdev);
-	pci_disable_msix(pdev);
+err_disable_irq:
+	pci_endpoint_test_free_irq_vectors(test);
 	pci_release_regions(pdev);
 
 err_disable_pdev:
@@ -648,7 +761,6 @@ err_disable_pdev:
 static void pci_endpoint_test_remove(struct pci_dev *pdev)
 {
 	int id;
-	int i;
 	enum pci_barno bar;
 	struct pci_endpoint_test *test = pci_get_drvdata(pdev);
 	struct miscdevice *misc_device = &test->miscdev;
@@ -665,10 +777,10 @@ static void pci_endpoint_test_remove(struct pci_dev *pdev)
 		if (test->bar[bar])
 			pci_iounmap(pdev, test->bar[bar]);
 	}
-	for (i = 0; i < test->num_irqs; i++)
-		devm_free_irq(&pdev->dev, pci_irq_vector(pdev, i), test);
-	pci_disable_msi(pdev);
-	pci_disable_msix(pdev);
+
+	pci_endpoint_test_release_irq(test);
+	pci_endpoint_test_free_irq_vectors(test);
+
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
 }
diff --git a/include/uapi/linux/pcitest.h b/include/uapi/linux/pcitest.h
index d746fb159dcd..cbf422e56696 100644
--- a/include/uapi/linux/pcitest.h
+++ b/include/uapi/linux/pcitest.h
@@ -17,5 +17,7 @@
 #define PCITEST_READ		_IOW('P', 0x5, unsigned long)
 #define PCITEST_COPY		_IOW('P', 0x6, unsigned long)
 #define PCITEST_MSIX		_IOW('P', 0x7, int)
+#define PCITEST_SET_IRQTYPE	_IOW('P', 0x8, int)
+#define PCITEST_GET_IRQTYPE	_IO('P', 0x9)
 
 #endif /* __UAPI_LINUX_PCITEST_H */
-- 
cgit v1.2.3


From 0653217c180f0e5332ef75f7299220e644091b20 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:21 +0200
Subject: tools: PCI: Add MSI-X support

Add MSI-X support to pcitest tool.

Modify pcitest.sh script to accommodate MSI-X interrupt tests.

Update documentation accordingly.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 Documentation/PCI/endpoint/pci-test-howto.txt | 36 +++++++++++--------
 tools/pci/pcitest.c                           | 51 ++++++++++++++++++++++++++-
 tools/pci/pcitest.sh                          | 15 ++++++++
 3 files changed, 87 insertions(+), 15 deletions(-)

diff --git a/Documentation/PCI/endpoint/pci-test-howto.txt b/Documentation/PCI/endpoint/pci-test-howto.txt
index 65f1a137e35c..e40cf0fb58d7 100644
--- a/Documentation/PCI/endpoint/pci-test-howto.txt
+++ b/Documentation/PCI/endpoint/pci-test-howto.txt
@@ -121,7 +121,9 @@ following commands.
 
 	Interrupt tests
 
+	SET IRQ TYPE TO LEGACY:         OKAY
 	LEGACY IRQ:     NOT OKAY
+	SET IRQ TYPE TO MSI:            OKAY
 	MSI1:           OKAY
 	MSI2:           OKAY
 	MSI3:           OKAY
@@ -154,24 +156,30 @@ following commands.
 	MSI30:          NOT OKAY
 	MSI31:          NOT OKAY
 	MSI32:          NOT OKAY
-	MSIX1:          OKAY
-	MSIX2:          OKAY
-	MSIX3:          OKAY
-	MSIX4:          OKAY
-	MSIX5:          OKAY
-	MSIX6:          OKAY
-	MSIX7:          OKAY
-	MSIX8:          OKAY
-	MSIX9:          NOT OKAY
-	MSIX10:         NOT OKAY
-	MSIX11:         NOT OKAY
-	MSIX12:         NOT OKAY
-	MSIX13:         NOT OKAY
+	SET IRQ TYPE TO MSI-X:          OKAY
+	MSI-X1:         OKAY
+	MSI-X2:         OKAY
+	MSI-X3:         OKAY
+	MSI-X4:         OKAY
+	MSI-X5:         OKAY
+	MSI-X6:         OKAY
+	MSI-X7:         OKAY
+	MSI-X8:         OKAY
+	MSI-X9:         NOT OKAY
+	MSI-X10:        NOT OKAY
+	MSI-X11:        NOT OKAY
+	MSI-X12:        NOT OKAY
+	MSI-X13:        NOT OKAY
+	MSI-X14:        NOT OKAY
+	MSI-X15:        NOT OKAY
+	MSI-X16:        NOT OKAY
 	[...]
-	MSIX2048:       NOT OKAY
+	MSI-X2047:      NOT OKAY
+	MSI-X2048:      NOT OKAY
 
 	Read Tests
 
+	SET IRQ TYPE TO MSI:            OKAY
 	READ (      1 bytes):           OKAY
 	READ (   1024 bytes):           OKAY
 	READ (   1025 bytes):           OKAY
diff --git a/tools/pci/pcitest.c b/tools/pci/pcitest.c
index 9074b477bff0..af146bb03b4d 100644
--- a/tools/pci/pcitest.c
+++ b/tools/pci/pcitest.c
@@ -31,12 +31,17 @@
 #define BILLION 1E9
 
 static char *result[] = { "NOT OKAY", "OKAY" };
+static char *irq[] = { "LEGACY", "MSI", "MSI-X" };
 
 struct pci_test {
 	char		*device;
 	char		barnum;
 	bool		legacyirq;
 	unsigned int	msinum;
+	unsigned int	msixnum;
+	int		irqtype;
+	bool		set_irqtype;
+	bool		get_irqtype;
 	bool		read;
 	bool		write;
 	bool		copy;
@@ -65,6 +70,24 @@ static int run_test(struct pci_test *test)
 			fprintf(stdout, "%s\n", result[ret]);
 	}
 
+	if (test->set_irqtype) {
+		ret = ioctl(fd, PCITEST_SET_IRQTYPE, test->irqtype);
+		fprintf(stdout, "SET IRQ TYPE TO %s:\t\t", irq[test->irqtype]);
+		if (ret < 0)
+			fprintf(stdout, "FAILED\n");
+		else
+			fprintf(stdout, "%s\n", result[ret]);
+	}
+
+	if (test->get_irqtype) {
+		ret = ioctl(fd, PCITEST_GET_IRQTYPE);
+		fprintf(stdout, "GET IRQ TYPE:\t\t");
+		if (ret < 0)
+			fprintf(stdout, "FAILED\n");
+		else
+			fprintf(stdout, "%s\n", irq[ret]);
+	}
+
 	if (test->legacyirq) {
 		ret = ioctl(fd, PCITEST_LEGACY_IRQ, 0);
 		fprintf(stdout, "LEGACY IRQ:\t");
@@ -83,6 +106,15 @@ static int run_test(struct pci_test *test)
 			fprintf(stdout, "%s\n", result[ret]);
 	}
 
+	if (test->msixnum > 0 && test->msixnum <= 2048) {
+		ret = ioctl(fd, PCITEST_MSIX, test->msixnum);
+		fprintf(stdout, "MSI-X%d:\t\t", test->msixnum);
+		if (ret < 0)
+			fprintf(stdout, "TEST FAILED\n");
+		else
+			fprintf(stdout, "%s\n", result[ret]);
+	}
+
 	if (test->write) {
 		ret = ioctl(fd, PCITEST_WRITE, test->size);
 		fprintf(stdout, "WRITE (%7ld bytes):\t\t", test->size);
@@ -133,7 +165,7 @@ int main(int argc, char **argv)
 	/* set default endpoint device */
 	test->device = "/dev/pci-endpoint-test.0";
 
-	while ((c = getopt(argc, argv, "D:b:m:lrwcs:")) != EOF)
+	while ((c = getopt(argc, argv, "D:b:m:x:i:Ilrwcs:")) != EOF)
 	switch (c) {
 	case 'D':
 		test->device = optarg;
@@ -151,6 +183,20 @@ int main(int argc, char **argv)
 		if (test->msinum < 1 || test->msinum > 32)
 			goto usage;
 		continue;
+	case 'x':
+		test->msixnum = atoi(optarg);
+		if (test->msixnum < 1 || test->msixnum > 2048)
+			goto usage;
+		continue;
+	case 'i':
+		test->irqtype = atoi(optarg);
+		if (test->irqtype < 0 || test->irqtype > 2)
+			goto usage;
+		test->set_irqtype = true;
+		continue;
+	case 'I':
+		test->get_irqtype = true;
+		continue;
 	case 'r':
 		test->read = true;
 		continue;
@@ -173,6 +219,9 @@ usage:
 			"\t-D <dev>		PCI endpoint test device {default: /dev/pci-endpoint-test.0}\n"
 			"\t-b <bar num>		BAR test (bar number between 0..5)\n"
 			"\t-m <msi num>		MSI test (msi number between 1..32)\n"
+			"\t-x <msix num>	\tMSI-X test (msix number between 1..2048)\n"
+			"\t-i <irq type>	\tSet IRQ type (0 - Legacy, 1 - MSI, 2 - MSI-X)\n"
+			"\t-I			Get current IRQ type configured\n"
 			"\t-l			Legacy IRQ test\n"
 			"\t-r			Read buffer test\n"
 			"\t-w			Write buffer test\n"
diff --git a/tools/pci/pcitest.sh b/tools/pci/pcitest.sh
index 77e8c85ef744..75ed48ff2990 100644
--- a/tools/pci/pcitest.sh
+++ b/tools/pci/pcitest.sh
@@ -16,7 +16,10 @@ echo
 echo "Interrupt tests"
 echo
 
+pcitest -i 0
 pcitest -l
+
+pcitest -i 1
 msi=1
 
 while [ $msi -lt 33 ]
@@ -26,9 +29,21 @@ do
 done
 echo
 
+pcitest -i 2
+msix=1
+
+while [ $msix -lt 2049 ]
+do
+        pcitest -x $msix
+        msix=`expr $msix + 1`
+done
+echo
+
 echo "Read Tests"
 echo
 
+pcitest -i 1
+
 pcitest -r -s 1
 pcitest -r -s 1024
 pcitest -r -s 1025
-- 
cgit v1.2.3


From 15c972dfb3954569e7d17ebadf1b10d0a0c3baa3 Mon Sep 17 00:00:00 2001
From: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Date: Thu, 19 Jul 2018 10:32:22 +0200
Subject: PCI: endpoint: Add MSI set maximum restriction

Add pci_epc_set_msi() maximum 32 interrupts validation.

Signed-off-by: Gustavo Pimentel <gustavo.pimentel@synopsys.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Acked-by: Kishon Vijay Abraham I <kishon@ti.com>
---
 drivers/pci/endpoint/pci-epc-core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index c72e656e7e29..094dcc3203b8 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -201,7 +201,8 @@ int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 interrupts)
 	u8 encode_int;
 	unsigned long flags;
 
-	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions)
+	if (IS_ERR_OR_NULL(epc) || func_no >= epc->max_functions ||
+	    interrupts > 32)
 		return -EINVAL;
 
 	if (!epc->ops->set_msi)
-- 
cgit v1.2.3


From eea033d07543a177fc2ab35a6d633b2aa9684b0f Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 18 Jul 2018 14:51:59 -0700
Subject: cpufreq: intel_pstate: Show different max frequency with turbo 3 and
 HWP

On HWP platforms with Turbo 3.0, the HWP capability max ratio shows the
maximum ratio of that core, which can be different than other cores. If
we show the correct maximum frequency in cpufreq sysfs via
cpuinfo_max_freq and scaling_max_freq then, user can know which cores
can run faster for pinning some high priority tasks.

Currently the max turbo frequency is shown as max frequency, which is
the max of all cores, even if some cores can't reach that frequency
even for single threaded workload.

But it is possible that max ratio in HWP capabilities is set as 0xFF or
some high invalid value (E.g. One KBL NUC). Since the actual performance
can never exceed 1 core turbo frequency from MSR TURBO_RATIO_LIMIT, we
use this as a bound check.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index a5c368425e36..2584dd00e3c9 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2069,6 +2069,15 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
 
+	if (hwp_active) {
+		unsigned int max_freq;
+
+		max_freq = global.turbo_disabled ?
+			cpu->pstate.max_freq : cpu->pstate.turbo_freq;
+		if (max_freq < policy->cpuinfo.max_freq)
+			policy->cpuinfo.max_freq = max_freq;
+	}
+
 	intel_pstate_init_acpi_perf_limits(policy);
 
 	policy->fast_switch_possible = true;
-- 
cgit v1.2.3


From 46b1063f91e5680eff2a6b9fe432f6aae3bef54e Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Jul 2018 08:22:06 +0100
Subject: drm/i915: Handle recursive shrinker for vma->last_active allocation

If we call into the shrinker for direct relcaim inside kmalloc, it will
retire the requests. If we retire the vma->last_active while processing a
new i915_vma_move_to_active() we can upset the delicate bookkeeping
required for the cache. After the possible invocation of the shrinker, we
need to double check the vma->last_active is still valid.

Fixes: 8b293eb53a7d ("drm/i915: Track the last-active inside the i915_vma")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105600#c39
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180719072206.16015-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/i915_vma.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index ed4e0fb558f7..11d834f94220 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -942,6 +942,14 @@ static struct i915_gem_active *active_instance(struct i915_vma *vma, u64 idx)
 	}
 
 	active = kmalloc(sizeof(*active), GFP_KERNEL);
+
+	/* kmalloc may retire the vma->last_active request (thanks shrinker)! */
+	if (unlikely(!i915_gem_active_raw(&vma->last_active,
+					  &vma->vm->i915->drm.struct_mutex))) {
+		kfree(active);
+		goto out;
+	}
+
 	if (unlikely(!active))
 		return ERR_PTR(-ENOMEM);
 
-- 
cgit v1.2.3


From d78d3343dce7787a5f7fd0b3d522a3510fd26ef9 Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 19 Jul 2018 08:50:29 +0100
Subject: drm/i915/execlists: Move the assertion we have the rpm wakeref down

There's a race between idling the engine and finishing off the last
tasklet (as we may kick the tasklets after declaring an individual
engine idle). However, since we do not need to access the device until
we try to submit to the ELSP register (processing the CSB just requires
normal CPU access to the HWSP, and when idle we should not need to
submit!) we can defer the assertion unto that point. The assertion is
still useful as it does verify that we do hold the longterm GT wakeref
taken from request allocation until request completion.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107274
Fixes: 9512f985c32d ("drm/i915/execlists: Direct submission of new requests (avoid tasklet/ksoftirqd)")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180719075029.28643-1-chris@chris-wilson.co.uk
---
 drivers/gpu/drm/i915/intel_lrc.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c64ed9090e29..174479232e94 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -452,6 +452,16 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 	struct execlist_port *port = execlists->port;
 	unsigned int n;
 
+	/*
+	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
+	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
+	 * not be relinquished until the device is idle (see
+	 * i915_gem_idle_work_handler()). As a precaution, we make sure
+	 * that all ELSP are drained i.e. we have processed the CSB,
+	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
+	 */
+	GEM_BUG_ON(!engine->i915->gt.awake);
+
 	/*
 	 * ELSQ note: the submit queue is not cleared after being submitted
 	 * to the HW so we need to make sure we always clean it up. This is
@@ -1043,16 +1053,6 @@ static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
 {
 	lockdep_assert_held(&engine->timeline.lock);
 
-	/*
-	 * We can skip acquiring intel_runtime_pm_get() here as it was taken
-	 * on our behalf by the request (see i915_gem_mark_busy()) and it will
-	 * not be relinquished until the device is idle (see
-	 * i915_gem_idle_work_handler()). As a precaution, we make sure
-	 * that all ELSP are drained i.e. we have processed the CSB,
-	 * before allowing ourselves to idle and calling intel_runtime_pm_put().
-	 */
-	GEM_BUG_ON(!engine->i915->gt.awake);
-
 	process_csb(engine);
 	if (!execlists_is_active(&engine->execlists, EXECLISTS_ACTIVE_PREEMPT))
 		execlists_dequeue(engine);
@@ -1073,10 +1073,7 @@ static void execlists_submission_tasklet(unsigned long data)
 		  engine->execlists.active);
 
 	spin_lock_irqsave(&engine->timeline.lock, flags);
-
-	if (engine->i915->gt.awake) /* we may be delayed until after we idle! */
-		__execlists_submission_tasklet(engine);
-
+	__execlists_submission_tasklet(engine);
 	spin_unlock_irqrestore(&engine->timeline.lock, flags);
 }
 
-- 
cgit v1.2.3


From 868e49a4a00afaca07d2c450a02e49581eaece6c Mon Sep 17 00:00:00 2001
From: Stuart Henderson <stuarth@opensource.cirrus.com>
Date: Thu, 19 Jul 2018 11:50:37 +0100
Subject: ASoC: wm_adsp: Ensure DSP boot work complete before preloader_put
 return

All controls derived from the loaded firmware should be created prior
to returning from the preloader's put function, such that they are
immediately available to user-space.

Signed-off-by: Stuart Henderson <stuarth@opensource.cirrus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index b7b914963c62..4e7f8525449e 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -2672,6 +2672,8 @@ int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 
 	snd_soc_dapm_sync(dapm);
 
+	flush_work(&dsp->boot_work);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_preloader_put);
-- 
cgit v1.2.3


From 517ee74e1b3124b696f293aa4e220418f8125b4c Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Thu, 19 Jul 2018 11:50:35 +0100
Subject: ASoC: wm_adsp: Correct algorithm list allocation size

Commit 6396bb221514 ("treewide: kzalloc() -> kcalloc()") was
overlooked when doing some refactoring to the algorithm list
handling, which lead to twice as much buffer being allocated
as required for reading the algorithm list. A kcalloc is no
longer appropriate since the allocation size is now in bytes
not registers, as such change back to kzalloc.

Fixes: 7f7cca08abf4 ("ASoC: wm_adsp: Simplify handling of alg offset and length")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 07c17acc8a4f..99108d18de8d 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1906,7 +1906,7 @@ static void *wm_adsp_read_algs(struct wm_adsp *dsp, size_t n_algs,
 	/* Convert length from DSP words to bytes */
 	len *= sizeof(u32);
 
-	alg = kcalloc(len, 2, GFP_KERNEL | GFP_DMA);
+	alg = kzalloc(len, GFP_KERNEL | GFP_DMA);
 	if (!alg)
 		return ERR_PTR(-ENOMEM);
 
-- 
cgit v1.2.3


From b7ede5af62ab6bfad0980fad58e82d3fb56866df Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Thu, 19 Jul 2018 11:50:36 +0100
Subject: ASoC: wm_adsp: Take prefix into account in control name length

Currently when creating ALSA control names for the DSP the length of any
prefix applied to the CODEC is not taken into account. Whilst this is
mostly harmless it does result in ALSA doing the truncation of the
control names and printing a warning. It is better to have the driver do
the truncation so it can truncate from the start of parameter name
itself to give a greater chance of the result maintain a unique name.

Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 99108d18de8d..eec73c98a141 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1343,6 +1343,9 @@ static int wm_adsp_create_control(struct wm_adsp *dsp,
 			int avail = SNDRV_CTL_ELEM_ID_NAME_MAXLEN - ret - 2;
 			int skip = 0;
 
+			if (dsp->component->name_prefix)
+				avail -= strlen(dsp->component->name_prefix) + 1;
+
 			if (subname_len > avail)
 				skip = subname_len - avail;
 
-- 
cgit v1.2.3


From 3bbc2705a3d132b9a86a0e4083f82a2b3c9bfdfd Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 19 Jul 2018 11:50:38 +0100
Subject: ASoC: wm_adsp: Allow up to 8 channels for voice control

Newer voice control firmwares can capture multiple audio channels.
Allow up to 8 channels for future-proofing.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index eec73c98a141..aeb1b8c27670 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -418,7 +418,7 @@ static const struct wm_adsp_fw_caps ctrl_caps[] = {
 	{
 		.id = SND_AUDIOCODEC_BESPOKE,
 		.desc = {
-			.max_ch = 1,
+			.max_ch = 8,
 			.sample_rates = { 16000 },
 			.num_sample_rates = 1,
 			.formats = SNDRV_PCM_FMTBIT_S16_LE,
-- 
cgit v1.2.3


From d52ed4b0bc73c1c7816f5b7a36229a95acfc76c8 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Thu, 19 Jul 2018 11:50:39 +0100
Subject: ASoC: wm_adsp: Parse HOST_BUFFER controls

Currently the compressed streams in DSP firmwares are
identified essentially by looking at a fixed location inside
the firmware. This is fragile and also limits things to a
single compressed stream.

Here a new form of firmware parameter is added, the HOST_BUFFER
which identifies a compressed stream from meta-data in the
firmware file. This is more robust and allows for the possiblity
of using multiple streams per core in the future. Currently the
implementation is still limited to a single stream and will
use the first HOST_BUFFER parameter encountered. If there aren't
any HOST_BUFFER parameters it will fall back to the legacy way
of finding the host buffer.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 66 +++++++++++++++++++++++++++++++++++++++++++++-
 sound/soc/codecs/wmfw.h    |  1 +
 2 files changed, 66 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index aeb1b8c27670..e39b0e0b04df 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -1607,6 +1607,15 @@ static int wm_adsp_parse_coeff(struct wm_adsp *dsp,
 			if (ret)
 				return -EINVAL;
 			break;
+		case WMFW_CTL_TYPE_HOST_BUFFER:
+			ret = wm_adsp_check_coeff_flags(dsp, &coeff_blk,
+						WMFW_CTL_FLAG_SYS |
+						WMFW_CTL_FLAG_VOLATILE |
+						WMFW_CTL_FLAG_READABLE,
+						0);
+			if (ret)
+				return -EINVAL;
+			break;
 		default:
 			adsp_err(dsp, "Unknown control type: %d\n",
 				 coeff_blk.ctl_type);
@@ -3200,7 +3209,7 @@ static inline int wm_adsp_buffer_write(struct wm_adsp_compr_buf *buf,
 				       buf->host_buf_ptr + field_offset, data);
 }
 
-static int wm_adsp_buffer_locate(struct wm_adsp_compr_buf *buf)
+static int wm_adsp_legacy_host_buf_addr(struct wm_adsp_compr_buf *buf)
 {
 	struct wm_adsp_alg_region *alg_region;
 	struct wm_adsp *dsp = buf->dsp;
@@ -3239,6 +3248,61 @@ static int wm_adsp_buffer_locate(struct wm_adsp_compr_buf *buf)
 	return 0;
 }
 
+static struct wm_coeff_ctl *
+wm_adsp_find_host_buffer_ctrl(struct wm_adsp_compr_buf *buf)
+{
+	struct wm_adsp *dsp = buf->dsp;
+	struct wm_coeff_ctl *ctl;
+
+	list_for_each_entry(ctl, &dsp->ctl_list, list) {
+		if (ctl->type != WMFW_CTL_TYPE_HOST_BUFFER)
+			continue;
+
+		if (!ctl->enabled)
+			continue;
+
+		return ctl;
+	}
+
+	return NULL;
+}
+
+static int wm_adsp_buffer_locate(struct wm_adsp_compr_buf *buf)
+{
+	struct wm_adsp *dsp = buf->dsp;
+	struct wm_coeff_ctl *ctl;
+	unsigned int reg;
+	u32 val;
+	int i, ret;
+
+	ctl = wm_adsp_find_host_buffer_ctrl(buf);
+	if (!ctl)
+		return wm_adsp_legacy_host_buf_addr(buf);
+
+	ret = wm_coeff_base_reg(ctl, &reg);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < 5; ++i) {
+		ret = regmap_raw_read(dsp->regmap, reg, &val, sizeof(val));
+		if (ret < 0)
+			return ret;
+
+		if (val)
+			break;
+
+		usleep_range(1000, 2000);
+	}
+
+	if (!val)
+		return -EIO;
+
+	buf->host_buf_ptr = be32_to_cpu(val);
+	adsp_dbg(dsp, "host_buf_ptr=%x\n", buf->host_buf_ptr);
+
+	return 0;
+}
+
 static int wm_adsp_buffer_populate(struct wm_adsp_compr_buf *buf)
 {
 	const struct wm_adsp_fw_caps *caps = wm_adsp_fw[buf->dsp->fw].caps;
diff --git a/sound/soc/codecs/wmfw.h b/sound/soc/codecs/wmfw.h
index ec78b9da020f..0c3f50acb8b1 100644
--- a/sound/soc/codecs/wmfw.h
+++ b/sound/soc/codecs/wmfw.h
@@ -29,6 +29,7 @@
 /* Non-ALSA coefficient types start at 0x1000 */
 #define WMFW_CTL_TYPE_ACKED       0x1000 /* acked control */
 #define WMFW_CTL_TYPE_HOSTEVENT   0x1001 /* event control */
+#define WMFW_CTL_TYPE_HOST_BUFFER 0x1002 /* host buffer pointer */
 
 struct wmfw_header {
 	char magic[4];
-- 
cgit v1.2.3


From 054732837c312c6007994badbc86b0976b228f77 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Thu, 19 Jul 2018 10:27:33 +0200
Subject: s390/keyboard: sanitize array index in do_kdsk_ioctl

The kbd_ioctl uses two user controlled indexes for KDGKBENT/KDSKBENT.
Use array_index_nospec to prevent any out of bounds speculation.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/char/keyboard.c | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/s390/char/keyboard.c b/drivers/s390/char/keyboard.c
index 79eb60958015..bbb3001b0961 100644
--- a/drivers/s390/char/keyboard.c
+++ b/drivers/s390/char/keyboard.c
@@ -334,37 +334,41 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 	      int cmd, int perm)
 {
 	struct kbentry tmp;
+	unsigned long kb_index, kb_table;
 	ushort *key_map, val, ov;
 
 	if (copy_from_user(&tmp, user_kbe, sizeof(struct kbentry)))
 		return -EFAULT;
+	kb_index = (unsigned long) tmp.kb_index;
 #if NR_KEYS < 256
-	if (tmp.kb_index >= NR_KEYS)
+	if (kb_index >= NR_KEYS)
 		return -EINVAL;
 #endif
+	kb_table = (unsigned long) tmp.kb_table;
 #if MAX_NR_KEYMAPS < 256
-	if (tmp.kb_table >= MAX_NR_KEYMAPS)
+	if (kb_table >= MAX_NR_KEYMAPS)
 		return -EINVAL;	
+	kb_table = array_index_nospec(kb_table , MAX_NR_KEYMAPS);
 #endif
 
 	switch (cmd) {
 	case KDGKBENT:
-		key_map = kbd->key_maps[tmp.kb_table];
+		key_map = kbd->key_maps[kb_table];
 		if (key_map) {
-		    val = U(key_map[tmp.kb_index]);
+		    val = U(key_map[kb_index]);
 		    if (KTYP(val) >= KBD_NR_TYPES)
 			val = K_HOLE;
 		} else
-		    val = (tmp.kb_index ? K_HOLE : K_NOSUCHMAP);
+		    val = (kb_index ? K_HOLE : K_NOSUCHMAP);
 		return put_user(val, &user_kbe->kb_value);
 	case KDSKBENT:
 		if (!perm)
 			return -EPERM;
-		if (!tmp.kb_index && tmp.kb_value == K_NOSUCHMAP) {
+		if (!kb_index && tmp.kb_value == K_NOSUCHMAP) {
 			/* disallocate map */
-			key_map = kbd->key_maps[tmp.kb_table];
+			key_map = kbd->key_maps[kb_table];
 			if (key_map) {
-			    kbd->key_maps[tmp.kb_table] = NULL;
+			    kbd->key_maps[kb_table] = NULL;
 			    kfree(key_map);
 			}
 			break;
@@ -375,18 +379,18 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (KVAL(tmp.kb_value) > kbd_max_vals[KTYP(tmp.kb_value)])
 			return -EINVAL;
 
-		if (!(key_map = kbd->key_maps[tmp.kb_table])) {
+		if (!(key_map = kbd->key_maps[kb_table])) {
 			int j;
 
 			key_map = kmalloc(sizeof(plain_map),
 						     GFP_KERNEL);
 			if (!key_map)
 				return -ENOMEM;
-			kbd->key_maps[tmp.kb_table] = key_map;
+			kbd->key_maps[kb_table] = key_map;
 			for (j = 0; j < NR_KEYS; j++)
 				key_map[j] = U(K_HOLE);
 		}
-		ov = U(key_map[tmp.kb_index]);
+		ov = U(key_map[kb_index]);
 		if (tmp.kb_value == ov)
 			break;	/* nothing to do */
 		/*
@@ -395,7 +399,7 @@ do_kdsk_ioctl(struct kbd_data *kbd, struct kbentry __user *user_kbe,
 		if (((ov == K_SAK) || (tmp.kb_value == K_SAK)) &&
 		    !capable(CAP_SYS_ADMIN))
 			return -EPERM;
-		key_map[tmp.kb_index] = U(tmp.kb_value);
+		key_map[kb_index] = U(tmp.kb_value);
 		break;
 	}
 	return 0;
-- 
cgit v1.2.3


From 9c705206d0b5f834650c379d6cfbd07a597a0a1e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 23:42:05 -0500
Subject: s390/ap_bus: replace PTR_RET with PTR_ERR_OR_ZERO

PTR_RET is deprecated, use PTR_ERR_OR_ZERO instead.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/crypto/ap_bus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
index c0a6723be54b..bf27fc4d1335 100644
--- a/drivers/s390/crypto/ap_bus.c
+++ b/drivers/s390/crypto/ap_bus.c
@@ -474,7 +474,7 @@ static int ap_poll_thread_start(void)
 		return 0;
 	mutex_lock(&ap_poll_thread_mutex);
 	ap_poll_kthread = kthread_run(ap_poll_thread, NULL, "appoll");
-	rc = PTR_RET(ap_poll_kthread);
+	rc = PTR_ERR_OR_ZERO(ap_poll_kthread);
 	if (rc)
 		ap_poll_kthread = NULL;
 	mutex_unlock(&ap_poll_thread_mutex);
@@ -1242,7 +1242,7 @@ static int __init ap_module_init(void)
 
 	/* Create /sys/devices/ap. */
 	ap_root_device = root_device_register("ap");
-	rc = PTR_RET(ap_root_device);
+	rc = PTR_ERR_OR_ZERO(ap_root_device);
 	if (rc)
 		goto out_bus;
 
-- 
cgit v1.2.3


From 757853ea19755c24609e122268145527b541a4d4 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 23:50:50 -0500
Subject: s390/dasd: replace PTR_RET with PTR_ERR_OR_ZERO

PTR_RET is deprecated, use PTR_ERR_OR_ZERO instead.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/dasd_eckd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index bbf95b78ef5d..c5a55513b07c 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -3535,7 +3535,7 @@ static int prepare_itcw(struct itcw *itcw,
 
 	dcw = itcw_add_dcw(itcw, pfx_cmd, 0,
 		     &pfxdata, sizeof(pfxdata), total_data_size);
-	return PTR_RET(dcw);
+	return PTR_ERR_OR_ZERO(dcw);
 }
 
 static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
-- 
cgit v1.2.3


From 9fa6a659ca98c45a5c226d165adfed96a1e01564 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 19 Jul 2018 00:08:30 -0500
Subject: s390/hypfs: Replace PTR_RET with PTR_ERR_OR_ZERO

PTR_RET is deprecated, use PTR_ERR_OR_ZERO instead.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/hypfs/hypfs_diag.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/s390/hypfs/hypfs_diag.c b/arch/s390/hypfs/hypfs_diag.c
index a2945b289a29..3452e18bb1ca 100644
--- a/arch/s390/hypfs/hypfs_diag.c
+++ b/arch/s390/hypfs/hypfs_diag.c
@@ -497,7 +497,7 @@ static int hypfs_create_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 	}
 	diag224_idx2name(cpu_info__ctidx(diag204_info_type, cpu_info), buffer);
 	rc = hypfs_create_str(cpu_dir, "type", buffer);
-	return PTR_RET(rc);
+	return PTR_ERR_OR_ZERO(rc);
 }
 
 static void *hypfs_create_lpar_files(struct dentry *systems_dir, void *part_hdr)
@@ -544,7 +544,7 @@ static int hypfs_create_phys_cpu_files(struct dentry *cpus_dir, void *cpu_info)
 		return PTR_ERR(rc);
 	diag224_idx2name(phys_cpu__ctidx(diag204_info_type, cpu_info), buffer);
 	rc = hypfs_create_str(cpu_dir, "type", buffer);
-	return PTR_RET(rc);
+	return PTR_ERR_OR_ZERO(rc);
 }
 
 static void *hypfs_create_phys_files(struct dentry *parent_dir, void *phys_hdr)
-- 
cgit v1.2.3


From cd0ed39dc9e8b10d469f53ae03310bca09296bdd Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 23:46:53 -0500
Subject: s390/tape: replace PTR_RET with PTR_ERR_OR_ZERO

PTR_RET is deprecated, use PTR_ERR_OR_ZERO instead.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/char/tape_class.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/s390/char/tape_class.c b/drivers/s390/char/tape_class.c
index e403edf92e00..b58df0dd0039 100644
--- a/drivers/s390/char/tape_class.c
+++ b/drivers/s390/char/tape_class.c
@@ -77,7 +77,7 @@ struct tape_class_device *register_tape_dev(
 	tcd->class_device = device_create(tape_class, device,
 					  tcd->char_device->dev, NULL,
 					  "%s", tcd->device_name);
-	rc = PTR_RET(tcd->class_device);
+	rc = PTR_ERR_OR_ZERO(tcd->class_device);
 	if (rc)
 		goto fail_with_cdev;
 	rc = sysfs_create_link(
-- 
cgit v1.2.3


From 8e974b3b8eddd42a8c43a18e8ea66a3e7b803a0d Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 19 Jul 2018 23:07:58 +0900
Subject: x86: Avoid pr_cont() in show_opcodes()

If concurrent printk() messages are emitted, then pr_cont() is making it
extremly hard to decode which part of the output belongs to what. See the
convoluted example at:

  https://syzkaller.appspot.com/text?tag=CrashReport&x=139d342c400000

Avoid this by using a proper prefix for each line and by using %ph format
in show_opcodes() which emits the 'Code:' line in one go.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: joe@perches.com
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@suse.de>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/1532009278-5953-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp
---
 arch/x86/kernel/dumpstack.c | 28 +++++++++-------------------
 1 file changed, 9 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index 666a284116ac..9c8652974f8e 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -22,8 +22,6 @@
 #include <asm/stacktrace.h>
 #include <asm/unwind.h>
 
-#define OPCODE_BUFSIZE 64
-
 int panic_on_unrecovered_nmi;
 int panic_on_io_nmi;
 static int die_counter;
@@ -93,26 +91,18 @@ static void printk_stack_address(unsigned long address, int reliable,
  */
 void show_opcodes(u8 *rip, const char *loglvl)
 {
-	unsigned int code_prologue = OPCODE_BUFSIZE * 2 / 3;
+#define PROLOGUE_SIZE 42
+#define EPILOGUE_SIZE 21
+#define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
-	u8 *ip;
-	int i;
-
-	printk("%sCode: ", loglvl);
-
-	ip = (u8 *)rip - code_prologue;
-	if (probe_kernel_read(opcodes, ip, OPCODE_BUFSIZE)) {
-		pr_cont("Bad RIP value.\n");
-		return;
-	}
 
-	for (i = 0; i < OPCODE_BUFSIZE; i++, ip++) {
-		if (ip == rip)
-			pr_cont("<%02x> ", opcodes[i]);
-		else
-			pr_cont("%02x ", opcodes[i]);
+	if (probe_kernel_read(opcodes, rip - PROLOGUE_SIZE, OPCODE_BUFSIZE)) {
+		printk("%sCode: Bad RIP value.\n", loglvl);
+	} else {
+		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
+		       __stringify(EPILOGUE_SIZE) "ph\n", loglvl, opcodes,
+		       opcodes[PROLOGUE_SIZE], opcodes + PROLOGUE_SIZE + 1);
 	}
-	pr_cont("\n");
 }
 
 void show_ip(struct pt_regs *regs, const char *loglvl)
-- 
cgit v1.2.3


From 30587589251a00974115e0815ac316980f48dbb5 Mon Sep 17 00:00:00 2001
From: Yi Wang <wang.yi59@zte.com.cn>
Date: Mon, 16 Jul 2018 14:08:57 +0800
Subject: timer: Fix coding style

The call to wake_up_nohz_cpu() is incorrectly indented. Remove the surplus TAB.

Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn>
Cc: john.stultz@linaro.org
Cc: sboyd@kernel.org
Cc: zhong.weidong@zte.com.cn
CC: Anna-Maria Gleixner <anna-maria@linutronix.de>
Link: https://lkml.kernel.org/r/1531721337-30284-1-git-send-email-wang.yi59@zte.com.cn
---
 kernel/time/timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index cc2d23e6ff61..baa528a24a73 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -581,7 +581,7 @@ trigger_dyntick_cpu(struct timer_base *base, struct timer_list *timer)
 	 * wheel:
 	 */
 	base->next_expiry = timer->expires;
-		wake_up_nohz_cpu(base->cpu);
+	wake_up_nohz_cpu(base->cpu);
 }
 
 static void
-- 
cgit v1.2.3


From eea1662525bd4a158a67ac836b2a1fd9cf77cc81 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 18 Jul 2018 22:55:37 +0200
Subject: ASoC: rt5651: Add IN3 Boost volume control

Add a mixer control for the IN3 Boost volume, IN3 is used for the headset
mic on most devices, so this is necessary to control the headset mic
volume.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5651.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/rt5651.c b/sound/soc/codecs/rt5651.c
index 0462049e739c..985852fd9723 100644
--- a/sound/soc/codecs/rt5651.c
+++ b/sound/soc/codecs/rt5651.c
@@ -331,11 +331,13 @@ static const struct snd_kcontrol_new rt5651_snd_controls[] = {
 	SOC_DOUBLE_TLV("Mono DAC Playback Volume", RT5651_DAC2_DIG_VOL,
 			RT5651_L_VOL_SFT, RT5651_R_VOL_SFT,
 			175, 0, dac_vol_tlv),
-	/* IN1/IN2 Control */
+	/* IN1/IN2/IN3 Control */
 	SOC_SINGLE_TLV("IN1 Boost", RT5651_IN1_IN2,
 		RT5651_BST_SFT1, 8, 0, bst_tlv),
 	SOC_SINGLE_TLV("IN2 Boost", RT5651_IN1_IN2,
 		RT5651_BST_SFT2, 8, 0, bst_tlv),
+	SOC_SINGLE_TLV("IN3 Boost", RT5651_IN3,
+		RT5651_BST_SFT1, 8, 0, bst_tlv),
 	/* INL/INR Volume Control */
 	SOC_DOUBLE_TLV("IN Capture Volume", RT5651_INL1_INR1_VOL,
 			RT5651_INL_VOL_SFT, RT5651_INR_VOL_SFT,
-- 
cgit v1.2.3


From 0a3badd141f78535315cca9ff5062a7ebf414281 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 18 Jul 2018 22:55:38 +0200
Subject: ASoC: Intel: bytcr_rt5651: Fix using the wrong GPIO for the ext-amp
 on some boards

Some boards have I2cSerialBusV2, GpioIo, GpioInt as ACPI resources, other
boards may  have I2cSerialBusV2, GpioInt, GpioIo instead. We want the
GpioIo one for the ext-amp-enable-gpio.

So far we've been assuming that the GpioIo one always comes first, this
commit adds code to detect which one comes first and to add the right
gpio-mapping.

This fixes sound not working on the Vios LTH17 laptop.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 69 +++++++++++++++++++++++++++++++++--
 1 file changed, 65 insertions(+), 4 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index b687043c8425..601e47c33ba8 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -747,13 +747,74 @@ static const struct x86_cpu_id cherrytrail_cpu_ids[] = {
 	{}
 };
 
-static const struct acpi_gpio_params ext_amp_enable_gpios = { 0, 0, false };
+static const struct acpi_gpio_params first_gpio = { 0, 0, false };
+static const struct acpi_gpio_params second_gpio = { 1, 0, false };
 
-static const struct acpi_gpio_mapping byt_rt5651_gpios[] = {
-	{ "ext-amp-enable-gpios", &ext_amp_enable_gpios, 1 },
+static const struct acpi_gpio_mapping byt_rt5651_amp_en_first[] = {
+	{ "ext-amp-enable-gpios", &first_gpio, 1 },
 	{ },
 };
 
+static const struct acpi_gpio_mapping byt_rt5651_amp_en_second[] = {
+	{ "ext-amp-enable-gpios", &second_gpio, 1 },
+	{ },
+};
+
+/*
+ * Some boards have I2cSerialBusV2, GpioIo, GpioInt as ACPI resources, other
+ * boards may  have I2cSerialBusV2, GpioInt, GpioIo instead. We want the
+ * GpioIo one for the ext-amp-enable-gpio and both count for the index in
+ * acpi_gpio_params index.  So we have 2 different mappings and the code
+ * below figures out which one to use.
+ */
+struct byt_rt5651_acpi_resource_data {
+	int gpio_count;
+	int gpio_int_idx;
+};
+
+static int snd_byt_rt5651_acpi_resource(struct acpi_resource *ares, void *arg)
+{
+	struct byt_rt5651_acpi_resource_data *data = arg;
+
+	if (ares->type != ACPI_RESOURCE_TYPE_GPIO)
+		return 0;
+
+	if (ares->data.gpio.connection_type == ACPI_RESOURCE_GPIO_TYPE_INT)
+		data->gpio_int_idx = data->gpio_count;
+
+	data->gpio_count++;
+	return 0;
+}
+
+static void snd_byt_rt5651_mc_add_amp_en_gpio_mapping(struct device *codec)
+{
+	struct byt_rt5651_acpi_resource_data data = { 0, -1 };
+	LIST_HEAD(resources);
+	int ret;
+
+	ret = acpi_dev_get_resources(ACPI_COMPANION(codec), &resources,
+				     snd_byt_rt5651_acpi_resource, &data);
+	if (ret < 0) {
+		dev_warn(codec, "Failed to get ACPI resources, not adding external amplifier GPIO mapping\n");
+		return;
+	}
+
+	/* All info we need is gathered during the walk */
+	acpi_dev_free_resource_list(&resources);
+
+	switch (data.gpio_int_idx) {
+	case 0:
+		devm_acpi_dev_add_driver_gpios(codec, byt_rt5651_amp_en_second);
+		break;
+	case 1:
+		devm_acpi_dev_add_driver_gpios(codec, byt_rt5651_amp_en_first);
+		break;
+	default:
+		dev_warn(codec, "Unknown GpioInt index %d, not adding external amplifier GPIO mapping\n",
+			 data.gpio_int_idx);
+	}
+}
+
 struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 	u64 aif_value;       /* 1: AIF1, 2: AIF2 */
 	u64 mclock_value;    /* usually 25MHz (0x17d7940), ignored */
@@ -876,7 +937,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 
 	/* Cherry Trail devices use an external amplifier enable gpio */
 	if (x86_match_cpu(cherrytrail_cpu_ids)) {
-		devm_acpi_dev_add_driver_gpios(codec_dev, byt_rt5651_gpios);
+		snd_byt_rt5651_mc_add_amp_en_gpio_mapping(codec_dev);
 		priv->ext_amp_gpio = devm_fwnode_get_index_gpiod_from_child(
 						&pdev->dev, "ext-amp-enable", 0,
 						codec_dev->fwnode,
-- 
cgit v1.2.3


From 8627fb257e1673d2c2277494545642921097da86 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 18 Jul 2018 22:55:39 +0200
Subject: ASoC: Intel: bytcr_rt5651: Set OVCD limit for VIOS LTH17 to 2000uA

With the default over current detect limit of 1500uA headsets on often
get detected as headphones on the VIOS LTH17 and even when detected as
headset the OVCD current triggers often while plugged in, resulting in
false-positive button press detection.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 601e47c33ba8..53ac97c15fc6 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -414,8 +414,11 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_SYS_VENDOR, "VIOS"),
 			DMI_MATCH(DMI_PRODUCT_NAME, "LTH17"),
 		},
-		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_IN2_MAP),
+		.driver_data = (void *)(BYT_RT5651_IN1_IN2_MAP |
+					BYT_RT5651_JD1_1 |
+					BYT_RT5651_OVCD_TH_2000UA |
+					BYT_RT5651_OVCD_SF_1P0 |
+					BYT_RT5651_MCLK_EN),
 	},
 	{}
 };
-- 
cgit v1.2.3


From ac275ee5aa67abe9b65d66071ee333c6b0905b93 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 18 Jul 2018 22:55:40 +0200
Subject: ASoC: Intel: bytcr_rt5651: Add IN2 input mapping

During the recent cleanup series 3 of the 6 input mappings where removed
from the bytcr_rt5651 machine driver because testing showed that none of
them were used.

However some devices do actually have their internal mic on IN2 (and
only IN2, not IN1 and IN2), this did not show during previous tests
due to a bug in the userspace UCM input device switching code.

This commit re-adds the IN2 mapping for devices with the internal mic.
on IN2 and the headser mic on IN3 and enables this mapping on devices
with their internal mic on IN2.

This commit also changes the default internal mic input to IN2, because
all my 7 test devices have their mic there.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 53ac97c15fc6..d85530b1cc8e 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -44,6 +44,7 @@
 enum {
 	BYT_RT5651_DMIC_MAP,
 	BYT_RT5651_IN1_MAP,
+	BYT_RT5651_IN2_MAP,
 	BYT_RT5651_IN1_IN2_MAP,
 };
 
@@ -93,9 +94,9 @@ struct byt_rt5651_private {
 	struct snd_soc_jack jack;
 };
 
-/* Default: jack-detect on JD1_1, internal mic on in1, headsetmic on in3 */
+/* Default: jack-detect on JD1_1, internal mic on in2, headsetmic on in3 */
 static unsigned long byt_rt5651_quirk = BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_MAP;
+					BYT_RT5651_IN2_MAP;
 
 static void log_quirks(struct device *dev)
 {
@@ -103,6 +104,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk DMIC_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_MAP)
 		dev_info(dev, "quirk IN1_MAP enabled");
+	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN2_MAP)
+		dev_info(dev, "quirk IN2_MAP enabled");
 	if (BYT_RT5651_MAP(byt_rt5651_quirk) == BYT_RT5651_IN1_IN2_MAP)
 		dev_info(dev, "quirk IN1_IN2_MAP enabled");
 	if (BYT_RT5651_JDSRC(byt_rt5651_quirk)) {
@@ -270,6 +273,12 @@ static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_map[] = {
 	{"IN3P", NULL, "Headset Mic"},
 };
 
+static const struct snd_soc_dapm_route byt_rt5651_intmic_in2_map[] = {
+	{"Internal Mic", NULL, "micbias1"},
+	{"IN2P", NULL, "Internal Mic"},
+	{"IN3P", NULL, "Headset Mic"},
+};
+
 static const struct snd_soc_dapm_route byt_rt5651_intmic_in1_in2_map[] = {
 	{"Internal Mic", NULL, "micbias1"},
 	{"IN1P", NULL, "Internal Mic"},
@@ -364,7 +373,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "X1D3_C806N"),
 		},
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_MAP |
+					BYT_RT5651_IN2_MAP |
 					BYT_RT5651_HP_LR_SWAPPED),
 	},
 	{
@@ -375,7 +384,7 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "D2D3_Vi8A1"),
 		},
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
-					BYT_RT5651_IN1_MAP |
+					BYT_RT5651_IN2_MAP |
 					BYT_RT5651_HP_LR_SWAPPED),
 	},
 	{
@@ -468,6 +477,10 @@ static int byt_rt5651_init(struct snd_soc_pcm_runtime *runtime)
 		custom_map = byt_rt5651_intmic_in1_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_map);
 		break;
+	case BYT_RT5651_IN2_MAP:
+		custom_map = byt_rt5651_intmic_in2_map;
+		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in2_map);
+		break;
 	case BYT_RT5651_IN1_IN2_MAP:
 		custom_map = byt_rt5651_intmic_in1_in2_map;
 		num_routes = ARRAY_SIZE(byt_rt5651_intmic_in1_in2_map);
@@ -825,7 +838,7 @@ struct acpi_chan_package {   /* ACPICA seems to require 64 bit integers */
 
 static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 {
-	const char * const mic_name[] = { "dmic", "in1", "in12" };
+	const char * const mic_name[] = { "dmic", "in1", "in2", "in12" };
 	struct byt_rt5651_private *priv;
 	struct snd_soc_acpi_mach *mach;
 	struct device *codec_dev;
-- 
cgit v1.2.3


From a0d1d867c262f4ad5d8e4925e2212711ebdbf2b7 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 18 Jul 2018 22:55:41 +0200
Subject: ASoC: Intel: bytcr_rt5651: Add mono speaker quirk

During my initial round of bytcr_rt5651 long-name patches I did not include
a difference for mono vs stereo speaker setups in the longname because it
seems that all 5651 devices with only a single speaker do some mixing of
left + right on the PCB.

However further testing has shown that while this works great when only
playing audio on the left or right channel, the output becomes garbled
when using both channels at once. Something which does not happen when
using the Stereo DAC MIXL / MIXR switches to mix the channels together
inside the codec and then only outputting on a single channel.

So we need to have separate UCM profiles and thus separate long-names
for devices with a mono speaker vs stereo speakers. Just as we already
have for the bytcr_rt5640 case.

This commit adds a new BYT_RT5651_MONO_SPEAKER quirk and adds "stereo-spk"
or "mono-spk" to the long-name based on this and enables this mapping on
devices with a mono speaker.

Changing the long-name like this is ok for now, since I'm still working
on the UCM profiles, so they are not in upstream alsa-lib yet.

This brings the long-name naming scheme fully in sync with the bytcr_rt5640
case, which is good from a consistency pov.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index d85530b1cc8e..8374e633796d 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -79,6 +79,7 @@ enum {
 #define BYT_RT5651_SSP0_AIF1		BIT(20)
 #define BYT_RT5651_SSP0_AIF2		BIT(21)
 #define BYT_RT5651_HP_LR_SWAPPED	BIT(22)
+#define BYT_RT5651_MONO_SPEAKER		BIT(23)
 
 #define BYT_RT5651_DEFAULT_QUIRKS	(BYT_RT5651_MCLK_EN | \
 					 BYT_RT5651_JD1_1   | \
@@ -128,6 +129,8 @@ static void log_quirks(struct device *dev)
 		dev_info(dev, "quirk SSP0_AIF1 enabled\n");
 	if (byt_rt5651_quirk & BYT_RT5651_SSP0_AIF2)
 		dev_info(dev, "quirk SSP0_AIF2 enabled\n");
+	if (byt_rt5651_quirk & BYT_RT5651_MONO_SPEAKER)
+		dev_info(dev, "quirk MONO_SPEAKER enabled\n");
 }
 
 #define BYT_CODEC_DAI1	"rt5651-aif1"
@@ -374,7 +377,8 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 		},
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN2_MAP |
-					BYT_RT5651_HP_LR_SWAPPED),
+					BYT_RT5651_HP_LR_SWAPPED |
+					BYT_RT5651_MONO_SPEAKER),
 	},
 	{
 		/* Chuwi Vi8 Plus (CWI519) */
@@ -385,7 +389,8 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 		},
 		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
 					BYT_RT5651_IN2_MAP |
-					BYT_RT5651_HP_LR_SWAPPED),
+					BYT_RT5651_HP_LR_SWAPPED |
+					BYT_RT5651_MONO_SPEAKER),
 	},
 	{
 		/* KIANO SlimNote 14.2 */
@@ -700,7 +705,7 @@ static struct snd_soc_dai_link byt_rt5651_dais[] = {
 static char byt_rt5651_codec_name[SND_ACPI_I2C_ID_LEN];
 static char byt_rt5651_codec_aif_name[12]; /*  = "rt5651-aif[1|2]" */
 static char byt_rt5651_cpu_dai_name[10]; /*  = "ssp[0|2]-port" */
-static char byt_rt5651_long_name[40]; /* = "bytcr-rt5651-*-mic[-swapped-hp]" */
+static char byt_rt5651_long_name[50]; /* = "bytcr-rt5651-*-spk-*-mic[-swapped-hp]" */
 
 static int byt_rt5651_suspend(struct snd_soc_card *card)
 {
@@ -1025,7 +1030,9 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
 		hp_swapped = "";
 
 	snprintf(byt_rt5651_long_name, sizeof(byt_rt5651_long_name),
-		 "bytcr-rt5651-%s-mic%s",
+		 "bytcr-rt5651-%s-spk-%s-mic%s",
+		 (byt_rt5651_quirk & BYT_RT5651_MONO_SPEAKER) ?
+			"mono" : "stereo",
 		 mic_name[BYT_RT5651_MAP(byt_rt5651_quirk)], hp_swapped);
 	byt_rt5651_card.long_name = byt_rt5651_long_name;
 
-- 
cgit v1.2.3


From 06aa6e51273c9ac458af0bb9be95603cfbad14ec Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 18 Jul 2018 22:55:42 +0200
Subject: ASoC: Intel: bytcr_rt5651: Add quirk table entries for various
 devices

Add quirk table entries for the following tablets:

ITWorks TW701
Ployer Momo7w
Trekstor win7
Yours 8"

These all use the default settings, except that they only have a single
speaker and thus need the mono-speaker quirk.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5651.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
index 8374e633796d..f8a68bdb3885 100644
--- a/sound/soc/intel/boards/bytcr_rt5651.c
+++ b/sound/soc/intel/boards/bytcr_rt5651.c
@@ -392,6 +392,21 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 					BYT_RT5651_HP_LR_SWAPPED |
 					BYT_RT5651_MONO_SPEAKER),
 	},
+	{
+		/* I.T.Works TW701, Ployer Momo7w and Trekstor ST70416-6
+		 * (these all use the same mainboard) */
+		.callback = byt_rt5651_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_BIOS_VENDOR, "INSYDE Corp."),
+			/* Partial match for all of itWORKS.G.WI71C.JGBMRBA,
+			 * TREK.G.WI71C.JGBMRBA0x and MOMO.G.WI71C.MABMRBA02 */
+			DMI_MATCH(DMI_BIOS_VERSION, ".G.WI71C."),
+		},
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN2_MAP |
+					BYT_RT5651_SSP0_AIF1 |
+					BYT_RT5651_MONO_SPEAKER),
+	},
 	{
 		/* KIANO SlimNote 14.2 */
 		.callback = byt_rt5651_quirk_cb,
@@ -434,6 +449,19 @@ static const struct dmi_system_id byt_rt5651_quirk_table[] = {
 					BYT_RT5651_OVCD_SF_1P0 |
 					BYT_RT5651_MCLK_EN),
 	},
+	{
+		/* Yours Y8W81 (and others using the same mainboard) */
+		.callback = byt_rt5651_quirk_cb,
+		.matches = {
+			DMI_MATCH(DMI_BIOS_VENDOR, "INSYDE Corp."),
+			/* Partial match for all devs with a W86C mainboard */
+			DMI_MATCH(DMI_BIOS_VERSION, ".F.W86C."),
+		},
+		.driver_data = (void *)(BYT_RT5651_DEFAULT_QUIRKS |
+					BYT_RT5651_IN2_MAP |
+					BYT_RT5651_SSP0_AIF1 |
+					BYT_RT5651_MONO_SPEAKER),
+	},
 	{}
 };
 
-- 
cgit v1.2.3


From 6bdd0299cf76c38453c06b33cdb58636878aad0d Mon Sep 17 00:00:00 2001
From: Ludovic Barre <ludovic.barre@st.com>
Date: Tue, 17 Jul 2018 14:14:27 +0200
Subject: irqchip/stm32: Add exti0 translation for stm32mp1

This patch fixes a datasheet issue, in the draft version the "exti0"
was not connected whereas is it.

Signed-off-by: Ludovic Barre <ludovic.barre@st.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-stm32-exti.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/irqchip/irq-stm32-exti.c b/drivers/irqchip/irq-stm32-exti.c
index 3a7e8905a97e..3df527fcf4e1 100644
--- a/drivers/irqchip/irq-stm32-exti.c
+++ b/drivers/irqchip/irq-stm32-exti.c
@@ -159,6 +159,7 @@ static const struct stm32_exti_bank *stm32mp1_exti_banks[] = {
 };
 
 static const struct stm32_desc_irq stm32mp1_desc_irq[] = {
+	{ .exti = 0, .irq_parent = 6 },
 	{ .exti = 1, .irq_parent = 7 },
 	{ .exti = 2, .irq_parent = 8 },
 	{ .exti = 3, .irq_parent = 9 },
-- 
cgit v1.2.3


From 1047557cb9574a5be889bd45c1b4aa85209080e7 Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Fri, 13 Jul 2018 16:49:09 +0200
Subject: irqchip/ingenic: Add support for the JZ4725B SoC

The interrupt controller of the JZ4725B works the same way as the other
JZ SoCs from Ingenic; so we just add a new compatible string.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt | 1 +
 drivers/irqchip/irq-ingenic.c                                           | 1 +
 2 files changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
index 5f89fb635a1b..f97fd8ab5e45 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
@@ -4,6 +4,7 @@ Required properties:
 
 - compatible : should be "ingenic,<socname>-intc". Valid strings are:
     ingenic,jz4740-intc
+    ingenic,jz4725b-intc
     ingenic,jz4770-intc
     ingenic,jz4775-intc
     ingenic,jz4780-intc
diff --git a/drivers/irqchip/irq-ingenic.c b/drivers/irqchip/irq-ingenic.c
index fc5953dea509..2ff08986b536 100644
--- a/drivers/irqchip/irq-ingenic.c
+++ b/drivers/irqchip/irq-ingenic.c
@@ -165,6 +165,7 @@ static int __init intc_1chip_of_init(struct device_node *node,
 	return ingenic_intc_of_init(node, 1);
 }
 IRQCHIP_DECLARE(jz4740_intc, "ingenic,jz4740-intc", intc_1chip_of_init);
+IRQCHIP_DECLARE(jz4725b_intc, "ingenic,jz4725b-intc", intc_1chip_of_init);
 
 static int __init intc_2chip_of_init(struct device_node *node,
 	struct device_node *parent)
-- 
cgit v1.2.3


From dcbabbbd2618991d349b3b4f75e6b2eb4fad37df Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Thu, 29 Mar 2018 11:17:08 +0100
Subject: dt-bindings: irqchip: renesas-irqc: Document r8a77470 support

Renesas RZ/G SoC have the R-Car gen2 compatible IRQC interrupt
controllers. Document RZ/G1C (also known as R8A77470) SoC bindings.

Reviewed-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
index 20f121daa910..1d5891a82dd3 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -7,6 +7,7 @@ Required properties:
     - "renesas,irqc-r8a73a4" (R-Mobile APE6)
     - "renesas,irqc-r8a7743" (RZ/G1M)
     - "renesas,irqc-r8a7745" (RZ/G1E)
+    - "renesas,irqc-r8a77470" (RZ/G1C)
     - "renesas,irqc-r8a7790" (R-Car H2)
     - "renesas,irqc-r8a7791" (R-Car M2-W)
     - "renesas,irqc-r8a7792" (R-Car V2H)
-- 
cgit v1.2.3


From d5fd14803573e57941100d11dd9cf3e84d17e180 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Tue, 17 Jul 2018 22:23:17 +0300
Subject: dt-bindings: irqchip: renesas-irqc: Document r8a77980 support

Document R-Car V3H (AKA R8A77980) SoC bindings.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
index 1d5891a82dd3..697ca2f26d1b 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/renesas,irqc.txt
@@ -17,6 +17,7 @@ Required properties:
     - "renesas,intc-ex-r8a7796" (R-Car M3-W)
     - "renesas,intc-ex-r8a77965" (R-Car M3-N)
     - "renesas,intc-ex-r8a77970" (R-Car V3M)
+    - "renesas,intc-ex-r8a77980" (R-Car V3H)
     - "renesas,intc-ex-r8a77995" (R-Car D3)
 - #interrupt-cells: has to be <2>: an interrupt index and flags, as defined in
   interrupts.txt in this directory
-- 
cgit v1.2.3


From 05c72e77ccda89ff624108b1b59a0fc43843f343 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 17 Jul 2018 20:42:14 +0300
Subject: drm/i915: Nuke the LVDS lid notifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We broke the LVDS notifier resume thing in (presumably) commit
e2c8b8701e2d ("drm/i915: Use atomic helpers for suspend, v2.") as
we no longer duplicate the current state in the LVDS notifier and
thus we never resume it properly either.

Instead of trying to fix it again let's just kill off the lid
notifier entirely. None of the machines tested thus far have
apparently needed it. Originally the lid notifier was added to
work around cases where the VBIOS was clobbering some of the
hardware state behind the driver's back, mostly on Thinkpads.
We now have a few report of Thinkpads working just fine without
the notifier. So maybe it was misdiagnosed originally, or
something else has changed (ACPI video stuff perhaps?).

If we do end up finding a machine where the VBIOS is still causing
problems I would suggest that we first try setting various bits in
the VBIOS scratch registers. There are several to choose from that
may instruct the VBIOS to steer clear.

With the notifier gone we'll also stop looking at the panel status
in ->detect().

v2: Nuke enum modeset_restore (Rodrigo)

Cc: stable@vger.kernel.org
Cc: Wolfgang Draxinger <wdraxinger.maillist@draxit.de>
Cc: Vito Caputo <vcaputo@pengaru.com>
Cc: kitsunyan <kitsunyan@airmail.cc>
Cc: Joonas Saarinen <jza@saunalahti.fi>
Tested-by: Vito Caputo <vcaputo@pengaru.com> # Thinkapd X61s
Tested-by: kitsunyan <kitsunyan@airmail.cc> # ThinkPad X200
Tested-by: Joonas Saarinen <jza@saunalahti.fi> # Fujitsu Siemens U9210
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=105902
References: https://lists.freedesktop.org/archives/intel-gfx/2018-June/169315.html
References: https://bugs.freedesktop.org/show_bug.cgi?id=21230
Fixes: e2c8b8701e2d ("drm/i915: Use atomic helpers for suspend, v2.")
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717174216.22252-1-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.c   |  10 ---
 drivers/gpu/drm/i915/i915_drv.h   |   8 ---
 drivers/gpu/drm/i915/intel_lvds.c | 136 +-------------------------------------
 3 files changed, 2 insertions(+), 152 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 337b1aad5212..343e79a44abd 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -900,7 +900,6 @@ static int i915_driver_init_early(struct drm_i915_private *dev_priv,
 	spin_lock_init(&dev_priv->uncore.lock);
 
 	mutex_init(&dev_priv->sb_lock);
-	mutex_init(&dev_priv->modeset_restore_lock);
 	mutex_init(&dev_priv->av_mutex);
 	mutex_init(&dev_priv->wm.wm_mutex);
 	mutex_init(&dev_priv->pps_mutex);
@@ -1570,11 +1569,6 @@ static int i915_drm_suspend(struct drm_device *dev)
 	struct pci_dev *pdev = dev_priv->drm.pdev;
 	pci_power_t opregion_target_state;
 
-	/* ignore lid events during suspend */
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	dev_priv->modeset_restore = MODESET_SUSPENDED;
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-
 	disable_rpm_wakeref_asserts(dev_priv);
 
 	/* We do a lot of poking in a lot of registers, make sure they work
@@ -1770,10 +1764,6 @@ static int i915_drm_resume(struct drm_device *dev)
 
 	intel_fbdev_set_suspend(dev, FBINFO_STATE_RUNNING, false);
 
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	dev_priv->modeset_restore = MODESET_DONE;
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-
 	intel_opregion_notify_adapter(dev_priv, PCI_D0);
 
 	enable_rpm_wakeref_asserts(dev_priv);
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 08d4303abb14..995656f51b57 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -1002,12 +1002,6 @@ struct i915_gem_mm {
 
 #define I915_ENGINE_WEDGED_TIMEOUT  (60 * HZ)  /* Reset but no recovery? */
 
-enum modeset_restore {
-	MODESET_ON_LID_OPEN,
-	MODESET_DONE,
-	MODESET_SUSPENDED,
-};
-
 #define DP_AUX_A 0x40
 #define DP_AUX_B 0x10
 #define DP_AUX_C 0x20
@@ -1730,8 +1724,6 @@ struct drm_i915_private {
 
 	unsigned long quirks;
 
-	enum modeset_restore modeset_restore;
-	struct mutex modeset_restore_lock;
 	struct drm_atomic_state *modeset_restore_state;
 	struct drm_modeset_acquire_ctx reset_ctx;
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index bb06744d28a4..a35404119257 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -44,8 +44,6 @@
 /* Private structure for the integrated LVDS support */
 struct intel_lvds_connector {
 	struct intel_connector base;
-
-	struct notifier_block lid_notifier;
 };
 
 struct intel_lvds_pps {
@@ -452,26 +450,9 @@ static bool intel_lvds_compute_config(struct intel_encoder *intel_encoder,
 	return true;
 }
 
-/*
- * Detect the LVDS connection.
- *
- * Since LVDS doesn't have hotlug, we use the lid as a proxy.  Open means
- * connected and closed means disconnected.  We also send hotplug events as
- * needed, using lid status notification from the input layer.
- */
 static enum drm_connector_status
 intel_lvds_detect(struct drm_connector *connector, bool force)
 {
-	struct drm_i915_private *dev_priv = to_i915(connector->dev);
-	enum drm_connector_status status;
-
-	DRM_DEBUG_KMS("[CONNECTOR:%d:%s]\n",
-		      connector->base.id, connector->name);
-
-	status = intel_panel_detect(dev_priv);
-	if (status != connector_status_unknown)
-		return status;
-
 	return connector_status_connected;
 }
 
@@ -496,117 +477,6 @@ static int intel_lvds_get_modes(struct drm_connector *connector)
 	return 1;
 }
 
-static int intel_no_modeset_on_lid_dmi_callback(const struct dmi_system_id *id)
-{
-	DRM_INFO("Skipping forced modeset for %s\n", id->ident);
-	return 1;
-}
-
-/* The GPU hangs up on these systems if modeset is performed on LID open */
-static const struct dmi_system_id intel_no_modeset_on_lid[] = {
-	{
-		.callback = intel_no_modeset_on_lid_dmi_callback,
-		.ident = "Toshiba Tecra A11",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "TOSHIBA"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "TECRA A11"),
-		},
-	},
-
-	{ }	/* terminating entry */
-};
-
-/*
- * Lid events. Note the use of 'modeset':
- *  - we set it to MODESET_ON_LID_OPEN on lid close,
- *    and set it to MODESET_DONE on open
- *  - we use it as a "only once" bit (ie we ignore
- *    duplicate events where it was already properly set)
- *  - the suspend/resume paths will set it to
- *    MODESET_SUSPENDED and ignore the lid open event,
- *    because they restore the mode ("lid open").
- */
-static int intel_lid_notify(struct notifier_block *nb, unsigned long val,
-			    void *unused)
-{
-	struct intel_lvds_connector *lvds_connector =
-		container_of(nb, struct intel_lvds_connector, lid_notifier);
-	struct drm_connector *connector = &lvds_connector->base.base;
-	struct drm_device *dev = connector->dev;
-	struct drm_i915_private *dev_priv = to_i915(dev);
-
-	if (dev->switch_power_state != DRM_SWITCH_POWER_ON)
-		return NOTIFY_OK;
-
-	mutex_lock(&dev_priv->modeset_restore_lock);
-	if (dev_priv->modeset_restore == MODESET_SUSPENDED)
-		goto exit;
-	/*
-	 * check and update the status of LVDS connector after receiving
-	 * the LID nofication event.
-	 */
-	connector->status = connector->funcs->detect(connector, false);
-
-	/* Don't force modeset on machines where it causes a GPU lockup */
-	if (dmi_check_system(intel_no_modeset_on_lid))
-		goto exit;
-	if (!acpi_lid_open()) {
-		/* do modeset on next lid open event */
-		dev_priv->modeset_restore = MODESET_ON_LID_OPEN;
-		goto exit;
-	}
-
-	if (dev_priv->modeset_restore == MODESET_DONE)
-		goto exit;
-
-	/*
-	 * Some old platform's BIOS love to wreak havoc while the lid is closed.
-	 * We try to detect this here and undo any damage. The split for PCH
-	 * platforms is rather conservative and a bit arbitrary expect that on
-	 * those platforms VGA disabling requires actual legacy VGA I/O access,
-	 * and as part of the cleanup in the hw state restore we also redisable
-	 * the vga plane.
-	 */
-	if (!HAS_PCH_SPLIT(dev_priv))
-		intel_display_resume(dev);
-
-	dev_priv->modeset_restore = MODESET_DONE;
-
-exit:
-	mutex_unlock(&dev_priv->modeset_restore_lock);
-	return NOTIFY_OK;
-}
-
-static int
-intel_lvds_connector_register(struct drm_connector *connector)
-{
-	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
-	int ret;
-
-	ret = intel_connector_register(connector);
-	if (ret)
-		return ret;
-
-	lvds->lid_notifier.notifier_call = intel_lid_notify;
-	if (acpi_lid_notifier_register(&lvds->lid_notifier)) {
-		DRM_DEBUG_KMS("lid notifier registration failed\n");
-		lvds->lid_notifier.notifier_call = NULL;
-	}
-
-	return 0;
-}
-
-static void
-intel_lvds_connector_unregister(struct drm_connector *connector)
-{
-	struct intel_lvds_connector *lvds = to_lvds_connector(connector);
-
-	if (lvds->lid_notifier.notifier_call)
-		acpi_lid_notifier_unregister(&lvds->lid_notifier);
-
-	intel_connector_unregister(connector);
-}
-
 /**
  * intel_lvds_destroy - unregister and free LVDS structures
  * @connector: connector to free
@@ -639,8 +509,8 @@ static const struct drm_connector_funcs intel_lvds_connector_funcs = {
 	.fill_modes = drm_helper_probe_single_connector_modes,
 	.atomic_get_property = intel_digital_connector_atomic_get_property,
 	.atomic_set_property = intel_digital_connector_atomic_set_property,
-	.late_register = intel_lvds_connector_register,
-	.early_unregister = intel_lvds_connector_unregister,
+	.late_register = intel_connector_register,
+	.early_unregister = intel_connector_unregister,
 	.destroy = intel_lvds_destroy,
 	.atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
 	.atomic_duplicate_state = intel_digital_connector_duplicate_state,
@@ -1114,8 +984,6 @@ void intel_lvds_init(struct drm_i915_private *dev_priv)
 	 * 2) check for VBT data
 	 * 3) check to see if LVDS is already on
 	 *    if none of the above, no panel
-	 * 4) make sure lid is open
-	 *    if closed, act like it's not there for now
 	 */
 
 	/*
-- 
cgit v1.2.3


From b93b41afcee272c13f4aa9df18b46ba40cce37e5 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 17 Jul 2018 20:42:15 +0300
Subject: drm/i915: Assume eDP is always connected
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We never registered any kind of lid notifier for eDP, so looking at the
lid status is pretty much bonkers. Let's just consider eDP always
connected instead.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717174216.22252-2-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/intel_dp.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index 5899cadf11e3..fee23cf93a2b 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -4406,14 +4406,7 @@ intel_dp_detect_dpcd(struct intel_dp *intel_dp)
 static enum drm_connector_status
 edp_detect(struct intel_dp *intel_dp)
 {
-	struct drm_i915_private *dev_priv = to_i915(intel_dp_to_dev(intel_dp));
-	enum drm_connector_status status;
-
-	status = intel_panel_detect(dev_priv);
-	if (status == connector_status_unknown)
-		status = connector_status_connected;
-
-	return status;
+	return connector_status_connected;
 }
 
 static bool ibx_digital_port_connected(struct intel_encoder *encoder)
@@ -4674,7 +4667,7 @@ intel_dp_long_pulse(struct intel_connector *connector)
 
 	intel_display_power_get(dev_priv, intel_dp->aux_power_domain);
 
-	/* Can't disconnect eDP, but you can close the lid... */
+	/* Can't disconnect eDP */
 	if (intel_dp_is_edp(intel_dp))
 		status = edp_detect(intel_dp);
 	else if (intel_digital_port_connected(&dp_to_dig_port(intel_dp)->base))
-- 
cgit v1.2.3


From d81be4f379e732c29e50fbf8fbdbe15980320bf6 Mon Sep 17 00:00:00 2001
From: Ville Syrjälä <ville.syrjala@linux.intel.com>
Date: Tue, 17 Jul 2018 20:42:16 +0300
Subject: drm/i915: Remove intel_panel_detect()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With neither LVDS or eDP no longer using intel_panel_detect() we can
kill it, and the accompanying modparam.

Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180717174216.22252-3-ville.syrjala@linux.intel.com
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_params.c |  4 ----
 drivers/gpu/drm/i915/i915_params.h |  1 -
 drivers/gpu/drm/i915/intel_drv.h   |  1 -
 drivers/gpu/drm/i915/intel_panel.c | 20 --------------------
 4 files changed, 26 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_params.c b/drivers/gpu/drm/i915/i915_params.c
index 817576701ed7..295e981e4a39 100644
--- a/drivers/gpu/drm/i915/i915_params.c
+++ b/drivers/gpu/drm/i915/i915_params.c
@@ -44,10 +44,6 @@ i915_param_named(modeset, int, 0400,
 	"Use kernel modesetting [KMS] (0=disable, "
 	"1=on, -1=force vga console preference [default])");
 
-i915_param_named_unsafe(panel_ignore_lid, int, 0600,
-	"Override lid status (0=autodetect, 1=autodetect disabled [default], "
-	"-1=force lid closed, -2=force lid open)");
-
 i915_param_named_unsafe(enable_dc, int, 0400,
 	"Enable power-saving display C-states. "
 	"(-1=auto [default]; 0=disable; 1=up to DC5; 2=up to DC6)");
diff --git a/drivers/gpu/drm/i915/i915_params.h b/drivers/gpu/drm/i915/i915_params.h
index aebe0469ddaa..6c4d4a21474b 100644
--- a/drivers/gpu/drm/i915/i915_params.h
+++ b/drivers/gpu/drm/i915/i915_params.h
@@ -36,7 +36,6 @@ struct drm_printer;
 #define I915_PARAMS_FOR_EACH(param) \
 	param(char *, vbt_firmware, NULL) \
 	param(int, modeset, -1) \
-	param(int, panel_ignore_lid, 1) \
 	param(int, lvds_channel_mode, 0) \
 	param(int, panel_use_ssc, -1) \
 	param(int, vbt_sdvo_panel_type, -1) \
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 92b68ebc7413..edcfd85e7b94 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -1889,7 +1889,6 @@ void intel_panel_enable_backlight(const struct intel_crtc_state *crtc_state,
 				  const struct drm_connector_state *conn_state);
 void intel_panel_disable_backlight(const struct drm_connector_state *old_conn_state);
 void intel_panel_destroy_backlight(struct drm_connector *connector);
-enum drm_connector_status intel_panel_detect(struct drm_i915_private *dev_priv);
 extern struct drm_display_mode *intel_find_panel_downclock(
 				struct drm_i915_private *dev_priv,
 				struct drm_display_mode *fixed_mode,
diff --git a/drivers/gpu/drm/i915/intel_panel.c b/drivers/gpu/drm/i915/intel_panel.c
index 14b827ec5427..4a9f139e7b73 100644
--- a/drivers/gpu/drm/i915/intel_panel.c
+++ b/drivers/gpu/drm/i915/intel_panel.c
@@ -375,26 +375,6 @@ out:
 	pipe_config->gmch_pfit.lvds_border_bits = border;
 }
 
-enum drm_connector_status
-intel_panel_detect(struct drm_i915_private *dev_priv)
-{
-	/* Assume that the BIOS does not lie through the OpRegion... */
-	if (!i915_modparams.panel_ignore_lid && dev_priv->opregion.lid_state) {
-		return *dev_priv->opregion.lid_state & 0x1 ?
-			connector_status_connected :
-			connector_status_disconnected;
-	}
-
-	switch (i915_modparams.panel_ignore_lid) {
-	case -2:
-		return connector_status_connected;
-	case -1:
-		return connector_status_disconnected;
-	default:
-		return connector_status_unknown;
-	}
-}
-
 /**
  * scale - scale values from one range to another
  * @source_val: value in range [@source_min..@source_max]
-- 
cgit v1.2.3


From ef821e3f14e868779505bf08f96afb4eade53652 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Thu, 19 Jul 2018 08:47:59 -0700
Subject: drm/i915: Update DRIVER_DATE to 20180719

Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 995656f51b57..ef1aabb751c6 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -86,8 +86,8 @@
 
 #define DRIVER_NAME		"i915"
 #define DRIVER_DESC		"Intel Graphics"
-#define DRIVER_DATE		"20180712"
-#define DRIVER_TIMESTAMP	1531464866
+#define DRIVER_DATE		"20180719"
+#define DRIVER_TIMESTAMP	1532015279
 
 /* Use I915_STATE_WARN(x) and I915_STATE_WARN_ON() (rather than WARN() and
  * WARN_ON()) for hw state sanity checks to check for unexpected conditions
-- 
cgit v1.2.3


From 9ee6f8a8cbbd203fb0a844f937007a9525422697 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Sun, 1 Jul 2018 11:30:23 +0200
Subject: ASoC: Intel: bytcr_rt5640: Add quirk for the "Connect Tablet 9"
 tablet

Add a quirk for the "Connect Tablet 9" tablet, this tablet has a
mono-speaker. Otherwise it works fine with the defaults.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bytcr_rt5640.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
index 657910a08261..d32844f94d74 100644
--- a/sound/soc/intel/boards/bytcr_rt5640.c
+++ b/sound/soc/intel/boards/bytcr_rt5640.c
@@ -486,6 +486,16 @@ static const struct dmi_system_id byt_rt5640_quirk_table[] = {
 		},
 		.driver_data = (void *)(BYT_RT5640_DMIC1_MAP),
 	},
+	{	/* Connect Tablet 9 */
+		.matches = {
+			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Connect"),
+			DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Tablet 9"),
+		},
+		.driver_data = (void *)(BYTCR_INPUT_DEFAULTS |
+					BYT_RT5640_MONO_SPEAKER |
+					BYT_RT5640_SSP0_AIF1 |
+					BYT_RT5640_MCLK_EN),
+	},
 	{
 		.matches = {
 			DMI_EXACT_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-- 
cgit v1.2.3


From c64fb6dade1637e80ab316be42a271747ac4033b Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 18 Jul 2018 16:07:11 -0500
Subject: drm/amdgpu/powerplay: use irq source defines for smu7 sources

Use the newly added irq source defines rather than magic numbers
for smu7 thermal interrupts.

Rewiewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Rex Zhu <rezhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
index 8eea49e4c74d..2aab1b475945 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu_helper.c
@@ -27,6 +27,7 @@
 #include "atom.h"
 #include "ivsrcid/thm/irqsrcs_thm_9_0.h"
 #include "ivsrcid/smuio/irqsrcs_smuio_9_0.h"
+#include "ivsrcid/ivsrcid_vislands30.h"
 
 uint8_t convert_to_vid(uint16_t vddc)
 {
@@ -545,17 +546,17 @@ int phm_irq_process(struct amdgpu_device *adev,
 	uint32_t src_id = entry->src_id;
 
 	if (client_id == AMDGPU_IH_CLIENTID_LEGACY) {
-		if (src_id == 230)
+		if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_LOW_TO_HIGH)
 			pr_warn("GPU over temperature range detected on PCIe %d:%d.%d!\n",
 						PCI_BUS_NUM(adev->pdev->devfn),
 						PCI_SLOT(adev->pdev->devfn),
 						PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == 231)
+		else if (src_id == VISLANDS30_IV_SRCID_CG_TSS_THERMAL_HIGH_TO_LOW)
 			pr_warn("GPU under temperature range detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
 					PCI_FUNC(adev->pdev->devfn));
-		else if (src_id == 83)
+		else if (src_id == VISLANDS30_IV_SRCID_GPIO_19)
 			pr_warn("GPU Critical Temperature Fault detected on PCIe %d:%d.%d!\n",
 					PCI_BUS_NUM(adev->pdev->devfn),
 					PCI_SLOT(adev->pdev->devfn),
-- 
cgit v1.2.3


From 1ce0688f3f6a9e9d34ae66bf779d54855def7bec Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Thu, 19 Jul 2018 13:21:43 +0800
Subject: drm/amd/powerplay: fixed uninitialized value

The 'result' is not initialized correctly. It causes the API
return an error code even on success.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 912d0d6cf476..4ed218dd8ba7 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -488,7 +488,7 @@ static int vega12_get_number_of_dpm_level(struct pp_hwmgr *hwmgr,
 static int vega12_get_dpm_frequency_by_index(struct pp_hwmgr *hwmgr,
 		PPCLK_e clkID, uint32_t index, uint32_t *clock)
 {
-	int result;
+	int result = 0;
 
 	/*
 	 *SMU expects the Clock ID to be in the top 16 bits.
-- 
cgit v1.2.3


From 4841203102a337b4b627e6dd3a1dc8c88aec982b Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Tue, 17 Jul 2018 12:37:45 +0200
Subject: drm/amdgpu/display: Replace CONFIG_DRM_AMD_DC_DCN1_0 with CONFIG_X86
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Allowing CONFIG_DRM_AMD_DC_DCN1_0 to be disabled on X86 was an
opportunity for display with Raven Ridge accidentally not working.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c           |  2 +-
 drivers/gpu/drm/amd/display/Kconfig                  |  8 --------
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c    |  8 ++++----
 drivers/gpu/drm/amd/display/dc/Makefile              |  2 +-
 .../drm/amd/display/dc/bios/command_table_helper2.c  |  2 +-
 drivers/gpu/drm/amd/display/dc/calcs/Makefile        |  2 +-
 drivers/gpu/drm/amd/display/dc/core/dc.c             |  6 +++---
 drivers/gpu/drm/amd/display/dc/core/dc_debug.c       |  2 +-
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c    | 12 ++++++------
 drivers/gpu/drm/amd/display/dc/dc.h                  |  2 +-
 .../gpu/drm/amd/display/dc/dce/dce_clock_source.c    |  6 +++---
 .../gpu/drm/amd/display/dc/dce/dce_clock_source.h    |  2 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c      |  8 ++++----
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h      |  2 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c        |  6 +++---
 .../gpu/drm/amd/display/dc/dce/dce_stream_encoder.c  | 20 ++++++++++----------
 .../drm/amd/display/dc/dce110/dce110_hw_sequencer.c  |  2 +-
 drivers/gpu/drm/amd/display/dc/gpio/Makefile         |  2 +-
 drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c     |  4 ++--
 drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c   |  4 ++--
 drivers/gpu/drm/amd/display/dc/i2caux/Makefile       |  2 +-
 drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c       |  4 ++--
 drivers/gpu/drm/amd/display/dc/inc/core_types.h      |  6 +++---
 drivers/gpu/drm/amd/display/dc/irq/Makefile          |  2 +-
 drivers/gpu/drm/amd/display/dc/irq/irq_service.c     |  2 +-
 drivers/gpu/drm/amd/display/dc/os_types.h            |  2 +-
 26 files changed, 56 insertions(+), 64 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 2b2de5f3e6e3..386a7b34d2f4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2200,7 +2200,7 @@ bool amdgpu_device_asic_has_dc_support(enum amd_asic_type asic_type)
 	case CHIP_VEGA10:
 	case CHIP_VEGA12:
 	case CHIP_VEGA20:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 #endif
 		return amdgpu_dc != 0;
diff --git a/drivers/gpu/drm/amd/display/Kconfig b/drivers/gpu/drm/amd/display/Kconfig
index 4c35625eb2c7..325083b0297e 100644
--- a/drivers/gpu/drm/amd/display/Kconfig
+++ b/drivers/gpu/drm/amd/display/Kconfig
@@ -9,14 +9,6 @@ config DRM_AMD_DC
 	  support for AMDGPU. This adds required support for Vega and
 	  Raven ASICs.
 
-config DRM_AMD_DC_DCN1_0
-	bool "DCN 1.0 Raven family"
-	depends on DRM_AMD_DC && X86
-	default y
-	help
-	  Choose this option if you want to have
-	  RV family for display engine
-
 config DEBUG_KERNEL_DC
 	bool "Enable kgdb break in DC"
 	depends on DRM_AMD_DC
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index e0cf54ccc9f4..2064cb21d0ed 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -60,7 +60,7 @@
 
 #include "modules/inc/mod_freesync.h"
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "ivsrcid/irqsrcs_dcn_1_0.h"
 
 #include "dcn/dcn_1_0_offset.h"
@@ -1192,7 +1192,7 @@ static int dce110_register_irq_handlers(struct amdgpu_device *adev)
 	return 0;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 /* Register IRQ sources and initialize IRQ callbacks */
 static int dcn10_register_irq_handlers(struct amdgpu_device *adev)
 {
@@ -1526,7 +1526,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			goto fail;
 		}
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 		if (dcn10_register_irq_handlers(dm->adev)) {
 			DRM_ERROR("DM: Failed to initialize IRQ\n");
@@ -1725,7 +1725,7 @@ static int dm_early_init(void *handle)
 		adev->mode_info.num_dig = 6;
 		adev->mode_info.plane_type = dm_plane_type_default;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case CHIP_RAVEN:
 		adev->mode_info.num_crtc = 4;
 		adev->mode_info.num_hpd = 4;
diff --git a/drivers/gpu/drm/amd/display/dc/Makefile b/drivers/gpu/drm/amd/display/dc/Makefile
index aed538a4d1ba..532a515fda9a 100644
--- a/drivers/gpu/drm/amd/display/dc/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/Makefile
@@ -25,7 +25,7 @@
 
 DC_LIBS = basics bios calcs dce gpio i2caux irq virtual
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 DC_LIBS += dcn10 dml
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
index bbbcef566c55..770ff89ba7e1 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table_helper2.c
@@ -55,7 +55,7 @@ bool dal_bios_parser_init_cmd_tbl_helper2(
 	case DCE_VERSION_11_22:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		*h = dal_cmd_tbl_helper_dce112_get_table2();
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/calcs/Makefile b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
index 95f332ee3e7e..416500e51b8d 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/calcs/Makefile
@@ -38,7 +38,7 @@ CFLAGS_dcn_calc_math.o := $(calcs_ccflags) -Wno-tautological-compare
 
 BW_CALCS = dce_calcs.o bw_fixed.o custom_float.o
 
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 BW_CALCS += dcn_calcs.o dcn_calc_math.o dcn_calc_auto.o
 endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
index cb0be7f6994c..733ac224e7fd 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
@@ -476,7 +476,7 @@ static void destruct(struct dc *dc)
 	kfree(dc->bw_dceip);
 	dc->bw_dceip = NULL;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	kfree(dc->dcn_soc);
 	dc->dcn_soc = NULL;
 
@@ -492,7 +492,7 @@ static bool construct(struct dc *dc,
 	struct dc_context *dc_ctx;
 	struct bw_calcs_dceip *dc_dceip;
 	struct bw_calcs_vbios *dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 #endif
@@ -514,7 +514,7 @@ static bool construct(struct dc *dc,
 	}
 
 	dc->bw_vbios = dc_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	dcn_soc = kzalloc(sizeof(*dcn_soc), GFP_KERNEL);
 	if (!dcn_soc) {
 		dm_error("%s: failed to create dcn_soc\n", __func__);
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
index e1ebdf7b5eaf..caece7c13bc6 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_debug.c
@@ -348,7 +348,7 @@ void context_clock_trace(
 		struct dc *dc,
 		struct dc_state *context)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	DC_LOGGER_INIT(dc->ctx->logger);
 	CLOCK_TRACE("Current: dispclk_khz:%d  max_dppclk_khz:%d  dcfclk_khz:%d\n"
 			"dcfclk_deep_sleep_khz:%d  fclk_khz:%d  socclk_khz:%d\n",
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 9abe5481e40c..2e65715f76a1 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -41,7 +41,7 @@
 #include "dce100/dce100_resource.h"
 #include "dce110/dce110_resource.h"
 #include "dce112/dce112_resource.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/dcn10_resource.h"
 #endif
 #include "dce120/dce120_resource.h"
@@ -85,7 +85,7 @@ enum dce_version resource_parse_asic_id(struct hw_asic_id asic_id)
 	case FAMILY_AI:
 		dc_version = DCE_VERSION_12_0;
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case FAMILY_RV:
 		dc_version = DCN_VERSION_1_0;
 		break;
@@ -136,7 +136,7 @@ struct resource_pool *dc_create_resource_pool(
 			num_virtual_links, dc);
 		break;
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		res_pool = dcn10_create_resource_pool(
 				num_virtual_links, dc);
@@ -1213,7 +1213,7 @@ static struct pipe_ctx *acquire_free_pipe_for_stream(
 
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static int acquire_first_split_pipe(
 		struct resource_context *res_ctx,
 		const struct resource_pool *pool,
@@ -1284,7 +1284,7 @@ bool dc_add_plane_to_context(
 
 	free_pipe = acquire_free_pipe_for_stream(context, pool, stream);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (!free_pipe) {
 		int pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 		if (pipe_idx >= 0)
@@ -1882,7 +1882,7 @@ enum dc_status resource_map_pool_resources(
 	/* acquire new resources */
 	pipe_idx = acquire_first_free_pipe(&context->res_ctx, pool, stream);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	if (pipe_idx < 0)
 		pipe_idx = acquire_first_split_pipe(&context->res_ctx, pool, stream);
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index b10dc177ad61..ceb4c3725893 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -289,7 +289,7 @@ struct dc {
 	/* Inputs into BW and WM calculations. */
 	struct bw_calcs_dceip *bw_dceip;
 	struct bw_calcs_vbios *bw_vbios;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct dcn_soc_bounding_box *dcn_soc;
 	struct dcn_ip_params *dcn_ip;
 	struct display_mode_lib dml;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
index ca137757a69e..439dcf3b596c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.c
@@ -592,7 +592,7 @@ static uint32_t dce110_get_pix_clk_dividers(
 	case DCE_VERSION_11_2:
 	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 #endif
 
@@ -909,7 +909,7 @@ static bool dce110_program_pix_clk(
 	struct dce110_clk_src *clk_src = TO_DCE110_CLK_SRC(clock_source);
 	struct bp_pixel_clock_parameters bp_pc_params = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (IS_FPGA_MAXIMUS_DC(clock_source->ctx->dce_environment)) {
 		unsigned int inst = pix_clk_params->controller_id - CONTROLLER_ID_D0;
 		unsigned dp_dto_ref_kHz = 700000;
@@ -982,7 +982,7 @@ static bool dce110_program_pix_clk(
 	case DCE_VERSION_11_2:
 	case DCE_VERSION_11_22:
 	case DCE_VERSION_12_0:
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
index c45e2f76189e..801bb65707b3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clock_source.h
@@ -55,7 +55,7 @@
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_DCCG_DEEP_COLOR_CNTL, mask_sh),\
 	CS_SF(PHYPLLA_PIXCLK_RESYNC_CNTL, PHYPLLA_PIXCLK_DOUBLE_RATE_ENABLE, mask_sh)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 
 #define CS_COMMON_REG_LIST_DCN1_0(index, pllid) \
 		SRI(PIXCLK_RESYNC_CNTL, PHYPLL, pllid),\
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 6882dc953a2c..8f8a2abac3f3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -30,7 +30,7 @@
 #include "bios_parser_interface.h"
 #include "dc.h"
 #include "dmcu.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn_calcs.h"
 #endif
 #include "core_types.h"
@@ -478,7 +478,7 @@ static void dce12_update_clocks(struct dccg *dccg,
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 static int dcn1_determine_dppclk_threshold(struct dccg *dccg, struct dc_clocks *new_clocks)
 {
 	bool request_dpp_div = new_clocks->dispclk_khz > new_clocks->dppclk_khz;
@@ -666,7 +666,7 @@ static void dce_update_clocks(struct dccg *dccg,
 	}
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 static const struct display_clock_funcs dcn1_funcs = {
 	.get_dp_ref_clk_frequency = dce12_get_dp_ref_freq_khz,
 	.set_dispclk = dce112_set_clock,
@@ -821,7 +821,7 @@ struct dccg *dce120_dccg_create(struct dc_context *ctx)
 	return &clk_dce->base;
 }
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 struct dccg *dcn1_dccg_create(struct dc_context *ctx)
 {
 	struct dc_debug *debug = &ctx->dc->debug;
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
index 8a6b2d328467..e5e44adc6c27 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.h
@@ -111,7 +111,7 @@ struct dccg *dce112_dccg_create(
 
 struct dccg *dce120_dccg_create(struct dc_context *ctx);
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 struct dccg *dcn1_dccg_create(struct dc_context *ctx);
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index a576b8bbb3cd..062a46543887 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -314,7 +314,7 @@ static void dce_get_psr_wait_loop(
 	return;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static void dcn10_get_dmcu_state(struct dmcu *dmcu)
 {
 	struct dce_dmcu *dmcu_dce = TO_DCE_DMCU(dmcu);
@@ -735,7 +735,7 @@ static const struct dmcu_funcs dce_funcs = {
 	.is_dmcu_initialized = dce_is_dmcu_initialized
 };
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 static const struct dmcu_funcs dcn10_funcs = {
 	.dmcu_init = dcn10_dmcu_init,
 	.load_iram = dcn10_dmcu_load_iram,
@@ -787,7 +787,7 @@ struct dmcu *dce_dmcu_create(
 	return &dmcu_dce->base;
 }
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 struct dmcu *dcn10_dmcu_create(
 	struct dc_context *ctx,
 	const struct dce_dmcu_registers *regs,
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
index 91642e684858..b139b4017820 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_stream_encoder.c
@@ -135,7 +135,7 @@ static void dce110_update_generic_info_packet(
 			AFMT_GENERIC0_UPDATE, (packet_index == 0),
 			AFMT_GENERIC2_UPDATE, (packet_index == 2));
 	}
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (REG(AFMT_VBI_PACKET_CONTROL1)) {
 		switch (packet_index) {
 		case 0:
@@ -229,7 +229,7 @@ static void dce110_update_hdmi_info_packet(
 				HDMI_GENERIC1_SEND, send,
 				HDMI_GENERIC1_LINE, line);
 		break;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case 4:
 		if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 			REG_UPDATE_3(HDMI_GENERIC_PACKET_CONTROL2,
@@ -274,7 +274,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	struct dc_crtc_timing *crtc_timing,
 	enum dc_color_space output_color_space)
 {
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	uint32_t h_active_start;
 	uint32_t v_active_start;
 	uint32_t misc0 = 0;
@@ -317,7 +317,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		if (enc110->se_mask->DP_VID_M_DOUBLE_VALUE_EN)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_M_DOUBLE_VALUE_EN, 1);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 		if (enc110->se_mask->DP_VID_N_MUL)
 			REG_UPDATE(DP_VID_TIMING, DP_VID_N_MUL, 1);
 #endif
@@ -328,7 +328,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 		break;
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (REG(DP_MSA_MISC))
 		misc1 = REG_READ(DP_MSA_MISC);
 #endif
@@ -362,7 +362,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 	/* set dynamic range and YCbCr range */
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	switch (crtc_timing->display_color_depth) {
 	case COLOR_DEPTH_666:
 		colorimetry_bpc = 0;
@@ -441,7 +441,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				DP_DYN_RANGE, dynamic_range_rgb,
 				DP_YCBCR_RANGE, dynamic_range_ycbcr);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 		if (REG(DP_MSA_COLORIMETRY))
 			REG_SET(DP_MSA_COLORIMETRY, 0, DP_MSA_MISC0, misc0);
 
@@ -476,7 +476,7 @@ static void dce110_stream_encoder_dp_set_stream_attribute(
 				crtc_timing->v_front_porch;
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 		/* start at begining of left border */
 		if (REG(DP_MSA_TIMING_PARAM2))
 			REG_SET_2(DP_MSA_TIMING_PARAM2, 0,
@@ -751,7 +751,7 @@ static void dce110_stream_encoder_update_hdmi_info_packets(
 		dce110_update_hdmi_info_packet(enc110, 3, &info_frame->hdrsmd);
 	}
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	if (enc110->se_mask->HDMI_DB_DISABLE) {
 		/* for bring up, disable dp double  TODO */
 		if (REG(HDMI_DB_CONTROL))
@@ -789,7 +789,7 @@ static void dce110_stream_encoder_stop_hdmi_info_packets(
 		HDMI_GENERIC1_LINE, 0,
 		HDMI_GENERIC1_SEND, 0);
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	/* stop generic packets 2 & 3 on HDMI */
 	if (REG(HDMI_GENERIC_PACKET_CONTROL2))
 		REG_SET_6(HDMI_GENERIC_PACKET_CONTROL2, 0,
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 45388bff2c7d..33a14e163f88 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -1250,7 +1250,7 @@ static void program_scaler(const struct dc *dc,
 {
 	struct tg_color color = {0};
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	/* TOFPGA */
 	if (pipe_ctx->plane_res.xfm->funcs->transform_set_pixel_storage_depth == NULL)
 		return;
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/Makefile b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
index 562ee189d780..b9d9930a4974 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/gpio/Makefile
@@ -61,7 +61,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_GPIO_DCE120)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 GPIO_DCN10 = hw_translate_dcn10.o hw_factory_dcn10.o
 
 AMD_DAL_GPIO_DCN10 = $(addprefix $(AMDDALPATH)/dc/gpio/dcn10/,$(GPIO_DCN10))
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
index 0caee3523017..83df779984e5 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_factory.c
@@ -43,7 +43,7 @@
 #include "dce80/hw_factory_dce80.h"
 #include "dce110/hw_factory_dce110.h"
 #include "dce120/hw_factory_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/hw_factory_dcn10.h"
 #endif
 
@@ -81,7 +81,7 @@ bool dal_hw_factory_init(
 	case DCE_VERSION_12_0:
 		dal_hw_factory_dce120_init(factory);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		dal_hw_factory_dcn10_init(factory);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
index 55c707488541..e7541310480b 100644
--- a/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
+++ b/drivers/gpu/drm/amd/display/dc/gpio/hw_translate.c
@@ -43,7 +43,7 @@
 #include "dce80/hw_translate_dce80.h"
 #include "dce110/hw_translate_dce110.h"
 #include "dce120/hw_translate_dce120.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/hw_translate_dcn10.h"
 #endif
 
@@ -78,7 +78,7 @@ bool dal_hw_translate_init(
 	case DCE_VERSION_12_0:
 		dal_hw_translate_dce120_init(translate);
 		return true;
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		dal_hw_translate_dcn10_init(translate);
 		return true;
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
index 352885cb4d07..a851d07f0190 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/Makefile
@@ -71,7 +71,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_I2CAUX_DCE112)
 ###############################################################################
 # DCN 1.0 family
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 I2CAUX_DCN1 = i2caux_dcn10.o
 
 AMD_DAL_I2CAUX_DCN1 = $(addprefix $(AMDDALPATH)/dc/i2caux/dcn10/,$(I2CAUX_DCN1))
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
index 9b0bcc6b769b..f7ed355fc84f 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/i2caux.c
@@ -59,7 +59,7 @@
 
 #include "dce120/i2caux_dce120.h"
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/i2caux_dcn10.h"
 #endif
 
@@ -91,7 +91,7 @@ struct i2caux *dal_i2caux_create(
 		return dal_i2caux_dce100_create(ctx);
 	case DCE_VERSION_12_0:
 		return dal_i2caux_dce120_create(ctx);
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 	case DCN_VERSION_1_0:
 		return dal_i2caux_dcn10_create(ctx);
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 1db26bc0bec3..4446652a9a9e 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -33,7 +33,7 @@
 #include "dc_bios_types.h"
 #include "mem_input.h"
 #include "hubp.h"
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "mpc.h"
 #endif
 
@@ -221,7 +221,7 @@ struct pipe_ctx {
 	struct pipe_ctx *top_pipe;
 	struct pipe_ctx *bottom_pipe;
 
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct _vcs_dpi_display_dlg_regs_st dlg_regs;
 	struct _vcs_dpi_display_ttu_regs_st ttu_regs;
 	struct _vcs_dpi_display_rq_regs_st rq_regs;
@@ -276,7 +276,7 @@ struct dc_state {
 
 	/* Note: these are big structures, do *not* put on stack! */
 	struct dm_pp_display_configuration pp_display_cfg;
-#ifdef CONFIG_DRM_AMD_DC_DCN1_0
+#ifdef CONFIG_X86
 	struct dcn_bw_internal_vars dcn_bw_vars;
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/irq/Makefile b/drivers/gpu/drm/amd/display/dc/irq/Makefile
index 498515aad4a5..a76ee600ecee 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/irq/Makefile
@@ -60,7 +60,7 @@ AMD_DISPLAY_FILES += $(AMD_DAL_IRQ_DCE12)
 ###############################################################################
 # DCN 1x
 ###############################################################################
-ifdef CONFIG_DRM_AMD_DC_DCN1_0
+ifdef CONFIG_X86
 IRQ_DCN1 = irq_service_dcn10.o
 
 AMD_DAL_IRQ_DCN1 = $(addprefix $(AMDDALPATH)/dc/irq/dcn10/,$(IRQ_DCN1))
diff --git a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
index 604bea01fc13..ae3fd0a235ba 100644
--- a/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
+++ b/drivers/gpu/drm/amd/display/dc/irq/irq_service.c
@@ -36,7 +36,7 @@
 #include "dce120/irq_service_dce120.h"
 
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include "dcn10/irq_service_dcn10.h"
 #endif
 
diff --git a/drivers/gpu/drm/amd/display/dc/os_types.h b/drivers/gpu/drm/amd/display/dc/os_types.h
index a407892905af..c9fce9066ad8 100644
--- a/drivers/gpu/drm/amd/display/dc/os_types.h
+++ b/drivers/gpu/drm/amd/display/dc/os_types.h
@@ -48,7 +48,7 @@
 
 #define dm_error(fmt, ...) DRM_ERROR(fmt, ##__VA_ARGS__)
 
-#if defined(CONFIG_DRM_AMD_DC_DCN1_0)
+#ifdef CONFIG_X86
 #include <asm/fpu/api.h>
 #endif
 
-- 
cgit v1.2.3


From 58c24b7c893cb1739918c875ae3cf4bb5f86ebb7 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 20:28:08 +0200
Subject: drm/amdgpu: remove superflous UVD encode entity
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Not sure what that was every used for, but now it is completely unused.

Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Chunming  Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h |  1 -
 drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c   | 12 ------------
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c   | 14 --------------
 3 files changed, 27 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index 8b23a1b00c76..cae3f526216b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -48,7 +48,6 @@ struct amdgpu_uvd_inst {
 	struct amdgpu_ring	ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
 	struct drm_sched_entity entity;
-	struct drm_sched_entity entity_enc;
 	uint32_t                srbm_soft_reset;
 };
 
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
index b796dc8375cd..598dbeaba636 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v6_0.c
@@ -418,16 +418,6 @@ static int uvd_v6_0_sw_init(void *handle)
 		adev->uvd.num_enc_rings = 0;
 
 		DRM_INFO("UVD ENC is disabled\n");
-	} else {
-		struct drm_sched_rq *rq;
-		ring = &adev->uvd.inst->ring_enc[0];
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&adev->uvd.inst->entity_enc,
-					  &rq, 1, NULL);
-		if (r) {
-			DRM_ERROR("Failed setting up UVD ENC run queue.\n");
-			return r;
-		}
 	}
 
 	r = amdgpu_uvd_resume(adev);
@@ -463,8 +453,6 @@ static int uvd_v6_0_sw_fini(void *handle)
 		return r;
 
 	if (uvd_v6_0_enc_support(adev)) {
-		drm_sched_entity_destroy(&adev->uvd.inst->ring_enc[0].sched, &adev->uvd.inst->entity_enc);
-
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst->ring_enc[i]);
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index 831bb995b0ed..db5f3d78ab12 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -389,7 +389,6 @@ static int uvd_v7_0_early_init(void *handle)
 static int uvd_v7_0_sw_init(void *handle)
 {
 	struct amdgpu_ring *ring;
-	struct drm_sched_rq *rq;
 	int i, j, r;
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
@@ -421,17 +420,6 @@ static int uvd_v7_0_sw_init(void *handle)
 		DRM_INFO("PSP loading UVD firmware\n");
 	}
 
-	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-		ring = &adev->uvd.inst[j].ring_enc[0];
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&adev->uvd.inst[j].entity_enc,
-					  &rq, 1, NULL);
-		if (r) {
-			DRM_ERROR("(%d)Failed setting up UVD ENC run queue.\n", j);
-			return r;
-		}
-	}
-
 	r = amdgpu_uvd_resume(adev);
 	if (r)
 		return r;
@@ -484,8 +472,6 @@ static int uvd_v7_0_sw_fini(void *handle)
 		return r;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
-		drm_sched_entity_destroy(&adev->uvd.inst[j].ring_enc[0].sched, &adev->uvd.inst[j].entity_enc);
-
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]);
 	}
-- 
cgit v1.2.3


From 5c675bf2c67c4efb36a78bebf44dc435db2daf16 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 20:30:51 +0200
Subject: drm/amdgpu: clean up UVD instance handling v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The whole handle, filp and entity handling is superfluous here.

We should have reviewed that more thoughtfully. It looks like somebody
just made the code instance aware without knowing the background.

v2: fix one more missed case in amdgpu_uvd_suspend

Reviewed-by: Leo Liu <leo.liu@amd.com>
Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Chunming  Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c | 121 ++++++++++++++++----------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h |  10 +--
 2 files changed, 64 insertions(+), 67 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index d708970244eb..80b5c453f8c1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -263,21 +263,20 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 			dev_err(adev->dev, "(%d) failed to allocate UVD bo\n", r);
 			return r;
 		}
+	}
 
-		ring = &adev->uvd.inst[j].ring;
-		rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
-		r = drm_sched_entity_init(&adev->uvd.inst[j].entity, &rq,
-					  1, NULL);
-		if (r != 0) {
-			DRM_ERROR("Failed setting up UVD(%d) run queue.\n", j);
-			return r;
-		}
-
-		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			atomic_set(&adev->uvd.inst[j].handles[i], 0);
-			adev->uvd.inst[j].filp[i] = NULL;
-		}
+	ring = &adev->uvd.inst[0].ring;
+	rq = &ring->sched.sched_rq[DRM_SCHED_PRIORITY_NORMAL];
+	r = drm_sched_entity_init(&adev->uvd.entity, &rq, 1, NULL);
+	if (r) {
+		DRM_ERROR("Failed setting up UVD kernel entity.\n");
+		return r;
 	}
+	for (i = 0; i < adev->uvd.max_handles; ++i) {
+		atomic_set(&adev->uvd.handles[i], 0);
+		adev->uvd.filp[i] = NULL;
+	}
+
 	/* from uvd v5.0 HW addressing capacity increased to 64 bits */
 	if (!amdgpu_device_ip_block_version_cmp(adev, AMD_IP_BLOCK_TYPE_UVD, 5, 0))
 		adev->uvd.address_64_bit = true;
@@ -306,11 +305,12 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
+	drm_sched_entity_destroy(&adev->uvd.inst->ring.sched,
+				 &adev->uvd.entity);
+
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
 		kfree(adev->uvd.inst[j].saved_bo);
 
-		drm_sched_entity_destroy(&adev->uvd.inst[j].ring.sched, &adev->uvd.inst[j].entity);
-
 		amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo,
 				      &adev->uvd.inst[j].gpu_addr,
 				      (void **)&adev->uvd.inst[j].cpu_addr);
@@ -333,20 +333,20 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 
 	cancel_delayed_work_sync(&adev->uvd.idle_work);
 
+	/* only valid for physical mode */
+	if (adev->asic_type < CHIP_POLARIS10) {
+		for (i = 0; i < adev->uvd.max_handles; ++i)
+			if (atomic_read(&adev->uvd.handles[i]))
+				break;
+
+		if (i == adev->uvd.max_handles)
+			return 0;
+	}
+
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
 		if (adev->uvd.inst[j].vcpu_bo == NULL)
 			continue;
 
-		/* only valid for physical mode */
-		if (adev->asic_type < CHIP_POLARIS10) {
-			for (i = 0; i < adev->uvd.max_handles; ++i)
-				if (atomic_read(&adev->uvd.inst[j].handles[i]))
-					break;
-
-			if (i == adev->uvd.max_handles)
-				continue;
-		}
-
 		size = amdgpu_bo_size(adev->uvd.inst[j].vcpu_bo);
 		ptr = adev->uvd.inst[j].cpu_addr;
 
@@ -398,30 +398,27 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 
 void amdgpu_uvd_free_handles(struct amdgpu_device *adev, struct drm_file *filp)
 {
-	struct amdgpu_ring *ring;
-	int i, j, r;
-
-	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-		ring = &adev->uvd.inst[j].ring;
+	struct amdgpu_ring *ring = &adev->uvd.inst[0].ring;
+	int i, r;
 
-		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			uint32_t handle = atomic_read(&adev->uvd.inst[j].handles[i]);
-			if (handle != 0 && adev->uvd.inst[j].filp[i] == filp) {
-				struct dma_fence *fence;
-
-				r = amdgpu_uvd_get_destroy_msg(ring, handle,
-							       false, &fence);
-				if (r) {
-					DRM_ERROR("Error destroying UVD(%d) %d!\n", j, r);
-					continue;
-				}
+	for (i = 0; i < adev->uvd.max_handles; ++i) {
+		uint32_t handle = atomic_read(&adev->uvd.handles[i]);
 
-				dma_fence_wait(fence, false);
-				dma_fence_put(fence);
+		if (handle != 0 && adev->uvd.filp[i] == filp) {
+			struct dma_fence *fence;
 
-				adev->uvd.inst[j].filp[i] = NULL;
-				atomic_set(&adev->uvd.inst[j].handles[i], 0);
+			r = amdgpu_uvd_get_destroy_msg(ring, handle, false,
+						       &fence);
+			if (r) {
+				DRM_ERROR("Error destroying UVD %d!\n", r);
+				continue;
 			}
+
+			dma_fence_wait(fence, false);
+			dma_fence_put(fence);
+
+			adev->uvd.filp[i] = NULL;
+			atomic_set(&adev->uvd.handles[i], 0);
 		}
 	}
 }
@@ -692,20 +689,19 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 			     struct amdgpu_bo *bo, unsigned offset)
 {
 	struct amdgpu_device *adev = ctx->parser->adev;
-	uint32_t ip_instance = ctx->parser->ring->me;
 	int32_t *msg, msg_type, handle;
 	void *ptr;
 	long r;
 	int i;
 
 	if (offset & 0x3F) {
-		DRM_ERROR("UVD(%d) messages must be 64 byte aligned!\n", ip_instance);
+		DRM_ERROR("UVD messages must be 64 byte aligned!\n");
 		return -EINVAL;
 	}
 
 	r = amdgpu_bo_kmap(bo, &ptr);
 	if (r) {
-		DRM_ERROR("Failed mapping the UVD(%d) message (%ld)!\n", ip_instance, r);
+		DRM_ERROR("Failed mapping the UVD) message (%ld)!\n", r);
 		return r;
 	}
 
@@ -715,7 +711,7 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 	handle = msg[2];
 
 	if (handle == 0) {
-		DRM_ERROR("Invalid UVD(%d) handle!\n", ip_instance);
+		DRM_ERROR("Invalid UVD handle!\n");
 		return -EINVAL;
 	}
 
@@ -726,18 +722,19 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* try to alloc a new handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
-				DRM_ERROR("(%d)Handle 0x%x already in use!\n", ip_instance, handle);
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				DRM_ERROR(")Handle 0x%x already in use!\n",
+					  handle);
 				return -EINVAL;
 			}
 
-			if (!atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], 0, handle)) {
-				adev->uvd.inst[ip_instance].filp[i] = ctx->parser->filp;
+			if (!atomic_cmpxchg(&adev->uvd.handles[i], 0, handle)) {
+				adev->uvd.filp[i] = ctx->parser->filp;
 				return 0;
 			}
 		}
 
-		DRM_ERROR("No more free UVD(%d) handles!\n", ip_instance);
+		DRM_ERROR("No more free UVD handles!\n");
 		return -ENOSPC;
 
 	case 1:
@@ -749,27 +746,27 @@ static int amdgpu_uvd_cs_msg(struct amdgpu_uvd_cs_ctx *ctx,
 
 		/* validate the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i) {
-			if (atomic_read(&adev->uvd.inst[ip_instance].handles[i]) == handle) {
-				if (adev->uvd.inst[ip_instance].filp[i] != ctx->parser->filp) {
-					DRM_ERROR("UVD(%d) handle collision detected!\n", ip_instance);
+			if (atomic_read(&adev->uvd.handles[i]) == handle) {
+				if (adev->uvd.filp[i] != ctx->parser->filp) {
+					DRM_ERROR("UVD handle collision detected!\n");
 					return -EINVAL;
 				}
 				return 0;
 			}
 		}
 
-		DRM_ERROR("Invalid UVD(%d) handle 0x%x!\n", ip_instance, handle);
+		DRM_ERROR("Invalid UVD handle 0x%x!\n", handle);
 		return -ENOENT;
 
 	case 2:
 		/* it's a destroy msg, free the handle */
 		for (i = 0; i < adev->uvd.max_handles; ++i)
-			atomic_cmpxchg(&adev->uvd.inst[ip_instance].handles[i], handle, 0);
+			atomic_cmpxchg(&adev->uvd.handles[i], handle, 0);
 		amdgpu_bo_kunmap(bo);
 		return 0;
 
 	default:
-		DRM_ERROR("Illegal UVD(%d) message type (%d)!\n", ip_instance, msg_type);
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
 		return -EINVAL;
 	}
 	BUG();
@@ -1071,7 +1068,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 		if (r)
 			goto err_free;
 
-		r = amdgpu_job_submit(job, &adev->uvd.inst[ring->me].entity,
+		r = amdgpu_job_submit(job, &adev->uvd.entity,
 				      AMDGPU_FENCE_OWNER_UNDEFINED, &f);
 		if (r)
 			goto err_free;
@@ -1273,7 +1270,7 @@ uint32_t amdgpu_uvd_used_handles(struct amdgpu_device *adev)
 		 * necessarily linear. So we need to count
 		 * all non-zero handles.
 		 */
-		if (atomic_read(&adev->uvd.inst->handles[i]))
+		if (atomic_read(&adev->uvd.handles[i]))
 			used_handles++;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index cae3f526216b..66872286ab12 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -42,12 +42,9 @@ struct amdgpu_uvd_inst {
 	void			*cpu_addr;
 	uint64_t		gpu_addr;
 	void			*saved_bo;
-	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
-	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
 	struct amdgpu_ring	ring;
 	struct amdgpu_ring	ring_enc[AMDGPU_MAX_UVD_ENC_RINGS];
 	struct amdgpu_irq_src	irq;
-	struct drm_sched_entity entity;
 	uint32_t                srbm_soft_reset;
 };
 
@@ -56,10 +53,13 @@ struct amdgpu_uvd {
 	unsigned		fw_version;
 	unsigned		max_handles;
 	unsigned		num_enc_rings;
-	uint8_t		num_uvd_inst;
+	uint8_t			num_uvd_inst;
 	bool			address_64_bit;
 	bool			use_ctx_buf;
-	struct amdgpu_uvd_inst		inst[AMDGPU_MAX_UVD_INSTANCES];
+	struct amdgpu_uvd_inst	inst[AMDGPU_MAX_UVD_INSTANCES];
+	struct drm_file		*filp[AMDGPU_MAX_UVD_HANDLES];
+	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
+	struct drm_sched_entity entity;
 	struct delayed_work	idle_work;
 };
 
-- 
cgit v1.2.3


From 2f819db565e82e5f73cd42b39925098986693378 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@mips.com>
Date: Tue, 15 May 2018 23:32:45 +0100
Subject: binfmt_elf: Respect error return from `regset->active'

The regset API documented in <linux/regset.h> defines -ENODEV as the
result of the `->active' handler to be used where the feature requested
is not available on the hardware found.  However code handling core file
note generation in `fill_thread_core_info' interpretes any non-zero
result from the `->active' handler as the regset requested being active.
Consequently processing continues (and hopefully gracefully fails later
on) rather than being abandoned right away for the regset requested.

Fix the problem then by making the code proceed only if a positive
result is returned from the `->active' handler.

Signed-off-by: Maciej W. Rozycki <macro@mips.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 4206d3aa1978 ("elf core dump: notes user_regset")
Patchwork: https://patchwork.linux-mips.org/patch/19332/
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 fs/binfmt_elf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 0ac456b52bdd..21b47c36309b 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1752,7 +1752,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		const struct user_regset *regset = &view->regsets[i];
 		do_thread_regset_writeback(t->task, regset);
 		if (regset->core_note_type && regset->get &&
-		    (!regset->active || regset->active(t->task, regset))) {
+		    (!regset->active || regset->active(t->task, regset) > 0)) {
 			int ret;
 			size_t size = regset_size(t->task, regset);
 			void *data = kmalloc(size, GFP_KERNEL);
-- 
cgit v1.2.3


From f5958b4cf4fc38ed4583ab83fb7c4cd1ab05f47b Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@mips.com>
Date: Tue, 15 May 2018 23:33:26 +0100
Subject: MIPS: Correct the 64-bit DSP accumulator register size

Use the `unsigned long' rather than `__u32' type for DSP accumulator
registers, like with the regular MIPS multiply/divide accumulator and
general-purpose registers, as all are 64-bit in 64-bit implementations
and using a 32-bit data type leads to contents truncation on context
saving.

Update `arch_ptrace' and `compat_arch_ptrace' accordingly, removing
casts that are similarly not used with multiply/divide accumulator or
general-purpose register accesses.

Signed-off-by: Maciej W. Rozycki <macro@mips.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: e50c0a8fa60d ("Support the MIPS32 / MIPS64 DSP ASE.")
Patchwork: https://patchwork.linux-mips.org/patch/19329/
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org # 2.6.15+
---
 arch/mips/include/asm/processor.h | 2 +-
 arch/mips/kernel/ptrace.c         | 2 +-
 arch/mips/kernel/ptrace32.c       | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index af34afbc32d9..d8a5951433fc 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -141,7 +141,7 @@ struct mips_fpu_struct {
 
 #define NUM_DSP_REGS   6
 
-typedef __u32 dspreg_t;
+typedef unsigned long dspreg_t;
 
 struct mips_dsp_state {
 	dspreg_t	dspr[NUM_DSP_REGS];
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 9f6c3f2aa2e2..8c8d42823bda 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -856,7 +856,7 @@ long arch_ptrace(struct task_struct *child, long request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
diff --git a/arch/mips/kernel/ptrace32.c b/arch/mips/kernel/ptrace32.c
index 7edc629304c8..bc348d44d151 100644
--- a/arch/mips/kernel/ptrace32.c
+++ b/arch/mips/kernel/ptrace32.c
@@ -142,7 +142,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
 				goto out;
 			}
 			dregs = __get_dsp_regs(child);
-			tmp = (unsigned long) (dregs[addr - DSP_BASE]);
+			tmp = dregs[addr - DSP_BASE];
 			break;
 		}
 		case DSP_CONTROL:
-- 
cgit v1.2.3


From 44109c60176ae73924a42a6bef64ef151aba9095 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@mips.com>
Date: Tue, 15 May 2018 23:34:28 +0100
Subject: MIPS: Add DSP ASE regset support

Define an NT_MIPS_DSP core file note type and implement a corresponding
regset holding the DSP ASE register context, following the layout of the
`mips_dsp_state' structure, except for the DSPControl register stored as
a 64-bit rather than 32-bit quantity in a 64-bit note.

The lack of DSP ASE register saving to core files can be considered a
design flaw with commit e50c0a8fa60d ("Support the MIPS32 / MIPS64 DSP
ASE."), leading to an incomplete state being saved.  Consequently no DSP
ASE regset has been created with commit 7aeb753b5353 ("MIPS: Implement
task_user_regset_view."), when regset support was added to the MIPS
port.

Additionally there is no way for ptrace(2) to correctly access the DSP
accumulator registers in n32 processes with the existing interfaces.
This is due to 32-bit truncation of data passed with PTRACE_PEEKUSR and
PTRACE_POKEUSR requests, which cannot be avoided owing to how the data
types for ptrace(3) have been defined.  This new NT_MIPS_DSP regset
fills the missing interface gap.

[paul.burton@mips.com:
  - Change NT_MIPS_DSP to 0x800 to avoid conflict with NT_VMCOREDD
    introduced by commit 2724273e8fd0 ("vmcore: add API to collect
    hardware dump in second kernel").
  - Drop stable tag. Whilst I agree the lack of this functionality can
    be considered a flaw in earlier DSP ASE support, it's still new
    functionality which doesn't meet up to the requirements set out in
    Documentation/process/stable-kernel-rules.rst.]

Signed-off-by: Maciej W. Rozycki <macro@mips.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
References: 7aeb753b5353 ("MIPS: Implement task_user_regset_view.")
Patchwork: https://patchwork.linux-mips.org/patch/19330/
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-fsdevel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/kernel/ptrace.c | 189 ++++++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/elf.h  |   1 +
 2 files changed, 190 insertions(+)

diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 8c8d42823bda..a536271ba084 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -41,6 +41,7 @@
 #include <asm/mipsmtregs.h>
 #include <asm/pgtable.h>
 #include <asm/page.h>
+#include <asm/processor.h>
 #include <asm/syscall.h>
 #include <linux/uaccess.h>
 #include <asm/bootinfo.h>
@@ -589,9 +590,179 @@ static int fpr_set(struct task_struct *target,
 	return err;
 }
 
+#if defined(CONFIG_32BIT) || defined(CONFIG_MIPS32_O32)
+
+/*
+ * Copy the DSP context to the supplied 32-bit NT_MIPS_DSP buffer.
+ */
+static int dsp32_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u32 dspregs[NUM_DSP_REGS + 1];
+
+	BUG_ON(count % sizeof(u32));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			dspregs[i] = target->thread.dsp.dspr[i];
+			break;
+		case NUM_DSP_REGS:
+			dspregs[i] = target->thread.dsp.dspcontrol;
+			break;
+		}
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				   sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 32-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp32_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u32 dspregs[NUM_DSP_REGS + 1];
+	int err;
+
+	BUG_ON(count % sizeof(u32));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u32);
+	num_regs = count / sizeof(u32);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				 sizeof(dspregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			target->thread.dsp.dspr[i] = (s32)dspregs[i];
+			break;
+		case NUM_DSP_REGS:
+			target->thread.dsp.dspcontrol = (s32)dspregs[i];
+			break;
+		}
+
+	return 0;
+}
+
+#endif /* CONFIG_32BIT || CONFIG_MIPS32_O32 */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Copy the DSP context to the supplied 64-bit NT_MIPS_DSP buffer.
+ */
+static int dsp64_get(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     void *kbuf, void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u64 dspregs[NUM_DSP_REGS + 1];
+
+	BUG_ON(count % sizeof(u64));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			dspregs[i] = target->thread.dsp.dspr[i];
+			break;
+		case NUM_DSP_REGS:
+			dspregs[i] = target->thread.dsp.dspcontrol;
+			break;
+		}
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				   sizeof(dspregs));
+}
+
+/*
+ * Copy the supplied 64-bit NT_MIPS_DSP buffer to the DSP context.
+ */
+static int dsp64_set(struct task_struct *target,
+		     const struct user_regset *regset,
+		     unsigned int pos, unsigned int count,
+		     const void *kbuf, const void __user *ubuf)
+{
+	unsigned int start, num_regs, i;
+	u64 dspregs[NUM_DSP_REGS + 1];
+	int err;
+
+	BUG_ON(count % sizeof(u64));
+
+	if (!cpu_has_dsp)
+		return -EIO;
+
+	start = pos / sizeof(u64);
+	num_regs = count / sizeof(u64);
+
+	if (start + num_regs > NUM_DSP_REGS + 1)
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, dspregs, 0,
+				 sizeof(dspregs));
+	if (err)
+		return err;
+
+	for (i = start; i < num_regs; i++)
+		switch (i) {
+		case 0 ... NUM_DSP_REGS - 1:
+			target->thread.dsp.dspr[i] = dspregs[i];
+			break;
+		case NUM_DSP_REGS:
+			target->thread.dsp.dspcontrol = dspregs[i];
+			break;
+		}
+
+	return 0;
+}
+
+#endif /* CONFIG_64BIT */
+
+/*
+ * Determine whether the DSP context is present.
+ */
+static int dsp_active(struct task_struct *target,
+		      const struct user_regset *regset)
+{
+	return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV;
+}
+
 enum mips_regset {
 	REGSET_GPR,
 	REGSET_FPR,
+	REGSET_DSP,
 };
 
 struct pt_regs_offset {
@@ -697,6 +868,15 @@ static const struct user_regset mips_regsets[] = {
 		.get		= fpr_get,
 		.set		= fpr_set,
 	},
+	[REGSET_DSP] = {
+		.core_note_type	= NT_MIPS_DSP,
+		.n		= NUM_DSP_REGS + 1,
+		.size		= sizeof(u32),
+		.align		= sizeof(u32),
+		.get		= dsp32_get,
+		.set		= dsp32_set,
+		.active		= dsp_active,
+	},
 };
 
 static const struct user_regset_view user_mips_view = {
@@ -728,6 +908,15 @@ static const struct user_regset mips64_regsets[] = {
 		.get		= fpr_get,
 		.set		= fpr_set,
 	},
+	[REGSET_DSP] = {
+		.core_note_type	= NT_MIPS_DSP,
+		.n		= NUM_DSP_REGS + 1,
+		.size		= sizeof(u64),
+		.align		= sizeof(u64),
+		.get		= dsp64_get,
+		.set		= dsp64_set,
+		.active		= dsp_active,
+	},
 };
 
 static const struct user_regset_view user_mips64_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index 4e12c423b9fe..e326c99b3881 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -422,6 +422,7 @@ typedef struct elf64_shdr {
 #define NT_ARM_SVE	0x405		/* ARM Scalable Vector Extension registers */
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
+#define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
 
 /* Note header in a PT_NOTE section */
 typedef struct elf32_note {
-- 
cgit v1.2.3


From 1ae22a0e35636efceab83728ba30b013df761592 Mon Sep 17 00:00:00 2001
From: "Maciej W. Rozycki" <macro@mips.com>
Date: Tue, 15 May 2018 23:40:18 +0100
Subject: MIPS: Add FP_MODE regset support

Define an NT_MIPS_FP_MODE core file note and implement a corresponding
regset holding the state handled by PR_SET_FP_MODE and PR_GET_FP_MODE
prctl(2) requests.  This lets debug software correctly interpret the
contents of floating-point general registers both in live debugging and
in core files, and also switch floating-point modes of a live process.

[paul.burton@mips.com:
  - Changed NT_MIPS_FP_MODE to 0x801 to match first nibble of
    NT_MIPS_DSP, which was also changed to avoid a conflict.]

Signed-off-by: Maciej W. Rozycki <macro@mips.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19331/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/kernel/ptrace.c | 63 +++++++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/elf.h  |  1 +
 2 files changed, 64 insertions(+)

diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index a536271ba084..e5ba56c01ee0 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -759,10 +759,57 @@ static int dsp_active(struct task_struct *target,
 	return cpu_has_dsp ? NUM_DSP_REGS + 1 : -ENODEV;
 }
 
+/* Copy the FP mode setting to the supplied NT_MIPS_FP_MODE buffer.  */
+static int fp_mode_get(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       void *kbuf, void __user *ubuf)
+{
+	int fp_mode;
+
+	fp_mode = mips_get_process_fp_mode(target);
+	return user_regset_copyout(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+				   sizeof(fp_mode));
+}
+
+/*
+ * Copy the supplied NT_MIPS_FP_MODE buffer to the FP mode setting.
+ *
+ * We optimize for the case where `count % sizeof(int) == 0', which
+ * is supposed to have been guaranteed by the kernel before calling
+ * us, e.g. in `ptrace_regset'.  We enforce that requirement, so
+ * that we can safely avoid preinitializing temporaries for partial
+ * mode writes.
+ */
+static int fp_mode_set(struct task_struct *target,
+		       const struct user_regset *regset,
+		       unsigned int pos, unsigned int count,
+		       const void *kbuf, const void __user *ubuf)
+{
+	int fp_mode;
+	int err;
+
+	BUG_ON(count % sizeof(int));
+
+	if (pos + count > sizeof(fp_mode))
+		return -EIO;
+
+	err = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fp_mode, 0,
+				 sizeof(fp_mode));
+	if (err)
+		return err;
+
+	if (count > 0)
+		err = mips_set_process_fp_mode(target, fp_mode);
+
+	return err;
+}
+
 enum mips_regset {
 	REGSET_GPR,
 	REGSET_FPR,
 	REGSET_DSP,
+	REGSET_FP_MODE,
 };
 
 struct pt_regs_offset {
@@ -877,6 +924,14 @@ static const struct user_regset mips_regsets[] = {
 		.set		= dsp32_set,
 		.active		= dsp_active,
 	},
+	[REGSET_FP_MODE] = {
+		.core_note_type	= NT_MIPS_FP_MODE,
+		.n		= 1,
+		.size		= sizeof(int),
+		.align		= sizeof(int),
+		.get		= fp_mode_get,
+		.set		= fp_mode_set,
+	},
 };
 
 static const struct user_regset_view user_mips_view = {
@@ -917,6 +972,14 @@ static const struct user_regset mips64_regsets[] = {
 		.set		= dsp64_set,
 		.active		= dsp_active,
 	},
+	[REGSET_FP_MODE] = {
+		.core_note_type	= NT_MIPS_FP_MODE,
+		.n		= 1,
+		.size		= sizeof(int),
+		.align		= sizeof(int),
+		.get		= fp_mode_get,
+		.set		= fp_mode_set,
+	},
 };
 
 static const struct user_regset_view user_mips64_view = {
diff --git a/include/uapi/linux/elf.h b/include/uapi/linux/elf.h
index e326c99b3881..c5358e0ae7c5 100644
--- a/include/uapi/linux/elf.h
+++ b/include/uapi/linux/elf.h
@@ -423,6 +423,7 @@ typedef struct elf64_shdr {
 #define NT_ARC_V2	0x600		/* ARCv2 accumulator/extra registers */
 #define NT_VMCOREDD	0x700		/* Vmcore Device Dump Note */
 #define NT_MIPS_DSP	0x800		/* MIPS DSP ASE registers */
+#define NT_MIPS_FP_MODE	0x801		/* MIPS floating-point mode */
 
 /* Note header in a PT_NOTE section */
 typedef struct elf32_note {
-- 
cgit v1.2.3


From a8222a84cefa9d3595a14cf076bc8c09287bf16c Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 17:09:52 +0200
Subject: mtd: Make Kconfig formatting consistent

Fix indentation and replace '---help---' by 'help' to make things
consistent.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/Kconfig         | 24 ++++++++++++------------
 drivers/mtd/chips/Kconfig   |  2 +-
 drivers/mtd/devices/Kconfig |  4 ++--
 drivers/mtd/lpddr/Kconfig   |  8 ++++----
 drivers/mtd/maps/Kconfig    | 24 ++++++++++++------------
 5 files changed, 31 insertions(+), 31 deletions(-)

diff --git a/drivers/mtd/Kconfig b/drivers/mtd/Kconfig
index 46ab7feec6b6..c77f537323ec 100644
--- a/drivers/mtd/Kconfig
+++ b/drivers/mtd/Kconfig
@@ -24,7 +24,7 @@ config MTD_TESTS
 
 config MTD_REDBOOT_PARTS
 	tristate "RedBoot partition table parsing"
-	---help---
+	help
 	  RedBoot is a ROM monitor and bootloader which deals with multiple
 	  'images' in flash devices by putting a table one of the erase
 	  blocks on the device, similar to a partition table, which gives
@@ -45,7 +45,7 @@ if MTD_REDBOOT_PARTS
 config MTD_REDBOOT_DIRECTORY_BLOCK
 	int "Location of RedBoot partition table"
 	default "-1"
-	---help---
+	help
 	  This option is the Linux counterpart to the
 	  CYGNUM_REDBOOT_FIS_DIRECTORY_BLOCK RedBoot compile time
 	  option.
@@ -75,7 +75,7 @@ endif # MTD_REDBOOT_PARTS
 config MTD_CMDLINE_PARTS
 	tristate "Command line partition table parsing"
 	depends on MTD
-	---help---
+	help
 	  Allow generic configuration of the MTD partition tables via the kernel
 	  command line. Multiple flash resources are supported for hardware where
 	  different kinds of flash memory are available.
@@ -112,7 +112,7 @@ config MTD_CMDLINE_PARTS
 config MTD_AFS_PARTS
 	tristate "ARM Firmware Suite partition parsing"
 	depends on (ARM || ARM64)
-	---help---
+	help
 	  The ARM Firmware Suite allows the user to divide flash devices into
 	  multiple 'images'. Each such image has a header containing its name
 	  and offset/size etc.
@@ -136,7 +136,7 @@ config MTD_OF_PARTS
 
 config MTD_AR7_PARTS
 	tristate "TI AR7 partitioning support"
-	---help---
+	help
 	  TI AR7 partitioning support
 
 config MTD_BCM63XX_PARTS
@@ -170,7 +170,7 @@ config MTD_BLOCK
 	tristate "Caching block device access to MTD devices"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  Although most flash chips have an erase size too large to be useful
 	  as block devices, it is possible to use MTD devices which are based
 	  on RAM chips in this manner. This block device is a user of MTD
@@ -205,7 +205,7 @@ config FTL
 	tristate "FTL (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the original Flash Translation Layer which
 	  is part of the PCMCIA specification. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -222,7 +222,7 @@ config NFTL
 	tristate "NFTL (NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the NAND Flash Translation Layer which is
 	  used on M-Systems' DiskOnChip devices. It uses a kind of pseudo-
 	  file system on a flash device to emulate a block device with
@@ -246,7 +246,7 @@ config INFTL
 	tristate "INFTL (Inverse NAND Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the Inverse NAND Flash Translation
 	  Layer which is used on M-Systems' newer DiskOnChip devices. It
 	  uses a kind of pseudo-file system on a flash device to emulate
@@ -261,10 +261,10 @@ config INFTL
 	  not use it.
 
 config RFD_FTL
-        tristate "Resident Flash Disk (Flash Translation Layer) support"
+	tristate "Resident Flash Disk (Flash Translation Layer) support"
 	depends on BLOCK
 	select MTD_BLKDEVS
-	---help---
+	help
 	  This provides support for the flash translation layer known
 	  as the Resident Flash Disk (RFD), as used by the Embedded BIOS
 	  of General Software. There is a blurb at:
@@ -308,7 +308,7 @@ config MTD_SWAP
 	select MTD_BLKDEVS
 	help
 	  Provides volatile block device driver on top of mtd partition
-          suitable for swapping.  The mapping of written blocks is not saved.
+	  suitable for swapping.  The mapping of written blocks is not saved.
 	  The driver provides wear leveling by storing erase counter into the
 	  OOB.
 
diff --git a/drivers/mtd/chips/Kconfig b/drivers/mtd/chips/Kconfig
index bbfa1f129266..39ec32a29051 100644
--- a/drivers/mtd/chips/Kconfig
+++ b/drivers/mtd/chips/Kconfig
@@ -44,7 +44,7 @@ choice
 	prompt "Flash cmd/query data swapping"
 	depends on MTD_CFI_ADV_OPTIONS
 	default MTD_CFI_NOSWAP
-	---help---
+	help
 	  This option defines the way in which the CPU attempts to arrange
 	  data bits when writing the 'magic' commands to the chips. Saying
 	  'NO', which is the default when CONFIG_MTD_CFI_ADV_OPTIONS isn't
diff --git a/drivers/mtd/devices/Kconfig b/drivers/mtd/devices/Kconfig
index 57b02c4b3f63..e514d57a0419 100644
--- a/drivers/mtd/devices/Kconfig
+++ b/drivers/mtd/devices/Kconfig
@@ -5,7 +5,7 @@ menu "Self-contained MTD device drivers"
 config MTD_PMC551
 	tristate "Ramix PMC551 PCI Mezzanine RAM card support"
 	depends on PCI
-	---help---
+	help
 	  This provides a MTD device driver for the Ramix PMC551 RAM PCI card
 	  from Ramix Inc. <http://www.ramix.com/products/memory/pmc551.html>.
 	  These devices come in memory configurations from 32M - 1G.  If you
@@ -209,7 +209,7 @@ config MTD_DOCG3
 	select BCH
 	select BCH_CONST_PARAMS
 	select BITREVERSE
-	---help---
+	help
 	  This provides an MTD device driver for the M-Systems DiskOnChip
 	  G3 devices.
 
diff --git a/drivers/mtd/lpddr/Kconfig b/drivers/mtd/lpddr/Kconfig
index 3a19cbee24d7..a5a332fbd593 100644
--- a/drivers/mtd/lpddr/Kconfig
+++ b/drivers/mtd/lpddr/Kconfig
@@ -13,10 +13,10 @@ config MTD_QINFO_PROBE
 	depends on MTD_LPDDR
 	tristate "Detect flash chips by QINFO probe"
 	help
-	    Device Information for LPDDR chips is offered through the Overlay
-	    Window QINFO interface, permits software to be used for entire
-	    families of devices. This serves similar purpose of CFI on legacy
-	    Flash products
+	  Device Information for LPDDR chips is offered through the Overlay
+	  Window QINFO interface, permits software to be used for entire
+	  families of devices. This serves similar purpose of CFI on legacy
+	  Flash products
 
 config MTD_LPDDR2_NVM
 	# ARM dependency is only for writel_relaxed()
diff --git a/drivers/mtd/maps/Kconfig b/drivers/mtd/maps/Kconfig
index bdc1283f30fb..afb36bff13a7 100644
--- a/drivers/mtd/maps/Kconfig
+++ b/drivers/mtd/maps/Kconfig
@@ -207,13 +207,13 @@ config MTD_ICHXROM
 	  BE VERY CAREFUL.
 
 config MTD_ESB2ROM
-        tristate "BIOS flash chip on Intel ESB Controller Hub 2"
-        depends on X86 && MTD_JEDECPROBE && PCI
-        help
-          Support for treating the BIOS flash chip on ESB2 motherboards
-          as an MTD device - with this you can reprogram your BIOS.
+	tristate "BIOS flash chip on Intel ESB Controller Hub 2"
+	depends on X86 && MTD_JEDECPROBE && PCI
+	help
+	  Support for treating the BIOS flash chip on ESB2 motherboards
+	  as an MTD device - with this you can reprogram your BIOS.
 
-          BE VERY CAREFUL.
+	  BE VERY CAREFUL.
 
 config MTD_CK804XROM
 	tristate "BIOS flash chip on Nvidia CK804"
@@ -401,12 +401,12 @@ config MTD_PISMO
 	  When built as a module, it will be called pismo.ko
 
 config MTD_LATCH_ADDR
-        tristate "Latch-assisted Flash Chip Support"
-        depends on MTD_COMPLEX_MAPPINGS
-        help
-          Map driver which allows flashes to be partially physically addressed
-          and have the upper address lines set by a board specific code.
+	tristate "Latch-assisted Flash Chip Support"
+	depends on MTD_COMPLEX_MAPPINGS
+	help
+	  Map driver which allows flashes to be partially physically addressed
+	  and have the upper address lines set by a board specific code.
 
-          If compiled as a module, it will be called latch-addr-flash.
+	  If compiled as a module, it will be called latch-addr-flash.
 
 endmenu
-- 
cgit v1.2.3


From d70420bcd447e5400a0116b20b9b6088bb32448e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jul 2018 22:33:02 +0200
Subject: mtd: adapt misleading comment in mtd_oob_ops structure

A comment in the kernel doc of the mtd_oob_ops structure tells that it
is not possible to write more than one page with OOB. This is actually
true for only a few MTD devices like 'onenand' but it is definitely not
a general limitation. While this would benefit to be handled elsewhere
either by the MTD layer or by the limited drivers, let's update this
comment to reflect the reality.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 include/linux/mtd/mtd.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index a86c4fa93115..cd0be91bdefa 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -67,9 +67,11 @@ struct mtd_erase_region_info {
  * @datbuf:	data buffer - if NULL only oob data are read/written
  * @oobbuf:	oob data buffer
  *
- * Note, it is allowed to read more than one OOB area at one go, but not write.
- * The interface assumes that the OOB write requests program only one page's
- * OOB area.
+ * Note, some MTD drivers do not allow you to write more than one OOB area at
+ * one go. If you try to do that on such an MTD device, -EINVAL will be
+ * returned. If you want to make your implementation portable on all kind of MTD
+ * devices you should split the write request into several sub-requests when the
+ * request crosses a page boundary.
  */
 struct mtd_oob_ops {
 	unsigned int	mode;
-- 
cgit v1.2.3


From 72b77bb018b3e913504fdb0a0612135e5391521e Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 19 Jul 2018 09:37:20 +0200
Subject: mtd: rawnand: jz4740: Use the proper format specifier to print chipnr

In jz_nand_detect_bank(), chipnr is a size_t argument. Use %zu instead
of %i when printing it.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/jz4740_nand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index a0254461812d..c5dea83b9ea0 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -355,7 +355,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 		mtd->size += chip->chipsize;
 	}
 
-	dev_info(&pdev->dev, "Found chip %i on bank %i\n", chipnr, bank);
+	dev_info(&pdev->dev, "Found chip %zu on bank %i\n", chipnr, bank);
 	return 0;
 
 notfound_id:
-- 
cgit v1.2.3


From ab99e11062c187533db08078ccae799faed8873e Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Mon, 9 Jul 2018 22:09:45 +0200
Subject: memory: jz4780-nemc: Allow selection of this driver when
 COMPILE_TEST=y

It just makes maintainers' life easier by allowing them to compile-test
this driver without having MACH_JZ4780 enabled.

We also need to add a dependency on HAS_IOMEM to make sure the
driver compiles correctly.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/memory/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index 78457ab2cbc4..a642552dfdc9 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -122,7 +122,8 @@ config FSL_IFC
 config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
 	default y
-	depends on MACH_JZ4780
+	depends on MACH_JZ4780 || COMPILE_TEST
+	depends on HAS_IOMEM
 	help
 	  This driver is for the NAND/External Memory Controller (NEMC) in
 	  the Ingenic JZ4780. This controller is used to handle external
-- 
cgit v1.2.3


From c2204734bb50899764129ed5568b8d5aa013c8fb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 11 Jul 2018 10:39:44 +0200
Subject: mtd: rawnand: MTD_NAND_BCM47XXNFLASH needs CONFIG_BCMA

We already have a dependency on BCMA_NFLASH, which in turn depends on
BCMA, but since BCMA is a tristate option and BCMA_NFLASH is bool,
we can run into an invalid configuration with MTD_NAND_BCM47XXNFLASH=y
and BCMA=m:

drivers/mtd/nand/raw/bcm47xxnflash/ops_bcm4706.o: In function `bcm47xxnflash_ops_bcm4706_init':
ops_bcm4706.c:(.text+0x790): undefined reference to `bcma_chipco_pll_read'

Adding the dependency here forces MTD_NAND_BCM47XXNFLASH to only be
configured =m here so it can link against the BCMA driver.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index d495759c94ac..b6738ece16f1 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -365,6 +365,7 @@ config MTD_NAND_BRCMNAND
 config MTD_NAND_BCM47XXNFLASH
 	tristate "Support for NAND flash on BCM4706 BCMA bus"
 	depends on BCMA_NFLASH
+	depends on BCMA
 	help
 	  BCMA bus can have various flash memories attached, they are
 	  registered by bcma as platform devices. This enables driver for
-- 
cgit v1.2.3


From 29597ca14dee1611eafbc09ae0c6bd756687105f Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 13 Jul 2018 11:27:31 +0200
Subject: mtd: rawnand: use mtd_device_register() where applicable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If driver doesn't specify parsers it can use that little helper.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Acked-by: Xiaolei Li <xiaolei.li@mediatek.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cmx270_nand.c  | 4 ++--
 drivers/mtd/nand/raw/cs553x_nand.c  | 3 +--
 drivers/mtd/nand/raw/davinci_nand.c | 3 +--
 drivers/mtd/nand/raw/jz4740_nand.c  | 5 ++---
 drivers/mtd/nand/raw/mtk_nand.c     | 2 +-
 drivers/mtd/nand/raw/s3c2410.c      | 4 ++--
 drivers/mtd/nand/raw/txx9ndfmc.c    | 2 +-
 7 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/mtd/nand/raw/cmx270_nand.c b/drivers/mtd/nand/raw/cmx270_nand.c
index 02d6751e9efe..b66e254b6802 100644
--- a/drivers/mtd/nand/raw/cmx270_nand.c
+++ b/drivers/mtd/nand/raw/cmx270_nand.c
@@ -200,8 +200,8 @@ static int __init cmx270_init(void)
 	}
 
 	/* Register the partitions */
-	ret = mtd_device_parse_register(cmx270_nand_mtd, NULL, NULL,
-					partition_info, NUM_PARTITIONS);
+	ret = mtd_device_register(cmx270_nand_mtd, partition_info,
+				  NUM_PARTITIONS);
 	if (ret)
 		goto err_scan;
 
diff --git a/drivers/mtd/nand/raw/cs553x_nand.c b/drivers/mtd/nand/raw/cs553x_nand.c
index 82269fde9e66..beafad62e7d5 100644
--- a/drivers/mtd/nand/raw/cs553x_nand.c
+++ b/drivers/mtd/nand/raw/cs553x_nand.c
@@ -310,8 +310,7 @@ static int __init cs553x_init(void)
 	for (i = 0; i < NR_CS553X_CONTROLLERS; i++) {
 		if (cs553x_mtd[i]) {
 			/* If any devices registered, return success. Else the last error. */
-			mtd_device_parse_register(cs553x_mtd[i], NULL, NULL,
-						  NULL, 0);
+			mtd_device_register(cs553x_mtd[i], NULL, 0);
 			err = 0;
 		}
 	}
diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index e79ed0f60ade..626c9363e460 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -800,8 +800,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 		goto err;
 
 	if (pdata->parts)
-		ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata->parts, pdata->nr_parts);
+		ret = mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
 	else
 		ret = mtd_device_register(mtd, NULL, 0);
 	if (ret < 0)
diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index c5dea83b9ea0..9bb8a89e09f9 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -466,9 +466,8 @@ static int jz_nand_probe(struct platform_device *pdev)
 		goto err_unclaim_banks;
 	}
 
-	ret = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->partitions : NULL,
-					pdata ? pdata->num_partitions : 0);
+	ret = mtd_device_register(mtd, pdata ? pdata->partitions : NULL,
+				  pdata ? pdata->num_partitions : 0);
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mtd device\n");
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 75c845adb050..e6b14b79c8a8 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -1357,7 +1357,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 	if (ret)
 		return ret;
 
-	ret = mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "mtd parse partition error\n");
 		nand_release(mtd);
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 19661c5d3220..10d81f367d26 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -802,8 +802,8 @@ static int s3c2410_nand_add_partition(struct s3c2410_nand_info *info,
 
 		mtdinfo->name = set->name;
 
-		return mtd_device_parse_register(mtdinfo, NULL, NULL,
-					 set->partitions, set->nr_partitions);
+		return mtd_device_register(mtdinfo, set->partitions,
+					   set->nr_partitions);
 	}
 
 	return -ENODEV;
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 04d57474ef97..5fe9da8b4a0a 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -366,7 +366,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		}
 		mtd->name = txx9_priv->mtdname;
 
-		mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+		mtd_device_register(mtd, NULL, 0);
 		drvdata->mtds[i] = mtd;
 	}
 
-- 
cgit v1.2.3


From e8b0ac398f5ec16b249f5243d8011d490e3b91c0 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 13 Jul 2018 11:27:32 +0200
Subject: mtd: onenand: use mtd_device_register() where applicable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If driver doesn't specify parsers it can use that little helper.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/onenand/generic.c | 5 ++---
 drivers/mtd/nand/onenand/samsung.c | 5 ++---
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/mtd/nand/onenand/generic.c b/drivers/mtd/nand/onenand/generic.c
index d5ccaf943b91..acad17ec6581 100644
--- a/drivers/mtd/nand/onenand/generic.c
+++ b/drivers/mtd/nand/onenand/generic.c
@@ -66,9 +66,8 @@ static int generic_onenand_probe(struct platform_device *pdev)
 		goto out_iounmap;
 	}
 
-	err = mtd_device_parse_register(&info->mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(&info->mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 
 	platform_set_drvdata(pdev, info);
 
diff --git a/drivers/mtd/nand/onenand/samsung.c b/drivers/mtd/nand/onenand/samsung.c
index 4cce4c0311ca..e64d0fdf7eb5 100644
--- a/drivers/mtd/nand/onenand/samsung.c
+++ b/drivers/mtd/nand/onenand/samsung.c
@@ -933,9 +933,8 @@ static int s3c_onenand_probe(struct platform_device *pdev)
 	if (s3c_read_reg(MEM_CFG_OFFSET) & ONENAND_SYS_CFG1_SYNC_READ)
 		dev_info(&onenand->pdev->dev, "OneNAND Sync. Burst Read enabled\n");
 
-	err = mtd_device_parse_register(mtd, NULL, NULL,
-					pdata ? pdata->parts : NULL,
-					pdata ? pdata->nr_parts : 0);
+	err = mtd_device_register(mtd, pdata ? pdata->parts : NULL,
+				  pdata ? pdata->nr_parts : 0);
 	if (err) {
 		dev_err(&pdev->dev, "failed to parse partitions and register the MTD device\n");
 		onenand_release(mtd);
-- 
cgit v1.2.3


From 6a943386ee364155727f62711f6f3e898d824cdd Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Sat, 14 Jul 2018 12:23:54 +0200
Subject: mtd: rawnand: add default values for dynamic timings

Some timings like tBERS (block erase time), tCCs (change column setup
time), tPROG (page program time) and tR (page read time) are derived
from the ONFI parameter page. They are set in the SDR interface only
if the chip is ONFI compliant.

It makes these timings unreliable and prevent the driver to use one of
these four values with a non-ONFI chip.

Fix this situation by taking the highest possible value (or a default
one) value for each missing timing (stored as unsigned 16-bit entries in
the parameter page).

This makes tBERS and tPROG being ~65ms while typical values are at most
a few milliseconds. As these are timeouts, it is not impacting at all
the performances in nominal use.

tR maximum time and tCCS minimum time (delay to wait after a change
column) are set, according to the ONFI specification, to default 'slow'
values; respectively 200us and 500ns.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_timings.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index 7c4e4a371bbc..9bb599106a31 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -13,6 +13,8 @@
 #include <linux/export.h>
 #include <linux/mtd/rawnand.h>
 
+#define ONFI_DYN_TIMING_MAX U16_MAX
+
 static const struct nand_data_interface onfi_sdr_timings[] = {
 	/* Mode 0 */
 	{
@@ -303,7 +305,7 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 
 	/*
 	 * Initialize timings that cannot be deduced from timing mode:
-	 * tR, tPROG, tCCS, ...
+	 * tPROG, tBERS, tR and tCCS.
 	 * These information are part of the ONFI parameter page.
 	 */
 	if (chip->parameters.onfi.version) {
@@ -317,6 +319,22 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 
 		/* nanoseconds -> picoseconds */
 		timings->tCCS_min = 1000UL * params->onfi.tCCS;
+	} else {
+		struct nand_sdr_timings *timings = &iface->timings.sdr;
+		/*
+		 * For non-ONFI chips we use the highest possible value for
+		 * tPROG and tBERS. tR and tCCS will take the default values
+		 * precised in the ONFI specification for timing mode 0,
+		 * respectively 200us and 500ns.
+		 */
+
+		/* microseconds -> picoseconds */
+		timings->tPROG_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tBERS_max = 1000000ULL * ONFI_DYN_TIMING_MAX;
+		timings->tR_max = 1000000ULL * 200000000ULL;
+
+		/* nanoseconds -> picoseconds */
+		timings->tCCS_min = 1000UL * 500000;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From d535934a9ad4dc435884958ac44a7d6ecb6278ce Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Tue, 17 Jul 2018 10:46:18 +0200
Subject: mtd: rawnand: tegra: check bounds of die_nr properly

The Tegra driver currently only support a single chip select, hence
check boundaries accordingly. This fixes a off by one issue catched
with Smatch:
    drivers/mtd/nand/raw/tegra_nand.c:476 tegra_nand_select_chip()
    warn: array off by one? 'nand->cs[die_nr]'

Also warn in case the stack asks for a chip select we currently do
not support.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/tegra_nand.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 9f7de36be893..56c0aa1bc81f 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -468,7 +468,9 @@ static void tegra_nand_select_chip(struct mtd_info *mtd, int die_nr)
 	struct tegra_nand_chip *nand = to_tegra_chip(chip);
 	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
 
-	if (die_nr < 0 || die_nr > 1) {
+	WARN_ON(die_nr >= (int)ARRAY_SIZE(nand->cs));
+
+	if (die_nr < 0 || die_nr > 0) {
 		ctrl->cur_cs = -1;
 		return;
 	}
-- 
cgit v1.2.3


From 7330fc505af4af262ef874a4fc4492393106fdce Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 17 Jul 2018 22:27:42 +0200
Subject: mtd: rawnand: qcom: stop using phys_to_dma()

Compile-testing this driver on x86 caused a link error:

ERROR: "__phys_to_dma" [drivers/mtd/nand/raw/qcom_nandc.ko] undefined!

The problem here is that the driver attempts to convert the physical
address into the DMA controller as a dma_addr_t and calls phys_to_dma()
to do the conversion.

The correct way to do the conversion is using the dma mapping interfaces.

Fixes: c76b78d8ec05 ("mtd: nand: Qualcomm NAND controller driver")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 994f980c6d86..645630953f38 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2957,14 +2957,6 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 
 	nandc->props = dev_data;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nandc->base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(nandc->base))
-		return PTR_ERR(nandc->base);
-
-	nandc->base_phys = res->start;
-	nandc->base_dma = phys_to_dma(dev, (phys_addr_t)res->start);
-
 	nandc->core_clk = devm_clk_get(dev, "core");
 	if (IS_ERR(nandc->core_clk))
 		return PTR_ERR(nandc->core_clk);
@@ -2977,9 +2969,21 @@ static int qcom_nandc_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nandc->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(nandc->base))
+		return PTR_ERR(nandc->base);
+
+	nandc->base_phys = res->start;
+	nandc->base_dma = dma_map_resource(dev, res->start,
+					   resource_size(res),
+					   DMA_BIDIRECTIONAL, 0);
+	if (!nandc->base_dma)
+		return -ENXIO;
+
 	ret = qcom_nandc_alloc(nandc);
 	if (ret)
-		goto err_core_clk;
+		goto err_nandc_alloc;
 
 	ret = clk_prepare_enable(nandc->core_clk);
 	if (ret)
@@ -3005,6 +3009,9 @@ err_aon_clk:
 	clk_disable_unprepare(nandc->core_clk);
 err_core_clk:
 	qcom_nandc_unalloc(nandc);
+err_nandc_alloc:
+	dma_unmap_resource(dev, res->start, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
 
 	return ret;
 }
@@ -3012,16 +3019,21 @@ err_core_clk:
 static int qcom_nandc_remove(struct platform_device *pdev)
 {
 	struct qcom_nand_controller *nandc = platform_get_drvdata(pdev);
+	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	struct qcom_nand_host *host;
 
 	list_for_each_entry(host, &nandc->host_list, node)
 		nand_release(nand_to_mtd(&host->chip));
 
+
 	qcom_nandc_unalloc(nandc);
 
 	clk_disable_unprepare(nandc->aon_clk);
 	clk_disable_unprepare(nandc->core_clk);
 
+	dma_unmap_resource(&pdev->dev, nandc->base_dma, resource_size(res),
+			   DMA_BIDIRECTIONAL, 0);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From 79e1ca37cc0c056f224cc1dd4a301b9dc2f94167 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:28:14 +0200
Subject: mtd: rawnand: fsmc: Stop using chip->read_buf()

chip->read_buf is left unassigned since commit 4da712e70294 ("mtd: nand:
fsmc: use ->exec_op()"), leading to a NULL pointer dereference when it's
called from fsmc_read_page_hwecc(). Fix that by using the appropriate
helper to read data out of the NAND.

Fixes: 4da712e70294 ("mtd: nand: fsmc: use ->exec_op()")
Cc: <stable@vger.kernel.org>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/fsmc_nand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 527bebc7e6c9..59524d181bfe 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -741,7 +741,7 @@ static int fsmc_read_page_hwecc(struct mtd_info *mtd, struct nand_chip *chip,
 	for (i = 0, s = 0; s < eccsteps; s++, i += eccbytes, p += eccsize) {
 		nand_read_page_op(chip, page, s * eccsize, NULL, 0);
 		chip->ecc.hwctl(mtd, NAND_ECC_READ);
-		chip->read_buf(mtd, p, eccsize);
+		nand_read_data_op(chip, p, eccsize, false);
 
 		for (j = 0; j < eccbytes;) {
 			struct mtd_oob_region oobregion;
-- 
cgit v1.2.3


From dbc44edbf8338d27639214be07fe7ab4f8a903e0 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:42:15 +0200
Subject: mtd: rawnand: micron: Fix on-die ECC detection logic

Basing the "mandatory on-die" detection on ID byte 2 does not work,
because Micron has plenty of NANDs using the same device ID code, and
not all of them have forcibly enabled on-die ECC.

Since the "Array Operation" feature does not provide the "ECC
enabled/disabled" bit when the ECC can't be disabled, let's try to use
the "ECC enabled/disabled" bit in the READ_ID bytes.

It seems that this bit is dynamically updated on NANDs where on-die ECC
can freely be enabled/disabled, so let's hope it stays at one when we
have a NAND with on-die ECC forcibly enabled.

Fixes: 51f3b3970a8c ("mtd: rawnand: micron: detect forced on-die ECC")
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 32 +++++++++++++++++++++++---------
 1 file changed, 23 insertions(+), 9 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index d30bd4df9b12..d85bb4d42686 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -196,6 +196,9 @@ enum {
 	MICRON_ON_DIE_MANDATORY,
 };
 
+#define MICRON_ID_INTERNAL_ECC_MASK	GENMASK(1, 0)
+#define MICRON_ID_ECC_ENABLED		BIT(7)
+
 /*
  * Try to detect if the NAND support on-die ECC. To do this, we enable
  * the feature, and read back if it has been enabled as expected. We
@@ -208,7 +211,7 @@ enum {
  */
 static int micron_supports_on_die_ecc(struct nand_chip *chip)
 {
-	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	u8 id[5];
 	int ret;
 
 	if (!chip->parameters.onfi.version)
@@ -217,26 +220,37 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip)
 	if (chip->bits_per_cell != 1)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
+	/*
+	 * We only support on-die ECC of 4/512 or 8/512
+	 */
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
+	/* 0x2 means on-die ECC is available. */
+	if (chip->id.len != 5 ||
+	    (chip->id.data[4] & MICRON_ID_INTERNAL_ECC_MASK) != 0x2)
+		return MICRON_ON_DIE_UNSUPPORTED;
+
 	ret = micron_nand_on_die_ecc_setup(chip, true);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if ((feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN) == 0)
+	if (!(id[4] & MICRON_ID_ECC_ENABLED))
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	ret = micron_nand_on_die_ecc_setup(chip, false);
 	if (ret)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
-	ret = nand_get_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
-	if (ret < 0)
-		return ret;
+	ret = nand_readid_op(chip, 0, id, sizeof(id));
+	if (ret)
+		return MICRON_ON_DIE_UNSUPPORTED;
 
-	if (feature[0] & ONFI_FEATURE_ON_DIE_ECC_EN)
+	if (id[4] & MICRON_ID_ECC_ENABLED)
 		return MICRON_ON_DIE_MANDATORY;
 
 	/*
-- 
cgit v1.2.3


From 3ec7cb369eb22a5a06f9867e358bc55d40055168 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Wed, 18 Jul 2018 10:42:16 +0200
Subject: mtd: rawnand: micron: support 8/512 on-die ECC

Micron MT29F1G08ABAFAWP-ITE:F supports an on-die ECC with 8 bits
per 512 bytes. Add support for this combination.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 161 ++++++++++++++++++++++++++++++-------
 1 file changed, 131 insertions(+), 30 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index d85bb4d42686..f8839c7f7464 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -18,10 +18,30 @@
 #include <linux/mtd/rawnand.h>
 
 /*
- * Special Micron status bit that indicates when the block has been
- * corrected by on-die ECC and should be rewritten
+ * Special Micron status bit 3 indicates that the block has been
+ * corrected by on-die ECC and should be rewritten.
  */
-#define NAND_STATUS_WRITE_RECOMMENDED	BIT(3)
+#define NAND_ECC_STATUS_WRITE_RECOMMENDED	BIT(3)
+
+/*
+ * On chips with 8-bit ECC and additional bit can be used to distinguish
+ * cases where a errors were corrected without needing a rewrite
+ *
+ * Bit 4 Bit 3 Bit 0 Description
+ * ----- ----- ----- -----------
+ * 0     0     0     No Errors
+ * 0     0     1     Multiple uncorrected errors
+ * 0     1     0     4 - 6 errors corrected, recommend rewrite
+ * 0     1     1     Reserved
+ * 1     0     0     1 - 3 errors corrected
+ * 1     0     1     Reserved
+ * 1     1     0     7 - 8 errors corrected, recommend rewrite
+ */
+#define NAND_ECC_STATUS_MASK		(BIT(4) | BIT(3) | BIT(0))
+#define NAND_ECC_STATUS_UNCORRECTABLE	BIT(0)
+#define NAND_ECC_STATUS_4_6_CORRECTED	BIT(3)
+#define NAND_ECC_STATUS_1_3_CORRECTED	BIT(4)
+#define NAND_ECC_STATUS_7_8_CORRECTED	(BIT(4) | BIT(3))
 
 struct nand_onfi_vendor_micron {
 	u8 two_plane_read;
@@ -74,8 +94,9 @@ static int micron_nand_onfi_init(struct nand_chip *chip)
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
-					    struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -86,8 +107,9 @@ static int micron_nand_on_die_ooblayout_ecc(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
-					     struct mtd_oob_region *oobregion)
+static int micron_nand_on_die_4_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
 {
 	if (section >= 4)
 		return -ERANGE;
@@ -98,9 +120,44 @@ static int micron_nand_on_die_ooblayout_free(struct mtd_info *mtd, int section,
 	return 0;
 }
 
-static const struct mtd_ooblayout_ops micron_nand_on_die_ooblayout_ops = {
-	.ecc = micron_nand_on_die_ooblayout_ecc,
-	.free = micron_nand_on_die_ooblayout_free,
+static const struct mtd_ooblayout_ops micron_nand_on_die_4_ooblayout_ops = {
+	.ecc = micron_nand_on_die_4_ooblayout_ecc,
+	.free = micron_nand_on_die_4_ooblayout_free,
+};
+
+static int micron_nand_on_die_8_ooblayout_ecc(struct mtd_info *mtd,
+					      int section,
+					      struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = mtd->oobsize - chip->ecc.total;
+	oobregion->length = chip->ecc.total;
+
+	return 0;
+}
+
+static int micron_nand_on_die_8_ooblayout_free(struct mtd_info *mtd,
+					       int section,
+					       struct mtd_oob_region *oobregion)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+
+	if (section)
+		return -ERANGE;
+
+	oobregion->offset = 2;
+	oobregion->length = mtd->oobsize - chip->ecc.total - 2;
+
+	return 0;
+}
+
+static const struct mtd_ooblayout_ops micron_nand_on_die_8_ooblayout_ops = {
+	.ecc = micron_nand_on_die_8_ooblayout_ecc,
+	.free = micron_nand_on_die_8_ooblayout_free,
 };
 
 static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
@@ -113,6 +170,55 @@ static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
 	return nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
 }
 
+static int micron_nand_on_die_ecc_status_4(struct nand_chip *chip, u8 status)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	/*
+	 * The internal ECC doesn't tell us the number of bitflips
+	 * that have been corrected, but tells us if it recommends to
+	 * rewrite the block. If it's the case, then we pretend we had
+	 * a number of bitflips equal to the ECC strength, which will
+	 * hint the NAND core to rewrite the block.
+	 */
+	if (status & NAND_STATUS_FAIL) {
+		mtd->ecc_stats.failed++;
+	} else if (status & NAND_ECC_STATUS_WRITE_RECOMMENDED) {
+		mtd->ecc_stats.corrected += chip->ecc.strength;
+		return chip->ecc.strength;
+	}
+
+	return 0;
+}
+
+static int micron_nand_on_die_ecc_status_8(struct nand_chip *chip, u8 status)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	/*
+	 * With 8/512 we have more information but still don't know precisely
+	 * how many bit-flips were seen.
+	 */
+	switch (status & NAND_ECC_STATUS_MASK) {
+	case NAND_ECC_STATUS_UNCORRECTABLE:
+		mtd->ecc_stats.failed++;
+		return 0;
+	case NAND_ECC_STATUS_1_3_CORRECTED:
+		mtd->ecc_stats.corrected += 3;
+		return 3;
+	case NAND_ECC_STATUS_4_6_CORRECTED:
+		mtd->ecc_stats.corrected += 6;
+		/* rewrite recommended */
+		return 6;
+	case NAND_ECC_STATUS_7_8_CORRECTED:
+		mtd->ecc_stats.corrected += 8;
+		/* rewrite recommended */
+		return 8;
+	default:
+		return 0;
+	}
+}
+
 static int
 micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
 				 uint8_t *buf, int oob_required,
@@ -137,19 +243,10 @@ micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
 	if (ret)
 		goto out;
 
-	if (status & NAND_STATUS_FAIL) {
-		mtd->ecc_stats.failed++;
-	} else if (status & NAND_STATUS_WRITE_RECOMMENDED) {
-		/*
-		 * The internal ECC doesn't tell us the number of bitflips
-		 * that have been corrected, but tells us if it recommends to
-		 * rewrite the block. If it's the case, then we pretend we had
-		 * a number of bitflips equal to the ECC strength, which will
-		 * hint the NAND core to rewrite the block.
-		 */
-		mtd->ecc_stats.corrected += chip->ecc.strength;
-		max_bitflips = chip->ecc.strength;
-	}
+	if (chip->ecc.strength == 4)
+		max_bitflips = micron_nand_on_die_ecc_status_4(chip, status);
+	else
+		max_bitflips = micron_nand_on_die_ecc_status_8(chip, status);
 
 	ret = nand_read_data_op(chip, buf, mtd->writesize, false);
 	if (!ret && oob_required)
@@ -254,10 +351,9 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip)
 		return MICRON_ON_DIE_MANDATORY;
 
 	/*
-	 * Some Micron NANDs have an on-die ECC of 4/512, some other
-	 * 8/512. We only support the former.
+	 * We only support on-die ECC of 4/512 or 8/512
 	 */
-	if (chip->ecc_strength_ds != 4)
+	if  (chip->ecc_strength_ds != 4 && chip->ecc_strength_ds != 8)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	return MICRON_ON_DIE_SUPPORTED;
@@ -289,16 +385,21 @@ static int micron_nand_init(struct nand_chip *chip)
 			return -EINVAL;
 		}
 
-		chip->ecc.bytes = 8;
+		if (chip->ecc_strength_ds == 4)
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_4_ooblayout_ops);
+		else
+			mtd_set_ooblayout(mtd,
+					  &micron_nand_on_die_8_ooblayout_ops);
+
+		chip->ecc.bytes = chip->ecc_strength_ds * 2;
 		chip->ecc.size = 512;
-		chip->ecc.strength = 4;
+		chip->ecc.strength = chip->ecc_strength_ds;
 		chip->ecc.algo = NAND_ECC_BCH;
 		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
 		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
 		chip->ecc.read_page_raw = nand_read_page_raw;
 		chip->ecc.write_page_raw = nand_write_page_raw;
-
-		mtd_set_ooblayout(mtd, &micron_nand_on_die_ooblayout_ops);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 0d6030ac041f6835974deb88a1a9c299b4adc3ad Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:42:17 +0200
Subject: mtd: rawnand: Expose _notsupp() helpers for raw page accessors

Some implementations simply can't disable their ECC engine. Expose
helpers returning -ENOTSUPP so that the caller knows that raw accesses
are not supported instead of silently falling back to non-raw
accessors.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 33 +++++++++++++++++++++++++++++++++
 include/linux/mtd/rawnand.h      |  4 ++++
 2 files changed, 37 insertions(+)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 4fa5e20d9690..c4b74630f4c5 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -2966,6 +2966,23 @@ int nand_check_erased_ecc_chunk(void *data, int datalen,
 }
 EXPORT_SYMBOL(nand_check_erased_ecc_chunk);
 
+/**
+ * nand_read_page_raw_notsupp - dummy read raw page function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: buffer to store read data
+ * @oob_required: caller requires OOB data read to chip->oob_poi
+ * @page: page number to read
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+			       u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_read_page_raw_notsupp);
+
 /**
  * nand_read_page_raw - [INTERN] read raw page data without ecc
  * @mtd: mtd info structure
@@ -3960,6 +3977,22 @@ static int nand_read_oob(struct mtd_info *mtd, loff_t from,
 	return ret;
 }
 
+/**
+ * nand_write_page_raw_notsupp - dummy raw page write function
+ * @mtd: mtd info structure
+ * @chip: nand chip info structure
+ * @buf: data buffer
+ * @oob_required: must write chip->oob_poi to OOB
+ * @page: page number to write
+ *
+ * Returns -ENOTSUPP unconditionally.
+ */
+int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+				const u8 *buf, int oob_required, int page)
+{
+	return -ENOTSUPP;
+}
+EXPORT_SYMBOL(nand_write_page_raw_notsupp);
 
 /**
  * nand_write_page_raw - [INTERN] raw page write function
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 11c2426fc363..f60fad29eae6 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1681,10 +1681,14 @@ int nand_get_set_features_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
 /* Default read_page_raw implementation */
 int nand_read_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 		       uint8_t *buf, int oob_required, int page);
+int nand_read_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+			       u8 *buf, int oob_required, int page);
 
 /* Default write_page_raw implementation */
 int nand_write_page_raw(struct mtd_info *mtd, struct nand_chip *chip,
 			const uint8_t *buf, int oob_required, int page);
+int nand_write_page_raw_notsupp(struct mtd_info *mtd, struct nand_chip *chip,
+				const u8 *buf, int oob_required, int page);
 
 /* Reset and initialize a NAND device */
 int nand_reset(struct nand_chip *chip, int chipnr);
-- 
cgit v1.2.3


From cb2bf403a462082a253fe0a94cfec020285ffbd8 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Wed, 18 Jul 2018 10:42:18 +0200
Subject: mtd: rawnand: micron: allow forced on-die ECC

Some Micron NAND chips have on-die ECC forceably enabled. Allow such
chips to be used as long as the controller has set chip->ecc.mode to
NAND_ECC_ON_DIE.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index f8839c7f7464..fd3f68e0909f 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -374,7 +374,8 @@ static int micron_nand_init(struct nand_chip *chip)
 
 	ondie = micron_supports_on_die_ecc(chip);
 
-	if (ondie == MICRON_ON_DIE_MANDATORY) {
+	if (ondie == MICRON_ON_DIE_MANDATORY &&
+	    chip->ecc.mode != NAND_ECC_ON_DIE) {
 		pr_err("On-die ECC forcefully enabled, not supported\n");
 		return -EINVAL;
 	}
@@ -398,8 +399,14 @@ static int micron_nand_init(struct nand_chip *chip)
 		chip->ecc.algo = NAND_ECC_BCH;
 		chip->ecc.read_page = micron_nand_read_page_on_die_ecc;
 		chip->ecc.write_page = micron_nand_write_page_on_die_ecc;
-		chip->ecc.read_page_raw = nand_read_page_raw;
-		chip->ecc.write_page_raw = nand_write_page_raw;
+
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
+			chip->ecc.read_page_raw = nand_read_page_raw_notsupp;
+			chip->ecc.write_page_raw = nand_write_page_raw_notsupp;
+		} else {
+			chip->ecc.read_page_raw = nand_read_page_raw;
+			chip->ecc.write_page_raw = nand_write_page_raw;
+		}
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 2301780711efc514a8bb183e853bda8decce746a Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:42:19 +0200
Subject: mtd: rawnand: micron: Get the actual number of bitflips

The MT29F2Gxxx chips with 4bits/512byte on-die ECC let us know when
some bitflips were corrected by the on-die ECC, but they do not report
the actual number of bitflips that were present in the data+ECC chunk.

We initially decided to always return ecc->strength to avoid re-reading
the page in raw mode + comparing it to the corrected buffer to extract
the real number of bitflips, but this forces UBI to move data around as
soon as one bitflip is present in a page.

This not only wears the NAND out faster, but also degrades
performances, since reading a full PEB + writing it back to a different
PEB + erasing the old one is much more expensive than re-reading the
faulty page in raw mode and comparing it to the corrected buffer.
In most cases, the actual number of bitflips does not exceed the
bitflips threshold, and UBI won't have to move data around. Otherwise,
we can assume the time spent re-reading the page and doing the
comparison is negligible compared to the time UBI spends moving a full
PEB to another PEB.

Note that this logic is not applied to chips with 8bits/512byte on-die
ECC, because those chips provide fine-grained information (the maximum
error is 1 bit, and it will not force UBI to move blocks around at the
first bitflip).

Suggested-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 139 +++++++++++++++++++++++++++++++------
 1 file changed, 119 insertions(+), 20 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index fd3f68e0909f..2cff25f7b48b 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -16,6 +16,7 @@
  */
 
 #include <linux/mtd/rawnand.h>
+#include <linux/slab.h>
 
 /*
  * Special Micron status bit 3 indicates that the block has been
@@ -63,6 +64,14 @@ struct nand_onfi_vendor_micron {
 	u8 param_revision;
 } __packed;
 
+struct micron_on_die_ecc {
+	void *rawbuf;
+};
+
+struct micron_nand {
+	struct micron_on_die_ecc ecc;
+};
+
 static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -170,25 +179,71 @@ static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
 	return nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
 }
 
-static int micron_nand_on_die_ecc_status_4(struct nand_chip *chip, u8 status)
+static int micron_nand_on_die_ecc_status_4(struct nand_chip *chip, u8 status,
+					   void *buf, int page,
+					   int oob_required)
 {
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	unsigned int step, max_bitflips = 0;
+	int ret;
+
+	if (!(status & NAND_ECC_STATUS_WRITE_RECOMMENDED)) {
+		if (status & NAND_STATUS_FAIL)
+			mtd->ecc_stats.failed++;
+
+		return 0;
+	}
 
 	/*
-	 * The internal ECC doesn't tell us the number of bitflips
-	 * that have been corrected, but tells us if it recommends to
-	 * rewrite the block. If it's the case, then we pretend we had
-	 * a number of bitflips equal to the ECC strength, which will
-	 * hint the NAND core to rewrite the block.
+	 * The internal ECC doesn't tell us the number of bitflips that have
+	 * been corrected, but tells us if it recommends to rewrite the block.
+	 * If it's the case, we need to read the page in raw mode and compare
+	 * its content to the corrected version to extract the actual number of
+	 * bitflips.
+	 * But before we do that, we must make sure we have all OOB bytes read
+	 * in non-raw mode, even if the user did not request those bytes.
 	 */
-	if (status & NAND_STATUS_FAIL) {
-		mtd->ecc_stats.failed++;
-	} else if (status & NAND_ECC_STATUS_WRITE_RECOMMENDED) {
-		mtd->ecc_stats.corrected += chip->ecc.strength;
-		return chip->ecc.strength;
+	if (!oob_required) {
+		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
+					false);
+		if (ret)
+			return ret;
 	}
 
-	return 0;
+	micron_nand_on_die_ecc_setup(chip, false);
+
+	ret = nand_read_page_op(chip, page, 0, micron->ecc.rawbuf,
+				mtd->writesize + mtd->oobsize);
+	if (ret)
+		return ret;
+
+	for (step = 0; step < chip->ecc.steps; step++) {
+		unsigned int offs, i, nbitflips = 0;
+		u8 *rawbuf, *corrbuf;
+
+		offs = step * chip->ecc.size;
+		rawbuf = micron->ecc.rawbuf + offs;
+		corrbuf = buf + offs;
+
+		for (i = 0; i < chip->ecc.size; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		offs = (step * 16) + 4;
+		rawbuf = micron->ecc.rawbuf + mtd->writesize + offs;
+		corrbuf = chip->oob_poi + offs;
+
+		for (i = 0; i < chip->ecc.bytes + 4; i++)
+			nbitflips += hweight8(corrbuf[i] ^ rawbuf[i]);
+
+		if (WARN_ON(nbitflips > chip->ecc.strength))
+			return -EINVAL;
+
+		max_bitflips = max(nbitflips, max_bitflips);
+		mtd->ecc_stats.corrected += nbitflips;
+	}
+
+	return max_bitflips;
 }
 
 static int micron_nand_on_die_ecc_status_8(struct nand_chip *chip, u8 status)
@@ -243,16 +298,18 @@ micron_nand_read_page_on_die_ecc(struct mtd_info *mtd, struct nand_chip *chip,
 	if (ret)
 		goto out;
 
-	if (chip->ecc.strength == 4)
-		max_bitflips = micron_nand_on_die_ecc_status_4(chip, status);
-	else
-		max_bitflips = micron_nand_on_die_ecc_status_8(chip, status);
-
 	ret = nand_read_data_op(chip, buf, mtd->writesize, false);
 	if (!ret && oob_required)
 		ret = nand_read_data_op(chip, chip->oob_poi, mtd->oobsize,
 					false);
 
+	if (chip->ecc.strength == 4)
+		max_bitflips = micron_nand_on_die_ecc_status_4(chip, status,
+							       buf, page,
+							       oob_required);
+	else
+		max_bitflips = micron_nand_on_die_ecc_status_8(chip, status);
+
 out:
 	micron_nand_on_die_ecc_setup(chip, false);
 
@@ -362,12 +419,19 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip)
 static int micron_nand_init(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct micron_nand *micron;
 	int ondie;
 	int ret;
 
+	micron = kzalloc(sizeof(*micron), GFP_KERNEL);
+	if (!micron)
+		return -ENOMEM;
+
+	nand_set_manufacturer_data(chip, micron);
+
 	ret = micron_nand_onfi_init(chip);
 	if (ret)
-		return ret;
+		goto err_free_manuf_data;
 
 	if (mtd->writesize == 2048)
 		chip->bbt_options |= NAND_BBT_SCAN2NDPAGE;
@@ -377,13 +441,33 @@ static int micron_nand_init(struct nand_chip *chip)
 	if (ondie == MICRON_ON_DIE_MANDATORY &&
 	    chip->ecc.mode != NAND_ECC_ON_DIE) {
 		pr_err("On-die ECC forcefully enabled, not supported\n");
-		return -EINVAL;
+		ret = -EINVAL;
+		goto err_free_manuf_data;
 	}
 
 	if (chip->ecc.mode == NAND_ECC_ON_DIE) {
 		if (ondie == MICRON_ON_DIE_UNSUPPORTED) {
 			pr_err("On-die ECC selected but not supported\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_free_manuf_data;
+		}
+
+		/*
+		 * In case of 4bit on-die ECC, we need a buffer to store a
+		 * page dumped in raw mode so that we can compare its content
+		 * to the same page after ECC correction happened and extract
+		 * the real number of bitflips from this comparison.
+		 * That's not needed for 8-bit ECC, because the status expose
+		 * a better approximation of the number of bitflips in a page.
+		 */
+		if (chip->ecc_strength_ds == 4) {
+			micron->ecc.rawbuf = kmalloc(mtd->writesize +
+						     mtd->oobsize,
+						     GFP_KERNEL);
+			if (!micron->ecc.rawbuf) {
+				ret = -ENOMEM;
+				goto err_free_manuf_data;
+			}
 		}
 
 		if (chip->ecc_strength_ds == 4)
@@ -410,6 +494,20 @@ static int micron_nand_init(struct nand_chip *chip)
 	}
 
 	return 0;
+
+err_free_manuf_data:
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
+
+	return ret;
+}
+
+static void micron_nand_cleanup(struct nand_chip *chip)
+{
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
+
+	kfree(micron->ecc.rawbuf);
+	kfree(micron);
 }
 
 static void micron_fixup_onfi_param_page(struct nand_chip *chip,
@@ -426,5 +524,6 @@ static void micron_fixup_onfi_param_page(struct nand_chip *chip,
 
 const struct nand_manufacturer_ops micron_nand_manuf_ops = {
 	.init = micron_nand_init,
+	.cleanup = micron_nand_cleanup,
 	.fixup_onfi_param_page = micron_fixup_onfi_param_page,
 };
-- 
cgit v1.2.3


From ef422e1ecd272d077efce64432907632758cf2e2 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:42:20 +0200
Subject: mtd: rawnand: micron: Avoid enabling/disabling ECC when it can't be
 disabled

Some chips have their on-die ECC forcibly enabled, there's no point in
trying to enable/disable the ECC engine in that case.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 2cff25f7b48b..9d13b701e581 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -65,6 +65,7 @@ struct nand_onfi_vendor_micron {
 } __packed;
 
 struct micron_on_die_ecc {
+	bool forced;
 	void *rawbuf;
 };
 
@@ -171,8 +172,12 @@ static const struct mtd_ooblayout_ops micron_nand_on_die_8_ooblayout_ops = {
 
 static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
 {
+	struct micron_nand *micron = nand_get_manufacturer_data(chip);
 	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
 
+	if (micron->ecc.forced)
+		return 0;
+
 	if (enable)
 		feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN;
 
@@ -452,6 +457,9 @@ static int micron_nand_init(struct nand_chip *chip)
 			goto err_free_manuf_data;
 		}
 
+		if (ondie == MICRON_ON_DIE_MANDATORY)
+			micron->ecc.forced = true;
+
 		/*
 		 * In case of 4bit on-die ECC, we need a buffer to store a
 		 * page dumped in raw mode so that we can compare its content
-- 
cgit v1.2.3


From 317c6d9b69eb2dcab2ca4759a2c1c04496ec1591 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:42:21 +0200
Subject: mtd: rawnand: micron: Make ECC activation stateful

We currently don't store the on-die ECC state (enabled/disabled) which
might force us to re-disable the engine even if it's already been
disabled after we've read the page in raw mode to count the actual
number of bitflips.

Add an "enabled" field to struct micron_on_die_ecc to keep track of the
ECC state.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Tested-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_micron.c | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 9d13b701e581..656947d91841 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -66,6 +66,7 @@ struct nand_onfi_vendor_micron {
 
 struct micron_on_die_ecc {
 	bool forced;
+	bool enabled;
 	void *rawbuf;
 };
 
@@ -174,14 +175,22 @@ static int micron_nand_on_die_ecc_setup(struct nand_chip *chip, bool enable)
 {
 	struct micron_nand *micron = nand_get_manufacturer_data(chip);
 	u8 feature[ONFI_SUBFEATURE_PARAM_LEN] = { 0, };
+	int ret;
 
 	if (micron->ecc.forced)
 		return 0;
 
+	if (micron->ecc.enabled == enable)
+		return 0;
+
 	if (enable)
 		feature[0] |= ONFI_FEATURE_ON_DIE_ECC_EN;
 
-	return nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	ret = nand_set_features(chip, ONFI_FEATURE_ON_DIE_ECC, feature);
+	if (!ret)
+		micron->ecc.enabled = enable;
+
+	return ret;
 }
 
 static int micron_nand_on_die_ecc_status_4(struct nand_chip *chip, u8 status,
@@ -457,8 +466,10 @@ static int micron_nand_init(struct nand_chip *chip)
 			goto err_free_manuf_data;
 		}
 
-		if (ondie == MICRON_ON_DIE_MANDATORY)
+		if (ondie == MICRON_ON_DIE_MANDATORY) {
 			micron->ecc.forced = true;
+			micron->ecc.enabled = true;
+		}
 
 		/*
 		 * In case of 4bit on-die ECC, we need a buffer to store a
-- 
cgit v1.2.3


From 1e4511604dfaf6d1642603ff89effb9e93682716 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Thu, 19 Jul 2018 16:16:55 -0500
Subject: PCI/AER: Expose internal API for obtaining AER information

Export some common AER functions and structures for other PCI core drivers
to use.  Since this is making the function externally visible inside the
PCI core, prepend "aer_" to the function name.

Signed-off-by: Keith Busch <keith.busch@intel.com>
[bhelgaas: move AER declarations from linux/aer.h to drivers/pci/pci.h]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pci.h      | 28 ++++++++++++++++++++++++++++
 drivers/pci/pcie/aer.c | 30 +++++-------------------------
 2 files changed, 33 insertions(+), 25 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c358e7a07f3f..4f723442f602 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -300,6 +300,34 @@ static inline bool pci_dev_is_disconnected(const struct pci_dev *dev)
 	return test_bit(PCI_DEV_DISCONNECTED, &dev->priv_flags);
 }
 
+#ifdef CONFIG_PCIEAER
+#include <linux/aer.h>
+
+#define AER_MAX_MULTI_ERR_DEVICES	5	/* Not likely to have more */
+
+struct aer_err_info {
+	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
+	int error_dev_num;
+
+	unsigned int id:16;
+
+	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
+	unsigned int __pad1:5;
+	unsigned int multi_error_valid:1;
+
+	unsigned int first_error:5;
+	unsigned int __pad2:2;
+	unsigned int tlp_header_valid:1;
+
+	unsigned int status;		/* COR/UNCOR Error Status */
+	unsigned int mask;		/* COR/UNCOR Error Mask */
+	struct aer_header_log_regs tlp;	/* TLP Header */
+};
+
+int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info);
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info);
+#endif	/* CONFIG_PCIEAER */
+
 #ifdef CONFIG_PCI_ATS
 void pci_restore_ats_state(struct pci_dev *dev);
 #else
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index a2e88386af28..0a60275f0582 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -31,26 +31,6 @@
 #include "portdrv.h"
 
 #define AER_ERROR_SOURCES_MAX		100
-#define AER_MAX_MULTI_ERR_DEVICES	5	/* Not likely to have more */
-
-struct aer_err_info {
-	struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES];
-	int error_dev_num;
-
-	unsigned int id:16;
-
-	unsigned int severity:2;	/* 0:NONFATAL | 1:FATAL | 2:COR */
-	unsigned int __pad1:5;
-	unsigned int multi_error_valid:1;
-
-	unsigned int first_error:5;
-	unsigned int __pad2:2;
-	unsigned int tlp_header_valid:1;
-
-	unsigned int status;		/* COR/UNCOR Error Status */
-	unsigned int mask;		/* COR/UNCOR Error Mask */
-	struct aer_header_log_regs tlp;	/* TLP Header */
-};
 
 struct aer_err_source {
 	unsigned int status;
@@ -547,7 +527,7 @@ static void __aer_print_error(struct pci_dev *dev,
 	}
 }
 
-static void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
+void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int layer, agent;
 	int id = ((dev->bus->number << 8) | dev->devfn);
@@ -876,7 +856,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue);
 #endif
 
 /**
- * get_device_error_info - read error status from dev and store it to info
+ * aer_get_device_error_info - read error status from dev and store it to info
  * @dev: pointer to the device expected to have a error record
  * @info: pointer to structure to store the error record
  *
@@ -884,7 +864,7 @@ EXPORT_SYMBOL_GPL(aer_recover_queue);
  *
  * Note that @info is reused among all error devices. Clear fields properly.
  */
-static int get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
+int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info)
 {
 	int pos, temp;
 
@@ -942,11 +922,11 @@ static inline void aer_process_err_devices(struct aer_err_info *e_info)
 
 	/* Report all before handle them, not to lost records by reset etc. */
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (get_device_error_info(e_info->dev[i], e_info))
+		if (aer_get_device_error_info(e_info->dev[i], e_info))
 			aer_print_error(e_info->dev[i], e_info);
 	}
 	for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) {
-		if (get_device_error_info(e_info->dev[i], e_info))
+		if (aer_get_device_error_info(e_info->dev[i], e_info))
 			handle_error_source(e_info->dev[i], e_info);
 	}
 }
-- 
cgit v1.2.3


From bd237801fef230cea8f2a5ab550d500f19f856d8 Mon Sep 17 00:00:00 2001
From: Tyler Baicar <tbaicar@codeaurora.org>
Date: Tue, 26 Jun 2018 11:44:15 -0400
Subject: PCI/AER: Adopt lspci names for AER error decoding

lspci uses abbreviated naming for AER error strings.  Adopt the same naming
convention for the AER printing so they match.

Signed-off-by: Tyler Baicar <tbaicar@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/aer.c | 46 +++++++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 0a60275f0582..e6d5255d718c 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -439,22 +439,22 @@ static const char *aer_error_layer[] = {
 };
 
 static const char *aer_correctable_error_string[] = {
-	"Receiver Error",		/* Bit Position 0	*/
+	"RxErr",			/* Bit Position 0	*/
 	NULL,
 	NULL,
 	NULL,
 	NULL,
 	NULL,
-	"Bad TLP",			/* Bit Position 6	*/
-	"Bad DLLP",			/* Bit Position 7	*/
-	"RELAY_NUM Rollover",		/* Bit Position 8	*/
+	"BadTLP",			/* Bit Position 6	*/
+	"BadDLLP",			/* Bit Position 7	*/
+	"Rollover",			/* Bit Position 8	*/
 	NULL,
 	NULL,
 	NULL,
-	"Replay Timer Timeout",		/* Bit Position 12	*/
-	"Advisory Non-Fatal",		/* Bit Position 13	*/
-	"Corrected Internal Error",	/* Bit Position 14	*/
-	"Header Log Overflow",		/* Bit Position 15	*/
+	"Timeout",			/* Bit Position 12	*/
+	"NonFatalErr",			/* Bit Position 13	*/
+	"CorrIntErr",			/* Bit Position 14	*/
+	"HeaderOF",			/* Bit Position 15	*/
 };
 
 static const char *aer_uncorrectable_error_string[] = {
@@ -462,28 +462,28 @@ static const char *aer_uncorrectable_error_string[] = {
 	NULL,
 	NULL,
 	NULL,
-	"Data Link Protocol",		/* Bit Position 4	*/
-	"Surprise Down Error",		/* Bit Position 5	*/
+	"DLP",				/* Bit Position 4	*/
+	"SDES",				/* Bit Position 5	*/
 	NULL,
 	NULL,
 	NULL,
 	NULL,
 	NULL,
 	NULL,
-	"Poisoned TLP",			/* Bit Position 12	*/
-	"Flow Control Protocol",	/* Bit Position 13	*/
-	"Completion Timeout",		/* Bit Position 14	*/
-	"Completer Abort",		/* Bit Position 15	*/
-	"Unexpected Completion",	/* Bit Position 16	*/
-	"Receiver Overflow",		/* Bit Position 17	*/
-	"Malformed TLP",		/* Bit Position 18	*/
+	"TLP",				/* Bit Position 12	*/
+	"FCP",				/* Bit Position 13	*/
+	"CmpltTO",			/* Bit Position 14	*/
+	"CmpltAbrt",			/* Bit Position 15	*/
+	"UnxCmplt",			/* Bit Position 16	*/
+	"RxOF",				/* Bit Position 17	*/
+	"MalfTLP",			/* Bit Position 18	*/
 	"ECRC",				/* Bit Position 19	*/
-	"Unsupported Request",		/* Bit Position 20	*/
-	"ACS Violation",		/* Bit Position 21	*/
-	"Uncorrectable Internal Error",	/* Bit Position 22	*/
-	"MC Blocked TLP",		/* Bit Position 23	*/
-	"AtomicOp Egress Blocked",	/* Bit Position 24	*/
-	"TLP Prefix Blocked Error",	/* Bit Position 25	*/
+	"UnsupReq",			/* Bit Position 20	*/
+	"ACSViol",			/* Bit Position 21	*/
+	"UncorrIntErr",			/* Bit Position 22	*/
+	"BlockedTLP",			/* Bit Position 23	*/
+	"AtomicOpBlocked",		/* Bit Position 24	*/
+	"TLPBlockedErr",		/* Bit Position 25	*/
 };
 
 static const char *aer_agent_string[] = {
-- 
cgit v1.2.3


From 60ed982a4e78ff938824a750dbac8a10e5b472ef Mon Sep 17 00:00:00 2001
From: Rajat Jain <rajatja@google.com>
Date: Thu, 21 Jun 2018 16:48:26 -0700
Subject: PCI/AER: Move internal declarations to drivers/pci/pci.h

Since pci_aer_init() and pci_no_aer() are used only internally, move their
declarations to the PCI internal header file.  Also, no one cares about
return value of pci_aer_init(), so make it void.

Signed-off-by: Rajat Jain <rajatja@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      | 8 ++++++++
 drivers/pci/pcie/aer.c | 4 ++--
 include/linux/pci.h    | 4 ----
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 4f723442f602..52bc5b350dfb 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -480,4 +480,12 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev,
 }
 #endif
 
+#ifdef CONFIG_PCIEAER
+void pci_no_aer(void);
+void pci_aer_init(struct pci_dev *dev);
+#else
+static inline void pci_no_aer(void) { }
+static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
+#endif
+
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index e6d5255d718c..0c6fe22eaf75 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -382,10 +382,10 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 	return 0;
 }
 
-int pci_aer_init(struct pci_dev *dev)
+void pci_aer_init(struct pci_dev *dev)
 {
 	dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
-	return pci_cleanup_aer_error_status_regs(dev);
+	pci_cleanup_aer_error_status_regs(dev);
 }
 
 #define AER_AGENT_RECEIVER		0
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..b4ffea05c999 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1468,13 +1468,9 @@ static inline bool pcie_aspm_support_enabled(void) { return false; }
 #endif
 
 #ifdef CONFIG_PCIEAER
-void pci_no_aer(void);
 bool pci_aer_available(void);
-int pci_aer_init(struct pci_dev *dev);
 #else
-static inline void pci_no_aer(void) { }
 static inline bool pci_aer_available(void) { return false; }
-static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
 #endif
 
 #ifdef CONFIG_PCIE_ECRC
-- 
cgit v1.2.3


From db89ccbe52c7885644ba578c7771e57620f879b1 Mon Sep 17 00:00:00 2001
From: Rajat Jain <rajatja@google.com>
Date: Sat, 30 Jun 2018 15:07:17 -0500
Subject: PCI/AER: Define aer_stats structure for AER capable devices

Define a structure to hold the AER statistics.  There are 2 groups of
statistics: dev_* counters that are to be collected for all AER capable
devices and rootport_* counters that are collected for all (AER capable)
rootports only.  Allocate and free this structure when device is added or
released (thus counters survive the lifetime of the device).

Signed-off-by: Rajat Jain <rajatja@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      |  2 ++
 drivers/pci/pcie/aer.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++--
 drivers/pci/probe.c    |  1 +
 include/linux/pci.h    |  1 +
 4 files changed, 55 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 52bc5b350dfb..1877a14e06a9 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -483,9 +483,11 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev,
 #ifdef CONFIG_PCIEAER
 void pci_no_aer(void);
 void pci_aer_init(struct pci_dev *dev);
+void pci_aer_exit(struct pci_dev *dev);
 #else
 static inline void pci_no_aer(void) { }
 static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
+static inline void pci_aer_exit(struct pci_dev *d) { }
 #endif
 
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 0c6fe22eaf75..fe1b9d22a331 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -32,6 +32,9 @@
 
 #define AER_ERROR_SOURCES_MAX		100
 
+#define AER_MAX_TYPEOF_COR_ERRS		16	/* as per PCI_ERR_COR_STATUS */
+#define AER_MAX_TYPEOF_UNCOR_ERRS	26	/* as per PCI_ERR_UNCOR_STATUS*/
+
 struct aer_err_source {
 	unsigned int status;
 	unsigned int id;
@@ -56,6 +59,42 @@ struct aer_rpc {
 					 */
 };
 
+/* AER stats for the device */
+struct aer_stats {
+
+	/*
+	 * Fields for all AER capable devices. They indicate the errors
+	 * "as seen by this device". Note that this may mean that if an
+	 * end point is causing problems, the AER counters may increment
+	 * at its link partner (e.g. root port) because the errors will be
+	 * "seen" by the link partner and not the the problematic end point
+	 * itself (which may report all counters as 0 as it never saw any
+	 * problems).
+	 */
+	/* Counters for different type of correctable errors */
+	u64 dev_cor_errs[AER_MAX_TYPEOF_COR_ERRS];
+	/* Counters for different type of fatal uncorrectable errors */
+	u64 dev_fatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS];
+	/* Counters for different type of nonfatal uncorrectable errors */
+	u64 dev_nonfatal_errs[AER_MAX_TYPEOF_UNCOR_ERRS];
+	/* Total number of ERR_COR sent by this device */
+	u64 dev_total_cor_errs;
+	/* Total number of ERR_FATAL sent by this device */
+	u64 dev_total_fatal_errs;
+	/* Total number of ERR_NONFATAL sent by this device */
+	u64 dev_total_nonfatal_errs;
+
+	/*
+	 * Fields for Root ports & root complex event collectors only, these
+	 * indicate the total number of ERR_COR, ERR_FATAL, and ERR_NONFATAL
+	 * messages received by the root port / event collector, INCLUDING the
+	 * ones that are generated internally (by the rootport itself)
+	 */
+	u64 rootport_total_cor_errs;
+	u64 rootport_total_fatal_errs;
+	u64 rootport_total_nonfatal_errs;
+};
+
 #define AER_LOG_TLP_MASKS		(PCI_ERR_UNC_POISON_TLP|	\
 					PCI_ERR_UNC_ECRC|		\
 					PCI_ERR_UNC_UNSUP|		\
@@ -385,9 +424,19 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 void pci_aer_init(struct pci_dev *dev)
 {
 	dev->aer_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+
+	if (dev->aer_cap)
+		dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL);
+
 	pci_cleanup_aer_error_status_regs(dev);
 }
 
+void pci_aer_exit(struct pci_dev *dev)
+{
+	kfree(dev->aer_stats);
+	dev->aer_stats = NULL;
+}
+
 #define AER_AGENT_RECEIVER		0
 #define AER_AGENT_REQUESTER		1
 #define AER_AGENT_COMPLETER		2
@@ -438,7 +487,7 @@ static const char *aer_error_layer[] = {
 	"Transaction Layer"
 };
 
-static const char *aer_correctable_error_string[] = {
+static const char *aer_correctable_error_string[AER_MAX_TYPEOF_COR_ERRS] = {
 	"RxErr",			/* Bit Position 0	*/
 	NULL,
 	NULL,
@@ -457,7 +506,7 @@ static const char *aer_correctable_error_string[] = {
 	"HeaderOF",			/* Bit Position 15	*/
 };
 
-static const char *aer_uncorrectable_error_string[] = {
+static const char *aer_uncorrectable_error_string[AER_MAX_TYPEOF_UNCOR_ERRS] = {
 	"Undefined",			/* Bit Position 0	*/
 	NULL,
 	NULL,
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..48edd0c9e4bc 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2064,6 +2064,7 @@ static void pci_configure_device(struct pci_dev *dev)
 
 static void pci_release_capabilities(struct pci_dev *dev)
 {
+	pci_aer_exit(dev);
 	pci_vpd_release(dev);
 	pci_iov_release(dev);
 	pci_free_cap_save_buffers(dev);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index b4ffea05c999..6bc0aa0fc33f 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -299,6 +299,7 @@ struct pci_dev {
 	u8		hdr_type;	/* PCI header type (`multi' flag masked out) */
 #ifdef CONFIG_PCIEAER
 	u16		aer_cap;	/* AER capability offset */
+	struct aer_stats *aer_stats;	/* AER stats for this device */
 #endif
 	u8		pcie_cap;	/* PCIe capability offset */
 	u8		msi_cap;	/* MSI capability offset */
-- 
cgit v1.2.3


From 81aa5206f9a7c9793e2f7971400351664e40b04f Mon Sep 17 00:00:00 2001
From: Rajat Jain <rajatja@google.com>
Date: Thu, 21 Jun 2018 16:48:28 -0700
Subject: PCI/AER: Add sysfs attributes to provide AER stats and breakdown

Add sysfs attributes to provide total and breakdown of the AERs seen,
into different type of correctable, fatal and nonfatal errors:

  /sys/bus/pci/devices/<dev>/aer_dev_correctable
  /sys/bus/pci/devices/<dev>/aer_dev_fatal
  /sys/bus/pci/devices/<dev>/aer_dev_nonfatal

Signed-off-by: Rajat Jain <rajatja@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 .../ABI/testing/sysfs-bus-pci-devices-aer_stats    | 94 ++++++++++++++++++++++
 Documentation/PCI/pcieaer-howto.txt                |  5 ++
 drivers/pci/pci-sysfs.c                            |  3 +
 drivers/pci/pci.h                                  |  1 +
 drivers/pci/pcie/aer.c                             | 94 ++++++++++++++++++++++
 5 files changed, 197 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats

diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
new file mode 100644
index 000000000000..3a784297cfed
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
@@ -0,0 +1,94 @@
+==========================
+PCIe Device AER statistics
+==========================
+These attributes show up under all the devices that are AER capable. These
+statistical counters indicate the errors "as seen/reported by the device".
+Note that this may mean that if an endpoint is causing problems, the AER
+counters may increment at its link partner (e.g. root port) because the
+errors may be "seen" / reported by the link partner and not the
+problematic endpoint itself (which may report all counters as 0 as it never
+saw any problems).
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_correctable
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of correctable errors seen and reported by this
+		PCI device using ERR_COR. Note that since multiple errors may
+		be reported using a single ERR_COR message, thus
+		TOTAL_ERR_COR at the end of the file may not match the actual
+		total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_correctable
+Receiver Error 2
+Bad TLP 0
+Bad DLLP 0
+RELAY_NUM Rollover 0
+Replay Timer Timeout 0
+Advisory Non-Fatal 0
+Corrected Internal Error 0
+Header Log Overflow 0
+TOTAL_ERR_COR 2
+-------------------------------------------------------------------------
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_fatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of uncorrectable fatal errors seen and reported by this
+		PCI device using ERR_FATAL. Note that since multiple errors may
+		be reported using a single ERR_FATAL message, thus
+		TOTAL_ERR_FATAL at the end of the file may not match the actual
+		total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_fatal
+Undefined 0
+Data Link Protocol 0
+Surprise Down Error 0
+Poisoned TLP 0
+Flow Control Protocol 0
+Completion Timeout 0
+Completer Abort 0
+Unexpected Completion 0
+Receiver Overflow 0
+Malformed TLP 0
+ECRC 0
+Unsupported Request 0
+ACS Violation 0
+Uncorrectable Internal Error 0
+MC Blocked TLP 0
+AtomicOp Egress Blocked 0
+TLP Prefix Blocked Error 0
+TOTAL_ERR_FATAL 0
+-------------------------------------------------------------------------
+
+Where:		/sys/bus/pci/devices/<dev>/aer_dev_nonfatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	List of uncorrectable nonfatal errors seen and reported by this
+		PCI device using ERR_NONFATAL. Note that since multiple errors
+		may be reported using a single ERR_FATAL message, thus
+		TOTAL_ERR_NONFATAL at the end of the file may not match the
+		actual total of all the errors in the file. Sample output:
+-------------------------------------------------------------------------
+localhost /sys/devices/pci0000:00/0000:00:1c.0 # cat aer_dev_nonfatal
+Undefined 0
+Data Link Protocol 0
+Surprise Down Error 0
+Poisoned TLP 0
+Flow Control Protocol 0
+Completion Timeout 0
+Completer Abort 0
+Unexpected Completion 0
+Receiver Overflow 0
+Malformed TLP 0
+ECRC 0
+Unsupported Request 0
+ACS Violation 0
+Uncorrectable Internal Error 0
+MC Blocked TLP 0
+AtomicOp Egress Blocked 0
+TLP Prefix Blocked Error 0
+TOTAL_ERR_NONFATAL 0
+-------------------------------------------------------------------------
diff --git a/Documentation/PCI/pcieaer-howto.txt b/Documentation/PCI/pcieaer-howto.txt
index acd0dddd6bb8..48ce7903e3c6 100644
--- a/Documentation/PCI/pcieaer-howto.txt
+++ b/Documentation/PCI/pcieaer-howto.txt
@@ -73,6 +73,11 @@ In the example, 'Requester ID' means the ID of the device who sends
 the error message to root port. Pls. refer to pci express specs for
 other fields.
 
+2.4 AER Statistics / Counters
+
+When PCIe AER errors are captured, the counters / statistics are also exposed
+in the form of sysfs attributes which are documented at
+Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
 
 3. Developer Guide
 
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 0c4653c1d2ce..9f1cb9051d7d 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1746,6 +1746,9 @@ static const struct attribute_group *pci_dev_attr_groups[] = {
 #endif
 	&pci_bridge_attr_group,
 	&pcie_dev_attr_group,
+#ifdef CONFIG_PCIEAER
+	&aer_stats_attr_group,
+#endif
 	NULL,
 };
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 1877a14e06a9..b1ce0dcad1dc 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -484,6 +484,7 @@ static inline int devm_of_pci_get_host_bridge_resources(struct device *dev,
 void pci_no_aer(void);
 void pci_aer_init(struct pci_dev *dev);
 void pci_aer_exit(struct pci_dev *dev);
+extern const struct attribute_group aer_stats_attr_group;
 #else
 static inline void pci_no_aer(void) { }
 static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index fe1b9d22a331..b18c5aca30bd 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -542,6 +542,99 @@ static const char *aer_agent_string[] = {
 	"Transmitter ID"
 };
 
+#define aer_stats_dev_attr(name, stats_array, strings_array,		\
+			   total_string, total_field)			\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *attr,	\
+		     char *buf)						\
+{									\
+	unsigned int i;							\
+	char *str = buf;						\
+	struct pci_dev *pdev = to_pci_dev(dev);				\
+	u64 *stats = pdev->aer_stats->stats_array;			\
+									\
+	for (i = 0; i < ARRAY_SIZE(strings_array); i++) {		\
+		if (strings_array[i])					\
+			str += sprintf(str, "%s %llu\n",		\
+				       strings_array[i], stats[i]);	\
+		else if (stats[i])					\
+			str += sprintf(str, #stats_array "_bit[%d] %llu\n",\
+				       i, stats[i]);			\
+	}								\
+	str += sprintf(str, "TOTAL_%s %llu\n", total_string,		\
+		       pdev->aer_stats->total_field);			\
+	return str-buf;							\
+}									\
+static DEVICE_ATTR_RO(name)
+
+aer_stats_dev_attr(aer_dev_correctable, dev_cor_errs,
+		   aer_correctable_error_string, "ERR_COR",
+		   dev_total_cor_errs);
+aer_stats_dev_attr(aer_dev_fatal, dev_fatal_errs,
+		   aer_uncorrectable_error_string, "ERR_FATAL",
+		   dev_total_fatal_errs);
+aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs,
+		   aer_uncorrectable_error_string, "ERR_NONFATAL",
+		   dev_total_nonfatal_errs);
+
+static struct attribute *aer_stats_attrs[] __ro_after_init = {
+	&dev_attr_aer_dev_correctable.attr,
+	&dev_attr_aer_dev_fatal.attr,
+	&dev_attr_aer_dev_nonfatal.attr,
+	NULL
+};
+
+static umode_t aer_stats_attrs_are_visible(struct kobject *kobj,
+					   struct attribute *a, int n)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pci_dev *pdev = to_pci_dev(dev);
+
+	if (!pdev->aer_stats)
+		return 0;
+
+	return a->mode;
+}
+
+const struct attribute_group aer_stats_attr_group = {
+	.attrs  = aer_stats_attrs,
+	.is_visible = aer_stats_attrs_are_visible,
+};
+
+static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
+				   struct aer_err_info *info)
+{
+	int status, i, max = -1;
+	u64 *counter = NULL;
+	struct aer_stats *aer_stats = pdev->aer_stats;
+
+	if (!aer_stats)
+		return;
+
+	switch (info->severity) {
+	case AER_CORRECTABLE:
+		aer_stats->dev_total_cor_errs++;
+		counter = &aer_stats->dev_cor_errs[0];
+		max = AER_MAX_TYPEOF_COR_ERRS;
+		break;
+	case AER_NONFATAL:
+		aer_stats->dev_total_nonfatal_errs++;
+		counter = &aer_stats->dev_nonfatal_errs[0];
+		max = AER_MAX_TYPEOF_UNCOR_ERRS;
+		break;
+	case AER_FATAL:
+		aer_stats->dev_total_fatal_errs++;
+		counter = &aer_stats->dev_fatal_errs[0];
+		max = AER_MAX_TYPEOF_UNCOR_ERRS;
+		break;
+	}
+
+	status = (info->status & ~info->mask);
+	for (i = 0; i < max; i++)
+		if (status & (1 << i))
+			counter[i]++;
+}
+
 static void __print_tlp_header(struct pci_dev *dev,
 			       struct aer_header_log_regs *t)
 {
@@ -574,6 +667,7 @@ static void __aer_print_error(struct pci_dev *dev,
 			pci_err(dev, "   [%2d] Unknown Error Bit%s\n",
 				i, info->first_error == i ? " (First)" : "");
 	}
+	pci_dev_aer_stats_incr(dev, info);
 }
 
 void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
-- 
cgit v1.2.3


From 12833017e581c384afa35fb85ce540082b2d59fc Mon Sep 17 00:00:00 2001
From: Rajat Jain <rajatja@google.com>
Date: Thu, 21 Jun 2018 16:48:29 -0700
Subject: PCI/AER: Add sysfs attributes for rootport cumulative stats

Add sysfs attributes for rootport statistics (that are cumulative of all
the ERR_* messages seen on this PCI hierarchy).

Signed-off-by: Rajat Jain <rajatja@google.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 .../ABI/testing/sysfs-bus-pci-devices-aer_stats    | 28 +++++++++++++
 drivers/pci/pcie/aer.c                             | 47 ++++++++++++++++++++++
 2 files changed, 75 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
index 3a784297cfed..4b0318c99507 100644
--- a/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
+++ b/Documentation/ABI/testing/sysfs-bus-pci-devices-aer_stats
@@ -92,3 +92,31 @@ AtomicOp Egress Blocked 0
 TLP Prefix Blocked Error 0
 TOTAL_ERR_NONFATAL 0
 -------------------------------------------------------------------------
+
+============================
+PCIe Rootport AER statistics
+============================
+These attributes show up under only the rootports (or root complex event
+collectors) that are AER capable. These indicate the number of error messages as
+"reported to" the rootport. Please note that the rootports also transmit
+(internally) the ERR_* messages for errors seen by the internal rootport PCI
+device, so these counters include them and are thus cumulative of all the error
+messages on the PCI hierarchy originating at that root port.
+
+Where:		/sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_cor
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	Total number of ERR_COR messages reported to rootport.
+
+Where:	    /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_fatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	Total number of ERR_FATAL messages reported to rootport.
+
+Where:	    /sys/bus/pci/devices/<dev>/aer_stats/aer_rootport_total_err_nonfatal
+Date:		July 2018
+Kernel Version: 4.19.0
+Contact:	linux-pci@vger.kernel.org, rajatja@google.com
+Description:	Total number of ERR_NONFATAL messages reported to rootport.
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index b18c5aca30bd..47c67de1ccf1 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -577,10 +577,30 @@ aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs,
 		   aer_uncorrectable_error_string, "ERR_NONFATAL",
 		   dev_total_nonfatal_errs);
 
+#define aer_stats_rootport_attr(name, field)				\
+	static ssize_t							\
+	name##_show(struct device *dev, struct device_attribute *attr,	\
+		     char *buf)						\
+{									\
+	struct pci_dev *pdev = to_pci_dev(dev);				\
+	return sprintf(buf, "%llu\n", pdev->aer_stats->field);		\
+}									\
+static DEVICE_ATTR_RO(name)
+
+aer_stats_rootport_attr(aer_rootport_total_err_cor,
+			 rootport_total_cor_errs);
+aer_stats_rootport_attr(aer_rootport_total_err_fatal,
+			 rootport_total_fatal_errs);
+aer_stats_rootport_attr(aer_rootport_total_err_nonfatal,
+			 rootport_total_nonfatal_errs);
+
 static struct attribute *aer_stats_attrs[] __ro_after_init = {
 	&dev_attr_aer_dev_correctable.attr,
 	&dev_attr_aer_dev_fatal.attr,
 	&dev_attr_aer_dev_nonfatal.attr,
+	&dev_attr_aer_rootport_total_err_cor.attr,
+	&dev_attr_aer_rootport_total_err_fatal.attr,
+	&dev_attr_aer_rootport_total_err_nonfatal.attr,
 	NULL
 };
 
@@ -593,6 +613,12 @@ static umode_t aer_stats_attrs_are_visible(struct kobject *kobj,
 	if (!pdev->aer_stats)
 		return 0;
 
+	if ((a == &dev_attr_aer_rootport_total_err_cor.attr ||
+	     a == &dev_attr_aer_rootport_total_err_fatal.attr ||
+	     a == &dev_attr_aer_rootport_total_err_nonfatal.attr) &&
+	    pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT)
+		return 0;
+
 	return a->mode;
 }
 
@@ -635,6 +661,25 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev,
 			counter[i]++;
 }
 
+static void pci_rootport_aer_stats_incr(struct pci_dev *pdev,
+				 struct aer_err_source *e_src)
+{
+	struct aer_stats *aer_stats = pdev->aer_stats;
+
+	if (!aer_stats)
+		return;
+
+	if (e_src->status & PCI_ERR_ROOT_COR_RCV)
+		aer_stats->rootport_total_cor_errs++;
+
+	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
+		if (e_src->status & PCI_ERR_ROOT_FATAL_RCV)
+			aer_stats->rootport_total_fatal_errs++;
+		else
+			aer_stats->rootport_total_nonfatal_errs++;
+	}
+}
+
 static void __print_tlp_header(struct pci_dev *dev,
 			       struct aer_header_log_regs *t)
 {
@@ -1085,6 +1130,8 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 	struct pci_dev *pdev = rpc->rpd;
 	struct aer_err_info *e_info = &rpc->e_info;
 
+	pci_rootport_aer_stats_incr(pdev, e_src);
+
 	/*
 	 * There is a possibility that both correctable error and
 	 * uncorrectable error being logged. Report correctable error first.
-- 
cgit v1.2.3


From 7af02fcd84c16801958936f88b848944c726ca07 Mon Sep 17 00:00:00 2001
From: Alexandru Gagniuc <mr.nuke.me@gmail.com>
Date: Tue, 3 Jul 2018 18:27:43 -0500
Subject: PCI/AER: Honor "pcie_ports=native" even if HEST sets FIRMWARE_FIRST

According to the documentation, "pcie_ports=native", linux should use
native AER and DPC services.  While that is true for the _OSC method
parsing, this is not the only place that is checked.  Should the HEST
list PCIe ports as firmware-first, linux will not use native services.

This happens because aer_acpi_firmware_first() doesn't take 'pcie_ports'
into account.  This is wrong.  DPC uses the same logic when it decides
whether to load or not, so fixing this also fixes DPC not loading.

Signed-off-by: Alexandru Gagniuc <mr.nuke.me@gmail.com>
[bhelgaas: return "false" from bool function (from kbuild robot)]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aer.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 47c67de1ccf1..766687094706 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -322,6 +322,9 @@ int pcie_aer_get_firmware_first(struct pci_dev *dev)
 	if (!pci_is_pcie(dev))
 		return 0;
 
+	if (pcie_ports_native)
+		return 0;
+
 	if (!dev->__aer_firmware_first_valid)
 		aer_set_firmware_first(dev);
 	return dev->__aer_firmware_first;
@@ -342,6 +345,9 @@ bool aer_acpi_firmware_first(void)
 		.firmware_first	= 0,
 	};
 
+	if (pcie_ports_native)
+		return false;
+
 	if (!parsed) {
 		apei_hest_parse(aer_hest_parse, &info);
 		aer_firmware_first = info.firmware_first;
-- 
cgit v1.2.3


From f8d46c89c86fa11c60c05e101a3a4c7458623103 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Wed, 20 Jun 2018 15:38:27 -0600
Subject: PCI/DPC: Leave interrupts enabled while handling event

Now that the DPC driver clears the interrupt status before exiting the
IRQ handler, we don't need to abuse the DPC control register to know if
a shared interrupt is for a new DPC event: a DPC port can not trigger
a second interrupt until the host clears the trigger status later in the
work queue handler.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/dpc.c | 23 +++++------------------
 1 file changed, 5 insertions(+), 18 deletions(-)

diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 921ed979109d..972aac892846 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -77,7 +77,7 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	struct dpc_dev *dpc;
 	struct pcie_device *pciedev;
 	struct device *devdpc;
-	u16 cap, ctl;
+	u16 cap;
 
 	/*
 	 * DPC disables the Link automatically in hardware, so it has
@@ -105,10 +105,6 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_TRIGGER);
 
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl);
-	pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL,
-			      ctl | PCI_EXP_DPC_CTL_INT_EN);
-
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
@@ -183,16 +179,11 @@ static irqreturn_t dpc_irq(int irq, void *context)
 	struct dpc_dev *dpc = (struct dpc_dev *)context;
 	struct pci_dev *pdev = dpc->dev->port;
 	struct device *dev = &dpc->dev->device;
-	u16 cap = dpc->cap_pos, ctl, status, source, reason, ext_reason;
-
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_CTL, &ctl);
-
-	if (!(ctl & PCI_EXP_DPC_CTL_INT_EN) || ctl == (u16)(~0))
-		return IRQ_NONE;
+	u16 cap = dpc->cap_pos, status, source, reason, ext_reason;
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
 
-	if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT))
+	if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT) || status == (u16)(~0))
 		return IRQ_NONE;
 
 	if (!(status & PCI_EXP_DPC_STATUS_TRIGGER)) {
@@ -201,9 +192,6 @@ static irqreturn_t dpc_irq(int irq, void *context)
 		return IRQ_HANDLED;
 	}
 
-	pci_write_config_word(pdev, cap + PCI_EXP_DPC_CTL,
-			      ctl & ~PCI_EXP_DPC_CTL_INT_EN);
-
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID,
 			     &source);
 
@@ -226,9 +214,8 @@ static irqreturn_t dpc_irq(int irq, void *context)
 
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_INTERRUPT);
-
-	schedule_work(&dpc->work);
-
+	if (status & PCI_EXP_DPC_STATUS_TRIGGER)
+		schedule_work(&dpc->work);
 	return IRQ_HANDLED;
 }
 
-- 
cgit v1.2.3


From 0c27e28f77179548aa3d25a8f7a3dda22fd3e080 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 16 Jul 2018 17:05:02 -0500
Subject: PCI/DPC: Defer event handling to work queue

Move all event handling to the existing work queue, which will
make it simpler to pass event information to the handler.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/dpc.c | 44 ++++++++++++++++++++------------------------
 1 file changed, 20 insertions(+), 24 deletions(-)

diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 972aac892846..5f5fac279c75 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -108,14 +108,6 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static void dpc_work(struct work_struct *work)
-{
-	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
-	struct pci_dev *pdev = dpc->dev->port;
-
-	/* We configure DPC so it only triggers on ERR_FATAL */
-	pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
-}
 
 static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 {
@@ -174,33 +166,21 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 	}
 }
 
-static irqreturn_t dpc_irq(int irq, void *context)
+static void dpc_work(struct work_struct *work)
 {
-	struct dpc_dev *dpc = (struct dpc_dev *)context;
+	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
 	struct pci_dev *pdev = dpc->dev->port;
 	struct device *dev = &dpc->dev->device;
 	u16 cap = dpc->cap_pos, status, source, reason, ext_reason;
 
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
-
-	if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT) || status == (u16)(~0))
-		return IRQ_NONE;
-
-	if (!(status & PCI_EXP_DPC_STATUS_TRIGGER)) {
-		pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
-				      PCI_EXP_DPC_STATUS_INTERRUPT);
-		return IRQ_HANDLED;
-	}
-
-	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID,
-			     &source);
+	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
 
 	dev_info(dev, "DPC containment event, status:%#06x source:%#06x\n",
-		status, source);
+		 status, source);
 
 	reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN) >> 1;
 	ext_reason = (status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT) >> 5;
-
 	dev_warn(dev, "DPC %s detected, remove downstream devices\n",
 		 (reason == 0) ? "unmasked uncorrectable error" :
 		 (reason == 1) ? "ERR_NONFATAL" :
@@ -208,10 +188,26 @@ static irqreturn_t dpc_irq(int irq, void *context)
 		 (ext_reason == 0) ? "RP PIO error" :
 		 (ext_reason == 1) ? "software trigger" :
 				     "reserved error");
+
 	/* show RP PIO error detail information */
 	if (dpc->rp_extensions && reason == 3 && ext_reason == 0)
 		dpc_process_rp_pio_error(dpc);
 
+	/* We configure DPC so it only triggers on ERR_FATAL */
+	pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
+}
+
+static irqreturn_t dpc_irq(int irq, void *context)
+{
+	struct dpc_dev *dpc = (struct dpc_dev *)context;
+	struct pci_dev *pdev = dpc->dev->port;
+	u16 cap = dpc->cap_pos, status;
+
+	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
+
+	if (!(status & PCI_EXP_DPC_STATUS_INTERRUPT) || status == (u16)(~0))
+		return IRQ_NONE;
+
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_INTERRUPT);
 	if (status & PCI_EXP_DPC_STATUS_TRIGGER)
-- 
cgit v1.2.3


From f1d16b17568e46f61cc59e2d0725b0fca856a34f Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 16 Jul 2018 17:05:03 -0500
Subject: PCI/DPC: Remove rp_pio_status from dpc struct

We don't need to save the rp pio status across multiple contexts as all
DPC event handling occurs in a single work queue context.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/dpc.c | 17 +++++------------
 1 file changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 5f5fac279c75..1b0b25ba947c 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -19,7 +19,6 @@ struct dpc_dev {
 	struct work_struct	work;
 	u16			cap_pos;
 	bool			rp_extensions;
-	u32			rp_pio_status;
 	u8			rp_log_size;
 };
 
@@ -96,11 +95,6 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 
 	if (dpc->rp_extensions && dpc_wait_rp_inactive(dpc))
 		return PCI_ERS_RESULT_DISCONNECT;
-	if (dpc->rp_extensions && dpc->rp_pio_status) {
-		pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS,
-				       dpc->rp_pio_status);
-		dpc->rp_pio_status = 0;
-	}
 
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_TRIGGER);
@@ -122,8 +116,6 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 	dev_err(dev, "rp_pio_status: %#010x, rp_pio_mask: %#010x\n",
 		status, mask);
 
-	dpc->rp_pio_status = status;
-
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SEVERITY, &sev);
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_SYSERROR, &syserr);
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_EXCEPTION, &exc);
@@ -134,15 +126,14 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &dpc_status);
 	first_error = (dpc_status & 0x1f00) >> 8;
 
-	status &= ~mask;
 	for (i = 0; i < ARRAY_SIZE(rp_pio_error_string); i++) {
-		if (status & (1 << i))
+		if ((status & ~mask) & (1 << i))
 			dev_err(dev, "[%2d] %s%s\n", i, rp_pio_error_string[i],
 				first_error == i ? " (First)" : "");
 	}
 
 	if (dpc->rp_log_size < 4)
-		return;
+		goto clear_status;
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG,
 			      &dw0);
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_HEADER_LOG + 4,
@@ -155,7 +146,7 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 		dw0, dw1, dw2, dw3);
 
 	if (dpc->rp_log_size < 5)
-		return;
+		goto clear_status;
 	pci_read_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_IMPSPEC_LOG, &log);
 	dev_err(dev, "RP PIO ImpSpec Log %#010x\n", log);
 
@@ -164,6 +155,8 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 			cap + PCI_EXP_DPC_RP_PIO_TLPPREFIX_LOG, &prefix);
 		dev_err(dev, "TLP Prefix Header: dw%d, %#010x\n", i, prefix);
 	}
+ clear_status:
+	pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status);
 }
 
 static void dpc_work(struct work_struct *work)
-- 
cgit v1.2.3


From 8aefa9b0d9105d70eb8799d2b4feffd784e22bae Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 16 Jul 2018 17:05:05 -0500
Subject: PCI/DPC: Print AER status in DPC event handling

A DPC enabled device suppresses ERR_(NON)FATAL messages, preventing the AER
handler from reporting error details.  If the DPC trigger reason says the
downstream port detected the error, collect the AER uncorrectable status
for logging, then clear the status.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/dpc.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index 1b0b25ba947c..f6098dd171f3 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -6,6 +6,7 @@
  * Copyright (C) 2016 Intel Corp.
  */
 
+#include <linux/aer.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/init.h>
@@ -161,6 +162,7 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 
 static void dpc_work(struct work_struct *work)
 {
+	struct aer_err_info info;
 	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
 	struct pci_dev *pdev = dpc->dev->port;
 	struct device *dev = &dpc->dev->device;
@@ -185,6 +187,10 @@ static void dpc_work(struct work_struct *work)
 	/* show RP PIO error detail information */
 	if (dpc->rp_extensions && reason == 3 && ext_reason == 0)
 		dpc_process_rp_pio_error(dpc);
+	else if (reason == 0 && aer_get_device_error_info(pdev, &info)) {
+		aer_print_error(pdev, &info);
+		pci_cleanup_aer_uncorrect_error_status(pdev);
+	}
 
 	/* We configure DPC so it only triggers on ERR_FATAL */
 	pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
-- 
cgit v1.2.3


From 738c4e411dadbe341f80f30d56518b68ae1e605f Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 16 Jul 2018 17:05:06 -0500
Subject: PCI/DPC: Use threaded IRQ for bottom half handling

Remove the work struct that was being used to handle a DPC event and use a
threaded IRQ instead.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/dpc.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index f6098dd171f3..fd6b96ca1c2d 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -17,7 +17,6 @@
 
 struct dpc_dev {
 	struct pcie_device	*dev;
-	struct work_struct	work;
 	u16			cap_pos;
 	bool			rp_extensions;
 	u8			rp_log_size;
@@ -160,10 +159,10 @@ static void dpc_process_rp_pio_error(struct dpc_dev *dpc)
 	pci_write_config_dword(pdev, cap + PCI_EXP_DPC_RP_PIO_STATUS, status);
 }
 
-static void dpc_work(struct work_struct *work)
+static irqreturn_t dpc_handler(int irq, void *context)
 {
 	struct aer_err_info info;
-	struct dpc_dev *dpc = container_of(work, struct dpc_dev, work);
+	struct dpc_dev *dpc = context;
 	struct pci_dev *pdev = dpc->dev->port;
 	struct device *dev = &dpc->dev->device;
 	u16 cap = dpc->cap_pos, status, source, reason, ext_reason;
@@ -194,6 +193,8 @@ static void dpc_work(struct work_struct *work)
 
 	/* We configure DPC so it only triggers on ERR_FATAL */
 	pcie_do_fatal_recovery(pdev, PCIE_PORT_SERVICE_DPC);
+
+	return IRQ_HANDLED;
 }
 
 static irqreturn_t dpc_irq(int irq, void *context)
@@ -210,7 +211,7 @@ static irqreturn_t dpc_irq(int irq, void *context)
 	pci_write_config_word(pdev, cap + PCI_EXP_DPC_STATUS,
 			      PCI_EXP_DPC_STATUS_INTERRUPT);
 	if (status & PCI_EXP_DPC_STATUS_TRIGGER)
-		schedule_work(&dpc->work);
+		return IRQ_WAKE_THREAD;
 	return IRQ_HANDLED;
 }
 
@@ -232,11 +233,11 @@ static int dpc_probe(struct pcie_device *dev)
 
 	dpc->cap_pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DPC);
 	dpc->dev = dev;
-	INIT_WORK(&dpc->work, dpc_work);
 	set_service_data(dev, dpc);
 
-	status = devm_request_irq(device, dev->irq, dpc_irq, IRQF_SHARED,
-				  "pcie-dpc", dpc);
+	status = devm_request_threaded_irq(device, dev->irq, dpc_irq,
+					   dpc_handler, IRQF_SHARED,
+					   "pcie-dpc", dpc);
 	if (status) {
 		dev_warn(device, "request IRQ%d failed: %d\n", dev->irq,
 			 status);
-- 
cgit v1.2.3


From e77b8216a2f9bec430ec46c34763567329ddafd9 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 16 Jul 2018 17:05:07 -0500
Subject: PCI/DPC: Remove indirection waiting for inactive link

Simplify waiting for the contained link to become inactive, removing the
indirection to a unnecessary DPC-specific handler.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/dpc.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
index fd6b96ca1c2d..f03279fc87cd 100644
--- a/drivers/pci/pcie/dpc.c
+++ b/drivers/pci/pcie/dpc.c
@@ -64,18 +64,12 @@ static int dpc_wait_rp_inactive(struct dpc_dev *dpc)
 	return 0;
 }
 
-static void dpc_wait_link_inactive(struct dpc_dev *dpc)
-{
-	struct pci_dev *pdev = dpc->dev->port;
-
-	pcie_wait_for_link(pdev, false);
-}
-
 static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 {
 	struct dpc_dev *dpc;
 	struct pcie_device *pciedev;
 	struct device *devdpc;
+
 	u16 cap;
 
 	/*
@@ -91,7 +85,7 @@ static pci_ers_result_t dpc_reset_link(struct pci_dev *pdev)
 	 * Wait until the Link is inactive, then clear DPC Trigger Status
 	 * to allow the Port to leave DPC.
 	 */
-	dpc_wait_link_inactive(dpc);
+	pcie_wait_for_link(pdev, false);
 
 	if (dpc->rp_extensions && dpc_wait_rp_inactive(dpc))
 		return PCI_ERS_RESULT_DISCONNECT;
-- 
cgit v1.2.3


From f2df5da66262f429cbb0d5da0e72ada6a6345f28 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 19 Jul 2018 17:35:51 -0400
Subject: fold generic_readlink() into its only caller

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/namei.c | 36 ++++++++++++------------------------
 1 file changed, 12 insertions(+), 24 deletions(-)

diff --git a/fs/namei.c b/fs/namei.c
index 734cef54fdf8..bb6c6e4f59e2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4712,29 +4712,6 @@ out:
 	return len;
 }
 
-/*
- * A helper for ->readlink().  This should be used *ONLY* for symlinks that
- * have ->get_link() not calling nd_jump_link().  Using (or not using) it
- * for any given inode is up to filesystem.
- */
-static int generic_readlink(struct dentry *dentry, char __user *buffer,
-			    int buflen)
-{
-	DEFINE_DELAYED_CALL(done);
-	struct inode *inode = d_inode(dentry);
-	const char *link = inode->i_link;
-	int res;
-
-	if (!link) {
-		link = inode->i_op->get_link(dentry, inode, &done);
-		if (IS_ERR(link))
-			return PTR_ERR(link);
-	}
-	res = readlink_copy(buffer, buflen, link);
-	do_delayed_call(&done);
-	return res;
-}
-
 /**
  * vfs_readlink - copy symlink body into userspace buffer
  * @dentry: dentry on which to get symbolic link
@@ -4748,6 +4725,9 @@ static int generic_readlink(struct dentry *dentry, char __user *buffer,
 int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 {
 	struct inode *inode = d_inode(dentry);
+	DEFINE_DELAYED_CALL(done);
+	const char *link;
+	int res;
 
 	if (unlikely(!(inode->i_opflags & IOP_DEFAULT_READLINK))) {
 		if (unlikely(inode->i_op->readlink))
@@ -4761,7 +4741,15 @@ int vfs_readlink(struct dentry *dentry, char __user *buffer, int buflen)
 		spin_unlock(&inode->i_lock);
 	}
 
-	return generic_readlink(dentry, buffer, buflen);
+	link = inode->i_link;
+	if (!link) {
+		link = inode->i_op->get_link(dentry, inode, &done);
+		if (IS_ERR(link))
+			return PTR_ERR(link);
+	}
+	res = readlink_copy(buffer, buflen, link);
+	do_delayed_call(&done);
+	return res;
 }
 EXPORT_SYMBOL(vfs_readlink);
 
-- 
cgit v1.2.3


From 51259d0022f1965047bb61662f6f0d5a79a6ddb3 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Fri, 25 May 2018 08:51:50 -0500
Subject: PCI/IOV: Tidy pci_sriov_set_totalvfs()

Fix minor style issues in pci_sriov_set_totalvfs().  No functional change
intended.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/iov.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index d0d73dbbd5ca..aee859971ba1 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -802,15 +802,15 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs)
 {
 	if (!dev->is_physfn)
 		return -ENOSYS;
+
 	if (numvfs > dev->sriov->total_VFs)
 		return -EINVAL;
 
 	/* Shouldn't change if VFs already enabled */
 	if (dev->sriov->ctrl & PCI_SRIOV_CTRL_VFE)
 		return -EBUSY;
-	else
-		dev->sriov->driver_max_VFs = numvfs;
 
+	dev->sriov->driver_max_VFs = numvfs;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_sriov_set_totalvfs);
-- 
cgit v1.2.3


From 0f9987b63dcc68606b82a349bbb2016b392a2c34 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 13 Jul 2018 14:06:40 +0200
Subject: ntp: Remove redundant arguments

The 'ts' argument of process_adj_status() and process_adjtimex_modes()
is unused and can be safely removed.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 kernel/time/ntp.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 10a79053e82f..3eddac25675f 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void)
 /*
  * Propagate a new txc->status value into the NTP state:
  */
-static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
+static inline void process_adj_status(struct timex *txc)
 {
 	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
 		time_state = TIME_OK;
@@ -665,12 +665,10 @@ static inline void process_adj_status(struct timex *txc, struct timespec64 *ts)
 }
 
 
-static inline void process_adjtimex_modes(struct timex *txc,
-						struct timespec64 *ts,
-						s32 *time_tai)
+static inline void process_adjtimex_modes(struct timex *txc, s32 *time_tai)
 {
 	if (txc->modes & ADJ_STATUS)
-		process_adj_status(txc, ts);
+		process_adj_status(txc);
 
 	if (txc->modes & ADJ_NANO)
 		time_status |= STA_NANO;
@@ -735,7 +733,7 @@ int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
 
 		/* If there are input parameters, then process them: */
 		if (txc->modes)
-			process_adjtimex_modes(txc, ts, time_tai);
+			process_adjtimex_modes(txc, time_tai);
 
 		txc->offset = shift_right(time_offset * NTP_INTERVAL_FREQ,
 				  NTP_SCALE_SHIFT);
-- 
cgit v1.2.3


From 86b2dcd4f02b86f6b5927fc0adcac777825f4030 Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 13 Jul 2018 14:06:41 +0200
Subject: ntp: Use kstrtos64 for s64 variable

...instead of kstrtol with a dirty cast.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 kernel/time/ntp.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index 3eddac25675f..a627cae8baab 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -1020,12 +1020,11 @@ void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_t
 
 static int __init ntp_tick_adj_setup(char *str)
 {
-	int rc = kstrtol(str, 0, (long *)&ntp_tick_adj);
-
+	int rc = kstrtos64(str, 0, &ntp_tick_adj);
 	if (rc)
 		return rc;
-	ntp_tick_adj <<= NTP_SCALE_SHIFT;
 
+	ntp_tick_adj <<= NTP_SCALE_SHIFT;
 	return 1;
 }
 
-- 
cgit v1.2.3


From 368a540e0232ad446931f5a4e8a5e06f69f21343 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:20 -0400
Subject: x86/kvmclock: Remove memblock dependency

KVM clock is initialized later compared to other hypervisor clocks because
it has a dependency on the memblock allocator.

Bring it in line with other hypervisors by using memory from the BSS
instead of allocating it.

The benefits:

  - Remove ifdef from common code
  - Earlier availability of the clock
  - Remove dependency on memblock, and reduce code

The downside:

  - Static allocation of the per cpu data structures sized NR_CPUS * 64byte
    Will be addressed in follow up patches.

[ tglx: Split out from larger series ]

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Link: https://lkml.kernel.org/r/20180719205545.16512-2-pasha.tatashin@oracle.com
---
 arch/x86/kernel/kvm.c      |  1 +
 arch/x86/kernel/kvmclock.c | 66 ++++++++--------------------------------------
 arch/x86/kernel/setup.c    |  4 ---
 3 files changed, 12 insertions(+), 59 deletions(-)

diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 5b2300b818af..c65c232d3ddd 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -628,6 +628,7 @@ const __initconst struct hypervisor_x86 x86_hyper_kvm = {
 	.name			= "KVM",
 	.detect			= kvm_detect,
 	.type			= X86_HYPER_KVM,
+	.init.init_platform	= kvmclock_init,
 	.init.guest_late_init	= kvm_guest_init,
 	.init.x2apic_available	= kvm_para_available,
 };
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 3b8e7c13c614..1f6ac5aaa904 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -23,9 +23,9 @@
 #include <asm/apic.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
-#include <linux/memblock.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
+#include <linux/mm.h>
 
 #include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
@@ -44,6 +44,13 @@ static int parse_no_kvmclock(char *arg)
 }
 early_param("no-kvmclock", parse_no_kvmclock);
 
+/* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
+#define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
+#define WALL_CLOCK_SIZE	(sizeof(struct pvclock_wall_clock))
+
+static u8 hv_clock_mem[PAGE_ALIGN(HV_CLOCK_SIZE)] __aligned(PAGE_SIZE);
+static u8 wall_clock_mem[PAGE_ALIGN(WALL_CLOCK_SIZE)] __aligned(PAGE_SIZE);
+
 /* The hypervisor will put information about time periodically here */
 static struct pvclock_vsyscall_time_info *hv_clock;
 static struct pvclock_wall_clock *wall_clock;
@@ -245,43 +252,12 @@ static void kvm_shutdown(void)
 	native_machine_shutdown();
 }
 
-static phys_addr_t __init kvm_memblock_alloc(phys_addr_t size,
-					     phys_addr_t align)
-{
-	phys_addr_t mem;
-
-	mem = memblock_alloc(size, align);
-	if (!mem)
-		return 0;
-
-	if (sev_active()) {
-		if (early_set_memory_decrypted((unsigned long)__va(mem), size))
-			goto e_free;
-	}
-
-	return mem;
-e_free:
-	memblock_free(mem, size);
-	return 0;
-}
-
-static void __init kvm_memblock_free(phys_addr_t addr, phys_addr_t size)
-{
-	if (sev_active())
-		early_set_memory_encrypted((unsigned long)__va(addr), size);
-
-	memblock_free(addr, size);
-}
-
 void __init kvmclock_init(void)
 {
 	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned long mem, mem_wall_clock;
-	int size, cpu, wall_clock_size;
+	int cpu;
 	u8 flags;
 
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
 	if (!kvm_para_available())
 		return;
 
@@ -291,28 +267,11 @@ void __init kvmclock_init(void)
 	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
 		return;
 
-	wall_clock_size = PAGE_ALIGN(sizeof(struct pvclock_wall_clock));
-	mem_wall_clock = kvm_memblock_alloc(wall_clock_size, PAGE_SIZE);
-	if (!mem_wall_clock)
-		return;
-
-	wall_clock = __va(mem_wall_clock);
-	memset(wall_clock, 0, wall_clock_size);
-
-	mem = kvm_memblock_alloc(size, PAGE_SIZE);
-	if (!mem) {
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
-		wall_clock = NULL;
-		return;
-	}
-
-	hv_clock = __va(mem);
-	memset(hv_clock, 0, size);
+	wall_clock = (struct pvclock_wall_clock *)wall_clock_mem;
+	hv_clock = (struct pvclock_vsyscall_time_info *)hv_clock_mem;
 
 	if (kvm_register_clock("primary cpu clock")) {
 		hv_clock = NULL;
-		kvm_memblock_free(mem, size);
-		kvm_memblock_free(mem_wall_clock, wall_clock_size);
 		wall_clock = NULL;
 		return;
 	}
@@ -357,13 +316,10 @@ int __init kvm_setup_vsyscall_timeinfo(void)
 	int cpu;
 	u8 flags;
 	struct pvclock_vcpu_time_info *vcpu_time;
-	unsigned int size;
 
 	if (!hv_clock)
 		return 0;
 
-	size = PAGE_ALIGN(sizeof(struct pvclock_vsyscall_time_info)*NR_CPUS);
-
 	cpu = get_cpu();
 
 	vcpu_time = &hv_clock[cpu].pvti;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 2f86d883dd95..da1dbd99cb6e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1197,10 +1197,6 @@ void __init setup_arch(char **cmdline_p)
 
 	memblock_find_dma_reserve();
 
-#ifdef CONFIG_KVM_GUEST
-	kvmclock_init();
-#endif
-
 	tsc_early_delay_calibrate();
 	if (!early_xdbc_setup_hardware())
 		early_xdbc_register_console();
-- 
cgit v1.2.3


From 7ef363a39514ed8a6f2333fbae1875ac0953715a Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 19 Jul 2018 16:55:21 -0400
Subject: x86/kvmclock: Remove page size requirement from wall_clock

There is no requirement for wall_clock data to be page aligned or page
sized.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Link: https://lkml.kernel.org/r/20180719205545.16512-3-pasha.tatashin@oracle.com
---
 arch/x86/kernel/kvmclock.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 1f6ac5aaa904..a995d7d7164c 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -46,14 +46,12 @@ early_param("no-kvmclock", parse_no_kvmclock);
 
 /* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
 #define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
-#define WALL_CLOCK_SIZE	(sizeof(struct pvclock_wall_clock))
 
 static u8 hv_clock_mem[PAGE_ALIGN(HV_CLOCK_SIZE)] __aligned(PAGE_SIZE);
-static u8 wall_clock_mem[PAGE_ALIGN(WALL_CLOCK_SIZE)] __aligned(PAGE_SIZE);
 
 /* The hypervisor will put information about time periodically here */
 static struct pvclock_vsyscall_time_info *hv_clock;
-static struct pvclock_wall_clock *wall_clock;
+static struct pvclock_wall_clock wall_clock;
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
@@ -66,15 +64,15 @@ static void kvm_get_wallclock(struct timespec64 *now)
 	int low, high;
 	int cpu;
 
-	low = (int)slow_virt_to_phys(wall_clock);
-	high = ((u64)slow_virt_to_phys(wall_clock) >> 32);
+	low = (int)slow_virt_to_phys(&wall_clock);
+	high = ((u64)slow_virt_to_phys(&wall_clock) >> 32);
 
 	native_write_msr(msr_kvm_wall_clock, low, high);
 
 	cpu = get_cpu();
 
 	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(wall_clock, vcpu_time, now);
+	pvclock_read_wallclock(&wall_clock, vcpu_time, now);
 
 	put_cpu();
 }
@@ -267,12 +265,10 @@ void __init kvmclock_init(void)
 	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
 		return;
 
-	wall_clock = (struct pvclock_wall_clock *)wall_clock_mem;
 	hv_clock = (struct pvclock_vsyscall_time_info *)hv_clock_mem;
 
 	if (kvm_register_clock("primary cpu clock")) {
 		hv_clock = NULL;
-		wall_clock = NULL;
 		return;
 	}
 
-- 
cgit v1.2.3


From 7a5ddc8fe0ea9518cd7fb6a929cac7d864c6f300 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 19 Jul 2018 16:55:22 -0400
Subject: x86/kvmclock: Decrapify kvm_register_clock()

The return value is pointless because the wrmsr cannot fail if
KVM_FEATURE_CLOCKSOURCE or KVM_FEATURE_CLOCKSOURCE2 are set.

kvm_register_clock() is only called locally so wants to be static.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Link: https://lkml.kernel.org/r/20180719205545.16512-4-pasha.tatashin@oracle.com
---
 arch/x86/include/asm/kvm_para.h |  1 -
 arch/x86/kernel/kvmclock.c      | 33 ++++++++++-----------------------
 2 files changed, 10 insertions(+), 24 deletions(-)

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 3aea2658323a..4c723632c036 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -7,7 +7,6 @@
 #include <uapi/asm/kvm_para.h>
 
 extern void kvmclock_init(void);
-extern int kvm_register_clock(char *txt);
 
 #ifdef CONFIG_KVM_GUEST
 bool kvm_check_and_clear_guest_paused(void);
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index a995d7d7164c..f0a0aef5e9fa 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -187,23 +187,19 @@ struct clocksource kvm_clock = {
 };
 EXPORT_SYMBOL_GPL(kvm_clock);
 
-int kvm_register_clock(char *txt)
+static void kvm_register_clock(char *txt)
 {
-	int cpu = smp_processor_id();
-	int low, high, ret;
 	struct pvclock_vcpu_time_info *src;
+	int cpu = smp_processor_id();
+	u64 pa;
 
 	if (!hv_clock)
-		return 0;
+		return;
 
 	src = &hv_clock[cpu].pvti;
-	low = (int)slow_virt_to_phys(src) | 1;
-	high = ((u64)slow_virt_to_phys(src) >> 32);
-	ret = native_write_msr_safe(msr_kvm_system_time, low, high);
-	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
-	       cpu, high, low, txt);
-
-	return ret;
+	pa = slow_virt_to_phys(src) | 0x01ULL;
+	wrmsrl(msr_kvm_system_time, pa);
+	pr_info("kvm-clock: cpu %d, msr %llx, %s\n", cpu, pa, txt);
 }
 
 static void kvm_save_sched_clock_state(void)
@@ -218,11 +214,7 @@ static void kvm_restore_sched_clock_state(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 static void kvm_setup_secondary_clock(void)
 {
-	/*
-	 * Now that the first cpu already had this clocksource initialized,
-	 * we shouldn't fail.
-	 */
-	WARN_ON(kvm_register_clock("secondary cpu clock"));
+	kvm_register_clock("secondary cpu clock");
 }
 #endif
 
@@ -265,16 +257,11 @@ void __init kvmclock_init(void)
 	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
 		return;
 
-	hv_clock = (struct pvclock_vsyscall_time_info *)hv_clock_mem;
-
-	if (kvm_register_clock("primary cpu clock")) {
-		hv_clock = NULL;
-		return;
-	}
-
 	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
+	hv_clock = (struct pvclock_vsyscall_time_info *)hv_clock_mem;
+	kvm_register_clock("primary cpu clock");
 	pvclock_set_pvti_cpu0_va(hv_clock);
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
-- 
cgit v1.2.3


From 146c394d0c3c8e88df433a179c2b0b85fd8cf247 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 19 Jul 2018 16:55:23 -0400
Subject: x86/kvmclock: Cleanup the code

- Cleanup the mrs write for wall clock. The type casts to (int) are sloppy
  because the wrmsr parameters are u32 and aside of that wrmsrl() already
  provides the high/low split for free.

- Remove the pointless get_cpu()/put_cpu() dance from various
  functions. Either they are called during early init where CPU is
  guaranteed to be 0 or they are already called from non preemptible
  context where smp_processor_id() can be used safely

- Simplify the convoluted check for kvmclock in the init function.

- Mark the parameter parsing function __init. No point in keeping it
  around.

- Convert to pr_info()

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Link: https://lkml.kernel.org/r/20180719205545.16512-5-pasha.tatashin@oracle.com
---
 arch/x86/kernel/kvmclock.c | 72 ++++++++++++++--------------------------------
 1 file changed, 22 insertions(+), 50 deletions(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index f0a0aef5e9fa..4afb03e49a4f 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -37,7 +37,7 @@ static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
 static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
 static u64 kvm_sched_clock_offset;
 
-static int parse_no_kvmclock(char *arg)
+static int __init parse_no_kvmclock(char *arg)
 {
 	kvmclock = 0;
 	return 0;
@@ -61,13 +61,9 @@ static struct pvclock_wall_clock wall_clock;
 static void kvm_get_wallclock(struct timespec64 *now)
 {
 	struct pvclock_vcpu_time_info *vcpu_time;
-	int low, high;
 	int cpu;
 
-	low = (int)slow_virt_to_phys(&wall_clock);
-	high = ((u64)slow_virt_to_phys(&wall_clock) >> 32);
-
-	native_write_msr(msr_kvm_wall_clock, low, high);
+	wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
 
 	cpu = get_cpu();
 
@@ -117,11 +113,11 @@ static inline void kvm_sched_clock_init(bool stable)
 	kvm_sched_clock_offset = kvm_clock_read();
 	pv_time_ops.sched_clock = kvm_sched_clock_read;
 
-	printk(KERN_INFO "kvm-clock: using sched offset of %llu cycles\n",
-			kvm_sched_clock_offset);
+	pr_info("kvm-clock: using sched offset of %llu cycles",
+		kvm_sched_clock_offset);
 
 	BUILD_BUG_ON(sizeof(kvm_sched_clock_offset) >
-	         sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
+		sizeof(((struct pvclock_vcpu_time_info *)NULL)->system_time));
 }
 
 /*
@@ -135,16 +131,8 @@ static inline void kvm_sched_clock_init(bool stable)
  */
 static unsigned long kvm_get_tsc_khz(void)
 {
-	struct pvclock_vcpu_time_info *src;
-	int cpu;
-	unsigned long tsc_khz;
-
-	cpu = get_cpu();
-	src = &hv_clock[cpu].pvti;
-	tsc_khz = pvclock_tsc_khz(src);
-	put_cpu();
 	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	return tsc_khz;
+	return pvclock_tsc_khz(&hv_clock[0].pvti);
 }
 
 static void kvm_get_preset_lpj(void)
@@ -161,29 +149,27 @@ static void kvm_get_preset_lpj(void)
 
 bool kvm_check_and_clear_guest_paused(void)
 {
-	bool ret = false;
 	struct pvclock_vcpu_time_info *src;
-	int cpu = smp_processor_id();
+	bool ret = false;
 
 	if (!hv_clock)
 		return ret;
 
-	src = &hv_clock[cpu].pvti;
+	src = &hv_clock[smp_processor_id()].pvti;
 	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
 		src->flags &= ~PVCLOCK_GUEST_STOPPED;
 		pvclock_touch_watchdogs();
 		ret = true;
 	}
-
 	return ret;
 }
 
 struct clocksource kvm_clock = {
-	.name = "kvm-clock",
-	.read = kvm_clock_get_cycles,
-	.rating = 400,
-	.mask = CLOCKSOURCE_MASK(64),
-	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	.name	= "kvm-clock",
+	.read	= kvm_clock_get_cycles,
+	.rating	= 400,
+	.mask	= CLOCKSOURCE_MASK(64),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 EXPORT_SYMBOL_GPL(kvm_clock);
 
@@ -199,7 +185,7 @@ static void kvm_register_clock(char *txt)
 	src = &hv_clock[cpu].pvti;
 	pa = slow_virt_to_phys(src) | 0x01ULL;
 	wrmsrl(msr_kvm_system_time, pa);
-	pr_info("kvm-clock: cpu %d, msr %llx, %s\n", cpu, pa, txt);
+	pr_info("kvm-clock: cpu %d, msr %llx, %s", cpu, pa, txt);
 }
 
 static void kvm_save_sched_clock_state(void)
@@ -244,20 +230,19 @@ static void kvm_shutdown(void)
 
 void __init kvmclock_init(void)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	int cpu;
 	u8 flags;
 
-	if (!kvm_para_available())
+	if (!kvm_para_available() || !kvmclock)
 		return;
 
-	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
+	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE2)) {
 		msr_kvm_system_time = MSR_KVM_SYSTEM_TIME_NEW;
 		msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK_NEW;
-	} else if (!(kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)))
+	} else if (!kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
 		return;
+	}
 
-	printk(KERN_INFO "kvm-clock: Using msrs %x and %x",
+	pr_info("kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
 	hv_clock = (struct pvclock_vsyscall_time_info *)hv_clock_mem;
@@ -267,20 +252,15 @@ void __init kvmclock_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
-	cpu = get_cpu();
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
+	flags = pvclock_read_flags(&hv_clock[0].pvti);
 	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
-	put_cpu();
 
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
 	x86_platform.calibrate_cpu = kvm_get_tsc_khz;
 	x86_platform.get_wallclock = kvm_get_wallclock;
 	x86_platform.set_wallclock = kvm_set_wallclock;
 #ifdef CONFIG_X86_LOCAL_APIC
-	x86_cpuinit.early_percpu_clock_init =
-		kvm_setup_secondary_clock;
+	x86_cpuinit.early_percpu_clock_init = kvm_setup_secondary_clock;
 #endif
 	x86_platform.save_sched_clock_state = kvm_save_sched_clock_state;
 	x86_platform.restore_sched_clock_state = kvm_restore_sched_clock_state;
@@ -296,20 +276,12 @@ void __init kvmclock_init(void)
 int __init kvm_setup_vsyscall_timeinfo(void)
 {
 #ifdef CONFIG_X86_64
-	int cpu;
 	u8 flags;
-	struct pvclock_vcpu_time_info *vcpu_time;
 
 	if (!hv_clock)
 		return 0;
 
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	flags = pvclock_read_flags(vcpu_time);
-
-	put_cpu();
-
+	flags = pvclock_read_flags(&hv_clock[0].pvti);
 	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
 		return 1;
 
-- 
cgit v1.2.3


From 42f8df935efefba51d0c5321b1325436523e3377 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 19 Jul 2018 16:55:24 -0400
Subject: x86/kvmclock: Mark variables __initdata and __ro_after_init

The kvmclock parameter is init data and the other variables are not
modified after init.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Link: https://lkml.kernel.org/r/20180719205545.16512-6-pasha.tatashin@oracle.com
---
 arch/x86/kernel/kvmclock.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 4afb03e49a4f..78aec160f5e0 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -32,10 +32,10 @@
 #include <asm/reboot.h>
 #include <asm/kvmclock.h>
 
-static int kvmclock __ro_after_init = 1;
-static int msr_kvm_system_time = MSR_KVM_SYSTEM_TIME;
-static int msr_kvm_wall_clock = MSR_KVM_WALL_CLOCK;
-static u64 kvm_sched_clock_offset;
+static int kvmclock __initdata = 1;
+static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
+static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
+static u64 kvm_sched_clock_offset __ro_after_init;
 
 static int __init parse_no_kvmclock(char *arg)
 {
@@ -50,7 +50,7 @@ early_param("no-kvmclock", parse_no_kvmclock);
 static u8 hv_clock_mem[PAGE_ALIGN(HV_CLOCK_SIZE)] __aligned(PAGE_SIZE);
 
 /* The hypervisor will put information about time periodically here */
-static struct pvclock_vsyscall_time_info *hv_clock;
+static struct pvclock_vsyscall_time_info *hv_clock __ro_after_init;
 static struct pvclock_wall_clock wall_clock;
 
 /*
-- 
cgit v1.2.3


From e499a9b6dc488aff7f284bee51936f510ab7ad15 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 19 Jul 2018 16:55:25 -0400
Subject: x86/kvmclock: Move kvmclock vsyscall param and init to kvmclock

There is no point to have this in the kvm code itself and call it from
there. This can be called from an initcall and the parameter is cleared
when the hypervisor is not KVM.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Link: https://lkml.kernel.org/r/20180719205545.16512-7-pasha.tatashin@oracle.com
---
 arch/x86/include/asm/kvm_guest.h |  7 -------
 arch/x86/kernel/kvm.c            | 13 ------------
 arch/x86/kernel/kvmclock.c       | 44 ++++++++++++++++++++++++----------------
 3 files changed, 27 insertions(+), 37 deletions(-)
 delete mode 100644 arch/x86/include/asm/kvm_guest.h

diff --git a/arch/x86/include/asm/kvm_guest.h b/arch/x86/include/asm/kvm_guest.h
deleted file mode 100644
index 46185263d9c2..000000000000
--- a/arch/x86/include/asm/kvm_guest.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_KVM_GUEST_H
-#define _ASM_X86_KVM_GUEST_H
-
-int kvm_setup_vsyscall_timeinfo(void);
-
-#endif /* _ASM_X86_KVM_GUEST_H */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index c65c232d3ddd..a560750cc76f 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -45,7 +45,6 @@
 #include <asm/apic.h>
 #include <asm/apicdef.h>
 #include <asm/hypervisor.h>
-#include <asm/kvm_guest.h>
 
 static int kvmapf = 1;
 
@@ -66,15 +65,6 @@ static int __init parse_no_stealacc(char *arg)
 
 early_param("no-steal-acc", parse_no_stealacc);
 
-static int kvmclock_vsyscall = 1;
-static int __init parse_no_kvmclock_vsyscall(char *arg)
-{
-        kvmclock_vsyscall = 0;
-        return 0;
-}
-
-early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
-
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_vcpu_pv_apf_data, apf_reason) __aligned(64);
 static DEFINE_PER_CPU_DECRYPTED(struct kvm_steal_time, steal_time) __aligned(64);
 static int has_steal_clock = 0;
@@ -560,9 +550,6 @@ static void __init kvm_guest_init(void)
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
 		apic_set_eoi_write(kvm_guest_apic_eoi_write);
 
-	if (kvmclock_vsyscall)
-		kvm_setup_vsyscall_timeinfo();
-
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_cpus = kvm_smp_prepare_cpus;
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 78aec160f5e0..7d690d2238f8 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -27,12 +27,14 @@
 #include <linux/sched/clock.h>
 #include <linux/mm.h>
 
+#include <asm/hypervisor.h>
 #include <asm/mem_encrypt.h>
 #include <asm/x86_init.h>
 #include <asm/reboot.h>
 #include <asm/kvmclock.h>
 
 static int kvmclock __initdata = 1;
+static int kvmclock_vsyscall __initdata = 1;
 static int msr_kvm_system_time __ro_after_init = MSR_KVM_SYSTEM_TIME;
 static int msr_kvm_wall_clock __ro_after_init = MSR_KVM_WALL_CLOCK;
 static u64 kvm_sched_clock_offset __ro_after_init;
@@ -44,6 +46,13 @@ static int __init parse_no_kvmclock(char *arg)
 }
 early_param("no-kvmclock", parse_no_kvmclock);
 
+static int __init parse_no_kvmclock_vsyscall(char *arg)
+{
+	kvmclock_vsyscall = 0;
+	return 0;
+}
+early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
+
 /* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
 #define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
 
@@ -228,6 +237,24 @@ static void kvm_shutdown(void)
 	native_machine_shutdown();
 }
 
+static int __init kvm_setup_vsyscall_timeinfo(void)
+{
+#ifdef CONFIG_X86_64
+	u8 flags;
+
+	if (!hv_clock || !kvmclock_vsyscall)
+		return 0;
+
+	flags = pvclock_read_flags(&hv_clock[0].pvti);
+	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
+		return 1;
+
+	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
+#endif
+	return 0;
+}
+early_initcall(kvm_setup_vsyscall_timeinfo);
+
 void __init kvmclock_init(void)
 {
 	u8 flags;
@@ -272,20 +299,3 @@ void __init kvmclock_init(void)
 	clocksource_register_hz(&kvm_clock, NSEC_PER_SEC);
 	pv_info.name = "KVM";
 }
-
-int __init kvm_setup_vsyscall_timeinfo(void)
-{
-#ifdef CONFIG_X86_64
-	u8 flags;
-
-	if (!hv_clock)
-		return 0;
-
-	flags = pvclock_read_flags(&hv_clock[0].pvti);
-	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
-		return 1;
-
-	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
-#endif
-	return 0;
-}
-- 
cgit v1.2.3


From 95a3d4454bb1cf5bfd666c27fdd2dc188e17c14d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 19 Jul 2018 16:55:26 -0400
Subject: x86/kvmclock: Switch kvmclock data to a PER_CPU variable

The previous removal of the memblock dependency from kvmclock introduced a
static data array sized 64bytes * CONFIG_NR_CPUS. That's wasteful on large
systems when kvmclock is not used.

Replace it with:

 - A static page sized array of pvclock data. It's page sized because the
   pvclock data of the boot cpu is mapped into the VDSO so otherwise random
   other data would be exposed to the vDSO

 - A PER_CPU variable of pvclock data pointers. This is used to access the
   pcvlock data storage on each CPU.

The setup is done in two stages:

 - Early boot stores the pointer to the static page for the boot CPU in
   the per cpu data.

 - In the preparatory stage of CPU hotplug assign either an element of
   the static array (when the CPU number is in that range) or allocate
   memory and initialize the per cpu pointer.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Link: https://lkml.kernel.org/r/20180719205545.16512-8-pasha.tatashin@oracle.com
---
 arch/x86/kernel/kvmclock.c | 99 +++++++++++++++++++++++++++++-----------------
 1 file changed, 62 insertions(+), 37 deletions(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 7d690d2238f8..91b94c0ae4e3 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -23,6 +23,7 @@
 #include <asm/apic.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/cpuhotplug.h>
 #include <linux/sched.h>
 #include <linux/sched/clock.h>
 #include <linux/mm.h>
@@ -55,12 +56,23 @@ early_param("no-kvmclock-vsyscall", parse_no_kvmclock_vsyscall);
 
 /* Aligned to page sizes to match whats mapped via vsyscalls to userspace */
 #define HV_CLOCK_SIZE	(sizeof(struct pvclock_vsyscall_time_info) * NR_CPUS)
+#define HVC_BOOT_ARRAY_SIZE \
+	(PAGE_SIZE / sizeof(struct pvclock_vsyscall_time_info))
 
-static u8 hv_clock_mem[PAGE_ALIGN(HV_CLOCK_SIZE)] __aligned(PAGE_SIZE);
-
-/* The hypervisor will put information about time periodically here */
-static struct pvclock_vsyscall_time_info *hv_clock __ro_after_init;
+static struct pvclock_vsyscall_time_info
+			hv_clock_boot[HVC_BOOT_ARRAY_SIZE] __aligned(PAGE_SIZE);
 static struct pvclock_wall_clock wall_clock;
+static DEFINE_PER_CPU(struct pvclock_vsyscall_time_info *, hv_clock_per_cpu);
+
+static inline struct pvclock_vcpu_time_info *this_cpu_pvti(void)
+{
+	return &this_cpu_read(hv_clock_per_cpu)->pvti;
+}
+
+static inline struct pvclock_vsyscall_time_info *this_cpu_hvclock(void)
+{
+	return this_cpu_read(hv_clock_per_cpu);
+}
 
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
@@ -69,17 +81,10 @@ static struct pvclock_wall_clock wall_clock;
  */
 static void kvm_get_wallclock(struct timespec64 *now)
 {
-	struct pvclock_vcpu_time_info *vcpu_time;
-	int cpu;
-
 	wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
-
-	cpu = get_cpu();
-
-	vcpu_time = &hv_clock[cpu].pvti;
-	pvclock_read_wallclock(&wall_clock, vcpu_time, now);
-
-	put_cpu();
+	preempt_disable();
+	pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
+	preempt_enable();
 }
 
 static int kvm_set_wallclock(const struct timespec64 *now)
@@ -89,14 +94,10 @@ static int kvm_set_wallclock(const struct timespec64 *now)
 
 static u64 kvm_clock_read(void)
 {
-	struct pvclock_vcpu_time_info *src;
 	u64 ret;
-	int cpu;
 
 	preempt_disable_notrace();
-	cpu = smp_processor_id();
-	src = &hv_clock[cpu].pvti;
-	ret = pvclock_clocksource_read(src);
+	ret = pvclock_clocksource_read(this_cpu_pvti());
 	preempt_enable_notrace();
 	return ret;
 }
@@ -141,7 +142,7 @@ static inline void kvm_sched_clock_init(bool stable)
 static unsigned long kvm_get_tsc_khz(void)
 {
 	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
-	return pvclock_tsc_khz(&hv_clock[0].pvti);
+	return pvclock_tsc_khz(this_cpu_pvti());
 }
 
 static void kvm_get_preset_lpj(void)
@@ -158,15 +159,14 @@ static void kvm_get_preset_lpj(void)
 
 bool kvm_check_and_clear_guest_paused(void)
 {
-	struct pvclock_vcpu_time_info *src;
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
 	bool ret = false;
 
-	if (!hv_clock)
+	if (!src)
 		return ret;
 
-	src = &hv_clock[smp_processor_id()].pvti;
-	if ((src->flags & PVCLOCK_GUEST_STOPPED) != 0) {
-		src->flags &= ~PVCLOCK_GUEST_STOPPED;
+	if ((src->pvti.flags & PVCLOCK_GUEST_STOPPED) != 0) {
+		src->pvti.flags &= ~PVCLOCK_GUEST_STOPPED;
 		pvclock_touch_watchdogs();
 		ret = true;
 	}
@@ -184,17 +184,15 @@ EXPORT_SYMBOL_GPL(kvm_clock);
 
 static void kvm_register_clock(char *txt)
 {
-	struct pvclock_vcpu_time_info *src;
-	int cpu = smp_processor_id();
+	struct pvclock_vsyscall_time_info *src = this_cpu_hvclock();
 	u64 pa;
 
-	if (!hv_clock)
+	if (!src)
 		return;
 
-	src = &hv_clock[cpu].pvti;
-	pa = slow_virt_to_phys(src) | 0x01ULL;
+	pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
 	wrmsrl(msr_kvm_system_time, pa);
-	pr_info("kvm-clock: cpu %d, msr %llx, %s", cpu, pa, txt);
+	pr_info("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
 }
 
 static void kvm_save_sched_clock_state(void)
@@ -242,12 +240,12 @@ static int __init kvm_setup_vsyscall_timeinfo(void)
 #ifdef CONFIG_X86_64
 	u8 flags;
 
-	if (!hv_clock || !kvmclock_vsyscall)
+	if (!per_cpu(hv_clock_per_cpu, 0) || !kvmclock_vsyscall)
 		return 0;
 
-	flags = pvclock_read_flags(&hv_clock[0].pvti);
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
 	if (!(flags & PVCLOCK_TSC_STABLE_BIT))
-		return 1;
+		return 0;
 
 	kvm_clock.archdata.vclock_mode = VCLOCK_PVCLOCK;
 #endif
@@ -255,6 +253,28 @@ static int __init kvm_setup_vsyscall_timeinfo(void)
 }
 early_initcall(kvm_setup_vsyscall_timeinfo);
 
+static int kvmclock_setup_percpu(unsigned int cpu)
+{
+	struct pvclock_vsyscall_time_info *p = per_cpu(hv_clock_per_cpu, cpu);
+
+	/*
+	 * The per cpu area setup replicates CPU0 data to all cpu
+	 * pointers. So carefully check. CPU0 has been set up in init
+	 * already.
+	 */
+	if (!cpu || (p && p != per_cpu(hv_clock_per_cpu, 0)))
+		return 0;
+
+	/* Use the static page for the first CPUs, allocate otherwise */
+	if (cpu < HVC_BOOT_ARRAY_SIZE)
+		p = &hv_clock_boot[cpu];
+	else
+		p = kzalloc(sizeof(*p), GFP_KERNEL);
+
+	per_cpu(hv_clock_per_cpu, cpu) = p;
+	return p ? 0 : -ENOMEM;
+}
+
 void __init kvmclock_init(void)
 {
 	u8 flags;
@@ -269,17 +289,22 @@ void __init kvmclock_init(void)
 		return;
 	}
 
+	if (cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "kvmclock:setup_percpu",
+			      kvmclock_setup_percpu, NULL) < 0) {
+		return;
+	}
+
 	pr_info("kvm-clock: Using msrs %x and %x",
 		msr_kvm_system_time, msr_kvm_wall_clock);
 
-	hv_clock = (struct pvclock_vsyscall_time_info *)hv_clock_mem;
+	this_cpu_write(hv_clock_per_cpu, &hv_clock_boot[0]);
 	kvm_register_clock("primary cpu clock");
-	pvclock_set_pvti_cpu0_va(hv_clock);
+	pvclock_set_pvti_cpu0_va(hv_clock_boot);
 
 	if (kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE_STABLE_BIT))
 		pvclock_set_flags(PVCLOCK_TSC_STABLE_BIT);
 
-	flags = pvclock_read_flags(&hv_clock[0].pvti);
+	flags = pvclock_read_flags(&hv_clock_boot[0].pvti);
 	kvm_sched_clock_init(flags & PVCLOCK_TSC_STABLE_BIT);
 
 	x86_platform.calibrate_tsc = kvm_get_tsc_khz;
-- 
cgit v1.2.3


From 6fffacb30349e0903602d664f7ab6fc87e85162e Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:27 -0400
Subject: x86/alternatives, jumplabel: Use text_poke_early() before mm_init()

It supposed to be safe to modify static branches after jump_label_init().
But, because static key modifying code eventually calls text_poke() it can
end up accessing a struct page which has not been initialized yet.

Here is how to quickly reproduce the problem. Insert code like this
into init/main.c:

| +static DEFINE_STATIC_KEY_FALSE(__test);
| asmlinkage __visible void __init start_kernel(void)
| {
|        char *command_line;
|@@ -587,6 +609,10 @@ asmlinkage __visible void __init start_kernel(void)
|        vfs_caches_init_early();
|        sort_main_extable();
|        trap_init();
|+       {
|+       static_branch_enable(&__test);
|+       WARN_ON(!static_branch_likely(&__test));
|+       }
|        mm_init();

The following warnings show-up:
WARNING: CPU: 0 PID: 0 at arch/x86/kernel/alternative.c:701 text_poke+0x20d/0x230
RIP: 0010:text_poke+0x20d/0x230
Call Trace:
 ? text_poke_bp+0x50/0xda
 ? arch_jump_label_transform+0x89/0xe0
 ? __jump_label_update+0x78/0xb0
 ? static_key_enable_cpuslocked+0x4d/0x80
 ? static_key_enable+0x11/0x20
 ? start_kernel+0x23e/0x4c8
 ? secondary_startup_64+0xa5/0xb0

---[ end trace abdc99c031b8a90a ]---

If the code above is moved after mm_init(), no warning is shown, as struct
pages are initialized during handover from memblock.

Use text_poke_early() in static branching until early boot IRQs are enabled
and from there switch to text_poke. Also, ensure text_poke() is never
invoked when unitialized memory access may happen by using adding a
!after_bootmem assertion.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-9-pasha.tatashin@oracle.com
---
 arch/x86/include/asm/text-patching.h |  1 +
 arch/x86/kernel/alternative.c        |  7 +++++++
 arch/x86/kernel/jump_label.c         | 11 +++++++----
 3 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 2ecd34e2d46c..e85ff65c43c3 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -37,5 +37,6 @@ extern void *text_poke_early(void *addr, const void *opcode, size_t len);
 extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern int after_bootmem;
 
 #endif /* _ASM_X86_TEXT_PATCHING_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a481763a3776..014f214da581 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -668,6 +668,7 @@ void *__init_or_module text_poke_early(void *addr, const void *opcode,
 	local_irq_save(flags);
 	memcpy(addr, opcode, len);
 	local_irq_restore(flags);
+	sync_core();
 	/* Could also do a CLFLUSH here to speed up CPU recovery; but
 	   that causes hangs on some VIA CPUs. */
 	return addr;
@@ -693,6 +694,12 @@ void *text_poke(void *addr, const void *opcode, size_t len)
 	struct page *pages[2];
 	int i;
 
+	/*
+	 * While boot memory allocator is runnig we cannot use struct
+	 * pages as they are not yet initialized.
+	 */
+	BUG_ON(!after_bootmem);
+
 	if (!core_kernel_text((unsigned long)addr)) {
 		pages[0] = vmalloc_to_page(addr);
 		pages[1] = vmalloc_to_page(addr + PAGE_SIZE);
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index e56c95be2808..eeea935e9bb5 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -37,15 +37,18 @@ static void bug_at(unsigned char *ip, int line)
 	BUG();
 }
 
-static void __jump_label_transform(struct jump_entry *entry,
-				   enum jump_label_type type,
-				   void *(*poker)(void *, const void *, size_t),
-				   int init)
+static void __ref __jump_label_transform(struct jump_entry *entry,
+					 enum jump_label_type type,
+					 void *(*poker)(void *, const void *, size_t),
+					 int init)
 {
 	union jump_code_union code;
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
 
+	if (early_boot_irqs_disabled)
+		poker = text_poke_early;
+
 	if (type == JUMP_LABEL_JMP) {
 		if (init) {
 			/*
-- 
cgit v1.2.3


From 8990cac6e5ea7fa57607736019fe8dca961b998f Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:28 -0400
Subject: x86/jump_label: Initialize static branching early

Static branching is useful to runtime patch branches that are used in hot
path, but are infrequently changed.

The x86 clock framework is one example that uses static branches to setup
the best clock during boot and never changes it again.

It is desired to enable the TSC based sched clock early to allow fine
grained boot time analysis early on. That requires the static branching
functionality to be functional early as well.

Static branching requires patching nop instructions, thus,
arch_init_ideal_nops() must be called prior to jump_label_init().

Do all the necessary steps to call arch_init_ideal_nops() right after
early_cpu_init(), which also allows to insert a call to jump_label_init()
right after that. jump_label_init() will be called again from the generic
init code, but the code is protected against reinitialization already.

[ tglx: Massaged changelog ]

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Borislav Petkov <bp@suse.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-10-pasha.tatashin@oracle.com
---
 arch/x86/kernel/cpu/amd.c    | 13 ++++++++-----
 arch/x86/kernel/cpu/common.c | 38 ++++++++++++++++++++------------------
 arch/x86/kernel/setup.c      |  4 ++--
 3 files changed, 30 insertions(+), 25 deletions(-)

diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 38915fbfae73..b732438c1a1e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -232,8 +232,6 @@ static void init_amd_k7(struct cpuinfo_x86 *c)
 		}
 	}
 
-	set_cpu_cap(c, X86_FEATURE_K7);
-
 	/* calling is from identify_secondary_cpu() ? */
 	if (!c->cpu_index)
 		return;
@@ -617,6 +615,14 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 
 	early_init_amd_mc(c);
 
+#ifdef CONFIG_X86_32
+	if (c->x86 == 6)
+		set_cpu_cap(c, X86_FEATURE_K7);
+#endif
+
+	if (c->x86 >= 0xf)
+		set_cpu_cap(c, X86_FEATURE_K8);
+
 	rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
 
 	/*
@@ -863,9 +869,6 @@ static void init_amd(struct cpuinfo_x86 *c)
 
 	init_amd_cacheinfo(c);
 
-	if (c->x86 >= 0xf)
-		set_cpu_cap(c, X86_FEATURE_K8);
-
 	if (cpu_has(c, X86_FEATURE_XMM2)) {
 		unsigned long long val;
 		int ret;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb4cb3efd20e..71281ac43b15 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1015,6 +1015,24 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN);
 }
 
+/*
+ * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
+ * unfortunately, that's not true in practice because of early VIA
+ * chips and (more importantly) broken virtualizers that are not easy
+ * to detect. In the latter case it doesn't even *fail* reliably, so
+ * probing for it doesn't even work. Disable it completely on 32-bit
+ * unless we can find a reliable way to detect all the broken cases.
+ * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
+ */
+static void detect_nopl(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_X86_32
+	clear_cpu_cap(c, X86_FEATURE_NOPL);
+#else
+	set_cpu_cap(c, X86_FEATURE_NOPL);
+#endif
+}
+
 /*
  * Do minimum CPU detection early.
  * Fields really needed: vendor, cpuid_level, family, model, mask,
@@ -1089,6 +1107,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (!pgtable_l5_enabled())
 		setup_clear_cpu_cap(X86_FEATURE_LA57);
+
+	detect_nopl(c);
 }
 
 void __init early_cpu_init(void)
@@ -1124,24 +1144,6 @@ void __init early_cpu_init(void)
 	early_identify_cpu(&boot_cpu_data);
 }
 
-/*
- * The NOPL instruction is supposed to exist on all CPUs of family >= 6;
- * unfortunately, that's not true in practice because of early VIA
- * chips and (more importantly) broken virtualizers that are not easy
- * to detect. In the latter case it doesn't even *fail* reliably, so
- * probing for it doesn't even work. Disable it completely on 32-bit
- * unless we can find a reliable way to detect all the broken cases.
- * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
- */
-static void detect_nopl(struct cpuinfo_x86 *c)
-{
-#ifdef CONFIG_X86_32
-	clear_cpu_cap(c, X86_FEATURE_NOPL);
-#else
-	set_cpu_cap(c, X86_FEATURE_NOPL);
-#endif
-}
-
 static void detect_null_seg_behavior(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index da1dbd99cb6e..7490de925a81 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -866,6 +866,8 @@ void __init setup_arch(char **cmdline_p)
 
 	idt_setup_early_traps();
 	early_cpu_init();
+	arch_init_ideal_nops();
+	jump_label_init();
 	early_ioremap_init();
 
 	setup_olpc_ofw_pgd();
@@ -1268,8 +1270,6 @@ void __init setup_arch(char **cmdline_p)
 
 	mcheck_init();
 
-	arch_init_ideal_nops();
-
 	register_refined_jiffies(CLOCK_TICK_RATE);
 
 #ifdef CONFIG_EFI
-- 
cgit v1.2.3


From 9b3661cd7e5400689ed168a7275e75af333177e6 Mon Sep 17 00:00:00 2001
From: Borislav Petkov <bp@alien8.de>
Date: Thu, 19 Jul 2018 16:55:29 -0400
Subject: x86/CPU: Call detect_nopl() only on the BSP

Make it use the setup_* variants and have it be called only on the BSP and
drop the call in generic_identify() - X86_FEATURE_NOPL will be replicated
to the APs through the forced caps. Helps to keep the mess at a manageable
level.

Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-11-pasha.tatashin@oracle.com
---
 arch/x86/kernel/cpu/common.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 71281ac43b15..46408a8cdf62 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1024,12 +1024,12 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
  * unless we can find a reliable way to detect all the broken cases.
  * Enable it explicitly on 64-bit for non-constant inputs of cpu_has().
  */
-static void detect_nopl(struct cpuinfo_x86 *c)
+static void detect_nopl(void)
 {
 #ifdef CONFIG_X86_32
-	clear_cpu_cap(c, X86_FEATURE_NOPL);
+	setup_clear_cpu_cap(X86_FEATURE_NOPL);
 #else
-	set_cpu_cap(c, X86_FEATURE_NOPL);
+	setup_force_cpu_cap(X86_FEATURE_NOPL);
 #endif
 }
 
@@ -1108,7 +1108,7 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 	if (!pgtable_l5_enabled())
 		setup_clear_cpu_cap(X86_FEATURE_LA57);
 
-	detect_nopl(c);
+	detect_nopl();
 }
 
 void __init early_cpu_init(void)
@@ -1206,8 +1206,6 @@ static void generic_identify(struct cpuinfo_x86 *c)
 
 	get_model_name(c); /* Default name */
 
-	detect_nopl(c);
-
 	detect_null_seg_behavior(c);
 
 	/*
-- 
cgit v1.2.3


From fe9af81e524e8a86bdd59c0cc0d9e2b0ccaf840f Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:30 -0400
Subject: x86/tsc: Redefine notsc to behave as tsc=unstable

Currently, the notsc kernel parameter disables the use of the TSC by
sched_clock(). However, this parameter does not prevent the kernel from
accessing tsc in other places.

The only rationale to boot with notsc is to avoid timing discrepancies on
multi-socket systems where TSC are not properly synchronized, and thus
exclude TSC from being used for time keeping. But that prevents using TSC
as sched_clock() as well, which is not necessary as the core sched_clock()
implementation can handle non synchronized TSC based sched clocks just
fine.

However, there is another method to solve the above problem: booting with
tsc=unstable parameter. This parameter allows sched_clock() to use TSC and
just excludes it from timekeeping.

So there is no real reason to keep notsc, but for compatibility reasons the
parameter has to stay. Make it behave like 'tsc=unstable' instead.

[ tglx: Massaged changelog ]

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-12-pasha.tatashin@oracle.com
---
 Documentation/admin-guide/kernel-parameters.txt |  2 --
 Documentation/x86/x86_64/boot-options.txt       |  4 +---
 arch/x86/kernel/tsc.c                           | 18 +++---------------
 3 files changed, 4 insertions(+), 20 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 533ff5c68970..5aed30cd0350 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2835,8 +2835,6 @@
 
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
-	notsc		[BUGS=X86-32] Disable Time Stamp Counter
-
 	nowatchdog	[KNL] Disable both lockup detectors, i.e.
 			soft-lockup and NMI watchdog (hard-lockup).
 
diff --git a/Documentation/x86/x86_64/boot-options.txt b/Documentation/x86/x86_64/boot-options.txt
index 8d109ef67ab6..66114ab4f9fe 100644
--- a/Documentation/x86/x86_64/boot-options.txt
+++ b/Documentation/x86/x86_64/boot-options.txt
@@ -92,9 +92,7 @@ APICs
 Timing
 
   notsc
-  Don't use the CPU time stamp counter to read the wall time.
-  This can be used to work around timing problems on multiprocessor systems
-  with not properly synchronized CPUs.
+  Deprecated, use tsc=unstable instead.
 
   nohpet
   Don't use the HPET timer.
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 74392d9d51e0..186395041725 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -38,11 +38,6 @@ EXPORT_SYMBOL(tsc_khz);
  */
 static int __read_mostly tsc_unstable;
 
-/* native_sched_clock() is called before tsc_init(), so
-   we must start with the TSC soft disabled to prevent
-   erroneous rdtsc usage on !boot_cpu_has(X86_FEATURE_TSC) processors */
-static int __read_mostly tsc_disabled = -1;
-
 static DEFINE_STATIC_KEY_FALSE(__use_tsc);
 
 int tsc_clocksource_reliable;
@@ -248,8 +243,7 @@ EXPORT_SYMBOL_GPL(check_tsc_unstable);
 #ifdef CONFIG_X86_TSC
 int __init notsc_setup(char *str)
 {
-	pr_warn("Kernel compiled with CONFIG_X86_TSC, cannot disable TSC completely\n");
-	tsc_disabled = 1;
+	mark_tsc_unstable("boot parameter notsc");
 	return 1;
 }
 #else
@@ -1307,7 +1301,7 @@ unreg:
 
 static int __init init_tsc_clocksource(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_TSC) || tsc_disabled > 0 || !tsc_khz)
+	if (!boot_cpu_has(X86_FEATURE_TSC) || !tsc_khz)
 		return 0;
 
 	if (tsc_unstable)
@@ -1414,12 +1408,6 @@ void __init tsc_init(void)
 		set_cyc2ns_scale(tsc_khz, cpu, cyc);
 	}
 
-	if (tsc_disabled > 0)
-		return;
-
-	/* now allow native_sched_clock() to use rdtsc */
-
-	tsc_disabled = 0;
 	static_branch_enable(&__use_tsc);
 
 	if (!no_sched_irq_time)
@@ -1455,7 +1443,7 @@ unsigned long calibrate_delay_is_known(void)
 	int constant_tsc = cpu_has(&cpu_data(cpu), X86_FEATURE_CONSTANT_TSC);
 	const struct cpumask *mask = topology_core_cpumask(cpu);
 
-	if (tsc_disabled || !constant_tsc || !mask)
+	if (!constant_tsc || !mask)
 		return 0;
 
 	sibling = cpumask_any_but(mask, cpu);
-- 
cgit v1.2.3


From 7b25b9cb0dad8395b5cf5a02196d0e88ccda67d5 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:31 -0400
Subject: x86/xen/time: Initialize pv xen time in init_hypervisor_platform()

In every hypervisor except for xen pv time ops are initialized in
init_hypervisor_platform().

Xen PV domains initialize time ops in x86_init.paging.pagetable_init(),
by calling xen_setup_shared_info() which is a poor design, as time is
needed prior to memory allocator.

xen_setup_shared_info() is called from two places: during boot, and
after suspend. Split the content of xen_setup_shared_info() into
three places:

1. add the clock relavent data into new xen pv init_platform vector, and
   set clock ops in there.

2. move xen_setup_vcpu_info_placement() to new xen_pv_guest_late_init()
   call.

3. Re-initializing parts of shared info copy to xen_pv_post_suspend() to
   be symmetric to xen_pv_pre_suspend

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-13-pasha.tatashin@oracle.com
---
 arch/x86/xen/enlighten_pv.c | 51 +++++++++++++++++++++------------------------
 arch/x86/xen/mmu_pv.c       |  6 ++----
 arch/x86/xen/suspend_pv.c   |  5 +++--
 arch/x86/xen/time.c         |  7 +++----
 arch/x86/xen/xen-ops.h      |  6 ++----
 5 files changed, 34 insertions(+), 41 deletions(-)

diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 439a94bf89ad..105a57d73701 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -119,6 +119,27 @@ static void __init xen_banner(void)
 	       version >> 16, version & 0xffff, extra.extraversion,
 	       xen_feature(XENFEAT_mmu_pt_update_preserve_ad) ? " (preserve-AD)" : "");
 }
+
+static void __init xen_pv_init_platform(void)
+{
+	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+	HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+
+	/* xen clock uses per-cpu vcpu_info, need to init it for boot cpu */
+	xen_vcpu_info_reset(0);
+
+	/* pvclock is in shared info area */
+	xen_init_time_ops();
+}
+
+static void __init xen_pv_guest_late_init(void)
+{
+#ifndef CONFIG_SMP
+	/* Setup shared vcpu info for non-smp configurations */
+	xen_setup_vcpu_info_placement();
+#endif
+}
+
 /* Check if running on Xen version (major, minor) or later */
 bool
 xen_running_on_version_or_later(unsigned int major, unsigned int minor)
@@ -947,34 +968,8 @@ static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
 	xen_write_msr_safe(msr, low, high);
 }
 
-void xen_setup_shared_info(void)
-{
-	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
-
-	HYPERVISOR_shared_info =
-		(struct shared_info *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
-
-	xen_setup_mfn_list_list();
-
-	if (system_state == SYSTEM_BOOTING) {
-#ifndef CONFIG_SMP
-		/*
-		 * In UP this is as good a place as any to set up shared info.
-		 * Limit this to boot only, at restore vcpu setup is done via
-		 * xen_vcpu_restore().
-		 */
-		xen_setup_vcpu_info_placement();
-#endif
-		/*
-		 * Now that shared info is set up we can start using routines
-		 * that point to pvclock area.
-		 */
-		xen_init_time_ops();
-	}
-}
-
 /* This is called once we have the cpu_possible_mask */
-void __ref xen_setup_vcpu_info_placement(void)
+void __init xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
 
@@ -1228,6 +1223,8 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	x86_init.irqs.intr_mode_init	= x86_init_noop;
 	x86_init.oem.arch_setup = xen_arch_setup;
 	x86_init.oem.banner = xen_banner;
+	x86_init.hyper.init_platform = xen_pv_init_platform;
+	x86_init.hyper.guest_late_init = xen_pv_guest_late_init;
 
 	/*
 	 * Set up some pagetable state before starting to set any ptes.
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 2c30cabfda90..52206ad81e4b 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -1230,8 +1230,7 @@ static void __init xen_pagetable_p2m_free(void)
 	 * We roundup to the PMD, which means that if anybody at this stage is
 	 * using the __ka address of xen_start_info or
 	 * xen_start_info->shared_info they are in going to crash. Fortunatly
-	 * we have already revectored in xen_setup_kernel_pagetable and in
-	 * xen_setup_shared_info.
+	 * we have already revectored in xen_setup_kernel_pagetable.
 	 */
 	size = roundup(size, PMD_SIZE);
 
@@ -1292,8 +1291,7 @@ static void __init xen_pagetable_init(void)
 
 	/* Remap memory freed due to conflicts with E820 map */
 	xen_remap_memory();
-
-	xen_setup_shared_info();
+	xen_setup_mfn_list_list();
 }
 static void xen_write_cr2(unsigned long cr2)
 {
diff --git a/arch/x86/xen/suspend_pv.c b/arch/x86/xen/suspend_pv.c
index a2e0f110af56..8303b58c79a9 100644
--- a/arch/x86/xen/suspend_pv.c
+++ b/arch/x86/xen/suspend_pv.c
@@ -27,8 +27,9 @@ void xen_pv_pre_suspend(void)
 void xen_pv_post_suspend(int suspend_cancelled)
 {
 	xen_build_mfn_list_list();
-
-	xen_setup_shared_info();
+	set_fixmap(FIX_PARAVIRT_BOOTMAP, xen_start_info->shared_info);
+	HYPERVISOR_shared_info = (void *)fix_to_virt(FIX_PARAVIRT_BOOTMAP);
+	xen_setup_mfn_list_list();
 
 	if (suspend_cancelled) {
 		xen_start_info->store_mfn =
diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index e0f1bcf01d63..53bb7a8d10b5 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -40,7 +40,7 @@ static unsigned long xen_tsc_khz(void)
 	return pvclock_tsc_khz(info);
 }
 
-u64 xen_clocksource_read(void)
+static u64 xen_clocksource_read(void)
 {
         struct pvclock_vcpu_time_info *src;
 	u64 ret;
@@ -503,7 +503,7 @@ static void __init xen_time_init(void)
 		pvclock_gtod_register_notifier(&xen_pvclock_gtod_notifier);
 }
 
-void __ref xen_init_time_ops(void)
+void __init xen_init_time_ops(void)
 {
 	pv_time_ops = xen_time_ops;
 
@@ -542,8 +542,7 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 
 	if (!xen_feature(XENFEAT_hvm_safe_pvclock)) {
-		printk(KERN_INFO "Xen doesn't support pvclock on HVM,"
-				"disable pv timer\n");
+		pr_info("Xen doesn't support pvclock on HVM, disable pv timer");
 		return;
 	}
 
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 3b34745d0a52..e78684597f57 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -31,7 +31,6 @@ extern struct shared_info xen_dummy_shared_info;
 extern struct shared_info *HYPERVISOR_shared_info;
 
 void xen_setup_mfn_list_list(void);
-void xen_setup_shared_info(void);
 void xen_build_mfn_list_list(void);
 void xen_setup_machphys_mapping(void);
 void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn);
@@ -68,12 +67,11 @@ void xen_init_irq_ops(void);
 void xen_setup_timer(int cpu);
 void xen_setup_runstate_info(int cpu);
 void xen_teardown_timer(int cpu);
-u64 xen_clocksource_read(void);
 void xen_setup_cpu_clockevents(void);
 void xen_save_time_memory_area(void);
 void xen_restore_time_memory_area(void);
-void __ref xen_init_time_ops(void);
-void __init xen_hvm_init_time_ops(void);
+void xen_init_time_ops(void);
+void xen_hvm_init_time_ops(void);
 
 irqreturn_t xen_debug_interrupt(int irq, void *dev_id);
 
-- 
cgit v1.2.3


From 38669ba205d178d2d38bfd194a196d65a44d5af2 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:32 -0400
Subject: x86/xen/time: Output xen sched_clock time from 0

It is expected for sched_clock() to output data from 0, when system boots.

Add an offset xen_sched_clock_offset (similarly how it is done in other
hypervisors i.e. kvm_sched_clock_offset) to count sched_clock() from 0,
when time is first initialized.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-14-pasha.tatashin@oracle.com
---
 arch/x86/xen/time.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/xen/time.c b/arch/x86/xen/time.c
index 53bb7a8d10b5..c84f1e039d84 100644
--- a/arch/x86/xen/time.c
+++ b/arch/x86/xen/time.c
@@ -31,6 +31,8 @@
 /* Xen may fire a timer up to this many ns early */
 #define TIMER_SLOP	100000
 
+static u64 xen_sched_clock_offset __read_mostly;
+
 /* Get the TSC speed from Xen */
 static unsigned long xen_tsc_khz(void)
 {
@@ -57,6 +59,11 @@ static u64 xen_clocksource_get_cycles(struct clocksource *cs)
 	return xen_clocksource_read();
 }
 
+static u64 xen_sched_clock(void)
+{
+	return xen_clocksource_read() - xen_sched_clock_offset;
+}
+
 static void xen_read_wallclock(struct timespec64 *ts)
 {
 	struct shared_info *s = HYPERVISOR_shared_info;
@@ -367,7 +374,7 @@ void xen_timer_resume(void)
 }
 
 static const struct pv_time_ops xen_time_ops __initconst = {
-	.sched_clock = xen_clocksource_read,
+	.sched_clock = xen_sched_clock,
 	.steal_clock = xen_steal_clock,
 };
 
@@ -505,6 +512,7 @@ static void __init xen_time_init(void)
 
 void __init xen_init_time_ops(void)
 {
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 
 	x86_init.timers.timer_init = xen_time_init;
@@ -546,6 +554,7 @@ void __init xen_hvm_init_time_ops(void)
 		return;
 	}
 
+	xen_sched_clock_offset = xen_clocksource_read();
 	pv_time_ops = xen_time_ops;
 	x86_init.timers.setup_percpu_clockev = xen_time_init;
 	x86_cpuinit.setup_percpu_clockev = xen_hvm_setup_cpu_clockevents;
-- 
cgit v1.2.3


From be2e0e4257678408b0ab00ea9e743b9094e393e8 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:33 -0400
Subject: s390/time: Add read_persistent_wall_and_boot_offset()

read_persistent_wall_and_boot_offset() will replace read_boot_clock64()
because on some architectures it is more convenient to read both sources
as one may depend on the other. For s390, implementation is the same
as read_boot_clock64() but also calling and returning value of
read_persistent_clock64()

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-15-pasha.tatashin@oracle.com
---
 arch/s390/kernel/time.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index cf561160ea88..d1f5447d5687 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -221,6 +221,24 @@ void read_persistent_clock64(struct timespec64 *ts)
 	ext_to_timespec64(clk, ts);
 }
 
+void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+						 struct timespec64 *boot_offset)
+{
+	unsigned char clk[STORE_CLOCK_EXT_SIZE];
+	struct timespec64 boot_time;
+	__u64 delta;
+
+	delta = initial_leap_seconds + TOD_UNIX_EPOCH;
+	memcpy(clk, tod_clock_base, STORE_CLOCK_EXT_SIZE);
+	*(__u64 *)&clk[1] -= delta;
+	if (*(__u64 *)&clk[1] > delta)
+		clk[0]--;
+	ext_to_timespec64(clk, &boot_time);
+
+	read_persistent_clock64(wall_time);
+	*boot_offset = timespec64_sub(*wall_time, boot_time);
+}
+
 void read_boot_clock64(struct timespec64 *ts)
 {
 	unsigned char clk[STORE_CLOCK_EXT_SIZE];
-- 
cgit v1.2.3


From 3eca993740b8eb40f514b90b1877a4dbcf0a6710 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:34 -0400
Subject: timekeeping: Replace read_boot_clock64() with
 read_persistent_wall_and_boot_offset()

If architecture does not support exact boot time, it is challenging to
estimate boot time without having a reference to the current persistent
clock value. Yet, it cannot read the persistent clock time again, because
this may lead to math discrepancies with the caller of read_boot_clock64()
who have read the persistent clock at a different time.

This is why it is better to provide two values simultaneously: the
persistent clock value, and the boot time.

Replace read_boot_clock64() with:
read_persistent_wall_and_boot_offset(wall_time, boot_offset)

Where wall_time is returned by read_persistent_clock() And boot_offset is
wall_time - boot time, which defaults to 0.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-16-pasha.tatashin@oracle.com
---
 include/linux/timekeeping.h |  3 ++-
 kernel/time/timekeeping.c   | 59 +++++++++++++++++++++++----------------------
 2 files changed, 32 insertions(+), 30 deletions(-)

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 86bc2026efce..686bc27acef0 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -243,7 +243,8 @@ extern void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot);
 extern int persistent_clock_is_local;
 
 extern void read_persistent_clock64(struct timespec64 *ts);
-extern void read_boot_clock64(struct timespec64 *ts);
+void read_persistent_clock_and_boot_offset(struct timespec64 *wall_clock,
+					   struct timespec64 *boot_offset);
 extern int update_persistent_clock64(struct timespec64 now);
 
 /*
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 4786df904c22..cb738f825c12 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -17,6 +17,7 @@
 #include <linux/nmi.h>
 #include <linux/sched.h>
 #include <linux/sched/loadavg.h>
+#include <linux/sched/clock.h>
 #include <linux/syscore_ops.h>
 #include <linux/clocksource.h>
 #include <linux/jiffies.h>
@@ -1496,18 +1497,20 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
 }
 
 /**
- * read_boot_clock64 -  Return time of the system start.
+ * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset
+ *                                        from the boot.
  *
  * Weak dummy function for arches that do not yet support it.
- * Function to read the exact time the system has been started.
- * Returns a timespec64 with tv_sec=0 and tv_nsec=0 if unsupported.
- *
- *  XXX - Do be sure to remove it once all arches implement it.
+ * wall_time	- current time as returned by persistent clock
+ * boot_offset	- offset that is defined as wall_time - boot_time
+ *		  default to 0.
  */
-void __weak read_boot_clock64(struct timespec64 *ts)
+void __weak __init
+read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
+				     struct timespec64 *boot_offset)
 {
-	ts->tv_sec = 0;
-	ts->tv_nsec = 0;
+	read_persistent_clock64(wall_time);
+	*boot_offset = (struct timespec64){0};
 }
 
 /* Flag for if timekeeping_resume() has injected sleeptime */
@@ -1521,28 +1524,29 @@ static bool persistent_clock_exists;
  */
 void __init timekeeping_init(void)
 {
+	struct timespec64 wall_time, boot_offset, wall_to_mono;
 	struct timekeeper *tk = &tk_core.timekeeper;
 	struct clocksource *clock;
 	unsigned long flags;
-	struct timespec64 now, boot, tmp;
-
-	read_persistent_clock64(&now);
-	if (!timespec64_valid_strict(&now)) {
-		pr_warn("WARNING: Persistent clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		now.tv_sec = 0;
-		now.tv_nsec = 0;
-	} else if (now.tv_sec || now.tv_nsec)
-		persistent_clock_exists = true;
 
-	read_boot_clock64(&boot);
-	if (!timespec64_valid_strict(&boot)) {
-		pr_warn("WARNING: Boot clock returned invalid value!\n"
-			"         Check your CMOS/BIOS settings.\n");
-		boot.tv_sec = 0;
-		boot.tv_nsec = 0;
+	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
+	if (timespec64_valid_strict(&wall_time) &&
+	    timespec64_to_ns(&wall_time) > 0) {
+		persistent_clock_exists = true;
+	} else {
+		pr_warn("Persistent clock returned invalid value");
+		wall_time = (struct timespec64){0};
 	}
 
+	if (timespec64_compare(&wall_time, &boot_offset) < 0)
+		boot_offset = (struct timespec64){0};
+
+	/*
+	 * We want set wall_to_mono, so the following is true:
+	 * wall time + wall_to_mono = boot time
+	 */
+	wall_to_mono = timespec64_sub(boot_offset, wall_time);
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	ntp_init();
@@ -1552,13 +1556,10 @@ void __init timekeeping_init(void)
 		clock->enable(clock);
 	tk_setup_internals(tk, clock);
 
-	tk_set_xtime(tk, &now);
+	tk_set_xtime(tk, &wall_time);
 	tk->raw_sec = 0;
-	if (boot.tv_sec == 0 && boot.tv_nsec == 0)
-		boot = tk_xtime(tk);
 
-	set_normalized_timespec64(&tmp, -boot.tv_sec, -boot.tv_nsec);
-	tk_set_wall_to_mono(tk, tmp);
+	tk_set_wall_to_mono(tk, wall_to_mono);
 
 	timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET);
 
-- 
cgit v1.2.3


From 4b1b7f8054896cee25669f6cea7cb6dd17f508f7 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:35 -0400
Subject: timekeeping: Default boot time offset to local_clock()

read_persistent_wall_and_boot_offset() is called during boot to read
both the persistent clock and also return the offset between the boot time
and the value of persistent clock.

Change the default boot_offset from zero to local_clock() so architectures,
that do not have a dedicated boot_clock but have early sched_clock(), such
as SPARCv9, x86, and possibly more will benefit from this change by getting
a better and more consistent estimate of the boot time without need for an
arch specific implementation.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-17-pasha.tatashin@oracle.com
---
 kernel/time/timekeeping.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index cb738f825c12..30d7f64ffc87 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1503,14 +1503,17 @@ void __weak read_persistent_clock64(struct timespec64 *ts64)
  * Weak dummy function for arches that do not yet support it.
  * wall_time	- current time as returned by persistent clock
  * boot_offset	- offset that is defined as wall_time - boot_time
- *		  default to 0.
+ * The default function calculates offset based on the current value of
+ * local_clock(). This way architectures that support sched_clock() but don't
+ * support dedicated boot time clock will provide the best estimate of the
+ * boot time.
  */
 void __weak __init
 read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
 				     struct timespec64 *boot_offset)
 {
 	read_persistent_clock64(wall_time);
-	*boot_offset = (struct timespec64){0};
+	*boot_offset = ns_to_timespec64(local_clock());
 }
 
 /* Flag for if timekeeping_resume() has injected sleeptime */
-- 
cgit v1.2.3


From 00067a6db2e95f3b9d9a017b3be3c715d54cc0de Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:36 -0400
Subject: s390/time: Remove read_boot_clock64()

read_boot_clock64() was replaced by read_persistent_wall_and_boot_offset()
so remove it.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-18-pasha.tatashin@oracle.com
---
 arch/s390/kernel/time.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index d1f5447d5687..e8766beee5ad 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -239,19 +239,6 @@ void __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
 	*boot_offset = timespec64_sub(*wall_time, boot_time);
 }
 
-void read_boot_clock64(struct timespec64 *ts)
-{
-	unsigned char clk[STORE_CLOCK_EXT_SIZE];
-	__u64 delta;
-
-	delta = initial_leap_seconds + TOD_UNIX_EPOCH;
-	memcpy(clk, tod_clock_base, 16);
-	*(__u64 *) &clk[1] -= delta;
-	if (*(__u64 *) &clk[1] > delta)
-		clk[0]--;
-	ext_to_timespec64(clk, ts);
-}
-
 static u64 read_tod_clock(struct clocksource *cs)
 {
 	unsigned long long now, adj;
-- 
cgit v1.2.3


From 227e3958a780499b3ec41c36d4752ac4f4962874 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:37 -0400
Subject: ARM/time: Remove read_boot_clock64()

read_boot_clock64() is deleted, and replaced with
read_persistent_wall_and_boot_offset().

The default implementation of read_persistent_wall_and_boot_offset()
provides a better fallback than the current stubs for read_boot_clock64()
that arm has with no users, so remove the old code.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-19-pasha.tatashin@oracle.com
---
 arch/arm/include/asm/mach/time.h    |  3 +--
 arch/arm/kernel/time.c              | 15 ++-------------
 arch/arm/plat-omap/counter_32k.c    |  2 +-
 drivers/clocksource/tegra20_timer.c |  2 +-
 4 files changed, 5 insertions(+), 17 deletions(-)

diff --git a/arch/arm/include/asm/mach/time.h b/arch/arm/include/asm/mach/time.h
index 0f79e4dec7f9..4ac3a019a46f 100644
--- a/arch/arm/include/asm/mach/time.h
+++ b/arch/arm/include/asm/mach/time.h
@@ -13,7 +13,6 @@
 extern void timer_tick(void);
 
 typedef void (*clock_access_fn)(struct timespec64 *);
-extern int register_persistent_clock(clock_access_fn read_boot,
-				     clock_access_fn read_persistent);
+extern int register_persistent_clock(clock_access_fn read_persistent);
 
 #endif
diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c
index cf2701cb0de8..078b259ead4e 100644
--- a/arch/arm/kernel/time.c
+++ b/arch/arm/kernel/time.c
@@ -83,29 +83,18 @@ static void dummy_clock_access(struct timespec64 *ts)
 }
 
 static clock_access_fn __read_persistent_clock = dummy_clock_access;
-static clock_access_fn __read_boot_clock = dummy_clock_access;
 
 void read_persistent_clock64(struct timespec64 *ts)
 {
 	__read_persistent_clock(ts);
 }
 
-void read_boot_clock64(struct timespec64 *ts)
-{
-	__read_boot_clock(ts);
-}
-
-int __init register_persistent_clock(clock_access_fn read_boot,
-				     clock_access_fn read_persistent)
+int __init register_persistent_clock(clock_access_fn read_persistent)
 {
 	/* Only allow the clockaccess functions to be registered once */
-	if (__read_persistent_clock == dummy_clock_access &&
-	    __read_boot_clock == dummy_clock_access) {
-		if (read_boot)
-			__read_boot_clock = read_boot;
+	if (__read_persistent_clock == dummy_clock_access) {
 		if (read_persistent)
 			__read_persistent_clock = read_persistent;
-
 		return 0;
 	}
 
diff --git a/arch/arm/plat-omap/counter_32k.c b/arch/arm/plat-omap/counter_32k.c
index 2438b96004c1..fcc5bfec8bd1 100644
--- a/arch/arm/plat-omap/counter_32k.c
+++ b/arch/arm/plat-omap/counter_32k.c
@@ -110,7 +110,7 @@ int __init omap_init_clocksource_32k(void __iomem *vbase)
 	}
 
 	sched_clock_register(omap_32k_read_sched_clock, 32, 32768);
-	register_persistent_clock(NULL, omap_read_persistent_clock64);
+	register_persistent_clock(omap_read_persistent_clock64);
 	pr_info("OMAP clocksource: 32k_counter at 32768 Hz\n");
 
 	return 0;
diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index c337a8100a7b..2242a36fc5b0 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -259,6 +259,6 @@ static int __init tegra20_init_rtc(struct device_node *np)
 	else
 		clk_prepare_enable(clk);
 
-	return register_persistent_clock(NULL, tegra_read_persistent_clock64);
+	return register_persistent_clock(tegra_read_persistent_clock64);
 }
 TIMER_OF_DECLARE(tegra20_rtc, "nvidia,tegra20-rtc", tegra20_init_rtc);
-- 
cgit v1.2.3


From cf7a63ef4e0203f6f33284c69e8188d91422de83 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:38 -0400
Subject: x86/tsc: Calibrate tsc only once

During boot tsc is calibrated twice: once in tsc_early_delay_calibrate(),
and the second time in tsc_init().

Rename tsc_early_delay_calibrate() to tsc_early_init(), and rework it so
the calibration is done only early, and make tsc_init() to use the values
already determined in tsc_early_init().

Sometimes it is not possible to determine tsc early, as the subsystem that
is required is not yet initialized, in such case try again later in
tsc_init().

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-20-pasha.tatashin@oracle.com
---
 arch/x86/include/asm/tsc.h |  2 +-
 arch/x86/kernel/setup.c    |  2 +-
 arch/x86/kernel/tsc.c      | 87 +++++++++++++++++++++++++---------------------
 3 files changed, 49 insertions(+), 42 deletions(-)

diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 2701d221583a..c4368ff73652 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -33,7 +33,7 @@ static inline cycles_t get_cycles(void)
 extern struct system_counterval_t convert_art_to_tsc(u64 art);
 extern struct system_counterval_t convert_art_ns_to_tsc(u64 art_ns);
 
-extern void tsc_early_delay_calibrate(void);
+extern void tsc_early_init(void);
 extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 7490de925a81..5d32c55aeb8b 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1014,6 +1014,7 @@ void __init setup_arch(char **cmdline_p)
 	 */
 	init_hypervisor_platform();
 
+	tsc_early_init();
 	x86_init.resources.probe_roms();
 
 	/* after parse_early_param, so could debug it */
@@ -1199,7 +1200,6 @@ void __init setup_arch(char **cmdline_p)
 
 	memblock_find_dma_reserve();
 
-	tsc_early_delay_calibrate();
 	if (!early_xdbc_setup_hardware())
 		early_xdbc_register_console();
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 186395041725..4cab2236169e 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -33,6 +33,8 @@ EXPORT_SYMBOL(cpu_khz);
 unsigned int __read_mostly tsc_khz;
 EXPORT_SYMBOL(tsc_khz);
 
+#define KHZ	1000
+
 /*
  * TSC can be unstable due to cpufreq or due to unsynced TSCs
  */
@@ -1335,34 +1337,10 @@ unreg:
  */
 device_initcall(init_tsc_clocksource);
 
-void __init tsc_early_delay_calibrate(void)
-{
-	unsigned long lpj;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC))
-		return;
-
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
-
-	tsc_khz = tsc_khz ? : cpu_khz;
-	if (!tsc_khz)
-		return;
-
-	lpj = tsc_khz * 1000;
-	do_div(lpj, HZ);
-	loops_per_jiffy = lpj;
-}
-
-void __init tsc_init(void)
+static bool __init determine_cpu_tsc_frequencies(void)
 {
-	u64 lpj, cyc;
-	int cpu;
-
-	if (!boot_cpu_has(X86_FEATURE_TSC)) {
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
-	}
+	/* Make sure that cpu and tsc are not already calibrated */
+	WARN_ON(cpu_khz || tsc_khz);
 
 	cpu_khz = x86_platform.calibrate_cpu();
 	tsc_khz = x86_platform.calibrate_tsc();
@@ -1377,20 +1355,52 @@ void __init tsc_init(void)
 	else if (abs(cpu_khz - tsc_khz) * 10 > tsc_khz)
 		cpu_khz = tsc_khz;
 
-	if (!tsc_khz) {
-		mark_tsc_unstable("could not calculate TSC khz");
-		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
-		return;
-	}
+	if (tsc_khz == 0)
+		return false;
 
 	pr_info("Detected %lu.%03lu MHz processor\n",
-		(unsigned long)cpu_khz / 1000,
-		(unsigned long)cpu_khz % 1000);
+		(unsigned long)cpu_khz / KHZ,
+		(unsigned long)cpu_khz % KHZ);
 
 	if (cpu_khz != tsc_khz) {
 		pr_info("Detected %lu.%03lu MHz TSC",
-			(unsigned long)tsc_khz / 1000,
-			(unsigned long)tsc_khz % 1000);
+			(unsigned long)tsc_khz / KHZ,
+			(unsigned long)tsc_khz % KHZ);
+	}
+	return true;
+}
+
+static unsigned long __init get_loops_per_jiffy(void)
+{
+	unsigned long lpj = tsc_khz * KHZ;
+
+	do_div(lpj, HZ);
+	return lpj;
+}
+
+void __init tsc_early_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_TSC))
+		return;
+	if (!determine_cpu_tsc_frequencies())
+		return;
+	loops_per_jiffy = get_loops_per_jiffy();
+}
+
+void __init tsc_init(void)
+{
+	if (!boot_cpu_has(X86_FEATURE_TSC)) {
+		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+		return;
+	}
+
+	if (!tsc_khz) {
+		/* We failed to determine frequencies earlier, try again */
+		if (!determine_cpu_tsc_frequencies()) {
+			mark_tsc_unstable("could not calculate TSC khz");
+			setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
+			return;
+		}
 	}
 
 	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
@@ -1413,10 +1423,7 @@ void __init tsc_init(void)
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
 
-	lpj = ((u64)tsc_khz * 1000);
-	do_div(lpj, HZ);
-	lpj_fine = lpj;
-
+	lpj_fine = get_loops_per_jiffy();
 	use_tsc_delay();
 
 	check_system_tsc_reliable();
-- 
cgit v1.2.3


From e2a9ca29b5edc89da2fddeae30e1070b272395c5 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:39 -0400
Subject: x86/tsc: Initialize cyc2ns when tsc frequency is determined

cyc2ns converts tsc to nanoseconds, and it is handled in a per-cpu data
structure.

Currently, the setup code for c2ns data for every possible CPU goes through
the same sequence of calculations as for the boot CPU, but is based on the
same tsc frequency as the boot CPU, and thus this is not necessary.

Initialize the boot cpu when tsc frequency is determined. Copy the
calculated data from the boot CPU to the other CPUs in tsc_init().

In addition do the following:

 - Remove unnecessary zeroing of c2ns data by removing cyc2ns_data_init()

 - Split set_cyc2ns_scale() into two functions, so set_cyc2ns_scale() can be
   called when system is up, and wraps around __set_cyc2ns_scale() that can
   be called directly when system is booting but avoids saving restoring
   IRQs and going and waking up from idle.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-21-pasha.tatashin@oracle.com
---
 arch/x86/kernel/tsc.c | 94 +++++++++++++++++++++++++++++----------------------
 1 file changed, 53 insertions(+), 41 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 4cab2236169e..7ea0718a4c75 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -103,23 +103,6 @@ void cyc2ns_read_end(void)
  *                      -johnstul@us.ibm.com "math is hard, lets go shopping!"
  */
 
-static void cyc2ns_data_init(struct cyc2ns_data *data)
-{
-	data->cyc2ns_mul = 0;
-	data->cyc2ns_shift = 0;
-	data->cyc2ns_offset = 0;
-}
-
-static void __init cyc2ns_init(int cpu)
-{
-	struct cyc2ns *c2n = &per_cpu(cyc2ns, cpu);
-
-	cyc2ns_data_init(&c2n->data[0]);
-	cyc2ns_data_init(&c2n->data[1]);
-
-	seqcount_init(&c2n->seq);
-}
-
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 {
 	struct cyc2ns_data data;
@@ -135,18 +118,11 @@ static inline unsigned long long cycles_2_ns(unsigned long long cyc)
 	return ns;
 }
 
-static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
 {
 	unsigned long long ns_now;
 	struct cyc2ns_data data;
 	struct cyc2ns *c2n;
-	unsigned long flags;
-
-	local_irq_save(flags);
-	sched_clock_idle_sleep_event();
-
-	if (!khz)
-		goto done;
 
 	ns_now = cycles_2_ns(tsc_now);
 
@@ -178,12 +154,55 @@ static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_
 	c2n->data[0] = data;
 	raw_write_seqcount_latch(&c2n->seq);
 	c2n->data[1] = data;
+}
+
+static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	sched_clock_idle_sleep_event();
+
+	if (khz)
+		__set_cyc2ns_scale(khz, cpu, tsc_now);
 
-done:
 	sched_clock_idle_wakeup_event();
 	local_irq_restore(flags);
 }
 
+/*
+ * Initialize cyc2ns for boot cpu
+ */
+static void __init cyc2ns_init_boot_cpu(void)
+{
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+
+	seqcount_init(&c2n->seq);
+	__set_cyc2ns_scale(tsc_khz, smp_processor_id(), rdtsc());
+}
+
+/*
+ * Secondary CPUs do not run through cyc2ns_init(), so set up
+ * all the scale factors for all CPUs, assuming the same
+ * speed as the bootup CPU. (cpufreq notifiers will fix this
+ * up if their speed diverges)
+ */
+static void __init cyc2ns_init_secondary_cpus(void)
+{
+	unsigned int cpu, this_cpu = smp_processor_id();
+	struct cyc2ns *c2n = this_cpu_ptr(&cyc2ns);
+	struct cyc2ns_data *data = c2n->data;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu != this_cpu) {
+			seqcount_init(&c2n->seq);
+			c2n = per_cpu_ptr(&cyc2ns, cpu);
+			c2n->data[0] = data[0];
+			c2n->data[1] = data[1];
+		}
+	}
+}
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */
@@ -1385,6 +1404,10 @@ void __init tsc_early_init(void)
 	if (!determine_cpu_tsc_frequencies())
 		return;
 	loops_per_jiffy = get_loops_per_jiffy();
+
+	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
+	tsc_store_and_check_tsc_adjust(true);
+	cyc2ns_init_boot_cpu();
 }
 
 void __init tsc_init(void)
@@ -1401,23 +1424,12 @@ void __init tsc_init(void)
 			setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 			return;
 		}
+		/* Sanitize TSC ADJUST before cyc2ns gets initialized */
+		tsc_store_and_check_tsc_adjust(true);
+		cyc2ns_init_boot_cpu();
 	}
 
-	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
-	tsc_store_and_check_tsc_adjust(true);
-
-	/*
-	 * Secondary CPUs do not run through tsc_init(), so set up
-	 * all the scale factors for all CPUs, assuming the same
-	 * speed as the bootup CPU. (cpufreq notifiers will fix this
-	 * up if their speed diverges)
-	 */
-	cyc = rdtsc();
-	for_each_possible_cpu(cpu) {
-		cyc2ns_init(cpu);
-		set_cyc2ns_scale(tsc_khz, cpu, cyc);
-	}
-
+	cyc2ns_init_secondary_cpus();
 	static_branch_enable(&__use_tsc);
 
 	if (!no_sched_irq_time)
-- 
cgit v1.2.3


From 4763f03d3d186ce8a1125844790152d76804ad60 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:40 -0400
Subject: x86/tsc: Use TSC as sched clock early

All prerequesites for enabling TSC as sched clock early in the boot
process are available now:

 - Early attempt of TSC calibration

 - Early availablity of static branch patching

If TSC frequency can be established in the early calibration, enable the
static key which switches sched clock to use TSC.

[ tglx: Massaged changelog ]

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-22-pasha.tatashin@oracle.com
---
 arch/x86/kernel/tsc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 7ea0718a4c75..9277ae9b68b3 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -1408,6 +1408,7 @@ void __init tsc_early_init(void)
 	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
 	tsc_store_and_check_tsc_adjust(true);
 	cyc2ns_init_boot_cpu();
+	static_branch_enable(&__use_tsc);
 }
 
 void __init tsc_init(void)
-- 
cgit v1.2.3


From 5d2a4e91a541cb04d20d11602f0f9340291322ac Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:41 -0400
Subject: sched/clock: Move sched clock initialization and merge with generic
 clock

sched_clock_postinit() initializes a generic clock on systems where no
other clock is provided. This function may be called only after
timekeeping_init().

Rename sched_clock_postinit to generic_clock_inti() and call it from
sched_clock_init(). Move the call for sched_clock_init() until after
time_init().

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-23-pasha.tatashin@oracle.com
---
 include/linux/sched_clock.h |  5 ++---
 init/main.c                 |  4 ++--
 kernel/sched/clock.c        | 27 +++++++++++++++++----------
 kernel/sched/core.c         |  1 -
 kernel/time/sched_clock.c   |  2 +-
 5 files changed, 22 insertions(+), 17 deletions(-)

diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index 411b52e424e1..abe28d5cb3f4 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -9,17 +9,16 @@
 #define LINUX_SCHED_CLOCK
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
-extern void sched_clock_postinit(void);
+extern void generic_sched_clock_init(void);
 
 extern void sched_clock_register(u64 (*read)(void), int bits,
 				 unsigned long rate);
 #else
-static inline void sched_clock_postinit(void) { }
+static inline void generic_sched_clock_init(void) { }
 
 static inline void sched_clock_register(u64 (*read)(void), int bits,
 					unsigned long rate)
 {
-	;
 }
 #endif
 
diff --git a/init/main.c b/init/main.c
index 3b4ada11ed52..162d931c9511 100644
--- a/init/main.c
+++ b/init/main.c
@@ -79,7 +79,7 @@
 #include <linux/pti.h>
 #include <linux/blkdev.h>
 #include <linux/elevator.h>
-#include <linux/sched_clock.h>
+#include <linux/sched/clock.h>
 #include <linux/sched/task.h>
 #include <linux/sched/task_stack.h>
 #include <linux/context_tracking.h>
@@ -642,7 +642,7 @@ asmlinkage __visible void __init start_kernel(void)
 	softirq_init();
 	timekeeping_init();
 	time_init();
-	sched_clock_postinit();
+	sched_clock_init();
 	printk_safe_init();
 	perf_event_init();
 	profile_init();
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 10c83e73837a..0e9dbb2d9aea 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -53,6 +53,7 @@
  *
  */
 #include "sched.h"
+#include <linux/sched_clock.h>
 
 /*
  * Scheduler clock - returns current time in nanosec units.
@@ -68,11 +69,6 @@ EXPORT_SYMBOL_GPL(sched_clock);
 
 __read_mostly int sched_clock_running;
 
-void sched_clock_init(void)
-{
-	sched_clock_running = 1;
-}
-
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 /*
  * We must start with !__sched_clock_stable because the unstable -> stable
@@ -199,6 +195,15 @@ void clear_sched_clock_stable(void)
 		__clear_sched_clock_stable();
 }
 
+static void __sched_clock_gtod_offset(void)
+{
+	__gtod_offset = (sched_clock() + __sched_clock_offset) - ktime_get_ns();
+}
+
+void __init sched_clock_init(void)
+{
+	sched_clock_running = 1;
+}
 /*
  * We run this as late_initcall() such that it runs after all built-in drivers,
  * notably: acpi_processor and intel_idle, which can mark the TSC as unstable.
@@ -385,8 +390,6 @@ void sched_clock_tick(void)
 
 void sched_clock_tick_stable(void)
 {
-	u64 gtod, clock;
-
 	if (!sched_clock_stable())
 		return;
 
@@ -398,9 +401,7 @@ void sched_clock_tick_stable(void)
 	 * TSC to be unstable, any computation will be computing crap.
 	 */
 	local_irq_disable();
-	gtod = ktime_get_ns();
-	clock = sched_clock();
-	__gtod_offset = (clock + __sched_clock_offset) - gtod;
+	__sched_clock_gtod_offset();
 	local_irq_enable();
 }
 
@@ -434,6 +435,12 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */
 
+void __init sched_clock_init(void)
+{
+	sched_clock_running = 1;
+	generic_sched_clock_init();
+}
+
 u64 sched_clock_cpu(int cpu)
 {
 	if (unlikely(!sched_clock_running))
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe365c9a08e9..552406e9713b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5954,7 +5954,6 @@ void __init sched_init(void)
 	int i, j;
 	unsigned long alloc_size = 0, ptr;
 
-	sched_clock_init();
 	wait_bit_init();
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index 2d8f05aad442..cbc72c2c1fca 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -237,7 +237,7 @@ sched_clock_register(u64 (*read)(void), int bits, unsigned long rate)
 	pr_debug("Registered %pF as sched_clock source\n", read);
 }
 
-void __init sched_clock_postinit(void)
+void __init generic_sched_clock_init(void)
 {
 	/*
 	 * If no sched_clock() function has been provided at that point,
-- 
cgit v1.2.3


From 857baa87b6422bcfb84ed3631d6839920cb5b09d Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:42 -0400
Subject: sched/clock: Enable sched clock early

Allow sched_clock() to be used before schec_clock_init() is called.  This
provides a way to get early boot timestamps on machines with unstable
clocks.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-24-pasha.tatashin@oracle.com
---
 init/main.c          |  2 +-
 kernel/sched/clock.c | 20 +++++++++++++++++++-
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/init/main.c b/init/main.c
index 162d931c9511..ff0a24170b95 100644
--- a/init/main.c
+++ b/init/main.c
@@ -642,7 +642,6 @@ asmlinkage __visible void __init start_kernel(void)
 	softirq_init();
 	timekeeping_init();
 	time_init();
-	sched_clock_init();
 	printk_safe_init();
 	perf_event_init();
 	profile_init();
@@ -697,6 +696,7 @@ asmlinkage __visible void __init start_kernel(void)
 	acpi_early_init();
 	if (late_time_init)
 		late_time_init();
+	sched_clock_init();
 	calibrate_delay();
 	pid_idr_init();
 	anon_vma_init();
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 0e9dbb2d9aea..422cd63f8f17 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -202,7 +202,25 @@ static void __sched_clock_gtod_offset(void)
 
 void __init sched_clock_init(void)
 {
+	unsigned long flags;
+
+	/*
+	 * Set __gtod_offset such that once we mark sched_clock_running,
+	 * sched_clock_tick() continues where sched_clock() left off.
+	 *
+	 * Even if TSC is buggered, we're still UP at this point so it
+	 * can't really be out of sync.
+	 */
+	local_irq_save(flags);
+	__sched_clock_gtod_offset();
+	local_irq_restore(flags);
+
 	sched_clock_running = 1;
+
+	/* Now that sched_clock_running is set adjust scd */
+	local_irq_save(flags);
+	sched_clock_tick();
+	local_irq_restore(flags);
 }
 /*
  * We run this as late_initcall() such that it runs after all built-in drivers,
@@ -356,7 +374,7 @@ u64 sched_clock_cpu(int cpu)
 		return sched_clock() + __sched_clock_offset;
 
 	if (unlikely(!sched_clock_running))
-		return 0ull;
+		return sched_clock();
 
 	preempt_disable_notrace();
 	scd = cpu_sdc(cpu);
-- 
cgit v1.2.3


From 46457ea464f5341d1f9dad8dd213805d45f7f117 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:43 -0400
Subject: sched/clock: Use static key for sched_clock_running

sched_clock_running may be read every time sched_clock_cpu() is called.
Yet, this variable is updated only twice during boot, and never changes
again, therefore it is better to make it a static key.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-25-pasha.tatashin@oracle.com
---
 kernel/sched/clock.c | 16 ++++++++--------
 kernel/sched/debug.c |  2 --
 2 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 422cd63f8f17..c5c47ad3f386 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -67,7 +67,7 @@ unsigned long long __weak sched_clock(void)
 }
 EXPORT_SYMBOL_GPL(sched_clock);
 
-__read_mostly int sched_clock_running;
+static DEFINE_STATIC_KEY_FALSE(sched_clock_running);
 
 #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK
 /*
@@ -191,7 +191,7 @@ void clear_sched_clock_stable(void)
 
 	smp_mb(); /* matches sched_clock_init_late() */
 
-	if (sched_clock_running == 2)
+	if (static_key_count(&sched_clock_running.key) == 2)
 		__clear_sched_clock_stable();
 }
 
@@ -215,7 +215,7 @@ void __init sched_clock_init(void)
 	__sched_clock_gtod_offset();
 	local_irq_restore(flags);
 
-	sched_clock_running = 1;
+	static_branch_inc(&sched_clock_running);
 
 	/* Now that sched_clock_running is set adjust scd */
 	local_irq_save(flags);
@@ -228,7 +228,7 @@ void __init sched_clock_init(void)
  */
 static int __init sched_clock_init_late(void)
 {
-	sched_clock_running = 2;
+	static_branch_inc(&sched_clock_running);
 	/*
 	 * Ensure that it is impossible to not do a static_key update.
 	 *
@@ -373,7 +373,7 @@ u64 sched_clock_cpu(int cpu)
 	if (sched_clock_stable())
 		return sched_clock() + __sched_clock_offset;
 
-	if (unlikely(!sched_clock_running))
+	if (!static_branch_unlikely(&sched_clock_running))
 		return sched_clock();
 
 	preempt_disable_notrace();
@@ -396,7 +396,7 @@ void sched_clock_tick(void)
 	if (sched_clock_stable())
 		return;
 
-	if (unlikely(!sched_clock_running))
+	if (!static_branch_unlikely(&sched_clock_running))
 		return;
 
 	lockdep_assert_irqs_disabled();
@@ -455,13 +455,13 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 
 void __init sched_clock_init(void)
 {
-	sched_clock_running = 1;
+	static_branch_inc(&sched_clock_running);
 	generic_sched_clock_init();
 }
 
 u64 sched_clock_cpu(int cpu)
 {
-	if (unlikely(!sched_clock_running))
+	if (!static_branch_unlikely(&sched_clock_running))
 		return 0;
 
 	return sched_clock();
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index e593b4118578..b0212f489a33 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -623,8 +623,6 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 #undef PU
 }
 
-extern __read_mostly int sched_clock_running;
-
 static void print_cpu(struct seq_file *m, int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-- 
cgit v1.2.3


From 03821f451d2d2d7599061244734245be139014ea Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:44 -0400
Subject: x86/tsc: Split native_calibrate_cpu() into early and late parts

During early boot TSC and CPU frequency can be calibrated using MSR, CPUID,
and quick PIT calibration methods. The other methods PIT/HPET/PMTIMER are
available only after ACPI is initialized.

Split native_calibrate_cpu() into early and late parts so they can be
called separately during early and late tsc calibration.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-26-pasha.tatashin@oracle.com
---
 arch/x86/include/asm/tsc.h |  1 +
 arch/x86/kernel/tsc.c      | 54 ++++++++++++++++++++++++++++++----------------
 2 files changed, 37 insertions(+), 18 deletions(-)

diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index c4368ff73652..88140e4f2292 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -40,6 +40,7 @@ extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern void mark_tsc_async_resets(char *reason);
 extern unsigned long native_calibrate_cpu(void);
+extern unsigned long native_calibrate_cpu_early(void);
 extern unsigned long native_calibrate_tsc(void);
 extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 9277ae9b68b3..60586779b02c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -680,30 +680,17 @@ static unsigned long cpu_khz_from_cpuid(void)
 	return eax_base_mhz * 1000;
 }
 
-/**
- * native_calibrate_cpu - calibrate the cpu on boot
+/*
+ * calibrate cpu using pit, hpet, and ptimer methods. They are available
+ * later in boot after acpi is initialized.
  */
-unsigned long native_calibrate_cpu(void)
+static unsigned long pit_hpet_ptimer_calibrate_cpu(void)
 {
 	u64 tsc1, tsc2, delta, ref1, ref2;
 	unsigned long tsc_pit_min = ULONG_MAX, tsc_ref_min = ULONG_MAX;
-	unsigned long flags, latch, ms, fast_calibrate;
+	unsigned long flags, latch, ms;
 	int hpet = is_hpet_enabled(), i, loopmin;
 
-	fast_calibrate = cpu_khz_from_cpuid();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	fast_calibrate = cpu_khz_from_msr();
-	if (fast_calibrate)
-		return fast_calibrate;
-
-	local_irq_save(flags);
-	fast_calibrate = quick_pit_calibrate();
-	local_irq_restore(flags);
-	if (fast_calibrate)
-		return fast_calibrate;
-
 	/*
 	 * Run 5 calibration loops to get the lowest frequency value
 	 * (the best estimate). We use two different calibration modes
@@ -846,6 +833,37 @@ unsigned long native_calibrate_cpu(void)
 	return tsc_pit_min;
 }
 
+/**
+ * native_calibrate_cpu_early - can calibrate the cpu early in boot
+ */
+unsigned long native_calibrate_cpu_early(void)
+{
+	unsigned long flags, fast_calibrate = cpu_khz_from_cpuid();
+
+	if (!fast_calibrate)
+		fast_calibrate = cpu_khz_from_msr();
+	if (!fast_calibrate) {
+		local_irq_save(flags);
+		fast_calibrate = quick_pit_calibrate();
+		local_irq_restore(flags);
+	}
+	return fast_calibrate;
+}
+
+
+/**
+ * native_calibrate_cpu - calibrate the cpu
+ */
+unsigned long native_calibrate_cpu(void)
+{
+	unsigned long tsc_freq = native_calibrate_cpu_early();
+
+	if (!tsc_freq)
+		tsc_freq = pit_hpet_ptimer_calibrate_cpu();
+
+	return tsc_freq;
+}
+
 void recalibrate_cpu_khz(void)
 {
 #ifndef CONFIG_SMP
-- 
cgit v1.2.3


From 8dbe438589f373544a1af8b4a859e4da853c0f90 Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Thu, 19 Jul 2018 16:55:45 -0400
Subject: x86/tsc: Make use of tsc_calibrate_cpu_early()

During early boot enable tsc_calibrate_cpu_early() and switch to
tsc_calibrate_cpu() only later. Do this unconditionally, because it is
unknown what methods other cpus will use to calibrate once they are
onlined.

If by the time tsc_init() is called tsc frequency is still unknown do only
pit_hpet_ptimer_calibrate_cpu() to calibrate, as this function contains the
only methods wich have not been called and tried earlier.

Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: peterz@infradead.org
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180719205545.16512-27-pasha.tatashin@oracle.com
---
 arch/x86/include/asm/tsc.h |  1 -
 arch/x86/kernel/tsc.c      | 25 +++++++++++++++++++------
 arch/x86/kernel/x86_init.c |  2 +-
 3 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 88140e4f2292..eb5bbfeccb66 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -39,7 +39,6 @@ extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
 extern void mark_tsc_async_resets(char *reason);
-extern unsigned long native_calibrate_cpu(void);
 extern unsigned long native_calibrate_cpu_early(void);
 extern unsigned long native_calibrate_tsc(void);
 extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 60586779b02c..02e416b87ac1 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -854,7 +854,7 @@ unsigned long native_calibrate_cpu_early(void)
 /**
  * native_calibrate_cpu - calibrate the cpu
  */
-unsigned long native_calibrate_cpu(void)
+static unsigned long native_calibrate_cpu(void)
 {
 	unsigned long tsc_freq = native_calibrate_cpu_early();
 
@@ -1374,13 +1374,19 @@ unreg:
  */
 device_initcall(init_tsc_clocksource);
 
-static bool __init determine_cpu_tsc_frequencies(void)
+static bool __init determine_cpu_tsc_frequencies(bool early)
 {
 	/* Make sure that cpu and tsc are not already calibrated */
 	WARN_ON(cpu_khz || tsc_khz);
 
-	cpu_khz = x86_platform.calibrate_cpu();
-	tsc_khz = x86_platform.calibrate_tsc();
+	if (early) {
+		cpu_khz = x86_platform.calibrate_cpu();
+		tsc_khz = x86_platform.calibrate_tsc();
+	} else {
+		/* We should not be here with non-native cpu calibration */
+		WARN_ON(x86_platform.calibrate_cpu != native_calibrate_cpu);
+		cpu_khz = pit_hpet_ptimer_calibrate_cpu();
+	}
 
 	/*
 	 * Trust non-zero tsc_khz as authorative,
@@ -1419,7 +1425,7 @@ void __init tsc_early_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_TSC))
 		return;
-	if (!determine_cpu_tsc_frequencies())
+	if (!determine_cpu_tsc_frequencies(true))
 		return;
 	loops_per_jiffy = get_loops_per_jiffy();
 
@@ -1431,6 +1437,13 @@ void __init tsc_early_init(void)
 
 void __init tsc_init(void)
 {
+	/*
+	 * native_calibrate_cpu_early can only calibrate using methods that are
+	 * available early in boot.
+	 */
+	if (x86_platform.calibrate_cpu == native_calibrate_cpu_early)
+		x86_platform.calibrate_cpu = native_calibrate_cpu;
+
 	if (!boot_cpu_has(X86_FEATURE_TSC)) {
 		setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 		return;
@@ -1438,7 +1451,7 @@ void __init tsc_init(void)
 
 	if (!tsc_khz) {
 		/* We failed to determine frequencies earlier, try again */
-		if (!determine_cpu_tsc_frequencies()) {
+		if (!determine_cpu_tsc_frequencies(false)) {
 			mark_tsc_unstable("could not calculate TSC khz");
 			setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 			return;
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index 3ab867603e81..2792b5573818 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -109,7 +109,7 @@ struct x86_cpuinit_ops x86_cpuinit = {
 static void default_nmi_init(void) { };
 
 struct x86_platform_ops x86_platform __ro_after_init = {
-	.calibrate_cpu			= native_calibrate_cpu,
+	.calibrate_cpu			= native_calibrate_cpu_early,
 	.calibrate_tsc			= native_calibrate_tsc,
 	.get_wallclock			= mach_get_cmos_time,
 	.set_wallclock			= mach_set_rtc_mmss,
-- 
cgit v1.2.3


From 1949f9f49792d65dba2090edddbe36a5f02e3ba3 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@intel.com>
Date: Thu, 19 Jul 2018 13:49:58 -0700
Subject: Documentation/l1tf: Fix typos

Fix spelling and other typos

Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/admin-guide/l1tf.rst | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/Documentation/admin-guide/l1tf.rst b/Documentation/admin-guide/l1tf.rst
index f2bb28cff439..ccf649cabdcd 100644
--- a/Documentation/admin-guide/l1tf.rst
+++ b/Documentation/admin-guide/l1tf.rst
@@ -17,7 +17,7 @@ vulnerability is not present on:
    - Older processor models, where the CPU family is < 6
 
    - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft,
-     Penwell, Pineview, Slivermont, Airmont, Merrifield)
+     Penwell, Pineview, Silvermont, Airmont, Merrifield)
 
    - The Intel Core Duo Yonah variants (2006 - 2008)
 
@@ -113,7 +113,7 @@ Attack scenarios
    deployment scenario. The mitigations, their protection scope and impact
    are described in the next sections.
 
-   The default mitigations and the rationale for chosing them are explained
+   The default mitigations and the rationale for choosing them are explained
    at the end of this document. See :ref:`default_mitigations`.
 
 .. _l1tf_sys_info:
@@ -191,15 +191,15 @@ Guest mitigation mechanisms
     - unconditional ('always')
 
    The conditional mode avoids L1D flushing after VMEXITs which execute
-   only audited code pathes before the corresponding VMENTER. These code
-   pathes have beed verified that they cannot expose secrets or other
+   only audited code paths before the corresponding VMENTER. These code
+   paths have been verified that they cannot expose secrets or other
    interesting data to an attacker, but they can leak information about the
    address space layout of the hypervisor.
 
    Unconditional mode flushes L1D on all VMENTER invocations and provides
    maximum protection. It has a higher overhead than the conditional
    mode. The overhead cannot be quantified correctly as it depends on the
-   work load scenario and the resulting number of VMEXITs.
+   workload scenario and the resulting number of VMEXITs.
 
    The general recommendation is to enable L1D flush on VMENTER. The kernel
    defaults to conditional mode on affected processors.
@@ -262,7 +262,7 @@ Guest mitigation mechanisms
    Whether the interrupts with are affine to CPUs, which run untrusted
    guests, provide interesting data for an attacker depends on the system
    configuration and the scenarios which run on the system. While for some
-   of the interrupts it can be assumed that they wont expose interesting
+   of the interrupts it can be assumed that they won't expose interesting
    information beyond exposing hints about the host OS memory layout, there
    is no way to make general assumptions.
 
@@ -299,7 +299,7 @@ Guest mitigation mechanisms
 		 to be brought up at least partially and are then shut down
 		 again.  "nosmt" can be undone via the sysfs interface.
 
-     nosmt=force Has the same effect as "nosmt' but it does not allow to
+     nosmt=force Has the same effect as "nosmt" but it does not allow to
 		 undo the SMT disable via the sysfs interface.
      =========== ==========================================================
 
-- 
cgit v1.2.3


From 1842623850d09b0b1147d4974573aa305658d97f Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Thu, 19 Jul 2018 18:04:09 -0500
Subject: PCI: Handle error return from pci_reset_bridge_secondary_bus()

Commit 01fd61c0b9bd ("PCI: Add a return type for
pci_reset_bridge_secondary_bus()") added a return value to the function to
return if a device is accessible following a reset.  Callers are not
checking the value.

Pass error code up high in the stack if device is not accessible.

Fixes: 01fd61c0b9bd ("PCI: Add a return type for pci_reset_bridge_secondary_bus()")
Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp_hpc.c |  5 +++--
 drivers/pci/pci.c                | 12 ++++++------
 drivers/pci/pcie/aer.c           |  5 +++--
 drivers/pci/pcie/err.c           |  6 ++++--
 4 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 718b6073afad..bbaa2114f953 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -728,6 +728,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	struct controller *ctrl = slot->ctrl;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 stat_mask = 0, ctrl_mask = 0;
+	int rc;
 
 	if (probe)
 		return 0;
@@ -745,7 +746,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	if (pciehp_poll_mode)
 		del_timer_sync(&ctrl->poll_timer);
 
-	pci_reset_bridge_secondary_bus(ctrl->pcie->port);
+	rc = pci_reset_bridge_secondary_bus(ctrl->pcie->port);
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
 	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
@@ -753,7 +754,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
 	if (pciehp_poll_mode)
 		int_poll_timeout(&ctrl->poll_timer);
-	return 0;
+	return rc;
 }
 
 int pcie_init_notification(struct controller *ctrl)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..98d149070205 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4253,9 +4253,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 	if (probe)
 		return 0;
 
-	pci_reset_bridge_secondary_bus(dev->bus->self);
-
-	return 0;
+	return pci_reset_bridge_secondary_bus(dev->bus->self);
 }
 
 static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe)
@@ -4850,6 +4848,8 @@ EXPORT_SYMBOL_GPL(pci_try_reset_slot);
 
 static int pci_bus_reset(struct pci_bus *bus, int probe)
 {
+	int ret;
+
 	if (!bus->self || !pci_bus_resetable(bus))
 		return -ENOTTY;
 
@@ -4860,11 +4860,11 @@ static int pci_bus_reset(struct pci_bus *bus, int probe)
 
 	might_sleep();
 
-	pci_reset_bridge_secondary_bus(bus->self);
+	ret = pci_reset_bridge_secondary_bus(bus->self);
 
 	pci_bus_unlock(bus);
 
-	return 0;
+	return ret;
 }
 
 /**
@@ -4924,7 +4924,7 @@ int pci_try_reset_bus(struct pci_bus *bus)
 
 	if (pci_bus_trylock(bus)) {
 		might_sleep();
-		pci_reset_bridge_secondary_bus(bus->self);
+		rc = pci_reset_bridge_secondary_bus(bus->self);
 		pci_bus_unlock(bus);
 	} else
 		rc = -EAGAIN;
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index a2e88386af28..bde723db3d65 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1305,6 +1305,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 {
 	u32 reg32;
 	int pos;
+	int rc;
 
 	pos = dev->aer_cap;
 
@@ -1313,7 +1314,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	pci_reset_bridge_secondary_bus(dev);
+	rc = pci_reset_bridge_secondary_bus(dev);
 	pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
 
 	/* Clear Root Error Status */
@@ -1325,7 +1326,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 |= ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	return PCI_ERS_RESULT_RECOVERED;
+	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
 /**
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index f7ce0cb0b0b7..03075cff86f4 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -175,9 +175,11 @@ out:
  */
 static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 {
-	pci_reset_bridge_secondary_bus(dev);
+	int rc;
+
+	rc = pci_reset_bridge_secondary_bus(dev);
 	pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n");
-	return PCI_ERS_RESULT_RECOVERED;
+	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
 
 static pci_ers_result_t reset_link(struct pci_dev *dev, u32 service)
-- 
cgit v1.2.3


From 409888e0966e2753f8e272b89806738469c47e1d Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Thu, 19 Jul 2018 18:04:10 -0500
Subject: IB/hfi1: Use pci_try_reset_bus() for initiating PCI Secondary Bus
 Reset

Getting ready to hide pci_reset_bridge_secondary_bus() from the drivers.
pci_reset_bridge_secondary_bus() should only be used internally by the
PCI code itself.

Other drivers should rely on higher level pci_try_reset_bus() API.

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/infiniband/hw/hfi1/pcie.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 4d4371bf2c7c..4570c4dc93d9 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -905,9 +905,7 @@ static int trigger_sbr(struct hfi1_devdata *dd)
 	 * delay after a reset is required.  Per spec requirements,
 	 * the link is either working or not after that point.
 	 */
-	pci_reset_bridge_secondary_bus(dev->bus->self);
-
-	return 0;
+	return pci_try_reset_bus(dev->bus);
 }
 
 /*
-- 
cgit v1.2.3


From 381634cad15b711e033a2638d558232b60f753f6 Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Thu, 19 Jul 2018 18:04:11 -0500
Subject: PCI: Hide pci_reset_bridge_secondary_bus() from drivers

Rename pci_reset_bridge_secondary_bus() to pci_bridge_secondary_bus_reset()
and move the declaration from linux/pci.h to drivers/pci.h to be used
internally in PCI directory only.

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp_hpc.c |  2 +-
 drivers/pci/pci.c                | 11 +++++------
 drivers/pci/pci.h                |  1 +
 drivers/pci/pcie/aer.c           |  2 +-
 drivers/pci/pcie/err.c           |  2 +-
 include/linux/pci.h              |  1 -
 6 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index bbaa2114f953..8dae23221344 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -746,7 +746,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	if (pciehp_poll_mode)
 		del_timer_sync(&ctrl->poll_timer);
 
-	rc = pci_reset_bridge_secondary_bus(ctrl->pcie->port);
+	rc = pci_bridge_secondary_bus_reset(ctrl->pcie->port);
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask);
 	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 98d149070205..236220cb0f77 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4224,19 +4224,18 @@ void __weak pcibios_reset_secondary_bus(struct pci_dev *dev)
 }
 
 /**
- * pci_reset_bridge_secondary_bus - Reset the secondary bus on a PCI bridge.
+ * pci_bridge_secondary_bus_reset - Reset the secondary bus on a PCI bridge.
  * @dev: Bridge device
  *
  * Use the bridge control register to assert reset on the secondary bus.
  * Devices on the secondary bus are left in power-on state.
  */
-int pci_reset_bridge_secondary_bus(struct pci_dev *dev)
+int pci_bridge_secondary_bus_reset(struct pci_dev *dev)
 {
 	pcibios_reset_secondary_bus(dev);
 
 	return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS);
 }
-EXPORT_SYMBOL_GPL(pci_reset_bridge_secondary_bus);
 
 static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 {
@@ -4253,7 +4252,7 @@ static int pci_parent_bus_reset(struct pci_dev *dev, int probe)
 	if (probe)
 		return 0;
 
-	return pci_reset_bridge_secondary_bus(dev->bus->self);
+	return pci_bridge_secondary_bus_reset(dev->bus->self);
 }
 
 static int pci_reset_hotplug_slot(struct hotplug_slot *hotplug, int probe)
@@ -4860,7 +4859,7 @@ static int pci_bus_reset(struct pci_bus *bus, int probe)
 
 	might_sleep();
 
-	ret = pci_reset_bridge_secondary_bus(bus->self);
+	ret = pci_bridge_secondary_bus_reset(bus->self);
 
 	pci_bus_unlock(bus);
 
@@ -4924,7 +4923,7 @@ int pci_try_reset_bus(struct pci_bus *bus)
 
 	if (pci_bus_trylock(bus)) {
 		might_sleep();
-		rc = pci_reset_bridge_secondary_bus(bus->self);
+		rc = pci_bridge_secondary_bus_reset(bus->self);
 		pci_bus_unlock(bus);
 	} else
 		rc = -EAGAIN;
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c358e7a07f3f..f784263ad587 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -33,6 +33,7 @@ int pci_mmap_fits(struct pci_dev *pdev, int resno, struct vm_area_struct *vmai,
 		  enum pci_mmap_api mmap_api);
 
 int pci_probe_reset_function(struct pci_dev *dev);
+int pci_bridge_secondary_bus_reset(struct pci_dev *dev);
 
 /**
  * struct pci_platform_pm_ops - Firmware PM callbacks
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index bde723db3d65..8c12efca9259 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1314,7 +1314,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
 	reg32 &= ~ROOT_PORT_INTR_ON_MESG_MASK;
 	pci_write_config_dword(dev, pos + PCI_ERR_ROOT_COMMAND, reg32);
 
-	rc = pci_reset_bridge_secondary_bus(dev);
+	rc = pci_bridge_secondary_bus_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "Root Port link has been reset\n");
 
 	/* Clear Root Error Status */
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 03075cff86f4..ae72f88d3ca2 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -177,7 +177,7 @@ static pci_ers_result_t default_reset_link(struct pci_dev *dev)
 {
 	int rc;
 
-	rc = pci_reset_bridge_secondary_bus(dev);
+	rc = pci_bridge_secondary_bus_reset(dev);
 	pci_printk(KERN_DEBUG, dev, "downstream link has been reset\n");
 	return rc ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED;
 }
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 6ba818449095..03520ff23d73 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1103,7 +1103,6 @@ int pci_reset_bus(struct pci_bus *bus);
 int pci_try_reset_bus(struct pci_bus *bus);
 void pci_reset_secondary_bus(struct pci_dev *dev);
 void pcibios_reset_secondary_bus(struct pci_dev *dev);
-int pci_reset_bridge_secondary_bus(struct pci_dev *dev);
 void pci_update_resource(struct pci_dev *dev, int resno);
 int __must_check pci_assign_resource(struct pci_dev *dev, int i);
 int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align);
-- 
cgit v1.2.3


From 811c5cb37df46b0cd714dbd053d19cdb97d08cff Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Thu, 19 Jul 2018 18:04:12 -0500
Subject: PCI: Unify try slot and bus reset API

Drivers are expected to call pci_try_reset_slot() or pci_try_reset_bus() by
querying if a system supports hotplug or not.  A survey showed that most
drivers don't do this and we are leaking hotplug capability to the user.

Hide pci_try_slot_reset() from drivers and embed into pci_try_bus_reset().
Change pci_try_reset_bus() parameter from struct pci_bus to struct pci_dev.

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/infiniband/hw/hfi1/pcie.c |  2 +-
 drivers/pci/pci.c                 | 21 ++++++++++++++++-----
 drivers/vfio/pci/vfio_pci.c       |  6 ++----
 include/linux/pci.h               |  3 +--
 4 files changed, 20 insertions(+), 12 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index 4570c4dc93d9..df4f2d390be8 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -905,7 +905,7 @@ static int trigger_sbr(struct hfi1_devdata *dd)
 	 * delay after a reset is required.  Per spec requirements,
 	 * the link is either working or not after that point.
 	 */
-	return pci_try_reset_bus(dev->bus);
+	return pci_try_reset_bus(dev);
 }
 
 /*
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 236220cb0f77..a31e6dbf21c3 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4817,12 +4817,12 @@ int pci_reset_slot(struct pci_slot *slot)
 EXPORT_SYMBOL_GPL(pci_reset_slot);
 
 /**
- * pci_try_reset_slot - Try to reset a PCI slot
+ * __pci_try_reset_slot - Try to reset a PCI slot
  * @slot: PCI slot to reset
  *
  * Same as above except return -EAGAIN if the slot cannot be locked
  */
-int pci_try_reset_slot(struct pci_slot *slot)
+static int __pci_try_reset_slot(struct pci_slot *slot)
 {
 	int rc;
 
@@ -4843,7 +4843,6 @@ int pci_try_reset_slot(struct pci_slot *slot)
 
 	return rc;
 }
-EXPORT_SYMBOL_GPL(pci_try_reset_slot);
 
 static int pci_bus_reset(struct pci_bus *bus, int probe)
 {
@@ -4906,12 +4905,12 @@ int pci_reset_bus(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(pci_reset_bus);
 
 /**
- * pci_try_reset_bus - Try to reset a PCI bus
+ * __pci_try_reset_bus - Try to reset a PCI bus
  * @bus: top level PCI bus to reset
  *
  * Same as above except return -EAGAIN if the bus cannot be locked
  */
-int pci_try_reset_bus(struct pci_bus *bus)
+static int __pci_try_reset_bus(struct pci_bus *bus)
 {
 	int rc;
 
@@ -4932,6 +4931,18 @@ int pci_try_reset_bus(struct pci_bus *bus)
 
 	return rc;
 }
+
+/**
+ * pci_try_reset_bus - Try to reset a PCI bus
+ * @pdev: top level PCI device to reset via slot/bus
+ *
+ * Same as above except return -EAGAIN if the bus cannot be locked
+ */
+int pci_try_reset_bus(struct pci_dev *pdev)
+{
+	return pci_probe_reset_slot(pdev->slot) ?
+	    __pci_try_reset_slot(pdev->slot) : __pci_try_reset_bus(pdev->bus);
+}
 EXPORT_SYMBOL_GPL(pci_try_reset_bus);
 
 /**
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index b423a309a6e0..71018ec9065b 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1010,8 +1010,7 @@ reset_info_exit:
 						    &info, slot);
 		if (!ret)
 			/* User has access, do the reset */
-			ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-				     pci_try_reset_bus(vdev->pdev->bus);
+			ret = pci_try_reset_bus(vdev->pdev);
 
 hot_reset_release:
 		for (i--; i >= 0; i--)
@@ -1373,8 +1372,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 	}
 
 	if (needs_reset)
-		ret = slot ? pci_try_reset_slot(vdev->pdev->slot) :
-			     pci_try_reset_bus(vdev->pdev->bus);
+		ret = pci_try_reset_bus(vdev->pdev);
 
 put_devs:
 	for (i = 0; i < devs.cur_index; i++) {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 03520ff23d73..19fb82559145 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1097,10 +1097,9 @@ int pci_reset_function_locked(struct pci_dev *dev);
 int pci_try_reset_function(struct pci_dev *dev);
 int pci_probe_reset_slot(struct pci_slot *slot);
 int pci_reset_slot(struct pci_slot *slot);
-int pci_try_reset_slot(struct pci_slot *slot);
 int pci_probe_reset_bus(struct pci_bus *bus);
 int pci_reset_bus(struct pci_bus *bus);
-int pci_try_reset_bus(struct pci_bus *bus);
+int pci_try_reset_bus(struct pci_dev *dev);
 void pci_reset_secondary_bus(struct pci_dev *dev);
 void pcibios_reset_secondary_bus(struct pci_dev *dev);
 void pci_update_resource(struct pci_dev *dev, int resno);
-- 
cgit v1.2.3


From fe32e2fa656c29d5d25f959f8e6168ac405d9ab4 Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Thu, 19 Jul 2018 18:04:14 -0500
Subject: PCI: Deprecate pci_reset_bus() and pci_reset_slot() functions

pci_reset_bus() and pci_reset_slot() functions are not being used by any
code.  Remove them from the kernel in favor of pci_try_reset_bus() and
pci_try_reset_slot() functions.

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 53 +----------------------------------------------------
 include/linux/pci.h |  2 --
 2 files changed, 1 insertion(+), 54 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a31e6dbf21c3..8ee9f386c1ee 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4784,7 +4784,7 @@ int pci_probe_reset_slot(struct pci_slot *slot)
 EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
 
 /**
- * pci_reset_slot - reset a PCI slot
+ * __pci_try_reset_slot - Try to reset a PCI slot
  * @slot: PCI slot to reset
  *
  * A PCI bus may host multiple slots, each slot may support a reset mechanism
@@ -4796,30 +4796,6 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
  * through this function.  PCI config space of all devices in the slot and
  * behind the slot is saved before and restored after reset.
  *
- * Return 0 on success, non-zero on error.
- */
-int pci_reset_slot(struct pci_slot *slot)
-{
-	int rc;
-
-	rc = pci_slot_reset(slot, 1);
-	if (rc)
-		return rc;
-
-	pci_slot_save_and_disable(slot);
-
-	rc = pci_slot_reset(slot, 0);
-
-	pci_slot_restore(slot);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pci_reset_slot);
-
-/**
- * __pci_try_reset_slot - Try to reset a PCI slot
- * @slot: PCI slot to reset
- *
  * Same as above except return -EAGAIN if the slot cannot be locked
  */
 static int __pci_try_reset_slot(struct pci_slot *slot)
@@ -4877,33 +4853,6 @@ int pci_probe_reset_bus(struct pci_bus *bus)
 }
 EXPORT_SYMBOL_GPL(pci_probe_reset_bus);
 
-/**
- * pci_reset_bus - reset a PCI bus
- * @bus: top level PCI bus to reset
- *
- * Do a bus reset on the given bus and any subordinate buses, saving
- * and restoring state of all devices.
- *
- * Return 0 on success, non-zero on error.
- */
-int pci_reset_bus(struct pci_bus *bus)
-{
-	int rc;
-
-	rc = pci_bus_reset(bus, 1);
-	if (rc)
-		return rc;
-
-	pci_bus_save_and_disable(bus);
-
-	rc = pci_bus_reset(bus, 0);
-
-	pci_bus_restore(bus);
-
-	return rc;
-}
-EXPORT_SYMBOL_GPL(pci_reset_bus);
-
 /**
  * __pci_try_reset_bus - Try to reset a PCI bus
  * @bus: top level PCI bus to reset
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 19fb82559145..cf53ecb50789 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1096,9 +1096,7 @@ int pci_reset_function(struct pci_dev *dev);
 int pci_reset_function_locked(struct pci_dev *dev);
 int pci_try_reset_function(struct pci_dev *dev);
 int pci_probe_reset_slot(struct pci_slot *slot);
-int pci_reset_slot(struct pci_slot *slot);
 int pci_probe_reset_bus(struct pci_bus *bus);
-int pci_reset_bus(struct pci_bus *bus);
 int pci_try_reset_bus(struct pci_dev *dev);
 void pci_reset_secondary_bus(struct pci_dev *dev);
 void pcibios_reset_secondary_bus(struct pci_dev *dev);
-- 
cgit v1.2.3


From c6a44ba950d147e15fe6dab6455a52f91d8fe625 Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@codeaurora.org>
Date: Thu, 19 Jul 2018 18:04:15 -0500
Subject: PCI: Rename pci_try_reset_bus() to pci_reset_bus()

Now that the old implementation of pci_reset_bus() is gone, replace
pci_try_reset_bus() with pci_reset_bus().

Compared to the old implementation, new code will fail immmediately with
-EAGAIN if object lock cannot be obtained.

Signed-off-by: Sinan Kaya <okaya@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/infiniband/hw/hfi1/pcie.c |  2 +-
 drivers/pci/pci.c                 | 16 ++++++++--------
 drivers/vfio/pci/vfio_pci.c       |  4 ++--
 include/linux/pci.h               |  2 +-
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c
index df4f2d390be8..baf7c324f7b8 100644
--- a/drivers/infiniband/hw/hfi1/pcie.c
+++ b/drivers/infiniband/hw/hfi1/pcie.c
@@ -905,7 +905,7 @@ static int trigger_sbr(struct hfi1_devdata *dd)
 	 * delay after a reset is required.  Per spec requirements,
 	 * the link is either working or not after that point.
 	 */
-	return pci_try_reset_bus(dev);
+	return pci_reset_bus(dev);
 }
 
 /*
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 8ee9f386c1ee..d123c2b173da 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4784,7 +4784,7 @@ int pci_probe_reset_slot(struct pci_slot *slot)
 EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
 
 /**
- * __pci_try_reset_slot - Try to reset a PCI slot
+ * __pci_reset_slot - Try to reset a PCI slot
  * @slot: PCI slot to reset
  *
  * A PCI bus may host multiple slots, each slot may support a reset mechanism
@@ -4798,7 +4798,7 @@ EXPORT_SYMBOL_GPL(pci_probe_reset_slot);
  *
  * Same as above except return -EAGAIN if the slot cannot be locked
  */
-static int __pci_try_reset_slot(struct pci_slot *slot)
+static int __pci_reset_slot(struct pci_slot *slot)
 {
 	int rc;
 
@@ -4854,12 +4854,12 @@ int pci_probe_reset_bus(struct pci_bus *bus)
 EXPORT_SYMBOL_GPL(pci_probe_reset_bus);
 
 /**
- * __pci_try_reset_bus - Try to reset a PCI bus
+ * __pci_reset_bus - Try to reset a PCI bus
  * @bus: top level PCI bus to reset
  *
  * Same as above except return -EAGAIN if the bus cannot be locked
  */
-static int __pci_try_reset_bus(struct pci_bus *bus)
+static int __pci_reset_bus(struct pci_bus *bus)
 {
 	int rc;
 
@@ -4882,17 +4882,17 @@ static int __pci_try_reset_bus(struct pci_bus *bus)
 }
 
 /**
- * pci_try_reset_bus - Try to reset a PCI bus
+ * pci_reset_bus - Try to reset a PCI bus
  * @pdev: top level PCI device to reset via slot/bus
  *
  * Same as above except return -EAGAIN if the bus cannot be locked
  */
-int pci_try_reset_bus(struct pci_dev *pdev)
+int pci_reset_bus(struct pci_dev *pdev)
 {
 	return pci_probe_reset_slot(pdev->slot) ?
-	    __pci_try_reset_slot(pdev->slot) : __pci_try_reset_bus(pdev->bus);
+	    __pci_reset_slot(pdev->slot) : __pci_reset_bus(pdev->bus);
 }
-EXPORT_SYMBOL_GPL(pci_try_reset_bus);
+EXPORT_SYMBOL_GPL(pci_reset_bus);
 
 /**
  * pcix_get_max_mmrbc - get PCI-X maximum designed memory read byte count
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 71018ec9065b..345c0dc8a6dc 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1010,7 +1010,7 @@ reset_info_exit:
 						    &info, slot);
 		if (!ret)
 			/* User has access, do the reset */
-			ret = pci_try_reset_bus(vdev->pdev);
+			ret = pci_reset_bus(vdev->pdev);
 
 hot_reset_release:
 		for (i--; i >= 0; i--)
@@ -1372,7 +1372,7 @@ static void vfio_pci_try_bus_reset(struct vfio_pci_device *vdev)
 	}
 
 	if (needs_reset)
-		ret = pci_try_reset_bus(vdev->pdev);
+		ret = pci_reset_bus(vdev->pdev);
 
 put_devs:
 	for (i = 0; i < devs.cur_index; i++) {
diff --git a/include/linux/pci.h b/include/linux/pci.h
index cf53ecb50789..307b336496f6 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1097,7 +1097,7 @@ int pci_reset_function_locked(struct pci_dev *dev);
 int pci_try_reset_function(struct pci_dev *dev);
 int pci_probe_reset_slot(struct pci_slot *slot);
 int pci_probe_reset_bus(struct pci_bus *bus);
-int pci_try_reset_bus(struct pci_dev *dev);
+int pci_reset_bus(struct pci_dev *dev);
 void pci_reset_secondary_bus(struct pci_dev *dev);
 void pcibios_reset_secondary_bus(struct pci_dev *dev);
 void pci_update_resource(struct pci_dev *dev, int resno);
-- 
cgit v1.2.3


From 9e97b73fdb235345a826519862a52a7398c89eb8 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:38 +0200
Subject: x86/asm-offsets: Move TSS_sp0 and TSS_sp1 to asm-offsets.c

These offsets will be used in 32 bit assembly code as well, so make them
available for all of x86 code.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-2-git-send-email-joro@8bytes.org
---
 arch/x86/kernel/asm-offsets.c    | 4 ++++
 arch/x86/kernel/asm-offsets_64.c | 2 --
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index dcb008c320fe..a1e16286a832 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -103,4 +103,8 @@ void common(void) {
 	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
 	OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
 	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
+
+	/* Offset for sp0 and sp1 into the tss_struct */
+	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
+	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 }
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index b2dcd161f514..3b9405e7ba2b 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -65,8 +65,6 @@ int main(void)
 #undef ENTRY
 
 	OFFSET(TSS_ist, tss_struct, x86_tss.ist);
-	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
-	OFFSET(TSS_sp1, tss_struct, x86_tss.sp1);
 	BLANK();
 
 #ifdef CONFIG_STACKPROTECTOR
-- 
cgit v1.2.3


From ae2e565bc6aaee3f3db420fec5fdd39755c9813e Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:39 +0200
Subject: x86/entry/32: Rename TSS_sysenter_sp0 to TSS_entry2task_stack

The stack address doesn't need to be stored in tss.sp0 if the stack is
switched manually like on sysenter. Rename the offset so that it still
makes sense when its location is changed in later patches.

This stackk will also be used for all kernel-entry points, not just
sysenter. Reflect that and the fact that it is the offset to the task-stack
location in the name as well.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-3-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S        | 2 +-
 arch/x86/kernel/asm-offsets_32.c | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index c371bfee137a..39f711ad0fc9 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -412,7 +412,7 @@ ENTRY(xen_sysenter_target)
  * 0(%ebp) arg6
  */
 ENTRY(entry_SYSENTER_32)
-	movl	TSS_sysenter_sp0(%esp), %esp
+	movl	TSS_entry2task_stack(%esp), %esp
 .Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
 	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index a4a3be399f4b..15b3f45b69cd 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -46,8 +46,9 @@ void foo(void)
 	OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
 	BLANK();
 
-	/* Offset from the sysenter stack to tss.sp0 */
-	DEFINE(TSS_sysenter_sp0, offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+	/* Offset from the entry stack to task stack stored in TSS */
+	DEFINE(TSS_entry2task_stack,
+	       offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
 	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
 #ifdef CONFIG_STACKPROTECTOR
-- 
cgit v1.2.3


From a6b744f3ce9d017dd86b28355de2d8e0d36496d4 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:40 +0200
Subject: x86/entry/32: Load task stack from x86_tss.sp1 in SYSENTER handler

x86_tss.sp0 will be used to point to the entry stack later to use it as a
trampoline stack for other kernel entry points besides SYSENTER.

So store the real task stack pointer in x86_tss.sp1, which is otherwise
unused by the hardware, as Linux doesn't make use of Ring 1.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-4-git-send-email-joro@8bytes.org
---
 arch/x86/kernel/asm-offsets_32.c | 9 +++++++--
 arch/x86/kernel/process_32.c     | 2 ++
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 15b3f45b69cd..82826f2275cc 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -46,9 +46,14 @@ void foo(void)
 	OFFSET(saved_context_gdt_desc, saved_context, gdt_desc);
 	BLANK();
 
-	/* Offset from the entry stack to task stack stored in TSS */
+	/*
+	 * Offset from the entry stack to task stack stored in TSS. Kernel entry
+	 * happens on the per-cpu entry-stack, and the asm code switches to the
+	 * task-stack pointer stored in x86_tss.sp1, which is a copy of
+	 * task->thread.sp0 where entry code can find it.
+	 */
 	DEFINE(TSS_entry2task_stack,
-	       offsetof(struct cpu_entry_area, tss.x86_tss.sp0) -
+	       offsetof(struct cpu_entry_area, tss.x86_tss.sp1) -
 	       offsetofend(struct cpu_entry_area, entry_stack_page.stack));
 
 #ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0ae659de21eb..ec62cc77388d 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -290,6 +290,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
+	/* SYSENTER reads the task-stack from tss.sp1 */
+	this_cpu_write(cpu_tss_rw.x86_tss.sp1, next_p->thread.sp0);
 
 	/*
 	 * Restore %gs if needed (which is common)
-- 
cgit v1.2.3


From 46eabca284f9f27fe94698a068a4a21ba93b4975 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:41 +0200
Subject: x86/entry/32: Put ESPFIX code into a macro

This makes it easier to split up the shared iret code path.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-5-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 97 ++++++++++++++++++++++++-----------------------
 1 file changed, 49 insertions(+), 48 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 39f711ad0fc9..ef7d65315e8e 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -221,6 +221,54 @@
 	POP_GS_EX
 .endm
 
+.macro CHECK_AND_APPLY_ESPFIX
+#ifdef CONFIG_X86_ESPFIX32
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
+
+	ALTERNATIVE	"jmp .Lend_\@", "", X86_BUG_ESPFIX
+
+	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
+	/*
+	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
+	 * are returning to the kernel.
+	 * See comments in process.c:copy_thread() for details.
+	 */
+	movb	PT_OLDSS(%esp), %ah
+	movb	PT_CS(%esp), %al
+	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
+	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
+	jne	.Lend_\@	# returning to user-space with LDT SS
+
+	/*
+	 * Setup and switch to ESPFIX stack
+	 *
+	 * We're returning to userspace with a 16 bit stack. The CPU will not
+	 * restore the high word of ESP for us on executing iret... This is an
+	 * "official" bug of all the x86-compatible CPUs, which we can work
+	 * around to make dosemu and wine happy. We do this by preloading the
+	 * high word of ESP with the high word of the userspace ESP while
+	 * compensating for the offset by changing to the ESPFIX segment with
+	 * a base address that matches for the difference.
+	 */
+	mov	%esp, %edx			/* load kernel esp */
+	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
+	mov	%dx, %ax			/* eax: new kernel esp */
+	sub	%eax, %edx			/* offset (low word is 0) */
+	shr	$16, %edx
+	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
+	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
+	pushl	$__ESPFIX_SS
+	pushl	%eax				/* new kernel esp */
+	/*
+	 * Disable interrupts, but do not irqtrace this section: we
+	 * will soon execute iret and the tracer was already set to
+	 * the irqstate after the IRET:
+	 */
+	DISABLE_INTERRUPTS(CLBR_ANY)
+	lss	(%esp), %esp			/* switch to espfix segment */
+.Lend_\@:
+#endif /* CONFIG_X86_ESPFIX32 */
+.endm
 /*
  * %eax: prev task
  * %edx: next task
@@ -547,21 +595,7 @@ ENTRY(entry_INT80_32)
 restore_all:
 	TRACE_IRQS_IRET
 .Lrestore_all_notrace:
-#ifdef CONFIG_X86_ESPFIX32
-	ALTERNATIVE	"jmp .Lrestore_nocheck", "", X86_BUG_ESPFIX
-
-	movl	PT_EFLAGS(%esp), %eax		# mix EFLAGS, SS and CS
-	/*
-	 * Warning: PT_OLDSS(%esp) contains the wrong/random values if we
-	 * are returning to the kernel.
-	 * See comments in process.c:copy_thread() for details.
-	 */
-	movb	PT_OLDSS(%esp), %ah
-	movb	PT_CS(%esp), %al
-	andl	$(X86_EFLAGS_VM | (SEGMENT_TI_MASK << 8) | SEGMENT_RPL_MASK), %eax
-	cmpl	$((SEGMENT_LDT << 8) | USER_RPL), %eax
-	je .Lldt_ss				# returning to user-space with LDT SS
-#endif
+	CHECK_AND_APPLY_ESPFIX
 .Lrestore_nocheck:
 	RESTORE_REGS 4				# skip orig_eax/error_code
 .Lirq_return:
@@ -579,39 +613,6 @@ ENTRY(iret_exc	)
 	jmp	common_exception
 .previous
 	_ASM_EXTABLE(.Lirq_return, iret_exc)
-
-#ifdef CONFIG_X86_ESPFIX32
-.Lldt_ss:
-/*
- * Setup and switch to ESPFIX stack
- *
- * We're returning to userspace with a 16 bit stack. The CPU will not
- * restore the high word of ESP for us on executing iret... This is an
- * "official" bug of all the x86-compatible CPUs, which we can work
- * around to make dosemu and wine happy. We do this by preloading the
- * high word of ESP with the high word of the userspace ESP while
- * compensating for the offset by changing to the ESPFIX segment with
- * a base address that matches for the difference.
- */
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
-	mov	%esp, %edx			/* load kernel esp */
-	mov	PT_OLDESP(%esp), %eax		/* load userspace esp */
-	mov	%dx, %ax			/* eax: new kernel esp */
-	sub	%eax, %edx			/* offset (low word is 0) */
-	shr	$16, %edx
-	mov	%dl, GDT_ESPFIX_SS + 4		/* bits 16..23 */
-	mov	%dh, GDT_ESPFIX_SS + 7		/* bits 24..31 */
-	pushl	$__ESPFIX_SS
-	pushl	%eax				/* new kernel esp */
-	/*
-	 * Disable interrupts, but do not irqtrace this section: we
-	 * will soon execute iret and the tracer was already set to
-	 * the irqstate after the IRET:
-	 */
-	DISABLE_INTERRUPTS(CLBR_ANY)
-	lss	(%esp), %esp			/* switch to espfix segment */
-	jmp	.Lrestore_nocheck
-#endif
 ENDPROC(entry_INT80_32)
 
 .macro FIXUP_ESPFIX_STACK
-- 
cgit v1.2.3


From 8e676ced31e9d1448d3ffc4159586a259cc67f30 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:42 +0200
Subject: x86/entry/32: Unshare NMI return path

NMI will no longer use most of the shared return path, because NMI needs
special handling when the CR3 switches for PTI are added. Prepare for that
change.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-6-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index ef7d65315e8e..43641310b6e3 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1017,7 +1017,7 @@ ENTRY(nmi)
 
 	/* Not on SYSENTER stack. */
 	call	do_nmi
-	jmp	.Lrestore_all_notrace
+	jmp	.Lnmi_return
 
 .Lnmi_from_sysenter_stack:
 	/*
@@ -1028,7 +1028,11 @@ ENTRY(nmi)
 	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
 	call	do_nmi
 	movl	%ebx, %esp
-	jmp	.Lrestore_all_notrace
+
+.Lnmi_return:
+	CHECK_AND_APPLY_ESPFIX
+	RESTORE_REGS 4
+	jmp	.Lirq_return
 
 #ifdef CONFIG_X86_ESPFIX32
 .Lnmi_espfix_stack:
-- 
cgit v1.2.3


From 0d2eb73b29996684d5bbb72f85c74b47b4c359f7 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:43 +0200
Subject: x86/entry/32: Split off return-to-kernel path

Use a separate return path when returning to the kernel.

This allows to put the PTI cr3-switch and the switch to the entry-stack
into the return-to-user path without further checking.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-7-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 43641310b6e3..7251c4f3e99e 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -65,7 +65,7 @@
 # define preempt_stop(clobbers)	DISABLE_INTERRUPTS(clobbers); TRACE_IRQS_OFF
 #else
 # define preempt_stop(clobbers)
-# define resume_kernel		restore_all
+# define resume_kernel		restore_all_kernel
 #endif
 
 .macro TRACE_IRQS_IRET
@@ -399,9 +399,9 @@ ENTRY(resume_kernel)
 	DISABLE_INTERRUPTS(CLBR_ANY)
 .Lneed_resched:
 	cmpl	$0, PER_CPU_VAR(__preempt_count)
-	jnz	restore_all
+	jnz	restore_all_kernel
 	testl	$X86_EFLAGS_IF, PT_EFLAGS(%esp)	# interrupts off (exception path) ?
-	jz	restore_all
+	jz	restore_all_kernel
 	call	preempt_schedule_irq
 	jmp	.Lneed_resched
 END(resume_kernel)
@@ -606,6 +606,11 @@ restore_all:
 	 */
 	INTERRUPT_RETURN
 
+restore_all_kernel:
+	TRACE_IRQS_IRET
+	RESTORE_REGS 4
+	jmp	.Lirq_return
+
 .section .fixup, "ax"
 ENTRY(iret_exc	)
 	pushl	$0				# no error code
-- 
cgit v1.2.3


From 45d7b255747c21fc4b1f5043bee0754d39c3bdbf Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:44 +0200
Subject: x86/entry/32: Enter the kernel via trampoline stack

Use the entry-stack as a trampoline to enter the kernel. The entry-stack is
already in the cpu_entry_area and will be mapped to userspace when PTI is
enabled.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-8-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S        | 119 ++++++++++++++++++++++++++++++++-------
 arch/x86/include/asm/switch_to.h |  14 ++++-
 arch/x86/kernel/asm-offsets.c    |   1 +
 arch/x86/kernel/cpu/common.c     |   5 +-
 arch/x86/kernel/process.c        |   2 -
 arch/x86/kernel/process_32.c     |   2 -
 6 files changed, 115 insertions(+), 28 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 7251c4f3e99e..fea49ec345ba 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -154,7 +154,7 @@
 
 #endif /* CONFIG_X86_32_LAZY_GS */
 
-.macro SAVE_ALL pt_regs_ax=%eax
+.macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
 	cld
 	PUSH_GS
 	pushl	%fs
@@ -173,6 +173,12 @@
 	movl	$(__KERNEL_PERCPU), %edx
 	movl	%edx, %fs
 	SET_KERNEL_GS %edx
+
+	/* Switch to kernel stack if necessary */
+.if \switch_stacks > 0
+	SWITCH_TO_KERNEL_STACK
+.endif
+
 .endm
 
 /*
@@ -269,6 +275,73 @@
 .Lend_\@:
 #endif /* CONFIG_X86_ESPFIX32 */
 .endm
+
+
+/*
+ * Called with pt_regs fully populated and kernel segments loaded,
+ * so we can access PER_CPU and use the integer registers.
+ *
+ * We need to be very careful here with the %esp switch, because an NMI
+ * can happen everywhere. If the NMI handler finds itself on the
+ * entry-stack, it will overwrite the task-stack and everything we
+ * copied there. So allocate the stack-frame on the task-stack and
+ * switch to it before we do any copying.
+ */
+.macro SWITCH_TO_KERNEL_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	/* Are we on the entry stack? Bail out if not! */
+	movl	PER_CPU_VAR(cpu_entry_area), %ecx
+	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
+	subl	%esp, %ecx	/* ecx = (end of entry_stack) - esp */
+	cmpl	$SIZEOF_entry_stack, %ecx
+	jae	.Lend_\@
+
+	/* Load stack pointer into %esi and %edi */
+	movl	%esp, %esi
+	movl	%esi, %edi
+
+	/* Move %edi to the top of the entry stack */
+	andl	$(MASK_entry_stack), %edi
+	addl	$(SIZEOF_entry_stack), %edi
+
+	/* Load top of task-stack into %edi */
+	movl	TSS_entry2task_stack(%edi), %edi
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$X86_EFLAGS_VM, PT_EFLAGS(%esi)
+	jz	.Lcopy_pt_regs_\@
+
+	/*
+	 * Stack-frame contains 4 additional segment registers when
+	 * coming from VM86 mode
+	 */
+	addl	$(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+	/* Allocate frame on task-stack */
+	subl	%ecx, %edi
+
+	/* Switch to task-stack */
+	movl	%edi, %esp
+
+	/*
+	 * We are now on the task-stack and can safely copy over the
+	 * stack-frame
+	 */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+.Lend_\@:
+.endm
+
 /*
  * %eax: prev task
  * %edx: next task
@@ -469,7 +542,7 @@ ENTRY(entry_SYSENTER_32)
 	pushl	$__USER_CS		/* pt_regs->cs */
 	pushl	$0			/* pt_regs->ip = 0 (placeholder) */
 	pushl	%eax			/* pt_regs->orig_ax */
-	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest, stack already switched */
 
 	/*
 	 * SYSENTER doesn't filter flags, so we need to clear NT, AC
@@ -580,7 +653,8 @@ ENDPROC(entry_SYSENTER_32)
 ENTRY(entry_INT80_32)
 	ASM_CLAC
 	pushl	%eax			/* pt_regs->orig_ax */
-	SAVE_ALL pt_regs_ax=$-ENOSYS	/* save rest */
+
+	SAVE_ALL pt_regs_ax=$-ENOSYS switch_stacks=1	/* save rest */
 
 	/*
 	 * User mode is traced as though IRQs are on, and the interrupt gate
@@ -677,7 +751,8 @@ END(irq_entries_start)
 common_interrupt:
 	ASM_CLAC
 	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
-	SAVE_ALL
+
+	SAVE_ALL switch_stacks=1
 	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	movl	%esp, %eax
@@ -685,16 +760,16 @@ common_interrupt:
 	jmp	ret_from_intr
 ENDPROC(common_interrupt)
 
-#define BUILD_INTERRUPT3(name, nr, fn)	\
-ENTRY(name)				\
-	ASM_CLAC;			\
-	pushl	$~(nr);			\
-	SAVE_ALL;			\
-	ENCODE_FRAME_POINTER;		\
-	TRACE_IRQS_OFF			\
-	movl	%esp, %eax;		\
-	call	fn;			\
-	jmp	ret_from_intr;		\
+#define BUILD_INTERRUPT3(name, nr, fn)			\
+ENTRY(name)						\
+	ASM_CLAC;					\
+	pushl	$~(nr);					\
+	SAVE_ALL switch_stacks=1;			\
+	ENCODE_FRAME_POINTER;				\
+	TRACE_IRQS_OFF					\
+	movl	%esp, %eax;				\
+	call	fn;					\
+	jmp	ret_from_intr;				\
 ENDPROC(name)
 
 #define BUILD_INTERRUPT(name, nr)		\
@@ -926,16 +1001,20 @@ common_exception:
 	pushl	%es
 	pushl	%ds
 	pushl	%eax
+	movl	$(__USER_DS), %eax
+	movl	%eax, %ds
+	movl	%eax, %es
+	movl	$(__KERNEL_PERCPU), %eax
+	movl	%eax, %fs
 	pushl	%ebp
 	pushl	%edi
 	pushl	%esi
 	pushl	%edx
 	pushl	%ecx
 	pushl	%ebx
+	SWITCH_TO_KERNEL_STACK
 	ENCODE_FRAME_POINTER
 	cld
-	movl	$(__KERNEL_PERCPU), %ecx
-	movl	%ecx, %fs
 	UNWIND_ESPFIX_STACK
 	GS_TO_REG %ecx
 	movl	PT_GS(%esp), %edi		# get the function address
@@ -943,9 +1022,6 @@ common_exception:
 	movl	$-1, PT_ORIG_EAX(%esp)		# no syscall to restart
 	REG_TO_PTGS %ecx
 	SET_KERNEL_GS %ecx
-	movl	$(__USER_DS), %ecx
-	movl	%ecx, %ds
-	movl	%ecx, %es
 	TRACE_IRQS_OFF
 	movl	%esp, %eax			# pt_regs pointer
 	CALL_NOSPEC %edi
@@ -964,6 +1040,7 @@ ENTRY(debug)
 	 */
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
+
 	SAVE_ALL
 	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# error code 0
@@ -999,6 +1076,7 @@ END(debug)
  */
 ENTRY(nmi)
 	ASM_CLAC
+
 #ifdef CONFIG_X86_ESPFIX32
 	pushl	%eax
 	movl	%ss, %eax
@@ -1066,7 +1144,8 @@ END(nmi)
 ENTRY(int3)
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
-	SAVE_ALL
+
+	SAVE_ALL switch_stacks=1
 	ENCODE_FRAME_POINTER
 	TRACE_IRQS_OFF
 	xorl	%edx, %edx			# zero error code
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index eb5f7999a893..8bc2f70b452e 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -89,13 +89,23 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 /* This is used when switching tasks or entering/exiting vm86 mode. */
 static inline void update_sp0(struct task_struct *task)
 {
-	/* On x86_64, sp0 always points to the entry trampoline stack, which is constant: */
+	/* sp0 always points to the entry trampoline stack, which is constant: */
 #ifdef CONFIG_X86_32
-	load_sp0(task->thread.sp0);
+	if (static_cpu_has(X86_FEATURE_XENPV))
+		load_sp0(task->thread.sp0);
+	else
+		this_cpu_write(cpu_tss_rw.x86_tss.sp1, task->thread.sp0);
 #else
+	/*
+	 * x86-64 updates x86_tss.sp1 via cpu_current_top_of_stack. That
+	 * doesn't work on x86-32 because sp1 and
+	 * cpu_current_top_of_stack have different values (because of
+	 * the non-zero stack-padding on 32bit).
+	 */
 	if (static_cpu_has(X86_FEATURE_XENPV))
 		load_sp0(task_top_of_stack(task));
 #endif
+
 }
 
 #endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index a1e16286a832..01de31db300d 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -103,6 +103,7 @@ void common(void) {
 	OFFSET(CPU_ENTRY_AREA_entry_trampoline, cpu_entry_area, entry_trampoline);
 	OFFSET(CPU_ENTRY_AREA_entry_stack, cpu_entry_area, entry_stack_page);
 	DEFINE(SIZEOF_entry_stack, sizeof(struct entry_stack));
+	DEFINE(MASK_entry_stack, (~(sizeof(struct entry_stack) - 1)));
 
 	/* Offset for sp0 and sp1 into the tss_struct */
 	OFFSET(TSS_sp0, tss_struct, x86_tss.sp0);
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb4cb3efd20e..43a927eb9c09 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1804,11 +1804,12 @@ void cpu_init(void)
 	enter_lazy_tlb(&init_mm, curr);
 
 	/*
-	 * Initialize the TSS.  Don't bother initializing sp0, as the initial
-	 * task never enters user mode.
+	 * Initialize the TSS.  sp0 points to the entry trampoline stack
+	 * regardless of what task is running.
 	 */
 	set_tss_desc(cpu, &get_cpu_entry_area(cpu)->tss.x86_tss);
 	load_TR_desc();
+	load_sp0((unsigned long)(cpu_entry_stack(cpu) + 1));
 
 	load_mm_ldt(&init_mm);
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 30ca2d1a9231..c93fcfdf1673 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -57,14 +57,12 @@ __visible DEFINE_PER_CPU_PAGE_ALIGNED(struct tss_struct, cpu_tss_rw) = {
 		 */
 		.sp0 = (1UL << (BITS_PER_LONG-1)) + 1,
 
-#ifdef CONFIG_X86_64
 		/*
 		 * .sp1 is cpu_current_top_of_stack.  The init task never
 		 * runs user code, but cpu_current_top_of_stack should still
 		 * be well defined before the first context switch.
 		 */
 		.sp1 = TOP_OF_INIT_STACK,
-#endif
 
 #ifdef CONFIG_X86_32
 		.ss0 = __KERNEL_DS,
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index ec62cc77388d..0ae659de21eb 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -290,8 +290,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
 		       THREAD_SIZE);
-	/* SYSENTER reads the task-stack from tss.sp1 */
-	this_cpu_write(cpu_tss_rw.x86_tss.sp1, next_p->thread.sp0);
 
 	/*
 	 * Restore %gs if needed (which is common)
-- 
cgit v1.2.3


From e5862d0515ad970ccec6208ecf5bb0cffe291ea3 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:45 +0200
Subject: x86/entry/32: Leave the kernel via trampoline stack

Switch back to the trampoline stack before returning to userspace.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-9-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 79 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 77 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index fea49ec345ba..a905e6215ea9 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -342,6 +342,60 @@
 .Lend_\@:
 .endm
 
+/*
+ * Switch back from the kernel stack to the entry stack.
+ *
+ * The %esp register must point to pt_regs on the task stack. It will
+ * first calculate the size of the stack-frame to copy, depending on
+ * whether we return to VM86 mode or not. With that it uses 'rep movsl'
+ * to copy the contents of the stack over to the entry stack.
+ *
+ * We must be very careful here, as we can't trust the contents of the
+ * task-stack once we switched to the entry-stack. When an NMI happens
+ * while on the entry-stack, the NMI handler will switch back to the top
+ * of the task stack, overwriting our stack-frame we are about to copy.
+ * Therefore we switch the stack only after everything is copied over.
+ */
+.macro SWITCH_TO_ENTRY_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$(X86_EFLAGS_VM), PT_EFLAGS(%esp)
+	jz	.Lcopy_pt_regs_\@
+
+	/* Additional 4 registers to copy when returning to VM86 mode */
+	addl    $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+	/* Initialize source and destination for movsl */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+	subl	%ecx, %edi
+	movl	%esp, %esi
+
+	/* Save future stack pointer in %ebx */
+	movl	%edi, %ebx
+
+	/* Copy over the stack-frame */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	/*
+	 * Switch to entry-stack - needs to happen after everything is
+	 * copied because the NMI handler will overwrite the task-stack
+	 * when on entry-stack
+	 */
+	movl	%ebx, %esp
+
+.Lend_\@:
+.endm
+
 /*
  * %eax: prev task
  * %edx: next task
@@ -581,25 +635,45 @@ ENTRY(entry_SYSENTER_32)
 
 /* Opportunistic SYSEXIT */
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+
+	/*
+	 * Setup entry stack - we keep the pointer in %eax and do the
+	 * switch after almost all user-state is restored.
+	 */
+
+	/* Load entry stack pointer and allocate frame for eflags/eax */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %eax
+	subl	$(2*4), %eax
+
+	/* Copy eflags and eax to entry stack */
+	movl	PT_EFLAGS(%esp), %edi
+	movl	PT_EAX(%esp), %esi
+	movl	%edi, (%eax)
+	movl	%esi, 4(%eax)
+
+	/* Restore user registers and segments */
 	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
 	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
 	PTGS_TO_GS
+
 	popl	%ebx			/* pt_regs->bx */
 	addl	$2*4, %esp		/* skip pt_regs->cx and pt_regs->dx */
 	popl	%esi			/* pt_regs->si */
 	popl	%edi			/* pt_regs->di */
 	popl	%ebp			/* pt_regs->bp */
-	popl	%eax			/* pt_regs->ax */
+
+	/* Switch to entry stack */
+	movl	%eax, %esp
 
 	/*
 	 * Restore all flags except IF. (We restore IF separately because
 	 * STI gives a one-instruction window in which we won't be interrupted,
 	 * whereas POPF does not.)
 	 */
-	addl	$PT_EFLAGS-PT_DS, %esp	/* point esp at pt_regs->flags */
 	btrl	$X86_EFLAGS_IF_BIT, (%esp)
 	popfl
+	popl	%eax
 
 	/*
 	 * Return back to the vDSO, which will pop ecx and edx.
@@ -668,6 +742,7 @@ ENTRY(entry_INT80_32)
 
 restore_all:
 	TRACE_IRQS_IRET
+	SWITCH_TO_ENTRY_STACK
 .Lrestore_all_notrace:
 	CHECK_AND_APPLY_ESPFIX
 .Lrestore_nocheck:
-- 
cgit v1.2.3


From 8b376fae0514dc7ee04786e2327169e39d12e51b Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:46 +0200
Subject: x86/entry/32: Introduce SAVE_ALL_NMI and RESTORE_ALL_NMI

These macros will be used in the NMI handler code and replace plain
SAVE_ALL and RESTORE_REGS there.

The NMI-specific CR3-switch will be added to these macros later.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-10-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index a905e6215ea9..763592596727 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -181,6 +181,9 @@
 
 .endm
 
+.macro SAVE_ALL_NMI
+	SAVE_ALL
+.endm
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
  * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
@@ -227,6 +230,10 @@
 	POP_GS_EX
 .endm
 
+.macro RESTORE_ALL_NMI pop=0
+	RESTORE_REGS pop=\pop
+.endm
+
 .macro CHECK_AND_APPLY_ESPFIX
 #ifdef CONFIG_X86_ESPFIX32
 #define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + (GDT_ENTRY_ESPFIX_SS * 8)
@@ -1161,7 +1168,7 @@ ENTRY(nmi)
 #endif
 
 	pushl	%eax				# pt_regs->orig_ax
-	SAVE_ALL
+	SAVE_ALL_NMI
 	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
@@ -1189,7 +1196,7 @@ ENTRY(nmi)
 
 .Lnmi_return:
 	CHECK_AND_APPLY_ESPFIX
-	RESTORE_REGS 4
+	RESTORE_ALL_NMI pop=4
 	jmp	.Lirq_return
 
 #ifdef CONFIG_X86_ESPFIX32
@@ -1205,12 +1212,12 @@ ENTRY(nmi)
 	pushl	16(%esp)
 	.endr
 	pushl	%eax
-	SAVE_ALL
+	SAVE_ALL_NMI
 	ENCODE_FRAME_POINTER
 	FIXUP_ESPFIX_STACK			# %eax == %esp
 	xorl	%edx, %edx			# zero error code
 	call	do_nmi
-	RESTORE_REGS
+	RESTORE_ALL_NMI
 	lss	12+4(%esp), %esp		# back to espfix stack
 	jmp	.Lirq_return
 #endif
-- 
cgit v1.2.3


From b92a165df17ee6e616e43107730f06bf6ecf5d8d Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:47 +0200
Subject: x86/entry/32: Handle Entry from Kernel-Mode on Entry-Stack

It is possible that the kernel is entered from kernel-mode and on the
entry-stack. The most common way this happens is when an exception is
triggered while loading the user-space segment registers on the
kernel-to-userspace exit path.

The segment loading needs to be done after the entry-stack switch, because
the stack-switch needs kernel %fs for per_cpu access.

When this happens, make sure to leave the kernel with the entry-stack
again, so that the interrupted code-path runs on the right stack when
switching to the user-cr3.

Detect this condition on kernel-entry by checking CS.RPL and %esp, and if
it happens, copy over the complete content of the entry stack to the
task-stack.  This needs to be done because once the exception handler is
entereed, the task might be scheduled out or even migrated to a different
CPU, so this cannot rely on the entry-stack contents. Leave a marker in the
stack-frame to detect this condition on the exit path.

On the exit path the copy is reversed, copy all of the remaining task-stack
back to the entry-stack and switch to it.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-11-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 116 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 115 insertions(+), 1 deletion(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 763592596727..9d6eceba0461 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -294,6 +294,9 @@
  * copied there. So allocate the stack-frame on the task-stack and
  * switch to it before we do any copying.
  */
+
+#define CS_FROM_ENTRY_STACK	(1 << 31)
+
 .macro SWITCH_TO_KERNEL_STACK
 
 	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
@@ -316,6 +319,16 @@
 	/* Load top of task-stack into %edi */
 	movl	TSS_entry2task_stack(%edi), %edi
 
+	/*
+	 * Clear unused upper bits of the dword containing the word-sized CS
+	 * slot in pt_regs in case hardware didn't clear it for us.
+	 */
+	andl	$(0x0000ffff), PT_CS(%esp)
+
+	/* Special case - entry from kernel mode via entry stack */
+	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
+	jz	.Lentry_from_kernel_\@
+
 	/* Bytes to copy */
 	movl	$PTREGS_SIZE, %ecx
 
@@ -329,8 +342,8 @@
 	 */
 	addl	$(4 * 4), %ecx
 
-.Lcopy_pt_regs_\@:
 #endif
+.Lcopy_pt_regs_\@:
 
 	/* Allocate frame on task-stack */
 	subl	%ecx, %edi
@@ -346,6 +359,56 @@
 	cld
 	rep movsl
 
+	jmp .Lend_\@
+
+.Lentry_from_kernel_\@:
+
+	/*
+	 * This handles the case when we enter the kernel from
+	 * kernel-mode and %esp points to the entry-stack. When this
+	 * happens we need to switch to the task-stack to run C code,
+	 * but switch back to the entry-stack again when we approach
+	 * iret and return to the interrupted code-path. This usually
+	 * happens when we hit an exception while restoring user-space
+	 * segment registers on the way back to user-space.
+	 *
+	 * When we switch to the task-stack here, we can't trust the
+	 * contents of the entry-stack anymore, as the exception handler
+	 * might be scheduled out or moved to another CPU. Therefore we
+	 * copy the complete entry-stack to the task-stack and set a
+	 * marker in the iret-frame (bit 31 of the CS dword) to detect
+	 * what we've done on the iret path.
+	 *
+	 * On the iret path we copy everything back and switch to the
+	 * entry-stack, so that the interrupted kernel code-path
+	 * continues on the same stack it was interrupted with.
+	 *
+	 * Be aware that an NMI can happen anytime in this code.
+	 *
+	 * %esi: Entry-Stack pointer (same as %esp)
+	 * %edi: Top of the task stack
+	 */
+
+	/* Calculate number of bytes on the entry stack in %ecx */
+	movl	%esi, %ecx
+
+	/* %ecx to the top of entry-stack */
+	andl	$(MASK_entry_stack), %ecx
+	addl	$(SIZEOF_entry_stack), %ecx
+
+	/* Number of bytes on the entry stack to %ecx */
+	sub	%esi, %ecx
+
+	/* Mark stackframe as coming from entry stack */
+	orl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
+
+	/*
+	 * %esi and %edi are unchanged, %ecx contains the number of
+	 * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate
+	 * the stack-frame on task-stack and copy everything over
+	 */
+	jmp .Lcopy_pt_regs_\@
+
 .Lend_\@:
 .endm
 
@@ -403,6 +466,56 @@
 .Lend_\@:
 .endm
 
+/*
+ * This macro handles the case when we return to kernel-mode on the iret
+ * path and have to switch back to the entry stack.
+ *
+ * See the comments below the .Lentry_from_kernel_\@ label in the
+ * SWITCH_TO_KERNEL_STACK macro for more details.
+ */
+.macro PARANOID_EXIT_TO_KERNEL_MODE
+
+	/*
+	 * Test if we entered the kernel with the entry-stack. Most
+	 * likely we did not, because this code only runs on the
+	 * return-to-kernel path.
+	 */
+	testl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
+	jz	.Lend_\@
+
+	/* Unlikely slow-path */
+
+	/* Clear marker from stack-frame */
+	andl	$(~CS_FROM_ENTRY_STACK), PT_CS(%esp)
+
+	/* Copy the remaining task-stack contents to entry-stack */
+	movl	%esp, %esi
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+
+	/* Bytes on the task-stack to ecx */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp1), %ecx
+	subl	%esi, %ecx
+
+	/* Allocate stack-frame on entry-stack */
+	subl	%ecx, %edi
+
+	/*
+	 * Save future stack-pointer, we must not switch until the
+	 * copy is done, otherwise the NMI handler could destroy the
+	 * contents of the task-stack we are about to copy.
+	 */
+	movl	%edi, %ebx
+
+	/* Do the copy */
+	shrl	$2, %ecx
+	cld
+	rep movsl
+
+	/* Safe to switch to entry-stack now */
+	movl	%ebx, %esp
+
+.Lend_\@:
+.endm
 /*
  * %eax: prev task
  * %edx: next task
@@ -764,6 +877,7 @@ restore_all:
 
 restore_all_kernel:
 	TRACE_IRQS_IRET
+	PARANOID_EXIT_TO_KERNEL_MODE
 	RESTORE_REGS 4
 	jmp	.Lirq_return
 
-- 
cgit v1.2.3


From 929b44eb5739bf11d4a9bce85d7346bd955fc24d Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:48 +0200
Subject: x86/entry/32: Simplify debug entry point

The common exception entry code now handles the entry-from-sysenter stack
situation and makes sure to leave with the same stack as it entered the
kernel.

So there is no need anymore for the special handling in the debug entry
code.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-12-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 35 +++--------------------------------
 1 file changed, 3 insertions(+), 32 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 9d6eceba0461..dbf7d619dcd6 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1226,41 +1226,12 @@ END(common_exception)
 
 ENTRY(debug)
 	/*
-	 * #DB can happen at the first instruction of
-	 * entry_SYSENTER_32 or in Xen's SYSENTER prologue.  If this
-	 * happens, then we will be running on a very small stack.  We
-	 * need to detect this condition and switch to the thread
-	 * stack before calling any C code at all.
-	 *
-	 * If you edit this code, keep in mind that NMIs can happen in here.
+	 * Entry from sysenter is now handled in common_exception
 	 */
 	ASM_CLAC
 	pushl	$-1				# mark this as an int
-
-	SAVE_ALL
-	ENCODE_FRAME_POINTER
-	xorl	%edx, %edx			# error code 0
-	movl	%esp, %eax			# pt_regs pointer
-
-	/* Are we currently on the SYSENTER stack? */
-	movl	PER_CPU_VAR(cpu_entry_area), %ecx
-	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
-	subl	%eax, %ecx	/* ecx = (end of entry_stack) - esp */
-	cmpl	$SIZEOF_entry_stack, %ecx
-	jb	.Ldebug_from_sysenter_stack
-
-	TRACE_IRQS_OFF
-	call	do_debug
-	jmp	ret_from_exception
-
-.Ldebug_from_sysenter_stack:
-	/* We're on the SYSENTER stack.  Switch off. */
-	movl	%esp, %ebx
-	movl	PER_CPU_VAR(cpu_current_top_of_stack), %esp
-	TRACE_IRQS_OFF
-	call	do_debug
-	movl	%ebx, %esp
-	jmp	ret_from_exception
+	pushl	$do_debug
+	jmp	common_exception
 END(debug)
 
 /*
-- 
cgit v1.2.3


From e464fb9f241ddf46815b31ca594af96f2699a78e Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:49 +0200
Subject: x86/entry/32: Add PTI cr3 switch to non-NMI entry/exit points

Add unconditional cr3 switches between user and kernel cr3 to all non-NMI
entry and exit points.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-13-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 86 ++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 82 insertions(+), 4 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index dbf7d619dcd6..60b28dfa00dc 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -77,6 +77,8 @@
 #endif
 .endm
 
+#define PTI_SWITCH_MASK         (1 << PAGE_SHIFT)
+
 /*
  * User gs save/restore
  *
@@ -154,6 +156,33 @@
 
 #endif /* CONFIG_X86_32_LAZY_GS */
 
+/* Unconditionally switch to user cr3 */
+.macro SWITCH_TO_USER_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+
+	movl	%cr3, \scratch_reg
+	orl	$PTI_SWITCH_MASK, \scratch_reg
+	movl	\scratch_reg, %cr3
+.Lend_\@:
+.endm
+
+/*
+ * Switch to kernel cr3 if not already loaded and return current cr3 in
+ * \scratch_reg
+ */
+.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	movl	%cr3, \scratch_reg
+	/* Test if we are already on kernel CR3 */
+	testl	$PTI_SWITCH_MASK, \scratch_reg
+	jz	.Lend_\@
+	andl	$(~PTI_SWITCH_MASK), \scratch_reg
+	movl	\scratch_reg, %cr3
+	/* Return original CR3 in \scratch_reg */
+	orl	$PTI_SWITCH_MASK, \scratch_reg
+.Lend_\@:
+.endm
+
 .macro SAVE_ALL pt_regs_ax=%eax switch_stacks=0
 	cld
 	PUSH_GS
@@ -283,7 +312,6 @@
 #endif /* CONFIG_X86_ESPFIX32 */
 .endm
 
-
 /*
  * Called with pt_regs fully populated and kernel segments loaded,
  * so we can access PER_CPU and use the integer registers.
@@ -296,11 +324,19 @@
  */
 
 #define CS_FROM_ENTRY_STACK	(1 << 31)
+#define CS_FROM_USER_CR3	(1 << 30)
 
 .macro SWITCH_TO_KERNEL_STACK
 
 	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
 
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+
+	/*
+	 * %eax now contains the entry cr3 and we carry it forward in
+	 * that register for the time this macro runs
+	 */
+
 	/* Are we on the entry stack? Bail out if not! */
 	movl	PER_CPU_VAR(cpu_entry_area), %ecx
 	addl	$CPU_ENTRY_AREA_entry_stack + SIZEOF_entry_stack, %ecx
@@ -370,7 +406,8 @@
 	 * but switch back to the entry-stack again when we approach
 	 * iret and return to the interrupted code-path. This usually
 	 * happens when we hit an exception while restoring user-space
-	 * segment registers on the way back to user-space.
+	 * segment registers on the way back to user-space or when the
+	 * sysenter handler runs with eflags.tf set.
 	 *
 	 * When we switch to the task-stack here, we can't trust the
 	 * contents of the entry-stack anymore, as the exception handler
@@ -387,6 +424,7 @@
 	 *
 	 * %esi: Entry-Stack pointer (same as %esp)
 	 * %edi: Top of the task stack
+	 * %eax: CR3 on kernel entry
 	 */
 
 	/* Calculate number of bytes on the entry stack in %ecx */
@@ -402,6 +440,14 @@
 	/* Mark stackframe as coming from entry stack */
 	orl	$CS_FROM_ENTRY_STACK, PT_CS(%esp)
 
+	/*
+	 * Test the cr3 used to enter the kernel and add a marker
+	 * so that we can switch back to it before iret.
+	 */
+	testl	$PTI_SWITCH_MASK, %eax
+	jz	.Lcopy_pt_regs_\@
+	orl	$CS_FROM_USER_CR3, PT_CS(%esp)
+
 	/*
 	 * %esi and %edi are unchanged, %ecx contains the number of
 	 * bytes to copy. The code at .Lcopy_pt_regs_\@ will allocate
@@ -468,7 +514,7 @@
 
 /*
  * This macro handles the case when we return to kernel-mode on the iret
- * path and have to switch back to the entry stack.
+ * path and have to switch back to the entry stack and/or user-cr3
  *
  * See the comments below the .Lentry_from_kernel_\@ label in the
  * SWITCH_TO_KERNEL_STACK macro for more details.
@@ -514,6 +560,18 @@
 	/* Safe to switch to entry-stack now */
 	movl	%ebx, %esp
 
+	/*
+	 * We came from entry-stack and need to check if we also need to
+	 * switch back to user cr3.
+	 */
+	testl	$CS_FROM_USER_CR3, PT_CS(%esp)
+	jz	.Lend_\@
+
+	/* Clear marker from stack-frame */
+	andl	$(~CS_FROM_USER_CR3), PT_CS(%esp)
+
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+
 .Lend_\@:
 .endm
 /*
@@ -707,7 +765,20 @@ ENTRY(xen_sysenter_target)
  * 0(%ebp) arg6
  */
 ENTRY(entry_SYSENTER_32)
+	/*
+	 * On entry-stack with all userspace-regs live - save and
+	 * restore eflags and %eax to use it as scratch-reg for the cr3
+	 * switch.
+	 */
+	pushfl
+	pushl	%eax
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
+	popl	%eax
+	popfl
+
+	/* Stack empty again, switch to task stack */
 	movl	TSS_entry2task_stack(%esp), %esp
+
 .Lsysenter_past_esp:
 	pushl	$__USER_DS		/* pt_regs->ss */
 	pushl	%ebp			/* pt_regs->sp (stashed in bp) */
@@ -786,6 +857,9 @@ ENTRY(entry_SYSENTER_32)
 	/* Switch to entry stack */
 	movl	%eax, %esp
 
+	/* Now ready to switch the cr3 */
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+
 	/*
 	 * Restore all flags except IF. (We restore IF separately because
 	 * STI gives a one-instruction window in which we won't be interrupted,
@@ -866,7 +940,11 @@ restore_all:
 .Lrestore_all_notrace:
 	CHECK_AND_APPLY_ESPFIX
 .Lrestore_nocheck:
-	RESTORE_REGS 4				# skip orig_eax/error_code
+	/* Switch back to user CR3 */
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+
+	/* Restore user state */
+	RESTORE_REGS pop=4			# skip orig_eax/error_code
 .Lirq_return:
 	/*
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
-- 
cgit v1.2.3


From b65bef400689ceee7108c2d47fb97ae91f4d1440 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:50 +0200
Subject: x86/entry/32: Add PTI CR3 switches to NMI handler code

The NMI handler is special, as it needs to leave with the same CR3 as it
was entered with. This is required because the NMI can happen within kernel
context but with user CR3 already loaded, i.e. after switching to user CR3
but before returning to user space.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-14-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 39 +++++++++++++++++++++++++++++++++------
 1 file changed, 33 insertions(+), 6 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 60b28dfa00dc..b1541c74c71a 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -210,8 +210,19 @@
 
 .endm
 
-.macro SAVE_ALL_NMI
+.macro SAVE_ALL_NMI cr3_reg:req
 	SAVE_ALL
+
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We can enter with either user or kernel cr3, the code will
+	 * store the old cr3 in \cr3_reg and switches to the kernel cr3
+	 * if necessary.
+	 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg
+
+.Lend_\@:
 .endm
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
@@ -259,7 +270,23 @@
 	POP_GS_EX
 .endm
 
-.macro RESTORE_ALL_NMI pop=0
+.macro RESTORE_ALL_NMI cr3_reg:req pop=0
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We enter with kernel cr3 and switch the cr3 to the value
+	 * stored on \cr3_reg, which is either a user or a kernel cr3.
+	 */
+	ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI
+
+	testl	$PTI_SWITCH_MASK, \cr3_reg
+	jz	.Lswitched_\@
+
+	/* User cr3 in \cr3_reg - write it to hardware cr3 */
+	movl	\cr3_reg, %cr3
+
+.Lswitched_\@:
+
 	RESTORE_REGS pop=\pop
 .endm
 
@@ -1331,7 +1358,7 @@ ENTRY(nmi)
 #endif
 
 	pushl	%eax				# pt_regs->orig_ax
-	SAVE_ALL_NMI
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
@@ -1359,7 +1386,7 @@ ENTRY(nmi)
 
 .Lnmi_return:
 	CHECK_AND_APPLY_ESPFIX
-	RESTORE_ALL_NMI pop=4
+	RESTORE_ALL_NMI cr3_reg=%edi pop=4
 	jmp	.Lirq_return
 
 #ifdef CONFIG_X86_ESPFIX32
@@ -1375,12 +1402,12 @@ ENTRY(nmi)
 	pushl	16(%esp)
 	.endr
 	pushl	%eax
-	SAVE_ALL_NMI
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	FIXUP_ESPFIX_STACK			# %eax == %esp
 	xorl	%edx, %edx			# zero error code
 	call	do_nmi
-	RESTORE_ALL_NMI
+	RESTORE_ALL_NMI cr3_reg=%edi
 	lss	12+4(%esp), %esp		# back to espfix stack
 	jmp	.Lirq_return
 #endif
-- 
cgit v1.2.3


From 252e1a0526304f0f3f6888fc09e81cb220f957f3 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:51 +0200
Subject: x86/entry: Rename update_sp0 to update_task_stack

The function does not update sp0 anymore but updates makes the task-stack
visible for entry code. This is by either writing it to sp1 or by doing a
hypercall. Rename the function to get rid of the misleading name.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-15-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/switch_to.h | 2 +-
 arch/x86/kernel/process_32.c     | 2 +-
 arch/x86/kernel/process_64.c     | 2 +-
 arch/x86/kernel/vm86_32.c        | 4 ++--
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 8bc2f70b452e..36bd243843d6 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -87,7 +87,7 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
 #endif
 
 /* This is used when switching tasks or entering/exiting vm86 mode. */
-static inline void update_sp0(struct task_struct *task)
+static inline void update_task_stack(struct task_struct *task)
 {
 	/* sp0 always points to the entry trampoline stack, which is constant: */
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 0ae659de21eb..2924fd447e61 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -285,7 +285,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 * current_thread_info().  Refresh the SYSENTER configuration in
 	 * case prev or next is vm86.
 	 */
-	update_sp0(next_p);
+	update_task_stack(next_p);
 	refresh_sysenter_cs(next);
 	this_cpu_write(cpu_current_top_of_stack,
 		       (unsigned long)task_stack_page(next_p) +
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 12bb445fb98d..476e3ddf8890 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -478,7 +478,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	this_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
 
 	/* Reload sp0. */
-	update_sp0(next_p);
+	update_task_stack(next_p);
 
 	/*
 	 * Now maybe reload the debug registers and handle I/O bitmaps
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 9d0b5af7db91..1c03e4aa6474 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -149,7 +149,7 @@ void save_v86_state(struct kernel_vm86_regs *regs, int retval)
 	preempt_disable();
 	tsk->thread.sp0 = vm86->saved_sp0;
 	tsk->thread.sysenter_cs = __KERNEL_CS;
-	update_sp0(tsk);
+	update_task_stack(tsk);
 	refresh_sysenter_cs(&tsk->thread);
 	vm86->saved_sp0 = 0;
 	preempt_enable();
@@ -374,7 +374,7 @@ static long do_sys_vm86(struct vm86plus_struct __user *user_vm86, bool plus)
 		refresh_sysenter_cs(&tsk->thread);
 	}
 
-	update_sp0(tsk);
+	update_task_stack(tsk);
 	preempt_enable();
 
 	if (vm86->flags & VM86_SCREEN_BITMAP)
-- 
cgit v1.2.3


From 23b772883d1ddcf7fdf883614b88b2a6205db4da Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:52 +0200
Subject: x86/pgtable: Rename pti_set_user_pgd() to pti_set_user_pgtbl()

The way page-table folding is implemented on 32 bit, these functions are
not only setting, but also PUDs and even PMDs. Give the function a more
generic name to reflect that.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-16-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable_64.h | 12 ++++++------
 arch/x86/mm/pti.c                 |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 3c5385f9a88f..9406c4fe1d38 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -196,21 +196,21 @@ static inline bool pgdp_maps_userspace(void *__ptr)
 }
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd);
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
 
 /*
  * Take a PGD location (pgdp) and a pgd value that needs to be set there.
  * Populates the user and returns the resulting PGD that must be set in
  * the kernel copy of the page tables.
  */
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 {
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return pgd;
-	return __pti_set_user_pgd(pgdp, pgd);
+	return __pti_set_user_pgtbl(pgdp, pgd);
 }
 #else
-static inline pgd_t pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 {
 	return pgd;
 }
@@ -226,7 +226,7 @@ static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 	}
 
 	pgd = native_make_pgd(native_p4d_val(p4d));
-	pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd);
+	pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd);
 	*p4dp = native_make_p4d(native_pgd_val(pgd));
 }
 
@@ -237,7 +237,7 @@ static inline void native_p4d_clear(p4d_t *p4d)
 
 static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
 {
-	*pgdp = pti_set_user_pgd(pgdp, pgd);
+	*pgdp = pti_set_user_pgtbl(pgdp, pgd);
 }
 
 static inline void native_pgd_clear(pgd_t *pgd)
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 9277e9ba92b5..71fba17c9d7c 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -117,7 +117,7 @@ enable:
 	setup_force_cpu_cap(X86_FEATURE_PTI);
 }
 
-pgd_t __pti_set_user_pgd(pgd_t *pgdp, pgd_t pgd)
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
 {
 	/*
 	 * Changes to the high (kernel) portion of the kernelmode page
-- 
cgit v1.2.3


From 7ffcf1497c8ab59a705bfafb7401876fd2f6f71e Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:53 +0200
Subject: x86/pgtable/pae: Unshare kernel PMDs when PTI is enabled

With PTI the per-process LDT must be mapped into the kernel address-space
for each process, which requires separate kernel PMDs per PGD.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-17-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable-3level_types.h | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 6a59a6d0cc50..78038e057876 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -21,9 +21,10 @@ typedef union {
 #endif	/* !__ASSEMBLY__ */
 
 #ifdef CONFIG_PARAVIRT
-#define SHARED_KERNEL_PMD	(pv_info.shared_kernel_pmd)
+#define SHARED_KERNEL_PMD	((!static_cpu_has(X86_FEATURE_PTI) &&	\
+				 (pv_info.shared_kernel_pmd)))
 #else
-#define SHARED_KERNEL_PMD	1
+#define SHARED_KERNEL_PMD	(!static_cpu_has(X86_FEATURE_PTI))
 #endif
 
 /*
-- 
cgit v1.2.3


From e3238faf20fb1b51a814497751398ab525a2c884 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:54 +0200
Subject: x86/pgtable/32: Allocate 8k page-tables when PTI is enabled

Allocate a kernel and a user page-table root when PTI is enabled. Also
allocate a full page per root for PAE because otherwise the bit to flip in
CR3 to switch between them would be non-constant, which creates a lot of
hassle.  Keep that for a later optimization.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-18-git-send-email-joro@8bytes.org
---
 arch/x86/kernel/head_32.S | 20 +++++++++++++++-----
 arch/x86/mm/pgtable.c     |  5 +++--
 2 files changed, 18 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index abe6df15a8fb..30f9cb2c0b55 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -512,11 +512,18 @@ ENTRY(initial_code)
 ENTRY(setup_once_ref)
 	.long setup_once
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#define	PGD_ALIGN	(2 * PAGE_SIZE)
+#define PTI_USER_PGD_FILL	1024
+#else
+#define	PGD_ALIGN	(PAGE_SIZE)
+#define PTI_USER_PGD_FILL	0
+#endif
 /*
  * BSS section
  */
 __PAGE_ALIGNED_BSS
-	.align PAGE_SIZE
+	.align PGD_ALIGN
 #ifdef CONFIG_X86_PAE
 .globl initial_pg_pmd
 initial_pg_pmd:
@@ -526,14 +533,17 @@ initial_pg_pmd:
 initial_page_table:
 	.fill 1024,4,0
 #endif
+	.align PGD_ALIGN
 initial_pg_fixmap:
 	.fill 1024,4,0
-.globl empty_zero_page
-empty_zero_page:
-	.fill 4096,1,0
 .globl swapper_pg_dir
+	.align PGD_ALIGN
 swapper_pg_dir:
 	.fill 1024,4,0
+	.fill PTI_USER_PGD_FILL,4,0
+.globl empty_zero_page
+empty_zero_page:
+	.fill 4096,1,0
 EXPORT_SYMBOL(empty_zero_page)
 
 /*
@@ -542,7 +552,7 @@ EXPORT_SYMBOL(empty_zero_page)
 #ifdef CONFIG_X86_PAE
 __PAGE_ALIGNED_DATA
 	/* Page-aligned for the benefit of paravirt? */
-	.align PAGE_SIZE
+	.align PGD_ALIGN
 ENTRY(initial_page_table)
 	.long	pa(initial_pg_pmd+PGD_IDENT_ATTR),0	/* low identity map */
 # if KPMDS == 3
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 47b5951e592b..db6fb7740bf7 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -343,7 +343,8 @@ static inline pgd_t *_pgd_alloc(void)
 	 * We allocate one page for pgd.
 	 */
 	if (!SHARED_KERNEL_PMD)
-		return (pgd_t *)__get_free_page(PGALLOC_GFP);
+		return (pgd_t *)__get_free_pages(PGALLOC_GFP,
+						 PGD_ALLOCATION_ORDER);
 
 	/*
 	 * Now PAE kernel is not running as a Xen domain. We can allocate
@@ -355,7 +356,7 @@ static inline pgd_t *_pgd_alloc(void)
 static inline void _pgd_free(pgd_t *pgd)
 {
 	if (!SHARED_KERNEL_PMD)
-		free_page((unsigned long)pgd);
+		free_pages((unsigned long)pgd, PGD_ALLOCATION_ORDER);
 	else
 		kmem_cache_free(pgd_cache, pgd);
 }
-- 
cgit v1.2.3


From 8372d66865deb45ee3ec21401a9c80f231b728c8 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:55 +0200
Subject: x86/pgtable: Move pgdp kernel/user conversion functions to pgtable.h

Make them available on 32 bit and clone_pgd_range() happy.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-19-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable.h    | 49 +++++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/pgtable_64.h | 49 ---------------------------------------
 2 files changed, 49 insertions(+), 49 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 5715647fc4fe..eb474329d751 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1155,6 +1155,55 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 }
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+/*
+ * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
+ * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
+ * the user one is in the last 4k.  To switch between them, you
+ * just need to flip the 12th bit in their addresses.
+ */
+#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
+
+/*
+ * This generates better code than the inline assembly in
+ * __set_bit().
+ */
+static inline void *ptr_set_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr |= BIT(bit);
+	return (void *)__ptr;
+}
+static inline void *ptr_clear_bit(void *ptr, int bit)
+{
+	unsigned long __ptr = (unsigned long)ptr;
+
+	__ptr &= ~BIT(bit);
+	return (void *)__ptr;
+}
+
+static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
+{
+	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
+{
+	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
+{
+	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+
+static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
+{
+	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
 /*
  * clone_pgd_range(pgd_t *dst, pgd_t *src, int count);
  *
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 9406c4fe1d38..4adba19c7bf6 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -132,55 +132,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-/*
- * All top-level PAGE_TABLE_ISOLATION page tables are order-1 pages
- * (8k-aligned and 8k in size).  The kernel one is at the beginning 4k and
- * the user one is in the last 4k.  To switch between them, you
- * just need to flip the 12th bit in their addresses.
- */
-#define PTI_PGTABLE_SWITCH_BIT	PAGE_SHIFT
-
-/*
- * This generates better code than the inline assembly in
- * __set_bit().
- */
-static inline void *ptr_set_bit(void *ptr, int bit)
-{
-	unsigned long __ptr = (unsigned long)ptr;
-
-	__ptr |= BIT(bit);
-	return (void *)__ptr;
-}
-static inline void *ptr_clear_bit(void *ptr, int bit)
-{
-	unsigned long __ptr = (unsigned long)ptr;
-
-	__ptr &= ~BIT(bit);
-	return (void *)__ptr;
-}
-
-static inline pgd_t *kernel_to_user_pgdp(pgd_t *pgdp)
-{
-	return ptr_set_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline pgd_t *user_to_kernel_pgdp(pgd_t *pgdp)
-{
-	return ptr_clear_bit(pgdp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *kernel_to_user_p4dp(p4d_t *p4dp)
-{
-	return ptr_set_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-
-static inline p4d_t *user_to_kernel_p4dp(p4d_t *p4dp)
-{
-	return ptr_clear_bit(p4dp, PTI_PGTABLE_SWITCH_BIT);
-}
-#endif /* CONFIG_PAGE_TABLE_ISOLATION */
-
 /*
  * Page table pages are page-aligned.  The lower half of the top
  * level is used for userspace and the top half for the kernel.
-- 
cgit v1.2.3


From fcbbd977572cfe5a3dcc97d663bf7480431a07ca Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:56 +0200
Subject: x86/pgtable: Move pti_set_user_pgtbl() to pgtable.h

There it is also usable from 32 bit code.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-20-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable.h | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index eb474329d751..cc117161f13d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -640,8 +640,31 @@ static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
 
 pmd_t *populate_extra_pmd(unsigned long vaddr);
 pte_t *populate_extra_pte(unsigned long vaddr);
+
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
+
+/*
+ * Take a PGD location (pgdp) and a pgd value that needs to be set there.
+ * Populates the user and returns the resulting PGD that must be set in
+ * the kernel copy of the page tables.
+ */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return pgd;
+	return __pti_set_user_pgtbl(pgdp, pgd);
+}
+#else   /* CONFIG_PAGE_TABLE_ISOLATION */
+static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+	return pgd;
+}
+#endif  /* CONFIG_PAGE_TABLE_ISOLATION */
+
 #endif	/* __ASSEMBLY__ */
 
+
 #ifdef CONFIG_X86_32
 # include <asm/pgtable_32.h>
 #else
-- 
cgit v1.2.3


From 76e258add7b653b60037ee4b25ebc40da6a35c4a Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:57 +0200
Subject: x86/pgtable: Move two more functions from pgtable_64.h to pgtable.h

These two functions are required for PTI on 32 bit:

	* pgdp_maps_userspace()
	* pgd_large()

Also re-implement pgdp_maps_userspace() so that it will work on 64 and 32
bit kernels.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-21-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable-2level_types.h |  3 +++
 arch/x86/include/asm/pgtable-3level_types.h |  1 +
 arch/x86/include/asm/pgtable.h              | 15 ++++++++++++
 arch/x86/include/asm/pgtable_32.h           |  2 --
 arch/x86/include/asm/pgtable_64.h           | 36 -----------------------------
 arch/x86/include/asm/pgtable_64_types.h     |  2 ++
 6 files changed, 21 insertions(+), 38 deletions(-)

diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index f982ef808e7e..6deb6cd236e3 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -35,4 +35,7 @@ typedef union {
 
 #define PTRS_PER_PTE	1024
 
+/* This covers all VMSPLIT_* and VMSPLIT_*_OPT variants */
+#define PGD_KERNEL_START	(CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
+
 #endif /* _ASM_X86_PGTABLE_2LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 78038e057876..858358a82b14 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -46,5 +46,6 @@ typedef union {
 #define PTRS_PER_PTE	512
 
 #define MAX_POSSIBLE_PHYSMEM_BITS	36
+#define PGD_KERNEL_START	(CONFIG_PAGE_OFFSET >> PGDIR_SHIFT)
 
 #endif /* _ASM_X86_PGTABLE_3LEVEL_DEFS_H */
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index cc117161f13d..e39088cb59ab 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -1177,6 +1177,21 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
 	}
 }
 #endif
+/*
+ * Page table pages are page-aligned.  The lower half of the top
+ * level is used for userspace and the top half for the kernel.
+ *
+ * Returns true for parts of the PGD that map userspace and
+ * false for the parts that map the kernel.
+ */
+static inline bool pgdp_maps_userspace(void *__ptr)
+{
+	unsigned long ptr = (unsigned long)__ptr;
+
+	return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
+}
+
+static inline int pgd_large(pgd_t pgd) { return 0; }
 
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 /*
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 88a056b01db4..b3ec519e3982 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -34,8 +34,6 @@ static inline void check_pgt_cache(void) { }
 void paging_init(void);
 void sync_initial_page_table(void);
 
-static inline int pgd_large(pgd_t pgd) { return 0; }
-
 /*
  * Define this if things work differently on an i386 and an i486:
  * it will (on an i486) warn about kernel memory accesses that are
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 4adba19c7bf6..acb6970e7bcf 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -132,41 +132,6 @@ static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 #endif
 }
 
-/*
- * Page table pages are page-aligned.  The lower half of the top
- * level is used for userspace and the top half for the kernel.
- *
- * Returns true for parts of the PGD that map userspace and
- * false for the parts that map the kernel.
- */
-static inline bool pgdp_maps_userspace(void *__ptr)
-{
-	unsigned long ptr = (unsigned long)__ptr;
-
-	return (ptr & ~PAGE_MASK) < (PAGE_SIZE / 2);
-}
-
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd);
-
-/*
- * Take a PGD location (pgdp) and a pgd value that needs to be set there.
- * Populates the user and returns the resulting PGD that must be set in
- * the kernel copy of the page tables.
- */
-static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
-{
-	if (!static_cpu_has(X86_FEATURE_PTI))
-		return pgd;
-	return __pti_set_user_pgtbl(pgdp, pgd);
-}
-#else
-static inline pgd_t pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
-{
-	return pgd;
-}
-#endif
-
 static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
 {
 	pgd_t pgd;
@@ -206,7 +171,6 @@ extern void sync_global_pgds(unsigned long start, unsigned long end);
 /*
  * Level 4 access.
  */
-static inline int pgd_large(pgd_t pgd) { return 0; }
 #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE)
 
 /* PUD - Level3 access */
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 054765ab2da2..066e0ab9ffab 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -153,4 +153,6 @@ extern unsigned int ptrs_per_p4d;
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 
+#define PGD_KERNEL_START	((PAGE_SIZE / 2) / sizeof(pgd_t))
+
 #endif /* _ASM_X86_PGTABLE_64_DEFS_H */
-- 
cgit v1.2.3


From 6c0df8689494e1fefa685377676fa8192291a0eb Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:58 +0200
Subject: x86/mm/pae: Populate valid user PGD entries

Generic page-table code populates all non-leaf entries with _KERNPG_TABLE
bits set. This is fine for all paging modes except PAE.

In PAE mode only a subset of the bits is allowed to be set.  Make sure to
only set allowed bits by masking out the reserved bits.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-22-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable_types.h | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 99fff853c944..b64acb08a62b 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -50,6 +50,7 @@
 #define _PAGE_GLOBAL	(_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL)
 #define _PAGE_SOFTW1	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1)
 #define _PAGE_SOFTW2	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW2)
+#define _PAGE_SOFTW3	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW3)
 #define _PAGE_PAT	(_AT(pteval_t, 1) << _PAGE_BIT_PAT)
 #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE)
 #define _PAGE_SPECIAL	(_AT(pteval_t, 1) << _PAGE_BIT_SPECIAL)
@@ -266,14 +267,37 @@ typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
 
 typedef struct { pgdval_t pgd; } pgd_t;
 
+#ifdef CONFIG_X86_PAE
+
+/*
+ * PHYSICAL_PAGE_MASK might be non-constant when SME is compiled in, so we can't
+ * use it here.
+ */
+
+#define PGD_PAE_PAGE_MASK	((signed long)PAGE_MASK)
+#define PGD_PAE_PHYS_MASK	(((1ULL << __PHYSICAL_MASK_SHIFT)-1) & PGD_PAE_PAGE_MASK)
+
+/*
+ * PAE allows Base Address, P, PWT, PCD and AVL bits to be set in PGD entries.
+ * All other bits are Reserved MBZ
+ */
+#define PGD_ALLOWED_BITS	(PGD_PAE_PHYS_MASK | _PAGE_PRESENT | \
+				 _PAGE_PWT | _PAGE_PCD | \
+				 _PAGE_SOFTW1 | _PAGE_SOFTW2 | _PAGE_SOFTW3)
+
+#else
+/* No need to mask any bits for !PAE */
+#define PGD_ALLOWED_BITS	(~0ULL)
+#endif
+
 static inline pgd_t native_make_pgd(pgdval_t val)
 {
-	return (pgd_t) { val };
+	return (pgd_t) { val & PGD_ALLOWED_BITS };
 }
 
 static inline pgdval_t native_pgd_val(pgd_t pgd)
 {
-	return pgd.pgd;
+	return pgd.pgd & PGD_ALLOWED_BITS;
 }
 
 static inline pgdval_t pgd_flags(pgd_t pgd)
-- 
cgit v1.2.3


From 9b7b8bbd7f6ba4ef7caa5a078ead70237e12d045 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:40:59 +0200
Subject: x86/mm/pae: Populate the user page-table with user pgd's

When a PGD entry is populated, make sure to populate it in the user
page-table too.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-23-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable-3level.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index f24df59c40b2..f2ca3139ca22 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -98,6 +98,9 @@ static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 
 static inline void native_set_pud(pud_t *pudp, pud_t pud)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pud.p4d.pgd = pti_set_user_pgtbl(&pudp->p4d.pgd, pud.p4d.pgd);
+#endif
 	set_64bit((unsigned long long *)(pudp), native_pud_val(pud));
 }
 
@@ -229,6 +232,10 @@ static inline pud_t native_pudp_get_and_clear(pud_t *pudp)
 {
 	union split_pud res, *orig = (union split_pud *)pudp;
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&pudp->p4d.pgd, __pgd(0));
+#endif
+
 	/* xchg acts as a barrier before setting of the high bits */
 	res.pud_low = xchg(&orig->pud_low, 0);
 	res.pud_high = orig->pud_high;
-- 
cgit v1.2.3


From 1f40a46cf47c12d93a5ad9dccd82bd36ff8f956a Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:00 +0200
Subject: x86/mm/legacy: Populate the user page-table with user pgd's

Also populate the user-spage pgd's in the user page-table.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-24-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable-2level.h | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index 685ffe8a0eaf..c399ea5eea41 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -19,6 +19,9 @@ static inline void native_set_pte(pte_t *ptep , pte_t pte)
 
 static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pmd.pud.p4d.pgd = pti_set_user_pgtbl(&pmdp->pud.p4d.pgd, pmd.pud.p4d.pgd);
+#endif
 	*pmdp = pmd;
 }
 
@@ -58,6 +61,9 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #ifdef CONFIG_SMP
 static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&xp->pud.p4d.pgd, __pgd(0));
+#endif
 	return __pmd(xchg((pmdval_t *)xp, 0));
 }
 #else
@@ -67,6 +73,9 @@ static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp)
 #ifdef CONFIG_SMP
 static inline pud_t native_pudp_get_and_clear(pud_t *xp)
 {
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+	pti_set_user_pgtbl(&xp->p4d.pgd, __pgd(0));
+#endif
 	return __pud(xchg((pudval_t *)xp, 0));
 }
 #else
-- 
cgit v1.2.3


From 935232ce28dfabff1171e5a7113b2d865fa9ee63 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:01 +0200
Subject: x86/mm/pti: Add an overflow check to pti_clone_pmds()

The addr counter will overflow if the last PMD of the address space is
cloned, resulting in an endless loop.

Check for that and bail out of the loop when it happens.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-25-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 71fba17c9d7c..79217868dd13 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -297,6 +297,10 @@ pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
 		p4d_t *p4d;
 		pud_t *pud;
 
+		/* Overflow check */
+		if (addr < start)
+			break;
+
 		pgd = pgd_offset_k(addr);
 		if (WARN_ON(pgd_none(*pgd)))
 			return;
-- 
cgit v1.2.3


From 2c1b9fbe83412598d2dccdd448147336b085e0c6 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:02 +0200
Subject: x86/mm/pti: Define X86_CR3_PTI_PCID_USER_BIT on x86_32

Move it out of the X86_64 specific processor defines so that its visible
for 32bit too.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-26-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/processor-flags.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/processor-flags.h b/arch/x86/include/asm/processor-flags.h
index 625a52a5594f..02c2cbda4a74 100644
--- a/arch/x86/include/asm/processor-flags.h
+++ b/arch/x86/include/asm/processor-flags.h
@@ -39,10 +39,6 @@
 #define CR3_PCID_MASK	0xFFFull
 #define CR3_NOFLUSH	BIT_ULL(63)
 
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-# define X86_CR3_PTI_PCID_USER_BIT	11
-#endif
-
 #else
 /*
  * CR3_ADDR_MASK needs at least bits 31:5 set on PAE systems, and we save
@@ -53,4 +49,8 @@
 #define CR3_NOFLUSH	0
 #endif
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+# define X86_CR3_PTI_PCID_USER_BIT	11
+#endif
+
 #endif /* _ASM_X86_PROCESSOR_FLAGS_H */
-- 
cgit v1.2.3


From f94560cd6b5117f8913f4c42f4d9a405c26ddc1c Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:03 +0200
Subject: x86/mm/pti: Clone CPU_ENTRY_AREA on PMD level on x86_32

Cloning on the P4D level would clone the complete kernel address space into
the user-space page-tables for PAE kernels. Cloning on PMD level is fine
for PAE and legacy paging.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-27-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 79217868dd13..a594e3b6401a 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -348,6 +348,7 @@ pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
 	}
 }
 
+#ifdef CONFIG_X86_64
 /*
  * Clone a single p4d (i.e. a top-level entry on 4-level systems and a
  * next-level entry on 5-level systems.
@@ -371,6 +372,25 @@ static void __init pti_clone_user_shared(void)
 	pti_clone_p4d(CPU_ENTRY_AREA_BASE);
 }
 
+#else /* CONFIG_X86_64 */
+
+/*
+ * On 32 bit PAE systems with 1GB of Kernel address space there is only
+ * one pgd/p4d for the whole kernel. Cloning that would map the whole
+ * address space into the user page-tables, making PTI useless. So clone
+ * the page-table on the PMD level to prevent that.
+ */
+static void __init pti_clone_user_shared(void)
+{
+	unsigned long start, end;
+
+	start = CPU_ENTRY_AREA_BASE;
+	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
+
+	pti_clone_pmds(start, end, 0);
+}
+#endif /* CONFIG_X86_64 */
+
 /*
  * Clone the ESPFIX P4D into the user space visible page table
  */
-- 
cgit v1.2.3


From 39d668e04edad25abe184fb329ce35a131146ee5 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:04 +0200
Subject: x86/mm/pti: Make pti_clone_kernel_text() compile on 32 bit

The pti_clone_kernel_text() function references __end_rodata_hpage_align,
which is only present on x86-64.  This makes sense as the end of the rodata
section is not huge-page aligned on 32 bit.

Nevertheless a symbol is required for the function that points at the right
address for both 32 and 64 bit. Introduce __end_rodata_aligned for that
purpose and use it in pti_clone_kernel_text().

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-28-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/sections.h |  1 +
 arch/x86/kernel/vmlinux.lds.S   | 17 ++++++++++-------
 arch/x86/mm/pti.c               |  2 +-
 3 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
index 5c019d23d06b..4a911a382ade 100644
--- a/arch/x86/include/asm/sections.h
+++ b/arch/x86/include/asm/sections.h
@@ -7,6 +7,7 @@
 
 extern char __brk_base[], __brk_limit[];
 extern struct exception_table_entry __stop___ex_table[];
+extern char __end_rodata_aligned[];
 
 #if defined(CONFIG_X86_64)
 extern char __end_rodata_hpage_align[];
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 5e1458f609a1..8bde0a419f86 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -55,19 +55,22 @@ jiffies_64 = jiffies;
  * so we can enable protection checks as well as retain 2MB large page
  * mappings for kernel text.
  */
-#define X64_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
+#define X86_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
 
-#define X64_ALIGN_RODATA_END					\
+#define X86_ALIGN_RODATA_END					\
 		. = ALIGN(HPAGE_SIZE);				\
-		__end_rodata_hpage_align = .;
+		__end_rodata_hpage_align = .;			\
+		__end_rodata_aligned = .;
 
 #define ALIGN_ENTRY_TEXT_BEGIN	. = ALIGN(PMD_SIZE);
 #define ALIGN_ENTRY_TEXT_END	. = ALIGN(PMD_SIZE);
 
 #else
 
-#define X64_ALIGN_RODATA_BEGIN
-#define X64_ALIGN_RODATA_END
+#define X86_ALIGN_RODATA_BEGIN
+#define X86_ALIGN_RODATA_END					\
+		. = ALIGN(PAGE_SIZE);				\
+		__end_rodata_aligned = .;
 
 #define ALIGN_ENTRY_TEXT_BEGIN
 #define ALIGN_ENTRY_TEXT_END
@@ -141,9 +144,9 @@ SECTIONS
 
 	/* .text should occupy whole number of pages */
 	. = ALIGN(PAGE_SIZE);
-	X64_ALIGN_RODATA_BEGIN
+	X86_ALIGN_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
-	X64_ALIGN_RODATA_END
+	X86_ALIGN_RODATA_END
 
 	/* Data */
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index a594e3b6401a..453d23760941 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -470,7 +470,7 @@ void pti_clone_kernel_text(void)
 	 * clone the areas past rodata, they might contain secrets.
 	 */
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = (unsigned long)__end_rodata_hpage_align;
+	unsigned long end = (unsigned long)__end_rodata_aligned;
 
 	if (!pti_kernel_image_global_ok())
 		return;
-- 
cgit v1.2.3


From 1ac228a7c87f697d1d01eb6362a6b5246705b0dd Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:05 +0200
Subject: x86/mm/pti: Keep permissions when cloning kernel text in
 pti_clone_kernel_text()

Mapping the kernel text area to user-space makes only sense if it has the
same permissions as in the kernel page-table.  If permissions are different
this will cause a TLB reload when using the kernel page-table, which is as
good as not mapping it at all.

On 64-bit kernels this patch makes no difference, as the whole range cloned
by pti_clone_kernel_text() is mapped RO anyway. On 32 bit there are
writeable mappings in the range, so just keep the permissions as they are.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-29-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 453d23760941..e41ee93c430d 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -482,7 +482,7 @@ void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end, _PAGE_RW);
+	pti_clone_pmds(start, end, 0);
 }
 
 /*
-- 
cgit v1.2.3


From b976690f5db26fbc7c2be413bfa0fbd270547a94 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:06 +0200
Subject: x86/mm/pti: Introduce pti_finalize()

Introduce a new function to finalize the kernel mappings for the userspace
page-table after all ro/nx protections have been applied to the kernel
mappings.

Also move the call to pti_clone_kernel_text() to that function so that it
will run on 32 bit kernels too.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-30-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pti.h |  3 +--
 arch/x86/mm/init_64.c      |  6 ------
 arch/x86/mm/pti.c          | 14 +++++++++++++-
 include/linux/pti.h        |  1 +
 init/main.c                |  7 +++++++
 5 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/pti.h b/arch/x86/include/asm/pti.h
index 38a17f1d5c9d..5df09a0b80b8 100644
--- a/arch/x86/include/asm/pti.h
+++ b/arch/x86/include/asm/pti.h
@@ -6,10 +6,9 @@
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 extern void pti_init(void);
 extern void pti_check_boottime_disable(void);
-extern void pti_clone_kernel_text(void);
+extern void pti_finalize(void);
 #else
 static inline void pti_check_boottime_disable(void) { }
-static inline void pti_clone_kernel_text(void) { }
 #endif
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a688617c727e..9b19f9a8948e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1291,12 +1291,6 @@ void mark_rodata_ro(void)
 			(unsigned long) __va(__pa_symbol(_sdata)));
 
 	debug_checkwx();
-
-	/*
-	 * Do this after all of the manipulation of the
-	 * kernel text page tables are complete.
-	 */
-	pti_clone_kernel_text();
 }
 
 int kern_addr_valid(unsigned long addr)
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index e41ee93c430d..fcfb815d420f 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -462,7 +462,7 @@ static inline bool pti_kernel_image_global_ok(void)
  * For some configurations, map all of kernel text into the user page
  * tables.  This reduces TLB misses, especially on non-PCID systems.
  */
-void pti_clone_kernel_text(void)
+static void pti_clone_kernel_text(void)
 {
 	/*
 	 * rodata is part of the kernel image and is normally
@@ -526,3 +526,15 @@ void __init pti_init(void)
 	pti_setup_espfix64();
 	pti_setup_vsyscall();
 }
+
+/*
+ * Finalize the kernel mappings in the userspace page-table.
+ */
+void pti_finalize(void)
+{
+	/*
+	 * Do this after all of the manipulation of the
+	 * kernel text page tables are complete.
+	 */
+	pti_clone_kernel_text();
+}
diff --git a/include/linux/pti.h b/include/linux/pti.h
index 0174883a935a..1a941efcaa62 100644
--- a/include/linux/pti.h
+++ b/include/linux/pti.h
@@ -6,6 +6,7 @@
 #include <asm/pti.h>
 #else
 static inline void pti_init(void) { }
+static inline void pti_finalize(void) { }
 #endif
 
 #endif
diff --git a/init/main.c b/init/main.c
index 3b4ada11ed52..fcfef46c935a 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1065,6 +1065,13 @@ static int __ref kernel_init(void *unused)
 	jump_label_invalidate_initmem();
 	free_initmem();
 	mark_readonly();
+
+	/*
+	 * Kernel mappings are now finalized - update the userspace page-table
+	 * to finalize PTI.
+	 */
+	pti_finalize();
+
 	system_state = SYSTEM_RUNNING;
 	numa_default_policy();
 
-- 
cgit v1.2.3


From ba0364e260ab37c02975557dbecc014a26072236 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:07 +0200
Subject: x86/mm/pti: Clone entry-text again in pti_finalize()

The mapping for entry-text might have changed in the kernel after it was
cloned to the user page-table. Clone again to update the user page-table to
bring the mapping in sync with the kernel again.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-31-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index fcfb815d420f..a536ecc91847 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -404,7 +404,7 @@ static void __init pti_setup_espfix64(void)
 /*
  * Clone the populated PMDs of the entry and irqentry text and force it RO.
  */
-static void __init pti_clone_entry_text(void)
+static void pti_clone_entry_text(void)
 {
 	pti_clone_pmds((unsigned long) __entry_text_start,
 			(unsigned long) __irqentry_text_end,
@@ -528,13 +528,18 @@ void __init pti_init(void)
 }
 
 /*
- * Finalize the kernel mappings in the userspace page-table.
+ * Finalize the kernel mappings in the userspace page-table. Some of the
+ * mappings for the kernel image might have changed since pti_init()
+ * cloned them. This is because parts of the kernel image have been
+ * mapped RO and/or NX.  These changes need to be cloned again to the
+ * userspace page-table.
  */
 void pti_finalize(void)
 {
 	/*
-	 * Do this after all of the manipulation of the
-	 * kernel text page tables are complete.
+	 * We need to clone everything (again) that maps parts of the
+	 * kernel image.
 	 */
+	pti_clone_entry_text();
 	pti_clone_kernel_text();
 }
-- 
cgit v1.2.3


From 4e8537e4a7a15402b87c424b22c25c9e59681d16 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:08 +0200
Subject: x86/mm/dump_pagetables: Define INIT_PGD

Define INIT_PGD to point to the correct initial page-table for 32 and 64
bit and use it where needed. This fixes the build on 32 bit with
CONFIG_PAGE_TABLE_ISOLATION enabled.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-32-git-send-email-joro@8bytes.org
---
 arch/x86/mm/dump_pagetables.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 2f3c9196b834..e6fd0cdef9ad 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -111,6 +111,8 @@ static struct addr_marker address_markers[] = {
 	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#define INIT_PGD	((pgd_t *) &init_top_pgt)
+
 #else /* CONFIG_X86_64 */
 
 enum address_markers_idx {
@@ -139,6 +141,8 @@ static struct addr_marker address_markers[] = {
 	[END_OF_SPACE_NR]	= { -1,			NULL }
 };
 
+#define INIT_PGD	(swapper_pg_dir)
+
 #endif /* !CONFIG_X86_64 */
 
 /* Multipliers for offsets within the PTEs */
@@ -496,11 +500,7 @@ static inline bool is_hypervisor_range(int idx)
 static void ptdump_walk_pgd_level_core(struct seq_file *m, pgd_t *pgd,
 				       bool checkwx, bool dmesg)
 {
-#ifdef CONFIG_X86_64
-	pgd_t *start = (pgd_t *) &init_top_pgt;
-#else
-	pgd_t *start = swapper_pg_dir;
-#endif
+	pgd_t *start = INIT_PGD;
 	pgprotval_t prot, eff;
 	int i;
 	struct pg_state st = {};
@@ -566,7 +566,7 @@ EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
 static void ptdump_walk_user_pgd_level_checkwx(void)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-	pgd_t *pgd = (pgd_t *) &init_top_pgt;
+	pgd_t *pgd = INIT_PGD;
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return;
-- 
cgit v1.2.3


From f59dbe9ca6707eb7ffd0e24359085651c2d7df48 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:09 +0200
Subject: x86/pgtable/pae: Use separate kernel PMDs for user page-table

When PTI is enabled, separate kernel PMDs in the user page-table are
required to map the per-process LDT for user-space.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-33-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pgtable.c | 100 ++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 81 insertions(+), 19 deletions(-)

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index db6fb7740bf7..8e4e63d46d81 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -182,6 +182,14 @@ static void pgd_dtor(pgd_t *pgd)
  */
 #define PREALLOCATED_PMDS	UNSHARED_PTRS_PER_PGD
 
+/*
+ * We allocate separate PMDs for the kernel part of the user page-table
+ * when PTI is enabled. We need them to map the per-process LDT into the
+ * user-space page-table.
+ */
+#define PREALLOCATED_USER_PMDS	 (static_cpu_has(X86_FEATURE_PTI) ? \
+					KERNEL_PGD_PTRS : 0)
+
 void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 {
 	paravirt_alloc_pmd(mm, __pa(pmd) >> PAGE_SHIFT);
@@ -202,14 +210,14 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
 
 /* No need to prepopulate any pagetable entries in non-PAE modes. */
 #define PREALLOCATED_PMDS	0
-
+#define PREALLOCATED_USER_PMDS	 0
 #endif	/* CONFIG_X86_PAE */
 
-static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static void free_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 {
 	int i;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++)
+	for (i = 0; i < count; i++)
 		if (pmds[i]) {
 			pgtable_pmd_page_dtor(virt_to_page(pmds[i]));
 			free_page((unsigned long)pmds[i]);
@@ -217,7 +225,7 @@ static void free_pmds(struct mm_struct *mm, pmd_t *pmds[])
 		}
 }
 
-static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
+static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
 {
 	int i;
 	bool failed = false;
@@ -226,7 +234,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 	if (mm == &init_mm)
 		gfp &= ~__GFP_ACCOUNT;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++) {
+	for (i = 0; i < count; i++) {
 		pmd_t *pmd = (pmd_t *)__get_free_page(gfp);
 		if (!pmd)
 			failed = true;
@@ -241,7 +249,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
 	}
 
 	if (failed) {
-		free_pmds(mm, pmds);
+		free_pmds(mm, pmds, count);
 		return -ENOMEM;
 	}
 
@@ -254,23 +262,38 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[])
  * preallocate which never got a corresponding vma will need to be
  * freed manually.
  */
+static void mop_up_one_pmd(struct mm_struct *mm, pgd_t *pgdp)
+{
+	pgd_t pgd = *pgdp;
+
+	if (pgd_val(pgd) != 0) {
+		pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+
+		*pgdp = native_make_pgd(0);
+
+		paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
+		pmd_free(mm, pmd);
+		mm_dec_nr_pmds(mm);
+	}
+}
+
 static void pgd_mop_up_pmds(struct mm_struct *mm, pgd_t *pgdp)
 {
 	int i;
 
-	for(i = 0; i < PREALLOCATED_PMDS; i++) {
-		pgd_t pgd = pgdp[i];
+	for (i = 0; i < PREALLOCATED_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i]);
 
-		if (pgd_val(pgd) != 0) {
-			pmd_t *pmd = (pmd_t *)pgd_page_vaddr(pgd);
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
 
-			pgdp[i] = native_make_pgd(0);
+	if (!static_cpu_has(X86_FEATURE_PTI))
+		return;
 
-			paravirt_release_pmd(pgd_val(pgd) >> PAGE_SHIFT);
-			pmd_free(mm, pmd);
-			mm_dec_nr_pmds(mm);
-		}
-	}
+	pgdp = kernel_to_user_pgdp(pgdp);
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++)
+		mop_up_one_pmd(mm, &pgdp[i + KERNEL_PGD_BOUNDARY]);
+#endif
 }
 
 static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
@@ -296,6 +319,38 @@ static void pgd_prepopulate_pmd(struct mm_struct *mm, pgd_t *pgd, pmd_t *pmds[])
 	}
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+	pgd_t *s_pgd = kernel_to_user_pgdp(swapper_pg_dir);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	p4d_t *u_p4d;
+	pud_t *u_pud;
+	int i;
+
+	u_p4d = p4d_offset(u_pgd, 0);
+	u_pud = pud_offset(u_p4d, 0);
+
+	s_pgd += KERNEL_PGD_BOUNDARY;
+	u_pud += KERNEL_PGD_BOUNDARY;
+
+	for (i = 0; i < PREALLOCATED_USER_PMDS; i++, u_pud++, s_pgd++) {
+		pmd_t *pmd = pmds[i];
+
+		memcpy(pmd, (pmd_t *)pgd_page_vaddr(*s_pgd),
+		       sizeof(pmd_t) * PTRS_PER_PMD);
+
+		pud_populate(mm, u_pud, pmd);
+	}
+
+}
+#else
+static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
+				     pgd_t *k_pgd, pmd_t *pmds[])
+{
+}
+#endif
 /*
  * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
  * assumes that pgd should be in one page.
@@ -376,6 +431,7 @@ static inline void _pgd_free(pgd_t *pgd)
 pgd_t *pgd_alloc(struct mm_struct *mm)
 {
 	pgd_t *pgd;
+	pmd_t *u_pmds[PREALLOCATED_USER_PMDS];
 	pmd_t *pmds[PREALLOCATED_PMDS];
 
 	pgd = _pgd_alloc();
@@ -385,12 +441,15 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	mm->pgd = pgd;
 
-	if (preallocate_pmds(mm, pmds) != 0)
+	if (preallocate_pmds(mm, pmds, PREALLOCATED_PMDS) != 0)
 		goto out_free_pgd;
 
-	if (paravirt_pgd_alloc(mm) != 0)
+	if (preallocate_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS) != 0)
 		goto out_free_pmds;
 
+	if (paravirt_pgd_alloc(mm) != 0)
+		goto out_free_user_pmds;
+
 	/*
 	 * Make sure that pre-populating the pmds is atomic with
 	 * respect to anything walking the pgd_list, so that they
@@ -400,13 +459,16 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 
 	pgd_ctor(mm, pgd);
 	pgd_prepopulate_pmd(mm, pgd, pmds);
+	pgd_prepopulate_user_pmd(mm, pgd, u_pmds);
 
 	spin_unlock(&pgd_lock);
 
 	return pgd;
 
+out_free_user_pmds:
+	free_pmds(mm, u_pmds, PREALLOCATED_USER_PMDS);
 out_free_pmds:
-	free_pmds(mm, pmds);
+	free_pmds(mm, pmds, PREALLOCATED_PMDS);
 out_free_pgd:
 	_pgd_free(pgd);
 out:
-- 
cgit v1.2.3


From f3e48e546c42e31c0c095a6f917a4ad64668608c Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:10 +0200
Subject: x86/ldt: Reserve address-space range on 32 bit for the LDT

Reserve 2MB/4MB of address-space for mapping the LDT to user-space on 32
bit PTI kernels.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-34-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable_32_types.h | 7 +++++--
 arch/x86/mm/dump_pagetables.c           | 9 +++++++++
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index d9a001a4a872..7297810747cf 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -50,13 +50,16 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 	((FIXADDR_TOT_START - PAGE_SIZE * (CPU_ENTRY_AREA_PAGES + 1))   \
 	 & PMD_MASK)
 
-#define PKMAP_BASE		\
+#define LDT_BASE_ADDR		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
+#define PKMAP_BASE		\
+	((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK)
+
 #ifdef CONFIG_HIGHMEM
 # define VMALLOC_END	(PKMAP_BASE - 2 * PAGE_SIZE)
 #else
-# define VMALLOC_END	(CPU_ENTRY_AREA_BASE - 2 * PAGE_SIZE)
+# define VMALLOC_END	(LDT_BASE_ADDR - 2 * PAGE_SIZE)
 #endif
 
 #define MODULES_VADDR	VMALLOC_START
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index e6fd0cdef9ad..ccd92c4da57c 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -122,6 +122,9 @@ enum address_markers_idx {
 	VMALLOC_END_NR,
 #ifdef CONFIG_HIGHMEM
 	PKMAP_BASE_NR,
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	LDT_NR,
 #endif
 	CPU_ENTRY_AREA_NR,
 	FIXADDR_START_NR,
@@ -135,6 +138,9 @@ static struct addr_marker address_markers[] = {
 	[VMALLOC_END_NR]	= { 0UL,		"vmalloc() End" },
 #ifdef CONFIG_HIGHMEM
 	[PKMAP_BASE_NR]		= { 0UL,		"Persistent kmap() Area" },
+#endif
+#ifdef CONFIG_MODIFY_LDT_SYSCALL
+	[LDT_NR]		= { 0UL,		"LDT remap" },
 #endif
 	[CPU_ENTRY_AREA_NR]	= { 0UL,		"CPU entry area" },
 	[FIXADDR_START_NR]	= { 0UL,		"Fixmap area" },
@@ -609,6 +615,9 @@ static int __init pt_dump_init(void)
 # endif
 	address_markers[FIXADDR_START_NR].start_address = FIXADDR_START;
 	address_markers[CPU_ENTRY_AREA_NR].start_address = CPU_ENTRY_AREA_BASE;
+# ifdef CONFIG_MODIFY_LDT_SYSCALL
+	address_markers[LDT_NR].start_address = LDT_BASE_ADDR;
+# endif
 #endif
 	return 0;
 }
-- 
cgit v1.2.3


From 8195d869d118bc30bf0be8d0c5d8849d6f58529b Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:11 +0200
Subject: x86/ldt: Define LDT_END_ADDR

It marks the end of the address-space range reserved for the LDT. The
LDT-code will use it when unmapping the LDT for user-space.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-35-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable_32_types.h | 2 ++
 arch/x86/include/asm/pgtable_64_types.h | 1 +
 arch/x86/kernel/ldt.c                   | 2 +-
 3 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/pgtable_32_types.h b/arch/x86/include/asm/pgtable_32_types.h
index 7297810747cf..b0bc0fff5f1f 100644
--- a/arch/x86/include/asm/pgtable_32_types.h
+++ b/arch/x86/include/asm/pgtable_32_types.h
@@ -53,6 +53,8 @@ extern bool __vmalloc_start_set; /* set once high_memory is set */
 #define LDT_BASE_ADDR		\
 	((CPU_ENTRY_AREA_BASE - PAGE_SIZE) & PMD_MASK)
 
+#define LDT_END_ADDR		(LDT_BASE_ADDR + PMD_SIZE)
+
 #define PKMAP_BASE		\
 	((LDT_BASE_ADDR - PAGE_SIZE) & PMD_MASK)
 
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 066e0ab9ffab..04edd2d58211 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -115,6 +115,7 @@ extern unsigned int ptrs_per_p4d;
 #define LDT_PGD_ENTRY_L5	-112UL
 #define LDT_PGD_ENTRY		(pgtable_l5_enabled() ? LDT_PGD_ENTRY_L5 : LDT_PGD_ENTRY_L4)
 #define LDT_BASE_ADDR		(LDT_PGD_ENTRY << PGDIR_SHIFT)
+#define LDT_END_ADDR		(LDT_BASE_ADDR + PGDIR_SIZE)
 
 #define __VMALLOC_BASE_L4	0xffffc90000000000UL
 #define __VMALLOC_BASE_L5 	0xffa0000000000000UL
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c9b14020f4dd..e921b3d494d5 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -206,7 +206,7 @@ static void free_ldt_pgtables(struct mm_struct *mm)
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 	struct mmu_gather tlb;
 	unsigned long start = LDT_BASE_ADDR;
-	unsigned long end = start + (1UL << PGDIR_SHIFT);
+	unsigned long end = LDT_END_ADDR;
 
 	if (!static_cpu_has(X86_FEATURE_PTI))
 		return;
-- 
cgit v1.2.3


From 9bae3197e15dd5e03ce8e237db6fe4486b08a775 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:12 +0200
Subject: x86/ldt: Split out sanity check in map_ldt_struct()

This splits out the mapping sanity check and the actual mapping of the LDT
to user-space from the map_ldt_struct() function in a way so that it is
re-usable for PAE paging.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-36-git-send-email-joro@8bytes.org
---
 arch/x86/kernel/ldt.c | 82 ++++++++++++++++++++++++++++++++++++---------------
 1 file changed, 58 insertions(+), 24 deletions(-)

diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index e921b3d494d5..69af9a0d57b7 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -100,6 +100,49 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 	return new_ldt;
 }
 
+#ifdef CONFIG_PAGE_TABLE_ISOLATION
+
+static void do_sanity_check(struct mm_struct *mm,
+			    bool had_kernel_mapping,
+			    bool had_user_mapping)
+{
+	if (mm->context.ldt) {
+		/*
+		 * We already had an LDT.  The top-level entry should already
+		 * have been allocated and synchronized with the usermode
+		 * tables.
+		 */
+		WARN_ON(!had_kernel_mapping);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(!had_user_mapping);
+	} else {
+		/*
+		 * This is the first time we're mapping an LDT for this process.
+		 * Sync the pgd to the usermode tables.
+		 */
+		WARN_ON(had_kernel_mapping);
+		if (static_cpu_has(X86_FEATURE_PTI))
+			WARN_ON(had_user_mapping);
+	}
+}
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+
+	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+		set_pgd(kernel_to_user_pgdp(pgd), *pgd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	bool had_kernel = (pgd->pgd != 0);
+	bool had_user   = (kernel_to_user_pgdp(pgd)->pgd != 0);
+
+	do_sanity_check(mm, had_kernel, had_user);
+}
+
 /*
  * If PTI is enabled, this maps the LDT into the kernelmode and
  * usermode tables for the given mm.
@@ -115,9 +158,8 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 static int
 map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 {
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
-	bool is_vmalloc, had_top_level_entry;
 	unsigned long va;
+	bool is_vmalloc;
 	spinlock_t *ptl;
 	pgd_t *pgd;
 	int i;
@@ -131,13 +173,15 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 	 */
 	WARN_ON(ldt->slot != -1);
 
+	/* Check if the current mappings are sane */
+	sanity_check_ldt_mapping(mm);
+
 	/*
 	 * Did we already have the top level entry allocated?  We can't
 	 * use pgd_none() for this because it doens't do anything on
 	 * 4-level page table kernels.
 	 */
 	pgd = pgd_offset(mm, LDT_BASE_ADDR);
-	had_top_level_entry = (pgd->pgd != 0);
 
 	is_vmalloc = is_vmalloc_addr(ldt->entries);
 
@@ -172,35 +216,25 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
 		pte_unmap_unlock(ptep, ptl);
 	}
 
-	if (mm->context.ldt) {
-		/*
-		 * We already had an LDT.  The top-level entry should already
-		 * have been allocated and synchronized with the usermode
-		 * tables.
-		 */
-		WARN_ON(!had_top_level_entry);
-		if (static_cpu_has(X86_FEATURE_PTI))
-			WARN_ON(!kernel_to_user_pgdp(pgd)->pgd);
-	} else {
-		/*
-		 * This is the first time we're mapping an LDT for this process.
-		 * Sync the pgd to the usermode tables.
-		 */
-		WARN_ON(had_top_level_entry);
-		if (static_cpu_has(X86_FEATURE_PTI)) {
-			WARN_ON(kernel_to_user_pgdp(pgd)->pgd);
-			set_pgd(kernel_to_user_pgdp(pgd), *pgd);
-		}
-	}
+	/* Propagate LDT mapping to the user page-table */
+	map_ldt_struct_to_user(mm);
 
 	va = (unsigned long)ldt_slot_va(slot);
 	flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0);
 
 	ldt->slot = slot;
-#endif
 	return 0;
 }
 
+#else /* !CONFIG_PAGE_TABLE_ISOLATION */
+
+static int
+map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot)
+{
+	return 0;
+}
+#endif /* CONFIG_PAGE_TABLE_ISOLATION */
+
 static void free_ldt_pgtables(struct mm_struct *mm)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
-- 
cgit v1.2.3


From 6df934b92a549cb3badb6d576f71aeb133e2f110 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:13 +0200
Subject: x86/ldt: Enable LDT user-mapping for PAE

This adds the needed special case for PAE to get the LDT mapped into the
user page-table when PTI is enabled. The big difference to the other paging
modes is that on PAE there is no full top-level PGD entry available for the
LDT, but only a PMD entry.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-37-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/mmu_context.h |  5 ----
 arch/x86/kernel/ldt.c              | 53 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index bbc796eb0a3b..eeeb9289c764 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -71,12 +71,7 @@ struct ldt_struct {
 
 static inline void *ldt_slot_va(int slot)
 {
-#ifdef CONFIG_X86_64
 	return (void *)(LDT_BASE_ADDR + LDT_SLOT_STRIDE * slot);
-#else
-	BUG();
-	return (void *)fix_to_virt(FIX_HOLE);
-#endif
 }
 
 /*
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 69af9a0d57b7..733e6ace0fa4 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -126,6 +126,57 @@ static void do_sanity_check(struct mm_struct *mm,
 	}
 }
 
+#ifdef CONFIG_X86_PAE
+
+static pmd_t *pgd_to_pmd_walk(pgd_t *pgd, unsigned long va)
+{
+	p4d_t *p4d;
+	pud_t *pud;
+
+	if (pgd->pgd == 0)
+		return NULL;
+
+	p4d = p4d_offset(pgd, va);
+	if (p4d_none(*p4d))
+		return NULL;
+
+	pud = pud_offset(p4d, va);
+	if (pud_none(*pud))
+		return NULL;
+
+	return pmd_offset(pud, va);
+}
+
+static void map_ldt_struct_to_user(struct mm_struct *mm)
+{
+	pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	pmd_t *k_pmd, *u_pmd;
+
+	k_pmd = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+	u_pmd = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+
+	if (static_cpu_has(X86_FEATURE_PTI) && !mm->context.ldt)
+		set_pmd(u_pmd, *k_pmd);
+}
+
+static void sanity_check_ldt_mapping(struct mm_struct *mm)
+{
+	pgd_t *k_pgd = pgd_offset(mm, LDT_BASE_ADDR);
+	pgd_t *u_pgd = kernel_to_user_pgdp(k_pgd);
+	bool had_kernel, had_user;
+	pmd_t *k_pmd, *u_pmd;
+
+	k_pmd      = pgd_to_pmd_walk(k_pgd, LDT_BASE_ADDR);
+	u_pmd      = pgd_to_pmd_walk(u_pgd, LDT_BASE_ADDR);
+	had_kernel = (k_pmd->pmd != 0);
+	had_user   = (u_pmd->pmd != 0);
+
+	do_sanity_check(mm, had_kernel, had_user);
+}
+
+#else /* !CONFIG_X86_PAE */
+
 static void map_ldt_struct_to_user(struct mm_struct *mm)
 {
 	pgd_t *pgd = pgd_offset(mm, LDT_BASE_ADDR);
@@ -143,6 +194,8 @@ static void sanity_check_ldt_mapping(struct mm_struct *mm)
 	do_sanity_check(mm, had_kernel, had_user);
 }
 
+#endif /* CONFIG_X86_PAE */
+
 /*
  * If PTI is enabled, this maps the LDT into the kernelmode and
  * usermode tables for the given mm.
-- 
cgit v1.2.3


From 7757d607c6b31867777de42e1fb0210b9c5d8b70 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:14 +0200
Subject: x86/pti: Allow CONFIG_PAGE_TABLE_ISOLATION for x86_32

Allow PTI to be compiled on x86_32.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-38-git-send-email-joro@8bytes.org
---
 security/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/Kconfig b/security/Kconfig
index c4302067a3ad..afa91c6f06bb 100644
--- a/security/Kconfig
+++ b/security/Kconfig
@@ -57,7 +57,7 @@ config SECURITY_NETWORK
 config PAGE_TABLE_ISOLATION
 	bool "Remove the kernel mapping in user mode"
 	default y
-	depends on X86_64 && !UML
+	depends on X86 && !UML
 	help
 	  This feature reduces the number of hardware side channels by
 	  ensuring that the majority of kernel addresses are not mapped
-- 
cgit v1.2.3


From 5e8105950a8b3e03e805299b4d05020ee4eda31a Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:15 +0200
Subject: x86/mm/pti: Add Warning when booting on a PCID capable CPU

Warn the user in case the performance can be significantly improved by
switching to a 64-bit kernel.

Suggested-by: Andy Lutomirski <luto@kernel.org>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-39-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index a536ecc91847..7b1c85759005 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -517,6 +517,28 @@ void __init pti_init(void)
 
 	pr_info("enabled\n");
 
+#ifdef CONFIG_X86_32
+	/*
+	 * We check for X86_FEATURE_PCID here. But the init-code will
+	 * clear the feature flag on 32 bit because the feature is not
+	 * supported on 32 bit anyway. To print the warning we need to
+	 * check with cpuid directly again.
+	 */
+	if (cpuid_ecx(0x1) && BIT(17)) {
+		/* Use printk to work around pr_fmt() */
+		printk(KERN_WARNING "\n");
+		printk(KERN_WARNING "************************************************************\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** You are using 32-bit PTI on a 64-bit PCID-capable CPU. **\n");
+		printk(KERN_WARNING "** Your performance will increase dramatically if you     **\n");
+		printk(KERN_WARNING "** switch to a 64-bit kernel!                             **\n");
+		printk(KERN_WARNING "**                                                        **\n");
+		printk(KERN_WARNING "** WARNING! WARNING! WARNING! WARNING! WARNING! WARNING!  **\n");
+		printk(KERN_WARNING "************************************************************\n");
+	}
+#endif
+
 	pti_clone_user_shared();
 
 	/* Undo all global bits from the init pagetables in head_64.S: */
-- 
cgit v1.2.3


From 97193702c6d353e12aefc0fb2f73a98ca421cd56 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 18 Jul 2018 11:41:16 +0200
Subject: x86/entry/32: Add debug code to check entry/exit CR3

Add code to check whether the kernel is entered and left with the correct
CR3 and make it depend on CONFIG_DEBUG_ENTRY.  This is needed because there
is no NX protection of user-addresses in the kernel-CR3 on x86-32 and that
type of bug would not be detected otherwise.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-40-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index b1541c74c71a..010cdb41e3c7 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -166,6 +166,24 @@
 .Lend_\@:
 .endm
 
+.macro BUG_IF_WRONG_CR3 no_user_check=0
+#ifdef CONFIG_DEBUG_ENTRY
+	ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_PTI
+	.if \no_user_check == 0
+	/* coming from usermode? */
+	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
+	jz	.Lend_\@
+	.endif
+	/* On user-cr3? */
+	movl	%cr3, %eax
+	testl	$PTI_SWITCH_MASK, %eax
+	jnz	.Lend_\@
+	/* From userspace with kernel cr3 - BUG */
+	ud2
+.Lend_\@:
+#endif
+.endm
+
 /*
  * Switch to kernel cr3 if not already loaded and return current cr3 in
  * \scratch_reg
@@ -213,6 +231,8 @@
 .macro SAVE_ALL_NMI cr3_reg:req
 	SAVE_ALL
 
+	BUG_IF_WRONG_CR3
+
 	/*
 	 * Now switch the CR3 when PTI is enabled.
 	 *
@@ -224,6 +244,7 @@
 
 .Lend_\@:
 .endm
+
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
  * frame pointer is replaced with an encoded pointer to pt_regs.  The encoding
@@ -287,6 +308,8 @@
 
 .Lswitched_\@:
 
+	BUG_IF_WRONG_CR3
+
 	RESTORE_REGS pop=\pop
 .endm
 
@@ -357,6 +380,8 @@
 
 	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
 
+	BUG_IF_WRONG_CR3
+
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
 
 	/*
@@ -799,6 +824,7 @@ ENTRY(entry_SYSENTER_32)
 	 */
 	pushfl
 	pushl	%eax
+	BUG_IF_WRONG_CR3 no_user_check=1
 	SWITCH_TO_KERNEL_CR3 scratch_reg=%eax
 	popl	%eax
 	popfl
@@ -893,6 +919,7 @@ ENTRY(entry_SYSENTER_32)
 	 * whereas POPF does not.)
 	 */
 	btrl	$X86_EFLAGS_IF_BIT, (%esp)
+	BUG_IF_WRONG_CR3 no_user_check=1
 	popfl
 	popl	%eax
 
@@ -970,6 +997,8 @@ restore_all:
 	/* Switch back to user CR3 */
 	SWITCH_TO_USER_CR3 scratch_reg=%eax
 
+	BUG_IF_WRONG_CR3
+
 	/* Restore user state */
 	RESTORE_REGS pop=4			# skip orig_eax/error_code
 .Lirq_return:
@@ -983,6 +1012,7 @@ restore_all:
 restore_all_kernel:
 	TRACE_IRQS_IRET
 	PARANOID_EXIT_TO_KERNEL_MODE
+	BUG_IF_WRONG_CR3
 	RESTORE_REGS 4
 	jmp	.Lirq_return
 
@@ -990,6 +1020,19 @@ restore_all_kernel:
 ENTRY(iret_exc	)
 	pushl	$0				# no error code
 	pushl	$do_iret_error
+
+#ifdef CONFIG_DEBUG_ENTRY
+	/*
+	 * The stack-frame here is the one that iret faulted on, so its a
+	 * return-to-user frame. We are on kernel-cr3 because we come here from
+	 * the fixup code. This confuses the CR3 checker, so switch to user-cr3
+	 * as the checker expects it.
+	 */
+	pushl	%eax
+	SWITCH_TO_USER_CR3 scratch_reg=%eax
+	popl	%eax
+#endif
+
 	jmp	common_exception
 .previous
 	_ASM_EXTABLE(.Lirq_return, iret_exc)
-- 
cgit v1.2.3


From 985e695074d35768cb04d65f58bca45f7bf1a99d Mon Sep 17 00:00:00 2001
From: Ondrej Mosnacek <omosnace@redhat.com>
Date: Fri, 13 Jul 2018 14:06:42 +0200
Subject: timekeeping/ntp: Constify some function arguments

Add 'const' to some function arguments and variables to make it easier
to read the code.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Ondrej Mosnacek <omosnace@redhat.com>
[jstultz: Also fixup pre-existing checkpatch warnings for
 prototype arguments with no variable name]
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/timekeeping.h        |  2 +-
 kernel/time/ntp.c                  |  6 +++---
 kernel/time/ntp_internal.h         |  4 ++--
 kernel/time/timekeeping.c          | 29 +++++++++++++++--------------
 kernel/time/timekeeping_debug.c    |  2 +-
 kernel/time/timekeeping_internal.h |  2 +-
 6 files changed, 23 insertions(+), 22 deletions(-)

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 86bc2026efce..edace6b656e9 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -177,7 +177,7 @@ static inline time64_t ktime_get_clocktai_seconds(void)
 extern bool timekeeping_rtc_skipsuspend(void);
 extern bool timekeeping_rtc_skipresume(void);
 
-extern void timekeeping_inject_sleeptime64(struct timespec64 *delta);
+extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
 
 /*
  * struct system_time_snapshot - simultaneous raw/real time capture with
diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
index a627cae8baab..c5e0cba3b39c 100644
--- a/kernel/time/ntp.c
+++ b/kernel/time/ntp.c
@@ -642,7 +642,7 @@ void ntp_notify_cmos_timer(void)
 /*
  * Propagate a new txc->status value into the NTP state:
  */
-static inline void process_adj_status(struct timex *txc)
+static inline void process_adj_status(const struct timex *txc)
 {
 	if ((time_status & STA_PLL) && !(txc->status & STA_PLL)) {
 		time_state = TIME_OK;
@@ -665,7 +665,7 @@ static inline void process_adj_status(struct timex *txc)
 }
 
 
-static inline void process_adjtimex_modes(struct timex *txc, s32 *time_tai)
+static inline void process_adjtimex_modes(const struct timex *txc, s32 *time_tai)
 {
 	if (txc->modes & ADJ_STATUS)
 		process_adj_status(txc);
@@ -716,7 +716,7 @@ static inline void process_adjtimex_modes(struct timex *txc, s32 *time_tai)
  * adjtimex mainly allows reading (and writing, if superuser) of
  * kernel time-keeping variables. used by xntpd.
  */
-int __do_adjtimex(struct timex *txc, struct timespec64 *ts, s32 *time_tai)
+int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai)
 {
 	int result;
 
diff --git a/kernel/time/ntp_internal.h b/kernel/time/ntp_internal.h
index 909bd1f1bfb1..c24b0e13f011 100644
--- a/kernel/time/ntp_internal.h
+++ b/kernel/time/ntp_internal.h
@@ -8,6 +8,6 @@ extern void ntp_clear(void);
 extern u64 ntp_tick_length(void);
 extern ktime_t ntp_get_next_leap(void);
 extern int second_overflow(time64_t secs);
-extern int __do_adjtimex(struct timex *, struct timespec64 *, s32 *);
-extern void __hardpps(const struct timespec64 *, const struct timespec64 *);
+extern int __do_adjtimex(struct timex *txc, const struct timespec64 *ts, s32 *time_tai);
+extern void __hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts);
 #endif /* _LINUX_NTP_INTERNAL_H */
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ad779c2ec53a..7033ac1fee65 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -105,7 +105,7 @@ static inline void tk_normalize_xtime(struct timekeeper *tk)
 	}
 }
 
-static inline struct timespec64 tk_xtime(struct timekeeper *tk)
+static inline struct timespec64 tk_xtime(const struct timekeeper *tk)
 {
 	struct timespec64 ts;
 
@@ -162,7 +162,7 @@ static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta)
  * a read of the fast-timekeeper tkrs (which is protected by its own locking
  * and update logic).
  */
-static inline u64 tk_clock_read(struct tk_read_base *tkr)
+static inline u64 tk_clock_read(const struct tk_read_base *tkr)
 {
 	struct clocksource *clock = READ_ONCE(tkr->clock);
 
@@ -211,7 +211,7 @@ static void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 	}
 }
 
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	u64 now, last, mask, max, delta;
@@ -255,7 +255,7 @@ static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
 static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset)
 {
 }
-static inline u64 timekeeping_get_delta(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_delta(const struct tk_read_base *tkr)
 {
 	u64 cycle_now, delta;
 
@@ -352,7 +352,7 @@ u32 (*arch_gettimeoffset)(void) = default_arch_gettimeoffset;
 static inline u32 arch_gettimeoffset(void) { return 0; }
 #endif
 
-static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
+static inline u64 timekeeping_delta_to_ns(const struct tk_read_base *tkr, u64 delta)
 {
 	u64 nsec;
 
@@ -363,7 +363,7 @@ static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
 	return nsec + arch_gettimeoffset();
 }
 
-static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
+static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr)
 {
 	u64 delta;
 
@@ -371,7 +371,7 @@ static inline u64 timekeeping_get_ns(struct tk_read_base *tkr)
 	return timekeeping_delta_to_ns(tkr, delta);
 }
 
-static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
+static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles)
 {
 	u64 delta;
 
@@ -394,7 +394,8 @@ static inline u64 timekeeping_cycles_to_ns(struct tk_read_base *tkr, u64 cycles)
  * slightly wrong timestamp (a few nanoseconds). See
  * @ktime_get_mono_fast_ns.
  */
-static void update_fast_timekeeper(struct tk_read_base *tkr, struct tk_fast *tkf)
+static void update_fast_timekeeper(const struct tk_read_base *tkr,
+				   struct tk_fast *tkf)
 {
 	struct tk_read_base *base = tkf->base;
 
@@ -549,10 +550,10 @@ EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns);
  * number of cycles every time until timekeeping is resumed at which time the
  * proper readout base for the fast timekeeper will be restored automatically.
  */
-static void halt_fast_timekeeper(struct timekeeper *tk)
+static void halt_fast_timekeeper(const struct timekeeper *tk)
 {
 	static struct tk_read_base tkr_dummy;
-	struct tk_read_base *tkr = &tk->tkr_mono;
+	const struct tk_read_base *tkr = &tk->tkr_mono;
 
 	memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy));
 	cycles_at_suspend = tk_clock_read(tkr);
@@ -1277,7 +1278,7 @@ EXPORT_SYMBOL(do_settimeofday64);
  *
  * Adds or subtracts an offset value from the current time.
  */
-static int timekeeping_inject_offset(struct timespec64 *ts)
+static int timekeeping_inject_offset(const struct timespec64 *ts)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -1585,7 +1586,7 @@ static struct timespec64 timekeeping_suspend_time;
  * adds the sleep offset to the timekeeping variables.
  */
 static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
-					   struct timespec64 *delta)
+					   const struct timespec64 *delta)
 {
 	if (!timespec64_valid_strict(delta)) {
 		printk_deferred(KERN_WARNING
@@ -1646,7 +1647,7 @@ bool timekeeping_rtc_skipsuspend(void)
  * This function should only be called by rtc_resume(), and allows
  * a suspend offset to be injected into the timekeeping values.
  */
-void timekeeping_inject_sleeptime64(struct timespec64 *delta)
+void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
 {
 	struct timekeeper *tk = &tk_core.timekeeper;
 	unsigned long flags;
@@ -2240,7 +2241,7 @@ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real,
 /**
  * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex
  */
-static int timekeeping_validate_timex(struct timex *txc)
+static int timekeeping_validate_timex(const struct timex *txc)
 {
 	if (txc->modes & ADJ_ADJTIME) {
 		/* singleshot must not be used with any other mode bits */
diff --git a/kernel/time/timekeeping_debug.c b/kernel/time/timekeeping_debug.c
index 0754cadfa9e6..238e4be60229 100644
--- a/kernel/time/timekeeping_debug.c
+++ b/kernel/time/timekeeping_debug.c
@@ -70,7 +70,7 @@ static int __init tk_debug_sleep_time_init(void)
 }
 late_initcall(tk_debug_sleep_time_init);
 
-void tk_debug_account_sleep_time(struct timespec64 *t)
+void tk_debug_account_sleep_time(const struct timespec64 *t)
 {
 	/* Cap bin index so we don't overflow the array */
 	int bin = min(fls(t->tv_sec), NUM_BINS-1);
diff --git a/kernel/time/timekeeping_internal.h b/kernel/time/timekeeping_internal.h
index cf5c0828ee31..bcbb52db2256 100644
--- a/kernel/time/timekeeping_internal.h
+++ b/kernel/time/timekeeping_internal.h
@@ -8,7 +8,7 @@
 #include <linux/time.h>
 
 #ifdef CONFIG_DEBUG_FS
-extern void tk_debug_account_sleep_time(struct timespec64 *t);
+extern void tk_debug_account_sleep_time(const struct timespec64 *t);
 #else
 #define tk_debug_account_sleep_time(x)
 #endif
-- 
cgit v1.2.3


From f473e5f467f6049370575390b08dc42131315d60 Mon Sep 17 00:00:00 2001
From: Mukesh Ojha <mojha@codeaurora.org>
Date: Tue, 17 Jul 2018 12:01:29 +0530
Subject: time: Fix extra sleeptime injection when suspend fails

Currently, there exists a corner case assuming when there is
only one clocksource e.g RTC, and system failed to go to
suspend mode. While resume rtc_resume() injects the sleeptime
as timekeeping_rtc_skipresume() returned 'false' (default value
of sleeptime_injected) due to which we can see mismatch in
timestamps.

This issue can also come in a system where more than one
clocksource are present and very first suspend fails.

Success case:
------------
                                        {sleeptime_injected=false}
rtc_suspend() => timekeeping_suspend() => timekeeping_resume() =>

(sleeptime injected)
 rtc_resume()

Failure case:
------------
         {failure in sleep path} {sleeptime_injected=false}
rtc_suspend()     =>          rtc_resume()

{sleeptime injected again which was not required as the suspend failed}

Fix this by handling the boolean logic properly.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Originally-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Mukesh Ojha <mojha@codeaurora.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 kernel/time/timekeeping.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 7033ac1fee65..19414b16cf9e 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1519,8 +1519,20 @@ void __weak read_boot_clock64(struct timespec64 *ts)
 	ts->tv_nsec = 0;
 }
 
-/* Flag for if timekeeping_resume() has injected sleeptime */
-static bool sleeptime_injected;
+/*
+ * Flag reflecting whether timekeeping_resume() has injected sleeptime.
+ *
+ * The flag starts of false and is only set when a suspend reaches
+ * timekeeping_suspend(), timekeeping_resume() sets it to false when the
+ * timekeeper clocksource is not stopping across suspend and has been
+ * used to update sleep time. If the timekeeper clocksource has stopped
+ * then the flag stays true and is used by the RTC resume code to decide
+ * whether sleeptime must be injected and if so the flag gets false then.
+ *
+ * If a suspend fails before reaching timekeeping_resume() then the flag
+ * stays false and prevents erroneous sleeptime injection.
+ */
+static bool suspend_timing_needed;
 
 /* Flag for if there is a persistent clock on this platform */
 static bool persistent_clock_exists;
@@ -1619,7 +1631,7 @@ static void __timekeeping_inject_sleeptime(struct timekeeper *tk,
  */
 bool timekeeping_rtc_skipresume(void)
 {
-	return sleeptime_injected;
+	return !suspend_timing_needed;
 }
 
 /**
@@ -1655,6 +1667,8 @@ void timekeeping_inject_sleeptime64(const struct timespec64 *delta)
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 
+	suspend_timing_needed = false;
+
 	timekeeping_forward_now(tk);
 
 	__timekeeping_inject_sleeptime(tk, delta);
@@ -1679,8 +1693,8 @@ void timekeeping_resume(void)
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
 	u64 cycle_now;
+	bool inject_sleeptime = false;
 
-	sleeptime_injected = false;
 	read_persistent_clock64(&ts_new);
 
 	clockevents_resume();
@@ -1710,14 +1724,16 @@ void timekeeping_resume(void)
 					      tk->tkr_mono.mask);
 		nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
 		ts_delta = ns_to_timespec64(nsec);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
 		ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time);
-		sleeptime_injected = true;
+		inject_sleeptime = true;
 	}
 
-	if (sleeptime_injected)
+	if (inject_sleeptime) {
+		suspend_timing_needed = false;
 		__timekeeping_inject_sleeptime(tk, &ts_delta);
+	}
 
 	/* Re-base the last cycle value */
 	tk->tkr_mono.cycle_last = cycle_now;
@@ -1752,6 +1768,8 @@ int timekeeping_suspend(void)
 	if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec)
 		persistent_clock_exists = true;
 
+	suspend_timing_needed = true;
+
 	raw_spin_lock_irqsave(&timekeeper_lock, flags);
 	write_seqcount_begin(&tk_core.seq);
 	timekeeping_forward_now(tk);
-- 
cgit v1.2.3


From 39232ed5a1793f67b11430c43ed8a9ed6e96c6eb Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linaro.org>
Date: Tue, 17 Jul 2018 15:55:16 +0800
Subject: time: Introduce one suspend clocksource to compensate the suspend
 time

On some hardware with multiple clocksources, we have coarse grained
clocksources that support the CLOCK_SOURCE_SUSPEND_NONSTOP flag, but
which are less than ideal for timekeeping whereas other clocksources
can be better candidates but halt on suspend.

Currently, the timekeeping core only supports timing suspend using
CLOCK_SOURCE_SUSPEND_NONSTOP clocksources if that clocksource is the
current clocksource for timekeeping.

As a result, some architectures try to implement read_persistent_clock64()
using those non-stop clocksources, but isn't really ideal, which will
introduce more duplicate code. To fix this, provide logic to allow a
registered SUSPEND_NONSTOP clocksource, which isn't the current
clocksource, to be used to calculate the suspend time.

Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Miroslav Lichvar <mlichvar@redhat.com>
Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Stephen Boyd <sboyd@kernel.org>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Baolin Wang <baolin.wang@linaro.org>
[jstultz: minor tweaks to merge with previous resume changes]
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 include/linux/clocksource.h |   3 +
 kernel/time/clocksource.c   | 149 ++++++++++++++++++++++++++++++++++++++++++++
 kernel/time/timekeeping.c   |  22 ++++---
 3 files changed, 166 insertions(+), 8 deletions(-)

diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 7dff1963c185..308918928767 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -194,6 +194,9 @@ extern void clocksource_suspend(void);
 extern void clocksource_resume(void);
 extern struct clocksource * __init clocksource_default_clock(void);
 extern void clocksource_mark_unstable(struct clocksource *cs);
+extern void
+clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles);
+extern u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 now);
 
 extern u64
 clocks_calc_max_nsecs(u32 mult, u32 shift, u32 maxadj, u64 mask, u64 *max_cycles);
diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
index f89a78e2792b..f74fb00d8064 100644
--- a/kernel/time/clocksource.c
+++ b/kernel/time/clocksource.c
@@ -94,6 +94,8 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
 /*[Clocksource internal variables]---------
  * curr_clocksource:
  *	currently selected clocksource.
+ * suspend_clocksource:
+ *	used to calculate the suspend time.
  * clocksource_list:
  *	linked list with the registered clocksources
  * clocksource_mutex:
@@ -102,10 +104,12 @@ EXPORT_SYMBOL_GPL(clocks_calc_mult_shift);
  *	Name of the user-specified clocksource.
  */
 static struct clocksource *curr_clocksource;
+static struct clocksource *suspend_clocksource;
 static LIST_HEAD(clocksource_list);
 static DEFINE_MUTEX(clocksource_mutex);
 static char override_name[CS_NAME_LEN];
 static int finished_booting;
+static u64 suspend_start;
 
 #ifdef CONFIG_CLOCKSOURCE_WATCHDOG
 static void clocksource_watchdog_work(struct work_struct *work);
@@ -447,6 +451,140 @@ static inline void clocksource_watchdog_unlock(unsigned long *flags) { }
 
 #endif /* CONFIG_CLOCKSOURCE_WATCHDOG */
 
+static bool clocksource_is_suspend(struct clocksource *cs)
+{
+	return cs == suspend_clocksource;
+}
+
+static void __clocksource_suspend_select(struct clocksource *cs)
+{
+	/*
+	 * Skip the clocksource which will be stopped in suspend state.
+	 */
+	if (!(cs->flags & CLOCK_SOURCE_SUSPEND_NONSTOP))
+		return;
+
+	/*
+	 * The nonstop clocksource can be selected as the suspend clocksource to
+	 * calculate the suspend time, so it should not supply suspend/resume
+	 * interfaces to suspend the nonstop clocksource when system suspends.
+	 */
+	if (cs->suspend || cs->resume) {
+		pr_warn("Nonstop clocksource %s should not supply suspend/resume interfaces\n",
+			cs->name);
+	}
+
+	/* Pick the best rating. */
+	if (!suspend_clocksource || cs->rating > suspend_clocksource->rating)
+		suspend_clocksource = cs;
+}
+
+/**
+ * clocksource_suspend_select - Select the best clocksource for suspend timing
+ * @fallback:	if select a fallback clocksource
+ */
+static void clocksource_suspend_select(bool fallback)
+{
+	struct clocksource *cs, *old_suspend;
+
+	old_suspend = suspend_clocksource;
+	if (fallback)
+		suspend_clocksource = NULL;
+
+	list_for_each_entry(cs, &clocksource_list, list) {
+		/* Skip current if we were requested for a fallback. */
+		if (fallback && cs == old_suspend)
+			continue;
+
+		__clocksource_suspend_select(cs);
+	}
+}
+
+/**
+ * clocksource_start_suspend_timing - Start measuring the suspend timing
+ * @cs:			current clocksource from timekeeping
+ * @start_cycles:	current cycles from timekeeping
+ *
+ * This function will save the start cycle values of suspend timer to calculate
+ * the suspend time when resuming system.
+ *
+ * This function is called late in the suspend process from timekeeping_suspend(),
+ * that means processes are freezed, non-boot cpus and interrupts are disabled
+ * now. It is therefore possible to start the suspend timer without taking the
+ * clocksource mutex.
+ */
+void clocksource_start_suspend_timing(struct clocksource *cs, u64 start_cycles)
+{
+	if (!suspend_clocksource)
+		return;
+
+	/*
+	 * If current clocksource is the suspend timer, we should use the
+	 * tkr_mono.cycle_last value as suspend_start to avoid same reading
+	 * from suspend timer.
+	 */
+	if (clocksource_is_suspend(cs)) {
+		suspend_start = start_cycles;
+		return;
+	}
+
+	if (suspend_clocksource->enable &&
+	    suspend_clocksource->enable(suspend_clocksource)) {
+		pr_warn_once("Failed to enable the non-suspend-able clocksource.\n");
+		return;
+	}
+
+	suspend_start = suspend_clocksource->read(suspend_clocksource);
+}
+
+/**
+ * clocksource_stop_suspend_timing - Stop measuring the suspend timing
+ * @cs:		current clocksource from timekeeping
+ * @cycle_now:	current cycles from timekeeping
+ *
+ * This function will calculate the suspend time from suspend timer.
+ *
+ * Returns nanoseconds since suspend started, 0 if no usable suspend clocksource.
+ *
+ * This function is called early in the resume process from timekeeping_resume(),
+ * that means there is only one cpu, no processes are running and the interrupts
+ * are disabled. It is therefore possible to stop the suspend timer without
+ * taking the clocksource mutex.
+ */
+u64 clocksource_stop_suspend_timing(struct clocksource *cs, u64 cycle_now)
+{
+	u64 now, delta, nsec = 0;
+
+	if (!suspend_clocksource)
+		return 0;
+
+	/*
+	 * If current clocksource is the suspend timer, we should use the
+	 * tkr_mono.cycle_last value from timekeeping as current cycle to
+	 * avoid same reading from suspend timer.
+	 */
+	if (clocksource_is_suspend(cs))
+		now = cycle_now;
+	else
+		now = suspend_clocksource->read(suspend_clocksource);
+
+	if (now > suspend_start) {
+		delta = clocksource_delta(now, suspend_start,
+					  suspend_clocksource->mask);
+		nsec = mul_u64_u32_shr(delta, suspend_clocksource->mult,
+				       suspend_clocksource->shift);
+	}
+
+	/*
+	 * Disable the suspend timer to save power if current clocksource is
+	 * not the suspend timer.
+	 */
+	if (!clocksource_is_suspend(cs) && suspend_clocksource->disable)
+		suspend_clocksource->disable(suspend_clocksource);
+
+	return nsec;
+}
+
 /**
  * clocksource_suspend - suspend the clocksource(s)
  */
@@ -792,6 +930,7 @@ int __clocksource_register_scale(struct clocksource *cs, u32 scale, u32 freq)
 
 	clocksource_select();
 	clocksource_select_watchdog(false);
+	__clocksource_suspend_select(cs);
 	mutex_unlock(&clocksource_mutex);
 	return 0;
 }
@@ -820,6 +959,7 @@ void clocksource_change_rating(struct clocksource *cs, int rating)
 
 	clocksource_select();
 	clocksource_select_watchdog(false);
+	clocksource_suspend_select(false);
 	mutex_unlock(&clocksource_mutex);
 }
 EXPORT_SYMBOL(clocksource_change_rating);
@@ -845,6 +985,15 @@ static int clocksource_unbind(struct clocksource *cs)
 			return -EBUSY;
 	}
 
+	if (clocksource_is_suspend(cs)) {
+		/*
+		 * Select and try to install a replacement suspend clocksource.
+		 * If no replacement suspend clocksource, we will just let the
+		 * clocksource go and have no suspend clocksource.
+		 */
+		clocksource_suspend_select(true);
+	}
+
 	clocksource_watchdog_lock(&flags);
 	clocksource_dequeue_watchdog(cs);
 	list_del_init(&cs->list);
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 19414b16cf9e..d9e659a12c76 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1692,7 +1692,7 @@ void timekeeping_resume(void)
 	struct clocksource *clock = tk->tkr_mono.clock;
 	unsigned long flags;
 	struct timespec64 ts_new, ts_delta;
-	u64 cycle_now;
+	u64 cycle_now, nsec;
 	bool inject_sleeptime = false;
 
 	read_persistent_clock64(&ts_new);
@@ -1716,13 +1716,8 @@ void timekeeping_resume(void)
 	 * usable source. The rtc part is handled separately in rtc core code.
 	 */
 	cycle_now = tk_clock_read(&tk->tkr_mono);
-	if ((clock->flags & CLOCK_SOURCE_SUSPEND_NONSTOP) &&
-		cycle_now > tk->tkr_mono.cycle_last) {
-		u64 nsec, cyc_delta;
-
-		cyc_delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last,
-					      tk->tkr_mono.mask);
-		nsec = mul_u64_u32_shr(cyc_delta, clock->mult, clock->shift);
+	nsec = clocksource_stop_suspend_timing(clock, cycle_now);
+	if (nsec > 0) {
 		ts_delta = ns_to_timespec64(nsec);
 		inject_sleeptime = true;
 	} else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) {
@@ -1757,6 +1752,8 @@ int timekeeping_suspend(void)
 	unsigned long flags;
 	struct timespec64		delta, delta_delta;
 	static struct timespec64	old_delta;
+	struct clocksource *curr_clock;
+	u64 cycle_now;
 
 	read_persistent_clock64(&timekeeping_suspend_time);
 
@@ -1775,6 +1772,15 @@ int timekeeping_suspend(void)
 	timekeeping_forward_now(tk);
 	timekeeping_suspended = 1;
 
+	/*
+	 * Since we've called forward_now, cycle_last stores the value
+	 * just read from the current clocksource. Save this to potentially
+	 * use in suspend timing.
+	 */
+	curr_clock = tk->tkr_mono.clock;
+	cycle_now = tk->tkr_mono.cycle_last;
+	clocksource_start_suspend_timing(curr_clock, cycle_now);
+
 	if (persistent_clock_exists) {
 		/*
 		 * To avoid drift caused by repeated suspend/resumes,
-- 
cgit v1.2.3


From 8111b5e334861c4cd12e49e151e7e2f0e617d46a Mon Sep 17 00:00:00 2001
From: liwei <liwei213@huawei.com>
Date: Tue, 17 Jul 2018 17:36:56 +0800
Subject: scsi: ufs: add Hisilicon ufs driver code

add Hisilicon ufs driver code.

Signed-off-by: Li Wei <liwei213@huawei.com>
Signed-off-by: Geng Jianfeng <gengjianfeng@hisilicon.com>
Signed-off-by: Zang Leigang <zangleigang@hisilicon.com>
Signed-off-by: Yu Jianfeng <steven.yujianfeng@hisilicon.com>
Tested-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/Kconfig    |   9 +
 drivers/scsi/ufs/Makefile   |   1 +
 drivers/scsi/ufs/ufs-hisi.c | 619 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/scsi/ufs/ufs-hisi.h | 115 ++++++++
 4 files changed, 744 insertions(+)
 create mode 100644 drivers/scsi/ufs/ufs-hisi.c
 create mode 100644 drivers/scsi/ufs/ufs-hisi.h

diff --git a/drivers/scsi/ufs/Kconfig b/drivers/scsi/ufs/Kconfig
index e27b4d4e6ae2..e09fe6ab3572 100644
--- a/drivers/scsi/ufs/Kconfig
+++ b/drivers/scsi/ufs/Kconfig
@@ -100,3 +100,12 @@ config SCSI_UFS_QCOM
 
 	  Select this if you have UFS controller on QCOM chipset.
 	  If unsure, say N.
+
+config SCSI_UFS_HISI
+	tristate "Hisilicon specific hooks to UFS controller platform driver"
+	depends on (ARCH_HISI || COMPILE_TEST) && SCSI_UFSHCD_PLATFORM
+	---help---
+	  This selects the Hisilicon specific additions to UFSHCD platform driver.
+
+	  Select this if you have UFS controller on Hisilicon chipset.
+	  If unsure, say N.
diff --git a/drivers/scsi/ufs/Makefile b/drivers/scsi/ufs/Makefile
index 918f5791202d..2c50f03d8c4a 100644
--- a/drivers/scsi/ufs/Makefile
+++ b/drivers/scsi/ufs/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_SCSI_UFSHCD) += ufshcd-core.o
 ufshcd-core-objs := ufshcd.o ufs-sysfs.o
 obj-$(CONFIG_SCSI_UFSHCD_PCI) += ufshcd-pci.o
 obj-$(CONFIG_SCSI_UFSHCD_PLATFORM) += ufshcd-pltfrm.o
+obj-$(CONFIG_SCSI_UFS_HISI) += ufs-hisi.o
diff --git a/drivers/scsi/ufs/ufs-hisi.c b/drivers/scsi/ufs/ufs-hisi.c
new file mode 100644
index 000000000000..46df707e6f2c
--- /dev/null
+++ b/drivers/scsi/ufs/ufs-hisi.c
@@ -0,0 +1,619 @@
+/*
+ * HiSilicon Hixxxx UFS Driver
+ *
+ * Copyright (c) 2016-2017 Linaro Ltd.
+ * Copyright (c) 2016-2017 HiSilicon Technologies Co., Ltd.
+ *
+ * Released under the GPLv2 only.
+ * SPDX-License-Identifier: GPL-2.0
+ */
+
+#include <linux/time.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/dma-mapping.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include "ufshcd.h"
+#include "ufshcd-pltfrm.h"
+#include "unipro.h"
+#include "ufs-hisi.h"
+#include "ufshci.h"
+
+static int ufs_hisi_check_hibern8(struct ufs_hba *hba)
+{
+	int err = 0;
+	u32 tx_fsm_val_0 = 0;
+	u32 tx_fsm_val_1 = 0;
+	unsigned long timeout = jiffies + msecs_to_jiffies(HBRN8_POLL_TOUT_MS);
+
+	do {
+		err = ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 0),
+				      &tx_fsm_val_0);
+		err |= ufshcd_dme_get(hba,
+		    UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 1), &tx_fsm_val_1);
+		if (err || (tx_fsm_val_0 == TX_FSM_HIBERN8 &&
+			tx_fsm_val_1 == TX_FSM_HIBERN8))
+			break;
+
+		/* sleep for max. 200us */
+		usleep_range(100, 200);
+	} while (time_before(jiffies, timeout));
+
+	/*
+	 * we might have scheduled out for long during polling so
+	 * check the state again.
+	 */
+	if (time_after(jiffies, timeout)) {
+		err = ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 0),
+				     &tx_fsm_val_0);
+		err |= ufshcd_dme_get(hba,
+		 UIC_ARG_MIB_SEL(MPHY_TX_FSM_STATE, 1), &tx_fsm_val_1);
+	}
+
+	if (err) {
+		dev_err(hba->dev, "%s: unable to get TX_FSM_STATE, err %d\n",
+			__func__, err);
+	} else if (tx_fsm_val_0 != TX_FSM_HIBERN8 ||
+			 tx_fsm_val_1 != TX_FSM_HIBERN8) {
+		err = -1;
+		dev_err(hba->dev, "%s: invalid TX_FSM_STATE, lane0 = %d, lane1 = %d\n",
+			__func__, tx_fsm_val_0, tx_fsm_val_1);
+	}
+
+	return err;
+}
+
+static void ufs_hi3660_clk_init(struct ufs_hba *hba)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	ufs_sys_ctrl_clr_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+	if (ufs_sys_ctrl_readl(host, PHY_CLK_CTRL) & BIT_SYSCTRL_REF_CLOCK_EN)
+		mdelay(1);
+	/* use abb clk */
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_REFCLK_SRC_SEl, UFS_SYSCTRL);
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_REFCLK_ISO_EN, PHY_ISO_EN);
+	/* open mphy ref clk */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+}
+
+static void ufs_hi3660_soc_init(struct ufs_hba *hba)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+	u32 reg;
+
+	if (!IS_ERR(host->rst))
+		reset_control_assert(host->rst);
+
+	/* HC_PSW powerup */
+	ufs_sys_ctrl_set_bits(host, BIT_UFS_PSW_MTCMOS_EN, PSW_POWER_CTRL);
+	udelay(10);
+	/* notify PWR ready */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_PWR_READY, HC_LP_CTRL);
+	ufs_sys_ctrl_writel(host, MASK_UFS_DEVICE_RESET | 0,
+		UFS_DEVICE_RESET_CTRL);
+
+	reg = ufs_sys_ctrl_readl(host, PHY_CLK_CTRL);
+	reg = (reg & ~MASK_SYSCTRL_CFG_CLOCK_FREQ) | UFS_FREQ_CFG_CLK;
+	/* set cfg clk freq */
+	ufs_sys_ctrl_writel(host, reg, PHY_CLK_CTRL);
+	/* set ref clk freq */
+	ufs_sys_ctrl_clr_bits(host, MASK_SYSCTRL_REF_CLOCK_SEL, PHY_CLK_CTRL);
+	/* bypass ufs clk gate */
+	ufs_sys_ctrl_set_bits(host, MASK_UFS_CLK_GATE_BYPASS,
+						 CLOCK_GATE_BYPASS);
+	ufs_sys_ctrl_set_bits(host, MASK_UFS_SYSCRTL_BYPASS, UFS_SYSCTRL);
+
+	/* open psw clk */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_PSW_CLK_EN, PSW_CLK_CTRL);
+	/* disable ufshc iso */
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_PSW_ISO_CTRL, PSW_POWER_CTRL);
+	/* disable phy iso */
+	ufs_sys_ctrl_clr_bits(host, BIT_UFS_PHY_ISO_CTRL, PHY_ISO_EN);
+	/* notice iso disable */
+	ufs_sys_ctrl_clr_bits(host, BIT_SYSCTRL_LP_ISOL_EN, HC_LP_CTRL);
+
+	/* disable lp_reset_n */
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_LP_RESET_N, RESET_CTRL_EN);
+	mdelay(1);
+
+	ufs_sys_ctrl_writel(host, MASK_UFS_DEVICE_RESET | BIT_UFS_DEVICE_RESET,
+		UFS_DEVICE_RESET_CTRL);
+
+	msleep(20);
+
+	/*
+	 * enable the fix of linereset recovery,
+	 * and enable rx_reset/tx_rest beat
+	 * enable ref_clk_en override(bit5) &
+	 * override value = 1(bit4), with mask
+	 */
+	ufs_sys_ctrl_writel(host, 0x03300330, UFS_DEVICE_RESET_CTRL);
+
+	if (!IS_ERR(host->rst))
+		reset_control_deassert(host->rst);
+}
+
+static int ufs_hisi_link_startup_pre_change(struct ufs_hba *hba)
+{
+	int err;
+	uint32_t value;
+	uint32_t reg;
+
+	/* Unipro VS_mphy_disable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD0C1, 0x0), 0x1);
+	/* PA_HSSeries */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x156A, 0x0), 0x2);
+	/* MPHY CBRATESEL */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8114, 0x0), 0x1);
+	/* MPHY CBOVRCTRL2 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8121, 0x0), 0x2D);
+	/* MPHY CBOVRCTRL3 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8122, 0x0), 0x1);
+	/* Unipro VS_MphyCfgUpdt */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+	/* MPHY RXOVRCTRL4 rx0 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800D, 0x4), 0x58);
+	/* MPHY RXOVRCTRL4 rx1 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800D, 0x5), 0x58);
+	/* MPHY RXOVRCTRL5 rx0 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800E, 0x4), 0xB);
+	/* MPHY RXOVRCTRL5 rx1 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x800E, 0x5), 0xB);
+	/* MPHY RXSQCONTROL rx0 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8009, 0x4), 0x1);
+	/* MPHY RXSQCONTROL rx1 */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8009, 0x5), 0x1);
+	/* Unipro VS_MphyCfgUpdt */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x8113, 0x0), 0x1);
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+
+	/* Tactive RX */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008F, 0x4), 0x7);
+	/* Tactive RX */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008F, 0x5), 0x7);
+
+	/* Gear3 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0095, 0x4), 0x4F);
+	/* Gear3 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0095, 0x5), 0x4F);
+	/* Gear2 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0094, 0x4), 0x4F);
+	/* Gear2 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x0094, 0x5), 0x4F);
+	/* Gear1 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008B, 0x4), 0x4F);
+	/* Gear1 Synclength */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x008B, 0x5), 0x4F);
+	/* Thibernate Tx */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x000F, 0x0), 0x5);
+	/* Thibernate Tx */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x000F, 0x1), 0x5);
+
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD085, 0x0), 0x1);
+	/* Unipro VS_mphy_disable */
+	ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(0xD0C1, 0x0), &value);
+	if (value != 0x1)
+		dev_info(hba->dev,
+		    "Warring!!! Unipro VS_mphy_disable is 0x%x\n", value);
+
+	/* Unipro VS_mphy_disable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD0C1, 0x0), 0x0);
+	err = ufs_hisi_check_hibern8(hba);
+	if (err)
+		dev_err(hba->dev, "ufs_hisi_check_hibern8 error\n");
+
+	ufshcd_writel(hba, UFS_HCLKDIV_NORMAL_VALUE, UFS_REG_HCLKDIV);
+
+	/* disable auto H8 */
+	reg = ufshcd_readl(hba, REG_AUTO_HIBERNATE_IDLE_TIMER);
+	reg = reg & (~UFS_AHIT_AH8ITV_MASK);
+	ufshcd_writel(hba, reg, REG_AUTO_HIBERNATE_IDLE_TIMER);
+
+	/* Unipro PA_Local_TX_LCC_Enable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0x155E, 0x0), 0x0);
+	/* close Unipro VS_Mk2ExtnSupport */
+	ufshcd_dme_set(hba, UIC_ARG_MIB_SEL(0xD0AB, 0x0), 0x0);
+	ufshcd_dme_get(hba, UIC_ARG_MIB_SEL(0xD0AB, 0x0), &value);
+	if (value != 0) {
+		/* Ensure close success */
+		dev_info(hba->dev, "WARN: close VS_Mk2ExtnSupport failed\n");
+	}
+
+	return err;
+}
+
+static int ufs_hisi_link_startup_post_change(struct ufs_hba *hba)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	/* Unipro DL_AFC0CreditThreshold */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x2044), 0x0);
+	/* Unipro DL_TC0OutAckThreshold */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x2045), 0x0);
+	/* Unipro DL_TC0TXFCThreshold */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x2040), 0x9);
+
+	/* not bypass ufs clk gate */
+	ufs_sys_ctrl_clr_bits(host, MASK_UFS_CLK_GATE_BYPASS,
+						CLOCK_GATE_BYPASS);
+	ufs_sys_ctrl_clr_bits(host, MASK_UFS_SYSCRTL_BYPASS,
+						UFS_SYSCTRL);
+
+	/* select received symbol cnt */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd09a), 0x80000000);
+	 /* reset counter0 and enable */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd09c), 0x00000005);
+
+	return 0;
+}
+
+static int ufs_hi3660_link_startup_notify(struct ufs_hba *hba,
+					  enum ufs_notify_change_status status)
+{
+	int err = 0;
+
+	switch (status) {
+	case PRE_CHANGE:
+		err = ufs_hisi_link_startup_pre_change(hba);
+		break;
+	case POST_CHANGE:
+		err = ufs_hisi_link_startup_post_change(hba);
+		break;
+	default:
+		break;
+	}
+
+	return err;
+}
+
+struct ufs_hisi_dev_params {
+	u32 pwm_rx_gear; /* pwm rx gear to work in */
+	u32 pwm_tx_gear; /* pwm tx gear to work in */
+	u32 hs_rx_gear;  /* hs rx gear to work in */
+	u32 hs_tx_gear;  /* hs tx gear to work in */
+	u32 rx_lanes;    /* number of rx lanes */
+	u32 tx_lanes;    /* number of tx lanes */
+	u32 rx_pwr_pwm;  /* rx pwm working pwr */
+	u32 tx_pwr_pwm;  /* tx pwm working pwr */
+	u32 rx_pwr_hs;   /* rx hs working pwr */
+	u32 tx_pwr_hs;   /* tx hs working pwr */
+	u32 hs_rate;     /* rate A/B to work in HS */
+	u32 desired_working_mode;
+};
+
+static int ufs_hisi_get_pwr_dev_param(
+				    struct ufs_hisi_dev_params *hisi_param,
+				    struct ufs_pa_layer_attr *dev_max,
+				    struct ufs_pa_layer_attr *agreed_pwr)
+{
+	int min_hisi_gear;
+	int min_dev_gear;
+	bool is_dev_sup_hs = false;
+	bool is_hisi_max_hs = false;
+
+	if (dev_max->pwr_rx == FASTAUTO_MODE || dev_max->pwr_rx == FAST_MODE)
+		is_dev_sup_hs = true;
+
+	if (hisi_param->desired_working_mode == FAST) {
+		is_hisi_max_hs = true;
+		min_hisi_gear = min_t(u32, hisi_param->hs_rx_gear,
+				       hisi_param->hs_tx_gear);
+	} else {
+		min_hisi_gear = min_t(u32, hisi_param->pwm_rx_gear,
+				       hisi_param->pwm_tx_gear);
+	}
+
+	/*
+	 * device doesn't support HS but
+	 * hisi_param->desired_working_mode is HS,
+	 * thus device and hisi_param don't agree
+	 */
+	if (!is_dev_sup_hs && is_hisi_max_hs) {
+		pr_err("%s: device not support HS\n", __func__);
+		return -ENOTSUPP;
+	} else if (is_dev_sup_hs && is_hisi_max_hs) {
+		/*
+		 * since device supports HS, it supports FAST_MODE.
+		 * since hisi_param->desired_working_mode is also HS
+		 * then final decision (FAST/FASTAUTO) is done according
+		 * to hisi_params as it is the restricting factor
+		 */
+		agreed_pwr->pwr_rx = agreed_pwr->pwr_tx =
+			hisi_param->rx_pwr_hs;
+	} else {
+		/*
+		 * here hisi_param->desired_working_mode is PWM.
+		 * it doesn't matter whether device supports HS or PWM,
+		 * in both cases hisi_param->desired_working_mode will
+		 * determine the mode
+		 */
+		agreed_pwr->pwr_rx = agreed_pwr->pwr_tx =
+			hisi_param->rx_pwr_pwm;
+	}
+
+	/*
+	 * we would like tx to work in the minimum number of lanes
+	 * between device capability and vendor preferences.
+	 * the same decision will be made for rx
+	 */
+	agreed_pwr->lane_tx =
+		min_t(u32, dev_max->lane_tx, hisi_param->tx_lanes);
+	agreed_pwr->lane_rx =
+		min_t(u32, dev_max->lane_rx, hisi_param->rx_lanes);
+
+	/* device maximum gear is the minimum between device rx and tx gears */
+	min_dev_gear = min_t(u32, dev_max->gear_rx, dev_max->gear_tx);
+
+	/*
+	 * if both device capabilities and vendor pre-defined preferences are
+	 * both HS or both PWM then set the minimum gear to be the chosen
+	 * working gear.
+	 * if one is PWM and one is HS then the one that is PWM get to decide
+	 * what is the gear, as it is the one that also decided previously what
+	 * pwr the device will be configured to.
+	 */
+	if ((is_dev_sup_hs && is_hisi_max_hs) ||
+	    (!is_dev_sup_hs && !is_hisi_max_hs))
+		agreed_pwr->gear_rx = agreed_pwr->gear_tx =
+			min_t(u32, min_dev_gear, min_hisi_gear);
+	else
+		agreed_pwr->gear_rx = agreed_pwr->gear_tx = min_hisi_gear;
+
+	agreed_pwr->hs_rate = hisi_param->hs_rate;
+
+	pr_info("ufs final power mode: gear = %d, lane = %d, pwr = %d, rate = %d\n",
+		agreed_pwr->gear_rx, agreed_pwr->lane_rx, agreed_pwr->pwr_rx,
+		agreed_pwr->hs_rate);
+	return 0;
+}
+
+static void ufs_hisi_set_dev_cap(struct ufs_hisi_dev_params *hisi_param)
+{
+	hisi_param->rx_lanes = UFS_HISI_LIMIT_NUM_LANES_RX;
+	hisi_param->tx_lanes = UFS_HISI_LIMIT_NUM_LANES_TX;
+	hisi_param->hs_rx_gear = UFS_HISI_LIMIT_HSGEAR_RX;
+	hisi_param->hs_tx_gear = UFS_HISI_LIMIT_HSGEAR_TX;
+	hisi_param->pwm_rx_gear = UFS_HISI_LIMIT_PWMGEAR_RX;
+	hisi_param->pwm_tx_gear = UFS_HISI_LIMIT_PWMGEAR_TX;
+	hisi_param->rx_pwr_pwm = UFS_HISI_LIMIT_RX_PWR_PWM;
+	hisi_param->tx_pwr_pwm = UFS_HISI_LIMIT_TX_PWR_PWM;
+	hisi_param->rx_pwr_hs = UFS_HISI_LIMIT_RX_PWR_HS;
+	hisi_param->tx_pwr_hs = UFS_HISI_LIMIT_TX_PWR_HS;
+	hisi_param->hs_rate = UFS_HISI_LIMIT_HS_RATE;
+	hisi_param->desired_working_mode = UFS_HISI_LIMIT_DESIRED_MODE;
+}
+
+static void ufs_hisi_pwr_change_pre_change(struct ufs_hba *hba)
+{
+	/* update */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15A8), 0x1);
+	/* PA_TxSkip */
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x155c), 0x0);
+	/*PA_PWRModeUserData0 = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b0), 8191);
+	/*PA_PWRModeUserData1 = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b1), 65535);
+	/*PA_PWRModeUserData2 = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b2), 32767);
+	/*DME_FC0ProtectionTimeOutVal = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd041), 8191);
+	/*DME_TC0ReplayTimeOutVal = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd042), 65535);
+	/*DME_AFC0ReqTimeOutVal = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd043), 32767);
+	/*PA_PWRModeUserData3 = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b3), 8191);
+	/*PA_PWRModeUserData4 = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b4), 65535);
+	/*PA_PWRModeUserData5 = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0x15b5), 32767);
+	/*DME_FC1ProtectionTimeOutVal = 8191, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd044), 8191);
+	/*DME_TC1ReplayTimeOutVal = 65535, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd045), 65535);
+	/*DME_AFC1ReqTimeOutVal = 32767, default is 0*/
+	ufshcd_dme_set(hba, UIC_ARG_MIB(0xd046), 32767);
+}
+
+static int ufs_hi3660_pwr_change_notify(struct ufs_hba *hba,
+				       enum ufs_notify_change_status status,
+				       struct ufs_pa_layer_attr *dev_max_params,
+				       struct ufs_pa_layer_attr *dev_req_params)
+{
+	struct ufs_hisi_dev_params ufs_hisi_cap;
+	int ret = 0;
+
+	if (!dev_req_params) {
+		dev_err(hba->dev,
+			    "%s: incoming dev_req_params is NULL\n", __func__);
+		ret = -EINVAL;
+		goto out;
+	}
+
+	switch (status) {
+	case PRE_CHANGE:
+		ufs_hisi_set_dev_cap(&ufs_hisi_cap);
+		ret = ufs_hisi_get_pwr_dev_param(
+			&ufs_hisi_cap, dev_max_params, dev_req_params);
+		if (ret) {
+			dev_err(hba->dev,
+			    "%s: failed to determine capabilities\n", __func__);
+			goto out;
+		}
+
+		ufs_hisi_pwr_change_pre_change(hba);
+		break;
+	case POST_CHANGE:
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+out:
+	return ret;
+}
+
+static int ufs_hisi_suspend(struct ufs_hba *hba, enum ufs_pm_op pm_op)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	if (ufshcd_is_runtime_pm(pm_op))
+		return 0;
+
+	if (host->in_suspend) {
+		WARN_ON(1);
+		return 0;
+	}
+
+	ufs_sys_ctrl_clr_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+	udelay(10);
+	/* set ref_dig_clk override of PHY PCS to 0 */
+	ufs_sys_ctrl_writel(host, 0x00100000, UFS_DEVICE_RESET_CTRL);
+
+	host->in_suspend = true;
+
+	return 0;
+}
+
+static int ufs_hisi_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op)
+{
+	struct ufs_hisi_host *host = ufshcd_get_variant(hba);
+
+	if (!host->in_suspend)
+		return 0;
+
+	/* set ref_dig_clk override of PHY PCS to 1 */
+	ufs_sys_ctrl_writel(host, 0x00100010, UFS_DEVICE_RESET_CTRL);
+	udelay(10);
+	ufs_sys_ctrl_set_bits(host, BIT_SYSCTRL_REF_CLOCK_EN, PHY_CLK_CTRL);
+
+	host->in_suspend = false;
+	return 0;
+}
+
+static int ufs_hisi_get_resource(struct ufs_hisi_host *host)
+{
+	struct resource *mem_res;
+	struct device *dev = host->hba->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+
+	/* get resource of ufs sys ctrl */
+	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	host->ufs_sys_ctrl = devm_ioremap_resource(dev, mem_res);
+	if (IS_ERR(host->ufs_sys_ctrl))
+		return PTR_ERR(host->ufs_sys_ctrl);
+
+	return 0;
+}
+
+static void ufs_hisi_set_pm_lvl(struct ufs_hba *hba)
+{
+	hba->rpm_lvl = UFS_PM_LVL_1;
+	hba->spm_lvl = UFS_PM_LVL_3;
+}
+
+/**
+ * ufs_hisi_init_common
+ * @hba: host controller instance
+ */
+static int ufs_hisi_init_common(struct ufs_hba *hba)
+{
+	int err = 0;
+	struct device *dev = hba->dev;
+	struct ufs_hisi_host *host;
+
+	host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+	if (!host)
+		return -ENOMEM;
+
+	host->hba = hba;
+	ufshcd_set_variant(hba, host);
+
+	host->rst  = devm_reset_control_get(dev, "rst");
+
+	ufs_hisi_set_pm_lvl(hba);
+
+	err = ufs_hisi_get_resource(host);
+	if (err) {
+		ufshcd_set_variant(hba, NULL);
+		return err;
+	}
+
+	return 0;
+}
+
+static int ufs_hi3660_init(struct ufs_hba *hba)
+{
+	int ret = 0;
+	struct device *dev = hba->dev;
+
+	ret = ufs_hisi_init_common(hba);
+	if (ret) {
+		dev_err(dev, "%s: ufs common init fail\n", __func__);
+		return ret;
+	}
+
+	ufs_hi3660_clk_init(hba);
+
+	ufs_hi3660_soc_init(hba);
+
+	return 0;
+}
+
+static struct ufs_hba_variant_ops ufs_hba_hisi_vops = {
+	.name = "hi3660",
+	.init = ufs_hi3660_init,
+	.link_startup_notify = ufs_hi3660_link_startup_notify,
+	.pwr_change_notify = ufs_hi3660_pwr_change_notify,
+	.suspend = ufs_hisi_suspend,
+	.resume = ufs_hisi_resume,
+};
+
+static int ufs_hisi_probe(struct platform_device *pdev)
+{
+	return ufshcd_pltfrm_init(pdev, &ufs_hba_hisi_vops);
+}
+
+static int ufs_hisi_remove(struct platform_device *pdev)
+{
+	struct ufs_hba *hba =  platform_get_drvdata(pdev);
+
+	ufshcd_remove(hba);
+	return 0;
+}
+
+static const struct of_device_id ufs_hisi_of_match[] = {
+	{ .compatible = "hisilicon,hi3660-ufs" },
+	{},
+};
+
+MODULE_DEVICE_TABLE(of, ufs_hisi_of_match);
+
+static const struct dev_pm_ops ufs_hisi_pm_ops = {
+	.suspend	= ufshcd_pltfrm_suspend,
+	.resume		= ufshcd_pltfrm_resume,
+	.runtime_suspend = ufshcd_pltfrm_runtime_suspend,
+	.runtime_resume  = ufshcd_pltfrm_runtime_resume,
+	.runtime_idle    = ufshcd_pltfrm_runtime_idle,
+};
+
+static struct platform_driver ufs_hisi_pltform = {
+	.probe	= ufs_hisi_probe,
+	.remove	= ufs_hisi_remove,
+	.shutdown = ufshcd_pltfrm_shutdown,
+	.driver	= {
+		.name	= "ufshcd-hisi",
+		.pm	= &ufs_hisi_pm_ops,
+		.of_match_table = of_match_ptr(ufs_hisi_of_match),
+	},
+};
+module_platform_driver(ufs_hisi_pltform);
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("platform:ufshcd-hisi");
+MODULE_DESCRIPTION("HiSilicon Hixxxx UFS Driver");
diff --git a/drivers/scsi/ufs/ufs-hisi.h b/drivers/scsi/ufs/ufs-hisi.h
new file mode 100644
index 000000000000..3df9cd7acc29
--- /dev/null
+++ b/drivers/scsi/ufs/ufs-hisi.h
@@ -0,0 +1,115 @@
+/*
+ * Copyright (c) 2017, HiSilicon. All rights reserved.
+ *
+ * Released under the GPLv2 only.
+ * SPDX-License-Identifier: GPL-2.0
+ */
+
+#ifndef UFS_HISI_H_
+#define UFS_HISI_H_
+
+#define HBRN8_POLL_TOUT_MS	1000
+
+/*
+ * ufs sysctrl specific define
+ */
+#define PSW_POWER_CTRL	(0x04)
+#define PHY_ISO_EN	(0x08)
+#define HC_LP_CTRL	(0x0C)
+#define PHY_CLK_CTRL	(0x10)
+#define PSW_CLK_CTRL	(0x14)
+#define CLOCK_GATE_BYPASS	(0x18)
+#define RESET_CTRL_EN	(0x1C)
+#define UFS_SYSCTRL	(0x5C)
+#define UFS_DEVICE_RESET_CTRL	(0x60)
+
+#define BIT_UFS_PSW_ISO_CTRL		(1 << 16)
+#define BIT_UFS_PSW_MTCMOS_EN		(1 << 0)
+#define BIT_UFS_REFCLK_ISO_EN		(1 << 16)
+#define BIT_UFS_PHY_ISO_CTRL		(1 << 0)
+#define BIT_SYSCTRL_LP_ISOL_EN		(1 << 16)
+#define BIT_SYSCTRL_PWR_READY		(1 << 8)
+#define BIT_SYSCTRL_REF_CLOCK_EN	(1 << 24)
+#define MASK_SYSCTRL_REF_CLOCK_SEL	(0x3 << 8)
+#define MASK_SYSCTRL_CFG_CLOCK_FREQ	(0xFF)
+#define UFS_FREQ_CFG_CLK                (0x39)
+#define BIT_SYSCTRL_PSW_CLK_EN		(1 << 4)
+#define MASK_UFS_CLK_GATE_BYPASS	(0x3F)
+#define BIT_SYSCTRL_LP_RESET_N		(1 << 0)
+#define BIT_UFS_REFCLK_SRC_SEl		(1 << 0)
+#define MASK_UFS_SYSCRTL_BYPASS		(0x3F << 16)
+#define MASK_UFS_DEVICE_RESET		(0x1 << 16)
+#define BIT_UFS_DEVICE_RESET		(0x1)
+
+/*
+ * M-TX Configuration Attributes for Hixxxx
+ */
+#define MPHY_TX_FSM_STATE	0x41
+#define TX_FSM_HIBERN8	0x1
+
+/*
+ * Hixxxx UFS HC specific Registers
+ */
+enum {
+	UFS_REG_OCPTHRTL = 0xc0,
+	UFS_REG_OOCPR    = 0xc4,
+
+	UFS_REG_CDACFG   = 0xd0,
+	UFS_REG_CDATX1   = 0xd4,
+	UFS_REG_CDATX2   = 0xd8,
+	UFS_REG_CDARX1   = 0xdc,
+	UFS_REG_CDARX2   = 0xe0,
+	UFS_REG_CDASTA   = 0xe4,
+
+	UFS_REG_LBMCFG   = 0xf0,
+	UFS_REG_LBMSTA   = 0xf4,
+	UFS_REG_UFSMODE  = 0xf8,
+
+	UFS_REG_HCLKDIV  = 0xfc,
+};
+
+/* AHIT - Auto-Hibernate Idle Timer */
+#define UFS_AHIT_AH8ITV_MASK	0x3FF
+
+/* REG UFS_REG_OCPTHRTL definition */
+#define UFS_HCLKDIV_NORMAL_VALUE	0xE4
+
+/* vendor specific pre-defined parameters */
+#define SLOW	1
+#define FAST	2
+
+#define UFS_HISI_LIMIT_NUM_LANES_RX	2
+#define UFS_HISI_LIMIT_NUM_LANES_TX	2
+#define UFS_HISI_LIMIT_HSGEAR_RX	UFS_HS_G3
+#define UFS_HISI_LIMIT_HSGEAR_TX	UFS_HS_G3
+#define UFS_HISI_LIMIT_PWMGEAR_RX	UFS_PWM_G4
+#define UFS_HISI_LIMIT_PWMGEAR_TX	UFS_PWM_G4
+#define UFS_HISI_LIMIT_RX_PWR_PWM	SLOW_MODE
+#define UFS_HISI_LIMIT_TX_PWR_PWM	SLOW_MODE
+#define UFS_HISI_LIMIT_RX_PWR_HS	FAST_MODE
+#define UFS_HISI_LIMIT_TX_PWR_HS	FAST_MODE
+#define UFS_HISI_LIMIT_HS_RATE	PA_HS_MODE_B
+#define UFS_HISI_LIMIT_DESIRED_MODE	FAST
+
+struct ufs_hisi_host {
+	struct ufs_hba *hba;
+	void __iomem *ufs_sys_ctrl;
+
+	struct reset_control	*rst;
+
+	uint64_t caps;
+
+	bool in_suspend;
+};
+
+#define ufs_sys_ctrl_writel(host, val, reg)                                    \
+	writel((val), (host)->ufs_sys_ctrl + (reg))
+#define ufs_sys_ctrl_readl(host, reg) readl((host)->ufs_sys_ctrl + (reg))
+#define ufs_sys_ctrl_set_bits(host, mask, reg)                                 \
+	ufs_sys_ctrl_writel(                                                   \
+		(host), ((mask) | (ufs_sys_ctrl_readl((host), (reg)))), (reg))
+#define ufs_sys_ctrl_clr_bits(host, mask, reg)                                 \
+	ufs_sys_ctrl_writel((host),                                            \
+			    ((~(mask)) & (ufs_sys_ctrl_readl((host), (reg)))), \
+			    (reg))
+#endif /* UFS_HISI_H_ */
-- 
cgit v1.2.3


From 8ee94ec065293f65f4f386f4cdfac92d32c3e71f Mon Sep 17 00:00:00 2001
From: liwei <liwei213@huawei.com>
Date: Tue, 17 Jul 2018 17:36:57 +0800
Subject: scsi: ufs: dt-bindings: add document for hisi-ufs

add ufs node document for Hisilicon.

Signed-off-by: Li Wei <liwei213@huawei.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 Documentation/devicetree/bindings/ufs/ufs-hisi.txt | 41 ++++++++++++++++++++++
 .../devicetree/bindings/ufs/ufshcd-pltfrm.txt      | 10 ++++--
 2 files changed, 48 insertions(+), 3 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/ufs/ufs-hisi.txt

diff --git a/Documentation/devicetree/bindings/ufs/ufs-hisi.txt b/Documentation/devicetree/bindings/ufs/ufs-hisi.txt
new file mode 100644
index 000000000000..a48c44817367
--- /dev/null
+++ b/Documentation/devicetree/bindings/ufs/ufs-hisi.txt
@@ -0,0 +1,41 @@
+* Hisilicon Universal Flash Storage (UFS) Host Controller
+
+UFS nodes are defined to describe on-chip UFS hardware macro.
+Each UFS Host Controller should have its own node.
+
+Required properties:
+- compatible        : compatible list, contains one of the following -
+					"hisilicon,hi3660-ufs", "jedec,ufs-1.1" for hisi ufs
+					host controller present on Hi36xx chipset.
+- reg               : should contain UFS register address space & UFS SYS CTRL register address,
+- interrupt-parent  : interrupt device
+- interrupts        : interrupt number
+- clocks	        : List of phandle and clock specifier pairs
+- clock-names       : List of clock input name strings sorted in the same
+					order as the clocks property. "ref_clk", "phy_clk" is optional
+- freq-table-hz     : Array of <min max> operating frequencies stored in the same
+                      order as the clocks property. If this property is not
+                      defined or a value in the array is "0" then it is assumed
+                      that the frequency is set by the parent clock or a
+                      fixed rate clock source.
+- resets            : describe reset node register
+- reset-names       : reset node register, the "rst" corresponds to reset the whole UFS IP.
+
+Example:
+
+	ufs: ufs@ff3b0000 {
+		compatible = "hisilicon,hi3660-ufs", "jedec,ufs-1.1";
+		/* 0: HCI standard */
+		/* 1: UFS SYS CTRL */
+		reg = <0x0 0xff3b0000 0x0 0x1000>,
+			<0x0 0xff3b1000 0x0 0x1000>;
+		interrupt-parent = <&gic>;
+		interrupts = <GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>;
+		clocks = <&crg_ctrl HI3660_CLK_GATE_UFSIO_REF>,
+			<&crg_ctrl HI3660_CLK_GATE_UFSPHY_CFG>;
+		clock-names = "ref_clk", "phy_clk";
+		freq-table-hz = <0 0>, <0 0>;
+		/* offset: 0x84; bit: 12  */
+		resets = <&crg_rst 0x84 12>;
+		reset-names = "rst";
+	};
diff --git a/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt b/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
index c39dfef76a18..2df00524bd21 100644
--- a/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
+++ b/Documentation/devicetree/bindings/ufs/ufshcd-pltfrm.txt
@@ -41,6 +41,8 @@ Optional properties:
 -lanes-per-direction	: number of lanes available per direction - either 1 or 2.
 			  Note that it is assume same number of lanes is used both
 			  directions at once. If not specified, default is 2 lanes per direction.
+- resets            : reset node register
+- reset-names       : describe reset node register, the "rst" corresponds to reset the whole UFS IP.
 
 Note: If above properties are not defined it can be assumed that the supply
 regulators or clocks are always on.
@@ -61,9 +63,11 @@ Example:
 		vccq-max-microamp = 200000;
 		vccq2-max-microamp = 200000;
 
-		clocks = <&core 0>, <&ref 0>, <&iface 0>;
-		clock-names = "core_clk", "ref_clk", "iface_clk";
-		freq-table-hz = <100000000 200000000>, <0 0>, <0 0>;
+		clocks = <&core 0>, <&ref 0>, <&phy 0>, <&iface 0>;
+		clock-names = "core_clk", "ref_clk", "phy_clk", "iface_clk";
+		freq-table-hz = <100000000 200000000>, <0 0>, <0 0>, <0 0>;
+		resets = <&reset 0 1>;
+		reset-names = "rst";
 		phys = <&ufsphy1>;
 		phy-names = "ufsphy";
 	};
-- 
cgit v1.2.3


From 360249d2ae5aa7dd31a81db2da5152f0b8bfae47 Mon Sep 17 00:00:00 2001
From: liwei <liwei213@huawei.com>
Date: Tue, 17 Jul 2018 17:36:58 +0800
Subject: scsi: arm64: dts: add ufs dts node

arm64: dts: add ufs node for Hisilicon.

Signed-off-by: Li Wei <liwei213@huawei.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Acked-by: Wei Xu <xuwei5@hisilicon.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 arch/arm64/boot/dts/hisilicon/hi3660.dtsi | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
index 8d477dcbfa58..851190a719ea 100644
--- a/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hi3660.dtsi
@@ -1000,6 +1000,24 @@
 			reset-gpios = <&gpio11 1 0 >;
 		};
 
+		/* UFS */
+		ufs: ufs@ff3b0000 {
+			compatible = "hisilicon,hi3660-ufs", "jedec,ufs-1.1";
+			/* 0: HCI standard */
+			/* 1: UFS SYS CTRL */
+			reg = <0x0 0xff3b0000 0x0 0x1000>,
+				<0x0 0xff3b1000 0x0 0x1000>;
+			interrupt-parent = <&gic>;
+			interrupts = <GIC_SPI 278 IRQ_TYPE_LEVEL_HIGH>;
+			clocks = <&crg_ctrl HI3660_CLK_GATE_UFSIO_REF>,
+				<&crg_ctrl HI3660_CLK_GATE_UFSPHY_CFG>;
+			clock-names = "ref_clk", "phy_clk";
+			freq-table-hz = <0 0>, <0 0>;
+			/* offset: 0x84; bit: 12 */
+			resets = <&crg_rst 0x84 12>;
+			reset-names = "rst";
+		};
+
 		/* SD */
 		dwmmc1: dwmmc1@ff37f000 {
 			#address-cells = <1>;
-- 
cgit v1.2.3


From 7ee7ef24d02d1e3dfc33b30e4901be0a2b3847e8 Mon Sep 17 00:00:00 2001
From: liwei <liwei213@huawei.com>
Date: Tue, 17 Jul 2018 17:36:59 +0800
Subject: scsi: arm64: defconfig: enable configs for Hisilicon ufs

Signed-off-by: Li Wei <liwei213@huawei.com>
Signed-off-by: Zhangfei Gao <zhangfei.gao@linaro.org>
Signed-off-by: Guodong Xu <guodong.xu@linaro.org>
Tested-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 arch/arm64/configs/defconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 3cfa8ca26738..d233e50fe950 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -197,6 +197,7 @@ CONFIG_SCSI_HISI_SAS=y
 CONFIG_SCSI_HISI_SAS_PCI=y
 CONFIG_SCSI_UFSHCD=m
 CONFIG_SCSI_UFSHCD_PLATFORM=m
+CONFIG_SCSI_UFS_HISI=y
 CONFIG_SCSI_UFS_QCOM=m
 CONFIG_ATA=y
 CONFIG_SATA_AHCI=y
-- 
cgit v1.2.3


From db67befa3d90e54e3dfd1b48926c0d833d9feea7 Mon Sep 17 00:00:00 2001
From: Varun Prakash <varun@chelsio.com>
Date: Tue, 17 Jul 2018 19:55:26 +0530
Subject: scsi: csiostor: update ingress pack and pad boundary value

T5/T6 can have different pack and pad boundary value. This patch sets
packing boundary based on cache line size and PCI-E maximum payload size
and sets smallest padding boundary value.

Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/csiostor/csio_wr.c | 84 ++++++++++++++++++++++++++++++++++++++---
 1 file changed, 79 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/csiostor/csio_wr.c b/drivers/scsi/csiostor/csio_wr.c
index faa357b62c61..5022e82ccc4f 100644
--- a/drivers/scsi/csiostor/csio_wr.c
+++ b/drivers/scsi/csiostor/csio_wr.c
@@ -39,6 +39,7 @@
 #include <asm/page.h>
 #include <linux/cache.h>
 
+#include "t4_values.h"
 #include "csio_hw.h"
 #include "csio_wr.h"
 #include "csio_mb.h"
@@ -1309,8 +1310,11 @@ csio_wr_fixup_host_params(struct csio_hw *hw)
 	struct csio_sge *sge = &wrm->sge;
 	uint32_t clsz = L1_CACHE_BYTES;
 	uint32_t s_hps = PAGE_SHIFT - 10;
-	uint32_t ingpad = 0;
 	uint32_t stat_len = clsz > 64 ? 128 : 64;
+	u32 fl_align = clsz < 32 ? 32 : clsz;
+	u32 pack_align;
+	u32 ingpad, ingpack;
+	int pcie_cap;
 
 	csio_wr_reg32(hw, HOSTPAGESIZEPF0_V(s_hps) | HOSTPAGESIZEPF1_V(s_hps) |
 		      HOSTPAGESIZEPF2_V(s_hps) | HOSTPAGESIZEPF3_V(s_hps) |
@@ -1318,14 +1322,82 @@ csio_wr_fixup_host_params(struct csio_hw *hw)
 		      HOSTPAGESIZEPF6_V(s_hps) | HOSTPAGESIZEPF7_V(s_hps),
 		      SGE_HOST_PAGE_SIZE_A);
 
-	sge->csio_fl_align = clsz < 32 ? 32 : clsz;
-	ingpad = ilog2(sge->csio_fl_align) - 5;
+	/* T5 introduced the separation of the Free List Padding and
+	 * Packing Boundaries.  Thus, we can select a smaller Padding
+	 * Boundary to avoid uselessly chewing up PCIe Link and Memory
+	 * Bandwidth, and use a Packing Boundary which is large enough
+	 * to avoid false sharing between CPUs, etc.
+	 *
+	 * For the PCI Link, the smaller the Padding Boundary the
+	 * better.  For the Memory Controller, a smaller Padding
+	 * Boundary is better until we cross under the Memory Line
+	 * Size (the minimum unit of transfer to/from Memory).  If we
+	 * have a Padding Boundary which is smaller than the Memory
+	 * Line Size, that'll involve a Read-Modify-Write cycle on the
+	 * Memory Controller which is never good.
+	 */
+
+	/* We want the Packing Boundary to be based on the Cache Line
+	 * Size in order to help avoid False Sharing performance
+	 * issues between CPUs, etc.  We also want the Packing
+	 * Boundary to incorporate the PCI-E Maximum Payload Size.  We
+	 * get best performance when the Packing Boundary is a
+	 * multiple of the Maximum Payload Size.
+	 */
+	pack_align = fl_align;
+	pcie_cap = pci_find_capability(hw->pdev, PCI_CAP_ID_EXP);
+	if (pcie_cap) {
+		u32 mps, mps_log;
+		u16 devctl;
+
+		/* The PCIe Device Control Maximum Payload Size field
+		 * [bits 7:5] encodes sizes as powers of 2 starting at
+		 * 128 bytes.
+		 */
+		pci_read_config_word(hw->pdev,
+				     pcie_cap + PCI_EXP_DEVCTL,
+				     &devctl);
+		mps_log = ((devctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5) + 7;
+		mps = 1 << mps_log;
+		if (mps > pack_align)
+			pack_align = mps;
+	}
+
+	/* T5/T6 have a special interpretation of the "0"
+	 * value for the Packing Boundary.  This corresponds to 16
+	 * bytes instead of the expected 32 bytes.
+	 */
+	if (pack_align <= 16) {
+		ingpack = INGPACKBOUNDARY_16B_X;
+		fl_align = 16;
+	} else if (pack_align == 32) {
+		ingpack = INGPACKBOUNDARY_64B_X;
+		fl_align = 64;
+	} else {
+		u32 pack_align_log = fls(pack_align) - 1;
+
+		ingpack = pack_align_log - INGPACKBOUNDARY_SHIFT_X;
+		fl_align = pack_align;
+	}
+
+	/* Use the smallest Ingress Padding which isn't smaller than
+	 * the Memory Controller Read/Write Size.  We'll take that as
+	 * being 8 bytes since we don't know of any system with a
+	 * wider Memory Controller Bus Width.
+	 */
+	if (csio_is_t5(hw->pdev->device & CSIO_HW_CHIP_MASK))
+		ingpad = INGPADBOUNDARY_32B_X;
+	else
+		ingpad = T6_INGPADBOUNDARY_8B_X;
 
 	csio_set_reg_field(hw, SGE_CONTROL_A,
 			   INGPADBOUNDARY_V(INGPADBOUNDARY_M) |
 			   EGRSTATUSPAGESIZE_F,
 			   INGPADBOUNDARY_V(ingpad) |
 			   EGRSTATUSPAGESIZE_V(stat_len != 64));
+	csio_set_reg_field(hw, SGE_CONTROL2_A,
+			   INGPACKBOUNDARY_V(INGPACKBOUNDARY_M),
+			   INGPACKBOUNDARY_V(ingpack));
 
 	/* FL BUFFER SIZE#0 is Page size i,e already aligned to cache line */
 	csio_wr_reg32(hw, PAGE_SIZE, SGE_FL_BUFFER_SIZE0_A);
@@ -1337,14 +1409,16 @@ csio_wr_fixup_host_params(struct csio_hw *hw)
 	if (hw->flags & CSIO_HWF_USING_SOFT_PARAMS) {
 		csio_wr_reg32(hw,
 			(csio_rd_reg32(hw, SGE_FL_BUFFER_SIZE2_A) +
-			sge->csio_fl_align - 1) & ~(sge->csio_fl_align - 1),
+			fl_align - 1) & ~(fl_align - 1),
 			SGE_FL_BUFFER_SIZE2_A);
 		csio_wr_reg32(hw,
 			(csio_rd_reg32(hw, SGE_FL_BUFFER_SIZE3_A) +
-			sge->csio_fl_align - 1) & ~(sge->csio_fl_align - 1),
+			fl_align - 1) & ~(fl_align - 1),
 			SGE_FL_BUFFER_SIZE3_A);
 	}
 
+	sge->csio_fl_align = fl_align;
+
 	csio_wr_reg32(hw, HPZ0_V(PAGE_SHIFT - 12), ULP_RX_TDDP_PSZ_A);
 
 	/* default value of rx_dma_offset of the NIC driver */
-- 
cgit v1.2.3


From 4e32b2f48427ea57743e4bdf9765076133b565ca Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Wed, 18 Jul 2018 22:14:25 +0800
Subject: scsi: hisi_sas: Drop hisi_sas_slot_abort()

For some time now we have not used hisi_sas_slot_abort() to handle erroring
slots, apart from in archaic v1 hw.

As such, remove this function and associated code. For v1 hw, move error
handling to same scheme as other hw revisions, where we allow erroring
commands to timeout.

Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h       |  1 -
 drivers/scsi/hisi_sas/hisi_sas_main.c  | 35 ----------------------------------
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c |  5 +----
 3 files changed, 1 insertion(+), 40 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index beda41238285..0ff911531295 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -204,7 +204,6 @@ struct hisi_sas_slot {
 	int	ready;
 	void	*cmd_hdr;
 	dma_addr_t cmd_hdr_dma;
-	struct work_struct abort_slot;
 	struct timer_list internal_abort_timer;
 	bool is_internal;
 	struct hisi_sas_tmf_task *tmf;
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 781b2af483a2..ed671af1f6e8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -281,40 +281,6 @@ static void hisi_sas_task_prep_abort(struct hisi_hba *hisi_hba,
 			device_id, abort_flag, tag_to_abort);
 }
 
-/*
- * This function will issue an abort TMF regardless of whether the
- * task is in the sdev or not. Then it will do the task complete
- * cleanup and callbacks.
- */
-static void hisi_sas_slot_abort(struct work_struct *work)
-{
-	struct hisi_sas_slot *abort_slot =
-		container_of(work, struct hisi_sas_slot, abort_slot);
-	struct sas_task *task = abort_slot->task;
-	struct hisi_hba *hisi_hba = dev_to_hisi_hba(task->dev);
-	struct scsi_cmnd *cmnd = task->uldd_task;
-	struct hisi_sas_tmf_task tmf_task;
-	struct scsi_lun lun;
-	struct device *dev = hisi_hba->dev;
-	int tag = abort_slot->idx;
-
-	if (!(task->task_proto & SAS_PROTOCOL_SSP)) {
-		dev_err(dev, "cannot abort slot for non-ssp task\n");
-		goto out;
-	}
-
-	int_to_scsilun(cmnd->device->lun, &lun);
-	tmf_task.tmf = TMF_ABORT_TASK;
-	tmf_task.tag_of_task_to_be_managed = cpu_to_le16(tag);
-
-	hisi_sas_debug_issue_ssp_tmf(task->dev, lun.scsi_lun, &tmf_task);
-out:
-	/* Do cleanup for this task */
-	hisi_sas_slot_task_free(hisi_hba, task, abort_slot);
-	if (task->task_done)
-		task->task_done(task);
-}
-
 static int hisi_sas_task_prep(struct sas_task *task,
 			      struct hisi_sas_dq **dq_pointer,
 			      bool is_tmf, struct hisi_sas_tmf_task *tmf,
@@ -451,7 +417,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	slot->tmf = tmf;
 	slot->is_internal = is_tmf;
 	task->lldd_task = slot;
-	INIT_WORK(&slot->abort_slot, hisi_sas_slot_abort);
 
 	memset(slot->cmd_hdr, 0, sizeof(struct hisi_sas_cmd_hdr));
 	memset(hisi_sas_cmd_hdr_addr_mem(slot), 0, HISI_SAS_COMMAND_TABLE_SZ);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 32774427bbad..7dc68740eac9 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -1296,11 +1296,8 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba,
 		!(cmplt_hdr_data & CMPLT_HDR_RSPNS_XFRD_MSK)) {
 
 		slot_err_v1_hw(hisi_hba, task, slot);
-		if (unlikely(slot->abort)) {
-			queue_work(hisi_hba->wq, &slot->abort_slot);
-			/* immediately return and do not complete */
+		if (unlikely(slot->abort))
 			return ts->stat;
-		}
 		goto out;
 	}
 
-- 
cgit v1.2.3


From d9d51e0cf462cf12956cbc95b1fd55d90c7c9ac5 Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Wed, 18 Jul 2018 22:14:26 +0800
Subject: scsi: hisi_sas: tidy channel interrupt handler for v3 hw

The ISR of channel interrupt of v3 hw is a little long and messy. This
patch tidies it by relocating CHL_INT1 and CHL_INT2 handling to new
function separately.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 156 ++++++++++++++++-----------------
 1 file changed, 78 insertions(+), 78 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 4b7688a856af..d7c377448ac8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1333,11 +1333,83 @@ static const struct hisi_sas_hw_error port_axi_error[] = {
 	},
 };
 
-static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
+static void handle_chl_int1_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
-	struct hisi_hba *hisi_hba = p;
+	u32 irq_value = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT1);
+	u32 irq_msk = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT1_MSK);
 	struct device *dev = hisi_hba->dev;
+	int i;
+
+	irq_value &= ~irq_msk;
+	if (!irq_value)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(port_axi_error); i++) {
+		const struct hisi_sas_hw_error *error = &port_axi_error[i];
+
+		if (!(irq_value & error->irq_msk))
+			continue;
+
+		dev_err(dev, "%s error (phy%d 0x%x) found!\n",
+			error->msg, phy_no, irq_value);
+		queue_work(hisi_hba->wq, &hisi_hba->rst_work);
+	}
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT1, irq_value);
+}
+
+static void handle_chl_int2_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
+{
+	u32 irq_msk = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT2_MSK);
+	u32 irq_value = hisi_sas_phy_read32(hisi_hba, phy_no, CHL_INT2);
+	struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
 	struct pci_dev *pci_dev = hisi_hba->pci_dev;
+	struct device *dev = hisi_hba->dev;
+
+	irq_value &= ~irq_msk;
+	if (!irq_value)
+		return;
+
+	if (irq_value & BIT(CHL_INT2_SL_IDAF_TOUT_CONF_OFF)) {
+		dev_warn(dev, "phy%d identify timeout\n", phy_no);
+		hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+	}
+
+	if (irq_value & BIT(CHL_INT2_STP_LINK_TIMEOUT_OFF)) {
+		u32 reg_value = hisi_sas_phy_read32(hisi_hba, phy_no,
+				STP_LINK_TIMEOUT_STATE);
+
+		dev_warn(dev, "phy%d stp link timeout (0x%x)\n",
+			 phy_no, reg_value);
+		if (reg_value & BIT(4))
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+	}
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, irq_value);
+
+	if ((irq_value & BIT(CHL_INT2_RX_INVLD_DW_OFF)) &&
+	    (pci_dev->revision == 0x20)) {
+		u32 reg_value;
+		int rc;
+
+		rc = hisi_sas_read32_poll_timeout_atomic(
+				HILINK_ERR_DFX, reg_value,
+				!((reg_value >> 8) & BIT(phy_no)),
+				1000, 10000);
+		if (rc) {
+			disable_phy_v3_hw(hisi_hba, phy_no);
+			hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2,
+					     BIT(CHL_INT2_RX_INVLD_DW_OFF));
+			hisi_sas_phy_read32(hisi_hba, phy_no, ERR_CNT_INVLD_DW);
+			mdelay(1);
+			enable_phy_v3_hw(hisi_hba, phy_no);
+		}
+	}
+}
+
+static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
+{
+	struct hisi_hba *hisi_hba = p;
 	u32 irq_msk;
 	int phy_no = 0;
 
@@ -1347,84 +1419,12 @@ static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
 	while (irq_msk) {
 		u32 irq_value0 = hisi_sas_phy_read32(hisi_hba, phy_no,
 						     CHL_INT0);
-		u32 irq_value1 = hisi_sas_phy_read32(hisi_hba, phy_no,
-						     CHL_INT1);
-		u32 irq_value2 = hisi_sas_phy_read32(hisi_hba, phy_no,
-						     CHL_INT2);
-		u32 irq_msk1 = hisi_sas_phy_read32(hisi_hba, phy_no,
-							CHL_INT1_MSK);
-		u32 irq_msk2 = hisi_sas_phy_read32(hisi_hba, phy_no,
-							CHL_INT2_MSK);
-
-		irq_value1 &= ~irq_msk1;
-		irq_value2 &= ~irq_msk2;
-
-		if ((irq_msk & (4 << (phy_no * 4))) &&
-						irq_value1) {
-			int i;
-
-			for (i = 0; i < ARRAY_SIZE(port_axi_error); i++) {
-				const struct hisi_sas_hw_error *error =
-						&port_axi_error[i];
-
-				if (!(irq_value1 & error->irq_msk))
-					continue;
-
-				dev_err(dev, "%s error (phy%d 0x%x) found!\n",
-					error->msg, phy_no, irq_value1);
-				queue_work(hisi_hba->wq, &hisi_hba->rst_work);
-			}
-
-			hisi_sas_phy_write32(hisi_hba, phy_no,
-					     CHL_INT1, irq_value1);
-		}
 
-		if (irq_msk & (8 << (phy_no * 4)) && irq_value2) {
-			struct hisi_sas_phy *phy = &hisi_hba->phy[phy_no];
-
-			if (irq_value2 & BIT(CHL_INT2_SL_IDAF_TOUT_CONF_OFF)) {
-				dev_warn(dev, "phy%d identify timeout\n",
-							phy_no);
-				hisi_sas_notify_phy_event(phy,
-					HISI_PHYE_LINK_RESET);
-
-			}
+		if (irq_msk & (4 << (phy_no * 4)))
+			handle_chl_int1_v3_hw(hisi_hba, phy_no);
 
-			if (irq_value2 & BIT(CHL_INT2_STP_LINK_TIMEOUT_OFF)) {
-				u32 reg_value = hisi_sas_phy_read32(hisi_hba,
-						phy_no, STP_LINK_TIMEOUT_STATE);
-
-				dev_warn(dev, "phy%d stp link timeout (0x%x)\n",
-							phy_no, reg_value);
-				if (reg_value & BIT(4))
-					hisi_sas_notify_phy_event(phy,
-						HISI_PHYE_LINK_RESET);
-			}
-
-			hisi_sas_phy_write32(hisi_hba, phy_no,
-					     CHL_INT2, irq_value2);
-
-			if ((irq_value2 & BIT(CHL_INT2_RX_INVLD_DW_OFF)) &&
-			    (pci_dev->revision == 0x20)) {
-				u32 reg_value;
-				int rc;
-
-				rc = hisi_sas_read32_poll_timeout_atomic(
-					HILINK_ERR_DFX, reg_value,
-					!((reg_value >> 8) & BIT(phy_no)),
-					1000, 10000);
-				if (rc) {
-					disable_phy_v3_hw(hisi_hba, phy_no);
-					hisi_sas_phy_write32(hisi_hba, phy_no,
-						CHL_INT2,
-						BIT(CHL_INT2_RX_INVLD_DW_OFF));
-					hisi_sas_phy_read32(hisi_hba, phy_no,
-						ERR_CNT_INVLD_DW);
-					mdelay(1);
-					enable_phy_v3_hw(hisi_hba, phy_no);
-				}
-			}
-		}
+		if (irq_msk & (8 << (phy_no * 4)))
+			handle_chl_int2_v3_hw(hisi_hba, phy_no);
 
 		if (irq_msk & (2 << (phy_no * 4)) && irq_value0) {
 			hisi_sas_phy_write32(hisi_hba, phy_no,
-- 
cgit v1.2.3


From 25908cac84b2ea18d4609fc237d6135d0037041d Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Wed, 18 Jul 2018 22:14:27 +0800
Subject: scsi: hisi_sas: Fix the failure of recovering PHY from STP link
 timeout

There is an issue that link reset can't recover PHY when STP link timeout.
Because current process of enabling PHY for v3 hw will wait last
transmission done. The time of one transmission depends IO size, disk model
and so on. Normally, it should be shorter than 50ms. But the last
transmission could be never done for some abnormal scenarios, such as STP
link timeout.

This patch is to fix the issue. Check PHY status after starting process of
enabling PHY for 50ms. If the PHY is still active, we disable it forcibly
by PHY reset. Of course, we need to clear the PHY reset bit when enable
PHY.

Besides, the function disable_phy_v3_hw() should not be suitable to call in
interrupts for hilink bug for this 50ms delay. Then, we do link reset for
hilink bug directly. The change is that we don't clear the invalid dword
count register. This is better. Because we should not clear such error
count while not saved.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index d7c377448ac8..70a6aa2daba2 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -120,6 +120,8 @@
 #define PHY_CFG_ENA_MSK			(0x1 << PHY_CFG_ENA_OFF)
 #define PHY_CFG_DC_OPT_OFF		2
 #define PHY_CFG_DC_OPT_MSK		(0x1 << PHY_CFG_DC_OPT_OFF)
+#define PHY_CFG_PHY_RST_OFF		3
+#define PHY_CFG_PHY_RST_MSK		(0x1 << PHY_CFG_PHY_RST_OFF)
 #define PROG_PHY_LINK_RATE		(PORT_BASE + 0x8)
 #define PHY_CTRL			(PORT_BASE + 0x14)
 #define PHY_CTRL_RESET_OFF		0
@@ -760,15 +762,25 @@ static void enable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
 
 	cfg |= PHY_CFG_ENA_MSK;
+	cfg &= ~PHY_CFG_PHY_RST_MSK;
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
 }
 
 static void disable_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 {
 	u32 cfg = hisi_sas_phy_read32(hisi_hba, phy_no, PHY_CFG);
+	u32 state;
 
 	cfg &= ~PHY_CFG_ENA_MSK;
 	hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+
+	mdelay(50);
+
+	state = hisi_sas_read32(hisi_hba, PHY_STATE);
+	if (state & BIT(phy_no)) {
+		cfg |= PHY_CFG_PHY_RST_MSK;
+		hisi_sas_phy_write32(hisi_hba, phy_no, PHY_CFG, cfg);
+	}
 }
 
 static void start_phy_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
@@ -1385,8 +1397,6 @@ static void handle_chl_int2_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
 	}
 
-	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, irq_value);
-
 	if ((irq_value & BIT(CHL_INT2_RX_INVLD_DW_OFF)) &&
 	    (pci_dev->revision == 0x20)) {
 		u32 reg_value;
@@ -1396,15 +1406,11 @@ static void handle_chl_int2_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 				HILINK_ERR_DFX, reg_value,
 				!((reg_value >> 8) & BIT(phy_no)),
 				1000, 10000);
-		if (rc) {
-			disable_phy_v3_hw(hisi_hba, phy_no);
-			hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2,
-					     BIT(CHL_INT2_RX_INVLD_DW_OFF));
-			hisi_sas_phy_read32(hisi_hba, phy_no, ERR_CNT_INVLD_DW);
-			mdelay(1);
-			enable_phy_v3_hw(hisi_hba, phy_no);
-		}
+		if (rc)
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
 	}
+
+	hisi_sas_phy_write32(hisi_hba, phy_no, CHL_INT2, irq_value);
 }
 
 static irqreturn_t int_chnl_int_v3_hw(int irq_no, void *p)
-- 
cgit v1.2.3


From 4522204ab218a8c1f4d3901276deb0a61e7ac9c0 Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Wed, 18 Jul 2018 22:14:28 +0800
Subject: scsi: hisi_sas: tidy host controller reset function a bit

This patch tidies host controller reset function by putting some code to
two new functions, and exports these two functions out, so that they could
be used by FLR feature to be realised.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas.h      |  3 ++
 drivers/scsi/hisi_sas/hisi_sas_main.c | 61 ++++++++++++++++++++++-------------
 2 files changed, 42 insertions(+), 22 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 0ff911531295..6c7d2e201abe 100644
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -320,6 +320,7 @@ struct hisi_hba {
 	const struct hisi_sas_hw *hw;	/* Low level hw interface */
 	unsigned long sata_dev_bitmap[BITS_TO_LONGS(HISI_SAS_MAX_DEVICES)];
 	struct work_struct rst_work;
+	u32 phy_state;
 };
 
 /* Generic HW DMA host memory structures */
@@ -480,4 +481,6 @@ extern bool hisi_sas_notify_phy_event(struct hisi_sas_phy *phy,
 				enum hisi_sas_phy_event event);
 extern void hisi_sas_release_tasks(struct hisi_hba *hisi_hba);
 extern u8 hisi_sas_get_prog_phy_linkrate_mask(enum sas_linkrate max);
+extern void hisi_sas_controller_reset_prepare(struct hisi_hba *hisi_hba);
+extern void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba);
 #endif
diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index ed671af1f6e8..b0bcd142adc7 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -1309,22 +1309,12 @@ static void hisi_sas_terminate_stp_reject(struct hisi_hba *hisi_hba)
 	}
 }
 
-static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
+void hisi_sas_controller_reset_prepare(struct hisi_hba *hisi_hba)
 {
-	struct device *dev = hisi_hba->dev;
 	struct Scsi_Host *shost = hisi_hba->shost;
-	u32 old_state, state;
-	int rc;
-
-	if (!hisi_hba->hw->soft_reset)
-		return -1;
-
-	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
-		return -1;
 
 	down(&hisi_hba->sem);
-	dev_info(dev, "controller resetting...\n");
-	old_state = hisi_hba->hw->get_phys_state(hisi_hba);
+	hisi_hba->phy_state = hisi_hba->hw->get_phys_state(hisi_hba);
 
 	scsi_block_requests(shost);
 	hisi_hba->hw->wait_cmds_complete_timeout(hisi_hba, 100, 5000);
@@ -1333,15 +1323,13 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 		del_timer_sync(&hisi_hba->timer);
 
 	set_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
-	rc = hisi_hba->hw->soft_reset(hisi_hba);
-	if (rc) {
-		dev_warn(dev, "controller reset failed (%d)\n", rc);
-		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
-		up(&hisi_hba->sem);
-		scsi_unblock_requests(shost);
-		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
-		return rc;
-	}
+}
+EXPORT_SYMBOL_GPL(hisi_sas_controller_reset_prepare);
+
+void hisi_sas_controller_reset_done(struct hisi_hba *hisi_hba)
+{
+	struct Scsi_Host *shost = hisi_hba->shost;
+	u32 state;
 
 	/* Init and wait for PHYs to come up and all libsas event finished. */
 	hisi_hba->hw->phys_init(hisi_hba);
@@ -1357,7 +1345,36 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
 	clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
 
 	state = hisi_hba->hw->get_phys_state(hisi_hba);
-	hisi_sas_rescan_topology(hisi_hba, old_state, state);
+	hisi_sas_rescan_topology(hisi_hba, hisi_hba->phy_state, state);
+}
+EXPORT_SYMBOL_GPL(hisi_sas_controller_reset_done);
+
+static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+	struct Scsi_Host *shost = hisi_hba->shost;
+	int rc;
+
+	if (!hisi_hba->hw->soft_reset)
+		return -1;
+
+	if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
+		return -1;
+
+	dev_info(dev, "controller resetting...\n");
+	hisi_sas_controller_reset_prepare(hisi_hba);
+
+	rc = hisi_hba->hw->soft_reset(hisi_hba);
+	if (rc) {
+		dev_warn(dev, "controller reset failed (%d)\n", rc);
+		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+		up(&hisi_hba->sem);
+		scsi_unblock_requests(shost);
+		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+		return rc;
+	}
+
+	hisi_sas_controller_reset_done(hisi_hba);
 	dev_info(dev, "controller reset complete\n");
 
 	return 0;
-- 
cgit v1.2.3


From e8ce775e516957a8eb79890c4051796daa4c6f4b Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Wed, 18 Jul 2018 22:14:29 +0800
Subject: scsi: hisi_sas: relocate some common code for v3 hw

Much code of PM suspend function also exists in soft reset function. This
is not concise. So, this patch relocates the common code of these two
functions to a separate function.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 50 ++++++++++++++++++----------------
 1 file changed, 27 insertions(+), 23 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 70a6aa2daba2..357784336b8e 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -210,6 +210,8 @@
 
 #define AXI_MASTER_CFG_BASE		(0x5000)
 #define AM_CTRL_GLOBAL			(0x0)
+#define AM_CTRL_SHUTDOWN_REQ_OFF	0
+#define AM_CTRL_SHUTDOWN_REQ_MSK	(0x1 << AM_CTRL_SHUTDOWN_REQ_OFF)
 #define AM_CURR_TRANS_RETURN	(0x150)
 
 #define AM_CFG_MAX_TRANS		(0x5010)
@@ -1976,11 +1978,11 @@ static void phy_get_events_v3_hw(struct hisi_hba *hisi_hba, int phy_no)
 
 }
 
-static int soft_reset_v3_hw(struct hisi_hba *hisi_hba)
+static int disable_host_v3_hw(struct hisi_hba *hisi_hba)
 {
 	struct device *dev = hisi_hba->dev;
+	u32 status, reg_val;
 	int rc;
-	u32 status;
 
 	interrupt_disable_v3_hw(hisi_hba);
 	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0x0);
@@ -1990,14 +1992,32 @@ static int soft_reset_v3_hw(struct hisi_hba *hisi_hba)
 
 	mdelay(10);
 
-	hisi_sas_write32(hisi_hba, AXI_MASTER_CFG_BASE + AM_CTRL_GLOBAL, 0x1);
+	reg_val = hisi_sas_read32(hisi_hba, AXI_MASTER_CFG_BASE +
+				  AM_CTRL_GLOBAL);
+	reg_val |= AM_CTRL_SHUTDOWN_REQ_MSK;
+	hisi_sas_write32(hisi_hba, AXI_MASTER_CFG_BASE +
+			 AM_CTRL_GLOBAL, reg_val);
 
 	/* wait until bus idle */
 	rc = hisi_sas_read32_poll_timeout(AXI_MASTER_CFG_BASE +
 					  AM_CURR_TRANS_RETURN, status,
 					  status == 0x3, 10, 100);
 	if (rc) {
-		dev_err(dev, "axi bus is not idle, rc = %d\n", rc);
+		dev_err(dev, "axi bus is not idle, rc=%d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static int soft_reset_v3_hw(struct hisi_hba *hisi_hba)
+{
+	struct device *dev = hisi_hba->dev;
+	int rc;
+
+	rc = disable_host_v3_hw(hisi_hba);
+	if (rc) {
+		dev_err(dev, "soft reset: disable host failed rc=%d\n", rc);
 		return rc;
 	}
 
@@ -2456,9 +2476,8 @@ static int hisi_sas_v3_suspend(struct pci_dev *pdev, pm_message_t state)
 	struct hisi_hba *hisi_hba = sha->lldd_ha;
 	struct device *dev = hisi_hba->dev;
 	struct Scsi_Host *shost = hisi_hba->shost;
-	u32 device_state, status;
+	u32 device_state;
 	int rc;
-	u32 reg_val;
 
 	if (!pdev->pm_cap) {
 		dev_err(dev, "PCI PM not supported\n");
@@ -2471,25 +2490,10 @@ static int hisi_sas_v3_suspend(struct pci_dev *pdev, pm_message_t state)
 	scsi_block_requests(shost);
 	set_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 	flush_workqueue(hisi_hba->wq);
-	/* disable DQ/PHY/bus */
-	interrupt_disable_v3_hw(hisi_hba);
-	hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, 0x0);
-	hisi_sas_kill_tasklets(hisi_hba);
 
-	hisi_sas_stop_phys(hisi_hba);
-
-	reg_val = hisi_sas_read32(hisi_hba, AXI_MASTER_CFG_BASE +
-		AM_CTRL_GLOBAL);
-	reg_val |= 0x1;
-	hisi_sas_write32(hisi_hba, AXI_MASTER_CFG_BASE +
-		AM_CTRL_GLOBAL, reg_val);
-
-	/* wait until bus idle */
-	rc = hisi_sas_read32_poll_timeout(AXI_MASTER_CFG_BASE +
-					  AM_CURR_TRANS_RETURN, status,
-					  status == 0x3, 10, 100);
+	rc = disable_host_v3_hw(hisi_hba);
 	if (rc) {
-		dev_err(dev, "axi bus is not idle, rc = %d\n", rc);
+		dev_err(dev, "PM suspend: disable host failed rc=%d\n", rc);
 		clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
 		clear_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
 		scsi_unblock_requests(shost);
-- 
cgit v1.2.3


From e5ea48014adcb030b9d92743e87fbbcbbb2a1d70 Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Wed, 18 Jul 2018 22:14:30 +0800
Subject: scsi: hisi_sas: Implement handlers of PCIe FLR for v3 hw

This patch implements handlers of PCIe FLR for v3 hw, reset_prepare() and
reset_done().

User can issue FLR through sysfs interface, as v3 hw support PCIe FLR.
Then if we don't implement these two handlers, our SAS controller will not
work after executing FLR.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 37 ++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 357784336b8e..3d20fcf38fdf 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -2465,6 +2465,41 @@ static pci_ers_result_t hisi_sas_slot_reset_v3_hw(struct pci_dev *pdev)
 	return PCI_ERS_RESULT_DISCONNECT;
 }
 
+static void hisi_sas_reset_prepare_v3_hw(struct pci_dev *pdev)
+{
+	struct sas_ha_struct *sha = pci_get_drvdata(pdev);
+	struct hisi_hba *hisi_hba = sha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
+	int rc;
+
+	dev_info(dev, "FLR prepare\n");
+	set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags);
+	hisi_sas_controller_reset_prepare(hisi_hba);
+
+	rc = disable_host_v3_hw(hisi_hba);
+	if (rc)
+		dev_err(dev, "FLR: disable host failed rc=%d\n", rc);
+}
+
+static void hisi_sas_reset_done_v3_hw(struct pci_dev *pdev)
+{
+	struct sas_ha_struct *sha = pci_get_drvdata(pdev);
+	struct hisi_hba *hisi_hba = sha->lldd_ha;
+	struct device *dev = hisi_hba->dev;
+	int rc;
+
+	hisi_sas_init_mem(hisi_hba);
+
+	rc = hw_init_v3_hw(hisi_hba);
+	if (rc) {
+		dev_err(dev, "FLR: hw init failed rc=%d\n", rc);
+		return;
+	}
+
+	hisi_sas_controller_reset_done(hisi_hba);
+	dev_info(dev, "FLR done\n");
+}
+
 enum {
 	/* instances of the controller */
 	hip08,
@@ -2556,6 +2591,8 @@ static const struct pci_error_handlers hisi_sas_err_handler = {
 	.error_detected	= hisi_sas_error_detected_v3_hw,
 	.mmio_enabled	= hisi_sas_mmio_enabled_v3_hw,
 	.slot_reset	= hisi_sas_slot_reset_v3_hw,
+	.reset_prepare	= hisi_sas_reset_prepare_v3_hw,
+	.reset_done	= hisi_sas_reset_done_v3_hw,
 };
 
 static struct pci_driver sas_v3_pci_driver = {
-- 
cgit v1.2.3


From 6cca51ee0aa2540d648ff8698c3889330d897f27 Mon Sep 17 00:00:00 2001
From: Xiang Chen <chenxiang66@hisilicon.com>
Date: Wed, 18 Jul 2018 22:14:31 +0800
Subject: scsi: hisi_sas: Tidy hisi_sas_task_prep()

To decrease the usage of spinlock during delivery IO, relocate some code in
hisi_sas_task_prep().

Also an invalid comment is removed.

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index b0bcd142adc7..432a38a118b1 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -296,8 +296,8 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	struct device *dev = hisi_hba->dev;
 	int dlvry_queue_slot, dlvry_queue, rc, slot_idx;
 	int n_elem = 0, n_elem_req = 0, n_elem_resp = 0;
-	unsigned long flags, flags_dq;
 	struct hisi_sas_dq *dq;
+	unsigned long flags;
 	int wr_q_index;
 
 	if (!sas_port) {
@@ -393,16 +393,17 @@ static int hisi_sas_task_prep(struct sas_task *task,
 
 	slot = &hisi_hba->slot_info[slot_idx];
 
-	spin_lock_irqsave(&dq->lock, flags_dq);
+	spin_lock_irqsave(&dq->lock, flags);
 	wr_q_index = hisi_hba->hw->get_free_slot(hisi_hba, dq);
 	if (wr_q_index < 0) {
-		spin_unlock_irqrestore(&dq->lock, flags_dq);
+		spin_unlock_irqrestore(&dq->lock, flags);
 		rc = -EAGAIN;
 		goto err_out_tag;
 	}
 
 	list_add_tail(&slot->delivery, &dq->list);
-	spin_unlock_irqrestore(&dq->lock, flags_dq);
+	list_add_tail(&slot->entry, &sas_dev->list);
+	spin_unlock_irqrestore(&dq->lock, flags);
 
 	dlvry_queue = dq->id;
 	dlvry_queue_slot = wr_q_index;
@@ -440,9 +441,6 @@ static int hisi_sas_task_prep(struct sas_task *task,
 		break;
 	}
 
-	spin_lock_irqsave(&dq->lock, flags);
-	list_add_tail(&slot->entry, &sas_dev->list);
-	spin_unlock_irqrestore(&dq->lock, flags);
 	spin_lock_irqsave(&task->task_state_lock, flags);
 	task->task_state_flags |= SAS_TASK_AT_INITIATOR;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
@@ -818,7 +816,6 @@ static void hisi_sas_do_release_task(struct hisi_hba *hisi_hba, struct sas_task
 	hisi_sas_slot_task_free(hisi_hba, task, slot);
 }
 
-/* hisi_hba.lock should be locked */
 static void hisi_sas_release_task(struct hisi_hba *hisi_hba,
 			struct domain_device *device)
 {
-- 
cgit v1.2.3


From 1c09b663168bb5fd8562234976b76115f2aebe91 Mon Sep 17 00:00:00 2001
From: Xiaofei Tan <tanxiaofei@huawei.com>
Date: Wed, 18 Jul 2018 22:14:32 +0800
Subject: scsi: hisi_sas: add memory barrier in task delivery function

In task start delivery function, we need to add a memory barrier to prevent
re-ordering of reading memory by hardware. Because the slot data is set in
task prepare function and it could be running in another CPU.

This patch adds an memory barrier after s->ready is read in the task start
delivery function, and uses WRITE_ONCE() in the places where s->ready is
set to ensure that the compiler does not re-order.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_main.c  |  4 ++--
 drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 15 ++++++++++-----
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 15 ++++++++++-----
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 15 ++++++++++-----
 4 files changed, 32 insertions(+), 17 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 432a38a118b1..a4e2e6aa9a6b 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -446,7 +446,7 @@ static int hisi_sas_task_prep(struct sas_task *task,
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
 	++(*pass);
-	slot->ready = 1;
+	WRITE_ONCE(slot->ready, 1);
 
 	return 0;
 
@@ -1749,7 +1749,7 @@ hisi_sas_internal_abort_task_exec(struct hisi_hba *hisi_hba, int device_id,
 	task->task_state_flags |= SAS_TASK_AT_INITIATOR;
 	spin_unlock_irqrestore(&task->task_state_lock, flags);
 
-	slot->ready = 1;
+	WRITE_ONCE(slot->ready, 1);
 	/* send abort command to the chip */
 	spin_lock_irqsave(&dq->lock, flags);
 	list_add_tail(&slot->entry, &sas_dev->list);
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
index 7dc68740eac9..8f60f0e04599 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c
@@ -903,23 +903,28 @@ get_free_slot_v1_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 static void start_delivery_v1_hw(struct hisi_sas_dq *dq)
 {
 	struct hisi_hba *hisi_hba = dq->hisi_hba;
-	struct hisi_sas_slot *s, *s1;
+	struct hisi_sas_slot *s, *s1, *s2 = NULL;
 	struct list_head *dq_list;
 	int dlvry_queue = dq->id;
-	int wp, count = 0;
+	int wp;
 
 	dq_list = &dq->list;
 	list_for_each_entry_safe(s, s1, &dq->list, delivery) {
 		if (!s->ready)
 			break;
-		count++;
-		wp = (s->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+		s2 = s;
 		list_del(&s->delivery);
 	}
 
-	if (!count)
+	if (!s2)
 		return;
 
+	/*
+	 * Ensure that memories for slots built on other CPUs is observed.
+	 */
+	smp_rmb();
+	wp = (s2->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14), wp);
 }
 
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 159576e560d7..5a3d6a775427 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -1665,23 +1665,28 @@ get_free_slot_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 static void start_delivery_v2_hw(struct hisi_sas_dq *dq)
 {
 	struct hisi_hba *hisi_hba = dq->hisi_hba;
-	struct hisi_sas_slot *s, *s1;
+	struct hisi_sas_slot *s, *s1, *s2 = NULL;
 	struct list_head *dq_list;
 	int dlvry_queue = dq->id;
-	int wp, count = 0;
+	int wp;
 
 	dq_list = &dq->list;
 	list_for_each_entry_safe(s, s1, &dq->list, delivery) {
 		if (!s->ready)
 			break;
-		count++;
-		wp = (s->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+		s2 = s;
 		list_del(&s->delivery);
 	}
 
-	if (!count)
+	if (!s2)
 		return;
 
+	/*
+	 * Ensure that memories for slots built on other CPUs is observed.
+	 */
+	smp_rmb();
+	wp = (s2->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14), wp);
 }
 
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 3d20fcf38fdf..70e22993ef05 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -882,23 +882,28 @@ get_free_slot_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_dq *dq)
 static void start_delivery_v3_hw(struct hisi_sas_dq *dq)
 {
 	struct hisi_hba *hisi_hba = dq->hisi_hba;
-	struct hisi_sas_slot *s, *s1;
+	struct hisi_sas_slot *s, *s1, *s2 = NULL;
 	struct list_head *dq_list;
 	int dlvry_queue = dq->id;
-	int wp, count = 0;
+	int wp;
 
 	dq_list = &dq->list;
 	list_for_each_entry_safe(s, s1, &dq->list, delivery) {
 		if (!s->ready)
 			break;
-		count++;
-		wp = (s->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+		s2 = s;
 		list_del(&s->delivery);
 	}
 
-	if (!count)
+	if (!s2)
 		return;
 
+	/*
+	 * Ensure that memories for slots built on other CPUs is observed.
+	 */
+	smp_rmb();
+	wp = (s2->dlvry_queue_slot + 1) % HISI_SAS_QUEUE_SLOTS;
+
 	hisi_sas_write32(hisi_hba, DLVRY_Q_0_WR_PTR + (dlvry_queue * 0x14), wp);
 }
 
-- 
cgit v1.2.3


From f4e34f2a5dd9c0db19baad3f015c3abd5f2e0343 Mon Sep 17 00:00:00 2001
From: Xiang Chen <chenxiang66@hisilicon.com>
Date: Wed, 18 Jul 2018 22:14:33 +0800
Subject: scsi: hisi_sas: Add SATA FIS check for v3 hw

Add a check ERR bit of status to decide whether there is something wrong
with initial register-D2H FIS. If error exist, PHY link reset the channel
to restart OOB.

Directly call work HISI_PHYE_LINK_RESET replacing disable_phy_vx_hw() and
enable_phy_vx_hw().

Signed-off-by: Xiang Chen <chenxiang66@hisilicon.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/hisi_sas/hisi_sas_v2_hw.c |  3 +--
 drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 10 ++++++++++
 2 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
index 5a3d6a775427..9c5c5a601332 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c
@@ -3240,8 +3240,7 @@ static irqreturn_t sata_int_v2_hw(int irq_no, void *p)
 	if (fis->status & ATA_ERR) {
 		dev_warn(dev, "sata int: phy%d FIS status: 0x%x\n", phy_no,
 				fis->status);
-		disable_phy_v2_hw(hisi_hba, phy_no);
-		enable_phy_v2_hw(hisi_hba, phy_no);
+		hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
 		res = IRQ_NONE;
 		goto end;
 	}
diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
index 70e22993ef05..08b503e274b8 100644
--- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c
@@ -1191,6 +1191,16 @@ static irqreturn_t phy_up_v3_hw(int phy_no, struct hisi_hba *hisi_hba)
 		dev_info(dev, "phyup: phy%d link_rate=%d(sata)\n", phy_no, link_rate);
 		initial_fis = &hisi_hba->initial_fis[phy_no];
 		fis = &initial_fis->fis;
+
+		/* check ERR bit of Status Register */
+		if (fis->status & ATA_ERR) {
+			dev_warn(dev, "sata int: phy%d FIS status: 0x%x\n",
+				 phy_no, fis->status);
+			hisi_sas_notify_phy_event(phy, HISI_PHYE_LINK_RESET);
+			res = IRQ_NONE;
+			goto end;
+		}
+
 		sas_phy->oob_mode = SATA_OOB_MODE;
 		attached_sas_addr[0] = 0x50;
 		attached_sas_addr[7] = phy_no;
-- 
cgit v1.2.3


From be0e16ce7c3bf9855f1ef5ae46cf889e1784ddea Mon Sep 17 00:00:00 2001
From: "K. Y. Srinivasan" <kys@microsoft.com>
Date: Fri, 20 Jul 2018 03:50:09 +0000
Subject: x86/hyper-v: Fix wrong merge conflict resolution

When the mapping betwween the Linux notion of CPU ID to the hypervisor's
notion of CPU ID is not initialized, IPI must fall back to the
non-enlightened path.

The recent merge of upstream changes into the hyperv branch resolved a
merge conflict wronly by returning success in that case, which results in
the IPI not being sent at all. Fix it up.

Fixes: 8f63e9230dec ("Merge branch 'x86/urgent' into x86/hyperv")
Reported-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: gregkh@linuxfoundation.org
Cc: devel@linuxdriverproject.org
Cc: olaf@aepfle.de
Cc: apw@canonical.com
Cc: jasowang@redhat.com
Cc: hpa@zytor.com
Cc: sthemmin@microsoft.com
Cc: Michael.H.Kelley@microsoft.com
Cc: vkuznets@redhat.com
Link: https://lkml.kernel.org/r/20180720035009.3995-1-kys@linuxonhyperv.com
---
 arch/x86/hyperv/hv_apic.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 0c3c9f8fee77..5b0f613428c2 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -168,7 +168,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector)
 	for_each_cpu(cur_cpu, mask) {
 		vcpu = hv_cpu_number_to_vp_number(cur_cpu);
 		if (vcpu == VP_INVAL)
-			return true;
+			return false;
 
 		/*
 		 * This particular version of the IPI hypercall can
-- 
cgit v1.2.3


From b2b7d986a89b6c94b1331a909de1217214fb08c1 Mon Sep 17 00:00:00 2001
From: Jiang Biao <jiang.biao2@zte.com.cn>
Date: Fri, 20 Jul 2018 08:06:31 +0800
Subject: x86/pti: Check the return value of pti_user_pagetable_walk_p4d()

pti_user_pagetable_walk_p4d() can return NULL, so the return value should
be checked to prevent a NULL pointer dereference.

Add the check and a warning when the P4D allocation fails.

Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: dave.hansen@linux.intel.com
Cc: luto@kernel.org
Cc: hpa@zytor.com
Cc: albcamus@gmail.com
Cc: zhong.weidong@zte.com.cn
Link: https://lkml.kernel.org/r/1532045192-49622-1-git-send-email-jiang.biao2@zte.com.cn
---
 arch/x86/mm/pti.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 7b1c85759005..001ee6b0619e 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -176,7 +176,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 
 	if (pgd_none(*pgd)) {
 		unsigned long new_p4d_page = __get_free_page(gfp);
-		if (!new_p4d_page)
+		if (WARN_ON_ONCE(!new_p4d_page))
 			return NULL;
 
 		set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
@@ -195,9 +195,13 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
 static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-	p4d_t *p4d = pti_user_pagetable_walk_p4d(address);
+	p4d_t *p4d;
 	pud_t *pud;
 
+	p4d = pti_user_pagetable_walk_p4d(address);
+	if (!p4d)
+		return NULL;
+
 	BUILD_BUG_ON(p4d_large(*p4d) != 0);
 	if (p4d_none(*p4d)) {
 		unsigned long new_pud_page = __get_free_page(gfp);
@@ -359,6 +363,9 @@ static void __init pti_clone_p4d(unsigned long addr)
 	pgd_t *kernel_pgd;
 
 	user_p4d = pti_user_pagetable_walk_p4d(addr);
+	if (!user_p4d)
+		return;
+
 	kernel_pgd = pgd_offset_k(addr);
 	kernel_p4d = p4d_offset(kernel_pgd, addr);
 	*user_p4d = *kernel_p4d;
-- 
cgit v1.2.3


From 8c934e01a7ce685d98e970880f5941d79272c654 Mon Sep 17 00:00:00 2001
From: Jiang Biao <jiang.biao2@zte.com.cn>
Date: Fri, 20 Jul 2018 08:06:32 +0800
Subject: x86/pti: Check the return value of pti_user_pagetable_walk_pmd()

pti_user_pagetable_walk_pmd() can return NULL, so the return value should
be checked to prevent a NULL pointer dereference.

Add the check and a warning when the PMD allocation fails.

Signed-off-by: Jiang Biao <jiang.biao2@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: dave.hansen@linux.intel.com
Cc: luto@kernel.org
Cc: hpa@zytor.com
Cc: albcamus@gmail.com
Cc: zhong.weidong@zte.com.cn
Link: https://lkml.kernel.org/r/1532045192-49622-2-git-send-email-jiang.biao2@zte.com.cn
---
 arch/x86/mm/pti.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 001ee6b0619e..bcf35dac1920 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -205,7 +205,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	BUILD_BUG_ON(p4d_large(*p4d) != 0);
 	if (p4d_none(*p4d)) {
 		unsigned long new_pud_page = __get_free_page(gfp);
-		if (!new_pud_page)
+		if (WARN_ON_ONCE(!new_pud_page))
 			return NULL;
 
 		set_p4d(p4d, __p4d(_KERNPG_TABLE | __pa(new_pud_page)));
@@ -219,7 +219,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	}
 	if (pud_none(*pud)) {
 		unsigned long new_pmd_page = __get_free_page(gfp);
-		if (!new_pmd_page)
+		if (WARN_ON_ONCE(!new_pmd_page))
 			return NULL;
 
 		set_pud(pud, __pud(_KERNPG_TABLE | __pa(new_pmd_page)));
@@ -241,9 +241,13 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 {
 	gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
-	pmd_t *pmd = pti_user_pagetable_walk_pmd(address);
+	pmd_t *pmd;
 	pte_t *pte;
 
+	pmd = pti_user_pagetable_walk_pmd(address);
+	if (!pmd)
+		return NULL;
+
 	/* We can't do anything sensible if we hit a large mapping. */
 	if (pmd_large(*pmd)) {
 		WARN_ON(1);
-- 
cgit v1.2.3


From 3fd8093b41e745448ffeb0a0d3becc2cd1f9d7ad Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 10 Jul 2018 09:22:52 -0500
Subject: crypto: dh - fix memory leak
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In case memory resources for *base* were allocated, release them
before return.

Addresses-Coverity-ID: 1471702 ("Resource leak")
Fixes: e3fe0ae12962 ("crypto: dh - add public key verification test")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Stephan Müller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/dh.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crypto/dh.c b/crypto/dh.c
index 8f79269db2b7..09a44de4209d 100644
--- a/crypto/dh.c
+++ b/crypto/dh.c
@@ -174,7 +174,7 @@ static int dh_compute_value(struct kpp_request *req)
 		}
 		ret = dh_is_pubkey_valid(ctx, base);
 		if (ret)
-			goto err_free_val;
+			goto err_free_base;
 	} else {
 		base = ctx->g;
 	}
-- 
cgit v1.2.3


From cf862cbc831982a27f14a08adf82ad9ca8d86205 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Tue, 10 Jul 2018 17:56:33 +0200
Subject: crypto: drbg - eliminate constant reinitialization of SGL

The CTR DRBG requires two SGLs pointing to input/output buffers for the
CTR AES operation. The used SGLs always have only one entry. Thus, the
SGL can be initialized during allocation time, preventing a
re-initialization of the SGLs during each call.

The performance is increased by about 1 to 3 percent depending on the
size of the requested buffer size.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/drbg.c         | 11 +++++++----
 include/crypto/drbg.h |  1 +
 2 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/crypto/drbg.c b/crypto/drbg.c
index 466a112a4446..ee302fd229ad 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -1715,6 +1715,9 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg)
 	drbg->outscratchpad = (u8 *)PTR_ALIGN(drbg->outscratchpadbuf,
 					      alignmask + 1);
 
+	sg_init_table(&drbg->sg_in, 1);
+	sg_init_table(&drbg->sg_out, 1);
+
 	return alignmask;
 }
 
@@ -1743,17 +1746,17 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 			      u8 *inbuf, u32 inlen,
 			      u8 *outbuf, u32 outlen)
 {
-	struct scatterlist sg_in, sg_out;
+	struct scatterlist *sg_in = &drbg->sg_in, *sg_out = &drbg->sg_out;
 	int ret;
 
-	sg_init_one(&sg_in, inbuf, inlen);
-	sg_init_one(&sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN);
+	sg_set_buf(sg_in, inbuf, inlen);
+	sg_set_buf(sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN);
 
 	while (outlen) {
 		u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN);
 
 		/* Output buffer may not be valid for SGL, use scratchpad */
-		skcipher_request_set_crypt(drbg->ctr_req, &sg_in, &sg_out,
+		skcipher_request_set_crypt(drbg->ctr_req, sg_in, sg_out,
 					   cryptlen, drbg->V);
 		ret = crypto_wait_req(crypto_skcipher_encrypt(drbg->ctr_req),
 					&drbg->ctr_wait);
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 8f941102af36..54b9f5d375f5 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -127,6 +127,7 @@ struct drbg_state {
 	__u8 *outscratchpadbuf;			/* CTR mode output scratchpad */
         __u8 *outscratchpad;			/* CTR mode aligned outbuf */
 	struct crypto_wait ctr_wait;		/* CTR mode async wait obj */
+	struct scatterlist sg_in, sg_out;	/* CTR mode SGLs */
 
 	bool seeded;		/* DRBG fully seeded? */
 	bool pr;		/* Prediction resistance enabled? */
-- 
cgit v1.2.3


From c98fae5e29fad0a4990e20b14bf0a4526518c4ed Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 11 Jul 2018 20:35:49 +0200
Subject: crypto: dh - update test for public key verification

By adding a zero byte-length for the DH parameter Q value, the public
key verification test is disabled for the given test.

Reported-by: Eric Biggers <ebiggers3@gmail.com>
Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/testmgr.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index b6362169771a..759462d65f41 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -644,12 +644,14 @@ static const struct kpp_testvec dh_tv_template[] = {
 	"\x11\x02" /* len */
 	"\x00\x01\x00\x00" /* key_size */
 	"\x00\x01\x00\x00" /* p_size */
+	"\x00\x00\x00\x00" /* q_size */
 	"\x01\x00\x00\x00" /* g_size */
 #else
 	"\x00\x01" /* type */
 	"\x02\x11" /* len */
 	"\x00\x00\x01\x00" /* key_size */
 	"\x00\x00\x01\x00" /* p_size */
+	"\x00\x00\x00\x00" /* q_size */
 	"\x00\x00\x00\x01" /* g_size */
 #endif
 	/* xa */
@@ -751,12 +753,14 @@ static const struct kpp_testvec dh_tv_template[] = {
 	"\x11\x02" /* len */
 	"\x00\x01\x00\x00" /* key_size */
 	"\x00\x01\x00\x00" /* p_size */
+	"\x00\x00\x00\x00" /* q_size */
 	"\x01\x00\x00\x00" /* g_size */
 #else
 	"\x00\x01" /* type */
 	"\x02\x11" /* len */
 	"\x00\x00\x01\x00" /* key_size */
 	"\x00\x00\x01\x00" /* p_size */
+	"\x00\x00\x00\x00" /* q_size */
 	"\x00\x00\x00\x01" /* g_size */
 #endif
 	/* xa */
-- 
cgit v1.2.3


From aef66587f19c7ecc52717328a4c5484f1d2268e9 Mon Sep 17 00:00:00 2001
From: Stephan Mueller <smueller@chronox.de>
Date: Wed, 11 Jul 2018 20:36:23 +0200
Subject: crypto: ecdh - fix typo of P-192 b value

Fix the b value to be compliant with FIPS 186-4 D.1.2.1. This fix is
required to make sure the SP800-56A public key test passes for P-192.

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ecc_curve_defs.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crypto/ecc_curve_defs.h b/crypto/ecc_curve_defs.h
index 94e883a9403f..336ab1805639 100644
--- a/crypto/ecc_curve_defs.h
+++ b/crypto/ecc_curve_defs.h
@@ -27,7 +27,7 @@ static u64 nist_p192_p[] = { 0xFFFFFFFFFFFFFFFFull, 0xFFFFFFFFFFFFFFFEull,
 static u64 nist_p192_n[] = { 0x146BC9B1B4D22831ull, 0xFFFFFFFF99DEF836ull,
 				0xFFFFFFFFFFFFFFFFull };
 static u64 nist_p192_a[] = { 0xFFFFFFFFFFFFFFFCull, 0xFFFFFFFFFFFFFFFEull,
-				0xFFFFFFFFFFFFFFFEull };
+				0xFFFFFFFFFFFFFFFFull };
 static u64 nist_p192_b[] = { 0xFEB8DEECC146B9B1ull, 0x0FA7E9AB72243049ull,
 				0x64210519E59C80E7ull };
 static struct ecc_curve nist_p192 = {
-- 
cgit v1.2.3


From 301422e37782ba20371ee1d3cdb900f816c58e66 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Fri, 13 Jul 2018 16:51:37 +0200
Subject: crypto: inside-secure - switch to SPDX identifiers

Use the appropriate SPDX license identifiers and drop the license text.
This patch is only cosmetic.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel.c        | 5 +----
 drivers/crypto/inside-secure/safexcel.h        | 5 +----
 drivers/crypto/inside-secure/safexcel_cipher.c | 5 +----
 drivers/crypto/inside-secure/safexcel_hash.c   | 5 +----
 drivers/crypto/inside-secure/safexcel_ring.c   | 5 +----
 5 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/drivers/crypto/inside-secure/safexcel.c b/drivers/crypto/inside-secure/safexcel.c
index bd3635cb1e50..7e71043457a6 100644
--- a/drivers/crypto/inside-secure/safexcel.c
+++ b/drivers/crypto/inside-secure/safexcel.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/clk.h>
diff --git a/drivers/crypto/inside-secure/safexcel.h b/drivers/crypto/inside-secure/safexcel.h
index 2f2834e67608..65624a81f0fd 100644
--- a/drivers/crypto/inside-secure/safexcel.h
+++ b/drivers/crypto/inside-secure/safexcel.h
@@ -1,11 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #ifndef __SAFEXCEL_H__
diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 1ae3c28fa898..54e0c615c4c8 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/device.h>
diff --git a/drivers/crypto/inside-secure/safexcel_hash.c b/drivers/crypto/inside-secure/safexcel_hash.c
index 6a790f069ebf..ac9282c1a5ec 100644
--- a/drivers/crypto/inside-secure/safexcel_hash.c
+++ b/drivers/crypto/inside-secure/safexcel_hash.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <crypto/hmac.h>
diff --git a/drivers/crypto/inside-secure/safexcel_ring.c b/drivers/crypto/inside-secure/safexcel_ring.c
index a1e81cfdc1f1..eb75fa684876 100644
--- a/drivers/crypto/inside-secure/safexcel_ring.c
+++ b/drivers/crypto/inside-secure/safexcel_ring.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2017 Marvell
  *
  * Antoine Tenart <antoine.tenart@free-electrons.com>
- *
- * This file is licensed under the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
  */
 
 #include <linux/dma-mapping.h>
-- 
cgit v1.2.3


From e5c8ee1f7cc2b090ecb44b34b1f7d22665526fdc Mon Sep 17 00:00:00 2001
From: Antoine Tenart <antoine.tenart@bootlin.com>
Date: Fri, 13 Jul 2018 17:43:16 +0200
Subject: crypto: inside-secure - initialize first_rdesc to make GCC happy

In the cipher safexcel_send_req function, GCC warns that
first_rdesc may be used uninitialized. While this should never
happen, this patch removes the warning by initializing this
variable to NULL to make GCC happy.

This was reported by the kbuild test robot.

Signed-off-by: Antoine Tenart <antoine.tenart@bootlin.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/inside-secure/safexcel_cipher.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/inside-secure/safexcel_cipher.c b/drivers/crypto/inside-secure/safexcel_cipher.c
index 54e0c615c4c8..3aef1d43e435 100644
--- a/drivers/crypto/inside-secure/safexcel_cipher.c
+++ b/drivers/crypto/inside-secure/safexcel_cipher.c
@@ -378,7 +378,7 @@ static int safexcel_send_req(struct crypto_async_request *base, int ring,
 	struct safexcel_cipher_ctx *ctx = crypto_tfm_ctx(base->tfm);
 	struct safexcel_crypto_priv *priv = ctx->priv;
 	struct safexcel_command_desc *cdesc;
-	struct safexcel_result_desc *rdesc, *first_rdesc;
+	struct safexcel_result_desc *rdesc, *first_rdesc = NULL;
 	struct scatterlist *sg;
 	unsigned int totlen = cryptlen + assoclen;
 	int nr_src, nr_dst, n_cdesc = 0, n_rdesc = 0, queued = totlen;
-- 
cgit v1.2.3


From 0e7d4d932ffc23f75efb31a8c2ac2396c1b81c55 Mon Sep 17 00:00:00 2001
From: Michael Müller <michael@fds-team.de>
Date: Sun, 15 Jul 2018 00:27:06 +0200
Subject: crypto: sharah - Unregister correct algorithms for SAHARA 3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch fixes two typos related to unregistering algorithms supported by
SAHARAH 3. In sahara_register_algs the wrong algorithms are unregistered
in case of an error. In sahara_unregister_algs the wrong array is used to
determine the iteration count.

Signed-off-by: Michael Müller <michael@fds-team.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/sahara.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/sahara.c b/drivers/crypto/sahara.c
index 4379f016fbee..e7540a5b8197 100644
--- a/drivers/crypto/sahara.c
+++ b/drivers/crypto/sahara.c
@@ -1349,7 +1349,7 @@ err_sha_v4_algs:
 
 err_sha_v3_algs:
 	for (j = 0; j < k; j++)
-		crypto_unregister_ahash(&sha_v4_algs[j]);
+		crypto_unregister_ahash(&sha_v3_algs[j]);
 
 err_aes_algs:
 	for (j = 0; j < i; j++)
@@ -1365,7 +1365,7 @@ static void sahara_unregister_algs(struct sahara_dev *dev)
 	for (i = 0; i < ARRAY_SIZE(aes_algs); i++)
 		crypto_unregister_alg(&aes_algs[i]);
 
-	for (i = 0; i < ARRAY_SIZE(sha_v4_algs); i++)
+	for (i = 0; i < ARRAY_SIZE(sha_v3_algs); i++)
 		crypto_unregister_ahash(&sha_v3_algs[i]);
 
 	if (dev->version > SAHARA_VERSION_3)
-- 
cgit v1.2.3


From 07a557f47d7e09b2c60ad4d51b1ac8b035b75f73 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 17 Jul 2018 19:27:16 +0300
Subject: net/sched: tunnel_key: Allow to set tos and ttl for tc based ip
 tunnels

Allow user-space to provide tos and ttl to be set for the tunnel headers.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/tc_act/tc_tunnel_key.h |  2 ++
 net/sched/act_tunnel_key.c                | 20 ++++++++++++++++++--
 2 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/tc_act/tc_tunnel_key.h b/include/uapi/linux/tc_act/tc_tunnel_key.h
index e284fec8c467..be384d63e1b5 100644
--- a/include/uapi/linux/tc_act/tc_tunnel_key.h
+++ b/include/uapi/linux/tc_act/tc_tunnel_key.h
@@ -39,6 +39,8 @@ enum {
 	TCA_TUNNEL_KEY_ENC_OPTS,	/* Nested TCA_TUNNEL_KEY_ENC_OPTS_
 					 * attributes
 					 */
+	TCA_TUNNEL_KEY_ENC_TOS,		/* u8 */
+	TCA_TUNNEL_KEY_ENC_TTL,		/* u8 */
 	__TCA_TUNNEL_KEY_MAX,
 };
 
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index 3ec585d58762..22f26e9ea8f1 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -197,6 +197,8 @@ static const struct nla_policy tunnel_key_policy[TCA_TUNNEL_KEY_MAX + 1] = {
 	[TCA_TUNNEL_KEY_ENC_DST_PORT] = {.type = NLA_U16},
 	[TCA_TUNNEL_KEY_NO_CSUM]      = { .type = NLA_U8 },
 	[TCA_TUNNEL_KEY_ENC_OPTS]     = { .type = NLA_NESTED },
+	[TCA_TUNNEL_KEY_ENC_TOS]      = { .type = NLA_U8 },
+	[TCA_TUNNEL_KEY_ENC_TTL]      = { .type = NLA_U8 },
 };
 
 static int tunnel_key_init(struct net *net, struct nlattr *nla,
@@ -216,6 +218,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 	int opts_len = 0;
 	__be64 key_id;
 	__be16 flags;
+	u8 tos, ttl;
 	int ret = 0;
 	int err;
 
@@ -273,6 +276,13 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			}
 		}
 
+		tos = 0;
+		if (tb[TCA_TUNNEL_KEY_ENC_TOS])
+			tos = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TOS]);
+		ttl = 0;
+		if (tb[TCA_TUNNEL_KEY_ENC_TTL])
+			ttl = nla_get_u8(tb[TCA_TUNNEL_KEY_ENC_TTL]);
+
 		if (tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC] &&
 		    tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]) {
 			__be32 saddr;
@@ -281,7 +291,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			saddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_SRC]);
 			daddr = nla_get_in_addr(tb[TCA_TUNNEL_KEY_ENC_IPV4_DST]);
 
-			metadata = __ip_tun_set_dst(saddr, daddr, 0, 0,
+			metadata = __ip_tun_set_dst(saddr, daddr, tos, ttl,
 						    dst_port, flags,
 						    key_id, opts_len);
 		} else if (tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC] &&
@@ -292,7 +302,7 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 			saddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_SRC]);
 			daddr = nla_get_in6_addr(tb[TCA_TUNNEL_KEY_ENC_IPV6_DST]);
 
-			metadata = __ipv6_tun_set_dst(&saddr, &daddr, 0, 0, dst_port,
+			metadata = __ipv6_tun_set_dst(&saddr, &daddr, tos, ttl, dst_port,
 						      0, flags,
 						      key_id, 0);
 		} else {
@@ -504,6 +514,12 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 			       !(key->tun_flags & TUNNEL_CSUM)) ||
 		    tunnel_key_opts_dump(skb, info))
 			goto nla_put_failure;
+
+		if (key->tos && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TOS, key->tos))
+			goto nla_put_failure;
+
+		if (key->ttl && nla_put_u8(skb, TCA_TUNNEL_KEY_ENC_TTL, key->ttl))
+			goto nla_put_failure;
 	}
 
 	tcf_tm_dump(&tm, &t->tcf_tm);
-- 
cgit v1.2.3


From 5544adb9707fda5d54494c37940701894c16b9a0 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 17 Jul 2018 19:27:17 +0300
Subject: flow_dissector: Dissect tos and ttl from the tunnel info

Add dissection of the tos and ttl from the ip tunnel headers
fields in case a match is needed on them.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h |  2 +-
 net/core/flow_dissector.c    | 14 +++++++++++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index c64406717eee..2a17f041f7a1 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -207,7 +207,7 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_TCP, /* struct flow_dissector_key_tcp */
 	FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */
 	FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */
-
+	FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */
 	FLOW_DISSECTOR_KEY_MAX,
 };
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index b555fc229e96..08a5184f4b34 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -152,7 +152,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 	    !dissector_uses_key(flow_dissector,
 				FLOW_DISSECTOR_KEY_ENC_CONTROL) &&
 	    !dissector_uses_key(flow_dissector,
-				FLOW_DISSECTOR_KEY_ENC_PORTS))
+				FLOW_DISSECTOR_KEY_ENC_PORTS) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_IP))
 		return;
 
 	info = skb_tunnel_info(skb);
@@ -212,6 +214,16 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 		tp->src = key->tp_src;
 		tp->dst = key->tp_dst;
 	}
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_dissector_key_ip *ip;
+
+		ip = skb_flow_dissector_target(flow_dissector,
+					       FLOW_DISSECTOR_KEY_ENC_IP,
+					       target_container);
+		ip->tos = key->tos;
+		ip->ttl = key->ttl;
+	}
 }
 EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 
-- 
cgit v1.2.3


From 0e2c17b64d5c7f57bcd7054ef87797376dcdee26 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 17 Jul 2018 19:27:18 +0300
Subject: net/sched: cls_flower: Support matching on ip tos and ttl for tunnels

Allow users to set rules matching on ipv4 tos and ttl or
ipv6 traffic-class and hoplimit of tunnel headers.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h |  5 +++++
 net/sched/cls_flower.c       | 43 ++++++++++++++++++++++++++++---------------
 2 files changed, 33 insertions(+), 15 deletions(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index c4262d911596..b4512254036b 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -473,6 +473,11 @@ enum {
 	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
 	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
 
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
 	__TCA_FLOWER_MAX,
 };
 
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index c53fdd411f90..38d74803e2df 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -52,6 +52,7 @@ struct fl_flow_key {
 	struct flow_dissector_key_mpls mpls;
 	struct flow_dissector_key_tcp tcp;
 	struct flow_dissector_key_ip ip;
+	struct flow_dissector_key_ip enc_ip;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -453,6 +454,10 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_CVLAN_ID]	= { .type = NLA_U16 },
 	[TCA_FLOWER_KEY_CVLAN_PRIO]	= { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_CVLAN_ETH_TYPE]	= { .type = NLA_U16 },
+	[TCA_FLOWER_KEY_ENC_IP_TOS]	= { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_IP_TOS_MASK] = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_IP_TTL]	 = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
@@ -561,17 +566,17 @@ static int fl_set_key_flags(struct nlattr **tb,
 	return 0;
 }
 
-static void fl_set_key_ip(struct nlattr **tb,
+static void fl_set_key_ip(struct nlattr **tb, bool encap,
 			  struct flow_dissector_key_ip *key,
 			  struct flow_dissector_key_ip *mask)
 {
-		fl_set_key_val(tb, &key->tos, TCA_FLOWER_KEY_IP_TOS,
-			       &mask->tos, TCA_FLOWER_KEY_IP_TOS_MASK,
-			       sizeof(key->tos));
+	int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS;
+	int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL;
+	int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK;
+	int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK;
 
-		fl_set_key_val(tb, &key->ttl, TCA_FLOWER_KEY_IP_TTL,
-			       &mask->ttl, TCA_FLOWER_KEY_IP_TTL_MASK,
-			       sizeof(key->ttl));
+	fl_set_key_val(tb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos));
+	fl_set_key_val(tb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl));
 }
 
 static int fl_set_key(struct net *net, struct nlattr **tb,
@@ -633,7 +638,7 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 		fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
 			       &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
 			       sizeof(key->basic.ip_proto));
-		fl_set_key_ip(tb, &key->ip, &mask->ip);
+		fl_set_key_ip(tb, false, &key->ip, &mask->ip);
 	}
 
 	if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) {
@@ -768,6 +773,8 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 		       &mask->enc_tp.dst, TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
 		       sizeof(key->enc_tp.dst));
 
+	fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip);
+
 	if (tb[TCA_FLOWER_KEY_FLAGS])
 		ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
 
@@ -860,6 +867,8 @@ static void fl_init_dissector(struct fl_flow_mask *mask)
 			   enc_control);
 	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
+	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+			     FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
 
 	skb_flow_dissector_init(&mask->dissector, keys, cnt);
 }
@@ -1208,14 +1217,17 @@ static int fl_dump_key_mpls(struct sk_buff *skb,
 	return 0;
 }
 
-static int fl_dump_key_ip(struct sk_buff *skb,
+static int fl_dump_key_ip(struct sk_buff *skb, bool encap,
 			  struct flow_dissector_key_ip *key,
 			  struct flow_dissector_key_ip *mask)
 {
-	if (fl_dump_key_val(skb, &key->tos, TCA_FLOWER_KEY_IP_TOS, &mask->tos,
-			    TCA_FLOWER_KEY_IP_TOS_MASK, sizeof(key->tos)) ||
-	    fl_dump_key_val(skb, &key->ttl, TCA_FLOWER_KEY_IP_TTL, &mask->ttl,
-			    TCA_FLOWER_KEY_IP_TTL_MASK, sizeof(key->ttl)))
+	int tos_key = encap ? TCA_FLOWER_KEY_ENC_IP_TOS : TCA_FLOWER_KEY_IP_TOS;
+	int ttl_key = encap ? TCA_FLOWER_KEY_ENC_IP_TTL : TCA_FLOWER_KEY_IP_TTL;
+	int tos_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TOS_MASK : TCA_FLOWER_KEY_IP_TOS_MASK;
+	int ttl_mask = encap ? TCA_FLOWER_KEY_ENC_IP_TTL_MASK : TCA_FLOWER_KEY_IP_TTL_MASK;
+
+	if (fl_dump_key_val(skb, &key->tos, tos_key, &mask->tos, tos_mask, sizeof(key->tos)) ||
+	    fl_dump_key_val(skb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl)))
 		return -1;
 
 	return 0;
@@ -1361,7 +1373,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	    (fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
 			    &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
 			    sizeof(key->basic.ip_proto)) ||
-	    fl_dump_key_ip(skb, &key->ip, &mask->ip)))
+	    fl_dump_key_ip(skb, false, &key->ip, &mask->ip)))
 		goto nla_put_failure;
 
 	if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
@@ -1486,7 +1498,8 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 			    TCA_FLOWER_KEY_ENC_UDP_DST_PORT,
 			    &mask->enc_tp.dst,
 			    TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
-			    sizeof(key->enc_tp.dst)))
+			    sizeof(key->enc_tp.dst)) ||
+	    fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip))
 		goto nla_put_failure;
 
 	if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
-- 
cgit v1.2.3


From b51dab46c6adfbb7e80cd0f59ae17b8a30d94b1a Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Wed, 18 Jul 2018 06:27:22 -0700
Subject: qed: Add qed APIs for PHY module query.

This patch adds qed APIs for reading the PHY module.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_hsi.h  | 16 ++++++++++
 drivers/net/ethernet/qlogic/qed/qed_main.c | 23 ++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_mcp.c  | 49 ++++++++++++++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_mcp.h  | 16 ++++++++++
 include/linux/qed/qed_if.h                 | 15 +++++++++
 5 files changed, 119 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
index bee10c1781fb..8faceb691657 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h
@@ -12444,6 +12444,8 @@ struct public_drv_mb {
 #define DRV_MSG_CODE_STATS_TYPE_ISCSI           3
 #define DRV_MSG_CODE_STATS_TYPE_RDMA            4
 
+#define DRV_MSG_CODE_TRANSCEIVER_READ           0x00160000
+
 #define DRV_MSG_CODE_MASK_PARITIES              0x001a0000
 
 #define DRV_MSG_CODE_BIST_TEST			0x001e0000
@@ -12543,6 +12545,15 @@ struct public_drv_mb {
 #define DRV_MB_PARAM_SET_LED_MODE_ON		0x1
 #define DRV_MB_PARAM_SET_LED_MODE_OFF		0x2
 
+#define DRV_MB_PARAM_TRANSCEIVER_PORT_OFFSET		0
+#define DRV_MB_PARAM_TRANSCEIVER_PORT_MASK		0x00000003
+#define DRV_MB_PARAM_TRANSCEIVER_SIZE_OFFSET		2
+#define DRV_MB_PARAM_TRANSCEIVER_SIZE_MASK		0x000000FC
+#define DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_OFFSET	8
+#define DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK	0x0000FF00
+#define DRV_MB_PARAM_TRANSCEIVER_OFFSET_OFFSET		16
+#define DRV_MB_PARAM_TRANSCEIVER_OFFSET_MASK		0xFFFF0000
+
 	/* Resource Allocation params - Driver version support */
 #define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_MASK	0xFFFF0000
 #define DRV_MB_PARAM_RESOURCE_ALLOC_VERSION_MAJOR_SHIFT	16
@@ -12596,6 +12607,9 @@ struct public_drv_mb {
 #define FW_MSG_CODE_PHY_OK			0x00110000
 #define FW_MSG_CODE_OK				0x00160000
 #define FW_MSG_CODE_ERROR			0x00170000
+#define FW_MSG_CODE_TRANSCEIVER_DIAG_OK		0x00160000
+#define FW_MSG_CODE_TRANSCEIVER_DIAG_ERROR	0x00170000
+#define FW_MSG_CODE_TRANSCEIVER_NOT_PRESENT	0x00020000
 
 #define FW_MSG_CODE_OS_WOL_SUPPORTED            0x00800000
 #define FW_MSG_CODE_OS_WOL_NOT_SUPPORTED        0x00810000
@@ -12687,6 +12701,8 @@ struct mcp_public_data {
 	struct public_func func[MCP_GLOB_FUNC_MAX];
 };
 
+#define MAX_I2C_TRANSACTION_SIZE	16
+
 /* OCBB definitions */
 enum tlvs {
 	/* Category 1: Device Properties */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index 0cbc74d6ca8b..158944aa6097 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -2102,6 +2102,28 @@ out:
 	return status;
 }
 
+static int qed_read_module_eeprom(struct qed_dev *cdev, char *buf,
+				  u8 dev_addr, u32 offset, u32 len)
+{
+	struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev);
+	struct qed_ptt *ptt;
+	int rc = 0;
+
+	if (IS_VF(cdev))
+		return 0;
+
+	ptt = qed_ptt_acquire(hwfn);
+	if (!ptt)
+		return -EAGAIN;
+
+	rc = qed_mcp_phy_sfp_read(hwfn, ptt, MFW_PORT(hwfn), dev_addr,
+				  offset, len, buf);
+
+	qed_ptt_release(hwfn, ptt);
+
+	return rc;
+}
+
 static struct qed_selftest_ops qed_selftest_ops_pass = {
 	.selftest_memory = &qed_selftest_memory,
 	.selftest_interrupt = &qed_selftest_interrupt,
@@ -2144,6 +2166,7 @@ const struct qed_common_ops qed_common_ops_pass = {
 	.update_mac = &qed_update_mac,
 	.update_mtu = &qed_update_mtu,
 	.update_wol = &qed_update_wol,
+	.read_module_eeprom = &qed_read_module_eeprom,
 };
 
 void qed_get_protocol_stats(struct qed_dev *cdev,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 4e0b443c9519..62a220fce6e1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -2463,6 +2463,55 @@ out:
 	return rc;
 }
 
+int qed_mcp_phy_sfp_read(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u32 port, u32 addr, u32 offset, u32 len, u8 *p_buf)
+{
+	u32 bytes_left, bytes_to_copy, buf_size, nvm_offset = 0;
+	u32 resp, param;
+	int rc;
+
+	nvm_offset |= (port << DRV_MB_PARAM_TRANSCEIVER_PORT_OFFSET) &
+		       DRV_MB_PARAM_TRANSCEIVER_PORT_MASK;
+	nvm_offset |= (addr << DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_OFFSET) &
+		       DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK;
+
+	addr = offset;
+	offset = 0;
+	bytes_left = len;
+	while (bytes_left > 0) {
+		bytes_to_copy = min_t(u32, bytes_left,
+				      MAX_I2C_TRANSACTION_SIZE);
+		nvm_offset &= (DRV_MB_PARAM_TRANSCEIVER_I2C_ADDRESS_MASK |
+			       DRV_MB_PARAM_TRANSCEIVER_PORT_MASK);
+		nvm_offset |= ((addr + offset) <<
+			       DRV_MB_PARAM_TRANSCEIVER_OFFSET_OFFSET) &
+			       DRV_MB_PARAM_TRANSCEIVER_OFFSET_MASK;
+		nvm_offset |= (bytes_to_copy <<
+			       DRV_MB_PARAM_TRANSCEIVER_SIZE_OFFSET) &
+			       DRV_MB_PARAM_TRANSCEIVER_SIZE_MASK;
+		rc = qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt,
+					DRV_MSG_CODE_TRANSCEIVER_READ,
+					nvm_offset, &resp, &param, &buf_size,
+					(u32 *)(p_buf + offset));
+		if (rc) {
+			DP_NOTICE(p_hwfn,
+				  "Failed to send a transceiver read command to the MFW. rc = %d.\n",
+				  rc);
+			return rc;
+		}
+
+		if (resp == FW_MSG_CODE_TRANSCEIVER_NOT_PRESENT)
+			return -ENODEV;
+		else if (resp != FW_MSG_CODE_TRANSCEIVER_DIAG_OK)
+			return -EINVAL;
+
+		offset += buf_size;
+		bytes_left -= buf_size;
+	}
+
+	return 0;
+}
+
 int qed_mcp_bist_register_test(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 {
 	u32 drv_mb_param = 0, rsp, param;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
index 632a838f1fe3..047976d5c6e9 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h
@@ -839,6 +839,22 @@ int qed_mcp_nvm_rd_cmd(struct qed_hwfn *p_hwfn,
 		       u32 *o_mcp_resp,
 		       u32 *o_mcp_param, u32 *o_txn_size, u32 *o_buf);
 
+/**
+ * @brief Read from sfp
+ *
+ *  @param p_hwfn - hw function
+ *  @param p_ptt  - PTT required for register access
+ *  @param port   - transceiver port
+ *  @param addr   - I2C address
+ *  @param offset - offset in sfp
+ *  @param len    - buffer length
+ *  @param p_buf  - buffer to read into
+ *
+ * @return int - 0 - operation was successful.
+ */
+int qed_mcp_phy_sfp_read(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt,
+			 u32 port, u32 addr, u32 offset, u32 len, u8 *p_buf);
+
 /**
  * @brief indicates whether the MFW objects [under mcp_info] are accessible
  *
diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h
index b4040023cbfb..8cd34645e892 100644
--- a/include/linux/qed/qed_if.h
+++ b/include/linux/qed/qed_if.h
@@ -759,6 +759,9 @@ struct qed_generic_tlvs {
 	u8 mac[QED_TLV_MAC_COUNT][ETH_ALEN];
 };
 
+#define QED_I2C_DEV_ADDR_A0 0xA0
+#define QED_I2C_DEV_ADDR_A2 0xA2
+
 #define QED_NVM_SIGNATURE 0x12435687
 
 enum qed_nvm_flash_cmd {
@@ -1026,6 +1029,18 @@ struct qed_common_ops {
  * @param enabled - true iff WoL should be enabled.
  */
 	int (*update_wol) (struct qed_dev *cdev, bool enabled);
+
+/**
+ * @brief read_module_eeprom
+ *
+ * @param cdev
+ * @param buf - buffer
+ * @param dev_addr - PHY device memory region
+ * @param offset - offset into eeprom contents to be read
+ * @param len - buffer length, i.e., max bytes to be read
+ */
+	int (*read_module_eeprom)(struct qed_dev *cdev,
+				  char *buf, u8 dev_addr, u32 offset, u32 len);
 };
 
 #define MASK_FIELD(_name, _value) \
-- 
cgit v1.2.3


From 97df0d65623b1a6e090df0a8298b8349d538c67e Mon Sep 17 00:00:00 2001
From: Sudarsana Reddy Kalluru <sudarsana.kalluru@cavium.com>
Date: Wed, 18 Jul 2018 06:27:23 -0700
Subject: qede: Add driver callbacks for eeprom module query.

This patch implements the ethtool callbacks for querying sfp/eeprom module.

Signed-off-by: Sudarsana Reddy Kalluru <Sudarsana.Kalluru@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c | 88 +++++++++++++++++++++++++
 1 file changed, 88 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index f4a0f8ff8261..b37857f3f950 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1780,6 +1780,92 @@ static int qede_set_eee(struct net_device *dev, struct ethtool_eee *edata)
 	return 0;
 }
 
+static int qede_get_module_info(struct net_device *dev,
+				struct ethtool_modinfo *modinfo)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u8 buf[4];
+	int rc;
+
+	/* Read first 4 bytes to find the sfp type */
+	rc = edev->ops->common->read_module_eeprom(edev->cdev, buf,
+						   QED_I2C_DEV_ADDR_A0, 0, 4);
+	if (rc) {
+		DP_ERR(edev, "Failed reading EEPROM data %d\n", rc);
+		return rc;
+	}
+
+	switch (buf[0]) {
+	case 0x3: /* SFP, SFP+, SFP-28 */
+		modinfo->type = ETH_MODULE_SFF_8472;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN;
+		break;
+	case 0xc: /* QSFP */
+	case 0xd: /* QSFP+ */
+		modinfo->type = ETH_MODULE_SFF_8436;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN;
+		break;
+	case 0x11: /* QSFP-28 */
+		modinfo->type = ETH_MODULE_SFF_8636;
+		modinfo->eeprom_len = ETH_MODULE_SFF_8636_LEN;
+		break;
+	default:
+		DP_ERR(edev, "Unknown transceiver type 0x%x\n", buf[0]);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int qede_get_module_eeprom(struct net_device *dev,
+				  struct ethtool_eeprom *ee, u8 *data)
+{
+	struct qede_dev *edev = netdev_priv(dev);
+	u32 start_addr = ee->offset, size = 0;
+	u8 *buf = data;
+	int rc = 0;
+
+	/* Read A0 section */
+	if (ee->offset < ETH_MODULE_SFF_8079_LEN) {
+		/* Limit transfer size to the A0 section boundary */
+		if (ee->offset + ee->len > ETH_MODULE_SFF_8079_LEN)
+			size = ETH_MODULE_SFF_8079_LEN - ee->offset;
+		else
+			size = ee->len;
+
+		rc = edev->ops->common->read_module_eeprom(edev->cdev, buf,
+							   QED_I2C_DEV_ADDR_A0,
+							   start_addr, size);
+		if (rc) {
+			DP_ERR(edev, "Failed reading A0 section  %d\n", rc);
+			return rc;
+		}
+
+		buf += size;
+		start_addr += size;
+	}
+
+	/* Read A2 section */
+	if (start_addr >= ETH_MODULE_SFF_8079_LEN &&
+	    start_addr < ETH_MODULE_SFF_8472_LEN) {
+		size = ee->len - size;
+		/* Limit transfer size to the A2 section boundary */
+		if (start_addr + size > ETH_MODULE_SFF_8472_LEN)
+			size = ETH_MODULE_SFF_8472_LEN - start_addr;
+		start_addr -= ETH_MODULE_SFF_8079_LEN;
+		rc = edev->ops->common->read_module_eeprom(edev->cdev, buf,
+							   QED_I2C_DEV_ADDR_A2,
+							   start_addr, size);
+		if (rc) {
+			DP_VERBOSE(edev, QED_MSG_DEBUG,
+				   "Failed reading A2 section %d\n", rc);
+			return 0;
+		}
+	}
+
+	return rc;
+}
+
 static const struct ethtool_ops qede_ethtool_ops = {
 	.get_link_ksettings = qede_get_link_ksettings,
 	.set_link_ksettings = qede_set_link_ksettings,
@@ -1813,6 +1899,8 @@ static const struct ethtool_ops qede_ethtool_ops = {
 	.get_channels = qede_get_channels,
 	.set_channels = qede_set_channels,
 	.self_test = qede_self_test,
+	.get_module_info = qede_get_module_info,
+	.get_module_eeprom = qede_get_module_eeprom,
 	.get_eee = qede_get_eee,
 	.set_eee = qede_set_eee,
 
-- 
cgit v1.2.3


From ae976358cd7b0272ccfbd2517edaf0d46f2a356b Mon Sep 17 00:00:00 2001
From: Kai Heng Feng <kai.heng.feng@canonical.com>
Date: Thu, 19 Jul 2018 19:00:30 +0800
Subject: Revert "ACPI / bus: Parse tables as term_list for Dell XPS 9570 and
 Precision M5530"

Reverts commit 36904703aeee (ACPI / bus: Parse tables as term_list
for Dell XPS 9570 and Precision M5530).

Since commit 5a8361f7ecce (ACPICA: Integrate package handling with
module-level code), acpi_gbl_execute_tables_as_methods is always
true, so we can remove the quirk for XPS 9570/Precision M5530.

Signed-off-by: Kai-Heng Feng <kai.heng.feng@canonical.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/bus.c | 38 +++++++-------------------------------
 1 file changed, 7 insertions(+), 31 deletions(-)

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 84b4a62018eb..f61f8927d843 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -66,37 +66,10 @@ static int set_copy_dsdt(const struct dmi_system_id *id)
 	return 0;
 }
 #endif
-static int set_gbl_term_list(const struct dmi_system_id *id)
-{
-	acpi_gbl_execute_tables_as_methods = 1;
-	return 0;
-}
 
-static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
-	/*
-	 * Touchpad on Dell XPS 9570/Precision M5530 doesn't work under I2C
-	 * mode.
-	 * https://bugzilla.kernel.org/show_bug.cgi?id=198515
-	 */
-	{
-		.callback = set_gbl_term_list,
-		.ident = "Dell Precision M5530",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "Precision M5530"),
-		},
-	},
-	{
-		.callback = set_gbl_term_list,
-		.ident = "Dell XPS 15 9570",
-		.matches = {
-			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
-			DMI_MATCH(DMI_PRODUCT_NAME, "XPS 15 9570"),
-		},
-	},
+static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
 	/*
 	 * Invoke DSDT corruption work-around on all Toshiba Satellite.
-	 * DSDT will be copied to memory.
 	 * https://bugzilla.kernel.org/show_bug.cgi?id=14679
 	 */
 	{
@@ -110,7 +83,7 @@ static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
 	{}
 };
 #else
-static const struct dmi_system_id acpi_quirks_dmi_table[] __initconst = {
+static const struct dmi_system_id dsdt_dmi_table[] __initconst = {
 	{}
 };
 #endif
@@ -1060,8 +1033,11 @@ void __init acpi_early_init(void)
 
 	acpi_permanent_mmap = true;
 
-	/* Check machine-specific quirks */
-	dmi_check_system(acpi_quirks_dmi_table);
+	/*
+	 * If the machine falls into the DMI check table,
+	 * DSDT will be copied to memory
+	 */
+	dmi_check_system(dsdt_dmi_table);
 
 	status = acpi_reallocate_root_table();
 	if (ACPI_FAILURE(status)) {
-- 
cgit v1.2.3


From 887532ca7ca59fcf0547a79211756791128030a3 Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@canonical.com>
Date: Wed, 18 Jul 2018 11:46:55 -0700
Subject: ACPI / OSI: Add OEM _OSI string to enable NVidia HDMI audio

Some ThinkPad systems have a power-saving feature that turns off HDMI
audio device in Windows, but NVidia Linux driver does not support this
feature. As a result, HDMI audio will not work on Linux.

A BIOS workaround is added with an OEM_OSI string
"Linux-Lenovo-NV-HDMI-Audio" to power on NVidia HDMI audio when booting.

The form of the OEM _OSI strings is defined by each OEMs and is
discussed in Documentation/acpi/osi.txt.

Signed-off-by: Alex Hung <alex.hung@canonical.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/osi.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/acpi/osi.c b/drivers/acpi/osi.c
index 8a8f43568510..b2a16ed7e81a 100644
--- a/drivers/acpi/osi.c
+++ b/drivers/acpi/osi.c
@@ -66,6 +66,14 @@ osi_setup_entries[OSI_STRING_ENTRIES_MAX] __initdata = {
 	 * be removed if both new and old graphics cards are supported.
 	 */
 	{"Linux-Dell-Video", true},
+	/*
+	 * Linux-Lenovo-NV-HDMI-Audio is used by BIOS to power on NVidia's HDMI
+	 * audio device which is turned off for power-saving in Windows OS.
+	 * This power management feature observed on some Lenovo Thinkpad
+	 * systems which will not be able to output audio via HDMI without
+	 * a BIOS workaround.
+	 */
+	{"Linux-Lenovo-NV-HDMI-Audio", true},
 };
 
 static u32 acpi_osi_handler(acpi_string interface, u32 supported)
-- 
cgit v1.2.3


From bc56b33404599edc412b91933d74b36873e8ea25 Mon Sep 17 00:00:00 2001
From: Benedict Wong <benedictwong@google.com>
Date: Thu, 19 Jul 2018 10:50:44 -0700
Subject: xfrm: Remove xfrmi interface ID from flowi

In order to remove performance impact of having the extra u32 in every
single flowi, this change removes the flowi_xfrm struct, prefering to
take the if_id as a method parameter where needed.

In the inbound direction, if_id is only needed during the
__xfrm_check_policy() function, and the if_id can be determined at that
point based on the skb. As such, xfrmi_decode_session() is only called
with the skb in __xfrm_check_policy().

In the outbound direction, the only place where if_id is needed is the
xfrm_lookup() call in xfrmi_xmit2(). With this change, the if_id is
directly passed into the xfrm_lookup_with_ifid() call. All existing
callers can still call xfrm_lookup(), which uses a default if_id of 0.

This change does not change any behavior of XFRMIs except for improving
overall system performance via flowi size reduction.

This change has been tested against the Android Kernel Networking Tests:

https://android.googlesource.com/kernel/tests/+/master/net/test

Signed-off-by: Benedict Wong <benedictwong@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 include/net/dst.h         | 14 +++++++
 include/net/flow.h        |  9 -----
 include/net/xfrm.h        |  2 +-
 net/xfrm/xfrm_interface.c |  4 +-
 net/xfrm/xfrm_policy.c    | 98 +++++++++++++++++++++++++++++++----------------
 net/xfrm/xfrm_state.c     |  3 +-
 6 files changed, 83 insertions(+), 47 deletions(-)

diff --git a/include/net/dst.h b/include/net/dst.h
index b3219cd8a5a1..7f735e76ca73 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -475,6 +475,14 @@ static inline struct dst_entry *xfrm_lookup(struct net *net,
 	return dst_orig;
 }
 
+static inline struct dst_entry *
+xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig,
+		      const struct flowi *fl, const struct sock *sk,
+		      int flags, u32 if_id)
+{
+	return dst_orig;
+}
+
 static inline struct dst_entry *xfrm_lookup_route(struct net *net,
 						  struct dst_entry *dst_orig,
 						  const struct flowi *fl,
@@ -494,6 +502,12 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 			      const struct flowi *fl, const struct sock *sk,
 			      int flags);
 
+struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
+					struct dst_entry *dst_orig,
+					const struct flowi *fl,
+					const struct sock *sk, int flags,
+					u32 if_id);
+
 struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
 				    const struct flowi *fl, const struct sock *sk,
 				    int flags);
diff --git a/include/net/flow.h b/include/net/flow.h
index 187c9bef672f..8ce21793094e 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -26,10 +26,6 @@ struct flowi_tunnel {
 	__be64			tun_id;
 };
 
-struct flowi_xfrm {
-	__u32			if_id;
-};
-
 struct flowi_common {
 	int	flowic_oif;
 	int	flowic_iif;
@@ -43,7 +39,6 @@ struct flowi_common {
 #define FLOWI_FLAG_SKIP_NH_OIF		0x04
 	__u32	flowic_secid;
 	struct flowi_tunnel flowic_tun_key;
-	struct flowi_xfrm xfrm;
 	kuid_t  flowic_uid;
 };
 
@@ -83,7 +78,6 @@ struct flowi4 {
 #define flowi4_secid		__fl_common.flowic_secid
 #define flowi4_tun_key		__fl_common.flowic_tun_key
 #define flowi4_uid		__fl_common.flowic_uid
-#define flowi4_xfrm		__fl_common.xfrm
 
 	/* (saddr,daddr) must be grouped, same order as in IP header */
 	__be32			saddr;
@@ -115,7 +109,6 @@ static inline void flowi4_init_output(struct flowi4 *fl4, int oif,
 	fl4->flowi4_flags = flags;
 	fl4->flowi4_secid = 0;
 	fl4->flowi4_tun_key.tun_id = 0;
-	fl4->flowi4_xfrm.if_id = 0;
 	fl4->flowi4_uid = uid;
 	fl4->daddr = daddr;
 	fl4->saddr = saddr;
@@ -145,7 +138,6 @@ struct flowi6 {
 #define flowi6_secid		__fl_common.flowic_secid
 #define flowi6_tun_key		__fl_common.flowic_tun_key
 #define flowi6_uid		__fl_common.flowic_uid
-#define flowi6_xfrm		__fl_common.xfrm
 	struct in6_addr		daddr;
 	struct in6_addr		saddr;
 	/* Note: flowi6_tos is encoded in flowlabel, too. */
@@ -193,7 +185,6 @@ struct flowi {
 #define flowi_secid	u.__fl_common.flowic_secid
 #define flowi_tun_key	u.__fl_common.flowic_tun_key
 #define flowi_uid	u.__fl_common.flowic_uid
-#define flowi_xfrm	u.__fl_common.xfrm
 } __attribute__((__aligned__(BITS_PER_LONG/8)));
 
 static inline struct flowi *flowi4_to_flowi(struct flowi4 *fl4)
diff --git a/include/net/xfrm.h b/include/net/xfrm.h
index 1350e2cf0749..ca820945f30c 100644
--- a/include/net/xfrm.h
+++ b/include/net/xfrm.h
@@ -1557,7 +1557,7 @@ struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr,
 				   const struct flowi *fl,
 				   struct xfrm_tmpl *tmpl,
 				   struct xfrm_policy *pol, int *err,
-				   unsigned short family);
+				   unsigned short family, u32 if_id);
 struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id,
 				       xfrm_address_t *daddr,
 				       xfrm_address_t *saddr,
diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 31cb1c7e3881..ccfe18d67e98 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -307,10 +307,8 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl)
 	if (!dst)
 		goto tx_err_link_failure;
 
-	fl->flowi_xfrm.if_id = xi->p.if_id;
-
 	dst_hold(dst);
-	dst = xfrm_lookup(xi->net, dst, fl, NULL, 0);
+	dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id);
 	if (IS_ERR(dst)) {
 		err = PTR_ERR(dst);
 		dst = NULL;
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5d2f734f4309..2f70fe68b9b0 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1068,14 +1068,14 @@ EXPORT_SYMBOL(xfrm_policy_walk_done);
  */
 static int xfrm_policy_match(const struct xfrm_policy *pol,
 			     const struct flowi *fl,
-			     u8 type, u16 family, int dir)
+			     u8 type, u16 family, int dir, u32 if_id)
 {
 	const struct xfrm_selector *sel = &pol->selector;
 	int ret = -ESRCH;
 	bool match;
 
 	if (pol->family != family ||
-	    pol->if_id != fl->flowi_xfrm.if_id ||
+	    pol->if_id != if_id ||
 	    (fl->flowi_mark & pol->mark.m) != pol->mark.v ||
 	    pol->type != type)
 		return ret;
@@ -1090,7 +1090,8 @@ static int xfrm_policy_match(const struct xfrm_policy *pol,
 
 static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 						     const struct flowi *fl,
-						     u16 family, u8 dir)
+						     u16 family, u8 dir,
+						     u32 if_id)
 {
 	int err;
 	struct xfrm_policy *pol, *ret;
@@ -1114,7 +1115,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 	priority = ~0U;
 	ret = NULL;
 	hlist_for_each_entry_rcu(pol, chain, bydst) {
-		err = xfrm_policy_match(pol, fl, type, family, dir);
+		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
 		if (err) {
 			if (err == -ESRCH)
 				continue;
@@ -1133,7 +1134,7 @@ static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type,
 		if ((pol->priority >= priority) && ret)
 			break;
 
-		err = xfrm_policy_match(pol, fl, type, family, dir);
+		err = xfrm_policy_match(pol, fl, type, family, dir, if_id);
 		if (err) {
 			if (err == -ESRCH)
 				continue;
@@ -1158,21 +1159,25 @@ fail:
 	return ret;
 }
 
-static struct xfrm_policy *
-xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir)
+static struct xfrm_policy *xfrm_policy_lookup(struct net *net,
+					      const struct flowi *fl,
+					      u16 family, u8 dir, u32 if_id)
 {
 #ifdef CONFIG_XFRM_SUB_POLICY
 	struct xfrm_policy *pol;
 
-	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir);
+	pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family,
+					dir, if_id);
 	if (pol != NULL)
 		return pol;
 #endif
-	return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir);
+	return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family,
+					 dir, if_id);
 }
 
 static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
-						 const struct flowi *fl, u16 family)
+						 const struct flowi *fl,
+						 u16 family, u32 if_id)
 {
 	struct xfrm_policy *pol;
 
@@ -1191,7 +1196,7 @@ static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir,
 		match = xfrm_selector_match(&pol->selector, fl, family);
 		if (match) {
 			if ((sk->sk_mark & pol->mark.m) != pol->mark.v ||
-			    pol->if_id != fl->flowi_xfrm.if_id) {
+			    pol->if_id != if_id) {
 				pol = NULL;
 				goto out;
 			}
@@ -1405,7 +1410,8 @@ xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl,
 			}
 		}
 
-		x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family);
+		x = xfrm_state_find(remote, local, fl, tmpl, policy, &error,
+				    family, policy->if_id);
 
 		if (x && x->km.state == XFRM_STATE_VALID) {
 			xfrm[nx++] = x;
@@ -1708,7 +1714,8 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family,
 		pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]),
 						    XFRM_POLICY_TYPE_MAIN,
 						    fl, family,
-						    XFRM_POLICY_OUT);
+						    XFRM_POLICY_OUT,
+						    pols[0]->if_id);
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				xfrm_pols_put(pols, *num_pols);
@@ -1942,8 +1949,10 @@ free_dst:
 	goto out;
 }
 
-static struct xfrm_dst *
-xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo)
+static struct xfrm_dst *xfrm_bundle_lookup(struct net *net,
+					   const struct flowi *fl,
+					   u16 family, u8 dir,
+					   struct xfrm_flo *xflo, u32 if_id)
 {
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	int num_pols = 0, num_xfrms = 0, err;
@@ -1952,7 +1961,7 @@ xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir,
 	/* Resolve policies to use if we couldn't get them from
 	 * previous cache entry */
 	num_pols = 1;
-	pols[0] = xfrm_policy_lookup(net, fl, family, dir);
+	pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id);
 	err = xfrm_expand_policies(fl, family, pols,
 					   &num_pols, &num_xfrms);
 	if (err < 0)
@@ -2020,14 +2029,19 @@ static struct dst_entry *make_blackhole(struct net *net, u16 family,
 	return ret;
 }
 
-/* Main function: finds/creates a bundle for given flow.
+/* Finds/creates a bundle for given flow and if_id
  *
  * At the moment we eat a raw IP route. Mostly to speed up lookups
  * on interfaces with disabled IPsec.
+ *
+ * xfrm_lookup uses an if_id of 0 by default, and is provided for
+ * compatibility
  */
-struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
-			      const struct flowi *fl,
-			      const struct sock *sk, int flags)
+struct dst_entry *xfrm_lookup_with_ifid(struct net *net,
+					struct dst_entry *dst_orig,
+					const struct flowi *fl,
+					const struct sock *sk,
+					int flags, u32 if_id)
 {
 	struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX];
 	struct xfrm_dst *xdst;
@@ -2043,7 +2057,8 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 	sk = sk_const_to_full_sk(sk);
 	if (sk && sk->sk_policy[XFRM_POLICY_OUT]) {
 		num_pols = 1;
-		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family);
+		pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family,
+						if_id);
 		err = xfrm_expand_policies(fl, family, pols,
 					   &num_pols, &num_xfrms);
 		if (err < 0)
@@ -2087,7 +2102,7 @@ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
 		    !net->xfrm.policy_count[XFRM_POLICY_OUT])
 			goto nopol;
 
-		xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo);
+		xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id);
 		if (xdst == NULL)
 			goto nopol;
 		if (IS_ERR(xdst)) {
@@ -2168,6 +2183,19 @@ dropdst:
 	xfrm_pols_put(pols, drop_pols);
 	return ERR_PTR(err);
 }
+EXPORT_SYMBOL(xfrm_lookup_with_ifid);
+
+/* Main function: finds/creates a bundle for given flow.
+ *
+ * At the moment we eat a raw IP route. Mostly to speed up lookups
+ * on interfaces with disabled IPsec.
+ */
+struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
+			      const struct flowi *fl, const struct sock *sk,
+			      int flags)
+{
+	return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0);
+}
 EXPORT_SYMBOL(xfrm_lookup);
 
 /* Callers of xfrm_lookup_route() must ensure a call to dst_output().
@@ -2257,19 +2285,12 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl,
 			  unsigned int family, int reverse)
 {
 	const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family);
-	const struct xfrm_if_cb *ifcb = xfrm_if_get_cb();
-	struct xfrm_if *xi;
 	int err;
 
 	if (unlikely(afinfo == NULL))
 		return -EAFNOSUPPORT;
 
 	afinfo->decode_session(skb, fl, reverse);
-	if (ifcb) {
-		xi = ifcb->decode_session(skb);
-		if (xi)
-			fl->flowi_xfrm.if_id = xi->p.if_id;
-	}
 
 	err = security_xfrm_decode_session(skb, &fl->flowi_secid);
 	rcu_read_unlock();
@@ -2301,6 +2322,19 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	int reverse;
 	struct flowi fl;
 	int xerr_idx = -1;
+	const struct xfrm_if_cb *ifcb;
+	struct xfrm_if *xi;
+	u32 if_id = 0;
+
+	rcu_read_lock();
+	ifcb = xfrm_if_get_cb();
+
+	if (ifcb) {
+		xi = ifcb->decode_session(skb);
+		if (xi)
+			if_id = xi->p.if_id;
+	}
+	rcu_read_unlock();
 
 	reverse = dir & ~XFRM_POLICY_MASK;
 	dir &= XFRM_POLICY_MASK;
@@ -2328,7 +2362,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	pol = NULL;
 	sk = sk_to_full_sk(sk);
 	if (sk && sk->sk_policy[dir]) {
-		pol = xfrm_sk_policy_lookup(sk, dir, &fl, family);
+		pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id);
 		if (IS_ERR(pol)) {
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
 			return 0;
@@ -2336,7 +2370,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	}
 
 	if (!pol)
-		pol = xfrm_policy_lookup(net, &fl, family, dir);
+		pol = xfrm_policy_lookup(net, &fl, family, dir, if_id);
 
 	if (IS_ERR(pol)) {
 		XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
@@ -2360,7 +2394,7 @@ int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb,
 	if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) {
 		pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN,
 						    &fl, family,
-						    XFRM_POLICY_IN);
+						    XFRM_POLICY_IN, if_id);
 		if (pols[1]) {
 			if (IS_ERR(pols[1])) {
 				XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR);
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 27c84e63c7ff..bd5cb7ad2447 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -930,7 +930,7 @@ struct xfrm_state *
 xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 		const struct flowi *fl, struct xfrm_tmpl *tmpl,
 		struct xfrm_policy *pol, int *err,
-		unsigned short family)
+		unsigned short family, u32 if_id)
 {
 	static xfrm_address_t saddr_wildcard = { };
 	struct net *net = xp_net(pol);
@@ -940,7 +940,6 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
 	int error = 0;
 	struct xfrm_state *best = NULL;
 	u32 mark = pol->mark.v & pol->mark.m;
-	u32 if_id = fl->flowi_xfrm.if_id;
 	unsigned short encap_family = tmpl->encap_family;
 	unsigned int sequence;
 	struct km_event c;
-- 
cgit v1.2.3


From 5baf4f9c0035f3e33bb693a1a1e87599f6e804e6 Mon Sep 17 00:00:00 2001
From: Nathan Harold <nharold@google.com>
Date: Thu, 19 Jul 2018 19:07:47 -0700
Subject: xfrm: Allow xfrmi if_id to be updated by UPDSA

Allow attaching an SA to an xfrm interface id after
the creation of the SA, so that tasks such as keying
which must be done as the SA is created, can remain
separate from the decision on how to route traffic
from an SA. This permits SA creation to be decomposed
in to three separate steps:
1) allocation of a SPI
2) algorithm and key negotiation
3) insertion into the data path

Signed-off-by: Nathan Harold <nharold@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_state.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index bd5cb7ad2447..b669262682c9 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -1561,10 +1561,14 @@ out:
 		if (x1->curlft.use_time)
 			xfrm_state_check_expire(x1);
 
-		if (x->props.smark.m || x->props.smark.v) {
+		if (x->props.smark.m || x->props.smark.v || x->if_id) {
 			spin_lock_bh(&net->xfrm.xfrm_state_lock);
 
-			x1->props.smark = x->props.smark;
+			if (x->props.smark.m || x->props.smark.v)
+				x1->props.smark = x->props.smark;
+
+			if (x->if_id)
+				x1->if_id = x->if_id;
 
 			__xfrm_state_bump_genids(x1);
 			spin_unlock_bh(&net->xfrm.xfrm_state_lock);
-- 
cgit v1.2.3


From 9407f5a7ee77c631d1e100436132437cf6237e45 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 20 Jul 2018 10:09:11 +0200
Subject: sched/clock: Close a hole in sched_clock_init()

All data required for the 'unstable' sched_clock must be set-up _before_
enabling it -- setting sched_clock_running. This includes the
__gtod_offset but also a recent scd stamp.

Make the gtod-offset update also set the csd stamp -- it requires the
same two clock reads _anyway_. This doesn't hurt in the
sched_clock_tick_stable() case and ensures sched_clock_init() gets
everything set-up before use.

Also switch to unconditional IRQ-disable/enable because the static key
stuff already requires this is not ran with IRQs disabled.

Fixes: 857baa87b642 ("sched/clock: Enable sched clock early")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: linux@armlinux.org.uk
Cc: schwidefsky@de.ibm.com
Cc: heiko.carstens@de.ibm.com
Cc: john.stultz@linaro.org
Cc: sboyd@codeaurora.org
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: prarit@redhat.com
Cc: feng.tang@intel.com
Cc: pmladek@suse.com
Cc: gnomes@lxorguk.ukuu.org.uk
Cc: linux-s390@vger.kernel.org
Cc: boris.ostrovsky@oracle.com
Cc: jgross@suse.com
Cc: pbonzini@redhat.com
Link: https://lkml.kernel.org/r/20180720080911.GM2494@hirez.programming.kicks-ass.net
---
 kernel/sched/clock.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index c5c47ad3f386..811a39aca1ce 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -197,13 +197,14 @@ void clear_sched_clock_stable(void)
 
 static void __sched_clock_gtod_offset(void)
 {
-	__gtod_offset = (sched_clock() + __sched_clock_offset) - ktime_get_ns();
+	struct sched_clock_data *scd = this_scd();
+
+	__scd_stamp(scd);
+	__gtod_offset = (scd->tick_raw + __sched_clock_offset) - scd->tick_gtod;
 }
 
 void __init sched_clock_init(void)
 {
-	unsigned long flags;
-
 	/*
 	 * Set __gtod_offset such that once we mark sched_clock_running,
 	 * sched_clock_tick() continues where sched_clock() left off.
@@ -211,16 +212,11 @@ void __init sched_clock_init(void)
 	 * Even if TSC is buggered, we're still UP at this point so it
 	 * can't really be out of sync.
 	 */
-	local_irq_save(flags);
+	local_irq_disable();
 	__sched_clock_gtod_offset();
-	local_irq_restore(flags);
+	local_irq_enable();
 
 	static_branch_inc(&sched_clock_running);
-
-	/* Now that sched_clock_running is set adjust scd */
-	local_irq_save(flags);
-	sched_clock_tick();
-	local_irq_restore(flags);
 }
 /*
  * We run this as late_initcall() such that it runs after all built-in drivers,
-- 
cgit v1.2.3


From 486c16f2b5d1eb12339fb7a020961ea1c40e619f Mon Sep 17 00:00:00 2001
From: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Date: Fri, 20 Jul 2018 09:53:02 +0200
Subject: ASoC: sgtl5000: fix spelling in devicetree binding document

This fixes a spelling mistake.

Signed-off-by: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/sgtl5000.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/sound/sgtl5000.txt b/Documentation/devicetree/bindings/sound/sgtl5000.txt
index 0f214457476f..9c58f724396a 100644
--- a/Documentation/devicetree/bindings/sound/sgtl5000.txt
+++ b/Documentation/devicetree/bindings/sound/sgtl5000.txt
@@ -17,7 +17,7 @@ Optional properties:
 
 - VDDD-supply : the regulator provider of VDDD
 
-- micbias-resistor-k-ohms : the bias resistor to be used in kOmhs
+- micbias-resistor-k-ohms : the bias resistor to be used in kOhms
 	The resistor can take values of 2k, 4k or 8k.
 	If set to 0 it will be off.
 	If this node is not mentioned or if the value is unknown, then
-- 
cgit v1.2.3


From e1548b1ba1643d4b5015f7168c64f240ebe114c8 Mon Sep 17 00:00:00 2001
From: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Date: Fri, 20 Jul 2018 10:02:50 +0200
Subject: MAINTAINERS: add entry for STI audio drivers

Add sound/soc/sti drivers entry for STI audio drivers from
ST Microelectronics.

Signed-off-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9d5eeff51b5f..b44d7167a9e9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13557,6 +13557,13 @@ L:	linux-block@vger.kernel.org
 S:	Maintained
 F:	drivers/block/skd*[ch]
 
+STI AUDIO (ASoC) DRIVERS
+M:	Arnaud Pouliquen <arnaud.pouliquen@st.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/sound/st,sti-asoc-card.txt
+F:	sound/soc/sti/
+
 STI CEC DRIVER
 M:	Benjamin Gaignard <benjamin.gaignard@linaro.org>
 S:	Maintained
-- 
cgit v1.2.3


From faa80b66c767ef4995e33835e9844a5df142c6cc Mon Sep 17 00:00:00 2001
From: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Date: Fri, 20 Jul 2018 10:02:51 +0200
Subject: MAINTAINERS: add entry for STM32 audio drivers

Add sound/soc/stm drivers entry for STM32 audio drivers from
ST Microelectronics.

Signed-off-by: Arnaud Pouliquen <arnaud.pouliquen@st.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index b44d7167a9e9..fc711d23dc83 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13577,6 +13577,14 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/usb/stk1160/
 
+STM32 AUDIO (ASoC) DRIVERS
+M:	Olivier Moysan <olivier.moysan@st.com>
+M:	Arnaud Pouliquen <arnaud.pouliquen@st.com>
+L:	alsa-devel@alsa-project.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/sound/st,stm32-*.txt
+F:	sound/soc/stm/
+
 STM32 TIMER/LPTIMER DRIVERS
 M:	Fabrice Gasnier <fabrice.gasnier@st.com>
 S:	Maintained
-- 
cgit v1.2.3


From 2ec42486358f63c4a426514c395d13f4b9de5da8 Mon Sep 17 00:00:00 2001
From: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Date: Fri, 20 Jul 2018 10:04:23 +0200
Subject: ASoC: tegra: improve goto error label

While the two error labels "err" and "err_clk_put" goto the same place
it is rather confusing that the earlier one is certainly used later
again.

Signed-off-by: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/tegra/tegra20_ac97.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/tegra/tegra20_ac97.c b/sound/soc/tegra/tegra20_ac97.c
index affad46bf188..682ef33afb5f 100644
--- a/sound/soc/tegra/tegra20_ac97.c
+++ b/sound/soc/tegra/tegra20_ac97.c
@@ -377,7 +377,7 @@ static int tegra20_ac97_platform_probe(struct platform_device *pdev)
 	ret = clk_prepare_enable(ac97->clk_ac97);
 	if (ret) {
 		dev_err(&pdev->dev, "clk_enable failed: %d\n", ret);
-		goto err;
+		goto err_clk_put;
 	}
 
 	ret = snd_soc_set_ac97_ops(&tegra20_ac97_ops);
-- 
cgit v1.2.3


From ebfee0309d496d89279d612ee99023f9bbf4f34e Mon Sep 17 00:00:00 2001
From: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Date: Tue, 10 Jul 2018 14:58:48 +0200
Subject: usb: dwc3: rockchip: Fix PHY documentation links.

Commit 34962fb8070c ("docs: Fix more broken references") replaced the
broken reference to rockchip,dwc3-usb-phy.txt binding for the Qualcomm
DWC3 binding (qcom-dwc3-usb-phy.txt). That's wrong, so replace that
reference for the correct ones.

Fixes: 34962fb8070c ("docs: Fix more broken references")
Signed-off-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/usb/rockchip,dwc3.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
index 252a05c5d976..c8c4b00ecb94 100644
--- a/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
+++ b/Documentation/devicetree/bindings/usb/rockchip,dwc3.txt
@@ -16,7 +16,8 @@ A child node must exist to represent the core DWC3 IP block. The name of
 the node is not important. The content of the node is defined in dwc3.txt.
 
 Phy documentation is provided in the following places:
-Documentation/devicetree/bindings/phy/qcom-dwc3-usb-phy.txt
+Documentation/devicetree/bindings/phy/phy-rockchip-inno-usb2.txt - USB2.0 PHY
+Documentation/devicetree/bindings/phy/phy-rockchip-typec.txt     - Type-C PHY
 
 Example device nodes:
 
-- 
cgit v1.2.3


From 9e960c0298b5811e5a2c1ebceea6aa3b7bbc61c6 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:57 +0200
Subject: ASoC: meson: add axg tdm interface DT bindings documentation

Add the DT bindings documentation for axg's TDM interfaces

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/sound/amlogic,axg-tdm-iface.txt       | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/amlogic,axg-tdm-iface.txt

diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-iface.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-iface.txt
new file mode 100644
index 000000000000..cabfb26a5f22
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-tdm-iface.txt
@@ -0,0 +1,22 @@
+* Amlogic Audio TDM Interfaces
+
+Required properties:
+- compatible: 'amlogic,axg-tdm-iface'
+- clocks: list of clock phandle, one for each entry clock-names.
+- clock-names: should contain the following:
+  * "sclk" : bit clock.
+  * "lrclk": sample clock
+  * "mclk" : master clock
+	     -> optional if the interface is in clock slave mode.
+- #sound-dai-cells: must be 0.
+
+Example of TDM_A on the A113 SoC:
+
+tdmif_a: audio-controller@0 {
+	compatible = "amlogic,axg-tdm-iface";
+	#sound-dai-cells = <0>;
+	clocks = <&clkc_audio AUD_CLKID_MST_A_MCLK>,
+		 <&clkc_audio AUD_CLKID_MST_A_SCLK>,
+		 <&clkc_audio AUD_CLKID_MST_A_LRCLK>;
+	clock-names = "mclk", "sclk", "lrclk";
+};
-- 
cgit v1.2.3


From 1a11d88f499ceb69e9b4098ddc36866820335a54 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:58 +0200
Subject: ASoC: meson: add tdm formatter base driver

Add Amlogic's axg TDM core driver. On this SoC, tdm is bit more
complex than usual, mainly because the different TDM input decoders can
be attached to any of TDM pad interface, including the output pads.

For the this, TDM on this SoC is modeled like this:
- TDM interface provides the DAIs the codecs will be attached to.
  The main responsibility of this driver is to manage the pad format
  and the TDM clock rates.
- TDM Formatters: These are the entities which are actually dealing with
  the TDM signal. TDMOUT produce a TDM signal from the audio sample
  provided by FRDDR using the clocks provided the TDM interface. TDMIN
  feeds TODDR with audio sample using the clocks and TDM signal provided
  by the TDM Interface.
- TDM Streams: This provides the link between 1 DAI stream of the TDM
  interface and one (or more) TDM formatters.

This driver provides the TDM formatter and TDM stream operations.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig             |   4 +
 sound/soc/meson/Makefile            |   2 +
 sound/soc/meson/axg-tdm-formatter.c | 381 ++++++++++++++++++++++++++++++++++++
 sound/soc/meson/axg-tdm-formatter.h |  39 ++++
 sound/soc/meson/axg-tdm.h           |  74 +++++++
 5 files changed, 500 insertions(+)
 create mode 100644 sound/soc/meson/axg-tdm-formatter.c
 create mode 100644 sound/soc/meson/axg-tdm-formatter.h
 create mode 100644 sound/soc/meson/axg-tdm.h

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index 9408214b5854..80a88689491f 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -19,6 +19,10 @@ config SND_MESON_AXG_TODDR
 	  Select Y or M to add support for the frontend capture interfaces
 	  embedded in the Amlogic AXG SoC family
 
+config SND_MESON_AXG_TDM_FORMATTER
+	tristate
+	select REGMAP_MMIO
+
 config SND_MESON_AXG_SPDIFOUT
 	tristate "Amlogic AXG SPDIF Output Support"
 	imply SND_SOC_SPDIF
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index d51ae045ef08..a06b56a1c995 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -3,9 +3,11 @@
 snd-soc-meson-axg-fifo-objs := axg-fifo.o
 snd-soc-meson-axg-frddr-objs := axg-frddr.o
 snd-soc-meson-axg-toddr-objs := axg-toddr.o
+snd-soc-meson-axg-tdm-formatter-objs := axg-tdm-formatter.o
 snd-soc-meson-axg-spdifout-objs := axg-spdifout.o
 
 obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
 obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
 obj-$(CONFIG_SND_MESON_AXG_TODDR) += snd-soc-meson-axg-toddr.o
+obj-$(CONFIG_SND_MESON_AXG_TDM_FORMATTER) += snd-soc-meson-axg-tdm-formatter.o
 obj-$(CONFIG_SND_MESON_AXG_SPDIFOUT) += snd-soc-meson-axg-spdifout.o
diff --git a/sound/soc/meson/axg-tdm-formatter.c b/sound/soc/meson/axg-tdm-formatter.c
new file mode 100644
index 000000000000..43e390f9358a
--- /dev/null
+++ b/sound/soc/meson/axg-tdm-formatter.c
@@ -0,0 +1,381 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+
+#include "axg-tdm-formatter.h"
+
+struct axg_tdm_formatter {
+	struct list_head list;
+	struct axg_tdm_stream *stream;
+	const struct axg_tdm_formatter_driver *drv;
+	struct clk *pclk;
+	struct clk *sclk;
+	struct clk *lrclk;
+	struct clk *sclk_sel;
+	struct clk *lrclk_sel;
+	bool enabled;
+	struct regmap *map;
+};
+
+int axg_tdm_formatter_set_channel_masks(struct regmap *map,
+					struct axg_tdm_stream *ts,
+					unsigned int offset)
+{
+	unsigned int val, ch = ts->channels;
+	unsigned long mask;
+	int i, j;
+
+	/*
+	 * Distribute the channels of the stream over the available slots
+	 * of each TDM lane
+	 */
+	for (i = 0; i < AXG_TDM_NUM_LANES; i++) {
+		val = 0;
+		mask = ts->mask[i];
+
+		for (j = find_first_bit(&mask, 32);
+		     (j < 32) && ch;
+		     j = find_next_bit(&mask, 32, j + 1)) {
+			val |= 1 << j;
+			ch -= 1;
+		}
+
+		regmap_write(map, offset, val);
+		offset += regmap_get_reg_stride(map);
+	}
+
+	/*
+	 * If we still have channel left at the end of the process, it means
+	 * the stream has more channels than we can accommodate and we should
+	 * have caught this earlier.
+	 */
+	if (WARN_ON(ch != 0)) {
+		pr_err("channel mask error\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_formatter_set_channel_masks);
+
+static int axg_tdm_formatter_enable(struct axg_tdm_formatter *formatter)
+{
+	struct axg_tdm_stream *ts = formatter->stream;
+	bool invert = formatter->drv->invert_sclk;
+	int ret;
+
+	/* Do nothing if the formatter is already enabled */
+	if (formatter->enabled)
+		return 0;
+
+	/*
+	 * If sclk is inverted, invert it back and provide the inversion
+	 * required by the formatter
+	 */
+	invert ^= axg_tdm_sclk_invert(ts->iface->fmt);
+	ret = clk_set_phase(formatter->sclk, invert ? 180 : 0);
+	if (ret)
+		return ret;
+
+	/* Setup the stream parameter in the formatter */
+	ret = formatter->drv->ops->prepare(formatter->map, formatter->stream);
+	if (ret)
+		return ret;
+
+	/* Enable the signal clocks feeding the formatter */
+	ret = clk_prepare_enable(formatter->sclk);
+	if (ret)
+		return ret;
+
+	ret = clk_prepare_enable(formatter->lrclk);
+	if (ret) {
+		clk_disable_unprepare(formatter->sclk);
+		return ret;
+	}
+
+	/* Finally, actually enable the formatter */
+	formatter->drv->ops->enable(formatter->map);
+	formatter->enabled = true;
+
+	return 0;
+}
+
+static void axg_tdm_formatter_disable(struct axg_tdm_formatter *formatter)
+{
+	/* Do nothing if the formatter is already disabled */
+	if (!formatter->enabled)
+		return;
+
+	formatter->drv->ops->disable(formatter->map);
+	clk_disable_unprepare(formatter->lrclk);
+	clk_disable_unprepare(formatter->sclk);
+	formatter->enabled = false;
+}
+
+static int axg_tdm_formatter_attach(struct axg_tdm_formatter *formatter)
+{
+	struct axg_tdm_stream *ts = formatter->stream;
+	int ret = 0;
+
+	mutex_lock(&ts->lock);
+
+	/* Catch up if the stream is already running when we attach */
+	if (ts->ready) {
+		ret = axg_tdm_formatter_enable(formatter);
+		if (ret) {
+			pr_err("failed to enable formatter\n");
+			goto out;
+		}
+	}
+
+	list_add_tail(&formatter->list, &ts->formatter_list);
+out:
+	mutex_unlock(&ts->lock);
+	return ret;
+}
+
+static void axg_tdm_formatter_dettach(struct axg_tdm_formatter *formatter)
+{
+	struct axg_tdm_stream *ts = formatter->stream;
+
+	mutex_lock(&ts->lock);
+	list_del(&formatter->list);
+	mutex_unlock(&ts->lock);
+
+	axg_tdm_formatter_disable(formatter);
+}
+
+static int axg_tdm_formatter_power_up(struct axg_tdm_formatter *formatter,
+				      struct snd_soc_dapm_widget *w)
+{
+	struct axg_tdm_stream *ts = formatter->drv->ops->get_stream(w);
+	int ret;
+
+	/*
+	 * If we don't get a stream at this stage, it would mean that the
+	 * widget is powering up but is not attached to any backend DAI.
+	 * It should not happen, ever !
+	 */
+	if (WARN_ON(!ts))
+		return -ENODEV;
+
+	/* Clock our device */
+	ret = clk_prepare_enable(formatter->pclk);
+	if (ret)
+		return ret;
+
+	/* Reparent the bit clock to the TDM interface */
+	ret = clk_set_parent(formatter->sclk_sel, ts->iface->sclk);
+	if (ret)
+		goto disable_pclk;
+
+	/* Reparent the sample clock to the TDM interface */
+	ret = clk_set_parent(formatter->lrclk_sel, ts->iface->lrclk);
+	if (ret)
+		goto disable_pclk;
+
+	formatter->stream = ts;
+	ret = axg_tdm_formatter_attach(formatter);
+	if (ret)
+		goto disable_pclk;
+
+	return 0;
+
+disable_pclk:
+	clk_disable_unprepare(formatter->pclk);
+	return ret;
+}
+
+static void axg_tdm_formatter_power_down(struct axg_tdm_formatter *formatter)
+{
+	axg_tdm_formatter_dettach(formatter);
+	clk_disable_unprepare(formatter->pclk);
+	formatter->stream = NULL;
+}
+
+int axg_tdm_formatter_event(struct snd_soc_dapm_widget *w,
+			    struct snd_kcontrol *control,
+			    int event)
+{
+	struct snd_soc_component *c = snd_soc_dapm_to_component(w->dapm);
+	struct axg_tdm_formatter *formatter = snd_soc_component_get_drvdata(c);
+	int ret = 0;
+
+	switch (event) {
+	case SND_SOC_DAPM_PRE_PMU:
+		ret = axg_tdm_formatter_power_up(formatter, w);
+		break;
+
+	case SND_SOC_DAPM_PRE_PMD:
+		axg_tdm_formatter_power_down(formatter);
+		break;
+
+	default:
+		dev_err(c->dev, "Unexpected event %d\n", event);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_formatter_event);
+
+int axg_tdm_formatter_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct axg_tdm_formatter_driver *drv;
+	struct axg_tdm_formatter *formatter;
+	struct resource *res;
+	void __iomem *regs;
+	int ret;
+
+	drv = of_device_get_match_data(dev);
+	if (!drv) {
+		dev_err(dev, "failed to match device\n");
+		return -ENODEV;
+	}
+
+	formatter = devm_kzalloc(dev, sizeof(*formatter), GFP_KERNEL);
+	if (!formatter)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, formatter);
+	formatter->drv = drv;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	regs = devm_ioremap_resource(dev, res);
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
+
+	formatter->map = devm_regmap_init_mmio(dev, regs, drv->regmap_cfg);
+	if (IS_ERR(formatter->map)) {
+		dev_err(dev, "failed to init regmap: %ld\n",
+			PTR_ERR(formatter->map));
+		return PTR_ERR(formatter->map);
+	}
+
+	/* Peripharal clock */
+	formatter->pclk = devm_clk_get(dev, "pclk");
+	if (IS_ERR(formatter->pclk)) {
+		ret = PTR_ERR(formatter->pclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get pclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter bit clock */
+	formatter->sclk = devm_clk_get(dev, "sclk");
+	if (IS_ERR(formatter->sclk)) {
+		ret = PTR_ERR(formatter->sclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get sclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter sample clock */
+	formatter->lrclk = devm_clk_get(dev, "lrclk");
+	if (IS_ERR(formatter->lrclk)) {
+		ret = PTR_ERR(formatter->lrclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get lrclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter bit clock input multiplexer */
+	formatter->sclk_sel = devm_clk_get(dev, "sclk_sel");
+	if (IS_ERR(formatter->sclk_sel)) {
+		ret = PTR_ERR(formatter->sclk_sel);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get sclk_sel: %d\n", ret);
+		return ret;
+	}
+
+	/* Formatter sample clock input multiplexer */
+	formatter->lrclk_sel = devm_clk_get(dev, "lrclk_sel");
+	if (IS_ERR(formatter->lrclk_sel)) {
+		ret = PTR_ERR(formatter->lrclk_sel);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get lrclk_sel: %d\n", ret);
+		return ret;
+	}
+
+	return devm_snd_soc_register_component(dev, drv->component_drv,
+					       NULL, 0);
+}
+EXPORT_SYMBOL_GPL(axg_tdm_formatter_probe);
+
+int axg_tdm_stream_start(struct axg_tdm_stream *ts)
+{
+	struct axg_tdm_formatter *formatter;
+	int ret = 0;
+
+	mutex_lock(&ts->lock);
+	ts->ready = true;
+
+	/* Start all the formatters attached to the stream */
+	list_for_each_entry(formatter, &ts->formatter_list, list) {
+		ret = axg_tdm_formatter_enable(formatter);
+		if (ret) {
+			pr_err("failed to start tdm stream\n");
+			goto out;
+		}
+	}
+
+out:
+	mutex_unlock(&ts->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_start);
+
+void axg_tdm_stream_stop(struct axg_tdm_stream *ts)
+{
+	struct axg_tdm_formatter *formatter;
+
+	mutex_lock(&ts->lock);
+	ts->ready = false;
+
+	/* Stop all the formatters attached to the stream */
+	list_for_each_entry(formatter, &ts->formatter_list, list) {
+		axg_tdm_formatter_disable(formatter);
+	}
+
+	mutex_unlock(&ts->lock);
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_stop);
+
+struct axg_tdm_stream *axg_tdm_stream_alloc(struct axg_tdm_iface *iface)
+{
+	struct axg_tdm_stream *ts;
+
+	ts = kzalloc(sizeof(*ts), GFP_KERNEL);
+	if (ts) {
+		INIT_LIST_HEAD(&ts->formatter_list);
+		mutex_init(&ts->lock);
+		ts->iface = iface;
+	}
+
+	return ts;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_alloc);
+
+void axg_tdm_stream_free(struct axg_tdm_stream *ts)
+{
+	/*
+	 * If the list is not empty, it would mean that one of the formatter
+	 * widget is still powered and attached to the interface while we
+	 * we are removing the TDM DAI. It should not be possible
+	 */
+	WARN_ON(!list_empty(&ts->formatter_list));
+	mutex_destroy(&ts->lock);
+	kfree(ts);
+}
+EXPORT_SYMBOL_GPL(axg_tdm_stream_free);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM formatter driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-tdm-formatter.h b/sound/soc/meson/axg-tdm-formatter.h
new file mode 100644
index 000000000000..cf947caf3cb1
--- /dev/null
+++ b/sound/soc/meson/axg-tdm-formatter.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ *
+ * Copyright (c) 2018 Baylibre SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef _MESON_AXG_TDM_FORMATTER_H
+#define _MESON_AXG_TDM_FORMATTER_H
+
+#include "axg-tdm.h"
+
+struct platform_device;
+struct regmap;
+struct snd_soc_dapm_widget;
+struct snd_kcontrol;
+
+struct axg_tdm_formatter_ops {
+	struct axg_tdm_stream *(*get_stream)(struct snd_soc_dapm_widget *w);
+	void (*enable)(struct regmap *map);
+	void (*disable)(struct regmap *map);
+	int (*prepare)(struct regmap *map, struct axg_tdm_stream *ts);
+};
+
+struct axg_tdm_formatter_driver {
+	const struct snd_soc_component_driver *component_drv;
+	const struct regmap_config *regmap_cfg;
+	const struct axg_tdm_formatter_ops *ops;
+	bool invert_sclk;
+};
+
+int axg_tdm_formatter_set_channel_masks(struct regmap *map,
+					struct axg_tdm_stream *ts,
+					unsigned int offset);
+int axg_tdm_formatter_event(struct snd_soc_dapm_widget *w,
+			    struct snd_kcontrol *control,
+			    int event);
+int axg_tdm_formatter_probe(struct platform_device *pdev);
+
+#endif /* _MESON_AXG_TDM_FORMATTER_H */
diff --git a/sound/soc/meson/axg-tdm.h b/sound/soc/meson/axg-tdm.h
new file mode 100644
index 000000000000..435d95b86457
--- /dev/null
+++ b/sound/soc/meson/axg-tdm.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT)
+ *
+ * Copyright (c) 2018 Baylibre SAS.
+ * Author: Jerome Brunet <jbrunet@baylibre.com>
+ */
+
+#ifndef _MESON_AXG_TDM_H
+#define _MESON_AXG_TDM_H
+
+#include <linux/clk.h>
+#include <linux/regmap.h>
+#include <sound/pcm.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#define AXG_TDM_NUM_LANES	4
+#define AXG_TDM_CHANNEL_MAX	128
+#define AXG_TDM_RATES		(SNDRV_PCM_RATE_5512 |		\
+				 SNDRV_PCM_RATE_8000_192000)
+#define AXG_TDM_FORMATS		(SNDRV_PCM_FMTBIT_S8 |		\
+				 SNDRV_PCM_FMTBIT_S16_LE |	\
+				 SNDRV_PCM_FMTBIT_S20_LE |	\
+				 SNDRV_PCM_FMTBIT_S24_LE |	\
+				 SNDRV_PCM_FMTBIT_S32_LE)
+
+struct axg_tdm_iface {
+	struct clk *sclk;
+	struct clk *lrclk;
+	struct clk *mclk;
+	unsigned long mclk_rate;
+
+	/* format is common to all the DAIs of the iface */
+	unsigned int fmt;
+	unsigned int slots;
+	unsigned int slot_width;
+
+	/* For component wide symmetry */
+	int rate;
+};
+
+static inline bool axg_tdm_lrclk_invert(unsigned int fmt)
+{
+	return (fmt & SND_SOC_DAIFMT_I2S) ^
+		!!(fmt & (SND_SOC_DAIFMT_IB_IF | SND_SOC_DAIFMT_NB_IF));
+}
+
+static inline bool axg_tdm_sclk_invert(unsigned int fmt)
+{
+	return fmt & (SND_SOC_DAIFMT_IB_IF | SND_SOC_DAIFMT_IB_NF);
+}
+
+struct axg_tdm_stream {
+	struct axg_tdm_iface *iface;
+	struct list_head formatter_list;
+	struct mutex lock;
+	unsigned int channels;
+	unsigned int width;
+	unsigned int physical_width;
+	u32 *mask;
+	bool ready;
+};
+
+struct axg_tdm_stream *axg_tdm_stream_alloc(struct axg_tdm_iface *iface);
+void axg_tdm_stream_free(struct axg_tdm_stream *ts);
+int axg_tdm_stream_start(struct axg_tdm_stream *ts);
+void axg_tdm_stream_stop(struct axg_tdm_stream *ts);
+
+static inline int axg_tdm_stream_reset(struct axg_tdm_stream *ts)
+{
+	axg_tdm_stream_stop(ts);
+	return axg_tdm_stream_start(ts);
+}
+
+#endif /* _MESON_AXG_TDM_H */
-- 
cgit v1.2.3


From d60e4f1e4be5e2dfb55fb084b119aed094227a35 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:42:59 +0200
Subject: ASoC: meson: add tdm interface driver

Add Amlogic's axg TDM interface driver. This driver manages the format
and clocks provided on the pads.

On this SoC, each stream direction provides 4 serial lanes. This makes
a maximum of 8 channels in i2s modes and 128 channels in DSP modes.

While each lanes operate on the same slot number (same bit clock), they
may have different TDM masks. This requires to provide a function to let
the card set the 4 masks, in lieu of the usual set_tdm_slots() callback
of the dai driver.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig             |   4 +
 sound/soc/meson/Makefile            |   2 +
 sound/soc/meson/axg-tdm-interface.c | 542 ++++++++++++++++++++++++++++++++++++
 sound/soc/meson/axg-tdm.h           |   4 +
 4 files changed, 552 insertions(+)
 create mode 100644 sound/soc/meson/axg-tdm-interface.c

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index 80a88689491f..869b359c2ce7 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -23,6 +23,10 @@ config SND_MESON_AXG_TDM_FORMATTER
 	tristate
 	select REGMAP_MMIO
 
+config SND_MESON_AXG_TDM_INTERFACE
+	tristate
+	select SND_MESON_AXG_TDM_FORMATTER
+
 config SND_MESON_AXG_SPDIFOUT
 	tristate "Amlogic AXG SPDIF Output Support"
 	imply SND_SOC_SPDIF
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index a06b56a1c995..1a8eb77402e3 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -4,10 +4,12 @@ snd-soc-meson-axg-fifo-objs := axg-fifo.o
 snd-soc-meson-axg-frddr-objs := axg-frddr.o
 snd-soc-meson-axg-toddr-objs := axg-toddr.o
 snd-soc-meson-axg-tdm-formatter-objs := axg-tdm-formatter.o
+snd-soc-meson-axg-tdm-interface-objs := axg-tdm-interface.o
 snd-soc-meson-axg-spdifout-objs := axg-spdifout.o
 
 obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
 obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
 obj-$(CONFIG_SND_MESON_AXG_TODDR) += snd-soc-meson-axg-toddr.o
 obj-$(CONFIG_SND_MESON_AXG_TDM_FORMATTER) += snd-soc-meson-axg-tdm-formatter.o
+obj-$(CONFIG_SND_MESON_AXG_TDM_INTERFACE) += snd-soc-meson-axg-tdm-interface.o
 obj-$(CONFIG_SND_MESON_AXG_SPDIFOUT) += snd-soc-meson-axg-spdifout.o
diff --git a/sound/soc/meson/axg-tdm-interface.c b/sound/soc/meson/axg-tdm-interface.c
new file mode 100644
index 000000000000..7b8baf46d968
--- /dev/null
+++ b/sound/soc/meson/axg-tdm-interface.c
@@ -0,0 +1,542 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm.h"
+
+enum {
+	TDM_IFACE_PAD,
+	TDM_IFACE_LOOPBACK,
+};
+
+static unsigned int axg_tdm_slots_total(u32 *mask)
+{
+	unsigned int slots = 0;
+	int i;
+
+	if (!mask)
+		return 0;
+
+	/* Count the total number of slots provided by all 4 lanes */
+	for (i = 0; i < AXG_TDM_NUM_LANES; i++)
+		slots += hweight32(mask[i]);
+
+	return slots;
+}
+
+int axg_tdm_set_tdm_slots(struct snd_soc_dai *dai, u32 *tx_mask,
+			  u32 *rx_mask, unsigned int slots,
+			  unsigned int slot_width)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	struct axg_tdm_stream *tx = (struct axg_tdm_stream *)
+		dai->playback_dma_data;
+	struct axg_tdm_stream *rx = (struct axg_tdm_stream *)
+		dai->capture_dma_data;
+	unsigned int tx_slots, rx_slots;
+
+	tx_slots = axg_tdm_slots_total(tx_mask);
+	rx_slots = axg_tdm_slots_total(rx_mask);
+
+	/* We should at least have a slot for a valid interface */
+	if (!tx_slots && !rx_slots) {
+		dev_err(dai->dev, "interface has no slot\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Amend the dai driver channel number and let dpcm channel merge do
+	 * its job
+	 */
+	if (tx) {
+		tx->mask = tx_mask;
+		dai->driver->playback.channels_max = tx_slots;
+	}
+
+	if (rx) {
+		rx->mask = rx_mask;
+		dai->driver->capture.channels_max = rx_slots;
+	}
+
+	iface->slots = slots;
+
+	switch (slot_width) {
+	case 0:
+		/* defaults width to 32 if not provided */
+		iface->slot_width = 32;
+		break;
+	case 8:
+	case 16:
+	case 24:
+	case 32:
+		iface->slot_width = slot_width;
+		break;
+	default:
+		dev_err(dai->dev, "unsupported slot width: %d\n", slot_width);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(axg_tdm_set_tdm_slots);
+
+static int axg_tdm_iface_set_sysclk(struct snd_soc_dai *dai, int clk_id,
+				    unsigned int freq, int dir)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	int ret = -ENOTSUPP;
+
+	if (dir == SND_SOC_CLOCK_OUT && clk_id == 0) {
+		if (!iface->mclk) {
+			dev_warn(dai->dev, "master clock not provided\n");
+		} else {
+			ret = clk_set_rate(iface->mclk, freq);
+			if (!ret)
+				iface->mclk_rate = freq;
+		}
+	}
+
+	return ret;
+}
+
+static int axg_tdm_iface_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+
+	/* These modes are not supported */
+	if (fmt & (SND_SOC_DAIFMT_CBS_CFM | SND_SOC_DAIFMT_CBM_CFS)) {
+		dev_err(dai->dev, "only CBS_CFS and CBM_CFM are supported\n");
+		return -EINVAL;
+	}
+
+	/* If the TDM interface is the clock master, it requires mclk */
+	if (!iface->mclk && (fmt & SND_SOC_DAIFMT_CBS_CFS)) {
+		dev_err(dai->dev, "cpu clock master: mclk missing\n");
+		return -ENODEV;
+	}
+
+	iface->fmt = fmt;
+	return 0;
+}
+
+static int axg_tdm_iface_startup(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	struct axg_tdm_stream *ts =
+		snd_soc_dai_get_dma_data(dai, substream);
+	int ret;
+
+	if (!axg_tdm_slots_total(ts->mask)) {
+		dev_err(dai->dev, "interface has not slots\n");
+		return -EINVAL;
+	}
+
+	/* Apply component wide rate symmetry */
+	if (dai->component->active) {
+		ret = snd_pcm_hw_constraint_single(substream->runtime,
+						   SNDRV_PCM_HW_PARAM_RATE,
+						   iface->rate);
+		if (ret < 0) {
+			dev_err(dai->dev,
+				"can't set iface rate constraint\n");
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int axg_tdm_iface_set_stream(struct snd_pcm_substream *substream,
+				    struct snd_pcm_hw_params *params,
+				    struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
+	unsigned int channels = params_channels(params);
+	unsigned int width = params_width(params);
+
+	/* Save rate and sample_bits for component symmetry */
+	iface->rate = params_rate(params);
+
+	/* Make sure this interface can cope with the stream */
+	if (axg_tdm_slots_total(ts->mask) < channels) {
+		dev_err(dai->dev, "not enough slots for channels\n");
+		return -EINVAL;
+	}
+
+	if (iface->slot_width < width) {
+		dev_err(dai->dev, "incompatible slots width for stream\n");
+		return -EINVAL;
+	}
+
+	/* Save the parameter for tdmout/tdmin widgets */
+	ts->physical_width = params_physical_width(params);
+	ts->width = params_width(params);
+	ts->channels = params_channels(params);
+
+	return 0;
+}
+
+static int axg_tdm_iface_set_lrclk(struct snd_soc_dai *dai,
+				   struct snd_pcm_hw_params *params)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	unsigned int ratio_num;
+	int ret;
+
+	ret = clk_set_rate(iface->lrclk, params_rate(params));
+	if (ret) {
+		dev_err(dai->dev, "setting sample clock failed: %d\n", ret);
+		return ret;
+	}
+
+	switch (iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+		/* 50% duty cycle ratio */
+		ratio_num = 1;
+		break;
+
+	case SND_SOC_DAIFMT_DSP_A:
+	case SND_SOC_DAIFMT_DSP_B:
+		/*
+		 * A zero duty cycle ratio will result in setting the mininum
+		 * ratio possible which, for this clock, is 1 cycle of the
+		 * parent bclk clock high and the rest low, This is exactly
+		 * what we want here.
+		 */
+		ratio_num = 0;
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	ret = clk_set_duty_cycle(iface->lrclk, ratio_num, 2);
+	if (ret) {
+		dev_err(dai->dev,
+			"setting sample clock duty cycle failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Set sample clock inversion */
+	ret = clk_set_phase(iface->lrclk,
+			    axg_tdm_lrclk_invert(iface->fmt) ? 180 : 0);
+	if (ret) {
+		dev_err(dai->dev,
+			"setting sample clock phase failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_tdm_iface_set_sclk(struct snd_soc_dai *dai,
+				  struct snd_pcm_hw_params *params)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	unsigned long srate;
+	int ret;
+
+	srate = iface->slots * iface->slot_width * params_rate(params);
+
+	if (!iface->mclk_rate) {
+		/* If no specific mclk is requested, default to bit clock * 4 */
+		clk_set_rate(iface->mclk, 4 * srate);
+	} else {
+		/* Check if we can actually get the bit clock from mclk */
+		if (iface->mclk_rate % srate) {
+			dev_err(dai->dev,
+				"can't derive sclk %lu from mclk %lu\n",
+				srate, iface->mclk_rate);
+			return -EINVAL;
+		}
+	}
+
+	ret = clk_set_rate(iface->sclk, srate);
+	if (ret) {
+		dev_err(dai->dev, "setting bit clock failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Set the bit clock inversion */
+	ret = clk_set_phase(iface->sclk,
+			    axg_tdm_sclk_invert(iface->fmt) ? 0 : 180);
+	if (ret) {
+		dev_err(dai->dev, "setting bit clock phase failed: %d\n", ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int axg_tdm_iface_hw_params(struct snd_pcm_substream *substream,
+				   struct snd_pcm_hw_params *params,
+				   struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+	int ret;
+
+	switch (iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+		if (iface->slots > 2) {
+			dev_err(dai->dev, "bad slot number for format: %d\n",
+				iface->slots);
+			return -EINVAL;
+		}
+		break;
+
+	case SND_SOC_DAI_FORMAT_DSP_A:
+	case SND_SOC_DAI_FORMAT_DSP_B:
+		break;
+
+	default:
+		dev_err(dai->dev, "unsupported dai format\n");
+		return -EINVAL;
+	}
+
+	ret = axg_tdm_iface_set_stream(substream, params, dai);
+	if (ret)
+		return ret;
+
+	if (iface->fmt & SND_SOC_DAIFMT_CBS_CFS) {
+		ret = axg_tdm_iface_set_sclk(dai, params);
+		if (ret)
+			return ret;
+
+		ret = axg_tdm_iface_set_lrclk(dai, params);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int axg_tdm_iface_hw_free(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
+
+	/* Stop all attached formatters */
+	axg_tdm_stream_stop(ts);
+
+	return 0;
+}
+
+static int axg_tdm_iface_prepare(struct snd_pcm_substream *substream,
+				 struct snd_soc_dai *dai)
+{
+	struct axg_tdm_stream *ts = snd_soc_dai_get_dma_data(dai, substream);
+
+	/* Force all attached formatters to update */
+	return axg_tdm_stream_reset(ts);
+}
+
+static int axg_tdm_iface_remove_dai(struct snd_soc_dai *dai)
+{
+	if (dai->capture_dma_data)
+		axg_tdm_stream_free(dai->capture_dma_data);
+
+	if (dai->playback_dma_data)
+		axg_tdm_stream_free(dai->playback_dma_data);
+
+	return 0;
+}
+
+static int axg_tdm_iface_probe_dai(struct snd_soc_dai *dai)
+{
+	struct axg_tdm_iface *iface = snd_soc_dai_get_drvdata(dai);
+
+	if (dai->capture_widget) {
+		dai->capture_dma_data = axg_tdm_stream_alloc(iface);
+		if (!dai->capture_dma_data)
+			return -ENOMEM;
+	}
+
+	if (dai->playback_widget) {
+		dai->playback_dma_data = axg_tdm_stream_alloc(iface);
+		if (!dai->playback_dma_data) {
+			axg_tdm_iface_remove_dai(dai);
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_dai_ops axg_tdm_iface_ops = {
+	.set_sysclk	= axg_tdm_iface_set_sysclk,
+	.set_fmt	= axg_tdm_iface_set_fmt,
+	.startup	= axg_tdm_iface_startup,
+	.hw_params	= axg_tdm_iface_hw_params,
+	.prepare	= axg_tdm_iface_prepare,
+	.hw_free	= axg_tdm_iface_hw_free,
+};
+
+/* TDM Backend DAIs */
+static const struct snd_soc_dai_driver axg_tdm_iface_dai_drv[] = {
+	[TDM_IFACE_PAD] = {
+		.name = "TDM Pad",
+		.playback = {
+			.stream_name	= "Playback",
+			.channels_min	= 1,
+			.channels_max	= AXG_TDM_CHANNEL_MAX,
+			.rates		= AXG_TDM_RATES,
+			.formats	= AXG_TDM_FORMATS,
+		},
+		.capture = {
+			.stream_name	= "Capture",
+			.channels_min	= 1,
+			.channels_max	= AXG_TDM_CHANNEL_MAX,
+			.rates		= AXG_TDM_RATES,
+			.formats	= AXG_TDM_FORMATS,
+		},
+		.id = TDM_IFACE_PAD,
+		.ops = &axg_tdm_iface_ops,
+		.probe = axg_tdm_iface_probe_dai,
+		.remove = axg_tdm_iface_remove_dai,
+	},
+	[TDM_IFACE_LOOPBACK] = {
+		.name = "TDM Loopback",
+		.capture = {
+			.stream_name	= "Loopback",
+			.channels_min	= 1,
+			.channels_max	= AXG_TDM_CHANNEL_MAX,
+			.rates		= AXG_TDM_RATES,
+			.formats	= AXG_TDM_FORMATS,
+		},
+		.id = TDM_IFACE_LOOPBACK,
+		.ops = &axg_tdm_iface_ops,
+		.probe = axg_tdm_iface_probe_dai,
+		.remove = axg_tdm_iface_remove_dai,
+	},
+};
+
+static int axg_tdm_iface_set_bias_level(struct snd_soc_component *component,
+					enum snd_soc_bias_level level)
+{
+	struct axg_tdm_iface *iface = snd_soc_component_get_drvdata(component);
+	enum snd_soc_bias_level now =
+		snd_soc_component_get_bias_level(component);
+	int ret = 0;
+
+	switch (level) {
+	case SND_SOC_BIAS_PREPARE:
+		if (now == SND_SOC_BIAS_STANDBY)
+			ret = clk_prepare_enable(iface->mclk);
+		break;
+
+	case SND_SOC_BIAS_STANDBY:
+		if (now == SND_SOC_BIAS_PREPARE)
+			clk_disable_unprepare(iface->mclk);
+		break;
+
+	case SND_SOC_BIAS_OFF:
+	case SND_SOC_BIAS_ON:
+		break;
+	}
+
+	return ret;
+}
+
+static const struct snd_soc_component_driver axg_tdm_iface_component_drv = {
+	.set_bias_level	= axg_tdm_iface_set_bias_level,
+};
+
+static const struct of_device_id axg_tdm_iface_of_match[] = {
+	{ .compatible = "amlogic,axg-tdm-iface", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, axg_tdm_iface_of_match);
+
+static int axg_tdm_iface_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct snd_soc_dai_driver *dai_drv;
+	struct axg_tdm_iface *iface;
+	int ret, i;
+
+	iface = devm_kzalloc(dev, sizeof(*iface), GFP_KERNEL);
+	if (!iface)
+		return -ENOMEM;
+	platform_set_drvdata(pdev, iface);
+
+	/*
+	 * Duplicate dai driver: depending on the slot masks configuration
+	 * We'll change the number of channel provided by DAI stream, so dpcm
+	 * channel merge can be done properly
+	 */
+	dai_drv = devm_kcalloc(dev, ARRAY_SIZE(axg_tdm_iface_dai_drv),
+			       sizeof(*dai_drv), GFP_KERNEL);
+	if (!dai_drv)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(axg_tdm_iface_dai_drv); i++)
+		memcpy(&dai_drv[i], &axg_tdm_iface_dai_drv[i],
+		       sizeof(*dai_drv));
+
+	/* Bit clock provided on the pad */
+	iface->sclk = devm_clk_get(dev, "sclk");
+	if (IS_ERR(iface->sclk)) {
+		ret = PTR_ERR(iface->sclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get sclk: %d\n", ret);
+		return ret;
+	}
+
+	/* Sample clock provided on the pad */
+	iface->lrclk = devm_clk_get(dev, "lrclk");
+	if (IS_ERR(iface->lrclk)) {
+		ret = PTR_ERR(iface->lrclk);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get lrclk: %d\n", ret);
+		return ret;
+	}
+
+	/*
+	 * mclk maybe be missing when the cpu dai is in slave mode and
+	 * the codec does not require it to provide a master clock.
+	 * At this point, ignore the error if mclk is missing. We'll
+	 * throw an error if the cpu dai is master and mclk is missing
+	 */
+	iface->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(iface->mclk)) {
+		ret = PTR_ERR(iface->mclk);
+		if (ret == -ENOENT) {
+			iface->mclk = NULL;
+		} else {
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "failed to get mclk: %d\n", ret);
+			return ret;
+		}
+	}
+
+	return devm_snd_soc_register_component(dev,
+					&axg_tdm_iface_component_drv, dai_drv,
+					ARRAY_SIZE(axg_tdm_iface_dai_drv));
+}
+
+static struct platform_driver axg_tdm_iface_pdrv = {
+	.probe = axg_tdm_iface_probe,
+	.driver = {
+		.name = "axg-tdm-iface",
+		.of_match_table = axg_tdm_iface_of_match,
+	},
+};
+module_platform_driver(axg_tdm_iface_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM interface driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/meson/axg-tdm.h b/sound/soc/meson/axg-tdm.h
index 435d95b86457..e578b6f40a07 100644
--- a/sound/soc/meson/axg-tdm.h
+++ b/sound/soc/meson/axg-tdm.h
@@ -71,4 +71,8 @@ static inline int axg_tdm_stream_reset(struct axg_tdm_stream *ts)
 	return axg_tdm_stream_start(ts);
 }
 
+int axg_tdm_set_tdm_slots(struct snd_soc_dai *dai, u32 *tx_mask,
+			  u32 *rx_mask, unsigned int slots,
+			  unsigned int slot_width);
+
 #endif /* _MESON_AXG_TDM_H */
-- 
cgit v1.2.3


From c41c2a355b86368608377eaf3df442ec0f342f1e Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:43:00 +0200
Subject: ASoC: meson: add tdm output driver

Add Amlogic's axg tdm output driver which pulls data from FRDDR fifo
and produce the TDM signals for 4 output lanes.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig      |   8 ++
 sound/soc/meson/Makefile     |   2 +
 sound/soc/meson/axg-tdmout.c | 259 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 269 insertions(+)
 create mode 100644 sound/soc/meson/axg-tdmout.c

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index 869b359c2ce7..08a522b77749 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -27,6 +27,14 @@ config SND_MESON_AXG_TDM_INTERFACE
 	tristate
 	select SND_MESON_AXG_TDM_FORMATTER
 
+config SND_MESON_AXG_TDMOUT
+	tristate "Amlogic AXG TDM Output Support"
+	select SND_MESON_AXG_TDM_FORMATTER
+	select SND_MESON_AXG_TDM_INTERFACE
+	help
+	  Select Y or M to add support for TDM output formatter embedded
+	  in the Amlogic AXG SoC family
+
 config SND_MESON_AXG_SPDIFOUT
 	tristate "Amlogic AXG SPDIF Output Support"
 	imply SND_SOC_SPDIF
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index 1a8eb77402e3..a665c6b76a95 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -5,6 +5,7 @@ snd-soc-meson-axg-frddr-objs := axg-frddr.o
 snd-soc-meson-axg-toddr-objs := axg-toddr.o
 snd-soc-meson-axg-tdm-formatter-objs := axg-tdm-formatter.o
 snd-soc-meson-axg-tdm-interface-objs := axg-tdm-interface.o
+snd-soc-meson-axg-tdmout-objs := axg-tdmout.o
 snd-soc-meson-axg-spdifout-objs := axg-spdifout.o
 
 obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
@@ -12,4 +13,5 @@ obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
 obj-$(CONFIG_SND_MESON_AXG_TODDR) += snd-soc-meson-axg-toddr.o
 obj-$(CONFIG_SND_MESON_AXG_TDM_FORMATTER) += snd-soc-meson-axg-tdm-formatter.o
 obj-$(CONFIG_SND_MESON_AXG_TDM_INTERFACE) += snd-soc-meson-axg-tdm-interface.o
+obj-$(CONFIG_SND_MESON_AXG_TDMOUT) += snd-soc-meson-axg-tdmout.o
 obj-$(CONFIG_SND_MESON_AXG_SPDIFOUT) += snd-soc-meson-axg-spdifout.o
diff --git a/sound/soc/meson/axg-tdmout.c b/sound/soc/meson/axg-tdmout.c
new file mode 100644
index 000000000000..f73368ee1088
--- /dev/null
+++ b/sound/soc/meson/axg-tdmout.c
@@ -0,0 +1,259 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm-formatter.h"
+
+#define TDMOUT_CTRL0			0x00
+#define  TDMOUT_CTRL0_BITNUM_MASK	GENMASK(4, 0)
+#define  TDMOUT_CTRL0_BITNUM(x)		((x) << 0)
+#define  TDMOUT_CTRL0_SLOTNUM_MASK	GENMASK(9, 5)
+#define  TDMOUT_CTRL0_SLOTNUM(x)	((x) << 5)
+#define  TDMOUT_CTRL0_INIT_BITNUM_MASK	GENMASK(19, 15)
+#define  TDMOUT_CTRL0_INIT_BITNUM(x)	((x) << 15)
+#define  TDMOUT_CTRL0_ENABLE		BIT(31)
+#define  TDMOUT_CTRL0_RST_OUT		BIT(29)
+#define  TDMOUT_CTRL0_RST_IN		BIT(28)
+#define TDMOUT_CTRL1			0x04
+#define  TDMOUT_CTRL1_TYPE_MASK		GENMASK(6, 4)
+#define  TDMOUT_CTRL1_TYPE(x)		((x) << 4)
+#define  TDMOUT_CTRL1_MSB_POS_MASK	GENMASK(12, 8)
+#define  TDMOUT_CTRL1_MSB_POS(x)	((x) << 8)
+#define  TDMOUT_CTRL1_SEL_SHIFT		24
+#define  TDMOUT_CTRL1_GAIN_EN		26
+#define  TDMOUT_CTRL1_WS_INV		BIT(28)
+#define TDMOUT_SWAP			0x08
+#define TDMOUT_MASK0			0x0c
+#define TDMOUT_MASK1			0x10
+#define TDMOUT_MASK2			0x14
+#define TDMOUT_MASK3			0x18
+#define TDMOUT_STAT			0x1c
+#define TDMOUT_GAIN0			0x20
+#define TDMOUT_GAIN1			0x24
+#define TDMOUT_MUTE_VAL			0x28
+#define TDMOUT_MUTE0			0x2c
+#define TDMOUT_MUTE1			0x30
+#define TDMOUT_MUTE2			0x34
+#define TDMOUT_MUTE3			0x38
+#define TDMOUT_MASK_VAL			0x3c
+
+static const struct regmap_config axg_tdmout_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= TDMOUT_MASK_VAL,
+};
+
+static const struct snd_kcontrol_new axg_tdmout_controls[] = {
+	SOC_DOUBLE("Lane 0 Volume", TDMOUT_GAIN0,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 1 Volume", TDMOUT_GAIN0, 16, 24, 255, 0),
+	SOC_DOUBLE("Lane 2 Volume", TDMOUT_GAIN1,  0,  8, 255, 0),
+	SOC_DOUBLE("Lane 3 Volume", TDMOUT_GAIN1, 16, 24, 255, 0),
+	SOC_SINGLE("Gain Enable Switch", TDMOUT_CTRL1,
+		   TDMOUT_CTRL1_GAIN_EN, 1, 0),
+};
+
+static const char * const tdmout_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2",
+};
+
+static SOC_ENUM_SINGLE_DECL(axg_tdmout_sel_enum, TDMOUT_CTRL1,
+			    TDMOUT_CTRL1_SEL_SHIFT, tdmout_sel_texts);
+
+static const struct snd_kcontrol_new axg_tdmout_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_tdmout_sel_enum);
+
+static struct snd_soc_dai *
+axg_tdmout_get_be(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dapm_path *p = NULL;
+	struct snd_soc_dai *be;
+
+	snd_soc_dapm_widget_for_each_sink_path(w, p) {
+		if (!p->connect)
+			continue;
+
+		if (p->sink->id == snd_soc_dapm_dai_in)
+			return (struct snd_soc_dai *)p->sink->priv;
+
+		be = axg_tdmout_get_be(p->sink);
+		if (be)
+			return be;
+	}
+
+	return NULL;
+}
+
+static struct axg_tdm_stream *
+axg_tdmout_get_tdm_stream(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dai *be = axg_tdmout_get_be(w);
+
+	if (!be)
+		return NULL;
+
+	return be->playback_dma_data;
+}
+
+static void axg_tdmout_enable(struct regmap *map)
+{
+	/* Apply both reset */
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_RST_OUT | TDMOUT_CTRL0_RST_IN, 0);
+
+	/* Clear out reset before in reset */
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_RST_OUT, TDMOUT_CTRL0_RST_OUT);
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_RST_IN,  TDMOUT_CTRL0_RST_IN);
+
+	/* Actually enable tdmout */
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_ENABLE, TDMOUT_CTRL0_ENABLE);
+}
+
+static void axg_tdmout_disable(struct regmap *map)
+{
+	regmap_update_bits(map, TDMOUT_CTRL0, TDMOUT_CTRL0_ENABLE, 0);
+}
+
+static int axg_tdmout_prepare(struct regmap *map, struct axg_tdm_stream *ts)
+{
+	unsigned int val = 0;
+
+	/* Set the stream skew */
+	switch (ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_DSP_A:
+		val |= TDMOUT_CTRL0_INIT_BITNUM(1);
+		break;
+
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+	case SND_SOC_DAIFMT_DSP_B:
+		val |= TDMOUT_CTRL0_INIT_BITNUM(2);
+		break;
+
+	default:
+		pr_err("Unsupported format: %u\n",
+		       ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK);
+		return -EINVAL;
+	}
+
+	/* Set the slot width */
+	val |= TDMOUT_CTRL0_BITNUM(ts->iface->slot_width - 1);
+
+	/* Set the slot number */
+	val |= TDMOUT_CTRL0_SLOTNUM(ts->iface->slots - 1);
+
+	regmap_update_bits(map, TDMOUT_CTRL0,
+			   TDMOUT_CTRL0_INIT_BITNUM_MASK |
+			   TDMOUT_CTRL0_BITNUM_MASK |
+			   TDMOUT_CTRL0_SLOTNUM_MASK, val);
+
+	/* Set the sample width */
+	val = TDMOUT_CTRL1_MSB_POS(ts->width - 1);
+
+	/* FIFO data are arranged in chunks of 64bits */
+	switch (ts->physical_width) {
+	case 8:
+		/* 8 samples of 8 bits */
+		val |= TDMOUT_CTRL1_TYPE(0);
+		break;
+	case 16:
+		/* 4 samples of 16 bits - right justified */
+		val |= TDMOUT_CTRL1_TYPE(2);
+		break;
+	case 32:
+		/* 2 samples of 32 bits - right justified */
+		val |= TDMOUT_CTRL1_TYPE(4);
+		break;
+	default:
+		pr_err("Unsupported physical width: %u\n",
+		       ts->physical_width);
+		return -EINVAL;
+	}
+
+	/* If the sample clock is inverted, invert it back for the formatter */
+	if (axg_tdm_lrclk_invert(ts->iface->fmt))
+		val |= TDMOUT_CTRL1_WS_INV;
+
+	regmap_update_bits(map, TDMOUT_CTRL1,
+			   (TDMOUT_CTRL1_TYPE_MASK | TDMOUT_CTRL1_MSB_POS_MASK |
+			    TDMOUT_CTRL1_WS_INV), val);
+
+	/* Set static swap mask configuration */
+	regmap_write(map, TDMOUT_SWAP, 0x76543210);
+
+	return axg_tdm_formatter_set_channel_masks(map, ts, TDMOUT_MASK0);
+}
+
+static const struct snd_soc_dapm_widget axg_tdmout_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_tdmout_in_mux),
+	SND_SOC_DAPM_PGA_E("ENC", SND_SOC_NOPM, 0, 0, NULL, 0,
+			   axg_tdm_formatter_event,
+			   (SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD)),
+	SND_SOC_DAPM_AIF_OUT("OUT", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_tdmout_dapm_routes[] = {
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "ENC", NULL, "SRC SEL" },
+	{ "OUT", NULL, "ENC" },
+};
+
+static const struct snd_soc_component_driver axg_tdmout_component_drv = {
+	.controls		= axg_tdmout_controls,
+	.num_controls		= ARRAY_SIZE(axg_tdmout_controls),
+	.dapm_widgets		= axg_tdmout_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_tdmout_dapm_widgets),
+	.dapm_routes		= axg_tdmout_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_tdmout_dapm_routes),
+};
+
+static const struct axg_tdm_formatter_ops axg_tdmout_ops = {
+	.get_stream	= axg_tdmout_get_tdm_stream,
+	.prepare	= axg_tdmout_prepare,
+	.enable		= axg_tdmout_enable,
+	.disable	= axg_tdmout_disable,
+};
+
+static const struct axg_tdm_formatter_driver axg_tdmout_drv = {
+	.component_drv	= &axg_tdmout_component_drv,
+	.regmap_cfg	= &axg_tdmout_regmap_cfg,
+	.ops		= &axg_tdmout_ops,
+	.invert_sclk	= true,
+};
+
+static const struct of_device_id axg_tdmout_of_match[] = {
+	{
+		.compatible = "amlogic,axg-tdmout",
+		.data = &axg_tdmout_drv,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_tdmout_of_match);
+
+static struct platform_driver axg_tdmout_pdrv = {
+	.probe = axg_tdm_formatter_probe,
+	.driver = {
+		.name = "axg-tdmout",
+		.of_match_table = axg_tdmout_of_match,
+	},
+};
+module_platform_driver(axg_tdmout_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM output formatter driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 13a22e6a98f8b47d61948fcd095d862377b3b143 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:43:01 +0200
Subject: ASoC: meson: add tdm input driver

Add Amlogic's axg TDM input driver which take the TDM signal of 4 input
lanes and push the decoded audio samples to TODDR fifo

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig     |   8 ++
 sound/soc/meson/Makefile    |   2 +
 sound/soc/meson/axg-tdmin.c | 229 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 239 insertions(+)
 create mode 100644 sound/soc/meson/axg-tdmin.c

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index 08a522b77749..00d05df67b52 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -27,6 +27,14 @@ config SND_MESON_AXG_TDM_INTERFACE
 	tristate
 	select SND_MESON_AXG_TDM_FORMATTER
 
+config SND_MESON_AXG_TDMIN
+	tristate "Amlogic AXG TDM Input Support"
+	select SND_MESON_AXG_TDM_FORMATTER
+	select SND_MESON_AXG_TDM_INTERFACE
+	help
+	  Select Y or M to add support for TDM input formatter embedded
+	  in the Amlogic AXG SoC family
+
 config SND_MESON_AXG_TDMOUT
 	tristate "Amlogic AXG TDM Output Support"
 	select SND_MESON_AXG_TDM_FORMATTER
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index a665c6b76a95..f62833fb44d8 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -5,6 +5,7 @@ snd-soc-meson-axg-frddr-objs := axg-frddr.o
 snd-soc-meson-axg-toddr-objs := axg-toddr.o
 snd-soc-meson-axg-tdm-formatter-objs := axg-tdm-formatter.o
 snd-soc-meson-axg-tdm-interface-objs := axg-tdm-interface.o
+snd-soc-meson-axg-tdmin-objs := axg-tdmin.o
 snd-soc-meson-axg-tdmout-objs := axg-tdmout.o
 snd-soc-meson-axg-spdifout-objs := axg-spdifout.o
 
@@ -13,5 +14,6 @@ obj-$(CONFIG_SND_MESON_AXG_FRDDR) += snd-soc-meson-axg-frddr.o
 obj-$(CONFIG_SND_MESON_AXG_TODDR) += snd-soc-meson-axg-toddr.o
 obj-$(CONFIG_SND_MESON_AXG_TDM_FORMATTER) += snd-soc-meson-axg-tdm-formatter.o
 obj-$(CONFIG_SND_MESON_AXG_TDM_INTERFACE) += snd-soc-meson-axg-tdm-interface.o
+obj-$(CONFIG_SND_MESON_AXG_TDMIN) += snd-soc-meson-axg-tdmin.o
 obj-$(CONFIG_SND_MESON_AXG_TDMOUT) += snd-soc-meson-axg-tdmout.o
 obj-$(CONFIG_SND_MESON_AXG_SPDIFOUT) += snd-soc-meson-axg-spdifout.o
diff --git a/sound/soc/meson/axg-tdmin.c b/sound/soc/meson/axg-tdmin.c
new file mode 100644
index 000000000000..bbac44c81688
--- /dev/null
+++ b/sound/soc/meson/axg-tdmin.c
@@ -0,0 +1,229 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/regmap.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm-formatter.h"
+
+#define TDMIN_CTRL			0x00
+#define  TDMIN_CTRL_ENABLE		BIT(31)
+#define  TDMIN_CTRL_I2S_MODE		BIT(30)
+#define  TDMIN_CTRL_RST_OUT		BIT(29)
+#define  TDMIN_CTRL_RST_IN		BIT(28)
+#define  TDMIN_CTRL_WS_INV		BIT(25)
+#define  TDMIN_CTRL_SEL_SHIFT		20
+#define  TDMIN_CTRL_IN_BIT_SKEW_MASK	GENMASK(18, 16)
+#define  TDMIN_CTRL_IN_BIT_SKEW(x)	((x) << 16)
+#define  TDMIN_CTRL_LSB_FIRST		BIT(5)
+#define  TDMIN_CTRL_BITNUM_MASK	GENMASK(4, 0)
+#define  TDMIN_CTRL_BITNUM(x)		((x) << 0)
+#define TDMIN_SWAP			0x04
+#define TDMIN_MASK0			0x08
+#define TDMIN_MASK1			0x0c
+#define TDMIN_MASK2			0x10
+#define TDMIN_MASK3			0x14
+#define TDMIN_STAT			0x18
+#define TDMIN_MUTE_VAL			0x1c
+#define TDMIN_MUTE0			0x20
+#define TDMIN_MUTE1			0x24
+#define TDMIN_MUTE2			0x28
+#define TDMIN_MUTE3			0x2c
+
+static const struct regmap_config axg_tdmin_regmap_cfg = {
+	.reg_bits	= 32,
+	.val_bits	= 32,
+	.reg_stride	= 4,
+	.max_register	= TDMIN_MUTE3,
+};
+
+static const char * const axg_tdmin_sel_texts[] = {
+	"IN 0", "IN 1", "IN 2", "IN 3", "IN 4", "IN 5",
+};
+
+/* Change to special mux control to reset dapm */
+static SOC_ENUM_SINGLE_DECL(axg_tdmin_sel_enum, TDMIN_CTRL,
+			    TDMIN_CTRL_SEL_SHIFT, axg_tdmin_sel_texts);
+
+static const struct snd_kcontrol_new axg_tdmin_in_mux =
+	SOC_DAPM_ENUM("Input Source", axg_tdmin_sel_enum);
+
+static struct snd_soc_dai *
+axg_tdmin_get_be(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dapm_path *p = NULL;
+	struct snd_soc_dai *be;
+
+	snd_soc_dapm_widget_for_each_source_path(w, p) {
+		if (!p->connect)
+			continue;
+
+		if (p->source->id == snd_soc_dapm_dai_out)
+			return (struct snd_soc_dai *)p->source->priv;
+
+		be = axg_tdmin_get_be(p->source);
+		if (be)
+			return be;
+	}
+
+	return NULL;
+}
+
+static struct axg_tdm_stream *
+axg_tdmin_get_tdm_stream(struct snd_soc_dapm_widget *w)
+{
+	struct snd_soc_dai *be = axg_tdmin_get_be(w);
+
+	if (!be)
+		return NULL;
+
+	return be->capture_dma_data;
+}
+
+static void axg_tdmin_enable(struct regmap *map)
+{
+	/* Apply both reset */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_RST_OUT | TDMIN_CTRL_RST_IN, 0);
+
+	/* Clear out reset before in reset */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_RST_OUT, TDMIN_CTRL_RST_OUT);
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_RST_IN,  TDMIN_CTRL_RST_IN);
+
+	/* Actually enable tdmin */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   TDMIN_CTRL_ENABLE, TDMIN_CTRL_ENABLE);
+}
+
+static void axg_tdmin_disable(struct regmap *map)
+{
+	regmap_update_bits(map, TDMIN_CTRL, TDMIN_CTRL_ENABLE, 0);
+}
+
+static int axg_tdmin_prepare(struct regmap *map, struct axg_tdm_stream *ts)
+{
+	unsigned int val = 0;
+
+	/* Set stream skew */
+	switch (ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_DSP_A:
+		val |= TDMIN_CTRL_IN_BIT_SKEW(3);
+		break;
+
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+	case SND_SOC_DAIFMT_DSP_B:
+		val = TDMIN_CTRL_IN_BIT_SKEW(2);
+		break;
+
+	default:
+		pr_err("Unsupported format: %u\n",
+		       ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK);
+		return -EINVAL;
+	}
+
+	/* Set stream format mode */
+	switch (ts->iface->fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+	case SND_SOC_DAIFMT_I2S:
+	case SND_SOC_DAIFMT_LEFT_J:
+	case SND_SOC_DAIFMT_RIGHT_J:
+		val |= TDMIN_CTRL_I2S_MODE;
+		break;
+	}
+
+	/* If the sample clock is inverted, invert it back for the formatter */
+	if (axg_tdm_lrclk_invert(ts->iface->fmt))
+		val |= TDMIN_CTRL_WS_INV;
+
+	/* Set the slot width */
+	val |= TDMIN_CTRL_BITNUM(ts->iface->slot_width - 1);
+
+	/*
+	 * The following also reset LSB_FIRST which result in the formatter
+	 * placing the first bit received at bit 31
+	 */
+	regmap_update_bits(map, TDMIN_CTRL,
+			   (TDMIN_CTRL_IN_BIT_SKEW_MASK | TDMIN_CTRL_WS_INV |
+			    TDMIN_CTRL_I2S_MODE | TDMIN_CTRL_LSB_FIRST |
+			    TDMIN_CTRL_BITNUM_MASK), val);
+
+	/* Set static swap mask configuration */
+	regmap_write(map, TDMIN_SWAP, 0x76543210);
+
+	return axg_tdm_formatter_set_channel_masks(map, ts, TDMIN_MASK0);
+}
+
+static const struct snd_soc_dapm_widget axg_tdmin_dapm_widgets[] = {
+	SND_SOC_DAPM_AIF_IN("IN 0", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 1", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 2", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 3", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 4", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_AIF_IN("IN 5", NULL, 0, SND_SOC_NOPM, 0, 0),
+	SND_SOC_DAPM_MUX("SRC SEL", SND_SOC_NOPM, 0, 0, &axg_tdmin_in_mux),
+	SND_SOC_DAPM_PGA_E("DEC", SND_SOC_NOPM, 0, 0, NULL, 0,
+			   axg_tdm_formatter_event,
+			   (SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_PRE_PMD)),
+	SND_SOC_DAPM_AIF_OUT("OUT", NULL, 0, SND_SOC_NOPM, 0, 0),
+};
+
+static const struct snd_soc_dapm_route axg_tdmin_dapm_routes[] = {
+	{ "SRC SEL", "IN 0", "IN 0" },
+	{ "SRC SEL", "IN 1", "IN 1" },
+	{ "SRC SEL", "IN 2", "IN 2" },
+	{ "SRC SEL", "IN 3", "IN 3" },
+	{ "SRC SEL", "IN 4", "IN 4" },
+	{ "SRC SEL", "IN 5", "IN 5" },
+	{ "DEC", NULL, "SRC SEL" },
+	{ "OUT", NULL, "DEC" },
+};
+
+static const struct snd_soc_component_driver axg_tdmin_component_drv = {
+	.dapm_widgets		= axg_tdmin_dapm_widgets,
+	.num_dapm_widgets	= ARRAY_SIZE(axg_tdmin_dapm_widgets),
+	.dapm_routes		= axg_tdmin_dapm_routes,
+	.num_dapm_routes	= ARRAY_SIZE(axg_tdmin_dapm_routes),
+};
+
+static const struct axg_tdm_formatter_ops axg_tdmin_ops = {
+	.get_stream	= axg_tdmin_get_tdm_stream,
+	.prepare	= axg_tdmin_prepare,
+	.enable		= axg_tdmin_enable,
+	.disable	= axg_tdmin_disable,
+};
+
+static const struct axg_tdm_formatter_driver axg_tdmin_drv = {
+	.component_drv	= &axg_tdmin_component_drv,
+	.regmap_cfg	= &axg_tdmin_regmap_cfg,
+	.ops		= &axg_tdmin_ops,
+	.invert_sclk	= false,
+};
+
+static const struct of_device_id axg_tdmin_of_match[] = {
+	{
+		.compatible = "amlogic,axg-tdmin",
+		.data = &axg_tdmin_drv,
+	}, {}
+};
+MODULE_DEVICE_TABLE(of, axg_tdmin_of_match);
+
+static struct platform_driver axg_tdmin_pdrv = {
+	.probe = axg_tdm_formatter_probe,
+	.driver = {
+		.name = "axg-tdmin",
+		.of_match_table = axg_tdmin_of_match,
+	},
+};
+module_platform_driver(axg_tdmin_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG TDM input formatter driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From cbdfab3b675f4c34258b0ec9e4707de44e1f6989 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:43:02 +0200
Subject: ASoC: export snd_soc_of_get_slot_mask

Amlogic's axg card driver can't use snd_soc_of_parse_tdm_slot()
directly because it needs to handle 4 mask for each direction.
Yet the parsing of each mask is the same, so export
snd_soc_of_get_slot_mask() to reuse the the existing code.

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  | 3 +++
 sound/soc/soc-core.c | 7 ++++---
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index a23ecdf3eff1..ace474e8649e 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1433,6 +1433,9 @@ int snd_soc_of_parse_card_name(struct snd_soc_card *card,
 			       const char *propname);
 int snd_soc_of_parse_audio_simple_widgets(struct snd_soc_card *card,
 					  const char *propname);
+int snd_soc_of_get_slot_mask(struct device_node *np,
+			     const char *prop_name,
+			     unsigned int *mask);
 int snd_soc_of_parse_tdm_slot(struct device_node *np,
 			      unsigned int *tx_mask,
 			      unsigned int *rx_mask,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 08e189485009..ad5b0ef16d82 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -3428,9 +3428,9 @@ int snd_soc_of_parse_audio_simple_widgets(struct snd_soc_card *card,
 }
 EXPORT_SYMBOL_GPL(snd_soc_of_parse_audio_simple_widgets);
 
-static int snd_soc_of_get_slot_mask(struct device_node *np,
-				    const char *prop_name,
-				    unsigned int *mask)
+int snd_soc_of_get_slot_mask(struct device_node *np,
+			     const char *prop_name,
+			     unsigned int *mask)
 {
 	u32 val;
 	const __be32 *of_slot_mask = of_get_property(np, prop_name, &val);
@@ -3445,6 +3445,7 @@ static int snd_soc_of_get_slot_mask(struct device_node *np,
 
 	return val;
 }
+EXPORT_SYMBOL_GPL(snd_soc_of_get_slot_mask);
 
 int snd_soc_of_parse_tdm_slot(struct device_node *np,
 			      unsigned int *tx_mask,
-- 
cgit v1.2.3


From 2a05c71ea17b09c88a212e8fa6be1ccddd4613ab Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:43:03 +0200
Subject: ASoC: meson: add axg sound card DT bindings documentation

Add the DT bindings documentation for axg sound card

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/sound/amlogic,axg-sound-card.txt      | 124 +++++++++++++++++++++
 1 file changed, 124 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt

diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt
new file mode 100644
index 000000000000..39e005da0407
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt
@@ -0,0 +1,124 @@
+Amlogic AXG sound card:
+
+Required properties:
+
+- compatible: "amlogic,axg-sound-card"
+- amlogic,name : User specified audio sound card name, one string
+
+Optional properties:
+
+- amlogic,aux-devs : List of phandles pointing to auxiliary devices
+- amlogic,widgets : Please refer to widgets.txt.
+- amlogic,routing : A list of the connections between audio components.
+
+Subnodes:
+
+- amlogic,dai-link: Container for dai-link level properties and the
+		    CODEC sub-nodes. There should be at least one (and
+		    probably) subnode of this type.
+
+Required dai-link properties:
+
+- sound-dai: phandle and port of the CPU DAI.
+
+Required TDM Backend dai-link properties:
+- dai-format : CPU/CODEC common audio format
+
+Optional TDM Backend dai-link properties:
+- dai-tdm-slot-rx-mask-{0,1,2,3}: Receive direction slot masks
+- dai-tdm-slot-tx-mask-{0,1,2,3}: Transmit direction slot masks
+				  When omitted, mask is assumed to have to no
+				  slots. A valid must have at one slot, so at
+				  least one these mask should be provided with
+				  an enabled slot.
+- dai-tdm-slot-num : Please refer to tdm-slot.txt.
+		     If omitted, slot number is set to accommodate the largest
+		     mask provided.
+- dai-tdm-slot-width : Please refer to tdm-slot.txt. default to 32 if omitted.
+- mclk-fs : Multiplication factor between stream rate and mclk
+
+Backend dai-link subnodes:
+
+- codec: dai-link representing backend links should have at least one subnode.
+	 One subnode for each codec of the dai-link.
+	 dai-link representing frontend links have no codec, therefore have no
+	 subnodes
+
+Required codec subnodes properties:
+
+- sound-dai: phandle and port of the CODEC DAI.
+
+Optional codec subnodes properties:
+
+- dai-tdm-slot-tx-mask : Please refer to tdm-slot.txt.
+- dai-tdm-slot-rx-mask : Please refer to tdm-slot.txt.
+
+Example:
+
+sound {
+	compatible = "amlogic,axg-sound-card";
+	amlogic,name = "AXG-S420";
+	amlogic,aux-devs = <&tdmin_a>, <&tdmout_c>;
+	amlogic,widgets = "Line", "Lineout",
+			  "Line", "Linein",
+			  "Speaker", "Speaker1 Left",
+			  "Speaker", "Speaker1 Right";
+			  "Speaker", "Speaker2 Left",
+			  "Speaker", "Speaker2 Right";
+	amlogic,routing = "TDMOUT_C IN 0", "FRDDR_A OUT 2",
+			  "SPDIFOUT IN 0", "FRDDR_A OUT 3",
+			  "TDM_C Playback", "TDMOUT_C OUT",
+			  "TDMIN_A IN 2", "TDM_C Capture",
+			  "TDMIN_A IN 5", "TDM_C Loopback",
+			  "TODDR_A IN 0", "TDMIN_A OUT",
+			  "Lineout", "Lineout AOUTL",
+			  "Lineout", "Lineout AOUTR",
+			  "Speaker1 Left", "SPK1 OUT_A",
+			  "Speaker2 Left", "SPK2 OUT_A",
+			  "Speaker1 Right", "SPK1 OUT_B",
+			  "Speaker2 Right", "SPK2 OUT_B",
+			  "Linein AINL", "Linein",
+			  "Linein AINR", "Linein";
+
+	amlogic,dai-link@0 {
+		sound-dai = <&frddr_a>;
+	};
+
+	amlogic,dai-link@1 {
+		sound-dai = <&toddr_a>;
+	};
+
+	amlogic,dai-link@2 {
+		sound-dai = <&tdmif_c>;
+		dai-format = "i2s";
+		dai-tdm-slot-tx-mask-2 = <1 1>;
+		dai-tdm-slot-tx-mask-3 = <1 1>;
+		dai-tdm-slot-rx-mask-1 = <1 1>;
+		mclk-fs = <256>;
+
+		codec@0 {
+			sound-dai = <&lineout>;
+		};
+
+		codec@1 {
+			sound-dai = <&speaker_amp1>;
+		};
+
+		codec@2 {
+			sound-dai = <&speaker_amp2>;
+		};
+
+		codec@3 {
+			sound-dai = <&linein>;
+		};
+
+	};
+
+	amlogic,dai-link@4 {
+		sound-dai = <&spdifout>;
+
+		codec {
+			sound-dai = <&spdif_dit>;
+		};
+	};
+};
-- 
cgit v1.2.3


From 7864a79f37b55769b817d5e6c5ae0ca4bfdba93b Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Tue, 17 Jul 2018 17:43:04 +0200
Subject: ASoC: meson: add axg sound card support

Add the axg sound card to handle the specifities of the axg audio
sub system.

This card is required to:
 * setup the dpcm links specific to the AXG (with a cpu sound dai)
 * handle the 4 lanes masks of the tdm interfaces
 * add the loopback link when a tdm pad interface has a playback
   stream
 * handle multi-codec links

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig    |  11 +
 sound/soc/meson/Makefile   |   2 +
 sound/soc/meson/axg-card.c | 671 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 684 insertions(+)
 create mode 100644 sound/soc/meson/axg-card.c

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index 00d05df67b52..4cf93c05a982 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -43,6 +43,17 @@ config SND_MESON_AXG_TDMOUT
 	  Select Y or M to add support for TDM output formatter embedded
 	  in the Amlogic AXG SoC family
 
+config SND_MESON_AXG_SOUND_CARD
+	tristate "Amlogic AXG Sound Card Support"
+	select SND_MESON_AXG_TDM_INTERFACE
+	imply SND_MESON_AXG_FRDDR
+	imply SND_MESON_AXG_TODDR
+	imply SND_MESON_AXG_TDMIN
+	imply SND_MESON_AXG_TDMOUT
+	imply SND_MESON_AXG_SPDIFOUT
+	help
+	  Select Y or M to add support for the AXG SoC sound card
+
 config SND_MESON_AXG_SPDIFOUT
 	tristate "Amlogic AXG SPDIF Output Support"
 	imply SND_SOC_SPDIF
diff --git a/sound/soc/meson/Makefile b/sound/soc/meson/Makefile
index f62833fb44d8..c5e003b093db 100644
--- a/sound/soc/meson/Makefile
+++ b/sound/soc/meson/Makefile
@@ -7,6 +7,7 @@ snd-soc-meson-axg-tdm-formatter-objs := axg-tdm-formatter.o
 snd-soc-meson-axg-tdm-interface-objs := axg-tdm-interface.o
 snd-soc-meson-axg-tdmin-objs := axg-tdmin.o
 snd-soc-meson-axg-tdmout-objs := axg-tdmout.o
+snd-soc-meson-axg-sound-card-objs := axg-card.o
 snd-soc-meson-axg-spdifout-objs := axg-spdifout.o
 
 obj-$(CONFIG_SND_MESON_AXG_FIFO) += snd-soc-meson-axg-fifo.o
@@ -16,4 +17,5 @@ obj-$(CONFIG_SND_MESON_AXG_TDM_FORMATTER) += snd-soc-meson-axg-tdm-formatter.o
 obj-$(CONFIG_SND_MESON_AXG_TDM_INTERFACE) += snd-soc-meson-axg-tdm-interface.o
 obj-$(CONFIG_SND_MESON_AXG_TDMIN) += snd-soc-meson-axg-tdmin.o
 obj-$(CONFIG_SND_MESON_AXG_TDMOUT) += snd-soc-meson-axg-tdmout.o
+obj-$(CONFIG_SND_MESON_AXG_SOUND_CARD) += snd-soc-meson-axg-sound-card.o
 obj-$(CONFIG_SND_MESON_AXG_SPDIFOUT) += snd-soc-meson-axg-spdifout.o
diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c
new file mode 100644
index 000000000000..d6d1081d94ad
--- /dev/null
+++ b/sound/soc/meson/axg-card.c
@@ -0,0 +1,671 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+//
+// Copyright (c) 2018 BayLibre, SAS.
+// Author: Jerome Brunet <jbrunet@baylibre.com>
+
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <sound/soc.h>
+#include <sound/soc-dai.h>
+
+#include "axg-tdm.h"
+
+struct axg_card {
+	struct snd_soc_card card;
+	void **link_data;
+};
+
+struct axg_dai_link_tdm_mask {
+	u32 tx;
+	u32 rx;
+};
+
+struct axg_dai_link_tdm_data {
+	unsigned int mclk_fs;
+	unsigned int slots;
+	unsigned int slot_width;
+	u32 *tx_mask;
+	u32 *rx_mask;
+	struct axg_dai_link_tdm_mask *codec_masks;
+};
+
+#define PREFIX "amlogic,"
+
+static int axg_card_reallocate_links(struct axg_card *priv,
+				     unsigned int num_links)
+{
+	struct snd_soc_dai_link *links;
+	void **ldata;
+
+	links = krealloc(priv->card.dai_link,
+			 num_links * sizeof(*priv->card.dai_link),
+			 GFP_KERNEL | __GFP_ZERO);
+	ldata = krealloc(priv->link_data,
+			 num_links * sizeof(*priv->link_data),
+			 GFP_KERNEL | __GFP_ZERO);
+
+	if (!links || !ldata) {
+		dev_err(priv->card.dev, "failed to allocate links\n");
+		return -ENOMEM;
+	}
+
+	priv->card.dai_link = links;
+	priv->link_data = ldata;
+	priv->card.num_links = num_links;
+	return 0;
+}
+
+static int axg_card_parse_dai(struct snd_soc_card *card,
+			      struct device_node *node,
+			      struct device_node **dai_of_node,
+			      const char **dai_name)
+{
+	struct of_phandle_args args;
+	int ret;
+
+	if (!dai_name || !dai_of_node || !node)
+		return -EINVAL;
+
+	ret = of_parse_phandle_with_args(node, "sound-dai",
+					 "#sound-dai-cells", 0, &args);
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(card->dev, "can't parse dai %d\n", ret);
+		return ret;
+	}
+	*dai_of_node = args.np;
+
+	return snd_soc_get_dai_name(&args, dai_name);
+}
+
+static int axg_card_set_link_name(struct snd_soc_card *card,
+				  struct snd_soc_dai_link *link,
+				  const char *prefix)
+{
+	char *name = devm_kasprintf(card->dev, GFP_KERNEL, "%s.%s",
+				    prefix, link->cpu_of_node->full_name);
+	if (!name)
+		return -ENOMEM;
+
+	link->name = name;
+	link->stream_name = name;
+
+	return 0;
+}
+
+static void axg_card_clean_references(struct axg_card *priv)
+{
+	struct snd_soc_card *card = &priv->card;
+	struct snd_soc_dai_link *link;
+	int i, j;
+
+	if (card->dai_link) {
+		for (i = 0; i < card->num_links; i++) {
+			link = &card->dai_link[i];
+			of_node_put(link->cpu_of_node);
+			for (j = 0; j < link->num_codecs; j++)
+				of_node_put(link->codecs[j].of_node);
+		}
+	}
+
+	if (card->aux_dev) {
+		for (i = 0; i < card->num_aux_devs; i++)
+			of_node_put(card->aux_dev[i].codec_of_node);
+	}
+
+	kfree(card->dai_link);
+	kfree(priv->link_data);
+}
+
+static int axg_card_add_aux_devices(struct snd_soc_card *card)
+{
+	struct device_node *node = card->dev->of_node;
+	struct snd_soc_aux_dev *aux;
+	int num, i;
+
+	num = of_count_phandle_with_args(node, PREFIX "aux-devs", NULL);
+	if (num == -ENOENT) {
+		/*
+		 * It is ok to have no auxiliary devices but for this card it
+		 * is a strange situtation. Let's warn the about it.
+		 */
+		dev_warn(card->dev, "card has no auxiliary devices\n");
+		return 0;
+	} else if (num < 0) {
+		dev_err(card->dev, "error getting auxiliary devices: %d\n",
+			num);
+		return num;
+	}
+
+	aux = devm_kcalloc(card->dev, num, sizeof(*aux), GFP_KERNEL);
+	if (!aux)
+		return -ENOMEM;
+	card->aux_dev = aux;
+	card->num_aux_devs = num;
+
+	for (i = 0; i < card->num_aux_devs; i++, aux++) {
+		aux->codec_of_node = of_parse_phandle(node,
+						      PREFIX "aux-devs", i);
+		if (!aux->codec_of_node)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int axg_card_tdm_be_hw_params(struct snd_pcm_substream *substream,
+				     struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct axg_card *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct axg_dai_link_tdm_data *be =
+		(struct axg_dai_link_tdm_data *)priv->link_data[rtd->num];
+	struct snd_soc_dai *codec_dai;
+	unsigned int mclk;
+	int ret, i;
+
+	if (be->mclk_fs) {
+		mclk = params_rate(params) * be->mclk_fs;
+
+		for (i = 0; i < rtd->num_codecs; i++) {
+			codec_dai = rtd->codec_dais[i];
+			ret = snd_soc_dai_set_sysclk(codec_dai, 0, mclk,
+						     SND_SOC_CLOCK_IN);
+			if (ret && ret != -ENOTSUPP)
+				return ret;
+		}
+
+		ret = snd_soc_dai_set_sysclk(rtd->cpu_dai, 0, mclk,
+					     SND_SOC_CLOCK_OUT);
+		if (ret && ret != -ENOTSUPP)
+			return ret;
+	}
+
+	return 0;
+}
+
+static const struct snd_soc_ops axg_card_tdm_be_ops = {
+	.hw_params = axg_card_tdm_be_hw_params,
+};
+
+static int axg_card_tdm_dai_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct axg_dai_link_tdm_data *be =
+		(struct axg_dai_link_tdm_data *)priv->link_data[rtd->num];
+	struct snd_soc_dai *codec_dai;
+	int ret, i;
+
+	for (i = 0; i < rtd->num_codecs; i++) {
+		codec_dai = rtd->codec_dais[i];
+		ret = snd_soc_dai_set_tdm_slot(codec_dai,
+					       be->codec_masks[i].tx,
+					       be->codec_masks[i].rx,
+					       be->slots, be->slot_width);
+		if (ret && ret != -ENOTSUPP) {
+			dev_err(codec_dai->dev,
+				"setting tdm link slots failed\n");
+			return ret;
+		}
+	}
+
+	ret = axg_tdm_set_tdm_slots(rtd->cpu_dai, be->tx_mask, be->rx_mask,
+				    be->slots, be->slot_width);
+	if (ret) {
+		dev_err(rtd->cpu_dai->dev, "setting tdm link slots failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_card_tdm_dai_lb_init(struct snd_soc_pcm_runtime *rtd)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(rtd->card);
+	struct axg_dai_link_tdm_data *be =
+		(struct axg_dai_link_tdm_data *)priv->link_data[rtd->num];
+	int ret;
+
+	/* The loopback rx_mask is the pad tx_mask */
+	ret = axg_tdm_set_tdm_slots(rtd->cpu_dai, NULL, be->tx_mask,
+				    be->slots, be->slot_width);
+	if (ret) {
+		dev_err(rtd->cpu_dai->dev, "setting tdm link slots failed\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int axg_card_add_tdm_loopback(struct snd_soc_card *card,
+				     int *index)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai_link *pad = &card->dai_link[*index];
+	struct snd_soc_dai_link *lb;
+	int ret;
+
+	/* extend links */
+	ret = axg_card_reallocate_links(priv, card->num_links + 1);
+	if (ret)
+		return ret;
+
+	lb = &card->dai_link[*index + 1];
+
+	lb->name = kasprintf(GFP_KERNEL, "%s-lb", pad->name);
+	if (!lb->name)
+		return -ENOMEM;
+
+	lb->stream_name = lb->name;
+	lb->cpu_of_node = pad->cpu_of_node;
+	lb->cpu_dai_name = "TDM Loopback";
+	lb->codec_name = "snd-soc-dummy";
+	lb->codec_dai_name = "snd-soc-dummy-dai";
+	lb->dpcm_capture = 1;
+	lb->no_pcm = 1;
+	lb->ops = &axg_card_tdm_be_ops;
+	lb->init = axg_card_tdm_dai_lb_init;
+
+	/* Provide the same link data to the loopback */
+	priv->link_data[*index + 1] = priv->link_data[*index];
+
+	/*
+	 * axg_card_clean_references() will iterate over this link,
+	 * make sure the node count is balanced
+	 */
+	of_node_get(lb->cpu_of_node);
+
+	/* Let add_links continue where it should */
+	*index += 1;
+
+	return 0;
+}
+
+static unsigned int axg_card_parse_daifmt(struct device_node *node,
+					  struct device_node *cpu_node)
+{
+	struct device_node *bitclkmaster = NULL;
+	struct device_node *framemaster = NULL;
+	unsigned int daifmt;
+
+	daifmt = snd_soc_of_parse_daifmt(node, PREFIX,
+					 &bitclkmaster, &framemaster);
+	daifmt &= ~SND_SOC_DAIFMT_MASTER_MASK;
+
+	/* If no master is provided, default to cpu master */
+	if (!bitclkmaster || bitclkmaster == cpu_node) {
+		daifmt |= (!framemaster || framemaster == cpu_node) ?
+			SND_SOC_DAIFMT_CBS_CFS : SND_SOC_DAIFMT_CBS_CFM;
+	} else {
+		daifmt |= (!framemaster || framemaster == cpu_node) ?
+			SND_SOC_DAIFMT_CBM_CFS : SND_SOC_DAIFMT_CBM_CFM;
+	}
+
+	of_node_put(bitclkmaster);
+	of_node_put(framemaster);
+
+	return daifmt;
+}
+
+static int axg_card_parse_cpu_tdm_slots(struct snd_soc_card *card,
+					struct snd_soc_dai_link *link,
+					struct device_node *node,
+					struct axg_dai_link_tdm_data *be)
+{
+	char propname[32];
+	u32 tx, rx;
+	int i;
+
+	be->tx_mask = devm_kcalloc(card->dev, AXG_TDM_NUM_LANES,
+				   sizeof(*be->tx_mask), GFP_KERNEL);
+	be->rx_mask = devm_kcalloc(card->dev, AXG_TDM_NUM_LANES,
+				   sizeof(*be->rx_mask), GFP_KERNEL);
+	if (!be->tx_mask || !be->rx_mask)
+		return -ENOMEM;
+
+	for (i = 0, tx = 0; i < AXG_TDM_NUM_LANES; i++) {
+		snprintf(propname, 32, "dai-tdm-slot-tx-mask-%d", i);
+		snd_soc_of_get_slot_mask(node, propname, &be->tx_mask[i]);
+		tx = max(tx, be->tx_mask[i]);
+	}
+
+	/* Disable playback is the interface has no tx slots */
+	if (!tx)
+		link->dpcm_playback = 0;
+
+	for (i = 0, rx = 0; i < AXG_TDM_NUM_LANES; i++) {
+		snprintf(propname, 32, "dai-tdm-slot-rx-mask-%d", i);
+		snd_soc_of_get_slot_mask(node, propname, &be->rx_mask[i]);
+		rx = max(rx, be->rx_mask[i]);
+	}
+
+	/* Disable capture is the interface has no rx slots */
+	if (!rx)
+		link->dpcm_capture = 0;
+
+	/* ... but the interface should at least have one of them */
+	if (!tx && !rx) {
+		dev_err(card->dev, "tdm link has no cpu slots\n");
+		return -EINVAL;
+	}
+
+	of_property_read_u32(node, "dai-tdm-slot-num", &be->slots);
+	if (!be->slots) {
+		/*
+		 * If the slot number is not provided, set it such as it
+		 * accommodates the largest mask
+		 */
+		be->slots = fls(max(tx, rx));
+	} else if (be->slots < fls(max(tx, rx)) || be->slots > 32) {
+		/*
+		 * Error if the slots can't accommodate the largest mask or
+		 * if it is just too big
+		 */
+		dev_err(card->dev, "bad slot number\n");
+		return -EINVAL;
+	}
+
+	of_property_read_u32(node, "dai-tdm-slot-width", &be->slot_width);
+
+	return 0;
+}
+
+static int axg_card_parse_codecs_masks(struct snd_soc_card *card,
+				       struct snd_soc_dai_link *link,
+				       struct device_node *node,
+				       struct axg_dai_link_tdm_data *be)
+{
+	struct axg_dai_link_tdm_mask *codec_mask;
+	struct device_node *np;
+
+	codec_mask = devm_kcalloc(card->dev, link->num_codecs,
+				  sizeof(*codec_mask), GFP_KERNEL);
+	if (!codec_mask)
+		return -ENOMEM;
+
+	be->codec_masks = codec_mask;
+
+	for_each_child_of_node(node, np) {
+		snd_soc_of_get_slot_mask(np, "dai-tdm-slot-rx-mask",
+					 &codec_mask->rx);
+		snd_soc_of_get_slot_mask(np, "dai-tdm-slot-tx-mask",
+					 &codec_mask->tx);
+
+		codec_mask++;
+	}
+
+	return 0;
+}
+
+static int axg_card_parse_tdm(struct snd_soc_card *card,
+			      struct device_node *node,
+			      int *index)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai_link *link = &card->dai_link[*index];
+	struct axg_dai_link_tdm_data *be;
+	int ret;
+
+	/* Allocate tdm link parameters */
+	be = devm_kzalloc(card->dev, sizeof(*be), GFP_KERNEL);
+	if (!be)
+		return -ENOMEM;
+	priv->link_data[*index] = be;
+
+	/* Setup tdm link */
+	link->ops = &axg_card_tdm_be_ops;
+	link->init = axg_card_tdm_dai_init;
+	link->dai_fmt = axg_card_parse_daifmt(node, link->cpu_of_node);
+
+	of_property_read_u32(node, "mclk-fs", &be->mclk_fs);
+
+	ret = axg_card_parse_cpu_tdm_slots(card, link, node, be);
+	if (ret) {
+		dev_err(card->dev, "error parsing tdm link slots\n");
+		return ret;
+	}
+
+	ret = axg_card_parse_codecs_masks(card, link, node, be);
+	if (ret)
+		return ret;
+
+	/* Add loopback if the pad dai has playback */
+	if (link->dpcm_playback) {
+		ret = axg_card_add_tdm_loopback(card, index);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int axg_card_set_be_link(struct snd_soc_card *card,
+				struct snd_soc_dai_link *link,
+				struct device_node *node)
+{
+	struct snd_soc_dai_link_component *codec;
+	struct device_node *np;
+	int ret, num_codecs;
+
+	link->no_pcm = 1;
+	link->dpcm_playback = 1;
+	link->dpcm_capture = 1;
+
+	num_codecs = of_get_child_count(node);
+	if (!num_codecs) {
+		dev_err(card->dev, "be link %s has no codec\n",
+			node->full_name);
+		return -EINVAL;
+	}
+
+	codec = devm_kcalloc(card->dev, num_codecs, sizeof(*codec), GFP_KERNEL);
+	if (!codec)
+		return -ENOMEM;
+
+	link->codecs = codec;
+	link->num_codecs = num_codecs;
+
+	for_each_child_of_node(node, np) {
+		ret = axg_card_parse_dai(card, np, &codec->of_node,
+					 &codec->dai_name);
+		if (ret) {
+			of_node_put(np);
+			return ret;
+		}
+
+		codec++;
+	}
+
+	ret = axg_card_set_link_name(card, link, "be");
+	if (ret)
+		dev_err(card->dev, "error setting %s link name\n", np->name);
+
+	return ret;
+}
+
+static int axg_card_set_fe_link(struct snd_soc_card *card,
+				struct snd_soc_dai_link *link,
+				bool is_playback)
+{
+	link->dynamic = 1;
+	link->dpcm_merged_format = 1;
+	link->dpcm_merged_chan = 1;
+	link->dpcm_merged_rate = 1;
+	link->codec_dai_name = "snd-soc-dummy-dai";
+	link->codec_name = "snd-soc-dummy";
+
+	if (is_playback)
+		link->dpcm_playback = 1;
+	else
+		link->dpcm_capture = 1;
+
+	return axg_card_set_link_name(card, link, "fe");
+}
+
+static int axg_card_cpu_is_capture_fe(struct device_node *np)
+{
+	return of_device_is_compatible(np, PREFIX "axg-toddr");
+}
+
+static int axg_card_cpu_is_playback_fe(struct device_node *np)
+{
+	return of_device_is_compatible(np, PREFIX "axg-frddr");
+}
+
+static int axg_card_cpu_is_tdm_iface(struct device_node *np)
+{
+	return of_device_is_compatible(np, PREFIX "axg-tdm-iface");
+}
+
+static int axg_card_add_link(struct snd_soc_card *card, struct device_node *np,
+			     int *index)
+{
+	struct snd_soc_dai_link *dai_link = &card->dai_link[*index];
+	int ret;
+
+	ret = axg_card_parse_dai(card, np, &dai_link->cpu_of_node,
+				 &dai_link->cpu_dai_name);
+	if (ret)
+		return ret;
+
+	if (axg_card_cpu_is_playback_fe(dai_link->cpu_of_node))
+		ret = axg_card_set_fe_link(card, dai_link, true);
+	else if (axg_card_cpu_is_capture_fe(dai_link->cpu_of_node))
+		ret = axg_card_set_fe_link(card, dai_link, false);
+	else
+		ret = axg_card_set_be_link(card, dai_link, np);
+
+	if (ret)
+		return ret;
+
+	if (axg_card_cpu_is_tdm_iface(dai_link->cpu_of_node))
+		ret = axg_card_parse_tdm(card, np, index);
+
+	return ret;
+}
+
+static int axg_card_add_links(struct snd_soc_card *card)
+{
+	struct axg_card *priv = snd_soc_card_get_drvdata(card);
+	struct device_node *node = card->dev->of_node;
+	struct device_node *np;
+	int num, i, ret;
+
+	num = of_get_child_count(node);
+	if (!num) {
+		dev_err(card->dev, "card has no links\n");
+		return -EINVAL;
+	}
+
+	ret = axg_card_reallocate_links(priv, num);
+	if (ret)
+		return ret;
+
+	i = 0;
+	for_each_child_of_node(node, np) {
+		ret = axg_card_add_link(card, np, &i);
+		if (ret) {
+			of_node_put(np);
+			return ret;
+		}
+
+		i++;
+	}
+
+	return 0;
+}
+
+static int axg_card_parse_of_optional(struct snd_soc_card *card,
+				      const char *propname,
+				      int (*func)(struct snd_soc_card *c,
+						  const char *p))
+{
+	/* If property is not provided, don't fail ... */
+	if (!of_property_read_bool(card->dev->of_node, propname))
+		return 0;
+
+	/* ... but do fail if it is provided and the parsing fails */
+	return func(card, propname);
+}
+
+static const struct of_device_id axg_card_of_match[] = {
+	{ .compatible = "amlogic,axg-sound-card", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, axg_card_of_match);
+
+static int axg_card_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct axg_card *priv;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, priv);
+	snd_soc_card_set_drvdata(&priv->card, priv);
+
+	priv->card.owner = THIS_MODULE;
+	priv->card.dev = dev;
+
+	ret = snd_soc_of_parse_card_name(&priv->card, PREFIX "name");
+	if (ret < 0)
+		return ret;
+
+	ret = axg_card_parse_of_optional(&priv->card, PREFIX "routing",
+					 snd_soc_of_parse_audio_routing);
+	if (ret) {
+		dev_err(dev, "error while parsing routing\n");
+		return ret;
+	}
+
+	ret = axg_card_parse_of_optional(&priv->card, PREFIX "widgets",
+					 snd_soc_of_parse_audio_simple_widgets);
+	if (ret) {
+		dev_err(dev, "error while parsing widgets\n");
+		return ret;
+	}
+
+	ret = axg_card_add_links(&priv->card);
+	if (ret)
+		goto out_err;
+
+	ret = axg_card_add_aux_devices(&priv->card);
+	if (ret)
+		goto out_err;
+
+	ret = devm_snd_soc_register_card(dev, &priv->card);
+	if (ret)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	axg_card_clean_references(priv);
+	return ret;
+}
+
+static int axg_card_remove(struct platform_device *pdev)
+{
+	struct axg_card *priv = platform_get_drvdata(pdev);
+
+	axg_card_clean_references(priv);
+
+	return 0;
+}
+
+static struct platform_driver axg_card_pdrv = {
+	.probe = axg_card_probe,
+	.remove = axg_card_remove,
+	.driver = {
+		.name = "axg-sound-card",
+		.of_match_table = axg_card_of_match,
+	},
+};
+module_platform_driver(axg_card_pdrv);
+
+MODULE_DESCRIPTION("Amlogic AXG ALSA machine driver");
+MODULE_AUTHOR("Jerome Brunet <jbrunet@baylibre.com>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From fffe7f52eb5db41eedadba9a8038e982dcfaee0c Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Mon, 16 Jul 2018 15:32:51 +0200
Subject: regulator: qcom_spmi: Fix warning Bad of_node_put()

For of_find_node_by_name(), you typically pass what the previous call
returned. Therefore, of_find_node_by_name() increases the refcount of
the returned node, and decreases the refcount of the node passed as the
first argument.

of_find_node_by_name() is incorrectly used, and produces a warning.
Fix the warning by using the more suitable function
of_get_child_by_name().

Also add a missing of_node_put() for the returned value, since this was
previously being leaked.

OF: ERROR: Bad of_node_put() on /soc/qcom,spmi@400f000/pmic@3/regulators
CPU: 1 PID: 1 Comm: swapper/0 Tainted: G        W         4.18.0-rc4-00223-gefd7b360b70e #12
Hardware name: Qualcomm Technologies, Inc. DB820c (DT)
Call trace:
 dump_backtrace+0x0/0x1a8
 show_stack+0x14/0x20
 dump_stack+0x90/0xb4
 of_node_release+0x74/0x78
 kobject_put+0x90/0x1f0
 of_node_put+0x14/0x20
 of_find_node_by_name+0x80/0xd8
 qcom_spmi_regulator_probe+0x30c/0x508

Fixes: 0caecaa87202 ("regulator: qcom_spmi: Add support for SAW")
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom_spmi-regulator.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 9817f1a75342..4cc14c65d86b 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1752,7 +1752,8 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 	const char *name;
 	struct device *dev = &pdev->dev;
 	struct device_node *node = pdev->dev.of_node;
-	struct device_node *syscon;
+	struct device_node *syscon, *reg_node;
+	struct property *reg_prop;
 	int ret, lenp;
 	struct list_head *vreg_list;
 
@@ -1780,10 +1781,13 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 
 	for (reg = match->data; reg->name; reg++) {
 
-		if (saw_regmap && \
-		    of_find_property(of_find_node_by_name(node, reg->name), \
-				     "qcom,saw-slave", &lenp)) {
-			continue;
+		if (saw_regmap) {
+			reg_node = of_get_child_by_name(node, reg->name);
+			reg_prop = of_find_property(reg_node, "qcom,saw-slave",
+						    &lenp);
+			of_node_put(reg_node);
+			if (reg_prop)
+				continue;
 		}
 
 		vreg = devm_kzalloc(dev, sizeof(*vreg), GFP_KERNEL);
@@ -1816,13 +1820,17 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 		if (ret)
 			continue;
 
-		if (saw_regmap && \
-		    of_find_property(of_find_node_by_name(node, reg->name), \
-				     "qcom,saw-leader", &lenp)) {
-			spmi_saw_ops = *(vreg->desc.ops);
-			spmi_saw_ops.set_voltage_sel = \
-				spmi_regulator_saw_set_voltage;
-			vreg->desc.ops = &spmi_saw_ops;
+		if (saw_regmap) {
+			reg_node = of_get_child_by_name(node, reg->name);
+			reg_prop = of_find_property(reg_node, "qcom,saw-leader",
+						    &lenp);
+			of_node_put(reg_node);
+			if (reg_prop) {
+				spmi_saw_ops = *(vreg->desc.ops);
+				spmi_saw_ops.set_voltage_sel =
+					spmi_regulator_saw_set_voltage;
+				vreg->desc.ops = &spmi_saw_ops;
+			}
 		}
 
 		config.dev = dev;
-- 
cgit v1.2.3


From 85046a15529606466bc778e1205f4cab8e3724d1 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Mon, 16 Jul 2018 15:32:52 +0200
Subject: regulator: qcom_spmi: Use correct regmap when checking for error

Since we have just assigned saw_regmap, and since the error message
refers to saw_regmap, it feels safe to assume that it is saw_regmap,
and not regmap, that should be checked for errors.

Fixes: 0caecaa87202 ("regulator: qcom_spmi: Add support for SAW")
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom_spmi-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 4cc14c65d86b..ba3d5e63ada6 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1775,7 +1775,7 @@ static int qcom_spmi_regulator_probe(struct platform_device *pdev)
 		syscon = of_parse_phandle(node, "qcom,saw-reg", 0);
 		saw_regmap = syscon_node_to_regmap(syscon);
 		of_node_put(syscon);
-		if (IS_ERR(regmap))
+		if (IS_ERR(saw_regmap))
 			dev_err(dev, "ERROR reading SAW regmap\n");
 	}
 
-- 
cgit v1.2.3


From 9689ca0af345b82d06a02e45cc214c1b8bad9e8d Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Mon, 16 Jul 2018 15:32:53 +0200
Subject: regulator: qcom_spmi: Do not initialise static to NULL

Fix the following checkpatch error:

ERROR: do not initialise statics to NULL
+static struct regmap *saw_regmap = NULL;

Fixes: 0caecaa87202 ("regulator: qcom_spmi: Add support for SAW")
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom_spmi-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index ba3d5e63ada6..5246f5b870c2 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1060,7 +1060,7 @@ static irqreturn_t spmi_regulator_vs_ocp_isr(int irq, void *data)
 #define SAW3_AVS_CTL_TGGL_MASK	0x8000000
 #define SAW3_AVS_CTL_CLEAR_MASK	0x7efc00
 
-static struct regmap *saw_regmap = NULL;
+static struct regmap *saw_regmap;
 
 static void spmi_saw_set_vdd(void *data)
 {
-- 
cgit v1.2.3


From 37164571fb25adef80ae2aaf55840b0105c15b22 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Mon, 16 Jul 2018 15:32:54 +0200
Subject: regulator: qcom_spmi: Indent with tabs instead of spaces

Fix the following checkpatch error:

ERROR: code indent should use tabs where possible
+        { }$

Fixes: ca5cd8c9400c ("regulator: qcom_spmi: Add support for pmi8994")
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/qcom_spmi-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/qcom_spmi-regulator.c b/drivers/regulator/qcom_spmi-regulator.c
index 5246f5b870c2..53a61fb65642 100644
--- a/drivers/regulator/qcom_spmi-regulator.c
+++ b/drivers/regulator/qcom_spmi-regulator.c
@@ -1728,7 +1728,7 @@ static const struct spmi_regulator_data pmi8994_regulators[] = {
 	{ "s2", 0x1700, "vdd_s2", },
 	{ "s3", 0x1a00, "vdd_s3", },
 	{ "l1", 0x4000, "vdd_l1", },
-        { }
+	{ }
 };
 
 static const struct of_device_id qcom_spmi_regulator_match[] = {
-- 
cgit v1.2.3


From a8e43c21a8a32a3af4abc605b6ebcab039f28e00 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Mon, 16 Jul 2018 08:24:45 +0200
Subject: ASoC: pxa: remove clock divider and pll setup from zylonite and
 magician

The SSP DAI now handles the clocking setup itself, all it needs is the
master clock frequency. Remove the code from Zylonite and Magician
platforms.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/pxa/magician.c | 106 +----------------------------------------------
 sound/soc/pxa/zylonite.c |   9 ----
 2 files changed, 2 insertions(+), 113 deletions(-)

diff --git a/sound/soc/pxa/magician.c b/sound/soc/pxa/magician.c
index 2fc012b06c43..935a248e5bf6 100644
--- a/sound/soc/pxa/magician.c
+++ b/sound/soc/pxa/magician.c
@@ -90,95 +90,9 @@ static int magician_playback_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	unsigned int acps, acds, width;
-	unsigned int div4 = PXA_SSP_CLK_SCDB_4;
+	unsigned int width;
 	int ret = 0;
 
-	width = snd_pcm_format_physical_width(params_format(params));
-
-	/*
-	 * rate = SSPSCLK / (2 * width(16 or 32))
-	 * SSPSCLK = (ACPS / ACDS) / SSPSCLKDIV(div4 or div1)
-	 */
-	switch (params_rate(params)) {
-	case 8000:
-		/* off by a factor of 2: bug in the PXA27x audio clock? */
-		acps = 32842000;
-		switch (width) {
-		case 16:
-			/* 513156 Hz ~= _2_ * 8000 Hz * 32 (+0.23%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_16;
-			break;
-		default: /* 32 */
-			/* 1026312 Hz ~= _2_ * 8000 Hz * 64 (+0.23%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_8;
-		}
-		break;
-	case 11025:
-		acps = 5622000;
-		switch (width) {
-		case 16:
-			/* 351375 Hz ~= 11025 Hz * 32 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_4;
-			break;
-		default: /* 32 */
-			/* 702750 Hz ~= 11025 Hz * 64 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-		}
-		break;
-	case 22050:
-		acps = 5622000;
-		switch (width) {
-		case 16:
-			/* 702750 Hz ~= 22050 Hz * 32 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			break;
-		default: /* 32 */
-			/* 1405500 Hz ~= 22050 Hz * 64 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-		}
-		break;
-	case 44100:
-		acps = 5622000;
-		switch (width) {
-		case 16:
-			/* 1405500 Hz ~= 44100 Hz * 32 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			break;
-		default: /* 32 */
-			/* 2811000 Hz ~= 44100 Hz * 64 (-0.41%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-		}
-		break;
-	case 48000:
-		acps = 12235000;
-		switch (width) {
-		case 16:
-			/* 1529375 Hz ~= 48000 Hz * 32 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			break;
-		default: /* 32 */
-			/* 3058750 Hz ~= 48000 Hz * 64 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-		}
-		break;
-	case 96000:
-	default:
-		acps = 12235000;
-		switch (width) {
-		case 16:
-			/* 3058750 Hz ~= 96000 Hz * 32 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_1;
-			break;
-		default: /* 32 */
-			/* 6117500 Hz ~= 96000 Hz * 64 (-0.44%) */
-			acds = PXA_SSP_CLK_AUDIO_DIV_2;
-			div4 = PXA_SSP_CLK_SCDB_1;
-			break;
-		}
-		break;
-	}
-
 	/* set codec DAI configuration */
 	ret = snd_soc_dai_set_fmt(codec_dai, SND_SOC_DAIFMT_MSB |
 			SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBS_CFS);
@@ -191,6 +105,7 @@ static int magician_playback_hw_params(struct snd_pcm_substream *substream,
 	if (ret < 0)
 		return ret;
 
+	width = snd_pcm_format_physical_width(params_format(params));
 	ret = snd_soc_dai_set_tdm_slot(cpu_dai, 1, 0, 1, width);
 	if (ret < 0)
 		return ret;
@@ -201,23 +116,6 @@ static int magician_playback_hw_params(struct snd_pcm_substream *substream,
 	if (ret < 0)
 		return ret;
 
-	/* set the SSP audio system clock ACDS divider */
-	ret = snd_soc_dai_set_clkdiv(cpu_dai,
-			PXA_SSP_AUDIO_DIV_ACDS, acds);
-	if (ret < 0)
-		return ret;
-
-	/* set the SSP audio system clock SCDB divider4 */
-	ret = snd_soc_dai_set_clkdiv(cpu_dai,
-			PXA_SSP_AUDIO_DIV_SCDB, div4);
-	if (ret < 0)
-		return ret;
-
-	/* set SSP audio pll clock */
-	ret = snd_soc_dai_set_pll(cpu_dai, 0, 0, 0, acps);
-	if (ret < 0)
-		return ret;
-
 	return 0;
 }
 
diff --git a/sound/soc/pxa/zylonite.c b/sound/soc/pxa/zylonite.c
index ba468e560dd2..230eee450f45 100644
--- a/sound/soc/pxa/zylonite.c
+++ b/sound/soc/pxa/zylonite.c
@@ -83,11 +83,9 @@ static int zylonite_voice_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_dai *codec_dai = rtd->codec_dai;
 	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
-	unsigned int pll_out = 0;
 	unsigned int wm9713_div = 0;
 	int ret = 0;
 	int rate = params_rate(params);
-	int width = snd_pcm_format_physical_width(params_format(params));
 
 	/* Only support ratios that we can generate neatly from the AC97
 	 * based master clock - in particular, this excludes 44.1kHz.
@@ -109,17 +107,10 @@ static int zylonite_voice_hw_params(struct snd_pcm_substream *substream,
 		return -EINVAL;
 	}
 
-	/* Add 1 to the width for the leading clock cycle */
-	pll_out = rate * (width + 1) * 8;
-
 	ret = snd_soc_dai_set_sysclk(cpu_dai, PXA_SSP_CLK_AUDIO, 0, 1);
 	if (ret < 0)
 		return ret;
 
-	ret = snd_soc_dai_set_pll(cpu_dai, 0, 0, 0, pll_out);
-	if (ret < 0)
-		return ret;
-
 	if (clk_pout)
 		ret = snd_soc_dai_set_clkdiv(codec_dai, WM9713_PCMCLK_PLL_DIV,
 					     WM9713_PCMDIV(wm9713_div));
-- 
cgit v1.2.3


From eecd6857709e08781e41f3eb0e0c669d9ca07d87 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 08:27:41 -0500
Subject: tls: Fix copy-paste error in tls_device_reencrypt

It seems that the proper structure to use in this particular
case is *skb_iter* instead of skb.

Addresses-Coverity-ID: 1471906 ("Copy-paste error")
Fixes: 4799ac81e52a ("tls: Add rx inline crypto offload")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 4995d84d228d..1e968d238adf 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -615,7 +615,7 @@ static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
 			     TLS_CIPHER_AES_GCM_128_TAG_SIZE);
 
 		if (skb_iter->decrypted)
-			skb_store_bits(skb, offset, buf, copy);
+			skb_store_bits(skb_iter, offset, buf, copy);
 
 		offset += copy;
 		buf += copy;
-- 
cgit v1.2.3


From 3f48c6813fc62af183660fbf04edaac7e3615205 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 17 Jul 2018 10:29:29 +0100
Subject: drm/amdgpu: fix spelling mistake "successed" -> "succeeded"

Trivial fix to spelling mistake in dev_err error message.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 386a7b34d2f4..9b8264c761f7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2004,7 +2004,7 @@ static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 				continue;
 
 			r = block->version->funcs->hw_init(adev);
-			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
 		}
@@ -2039,7 +2039,7 @@ static int amdgpu_device_ip_reinit_late_sriov(struct amdgpu_device *adev)
 				continue;
 
 			r = block->version->funcs->hw_init(adev);
-			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"successed");
+			DRM_INFO("RE-INIT: %s %s\n", block->version->funcs->name, r?"failed":"succeeded");
 			if (r)
 				return r;
 		}
@@ -3091,7 +3091,7 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
  * @adev: amdgpu device pointer
  *
  * attempt to do soft-reset or full-reset and reinitialize Asic
- * return 0 means successed otherwise failed
+ * return 0 means succeeded otherwise failed
  */
 static int amdgpu_device_reset(struct amdgpu_device *adev)
 {
@@ -3169,7 +3169,7 @@ out:
  * @from_hypervisor: request from hypervisor
  *
  * do VF FLR and reinitialize Asic
- * return 0 means successed otherwise failed
+ * return 0 means succeeded otherwise failed
  */
 static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
 				     bool from_hypervisor)
@@ -3294,7 +3294,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
 		dev_info(adev->dev, "GPU reset(%d) failed\n", atomic_read(&adev->gpu_reset_counter));
 		amdgpu_vf_error_put(adev, AMDGIM_ERROR_VF_GPU_RESET_FAIL, 0, r);
 	} else {
-		dev_info(adev->dev, "GPU reset(%d) successed!\n",atomic_read(&adev->gpu_reset_counter));
+		dev_info(adev->dev, "GPU reset(%d) succeeded!\n",atomic_read(&adev->gpu_reset_counter));
 	}
 
 	amdgpu_vf_error_trans_all(adev);
-- 
cgit v1.2.3


From 7b42573bb8a084175500eb62c4da9d46319e3d7e Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Thu, 19 Jul 2018 14:17:30 -0400
Subject: drm/amd/display: Drop unused backlight functions in DM

These are only ever called for non-DC code.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 5fc13e71a3b5..15c7b350f4f6 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1574,18 +1574,6 @@ static void dm_bandwidth_update(struct amdgpu_device *adev)
 	/* TODO: implement later */
 }
 
-static void dm_set_backlight_level(struct amdgpu_encoder *amdgpu_encoder,
-				     u8 level)
-{
-	/* TODO: translate amdgpu_encoder to display_index and call DAL */
-}
-
-static u8 dm_get_backlight_level(struct amdgpu_encoder *amdgpu_encoder)
-{
-	/* TODO: translate amdgpu_encoder to display_index and call DAL */
-	return 0;
-}
-
 static int amdgpu_notify_freesync(struct drm_device *dev, void *data,
 				struct drm_file *filp)
 {
@@ -1614,10 +1602,8 @@ static int amdgpu_notify_freesync(struct drm_device *dev, void *data,
 static const struct amdgpu_display_funcs dm_display_funcs = {
 	.bandwidth_update = dm_bandwidth_update, /* called unconditionally */
 	.vblank_get_counter = dm_vblank_get_counter,/* called unconditionally */
-	.backlight_set_level =
-		dm_set_backlight_level,/* called unconditionally */
-	.backlight_get_level =
-		dm_get_backlight_level,/* called unconditionally */
+	.backlight_set_level = NULL, /* never called for DC */
+	.backlight_get_level = NULL, /* never called for DC */
 	.hpd_sense = NULL,/* called unconditionally */
 	.hpd_set_polarity = NULL, /* called unconditionally */
 	.hpd_get_gpio_reg = NULL, /* VBIOS parsing. DAL does it. */
-- 
cgit v1.2.3


From 1bc460a45b9746db4b0e6be46c122c377120aace Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Tue, 17 Jul 2018 10:51:23 -0400
Subject: drm/amd/display: Honor pplib stutter mask for all ASICs in DC

[Why]
We were only setting this mask for DCN, but should really use it
universally for all ASICs.

[How]
Move the assignment out of the Raven switch statement for all ASICs
other than Stoney and Carrizo.

v2: Keep stutter always on for Carrizo and Stoney (Alex)

Cc: Rex.Zhu@amd.com
Cc: Feifei.Xu@amd.com
Cc: Kenneth.Feng@amd.com
Cc: Evan.Quan@amd.com
Cc: Bhawanpreet.Lakha@amd.com
Cc: Jordan.Lazare@amd.com
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 15c7b350f4f6..45e062022461 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1532,10 +1532,6 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 			DRM_ERROR("DM: Failed to initialize IRQ\n");
 			goto fail;
 		}
-		/*
-		 * Temporary disable until pplib/smu interaction is implemented
-		 */
-		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
 		break;
 #endif
 	default:
@@ -1543,6 +1539,9 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
 		goto fail;
 	}
 
+	if (adev->asic_type != CHIP_CARRIZO && adev->asic_type != CHIP_STONEY)
+		dm->dc->debug.disable_stutter = amdgpu_pp_feature_mask & PP_STUTTER_MODE ? false : true;
+
 	return 0;
 fail:
 	kfree(aencoder);
-- 
cgit v1.2.3


From 4d3b9ae50ea03d3295fc9b5f5c88f49fcd0e99f9 Mon Sep 17 00:00:00 2001
From: Shirish S <shirish.s@amd.com>
Date: Wed, 18 Jul 2018 13:36:26 +0530
Subject: drm/amdgpu: lock and unlock console only for amdgpu_fbdev_set_suspend
 [V5]
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[Why]
While the console_lock is held, console output will be buffered, till
its unlocked it wont be emitted, hence its ideal to unlock sooner to enable
debugging/detecting/fixing of any issue in the remaining sequence of events
in resume path.
The concern here is about consoles other than fbcon on the device,
e.g. a serial console

[How]
This patch restructures the console_lock, console_unlock around
amdgpu_fbdev_set_suspend() and moves this new block appropriately.

V2: Kept amdgpu_fbdev_set_suspend after pci_set_power_state
V3: Updated the commit message to clarify the real concern that this patch
    addresses.
V4: code clean-up.
V5: fixed return value

Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 22 +++++++---------------
 1 file changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 9b8264c761f7..fddf54773a6e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2720,15 +2720,12 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (dev->switch_power_state == DRM_SWITCH_POWER_OFF)
 		return 0;
 
-	if (fbcon)
-		console_lock();
-
 	if (resume) {
 		pci_set_power_state(dev->pdev, PCI_D0);
 		pci_restore_state(dev->pdev);
 		r = pci_enable_device(dev->pdev);
 		if (r)
-			goto unlock;
+			return r;
 	}
 
 	/* post card */
@@ -2741,14 +2738,14 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	r = amdgpu_device_ip_resume(adev);
 	if (r) {
 		DRM_ERROR("amdgpu_device_ip_resume failed (%d).\n", r);
-		goto unlock;
+		return r;
 	}
 	amdgpu_fence_driver_resume(adev);
 
 
 	r = amdgpu_device_ip_late_init(adev);
 	if (r)
-		goto unlock;
+		return r;
 
 	/* pin cursors */
 	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
@@ -2783,6 +2780,9 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			}
 			drm_modeset_unlock_all(dev);
 		}
+		console_lock();
+		amdgpu_fbdev_set_suspend(adev, 0);
+		console_unlock();
 	}
 
 	drm_kms_helper_poll_enable(dev);
@@ -2806,15 +2806,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 #ifdef CONFIG_PM
 	dev->dev->power.disable_depth--;
 #endif
-
-	if (fbcon)
-		amdgpu_fbdev_set_suspend(adev, 0);
-
-unlock:
-	if (fbcon)
-		console_unlock();
-
-	return r;
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 88de542e421ac86b8148b232f822de306004e5a0 Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Thu, 19 Jul 2018 16:21:42 +0800
Subject: drm/amd/pp: Read vbios vddc limit before use them

Use the vddc limit before read them from vbios

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 1a0dccb3fac1..755f23511fc3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -289,7 +289,15 @@ static int vega10_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
 	struct phm_ppt_v1_voltage_lookup_table *vddc_lookup_table;
 	struct phm_ppt_v1_clock_voltage_dependency_table *dep_table[3];
 	struct phm_ppt_v1_clock_voltage_dependency_table *od_table[3];
+	struct pp_atomfwctrl_avfs_parameters avfs_params = {0};
 	uint32_t i;
+	int result;
+
+	result = pp_atomfwctrl_get_avfs_information(hwmgr, &avfs_params);
+	if (!result) {
+		data->odn_dpm_table.max_vddc = avfs_params.ulMaxVddc;
+		data->odn_dpm_table.min_vddc = avfs_params.ulMinVddc;
+	}
 
 	od_lookup_table = &odn_table->vddc_lookup_table;
 	vddc_lookup_table = table_info->vddc_lookup_table;
@@ -2072,9 +2080,6 @@ static int vega10_populate_avfs_parameters(struct pp_hwmgr *hwmgr)
 	if (data->smu_features[GNLD_AVFS].supported) {
 		result = pp_atomfwctrl_get_avfs_information(hwmgr, &avfs_params);
 		if (!result) {
-			data->odn_dpm_table.max_vddc = avfs_params.ulMaxVddc;
-			data->odn_dpm_table.min_vddc = avfs_params.ulMinVddc;
-
 			pp_table->MinVoltageVid = (uint8_t)
 					convert_to_vid((uint16_t)(avfs_params.ulMinVddc));
 			pp_table->MaxVoltageVid = (uint8_t)
-- 
cgit v1.2.3


From a0c3bf0ff40d6c482d381fe2c577a4e6c50f522f Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Thu, 19 Jul 2018 16:32:05 +0800
Subject: drm/amd/pp: Update clk with od setting when set power state

This can fix the issue resume from S3, the user's OD setting
were reverted to default.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 755f23511fc3..6d93d52975ec 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3259,10 +3259,25 @@ static int vega10_populate_and_upload_sclk_mclk_dpm_levels(
 {
 	int result = 0;
 	struct vega10_hwmgr *data = hwmgr->backend;
+	struct vega10_dpm_table *dpm_table = &data->dpm_table;
+	struct vega10_odn_dpm_table *odn_table = &data->odn_dpm_table;
+	struct vega10_odn_clock_voltage_dependency_table *odn_clk_table = &odn_table->vdd_dep_on_sclk;
+	int count;
 
 	if (!data->need_update_dpm_table)
 		return 0;
 
+	if (hwmgr->od_enabled && data->need_update_dpm_table & DPMTABLE_OD_UPDATE_SCLK) {
+		for (count = 0; count < dpm_table->gfx_table.count; count++)
+			dpm_table->gfx_table.dpm_levels[count].value = odn_clk_table->entries[count].clk;
+	}
+
+	odn_clk_table = &odn_table->vdd_dep_on_mclk;
+	if (hwmgr->od_enabled && data->need_update_dpm_table & DPMTABLE_OD_UPDATE_MCLK) {
+		for (count = 0; count < dpm_table->mem_table.count; count++)
+			dpm_table->mem_table.dpm_levels[count].value = odn_clk_table->entries[count].clk;
+	}
+
 	if (data->need_update_dpm_table &
 			(DPMTABLE_OD_UPDATE_SCLK + DPMTABLE_UPDATE_SCLK + DPMTABLE_UPDATE_SOCCLK)) {
 		result = vega10_populate_all_graphic_levels(hwmgr);
-- 
cgit v1.2.3


From 97e8f102f5a9123d30258e196c6c1ea29cf52e83 Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Tue, 17 Jul 2018 18:31:50 +0800
Subject: drm/amd/pp: Set Max clock level to display by default

avoid the error in dmesg:
[drm:dm_pp_get_static_clocks]
*ERROR* DM_PPLIB: invalid powerlevel state: 0!

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/amd_powerplay.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
index 75c208283e5f..7a646f94b478 100644
--- a/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
+++ b/drivers/gpu/drm/amd/powerplay/amd_powerplay.c
@@ -998,7 +998,7 @@ static int pp_get_display_power_level(void *handle,
 static int pp_get_current_clocks(void *handle,
 		struct amd_pp_clock_info *clocks)
 {
-	struct amd_pp_simple_clock_info simple_clocks;
+	struct amd_pp_simple_clock_info simple_clocks = { 0 };
 	struct pp_clock_info hw_clocks;
 	struct pp_hwmgr *hwmgr = handle;
 	int ret = 0;
@@ -1034,7 +1034,10 @@ static int pp_get_current_clocks(void *handle,
 	clocks->max_engine_clock_in_sr = hw_clocks.max_eng_clk;
 	clocks->min_engine_clock_in_sr = hw_clocks.min_eng_clk;
 
-	clocks->max_clocks_state = simple_clocks.level;
+	if (simple_clocks.level == 0)
+		clocks->max_clocks_state = PP_DAL_POWERLEVEL_7;
+	else
+		clocks->max_clocks_state = simple_clocks.level;
 
 	if (0 == phm_get_current_shallow_sleep_clocks(hwmgr, &hwmgr->current_ps->hardware, &hw_clocks)) {
 		clocks->max_engine_clock_in_sr = hw_clocks.max_eng_clk;
@@ -1137,6 +1140,8 @@ static int pp_get_display_mode_validation_clocks(void *handle,
 	if (!hwmgr || !hwmgr->pm_en ||!clocks)
 		return -EINVAL;
 
+	clocks->level = PP_DAL_POWERLEVEL_7;
+
 	mutex_lock(&hwmgr->smu_lock);
 
 	if (phm_cap_enabled(hwmgr->platform_descriptor.platformCaps, PHM_PlatformCaps_DynamicPatchPowerState))
-- 
cgit v1.2.3


From 3dbd823e53b572df1c84d73e85c518212fcdaddb Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Tue, 17 Jul 2018 20:18:04 +0800
Subject: drm/amd/display: Convert 10kHz clks from PPLib into kHz

Except special naming as *_in_khz, The default clock unit in powerplay
is in 10KHz. so need to * 10 as expecting clock frequency in display
is in kHz.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
index c69ae78d82b2..fbe878ae1e8c 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_pp_smu.c
@@ -469,8 +469,8 @@ bool dm_pp_get_static_clocks(
 		return false;
 
 	static_clk_info->max_clocks_state = pp_to_dc_powerlevel_state(pp_clk_info.max_clocks_state);
-	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock;
-	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock;
+	static_clk_info->max_mclk_khz = pp_clk_info.max_memory_clock * 10;
+	static_clk_info->max_sclk_khz = pp_clk_info.max_engine_clock * 10;
 
 	return true;
 }
-- 
cgit v1.2.3


From ecb8c50382e2e8bfd60483e3edf8cb883f7bde62 Mon Sep 17 00:00:00 2001
From: Shirish S <shirish.s@amd.com>
Date: Fri, 20 Jul 2018 17:26:50 +0530
Subject: drm/amdgpu: use drm_fb helper for console_(un)lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch removes the usage of console_(un)lock
by replacing drm_fb_helper_set_suspend() to
drm_fb_helper_set_suspend_unlocked() which locks and
unlocks the console instead of locking ourselves.

Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 8 ++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c     | 4 ++--
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index fddf54773a6e..e57f90f444c5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2691,11 +2691,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			DRM_ERROR("amdgpu asic reset failed\n");
 	}
 
-	if (fbcon) {
-		console_lock();
+	if (fbcon)
 		amdgpu_fbdev_set_suspend(adev, 1);
-		console_unlock();
-	}
+
 	return 0;
 }
 
@@ -2780,9 +2778,7 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 			}
 			drm_modeset_unlock_all(dev);
 		}
-		console_lock();
 		amdgpu_fbdev_set_suspend(adev, 0);
-		console_unlock();
 	}
 
 	drm_kms_helper_poll_enable(dev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
index d44b76455e89..69c5d22f29bd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fb.c
@@ -373,8 +373,8 @@ void amdgpu_fbdev_fini(struct amdgpu_device *adev)
 void amdgpu_fbdev_set_suspend(struct amdgpu_device *adev, int state)
 {
 	if (adev->mode_info.rfbdev)
-		drm_fb_helper_set_suspend(&adev->mode_info.rfbdev->helper,
-			state);
+		drm_fb_helper_set_suspend_unlocked(&adev->mode_info.rfbdev->helper,
+						   state);
 }
 
 int amdgpu_fbdev_total_size(struct amdgpu_device *adev)
-- 
cgit v1.2.3


From 7766484b4a18373ac557ce6ea442ef28517c8224 Mon Sep 17 00:00:00 2001
From: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Date: Fri, 20 Jul 2018 11:42:24 -0400
Subject: drm/amdgpu: Fix warning in dma_fence_is_later on resume from S3.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Problem:
amdgpu_ttm_set_buffer_funcs_status destroys adev->mman.entity on suspend
without releasing adev->mman.bdev.man[TTM_PL_VRAM].move fence
so on resume the new drm_sched_entity.fence_context causes
the warning against the old fence context which is different.

Fix:
When destroying sched_entity in amdgpu_ttm_set_buffer_funcs_status
release  man->move and set the pointer to NULL.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 13977ea6a097..8ed102933ca2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1927,6 +1927,8 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 	} else {
 		drm_sched_entity_destroy(adev->mman.entity.sched,
 					 &adev->mman.entity);
+		dma_fence_put(man->move);
+		man->move = NULL;
 	}
 
 	/* this just adjusts TTM size idea, which sets lpfn to the correct value */
-- 
cgit v1.2.3


From 9e7204beae8cbb75939acd640829e10979f2c920 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 19 Jul 2018 09:17:02 -0500
Subject: drm/amdgpu/apci: don't call sbios request function if it's not
 supported

Check the supported functions mask before calling the bios
requests method.

Reviewed-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 53 +++++++++++++++++---------------
 1 file changed, 28 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 0d8c3fc6eace..455617813ec4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -364,7 +364,6 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 			       struct acpi_bus_event *event)
 {
 	struct amdgpu_atif *atif = adev->atif;
-	struct atif_sbios_requests req;
 	int count;
 
 	DRM_DEBUG_DRIVER("event, device_class = %s, type = %#x\n",
@@ -379,42 +378,46 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 		/* Not our event */
 		return NOTIFY_DONE;
 
-	/* Check pending SBIOS requests */
-	count = amdgpu_atif_get_sbios_requests(atif, &req);
+	if (atif->functions.sbios_requests) {
+		struct atif_sbios_requests req;
 
-	if (count <= 0)
-		return NOTIFY_DONE;
+		/* Check pending SBIOS requests */
+		count = amdgpu_atif_get_sbios_requests(atif, &req);
+
+		if (count <= 0)
+			return NOTIFY_DONE;
 
-	DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
+		DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
 
-	if (req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) {
-		struct amdgpu_encoder *enc = atif->encoder_for_bl;
+		if (req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) {
+			struct amdgpu_encoder *enc = atif->encoder_for_bl;
 
-		if (enc) {
-			struct amdgpu_encoder_atom_dig *dig = enc->enc_priv;
+			if (enc) {
+				struct amdgpu_encoder_atom_dig *dig = enc->enc_priv;
 
-			DRM_DEBUG_DRIVER("Changing brightness to %d\n",
-					req.backlight_level);
+				DRM_DEBUG_DRIVER("Changing brightness to %d\n",
+						 req.backlight_level);
 
-			amdgpu_display_backlight_set_level(adev, enc, req.backlight_level);
+				amdgpu_display_backlight_set_level(adev, enc, req.backlight_level);
 
 #if defined(CONFIG_BACKLIGHT_CLASS_DEVICE) || defined(CONFIG_BACKLIGHT_CLASS_DEVICE_MODULE)
-			backlight_force_update(dig->bl_dev,
-					       BACKLIGHT_UPDATE_HOTKEY);
+				backlight_force_update(dig->bl_dev,
+						       BACKLIGHT_UPDATE_HOTKEY);
 #endif
+			}
 		}
-	}
-	if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
-		if ((adev->flags & AMD_IS_PX) &&
-		    amdgpu_atpx_dgpu_req_power_for_displays()) {
-			pm_runtime_get_sync(adev->ddev->dev);
-			/* Just fire off a uevent and let userspace tell us what to do */
-			drm_helper_hpd_irq_event(adev->ddev);
-			pm_runtime_mark_last_busy(adev->ddev->dev);
-			pm_runtime_put_autosuspend(adev->ddev->dev);
+		if (req.pending & ATIF_DGPU_DISPLAY_EVENT) {
+			if ((adev->flags & AMD_IS_PX) &&
+			    amdgpu_atpx_dgpu_req_power_for_displays()) {
+				pm_runtime_get_sync(adev->ddev->dev);
+				/* Just fire off a uevent and let userspace tell us what to do */
+				drm_helper_hpd_irq_event(adev->ddev);
+				pm_runtime_mark_last_busy(adev->ddev->dev);
+				pm_runtime_put_autosuspend(adev->ddev->dev);
+			}
 		}
+		/* TODO: check other events */
 	}
-	/* TODO: check other events */
 
 	/* We've handled the event, stop the notifier chain. The ACPI interface
 	 * overloads ACPI_VIDEO_NOTIFY_PROBE, we don't want to send that to
-- 
cgit v1.2.3


From 5b8eb0edba15b1685acbb76751fbb189de4ca310 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 19 Jul 2018 09:28:23 -0500
Subject: drm/amdgpu/acpi: skip backlight events for DC

No change in behavior, just bail sooner.

Reviewed-by: Jim Qu <Jim.Qu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
index 455617813ec4..353993218f21 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acpi.c
@@ -389,7 +389,9 @@ static int amdgpu_atif_handler(struct amdgpu_device *adev,
 
 		DRM_DEBUG_DRIVER("ATIF: %d pending SBIOS requests\n", count);
 
-		if (req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) {
+		/* todo: add DC handling */
+		if ((req.pending & ATIF_PANEL_BRIGHTNESS_CHANGE_REQUEST) &&
+		    !amdgpu_device_has_dc_support(adev)) {
 			struct amdgpu_encoder *enc = atif->encoder_for_bl;
 
 			if (enc) {
-- 
cgit v1.2.3


From e7854a038015122538df4777b8c192e03b4eb6c2 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 19 Jul 2018 13:10:07 -0500
Subject: drm/amdgpu: split ip suspend into 2 phases

We need to do some IPs earlier to deal with ordering issues
similar to how resume is split into two phases. Do DCE first
to deal with atomic, then do the rest.

Acked-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-and-tested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 78 +++++++++++++++++++++++++++++-
 1 file changed, 76 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index e57f90f444c5..36426e66964d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1926,7 +1926,7 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
 }
 
 /**
- * amdgpu_device_ip_suspend - run suspend for hardware IPs
+ * amdgpu_device_ip_suspend_phase1 - run suspend for hardware IPs (phase 1)
  *
  * @adev: amdgpu_device pointer
  *
@@ -1936,7 +1936,55 @@ static void amdgpu_device_ip_late_init_func_handler(struct work_struct *work)
  * in each IP into a state suitable for suspend.
  * Returns 0 on success, negative error code on failure.
  */
-int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
+static int amdgpu_device_ip_suspend_phase1(struct amdgpu_device *adev)
+{
+	int i, r;
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_request_full_gpu(adev, false);
+
+	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
+		if (!adev->ip_blocks[i].status.valid)
+			continue;
+		/* displays are handled separately */
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE) {
+			/* ungate blocks so that suspend can properly shut them down */
+			if (adev->ip_blocks[i].version->funcs->set_clockgating_state) {
+				r = adev->ip_blocks[i].version->funcs->set_clockgating_state((void *)adev,
+											     AMD_CG_STATE_UNGATE);
+				if (r) {
+					DRM_ERROR("set_clockgating_state(ungate) of IP block <%s> failed %d\n",
+						  adev->ip_blocks[i].version->funcs->name, r);
+				}
+			}
+			/* XXX handle errors */
+			r = adev->ip_blocks[i].version->funcs->suspend(adev);
+			/* XXX handle errors */
+			if (r) {
+				DRM_ERROR("suspend of IP block <%s> failed %d\n",
+					  adev->ip_blocks[i].version->funcs->name, r);
+			}
+		}
+	}
+
+	if (amdgpu_sriov_vf(adev))
+		amdgpu_virt_release_full_gpu(adev, false);
+
+	return 0;
+}
+
+/**
+ * amdgpu_device_ip_suspend_phase2 - run suspend for hardware IPs (phase 2)
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main suspend function for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked, clockgating is disabled and the
+ * suspend callbacks are run.  suspend puts the hardware and software state
+ * in each IP into a state suitable for suspend.
+ * Returns 0 on success, negative error code on failure.
+ */
+static int amdgpu_device_ip_suspend_phase2(struct amdgpu_device *adev)
 {
 	int i, r;
 
@@ -1957,6 +2005,9 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
 		if (!adev->ip_blocks[i].status.valid)
 			continue;
+		/* displays are handled in phase1 */
+		if (adev->ip_blocks[i].version->type == AMD_IP_BLOCK_TYPE_DCE)
+			continue;
 		/* ungate blocks so that suspend can properly shut them down */
 		if (adev->ip_blocks[i].version->type != AMD_IP_BLOCK_TYPE_SMC &&
 			adev->ip_blocks[i].version->funcs->set_clockgating_state) {
@@ -1982,6 +2033,29 @@ int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
 	return 0;
 }
 
+/**
+ * amdgpu_device_ip_suspend - run suspend for hardware IPs
+ *
+ * @adev: amdgpu_device pointer
+ *
+ * Main suspend function for hardware IPs.  The list of all the hardware
+ * IPs that make up the asic is walked, clockgating is disabled and the
+ * suspend callbacks are run.  suspend puts the hardware and software state
+ * in each IP into a state suitable for suspend.
+ * Returns 0 on success, negative error code on failure.
+ */
+int amdgpu_device_ip_suspend(struct amdgpu_device *adev)
+{
+	int r;
+
+	r = amdgpu_device_ip_suspend_phase1(adev);
+	if (r)
+		return r;
+	r = amdgpu_device_ip_suspend_phase2(adev);
+
+	return r;
+}
+
 static int amdgpu_device_ip_reinit_early_sriov(struct amdgpu_device *adev)
 {
 	int i, r;
-- 
cgit v1.2.3


From fe1053b7859dcbe830212de43befe6c7e4f089a8 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 19 Jul 2018 13:24:33 -0500
Subject: drm/amdgpu: rework suspend and resume to deal with atomic changes

Use the newly split ip suspend functions to do suspend displays
first (to deal with atomic so that FBs can be unpinned before
attempting to evict vram), then evict vram, then suspend the
other IPs.  Also move the non-DC pinning code to only be
called in the non-DC cases since atomic should take care of
DC.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107065
Fixes: e00fb85 drm: Stop updating plane->crtc/fb/old_fb on atomic drivers
Acked-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-and-tested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 86 ++++++++++++++++--------------
 1 file changed, 45 insertions(+), 41 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 36426e66964d..61981d0701b5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2709,44 +2709,46 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			drm_helper_connector_dpms(connector, DRM_MODE_DPMS_OFF);
 		}
 		drm_modeset_unlock_all(dev);
-	}
-
-	amdgpu_amdkfd_suspend(adev);
-
-	/* unpin the front buffers and cursors */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-		struct drm_framebuffer *fb = crtc->primary->fb;
-		struct amdgpu_bo *robj;
-
-		if (amdgpu_crtc->cursor_bo) {
-			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-			r = amdgpu_bo_reserve(aobj, true);
-			if (r == 0) {
-				amdgpu_bo_unpin(aobj);
-				amdgpu_bo_unreserve(aobj);
+			/* unpin the front buffers and cursors */
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+			struct drm_framebuffer *fb = crtc->primary->fb;
+			struct amdgpu_bo *robj;
+
+			if (amdgpu_crtc->cursor_bo) {
+				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+				r = amdgpu_bo_reserve(aobj, true);
+				if (r == 0) {
+					amdgpu_bo_unpin(aobj);
+					amdgpu_bo_unreserve(aobj);
+				}
 			}
-		}
 
-		if (fb == NULL || fb->obj[0] == NULL) {
-			continue;
-		}
-		robj = gem_to_amdgpu_bo(fb->obj[0]);
-		/* don't unpin kernel fb objects */
-		if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
-			r = amdgpu_bo_reserve(robj, true);
-			if (r == 0) {
-				amdgpu_bo_unpin(robj);
-				amdgpu_bo_unreserve(robj);
+			if (fb == NULL || fb->obj[0] == NULL) {
+				continue;
+			}
+			robj = gem_to_amdgpu_bo(fb->obj[0]);
+			/* don't unpin kernel fb objects */
+			if (!amdgpu_fbdev_robj_is_fb(adev, robj)) {
+				r = amdgpu_bo_reserve(robj, true);
+				if (r == 0) {
+					amdgpu_bo_unpin(robj);
+					amdgpu_bo_unreserve(robj);
+				}
 			}
 		}
 	}
+
+	amdgpu_amdkfd_suspend(adev);
+
+	r = amdgpu_device_ip_suspend_phase1(adev);
+
 	/* evict vram memory */
 	amdgpu_bo_evict_vram(adev);
 
 	amdgpu_fence_driver_suspend(adev);
 
-	r = amdgpu_device_ip_suspend(adev);
+	r = amdgpu_device_ip_suspend_phase2(adev);
 
 	/* evict remaining vram memory
 	 * This second call to evict vram is to evict the gart page table
@@ -2819,19 +2821,21 @@ int amdgpu_device_resume(struct drm_device *dev, bool resume, bool fbcon)
 	if (r)
 		return r;
 
-	/* pin cursors */
-	list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
-		struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
-
-		if (amdgpu_crtc->cursor_bo) {
-			struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
-			r = amdgpu_bo_reserve(aobj, true);
-			if (r == 0) {
-				r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
-				if (r != 0)
-					DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
-				amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
-				amdgpu_bo_unreserve(aobj);
+	if (!amdgpu_device_has_dc_support(adev)) {
+		/* pin cursors */
+		list_for_each_entry(crtc, &dev->mode_config.crtc_list, head) {
+			struct amdgpu_crtc *amdgpu_crtc = to_amdgpu_crtc(crtc);
+
+			if (amdgpu_crtc->cursor_bo) {
+				struct amdgpu_bo *aobj = gem_to_amdgpu_bo(amdgpu_crtc->cursor_bo);
+				r = amdgpu_bo_reserve(aobj, true);
+				if (r == 0) {
+					r = amdgpu_bo_pin(aobj, AMDGPU_GEM_DOMAIN_VRAM);
+					if (r != 0)
+						DRM_ERROR("Failed to pin cursor BO (%d)\n", r);
+					amdgpu_crtc->cursor_addr = amdgpu_bo_gpu_offset(aobj);
+					amdgpu_bo_unreserve(aobj);
+				}
 			}
 		}
 	}
-- 
cgit v1.2.3


From a86c4120528f0c87b10837abbe3eada542791177 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Wed, 18 Jul 2018 09:32:43 -0700
Subject: nbd: constify nla_policy

The netlink policy should be const like other drivers.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/block/nbd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 74a05561b620..e07401d3901d 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1571,7 +1571,7 @@ static int find_free_cb(int id, void *ptr, void *data)
 }
 
 /* Netlink interface. */
-static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
+static const struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
 	[NBD_ATTR_INDEX]		=	{ .type = NLA_U32 },
 	[NBD_ATTR_SIZE_BYTES]		=	{ .type = NLA_U64 },
 	[NBD_ATTR_BLOCK_SIZE_BYTES]	=	{ .type = NLA_U64 },
@@ -1583,14 +1583,14 @@ static struct nla_policy nbd_attr_policy[NBD_ATTR_MAX + 1] = {
 	[NBD_ATTR_DEVICE_LIST]		=	{ .type = NLA_NESTED},
 };
 
-static struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
+static const struct nla_policy nbd_sock_policy[NBD_SOCK_MAX + 1] = {
 	[NBD_SOCK_FD]			=	{ .type = NLA_U32 },
 };
 
 /* We don't use this right now since we don't parse the incoming list, but we
  * still want it here so userspace knows what to expect.
  */
-static struct nla_policy __attribute__((unused))
+static const struct nla_policy __attribute__((unused))
 nbd_device_policy[NBD_DEVICE_ATTR_MAX + 1] = {
 	[NBD_DEVICE_INDEX]		=	{ .type = NLA_U32 },
 	[NBD_DEVICE_CONNECTED]		=	{ .type = NLA_U8 },
-- 
cgit v1.2.3


From 5761917a1aac77f40885ec17a3e1d50ab0c737c4 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Wed, 18 Jul 2018 09:32:44 -0700
Subject: gtp: constify nla_policy

The netlink policy structure can be constant like other
drivers.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/gtp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index ec629a730005..7a145172d503 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1255,7 +1255,7 @@ out:
 	return skb->len;
 }
 
-static struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
+static const struct nla_policy gtp_genl_policy[GTPA_MAX + 1] = {
 	[GTPA_LINK]		= { .type = NLA_U32, },
 	[GTPA_VERSION]		= { .type = NLA_U32, },
 	[GTPA_TID]		= { .type = NLA_U64, },
-- 
cgit v1.2.3


From 40999f11ce677ce3c5d0e8f5f76c40192a26b479 Mon Sep 17 00:00:00 2001
From: Jon Maloy <jon.maloy@ericsson.com>
Date: Wed, 18 Jul 2018 19:50:06 +0200
Subject: tipc: make link capability update thread safe

The commit referred to below introduced an update of the link
capabilities field that is not safe. Given the recently added
feature to remove idle node and link items after 5 minutes, there
is a small risk that the update will happen at the very moment the
targeted link is being removed. To avoid this we have to perform
the update inside the node item's write lock protection.

Fixes: 9012de508956 ("tipc: add sequence number check for link STATE messages")
Signed-off-by: Jon Maloy <jon.maloy@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/node.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/tipc/node.c b/net/tipc/node.c
index 52fd80b0e728..3819ab14e073 100644
--- a/net/tipc/node.c
+++ b/net/tipc/node.c
@@ -370,13 +370,17 @@ static struct tipc_node *tipc_node_create(struct net *net, u32 addr,
 	spin_lock_bh(&tn->node_list_lock);
 	n = tipc_node_find(net, addr);
 	if (n) {
+		if (n->capabilities == capabilities)
+			goto exit;
 		/* Same node may come back with new capabilities */
+		write_lock_bh(&n->lock);
 		n->capabilities = capabilities;
 		for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
 			l = n->links[bearer_id].link;
 			if (l)
 				tipc_link_update_caps(l, capabilities);
 		}
+		write_unlock_bh(&n->lock);
 		goto exit;
 	}
 	n = kzalloc(sizeof(*n), GFP_ATOMIC);
-- 
cgit v1.2.3


From 7ab92e89bf8b0a93f0d53b6d83270e4cd0f7c563 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 19 Jul 2018 17:55:58 -0500
Subject: PCI/AER: Clear only ERR_FATAL status bits during fatal recovery

During recovery from fatal errors, we previously called
pci_cleanup_aer_uncorrect_error_status(), which cleared *all* uncorrectable
error status bits (both ERR_FATAL and ERR_NONFATAL).

Instead, call a new pci_aer_clear_fatal_status() that clears only the
ERR_FATAL bits (as indicated by the PCI_ERR_UNCOR_SEVER register).

Based-on-patch-by: Oza Pawandeep <poza@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      |  2 ++
 drivers/pci/pcie/aer.c | 17 +++++++++++++++++
 drivers/pci/pcie/err.c |  2 +-
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index b1ce0dcad1dc..107c64892b66 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -485,10 +485,12 @@ void pci_no_aer(void);
 void pci_aer_init(struct pci_dev *dev);
 void pci_aer_exit(struct pci_dev *dev);
 extern const struct attribute_group aer_stats_attr_group;
+void pci_aer_clear_fatal_status(struct pci_dev *dev);
 #else
 static inline void pci_no_aer(void) { }
 static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
 static inline void pci_aer_exit(struct pci_dev *d) { }
+static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { }
 #endif
 
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 766687094706..b776a768a434 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -399,6 +399,23 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_cleanup_aer_uncorrect_error_status);
 
+void pci_aer_clear_fatal_status(struct pci_dev *dev)
+{
+	int pos;
+	u32 status, sev;
+
+	pos = dev->aer_cap;
+	if (!pos)
+		return;
+
+	/* Clear status bits for ERR_FATAL errors only */
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
+	status &= sev;
+	if (status)
+		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+}
+
 int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 {
 	int pos;
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index f7ce0cb0b0b7..0539518f9861 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -316,7 +316,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 		 * do error recovery on all subordinates of the bridge instead
 		 * of the bridge and clear the error status of the bridge.
 		 */
-		pci_cleanup_aer_uncorrect_error_status(dev);
+		pci_aer_clear_fatal_status(dev);
 	}
 
 	if (result == PCI_ERS_RESULT_RECOVERED) {
-- 
cgit v1.2.3


From e7b0b847de6db161e3917732276e425bc92a2feb Mon Sep 17 00:00:00 2001
From: Oza Pawandeep <poza@codeaurora.org>
Date: Thu, 19 Jul 2018 17:58:05 -0500
Subject: PCI/AER: Clear only ERR_NONFATAL bits during non-fatal recovery

pci_cleanup_aer_uncorrect_error_status() is called by driver .slot_reset()
methods when handling ERR_NONFATAL errors.  Previously this cleared *all*
the bits, including ERR_FATAL bits.

Since we're only handling ERR_NONFATAL errors, clear only the ERR_NONFATAL
error status bits.

Signed-off-by: Oza Pawandeep <poza@codeaurora.org>
[bhelgaas: split to separate patch]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aer.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index b776a768a434..f853e72524be 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -385,13 +385,16 @@ EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 {
 	int pos;
-	u32 status;
+	u32 status, sev;
 
 	pos = dev->aer_cap;
 	if (!pos)
 		return -EIO;
 
+	/* Clear status bits for ERR_NONFATAL errors only */
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
+	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
+	status &= ~sev;
 	if (status)
 		pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
 
-- 
cgit v1.2.3


From 5b6c09660da8779dd545fa717c2b0cc79d477c9e Mon Sep 17 00:00:00 2001
From: Oza Pawandeep <poza@codeaurora.org>
Date: Thu, 19 Jul 2018 17:58:06 -0500
Subject: PCI/AER: Factor out ERR_NONFATAL status bit clearing

aer_error_resume() clears all ERR_NONFATAL error status bits.  This is
exactly what pci_cleanup_aer_uncorrect_error_status(), so use that instead
of duplicating the code.

Signed-off-by: Oza Pawandeep <poza@codeaurora.org>
[bhelgaas: split to separate patch]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aer.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index f853e72524be..4411ada4a91c 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1532,20 +1532,13 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
  */
 static void aer_error_resume(struct pci_dev *dev)
 {
-	int pos;
-	u32 status, mask;
 	u16 reg16;
 
 	/* Clean up Root device status */
 	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &reg16);
 	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, reg16);
 
-	/* Clean AER Root Error Status */
-	pos = dev->aer_cap;
-	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
-	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &mask);
-	status &= ~mask; /* Clear corresponding nonfatal bits */
-	pci_write_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, status);
+	pci_cleanup_aer_uncorrect_error_status(dev);
 }
 
 static struct pcie_port_service_driver aerdriver = {
-- 
cgit v1.2.3


From 43ec03a9e5f382ff70fdef35b4ea813263cd8270 Mon Sep 17 00:00:00 2001
From: Oza Pawandeep <poza@codeaurora.org>
Date: Thu, 19 Jul 2018 17:58:07 -0500
Subject: PCI/AER: Remove ERR_FATAL code from ERR_NONFATAL path

broadcast_error_message() is only used for ERR_NONFATAL events, when the
state is always pci_channel_io_normal, so remove the unused alternate path.

Signed-off-by: Oza Pawandeep <poza@codeaurora.org>
[bhelgaas: changelog]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/err.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 0539518f9861..638eda5c1d79 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -259,15 +259,10 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 		/*
 		 * If the error is reported by an end point, we think this
 		 * error is related to the upstream link of the end point.
+		 * The error is non fatal so the bus is ok; just invoke
+		 * the callback for the function that logged the error.
 		 */
-		if (state == pci_channel_io_normal)
-			/*
-			 * the error is non fatal so the bus is ok, just invoke
-			 * the callback for the function that logged the error.
-			 */
-			cb(dev, &result_data);
-		else
-			pci_walk_bus(dev->bus, cb, &result_data);
+		cb(dev, &result_data);
 	}
 
 	return result_data.result;
-- 
cgit v1.2.3


From ec752f5d54d723af3df03959637f963079643cd8 Mon Sep 17 00:00:00 2001
From: Oza Pawandeep <poza@codeaurora.org>
Date: Thu, 19 Jul 2018 17:58:09 -0500
Subject: PCI/AER: Clear device status bits during ERR_FATAL and ERR_NONFATAL

Clear the device status bits while handling both ERR_FATAL and ERR_NONFATAL
cases.

Signed-off-by: Oza Pawandeep <poza@codeaurora.org>
[bhelgaas: rename to pci_aer_clear_device_status(), declare internal to PCI
core instead of exposing it everywhere]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h      |  2 ++
 drivers/pci/pcie/aer.c | 15 +++++++++------
 drivers/pci/pcie/err.c |  2 ++
 3 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 107c64892b66..138a2b66f620 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -486,11 +486,13 @@ void pci_aer_init(struct pci_dev *dev);
 void pci_aer_exit(struct pci_dev *dev);
 extern const struct attribute_group aer_stats_attr_group;
 void pci_aer_clear_fatal_status(struct pci_dev *dev);
+void pci_aer_clear_device_status(struct pci_dev *dev);
 #else
 static inline void pci_no_aer(void) { }
 static inline int pci_aer_init(struct pci_dev *d) { return -ENODEV; }
 static inline void pci_aer_exit(struct pci_dev *d) { }
 static inline void pci_aer_clear_fatal_status(struct pci_dev *dev) { }
+static inline void pci_aer_clear_device_status(struct pci_dev *dev) { }
 #endif
 
 #endif /* DRIVERS_PCI_H */
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 4411ada4a91c..2a40b24ae4e3 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -382,6 +382,14 @@ int pci_disable_pcie_error_reporting(struct pci_dev *dev)
 }
 EXPORT_SYMBOL_GPL(pci_disable_pcie_error_reporting);
 
+void pci_aer_clear_device_status(struct pci_dev *dev)
+{
+	u16 sta;
+
+	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &sta);
+	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, sta);
+}
+
 int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 {
 	int pos;
@@ -1532,12 +1540,7 @@ static pci_ers_result_t aer_root_reset(struct pci_dev *dev)
  */
 static void aer_error_resume(struct pci_dev *dev)
 {
-	u16 reg16;
-
-	/* Clean up Root device status */
-	pcie_capability_read_word(dev, PCI_EXP_DEVSTA, &reg16);
-	pcie_capability_write_word(dev, PCI_EXP_DEVSTA, reg16);
-
+	pci_aer_clear_device_status(dev);
 	pci_cleanup_aer_uncorrect_error_status(dev);
 }
 
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 638eda5c1d79..fdbcc555860d 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -252,6 +252,7 @@ static pci_ers_result_t broadcast_error_message(struct pci_dev *dev,
 			dev->error_state = state;
 		pci_walk_bus(dev->subordinate, cb, &result_data);
 		if (cb == report_resume) {
+			pci_aer_clear_device_status(dev);
 			pci_cleanup_aer_uncorrect_error_status(dev);
 			dev->error_state = pci_channel_io_normal;
 		}
@@ -312,6 +313,7 @@ void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service)
 		 * of the bridge and clear the error status of the bridge.
 		 */
 		pci_aer_clear_fatal_status(dev);
+		pci_aer_clear_device_status(dev);
 	}
 
 	if (result == PCI_ERS_RESULT_RECOVERED) {
-- 
cgit v1.2.3


From 10d790d99d3b42ec07d54178b291708f14af886d Mon Sep 17 00:00:00 2001
From: Oza Pawandeep <poza@codeaurora.org>
Date: Thu, 19 Jul 2018 17:58:09 -0500
Subject: PCI/AER: Clear device status bits during ERR_COR handling

In case of correctable error, the Correctable Error Detected bit in the
Device Status register is set.  Clear it after handling the error.

Signed-off-by: Oza Pawandeep <poza@codeaurora.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aer.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 2a40b24ae4e3..2b344c9e2d46 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -1001,6 +1001,7 @@ static void handle_error_source(struct pci_dev *dev, struct aer_err_info *info)
 		if (pos)
 			pci_write_config_dword(dev, pos + PCI_ERR_COR_STATUS,
 					info->status);
+		pci_aer_clear_device_status(dev);
 	} else if (info->severity == AER_NONFATAL)
 		pcie_do_nonfatal_recovery(dev);
 	else if (info->severity == AER_FATAL)
-- 
cgit v1.2.3


From 89e1f5cb1ecc1cd509a196f4e79d12a1e39410b6 Mon Sep 17 00:00:00 2001
From: Oza Pawandeep <poza@codeaurora.org>
Date: Thu, 19 Jul 2018 17:58:10 -0500
Subject: PCI/portdrv: Remove pcie_portdrv_err_handler.slot_reset

The pci_error_handlers.slot_reset() callback is only used for non-bridge
devices (see broadcast_error_message()).  Since portdrv only binds to
bridges, we don't need pcie_portdrv_slot_reset(), so remove it.

Signed-off-by: Oza Pawandeep <poza@codeaurora.org>
[bhelgaas: changelog, remove pcie_portdrv_slot_reset() completely]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/portdrv_pci.c | 25 -------------------------
 1 file changed, 25 deletions(-)

diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 973f1b80a038..b78840f54a9b 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -42,17 +42,6 @@ __setup("pcie_ports=", pcie_port_setup);
 
 /* global data */
 
-static int pcie_portdrv_restore_config(struct pci_dev *dev)
-{
-	int retval;
-
-	retval = pci_enable_device(dev);
-	if (retval)
-		return retval;
-	pci_set_master(dev);
-	return 0;
-}
-
 #ifdef CONFIG_PM
 static int pcie_port_runtime_suspend(struct device *dev)
 {
@@ -160,19 +149,6 @@ static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev)
 	return PCI_ERS_RESULT_RECOVERED;
 }
 
-static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev)
-{
-	/* If fatal, restore cfg space for possible link reset at upstream */
-	if (dev->error_state == pci_channel_io_frozen) {
-		dev->state_saved = true;
-		pci_restore_state(dev);
-		pcie_portdrv_restore_config(dev);
-		pci_enable_pcie_error_reporting(dev);
-	}
-
-	return PCI_ERS_RESULT_RECOVERED;
-}
-
 static int resume_iter(struct device *device, void *data)
 {
 	struct pcie_device *pcie_device;
@@ -208,7 +184,6 @@ static const struct pci_device_id port_pci_ids[] = { {
 static const struct pci_error_handlers pcie_portdrv_err_handler = {
 	.error_detected = pcie_portdrv_error_detected,
 	.mmio_enabled = pcie_portdrv_mmio_enabled,
-	.slot_reset = pcie_portdrv_slot_reset,
 	.resume = pcie_portdrv_err_resume,
 };
 
-- 
cgit v1.2.3


From 77754cfa09a6c528c38cbca9ee4cc4f7cf6ad6f2 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Fri, 20 Jul 2018 18:22:22 +0200
Subject: perf/core: Make sure the ring-buffer is mapped in all page-tables

The ring-buffer is accessed in the NMI handler, so it's better to avoid
faulting on it. Sync the vmalloc range with all page-tables in system to
make sure everyone has it mapped.

This fixes a WARN_ON_ONCE() that can be triggered with PTI enabled on
x86-32:

  WARNING: CPU: 4 PID: 0 at arch/x86/mm/fault.c:320 vmalloc_fault+0x220/0x230

This triggers because with PTI enabled on an PAE kernel the PMDs are no
longer shared between the page-tables, so the vmalloc changes do not
propagate automatically.

Note: Andy said rightfully that we should try to fix the vmalloc code for
that case, but that's not a hot fix for the issue at hand.

Fixes: 7757d607c6b3 ("x86/pti: Allow CONFIG_PAGE_TABLE_ISOLATION for x86_32")
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1532103744-31902-2-git-send-email-joro@8bytes.org
---
 kernel/events/ring_buffer.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 5d3cf407e374..df2d8cf0072c 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -814,6 +814,13 @@ static void rb_free_work(struct work_struct *work)
 
 	vfree(base);
 	kfree(rb);
+
+	/*
+	 * FIXME: PAE workaround for vmalloc_fault(): Make sure buffer is
+	 * unmapped in all page-tables.
+	 */
+	if (IS_ENABLED(CONFIG_X86_PAE))
+		vmalloc_sync_all();
 }
 
 void rb_free(struct ring_buffer *rb)
@@ -840,6 +847,15 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	if (!all_buf)
 		goto fail_all_buf;
 
+	/*
+	 * FIXME: PAE workaround for vmalloc_fault(): The buffer is
+	 * accessed in NMI handlers, make sure it is mapped in all
+	 * page-tables in the system so that we don't fault on the range in
+	 * an NMI handler.
+	 */
+	if (IS_ENABLED(CONFIG_X86_PAE))
+		vmalloc_sync_all();
+
 	rb->user_page = all_buf;
 	rb->data_pages[0] = all_buf + PAGE_SIZE;
 	if (nr_pages) {
-- 
cgit v1.2.3


From d5e84c21dbf5ea458897f88346dc979909eed913 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Fri, 20 Jul 2018 18:22:23 +0200
Subject: x86/entry/32: Check for VM86 mode in slow-path check

The SWITCH_TO_KERNEL_STACK macro only checks for CPL == 0 to go down the
slow and paranoid entry path. The problem is that this check also returns
true when coming from VM86 mode. This is not a problem by itself, as the
paranoid path handles VM86 stack-frames just fine, but it is not necessary
as the normal code path handles VM86 mode as well (and faster).

Extend the check to include VM86 mode. This also makes an optimization of
the paranoid path possible.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1532103744-31902-3-git-send-email-joro@8bytes.org
---
 arch/x86/entry/entry_32.S | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 010cdb41e3c7..2767c625a52c 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -414,8 +414,16 @@
 	andl	$(0x0000ffff), PT_CS(%esp)
 
 	/* Special case - entry from kernel mode via entry stack */
-	testl	$SEGMENT_RPL_MASK, PT_CS(%esp)
-	jz	.Lentry_from_kernel_\@
+#ifdef CONFIG_VM86
+	movl	PT_EFLAGS(%esp), %ecx		# mix EFLAGS and CS
+	movb	PT_CS(%esp), %cl
+	andl	$(X86_EFLAGS_VM | SEGMENT_RPL_MASK), %ecx
+#else
+	movl	PT_CS(%esp), %ecx
+	andl	$SEGMENT_RPL_MASK, %ecx
+#endif
+	cmpl	$USER_RPL, %ecx
+	jb	.Lentry_from_kernel_\@
 
 	/* Bytes to copy */
 	movl	$PTREGS_SIZE, %ecx
-- 
cgit v1.2.3


From bb81955fd4a49fffdd86d50afd0c1f2eea044c05 Mon Sep 17 00:00:00 2001
From: Dirk Gouders <dirk@gouders.net>
Date: Wed, 18 Jul 2018 11:13:36 +0200
Subject: kbuild: if_changed: document single use per target limitation

Users of if_changed could easily feel invited to use it to divide a
recipe into parts like:

a: prereq FORCE
	$(call if_changed,do_a)
	$(call if_changed,do_b)

But this is problematic, because if_changed should not be used more
than once per target: in the above example, if_changed stores the
command-line of the given command in .a.cmd and when a is up-to-date
with respect to prereq, the file .a.cmd contains the command-line for
the last command executed, i.e. do_b.

When the recipe is then executed again, without any change of
prerequisites, the command-line check for do_a will fail, do_a will be
executed and stored in .a.cmd.  The next check, however, will still see
the old content (the file isn't re-read) and if_changed will skip
do_b, because the command-line test will not recognize a change.  On
the next execution of the recipe the roles will flip: do_a is OK but
do_b not and it will be executed.  And so on...

Signed-off-by: Dirk Gouders <dirk@gouders.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/kbuild/makefiles.txt | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/kbuild/makefiles.txt b/Documentation/kbuild/makefiles.txt
index 63655c1a3ad6..766355b1d221 100644
--- a/Documentation/kbuild/makefiles.txt
+++ b/Documentation/kbuild/makefiles.txt
@@ -1105,6 +1105,12 @@ When kbuild executes, the following steps are followed (roughly):
 		target: source(s) FORCE
 	#WRONG!#	$(call if_changed, ld/objcopy/gzip/...)
 
+        Note: if_changed should not be used more than once per target.
+              It stores the executed command in a corresponding .cmd
+        file and multiple calls would result in overwrites and
+        unwanted results when the target is up to date and only the
+        tests on changed commands trigger execution of commands.
+
     ld
 	Link target. Often, LDFLAGS_$@ is used to set specific options to ld.
 
-- 
cgit v1.2.3


From eef5ba1aa148ca5e6deb1e0aa1de797fa4e12cb7 Mon Sep 17 00:00:00 2001
From: Peter Rosin <peda@axentia.se>
Date: Wed, 20 Jun 2018 10:51:53 +0200
Subject: i2c: smbus: add unlocked __i2c_smbus_xfer variant

Removes all locking from i2c_smbus_xfer and renames it to __i2c_smbus_xfer,
then adds a new i2c_smbus_xfer function that simply grabs the lock while
calling the unlocked variant.

This is not perfectly equivalent, since i2c_smbus_xfer was callable from
atomic/irq context if you happened to end up emulating SMBus with an I2C
transfer, and that is no longer the case with this patch. It is unknown
(to me) if anything depends on that quirk, but it seems fragile enough to
simply break those cases and require them to call i2c_transfer directly
instead.

While at it, for consistency rename the 2nd to last argument (size) of
the i2c_smbus_xfer declaration to protocol and remove the surplus extern
marker.

Signed-off-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
---
 drivers/i2c/i2c-core-smbus.c | 28 ++++++++++++++++++++--------
 include/linux/i2c.h          | 11 ++++++++---
 2 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/drivers/i2c/i2c-core-smbus.c b/drivers/i2c/i2c-core-smbus.c
index 51970bae3c4a..9cd66cabb84f 100644
--- a/drivers/i2c/i2c-core-smbus.c
+++ b/drivers/i2c/i2c-core-smbus.c
@@ -463,7 +463,7 @@ static s32 i2c_smbus_xfer_emulated(struct i2c_adapter *adapter, u16 addr,
 			msg[num-1].len++;
 	}
 
-	status = i2c_transfer(adapter, msg, num);
+	status = __i2c_transfer(adapter, msg, num);
 	if (status < 0)
 		goto cleanup;
 	if (status != num) {
@@ -524,9 +524,24 @@ cleanup:
  * This executes an SMBus protocol operation, and returns a negative
  * errno code else zero on success.
  */
-s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
-		   char read_write, u8 command, int protocol,
-		   union i2c_smbus_data *data)
+s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		   unsigned short flags, char read_write,
+		   u8 command, int protocol, union i2c_smbus_data *data)
+{
+	s32 res;
+
+	i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
+	res = __i2c_smbus_xfer(adapter, addr, flags, read_write,
+			       command, protocol, data);
+	i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
+
+	return res;
+}
+EXPORT_SYMBOL(i2c_smbus_xfer);
+
+s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		     unsigned short flags, char read_write,
+		     u8 command, int protocol, union i2c_smbus_data *data)
 {
 	unsigned long orig_jiffies;
 	int try;
@@ -543,8 +558,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
 	flags &= I2C_M_TEN | I2C_CLIENT_PEC | I2C_CLIENT_SCCB;
 
 	if (adapter->algo->smbus_xfer) {
-		i2c_lock_bus(adapter, I2C_LOCK_SEGMENT);
-
 		/* Retry automatically on arbitration loss */
 		orig_jiffies = jiffies;
 		for (res = 0, try = 0; try <= adapter->retries; try++) {
@@ -557,7 +570,6 @@ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags,
 				       orig_jiffies + adapter->timeout))
 				break;
 		}
-		i2c_unlock_bus(adapter, I2C_LOCK_SEGMENT);
 
 		if (res != -EOPNOTSUPP || !adapter->algo->master_xfer)
 			goto trace;
@@ -579,7 +591,7 @@ trace:
 
 	return res;
 }
-EXPORT_SYMBOL(i2c_smbus_xfer);
+EXPORT_SYMBOL(__i2c_smbus_xfer);
 
 /**
  * i2c_smbus_read_i2c_block_data_or_emulated - read block or emulate
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 254cd34eeae2..465afb092fa7 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -140,9 +140,14 @@ extern int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs,
    and probably just as fast.
    Note that we use i2c_adapter here, because you do not need a specific
    smbus adapter to call this function. */
-extern s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
-			  unsigned short flags, char read_write, u8 command,
-			  int size, union i2c_smbus_data *data);
+s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		   unsigned short flags, char read_write, u8 command,
+		   int protocol, union i2c_smbus_data *data);
+
+/* Unlocked flavor */
+s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr,
+		     unsigned short flags, char read_write, u8 command,
+		     int protocol, union i2c_smbus_data *data);
 
 /* Now follow the 'nice' access routines. These also document the calling
    conventions of i2c_smbus_xfer. */
-- 
cgit v1.2.3


From 788654285da76dc853ebd25a5ecb4043de22d0e5 Mon Sep 17 00:00:00 2001
From: Serge Semin <fancer.lancer@gmail.com>
Date: Fri, 20 Jul 2018 23:14:27 +0300
Subject: mips: mm: Discard ioremap_cacheable_cow() method

This macro substitution is the shortcut to map cacheable IO memory
with coherent and write-back attributes. Since it is entirely unused
by kernel, lets just remove it.

Signed-off-by: Serge Semin <fancer.lancer@gmail.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Suggested-by: Christoph Hellwig <hch@infradead.org>
Patchwork: https://patchwork.linux-mips.org/patch/19937/
CC: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Sinan Kaya <okaya@codeaurora.org>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: Sergey.Semin@t-platforms.ru
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/include/asm/io.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index f613d1df66c0..cd170d920d55 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -300,13 +300,6 @@ static inline void __iomem * __ioremap_mode(phys_addr_t offset, unsigned long si
 #define ioremap_wc(offset, size)					\
 	__ioremap_mode((offset), (size), boot_cpu_data.writecombine)
 
-/*
- * This is a MIPS specific ioremap variant. ioremap_cacheable_cow
- * requests a cachable mapping with CWB attribute enabled.
- */
-#define ioremap_cacheable_cow(offset, size)				\
-	__ioremap_mode((offset), (size), _CACHE_CACHABLE_COW)
-
 static inline void iounmap(const volatile void __iomem *addr)
 {
 	if (plat_iounmap(addr))
-- 
cgit v1.2.3


From 7c4ec749a3bd89237d7195ccd621bf5d4124d6b5 Mon Sep 17 00:00:00 2001
From: "David S. Miller" <davem@davemloft.net>
Date: Fri, 20 Jul 2018 23:37:55 -0700
Subject: net: Init backlog NAPI's gro_hash.

Based upon a patch by Sean Tranchetti.

Fixes: d4546c2509b1 ("net: Convert GRO SKB handling to list_head.")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 18 ++++++++++++------
 1 file changed, 12 insertions(+), 6 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 4f8b92d81d10..87c42c8249ae 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6115,19 +6115,24 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
-		    int (*poll)(struct napi_struct *, int), int weight)
+static void init_gro_hash(struct napi_struct *napi)
 {
 	int i;
 
-	INIT_LIST_HEAD(&napi->poll_list);
-	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
-	napi->timer.function = napi_watchdog;
-	napi->gro_bitmask = 0;
 	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
 		INIT_LIST_HEAD(&napi->gro_hash[i].list);
 		napi->gro_hash[i].count = 0;
 	}
+	napi->gro_bitmask = 0;
+}
+
+void netif_napi_add(struct net_device *dev, struct napi_struct *napi,
+		    int (*poll)(struct napi_struct *, int), int weight)
+{
+	INIT_LIST_HEAD(&napi->poll_list);
+	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
+	napi->timer.function = napi_watchdog;
+	init_gro_hash(napi);
 	napi->skb = NULL;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
@@ -9554,6 +9559,7 @@ static int __init net_dev_init(void)
 		sd->cpu = i;
 #endif
 
+		init_gro_hash(&sd->backlog);
 		sd->backlog.poll = process_backlog;
 		sd->backlog.weight = weight_p;
 	}
-- 
cgit v1.2.3


From 488dee96bb62f0b3d9e678cf42574034d5b033a5 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 20 Jul 2018 21:56:47 +0000
Subject: kernfs: allow creating kernfs objects with arbitrary uid/gid

This change allows creating kernfs files and directories with arbitrary
uid/gid instead of always using GLOBAL_ROOT_UID/GID by extending
kernfs_create_dir_ns() and kernfs_create_file_ns() with uid/gid arguments.
The "simple" kernfs_create_file() and kernfs_create_dir() are left alone
and always create objects belonging to the global root.

When creating symlinks ownership (uid/gid) is taken from the target kernfs
object.

Co-Developed-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c |  4 +++-
 fs/kernfs/dir.c                          | 29 ++++++++++++++++++++++++++---
 fs/kernfs/file.c                         |  8 ++++++--
 fs/kernfs/inode.c                        |  2 +-
 fs/kernfs/kernfs-internal.h              |  2 ++
 fs/kernfs/symlink.c                      | 11 ++++++++++-
 fs/sysfs/dir.c                           |  4 +++-
 fs/sysfs/file.c                          |  5 +++--
 include/linux/kernfs.h                   | 28 +++++++++++++++++++---------
 kernel/cgroup/cgroup.c                   |  4 +++-
 10 files changed, 76 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 749856a2e736..9af1a21265d3 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -146,6 +146,7 @@ static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
 	int ret;
 
 	kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
+				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
 				  0, rft->kf_ops, rft, NULL, NULL);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
@@ -1503,7 +1504,8 @@ static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
 	struct kernfs_node *kn;
 	int ret = 0;
 
-	kn = __kernfs_create_file(parent_kn, name, 0444, 0,
+	kn = __kernfs_create_file(parent_kn, name, 0444,
+				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
 				  &kf_mondata_ops, priv, NULL, NULL);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index d66cc0777303..4ca0b5c18192 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -619,6 +619,7 @@ struct kernfs_node *kernfs_node_from_dentry(struct dentry *dentry)
 
 static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 					     const char *name, umode_t mode,
+					     kuid_t uid, kgid_t gid,
 					     unsigned flags)
 {
 	struct kernfs_node *kn;
@@ -661,8 +662,22 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 	kn->mode = mode;
 	kn->flags = flags;
 
+	if (!uid_eq(uid, GLOBAL_ROOT_UID) || !gid_eq(gid, GLOBAL_ROOT_GID)) {
+		struct iattr iattr = {
+			.ia_valid = ATTR_UID | ATTR_GID,
+			.ia_uid = uid,
+			.ia_gid = gid,
+		};
+
+		ret = __kernfs_setattr(kn, &iattr);
+		if (ret < 0)
+			goto err_out3;
+	}
+
 	return kn;
 
+ err_out3:
+	idr_remove(&root->ino_idr, kn->id.ino);
  err_out2:
 	kmem_cache_free(kernfs_node_cache, kn);
  err_out1:
@@ -672,11 +687,13 @@ static struct kernfs_node *__kernfs_new_node(struct kernfs_root *root,
 
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
+				    kuid_t uid, kgid_t gid,
 				    unsigned flags)
 {
 	struct kernfs_node *kn;
 
-	kn = __kernfs_new_node(kernfs_root(parent), name, mode, flags);
+	kn = __kernfs_new_node(kernfs_root(parent),
+			       name, mode, uid, gid, flags);
 	if (kn) {
 		kernfs_get(parent);
 		kn->parent = parent;
@@ -946,6 +963,7 @@ struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 	root->next_generation = 1;
 
 	kn = __kernfs_new_node(root, "", S_IFDIR | S_IRUGO | S_IXUGO,
+			       GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
 			       KERNFS_DIR);
 	if (!kn) {
 		idr_destroy(&root->ino_idr);
@@ -984,6 +1002,8 @@ void kernfs_destroy_root(struct kernfs_root *root)
  * @parent: parent in which to create a new directory
  * @name: name of the new directory
  * @mode: mode of the new directory
+ * @uid: uid of the new directory
+ * @gid: gid of the new directory
  * @priv: opaque data associated with the new directory
  * @ns: optional namespace tag of the directory
  *
@@ -991,13 +1011,15 @@ void kernfs_destroy_root(struct kernfs_root *root)
  */
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
+					 kuid_t uid, kgid_t gid,
 					 void *priv, const void *ns)
 {
 	struct kernfs_node *kn;
 	int rc;
 
 	/* allocate */
-	kn = kernfs_new_node(parent, name, mode | S_IFDIR, KERNFS_DIR);
+	kn = kernfs_new_node(parent, name, mode | S_IFDIR,
+			     uid, gid, KERNFS_DIR);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 
@@ -1028,7 +1050,8 @@ struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 	int rc;
 
 	/* allocate */
-	kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR, KERNFS_DIR);
+	kn = kernfs_new_node(parent, name, S_IRUGO|S_IXUGO|S_IFDIR,
+			     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, KERNFS_DIR);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 2015d8c45e4a..dbf5bc250bfd 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -965,6 +965,8 @@ const struct file_operations kernfs_file_fops = {
  * @parent: directory to create the file in
  * @name: name of the file
  * @mode: mode of the file
+ * @uid: uid of the file
+ * @gid: gid of the file
  * @size: size of the file
  * @ops: kernfs operations for the file
  * @priv: private data for the file
@@ -975,7 +977,8 @@ const struct file_operations kernfs_file_fops = {
  */
 struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 					 const char *name,
-					 umode_t mode, loff_t size,
+					 umode_t mode, kuid_t uid, kgid_t gid,
+					 loff_t size,
 					 const struct kernfs_ops *ops,
 					 void *priv, const void *ns,
 					 struct lock_class_key *key)
@@ -986,7 +989,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 
 	flags = KERNFS_FILE;
 
-	kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, flags);
+	kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG,
+			     uid, gid, flags);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index 3d73fe9d56e2..80cebcd94c90 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -63,7 +63,7 @@ out_unlock:
 	return ret;
 }
 
-static int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
+int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr)
 {
 	struct kernfs_iattrs *attrs;
 	struct iattr *iattrs;
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index 0f260dcca177..3d83b114bb08 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -90,6 +90,7 @@ int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr);
 int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
 		       u32 request_mask, unsigned int query_flags);
 ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
+int __kernfs_setattr(struct kernfs_node *kn, const struct iattr *iattr);
 
 /*
  * dir.c
@@ -104,6 +105,7 @@ void kernfs_put_active(struct kernfs_node *kn);
 int kernfs_add_one(struct kernfs_node *kn);
 struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
 				    const char *name, umode_t mode,
+				    kuid_t uid, kgid_t gid,
 				    unsigned flags);
 struct kernfs_node *kernfs_find_and_get_node_by_ino(struct kernfs_root *root,
 						    unsigned int ino);
diff --git a/fs/kernfs/symlink.c b/fs/kernfs/symlink.c
index 08ccabd7047f..5ffed48f3d0e 100644
--- a/fs/kernfs/symlink.c
+++ b/fs/kernfs/symlink.c
@@ -21,6 +21,7 @@
  * @target: target node for the symlink to point to
  *
  * Returns the created node on success, ERR_PTR() value on error.
+ * Ownership of the link matches ownership of the target.
  */
 struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 				       const char *name,
@@ -28,8 +29,16 @@ struct kernfs_node *kernfs_create_link(struct kernfs_node *parent,
 {
 	struct kernfs_node *kn;
 	int error;
+	kuid_t uid = GLOBAL_ROOT_UID;
+	kgid_t gid = GLOBAL_ROOT_GID;
 
-	kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, KERNFS_LINK);
+	if (target->iattr) {
+		uid = target->iattr->ia_iattr.ia_uid;
+		gid = target->iattr->ia_iattr.ia_gid;
+	}
+
+	kn = kernfs_new_node(parent, name, S_IFLNK|S_IRWXUGO, uid, gid,
+			     KERNFS_LINK);
 	if (!kn)
 		return ERR_PTR(-ENOMEM);
 
diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index 58eba92a0e41..e39b884f0867 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -52,7 +52,9 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 		return -ENOENT;
 
 	kn = kernfs_create_dir_ns(parent, kobject_name(kobj),
-				  S_IRWXU | S_IRUGO | S_IXUGO, kobj, ns);
+				  S_IRWXU | S_IRUGO | S_IXUGO,
+				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				  kobj, ns);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
 			sysfs_warn_dup(parent, kobject_name(kobj));
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 5c13f29bfcdb..513fa691ecbd 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -302,8 +302,9 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 	if (!attr->ignore_lockdep)
 		key = attr->key ?: (struct lock_class_key *)&attr->skey;
 #endif
-	kn = __kernfs_create_file(parent, attr->name, mode & 0777, size, ops,
-				  (void *)attr, ns, key);
+	kn = __kernfs_create_file(parent, attr->name,
+				  mode & 0777, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				  size, ops, (void *)attr, ns, key);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
 			sysfs_warn_dup(parent, attr->name);
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index ab25c8b6d9e3..814643f7ee52 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -15,6 +15,7 @@
 #include <linux/lockdep.h>
 #include <linux/rbtree.h>
 #include <linux/atomic.h>
+#include <linux/uidgid.h>
 #include <linux/wait.h>
 
 struct file;
@@ -325,12 +326,14 @@ void kernfs_destroy_root(struct kernfs_root *root);
 
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
+					 kuid_t uid, kgid_t gid,
 					 void *priv, const void *ns);
 struct kernfs_node *kernfs_create_empty_dir(struct kernfs_node *parent,
 					    const char *name);
 struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
-					 const char *name,
-					 umode_t mode, loff_t size,
+					 const char *name, umode_t mode,
+					 kuid_t uid, kgid_t gid,
+					 loff_t size,
 					 const struct kernfs_ops *ops,
 					 void *priv, const void *ns,
 					 struct lock_class_key *key);
@@ -415,12 +418,14 @@ static inline void kernfs_destroy_root(struct kernfs_root *root) { }
 
 static inline struct kernfs_node *
 kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
-		     umode_t mode, void *priv, const void *ns)
+		     umode_t mode, kuid_t uid, kgid_t gid,
+		     void *priv, const void *ns)
 { return ERR_PTR(-ENOSYS); }
 
 static inline struct kernfs_node *
 __kernfs_create_file(struct kernfs_node *parent, const char *name,
-		     umode_t mode, loff_t size, const struct kernfs_ops *ops,
+		     umode_t mode, kuid_t uid, kgid_t gid,
+		     loff_t size, const struct kernfs_ops *ops,
 		     void *priv, const void *ns, struct lock_class_key *key)
 { return ERR_PTR(-ENOSYS); }
 
@@ -498,12 +503,15 @@ static inline struct kernfs_node *
 kernfs_create_dir(struct kernfs_node *parent, const char *name, umode_t mode,
 		  void *priv)
 {
-	return kernfs_create_dir_ns(parent, name, mode, priv, NULL);
+	return kernfs_create_dir_ns(parent, name, mode,
+				    GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				    priv, NULL);
 }
 
 static inline struct kernfs_node *
 kernfs_create_file_ns(struct kernfs_node *parent, const char *name,
-		      umode_t mode, loff_t size, const struct kernfs_ops *ops,
+		      umode_t mode, kuid_t uid, kgid_t gid,
+		      loff_t size, const struct kernfs_ops *ops,
 		      void *priv, const void *ns)
 {
 	struct lock_class_key *key = NULL;
@@ -511,15 +519,17 @@ kernfs_create_file_ns(struct kernfs_node *parent, const char *name,
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	key = (struct lock_class_key *)&ops->lockdep_key;
 #endif
-	return __kernfs_create_file(parent, name, mode, size, ops, priv, ns,
-				    key);
+	return __kernfs_create_file(parent, name, mode, uid, gid,
+				    size, ops, priv, ns, key);
 }
 
 static inline struct kernfs_node *
 kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode,
 		   loff_t size, const struct kernfs_ops *ops, void *priv)
 {
-	return kernfs_create_file_ns(parent, name, mode, size, ops, priv, NULL);
+	return kernfs_create_file_ns(parent, name, mode,
+				     GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				     size, ops, priv, NULL);
 }
 
 static inline int kernfs_remove_by_name(struct kernfs_node *parent,
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index 077370bf8964..35cf3d71f8aa 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -3557,7 +3557,9 @@ static int cgroup_add_file(struct cgroup_subsys_state *css, struct cgroup *cgrp,
 	key = &cft->lockdep_key;
 #endif
 	kn = __kernfs_create_file(cgrp->kn, cgroup_file_name(cgrp, cft, name),
-				  cgroup_file_mode(cft), 0, cft->kf_ops, cft,
+				  cgroup_file_mode(cft),
+				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				  0, cft->kf_ops, cft,
 				  NULL, key);
 	if (IS_ERR(kn))
 		return PTR_ERR(kn);
-- 
cgit v1.2.3


From 5f81880d5204ee2388fd9a75bb850ccd526885b7 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 20 Jul 2018 21:56:48 +0000
Subject: sysfs, kobject: allow creating kobject belonging to arbitrary users

Normally kobjects and their sysfs representation belong to global root,
however it is not necessarily the case for objects in separate namespaces.
For example, objects in separate network namespace logically belong to the
container's root and not global root.

This change lays groundwork for allowing network namespace objects
ownership to be transferred to container's root user by defining
get_ownership() callback in ktype structure and using it in sysfs code to
retrieve desired uid/gid when creating sysfs objects for given kobject.

Co-Developed-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/sysfs/dir.c          |  7 +++++--
 fs/sysfs/file.c         | 32 ++++++++++++++++++++------------
 fs/sysfs/group.c        | 23 +++++++++++++++++------
 fs/sysfs/sysfs.h        |  5 ++---
 include/linux/kobject.h |  4 ++++
 lib/kobject.c           | 19 +++++++++++++++++++
 6 files changed, 67 insertions(+), 23 deletions(-)

diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c
index e39b884f0867..feeae8081c22 100644
--- a/fs/sysfs/dir.c
+++ b/fs/sysfs/dir.c
@@ -40,6 +40,8 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name)
 int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 {
 	struct kernfs_node *parent, *kn;
+	kuid_t uid;
+	kgid_t gid;
 
 	BUG_ON(!kobj);
 
@@ -51,9 +53,10 @@ int sysfs_create_dir_ns(struct kobject *kobj, const void *ns)
 	if (!parent)
 		return -ENOENT;
 
+	kobject_get_ownership(kobj, &uid, &gid);
+
 	kn = kernfs_create_dir_ns(parent, kobject_name(kobj),
-				  S_IRWXU | S_IRUGO | S_IXUGO,
-				  GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+				  S_IRWXU | S_IRUGO | S_IXUGO, uid, gid,
 				  kobj, ns);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 513fa691ecbd..fa46216523cf 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -245,7 +245,7 @@ static const struct kernfs_ops sysfs_bin_kfops_mmap = {
 
 int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 			   const struct attribute *attr, bool is_bin,
-			   umode_t mode, const void *ns)
+			   umode_t mode, kuid_t uid, kgid_t gid, const void *ns)
 {
 	struct lock_class_key *key = NULL;
 	const struct kernfs_ops *ops;
@@ -302,8 +302,8 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 	if (!attr->ignore_lockdep)
 		key = attr->key ?: (struct lock_class_key *)&attr->skey;
 #endif
-	kn = __kernfs_create_file(parent, attr->name,
-				  mode & 0777, GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
+
+	kn = __kernfs_create_file(parent, attr->name, mode & 0777, uid, gid,
 				  size, ops, (void *)attr, ns, key);
 	if (IS_ERR(kn)) {
 		if (PTR_ERR(kn) == -EEXIST)
@@ -313,12 +313,6 @@ int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 	return 0;
 }
 
-int sysfs_add_file(struct kernfs_node *parent, const struct attribute *attr,
-		   bool is_bin)
-{
-	return sysfs_add_file_mode_ns(parent, attr, is_bin, attr->mode, NULL);
-}
-
 /**
  * sysfs_create_file_ns - create an attribute file for an object with custom ns
  * @kobj: object we're creating for
@@ -328,9 +322,14 @@ int sysfs_add_file(struct kernfs_node *parent, const struct attribute *attr,
 int sysfs_create_file_ns(struct kobject *kobj, const struct attribute *attr,
 			 const void *ns)
 {
+	kuid_t uid;
+	kgid_t gid;
+
 	BUG_ON(!kobj || !kobj->sd || !attr);
 
-	return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode, ns);
+	kobject_get_ownership(kobj, &uid, &gid);
+	return sysfs_add_file_mode_ns(kobj->sd, attr, false, attr->mode,
+				      uid, gid, ns);
 
 }
 EXPORT_SYMBOL_GPL(sysfs_create_file_ns);
@@ -359,6 +358,8 @@ int sysfs_add_file_to_group(struct kobject *kobj,
 		const struct attribute *attr, const char *group)
 {
 	struct kernfs_node *parent;
+	kuid_t uid;
+	kgid_t gid;
 	int error;
 
 	if (group) {
@@ -371,7 +372,9 @@ int sysfs_add_file_to_group(struct kobject *kobj,
 	if (!parent)
 		return -ENOENT;
 
-	error = sysfs_add_file(parent, attr, false);
+	kobject_get_ownership(kobj, &uid, &gid);
+	error = sysfs_add_file_mode_ns(kobj->sd, attr, false,
+				       attr->mode, uid, gid, NULL);
 	kernfs_put(parent);
 
 	return error;
@@ -487,9 +490,14 @@ EXPORT_SYMBOL_GPL(sysfs_remove_file_from_group);
 int sysfs_create_bin_file(struct kobject *kobj,
 			  const struct bin_attribute *attr)
 {
+	kuid_t uid;
+	kgid_t gid;
+
 	BUG_ON(!kobj || !kobj->sd || !attr);
 
-	return sysfs_add_file(kobj->sd, &attr->attr, true);
+	kobject_get_ownership(kobj, &uid, &gid);
+	return sysfs_add_file_mode_ns(kobj->sd, &attr->attr, true,
+				      attr->attr.mode, uid, gid, NULL);
 }
 EXPORT_SYMBOL_GPL(sysfs_create_bin_file);
 
diff --git a/fs/sysfs/group.c b/fs/sysfs/group.c
index 4802ec0e1e3a..c7a716c4acc9 100644
--- a/fs/sysfs/group.c
+++ b/fs/sysfs/group.c
@@ -31,6 +31,7 @@ static void remove_files(struct kernfs_node *parent,
 }
 
 static int create_files(struct kernfs_node *parent, struct kobject *kobj,
+			kuid_t uid, kgid_t gid,
 			const struct attribute_group *grp, int update)
 {
 	struct attribute *const *attr;
@@ -60,7 +61,7 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
 
 			mode &= SYSFS_PREALLOC | 0664;
 			error = sysfs_add_file_mode_ns(parent, *attr, false,
-						       mode, NULL);
+						       mode, uid, gid, NULL);
 			if (unlikely(error))
 				break;
 		}
@@ -90,7 +91,8 @@ static int create_files(struct kernfs_node *parent, struct kobject *kobj,
 			mode &= SYSFS_PREALLOC | 0664;
 			error = sysfs_add_file_mode_ns(parent,
 					&(*bin_attr)->attr, true,
-					mode, NULL);
+					mode,
+					uid, gid, NULL);
 			if (error)
 				break;
 		}
@@ -106,6 +108,8 @@ static int internal_create_group(struct kobject *kobj, int update,
 				 const struct attribute_group *grp)
 {
 	struct kernfs_node *kn;
+	kuid_t uid;
+	kgid_t gid;
 	int error;
 
 	BUG_ON(!kobj || (!update && !kobj->sd));
@@ -118,9 +122,11 @@ static int internal_create_group(struct kobject *kobj, int update,
 			kobj->name, grp->name ?: "");
 		return -EINVAL;
 	}
+	kobject_get_ownership(kobj, &uid, &gid);
 	if (grp->name) {
-		kn = kernfs_create_dir(kobj->sd, grp->name,
-				       S_IRWXU | S_IRUGO | S_IXUGO, kobj);
+		kn = kernfs_create_dir_ns(kobj->sd, grp->name,
+					  S_IRWXU | S_IRUGO | S_IXUGO,
+					  uid, gid, kobj, NULL);
 		if (IS_ERR(kn)) {
 			if (PTR_ERR(kn) == -EEXIST)
 				sysfs_warn_dup(kobj->sd, grp->name);
@@ -129,7 +135,7 @@ static int internal_create_group(struct kobject *kobj, int update,
 	} else
 		kn = kobj->sd;
 	kernfs_get(kn);
-	error = create_files(kn, kobj, grp, update);
+	error = create_files(kn, kobj, uid, gid, grp, update);
 	if (error) {
 		if (grp->name)
 			kernfs_remove(kn);
@@ -281,6 +287,8 @@ int sysfs_merge_group(struct kobject *kobj,
 		       const struct attribute_group *grp)
 {
 	struct kernfs_node *parent;
+	kuid_t uid;
+	kgid_t gid;
 	int error = 0;
 	struct attribute *const *attr;
 	int i;
@@ -289,8 +297,11 @@ int sysfs_merge_group(struct kobject *kobj,
 	if (!parent)
 		return -ENOENT;
 
+	kobject_get_ownership(kobj, &uid, &gid);
+
 	for ((i = 0, attr = grp->attrs); *attr && !error; (++i, ++attr))
-		error = sysfs_add_file(parent, *attr, false);
+		error = sysfs_add_file_mode_ns(parent, *attr, false,
+					       (*attr)->mode, uid, gid, NULL);
 	if (error) {
 		while (--i >= 0)
 			kernfs_remove_by_name(parent, (*--attr)->name);
diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h
index d098e015fcc9..0050cc0c0236 100644
--- a/fs/sysfs/sysfs.h
+++ b/fs/sysfs/sysfs.h
@@ -27,11 +27,10 @@ void sysfs_warn_dup(struct kernfs_node *parent, const char *name);
 /*
  * file.c
  */
-int sysfs_add_file(struct kernfs_node *parent,
-		   const struct attribute *attr, bool is_bin);
 int sysfs_add_file_mode_ns(struct kernfs_node *parent,
 			   const struct attribute *attr, bool is_bin,
-			   umode_t amode, const void *ns);
+			   umode_t amode, kuid_t uid, kgid_t gid,
+			   const void *ns);
 
 /*
  * symlink.c
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index 7f6f93c3df9c..b49ff230beba 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -26,6 +26,7 @@
 #include <linux/wait.h>
 #include <linux/atomic.h>
 #include <linux/workqueue.h>
+#include <linux/uidgid.h>
 
 #define UEVENT_HELPER_PATH_LEN		256
 #define UEVENT_NUM_ENVP			32	/* number of env pointers */
@@ -114,6 +115,8 @@ extern struct kobject * __must_check kobject_get_unless_zero(
 extern void kobject_put(struct kobject *kobj);
 
 extern const void *kobject_namespace(struct kobject *kobj);
+extern void kobject_get_ownership(struct kobject *kobj,
+				  kuid_t *uid, kgid_t *gid);
 extern char *kobject_get_path(struct kobject *kobj, gfp_t flag);
 
 struct kobj_type {
@@ -122,6 +125,7 @@ struct kobj_type {
 	struct attribute **default_attrs;
 	const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj);
 	const void *(*namespace)(struct kobject *kobj);
+	void (*get_ownership)(struct kobject *kobj, kuid_t *uid, kgid_t *gid);
 };
 
 struct kobj_uevent_env {
diff --git a/lib/kobject.c b/lib/kobject.c
index 18989b5b3b56..f2dc1f756007 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -35,6 +35,25 @@ const void *kobject_namespace(struct kobject *kobj)
 	return kobj->ktype->namespace(kobj);
 }
 
+/**
+ * kobject_get_ownership - get sysfs ownership data for @kobj
+ * @kobj: kobject in question
+ * @uid: kernel user ID for sysfs objects
+ * @gid: kernel group ID for sysfs objects
+ *
+ * Returns initial uid/gid pair that should be used when creating sysfs
+ * representation of given kobject. Normally used to adjust ownership of
+ * objects in a container.
+ */
+void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid)
+{
+	*uid = GLOBAL_ROOT_UID;
+	*gid = GLOBAL_ROOT_GID;
+
+	if (kobj->ktype->get_ownership)
+		kobj->ktype->get_ownership(kobj, uid, gid);
+}
+
 /*
  * populate_dir - populate directory with attributes.
  * @kobj: object we're working on.
-- 
cgit v1.2.3


From d028b6f703209dbe96201b2714ff46625877128e Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 20 Jul 2018 21:56:49 +0000
Subject: kobject: kset_create_and_add() - fetch ownership info from parent

This change implements get_ownership() for ksets created with
kset_create_and_add() call by fetching ownership data from parent kobject.
This is done mostly for benefit of "queues" attribute of net devices so
that corresponding directory belongs to container's root instead of global
root for network devices in a container.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Reviewed-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 lib/kobject.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/lib/kobject.c b/lib/kobject.c
index f2dc1f756007..389829d3a1d1 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -887,9 +887,16 @@ static void kset_release(struct kobject *kobj)
 	kfree(kset);
 }
 
+void kset_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid)
+{
+	if (kobj->parent)
+		kobject_get_ownership(kobj->parent, uid, gid);
+}
+
 static struct kobj_type kset_ktype = {
 	.sysfs_ops	= &kobj_sysfs_ops,
-	.release = kset_release,
+	.release	= kset_release,
+	.get_ownership	= kset_get_ownership,
 };
 
 /**
-- 
cgit v1.2.3


From 9944e894c1266dc8515c82d1ff752d681215526b Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 20 Jul 2018 21:56:50 +0000
Subject: driver core: set up ownership of class devices in sysfs

Plumb in get_ownership() callback for devices belonging to a class so that
they can be created with uid/gid different from global root. This will
allow network devices in a container to belong to container's root and not
global root.

Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Reviewed-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/base/core.c    | 9 +++++++++
 include/linux/device.h | 5 +++++
 2 files changed, 14 insertions(+)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index df3e1a44707a..276c7e3f754c 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -866,10 +866,19 @@ static const void *device_namespace(struct kobject *kobj)
 	return ns;
 }
 
+static void device_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid)
+{
+	struct device *dev = kobj_to_dev(kobj);
+
+	if (dev->class && dev->class->get_ownership)
+		dev->class->get_ownership(dev, uid, gid);
+}
+
 static struct kobj_type device_ktype = {
 	.release	= device_release,
 	.sysfs_ops	= &dev_sysfs_ops,
 	.namespace	= device_namespace,
+	.get_ownership	= device_get_ownership,
 };
 
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69dbcd18..fe6ccb6dc119 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -384,6 +384,9 @@ int subsys_virtual_register(struct bus_type *subsys,
  * @shutdown_pre: Called at shut-down time before driver shutdown.
  * @ns_type:	Callbacks so sysfs can detemine namespaces.
  * @namespace:	Namespace of the device belongs to this class.
+ * @get_ownership: Allows class to specify uid/gid of the sysfs directories
+ *		for the devices belonging to the class. Usually tied to
+ *		device's namespace.
  * @pm:		The default device power management operations of this class.
  * @p:		The private data of the driver core, no one other than the
  *		driver core can touch this.
@@ -413,6 +416,8 @@ struct class {
 	const struct kobj_ns_type_operations *ns_type;
 	const void *(*namespace)(struct device *dev);
 
+	void (*get_ownership)(struct device *dev, kuid_t *uid, kgid_t *gid);
+
 	const struct dev_pm_ops *pm;
 
 	struct subsys_private *p;
-- 
cgit v1.2.3


From 3033fced2f689d4a870b3ba6a8a676db1261d262 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@canonical.com>
Date: Fri, 20 Jul 2018 21:56:51 +0000
Subject: net-sysfs: require net admin in the init ns for setting tx_maxrate

An upcoming change will allow container root to open some /sys/class/net
files for writing. The tx_maxrate attribute can result in changes
to actual hardware devices so err on the side of caution by requiring
CAP_NET_ADMIN in the init namespace in the corresponding attribute store
operation.

Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ffa1d18f2c2c..405c41ecb20b 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1087,6 +1087,9 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue,
 	int err, index = get_netdev_queue_index(queue);
 	u32 rate = 0;
 
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
 	err = kstrtou32(buf, 10, &rate);
 	if (err < 0)
 		return err;
-- 
cgit v1.2.3


From b0e37c0d8a6abed0cd1b611314a7ebf50b0a8ed4 Mon Sep 17 00:00:00 2001
From: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Date: Fri, 20 Jul 2018 21:56:52 +0000
Subject: net-sysfs: make sure objects belong to container's owner

When creating various objects in /sys/class/net/... make sure that they
belong to container's owner instead of global root (if they belong to a
container/namespace).

Co-Developed-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/net-sysfs.c | 47 ++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 405c41ecb20b..ada065fc685e 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -656,6 +656,24 @@ static const struct attribute_group wireless_group = {
 #define net_class_groups	NULL
 #endif /* CONFIG_SYSFS */
 
+static void net_ns_get_ownership(const struct net *net,
+				 kuid_t *uid, kgid_t *gid)
+{
+	if (net) {
+		kuid_t ns_root_uid = make_kuid(net->user_ns, 0);
+		kgid_t ns_root_gid = make_kgid(net->user_ns, 0);
+
+		if (uid_valid(ns_root_uid))
+			*uid = ns_root_uid;
+
+		if (gid_valid(ns_root_gid))
+			*gid = ns_root_gid;
+	} else {
+		*uid = GLOBAL_ROOT_UID;
+		*gid = GLOBAL_ROOT_GID;
+	}
+}
+
 #ifdef CONFIG_SYSFS
 #define to_rx_queue_attr(_attr) \
 	container_of(_attr, struct rx_queue_attribute, attr)
@@ -905,11 +923,20 @@ static const void *rx_queue_namespace(struct kobject *kobj)
 	return ns;
 }
 
+static void rx_queue_get_ownership(struct kobject *kobj,
+				   kuid_t *uid, kgid_t *gid)
+{
+	const struct net *net = rx_queue_namespace(kobj);
+
+	net_ns_get_ownership(net, uid, gid);
+}
+
 static struct kobj_type rx_queue_ktype __ro_after_init = {
 	.sysfs_ops = &rx_queue_sysfs_ops,
 	.release = rx_queue_release,
 	.default_attrs = rx_queue_default_attrs,
-	.namespace = rx_queue_namespace
+	.namespace = rx_queue_namespace,
+	.get_ownership = rx_queue_get_ownership,
 };
 
 static int rx_queue_add_kobject(struct net_device *dev, int index)
@@ -1431,11 +1458,20 @@ static const void *netdev_queue_namespace(struct kobject *kobj)
 	return ns;
 }
 
+static void netdev_queue_get_ownership(struct kobject *kobj,
+				       kuid_t *uid, kgid_t *gid)
+{
+	const struct net *net = netdev_queue_namespace(kobj);
+
+	net_ns_get_ownership(net, uid, gid);
+}
+
 static struct kobj_type netdev_queue_ktype __ro_after_init = {
 	.sysfs_ops = &netdev_queue_sysfs_ops,
 	.release = netdev_queue_release,
 	.default_attrs = netdev_queue_default_attrs,
 	.namespace = netdev_queue_namespace,
+	.get_ownership = netdev_queue_get_ownership,
 };
 
 static int netdev_queue_add_kobject(struct net_device *dev, int index)
@@ -1625,6 +1661,14 @@ static const void *net_namespace(struct device *d)
 	return dev_net(dev);
 }
 
+static void net_get_ownership(struct device *d, kuid_t *uid, kgid_t *gid)
+{
+	struct net_device *dev = to_net_dev(d);
+	const struct net *net = dev_net(dev);
+
+	net_ns_get_ownership(net, uid, gid);
+}
+
 static struct class net_class __ro_after_init = {
 	.name = "net",
 	.dev_release = netdev_release,
@@ -1632,6 +1676,7 @@ static struct class net_class __ro_after_init = {
 	.dev_uevent = netdev_uevent,
 	.ns_type = &net_ns_type_operations,
 	.namespace = net_namespace,
+	.get_ownership = net_get_ownership,
 };
 
 #ifdef CONFIG_OF_NET
-- 
cgit v1.2.3


From fbdeaed408cf2728c62640c10848ddb1b67e63d3 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@canonical.com>
Date: Fri, 20 Jul 2018 21:56:53 +0000
Subject: net: create reusable function for getting ownership info of sysfs
 inodes

Make net_ns_get_ownership() reusable by networking code outside of core.
This is useful, for example, to allow bridge related sysfs files to be
owned by container root.

Add a function comment since this is a potentially dangerous function to
use given the way that kobject_get_ownership() works by initializing uid
and gid before calling .get_ownership().

Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/net_namespace.h | 10 ++++++++++
 net/core/net-sysfs.c        | 18 ------------------
 net/core/net_namespace.c    | 28 ++++++++++++++++++++++++++++
 3 files changed, 38 insertions(+), 18 deletions(-)

diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index a71264d75d7f..9b5fdc50519a 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -10,6 +10,7 @@
 #include <linux/workqueue.h>
 #include <linux/list.h>
 #include <linux/sysctl.h>
+#include <linux/uidgid.h>
 
 #include <net/flow.h>
 #include <net/netns/core.h>
@@ -170,6 +171,8 @@ extern struct net init_net;
 struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns,
 			struct net *old_net);
 
+void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid);
+
 void net_ns_barrier(void);
 #else /* CONFIG_NET_NS */
 #include <linux/sched.h>
@@ -182,6 +185,13 @@ static inline struct net *copy_net_ns(unsigned long flags,
 	return old_net;
 }
 
+static inline void net_ns_get_ownership(const struct net *net,
+					kuid_t *uid, kgid_t *gid)
+{
+	*uid = GLOBAL_ROOT_UID;
+	*gid = GLOBAL_ROOT_GID;
+}
+
 static inline void net_ns_barrier(void) {}
 #endif /* CONFIG_NET_NS */
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index ada065fc685e..0a95bcf64cdc 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -656,24 +656,6 @@ static const struct attribute_group wireless_group = {
 #define net_class_groups	NULL
 #endif /* CONFIG_SYSFS */
 
-static void net_ns_get_ownership(const struct net *net,
-				 kuid_t *uid, kgid_t *gid)
-{
-	if (net) {
-		kuid_t ns_root_uid = make_kuid(net->user_ns, 0);
-		kgid_t ns_root_gid = make_kgid(net->user_ns, 0);
-
-		if (uid_valid(ns_root_uid))
-			*uid = ns_root_uid;
-
-		if (gid_valid(ns_root_gid))
-			*gid = ns_root_gid;
-	} else {
-		*uid = GLOBAL_ROOT_UID;
-		*gid = GLOBAL_ROOT_GID;
-	}
-}
-
 #ifdef CONFIG_SYSFS
 #define to_rx_queue_attr(_attr) \
 	container_of(_attr, struct rx_queue_attribute, attr)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index a11e03f920d3..738871af5efa 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -17,6 +17,7 @@
 #include <linux/user_namespace.h>
 #include <linux/net_namespace.h>
 #include <linux/sched/task.h>
+#include <linux/uidgid.h>
 
 #include <net/sock.h>
 #include <net/netlink.h>
@@ -448,6 +449,33 @@ dec_ucounts:
 	return net;
 }
 
+/**
+ * net_ns_get_ownership - get sysfs ownership data for @net
+ * @net: network namespace in question (can be NULL)
+ * @uid: kernel user ID for sysfs objects
+ * @gid: kernel group ID for sysfs objects
+ *
+ * Returns the uid/gid pair of root in the user namespace associated with the
+ * given network namespace.
+ */
+void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid)
+{
+	if (net) {
+		kuid_t ns_root_uid = make_kuid(net->user_ns, 0);
+		kgid_t ns_root_gid = make_kgid(net->user_ns, 0);
+
+		if (uid_valid(ns_root_uid))
+			*uid = ns_root_uid;
+
+		if (gid_valid(ns_root_gid))
+			*gid = ns_root_gid;
+	} else {
+		*uid = GLOBAL_ROOT_UID;
+		*gid = GLOBAL_ROOT_GID;
+	}
+}
+EXPORT_SYMBOL_GPL(net_ns_get_ownership);
+
 static void unhash_nsid(struct net *net, struct net *last)
 {
 	struct net *tmp;
-- 
cgit v1.2.3


From 705e0dea4d52ef420a7d37fd9cc6725092e5e1ff Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@canonical.com>
Date: Fri, 20 Jul 2018 21:56:54 +0000
Subject: bridge: make sure objects belong to container's owner

When creating various bridge objects in /sys/class/net/... make sure
that they belong to the container's owner instead of global root (if
they belong to a container/namespace).

Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_if.c       | 9 +++++++++
 net/bridge/br_private.h  | 2 ++
 net/bridge/br_sysfs_if.c | 5 ++---
 3 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 05e42d86882d..e7c8d55212aa 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -26,6 +26,7 @@
 #include <net/sock.h>
 #include <linux/if_vlan.h>
 #include <net/switchdev.h>
+#include <net/net_namespace.h>
 
 #include "br_private.h"
 
@@ -204,11 +205,19 @@ static void release_nbp(struct kobject *kobj)
 	kfree(p);
 }
 
+static void brport_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid)
+{
+	struct net_bridge_port *p = kobj_to_brport(kobj);
+
+	net_ns_get_ownership(dev_net(p->dev), uid, gid);
+}
+
 static struct kobj_type brport_ktype = {
 #ifdef CONFIG_SYSFS
 	.sysfs_ops = &brport_sysfs_ops,
 #endif
 	.release = release_nbp,
+	.get_ownership = brport_get_ownership,
 };
 
 static void destroy_nbp(struct net_bridge_port *p)
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 5216a524b537..cf0005d2a4d0 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -283,6 +283,8 @@ struct net_bridge_port {
 	u16				group_fwd_mask;
 };
 
+#define kobj_to_brport(obj)	container_of(obj, struct net_bridge_port, kobj)
+
 #define br_auto_port(p) ((p)->flags & BR_AUTO_MASK)
 #define br_promisc_port(p) ((p)->flags & BR_PROMISC)
 
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index f99c5bf5c906..ab4c7f8adf68 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -249,13 +249,12 @@ static const struct brport_attribute *brport_attrs[] = {
 };
 
 #define to_brport_attr(_at) container_of(_at, struct brport_attribute, attr)
-#define to_brport(obj)	container_of(obj, struct net_bridge_port, kobj)
 
 static ssize_t brport_show(struct kobject *kobj,
 			   struct attribute *attr, char *buf)
 {
 	struct brport_attribute *brport_attr = to_brport_attr(attr);
-	struct net_bridge_port *p = to_brport(kobj);
+	struct net_bridge_port *p = kobj_to_brport(kobj);
 
 	if (!brport_attr->show)
 		return -EINVAL;
@@ -268,7 +267,7 @@ static ssize_t brport_store(struct kobject *kobj,
 			    const char *buf, size_t count)
 {
 	struct brport_attribute *brport_attr = to_brport_attr(attr);
-	struct net_bridge_port *p = to_brport(kobj);
+	struct net_bridge_port *p = kobj_to_brport(kobj);
 	ssize_t ret = -EINVAL;
 	char *endp;
 	unsigned long val;
-- 
cgit v1.2.3


From 646cb51228d497b1c56b1d8ee18bb2b1bd87c93c Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:46:58 +0100
Subject: net: hns3: Remove some redundant assignments

Remove some redundant assignments, because they have
been set to zero when allocate hdev.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 266c68607e53..b271880c068f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5595,8 +5595,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hdev->pdev = pdev;
 	hdev->ae_dev = ae_dev;
 	hdev->reset_type = HNAE3_NONE_RESET;
-	hdev->reset_request = 0;
-	hdev->reset_pending = 0;
 	ae_dev->priv = hdev;
 
 	ret = hclge_pci_init(hdev);
-- 
cgit v1.2.3


From 3f639907e02e5a63ef5cca6aa5ddf87e93c40510 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:46:59 +0100
Subject: net: hns3: Standardize the handle of return value

Apply the standard minor cleanup by returning ret outside
the brackets.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 133 +++++++--------------
 1 file changed, 46 insertions(+), 87 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b271880c068f..cca5b2f34a47 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1108,12 +1108,12 @@ static int hclge_get_cfg(struct hclge_dev *hdev, struct hclge_cfg *hcfg)
 
 	ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_PF_CFG_DESC_NUM);
 	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"get config failed %d.\n", ret);
+		dev_err(&hdev->pdev->dev, "get config failed %d.\n", ret);
 		return ret;
 	}
 
 	hclge_parse_cfg(hcfg, desc);
+
 	return 0;
 }
 
@@ -1130,13 +1130,10 @@ static int hclge_get_cap(struct hclge_dev *hdev)
 
 	/* get pf resource */
 	ret = hclge_query_pf_resource(hdev);
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"query pf resource error %d.\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_err(&hdev->pdev->dev, "query pf resource error %d.\n", ret);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_configure(struct hclge_dev *hdev)
@@ -1265,13 +1262,10 @@ static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id,
 	req->tqp_vid = cpu_to_le16(tqp_vid);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
-		dev_err(&hdev->pdev->dev, "TQP map failed %d.\n",
-			ret);
-		return ret;
-	}
+	if (ret)
+		dev_err(&hdev->pdev->dev, "TQP map failed %d.\n", ret);
 
-	return 0;
+	return ret;
 }
 
 static int  hclge_assign_tqp(struct hclge_vport *vport,
@@ -1330,12 +1324,10 @@ static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps)
 		return -ENOMEM;
 
 	ret = hclge_assign_tqp(vport, kinfo->tqp, kinfo->num_tqps);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "fail to assign TQPs %d.\n", ret);
-		return -EINVAL;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_map_tqp_to_vport(struct hclge_dev *hdev,
@@ -1487,13 +1479,11 @@ static int  hclge_cmd_alloc_tx_buff(struct hclge_dev *hdev,
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "tx buffer alloc cmd failed %d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
@@ -1501,13 +1491,10 @@ static int hclge_tx_buffer_alloc(struct hclge_dev *hdev,
 {
 	int ret = hclge_cmd_alloc_tx_buff(hdev, buf_alloc);
 
-	if (ret) {
-		dev_err(&hdev->pdev->dev,
-			"tx buffer alloc failed %d\n", ret);
-		return ret;
-	}
+	if (ret)
+		dev_err(&hdev->pdev->dev, "tx buffer alloc failed %d\n", ret);
 
-	return 0;
+	return ret;
 }
 
 static int hclge_get_tc_num(struct hclge_dev *hdev)
@@ -1825,13 +1812,11 @@ static int hclge_rx_priv_buf_alloc(struct hclge_dev *hdev,
 			    (1 << HCLGE_TC0_PRI_BUF_EN_B));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"rx private buffer alloc cmd failed %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
@@ -1871,13 +1856,11 @@ static int hclge_rx_priv_wl_config(struct hclge_dev *hdev,
 
 	/* Send 2 descriptor at one time */
 	ret = hclge_cmd_send(&hdev->hw, desc, 2);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"rx private waterline config cmd failed %d\n",
 			ret);
-		return ret;
-	}
-	return 0;
+	return ret;
 }
 
 static int hclge_common_thrd_config(struct hclge_dev *hdev,
@@ -1917,12 +1900,10 @@ static int hclge_common_thrd_config(struct hclge_dev *hdev,
 
 	/* Send 2 descriptors at one time */
 	ret = hclge_cmd_send(&hdev->hw, desc, 2);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"common threshold config cmd failed %d\n", ret);
-		return ret;
-	}
-	return 0;
+	return ret;
 }
 
 static int hclge_common_wl_config(struct hclge_dev *hdev,
@@ -1943,13 +1924,11 @@ static int hclge_common_wl_config(struct hclge_dev *hdev,
 	req->com_wl.low |=  cpu_to_le16(BIT(HCLGE_RX_PRIV_EN_B));
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"common waterline config cmd failed %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 int hclge_buffer_alloc(struct hclge_dev *hdev)
@@ -2196,13 +2175,11 @@ static int hclge_query_mac_an_speed_dup(struct hclge_dev *hdev, int *speed,
 				    HCLGE_QUERY_SPEED_S);
 
 	ret = hclge_parse_speed(speed_tmp, speed);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"could not parse speed(=%d), %d\n", speed_tmp, ret);
-		return -EIO;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
@@ -2219,13 +2196,11 @@ static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
 	req->cfg_an_cmd_flag = cpu_to_le32(flag);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "auto neg set cmd failed %d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_autoneg(struct hnae3_handle *handle, bool enable)
@@ -2331,13 +2306,11 @@ static int hclge_mac_init(struct hclge_dev *hdev)
 		mtu = ETH_DATA_LEN;
 
 	ret = hclge_set_mtu(handle, mtu);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"set mtu failed ret=%d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static void hclge_mbx_task_schedule(struct hclge_dev *hdev)
@@ -3121,13 +3094,11 @@ static int hclge_set_rss_tc_mode(struct hclge_dev *hdev, u16 *tc_valid,
 	}
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Configure rss tc mode fail, status = %d\n", ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_rss_input_tuple(struct hclge_dev *hdev)
@@ -3150,13 +3121,10 @@ static int hclge_set_rss_input_tuple(struct hclge_dev *hdev)
 	req->ipv6_sctp_en = hdev->vport[0].rss_tuple_sets.ipv6_sctp_en;
 	req->ipv6_fragment_en = hdev->vport[0].rss_tuple_sets.ipv6_fragment_en;
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Configure rss input fail, status = %d\n", ret);
-		return ret;
-	}
-
-	return 0;
+	return ret;
 }
 
 static int hclge_get_rss(struct hnae3_handle *handle, u32 *indir,
@@ -3604,12 +3572,11 @@ int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev,
 		HCLGE_PROMISC_TX_EN_B | HCLGE_PROMISC_RX_EN_B;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Set promisc mode fail, status is %d.\n", ret);
-		return ret;
-	}
-	return 0;
+
+	return ret;
 }
 
 void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc,
@@ -3960,14 +3927,12 @@ static int hclge_set_mta_filter_mode(struct hclge_dev *hdev,
 			HCLGE_CFG_MTA_MAC_SEL_S, mta_mac_sel);
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Config mat filter mode failed for cmd_send, ret =%d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 int hclge_cfg_func_mta_filter(struct hclge_dev *hdev,
@@ -3986,14 +3951,12 @@ int hclge_cfg_func_mta_filter(struct hclge_dev *hdev,
 	req->function_id = func_id;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Config func_id enable failed for cmd_send, ret =%d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_mta_table_item(struct hclge_vport *vport,
@@ -4598,13 +4561,11 @@ static int hclge_set_vlan_filter_ctrl(struct hclge_dev *hdev, u8 vlan_type,
 	req->vlan_fe = filter_en;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "set vlan filter fail, ret =%d.\n",
 			ret);
-		return ret;
-	}
 
-	return 0;
+	return ret;
 }
 
 #define HCLGE_FILTER_TYPE_VF		0
@@ -4996,14 +4957,12 @@ static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mtu)
 	req->min_frm_size = HCLGE_MAC_MIN_FRAME;
 
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
-	if (ret) {
+	if (ret)
 		dev_err(&hdev->pdev->dev, "set mtu fail, ret =%d.\n", ret);
-		return ret;
-	}
-
-	hdev->mps = max_frm_size;
+	else
+		hdev->mps = max_frm_size;
 
-	return 0;
+	return ret;
 }
 
 static int hclge_set_mtu(struct hnae3_handle *handle, int new_mtu)
-- 
cgit v1.2.3


From a10829c4aeab1fd837129537a4d44f6a79a18202 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:47:00 +0100
Subject: net: hns3: Remove extra space and brackets

Remove extra space and brackets.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 656c3e622ec8..e66a762e2462 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -37,7 +37,7 @@ struct hclge_cmq_ring {
 	dma_addr_t desc_dma_addr;
 	struct hclge_desc *desc;
 	struct hclge_desc_cb *desc_cb;
-	struct hclge_dev  *dev;
+	struct hclge_dev *dev;
 	u32 head;
 	u32 tail;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index cca5b2f34a47..b09798847716 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -4288,7 +4288,7 @@ static int hclge_add_mc_addr(struct hnae3_handle *handle,
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 
-	return	hclge_add_mc_addr_common(vport, addr);
+	return hclge_add_mc_addr_common(vport, addr);
 }
 
 int hclge_add_mc_addr_common(struct hclge_vport *vport,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index a5abf8ee9b96..b01a51d941f0 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -77,11 +77,11 @@
 /* Copper Specific Status Register */
 #define HCLGE_PHY_CSS_REG		17
 
-#define HCLGE_PHY_MDIX_CTRL_S		(5)
+#define HCLGE_PHY_MDIX_CTRL_S		5
 #define HCLGE_PHY_MDIX_CTRL_M		GENMASK(6, 5)
 
-#define HCLGE_PHY_MDIX_STATUS_B	(6)
-#define HCLGE_PHY_SPEED_DUP_RESOLVE_B	(11)
+#define HCLGE_PHY_MDIX_STATUS_B		6
+#define HCLGE_PHY_SPEED_DUP_RESOLVE_B	11
 
 /* Factor used to calculate offset and bitmap of VF num */
 #define HCLGE_VF_NUM_PER_CMD           64
-- 
cgit v1.2.3


From fdace1bc4a1e427e77683d8ada782056022faed4 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:47:01 +0100
Subject: net: hns3: Correct unreasonable code comments

This patch fixes some comment spelling errors, removes
redundant comments, rewrites misleading comments, and
adds some necessary comments.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 33 ++++++++++------------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  1 +
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    | 13 +++++----
 3 files changed, 23 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index e66a762e2462..940c1599dbb4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -71,7 +71,7 @@ struct hclge_misc_vector {
 struct hclge_cmq {
 	struct hclge_cmq_ring csq;
 	struct hclge_cmq_ring crq;
-	u16 tx_timeout; /* Tx timeout */
+	u16 tx_timeout;
 	enum hclge_cmd_status last_status;
 };
 
@@ -90,7 +90,7 @@ struct hclge_cmq {
 #define HCLGE_CMD_FLAG_ERR_INTR	BIT(HCLGE_CMD_FLAG_ERR_INTR_SHIFT)
 
 enum hclge_opcode_type {
-	/* Generic command */
+	/* Generic commands */
 	HCLGE_OPC_QUERY_FW_VER		= 0x0001,
 	HCLGE_OPC_CFG_RST_TRIGGER	= 0x0020,
 	HCLGE_OPC_GBL_RST_STATUS	= 0x0021,
@@ -106,18 +106,16 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QUERY_REG_NUM		= 0x0040,
 	HCLGE_OPC_QUERY_32_BIT_REG	= 0x0041,
 	HCLGE_OPC_QUERY_64_BIT_REG	= 0x0042,
-	/* Device management command */
 
-	/* MAC commond */
+	/* MAC command */
 	HCLGE_OPC_CONFIG_MAC_MODE	= 0x0301,
 	HCLGE_OPC_CONFIG_AN_MODE	= 0x0304,
 	HCLGE_OPC_QUERY_AN_RESULT	= 0x0306,
 	HCLGE_OPC_QUERY_LINK_STATUS	= 0x0307,
 	HCLGE_OPC_CONFIG_MAX_FRM_SIZE	= 0x0308,
 	HCLGE_OPC_CONFIG_SPEED_DUP	= 0x0309,
-	/* MACSEC command */
 
-	/* PFC/Pause CMD*/
+	/* PFC/Pause commands */
 	HCLGE_OPC_CFG_MAC_PAUSE_EN      = 0x0701,
 	HCLGE_OPC_CFG_PFC_PAUSE_EN      = 0x0702,
 	HCLGE_OPC_CFG_MAC_PARA          = 0x0703,
@@ -148,7 +146,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_TM_QS_SCH_MODE_CFG    = 0x0814,
 	HCLGE_OPC_TM_BP_TO_QSET_MAPPING = 0x0815,
 
-	/* Packet buffer allocate command */
+	/* Packet buffer allocate commands */
 	HCLGE_OPC_TX_BUFF_ALLOC		= 0x0901,
 	HCLGE_OPC_RX_PRIV_BUFF_ALLOC	= 0x0902,
 	HCLGE_OPC_RX_PRIV_WL_ALLOC	= 0x0903,
@@ -156,11 +154,10 @@ enum hclge_opcode_type {
 	HCLGE_OPC_RX_COM_WL_ALLOC	= 0x0905,
 	HCLGE_OPC_RX_GBL_PKT_CNT	= 0x0906,
 
-	/* PTP command */
 	/* TQP management command */
 	HCLGE_OPC_SET_TQP_MAP		= 0x0A01,
 
-	/* TQP command */
+	/* TQP commands */
 	HCLGE_OPC_CFG_TX_QUEUE		= 0x0B01,
 	HCLGE_OPC_QUERY_TX_POINTER	= 0x0B02,
 	HCLGE_OPC_QUERY_TX_STATUS	= 0x0B03,
@@ -172,10 +169,10 @@ enum hclge_opcode_type {
 	HCLGE_OPC_CFG_COM_TQP_QUEUE	= 0x0B20,
 	HCLGE_OPC_RESET_TQP_QUEUE	= 0x0B22,
 
-	/* TSO cmd */
+	/* TSO command */
 	HCLGE_OPC_TSO_GENERIC_CONFIG	= 0x0C01,
 
-	/* RSS cmd */
+	/* RSS commands */
 	HCLGE_OPC_RSS_GENERIC_CONFIG	= 0x0D01,
 	HCLGE_OPC_RSS_INDIR_TABLE	= 0x0D07,
 	HCLGE_OPC_RSS_TC_MODE		= 0x0D08,
@@ -184,15 +181,15 @@ enum hclge_opcode_type {
 	/* Promisuous mode command */
 	HCLGE_OPC_CFG_PROMISC_MODE	= 0x0E01,
 
-	/* Vlan offload command */
+	/* Vlan offload commands */
 	HCLGE_OPC_VLAN_PORT_TX_CFG	= 0x0F01,
 	HCLGE_OPC_VLAN_PORT_RX_CFG	= 0x0F02,
 
-	/* Interrupts cmd */
+	/* Interrupts commands */
 	HCLGE_OPC_ADD_RING_TO_VECTOR	= 0x1503,
 	HCLGE_OPC_DEL_RING_TO_VECTOR	= 0x1504,
 
-	/* MAC command */
+	/* MAC commands */
 	HCLGE_OPC_MAC_VLAN_ADD		    = 0x1000,
 	HCLGE_OPC_MAC_VLAN_REMOVE	    = 0x1001,
 	HCLGE_OPC_MAC_VLAN_TYPE_ID	    = 0x1002,
@@ -201,13 +198,13 @@ enum hclge_opcode_type {
 	HCLGE_OPC_MAC_ETHTYPE_REMOVE	= 0x1011,
 	HCLGE_OPC_MAC_VLAN_MASK_SET	= 0x1012,
 
-	/* Multicast linear table cmd */
+	/* Multicast linear table commands */
 	HCLGE_OPC_MTA_MAC_MODE_CFG	    = 0x1020,
 	HCLGE_OPC_MTA_MAC_FUNC_CFG	    = 0x1021,
 	HCLGE_OPC_MTA_TBL_ITEM_CFG	    = 0x1022,
 	HCLGE_OPC_MTA_TBL_ITEM_QUERY	= 0x1023,
 
-	/* VLAN command */
+	/* VLAN commands */
 	HCLGE_OPC_VLAN_FILTER_CTRL	    = 0x1100,
 	HCLGE_OPC_VLAN_FILTER_PF_CFG	= 0x1101,
 	HCLGE_OPC_VLAN_FILTER_VF_CFG	= 0x1102,
@@ -215,7 +212,7 @@ enum hclge_opcode_type {
 	/* MDIO command */
 	HCLGE_OPC_MDIO_CONFIG		= 0x1900,
 
-	/* QCN command */
+	/* QCN commands */
 	HCLGE_OPC_QCN_MOD_CFG		= 0x1A01,
 	HCLGE_OPC_QCN_GRP_TMPLT_CFG	= 0x1A02,
 	HCLGE_OPC_QCN_SHAPPING_IR_CFG	= 0x1A03,
@@ -225,7 +222,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QCN_AJUST_INIT	= 0x1A07,
 	HCLGE_OPC_QCN_DFX_CNT_STATUS    = 0x1A08,
 
-	/* Mailbox cmd */
+	/* Mailbox command */
 	HCLGEVF_OPC_MBX_PF_TO_VF	= 0x2000,
 
 	/* Led command */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index b09798847716..de36dfb75fee 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -5866,6 +5866,7 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 	u32 *rss_indir;
 	int ret, i;
 
+	/* Free old tqps, and reallocate with new tqp number when nic setup */
 	hclge_release_tqp(vport);
 
 	ret = hclge_knic_setup(vport, new_tqps_num);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index b01a51d941f0..b84a140c0117 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -203,7 +203,10 @@ struct hlcge_tqp_stats {
 };
 
 struct hclge_tqp {
-	struct device *dev;	/* Device for DMA mapping */
+	/* copy of device pointer from pci_dev,
+	 * used when perform DMA mapping
+	 */
+	struct device *dev;
 	struct hnae3_queue q;
 	struct hlcge_tqp_stats tqp_stats;
 	u16 index;	/* Global index in a NIC controller */
@@ -493,13 +496,11 @@ struct hclge_dev {
 	u16 num_tqps;			/* Num task queue pairs of this PF */
 	u16 num_req_vfs;		/* Num VFs requested for this PF */
 
-	/* Base task tqp physical id of this PF */
-	u16 base_tqp_pid;
+	u16 base_tqp_pid;	/* Base task tqp physical id of this PF */
 	u16 alloc_rss_size;		/* Allocated RSS task queue */
 	u16 rss_size_max;		/* HW defined max RSS task queue */
 
-	/* Num of guaranteed filters for this PF */
-	u16 fdir_pf_filter_count;
+	u16 fdir_pf_filter_count; /* Num of guaranteed filters for this PF */
 	u16 num_alloc_vport;		/* Num vports this driver supports */
 	u32 numa_node_mask;
 	u16 rx_buf_len;
@@ -561,7 +562,7 @@ struct hclge_dev {
 	u32 mps; /* Max packet size */
 
 	enum hclge_mta_dmac_sel_type mta_mac_sel_type;
-	bool enable_mta; /* Mutilcast filter enable */
+	bool enable_mta; /* Multicast filter enable */
 
 	struct hclge_vlan_type_cfg vlan_type_cfg;
 
-- 
cgit v1.2.3


From f8a91784a13e083862b7ec325dda6bea1d25645e Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:47:02 +0100
Subject: net: hns3: Use decimal for bit offset macros

Using hex for bit offsets is inconsistent with the rest
of the file. Change them to decimal.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 24 +++++++++++-----------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  4 ++--
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 940c1599dbb4..219ffc746260 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -579,13 +579,13 @@ enum hclge_mac_vlan_tbl_opcode {
 	HCLGE_MAC_VLAN_LKUP,    /* Lookup a entry through mac_vlan key */
 };
 
-#define HCLGE_MAC_VLAN_BIT0_EN_B	0x0
-#define HCLGE_MAC_VLAN_BIT1_EN_B	0x1
-#define HCLGE_MAC_EPORT_SW_EN_B		0xc
-#define HCLGE_MAC_EPORT_TYPE_B		0xb
-#define HCLGE_MAC_EPORT_VFID_S		0x3
+#define HCLGE_MAC_VLAN_BIT0_EN_B	0
+#define HCLGE_MAC_VLAN_BIT1_EN_B	1
+#define HCLGE_MAC_EPORT_SW_EN_B		12
+#define HCLGE_MAC_EPORT_TYPE_B		11
+#define HCLGE_MAC_EPORT_VFID_S		3
 #define HCLGE_MAC_EPORT_VFID_M		GENMASK(10, 3)
-#define HCLGE_MAC_EPORT_PFID_S		0x0
+#define HCLGE_MAC_EPORT_PFID_S		0
 #define HCLGE_MAC_EPORT_PFID_M		GENMASK(2, 0)
 struct hclge_mac_vlan_tbl_entry_cmd {
 	u8	flags;
@@ -601,7 +601,7 @@ struct hclge_mac_vlan_tbl_entry_cmd {
 	u8      rsv2[6];
 };
 
-#define HCLGE_VLAN_MASK_EN_B		0x0
+#define HCLGE_VLAN_MASK_EN_B		0
 struct hclge_mac_vlan_mask_entry_cmd {
 	u8 rsv0[2];
 	u8 vlan_mask;
@@ -632,23 +632,23 @@ struct hclge_mac_mgr_tbl_entry_cmd {
 	u8      rsv3[2];
 };
 
-#define HCLGE_CFG_MTA_MAC_SEL_S		0x0
+#define HCLGE_CFG_MTA_MAC_SEL_S		0
 #define HCLGE_CFG_MTA_MAC_SEL_M		GENMASK(1, 0)
-#define HCLGE_CFG_MTA_MAC_EN_B		0x7
+#define HCLGE_CFG_MTA_MAC_EN_B		7
 struct hclge_mta_filter_mode_cmd {
 	u8	dmac_sel_en; /* Use lowest 2 bit as sel_mode, bit 7 as enable */
 	u8      rsv[23];
 };
 
-#define HCLGE_CFG_FUNC_MTA_ACCEPT_B	0x0
+#define HCLGE_CFG_FUNC_MTA_ACCEPT_B	0
 struct hclge_cfg_func_mta_filter_cmd {
 	u8	accept; /* Only used lowest 1 bit */
 	u8      function_id;
 	u8      rsv[22];
 };
 
-#define HCLGE_CFG_MTA_ITEM_ACCEPT_B	0x0
-#define HCLGE_CFG_MTA_ITEM_IDX_S	0x0
+#define HCLGE_CFG_MTA_ITEM_ACCEPT_B	0
+#define HCLGE_CFG_MTA_ITEM_IDX_S	0
 #define HCLGE_CFG_MTA_ITEM_IDX_M	GENMASK(11, 0)
 struct hclge_cfg_func_mta_item_cmd {
 	__le16	item_idx; /* Only used lowest 12 bit */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index b84a140c0117..aeae1baa4e6f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -91,8 +91,8 @@
 #define HCLGE_MISC_RESET_STS_REG	0x20700
 #define HCLGE_MISC_VECTOR_INT_STS	0x20800
 #define HCLGE_GLOBAL_RESET_REG		0x20A00
-#define HCLGE_GLOBAL_RESET_BIT		0x0
-#define HCLGE_CORE_RESET_BIT		0x1
+#define HCLGE_GLOBAL_RESET_BIT		0
+#define HCLGE_CORE_RESET_BIT		1
 #define HCLGE_FUN_RST_ING		0x20C00
 #define HCLGE_FUN_RST_ING_B		0
 
-- 
cgit v1.2.3


From c79301d8d985a3f40c233bd744338eafdc57e51a Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:47:03 +0100
Subject: net: hns3: Modify inconsistent bit mask macros

Use BIT() and GENMASK() to convert the bit mask, modify
the inconsistent ones, and remove useless ones.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 25 ++++++++--------------
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    |  2 +-
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.h    |  2 +-
 3 files changed, 11 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 219ffc746260..ec7b8d74b941 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -75,19 +75,12 @@ struct hclge_cmq {
 	enum hclge_cmd_status last_status;
 };
 
-#define HCLGE_CMD_FLAG_IN_VALID_SHIFT	0
-#define HCLGE_CMD_FLAG_OUT_VALID_SHIFT	1
-#define HCLGE_CMD_FLAG_NEXT_SHIFT	2
-#define HCLGE_CMD_FLAG_WR_OR_RD_SHIFT	3
-#define HCLGE_CMD_FLAG_NO_INTR_SHIFT	4
-#define HCLGE_CMD_FLAG_ERR_INTR_SHIFT	5
-
-#define HCLGE_CMD_FLAG_IN	BIT(HCLGE_CMD_FLAG_IN_VALID_SHIFT)
-#define HCLGE_CMD_FLAG_OUT	BIT(HCLGE_CMD_FLAG_OUT_VALID_SHIFT)
-#define HCLGE_CMD_FLAG_NEXT	BIT(HCLGE_CMD_FLAG_NEXT_SHIFT)
-#define HCLGE_CMD_FLAG_WR	BIT(HCLGE_CMD_FLAG_WR_OR_RD_SHIFT)
-#define HCLGE_CMD_FLAG_NO_INTR	BIT(HCLGE_CMD_FLAG_NO_INTR_SHIFT)
-#define HCLGE_CMD_FLAG_ERR_INTR	BIT(HCLGE_CMD_FLAG_ERR_INTR_SHIFT)
+#define HCLGE_CMD_FLAG_IN	BIT(0)
+#define HCLGE_CMD_FLAG_OUT	BIT(1)
+#define HCLGE_CMD_FLAG_NEXT	BIT(2)
+#define HCLGE_CMD_FLAG_WR	BIT(3)
+#define HCLGE_CMD_FLAG_NO_INTR	BIT(4)
+#define HCLGE_CMD_FLAG_ERR_INTR	BIT(5)
 
 enum hclge_opcode_type {
 	/* Generic commands */
@@ -379,7 +372,7 @@ struct hclge_pf_res_cmd {
 	__le16 msixcap_localid_ba_nic;
 	__le16 msixcap_localid_ba_rocee;
 #define HCLGE_PF_VEC_NUM_S		0
-#define HCLGE_PF_VEC_NUM_M		(0xff << HCLGE_PF_VEC_NUM_S)
+#define HCLGE_PF_VEC_NUM_M		GENMASK(7, 0)
 	__le16 pf_intr_vector_number;
 	__le16 pf_own_fun_number;
 	__le32 rsv[3];
@@ -468,8 +461,8 @@ struct hclge_rss_tc_mode_cmd {
 	u8 rsv[8];
 };
 
-#define HCLGE_LINK_STS_B	0
-#define HCLGE_LINK_STATUS	BIT(HCLGE_LINK_STS_B)
+#define HCLGE_LINK_STATUS_UP_B	0
+#define HCLGE_LINK_STATUS_UP_M	BIT(HCLGE_LINK_STATUS_UP_B)
 struct hclge_link_status_cmd {
 	u8 status;
 	u8 rsv[23];
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index de36dfb75fee..e0b617c8628f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -2349,7 +2349,7 @@ static int hclge_get_mac_link_status(struct hclge_dev *hdev)
 	}
 
 	req = (struct hclge_link_status_cmd *)desc.data;
-	link_status = req->status & HCLGE_LINK_STATUS;
+	link_status = req->status & HCLGE_LINK_STATUS_UP_M;
 
 	return !!link_status;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index aeae1baa4e6f..a1ed6df444f9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -40,7 +40,7 @@
 #define HCLGE_RSS_HASH_ALGO_TOEPLITZ	0
 #define HCLGE_RSS_HASH_ALGO_SIMPLE	1
 #define HCLGE_RSS_HASH_ALGO_SYMMETRIC	2
-#define HCLGE_RSS_HASH_ALGO_MASK	0xf
+#define HCLGE_RSS_HASH_ALGO_MASK	GENMASK(3, 0)
 #define HCLGE_RSS_CFG_TBL_NUM \
 	(HCLGE_RSS_IND_TBL_SIZE / HCLGE_RSS_CFG_TBL_SIZE)
 
-- 
cgit v1.2.3


From ef0c5009619c90646211a576f280339e4151e39d Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:47:04 +0100
Subject: net: hns3: Fix misleading parameter name

The input parameter "dev" of hns3_irq_handle() is indeed
used as a tqp vector, it is misleadin.

The struct member "flag" is used to indicate ring type,
so rename it.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c        | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 4 ++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 29be96e5cc47..ba2797ed5652 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -62,9 +62,9 @@ static const struct pci_device_id hns3_pci_tbl[] = {
 };
 MODULE_DEVICE_TABLE(pci, hns3_pci_tbl);
 
-static irqreturn_t hns3_irq_handle(int irq, void *dev)
+static irqreturn_t hns3_irq_handle(int irq, void *vector)
 {
-	struct hns3_enet_tqp_vector *tqp_vector = dev;
+	struct hns3_enet_tqp_vector *tqp_vector = vector;
 
 	napi_schedule(&tqp_vector->napi);
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index cf40afca66db..68356da4ac46 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -72,7 +72,7 @@ static int hclge_alloc_cmd_queue(struct hclge_dev *hdev, int ring_type)
 		(ring_type == HCLGE_TYPE_CSQ) ? &hw->cmq.csq : &hw->cmq.crq;
 	int ret;
 
-	ring->flag = ring_type;
+	ring->ring_type = ring_type;
 	ring->dev = hdev;
 
 	ret = hclge_alloc_cmd_desc(ring);
@@ -111,7 +111,7 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring)
 	struct hclge_dev *hdev = ring->dev;
 	struct hclge_hw *hw = &hdev->hw;
 
-	if (ring->flag == HCLGE_TYPE_CSQ) {
+	if (ring->ring_type == HCLGE_TYPE_CSQ) {
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG,
 				lower_32_bits(dma));
 		hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG,
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index ec7b8d74b941..54e199d1592c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -45,7 +45,7 @@ struct hclge_cmq_ring {
 	u16 desc_num;
 	int next_to_use;
 	int next_to_clean;
-	u8 flag;
+	u8 ring_type; /* cmq ring type */
 	spinlock_t lock; /* Command queue lock */
 };
 
-- 
cgit v1.2.3


From 584b464f83a1f6fcc21a201ea46c889647ed3255 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:47:05 +0100
Subject: net: hns3: Remove unused struct member and definition

The struct hclge_desc_cb and hclge_desc_cb are never used in
anywhere. This patch removes them.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 7 -------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 7 -------
 2 files changed, 14 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 54e199d1592c..66a534a9c0e2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -27,16 +27,9 @@ struct hclge_desc {
 	__le32 data[6];
 };
 
-struct hclge_desc_cb {
-	dma_addr_t dma;
-	void *va;
-	u32 length;
-};
-
 struct hclge_cmq_ring {
 	dma_addr_t desc_dma_addr;
 	struct hclge_desc *desc;
-	struct hclge_desc_cb *desc_cb;
 	struct hclge_dev *dev;
 	u32 head;
 	u32 tail;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index a1ed6df444f9..7d4845ea487c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -140,12 +140,6 @@ enum hclge_evt_cause {
 };
 
 #define HCLGE_MPF_ENBALE 1
-struct hclge_caps {
-	u16 num_tqp;
-	u16 num_buffer_cell;
-	u32 flag;
-	u16 vmdq;
-};
 
 enum HCLGE_MAC_SPEED {
 	HCLGE_MAC_SPEED_10M	= 10,		/* 10 Mbps */
@@ -191,7 +185,6 @@ struct hclge_hw {
 	struct hclge_mac mac;
 	int num_vec;
 	struct hclge_cmq cmq;
-	struct hclge_caps caps;
 };
 
 /* TQP stats */
-- 
cgit v1.2.3


From d71d8381c5b7f5edbc154d8ce586a747a01c3b0c Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Thu, 19 Jul 2018 15:47:06 +0100
Subject: net: hns3: Add SPDX tags to HNS3 PF driver

Add the SPDX identifiers to HNS3 PF driver.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hnae3.c             | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hnae3.h             | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c        | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c         | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h         | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c      | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c  | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c  | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h  | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c   | 10 ++--------
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h   | 10 ++--------
 16 files changed, 32 insertions(+), 128 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
index 0762ad18fdcc..fff5be8078ac 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/list.h>
 #include <linux/spinlock.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
index da806fdfbbe6..67befff0bfc5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNAE3_H
 #define __HNAE3_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
index eb82700da7d0..ea5f8a84070d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_dcbnl.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include "hnae3.h"
 #include "hns3_enet.h"
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index ba2797ed5652..6c9e5d62455b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/dma-mapping.h>
 #include <linux/etherdevice.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index bf9aa02be994..e4b4a8f2ceaa 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HNS3_ENET_H
 #define __HNS3_ENET_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 11620e003a8e..80ba95d76260 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
 #include <linux/string.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 68356da4ac46..165c3d5e1c4c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/dma-mapping.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 66a534a9c0e2..5cd22f9bbdec 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_CMD_H
 #define __HCLGE_CMD_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
index 955f0e3d5c95..f08ebb7caaaf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include "hclge_main.h"
 #include "hclge_tm.h"
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
index 7d808ee96694..278f21e02736 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_DCB_H__
 #define __HCLGE_DCB_H__
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index e0b617c8628f..a9b888f1544a 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/acpi.h>
 #include <linux/device.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index 7d4845ea487c..dfa5c9456d22 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MAIN_H
 #define __HCLGE_MAIN_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index b6cfe6ff988d..2065ee2fd358 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index c5e91cfb8f2c..bb3ce35e0d66 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016-2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_MDIO_H
 #define __HCLGE_MDIO_H
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
index e2acf3bd6ba3..5db70a1451c5 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #include <linux/etherdevice.h>
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
index c82d49ebd5bf..dd4c194747c1 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.h
@@ -1,11 +1,5 @@
-/*
- * Copyright (c) 2016~2017 Hisilicon Limited.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2016-2017 Hisilicon Limited.
 
 #ifndef __HCLGE_TM_H
 #define __HCLGE_TM_H
-- 
cgit v1.2.3


From a702349a4099cd5a7bab0904689d8e0bf8dcd622 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:48 +0200
Subject: s390/qeth: fix race in used-buffer accounting

By updating q->used_buffers only _after_ do_QDIO() has completed, there
is a potential race against the buffer's TX completion. In the unlikely
case that the TX completion path wins, qeth_qdio_output_handler() would
decrement the counter before qeth_flush_buffers() even incremented it.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index d80972b9bfc7..f7ddd6455638 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3506,13 +3506,14 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 	qdio_flags = QDIO_FLAG_SYNC_OUTPUT;
 	if (atomic_read(&queue->set_pci_flags_count))
 		qdio_flags |= QDIO_FLAG_PCI_OUT;
+	atomic_add(count, &queue->used_buffers);
+
 	rc = do_QDIO(CARD_DDEV(queue->card), qdio_flags,
 		     queue->queue_no, index, count);
 	if (queue->card->options.performance_stats)
 		queue->card->perf_stats.outbound_do_qdio_time +=
 			qeth_get_micros() -
 			queue->card->perf_stats.outbound_do_qdio_start_time;
-	atomic_add(count, &queue->used_buffers);
 	if (rc) {
 		queue->card->stats.tx_errors += count;
 		/* ignore temporary SIGA errors without busy condition */
-- 
cgit v1.2.3


From 70551dc46ffa3555a0b5f3545b0cd87ab67fd002 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:49 +0200
Subject: s390/qeth: reset layer2 attribute on layer switch

After the subdriver's remove() routine has completed, the card's layer
mode is undetermined again. Reflect this in the layer2 field.

If qeth_dev_layer2_store() hits an error after remove() was called, the
card _always_ requires a setup(), even if the previous layer mode is
requested again.
But qeth_dev_layer2_store() bails out early if the requested layer mode
still matches the current one. So unless we reset the layer2 field,
re-probing the card back to its previous mode is currently not possible.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_sys.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index c3f18afb368b..cfb659747693 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -426,6 +426,7 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 	if (card->discipline) {
 		card->discipline->remove(card->gdev);
 		qeth_core_free_discipline(card);
+		card->options.layer2 = -1;
 	}
 
 	rc = qeth_core_load_discipline(card, newdis);
-- 
cgit v1.2.3


From addc5ee87242a3592fdc9134ddff54c7aa372805 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:50 +0200
Subject: s390/qeth: remove redundant netif_carrier_ok() checks

netif_carrier_off() does its own checking.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 2 +-
 drivers/s390/net/qeth_l2_main.c   | 2 +-
 drivers/s390/net/qeth_l3_main.c   | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index f7ddd6455638..7c3b643550f6 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -653,7 +653,7 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 						cmd->hdr.return_code, card);
 				}
 				card->lan_online = 0;
-				if (card->dev && netif_carrier_ok(card->dev))
+				if (card->dev)
 					netif_carrier_off(card->dev);
 				return NULL;
 			case IPA_CMD_STARTLAN:
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8ac243de7a9e..089bde458fd5 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1163,7 +1163,7 @@ static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev,
 	QETH_DBF_TEXT(SETUP, 3, "setoffl");
 	QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *));
 
-	if (card->dev && netif_carrier_ok(card->dev))
+	if (card->dev)
 		netif_carrier_off(card->dev);
 	recover_flag = card->state;
 	if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 062f62b49294..ee99af08b2c4 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2773,7 +2773,7 @@ static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev,
 	QETH_DBF_TEXT(SETUP, 3, "setoffl");
 	QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *));
 
-	if (card->dev && netif_carrier_ok(card->dev))
+	if (card->dev)
 		netif_carrier_off(card->dev);
 	recover_flag = card->state;
 	if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
-- 
cgit v1.2.3


From d3d1b205e89f1e4194b9f8924022c77ea749d113 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:51 +0200
Subject: s390/qeth: allocate netdevice early

Allocation of the netdevice is currently delayed until a qeth card first
goes online. This complicates matters in several places, where we need
to cache values instead of applying them straight to the netdevice.

Improve on this by moving the allocation up to where the qeth card
itself is created. This is also one step in direction of eventually
placing the qeth card into netdev_priv().

In all subsequent code, remove the now redundant checks whether
card->dev is valid.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  1 +
 drivers/s390/net/qeth_core_main.c | 61 ++++++++++++++++++++++++++++++++-------
 drivers/s390/net/qeth_core_sys.c  | 14 +++++++--
 drivers/s390/net/qeth_l2_main.c   | 52 +++++++++------------------------
 drivers/s390/net/qeth_l3_main.c   | 48 ++++++++++--------------------
 drivers/s390/net/qeth_l3_sys.c    |  6 ++--
 6 files changed, 94 insertions(+), 88 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index a932aac62d0e..4d6827c8aba4 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -966,6 +966,7 @@ extern struct qeth_card_list_struct qeth_core_card_list;
 extern struct kmem_cache *qeth_core_header_cache;
 extern struct qeth_dbf_info qeth_dbf[QETH_DBF_INFOS];
 
+struct net_device *qeth_clone_netdev(struct net_device *orig);
 void qeth_set_recovery_task(struct qeth_card *);
 void qeth_clear_recovery_task(struct qeth_card *);
 void qeth_set_allowed_threads(struct qeth_card *, unsigned long , int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 7c3b643550f6..6df2226417f1 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -653,8 +653,7 @@ static struct qeth_ipa_cmd *qeth_check_ipa_data(struct qeth_card *card,
 						cmd->hdr.return_code, card);
 				}
 				card->lan_online = 0;
-				if (card->dev)
-					netif_carrier_off(card->dev);
+				netif_carrier_off(card->dev);
 				return NULL;
 			case IPA_CMD_STARTLAN:
 				dev_info(&card->gdev->dev,
@@ -2350,9 +2349,8 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply,
 		}
 		if (card->info.initial_mtu && (card->info.initial_mtu != mtu)) {
 			/* frame size has changed */
-			if (card->dev &&
-			    ((card->dev->mtu == card->info.initial_mtu) ||
-			     (card->dev->mtu > mtu)))
+			if ((card->dev->mtu == card->info.initial_mtu) ||
+			    (card->dev->mtu > mtu))
 				card->dev->mtu = mtu;
 			qeth_free_qdio_buffers(card);
 		}
@@ -3578,7 +3576,7 @@ static void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue,
 {
 	struct qeth_card *card = (struct qeth_card *)card_ptr;
 
-	if (card->dev && (card->dev->flags & IFF_UP))
+	if (card->dev->flags & IFF_UP)
 		napi_schedule(&card->napi);
 }
 
@@ -4794,9 +4792,6 @@ int qeth_vm_request_mac(struct qeth_card *card)
 
 	QETH_DBF_TEXT(SETUP, 2, "vmreqmac");
 
-	if (!card->dev)
-		return -ENODEV;
-
 	request = kzalloc(sizeof(*request), GFP_KERNEL | GFP_DMA);
 	response = kzalloc(sizeof(*response), GFP_KERNEL | GFP_DMA);
 	if (!request || !response) {
@@ -5676,6 +5671,44 @@ static void qeth_clear_dbf_list(void)
 	mutex_unlock(&qeth_dbf_list_mutex);
 }
 
+static struct net_device *qeth_alloc_netdev(struct qeth_card *card)
+{
+	struct net_device *dev;
+
+	switch (card->info.type) {
+	case QETH_CARD_TYPE_IQD:
+		dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN, ether_setup);
+		break;
+	case QETH_CARD_TYPE_OSN:
+		dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN, ether_setup);
+		break;
+	default:
+		dev = alloc_etherdev(0);
+	}
+
+	if (!dev)
+		return NULL;
+
+	dev->ml_priv = card;
+	dev->watchdog_timeo = QETH_TX_TIMEOUT;
+	dev->min_mtu = 64;
+	dev->max_mtu = ETH_MAX_MTU;
+	SET_NETDEV_DEV(dev, &card->gdev->dev);
+	netif_carrier_off(dev);
+	return dev;
+}
+
+struct net_device *qeth_clone_netdev(struct net_device *orig)
+{
+	struct net_device *clone = qeth_alloc_netdev(orig->ml_priv);
+
+	if (!clone)
+		return NULL;
+
+	clone->dev_port = orig->dev_port;
+	return clone;
+}
+
 static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card;
@@ -5725,6 +5758,10 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		goto err_card;
 	}
 
+	card->dev = qeth_alloc_netdev(card);
+	if (!card->dev)
+		goto err_card;
+
 	qeth_determine_capabilities(card);
 	enforced_disc = qeth_enforce_discipline(card);
 	switch (enforced_disc) {
@@ -5735,7 +5772,7 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 		card->info.layer_enforced = true;
 		rc = qeth_core_load_discipline(card, enforced_disc);
 		if (rc)
-			goto err_card;
+			goto err_load;
 
 		gdev->dev.type = (card->info.type != QETH_CARD_TYPE_OSN)
 					? card->discipline->devtype
@@ -5753,6 +5790,8 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 
 err_disc:
 	qeth_core_free_discipline(card);
+err_load:
+	free_netdev(card->dev);
 err_card:
 	qeth_core_free_card(card);
 err_dev:
@@ -5775,10 +5814,10 @@ static void qeth_core_remove_device(struct ccwgroup_device *gdev)
 	write_lock_irqsave(&qeth_core_card_list.rwlock, flags);
 	list_del(&card->list);
 	write_unlock_irqrestore(&qeth_core_card_list.rwlock, flags);
+	free_netdev(card->dev);
 	qeth_core_free_card(card);
 	dev_set_drvdata(&gdev->dev, NULL);
 	put_device(&gdev->dev);
-	return;
 }
 
 static int qeth_core_set_online(struct ccwgroup_device *gdev)
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index cfb659747693..9bef19ed7e04 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -144,8 +144,7 @@ static ssize_t qeth_dev_portno_store(struct device *dev,
 		goto out;
 	}
 	card->info.portno = portno;
-	if (card->dev)
-		card->dev->dev_port = portno;
+	card->dev->dev_port = portno;
 out:
 	mutex_unlock(&card->conf_mutex);
 	return rc ? rc : count;
@@ -388,6 +387,7 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 		struct device_attribute *attr, const char *buf, size_t count)
 {
 	struct qeth_card *card = dev_get_drvdata(dev);
+	struct net_device *ndev;
 	char *tmp;
 	int i, rc = 0;
 	enum qeth_discipline_id newdis;
@@ -424,9 +424,19 @@ static ssize_t qeth_dev_layer2_store(struct device *dev,
 
 	card->info.mac_bits = 0;
 	if (card->discipline) {
+		/* start with a new, pristine netdevice: */
+		ndev = qeth_clone_netdev(card->dev);
+		if (!ndev) {
+			rc = -ENOMEM;
+			goto out;
+		}
+
 		card->discipline->remove(card->gdev);
 		qeth_core_free_discipline(card);
 		card->options.layer2 = -1;
+
+		free_netdev(card->dev);
+		card->dev = ndev;
 	}
 
 	rc = qeth_core_load_discipline(card, newdis);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 089bde458fd5..8392fc7e809c 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -899,13 +899,7 @@ static void qeth_l2_remove_device(struct ccwgroup_device *cgdev)
 
 	if (cgdev->state == CCWGROUP_ONLINE)
 		qeth_l2_set_offline(cgdev);
-
-	if (card->dev) {
-		unregister_netdev(card->dev);
-		free_netdev(card->dev);
-		card->dev = NULL;
-	}
-	return;
+	unregister_netdev(card->dev);
 }
 
 static const struct ethtool_ops qeth_l2_ethtool_ops = {
@@ -944,29 +938,13 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 
 static int qeth_l2_setup_netdev(struct qeth_card *card)
 {
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_IQD:
-		card->dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN,
-					 ether_setup);
-		break;
-	case QETH_CARD_TYPE_OSN:
-		card->dev = alloc_netdev(0, "osn%d", NET_NAME_UNKNOWN,
-					 ether_setup);
-		break;
-	default:
-		card->dev = alloc_etherdev(0);
-	}
+	int rc;
 
-	if (!card->dev)
-		return -ENODEV;
+	if (card->dev->netdev_ops)
+		return 0;
 
-	card->dev->ml_priv = card;
 	card->dev->priv_flags |= IFF_UNICAST_FLT;
-	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	card->dev->mtu = card->info.initial_mtu;
-	card->dev->min_mtu = 64;
-	card->dev->max_mtu = ETH_MAX_MTU;
-	card->dev->dev_port = card->info.portno;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
 	if (card->info.type == QETH_CARD_TYPE_OSN) {
 		card->dev->ethtool_ops = &qeth_l2_osn_ops;
@@ -1006,12 +984,12 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 		card->dev->vlan_features |= NETIF_F_RXCSUM;
 	}
 
-	card->info.broadcast_capable = 1;
 	qeth_l2_request_initial_mac(card);
-	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
-	netif_carrier_off(card->dev);
-	return register_netdev(card->dev);
+	rc = register_netdev(card->dev);
+	if (rc)
+		card->dev->netdev_ops = NULL;
+	return rc;
 }
 
 static int qeth_l2_start_ipassists(struct qeth_card *card)
@@ -1057,10 +1035,9 @@ static int __qeth_l2_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		dev_info(&card->gdev->dev,
 		"The device represents a Bridge Capable Port\n");
 
-	if (!card->dev && qeth_l2_setup_netdev(card)) {
-		rc = -ENODEV;
+	rc = qeth_l2_setup_netdev(card);
+	if (rc)
 		goto out_remove;
-	}
 
 	if (card->info.type != QETH_CARD_TYPE_OSN &&
 	    !qeth_l2_send_setmac(card, card->dev->dev_addr))
@@ -1163,8 +1140,7 @@ static int __qeth_l2_set_offline(struct ccwgroup_device *cgdev,
 	QETH_DBF_TEXT(SETUP, 3, "setoffl");
 	QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *));
 
-	if (card->dev)
-		netif_carrier_off(card->dev);
+	netif_carrier_off(card->dev);
 	recover_flag = card->state;
 	if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
@@ -1237,8 +1213,7 @@ static int qeth_l2_pm_suspend(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 
-	if (card->dev)
-		netif_device_detach(card->dev);
+	netif_device_detach(card->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 	if (gdev->state == CCWGROUP_OFFLINE)
@@ -1271,8 +1246,7 @@ static int qeth_l2_pm_resume(struct ccwgroup_device *gdev)
 		rc = __qeth_l2_set_online(card->gdev, 0);
 out:
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
-	if (card->dev)
-		netif_device_attach(card->dev);
+	netif_device_attach(card->dev);
 	if (rc)
 		dev_warn(&card->gdev->dev, "The qeth device driver "
 			"failed to recover an error on the device\n");
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index ee99af08b2c4..72c8f323801b 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2536,6 +2536,9 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 {
 	int rc;
 
+	if (card->dev->netdev_ops)
+		return 0;
+
 	if (card->info.type == QETH_CARD_TYPE_OSD ||
 	    card->info.type == QETH_CARD_TYPE_OSX) {
 		if ((card->info.link_type == QETH_LINK_TYPE_LANE_TR) ||
@@ -2544,9 +2547,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 			return -ENODEV;
 		}
 
-		card->dev = alloc_etherdev(0);
-		if (!card->dev)
-			return -ENODEV;
 		card->dev->netdev_ops = &qeth_l3_osa_netdev_ops;
 
 		/*IPv6 address autoconfiguration stuff*/
@@ -2567,27 +2567,19 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 			card->dev->vlan_features |= NETIF_F_IPV6_CSUM;
 		}
 	} else if (card->info.type == QETH_CARD_TYPE_IQD) {
-		card->dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN,
-					 ether_setup);
-		if (!card->dev)
-			return -ENODEV;
 		card->dev->flags |= IFF_NOARP;
 		card->dev->netdev_ops = &qeth_l3_netdev_ops;
 
 		rc = qeth_l3_iqd_read_initial_mac(card);
 		if (rc)
-			return rc;
+			goto out;
+
 		if (card->options.hsuid[0])
 			memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 	} else
 		return -ENODEV;
 
-	card->dev->ml_priv = card;
-	card->dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	card->dev->mtu = card->info.initial_mtu;
-	card->dev->min_mtu = 64;
-	card->dev->max_mtu = ETH_MAX_MTU;
-	card->dev->dev_port = card->info.portno;
 	card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
 	card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
@@ -2602,10 +2594,12 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 		netif_set_gso_max_size(card->dev,
 				       PAGE_SIZE * (QETH_MAX_BUFFER_ELEMENTS(card) - 1));
 
-	SET_NETDEV_DEV(card->dev, &card->gdev->dev);
 	netif_napi_add(card->dev, &card->napi, qeth_poll, QETH_NAPI_WEIGHT);
-	netif_carrier_off(card->dev);
-	return register_netdev(card->dev);
+	rc = register_netdev(card->dev);
+out:
+	if (rc)
+		card->dev->netdev_ops = NULL;
+	return rc;
 }
 
 static const struct device_type qeth_l3_devtype = {
@@ -2643,15 +2637,9 @@ static void qeth_l3_remove_device(struct ccwgroup_device *cgdev)
 	if (cgdev->state == CCWGROUP_ONLINE)
 		qeth_l3_set_offline(cgdev);
 
-	if (card->dev) {
-		unregister_netdev(card->dev);
-		free_netdev(card->dev);
-		card->dev = NULL;
-	}
-
+	unregister_netdev(card->dev);
 	qeth_l3_clear_ip_htable(card, 0);
 	qeth_l3_clear_ipato_list(card);
-	return;
 }
 
 static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
@@ -2673,10 +2661,9 @@ static int __qeth_l3_set_online(struct ccwgroup_device *gdev, int recovery_mode)
 		goto out_remove;
 	}
 
-	if (!card->dev && qeth_l3_setup_netdev(card)) {
-		rc = -ENODEV;
+	rc = qeth_l3_setup_netdev(card);
+	if (rc)
 		goto out_remove;
-	}
 
 	if (qeth_is_diagass_supported(card, QETH_DIAGS_CMD_TRAP)) {
 		if (card->info.hwtrap &&
@@ -2773,8 +2760,7 @@ static int __qeth_l3_set_offline(struct ccwgroup_device *cgdev,
 	QETH_DBF_TEXT(SETUP, 3, "setoffl");
 	QETH_DBF_HEX(SETUP, 3, &card, sizeof(void *));
 
-	if (card->dev)
-		netif_carrier_off(card->dev);
+	netif_carrier_off(card->dev);
 	recover_flag = card->state;
 	if ((!recovery_mode && card->info.hwtrap) || card->info.hwtrap == 2) {
 		qeth_hw_trap(card, QETH_DIAGS_TRAP_DISARM);
@@ -2842,8 +2828,7 @@ static int qeth_l3_pm_suspend(struct ccwgroup_device *gdev)
 {
 	struct qeth_card *card = dev_get_drvdata(&gdev->dev);
 
-	if (card->dev)
-		netif_device_detach(card->dev);
+	netif_device_detach(card->dev);
 	qeth_set_allowed_threads(card, 0, 1);
 	wait_event(card->wait_q, qeth_threads_running(card, 0xffffffff) == 0);
 	if (gdev->state == CCWGROUP_OFFLINE)
@@ -2876,8 +2861,7 @@ static int qeth_l3_pm_resume(struct ccwgroup_device *gdev)
 		rc = __qeth_l3_set_online(card->gdev, 0);
 out:
 	qeth_set_allowed_threads(card, 0xffffffff, 0);
-	if (card->dev)
-		netif_device_attach(card->dev);
+	netif_device_attach(card->dev);
 	if (rc)
 		dev_warn(&card->gdev->dev, "The qeth device driver "
 			"failed to recover an error on the device\n");
diff --git a/drivers/s390/net/qeth_l3_sys.c b/drivers/s390/net/qeth_l3_sys.c
index f61192a048f4..45ac6d8705c6 100644
--- a/drivers/s390/net/qeth_l3_sys.c
+++ b/drivers/s390/net/qeth_l3_sys.c
@@ -299,8 +299,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 	if (strlen(tmp) == 0) {
 		/* delete ip address only */
 		card->options.hsuid[0] = '\0';
-		if (card->dev)
-			memcpy(card->dev->perm_addr, card->options.hsuid, 9);
+		memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 		qeth_configure_cq(card, QETH_CQ_DISABLED);
 		return count;
 	}
@@ -311,8 +310,7 @@ static ssize_t qeth_l3_dev_hsuid_store(struct device *dev,
 	snprintf(card->options.hsuid, sizeof(card->options.hsuid),
 		 "%-8s", tmp);
 	ASCEBC(card->options.hsuid, 8);
-	if (card->dev)
-		memcpy(card->dev->perm_addr, card->options.hsuid, 9);
+	memcpy(card->dev->perm_addr, card->options.hsuid, 9);
 
 	rc = qeth_l3_modify_hsuid(card, true);
 
-- 
cgit v1.2.3


From 92d2720969bc741c8aa7269cb3561c49227cd04f Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:52 +0200
Subject: s390/qeth: don't cache HW port number

The netdevice is always available now, so get the portno from there.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      | 1 -
 drivers/s390/net/qeth_core_main.c | 7 +++----
 drivers/s390/net/qeth_core_sys.c  | 3 +--
 3 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 4d6827c8aba4..04b900c7060d 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -658,7 +658,6 @@ struct qeth_card_info {
 	char mcl_level[QETH_MCL_LENGTH + 1];
 	int guestlan;
 	int mac_bits;
-	int portno;
 	enum qeth_card_types type;
 	enum qeth_link_types link_type;
 	int initial_mtu;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 6df2226417f1..39c429787c4d 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1920,7 +1920,7 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 		memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
 		       &card->seqno.trans_hdr, QETH_SEQ_NO_LENGTH);
 	}
-	tmp = ((__u8)card->info.portno) | 0x80;
+	tmp = ((u8)card->dev->dev_port) | 0x80;
 	memcpy(QETH_IDX_ACT_PNO(iob->data), &tmp, 1);
 	memcpy(QETH_IDX_ACT_ISSUER_RM_TOKEN(iob->data),
 	       &card->token.issuer_rm_w, QETH_MPC_TOKEN_LENGTH);
@@ -2389,8 +2389,7 @@ static int qeth_ulp_enable(struct qeth_card *card)
 	iob = qeth_wait_for_buffer(&card->write);
 	memcpy(iob->data, ULP_ENABLE, ULP_ENABLE_SIZE);
 
-	*(QETH_ULP_ENABLE_LINKNUM(iob->data)) =
-		(__u8) card->info.portno;
+	*(QETH_ULP_ENABLE_LINKNUM(iob->data)) = (u8) card->dev->dev_port;
 	if (card->options.layer2)
 		if (card->info.type == QETH_CARD_TYPE_OSN)
 			prot_type = QETH_PROT_OSN2;
@@ -2918,7 +2917,7 @@ static void qeth_fill_ipacmd_header(struct qeth_card *card,
 	cmd->hdr.initiator = IPA_CMD_INITIATOR_HOST;
 	/* cmd->hdr.seqno is set by qeth_send_control_data() */
 	cmd->hdr.adapter_type = qeth_get_ipa_adp_type(card->info.link_type);
-	cmd->hdr.rel_adapter_no = (__u8) card->info.portno;
+	cmd->hdr.rel_adapter_no = (u8) card->dev->dev_port;
 	if (card->options.layer2)
 		cmd->hdr.prim_version_no = 2;
 	else
diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c
index 9bef19ed7e04..25d0be25bcb3 100644
--- a/drivers/s390/net/qeth_core_sys.c
+++ b/drivers/s390/net/qeth_core_sys.c
@@ -112,7 +112,7 @@ static ssize_t qeth_dev_portno_show(struct device *dev,
 	if (!card)
 		return -EINVAL;
 
-	return sprintf(buf, "%i\n", card->info.portno);
+	return sprintf(buf, "%i\n", card->dev->dev_port);
 }
 
 static ssize_t qeth_dev_portno_store(struct device *dev,
@@ -143,7 +143,6 @@ static ssize_t qeth_dev_portno_store(struct device *dev,
 		rc = -EINVAL;
 		goto out;
 	}
-	card->info.portno = portno;
 	card->dev->dev_port = portno;
 out:
 	mutex_unlock(&card->conf_mutex);
-- 
cgit v1.2.3


From 8ce7a9e064db4a31e9d9d08300e2f3e9679eaffe Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:53 +0200
Subject: s390/qeth: simplify max MTU handling

When the MPC initialization code discovers the HW-specific max MTU,
apply the resulting changes straight to the netdevice.

If this is the device's first initialization, also set its MTU
(HiperSockets: the max MTU; else: a layer-specific default value).
Then cap the current MTU by the new max MTU.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 -
 drivers/s390/net/qeth_core_main.c | 82 +++++++++++++++++++++------------------
 drivers/s390/net/qeth_l2_main.c   |  1 -
 drivers/s390/net/qeth_l3_main.c   |  1 -
 4 files changed, 45 insertions(+), 41 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 04b900c7060d..6f02a6cbe59e 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -660,8 +660,6 @@ struct qeth_card_info {
 	int mac_bits;
 	enum qeth_card_types type;
 	enum qeth_link_types link_type;
-	int initial_mtu;
-	int max_mtu;
 	int broadcast_capable;
 	int unique_id;
 	bool layer_enforced;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 39c429787c4d..ab3d63f98779 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2278,19 +2278,42 @@ static int qeth_cm_setup(struct qeth_card *card)
 
 }
 
-static int qeth_get_initial_mtu_for_card(struct qeth_card *card)
+static int qeth_update_max_mtu(struct qeth_card *card, unsigned int max_mtu)
 {
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_IQD:
-		return card->info.max_mtu;
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSX:
-		if (!card->options.layer2)
-			return ETH_DATA_LEN - 8; /* L3: allow for LLC + SNAP */
-		/* fall through */
-	default:
-		return ETH_DATA_LEN;
+	struct net_device *dev = card->dev;
+	unsigned int new_mtu;
+
+	if (!max_mtu) {
+		/* IQD needs accurate max MTU to set up its RX buffers: */
+		if (IS_IQD(card))
+			return -EINVAL;
+		/* tolerate quirky HW: */
+		max_mtu = ETH_MAX_MTU;
+	}
+
+	rtnl_lock();
+	if (IS_IQD(card)) {
+		/* move any device with default MTU to new max MTU: */
+		new_mtu = (dev->mtu == dev->max_mtu) ? max_mtu : dev->mtu;
+
+		/* adjust RX buffer size to new max MTU: */
+		card->qdio.in_buf_size = max_mtu + 2 * PAGE_SIZE;
+		if (dev->max_mtu && dev->max_mtu != max_mtu)
+			qeth_free_qdio_buffers(card);
+	} else {
+		if (dev->mtu)
+			new_mtu = dev->mtu;
+		/* default MTUs for first setup: */
+		else if (card->options.layer2)
+			new_mtu = ETH_DATA_LEN;
+		else
+			new_mtu = ETH_DATA_LEN - 8; /* allow for LLC + SNAP */
 	}
+
+	dev->max_mtu = max_mtu;
+	dev->mtu = min(new_mtu, max_mtu);
+	rtnl_unlock();
+	return 0;
 }
 
 static int qeth_get_mtu_outof_framesize(int framesize)
@@ -2316,8 +2339,7 @@ static int qeth_mtu_is_valid(struct qeth_card *card, int mtu)
 	case QETH_CARD_TYPE_OSM:
 	case QETH_CARD_TYPE_OSX:
 	case QETH_CARD_TYPE_IQD:
-		return ((mtu >= 576) &&
-			(mtu <= card->info.max_mtu));
+		return ((mtu >= 576) && (mtu <= card->dev->max_mtu));
 	case QETH_CARD_TYPE_OSN:
 	default:
 		return 1;
@@ -2342,28 +2364,10 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply,
 	if (card->info.type == QETH_CARD_TYPE_IQD) {
 		memcpy(&framesize, QETH_ULP_ENABLE_RESP_MAX_MTU(iob->data), 2);
 		mtu = qeth_get_mtu_outof_framesize(framesize);
-		if (!mtu) {
-			iob->rc = -EINVAL;
-			QETH_DBF_TEXT_(SETUP, 2, "  rc%d", iob->rc);
-			return 0;
-		}
-		if (card->info.initial_mtu && (card->info.initial_mtu != mtu)) {
-			/* frame size has changed */
-			if ((card->dev->mtu == card->info.initial_mtu) ||
-			    (card->dev->mtu > mtu))
-				card->dev->mtu = mtu;
-			qeth_free_qdio_buffers(card);
-		}
-		card->info.initial_mtu = mtu;
-		card->info.max_mtu = mtu;
-		card->qdio.in_buf_size = mtu + 2 * PAGE_SIZE;
 	} else {
-		card->info.max_mtu = *(__u16 *)QETH_ULP_ENABLE_RESP_MAX_MTU(
-			iob->data);
-		card->info.initial_mtu = min(card->info.max_mtu,
-					qeth_get_initial_mtu_for_card(card));
-		card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT;
+		mtu = *(__u16 *)QETH_ULP_ENABLE_RESP_MAX_MTU(iob->data);
 	}
+	*(u16 *)reply->param = mtu;
 
 	memcpy(&len, QETH_ULP_ENABLE_RESP_DIFINFO_LEN(iob->data), 2);
 	if (len >= QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE) {
@@ -2382,6 +2386,7 @@ static int qeth_ulp_enable(struct qeth_card *card)
 	int rc;
 	char prot_type;
 	struct qeth_cmd_buffer *iob;
+	u16 max_mtu;
 
 	/*FIXME: trace view callbacks*/
 	QETH_DBF_TEXT(SETUP, 2, "ulpenabl");
@@ -2404,9 +2409,10 @@ static int qeth_ulp_enable(struct qeth_card *card)
 	memcpy(QETH_ULP_ENABLE_FILTER_TOKEN(iob->data),
 	       &card->token.ulp_filter_w, QETH_MPC_TOKEN_LENGTH);
 	rc = qeth_send_control_data(card, ULP_ENABLE_SIZE, iob,
-				    qeth_ulp_enable_cb, NULL);
-	return rc;
-
+				    qeth_ulp_enable_cb, &max_mtu);
+	if (rc)
+		return rc;
+	return qeth_update_max_mtu(card, max_mtu);
 }
 
 static int qeth_ulp_setup_cb(struct qeth_card *card, struct qeth_reply *reply,
@@ -5691,7 +5697,9 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card)
 	dev->ml_priv = card;
 	dev->watchdog_timeo = QETH_TX_TIMEOUT;
 	dev->min_mtu = 64;
-	dev->max_mtu = ETH_MAX_MTU;
+	 /* initialized when device first goes online: */
+	dev->max_mtu = 0;
+	dev->mtu = 0;
 	SET_NETDEV_DEV(dev, &card->gdev->dev);
 	netif_carrier_off(dev);
 	return dev;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 8392fc7e809c..00d8bb1d2a41 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -944,7 +944,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 		return 0;
 
 	card->dev->priv_flags |= IFF_UNICAST_FLT;
-	card->dev->mtu = card->info.initial_mtu;
 	card->dev->netdev_ops = &qeth_l2_netdev_ops;
 	if (card->info.type == QETH_CARD_TYPE_OSN) {
 		card->dev->ethtool_ops = &qeth_l2_osn_ops;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 72c8f323801b..e5fa8e5ac1b3 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2579,7 +2579,6 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 	} else
 		return -ENODEV;
 
-	card->dev->mtu = card->info.initial_mtu;
 	card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
 	card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
-- 
cgit v1.2.3


From 72f219da79d22384bbc809fc67ed305dbe824e39 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:54 +0200
Subject: s390/qeth: use core MTU range checking

qeth's ndo_change_mtu() only applies some trivial bounds checking. Set
up dev->min_mtu properly, so that dev_set_mtu() can do this for us.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  1 -
 drivers/s390/net/qeth_core_main.c | 34 +---------------------------------
 drivers/s390/net/qeth_core_mpc.h  |  1 +
 drivers/s390/net/qeth_l2_main.c   |  1 -
 drivers/s390/net/qeth_l3_main.c   |  2 --
 5 files changed, 2 insertions(+), 37 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 6f02a6cbe59e..994ac7f434d5 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -993,7 +993,6 @@ void qeth_clear_cmd_buffers(struct qeth_channel *);
 void qeth_clear_qdio_buffers(struct qeth_card *);
 void qeth_setadp_promisc_mode(struct qeth_card *);
 struct net_device_stats *qeth_get_stats(struct net_device *);
-int qeth_change_mtu(struct net_device *, int);
 int qeth_setadpparms_change_macaddr(struct qeth_card *);
 void qeth_tx_timeout(struct net_device *);
 void qeth_prepare_control_data(struct qeth_card *, int,
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index ab3d63f98779..717511c167e7 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2332,20 +2332,6 @@ static int qeth_get_mtu_outof_framesize(int framesize)
 	}
 }
 
-static int qeth_mtu_is_valid(struct qeth_card *card, int mtu)
-{
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_OSD:
-	case QETH_CARD_TYPE_OSM:
-	case QETH_CARD_TYPE_OSX:
-	case QETH_CARD_TYPE_IQD:
-		return ((mtu >= 576) && (mtu <= card->dev->max_mtu));
-	case QETH_CARD_TYPE_OSN:
-	default:
-		return 1;
-	}
-}
-
 static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply,
 		unsigned long data)
 {
@@ -4204,24 +4190,6 @@ void qeth_setadp_promisc_mode(struct qeth_card *card)
 }
 EXPORT_SYMBOL_GPL(qeth_setadp_promisc_mode);
 
-int qeth_change_mtu(struct net_device *dev, int new_mtu)
-{
-	struct qeth_card *card;
-	char dbf_text[15];
-
-	card = dev->ml_priv;
-
-	QETH_CARD_TEXT(card, 4, "chgmtu");
-	sprintf(dbf_text, "%8x", new_mtu);
-	QETH_CARD_TEXT(card, 4, dbf_text);
-
-	if (!qeth_mtu_is_valid(card, new_mtu))
-		return -EINVAL;
-	dev->mtu = new_mtu;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(qeth_change_mtu);
-
 struct net_device_stats *qeth_get_stats(struct net_device *dev)
 {
 	struct qeth_card *card;
@@ -5696,7 +5664,7 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card)
 
 	dev->ml_priv = card;
 	dev->watchdog_timeo = QETH_TX_TIMEOUT;
-	dev->min_mtu = 64;
+	dev->min_mtu = IS_OSN(card) ? 64 : 576;
 	 /* initialized when device first goes online: */
 	dev->max_mtu = 0;
 	dev->mtu = 0;
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index 54c35224262a..cf5ad94e960a 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -65,6 +65,7 @@ enum qeth_card_types {
 };
 
 #define IS_IQD(card)	((card)->info.type == QETH_CARD_TYPE_IQD)
+#define IS_OSN(card)	((card)->info.type == QETH_CARD_TYPE_OSN)
 
 #define QETH_MPC_DIFINFO_LEN_INDICATES_LINK_TYPE 0x18
 /* only the first two bytes are looked at in qeth_get_cardname_short */
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 00d8bb1d2a41..668f80680575 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -928,7 +928,6 @@ static const struct net_device_ops qeth_l2_netdev_ops = {
 	.ndo_set_rx_mode	= qeth_l2_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
 	.ndo_set_mac_address    = qeth_l2_set_mac_address,
-	.ndo_change_mtu	   	= qeth_change_mtu,
 	.ndo_vlan_rx_add_vid	= qeth_l2_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = qeth_l2_vlan_rx_kill_vid,
 	.ndo_tx_timeout	   	= qeth_tx_timeout,
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index e5fa8e5ac1b3..078b891a6d24 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2506,7 +2506,6 @@ static const struct net_device_ops qeth_l3_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
-	.ndo_change_mtu		= qeth_change_mtu,
 	.ndo_fix_features	= qeth_fix_features,
 	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
@@ -2523,7 +2522,6 @@ static const struct net_device_ops qeth_l3_osa_netdev_ops = {
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_rx_mode	= qeth_l3_set_rx_mode,
 	.ndo_do_ioctl		= qeth_do_ioctl,
-	.ndo_change_mtu		= qeth_change_mtu,
 	.ndo_fix_features	= qeth_fix_features,
 	.ndo_set_features	= qeth_set_features,
 	.ndo_vlan_rx_add_vid	= qeth_l3_vlan_rx_add_vid,
-- 
cgit v1.2.3


From d2a274b25be7218f8400037868a756640e8a4b0d Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:55 +0200
Subject: s390/qeth: add statistics for consumed buffer elements

Nowadays an skb fragment typically spans over multiple pages. So replace
the obsolete, SG-only 'fragments' counter with one that tracks the
consumed buffer elements. This is what actually matters for performance.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 +-
 drivers/s390/net/qeth_core_main.c |  4 ++--
 drivers/s390/net/qeth_l2_main.c   | 13 +++++++------
 drivers/s390/net/qeth_l3_main.c   | 28 ++++++++++++++--------------
 4 files changed, 24 insertions(+), 23 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 994ac7f434d5..6d8005af67f5 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -104,6 +104,7 @@ struct qeth_dbf_info {
 struct qeth_perf_stats {
 	unsigned int bufs_rec;
 	unsigned int bufs_sent;
+	unsigned int buf_elements_sent;
 
 	unsigned int skbs_sent_pack;
 	unsigned int bufs_sent_pack;
@@ -137,7 +138,6 @@ struct qeth_perf_stats {
 	unsigned int large_send_bytes;
 	unsigned int large_send_cnt;
 	unsigned int sg_skbs_sent;
-	unsigned int sg_frags_sent;
 	/* initial values when measuring starts */
 	unsigned long initial_rx_packets;
 	unsigned long initial_tx_packets;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 717511c167e7..84f1e1e33f3f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5970,7 +5970,7 @@ static struct {
 	{"tx skbs packing"},
 	{"tx buffers packing"},
 	{"tx sg skbs"},
-	{"tx sg frags"},
+	{"tx buffer elements"},
 /* 10 */{"rx sg skbs"},
 	{"rx sg frags"},
 	{"rx sg page allocs"},
@@ -6029,7 +6029,7 @@ void qeth_core_get_ethtool_stats(struct net_device *dev,
 	data[6] = card->perf_stats.skbs_sent_pack;
 	data[7] = card->perf_stats.bufs_sent_pack;
 	data[8] = card->perf_stats.sg_skbs_sent;
-	data[9] = card->perf_stats.sg_frags_sent;
+	data[9] = card->perf_stats.buf_elements_sent;
 	data[10] = card->perf_stats.sg_skbs_rx;
 	data[11] = card->perf_stats.sg_frags_rx;
 	data[12] = card->perf_stats.sg_alloc_page_rx;
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 668f80680575..a785c5ff73cd 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -672,10 +672,11 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 			    int ipv)
 {
 	int push_len = sizeof(struct qeth_hdr);
-	unsigned int elements, nr_frags;
 	unsigned int hdr_elements = 0;
 	struct qeth_hdr *hdr = NULL;
 	unsigned int hd_len = 0;
+	unsigned int elements;
+	bool is_sg;
 	int rc;
 
 	/* fix hardware limitation: as long as we do not have sbal
@@ -693,7 +694,6 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 		if (rc)
 			return rc;
 	}
-	nr_frags = skb_shinfo(skb)->nr_frags;
 
 	rc = skb_cow_head(skb, push_len);
 	if (rc)
@@ -720,15 +720,16 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 	}
 	elements += hdr_elements;
 
+	is_sg = skb_is_nonlinear(skb);
 	/* TODO: remove the skb_orphan() once TX completion is fast enough */
 	skb_orphan(skb);
 	rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len, elements);
 out:
 	if (!rc) {
-		if (card->options.performance_stats && nr_frags) {
-			card->perf_stats.sg_skbs_sent++;
-			/* nr_frags + skb->data */
-			card->perf_stats.sg_frags_sent += nr_frags + 1;
+		if (card->options.performance_stats) {
+			card->perf_stats.buf_elements_sent += elements;
+			if (is_sg)
+				card->perf_stats.sg_skbs_sent++;
 		}
 	} else {
 		if (hd_len)
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 078b891a6d24..c12aeb7d8f26 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2166,12 +2166,13 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 				int cast_type)
 {
 	const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
-	unsigned int frame_len, nr_frags;
 	unsigned char eth_hdr[ETH_HLEN];
 	unsigned int hdr_elements = 0;
 	struct qeth_hdr *hdr = NULL;
 	int elements, push_len, rc;
 	unsigned int hd_len = 0;
+	unsigned int frame_len;
+	bool is_sg;
 
 	/* compress skb to fit into one IO buffer: */
 	if (!qeth_get_elements_no(card, skb, 0, 0)) {
@@ -2194,7 +2195,6 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 	skb_copy_from_linear_data(skb, eth_hdr, ETH_HLEN);
 	skb_pull(skb, ETH_HLEN);
 	frame_len = skb->len;
-	nr_frags = skb_shinfo(skb)->nr_frags;
 
 	push_len = qeth_push_hdr(skb, &hdr, hw_hdr_len);
 	if (push_len < 0)
@@ -2217,6 +2217,7 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 	else
 		qeth_l3_fill_header(card, hdr, skb, ipv, cast_type, frame_len);
 
+	is_sg = skb_is_nonlinear(skb);
 	if (IS_IQD(card)) {
 		rc = qeth_do_send_packet_fast(queue, skb, hdr, 0, hd_len);
 	} else {
@@ -2227,10 +2228,10 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 	}
 out:
 	if (!rc) {
-		if (card->options.performance_stats && nr_frags) {
-			card->perf_stats.sg_skbs_sent++;
-			/* nr_frags + skb->data */
-			card->perf_stats.sg_frags_sent += nr_frags + 1;
+		if (card->options.performance_stats) {
+			card->perf_stats.buf_elements_sent += elements;
+			if (is_sg)
+				card->perf_stats.sg_skbs_sent++;
 		}
 	} else {
 		if (!push_len)
@@ -2248,14 +2249,14 @@ out:
 static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 			struct qeth_qdio_out_q *queue, int ipv, int cast_type)
 {
-	unsigned int hd_len, nr_frags;
 	int elements, len, rc;
 	__be16 *tag;
 	struct qeth_hdr *hdr = NULL;
 	int hdr_elements = 0;
 	struct sk_buff *new_skb = NULL;
 	int tx_bytes = skb->len;
-	bool use_tso;
+	unsigned int hd_len;
+	bool use_tso, is_sg;
 
 	/* Ignore segment size from skb_is_gso(), 1 page is always used. */
 	use_tso = skb_is_gso(skb) &&
@@ -2297,7 +2298,6 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 		if (rc)
 			goto out;
 	}
-	nr_frags = skb_shinfo(new_skb)->nr_frags;
 
 	if (use_tso) {
 		hdr = skb_push(new_skb, sizeof(struct qeth_hdr_tso));
@@ -2334,6 +2334,8 @@ static int qeth_l3_xmit(struct qeth_card *card, struct sk_buff *skb,
 		rc = -EINVAL;
 		goto out;
 	}
+
+	is_sg = skb_is_nonlinear(new_skb);
 	rc = qeth_do_send_packet(card, queue, new_skb, hdr, hd_len, hd_len,
 				 elements);
 out:
@@ -2341,15 +2343,13 @@ out:
 		if (new_skb != skb)
 			dev_kfree_skb_any(skb);
 		if (card->options.performance_stats) {
+			card->perf_stats.buf_elements_sent += elements;
+			if (is_sg)
+				card->perf_stats.sg_skbs_sent++;
 			if (use_tso) {
 				card->perf_stats.large_send_bytes += tx_bytes;
 				card->perf_stats.large_send_cnt++;
 			}
-			if (nr_frags) {
-				card->perf_stats.sg_skbs_sent++;
-				/* nr_frags + skb->data */
-				card->perf_stats.sg_frags_sent += nr_frags + 1;
-			}
 		}
 	} else {
 		if (new_skb != skb)
-- 
cgit v1.2.3


From ba86ceee9d1b5aa71fe3db75b2ec5452c9a48307 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:56 +0200
Subject: s390/qeth: merge linearize-check into HW header construction

When checking whether an skb needs to be linearized to fit into an IO
buffer, it's desirable to consider the skb's final size and layout
(ie. after the HW header was added). But a subsequent linearization can
then cause the re-positioned HW header to violate its alignment
restrictions.

Dealing with this situation in two different code paths is quite tricky.
This patch integrates a) linearize-check and b) HW header construction
into one 3 step-sequence:
1. evaluate how the HW header needs to be added (to identify if it takes
   up an additional buffer element), then
2. check if the required buffer elements exceed the device's limit.
   Linearize when necessary and re-evaluate the HW header placement.
3. Add the HW header in the best-possible way:
   a) push, without taking up an additional buffer element
   b) push, but consume another buffer element
   c) allocate a header object from the cache.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  4 +-
 drivers/s390/net/qeth_core_main.c | 86 ++++++++++++++++++++++++++++++++-------
 drivers/s390/net/qeth_l2_main.c   | 29 +------------
 drivers/s390/net/qeth_l3_main.c   | 31 ++------------
 4 files changed, 80 insertions(+), 70 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 6d8005af67f5..2a5ec99643df 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1047,7 +1047,9 @@ netdev_features_t qeth_features_check(struct sk_buff *skb,
 				      struct net_device *dev,
 				      netdev_features_t features);
 int qeth_vm_request_mac(struct qeth_card *card);
-int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len);
+int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
+		       struct qeth_hdr **hdr, unsigned int len,
+		       unsigned int *elements);
 
 /* exports for OSN */
 int qeth_osn_assist(struct net_device *, void *, int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 84f1e1e33f3f..e7b34624df1e 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3831,6 +3831,17 @@ int qeth_get_elements_for_frags(struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 
+static unsigned int qeth_count_elements(struct sk_buff *skb, int data_offset)
+{
+	unsigned int elements = qeth_get_elements_for_frags(skb);
+	addr_t end = (addr_t)skb->data + skb_headlen(skb);
+	addr_t start = (addr_t)skb->data + data_offset;
+
+	if (start != end)
+		elements += qeth_get_elements_for_range(start, end);
+	return elements;
+}
+
 /**
  * qeth_get_elements_no() -	find number of SBALEs for skb data, inc. frags.
  * @card:			qeth card structure, to check max. elems.
@@ -3846,12 +3857,7 @@ EXPORT_SYMBOL_GPL(qeth_get_elements_for_frags);
 int qeth_get_elements_no(struct qeth_card *card,
 		     struct sk_buff *skb, int extra_elems, int data_offset)
 {
-	addr_t end = (addr_t)skb->data + skb_headlen(skb);
-	int elements = qeth_get_elements_for_frags(skb);
-	addr_t start = (addr_t)skb->data + data_offset;
-
-	if (start != end)
-		elements += qeth_get_elements_for_range(start, end);
+	int elements = qeth_count_elements(skb, data_offset);
 
 	if ((elements + extra_elems) > QETH_MAX_BUFFER_ELEMENTS(card)) {
 		QETH_DBF_MESSAGE(2, "Invalid size of IP packet "
@@ -3885,22 +3891,72 @@ int qeth_hdr_chk_and_bounce(struct sk_buff *skb, struct qeth_hdr **hdr, int len)
 EXPORT_SYMBOL_GPL(qeth_hdr_chk_and_bounce);
 
 /**
- * qeth_push_hdr() - push a qeth_hdr onto an skb.
- * @skb: skb that the qeth_hdr should be pushed onto.
+ * qeth_add_hw_header() - add a HW header to an skb.
+ * @skb: skb that the HW header should be added to.
  * @hdr: double pointer to a qeth_hdr. When returning with >= 0,
  *	 it contains a valid pointer to a qeth_hdr.
- * @len: length of the hdr that needs to be pushed on.
+ * @len: length of the HW header.
  *
  * Returns the pushed length. If the header can't be pushed on
  * (eg. because it would cross a page boundary), it is allocated from
  * the cache instead and 0 is returned.
+ * The number of needed buffer elements is returned in @elements.
  * Error to create the hdr is indicated by returning with < 0.
  */
-int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len)
-{
-	if (skb_headroom(skb) >= len &&
-	    qeth_get_elements_for_range((addr_t)skb->data - len,
-					(addr_t)skb->data) == 1) {
+int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
+		       struct qeth_hdr **hdr, unsigned int len,
+		       unsigned int *elements)
+{
+	const unsigned int max_elements = QETH_MAX_BUFFER_ELEMENTS(card);
+	unsigned int __elements;
+	addr_t start, end;
+	bool push_ok;
+	int rc;
+
+check_layout:
+	start = (addr_t)skb->data - len;
+	end = (addr_t)skb->data;
+
+	if (qeth_get_elements_for_range(start, end + 1) == 1) {
+		/* Push HW header into same page as first protocol header. */
+		push_ok = true;
+		__elements = qeth_count_elements(skb, 0);
+	} else {
+		__elements = 1 + qeth_count_elements(skb, 0);
+		if (qeth_get_elements_for_range(start, end) == 1)
+			/* Push HW header into a new page. */
+			push_ok = true;
+		else
+			/* Use header cache. */
+			push_ok = false;
+	}
+
+	/* Compress skb to fit into one IO buffer: */
+	if (__elements > max_elements) {
+		if (!skb_is_nonlinear(skb)) {
+			/* Drop it, no easy way of shrinking it further. */
+			QETH_DBF_MESSAGE(2, "Dropped an oversized skb (Max Elements=%u / Actual=%u / Length=%u).\n",
+					 max_elements, __elements, skb->len);
+			return -E2BIG;
+		}
+
+		rc = skb_linearize(skb);
+		if (card->options.performance_stats) {
+			if (rc)
+				card->perf_stats.tx_linfail++;
+			else
+				card->perf_stats.tx_lin++;
+		}
+		if (rc)
+			return rc;
+
+		/* Linearization changed the layout, re-evaluate: */
+		goto check_layout;
+	}
+
+	*elements = __elements;
+	/* Add the header: */
+	if (push_ok) {
 		*hdr = skb_push(skb, len);
 		return len;
 	}
@@ -3910,7 +3966,7 @@ int qeth_push_hdr(struct sk_buff *skb, struct qeth_hdr **hdr, unsigned int len)
 		return -ENOMEM;
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qeth_push_hdr);
+EXPORT_SYMBOL_GPL(qeth_add_hw_header);
 
 static void __qeth_fill_buffer(struct sk_buff *skb,
 			       struct qeth_qdio_out_buffer *buf,
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index a785c5ff73cd..905f3bb3a87c 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -672,39 +672,21 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 			    int ipv)
 {
 	int push_len = sizeof(struct qeth_hdr);
-	unsigned int hdr_elements = 0;
 	struct qeth_hdr *hdr = NULL;
 	unsigned int hd_len = 0;
 	unsigned int elements;
 	bool is_sg;
 	int rc;
 
-	/* fix hardware limitation: as long as we do not have sbal
-	 * chaining we can not send long frag lists
-	 */
-	if (!qeth_get_elements_no(card, skb, 0, 0)) {
-		rc = skb_linearize(skb);
-
-		if (card->options.performance_stats) {
-			if (rc)
-				card->perf_stats.tx_linfail++;
-			else
-				card->perf_stats.tx_lin++;
-		}
-		if (rc)
-			return rc;
-	}
-
 	rc = skb_cow_head(skb, push_len);
 	if (rc)
 		return rc;
-	push_len = qeth_push_hdr(skb, &hdr, push_len);
+	push_len = qeth_add_hw_header(card, skb, &hdr, push_len, &elements);
 	if (push_len < 0)
 		return push_len;
 	if (!push_len) {
 		/* hdr was allocated from cache */
 		hd_len = sizeof(*hdr);
-		hdr_elements = 1;
 	}
 	qeth_l2_fill_header(hdr, skb, cast_type, skb->len - push_len);
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
@@ -713,18 +695,11 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 			card->perf_stats.tx_csum++;
 	}
 
-	elements = qeth_get_elements_no(card, skb, hdr_elements, 0);
-	if (!elements) {
-		rc = -E2BIG;
-		goto out;
-	}
-	elements += hdr_elements;
-
 	is_sg = skb_is_nonlinear(skb);
 	/* TODO: remove the skb_orphan() once TX completion is fast enough */
 	skb_orphan(skb);
 	rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len, elements);
-out:
+
 	if (!rc) {
 		if (card->options.performance_stats) {
 			card->perf_stats.buf_elements_sent += elements;
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index c12aeb7d8f26..f7bcc4853c45 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2166,28 +2166,13 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 				int cast_type)
 {
 	const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
+	unsigned int frame_len, elements;
 	unsigned char eth_hdr[ETH_HLEN];
-	unsigned int hdr_elements = 0;
 	struct qeth_hdr *hdr = NULL;
-	int elements, push_len, rc;
 	unsigned int hd_len = 0;
-	unsigned int frame_len;
+	int push_len, rc;
 	bool is_sg;
 
-	/* compress skb to fit into one IO buffer: */
-	if (!qeth_get_elements_no(card, skb, 0, 0)) {
-		rc = skb_linearize(skb);
-
-		if (card->options.performance_stats) {
-			if (rc)
-				card->perf_stats.tx_linfail++;
-			else
-				card->perf_stats.tx_lin++;
-		}
-		if (rc)
-			return rc;
-	}
-
 	/* re-use the L2 header area for the HW header: */
 	rc = skb_cow_head(skb, hw_hdr_len - ETH_HLEN);
 	if (rc)
@@ -2196,22 +2181,14 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 	skb_pull(skb, ETH_HLEN);
 	frame_len = skb->len;
 
-	push_len = qeth_push_hdr(skb, &hdr, hw_hdr_len);
+	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, &elements);
 	if (push_len < 0)
 		return push_len;
 	if (!push_len) {
 		/* hdr was added discontiguous from skb->data */
 		hd_len = hw_hdr_len;
-		hdr_elements = 1;
 	}
 
-	elements = qeth_get_elements_no(card, skb, hdr_elements, 0);
-	if (!elements) {
-		rc = -E2BIG;
-		goto out;
-	}
-	elements += hdr_elements;
-
 	if (skb->protocol == htons(ETH_P_AF_IUCV))
 		qeth_l3_fill_af_iucv_hdr(hdr, skb, frame_len);
 	else
@@ -2226,7 +2203,7 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 		rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len,
 					 elements);
 	}
-out:
+
 	if (!rc) {
 		if (card->options.performance_stats) {
 			card->perf_stats.buf_elements_sent += elements;
-- 
cgit v1.2.3


From a7c2f4a33290fbad615a0c4e977f317f37d7a057 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:57 +0200
Subject: s390/qeth: add support for constrained HW headers

Some transmit modes require that the HW header is located in the same
page as the initial protocol headers in skb->data. Let callers specify
the size of this contiguous header range, and enforce it when building
the HW header.

While at it, apply some gentle renaming to the relevant L2 code so that
it matches the L3 code.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  4 ++--
 drivers/s390/net/qeth_core_main.c | 33 +++++++++++++++++++--------------
 drivers/s390/net/qeth_l2_main.c   | 12 +++++++-----
 drivers/s390/net/qeth_l3_main.c   |  3 ++-
 4 files changed, 30 insertions(+), 22 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 2a5ec99643df..605ec4706773 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -1048,8 +1048,8 @@ netdev_features_t qeth_features_check(struct sk_buff *skb,
 				      netdev_features_t features);
 int qeth_vm_request_mac(struct qeth_card *card);
 int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
-		       struct qeth_hdr **hdr, unsigned int len,
-		       unsigned int *elements);
+		       struct qeth_hdr **hdr, unsigned int hdr_len,
+		       unsigned int proto_len, unsigned int *elements);
 
 /* exports for OSN */
 int qeth_osn_assist(struct net_device *, void *, int);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index e7b34624df1e..732b517369c7 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -3895,7 +3895,9 @@ EXPORT_SYMBOL_GPL(qeth_hdr_chk_and_bounce);
  * @skb: skb that the HW header should be added to.
  * @hdr: double pointer to a qeth_hdr. When returning with >= 0,
  *	 it contains a valid pointer to a qeth_hdr.
- * @len: length of the HW header.
+ * @hdr_len: length of the HW header.
+ * @proto_len: length of protocol headers that need to be in same page as the
+ *	       HW header.
  *
  * Returns the pushed length. If the header can't be pushed on
  * (eg. because it would cross a page boundary), it is allocated from
@@ -3904,31 +3906,32 @@ EXPORT_SYMBOL_GPL(qeth_hdr_chk_and_bounce);
  * Error to create the hdr is indicated by returning with < 0.
  */
 int qeth_add_hw_header(struct qeth_card *card, struct sk_buff *skb,
-		       struct qeth_hdr **hdr, unsigned int len,
-		       unsigned int *elements)
+		       struct qeth_hdr **hdr, unsigned int hdr_len,
+		       unsigned int proto_len, unsigned int *elements)
 {
 	const unsigned int max_elements = QETH_MAX_BUFFER_ELEMENTS(card);
+	const unsigned int contiguous = proto_len ? proto_len : 1;
 	unsigned int __elements;
 	addr_t start, end;
 	bool push_ok;
 	int rc;
 
 check_layout:
-	start = (addr_t)skb->data - len;
+	start = (addr_t)skb->data - hdr_len;
 	end = (addr_t)skb->data;
 
-	if (qeth_get_elements_for_range(start, end + 1) == 1) {
+	if (qeth_get_elements_for_range(start, end + contiguous) == 1) {
 		/* Push HW header into same page as first protocol header. */
 		push_ok = true;
 		__elements = qeth_count_elements(skb, 0);
-	} else {
+	} else if (!proto_len && qeth_get_elements_for_range(start, end) == 1) {
+		/* Push HW header into a new page. */
+		push_ok = true;
 		__elements = 1 + qeth_count_elements(skb, 0);
-		if (qeth_get_elements_for_range(start, end) == 1)
-			/* Push HW header into a new page. */
-			push_ok = true;
-		else
-			/* Use header cache. */
-			push_ok = false;
+	} else {
+		/* Use header cache, copy protocol headers up. */
+		push_ok = false;
+		__elements = 1 + qeth_count_elements(skb, proto_len);
 	}
 
 	/* Compress skb to fit into one IO buffer: */
@@ -3957,13 +3960,15 @@ check_layout:
 	*elements = __elements;
 	/* Add the header: */
 	if (push_ok) {
-		*hdr = skb_push(skb, len);
-		return len;
+		*hdr = skb_push(skb, hdr_len);
+		return hdr_len;
 	}
 	/* fall back */
 	*hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
 	if (!*hdr)
 		return -ENOMEM;
+	/* Copy protocol headers behind HW header: */
+	skb_copy_from_linear_data(skb, ((char *)*hdr) + hdr_len, proto_len);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(qeth_add_hw_header);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index 905f3bb3a87c..c302002e422f 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -671,17 +671,19 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 			    struct qeth_qdio_out_q *queue, int cast_type,
 			    int ipv)
 {
-	int push_len = sizeof(struct qeth_hdr);
+	const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
 	struct qeth_hdr *hdr = NULL;
 	unsigned int hd_len = 0;
 	unsigned int elements;
+	int push_len, rc;
 	bool is_sg;
-	int rc;
 
-	rc = skb_cow_head(skb, push_len);
+	rc = skb_cow_head(skb, hw_hdr_len);
 	if (rc)
 		return rc;
-	push_len = qeth_add_hw_header(card, skb, &hdr, push_len, &elements);
+
+	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, 0,
+				      &elements);
 	if (push_len < 0)
 		return push_len;
 	if (!push_len) {
@@ -707,7 +709,7 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 				card->perf_stats.sg_skbs_sent++;
 		}
 	} else {
-		if (hd_len)
+		if (!push_len)
 			kmem_cache_free(qeth_core_header_cache, hdr);
 		if (rc == -EBUSY)
 			/* roll back to ETH header */
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index f7bcc4853c45..b8e828556cf6 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2181,7 +2181,8 @@ static int qeth_l3_xmit_offload(struct qeth_card *card, struct sk_buff *skb,
 	skb_pull(skb, ETH_HLEN);
 	frame_len = skb->len;
 
-	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, &elements);
+	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, 0,
+				      &elements);
 	if (push_len < 0)
 		return push_len;
 	if (!push_len) {
-- 
cgit v1.2.3


From 5f89eca577776952325ee35da54786d26de1120a Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 19 Jul 2018 12:43:58 +0200
Subject: s390/qeth: speed up L2 IQD xmit

Modify the L2 OSA xmit path so that it also supports L2 IQD devices
(in particular, their HW header requirements). This allows IQD devices
to advertise NETIF_F_SG support, and eliminates the allocation overhead
for the HW header.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c |  7 ++++
 drivers/s390/net/qeth_l2_main.c   | 76 ++++++++++++---------------------------
 drivers/s390/net/qeth_l3_main.c   |  3 --
 3 files changed, 30 insertions(+), 56 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 732b517369c7..d09a7110b381 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5731,6 +5731,13 @@ static struct net_device *qeth_alloc_netdev(struct qeth_card *card)
 	dev->mtu = 0;
 	SET_NETDEV_DEV(dev, &card->gdev->dev);
 	netif_carrier_off(dev);
+
+	if (!IS_OSN(card)) {
+		dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+		dev->hw_features |= NETIF_F_SG;
+		dev->vlan_features |= NETIF_F_SG;
+	}
+
 	return dev;
 }
 
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index c302002e422f..c1829a4b955d 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -641,37 +641,13 @@ static void qeth_l2_set_rx_mode(struct net_device *dev)
 		qeth_promisc_to_bridge(card);
 }
 
-static int qeth_l2_xmit_iqd(struct qeth_card *card, struct sk_buff *skb,
-			    struct qeth_qdio_out_q *queue, int cast_type)
-{
-	unsigned int data_offset = ETH_HLEN;
-	struct qeth_hdr *hdr;
-	int rc;
-
-	hdr = kmem_cache_alloc(qeth_core_header_cache, GFP_ATOMIC);
-	if (!hdr)
-		return -ENOMEM;
-	qeth_l2_fill_header(hdr, skb, cast_type, skb->len);
-	skb_copy_from_linear_data(skb, ((char *)hdr) + sizeof(*hdr),
-				  data_offset);
-
-	if (!qeth_get_elements_no(card, skb, 1, data_offset)) {
-		rc = -E2BIG;
-		goto out;
-	}
-	rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset,
-				      sizeof(*hdr) + data_offset);
-out:
-	if (rc)
-		kmem_cache_free(qeth_core_header_cache, hdr);
-	return rc;
-}
-
-static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
-			    struct qeth_qdio_out_q *queue, int cast_type,
-			    int ipv)
+static int qeth_l2_xmit(struct qeth_card *card, struct sk_buff *skb,
+			struct qeth_qdio_out_q *queue, int cast_type, int ipv)
 {
+	const unsigned int proto_len = IS_IQD(card) ? ETH_HLEN : 0;
 	const unsigned int hw_hdr_len = sizeof(struct qeth_hdr);
+	unsigned int frame_len = skb->len;
+	unsigned int data_offset = 0;
 	struct qeth_hdr *hdr = NULL;
 	unsigned int hd_len = 0;
 	unsigned int elements;
@@ -682,15 +658,16 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 	if (rc)
 		return rc;
 
-	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, 0,
+	push_len = qeth_add_hw_header(card, skb, &hdr, hw_hdr_len, proto_len,
 				      &elements);
 	if (push_len < 0)
 		return push_len;
 	if (!push_len) {
-		/* hdr was allocated from cache */
-		hd_len = sizeof(*hdr);
+		/* HW header needs its own buffer element. */
+		hd_len = hw_hdr_len + proto_len;
+		data_offset = proto_len;
 	}
-	qeth_l2_fill_header(hdr, skb, cast_type, skb->len - push_len);
+	qeth_l2_fill_header(hdr, skb, cast_type, frame_len);
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv);
 		if (card->options.performance_stats)
@@ -698,9 +675,15 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb,
 	}
 
 	is_sg = skb_is_nonlinear(skb);
-	/* TODO: remove the skb_orphan() once TX completion is fast enough */
-	skb_orphan(skb);
-	rc = qeth_do_send_packet(card, queue, skb, hdr, 0, hd_len, elements);
+	if (IS_IQD(card)) {
+		rc = qeth_do_send_packet_fast(queue, skb, hdr, data_offset,
+					      hd_len);
+	} else {
+		/* TODO: drop skb_orphan() once TX completion is fast enough */
+		skb_orphan(skb);
+		rc = qeth_do_send_packet(card, queue, skb, hdr, data_offset,
+					 hd_len, elements);
+	}
 
 	if (!rc) {
 		if (card->options.performance_stats) {
@@ -759,16 +742,10 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb,
 	}
 	netif_stop_queue(dev);
 
-	switch (card->info.type) {
-	case QETH_CARD_TYPE_OSN:
+	if (IS_OSN(card))
 		rc = qeth_l2_xmit_osn(card, skb, queue);
-		break;
-	case QETH_CARD_TYPE_IQD:
-		rc = qeth_l2_xmit_iqd(card, skb, queue, cast_type);
-		break;
-	default:
-		rc = qeth_l2_xmit_osa(card, skb, queue, cast_type, ipv);
-	}
+	else
+		rc = qeth_l2_xmit(card, skb, queue, cast_type, ipv);
 
 	if (!rc) {
 		card->stats.tx_packets++;
@@ -927,6 +904,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 		card->dev->flags |= IFF_NOARP;
 	} else {
 		card->dev->ethtool_ops = &qeth_l2_ethtool_ops;
+		card->dev->needed_headroom = sizeof(struct qeth_hdr);
 	}
 
 	if (card->info.type == QETH_CARD_TYPE_OSM)
@@ -934,14 +912,6 @@ static int qeth_l2_setup_netdev(struct qeth_card *card)
 	else
 		card->dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 
-	if (card->info.type != QETH_CARD_TYPE_OSN &&
-	    card->info.type != QETH_CARD_TYPE_IQD) {
-		card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
-		card->dev->needed_headroom = sizeof(struct qeth_hdr);
-		card->dev->hw_features |= NETIF_F_SG;
-		card->dev->vlan_features |= NETIF_F_SG;
-	}
-
 	if (card->info.type == QETH_CARD_TYPE_OSD && !card->info.guestlan) {
 		card->dev->features |= NETIF_F_SG;
 		/* OSA 3S and earlier has no RX/TX support */
diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index b8e828556cf6..1833e7505aca 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -2556,13 +2556,10 @@ static int qeth_l3_setup_netdev(struct qeth_card *card)
 		return -ENODEV;
 
 	card->dev->ethtool_ops = &qeth_l3_ethtool_ops;
-	card->dev->priv_flags &= ~IFF_TX_SKB_SHARING;
 	card->dev->needed_headroom = sizeof(struct qeth_hdr) - ETH_HLEN;
 	card->dev->features |=	NETIF_F_HW_VLAN_CTAG_TX |
 				NETIF_F_HW_VLAN_CTAG_RX |
 				NETIF_F_HW_VLAN_CTAG_FILTER;
-	card->dev->hw_features |= NETIF_F_SG;
-	card->dev->vlan_features |= NETIF_F_SG;
 
 	netif_keep_dst(card->dev);
 	if (card->dev->hw_features & NETIF_F_TSO)
-- 
cgit v1.2.3


From 9bcc66e1983d10861deb6920fb0c151c5b01772a Mon Sep 17 00:00:00 2001
From: Jon Maxwell <jmaxwell37@gmail.com>
Date: Thu, 19 Jul 2018 11:14:42 +1000
Subject: tcp: convert icsk_user_timeout from jiffies to msecs

This is a preparatory commit. Part of this series that improves the
socket TCP_USER_TIMEOUT option accuracy. Implement Eric Dumazets idea
to convert icsk->icsk_user_timeout from jiffies to msecs. To eliminate
the msecs_to_jiffies() and jiffies_to_msecs() dance in future.

Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c       | 4 ++--
 net/ipv4/tcp_timer.c | 8 ++++----
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index bce53b1728a6..514aaac1626f 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2989,7 +2989,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 		if (val < 0)
 			err = -EINVAL;
 		else
-			icsk->icsk_user_timeout = msecs_to_jiffies(val);
+			icsk->icsk_user_timeout = val;
 		break;
 
 	case TCP_FASTOPEN:
@@ -3445,7 +3445,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		break;
 
 	case TCP_USER_TIMEOUT:
-		val = jiffies_to_msecs(icsk->icsk_user_timeout);
+		val = icsk->icsk_user_timeout;
 		break;
 
 	case TCP_FASTOPEN:
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 3b3611729928..fa34984d0b12 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -183,8 +183,9 @@ static bool retransmits_timed_out(struct sock *sk,
 		else
 			timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
 				(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+		timeout = jiffies_to_msecs(timeout);
 	}
-	return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= jiffies_to_msecs(timeout);
+	return (tcp_time_stamp(tcp_sk(sk)) - start_ts) >= timeout;
 }
 
 /* A write timeout has occurred. Process the after effects. */
@@ -337,8 +338,7 @@ static void tcp_probe_timer(struct sock *sk)
 	if (!start_ts)
 		skb->skb_mstamp = tp->tcp_mstamp;
 	else if (icsk->icsk_user_timeout &&
-		 (s32)(tcp_time_stamp(tp) - start_ts) >
-		 jiffies_to_msecs(icsk->icsk_user_timeout))
+		 (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout)
 		goto abort;
 
 	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
@@ -672,7 +672,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 		 * to determine when to timeout instead.
 		 */
 		if ((icsk->icsk_user_timeout != 0 &&
-		    elapsed >= icsk->icsk_user_timeout &&
+		    elapsed >= msecs_to_jiffies(icsk->icsk_user_timeout) &&
 		    icsk->icsk_probes_out > 0) ||
 		    (icsk->icsk_user_timeout == 0 &&
 		    icsk->icsk_probes_out >= keepalive_probes(tp))) {
-- 
cgit v1.2.3


From a7fa37703d495310819d0a6747e5b32362305374 Mon Sep 17 00:00:00 2001
From: Jon Maxwell <jmaxwell37@gmail.com>
Date: Thu, 19 Jul 2018 11:14:43 +1000
Subject: tcp: Add tcp_retransmit_stamp() helper routine

Create a seperate helper routine as per Neal Cardwells suggestion. To
be used by the final commit in this series and retransmits_timed_out().

Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index fa34984d0b12..d212f183dd2d 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -22,6 +22,20 @@
 #include <linux/gfp.h>
 #include <net/tcp.h>
 
+u32 tcp_retransmit_stamp(const struct sock *sk)
+{
+	u32 start_ts = tcp_sk(sk)->retrans_stamp;
+
+	if (unlikely(!start_ts)) {
+		struct sk_buff *head = tcp_rtx_queue_head(sk);
+
+		if (!head)
+			return 0;
+		start_ts = tcp_skb_timestamp(head);
+	}
+	return start_ts;
+}
+
 /**
  *  tcp_write_err() - close socket and save error info
  *  @sk:  The socket the error has appeared on.
@@ -166,14 +180,9 @@ static bool retransmits_timed_out(struct sock *sk,
 	if (!inet_csk(sk)->icsk_retransmits)
 		return false;
 
-	start_ts = tcp_sk(sk)->retrans_stamp;
-	if (unlikely(!start_ts)) {
-		struct sk_buff *head = tcp_rtx_queue_head(sk);
-
-		if (!head)
-			return false;
-		start_ts = tcp_skb_timestamp(head);
-	}
+	start_ts = tcp_retransmit_stamp(sk);
+	if (!start_ts)
+		return false;
 
 	if (likely(timeout == 0)) {
 		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);
-- 
cgit v1.2.3


From b701a99e431db784714c32fc6b68123045714679 Mon Sep 17 00:00:00 2001
From: Jon Maxwell <jmaxwell37@gmail.com>
Date: Thu, 19 Jul 2018 11:14:44 +1000
Subject: tcp: Add tcp_clamp_rto_to_user_timeout() helper to improve accuracy

Create the tcp_clamp_rto_to_user_timeout() helper routine. To calculate
the correct rto, so that the TCP_USER_TIMEOUT socket option is more
accurate. Taking suggestions and feedback into account from
Eric Dumazet, Neal Cardwell and David Laight. Due to the 1st commit we
can avoid the msecs_to_jiffies() and jiffies_to_msecs() dance.

Signed-off-by: Jon Maxwell <jmaxwell37@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index d212f183dd2d..a242f8874629 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -36,6 +36,21 @@ u32 tcp_retransmit_stamp(const struct sock *sk)
 	return start_ts;
 }
 
+static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	u32 elapsed, start_ts;
+
+	start_ts = tcp_retransmit_stamp(sk);
+	if (!icsk->icsk_user_timeout || !start_ts)
+		return icsk->icsk_rto;
+	elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts;
+	if (elapsed >= icsk->icsk_user_timeout)
+		return 1; /* user timeout has passed; fire ASAP */
+	else
+		return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(icsk->icsk_user_timeout - elapsed));
+}
+
 /**
  *  tcp_write_err() - close socket and save error info
  *  @sk:  The socket the error has appeared on.
@@ -544,7 +559,8 @@ out_reset_timer:
 		/* Use normal (exponential) backoff */
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
+	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+				  tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
 	if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0))
 		__sk_dst_reset(sk);
 
-- 
cgit v1.2.3


From 0b65c59e3a5475895c93ea5f130597db16b8abf6 Mon Sep 17 00:00:00 2001
From: Bjorn Andersson <bjorn.andersson@linaro.org>
Date: Mon, 25 Jun 2018 13:06:13 -0700
Subject: soc: qcom: smem: Correct check for global partition

The moved check for the global partition ended up in the wrong place and I
failed to spot this in my review. This moves it to the correct place.

Fixes: 11d2e7edac6a ("soc: qcom: smem: check sooner in qcom_smem_set_global_partition()")
Signed-off-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Reviewed-by: Alex Elder <elder@linaro.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/smem.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c
index 70b2ee80d6bd..bf4bd71ab53f 100644
--- a/drivers/soc/qcom/smem.c
+++ b/drivers/soc/qcom/smem.c
@@ -364,11 +364,6 @@ static int qcom_smem_alloc_private(struct qcom_smem *smem,
 	end = phdr_to_last_uncached_entry(phdr);
 	cached = phdr_to_last_cached_entry(phdr);
 
-	if (smem->global_partition) {
-		dev_err(smem->dev, "Already found the global partition\n");
-		return -EINVAL;
-	}
-
 	while (hdr < end) {
 		if (hdr->canary != SMEM_PRIVATE_CANARY)
 			goto bad_canary;
@@ -736,6 +731,11 @@ static int qcom_smem_set_global_partition(struct qcom_smem *smem)
 	bool found = false;
 	int i;
 
+	if (smem->global_partition) {
+		dev_err(smem->dev, "Already found the global partition\n");
+		return -EINVAL;
+	}
+
 	ptable = qcom_smem_get_ptable(smem);
 	if (IS_ERR(ptable))
 		return PTR_ERR(ptable);
-- 
cgit v1.2.3


From 7e5700ae64f6a8921c130f34946af4de4483bb7c Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Wed, 23 May 2018 17:35:20 -0700
Subject: dt-bindings: Documentation for qcom, llcc

Documentation for last level cache controller device tree bindings,
client bindings usage examples.

Signed-off-by: Channagoud Kadabi <ckadabi@codeaurora.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Reviewed-by: Evan Green <evgreen@chromium.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 .../devicetree/bindings/arm/msm/qcom,llcc.txt      | 26 ++++++++++++++++++++++
 1 file changed, 26 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/arm/msm/qcom,llcc.txt

diff --git a/Documentation/devicetree/bindings/arm/msm/qcom,llcc.txt b/Documentation/devicetree/bindings/arm/msm/qcom,llcc.txt
new file mode 100644
index 000000000000..5e85749262ae
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/msm/qcom,llcc.txt
@@ -0,0 +1,26 @@
+== Introduction==
+
+LLCC (Last Level Cache Controller) provides last level of cache memory in SOC,
+that can be shared by multiple clients. Clients here are different cores in the
+SOC, the idea is to minimize the local caches at the clients and migrate to
+common pool of memory. Cache memory is divided into partitions called slices
+which are assigned to clients. Clients can query the slice details, activate
+and deactivate them.
+
+Properties:
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: must be "qcom,sdm845-llcc"
+
+- reg:
+	Usage: required
+	Value Type: <prop-encoded-array>
+	Definition: Start address and the the size of the register region.
+
+Example:
+
+	cache-controller@1100000 {
+		compatible = "qcom,sdm845-llcc";
+		reg = <0x1100000 0x250000>;
+	};
-- 
cgit v1.2.3


From a3134fb09e0bc5bee76e13bf863173b86f21cf87 Mon Sep 17 00:00:00 2001
From: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Date: Wed, 23 May 2018 17:35:21 -0700
Subject: drivers: soc: Add LLCC driver

LLCC (Last Level Cache Controller) provides additional cache memory
in the system. LLCC is partitioned into multiple slices and each
slice gets its own priority, size, ID and other config parameters.
LLCC driver programs these parameters for each slice. Clients that
are assigned to use LLCC need to get information such size & ID of the
slice they get and activate or deactivate the slice as needed. LLCC driver
provides API for the clients to perform these operations.

Signed-off-by: Channagoud Kadabi <ckadabi@codeaurora.org>
Signed-off-by: Rishabh Bhatnagar <rishabhb@codeaurora.org>
Reviewed-by: Evan Green <evgreen@chromium.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/Kconfig           |  17 ++
 drivers/soc/qcom/Makefile          |   2 +
 drivers/soc/qcom/llcc-sdm845.c     |  94 +++++++++++
 drivers/soc/qcom/llcc-slice.c      | 335 +++++++++++++++++++++++++++++++++++++
 include/linux/soc/qcom/llcc-qcom.h | 180 ++++++++++++++++++++
 5 files changed, 628 insertions(+)
 create mode 100644 drivers/soc/qcom/llcc-sdm845.c
 create mode 100644 drivers/soc/qcom/llcc-slice.c
 create mode 100644 include/linux/soc/qcom/llcc-qcom.h

diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 9dc02f390ba3..d1a41852ae7a 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -39,6 +39,23 @@ config QCOM_GSBI
           functions for connecting the underlying serial UART, SPI, and I2C
           devices to the output pins.
 
+config QCOM_LLCC
+	tristate "Qualcomm Technologies, Inc. LLCC driver"
+	depends on ARCH_QCOM
+	help
+	  Qualcomm Technologies, Inc. platform specific
+	  Last Level Cache Controller(LLCC) driver. This provides interfaces
+	  to clients that use the LLCC. Say yes here to enable LLCC slice
+	  driver.
+
+config QCOM_SDM845_LLCC
+	tristate "Qualcomm Technologies, Inc. SDM845 LLCC driver"
+	depends on QCOM_LLCC
+	help
+	  Say yes here to enable the LLCC driver for SDM845. This provides
+	  data required to configure LLCC so that clients can start using the
+	  LLCC slices.
+
 config QCOM_MDT_LOADER
 	tristate
 	select QCOM_SCM
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 19dcf957cb3a..5921454c4ddd 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -15,3 +15,5 @@ obj-$(CONFIG_QCOM_SMP2P)	+= smp2p.o
 obj-$(CONFIG_QCOM_SMSM)	+= smsm.o
 obj-$(CONFIG_QCOM_WCNSS_CTRL) += wcnss_ctrl.o
 obj-$(CONFIG_QCOM_APR) += apr.o
+obj-$(CONFIG_QCOM_LLCC) += llcc-slice.o
+obj-$(CONFIG_QCOM_SDM845_LLCC) += llcc-sdm845.o
diff --git a/drivers/soc/qcom/llcc-sdm845.c b/drivers/soc/qcom/llcc-sdm845.c
new file mode 100644
index 000000000000..2e1e4f0a5db8
--- /dev/null
+++ b/drivers/soc/qcom/llcc-sdm845.c
@@ -0,0 +1,94 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/soc/qcom/llcc-qcom.h>
+
+/*
+ * SCT(System Cache Table) entry contains of the following members:
+ * usecase_id: Unique id for the client's use case
+ * slice_id: llcc slice id for each client
+ * max_cap: The maximum capacity of the cache slice provided in KB
+ * priority: Priority of the client used to select victim line for replacement
+ * fixed_size: Boolean indicating if the slice has a fixed capacity
+ * bonus_ways: Bonus ways are additional ways to be used for any slice,
+ *		if client ends up using more than reserved cache ways. Bonus
+ *		ways are allocated only if they are not reserved for some
+ *		other client.
+ * res_ways: Reserved ways for the cache slice, the reserved ways cannot
+ *		be used by any other client than the one its assigned to.
+ * cache_mode: Each slice operates as a cache, this controls the mode of the
+ *             slice: normal or TCM(Tightly Coupled Memory)
+ * probe_target_ways: Determines what ways to probe for access hit. When
+ *                    configured to 1 only bonus and reserved ways are probed.
+ *                    When configured to 0 all ways in llcc are probed.
+ * dis_cap_alloc: Disable capacity based allocation for a client
+ * retain_on_pc: If this bit is set and client has maintained active vote
+ *               then the ways assigned to this client are not flushed on power
+ *               collapse.
+ * activate_on_init: Activate the slice immediately after the SCT is programmed
+ */
+#define SCT_ENTRY(uid, sid, mc, p, fs, bway, rway, cmod, ptw, dca, rp, a) \
+	{					\
+		.usecase_id = uid,		\
+		.slice_id = sid,		\
+		.max_cap = mc,			\
+		.priority = p,			\
+		.fixed_size = fs,		\
+		.bonus_ways = bway,		\
+		.res_ways = rway,		\
+		.cache_mode = cmod,		\
+		.probe_target_ways = ptw,	\
+		.dis_cap_alloc = dca,		\
+		.retain_on_pc = rp,		\
+		.activate_on_init = a,		\
+	}
+
+static struct llcc_slice_config sdm845_data[] =  {
+	SCT_ENTRY(LLCC_CPUSS,    1,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 1),
+	SCT_ENTRY(LLCC_VIDSC0,   2,  512,  2, 1, 0x0,   0x0f0, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VIDSC1,   3,  512,  2, 1, 0x0,   0x0f0, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_ROTATOR,  4,  563,  2, 1, 0x0,   0x00e, 2, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VOICE,    5,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_AUDIO,    6,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMHPGRW, 7,  1024, 2, 0, 0xfc,  0xf00, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDM,      8,  2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_CMPT,     10, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_GPUHTW,   11, 512,  1, 1, 0xc,   0x0,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_GPU,      12, 2304, 1, 0, 0xff0, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MMUHWT,   13, 256,  2, 0, 0x0,   0x1,   0, 0, 1, 0, 1),
+	SCT_ENTRY(LLCC_CMPTDMA,  15, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_DISP,     16, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_VIDFW,    17, 2816, 1, 0, 0xffc, 0x2,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMHPFX,  20, 1024, 2, 1, 0x0,   0xf00, 0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_MDMPNG,   21, 1024, 0, 1, 0x1e,  0x0,   0, 0, 1, 1, 0),
+	SCT_ENTRY(LLCC_AUDHW,    22, 1024, 1, 1, 0xffc, 0x2,   0, 0, 1, 1, 0),
+};
+
+static int sdm845_qcom_llcc_probe(struct platform_device *pdev)
+{
+	return qcom_llcc_probe(pdev, sdm845_data, ARRAY_SIZE(sdm845_data));
+}
+
+static const struct of_device_id sdm845_qcom_llcc_of_match[] = {
+	{ .compatible = "qcom,sdm845-llcc", },
+	{ }
+};
+
+static struct platform_driver sdm845_qcom_llcc_driver = {
+	.driver = {
+		.name = "sdm845-llcc",
+		.of_match_table = sdm845_qcom_llcc_of_match,
+	},
+	.probe = sdm845_qcom_llcc_probe,
+};
+module_platform_driver(sdm845_qcom_llcc_driver);
+
+MODULE_DESCRIPTION("QCOM sdm845 LLCC driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c
new file mode 100644
index 000000000000..fcaad1a4b41d
--- /dev/null
+++ b/drivers/soc/qcom/llcc-slice.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/llcc-qcom.h>
+
+#define ACTIVATE                      BIT(0)
+#define DEACTIVATE                    BIT(1)
+#define ACT_CTRL_OPCODE_ACTIVATE      BIT(0)
+#define ACT_CTRL_OPCODE_DEACTIVATE    BIT(1)
+#define ACT_CTRL_ACT_TRIG             BIT(0)
+#define ACT_CTRL_OPCODE_SHIFT         0x01
+#define ATTR1_PROBE_TARGET_WAYS_SHIFT 0x02
+#define ATTR1_FIXED_SIZE_SHIFT        0x03
+#define ATTR1_PRIORITY_SHIFT          0x04
+#define ATTR1_MAX_CAP_SHIFT           0x10
+#define ATTR0_RES_WAYS_MASK           GENMASK(11, 0)
+#define ATTR0_BONUS_WAYS_MASK         GENMASK(27, 16)
+#define ATTR0_BONUS_WAYS_SHIFT        0x10
+#define LLCC_STATUS_READ_DELAY        100
+
+#define CACHE_LINE_SIZE_SHIFT         6
+
+#define LLCC_COMMON_STATUS0           0x0003000c
+#define LLCC_LB_CNT_MASK              GENMASK(31, 28)
+#define LLCC_LB_CNT_SHIFT             28
+
+#define MAX_CAP_TO_BYTES(n)           (n * SZ_1K)
+#define LLCC_TRP_ACT_CTRLn(n)         (n * SZ_4K)
+#define LLCC_TRP_STATUSn(n)           (4 + n * SZ_4K)
+#define LLCC_TRP_ATTR0_CFGn(n)        (0x21000 + SZ_8 * n)
+#define LLCC_TRP_ATTR1_CFGn(n)        (0x21004 + SZ_8 * n)
+
+#define BANK_OFFSET_STRIDE	      0x80000
+
+static struct llcc_drv_data *drv_data;
+
+static const struct regmap_config llcc_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+};
+
+/**
+ * llcc_slice_getd - get llcc slice descriptor
+ * @uid: usecase_id for the client
+ *
+ * A pointer to llcc slice descriptor will be returned on success and
+ * and error pointer is returned on failure
+ */
+struct llcc_slice_desc *llcc_slice_getd(u32 uid)
+{
+	const struct llcc_slice_config *cfg;
+	struct llcc_slice_desc *desc;
+	u32 sz, count;
+
+	cfg = drv_data->cfg;
+	sz = drv_data->cfg_size;
+
+	for (count = 0; cfg && count < sz; count++, cfg++)
+		if (cfg->usecase_id == uid)
+			break;
+
+	if (count == sz || !cfg)
+		return ERR_PTR(-ENODEV);
+
+	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+	if (!desc)
+		return ERR_PTR(-ENOMEM);
+
+	desc->slice_id = cfg->slice_id;
+	desc->slice_size = cfg->max_cap;
+
+	return desc;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_getd);
+
+/**
+ * llcc_slice_putd - llcc slice descritpor
+ * @desc: Pointer to llcc slice descriptor
+ */
+void llcc_slice_putd(struct llcc_slice_desc *desc)
+{
+	kfree(desc);
+}
+EXPORT_SYMBOL_GPL(llcc_slice_putd);
+
+static int llcc_update_act_ctrl(u32 sid,
+				u32 act_ctrl_reg_val, u32 status)
+{
+	u32 act_ctrl_reg;
+	u32 status_reg;
+	u32 slice_status;
+	int ret;
+
+	act_ctrl_reg = drv_data->bcast_off + LLCC_TRP_ACT_CTRLn(sid);
+	status_reg = drv_data->bcast_off + LLCC_TRP_STATUSn(sid);
+
+	/* Set the ACTIVE trigger */
+	act_ctrl_reg_val |= ACT_CTRL_ACT_TRIG;
+	ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val);
+	if (ret)
+		return ret;
+
+	/* Clear the ACTIVE trigger */
+	act_ctrl_reg_val &= ~ACT_CTRL_ACT_TRIG;
+	ret = regmap_write(drv_data->regmap, act_ctrl_reg, act_ctrl_reg_val);
+	if (ret)
+		return ret;
+
+	ret = regmap_read_poll_timeout(drv_data->regmap, status_reg,
+				      slice_status, !(slice_status & status),
+				      0, LLCC_STATUS_READ_DELAY);
+	return ret;
+}
+
+/**
+ * llcc_slice_activate - Activate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ *
+ * A value of zero will be returned on success and a negative errno will
+ * be returned in error cases
+ */
+int llcc_slice_activate(struct llcc_slice_desc *desc)
+{
+	int ret;
+	u32 act_ctrl_val;
+
+	mutex_lock(&drv_data->lock);
+	if (test_bit(desc->slice_id, drv_data->bitmap)) {
+		mutex_unlock(&drv_data->lock);
+		return 0;
+	}
+
+	act_ctrl_val = ACT_CTRL_OPCODE_ACTIVATE << ACT_CTRL_OPCODE_SHIFT;
+
+	ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val,
+				  DEACTIVATE);
+	if (ret) {
+		mutex_unlock(&drv_data->lock);
+		return ret;
+	}
+
+	__set_bit(desc->slice_id, drv_data->bitmap);
+	mutex_unlock(&drv_data->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_activate);
+
+/**
+ * llcc_slice_deactivate - Deactivate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ *
+ * A value of zero will be returned on success and a negative errno will
+ * be returned in error cases
+ */
+int llcc_slice_deactivate(struct llcc_slice_desc *desc)
+{
+	u32 act_ctrl_val;
+	int ret;
+
+	mutex_lock(&drv_data->lock);
+	if (!test_bit(desc->slice_id, drv_data->bitmap)) {
+		mutex_unlock(&drv_data->lock);
+		return 0;
+	}
+	act_ctrl_val = ACT_CTRL_OPCODE_DEACTIVATE << ACT_CTRL_OPCODE_SHIFT;
+
+	ret = llcc_update_act_ctrl(desc->slice_id, act_ctrl_val,
+				  ACTIVATE);
+	if (ret) {
+		mutex_unlock(&drv_data->lock);
+		return ret;
+	}
+
+	__clear_bit(desc->slice_id, drv_data->bitmap);
+	mutex_unlock(&drv_data->lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(llcc_slice_deactivate);
+
+/**
+ * llcc_get_slice_id - return the slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_get_slice_id(struct llcc_slice_desc *desc)
+{
+	return desc->slice_id;
+}
+EXPORT_SYMBOL_GPL(llcc_get_slice_id);
+
+/**
+ * llcc_get_slice_size - return the slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+size_t llcc_get_slice_size(struct llcc_slice_desc *desc)
+{
+	return desc->slice_size;
+}
+EXPORT_SYMBOL_GPL(llcc_get_slice_size);
+
+static int qcom_llcc_cfg_program(struct platform_device *pdev)
+{
+	int i;
+	u32 attr1_cfg;
+	u32 attr0_cfg;
+	u32 attr1_val;
+	u32 attr0_val;
+	u32 max_cap_cacheline;
+	u32 sz;
+	int ret;
+	const struct llcc_slice_config *llcc_table;
+	struct llcc_slice_desc desc;
+	u32 bcast_off = drv_data->bcast_off;
+
+	sz = drv_data->cfg_size;
+	llcc_table = drv_data->cfg;
+
+	for (i = 0; i < sz; i++) {
+		attr1_cfg = bcast_off +
+				LLCC_TRP_ATTR1_CFGn(llcc_table[i].slice_id);
+		attr0_cfg = bcast_off +
+				LLCC_TRP_ATTR0_CFGn(llcc_table[i].slice_id);
+
+		attr1_val = llcc_table[i].cache_mode;
+		attr1_val |= llcc_table[i].probe_target_ways <<
+				ATTR1_PROBE_TARGET_WAYS_SHIFT;
+		attr1_val |= llcc_table[i].fixed_size <<
+				ATTR1_FIXED_SIZE_SHIFT;
+		attr1_val |= llcc_table[i].priority <<
+				ATTR1_PRIORITY_SHIFT;
+
+		max_cap_cacheline = MAX_CAP_TO_BYTES(llcc_table[i].max_cap);
+
+		/* LLCC instances can vary for each target.
+		 * The SW writes to broadcast register which gets propagated
+		 * to each llcc instace (llcc0,.. llccN).
+		 * Since the size of the memory is divided equally amongst the
+		 * llcc instances, we need to configure the max cap accordingly.
+		 */
+		max_cap_cacheline = max_cap_cacheline / drv_data->num_banks;
+		max_cap_cacheline >>= CACHE_LINE_SIZE_SHIFT;
+		attr1_val |= max_cap_cacheline << ATTR1_MAX_CAP_SHIFT;
+
+		attr0_val = llcc_table[i].res_ways & ATTR0_RES_WAYS_MASK;
+		attr0_val |= llcc_table[i].bonus_ways << ATTR0_BONUS_WAYS_SHIFT;
+
+		ret = regmap_write(drv_data->regmap, attr1_cfg, attr1_val);
+		if (ret)
+			return ret;
+		ret = regmap_write(drv_data->regmap, attr0_cfg, attr0_val);
+		if (ret)
+			return ret;
+		if (llcc_table[i].activate_on_init) {
+			desc.slice_id = llcc_table[i].slice_id;
+			ret = llcc_slice_activate(&desc);
+		}
+	}
+	return ret;
+}
+
+int qcom_llcc_probe(struct platform_device *pdev,
+		      const struct llcc_slice_config *llcc_cfg, u32 sz)
+{
+	u32 num_banks;
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	void __iomem *base;
+	int ret, i;
+
+	drv_data = devm_kzalloc(dev, sizeof(*drv_data), GFP_KERNEL);
+	if (!drv_data)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	drv_data->regmap = devm_regmap_init_mmio(dev, base,
+					&llcc_regmap_config);
+	if (IS_ERR(drv_data->regmap))
+		return PTR_ERR(drv_data->regmap);
+
+	ret = regmap_read(drv_data->regmap, LLCC_COMMON_STATUS0,
+						&num_banks);
+	if (ret)
+		return ret;
+
+	num_banks &= LLCC_LB_CNT_MASK;
+	num_banks >>= LLCC_LB_CNT_SHIFT;
+	drv_data->num_banks = num_banks;
+
+	for (i = 0; i < sz; i++)
+		if (llcc_cfg[i].slice_id > drv_data->max_slices)
+			drv_data->max_slices = llcc_cfg[i].slice_id;
+
+	drv_data->offsets = devm_kcalloc(dev, num_banks, sizeof(u32),
+							GFP_KERNEL);
+	if (!drv_data->offsets)
+		return -ENOMEM;
+
+	for (i = 0; i < num_banks; i++)
+		drv_data->offsets[i] = i * BANK_OFFSET_STRIDE;
+
+	drv_data->bcast_off = num_banks * BANK_OFFSET_STRIDE;
+
+	drv_data->bitmap = devm_kcalloc(dev,
+	BITS_TO_LONGS(drv_data->max_slices), sizeof(unsigned long),
+						GFP_KERNEL);
+	if (!drv_data->bitmap)
+		return -ENOMEM;
+
+	drv_data->cfg = llcc_cfg;
+	drv_data->cfg_size = sz;
+	mutex_init(&drv_data->lock);
+	platform_set_drvdata(pdev, drv_data);
+
+	return qcom_llcc_cfg_program(pdev);
+}
+EXPORT_SYMBOL_GPL(qcom_llcc_probe);
diff --git a/include/linux/soc/qcom/llcc-qcom.h b/include/linux/soc/qcom/llcc-qcom.h
new file mode 100644
index 000000000000..7e3b9c605ab2
--- /dev/null
+++ b/include/linux/soc/qcom/llcc-qcom.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ */
+
+#include <linux/platform_device.h>
+#ifndef __LLCC_QCOM__
+#define __LLCC_QCOM__
+
+#define LLCC_CPUSS       1
+#define LLCC_VIDSC0      2
+#define LLCC_VIDSC1      3
+#define LLCC_ROTATOR     4
+#define LLCC_VOICE       5
+#define LLCC_AUDIO       6
+#define LLCC_MDMHPGRW    7
+#define LLCC_MDM         8
+#define LLCC_CMPT        10
+#define LLCC_GPUHTW      11
+#define LLCC_GPU         12
+#define LLCC_MMUHWT      13
+#define LLCC_CMPTDMA     15
+#define LLCC_DISP        16
+#define LLCC_VIDFW       17
+#define LLCC_MDMHPFX     20
+#define LLCC_MDMPNG      21
+#define LLCC_AUDHW       22
+
+/**
+ * llcc_slice_desc - Cache slice descriptor
+ * @slice_id: llcc slice id
+ * @slice_size: Size allocated for the llcc slice
+ */
+struct llcc_slice_desc {
+	u32 slice_id;
+	size_t slice_size;
+};
+
+/**
+ * llcc_slice_config - Data associated with the llcc slice
+ * @usecase_id: usecase id for which the llcc slice is used
+ * @slice_id: llcc slice id assigned to each slice
+ * @max_cap: maximum capacity of the llcc slice
+ * @priority: priority of the llcc slice
+ * @fixed_size: whether the llcc slice can grow beyond its size
+ * @bonus_ways: bonus ways associated with llcc slice
+ * @res_ways: reserved ways associated with llcc slice
+ * @cache_mode: mode of the llcc slice
+ * @probe_target_ways: Probe only reserved and bonus ways on a cache miss
+ * @dis_cap_alloc: Disable capacity based allocation
+ * @retain_on_pc: Retain through power collapse
+ * @activate_on_init: activate the slice on init
+ */
+struct llcc_slice_config {
+	u32 usecase_id;
+	u32 slice_id;
+	u32 max_cap;
+	u32 priority;
+	bool fixed_size;
+	u32 bonus_ways;
+	u32 res_ways;
+	u32 cache_mode;
+	u32 probe_target_ways;
+	bool dis_cap_alloc;
+	bool retain_on_pc;
+	bool activate_on_init;
+};
+
+/**
+ * llcc_drv_data - Data associated with the llcc driver
+ * @regmap: regmap associated with the llcc device
+ * @cfg: pointer to the data structure for slice configuration
+ * @lock: mutex associated with each slice
+ * @cfg_size: size of the config data table
+ * @max_slices: max slices as read from device tree
+ * @bcast_off: Offset of the broadcast bank
+ * @num_banks: Number of llcc banks
+ * @bitmap: Bit map to track the active slice ids
+ * @offsets: Pointer to the bank offsets array
+ */
+struct llcc_drv_data {
+	struct regmap *regmap;
+	const struct llcc_slice_config *cfg;
+	struct mutex lock;
+	u32 cfg_size;
+	u32 max_slices;
+	u32 bcast_off;
+	u32 num_banks;
+	unsigned long *bitmap;
+	u32 *offsets;
+};
+
+#if IS_ENABLED(CONFIG_QCOM_LLCC)
+/**
+ * llcc_slice_getd - get llcc slice descriptor
+ * @uid: usecase_id of the client
+ */
+struct llcc_slice_desc *llcc_slice_getd(u32 uid);
+
+/**
+ * llcc_slice_putd - llcc slice descritpor
+ * @desc: Pointer to llcc slice descriptor
+ */
+void llcc_slice_putd(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_get_slice_id - get slice id
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_get_slice_id(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_get_slice_size - llcc slice size
+ * @desc: Pointer to llcc slice descriptor
+ */
+size_t llcc_get_slice_size(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_slice_activate - Activate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_slice_activate(struct llcc_slice_desc *desc);
+
+/**
+ * llcc_slice_deactivate - Deactivate the llcc slice
+ * @desc: Pointer to llcc slice descriptor
+ */
+int llcc_slice_deactivate(struct llcc_slice_desc *desc);
+
+/**
+ * qcom_llcc_probe - program the sct table
+ * @pdev: platform device pointer
+ * @table: soc sct table
+ * @sz: Size of the config table
+ */
+int qcom_llcc_probe(struct platform_device *pdev,
+		      const struct llcc_slice_config *table, u32 sz);
+#else
+static inline struct llcc_slice_desc *llcc_slice_getd(u32 uid)
+{
+	return NULL;
+}
+
+static inline void llcc_slice_putd(struct llcc_slice_desc *desc)
+{
+
+};
+
+static inline int llcc_get_slice_id(struct llcc_slice_desc *desc)
+{
+	return -EINVAL;
+}
+
+static inline size_t llcc_get_slice_size(struct llcc_slice_desc *desc)
+{
+	return 0;
+}
+static inline int llcc_slice_activate(struct llcc_slice_desc *desc)
+{
+	return -EINVAL;
+}
+
+static inline int llcc_slice_deactivate(struct llcc_slice_desc *desc)
+{
+	return -EINVAL;
+}
+static inline int qcom_llcc_probe(struct platform_device *pdev,
+		      const struct llcc_slice_config *table, u32 sz)
+{
+	return -ENODEV;
+}
+
+static inline int qcom_llcc_remove(struct platform_device *pdev)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif
-- 
cgit v1.2.3


From 658628e7ef78e875cfe13064387c1a7a287d6338 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:56:58 +0530
Subject: drivers: qcom: rpmh-rsc: add RPMH controller for QCOM SoCs

Add controller driver for QCOM SoCs that have hardware based shared
resource management. The hardware IP known as RSC (Resource State
Coordinator) houses multiple Direct Resource Voter (DRV) for different
execution levels. A DRV is a unique voter on the state of a shared
resource. A Trigger Control Set (TCS) is a bunch of slots that can house
multiple resource state requests, that when triggered will issue those
requests through an internal bus to the Resource Power Manager Hardened
(RPMH) blocks. These hardware blocks are capable of adjusting clocks,
voltages, etc. The resource state request from a DRV are aggregated
along with state requests from other processors in the SoC and the
aggregate value is applied on the resource.

Some important aspects of the RPMH communication -
- Requests are <addr, value> with some header information
- Multiple requests (upto 16) may be sent through a TCS, at a time
- Requests in a TCS are sent in sequence
- Requests may be fire-n-forget or completion (response expected)
- Multiple TCS from the same DRV may be triggered simultaneously
- Cannot send a request if another request for the same addr is in
  progress from the same DRV
- When all the requests from a TCS are complete, an IRQ is raised
- The IRQ handler needs to clear the TCS before it is available for
  reuse
- TCS configuration is specific to a DRV
- Platform drivers may use DRV from different RSCs to make requests

Resource state requests made when CPUs are active are called 'active'
state requests. Requests made when all the CPUs are powered down (idle
state) are called 'sleep' state requests. They are matched by a
corresponding 'wake' state requests which puts the resources back in to
previously requested active state before resuming any CPU. TCSes are
dedicated for each type of requests. Active mode TCSes (AMC) are used to
send requests immediately to the resource, while control TCS are used to
provide specific information to the controller. Sleep and Wake TCS send
sleep and wake requests, after and before the system halt respectively.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/Kconfig                |  10 +
 drivers/soc/qcom/Makefile               |   1 +
 drivers/soc/qcom/rpmh-internal.h        |  69 +++++
 drivers/soc/qcom/rpmh-rsc.c             | 481 ++++++++++++++++++++++++++++++++
 include/dt-bindings/soc/qcom,rpmh-rsc.h |  14 +
 include/soc/qcom/tcs.h                  |  56 ++++
 6 files changed, 631 insertions(+)
 create mode 100644 drivers/soc/qcom/rpmh-internal.h
 create mode 100644 drivers/soc/qcom/rpmh-rsc.c
 create mode 100644 include/dt-bindings/soc/qcom,rpmh-rsc.h
 create mode 100644 include/soc/qcom/tcs.h

diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index d1a41852ae7a..ccbdb398fa63 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -91,6 +91,16 @@ config QCOM_RMTFS_MEM
 
 	  Say y here if you intend to boot the modem remoteproc.
 
+config QCOM_RPMH
+	bool "Qualcomm RPM-Hardened (RPMH) Communication"
+	depends on ARCH_QCOM && ARM64 && OF || COMPILE_TEST
+	help
+	  Support for communication with the hardened-RPM blocks in
+	  Qualcomm Technologies Inc (QTI) SoCs. RPMH communication uses an
+	  internal bus to transmit state requests for shared resources. A set
+	  of hardware components aggregate requests for these resources and
+	  help apply the aggregated state on the resource.
+
 config QCOM_SMEM
 	tristate "Qualcomm Shared Memory Manager (SMEM)"
 	depends on ARCH_QCOM
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 5921454c4ddd..b2faf9aeed3f 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_QCOM_PM)	+=	spm.o
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
 obj-$(CONFIG_QCOM_RMTFS_MEM)	+= rmtfs_mem.o
+obj-$(CONFIG_QCOM_RPMH)	+=	rpmh-rsc.o
 obj-$(CONFIG_QCOM_SMD_RPM)	+= smd-rpm.o
 obj-$(CONFIG_QCOM_SMEM) +=	smem.o
 obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
new file mode 100644
index 000000000000..cc29176f1303
--- /dev/null
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+
+#ifndef __RPM_INTERNAL_H__
+#define __RPM_INTERNAL_H__
+
+#include <linux/bitmap.h>
+#include <soc/qcom/tcs.h>
+
+#define TCS_TYPE_NR			4
+#define MAX_CMDS_PER_TCS		16
+#define MAX_TCS_PER_TYPE		3
+#define MAX_TCS_NR			(MAX_TCS_PER_TYPE * TCS_TYPE_NR)
+
+struct rsc_drv;
+
+/**
+ * struct tcs_group: group of Trigger Command Sets (TCS) to send state requests
+ * to the controller
+ *
+ * @drv:       the controller
+ * @type:      type of the TCS in this group - active, sleep, wake
+ * @mask:      mask of the TCSes relative to all the TCSes in the RSC
+ * @offset:    start of the TCS group relative to the TCSes in the RSC
+ * @num_tcs:   number of TCSes in this type
+ * @ncpt:      number of commands in each TCS
+ * @lock:      lock for synchronizing this TCS writes
+ * @req:       requests that are sent from the TCS
+ */
+struct tcs_group {
+	struct rsc_drv *drv;
+	int type;
+	u32 mask;
+	u32 offset;
+	int num_tcs;
+	int ncpt;
+	spinlock_t lock;
+	const struct tcs_request *req[MAX_TCS_PER_TYPE];
+};
+
+/**
+ * struct rsc_drv: the Direct Resource Voter (DRV) of the
+ * Resource State Coordinator controller (RSC)
+ *
+ * @name:       controller identifier
+ * @tcs_base:   start address of the TCS registers in this controller
+ * @id:         instance id in the controller (Direct Resource Voter)
+ * @num_tcs:    number of TCSes in this DRV
+ * @tcs:        TCS groups
+ * @tcs_in_use: s/w state of the TCS
+ * @lock:       synchronize state of the controller
+ */
+struct rsc_drv {
+	const char *name;
+	void __iomem *tcs_base;
+	int id;
+	int num_tcs;
+	struct tcs_group tcs[TCS_TYPE_NR];
+	DECLARE_BITMAP(tcs_in_use, MAX_TCS_NR);
+	spinlock_t lock;
+};
+
+
+int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg);
+
+#endif /* __RPM_INTERNAL_H__ */
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
new file mode 100644
index 000000000000..c5e0793cdfb7
--- /dev/null
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -0,0 +1,481 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#define pr_fmt(fmt) "%s " fmt, KBUILD_MODNAME
+
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+
+#include <soc/qcom/tcs.h>
+#include <dt-bindings/soc/qcom,rpmh-rsc.h>
+
+#include "rpmh-internal.h"
+
+#define RSC_DRV_TCS_OFFSET		672
+#define RSC_DRV_CMD_OFFSET		20
+
+/* DRV Configuration Information Register */
+#define DRV_PRNT_CHLD_CONFIG		0x0C
+#define DRV_NUM_TCS_MASK		0x3F
+#define DRV_NUM_TCS_SHIFT		6
+#define DRV_NCPT_MASK			0x1F
+#define DRV_NCPT_SHIFT			27
+
+/* Register offsets */
+#define RSC_DRV_IRQ_ENABLE		0x00
+#define RSC_DRV_IRQ_STATUS		0x04
+#define RSC_DRV_IRQ_CLEAR		0x08
+#define RSC_DRV_CMD_WAIT_FOR_CMPL	0x10
+#define RSC_DRV_CONTROL			0x14
+#define RSC_DRV_STATUS			0x18
+#define RSC_DRV_CMD_ENABLE		0x1C
+#define RSC_DRV_CMD_MSGID		0x30
+#define RSC_DRV_CMD_ADDR		0x34
+#define RSC_DRV_CMD_DATA		0x38
+#define RSC_DRV_CMD_STATUS		0x3C
+#define RSC_DRV_CMD_RESP_DATA		0x40
+
+#define TCS_AMC_MODE_ENABLE		BIT(16)
+#define TCS_AMC_MODE_TRIGGER		BIT(24)
+
+/* TCS CMD register bit mask */
+#define CMD_MSGID_LEN			8
+#define CMD_MSGID_RESP_REQ		BIT(8)
+#define CMD_MSGID_WRITE			BIT(16)
+#define CMD_STATUS_ISSUED		BIT(8)
+#define CMD_STATUS_COMPL		BIT(16)
+
+static u32 read_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id)
+{
+	return readl_relaxed(drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
+			     RSC_DRV_CMD_OFFSET * cmd_id);
+}
+
+static void write_tcs_cmd(struct rsc_drv *drv, int reg, int tcs_id, int cmd_id,
+			  u32 data)
+{
+	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id +
+		       RSC_DRV_CMD_OFFSET * cmd_id);
+}
+
+static void write_tcs_reg(struct rsc_drv *drv, int reg, int tcs_id, u32 data)
+{
+	writel_relaxed(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
+}
+
+static void write_tcs_reg_sync(struct rsc_drv *drv, int reg, int tcs_id,
+			       u32 data)
+{
+	writel(data, drv->tcs_base + reg + RSC_DRV_TCS_OFFSET * tcs_id);
+	for (;;) {
+		if (data == readl(drv->tcs_base + reg +
+				  RSC_DRV_TCS_OFFSET * tcs_id))
+			break;
+		udelay(1);
+	}
+}
+
+static bool tcs_is_free(struct rsc_drv *drv, int tcs_id)
+{
+	return !test_bit(tcs_id, drv->tcs_in_use) &&
+	       read_tcs_reg(drv, RSC_DRV_STATUS, tcs_id, 0);
+}
+
+static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type)
+{
+	return &drv->tcs[type];
+}
+
+static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
+					 const struct tcs_request *msg)
+{
+	int type;
+
+	switch (msg->state) {
+	case RPMH_ACTIVE_ONLY_STATE:
+		type = ACTIVE_TCS;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+
+	return get_tcs_of_type(drv, type);
+}
+
+static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
+						  int tcs_id)
+{
+	struct tcs_group *tcs;
+	int i;
+
+	for (i = 0; i < drv->num_tcs; i++) {
+		tcs = &drv->tcs[i];
+		if (tcs->mask & BIT(tcs_id))
+			return tcs->req[tcs_id - tcs->offset];
+	}
+
+	return NULL;
+}
+
+/**
+ * tcs_tx_done: TX Done interrupt handler
+ */
+static irqreturn_t tcs_tx_done(int irq, void *p)
+{
+	struct rsc_drv *drv = p;
+	int i, j;
+	unsigned long irq_status;
+	const struct tcs_request *req;
+	struct tcs_cmd *cmd;
+
+	irq_status = read_tcs_reg(drv, RSC_DRV_IRQ_STATUS, 0, 0);
+
+	for_each_set_bit(i, &irq_status, BITS_PER_LONG) {
+		req = get_req_from_tcs(drv, i);
+		if (!req) {
+			WARN_ON(1);
+			goto skip;
+		}
+
+		for (j = 0; j < req->num_cmds; j++) {
+			u32 sts;
+
+			cmd = &req->cmds[j];
+			sts = read_tcs_reg(drv, RSC_DRV_CMD_STATUS, i, j);
+			if (!(sts & CMD_STATUS_ISSUED) ||
+			   ((req->wait_for_compl || cmd->wait) &&
+			   !(sts & CMD_STATUS_COMPL))) {
+				pr_err("Incomplete request: %s: addr=%#x data=%#x",
+				       drv->name, cmd->addr, cmd->data);
+			}
+		}
+skip:
+		/* Reclaim the TCS */
+		write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0);
+		write_tcs_reg(drv, RSC_DRV_IRQ_CLEAR, 0, BIT(i));
+		spin_lock(&drv->lock);
+		clear_bit(i, drv->tcs_in_use);
+		spin_unlock(&drv->lock);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
+			       const struct tcs_request *msg)
+{
+	u32 msgid, cmd_msgid;
+	u32 cmd_enable = 0;
+	u32 cmd_complete;
+	struct tcs_cmd *cmd;
+	int i, j;
+
+	cmd_msgid = CMD_MSGID_LEN;
+	cmd_msgid |= msg->wait_for_compl ? CMD_MSGID_RESP_REQ : 0;
+	cmd_msgid |= CMD_MSGID_WRITE;
+
+	cmd_complete = read_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, 0);
+
+	for (i = 0, j = cmd_id; i < msg->num_cmds; i++, j++) {
+		cmd = &msg->cmds[i];
+		cmd_enable |= BIT(j);
+		cmd_complete |= cmd->wait << j;
+		msgid = cmd_msgid;
+		msgid |= cmd->wait ? CMD_MSGID_RESP_REQ : 0;
+		write_tcs_cmd(drv, RSC_DRV_CMD_MSGID, tcs_id, j, msgid);
+		write_tcs_cmd(drv, RSC_DRV_CMD_ADDR, tcs_id, j, cmd->addr);
+		write_tcs_cmd(drv, RSC_DRV_CMD_DATA, tcs_id, j, cmd->data);
+	}
+
+	write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, cmd_complete);
+	cmd_enable |= read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+	write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, cmd_enable);
+}
+
+static void __tcs_trigger(struct rsc_drv *drv, int tcs_id)
+{
+	u32 enable;
+
+	/*
+	 * HW req: Clear the DRV_CONTROL and enable TCS again
+	 * While clearing ensure that the AMC mode trigger is cleared
+	 * and then the mode enable is cleared.
+	 */
+	enable = read_tcs_reg(drv, RSC_DRV_CONTROL, tcs_id, 0);
+	enable &= ~TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable &= ~TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+
+	/* Enable the AMC mode on the TCS and then trigger the TCS */
+	enable = TCS_AMC_MODE_ENABLE;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+	enable |= TCS_AMC_MODE_TRIGGER;
+	write_tcs_reg_sync(drv, RSC_DRV_CONTROL, tcs_id, enable);
+}
+
+static int check_for_req_inflight(struct rsc_drv *drv, struct tcs_group *tcs,
+				  const struct tcs_request *msg)
+{
+	unsigned long curr_enabled;
+	u32 addr;
+	int i, j, k;
+	int tcs_id = tcs->offset;
+
+	for (i = 0; i < tcs->num_tcs; i++, tcs_id++) {
+		if (tcs_is_free(drv, tcs_id))
+			continue;
+
+		curr_enabled = read_tcs_reg(drv, RSC_DRV_CMD_ENABLE, tcs_id, 0);
+
+		for_each_set_bit(j, &curr_enabled, MAX_CMDS_PER_TCS) {
+			addr = read_tcs_reg(drv, RSC_DRV_CMD_ADDR, tcs_id, j);
+			for (k = 0; k < msg->num_cmds; k++) {
+				if (addr == msg->cmds[k].addr)
+					return -EBUSY;
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int find_free_tcs(struct tcs_group *tcs)
+{
+	int i;
+
+	for (i = 0; i < tcs->num_tcs; i++) {
+		if (tcs_is_free(tcs->drv, tcs->offset + i))
+			return tcs->offset + i;
+	}
+
+	return -EBUSY;
+}
+
+static int tcs_write(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	struct tcs_group *tcs;
+	int tcs_id;
+	unsigned long flags;
+	int ret;
+
+	tcs = get_tcs_for_msg(drv, msg);
+	if (IS_ERR(tcs))
+		return PTR_ERR(tcs);
+
+	spin_lock_irqsave(&tcs->lock, flags);
+	spin_lock(&drv->lock);
+	/*
+	 * The h/w does not like if we send a request to the same address,
+	 * when one is already in-flight or being processed.
+	 */
+	ret = check_for_req_inflight(drv, tcs, msg);
+	if (ret) {
+		spin_unlock(&drv->lock);
+		goto done_write;
+	}
+
+	tcs_id = find_free_tcs(tcs);
+	if (tcs_id < 0) {
+		ret = tcs_id;
+		spin_unlock(&drv->lock);
+		goto done_write;
+	}
+
+	tcs->req[tcs_id - tcs->offset] = msg;
+	set_bit(tcs_id, drv->tcs_in_use);
+	spin_unlock(&drv->lock);
+
+	__tcs_buffer_write(drv, tcs_id, 0, msg);
+	__tcs_trigger(drv, tcs_id);
+
+done_write:
+	spin_unlock_irqrestore(&tcs->lock, flags);
+	return ret;
+}
+
+/**
+ * rpmh_rsc_send_data: Validate the incoming message and write to the
+ * appropriate TCS block.
+ *
+ * @drv: the controller
+ * @msg: the data to be sent
+ *
+ * Return: 0 on success, -EINVAL on error.
+ * Note: This call blocks until a valid data is written to the TCS.
+ */
+int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	int ret;
+
+	if (!msg || !msg->cmds || !msg->num_cmds ||
+	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	do {
+		ret = tcs_write(drv, msg);
+		if (ret == -EBUSY) {
+			pr_info_ratelimited("TCS Busy, retrying RPMH message send: addr=%#x\n",
+					    msg->cmds[0].addr);
+			udelay(10);
+		}
+	} while (ret == -EBUSY);
+
+	return ret;
+}
+
+static int rpmh_probe_tcs_config(struct platform_device *pdev,
+				 struct rsc_drv *drv)
+{
+	struct tcs_type_config {
+		u32 type;
+		u32 n;
+	} tcs_cfg[TCS_TYPE_NR] = { { 0 } };
+	struct device_node *dn = pdev->dev.of_node;
+	u32 config, max_tcs, ncpt, offset;
+	int i, ret, n, st = 0;
+	struct tcs_group *tcs;
+	struct resource *res;
+	void __iomem *base;
+	char drv_id[10] = {0};
+
+	snprintf(drv_id, ARRAY_SIZE(drv_id), "drv-%d", drv->id);
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, drv_id);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	ret = of_property_read_u32(dn, "qcom,tcs-offset", &offset);
+	if (ret)
+		return ret;
+	drv->tcs_base = base + offset;
+
+	config = readl_relaxed(base + DRV_PRNT_CHLD_CONFIG);
+
+	max_tcs = config;
+	max_tcs &= DRV_NUM_TCS_MASK << (DRV_NUM_TCS_SHIFT * drv->id);
+	max_tcs = max_tcs >> (DRV_NUM_TCS_SHIFT * drv->id);
+
+	ncpt = config & (DRV_NCPT_MASK << DRV_NCPT_SHIFT);
+	ncpt = ncpt >> DRV_NCPT_SHIFT;
+
+	n = of_property_count_u32_elems(dn, "qcom,tcs-config");
+	if (n != 2 * TCS_TYPE_NR)
+		return -EINVAL;
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		ret = of_property_read_u32_index(dn, "qcom,tcs-config",
+						 i * 2, &tcs_cfg[i].type);
+		if (ret)
+			return ret;
+		if (tcs_cfg[i].type >= TCS_TYPE_NR)
+			return -EINVAL;
+
+		ret = of_property_read_u32_index(dn, "qcom,tcs-config",
+						 i * 2 + 1, &tcs_cfg[i].n);
+		if (ret)
+			return ret;
+		if (tcs_cfg[i].n > MAX_TCS_PER_TYPE)
+			return -EINVAL;
+	}
+
+	for (i = 0; i < TCS_TYPE_NR; i++) {
+		tcs = &drv->tcs[tcs_cfg[i].type];
+		if (tcs->drv)
+			return -EINVAL;
+		tcs->drv = drv;
+		tcs->type = tcs_cfg[i].type;
+		tcs->num_tcs = tcs_cfg[i].n;
+		tcs->ncpt = ncpt;
+		spin_lock_init(&tcs->lock);
+
+		if (!tcs->num_tcs || tcs->type == CONTROL_TCS)
+			continue;
+
+		if (st + tcs->num_tcs > max_tcs ||
+		    st + tcs->num_tcs >= BITS_PER_BYTE * sizeof(tcs->mask))
+			return -EINVAL;
+
+		tcs->mask = ((1 << tcs->num_tcs) - 1) << st;
+		tcs->offset = st;
+		st += tcs->num_tcs;
+	}
+
+	drv->num_tcs = st;
+
+	return 0;
+}
+
+static int rpmh_rsc_probe(struct platform_device *pdev)
+{
+	struct device_node *dn = pdev->dev.of_node;
+	struct rsc_drv *drv;
+	int ret, irq;
+
+	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
+	if (!drv)
+		return -ENOMEM;
+
+	ret = of_property_read_u32(dn, "qcom,drv-id", &drv->id);
+	if (ret)
+		return ret;
+
+	drv->name = of_get_property(dn, "label", NULL);
+	if (!drv->name)
+		drv->name = dev_name(&pdev->dev);
+
+	ret = rpmh_probe_tcs_config(pdev, drv);
+	if (ret)
+		return ret;
+
+	spin_lock_init(&drv->lock);
+	bitmap_zero(drv->tcs_in_use, MAX_TCS_NR);
+
+	irq = platform_get_irq(pdev, drv->id);
+	if (irq < 0)
+		return irq;
+
+	ret = devm_request_irq(&pdev->dev, irq, tcs_tx_done,
+			       IRQF_TRIGGER_HIGH | IRQF_NO_SUSPEND,
+			       drv->name, drv);
+	if (ret)
+		return ret;
+
+	/* Enable the active TCS to send requests immediately */
+	write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask);
+
+	return devm_of_platform_populate(&pdev->dev);
+}
+
+static const struct of_device_id rpmh_drv_match[] = {
+	{ .compatible = "qcom,rpmh-rsc", },
+	{ }
+};
+
+static struct platform_driver rpmh_driver = {
+	.probe = rpmh_rsc_probe,
+	.driver = {
+		  .name = "rpmh",
+		  .of_match_table = rpmh_drv_match,
+	},
+};
+
+static int __init rpmh_driver_init(void)
+{
+	return platform_driver_register(&rpmh_driver);
+}
+arch_initcall(rpmh_driver_init);
diff --git a/include/dt-bindings/soc/qcom,rpmh-rsc.h b/include/dt-bindings/soc/qcom,rpmh-rsc.h
new file mode 100644
index 000000000000..868f998ea998
--- /dev/null
+++ b/include/dt-bindings/soc/qcom,rpmh-rsc.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __DT_QCOM_RPMH_RSC_H__
+#define __DT_QCOM_RPMH_RSC_H__
+
+#define SLEEP_TCS	0
+#define WAKE_TCS	1
+#define ACTIVE_TCS	2
+#define CONTROL_TCS	3
+
+#endif /* __DT_QCOM_RPMH_RSC_H__ */
diff --git a/include/soc/qcom/tcs.h b/include/soc/qcom/tcs.h
new file mode 100644
index 000000000000..262876a59e86
--- /dev/null
+++ b/include/soc/qcom/tcs.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __SOC_QCOM_TCS_H__
+#define __SOC_QCOM_TCS_H__
+
+#define MAX_RPMH_PAYLOAD	16
+
+/**
+ * rpmh_state: state for the request
+ *
+ * RPMH_SLEEP_STATE:       State of the resource when the processor subsystem
+ *                         is powered down. There is no client using the
+ *                         resource actively.
+ * RPMH_WAKE_ONLY_STATE:   Resume resource state to the value previously
+ *                         requested before the processor was powered down.
+ * RPMH_ACTIVE_ONLY_STATE: Active or AMC mode requests. Resource state
+ *                         is aggregated immediately.
+ */
+enum rpmh_state {
+	RPMH_SLEEP_STATE,
+	RPMH_WAKE_ONLY_STATE,
+	RPMH_ACTIVE_ONLY_STATE,
+};
+
+/**
+ * struct tcs_cmd: an individual request to RPMH.
+ *
+ * @addr: the address of the resource slv_id:18:16 | offset:0:15
+ * @data: the resource state request
+ * @wait: wait for this request to be complete before sending the next
+ */
+struct tcs_cmd {
+	u32 addr;
+	u32 data;
+	u32 wait;
+};
+
+/**
+ * struct tcs_request: A set of tcs_cmds sent together in a TCS
+ *
+ * @state:          state for the request.
+ * @wait_for_compl: wait until we get a response from the h/w accelerator
+ * @num_cmds:       the number of @cmds in this request
+ * @cmds:           an array of tcs_cmds
+ */
+struct tcs_request {
+	enum rpmh_state state;
+	u32 wait_for_compl;
+	u32 num_cmds;
+	struct tcs_cmd *cmds;
+};
+
+#endif /* __SOC_QCOM_TCS_H__ */
-- 
cgit v1.2.3


From 2e4690a09fca9a8314e22ff98702c52a30211e25 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:56:59 +0530
Subject: dt-bindings: introduce RPMH RSC bindings for Qualcomm SoCs

Add device binding documentation for Qualcomm Technology Inc's RPMH RSC
driver. The driver is used for communicating resource state requests for
shared resources.

Cc: devicetree@vger.kernel.org
Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
[rplsssn@codeaurora.org: minor order correction for TCS type]
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 .../devicetree/bindings/soc/qcom/rpmh-rsc.txt      | 137 +++++++++++++++++++++
 1 file changed, 137 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/soc/qcom/rpmh-rsc.txt

diff --git a/Documentation/devicetree/bindings/soc/qcom/rpmh-rsc.txt b/Documentation/devicetree/bindings/soc/qcom/rpmh-rsc.txt
new file mode 100644
index 000000000000..9b86d1eff219
--- /dev/null
+++ b/Documentation/devicetree/bindings/soc/qcom/rpmh-rsc.txt
@@ -0,0 +1,137 @@
+RPMH RSC:
+------------
+
+Resource Power Manager Hardened (RPMH) is the mechanism for communicating with
+the hardened resource accelerators on Qualcomm SoCs. Requests to the resources
+can be written to the Trigger Command Set (TCS)  registers and using a (addr,
+val) pair and triggered. Messages in the TCS are then sent in sequence over an
+internal bus.
+
+The hardware block (Direct Resource Voter or DRV) is a part of the h/w entity
+(Resource State Coordinator a.k.a RSC) that can handle multiple sleep and
+active/wake resource requests. Multiple such DRVs can exist in a SoC and can
+be written to from Linux. The structure of each DRV follows the same template
+with a few variations that are captured by the properties here.
+
+A TCS may be triggered from Linux or triggered by the F/W after all the CPUs
+have powered off to facilitate idle power saving. TCS could be classified as -
+
+	ACTIVE  /* Triggered by Linux */
+	SLEEP   /* Triggered by F/W */
+	WAKE    /* Triggered by F/W */
+	CONTROL /* Triggered by F/W */
+
+The order in which they are described in the DT, should match the hardware
+configuration.
+
+Requests can be made for the state of a resource, when the subsystem is active
+or idle. When all subsystems like Modem, GPU, CPU are idle, the resource state
+will be an aggregate of the sleep votes from each of those subsystems. Clients
+may request a sleep value for their shared resources in addition to the active
+mode requests.
+
+Properties:
+
+- compatible:
+	Usage: required
+	Value type: <string>
+	Definition: Should be "qcom,rpmh-rsc".
+
+- reg:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: The first register specifies the base address of the
+		    DRV(s). The number of DRVs in the dependent on the RSC.
+	            The tcs-offset specifies the start address of the
+	            TCS in the DRVs.
+
+- reg-names:
+	Usage: required
+	Value type: <string>
+	Definition: Maps the register specified in the reg property. Must be
+	            "drv-0", "drv-1", "drv-2" etc and "tcs-offset". The
+
+- interrupts:
+	Usage: required
+	Value type: <prop-encoded-interrupt>
+	Definition: The interrupt that trips when a message complete/response
+	           is received for this DRV from the accelerators.
+
+- qcom,drv-id:
+	Usage: required
+	Value type: <u32>
+	Definition: The id of the DRV in the RSC block that will be used by
+		    this controller.
+
+- qcom,tcs-config:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: The tuple defining the configuration of TCS.
+	            Must have 2 cells which describe each TCS type.
+	            <type number_of_tcs>.
+	            The order of the TCS must match the hardware
+	            configuration.
+	- Cell #1 (TCS Type): TCS types to be specified -
+	            ACTIVE_TCS
+	            SLEEP_TCS
+	            WAKE_TCS
+	            CONTROL_TCS
+	- Cell #2 (Number of TCS): <u32>
+
+- label:
+	Usage: optional
+	Value type: <string>
+	Definition: Name for the RSC. The name would be used in trace logs.
+
+Drivers that want to use the RSC to communicate with RPMH must specify their
+bindings as child nodes of the RSC controllers they wish to communicate with.
+
+Example 1:
+
+For a TCS whose RSC base address is is 0x179C0000 and is at a DRV id of 2, the
+register offsets for DRV2 start at 0D00, the register calculations are like
+this -
+DRV0: 0x179C0000
+DRV2: 0x179C0000 + 0x10000 = 0x179D0000
+DRV2: 0x179C0000 + 0x10000 * 2 = 0x179E0000
+TCS-OFFSET: 0xD00
+
+	apps_rsc: rsc@179c0000 {
+		label = "apps_rsc";
+		compatible = "qcom,rpmh-rsc";
+		reg = <0x179c0000 0x10000>,
+		      <0x179d0000 0x10000>,
+		      <0x179e0000 0x10000>;
+		reg-names = "drv-0", "drv-1", "drv-2";
+		interrupts = <GIC_SPI 3 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 4 IRQ_TYPE_LEVEL_HIGH>,
+			     <GIC_SPI 5 IRQ_TYPE_LEVEL_HIGH>;
+		qcom,tcs-offset = <0xd00>;
+		qcom,drv-id = <2>;
+		qcom,tcs-config = <ACTIVE_TCS  2>,
+				  <SLEEP_TCS   3>,
+				  <WAKE_TCS    3>,
+				  <CONTROL_TCS 1>;
+	};
+
+Example 2:
+
+For a TCS whose RSC base address is 0xAF20000 and is at DRV id of 0, the
+register offsets for DRV0 start at 01C00, the register calculations are like
+this -
+DRV0: 0xAF20000
+TCS-OFFSET: 0x1C00
+
+	disp_rsc: rsc@af20000 {
+		label = "disp_rsc";
+		compatible = "qcom,rpmh-rsc";
+		reg = <0xaf20000 0x10000>;
+		reg-names = "drv-0";
+		interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>;
+		qcom,tcs-offset = <0x1c00>;
+		qcom,drv-id = <0>;
+		qcom,tcs-config = <ACTIVE_TCS  0>,
+				  <SLEEP_TCS   1>,
+				  <WAKE_TCS    1>,
+				  <CONTROL_TCS 0>;
+	};
-- 
cgit v1.2.3


From fc087fe5a45e7210be89fe015505e1bb3746395c Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:00 +0530
Subject: drivers: qcom: rpmh-rsc: log RPMH requests in FTRACE

Log sent RPMH requests and interrupt responses in FTRACE.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
[rplsssn@codeaurora.org: rebase to v4.18-rc1 & fix merge conflict]
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/Makefile     |  1 +
 drivers/soc/qcom/rpmh-rsc.c   | 11 +++++-
 drivers/soc/qcom/trace-rpmh.h | 82 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 93 insertions(+), 1 deletion(-)
 create mode 100644 drivers/soc/qcom/trace-rpmh.h

diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index b2faf9aeed3f..036ecc45cbbd 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -1,4 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
+CFLAGS_rpmh-rsc.o := -I$(src)
 obj-$(CONFIG_QCOM_GENI_SE) +=	qcom-geni-se.o
 obj-$(CONFIG_QCOM_COMMAND_DB) += cmd-db.o
 obj-$(CONFIG_QCOM_GLINK_SSR) +=	glink_ssr.o
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index c5e0793cdfb7..89d41cdd8d71 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -23,6 +23,9 @@
 
 #include "rpmh-internal.h"
 
+#define CREATE_TRACE_POINTS
+#include "trace-rpmh.h"
+
 #define RSC_DRV_TCS_OFFSET		672
 #define RSC_DRV_CMD_OFFSET		20
 
@@ -135,7 +138,7 @@ static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
 static irqreturn_t tcs_tx_done(int irq, void *p)
 {
 	struct rsc_drv *drv = p;
-	int i, j;
+	int i, j, err;
 	unsigned long irq_status;
 	const struct tcs_request *req;
 	struct tcs_cmd *cmd;
@@ -149,6 +152,7 @@ static irqreturn_t tcs_tx_done(int irq, void *p)
 			goto skip;
 		}
 
+		err = 0;
 		for (j = 0; j < req->num_cmds; j++) {
 			u32 sts;
 
@@ -159,8 +163,11 @@ static irqreturn_t tcs_tx_done(int irq, void *p)
 			   !(sts & CMD_STATUS_COMPL))) {
 				pr_err("Incomplete request: %s: addr=%#x data=%#x",
 				       drv->name, cmd->addr, cmd->data);
+				err = -EIO;
 			}
 		}
+
+		trace_rpmh_tx_done(drv, i, req, err);
 skip:
 		/* Reclaim the TCS */
 		write_tcs_reg(drv, RSC_DRV_CMD_ENABLE, i, 0);
@@ -194,9 +201,11 @@ static void __tcs_buffer_write(struct rsc_drv *drv, int tcs_id, int cmd_id,
 		cmd_complete |= cmd->wait << j;
 		msgid = cmd_msgid;
 		msgid |= cmd->wait ? CMD_MSGID_RESP_REQ : 0;
+
 		write_tcs_cmd(drv, RSC_DRV_CMD_MSGID, tcs_id, j, msgid);
 		write_tcs_cmd(drv, RSC_DRV_CMD_ADDR, tcs_id, j, cmd->addr);
 		write_tcs_cmd(drv, RSC_DRV_CMD_DATA, tcs_id, j, cmd->data);
+		trace_rpmh_send_msg(drv, tcs_id, j, msgid, cmd);
 	}
 
 	write_tcs_reg(drv, RSC_DRV_CMD_WAIT_FOR_CMPL, tcs_id, cmd_complete);
diff --git a/drivers/soc/qcom/trace-rpmh.h b/drivers/soc/qcom/trace-rpmh.h
new file mode 100644
index 000000000000..feb0cb455e37
--- /dev/null
+++ b/drivers/soc/qcom/trace-rpmh.h
@@ -0,0 +1,82 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#if !defined(_TRACE_RPMH_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_RPMH_H
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM rpmh
+
+#include <linux/tracepoint.h>
+#include "rpmh-internal.h"
+
+TRACE_EVENT(rpmh_tx_done,
+
+	TP_PROTO(struct rsc_drv *d, int m, const struct tcs_request *r, int e),
+
+	TP_ARGS(d, m, r, e),
+
+	TP_STRUCT__entry(
+			 __string(name, d->name)
+			 __field(int, m)
+			 __field(u32, addr)
+			 __field(u32, data)
+			 __field(int, err)
+	),
+
+	TP_fast_assign(
+		       __assign_str(name, d->name);
+		       __entry->m = m;
+		       __entry->addr = r->cmds[0].addr;
+		       __entry->data = r->cmds[0].data;
+		       __entry->err = e;
+	),
+
+	TP_printk("%s: ack: tcs-m: %d addr: %#x data: %#x errno: %d",
+		  __get_str(name), __entry->m, __entry->addr, __entry->data,
+		  __entry->err)
+);
+
+TRACE_EVENT(rpmh_send_msg,
+
+	TP_PROTO(struct rsc_drv *d, int m, int n, u32 h,
+		 const struct tcs_cmd *c),
+
+	TP_ARGS(d, m, n, h, c),
+
+	TP_STRUCT__entry(
+			 __string(name, d->name)
+			 __field(int, m)
+			 __field(int, n)
+			 __field(u32, hdr)
+			 __field(u32, addr)
+			 __field(u32, data)
+			 __field(bool, wait)
+	),
+
+	TP_fast_assign(
+		       __assign_str(name, d->name);
+		       __entry->m = m;
+		       __entry->n = n;
+		       __entry->hdr = h;
+		       __entry->addr = c->addr;
+		       __entry->data = c->data;
+		       __entry->wait = c->wait;
+	),
+
+	TP_printk("%s: send-msg: tcs(m): %d cmd(n): %d msgid: %#x addr: %#x data: %#x complete: %d",
+		  __get_str(name), __entry->m, __entry->n, __entry->hdr,
+		  __entry->addr, __entry->data, __entry->wait)
+);
+
+#endif /* _TRACE_RPMH_H */
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace-rpmh
+
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From c1038456b02b86cc4445441a8d33c5aca0ac103e Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:01 +0530
Subject: drivers: qcom: rpmh: add RPMH helper functions

Sending RPMH requests and waiting for response from the controller
through a callback is common functionality across all platform drivers.
To simplify drivers, add a library functions to create RPMH client and
send resource state requests.

rpmh_write() is a synchronous blocking call that can be used to send
active state requests.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/Makefile        |   4 +-
 drivers/soc/qcom/rpmh-internal.h |  31 ++++++++++-
 drivers/soc/qcom/rpmh-rsc.c      |   6 +-
 drivers/soc/qcom/rpmh.c          | 116 +++++++++++++++++++++++++++++++++++++++
 include/soc/qcom/rpmh.h          |  25 +++++++++
 5 files changed, 179 insertions(+), 3 deletions(-)
 create mode 100644 drivers/soc/qcom/rpmh.c
 create mode 100644 include/soc/qcom/rpmh.h

diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index 036ecc45cbbd..f25b54cd6cf8 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -9,7 +9,9 @@ obj-$(CONFIG_QCOM_PM)	+=	spm.o
 obj-$(CONFIG_QCOM_QMI_HELPERS)	+= qmi_helpers.o
 qmi_helpers-y	+= qmi_encdec.o qmi_interface.o
 obj-$(CONFIG_QCOM_RMTFS_MEM)	+= rmtfs_mem.o
-obj-$(CONFIG_QCOM_RPMH)	+=	rpmh-rsc.o
+obj-$(CONFIG_QCOM_RPMH)		+= qcom_rpmh.o
+qcom_rpmh-y			+= rpmh-rsc.o
+qcom_rpmh-y			+= rpmh.o
 obj-$(CONFIG_QCOM_SMD_RPM)	+= smd-rpm.o
 obj-$(CONFIG_QCOM_SMEM) +=	smem.o
 obj-$(CONFIG_QCOM_SMEM_STATE) += smem_state.o
diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
index cc29176f1303..1e687f719301 100644
--- a/drivers/soc/qcom/rpmh-internal.h
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -41,6 +41,32 @@ struct tcs_group {
 	const struct tcs_request *req[MAX_TCS_PER_TYPE];
 };
 
+/**
+ * struct rpmh_request: the message to be sent to rpmh-rsc
+ *
+ * @msg: the request
+ * @cmd: the payload that will be part of the @msg
+ * @completion: triggered when request is done
+ * @dev: the device making the request
+ * @err: err return from the controller
+ */
+struct rpmh_request {
+	struct tcs_request msg;
+	struct tcs_cmd cmd[MAX_RPMH_PAYLOAD];
+	struct completion *completion;
+	const struct device *dev;
+	int err;
+};
+
+/**
+ * struct rpmh_ctrlr: our representation of the controller
+ *
+ * @drv: the controller instance
+ */
+struct rpmh_ctrlr {
+	struct rsc_drv *drv;
+};
+
 /**
  * struct rsc_drv: the Direct Resource Voter (DRV) of the
  * Resource State Coordinator controller (RSC)
@@ -52,6 +78,7 @@ struct tcs_group {
  * @tcs:        TCS groups
  * @tcs_in_use: s/w state of the TCS
  * @lock:       synchronize state of the controller
+ * @client:     handle to the DRV's client.
  */
 struct rsc_drv {
 	const char *name;
@@ -61,9 +88,11 @@ struct rsc_drv {
 	struct tcs_group tcs[TCS_TYPE_NR];
 	DECLARE_BITMAP(tcs_in_use, MAX_TCS_NR);
 	spinlock_t lock;
+	struct rpmh_ctrlr client;
 };
 
-
 int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg);
 
+void rpmh_tx_done(const struct tcs_request *msg, int r);
+
 #endif /* __RPM_INTERNAL_H__ */
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 89d41cdd8d71..91f8d60d17cc 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -138,7 +138,7 @@ static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
 static irqreturn_t tcs_tx_done(int irq, void *p)
 {
 	struct rsc_drv *drv = p;
-	int i, j, err;
+	int i, j, err = 0;
 	unsigned long irq_status;
 	const struct tcs_request *req;
 	struct tcs_cmd *cmd;
@@ -175,6 +175,8 @@ skip:
 		spin_lock(&drv->lock);
 		clear_bit(i, drv->tcs_in_use);
 		spin_unlock(&drv->lock);
+		if (req)
+			rpmh_tx_done(req, err);
 	}
 
 	return IRQ_HANDLED;
@@ -467,6 +469,8 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 	/* Enable the active TCS to send requests immediately */
 	write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask);
 
+	dev_set_drvdata(&pdev->dev, drv);
+
 	return devm_of_platform_populate(&pdev->dev);
 }
 
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
new file mode 100644
index 000000000000..5e022cba8ab5
--- /dev/null
+++ b/drivers/soc/qcom/rpmh.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/atomic.h>
+#include <linux/bug.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/wait.h>
+
+#include <soc/qcom/rpmh.h>
+
+#include "rpmh-internal.h"
+
+#define RPMH_TIMEOUT_MS			msecs_to_jiffies(10000)
+
+#define DEFINE_RPMH_MSG_ONSTACK(dev, s, q, name)	\
+	struct rpmh_request name = {			\
+		.msg = {				\
+			.state = s,			\
+			.cmds = name.cmd,		\
+			.num_cmds = 0,			\
+			.wait_for_compl = true,		\
+		},					\
+		.cmd = { { 0 } },			\
+		.completion = q,			\
+		.dev = dev,				\
+	}
+
+#define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client)
+
+static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev)
+{
+	struct rsc_drv *drv = dev_get_drvdata(dev->parent);
+
+	return &drv->client;
+}
+
+void rpmh_tx_done(const struct tcs_request *msg, int r)
+{
+	struct rpmh_request *rpm_msg = container_of(msg, struct rpmh_request,
+						    msg);
+	struct completion *compl = rpm_msg->completion;
+
+	rpm_msg->err = r;
+
+	if (r)
+		dev_err(rpm_msg->dev, "RPMH TX fail in msg addr=%#x, err=%d\n",
+			rpm_msg->msg.cmds[0].addr, r);
+
+	/* Signal the blocking thread we are done */
+	if (compl)
+		complete(compl);
+}
+
+/**
+ * __rpmh_write: send the RPMH request
+ *
+ * @dev: The device making the request
+ * @state: Active/Sleep request type
+ * @rpm_msg: The data that needs to be sent (cmds).
+ */
+static int __rpmh_write(const struct device *dev, enum rpmh_state state,
+			struct rpmh_request *rpm_msg)
+{
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+
+	rpm_msg->msg.state = state;
+
+	if (state != RPMH_ACTIVE_ONLY_STATE)
+		return -EINVAL;
+
+	WARN_ON(irqs_disabled());
+
+	return rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg);
+}
+
+/**
+ * rpmh_write: Write a set of RPMH commands and block until response
+ *
+ * @rc: The RPMH handle got from rpmh_get_client
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The number of elements in @cmd
+ *
+ * May sleep. Do not call from atomic contexts.
+ */
+int rpmh_write(const struct device *dev, enum rpmh_state state,
+	       const struct tcs_cmd *cmd, u32 n)
+{
+	DECLARE_COMPLETION_ONSTACK(compl);
+	DEFINE_RPMH_MSG_ONSTACK(dev, state, &compl, rpm_msg);
+	int ret;
+
+	if (!cmd || !n || n > MAX_RPMH_PAYLOAD)
+		return -EINVAL;
+
+	memcpy(rpm_msg.cmd, cmd, n * sizeof(*cmd));
+	rpm_msg.msg.num_cmds = n;
+
+	ret = __rpmh_write(dev, state, &rpm_msg);
+	if (ret)
+		return ret;
+
+	ret = wait_for_completion_timeout(&compl, RPMH_TIMEOUT_MS);
+	WARN_ON(!ret);
+	return (ret > 0) ? 0 : -ETIMEDOUT;
+}
+EXPORT_SYMBOL(rpmh_write);
diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h
new file mode 100644
index 000000000000..c1d0f902bd71
--- /dev/null
+++ b/include/soc/qcom/rpmh.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef __SOC_QCOM_RPMH_H__
+#define __SOC_QCOM_RPMH_H__
+
+#include <soc/qcom/tcs.h>
+#include <linux/platform_device.h>
+
+
+#if IS_ENABLED(CONFIG_QCOM_RPMH)
+int rpmh_write(const struct device *dev, enum rpmh_state state,
+	       const struct tcs_cmd *cmd, u32 n);
+
+#else
+
+static inline int rpmh_write(const struct device *dev, enum rpmh_state state,
+			     const struct tcs_cmd *cmd, u32 n)
+{ return -ENODEV; }
+
+#endif /* CONFIG_QCOM_RPMH */
+
+#endif /* __SOC_QCOM_RPMH_H__ */
-- 
cgit v1.2.3


From fa460e453a83af0054dc3d3d210a6617db333a20 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:02 +0530
Subject: drivers: qcom: rpmh-rsc: write sleep/wake requests to TCS

Sleep and wake requests are sent when the application processor
subsystem of the SoC is entering deep sleep states like in suspend.
These requests help lower the system power requirements when the
resources are not in use.

Sleep and wake requests are written to the TCS slots but are not
triggered at the time of writing. The TCS are triggered by the firmware
after the last of the CPUs has executed its WFI. Since these requests
may come in different batches of requests, it is the job of this
controller driver to find and arrange the requests into the available
TCSes.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Reviewed-by: Evan Green <evgreen@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-internal.h |   8 +++
 drivers/soc/qcom/rpmh-rsc.c      | 121 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 129 insertions(+)

diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
index 1e687f719301..af4da1cb6558 100644
--- a/drivers/soc/qcom/rpmh-internal.h
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -14,6 +14,7 @@
 #define MAX_CMDS_PER_TCS		16
 #define MAX_TCS_PER_TYPE		3
 #define MAX_TCS_NR			(MAX_TCS_PER_TYPE * TCS_TYPE_NR)
+#define MAX_TCS_SLOTS			(MAX_CMDS_PER_TCS * MAX_TCS_PER_TYPE)
 
 struct rsc_drv;
 
@@ -29,6 +30,8 @@ struct rsc_drv;
  * @ncpt:      number of commands in each TCS
  * @lock:      lock for synchronizing this TCS writes
  * @req:       requests that are sent from the TCS
+ * @cmd_cache: flattened cache of cmds in sleep/wake TCS
+ * @slots:     indicates which of @cmd_addr are occupied
  */
 struct tcs_group {
 	struct rsc_drv *drv;
@@ -39,6 +42,8 @@ struct tcs_group {
 	int ncpt;
 	spinlock_t lock;
 	const struct tcs_request *req[MAX_TCS_PER_TYPE];
+	u32 *cmd_cache;
+	DECLARE_BITMAP(slots, MAX_TCS_SLOTS);
 };
 
 /**
@@ -92,6 +97,9 @@ struct rsc_drv {
 };
 
 int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg);
+int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv,
+			     const struct tcs_request *msg);
+int rpmh_rsc_invalidate(struct rsc_drv *drv);
 
 void rpmh_tx_done(const struct tcs_request *msg, int r);
 
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 91f8d60d17cc..604ebb6757cc 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -110,6 +110,12 @@ static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 	case RPMH_ACTIVE_ONLY_STATE:
 		type = ACTIVE_TCS;
 		break;
+	case RPMH_WAKE_ONLY_STATE:
+		type = WAKE_TCS;
+		break;
+	case RPMH_SLEEP_STATE:
+		type = SLEEP_TCS;
+		break;
 	default:
 		return ERR_PTR(-EINVAL);
 	}
@@ -349,6 +355,108 @@ int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
 	return ret;
 }
 
+static int find_match(const struct tcs_group *tcs, const struct tcs_cmd *cmd,
+		      int len)
+{
+	int i, j;
+
+	/* Check for already cached commands */
+	for_each_set_bit(i, tcs->slots, MAX_TCS_SLOTS) {
+		if (tcs->cmd_cache[i] != cmd[0].addr)
+			continue;
+		if (i + len >= tcs->num_tcs * tcs->ncpt)
+			goto seq_err;
+		for (j = 0; j < len; j++) {
+			if (tcs->cmd_cache[i + j] != cmd[j].addr)
+				goto seq_err;
+		}
+		return i;
+	}
+
+	return -ENODATA;
+
+seq_err:
+	WARN(1, "Message does not match previous sequence.\n");
+	return -EINVAL;
+}
+
+static int find_slots(struct tcs_group *tcs, const struct tcs_request *msg,
+		      int *tcs_id, int *cmd_id)
+{
+	int slot, offset;
+	int i = 0;
+
+	/* Find if we already have the msg in our TCS */
+	slot = find_match(tcs, msg->cmds, msg->num_cmds);
+	if (slot >= 0)
+		goto copy_data;
+
+	/* Do over, until we can fit the full payload in a TCS */
+	do {
+		slot = bitmap_find_next_zero_area(tcs->slots, MAX_TCS_SLOTS,
+						  i, msg->num_cmds, 0);
+		if (slot == tcs->num_tcs * tcs->ncpt)
+			return -ENOMEM;
+		i += tcs->ncpt;
+	} while (slot + msg->num_cmds - 1 >= i);
+
+copy_data:
+	bitmap_set(tcs->slots, slot, msg->num_cmds);
+	/* Copy the addresses of the resources over to the slots */
+	for (i = 0; i < msg->num_cmds; i++)
+		tcs->cmd_cache[slot + i] = msg->cmds[i].addr;
+
+	offset = slot / tcs->ncpt;
+	*tcs_id = offset + tcs->offset;
+	*cmd_id = slot % tcs->ncpt;
+
+	return 0;
+}
+
+static int tcs_ctrl_write(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	struct tcs_group *tcs;
+	int tcs_id = 0, cmd_id = 0;
+	unsigned long flags;
+	int ret;
+
+	tcs = get_tcs_for_msg(drv, msg);
+	if (IS_ERR(tcs))
+		return PTR_ERR(tcs);
+
+	spin_lock_irqsave(&tcs->lock, flags);
+	/* find the TCS id and the command in the TCS to write to */
+	ret = find_slots(tcs, msg, &tcs_id, &cmd_id);
+	if (!ret)
+		__tcs_buffer_write(drv, tcs_id, cmd_id, msg);
+	spin_unlock_irqrestore(&tcs->lock, flags);
+
+	return ret;
+}
+
+/**
+ * rpmh_rsc_write_ctrl_data: Write request to the controller
+ *
+ * @drv: the controller
+ * @msg: the data to be written to the controller
+ *
+ * There is no response returned for writing the request to the controller.
+ */
+int rpmh_rsc_write_ctrl_data(struct rsc_drv *drv, const struct tcs_request *msg)
+{
+	if (!msg || !msg->cmds || !msg->num_cmds ||
+	    msg->num_cmds > MAX_RPMH_PAYLOAD) {
+		pr_err("Payload error\n");
+		return -EINVAL;
+	}
+
+	/* Data sent to this API will not be sent immediately */
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE)
+		return -EINVAL;
+
+	return tcs_ctrl_write(drv, msg);
+}
+
 static int rpmh_probe_tcs_config(struct platform_device *pdev,
 				 struct rsc_drv *drv)
 {
@@ -424,6 +532,19 @@ static int rpmh_probe_tcs_config(struct platform_device *pdev,
 		tcs->mask = ((1 << tcs->num_tcs) - 1) << st;
 		tcs->offset = st;
 		st += tcs->num_tcs;
+
+		/*
+		 * Allocate memory to cache sleep and wake requests to
+		 * avoid reading TCS register memory.
+		 */
+		if (tcs->type == ACTIVE_TCS)
+			continue;
+
+		tcs->cmd_cache = devm_kcalloc(&pdev->dev,
+					      tcs->num_tcs * ncpt, sizeof(u32),
+					      GFP_KERNEL);
+		if (!tcs->cmd_cache)
+			return -ENOMEM;
 	}
 
 	drv->num_tcs = st;
-- 
cgit v1.2.3


From 9a3afcfbc0cc9af5e18ff53bb0d41a30e0d3d896 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:03 +0530
Subject: drivers: qcom: rpmh-rsc: allow invalidation of sleep/wake TCS

Allow sleep and wake commands to be cleared from the respective TCSes,
so that they can be re-populated.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-rsc.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 604ebb6757cc..fed8459c0ef6 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -101,6 +101,50 @@ static struct tcs_group *get_tcs_of_type(struct rsc_drv *drv, int type)
 	return &drv->tcs[type];
 }
 
+static int tcs_invalidate(struct rsc_drv *drv, int type)
+{
+	int m;
+	struct tcs_group *tcs;
+
+	tcs = get_tcs_of_type(drv, type);
+	if (IS_ERR(tcs))
+		return PTR_ERR(tcs);
+
+	spin_lock(&tcs->lock);
+	if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) {
+		spin_unlock(&tcs->lock);
+		return 0;
+	}
+
+	for (m = tcs->offset; m < tcs->offset + tcs->num_tcs; m++) {
+		if (!tcs_is_free(drv, m)) {
+			spin_unlock(&tcs->lock);
+			return -EAGAIN;
+		}
+		write_tcs_reg_sync(drv, RSC_DRV_CMD_ENABLE, m, 0);
+	}
+	bitmap_zero(tcs->slots, MAX_TCS_SLOTS);
+	spin_unlock(&tcs->lock);
+
+	return 0;
+}
+
+/**
+ * rpmh_rsc_invalidate - Invalidate sleep and wake TCSes
+ *
+ * @drv: the RSC controller
+ */
+int rpmh_rsc_invalidate(struct rsc_drv *drv)
+{
+	int ret;
+
+	ret = tcs_invalidate(drv, SLEEP_TCS);
+	if (!ret)
+		ret = tcs_invalidate(drv, WAKE_TCS);
+
+	return ret;
+}
+
 static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 					 const struct tcs_request *msg)
 {
-- 
cgit v1.2.3


From 600513dfeef33cb05c694d1b13d319b9e8cde536 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:04 +0530
Subject: drivers: qcom: rpmh: cache sleep/wake state requests

Active state requests are sent immediately to the RSC controller, while
sleep and wake state requests are cached in this driver to avoid taxing
the RSC controller repeatedly. The cached values will be sent to the
controller when the rpmh_flush() is called.

Generally, flushing is a system PM activity and may be called from the
system PM drivers when the system is entering suspend or deeper sleep
modes during cpuidle.

Also allow invalidating the cached requests, so they may be re-populated
again.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
[rplsssn: remove unneeded semicolon, address line over 80chars error]
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Reviewed-by: Evan Green <evgreen@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-internal.h |   8 +-
 drivers/soc/qcom/rpmh-rsc.c      |   3 +
 drivers/soc/qcom/rpmh.c          | 201 ++++++++++++++++++++++++++++++++++++++-
 include/soc/qcom/rpmh.h          |  11 +++
 4 files changed, 216 insertions(+), 7 deletions(-)

diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
index af4da1cb6558..101145c9db1c 100644
--- a/drivers/soc/qcom/rpmh-internal.h
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -66,10 +66,14 @@ struct rpmh_request {
 /**
  * struct rpmh_ctrlr: our representation of the controller
  *
- * @drv: the controller instance
+ * @cache: the list of cached requests
+ * @cache_lock: synchronize access to the cache data
+ * @dirty: was the cache updated since flush
  */
 struct rpmh_ctrlr {
-	struct rsc_drv *drv;
+	struct list_head cache;
+	spinlock_t cache_lock;
+	bool dirty;
 };
 
 /**
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index fed8459c0ef6..5d0dd0581904 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -634,6 +634,9 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 	/* Enable the active TCS to send requests immediately */
 	write_tcs_reg(drv, RSC_DRV_IRQ_ENABLE, 0, drv->tcs[ACTIVE_TCS].mask);
 
+	spin_lock_init(&drv->client.cache_lock);
+	INIT_LIST_HEAD(&drv->client.cache);
+
 	dev_set_drvdata(&pdev->dev, drv);
 
 	return devm_of_platform_populate(&pdev->dev);
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
index 5e022cba8ab5..c355ba13e73f 100644
--- a/drivers/soc/qcom/rpmh.c
+++ b/drivers/soc/qcom/rpmh.c
@@ -8,10 +8,12 @@
 #include <linux/interrupt.h>
 #include <linux/jiffies.h>
 #include <linux/kernel.h>
+#include <linux/list.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/wait.h>
 
@@ -36,6 +38,21 @@
 
 #define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client)
 
+/**
+ * struct cache_req: the request object for caching
+ *
+ * @addr: the address of the resource
+ * @sleep_val: the sleep vote
+ * @wake_val: the wake vote
+ * @list: linked list obj
+ */
+struct cache_req {
+	u32 addr;
+	u32 sleep_val;
+	u32 wake_val;
+	struct list_head list;
+};
+
 static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev)
 {
 	struct rsc_drv *drv = dev_get_drvdata(dev->parent);
@@ -60,26 +77,107 @@ void rpmh_tx_done(const struct tcs_request *msg, int r)
 		complete(compl);
 }
 
+static struct cache_req *__find_req(struct rpmh_ctrlr *ctrlr, u32 addr)
+{
+	struct cache_req *p, *req = NULL;
+
+	list_for_each_entry(p, &ctrlr->cache, list) {
+		if (p->addr == addr) {
+			req = p;
+			break;
+		}
+	}
+
+	return req;
+}
+
+static struct cache_req *cache_rpm_request(struct rpmh_ctrlr *ctrlr,
+					   enum rpmh_state state,
+					   struct tcs_cmd *cmd)
+{
+	struct cache_req *req;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	req = __find_req(ctrlr, cmd->addr);
+	if (req)
+		goto existing;
+
+	req = kzalloc(sizeof(*req), GFP_ATOMIC);
+	if (!req) {
+		req = ERR_PTR(-ENOMEM);
+		goto unlock;
+	}
+
+	req->addr = cmd->addr;
+	req->sleep_val = req->wake_val = UINT_MAX;
+	INIT_LIST_HEAD(&req->list);
+	list_add_tail(&req->list, &ctrlr->cache);
+
+existing:
+	switch (state) {
+	case RPMH_ACTIVE_ONLY_STATE:
+		if (req->sleep_val != UINT_MAX)
+			req->wake_val = cmd->data;
+		break;
+	case RPMH_WAKE_ONLY_STATE:
+		req->wake_val = cmd->data;
+		break;
+	case RPMH_SLEEP_STATE:
+		req->sleep_val = cmd->data;
+		break;
+	default:
+		break;
+	}
+
+	ctrlr->dirty = true;
+unlock:
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+
+	return req;
+}
+
 /**
- * __rpmh_write: send the RPMH request
+ * __rpmh_write: Cache and send the RPMH request
  *
  * @dev: The device making the request
  * @state: Active/Sleep request type
  * @rpm_msg: The data that needs to be sent (cmds).
+ *
+ * Cache the RPMH request and send if the state is ACTIVE_ONLY.
+ * SLEEP/WAKE_ONLY requests are not sent to the controller at
+ * this time. Use rpmh_flush() to send them to the controller.
  */
 static int __rpmh_write(const struct device *dev, enum rpmh_state state,
 			struct rpmh_request *rpm_msg)
 {
 	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret = -EINVAL;
+	struct cache_req *req;
+	int i;
 
 	rpm_msg->msg.state = state;
 
-	if (state != RPMH_ACTIVE_ONLY_STATE)
-		return -EINVAL;
+	/* Cache the request in our store and link the payload */
+	for (i = 0; i < rpm_msg->msg.num_cmds; i++) {
+		req = cache_rpm_request(ctrlr, state, &rpm_msg->msg.cmds[i]);
+		if (IS_ERR(req))
+			return PTR_ERR(req);
+	}
+
+	rpm_msg->msg.state = state;
 
-	WARN_ON(irqs_disabled());
+	if (state == RPMH_ACTIVE_ONLY_STATE) {
+		WARN_ON(irqs_disabled());
+		ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg);
+	} else {
+		ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr),
+				&rpm_msg->msg);
+		/* Clean up our call by spoofing tx_done */
+		rpmh_tx_done(&rpm_msg->msg, ret);
+	}
 
-	return rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg);
+	return ret;
 }
 
 /**
@@ -114,3 +212,96 @@ int rpmh_write(const struct device *dev, enum rpmh_state state,
 	return (ret > 0) ? 0 : -ETIMEDOUT;
 }
 EXPORT_SYMBOL(rpmh_write);
+
+static int is_req_valid(struct cache_req *req)
+{
+	return (req->sleep_val != UINT_MAX &&
+		req->wake_val != UINT_MAX &&
+		req->sleep_val != req->wake_val);
+}
+
+static int send_single(const struct device *dev, enum rpmh_state state,
+		       u32 addr, u32 data)
+{
+	DEFINE_RPMH_MSG_ONSTACK(dev, state, NULL, rpm_msg);
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+
+	/* Wake sets are always complete and sleep sets are not */
+	rpm_msg.msg.wait_for_compl = (state == RPMH_WAKE_ONLY_STATE);
+	rpm_msg.cmd[0].addr = addr;
+	rpm_msg.cmd[0].data = data;
+	rpm_msg.msg.num_cmds = 1;
+
+	return rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr), &rpm_msg.msg);
+}
+
+/**
+ * rpmh_flush: Flushes the buffered active and sleep sets to TCS
+ *
+ * @dev: The device making the request
+ *
+ * Return: -EBUSY if the controller is busy, probably waiting on a response
+ * to a RPMH request sent earlier.
+ *
+ * This function is always called from the sleep code from the last CPU
+ * that is powering down the entire system. Since no other RPMH API would be
+ * executing at this time, it is safe to run lockless.
+ */
+int rpmh_flush(const struct device *dev)
+{
+	struct cache_req *p;
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret;
+
+	if (!ctrlr->dirty) {
+		pr_debug("Skipping flush, TCS has latest data.\n");
+		return 0;
+	}
+
+	/*
+	 * Nobody else should be calling this function other than system PM,
+	 * hence we can run without locks.
+	 */
+	list_for_each_entry(p, &ctrlr->cache, list) {
+		if (!is_req_valid(p)) {
+			pr_debug("%s: skipping RPMH req: a:%#x s:%#x w:%#x",
+				 __func__, p->addr, p->sleep_val, p->wake_val);
+			continue;
+		}
+		ret = send_single(dev, RPMH_SLEEP_STATE, p->addr, p->sleep_val);
+		if (ret)
+			return ret;
+		ret = send_single(dev, RPMH_WAKE_ONLY_STATE,
+				  p->addr, p->wake_val);
+		if (ret)
+			return ret;
+	}
+
+	ctrlr->dirty = false;
+
+	return 0;
+}
+EXPORT_SYMBOL(rpmh_flush);
+
+/**
+ * rpmh_invalidate: Invalidate all sleep and active sets
+ * sets.
+ *
+ * @dev: The device making the request
+ *
+ * Invalidate the sleep and active values in the TCS blocks.
+ */
+int rpmh_invalidate(const struct device *dev)
+{
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	int ret;
+
+	ctrlr->dirty = true;
+
+	do {
+		ret = rpmh_rsc_invalidate(ctrlr_to_drv(ctrlr));
+	} while (ret == -EAGAIN);
+
+	return ret;
+}
+EXPORT_SYMBOL(rpmh_invalidate);
diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h
index c1d0f902bd71..42e62a0d26d8 100644
--- a/include/soc/qcom/rpmh.h
+++ b/include/soc/qcom/rpmh.h
@@ -14,12 +14,23 @@
 int rpmh_write(const struct device *dev, enum rpmh_state state,
 	       const struct tcs_cmd *cmd, u32 n);
 
+int rpmh_flush(const struct device *dev);
+
+int rpmh_invalidate(const struct device *dev);
+
 #else
 
 static inline int rpmh_write(const struct device *dev, enum rpmh_state state,
 			     const struct tcs_cmd *cmd, u32 n)
 { return -ENODEV; }
 
+
+static inline int rpmh_flush(const struct device *dev)
+{ return -ENODEV; }
+
+static inline int rpmh_invalidate(const struct device *dev)
+{ return -ENODEV; }
+
 #endif /* CONFIG_QCOM_RPMH */
 
 #endif /* __SOC_QCOM_RPMH_H__ */
-- 
cgit v1.2.3


From 564b5e24ccd4c840a7f84dfd952e5715dd9b3966 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:05 +0530
Subject: drivers: qcom: rpmh: allow requests to be sent asynchronously

Platform drivers that want to send a request but do not want to block
until the RPMH request completes have now a new API -
rpmh_write_async().

The API allocates memory and send the requests and returns the control
back to the platform driver. The tx_done callback from the controller is
handled in the context of the controller's thread and frees the
allocated memory. This API allows RPMH requests from atomic contexts as
well.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-internal.h |  2 ++
 drivers/soc/qcom/rpmh.c          | 51 ++++++++++++++++++++++++++++++++++++++++
 include/soc/qcom/rpmh.h          |  7 ++++++
 3 files changed, 60 insertions(+)

diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
index 101145c9db1c..6a8a4b7aeead 100644
--- a/drivers/soc/qcom/rpmh-internal.h
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -54,6 +54,7 @@ struct tcs_group {
  * @completion: triggered when request is done
  * @dev: the device making the request
  * @err: err return from the controller
+ * @needs_free: check to free dynamically allocated request object
  */
 struct rpmh_request {
 	struct tcs_request msg;
@@ -61,6 +62,7 @@ struct rpmh_request {
 	struct completion *completion;
 	const struct device *dev;
 	int err;
+	bool needs_free;
 };
 
 /**
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
index c355ba13e73f..1e3d34876af1 100644
--- a/drivers/soc/qcom/rpmh.c
+++ b/drivers/soc/qcom/rpmh.c
@@ -34,6 +34,7 @@
 		.cmd = { { 0 } },			\
 		.completion = q,			\
 		.dev = dev,				\
+		.needs_free = false,				\
 	}
 
 #define ctrlr_to_drv(ctrlr) container_of(ctrlr, struct rsc_drv, client)
@@ -75,6 +76,9 @@ void rpmh_tx_done(const struct tcs_request *msg, int r)
 	/* Signal the blocking thread we are done */
 	if (compl)
 		complete(compl);
+
+	if (rpm_msg->needs_free)
+		kfree(rpm_msg);
 }
 
 static struct cache_req *__find_req(struct rpmh_ctrlr *ctrlr, u32 addr)
@@ -180,6 +184,53 @@ static int __rpmh_write(const struct device *dev, enum rpmh_state state,
 	return ret;
 }
 
+static int __fill_rpmh_msg(struct rpmh_request *req, enum rpmh_state state,
+		const struct tcs_cmd *cmd, u32 n)
+{
+	if (!cmd || !n || n > MAX_RPMH_PAYLOAD)
+		return -EINVAL;
+
+	memcpy(req->cmd, cmd, n * sizeof(*cmd));
+
+	req->msg.state = state;
+	req->msg.cmds = req->cmd;
+	req->msg.num_cmds = n;
+
+	return 0;
+}
+
+/**
+ * rpmh_write_async: Write a set of RPMH commands
+ *
+ * @dev: The device making the request
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The number of elements in payload
+ *
+ * Write a set of RPMH commands, the order of commands is maintained
+ * and will be sent as a single shot.
+ */
+int rpmh_write_async(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 n)
+{
+	struct rpmh_request *rpm_msg;
+	int ret;
+
+	rpm_msg = kzalloc(sizeof(*rpm_msg), GFP_ATOMIC);
+	if (!rpm_msg)
+		return -ENOMEM;
+	rpm_msg->needs_free = true;
+
+	ret = __fill_rpmh_msg(rpm_msg, state, cmd, n);
+	if (ret) {
+		kfree(rpm_msg);
+		return ret;
+	}
+
+	return __rpmh_write(dev, state, rpm_msg);
+}
+EXPORT_SYMBOL(rpmh_write_async);
+
 /**
  * rpmh_write: Write a set of RPMH commands and block until response
  *
diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h
index 42e62a0d26d8..1161a5c77e75 100644
--- a/include/soc/qcom/rpmh.h
+++ b/include/soc/qcom/rpmh.h
@@ -14,6 +14,9 @@
 int rpmh_write(const struct device *dev, enum rpmh_state state,
 	       const struct tcs_cmd *cmd, u32 n);
 
+int rpmh_write_async(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 n);
+
 int rpmh_flush(const struct device *dev);
 
 int rpmh_invalidate(const struct device *dev);
@@ -24,6 +27,10 @@ static inline int rpmh_write(const struct device *dev, enum rpmh_state state,
 			     const struct tcs_cmd *cmd, u32 n)
 { return -ENODEV; }
 
+static inline int rpmh_write_async(const struct device *dev,
+				   enum rpmh_state state,
+				   const struct tcs_cmd *cmd, u32 n)
+{ return -ENODEV; }
 
 static inline int rpmh_flush(const struct device *dev)
 { return -ENODEV; }
-- 
cgit v1.2.3


From c8790cb6da58d3fa09dfa707aa486fe6769c23bc Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:06 +0530
Subject: drivers: qcom: rpmh: add support for batch RPMH request

Platform drivers need make a lot of resource state requests at the same
time, say, at the start or end of an usecase. It can be quite
inefficient to send each request separately. Instead they can give the
RPMH library a batch of requests to be sent and wait on the whole
transaction to be complete.

rpmh_write_batch() is a blocking call that can be used to send multiple
RPMH command sets. Each RPMH command set is set asynchronously and the
API blocks until all the command sets are complete and receive their
tx_done callbacks.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-internal.h |   2 +
 drivers/soc/qcom/rpmh-rsc.c      |   1 +
 drivers/soc/qcom/rpmh.c          | 159 ++++++++++++++++++++++++++++++++++++++-
 include/soc/qcom/rpmh.h          |   8 ++
 4 files changed, 168 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/qcom/rpmh-internal.h b/drivers/soc/qcom/rpmh-internal.h
index 6a8a4b7aeead..a7bbbb67991c 100644
--- a/drivers/soc/qcom/rpmh-internal.h
+++ b/drivers/soc/qcom/rpmh-internal.h
@@ -71,11 +71,13 @@ struct rpmh_request {
  * @cache: the list of cached requests
  * @cache_lock: synchronize access to the cache data
  * @dirty: was the cache updated since flush
+ * @batch_cache: Cache sleep and wake requests sent as batch
  */
 struct rpmh_ctrlr {
 	struct list_head cache;
 	spinlock_t cache_lock;
 	bool dirty;
+	struct list_head batch_cache;
 };
 
 /**
diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 5d0dd0581904..4c0c1f24911a 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -636,6 +636,7 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 
 	spin_lock_init(&drv->client.cache_lock);
 	INIT_LIST_HEAD(&drv->client.cache);
+	INIT_LIST_HEAD(&drv->client.batch_cache);
 
 	dev_set_drvdata(&pdev->dev, drv);
 
diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
index 1e3d34876af1..c7beb6841289 100644
--- a/drivers/soc/qcom/rpmh.c
+++ b/drivers/soc/qcom/rpmh.c
@@ -54,6 +54,20 @@ struct cache_req {
 	struct list_head list;
 };
 
+/**
+ * struct batch_cache_req - An entry in our batch catch
+ *
+ * @list: linked list obj
+ * @count: number of messages
+ * @rpm_msgs: the messages
+ */
+
+struct batch_cache_req {
+	struct list_head list;
+	int count;
+	struct rpmh_request rpm_msgs[];
+};
+
 static struct rpmh_ctrlr *get_rpmh_ctrlr(const struct device *dev)
 {
 	struct rsc_drv *drv = dev_get_drvdata(dev->parent);
@@ -73,10 +87,13 @@ void rpmh_tx_done(const struct tcs_request *msg, int r)
 		dev_err(rpm_msg->dev, "RPMH TX fail in msg addr=%#x, err=%d\n",
 			rpm_msg->msg.cmds[0].addr, r);
 
+	if (!compl)
+		goto exit;
+
 	/* Signal the blocking thread we are done */
-	if (compl)
-		complete(compl);
+	complete(compl);
 
+exit:
 	if (rpm_msg->needs_free)
 		kfree(rpm_msg);
 }
@@ -264,6 +281,138 @@ int rpmh_write(const struct device *dev, enum rpmh_state state,
 }
 EXPORT_SYMBOL(rpmh_write);
 
+static void cache_batch(struct rpmh_ctrlr *ctrlr, struct batch_cache_req *req)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_add_tail(&req->list, &ctrlr->batch_cache);
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+}
+
+static int flush_batch(struct rpmh_ctrlr *ctrlr)
+{
+	struct batch_cache_req *req;
+	const struct rpmh_request *rpm_msg;
+	unsigned long flags;
+	int ret = 0;
+	int i;
+
+	/* Send Sleep/Wake requests to the controller, expect no response */
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry(req, &ctrlr->batch_cache, list) {
+		for (i = 0; i < req->count; i++) {
+			rpm_msg = req->rpm_msgs + i;
+			ret = rpmh_rsc_write_ctrl_data(ctrlr_to_drv(ctrlr),
+						       &rpm_msg->msg);
+			if (ret)
+				break;
+		}
+	}
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+
+	return ret;
+}
+
+static void invalidate_batch(struct rpmh_ctrlr *ctrlr)
+{
+	struct batch_cache_req *req, *tmp;
+	unsigned long flags;
+
+	spin_lock_irqsave(&ctrlr->cache_lock, flags);
+	list_for_each_entry_safe(req, tmp, &ctrlr->batch_cache, list)
+		kfree(req);
+	INIT_LIST_HEAD(&ctrlr->batch_cache);
+	spin_unlock_irqrestore(&ctrlr->cache_lock, flags);
+}
+
+/**
+ * rpmh_write_batch: Write multiple sets of RPMH commands and wait for the
+ * batch to finish.
+ *
+ * @dev: the device making the request
+ * @state: Active/sleep set
+ * @cmd: The payload data
+ * @n: The array of count of elements in each batch, 0 terminated.
+ *
+ * Write a request to the RSC controller without caching. If the request
+ * state is ACTIVE, then the requests are treated as completion request
+ * and sent to the controller immediately. The function waits until all the
+ * commands are complete. If the request was to SLEEP or WAKE_ONLY, then the
+ * request is sent as fire-n-forget and no ack is expected.
+ *
+ * May sleep. Do not call from atomic contexts for ACTIVE_ONLY requests.
+ */
+int rpmh_write_batch(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 *n)
+{
+	struct batch_cache_req *req;
+	struct rpmh_request *rpm_msgs;
+	DECLARE_COMPLETION_ONSTACK(compl);
+	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
+	unsigned long time_left;
+	int count = 0;
+	int ret, i, j;
+
+	if (!cmd || !n)
+		return -EINVAL;
+
+	while (n[count] > 0)
+		count++;
+	if (!count)
+		return -EINVAL;
+
+	req = kzalloc(sizeof(*req) + count * sizeof(req->rpm_msgs[0]),
+		      GFP_ATOMIC);
+	if (!req)
+		return -ENOMEM;
+	req->count = count;
+	rpm_msgs = req->rpm_msgs;
+
+	for (i = 0; i < count; i++) {
+		__fill_rpmh_msg(rpm_msgs + i, state, cmd, n[i]);
+		cmd += n[i];
+	}
+
+	if (state != RPMH_ACTIVE_ONLY_STATE) {
+		cache_batch(ctrlr, req);
+		return 0;
+	}
+
+	for (i = 0; i < count; i++) {
+		rpm_msgs[i].completion = &compl;
+		ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msgs[i].msg);
+		if (ret) {
+			pr_err("Error(%d) sending RPMH message addr=%#x\n",
+			       ret, rpm_msgs[i].msg.cmds[0].addr);
+			for (j = i; j < count; j++)
+				rpmh_tx_done(&rpm_msgs[j].msg, ret);
+			break;
+		}
+	}
+
+	time_left = RPMH_TIMEOUT_MS;
+	for (i = 0; i < count; i++) {
+		time_left = wait_for_completion_timeout(&compl, time_left);
+		if (!time_left) {
+			/*
+			 * Better hope they never finish because they'll signal
+			 * the completion on our stack and that's bad once
+			 * we've returned from the function.
+			 */
+			WARN_ON(1);
+			ret = -ETIMEDOUT;
+			goto exit;
+		}
+	}
+
+exit:
+	kfree(req);
+
+	return ret;
+}
+EXPORT_SYMBOL(rpmh_write_batch);
+
 static int is_req_valid(struct cache_req *req)
 {
 	return (req->sleep_val != UINT_MAX &&
@@ -309,6 +458,11 @@ int rpmh_flush(const struct device *dev)
 		return 0;
 	}
 
+	/* First flush the cached batch requests */
+	ret = flush_batch(ctrlr);
+	if (ret)
+		return ret;
+
 	/*
 	 * Nobody else should be calling this function other than system PM,
 	 * hence we can run without locks.
@@ -347,6 +501,7 @@ int rpmh_invalidate(const struct device *dev)
 	struct rpmh_ctrlr *ctrlr = get_rpmh_ctrlr(dev);
 	int ret;
 
+	invalidate_batch(ctrlr);
 	ctrlr->dirty = true;
 
 	do {
diff --git a/include/soc/qcom/rpmh.h b/include/soc/qcom/rpmh.h
index 1161a5c77e75..619e07c75da9 100644
--- a/include/soc/qcom/rpmh.h
+++ b/include/soc/qcom/rpmh.h
@@ -17,6 +17,9 @@ int rpmh_write(const struct device *dev, enum rpmh_state state,
 int rpmh_write_async(const struct device *dev, enum rpmh_state state,
 		     const struct tcs_cmd *cmd, u32 n);
 
+int rpmh_write_batch(const struct device *dev, enum rpmh_state state,
+		     const struct tcs_cmd *cmd, u32 *n);
+
 int rpmh_flush(const struct device *dev);
 
 int rpmh_invalidate(const struct device *dev);
@@ -32,6 +35,11 @@ static inline int rpmh_write_async(const struct device *dev,
 				   const struct tcs_cmd *cmd, u32 n)
 { return -ENODEV; }
 
+static inline int rpmh_write_batch(const struct device *dev,
+				   enum rpmh_state state,
+				   const struct tcs_cmd *cmd, u32 *n)
+{ return -ENODEV; }
+
 static inline int rpmh_flush(const struct device *dev)
 { return -ENODEV; }
 
-- 
cgit v1.2.3


From 2de4b8d33eab86a6d9653041f8543f6f5f882a25 Mon Sep 17 00:00:00 2001
From: Lina Iyer <ilina@codeaurora.org>
Date: Wed, 20 Jun 2018 18:57:07 +0530
Subject: drivers: qcom: rpmh-rsc: allow active requests from wake TCS

Some RSCs may only have sleep and wake TCS, i.e, there is no dedicated
TCS for active mode request, but drivers may still want to make active
requests from these RSCs. In such cases re-purpose the wake TCS to send
active state requests.

The requirement for this is that the driver is aware that the wake TCS
is being repurposed to send active request, hence the sleep and wake
TCSes be invalidated before the active request is sent.

Signed-off-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-rsc.c | 23 +++++++++++++++++++++--
 1 file changed, 21 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 4c0c1f24911a..098feb928576 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -148,7 +148,8 @@ int rpmh_rsc_invalidate(struct rsc_drv *drv)
 static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 					 const struct tcs_request *msg)
 {
-	int type;
+	int type, ret;
+	struct tcs_group *tcs;
 
 	switch (msg->state) {
 	case RPMH_ACTIVE_ONLY_STATE:
@@ -164,7 +165,25 @@ static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 		return ERR_PTR(-EINVAL);
 	}
 
-	return get_tcs_of_type(drv, type);
+	/*
+	 * If we are making an active request on a RSC that does not have a
+	 * dedicated TCS for active state use, then re-purpose a wake TCS to
+	 * send active votes.
+	 * NOTE: The driver must be aware that this RSC does not have a
+	 * dedicated AMC, and therefore would invalidate the sleep and wake
+	 * TCSes before making an active state request.
+	 */
+	tcs = get_tcs_of_type(drv, type);
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && IS_ERR(tcs)) {
+		tcs = get_tcs_of_type(drv, WAKE_TCS);
+		if (!IS_ERR(tcs)) {
+			ret = rpmh_rsc_invalidate(drv);
+			if (ret)
+				return ERR_PTR(ret);
+		}
+	}
+
+	return tcs;
 }
 
 static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
-- 
cgit v1.2.3


From fdd102b52cfd9aa34b078b2b6f1a9aeafef04537 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Mon, 18 Jun 2018 11:36:52 -0700
Subject: drivers: qcom: rpmh-rsc: Check cmd_db_ready() to help children

Children of RPMh will need access to cmd_db.  Rather than having each
child have code to check if cmd_db is ready let's add the check to
RPMh.

With this we'll be able to remove this boilerplate code from
clk-rpmh.c and qcom-rpmh-regulator.c.  Neither of these files has
landed upstream yet but patches are pretty far along.

===
This code is based upon v11 of Lina and Raju's RPMh series.

Suggested-by: Stephen Boyd <sboyd@kernel.org>
Signed-off-by: Douglas Anderson <dianders@chromium.org>
Acked-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-rsc.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 098feb928576..8e297759c162 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 
+#include <soc/qcom/cmd-db.h>
 #include <soc/qcom/tcs.h>
 #include <dt-bindings/soc/qcom,rpmh-rsc.h>
 
@@ -621,6 +622,18 @@ static int rpmh_rsc_probe(struct platform_device *pdev)
 	struct rsc_drv *drv;
 	int ret, irq;
 
+	/*
+	 * Even though RPMh doesn't directly use cmd-db, all of its children
+	 * do. To avoid adding this check to our children we'll do it now.
+	 */
+	ret = cmd_db_ready();
+	if (ret) {
+		if (ret != -EPROBE_DEFER)
+			dev_err(&pdev->dev, "Command DB not available (%d)\n",
+									ret);
+		return ret;
+	}
+
 	drv = devm_kzalloc(&pdev->dev, sizeof(*drv), GFP_KERNEL);
 	if (!drv)
 		return -ENOMEM;
-- 
cgit v1.2.3


From a0b1561f846191a1967e8f5a26d8ef59c1b9162a Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Tue, 12 Jun 2018 15:23:13 +0200
Subject: firmware: qcom: scm: add a dummy qcom_scm_assign_mem()

Add a dummy qcom_scm_assign_mem() to enable building drivers when
CONFIG_COMPILE_TEST=y && CONFIG_QCOM_SCM=n.

All other qcom_scm_* functions already have a dummy version.

Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 include/linux/qcom_scm.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/include/linux/qcom_scm.h b/include/linux/qcom_scm.h
index b401b962afff..5d65521260b3 100644
--- a/include/linux/qcom_scm.h
+++ b/include/linux/qcom_scm.h
@@ -87,6 +87,10 @@ static inline int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr,
 static inline int
 qcom_scm_pas_auth_and_reset(u32 peripheral) { return -ENODEV; }
 static inline int qcom_scm_pas_shutdown(u32 peripheral) { return -ENODEV; }
+static inline int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
+				      unsigned int *src,
+				      struct qcom_scm_vmperm *newvm,
+				      int dest_cnt) { return -ENODEV; }
 static inline void qcom_scm_cpu_power_down(u32 flags) {}
 static inline u32 qcom_scm_get_version(void) { return 0; }
 static inline u32
-- 
cgit v1.2.3


From efa1c257b3fc7ef2a1db604b260784cc8bcdfd23 Mon Sep 17 00:00:00 2001
From: "Raju P.L.S.S.S.N" <rplsssn@codeaurora.org>
Date: Thu, 19 Jul 2018 12:43:02 +0530
Subject: drivers: qcom: rpmh-rsc: fix the loop index check in get_req_from_tcs

get_req_from_tcs introduced in patch[1] returns tcs_request from
tcs_group. The size of tcs (of type - tcs_group) array in rsc_drv is
TCS_TYPE_NR. So the loop index needs to be iterated up to TCS_TYPE_NR only.

[1] https://patchwork.kernel.org/patch/10477547/

Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-rsc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 8e297759c162..8d9da6e7df0e 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -193,7 +193,7 @@ static const struct tcs_request *get_req_from_tcs(struct rsc_drv *drv,
 	struct tcs_group *tcs;
 	int i;
 
-	for (i = 0; i < drv->num_tcs; i++) {
+	for (i = 0; i < TCS_TYPE_NR; i++) {
 		tcs = &drv->tcs[i];
 		if (tcs->mask & BIT(tcs_id))
 			return tcs->req[tcs_id - tcs->offset];
-- 
cgit v1.2.3


From 6c805adf17d491ea66d3cf80db3ada75b7180268 Mon Sep 17 00:00:00 2001
From: "Raju P.L.S.S.S.N" <rplsssn@codeaurora.org>
Date: Fri, 13 Jul 2018 19:15:46 +0530
Subject: drivers: qcom: rpmh: fix unwanted error check for get_tcs_of_type()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The patch fixes the bug reported by Dan Carpenter.
It removes the unnecessary err check for ‘tcs’ reported by
static checker warning:

drivers/soc/qcom/rpmh-rsc.c:111 tcs_invalidate()
warn: 'tcs' isn't an ERR_PTR
See also:
drivers/soc/qcom/rpmh-rsc.c:178 get_tcs_for_msg() warn: 'tcs' isn't
an ERR_PTR
drivers/soc/qcom/rpmh-rsc.c:180 get_tcs_for_msg() warn: 'tcs' isn't
an ERR_PTR

https://www.spinics.net/lists/linux-soc/msg04624.html

Fixes: 9a3afcf ("drivers: qcom: rpmh-rsc: allow invalidation
of sleep/wake TCS")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Raju P.L.S.S.S.N <rplsssn@codeaurora.org>
Reviewed-by: Lina Iyer <ilina@codeaurora.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rpmh-rsc.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
index 8d9da6e7df0e..ee75da66d64b 100644
--- a/drivers/soc/qcom/rpmh-rsc.c
+++ b/drivers/soc/qcom/rpmh-rsc.c
@@ -108,8 +108,6 @@ static int tcs_invalidate(struct rsc_drv *drv, int type)
 	struct tcs_group *tcs;
 
 	tcs = get_tcs_of_type(drv, type);
-	if (IS_ERR(tcs))
-		return PTR_ERR(tcs);
 
 	spin_lock(&tcs->lock);
 	if (bitmap_empty(tcs->slots, MAX_TCS_SLOTS)) {
@@ -175,9 +173,9 @@ static struct tcs_group *get_tcs_for_msg(struct rsc_drv *drv,
 	 * TCSes before making an active state request.
 	 */
 	tcs = get_tcs_of_type(drv, type);
-	if (msg->state == RPMH_ACTIVE_ONLY_STATE && IS_ERR(tcs)) {
+	if (msg->state == RPMH_ACTIVE_ONLY_STATE && !tcs->num_tcs) {
 		tcs = get_tcs_of_type(drv, WAKE_TCS);
-		if (!IS_ERR(tcs)) {
+		if (tcs->num_tcs) {
 			ret = rpmh_rsc_invalidate(drv);
 			if (ret)
 				return ERR_PTR(ret);
-- 
cgit v1.2.3


From 4da3b0452bc66af8feca71b176668faf3d0e750d Mon Sep 17 00:00:00 2001
From: Niklas Cassel <niklas.cassel@linaro.org>
Date: Fri, 29 Jun 2018 17:44:47 +0200
Subject: soc: qcom: llc-slice: Add missing MODULE_LICENSE()

Add missing MODULE_LICENSE().
According to the SPDX-License-Identifier, the license is GPL v2.

Fixes the following warning:
WARNING: modpost: missing MODULE_LICENSE() in drivers/soc/qcom/llcc-slice.o

Fixes: a3134fb ("drivers: soc: Add LLCC driver")
Signed-off-by: Niklas Cassel <niklas.cassel@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/llcc-slice.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/soc/qcom/llcc-slice.c b/drivers/soc/qcom/llcc-slice.c
index fcaad1a4b41d..54063a31132f 100644
--- a/drivers/soc/qcom/llcc-slice.c
+++ b/drivers/soc/qcom/llcc-slice.c
@@ -9,6 +9,7 @@
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/of_device.h>
 #include <linux/regmap.h>
@@ -333,3 +334,5 @@ int qcom_llcc_probe(struct platform_device *pdev,
 	return qcom_llcc_cfg_program(pdev);
 }
 EXPORT_SYMBOL_GPL(qcom_llcc_probe);
+
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 78ee559d7fc65e37670a46cfbeaaa62cb014af67 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Tue, 12 Jun 2018 14:41:41 +0200
Subject: soc: qcom: rmtfs-mem: fix memleak in probe error paths

Make sure to set the mem device release callback before calling
put_device() in a couple of probe error paths so that the containing
object also gets freed.

Fixes: d1de6d6c639b ("soc: qcom: Remote filesystem memory driver")
Cc: stable <stable@vger.kernel.org>     # 4.15
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Johan Hovold <johan@kernel.org>
Signed-off-by: Andy Gross <andy.gross@linaro.org>
---
 drivers/soc/qcom/rmtfs_mem.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/soc/qcom/rmtfs_mem.c b/drivers/soc/qcom/rmtfs_mem.c
index c8999e38b005..8a3678c2e83c 100644
--- a/drivers/soc/qcom/rmtfs_mem.c
+++ b/drivers/soc/qcom/rmtfs_mem.c
@@ -184,6 +184,7 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev)
 	device_initialize(&rmtfs_mem->dev);
 	rmtfs_mem->dev.parent = &pdev->dev;
 	rmtfs_mem->dev.groups = qcom_rmtfs_mem_groups;
+	rmtfs_mem->dev.release = qcom_rmtfs_mem_release_device;
 
 	rmtfs_mem->base = devm_memremap(&rmtfs_mem->dev, rmtfs_mem->addr,
 					rmtfs_mem->size, MEMREMAP_WC);
@@ -206,8 +207,6 @@ static int qcom_rmtfs_mem_probe(struct platform_device *pdev)
 		goto put_device;
 	}
 
-	rmtfs_mem->dev.release = qcom_rmtfs_mem_release_device;
-
 	ret = of_property_read_u32(node, "qcom,vmid", &vmid);
 	if (ret < 0 && ret != -EINVAL) {
 		dev_err(&pdev->dev, "failed to parse qcom,vmid\n");
-- 
cgit v1.2.3


From baa2d2b17ee93e2a5b8accc2dd5328db17caf90e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 23:14:17 -0500
Subject: net: sched: use PTR_ERR_OR_ZERO macro in tcf_block_cb_register

This line makes up what macro PTR_ERR_OR_ZERO already does. So,
make use of PTR_ERR_OR_ZERO rather than an open-code version.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 623fe2cfe529..620067209ba8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -818,7 +818,7 @@ int tcf_block_cb_register(struct tcf_block *block,
 
 	block_cb = __tcf_block_cb_register(block, cb, cb_ident, cb_priv,
 					   extack);
-	return IS_ERR(block_cb) ? PTR_ERR(block_cb) : 0;
+	return PTR_ERR_OR_ZERO(block_cb);
 }
 EXPORT_SYMBOL(tcf_block_cb_register);
 
-- 
cgit v1.2.3


From e064cce130497023806e2ae6a4114f1fed28eacd Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 19 Jul 2018 17:16:59 +0800
Subject: tipc: make some functions static

Fixes the following sparse warnings:

net/tipc/link.c:376:5: warning: symbol 'link_bc_rcv_gap' was not declared. Should it be static?
net/tipc/link.c:823:6: warning: symbol 'link_prepare_wakeup' was not declared. Should it be static?
net/tipc/link.c:959:6: warning: symbol 'tipc_link_advance_backlog' was not declared. Should it be static?
net/tipc/link.c:1009:5: warning: symbol 'tipc_link_retrans' was not declared. Should it be static?
net/tipc/monitor.c:687:5: warning: symbol '__tipc_nl_add_monitor_peer' was not declared. Should it be static?
net/tipc/group.c:230:20: warning: symbol 'tipc_group_find_member' was not declared. Should it be static?

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/group.c   |  4 ++--
 net/tipc/link.c    | 11 ++++++-----
 net/tipc/monitor.c |  3 ++-
 3 files changed, 10 insertions(+), 8 deletions(-)

diff --git a/net/tipc/group.c b/net/tipc/group.c
index 8f43e7d6046b..e82f13cb2dc5 100644
--- a/net/tipc/group.c
+++ b/net/tipc/group.c
@@ -227,8 +227,8 @@ void tipc_group_delete(struct net *net, struct tipc_group *grp)
 	kfree(grp);
 }
 
-struct tipc_member *tipc_group_find_member(struct tipc_group *grp,
-					   u32 node, u32 port)
+static struct tipc_member *tipc_group_find_member(struct tipc_group *grp,
+						  u32 node, u32 port)
 {
 	struct rb_node *n = grp->members.rb_node;
 	u64 nkey, key = (u64)node << 32 | port;
diff --git a/net/tipc/link.c b/net/tipc/link.c
index 6987ffc8e7a1..b1f0bee54eac 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -373,7 +373,7 @@ int tipc_link_bc_peers(struct tipc_link *l)
 	return l->ackers;
 }
 
-u16 link_bc_rcv_gap(struct tipc_link *l)
+static u16 link_bc_rcv_gap(struct tipc_link *l)
 {
 	struct sk_buff *skb = skb_peek(&l->deferdq);
 	u16 gap = 0;
@@ -820,7 +820,7 @@ static int link_schedule_user(struct tipc_link *l, struct tipc_msg *hdr)
  * Wake up a number of waiting users, as permitted by available space
  * in the send queue
  */
-void link_prepare_wakeup(struct tipc_link *l)
+static void link_prepare_wakeup(struct tipc_link *l)
 {
 	struct sk_buff *skb, *tmp;
 	int imp, i = 0;
@@ -956,7 +956,8 @@ int tipc_link_xmit(struct tipc_link *l, struct sk_buff_head *list,
 	return rc;
 }
 
-void tipc_link_advance_backlog(struct tipc_link *l, struct sk_buff_head *xmitq)
+static void tipc_link_advance_backlog(struct tipc_link *l,
+				      struct sk_buff_head *xmitq)
 {
 	struct sk_buff *skb, *_skb;
 	struct tipc_msg *hdr;
@@ -1006,8 +1007,8 @@ static void link_retransmit_failure(struct tipc_link *l, struct sk_buff *skb)
  * @to: retransmit to (inclusive) this sequence number
  * xmitq: queue for accumulating the retransmitted packets
  */
-int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
-		      u16 from, u16 to, struct sk_buff_head *xmitq)
+static int tipc_link_retrans(struct tipc_link *l, struct tipc_link *r,
+			     u16 from, u16 to, struct sk_buff_head *xmitq)
 {
 	struct sk_buff *_skb, *skb = skb_peek(&l->transmq);
 	u16 bc_ack = l->bc_rcvlink->rcv_nxt - 1;
diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c
index 5453e564da82..67f69389ec17 100644
--- a/net/tipc/monitor.c
+++ b/net/tipc/monitor.c
@@ -684,7 +684,8 @@ int tipc_nl_monitor_get_threshold(struct net *net)
 	return tn->mon_threshold;
 }
 
-int __tipc_nl_add_monitor_peer(struct tipc_peer *peer, struct tipc_nl_msg *msg)
+static int __tipc_nl_add_monitor_peer(struct tipc_peer *peer,
+				      struct tipc_nl_msg *msg)
 {
 	struct tipc_mon_domain *dom = peer->domain;
 	struct nlattr *attrs;
-- 
cgit v1.2.3


From c1907e53ab91495346c2a6fbff92478a6804c9bd Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 19 Jul 2018 21:57:11 +0800
Subject: net: hix5hd2_gmac: use dma_zalloc_coherent instead of
 allocator/memset

Use dma_zalloc_coherent instead of dma_alloc_coherent
followed by memset 0.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hix5hd2_gmac.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
index 25a6c8722eca..c5727003af8c 100644
--- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c
@@ -1006,12 +1006,11 @@ static int hix5hd2_init_hw_desc_queue(struct hix5hd2_priv *priv)
 
 	for (i = 0; i < QUEUE_NUMS; i++) {
 		size = priv->pool[i].count * sizeof(struct hix5hd2_desc);
-		virt_addr = dma_alloc_coherent(dev, size, &phys_addr,
-					       GFP_KERNEL);
+		virt_addr = dma_zalloc_coherent(dev, size, &phys_addr,
+						GFP_KERNEL);
 		if (virt_addr == NULL)
 			goto error_free_pool;
 
-		memset(virt_addr, 0, size);
 		priv->pool[i].size = size;
 		priv->pool[i].desc = virt_addr;
 		priv->pool[i].phys_addr = phys_addr;
-- 
cgit v1.2.3


From 4c303373497015773234e455fafa5c7c6386d19d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 19 Jul 2018 22:18:27 +0800
Subject: libcxgb: replace vmalloc and memset with vzalloc

Use vzalloc instead of the vmalloc, memset combo

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
index 0ed161642371..74849be5f004 100644
--- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
+++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_ppm.c
@@ -412,12 +412,10 @@ int cxgbi_ppm_init(void **ppm_pp, struct net_device *ndev,
 			ppmax * (sizeof(struct cxgbi_ppod_data)) +
 			ppod_bmap_size * sizeof(unsigned long);
 
-	ppm = vmalloc(alloc_sz);
+	ppm = vzalloc(alloc_sz);
 	if (!ppm)
 		goto release_ppm_pool;
 
-	memset(ppm, 0, alloc_sz);
-
 	ppm->ppod_bmap = (unsigned long *)(&ppm->ppod_data[ppmax]);
 
 	if ((ppod_bmap_size >> 3) > (ppmax - ppmax_pool)) {
-- 
cgit v1.2.3


From b5293443de89460047aad7d94b8e6ff783c29e0c Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 19 Jul 2018 09:41:39 -0700
Subject: net: phy: sfp: Do not use "imply HWMON"

"imply HWMON" was supposed to ensure that the SFP phy code can be built
with HWMON enabled or disabled while at the same time ensuring that
HWMON is not built as module if SFP is built into the kernel.
Unfortunately, that does not work as intended. With "allmodconfig", it
results in several unrelated HWMON drivers to be disabled instead of
being built as module as expected.

Let's use the old "depends on HWMON || HWMON=n" instead. This is slightly
different (it enforces SFP to be built as module if HWMON is built as
module), but it is better than the alternative of using "IS_REACHABLE()"
in the driver since that would disable sensor support if HWMON is built
as module and SFP is built into the kernel.

Fixes: 1323061a018a ("net: phy: sfp: Add HWMON support for module sensors")
Cc: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index b7ff0af419b4..82070792edbb 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -214,8 +214,8 @@ comment "MII PHY device drivers"
 config SFP
 	tristate "SFP cage support"
 	depends on I2C && PHYLINK
+	depends on HWMON || HWMON=n
 	select MDIO_I2C
-	imply HWMON
 
 config AMD_PHY
 	tristate "AMD PHYs"
-- 
cgit v1.2.3


From ef32477971b50c1fa11f52f5ed44cfbc98075030 Mon Sep 17 00:00:00 2001
From: Mark Railton <mark@markrailton.com>
Date: Fri, 20 Jul 2018 00:11:46 +0100
Subject: net: wimax: stack: fixed multi line comment issue

Moved end of comment to it's own line per guide

Signed-off-by: Mark Railton <mark@markrailton.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/wimax/stack.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index 5db731512014..73dba9c077bb 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -486,7 +486,8 @@ int wimax_dev_add(struct wimax_dev *wimax_dev, struct net_device *net_dev)
 	d_fnstart(3, dev, "(wimax_dev %p net_dev %p)\n", wimax_dev, net_dev);
 
 	/* Do the RFKILL setup before locking, as RFKILL will call
-	 * into our functions. */
+	 * into our functions.
+	 */
 	wimax_dev->net_dev = net_dev;
 	result = wimax_rfkill_add(wimax_dev);
 	if (result < 0)
-- 
cgit v1.2.3


From 0ae0d60a379c11d6f3b11d9b9e8dbdd1fc683a1a Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Fri, 20 Jul 2018 14:07:42 +0800
Subject: multicast: remove useless parameter for group add

Remove the mode parameter for igmp/igmp6_group_added as we can get it
from first parameter.

Fixes: 6e2059b53f988 (ipv4/igmp: init group mode as INCLUDE when join source group)
Fixes: c7ea20c9da5b9 (ipv6/mcast: init as INCLUDE when join SSM INCLUDE group)
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/igmp.c  | 10 +++++-----
 net/ipv6/mcast.c |  8 ++++----
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index b3c899a630a0..598333b123b9 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -1289,7 +1289,7 @@ static void igmp_group_dropped(struct ip_mc_list *im)
 #endif
 }
 
-static void igmp_group_added(struct ip_mc_list *im, unsigned int mode)
+static void igmp_group_added(struct ip_mc_list *im)
 {
 	struct in_device *in_dev = im->interface;
 #ifdef CONFIG_IP_MULTICAST
@@ -1321,7 +1321,7 @@ static void igmp_group_added(struct ip_mc_list *im, unsigned int mode)
 	 * not send filter-mode change record as the mode should be from
 	 * IN() to IN(A).
 	 */
-	if (mode == MCAST_EXCLUDE)
+	if (im->sfmode == MCAST_EXCLUDE)
 		im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
 
 	igmp_ifc_event(in_dev);
@@ -1432,7 +1432,7 @@ void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode)
 #ifdef CONFIG_IP_MULTICAST
 	igmpv3_del_delrec(in_dev, im);
 #endif
-	igmp_group_added(im, mode);
+	igmp_group_added(im);
 	if (!in_dev->dead)
 		ip_rt_multicast_event(in_dev);
 out:
@@ -1699,7 +1699,7 @@ void ip_mc_remap(struct in_device *in_dev)
 #ifdef CONFIG_IP_MULTICAST
 		igmpv3_del_delrec(in_dev, pmc);
 #endif
-		igmp_group_added(pmc, pmc->sfmode);
+		igmp_group_added(pmc);
 	}
 }
 
@@ -1762,7 +1762,7 @@ void ip_mc_up(struct in_device *in_dev)
 #ifdef CONFIG_IP_MULTICAST
 		igmpv3_del_delrec(in_dev, pmc);
 #endif
-		igmp_group_added(pmc, pmc->sfmode);
+		igmp_group_added(pmc);
 	}
 }
 
diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c
index 2699be7202be..195ed2db2207 100644
--- a/net/ipv6/mcast.c
+++ b/net/ipv6/mcast.c
@@ -660,7 +660,7 @@ bool inet6_mc_check(struct sock *sk, const struct in6_addr *mc_addr,
 	return rv;
 }
 
-static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode)
+static void igmp6_group_added(struct ifmcaddr6 *mc)
 {
 	struct net_device *dev = mc->idev->dev;
 	char buf[MAX_ADDR_LEN];
@@ -690,7 +690,7 @@ static void igmp6_group_added(struct ifmcaddr6 *mc, unsigned int mode)
 	 * should not send filter-mode change record as the mode
 	 * should be from IN() to IN(A).
 	 */
-	if (mode == MCAST_EXCLUDE)
+	if (mc->mca_sfmode == MCAST_EXCLUDE)
 		mc->mca_crcount = mc->idev->mc_qrv;
 
 	mld_ifc_event(mc->idev);
@@ -932,7 +932,7 @@ static int __ipv6_dev_mc_inc(struct net_device *dev,
 	write_unlock_bh(&idev->lock);
 
 	mld_del_delrec(idev, mc);
-	igmp6_group_added(mc, mode);
+	igmp6_group_added(mc);
 	ma_put(mc);
 	return 0;
 }
@@ -2572,7 +2572,7 @@ void ipv6_mc_up(struct inet6_dev *idev)
 	ipv6_mc_reset(idev);
 	for (i = idev->mc_list; i; i = i->next) {
 		mld_del_delrec(idev, i);
-		igmp6_group_added(i, i->mca_sfmode);
+		igmp6_group_added(i);
 	}
 	read_unlock_bh(&idev->lock);
 }
-- 
cgit v1.2.3


From d10ee9c542365bdc0a7497306e21ff6c7f2172b0 Mon Sep 17 00:00:00 2001
From: Srikanth K H <srikanth.h@samsung.com>
Date: Fri, 20 Jul 2018 11:13:51 +0530
Subject: ALSA: timer: catch invalid timer object creation

A timer object for the classes SNDRV_TIMER_CLASS_CARD and
SNDRV_TIMER_CLASS_PCM has to be associated with a card object, but we
have no check at creation time.  Such a timer object with NULL card
causes various unexpected problems, e.g. NULL dereference at reading
the sound timer proc file.

So as preventive measure while the creating the sound timer object is
created the card information availability is checked for the mentioned
entries and returned error if its NULL.

Signed-off-by: Srikanth K H <srikanth.h@samsung.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/timer.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/core/timer.c b/sound/core/timer.c
index b6f076bbc72d..61a0cec6e1f6 100644
--- a/sound/core/timer.c
+++ b/sound/core/timer.c
@@ -883,6 +883,11 @@ int snd_timer_new(struct snd_card *card, char *id, struct snd_timer_id *tid,
 
 	if (snd_BUG_ON(!tid))
 		return -EINVAL;
+	if (tid->dev_class == SNDRV_TIMER_CLASS_CARD ||
+	    tid->dev_class == SNDRV_TIMER_CLASS_PCM) {
+		if (WARN_ON(!card))
+			return -EINVAL;
+	}
 	if (rtimer)
 		*rtimer = NULL;
 	timer = kzalloc(sizeof(*timer), GFP_KERNEL);
-- 
cgit v1.2.3


From 83a0a2ea0b991927e42984be220329e776ce7137 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 20 Jul 2018 10:47:18 +0900
Subject: efi/x86: Prevent reentrant firmware calls in mixed mode

The UEFI spec does not permit runtime services to be called
reentrantly, and so it is up to the OS to provide proper locking
around such calls.

For the native case, this was fixed a long time ago, but for the
mixed mode case, no locking is done whatsoever. Note that the calls
are made with preemption and interrupts disabled, so only SMP
configurations are affected by this issue.

So add a spinlock and grab it when invoking a UEFI runtime service
in mixed mode. We will also need to provide non-blocking versions
of SetVariable() and QueryVariableInfo(), so add those as well.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-2-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/platform/efi/efi_64.c | 101 +++++++++++++++++++++++++++++++++++++++--
 1 file changed, 98 insertions(+), 3 deletions(-)

diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index 77873ce700ae..448267f1c073 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -636,6 +636,8 @@ void efi_switch_mm(struct mm_struct *mm)
 #ifdef CONFIG_EFI_MIXED
 extern efi_status_t efi64_thunk(u32, ...);
 
+static DEFINE_SPINLOCK(efi_runtime_lock);
+
 #define runtime_service32(func)						 \
 ({									 \
 	u32 table = (u32)(unsigned long)efi.systab;			 \
@@ -657,17 +659,14 @@ extern efi_status_t efi64_thunk(u32, ...);
 #define efi_thunk(f, ...)						\
 ({									\
 	efi_status_t __s;						\
-	unsigned long __flags;						\
 	u32 __func;							\
 									\
-	local_irq_save(__flags);					\
 	arch_efi_call_virt_setup();					\
 									\
 	__func = runtime_service32(f);					\
 	__s = efi64_thunk(__func, __VA_ARGS__);				\
 									\
 	arch_efi_call_virt_teardown();					\
-	local_irq_restore(__flags);					\
 									\
 	__s;								\
 })
@@ -702,14 +701,17 @@ static efi_status_t efi_thunk_get_time(efi_time_t *tm, efi_time_cap_t *tc)
 {
 	efi_status_t status;
 	u32 phys_tm, phys_tc;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 	phys_tc = virt_to_phys_or_null(tc);
 
 	status = efi_thunk(get_time, phys_tm, phys_tc);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -719,13 +721,16 @@ static efi_status_t efi_thunk_set_time(efi_time_t *tm)
 {
 	efi_status_t status;
 	u32 phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_time, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -737,8 +742,10 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 {
 	efi_status_t status;
 	u32 phys_enabled, phys_pending, phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_enabled = virt_to_phys_or_null(enabled);
 	phys_pending = virt_to_phys_or_null(pending);
@@ -747,6 +754,7 @@ efi_thunk_get_wakeup_time(efi_bool_t *enabled, efi_bool_t *pending,
 	status = efi_thunk(get_wakeup_time, phys_enabled,
 			     phys_pending, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -757,13 +765,16 @@ efi_thunk_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
 {
 	efi_status_t status;
 	u32 phys_tm;
+	unsigned long flags;
 
 	spin_lock(&rtc_lock);
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_tm = virt_to_phys_or_null(tm);
 
 	status = efi_thunk(set_wakeup_time, enabled, phys_tm);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 	spin_unlock(&rtc_lock);
 
 	return status;
@@ -781,6 +792,9 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	efi_status_t status;
 	u32 phys_name, phys_vendor, phys_attr;
 	u32 phys_data_size, phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_data_size = virt_to_phys_or_null(data_size);
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -791,6 +805,8 @@ efi_thunk_get_variable(efi_char16_t *name, efi_guid_t *vendor,
 	status = efi_thunk(get_variable, phys_name, phys_vendor,
 			   phys_attr, phys_data_size, phys_data);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -800,6 +816,34 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 {
 	u32 phys_name, phys_vendor, phys_data;
 	efi_status_t status;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
+	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
+	phys_vendor = virt_to_phys_or_null(vendor);
+	phys_data = virt_to_phys_or_null_size(data, data_size);
+
+	/* If data_size is > sizeof(u32) we've got problems */
+	status = efi_thunk(set_variable, phys_name, phys_vendor,
+			   attr, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
+				   u32 attr, unsigned long data_size,
+				   void *data)
+{
+	u32 phys_name, phys_vendor, phys_data;
+	efi_status_t status;
+	unsigned long flags;
+
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
 
 	phys_name = virt_to_phys_or_null_size(name, efi_name_size(name));
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -809,6 +853,8 @@ efi_thunk_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 	status = efi_thunk(set_variable, phys_name, phys_vendor,
 			   attr, data_size, phys_data);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -819,6 +865,9 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 {
 	efi_status_t status;
 	u32 phys_name_size, phys_name, phys_vendor;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_name_size = virt_to_phys_or_null(name_size);
 	phys_vendor = virt_to_phys_or_null(vendor);
@@ -827,6 +876,8 @@ efi_thunk_get_next_variable(unsigned long *name_size,
 	status = efi_thunk(get_next_variable, phys_name_size,
 			   phys_name, phys_vendor);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -835,10 +886,15 @@ efi_thunk_get_next_high_mono_count(u32 *count)
 {
 	efi_status_t status;
 	u32 phys_count;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_count = virt_to_phys_or_null(count);
 	status = efi_thunk(get_next_high_mono_count, phys_count);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -847,10 +903,15 @@ efi_thunk_reset_system(int reset_type, efi_status_t status,
 		       unsigned long data_size, efi_char16_t *data)
 {
 	u32 phys_data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&efi_runtime_lock, flags);
 
 	phys_data = virt_to_phys_or_null_size(data, data_size);
 
 	efi_thunk(reset_system, reset_type, status, data_size, phys_data);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
 }
 
 static efi_status_t
@@ -872,10 +933,13 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 {
 	efi_status_t status;
 	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
 
 	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
 		return EFI_UNSUPPORTED;
 
+	spin_lock_irqsave(&efi_runtime_lock, flags);
+
 	phys_storage = virt_to_phys_or_null(storage_space);
 	phys_remaining = virt_to_phys_or_null(remaining_space);
 	phys_max = virt_to_phys_or_null(max_variable_size);
@@ -883,6 +947,35 @@ efi_thunk_query_variable_info(u32 attr, u64 *storage_space,
 	status = efi_thunk(query_variable_info, attr, phys_storage,
 			   phys_remaining, phys_max);
 
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
+	return status;
+}
+
+static efi_status_t
+efi_thunk_query_variable_info_nonblocking(u32 attr, u64 *storage_space,
+					  u64 *remaining_space,
+					  u64 *max_variable_size)
+{
+	efi_status_t status;
+	u32 phys_storage, phys_remaining, phys_max;
+	unsigned long flags;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (!spin_trylock_irqsave(&efi_runtime_lock, flags))
+		return EFI_NOT_READY;
+
+	phys_storage = virt_to_phys_or_null(storage_space);
+	phys_remaining = virt_to_phys_or_null(remaining_space);
+	phys_max = virt_to_phys_or_null(max_variable_size);
+
+	status = efi_thunk(query_variable_info, attr, phys_storage,
+			   phys_remaining, phys_max);
+
+	spin_unlock_irqrestore(&efi_runtime_lock, flags);
+
 	return status;
 }
 
@@ -908,9 +1001,11 @@ void efi_thunk_runtime_setup(void)
 	efi.get_variable = efi_thunk_get_variable;
 	efi.get_next_variable = efi_thunk_get_next_variable;
 	efi.set_variable = efi_thunk_set_variable;
+	efi.set_variable_nonblocking = efi_thunk_set_variable_nonblocking;
 	efi.get_next_high_mono_count = efi_thunk_get_next_high_mono_count;
 	efi.reset_system = efi_thunk_reset_system;
 	efi.query_variable_info = efi_thunk_query_variable_info;
+	efi.query_variable_info_nonblocking = efi_thunk_query_variable_info_nonblocking;
 	efi.update_capsule = efi_thunk_update_capsule;
 	efi.query_capsule_caps = efi_thunk_query_capsule_caps;
 }
-- 
cgit v1.2.3


From 75c5a713ab4b774c7d990ec748dddba714034436 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 20 Jul 2018 10:47:19 +0900
Subject: efi/x86: Merge the setup_efi_pci32() and setup_efi_pci64() routines

After merging the 32-bit and 64-bit versions of the code that invokes
the PCI I/O protocol methods to preserve PCI ROM images in commit:

  2c3625cb9fa2 ("efi/x86: Fold __setup_efi_pci32() and __setup_efi_pci64() ...")

there are still separate code paths for 32-bit and 64-bit, where the only
difference is the size of a EFI_HANDLE. So let's parameterize a single
implementation for that difference only, and get rid of the two copies of
the code.

While at it, rename __setup_efi_pci() to preserve_pci_rom_image() to
better reflect its purpose.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-3-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/eboot.c | 123 ++++++++++-----------------------------
 1 file changed, 32 insertions(+), 91 deletions(-)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 9f6813493945..c72550783c16 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -111,7 +111,7 @@ void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 }
 
 static efi_status_t
-__setup_efi_pci(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
+preserve_pci_rom_image(efi_pci_io_protocol_t *pci, struct pci_setup_rom **__rom)
 {
 	struct pci_setup_rom *rom = NULL;
 	efi_status_t status;
@@ -181,92 +181,6 @@ free_struct:
 	return status;
 }
 
-static void
-setup_efi_pci32(struct boot_params *params, void **pci_handle, unsigned long size)
-{
-	efi_pci_io_protocol_t *pci = NULL;
-	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-	u32 *handles = (u32 *)(unsigned long)pci_handle;
-	efi_status_t status;
-	unsigned long nr_pci;
-	struct setup_data *data;
-	int i;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	nr_pci = size / sizeof(u32);
-	for (i = 0; i < nr_pci; i++) {
-		struct pci_setup_rom *rom = NULL;
-		u32 h = handles[i];
-
-		status = efi_call_early(handle_protocol, h,
-					&pci_proto, (void **)&pci);
-
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (!pci)
-			continue;
-
-		status = __setup_efi_pci(pci, &rom);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (data)
-			data->next = (unsigned long)rom;
-		else
-			params->hdr.setup_data = (unsigned long)rom;
-
-		data = (struct setup_data *)rom;
-	}
-}
-
-static void
-setup_efi_pci64(struct boot_params *params, void **pci_handle, unsigned long size)
-{
-	efi_pci_io_protocol_t *pci = NULL;
-	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
-	u64 *handles = (u64 *)(unsigned long)pci_handle;
-	efi_status_t status;
-	unsigned long nr_pci;
-	struct setup_data *data;
-	int i;
-
-	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
-
-	while (data && data->next)
-		data = (struct setup_data *)(unsigned long)data->next;
-
-	nr_pci = size / sizeof(u64);
-	for (i = 0; i < nr_pci; i++) {
-		struct pci_setup_rom *rom = NULL;
-		u64 h = handles[i];
-
-		status = efi_call_early(handle_protocol, h,
-					&pci_proto, (void **)&pci);
-
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (!pci)
-			continue;
-
-		status = __setup_efi_pci(pci, &rom);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		if (data)
-			data->next = (unsigned long)rom;
-		else
-			params->hdr.setup_data = (unsigned long)rom;
-
-		data = (struct setup_data *)rom;
-	}
-}
-
 /*
  * There's no way to return an informative status from this function,
  * because any analysis (and printing of error messages) needs to be
@@ -282,6 +196,9 @@ static void setup_efi_pci(struct boot_params *params)
 	void **pci_handle = NULL;
 	efi_guid_t pci_proto = EFI_PCI_IO_PROTOCOL_GUID;
 	unsigned long size = 0;
+	unsigned long nr_pci;
+	struct setup_data *data;
+	int i;
 
 	status = efi_call_early(locate_handle,
 				EFI_LOCATE_BY_PROTOCOL,
@@ -305,10 +222,34 @@ static void setup_efi_pci(struct boot_params *params)
 	if (status != EFI_SUCCESS)
 		goto free_handle;
 
-	if (efi_early->is64)
-		setup_efi_pci64(params, pci_handle, size);
-	else
-		setup_efi_pci32(params, pci_handle, size);
+	data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+	while (data && data->next)
+		data = (struct setup_data *)(unsigned long)data->next;
+
+	nr_pci = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
+	for (i = 0; i < nr_pci; i++) {
+		efi_pci_io_protocol_t *pci = NULL;
+		struct pci_setup_rom *rom;
+
+		status = efi_call_early(handle_protocol,
+					efi_is_64bit() ? ((u64 *)pci_handle)[i]
+						       : ((u32 *)pci_handle)[i],
+					&pci_proto, (void **)&pci);
+		if (status != EFI_SUCCESS || !pci)
+			continue;
+
+		status = preserve_pci_rom_image(pci, &rom);
+		if (status != EFI_SUCCESS)
+			continue;
+
+		if (data)
+			data->next = (unsigned long)rom;
+		else
+			params->hdr.setup_data = (unsigned long)rom;
+
+		data = (struct setup_data *)rom;
+	}
 
 free_handle:
 	efi_call_early(free_pool, pci_handle);
-- 
cgit v1.2.3


From 0b767b16d7b634dd62667f224425cef3c78e031c Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 20 Jul 2018 10:47:20 +0900
Subject: efi/x86: Align efi_uga_draw_protocol typedef names to convention

The linux-efi subsystem uses typedefs with the _t suffix to declare
data structures that originate in the UEFI spec. Our type mangling
for mixed mode depends on this convention, so rename the UGA drawing
protocols to allow efi_call_proto() to be used with them in a
subsequent patch.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-4-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/eboot.c |  4 ++--
 arch/x86/boot/compressed/eboot.h | 12 ++++++------
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index c72550783c16..011d5c289449 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -321,7 +321,7 @@ static void setup_quirks(struct boot_params *boot_params)
 static efi_status_t
 setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 {
-	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+	efi_uga_draw_protocol_t *uga = NULL, *first_uga;
 	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
 	unsigned long nr_ugas;
 	u32 *handles = (u32 *)uga_handle;
@@ -366,7 +366,7 @@ setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 static efi_status_t
 setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 {
-	struct efi_uga_draw_protocol *uga = NULL, *first_uga;
+	efi_uga_draw_protocol_t *uga = NULL, *first_uga;
 	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
 	unsigned long nr_ugas;
 	u64 *handles = (u64 *)uga_handle;
diff --git a/arch/x86/boot/compressed/eboot.h b/arch/x86/boot/compressed/eboot.h
index e799dc5c6448..8297387c4676 100644
--- a/arch/x86/boot/compressed/eboot.h
+++ b/arch/x86/boot/compressed/eboot.h
@@ -12,22 +12,22 @@
 
 #define DESC_TYPE_CODE_DATA	(1 << 0)
 
-struct efi_uga_draw_protocol_32 {
+typedef struct {
 	u32 get_mode;
 	u32 set_mode;
 	u32 blt;
-};
+} efi_uga_draw_protocol_32_t;
 
-struct efi_uga_draw_protocol_64 {
+typedef struct {
 	u64 get_mode;
 	u64 set_mode;
 	u64 blt;
-};
+} efi_uga_draw_protocol_64_t;
 
-struct efi_uga_draw_protocol {
+typedef struct {
 	void *get_mode;
 	void *set_mode;
 	void *blt;
-};
+} efi_uga_draw_protocol_t;
 
 #endif /* BOOT_COMPRESSED_EBOOT_H */
-- 
cgit v1.2.3


From 290084c2fa13e9aaa7f856ed1ab30760327dd9f8 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 20 Jul 2018 10:47:21 +0900
Subject: efi/x86: Merge 32-bit and 64-bit UGA draw protocol setup routines

The two versions of setup_uga##() are mostly identical, with the
exception of the size of EFI_HANDLE. So let's merge the two, and
pull the implementation into the calling function setup_uga().

Note that the 32-bit version was only mixed-mode safe by accident:
it only calls the get_mode() method of the UGA draw protocol, which
happens to be the first member, and so truncating the 64-bit void* at
offset 0 to 32 bits happens to produce the correct value. But let's
not rely on that, and use the proper API instead.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-5-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/eboot.c | 111 +++++++++------------------------------
 1 file changed, 26 insertions(+), 85 deletions(-)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 011d5c289449..ac8e442db71f 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -318,81 +318,54 @@ static void setup_quirks(struct boot_params *boot_params)
 	}
 }
 
+/*
+ * See if we have Universal Graphics Adapter (UGA) protocol
+ */
 static efi_status_t
-setup_uga32(void **uga_handle, unsigned long size, u32 *width, u32 *height)
+setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size)
 {
+	efi_status_t status;
+	u32 width, height;
+	void **uga_handle = NULL;
 	efi_uga_draw_protocol_t *uga = NULL, *first_uga;
-	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
 	unsigned long nr_ugas;
-	u32 *handles = (u32 *)uga_handle;
-	efi_status_t status = EFI_INVALID_PARAMETER;
 	int i;
 
-	first_uga = NULL;
-	nr_ugas = size / sizeof(u32);
-	for (i = 0; i < nr_ugas; i++) {
-		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
-		u32 w, h, depth, refresh;
-		void *pciio;
-		u32 handle = handles[i];
-
-		status = efi_call_early(handle_protocol, handle,
-					&uga_proto, (void **)&uga);
-		if (status != EFI_SUCCESS)
-			continue;
-
-		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
-
-		status = efi_early->call((unsigned long)uga->get_mode, uga,
-					 &w, &h, &depth, &refresh);
-		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-			*width = w;
-			*height = h;
-
-			/*
-			 * Once we've found a UGA supporting PCIIO,
-			 * don't bother looking any further.
-			 */
-			if (pciio)
-				break;
-
-			first_uga = uga;
-		}
-	}
+	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
+				size, (void **)&uga_handle);
+	if (status != EFI_SUCCESS)
+		return status;
 
-	return status;
-}
+	status = efi_call_early(locate_handle,
+				EFI_LOCATE_BY_PROTOCOL,
+				uga_proto, NULL, &size, uga_handle);
+	if (status != EFI_SUCCESS)
+		goto free_handle;
 
-static efi_status_t
-setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
-{
-	efi_uga_draw_protocol_t *uga = NULL, *first_uga;
-	efi_guid_t uga_proto = EFI_UGA_PROTOCOL_GUID;
-	unsigned long nr_ugas;
-	u64 *handles = (u64 *)uga_handle;
-	efi_status_t status = EFI_INVALID_PARAMETER;
-	int i;
+	height = 0;
+	width = 0;
 
 	first_uga = NULL;
-	nr_ugas = size / sizeof(u64);
+	nr_ugas = size / (efi_is_64bit() ? sizeof(u64) : sizeof(u32));
 	for (i = 0; i < nr_ugas; i++) {
 		efi_guid_t pciio_proto = EFI_PCI_IO_PROTOCOL_GUID;
 		u32 w, h, depth, refresh;
 		void *pciio;
-		u64 handle = handles[i];
+		unsigned long handle = efi_is_64bit() ? ((u64 *)uga_handle)[i]
+						      : ((u32 *)uga_handle)[i];
 
 		status = efi_call_early(handle_protocol, handle,
-					&uga_proto, (void **)&uga);
+					uga_proto, (void **)&uga);
 		if (status != EFI_SUCCESS)
 			continue;
 
 		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
 
-		status = efi_early->call((unsigned long)uga->get_mode, uga,
-					 &w, &h, &depth, &refresh);
+		status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga,
+					&w, &h, &depth, &refresh);
 		if (status == EFI_SUCCESS && (!first_uga || pciio)) {
-			*width = w;
-			*height = h;
+			width = w;
+			height = h;
 
 			/*
 			 * Once we've found a UGA supporting PCIIO,
@@ -405,38 +378,6 @@ setup_uga64(void **uga_handle, unsigned long size, u32 *width, u32 *height)
 		}
 	}
 
-	return status;
-}
-
-/*
- * See if we have Universal Graphics Adapter (UGA) protocol
- */
-static efi_status_t
-setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size)
-{
-	efi_status_t status;
-	u32 width, height;
-	void **uga_handle = NULL;
-
-	status = efi_call_early(allocate_pool, EFI_LOADER_DATA,
-				size, (void **)&uga_handle);
-	if (status != EFI_SUCCESS)
-		return status;
-
-	status = efi_call_early(locate_handle,
-				EFI_LOCATE_BY_PROTOCOL,
-				uga_proto, NULL, &size, uga_handle);
-	if (status != EFI_SUCCESS)
-		goto free_handle;
-
-	height = 0;
-	width = 0;
-
-	if (efi_early->is64)
-		status = setup_uga64(uga_handle, size, &width, &height);
-	else
-		status = setup_uga32(uga_handle, size, &width, &height);
-
 	if (!width && !height)
 		goto free_handle;
 
-- 
cgit v1.2.3


From 093174f52553532b9eb0e63cbbb254f6990d46d5 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 20 Jul 2018 10:47:22 +0900
Subject: efi/x86: Add missing NULL initialization in UGA draw protocol
 discovery

The UGA draw protocol discovery routine looks for a EFI handle that has
both the UGA draw protocol and the PCI I/O protocol installed. It checks
for the latter by calling handle_protocol() and pass it a PCI I/O
protocol pointer variable by reference, but fails to initialize it to
NULL, which means the non-NULL check later on in the code could produce
false positives, given that the return code of the handle_protocol() call
is ignored entirely. So add the missing initialization.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-6-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/eboot.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index ac8e442db71f..92b573fd239c 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -359,6 +359,7 @@ setup_uga(struct screen_info *si, efi_guid_t *uga_proto, unsigned long size)
 		if (status != EFI_SUCCESS)
 			continue;
 
+		pciio = NULL;
 		efi_call_early(handle_protocol, handle, &pciio_proto, &pciio);
 
 		status = efi_call_proto(efi_uga_draw_protocol, get_mode, uga,
-- 
cgit v1.2.3


From c4db9c1e8c70bc60e392da8a485bcfb035d559c2 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Fri, 20 Jul 2018 10:47:23 +0900
Subject: efi: Deduplicate efi_open_volume()

There's one ARM, one x86_32 and one x86_64 version of efi_open_volume()
which can be folded into a single shared version by masking their
differences with the efi_call_proto() macro introduced by commit:

  3552fdf29f01 ("efi: Allow bitness-agnostic protocol calls").

To be able to dereference the device_handle attribute from the
efi_loaded_image_t table in an arch- and bitness-agnostic manner,
introduce the efi_table_attr() macro (which already exists for x86)
to arm and arm64.

No functional change intended.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-7-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/efi.h                     |  3 ++
 arch/arm64/include/asm/efi.h                   |  3 ++
 arch/x86/boot/compressed/eboot.c               | 63 --------------------------
 drivers/firmware/efi/libstub/arm-stub.c        | 25 ----------
 drivers/firmware/efi/libstub/efi-stub-helper.c | 31 ++++++++++++-
 drivers/firmware/efi/libstub/efistub.h         |  3 --
 include/linux/efi.h                            | 10 ++++
 7 files changed, 45 insertions(+), 93 deletions(-)

diff --git a/arch/arm/include/asm/efi.h b/arch/arm/include/asm/efi.h
index 17f1f1a814ff..38badaae8d9d 100644
--- a/arch/arm/include/asm/efi.h
+++ b/arch/arm/include/asm/efi.h
@@ -58,6 +58,9 @@ void efi_virtmap_unload(void);
 #define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(false)
 
+#define efi_table_attr(table, attr, instance)				\
+	((table##_t *)instance)->attr
+
 #define efi_call_proto(protocol, f, instance, ...)			\
 	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
 
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index 192d791f1103..7ed320895d1f 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -87,6 +87,9 @@ static inline unsigned long efi_get_max_initrd_addr(unsigned long dram_base,
 #define efi_call_runtime(f, ...)	sys_table_arg->runtime->f(__VA_ARGS__)
 #define efi_is_64bit()			(true)
 
+#define efi_table_attr(table, attr, instance)				\
+	((table##_t *)instance)->attr
+
 #define efi_call_proto(protocol, f, instance, ...)			\
 	((protocol##_t *)instance)->f(instance, ##__VA_ARGS__)
 
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 92b573fd239c..915c64edbe8e 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -41,69 +41,6 @@ static void setup_boot_services##bits(struct efi_config *c)		\
 BOOT_SERVICES(32);
 BOOT_SERVICES(64);
 
-static inline efi_status_t __open_volume32(void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_32_t *image = __image;
-	efi_file_handle_32_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-	unsigned long func;
-
-	status = efi_call_early(handle_protocol, handle,
-				&fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	func = (unsigned long)io->open_volume;
-	status = efi_early->call(func, io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to open volume\n");
-
-	*__fh = fh;
-
-	return status;
-}
-
-static inline efi_status_t __open_volume64(void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_64_t *image = __image;
-	efi_file_handle_64_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-	unsigned long func;
-
-	status = efi_call_early(handle_protocol, handle,
-				&fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	func = (unsigned long)io->open_volume;
-	status = efi_early->call(func, io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table, "Failed to open volume\n");
-
-	*__fh = fh;
-
-	return status;
-}
-
-efi_status_t
-efi_open_volume(efi_system_table_t *sys_table, void *__image, void **__fh)
-{
-	if (efi_early->is64)
-		return __open_volume64(__image, __fh);
-
-	return __open_volume32(__image, __fh);
-}
-
 void efi_char16_printk(efi_system_table_t *table, efi_char16_t *str)
 {
 	efi_call_proto(efi_simple_text_output_protocol, output_string,
diff --git a/drivers/firmware/efi/libstub/arm-stub.c b/drivers/firmware/efi/libstub/arm-stub.c
index c98b1856fc3d..6920033de6d4 100644
--- a/drivers/firmware/efi/libstub/arm-stub.c
+++ b/drivers/firmware/efi/libstub/arm-stub.c
@@ -40,31 +40,6 @@
 
 static u64 virtmap_base = EFI_RT_VIRTUAL_BASE;
 
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
-			     void *__image, void **__fh)
-{
-	efi_file_io_interface_t *io;
-	efi_loaded_image_t *image = __image;
-	efi_file_handle_t *fh;
-	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
-	efi_status_t status;
-	void *handle = (void *)(unsigned long)image->device_handle;
-
-	status = sys_table_arg->boottime->handle_protocol(handle,
-				 &fs_proto, (void **)&io);
-	if (status != EFI_SUCCESS) {
-		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
-		return status;
-	}
-
-	status = io->open_volume(io, &fh);
-	if (status != EFI_SUCCESS)
-		efi_printk(sys_table_arg, "Failed to open volume\n");
-
-	*__fh = fh;
-	return status;
-}
-
 void efi_char16_printk(efi_system_table_t *sys_table_arg,
 			      efi_char16_t *str)
 {
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index 50a9cab5a834..e94975f4655b 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -413,6 +413,34 @@ static efi_status_t efi_file_close(void *handle)
 	return efi_call_proto(efi_file_handle, close, handle);
 }
 
+static efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg,
+				    efi_loaded_image_t *image,
+				    efi_file_handle_t **__fh)
+{
+	efi_file_io_interface_t *io;
+	efi_file_handle_t *fh;
+	efi_guid_t fs_proto = EFI_FILE_SYSTEM_GUID;
+	efi_status_t status;
+	void *handle = (void *)(unsigned long)efi_table_attr(efi_loaded_image,
+							     device_handle,
+							     image);
+
+	status = efi_call_early(handle_protocol, handle,
+				&fs_proto, (void **)&io);
+	if (status != EFI_SUCCESS) {
+		efi_printk(sys_table_arg, "Failed to handle fs_proto\n");
+		return status;
+	}
+
+	status = efi_call_proto(efi_file_io_interface, open_volume, io, &fh);
+	if (status != EFI_SUCCESS)
+		efi_printk(sys_table_arg, "Failed to open volume\n");
+	else
+		*__fh = fh;
+
+	return status;
+}
+
 /*
  * Parse the ASCII string 'cmdline' for EFI options, denoted by the efi=
  * option, e.g. efi=nochunk.
@@ -563,8 +591,7 @@ efi_status_t handle_cmdline_files(efi_system_table_t *sys_table_arg,
 
 		/* Only open the volume once. */
 		if (!i) {
-			status = efi_open_volume(sys_table_arg, image,
-						 (void **)&fh);
+			status = efi_open_volume(sys_table_arg, image, &fh);
 			if (status != EFI_SUCCESS)
 				goto free_files;
 		}
diff --git a/drivers/firmware/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index f59564b72ddc..32799cf039ef 100644
--- a/drivers/firmware/efi/libstub/efistub.h
+++ b/drivers/firmware/efi/libstub/efistub.h
@@ -36,9 +36,6 @@ extern int __pure is_quiet(void);
 
 void efi_char16_printk(efi_system_table_t *, efi_char16_t *);
 
-efi_status_t efi_open_volume(efi_system_table_t *sys_table_arg, void *__image,
-			     void **__fh);
-
 unsigned long get_dram_base(efi_system_table_t *sys_table_arg);
 
 efi_status_t allocate_new_fdt_and_exit_boot(efi_system_table_t *sys_table,
diff --git a/include/linux/efi.h b/include/linux/efi.h
index e190652f5ef9..401e4b254e30 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -894,6 +894,16 @@ typedef struct _efi_file_handle {
 	void *flush;
 } efi_file_handle_t;
 
+typedef struct {
+	u64 revision;
+	u32 open_volume;
+} efi_file_io_interface_32_t;
+
+typedef struct {
+	u64 revision;
+	u64 open_volume;
+} efi_file_io_interface_64_t;
+
 typedef struct _efi_file_io_interface {
 	u64 revision;
 	int (*open_volume)(struct _efi_file_io_interface *,
-- 
cgit v1.2.3


From aab9593c0cb4454f9d261a8c87a3361f3186c4ec Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Fri, 20 Jul 2018 10:47:24 +0900
Subject: efi/x86: Replace references to efi_early->is64 with efi_is_64bit()

There are a couple of places in the x86 EFI stub code where we select
between 32-bit and 64-bit versions of the support routines based on
the value of efi_early->is64. Referencing that field directly is a
bad idea, since it prevents the compiler from inferring that this
field can never be true on a 32-bit build, and can only become false
on a 64-bit build if support for mixed mode is compiled in. This
results in dead code to be retained in the uncompressed part of the
kernel image, which is wasteful.

So switch to the efi_is_64bit() helper, which will resolve to a
constant boolean unless building for 64-bit with mixed mode support.

Tested-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-8-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/boot/compressed/eboot.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 915c64edbe8e..1458b1700fc7 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -404,7 +404,7 @@ struct boot_params *make_boot_params(struct efi_config *c)
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		return NULL;
 
-	if (efi_early->is64)
+	if (efi_is_64bit())
 		setup_boot_services64(efi_early);
 	else
 		setup_boot_services32(efi_early);
@@ -639,7 +639,6 @@ struct exit_boot_struct {
 	struct efi_info		*efi;
 	struct setup_data	*e820ext;
 	__u32			e820ext_size;
-	bool			is64;
 };
 
 static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
@@ -666,7 +665,8 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 		first = false;
 	}
 
-	signature = p->is64 ? EFI64_LOADER_SIGNATURE : EFI32_LOADER_SIGNATURE;
+	signature = efi_is_64bit() ? EFI64_LOADER_SIGNATURE
+				   : EFI32_LOADER_SIGNATURE;
 	memcpy(&p->efi->efi_loader_signature, signature, sizeof(__u32));
 
 	p->efi->efi_systab		= (unsigned long)sys_table_arg;
@@ -683,8 +683,7 @@ static efi_status_t exit_boot_func(efi_system_table_t *sys_table_arg,
 	return EFI_SUCCESS;
 }
 
-static efi_status_t exit_boot(struct boot_params *boot_params,
-			      void *handle, bool is64)
+static efi_status_t exit_boot(struct boot_params *boot_params, void *handle)
 {
 	unsigned long map_sz, key, desc_size, buff_size;
 	efi_memory_desc_t *mem_map;
@@ -705,7 +704,6 @@ static efi_status_t exit_boot(struct boot_params *boot_params,
 	priv.efi		= &boot_params->efi_info;
 	priv.e820ext		= NULL;
 	priv.e820ext_size	= 0;
-	priv.is64		= is64;
 
 	/* Might as well exit boot services now */
 	status = efi_exit_boot_services(sys_table, handle, &map, &priv,
@@ -740,13 +738,11 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
 	struct desc_struct *desc;
 	void *handle;
 	efi_system_table_t *_table;
-	bool is64;
 
 	efi_early = c;
 
 	_table = (efi_system_table_t *)(unsigned long)efi_early->table;
 	handle = (void *)(unsigned long)efi_early->image_handle;
-	is64 = efi_early->is64;
 
 	sys_table = _table;
 
@@ -754,7 +750,7 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		goto fail;
 
-	if (is64)
+	if (efi_is_64bit())
 		setup_boot_services64(efi_early);
 	else
 		setup_boot_services32(efi_early);
@@ -810,7 +806,7 @@ efi_main(struct efi_config *c, struct boot_params *boot_params)
 		hdr->code32_start = bzimage_addr;
 	}
 
-	status = exit_boot(boot_params, handle, is64);
+	status = exit_boot(boot_params, handle);
 	if (status != EFI_SUCCESS) {
 		efi_printk(sys_table, "exit_boot() failed!\n");
 		goto fail;
-- 
cgit v1.2.3


From e8f4194d9b98aa13f9f567a0056bbf683d2b1ab8 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 20 Jul 2018 10:47:25 +0900
Subject: efi/cper: Use consistent types for UUIDs

The commit:

  2f74f09bce4f ("efi: parse ARM processor error")

... brought inconsistency in UUID types which are used across the CPER.

Fix this by moving to use guid_t API everywhere.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tyler Baicar <tbaicar@codeaurora.org>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-9-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 drivers/firmware/efi/cper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/cper.c b/drivers/firmware/efi/cper.c
index b73fc4cab083..a7902fccdcfa 100644
--- a/drivers/firmware/efi/cper.c
+++ b/drivers/firmware/efi/cper.c
@@ -472,7 +472,7 @@ cper_estatus_print_section(const char *pfx, struct acpi_hest_generic_data *gdata
 		else
 			goto err_section_too_small;
 #if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
-	} else if (!uuid_le_cmp(*sec_type, CPER_SEC_PROC_ARM)) {
+	} else if (guid_equal(sec_type, &CPER_SEC_PROC_ARM)) {
 		struct cper_sec_proc_arm *arm_err = acpi_hest_get_payload(gdata);
 
 		printk("%ssection_type: ARM processor error\n", newpfx);
-- 
cgit v1.2.3


From c4326563d9abe86ad54474f9e9142bd2663eede5 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 20 Jul 2018 10:47:26 +0900
Subject: efivars: Call guid_parse() against guid_t type of variable

uuid_le_to_bin() is deprecated API and take into consideration that variable,
to where we store parsed data, is type of guid_t we switch to guid_parse()
for sake of consistency.

While here, add error checking to it.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Lukas Wunner <lukas@wunner.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-efi@vger.kernel.org
Link: http://lkml.kernel.org/r/20180720014726.24031-10-ard.biesheuvel@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 fs/efivarfs/inode.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 71fccccf317e..8c6ab6c95727 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -86,7 +86,9 @@ static int efivarfs_create(struct inode *dir, struct dentry *dentry,
 	/* length of the variable name itself: remove GUID and separator */
 	namelen = dentry->d_name.len - EFI_VARIABLE_GUID_LEN - 1;
 
-	uuid_le_to_bin(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+	err = guid_parse(dentry->d_name.name + namelen + 1, &var->var.VendorGuid);
+	if (err)
+		goto out;
 
 	if (efivar_variable_is_removable(var->var.VendorGuid,
 					 dentry->d_name.name, namelen))
-- 
cgit v1.2.3


From 652e4f3e82a144500f17af772503b6e216441f9f Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:13 +0800
Subject: vhost_net: drop unnecessary parameter

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index b2240361f1a1..1a8175ae2941 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -430,7 +430,6 @@ static int vhost_net_enable_vq(struct vhost_net *n,
 
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 				    struct vhost_virtqueue *vq,
-				    struct iovec iov[], unsigned int iov_size,
 				    unsigned int *out_num, unsigned int *in_num,
 				    bool *busyloop_intr)
 {
@@ -512,9 +511,8 @@ static void handle_tx(struct vhost_net *net)
 			vhost_zerocopy_signal_used(net, vq);
 
 		busyloop_intr = false;
-		head = vhost_net_tx_get_vq_desc(net, vq, vq->iov,
-						ARRAY_SIZE(vq->iov),
-						&out, &in, &busyloop_intr);
+		head = vhost_net_tx_get_vq_desc(net, vq, &out, &in,
+						&busyloop_intr);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(head < 0))
 			break;
-- 
cgit v1.2.3


From b0d0ea50e7827b1d71c8ea466ff8b4b358f9548d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:14 +0800
Subject: vhost_net: introduce helper to initialize tx iov iter

Introduce init_iov_iter() in order to be reused by future patch.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 1a8175ae2941..cac28fdc938d 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -466,6 +466,18 @@ static bool vhost_exceeds_maxpend(struct vhost_net *net)
 	       min_t(unsigned int, VHOST_MAX_PEND, vq->num >> 2);
 }
 
+static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter,
+			    size_t hdr_size, int out)
+{
+	/* Skip header. TODO: support TSO. */
+	size_t len = iov_length(vq->iov, out);
+
+	iov_iter_init(iter, WRITE, vq->iov, out, len);
+	iov_iter_advance(iter, hdr_size);
+
+	return iov_iter_count(iter);
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -531,18 +543,14 @@ static void handle_tx(struct vhost_net *net)
 			       "out %d, int %d\n", out, in);
 			break;
 		}
-		/* Skip header. TODO: support TSO. */
-		len = iov_length(vq->iov, out);
-		iov_iter_init(&msg.msg_iter, WRITE, vq->iov, out, len);
-		iov_iter_advance(&msg.msg_iter, hdr_size);
+
 		/* Sanity check */
-		if (!msg_data_left(&msg)) {
-			vq_err(vq, "Unexpected header len for TX: "
-			       "%zd expected %zd\n",
-			       len, hdr_size);
+		len = init_iov_iter(vq, &msg.msg_iter, hdr_size, out);
+		if (!len) {
+			vq_err(vq, "Unexpected header len for TX: %zd expected %zd\n",
+			len, hdr_size);
 			break;
 		}
-		len = msg_data_left(&msg);
 
 		zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
 				   && !vhost_exceeds_maxpend(net)
-- 
cgit v1.2.3


From 272f35cba53d088085e5952fd81d7a133ab90789 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:15 +0800
Subject: vhost_net: introduce vhost_exceeds_weight()

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index cac28fdc938d..b9e1674ca9e1 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -478,6 +478,12 @@ static size_t init_iov_iter(struct vhost_virtqueue *vq, struct iov_iter *iter,
 	return iov_iter_count(iter);
 }
 
+static bool vhost_exceeds_weight(int pkts, int total_len)
+{
+	return total_len >= VHOST_NET_WEIGHT ||
+	       pkts >= VHOST_NET_PKT_WEIGHT;
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -576,7 +582,6 @@ static void handle_tx(struct vhost_net *net)
 			msg.msg_control = NULL;
 			ubufs = NULL;
 		}
-
 		total_len += len;
 		if (total_len < VHOST_NET_WEIGHT &&
 		    !vhost_vq_avail_empty(&net->dev, vq) &&
@@ -606,8 +611,7 @@ static void handle_tx(struct vhost_net *net)
 		else
 			vhost_zerocopy_signal_used(net, vq);
 		vhost_net_tx_packet(net);
-		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
-		    unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) {
+		if (unlikely(vhost_exceeds_weight(++sent_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
 			break;
 		}
@@ -918,8 +922,7 @@ static void handle_rx(struct vhost_net *net)
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		total_len += vhost_len;
-		if (unlikely(total_len >= VHOST_NET_WEIGHT) ||
-		    unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) {
+		if (unlikely(vhost_exceeds_weight(++recv_pkts, total_len))) {
 			vhost_poll_queue(&vq->poll);
 			goto out;
 		}
-- 
cgit v1.2.3


From a2a91a137ad4e9c538c9b63b2bfcf7a105924143 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:16 +0800
Subject: vhost_net: introduce get_tx_bufs()

Factor out logic of getting tx buffer and iov iter
initialization. This will be used for reducing codes duplication in
the future.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 49 ++++++++++++++++++++++++++++++++-----------------
 1 file changed, 32 insertions(+), 17 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index b9e1674ca9e1..a014ca042390 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -484,6 +484,36 @@ static bool vhost_exceeds_weight(int pkts, int total_len)
 	       pkts >= VHOST_NET_PKT_WEIGHT;
 }
 
+static int get_tx_bufs(struct vhost_net *net,
+		       struct vhost_net_virtqueue *nvq,
+		       struct msghdr *msg,
+		       unsigned int *out, unsigned int *in,
+		       size_t *len, bool *busyloop_intr)
+{
+	struct vhost_virtqueue *vq = &nvq->vq;
+	int ret;
+
+	ret = vhost_net_tx_get_vq_desc(net, vq, out, in, busyloop_intr);
+	if (ret < 0 || ret == vq->num)
+		return ret;
+
+	if (*in) {
+		vq_err(vq, "Unexpected descriptor format for TX: out %d, int %d\n",
+			*out, *in);
+		return -EFAULT;
+	}
+
+	/* Sanity check */
+	*len = init_iov_iter(vq, &msg->msg_iter, nvq->vhost_hlen, *out);
+	if (*len == 0) {
+		vq_err(vq, "Unexpected header len for TX: %zd expected %zd\n",
+			*len, nvq->vhost_hlen);
+		return -EFAULT;
+	}
+
+	return ret;
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -501,7 +531,6 @@ static void handle_tx(struct vhost_net *net)
 	};
 	size_t len, total_len = 0;
 	int err;
-	size_t hdr_size;
 	struct socket *sock;
 	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
 	bool zcopy, zcopy_used;
@@ -518,7 +547,6 @@ static void handle_tx(struct vhost_net *net)
 	vhost_disable_notify(&net->dev, vq);
 	vhost_net_disable_vq(net, vq);
 
-	hdr_size = nvq->vhost_hlen;
 	zcopy = nvq->ubufs;
 
 	for (;;) {
@@ -529,8 +557,8 @@ static void handle_tx(struct vhost_net *net)
 			vhost_zerocopy_signal_used(net, vq);
 
 		busyloop_intr = false;
-		head = vhost_net_tx_get_vq_desc(net, vq, &out, &in,
-						&busyloop_intr);
+		head = get_tx_bufs(net, nvq, &msg, &out, &in, &len,
+				   &busyloop_intr);
 		/* On error, stop handling until the next kick. */
 		if (unlikely(head < 0))
 			break;
@@ -544,19 +572,6 @@ static void handle_tx(struct vhost_net *net)
 			}
 			break;
 		}
-		if (in) {
-			vq_err(vq, "Unexpected descriptor format for TX: "
-			       "out %d, int %d\n", out, in);
-			break;
-		}
-
-		/* Sanity check */
-		len = init_iov_iter(vq, &msg.msg_iter, hdr_size, out);
-		if (!len) {
-			vq_err(vq, "Unexpected header len for TX: %zd expected %zd\n",
-			len, hdr_size);
-			break;
-		}
 
 		zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
 				   && !vhost_exceeds_maxpend(net)
-- 
cgit v1.2.3


From c92a8a8cb7d499a352ebb625667a780bfc99ba77 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:17 +0800
Subject: vhost_net: introduce tx_can_batch()

Introduce tx_can_batch() to determine whether TX could be
batched. This will help to reduce the code duplication in the future.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index a014ca042390..f59b615e2989 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -514,6 +514,12 @@ static int get_tx_bufs(struct vhost_net *net,
 	return ret;
 }
 
+static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len)
+{
+	return total_len < VHOST_NET_WEIGHT &&
+	       !vhost_vq_avail_empty(vq->dev, vq);
+}
+
 /* Expects to be always run from workqueue - which acts as
  * read-size critical section for our kind of RCU. */
 static void handle_tx(struct vhost_net *net)
@@ -598,8 +604,7 @@ static void handle_tx(struct vhost_net *net)
 			ubufs = NULL;
 		}
 		total_len += len;
-		if (total_len < VHOST_NET_WEIGHT &&
-		    !vhost_vq_avail_empty(&net->dev, vq) &&
+		if (tx_can_batch(vq, total_len) &&
 		    likely(!vhost_exceeds_maxpend(net))) {
 			msg.msg_flags |= MSG_MORE;
 		} else {
-- 
cgit v1.2.3


From 0d20bdf34dc7d6aeaa04f762be3e313bc4fa1b02 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:18 +0800
Subject: vhost_net: split out datacopy logic

Instead of mixing zerocopy and datacopy logics, this patch tries to
split datacopy logic out. This results for a more compact code and
ad-hoc optimization could be done on top more easily.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 110 ++++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 90 insertions(+), 20 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f59b615e2989..9cef0b2502b0 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -520,9 +520,7 @@ static bool tx_can_batch(struct vhost_virtqueue *vq, size_t total_len)
 	       !vhost_vq_avail_empty(vq->dev, vq);
 }
 
-/* Expects to be always run from workqueue - which acts as
- * read-size critical section for our kind of RCU. */
-static void handle_tx(struct vhost_net *net)
+static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 {
 	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
 	struct vhost_virtqueue *vq = &nvq->vq;
@@ -537,30 +535,76 @@ static void handle_tx(struct vhost_net *net)
 	};
 	size_t len, total_len = 0;
 	int err;
-	struct socket *sock;
-	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
-	bool zcopy, zcopy_used;
 	int sent_pkts = 0;
 
-	mutex_lock(&vq->mutex);
-	sock = vq->private_data;
-	if (!sock)
-		goto out;
+	for (;;) {
+		bool busyloop_intr = false;
 
-	if (!vq_iotlb_prefetch(vq))
-		goto out;
+		head = get_tx_bufs(net, nvq, &msg, &out, &in, &len,
+				   &busyloop_intr);
+		/* On error, stop handling until the next kick. */
+		if (unlikely(head < 0))
+			break;
+		/* Nothing new?  Wait for eventfd to tell us they refilled. */
+		if (head == vq->num) {
+			if (unlikely(busyloop_intr)) {
+				vhost_poll_queue(&vq->poll);
+			} else if (unlikely(vhost_enable_notify(&net->dev,
+								vq))) {
+				vhost_disable_notify(&net->dev, vq);
+				continue;
+			}
+			break;
+		}
 
-	vhost_disable_notify(&net->dev, vq);
-	vhost_net_disable_vq(net, vq);
+		total_len += len;
+		if (tx_can_batch(vq, total_len))
+			msg.msg_flags |= MSG_MORE;
+		else
+			msg.msg_flags &= ~MSG_MORE;
+
+		/* TODO: Check specific error and bomb out unless ENOBUFS? */
+		err = sock->ops->sendmsg(sock, &msg, len);
+		if (unlikely(err < 0)) {
+			vhost_discard_vq_desc(vq, 1);
+			vhost_net_enable_vq(net, vq);
+			break;
+		}
+		if (err != len)
+			pr_debug("Truncated TX packet: len %d != %zd\n",
+				 err, len);
+		vhost_add_used_and_signal(&net->dev, vq, head, 0);
+		if (vhost_exceeds_weight(++sent_pkts, total_len)) {
+			vhost_poll_queue(&vq->poll);
+			break;
+		}
+	}
+}
 
-	zcopy = nvq->ubufs;
+static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
+{
+	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *vq = &nvq->vq;
+	unsigned out, in;
+	int head;
+	struct msghdr msg = {
+		.msg_name = NULL,
+		.msg_namelen = 0,
+		.msg_control = NULL,
+		.msg_controllen = 0,
+		.msg_flags = MSG_DONTWAIT,
+	};
+	size_t len, total_len = 0;
+	int err;
+	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
+	bool zcopy_used;
+	int sent_pkts = 0;
 
 	for (;;) {
 		bool busyloop_intr;
 
 		/* Release DMAs done buffers first */
-		if (zcopy)
-			vhost_zerocopy_signal_used(net, vq);
+		vhost_zerocopy_signal_used(net, vq);
 
 		busyloop_intr = false;
 		head = get_tx_bufs(net, nvq, &msg, &out, &in, &len,
@@ -579,9 +623,9 @@ static void handle_tx(struct vhost_net *net)
 			break;
 		}
 
-		zcopy_used = zcopy && len >= VHOST_GOODCOPY_LEN
-				   && !vhost_exceeds_maxpend(net)
-				   && vhost_net_tx_select_zcopy(net);
+		zcopy_used = len >= VHOST_GOODCOPY_LEN
+			     && !vhost_exceeds_maxpend(net)
+			     && vhost_net_tx_select_zcopy(net);
 
 		/* use msg_control to pass vhost zerocopy ubuf info to skb */
 		if (zcopy_used) {
@@ -636,6 +680,32 @@ static void handle_tx(struct vhost_net *net)
 			break;
 		}
 	}
+}
+
+/* Expects to be always run from workqueue - which acts as
+ * read-size critical section for our kind of RCU. */
+static void handle_tx(struct vhost_net *net)
+{
+	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
+	struct vhost_virtqueue *vq = &nvq->vq;
+	struct socket *sock;
+
+	mutex_lock(&vq->mutex);
+	sock = vq->private_data;
+	if (!sock)
+		goto out;
+
+	if (!vq_iotlb_prefetch(vq))
+		goto out;
+
+	vhost_disable_notify(&net->dev, vq);
+	vhost_net_disable_vq(net, vq);
+
+	if (vhost_sock_zcopy(sock))
+		handle_tx_zerocopy(net, sock);
+	else
+		handle_tx_copy(net, sock);
+
 out:
 	mutex_unlock(&vq->mutex);
 }
-- 
cgit v1.2.3


From 09c3248938c3e3b0ef870c8f1b3f13d6dcbf67ce Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:19 +0800
Subject: vhost_net: rename vhost_rx_signal_used() to vhost_net_signal_used()

Rename for reusing this for TX.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 9cef0b2502b0..53d305b368b1 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -741,7 +741,7 @@ static int sk_has_rx_data(struct sock *sk)
 	return skb_queue_empty(&sk->sk_receive_queue);
 }
 
-static void vhost_rx_signal_used(struct vhost_net_virtqueue *nvq)
+static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq)
 {
 	struct vhost_virtqueue *vq = &nvq->vq;
 	struct vhost_dev *dev = vq->dev;
@@ -765,7 +765,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 
 	if (!len && tvq->busyloop_timeout) {
 		/* Flush batched heads first */
-		vhost_rx_signal_used(rnvq);
+		vhost_net_signal_used(rnvq);
 		/* Both tx vq and rx socket were polled here */
 		mutex_lock_nested(&tvq->mutex, 1);
 		vhost_disable_notify(&net->dev, tvq);
@@ -1008,7 +1008,7 @@ static void handle_rx(struct vhost_net *net)
 		}
 		nvq->done_idx += headcount;
 		if (nvq->done_idx > VHOST_RX_BATCH)
-			vhost_rx_signal_used(nvq);
+			vhost_net_signal_used(nvq);
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
 		total_len += vhost_len;
@@ -1022,7 +1022,7 @@ static void handle_rx(struct vhost_net *net)
 	else
 		vhost_net_enable_vq(net, vq);
 out:
-	vhost_rx_signal_used(nvq);
+	vhost_net_signal_used(nvq);
 	mutex_unlock(&vq->mutex);
 }
 
-- 
cgit v1.2.3


From d0d869718754da534719be32f2c28b1210c3955d Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:20 +0800
Subject: vhost_net: rename VHOST_RX_BATCH to VHOST_NET_BATCH

A more generic name which could be used for TX as well.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 53d305b368b1..2fd2f0e3d0f4 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -94,7 +94,7 @@ struct vhost_net_ubuf_ref {
 	struct vhost_virtqueue *vq;
 };
 
-#define VHOST_RX_BATCH 64
+#define VHOST_NET_BATCH 64
 struct vhost_net_buf {
 	void **queue;
 	int tail;
@@ -168,7 +168,7 @@ static int vhost_net_buf_produce(struct vhost_net_virtqueue *nvq)
 
 	rxq->head = 0;
 	rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
-					      VHOST_RX_BATCH);
+					      VHOST_NET_BATCH);
 	return rxq->tail;
 }
 
@@ -1007,7 +1007,7 @@ static void handle_rx(struct vhost_net *net)
 			goto out;
 		}
 		nvq->done_idx += headcount;
-		if (nvq->done_idx > VHOST_RX_BATCH)
+		if (nvq->done_idx > VHOST_NET_BATCH)
 			vhost_net_signal_used(nvq);
 		if (unlikely(vq_log))
 			vhost_log_write(vq, vq_log, log, vhost_len);
@@ -1075,7 +1075,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 		return -ENOMEM;
 	}
 
-	queue = kmalloc_array(VHOST_RX_BATCH, sizeof(void *),
+	queue = kmalloc_array(VHOST_NET_BATCH, sizeof(void *),
 			      GFP_KERNEL);
 	if (!queue) {
 		kfree(vqs);
-- 
cgit v1.2.3


From 4afb52c2af44ac761e829d4cd511a20b577959fa Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Fri, 20 Jul 2018 08:15:21 +0800
Subject: vhost_net: batch update used ring for datacopy TX

Like commit e2b3b35eb989 ("vhost_net: batch used ring update in rx"),
this patches implements batch used ring update for datacopy TX
(zerocopy has already done some kind of batching).

Testpmd transmission from guest to host (XDP_DROP on tap) shows 25.8%
improvement (from ~3.1Mpps to ~3.9Mpps) on Broadwell i7-5600U CPU @
2.60GHz machine. Netperf TCP tests does not show obvious differences.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c | 40 +++++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 2fd2f0e3d0f4..367d8023b54d 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -428,16 +428,31 @@ static int vhost_net_enable_vq(struct vhost_net *n,
 	return vhost_poll_start(poll, sock->file);
 }
 
+static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq)
+{
+	struct vhost_virtqueue *vq = &nvq->vq;
+	struct vhost_dev *dev = vq->dev;
+
+	if (!nvq->done_idx)
+		return;
+
+	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
+	nvq->done_idx = 0;
+}
+
 static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
-				    struct vhost_virtqueue *vq,
+				    struct vhost_net_virtqueue *nvq,
 				    unsigned int *out_num, unsigned int *in_num,
 				    bool *busyloop_intr)
 {
+	struct vhost_virtqueue *vq = &nvq->vq;
 	unsigned long uninitialized_var(endtime);
 	int r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
 				  out_num, in_num, NULL, NULL);
 
 	if (r == vq->num && vq->busyloop_timeout) {
+		if (!vhost_sock_zcopy(vq->private_data))
+			vhost_net_signal_used(nvq);
 		preempt_disable();
 		endtime = busy_clock() + vq->busyloop_timeout;
 		while (vhost_can_busy_poll(endtime)) {
@@ -493,7 +508,8 @@ static int get_tx_bufs(struct vhost_net *net,
 	struct vhost_virtqueue *vq = &nvq->vq;
 	int ret;
 
-	ret = vhost_net_tx_get_vq_desc(net, vq, out, in, busyloop_intr);
+	ret = vhost_net_tx_get_vq_desc(net, nvq, out, in, busyloop_intr);
+
 	if (ret < 0 || ret == vq->num)
 		return ret;
 
@@ -557,6 +573,9 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 			break;
 		}
 
+		vq->heads[nvq->done_idx].id = cpu_to_vhost32(vq, head);
+		vq->heads[nvq->done_idx].len = 0;
+
 		total_len += len;
 		if (tx_can_batch(vq, total_len))
 			msg.msg_flags |= MSG_MORE;
@@ -573,12 +592,15 @@ static void handle_tx_copy(struct vhost_net *net, struct socket *sock)
 		if (err != len)
 			pr_debug("Truncated TX packet: len %d != %zd\n",
 				 err, len);
-		vhost_add_used_and_signal(&net->dev, vq, head, 0);
+		if (++nvq->done_idx >= VHOST_NET_BATCH)
+			vhost_net_signal_used(nvq);
 		if (vhost_exceeds_weight(++sent_pkts, total_len)) {
 			vhost_poll_queue(&vq->poll);
 			break;
 		}
 	}
+
+	vhost_net_signal_used(nvq);
 }
 
 static void handle_tx_zerocopy(struct vhost_net *net, struct socket *sock)
@@ -741,18 +763,6 @@ static int sk_has_rx_data(struct sock *sk)
 	return skb_queue_empty(&sk->sk_receive_queue);
 }
 
-static void vhost_net_signal_used(struct vhost_net_virtqueue *nvq)
-{
-	struct vhost_virtqueue *vq = &nvq->vq;
-	struct vhost_dev *dev = vq->dev;
-
-	if (!nvq->done_idx)
-		return;
-
-	vhost_add_used_and_signal_n(dev, vq, vq->heads, nvq->done_idx);
-	nvq->done_idx = 0;
-}
-
 static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk,
 				      bool *busyloop_intr)
 {
-- 
cgit v1.2.3


From 5b3df177233ef4413ffc2c1a7647736ba89d4df1 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Sun, 22 Jul 2018 11:37:31 +0300
Subject: bonding: don't cast const buf in sysfs store

As was recently discussed [1], let's avoid casting the const buf in
bonding_sysfs_store_option and use kstrndup/kfree instead.

[1] http://lists.openwall.net/netdev/2018/07/22/25

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/bonding/bond_sysfs.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c
index 6096440e96ea..35847250da5a 100644
--- a/drivers/net/bonding/bond_sysfs.c
+++ b/drivers/net/bonding/bond_sysfs.c
@@ -160,14 +160,19 @@ static ssize_t bonding_sysfs_store_option(struct device *d,
 {
 	struct bonding *bond = to_bond(d);
 	const struct bond_option *opt;
+	char *buffer_clone;
 	int ret;
 
 	opt = bond_opt_get_by_name(attr->attr.name);
 	if (WARN_ON(!opt))
 		return -ENOENT;
-	ret = bond_opt_tryset_rtnl(bond, opt->id, (char *)buffer);
+	buffer_clone = kstrndup(buffer, count, GFP_KERNEL);
+	if (!buffer_clone)
+		return -ENOMEM;
+	ret = bond_opt_tryset_rtnl(bond, opt->id, buffer_clone);
 	if (!ret)
 		ret = count;
+	kfree(buffer_clone);
 
 	return ret;
 }
-- 
cgit v1.2.3


From be5a8ffa9cdb14833c64a7ef40e76ce7fd265d9f Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 20 Jul 2018 09:16:02 -0700
Subject: net/dsa/realtek: add MODULE_LICENSE()

Add MODULE_LICENSE() to net/dsa/realtek.o to fix build warning message.

WARNING: modpost: missing MODULE_LICENSE() in drivers/net/dsa/realtek.o

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/realtek-smi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/realtek-smi.c b/drivers/net/dsa/realtek-smi.c
index f941f4582825..b4b839a1d095 100644
--- a/drivers/net/dsa/realtek-smi.c
+++ b/drivers/net/dsa/realtek-smi.c
@@ -485,3 +485,5 @@ static struct platform_driver realtek_smi_driver = {
 	.remove = realtek_smi_remove,
 };
 module_platform_driver(realtek_smi_driver);
+
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 2d408c0d4574b01b9ed45e02516888bf925e11a9 Mon Sep 17 00:00:00 2001
From: Vitaly Kuznetsov <vkuznets@redhat.com>
Date: Fri, 20 Jul 2018 18:33:59 +0200
Subject: xen-netfront: fix queue name setting

Commit f599c64fdf7d ("xen-netfront: Fix race between device setup and
open") changed the initialization order: xennet_create_queues() now
happens before we do register_netdev() so using netdev->name in
xennet_init_queue() is incorrect, we end up with the following in
/proc/interrupts:

 60:        139          0   xen-dyn    -event     eth%d-q0-tx
 61:        265          0   xen-dyn    -event     eth%d-q0-rx
 62:        234          0   xen-dyn    -event     eth%d-q1-tx
 63:          1          0   xen-dyn    -event     eth%d-q1-rx

and this looks ugly. Actually, using early netdev name (even when it's
already set) is also not ideal: nowadays we tend to rename eth devices
and queue name may end up not corresponding to the netdev name.

Use nodename from xenbus device for queue naming: this can't change in VM's
lifetime. Now /proc/interrupts looks like

 62:        202          0   xen-dyn    -event     device/vif/0-q0-tx
 63:        317          0   xen-dyn    -event     device/vif/0-q0-rx
 64:        262          0   xen-dyn    -event     device/vif/0-q1-tx
 65:         17          0   xen-dyn    -event     device/vif/0-q1-rx

Fixes: f599c64fdf7d ("xen-netfront: Fix race between device setup and open")
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Reviewed-by: Ross Lagerwall <ross.lagerwall@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index d67cd379d156..4d88aa394273 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1605,7 +1605,7 @@ static int xennet_init_queue(struct netfront_queue *queue)
 	timer_setup(&queue->rx_refill_timer, rx_refill_timeout, 0);
 
 	snprintf(queue->name, sizeof(queue->name), "%s-q%u",
-		 queue->info->netdev->name, queue->id);
+		 queue->info->xbdev->nodename, queue->id);
 
 	/* Initialise tx_skbs as a free chain containing every entry. */
 	queue->tx_skb_freelist = 0;
-- 
cgit v1.2.3


From 22f17952c7873a427e6e4280d723c0f686d75fb9 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Thu, 19 Jul 2018 21:42:13 -0400
Subject: blk-rq-qos: make depth comparisons unsigned

With the change to use UINT_MAX I broke the depth check as any value of
inflight (ie 0) would be less than (int)UINT_MAX.  Fix this by changing
everything to unsigned int to match the depth.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-rq-qos.c | 8 ++++----
 block/blk-rq-qos.h | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 5134b24482f6..0005dfd568dd 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -4,12 +4,12 @@
  * Increment 'v', if 'v' is below 'below'. Returns true if we succeeded,
  * false if 'v' + 1 would be bigger than 'below'.
  */
-static bool atomic_inc_below(atomic_t *v, int below)
+static bool atomic_inc_below(atomic_t *v, unsigned int below)
 {
-	int cur = atomic_read(v);
+	unsigned int cur = atomic_read(v);
 
 	for (;;) {
-		int old;
+		unsigned int old;
 
 		if (cur >= below)
 			return false;
@@ -22,7 +22,7 @@ static bool atomic_inc_below(atomic_t *v, int below)
 	return true;
 }
 
-bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit)
+bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit)
 {
 	return atomic_inc_below(&rq_wait->inflight, limit);
 }
diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h
index d5e2f68fe41e..32b02efbfa66 100644
--- a/block/blk-rq-qos.h
+++ b/block/blk-rq-qos.h
@@ -93,7 +93,7 @@ static inline void rq_qos_del(struct request_queue *q, struct rq_qos *rqos)
 	}
 }
 
-bool rq_wait_inc_below(struct rq_wait *rq_wait, int limit);
+bool rq_wait_inc_below(struct rq_wait *rq_wait, unsigned int limit);
 void rq_depth_scale_up(struct rq_depth *rqd);
 void rq_depth_scale_down(struct rq_depth *rqd, bool hard_throttle);
 bool rq_depth_calc_max_depth(struct rq_depth *rqd);
-- 
cgit v1.2.3


From 042f8825569d628517784d558aefe23c212f0fb2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 20 Jul 2018 21:14:38 -0700
Subject: nfp: bring back support for offloading shared blocks

Now that we have offload replay infrastructure added by
commit 326367427cc0 ("net: sched: call reoffload op on block callback reg")
and flows are guaranteed to be removed correctly, we can revert
commit 951a8ee6def3 ("nfp: reject binding to shared blocks").

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: John Hurley <john.hurley@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/main.c       | 3 ---
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 3 ---
 include/net/pkt_cls.h                               | 5 -----
 3 files changed, 11 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 458f49235d06..994d2b756fe1 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -195,9 +195,6 @@ static int nfp_bpf_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
-	if (tcf_block_shared(f->block))
-		return -EOPNOTSUPP;
-
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 43b9bf12b174..6bc8a97f7e03 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -631,9 +631,6 @@ static int nfp_flower_setup_tc_block(struct net_device *netdev,
 	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
 		return -EOPNOTSUPP;
 
-	if (tcf_block_shared(f->block))
-		return -EOPNOTSUPP;
-
 	switch (f->command) {
 	case TC_BLOCK_BIND:
 		return tcf_block_cb_register(f->block,
diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index e4252a176eec..4f405ca8346f 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -114,11 +114,6 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 {
 }
 
-static inline bool tcf_block_shared(struct tcf_block *block)
-{
-	return false;
-}
-
 static inline struct Qdisc *tcf_block_q(struct tcf_block *block)
 {
 	return NULL;
-- 
cgit v1.2.3


From 07300f774fec9519663a597987a4083225588be4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 20 Jul 2018 21:14:39 -0700
Subject: nfp: avoid buffer leak when FW communication fails

After device is stopped we reset the rings by moving all free buffers
to positions [0, cnt - 2], and clear the position cnt - 1 in the ring.
We then proceed to clear the read/write pointers.  This means that if
we try to reset the ring again the code will assume that the next to
fill buffer is at position 0 and swap it with cnt - 1.  Since we
previously cleared position cnt - 1 it will lead to leaking the first
buffer and leaving ring in a bad state.

This scenario can only happen if FW communication fails, in which case
the ring will never be used again, so the fact it's in a bad state will
not be noticed.  Buffer leak is the only problem.  Don't try to move
buffers in the ring if the read/write pointers indicate the ring was
never used or have already been reset.

nfp_net_clear_config_and_disable() is now fully idempotent.

Found by code inspection, FW communication failures are very rare,
and reconfiguring a live device is not common either, so it's unlikely
anyone has ever noticed the leak.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 279b8ab8a17b..cf1704e972b7 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1078,7 +1078,7 @@ static bool nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring)
  * @dp:		NFP Net data path struct
  * @tx_ring:	TX ring structure
  *
- * Assumes that the device is stopped
+ * Assumes that the device is stopped, must be idempotent.
  */
 static void
 nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
@@ -1280,13 +1280,18 @@ static void nfp_net_rx_give_one(const struct nfp_net_dp *dp,
  * nfp_net_rx_ring_reset() - Reflect in SW state of freelist after disable
  * @rx_ring:	RX ring structure
  *
- * Warning: Do *not* call if ring buffers were never put on the FW freelist
- *	    (i.e. device was not enabled)!
+ * Assumes that the device is stopped, must be idempotent.
  */
 static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 {
 	unsigned int wr_idx, last_idx;
 
+	/* wr_p == rd_p means ring was never fed FL bufs.  RX rings are always
+	 * kept at cnt - 1 FL bufs.
+	 */
+	if (rx_ring->wr_p == 0 && rx_ring->rd_p == 0)
+		return;
+
 	/* Move the empty entry to the end of the list */
 	wr_idx = D_IDX(rx_ring, rx_ring->wr_p);
 	last_idx = rx_ring->cnt - 1;
@@ -2508,6 +2513,8 @@ static void nfp_net_vec_clear_ring_data(struct nfp_net *nn, unsigned int idx)
 /**
  * nfp_net_clear_config_and_disable() - Clear control BAR and disable NFP
  * @nn:      NFP Net device to reconfigure
+ *
+ * Warning: must be fully idempotent.
  */
 static void nfp_net_clear_config_and_disable(struct nfp_net *nn)
 {
-- 
cgit v1.2.3


From 3dd0f18c70d94ca2432c78c5735744429f071b0b Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 11 Jul 2018 13:28:40 +0000
Subject: EVM: fix return value check in evm_write_xattrs()

In case of error, the function audit_log_start() returns NULL pointer
not ERR_PTR(). The IS_ERR() test in the return value check should be
replaced with NULL test.

Fixes: fa516b66a1bf ("EVM: Allow runtime modification of the set of verified xattrs")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 security/integrity/evm/evm_secfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/security/integrity/evm/evm_secfs.c b/security/integrity/evm/evm_secfs.c
index 637eb999e340..77de71b7794c 100644
--- a/security/integrity/evm/evm_secfs.c
+++ b/security/integrity/evm/evm_secfs.c
@@ -193,8 +193,8 @@ static ssize_t evm_write_xattrs(struct file *file, const char __user *buf,
 		return -E2BIG;
 
 	ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_INTEGRITY_EVM_XATTR);
-	if (IS_ERR(ab))
-		return PTR_ERR(ab);
+	if (!ab)
+		return -ENOMEM;
 
 	xattr = kmalloc(sizeof(struct xattr_list), GFP_KERNEL);
 	if (!xattr) {
-- 
cgit v1.2.3


From 8824f62246bef288173a6624a363352f0d4d3b09 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Sun, 22 Jul 2018 14:10:15 +0800
Subject: blk-mq: fail the request in case issue failure

Inside blk_mq_try_issue_list_directly(), if the request is issued as
failed, we shouldn't try to do it again, otherwise the warning in
blk_mq_start_request() will be triggered. This change is aligned to
behaviour of other ways of request issue & dispatch.

Fixes: 6ce3dd6eec1 ("blk-mq: issue directly if hw queue isn't busy in case of 'none'")
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: Laurence Oberman <loberman@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Hannes Reinecke <hare@suse.de>
Cc: Kashyap Desai <kashyap.desai@broadcom.com>
Cc: kernel test robot <rong.a.chen@intel.com>
Cc: LKP <lkp@01.org>
Reported-by: kernel test robot <rong.a.chen@intel.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 21f3eda98431..e13bdc2707ce 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1794,8 +1794,12 @@ void blk_mq_try_issue_list_directly(struct blk_mq_hw_ctx *hctx,
 		list_del_init(&rq->queuelist);
 		ret = blk_mq_request_issue_directly(rq);
 		if (ret != BLK_STS_OK) {
-			list_add(&rq->queuelist, list);
-			break;
+			if (ret == BLK_STS_RESOURCE ||
+					ret == BLK_STS_DEV_RESOURCE) {
+				list_add(&rq->queuelist, list);
+				break;
+			}
+			blk_mq_end_request(rq, ret);
 		}
 	}
 }
-- 
cgit v1.2.3


From 0a78c3803d1924845ded22a379b66f897ba647a3 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 23 Jul 2018 11:16:47 +0800
Subject: net: mediatek: use dma_zalloc_coherent instead of allocator/memset

Use dma_zalloc_coherent instead of dma_alloc_coherent
followed by memset 0.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index d8ebf0a05e0c..c30aea2ab767 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -1221,14 +1221,11 @@ static int mtk_tx_alloc(struct mtk_eth *eth)
 	if (!ring->buf)
 		goto no_tx_mem;
 
-	ring->dma = dma_alloc_coherent(eth->dev,
-					  MTK_DMA_SIZE * sz,
-					  &ring->phys,
-					  GFP_ATOMIC | __GFP_ZERO);
+	ring->dma = dma_zalloc_coherent(eth->dev, MTK_DMA_SIZE * sz,
+					&ring->phys, GFP_ATOMIC);
 	if (!ring->dma)
 		goto no_tx_mem;
 
-	memset(ring->dma, 0, MTK_DMA_SIZE * sz);
 	for (i = 0; i < MTK_DMA_SIZE; i++) {
 		int next = (i + 1) % MTK_DMA_SIZE;
 		u32 next_ptr = ring->phys + next * sz;
-- 
cgit v1.2.3


From dfef01e150824b0e6da750cacda8958188d29aea Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 19 Jul 2018 11:01:04 +0200
Subject: ALSA: memalloc: Don't exceed over the requested size

snd_dma_alloc_pages_fallback() tries to allocate pages again when the
allocation fails with reduced size.  But the first try actually
*increases* the size to power-of-two, which may give back a larger
chunk than the requested size.  This confuses the callers, e.g. sgbuf
assumes that the size is equal or less, and it may result in a bad
loop due to the underflow and eventually lead to Oops.

The code of this function seems incorrectly assuming the usage of
get_order().  We need to decrease at first, then align to
power-of-two.

Reported-and-tested-by: he, bo <bo.he@intel.com>
Reported-by: zhang jun <jun.zhang@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/memalloc.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/sound/core/memalloc.c b/sound/core/memalloc.c
index 7f89d3c79a4b..753d5fc4b284 100644
--- a/sound/core/memalloc.c
+++ b/sound/core/memalloc.c
@@ -242,16 +242,12 @@ int snd_dma_alloc_pages_fallback(int type, struct device *device, size_t size,
 	int err;
 
 	while ((err = snd_dma_alloc_pages(type, device, size, dmab)) < 0) {
-		size_t aligned_size;
 		if (err != -ENOMEM)
 			return err;
 		if (size <= PAGE_SIZE)
 			return -ENOMEM;
-		aligned_size = PAGE_SIZE << get_order(size);
-		if (size != aligned_size)
-			size = aligned_size;
-		else
-			size >>= 1;
+		size >>= 1;
+		size = PAGE_SIZE << get_order(size);
 	}
 	if (! dmab->area)
 		return -ENOMEM;
-- 
cgit v1.2.3


From 40c6f9c28ef03f2f2c3ee58c2447a6e6b9a713f2 Mon Sep 17 00:00:00 2001
From: Revanth Rajashekar <revanth.rajashekar@intel.com>
Date: Fri, 15 Jun 2018 12:39:27 -0600
Subject: nvme.h: resync with nvme-cli

Added some feature ids present in nvme-cli but not kernel.

Signed-off-by: Revanth Rajashekar <revanth.rajashekar@intel.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/nvme.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 2950ce957656..80dfedcf0bf7 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -749,6 +749,11 @@ enum {
 	NVME_FEAT_HOST_MEM_BUF	= 0x0d,
 	NVME_FEAT_TIMESTAMP	= 0x0e,
 	NVME_FEAT_KATO		= 0x0f,
+	NVME_FEAT_HCTM		= 0x10,
+	NVME_FEAT_NOPSC		= 0x11,
+	NVME_FEAT_RRL		= 0x12,
+	NVME_FEAT_PLM_CONFIG	= 0x13,
+	NVME_FEAT_PLM_WINDOW	= 0x14,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
-- 
cgit v1.2.3


From 230f1f9e04e2abee34b1478b3bcc2d947b7cc2a0 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 12 Jun 2018 16:28:24 -0700
Subject: nvme: move init of keep_alive work item to controller initialization

Currently, the code initializes the keep alive work item whenever
nvme_start_keep_alive() is called. However, this routine is called
several times while reconnecting, etc. Although it's hoped that keep
alive is always disabled and not scheduled when start is called,
re-initing if it were scheduled or completing can have very bad
side effects. There's no need for re-initialization.

Move the keep_alive work item and cmd struct initialization to
controller init.

Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 46df030b2c3f..e541fe268bcf 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -848,9 +848,6 @@ static void nvme_start_keep_alive(struct nvme_ctrl *ctrl)
 	if (unlikely(ctrl->kato == 0))
 		return;
 
-	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
-	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
-	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
 	schedule_delayed_work(&ctrl->ka_work, ctrl->kato * HZ);
 }
 
@@ -3484,6 +3481,10 @@ int nvme_init_ctrl(struct nvme_ctrl *ctrl, struct device *dev,
 	INIT_WORK(&ctrl->fw_act_work, nvme_fw_act_work);
 	INIT_WORK(&ctrl->delete_work, nvme_delete_ctrl_work);
 
+	INIT_DELAYED_WORK(&ctrl->ka_work, nvme_keep_alive_work);
+	memset(&ctrl->ka_cmd, 0, sizeof(ctrl->ka_cmd));
+	ctrl->ka_cmd.common.opcode = nvme_admin_keep_alive;
+
 	ret = ida_simple_get(&nvme_instance_ida, 0, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto out;
-- 
cgit v1.2.3


From 0866bf0c3778661e65f68a5c93df8e0a1e9e43cc Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Mon, 11 Jun 2018 13:40:07 -0400
Subject: nvmet: add commands supported and effects log page

This patch adds support for Commands Supported and Effects log page
(Log Identifier 05h) for NVMeOF. This also makes it easier to find
which commands are supported, e.g. :-

subnqn    : testnqn1
Admin Command Set
ACS2     [Get Log Page                    ] 00000001
ACS6     [Identify                        ] 00000001
ACS8     [Abort                           ] 00000001
ACS9     [Set Features                    ] 00000001
ACS10    [Get Features                    ] 00000001
ACS12    [Asynchronous Event Request      ] 00000001
ACS24    [Keep Alive                      ] 00000001

NVM Command Set
IOCS0    [Flush                           ] 00000001
IOCS1    [Write                           ] 00000001
IOCS2    [Read                            ] 00000001
IOCS8    [Write Zeroes                    ] 00000001
IOCS9    [Dataset Management              ] 00000001

This partticular functionality can be used from the host side to examine
the NVMeOF ctrl commands supported.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/admin-cmd.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 38803576d5e1..e2c6f8b39388 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -128,6 +128,36 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static void nvmet_execute_get_log_cmd_effects_ns(struct nvmet_req *req)
+{
+	u16 status = NVME_SC_INTERNAL;
+	struct nvme_effects_log *log;
+
+	log = kzalloc(sizeof(*log), GFP_KERNEL);
+	if (!log)
+		goto out;
+
+	log->acs[nvme_admin_get_log_page]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_identify]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_abort_cmd]		= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_set_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_get_features]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_async_event]	= cpu_to_le32(1 << 0);
+	log->acs[nvme_admin_keep_alive]		= cpu_to_le32(1 << 0);
+
+	log->iocs[nvme_cmd_read]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_flush]		= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_dsm]			= cpu_to_le32(1 << 0);
+	log->iocs[nvme_cmd_write_zeroes]	= cpu_to_le32(1 << 0);
+
+	status = nvmet_copy_to_sgl(req, 0, log, sizeof(*log));
+
+	kfree(log);
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -208,7 +238,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	/* first slot is read-only, only one slot supported */
 	id->frmw = (1 << 0) | (1 << 1);
-	id->lpa = (1 << 0) | (1 << 2);
+	id->lpa = (1 << 0) | (1 << 1) | (1 << 2);
 	id->elpe = NVMET_ERROR_LOG_SLOTS - 1;
 	id->npss = 0;
 
@@ -586,6 +616,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		case NVME_LOG_CHANGED_NS:
 			req->execute = nvmet_execute_get_log_changed_ns;
 			return 0;
+		case NVME_LOG_CMD_EFFECTS:
+			req->execute = nvmet_execute_get_log_cmd_effects_ns;
+			return 0;
 		}
 		break;
 	case nvme_admin_identify:
-- 
cgit v1.2.3


From 55eb942eda2ccbbbea61db4c1a774ba22b618046 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Wed, 20 Jun 2018 00:01:41 -0400
Subject: nvmet: add buffered I/O support for file backed ns

Add a new "buffered_io" attribute, which disabled direct I/O and thus
enables page cache based caching when enabled.   The attribute can only
be changed when the namespace is disabled as the file has to be reopend
for the change to take effect.

The possibly blocking read/write are deferred to a newly introduced
global workqueue.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/configfs.c    | 29 +++++++++++++++++++++++++++++
 drivers/nvme/target/core.c        |  9 +++++++++
 drivers/nvme/target/io-cmd-file.c | 31 ++++++++++++++++++++++++++-----
 drivers/nvme/target/nvmet.h       |  3 +++
 4 files changed, 67 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index d3f3b3ec4d1a..fee56b3a23bc 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -407,11 +407,40 @@ static ssize_t nvmet_ns_enable_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_ns_, enable);
 
+static ssize_t nvmet_ns_buffered_io_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%d\n", to_nvmet_ns(item)->buffered_io);
+}
+
+static ssize_t nvmet_ns_buffered_io_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	bool val;
+
+	if (strtobool(page, &val))
+		return -EINVAL;
+
+	mutex_lock(&ns->subsys->lock);
+	if (ns->enabled) {
+		pr_err("disable ns before setting buffered_io value.\n");
+		mutex_unlock(&ns->subsys->lock);
+		return -EINVAL;
+	}
+
+	ns->buffered_io = val;
+	mutex_unlock(&ns->subsys->lock);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, buffered_io);
+
 static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_device_path,
 	&nvmet_ns_attr_device_nguid,
 	&nvmet_ns_attr_device_uuid,
 	&nvmet_ns_attr_enable,
+	&nvmet_ns_attr_buffered_io,
 	NULL,
 };
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 74d4b785d2da..96eafbd419e7 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -18,6 +18,7 @@
 
 #include "nvmet.h"
 
+struct workqueue_struct *buffered_io_wq;
 static const struct nvmet_fabrics_ops *nvmet_transports[NVMF_TRTYPE_MAX];
 static DEFINE_IDA(cntlid_ida);
 
@@ -437,6 +438,7 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	ns->nsid = nsid;
 	ns->subsys = subsys;
 	uuid_gen(&ns->uuid);
+	ns->buffered_io = false;
 
 	return ns;
 }
@@ -1109,6 +1111,12 @@ static int __init nvmet_init(void)
 {
 	int error;
 
+	buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
+			WQ_MEM_RECLAIM, 0);
+	if (!buffered_io_wq) {
+		error = -ENOMEM;
+		goto out;
+	}
 	error = nvmet_init_discovery();
 	if (error)
 		goto out;
@@ -1129,6 +1137,7 @@ static void __exit nvmet_exit(void)
 	nvmet_exit_configfs();
 	nvmet_exit_discovery();
 	ida_destroy(&cntlid_ida);
+	destroy_workqueue(buffered_io_wq);
 
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_entry) != 1024);
 	BUILD_BUG_ON(sizeof(struct nvmf_disc_rsp_page_hdr) != 1024);
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 8c42b3a8c420..57c660e3245d 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -16,6 +16,8 @@
 void nvmet_file_ns_disable(struct nvmet_ns *ns)
 {
 	if (ns->file) {
+		if (ns->buffered_io)
+			flush_workqueue(buffered_io_wq);
 		mempool_destroy(ns->bvec_pool);
 		ns->bvec_pool = NULL;
 		kmem_cache_destroy(ns->bvec_cache);
@@ -27,11 +29,14 @@ void nvmet_file_ns_disable(struct nvmet_ns *ns)
 
 int nvmet_file_ns_enable(struct nvmet_ns *ns)
 {
-	int ret;
+	int flags = O_RDWR | O_LARGEFILE;
 	struct kstat stat;
+	int ret;
+
+	if (!ns->buffered_io)
+		flags |= O_DIRECT;
 
-	ns->file = filp_open(ns->device_path,
-			O_RDWR | O_LARGEFILE | O_DIRECT, 0);
+	ns->file = filp_open(ns->device_path, flags, 0);
 	if (IS_ERR(ns->file)) {
 		pr_err("failed to open file %s: (%ld)\n",
 				ns->device_path, PTR_ERR(ns->file));
@@ -100,7 +105,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos,
 
 	iocb->ki_pos = pos;
 	iocb->ki_filp = req->ns->file;
-	iocb->ki_flags = IOCB_DIRECT | ki_flags;
+	iocb->ki_flags = ki_flags | iocb_flags(req->ns->file);
 
 	ret = call_iter(iocb, &iter);
 
@@ -189,6 +194,19 @@ out:
 	nvmet_file_submit_bvec(req, pos, bv_cnt, total_len);
 }
 
+static void nvmet_file_buffered_io_work(struct work_struct *w)
+{
+	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
+
+	nvmet_file_execute_rw(req);
+}
+
+static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
+{
+	INIT_WORK(&req->f.work, nvmet_file_buffered_io_work);
+	queue_work(buffered_io_wq, &req->f.work);
+}
+
 static void nvmet_file_flush_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
@@ -280,7 +298,10 @@ u16 nvmet_file_parse_io_cmd(struct nvmet_req *req)
 	switch (cmd->common.opcode) {
 	case nvme_cmd_read:
 	case nvme_cmd_write:
-		req->execute = nvmet_file_execute_rw;
+		if (req->ns->buffered_io)
+			req->execute = nvmet_file_execute_rw_buffered_io;
+		else
+			req->execute = nvmet_file_execute_rw;
 		req->data_len = nvmet_rw_len(req);
 		return 0;
 	case nvme_cmd_flush:
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 480dfe10fad9..5efb98ec95df 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -65,6 +65,7 @@ struct nvmet_ns {
 	u8			nguid[16];
 	uuid_t			uuid;
 
+	bool			buffered_io;
 	bool			enabled;
 	struct nvmet_subsys	*subsys;
 	const char		*device_path;
@@ -269,6 +270,8 @@ struct nvmet_req {
 	const struct nvmet_fabrics_ops *ops;
 };
 
+extern struct workqueue_struct *buffered_io_wq;
+
 static inline void nvmet_set_status(struct nvmet_req *req, u16 status)
 {
 	req->rsp->status = cpu_to_le16(status << 1);
-- 
cgit v1.2.3


From 64a741c1eaa83e34a8846c7196feb8e45785bebc Mon Sep 17 00:00:00 2001
From: Steve Wise <swise@opengridcomputing.com>
Date: Wed, 20 Jun 2018 07:15:05 -0700
Subject: nvme-rdma: support up to 4 segments of inline data

Allow up to 4 segments of inline data for NVMF WRITE operations. This
reduces latency for small WRITEs by removing the need for the target to
issue a READ WR for IB, or a REG_MR + READ WR chain for iWarp.

Also cap the inline segments used based on the limitations of the
device.

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/rdma.c | 38 +++++++++++++++++++++++++++-----------
 1 file changed, 27 insertions(+), 11 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 518c5b09038c..363f73fe549c 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -40,13 +40,14 @@
 
 #define NVME_RDMA_MAX_SEGMENTS		256
 
-#define NVME_RDMA_MAX_INLINE_SEGMENTS	1
+#define NVME_RDMA_MAX_INLINE_SEGMENTS	4
 
 struct nvme_rdma_device {
 	struct ib_device	*dev;
 	struct ib_pd		*pd;
 	struct kref		ref;
 	struct list_head	entry;
+	unsigned int		num_inline_segments;
 };
 
 struct nvme_rdma_qe {
@@ -117,6 +118,7 @@ struct nvme_rdma_ctrl {
 	struct sockaddr_storage src_addr;
 
 	struct nvme_ctrl	ctrl;
+	bool			use_inline_data;
 };
 
 static inline struct nvme_rdma_ctrl *to_rdma_ctrl(struct nvme_ctrl *ctrl)
@@ -249,7 +251,7 @@ static int nvme_rdma_create_qp(struct nvme_rdma_queue *queue, const int factor)
 	/* +1 for drain */
 	init_attr.cap.max_recv_wr = queue->queue_size + 1;
 	init_attr.cap.max_recv_sge = 1;
-	init_attr.cap.max_send_sge = 1 + NVME_RDMA_MAX_INLINE_SEGMENTS;
+	init_attr.cap.max_send_sge = 1 + dev->num_inline_segments;
 	init_attr.sq_sig_type = IB_SIGNAL_REQ_WR;
 	init_attr.qp_type = IB_QPT_RC;
 	init_attr.send_cq = queue->ib_cq;
@@ -374,6 +376,8 @@ nvme_rdma_find_get_device(struct rdma_cm_id *cm_id)
 		goto out_free_pd;
 	}
 
+	ndev->num_inline_segments = min(NVME_RDMA_MAX_INLINE_SEGMENTS,
+					ndev->dev->attrs.max_sge - 1);
 	list_add(&ndev->entry, &device_list);
 out_unlock:
 	mutex_unlock(&device_list_mutex);
@@ -925,6 +929,9 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	if (ret)
 		goto requeue;
 
+	if (ctrl->ctrl.sgls & (1 << 20))
+		ctrl->use_inline_data = true;
+
 	if (ctrl->ctrl.queue_count > 1) {
 		ret = nvme_rdma_configure_io_queues(ctrl, false);
 		if (ret)
@@ -1090,19 +1097,27 @@ static int nvme_rdma_set_sg_null(struct nvme_command *c)
 }
 
 static int nvme_rdma_map_sg_inline(struct nvme_rdma_queue *queue,
-		struct nvme_rdma_request *req, struct nvme_command *c)
+		struct nvme_rdma_request *req, struct nvme_command *c,
+		int count)
 {
 	struct nvme_sgl_desc *sg = &c->common.dptr.sgl;
+	struct scatterlist *sgl = req->sg_table.sgl;
+	struct ib_sge *sge = &req->sge[1];
+	u32 len = 0;
+	int i;
 
-	req->sge[1].addr = sg_dma_address(req->sg_table.sgl);
-	req->sge[1].length = sg_dma_len(req->sg_table.sgl);
-	req->sge[1].lkey = queue->device->pd->local_dma_lkey;
+	for (i = 0; i < count; i++, sgl++, sge++) {
+		sge->addr = sg_dma_address(sgl);
+		sge->length = sg_dma_len(sgl);
+		sge->lkey = queue->device->pd->local_dma_lkey;
+		len += sge->length;
+	}
 
 	sg->addr = cpu_to_le64(queue->ctrl->ctrl.icdoff);
-	sg->length = cpu_to_le32(sg_dma_len(req->sg_table.sgl));
+	sg->length = cpu_to_le32(len);
 	sg->type = (NVME_SGL_FMT_DATA_DESC << 4) | NVME_SGL_FMT_OFFSET;
 
-	req->num_sge++;
+	req->num_sge += count;
 	return 0;
 }
 
@@ -1195,15 +1210,16 @@ static int nvme_rdma_map_data(struct nvme_rdma_queue *queue,
 		goto out_free_table;
 	}
 
-	if (count == 1) {
+	if (count <= dev->num_inline_segments) {
 		if (rq_data_dir(rq) == WRITE && nvme_rdma_queue_idx(queue) &&
+		    queue->ctrl->use_inline_data &&
 		    blk_rq_payload_bytes(rq) <=
 				nvme_rdma_inline_data_size(queue)) {
-			ret = nvme_rdma_map_sg_inline(queue, req, c);
+			ret = nvme_rdma_map_sg_inline(queue, req, c, count);
 			goto out;
 		}
 
-		if (dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
+		if (count == 1 && dev->pd->flags & IB_PD_UNSAFE_GLOBAL_RKEY) {
 			ret = nvme_rdma_map_sg_single(queue, req, c);
 			goto out;
 		}
-- 
cgit v1.2.3


From 0d5ee2b2ab4f6776c361bc975c2323bc8b5cf349 Mon Sep 17 00:00:00 2001
From: Steve Wise <swise@opengridcomputing.com>
Date: Wed, 20 Jun 2018 07:15:10 -0700
Subject: nvmet-rdma: support max(16KB, PAGE_SIZE) inline data

The patch enables inline data sizes using up to 4 recv sges, and capping
the size at 16KB or at least 1 page size.  So on a 4K page system, up to
16KB is supported, and for a 64K page system 1 page of 64KB is supported.

We avoid > 0 order page allocations for the inline buffers by using
multiple recv sges, one for each page.  If the device cannot support
the configured inline data size due to lack of enough recv sges, then
log a warning and reduce the inline size.

Add a new configfs port attribute, called param_inline_data_size,
to allow configuring the size of inline data for a given nvmf port.
The maximum size allowed is still enforced by nvmet-rdma with
NVMET_RDMA_MAX_INLINE_DATA_SIZE, which is now max(16KB, PAGE_SIZE).
And the default size, if not specified via configfs, is still PAGE_SIZE.
This preserves the existing behavior, but allows larger inline sizes
for small page systems.  If the configured inline data size exceeds
NVMET_RDMA_MAX_INLINE_DATA_SIZE, a warning is logged and the size is
reduced.  If param_inline_data_size is set to 0, then inline data is
disabled for that nvmf port.

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/admin-cmd.c |   4 +-
 drivers/nvme/target/configfs.c  |  31 ++++++++
 drivers/nvme/target/core.c      |   4 +
 drivers/nvme/target/discovery.c |   2 +-
 drivers/nvme/target/nvmet.h     |   2 +-
 drivers/nvme/target/rdma.c      | 169 ++++++++++++++++++++++++++++++----------
 6 files changed, 169 insertions(+), 43 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index e2c6f8b39388..837bbdbfaa4b 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -268,14 +268,14 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
 
 	/* Max command capsule size is sqe + single page of in-capsule data */
 	id->ioccsz = cpu_to_le32((sizeof(struct nvme_command) +
-				  ctrl->ops->sqe_inline_size) / 16);
+				  req->port->inline_data_size) / 16);
 	/* Max response capsule size is cqe */
 	id->iorcsz = cpu_to_le32(sizeof(struct nvme_completion) / 16);
 
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index fee56b3a23bc..3ba5ea5c4376 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -218,6 +218,35 @@ static ssize_t nvmet_addr_trsvcid_store(struct config_item *item,
 
 CONFIGFS_ATTR(nvmet_, addr_trsvcid);
 
+static ssize_t nvmet_param_inline_data_size_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+
+	return snprintf(page, PAGE_SIZE, "%d\n", port->inline_data_size);
+}
+
+static ssize_t nvmet_param_inline_data_size_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_port *port = to_nvmet_port(item);
+	int ret;
+
+	if (port->enabled) {
+		pr_err("Cannot modify inline_data_size while port enabled\n");
+		pr_err("Disable the port before modifying\n");
+		return -EACCES;
+	}
+	ret = kstrtoint(page, 0, &port->inline_data_size);
+	if (ret) {
+		pr_err("Invalid value '%s' for inline_data_size\n", page);
+		return -EINVAL;
+	}
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_, param_inline_data_size);
+
 static ssize_t nvmet_addr_trtype_show(struct config_item *item,
 		char *page)
 {
@@ -903,6 +932,7 @@ static struct configfs_attribute *nvmet_port_attrs[] = {
 	&nvmet_attr_addr_traddr,
 	&nvmet_attr_addr_trsvcid,
 	&nvmet_attr_addr_trtype,
+	&nvmet_attr_param_inline_data_size,
 	NULL,
 };
 
@@ -932,6 +962,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
+	port->inline_data_size = -1;	/* < 0 == let the transport choose */
 
 	port->disc_addr.portid = cpu_to_le16(portid);
 	config_group_init_type_name(&port->group, name, &nvmet_port_type);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 96eafbd419e7..ddd85715a00a 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -242,6 +242,10 @@ int nvmet_enable_port(struct nvmet_port *port)
 		return ret;
 	}
 
+	/* If the transport didn't set inline_data_size, then disable it. */
+	if (port->inline_data_size < 0)
+		port->inline_data_size = 0;
+
 	port->enabled = true;
 	return 0;
 }
diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
index 08656b849bd6..eae29f493a07 100644
--- a/drivers/nvme/target/discovery.c
+++ b/drivers/nvme/target/discovery.c
@@ -171,7 +171,7 @@ static void nvmet_execute_identify_disc_ctrl(struct nvmet_req *req)
 	id->sgls = cpu_to_le32(1 << 0);	/* we always support SGLs */
 	if (ctrl->ops->has_keyed_sgls)
 		id->sgls |= cpu_to_le32(1 << 2);
-	if (ctrl->ops->sqe_inline_size)
+	if (req->port->inline_data_size)
 		id->sgls |= cpu_to_le32(1 << 20);
 
 	strcpy(id->subnqn, ctrl->subsys->subsysnqn);
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 5efb98ec95df..688993855402 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -117,6 +117,7 @@ struct nvmet_port {
 	struct list_head		referrals;
 	void				*priv;
 	bool				enabled;
+	int				inline_data_size;
 };
 
 static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
@@ -226,7 +227,6 @@ struct nvmet_req;
 struct nvmet_fabrics_ops {
 	struct module *owner;
 	unsigned int type;
-	unsigned int sqe_inline_size;
 	unsigned int msdbd;
 	bool has_keyed_sgls : 1;
 	void (*queue_response)(struct nvmet_req *req);
diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 52e0c5d579a7..2106ae2ec177 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -33,16 +33,17 @@
 #include "nvmet.h"
 
 /*
- * We allow up to a page of inline data to go with the SQE
+ * We allow at least 1 page, up to 4 SGEs, and up to 16KB of inline data
  */
-#define NVMET_RDMA_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE	PAGE_SIZE
+#define NVMET_RDMA_MAX_INLINE_SGE		4
+#define NVMET_RDMA_MAX_INLINE_DATA_SIZE		max_t(int, SZ_16K, PAGE_SIZE)
 
 struct nvmet_rdma_cmd {
-	struct ib_sge		sge[2];
+	struct ib_sge		sge[NVMET_RDMA_MAX_INLINE_SGE + 1];
 	struct ib_cqe		cqe;
 	struct ib_recv_wr	wr;
-	struct scatterlist	inline_sg;
-	struct page		*inline_page;
+	struct scatterlist	inline_sg[NVMET_RDMA_MAX_INLINE_SGE];
 	struct nvme_command     *nvme_cmd;
 	struct nvmet_rdma_queue	*queue;
 };
@@ -116,6 +117,8 @@ struct nvmet_rdma_device {
 	size_t			srq_size;
 	struct kref		ref;
 	struct list_head	entry;
+	int			inline_data_size;
+	int			inline_page_count;
 };
 
 static bool nvmet_rdma_use_srq;
@@ -138,6 +141,11 @@ static void nvmet_rdma_queue_disconnect(struct nvmet_rdma_queue *queue);
 
 static const struct nvmet_fabrics_ops nvmet_rdma_ops;
 
+static int num_pages(int len)
+{
+	return 1 + (((len - 1) & PAGE_MASK) >> PAGE_SHIFT);
+}
+
 /* XXX: really should move to a generic header sooner or later.. */
 static inline u32 get_unaligned_le24(const u8 *p)
 {
@@ -184,6 +192,71 @@ nvmet_rdma_put_rsp(struct nvmet_rdma_rsp *rsp)
 	spin_unlock_irqrestore(&rsp->queue->rsps_lock, flags);
 }
 
+static void nvmet_rdma_free_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return;
+
+	sg = c->inline_sg;
+	sge = &c->sge[1];
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+}
+
+static int nvmet_rdma_alloc_inline_pages(struct nvmet_rdma_device *ndev,
+				struct nvmet_rdma_cmd *c)
+{
+	struct scatterlist *sg;
+	struct ib_sge *sge;
+	struct page *pg;
+	int len;
+	int i;
+
+	if (!ndev->inline_data_size)
+		return 0;
+
+	sg = c->inline_sg;
+	sg_init_table(sg, ndev->inline_page_count);
+	sge = &c->sge[1];
+	len = ndev->inline_data_size;
+
+	for (i = 0; i < ndev->inline_page_count; i++, sg++, sge++) {
+		pg = alloc_page(GFP_KERNEL);
+		if (!pg)
+			goto out_err;
+		sg_assign_page(sg, pg);
+		sge->addr = ib_dma_map_page(ndev->device,
+			pg, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+		if (ib_dma_mapping_error(ndev->device, sge->addr))
+			goto out_err;
+		sge->length = min_t(int, len, PAGE_SIZE);
+		sge->lkey = ndev->pd->local_dma_lkey;
+		len -= sge->length;
+	}
+
+	return 0;
+out_err:
+	for (; i >= 0; i--, sg--, sge--) {
+		if (sge->length)
+			ib_dma_unmap_page(ndev->device, sge->addr,
+					sge->length, DMA_FROM_DEVICE);
+		if (sg_page(sg))
+			__free_page(sg_page(sg));
+	}
+	return -ENOMEM;
+}
+
 static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 			struct nvmet_rdma_cmd *c, bool admin)
 {
@@ -200,33 +273,17 @@ static int nvmet_rdma_alloc_cmd(struct nvmet_rdma_device *ndev,
 	c->sge[0].length = sizeof(*c->nvme_cmd);
 	c->sge[0].lkey = ndev->pd->local_dma_lkey;
 
-	if (!admin) {
-		c->inline_page = alloc_pages(GFP_KERNEL,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-		if (!c->inline_page)
-			goto out_unmap_cmd;
-		c->sge[1].addr = ib_dma_map_page(ndev->device,
-				c->inline_page, 0, NVMET_RDMA_INLINE_DATA_SIZE,
-				DMA_FROM_DEVICE);
-		if (ib_dma_mapping_error(ndev->device, c->sge[1].addr))
-			goto out_free_inline_page;
-		c->sge[1].length = NVMET_RDMA_INLINE_DATA_SIZE;
-		c->sge[1].lkey = ndev->pd->local_dma_lkey;
-	}
+	if (!admin && nvmet_rdma_alloc_inline_pages(ndev, c))
+		goto out_unmap_cmd;
 
 	c->cqe.done = nvmet_rdma_recv_done;
 
 	c->wr.wr_cqe = &c->cqe;
 	c->wr.sg_list = c->sge;
-	c->wr.num_sge = admin ? 1 : 2;
+	c->wr.num_sge = admin ? 1 : ndev->inline_page_count + 1;
 
 	return 0;
 
-out_free_inline_page:
-	if (!admin) {
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
 out_unmap_cmd:
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 			sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
@@ -240,12 +297,8 @@ out:
 static void nvmet_rdma_free_cmd(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *c, bool admin)
 {
-	if (!admin) {
-		ib_dma_unmap_page(ndev->device, c->sge[1].addr,
-				NVMET_RDMA_INLINE_DATA_SIZE, DMA_FROM_DEVICE);
-		__free_pages(c->inline_page,
-				get_order(NVMET_RDMA_INLINE_DATA_SIZE));
-	}
+	if (!admin)
+		nvmet_rdma_free_inline_pages(ndev, c);
 	ib_dma_unmap_single(ndev->device, c->sge[0].addr,
 				sizeof(*c->nvme_cmd), DMA_FROM_DEVICE);
 	kfree(c->nvme_cmd);
@@ -429,7 +482,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp)
 				rsp->req.sg_cnt, nvmet_data_dir(&rsp->req));
 	}
 
-	if (rsp->req.sg != &rsp->cmd->inline_sg)
+	if (rsp->req.sg != rsp->cmd->inline_sg)
 		sgl_free(rsp->req.sg);
 
 	if (unlikely(!list_empty_careful(&queue->rsp_wr_wait_list)))
@@ -529,10 +582,25 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)
 static void nvmet_rdma_use_inline_sg(struct nvmet_rdma_rsp *rsp, u32 len,
 		u64 off)
 {
-	sg_init_table(&rsp->cmd->inline_sg, 1);
-	sg_set_page(&rsp->cmd->inline_sg, rsp->cmd->inline_page, len, off);
-	rsp->req.sg = &rsp->cmd->inline_sg;
-	rsp->req.sg_cnt = 1;
+	int sg_count = num_pages(len);
+	struct scatterlist *sg;
+	int i;
+
+	sg = rsp->cmd->inline_sg;
+	for (i = 0; i < sg_count; i++, sg++) {
+		if (i < sg_count - 1)
+			sg_unmark_end(sg);
+		else
+			sg_mark_end(sg);
+		sg->offset = off;
+		sg->length = min_t(int, len, PAGE_SIZE - off);
+		len -= sg->length;
+		if (!i)
+			off = 0;
+	}
+
+	rsp->req.sg = rsp->cmd->inline_sg;
+	rsp->req.sg_cnt = sg_count;
 }
 
 static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
@@ -544,7 +612,7 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
 	if (!nvme_is_write(rsp->req.cmd))
 		return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 
-	if (off + len > NVMET_RDMA_INLINE_DATA_SIZE) {
+	if (off + len > rsp->queue->dev->inline_data_size) {
 		pr_err("invalid inline data offset!\n");
 		return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
 	}
@@ -743,7 +811,7 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	srq_size = 4095;	/* XXX: tune */
 
 	srq_attr.attr.max_wr = srq_size;
-	srq_attr.attr.max_sge = 2;
+	srq_attr.attr.max_sge = 1 + ndev->inline_page_count;
 	srq_attr.attr.srq_limit = 0;
 	srq_attr.srq_type = IB_SRQT_BASIC;
 	srq = ib_create_srq(ndev->pd, &srq_attr);
@@ -793,7 +861,10 @@ static void nvmet_rdma_free_dev(struct kref *ref)
 static struct nvmet_rdma_device *
 nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 {
+	struct nvmet_port *port = cm_id->context;
 	struct nvmet_rdma_device *ndev;
+	int inline_page_count;
+	int inline_sge_count;
 	int ret;
 
 	mutex_lock(&device_list_mutex);
@@ -807,6 +878,18 @@ nvmet_rdma_find_get_device(struct rdma_cm_id *cm_id)
 	if (!ndev)
 		goto out_err;
 
+	inline_page_count = num_pages(port->inline_data_size);
+	inline_sge_count = max(cm_id->device->attrs.max_sge_rd,
+				cm_id->device->attrs.max_sge) - 1;
+	if (inline_page_count > inline_sge_count) {
+		pr_warn("inline_data_size %d cannot be supported by device %s. Reducing to %lu.\n",
+			port->inline_data_size, cm_id->device->name,
+			inline_sge_count * PAGE_SIZE);
+		port->inline_data_size = inline_sge_count * PAGE_SIZE;
+		inline_page_count = inline_sge_count;
+	}
+	ndev->inline_data_size = port->inline_data_size;
+	ndev->inline_page_count = inline_page_count;
 	ndev->device = cm_id->device;
 	kref_init(&ndev->ref);
 
@@ -881,7 +964,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	} else {
 		/* +1 for drain */
 		qp_attr.cap.max_recv_wr = 1 + queue->recv_queue_size;
-		qp_attr.cap.max_recv_sge = 2;
+		qp_attr.cap.max_recv_sge = 1 + ndev->inline_page_count;
 	}
 
 	ret = rdma_create_qp(queue->cm_id, ndev->pd, &qp_attr);
@@ -1379,6 +1462,15 @@ static int nvmet_rdma_add_port(struct nvmet_port *port)
 		return -EINVAL;
 	}
 
+	if (port->inline_data_size < 0) {
+		port->inline_data_size = NVMET_RDMA_DEFAULT_INLINE_DATA_SIZE;
+	} else if (port->inline_data_size > NVMET_RDMA_MAX_INLINE_DATA_SIZE) {
+		pr_warn("inline_data_size %u is too large, reducing to %u\n",
+			port->inline_data_size,
+			NVMET_RDMA_MAX_INLINE_DATA_SIZE);
+		port->inline_data_size = NVMET_RDMA_MAX_INLINE_DATA_SIZE;
+	}
+
 	ret = inet_pton_with_scope(&init_net, af, port->disc_addr.traddr,
 			port->disc_addr.trsvcid, &addr);
 	if (ret) {
@@ -1456,7 +1548,6 @@ static void nvmet_rdma_disc_port_addr(struct nvmet_req *req,
 static const struct nvmet_fabrics_ops nvmet_rdma_ops = {
 	.owner			= THIS_MODULE,
 	.type			= NVMF_TRTYPE_RDMA,
-	.sqe_inline_size	= NVMET_RDMA_INLINE_DATA_SIZE,
 	.msdbd			= 1,
 	.has_keyed_sgls		= 1,
 	.add_port		= nvmet_rdma_add_port,
-- 
cgit v1.2.3


From 2fc464e2162c2b2f7faf7404fa9c35d1cf70aa00 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Wed, 27 Jun 2018 14:58:02 +0300
Subject: nvmet-rdma: add unlikely check in the fast path

ib_post_send operation should succeed unless something unusual
happened to the ib device.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/rdma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 2106ae2ec177..4ca09456bbbb 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -546,7 +546,7 @@ static void nvmet_rdma_queue_response(struct nvmet_req *req)
 		rsp->send_sge.addr, rsp->send_sge.length,
 		DMA_TO_DEVICE);
 
-	if (ib_post_send(cm_id->qp, first_wr, &bad_wr)) {
+	if (unlikely(ib_post_send(cm_id->qp, first_wr, &bad_wr))) {
 		pr_err("sending cmd response failed\n");
 		nvmet_rdma_release_rsp(rsp);
 	}
-- 
cgit v1.2.3


From 202093848cac2da7d92ae666b51b7109bbab633c Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Sun, 1 Jul 2018 12:20:24 +0300
Subject: nvmet-rdma: add an error flow for post_recv failures

Posting receive buffer operation can fail, thus we should make
sure to have an error flow during initialization phase. While
we're here, add a debug print in case of a failure.

Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/rdma.c | 26 +++++++++++++++++++++-----
 1 file changed, 21 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 4ca09456bbbb..e7f43d1e1779 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -436,14 +436,21 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev,
 		struct nvmet_rdma_cmd *cmd)
 {
 	struct ib_recv_wr *bad_wr;
+	int ret;
 
 	ib_dma_sync_single_for_device(ndev->device,
 		cmd->sge[0].addr, cmd->sge[0].length,
 		DMA_FROM_DEVICE);
 
 	if (ndev->srq)
-		return ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
-	return ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
+		ret = ib_post_srq_recv(ndev->srq, &cmd->wr, &bad_wr);
+	else
+		ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, &bad_wr);
+
+	if (unlikely(ret))
+		pr_err("post_recv cmd failed\n");
+
+	return ret;
 }
 
 static void nvmet_rdma_process_wr_wait_list(struct nvmet_rdma_queue *queue)
@@ -833,11 +840,16 @@ static int nvmet_rdma_init_srq(struct nvmet_rdma_device *ndev)
 	ndev->srq = srq;
 	ndev->srq_size = srq_size;
 
-	for (i = 0; i < srq_size; i++)
-		nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+	for (i = 0; i < srq_size; i++) {
+		ret = nvmet_rdma_post_recv(ndev, &ndev->srq_cmds[i]);
+		if (ret)
+			goto out_free_cmds;
+	}
 
 	return 0;
 
+out_free_cmds:
+	nvmet_rdma_free_cmds(ndev, ndev->srq_cmds, ndev->srq_size, false);
 out_destroy_srq:
 	ib_destroy_srq(srq);
 	return ret;
@@ -982,13 +994,17 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)
 	if (!ndev->srq) {
 		for (i = 0; i < queue->recv_queue_size; i++) {
 			queue->cmds[i].queue = queue;
-			nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			ret = nvmet_rdma_post_recv(ndev, &queue->cmds[i]);
+			if (ret)
+				goto err_destroy_qp;
 		}
 	}
 
 out:
 	return ret;
 
+err_destroy_qp:
+	rdma_destroy_qp(queue->cm_id);
 err_destroy_cq:
 	ib_free_cq(queue->cq);
 	goto out;
-- 
cgit v1.2.3


From 59e29ce66bc52ebd6d0cb450f13079c7e913430d Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Fri, 29 Jun 2018 16:50:00 -0600
Subject: nvme: cache struct nvme_ctrl reference to struct nvme_request

We will need to reference the controller in the setup and completion
time for tracing and future traffic based keep alive support.

Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/fc.c     | 1 +
 drivers/nvme/host/nvme.h   | 1 +
 drivers/nvme/host/pci.c    | 2 ++
 drivers/nvme/host/rdma.c   | 1 +
 drivers/nvme/target/loop.c | 1 +
 5 files changed, 6 insertions(+)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index 41d45a1b5c62..9cc33752539a 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -1737,6 +1737,7 @@ nvme_fc_init_request(struct blk_mq_tag_set *set, struct request *rq,
 	int queue_idx = (set == &ctrl->tag_set) ? hctx_idx + 1 : 0;
 	struct nvme_fc_queue *queue = &ctrl->queues[queue_idx];
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	return __nvme_fc_init_request(ctrl, queue, op, rq, queue->rqcnt++);
 }
 
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 0c4a33df3b2f..f2249387b60d 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -102,6 +102,7 @@ struct nvme_request {
 	u8			retries;
 	u8			flags;
 	u16			status;
+	struct nvme_ctrl	*ctrl;
 };
 
 /*
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index ba943f211687..8dcae11bbf3a 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -418,6 +418,8 @@ static int nvme_init_request(struct blk_mq_tag_set *set, struct request *req,
 
 	BUG_ON(!nvmeq);
 	iod->nvmeq = nvmeq;
+
+	nvme_req(req)->ctrl = &dev->ctrl;
 	return 0;
 }
 
diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 363f73fe549c..bb6e26fa8331 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -288,6 +288,7 @@ static int nvme_rdma_init_request(struct blk_mq_tag_set *set,
 	struct ib_device *ibdev = dev->dev;
 	int ret;
 
+	nvme_req(rq)->ctrl = &ctrl->ctrl;
 	ret = nvme_rdma_alloc_qe(ibdev, &req->sqe, sizeof(struct nvme_command),
 			DMA_TO_DEVICE);
 	if (ret)
diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c
index d8d91f04bd7e..af7fbf4132b0 100644
--- a/drivers/nvme/target/loop.c
+++ b/drivers/nvme/target/loop.c
@@ -227,6 +227,7 @@ static int nvme_loop_init_request(struct blk_mq_tag_set *set,
 {
 	struct nvme_loop_ctrl *ctrl = set->driver_data;
 
+	nvme_req(req)->ctrl = &ctrl->ctrl;
 	return nvme_loop_init_iod(ctrl, blk_mq_rq_to_pdu(req),
 			(set == &ctrl->tag_set) ? hctx_idx + 1 : 0);
 }
-- 
cgit v1.2.3


From 5d87eb94d9ba13e5e2d5ceb56ac6fe0948259ffa Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 29 Jun 2018 16:50:01 -0600
Subject: nvme: use hw qid in trace events

We can not match a command to its completion based on the command
id alone. We need the submitting queue identifier to pair with the
completion, so this patch adds that to the trace buffer.

This patch is also collapsing the admin and IO submission traces into a
single one so we don't need to duplicate this and creating unnecessary
code branches: we know if the command is an admin vs IO based on the qid.

And since we're here, the patch fixes code formatting in the area.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
[hch: move the qid helper to nvme.h and made it an inline function]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c  |   5 +--
 drivers/nvme/host/nvme.h  |   7 +++
 drivers/nvme/host/trace.h | 112 +++++++++++++++++++---------------------------
 3 files changed, 53 insertions(+), 71 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e541fe268bcf..e77e6418a21c 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -652,10 +652,7 @@ blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 	}
 
 	cmd->common.command_id = req->tag;
-	if (ns)
-		trace_nvme_setup_nvm_cmd(req->q->id, cmd);
-	else
-		trace_nvme_setup_admin_cmd(cmd);
+	trace_nvme_setup_cmd(req, cmd);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nvme_setup_cmd);
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f2249387b60d..4ad0c8ad2a27 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -120,6 +120,13 @@ static inline struct nvme_request *nvme_req(struct request *req)
 	return blk_mq_rq_to_pdu(req);
 }
 
+static inline u16 nvme_req_qid(struct request *req)
+{
+	if (!req->rq_disk)
+		return 0;
+	return blk_mq_unique_tag_to_hwq(blk_mq_unique_tag(req)) + 1;
+}
+
 /* The below value is the specific amount of delay needed before checking
  * readiness in case of the PCI_DEVICE(0x1c58, 0x0003), which needs the
  * NVME_QUIRK_DELAY_BEFORE_CHK_RDY quirk enabled. The value (in ms) was
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 01390f0e1671..e6362677447d 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -50,13 +50,8 @@
 		nvme_admin_opcode_name(nvme_admin_security_recv),	\
 		nvme_admin_opcode_name(nvme_admin_sanitize_nvm))
 
-const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
-				       u8 *cdw10);
-#define __parse_nvme_admin_cmd(opcode, cdw10) \
-	nvme_trace_parse_admin_cmd(p, opcode, cdw10)
-
 #define nvme_opcode_name(opcode)	{ opcode, #opcode }
-#define show_opcode_name(val)					\
+#define show_nvm_opcode_name(val)				\
 	__print_symbolic(val,					\
 		nvme_opcode_name(nvme_cmd_flush),		\
 		nvme_opcode_name(nvme_cmd_write),		\
@@ -70,83 +65,66 @@ const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
 		nvme_opcode_name(nvme_cmd_resv_acquire),	\
 		nvme_opcode_name(nvme_cmd_resv_release))
 
-const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
-				     u8 *cdw10);
-#define __parse_nvme_cmd(opcode, cdw10) \
-	nvme_trace_parse_nvm_cmd(p, opcode, cdw10)
+#define show_opcode_name(qid, opcode)					\
+	(qid ? show_nvm_opcode_name(opcode) : show_admin_opcode_name(opcode))
 
-TRACE_EVENT(nvme_setup_admin_cmd,
-	    TP_PROTO(struct nvme_command *cmd),
-	    TP_ARGS(cmd),
-	    TP_STRUCT__entry(
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
-	    ),
-	    TP_fast_assign(
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
-	    ),
-	    TP_printk(" cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->cid, __entry->flags, __entry->metadata,
-		      show_admin_opcode_name(__entry->opcode),
-		      __parse_nvme_admin_cmd(__entry->opcode, __entry->cdw10))
-);
+const char *nvme_trace_parse_admin_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
+const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
+		u8 *cdw10);
 
+#define parse_nvme_cmd(qid, opcode, cdw10) 			\
+	(qid ?							\
+	 nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : 		\
+	 nvme_trace_parse_admin_cmd(p, opcode, cdw10))
 
-TRACE_EVENT(nvme_setup_nvm_cmd,
-	    TP_PROTO(int qid, struct nvme_command *cmd),
-	    TP_ARGS(qid, cmd),
+TRACE_EVENT(nvme_setup_cmd,
+	    TP_PROTO(struct request *req, struct nvme_command *cmd),
+	    TP_ARGS(req, cmd),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(u8, opcode)
-		    __field(u8, flags)
-		    __field(u16, cid)
-		    __field(u32, nsid)
-		    __field(u64, metadata)
-		    __array(u8, cdw10, 24)
+		__field(int, qid)
+		__field(u8, opcode)
+		__field(u8, flags)
+		__field(u16, cid)
+		__field(u32, nsid)
+		__field(u64, metadata)
+		__array(u8, cdw10, 24)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = qid;
-		    __entry->opcode = cmd->common.opcode;
-		    __entry->flags = cmd->common.flags;
-		    __entry->cid = cmd->common.command_id;
-		    __entry->nsid = le32_to_cpu(cmd->common.nsid);
-		    __entry->metadata = le64_to_cpu(cmd->common.metadata);
-		    memcpy(__entry->cdw10, cmd->common.cdw10,
-			   sizeof(__entry->cdw10));
+		__entry->qid = nvme_req_qid(req);
+		__entry->opcode = cmd->common.opcode;
+		__entry->flags = cmd->common.flags;
+		__entry->cid = cmd->common.command_id;
+		__entry->nsid = le32_to_cpu(cmd->common.nsid);
+		__entry->metadata = le64_to_cpu(cmd->common.metadata);
+		memcpy(__entry->cdw10, cmd->common.cdw10,
+		       sizeof(__entry->cdw10));
 	    ),
-	    TP_printk("qid=%d, nsid=%u, cmdid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->qid, __entry->nsid, __entry->cid,
+	    TP_printk("qid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+		      __entry->qid, __entry->cid, __entry->nsid,
 		      __entry->flags, __entry->metadata,
-		      show_opcode_name(__entry->opcode),
-		      __parse_nvme_cmd(__entry->opcode, __entry->cdw10))
+		      show_opcode_name(__entry->qid, __entry->opcode),
+		      parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->cdw10))
 );
 
 TRACE_EVENT(nvme_complete_rq,
 	    TP_PROTO(struct request *req),
 	    TP_ARGS(req),
 	    TP_STRUCT__entry(
-		    __field(int, qid)
-		    __field(int, cid)
-		    __field(u64, result)
-		    __field(u8, retries)
-		    __field(u8, flags)
-		    __field(u16, status)
+		__field(int, qid)
+		__field(int, cid)
+		__field(u64, result)
+		__field(u8, retries)
+		__field(u8, flags)
+		__field(u16, status)
 	    ),
 	    TP_fast_assign(
-		    __entry->qid = req->q->id;
-		    __entry->cid = req->tag;
-		    __entry->result = le64_to_cpu(nvme_req(req)->result.u64);
-		    __entry->retries = nvme_req(req)->retries;
-		    __entry->flags = nvme_req(req)->flags;
-		    __entry->status = nvme_req(req)->status;
+		__entry->qid = nvme_req_qid(req);
+		__entry->cid = req->tag;
+		__entry->result = le64_to_cpu(nvme_req(req)->result.u64);
+		__entry->retries = nvme_req(req)->retries;
+		__entry->flags = nvme_req(req)->flags;
+		__entry->status = nvme_req(req)->status;
 	    ),
 	    TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
 		      __entry->qid, __entry->cid, __entry->result,
-- 
cgit v1.2.3


From 1ea0358ecb848058b35b6da13d7f4c08610a73a8 Mon Sep 17 00:00:00 2001
From: Yue Wang <yuleopen@gmail.com>
Date: Mon, 23 Jul 2018 01:56:46 -0700
Subject: ALSA: usb-audio: Generic DSD detection for Thesycon-based
 implementations

Thesycon provides solutions to XMOS chips, and has its own device
vendor id.

In this patch, we use generic method to detect DSD capability of
Thesycon-based UAC2 implementations in order to support a wide range
of current and future devices.

The patch will enable the SNDRV_PCM_FMTBIT_DSD_U32_BE bit for the DAC
hence enable native DSD playback up to DSD512 format.

Signed-off-by: Yue Wang <yuleopen@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 02b6cc02767f..06ae3f5adf4b 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1443,6 +1443,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 	 */
 	switch (USB_ID_VENDOR(chip->usb_id)) {
 	case 0x20b1:  /* XMOS based devices */
+	case 0x152a:  /* Thesycon devices */
 	case 0x25ce:  /* Mytek devices */
 		if (fp->dsd_raw)
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
-- 
cgit v1.2.3


From 977d5ad39f3ea12ac0bd51d75020cea5ecdca235 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:11 +0300
Subject: ACPI: Convert ACPI reference args to generic fwnode reference args

Convert all users of struct acpi_reference_args to more generic
fwnode_reference_args. This will

 1) avoid an ACPI specific references to device nodes with integer
    arguments as well as

 2) allow making references to nodes other than device nodes in ACPI.

As a by-product, convert the fwnode interger arguments to u64. The
arguments were 64-bit integers on ACPI but the fwnode arguments were
just 32-bit.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c                           | 36 ++++++++---------------
 drivers/gpio/gpiolib-acpi.c                       | 11 ++++---
 drivers/infiniband/hw/hns/hns_roce_hw_v1.c        | 10 +++----
 drivers/media/v4l2-core/v4l2-fwnode.c             |  2 +-
 drivers/net/ethernet/apm/xgene/xgene_enet_hw.c    |  6 ++--
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c |  6 ++--
 drivers/net/ethernet/hisilicon/hns/hns_enet.c     |  8 +++--
 include/linux/acpi.h                              | 17 ++++-------
 include/linux/fwnode.h                            |  2 +-
 9 files changed, 43 insertions(+), 55 deletions(-)

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 5815356ea6ad..3fa40010fd67 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -579,7 +579,7 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
  */
 int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 	const char *propname, size_t index, size_t num_args,
-	struct acpi_reference_args *args)
+	struct fwnode_reference_args *args)
 {
 	const union acpi_object *element, *end;
 	const union acpi_object *obj;
@@ -607,7 +607,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		if (ret)
 			return ret == -ENODEV ? -EINVAL : ret;
 
-		args->adev = device;
+		args->fwnode = acpi_fwnode_handle(device);
 		args->nargs = 0;
 		return 0;
 	}
@@ -653,11 +653,11 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 					return -EINVAL;
 			}
 
-			if (nargs > MAX_ACPI_REFERENCE_ARGS)
+			if (nargs > NR_FWNODE_REFERENCE_ARGS)
 				return -EINVAL;
 
 			if (idx == index) {
-				args->adev = device;
+				args->fwnode = acpi_fwnode_handle(device);
 				args->nargs = nargs;
 				for (i = 0; i < nargs; i++)
 					args->args[i] = element[i].integer.value;
@@ -1089,7 +1089,7 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode,
 {
 	struct fwnode_handle *fwnode;
 	unsigned int port_nr, endpoint_nr;
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	int ret;
 
 	memset(&args, 0, sizeof(args));
@@ -1098,6 +1098,10 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode,
 	if (ret)
 		return ret;
 
+	/* Ensure this is a device node. */
+	if (!is_acpi_device_node(args.fwnode))
+		return -ENODEV;
+
 	/*
 	 * Always require two arguments with the reference: port and
 	 * endpoint indices.
@@ -1105,7 +1109,7 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode,
 	if (args.nargs != 2)
 		return -EPROTO;
 
-	fwnode = acpi_fwnode_handle(args.adev);
+	fwnode = args.fwnode;
 	port_nr = args.args[0];
 	endpoint_nr = args.args[1];
 
@@ -1209,24 +1213,8 @@ acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
 			       unsigned int args_count, unsigned int index,
 			       struct fwnode_reference_args *args)
 {
-	struct acpi_reference_args acpi_args;
-	unsigned int i;
-	int ret;
-
-	ret = __acpi_node_get_property_reference(fwnode, prop, index,
-						 args_count, &acpi_args);
-	if (ret < 0)
-		return ret;
-	if (!args)
-		return 0;
-
-	args->nargs = acpi_args.nargs;
-	args->fwnode = acpi_fwnode_handle(acpi_args.adev);
-
-	for (i = 0; i < NR_FWNODE_REFERENCE_ARGS; i++)
-		args->args[i] = i < acpi_args.nargs ? acpi_args.args[i] : 0;
-
-	return 0;
+	return __acpi_node_get_property_reference(fwnode, prop, index,
+						  args_count, args);
 }
 
 static struct fwnode_handle *
diff --git a/drivers/gpio/gpiolib-acpi.c b/drivers/gpio/gpiolib-acpi.c
index e2232cbcec8b..4e8fdae1cde4 100644
--- a/drivers/gpio/gpiolib-acpi.c
+++ b/drivers/gpio/gpiolib-acpi.c
@@ -353,7 +353,7 @@ EXPORT_SYMBOL_GPL(devm_acpi_dev_remove_driver_gpios);
 
 static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 				      const char *name, int index,
-				      struct acpi_reference_args *args,
+				      struct fwnode_reference_args *args,
 				      unsigned int *quirks)
 {
 	const struct acpi_gpio_mapping *gm;
@@ -365,7 +365,7 @@ static bool acpi_get_driver_gpio_data(struct acpi_device *adev,
 		if (!strcmp(name, gm->name) && gm->data && index < gm->size) {
 			const struct acpi_gpio_params *par = gm->data + index;
 
-			args->adev = adev;
+			args->fwnode = acpi_fwnode_handle(adev);
 			args->args[0] = par->crs_entry_index;
 			args->args[1] = par->line_index;
 			args->args[2] = par->active_low;
@@ -528,7 +528,7 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 				     const char *propname, int index,
 				     struct acpi_gpio_lookup *lookup)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	unsigned int quirks = 0;
 	int ret;
 
@@ -549,6 +549,8 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 	 * The property was found and resolved, so need to lookup the GPIO based
 	 * on returned args.
 	 */
+	if (!to_acpi_device_node(args.fwnode))
+		return -EINVAL;
 	if (args.nargs != 3)
 		return -EPROTO;
 
@@ -556,8 +558,9 @@ static int acpi_gpio_property_lookup(struct fwnode_handle *fwnode,
 	lookup->pin_index = args.args[1];
 	lookup->active_low = !!args.args[2];
 
-	lookup->info.adev = args.adev;
+	lookup->info.adev = to_acpi_device_node(args.fwnode);
 	lookup->info.quirks = quirks;
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
index 8013d69c5ac4..8444234ed092 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v1.c
@@ -1435,7 +1435,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
 		}
 		fwnode = &dsaf_node->fwnode;
 	} else if (is_acpi_device_node(dev->fwnode)) {
-		struct acpi_reference_args args;
+		struct fwnode_reference_args args;
 
 		ret = acpi_node_get_property_reference(dev->fwnode,
 						       "dsaf-handle", 0, &args);
@@ -1443,7 +1443,7 @@ static int hns_roce_v1_reset(struct hns_roce_dev *hr_dev, bool dereset)
 			dev_err(dev, "could not find dsaf-handle\n");
 			return ret;
 		}
-		fwnode = acpi_fwnode_handle(args.adev);
+		fwnode = args.fwnode;
 	} else {
 		dev_err(dev, "cannot read data from DT or ACPI\n");
 		return -ENXIO;
@@ -4835,16 +4835,14 @@ static int hns_roce_get_cfg(struct hns_roce_dev *hr_dev)
 				continue;
 			pdev = of_find_device_by_node(net_node);
 		} else if (is_acpi_device_node(dev->fwnode)) {
-			struct acpi_reference_args args;
-			struct fwnode_handle *fwnode;
+			struct fwnode_reference_args args;
 
 			ret = acpi_node_get_property_reference(dev->fwnode,
 							       "eth-handle",
 							       i, &args);
 			if (ret)
 				continue;
-			fwnode = acpi_fwnode_handle(args.adev);
-			pdev = hns_roce_find_pdev(fwnode);
+			pdev = hns_roce_find_pdev(args.fwnode);
 		} else {
 			dev_err(dev, "cannot read data from DT or ACPI\n");
 			return -ENXIO;
diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c
index 3f77aa318035..82595cebc0b8 100644
--- a/drivers/media/v4l2-core/v4l2-fwnode.c
+++ b/drivers/media/v4l2-core/v4l2-fwnode.c
@@ -739,7 +739,7 @@ static struct fwnode_handle *v4l2_fwnode_reference_get_int_prop(
 	const char * const *props, unsigned int nprops)
 {
 	struct fwnode_reference_args fwnode_args;
-	unsigned int *args = fwnode_args.args;
+	u64 *args = fwnode_args.args;
 	struct fwnode_handle *child;
 	int ret;
 
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
index 3188f553da35..078a04dc1182 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c
@@ -836,19 +836,19 @@ static void xgene_enet_adjust_link(struct net_device *ndev)
 #ifdef CONFIG_ACPI
 static struct acpi_device *acpi_phy_find_device(struct device *dev)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	struct fwnode_handle *fw_node;
 	int status;
 
 	fw_node = acpi_fwnode_handle(ACPI_COMPANION(dev));
 	status = acpi_node_get_property_reference(fw_node, "phy-handle", 0,
 						  &args);
-	if (ACPI_FAILURE(status)) {
+	if (ACPI_FAILURE(status) || !is_acpi_device_node(args.fwnode)) {
 		dev_dbg(dev, "No matching phy in ACPI table\n");
 		return NULL;
 	}
 
-	return args.adev;
+	return to_acpi_device_node(args.fwnode);
 }
 #endif
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 9dcc5765f11f..794516718d9d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -708,7 +708,7 @@ hns_mac_register_phydev(struct mii_bus *mdio, struct hns_mac_cb *mac_cb,
 
 static int hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 {
-	struct acpi_reference_args args;
+	struct fwnode_reference_args args;
 	struct platform_device *pdev;
 	struct mii_bus *mii_bus;
 	int rc;
@@ -722,13 +722,15 @@ static int hns_mac_register_phy(struct hns_mac_cb *mac_cb)
 			mac_cb->fw_port, "mdio-node", 0, &args);
 	if (rc)
 		return rc;
+	if (!is_acpi_device_node(args.fwnode))
+		return -EINVAL;
 
 	addr = hns_mac_phy_parse_addr(mac_cb->dev, mac_cb->fw_port);
 	if (addr < 0)
 		return addr;
 
 	/* dev address in adev */
-	pdev = hns_dsaf_find_platform_device(acpi_fwnode_handle(args.adev));
+	pdev = hns_dsaf_find_platform_device(args.fwnode);
 	if (!pdev) {
 		dev_err(mac_cb->dev, "mac%d mdio pdev is NULL\n",
 			mac_cb->mac_id);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index ef9ef703d13a..5608f807d7ba 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -2377,7 +2377,7 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 		}
 		priv->fwnode = &ae_node->fwnode;
 	} else if (is_acpi_node(dev->fwnode)) {
-		struct acpi_reference_args args;
+		struct fwnode_reference_args args;
 
 		if (acpi_dev_found(hns_enet_acpi_match[0].id))
 			priv->enet_ver = AE_VERSION_1;
@@ -2393,7 +2393,11 @@ static int hns_nic_dev_probe(struct platform_device *pdev)
 			dev_err(dev, "not find ae-handle\n");
 			goto out_read_prop_fail;
 		}
-		priv->fwnode = acpi_fwnode_handle(args.adev);
+		if (!is_acpi_device_node(args.fwnode)) {
+			ret = -EINVAL;
+			goto out_read_prop_fail;
+		}
+		priv->fwnode = args.fwnode;
 	} else {
 		dev_err(dev, "cannot read cfg data from OF or acpi\n");
 		return -ENXIO;
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index e54f40974eb0..11cf39719fd8 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1058,27 +1058,20 @@ static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
 
 /* Device properties */
 
-#define MAX_ACPI_REFERENCE_ARGS	8
-struct acpi_reference_args {
-	struct acpi_device *adev;
-	size_t nargs;
-	u64 args[MAX_ACPI_REFERENCE_ARGS];
-};
-
 #ifdef CONFIG_ACPI
 int acpi_dev_get_property(const struct acpi_device *adev, const char *name,
 			  acpi_object_type type, const union acpi_object **obj);
 int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				const char *name, size_t index, size_t num_args,
-				struct acpi_reference_args *args);
+				struct fwnode_reference_args *args);
 
 static inline int acpi_node_get_property_reference(
 				const struct fwnode_handle *fwnode,
 				const char *name, size_t index,
-				struct acpi_reference_args *args)
+				struct fwnode_reference_args *args)
 {
 	return __acpi_node_get_property_reference(fwnode, name, index,
-		MAX_ACPI_REFERENCE_ARGS, args);
+		NR_FWNODE_REFERENCE_ARGS, args);
 }
 
 int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname,
@@ -1169,7 +1162,7 @@ static inline int acpi_dev_get_property(struct acpi_device *adev,
 static inline int
 __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				const char *name, size_t index, size_t num_args,
-				struct acpi_reference_args *args)
+				struct fwnode_reference_args *args)
 {
 	return -ENXIO;
 }
@@ -1177,7 +1170,7 @@ __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 static inline int
 acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				 const char *name, size_t index,
-				 struct acpi_reference_args *args)
+				 struct fwnode_reference_args *args)
 {
 	return -ENXIO;
 }
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 4fe8f289b3f6..faebf0ca0686 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -45,7 +45,7 @@ struct fwnode_endpoint {
 struct fwnode_reference_args {
 	struct fwnode_handle *fwnode;
 	unsigned int nargs;
-	unsigned int args[NR_FWNODE_REFERENCE_ARGS];
+	u64 args[NR_FWNODE_REFERENCE_ARGS];
 };
 
 /**
-- 
cgit v1.2.3


From 4eb0c3bf5ee52ffc88500763d80ba01393879794 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:12 +0300
Subject: ACPI: property: Allow making references to non-device nodes

Implement references to non-device nodes using the first package
entry in the hierarchical data extension reference, the second one
being the name of the referred object.

The data node references are parsed just after the device arguments
before the integer arguments. If there are no strings after the
device arguments, the parsing works exactly as it used to be.

Referring to a data node called "node" under device DEV, with
integer arguments 0, 2 would thus look like:

	Package() { DEV, "node", 0, 2 }

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c | 51 ++++++++++++++++++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 18 deletions(-)

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 3fa40010fd67..5878d3678b38 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -542,6 +542,23 @@ static int acpi_data_get_property_array(const struct acpi_device_data *data,
 	return 0;
 }
 
+static struct fwnode_handle *
+acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
+				 const char *childname)
+{
+	struct fwnode_handle *child;
+
+	/*
+	 * Find first matching named child node of this fwnode.
+	 * For ACPI this will be a data only sub-node.
+	 */
+	fwnode_for_each_child_node(fwnode, child)
+		if (acpi_data_node_match(child, childname))
+			return child;
+
+	return NULL;
+}
+
 /**
  * __acpi_node_get_property_reference - returns handle to the referenced object
  * @fwnode: Firmware node to get the property from
@@ -633,6 +650,8 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 		u32 nargs, i;
 
 		if (element->type == ACPI_TYPE_LOCAL_REFERENCE) {
+			struct fwnode_handle *ref_fwnode;
+
 			ret = acpi_bus_get_device(element->reference.handle,
 						  &device);
 			if (ret)
@@ -641,6 +660,19 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 			nargs = 0;
 			element++;
 
+			/*
+			 * Find the referred data extension node under the
+			 * referred device node.
+			 */
+			for (ref_fwnode = acpi_fwnode_handle(device);
+			     element < end && element->type == ACPI_TYPE_STRING;
+			     element++) {
+				ref_fwnode = acpi_fwnode_get_named_child_node(
+					ref_fwnode, element->string.pointer);
+				if (!ref_fwnode)
+					return -EINVAL;
+			}
+
 			/* assume following integer elements are all args */
 			for (i = 0; element + i < end && i < num_args; i++) {
 				int type = element[i].type;
@@ -657,7 +689,7 @@ int __acpi_node_get_property_reference(const struct fwnode_handle *fwnode,
 				return -EINVAL;
 
 			if (idx == index) {
-				args->fwnode = acpi_fwnode_handle(device);
+				args->fwnode = ref_fwnode;
 				args->nargs = nargs;
 				for (i = 0; i < nargs; i++)
 					args->args[i] = element[i].integer.value;
@@ -1190,23 +1222,6 @@ acpi_fwnode_property_read_string_array(const struct fwnode_handle *fwnode,
 				   val, nval);
 }
 
-static struct fwnode_handle *
-acpi_fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
-				 const char *childname)
-{
-	struct fwnode_handle *child;
-
-	/*
-	 * Find first matching named child node of this fwnode.
-	 * For ACPI this will be a data only sub-node.
-	 */
-	fwnode_for_each_child_node(fwnode, child)
-		if (acpi_data_node_match(child, childname))
-			return child;
-
-	return NULL;
-}
-
 static int
 acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
 			       const char *prop, const char *nargs_prop,
-- 
cgit v1.2.3


From b10134a3643dced57976f9346764144203cfb302 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:13 +0300
Subject: ACPI: property: Document hierarchical data extension references

Add documentation on how to refer to hierarchical data nodes in a
generic way. This brings ACPI to feature parity with Device Tree in
terms of being able to refer to any node in the tree.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/acpi/dsd/data-node-references.txt | 69 +++++++++++++++++++++++++
 1 file changed, 69 insertions(+)
 create mode 100644 Documentation/acpi/dsd/data-node-references.txt

diff --git a/Documentation/acpi/dsd/data-node-references.txt b/Documentation/acpi/dsd/data-node-references.txt
new file mode 100644
index 000000000000..00c3b5fe1f2e
--- /dev/null
+++ b/Documentation/acpi/dsd/data-node-references.txt
@@ -0,0 +1,69 @@
+Copyright (C) 2018 Intel Corporation
+Author: Sakari Ailus <sakari.ailus@linux.intel.com>
+
+
+Referencing hierarchical data nodes
+-----------------------------------
+
+ACPI in general allows referring to device objects in the tree only.
+Hierarchical data extension nodes may not be referred to directly, hence this
+document defines a scheme to implement such references.
+
+A reference consist of the device object name followed by one or more
+hierarchical data extension [1] keys. Specifically, the hierarchical data
+extension node which is referred to by the key shall lie directly under the
+parent object i.e. either the device object or another hierarchical data
+extension node.
+
+Example
+-------
+
+	In the ASL snippet below, the "reference" _DSD property [2] contains a
+	device object reference to DEV0 and under that device object, a
+	hierarchical data extension key "node" referring to the NODE object and
+	lastly, a hierarchical data extension key "anothernode" referring to the
+	ANOD object which is also the final target of the reference.
+
+	Device (DEV0)
+	{
+	    Name (_DSD, Package () {
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "node", NODE },
+		}
+	    })
+	    Name (NODE, Package() {
+		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
+		Package () {
+		    Package () { "anothernode", ANOD },
+		}
+	    })
+	    Name (ANOD, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "random-property", 0 },
+		}
+	    })
+	}
+
+	Device (DEV1)
+	{
+	    Name (_DSD, Package () {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "reference", ^DEV0, "node", "anothernode" },
+		}
+	    })
+	}
+
+
+References
+----------
+
+[1] Hierarchical Data Extension UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
+    referenced 2018-07-17.
+
+[2] Device Properties UUID For _DSD.
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-device-properties-UUID.pdf>,
+    referenced 2016-10-04.
-- 
cgit v1.2.3


From 0ef7478639c5165a672f01b4024aacfffa951813 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:14 +0300
Subject: ACPI: property: Make the ACPI graph API private

The fwnode graph API is preferred over the ACPI graph API. Therefore
make the ACPI graph API private, and use it as a back-end for the
fwnode graph API only.

Unused functionality is removed while the functionality actually used
remains the same.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c | 83 ++++++++++---------------------------------------
 include/linux/acpi.h    |  8 -----
 2 files changed, 16 insertions(+), 75 deletions(-)

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 5878d3678b38..19bdada64435 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1033,10 +1033,10 @@ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode)
  * @prev: Previous endpoint node or %NULL to get the first
  *
  * Looks up next endpoint ACPI firmware node below a given @fwnode. Returns
- * %NULL if there is no next endpoint, ERR_PTR() in case of error. In case
- * of success the next endpoint is returned.
+ * %NULL if there is no next endpoint or in case of error. In case of success
+ * the next endpoint is returned.
  */
-struct fwnode_handle *acpi_graph_get_next_endpoint(
+static struct fwnode_handle *acpi_graph_get_next_endpoint(
 	const struct fwnode_handle *fwnode, struct fwnode_handle *prev)
 {
 	struct fwnode_handle *port = NULL;
@@ -1065,11 +1065,9 @@ struct fwnode_handle *acpi_graph_get_next_endpoint(
 			endpoint = fwnode_get_next_child_node(port, NULL);
 	}
 
-	if (endpoint) {
-		/* Endpoints must have "endpoint" property */
-		if (!fwnode_property_present(endpoint, "endpoint"))
-			return ERR_PTR(-EPROTO);
-	}
+	/* Endpoints must have "endpoint" property */
+	if (!fwnode_property_present(endpoint, "endpoint"))
+		return NULL;
 
 	return endpoint;
 }
@@ -1106,18 +1104,12 @@ static struct fwnode_handle *acpi_graph_get_child_prop_value(
 /**
  * acpi_graph_get_remote_enpoint - Parses and returns remote end of an endpoint
  * @fwnode: Endpoint firmware node pointing to a remote device
- * @parent: Firmware node of remote port parent is filled here if not %NULL
- * @port: Firmware node of remote port is filled here if not %NULL
  * @endpoint: Firmware node of remote endpoint is filled here if not %NULL
  *
- * Function parses remote end of ACPI firmware remote endpoint and fills in
- * fields requested by the caller. Returns %0 in case of success and
- * negative errno otherwise.
+ * Returns the remote endpoint corresponding to @__fwnode. NULL on error.
  */
-int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode,
-				   struct fwnode_handle **parent,
-				   struct fwnode_handle **port,
-				   struct fwnode_handle **endpoint)
+static struct fwnode_handle *
+acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode)
 {
 	struct fwnode_handle *fwnode;
 	unsigned int port_nr, endpoint_nr;
@@ -1128,47 +1120,27 @@ int acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode,
 	ret = acpi_node_get_property_reference(__fwnode, "remote-endpoint", 0,
 					       &args);
 	if (ret)
-		return ret;
+		return NULL;
 
 	/* Ensure this is a device node. */
 	if (!is_acpi_device_node(args.fwnode))
-		return -ENODEV;
+		return NULL;
 
 	/*
 	 * Always require two arguments with the reference: port and
 	 * endpoint indices.
 	 */
 	if (args.nargs != 2)
-		return -EPROTO;
+		return NULL;
 
 	fwnode = args.fwnode;
 	port_nr = args.args[0];
 	endpoint_nr = args.args[1];
 
-	if (parent)
-		*parent = fwnode;
-
-	if (!port && !endpoint)
-		return 0;
-
 	fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr);
-	if (!fwnode)
-		return -EPROTO;
-
-	if (port)
-		*port = fwnode;
-
-	if (!endpoint)
-		return 0;
-
-	fwnode = acpi_graph_get_child_prop_value(fwnode, "endpoint",
-						 endpoint_nr);
-	if (!fwnode)
-		return -EPROTO;
 
-	*endpoint = fwnode;
-
-	return 0;
+	return acpi_graph_get_child_prop_value(fwnode, "endpoint",
+					       endpoint_nr);
 }
 
 static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode)
@@ -1232,29 +1204,6 @@ acpi_fwnode_get_reference_args(const struct fwnode_handle *fwnode,
 						  args_count, args);
 }
 
-static struct fwnode_handle *
-acpi_fwnode_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
-				    struct fwnode_handle *prev)
-{
-	struct fwnode_handle *endpoint;
-
-	endpoint = acpi_graph_get_next_endpoint(fwnode, prev);
-	if (IS_ERR(endpoint))
-		return NULL;
-
-	return endpoint;
-}
-
-static struct fwnode_handle *
-acpi_fwnode_graph_get_remote_endpoint(const struct fwnode_handle *fwnode)
-{
-	struct fwnode_handle *endpoint = NULL;
-
-	acpi_graph_get_remote_endpoint(fwnode, NULL, NULL, &endpoint);
-
-	return endpoint;
-}
-
 static struct fwnode_handle *
 acpi_fwnode_get_parent(struct fwnode_handle *fwnode)
 {
@@ -1295,9 +1244,9 @@ acpi_fwnode_device_get_match_data(const struct fwnode_handle *fwnode,
 		.get_named_child_node = acpi_fwnode_get_named_child_node, \
 		.get_reference_args = acpi_fwnode_get_reference_args,	\
 		.graph_get_next_endpoint =				\
-			acpi_fwnode_graph_get_next_endpoint,		\
+			acpi_graph_get_next_endpoint,			\
 		.graph_get_remote_endpoint =				\
-			acpi_fwnode_graph_get_remote_endpoint,		\
+			acpi_graph_get_remote_endpoint,			\
 		.graph_get_port_parent = acpi_fwnode_get_parent,	\
 		.graph_parse_endpoint = acpi_fwnode_graph_parse_endpoint, \
 	};								\
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 11cf39719fd8..de8d3d3fa651 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1089,14 +1089,6 @@ struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode,
 					    struct fwnode_handle *child);
 struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode);
 
-struct fwnode_handle *
-acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
-			     struct fwnode_handle *prev);
-int acpi_graph_get_remote_endpoint(const struct fwnode_handle *fwnode,
-				   struct fwnode_handle **remote,
-				   struct fwnode_handle **port,
-				   struct fwnode_handle **endpoint);
-
 struct acpi_probe_entry;
 typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *,
 						 struct acpi_probe_entry *);
-- 
cgit v1.2.3


From 6561eb3d3a23c4d38ba428396b7a14e184804535 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:15 +0300
Subject: ACPI: property: Allow direct graph endpoint references

By using device and further data node references, allow direct references
to endpoints. These are of form

	Package() { \DEV, "portX", "endpointY" }

where X is the number of the port and Y is the number of the endpoint.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 19bdada64435..10af340eedd2 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1122,9 +1122,9 @@ acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode)
 	if (ret)
 		return NULL;
 
-	/* Ensure this is a device node. */
+	/* Direct endpoint reference? */
 	if (!is_acpi_device_node(args.fwnode))
-		return NULL;
+		return args.nargs ? NULL : args.fwnode;
 
 	/*
 	 * Always require two arguments with the reference: port and
-- 
cgit v1.2.3


From 18f1e58d1536f69d4e35f6eabaa07e57eb317314 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:16 +0300
Subject: ACPI: property: Use data node name and reg property for graphs

Instead of using the port and endpoint properties, rely on the names of
the port and endpoint nodes as well as the reg property, as on DT.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/property.c | 51 ++++++++++++++++++++++++++++++++++++++++---------
 1 file changed, 42 insertions(+), 9 deletions(-)

diff --git a/drivers/acpi/property.c b/drivers/acpi/property.c
index 10af340eedd2..693cf05b0cc4 100644
--- a/drivers/acpi/property.c
+++ b/drivers/acpi/property.c
@@ -1027,6 +1027,26 @@ struct fwnode_handle *acpi_node_get_parent(const struct fwnode_handle *fwnode)
 	return NULL;
 }
 
+/*
+ * Return true if the node is an ACPI graph node. Called on either ports
+ * or endpoints.
+ */
+static bool is_acpi_graph_node(struct fwnode_handle *fwnode,
+			       const char *str)
+{
+	unsigned int len = strlen(str);
+	const char *name;
+
+	if (!len || !is_acpi_data_node(fwnode))
+		return false;
+
+	name = to_acpi_data_node(fwnode)->name;
+
+	return (fwnode_property_present(fwnode, "reg") &&
+		!strncmp(name, str, len) && name[len] == '@') ||
+		fwnode_property_present(fwnode, str);
+}
+
 /**
  * acpi_graph_get_next_endpoint - Get next endpoint ACPI firmware node
  * @fwnode: Pointer to the parent firmware node
@@ -1045,8 +1065,14 @@ static struct fwnode_handle *acpi_graph_get_next_endpoint(
 	if (!prev) {
 		do {
 			port = fwnode_get_next_child_node(fwnode, port);
-			/* Ports must have port property */
-			if (fwnode_property_present(port, "port"))
+			/*
+			 * The names of the port nodes begin with "port@"
+			 * followed by the number of the port node and they also
+			 * have a "reg" property that also has the number of the
+			 * port node. For compatibility reasons a node is also
+			 * recognised as a port node from the "port" property.
+			 */
+			if (is_acpi_graph_node(port, "port"))
 				break;
 		} while (port);
 	} else {
@@ -1061,12 +1087,18 @@ static struct fwnode_handle *acpi_graph_get_next_endpoint(
 		port = fwnode_get_next_child_node(fwnode, port);
 		if (!port)
 			break;
-		if (fwnode_property_present(port, "port"))
+		if (is_acpi_graph_node(port, "port"))
 			endpoint = fwnode_get_next_child_node(port, NULL);
 	}
 
-	/* Endpoints must have "endpoint" property */
-	if (!fwnode_property_present(endpoint, "endpoint"))
+	/*
+	 * The names of the endpoint nodes begin with "endpoint@" followed by
+	 * the number of the endpoint node and they also have a "reg" property
+	 * that also has the number of the endpoint node. For compatibility
+	 * reasons a node is also recognised as an endpoint node from the
+	 * "endpoint" property.
+	 */
+	if (!is_acpi_graph_node(endpoint, "endpoint"))
 		return NULL;
 
 	return endpoint;
@@ -1139,8 +1171,7 @@ acpi_graph_get_remote_endpoint(const struct fwnode_handle *__fwnode)
 
 	fwnode = acpi_graph_get_child_prop_value(fwnode, "port", port_nr);
 
-	return acpi_graph_get_child_prop_value(fwnode, "endpoint",
-					       endpoint_nr);
+	return acpi_graph_get_child_prop_value(fwnode, "endpoint", endpoint_nr);
 }
 
 static bool acpi_fwnode_device_is_available(const struct fwnode_handle *fwnode)
@@ -1217,8 +1248,10 @@ static int acpi_fwnode_graph_parse_endpoint(const struct fwnode_handle *fwnode,
 
 	endpoint->local_fwnode = fwnode;
 
-	fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
-	fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
+	if (fwnode_property_read_u32(port_fwnode, "reg", &endpoint->port))
+		fwnode_property_read_u32(port_fwnode, "port", &endpoint->port);
+	if (fwnode_property_read_u32(fwnode, "reg", &endpoint->id))
+		fwnode_property_read_u32(fwnode, "endpoint", &endpoint->id);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 2285e6d9f68912c786cfc46f798be42ef9800ae8 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:17 +0300
Subject: ACPI: property: Document key numbering for hierarchical data
 extension refs

As part of the hierarchical data extension key naming, introduce numbering
scheme for the nodes that may be referred to using hierarchical data
extension references. This allows iterating over particular kind of nodes
recognised by the node name whilst allowing numbering the nodes, bringing
ACPI to feature parity with DT in this respect.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/acpi/dsd/data-node-references.txt | 31 ++++++++++++++++++++-----
 1 file changed, 25 insertions(+), 6 deletions(-)

diff --git a/Documentation/acpi/dsd/data-node-references.txt b/Documentation/acpi/dsd/data-node-references.txt
index 00c3b5fe1f2e..6e9a5f925edd 100644
--- a/Documentation/acpi/dsd/data-node-references.txt
+++ b/Documentation/acpi/dsd/data-node-references.txt
@@ -15,24 +15,43 @@ extension node which is referred to by the key shall lie directly under the
 parent object i.e. either the device object or another hierarchical data
 extension node.
 
+The keys in the hierarchical data nodes shall consist of the name of the node,
+"@" character and the number of the node in hexadecimal notation (without pre-
+or postfixes). The same ACPI object shall include the _DSD property extension
+with a property "reg" that shall have the same numerical value as the number of
+the node.
+
+In case a hierarchical data extensions node has no numerical value, then the
+"reg" property shall be omitted from the ACPI object's _DSD properties and the
+"@" character and the number shall be omitted from the hierarchical data
+extension key.
+
+
 Example
 -------
 
 	In the ASL snippet below, the "reference" _DSD property [2] contains a
 	device object reference to DEV0 and under that device object, a
-	hierarchical data extension key "node" referring to the NODE object and
-	lastly, a hierarchical data extension key "anothernode" referring to the
-	ANOD object which is also the final target of the reference.
+	hierarchical data extension key "node@1" referring to the NOD1 object
+	and lastly, a hierarchical data extension key "anothernode" referring to
+	the ANOD object which is also the final target node of the reference.
 
 	Device (DEV0)
 	{
 	    Name (_DSD, Package () {
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "node", NODE },
+		    Package () { "node@0", NOD0 },
+		    Package () { "node@1", NOD1 },
+		}
+	    })
+	    Name (NOD0, Package() {
+		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+		Package () {
+		    Package () { "random-property", 3 },
 		}
 	    })
-	    Name (NODE, Package() {
+	    Name (NOD1, Package() {
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
 		    Package () { "anothernode", ANOD },
@@ -51,7 +70,7 @@ Example
 	    Name (_DSD, Package () {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "reference", ^DEV0, "node", "anothernode" },
+		    Package () { "reference", ^DEV0, "node@1", "anothernode" },
 		}
 	    })
 	}
-- 
cgit v1.2.3


From e4702b2ca7b4aa81cc067c1b8e7aaa1350239fa2 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:18 +0300
Subject: ACPI: property: Update documentation for hierarchical data extension
 1.1

Hierarchical data extension 1.1 allows using references as the second
entries of the hierearchical data extension packages. Update the
references and the examples.

The quotes are left in documentation for clarity.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/acpi/dsd/graph.txt | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/acpi/dsd/graph.txt
index ac09e3138b79..591c47509c63 100644
--- a/Documentation/acpi/dsd/graph.txt
+++ b/Documentation/acpi/dsd/graph.txt
@@ -76,7 +76,7 @@ A simple example of this is show below:
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "port0", "PRT0" },
+		    Package () { "port0", PRT0 },
 		}
 	    })
 	    Name (PRT0, Package() {
@@ -86,7 +86,7 @@ A simple example of this is show below:
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "endpoint0", "EP00" },
+		    Package () { "endpoint0", EP00 },
 		}
 	    })
 	    Name (EP00, Package() {
@@ -106,7 +106,7 @@ A simple example of this is show below:
 	    Name (_DSD, Package () {
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "port4", "PRT4" },
+		    Package () { "port4", PRT4 },
 		}
 	    })
 
@@ -117,7 +117,7 @@ A simple example of this is show below:
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "endpoint0", "EP40" },
+		    Package () { "endpoint0", EP40 },
 		}
 	    })
 
@@ -151,7 +151,7 @@ References
     referenced 2016-10-04.
 
 [5] Hierarchical Data Extension UUID For _DSD.
-    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.pdf>,
+    <URL:http://www.uefi.org/sites/default/files/resources/_DSD-hierarchical-data-extension-UUID-v1.1.pdf>,
     referenced 2016-10-04.
 
 [6] Advanced Configuration and Power Interface Specification.
-- 
cgit v1.2.3


From e58b1c6a9422b97b30838e77b7d1d2bbed121e96 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:19 +0300
Subject: ACPI: property: graph: Fix graph documentation

Address a few issues in the ACPI _DSD properties graph documentation:

 - the extension for port nodes is a data extension (and not property
   extension),

 - clean up language in port hierarchical data extension definition,

 - add examples of port and endpoint packages,

 - port property value is the number of the "port" and not the number
   of the "port node",

 - remove word "individual" from endpoint data node description, it
   was redundant,

 - remove the extra "The" in the endpoint property description,

 - refer to hierarchical data extension keys and targets instead of
   first and second package list entries.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/acpi/dsd/graph.txt | 28 ++++++++++++++++------------
 1 file changed, 16 insertions(+), 12 deletions(-)

diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/acpi/dsd/graph.txt
index 591c47509c63..0b007fceda0e 100644
--- a/Documentation/acpi/dsd/graph.txt
+++ b/Documentation/acpi/dsd/graph.txt
@@ -36,20 +36,24 @@ The port and endpoint concepts are very similar to those in Devicetree
 [3]. A port represents an interface in a device, and an endpoint
 represents a connection to that interface.
 
-All port nodes are located under the device's "_DSD" node in the
-hierarchical data extension tree. The property extension related to
-each port node must contain the key "port" and an integer value which
-is the number of the port. The object it refers to should be called "PRTX",
-where "X" is the number of the port.
-
-Further on, endpoints are located under the individual port nodes. The
-first hierarchical data extension package list entry of the endpoint
-nodes must begin with "endpoint" and must be followed by the number
-of the endpoint. The object it refers to should be called "EPXY", where
-"X" is the number of the port and "Y" is the number of the endpoint.
+All port nodes are located under the device's "_DSD" node in the hierarchical
+data extension tree. The data extension related to each port node must begin
+with "port" and must be followed by the number of the port as its key. The
+target object it refers to should be called "PRTX", where "X" is the number of
+the port. An example of such a package would be:
+
+    Package() { "port4", PRT4 }
+
+Further on, endpoints are located under the port nodes. The hierarchical data
+extension key of the endpoint nodes must begin with "endpoint" and must be
+followed by the number of the endpoint. The object it refers to should be called
+"EPXY", where "X" is the number of the port and "Y" is the number of the
+endpoint. An example of such a package would be:
+
+    Package() { "endpoint0", EP40 }
 
 Each port node contains a property extension key "port", the value of
-which is the number of the port node. The each endpoint is similarly numbered
+which is the number of the port. Each endpoint is similarly numbered
 with a property extension key "endpoint". Port numbers must be unique within a
 device and endpoint numbers must be unique within a port.
 
-- 
cgit v1.2.3


From e49363e96fd2ee3fd5259fd2a6f9050cb4af82c8 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:20 +0300
Subject: ACPI: property: graph: Improve graph documentation for port/ep
 numbering

Document that if a port has a single endpoint only, its value shall be
zero. Similarly, if a device object only has a single port, its value
shlla be zero.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/acpi/dsd/graph.txt | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/acpi/dsd/graph.txt
index 0b007fceda0e..3131f457882b 100644
--- a/Documentation/acpi/dsd/graph.txt
+++ b/Documentation/acpi/dsd/graph.txt
@@ -55,7 +55,10 @@ endpoint. An example of such a package would be:
 Each port node contains a property extension key "port", the value of
 which is the number of the port. Each endpoint is similarly numbered
 with a property extension key "endpoint". Port numbers must be unique within a
-device and endpoint numbers must be unique within a port.
+device and endpoint numbers must be unique within a port. If a device object
+may only has a single port, then the number of that port shall be zero.
+Similarly, if a port may only have a single endpoint, the number of that
+endpoint shall be zero.
 
 The endpoint reference uses property extension with "remote-endpoint" property
 name followed by a reference in the same package. Such references consist of the
-- 
cgit v1.2.3


From a4138e7c12287268348cc2dcad414a62c515d77a Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 17 Jul 2018 17:19:21 +0300
Subject: ACPI: property: graph: Update graph documentation to use generic
 references

Instead of port and endpoint properties for representing ports and
endpoints, use the keys of the hierarchical data extension references
when referring to the port and endpoint nodes. Additionally, use "reg"
properties as in Device Tree to specify the number of the port or the
endpoint.

The keys of the port nodes begin with "port" and the keys of the endpoint
nodes begin with "endpoint", both followed by "@" character and the number
of the port or the endpoint.

These changes have the advantage that no ACPI specific properties need to
be added to refer to non-device nodes. Additionally, using the name of the
node instead of an integer property inside the node is easier to parse in
code and easier for humans to understand.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/acpi/dsd/data-node-references.txt |  1 +
 Documentation/acpi/dsd/graph.txt                | 65 +++++++++++++------------
 2 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/Documentation/acpi/dsd/data-node-references.txt b/Documentation/acpi/dsd/data-node-references.txt
index 6e9a5f925edd..c3871565c8cf 100644
--- a/Documentation/acpi/dsd/data-node-references.txt
+++ b/Documentation/acpi/dsd/data-node-references.txt
@@ -75,6 +75,7 @@ Example
 	    })
 	}
 
+Please also see a graph example in graph.txt .
 
 References
 ----------
diff --git a/Documentation/acpi/dsd/graph.txt b/Documentation/acpi/dsd/graph.txt
index 3131f457882b..b9ce910781dc 100644
--- a/Documentation/acpi/dsd/graph.txt
+++ b/Documentation/acpi/dsd/graph.txt
@@ -38,34 +38,39 @@ represents a connection to that interface.
 
 All port nodes are located under the device's "_DSD" node in the hierarchical
 data extension tree. The data extension related to each port node must begin
-with "port" and must be followed by the number of the port as its key. The
-target object it refers to should be called "PRTX", where "X" is the number of
-the port. An example of such a package would be:
+with "port" and must be followed by the "@" character and the number of the port
+as its key. The target object it refers to should be called "PRTX", where "X" is
+the number of the port. An example of such a package would be:
 
-    Package() { "port4", PRT4 }
+    Package() { "port@4", PRT4 }
 
-Further on, endpoints are located under the port nodes. The hierarchical data
-extension key of the endpoint nodes must begin with "endpoint" and must be
-followed by the number of the endpoint. The object it refers to should be called
-"EPXY", where "X" is the number of the port and "Y" is the number of the
-endpoint. An example of such a package would be:
+Further on, endpoints are located under the port nodes. The hierarchical
+data extension key of the endpoint nodes must begin with
+"endpoint" and must be followed by the "@" character and the number of the
+endpoint. The object it refers to should be called "EPXY", where "X" is the
+number of the port and "Y" is the number of the endpoint. An example of such a
+package would be:
 
-    Package() { "endpoint0", EP40 }
+    Package() { "endpoint@0", EP40 }
 
-Each port node contains a property extension key "port", the value of
-which is the number of the port. Each endpoint is similarly numbered
-with a property extension key "endpoint". Port numbers must be unique within a
-device and endpoint numbers must be unique within a port. If a device object
-may only has a single port, then the number of that port shall be zero.
-Similarly, if a port may only have a single endpoint, the number of that
-endpoint shall be zero.
+Each port node contains a property extension key "port", the value of which is
+the number of the port. Each endpoint is similarly numbered with a property
+extension key "reg", the value of which is the number of the endpoint. Port
+numbers must be unique within a device and endpoint numbers must be unique
+within a port. If a device object may only has a single port, then the number
+of that port shall be zero. Similarly, if a port may only have a single
+endpoint, the number of that endpoint shall be zero.
 
 The endpoint reference uses property extension with "remote-endpoint" property
 name followed by a reference in the same package. Such references consist of the
-the remote device reference, number of the port in the device and finally the
-number of the endpoint in that port. Individual references thus appear as:
+the remote device reference, the first package entry of the port data extension
+reference under the device and finally the first package entry of the endpoint
+data extension reference under the port. Individual references thus appear as:
 
-    Package() { device, port_number, endpoint_number }
+    Package() { device, "port@X", "endpoint@Y" }
+
+In the above example, "X" is the number of the port and "Y" is the number of the
+endpoint.
 
 The references to endpoints must be always done both ways, to the
 remote endpoint and back from the referred remote endpoint node.
@@ -83,24 +88,24 @@ A simple example of this is show below:
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "port0", PRT0 },
+		    Package () { "port@0", PRT0 },
 		}
 	    })
 	    Name (PRT0, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "port", 0 },
+		    Package () { "reg", 0 },
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "endpoint0", EP00 },
+		    Package () { "endpoint@0", EP00 },
 		}
 	    })
 	    Name (EP00, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "endpoint", 0 },
-		    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, 4, 0 } },
+		    Package () { "reg", 0 },
+		    Package () { "remote-endpoint", Package() { \_SB.PCI0.ISP, "port@4", "endpoint@0" } },
 		}
 	    })
 	}
@@ -113,26 +118,26 @@ A simple example of this is show below:
 	    Name (_DSD, Package () {
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "port4", PRT4 },
+		    Package () { "port@4", PRT4 },
 		}
 	    })
 
 	    Name (PRT4, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "port", 4 }, /* CSI-2 port number */
+		    Package () { "reg", 4 }, /* CSI-2 port number */
 		},
 		ToUUID("dbb8e3e6-5886-4ba6-8795-1319f52a966b"),
 		Package () {
-		    Package () { "endpoint0", EP40 },
+		    Package () { "endpoint@0", EP40 },
 		}
 	    })
 
 	    Name (EP40, Package() {
 		ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
 		Package () {
-		    Package () { "endpoint", 0 },
-		    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, 0, 0 } },
+		    Package () { "reg", 0 },
+		    Package () { "remote-endpoint", Package () { \_SB.PCI0.I2C2.CAM0, "port@0", "endpoint@0" } },
 		}
 	    })
 	}
-- 
cgit v1.2.3


From 661c959bae317bf3c61e438ffffec92fc9ad38e2 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 3 Jul 2018 09:41:12 +0200
Subject: s390 cio: Rewrite trace point in s390_cio_interrupt

Tools like 'perf stat' parse the trace point format files defined
in /sys/kernel/debug/tracing/events/s390/.../format to handle
the print fmt: statement. The kernel provides a library in
directory linux/tools/lib/traceevent/* for this reason.

This library can not handle structures or unions defined in
the TRACE_EVENT/TP_STRUCT__entry macros with __field_struct macro.
There is no possibility to extract a structure member
(which might be a bit field) since there is no packing
information nor bit field offset by parsing the printf fmt line.

Therefore rewrite the TRACE_EVENT macro and add the
__field macro for the necessary fields.
Keep the __fieldstruct macro to extract the complete
structure when dumps are analysed.

Note that the same information is displayed, this is no
interface change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Acked-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/trace.h | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index 1f8d1c1e566d..ab0144c8a7d3 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -299,16 +299,20 @@ TRACE_EVENT(s390_cio_interrupt,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
-		__entry->cssid = __entry->tpi_info.schid.cssid;
-		__entry->ssid = __entry->tpi_info.schid.ssid;
-		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->cssid = tpi_info->schid.cssid;
+		__entry->ssid = tpi_info->schid.ssid;
+		__entry->schno = tpi_info->schid.sch_no;
+		__entry->isc = tpi_info->isc;
+		__entry->type = tpi_info->type;
 	),
 	TP_printk("schid=%x.%x.%04x isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno,
-		  __entry->tpi_info.isc, __entry->tpi_info.type
+		  __entry->isc, __entry->type
 	)
 );
 
-- 
cgit v1.2.3


From 5925e819274260bb48e10a2fc6d22b996d1e135f Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 3 Jul 2018 10:15:10 +0200
Subject: s390 cio: Rewrite trace point in s390_cio_tpi

Tools like 'perf stat' parse the trace point format files defined
in /sys/kernel/debug/tracing/events/s390/.../format to handle
the print fmt: statement. The kernel provides a library in
directory linux/tools/lib/traceevent/* for this reason.

This library can not handle structures or unions defined in
the TRACE_EVENT/TP_STRUCT__entry macros with __field_struct macro.
There is no possibility to extract a structure member
(which might be a bit field) since there is no packing
information nor bit field offset by parsing the printf fmt line.

Therefore rewrite the TRACE_EVENT macro and add the
__field macro for the members adapter_IO, isc and type
of struct tpi_info.

Note that the same information is displayed, this is no
interface change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Acked-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/trace.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index ab0144c8a7d3..5c06b680471e 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -122,6 +122,9 @@ TRACE_EVENT(s390_cio_tpi,
 		__field(u8, cssid)
 		__field(u8, ssid)
 		__field(u16, schno)
+		__field(u8, adapter_IO)
+		__field(u8, isc)
+		__field(u8, type)
 	),
 	TP_fast_assign(
 		__entry->cc = cc;
@@ -136,11 +139,14 @@ TRACE_EVENT(s390_cio_tpi,
 		__entry->cssid = __entry->tpi_info.schid.cssid;
 		__entry->ssid = __entry->tpi_info.schid.ssid;
 		__entry->schno = __entry->tpi_info.schid.sch_no;
+		__entry->adapter_IO = __entry->tpi_info.adapter_IO;
+		__entry->isc = __entry->tpi_info.isc;
+		__entry->type = __entry->tpi_info.type;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d a=%d isc=%d type=%d",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->tpi_info.adapter_IO, __entry->tpi_info.isc,
-		  __entry->tpi_info.type
+		  __entry->adapter_IO, __entry->isc,
+		  __entry->type
 	)
 );
 
-- 
cgit v1.2.3


From 67faae15675aac8327b094677a830fdffb7dd68d Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Wed, 11 Jul 2018 10:27:12 +0200
Subject: s390 cio: Rewrite trace point in s390_cio_stcrw

Tools like 'perf stat' parse the trace point format files defined
in /sys/kernel/debug/tracing/events/s390/.../format to handle
the print fmt: statement. The kernel provides a library in
directory linux/tools/lib/traceevent/* for this reason.

This library can not handle structures or unions defined in
the TRACE_EVENT/TP_STRUCT__entry macros with __field_struct macro.
There is no possibility to extract a structure member
(which might be a bit field) since there is no packing
information nor bit field offset by parsing the printf fmt line.

Therefore rewrite the TRACE_EVENT macro and add the
the __field macro for the missing members.
Keep the __fieldstruct macro to extract the complete
structure when dumps are analysed.

Note that the same information is displayed, this is no
interface change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Acked-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/trace.h | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index 5c06b680471e..baff0303533e 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -349,16 +349,30 @@ TRACE_EVENT(s390_cio_stcrw,
 	TP_STRUCT__entry(
 		__field_struct(struct crw, crw)
 		__field(int, cc)
+		__field(u8, slct)
+		__field(u8, oflw)
+		__field(u8, chn)
+		__field(u8, rsc)
+		__field(u8, anc)
+		__field(u8, erc)
+		__field(u16, rsid)
 	),
 	TP_fast_assign(
 		__entry->crw = *crw;
 		__entry->cc = cc;
+		__entry->slct = crw->slct;
+		__entry->oflw = crw->oflw;
+		__entry->chn = crw->chn;
+		__entry->rsc = crw->rsc;
+		__entry->anc = crw->anc;
+		__entry->erc = crw->erc;
+		__entry->rsid = crw->rsid;
 	),
 	TP_printk("cc=%d slct=%d oflw=%d chn=%d rsc=%d anc=%d erc=0x%x "
 		  "rsid=0x%x",
-		  __entry->cc, __entry->crw.slct, __entry->crw.oflw,
-		  __entry->crw.chn, __entry->crw.rsc,  __entry->crw.anc,
-		  __entry->crw.erc, __entry->crw.rsid
+		  __entry->cc, __entry->slct, __entry->oflw,
+		  __entry->chn, __entry->rsc,  __entry->anc,
+		  __entry->erc, __entry->rsid
 	)
 );
 
-- 
cgit v1.2.3


From 27c0620ce94798688a425cb04db0e7f568e44d52 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 3 Jul 2018 10:38:16 +0200
Subject: s390 cio: Rewrite trace point in s390_cio_adapter_int

Tools like 'perf stat' parse the trace point format files defined
in /sys/kernel/debug/tracing/events/s390/.../format to handle
the print fmt: statement. The kernel provides a library in
directory linux/tools/lib/traceevent/* for this reason.

This library can not handle structures or unions defined in
the TRACE_EVENT/TP_STRUCT__entry macros with __field_struct macro.
There is no possibility to extract a structure member
(which might be a bit field) since there is no packing
information nor bit field offset by parsing the printf fmt line.

Therefore rewrite the TRACE_EVENT macro and add the
__field macro for the necessary members.
Keep the __fieldstruct macro to extract the complete
structure when dumps are analysed.

Note that the same information is displayed, this is no
interface change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Acked-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/trace.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index baff0303533e..4337317f64fd 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -331,11 +331,13 @@ TRACE_EVENT(s390_cio_adapter_int,
 	TP_ARGS(tpi_info),
 	TP_STRUCT__entry(
 		__field_struct(struct tpi_info, tpi_info)
+		__field(u8, isc)
 	),
 	TP_fast_assign(
 		__entry->tpi_info = *tpi_info;
+		__entry->isc = tpi_info->isc;
 	),
-	TP_printk("isc=%d", __entry->tpi_info.isc)
+	TP_printk("isc=%d", __entry->isc)
 );
 
 /**
-- 
cgit v1.2.3


From 933df441e771bb8b39e1d90f868bfbdae2ed2b40 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 9 Jul 2018 10:30:34 +0200
Subject: s390 cio: Rewrite trace point in s390_cio_tsch

Tools like 'perf stat' parse the trace point format files defined
in /sys/kernel/debug/tracing/events/s390/.../format to handle
the print fmt: statement. The kernel provides a library in
directory linux/tools/lib/traceevent/* for this reason.

This library can not handle structures or unions defined in
the TRACE_EVENT/TP_STRUCT__entry macros with __field_struct macro.
There is no possibility to extract a structure member
(which might be a bit field) since there is no packing
information nor bit field offset by parsing the printf fmt line.

Therefore rewrite the TRACE_EVENT macro and add the
__field macro for the necessary members.
Keep the __fieldstruct macro to extract the complete
structure when dumps are analysed.

Note that the same information is displayed, this is no
interface change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Acked-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/trace.h | 22 ++++++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index 4337317f64fd..137410da1e9f 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -89,6 +89,13 @@ TRACE_EVENT(s390_cio_tsch,
 		__field(u8, ssid)
 		__field(u16, schno)
 		__field_struct(struct irb, irb)
+		__field(u8, scsw_dcc)
+		__field(u8, scsw_pno)
+		__field(u8, scsw_fctl)
+		__field(u8, scsw_actl)
+		__field(u8, scsw_stctl)
+		__field(u8, scsw_dstat)
+		__field(u8, scsw_cstat)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -96,15 +103,22 @@ TRACE_EVENT(s390_cio_tsch,
 		__entry->ssid = schid.ssid;
 		__entry->schno = schid.sch_no;
 		__entry->irb = *irb;
+		__entry->scsw_dcc = scsw_cc(&irb->scsw);
+		__entry->scsw_pno = scsw_pno(&irb->scsw);
+		__entry->scsw_fctl = scsw_fctl(&irb->scsw);
+		__entry->scsw_actl = scsw_actl(&irb->scsw);
+		__entry->scsw_stctl = scsw_stctl(&irb->scsw);
+		__entry->scsw_dstat = scsw_dstat(&irb->scsw);
+		__entry->scsw_cstat = scsw_cstat(&irb->scsw);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d dcc=%d pno=%d fctl=0x%x actl=0x%x "
 		  "stctl=0x%x dstat=0x%x cstat=0x%x",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  scsw_cc(&__entry->irb.scsw), scsw_pno(&__entry->irb.scsw),
-		  scsw_fctl(&__entry->irb.scsw), scsw_actl(&__entry->irb.scsw),
-		  scsw_stctl(&__entry->irb.scsw),
-		  scsw_dstat(&__entry->irb.scsw), scsw_cstat(&__entry->irb.scsw)
+		  __entry->scsw_dcc, __entry->scsw_pno,
+		  __entry->scsw_fctl, __entry->scsw_actl,
+		  __entry->scsw_stctl,
+		  __entry->scsw_dstat, __entry->scsw_cstat
 	)
 );
 
-- 
cgit v1.2.3


From d1de8633d96ac48d59e91775a17b828760bebc62 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 3 Jul 2018 11:21:06 +0200
Subject: s390 cio: Rewrite trace point class s390_class_schib

Tools like 'perf stat' parse the trace point format files defined
in /sys/kernel/debug/tracing/events/s390/.../format to handle
the print fmt: statement. The kernel provides a library in
directory linux/tools/lib/traceevent/* for this reason.

This library can not handle structures or unions defined in
the TRACE_EVENT/TP_STRUCT__entry macros with __field_struct macro.
There is no possibility to extract a structure member
(which might be a bit field) since there is no packing
information nor bit field offset by parsing the printf fmt line.

Therefore rewrite the TRACE_EVENT macro and add the
__field macro for the necessary members.
Keep the __fieldstruct macro to extract the complete
structure when dumps are analysed.

Note that the same information is displayed, this is no
interface change.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Acked-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/cio/trace.h | 34 ++++++++++++++++++++++++++++------
 1 file changed, 28 insertions(+), 6 deletions(-)

diff --git a/drivers/s390/cio/trace.h b/drivers/s390/cio/trace.h
index 137410da1e9f..0ebb29b6fd6d 100644
--- a/drivers/s390/cio/trace.h
+++ b/drivers/s390/cio/trace.h
@@ -30,6 +30,17 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__field(u16, schno)
 		__field(u16, devno)
 		__field_struct(struct schib, schib)
+		__field(u8, pmcw_ena)
+		__field(u8, pmcw_st)
+		__field(u8, pmcw_dnv)
+		__field(u16, pmcw_dev)
+		__field(u8, pmcw_lpm)
+		__field(u8, pmcw_pnom)
+		__field(u8, pmcw_lpum)
+		__field(u8, pmcw_pim)
+		__field(u8, pmcw_pam)
+		__field(u8, pmcw_pom)
+		__field(u64, pmcw_chpid)
 		__field(int, cc)
 	),
 	TP_fast_assign(
@@ -38,18 +49,29 @@ DECLARE_EVENT_CLASS(s390_class_schib,
 		__entry->schno = schid.sch_no;
 		__entry->devno = schib->pmcw.dev;
 		__entry->schib = *schib;
+		__entry->pmcw_ena = schib->pmcw.ena;
+		__entry->pmcw_st = schib->pmcw.ena;
+		__entry->pmcw_dnv = schib->pmcw.dnv;
+		__entry->pmcw_dev = schib->pmcw.dev;
+		__entry->pmcw_lpm = schib->pmcw.lpm;
+		__entry->pmcw_pnom = schib->pmcw.pnom;
+		__entry->pmcw_lpum = schib->pmcw.lpum;
+		__entry->pmcw_pim = schib->pmcw.pim;
+		__entry->pmcw_pam = schib->pmcw.pam;
+		__entry->pmcw_pom = schib->pmcw.pom;
+		memcpy(&__entry->pmcw_chpid, &schib->pmcw.chpid, 8);
 		__entry->cc = cc;
 	),
 	TP_printk("schid=%x.%x.%04x cc=%d ena=%d st=%d dnv=%d dev=%04x "
 		  "lpm=0x%02x pnom=0x%02x lpum=0x%02x pim=0x%02x pam=0x%02x "
 		  "pom=0x%02x chpids=%016llx",
 		  __entry->cssid, __entry->ssid, __entry->schno, __entry->cc,
-		  __entry->schib.pmcw.ena, __entry->schib.pmcw.st,
-		  __entry->schib.pmcw.dnv, __entry->schib.pmcw.dev,
-		  __entry->schib.pmcw.lpm, __entry->schib.pmcw.pnom,
-		  __entry->schib.pmcw.lpum, __entry->schib.pmcw.pim,
-		  __entry->schib.pmcw.pam, __entry->schib.pmcw.pom,
-		  *((u64 *) __entry->schib.pmcw.chpid)
+		  __entry->pmcw_ena, __entry->pmcw_st,
+		  __entry->pmcw_dnv, __entry->pmcw_dev,
+		  __entry->pmcw_lpm, __entry->pmcw_pnom,
+		  __entry->pmcw_lpum, __entry->pmcw_pim,
+		  __entry->pmcw_pam, __entry->pmcw_pom,
+		  __entry->pmcw_chpid
 	)
 );
 
-- 
cgit v1.2.3


From ef4b891f7924aca43147928532ea729f290ca38e Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Sun, 22 Jul 2018 19:11:09 +0530
Subject: s390: vdso_fault return type

Use new return type vm_fault_t for fault handler vdso_fault.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/vdso.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c
index 09abae40f917..3031cc6dd0ab 100644
--- a/arch/s390/kernel/vdso.c
+++ b/arch/s390/kernel/vdso.c
@@ -47,7 +47,7 @@ static struct page **vdso64_pagelist;
  */
 unsigned int __read_mostly vdso_enabled = 1;
 
-static int vdso_fault(const struct vm_special_mapping *sm,
+static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page **vdso_pagelist;
-- 
cgit v1.2.3


From cf85d89562f39cc7ae73de54639f1915a9195b7a Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Fri, 25 May 2018 17:34:36 +1000
Subject: m68k/mac: Enable PDMA for PowerBook 500 series

I can confirm that mac_scsi PDMA now works on these machines.
This increases sequential read throughput by a factor of 4.5.

Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/include/asm/macintosh.h |  1 -
 arch/m68k/mac/config.c            | 19 +------------------
 2 files changed, 1 insertion(+), 19 deletions(-)

diff --git a/arch/m68k/include/asm/macintosh.h b/arch/m68k/include/asm/macintosh.h
index 9b840c03ebb7..08cee11180e6 100644
--- a/arch/m68k/include/asm/macintosh.h
+++ b/arch/m68k/include/asm/macintosh.h
@@ -57,7 +57,6 @@ struct mac_model
 #define MAC_SCSI_IIFX		5
 #define MAC_SCSI_DUO		6
 #define MAC_SCSI_LC		7
-#define MAC_SCSI_LATE		8
 
 #define MAC_IDE_NONE		0
 #define MAC_IDE_QUADRA		1
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index e522307db47c..d468a9d467a0 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -709,7 +709,7 @@ static struct mac_model mac_data_table[] = {
 		.name		= "PowerBook 520",
 		.adb_type	= MAC_ADB_PB2,
 		.via_type	= MAC_VIA_QUADRA,
-		.scsi_type	= MAC_SCSI_LATE,
+		.scsi_type	= MAC_SCSI_OLD,
 		.scc_type	= MAC_SCC_QUADRA,
 		.ether_type	= MAC_ETHER_SONIC,
 		.floppy_type	= MAC_FLOPPY_SWIM_ADDR2,
@@ -943,18 +943,6 @@ static const struct resource mac_scsi_old_rsrc[] __initconst = {
 	},
 };
 
-static const struct resource mac_scsi_late_rsrc[] __initconst = {
-	{
-		.flags = IORESOURCE_IRQ,
-		.start = IRQ_MAC_SCSI,
-		.end   = IRQ_MAC_SCSI,
-	}, {
-		.flags = IORESOURCE_MEM,
-		.start = 0x50010000,
-		.end   = 0x50011FFF,
-	},
-};
-
 static const struct resource mac_scsi_ccl_rsrc[] __initconst = {
 	{
 		.flags = IORESOURCE_IRQ,
@@ -1064,11 +1052,6 @@ int __init mac_platform_init(void)
 		platform_device_register_simple("mac_scsi", 0,
 			mac_scsi_old_rsrc, ARRAY_SIZE(mac_scsi_old_rsrc));
 		break;
-	case MAC_SCSI_LATE:
-		/* XXX PDMA support for PowerBook 500 series needs testing */
-		platform_device_register_simple("mac_scsi", 0,
-			mac_scsi_late_rsrc, ARRAY_SIZE(mac_scsi_late_rsrc));
-		break;
 	case MAC_SCSI_LC:
 		/* Addresses from Mac LC data in Designing Cards & Drivers 3ed.
 		 * Also from the Developer Notes for Classic II, LC III,
-- 
cgit v1.2.3


From a8c5cb994341d4af6d75286fcb66684e53295135 Mon Sep 17 00:00:00 2001
From: Finn Thain <fthain@telegraphics.com.au>
Date: Mon, 25 Jun 2018 21:46:11 +1000
Subject: nubus: Set default dma mask for nubus_board devices

A 32-bit mask is used by default because a NuBus slot has 32
address/data lines and a NuBus board is free to use all of them.

Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 drivers/nubus/bus.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/nubus/bus.c b/drivers/nubus/bus.c
index a59b6c4bb5b8..ad3d17c42e23 100644
--- a/drivers/nubus/bus.c
+++ b/drivers/nubus/bus.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2017 Finn Thain
 
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <linux/list.h>
 #include <linux/nubus.h>
 #include <linux/seq_file.h>
@@ -93,6 +94,8 @@ int nubus_device_register(struct nubus_board *board)
 	board->dev.release = nubus_device_release;
 	board->dev.bus = &nubus_bus_type;
 	dev_set_name(&board->dev, "slot.%X", board->slot);
+	board->dev.dma_mask = &board->dev.coherent_dma_mask;
+	dma_set_mask(&board->dev, DMA_BIT_MASK(32));
 	return device_register(&board->dev);
 }
 
-- 
cgit v1.2.3


From 9eb8be602bf8d550a33b4e1f9fac543bd5c89f4d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 20 Jun 2018 10:19:45 +0200
Subject: m68k: Use generic dma_noncoherent_ops

Switch to the generic noncoherent direct mapping implementation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Greg Ungerer <gerg@linux-m68k.org>
Tested-by: Greg Ungerer <gerg@linux-m68k.org>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/Kconfig                   |  2 ++
 arch/m68k/include/asm/Kbuild        |  1 +
 arch/m68k/include/asm/dma-mapping.h | 12 -------
 arch/m68k/kernel/dma.c              | 68 +++++--------------------------------
 4 files changed, 11 insertions(+), 72 deletions(-)
 delete mode 100644 arch/m68k/include/asm/dma-mapping.h

diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 785612b576f7..3f61327da2d5 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -2,6 +2,7 @@
 config M68K
 	bool
 	default y
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE if HAS_DMA
 	select ARCH_MIGHT_HAVE_PC_PARPORT if ISA
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
 	select HAVE_IDE
@@ -24,6 +25,7 @@ config M68K
 	select MODULES_USE_ELF_RELA
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
+	select DMA_NONCOHERENT_OPS if HAS_DMA
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index 4d8d68c4e3dd..a4b8d3331a9e 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -1,6 +1,7 @@
 generic-y += barrier.h
 generic-y += compat.h
 generic-y += device.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h
deleted file mode 100644
index e3722ed04fbb..000000000000
--- a/arch/m68k/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _M68K_DMA_MAPPING_H
-#define _M68K_DMA_MAPPING_H
-
-extern const struct dma_map_ops m68k_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-        return &m68k_dma_ops;
-}
-
-#endif  /* _M68K_DMA_MAPPING_H */
diff --git a/arch/m68k/kernel/dma.c b/arch/m68k/kernel/dma.c
index 463572c4943f..e99993c57d6b 100644
--- a/arch/m68k/kernel/dma.c
+++ b/arch/m68k/kernel/dma.c
@@ -6,7 +6,7 @@
 
 #undef DEBUG
 
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/device.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
@@ -19,7 +19,7 @@
 
 #if defined(CONFIG_MMU) && !defined(CONFIG_COLDFIRE)
 
-static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 		gfp_t flag, unsigned long attrs)
 {
 	struct page *page, **map;
@@ -62,7 +62,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
 	return addr;
 }
 
-static void m68k_dma_free(struct device *dev, size_t size, void *addr,
+void arch_dma_free(struct device *dev, size_t size, void *addr,
 		dma_addr_t handle, unsigned long attrs)
 {
 	pr_debug("dma_free_coherent: %p, %x\n", addr, handle);
@@ -73,8 +73,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *addr,
 
 #include <asm/cacheflush.h>
 
-static void *m68k_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
 
@@ -89,7 +89,7 @@ static void *m68k_dma_alloc(struct device *dev, size_t size,
 	return ret;
 }
 
-static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
@@ -97,8 +97,8 @@ static void m68k_dma_free(struct device *dev, size_t size, void *vaddr,
 
 #endif /* CONFIG_MMU && !CONFIG_COLDFIRE */
 
-static void m68k_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t handle, size_t size, enum dma_data_direction dir)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t handle,
+		size_t size, enum dma_data_direction dir)
 {
 	switch (dir) {
 	case DMA_BIDIRECTIONAL:
@@ -115,58 +115,6 @@ static void m68k_dma_sync_single_for_device(struct device *dev,
 	}
 }
 
-static void m68k_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sglist, int nents, enum dma_data_direction dir)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
-					   dir);
-	}
-}
-
-static dma_addr_t m68k_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size, enum dma_data_direction dir,
-		unsigned long attrs)
-{
-	dma_addr_t handle = page_to_phys(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		dma_sync_single_for_device(dev, handle, size, dir);
-
-	return handle;
-}
-
-static int m68k_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	for_each_sg(sglist, sg, nents, i) {
-		sg->dma_address = sg_phys(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		dma_sync_single_for_device(dev, sg->dma_address, sg->length,
-					   dir);
-	}
-	return nents;
-}
-
-const struct dma_map_ops m68k_dma_ops = {
-	.alloc			= m68k_dma_alloc,
-	.free			= m68k_dma_free,
-	.map_page		= m68k_dma_map_page,
-	.map_sg			= m68k_dma_map_sg,
-	.sync_single_for_device	= m68k_dma_sync_single_for_device,
-	.sync_sg_for_device	= m68k_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(m68k_dma_ops);
-
 void arch_setup_pdev_archdata(struct platform_device *pdev)
 {
 	if (pdev->dev.coherent_dma_mask == DMA_MASK_NONE &&
-- 
cgit v1.2.3


From 14d6e289a89780377f8bb09de8926d3c62d763cd Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 10 Jul 2018 19:01:22 +0100
Subject: arm64: fix possible spectre-v1 write in ptrace_hbp_set_event()

It's possible for userspace to control idx. Sanitize idx when using it
as an array index, to inhibit the potential spectre-v1 write gadget.

Found by smatch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/ptrace.c | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 379b2b714193..299758f9b9c4 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -277,19 +277,22 @@ static int ptrace_hbp_set_event(unsigned int note_type,
 
 	switch (note_type) {
 	case NT_ARM_HW_BREAK:
-		if (idx < ARM_MAX_BRP) {
-			tsk->thread.debug.hbp_break[idx] = bp;
-			err = 0;
-		}
+		if (idx >= ARM_MAX_BRP)
+			goto out;
+		idx = array_index_nospec(idx, ARM_MAX_BRP);
+		tsk->thread.debug.hbp_break[idx] = bp;
+		err = 0;
 		break;
 	case NT_ARM_HW_WATCH:
-		if (idx < ARM_MAX_WRP) {
-			tsk->thread.debug.hbp_watch[idx] = bp;
-			err = 0;
-		}
+		if (idx >= ARM_MAX_WRP)
+			goto out;
+		idx = array_index_nospec(idx, ARM_MAX_WRP);
+		tsk->thread.debug.hbp_watch[idx] = bp;
+		err = 0;
 		break;
 	}
 
+out:
 	return err;
 }
 
-- 
cgit v1.2.3


From c931d34ea0853d41349e93f871bd3f17f1c03a6b Mon Sep 17 00:00:00 2001
From: Olof Johansson <olof@lixom.net>
Date: Fri, 13 Jul 2018 08:30:33 -0700
Subject: arm64: build with baremetal linker target instead of Linux when
 available

Not all toolchains have the baremetal elf targets, RedHat/Fedora ones
in particular. So, probe for whether it's available and use the previous
(linux) targets if it isn't.

Reported-by: Laura Abbott <labbott@redhat.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Cc: Paul Kocialkowski <contact@paulk.fr>
Signed-off-by: Olof Johansson <olof@lixom.net>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Makefile    | 9 +++++----
 scripts/Kbuild.include | 4 ++--
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 45272266dafb..99a1d859b8b8 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -60,15 +60,16 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 CHECKFLAGS	+= -D__AARCH64EB__
 AS		+= -EB
-LD		+= -EB
-LDFLAGS		+= -maarch64linuxb
+# Prefer the baremetal ELF build target, but not all toolchains include
+# it so fall back to the standard linux version if needed.
+LDFLAGS		+= -EB $(call ld-option, -maarch64elfb, -maarch64linuxb)
 UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 CHECKFLAGS	+= -D__AARCH64EL__
 AS		+= -EL
-LD		+= -EL
-LDFLAGS		+= -maarch64linux
+# Same as above, prefer ELF but fall back to linux target if needed.
+LDFLAGS		+= -EL $(call ld-option, -maarch64elf, -maarch64linux)
 UTS_MACHINE	:= aarch64
 endif
 
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index c8156d61678c..1e13f502b42f 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -163,8 +163,8 @@ cc-ldoption = $(call try-run,\
 	$(CC) $(1) $(KBUILD_CPPFLAGS) $(CC_OPTION_CFLAGS) -nostdlib -x c /dev/null -o "$$TMP",$(1),$(2))
 
 # ld-option
-# Usage: LDFLAGS += $(call ld-option, -X)
-ld-option = $(call try-run, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2))
+# Usage: LDFLAGS += $(call ld-option, -X, -Y)
+ld-option = $(call try-run, $(LD) $(LDFLAGS) $(1) -v,$(1),$(2),$(3))
 
 # ar-option
 # Usage: KBUILD_ARFLAGS := $(call ar-option,D)
-- 
cgit v1.2.3


From 50d7ba36b916d0fd4687149ec143bf49c326523f Mon Sep 17 00:00:00 2001
From: James Morse <james.morse@arm.com>
Date: Mon, 23 Jul 2018 10:57:28 +0900
Subject: arm64: export memblock_reserve()d regions via /proc/iomem

There has been some confusion around what is necessary to prevent kexec
overwriting important memory regions. memblock: reserve, or nomap?
Only memblock nomap regions are reported via /proc/iomem, kexec's
user-space doesn't know about memblock_reserve()d regions.

Until commit f56ab9a5b73ca ("efi/arm: Don't mark ACPI reclaim memory
as MEMBLOCK_NOMAP") the ACPI tables were nomap, now they are reserved
and thus possible for kexec to overwrite with the new kernel or initrd.
But this was always broken, as the UEFI memory map is also reserved
and not marked as nomap.

Exporting both nomap and reserved memblock types is a nuisance as
they live in different memblock structures which we can't walk at
the same time.

Take a second walk over memblock.reserved and add new 'reserved'
subnodes for the memblock_reserved() regions that aren't already
described by the existing code. (e.g. Kernel Code)

We use reserve_region_with_split() to find the gaps in existing named
regions. This handles the gap between 'kernel code' and 'kernel data'
which is memblock_reserve()d, but already partially described by
request_standard_resources(). e.g.:
| 80000000-dfffffff : System RAM
|   80080000-80ffffff : Kernel code
|   81000000-8158ffff : reserved
|   81590000-8237efff : Kernel data
|   a0000000-dfffffff : Crash kernel
| e00f0000-f949ffff : System RAM

reserve_region_with_split needs kzalloc() which isn't available when
request_standard_resources() is called, use an initcall.

Reported-by: Bhupesh Sharma <bhsharma@redhat.com>
Reported-by: Tyler Baicar <tbaicar@codeaurora.org>
Suggested-by: Akashi Takahiro <takahiro.akashi@linaro.org>
Signed-off-by: James Morse <james.morse@arm.com>
Fixes: d28f6df1305a ("arm64/kexec: Add core kexec support")
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
CC: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/setup.c | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
index 30ad2f085d1f..5b4fac434c84 100644
--- a/arch/arm64/kernel/setup.c
+++ b/arch/arm64/kernel/setup.c
@@ -241,6 +241,44 @@ static void __init request_standard_resources(void)
 	}
 }
 
+static int __init reserve_memblock_reserved_regions(void)
+{
+	phys_addr_t start, end, roundup_end = 0;
+	struct resource *mem, *res;
+	u64 i;
+
+	for_each_reserved_mem_region(i, &start, &end) {
+		if (end <= roundup_end)
+			continue; /* done already */
+
+		start = __pfn_to_phys(PFN_DOWN(start));
+		end = __pfn_to_phys(PFN_UP(end)) - 1;
+		roundup_end = end;
+
+		res = kzalloc(sizeof(*res), GFP_ATOMIC);
+		if (WARN_ON(!res))
+			return -ENOMEM;
+		res->start = start;
+		res->end = end;
+		res->name  = "reserved";
+		res->flags = IORESOURCE_MEM;
+
+		mem = request_resource_conflict(&iomem_resource, res);
+		/*
+		 * We expected memblock_reserve() regions to conflict with
+		 * memory created by request_standard_resources().
+		 */
+		if (WARN_ON_ONCE(!mem))
+			continue;
+		kfree(res);
+
+		reserve_region_with_split(mem, start, end, "reserved");
+	}
+
+	return 0;
+}
+arch_initcall(reserve_memblock_reserved_regions);
+
 u64 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = INVALID_HWID };
 
 void __init setup_arch(char **cmdline_p)
-- 
cgit v1.2.3


From 5bcd44083a082f314032969cd6db1eb8275ac77a Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Mon, 23 Jul 2018 10:57:29 +0900
Subject: drivers: acpi: add dependency of EFI for arm64

As Ard suggested, CONFIG_ACPI && !CONFIG_EFI doesn't make sense on arm64,
while CONFIG_ACPI and CONFIG_CPU_BIG_ENDIAN doesn't make sense either.

As CONFIG_EFI already has a dependency of !CONFIG_CPU_BIG_ENDIAN, it is
good enough to add a dependency of CONFIG_EFI to avoid any useless
combination of configuration.

This bug, reported by Will, will be revealed when my patch series,
"arm64: kexec,kdump: fix boot failures on acpi-only system," is applied
and the kernel is built under allmodconfig.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Suggested-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/acpi/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index b533eeb6139d..15ab1daaa808 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -6,7 +6,7 @@
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
 	depends on !IA64_HP_SIM
-	depends on IA64 || X86 || ARM64
+	depends on IA64 || X86 || (ARM64 && EFI)
 	depends on PCI
 	select PNP
 	default y if (IA64 || X86)
-- 
cgit v1.2.3


From 3ea86495aef2f6de26b7cb1599ba350dd6a0c521 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 23 Jul 2018 10:57:30 +0900
Subject: efi/arm: preserve early mapping of UEFI memory map longer for BGRT

The BGRT code validates the contents of the table against the UEFI
memory map, and so it expects it to be mapped when the code runs.

On ARM, this is currently not the case, since we tear down the early
mapping after efi_init() completes, and only create the permanent
mapping in arm_enable_runtime_services(), which executes as an early
initcall, but still leaves a window where the UEFI memory map is not
mapped.

So move the call to efi_memmap_unmap() from efi_init() to
arm_enable_runtime_services().

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
[will: fold in EFI_MEMMAP attribute check from Ard]
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/firmware/efi/arm-init.c    | 1 -
 drivers/firmware/efi/arm-runtime.c | 4 +++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/arm-init.c b/drivers/firmware/efi/arm-init.c
index b5214c143fee..388a929baf95 100644
--- a/drivers/firmware/efi/arm-init.c
+++ b/drivers/firmware/efi/arm-init.c
@@ -259,7 +259,6 @@ void __init efi_init(void)
 
 	reserve_regions();
 	efi_esrt_init();
-	efi_memmap_unmap();
 
 	memblock_reserve(params.mmap & PAGE_MASK,
 			 PAGE_ALIGN(params.mmap_size +
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 5889cbea60b8..4712445c3213 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -110,11 +110,13 @@ static int __init arm_enable_runtime_services(void)
 {
 	u64 mapsize;
 
-	if (!efi_enabled(EFI_BOOT)) {
+	if (!efi_enabled(EFI_BOOT) || !efi_enabled(EFI_MEMMAP)) {
 		pr_info("EFI services will not be available.\n");
 		return 0;
 	}
 
+	efi_memmap_unmap();
+
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
 		return 0;
-- 
cgit v1.2.3


From 20d12cf990618845e76d3f24daaebd15d65a5e46 Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Mon, 23 Jul 2018 10:57:31 +0900
Subject: efi/arm: map UEFI memory map even w/o runtime services enabled

Under the current implementation, UEFI memory map will be mapped and made
available in virtual mappings only if runtime services are enabled.
But in a later patch, we want to use UEFI memory map in acpi_os_ioremap()
to create mappings of ACPI tables using memory attributes described in
UEFI memory map.
See the following commit:
    arm64: acpi: fix alignment fault in accessing ACPI tables

So, as a first step, arm_enter_runtime_services() is modified, alongside
Ard's patch[1], so that UEFI memory map will not be freed even if
efi=noruntime.

[1] https://marc.info/?l=linux-efi&m=152930773507524&w=2

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/firmware/efi/arm-runtime.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 4712445c3213..922cfb813109 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -117,6 +117,13 @@ static int __init arm_enable_runtime_services(void)
 
 	efi_memmap_unmap();
 
+	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
+
+	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
+		pr_err("Failed to remap EFI memory map\n");
+		return 0;
+	}
+
 	if (efi_runtime_disabled()) {
 		pr_info("EFI runtime services will be disabled.\n");
 		return 0;
@@ -129,13 +136,6 @@ static int __init arm_enable_runtime_services(void)
 
 	pr_info("Remapping and enabling EFI services.\n");
 
-	mapsize = efi.memmap.desc_size * efi.memmap.nr_map;
-
-	if (efi_memmap_init_late(efi.memmap.phys_map, mapsize)) {
-		pr_err("Failed to remap EFI memory map\n");
-		return -ENOMEM;
-	}
-
 	if (!efi_virtmap_init()) {
 		pr_err("UEFI virtual mapping missing or invalid -- runtime services will not be available\n");
 		return -ENOMEM;
-- 
cgit v1.2.3


From 09ffcb0d718a0b100f0bed029b830987ecf53fab Mon Sep 17 00:00:00 2001
From: AKASHI Takahiro <takahiro.akashi@linaro.org>
Date: Mon, 23 Jul 2018 10:57:32 +0900
Subject: arm64: acpi: fix alignment fault in accessing ACPI

This is a fix against the issue that crash dump kernel may hang up
during booting, which can happen on any ACPI-based system with "ACPI
Reclaim Memory."

(kernel messages after panic kicked off kdump)
	   (snip...)
	Bye!
	   (snip...)
	ACPI: Core revision 20170728
	pud=000000002e7d0003, *pmd=000000002e7c0003, *pte=00e8000039710707
	Internal error: Oops: 96000021 [#1] SMP
	Modules linked in:
	CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.14.0-rc6 #1
	task: ffff000008d05180 task.stack: ffff000008cc0000
	PC is at acpi_ns_lookup+0x25c/0x3c0
	LR is at acpi_ds_load1_begin_op+0xa4/0x294
	   (snip...)
	Process swapper/0 (pid: 0, stack limit = 0xffff000008cc0000)
	Call trace:
	   (snip...)
	[<ffff0000084a6764>] acpi_ns_lookup+0x25c/0x3c0
	[<ffff00000849b4f8>] acpi_ds_load1_begin_op+0xa4/0x294
	[<ffff0000084ad4ac>] acpi_ps_build_named_op+0xc4/0x198
	[<ffff0000084ad6cc>] acpi_ps_create_op+0x14c/0x270
	[<ffff0000084acfa8>] acpi_ps_parse_loop+0x188/0x5c8
	[<ffff0000084ae048>] acpi_ps_parse_aml+0xb0/0x2b8
	[<ffff0000084a8e10>] acpi_ns_one_complete_parse+0x144/0x184
	[<ffff0000084a8e98>] acpi_ns_parse_table+0x48/0x68
	[<ffff0000084a82cc>] acpi_ns_load_table+0x4c/0xdc
	[<ffff0000084b32f8>] acpi_tb_load_namespace+0xe4/0x264
	[<ffff000008baf9b4>] acpi_load_tables+0x48/0xc0
	[<ffff000008badc20>] acpi_early_init+0x9c/0xd0
	[<ffff000008b70d50>] start_kernel+0x3b4/0x43c
	Code: b9008fb9 2a000318 36380054 32190318 (b94002c0)
	---[ end trace c46ed37f9651c58e ]---
	Kernel panic - not syncing: Fatal exception
	Rebooting in 10 seconds..

(diagnosis)
* This fault is a data abort, alignment fault (ESR=0x96000021)
  during reading out ACPI table.
* Initial ACPI tables are normally stored in system ram and marked as
  "ACPI Reclaim memory" by the firmware.
* After the commit f56ab9a5b73c ("efi/arm: Don't mark ACPI reclaim
  memory as MEMBLOCK_NOMAP"), those regions are differently handled
  as they are "memblock-reserved", without NOMAP bit.
* So they are now excluded from device tree's "usable-memory-range"
  which kexec-tools determines based on a current view of /proc/iomem.
* When crash dump kernel boots up, it tries to accesses ACPI tables by
  mapping them with ioremap(), not ioremap_cache(), in acpi_os_ioremap()
  since they are no longer part of mapped system ram.
* Given that ACPI accessor/helper functions are compiled in without
  unaligned access support (ACPI_MISALIGNMENT_NOT_SUPPORTED),
  any unaligned access to ACPI tables can cause a fatal panic.

With this patch, acpi_os_ioremap() always honors memory attribute
information provided by the firmware (EFI) and retaining cacheability
allows the kernel safe access to ACPI tables.

Signed-off-by: AKASHI Takahiro <takahiro.akashi@linaro.org>
Reviewed-by: James Morse <james.morse@arm.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Reported-by and Tested-by: Bhupesh Sharma <bhsharma@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/acpi.h | 23 ++++++++++++++++-------
 arch/arm64/kernel/acpi.c      | 11 +++--------
 2 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
index d1c290f29b6f..709208dfdc8b 100644
--- a/arch/arm64/include/asm/acpi.h
+++ b/arch/arm64/include/asm/acpi.h
@@ -12,10 +12,12 @@
 #ifndef _ASM_ACPI_H
 #define _ASM_ACPI_H
 
+#include <linux/efi.h>
 #include <linux/memblock.h>
 #include <linux/psci.h>
 
 #include <asm/cputype.h>
+#include <asm/io.h>
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
 
@@ -29,18 +31,22 @@
 
 /* Basic configuration for ACPI */
 #ifdef	CONFIG_ACPI
+pgprot_t __acpi_get_mem_attribute(phys_addr_t addr);
+
 /* ACPI table mapping after acpi_permanent_mmap is set */
 static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 					    acpi_size size)
 {
+	/* For normal memory we already have a cacheable mapping. */
+	if (memblock_is_map_memory(phys))
+		return (void __iomem *)__phys_to_virt(phys);
+
 	/*
-	 * EFI's reserve_regions() call adds memory with the WB attribute
-	 * to memblock via early_init_dt_add_memory_arch().
+	 * We should still honor the memory's attribute here because
+	 * crash dump kernel possibly excludes some ACPI (reclaim)
+	 * regions from memblock list.
 	 */
-	if (!memblock_is_memory(phys))
-		return ioremap(phys, size);
-
-	return ioremap_cache(phys, size);
+	return __ioremap(phys, size, __acpi_get_mem_attribute(phys));
 }
 #define acpi_os_ioremap acpi_os_ioremap
 
@@ -129,7 +135,10 @@ static inline const char *acpi_get_enable_method(int cpu)
  * for compatibility.
  */
 #define acpi_disable_cmcff 1
-pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr);
+static inline pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
+{
+	return __acpi_get_mem_attribute(addr);
+}
 #endif /* CONFIG_ACPI_APEI */
 
 #ifdef CONFIG_ACPI_NUMA
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c
index 7b09487ff8fb..ed46dc188b22 100644
--- a/arch/arm64/kernel/acpi.c
+++ b/arch/arm64/kernel/acpi.c
@@ -18,6 +18,7 @@
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/cpumask.h>
+#include <linux/efi.h>
 #include <linux/efi-bgrt.h>
 #include <linux/init.h>
 #include <linux/irq.h>
@@ -29,13 +30,9 @@
 
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
+#include <asm/pgtable.h>
 #include <asm/smp_plat.h>
 
-#ifdef CONFIG_ACPI_APEI
-# include <linux/efi.h>
-# include <asm/pgtable.h>
-#endif
-
 int acpi_noirq = 1;		/* skip ACPI IRQ initialization */
 int acpi_disabled = 1;
 EXPORT_SYMBOL(acpi_disabled);
@@ -239,8 +236,7 @@ done:
 	}
 }
 
-#ifdef CONFIG_ACPI_APEI
-pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
+pgprot_t __acpi_get_mem_attribute(phys_addr_t addr)
 {
 	/*
 	 * According to "Table 8 Map: EFI memory types to AArch64 memory
@@ -261,4 +257,3 @@ pgprot_t arch_apei_get_mem_attribute(phys_addr_t addr)
 		return __pgprot(PROT_NORMAL_NC);
 	return __pgprot(PROT_DEVICE_nGnRnE);
 }
-#endif
-- 
cgit v1.2.3


From 7749a57a285342ff5664c80236a63c7fa53cbdfc Mon Sep 17 00:00:00 2001
From: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Date: Fri, 13 Jul 2018 16:10:59 +0100
Subject: drm: mali-dp: Report writeback connector as connected

Older version of this patch series reported writeback as disconnected
to avoid confusing userspace not aware of writeback connectors.
However, the version that got merged uses a special cap
(DRM_CLIENT_CAP_WRITEBACK_CONNECTORS) for this purpose.

This helps us avoid some special handling of writeback connector
in drm_helper_probe_single_connector_modes, see [1].

https://lists.freedesktop.org/archives/dri-devel/2018-July/183144.html

Signed-off-by: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_mw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/arm/malidp_mw.c b/drivers/gpu/drm/arm/malidp_mw.c
index cfd718e7e97c..ba6ae66387c9 100644
--- a/drivers/gpu/drm/arm/malidp_mw.c
+++ b/drivers/gpu/drm/arm/malidp_mw.c
@@ -73,7 +73,7 @@ static void malidp_mw_connector_reset(struct drm_connector *connector)
 static enum drm_connector_status
 malidp_mw_connector_detect(struct drm_connector *connector, bool force)
 {
-	return connector_status_disconnected;
+	return connector_status_connected;
 }
 
 static void malidp_mw_connector_destroy(struct drm_connector *connector)
-- 
cgit v1.2.3


From 2e012e76ad59edb4a5a175c0957a44337dc39d87 Mon Sep 17 00:00:00 2001
From: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Date: Fri, 13 Jul 2018 16:11:00 +0100
Subject: drm: mali-dp: Set encoder possible_clones

Set possible_clones field to report that the writeback connector and
the one driving the display could be enabled at the same time.

Signed-off-by: Alexandru Gheorghe <alexandru-cosmin.gheorghe@arm.com>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/malidp_drv.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/arm/malidp_drv.c b/drivers/gpu/drm/arm/malidp_drv.c
index 5b7260557391..08b5bb219816 100644
--- a/drivers/gpu/drm/arm/malidp_drv.c
+++ b/drivers/gpu/drm/arm/malidp_drv.c
@@ -616,6 +616,7 @@ static int malidp_bind(struct device *dev)
 	struct malidp_hw_device *hwdev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct of_device_id const *dev_id;
+	struct drm_encoder *encoder;
 	/* number of lines for the R, G and B output */
 	u8 output_width[MAX_OUTPUT_CHANNELS];
 	int ret = 0, i;
@@ -737,6 +738,15 @@ static int malidp_bind(struct device *dev)
 		goto bind_fail;
 	}
 
+	/* We expect to have a maximum of two encoders one for the actual
+	 * display and a virtual one for the writeback connector
+	 */
+	WARN_ON(drm->mode_config.num_encoder > 2);
+	list_for_each_entry(encoder, &drm->mode_config.encoder_list, head) {
+		encoder->possible_clones =
+				(1 << drm->mode_config.num_encoder) -  1;
+	}
+
 	ret = malidp_irq_init(pdev);
 	if (ret < 0)
 		goto irq_init_fail;
-- 
cgit v1.2.3


From b965746306bcb058a6876d3a61b502d3dbb9fe91 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Wed, 20 Jun 2018 17:17:47 +0100
Subject: rseq/selftests: Add support for arm64

Hook up arm64 support to the rseq selftests.

Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 tools/testing/selftests/rseq/param_test.c |  20 +
 tools/testing/selftests/rseq/rseq-arm64.h | 594 ++++++++++++++++++++++++++++++
 tools/testing/selftests/rseq/rseq.h       |   2 +
 3 files changed, 616 insertions(+)
 create mode 100644 tools/testing/selftests/rseq/rseq-arm64.h

diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 615252331813..fa144c556371 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -114,6 +114,26 @@ unsigned int yield_mod_cnt, nr_abort;
 	"bne 222b\n\t" \
 	"333:\n\t"
 
+#elif defined(__AARCH64EL__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1] "Qo" (loop_cnt[1]) \
+	, [loop_cnt_2] "Qo" (loop_cnt[2]) \
+	, [loop_cnt_3] "Qo" (loop_cnt[3]) \
+	, [loop_cnt_4] "Qo" (loop_cnt[4]) \
+	, [loop_cnt_5] "Qo" (loop_cnt[5]) \
+	, [loop_cnt_6] "Qo" (loop_cnt[6])
+
+#define INJECT_ASM_REG	RSEQ_ASM_TMP_REG32
+
+#define RSEQ_INJECT_ASM(n) \
+	"	ldr	" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n"	\
+	"	cbz	" INJECT_ASM_REG ", 333f\n"			\
+	"222:\n"							\
+	"	sub	" INJECT_ASM_REG ", " INJECT_ASM_REG ", #1\n"	\
+	"	cbnz	" INJECT_ASM_REG ", 222b\n"			\
+	"333:\n"
+
 #elif __PPC__
 
 #define RSEQ_INJECT_INPUT \
diff --git a/tools/testing/selftests/rseq/rseq-arm64.h b/tools/testing/selftests/rseq/rseq-arm64.h
new file mode 100644
index 000000000000..954f34671ca6
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-arm64.h
@@ -0,0 +1,594 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+/*
+ * rseq-arm64.h
+ *
+ * (C) Copyright 2016-2018 - Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ * (C) Copyright 2018 - Will Deacon <will.deacon@arm.com>
+ */
+
+#define RSEQ_SIG	0xd428bc00	/* BRK #0x45E0 */
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("dmb ish" ::: "memory")
+#define rseq_smp_rmb()	__asm__ __volatile__ ("dmb ishld" ::: "memory")
+#define rseq_smp_wmb()	__asm__ __volatile__ ("dmb ishst" ::: "memory")
+
+#define rseq_smp_load_acquire(p)						\
+__extension__ ({								\
+	__typeof(*p) ____p1;							\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		asm volatile ("ldarb %w0, %1"					\
+			: "=r" (*(__u8 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 2:									\
+		asm volatile ("ldarh %w0, %1"					\
+			: "=r" (*(__u16 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 4:									\
+		asm volatile ("ldar %w0, %1"					\
+			: "=r" (*(__u32 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	case 8:									\
+		asm volatile ("ldar %0, %1"					\
+			: "=r" (*(__u64 *)p)					\
+			: "Q" (*p) : "memory");					\
+		break;								\
+	}									\
+	____p1;									\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)						\
+do {										\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		asm volatile ("stlrb %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u8)v)					\
+				: "memory");					\
+		break;								\
+	case 2:									\
+		asm volatile ("stlrh %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u16)v)				\
+				: "memory");					\
+		break;								\
+	case 4:									\
+		asm volatile ("stlr %w1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u32)v)				\
+				: "memory");					\
+		break;								\
+	case 8:									\
+		asm volatile ("stlr %1, %0"					\
+				: "=Q" (*p)					\
+				: "r" ((__u64)v)				\
+				: "memory");					\
+		break;								\
+	}									\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#define RSEQ_ASM_TMP_REG32	"w15"
+#define RSEQ_ASM_TMP_REG	"x15"
+#define RSEQ_ASM_TMP_REG_2	"x14"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags, start_ip,		\
+				post_commit_offset, abort_ip)			\
+	"	.pushsection	__rseq_table, \"aw\"\n"				\
+	"	.balign	32\n"							\
+	__rseq_str(label) ":\n"							\
+	"	.long	" __rseq_str(version) ", " __rseq_str(flags) "\n"	\
+	"	.quad	" __rseq_str(start_ip) ", "				\
+			  __rseq_str(post_commit_offset) ", "			\
+			  __rseq_str(abort_ip) "\n"				\
+	"	.popsection\n"
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip)	\
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,			\
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)			\
+	RSEQ_INJECT_ASM(1)							\
+	"	adrp	" RSEQ_ASM_TMP_REG ", " __rseq_str(cs_label) "\n"	\
+	"	add	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", :lo12:" __rseq_str(cs_label) "\n"			\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(rseq_cs) "]\n"	\
+	__rseq_str(label) ":\n"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, abort_label)				\
+	"	b	222f\n"							\
+	"	.inst 	"	__rseq_str(RSEQ_SIG) "\n"			\
+	__rseq_str(label) ":\n"							\
+	"	b	%l[" __rseq_str(abort_label) "]\n"			\
+	"222:\n"
+
+#define RSEQ_ASM_OP_STORE(value, var)						\
+	"	str	%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_STORE_RELEASE(value, var)					\
+	"	stlr	%[" __rseq_str(value) "], %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE(value, var, post_commit_label)			\
+	RSEQ_ASM_OP_STORE(value, var)						\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_FINAL_STORE_RELEASE(value, var, post_commit_label)		\
+	RSEQ_ASM_OP_STORE_RELEASE(value, var)					\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_CMPEQ(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	"	sub	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(expect) "]\n"				\
+	"	cbnz	" RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPEQ32(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG32 ", %[" __rseq_str(var) "]\n"	\
+	"	sub	" RSEQ_ASM_TMP_REG32 ", " RSEQ_ASM_TMP_REG32		\
+			", %w[" __rseq_str(expect) "]\n"			\
+	"	cbnz	" RSEQ_ASM_TMP_REG32 ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_OP_CMPNE(var, expect, label)					\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	"	sub	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(expect) "]\n"				\
+	"	cbz	" RSEQ_ASM_TMP_REG ", " __rseq_str(label) "\n"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)			\
+	RSEQ_INJECT_ASM(2)							\
+	RSEQ_ASM_OP_CMPEQ32(current_cpu_id, cpu_id, label)
+
+#define RSEQ_ASM_OP_R_LOAD(var)							\
+	"	ldr	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_STORE(var)						\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"
+
+#define RSEQ_ASM_OP_R_LOAD_OFF(offset)						\
+	"	ldr	" RSEQ_ASM_TMP_REG ", [" RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(offset) "]]\n"
+
+#define RSEQ_ASM_OP_R_ADD(count)						\
+	"	add	" RSEQ_ASM_TMP_REG ", " RSEQ_ASM_TMP_REG		\
+			", %[" __rseq_str(count) "]\n"
+
+#define RSEQ_ASM_OP_R_FINAL_STORE(var, post_commit_label)			\
+	"	str	" RSEQ_ASM_TMP_REG ", %[" __rseq_str(var) "]\n"		\
+	__rseq_str(post_commit_label) ":\n"
+
+#define RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)					\
+	"	cbz	%[" __rseq_str(len) "], 333f\n"				\
+	"	mov	" RSEQ_ASM_TMP_REG_2 ", %[" __rseq_str(len) "]\n"	\
+	"222:	sub	" RSEQ_ASM_TMP_REG_2 ", " RSEQ_ASM_TMP_REG_2 ", #1\n"	\
+	"	ldrb	" RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(src) "]"	\
+			", " RSEQ_ASM_TMP_REG_2 "]\n"				\
+	"	strb	" RSEQ_ASM_TMP_REG32 ", [%[" __rseq_str(dst) "]"	\
+			", " RSEQ_ASM_TMP_REG_2 "]\n"				\
+	"	cbnz	" RSEQ_ASM_TMP_REG_2 ", 222b\n"				\
+	"333:\n"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPNE(v, expectnot, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_LOAD(v)
+		RSEQ_ASM_OP_R_STORE(load)
+		RSEQ_ASM_OP_R_LOAD_OFF(voffp)
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [load]		"Qo" (*load),
+		  [voffp]		"r" (voffp)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		RSEQ_ASM_OP_R_LOAD(v)
+		RSEQ_ASM_OP_R_ADD(count)
+		RSEQ_ASM_OP_R_FINAL_STORE(v, 3)
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [v2]			"Qo" (*v2),
+		  [newv2]		"r" (newv2)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_STORE(newv2, v2)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [v2]			"Qo" (*v2),
+		  [newv2]		"r" (newv2)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[cmpfail])
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+		RSEQ_ASM_OP_CMPEQ(v2, expect2, %l[error3])
+#endif
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"Qo" (*v),
+		  [expect]		"r" (expect),
+		  [v2]			"Qo" (*v2),
+		  [expect2]		"r" (expect2),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(1, 2f, 3f, 4f)
+		RSEQ_ASM_STORE_RSEQ_CS(2, 1b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[cmpfail])
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		RSEQ_ASM_OP_CMPEQ(v, expect, %l[error2])
+#endif
+		RSEQ_ASM_OP_R_BAD_MEMCPY(dst, src, len)
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_OP_FINAL_STORE_RELEASE(newv, v, 3)
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"Qo" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [expect]		"r" (expect),
+		  [v]			"Qo" (*v),
+		  [newv]		"r" (newv),
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len)
+		  RSEQ_INJECT_INPUT
+		: "memory", RSEQ_ASM_TMP_REG, RSEQ_ASM_TMP_REG_2
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index a4684112676c..b5d94087fe31 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -71,6 +71,8 @@ extern __thread volatile struct rseq __rseq_abi;
 #include <rseq-x86.h>
 #elif defined(__ARMEL__)
 #include <rseq-arm.h>
+#elif defined (__AARCH64EL__)
+#include <rseq-arm64.h>
 #elif defined(__PPC__)
 #include <rseq-ppc.h>
 #elif defined(__mips__)
-- 
cgit v1.2.3


From 0e3fd810c4f41dbd63fb7caddc11684959176727 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jul 2018 16:46:41 +0200
Subject: Documentation: document ktime_get_*() APIs

As Dave Chinner points out, we don't have a proper documentation for the
ktime_get() family of interfaces, making it rather unclear which of the
over 30 (!) interfaces one should actually use in a driver or elsewhere
in the kernel.

I wrote up an explanation from how I personally see the interfaces,
documenting what each of the functions do and hopefully making it a bit
clearer which should be used where.

This is the first time I tried writing .rst format documentation, so
in addition to any mistakes in the content, I probably also introduce
nonstandard formatting ;-)

I first tried to add an extra section to
Documentation/timers/timekeeping.txt, but this is currently not included
in the generated API, and it seems useful to have the API docs as part
of what gets generated in
https://www.kernel.org/doc/html/latest/core-api/index.html#core-utilities
instead, so I started a new file there.

I also considered adding the documentation inline in the
include/linux/timekeeping.h header, but couldn't figure out how to do
that in a way that would result both in helpful inline comments as
well as readable html output, so I settled for the latter, with
a small note pointing to it from the header.

Cc: Dave Chinner <david@fromorbit.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Stephen Boyd <sboyd@kernel.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/core-api/index.rst       |   1 +
 Documentation/core-api/timekeeping.rst | 185 +++++++++++++++++++++++++++++++++
 include/linux/timekeeping.h            |  15 +++
 3 files changed, 201 insertions(+)
 create mode 100644 Documentation/core-api/timekeeping.rst

diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index f5a66b72f984..989c97cc232a 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -28,6 +28,7 @@ Core utilities
    printk-formats
    circular-buffers
    gfp_mask-from-fs-io
+   timekeeping
 
 Interfaces for kernel debugging
 ===============================
diff --git a/Documentation/core-api/timekeeping.rst b/Documentation/core-api/timekeeping.rst
new file mode 100644
index 000000000000..93cbeb9daec0
--- /dev/null
+++ b/Documentation/core-api/timekeeping.rst
@@ -0,0 +1,185 @@
+ktime accessors
+===============
+
+Device drivers can read the current time using ktime_get() and the many
+related functions declared in linux/timekeeping.h. As a rule of thumb,
+using an accessor with a shorter name is preferred over one with a longer
+name if both are equally fit for a particular use case.
+
+Basic ktime_t based interfaces
+------------------------------
+
+The recommended simplest form returns an opaque ktime_t, with variants
+that return time for different clock references:
+
+
+.. c:function:: ktime_t ktime_get( void )
+
+	CLOCK_MONOTONIC
+
+	Useful for reliable timestamps and measuring short time intervals
+	accurately. Starts at system boot time but stops during suspend.
+
+.. c:function:: ktime_t ktime_get_boottime( void )
+
+	CLOCK_BOOTTIME
+
+	Like ktime_get(), but does not stop when suspended. This can be
+	used e.g. for key expiration times that need to be synchronized
+	with other machines across a suspend operation.
+
+.. c:function:: ktime_t ktime_get_real( void )
+
+	CLOCK_REALTIME
+
+	Returns the time in relative to the UNIX epoch starting in 1970
+	using the Coordinated Universal Time (UTC), same as gettimeofday()
+	user space. This is used for all timestamps that need to
+	persist across a reboot, like inode times, but should be avoided
+	for internal uses, since it can jump backwards due to a leap
+	second update, NTP adjustment settimeofday() operation from user
+	space.
+
+.. c:function:: ktime_t ktime_get_clocktai( void )
+
+	 CLOCK_TAI
+
+	Like ktime_get_real(), but uses the International Atomic Time (TAI)
+	reference instead of UTC to avoid jumping on leap second updates.
+	This is rarely useful in the kernel.
+
+.. c:function:: ktime_t ktime_get_raw( void )
+
+	CLOCK_MONOTONIC_RAW
+
+	Like ktime_get(), but runs at the same rate as the hardware
+	clocksource without (NTP) adjustments for clock drift. This is
+	also rarely needed in the kernel.
+
+nanosecond, timespec64, and second output
+-----------------------------------------
+
+For all of the above, there are variants that return the time in a
+different format depending on what is required by the user:
+
+.. c:function:: u64 ktime_get_ns( void )
+		u64 ktime_get_boottime_ns( void )
+		u64 ktime_get_real_ns( void )
+		u64 ktime_get_tai_ns( void )
+		u64 ktime_get_raw_ns( void )
+
+	Same as the plain ktime_get functions, but returning a u64 number
+	of nanoseconds in the respective time reference, which may be
+	more convenient for some callers.
+
+.. c:function:: void ktime_get_ts64( struct timespec64 * )
+		void ktime_get_boottime_ts64( struct timespec64 * )
+		void ktime_get_real_ts64( struct timespec64 * )
+		void ktime_get_clocktai_ts64( struct timespec64 * )
+		void ktime_get_raw_ts64( struct timespec64 * )
+
+	Same above, but returns the time in a 'struct timespec64', split
+	into seconds and nanoseconds. This can avoid an extra division
+	when printing the time, or when passing it into an external
+	interface that expects a 'timespec' or 'timeval' structure.
+
+.. c:function:: time64_t ktime_get_seconds( void )
+		time64_t ktime_get_boottime_seconds( void )
+		time64_t ktime_get_real_seconds( void )
+		time64_t ktime_get_clocktai_seconds( void )
+		time64_t ktime_get_raw_seconds( void )
+
+	Return a coarse-grained version of the time as a scalar
+	time64_t. This avoids accessing the clock hardware and rounds
+	down the seconds to the full seconds of the last timer tick
+	using the respective reference.
+
+Coarse and fast_ns access
+-------------------------
+
+Some additional variants exist for more specialized cases:
+
+.. c:function:: ktime_t ktime_get_coarse_boottime( void )
+		ktime_t ktime_get_coarse_real( void )
+		ktime_t ktime_get_coarse_clocktai( void )
+		ktime_t ktime_get_coarse_raw( void )
+
+.. c:function:: void ktime_get_coarse_ts64( struct timespec64 * )
+		void ktime_get_coarse_boottime_ts64( struct timespec64 * )
+		void ktime_get_coarse_real_ts64( struct timespec64 * )
+		void ktime_get_coarse_clocktai_ts64( struct timespec64 * )
+		void ktime_get_coarse_raw_ts64( struct timespec64 * )
+
+	These are quicker than the non-coarse versions, but less accurate,
+	corresponding to CLOCK_MONONOTNIC_COARSE and CLOCK_REALTIME_COARSE
+	in user space, along with the equivalent boottime/tai/raw
+	timebase not available in user space.
+
+	The time returned here corresponds to the last timer tick, which
+	may be as much as 10ms in the past (for CONFIG_HZ=100), same as
+	reading the 'jiffies' variable.  These are only useful when called
+	in a fast path and one still expects better than second accuracy,
+	but can't easily use 'jiffies', e.g. for inode timestamps.
+	Skipping the hardware clock access saves around 100 CPU cycles
+	on most modern machines with a reliable cycle counter, but
+	up to several microseconds on older hardware with an external
+	clocksource.
+
+.. c:function:: u64 ktime_get_mono_fast_ns( void )
+		u64 ktime_get_raw_fast_ns( void )
+		u64 ktime_get_boot_fast_ns( void )
+		u64 ktime_get_real_fast_ns( void )
+
+	These variants are safe to call from any context, including from
+	a non-maskable interrupt (NMI) during a timekeeper update, and
+	while we are entering suspend with the clocksource powered down.
+	This is useful in some tracing or debugging code as well as
+	machine check reporting, but most drivers should never call them,
+	since the time is allowed to jump under certain conditions.
+
+Deprecated time interfaces
+--------------------------
+
+Older kernels used some other interfaces that are now being phased out
+but may appear in third-party drivers being ported here. In particular,
+all interfaces returning a 'struct timeval' or 'struct timespec' have
+been replaced because the tv_sec member overflows in year 2038 on 32-bit
+architectures. These are the recommended replacements:
+
+.. c:function:: void ktime_get_ts( struct timespec * )
+
+	Use ktime_get() or ktime_get_ts64() instead.
+
+.. c:function:: struct timeval do_gettimeofday( void )
+		struct timespec getnstimeofday( void )
+		struct timespec64 getnstimeofday64( void )
+		void ktime_get_real_ts( struct timespec * )
+
+	ktime_get_real_ts64() is a direct replacement, but consider using
+	monotonic time (ktime_get_ts64()) and/or a ktime_t based interface
+	(ktime_get()/ktime_get_real()).
+
+.. c:function:: struct timespec current_kernel_time( void )
+		struct timespec64 current_kernel_time64( void )
+		struct timespec get_monotonic_coarse( void )
+		struct timespec64 get_monotonic_coarse64( void )
+
+	These are replaced by ktime_get_coarse_real_ts64() and
+	ktime_get_coarse_ts64(). However, A lot of code that wants
+	coarse-grained times can use the simple 'jiffies' instead, while
+	some drivers may actually want the higher resolution accessors
+	these days.
+
+.. c:function:: struct timespec getrawmonotonic( void )
+		struct timespec64 getrawmonotonic64( void )
+		struct timespec timekeeping_clocktai( void )
+		struct timespec64 timekeeping_clocktai64( void )
+		struct timespec get_monotonic_boottime( void )
+		struct timespec64 get_monotonic_boottime64( void )
+
+	These are replaced by ktime_get_raw()/ktime_get_raw_ts64(),
+	ktime_get_clocktai()/ktime_get_clocktai_ts64() as well
+	as ktime_get_boottime()/ktime_get_boottime_ts64().
+	However, if the particular choice of clock source is not
+	important for the user, consider converting to
+	ktime_get()/ktime_get_ts64() instead for consistency.
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 86bc2026efce..947b1b8d2d01 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -20,6 +20,21 @@ extern int do_settimeofday64(const struct timespec64 *ts);
 extern int do_sys_settimeofday64(const struct timespec64 *tv,
 				 const struct timezone *tz);
 
+/*
+ * ktime_get() family: read the current time in a multitude of ways,
+ *
+ * The default time reference is CLOCK_MONOTONIC, starting at
+ * boot time but not counting the time spent in suspend.
+ * For other references, use the functions with "real", "clocktai",
+ * "boottime" and "raw" suffixes.
+ *
+ * To get the time in a different format, use the ones wit
+ * "ns", "ts64" and "seconds" suffix.
+ *
+ * See Documentation/core-api/timekeeping.rst for more details.
+ */
+
+
 /*
  * timespec64 based interfaces
  */
-- 
cgit v1.2.3


From 655c75a206e65058c50abe731c0518fae5e25c73 Mon Sep 17 00:00:00 2001
From: Prashant Dhamdhere <pdhamdhe@redhat.com>
Date: Fri, 13 Jul 2018 22:58:06 +0530
Subject: Documentation: proc.txt: Adding 'HardwareCorrupted' field and
 description.

Fill in missing documentation for the HardwareCorrupted field in proc.txt.

Signed-off-by: Prashant Dhamdhere <pdhamdhe@redhat.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/filesystems/proc.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 520f6a84cf50..1605acbb23b6 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -870,6 +870,7 @@ Committed_AS:   100056 kB
 VmallocTotal:   112216 kB
 VmallocUsed:       428 kB
 VmallocChunk:   111088 kB
+HardwareCorrupted:   0 kB
 AnonHugePages:   49152 kB
 ShmemHugePages:      0 kB
 ShmemPmdMapped:      0 kB
@@ -915,6 +916,8 @@ MemAvailable: An estimate of how much memory is available for starting new
        Dirty: Memory which is waiting to get written back to the disk
    Writeback: Memory which is actively being written back to the disk
    AnonPages: Non-file backed pages mapped into userspace page tables
+HardwareCorrupted: The amount of RAM/memory in KB, the kernel identifies as
+	      corrupted.
 AnonHugePages: Non-file backed huge pages mapped into userspace page tables
       Mapped: files which have been mmaped, such as libraries
        Shmem: Total memory used by shared memory (shmem) and tmpfs
-- 
cgit v1.2.3


From e50891d6eff5bc446ecf5d4c04906a19d2eb8424 Mon Sep 17 00:00:00 2001
From: Andreas Ziegler <andreas.ziegler@fau.de>
Date: Mon, 16 Jul 2018 13:05:57 +0200
Subject: Documentation: {u,k}probes: fix filename for event enabling

The per-event files to enable or disable kprobes and uprobes
are named 'enable', not 'enabled'. Fix the corresponding
documentation.

Signed-off-by: Andreas Ziegler <andreas.ziegler@fau.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/trace/kprobetrace.rst  | 6 +++---
 Documentation/trace/uprobetracer.rst | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index 3e0f971b12de..c4aaef7d7c89 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -18,7 +18,7 @@ To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
 /sys/kernel/debug/tracing/kprobe_events, and enable it via
-/sys/kernel/debug/tracing/events/kprobes/<EVENT>/enabled.
+/sys/kernel/debug/tracing/events/kprobes/<EVENT>/enable.
 
 
 Synopsis of kprobe_events
@@ -81,9 +81,9 @@ Per-probe event filtering feature allows you to set different filter on each
 probe and gives you what arguments will be shown in trace buffer. If an event
 name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event
 under tracing/events/kprobes/<EVENT>, at the directory you can see 'id',
-'enabled', 'format' and 'filter'.
+'enable', 'format' and 'filter'.
 
-enabled:
+enable:
   You can enable/disable the probe by writing 1 or 0 on it.
 
 format:
diff --git a/Documentation/trace/uprobetracer.rst b/Documentation/trace/uprobetracer.rst
index 98d3f692957a..d0822811527a 100644
--- a/Documentation/trace/uprobetracer.rst
+++ b/Documentation/trace/uprobetracer.rst
@@ -13,7 +13,7 @@ To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
 /sys/kernel/debug/tracing/uprobe_events, and enable it via
-/sys/kernel/debug/tracing/events/uprobes/<EVENT>/enabled.
+/sys/kernel/debug/tracing/events/uprobes/<EVENT>/enable.
 
 However unlike kprobe-event tracer, the uprobe event interface expects the
 user to calculate the offset of the probepoint in the object.
-- 
cgit v1.2.3


From 31130c8ec8cc03dec563b8e1317be508d4268225 Mon Sep 17 00:00:00 2001
From: Andreas Ziegler <andreas.ziegler@fau.de>
Date: Mon, 16 Jul 2018 13:05:58 +0200
Subject: Documentation: kprobetrace: document 'trigger' file

As the other files are documented explicitly, let's add a
short description for 'trigger' as well.

Signed-off-by: Andreas Ziegler <andreas.ziegler@fau.de>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/trace/kprobetrace.rst | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/Documentation/trace/kprobetrace.rst b/Documentation/trace/kprobetrace.rst
index c4aaef7d7c89..8bfc75c90806 100644
--- a/Documentation/trace/kprobetrace.rst
+++ b/Documentation/trace/kprobetrace.rst
@@ -81,7 +81,7 @@ Per-probe event filtering feature allows you to set different filter on each
 probe and gives you what arguments will be shown in trace buffer. If an event
 name is specified right after 'p:' or 'r:' in kprobe_events, it adds an event
 under tracing/events/kprobes/<EVENT>, at the directory you can see 'id',
-'enable', 'format' and 'filter'.
+'enable', 'format', 'filter' and 'trigger'.
 
 enable:
   You can enable/disable the probe by writing 1 or 0 on it.
@@ -95,6 +95,9 @@ filter:
 id:
   This shows the id of this probe event.
 
+trigger:
+  This allows to install trigger commands which are executed when the event is
+  hit (for details, see Documentation/trace/events.rst, section 6).
 
 Event Profiling
 ---------------
-- 
cgit v1.2.3


From 701b3a3c0ac42630f74a5efba8545d61ac0e3293 Mon Sep 17 00:00:00 2001
From: "valdis.kletnieks@vt.edu" <valdis.kletnieks@vt.edu>
Date: Tue, 17 Jul 2018 12:57:29 -0400
Subject: PATCH scripts/kernel-doc

Fix a warning whinge from Perl introduced by "scripts: kernel-doc: parse next structs/unions"

Unescaped left brace in regex is deprecated here (and will be fatal in Perl 5.32), passed through in regex; marked by <-- HERE in m/({ <-- HERE [^\{\}]*})/ at ./scripts/kernel-doc line 1155.
Unescaped left brace in regex is deprecated here (and will be fatal in Perl 5.32), passed through in regex; marked by <-- HERE in m/({ <-- HERE )/ at ./scripts/kernel-doc line 1179.

Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Reviewed-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 scripts/kernel-doc | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 0057d8eafcc1..31a34ced55a3 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1152,7 +1152,7 @@ sub dump_struct($$) {
 	}
 
 	# Ignore other nested elements, like enums
-	$members =~ s/({[^\{\}]*})//g;
+	$members =~ s/(\{[^\{\}]*})//g;
 
 	create_parameterlist($members, ';', $file, $declaration_name);
 	check_sections($file, $declaration_name, $decl_type, $sectcheck, $struct_actual);
@@ -1176,7 +1176,7 @@ sub dump_struct($$) {
 			$declaration .= "\t" x $level;
 		}
 		$declaration .= "\t" . $clause . "\n";
-		$level++ if ($clause =~ m/({)/ && !($clause =~m/}/));
+		$level++ if ($clause =~ m/(\{)/ && !($clause =~m/}/));
 	}
 	output_declaration($declaration_name,
 			   'struct',
-- 
cgit v1.2.3


From 9e7c758ec4768cf47779dea3cc8452f871f8d07e Mon Sep 17 00:00:00 2001
From: Siddaraju DH <siddarajudh@gmail.com>
Date: Thu, 19 Jul 2018 22:06:51 +0530
Subject: timekeeping.txt: Correct maxCount of n-bit binary counter

A n-bit binary counter can count a maximum of 2^n events and the count
value ranges from 0 to (2^n)-1

Signed-off-by: Siddaraju DH <siddarajudh@gmail.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/timers/timekeeping.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/timers/timekeeping.txt b/Documentation/timers/timekeeping.txt
index f3a8cf28f802..2d1732b0a868 100644
--- a/Documentation/timers/timekeeping.txt
+++ b/Documentation/timers/timekeeping.txt
@@ -27,7 +27,7 @@ a Linux system will eventually read the clock source to determine exactly
 what time it is.
 
 Typically the clock source is a monotonic, atomic counter which will provide
-n bits which count from 0 to 2^(n-1) and then wraps around to 0 and start over.
+n bits which count from 0 to (2^n)-1 and then wraps around to 0 and start over.
 It will ideally NEVER stop ticking as long as the system is running. It
 may stop during system suspend.
 
-- 
cgit v1.2.3


From 203b400ee24ef11153651b6c4580896a99de412e Mon Sep 17 00:00:00 2001
From: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Date: Fri, 20 Jul 2018 09:53:33 +0200
Subject: mtd: nand: correct documentation for NAND_ECC_HW8_512

The documentation for this parameter said "6 bytes" when "8 bytes" was
intended; correct it.

Signed-off-by: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/driver-api/mtdnand.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/driver-api/mtdnand.rst b/Documentation/driver-api/mtdnand.rst
index dcd63599f700..c55a6034c397 100644
--- a/Documentation/driver-api/mtdnand.rst
+++ b/Documentation/driver-api/mtdnand.rst
@@ -374,7 +374,7 @@ The nand driver supports three different types of hardware ECC.
 
 -  NAND_ECC_HW8_512
 
-   Hardware ECC generator providing 6 bytes ECC per 512 byte.
+   Hardware ECC generator providing 8 bytes ECC per 512 byte.
 
 If your hardware generator has a different functionality add it at the
 appropriate place in nand_base.c
@@ -889,7 +889,7 @@ Use these constants to select the ECC algorithm::
     #define NAND_ECC_HW3_512    3
     /* Hardware ECC 6 byte ECC per 512 Byte data */
     #define NAND_ECC_HW6_512    4
-    /* Hardware ECC 6 byte ECC per 512 Byte data */
+    /* Hardware ECC 8 byte ECC per 512 Byte data */
     #define NAND_ECC_HW8_512    6
 
 
-- 
cgit v1.2.3


From fe3136f441411c2aeb4ffe29ef44b1a87c116775 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Sun, 22 Jul 2018 18:31:34 +0530
Subject: mm: Introduce new type vm_fault_t

We have introduce a new return type vm_fault_t for
fault, page_mkwrite and pfn_mkwrite handlers. Update
the document for the same

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/filesystems/Locking | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index 37bf0a9de75c..f64bbec3a8cf 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -532,9 +532,9 @@ More details about quota locking can be found in fs/dquot.c.
 prototypes:
 	void (*open)(struct vm_area_struct*);
 	void (*close)(struct vm_area_struct*);
-	int (*fault)(struct vm_area_struct*, struct vm_fault *);
-	int (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
-	int (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
+	vm_fault_t (*fault)(struct vm_area_struct*, struct vm_fault *);
+	vm_fault_t (*page_mkwrite)(struct vm_area_struct *, struct vm_fault *);
+	vm_fault_t (*pfn_mkwrite)(struct vm_area_struct *, struct vm_fault *);
 	int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
 
 locking rules:
-- 
cgit v1.2.3


From 6709514f266e9163f9f579006496fbc8bc986d80 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 11:09:00 +0800
Subject: bluetooth: bfusb: Replace GFP_ATOMIC with GFP_KERNEL in
 bfusb_send_frame()

bfusb_send_frame() is only set to hdev->send, and hdev->send() is never
called in atomic context.

bfusb_send_frame() calls bt_skb_alloc() with GFP_ATOMIC, which is not
necessary. GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/bfusb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c
index ab090a313a5f..0588639b899a 100644
--- a/drivers/bluetooth/bfusb.c
+++ b/drivers/bluetooth/bfusb.c
@@ -490,7 +490,7 @@ static int bfusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	count = skb->len;
 
 	/* Max HCI frame size seems to be 1511 + 1 */
-	nskb = bt_skb_alloc(count + 32, GFP_ATOMIC);
+	nskb = bt_skb_alloc(count + 32, GFP_KERNEL);
 	if (!nskb) {
 		BT_ERR("Can't allocate memory for new packet");
 		return -ENOMEM;
-- 
cgit v1.2.3


From 5f9c6580f6324e279417fc66e80ade0c42bfa9d9 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 11:17:35 +0800
Subject: bluetooth: bluecard_cs: Replace GFP_ATOMIC with GFP_KERNEL in
 bluecard_hci_set_baud_rate()

bluecard_hci_set_baud_rate() is never called in atomic context.

bluecard_hci_set_baud_rate() is only by bluecard_hci_open(), which is
set to hdev->open, and hdev->open() is never called in atomic context.

bluecard_hci_set_baud_rate() calls bt_skb_alloc() with GFP_ATOMIC,
which is not necessary. GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/bluecard_cs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/bluecard_cs.c b/drivers/bluetooth/bluecard_cs.c
index 82437a69f99c..cc6e56223656 100644
--- a/drivers/bluetooth/bluecard_cs.c
+++ b/drivers/bluetooth/bluecard_cs.c
@@ -565,7 +565,7 @@ static int bluecard_hci_set_baud_rate(struct hci_dev *hdev, int baud)
 	/* Ericsson baud rate command */
 	unsigned char cmd[] = { HCI_COMMAND_PKT, 0x09, 0xfc, 0x01, 0x03 };
 
-	skb = bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_ATOMIC);
+	skb = bt_skb_alloc(HCI_MAX_FRAME_SIZE, GFP_KERNEL);
 	if (!skb) {
 		BT_ERR("Can't allocate mem for new packet");
 		return -1;
-- 
cgit v1.2.3


From 478113e43162e409bbc6d79e87c2301728f26db2 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 11:24:02 +0800
Subject: bluetooth: bpa10x: Replace GFP_ATOMIC with GFP_KERNEL in
 bpa10x_send_frame()

bpa10x_send_frame() is only set to hdev->send, and hdev->send() is never
called in atomic context.

bpa10x_send_frame() calls usb_alloc_urb(), kmalloc() and usb_submit_urb()
with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/bpa10x.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/bluetooth/bpa10x.c b/drivers/bluetooth/bpa10x.c
index c6f7cc57db14..d1c2adf08576 100644
--- a/drivers/bluetooth/bpa10x.c
+++ b/drivers/bluetooth/bpa10x.c
@@ -289,7 +289,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	skb->dev = (void *) hdev;
 
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	urb = usb_alloc_urb(0, GFP_KERNEL);
 	if (!urb)
 		return -ENOMEM;
 
@@ -298,7 +298,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	switch (hci_skb_pkt_type(skb)) {
 	case HCI_COMMAND_PKT:
-		dr = kmalloc(sizeof(*dr), GFP_ATOMIC);
+		dr = kmalloc(sizeof(*dr), GFP_KERNEL);
 		if (!dr) {
 			usb_free_urb(urb);
 			return -ENOMEM;
@@ -343,7 +343,7 @@ static int bpa10x_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	usb_anchor_urb(urb, &data->tx_anchor);
 
-	err = usb_submit_urb(urb, GFP_ATOMIC);
+	err = usb_submit_urb(urb, GFP_KERNEL);
 	if (err < 0) {
 		bt_dev_err(hdev, "urb %p submission failed", urb);
 		kfree(urb->setup_packet);
-- 
cgit v1.2.3


From 436018eee5eaf1891793efca38ed9455fa21e16c Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 11:30:03 +0800
Subject: bluetooth: btmrvl_sdio: Replace GFP_ATOMIC with GFP_KERNEL in
 btmrvl_sdio_card_to_host()

btmrvl_sdio_card_to_host() is never called in atomic context.
It calls bt_skb_alloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btmrvl_sdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btmrvl_sdio.c b/drivers/bluetooth/btmrvl_sdio.c
index 888bac49a87b..fb3d03928460 100644
--- a/drivers/bluetooth/btmrvl_sdio.c
+++ b/drivers/bluetooth/btmrvl_sdio.c
@@ -718,7 +718,7 @@ static int btmrvl_sdio_card_to_host(struct btmrvl_private *priv)
 	}
 
 	/* Allocate buffer */
-	skb = bt_skb_alloc(num_blocks * blksz + BTSDIO_DMA_ALIGN, GFP_ATOMIC);
+	skb = bt_skb_alloc(num_blocks * blksz + BTSDIO_DMA_ALIGN, GFP_KERNEL);
 	if (!skb) {
 		BT_ERR("No free skb");
 		ret = -ENOMEM;
-- 
cgit v1.2.3


From cf07e3412668ac1d7a346a9b86c8a21e5cffd6b6 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 11:38:51 +0800
Subject: bluetooth: btusb: Replace GFP_ATOMIC with GFP_KERNEL in
 inject_cmd_complete()

inject_cmd_complete() is only called by btusb_send_frame_intel(),
which is set to hdev->send, and hdev->send() is never
called in atomic context.

inject_cmd_complete() calls bt_skb_alloc() with GFP_ATOMIC,
which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btusb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index fc39c2d343d7..572fd75fbcf6 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -1895,7 +1895,7 @@ static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode)
 	struct hci_event_hdr *hdr;
 	struct hci_ev_cmd_complete *evt;
 
-	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC);
+	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From f6ebfc24e78d99ebfa0f8d1761b1d77b733dcbb9 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 11:53:21 +0800
Subject: bluetooth: hci_intel: Replace GFP_ATOMIC with GFP_KERNEL in
 inject_cmd_complete()

inject_cmd_complete() is only called by intel_dequeue(),
which is never called in atomic context.

inject_cmd_complete() calls bt_skb_alloc() with GFP_ATOMIC,
which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/hci_intel.c b/drivers/bluetooth/hci_intel.c
index 7c166e3b308b..46ace321bf60 100644
--- a/drivers/bluetooth/hci_intel.c
+++ b/drivers/bluetooth/hci_intel.c
@@ -458,7 +458,7 @@ static int inject_cmd_complete(struct hci_dev *hdev, __u16 opcode)
 	struct hci_event_hdr *hdr;
 	struct hci_ev_cmd_complete *evt;
 
-	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_ATOMIC);
+	skb = bt_skb_alloc(sizeof(*hdr) + sizeof(*evt) + 1, GFP_KERNEL);
 	if (!skb)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 25a13e382de2b0f844cd6303e45f2b33c8fbabac Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 11:56:51 +0800
Subject: bluetooth: hci_qca: Replace GFP_ATOMIC with GFP_KERNEL

qca_open() and qca_set_baudrate() are never called in atomic context.

They call kzalloc() and bt_skb_alloc() with GFP_ATOMIC,
which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_qca.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 51790dd02afb..8431be3a837f 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -405,7 +405,7 @@ static int qca_open(struct hci_uart *hu)
 
 	BT_DBG("hu %p qca_open", hu);
 
-	qca = kzalloc(sizeof(struct qca_data), GFP_ATOMIC);
+	qca = kzalloc(sizeof(struct qca_data), GFP_KERNEL);
 	if (!qca)
 		return -ENOMEM;
 
@@ -891,7 +891,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 
 	cmd[4] = baudrate;
 
-	skb = bt_skb_alloc(sizeof(cmd), GFP_ATOMIC);
+	skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL);
 	if (!skb) {
 		bt_dev_err(hdev, "Failed to allocate baudrate packet");
 		return -ENOMEM;
-- 
cgit v1.2.3


From 65cfcc3897d7715a878b9f59736e7527ca27514f Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:24:55 -0700
Subject: xfs: check leaf attribute block freemap in verifier

Check the leaf attribute freemap when we're verifying the block.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_attr_leaf.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 8ff287979a8c..088ffcd22fa2 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -244,6 +244,8 @@ xfs_attr3_leaf_verify(
 	struct xfs_attr_leafblock	*leaf = bp->b_addr;
 	struct xfs_perag		*pag = bp->b_pag;
 	struct xfs_attr_leaf_entry	*entries;
+	uint16_t			end;
+	int				i;
 
 	xfs_attr3_leaf_hdr_from_disk(mp->m_attr_geo, &ichdr, leaf);
 
@@ -289,6 +291,26 @@ xfs_attr3_leaf_verify(
 	/* XXX: need to range check rest of attr header values */
 	/* XXX: hash order check? */
 
+	/*
+	 * Quickly check the freemap information.  Attribute data has to be
+	 * aligned to 4-byte boundaries, and likewise for the free space.
+	 */
+	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
+		if (ichdr.freemap[i].base > mp->m_attr_geo->blksize)
+			return __this_address;
+		if (ichdr.freemap[i].base & 0x3)
+			return __this_address;
+		if (ichdr.freemap[i].size > mp->m_attr_geo->blksize)
+			return __this_address;
+		if (ichdr.freemap[i].size & 0x3)
+			return __this_address;
+		end = ichdr.freemap[i].base + ichdr.freemap[i].size;
+		if (end < ichdr.freemap[i].base)
+			return __this_address;
+		if (end > mp->m_attr_geo->blksize)
+			return __this_address;
+	}
+
 	return NULL;
 }
 
-- 
cgit v1.2.3


From 81b549aa626b650bbf00423c084c0fd5581169b9 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:25:47 -0700
Subject: xfs: return from _defer_finish with a clean transaction

The following assertion was seen on generic/051:

XFS: Assertion failed: tp->t_firstblock == NULLFSBLOCK, file: fs/xfs/libxfs5
------------[ cut here ]------------
kernel BUG at fs/xfs/xfs_message.c:102!
invalid opcode: 0000 [#1] SMP PTI
CPU: 2 PID: 20757 Comm: fsstress Not tainted 4.18.0-rc4+ #3969
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.1-1 04/01/4
RIP: 0010:assfail+0x23/0x30
Code: c3 66 0f 1f 44 00 00 48 89 f1 41 89 d0 48 c7 c6 88 e0 8c 82 48 89 fa
RSP: 0018:ffff88012dc43c08 EFLAGS: 00010202
RAX: 0000000000000000 RBX: ffff88012dc43ca0 RCX: 0000000000000000
RDX: 00000000ffffffc0 RSI: 000000000000000a RDI: ffffffff828480eb
RBP: ffff88012aa92758 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: f000000000000000 R12: 0000000000000000
R13: ffff88012dc43d48 R14: ffff88013092e7e8 R15: 0000000000000014
FS:  00007f8d689b8e80(0000) GS:ffff88013fd00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f8d689c7000 CR3: 000000012ba6a000 CR4: 00000000000006e0
Call Trace:
 xfs_defer_init+0xff/0x160
 xfs_reflink_remap_extent+0x31b/0xa00
 xfs_reflink_remap_blocks+0xec/0x4a0
 xfs_reflink_remap_range+0x3a1/0x650
 xfs_file_dedupe_range+0x39/0x50
 vfs_dedupe_file_range+0x218/0x260
 do_vfs_ioctl+0x262/0x6a0
 ? __se_sys_newfstat+0x3c/0x60
 ksys_ioctl+0x35/0x60
 __x64_sys_ioctl+0x11/0x20
 do_syscall_64+0x4b/0x190
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

The root cause of the assertion failure is that xfs_defer_finish doesn't
roll the transaction after processing all the deferred items.  Therefore
it returns a dirty transaction to the caller, which leaves the caller at
risk of exceeding the transaction reservation if it logs more items.

Brian Foster's patchset to move the defer_ops firstblock into the
transaction requires t_firstblock == NULLFSBLOCK upon defer_ops
initialization, which is how this was noticed at all.

Reported-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_defer.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 2713e2d808a7..c4b0eaeb5190 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -424,6 +424,12 @@ xfs_defer_finish(
 			cleanup_fn(*tp, state, error);
 	}
 
+	/*
+	 * Roll the transaction once more to avoid returning to the caller
+	 * with a dirty transaction.
+	 */
+	if ((*tp)->t_flags & XFS_TRANS_DIRTY)
+		error = xfs_defer_trans_roll(tp, dop);
 out:
 	(*tp)->t_dfops = orig_dop;
 	if (error)
-- 
cgit v1.2.3


From 0b04b6b875b32f2b32263ba46d54d001e05724f9 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:26:31 -0700
Subject: xfs: trivial xfs_btree_del_cursor cleanups

The error argument to xfs_btree_del_cursor already understands the
"nonzero for error" semantics, so remove pointless error testing in the
callers and pass it directly.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_bmap.c         | 24 ++++++++----------------
 fs/xfs/libxfs/xfs_bmap_btree.c   |  2 +-
 fs/xfs/libxfs/xfs_ialloc.c       |  2 +-
 fs/xfs/libxfs/xfs_ialloc_btree.c |  2 +-
 fs/xfs/libxfs/xfs_refcount.c     |  2 +-
 fs/xfs/libxfs/xfs_rmap.c         | 18 +++---------------
 fs/xfs/scrub/bmap.c              |  5 ++---
 fs/xfs/scrub/repair.c            |  2 +-
 fs/xfs/xfs_discard.c             |  2 +-
 fs/xfs/xfs_fsmap.c               |  2 +-
 fs/xfs/xfs_itable.c              |  6 ++----
 fs/xfs/xfs_reflink.c             |  2 +-
 12 files changed, 23 insertions(+), 46 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 7b93b1e16ad9..6bc0cdff488e 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -961,8 +961,7 @@ xfs_bmap_add_attrfork_extents(
 					  XFS_DATA_FORK);
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 	return error;
 }
@@ -4447,8 +4446,7 @@ error0:
 		xfs_trans_log_inode(tp, ip, bma.logflags);
 
 	if (bma.cur) {
-		xfs_btree_del_cursor(bma.cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(bma.cur, error);
 	}
 	if (!error)
 		xfs_bmap_validate_ret(orig_bno, orig_len, orig_flags, orig_mval,
@@ -4542,10 +4540,8 @@ error0:
 
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
-	if (cur) {
-		xfs_btree_del_cursor(cur,
-				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
-	}
+	if (cur)
+		xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -5439,8 +5435,7 @@ error0:
 	if (cur) {
 		if (!error)
 			cur->bc_private.b.allocated = 0;
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 	return error;
 }
@@ -5700,8 +5695,7 @@ done:
 	*next_fsb = got.br_startoff;
 del_cursor:
 	if (cur)
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	return error;
@@ -5828,8 +5822,7 @@ xfs_bmap_insert_extents(
 	*next_fsb = got.br_startoff;
 del_cursor:
 	if (cur)
-		xfs_btree_del_cursor(cur,
-			error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	return error;
@@ -5945,8 +5938,7 @@ xfs_bmap_split_extent_at(
 del_cursor:
 	if (cur) {
 		cur->bc_private.b.allocated = 0;
-		xfs_btree_del_cursor(cur,
-				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 	}
 
 	if (logflags)
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 628ed82ca286..01489714a253 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -639,7 +639,7 @@ xfs_bmbt_change_owner(
 	cur->bc_private.b.flags |= XFS_BTCUR_BPRV_INVALID_OWNER;
 
 	error = xfs_btree_change_owner(cur, new_owner, buffer_list);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 811d36afd024..295304ad1bc1 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -2258,7 +2258,7 @@ xfs_imap_lookup(
 	}
 
 	xfs_trans_brelse(tp, agbp);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index a5237afec5ab..735a33252eb2 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -566,7 +566,7 @@ xfs_inobt_count_blocks(
 
 	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
 	error = xfs_btree_count_blocks(cur, tree_blocks);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	xfs_buf_relse(agbp);
 
 	return error;
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 2ecfb0518580..a2dfae67ade1 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1067,7 +1067,7 @@ xfs_refcount_finish_one_cleanup(
 	if (rcur == NULL)
 		return;
 	agbp = rcur->bc_private.a.agbp;
-	xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(rcur, error);
 	if (error)
 		xfs_trans_brelse(tp, agbp);
 }
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 8b2a2f81d110..fb266fa2cc45 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -670,14 +670,8 @@ xfs_rmap_free(
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
 
 	error = xfs_rmap_unmap(cur, bno, len, false, oinfo);
-	if (error)
-		goto out_error;
 
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	return 0;
-
-out_error:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -912,14 +906,8 @@ xfs_rmap_alloc(
 
 	cur = xfs_rmapbt_init_cursor(mp, tp, agbp, agno);
 	error = xfs_rmap_map(cur, bno, len, false, oinfo);
-	if (error)
-		goto out_error;
 
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	return 0;
-
-out_error:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -2156,7 +2144,7 @@ xfs_rmap_finish_one_cleanup(
 	if (rcur == NULL)
 		return;
 	agbp = rcur->bc_private.a.agbp;
-	xfs_btree_del_cursor(rcur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(rcur, error);
 	if (error)
 		xfs_trans_brelse(tp, agbp);
 }
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 3d08589f5c60..ebbfab173e97 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -404,8 +404,7 @@ xfs_scrub_bmap_btree(
 	cur = xfs_bmbt_init_cursor(mp, sc->tp, ip, whichfork);
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
 	error = xfs_scrub_btree(sc, cur, xfs_scrub_bmapbt_rec, &oinfo, info);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR :
-					  XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
@@ -514,7 +513,7 @@ xfs_scrub_bmap_check_ag_rmaps(
 	if (error == XFS_BTREE_QUERY_RANGE_ABORT)
 		error = 0;
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 out_agf:
 	xfs_trans_brelse(sc->tp, agf);
 	return error;
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 326be4e8b71e..35c589a04fac 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -1009,7 +1009,7 @@ xfs_repair_find_ag_btree_roots(
 
 	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
 	error = xfs_rmap_query_all(cur, xfs_repair_findroot_rmap, &ri);
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 
 	return error;
 }
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 678a5fcd7576..93f07edafd81 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -128,7 +128,7 @@ next_extent:
 	}
 
 out_del_cursor:
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	xfs_buf_relse(agbp);
 out_put_perag:
 	xfs_perag_put(pag);
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 297d7ce2901e..3d76a9e35870 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -219,7 +219,7 @@ xfs_getfsmap_is_shared(
 	error = xfs_refcount_find_shared(cur, rec->rm_startblock,
 			rec->rm_blockcount, &fbno, &flen, false);
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 24f4f1c555b5..65810827a8d0 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -458,8 +458,7 @@ xfs_bulkstat(
 		 * pending error, then we are done.
 		 */
 del_cursor:
-		xfs_btree_del_cursor(cur, error ?
-					  XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+		xfs_btree_del_cursor(cur, error);
 		xfs_buf_relse(agbp);
 		if (error)
 			break;
@@ -632,8 +631,7 @@ next_ag:
 
 	kmem_free(buffer);
 	if (cur)
-		xfs_btree_del_cursor(cur, (error ? XFS_BTREE_ERROR :
-					   XFS_BTREE_NOERROR));
+		xfs_btree_del_cursor(cur, error);
 	if (agbp)
 		xfs_buf_relse(agbp);
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 3143889097f1..406f79d44153 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -162,7 +162,7 @@ xfs_reflink_find_shared(
 	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
 			find_end_of_shared);
 
-	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 
 	xfs_trans_brelse(tp, agbp);
 	return error;
-- 
cgit v1.2.3


From ef97ef26d263fb65f0c7446a10cf93201dc0388c Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:29:10 -0700
Subject: xfs: clean up xfs_btree_del_cursor callers

Less trivial cleanups of the error argument to xfs_btree_del_cursor;
these require some minor code refactoring.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_refcount.c | 11 +++--------
 fs/xfs/scrub/repair.c        |  7 +++----
 2 files changed, 6 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index a2dfae67ade1..9ef1f440a6f2 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1675,11 +1675,11 @@ xfs_refcount_recover_cow_leftovers(
 	high.rc.rc_startblock = -1U;
 	error = xfs_btree_query_range(cur, &low, &high,
 			xfs_refcount_recover_extent, &debris);
-	if (error)
-		goto out_cursor;
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	xfs_btree_del_cursor(cur, error);
 	xfs_trans_brelse(tp, agbp);
 	xfs_trans_cancel(tp);
+	if (error)
+		goto out_free;
 
 	/* Now iterate the list to free the leftovers */
 	list_for_each_entry_safe(rr, n, &debris, rr_list) {
@@ -1727,11 +1727,6 @@ out_free:
 		kmem_free(rr);
 	}
 	return error;
-
-out_cursor:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	xfs_trans_brelse(tp, agbp);
-	goto out_trans;
 }
 
 /* Is there a record covering a given extent? */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 35c589a04fac..ea39e2bdc96a 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -747,9 +747,9 @@ xfs_repair_dispose_btree_block(
 
 	/* Can we find any other rmappings? */
 	error = xfs_rmap_has_other_keys(cur, agbno, 1, oinfo, &has_other_rmap);
+	xfs_btree_del_cursor(cur, error);
 	if (error)
-		goto out_cur;
-	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+		goto out_free;
 
 	/*
 	 * If there are other rmappings, this block is cross linked and must
@@ -779,8 +779,7 @@ xfs_repair_dispose_btree_block(
 		return xfs_trans_roll_inode(&sc->tp, sc->ip);
 	return xfs_repair_roll_ag_trans(sc);
 
-out_cur:
-	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+out_free:
 	if (agf_bp != sc->sa.agf_bp)
 		xfs_trans_brelse(sc->tp, agf_bp);
 	return error;
-- 
cgit v1.2.3


From c517b3aa02cff1dd688aa783b748e06c8aee1285 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:29:11 -0700
Subject: xfs: shorten xfs_scrub_ prefix

Shorten all the metadata checking xfs_scrub_ prefixes to xchk_.  After
this, the only xfs_scrub* symbols are the ones that pertain to both
scrub and repair.  Whitespace damage will be fixed in a subsequent
patch.  There are no functional changes.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/agheader.c | 318 ++++++++++++++++++++++++------------------------
 fs/xfs/scrub/alloc.c    |  56 ++++-----
 fs/xfs/scrub/attr.c     | 106 ++++++++--------
 fs/xfs/scrub/bmap.c     | 176 +++++++++++++--------------
 fs/xfs/scrub/btree.c    | 166 ++++++++++++-------------
 fs/xfs/scrub/btree.h    |  22 ++--
 fs/xfs/scrub/common.c   | 172 +++++++++++++-------------
 fs/xfs/scrub/common.h   | 102 ++++++++--------
 fs/xfs/scrub/dabtree.c  | 124 +++++++++----------
 fs/xfs/scrub/dabtree.h  |  14 +--
 fs/xfs/scrub/dir.c      | 170 +++++++++++++-------------
 fs/xfs/scrub/ialloc.c   | 138 ++++++++++-----------
 fs/xfs/scrub/inode.c    | 160 ++++++++++++------------
 fs/xfs/scrub/parent.c   |  62 +++++-----
 fs/xfs/scrub/quota.c    |  64 +++++-----
 fs/xfs/scrub/refcount.c | 114 ++++++++---------
 fs/xfs/scrub/repair.c   |   4 +-
 fs/xfs/scrub/rmap.c     |  78 ++++++------
 fs/xfs/scrub/rtbitmap.c |  30 ++---
 fs/xfs/scrub/scrub.c    | 142 ++++++++++-----------
 fs/xfs/scrub/scrub.h    |  82 ++++++-------
 fs/xfs/scrub/symlink.c  |  14 +--
 fs/xfs/scrub/trace.c    |   2 +-
 fs/xfs/scrub/trace.h    |  70 +++++------
 24 files changed, 1196 insertions(+), 1190 deletions(-)

diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 9bb0745f1ad2..c0625ec16d63 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -28,7 +28,7 @@
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_superblock_xref(
+xchk_superblock_xref(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*bp)
 {
@@ -43,15 +43,15 @@ xfs_scrub_superblock_xref(
 
 	agbno = XFS_SB_BLOCK(mp);
 
-	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
-	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
+	error = xchk_ag_init(sc, agno, &sc->sa);
+	if (!xchk_xref_process_error(sc, agno, agbno, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
@@ -65,7 +65,7 @@ xfs_scrub_superblock_xref(
  * sb 0 is ok and we can use its information to check everything else.
  */
 int
-xfs_scrub_superblock(
+xchk_superblock(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
@@ -98,7 +98,7 @@ xfs_scrub_superblock(
 	default:
 		break;
 	}
-	if (!xfs_scrub_process_error(sc, agno, XFS_SB_BLOCK(mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_SB_BLOCK(mp), &error))
 		return error;
 
 	sb = XFS_BUF_TO_SBP(bp);
@@ -110,46 +110,46 @@ xfs_scrub_superblock(
 	 * checked.
 	 */
 	if (sb->sb_blocksize != cpu_to_be32(mp->m_sb.sb_blocksize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_dblocks != cpu_to_be64(mp->m_sb.sb_dblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rblocks != cpu_to_be64(mp->m_sb.sb_rblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rextents != cpu_to_be64(mp->m_sb.sb_rextents))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (!uuid_equal(&sb->sb_uuid, &mp->m_sb.sb_uuid))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_logstart != cpu_to_be64(mp->m_sb.sb_logstart))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rootino != cpu_to_be64(mp->m_sb.sb_rootino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rbmino != cpu_to_be64(mp->m_sb.sb_rbmino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rsumino != cpu_to_be64(mp->m_sb.sb_rsumino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_rextsize != cpu_to_be32(mp->m_sb.sb_rextsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agblocks != cpu_to_be32(mp->m_sb.sb_agblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agcount != cpu_to_be32(mp->m_sb.sb_agcount))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rbmblocks != cpu_to_be32(mp->m_sb.sb_rbmblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logblocks != cpu_to_be32(mp->m_sb.sb_logblocks))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_versionnum bits that are set at mkfs time. */
 	vernum_mask = cpu_to_be16(~XFS_SB_VERSION_OKBITS |
@@ -163,7 +163,7 @@ xfs_scrub_superblock(
 				  XFS_SB_VERSION_DIRV2BIT);
 	if ((sb->sb_versionnum & vernum_mask) !=
 	    (cpu_to_be16(mp->m_sb.sb_versionnum) & vernum_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_versionnum bits that can be set after mkfs time. */
 	vernum_mask = cpu_to_be16(XFS_SB_VERSION_ATTRBIT |
@@ -171,40 +171,40 @@ xfs_scrub_superblock(
 				  XFS_SB_VERSION_QUOTABIT);
 	if ((sb->sb_versionnum & vernum_mask) !=
 	    (cpu_to_be16(mp->m_sb.sb_versionnum) & vernum_mask))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_sectsize != cpu_to_be16(mp->m_sb.sb_sectsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inodesize != cpu_to_be16(mp->m_sb.sb_inodesize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inopblock != cpu_to_be16(mp->m_sb.sb_inopblock))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (memcmp(sb->sb_fname, mp->m_sb.sb_fname, sizeof(sb->sb_fname)))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_blocklog != mp->m_sb.sb_blocklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_sectlog != mp->m_sb.sb_sectlog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inodelog != mp->m_sb.sb_inodelog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inopblog != mp->m_sb.sb_inopblog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_agblklog != mp->m_sb.sb_agblklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_rextslog != mp->m_sb.sb_rextslog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_imax_pct != mp->m_sb.sb_imax_pct)
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	/*
 	 * Skip the summary counters since we track them in memory anyway.
@@ -212,10 +212,10 @@ xfs_scrub_superblock(
 	 */
 
 	if (sb->sb_uquotino != cpu_to_be64(mp->m_sb.sb_uquotino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_gquotino != cpu_to_be64(mp->m_sb.sb_gquotino))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	/*
 	 * Skip the quota flags since repair will force quotacheck.
@@ -223,46 +223,46 @@ xfs_scrub_superblock(
 	 */
 
 	if (sb->sb_flags != mp->m_sb.sb_flags)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_shared_vn != mp->m_sb.sb_shared_vn)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_inoalignmt != cpu_to_be32(mp->m_sb.sb_inoalignmt))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_unit != cpu_to_be32(mp->m_sb.sb_unit))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_width != cpu_to_be32(mp->m_sb.sb_width))
-		xfs_scrub_block_set_preen(sc, bp);
+		xchk_block_set_preen(sc, bp);
 
 	if (sb->sb_dirblklog != mp->m_sb.sb_dirblklog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsectlog != mp->m_sb.sb_logsectlog)
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsectsize != cpu_to_be16(mp->m_sb.sb_logsectsize))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (sb->sb_logsunit != cpu_to_be32(mp->m_sb.sb_logsunit))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Do we see any invalid bits in sb_features2? */
 	if (!xfs_sb_version_hasmorebits(&mp->m_sb)) {
 		if (sb->sb_features2 != 0)
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	} else {
 		v2_ok = XFS_SB_VERSION2_OKBITS;
 		if (XFS_SB_VERSION_NUM(&mp->m_sb) >= XFS_SB_VERSION_5)
 			v2_ok |= XFS_SB_VERSION2_CRCBIT;
 
 		if (!!(sb->sb_features2 & cpu_to_be32(~v2_ok)))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		if (sb->sb_features2 != sb->sb_bad_features2)
-			xfs_scrub_block_set_preen(sc, bp);
+			xchk_block_set_preen(sc, bp);
 	}
 
 	/* Check sb_features2 flags that are set at mkfs time. */
@@ -272,26 +272,26 @@ xfs_scrub_superblock(
 				    XFS_SB_VERSION2_FTYPE);
 	if ((sb->sb_features2 & features_mask) !=
 	    (cpu_to_be32(mp->m_sb.sb_features2) & features_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	/* Check sb_features2 flags that can be set after mkfs time. */
 	features_mask = cpu_to_be32(XFS_SB_VERSION2_ATTR2BIT);
 	if ((sb->sb_features2 & features_mask) !=
 	    (cpu_to_be32(mp->m_sb.sb_features2) & features_mask))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
 	if (!xfs_sb_version_hascrc(&mp->m_sb)) {
 		/* all v5 fields must be zero */
 		if (memchr_inv(&sb->sb_features_compat, 0,
 				sizeof(struct xfs_dsb) -
 				offsetof(struct xfs_dsb, sb_features_compat)))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	} else {
 		/* Check compat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_COMPAT_UNKNOWN);
 		if ((sb->sb_features_compat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_compat) & features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check ro compat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_RO_COMPAT_UNKNOWN |
@@ -301,7 +301,7 @@ xfs_scrub_superblock(
 		if ((sb->sb_features_ro_compat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_ro_compat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check incompat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_INCOMPAT_UNKNOWN |
@@ -311,22 +311,22 @@ xfs_scrub_superblock(
 		if ((sb->sb_features_incompat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_incompat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Check log incompat flags; all are set at mkfs time. */
 		features_mask = cpu_to_be32(XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN);
 		if ((sb->sb_features_log_incompat & features_mask) !=
 		    (cpu_to_be32(mp->m_sb.sb_features_log_incompat) &
 		     features_mask))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		/* Don't care about sb_crc */
 
 		if (sb->sb_spino_align != cpu_to_be32(mp->m_sb.sb_spino_align))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 
 		if (sb->sb_pquotino != cpu_to_be64(mp->m_sb.sb_pquotino))
-			xfs_scrub_block_set_preen(sc, bp);
+			xchk_block_set_preen(sc, bp);
 
 		/* Don't care about sb_lsn */
 	}
@@ -334,15 +334,15 @@ xfs_scrub_superblock(
 	if (xfs_sb_version_hasmetauuid(&mp->m_sb)) {
 		/* The metadata UUID must be the same for all supers */
 		if (!uuid_equal(&sb->sb_meta_uuid, &mp->m_sb.sb_meta_uuid))
-			xfs_scrub_block_set_corrupt(sc, bp);
+			xchk_block_set_corrupt(sc, bp);
 	}
 
 	/* Everything else must be zero. */
 	if (memchr_inv(sb + 1, 0,
 			BBTOB(bp->b_length) - sizeof(struct xfs_dsb)))
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 
-	xfs_scrub_superblock_xref(sc, bp);
+	xchk_superblock_xref(sc, bp);
 
 	return error;
 }
@@ -351,7 +351,7 @@ xfs_scrub_superblock(
 
 /* Tally freespace record lengths. */
 STATIC int
-xfs_scrub_agf_record_bno_lengths(
+xchk_agf_record_bno_lengths(
 	struct xfs_btree_cur		*cur,
 	struct xfs_alloc_rec_incore	*rec,
 	void				*priv)
@@ -364,7 +364,7 @@ xfs_scrub_agf_record_bno_lengths(
 
 /* Check agf_freeblks */
 static inline void
-xfs_scrub_agf_xref_freeblks(
+xchk_agf_xref_freeblks(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
@@ -375,16 +375,16 @@ xfs_scrub_agf_xref_freeblks(
 		return;
 
 	error = xfs_alloc_query_all(sc->sa.bno_cur,
-			xfs_scrub_agf_record_bno_lengths, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+			xchk_agf_record_bno_lengths, &blocks);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	if (blocks != be32_to_cpu(agf->agf_freeblks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Cross reference the AGF with the cntbt (freespace by length btree) */
 static inline void
-xfs_scrub_agf_xref_cntbt(
+xchk_agf_xref_cntbt(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
@@ -398,25 +398,25 @@ xfs_scrub_agf_xref_cntbt(
 
 	/* Any freespace at all? */
 	error = xfs_alloc_lookup_le(sc->sa.cnt_cur, 0, -1U, &have);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	if (!have) {
 		if (agf->agf_freeblks != be32_to_cpu(0))
-			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 		return;
 	}
 
 	/* Check agf_longest */
 	error = xfs_alloc_get_rec(sc->sa.cnt_cur, &agbno, &blocks, &have);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	if (!have || blocks != be32_to_cpu(agf->agf_longest))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Check the btree block counts in the AGF against the btrees. */
 STATIC void
-xfs_scrub_agf_xref_btreeblks(
+xchk_agf_xref_btreeblks(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
@@ -428,11 +428,11 @@ xfs_scrub_agf_xref_btreeblks(
 	/* Check agf_rmap_blocks; set up for agf_btreeblks check */
 	if (sc->sa.rmap_cur) {
 		error = xfs_btree_count_blocks(sc->sa.rmap_cur, &blocks);
-		if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+		if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 			return;
 		btreeblks = blocks - 1;
 		if (blocks != be32_to_cpu(agf->agf_rmap_blocks))
-			xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 	} else {
 		btreeblks = 0;
 	}
@@ -447,22 +447,22 @@ xfs_scrub_agf_xref_btreeblks(
 
 	/* Check agf_btreeblks */
 	error = xfs_btree_count_blocks(sc->sa.bno_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	btreeblks += blocks - 1;
 
 	error = xfs_btree_count_blocks(sc->sa.cnt_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.cnt_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.cnt_cur))
 		return;
 	btreeblks += blocks - 1;
 
 	if (btreeblks != be32_to_cpu(agf->agf_btreeblks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Check agf_refcount_blocks against tree size */
 static inline void
-xfs_scrub_agf_xref_refcblks(
+xchk_agf_xref_refcblks(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
@@ -473,15 +473,15 @@ xfs_scrub_agf_xref_refcblks(
 		return;
 
 	error = xfs_btree_count_blocks(sc->sa.refc_cur, &blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (blocks != be32_to_cpu(agf->agf_refcount_blocks))
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agf_bp);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agf_xref(
+xchk_agf_xref(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_owner_info		oinfo;
@@ -494,26 +494,26 @@ xfs_scrub_agf_xref(
 
 	agbno = XFS_AGF_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_agf_xref_freeblks(sc);
-	xfs_scrub_agf_xref_cntbt(sc);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_agf_xref_freeblks(sc);
+	xchk_agf_xref_cntbt(sc);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_agf_xref_btreeblks(sc);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
-	xfs_scrub_agf_xref_refcblks(sc);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_agf_xref_btreeblks(sc);
+	xchk_xref_is_not_shared(sc, agbno, 1);
+	xchk_agf_xref_refcblks(sc);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGF. */
 int
-xfs_scrub_agf(
+xchk_agf(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
@@ -529,54 +529,54 @@ xfs_scrub_agf(
 	int				error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGF_BLOCK(sc->mp), &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agf_bp);
+	xchk_buffer_recheck(sc, sc->sa.agf_bp);
 
 	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agf->agf_length);
 	if (eoag != xfs_ag_block_count(mp, agno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	/* Check the AGF btree roots and levels */
 	agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_BNO]);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_CNT]);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 	if (xfs_sb_version_hasrmapbt(&mp->m_sb)) {
 		agbno = be32_to_cpu(agf->agf_roots[XFS_BTNUM_RMAP]);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 		level = be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAP]);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	}
 
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
 		agbno = be32_to_cpu(agf->agf_refcount_root);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
 		level = be32_to_cpu(agf->agf_refcount_level);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 	}
 
 	/* Check the AGFL counters */
@@ -588,16 +588,16 @@ xfs_scrub_agf(
 	else
 		fl_count = xfs_agfl_size(mp) - agfl_first + agfl_last + 1;
 	if (agfl_count != 0 && fl_count != agfl_count)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 
-	xfs_scrub_agf_xref(sc);
+	xchk_agf_xref(sc);
 out:
 	return error;
 }
 
 /* AGFL */
 
-struct xfs_scrub_agfl_info {
+struct xchk_agfl_info {
 	struct xfs_owner_info		oinfo;
 	unsigned int			sz_entries;
 	unsigned int			nr_entries;
@@ -607,7 +607,7 @@ struct xfs_scrub_agfl_info {
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agfl_block_xref(
+xchk_agfl_block_xref(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	struct xfs_owner_info		*oinfo)
@@ -615,20 +615,20 @@ xfs_scrub_agfl_block_xref(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 }
 
 /* Scrub an AGFL block. */
 STATIC int
-xfs_scrub_agfl_block(
+xchk_agfl_block(
 	struct xfs_mount		*mp,
 	xfs_agblock_t			agbno,
 	void				*priv)
 {
-	struct xfs_scrub_agfl_info	*sai = priv;
+	struct xchk_agfl_info		*sai = priv;
 	struct xfs_scrub_context	*sc = sai->sc;
 	xfs_agnumber_t			agno = sc->sa.agno;
 
@@ -636,9 +636,9 @@ xfs_scrub_agfl_block(
 	    sai->nr_entries < sai->sz_entries)
 		sai->entries[sai->nr_entries++] = agbno;
 	else
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agfl_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agfl_bp);
 
-	xfs_scrub_agfl_block_xref(sc, agbno, priv);
+	xchk_agfl_block_xref(sc, agbno, priv);
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return XFS_BTREE_QUERY_RANGE_ABORT;
@@ -647,7 +647,7 @@ xfs_scrub_agfl_block(
 }
 
 static int
-xfs_scrub_agblock_cmp(
+xchk_agblock_cmp(
 	const void		*pa,
 	const void		*pb)
 {
@@ -659,7 +659,7 @@ xfs_scrub_agblock_cmp(
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agfl_xref(
+xchk_agfl_xref(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_owner_info		oinfo;
@@ -672,15 +672,15 @@ xfs_scrub_agfl_xref(
 
 	agbno = XFS_AGFL_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/*
 	 * Scrub teardown will take care of sc->sa for us.  Leave sc->sa
@@ -690,10 +690,10 @@ xfs_scrub_agfl_xref(
 
 /* Scrub the AGFL. */
 int
-xfs_scrub_agfl(
+xchk_agfl(
 	struct xfs_scrub_context	*sc)
 {
-	struct xfs_scrub_agfl_info	sai;
+	struct xchk_agfl_info		sai;
 	struct xfs_agf			*agf;
 	xfs_agnumber_t			agno;
 	unsigned int			agflcount;
@@ -701,15 +701,15 @@ xfs_scrub_agfl(
 	int				error;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGFL_BLOCK(sc->mp), &error))
 		goto out;
 	if (!sc->sa.agf_bp)
 		return -EFSCORRUPTED;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agfl_bp);
+	xchk_buffer_recheck(sc, sc->sa.agfl_bp);
 
-	xfs_scrub_agfl_xref(sc);
+	xchk_agfl_xref(sc);
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
@@ -718,7 +718,7 @@ xfs_scrub_agfl(
 	agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	agflcount = be32_to_cpu(agf->agf_flcount);
 	if (agflcount > xfs_agfl_size(sc->mp)) {
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 		goto out;
 	}
 	memset(&sai, 0, sizeof(sai));
@@ -734,7 +734,7 @@ xfs_scrub_agfl(
 	/* Check the blocks in the AGFL. */
 	xfs_rmap_ag_owner(&sai.oinfo, XFS_RMAP_OWN_AG);
 	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(sc->sa.agf_bp),
-			sc->sa.agfl_bp, xfs_scrub_agfl_block, &sai);
+			sc->sa.agfl_bp, xchk_agfl_block, &sai);
 	if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
 		error = 0;
 		goto out_free;
@@ -743,16 +743,16 @@ xfs_scrub_agfl(
 		goto out_free;
 
 	if (agflcount != sai.nr_entries) {
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 		goto out_free;
 	}
 
 	/* Sort entries, check for duplicates. */
 	sort(sai.entries, sai.nr_entries, sizeof(sai.entries[0]),
-			xfs_scrub_agblock_cmp, NULL);
+			xchk_agblock_cmp, NULL);
 	for (i = 1; i < sai.nr_entries; i++) {
 		if (sai.entries[i] == sai.entries[i - 1]) {
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agf_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agf_bp);
 			break;
 		}
 	}
@@ -767,7 +767,7 @@ out:
 
 /* Check agi_count/agi_freecount */
 static inline void
-xfs_scrub_agi_xref_icounts(
+xchk_agi_xref_icounts(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_agi			*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
@@ -779,16 +779,16 @@ xfs_scrub_agi_xref_icounts(
 		return;
 
 	error = xfs_ialloc_count_inodes(sc->sa.ino_cur, &icount, &freecount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.ino_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.ino_cur))
 		return;
 	if (be32_to_cpu(agi->agi_count) != icount ||
 	    be32_to_cpu(agi->agi_freecount) != freecount)
-		xfs_scrub_block_xref_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_xref_set_corrupt(sc, sc->sa.agi_bp);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_agi_xref(
+xchk_agi_xref(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_owner_info		oinfo;
@@ -801,23 +801,23 @@ xfs_scrub_agi_xref(
 
 	agbno = XFS_AGI_BLOCK(mp);
 
-	error = xfs_scrub_ag_btcur_init(sc, &sc->sa);
+	error = xchk_ag_btcur_init(sc, &sc->sa);
 	if (error)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, 1);
-	xfs_scrub_agi_xref_icounts(sc);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_xref_is_not_inode_chunk(sc, agbno, 1);
+	xchk_agi_xref_icounts(sc);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_FS);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
 
 	/* scrub teardown will take care of sc->sa for us */
 }
 
 /* Scrub the AGI. */
 int
-xfs_scrub_agi(
+xchk_agi(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
@@ -834,36 +834,36 @@ xfs_scrub_agi(
 	int				error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sc->sa.agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
 			&sc->sa.agf_bp, &sc->sa.agfl_bp);
-	if (!xfs_scrub_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
+	if (!xchk_process_error(sc, agno, XFS_AGI_BLOCK(sc->mp), &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, sc->sa.agi_bp);
+	xchk_buffer_recheck(sc, sc->sa.agi_bp);
 
 	agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
 
 	/* Check the AG length */
 	eoag = be32_to_cpu(agi->agi_length);
 	if (eoag != xfs_ag_block_count(mp, agno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check btree roots and levels */
 	agbno = be32_to_cpu(agi->agi_root);
 	if (!xfs_verify_agbno(mp, agno, agbno))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	level = be32_to_cpu(agi->agi_level);
 	if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	if (xfs_sb_version_hasfinobt(&mp->m_sb)) {
 		agbno = be32_to_cpu(agi->agi_free_root);
 		if (!xfs_verify_agbno(mp, agno, agbno))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 		level = be32_to_cpu(agi->agi_free_level);
 		if (level <= 0 || level > XFS_BTREE_MAXLEVELS)
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 	}
 
 	/* Check inode counters */
@@ -871,16 +871,16 @@ xfs_scrub_agi(
 	icount = be32_to_cpu(agi->agi_count);
 	if (icount > last_agino - first_agino + 1 ||
 	    icount < be32_to_cpu(agi->agi_freecount))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check inode pointers */
 	agino = be32_to_cpu(agi->agi_newino);
 	if (agino != NULLAGINO && !xfs_verify_agino(mp, agno, agino))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	agino = be32_to_cpu(agi->agi_dirino);
 	if (agino != NULLAGINO && !xfs_verify_agino(mp, agno, agino))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
 	/* Check unlinked inode buckets */
 	for (i = 0; i < XFS_AGI_UNLINKED_BUCKETS; i++) {
@@ -888,13 +888,13 @@ xfs_scrub_agi(
 		if (agino == NULLAGINO)
 			continue;
 		if (!xfs_verify_agino(mp, agno, agino))
-			xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+			xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 	}
 
 	if (agi->agi_pad32 != cpu_to_be32(0))
-		xfs_scrub_block_set_corrupt(sc, sc->sa.agi_bp);
+		xchk_block_set_corrupt(sc, sc->sa.agi_bp);
 
-	xfs_scrub_agi_xref(sc);
+	xchk_agi_xref(sc);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 50e4f7fa06f0..1f6e3a6a1fdd 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -28,11 +28,11 @@
  * Set us up to scrub free space btrees.
  */
 int
-xfs_scrub_setup_ag_allocbt(
+xchk_setup_ag_allocbt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Free space btree scrubber. */
@@ -41,7 +41,7 @@ xfs_scrub_setup_ag_allocbt(
  * bnobt/cntbt record, respectively.
  */
 STATIC void
-xfs_scrub_allocbt_xref_other(
+xchk_allocbt_xref_other(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
@@ -56,32 +56,32 @@ xfs_scrub_allocbt_xref_other(
 		pcur = &sc->sa.cnt_cur;
 	else
 		pcur = &sc->sa.bno_cur;
-	if (!*pcur || xfs_scrub_skip_xref(sc->sm))
+	if (!*pcur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_lookup_le(*pcur, agbno, len, &has_otherrec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (!has_otherrec) {
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 		return;
 	}
 
 	error = xfs_alloc_get_rec(*pcur, &fbno, &flen, &has_otherrec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (!has_otherrec) {
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 		return;
 	}
 
 	if (fbno != agbno || flen != len)
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_allocbt_xref(
+xchk_allocbt_xref(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
@@ -89,16 +89,16 @@ xfs_scrub_allocbt_xref(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_allocbt_xref_other(sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
-	xfs_scrub_xref_has_no_owner(sc, agbno, len);
-	xfs_scrub_xref_is_not_shared(sc, agbno, len);
+	xchk_allocbt_xref_other(sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(sc, agbno, len);
+	xchk_xref_has_no_owner(sc, agbno, len);
+	xchk_xref_is_not_shared(sc, agbno, len);
 }
 
 /* Scrub a bnobt/cntbt record. */
 STATIC int
-xfs_scrub_allocbt_rec(
-	struct xfs_scrub_btree		*bs,
+xchk_allocbt_rec(
+	struct xchk_btree		*bs,
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
@@ -113,16 +113,16 @@ xfs_scrub_allocbt_rec(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_allocbt_xref(bs->sc, bno, len);
+	xchk_allocbt_xref(bs->sc, bno, len);
 
 	return error;
 }
 
 /* Scrub the freespace btrees for some AG. */
 STATIC int
-xfs_scrub_allocbt(
+xchk_allocbt(
 	struct xfs_scrub_context	*sc,
 	xfs_btnum_t			which)
 {
@@ -131,26 +131,26 @@ xfs_scrub_allocbt(
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
 	cur = which == XFS_BTNUM_BNO ? sc->sa.bno_cur : sc->sa.cnt_cur;
-	return xfs_scrub_btree(sc, cur, xfs_scrub_allocbt_rec, &oinfo, NULL);
+	return xchk_btree(sc, cur, xchk_allocbt_rec, &oinfo, NULL);
 }
 
 int
-xfs_scrub_bnobt(
+xchk_bnobt(
 	struct xfs_scrub_context	*sc)
 {
-	return xfs_scrub_allocbt(sc, XFS_BTNUM_BNO);
+	return xchk_allocbt(sc, XFS_BTNUM_BNO);
 }
 
 int
-xfs_scrub_cntbt(
+xchk_cntbt(
 	struct xfs_scrub_context	*sc)
 {
-	return xfs_scrub_allocbt(sc, XFS_BTNUM_CNT);
+	return xchk_allocbt(sc, XFS_BTNUM_CNT);
 }
 
 /* xref check that the extent is not free */
 void
-xfs_scrub_xref_is_used_space(
+xchk_xref_is_used_space(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
@@ -158,12 +158,12 @@ xfs_scrub_xref_is_used_space(
 	bool				is_freesp;
 	int				error;
 
-	if (!sc->sa.bno_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.bno_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_alloc_has_record(sc->sa.bno_cur, agbno, len, &is_freesp);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.bno_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.bno_cur))
 		return;
 	if (is_freesp)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.bno_cur, 0);
 }
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index de51cf8a8516..0068bebddf3e 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -32,7 +32,7 @@
 
 /* Set us up to scrub an inode's extended attributes. */
 int
-xfs_scrub_setup_xattr(
+xchk_setup_xattr(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
@@ -50,12 +50,12 @@ xfs_scrub_setup_xattr(
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Extended Attributes */
 
-struct xfs_scrub_xattr {
+struct xchk_xattr {
 	struct xfs_attr_list_context	context;
 	struct xfs_scrub_context	*sc;
 };
@@ -69,22 +69,22 @@ struct xfs_scrub_xattr {
  * or if we get more or less data than we expected.
  */
 static void
-xfs_scrub_xattr_listent(
+xchk_xattr_listent(
 	struct xfs_attr_list_context	*context,
 	int				flags,
 	unsigned char			*name,
 	int				namelen,
 	int				valuelen)
 {
-	struct xfs_scrub_xattr		*sx;
+	struct xchk_xattr		*sx;
 	struct xfs_da_args		args = { NULL };
 	int				error = 0;
 
-	sx = container_of(context, struct xfs_scrub_xattr, context);
+	sx = container_of(context, struct xchk_xattr, context);
 
 	if (flags & XFS_ATTR_INCOMPLETE) {
 		/* Incomplete attr key, just mark the inode for preening. */
-		xfs_scrub_ino_set_preen(sx->sc, context->dp->i_ino);
+		xchk_ino_set_preen(sx->sc, context->dp->i_ino);
 		return;
 	}
 
@@ -106,11 +106,11 @@ xfs_scrub_xattr_listent(
 	error = xfs_attr_get_ilocked(context->dp, &args);
 	if (error == -EEXIST)
 		error = 0;
-	if (!xfs_scrub_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
+	if (!xchk_fblock_process_error(sx->sc, XFS_ATTR_FORK, args.blkno,
 			&error))
 		goto fail_xref;
 	if (args.valuelen != valuelen)
-		xfs_scrub_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
+		xchk_fblock_set_corrupt(sx->sc, XFS_ATTR_FORK,
 					     args.blkno);
 fail_xref:
 	if (sx->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -126,7 +126,7 @@ fail_xref:
  * the smallest address
  */
 STATIC bool
-xfs_scrub_xattr_set_map(
+xchk_xattr_set_map(
 	struct xfs_scrub_context	*sc,
 	unsigned long			*map,
 	unsigned int			start,
@@ -154,7 +154,7 @@ xfs_scrub_xattr_set_map(
  * attr freemap has problems or points to used space.
  */
 STATIC bool
-xfs_scrub_xattr_check_freemap(
+xchk_xattr_check_freemap(
 	struct xfs_scrub_context	*sc,
 	unsigned long			*map,
 	struct xfs_attr3_icleaf_hdr	*leafhdr)
@@ -168,7 +168,7 @@ xfs_scrub_xattr_check_freemap(
 	freemap = (unsigned long *)sc->buf + BITS_TO_LONGS(mapsize);
 	bitmap_zero(freemap, mapsize);
 	for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) {
-		if (!xfs_scrub_xattr_set_map(sc, freemap,
+		if (!xchk_xattr_set_map(sc, freemap,
 				leafhdr->freemap[i].base,
 				leafhdr->freemap[i].size))
 			return false;
@@ -184,8 +184,8 @@ xfs_scrub_xattr_check_freemap(
  * Returns the number of bytes used for the name/value data.
  */
 STATIC void
-xfs_scrub_xattr_entry(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_entry(
+	struct xchk_da_btree		*ds,
 	int				level,
 	char				*buf_end,
 	struct xfs_attr_leafblock	*leaf,
@@ -204,17 +204,17 @@ xfs_scrub_xattr_entry(
 	unsigned int			namesize;
 
 	if (ent->pad2 != 0)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	/* Hash values in order? */
 	if (be32_to_cpu(ent->hashval) < *last_hashval)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	*last_hashval = be32_to_cpu(ent->hashval);
 
 	nameidx = be16_to_cpu(ent->nameidx);
 	if (nameidx < leafhdr->firstused ||
 	    nameidx >= mp->m_attr_geo->blksize) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return;
 	}
 
@@ -225,27 +225,27 @@ xfs_scrub_xattr_entry(
 				be16_to_cpu(lentry->valuelen));
 		name_end = (char *)lentry + namesize;
 		if (lentry->namelen == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	} else {
 		rentry = xfs_attr3_leaf_name_remote(leaf, idx);
 		namesize = xfs_attr_leaf_entsize_remote(rentry->namelen);
 		name_end = (char *)rentry + namesize;
 		if (rentry->namelen == 0 || rentry->valueblk == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 	if (name_end > buf_end)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
-	if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, nameidx, namesize))
-		xfs_scrub_da_set_corrupt(ds, level);
+	if (!xchk_xattr_set_map(ds->sc, usedmap, nameidx, namesize))
+		xchk_da_set_corrupt(ds, level);
 	if (!(ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		*usedbytes += namesize;
 }
 
 /* Scrub an attribute leaf. */
 STATIC int
-xfs_scrub_xattr_block(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_block(
+	struct xchk_da_btree		*ds,
 	int				level)
 {
 	struct xfs_attr3_icleaf_hdr	leafhdr;
@@ -275,10 +275,10 @@ xfs_scrub_xattr_block(
 
 		if (leaf->hdr.pad1 != 0 || leaf->hdr.pad2 != 0 ||
 		    leaf->hdr.info.hdr.pad != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	} else {
 		if (leaf->hdr.pad1 != 0 || leaf->hdr.info.pad != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 
 	/* Check the leaf header */
@@ -286,44 +286,44 @@ xfs_scrub_xattr_block(
 	hdrsize = xfs_attr3_leaf_hdr_size(leaf);
 
 	if (leafhdr.usedbytes > mp->m_attr_geo->blksize)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (leafhdr.firstused > mp->m_attr_geo->blksize)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (leafhdr.firstused < hdrsize)
-		xfs_scrub_da_set_corrupt(ds, level);
-	if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, 0, hdrsize))
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
+	if (!xchk_xattr_set_map(ds->sc, usedmap, 0, hdrsize))
+		xchk_da_set_corrupt(ds, level);
 
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
 	entries = xfs_attr3_leaf_entryp(leaf);
 	if ((char *)&entries[leafhdr.count] > (char *)leaf + leafhdr.firstused)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	buf_end = (char *)bp->b_addr + mp->m_attr_geo->blksize;
 	for (i = 0, ent = entries; i < leafhdr.count; ent++, i++) {
 		/* Mark the leaf entry itself. */
 		off = (char *)ent - (char *)leaf;
-		if (!xfs_scrub_xattr_set_map(ds->sc, usedmap, off,
+		if (!xchk_xattr_set_map(ds->sc, usedmap, off,
 				sizeof(xfs_attr_leaf_entry_t))) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 
 		/* Check the entry and nameval. */
-		xfs_scrub_xattr_entry(ds, level, buf_end, leaf, &leafhdr,
+		xchk_xattr_entry(ds, level, buf_end, leaf, &leafhdr,
 				usedmap, ent, i, &usedbytes, &last_hashval);
 
 		if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out;
 	}
 
-	if (!xfs_scrub_xattr_check_freemap(ds->sc, usedmap, &leafhdr))
-		xfs_scrub_da_set_corrupt(ds, level);
+	if (!xchk_xattr_check_freemap(ds->sc, usedmap, &leafhdr))
+		xchk_da_set_corrupt(ds, level);
 
 	if (leafhdr.usedbytes != usedbytes)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 out:
 	return 0;
@@ -331,8 +331,8 @@ out:
 
 /* Scrub a attribute btree record. */
 STATIC int
-xfs_scrub_xattr_rec(
-	struct xfs_scrub_da_btree	*ds,
+xchk_xattr_rec(
+	struct xchk_da_btree		*ds,
 	int				level,
 	void				*rec)
 {
@@ -352,14 +352,14 @@ xfs_scrub_xattr_rec(
 	blk = &ds->state->path.blk[level];
 
 	/* Check the whole block, if necessary. */
-	error = xfs_scrub_xattr_block(ds, level);
+	error = xchk_xattr_block(ds, level);
 	if (error)
 		goto out;
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
 	/* Check the hash of the entry. */
-	error = xfs_scrub_da_btree_hash(ds, level, &ent->hashval);
+	error = xchk_da_btree_hash(ds, level, &ent->hashval);
 	if (error)
 		goto out;
 
@@ -368,7 +368,7 @@ xfs_scrub_xattr_rec(
 	hdrsize = xfs_attr3_leaf_hdr_size(bp->b_addr);
 	nameidx = be16_to_cpu(ent->nameidx);
 	if (nameidx < hdrsize || nameidx >= mp->m_attr_geo->blksize) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out;
 	}
 
@@ -377,12 +377,12 @@ xfs_scrub_xattr_rec(
 	badflags = ~(XFS_ATTR_LOCAL | XFS_ATTR_ROOT | XFS_ATTR_SECURE |
 			XFS_ATTR_INCOMPLETE);
 	if ((ent->flags & badflags) != 0)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	if (ent->flags & XFS_ATTR_LOCAL) {
 		lentry = (struct xfs_attr_leaf_name_local *)
 				(((char *)bp->b_addr) + nameidx);
 		if (lentry->namelen <= 0) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 		calc_hash = xfs_da_hashname(lentry->nameval, lentry->namelen);
@@ -390,13 +390,13 @@ xfs_scrub_xattr_rec(
 		rentry = (struct xfs_attr_leaf_name_remote *)
 				(((char *)bp->b_addr) + nameidx);
 		if (rentry->namelen <= 0) {
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 			goto out;
 		}
 		calc_hash = xfs_da_hashname(rentry->name, rentry->namelen);
 	}
 	if (calc_hash != hash)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 out:
 	return error;
@@ -404,10 +404,10 @@ out:
 
 /* Scrub the extended attribute metadata. */
 int
-xfs_scrub_xattr(
+xchk_xattr(
 	struct xfs_scrub_context	*sc)
 {
-	struct xfs_scrub_xattr		sx;
+	struct xchk_xattr		sx;
 	struct attrlist_cursor_kern	cursor = { 0 };
 	xfs_dablk_t			last_checked = -1U;
 	int				error = 0;
@@ -417,7 +417,7 @@ xfs_scrub_xattr(
 
 	memset(&sx, 0, sizeof(sx));
 	/* Check attribute tree structure */
-	error = xfs_scrub_da_btree(sc, XFS_ATTR_FORK, xfs_scrub_xattr_rec,
+	error = xchk_da_btree(sc, XFS_ATTR_FORK, xchk_xattr_rec,
 			&last_checked);
 	if (error)
 		goto out;
@@ -429,7 +429,7 @@ xfs_scrub_xattr(
 	sx.context.dp = sc->ip;
 	sx.context.cursor = &cursor;
 	sx.context.resynch = 1;
-	sx.context.put_listent = xfs_scrub_xattr_listent;
+	sx.context.put_listent = xchk_xattr_listent;
 	sx.context.tp = sc->tp;
 	sx.context.flags = ATTR_INCOMPLETE;
 	sx.sc = sc;
@@ -438,7 +438,7 @@ xfs_scrub_xattr(
 	 * Look up every xattr in this file by name.
 	 *
 	 * Use the backend implementation of xfs_attr_list to call
-	 * xfs_scrub_xattr_listent on every attribute key in this inode.
+	 * xchk_xattr_listent on every attribute key in this inode.
 	 * In other words, we use the same iterator/callback mechanism
 	 * that listattr uses to scrub extended attributes, though in our
 	 * _listent function, we check the value of the attribute.
@@ -451,7 +451,7 @@ xfs_scrub_xattr(
 	 * locking order.
 	 */
 	error = xfs_attr_list_int_ilocked(&sx.context);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_ATTR_FORK, 0, &error))
 		goto out;
 out:
 	return error;
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index ebbfab173e97..19cfbd3910a2 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -33,13 +33,13 @@
 
 /* Set us up with an inode's bmap. */
 int
-xfs_scrub_setup_inode_bmap(
+xchk_setup_inode_bmap(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
 	int				error;
 
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	if (error)
 		goto out;
 
@@ -60,7 +60,7 @@ xfs_scrub_setup_inode_bmap(
 	}
 
 	/* Got the inode, lock it and we're ready to go. */
-	error = xfs_scrub_trans_alloc(sc, 0);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -78,7 +78,7 @@ out:
  * is in btree format.
  */
 
-struct xfs_scrub_bmap_info {
+struct xchk_bmap_info {
 	struct xfs_scrub_context	*sc;
 	xfs_fileoff_t			lastoff;
 	bool				is_rt;
@@ -88,8 +88,8 @@ struct xfs_scrub_bmap_info {
 
 /* Look for a corresponding rmap for this irec. */
 static inline bool
-xfs_scrub_bmap_get_rmap(
-	struct xfs_scrub_bmap_info	*info,
+xchk_bmap_get_rmap(
+	struct xchk_bmap_info		*info,
 	struct xfs_bmbt_irec		*irec,
 	xfs_agblock_t			agbno,
 	uint64_t			owner,
@@ -120,7 +120,7 @@ xfs_scrub_bmap_get_rmap(
 	if (info->is_shared) {
 		error = xfs_rmap_lookup_le_range(info->sc->sa.rmap_cur, agbno,
 				owner, offset, rflags, rmap, &has_rmap);
-		if (!xfs_scrub_should_check_xref(info->sc, &error,
+		if (!xchk_should_check_xref(info->sc, &error,
 				&info->sc->sa.rmap_cur))
 			return false;
 		goto out;
@@ -131,28 +131,28 @@ xfs_scrub_bmap_get_rmap(
 	 */
 	error = xfs_rmap_lookup_le(info->sc->sa.rmap_cur, agbno, 0, owner,
 			offset, rflags, &has_rmap);
-	if (!xfs_scrub_should_check_xref(info->sc, &error,
+	if (!xchk_should_check_xref(info->sc, &error,
 			&info->sc->sa.rmap_cur))
 		return false;
 	if (!has_rmap)
 		goto out;
 
 	error = xfs_rmap_get_rec(info->sc->sa.rmap_cur, rmap, &has_rmap);
-	if (!xfs_scrub_should_check_xref(info->sc, &error,
+	if (!xchk_should_check_xref(info->sc, &error,
 			&info->sc->sa.rmap_cur))
 		return false;
 
 out:
 	if (!has_rmap)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 			irec->br_startoff);
 	return has_rmap;
 }
 
 /* Make sure that we have rmapbt records for this extent. */
 STATIC void
-xfs_scrub_bmap_xref_rmap(
-	struct xfs_scrub_bmap_info	*info,
+xchk_bmap_xref_rmap(
+	struct xchk_bmap_info		*info,
 	struct xfs_bmbt_irec		*irec,
 	xfs_agblock_t			agbno)
 {
@@ -160,7 +160,7 @@ xfs_scrub_bmap_xref_rmap(
 	unsigned long long		rmap_end;
 	uint64_t			owner;
 
-	if (!info->sc->sa.rmap_cur || xfs_scrub_skip_xref(info->sc->sm))
+	if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm))
 		return;
 
 	if (info->whichfork == XFS_COW_FORK)
@@ -169,14 +169,14 @@ xfs_scrub_bmap_xref_rmap(
 		owner = info->sc->ip->i_ino;
 
 	/* Find the rmap record for this irec. */
-	if (!xfs_scrub_bmap_get_rmap(info, irec, agbno, owner, &rmap))
+	if (!xchk_bmap_get_rmap(info, irec, agbno, owner, &rmap))
 		return;
 
 	/* Check the rmap. */
 	rmap_end = (unsigned long long)rmap.rm_startblock + rmap.rm_blockcount;
 	if (rmap.rm_startblock > agbno ||
 	    agbno + irec->br_blockcount > rmap_end)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -189,12 +189,12 @@ xfs_scrub_bmap_xref_rmap(
 				rmap.rm_blockcount;
 		if (rmap.rm_offset > irec->br_startoff ||
 		    irec->br_startoff + irec->br_blockcount > rmap_end)
-			xfs_scrub_fblock_xref_set_corrupt(info->sc,
+			xchk_fblock_xref_set_corrupt(info->sc,
 					info->whichfork, irec->br_startoff);
 	}
 
 	if (rmap.rm_owner != owner)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -207,22 +207,22 @@ xfs_scrub_bmap_xref_rmap(
 	if (owner != XFS_RMAP_OWN_COW &&
 	    irec->br_state == XFS_EXT_UNWRITTEN &&
 	    !(rmap.rm_flags & XFS_RMAP_UNWRITTEN))
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	if (info->whichfork == XFS_ATTR_FORK &&
 	    !(rmap.rm_flags & XFS_RMAP_ATTR_FORK))
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (rmap.rm_flags & XFS_RMAP_BMBT_BLOCK)
-		xfs_scrub_fblock_xref_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_xref_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 }
 
 /* Cross-reference a single rtdev extent record. */
 STATIC void
-xfs_scrub_bmap_rt_extent_xref(
-	struct xfs_scrub_bmap_info	*info,
+xchk_bmap_rt_extent_xref(
+	struct xchk_bmap_info		*info,
 	struct xfs_inode		*ip,
 	struct xfs_btree_cur		*cur,
 	struct xfs_bmbt_irec		*irec)
@@ -230,14 +230,14 @@ xfs_scrub_bmap_rt_extent_xref(
 	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_rt_space(info->sc, irec->br_startblock,
+	xchk_xref_is_used_rt_space(info->sc, irec->br_startblock,
 			irec->br_blockcount);
 }
 
 /* Cross-reference a single datadev extent record. */
 STATIC void
-xfs_scrub_bmap_extent_xref(
-	struct xfs_scrub_bmap_info	*info,
+xchk_bmap_extent_xref(
+	struct xchk_bmap_info		*info,
 	struct xfs_inode		*ip,
 	struct xfs_btree_cur		*cur,
 	struct xfs_bmbt_irec		*irec)
@@ -255,38 +255,38 @@ xfs_scrub_bmap_extent_xref(
 	agbno = XFS_FSB_TO_AGBNO(mp, irec->br_startblock);
 	len = irec->br_blockcount;
 
-	error = xfs_scrub_ag_init(info->sc, agno, &info->sc->sa);
-	if (!xfs_scrub_fblock_process_error(info->sc, info->whichfork,
+	error = xchk_ag_init(info->sc, agno, &info->sc->sa);
+	if (!xchk_fblock_process_error(info->sc, info->whichfork,
 			irec->br_startoff, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(info->sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(info->sc, agbno, len);
-	xfs_scrub_bmap_xref_rmap(info, irec, agbno);
+	xchk_xref_is_used_space(info->sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(info->sc, agbno, len);
+	xchk_bmap_xref_rmap(info, irec, agbno);
 	switch (info->whichfork) {
 	case XFS_DATA_FORK:
 		if (xfs_is_reflink_inode(info->sc->ip))
 			break;
 		/* fall through */
 	case XFS_ATTR_FORK:
-		xfs_scrub_xref_is_not_shared(info->sc, agbno,
+		xchk_xref_is_not_shared(info->sc, agbno,
 				irec->br_blockcount);
 		break;
 	case XFS_COW_FORK:
-		xfs_scrub_xref_is_cow_staging(info->sc, agbno,
+		xchk_xref_is_cow_staging(info->sc, agbno,
 				irec->br_blockcount);
 		break;
 	}
 
-	xfs_scrub_ag_free(info->sc, &info->sc->sa);
+	xchk_ag_free(info->sc, &info->sc->sa);
 }
 
 /* Scrub a single extent record. */
 STATIC int
-xfs_scrub_bmap_extent(
+xchk_bmap_extent(
 	struct xfs_inode		*ip,
 	struct xfs_btree_cur		*cur,
-	struct xfs_scrub_bmap_info	*info,
+	struct xchk_bmap_info		*info,
 	struct xfs_bmbt_irec		*irec)
 {
 	struct xfs_mount		*mp = info->sc->mp;
@@ -302,12 +302,12 @@ xfs_scrub_bmap_extent(
 	 * from the incore list, for which there is no ordering check.
 	 */
 	if (irec->br_startoff < info->lastoff)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* There should never be a "hole" extent in either extent list. */
 	if (irec->br_startblock == HOLESTARTBLOCK)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/*
@@ -315,40 +315,40 @@ xfs_scrub_bmap_extent(
 	 * in-core extent scan, and we should never see these in the bmbt.
 	 */
 	if (isnullstartblock(irec->br_startblock))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* Make sure the extent points to a valid place. */
 	if (irec->br_blockcount > MAXEXTLEN)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (irec->br_startblock + irec->br_blockcount <= irec->br_startblock)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	end = irec->br_startblock + irec->br_blockcount - 1;
 	if (info->is_rt &&
 	    (!xfs_verify_rtbno(mp, irec->br_startblock) ||
 	     !xfs_verify_rtbno(mp, end)))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 	if (!info->is_rt &&
 	    (!xfs_verify_fsbno(mp, irec->br_startblock) ||
 	     !xfs_verify_fsbno(mp, end) ||
 	     XFS_FSB_TO_AGNO(mp, irec->br_startblock) !=
 				XFS_FSB_TO_AGNO(mp, end)))
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	/* We don't allow unwritten extents on attr forks. */
 	if (irec->br_state == XFS_EXT_UNWRITTEN &&
 	    info->whichfork == XFS_ATTR_FORK)
-		xfs_scrub_fblock_set_corrupt(info->sc, info->whichfork,
+		xchk_fblock_set_corrupt(info->sc, info->whichfork,
 				irec->br_startoff);
 
 	if (info->is_rt)
-		xfs_scrub_bmap_rt_extent_xref(info, ip, cur, irec);
+		xchk_bmap_rt_extent_xref(info, ip, cur, irec);
 	else
-		xfs_scrub_bmap_extent_xref(info, ip, cur, irec);
+		xchk_bmap_extent_xref(info, ip, cur, irec);
 
 	info->lastoff = irec->br_startoff + irec->br_blockcount;
 	return error;
@@ -356,12 +356,12 @@ xfs_scrub_bmap_extent(
 
 /* Scrub a bmbt record. */
 STATIC int
-xfs_scrub_bmapbt_rec(
-	struct xfs_scrub_btree		*bs,
+xchk_bmapbt_rec(
+	struct xchk_btree		*bs,
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_info	*info = bs->private;
+	struct xchk_bmap_info		*info = bs->private;
 	struct xfs_inode		*ip = bs->cur->bc_private.b.ip;
 	struct xfs_buf			*bp = NULL;
 	struct xfs_btree_block		*block;
@@ -378,22 +378,22 @@ xfs_scrub_bmapbt_rec(
 			block = xfs_btree_get_block(bs->cur, i, &bp);
 			owner = be64_to_cpu(block->bb_u.l.bb_owner);
 			if (owner != ip->i_ino)
-				xfs_scrub_fblock_set_corrupt(bs->sc,
+				xchk_fblock_set_corrupt(bs->sc,
 						info->whichfork, 0);
 		}
 	}
 
 	/* Set up the in-core record and scrub it. */
 	xfs_bmbt_disk_get_all(&rec->bmbt, &irec);
-	return xfs_scrub_bmap_extent(ip, bs->cur, info, &irec);
+	return xchk_bmap_extent(ip, bs->cur, info, &irec);
 }
 
 /* Scan the btree records. */
 STATIC int
-xfs_scrub_bmap_btree(
+xchk_bmap_btree(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
-	struct xfs_scrub_bmap_info	*info)
+	struct xchk_bmap_info		*info)
 {
 	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
@@ -403,12 +403,12 @@ xfs_scrub_bmap_btree(
 
 	cur = xfs_bmbt_init_cursor(mp, sc->tp, ip, whichfork);
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	error = xfs_scrub_btree(sc, cur, xfs_scrub_bmapbt_rec, &oinfo, info);
+	error = xchk_btree(sc, cur, xchk_bmapbt_rec, &oinfo, info);
 	xfs_btree_del_cursor(cur, error);
 	return error;
 }
 
-struct xfs_scrub_bmap_check_rmap_info {
+struct xchk_bmap_check_rmap_info {
 	struct xfs_scrub_context	*sc;
 	int				whichfork;
 	struct xfs_iext_cursor		icur;
@@ -416,13 +416,13 @@ struct xfs_scrub_bmap_check_rmap_info {
 
 /* Can we find bmaps that fit this rmap? */
 STATIC int
-xfs_scrub_bmap_check_rmap(
+xchk_bmap_check_rmap(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
 	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_check_rmap_info	*sbcri = priv;
+	struct xchk_bmap_check_rmap_info	*sbcri = priv;
 	struct xfs_ifork		*ifp;
 	struct xfs_scrub_context	*sc = sbcri->sc;
 	bool				have_map;
@@ -439,14 +439,14 @@ xfs_scrub_bmap_check_rmap(
 	/* Now look up the bmbt record. */
 	ifp = XFS_IFORK_PTR(sc->ip, sbcri->whichfork);
 	if (!ifp) {
-		xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+		xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 				rec->rm_offset);
 		goto out;
 	}
 	have_map = xfs_iext_lookup_extent(sc->ip, ifp, rec->rm_offset,
 			&sbcri->icur, &irec);
 	if (!have_map)
-		xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+		xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 				rec->rm_offset);
 	/*
 	 * bmap extent record lengths are constrained to 2^21 blocks in length
@@ -457,14 +457,14 @@ xfs_scrub_bmap_check_rmap(
 	 */
 	while (have_map) {
 		if (irec.br_startoff != rec->rm_offset)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (irec.br_startblock != XFS_AGB_TO_FSB(sc->mp,
 				cur->bc_private.a.agno, rec->rm_startblock))
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (irec.br_blockcount > rec->rm_blockcount)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			break;
@@ -475,7 +475,7 @@ xfs_scrub_bmap_check_rmap(
 			break;
 		have_map = xfs_iext_next_extent(ifp, &sbcri->icur, &irec);
 		if (!have_map)
-			xfs_scrub_fblock_set_corrupt(sc, sbcri->whichfork,
+			xchk_fblock_set_corrupt(sc, sbcri->whichfork,
 					rec->rm_offset);
 	}
 
@@ -487,12 +487,12 @@ out:
 
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
-xfs_scrub_bmap_check_ag_rmaps(
+xchk_bmap_check_ag_rmaps(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_agnumber_t			agno)
 {
-	struct xfs_scrub_bmap_check_rmap_info	sbcri;
+	struct xchk_bmap_check_rmap_info	sbcri;
 	struct xfs_btree_cur		*cur;
 	struct xfs_buf			*agf;
 	int				error;
@@ -509,7 +509,7 @@ xfs_scrub_bmap_check_ag_rmaps(
 
 	sbcri.sc = sc;
 	sbcri.whichfork = whichfork;
-	error = xfs_rmap_query_all(cur, xfs_scrub_bmap_check_rmap, &sbcri);
+	error = xfs_rmap_query_all(cur, xchk_bmap_check_rmap, &sbcri);
 	if (error == XFS_BTREE_QUERY_RANGE_ABORT)
 		error = 0;
 
@@ -521,7 +521,7 @@ out_agf:
 
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
-xfs_scrub_bmap_check_rmaps(
+xchk_bmap_check_rmaps(
 	struct xfs_scrub_context	*sc,
 	int				whichfork)
 {
@@ -561,7 +561,7 @@ xfs_scrub_bmap_check_rmaps(
 		return 0;
 
 	for (agno = 0; agno < sc->mp->m_sb.sb_agcount; agno++) {
-		error = xfs_scrub_bmap_check_ag_rmaps(sc, whichfork, agno);
+		error = xchk_bmap_check_ag_rmaps(sc, whichfork, agno);
 		if (error)
 			return error;
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -578,12 +578,12 @@ xfs_scrub_bmap_check_rmaps(
  * Then we unconditionally scan the incore extent cache.
  */
 STATIC int
-xfs_scrub_bmap(
+xchk_bmap(
 	struct xfs_scrub_context	*sc,
 	int				whichfork)
 {
 	struct xfs_bmbt_irec		irec;
-	struct xfs_scrub_bmap_info	info = { NULL };
+	struct xchk_bmap_info		info = { NULL };
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_inode		*ip = sc->ip;
 	struct xfs_ifork		*ifp;
@@ -605,7 +605,7 @@ xfs_scrub_bmap(
 			goto out;
 		/* No CoW forks on non-reflink inodes/filesystems. */
 		if (!xfs_is_reflink_inode(ip)) {
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 			goto out;
 		}
 		break;
@@ -614,7 +614,7 @@ xfs_scrub_bmap(
 			goto out_check_rmap;
 		if (!xfs_sb_version_hasattr(&mp->m_sb) &&
 		    !xfs_sb_version_hasattr2(&mp->m_sb))
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		break;
 	default:
 		ASSERT(whichfork == XFS_DATA_FORK);
@@ -630,22 +630,22 @@ xfs_scrub_bmap(
 		goto out;
 	case XFS_DINODE_FMT_EXTENTS:
 		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+			xchk_fblock_set_corrupt(sc, whichfork, 0);
 			goto out;
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (whichfork == XFS_COW_FORK) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+			xchk_fblock_set_corrupt(sc, whichfork, 0);
 			goto out;
 		}
 
-		error = xfs_scrub_bmap_btree(sc, whichfork, &info);
+		error = xchk_bmap_btree(sc, whichfork, &info);
 		if (error)
 			goto out;
 		break;
 	default:
-		xfs_scrub_fblock_set_corrupt(sc, whichfork, 0);
+		xchk_fblock_set_corrupt(sc, whichfork, 0);
 		goto out;
 	}
 
@@ -655,37 +655,37 @@ xfs_scrub_bmap(
 	/* Now try to scrub the in-memory extent list. */
         if (!(ifp->if_flags & XFS_IFEXTENTS)) {
 		error = xfs_iread_extents(sc->tp, ip, whichfork);
-		if (!xfs_scrub_fblock_process_error(sc, whichfork, 0, &error))
+		if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
 			goto out;
 	}
 
 	/* Find the offset of the last extent in the mapping. */
 	error = xfs_bmap_last_offset(ip, &endoff, whichfork);
-	if (!xfs_scrub_fblock_process_error(sc, whichfork, 0, &error))
+	if (!xchk_fblock_process_error(sc, whichfork, 0, &error))
 		goto out;
 
 	/* Scrub extent records. */
 	info.lastoff = 0;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	for_each_xfs_iext(ifp, &icur, &irec) {
-		if (xfs_scrub_should_terminate(sc, &error) ||
+		if (xchk_should_terminate(sc, &error) ||
 		    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 			break;
 		if (isnullstartblock(irec.br_startblock))
 			continue;
 		if (irec.br_startoff >= endoff) {
-			xfs_scrub_fblock_set_corrupt(sc, whichfork,
+			xchk_fblock_set_corrupt(sc, whichfork,
 					irec.br_startoff);
 			goto out;
 		}
-		error = xfs_scrub_bmap_extent(ip, NULL, &info, &irec);
+		error = xchk_bmap_extent(ip, NULL, &info, &irec);
 		if (error)
 			goto out;
 	}
 
 out_check_rmap:
-	error = xfs_scrub_bmap_check_rmaps(sc, whichfork);
-	if (!xfs_scrub_fblock_xref_process_error(sc, whichfork, 0, &error))
+	error = xchk_bmap_check_rmaps(sc, whichfork);
+	if (!xchk_fblock_xref_process_error(sc, whichfork, 0, &error))
 		goto out;
 out:
 	return error;
@@ -693,27 +693,27 @@ out:
 
 /* Scrub an inode's data fork. */
 int
-xfs_scrub_bmap_data(
+xchk_bmap_data(
 	struct xfs_scrub_context	*sc)
 {
-	return xfs_scrub_bmap(sc, XFS_DATA_FORK);
+	return xchk_bmap(sc, XFS_DATA_FORK);
 }
 
 /* Scrub an inode's attr fork. */
 int
-xfs_scrub_bmap_attr(
+xchk_bmap_attr(
 	struct xfs_scrub_context	*sc)
 {
-	return xfs_scrub_bmap(sc, XFS_ATTR_FORK);
+	return xchk_bmap(sc, XFS_ATTR_FORK);
 }
 
 /* Scrub an inode's CoW fork. */
 int
-xfs_scrub_bmap_cow(
+xchk_bmap_cow(
 	struct xfs_scrub_context	*sc)
 {
 	if (!xfs_is_reflink_inode(sc->ip))
 		return -ENOENT;
 
-	return xfs_scrub_bmap(sc, XFS_COW_FORK);
+	return xchk_bmap(sc, XFS_COW_FORK);
 }
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 5b472045f036..30fe9a147959 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -29,7 +29,7 @@
  * operational errors in common.c.
  */
 static bool
-__xfs_scrub_btree_process_error(
+__xchk_btree_process_error(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
@@ -43,7 +43,7 @@ __xfs_scrub_btree_process_error(
 	switch (*error) {
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -53,10 +53,10 @@ __xfs_scrub_btree_process_error(
 		/* fall through */
 	default:
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
-			trace_xfs_scrub_ifork_btree_op_error(sc, cur, level,
+			trace_xchk_ifork_btree_op_error(sc, cur, level,
 					*error, ret_ip);
 		else
-			trace_xfs_scrub_btree_op_error(sc, cur, level,
+			trace_xchk_btree_op_error(sc, cur, level,
 					*error, ret_ip);
 		break;
 	}
@@ -64,30 +64,30 @@ __xfs_scrub_btree_process_error(
 }
 
 bool
-xfs_scrub_btree_process_error(
+xchk_btree_process_error(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
 	int				*error)
 {
-	return __xfs_scrub_btree_process_error(sc, cur, level, error,
+	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_btree_xref_process_error(
+xchk_btree_xref_process_error(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
 	int				*error)
 {
-	return __xfs_scrub_btree_process_error(sc, cur, level, error,
+	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
 /* Record btree block corruption. */
 static void
-__xfs_scrub_btree_set_corrupt(
+__xchk_btree_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
@@ -97,30 +97,30 @@ __xfs_scrub_btree_set_corrupt(
 	sc->sm->sm_flags |= errflag;
 
 	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
-		trace_xfs_scrub_ifork_btree_error(sc, cur, level,
+		trace_xchk_ifork_btree_error(sc, cur, level,
 				ret_ip);
 	else
-		trace_xfs_scrub_btree_error(sc, cur, level,
+		trace_xchk_btree_error(sc, cur, level,
 				ret_ip);
 }
 
 void
-xfs_scrub_btree_set_corrupt(
+xchk_btree_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level)
 {
-	__xfs_scrub_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
+	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
 			__return_address);
 }
 
 void
-xfs_scrub_btree_xref_set_corrupt(
+xchk_btree_xref_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level)
 {
-	__xfs_scrub_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
+	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
 			__return_address);
 }
 
@@ -129,8 +129,8 @@ xfs_scrub_btree_xref_set_corrupt(
  * keys.
  */
 STATIC void
-xfs_scrub_btree_rec(
-	struct xfs_scrub_btree	*bs)
+xchk_btree_rec(
+	struct xchk_btree	*bs)
 {
 	struct xfs_btree_cur	*cur = bs->cur;
 	union xfs_btree_rec	*rec;
@@ -144,11 +144,11 @@ xfs_scrub_btree_rec(
 	block = xfs_btree_get_block(cur, 0, &bp);
 	rec = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
 
-	trace_xfs_scrub_btree_rec(bs->sc, cur, 0);
+	trace_xchk_btree_rec(bs->sc, cur, 0);
 
 	/* If this isn't the first record, are they in order? */
 	if (!bs->firstrec && !cur->bc_ops->recs_inorder(cur, &bs->lastrec, rec))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 0);
+		xchk_btree_set_corrupt(bs->sc, cur, 0);
 	bs->firstrec = false;
 	memcpy(&bs->lastrec, rec, cur->bc_ops->rec_len);
 
@@ -160,7 +160,7 @@ xfs_scrub_btree_rec(
 	keyblock = xfs_btree_get_block(cur, 1, &bp);
 	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, &key, keyp) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -169,7 +169,7 @@ xfs_scrub_btree_rec(
 	cur->bc_ops->init_high_key_from_rec(&hkey, rec);
 	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, keyp, &hkey) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 }
 
 /*
@@ -177,8 +177,8 @@ xfs_scrub_btree_rec(
  * keys.
  */
 STATIC void
-xfs_scrub_btree_key(
-	struct xfs_scrub_btree	*bs,
+xchk_btree_key(
+	struct xchk_btree	*bs,
 	int			level)
 {
 	struct xfs_btree_cur	*cur = bs->cur;
@@ -191,12 +191,12 @@ xfs_scrub_btree_key(
 	block = xfs_btree_get_block(cur, level, &bp);
 	key = xfs_btree_key_addr(cur, cur->bc_ptrs[level], block);
 
-	trace_xfs_scrub_btree_key(bs->sc, cur, level);
+	trace_xchk_btree_key(bs->sc, cur, level);
 
 	/* If this isn't the first key, are they in order? */
 	if (!bs->firstkey[level] &&
 	    !cur->bc_ops->keys_inorder(cur, &bs->lastkey[level], key))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 	bs->firstkey[level] = false;
 	memcpy(&bs->lastkey[level], key, cur->bc_ops->key_len);
 
@@ -207,7 +207,7 @@ xfs_scrub_btree_key(
 	keyblock = xfs_btree_get_block(cur, level + 1, &bp);
 	keyp = xfs_btree_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, key, keyp) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -216,7 +216,7 @@ xfs_scrub_btree_key(
 	key = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level], block);
 	keyp = xfs_btree_high_key_addr(cur, cur->bc_ptrs[level + 1], keyblock);
 	if (cur->bc_ops->diff_two_keys(cur, keyp, key) < 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 }
 
 /*
@@ -224,8 +224,8 @@ xfs_scrub_btree_key(
  * Callers do not need to set the corrupt flag.
  */
 static bool
-xfs_scrub_btree_ptr_ok(
-	struct xfs_scrub_btree		*bs,
+xchk_btree_ptr_ok(
+	struct xchk_btree		*bs,
 	int				level,
 	union xfs_btree_ptr		*ptr)
 {
@@ -242,15 +242,15 @@ xfs_scrub_btree_ptr_ok(
 	else
 		res = xfs_btree_check_sptr(bs->cur, be32_to_cpu(ptr->s), level);
 	if (!res)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 
 	return res;
 }
 
 /* Check that a btree block's sibling matches what we expect it. */
 STATIC int
-xfs_scrub_btree_block_check_sibling(
-	struct xfs_scrub_btree		*bs,
+xchk_btree_block_check_sibling(
+	struct xchk_btree		*bs,
 	int				level,
 	int				direction,
 	union xfs_btree_ptr		*sibling)
@@ -264,7 +264,7 @@ xfs_scrub_btree_block_check_sibling(
 	int				error;
 
 	error = xfs_btree_dup_cursor(cur, &ncur);
-	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error) ||
+	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error) ||
 	    !ncur)
 		return error;
 
@@ -278,7 +278,7 @@ xfs_scrub_btree_block_check_sibling(
 		else
 			error = xfs_btree_decrement(ncur, level + 1, &success);
 		if (error == 0 && success)
-			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+			xchk_btree_set_corrupt(bs->sc, cur, level);
 		error = 0;
 		goto out;
 	}
@@ -288,23 +288,23 @@ xfs_scrub_btree_block_check_sibling(
 		error = xfs_btree_increment(ncur, level + 1, &success);
 	else
 		error = xfs_btree_decrement(ncur, level + 1, &success);
-	if (!xfs_scrub_btree_process_error(bs->sc, cur, level + 1, &error))
+	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error))
 		goto out;
 	if (!success) {
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level + 1);
+		xchk_btree_set_corrupt(bs->sc, cur, level + 1);
 		goto out;
 	}
 
 	/* Compare upper level pointer to sibling pointer. */
 	pblock = xfs_btree_get_block(ncur, level + 1, &pbp);
 	pp = xfs_btree_ptr_addr(ncur, ncur->bc_ptrs[level + 1], pblock);
-	if (!xfs_scrub_btree_ptr_ok(bs, level + 1, pp))
+	if (!xchk_btree_ptr_ok(bs, level + 1, pp))
 		goto out;
 	if (pbp)
-		xfs_scrub_buffer_recheck(bs->sc, pbp);
+		xchk_buffer_recheck(bs->sc, pbp);
 
 	if (xfs_btree_diff_two_ptrs(cur, pp, sibling))
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+		xchk_btree_set_corrupt(bs->sc, cur, level);
 out:
 	xfs_btree_del_cursor(ncur, XFS_BTREE_ERROR);
 	return error;
@@ -312,8 +312,8 @@ out:
 
 /* Check the siblings of a btree block. */
 STATIC int
-xfs_scrub_btree_block_check_siblings(
-	struct xfs_scrub_btree		*bs,
+xchk_btree_block_check_siblings(
+	struct xchk_btree		*bs,
 	struct xfs_btree_block		*block)
 {
 	struct xfs_btree_cur		*cur = bs->cur;
@@ -330,7 +330,7 @@ xfs_scrub_btree_block_check_siblings(
 	if (level == cur->bc_nlevels - 1) {
 		if (!xfs_btree_ptr_is_null(cur, &leftsib) ||
 		    !xfs_btree_ptr_is_null(cur, &rightsib))
-			xfs_scrub_btree_set_corrupt(bs->sc, cur, level);
+			xchk_btree_set_corrupt(bs->sc, cur, level);
 		goto out;
 	}
 
@@ -339,10 +339,10 @@ xfs_scrub_btree_block_check_siblings(
 	 * parent level pointers?
 	 * (These function absorbs error codes for us.)
 	 */
-	error = xfs_scrub_btree_block_check_sibling(bs, level, -1, &leftsib);
+	error = xchk_btree_block_check_sibling(bs, level, -1, &leftsib);
 	if (error)
 		return error;
-	error = xfs_scrub_btree_block_check_sibling(bs, level, 1, &rightsib);
+	error = xchk_btree_block_check_sibling(bs, level, 1, &rightsib);
 	if (error)
 		return error;
 out:
@@ -360,8 +360,8 @@ struct check_owner {
  * an rmap record for it.
  */
 STATIC int
-xfs_scrub_btree_check_block_owner(
-	struct xfs_scrub_btree		*bs,
+xchk_btree_check_block_owner(
+	struct xchk_btree		*bs,
 	int				level,
 	xfs_daddr_t			daddr)
 {
@@ -380,13 +380,13 @@ xfs_scrub_btree_check_block_owner(
 
 	init_sa = bs->cur->bc_flags & XFS_BTREE_LONG_PTRS;
 	if (init_sa) {
-		error = xfs_scrub_ag_init(bs->sc, agno, &bs->sc->sa);
-		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur,
+		error = xchk_ag_init(bs->sc, agno, &bs->sc->sa);
+		if (!xchk_btree_xref_process_error(bs->sc, bs->cur,
 				level, &error))
 			return error;
 	}
 
-	xfs_scrub_xref_is_used_space(bs->sc, agbno, 1);
+	xchk_xref_is_used_space(bs->sc, agbno, 1);
 	/*
 	 * The bnobt scrubber aliases bs->cur to bs->sc->sa.bno_cur, so we
 	 * have to nullify it (to shut down further block owner checks) if
@@ -395,20 +395,20 @@ xfs_scrub_btree_check_block_owner(
 	if (!bs->sc->sa.bno_cur && btnum == XFS_BTNUM_BNO)
 		bs->cur = NULL;
 
-	xfs_scrub_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo);
+	xchk_xref_is_owned_by(bs->sc, agbno, 1, bs->oinfo);
 	if (!bs->sc->sa.rmap_cur && btnum == XFS_BTNUM_RMAP)
 		bs->cur = NULL;
 
 	if (init_sa)
-		xfs_scrub_ag_free(bs->sc, &bs->sc->sa);
+		xchk_ag_free(bs->sc, &bs->sc->sa);
 
 	return error;
 }
 
 /* Check the owner of a btree block. */
 STATIC int
-xfs_scrub_btree_check_owner(
-	struct xfs_scrub_btree		*bs,
+xchk_btree_check_owner(
+	struct xchk_btree		*bs,
 	int				level,
 	struct xfs_buf			*bp)
 {
@@ -437,7 +437,7 @@ xfs_scrub_btree_check_owner(
 		return 0;
 	}
 
-	return xfs_scrub_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
+	return xchk_btree_check_block_owner(bs, level, XFS_BUF_ADDR(bp));
 }
 
 /*
@@ -445,8 +445,8 @@ xfs_scrub_btree_check_owner(
  * special blocks that don't require that.
  */
 STATIC void
-xfs_scrub_btree_check_minrecs(
-	struct xfs_scrub_btree	*bs,
+xchk_btree_check_minrecs(
+	struct xchk_btree	*bs,
 	int			level,
 	struct xfs_btree_block	*block)
 {
@@ -475,7 +475,7 @@ xfs_scrub_btree_check_minrecs(
 	if (level >= ok_level)
 		return;
 
-	xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+	xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 }
 
 /*
@@ -483,8 +483,8 @@ xfs_scrub_btree_check_minrecs(
  * and buffer pointers (if applicable) if they're ok to use.
  */
 STATIC int
-xfs_scrub_btree_get_block(
-	struct xfs_scrub_btree		*bs,
+xchk_btree_get_block(
+	struct xchk_btree		*bs,
 	int				level,
 	union xfs_btree_ptr		*pp,
 	struct xfs_btree_block		**pblock,
@@ -497,7 +497,7 @@ xfs_scrub_btree_get_block(
 	*pbp = NULL;
 
 	error = xfs_btree_lookup_get_block(bs->cur, level, pp, pblock);
-	if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, level, &error) ||
+	if (!xchk_btree_process_error(bs->sc, bs->cur, level, &error) ||
 	    !*pblock)
 		return error;
 
@@ -509,19 +509,19 @@ xfs_scrub_btree_get_block(
 		failed_at = __xfs_btree_check_sblock(bs->cur, *pblock,
 				 level, *pbp);
 	if (failed_at) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, level);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, level);
 		return 0;
 	}
 	if (*pbp)
-		xfs_scrub_buffer_recheck(bs->sc, *pbp);
+		xchk_buffer_recheck(bs->sc, *pbp);
 
-	xfs_scrub_btree_check_minrecs(bs, level, *pblock);
+	xchk_btree_check_minrecs(bs, level, *pblock);
 
 	/*
 	 * Check the block's owner; this function absorbs error codes
 	 * for us.
 	 */
-	error = xfs_scrub_btree_check_owner(bs, level, *pbp);
+	error = xchk_btree_check_owner(bs, level, *pbp);
 	if (error)
 		return error;
 
@@ -529,7 +529,7 @@ xfs_scrub_btree_get_block(
 	 * Check the block's siblings; this function absorbs error codes
 	 * for us.
 	 */
-	return xfs_scrub_btree_block_check_siblings(bs, *pblock);
+	return xchk_btree_block_check_siblings(bs, *pblock);
 }
 
 /*
@@ -537,8 +537,8 @@ xfs_scrub_btree_get_block(
  * in the parent block.
  */
 STATIC void
-xfs_scrub_btree_block_keys(
-	struct xfs_scrub_btree		*bs,
+xchk_btree_block_keys(
+	struct xchk_btree		*bs,
 	int				level,
 	struct xfs_btree_block		*block)
 {
@@ -562,7 +562,7 @@ xfs_scrub_btree_block_keys(
 			parent_block);
 
 	if (cur->bc_ops->diff_two_keys(cur, &block_keys, parent_keys) != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 
 	if (!(cur->bc_flags & XFS_BTREE_OVERLAPPING))
 		return;
@@ -573,7 +573,7 @@ xfs_scrub_btree_block_keys(
 			parent_block);
 
 	if (cur->bc_ops->diff_two_keys(cur, high_bk, high_pk) != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, cur, 1);
+		xchk_btree_set_corrupt(bs->sc, cur, 1);
 }
 
 /*
@@ -582,14 +582,14 @@ xfs_scrub_btree_block_keys(
  * so that the caller can verify individual records.
  */
 int
-xfs_scrub_btree(
+xchk_btree(
 	struct xfs_scrub_context	*sc,
 	struct xfs_btree_cur		*cur,
-	xfs_scrub_btree_rec_fn		scrub_fn,
+	xchk_btree_rec_fn		scrub_fn,
 	struct xfs_owner_info		*oinfo,
 	void				*private)
 {
-	struct xfs_scrub_btree		bs = { NULL };
+	struct xchk_btree		bs = { NULL };
 	union xfs_btree_ptr		ptr;
 	union xfs_btree_ptr		*pp;
 	union xfs_btree_rec		*recp;
@@ -614,7 +614,7 @@ xfs_scrub_btree(
 
 	/* Don't try to check a tree with a height we can't handle. */
 	if (cur->bc_nlevels > XFS_BTREE_MAXLEVELS) {
-		xfs_scrub_btree_set_corrupt(sc, cur, 0);
+		xchk_btree_set_corrupt(sc, cur, 0);
 		goto out;
 	}
 
@@ -624,9 +624,9 @@ xfs_scrub_btree(
 	 */
 	level = cur->bc_nlevels - 1;
 	cur->bc_ops->init_ptr_from_cur(cur, &ptr);
-	if (!xfs_scrub_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
+	if (!xchk_btree_ptr_ok(&bs, cur->bc_nlevels, &ptr))
 		goto out;
-	error = xfs_scrub_btree_get_block(&bs, level, &ptr, &block, &bp);
+	error = xchk_btree_get_block(&bs, level, &ptr, &block, &bp);
 	if (error || !block)
 		goto out;
 
@@ -639,7 +639,7 @@ xfs_scrub_btree(
 			/* End of leaf, pop back towards the root. */
 			if (cur->bc_ptrs[level] >
 			    be16_to_cpu(block->bb_numrecs)) {
-				xfs_scrub_btree_block_keys(&bs, level, block);
+				xchk_btree_block_keys(&bs, level, block);
 				if (level < cur->bc_nlevels - 1)
 					cur->bc_ptrs[level + 1]++;
 				level++;
@@ -647,14 +647,14 @@ xfs_scrub_btree(
 			}
 
 			/* Records in order for scrub? */
-			xfs_scrub_btree_rec(&bs);
+			xchk_btree_rec(&bs);
 
 			/* Call out to the record checker. */
 			recp = xfs_btree_rec_addr(cur, cur->bc_ptrs[0], block);
 			error = bs.scrub_rec(&bs, recp);
 			if (error)
 				break;
-			if (xfs_scrub_should_terminate(sc, &error) ||
+			if (xchk_should_terminate(sc, &error) ||
 			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 				break;
 
@@ -664,7 +664,7 @@ xfs_scrub_btree(
 
 		/* End of node, pop back towards the root. */
 		if (cur->bc_ptrs[level] > be16_to_cpu(block->bb_numrecs)) {
-			xfs_scrub_btree_block_keys(&bs, level, block);
+			xchk_btree_block_keys(&bs, level, block);
 			if (level < cur->bc_nlevels - 1)
 				cur->bc_ptrs[level + 1]++;
 			level++;
@@ -672,16 +672,16 @@ xfs_scrub_btree(
 		}
 
 		/* Keys in order for scrub? */
-		xfs_scrub_btree_key(&bs, level);
+		xchk_btree_key(&bs, level);
 
 		/* Drill another level deeper. */
 		pp = xfs_btree_ptr_addr(cur, cur->bc_ptrs[level], block);
-		if (!xfs_scrub_btree_ptr_ok(&bs, level, pp)) {
+		if (!xchk_btree_ptr_ok(&bs, level, pp)) {
 			cur->bc_ptrs[level]++;
 			continue;
 		}
 		level--;
-		error = xfs_scrub_btree_get_block(&bs, level, pp, &block, &bp);
+		error = xchk_btree_get_block(&bs, level, pp, &block, &bp);
 		if (error || !block)
 			goto out;
 
@@ -692,7 +692,7 @@ out:
 	/* Process deferred owner checks on btree blocks. */
 	list_for_each_entry_safe(co, n, &bs.to_check, list) {
 		if (!error && bs.cur)
-			error = xfs_scrub_btree_check_block_owner(&bs,
+			error = xchk_btree_check_block_owner(&bs,
 					co->level, co->daddr);
 		list_del(&co->list);
 		kmem_free(co);
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index 956627500f2c..598ac04a6c3e 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -9,32 +9,32 @@
 /* btree scrub */
 
 /* Check for btree operation errors. */
-bool xfs_scrub_btree_process_error(struct xfs_scrub_context *sc,
+bool xchk_btree_process_error(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur *cur, int level, int *error);
 
 /* Check for btree xref operation errors. */
-bool xfs_scrub_btree_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_btree_xref_process_error(struct xfs_scrub_context *sc,
 				struct xfs_btree_cur *cur, int level,
 				int *error);
 
 /* Check for btree corruption. */
-void xfs_scrub_btree_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_set_corrupt(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur *cur, int level);
 
 /* Check for btree xref discrepancies. */
-void xfs_scrub_btree_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_xref_set_corrupt(struct xfs_scrub_context *sc,
 		struct xfs_btree_cur *cur, int level);
 
-struct xfs_scrub_btree;
-typedef int (*xfs_scrub_btree_rec_fn)(
-	struct xfs_scrub_btree	*bs,
+struct xchk_btree;
+typedef int (*xchk_btree_rec_fn)(
+	struct xchk_btree	*bs,
 	union xfs_btree_rec	*rec);
 
-struct xfs_scrub_btree {
+struct xchk_btree {
 	/* caller-provided scrub state */
 	struct xfs_scrub_context	*sc;
 	struct xfs_btree_cur		*cur;
-	xfs_scrub_btree_rec_fn		scrub_rec;
+	xchk_btree_rec_fn		scrub_rec;
 	struct xfs_owner_info		*oinfo;
 	void				*private;
 
@@ -45,8 +45,8 @@ struct xfs_scrub_btree {
 	bool				firstkey[XFS_BTREE_MAXLEVELS];
 	struct list_head		to_check;
 };
-int xfs_scrub_btree(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
-		    xfs_scrub_btree_rec_fn scrub_fn,
+int xchk_btree(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+		    xchk_btree_rec_fn scrub_fn,
 		    struct xfs_owner_info *oinfo, void *private);
 
 #endif /* __XFS_SCRUB_BTREE_H__ */
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 385fa5b9c878..5c3d4e7c6166 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -68,7 +68,7 @@
 
 /* Check for operational errors. */
 static bool
-__xfs_scrub_process_error(
+__xchk_process_error(
 	struct xfs_scrub_context	*sc,
 	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
@@ -81,7 +81,7 @@ __xfs_scrub_process_error(
 		return true;
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -90,7 +90,7 @@ __xfs_scrub_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_op_error(sc, agno, bno, *error,
+		trace_xchk_op_error(sc, agno, bno, *error,
 				ret_ip);
 		break;
 	}
@@ -98,30 +98,30 @@ __xfs_scrub_process_error(
 }
 
 bool
-xfs_scrub_process_error(
+xchk_process_error(
 	struct xfs_scrub_context	*sc,
 	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
 	int				*error)
 {
-	return __xfs_scrub_process_error(sc, agno, bno, error,
+	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_xref_process_error(
+xchk_xref_process_error(
 	struct xfs_scrub_context	*sc,
 	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
 	int				*error)
 {
-	return __xfs_scrub_process_error(sc, agno, bno, error,
+	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
 /* Check for operational errors for a file offset. */
 static bool
-__xfs_scrub_fblock_process_error(
+__xchk_fblock_process_error(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset,
@@ -134,7 +134,7 @@ __xfs_scrub_fblock_process_error(
 		return true;
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -143,7 +143,7 @@ __xfs_scrub_fblock_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_file_op_error(sc, whichfork, offset, *error,
+		trace_xchk_file_op_error(sc, whichfork, offset, *error,
 				ret_ip);
 		break;
 	}
@@ -151,24 +151,24 @@ __xfs_scrub_fblock_process_error(
 }
 
 bool
-xfs_scrub_fblock_process_error(
+xchk_fblock_process_error(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset,
 	int				*error)
 {
-	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
 }
 
 bool
-xfs_scrub_fblock_xref_process_error(
+xchk_fblock_xref_process_error(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset,
 	int				*error)
 {
-	return __xfs_scrub_fblock_process_error(sc, whichfork, offset, error,
+	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
 }
 
@@ -186,12 +186,12 @@ xfs_scrub_fblock_xref_process_error(
 
 /* Record a block which could be optimized. */
 void
-xfs_scrub_block_set_preen(
+xchk_block_set_preen(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
-	trace_xfs_scrub_block_preen(sc, bp->b_bn, __return_address);
+	trace_xchk_block_preen(sc, bp->b_bn, __return_address);
 }
 
 /*
@@ -200,32 +200,32 @@ xfs_scrub_block_set_preen(
  * the block location of the inode record itself.
  */
 void
-xfs_scrub_ino_set_preen(
+xchk_ino_set_preen(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
-	trace_xfs_scrub_ino_preen(sc, ino, __return_address);
+	trace_xchk_ino_preen(sc, ino, __return_address);
 }
 
 /* Record a corrupt block. */
 void
-xfs_scrub_block_set_corrupt(
+xchk_block_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
+	trace_xchk_block_error(sc, bp->b_bn, __return_address);
 }
 
 /* Record a corruption while cross-referencing. */
 void
-xfs_scrub_block_xref_set_corrupt(
+xchk_block_xref_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, __return_address);
+	trace_xchk_block_error(sc, bp->b_bn, __return_address);
 }
 
 /*
@@ -234,44 +234,44 @@ xfs_scrub_block_xref_set_corrupt(
  * inode record itself.
  */
 void
-xfs_scrub_ino_set_corrupt(
+xchk_ino_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_ino_error(sc, ino, __return_address);
+	trace_xchk_ino_error(sc, ino, __return_address);
 }
 
 /* Record a corruption while cross-referencing with an inode. */
 void
-xfs_scrub_ino_xref_set_corrupt(
+xchk_ino_xref_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_ino_error(sc, ino, __return_address);
+	trace_xchk_ino_error(sc, ino, __return_address);
 }
 
 /* Record corruption in a block indexed by a file fork. */
 void
-xfs_scrub_fblock_set_corrupt(
+xchk_fblock_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
 }
 
 /* Record a corruption while cross-referencing a fork block. */
 void
-xfs_scrub_fblock_xref_set_corrupt(
+xchk_fblock_xref_set_corrupt(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
-	trace_xfs_scrub_fblock_error(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
 }
 
 /*
@@ -279,32 +279,32 @@ xfs_scrub_fblock_xref_set_corrupt(
  * incorrect.
  */
 void
-xfs_scrub_ino_set_warning(
+xchk_ino_set_warning(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
-	trace_xfs_scrub_ino_warning(sc, ino, __return_address);
+	trace_xchk_ino_warning(sc, ino, __return_address);
 }
 
 /* Warn about a block indexed by a file fork that needs review. */
 void
-xfs_scrub_fblock_set_warning(
+xchk_fblock_set_warning(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
-	trace_xfs_scrub_fblock_warning(sc, whichfork, offset, __return_address);
+	trace_xchk_fblock_warning(sc, whichfork, offset, __return_address);
 }
 
 /* Signal an incomplete scrub. */
 void
-xfs_scrub_set_incomplete(
+xchk_set_incomplete(
 	struct xfs_scrub_context	*sc)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_INCOMPLETE;
-	trace_xfs_scrub_incomplete(sc, __return_address);
+	trace_xchk_incomplete(sc, __return_address);
 }
 
 /*
@@ -312,18 +312,18 @@ xfs_scrub_set_incomplete(
  * at least according to the reverse mapping data.
  */
 
-struct xfs_scrub_rmap_ownedby_info {
+struct xchk_rmap_ownedby_info {
 	struct xfs_owner_info	*oinfo;
 	xfs_filblks_t		*blocks;
 };
 
 STATIC int
-xfs_scrub_count_rmap_ownedby_irec(
+xchk_count_rmap_ownedby_irec(
 	struct xfs_btree_cur			*cur,
 	struct xfs_rmap_irec			*rec,
 	void					*priv)
 {
-	struct xfs_scrub_rmap_ownedby_info	*sroi = priv;
+	struct xchk_rmap_ownedby_info		*sroi = priv;
 	bool					irec_attr;
 	bool					oinfo_attr;
 
@@ -344,19 +344,19 @@ xfs_scrub_count_rmap_ownedby_irec(
  * The caller should pass us an rmapbt cursor.
  */
 int
-xfs_scrub_count_rmap_ownedby_ag(
+xchk_count_rmap_ownedby_ag(
 	struct xfs_scrub_context		*sc,
 	struct xfs_btree_cur			*cur,
 	struct xfs_owner_info			*oinfo,
 	xfs_filblks_t				*blocks)
 {
-	struct xfs_scrub_rmap_ownedby_info	sroi;
+	struct xchk_rmap_ownedby_info		sroi;
 
 	sroi.oinfo = oinfo;
 	*blocks = 0;
 	sroi.blocks = blocks;
 
-	return xfs_rmap_query_all(cur, xfs_scrub_count_rmap_ownedby_irec,
+	return xfs_rmap_query_all(cur, xchk_count_rmap_ownedby_irec,
 			&sroi);
 }
 
@@ -392,12 +392,12 @@ want_ag_read_header_failure(
 /*
  * Grab all the headers for an AG.
  *
- * The headers should be released by xfs_scrub_ag_free, but as a fail
+ * The headers should be released by xchk_ag_free, but as a fail
  * safe we attach all the buffers we grab to the scrub transaction so
  * they'll all be freed when we cancel it.
  */
 int
-xfs_scrub_ag_read_headers(
+xchk_ag_read_headers(
 	struct xfs_scrub_context	*sc,
 	xfs_agnumber_t			agno,
 	struct xfs_buf			**agi,
@@ -425,8 +425,8 @@ out:
 
 /* Release all the AG btree cursors. */
 void
-xfs_scrub_ag_btcur_free(
-	struct xfs_scrub_ag		*sa)
+xchk_ag_btcur_free(
+	struct xchk_ag		*sa)
 {
 	if (sa->refc_cur)
 		xfs_btree_del_cursor(sa->refc_cur, XFS_BTREE_ERROR);
@@ -451,9 +451,9 @@ xfs_scrub_ag_btcur_free(
 
 /* Initialize all the btree cursors for an AG. */
 int
-xfs_scrub_ag_btcur_init(
+xchk_ag_btcur_init(
 	struct xfs_scrub_context	*sc,
-	struct xfs_scrub_ag		*sa)
+	struct xchk_ag		*sa)
 {
 	struct xfs_mount		*mp = sc->mp;
 	xfs_agnumber_t			agno = sa->agno;
@@ -511,11 +511,11 @@ err:
 
 /* Release the AG header context and btree cursors. */
 void
-xfs_scrub_ag_free(
+xchk_ag_free(
 	struct xfs_scrub_context	*sc,
-	struct xfs_scrub_ag		*sa)
+	struct xchk_ag		*sa)
 {
-	xfs_scrub_ag_btcur_free(sa);
+	xchk_ag_btcur_free(sa);
 	if (sa->agfl_bp) {
 		xfs_trans_brelse(sc->tp, sa->agfl_bp);
 		sa->agfl_bp = NULL;
@@ -543,30 +543,30 @@ xfs_scrub_ag_free(
  * transaction ourselves.
  */
 int
-xfs_scrub_ag_init(
+xchk_ag_init(
 	struct xfs_scrub_context	*sc,
 	xfs_agnumber_t			agno,
-	struct xfs_scrub_ag		*sa)
+	struct xchk_ag		*sa)
 {
 	int				error;
 
 	sa->agno = agno;
-	error = xfs_scrub_ag_read_headers(sc, agno, &sa->agi_bp,
+	error = xchk_ag_read_headers(sc, agno, &sa->agi_bp,
 			&sa->agf_bp, &sa->agfl_bp);
 	if (error)
 		return error;
 
-	return xfs_scrub_ag_btcur_init(sc, sa);
+	return xchk_ag_btcur_init(sc, sa);
 }
 
 /*
  * Grab the per-ag structure if we haven't already gotten it.  Teardown of the
- * xfs_scrub_ag will release it for us.
+ * xchk_ag will release it for us.
  */
 void
-xfs_scrub_perag_get(
+xchk_perag_get(
 	struct xfs_mount	*mp,
-	struct xfs_scrub_ag	*sa)
+	struct xchk_ag	*sa)
 {
 	if (!sa->pag)
 		sa->pag = xfs_perag_get(mp, sa->agno);
@@ -585,7 +585,7 @@ xfs_scrub_perag_get(
  * the metadata object.
  */
 int
-xfs_scrub_trans_alloc(
+xchk_trans_alloc(
 	struct xfs_scrub_context	*sc,
 	uint				resblks)
 {
@@ -598,19 +598,19 @@ xfs_scrub_trans_alloc(
 
 /* Set us up with a transaction and an empty context. */
 int
-xfs_scrub_setup_fs(
+xchk_setup_fs(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
 	uint				resblks;
 
 	resblks = xfs_repair_calc_ag_resblks(sc);
-	return xfs_scrub_trans_alloc(sc, resblks);
+	return xchk_trans_alloc(sc, resblks);
 }
 
 /* Set us up with AG headers and btree cursors. */
 int
-xfs_scrub_setup_ag_btree(
+xchk_setup_ag_btree(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip,
 	bool				force_log)
@@ -625,21 +625,21 @@ xfs_scrub_setup_ag_btree(
 	 * document why they need to do so.
 	 */
 	if (force_log) {
-		error = xfs_scrub_checkpoint_log(mp);
+		error = xchk_checkpoint_log(mp);
 		if (error)
 			return error;
 	}
 
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 
-	return xfs_scrub_ag_init(sc, sc->sm->sm_agno, &sc->sa);
+	return xchk_ag_init(sc, sc->sm->sm_agno, &sc->sa);
 }
 
 /* Push everything out of the log onto disk. */
 int
-xfs_scrub_checkpoint_log(
+xchk_checkpoint_log(
 	struct xfs_mount	*mp)
 {
 	int			error;
@@ -657,7 +657,7 @@ xfs_scrub_checkpoint_log(
  * The inode is not locked.
  */
 int
-xfs_scrub_get_inode(
+xchk_get_inode(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip_in)
 {
@@ -704,7 +704,7 @@ xfs_scrub_get_inode(
 		error = -EFSCORRUPTED;
 		/* fall through */
 	default:
-		trace_xfs_scrub_op_error(sc,
+		trace_xchk_op_error(sc,
 				XFS_INO_TO_AGNO(mp, sc->sm->sm_ino),
 				XFS_INO_TO_AGBNO(mp, sc->sm->sm_ino),
 				error, __return_address);
@@ -721,21 +721,21 @@ xfs_scrub_get_inode(
 
 /* Set us up to scrub a file's contents. */
 int
-xfs_scrub_setup_inode_contents(
+xchk_setup_inode_contents(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip,
 	unsigned int			resblks)
 {
 	int				error;
 
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	if (error)
 		return error;
 
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc, resblks);
+	error = xchk_trans_alloc(sc, resblks);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -752,13 +752,13 @@ out:
  * the cursor and skip the check.
  */
 bool
-xfs_scrub_should_check_xref(
+xchk_should_check_xref(
 	struct xfs_scrub_context	*sc,
 	int				*error,
 	struct xfs_btree_cur		**curpp)
 {
 	/* No point in xref if we already know we're corrupt. */
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return false;
 
 	if (*error == 0)
@@ -775,7 +775,7 @@ xfs_scrub_should_check_xref(
 	}
 
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XFAIL;
-	trace_xfs_scrub_xref_error(sc, *error, __return_address);
+	trace_xchk_xref_error(sc, *error, __return_address);
 
 	/*
 	 * Errors encountered during cross-referencing with another
@@ -787,25 +787,25 @@ xfs_scrub_should_check_xref(
 
 /* Run the structure verifiers on in-memory buffers to detect bad memory. */
 void
-xfs_scrub_buffer_recheck(
+xchk_buffer_recheck(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*bp)
 {
 	xfs_failaddr_t			fa;
 
 	if (bp->b_ops == NULL) {
-		xfs_scrub_block_set_corrupt(sc, bp);
+		xchk_block_set_corrupt(sc, bp);
 		return;
 	}
 	if (bp->b_ops->verify_struct == NULL) {
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 		return;
 	}
 	fa = bp->b_ops->verify_struct(bp);
 	if (!fa)
 		return;
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
-	trace_xfs_scrub_block_error(sc, bp->b_bn, fa);
+	trace_xchk_block_error(sc, bp->b_bn, fa);
 }
 
 /*
@@ -813,7 +813,7 @@ xfs_scrub_buffer_recheck(
  * pointed to by sc->ip and the ILOCK must be held.
  */
 int
-xfs_scrub_metadata_inode_forks(
+xchk_metadata_inode_forks(
 	struct xfs_scrub_context	*sc)
 {
 	__u32				smtype;
@@ -825,26 +825,26 @@ xfs_scrub_metadata_inode_forks(
 
 	/* Metadata inodes don't live on the rt device. */
 	if (sc->ip->i_d.di_flags & XFS_DIFLAG_REALTIME) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* They should never participate in reflink. */
 	if (xfs_is_reflink_inode(sc->ip)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* They also should never have extended attributes. */
 	if (xfs_inode_hasattr(sc->ip)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		return 0;
 	}
 
 	/* Invoke the data fork scrubber. */
 	smtype = sc->sm->sm_type;
 	sc->sm->sm_type = XFS_SCRUB_TYPE_BMBTD;
-	error = xfs_scrub_bmap_data(sc);
+	error = xchk_bmap_data(sc);
 	sc->sm->sm_type = smtype;
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
@@ -853,11 +853,11 @@ xfs_scrub_metadata_inode_forks(
 	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
 		error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
 				&shared);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			return error;
 		if (shared)
-			xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 	}
 
 	return error;
@@ -871,7 +871,7 @@ xfs_scrub_metadata_inode_forks(
  * we can't.
  */
 int
-xfs_scrub_ilock_inverted(
+xchk_ilock_inverted(
 	struct xfs_inode	*ip,
 	uint			lock_mode)
 {
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 2172bd5361e2..5881cb2ecc26 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -12,7 +12,7 @@
  * Note that we're careful not to make any judgements about *error.
  */
 static inline bool
-xfs_scrub_should_terminate(
+xchk_should_terminate(
 	struct xfs_scrub_context	*sc,
 	int				*error)
 {
@@ -24,121 +24,121 @@ xfs_scrub_should_terminate(
 	return false;
 }
 
-int xfs_scrub_trans_alloc(struct xfs_scrub_context *sc, uint resblks);
-bool xfs_scrub_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+int xchk_trans_alloc(struct xfs_scrub_context *sc, uint resblks);
+bool xchk_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
 		xfs_agblock_t bno, int *error);
-bool xfs_scrub_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
+bool xchk_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
 		xfs_fileoff_t offset, int *error);
 
-bool xfs_scrub_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_xref_process_error(struct xfs_scrub_context *sc,
 		xfs_agnumber_t agno, xfs_agblock_t bno, int *error);
-bool xfs_scrub_fblock_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_fblock_xref_process_error(struct xfs_scrub_context *sc,
 		int whichfork, xfs_fileoff_t offset, int *error);
 
-void xfs_scrub_block_set_preen(struct xfs_scrub_context *sc,
+void xchk_block_set_preen(struct xfs_scrub_context *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_set_preen(struct xfs_scrub_context *sc, xfs_ino_t ino);
+void xchk_ino_set_preen(struct xfs_scrub_context *sc, xfs_ino_t ino);
 
-void xfs_scrub_block_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_set_corrupt(struct xfs_scrub_context *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_set_corrupt(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xfs_scrub_fblock_set_corrupt(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_corrupt(struct xfs_scrub_context *sc, xfs_ino_t ino);
+void xchk_fblock_set_corrupt(struct xfs_scrub_context *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xfs_scrub_block_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_xref_set_corrupt(struct xfs_scrub_context *sc,
 		struct xfs_buf *bp);
-void xfs_scrub_ino_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_ino_xref_set_corrupt(struct xfs_scrub_context *sc,
 		xfs_ino_t ino);
-void xfs_scrub_fblock_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_fblock_xref_set_corrupt(struct xfs_scrub_context *sc,
 		int whichfork, xfs_fileoff_t offset);
 
-void xfs_scrub_ino_set_warning(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xfs_scrub_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_warning(struct xfs_scrub_context *sc, xfs_ino_t ino);
+void xchk_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xfs_scrub_set_incomplete(struct xfs_scrub_context *sc);
-int xfs_scrub_checkpoint_log(struct xfs_mount *mp);
+void xchk_set_incomplete(struct xfs_scrub_context *sc);
+int xchk_checkpoint_log(struct xfs_mount *mp);
 
 /* Are we set up for a cross-referencing check? */
-bool xfs_scrub_should_check_xref(struct xfs_scrub_context *sc, int *error,
+bool xchk_should_check_xref(struct xfs_scrub_context *sc, int *error,
 			   struct xfs_btree_cur **curpp);
 
 /* Setup functions */
-int xfs_scrub_setup_fs(struct xfs_scrub_context *sc, struct xfs_inode *ip);
-int xfs_scrub_setup_ag_allocbt(struct xfs_scrub_context *sc,
+int xchk_setup_fs(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_ag_allocbt(struct xfs_scrub_context *sc,
 			       struct xfs_inode *ip);
-int xfs_scrub_setup_ag_iallocbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_iallocbt(struct xfs_scrub_context *sc,
 				struct xfs_inode *ip);
-int xfs_scrub_setup_ag_rmapbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_rmapbt(struct xfs_scrub_context *sc,
 			      struct xfs_inode *ip);
-int xfs_scrub_setup_ag_refcountbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_refcountbt(struct xfs_scrub_context *sc,
 				  struct xfs_inode *ip);
-int xfs_scrub_setup_inode(struct xfs_scrub_context *sc,
+int xchk_setup_inode(struct xfs_scrub_context *sc,
 			  struct xfs_inode *ip);
-int xfs_scrub_setup_inode_bmap(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap(struct xfs_scrub_context *sc,
 			       struct xfs_inode *ip);
-int xfs_scrub_setup_inode_bmap_data(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap_data(struct xfs_scrub_context *sc,
 				    struct xfs_inode *ip);
-int xfs_scrub_setup_directory(struct xfs_scrub_context *sc,
+int xchk_setup_directory(struct xfs_scrub_context *sc,
 			      struct xfs_inode *ip);
-int xfs_scrub_setup_xattr(struct xfs_scrub_context *sc,
+int xchk_setup_xattr(struct xfs_scrub_context *sc,
 			  struct xfs_inode *ip);
-int xfs_scrub_setup_symlink(struct xfs_scrub_context *sc,
+int xchk_setup_symlink(struct xfs_scrub_context *sc,
 			    struct xfs_inode *ip);
-int xfs_scrub_setup_parent(struct xfs_scrub_context *sc,
+int xchk_setup_parent(struct xfs_scrub_context *sc,
 			   struct xfs_inode *ip);
 #ifdef CONFIG_XFS_RT
-int xfs_scrub_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip);
 #else
 static inline int
-xfs_scrub_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip);
 #else
 static inline int
-xfs_scrub_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 
-void xfs_scrub_ag_free(struct xfs_scrub_context *sc, struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_init(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
-		      struct xfs_scrub_ag *sa);
-void xfs_scrub_perag_get(struct xfs_mount *mp, struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_read_headers(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+void xchk_ag_free(struct xfs_scrub_context *sc, struct xchk_ag *sa);
+int xchk_ag_init(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+		      struct xchk_ag *sa);
+void xchk_perag_get(struct xfs_mount *mp, struct xchk_ag *sa);
+int xchk_ag_read_headers(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
 			      struct xfs_buf **agi, struct xfs_buf **agf,
 			      struct xfs_buf **agfl);
-void xfs_scrub_ag_btcur_free(struct xfs_scrub_ag *sa);
-int xfs_scrub_ag_btcur_init(struct xfs_scrub_context *sc,
-			    struct xfs_scrub_ag *sa);
-int xfs_scrub_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
+void xchk_ag_btcur_free(struct xchk_ag *sa);
+int xchk_ag_btcur_init(struct xfs_scrub_context *sc,
+			    struct xchk_ag *sa);
+int xchk_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
 				    struct xfs_btree_cur *cur,
 				    struct xfs_owner_info *oinfo,
 				    xfs_filblks_t *blocks);
 
-int xfs_scrub_setup_ag_btree(struct xfs_scrub_context *sc,
+int xchk_setup_ag_btree(struct xfs_scrub_context *sc,
 			     struct xfs_inode *ip, bool force_log);
-int xfs_scrub_get_inode(struct xfs_scrub_context *sc, struct xfs_inode *ip_in);
-int xfs_scrub_setup_inode_contents(struct xfs_scrub_context *sc,
+int xchk_get_inode(struct xfs_scrub_context *sc, struct xfs_inode *ip_in);
+int xchk_setup_inode_contents(struct xfs_scrub_context *sc,
 				   struct xfs_inode *ip, unsigned int resblks);
-void xfs_scrub_buffer_recheck(struct xfs_scrub_context *sc, struct xfs_buf *bp);
+void xchk_buffer_recheck(struct xfs_scrub_context *sc, struct xfs_buf *bp);
 
 /*
  * Don't bother cross-referencing if we already found corruption or cross
  * referencing discrepancies.
  */
-static inline bool xfs_scrub_skip_xref(struct xfs_scrub_metadata *sm)
+static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
 {
 	return sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
 			       XFS_SCRUB_OFLAG_XCORRUPT);
 }
 
-int xfs_scrub_metadata_inode_forks(struct xfs_scrub_context *sc);
-int xfs_scrub_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
+int xchk_metadata_inode_forks(struct xfs_scrub_context *sc);
+int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
 
 #endif	/* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index d700c4d4d4ef..fee80f6ddfd7 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -35,8 +35,8 @@
  * operational errors in common.c.
  */
 bool
-xfs_scrub_da_process_error(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_process_error(
+	struct xchk_da_btree		*ds,
 	int				level,
 	int				*error)
 {
@@ -48,7 +48,7 @@ xfs_scrub_da_process_error(
 	switch (*error) {
 	case -EDEADLOCK:
 		/* Used to restart an op with deadlock avoidance. */
-		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		trace_xchk_deadlock_retry(sc->ip, sc->sm, *error);
 		break;
 	case -EFSBADCRC:
 	case -EFSCORRUPTED:
@@ -57,7 +57,7 @@ xfs_scrub_da_process_error(
 		*error = 0;
 		/* fall through */
 	default:
-		trace_xfs_scrub_file_op_error(sc, ds->dargs.whichfork,
+		trace_xchk_file_op_error(sc, ds->dargs.whichfork,
 				xfs_dir2_da_to_db(ds->dargs.geo,
 					ds->state->path.blk[level].blkno),
 				*error, __return_address);
@@ -71,15 +71,15 @@ xfs_scrub_da_process_error(
  * operational errors in common.c.
  */
 void
-xfs_scrub_da_set_corrupt(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_set_corrupt(
+	struct xchk_da_btree		*ds,
 	int				level)
 {
 	struct xfs_scrub_context	*sc = ds->sc;
 
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 
-	trace_xfs_scrub_fblock_error(sc, ds->dargs.whichfork,
+	trace_xchk_fblock_error(sc, ds->dargs.whichfork,
 			xfs_dir2_da_to_db(ds->dargs.geo,
 				ds->state->path.blk[level].blkno),
 			__return_address);
@@ -87,8 +87,8 @@ xfs_scrub_da_set_corrupt(
 
 /* Find an entry at a certain level in a da btree. */
 STATIC void *
-xfs_scrub_da_btree_entry(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_entry(
+	struct xchk_da_btree		*ds,
 	int				level,
 	int				rec)
 {
@@ -123,8 +123,8 @@ xfs_scrub_da_btree_entry(
 
 /* Scrub a da btree hash (key). */
 int
-xfs_scrub_da_btree_hash(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_hash(
+	struct xchk_da_btree		*ds,
 	int				level,
 	__be32				*hashp)
 {
@@ -136,7 +136,7 @@ xfs_scrub_da_btree_hash(
 	/* Is this hash in order? */
 	hash = be32_to_cpu(*hashp);
 	if (hash < ds->hashes[level])
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	ds->hashes[level] = hash;
 
 	if (level == 0)
@@ -144,10 +144,10 @@ xfs_scrub_da_btree_hash(
 
 	/* Is this hash no larger than the parent hash? */
 	blks = ds->state->path.blk;
-	entry = xfs_scrub_da_btree_entry(ds, level - 1, blks[level - 1].index);
+	entry = xchk_da_btree_entry(ds, level - 1, blks[level - 1].index);
 	parent_hash = be32_to_cpu(entry->hashval);
 	if (parent_hash < hash)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	return 0;
 }
@@ -157,13 +157,13 @@ xfs_scrub_da_btree_hash(
  * pointer.
  */
 STATIC bool
-xfs_scrub_da_btree_ptr_ok(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_ptr_ok(
+	struct xchk_da_btree		*ds,
 	int				level,
 	xfs_dablk_t			blkno)
 {
 	if (blkno < ds->lowest || (ds->highest != 0 && blkno >= ds->highest)) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return false;
 	}
 
@@ -176,7 +176,7 @@ xfs_scrub_da_btree_ptr_ok(
  * leaf1, we must multiplex the verifiers.
  */
 static void
-xfs_scrub_da_btree_read_verify(
+xchk_da_btree_read_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -198,7 +198,7 @@ xfs_scrub_da_btree_read_verify(
 	}
 }
 static void
-xfs_scrub_da_btree_write_verify(
+xchk_da_btree_write_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -220,7 +220,7 @@ xfs_scrub_da_btree_write_verify(
 	}
 }
 static void *
-xfs_scrub_da_btree_verify(
+xchk_da_btree_verify(
 	struct xfs_buf		*bp)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
@@ -236,17 +236,17 @@ xfs_scrub_da_btree_verify(
 	}
 }
 
-static const struct xfs_buf_ops xfs_scrub_da_btree_buf_ops = {
-	.name = "xfs_scrub_da_btree",
-	.verify_read = xfs_scrub_da_btree_read_verify,
-	.verify_write = xfs_scrub_da_btree_write_verify,
-	.verify_struct = xfs_scrub_da_btree_verify,
+static const struct xfs_buf_ops xchk_da_btree_buf_ops = {
+	.name = "xchk_da_btree",
+	.verify_read = xchk_da_btree_read_verify,
+	.verify_write = xchk_da_btree_write_verify,
+	.verify_struct = xchk_da_btree_verify,
 };
 
 /* Check a block's sibling. */
 STATIC int
-xfs_scrub_da_btree_block_check_sibling(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_block_check_sibling(
+	struct xchk_da_btree		*ds,
 	int				level,
 	int				direction,
 	xfs_dablk_t			sibling)
@@ -265,7 +265,7 @@ xfs_scrub_da_btree_block_check_sibling(
 		error = xfs_da3_path_shift(ds->state, &ds->state->altpath,
 				direction, false, &retval);
 		if (error == 0 && retval == 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		error = 0;
 		goto out;
 	}
@@ -273,19 +273,19 @@ xfs_scrub_da_btree_block_check_sibling(
 	/* Move the alternate cursor one block in the direction given. */
 	error = xfs_da3_path_shift(ds->state, &ds->state->altpath,
 			direction, false, &retval);
-	if (!xfs_scrub_da_process_error(ds, level, &error))
+	if (!xchk_da_process_error(ds, level, &error))
 		return error;
 	if (retval) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		return error;
 	}
 	if (ds->state->altpath.blk[level].bp)
-		xfs_scrub_buffer_recheck(ds->sc,
+		xchk_buffer_recheck(ds->sc,
 				ds->state->altpath.blk[level].bp);
 
 	/* Compare upper level pointer to sibling pointer. */
 	if (ds->state->altpath.blk[level].blkno != sibling)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 	xfs_trans_brelse(ds->dargs.trans, ds->state->altpath.blk[level].bp);
 out:
 	return error;
@@ -293,8 +293,8 @@ out:
 
 /* Check a block's sibling pointers. */
 STATIC int
-xfs_scrub_da_btree_block_check_siblings(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_block_check_siblings(
+	struct xchk_da_btree		*ds,
 	int				level,
 	struct xfs_da_blkinfo		*hdr)
 {
@@ -308,7 +308,7 @@ xfs_scrub_da_btree_block_check_siblings(
 	/* Top level blocks should not have sibling pointers. */
 	if (level == 0) {
 		if (forw != 0 || back != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		return 0;
 	}
 
@@ -316,10 +316,10 @@ xfs_scrub_da_btree_block_check_siblings(
 	 * Check back (left) and forw (right) pointers.  These functions
 	 * absorb error codes for us.
 	 */
-	error = xfs_scrub_da_btree_block_check_sibling(ds, level, 0, back);
+	error = xchk_da_btree_block_check_sibling(ds, level, 0, back);
 	if (error)
 		goto out;
-	error = xfs_scrub_da_btree_block_check_sibling(ds, level, 1, forw);
+	error = xchk_da_btree_block_check_sibling(ds, level, 1, forw);
 
 out:
 	memset(&ds->state->altpath, 0, sizeof(ds->state->altpath));
@@ -328,8 +328,8 @@ out:
 
 /* Load a dir/attribute block from a btree. */
 STATIC int
-xfs_scrub_da_btree_block(
-	struct xfs_scrub_da_btree	*ds,
+xchk_da_btree_block(
+	struct xchk_da_btree		*ds,
 	int				level,
 	xfs_dablk_t			blkno)
 {
@@ -355,17 +355,17 @@ xfs_scrub_da_btree_block(
 
 	/* Check the pointer. */
 	blk->blkno = blkno;
-	if (!xfs_scrub_da_btree_ptr_ok(ds, level, blkno))
+	if (!xchk_da_btree_ptr_ok(ds, level, blkno))
 		goto out_nobuf;
 
 	/* Read the buffer. */
 	error = xfs_da_read_buf(dargs->trans, dargs->dp, blk->blkno, -2,
 			&blk->bp, dargs->whichfork,
-			&xfs_scrub_da_btree_buf_ops);
-	if (!xfs_scrub_da_process_error(ds, level, &error))
+			&xchk_da_btree_buf_ops);
+	if (!xchk_da_process_error(ds, level, &error))
 		goto out_nobuf;
 	if (blk->bp)
-		xfs_scrub_buffer_recheck(ds->sc, blk->bp);
+		xchk_buffer_recheck(ds->sc, blk->bp);
 
 	/*
 	 * We didn't find a dir btree root block, which means that
@@ -378,7 +378,7 @@ xfs_scrub_da_btree_block(
 
 	/* It's /not/ ok for attr trees not to have a da btree. */
 	if (blk->bp == NULL) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out_nobuf;
 	}
 
@@ -388,17 +388,17 @@ xfs_scrub_da_btree_block(
 
 	/* We only started zeroing the header on v5 filesystems. */
 	if (xfs_sb_version_hascrc(&ds->sc->mp->m_sb) && hdr3->hdr.pad)
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 
 	/* Check the owner. */
 	if (xfs_sb_version_hascrc(&ip->i_mount->m_sb)) {
 		owner = be64_to_cpu(hdr3->owner);
 		if (owner != ip->i_ino)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 	}
 
 	/* Check the siblings. */
-	error = xfs_scrub_da_btree_block_check_siblings(ds, level, &hdr3->hdr);
+	error = xchk_da_btree_block_check_siblings(ds, level, &hdr3->hdr);
 	if (error)
 		goto out;
 
@@ -411,7 +411,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_ATTR_LEAF_MAGIC;
 		blk->hashval = xfs_attr_leaf_lasthash(blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DIR2_LEAFN_MAGIC:
 	case XFS_DIR3_LEAFN_MAGIC:
@@ -420,7 +420,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_DIR2_LEAFN_MAGIC;
 		blk->hashval = xfs_dir2_leaf_lasthash(ip, blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DIR2_LEAF1_MAGIC:
 	case XFS_DIR3_LEAF1_MAGIC:
@@ -429,7 +429,7 @@ xfs_scrub_da_btree_block(
 		blk->magic = XFS_DIR2_LEAF1_MAGIC;
 		blk->hashval = xfs_dir2_leaf_lasthash(ip, blk->bp, pmaxrecs);
 		if (ds->tree_level != 0)
-			xfs_scrub_da_set_corrupt(ds, level);
+			xchk_da_set_corrupt(ds, level);
 		break;
 	case XFS_DA_NODE_MAGIC:
 	case XFS_DA3_NODE_MAGIC:
@@ -443,13 +443,13 @@ xfs_scrub_da_btree_block(
 		blk->hashval = be32_to_cpu(btree[*pmaxrecs - 1].hashval);
 		if (level == 0) {
 			if (nodehdr.level >= XFS_DA_NODE_MAXDEPTH) {
-				xfs_scrub_da_set_corrupt(ds, level);
+				xchk_da_set_corrupt(ds, level);
 				goto out_freebp;
 			}
 			ds->tree_level = nodehdr.level;
 		} else {
 			if (ds->tree_level != nodehdr.level) {
-				xfs_scrub_da_set_corrupt(ds, level);
+				xchk_da_set_corrupt(ds, level);
 				goto out_freebp;
 			}
 		}
@@ -457,7 +457,7 @@ xfs_scrub_da_btree_block(
 		/* XXX: Check hdr3.pad32 once we know how to fix it. */
 		break;
 	default:
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out_freebp;
 	}
 
@@ -473,13 +473,13 @@ out_nobuf:
 
 /* Visit all nodes and leaves of a da btree. */
 int
-xfs_scrub_da_btree(
+xchk_da_btree(
 	struct xfs_scrub_context	*sc,
 	int				whichfork,
-	xfs_scrub_da_btree_rec_fn	scrub_fn,
+	xchk_da_btree_rec_fn	scrub_fn,
 	void				*private)
 {
-	struct xfs_scrub_da_btree	ds = {};
+	struct xchk_da_btree		ds = {};
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_da_state_blk		*blks;
 	struct xfs_da_node_entry	*key;
@@ -517,7 +517,7 @@ xfs_scrub_da_btree(
 
 	/* Find the root of the da tree, if present. */
 	blks = ds.state->path.blk;
-	error = xfs_scrub_da_btree_block(&ds, level, blkno);
+	error = xchk_da_btree_block(&ds, level, blkno);
 	if (error)
 		goto out_state;
 	/*
@@ -542,12 +542,12 @@ xfs_scrub_da_btree(
 			}
 
 			/* Dispatch record scrubbing. */
-			rec = xfs_scrub_da_btree_entry(&ds, level,
+			rec = xchk_da_btree_entry(&ds, level,
 					blks[level].index);
 			error = scrub_fn(&ds, level, rec);
 			if (error)
 				break;
-			if (xfs_scrub_should_terminate(sc, &error) ||
+			if (xchk_should_terminate(sc, &error) ||
 			    (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 				break;
 
@@ -566,8 +566,8 @@ xfs_scrub_da_btree(
 		}
 
 		/* Hashes in order for scrub? */
-		key = xfs_scrub_da_btree_entry(&ds, level, blks[level].index);
-		error = xfs_scrub_da_btree_hash(&ds, level, &key->hashval);
+		key = xchk_da_btree_entry(&ds, level, blks[level].index);
+		error = xchk_da_btree_hash(&ds, level, &key->hashval);
 		if (error)
 			goto out;
 
@@ -575,7 +575,7 @@ xfs_scrub_da_btree(
 		blkno = be32_to_cpu(key->before);
 		level++;
 		ds.tree_level--;
-		error = xfs_scrub_da_btree_block(&ds, level, blkno);
+		error = xchk_da_btree_block(&ds, level, blkno);
 		if (error)
 			goto out;
 		if (blks[level].bp == NULL)
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index 365f9f0019e6..80e4af0e2589 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -8,7 +8,7 @@
 
 /* dir/attr btree */
 
-struct xfs_scrub_da_btree {
+struct xchk_da_btree {
 	struct xfs_da_args		dargs;
 	xfs_dahash_t			hashes[XFS_DA_NODE_MAXDEPTH];
 	int				maxrecs[XFS_DA_NODE_MAXDEPTH];
@@ -28,18 +28,18 @@ struct xfs_scrub_da_btree {
 	int				tree_level;
 };
 
-typedef int (*xfs_scrub_da_btree_rec_fn)(struct xfs_scrub_da_btree *ds,
+typedef int (*xchk_da_btree_rec_fn)(struct xchk_da_btree *ds,
 		int level, void *rec);
 
 /* Check for da btree operation errors. */
-bool xfs_scrub_da_process_error(struct xfs_scrub_da_btree *ds, int level, int *error);
+bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
 
 /* Check for da btree corruption. */
-void xfs_scrub_da_set_corrupt(struct xfs_scrub_da_btree *ds, int level);
+void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
 
-int xfs_scrub_da_btree_hash(struct xfs_scrub_da_btree *ds, int level,
+int xchk_da_btree_hash(struct xchk_da_btree *ds, int level,
 			    __be32 *hashp);
-int xfs_scrub_da_btree(struct xfs_scrub_context *sc, int whichfork,
-		       xfs_scrub_da_btree_rec_fn scrub_fn, void *private);
+int xchk_da_btree(struct xfs_scrub_context *sc, int whichfork,
+		       xchk_da_btree_rec_fn scrub_fn, void *private);
 
 #endif /* __XFS_SCRUB_DABTREE_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 86324775fc9b..2ac07bb73478 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -31,18 +31,18 @@
 
 /* Set us up to scrub directories. */
 int
-xfs_scrub_setup_directory(
+xchk_setup_directory(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Directories */
 
 /* Scrub a directory entry. */
 
-struct xfs_scrub_dir_ctx {
+struct xchk_dir_ctx {
 	/* VFS fill-directory iterator */
 	struct dir_context		dir_iter;
 
@@ -51,8 +51,8 @@ struct xfs_scrub_dir_ctx {
 
 /* Check that an inode's mode matches a given DT_ type. */
 STATIC int
-xfs_scrub_dir_check_ftype(
-	struct xfs_scrub_dir_ctx	*sdc,
+xchk_dir_check_ftype(
+	struct xchk_dir_ctx		*sdc,
 	xfs_fileoff_t			offset,
 	xfs_ino_t			inum,
 	int				dtype)
@@ -64,7 +64,7 @@ xfs_scrub_dir_check_ftype(
 
 	if (!xfs_sb_version_hasftype(&mp->m_sb)) {
 		if (dtype != DT_UNKNOWN && dtype != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		goto out;
 	}
@@ -78,7 +78,7 @@ xfs_scrub_dir_check_ftype(
 	 * inodes can trigger immediate inactive cleanup of the inode.
 	 */
 	error = xfs_iget(mp, sdc->sc->tp, inum, 0, 0, &ip);
-	if (!xfs_scrub_fblock_xref_process_error(sdc->sc, XFS_DATA_FORK, offset,
+	if (!xchk_fblock_xref_process_error(sdc->sc, XFS_DATA_FORK, offset,
 			&error))
 		goto out;
 
@@ -86,7 +86,7 @@ xfs_scrub_dir_check_ftype(
 	ino_dtype = xfs_dir3_get_dtype(mp,
 			xfs_mode_to_ftype(VFS_I(ip)->i_mode));
 	if (ino_dtype != dtype)
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 	iput(VFS_I(ip));
 out:
 	return error;
@@ -101,7 +101,7 @@ out:
  * we can look up this filename.  Finally, we check the ftype.
  */
 STATIC int
-xfs_scrub_dir_actor(
+xchk_dir_actor(
 	struct dir_context		*dir_iter,
 	const char			*name,
 	int				namelen,
@@ -111,13 +111,13 @@ xfs_scrub_dir_actor(
 {
 	struct xfs_mount		*mp;
 	struct xfs_inode		*ip;
-	struct xfs_scrub_dir_ctx	*sdc;
+	struct xchk_dir_ctx		*sdc;
 	struct xfs_name			xname;
 	xfs_ino_t			lookup_ino;
 	xfs_dablk_t			offset;
 	int				error = 0;
 
-	sdc = container_of(dir_iter, struct xfs_scrub_dir_ctx, dir_iter);
+	sdc = container_of(dir_iter, struct xchk_dir_ctx, dir_iter);
 	ip = sdc->sc->ip;
 	mp = ip->i_mount;
 	offset = xfs_dir2_db_to_da(mp->m_dir_geo,
@@ -125,17 +125,17 @@ xfs_scrub_dir_actor(
 
 	/* Does this inode number make sense? */
 	if (!xfs_verify_dir_ino(mp, ino)) {
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 		goto out;
 	}
 
 	if (!strncmp(".", name, namelen)) {
 		/* If this is "." then check that the inum matches the dir. */
 		if (xfs_sb_version_hasftype(&mp->m_sb) && type != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		if (ino != ip->i_ino)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 	} else if (!strncmp("..", name, namelen)) {
 		/*
@@ -143,10 +143,10 @@ xfs_scrub_dir_actor(
 		 * matches this dir.
 		 */
 		if (xfs_sb_version_hasftype(&mp->m_sb) && type != DT_DIR)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 		if (ip->i_ino == mp->m_sb.sb_rootino && ino != ip->i_ino)
-			xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK,
 					offset);
 	}
 
@@ -156,23 +156,23 @@ xfs_scrub_dir_actor(
 	xname.type = XFS_DIR3_FT_UNKNOWN;
 
 	error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL);
-	if (!xfs_scrub_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
+	if (!xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset,
 			&error))
 		goto out;
 	if (lookup_ino != ino) {
-		xfs_scrub_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
 		goto out;
 	}
 
 	/* Verify the file type.  This function absorbs error codes. */
-	error = xfs_scrub_dir_check_ftype(sdc, offset, lookup_ino, type);
+	error = xchk_dir_check_ftype(sdc, offset, lookup_ino, type);
 	if (error)
 		goto out;
 out:
 	/*
 	 * A negative error code returned here is supposed to cause the
 	 * dir_emit caller (xfs_readdir) to abort the directory iteration
-	 * and return zero to xfs_scrub_directory.
+	 * and return zero to xchk_directory.
 	 */
 	if (error == 0 && sdc->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return -EFSCORRUPTED;
@@ -181,8 +181,8 @@ out:
 
 /* Scrub a directory btree record. */
 STATIC int
-xfs_scrub_dir_rec(
-	struct xfs_scrub_da_btree	*ds,
+xchk_dir_rec(
+	struct xchk_da_btree		*ds,
 	int				level,
 	void				*rec)
 {
@@ -203,7 +203,7 @@ xfs_scrub_dir_rec(
 	int				error;
 
 	/* Check the hash of the entry. */
-	error = xfs_scrub_da_btree_hash(ds, level, &ent->hashval);
+	error = xchk_da_btree_hash(ds, level, &ent->hashval);
 	if (error)
 		goto out;
 
@@ -218,18 +218,18 @@ xfs_scrub_dir_rec(
 	rec_bno = xfs_dir2_db_to_da(mp->m_dir_geo, db);
 
 	if (rec_bno >= mp->m_dir_geo->leafblk) {
-		xfs_scrub_da_set_corrupt(ds, level);
+		xchk_da_set_corrupt(ds, level);
 		goto out;
 	}
 	error = xfs_dir3_data_read(ds->dargs.trans, dp, rec_bno, -2, &bp);
-	if (!xfs_scrub_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
+	if (!xchk_fblock_process_error(ds->sc, XFS_DATA_FORK, rec_bno,
 			&error))
 		goto out;
 	if (!bp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out;
 	}
-	xfs_scrub_buffer_recheck(ds->sc, bp);
+	xchk_buffer_recheck(ds->sc, bp);
 
 	if (ds->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out_relse;
@@ -240,7 +240,7 @@ xfs_scrub_dir_rec(
 	p = (char *)mp->m_dir_inode_ops->data_entry_p(bp->b_addr);
 	endp = xfs_dir3_data_endp(mp->m_dir_geo, bp->b_addr);
 	if (!endp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 	while (p < endp) {
@@ -258,7 +258,7 @@ xfs_scrub_dir_rec(
 		p += mp->m_dir_inode_ops->data_entsize(dep->namelen);
 	}
 	if (p >= endp) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 
@@ -267,14 +267,14 @@ xfs_scrub_dir_rec(
 	hash = be32_to_cpu(ent->hashval);
 	tag = be16_to_cpup(dp->d_ops->data_entry_tag_p(dent));
 	if (!xfs_verify_dir_ino(mp, ino) || tag != off)
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 	if (dent->namelen == 0) {
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 		goto out_relse;
 	}
 	calc_hash = xfs_da_hashname(dent->name, dent->namelen);
 	if (calc_hash != hash)
-		xfs_scrub_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
+		xchk_fblock_set_corrupt(ds->sc, XFS_DATA_FORK, rec_bno);
 
 out_relse:
 	xfs_trans_brelse(ds->dargs.trans, bp);
@@ -288,7 +288,7 @@ out:
  * shortest, and that there aren't any bogus entries.
  */
 STATIC void
-xfs_scrub_directory_check_free_entry(
+xchk_directory_check_free_entry(
 	struct xfs_scrub_context	*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_dir2_data_free	*bf,
@@ -308,12 +308,12 @@ xfs_scrub_directory_check_free_entry(
 			return;
 
 	/* Unused entry should be in the bestfrees but wasn't found. */
-	xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+	xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 }
 
 /* Check free space info in a directory data block. */
 STATIC int
-xfs_scrub_directory_data_bestfree(
+xchk_directory_data_bestfree(
 	struct xfs_scrub_context	*sc,
 	xfs_dablk_t			lblk,
 	bool				is_block)
@@ -339,15 +339,15 @@ xfs_scrub_directory_data_bestfree(
 	if (is_block) {
 		/* dir block format */
 		if (lblk != XFS_B_TO_FSBT(mp, XFS_DIR2_DATA_OFFSET))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		error = xfs_dir3_block_read(sc->tp, sc->ip, &bp);
 	} else {
 		/* dir data format */
 		error = xfs_dir3_data_read(sc->tp, sc->ip, lblk, -1, &bp);
 	}
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	/* XXX: Check xfs_dir3_data_hdr.pad is zero once we start setting it. */
 
@@ -362,7 +362,7 @@ xfs_scrub_directory_data_bestfree(
 		if (offset == 0)
 			continue;
 		if (offset >= mp->m_dir_geo->blksize) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 		dup = (struct xfs_dir2_data_unused *)(bp->b_addr + offset);
@@ -372,13 +372,13 @@ xfs_scrub_directory_data_bestfree(
 		if (dup->freetag != cpu_to_be16(XFS_DIR2_DATA_FREE_TAG) ||
 		    be16_to_cpu(dup->length) != be16_to_cpu(dfp->length) ||
 		    tag != ((char *)dup - (char *)bp->b_addr)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
 		/* bestfree records should be ordered largest to smallest */
 		if (smallest_bestfree < be16_to_cpu(dfp->length)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
@@ -400,7 +400,7 @@ xfs_scrub_directory_data_bestfree(
 			dep = (struct xfs_dir2_data_entry *)ptr;
 			newlen = d_ops->data_entsize(dep->namelen);
 			if (newlen <= 0) {
-				xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+				xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 						lblk);
 				goto out_buf;
 			}
@@ -411,7 +411,7 @@ xfs_scrub_directory_data_bestfree(
 		/* Spot check this free entry */
 		tag = be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup));
 		if (tag != ((char *)dup - (char *)bp->b_addr)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 
@@ -419,14 +419,14 @@ xfs_scrub_directory_data_bestfree(
 		 * Either this entry is a bestfree or it's smaller than
 		 * any of the bestfrees.
 		 */
-		xfs_scrub_directory_check_free_entry(sc, lblk, bf, dup);
+		xchk_directory_check_free_entry(sc, lblk, bf, dup);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out_buf;
 
 		/* Move on. */
 		newlen = be16_to_cpu(dup->length);
 		if (newlen <= 0) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out_buf;
 		}
 		ptr += newlen;
@@ -436,11 +436,11 @@ xfs_scrub_directory_data_bestfree(
 
 	/* We're required to fill all the space. */
 	if (ptr != endptr)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 
 	/* Did we see at least as many free slots as there are bestfrees? */
 	if (nr_frees < nr_bestfrees)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 out_buf:
 	xfs_trans_brelse(sc->tp, bp);
 out:
@@ -454,7 +454,7 @@ out:
  * array is in order.
  */
 STATIC void
-xfs_scrub_directory_check_freesp(
+xchk_directory_check_freesp(
 	struct xfs_scrub_context	*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_buf			*dbp,
@@ -465,15 +465,15 @@ xfs_scrub_directory_check_freesp(
 	dfp = sc->ip->d_ops->data_bestfree_p(dbp->b_addr);
 
 	if (len != be16_to_cpu(dfp->length))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 
 	if (len > 0 && be16_to_cpu(dfp->offset) == 0)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 }
 
 /* Check free space info in a directory leaf1 block. */
 STATIC int
-xfs_scrub_directory_leaf1_bestfree(
+xchk_directory_leaf1_bestfree(
 	struct xfs_scrub_context	*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
@@ -497,9 +497,9 @@ xfs_scrub_directory_leaf1_bestfree(
 
 	/* Read the free space block. */
 	error = xfs_dir3_leaf_read(sc->tp, sc->ip, lblk, -1, &bp);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	leaf = bp->b_addr;
 	d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
@@ -512,7 +512,7 @@ xfs_scrub_directory_leaf1_bestfree(
 		struct xfs_dir3_leaf_hdr	*hdr3 = bp->b_addr;
 
 		if (hdr3->pad != cpu_to_be32(0))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	}
 
 	/*
@@ -520,19 +520,19 @@ xfs_scrub_directory_leaf1_bestfree(
 	 * blocks that can fit under i_size.
 	 */
 	if (bestcount != xfs_dir2_byte_to_db(geo, sc->ip->i_d.di_size)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
 	/* Is the leaf count even remotely sane? */
 	if (leafhdr.count > d_ops->leaf_max_ents(geo)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
 	/* Leaves and bests don't overlap in leaf format. */
 	if ((char *)&ents[leafhdr.count] > (char *)bestp) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		goto out;
 	}
 
@@ -540,13 +540,13 @@ xfs_scrub_directory_leaf1_bestfree(
 	for (i = 0; i < leafhdr.count; i++) {
 		hash = be32_to_cpu(ents[i].hashval);
 		if (i > 0 && lasthash > hash)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 		lasthash = hash;
 		if (ents[i].address == cpu_to_be32(XFS_DIR2_NULL_DATAPTR))
 			stale++;
 	}
 	if (leafhdr.stale != stale)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
@@ -557,10 +557,10 @@ xfs_scrub_directory_leaf1_bestfree(
 			continue;
 		error = xfs_dir3_data_read(sc->tp, sc->ip,
 				i * args->geo->fsbcount, -1, &dbp);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
 			break;
-		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
+		xchk_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
 		if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 			goto out;
@@ -571,7 +571,7 @@ out:
 
 /* Check free space info in a directory freespace block. */
 STATIC int
-xfs_scrub_directory_free_bestfree(
+xchk_directory_free_bestfree(
 	struct xfs_scrub_context	*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
@@ -587,15 +587,15 @@ xfs_scrub_directory_free_bestfree(
 
 	/* Read the free space block */
 	error = xfs_dir2_free_read(sc->tp, sc->ip, lblk, &bp);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
-	xfs_scrub_buffer_recheck(sc, bp);
+	xchk_buffer_recheck(sc, bp);
 
 	if (xfs_sb_version_hascrc(&sc->mp->m_sb)) {
 		struct xfs_dir3_free_hdr	*hdr3 = bp->b_addr;
 
 		if (hdr3->pad != cpu_to_be32(0))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 	}
 
 	/* Check all the entries. */
@@ -610,22 +610,22 @@ xfs_scrub_directory_free_bestfree(
 		error = xfs_dir3_data_read(sc->tp, sc->ip,
 				(freehdr.firstdb + i) * args->geo->fsbcount,
 				-1, &dbp);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk,
 				&error))
 			break;
-		xfs_scrub_directory_check_freesp(sc, lblk, dbp, best);
+		xchk_directory_check_freesp(sc, lblk, dbp, best);
 		xfs_trans_brelse(sc->tp, dbp);
 	}
 
 	if (freehdr.nused + stale != freehdr.nvalid)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 out:
 	return error;
 }
 
 /* Check free space information in directories. */
 STATIC int
-xfs_scrub_directory_blocks(
+xchk_directory_blocks(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_bmbt_irec		got;
@@ -656,7 +656,7 @@ xfs_scrub_directory_blocks(
 	args.geo = mp->m_dir_geo;
 	args.trans = sc->tp;
 	error = xfs_dir2_isblock(&args, &is_block);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, lblk, &error))
 		goto out;
 
 	/* Iterate all the data extents in the directory... */
@@ -666,7 +666,7 @@ xfs_scrub_directory_blocks(
 		if (is_block &&
 		    (got.br_startoff > 0 ||
 		     got.br_blockcount != args.geo->fsbcount)) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					got.br_startoff);
 			break;
 		}
@@ -690,7 +690,7 @@ xfs_scrub_directory_blocks(
 				args.geo->fsbcount);
 		     lblk < got.br_startoff + got.br_blockcount;
 		     lblk += args.geo->fsbcount) {
-			error = xfs_scrub_directory_data_bestfree(sc, lblk,
+			error = xchk_directory_data_bestfree(sc, lblk,
 					is_block);
 			if (error)
 				goto out;
@@ -709,10 +709,10 @@ xfs_scrub_directory_blocks(
 	    got.br_blockcount == args.geo->fsbcount &&
 	    !xfs_iext_next_extent(ifp, &icur, &got)) {
 		if (is_block) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
-		error = xfs_scrub_directory_leaf1_bestfree(sc, &args,
+		error = xchk_directory_leaf1_bestfree(sc, &args,
 				leaf_lblk);
 		if (error)
 			goto out;
@@ -731,11 +731,11 @@ xfs_scrub_directory_blocks(
 		 */
 		lblk = got.br_startoff;
 		if (lblk & ~0xFFFFFFFFULL) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
 		if (is_block) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, lblk);
 			goto out;
 		}
 
@@ -754,7 +754,7 @@ xfs_scrub_directory_blocks(
 				args.geo->fsbcount);
 		     lblk < got.br_startoff + got.br_blockcount;
 		     lblk += args.geo->fsbcount) {
-			error = xfs_scrub_directory_free_bestfree(sc, &args,
+			error = xchk_directory_free_bestfree(sc, &args,
 					lblk);
 			if (error)
 				goto out;
@@ -769,11 +769,11 @@ out:
 
 /* Scrub a whole directory. */
 int
-xfs_scrub_directory(
+xchk_directory(
 	struct xfs_scrub_context	*sc)
 {
-	struct xfs_scrub_dir_ctx	sdc = {
-		.dir_iter.actor = xfs_scrub_dir_actor,
+	struct xchk_dir_ctx		sdc = {
+		.dir_iter.actor = xchk_dir_actor,
 		.dir_iter.pos = 0,
 		.sc = sc,
 	};
@@ -786,12 +786,12 @@ xfs_scrub_directory(
 
 	/* Plausible size? */
 	if (sc->ip->i_d.di_size < xfs_dir2_sf_hdr_size(0)) {
-		xfs_scrub_ino_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 		goto out;
 	}
 
 	/* Check directory tree structure */
-	error = xfs_scrub_da_btree(sc, XFS_DATA_FORK, xfs_scrub_dir_rec, NULL);
+	error = xchk_da_btree(sc, XFS_DATA_FORK, xchk_dir_rec, NULL);
 	if (error)
 		return error;
 
@@ -799,7 +799,7 @@ xfs_scrub_directory(
 		return error;
 
 	/* Check the freespace. */
-	error = xfs_scrub_directory_blocks(sc);
+	error = xchk_directory_blocks(sc);
 	if (error)
 		return error;
 
@@ -816,7 +816,7 @@ xfs_scrub_directory(
 	/*
 	 * Look up every name in this directory by hash.
 	 *
-	 * Use the xfs_readdir function to call xfs_scrub_dir_actor on
+	 * Use the xfs_readdir function to call xchk_dir_actor on
 	 * every directory entry in this directory.  In _actor, we check
 	 * the name, inode number, and ftype (if applicable) of the
 	 * entry.  xfs_readdir uses the VFS filldir functions to provide
@@ -834,7 +834,7 @@ xfs_scrub_directory(
 	xfs_iunlock(sc->ip, XFS_ILOCK_EXCL);
 	while (true) {
 		error = xfs_readdir(sc->tp, sc->ip, &sdc.dir_iter, bufsize);
-		if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0,
+		if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			goto out;
 		if (oldpos == sdc.dir_iter.pos)
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 13d43d108574..69d652b7299c 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -35,11 +35,11 @@
  * try again after forcing logged inode cores out to disk.
  */
 int
-xfs_scrub_setup_ag_iallocbt(
+xchk_setup_ag_iallocbt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, sc->try_harder);
+	return xchk_setup_ag_btree(sc, ip, sc->try_harder);
 }
 
 /* Inode btree scrubber. */
@@ -50,7 +50,7 @@ xfs_scrub_setup_ag_iallocbt(
  * we have a record or not depending on freecount.
  */
 static inline void
-xfs_scrub_iallocbt_chunk_xref_other(
+xchk_iallocbt_chunk_xref_other(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino)
@@ -66,16 +66,16 @@ xfs_scrub_iallocbt_chunk_xref_other(
 	if (!(*pcur))
 		return;
 	error = xfs_ialloc_has_inode_record(*pcur, agino, agino, &has_irec);
-	if (!xfs_scrub_should_check_xref(sc, &error, pcur))
+	if (!xchk_should_check_xref(sc, &error, pcur))
 		return;
 	if (((irec->ir_freecount > 0 && !has_irec) ||
 	     (irec->ir_freecount == 0 && has_irec)))
-		xfs_scrub_btree_xref_set_corrupt(sc, *pcur, 0);
+		xchk_btree_xref_set_corrupt(sc, *pcur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_iallocbt_chunk_xref(
+xchk_iallocbt_chunk_xref(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
@@ -87,17 +87,17 @@ xfs_scrub_iallocbt_chunk_xref(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
-	xfs_scrub_iallocbt_chunk_xref_other(sc, irec, agino);
+	xchk_xref_is_used_space(sc, agbno, len);
+	xchk_iallocbt_chunk_xref_other(sc, irec, agino);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	xfs_scrub_xref_is_owned_by(sc, agbno, len, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, len);
+	xchk_xref_is_owned_by(sc, agbno, len, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, len);
 }
 
 /* Is this chunk worth checking? */
 STATIC bool
-xfs_scrub_iallocbt_chunk(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_chunk(
+	struct xchk_btree		*bs,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
 	xfs_extlen_t			len)
@@ -110,16 +110,16 @@ xfs_scrub_iallocbt_chunk(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
+	xchk_iallocbt_chunk_xref(bs->sc, irec, agino, bno, len);
 
 	return true;
 }
 
 /* Count the number of free inodes. */
 static unsigned int
-xfs_scrub_iallocbt_freecount(
+xchk_iallocbt_freecount(
 	xfs_inofree_t			freemask)
 {
 	BUILD_BUG_ON(sizeof(freemask) != sizeof(__u64));
@@ -128,8 +128,8 @@ xfs_scrub_iallocbt_freecount(
 
 /* Check a particular inode with ir_free. */
 STATIC int
-xfs_scrub_iallocbt_check_cluster_freemask(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_check_cluster_freemask(
+	struct xchk_btree		*bs,
 	xfs_ino_t			fsino,
 	xfs_agino_t			chunkino,
 	xfs_agino_t			clusterino,
@@ -143,14 +143,14 @@ xfs_scrub_iallocbt_check_cluster_freemask(
 	bool				inuse;
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(bs->sc, &error))
+	if (xchk_should_terminate(bs->sc, &error))
 		return error;
 
 	dip = xfs_buf_offset(bp, clusterino * mp->m_sb.sb_inodesize);
 	if (be16_to_cpu(dip->di_magic) != XFS_DINODE_MAGIC ||
 	    (dip->di_version >= 3 &&
 	     be64_to_cpu(dip->di_ino) != fsino + clusterino)) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		goto out;
 	}
 
@@ -175,15 +175,15 @@ xfs_scrub_iallocbt_check_cluster_freemask(
 		freemask_ok = inode_is_free ^ inuse;
 	}
 	if (!freemask_ok)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 out:
 	return 0;
 }
 
 /* Make sure the free mask is consistent with what the inodes think. */
 STATIC int
-xfs_scrub_iallocbt_check_freemask(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_check_freemask(
+	struct xchk_btree		*bs,
 	struct xfs_inobt_rec_incore	*irec)
 {
 	struct xfs_owner_info		oinfo;
@@ -223,18 +223,18 @@ xfs_scrub_iallocbt_check_freemask(
 		/* The whole cluster must be a hole or not a hole. */
 		ir_holemask = (irec->ir_holemask & holemask);
 		if (ir_holemask != holemask && ir_holemask != 0) {
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 			continue;
 		}
 
 		/* If any part of this is a hole, skip it. */
 		if (ir_holemask) {
-			xfs_scrub_xref_is_not_owned_by(bs->sc, agbno,
+			xchk_xref_is_not_owned_by(bs->sc, agbno,
 					blks_per_cluster, &oinfo);
 			continue;
 		}
 
-		xfs_scrub_xref_is_owned_by(bs->sc, agbno, blks_per_cluster,
+		xchk_xref_is_owned_by(bs->sc, agbno, blks_per_cluster,
 				&oinfo);
 
 		/* Grab the inode cluster buffer. */
@@ -245,13 +245,13 @@ xfs_scrub_iallocbt_check_freemask(
 
 		error = xfs_imap_to_bp(mp, bs->cur->bc_tp, &imap,
 				&dip, &bp, 0, 0);
-		if (!xfs_scrub_btree_xref_process_error(bs->sc, bs->cur, 0,
+		if (!xchk_btree_xref_process_error(bs->sc, bs->cur, 0,
 				&error))
 			continue;
 
 		/* Which inodes are free? */
 		for (clusterino = 0; clusterino < nr_inodes; clusterino++) {
-			error = xfs_scrub_iallocbt_check_cluster_freemask(bs,
+			error = xchk_iallocbt_check_cluster_freemask(bs,
 					fsino, chunkino, clusterino, irec, bp);
 			if (error) {
 				xfs_trans_brelse(bs->cur->bc_tp, bp);
@@ -267,8 +267,8 @@ xfs_scrub_iallocbt_check_freemask(
 
 /* Scrub an inobt/finobt record. */
 STATIC int
-xfs_scrub_iallocbt_rec(
-	struct xfs_scrub_btree		*bs,
+xchk_iallocbt_rec(
+	struct xchk_btree		*bs,
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
@@ -289,18 +289,18 @@ xfs_scrub_iallocbt_rec(
 
 	if (irec.ir_count > XFS_INODES_PER_CHUNK ||
 	    irec.ir_freecount > XFS_INODES_PER_CHUNK)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	real_freecount = irec.ir_freecount +
 			(XFS_INODES_PER_CHUNK - irec.ir_count);
-	if (real_freecount != xfs_scrub_iallocbt_freecount(irec.ir_free))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+	if (real_freecount != xchk_iallocbt_freecount(irec.ir_free))
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	agino = irec.ir_startino;
 	/* Record has to be properly aligned within the AG. */
 	if (!xfs_verify_agino(mp, agno, agino) ||
 	    !xfs_verify_agino(mp, agno, agino + XFS_INODES_PER_CHUNK - 1)) {
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		goto out;
 	}
 
@@ -308,7 +308,7 @@ xfs_scrub_iallocbt_rec(
 	agbno = XFS_AGINO_TO_AGBNO(mp, irec.ir_startino);
 	if ((agbno & (xfs_ialloc_cluster_alignment(mp) - 1)) ||
 	    (agbno & (xfs_icluster_size_fsb(mp) - 1)))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	*inode_blocks += XFS_B_TO_FSB(mp,
 			irec.ir_count * mp->m_sb.sb_inodesize);
@@ -318,9 +318,9 @@ xfs_scrub_iallocbt_rec(
 		len = XFS_B_TO_FSB(mp,
 				XFS_INODES_PER_CHUNK * mp->m_sb.sb_inodesize);
 		if (irec.ir_count != XFS_INODES_PER_CHUNK)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-		if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+		if (!xchk_iallocbt_chunk(bs, &irec, agino, len))
 			goto out;
 		goto check_freemask;
 	}
@@ -333,12 +333,12 @@ xfs_scrub_iallocbt_rec(
 	holes = ~xfs_inobt_irec_to_allocmask(&irec);
 	if ((holes & irec.ir_free) != holes ||
 	    irec.ir_freecount > irec.ir_count)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	for (i = 0; i < XFS_INOBT_HOLEMASK_BITS; i++) {
 		if (holemask & 1)
 			holecount += XFS_INODES_PER_HOLEMASK_BIT;
-		else if (!xfs_scrub_iallocbt_chunk(bs, &irec, agino, len))
+		else if (!xchk_iallocbt_chunk(bs, &irec, agino, len))
 			break;
 		holemask >>= 1;
 		agino += XFS_INODES_PER_HOLEMASK_BIT;
@@ -346,10 +346,10 @@ xfs_scrub_iallocbt_rec(
 
 	if (holecount > XFS_INODES_PER_CHUNK ||
 	    holecount + irec.ir_count != XFS_INODES_PER_CHUNK)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 check_freemask:
-	error = xfs_scrub_iallocbt_check_freemask(bs, &irec);
+	error = xchk_iallocbt_check_freemask(bs, &irec);
 	if (error)
 		goto out;
 
@@ -362,7 +362,7 @@ out:
  * Don't bother if we're missing btree cursors, as we're already corrupt.
  */
 STATIC void
-xfs_scrub_iallocbt_xref_rmap_btreeblks(
+xchk_iallocbt_xref_rmap_btreeblks(
 	struct xfs_scrub_context	*sc,
 	int				which)
 {
@@ -374,27 +374,27 @@ xfs_scrub_iallocbt_xref_rmap_btreeblks(
 
 	if (!sc->sa.ino_cur || !sc->sa.rmap_cur ||
 	    (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur) ||
-	    xfs_scrub_skip_xref(sc->sm))
+	    xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inobt blocks as the rmap says. */
 	error = xfs_btree_count_blocks(sc->sa.ino_cur, &inobt_blocks);
-	if (!xfs_scrub_process_error(sc, 0, 0, &error))
+	if (!xchk_process_error(sc, 0, 0, &error))
 		return;
 
 	if (sc->sa.fino_cur) {
 		error = xfs_btree_count_blocks(sc->sa.fino_cur, &finobt_blocks);
-		if (!xfs_scrub_process_error(sc, 0, 0, &error))
+		if (!xchk_process_error(sc, 0, 0, &error))
 			return;
 	}
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != inobt_blocks + finobt_blocks)
-		xfs_scrub_btree_set_corrupt(sc, sc->sa.ino_cur, 0);
+		xchk_btree_set_corrupt(sc, sc->sa.ino_cur, 0);
 }
 
 /*
@@ -402,7 +402,7 @@ xfs_scrub_iallocbt_xref_rmap_btreeblks(
  * the rmap says are owned by inodes.
  */
 STATIC void
-xfs_scrub_iallocbt_xref_rmap_inodes(
+xchk_iallocbt_xref_rmap_inodes(
 	struct xfs_scrub_context	*sc,
 	int				which,
 	xfs_filblks_t			inode_blocks)
@@ -411,22 +411,22 @@ xfs_scrub_iallocbt_xref_rmap_inodes(
 	xfs_filblks_t			blocks;
 	int				error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many inode blocks as the rmap knows about. */
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, &oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != inode_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* Scrub the inode btrees for some AG. */
 STATIC int
-xfs_scrub_iallocbt(
+xchk_iallocbt(
 	struct xfs_scrub_context	*sc,
 	xfs_btnum_t			which)
 {
@@ -437,12 +437,12 @@ xfs_scrub_iallocbt(
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
 	cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
-	error = xfs_scrub_btree(sc, cur, xfs_scrub_iallocbt_rec, &oinfo,
+	error = xchk_btree(sc, cur, xchk_iallocbt_rec, &oinfo,
 			&inode_blocks);
 	if (error)
 		return error;
 
-	xfs_scrub_iallocbt_xref_rmap_btreeblks(sc, which);
+	xchk_iallocbt_xref_rmap_btreeblks(sc, which);
 
 	/*
 	 * If we're scrubbing the inode btree, inode_blocks is the number of
@@ -452,28 +452,28 @@ xfs_scrub_iallocbt(
 	 * to inode chunks with free inodes.
 	 */
 	if (which == XFS_BTNUM_INO)
-		xfs_scrub_iallocbt_xref_rmap_inodes(sc, which, inode_blocks);
+		xchk_iallocbt_xref_rmap_inodes(sc, which, inode_blocks);
 
 	return error;
 }
 
 int
-xfs_scrub_inobt(
+xchk_inobt(
 	struct xfs_scrub_context	*sc)
 {
-	return xfs_scrub_iallocbt(sc, XFS_BTNUM_INO);
+	return xchk_iallocbt(sc, XFS_BTNUM_INO);
 }
 
 int
-xfs_scrub_finobt(
+xchk_finobt(
 	struct xfs_scrub_context	*sc)
 {
-	return xfs_scrub_iallocbt(sc, XFS_BTNUM_FINO);
+	return xchk_iallocbt(sc, XFS_BTNUM_FINO);
 }
 
 /* See if an inode btree has (or doesn't have) an inode chunk record. */
 static inline void
-xfs_scrub_xref_inode_check(
+xchk_xref_inode_check(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len,
@@ -483,33 +483,33 @@ xfs_scrub_xref_inode_check(
 	bool				has_inodes;
 	int				error;
 
-	if (!(*icur) || xfs_scrub_skip_xref(sc->sm))
+	if (!(*icur) || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_ialloc_has_inodes_at_extent(*icur, agbno, len, &has_inodes);
-	if (!xfs_scrub_should_check_xref(sc, &error, icur))
+	if (!xchk_should_check_xref(sc, &error, icur))
 		return;
 	if (has_inodes != should_have_inodes)
-		xfs_scrub_btree_xref_set_corrupt(sc, *icur, 0);
+		xchk_btree_xref_set_corrupt(sc, *icur, 0);
 }
 
 /* xref check that the extent is not covered by inodes */
 void
-xfs_scrub_xref_is_not_inode_chunk(
+xchk_xref_is_not_inode_chunk(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
 }
 
 /* xref check that the extent is covered by inodes */
 void
-xfs_scrub_xref_is_inode_chunk(
+xchk_xref_is_inode_chunk(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
-	xfs_scrub_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
+	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
 }
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 7a6208505980..d85fbec39e52 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -37,7 +37,7 @@
  * the goal.
  */
 int
-xfs_scrub_setup_inode(
+xchk_setup_inode(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
@@ -47,13 +47,13 @@ xfs_scrub_setup_inode(
 	 * Try to get the inode.  If the verifiers fail, we try again
 	 * in raw mode.
 	 */
-	error = xfs_scrub_get_inode(sc, ip);
+	error = xchk_get_inode(sc, ip);
 	switch (error) {
 	case 0:
 		break;
 	case -EFSCORRUPTED:
 	case -EFSBADCRC:
-		return xfs_scrub_trans_alloc(sc, 0);
+		return xchk_trans_alloc(sc, 0);
 	default:
 		return error;
 	}
@@ -61,7 +61,7 @@ xfs_scrub_setup_inode(
 	/* Got the inode, lock it and we're ready to go. */
 	sc->ilock_flags = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	error = xfs_scrub_trans_alloc(sc, 0);
+	error = xchk_trans_alloc(sc, 0);
 	if (error)
 		goto out;
 	sc->ilock_flags |= XFS_ILOCK_EXCL;
@@ -76,7 +76,7 @@ out:
 
 /* Validate di_extsize hint. */
 STATIC void
-xfs_scrub_inode_extsize(
+xchk_inode_extsize(
 	struct xfs_scrub_context	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
@@ -88,7 +88,7 @@ xfs_scrub_inode_extsize(
 	fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize),
 			mode, flags);
 	if (fa)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /*
@@ -98,7 +98,7 @@ xfs_scrub_inode_extsize(
  * These functions must be kept in sync with each other.
  */
 STATIC void
-xfs_scrub_inode_cowextsize(
+xchk_inode_cowextsize(
 	struct xfs_scrub_context	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
@@ -112,12 +112,12 @@ xfs_scrub_inode_cowextsize(
 			be32_to_cpu(dip->di_cowextsize), mode, flags,
 			flags2);
 	if (fa)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Make sure the di_flags make sense for the inode. */
 STATIC void
-xfs_scrub_inode_flags(
+xchk_inode_flags(
 	struct xfs_scrub_context	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
@@ -157,12 +157,12 @@ xfs_scrub_inode_flags(
 
 	return;
 bad:
-	xfs_scrub_ino_set_corrupt(sc, ino);
+	xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Make sure the di_flags2 make sense for the inode. */
 STATIC void
-xfs_scrub_inode_flags2(
+xchk_inode_flags2(
 	struct xfs_scrub_context	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
@@ -200,12 +200,12 @@ xfs_scrub_inode_flags2(
 
 	return;
 bad:
-	xfs_scrub_ino_set_corrupt(sc, ino);
+	xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Scrub all the ondisk inode fields. */
 STATIC void
-xfs_scrub_dinode(
+xchk_dinode(
 	struct xfs_scrub_context	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino)
@@ -237,7 +237,7 @@ xfs_scrub_dinode(
 		/* mode is recognized */
 		break;
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
@@ -248,22 +248,22 @@ xfs_scrub_dinode(
 		 * We autoconvert v1 inodes into v2 inodes on writeout,
 		 * so just mark this inode for preening.
 		 */
-		xfs_scrub_ino_set_preen(sc, ino);
+		xchk_ino_set_preen(sc, ino);
 		break;
 	case 2:
 	case 3:
 		if (dip->di_onlink != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 
 		if (dip->di_mode == 0 && sc->ip)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 
 		if (dip->di_projid_hi != 0 &&
 		    !xfs_sb_version_hasprojid32bit(&mp->m_sb))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		return;
 	}
 
@@ -273,40 +273,40 @@ xfs_scrub_dinode(
 	 */
 	if (dip->di_uid == cpu_to_be32(-1U) ||
 	    dip->di_gid == cpu_to_be32(-1U))
-		xfs_scrub_ino_set_warning(sc, ino);
+		xchk_ino_set_warning(sc, ino);
 
 	/* di_format */
 	switch (dip->di_format) {
 	case XFS_DINODE_FMT_DEV:
 		if (!S_ISCHR(mode) && !S_ISBLK(mode) &&
 		    !S_ISFIFO(mode) && !S_ISSOCK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_LOCAL:
 		if (!S_ISDIR(mode) && !S_ISLNK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_EXTENTS:
 		if (!S_ISREG(mode) && !S_ISDIR(mode) && !S_ISLNK(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (!S_ISREG(mode) && !S_ISDIR(mode))
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_UUID:
 	default:
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
 	/* di_[amc]time.nsec */
 	if (be32_to_cpu(dip->di_atime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (be32_to_cpu(dip->di_mtime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (be32_to_cpu(dip->di_ctime.t_nsec) >= NSEC_PER_SEC)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/*
 	 * di_size.  xfs_dinode_verify checks for things that screw up
@@ -315,19 +315,19 @@ xfs_scrub_dinode(
 	 */
 	isize = be64_to_cpu(dip->di_size);
 	if (isize & (1ULL << 63))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Devices, fifos, and sockets must have zero size */
 	if (!S_ISDIR(mode) && !S_ISREG(mode) && !S_ISLNK(mode) && isize != 0)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Directories can't be larger than the data section size (32G) */
 	if (S_ISDIR(mode) && (isize == 0 || isize >= XFS_DIR2_SPACE_SIZE))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* Symlinks can't be larger than SYMLINK_MAXLEN */
 	if (S_ISLNK(mode) && (isize == 0 || isize >= XFS_SYMLINK_MAXLEN))
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/*
 	 * Warn if the running kernel can't handle the kinds of offsets
@@ -336,7 +336,7 @@ xfs_scrub_dinode(
 	 * overly large offsets, flag the inode for admin review.
 	 */
 	if (isize >= mp->m_super->s_maxbytes)
-		xfs_scrub_ino_set_warning(sc, ino);
+		xchk_ino_set_warning(sc, ino);
 
 	/* di_nblocks */
 	if (flags2 & XFS_DIFLAG2_REFLINK) {
@@ -351,15 +351,15 @@ xfs_scrub_dinode(
 		 */
 		if (be64_to_cpu(dip->di_nblocks) >=
 		    mp->m_sb.sb_dblocks + mp->m_sb.sb_rblocks)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	} else {
 		if (be64_to_cpu(dip->di_nblocks) >= mp->m_sb.sb_dblocks)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	}
 
-	xfs_scrub_inode_flags(sc, dip, ino, mode, flags);
+	xchk_inode_flags(sc, dip, ino, mode, flags);
 
-	xfs_scrub_inode_extsize(sc, dip, ino, mode, flags);
+	xchk_inode_extsize(sc, dip, ino, mode, flags);
 
 	/* di_nextents */
 	nextents = be32_to_cpu(dip->di_nextents);
@@ -367,31 +367,31 @@ xfs_scrub_dinode(
 	switch (dip->di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
 		if (nextents > fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (nextents <= fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
 		if (nextents != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	}
 
 	/* di_forkoff */
 	if (XFS_DFORK_APTR(dip) >= (char *)dip + mp->m_sb.sb_inodesize)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (dip->di_anextents != 0 && dip->di_forkoff == 0)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 	if (dip->di_forkoff == 0 && dip->di_aformat != XFS_DINODE_FMT_EXTENTS)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* di_aformat */
 	if (dip->di_aformat != XFS_DINODE_FMT_LOCAL &&
 	    dip->di_aformat != XFS_DINODE_FMT_EXTENTS &&
 	    dip->di_aformat != XFS_DINODE_FMT_BTREE)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 
 	/* di_anextents */
 	nextents = be16_to_cpu(dip->di_anextents);
@@ -399,22 +399,22 @@ xfs_scrub_dinode(
 	switch (dip->di_aformat) {
 	case XFS_DINODE_FMT_EXTENTS:
 		if (nextents > fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	case XFS_DINODE_FMT_BTREE:
 		if (nextents <= fork_recs)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 		break;
 	default:
 		if (nextents != 0)
-			xfs_scrub_ino_set_corrupt(sc, ino);
+			xchk_ino_set_corrupt(sc, ino);
 	}
 
 	if (dip->di_version >= 3) {
 		if (be32_to_cpu(dip->di_crtime.t_nsec) >= NSEC_PER_SEC)
-			xfs_scrub_ino_set_corrupt(sc, ino);
-		xfs_scrub_inode_flags2(sc, dip, ino, mode, flags, flags2);
-		xfs_scrub_inode_cowextsize(sc, dip, ino, mode, flags,
+			xchk_ino_set_corrupt(sc, ino);
+		xchk_inode_flags2(sc, dip, ino, mode, flags, flags2);
+		xchk_inode_cowextsize(sc, dip, ino, mode, flags,
 				flags2);
 	}
 }
@@ -425,7 +425,7 @@ xfs_scrub_dinode(
  * IGET_UNTRUSTED, which checks the inobt for us.
  */
 static void
-xfs_scrub_inode_xref_finobt(
+xchk_inode_xref_finobt(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			ino)
 {
@@ -434,7 +434,7 @@ xfs_scrub_inode_xref_finobt(
 	int				has_record;
 	int				error;
 
-	if (!sc->sa.fino_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.fino_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	agino = XFS_INO_TO_AGINO(sc->mp, ino);
@@ -445,12 +445,12 @@ xfs_scrub_inode_xref_finobt(
 	 */
 	error = xfs_inobt_lookup(sc->sa.fino_cur, agino, XFS_LOOKUP_LE,
 			&has_record);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
 	    !has_record)
 		return;
 
 	error = xfs_inobt_get_rec(sc->sa.fino_cur, &rec, &has_record);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.fino_cur) ||
 	    !has_record)
 		return;
 
@@ -463,12 +463,12 @@ xfs_scrub_inode_xref_finobt(
 		return;
 
 	if (rec.ir_free & XFS_INOBT_MASK(agino - rec.ir_startino))
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.fino_cur, 0);
 }
 
 /* Cross reference the inode fields with the forks. */
 STATIC void
-xfs_scrub_inode_xref_bmap(
+xchk_inode_xref_bmap(
 	struct xfs_scrub_context	*sc,
 	struct xfs_dinode		*dip)
 {
@@ -477,32 +477,32 @@ xfs_scrub_inode_xref_bmap(
 	xfs_filblks_t			acount;
 	int				error;
 
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return;
 
 	/* Walk all the extents to check nextents/naextents/nblocks. */
 	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_DATA_FORK,
 			&nextents, &count);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents < be32_to_cpu(dip->di_nextents))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 
 	error = xfs_bmap_count_blocks(sc->tp, sc->ip, XFS_ATTR_FORK,
 			&nextents, &acount);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (nextents != be16_to_cpu(dip->di_anextents))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 
 	/* Check nblocks against the inode. */
 	if (count + acount != be64_to_cpu(dip->di_nblocks))
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->ip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->ip->i_ino);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_inode_xref(
+xchk_inode_xref(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			ino,
 	struct xfs_dinode		*dip)
@@ -518,18 +518,18 @@ xfs_scrub_inode_xref(
 	agno = XFS_INO_TO_AGNO(sc->mp, ino);
 	agbno = XFS_INO_TO_AGBNO(sc->mp, ino);
 
-	error = xfs_scrub_ag_init(sc, agno, &sc->sa);
-	if (!xfs_scrub_xref_process_error(sc, agno, agbno, &error))
+	error = xchk_ag_init(sc, agno, &sc->sa);
+	if (!xchk_xref_process_error(sc, agno, agbno, &error))
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, 1);
-	xfs_scrub_inode_xref_finobt(sc, ino);
+	xchk_xref_is_used_space(sc, agbno, 1);
+	xchk_inode_xref_finobt(sc, ino);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
-	xfs_scrub_xref_is_owned_by(sc, agbno, 1, &oinfo);
-	xfs_scrub_xref_is_not_shared(sc, agbno, 1);
-	xfs_scrub_inode_xref_bmap(sc, dip);
+	xchk_xref_is_owned_by(sc, agbno, 1, &oinfo);
+	xchk_xref_is_not_shared(sc, agbno, 1);
+	xchk_inode_xref_bmap(sc, dip);
 
-	xfs_scrub_ag_free(sc, &sc->sa);
+	xchk_ag_free(sc, &sc->sa);
 }
 
 /*
@@ -539,7 +539,7 @@ xfs_scrub_inode_xref(
  * reflink filesystem.
  */
 static void
-xfs_scrub_inode_check_reflink_iflag(
+xchk_inode_check_reflink_iflag(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			ino)
 {
@@ -552,18 +552,18 @@ xfs_scrub_inode_check_reflink_iflag(
 
 	error = xfs_reflink_inode_has_shared_extents(sc->tp, sc->ip,
 			&has_shared);
-	if (!xfs_scrub_xref_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
+	if (!xchk_xref_process_error(sc, XFS_INO_TO_AGNO(mp, ino),
 			XFS_INO_TO_AGBNO(mp, ino), &error))
 		return;
 	if (xfs_is_reflink_inode(sc->ip) && !has_shared)
-		xfs_scrub_ino_set_preen(sc, ino);
+		xchk_ino_set_preen(sc, ino);
 	else if (!xfs_is_reflink_inode(sc->ip) && has_shared)
-		xfs_scrub_ino_set_corrupt(sc, ino);
+		xchk_ino_set_corrupt(sc, ino);
 }
 
 /* Scrub an inode. */
 int
-xfs_scrub_inode(
+xchk_inode(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_dinode		di;
@@ -575,13 +575,13 @@ xfs_scrub_inode(
 	 * and a NULL inode, so flag the corruption error and return.
 	 */
 	if (!sc->ip) {
-		xfs_scrub_ino_set_corrupt(sc, sc->sm->sm_ino);
+		xchk_ino_set_corrupt(sc, sc->sm->sm_ino);
 		return 0;
 	}
 
 	/* Scrub the inode core. */
 	xfs_inode_to_disk(sc->ip, &di, 0);
-	xfs_scrub_dinode(sc, &di, sc->ip->i_ino);
+	xchk_dinode(sc, &di, sc->ip->i_ino);
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		goto out;
 
@@ -591,9 +591,9 @@ xfs_scrub_inode(
 	 * we scrubbed the dinode.
 	 */
 	if (S_ISREG(VFS_I(sc->ip)->i_mode))
-		xfs_scrub_inode_check_reflink_iflag(sc, sc->ip->i_ino);
+		xchk_inode_check_reflink_iflag(sc, sc->ip->i_ino);
 
-	xfs_scrub_inode_xref(sc, sc->ip->i_ino, &di);
+	xchk_inode_xref(sc, sc->ip->i_ino, &di);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index e2bda58c32f0..0a78d8411f23 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -27,18 +27,18 @@
 
 /* Set us up to scrub parents. */
 int
-xfs_scrub_setup_parent(
+xchk_setup_parent(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Parent pointers */
 
 /* Look for an entry in a parent pointing to this inode. */
 
-struct xfs_scrub_parent_ctx {
+struct xchk_parent_ctx {
 	struct dir_context		dc;
 	xfs_ino_t			ino;
 	xfs_nlink_t			nlink;
@@ -46,7 +46,7 @@ struct xfs_scrub_parent_ctx {
 
 /* Look for a single entry in a directory pointing to an inode. */
 STATIC int
-xfs_scrub_parent_actor(
+xchk_parent_actor(
 	struct dir_context		*dc,
 	const char			*name,
 	int				namelen,
@@ -54,9 +54,9 @@ xfs_scrub_parent_actor(
 	u64				ino,
 	unsigned			type)
 {
-	struct xfs_scrub_parent_ctx	*spc;
+	struct xchk_parent_ctx		*spc;
 
-	spc = container_of(dc, struct xfs_scrub_parent_ctx, dc);
+	spc = container_of(dc, struct xchk_parent_ctx, dc);
 	if (spc->ino == ino)
 		spc->nlink++;
 	return 0;
@@ -64,13 +64,13 @@ xfs_scrub_parent_actor(
 
 /* Count the number of dentries in the parent dir that point to this inode. */
 STATIC int
-xfs_scrub_parent_count_parent_dentries(
+xchk_parent_count_parent_dentries(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*parent,
 	xfs_nlink_t			*nlink)
 {
-	struct xfs_scrub_parent_ctx	spc = {
-		.dc.actor = xfs_scrub_parent_actor,
+	struct xchk_parent_ctx		spc = {
+		.dc.actor = xchk_parent_actor,
 		.dc.pos = 0,
 		.ino = sc->ip->i_ino,
 		.nlink = 0,
@@ -120,7 +120,7 @@ out:
  * entry pointing back to the inode being scrubbed.
  */
 STATIC int
-xfs_scrub_parent_validate(
+xchk_parent_validate(
 	struct xfs_scrub_context	*sc,
 	xfs_ino_t			dnum,
 	bool				*try_again)
@@ -138,7 +138,7 @@ xfs_scrub_parent_validate(
 
 	/* '..' must not point to ourselves. */
 	if (sc->ip->i_ino == dnum) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -165,13 +165,13 @@ xfs_scrub_parent_validate(
 	error = xfs_iget(mp, sc->tp, dnum, XFS_IGET_UNTRUSTED, 0, &dp);
 	if (error == -EINVAL) {
 		error = -EFSCORRUPTED;
-		xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error);
+		xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error);
 		goto out;
 	}
-	if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (dp == sc->ip || !S_ISDIR(VFS_I(dp)->i_mode)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_rele;
 	}
 
@@ -183,12 +183,12 @@ xfs_scrub_parent_validate(
 	 * the child inodes.
 	 */
 	if (xfs_ilock_nowait(dp, XFS_IOLOCK_SHARED)) {
-		error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
-		if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
+		error = xchk_parent_count_parent_dentries(sc, dp, &nlink);
+		if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0,
 				&error))
 			goto out_unlock;
 		if (nlink != expected_nlink)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out_unlock;
 	}
 
@@ -200,18 +200,18 @@ xfs_scrub_parent_validate(
 	 */
 	xfs_iunlock(sc->ip, sc->ilock_flags);
 	sc->ilock_flags = 0;
-	error = xfs_scrub_ilock_inverted(dp, XFS_IOLOCK_SHARED);
+	error = xchk_ilock_inverted(dp, XFS_IOLOCK_SHARED);
 	if (error)
 		goto out_rele;
 
 	/* Go looking for our dentry. */
-	error = xfs_scrub_parent_count_parent_dentries(sc, dp, &nlink);
-	if (!xfs_scrub_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
+	error = xchk_parent_count_parent_dentries(sc, dp, &nlink);
+	if (!xchk_fblock_xref_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out_unlock;
 
 	/* Drop the parent lock, relock this inode. */
 	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
-	error = xfs_scrub_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
+	error = xchk_ilock_inverted(sc->ip, XFS_IOLOCK_EXCL);
 	if (error)
 		goto out_rele;
 	sc->ilock_flags = XFS_IOLOCK_EXCL;
@@ -225,7 +225,7 @@ xfs_scrub_parent_validate(
 
 	/* Look up '..' to see if the inode changed. */
 	error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out_rele;
 
 	/* Drat, parent changed.  Try again! */
@@ -241,7 +241,7 @@ xfs_scrub_parent_validate(
 	 * for us in the parent.
 	 */
 	if (nlink != expected_nlink)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return error;
 
 out_unlock:
@@ -254,7 +254,7 @@ out:
 
 /* Scrub a parent pointer. */
 int
-xfs_scrub_parent(
+xchk_parent(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
@@ -272,7 +272,7 @@ xfs_scrub_parent(
 
 	/* We're not a special inode, are we? */
 	if (!xfs_verify_dir_ino(mp, sc->ip->i_ino)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -288,10 +288,10 @@ xfs_scrub_parent(
 
 	/* Look up '..' */
 	error = xfs_dir_lookup(sc->tp, sc->ip, &xfs_name_dotdot, &dnum, NULL);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (!xfs_verify_dir_ino(mp, dnum)) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -299,12 +299,12 @@ xfs_scrub_parent(
 	if (sc->ip == mp->m_rootip) {
 		if (sc->ip->i_ino != mp->m_sb.sb_rootino ||
 		    sc->ip->i_ino != dnum)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
 	do {
-		error = xfs_scrub_parent_validate(sc, dnum, &try_again);
+		error = xchk_parent_validate(sc, dnum, &try_again);
 		if (error)
 			goto out;
 	} while (try_again && ++tries < 20);
@@ -314,7 +314,7 @@ xfs_scrub_parent(
 	 * incomplete.  Userspace can decide if it wants to try again.
 	 */
 	if (try_again && tries == 20)
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 out:
 	/*
 	 * If we failed to lock the parent inode even after a retry, just mark
@@ -322,7 +322,7 @@ out:
 	 */
 	if (sc->try_harder && error == -EDEADLOCK) {
 		error = 0;
-		xfs_scrub_set_incomplete(sc);
+		xchk_set_incomplete(sc);
 	}
 	return error;
 }
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 6ff906aa0a3b..d1b52dd7efcd 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -30,7 +30,7 @@
 
 /* Convert a scrub type code to a DQ flag, or return 0 if error. */
 static inline uint
-xfs_scrub_quota_to_dqtype(
+xchk_quota_to_dqtype(
 	struct xfs_scrub_context	*sc)
 {
 	switch (sc->sm->sm_type) {
@@ -47,7 +47,7 @@ xfs_scrub_quota_to_dqtype(
 
 /* Set us up to scrub a quota. */
 int
-xfs_scrub_setup_quota(
+xchk_setup_quota(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
@@ -57,14 +57,14 @@ xfs_scrub_setup_quota(
 	if (!XFS_IS_QUOTA_RUNNING(sc->mp) || !XFS_IS_QUOTA_ON(sc->mp))
 		return -ENOENT;
 
-	dqtype = xfs_scrub_quota_to_dqtype(sc);
+	dqtype = xchk_quota_to_dqtype(sc);
 	if (dqtype == 0)
 		return -EINVAL;
 	sc->has_quotaofflock = true;
 	mutex_lock(&sc->mp->m_quotainfo->qi_quotaofflock);
 	if (!xfs_this_quota_on(sc->mp, dqtype))
 		return -ENOENT;
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 	sc->ip = xfs_quota_inode(sc->mp, dqtype);
@@ -75,19 +75,19 @@ xfs_scrub_setup_quota(
 
 /* Quotas. */
 
-struct xfs_scrub_quota_info {
+struct xchk_quota_info {
 	struct xfs_scrub_context	*sc;
 	xfs_dqid_t			last_id;
 };
 
 /* Scrub the fields in an individual quota item. */
 STATIC int
-xfs_scrub_quota_item(
+xchk_quota_item(
 	struct xfs_dquot		*dq,
 	uint				dqtype,
 	void				*priv)
 {
-	struct xfs_scrub_quota_info	*sqi = priv;
+	struct xchk_quota_info		*sqi = priv;
 	struct xfs_scrub_context	*sc = sqi->sc;
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_disk_dquot		*d = &dq->q_core;
@@ -111,16 +111,16 @@ xfs_scrub_quota_item(
 	 */
 	offset = id / qi->qi_dqperchunk;
 	if (id && id <= sqi->last_id)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	sqi->last_id = id;
 
 	/* Did we get the dquot type we wanted? */
 	if (dqtype != (d->d_flags & XFS_DQ_ALLTYPES))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (d->d_pad0 != cpu_to_be32(0) || d->d_pad != cpu_to_be16(0))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/* Check the limits. */
 	bhard = be64_to_cpu(d->d_blk_hardlimit);
@@ -140,19 +140,19 @@ xfs_scrub_quota_item(
 	 * the hard limit.
 	 */
 	if (bhard > mp->m_sb.sb_dblocks)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (bsoft > bhard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (ihard > mp->m_maxicount)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (isoft > ihard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	if (rhard > mp->m_sb.sb_rblocks)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (rsoft > rhard)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/* Check the resource counts. */
 	bcount = be64_to_cpu(d->d_bcount);
@@ -167,15 +167,15 @@ xfs_scrub_quota_item(
 	 */
 	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
 		if (mp->m_sb.sb_dblocks < bcount)
-			xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK,
+			xchk_fblock_set_warning(sc, XFS_DATA_FORK,
 					offset);
 	} else {
 		if (mp->m_sb.sb_dblocks < bcount)
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					offset);
 	}
 	if (icount > fs_icount || rcount > mp->m_sb.sb_rblocks)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, offset);
 
 	/*
 	 * We can violate the hard limits if the admin suddenly sets a
@@ -183,18 +183,18 @@ xfs_scrub_quota_item(
 	 * admin review.
 	 */
 	if (id != 0 && bhard != 0 && bcount > bhard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (id != 0 && ihard != 0 && icount > ihard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 	if (id != 0 && rhard != 0 && rcount > rhard)
-		xfs_scrub_fblock_set_warning(sc, XFS_DATA_FORK, offset);
+		xchk_fblock_set_warning(sc, XFS_DATA_FORK, offset);
 
 	return 0;
 }
 
 /* Check the quota's data fork. */
 STATIC int
-xfs_scrub_quota_data_fork(
+xchk_quota_data_fork(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_bmbt_irec		irec = { 0 };
@@ -205,7 +205,7 @@ xfs_scrub_quota_data_fork(
 	int				error = 0;
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
@@ -213,7 +213,7 @@ xfs_scrub_quota_data_fork(
 	max_dqid_off = ((xfs_dqid_t)-1) / qi->qi_dqperchunk;
 	ifp = XFS_IFORK_PTR(sc->ip, XFS_DATA_FORK);
 	for_each_xfs_iext(ifp, &icur, &irec) {
-		if (xfs_scrub_should_terminate(sc, &error))
+		if (xchk_should_terminate(sc, &error))
 			break;
 		/*
 		 * delalloc extents or blocks mapped above the highest
@@ -222,7 +222,7 @@ xfs_scrub_quota_data_fork(
 		if (isnullstartblock(irec.br_startblock) ||
 		    irec.br_startoff > max_dqid_off ||
 		    irec.br_startoff + irec.br_blockcount - 1 > max_dqid_off) {
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK,
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK,
 					irec.br_startoff);
 			break;
 		}
@@ -233,19 +233,19 @@ xfs_scrub_quota_data_fork(
 
 /* Scrub all of a quota type's items. */
 int
-xfs_scrub_quota(
+xchk_quota(
 	struct xfs_scrub_context	*sc)
 {
-	struct xfs_scrub_quota_info	sqi;
+	struct xchk_quota_info		sqi;
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_quotainfo		*qi = mp->m_quotainfo;
 	uint				dqtype;
 	int				error = 0;
 
-	dqtype = xfs_scrub_quota_to_dqtype(sc);
+	dqtype = xchk_quota_to_dqtype(sc);
 
 	/* Look for problem extents. */
-	error = xfs_scrub_quota_data_fork(sc);
+	error = xchk_quota_data_fork(sc);
 	if (error)
 		goto out;
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
@@ -260,10 +260,10 @@ xfs_scrub_quota(
 	sc->ilock_flags = 0;
 	sqi.sc = sc;
 	sqi.last_id = 0;
-	error = xfs_qm_dqiterate(mp, dqtype, xfs_scrub_quota_item, &sqi);
+	error = xfs_qm_dqiterate(mp, dqtype, xchk_quota_item, &sqi);
 	sc->ilock_flags = XFS_ILOCK_EXCL;
 	xfs_ilock(sc->ip, sc->ilock_flags);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK,
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK,
 			sqi.last_id * qi->qi_dqperchunk, &error))
 		goto out;
 
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 607a9faa8ecc..274febc49b23 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -28,11 +28,11 @@
  * Set us up to scrub reference count btrees.
  */
 int
-xfs_scrub_setup_ag_refcountbt(
+xchk_setup_ag_refcountbt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Reference count btree scrubber. */
@@ -73,12 +73,12 @@ xfs_scrub_setup_ag_refcountbt(
  * If the refcount is correct, all the check conditions in the algorithm
  * should always hold true.  If not, the refcount is incorrect.
  */
-struct xfs_scrub_refcnt_frag {
+struct xchk_refcnt_frag {
 	struct list_head		list;
 	struct xfs_rmap_irec		rm;
 };
 
-struct xfs_scrub_refcnt_check {
+struct xchk_refcnt_check {
 	struct xfs_scrub_context	*sc;
 	struct list_head		fragments;
 
@@ -99,18 +99,18 @@ struct xfs_scrub_refcnt_check {
  * fragments as the refcountbt says we should have.
  */
 STATIC int
-xfs_scrub_refcountbt_rmap_check(
+xchk_refcountbt_rmap_check(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
-	struct xfs_scrub_refcnt_check	*refchk = priv;
-	struct xfs_scrub_refcnt_frag	*frag;
+	struct xchk_refcnt_check	*refchk = priv;
+	struct xchk_refcnt_frag		*frag;
 	xfs_agblock_t			rm_last;
 	xfs_agblock_t			rc_last;
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(refchk->sc, &error))
+	if (xchk_should_terminate(refchk->sc, &error))
 		return error;
 
 	rm_last = rec->rm_startblock + rec->rm_blockcount - 1;
@@ -118,7 +118,7 @@ xfs_scrub_refcountbt_rmap_check(
 
 	/* Confirm that a single-owner refc extent is a CoW stage. */
 	if (refchk->refcount == 1 && rec->rm_owner != XFS_RMAP_OWN_COW) {
-		xfs_scrub_btree_xref_set_corrupt(refchk->sc, cur, 0);
+		xchk_btree_xref_set_corrupt(refchk->sc, cur, 0);
 		return 0;
 	}
 
@@ -135,7 +135,7 @@ xfs_scrub_refcountbt_rmap_check(
 		 * is healthy each rmap_irec we see will be in agbno order
 		 * so we don't need insertion sort here.
 		 */
-		frag = kmem_alloc(sizeof(struct xfs_scrub_refcnt_frag),
+		frag = kmem_alloc(sizeof(struct xchk_refcnt_frag),
 				KM_MAYFAIL);
 		if (!frag)
 			return -ENOMEM;
@@ -154,12 +154,12 @@ xfs_scrub_refcountbt_rmap_check(
  * we have a refcountbt error.
  */
 STATIC void
-xfs_scrub_refcountbt_process_rmap_fragments(
-	struct xfs_scrub_refcnt_check	*refchk)
+xchk_refcountbt_process_rmap_fragments(
+	struct xchk_refcnt_check	*refchk)
 {
 	struct list_head		worklist;
-	struct xfs_scrub_refcnt_frag	*frag;
-	struct xfs_scrub_refcnt_frag	*n;
+	struct xchk_refcnt_frag		*frag;
+	struct xchk_refcnt_frag		*n;
 	xfs_agblock_t			bno;
 	xfs_agblock_t			rbno;
 	xfs_agblock_t			next_rbno;
@@ -277,13 +277,13 @@ done:
 
 /* Use the rmap entries covering this extent to verify the refcount. */
 STATIC void
-xfs_scrub_refcountbt_xref_rmap(
+xchk_refcountbt_xref_rmap(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	xfs_nlink_t			refcount)
 {
-	struct xfs_scrub_refcnt_check	refchk = {
+	struct xchk_refcnt_check	refchk = {
 		.sc = sc,
 		.bno = bno,
 		.len = len,
@@ -292,11 +292,11 @@ xfs_scrub_refcountbt_xref_rmap(
 	};
 	struct xfs_rmap_irec		low;
 	struct xfs_rmap_irec		high;
-	struct xfs_scrub_refcnt_frag	*frag;
-	struct xfs_scrub_refcnt_frag	*n;
+	struct xchk_refcnt_frag		*frag;
+	struct xchk_refcnt_frag		*n;
 	int				error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Cross-reference with the rmapbt to confirm the refcount. */
@@ -307,13 +307,13 @@ xfs_scrub_refcountbt_xref_rmap(
 
 	INIT_LIST_HEAD(&refchk.fragments);
 	error = xfs_rmap_query_range(sc->sa.rmap_cur, &low, &high,
-			&xfs_scrub_refcountbt_rmap_check, &refchk);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+			&xchk_refcountbt_rmap_check, &refchk);
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		goto out_free;
 
-	xfs_scrub_refcountbt_process_rmap_fragments(&refchk);
+	xchk_refcountbt_process_rmap_fragments(&refchk);
 	if (refcount != refchk.seen)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 
 out_free:
 	list_for_each_entry_safe(frag, n, &refchk.fragments, list) {
@@ -324,7 +324,7 @@ out_free:
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_refcountbt_xref(
+xchk_refcountbt_xref(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len,
@@ -333,15 +333,15 @@ xfs_scrub_refcountbt_xref(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
-	xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
-	xfs_scrub_refcountbt_xref_rmap(sc, agbno, len, refcount);
+	xchk_xref_is_used_space(sc, agbno, len);
+	xchk_xref_is_not_inode_chunk(sc, agbno, len);
+	xchk_refcountbt_xref_rmap(sc, agbno, len, refcount);
 }
 
 /* Scrub a refcountbt record. */
 STATIC int
-xfs_scrub_refcountbt_rec(
-	struct xfs_scrub_btree		*bs,
+xchk_refcountbt_rec(
+	struct xchk_btree		*bs,
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
@@ -360,7 +360,7 @@ xfs_scrub_refcountbt_rec(
 	/* Only CoW records can have refcount == 1. */
 	has_cowflag = (bno & XFS_REFC_COW_START);
 	if ((refcount == 1 && !has_cowflag) || (refcount != 1 && has_cowflag))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	if (has_cowflag)
 		(*cow_blocks) += len;
 
@@ -369,19 +369,19 @@ xfs_scrub_refcountbt_rec(
 	if (bno + len <= bno ||
 	    !xfs_verify_agbno(mp, agno, bno) ||
 	    !xfs_verify_agbno(mp, agno, bno + len - 1))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (refcount == 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
-	xfs_scrub_refcountbt_xref(bs->sc, bno, len, refcount);
+	xchk_refcountbt_xref(bs->sc, bno, len, refcount);
 
 	return error;
 }
 
 /* Make sure we have as many refc blocks as the rmap says. */
 STATIC void
-xfs_scrub_refcount_xref_rmap(
+xchk_refcount_xref_rmap(
 	struct xfs_scrub_context	*sc,
 	struct xfs_owner_info		*oinfo,
 	xfs_filblks_t			cow_blocks)
@@ -390,33 +390,33 @@ xfs_scrub_refcount_xref_rmap(
 	xfs_filblks_t			blocks;
 	int				error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Check that we saw as many refcbt blocks as the rmap knows about. */
 	error = xfs_btree_count_blocks(sc->sa.refc_cur, &refcbt_blocks);
-	if (!xfs_scrub_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
+	if (!xchk_btree_process_error(sc, sc->sa.refc_cur, 0, &error))
 		return;
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != refcbt_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 
 	/* Check that we saw as many cow blocks as the rmap knows about. */
 	xfs_rmap_ag_owner(oinfo, XFS_RMAP_OWN_COW);
-	error = xfs_scrub_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
+	error = xchk_count_rmap_ownedby_ag(sc, sc->sa.rmap_cur, oinfo,
 			&blocks);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (blocks != cow_blocks)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* Scrub the refcount btree for some AG. */
 int
-xfs_scrub_refcountbt(
+xchk_refcountbt(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_owner_info		oinfo;
@@ -424,19 +424,19 @@ xfs_scrub_refcountbt(
 	int				error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_REFC);
-	error = xfs_scrub_btree(sc, sc->sa.refc_cur, xfs_scrub_refcountbt_rec,
+	error = xchk_btree(sc, sc->sa.refc_cur, xchk_refcountbt_rec,
 			&oinfo, &cow_blocks);
 	if (error)
 		return error;
 
-	xfs_scrub_refcount_xref_rmap(sc, &oinfo, cow_blocks);
+	xchk_refcount_xref_rmap(sc, &oinfo, cow_blocks);
 
 	return 0;
 }
 
 /* xref check that a cow staging extent is marked in the refcountbt. */
 void
-xfs_scrub_xref_is_cow_staging(
+xchk_xref_is_cow_staging(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
@@ -446,35 +446,35 @@ xfs_scrub_xref_is_cow_staging(
 	int				has_refcount;
 	int				error;
 
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	/* Find the CoW staging extent. */
 	error = xfs_refcount_lookup_le(sc->sa.refc_cur,
 			agbno + XFS_REFC_COW_START, &has_refcount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (!has_refcount) {
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 		return;
 	}
 
 	error = xfs_refcount_get_rec(sc->sa.refc_cur, &rc, &has_refcount);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (!has_refcount) {
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 		return;
 	}
 
 	/* CoW flag must be set, refcount must be 1. */
 	has_cowflag = (rc.rc_startblock & XFS_REFC_COW_START);
 	if (!has_cowflag || rc.rc_refcount != 1)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 
 	/* Must be at least as long as what was passed in */
 	if (rc.rc_blockcount < len)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
 
 /*
@@ -482,7 +482,7 @@ xfs_scrub_xref_is_cow_staging(
  * can have multiple owners.
  */
 void
-xfs_scrub_xref_is_not_shared(
+xchk_xref_is_not_shared(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
@@ -490,12 +490,12 @@ xfs_scrub_xref_is_not_shared(
 	bool				shared;
 	int				error;
 
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_refcount_has_record(sc->sa.refc_cur, agbno, len, &shared);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (shared)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index ea39e2bdc96a..5eccd89c64a8 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -50,7 +50,7 @@ xfs_repair_attempt(
 
 	trace_xfs_repair_attempt(ip, sc->sm, error);
 
-	xfs_scrub_ag_btcur_free(&sc->sa);
+	xchk_ag_btcur_free(&sc->sa);
 
 	/* Repair whatever's broken. */
 	ASSERT(sc->ops->repair);
@@ -110,7 +110,7 @@ xfs_repair_probe(
 {
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(sc, &error))
+	if (xchk_should_terminate(sc, &error))
 		return error;
 
 	return 0;
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index c6d763236ba7..4b75fc2f31f3 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -29,18 +29,18 @@
  * Set us up to scrub reverse mapping btrees.
  */
 int
-xfs_scrub_setup_ag_rmapbt(
+xchk_setup_ag_rmapbt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
-	return xfs_scrub_setup_ag_btree(sc, ip, false);
+	return xchk_setup_ag_btree(sc, ip, false);
 }
 
 /* Reverse-mapping scrubber. */
 
 /* Cross-reference a rmap against the refcount btree. */
 STATIC void
-xfs_scrub_rmapbt_xref_refc(
+xchk_rmapbt_xref_refc(
 	struct xfs_scrub_context	*sc,
 	struct xfs_rmap_irec		*irec)
 {
@@ -52,7 +52,7 @@ xfs_scrub_rmapbt_xref_refc(
 	bool				is_unwritten;
 	int				error;
 
-	if (!sc->sa.refc_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	non_inode = XFS_RMAP_NON_INODE_OWNER(irec->rm_owner);
@@ -63,15 +63,15 @@ xfs_scrub_rmapbt_xref_refc(
 	/* If this is shared, must be a data fork extent. */
 	error = xfs_refcount_find_shared(sc->sa.refc_cur, irec->rm_startblock,
 			irec->rm_blockcount, &fbno, &flen, false);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.refc_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.refc_cur))
 		return;
 	if (flen != 0 && (non_inode || is_attr || is_bmbt || is_unwritten))
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.refc_cur, 0);
 }
 
 /* Cross-reference with the other btrees. */
 STATIC void
-xfs_scrub_rmapbt_xref(
+xchk_rmapbt_xref(
 	struct xfs_scrub_context	*sc,
 	struct xfs_rmap_irec		*irec)
 {
@@ -81,22 +81,22 @@ xfs_scrub_rmapbt_xref(
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
 
-	xfs_scrub_xref_is_used_space(sc, agbno, len);
+	xchk_xref_is_used_space(sc, agbno, len);
 	if (irec->rm_owner == XFS_RMAP_OWN_INODES)
-		xfs_scrub_xref_is_inode_chunk(sc, agbno, len);
+		xchk_xref_is_inode_chunk(sc, agbno, len);
 	else
-		xfs_scrub_xref_is_not_inode_chunk(sc, agbno, len);
+		xchk_xref_is_not_inode_chunk(sc, agbno, len);
 	if (irec->rm_owner == XFS_RMAP_OWN_COW)
-		xfs_scrub_xref_is_cow_staging(sc, irec->rm_startblock,
+		xchk_xref_is_cow_staging(sc, irec->rm_startblock,
 				irec->rm_blockcount);
 	else
-		xfs_scrub_rmapbt_xref_refc(sc, irec);
+		xchk_rmapbt_xref_refc(sc, irec);
 }
 
 /* Scrub an rmapbt record. */
 STATIC int
-xfs_scrub_rmapbt_rec(
-	struct xfs_scrub_btree		*bs,
+xchk_rmapbt_rec(
+	struct xchk_btree		*bs,
 	union xfs_btree_rec		*rec)
 {
 	struct xfs_mount		*mp = bs->cur->bc_mp;
@@ -109,12 +109,12 @@ xfs_scrub_rmapbt_rec(
 	int				error;
 
 	error = xfs_rmap_btrec_to_irec(rec, &irec);
-	if (!xfs_scrub_btree_process_error(bs->sc, bs->cur, 0, &error))
+	if (!xchk_btree_process_error(bs->sc, bs->cur, 0, &error))
 		goto out;
 
 	/* Check extent. */
 	if (irec.rm_startblock + irec.rm_blockcount <= irec.rm_startblock)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (irec.rm_owner == XFS_RMAP_OWN_FS) {
 		/*
@@ -124,7 +124,7 @@ xfs_scrub_rmapbt_rec(
 		 */
 		if (irec.rm_startblock != 0 ||
 		    irec.rm_blockcount != XFS_AGFL_BLOCK(mp) + 1)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	} else {
 		/*
 		 * Otherwise we must point somewhere past the static metadata
@@ -133,7 +133,7 @@ xfs_scrub_rmapbt_rec(
 		if (!xfs_verify_agbno(mp, agno, irec.rm_startblock) ||
 		    !xfs_verify_agbno(mp, agno, irec.rm_startblock +
 				irec.rm_blockcount - 1))
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	}
 
 	/* Check flags. */
@@ -143,47 +143,47 @@ xfs_scrub_rmapbt_rec(
 	is_unwritten = irec.rm_flags & XFS_RMAP_UNWRITTEN;
 
 	if (is_bmbt && irec.rm_offset != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (non_inode && irec.rm_offset != 0)
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (is_unwritten && (is_bmbt || non_inode || is_attr))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (non_inode && (is_bmbt || is_unwritten || is_attr))
-		xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 
 	if (!non_inode) {
 		if (!xfs_verify_ino(mp, irec.rm_owner))
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	} else {
 		/* Non-inode owner within the magic values? */
 		if (irec.rm_owner <= XFS_RMAP_OWN_MIN ||
 		    irec.rm_owner > XFS_RMAP_OWN_FS)
-			xfs_scrub_btree_set_corrupt(bs->sc, bs->cur, 0);
+			xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 	}
 
-	xfs_scrub_rmapbt_xref(bs->sc, &irec);
+	xchk_rmapbt_xref(bs->sc, &irec);
 out:
 	return error;
 }
 
 /* Scrub the rmap btree for some AG. */
 int
-xfs_scrub_rmapbt(
+xchk_rmapbt(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_owner_info		oinfo;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
-	return xfs_scrub_btree(sc, sc->sa.rmap_cur, xfs_scrub_rmapbt_rec,
+	return xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec,
 			&oinfo, NULL);
 }
 
 /* xref check that the extent is owned by a given owner */
 static inline void
-xfs_scrub_xref_check_owner(
+xchk_xref_check_owner(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
@@ -193,42 +193,42 @@ xfs_scrub_xref_check_owner(
 	bool				has_rmap;
 	int				error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_record_exists(sc->sa.rmap_cur, bno, len, oinfo,
 			&has_rmap);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (has_rmap != should_have_rmap)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
 
 /* xref check that the extent is owned by a given owner */
 void
-xfs_scrub_xref_is_owned_by(
+xchk_xref_is_owned_by(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	struct xfs_owner_info		*oinfo)
 {
-	xfs_scrub_xref_check_owner(sc, bno, len, oinfo, true);
+	xchk_xref_check_owner(sc, bno, len, oinfo, true);
 }
 
 /* xref check that the extent is not owned by a given owner */
 void
-xfs_scrub_xref_is_not_owned_by(
+xchk_xref_is_not_owned_by(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	struct xfs_owner_info		*oinfo)
 {
-	xfs_scrub_xref_check_owner(sc, bno, len, oinfo, false);
+	xchk_xref_check_owner(sc, bno, len, oinfo, false);
 }
 
 /* xref check that the extent has no reverse mapping at all */
 void
-xfs_scrub_xref_has_no_owner(
+xchk_xref_has_no_owner(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len)
@@ -236,12 +236,12 @@ xfs_scrub_xref_has_no_owner(
 	bool				has_rmap;
 	int				error;
 
-	if (!sc->sa.rmap_cur || xfs_scrub_skip_xref(sc->sm))
+	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
 
 	error = xfs_rmap_has_record(sc->sa.rmap_cur, bno, len, &has_rmap);
-	if (!xfs_scrub_should_check_xref(sc, &error, &sc->sa.rmap_cur))
+	if (!xchk_should_check_xref(sc, &error, &sc->sa.rmap_cur))
 		return;
 	if (has_rmap)
-		xfs_scrub_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
+		xchk_btree_xref_set_corrupt(sc, sc->sa.rmap_cur, 0);
 }
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 1f86e02a07ca..3f0fc83562ae 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -25,13 +25,13 @@
 
 /* Set us up with the realtime metadata locked. */
 int
-xfs_scrub_setup_rt(
+xchk_setup_rt(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
 	int				error;
 
-	error = xfs_scrub_setup_fs(sc, ip);
+	error = xchk_setup_fs(sc, ip);
 	if (error)
 		return error;
 
@@ -46,7 +46,7 @@ xfs_scrub_setup_rt(
 
 /* Scrub a free extent record from the realtime bitmap. */
 STATIC int
-xfs_scrub_rtbitmap_rec(
+xchk_rtbitmap_rec(
 	struct xfs_trans		*tp,
 	struct xfs_rtalloc_rec		*rec,
 	void				*priv)
@@ -61,24 +61,24 @@ xfs_scrub_rtbitmap_rec(
 	if (startblock + blockcount <= startblock ||
 	    !xfs_verify_rtbno(sc->mp, startblock) ||
 	    !xfs_verify_rtbno(sc->mp, startblock + blockcount - 1))
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 	return 0;
 }
 
 /* Scrub the realtime bitmap. */
 int
-xfs_scrub_rtbitmap(
+xchk_rtbitmap(
 	struct xfs_scrub_context	*sc)
 {
 	int				error;
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		return error;
 
-	error = xfs_rtalloc_query_all(sc->tp, xfs_scrub_rtbitmap_rec, sc);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	error = xfs_rtalloc_query_all(sc->tp, xchk_rtbitmap_rec, sc);
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 
 out:
@@ -87,7 +87,7 @@ out:
 
 /* Scrub the realtime summary. */
 int
-xfs_scrub_rtsummary(
+xchk_rtsummary(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_inode		*rsumip = sc->mp->m_rsumip;
@@ -107,12 +107,12 @@ xfs_scrub_rtsummary(
 	xfs_ilock(sc->ip, sc->ilock_flags);
 
 	/* Invoke the fork scrubber. */
-	error = xfs_scrub_metadata_inode_forks(sc);
+	error = xchk_metadata_inode_forks(sc);
 	if (error || (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT))
 		goto out;
 
 	/* XXX: implement this some day */
-	xfs_scrub_set_incomplete(sc);
+	xchk_set_incomplete(sc);
 out:
 	/* Switch back to the rtbitmap inode and lock flags. */
 	xfs_iunlock(sc->ip, sc->ilock_flags);
@@ -124,7 +124,7 @@ out:
 
 /* xref check that the extent is not free in the rtbitmap */
 void
-xfs_scrub_xref_is_used_rt_space(
+xchk_xref_is_used_rt_space(
 	struct xfs_scrub_context	*sc,
 	xfs_rtblock_t			fsbno,
 	xfs_extlen_t			len)
@@ -135,7 +135,7 @@ xfs_scrub_xref_is_used_rt_space(
 	bool				is_free;
 	int				error;
 
-	if (xfs_scrub_skip_xref(sc->sm))
+	if (xchk_skip_xref(sc->sm))
 		return;
 
 	startext = fsbno;
@@ -147,10 +147,10 @@ xfs_scrub_xref_is_used_rt_space(
 	xfs_ilock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 	error = xfs_rtalloc_extent_is_free(sc->mp, sc->tp, startext, extcount,
 			&is_free);
-	if (!xfs_scrub_should_check_xref(sc, &error, NULL))
+	if (!xchk_should_check_xref(sc, &error, NULL))
 		goto out_unlock;
 	if (is_free)
-		xfs_scrub_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, sc->mp->m_rbmip->i_ino);
 out_unlock:
 	xfs_iunlock(sc->mp->m_rbmip, XFS_ILOCK_SHARED | XFS_ILOCK_RTBITMAP);
 }
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 58ae76b3a421..ead97ab91a3c 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -131,6 +131,12 @@
  * optimize the structure so that the rebuild knows what to do.  The
  * second check evaluates the completeness of the repair; that is what
  * is reported to userspace.
+ *
+ * A quick note on symbol prefixes:
+ * - "xfs_" are general XFS symbols.
+ * - "xchk_" are symbols related to metadata checking.
+ * - "xrep_" are symbols related to metadata repair.
+ * - "xfs_scrub_" are symbols that tie online fsck to the rest of XFS.
  */
 
 /*
@@ -144,12 +150,12 @@
  * supported by the running kernel.
  */
 static int
-xfs_scrub_probe(
+xchk_probe(
 	struct xfs_scrub_context	*sc)
 {
 	int				error = 0;
 
-	if (xfs_scrub_should_terminate(sc, &error))
+	if (xchk_should_terminate(sc, &error))
 		return error;
 
 	return 0;
@@ -159,12 +165,12 @@ xfs_scrub_probe(
 
 /* Free all the resources and finish the transactions. */
 STATIC int
-xfs_scrub_teardown(
+xchk_teardown(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip_in,
 	int				error)
 {
-	xfs_scrub_ag_free(sc, &sc->sa);
+	xchk_ag_free(sc, &sc->sa);
 	if (sc->tp) {
 		if (error == 0 && (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR))
 			error = xfs_trans_commit(sc->tp);
@@ -191,165 +197,165 @@ xfs_scrub_teardown(
 
 /* Scrubbing dispatch. */
 
-static const struct xfs_scrub_meta_ops meta_scrub_ops[] = {
+static const struct xchk_meta_ops meta_scrub_ops[] = {
 	[XFS_SCRUB_TYPE_PROBE] = {	/* ioctl presence test */
 		.type	= ST_NONE,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_probe,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_probe,
 		.repair = xfs_repair_probe,
 	},
 	[XFS_SCRUB_TYPE_SB] = {		/* superblock */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_superblock,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_superblock,
 		.repair	= xfs_repair_superblock,
 	},
 	[XFS_SCRUB_TYPE_AGF] = {	/* agf */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agf,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agf,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_AGFL]= {	/* agfl */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agfl,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agfl,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {	/* agi */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_fs,
-		.scrub	= xfs_scrub_agi,
+		.setup	= xchk_setup_fs,
+		.scrub	= xchk_agi,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BNOBT] = {	/* bnobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_allocbt,
-		.scrub	= xfs_scrub_bnobt,
+		.setup	= xchk_setup_ag_allocbt,
+		.scrub	= xchk_bnobt,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_CNTBT] = {	/* cntbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_allocbt,
-		.scrub	= xfs_scrub_cntbt,
+		.setup	= xchk_setup_ag_allocbt,
+		.scrub	= xchk_cntbt,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INOBT] = {	/* inobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_iallocbt,
-		.scrub	= xfs_scrub_inobt,
+		.setup	= xchk_setup_ag_iallocbt,
+		.scrub	= xchk_inobt,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_FINOBT] = {	/* finobt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_iallocbt,
-		.scrub	= xfs_scrub_finobt,
+		.setup	= xchk_setup_ag_iallocbt,
+		.scrub	= xchk_finobt,
 		.has	= xfs_sb_version_hasfinobt,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RMAPBT] = {	/* rmapbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_rmapbt,
-		.scrub	= xfs_scrub_rmapbt,
+		.setup	= xchk_setup_ag_rmapbt,
+		.scrub	= xchk_rmapbt,
 		.has	= xfs_sb_version_hasrmapbt,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_REFCNTBT] = {	/* refcountbt */
 		.type	= ST_PERAG,
-		.setup	= xfs_scrub_setup_ag_refcountbt,
-		.scrub	= xfs_scrub_refcountbt,
+		.setup	= xchk_setup_ag_refcountbt,
+		.scrub	= xchk_refcountbt,
 		.has	= xfs_sb_version_hasreflink,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {	/* inode record */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode,
-		.scrub	= xfs_scrub_inode,
+		.setup	= xchk_setup_inode,
+		.scrub	= xchk_inode,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {	/* inode data fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_data,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_data,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {	/* inode attr fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_attr,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_attr,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {	/* inode CoW fork */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_inode_bmap,
-		.scrub	= xfs_scrub_bmap_cow,
+		.setup	= xchk_setup_inode_bmap,
+		.scrub	= xchk_bmap_cow,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_DIR] = {	/* directory */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_directory,
-		.scrub	= xfs_scrub_directory,
+		.setup	= xchk_setup_directory,
+		.scrub	= xchk_directory,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_XATTR] = {	/* extended attributes */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_xattr,
-		.scrub	= xfs_scrub_xattr,
+		.setup	= xchk_setup_xattr,
+		.scrub	= xchk_xattr,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_SYMLINK] = {	/* symbolic link */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_symlink,
-		.scrub	= xfs_scrub_symlink,
+		.setup	= xchk_setup_symlink,
+		.scrub	= xchk_symlink,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {	/* parent pointers */
 		.type	= ST_INODE,
-		.setup	= xfs_scrub_setup_parent,
-		.scrub	= xfs_scrub_parent,
+		.setup	= xchk_setup_parent,
+		.scrub	= xchk_parent,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_rt,
-		.scrub	= xfs_scrub_rtbitmap,
+		.setup	= xchk_setup_rt,
+		.scrub	= xchk_rtbitmap,
 		.has	= xfs_sb_version_hasrealtime,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_rt,
-		.scrub	= xfs_scrub_rtsummary,
+		.setup	= xchk_setup_rt,
+		.scrub	= xchk_rtsummary,
 		.has	= xfs_sb_version_hasrealtime,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {	/* user quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_GQUOTA] = {	/* group quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
 		.repair	= xfs_repair_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PQUOTA] = {	/* project quota */
 		.type	= ST_FS,
-		.setup	= xfs_scrub_setup_quota,
-		.scrub	= xfs_scrub_quota,
+		.setup	= xchk_setup_quota,
+		.scrub	= xchk_quota,
 		.repair	= xfs_repair_notsupported,
 	},
 };
 
 /* This isn't a stable feature, warn once per day. */
 static inline void
-xfs_scrub_experimental_warning(
+xchk_experimental_warning(
 	struct xfs_mount	*mp)
 {
 	static struct ratelimit_state scrub_warning = RATELIMIT_STATE_INIT(
-			"xfs_scrub_warning", 86400 * HZ, 1);
+			"xchk_warning", 86400 * HZ, 1);
 	ratelimit_set_flags(&scrub_warning, RATELIMIT_MSG_ON_RELEASE);
 
 	if (__ratelimit(&scrub_warning))
@@ -358,12 +364,12 @@ xfs_scrub_experimental_warning(
 }
 
 static int
-xfs_scrub_validate_inputs(
+xchk_validate_inputs(
 	struct xfs_mount		*mp,
 	struct xfs_scrub_metadata	*sm)
 {
 	int				error;
-	const struct xfs_scrub_meta_ops	*ops;
+	const struct xchk_meta_ops	*ops;
 
 	error = -EINVAL;
 	/* Check our inputs. */
@@ -441,7 +447,7 @@ out:
 }
 
 #ifdef CONFIG_XFS_ONLINE_REPAIR
-static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub_context *sc)
 {
 	/*
 	 * Userspace asked us to repair something, we repaired it, rescanned
@@ -454,7 +460,7 @@ static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
 		xfs_repair_failure(sc->mp);
 }
 #else
-static inline void xfs_scrub_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub_context *sc)
 {
 	/*
 	 * Userspace asked us to scrub something, it's broken, and we have no
@@ -480,9 +486,9 @@ xfs_scrub_metadata(
 	int				error = 0;
 
 	BUILD_BUG_ON(sizeof(meta_scrub_ops) !=
-		(sizeof(struct xfs_scrub_meta_ops) * XFS_SCRUB_TYPE_NR));
+		(sizeof(struct xchk_meta_ops) * XFS_SCRUB_TYPE_NR));
 
-	trace_xfs_scrub_start(ip, sm, error);
+	trace_xchk_start(ip, sm, error);
 
 	/* Forbidden if we are shut down or mounted norecovery. */
 	error = -ESHUTDOWN;
@@ -492,11 +498,11 @@ xfs_scrub_metadata(
 	if (mp->m_flags & XFS_MOUNT_NORECOVERY)
 		goto out;
 
-	error = xfs_scrub_validate_inputs(mp, sm);
+	error = xchk_validate_inputs(mp, sm);
 	if (error)
 		goto out;
 
-	xfs_scrub_experimental_warning(mp);
+	xchk_experimental_warning(mp);
 
 retry_op:
 	/* Set up for the operation. */
@@ -518,7 +524,7 @@ retry_op:
 		 * Tear down everything we hold, then set up again with
 		 * preparation for worst-case scenarios.
 		 */
-		error = xfs_scrub_teardown(&sc, ip, 0);
+		error = xchk_teardown(&sc, ip, 0);
 		if (error)
 			goto out;
 		try_harder = true;
@@ -553,7 +559,7 @@ retry_op:
 		if (error == -EAGAIN) {
 			if (sc.try_harder)
 				try_harder = true;
-			error = xfs_scrub_teardown(&sc, ip, 0);
+			error = xchk_teardown(&sc, ip, 0);
 			if (error) {
 				xfs_repair_failure(mp);
 				goto out;
@@ -563,11 +569,11 @@ retry_op:
 	}
 
 out_nofix:
-	xfs_scrub_postmortem(&sc);
+	xchk_postmortem(&sc);
 out_teardown:
-	error = xfs_scrub_teardown(&sc, ip, error);
+	error = xchk_teardown(&sc, ip, error);
 out:
-	trace_xfs_scrub_done(ip, sm, error);
+	trace_xchk_done(ip, sm, error);
 	if (error == -EFSCORRUPTED || error == -EFSBADCRC) {
 		sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 		error = 0;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index b295edd5fc0e..0f59a47c4bb0 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -9,14 +9,14 @@
 struct xfs_scrub_context;
 
 /* Type info and names for the scrub types. */
-enum xfs_scrub_type {
+enum xchk_type {
 	ST_NONE = 1,	/* disabled */
 	ST_PERAG,	/* per-AG metadata */
 	ST_FS,		/* per-FS metadata */
 	ST_INODE,	/* per-inode metadata */
 };
 
-struct xfs_scrub_meta_ops {
+struct xchk_meta_ops {
 	/* Acquire whatever resources are needed for the operation. */
 	int		(*setup)(struct xfs_scrub_context *,
 				 struct xfs_inode *);
@@ -31,11 +31,11 @@ struct xfs_scrub_meta_ops {
 	bool		(*has)(struct xfs_sb *);
 
 	/* type describing required/allowed inputs */
-	enum xfs_scrub_type	type;
+	enum xchk_type	type;
 };
 
 /* Buffer pointers and btree cursors for an entire AG. */
-struct xfs_scrub_ag {
+struct xchk_ag {
 	xfs_agnumber_t			agno;
 	struct xfs_perag		*pag;
 
@@ -57,7 +57,7 @@ struct xfs_scrub_context {
 	/* General scrub state. */
 	struct xfs_mount		*mp;
 	struct xfs_scrub_metadata	*sm;
-	const struct xfs_scrub_meta_ops	*ops;
+	const struct xchk_meta_ops	*ops;
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip;
 	void				*buf;
@@ -66,78 +66,78 @@ struct xfs_scrub_context {
 	bool				has_quotaofflock;
 
 	/* State tracking for single-AG operations. */
-	struct xfs_scrub_ag		sa;
+	struct xchk_ag		sa;
 };
 
 /* Metadata scrubbers */
-int xfs_scrub_tester(struct xfs_scrub_context *sc);
-int xfs_scrub_superblock(struct xfs_scrub_context *sc);
-int xfs_scrub_agf(struct xfs_scrub_context *sc);
-int xfs_scrub_agfl(struct xfs_scrub_context *sc);
-int xfs_scrub_agi(struct xfs_scrub_context *sc);
-int xfs_scrub_bnobt(struct xfs_scrub_context *sc);
-int xfs_scrub_cntbt(struct xfs_scrub_context *sc);
-int xfs_scrub_inobt(struct xfs_scrub_context *sc);
-int xfs_scrub_finobt(struct xfs_scrub_context *sc);
-int xfs_scrub_rmapbt(struct xfs_scrub_context *sc);
-int xfs_scrub_refcountbt(struct xfs_scrub_context *sc);
-int xfs_scrub_inode(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_data(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_attr(struct xfs_scrub_context *sc);
-int xfs_scrub_bmap_cow(struct xfs_scrub_context *sc);
-int xfs_scrub_directory(struct xfs_scrub_context *sc);
-int xfs_scrub_xattr(struct xfs_scrub_context *sc);
-int xfs_scrub_symlink(struct xfs_scrub_context *sc);
-int xfs_scrub_parent(struct xfs_scrub_context *sc);
+int xchk_tester(struct xfs_scrub_context *sc);
+int xchk_superblock(struct xfs_scrub_context *sc);
+int xchk_agf(struct xfs_scrub_context *sc);
+int xchk_agfl(struct xfs_scrub_context *sc);
+int xchk_agi(struct xfs_scrub_context *sc);
+int xchk_bnobt(struct xfs_scrub_context *sc);
+int xchk_cntbt(struct xfs_scrub_context *sc);
+int xchk_inobt(struct xfs_scrub_context *sc);
+int xchk_finobt(struct xfs_scrub_context *sc);
+int xchk_rmapbt(struct xfs_scrub_context *sc);
+int xchk_refcountbt(struct xfs_scrub_context *sc);
+int xchk_inode(struct xfs_scrub_context *sc);
+int xchk_bmap_data(struct xfs_scrub_context *sc);
+int xchk_bmap_attr(struct xfs_scrub_context *sc);
+int xchk_bmap_cow(struct xfs_scrub_context *sc);
+int xchk_directory(struct xfs_scrub_context *sc);
+int xchk_xattr(struct xfs_scrub_context *sc);
+int xchk_symlink(struct xfs_scrub_context *sc);
+int xchk_parent(struct xfs_scrub_context *sc);
 #ifdef CONFIG_XFS_RT
-int xfs_scrub_rtbitmap(struct xfs_scrub_context *sc);
-int xfs_scrub_rtsummary(struct xfs_scrub_context *sc);
+int xchk_rtbitmap(struct xfs_scrub_context *sc);
+int xchk_rtsummary(struct xfs_scrub_context *sc);
 #else
 static inline int
-xfs_scrub_rtbitmap(struct xfs_scrub_context *sc)
+xchk_rtbitmap(struct xfs_scrub_context *sc)
 {
 	return -ENOENT;
 }
 static inline int
-xfs_scrub_rtsummary(struct xfs_scrub_context *sc)
+xchk_rtsummary(struct xfs_scrub_context *sc)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xfs_scrub_quota(struct xfs_scrub_context *sc);
+int xchk_quota(struct xfs_scrub_context *sc);
 #else
 static inline int
-xfs_scrub_quota(struct xfs_scrub_context *sc)
+xchk_quota(struct xfs_scrub_context *sc)
 {
 	return -ENOENT;
 }
 #endif
 
 /* cross-referencing helpers */
-void xfs_scrub_xref_is_used_space(struct xfs_scrub_context *sc,
+void xchk_xref_is_used_space(struct xfs_scrub_context *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_not_inode_chunk(struct xfs_scrub_context *sc,
+void xchk_xref_is_not_inode_chunk(struct xfs_scrub_context *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_inode_chunk(struct xfs_scrub_context *sc,
+void xchk_xref_is_inode_chunk(struct xfs_scrub_context *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_owned_by(struct xfs_scrub_context *sc,
+void xchk_xref_is_owned_by(struct xfs_scrub_context *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len,
 		struct xfs_owner_info *oinfo);
-void xfs_scrub_xref_is_not_owned_by(struct xfs_scrub_context *sc,
+void xchk_xref_is_not_owned_by(struct xfs_scrub_context *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len,
 		struct xfs_owner_info *oinfo);
-void xfs_scrub_xref_has_no_owner(struct xfs_scrub_context *sc,
+void xchk_xref_has_no_owner(struct xfs_scrub_context *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xfs_scrub_xref_is_cow_staging(struct xfs_scrub_context *sc,
+void xchk_xref_is_cow_staging(struct xfs_scrub_context *sc,
 		xfs_agblock_t bno, xfs_extlen_t len);
-void xfs_scrub_xref_is_not_shared(struct xfs_scrub_context *sc,
+void xchk_xref_is_not_shared(struct xfs_scrub_context *sc,
 		xfs_agblock_t bno, xfs_extlen_t len);
 #ifdef CONFIG_XFS_RT
-void xfs_scrub_xref_is_used_rt_space(struct xfs_scrub_context *sc,
+void xchk_xref_is_used_rt_space(struct xfs_scrub_context *sc,
 		xfs_rtblock_t rtbno, xfs_extlen_t len);
 #else
-# define xfs_scrub_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
+# define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
 #endif
 
 #endif	/* __XFS_SCRUB_SCRUB_H__ */
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 570a89812116..e2a288e34337 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -25,7 +25,7 @@
 
 /* Set us up to scrub a symbolic link. */
 int
-xfs_scrub_setup_symlink(
+xchk_setup_symlink(
 	struct xfs_scrub_context	*sc,
 	struct xfs_inode		*ip)
 {
@@ -34,13 +34,13 @@ xfs_scrub_setup_symlink(
 	if (!sc->buf)
 		return -ENOMEM;
 
-	return xfs_scrub_setup_inode_contents(sc, ip, 0);
+	return xchk_setup_inode_contents(sc, ip, 0);
 }
 
 /* Symbolic links. */
 
 int
-xfs_scrub_symlink(
+xchk_symlink(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_inode		*ip = sc->ip;
@@ -55,7 +55,7 @@ xfs_scrub_symlink(
 
 	/* Plausible size? */
 	if (len > XFS_SYMLINK_MAXLEN || len <= 0) {
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
@@ -63,16 +63,16 @@ xfs_scrub_symlink(
 	if (ifp->if_flags & XFS_IFINLINE) {
 		if (len > XFS_IFORK_DSIZE(ip) ||
 		    len > strnlen(ifp->if_u1.if_data, XFS_IFORK_DSIZE(ip)))
-			xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+			xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 		goto out;
 	}
 
 	/* Remote symlink; must read the contents. */
 	error = xfs_readlink_bmap_ilocked(sc->ip, sc->buf);
-	if (!xfs_scrub_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
+	if (!xchk_fblock_process_error(sc, XFS_DATA_FORK, 0, &error))
 		goto out;
 	if (strnlen(sc->buf, XFS_SYMLINK_MAXLEN) < len)
-		xfs_scrub_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
+		xchk_fblock_set_corrupt(sc, XFS_DATA_FORK, 0);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 7c76d8b5cb05..1ef1202a1e45 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -22,7 +22,7 @@
 
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
-xfs_scrub_btree_cur_fsbno(
+xchk_btree_cur_fsbno(
 	struct xfs_btree_cur		*cur,
 	int				level)
 {
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index cec3e5ece5a1..11967d3942ac 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -12,7 +12,7 @@
 #include <linux/tracepoint.h>
 #include "xfs_bit.h"
 
-DECLARE_EVENT_CLASS(xfs_scrub_class,
+DECLARE_EVENT_CLASS(xchk_class,
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm,
 		 int error),
 	TP_ARGS(ip, sm, error),
@@ -47,18 +47,18 @@ DECLARE_EVENT_CLASS(xfs_scrub_class,
 		  __entry->error)
 )
 #define DEFINE_SCRUB_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_class, name, \
+DEFINE_EVENT(xchk_class, name, \
 	TP_PROTO(struct xfs_inode *ip, struct xfs_scrub_metadata *sm, \
 		 int error), \
 	TP_ARGS(ip, sm, error))
 
-DEFINE_SCRUB_EVENT(xfs_scrub_start);
-DEFINE_SCRUB_EVENT(xfs_scrub_done);
-DEFINE_SCRUB_EVENT(xfs_scrub_deadlock_retry);
+DEFINE_SCRUB_EVENT(xchk_start);
+DEFINE_SCRUB_EVENT(xchk_done);
+DEFINE_SCRUB_EVENT(xchk_deadlock_retry);
 DEFINE_SCRUB_EVENT(xfs_repair_attempt);
 DEFINE_SCRUB_EVENT(xfs_repair_done);
 
-TRACE_EVENT(xfs_scrub_op_error,
+TRACE_EVENT(xchk_op_error,
 	TP_PROTO(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
 		 xfs_agblock_t bno, int error, void *ret_ip),
 	TP_ARGS(sc, agno, bno, error, ret_ip),
@@ -87,7 +87,7 @@ TRACE_EVENT(xfs_scrub_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_file_op_error,
+TRACE_EVENT(xchk_file_op_error,
 	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
 		 xfs_fileoff_t offset, int error, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, error, ret_ip),
@@ -119,7 +119,7 @@ TRACE_EVENT(xfs_scrub_file_op_error,
 		  __entry->ret_ip)
 );
 
-DECLARE_EVENT_CLASS(xfs_scrub_block_error_class,
+DECLARE_EVENT_CLASS(xchk_block_error_class,
 	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, void *ret_ip),
 	TP_ARGS(sc, daddr, ret_ip),
 	TP_STRUCT__entry(
@@ -153,15 +153,15 @@ DECLARE_EVENT_CLASS(xfs_scrub_block_error_class,
 )
 
 #define DEFINE_SCRUB_BLOCK_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_block_error_class, name, \
+DEFINE_EVENT(xchk_block_error_class, name, \
 	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, \
 		 void *ret_ip), \
 	TP_ARGS(sc, daddr, ret_ip))
 
-DEFINE_SCRUB_BLOCK_ERROR_EVENT(xfs_scrub_block_error);
-DEFINE_SCRUB_BLOCK_ERROR_EVENT(xfs_scrub_block_preen);
+DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_error);
+DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_preen);
 
-DECLARE_EVENT_CLASS(xfs_scrub_ino_error_class,
+DECLARE_EVENT_CLASS(xchk_ino_error_class,
 	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, void *ret_ip),
 	TP_ARGS(sc, ino, ret_ip),
 	TP_STRUCT__entry(
@@ -184,16 +184,16 @@ DECLARE_EVENT_CLASS(xfs_scrub_ino_error_class,
 )
 
 #define DEFINE_SCRUB_INO_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_ino_error_class, name, \
+DEFINE_EVENT(xchk_ino_error_class, name, \
 	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, \
 		 void *ret_ip), \
 	TP_ARGS(sc, ino, ret_ip))
 
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_error);
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_preen);
-DEFINE_SCRUB_INO_ERROR_EVENT(xfs_scrub_ino_warning);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_error);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_preen);
+DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_warning);
 
-DECLARE_EVENT_CLASS(xfs_scrub_fblock_error_class,
+DECLARE_EVENT_CLASS(xchk_fblock_error_class,
 	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
 		 xfs_fileoff_t offset, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, ret_ip),
@@ -223,15 +223,15 @@ DECLARE_EVENT_CLASS(xfs_scrub_fblock_error_class,
 );
 
 #define DEFINE_SCRUB_FBLOCK_ERROR_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_fblock_error_class, name, \
+DEFINE_EVENT(xchk_fblock_error_class, name, \
 	TP_PROTO(struct xfs_scrub_context *sc, int whichfork, \
 		 xfs_fileoff_t offset, void *ret_ip), \
 	TP_ARGS(sc, whichfork, offset, ret_ip))
 
-DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xfs_scrub_fblock_error);
-DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xfs_scrub_fblock_warning);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
+DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
 
-TRACE_EVENT(xfs_scrub_incomplete,
+TRACE_EVENT(xchk_incomplete,
 	TP_PROTO(struct xfs_scrub_context *sc, void *ret_ip),
 	TP_ARGS(sc, ret_ip),
 	TP_STRUCT__entry(
@@ -250,7 +250,7 @@ TRACE_EVENT(xfs_scrub_incomplete,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_btree_op_error,
+TRACE_EVENT(xchk_btree_op_error,
 	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
@@ -266,7 +266,7 @@ TRACE_EVENT(xfs_scrub_btree_op_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
@@ -290,7 +290,7 @@ TRACE_EVENT(xfs_scrub_btree_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
+TRACE_EVENT(xchk_ifork_btree_op_error,
 	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
@@ -308,7 +308,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->ino = sc->ip->i_ino;
 		__entry->whichfork = cur->bc_private.b.whichfork;
@@ -335,7 +335,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_btree_error,
+TRACE_EVENT(xchk_btree_error,
 	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
@@ -350,7 +350,7 @@ TRACE_EVENT(xfs_scrub_btree_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
 		__entry->btnum = cur->bc_btnum;
@@ -371,7 +371,7 @@ TRACE_EVENT(xfs_scrub_btree_error,
 		  __entry->ret_ip)
 );
 
-TRACE_EVENT(xfs_scrub_ifork_btree_error,
+TRACE_EVENT(xchk_ifork_btree_error,
 	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
@@ -388,7 +388,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_error,
 		__field(void *, ret_ip)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->ino = sc->ip->i_ino;
 		__entry->whichfork = cur->bc_private.b.whichfork;
@@ -413,7 +413,7 @@ TRACE_EVENT(xfs_scrub_ifork_btree_error,
 		  __entry->ret_ip)
 );
 
-DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
+DECLARE_EVENT_CLASS(xchk_sbtree_class,
 	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
 		 int level),
 	TP_ARGS(sc, cur, level),
@@ -428,7 +428,7 @@ DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
 		__field(int, ptr)
 	),
 	TP_fast_assign(
-		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		xfs_fsblock_t fsbno = xchk_btree_cur_fsbno(cur, level);
 
 		__entry->dev = sc->mp->m_super->s_dev;
 		__entry->type = sc->sm->sm_type;
@@ -450,15 +450,15 @@ DECLARE_EVENT_CLASS(xfs_scrub_sbtree_class,
 		  __entry->ptr)
 )
 #define DEFINE_SCRUB_SBTREE_EVENT(name) \
-DEFINE_EVENT(xfs_scrub_sbtree_class, name, \
+DEFINE_EVENT(xchk_sbtree_class, name, \
 	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur, \
 		 int level), \
 	TP_ARGS(sc, cur, level))
 
-DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_rec);
-DEFINE_SCRUB_SBTREE_EVENT(xfs_scrub_btree_key);
+DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_rec);
+DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_key);
 
-TRACE_EVENT(xfs_scrub_xref_error,
+TRACE_EVENT(xchk_xref_error,
 	TP_PROTO(struct xfs_scrub_context *sc, int error, void *ret_ip),
 	TP_ARGS(sc, error, ret_ip),
 	TP_STRUCT__entry(
-- 
cgit v1.2.3


From b5e2196e9c7217387bab2ab4231ad9f4585f55c5 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:29:11 -0700
Subject: xfs: shorten xfs_repair_ prefix to xrep_

Shorten all the metadata repair xfs_repair_* symbols to xrep_.
Whitespace damage will be fixed by a subsequent patch.  There are no
functional changes.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/agheader_repair.c |   2 +-
 fs/xfs/scrub/common.c          |   2 +-
 fs/xfs/scrub/repair.c          | 164 ++++++++++++++++++++---------------------
 fs/xfs/scrub/repair.h          |  74 +++++++++----------
 fs/xfs/scrub/scrub.c           |  54 +++++++-------
 fs/xfs/scrub/trace.h           |  40 +++++-----
 6 files changed, 168 insertions(+), 168 deletions(-)

diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 117eedac53df..631940f3ca4d 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -28,7 +28,7 @@
 
 /* Repair the superblock. */
 int
-xfs_repair_superblock(
+xrep_superblock(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index 5c3d4e7c6166..d40bba9e7596 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -604,7 +604,7 @@ xchk_setup_fs(
 {
 	uint				resblks;
 
-	resblks = xfs_repair_calc_ag_resblks(sc);
+	resblks = xrep_calc_ag_resblks(sc);
 	return xchk_trans_alloc(sc, resblks);
 }
 
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 5eccd89c64a8..7e6a56a5f59d 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -41,21 +41,21 @@
  * and will set *fixed to true if it thinks it repaired anything.
  */
 int
-xfs_repair_attempt(
+xrep_attempt(
 	struct xfs_inode		*ip,
 	struct xfs_scrub_context	*sc,
 	bool				*fixed)
 {
 	int				error = 0;
 
-	trace_xfs_repair_attempt(ip, sc->sm, error);
+	trace_xrep_attempt(ip, sc->sm, error);
 
 	xchk_ag_btcur_free(&sc->sa);
 
 	/* Repair whatever's broken. */
 	ASSERT(sc->ops->repair);
 	error = sc->ops->repair(sc);
-	trace_xfs_repair_done(ip, sc->sm, error);
+	trace_xrep_done(ip, sc->sm, error);
 	switch (error) {
 	case 0:
 		/*
@@ -93,7 +93,7 @@ xfs_repair_attempt(
  * structure to track rate limiting information.
  */
 void
-xfs_repair_failure(
+xrep_failure(
 	struct xfs_mount		*mp)
 {
 	xfs_alert_ratelimited(mp,
@@ -105,7 +105,7 @@ xfs_repair_failure(
  * given mountpoint.
  */
 int
-xfs_repair_probe(
+xrep_probe(
 	struct xfs_scrub_context	*sc)
 {
 	int				error = 0;
@@ -121,7 +121,7 @@ xfs_repair_probe(
  * the btree cursors.
  */
 int
-xfs_repair_roll_ag_trans(
+xrep_roll_ag_trans(
 	struct xfs_scrub_context	*sc)
 {
 	int				error;
@@ -162,7 +162,7 @@ out_release:
  * in AG reservations) to construct a whole btree.
  */
 bool
-xfs_repair_ag_has_space(
+xrep_ag_has_space(
 	struct xfs_perag		*pag,
 	xfs_extlen_t			nr_blocks,
 	enum xfs_ag_resv_type		type)
@@ -178,7 +178,7 @@ xfs_repair_ag_has_space(
  * any type of per-AG btree.
  */
 xfs_extlen_t
-xfs_repair_calc_ag_resblks(
+xrep_calc_ag_resblks(
 	struct xfs_scrub_context	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
@@ -231,7 +231,7 @@ xfs_repair_calc_ag_resblks(
 	}
 	xfs_perag_put(pag);
 
-	trace_xfs_repair_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
+	trace_xrep_calc_ag_resblks(mp, sm->sm_agno, icount, aglen,
 			freelen, usedlen);
 
 	/*
@@ -270,7 +270,7 @@ xfs_repair_calc_ag_resblks(
 		rmapbt_sz = 0;
 	}
 
-	trace_xfs_repair_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
+	trace_xrep_calc_ag_resblks_btsize(mp, sm->sm_agno, bnobt_sz,
 			inobt_sz, rmapbt_sz, refcbt_sz);
 
 	return max(max(bnobt_sz, inobt_sz), max(rmapbt_sz, refcbt_sz));
@@ -278,7 +278,7 @@ xfs_repair_calc_ag_resblks(
 
 /* Allocate a block in an AG. */
 int
-xfs_repair_alloc_ag_block(
+xrep_alloc_ag_block(
 	struct xfs_scrub_context	*sc,
 	struct xfs_owner_info		*oinfo,
 	xfs_fsblock_t			*fsbno,
@@ -329,7 +329,7 @@ xfs_repair_alloc_ag_block(
 
 /* Initialize a new AG btree root block with zero entries. */
 int
-xfs_repair_init_btblock(
+xrep_init_btblock(
 	struct xfs_scrub_context	*sc,
 	xfs_fsblock_t			fsb,
 	struct xfs_buf			**bpp,
@@ -340,7 +340,7 @@ xfs_repair_init_btblock(
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_buf			*bp;
 
-	trace_xfs_repair_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
+	trace_xrep_init_btblock(mp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), btnum);
 
 	ASSERT(XFS_FSB_TO_AGNO(mp, fsb) == sc->sa.agno);
@@ -384,19 +384,19 @@ xfs_repair_init_btblock(
 
 /* Collect a dead btree extent for later disposal. */
 int
-xfs_repair_collect_btree_extent(
+xrep_collect_btree_extent(
 	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
+	struct xrep_extent_list		*exlist,
 	xfs_fsblock_t			fsbno,
 	xfs_extlen_t			len)
 {
-	struct xfs_repair_extent	*rex;
+	struct xrep_extent		*rex;
 
-	trace_xfs_repair_collect_btree_extent(sc->mp,
+	trace_xrep_collect_btree_extent(sc->mp,
 			XFS_FSB_TO_AGNO(sc->mp, fsbno),
 			XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
 
-	rex = kmem_alloc(sizeof(struct xfs_repair_extent), KM_MAYFAIL);
+	rex = kmem_alloc(sizeof(struct xrep_extent), KM_MAYFAIL);
 	if (!rex)
 		return -ENOMEM;
 
@@ -414,14 +414,14 @@ xfs_repair_collect_btree_extent(
  * Therefore, free all the memory associated with the list so we can die.
  */
 void
-xfs_repair_cancel_btree_extents(
+xrep_cancel_btree_extents(
 	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist)
+	struct xrep_extent_list		*exlist)
 {
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
+	struct xrep_extent		*rex;
+	struct xrep_extent		*n;
 
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+	for_each_xrep_extent_safe(rex, n, exlist) {
 		list_del(&rex->list);
 		kmem_free(rex);
 	}
@@ -429,16 +429,16 @@ xfs_repair_cancel_btree_extents(
 
 /* Compare two btree extents. */
 static int
-xfs_repair_btree_extent_cmp(
+xrep_btree_extent_cmp(
 	void				*priv,
 	struct list_head		*a,
 	struct list_head		*b)
 {
-	struct xfs_repair_extent	*ap;
-	struct xfs_repair_extent	*bp;
+	struct xrep_extent		*ap;
+	struct xrep_extent		*bp;
 
-	ap = container_of(a, struct xfs_repair_extent, list);
-	bp = container_of(b, struct xfs_repair_extent, list);
+	ap = container_of(a, struct xrep_extent, list);
+	bp = container_of(b, struct xrep_extent, list);
 
 	if (ap->fsbno > bp->fsbno)
 		return 1;
@@ -462,15 +462,15 @@ xfs_repair_btree_extent_cmp(
 #define LEFT_ALIGNED	(1 << 0)
 #define RIGHT_ALIGNED	(1 << 1)
 int
-xfs_repair_subtract_extents(
+xrep_subtract_extents(
 	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
-	struct xfs_repair_extent_list	*sublist)
+	struct xrep_extent_list		*exlist,
+	struct xrep_extent_list		*sublist)
 {
 	struct list_head		*lp;
-	struct xfs_repair_extent	*ex;
-	struct xfs_repair_extent	*newex;
-	struct xfs_repair_extent	*subex;
+	struct xrep_extent		*ex;
+	struct xrep_extent		*newex;
+	struct xrep_extent		*subex;
 	xfs_fsblock_t			sub_fsb;
 	xfs_extlen_t			sub_len;
 	int				state;
@@ -480,8 +480,8 @@ xfs_repair_subtract_extents(
 		return 0;
 	ASSERT(!list_empty(&sublist->list));
 
-	list_sort(NULL, &exlist->list, xfs_repair_btree_extent_cmp);
-	list_sort(NULL, &sublist->list, xfs_repair_btree_extent_cmp);
+	list_sort(NULL, &exlist->list, xrep_btree_extent_cmp);
+	list_sort(NULL, &sublist->list, xrep_btree_extent_cmp);
 
 	/*
 	 * Now that we've sorted both lists, we iterate exlist once, rolling
@@ -491,11 +491,11 @@ xfs_repair_subtract_extents(
 	 * list traversal is similar to merge sort, but we're deleting
 	 * instead.  In this manner we avoid O(n^2) operations.
 	 */
-	subex = list_first_entry(&sublist->list, struct xfs_repair_extent,
+	subex = list_first_entry(&sublist->list, struct xrep_extent,
 			list);
 	lp = exlist->list.next;
 	while (lp != &exlist->list) {
-		ex = list_entry(lp, struct xfs_repair_extent, list);
+		ex = list_entry(lp, struct xrep_extent, list);
 
 		/*
 		 * Advance subex and/or ex until we find a pair that
@@ -548,7 +548,7 @@ xfs_repair_subtract_extents(
 			 * Deleting from the middle: add the new right extent
 			 * and then shrink the left extent.
 			 */
-			newex = kmem_alloc(sizeof(struct xfs_repair_extent),
+			newex = kmem_alloc(sizeof(struct xrep_extent),
 					KM_MAYFAIL);
 			if (!newex) {
 				error = -ENOMEM;
@@ -619,12 +619,12 @@ out:
  * is not intended for use with file data repairs; we have bunmapi for that.
  */
 int
-xfs_repair_invalidate_blocks(
+xrep_invalidate_blocks(
 	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist)
+	struct xrep_extent_list		*exlist)
 {
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
+	struct xrep_extent		*rex;
+	struct xrep_extent		*n;
 	struct xfs_buf			*bp;
 	xfs_fsblock_t			fsbno;
 	xfs_agblock_t			i;
@@ -637,7 +637,7 @@ xfs_repair_invalidate_blocks(
 	 * because we never own those; and if we can't TRYLOCK the buffer we
 	 * assume it's owned by someone else.
 	 */
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+	for_each_xrep_extent_safe(rex, n, exlist) {
 		for (fsbno = rex->fsbno, i = rex->len; i > 0; fsbno++, i--) {
 			/* Skip AG headers and post-EOFS blocks */
 			if (!xfs_verify_fsbno(sc->mp, fsbno))
@@ -657,7 +657,7 @@ xfs_repair_invalidate_blocks(
 
 /* Ensure the freelist is the correct size. */
 int
-xfs_repair_fix_freelist(
+xrep_fix_freelist(
 	struct xfs_scrub_context	*sc,
 	bool				can_shrink)
 {
@@ -677,7 +677,7 @@ xfs_repair_fix_freelist(
  * Put a block back on the AGFL.
  */
 STATIC int
-xfs_repair_put_freelist(
+xrep_put_freelist(
 	struct xfs_scrub_context	*sc,
 	xfs_agblock_t			agbno)
 {
@@ -685,7 +685,7 @@ xfs_repair_put_freelist(
 	int				error;
 
 	/* Make sure there's space on the freelist. */
-	error = xfs_repair_fix_freelist(sc, true);
+	error = xrep_fix_freelist(sc, true);
 	if (error)
 		return error;
 
@@ -713,7 +713,7 @@ xfs_repair_put_freelist(
 
 /* Dispose of a single metadata block. */
 STATIC int
-xfs_repair_dispose_btree_block(
+xrep_dispose_btree_block(
 	struct xfs_scrub_context	*sc,
 	xfs_fsblock_t			fsbno,
 	struct xfs_owner_info		*oinfo,
@@ -767,7 +767,7 @@ xfs_repair_dispose_btree_block(
 	if (has_other_rmap)
 		error = xfs_rmap_free(sc->tp, agf_bp, agno, agbno, 1, oinfo);
 	else if (resv == XFS_AG_RESV_AGFL)
-		error = xfs_repair_put_freelist(sc, agbno);
+		error = xrep_put_freelist(sc, agbno);
 	else
 		error = xfs_free_extent(sc->tp, fsbno, 1, oinfo, resv);
 	if (agf_bp != sc->sa.agf_bp)
@@ -777,7 +777,7 @@ xfs_repair_dispose_btree_block(
 
 	if (sc->ip)
 		return xfs_trans_roll_inode(&sc->tp, sc->ip);
-	return xfs_repair_roll_ag_trans(sc);
+	return xrep_roll_ag_trans(sc);
 
 out_free:
 	if (agf_bp != sc->sa.agf_bp)
@@ -787,29 +787,29 @@ out_free:
 
 /* Dispose of btree blocks from an old per-AG btree. */
 int
-xfs_repair_reap_btree_extents(
+xrep_reap_btree_extents(
 	struct xfs_scrub_context	*sc,
-	struct xfs_repair_extent_list	*exlist,
+	struct xrep_extent_list		*exlist,
 	struct xfs_owner_info		*oinfo,
 	enum xfs_ag_resv_type		type)
 {
-	struct xfs_repair_extent	*rex;
-	struct xfs_repair_extent	*n;
+	struct xrep_extent		*rex;
+	struct xrep_extent		*n;
 	int				error = 0;
 
 	ASSERT(xfs_sb_version_hasrmapbt(&sc->mp->m_sb));
 
 	/* Dispose of every block from the old btree. */
-	for_each_xfs_repair_extent_safe(rex, n, exlist) {
+	for_each_xrep_extent_safe(rex, n, exlist) {
 		ASSERT(sc->ip != NULL ||
 		       XFS_FSB_TO_AGNO(sc->mp, rex->fsbno) == sc->sa.agno);
 
-		trace_xfs_repair_dispose_btree_extent(sc->mp,
+		trace_xrep_dispose_btree_extent(sc->mp,
 				XFS_FSB_TO_AGNO(sc->mp, rex->fsbno),
 				XFS_FSB_TO_AGBNO(sc->mp, rex->fsbno), rex->len);
 
 		for (; rex->len > 0; rex->len--, rex->fsbno++) {
-			error = xfs_repair_dispose_btree_block(sc, rex->fsbno,
+			error = xrep_dispose_btree_block(sc, rex->fsbno,
 					oinfo, type);
 			if (error)
 				goto out;
@@ -819,7 +819,7 @@ xfs_repair_reap_btree_extents(
 	}
 
 out:
-	xfs_repair_cancel_btree_extents(sc, exlist);
+	xrep_cancel_btree_extents(sc, exlist);
 	return error;
 }
 
@@ -831,12 +831,12 @@ out:
  * btree roots.  This is not guaranteed to work if the AG is heavily damaged
  * or the rmap data are corrupt.
  *
- * Callers of xfs_repair_find_ag_btree_roots must lock the AGF and AGFL
+ * Callers of xrep_find_ag_btree_roots must lock the AGF and AGFL
  * buffers if the AGF is being rebuilt; or the AGF and AGI buffers if the
  * AGI is being rebuilt.  It must maintain these locks until it's safe for
  * other threads to change the btrees' shapes.  The caller provides
  * information about the btrees to look for by passing in an array of
- * xfs_repair_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
+ * xrep_find_ag_btree with the (rmap owner, buf_ops, magic) fields set.
  * The (root, height) fields will be set on return if anything is found.  The
  * last element of the array should have a NULL buf_ops to mark the end of the
  * array.
@@ -850,16 +850,16 @@ out:
  * should be the roots.
  */
 
-struct xfs_repair_findroot {
+struct xrep_findroot {
 	struct xfs_scrub_context	*sc;
 	struct xfs_buf			*agfl_bp;
 	struct xfs_agf			*agf;
-	struct xfs_repair_find_ag_btree	*btree_info;
+	struct xrep_find_ag_btree	*btree_info;
 };
 
 /* See if our block is in the AGFL. */
 STATIC int
-xfs_repair_findroot_agfl_walk(
+xrep_findroot_agfl_walk(
 	struct xfs_mount		*mp,
 	xfs_agblock_t			bno,
 	void				*priv)
@@ -871,9 +871,9 @@ xfs_repair_findroot_agfl_walk(
 
 /* Does this block match the btree information passed in? */
 STATIC int
-xfs_repair_findroot_block(
-	struct xfs_repair_findroot	*ri,
-	struct xfs_repair_find_ag_btree	*fab,
+xrep_findroot_block(
+	struct xrep_findroot		*ri,
+	struct xrep_find_ag_btree	*fab,
 	uint64_t			owner,
 	xfs_agblock_t			agbno,
 	bool				*found_it)
@@ -894,7 +894,7 @@ xfs_repair_findroot_block(
 	 */
 	if (owner == XFS_RMAP_OWN_AG) {
 		error = xfs_agfl_walk(mp, ri->agf, ri->agfl_bp,
-				xfs_repair_findroot_agfl_walk, &agbno);
+				xrep_findroot_agfl_walk, &agbno);
 		if (error == XFS_BTREE_QUERY_RANGE_ABORT)
 			return 0;
 		if (error)
@@ -932,7 +932,7 @@ xfs_repair_findroot_block(
 	fab->height = xfs_btree_get_level(btblock) + 1;
 	*found_it = true;
 
-	trace_xfs_repair_findroot_block(mp, ri->sc->sa.agno, agbno,
+	trace_xrep_findroot_block(mp, ri->sc->sa.agno, agbno,
 			be32_to_cpu(btblock->bb_magic), fab->height - 1);
 out:
 	xfs_trans_brelse(ri->sc->tp, bp);
@@ -944,13 +944,13 @@ out:
  * looking for?
  */
 STATIC int
-xfs_repair_findroot_rmap(
+xrep_findroot_rmap(
 	struct xfs_btree_cur		*cur,
 	struct xfs_rmap_irec		*rec,
 	void				*priv)
 {
-	struct xfs_repair_findroot	*ri = priv;
-	struct xfs_repair_find_ag_btree	*fab;
+	struct xrep_findroot		*ri = priv;
+	struct xrep_find_ag_btree	*fab;
 	xfs_agblock_t			b;
 	bool				found_it;
 	int				error = 0;
@@ -965,7 +965,7 @@ xfs_repair_findroot_rmap(
 		for (fab = ri->btree_info; fab->buf_ops; fab++) {
 			if (rec->rm_owner != fab->rmap_owner)
 				continue;
-			error = xfs_repair_findroot_block(ri, fab,
+			error = xrep_findroot_block(ri, fab,
 					rec->rm_owner, rec->rm_startblock + b,
 					&found_it);
 			if (error)
@@ -980,15 +980,15 @@ xfs_repair_findroot_rmap(
 
 /* Find the roots of the per-AG btrees described in btree_info. */
 int
-xfs_repair_find_ag_btree_roots(
+xrep_find_ag_btree_roots(
 	struct xfs_scrub_context	*sc,
 	struct xfs_buf			*agf_bp,
-	struct xfs_repair_find_ag_btree	*btree_info,
+	struct xrep_find_ag_btree	*btree_info,
 	struct xfs_buf			*agfl_bp)
 {
 	struct xfs_mount		*mp = sc->mp;
-	struct xfs_repair_findroot	ri;
-	struct xfs_repair_find_ag_btree	*fab;
+	struct xrep_findroot		ri;
+	struct xrep_find_ag_btree	*fab;
 	struct xfs_btree_cur		*cur;
 	int				error;
 
@@ -1007,7 +1007,7 @@ xfs_repair_find_ag_btree_roots(
 	}
 
 	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
-	error = xfs_rmap_query_all(cur, xfs_repair_findroot_rmap, &ri);
+	error = xfs_rmap_query_all(cur, xrep_findroot_rmap, &ri);
 	xfs_btree_del_cursor(cur, error);
 
 	return error;
@@ -1015,7 +1015,7 @@ xfs_repair_find_ag_btree_roots(
 
 /* Force a quotacheck the next time we mount. */
 void
-xfs_repair_force_quotacheck(
+xrep_force_quotacheck(
 	struct xfs_scrub_context	*sc,
 	uint				dqtype)
 {
@@ -1043,7 +1043,7 @@ xfs_repair_force_quotacheck(
  * repair corruptions in the quota metadata.
  */
 int
-xfs_repair_ino_dqattach(
+xrep_ino_dqattach(
 	struct xfs_scrub_context	*sc)
 {
 	int				error;
@@ -1057,11 +1057,11 @@ xfs_repair_ino_dqattach(
 "inode %llu repair encountered quota error %d, quotacheck forced.",
 				(unsigned long long)sc->ip->i_ino, error);
 		if (XFS_IS_UQUOTA_ON(sc->mp) && !sc->ip->i_udquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_USER);
+			xrep_force_quotacheck(sc, XFS_DQ_USER);
 		if (XFS_IS_GQUOTA_ON(sc->mp) && !sc->ip->i_gdquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_GROUP);
+			xrep_force_quotacheck(sc, XFS_DQ_GROUP);
 		if (XFS_IS_PQUOTA_ON(sc->mp) && !sc->ip->i_pdquot)
-			xfs_repair_force_quotacheck(sc, XFS_DQ_PROJ);
+			xrep_force_quotacheck(sc, XFS_DQ_PROJ);
 		/* fall through */
 	case -ESRCH:
 		error = 0;
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index ef47826b6725..60d81294797b 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -6,7 +6,7 @@
 #ifndef __XFS_SCRUB_REPAIR_H__
 #define __XFS_SCRUB_REPAIR_H__
 
-static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
+static inline int xrep_notsupported(struct xfs_scrub_context *sc)
 {
 	return -EOPNOTSUPP;
 }
@@ -15,55 +15,55 @@ static inline int xfs_repair_notsupported(struct xfs_scrub_context *sc)
 
 /* Repair helpers */
 
-int xfs_repair_attempt(struct xfs_inode *ip, struct xfs_scrub_context *sc,
+int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub_context *sc,
 		bool *fixed);
-void xfs_repair_failure(struct xfs_mount *mp);
-int xfs_repair_roll_ag_trans(struct xfs_scrub_context *sc);
-bool xfs_repair_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
+void xrep_failure(struct xfs_mount *mp);
+int xrep_roll_ag_trans(struct xfs_scrub_context *sc);
+bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
 		enum xfs_ag_resv_type type);
-xfs_extlen_t xfs_repair_calc_ag_resblks(struct xfs_scrub_context *sc);
-int xfs_repair_alloc_ag_block(struct xfs_scrub_context *sc,
+xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub_context *sc);
+int xrep_alloc_ag_block(struct xfs_scrub_context *sc,
 		struct xfs_owner_info *oinfo, xfs_fsblock_t *fsbno,
 		enum xfs_ag_resv_type resv);
-int xfs_repair_init_btblock(struct xfs_scrub_context *sc, xfs_fsblock_t fsb,
+int xrep_init_btblock(struct xfs_scrub_context *sc, xfs_fsblock_t fsb,
 		struct xfs_buf **bpp, xfs_btnum_t btnum,
 		const struct xfs_buf_ops *ops);
 
-struct xfs_repair_extent {
+struct xrep_extent {
 	struct list_head		list;
 	xfs_fsblock_t			fsbno;
 	xfs_extlen_t			len;
 };
 
-struct xfs_repair_extent_list {
+struct xrep_extent_list {
 	struct list_head		list;
 };
 
 static inline void
-xfs_repair_init_extent_list(
-	struct xfs_repair_extent_list	*exlist)
+xrep_init_extent_list(
+	struct xrep_extent_list		*exlist)
 {
 	INIT_LIST_HEAD(&exlist->list);
 }
 
-#define for_each_xfs_repair_extent_safe(rbe, n, exlist) \
+#define for_each_xrep_extent_safe(rbe, n, exlist) \
 	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
-int xfs_repair_collect_btree_extent(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist, xfs_fsblock_t fsbno,
+int xrep_collect_btree_extent(struct xfs_scrub_context *sc,
+		struct xrep_extent_list *btlist, xfs_fsblock_t fsbno,
 		xfs_extlen_t len);
-void xfs_repair_cancel_btree_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist);
-int xfs_repair_subtract_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *exlist,
-		struct xfs_repair_extent_list *sublist);
-int xfs_repair_fix_freelist(struct xfs_scrub_context *sc, bool can_shrink);
-int xfs_repair_invalidate_blocks(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *btlist);
-int xfs_repair_reap_btree_extents(struct xfs_scrub_context *sc,
-		struct xfs_repair_extent_list *exlist,
+void xrep_cancel_btree_extents(struct xfs_scrub_context *sc,
+		struct xrep_extent_list *btlist);
+int xrep_subtract_extents(struct xfs_scrub_context *sc,
+		struct xrep_extent_list *exlist,
+		struct xrep_extent_list *sublist);
+int xrep_fix_freelist(struct xfs_scrub_context *sc, bool can_shrink);
+int xrep_invalidate_blocks(struct xfs_scrub_context *sc,
+		struct xrep_extent_list *btlist);
+int xrep_reap_btree_extents(struct xfs_scrub_context *sc,
+		struct xrep_extent_list *exlist,
 		struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
 
-struct xfs_repair_find_ag_btree {
+struct xrep_find_ag_btree {
 	/* in: rmap owner of the btree we're looking for */
 	uint64_t			rmap_owner;
 
@@ -78,21 +78,21 @@ struct xfs_repair_find_ag_btree {
 	unsigned int			height;
 };
 
-int xfs_repair_find_ag_btree_roots(struct xfs_scrub_context *sc,
+int xrep_find_ag_btree_roots(struct xfs_scrub_context *sc,
 		struct xfs_buf *agf_bp,
-		struct xfs_repair_find_ag_btree *btree_info,
+		struct xrep_find_ag_btree *btree_info,
 		struct xfs_buf *agfl_bp);
-void xfs_repair_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
-int xfs_repair_ino_dqattach(struct xfs_scrub_context *sc);
+void xrep_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
+int xrep_ino_dqattach(struct xfs_scrub_context *sc);
 
 /* Metadata repairers */
 
-int xfs_repair_probe(struct xfs_scrub_context *sc);
-int xfs_repair_superblock(struct xfs_scrub_context *sc);
+int xrep_probe(struct xfs_scrub_context *sc);
+int xrep_superblock(struct xfs_scrub_context *sc);
 
 #else
 
-static inline int xfs_repair_attempt(
+static inline int xrep_attempt(
 	struct xfs_inode		*ip,
 	struct xfs_scrub_context	*sc,
 	bool				*fixed)
@@ -100,18 +100,18 @@ static inline int xfs_repair_attempt(
 	return -EOPNOTSUPP;
 }
 
-static inline void xfs_repair_failure(struct xfs_mount *mp) {}
+static inline void xrep_failure(struct xfs_mount *mp) {}
 
 static inline xfs_extlen_t
-xfs_repair_calc_ag_resblks(
+xrep_calc_ag_resblks(
 	struct xfs_scrub_context	*sc)
 {
 	ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
 	return 0;
 }
 
-#define xfs_repair_probe		xfs_repair_notsupported
-#define xfs_repair_superblock		xfs_repair_notsupported
+#define xrep_probe			xrep_notsupported
+#define xrep_superblock			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index ead97ab91a3c..a6efede6e430 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -202,150 +202,150 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_NONE,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_probe,
-		.repair = xfs_repair_probe,
+		.repair = xrep_probe,
 	},
 	[XFS_SCRUB_TYPE_SB] = {		/* superblock */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_superblock,
-		.repair	= xfs_repair_superblock,
+		.repair	= xrep_superblock,
 	},
 	[XFS_SCRUB_TYPE_AGF] = {	/* agf */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_agf,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_AGFL]= {	/* agfl */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_agfl,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {	/* agi */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_agi,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BNOBT] = {	/* bnobt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_allocbt,
 		.scrub	= xchk_bnobt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_CNTBT] = {	/* cntbt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_allocbt,
 		.scrub	= xchk_cntbt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INOBT] = {	/* inobt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_iallocbt,
 		.scrub	= xchk_inobt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_FINOBT] = {	/* finobt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_iallocbt,
 		.scrub	= xchk_finobt,
 		.has	= xfs_sb_version_hasfinobt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RMAPBT] = {	/* rmapbt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_rmapbt,
 		.scrub	= xchk_rmapbt,
 		.has	= xfs_sb_version_hasrmapbt,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_REFCNTBT] = {	/* refcountbt */
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_ag_refcountbt,
 		.scrub	= xchk_refcountbt,
 		.has	= xfs_sb_version_hasreflink,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {	/* inode record */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode,
 		.scrub	= xchk_inode,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTD] = {	/* inode data fork */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_data,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTA] = {	/* inode attr fork */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_attr,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_BMBTC] = {	/* inode CoW fork */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_inode_bmap,
 		.scrub	= xchk_bmap_cow,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_DIR] = {	/* directory */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_directory,
 		.scrub	= xchk_directory,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_XATTR] = {	/* extended attributes */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_xattr,
 		.scrub	= xchk_xattr,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_SYMLINK] = {	/* symbolic link */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_symlink,
 		.scrub	= xchk_symlink,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PARENT] = {	/* parent pointers */
 		.type	= ST_INODE,
 		.setup	= xchk_setup_parent,
 		.scrub	= xchk_parent,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_FS,
 		.setup	= xchk_setup_rt,
 		.scrub	= xchk_rtbitmap,
 		.has	= xfs_sb_version_hasrealtime,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_FS,
 		.setup	= xchk_setup_rt,
 		.scrub	= xchk_rtsummary,
 		.has	= xfs_sb_version_hasrealtime,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_UQUOTA] = {	/* user quota */
 		.type	= ST_FS,
 		.setup	= xchk_setup_quota,
 		.scrub	= xchk_quota,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_GQUOTA] = {	/* group quota */
 		.type	= ST_FS,
 		.setup	= xchk_setup_quota,
 		.scrub	= xchk_quota,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 	[XFS_SCRUB_TYPE_PQUOTA] = {	/* project quota */
 		.type	= ST_FS,
 		.setup	= xchk_setup_quota,
 		.scrub	= xchk_quota,
-		.repair	= xfs_repair_notsupported,
+		.repair	= xrep_notsupported,
 	},
 };
 
@@ -457,7 +457,7 @@ static inline void xchk_postmortem(struct xfs_scrub_context *sc)
 	if ((sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) &&
 	    (sc->sm->sm_flags & (XFS_SCRUB_OFLAG_CORRUPT |
 				 XFS_SCRUB_OFLAG_XCORRUPT)))
-		xfs_repair_failure(sc->mp);
+		xrep_failure(sc->mp);
 }
 #else
 static inline void xchk_postmortem(struct xfs_scrub_context *sc)
@@ -555,13 +555,13 @@ retry_op:
 		 * If it's broken, userspace wants us to fix it, and we haven't
 		 * already tried to fix it, then attempt a repair.
 		 */
-		error = xfs_repair_attempt(ip, &sc, &already_fixed);
+		error = xrep_attempt(ip, &sc, &already_fixed);
 		if (error == -EAGAIN) {
 			if (sc.try_harder)
 				try_harder = true;
 			error = xchk_teardown(&sc, ip, 0);
 			if (error) {
-				xfs_repair_failure(mp);
+				xrep_failure(mp);
 				goto out;
 			}
 			goto retry_op;
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 11967d3942ac..96f3edda3e91 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -55,8 +55,8 @@ DEFINE_EVENT(xchk_class, name, \
 DEFINE_SCRUB_EVENT(xchk_start);
 DEFINE_SCRUB_EVENT(xchk_done);
 DEFINE_SCRUB_EVENT(xchk_deadlock_retry);
-DEFINE_SCRUB_EVENT(xfs_repair_attempt);
-DEFINE_SCRUB_EVENT(xfs_repair_done);
+DEFINE_SCRUB_EVENT(xrep_attempt);
+DEFINE_SCRUB_EVENT(xrep_done);
 
 TRACE_EVENT(xchk_op_error,
 	TP_PROTO(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
@@ -483,7 +483,7 @@ TRACE_EVENT(xchk_xref_error,
 /* repair tracepoints */
 #if IS_ENABLED(CONFIG_XFS_ONLINE_REPAIR)
 
-DECLARE_EVENT_CLASS(xfs_repair_extent_class,
+DECLARE_EVENT_CLASS(xrep_extent_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len),
 	TP_ARGS(mp, agno, agbno, len),
@@ -506,15 +506,15 @@ DECLARE_EVENT_CLASS(xfs_repair_extent_class,
 		  __entry->len)
 );
 #define DEFINE_REPAIR_EXTENT_EVENT(name) \
-DEFINE_EVENT(xfs_repair_extent_class, name, \
+DEFINE_EVENT(xrep_extent_class, name, \
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
 		 xfs_agblock_t agbno, xfs_extlen_t len), \
 	TP_ARGS(mp, agno, agbno, len))
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_dispose_btree_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_collect_btree_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xfs_repair_agfl_insert);
+DEFINE_REPAIR_EXTENT_EVENT(xrep_dispose_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xrep_collect_btree_extent);
+DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
 
-DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
+DECLARE_EVENT_CLASS(xrep_rmap_class,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t agbno, xfs_extlen_t len,
 		 uint64_t owner, uint64_t offset, unsigned int flags),
@@ -547,17 +547,17 @@ DECLARE_EVENT_CLASS(xfs_repair_rmap_class,
 		  __entry->flags)
 );
 #define DEFINE_REPAIR_RMAP_EVENT(name) \
-DEFINE_EVENT(xfs_repair_rmap_class, name, \
+DEFINE_EVENT(xrep_rmap_class, name, \
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, \
 		 xfs_agblock_t agbno, xfs_extlen_t len, \
 		 uint64_t owner, uint64_t offset, unsigned int flags), \
 	TP_ARGS(mp, agno, agbno, len, owner, offset, flags))
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_alloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_ialloc_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_rmap_extent_fn);
-DEFINE_REPAIR_RMAP_EVENT(xfs_repair_bmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_alloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_ialloc_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_rmap_extent_fn);
+DEFINE_REPAIR_RMAP_EVENT(xrep_bmap_extent_fn);
 
-TRACE_EVENT(xfs_repair_refcount_extent_fn,
+TRACE_EVENT(xrep_refcount_extent_fn,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 struct xfs_refcount_irec *irec),
 	TP_ARGS(mp, agno, irec),
@@ -583,7 +583,7 @@ TRACE_EVENT(xfs_repair_refcount_extent_fn,
 		  __entry->refcount)
 )
 
-TRACE_EVENT(xfs_repair_init_btblock,
+TRACE_EVENT(xrep_init_btblock,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 xfs_btnum_t btnum),
 	TP_ARGS(mp, agno, agbno, btnum),
@@ -605,7 +605,7 @@ TRACE_EVENT(xfs_repair_init_btblock,
 		  __entry->agbno,
 		  __entry->btnum)
 )
-TRACE_EVENT(xfs_repair_findroot_block,
+TRACE_EVENT(xrep_findroot_block,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno, xfs_agblock_t agbno,
 		 uint32_t magic, uint16_t level),
 	TP_ARGS(mp, agno, agbno, magic, level),
@@ -630,7 +630,7 @@ TRACE_EVENT(xfs_repair_findroot_block,
 		  __entry->magic,
 		  __entry->level)
 )
-TRACE_EVENT(xfs_repair_calc_ag_resblks,
+TRACE_EVENT(xrep_calc_ag_resblks,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agino_t icount, xfs_agblock_t aglen, xfs_agblock_t freelen,
 		 xfs_agblock_t usedlen),
@@ -659,7 +659,7 @@ TRACE_EVENT(xfs_repair_calc_ag_resblks,
 		  __entry->freelen,
 		  __entry->usedlen)
 )
-TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
+TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agblock_t bnobt_sz, xfs_agblock_t inobt_sz,
 		 xfs_agblock_t rmapbt_sz, xfs_agblock_t refcbt_sz),
@@ -688,7 +688,7 @@ TRACE_EVENT(xfs_repair_calc_ag_resblks_btsize,
 		  __entry->rmapbt_sz,
 		  __entry->refcbt_sz)
 )
-TRACE_EVENT(xfs_repair_reset_counters,
+TRACE_EVENT(xrep_reset_counters,
 	TP_PROTO(struct xfs_mount *mp),
 	TP_ARGS(mp),
 	TP_STRUCT__entry(
@@ -701,7 +701,7 @@ TRACE_EVENT(xfs_repair_reset_counters,
 		  MAJOR(__entry->dev), MINOR(__entry->dev))
 )
 
-TRACE_EVENT(xfs_repair_ialloc_insert,
+TRACE_EVENT(xrep_ialloc_insert,
 	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
 		 xfs_agino_t startino, uint16_t holemask, uint8_t count,
 		 uint8_t freecount, uint64_t freemask),
-- 
cgit v1.2.3


From 1d8a748a8aa94a7da8f3d4fac1892037890d3cff Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:29:12 -0700
Subject: xfs: shorten struct xfs_scrub_context to struct xfs_scrub

Shorten the name of the online fsck context structure.  Whitespace
damage will be fixed by a subsequent patch.  There are no functional
changes.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/agheader.c        | 32 +++++++--------
 fs/xfs/scrub/agheader_repair.c |  2 +-
 fs/xfs/scrub/alloc.c           | 14 +++----
 fs/xfs/scrub/attr.c            | 10 ++---
 fs/xfs/scrub/bmap.c            | 22 +++++------
 fs/xfs/scrub/btree.c           | 14 +++----
 fs/xfs/scrub/btree.h           | 12 +++---
 fs/xfs/scrub/common.c          | 62 ++++++++++++++---------------
 fs/xfs/scrub/common.h          | 88 +++++++++++++++++++++---------------------
 fs/xfs/scrub/dabtree.c         |  6 +--
 fs/xfs/scrub/dabtree.h         |  4 +-
 fs/xfs/scrub/dir.c             | 18 ++++-----
 fs/xfs/scrub/ialloc.c          | 22 +++++------
 fs/xfs/scrub/inode.c           | 22 +++++------
 fs/xfs/scrub/parent.c          |  8 ++--
 fs/xfs/scrub/quota.c           | 12 +++---
 fs/xfs/scrub/refcount.c        | 16 ++++----
 fs/xfs/scrub/repair.c          | 36 ++++++++---------
 fs/xfs/scrub/repair.h          | 38 +++++++++---------
 fs/xfs/scrub/rmap.c            | 16 ++++----
 fs/xfs/scrub/rtbitmap.c        | 10 ++---
 fs/xfs/scrub/scrub.c           | 10 ++---
 fs/xfs/scrub/scrub.h           | 78 ++++++++++++++++++-------------------
 fs/xfs/scrub/symlink.c         |  4 +-
 fs/xfs/scrub/trace.h           | 32 +++++++--------
 25 files changed, 294 insertions(+), 294 deletions(-)

diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index c0625ec16d63..14ba4189ae8f 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -29,7 +29,7 @@
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_superblock_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_buf			*bp)
 {
 	struct xfs_owner_info		oinfo;
@@ -66,7 +66,7 @@ xchk_superblock_xref(
  */
 int
 xchk_superblock(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_buf			*bp;
@@ -365,7 +365,7 @@ xchk_agf_record_bno_lengths(
 /* Check agf_freeblks */
 static inline void
 xchk_agf_xref_freeblks(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	xfs_extlen_t			blocks = 0;
@@ -385,7 +385,7 @@ xchk_agf_xref_freeblks(
 /* Cross reference the AGF with the cntbt (freespace by length btree) */
 static inline void
 xchk_agf_xref_cntbt(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	xfs_agblock_t			agbno;
@@ -417,7 +417,7 @@ xchk_agf_xref_cntbt(
 /* Check the btree block counts in the AGF against the btrees. */
 STATIC void
 xchk_agf_xref_btreeblks(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	struct xfs_mount		*mp = sc->mp;
@@ -463,7 +463,7 @@ xchk_agf_xref_btreeblks(
 /* Check agf_refcount_blocks against tree size */
 static inline void
 xchk_agf_xref_refcblks(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
 	xfs_agblock_t			blocks;
@@ -482,7 +482,7 @@ xchk_agf_xref_refcblks(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_agf_xref(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
@@ -514,7 +514,7 @@ xchk_agf_xref(
 /* Scrub the AGF. */
 int
 xchk_agf(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_agf			*agf;
@@ -602,13 +602,13 @@ struct xchk_agfl_info {
 	unsigned int			sz_entries;
 	unsigned int			nr_entries;
 	xfs_agblock_t			*entries;
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 };
 
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_agfl_block_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	struct xfs_owner_info		*oinfo)
 {
@@ -629,7 +629,7 @@ xchk_agfl_block(
 	void				*priv)
 {
 	struct xchk_agfl_info		*sai = priv;
-	struct xfs_scrub_context	*sc = sai->sc;
+	struct xfs_scrub	*sc = sai->sc;
 	xfs_agnumber_t			agno = sc->sa.agno;
 
 	if (xfs_verify_agbno(mp, agno, agbno) &&
@@ -660,7 +660,7 @@ xchk_agblock_cmp(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_agfl_xref(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
@@ -691,7 +691,7 @@ xchk_agfl_xref(
 /* Scrub the AGFL. */
 int
 xchk_agfl(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xchk_agfl_info		sai;
 	struct xfs_agf			*agf;
@@ -768,7 +768,7 @@ out:
 /* Check agi_count/agi_freecount */
 static inline void
 xchk_agi_xref_icounts(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_agi			*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
 	xfs_agino_t			icount;
@@ -789,7 +789,7 @@ xchk_agi_xref_icounts(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_agi_xref(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_owner_info		oinfo;
 	struct xfs_mount		*mp = sc->mp;
@@ -818,7 +818,7 @@ xchk_agi_xref(
 /* Scrub the AGI. */
 int
 xchk_agi(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_agi			*agi;
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 631940f3ca4d..2457968482f8 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -29,7 +29,7 @@
 /* Repair the superblock. */
 int
 xrep_superblock(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_buf			*bp;
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 1f6e3a6a1fdd..653d80b3aa39 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -29,7 +29,7 @@
  */
 int
 xchk_setup_ag_allocbt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, false);
@@ -42,7 +42,7 @@ xchk_setup_ag_allocbt(
  */
 STATIC void
 xchk_allocbt_xref_other(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
@@ -82,7 +82,7 @@ xchk_allocbt_xref_other(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_allocbt_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
@@ -123,7 +123,7 @@ xchk_allocbt_rec(
 /* Scrub the freespace btrees for some AG. */
 STATIC int
 xchk_allocbt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_btnum_t			which)
 {
 	struct xfs_owner_info		oinfo;
@@ -136,14 +136,14 @@ xchk_allocbt(
 
 int
 xchk_bnobt(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	return xchk_allocbt(sc, XFS_BTNUM_BNO);
 }
 
 int
 xchk_cntbt(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	return xchk_allocbt(sc, XFS_BTNUM_CNT);
 }
@@ -151,7 +151,7 @@ xchk_cntbt(
 /* xref check that the extent is not free */
 void
 xchk_xref_is_used_space(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 0068bebddf3e..6650fb3010b6 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -33,7 +33,7 @@
 /* Set us up to scrub an inode's extended attributes. */
 int
 xchk_setup_xattr(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	size_t				sz;
@@ -57,7 +57,7 @@ xchk_setup_xattr(
 
 struct xchk_xattr {
 	struct xfs_attr_list_context	context;
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 };
 
 /*
@@ -127,7 +127,7 @@ fail_xref:
  */
 STATIC bool
 xchk_xattr_set_map(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	unsigned long			*map,
 	unsigned int			start,
 	unsigned int			len)
@@ -155,7 +155,7 @@ xchk_xattr_set_map(
  */
 STATIC bool
 xchk_xattr_check_freemap(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	unsigned long			*map,
 	struct xfs_attr3_icleaf_hdr	*leafhdr)
 {
@@ -405,7 +405,7 @@ out:
 /* Scrub the extended attribute metadata. */
 int
 xchk_xattr(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xchk_xattr		sx;
 	struct attrlist_cursor_kern	cursor = { 0 };
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 19cfbd3910a2..0e5166232b15 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -34,7 +34,7 @@
 /* Set us up with an inode's bmap. */
 int
 xchk_setup_inode_bmap(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	int				error;
@@ -79,7 +79,7 @@ out:
  */
 
 struct xchk_bmap_info {
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 	xfs_fileoff_t			lastoff;
 	bool				is_rt;
 	bool				is_shared;
@@ -391,7 +391,7 @@ xchk_bmapbt_rec(
 /* Scan the btree records. */
 STATIC int
 xchk_bmap_btree(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	struct xchk_bmap_info		*info)
 {
@@ -409,7 +409,7 @@ xchk_bmap_btree(
 }
 
 struct xchk_bmap_check_rmap_info {
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 	int				whichfork;
 	struct xfs_iext_cursor		icur;
 };
@@ -424,7 +424,7 @@ xchk_bmap_check_rmap(
 	struct xfs_bmbt_irec		irec;
 	struct xchk_bmap_check_rmap_info	*sbcri = priv;
 	struct xfs_ifork		*ifp;
-	struct xfs_scrub_context	*sc = sbcri->sc;
+	struct xfs_scrub	*sc = sbcri->sc;
 	bool				have_map;
 
 	/* Is this even the right fork? */
@@ -488,7 +488,7 @@ out:
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
 xchk_bmap_check_ag_rmaps(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xfs_agnumber_t			agno)
 {
@@ -522,7 +522,7 @@ out_agf:
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
 xchk_bmap_check_rmaps(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork)
 {
 	loff_t				size;
@@ -579,7 +579,7 @@ xchk_bmap_check_rmaps(
  */
 STATIC int
 xchk_bmap(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork)
 {
 	struct xfs_bmbt_irec		irec;
@@ -694,7 +694,7 @@ out:
 /* Scrub an inode's data fork. */
 int
 xchk_bmap_data(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	return xchk_bmap(sc, XFS_DATA_FORK);
 }
@@ -702,7 +702,7 @@ xchk_bmap_data(
 /* Scrub an inode's attr fork. */
 int
 xchk_bmap_attr(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	return xchk_bmap(sc, XFS_ATTR_FORK);
 }
@@ -710,7 +710,7 @@ xchk_bmap_attr(
 /* Scrub an inode's CoW fork. */
 int
 xchk_bmap_cow(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	if (!xfs_is_reflink_inode(sc->ip))
 		return -ENOENT;
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index 30fe9a147959..c4e1dce8c5b3 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -30,7 +30,7 @@
  */
 static bool
 __xchk_btree_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
 	int				*error,
@@ -65,7 +65,7 @@ __xchk_btree_process_error(
 
 bool
 xchk_btree_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
 	int				*error)
@@ -76,7 +76,7 @@ xchk_btree_process_error(
 
 bool
 xchk_btree_xref_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
 	int				*error)
@@ -88,7 +88,7 @@ xchk_btree_xref_process_error(
 /* Record btree block corruption. */
 static void
 __xchk_btree_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level,
 	__u32				errflag,
@@ -106,7 +106,7 @@ __xchk_btree_set_corrupt(
 
 void
 xchk_btree_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level)
 {
@@ -116,7 +116,7 @@ xchk_btree_set_corrupt(
 
 void
 xchk_btree_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_btree_cur		*cur,
 	int				level)
 {
@@ -583,7 +583,7 @@ xchk_btree_block_keys(
  */
 int
 xchk_btree(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_btree_cur		*cur,
 	xchk_btree_rec_fn		scrub_fn,
 	struct xfs_owner_info		*oinfo,
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index 598ac04a6c3e..a0b74b515b9b 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -9,20 +9,20 @@
 /* btree scrub */
 
 /* Check for btree operation errors. */
-bool xchk_btree_process_error(struct xfs_scrub_context *sc,
+bool xchk_btree_process_error(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level, int *error);
 
 /* Check for btree xref operation errors. */
-bool xchk_btree_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_btree_xref_process_error(struct xfs_scrub *sc,
 				struct xfs_btree_cur *cur, int level,
 				int *error);
 
 /* Check for btree corruption. */
-void xchk_btree_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level);
 
 /* Check for btree xref discrepancies. */
-void xchk_btree_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_btree_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_btree_cur *cur, int level);
 
 struct xchk_btree;
@@ -32,7 +32,7 @@ typedef int (*xchk_btree_rec_fn)(
 
 struct xchk_btree {
 	/* caller-provided scrub state */
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 	struct xfs_btree_cur		*cur;
 	xchk_btree_rec_fn		scrub_rec;
 	struct xfs_owner_info		*oinfo;
@@ -45,7 +45,7 @@ struct xchk_btree {
 	bool				firstkey[XFS_BTREE_MAXLEVELS];
 	struct list_head		to_check;
 };
-int xchk_btree(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+int xchk_btree(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		    xchk_btree_rec_fn scrub_fn,
 		    struct xfs_owner_info *oinfo, void *private);
 
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index d40bba9e7596..ed9195116556 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -69,7 +69,7 @@
 /* Check for operational errors. */
 static bool
 __xchk_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
 	int				*error,
@@ -99,7 +99,7 @@ __xchk_process_error(
 
 bool
 xchk_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
 	int				*error)
@@ -110,7 +110,7 @@ xchk_process_error(
 
 bool
 xchk_xref_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agnumber_t			agno,
 	xfs_agblock_t			bno,
 	int				*error)
@@ -122,7 +122,7 @@ xchk_xref_process_error(
 /* Check for operational errors for a file offset. */
 static bool
 __xchk_fblock_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset,
 	int				*error,
@@ -152,7 +152,7 @@ __xchk_fblock_process_error(
 
 bool
 xchk_fblock_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset,
 	int				*error)
@@ -163,7 +163,7 @@ xchk_fblock_process_error(
 
 bool
 xchk_fblock_xref_process_error(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset,
 	int				*error)
@@ -187,7 +187,7 @@ xchk_fblock_xref_process_error(
 /* Record a block which could be optimized. */
 void
 xchk_block_set_preen(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_buf			*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
@@ -201,7 +201,7 @@ xchk_block_set_preen(
  */
 void
 xchk_ino_set_preen(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
@@ -211,7 +211,7 @@ xchk_ino_set_preen(
 /* Record a corrupt block. */
 void
 xchk_block_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_buf			*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
@@ -221,7 +221,7 @@ xchk_block_set_corrupt(
 /* Record a corruption while cross-referencing. */
 void
 xchk_block_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_buf			*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
@@ -235,7 +235,7 @@ xchk_block_xref_set_corrupt(
  */
 void
 xchk_ino_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
@@ -245,7 +245,7 @@ xchk_ino_set_corrupt(
 /* Record a corruption while cross-referencing with an inode. */
 void
 xchk_ino_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
@@ -255,7 +255,7 @@ xchk_ino_xref_set_corrupt(
 /* Record corruption in a block indexed by a file fork. */
 void
 xchk_fblock_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset)
 {
@@ -266,7 +266,7 @@ xchk_fblock_set_corrupt(
 /* Record a corruption while cross-referencing a fork block. */
 void
 xchk_fblock_xref_set_corrupt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset)
 {
@@ -280,7 +280,7 @@ xchk_fblock_xref_set_corrupt(
  */
 void
 xchk_ino_set_warning(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
@@ -290,7 +290,7 @@ xchk_ino_set_warning(
 /* Warn about a block indexed by a file fork that needs review. */
 void
 xchk_fblock_set_warning(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xfs_fileoff_t			offset)
 {
@@ -301,7 +301,7 @@ xchk_fblock_set_warning(
 /* Signal an incomplete scrub. */
 void
 xchk_set_incomplete(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_INCOMPLETE;
 	trace_xchk_incomplete(sc, __return_address);
@@ -345,7 +345,7 @@ xchk_count_rmap_ownedby_irec(
  */
 int
 xchk_count_rmap_ownedby_ag(
-	struct xfs_scrub_context		*sc,
+	struct xfs_scrub		*sc,
 	struct xfs_btree_cur			*cur,
 	struct xfs_owner_info			*oinfo,
 	xfs_filblks_t				*blocks)
@@ -371,7 +371,7 @@ xchk_count_rmap_ownedby_ag(
 /* Decide if we want to return an AG header read failure. */
 static inline bool
 want_ag_read_header_failure(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	unsigned int			type)
 {
 	/* Return all AG header read failures when scanning btrees. */
@@ -398,7 +398,7 @@ want_ag_read_header_failure(
  */
 int
 xchk_ag_read_headers(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agnumber_t			agno,
 	struct xfs_buf			**agi,
 	struct xfs_buf			**agf,
@@ -452,7 +452,7 @@ xchk_ag_btcur_free(
 /* Initialize all the btree cursors for an AG. */
 int
 xchk_ag_btcur_init(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xchk_ag		*sa)
 {
 	struct xfs_mount		*mp = sc->mp;
@@ -512,7 +512,7 @@ err:
 /* Release the AG header context and btree cursors. */
 void
 xchk_ag_free(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xchk_ag		*sa)
 {
 	xchk_ag_btcur_free(sa);
@@ -544,7 +544,7 @@ xchk_ag_free(
  */
 int
 xchk_ag_init(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agnumber_t			agno,
 	struct xchk_ag		*sa)
 {
@@ -586,7 +586,7 @@ xchk_perag_get(
  */
 int
 xchk_trans_alloc(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	uint				resblks)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
@@ -599,7 +599,7 @@ xchk_trans_alloc(
 /* Set us up with a transaction and an empty context. */
 int
 xchk_setup_fs(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	uint				resblks;
@@ -611,7 +611,7 @@ xchk_setup_fs(
 /* Set us up with AG headers and btree cursors. */
 int
 xchk_setup_ag_btree(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip,
 	bool				force_log)
 {
@@ -658,7 +658,7 @@ xchk_checkpoint_log(
  */
 int
 xchk_get_inode(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip_in)
 {
 	struct xfs_imap			imap;
@@ -722,7 +722,7 @@ xchk_get_inode(
 /* Set us up to scrub a file's contents. */
 int
 xchk_setup_inode_contents(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip,
 	unsigned int			resblks)
 {
@@ -753,7 +753,7 @@ out:
  */
 bool
 xchk_should_check_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				*error,
 	struct xfs_btree_cur		**curpp)
 {
@@ -788,7 +788,7 @@ xchk_should_check_xref(
 /* Run the structure verifiers on in-memory buffers to detect bad memory. */
 void
 xchk_buffer_recheck(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_buf			*bp)
 {
 	xfs_failaddr_t			fa;
@@ -814,7 +814,7 @@ xchk_buffer_recheck(
  */
 int
 xchk_metadata_inode_forks(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	__u32				smtype;
 	bool				shared;
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index 5881cb2ecc26..c321230d32dc 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -13,7 +13,7 @@
  */
 static inline bool
 xchk_should_terminate(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				*error)
 {
 	if (fatal_signal_pending(current)) {
@@ -24,109 +24,109 @@ xchk_should_terminate(
 	return false;
 }
 
-int xchk_trans_alloc(struct xfs_scrub_context *sc, uint resblks);
-bool xchk_process_error(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+int xchk_trans_alloc(struct xfs_scrub *sc, uint resblks);
+bool xchk_process_error(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		xfs_agblock_t bno, int *error);
-bool xchk_fblock_process_error(struct xfs_scrub_context *sc, int whichfork,
+bool xchk_fblock_process_error(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset, int *error);
 
-bool xchk_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_xref_process_error(struct xfs_scrub *sc,
 		xfs_agnumber_t agno, xfs_agblock_t bno, int *error);
-bool xchk_fblock_xref_process_error(struct xfs_scrub_context *sc,
+bool xchk_fblock_xref_process_error(struct xfs_scrub *sc,
 		int whichfork, xfs_fileoff_t offset, int *error);
 
-void xchk_block_set_preen(struct xfs_scrub_context *sc,
+void xchk_block_set_preen(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xchk_ino_set_preen(struct xfs_scrub_context *sc, xfs_ino_t ino);
+void xchk_ino_set_preen(struct xfs_scrub *sc, xfs_ino_t ino);
 
-void xchk_block_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xchk_ino_set_corrupt(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xchk_fblock_set_corrupt(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_corrupt(struct xfs_scrub *sc, xfs_ino_t ino);
+void xchk_fblock_set_corrupt(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xchk_block_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_block_xref_set_corrupt(struct xfs_scrub *sc,
 		struct xfs_buf *bp);
-void xchk_ino_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_ino_xref_set_corrupt(struct xfs_scrub *sc,
 		xfs_ino_t ino);
-void xchk_fblock_xref_set_corrupt(struct xfs_scrub_context *sc,
+void xchk_fblock_xref_set_corrupt(struct xfs_scrub *sc,
 		int whichfork, xfs_fileoff_t offset);
 
-void xchk_ino_set_warning(struct xfs_scrub_context *sc, xfs_ino_t ino);
-void xchk_fblock_set_warning(struct xfs_scrub_context *sc, int whichfork,
+void xchk_ino_set_warning(struct xfs_scrub *sc, xfs_ino_t ino);
+void xchk_fblock_set_warning(struct xfs_scrub *sc, int whichfork,
 		xfs_fileoff_t offset);
 
-void xchk_set_incomplete(struct xfs_scrub_context *sc);
+void xchk_set_incomplete(struct xfs_scrub *sc);
 int xchk_checkpoint_log(struct xfs_mount *mp);
 
 /* Are we set up for a cross-referencing check? */
-bool xchk_should_check_xref(struct xfs_scrub_context *sc, int *error,
+bool xchk_should_check_xref(struct xfs_scrub *sc, int *error,
 			   struct xfs_btree_cur **curpp);
 
 /* Setup functions */
-int xchk_setup_fs(struct xfs_scrub_context *sc, struct xfs_inode *ip);
-int xchk_setup_ag_allocbt(struct xfs_scrub_context *sc,
+int xchk_setup_fs(struct xfs_scrub *sc, struct xfs_inode *ip);
+int xchk_setup_ag_allocbt(struct xfs_scrub *sc,
 			       struct xfs_inode *ip);
-int xchk_setup_ag_iallocbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_iallocbt(struct xfs_scrub *sc,
 				struct xfs_inode *ip);
-int xchk_setup_ag_rmapbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_rmapbt(struct xfs_scrub *sc,
 			      struct xfs_inode *ip);
-int xchk_setup_ag_refcountbt(struct xfs_scrub_context *sc,
+int xchk_setup_ag_refcountbt(struct xfs_scrub *sc,
 				  struct xfs_inode *ip);
-int xchk_setup_inode(struct xfs_scrub_context *sc,
+int xchk_setup_inode(struct xfs_scrub *sc,
 			  struct xfs_inode *ip);
-int xchk_setup_inode_bmap(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap(struct xfs_scrub *sc,
 			       struct xfs_inode *ip);
-int xchk_setup_inode_bmap_data(struct xfs_scrub_context *sc,
+int xchk_setup_inode_bmap_data(struct xfs_scrub *sc,
 				    struct xfs_inode *ip);
-int xchk_setup_directory(struct xfs_scrub_context *sc,
+int xchk_setup_directory(struct xfs_scrub *sc,
 			      struct xfs_inode *ip);
-int xchk_setup_xattr(struct xfs_scrub_context *sc,
+int xchk_setup_xattr(struct xfs_scrub *sc,
 			  struct xfs_inode *ip);
-int xchk_setup_symlink(struct xfs_scrub_context *sc,
+int xchk_setup_symlink(struct xfs_scrub *sc,
 			    struct xfs_inode *ip);
-int xchk_setup_parent(struct xfs_scrub_context *sc,
+int xchk_setup_parent(struct xfs_scrub *sc,
 			   struct xfs_inode *ip);
 #ifdef CONFIG_XFS_RT
-int xchk_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip);
 #else
 static inline int
-xchk_setup_rt(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_rt(struct xfs_scrub *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xchk_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip);
+int xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip);
 #else
 static inline int
-xchk_setup_quota(struct xfs_scrub_context *sc, struct xfs_inode *ip)
+xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip)
 {
 	return -ENOENT;
 }
 #endif
 
-void xchk_ag_free(struct xfs_scrub_context *sc, struct xchk_ag *sa);
-int xchk_ag_init(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		      struct xchk_ag *sa);
 void xchk_perag_get(struct xfs_mount *mp, struct xchk_ag *sa);
-int xchk_ag_read_headers(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
 			      struct xfs_buf **agi, struct xfs_buf **agf,
 			      struct xfs_buf **agfl);
 void xchk_ag_btcur_free(struct xchk_ag *sa);
-int xchk_ag_btcur_init(struct xfs_scrub_context *sc,
+int xchk_ag_btcur_init(struct xfs_scrub *sc,
 			    struct xchk_ag *sa);
-int xchk_count_rmap_ownedby_ag(struct xfs_scrub_context *sc,
+int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc,
 				    struct xfs_btree_cur *cur,
 				    struct xfs_owner_info *oinfo,
 				    xfs_filblks_t *blocks);
 
-int xchk_setup_ag_btree(struct xfs_scrub_context *sc,
+int xchk_setup_ag_btree(struct xfs_scrub *sc,
 			     struct xfs_inode *ip, bool force_log);
-int xchk_get_inode(struct xfs_scrub_context *sc, struct xfs_inode *ip_in);
-int xchk_setup_inode_contents(struct xfs_scrub_context *sc,
+int xchk_get_inode(struct xfs_scrub *sc, struct xfs_inode *ip_in);
+int xchk_setup_inode_contents(struct xfs_scrub *sc,
 				   struct xfs_inode *ip, unsigned int resblks);
-void xchk_buffer_recheck(struct xfs_scrub_context *sc, struct xfs_buf *bp);
+void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
 
 /*
  * Don't bother cross-referencing if we already found corruption or cross
@@ -138,7 +138,7 @@ static inline bool xchk_skip_xref(struct xfs_scrub_metadata *sm)
 			       XFS_SCRUB_OFLAG_XCORRUPT);
 }
 
-int xchk_metadata_inode_forks(struct xfs_scrub_context *sc);
+int xchk_metadata_inode_forks(struct xfs_scrub *sc);
 int xchk_ilock_inverted(struct xfs_inode *ip, uint lock_mode);
 
 #endif	/* __XFS_SCRUB_COMMON_H__ */
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index fee80f6ddfd7..7fc12d540ea6 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -40,7 +40,7 @@ xchk_da_process_error(
 	int				level,
 	int				*error)
 {
-	struct xfs_scrub_context	*sc = ds->sc;
+	struct xfs_scrub	*sc = ds->sc;
 
 	if (*error == 0)
 		return true;
@@ -75,7 +75,7 @@ xchk_da_set_corrupt(
 	struct xchk_da_btree		*ds,
 	int				level)
 {
-	struct xfs_scrub_context	*sc = ds->sc;
+	struct xfs_scrub	*sc = ds->sc;
 
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 
@@ -474,7 +474,7 @@ out_nobuf:
 /* Visit all nodes and leaves of a da btree. */
 int
 xchk_da_btree(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				whichfork,
 	xchk_da_btree_rec_fn	scrub_fn,
 	void				*private)
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index 80e4af0e2589..a15c03389e8f 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -13,7 +13,7 @@ struct xchk_da_btree {
 	xfs_dahash_t			hashes[XFS_DA_NODE_MAXDEPTH];
 	int				maxrecs[XFS_DA_NODE_MAXDEPTH];
 	struct xfs_da_state		*state;
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 	void				*private;
 
 	/*
@@ -39,7 +39,7 @@ void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
 
 int xchk_da_btree_hash(struct xchk_da_btree *ds, int level,
 			    __be32 *hashp);
-int xchk_da_btree(struct xfs_scrub_context *sc, int whichfork,
+int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
 		       xchk_da_btree_rec_fn scrub_fn, void *private);
 
 #endif /* __XFS_SCRUB_DABTREE_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 2ac07bb73478..194a3ef69a9f 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -32,7 +32,7 @@
 /* Set us up to scrub directories. */
 int
 xchk_setup_directory(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	return xchk_setup_inode_contents(sc, ip, 0);
@@ -46,7 +46,7 @@ struct xchk_dir_ctx {
 	/* VFS fill-directory iterator */
 	struct dir_context		dir_iter;
 
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 };
 
 /* Check that an inode's mode matches a given DT_ type. */
@@ -289,7 +289,7 @@ out:
  */
 STATIC void
 xchk_directory_check_free_entry(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_dir2_data_free	*bf,
 	struct xfs_dir2_data_unused	*dup)
@@ -314,7 +314,7 @@ xchk_directory_check_free_entry(
 /* Check free space info in a directory data block. */
 STATIC int
 xchk_directory_data_bestfree(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_dablk_t			lblk,
 	bool				is_block)
 {
@@ -455,7 +455,7 @@ out:
  */
 STATIC void
 xchk_directory_check_freesp(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_buf			*dbp,
 	unsigned int			len)
@@ -474,7 +474,7 @@ xchk_directory_check_freesp(
 /* Check free space info in a directory leaf1 block. */
 STATIC int
 xchk_directory_leaf1_bestfree(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -572,7 +572,7 @@ out:
 /* Check free space info in a directory freespace block. */
 STATIC int
 xchk_directory_free_bestfree(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -626,7 +626,7 @@ out:
 /* Check free space information in directories. */
 STATIC int
 xchk_directory_blocks(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_bmbt_irec		got;
 	struct xfs_da_args		args;
@@ -770,7 +770,7 @@ out:
 /* Scrub a whole directory. */
 int
 xchk_directory(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xchk_dir_ctx		sdc = {
 		.dir_iter.actor = xchk_dir_actor,
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 69d652b7299c..6df8eba9f52b 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -36,7 +36,7 @@
  */
 int
 xchk_setup_ag_iallocbt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, sc->try_harder);
@@ -51,7 +51,7 @@ xchk_setup_ag_iallocbt(
  */
 static inline void
 xchk_iallocbt_chunk_xref_other(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino)
 {
@@ -76,7 +76,7 @@ xchk_iallocbt_chunk_xref_other(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_iallocbt_chunk_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
 	xfs_agblock_t			agbno,
@@ -363,7 +363,7 @@ out:
  */
 STATIC void
 xchk_iallocbt_xref_rmap_btreeblks(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				which)
 {
 	struct xfs_owner_info		oinfo;
@@ -403,7 +403,7 @@ xchk_iallocbt_xref_rmap_btreeblks(
  */
 STATIC void
 xchk_iallocbt_xref_rmap_inodes(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	int				which,
 	xfs_filblks_t			inode_blocks)
 {
@@ -427,7 +427,7 @@ xchk_iallocbt_xref_rmap_inodes(
 /* Scrub the inode btrees for some AG. */
 STATIC int
 xchk_iallocbt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_btnum_t			which)
 {
 	struct xfs_btree_cur		*cur;
@@ -459,14 +459,14 @@ xchk_iallocbt(
 
 int
 xchk_inobt(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	return xchk_iallocbt(sc, XFS_BTNUM_INO);
 }
 
 int
 xchk_finobt(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	return xchk_iallocbt(sc, XFS_BTNUM_FINO);
 }
@@ -474,7 +474,7 @@ xchk_finobt(
 /* See if an inode btree has (or doesn't have) an inode chunk record. */
 static inline void
 xchk_xref_inode_check(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len,
 	struct xfs_btree_cur		**icur,
@@ -496,7 +496,7 @@ xchk_xref_inode_check(
 /* xref check that the extent is not covered by inodes */
 void
 xchk_xref_is_not_inode_chunk(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
@@ -507,7 +507,7 @@ xchk_xref_is_not_inode_chunk(
 /* xref check that the extent is covered by inodes */
 void
 xchk_xref_is_inode_chunk(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index d85fbec39e52..6cc027983c13 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -38,7 +38,7 @@
  */
 int
 xchk_setup_inode(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	int				error;
@@ -77,7 +77,7 @@ out:
 /* Validate di_extsize hint. */
 STATIC void
 xchk_inode_extsize(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
 	uint16_t			mode,
@@ -99,7 +99,7 @@ xchk_inode_extsize(
  */
 STATIC void
 xchk_inode_cowextsize(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
 	uint16_t			mode,
@@ -118,7 +118,7 @@ xchk_inode_cowextsize(
 /* Make sure the di_flags make sense for the inode. */
 STATIC void
 xchk_inode_flags(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
 	uint16_t			mode,
@@ -163,7 +163,7 @@ bad:
 /* Make sure the di_flags2 make sense for the inode. */
 STATIC void
 xchk_inode_flags2(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino,
 	uint16_t			mode,
@@ -206,7 +206,7 @@ bad:
 /* Scrub all the ondisk inode fields. */
 STATIC void
 xchk_dinode(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_dinode		*dip,
 	xfs_ino_t			ino)
 {
@@ -426,7 +426,7 @@ xchk_dinode(
  */
 static void
 xchk_inode_xref_finobt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			ino)
 {
 	struct xfs_inobt_rec_incore	rec;
@@ -469,7 +469,7 @@ xchk_inode_xref_finobt(
 /* Cross reference the inode fields with the forks. */
 STATIC void
 xchk_inode_xref_bmap(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_dinode		*dip)
 {
 	xfs_extnum_t			nextents;
@@ -503,7 +503,7 @@ xchk_inode_xref_bmap(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_inode_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			ino,
 	struct xfs_dinode		*dip)
 {
@@ -540,7 +540,7 @@ xchk_inode_xref(
  */
 static void
 xchk_inode_check_reflink_iflag(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			ino)
 {
 	struct xfs_mount		*mp = sc->mp;
@@ -564,7 +564,7 @@ xchk_inode_check_reflink_iflag(
 /* Scrub an inode. */
 int
 xchk_inode(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_dinode		di;
 	int				error = 0;
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 0a78d8411f23..808459ad0c35 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -28,7 +28,7 @@
 /* Set us up to scrub parents. */
 int
 xchk_setup_parent(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	return xchk_setup_inode_contents(sc, ip, 0);
@@ -65,7 +65,7 @@ xchk_parent_actor(
 /* Count the number of dentries in the parent dir that point to this inode. */
 STATIC int
 xchk_parent_count_parent_dentries(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*parent,
 	xfs_nlink_t			*nlink)
 {
@@ -121,7 +121,7 @@ out:
  */
 STATIC int
 xchk_parent_validate(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_ino_t			dnum,
 	bool				*try_again)
 {
@@ -255,7 +255,7 @@ out:
 /* Scrub a parent pointer. */
 int
 xchk_parent(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	xfs_ino_t			dnum;
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index d1b52dd7efcd..309ebeecfa5d 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -31,7 +31,7 @@
 /* Convert a scrub type code to a DQ flag, or return 0 if error. */
 static inline uint
 xchk_quota_to_dqtype(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	switch (sc->sm->sm_type) {
 	case XFS_SCRUB_TYPE_UQUOTA:
@@ -48,7 +48,7 @@ xchk_quota_to_dqtype(
 /* Set us up to scrub a quota. */
 int
 xchk_setup_quota(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	uint				dqtype;
@@ -76,7 +76,7 @@ xchk_setup_quota(
 /* Quotas. */
 
 struct xchk_quota_info {
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 	xfs_dqid_t			last_id;
 };
 
@@ -88,7 +88,7 @@ xchk_quota_item(
 	void				*priv)
 {
 	struct xchk_quota_info		*sqi = priv;
-	struct xfs_scrub_context	*sc = sqi->sc;
+	struct xfs_scrub	*sc = sqi->sc;
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_disk_dquot		*d = &dq->q_core;
 	struct xfs_quotainfo		*qi = mp->m_quotainfo;
@@ -195,7 +195,7 @@ xchk_quota_item(
 /* Check the quota's data fork. */
 STATIC int
 xchk_quota_data_fork(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_bmbt_irec		irec = { 0 };
 	struct xfs_iext_cursor		icur;
@@ -234,7 +234,7 @@ xchk_quota_data_fork(
 /* Scrub all of a quota type's items. */
 int
 xchk_quota(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xchk_quota_info		sqi;
 	struct xfs_mount		*mp = sc->mp;
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index 274febc49b23..c1162d408987 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -29,7 +29,7 @@
  */
 int
 xchk_setup_ag_refcountbt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, false);
@@ -79,7 +79,7 @@ struct xchk_refcnt_frag {
 };
 
 struct xchk_refcnt_check {
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 	struct list_head		fragments;
 
 	/* refcount extent we're examining */
@@ -278,7 +278,7 @@ done:
 /* Use the rmap entries covering this extent to verify the refcount. */
 STATIC void
 xchk_refcountbt_xref_rmap(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	xfs_nlink_t			refcount)
@@ -325,7 +325,7 @@ out_free:
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_refcountbt_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len,
 	xfs_nlink_t			refcount)
@@ -382,7 +382,7 @@ xchk_refcountbt_rec(
 /* Make sure we have as many refc blocks as the rmap says. */
 STATIC void
 xchk_refcount_xref_rmap(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_owner_info		*oinfo,
 	xfs_filblks_t			cow_blocks)
 {
@@ -417,7 +417,7 @@ xchk_refcount_xref_rmap(
 /* Scrub the refcount btree for some AG. */
 int
 xchk_refcountbt(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_owner_info		oinfo;
 	xfs_agblock_t			cow_blocks = 0;
@@ -437,7 +437,7 @@ xchk_refcountbt(
 /* xref check that a cow staging extent is marked in the refcountbt. */
 void
 xchk_xref_is_cow_staging(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
@@ -483,7 +483,7 @@ xchk_xref_is_cow_staging(
  */
 void
 xchk_xref_is_not_shared(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 7e6a56a5f59d..29debd5649ac 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -43,7 +43,7 @@
 int
 xrep_attempt(
 	struct xfs_inode		*ip,
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	bool				*fixed)
 {
 	int				error = 0;
@@ -106,7 +106,7 @@ xrep_failure(
  */
 int
 xrep_probe(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	int				error = 0;
 
@@ -122,7 +122,7 @@ xrep_probe(
  */
 int
 xrep_roll_ag_trans(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	int				error;
 
@@ -179,7 +179,7 @@ xrep_ag_has_space(
  */
 xfs_extlen_t
 xrep_calc_ag_resblks(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_scrub_metadata	*sm = sc->sm;
@@ -279,7 +279,7 @@ xrep_calc_ag_resblks(
 /* Allocate a block in an AG. */
 int
 xrep_alloc_ag_block(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_owner_info		*oinfo,
 	xfs_fsblock_t			*fsbno,
 	enum xfs_ag_resv_type		resv)
@@ -330,7 +330,7 @@ xrep_alloc_ag_block(
 /* Initialize a new AG btree root block with zero entries. */
 int
 xrep_init_btblock(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_fsblock_t			fsb,
 	struct xfs_buf			**bpp,
 	xfs_btnum_t			btnum,
@@ -385,7 +385,7 @@ xrep_init_btblock(
 /* Collect a dead btree extent for later disposal. */
 int
 xrep_collect_btree_extent(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xrep_extent_list		*exlist,
 	xfs_fsblock_t			fsbno,
 	xfs_extlen_t			len)
@@ -415,7 +415,7 @@ xrep_collect_btree_extent(
  */
 void
 xrep_cancel_btree_extents(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xrep_extent_list		*exlist)
 {
 	struct xrep_extent		*rex;
@@ -463,7 +463,7 @@ xrep_btree_extent_cmp(
 #define RIGHT_ALIGNED	(1 << 1)
 int
 xrep_subtract_extents(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xrep_extent_list		*exlist,
 	struct xrep_extent_list		*sublist)
 {
@@ -620,7 +620,7 @@ out:
  */
 int
 xrep_invalidate_blocks(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xrep_extent_list		*exlist)
 {
 	struct xrep_extent		*rex;
@@ -658,7 +658,7 @@ xrep_invalidate_blocks(
 /* Ensure the freelist is the correct size. */
 int
 xrep_fix_freelist(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	bool				can_shrink)
 {
 	struct xfs_alloc_arg		args = {0};
@@ -678,7 +678,7 @@ xrep_fix_freelist(
  */
 STATIC int
 xrep_put_freelist(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			agbno)
 {
 	struct xfs_owner_info		oinfo;
@@ -714,7 +714,7 @@ xrep_put_freelist(
 /* Dispose of a single metadata block. */
 STATIC int
 xrep_dispose_btree_block(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_fsblock_t			fsbno,
 	struct xfs_owner_info		*oinfo,
 	enum xfs_ag_resv_type		resv)
@@ -788,7 +788,7 @@ out_free:
 /* Dispose of btree blocks from an old per-AG btree. */
 int
 xrep_reap_btree_extents(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xrep_extent_list		*exlist,
 	struct xfs_owner_info		*oinfo,
 	enum xfs_ag_resv_type		type)
@@ -851,7 +851,7 @@ out:
  */
 
 struct xrep_findroot {
-	struct xfs_scrub_context	*sc;
+	struct xfs_scrub	*sc;
 	struct xfs_buf			*agfl_bp;
 	struct xfs_agf			*agf;
 	struct xrep_find_ag_btree	*btree_info;
@@ -981,7 +981,7 @@ xrep_findroot_rmap(
 /* Find the roots of the per-AG btrees described in btree_info. */
 int
 xrep_find_ag_btree_roots(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_buf			*agf_bp,
 	struct xrep_find_ag_btree	*btree_info,
 	struct xfs_buf			*agfl_bp)
@@ -1016,7 +1016,7 @@ xrep_find_ag_btree_roots(
 /* Force a quotacheck the next time we mount. */
 void
 xrep_force_quotacheck(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	uint				dqtype)
 {
 	uint				flag;
@@ -1044,7 +1044,7 @@ xrep_force_quotacheck(
  */
 int
 xrep_ino_dqattach(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	int				error;
 
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 60d81294797b..677f4b73b5ec 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -6,7 +6,7 @@
 #ifndef __XFS_SCRUB_REPAIR_H__
 #define __XFS_SCRUB_REPAIR_H__
 
-static inline int xrep_notsupported(struct xfs_scrub_context *sc)
+static inline int xrep_notsupported(struct xfs_scrub *sc)
 {
 	return -EOPNOTSUPP;
 }
@@ -15,17 +15,17 @@ static inline int xrep_notsupported(struct xfs_scrub_context *sc)
 
 /* Repair helpers */
 
-int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub_context *sc,
+int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc,
 		bool *fixed);
 void xrep_failure(struct xfs_mount *mp);
-int xrep_roll_ag_trans(struct xfs_scrub_context *sc);
+int xrep_roll_ag_trans(struct xfs_scrub *sc);
 bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
 		enum xfs_ag_resv_type type);
-xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub_context *sc);
-int xrep_alloc_ag_block(struct xfs_scrub_context *sc,
+xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub *sc);
+int xrep_alloc_ag_block(struct xfs_scrub *sc,
 		struct xfs_owner_info *oinfo, xfs_fsblock_t *fsbno,
 		enum xfs_ag_resv_type resv);
-int xrep_init_btblock(struct xfs_scrub_context *sc, xfs_fsblock_t fsb,
+int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb,
 		struct xfs_buf **bpp, xfs_btnum_t btnum,
 		const struct xfs_buf_ops *ops);
 
@@ -48,18 +48,18 @@ xrep_init_extent_list(
 
 #define for_each_xrep_extent_safe(rbe, n, exlist) \
 	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
-int xrep_collect_btree_extent(struct xfs_scrub_context *sc,
+int xrep_collect_btree_extent(struct xfs_scrub *sc,
 		struct xrep_extent_list *btlist, xfs_fsblock_t fsbno,
 		xfs_extlen_t len);
-void xrep_cancel_btree_extents(struct xfs_scrub_context *sc,
+void xrep_cancel_btree_extents(struct xfs_scrub *sc,
 		struct xrep_extent_list *btlist);
-int xrep_subtract_extents(struct xfs_scrub_context *sc,
+int xrep_subtract_extents(struct xfs_scrub *sc,
 		struct xrep_extent_list *exlist,
 		struct xrep_extent_list *sublist);
-int xrep_fix_freelist(struct xfs_scrub_context *sc, bool can_shrink);
-int xrep_invalidate_blocks(struct xfs_scrub_context *sc,
+int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
+int xrep_invalidate_blocks(struct xfs_scrub *sc,
 		struct xrep_extent_list *btlist);
-int xrep_reap_btree_extents(struct xfs_scrub_context *sc,
+int xrep_reap_btree_extents(struct xfs_scrub *sc,
 		struct xrep_extent_list *exlist,
 		struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
 
@@ -78,23 +78,23 @@ struct xrep_find_ag_btree {
 	unsigned int			height;
 };
 
-int xrep_find_ag_btree_roots(struct xfs_scrub_context *sc,
+int xrep_find_ag_btree_roots(struct xfs_scrub *sc,
 		struct xfs_buf *agf_bp,
 		struct xrep_find_ag_btree *btree_info,
 		struct xfs_buf *agfl_bp);
-void xrep_force_quotacheck(struct xfs_scrub_context *sc, uint dqtype);
-int xrep_ino_dqattach(struct xfs_scrub_context *sc);
+void xrep_force_quotacheck(struct xfs_scrub *sc, uint dqtype);
+int xrep_ino_dqattach(struct xfs_scrub *sc);
 
 /* Metadata repairers */
 
-int xrep_probe(struct xfs_scrub_context *sc);
-int xrep_superblock(struct xfs_scrub_context *sc);
+int xrep_probe(struct xfs_scrub *sc);
+int xrep_superblock(struct xfs_scrub *sc);
 
 #else
 
 static inline int xrep_attempt(
 	struct xfs_inode		*ip,
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	bool				*fixed)
 {
 	return -EOPNOTSUPP;
@@ -104,7 +104,7 @@ static inline void xrep_failure(struct xfs_mount *mp) {}
 
 static inline xfs_extlen_t
 xrep_calc_ag_resblks(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	ASSERT(!(sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR));
 	return 0;
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index 4b75fc2f31f3..dc9c91a706ff 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -30,7 +30,7 @@
  */
 int
 xchk_setup_ag_rmapbt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, false);
@@ -41,7 +41,7 @@ xchk_setup_ag_rmapbt(
 /* Cross-reference a rmap against the refcount btree. */
 STATIC void
 xchk_rmapbt_xref_refc(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_rmap_irec		*irec)
 {
 	xfs_agblock_t			fbno;
@@ -72,7 +72,7 @@ xchk_rmapbt_xref_refc(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_rmapbt_xref(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_rmap_irec		*irec)
 {
 	xfs_agblock_t			agbno = irec->rm_startblock;
@@ -172,7 +172,7 @@ out:
 /* Scrub the rmap btree for some AG. */
 int
 xchk_rmapbt(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_owner_info		oinfo;
 
@@ -184,7 +184,7 @@ xchk_rmapbt(
 /* xref check that the extent is owned by a given owner */
 static inline void
 xchk_xref_check_owner(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	struct xfs_owner_info		*oinfo,
@@ -207,7 +207,7 @@ xchk_xref_check_owner(
 /* xref check that the extent is owned by a given owner */
 void
 xchk_xref_is_owned_by(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	struct xfs_owner_info		*oinfo)
@@ -218,7 +218,7 @@ xchk_xref_is_owned_by(
 /* xref check that the extent is not owned by a given owner */
 void
 xchk_xref_is_not_owned_by(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	struct xfs_owner_info		*oinfo)
@@ -229,7 +229,7 @@ xchk_xref_is_not_owned_by(
 /* xref check that the extent has no reverse mapping at all */
 void
 xchk_xref_has_no_owner(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len)
 {
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 3f0fc83562ae..653a809bba34 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -26,7 +26,7 @@
 /* Set us up with the realtime metadata locked. */
 int
 xchk_setup_rt(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	int				error;
@@ -51,7 +51,7 @@ xchk_rtbitmap_rec(
 	struct xfs_rtalloc_rec		*rec,
 	void				*priv)
 {
-	struct xfs_scrub_context	*sc = priv;
+	struct xfs_scrub	*sc = priv;
 	xfs_rtblock_t			startblock;
 	xfs_rtblock_t			blockcount;
 
@@ -68,7 +68,7 @@ xchk_rtbitmap_rec(
 /* Scrub the realtime bitmap. */
 int
 xchk_rtbitmap(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	int				error;
 
@@ -88,7 +88,7 @@ out:
 /* Scrub the realtime summary. */
 int
 xchk_rtsummary(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_inode		*rsumip = sc->mp->m_rsumip;
 	struct xfs_inode		*old_ip = sc->ip;
@@ -125,7 +125,7 @@ out:
 /* xref check that the extent is not free in the rtbitmap */
 void
 xchk_xref_is_used_rt_space(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	xfs_rtblock_t			fsbno,
 	xfs_extlen_t			len)
 {
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index a6efede6e430..b3c6420ccae5 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -151,7 +151,7 @@
  */
 static int
 xchk_probe(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	int				error = 0;
 
@@ -166,7 +166,7 @@ xchk_probe(
 /* Free all the resources and finish the transactions. */
 STATIC int
 xchk_teardown(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip_in,
 	int				error)
 {
@@ -447,7 +447,7 @@ out:
 }
 
 #ifdef CONFIG_XFS_ONLINE_REPAIR
-static inline void xchk_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub *sc)
 {
 	/*
 	 * Userspace asked us to repair something, we repaired it, rescanned
@@ -460,7 +460,7 @@ static inline void xchk_postmortem(struct xfs_scrub_context *sc)
 		xrep_failure(sc->mp);
 }
 #else
-static inline void xchk_postmortem(struct xfs_scrub_context *sc)
+static inline void xchk_postmortem(struct xfs_scrub *sc)
 {
 	/*
 	 * Userspace asked us to scrub something, it's broken, and we have no
@@ -479,7 +479,7 @@ xfs_scrub_metadata(
 	struct xfs_inode		*ip,
 	struct xfs_scrub_metadata	*sm)
 {
-	struct xfs_scrub_context	sc;
+	struct xfs_scrub	sc;
 	struct xfs_mount		*mp = ip->i_mount;
 	bool				try_harder = false;
 	bool				already_fixed = false;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 0f59a47c4bb0..47c75d2f28da 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -6,7 +6,7 @@
 #ifndef __XFS_SCRUB_SCRUB_H__
 #define __XFS_SCRUB_SCRUB_H__
 
-struct xfs_scrub_context;
+struct xfs_scrub;
 
 /* Type info and names for the scrub types. */
 enum xchk_type {
@@ -18,14 +18,14 @@ enum xchk_type {
 
 struct xchk_meta_ops {
 	/* Acquire whatever resources are needed for the operation. */
-	int		(*setup)(struct xfs_scrub_context *,
+	int		(*setup)(struct xfs_scrub *,
 				 struct xfs_inode *);
 
 	/* Examine metadata for errors. */
-	int		(*scrub)(struct xfs_scrub_context *);
+	int		(*scrub)(struct xfs_scrub *);
 
 	/* Repair or optimize the metadata. */
-	int		(*repair)(struct xfs_scrub_context *);
+	int		(*repair)(struct xfs_scrub *);
 
 	/* Decide if we even have this piece of metadata. */
 	bool		(*has)(struct xfs_sb *);
@@ -53,7 +53,7 @@ struct xchk_ag {
 	struct xfs_btree_cur		*refc_cur;
 };
 
-struct xfs_scrub_context {
+struct xfs_scrub {
 	/* General scrub state. */
 	struct xfs_mount		*mp;
 	struct xfs_scrub_metadata	*sm;
@@ -70,71 +70,71 @@ struct xfs_scrub_context {
 };
 
 /* Metadata scrubbers */
-int xchk_tester(struct xfs_scrub_context *sc);
-int xchk_superblock(struct xfs_scrub_context *sc);
-int xchk_agf(struct xfs_scrub_context *sc);
-int xchk_agfl(struct xfs_scrub_context *sc);
-int xchk_agi(struct xfs_scrub_context *sc);
-int xchk_bnobt(struct xfs_scrub_context *sc);
-int xchk_cntbt(struct xfs_scrub_context *sc);
-int xchk_inobt(struct xfs_scrub_context *sc);
-int xchk_finobt(struct xfs_scrub_context *sc);
-int xchk_rmapbt(struct xfs_scrub_context *sc);
-int xchk_refcountbt(struct xfs_scrub_context *sc);
-int xchk_inode(struct xfs_scrub_context *sc);
-int xchk_bmap_data(struct xfs_scrub_context *sc);
-int xchk_bmap_attr(struct xfs_scrub_context *sc);
-int xchk_bmap_cow(struct xfs_scrub_context *sc);
-int xchk_directory(struct xfs_scrub_context *sc);
-int xchk_xattr(struct xfs_scrub_context *sc);
-int xchk_symlink(struct xfs_scrub_context *sc);
-int xchk_parent(struct xfs_scrub_context *sc);
+int xchk_tester(struct xfs_scrub *sc);
+int xchk_superblock(struct xfs_scrub *sc);
+int xchk_agf(struct xfs_scrub *sc);
+int xchk_agfl(struct xfs_scrub *sc);
+int xchk_agi(struct xfs_scrub *sc);
+int xchk_bnobt(struct xfs_scrub *sc);
+int xchk_cntbt(struct xfs_scrub *sc);
+int xchk_inobt(struct xfs_scrub *sc);
+int xchk_finobt(struct xfs_scrub *sc);
+int xchk_rmapbt(struct xfs_scrub *sc);
+int xchk_refcountbt(struct xfs_scrub *sc);
+int xchk_inode(struct xfs_scrub *sc);
+int xchk_bmap_data(struct xfs_scrub *sc);
+int xchk_bmap_attr(struct xfs_scrub *sc);
+int xchk_bmap_cow(struct xfs_scrub *sc);
+int xchk_directory(struct xfs_scrub *sc);
+int xchk_xattr(struct xfs_scrub *sc);
+int xchk_symlink(struct xfs_scrub *sc);
+int xchk_parent(struct xfs_scrub *sc);
 #ifdef CONFIG_XFS_RT
-int xchk_rtbitmap(struct xfs_scrub_context *sc);
-int xchk_rtsummary(struct xfs_scrub_context *sc);
+int xchk_rtbitmap(struct xfs_scrub *sc);
+int xchk_rtsummary(struct xfs_scrub *sc);
 #else
 static inline int
-xchk_rtbitmap(struct xfs_scrub_context *sc)
+xchk_rtbitmap(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 static inline int
-xchk_rtsummary(struct xfs_scrub_context *sc)
+xchk_rtsummary(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
 #ifdef CONFIG_XFS_QUOTA
-int xchk_quota(struct xfs_scrub_context *sc);
+int xchk_quota(struct xfs_scrub *sc);
 #else
 static inline int
-xchk_quota(struct xfs_scrub_context *sc)
+xchk_quota(struct xfs_scrub *sc)
 {
 	return -ENOENT;
 }
 #endif
 
 /* cross-referencing helpers */
-void xchk_xref_is_used_space(struct xfs_scrub_context *sc,
+void xchk_xref_is_used_space(struct xfs_scrub *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_not_inode_chunk(struct xfs_scrub_context *sc,
+void xchk_xref_is_not_inode_chunk(struct xfs_scrub *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_inode_chunk(struct xfs_scrub_context *sc,
+void xchk_xref_is_inode_chunk(struct xfs_scrub *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_owned_by(struct xfs_scrub_context *sc,
+void xchk_xref_is_owned_by(struct xfs_scrub *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len,
 		struct xfs_owner_info *oinfo);
-void xchk_xref_is_not_owned_by(struct xfs_scrub_context *sc,
+void xchk_xref_is_not_owned_by(struct xfs_scrub *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len,
 		struct xfs_owner_info *oinfo);
-void xchk_xref_has_no_owner(struct xfs_scrub_context *sc,
+void xchk_xref_has_no_owner(struct xfs_scrub *sc,
 		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_cow_staging(struct xfs_scrub_context *sc,
+void xchk_xref_is_cow_staging(struct xfs_scrub *sc,
 		xfs_agblock_t bno, xfs_extlen_t len);
-void xchk_xref_is_not_shared(struct xfs_scrub_context *sc,
+void xchk_xref_is_not_shared(struct xfs_scrub *sc,
 		xfs_agblock_t bno, xfs_extlen_t len);
 #ifdef CONFIG_XFS_RT
-void xchk_xref_is_used_rt_space(struct xfs_scrub_context *sc,
+void xchk_xref_is_used_rt_space(struct xfs_scrub *sc,
 		xfs_rtblock_t rtbno, xfs_extlen_t len);
 #else
 # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index e2a288e34337..56c6347e9482 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -26,7 +26,7 @@
 /* Set us up to scrub a symbolic link. */
 int
 xchk_setup_symlink(
-	struct xfs_scrub_context	*sc,
+	struct xfs_scrub	*sc,
 	struct xfs_inode		*ip)
 {
 	/* Allocate the buffer without the inode lock held. */
@@ -41,7 +41,7 @@ xchk_setup_symlink(
 
 int
 xchk_symlink(
-	struct xfs_scrub_context	*sc)
+	struct xfs_scrub	*sc)
 {
 	struct xfs_inode		*ip = sc->ip;
 	struct xfs_ifork		*ifp;
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 96f3edda3e91..93db22c39b51 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -59,7 +59,7 @@ DEFINE_SCRUB_EVENT(xrep_attempt);
 DEFINE_SCRUB_EVENT(xrep_done);
 
 TRACE_EVENT(xchk_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_agnumber_t agno,
+	TP_PROTO(struct xfs_scrub *sc, xfs_agnumber_t agno,
 		 xfs_agblock_t bno, int error, void *ret_ip),
 	TP_ARGS(sc, agno, bno, error, ret_ip),
 	TP_STRUCT__entry(
@@ -88,7 +88,7 @@ TRACE_EVENT(xchk_op_error,
 );
 
 TRACE_EVENT(xchk_file_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
+	TP_PROTO(struct xfs_scrub *sc, int whichfork,
 		 xfs_fileoff_t offset, int error, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, error, ret_ip),
 	TP_STRUCT__entry(
@@ -120,7 +120,7 @@ TRACE_EVENT(xchk_file_op_error,
 );
 
 DECLARE_EVENT_CLASS(xchk_block_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, void *ret_ip),
+	TP_PROTO(struct xfs_scrub *sc, xfs_daddr_t daddr, void *ret_ip),
 	TP_ARGS(sc, daddr, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -154,7 +154,7 @@ DECLARE_EVENT_CLASS(xchk_block_error_class,
 
 #define DEFINE_SCRUB_BLOCK_ERROR_EVENT(name) \
 DEFINE_EVENT(xchk_block_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_daddr_t daddr, \
+	TP_PROTO(struct xfs_scrub *sc, xfs_daddr_t daddr, \
 		 void *ret_ip), \
 	TP_ARGS(sc, daddr, ret_ip))
 
@@ -162,7 +162,7 @@ DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_error);
 DEFINE_SCRUB_BLOCK_ERROR_EVENT(xchk_block_preen);
 
 DECLARE_EVENT_CLASS(xchk_ino_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, void *ret_ip),
+	TP_PROTO(struct xfs_scrub *sc, xfs_ino_t ino, void *ret_ip),
 	TP_ARGS(sc, ino, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -185,7 +185,7 @@ DECLARE_EVENT_CLASS(xchk_ino_error_class,
 
 #define DEFINE_SCRUB_INO_ERROR_EVENT(name) \
 DEFINE_EVENT(xchk_ino_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, xfs_ino_t ino, \
+	TP_PROTO(struct xfs_scrub *sc, xfs_ino_t ino, \
 		 void *ret_ip), \
 	TP_ARGS(sc, ino, ret_ip))
 
@@ -194,7 +194,7 @@ DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_preen);
 DEFINE_SCRUB_INO_ERROR_EVENT(xchk_ino_warning);
 
 DECLARE_EVENT_CLASS(xchk_fblock_error_class,
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork,
+	TP_PROTO(struct xfs_scrub *sc, int whichfork,
 		 xfs_fileoff_t offset, void *ret_ip),
 	TP_ARGS(sc, whichfork, offset, ret_ip),
 	TP_STRUCT__entry(
@@ -224,7 +224,7 @@ DECLARE_EVENT_CLASS(xchk_fblock_error_class,
 
 #define DEFINE_SCRUB_FBLOCK_ERROR_EVENT(name) \
 DEFINE_EVENT(xchk_fblock_error_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, int whichfork, \
+	TP_PROTO(struct xfs_scrub *sc, int whichfork, \
 		 xfs_fileoff_t offset, void *ret_ip), \
 	TP_ARGS(sc, whichfork, offset, ret_ip))
 
@@ -232,7 +232,7 @@ DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_error);
 DEFINE_SCRUB_FBLOCK_ERROR_EVENT(xchk_fblock_warning);
 
 TRACE_EVENT(xchk_incomplete,
-	TP_PROTO(struct xfs_scrub_context *sc, void *ret_ip),
+	TP_PROTO(struct xfs_scrub *sc, void *ret_ip),
 	TP_ARGS(sc, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
@@ -251,7 +251,7 @@ TRACE_EVENT(xchk_incomplete,
 );
 
 TRACE_EVENT(xchk_btree_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
 	TP_STRUCT__entry(
@@ -291,7 +291,7 @@ TRACE_EVENT(xchk_btree_op_error,
 );
 
 TRACE_EVENT(xchk_ifork_btree_op_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, int error, void *ret_ip),
 	TP_ARGS(sc, cur, level, error, ret_ip),
 	TP_STRUCT__entry(
@@ -336,7 +336,7 @@ TRACE_EVENT(xchk_ifork_btree_op_error,
 );
 
 TRACE_EVENT(xchk_btree_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
 	TP_STRUCT__entry(
@@ -372,7 +372,7 @@ TRACE_EVENT(xchk_btree_error,
 );
 
 TRACE_EVENT(xchk_ifork_btree_error,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level, void *ret_ip),
 	TP_ARGS(sc, cur, level, ret_ip),
 	TP_STRUCT__entry(
@@ -414,7 +414,7 @@ TRACE_EVENT(xchk_ifork_btree_error,
 );
 
 DECLARE_EVENT_CLASS(xchk_sbtree_class,
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
 		 int level),
 	TP_ARGS(sc, cur, level),
 	TP_STRUCT__entry(
@@ -451,7 +451,7 @@ DECLARE_EVENT_CLASS(xchk_sbtree_class,
 )
 #define DEFINE_SCRUB_SBTREE_EVENT(name) \
 DEFINE_EVENT(xchk_sbtree_class, name, \
-	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur, \
+	TP_PROTO(struct xfs_scrub *sc, struct xfs_btree_cur *cur, \
 		 int level), \
 	TP_ARGS(sc, cur, level))
 
@@ -459,7 +459,7 @@ DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_rec);
 DEFINE_SCRUB_SBTREE_EVENT(xchk_btree_key);
 
 TRACE_EVENT(xchk_xref_error,
-	TP_PROTO(struct xfs_scrub_context *sc, int error, void *ret_ip),
+	TP_PROTO(struct xfs_scrub *sc, int error, void *ret_ip),
 	TP_ARGS(sc, error, ret_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-- 
cgit v1.2.3


From 032d91f9820f6d241dc5584c27a668cfd377aaf0 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:29:12 -0700
Subject: xfs: fix indentation and other whitespace problems in scrub/repair

Now that we've shortened everything, fix up all the indentation and
whitespace problems.  There are no functional changes.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/agheader.c        | 172 ++++++++++++++++++++---------------------
 fs/xfs/scrub/agheader_repair.c |   8 +-
 fs/xfs/scrub/alloc.c           |  48 ++++++------
 fs/xfs/scrub/attr.c            |  20 ++---
 fs/xfs/scrub/bmap.c            | 150 +++++++++++++++++------------------
 fs/xfs/scrub/btree.c           | 172 ++++++++++++++++++++---------------------
 fs/xfs/scrub/btree.h           |  25 +++---
 fs/xfs/scrub/common.c          | 158 ++++++++++++++++++-------------------
 fs/xfs/scrub/common.h          |  23 +++---
 fs/xfs/scrub/dabtree.c         |  56 +++++++-------
 fs/xfs/scrub/dabtree.h         |  21 +++--
 fs/xfs/scrub/dir.c             |  88 ++++++++++-----------
 fs/xfs/scrub/ialloc.c          |  58 +++++++-------
 fs/xfs/scrub/inode.c           | 102 ++++++++++++------------
 fs/xfs/scrub/parent.c          |  60 +++++++-------
 fs/xfs/scrub/quota.c           |  68 ++++++++--------
 fs/xfs/scrub/refcount.c        |  70 ++++++++---------
 fs/xfs/scrub/repair.c          | 148 +++++++++++++++++------------------
 fs/xfs/scrub/repair.h          |  28 +++----
 fs/xfs/scrub/rmap.c            |  78 +++++++++----------
 fs/xfs/scrub/rtbitmap.c        |  38 ++++-----
 fs/xfs/scrub/scrub.c           |   8 +-
 fs/xfs/scrub/scrub.h           |  62 +++++++--------
 fs/xfs/scrub/symlink.c         |  10 +--
 fs/xfs/scrub/trace.c           |   4 +-
 25 files changed, 832 insertions(+), 843 deletions(-)

diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 14ba4189ae8f..3068a9382feb 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -30,13 +30,13 @@
 STATIC void
 xchk_superblock_xref(
 	struct xfs_scrub	*sc,
-	struct xfs_buf			*bp)
+	struct xfs_buf		*bp)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agnumber_t			agno = sc->sm->sm_agno;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agnumber_t		agno = sc->sm->sm_agno;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -68,14 +68,14 @@ int
 xchk_superblock(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_buf			*bp;
-	struct xfs_dsb			*sb;
-	xfs_agnumber_t			agno;
-	uint32_t			v2_ok;
-	__be32				features_mask;
-	int				error;
-	__be16				vernum_mask;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	struct xfs_dsb		*sb;
+	xfs_agnumber_t		agno;
+	uint32_t		v2_ok;
+	__be32			features_mask;
+	int			error;
+	__be16			vernum_mask;
 
 	agno = sc->sm->sm_agno;
 	if (agno == 0)
@@ -367,9 +367,9 @@ static inline void
 xchk_agf_xref_freeblks(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_extlen_t			blocks = 0;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_extlen_t		blocks = 0;
+	int			error;
 
 	if (!sc->sa.bno_cur)
 		return;
@@ -387,11 +387,11 @@ static inline void
 xchk_agf_xref_cntbt(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_agblock_t			agbno;
-	xfs_extlen_t			blocks;
-	int				have;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_agblock_t		agbno;
+	xfs_extlen_t		blocks;
+	int			have;
+	int			error;
 
 	if (!sc->sa.cnt_cur)
 		return;
@@ -419,11 +419,11 @@ STATIC void
 xchk_agf_xref_btreeblks(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			blocks;
-	xfs_agblock_t			btreeblks;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		blocks;
+	xfs_agblock_t		btreeblks;
+	int			error;
 
 	/* Check agf_rmap_blocks; set up for agf_btreeblks check */
 	if (sc->sa.rmap_cur) {
@@ -465,9 +465,9 @@ static inline void
 xchk_agf_xref_refcblks(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_agf			*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
-	xfs_agblock_t			blocks;
-	int				error;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(sc->sa.agf_bp);
+	xfs_agblock_t		blocks;
+	int			error;
 
 	if (!sc->sa.refc_cur)
 		return;
@@ -484,10 +484,10 @@ STATIC void
 xchk_agf_xref(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -516,17 +516,17 @@ int
 xchk_agf(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_agf			*agf;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_agblock_t			eoag;
-	xfs_agblock_t			agfl_first;
-	xfs_agblock_t			agfl_last;
-	xfs_agblock_t			agfl_count;
-	xfs_agblock_t			fl_count;
-	int				level;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agf		*agf;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		eoag;
+	xfs_agblock_t		agfl_first;
+	xfs_agblock_t		agfl_last;
+	xfs_agblock_t		agfl_count;
+	xfs_agblock_t		fl_count;
+	int			level;
+	int			error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
 	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
@@ -598,10 +598,10 @@ out:
 /* AGFL */
 
 struct xchk_agfl_info {
-	struct xfs_owner_info		oinfo;
-	unsigned int			sz_entries;
-	unsigned int			nr_entries;
-	xfs_agblock_t			*entries;
+	struct xfs_owner_info	oinfo;
+	unsigned int		sz_entries;
+	unsigned int		nr_entries;
+	xfs_agblock_t		*entries;
 	struct xfs_scrub	*sc;
 };
 
@@ -609,8 +609,8 @@ struct xchk_agfl_info {
 STATIC void
 xchk_agfl_block_xref(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	struct xfs_owner_info		*oinfo)
+	xfs_agblock_t		agbno,
+	struct xfs_owner_info	*oinfo)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -624,13 +624,13 @@ xchk_agfl_block_xref(
 /* Scrub an AGFL block. */
 STATIC int
 xchk_agfl_block(
-	struct xfs_mount		*mp,
-	xfs_agblock_t			agbno,
-	void				*priv)
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
 {
-	struct xchk_agfl_info		*sai = priv;
+	struct xchk_agfl_info	*sai = priv;
 	struct xfs_scrub	*sc = sai->sc;
-	xfs_agnumber_t			agno = sc->sa.agno;
+	xfs_agnumber_t		agno = sc->sa.agno;
 
 	if (xfs_verify_agbno(mp, agno, agbno) &&
 	    sai->nr_entries < sai->sz_entries)
@@ -662,10 +662,10 @@ STATIC void
 xchk_agfl_xref(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -693,12 +693,12 @@ int
 xchk_agfl(
 	struct xfs_scrub	*sc)
 {
-	struct xchk_agfl_info		sai;
-	struct xfs_agf			*agf;
-	xfs_agnumber_t			agno;
-	unsigned int			agflcount;
-	unsigned int			i;
-	int				error;
+	struct xchk_agfl_info	sai;
+	struct xfs_agf		*agf;
+	xfs_agnumber_t		agno;
+	unsigned int		agflcount;
+	unsigned int		i;
+	int			error;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
 	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
@@ -770,10 +770,10 @@ static inline void
 xchk_agi_xref_icounts(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_agi			*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
-	xfs_agino_t			icount;
-	xfs_agino_t			freecount;
-	int				error;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(sc->sa.agi_bp);
+	xfs_agino_t		icount;
+	xfs_agino_t		freecount;
+	int			error;
 
 	if (!sc->sa.ino_cur)
 		return;
@@ -791,10 +791,10 @@ STATIC void
 xchk_agi_xref(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -820,18 +820,18 @@ int
 xchk_agi(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_agi			*agi;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_agblock_t			eoag;
-	xfs_agino_t			agino;
-	xfs_agino_t			first_agino;
-	xfs_agino_t			last_agino;
-	xfs_agino_t			icount;
-	int				i;
-	int				level;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agi		*agi;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_agblock_t		eoag;
+	xfs_agino_t		agino;
+	xfs_agino_t		first_agino;
+	xfs_agino_t		last_agino;
+	xfs_agino_t		icount;
+	int			i;
+	int			level;
+	int			error = 0;
 
 	agno = sc->sa.agno = sc->sm->sm_agno;
 	error = xchk_ag_read_headers(sc, agno, &sc->sa.agi_bp,
diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 2457968482f8..1e96621ece3a 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -31,10 +31,10 @@ int
 xrep_superblock(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_buf			*bp;
-	xfs_agnumber_t			agno;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*bp;
+	xfs_agnumber_t		agno;
+	int			error;
 
 	/* Don't try to repair AG 0's sb; let xfs_repair deal with it. */
 	agno = sc->sm->sm_agno;
diff --git a/fs/xfs/scrub/alloc.c b/fs/xfs/scrub/alloc.c
index 653d80b3aa39..036b5c7021eb 100644
--- a/fs/xfs/scrub/alloc.c
+++ b/fs/xfs/scrub/alloc.c
@@ -30,7 +30,7 @@
 int
 xchk_setup_ag_allocbt(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, false);
 }
@@ -43,14 +43,14 @@ xchk_setup_ag_allocbt(
 STATIC void
 xchk_allocbt_xref_other(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	struct xfs_btree_cur		**pcur;
-	xfs_agblock_t			fbno;
-	xfs_extlen_t			flen;
-	int				has_otherrec;
-	int				error;
+	struct xfs_btree_cur	**pcur;
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	int			has_otherrec;
+	int			error;
 
 	if (sc->sm->sm_type == XFS_SCRUB_TYPE_BNOBT)
 		pcur = &sc->sa.cnt_cur;
@@ -83,8 +83,8 @@ xchk_allocbt_xref_other(
 STATIC void
 xchk_allocbt_xref(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -98,14 +98,14 @@ xchk_allocbt_xref(
 /* Scrub a bnobt/cntbt record. */
 STATIC int
 xchk_allocbt_rec(
-	struct xchk_btree		*bs,
-	union xfs_btree_rec		*rec)
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	int				error = 0;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	int			error = 0;
 
 	bno = be32_to_cpu(rec->alloc.ar_startblock);
 	len = be32_to_cpu(rec->alloc.ar_blockcount);
@@ -124,10 +124,10 @@ xchk_allocbt_rec(
 STATIC int
 xchk_allocbt(
 	struct xfs_scrub	*sc,
-	xfs_btnum_t			which)
+	xfs_btnum_t		which)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_btree_cur		*cur;
+	struct xfs_owner_info	oinfo;
+	struct xfs_btree_cur	*cur;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
 	cur = which == XFS_BTNUM_BNO ? sc->sa.bno_cur : sc->sa.cnt_cur;
@@ -152,11 +152,11 @@ xchk_cntbt(
 void
 xchk_xref_is_used_space(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	bool				is_freesp;
-	int				error;
+	bool			is_freesp;
+	int			error;
 
 	if (!sc->sa.bno_cur || xchk_skip_xref(sc->sm))
 		return;
diff --git a/fs/xfs/scrub/attr.c b/fs/xfs/scrub/attr.c
index 6650fb3010b6..81d5e90547a1 100644
--- a/fs/xfs/scrub/attr.c
+++ b/fs/xfs/scrub/attr.c
@@ -34,9 +34,9 @@
 int
 xchk_setup_xattr(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
-	size_t				sz;
+	size_t			sz;
 
 	/*
 	 * Allocate the buffer without the inode lock held.  We need enough
@@ -57,7 +57,7 @@ xchk_setup_xattr(
 
 struct xchk_xattr {
 	struct xfs_attr_list_context	context;
-	struct xfs_scrub	*sc;
+	struct xfs_scrub		*sc;
 };
 
 /*
@@ -128,12 +128,12 @@ fail_xref:
 STATIC bool
 xchk_xattr_set_map(
 	struct xfs_scrub	*sc,
-	unsigned long			*map,
-	unsigned int			start,
-	unsigned int			len)
+	unsigned long		*map,
+	unsigned int		start,
+	unsigned int		len)
 {
-	unsigned int			mapsize = sc->mp->m_attr_geo->blksize;
-	bool				ret = true;
+	unsigned int		mapsize = sc->mp->m_attr_geo->blksize;
+	bool			ret = true;
 
 	if (start >= mapsize)
 		return false;
@@ -155,7 +155,7 @@ xchk_xattr_set_map(
  */
 STATIC bool
 xchk_xattr_check_freemap(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	unsigned long			*map,
 	struct xfs_attr3_icleaf_hdr	*leafhdr)
 {
@@ -405,7 +405,7 @@ out:
 /* Scrub the extended attribute metadata. */
 int
 xchk_xattr(
-	struct xfs_scrub	*sc)
+	struct xfs_scrub		*sc)
 {
 	struct xchk_xattr		sx;
 	struct attrlist_cursor_kern	cursor = { 0 };
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 0e5166232b15..e1d11f3223e3 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -35,9 +35,9 @@
 int
 xchk_setup_inode_bmap(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
 	error = xchk_get_inode(sc, ip);
 	if (error)
@@ -80,25 +80,25 @@ out:
 
 struct xchk_bmap_info {
 	struct xfs_scrub	*sc;
-	xfs_fileoff_t			lastoff;
-	bool				is_rt;
-	bool				is_shared;
-	int				whichfork;
+	xfs_fileoff_t		lastoff;
+	bool			is_rt;
+	bool			is_shared;
+	int			whichfork;
 };
 
 /* Look for a corresponding rmap for this irec. */
 static inline bool
 xchk_bmap_get_rmap(
-	struct xchk_bmap_info		*info,
-	struct xfs_bmbt_irec		*irec,
-	xfs_agblock_t			agbno,
-	uint64_t			owner,
-	struct xfs_rmap_irec		*rmap)
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec,
+	xfs_agblock_t		agbno,
+	uint64_t		owner,
+	struct xfs_rmap_irec	*rmap)
 {
-	xfs_fileoff_t			offset;
-	unsigned int			rflags = 0;
-	int				has_rmap;
-	int				error;
+	xfs_fileoff_t		offset;
+	unsigned int		rflags = 0;
+	int			has_rmap;
+	int			error;
 
 	if (info->whichfork == XFS_ATTR_FORK)
 		rflags |= XFS_RMAP_ATTR_FORK;
@@ -152,13 +152,13 @@ out:
 /* Make sure that we have rmapbt records for this extent. */
 STATIC void
 xchk_bmap_xref_rmap(
-	struct xchk_bmap_info		*info,
-	struct xfs_bmbt_irec		*irec,
-	xfs_agblock_t			agbno)
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec,
+	xfs_agblock_t		agbno)
 {
-	struct xfs_rmap_irec		rmap;
-	unsigned long long		rmap_end;
-	uint64_t			owner;
+	struct xfs_rmap_irec	rmap;
+	unsigned long long	rmap_end;
+	uint64_t		owner;
 
 	if (!info->sc->sa.rmap_cur || xchk_skip_xref(info->sc->sm))
 		return;
@@ -222,10 +222,10 @@ xchk_bmap_xref_rmap(
 /* Cross-reference a single rtdev extent record. */
 STATIC void
 xchk_bmap_rt_extent_xref(
-	struct xchk_bmap_info		*info,
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_bmbt_irec		*irec)
+	struct xchk_bmap_info	*info,
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*irec)
 {
 	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -237,16 +237,16 @@ xchk_bmap_rt_extent_xref(
 /* Cross-reference a single datadev extent record. */
 STATIC void
 xchk_bmap_extent_xref(
-	struct xchk_bmap_info		*info,
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xfs_bmbt_irec		*irec)
+	struct xchk_bmap_info	*info,
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount		*mp = info->sc->mp;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_extlen_t			len;
-	int				error;
+	struct xfs_mount	*mp = info->sc->mp;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_extlen_t		len;
+	int			error;
 
 	if (info->sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -284,15 +284,15 @@ xchk_bmap_extent_xref(
 /* Scrub a single extent record. */
 STATIC int
 xchk_bmap_extent(
-	struct xfs_inode		*ip,
-	struct xfs_btree_cur		*cur,
-	struct xchk_bmap_info		*info,
-	struct xfs_bmbt_irec		*irec)
+	struct xfs_inode	*ip,
+	struct xfs_btree_cur	*cur,
+	struct xchk_bmap_info	*info,
+	struct xfs_bmbt_irec	*irec)
 {
-	struct xfs_mount		*mp = info->sc->mp;
-	struct xfs_buf			*bp = NULL;
-	xfs_filblks_t			end;
-	int				error = 0;
+	struct xfs_mount	*mp = info->sc->mp;
+	struct xfs_buf		*bp = NULL;
+	xfs_filblks_t		end;
+	int			error = 0;
 
 	if (cur)
 		xfs_btree_get_block(cur, 0, &bp);
@@ -357,16 +357,16 @@ xchk_bmap_extent(
 /* Scrub a bmbt record. */
 STATIC int
 xchk_bmapbt_rec(
-	struct xchk_btree		*bs,
-	union xfs_btree_rec		*rec)
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xchk_bmap_info		*info = bs->private;
-	struct xfs_inode		*ip = bs->cur->bc_private.b.ip;
-	struct xfs_buf			*bp = NULL;
-	struct xfs_btree_block		*block;
-	uint64_t			owner;
-	int				i;
+	struct xfs_bmbt_irec	irec;
+	struct xchk_bmap_info	*info = bs->private;
+	struct xfs_inode	*ip = bs->cur->bc_private.b.ip;
+	struct xfs_buf		*bp = NULL;
+	struct xfs_btree_block	*block;
+	uint64_t		owner;
+	int			i;
 
 	/*
 	 * Check the owners of the btree blocks up to the level below
@@ -392,14 +392,14 @@ xchk_bmapbt_rec(
 STATIC int
 xchk_bmap_btree(
 	struct xfs_scrub	*sc,
-	int				whichfork,
-	struct xchk_bmap_info		*info)
+	int			whichfork,
+	struct xchk_bmap_info	*info)
 {
-	struct xfs_owner_info		oinfo;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_btree_cur		*cur;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_btree_cur	*cur;
+	int			error;
 
 	cur = xfs_bmbt_init_cursor(mp, sc->tp, ip, whichfork);
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
@@ -410,8 +410,8 @@ xchk_bmap_btree(
 
 struct xchk_bmap_check_rmap_info {
 	struct xfs_scrub	*sc;
-	int				whichfork;
-	struct xfs_iext_cursor		icur;
+	int			whichfork;
+	struct xfs_iext_cursor	icur;
 };
 
 /* Can we find bmaps that fit this rmap? */
@@ -424,7 +424,7 @@ xchk_bmap_check_rmap(
 	struct xfs_bmbt_irec		irec;
 	struct xchk_bmap_check_rmap_info	*sbcri = priv;
 	struct xfs_ifork		*ifp;
-	struct xfs_scrub	*sc = sbcri->sc;
+	struct xfs_scrub		*sc = sbcri->sc;
 	bool				have_map;
 
 	/* Is this even the right fork? */
@@ -488,7 +488,7 @@ out:
 /* Make sure each rmap has a corresponding bmbt entry. */
 STATIC int
 xchk_bmap_check_ag_rmaps(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	int				whichfork,
 	xfs_agnumber_t			agno)
 {
@@ -523,11 +523,11 @@ out_agf:
 STATIC int
 xchk_bmap_check_rmaps(
 	struct xfs_scrub	*sc,
-	int				whichfork)
+	int			whichfork)
 {
-	loff_t				size;
-	xfs_agnumber_t			agno;
-	int				error;
+	loff_t			size;
+	xfs_agnumber_t		agno;
+	int			error;
 
 	if (!xfs_sb_version_hasrmapbt(&sc->mp->m_sb) ||
 	    whichfork == XFS_COW_FORK ||
@@ -580,16 +580,16 @@ xchk_bmap_check_rmaps(
 STATIC int
 xchk_bmap(
 	struct xfs_scrub	*sc,
-	int				whichfork)
+	int			whichfork)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xchk_bmap_info		info = { NULL };
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_ifork		*ifp;
-	xfs_fileoff_t			endoff;
-	struct xfs_iext_cursor		icur;
-	int				error = 0;
+	struct xfs_bmbt_irec	irec;
+	struct xchk_bmap_info	info = { NULL };
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		endoff;
+	struct xfs_iext_cursor	icur;
+	int			error = 0;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
index c4e1dce8c5b3..4ae959f7ad2c 100644
--- a/fs/xfs/scrub/btree.c
+++ b/fs/xfs/scrub/btree.c
@@ -31,11 +31,11 @@
 static bool
 __xchk_btree_process_error(
 	struct xfs_scrub	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	if (*error == 0)
 		return true;
@@ -66,9 +66,9 @@ __xchk_btree_process_error(
 bool
 xchk_btree_process_error(
 	struct xfs_scrub	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error)
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error)
 {
 	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
@@ -77,9 +77,9 @@ xchk_btree_process_error(
 bool
 xchk_btree_xref_process_error(
 	struct xfs_scrub	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	int				*error)
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			*error)
 {
 	return __xchk_btree_process_error(sc, cur, level, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
@@ -89,10 +89,10 @@ xchk_btree_xref_process_error(
 static void
 __xchk_btree_set_corrupt(
 	struct xfs_scrub	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level,
-	__u32				errflag,
-	void				*ret_ip)
+	struct xfs_btree_cur	*cur,
+	int			level,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	sc->sm->sm_flags |= errflag;
 
@@ -107,8 +107,8 @@ __xchk_btree_set_corrupt(
 void
 xchk_btree_set_corrupt(
 	struct xfs_scrub	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level)
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
 	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_CORRUPT,
 			__return_address);
@@ -117,8 +117,8 @@ xchk_btree_set_corrupt(
 void
 xchk_btree_xref_set_corrupt(
 	struct xfs_scrub	*sc,
-	struct xfs_btree_cur		*cur,
-	int				level)
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
 	__xchk_btree_set_corrupt(sc, cur, level, XFS_SCRUB_OFLAG_XCORRUPT,
 			__return_address);
@@ -225,11 +225,11 @@ xchk_btree_key(
  */
 static bool
 xchk_btree_ptr_ok(
-	struct xchk_btree		*bs,
-	int				level,
-	union xfs_btree_ptr		*ptr)
+	struct xchk_btree	*bs,
+	int			level,
+	union xfs_btree_ptr	*ptr)
 {
-	bool				res;
+	bool			res;
 
 	/* A btree rooted in an inode has no block pointer to the root. */
 	if ((bs->cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) &&
@@ -250,18 +250,18 @@ xchk_btree_ptr_ok(
 /* Check that a btree block's sibling matches what we expect it. */
 STATIC int
 xchk_btree_block_check_sibling(
-	struct xchk_btree		*bs,
-	int				level,
-	int				direction,
-	union xfs_btree_ptr		*sibling)
+	struct xchk_btree	*bs,
+	int			level,
+	int			direction,
+	union xfs_btree_ptr	*sibling)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	struct xfs_btree_block		*pblock;
-	struct xfs_buf			*pbp;
-	struct xfs_btree_cur		*ncur = NULL;
-	union xfs_btree_ptr		*pp;
-	int				success;
-	int				error;
+	struct xfs_btree_cur	*cur = bs->cur;
+	struct xfs_btree_block	*pblock;
+	struct xfs_buf		*pbp;
+	struct xfs_btree_cur	*ncur = NULL;
+	union xfs_btree_ptr	*pp;
+	int			success;
+	int			error;
 
 	error = xfs_btree_dup_cursor(cur, &ncur);
 	if (!xchk_btree_process_error(bs->sc, cur, level + 1, &error) ||
@@ -313,14 +313,14 @@ out:
 /* Check the siblings of a btree block. */
 STATIC int
 xchk_btree_block_check_siblings(
-	struct xchk_btree		*bs,
-	struct xfs_btree_block		*block)
+	struct xchk_btree	*bs,
+	struct xfs_btree_block	*block)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	union xfs_btree_ptr		leftsib;
-	union xfs_btree_ptr		rightsib;
-	int				level;
-	int				error = 0;
+	struct xfs_btree_cur	*cur = bs->cur;
+	union xfs_btree_ptr	leftsib;
+	union xfs_btree_ptr	rightsib;
+	int			level;
+	int			error = 0;
 
 	xfs_btree_get_sibling(cur, block, &leftsib, XFS_BB_LEFTSIB);
 	xfs_btree_get_sibling(cur, block, &rightsib, XFS_BB_RIGHTSIB);
@@ -361,15 +361,15 @@ struct check_owner {
  */
 STATIC int
 xchk_btree_check_block_owner(
-	struct xchk_btree		*bs,
-	int				level,
-	xfs_daddr_t			daddr)
+	struct xchk_btree	*bs,
+	int			level,
+	xfs_daddr_t		daddr)
 {
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	xfs_btnum_t			btnum;
-	bool				init_sa;
-	int				error = 0;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_btnum_t		btnum;
+	bool			init_sa;
+	int			error = 0;
 
 	if (!bs->cur)
 		return 0;
@@ -408,12 +408,12 @@ xchk_btree_check_block_owner(
 /* Check the owner of a btree block. */
 STATIC int
 xchk_btree_check_owner(
-	struct xchk_btree		*bs,
-	int				level,
-	struct xfs_buf			*bp)
+	struct xchk_btree	*bs,
+	int			level,
+	struct xfs_buf		*bp)
 {
-	struct xfs_btree_cur		*cur = bs->cur;
-	struct check_owner		*co;
+	struct xfs_btree_cur	*cur = bs->cur;
+	struct check_owner	*co;
 
 	if ((cur->bc_flags & XFS_BTREE_ROOT_IN_INODE) && bp == NULL)
 		return 0;
@@ -484,14 +484,14 @@ xchk_btree_check_minrecs(
  */
 STATIC int
 xchk_btree_get_block(
-	struct xchk_btree		*bs,
-	int				level,
-	union xfs_btree_ptr		*pp,
-	struct xfs_btree_block		**pblock,
-	struct xfs_buf			**pbp)
+	struct xchk_btree	*bs,
+	int			level,
+	union xfs_btree_ptr	*pp,
+	struct xfs_btree_block	**pblock,
+	struct xfs_buf		**pbp)
 {
-	void				*failed_at;
-	int				error;
+	xfs_failaddr_t		failed_at;
+	int			error;
 
 	*pblock = NULL;
 	*pbp = NULL;
@@ -538,17 +538,17 @@ xchk_btree_get_block(
  */
 STATIC void
 xchk_btree_block_keys(
-	struct xchk_btree		*bs,
-	int				level,
-	struct xfs_btree_block		*block)
+	struct xchk_btree	*bs,
+	int			level,
+	struct xfs_btree_block	*block)
 {
-	union xfs_btree_key		block_keys;
-	struct xfs_btree_cur		*cur = bs->cur;
-	union xfs_btree_key		*high_bk;
-	union xfs_btree_key		*parent_keys;
-	union xfs_btree_key		*high_pk;
-	struct xfs_btree_block		*parent_block;
-	struct xfs_buf			*bp;
+	union xfs_btree_key	block_keys;
+	struct xfs_btree_cur	*cur = bs->cur;
+	union xfs_btree_key	*high_bk;
+	union xfs_btree_key	*parent_keys;
+	union xfs_btree_key	*high_pk;
+	struct xfs_btree_block	*parent_block;
+	struct xfs_buf		*bp;
 
 	if (level >= cur->bc_nlevels - 1)
 		return;
@@ -584,22 +584,22 @@ xchk_btree_block_keys(
 int
 xchk_btree(
 	struct xfs_scrub	*sc,
-	struct xfs_btree_cur		*cur,
-	xchk_btree_rec_fn		scrub_fn,
-	struct xfs_owner_info		*oinfo,
-	void				*private)
+	struct xfs_btree_cur	*cur,
+	xchk_btree_rec_fn	scrub_fn,
+	struct xfs_owner_info	*oinfo,
+	void			*private)
 {
-	struct xchk_btree		bs = { NULL };
-	union xfs_btree_ptr		ptr;
-	union xfs_btree_ptr		*pp;
-	union xfs_btree_rec		*recp;
-	struct xfs_btree_block		*block;
-	int				level;
-	struct xfs_buf			*bp;
-	struct check_owner		*co;
-	struct check_owner		*n;
-	int				i;
-	int				error = 0;
+	struct xchk_btree	bs = { NULL };
+	union xfs_btree_ptr	ptr;
+	union xfs_btree_ptr	*pp;
+	union xfs_btree_rec	*recp;
+	struct xfs_btree_block	*block;
+	int			level;
+	struct xfs_buf		*bp;
+	struct check_owner	*co;
+	struct check_owner	*n;
+	int			i;
+	int			error = 0;
 
 	/* Initialize scrub state */
 	bs.cur = cur;
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
index a0b74b515b9b..aada763cd006 100644
--- a/fs/xfs/scrub/btree.h
+++ b/fs/xfs/scrub/btree.h
@@ -14,8 +14,7 @@ bool xchk_btree_process_error(struct xfs_scrub *sc,
 
 /* Check for btree xref operation errors. */
 bool xchk_btree_xref_process_error(struct xfs_scrub *sc,
-				struct xfs_btree_cur *cur, int level,
-				int *error);
+		struct xfs_btree_cur *cur, int level, int *error);
 
 /* Check for btree corruption. */
 void xchk_btree_set_corrupt(struct xfs_scrub *sc,
@@ -33,20 +32,20 @@ typedef int (*xchk_btree_rec_fn)(
 struct xchk_btree {
 	/* caller-provided scrub state */
 	struct xfs_scrub	*sc;
-	struct xfs_btree_cur		*cur;
-	xchk_btree_rec_fn		scrub_rec;
-	struct xfs_owner_info		*oinfo;
-	void				*private;
+	struct xfs_btree_cur	*cur;
+	xchk_btree_rec_fn	scrub_rec;
+	struct xfs_owner_info	*oinfo;
+	void			*private;
 
 	/* internal scrub state */
-	union xfs_btree_rec		lastrec;
-	bool				firstrec;
-	union xfs_btree_key		lastkey[XFS_BTREE_MAXLEVELS];
-	bool				firstkey[XFS_BTREE_MAXLEVELS];
-	struct list_head		to_check;
+	union xfs_btree_rec	lastrec;
+	bool			firstrec;
+	union xfs_btree_key	lastkey[XFS_BTREE_MAXLEVELS];
+	bool			firstkey[XFS_BTREE_MAXLEVELS];
+	struct list_head	to_check;
 };
 int xchk_btree(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
-		    xchk_btree_rec_fn scrub_fn,
-		    struct xfs_owner_info *oinfo, void *private);
+		xchk_btree_rec_fn scrub_fn, struct xfs_owner_info *oinfo,
+		void *private);
 
 #endif /* __XFS_SCRUB_BTREE_H__ */
diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index ed9195116556..baac08304a5a 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -70,11 +70,11 @@
 static bool
 __xchk_process_error(
 	struct xfs_scrub	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	switch (*error) {
 	case 0:
@@ -100,9 +100,9 @@ __xchk_process_error(
 bool
 xchk_process_error(
 	struct xfs_scrub	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error)
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error)
 {
 	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
@@ -111,9 +111,9 @@ xchk_process_error(
 bool
 xchk_xref_process_error(
 	struct xfs_scrub	*sc,
-	xfs_agnumber_t			agno,
-	xfs_agblock_t			bno,
-	int				*error)
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		bno,
+	int			*error)
 {
 	return __xchk_process_error(sc, agno, bno, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
@@ -123,11 +123,11 @@ xchk_xref_process_error(
 static bool
 __xchk_fblock_process_error(
 	struct xfs_scrub	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error,
-	__u32				errflag,
-	void				*ret_ip)
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error,
+	__u32			errflag,
+	void			*ret_ip)
 {
 	switch (*error) {
 	case 0:
@@ -153,9 +153,9 @@ __xchk_fblock_process_error(
 bool
 xchk_fblock_process_error(
 	struct xfs_scrub	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error)
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error)
 {
 	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_CORRUPT, __return_address);
@@ -164,9 +164,9 @@ xchk_fblock_process_error(
 bool
 xchk_fblock_xref_process_error(
 	struct xfs_scrub	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset,
-	int				*error)
+	int			whichfork,
+	xfs_fileoff_t		offset,
+	int			*error)
 {
 	return __xchk_fblock_process_error(sc, whichfork, offset, error,
 			XFS_SCRUB_OFLAG_XFAIL, __return_address);
@@ -188,7 +188,7 @@ xchk_fblock_xref_process_error(
 void
 xchk_block_set_preen(
 	struct xfs_scrub	*sc,
-	struct xfs_buf			*bp)
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
 	trace_xchk_block_preen(sc, bp->b_bn, __return_address);
@@ -202,7 +202,7 @@ xchk_block_set_preen(
 void
 xchk_ino_set_preen(
 	struct xfs_scrub	*sc,
-	xfs_ino_t			ino)
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_PREEN;
 	trace_xchk_ino_preen(sc, ino, __return_address);
@@ -212,7 +212,7 @@ xchk_ino_set_preen(
 void
 xchk_block_set_corrupt(
 	struct xfs_scrub	*sc,
-	struct xfs_buf			*bp)
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 	trace_xchk_block_error(sc, bp->b_bn, __return_address);
@@ -222,7 +222,7 @@ xchk_block_set_corrupt(
 void
 xchk_block_xref_set_corrupt(
 	struct xfs_scrub	*sc,
-	struct xfs_buf			*bp)
+	struct xfs_buf		*bp)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
 	trace_xchk_block_error(sc, bp->b_bn, __return_address);
@@ -236,7 +236,7 @@ xchk_block_xref_set_corrupt(
 void
 xchk_ino_set_corrupt(
 	struct xfs_scrub	*sc,
-	xfs_ino_t			ino)
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 	trace_xchk_ino_error(sc, ino, __return_address);
@@ -246,7 +246,7 @@ xchk_ino_set_corrupt(
 void
 xchk_ino_xref_set_corrupt(
 	struct xfs_scrub	*sc,
-	xfs_ino_t			ino)
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
 	trace_xchk_ino_error(sc, ino, __return_address);
@@ -256,8 +256,8 @@ xchk_ino_xref_set_corrupt(
 void
 xchk_fblock_set_corrupt(
 	struct xfs_scrub	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
 	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
@@ -267,8 +267,8 @@ xchk_fblock_set_corrupt(
 void
 xchk_fblock_xref_set_corrupt(
 	struct xfs_scrub	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_XCORRUPT;
 	trace_xchk_fblock_error(sc, whichfork, offset, __return_address);
@@ -281,7 +281,7 @@ xchk_fblock_xref_set_corrupt(
 void
 xchk_ino_set_warning(
 	struct xfs_scrub	*sc,
-	xfs_ino_t			ino)
+	xfs_ino_t		ino)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
 	trace_xchk_ino_warning(sc, ino, __return_address);
@@ -291,8 +291,8 @@ xchk_ino_set_warning(
 void
 xchk_fblock_set_warning(
 	struct xfs_scrub	*sc,
-	int				whichfork,
-	xfs_fileoff_t			offset)
+	int			whichfork,
+	xfs_fileoff_t		offset)
 {
 	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_WARNING;
 	trace_xchk_fblock_warning(sc, whichfork, offset, __return_address);
@@ -319,13 +319,13 @@ struct xchk_rmap_ownedby_info {
 
 STATIC int
 xchk_count_rmap_ownedby_irec(
-	struct xfs_btree_cur			*cur,
-	struct xfs_rmap_irec			*rec,
-	void					*priv)
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
 {
-	struct xchk_rmap_ownedby_info		*sroi = priv;
-	bool					irec_attr;
-	bool					oinfo_attr;
+	struct xchk_rmap_ownedby_info	*sroi = priv;
+	bool				irec_attr;
+	bool				oinfo_attr;
 
 	irec_attr = rec->rm_flags & XFS_RMAP_ATTR_FORK;
 	oinfo_attr = sroi->oinfo->oi_flags & XFS_OWNER_INFO_ATTR_FORK;
@@ -346,11 +346,11 @@ xchk_count_rmap_ownedby_irec(
 int
 xchk_count_rmap_ownedby_ag(
 	struct xfs_scrub		*sc,
-	struct xfs_btree_cur			*cur,
-	struct xfs_owner_info			*oinfo,
-	xfs_filblks_t				*blocks)
+	struct xfs_btree_cur		*cur,
+	struct xfs_owner_info		*oinfo,
+	xfs_filblks_t			*blocks)
 {
-	struct xchk_rmap_ownedby_info		sroi;
+	struct xchk_rmap_ownedby_info	sroi;
 
 	sroi.oinfo = oinfo;
 	*blocks = 0;
@@ -372,7 +372,7 @@ xchk_count_rmap_ownedby_ag(
 static inline bool
 want_ag_read_header_failure(
 	struct xfs_scrub	*sc,
-	unsigned int			type)
+	unsigned int		type)
 {
 	/* Return all AG header read failures when scanning btrees. */
 	if (sc->sm->sm_type != XFS_SCRUB_TYPE_AGF &&
@@ -399,13 +399,13 @@ want_ag_read_header_failure(
 int
 xchk_ag_read_headers(
 	struct xfs_scrub	*sc,
-	xfs_agnumber_t			agno,
-	struct xfs_buf			**agi,
-	struct xfs_buf			**agf,
-	struct xfs_buf			**agfl)
+	xfs_agnumber_t		agno,
+	struct xfs_buf		**agi,
+	struct xfs_buf		**agf,
+	struct xfs_buf		**agfl)
 {
-	struct xfs_mount		*mp = sc->mp;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
 
 	error = xfs_ialloc_read_agi(mp, sc->tp, agno, agi);
 	if (error && want_ag_read_header_failure(sc, XFS_SCRUB_TYPE_AGI))
@@ -455,8 +455,8 @@ xchk_ag_btcur_init(
 	struct xfs_scrub	*sc,
 	struct xchk_ag		*sa)
 {
-	struct xfs_mount		*mp = sc->mp;
-	xfs_agnumber_t			agno = sa->agno;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agnumber_t		agno = sa->agno;
 
 	if (sa->agf_bp) {
 		/* Set up a bnobt cursor for cross-referencing. */
@@ -545,10 +545,10 @@ xchk_ag_free(
 int
 xchk_ag_init(
 	struct xfs_scrub	*sc,
-	xfs_agnumber_t			agno,
+	xfs_agnumber_t		agno,
 	struct xchk_ag		*sa)
 {
-	int				error;
+	int			error;
 
 	sa->agno = agno;
 	error = xchk_ag_read_headers(sc, agno, &sa->agi_bp,
@@ -566,7 +566,7 @@ xchk_ag_init(
 void
 xchk_perag_get(
 	struct xfs_mount	*mp,
-	struct xchk_ag	*sa)
+	struct xchk_ag		*sa)
 {
 	if (!sa->pag)
 		sa->pag = xfs_perag_get(mp, sa->agno);
@@ -587,7 +587,7 @@ xchk_perag_get(
 int
 xchk_trans_alloc(
 	struct xfs_scrub	*sc,
-	uint				resblks)
+	uint			resblks)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
 		return xfs_trans_alloc(sc->mp, &M_RES(sc->mp)->tr_itruncate,
@@ -600,9 +600,9 @@ xchk_trans_alloc(
 int
 xchk_setup_fs(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
-	uint				resblks;
+	uint			resblks;
 
 	resblks = xrep_calc_ag_resblks(sc);
 	return xchk_trans_alloc(sc, resblks);
@@ -612,11 +612,11 @@ xchk_setup_fs(
 int
 xchk_setup_ag_btree(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip,
-	bool				force_log)
+	struct xfs_inode	*ip,
+	bool			force_log)
 {
-	struct xfs_mount		*mp = sc->mp;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	int			error;
 
 	/*
 	 * If the caller asks us to checkpont the log, do so.  This
@@ -659,12 +659,12 @@ xchk_checkpoint_log(
 int
 xchk_get_inode(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip_in)
+	struct xfs_inode	*ip_in)
 {
-	struct xfs_imap			imap;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*ip = NULL;
-	int				error;
+	struct xfs_imap		imap;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*ip = NULL;
+	int			error;
 
 	/* We want to scan the inode we already had opened. */
 	if (sc->sm->sm_ino == 0 || sc->sm->sm_ino == ip_in->i_ino) {
@@ -723,10 +723,10 @@ xchk_get_inode(
 int
 xchk_setup_inode_contents(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip,
-	unsigned int			resblks)
+	struct xfs_inode	*ip,
+	unsigned int		resblks)
 {
-	int				error;
+	int			error;
 
 	error = xchk_get_inode(sc, ip);
 	if (error)
@@ -754,8 +754,8 @@ out:
 bool
 xchk_should_check_xref(
 	struct xfs_scrub	*sc,
-	int				*error,
-	struct xfs_btree_cur		**curpp)
+	int			*error,
+	struct xfs_btree_cur	**curpp)
 {
 	/* No point in xref if we already know we're corrupt. */
 	if (xchk_skip_xref(sc->sm))
@@ -789,9 +789,9 @@ xchk_should_check_xref(
 void
 xchk_buffer_recheck(
 	struct xfs_scrub	*sc,
-	struct xfs_buf			*bp)
+	struct xfs_buf		*bp)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	if (bp->b_ops == NULL) {
 		xchk_block_set_corrupt(sc, bp);
@@ -816,9 +816,9 @@ int
 xchk_metadata_inode_forks(
 	struct xfs_scrub	*sc)
 {
-	__u32				smtype;
-	bool				shared;
-	int				error;
+	__u32			smtype;
+	bool			shared;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return 0;
diff --git a/fs/xfs/scrub/common.h b/fs/xfs/scrub/common.h
index c321230d32dc..2d4324d12f9a 100644
--- a/fs/xfs/scrub/common.h
+++ b/fs/xfs/scrub/common.h
@@ -108,24 +108,21 @@ xchk_setup_quota(struct xfs_scrub *sc, struct xfs_inode *ip)
 
 void xchk_ag_free(struct xfs_scrub *sc, struct xchk_ag *sa);
 int xchk_ag_init(struct xfs_scrub *sc, xfs_agnumber_t agno,
-		      struct xchk_ag *sa);
+		struct xchk_ag *sa);
 void xchk_perag_get(struct xfs_mount *mp, struct xchk_ag *sa);
 int xchk_ag_read_headers(struct xfs_scrub *sc, xfs_agnumber_t agno,
-			      struct xfs_buf **agi, struct xfs_buf **agf,
-			      struct xfs_buf **agfl);
+		struct xfs_buf **agi, struct xfs_buf **agf,
+		struct xfs_buf **agfl);
 void xchk_ag_btcur_free(struct xchk_ag *sa);
-int xchk_ag_btcur_init(struct xfs_scrub *sc,
-			    struct xchk_ag *sa);
-int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc,
-				    struct xfs_btree_cur *cur,
-				    struct xfs_owner_info *oinfo,
-				    xfs_filblks_t *blocks);
+int xchk_ag_btcur_init(struct xfs_scrub *sc, struct xchk_ag *sa);
+int xchk_count_rmap_ownedby_ag(struct xfs_scrub *sc, struct xfs_btree_cur *cur,
+		struct xfs_owner_info *oinfo, xfs_filblks_t *blocks);
 
-int xchk_setup_ag_btree(struct xfs_scrub *sc,
-			     struct xfs_inode *ip, bool force_log);
+int xchk_setup_ag_btree(struct xfs_scrub *sc, struct xfs_inode *ip,
+		bool force_log);
 int xchk_get_inode(struct xfs_scrub *sc, struct xfs_inode *ip_in);
-int xchk_setup_inode_contents(struct xfs_scrub *sc,
-				   struct xfs_inode *ip, unsigned int resblks);
+int xchk_setup_inode_contents(struct xfs_scrub *sc, struct xfs_inode *ip,
+		unsigned int resblks);
 void xchk_buffer_recheck(struct xfs_scrub *sc, struct xfs_buf *bp);
 
 /*
diff --git a/fs/xfs/scrub/dabtree.c b/fs/xfs/scrub/dabtree.c
index 7fc12d540ea6..f1260b4bfdee 100644
--- a/fs/xfs/scrub/dabtree.c
+++ b/fs/xfs/scrub/dabtree.c
@@ -36,9 +36,9 @@
  */
 bool
 xchk_da_process_error(
-	struct xchk_da_btree		*ds,
-	int				level,
-	int				*error)
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			*error)
 {
 	struct xfs_scrub	*sc = ds->sc;
 
@@ -72,8 +72,8 @@ xchk_da_process_error(
  */
 void
 xchk_da_set_corrupt(
-	struct xchk_da_btree		*ds,
-	int				level)
+	struct xchk_da_btree	*ds,
+	int			level)
 {
 	struct xfs_scrub	*sc = ds->sc;
 
@@ -88,13 +88,13 @@ xchk_da_set_corrupt(
 /* Find an entry at a certain level in a da btree. */
 STATIC void *
 xchk_da_btree_entry(
-	struct xchk_da_btree		*ds,
-	int				level,
-	int				rec)
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			rec)
 {
-	char				*ents;
-	struct xfs_da_state_blk		*blk;
-	void				*baddr;
+	char			*ents;
+	struct xfs_da_state_blk	*blk;
+	void			*baddr;
 
 	/* Dispatch the entry finding function. */
 	blk = &ds->state->path.blk[level];
@@ -158,9 +158,9 @@ xchk_da_btree_hash(
  */
 STATIC bool
 xchk_da_btree_ptr_ok(
-	struct xchk_da_btree		*ds,
-	int				level,
-	xfs_dablk_t			blkno)
+	struct xchk_da_btree	*ds,
+	int			level,
+	xfs_dablk_t		blkno)
 {
 	if (blkno < ds->lowest || (ds->highest != 0 && blkno >= ds->highest)) {
 		xchk_da_set_corrupt(ds, level);
@@ -246,13 +246,13 @@ static const struct xfs_buf_ops xchk_da_btree_buf_ops = {
 /* Check a block's sibling. */
 STATIC int
 xchk_da_btree_block_check_sibling(
-	struct xchk_da_btree		*ds,
-	int				level,
-	int				direction,
-	xfs_dablk_t			sibling)
+	struct xchk_da_btree	*ds,
+	int			level,
+	int			direction,
+	xfs_dablk_t		sibling)
 {
-	int				retval;
-	int				error;
+	int			retval;
+	int			error;
 
 	memcpy(&ds->state->altpath, &ds->state->path,
 			sizeof(ds->state->altpath));
@@ -294,13 +294,13 @@ out:
 /* Check a block's sibling pointers. */
 STATIC int
 xchk_da_btree_block_check_siblings(
-	struct xchk_da_btree		*ds,
-	int				level,
-	struct xfs_da_blkinfo		*hdr)
+	struct xchk_da_btree	*ds,
+	int			level,
+	struct xfs_da_blkinfo	*hdr)
 {
-	xfs_dablk_t			forw;
-	xfs_dablk_t			back;
-	int				error = 0;
+	xfs_dablk_t		forw;
+	xfs_dablk_t		back;
+	int			error = 0;
 
 	forw = be32_to_cpu(hdr->forw);
 	back = be32_to_cpu(hdr->back);
@@ -474,9 +474,9 @@ out_nobuf:
 /* Visit all nodes and leaves of a da btree. */
 int
 xchk_da_btree(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	int				whichfork,
-	xchk_da_btree_rec_fn	scrub_fn,
+	xchk_da_btree_rec_fn		scrub_fn,
 	void				*private)
 {
 	struct xchk_da_btree		ds = {};
diff --git a/fs/xfs/scrub/dabtree.h b/fs/xfs/scrub/dabtree.h
index a15c03389e8f..cb3f0003245b 100644
--- a/fs/xfs/scrub/dabtree.h
+++ b/fs/xfs/scrub/dabtree.h
@@ -9,12 +9,12 @@
 /* dir/attr btree */
 
 struct xchk_da_btree {
-	struct xfs_da_args		dargs;
-	xfs_dahash_t			hashes[XFS_DA_NODE_MAXDEPTH];
-	int				maxrecs[XFS_DA_NODE_MAXDEPTH];
-	struct xfs_da_state		*state;
+	struct xfs_da_args	dargs;
+	xfs_dahash_t		hashes[XFS_DA_NODE_MAXDEPTH];
+	int			maxrecs[XFS_DA_NODE_MAXDEPTH];
+	struct xfs_da_state	*state;
 	struct xfs_scrub	*sc;
-	void				*private;
+	void			*private;
 
 	/*
 	 * Lowest and highest directory block address in which we expect
@@ -22,10 +22,10 @@ struct xchk_da_btree {
 	 * (presumably) means between LEAF_OFFSET and FREE_OFFSET; for
 	 * attributes there is no limit.
 	 */
-	xfs_dablk_t			lowest;
-	xfs_dablk_t			highest;
+	xfs_dablk_t		lowest;
+	xfs_dablk_t		highest;
 
-	int				tree_level;
+	int			tree_level;
 };
 
 typedef int (*xchk_da_btree_rec_fn)(struct xchk_da_btree *ds,
@@ -37,9 +37,8 @@ bool xchk_da_process_error(struct xchk_da_btree *ds, int level, int *error);
 /* Check for da btree corruption. */
 void xchk_da_set_corrupt(struct xchk_da_btree *ds, int level);
 
-int xchk_da_btree_hash(struct xchk_da_btree *ds, int level,
-			    __be32 *hashp);
+int xchk_da_btree_hash(struct xchk_da_btree *ds, int level, __be32 *hashp);
 int xchk_da_btree(struct xfs_scrub *sc, int whichfork,
-		       xchk_da_btree_rec_fn scrub_fn, void *private);
+		xchk_da_btree_rec_fn scrub_fn, void *private);
 
 #endif /* __XFS_SCRUB_DABTREE_H__ */
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index 194a3ef69a9f..f58709052b03 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -33,7 +33,7 @@
 int
 xchk_setup_directory(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
 	return xchk_setup_inode_contents(sc, ip, 0);
 }
@@ -44,7 +44,7 @@ xchk_setup_directory(
 
 struct xchk_dir_ctx {
 	/* VFS fill-directory iterator */
-	struct dir_context		dir_iter;
+	struct dir_context	dir_iter;
 
 	struct xfs_scrub	*sc;
 };
@@ -52,15 +52,15 @@ struct xchk_dir_ctx {
 /* Check that an inode's mode matches a given DT_ type. */
 STATIC int
 xchk_dir_check_ftype(
-	struct xchk_dir_ctx		*sdc,
-	xfs_fileoff_t			offset,
-	xfs_ino_t			inum,
-	int				dtype)
+	struct xchk_dir_ctx	*sdc,
+	xfs_fileoff_t		offset,
+	xfs_ino_t		inum,
+	int			dtype)
 {
-	struct xfs_mount		*mp = sdc->sc->mp;
-	struct xfs_inode		*ip;
-	int				ino_dtype;
-	int				error = 0;
+	struct xfs_mount	*mp = sdc->sc->mp;
+	struct xfs_inode	*ip;
+	int			ino_dtype;
+	int			error = 0;
 
 	if (!xfs_sb_version_hasftype(&mp->m_sb)) {
 		if (dtype != DT_UNKNOWN && dtype != DT_DIR)
@@ -102,20 +102,20 @@ out:
  */
 STATIC int
 xchk_dir_actor(
-	struct dir_context		*dir_iter,
-	const char			*name,
-	int				namelen,
-	loff_t				pos,
-	u64				ino,
-	unsigned			type)
+	struct dir_context	*dir_iter,
+	const char		*name,
+	int			namelen,
+	loff_t			pos,
+	u64			ino,
+	unsigned		type)
 {
-	struct xfs_mount		*mp;
-	struct xfs_inode		*ip;
-	struct xchk_dir_ctx		*sdc;
-	struct xfs_name			xname;
-	xfs_ino_t			lookup_ino;
-	xfs_dablk_t			offset;
-	int				error = 0;
+	struct xfs_mount	*mp;
+	struct xfs_inode	*ip;
+	struct xchk_dir_ctx	*sdc;
+	struct xfs_name		xname;
+	xfs_ino_t		lookup_ino;
+	xfs_dablk_t		offset;
+	int			error = 0;
 
 	sdc = container_of(dir_iter, struct xchk_dir_ctx, dir_iter);
 	ip = sdc->sc->ip;
@@ -289,7 +289,7 @@ out:
  */
 STATIC void
 xchk_directory_check_free_entry(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_dir2_data_free	*bf,
 	struct xfs_dir2_data_unused	*dup)
@@ -314,7 +314,7 @@ xchk_directory_check_free_entry(
 /* Check free space info in a directory data block. */
 STATIC int
 xchk_directory_data_bestfree(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	bool				is_block)
 {
@@ -455,7 +455,7 @@ out:
  */
 STATIC void
 xchk_directory_check_freesp(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	xfs_dablk_t			lblk,
 	struct xfs_buf			*dbp,
 	unsigned int			len)
@@ -474,7 +474,7 @@ xchk_directory_check_freesp(
 /* Check free space info in a directory leaf1 block. */
 STATIC int
 xchk_directory_leaf1_bestfree(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -572,7 +572,7 @@ out:
 /* Check free space info in a directory freespace block. */
 STATIC int
 xchk_directory_free_bestfree(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	struct xfs_da_args		*args,
 	xfs_dablk_t			lblk)
 {
@@ -628,18 +628,18 @@ STATIC int
 xchk_directory_blocks(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_bmbt_irec		got;
-	struct xfs_da_args		args;
-	struct xfs_ifork		*ifp;
-	struct xfs_mount		*mp = sc->mp;
-	xfs_fileoff_t			leaf_lblk;
-	xfs_fileoff_t			free_lblk;
-	xfs_fileoff_t			lblk;
-	struct xfs_iext_cursor		icur;
-	xfs_dablk_t			dabno;
-	bool				found;
-	int				is_block = 0;
-	int				error;
+	struct xfs_bmbt_irec	got;
+	struct xfs_da_args	args;
+	struct xfs_ifork	*ifp;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_fileoff_t		leaf_lblk;
+	xfs_fileoff_t		free_lblk;
+	xfs_fileoff_t		lblk;
+	struct xfs_iext_cursor	icur;
+	xfs_dablk_t		dabno;
+	bool			found;
+	int			is_block = 0;
+	int			error;
 
 	/* Ignore local format directories. */
 	if (sc->ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
@@ -772,14 +772,14 @@ int
 xchk_directory(
 	struct xfs_scrub	*sc)
 {
-	struct xchk_dir_ctx		sdc = {
+	struct xchk_dir_ctx	sdc = {
 		.dir_iter.actor = xchk_dir_actor,
 		.dir_iter.pos = 0,
 		.sc = sc,
 	};
-	size_t				bufsize;
-	loff_t				oldpos;
-	int				error = 0;
+	size_t			bufsize;
+	loff_t			oldpos;
+	int			error = 0;
 
 	if (!S_ISDIR(VFS_I(sc->ip)->i_mode))
 		return -ENOENT;
diff --git a/fs/xfs/scrub/ialloc.c b/fs/xfs/scrub/ialloc.c
index 6df8eba9f52b..224dba937492 100644
--- a/fs/xfs/scrub/ialloc.c
+++ b/fs/xfs/scrub/ialloc.c
@@ -37,7 +37,7 @@
 int
 xchk_setup_ag_iallocbt(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, sc->try_harder);
 }
@@ -51,7 +51,7 @@ xchk_setup_ag_iallocbt(
  */
 static inline void
 xchk_iallocbt_chunk_xref_other(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino)
 {
@@ -76,7 +76,7 @@ xchk_iallocbt_chunk_xref_other(
 /* Cross-reference with the other btrees. */
 STATIC void
 xchk_iallocbt_chunk_xref(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	struct xfs_inobt_rec_incore	*irec,
 	xfs_agino_t			agino,
 	xfs_agblock_t			agbno,
@@ -364,13 +364,13 @@ out:
 STATIC void
 xchk_iallocbt_xref_rmap_btreeblks(
 	struct xfs_scrub	*sc,
-	int				which)
+	int			which)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			blocks;
-	xfs_extlen_t			inobt_blocks = 0;
-	xfs_extlen_t			finobt_blocks = 0;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		blocks;
+	xfs_extlen_t		inobt_blocks = 0;
+	xfs_extlen_t		finobt_blocks = 0;
+	int			error;
 
 	if (!sc->sa.ino_cur || !sc->sa.rmap_cur ||
 	    (xfs_sb_version_hasfinobt(&sc->mp->m_sb) && !sc->sa.fino_cur) ||
@@ -404,12 +404,12 @@ xchk_iallocbt_xref_rmap_btreeblks(
 STATIC void
 xchk_iallocbt_xref_rmap_inodes(
 	struct xfs_scrub	*sc,
-	int				which,
-	xfs_filblks_t			inode_blocks)
+	int			which,
+	xfs_filblks_t		inode_blocks)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			blocks;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		blocks;
+	int			error;
 
 	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
@@ -428,12 +428,12 @@ xchk_iallocbt_xref_rmap_inodes(
 STATIC int
 xchk_iallocbt(
 	struct xfs_scrub	*sc,
-	xfs_btnum_t			which)
+	xfs_btnum_t		which)
 {
-	struct xfs_btree_cur		*cur;
-	struct xfs_owner_info		oinfo;
-	xfs_filblks_t			inode_blocks = 0;
-	int				error;
+	struct xfs_btree_cur	*cur;
+	struct xfs_owner_info	oinfo;
+	xfs_filblks_t		inode_blocks = 0;
+	int			error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INOBT);
 	cur = which == XFS_BTNUM_INO ? sc->sa.ino_cur : sc->sa.fino_cur;
@@ -475,13 +475,13 @@ xchk_finobt(
 static inline void
 xchk_xref_inode_check(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len,
-	struct xfs_btree_cur		**icur,
-	bool				should_have_inodes)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len,
+	struct xfs_btree_cur	**icur,
+	bool			should_have_inodes)
 {
-	bool				has_inodes;
-	int				error;
+	bool			has_inodes;
+	int			error;
 
 	if (!(*icur) || xchk_skip_xref(sc->sm))
 		return;
@@ -497,8 +497,8 @@ xchk_xref_inode_check(
 void
 xchk_xref_is_not_inode_chunk(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
 	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, false);
 	xchk_xref_inode_check(sc, agbno, len, &sc->sa.fino_cur, false);
@@ -508,8 +508,8 @@ xchk_xref_is_not_inode_chunk(
 void
 xchk_xref_is_inode_chunk(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
 	xchk_xref_inode_check(sc, agbno, len, &sc->sa.ino_cur, true);
 }
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 6cc027983c13..5b3b177c0fc9 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -39,9 +39,9 @@
 int
 xchk_setup_inode(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
 	/*
 	 * Try to get the inode.  If the verifiers fail, we try again
@@ -78,12 +78,12 @@ out:
 STATIC void
 xchk_inode_extsize(
 	struct xfs_scrub	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags)
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	fa = xfs_inode_validate_extsize(sc->mp, be32_to_cpu(dip->di_extsize),
 			mode, flags);
@@ -100,13 +100,13 @@ xchk_inode_extsize(
 STATIC void
 xchk_inode_cowextsize(
 	struct xfs_scrub	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags,
-	uint64_t			flags2)
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
 {
-	xfs_failaddr_t			fa;
+	xfs_failaddr_t		fa;
 
 	fa = xfs_inode_validate_cowextsize(sc->mp,
 			be32_to_cpu(dip->di_cowextsize), mode, flags,
@@ -119,12 +119,12 @@ xchk_inode_cowextsize(
 STATIC void
 xchk_inode_flags(
 	struct xfs_scrub	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags)
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags)
 {
-	struct xfs_mount		*mp = sc->mp;
+	struct xfs_mount	*mp = sc->mp;
 
 	if (flags & ~XFS_DIFLAG_ANY)
 		goto bad;
@@ -164,13 +164,13 @@ bad:
 STATIC void
 xchk_inode_flags2(
 	struct xfs_scrub	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino,
-	uint16_t			mode,
-	uint16_t			flags,
-	uint64_t			flags2)
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint64_t		flags2)
 {
-	struct xfs_mount		*mp = sc->mp;
+	struct xfs_mount	*mp = sc->mp;
 
 	if (flags2 & ~XFS_DIFLAG2_ANY)
 		goto bad;
@@ -207,16 +207,16 @@ bad:
 STATIC void
 xchk_dinode(
 	struct xfs_scrub	*sc,
-	struct xfs_dinode		*dip,
-	xfs_ino_t			ino)
+	struct xfs_dinode	*dip,
+	xfs_ino_t		ino)
 {
-	struct xfs_mount		*mp = sc->mp;
-	size_t				fork_recs;
-	unsigned long long		isize;
-	uint64_t			flags2;
-	uint32_t			nextents;
-	uint16_t			flags;
-	uint16_t			mode;
+	struct xfs_mount	*mp = sc->mp;
+	size_t			fork_recs;
+	unsigned long long	isize;
+	uint64_t		flags2;
+	uint32_t		nextents;
+	uint16_t		flags;
+	uint16_t		mode;
 
 	flags = be16_to_cpu(dip->di_flags);
 	if (dip->di_version >= 3)
@@ -426,7 +426,7 @@ xchk_dinode(
  */
 static void
 xchk_inode_xref_finobt(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	xfs_ino_t			ino)
 {
 	struct xfs_inobt_rec_incore	rec;
@@ -470,12 +470,12 @@ xchk_inode_xref_finobt(
 STATIC void
 xchk_inode_xref_bmap(
 	struct xfs_scrub	*sc,
-	struct xfs_dinode		*dip)
+	struct xfs_dinode	*dip)
 {
-	xfs_extnum_t			nextents;
-	xfs_filblks_t			count;
-	xfs_filblks_t			acount;
-	int				error;
+	xfs_extnum_t		nextents;
+	xfs_filblks_t		count;
+	xfs_filblks_t		acount;
+	int			error;
 
 	if (xchk_skip_xref(sc->sm))
 		return;
@@ -504,13 +504,13 @@ xchk_inode_xref_bmap(
 STATIC void
 xchk_inode_xref(
 	struct xfs_scrub	*sc,
-	xfs_ino_t			ino,
-	struct xfs_dinode		*dip)
+	xfs_ino_t		ino,
+	struct xfs_dinode	*dip)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	int			error;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -541,11 +541,11 @@ xchk_inode_xref(
 static void
 xchk_inode_check_reflink_iflag(
 	struct xfs_scrub	*sc,
-	xfs_ino_t			ino)
+	xfs_ino_t		ino)
 {
-	struct xfs_mount		*mp = sc->mp;
-	bool				has_shared;
-	int				error;
+	struct xfs_mount	*mp = sc->mp;
+	bool			has_shared;
+	int			error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return;
@@ -566,8 +566,8 @@ int
 xchk_inode(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_dinode		di;
-	int				error = 0;
+	struct xfs_dinode	di;
+	int			error = 0;
 
 	/*
 	 * If sc->ip is NULL, that means that the setup function called
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index 808459ad0c35..aacb0284c48a 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -29,7 +29,7 @@
 int
 xchk_setup_parent(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
 	return xchk_setup_inode_contents(sc, ip, 0);
 }
@@ -39,22 +39,22 @@ xchk_setup_parent(
 /* Look for an entry in a parent pointing to this inode. */
 
 struct xchk_parent_ctx {
-	struct dir_context		dc;
-	xfs_ino_t			ino;
-	xfs_nlink_t			nlink;
+	struct dir_context	dc;
+	xfs_ino_t		ino;
+	xfs_nlink_t		nlink;
 };
 
 /* Look for a single entry in a directory pointing to an inode. */
 STATIC int
 xchk_parent_actor(
-	struct dir_context		*dc,
-	const char			*name,
-	int				namelen,
-	loff_t				pos,
-	u64				ino,
-	unsigned			type)
+	struct dir_context	*dc,
+	const char		*name,
+	int			namelen,
+	loff_t			pos,
+	u64			ino,
+	unsigned		type)
 {
-	struct xchk_parent_ctx		*spc;
+	struct xchk_parent_ctx	*spc;
 
 	spc = container_of(dc, struct xchk_parent_ctx, dc);
 	if (spc->ino == ino)
@@ -66,19 +66,19 @@ xchk_parent_actor(
 STATIC int
 xchk_parent_count_parent_dentries(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*parent,
-	xfs_nlink_t			*nlink)
+	struct xfs_inode	*parent,
+	xfs_nlink_t		*nlink)
 {
-	struct xchk_parent_ctx		spc = {
+	struct xchk_parent_ctx	spc = {
 		.dc.actor = xchk_parent_actor,
 		.dc.pos = 0,
 		.ino = sc->ip->i_ino,
 		.nlink = 0,
 	};
-	size_t				bufsize;
-	loff_t				oldpos;
-	uint				lock_mode;
-	int				error = 0;
+	size_t			bufsize;
+	loff_t			oldpos;
+	uint			lock_mode;
+	int			error = 0;
 
 	/*
 	 * If there are any blocks, read-ahead block 0 as we're almost
@@ -122,14 +122,14 @@ out:
 STATIC int
 xchk_parent_validate(
 	struct xfs_scrub	*sc,
-	xfs_ino_t			dnum,
-	bool				*try_again)
+	xfs_ino_t		dnum,
+	bool			*try_again)
 {
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_inode		*dp = NULL;
-	xfs_nlink_t			expected_nlink;
-	xfs_nlink_t			nlink;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_inode	*dp = NULL;
+	xfs_nlink_t		expected_nlink;
+	xfs_nlink_t		nlink;
+	int			error = 0;
 
 	*try_again = false;
 
@@ -257,11 +257,11 @@ int
 xchk_parent(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_mount		*mp = sc->mp;
-	xfs_ino_t			dnum;
-	bool				try_again;
-	int				tries = 0;
-	int				error = 0;
+	struct xfs_mount	*mp = sc->mp;
+	xfs_ino_t		dnum;
+	bool			try_again;
+	int			tries = 0;
+	int			error = 0;
 
 	/*
 	 * If we're a directory, check that the '..' link points up to
diff --git a/fs/xfs/scrub/quota.c b/fs/xfs/scrub/quota.c
index 309ebeecfa5d..782d582d3edd 100644
--- a/fs/xfs/scrub/quota.c
+++ b/fs/xfs/scrub/quota.c
@@ -49,10 +49,10 @@ xchk_quota_to_dqtype(
 int
 xchk_setup_quota(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
-	uint				dqtype;
-	int				error;
+	uint			dqtype;
+	int			error;
 
 	if (!XFS_IS_QUOTA_RUNNING(sc->mp) || !XFS_IS_QUOTA_ON(sc->mp))
 		return -ENOENT;
@@ -77,33 +77,33 @@ xchk_setup_quota(
 
 struct xchk_quota_info {
 	struct xfs_scrub	*sc;
-	xfs_dqid_t			last_id;
+	xfs_dqid_t		last_id;
 };
 
 /* Scrub the fields in an individual quota item. */
 STATIC int
 xchk_quota_item(
-	struct xfs_dquot		*dq,
-	uint				dqtype,
-	void				*priv)
+	struct xfs_dquot	*dq,
+	uint			dqtype,
+	void			*priv)
 {
-	struct xchk_quota_info		*sqi = priv;
+	struct xchk_quota_info	*sqi = priv;
 	struct xfs_scrub	*sc = sqi->sc;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_disk_dquot		*d = &dq->q_core;
-	struct xfs_quotainfo		*qi = mp->m_quotainfo;
-	xfs_fileoff_t			offset;
-	unsigned long long		bsoft;
-	unsigned long long		isoft;
-	unsigned long long		rsoft;
-	unsigned long long		bhard;
-	unsigned long long		ihard;
-	unsigned long long		rhard;
-	unsigned long long		bcount;
-	unsigned long long		icount;
-	unsigned long long		rcount;
-	xfs_ino_t			fs_icount;
-	xfs_dqid_t			id = be32_to_cpu(d->d_id);
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_disk_dquot	*d = &dq->q_core;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	xfs_fileoff_t		offset;
+	unsigned long long	bsoft;
+	unsigned long long	isoft;
+	unsigned long long	rsoft;
+	unsigned long long	bhard;
+	unsigned long long	ihard;
+	unsigned long long	rhard;
+	unsigned long long	bcount;
+	unsigned long long	icount;
+	unsigned long long	rcount;
+	xfs_ino_t		fs_icount;
+	xfs_dqid_t		id = be32_to_cpu(d->d_id);
 
 	/*
 	 * Except for the root dquot, the actual dquot we got must either have
@@ -197,12 +197,12 @@ STATIC int
 xchk_quota_data_fork(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_bmbt_irec		irec = { 0 };
-	struct xfs_iext_cursor		icur;
-	struct xfs_quotainfo		*qi = sc->mp->m_quotainfo;
-	struct xfs_ifork		*ifp;
-	xfs_fileoff_t			max_dqid_off;
-	int				error = 0;
+	struct xfs_bmbt_irec	irec = { 0 };
+	struct xfs_iext_cursor	icur;
+	struct xfs_quotainfo	*qi = sc->mp->m_quotainfo;
+	struct xfs_ifork	*ifp;
+	xfs_fileoff_t		max_dqid_off;
+	int			error = 0;
 
 	/* Invoke the fork scrubber. */
 	error = xchk_metadata_inode_forks(sc);
@@ -236,11 +236,11 @@ int
 xchk_quota(
 	struct xfs_scrub	*sc)
 {
-	struct xchk_quota_info		sqi;
-	struct xfs_mount		*mp = sc->mp;
-	struct xfs_quotainfo		*qi = mp->m_quotainfo;
-	uint				dqtype;
-	int				error = 0;
+	struct xchk_quota_info	sqi;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_quotainfo	*qi = mp->m_quotainfo;
+	uint			dqtype;
+	int			error = 0;
 
 	dqtype = xchk_quota_to_dqtype(sc);
 
diff --git a/fs/xfs/scrub/refcount.c b/fs/xfs/scrub/refcount.c
index c1162d408987..e8c82b026083 100644
--- a/fs/xfs/scrub/refcount.c
+++ b/fs/xfs/scrub/refcount.c
@@ -30,7 +30,7 @@
 int
 xchk_setup_ag_refcountbt(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, false);
 }
@@ -74,21 +74,21 @@ xchk_setup_ag_refcountbt(
  * should always hold true.  If not, the refcount is incorrect.
  */
 struct xchk_refcnt_frag {
-	struct list_head		list;
-	struct xfs_rmap_irec		rm;
+	struct list_head	list;
+	struct xfs_rmap_irec	rm;
 };
 
 struct xchk_refcnt_check {
 	struct xfs_scrub	*sc;
-	struct list_head		fragments;
+	struct list_head	fragments;
 
 	/* refcount extent we're examining */
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	xfs_nlink_t			refcount;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	xfs_nlink_t		refcount;
 
 	/* number of owners seen */
-	xfs_nlink_t			seen;
+	xfs_nlink_t		seen;
 };
 
 /*
@@ -278,7 +278,7 @@ done:
 /* Use the rmap entries covering this extent to verify the refcount. */
 STATIC void
 xchk_refcountbt_xref_rmap(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	xfs_agblock_t			bno,
 	xfs_extlen_t			len,
 	xfs_nlink_t			refcount)
@@ -326,9 +326,9 @@ out_free:
 STATIC void
 xchk_refcountbt_xref(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len,
-	xfs_nlink_t			refcount)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len,
+	xfs_nlink_t		refcount)
 {
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -341,17 +341,17 @@ xchk_refcountbt_xref(
 /* Scrub a refcountbt record. */
 STATIC int
 xchk_refcountbt_rec(
-	struct xchk_btree		*bs,
-	union xfs_btree_rec		*rec)
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	xfs_agblock_t			*cow_blocks = bs->private;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	xfs_agblock_t			bno;
-	xfs_extlen_t			len;
-	xfs_nlink_t			refcount;
-	bool				has_cowflag;
-	int				error = 0;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	xfs_agblock_t		*cow_blocks = bs->private;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	xfs_agblock_t		bno;
+	xfs_extlen_t		len;
+	xfs_nlink_t		refcount;
+	bool			has_cowflag;
+	int			error = 0;
 
 	bno = be32_to_cpu(rec->refc.rc_startblock);
 	len = be32_to_cpu(rec->refc.rc_blockcount);
@@ -383,12 +383,12 @@ xchk_refcountbt_rec(
 STATIC void
 xchk_refcount_xref_rmap(
 	struct xfs_scrub	*sc,
-	struct xfs_owner_info		*oinfo,
-	xfs_filblks_t			cow_blocks)
+	struct xfs_owner_info	*oinfo,
+	xfs_filblks_t		cow_blocks)
 {
-	xfs_extlen_t			refcbt_blocks = 0;
-	xfs_filblks_t			blocks;
-	int				error;
+	xfs_extlen_t		refcbt_blocks = 0;
+	xfs_filblks_t		blocks;
+	int			error;
 
 	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
@@ -419,9 +419,9 @@ int
 xchk_refcountbt(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
-	xfs_agblock_t			cow_blocks = 0;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	xfs_agblock_t		cow_blocks = 0;
+	int			error;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_REFC);
 	error = xchk_btree(sc, sc->sa.refc_cur, xchk_refcountbt_rec,
@@ -437,7 +437,7 @@ xchk_refcountbt(
 /* xref check that a cow staging extent is marked in the refcountbt. */
 void
 xchk_xref_is_cow_staging(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	xfs_agblock_t			agbno,
 	xfs_extlen_t			len)
 {
@@ -484,11 +484,11 @@ xchk_xref_is_cow_staging(
 void
 xchk_xref_is_not_shared(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno,
-	xfs_extlen_t			len)
+	xfs_agblock_t		agbno,
+	xfs_extlen_t		len)
 {
-	bool				shared;
-	int				error;
+	bool			shared;
+	int			error;
 
 	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 29debd5649ac..5de1cac424ec 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -42,11 +42,11 @@
  */
 int
 xrep_attempt(
-	struct xfs_inode		*ip,
+	struct xfs_inode	*ip,
 	struct xfs_scrub	*sc,
-	bool				*fixed)
+	bool			*fixed)
 {
-	int				error = 0;
+	int			error = 0;
 
 	trace_xrep_attempt(ip, sc->sm, error);
 
@@ -94,7 +94,7 @@ xrep_attempt(
  */
 void
 xrep_failure(
-	struct xfs_mount		*mp)
+	struct xfs_mount	*mp)
 {
 	xfs_alert_ratelimited(mp,
 "Corruption not fixed during online repair.  Unmount and run xfs_repair.");
@@ -108,7 +108,7 @@ int
 xrep_probe(
 	struct xfs_scrub	*sc)
 {
-	int				error = 0;
+	int			error = 0;
 
 	if (xchk_should_terminate(sc, &error))
 		return error;
@@ -124,7 +124,7 @@ int
 xrep_roll_ag_trans(
 	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	/* Keep the AG header buffers locked so we can keep going. */
 	xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
@@ -163,9 +163,9 @@ out_release:
  */
 bool
 xrep_ag_has_space(
-	struct xfs_perag		*pag,
-	xfs_extlen_t			nr_blocks,
-	enum xfs_ag_resv_type		type)
+	struct xfs_perag	*pag,
+	xfs_extlen_t		nr_blocks,
+	enum xfs_ag_resv_type	type)
 {
 	return  !xfs_ag_resv_critical(pag, XFS_AG_RESV_RMAPBT) &&
 		!xfs_ag_resv_critical(pag, XFS_AG_RESV_METADATA) &&
@@ -179,7 +179,7 @@ xrep_ag_has_space(
  */
 xfs_extlen_t
 xrep_calc_ag_resblks(
-	struct xfs_scrub	*sc)
+	struct xfs_scrub		*sc)
 {
 	struct xfs_mount		*mp = sc->mp;
 	struct xfs_scrub_metadata	*sm = sc->sm;
@@ -280,13 +280,13 @@ xrep_calc_ag_resblks(
 int
 xrep_alloc_ag_block(
 	struct xfs_scrub	*sc,
-	struct xfs_owner_info		*oinfo,
-	xfs_fsblock_t			*fsbno,
-	enum xfs_ag_resv_type		resv)
+	struct xfs_owner_info	*oinfo,
+	xfs_fsblock_t		*fsbno,
+	enum xfs_ag_resv_type	resv)
 {
-	struct xfs_alloc_arg		args = {0};
-	xfs_agblock_t			bno;
-	int				error;
+	struct xfs_alloc_arg	args = {0};
+	xfs_agblock_t		bno;
+	int			error;
 
 	switch (resv) {
 	case XFS_AG_RESV_AGFL:
@@ -330,7 +330,7 @@ xrep_alloc_ag_block(
 /* Initialize a new AG btree root block with zero entries. */
 int
 xrep_init_btblock(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	xfs_fsblock_t			fsb,
 	struct xfs_buf			**bpp,
 	xfs_btnum_t			btnum,
@@ -386,11 +386,11 @@ xrep_init_btblock(
 int
 xrep_collect_btree_extent(
 	struct xfs_scrub	*sc,
-	struct xrep_extent_list		*exlist,
-	xfs_fsblock_t			fsbno,
-	xfs_extlen_t			len)
+	struct xrep_extent_list	*exlist,
+	xfs_fsblock_t		fsbno,
+	xfs_extlen_t		len)
 {
-	struct xrep_extent		*rex;
+	struct xrep_extent	*rex;
 
 	trace_xrep_collect_btree_extent(sc->mp,
 			XFS_FSB_TO_AGNO(sc->mp, fsbno),
@@ -416,10 +416,10 @@ xrep_collect_btree_extent(
 void
 xrep_cancel_btree_extents(
 	struct xfs_scrub	*sc,
-	struct xrep_extent_list		*exlist)
+	struct xrep_extent_list	*exlist)
 {
-	struct xrep_extent		*rex;
-	struct xrep_extent		*n;
+	struct xrep_extent	*rex;
+	struct xrep_extent	*n;
 
 	for_each_xrep_extent_safe(rex, n, exlist) {
 		list_del(&rex->list);
@@ -430,12 +430,12 @@ xrep_cancel_btree_extents(
 /* Compare two btree extents. */
 static int
 xrep_btree_extent_cmp(
-	void				*priv,
-	struct list_head		*a,
-	struct list_head		*b)
+	void			*priv,
+	struct list_head	*a,
+	struct list_head	*b)
 {
-	struct xrep_extent		*ap;
-	struct xrep_extent		*bp;
+	struct xrep_extent	*ap;
+	struct xrep_extent	*bp;
 
 	ap = container_of(a, struct xrep_extent, list);
 	bp = container_of(b, struct xrep_extent, list);
@@ -464,17 +464,17 @@ xrep_btree_extent_cmp(
 int
 xrep_subtract_extents(
 	struct xfs_scrub	*sc,
-	struct xrep_extent_list		*exlist,
-	struct xrep_extent_list		*sublist)
+	struct xrep_extent_list	*exlist,
+	struct xrep_extent_list	*sublist)
 {
-	struct list_head		*lp;
-	struct xrep_extent		*ex;
-	struct xrep_extent		*newex;
-	struct xrep_extent		*subex;
-	xfs_fsblock_t			sub_fsb;
-	xfs_extlen_t			sub_len;
-	int				state;
-	int				error = 0;
+	struct list_head	*lp;
+	struct xrep_extent	*ex;
+	struct xrep_extent	*newex;
+	struct xrep_extent	*subex;
+	xfs_fsblock_t		sub_fsb;
+	xfs_extlen_t		sub_len;
+	int			state;
+	int			error = 0;
 
 	if (list_empty(&exlist->list) || list_empty(&sublist->list))
 		return 0;
@@ -621,13 +621,13 @@ out:
 int
 xrep_invalidate_blocks(
 	struct xfs_scrub	*sc,
-	struct xrep_extent_list		*exlist)
+	struct xrep_extent_list	*exlist)
 {
-	struct xrep_extent		*rex;
-	struct xrep_extent		*n;
-	struct xfs_buf			*bp;
-	xfs_fsblock_t			fsbno;
-	xfs_agblock_t			i;
+	struct xrep_extent	*rex;
+	struct xrep_extent	*n;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
+	xfs_agblock_t		i;
 
 	/*
 	 * For each block in each extent, see if there's an incore buffer for
@@ -659,9 +659,9 @@ xrep_invalidate_blocks(
 int
 xrep_fix_freelist(
 	struct xfs_scrub	*sc,
-	bool				can_shrink)
+	bool			can_shrink)
 {
-	struct xfs_alloc_arg		args = {0};
+	struct xfs_alloc_arg	args = {0};
 
 	args.mp = sc->mp;
 	args.tp = sc->tp;
@@ -679,10 +679,10 @@ xrep_fix_freelist(
 STATIC int
 xrep_put_freelist(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			agbno)
+	xfs_agblock_t		agbno)
 {
-	struct xfs_owner_info		oinfo;
-	int				error;
+	struct xfs_owner_info	oinfo;
+	int			error;
 
 	/* Make sure there's space on the freelist. */
 	error = xrep_fix_freelist(sc, true);
@@ -715,16 +715,16 @@ xrep_put_freelist(
 STATIC int
 xrep_dispose_btree_block(
 	struct xfs_scrub	*sc,
-	xfs_fsblock_t			fsbno,
-	struct xfs_owner_info		*oinfo,
-	enum xfs_ag_resv_type		resv)
+	xfs_fsblock_t		fsbno,
+	struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type	resv)
 {
-	struct xfs_btree_cur		*cur;
-	struct xfs_buf			*agf_bp = NULL;
-	xfs_agnumber_t			agno;
-	xfs_agblock_t			agbno;
-	bool				has_other_rmap;
-	int				error;
+	struct xfs_btree_cur	*cur;
+	struct xfs_buf		*agf_bp = NULL;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	bool			has_other_rmap;
+	int			error;
 
 	agno = XFS_FSB_TO_AGNO(sc->mp, fsbno);
 	agbno = XFS_FSB_TO_AGBNO(sc->mp, fsbno);
@@ -789,13 +789,13 @@ out_free:
 int
 xrep_reap_btree_extents(
 	struct xfs_scrub	*sc,
-	struct xrep_extent_list		*exlist,
-	struct xfs_owner_info		*oinfo,
-	enum xfs_ag_resv_type		type)
+	struct xrep_extent_list	*exlist,
+	struct xfs_owner_info	*oinfo,
+	enum xfs_ag_resv_type	type)
 {
-	struct xrep_extent		*rex;
-	struct xrep_extent		*n;
-	int				error = 0;
+	struct xrep_extent	*rex;
+	struct xrep_extent	*n;
+	int			error = 0;
 
 	ASSERT(xfs_sb_version_hasrmapbt(&sc->mp->m_sb));
 
@@ -851,7 +851,7 @@ out:
  */
 
 struct xrep_findroot {
-	struct xfs_scrub	*sc;
+	struct xfs_scrub		*sc;
 	struct xfs_buf			*agfl_bp;
 	struct xfs_agf			*agf;
 	struct xrep_find_ag_btree	*btree_info;
@@ -860,11 +860,11 @@ struct xrep_findroot {
 /* See if our block is in the AGFL. */
 STATIC int
 xrep_findroot_agfl_walk(
-	struct xfs_mount		*mp,
-	xfs_agblock_t			bno,
-	void				*priv)
+	struct xfs_mount	*mp,
+	xfs_agblock_t		bno,
+	void			*priv)
 {
-	xfs_agblock_t			*agbno = priv;
+	xfs_agblock_t		*agbno = priv;
 
 	return (*agbno == bno) ? XFS_BTREE_QUERY_RANGE_ABORT : 0;
 }
@@ -981,7 +981,7 @@ xrep_findroot_rmap(
 /* Find the roots of the per-AG btrees described in btree_info. */
 int
 xrep_find_ag_btree_roots(
-	struct xfs_scrub	*sc,
+	struct xfs_scrub		*sc,
 	struct xfs_buf			*agf_bp,
 	struct xrep_find_ag_btree	*btree_info,
 	struct xfs_buf			*agfl_bp)
@@ -1017,9 +1017,9 @@ xrep_find_ag_btree_roots(
 void
 xrep_force_quotacheck(
 	struct xfs_scrub	*sc,
-	uint				dqtype)
+	uint			dqtype)
 {
-	uint				flag;
+	uint			flag;
 
 	flag = xfs_quota_chkd_flag(dqtype);
 	if (!(flag & sc->mp->m_qflags))
@@ -1046,7 +1046,7 @@ int
 xrep_ino_dqattach(
 	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	error = xfs_qm_dqattach_locked(sc->ip, false);
 	switch (error) {
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 677f4b73b5ec..91355f6b0087 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -15,33 +15,31 @@ static inline int xrep_notsupported(struct xfs_scrub *sc)
 
 /* Repair helpers */
 
-int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc,
-		bool *fixed);
+int xrep_attempt(struct xfs_inode *ip, struct xfs_scrub *sc, bool *fixed);
 void xrep_failure(struct xfs_mount *mp);
 int xrep_roll_ag_trans(struct xfs_scrub *sc);
 bool xrep_ag_has_space(struct xfs_perag *pag, xfs_extlen_t nr_blocks,
 		enum xfs_ag_resv_type type);
 xfs_extlen_t xrep_calc_ag_resblks(struct xfs_scrub *sc);
-int xrep_alloc_ag_block(struct xfs_scrub *sc,
-		struct xfs_owner_info *oinfo, xfs_fsblock_t *fsbno,
-		enum xfs_ag_resv_type resv);
+int xrep_alloc_ag_block(struct xfs_scrub *sc, struct xfs_owner_info *oinfo,
+		xfs_fsblock_t *fsbno, enum xfs_ag_resv_type resv);
 int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb,
 		struct xfs_buf **bpp, xfs_btnum_t btnum,
 		const struct xfs_buf_ops *ops);
 
 struct xrep_extent {
-	struct list_head		list;
-	xfs_fsblock_t			fsbno;
-	xfs_extlen_t			len;
+	struct list_head	list;
+	xfs_fsblock_t		fsbno;
+	xfs_extlen_t		len;
 };
 
 struct xrep_extent_list {
-	struct list_head		list;
+	struct list_head	list;
 };
 
 static inline void
 xrep_init_extent_list(
-	struct xrep_extent_list		*exlist)
+	struct xrep_extent_list	*exlist)
 {
 	INIT_LIST_HEAD(&exlist->list);
 }
@@ -78,10 +76,8 @@ struct xrep_find_ag_btree {
 	unsigned int			height;
 };
 
-int xrep_find_ag_btree_roots(struct xfs_scrub *sc,
-		struct xfs_buf *agf_bp,
-		struct xrep_find_ag_btree *btree_info,
-		struct xfs_buf *agfl_bp);
+int xrep_find_ag_btree_roots(struct xfs_scrub *sc, struct xfs_buf *agf_bp,
+		struct xrep_find_ag_btree *btree_info, struct xfs_buf *agfl_bp);
 void xrep_force_quotacheck(struct xfs_scrub *sc, uint dqtype);
 int xrep_ino_dqattach(struct xfs_scrub *sc);
 
@@ -93,9 +89,9 @@ int xrep_superblock(struct xfs_scrub *sc);
 #else
 
 static inline int xrep_attempt(
-	struct xfs_inode		*ip,
+	struct xfs_inode	*ip,
 	struct xfs_scrub	*sc,
-	bool				*fixed)
+	bool			*fixed)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index dc9c91a706ff..5e293c129813 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -31,7 +31,7 @@
 int
 xchk_setup_ag_rmapbt(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
 	return xchk_setup_ag_btree(sc, ip, false);
 }
@@ -42,15 +42,15 @@ xchk_setup_ag_rmapbt(
 STATIC void
 xchk_rmapbt_xref_refc(
 	struct xfs_scrub	*sc,
-	struct xfs_rmap_irec		*irec)
+	struct xfs_rmap_irec	*irec)
 {
-	xfs_agblock_t			fbno;
-	xfs_extlen_t			flen;
-	bool				non_inode;
-	bool				is_bmbt;
-	bool				is_attr;
-	bool				is_unwritten;
-	int				error;
+	xfs_agblock_t		fbno;
+	xfs_extlen_t		flen;
+	bool			non_inode;
+	bool			is_bmbt;
+	bool			is_attr;
+	bool			is_unwritten;
+	int			error;
 
 	if (!sc->sa.refc_cur || xchk_skip_xref(sc->sm))
 		return;
@@ -73,10 +73,10 @@ xchk_rmapbt_xref_refc(
 STATIC void
 xchk_rmapbt_xref(
 	struct xfs_scrub	*sc,
-	struct xfs_rmap_irec		*irec)
+	struct xfs_rmap_irec	*irec)
 {
-	xfs_agblock_t			agbno = irec->rm_startblock;
-	xfs_extlen_t			len = irec->rm_blockcount;
+	xfs_agblock_t		agbno = irec->rm_startblock;
+	xfs_extlen_t		len = irec->rm_blockcount;
 
 	if (sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)
 		return;
@@ -96,17 +96,17 @@ xchk_rmapbt_xref(
 /* Scrub an rmapbt record. */
 STATIC int
 xchk_rmapbt_rec(
-	struct xchk_btree		*bs,
-	union xfs_btree_rec		*rec)
+	struct xchk_btree	*bs,
+	union xfs_btree_rec	*rec)
 {
-	struct xfs_mount		*mp = bs->cur->bc_mp;
-	struct xfs_rmap_irec		irec;
-	xfs_agnumber_t			agno = bs->cur->bc_private.a.agno;
-	bool				non_inode;
-	bool				is_unwritten;
-	bool				is_bmbt;
-	bool				is_attr;
-	int				error;
+	struct xfs_mount	*mp = bs->cur->bc_mp;
+	struct xfs_rmap_irec	irec;
+	xfs_agnumber_t		agno = bs->cur->bc_private.a.agno;
+	bool			non_inode;
+	bool			is_unwritten;
+	bool			is_bmbt;
+	bool			is_attr;
+	int			error;
 
 	error = xfs_rmap_btrec_to_irec(rec, &irec);
 	if (!xchk_btree_process_error(bs->sc, bs->cur, 0, &error))
@@ -174,7 +174,7 @@ int
 xchk_rmapbt(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_owner_info		oinfo;
+	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
 	return xchk_btree(sc, sc->sa.rmap_cur, xchk_rmapbt_rec,
@@ -185,13 +185,13 @@ xchk_rmapbt(
 static inline void
 xchk_xref_check_owner(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo,
-	bool				should_have_rmap)
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo,
+	bool			should_have_rmap)
 {
-	bool				has_rmap;
-	int				error;
+	bool			has_rmap;
+	int			error;
 
 	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
@@ -208,9 +208,9 @@ xchk_xref_check_owner(
 void
 xchk_xref_is_owned_by(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo)
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo)
 {
 	xchk_xref_check_owner(sc, bno, len, oinfo, true);
 }
@@ -219,9 +219,9 @@ xchk_xref_is_owned_by(
 void
 xchk_xref_is_not_owned_by(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len,
-	struct xfs_owner_info		*oinfo)
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len,
+	struct xfs_owner_info	*oinfo)
 {
 	xchk_xref_check_owner(sc, bno, len, oinfo, false);
 }
@@ -230,11 +230,11 @@ xchk_xref_is_not_owned_by(
 void
 xchk_xref_has_no_owner(
 	struct xfs_scrub	*sc,
-	xfs_agblock_t			bno,
-	xfs_extlen_t			len)
+	xfs_agblock_t		bno,
+	xfs_extlen_t		len)
 {
-	bool				has_rmap;
-	int				error;
+	bool			has_rmap;
+	int			error;
 
 	if (!sc->sa.rmap_cur || xchk_skip_xref(sc->sm))
 		return;
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index 653a809bba34..665d4bbb17cc 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -27,9 +27,9 @@
 int
 xchk_setup_rt(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
-	int				error;
+	int			error;
 
 	error = xchk_setup_fs(sc, ip);
 	if (error)
@@ -47,13 +47,13 @@ xchk_setup_rt(
 /* Scrub a free extent record from the realtime bitmap. */
 STATIC int
 xchk_rtbitmap_rec(
-	struct xfs_trans		*tp,
-	struct xfs_rtalloc_rec		*rec,
-	void				*priv)
+	struct xfs_trans	*tp,
+	struct xfs_rtalloc_rec	*rec,
+	void			*priv)
 {
 	struct xfs_scrub	*sc = priv;
-	xfs_rtblock_t			startblock;
-	xfs_rtblock_t			blockcount;
+	xfs_rtblock_t		startblock;
+	xfs_rtblock_t		blockcount;
 
 	startblock = rec->ar_startext * tp->t_mountp->m_sb.sb_rextsize;
 	blockcount = rec->ar_extcount * tp->t_mountp->m_sb.sb_rextsize;
@@ -70,7 +70,7 @@ int
 xchk_rtbitmap(
 	struct xfs_scrub	*sc)
 {
-	int				error;
+	int			error;
 
 	/* Invoke the fork scrubber. */
 	error = xchk_metadata_inode_forks(sc);
@@ -90,10 +90,10 @@ int
 xchk_rtsummary(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_inode		*rsumip = sc->mp->m_rsumip;
-	struct xfs_inode		*old_ip = sc->ip;
-	uint				old_ilock_flags = sc->ilock_flags;
-	int				error = 0;
+	struct xfs_inode	*rsumip = sc->mp->m_rsumip;
+	struct xfs_inode	*old_ip = sc->ip;
+	uint			old_ilock_flags = sc->ilock_flags;
+	int			error = 0;
 
 	/*
 	 * We ILOCK'd the rt bitmap ip in the setup routine, now lock the
@@ -126,14 +126,14 @@ out:
 void
 xchk_xref_is_used_rt_space(
 	struct xfs_scrub	*sc,
-	xfs_rtblock_t			fsbno,
-	xfs_extlen_t			len)
+	xfs_rtblock_t		fsbno,
+	xfs_extlen_t		len)
 {
-	xfs_rtblock_t			startext;
-	xfs_rtblock_t			endext;
-	xfs_rtblock_t			extcount;
-	bool				is_free;
-	int				error;
+	xfs_rtblock_t		startext;
+	xfs_rtblock_t		endext;
+	xfs_rtblock_t		extcount;
+	bool			is_free;
+	int			error;
 
 	if (xchk_skip_xref(sc->sm))
 		return;
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index b3c6420ccae5..5956b8073e2f 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -153,7 +153,7 @@ static int
 xchk_probe(
 	struct xfs_scrub	*sc)
 {
-	int				error = 0;
+	int			error = 0;
 
 	if (xchk_should_terminate(sc, &error))
 		return error;
@@ -167,8 +167,8 @@ xchk_probe(
 STATIC int
 xchk_teardown(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip_in,
-	int				error)
+	struct xfs_inode	*ip_in,
+	int			error)
 {
 	xchk_ag_free(sc, &sc->sa);
 	if (sc->tp) {
@@ -479,7 +479,7 @@ xfs_scrub_metadata(
 	struct xfs_inode		*ip,
 	struct xfs_scrub_metadata	*sm)
 {
-	struct xfs_scrub	sc;
+	struct xfs_scrub		sc;
 	struct xfs_mount		*mp = ip->i_mount;
 	bool				try_harder = false;
 	bool				already_fixed = false;
diff --git a/fs/xfs/scrub/scrub.h b/fs/xfs/scrub/scrub.h
index 47c75d2f28da..af323b229c4b 100644
--- a/fs/xfs/scrub/scrub.h
+++ b/fs/xfs/scrub/scrub.h
@@ -36,21 +36,21 @@ struct xchk_meta_ops {
 
 /* Buffer pointers and btree cursors for an entire AG. */
 struct xchk_ag {
-	xfs_agnumber_t			agno;
-	struct xfs_perag		*pag;
+	xfs_agnumber_t		agno;
+	struct xfs_perag	*pag;
 
 	/* AG btree roots */
-	struct xfs_buf			*agf_bp;
-	struct xfs_buf			*agfl_bp;
-	struct xfs_buf			*agi_bp;
+	struct xfs_buf		*agf_bp;
+	struct xfs_buf		*agfl_bp;
+	struct xfs_buf		*agi_bp;
 
 	/* AG btrees */
-	struct xfs_btree_cur		*bno_cur;
-	struct xfs_btree_cur		*cnt_cur;
-	struct xfs_btree_cur		*ino_cur;
-	struct xfs_btree_cur		*fino_cur;
-	struct xfs_btree_cur		*rmap_cur;
-	struct xfs_btree_cur		*refc_cur;
+	struct xfs_btree_cur	*bno_cur;
+	struct xfs_btree_cur	*cnt_cur;
+	struct xfs_btree_cur	*ino_cur;
+	struct xfs_btree_cur	*fino_cur;
+	struct xfs_btree_cur	*rmap_cur;
+	struct xfs_btree_cur	*refc_cur;
 };
 
 struct xfs_scrub {
@@ -66,7 +66,7 @@ struct xfs_scrub {
 	bool				has_quotaofflock;
 
 	/* State tracking for single-AG operations. */
-	struct xchk_ag		sa;
+	struct xchk_ag			sa;
 };
 
 /* Metadata scrubbers */
@@ -115,27 +115,25 @@ xchk_quota(struct xfs_scrub *sc)
 #endif
 
 /* cross-referencing helpers */
-void xchk_xref_is_used_space(struct xfs_scrub *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_not_inode_chunk(struct xfs_scrub *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_inode_chunk(struct xfs_scrub *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_owned_by(struct xfs_scrub *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len,
-		struct xfs_owner_info *oinfo);
-void xchk_xref_is_not_owned_by(struct xfs_scrub *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len,
-		struct xfs_owner_info *oinfo);
-void xchk_xref_has_no_owner(struct xfs_scrub *sc,
-		xfs_agblock_t agbno, xfs_extlen_t len);
-void xchk_xref_is_cow_staging(struct xfs_scrub *sc,
-		xfs_agblock_t bno, xfs_extlen_t len);
-void xchk_xref_is_not_shared(struct xfs_scrub *sc,
-		xfs_agblock_t bno, xfs_extlen_t len);
+void xchk_xref_is_used_space(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_not_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_inode_chunk(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xchk_xref_is_not_owned_by(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len, struct xfs_owner_info *oinfo);
+void xchk_xref_has_no_owner(struct xfs_scrub *sc, xfs_agblock_t agbno,
+		xfs_extlen_t len);
+void xchk_xref_is_cow_staging(struct xfs_scrub *sc, xfs_agblock_t bno,
+		xfs_extlen_t len);
+void xchk_xref_is_not_shared(struct xfs_scrub *sc, xfs_agblock_t bno,
+		xfs_extlen_t len);
 #ifdef CONFIG_XFS_RT
-void xchk_xref_is_used_rt_space(struct xfs_scrub *sc,
-		xfs_rtblock_t rtbno, xfs_extlen_t len);
+void xchk_xref_is_used_rt_space(struct xfs_scrub *sc, xfs_rtblock_t rtbno,
+		xfs_extlen_t len);
 #else
 # define xchk_xref_is_used_rt_space(sc, rtbno, len) do { } while (0)
 #endif
diff --git a/fs/xfs/scrub/symlink.c b/fs/xfs/scrub/symlink.c
index 56c6347e9482..f7ebaa946999 100644
--- a/fs/xfs/scrub/symlink.c
+++ b/fs/xfs/scrub/symlink.c
@@ -27,7 +27,7 @@
 int
 xchk_setup_symlink(
 	struct xfs_scrub	*sc,
-	struct xfs_inode		*ip)
+	struct xfs_inode	*ip)
 {
 	/* Allocate the buffer without the inode lock held. */
 	sc->buf = kmem_zalloc_large(XFS_SYMLINK_MAXLEN + 1, KM_SLEEP);
@@ -43,10 +43,10 @@ int
 xchk_symlink(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_inode		*ip = sc->ip;
-	struct xfs_ifork		*ifp;
-	loff_t				len;
-	int				error = 0;
+	struct xfs_inode	*ip = sc->ip;
+	struct xfs_ifork	*ifp;
+	loff_t			len;
+	int			error = 0;
 
 	if (!S_ISLNK(VFS_I(ip)->i_mode))
 		return -ENOENT;
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 1ef1202a1e45..96feaf8dcdec 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -23,8 +23,8 @@
 /* Figure out which block the btree cursor was pointing to. */
 static inline xfs_fsblock_t
 xchk_btree_cur_fsbno(
-	struct xfs_btree_cur		*cur,
-	int				level)
+	struct xfs_btree_cur	*cur,
+	int			level)
 {
 	if (level < cur->bc_nlevels && cur->bc_bufs[level])
 		return XFS_DADDR_TO_FSB(cur->bc_mp, cur->bc_bufs[level]->b_bn);
-- 
cgit v1.2.3


From 2e9e6481e2a78de3a85083beccfbf6eda2689922 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 19 Jul 2018 12:29:13 -0700
Subject: xfs: detect and fix bad summary counts at mount

Filippo Giunchedi complained that xfs doesn't even perform basic sanity
checks of the fs summary counters at mount time.  Therefore, recalculate
the summary counters from the AGFs after log recovery if the counts were
bad (or we had to recover the fs).  Enhance the recalculation routine to
fail the mount entirely if the new values are also obviously incorrect.

We use a mount state flag to record the "bad summary count" state so
that the (subsequent) online fsck patches can detect subtlely incorrect
counts and set the flag; clear it userspace asks for a repair; or force
a recalculation at the next mount if nobody fixes it by unmount time.

Reported-by: Filippo Giunchedi <fgiunchedi@wikimedia.org>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_sb.c | 21 +++++++++++--
 fs/xfs/xfs_mount.c     | 80 ++++++++++++++++++++++++++++++++++----------------
 fs/xfs/xfs_mount.h     |  1 +
 3 files changed, 73 insertions(+), 29 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 350119eeaecb..b3ad15956366 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -804,6 +804,7 @@ xfs_initialize_perag_data(
 	uint64_t	bfree = 0;
 	uint64_t	bfreelst = 0;
 	uint64_t	btree = 0;
+	uint64_t	fdblocks;
 	int		error;
 
 	for (index = 0; index < agcount; index++) {
@@ -827,17 +828,31 @@ xfs_initialize_perag_data(
 		btree += pag->pagf_btreeblks;
 		xfs_perag_put(pag);
 	}
+	fdblocks = bfree + bfreelst + btree;
+
+	/*
+	 * If the new summary counts are obviously incorrect, fail the
+	 * mount operation because that implies the AGFs are also corrupt.
+	 * Clear BAD_SUMMARY so that we don't unmount with a dirty log, which
+	 * will prevent xfs_repair from fixing anything.
+	 */
+	if (fdblocks > sbp->sb_dblocks || ifree > ialloc) {
+		xfs_alert(mp, "AGF corruption. Please run xfs_repair.");
+		error = -EFSCORRUPTED;
+		goto out;
+	}
 
 	/* Overwrite incore superblock counters with just-read data */
 	spin_lock(&mp->m_sb_lock);
 	sbp->sb_ifree = ifree;
 	sbp->sb_icount = ialloc;
-	sbp->sb_fdblocks = bfree + bfreelst + btree;
+	sbp->sb_fdblocks = fdblocks;
 	spin_unlock(&mp->m_sb_lock);
 
 	xfs_reinit_percpu_counters(mp);
-
-	return 0;
+out:
+	mp->m_flags &= ~XFS_MOUNT_BAD_SUMMARY;
+	return error;
 }
 
 /*
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index a3378252baa1..60462c35ad4b 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -606,6 +606,56 @@ xfs_default_resblks(xfs_mount_t *mp)
 	return resblks;
 }
 
+/* Ensure the summary counts are correct. */
+STATIC int
+xfs_check_summary_counts(
+	struct xfs_mount	*mp)
+{
+	/*
+	 * The AG0 superblock verifier rejects in-progress filesystems,
+	 * so we should never see the flag set this far into mounting.
+	 */
+	if (mp->m_sb.sb_inprogress) {
+		xfs_err(mp, "sb_inprogress set after log recovery??");
+		WARN_ON(1);
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Now the log is mounted, we know if it was an unclean shutdown or
+	 * not. If it was, with the first phase of recovery has completed, we
+	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
+	 * but they are recovered transactionally in the second recovery phase
+	 * later.
+	 *
+	 * If the log was clean when we mounted, we can check the summary
+	 * counters.  If any of them are obviously incorrect, we can recompute
+	 * them from the AGF headers in the next step.
+	 */
+	if (XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
+	    (mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks ||
+	     mp->m_sb.sb_ifree > mp->m_sb.sb_icount))
+		mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+
+	/*
+	 * We can safely re-initialise incore superblock counters from the
+	 * per-ag data. These may not be correct if the filesystem was not
+	 * cleanly unmounted, so we waited for recovery to finish before doing
+	 * this.
+	 *
+	 * If the filesystem was cleanly unmounted or the previous check did
+	 * not flag anything weird, then we can trust the values in the
+	 * superblock to be correct and we don't need to do anything here.
+	 * Otherwise, recalculate the summary counters.
+	 */
+	if ((!xfs_sb_version_haslazysbcount(&mp->m_sb) ||
+	     XFS_LAST_UNMOUNT_WAS_CLEAN(mp)) &&
+	    !(mp->m_flags & XFS_MOUNT_BAD_SUMMARY))
+		return 0;
+
+	return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount);
+}
+
 /*
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
@@ -831,32 +881,10 @@ xfs_mountfs(
 		goto out_fail_wait;
 	}
 
-	/*
-	 * Now the log is mounted, we know if it was an unclean shutdown or
-	 * not. If it was, with the first phase of recovery has completed, we
-	 * have consistent AG blocks on disk. We have not recovered EFIs yet,
-	 * but they are recovered transactionally in the second recovery phase
-	 * later.
-	 *
-	 * Hence we can safely re-initialise incore superblock counters from
-	 * the per-ag data. These may not be correct if the filesystem was not
-	 * cleanly unmounted, so we need to wait for recovery to finish before
-	 * doing this.
-	 *
-	 * If the filesystem was cleanly unmounted, then we can trust the
-	 * values in the superblock to be correct and we don't need to do
-	 * anything here.
-	 *
-	 * If we are currently making the filesystem, the initialisation will
-	 * fail as the perag data is in an undefined state.
-	 */
-	if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
-	    !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
-	     !mp->m_sb.sb_inprogress) {
-		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
-		if (error)
-			goto out_log_dealloc;
-	}
+	/* Make sure the summary counts are ok. */
+	error = xfs_check_summary_counts(mp);
+	if (error)
+		goto out_log_dealloc;
 
 	/*
 	 * Get and sanity-check the root inode.
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 245349d1e23f..f08907db9c61 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -202,6 +202,7 @@ typedef struct xfs_mount {
 						   must be synchronous except
 						   for space allocations */
 #define XFS_MOUNT_UNMOUNTING	(1ULL << 1)	/* filesystem is unmounting */
+#define XFS_MOUNT_BAD_SUMMARY	(1ULL << 2)	/* summary counters are bad */
 #define XFS_MOUNT_WAS_CLEAN	(1ULL << 3)
 #define XFS_MOUNT_FS_SHUTDOWN	(1ULL << 4)	/* atomic stop of all filesystem
 						   operations, typically for
-- 
cgit v1.2.3


From 53235f22151ea7229e1251e46e68098bcf74922d Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 20 Jul 2018 09:28:39 -0700
Subject: xfs: refactor unmount record write

Refactor the writing of the unmount record into a separate helper.  No
functionality changes.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_log_format.h |  13 ++++
 fs/xfs/xfs_log.c               | 131 ++++++++++++++++++++++-------------------
 2 files changed, 82 insertions(+), 62 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 79bb79853c9f..e5f97c69b320 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -77,6 +77,19 @@ static inline uint xlog_get_cycle(char *ptr)
 
 #define XLOG_UNMOUNT_TYPE	0x556e	/* Un for Unmount */
 
+/*
+ * Log item for unmount records.
+ *
+ * The unmount record used to have a string "Unmount filesystem--" in the
+ * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
+ * We just write the magic number now; see xfs_log_unmount_write.
+ */
+struct xfs_unmount_log_format {
+	uint16_t	magic;	/* XLOG_UNMOUNT_TYPE */
+	uint16_t	pad1;
+	uint32_t	pad2;	/* may as well make it 64 bits */
+};
+
 /* Region types for iovec's i_type */
 #define XLOG_REG_TYPE_BFORMAT		1
 #define XLOG_REG_TYPE_BCHUNK		2
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 5e56f3b93d4b..bac586cbc54e 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -826,6 +826,74 @@ xfs_log_mount_cancel(
  * deallocation must not be done until source-end.
  */
 
+/* Actually write the unmount record to disk. */
+static void
+xfs_log_write_unmount_record(
+	struct xfs_mount	*mp)
+{
+	/* the data section must be 32 bit size aligned */
+	struct xfs_unmount_log_format magic = {
+		.magic = XLOG_UNMOUNT_TYPE,
+	};
+	struct xfs_log_iovec reg = {
+		.i_addr = &magic,
+		.i_len = sizeof(magic),
+		.i_type = XLOG_REG_TYPE_UNMOUNT,
+	};
+	struct xfs_log_vec vec = {
+		.lv_niovecs = 1,
+		.lv_iovecp = &reg,
+	};
+	struct xlog		*log = mp->m_log;
+	struct xlog_in_core	*iclog;
+	struct xlog_ticket	*tic = NULL;
+	xfs_lsn_t		lsn;
+	int			error;
+
+	error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
+	if (error)
+		goto out_err;
+
+	/* remove inited flag, and account for space used */
+	tic->t_flags = 0;
+	tic->t_curr_res -= sizeof(magic);
+	error = xlog_write(log, &vec, tic, &lsn, NULL, XLOG_UNMOUNT_TRANS);
+	/*
+	 * At this point, we're umounting anyway, so there's no point in
+	 * transitioning log state to IOERROR. Just continue...
+	 */
+out_err:
+	if (error)
+		xfs_alert(mp, "%s: unmount record failed", __func__);
+
+	spin_lock(&log->l_icloglock);
+	iclog = log->l_iclog;
+	atomic_inc(&iclog->ic_refcnt);
+	xlog_state_want_sync(log, iclog);
+	spin_unlock(&log->l_icloglock);
+	error = xlog_state_release_iclog(log, iclog);
+
+	spin_lock(&log->l_icloglock);
+	switch (iclog->ic_state) {
+	default:
+		if (!XLOG_FORCED_SHUTDOWN(log)) {
+			xlog_wait(&iclog->ic_force_wait, &log->l_icloglock);
+			break;
+		}
+		/* fall through */
+	case XLOG_STATE_ACTIVE:
+	case XLOG_STATE_DIRTY:
+		spin_unlock(&log->l_icloglock);
+		break;
+	}
+
+	if (tic) {
+		trace_xfs_log_umount_write(log, tic);
+		xlog_ungrant_log_space(log, tic);
+		xfs_log_ticket_put(tic);
+	}
+}
+
 /*
  * Unmount record used to have a string "Unmount filesystem--" in the
  * data section where the "Un" was really a magic number (XLOG_UNMOUNT_TYPE).
@@ -842,8 +910,6 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 #ifdef DEBUG
 	xlog_in_core_t	 *first_iclog;
 #endif
-	xlog_ticket_t	*tic = NULL;
-	xfs_lsn_t	 lsn;
 	int		 error;
 
 	/*
@@ -870,66 +936,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 	} while (iclog != first_iclog);
 #endif
 	if (! (XLOG_FORCED_SHUTDOWN(log))) {
-		error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
-		if (!error) {
-			/* the data section must be 32 bit size aligned */
-			struct {
-			    uint16_t magic;
-			    uint16_t pad1;
-			    uint32_t pad2; /* may as well make it 64 bits */
-			} magic = {
-				.magic = XLOG_UNMOUNT_TYPE,
-			};
-			struct xfs_log_iovec reg = {
-				.i_addr = &magic,
-				.i_len = sizeof(magic),
-				.i_type = XLOG_REG_TYPE_UNMOUNT,
-			};
-			struct xfs_log_vec vec = {
-				.lv_niovecs = 1,
-				.lv_iovecp = &reg,
-			};
-
-			/* remove inited flag, and account for space used */
-			tic->t_flags = 0;
-			tic->t_curr_res -= sizeof(magic);
-			error = xlog_write(log, &vec, tic, &lsn,
-					   NULL, XLOG_UNMOUNT_TRANS);
-			/*
-			 * At this point, we're umounting anyway,
-			 * so there's no point in transitioning log state
-			 * to IOERROR. Just continue...
-			 */
-		}
-
-		if (error)
-			xfs_alert(mp, "%s: unmount record failed", __func__);
-
-
-		spin_lock(&log->l_icloglock);
-		iclog = log->l_iclog;
-		atomic_inc(&iclog->ic_refcnt);
-		xlog_state_want_sync(log, iclog);
-		spin_unlock(&log->l_icloglock);
-		error = xlog_state_release_iclog(log, iclog);
-
-		spin_lock(&log->l_icloglock);
-		if (!(iclog->ic_state == XLOG_STATE_ACTIVE ||
-		      iclog->ic_state == XLOG_STATE_DIRTY)) {
-			if (!XLOG_FORCED_SHUTDOWN(log)) {
-				xlog_wait(&iclog->ic_force_wait,
-							&log->l_icloglock);
-			} else {
-				spin_unlock(&log->l_icloglock);
-			}
-		} else {
-			spin_unlock(&log->l_icloglock);
-		}
-		if (tic) {
-			trace_xfs_log_umount_write(log, tic);
-			xlog_ungrant_log_space(log, tic);
-			xfs_log_ticket_put(tic);
-		}
+		xfs_log_write_unmount_record(mp);
 	} else {
 		/*
 		 * We're already in forced_shutdown mode, couldn't
-- 
cgit v1.2.3


From f467cad95f5e3814fda408dea76eb962ab19685d Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Fri, 20 Jul 2018 09:28:40 -0700
Subject: xfs: force summary counter recalc at next mount

Use the "bad summary count" mount flag from the previous patch to skip
writing the unmount record to force log recovery at the next mount,
which will recalculate the summary counters for us.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_errortag.h |  4 +++-
 fs/xfs/xfs_error.c           |  3 +++
 fs/xfs/xfs_log.c             | 16 +++++++++++++++-
 fs/xfs/xfs_mount.c           | 13 +++++++++++++
 fs/xfs/xfs_mount.h           |  1 +
 5 files changed, 35 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_errortag.h b/fs/xfs/libxfs/xfs_errortag.h
index b9974e7a8e6e..66077a105cbb 100644
--- a/fs/xfs/libxfs/xfs_errortag.h
+++ b/fs/xfs/libxfs/xfs_errortag.h
@@ -53,7 +53,8 @@
 #define XFS_ERRTAG_LOG_ITEM_PIN				30
 #define XFS_ERRTAG_BUF_LRU_REF				31
 #define XFS_ERRTAG_FORCE_SCRUB_REPAIR			32
-#define XFS_ERRTAG_MAX					33
+#define XFS_ERRTAG_FORCE_SUMMARY_RECALC			33
+#define XFS_ERRTAG_MAX					34
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -91,5 +92,6 @@
 #define XFS_RANDOM_LOG_ITEM_PIN				1
 #define XFS_RANDOM_BUF_LRU_REF				2
 #define XFS_RANDOM_FORCE_SCRUB_REPAIR			1
+#define XFS_RANDOM_FORCE_SUMMARY_RECALC			1
 
 #endif /* __XFS_ERRORTAG_H_ */
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index 0470114a8d80..9866f542e77b 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -50,6 +50,7 @@ static unsigned int xfs_errortag_random_default[] = {
 	XFS_RANDOM_LOG_ITEM_PIN,
 	XFS_RANDOM_BUF_LRU_REF,
 	XFS_RANDOM_FORCE_SCRUB_REPAIR,
+	XFS_RANDOM_FORCE_SUMMARY_RECALC,
 };
 
 struct xfs_errortag_attr {
@@ -157,6 +158,7 @@ XFS_ERRORTAG_ATTR_RW(log_bad_crc,	XFS_ERRTAG_LOG_BAD_CRC);
 XFS_ERRORTAG_ATTR_RW(log_item_pin,	XFS_ERRTAG_LOG_ITEM_PIN);
 XFS_ERRORTAG_ATTR_RW(buf_lru_ref,	XFS_ERRTAG_BUF_LRU_REF);
 XFS_ERRORTAG_ATTR_RW(force_repair,	XFS_ERRTAG_FORCE_SCRUB_REPAIR);
+XFS_ERRORTAG_ATTR_RW(bad_summary,	XFS_ERRTAG_FORCE_SUMMARY_RECALC);
 
 static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(noerror),
@@ -192,6 +194,7 @@ static struct attribute *xfs_errortag_attrs[] = {
 	XFS_ERRORTAG_ATTR_LIST(log_item_pin),
 	XFS_ERRORTAG_ATTR_LIST(buf_lru_ref),
 	XFS_ERRORTAG_ATTR_LIST(force_repair),
+	XFS_ERRORTAG_ATTR_LIST(bad_summary),
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index bac586cbc54e..fd10b1426382 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -848,16 +848,30 @@ xfs_log_write_unmount_record(
 	struct xlog_in_core	*iclog;
 	struct xlog_ticket	*tic = NULL;
 	xfs_lsn_t		lsn;
+	uint			flags = XLOG_UNMOUNT_TRANS;
 	int			error;
 
 	error = xfs_log_reserve(mp, 600, 1, &tic, XFS_LOG, 0);
 	if (error)
 		goto out_err;
 
+	/*
+	 * If we think the summary counters are bad, clear the unmount header
+	 * flag in the unmount record so that the summary counters will be
+	 * recalculated during log recovery at next mount.  Refer to
+	 * xlog_check_unmount_rec for more details.
+	 */
+	if (XFS_TEST_ERROR((mp->m_flags & XFS_MOUNT_BAD_SUMMARY), mp,
+			XFS_ERRTAG_FORCE_SUMMARY_RECALC)) {
+		xfs_alert(mp, "%s: will fix summary counters at next mount",
+				__func__);
+		flags &= ~XLOG_UNMOUNT_TRANS;
+	}
+
 	/* remove inited flag, and account for space used */
 	tic->t_flags = 0;
 	tic->t_curr_res -= sizeof(magic);
-	error = xlog_write(log, &vec, tic, &lsn, NULL, XLOG_UNMOUNT_TRANS);
+	error = xlog_write(log, &vec, tic, &lsn, NULL, flags);
 	/*
 	 * At this point, we're umounting anyway, so there's no point in
 	 * transitioning log state to IOERROR. Just continue...
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 60462c35ad4b..4fb361cde32a 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1423,3 +1423,16 @@ xfs_dev_is_read_only(
 	}
 	return 0;
 }
+
+/* Force the summary counters to be recalculated at next mount. */
+void
+xfs_force_summary_recalc(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_sb_version_haslazysbcount(&mp->m_sb))
+		return;
+
+	spin_lock(&mp->m_sb_lock);
+	mp->m_flags |= XFS_MOUNT_BAD_SUMMARY;
+	spin_unlock(&mp->m_sb_lock);
+}
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index f08907db9c61..540353a51478 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -435,5 +435,6 @@ int	xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
 
 struct xfs_error_cfg * xfs_error_get_cfg(struct xfs_mount *mp,
 		int error_class, int error);
+void xfs_force_summary_recalc(struct xfs_mount *mp);
 
 #endif	/* __XFS_MOUNT_H__ */
-- 
cgit v1.2.3


From a5f3ea54f3ccd881562d47f34b4a83441796bf19 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 23 Jul 2018 11:16:58 +0300
Subject: net: bridge: add support for raw sysfs port options

This patch adds a new alternative store callback for port sysfs options
which takes a raw value (buf) and can use it directly. It is needed for the
backup port sysfs support since we have to pass the device by its name.

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_sysfs_if.c | 56 ++++++++++++++++++++++++++++++++++++------------
 1 file changed, 42 insertions(+), 14 deletions(-)

diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index ab4c7f8adf68..4ac940067754 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -25,6 +25,15 @@ struct brport_attribute {
 	struct attribute	attr;
 	ssize_t (*show)(struct net_bridge_port *, char *);
 	int (*store)(struct net_bridge_port *, unsigned long);
+	int (*store_raw)(struct net_bridge_port *, char *);
+};
+
+#define BRPORT_ATTR_RAW(_name, _mode, _show, _store)			\
+const struct brport_attribute brport_attr_##_name = {			\
+	.attr		= {.name = __stringify(_name),			\
+			   .mode = _mode },				\
+	.show		= _show,					\
+	.store_raw	= _store,					\
 };
 
 #define BRPORT_ATTR(_name, _mode, _show, _store)		\
@@ -269,27 +278,46 @@ static ssize_t brport_store(struct kobject *kobj,
 	struct brport_attribute *brport_attr = to_brport_attr(attr);
 	struct net_bridge_port *p = kobj_to_brport(kobj);
 	ssize_t ret = -EINVAL;
-	char *endp;
 	unsigned long val;
+	char *endp;
 
 	if (!ns_capable(dev_net(p->dev)->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 
-	val = simple_strtoul(buf, &endp, 0);
-	if (endp != buf) {
-		if (!rtnl_trylock())
-			return restart_syscall();
-		if (p->dev && p->br && brport_attr->store) {
-			spin_lock_bh(&p->br->lock);
-			ret = brport_attr->store(p, val);
-			spin_unlock_bh(&p->br->lock);
-			if (!ret) {
-				br_ifinfo_notify(RTM_NEWLINK, NULL, p);
-				ret = count;
-			}
+	if (!rtnl_trylock())
+		return restart_syscall();
+
+	if (!p->dev || !p->br)
+		goto out_unlock;
+
+	if (brport_attr->store_raw) {
+		char *buf_copy;
+
+		buf_copy = kstrndup(buf, count, GFP_KERNEL);
+		if (!buf_copy) {
+			ret = -ENOMEM;
+			goto out_unlock;
 		}
-		rtnl_unlock();
+		spin_lock_bh(&p->br->lock);
+		ret = brport_attr->store_raw(p, buf_copy);
+		spin_unlock_bh(&p->br->lock);
+		kfree(buf_copy);
+	} else if (brport_attr->store) {
+		val = simple_strtoul(buf, &endp, 0);
+		if (endp == buf)
+			goto out_unlock;
+		spin_lock_bh(&p->br->lock);
+		ret = brport_attr->store(p, val);
+		spin_unlock_bh(&p->br->lock);
 	}
+
+	if (!ret) {
+		br_ifinfo_notify(RTM_NEWLINK, NULL, p);
+		ret = count;
+	}
+out_unlock:
+	rtnl_unlock();
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From 2756f68c314917d03eb348084edb08bb929139d9 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Date: Mon, 23 Jul 2018 11:16:59 +0300
Subject: net: bridge: add support for backup port

This patch adds a new port attribute - IFLA_BRPORT_BACKUP_PORT, which
allows to set a backup port to be used for known unicast traffic if the
port has gone carrier down. The backup pointer is rcu protected and set
only under RTNL, a counter is maintained so when deleting a port we know
how many other ports reference it as a backup and we remove it from all.
Also the pointer is in the first cache line which is hot at the time of
the check and thus in the common case we only add one more test.
The backup port will be used only for the non-flooding case since
it's a part of the bridge and the flooded packets will be forwarded to it
anyway. To remove the forwarding just send a 0/non-existing backup port.
This is used to avoid numerous scalability problems when using MLAG most
notably if we have thousands of fdbs one would need to change all of them
on port carrier going down which takes too long and causes a storm of fdb
notifications (and again when the port comes back up). In a Multi-chassis
Link Aggregation setup usually hosts are connected to two different
switches which act as a single logical switch. Those switches usually have
a control and backup link between them called peerlink which might be used
for communication in case a host loses connectivity to one of them.
We need a fast way to failover in case a host port goes down and currently
none of the solutions (like bond) cannot fulfill the requirements because
the participating ports are actually the "master" devices and must have the
same peerlink as their backup interface and at the same time all of them
must participate in the bridge device. As Roopa noted it's normal practice
in routing called fast re-route where a precalculated backup path is used
when the main one is down.
Another use case of this is with EVPN, having a single vxlan device which
is backup of every port. Due to the nature of master devices it's not
currently possible to use one device as a backup for many and still have
all of them participate in the bridge (which is master itself).
More detailed information about MLAG is available at the link below.
https://docs.cumulusnetworks.com/display/DOCS/Multi-Chassis+Link+Aggregation+-+MLAG

Further explanation and a diagram by Roopa:
Two switches acting in a MLAG pair are connected by the peerlink
interface which is a bridge port.

the config on one of the switches looks like the below. The other
switch also has a similar config.
eth0 is connected to one port on the server. And the server is
connected to both switches.

br0 -- team0---eth0
      |
      -- switch-peerlink

Signed-off-by: Nikolay Aleksandrov <nikolay@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h |  1 +
 net/bridge/br_forward.c      | 16 ++++++++++++-
 net/bridge/br_if.c           | 53 ++++++++++++++++++++++++++++++++++++++++++++
 net/bridge/br_netlink.c      | 30 ++++++++++++++++++++++++-
 net/bridge/br_private.h      |  3 +++
 net/bridge/br_sysfs_if.c     | 33 +++++++++++++++++++++++++++
 6 files changed, 134 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 8759cfb8aa2e..01b5069a73a5 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -334,6 +334,7 @@ enum {
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
+	IFLA_BRPORT_BACKUP_PORT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
index 9019f326fe81..5372e2042adf 100644
--- a/net/bridge/br_forward.c
+++ b/net/bridge/br_forward.c
@@ -142,7 +142,20 @@ static int deliver_clone(const struct net_bridge_port *prev,
 void br_forward(const struct net_bridge_port *to,
 		struct sk_buff *skb, bool local_rcv, bool local_orig)
 {
-	if (to && should_deliver(to, skb)) {
+	if (unlikely(!to))
+		goto out;
+
+	/* redirect to backup link if the destination port is down */
+	if (rcu_access_pointer(to->backup_port) && !netif_carrier_ok(to->dev)) {
+		struct net_bridge_port *backup_port;
+
+		backup_port = rcu_dereference(to->backup_port);
+		if (unlikely(!backup_port))
+			goto out;
+		to = backup_port;
+	}
+
+	if (should_deliver(to, skb)) {
 		if (local_rcv)
 			deliver_clone(to, skb, local_orig);
 		else
@@ -150,6 +163,7 @@ void br_forward(const struct net_bridge_port *to,
 		return;
 	}
 
+out:
 	if (!local_rcv)
 		kfree_skb(skb);
 }
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index e7c8d55212aa..0363f1bdc401 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -170,6 +170,58 @@ void br_manage_promisc(struct net_bridge *br)
 	}
 }
 
+int nbp_backup_change(struct net_bridge_port *p,
+		      struct net_device *backup_dev)
+{
+	struct net_bridge_port *old_backup = rtnl_dereference(p->backup_port);
+	struct net_bridge_port *backup_p = NULL;
+
+	ASSERT_RTNL();
+
+	if (backup_dev) {
+		if (!br_port_exists(backup_dev))
+			return -ENOENT;
+
+		backup_p = br_port_get_rtnl(backup_dev);
+		if (backup_p->br != p->br)
+			return -EINVAL;
+	}
+
+	if (p == backup_p)
+		return -EINVAL;
+
+	if (old_backup == backup_p)
+		return 0;
+
+	/* if the backup link is already set, clear it */
+	if (old_backup)
+		old_backup->backup_redirected_cnt--;
+
+	if (backup_p)
+		backup_p->backup_redirected_cnt++;
+	rcu_assign_pointer(p->backup_port, backup_p);
+
+	return 0;
+}
+
+static void nbp_backup_clear(struct net_bridge_port *p)
+{
+	nbp_backup_change(p, NULL);
+	if (p->backup_redirected_cnt) {
+		struct net_bridge_port *cur_p;
+
+		list_for_each_entry(cur_p, &p->br->port_list, list) {
+			struct net_bridge_port *backup_p;
+
+			backup_p = rtnl_dereference(cur_p->backup_port);
+			if (backup_p == p)
+				nbp_backup_change(cur_p, NULL);
+		}
+	}
+
+	WARN_ON(rcu_access_pointer(p->backup_port) || p->backup_redirected_cnt);
+}
+
 static void nbp_update_port_count(struct net_bridge *br)
 {
 	struct net_bridge_port *p;
@@ -295,6 +347,7 @@ static void del_nbp(struct net_bridge_port *p)
 	nbp_vlan_flush(p);
 	br_fdb_delete_by_port(br, p, 0, 1);
 	switchdev_deferred_process();
+	nbp_backup_clear(p);
 
 	nbp_update_port_count(br);
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 9f5eb05b0373..ec2b58a09f76 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -169,13 +169,15 @@ static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask)
 		+ nla_total_size(1) /* IFLA_OPERSTATE */
 		+ nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */
 		+ nla_total_size(br_get_link_af_size_filtered(dev,
-				 filter_mask)); /* IFLA_AF_SPEC */
+				 filter_mask)) /* IFLA_AF_SPEC */
+		+ nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */
 }
 
 static int br_port_fill_attrs(struct sk_buff *skb,
 			      const struct net_bridge_port *p)
 {
 	u8 mode = !!(p->flags & BR_HAIRPIN_MODE);
+	struct net_bridge_port *backup_p;
 	u64 timerval;
 
 	if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) ||
@@ -237,6 +239,14 @@ static int br_port_fill_attrs(struct sk_buff *skb,
 		return -EMSGSIZE;
 #endif
 
+	/* we might be called only with br->lock */
+	rcu_read_lock();
+	backup_p = rcu_dereference(p->backup_port);
+	if (backup_p)
+		nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT,
+			    backup_p->dev->ifindex);
+	rcu_read_unlock();
+
 	return 0;
 }
 
@@ -663,6 +673,7 @@ static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = {
 	[IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 },
 	[IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 },
 	[IFLA_BRPORT_ISOLATED]	= { .type = NLA_U8 },
+	[IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 },
 };
 
 /* Change the state of the port and notify spanning tree */
@@ -817,6 +828,23 @@ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[])
 	if (err)
 		return err;
 
+	if (tb[IFLA_BRPORT_BACKUP_PORT]) {
+		struct net_device *backup_dev = NULL;
+		u32 backup_ifindex;
+
+		backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]);
+		if (backup_ifindex) {
+			backup_dev = __dev_get_by_index(dev_net(p->dev),
+							backup_ifindex);
+			if (!backup_dev)
+				return -ENOENT;
+		}
+
+		err = nbp_backup_change(p, backup_dev);
+		if (err)
+			return err;
+	}
+
 	br_port_flags_change(p, old_flags ^ p->flags);
 	return 0;
 }
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index cf0005d2a4d0..11ed2029985f 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -237,6 +237,7 @@ struct net_bridge_port {
 #ifdef CONFIG_BRIDGE_VLAN_FILTERING
 	struct net_bridge_vlan_group	__rcu *vlgrp;
 #endif
+	struct net_bridge_port		__rcu *backup_port;
 
 	/* STP */
 	u8				priority;
@@ -281,6 +282,7 @@ struct net_bridge_port {
 	int				offload_fwd_mark;
 #endif
 	u16				group_fwd_mask;
+	u16				backup_redirected_cnt;
 };
 
 #define kobj_to_brport(obj)	container_of(obj, struct net_bridge_port, kobj)
@@ -597,6 +599,7 @@ netdev_features_t br_features_recompute(struct net_bridge *br,
 					netdev_features_t features);
 void br_port_flags_change(struct net_bridge_port *port, unsigned long mask);
 void br_manage_promisc(struct net_bridge *br);
+int nbp_backup_change(struct net_bridge_port *p, struct net_device *backup_dev);
 
 /* br_input.c */
 int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/net/bridge/br_sysfs_if.c b/net/bridge/br_sysfs_if.c
index 4ac940067754..7c87a2fe5248 100644
--- a/net/bridge/br_sysfs_if.c
+++ b/net/bridge/br_sysfs_if.c
@@ -191,6 +191,38 @@ static int store_group_fwd_mask(struct net_bridge_port *p,
 static BRPORT_ATTR(group_fwd_mask, 0644, show_group_fwd_mask,
 		   store_group_fwd_mask);
 
+static ssize_t show_backup_port(struct net_bridge_port *p, char *buf)
+{
+	struct net_bridge_port *backup_p;
+	int ret = 0;
+
+	rcu_read_lock();
+	backup_p = rcu_dereference(p->backup_port);
+	if (backup_p)
+		ret = sprintf(buf, "%s\n", backup_p->dev->name);
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int store_backup_port(struct net_bridge_port *p, char *buf)
+{
+	struct net_device *backup_dev = NULL;
+	char *nl = strchr(buf, '\n');
+
+	if (nl)
+		*nl = '\0';
+
+	if (strlen(buf) > 0) {
+		backup_dev = __dev_get_by_name(dev_net(p->dev), buf);
+		if (!backup_dev)
+			return -ENOENT;
+	}
+
+	return nbp_backup_change(p, backup_dev);
+}
+static BRPORT_ATTR_RAW(backup_port, 0644, show_backup_port, store_backup_port);
+
 BRPORT_ATTR_FLAG(hairpin_mode, BR_HAIRPIN_MODE);
 BRPORT_ATTR_FLAG(bpdu_guard, BR_BPDU_GUARD);
 BRPORT_ATTR_FLAG(root_block, BR_ROOT_BLOCK);
@@ -254,6 +286,7 @@ static const struct brport_attribute *brport_attrs[] = {
 	&brport_attr_group_fwd_mask,
 	&brport_attr_neigh_suppress,
 	&brport_attr_isolated,
+	&brport_attr_backup_port,
 	NULL
 };
 
-- 
cgit v1.2.3


From 7fa41efac14ffbe8db7660ad2da3928969d10caf Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 23 Jul 2018 16:33:19 +0800
Subject: ipv6: sr: Use kmemdup instead of duplicating it in parse_nla_srh

Replace calls to kmalloc followed by a memcpy with a direct call to
kmemdup.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/seg6_local.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index cd6e4cab63f6..e1025b493a18 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -637,12 +637,10 @@ static int parse_nla_srh(struct nlattr **attrs, struct seg6_local_lwt *slwt)
 	if (!seg6_validate_srh(srh, len))
 		return -EINVAL;
 
-	slwt->srh = kmalloc(len, GFP_KERNEL);
+	slwt->srh = kmemdup(srh, len, GFP_KERNEL);
 	if (!slwt->srh)
 		return -ENOMEM;
 
-	memcpy(slwt->srh, srh, len);
-
 	slwt->headroom += len;
 
 	return 0;
-- 
cgit v1.2.3


From 9a2ad3623868752e4f4d0a04a4dc43d5fcde07ce Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 23 Jul 2018 12:33:08 +0200
Subject: selftests: forwarding: gre_multipath: Drop IPv6 tests

Support for device-only IPv6 multipath next hops was dropped in
commit 33bd5ac54dc4 ("net/ipv6: Revert attempt to simplify route replace
and append") and as of commit b5d2d75e079a ("net/ipv6: Do not allow
device only routes via the multipath API"), attempts to add a next hop
like that yield an explicit diagnostic.

Correspondingly, drop the IPv6 parts of GRE multipath test that are
supposed to test that code.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/gre_multipath.sh      | 113 ++-------------------
 1 file changed, 6 insertions(+), 107 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh
index 982cc8c23200..3b1e047f7617 100755
--- a/tools/testing/selftests/net/forwarding/gre_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh
@@ -8,14 +8,12 @@
 # | H1                      |
 # |               $h1 +     |
 # |      192.0.2.1/28 |     |
-# |  2001:db8:1::1/64 |     |
 # +-------------------|-----+
 #                     |
 # +-------------------|------------------------+
 # | SW1               |                        |
 # |              $ol1 +                        |
 # |      192.0.2.2/28                          |
-# |  2001:db8:1::2/64                          |
 # |                                            |
 # |  + g1a (gre)          + g1b (gre)          |
 # |    loc=192.0.2.65       loc=192.0.2.81     |
@@ -49,22 +47,17 @@
 # |                                            |
 # |              $ol2 +                        |
 # |     192.0.2.17/28 |                        |
-# |  2001:db8:2::1/64 |                        |
 # +-------------------|------------------------+
 #                     |
 # +-------------------|-----+
 # | H2                |     |
 # |               $h2 +     |
 # |     192.0.2.18/28       |
-# |  2001:db8:2::2/64       |
 # +-------------------------+
 
 ALL_TESTS="
 	ping_ipv4
-	ping_ipv6
 	multipath_ipv4
-	multipath_ipv6
-	multipath_ipv6_l4
 "
 
 NUM_NETIFS=6
@@ -74,19 +67,17 @@ h1_create()
 {
 	simple_if_init $h1 192.0.2.1/28 2001:db8:1::1/64
 	ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
-	ip route add vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
 }
 
 h1_destroy()
 {
-	ip route del vrf v$h1 2001:db8:2::/64 via 2001:db8:1::2
 	ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
 	simple_if_fini $h1 192.0.2.1/28
 }
 
 sw1_create()
 {
-	simple_if_init $ol1 192.0.2.2/28 2001:db8:1::2/64
+	simple_if_init $ol1 192.0.2.2/28
 	__simple_if_init $ul1 v$ol1
 	vlan_create $ul1 111 v$ol1 192.0.2.129/28
 	vlan_create $ul1 222 v$ol1 192.0.2.145/28
@@ -102,9 +93,6 @@ sw1_create()
 	ip route add vrf v$ol1 192.0.2.16/28 \
 	   nexthop dev g1a \
 	   nexthop dev g1b
-	ip route add vrf v$ol1 2001:db8:2::/64 \
-	   nexthop dev g1a \
-	   nexthop dev g1b
 
 	tc qdisc add dev $ul1 clsact
 	tc filter add dev $ul1 egress pref 111 prot 802.1q \
@@ -117,7 +105,6 @@ sw1_destroy()
 {
 	tc qdisc del dev $ul1 clsact
 
-	ip route del vrf v$ol1 2001:db8:2::/64
 	ip route del vrf v$ol1 192.0.2.16/28
 
 	ip route del vrf v$ol1 192.0.2.82/32 via 192.0.2.146
@@ -131,12 +118,12 @@ sw1_destroy()
 	vlan_destroy $ul1 222
 	vlan_destroy $ul1 111
 	__simple_if_fini $ul1
-	simple_if_fini $ol1 192.0.2.2/28 2001:db8:1::2/64
+	simple_if_fini $ol1 192.0.2.2/28
 }
 
 sw2_create()
 {
-	simple_if_init $ol2 192.0.2.17/28 2001:db8:2::1/64
+	simple_if_init $ol2 192.0.2.17/28
 	__simple_if_init $ul2 v$ol2
 	vlan_create $ul2 111 v$ol2 192.0.2.130/28
 	vlan_create $ul2 222 v$ol2 192.0.2.146/28
@@ -152,14 +139,10 @@ sw2_create()
 	ip route add vrf v$ol2 192.0.2.0/28 \
 	   nexthop dev g2a \
 	   nexthop dev g2b
-	ip route add vrf v$ol2 2001:db8:1::/64 \
-	   nexthop dev g2a \
-	   nexthop dev g2b
 }
 
 sw2_destroy()
 {
-	ip route del vrf v$ol2 2001:db8:1::/64
 	ip route del vrf v$ol2 192.0.2.0/28
 
 	ip route del vrf v$ol2 192.0.2.81/32 via 192.0.2.145
@@ -173,21 +156,19 @@ sw2_destroy()
 	vlan_destroy $ul2 222
 	vlan_destroy $ul2 111
 	__simple_if_fini $ul2
-	simple_if_fini $ol2 192.0.2.17/28 2001:db8:2::1/64
+	simple_if_fini $ol2 192.0.2.17/28
 }
 
 h2_create()
 {
-	simple_if_init $h2 192.0.2.18/28 2001:db8:2::2/64
+	simple_if_init $h2 192.0.2.18/28
 	ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
-	ip route add vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
 }
 
 h2_destroy()
 {
-	ip route del vrf v$h2 2001:db8:1::/64 via 2001:db8:2::1
 	ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
-	simple_if_fini $h2 192.0.2.18/28 2001:db8:2::2/64
+	simple_if_fini $h2 192.0.2.18/28
 }
 
 setup_prepare()
@@ -250,77 +231,11 @@ multipath4_test()
 	sysctl_restore net.ipv4.fib_multipath_hash_policy
 }
 
-multipath6_l4_test()
-{
-	local what=$1; shift
-	local weight1=$1; shift
-	local weight2=$1; shift
-
-	sysctl_set net.ipv6.fib_multipath_hash_policy 1
-	ip route replace vrf v$ol1 2001:db8:2::/64 \
-	   nexthop dev g1a weight $weight1 \
-	   nexthop dev g1b weight $weight2
-
-	local t0_111=$(tc_rule_stats_get $ul1 111 egress)
-	local t0_222=$(tc_rule_stats_get $ul1 222 egress)
-
-	ip vrf exec v$h1 \
-	   $MZ $h1 -6 -q -p 64 -A 2001:db8:1::1 -B 2001:db8:2::2 \
-	       -d 1msec -t udp "sp=1024,dp=0-32768"
-
-	local t1_111=$(tc_rule_stats_get $ul1 111 egress)
-	local t1_222=$(tc_rule_stats_get $ul1 222 egress)
-
-	local d111=$((t1_111 - t0_111))
-	local d222=$((t1_222 - t0_222))
-	multipath_eval "$what" $weight1 $weight2 $d111 $d222
-
-	ip route replace vrf v$ol1 2001:db8:2::/64 \
-	   nexthop dev g1a \
-	   nexthop dev g1b
-	sysctl_restore net.ipv6.fib_multipath_hash_policy
-}
-
-multipath6_test()
-{
-	local what=$1; shift
-	local weight1=$1; shift
-	local weight2=$1; shift
-
-	ip route replace vrf v$ol1 2001:db8:2::/64 \
-	   nexthop dev g1a weight $weight1 \
-	   nexthop dev g1b weight $weight2
-
-	local t0_111=$(tc_rule_stats_get $ul1 111 egress)
-	local t0_222=$(tc_rule_stats_get $ul1 222 egress)
-
-        # Generate 16384 echo requests, each with a random flow label.
-	for ((i=0; i < 16384; ++i)); do
-		ip vrf exec v$h1 $PING6 2001:db8:2::2 -F 0 -c 1 -q &> /dev/null
-	done
-
-	local t1_111=$(tc_rule_stats_get $ul1 111 egress)
-	local t1_222=$(tc_rule_stats_get $ul1 222 egress)
-
-	local d111=$((t1_111 - t0_111))
-	local d222=$((t1_222 - t0_222))
-	multipath_eval "$what" $weight1 $weight2 $d111 $d222
-
-	ip route replace vrf v$ol1 2001:db8:2::/64 \
-	   nexthop dev g1a \
-	   nexthop dev g1b
-}
-
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.18
 }
 
-ping_ipv6()
-{
-	ping6_test $h1 2001:db8:2::2
-}
-
 multipath_ipv4()
 {
 	log_info "Running IPv4 multipath tests"
@@ -329,22 +244,6 @@ multipath_ipv4()
 	multipath4_test "Weighted MP 11:45" 11 45
 }
 
-multipath_ipv6()
-{
-	log_info "Running IPv6 multipath tests"
-	multipath6_test "ECMP" 1 1
-	multipath6_test "Weighted MP 2:1" 2 1
-	multipath6_test "Weighted MP 11:45" 11 45
-}
-
-multipath_ipv6_l4()
-{
-	log_info "Running IPv6 L4 hash multipath tests"
-	multipath6_l4_test "ECMP" 1 1
-	multipath6_l4_test "Weighted MP 2:1" 2 1
-	multipath6_l4_test "Weighted MP 11:45" 11 45
-}
-
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From 08edaaa6d6fa5f6ac9be2adcc71f80b4083b6494 Mon Sep 17 00:00:00 2001
From: Anna-Maria Gleixner <anna-maria@linutronix.de>
Date: Tue, 3 Jul 2018 22:01:37 +0200
Subject: drivers/md/raid5: Do not disable irq on
 release_inactive_stripe_list() call

There is no need to invoke release_inactive_stripe_list() with interrupts
disabled. All call sites, except raid5_release_stripe(), unlock
->device_lock and enable interrupts before invoking the function.

Make it consistent.

Cc: Shaohua Li <shli@kernel.org>
Cc: linux-raid@vger.kernel.org
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Anna-Maria Gleixner <anna-maria@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index e933bff9459e..ca1dd0cb04c5 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -414,9 +414,8 @@ slow_path:
 		INIT_LIST_HEAD(&list);
 		hash = sh->hash_lock_index;
 		do_release_stripe(conf, sh, &list);
-		spin_unlock(&conf->device_lock);
+		spin_unlock_irqrestore(&conf->device_lock, flags);
 		release_inactive_stripe_list(conf, &list, hash);
-		local_irq_restore(flags);
 	}
 }
 
-- 
cgit v1.2.3


From 75eb3a67a29e9f87c07c8bd184a7ed4274a58ef0 Mon Sep 17 00:00:00 2001
From: Akinobu Mita <akinobu.mita@gmail.com>
Date: Mon, 23 Jul 2018 00:45:46 +0900
Subject: regmap: sccb: fix typo and sort headers alphabetically

Fix typos 's/wit/with/' in the comments and sort headers alphabetically
in order to avoid duplicate includes in future.

Fixes: bcf7eac3d97f ("regmap: add SCCB support")
Reported-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Reviewed-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/regmap-sccb.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/base/regmap/regmap-sccb.c b/drivers/base/regmap/regmap-sccb.c
index b6eb876ea819..597042e2d009 100644
--- a/drivers/base/regmap/regmap-sccb.c
+++ b/drivers/base/regmap/regmap-sccb.c
@@ -1,9 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 // Register map access API - SCCB support
 
-#include <linux/regmap.h>
 #include <linux/i2c.h>
 #include <linux/module.h>
+#include <linux/regmap.h>
 
 #include "internal.h"
 
@@ -29,7 +29,7 @@ static bool sccb_is_available(struct i2c_adapter *adap)
 
 /**
  * regmap_sccb_read - Read data from SCCB slave device
- * @context: Device that will be interacted wit
+ * @context: Device that will be interacted with
  * @reg: Register to be read from
  * @val: Pointer to store read value
  *
@@ -65,7 +65,7 @@ out:
 
 /**
  * regmap_sccb_write - Write data to SCCB slave device
- * @context: Device that will be interacted wit
+ * @context: Device that will be interacted with
  * @reg: Register to write to
  * @val: Value to be written
  *
-- 
cgit v1.2.3


From a30718868915fbb991a9ae9e45594b059f28e9ae Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Fri, 13 Jul 2018 15:37:57 +0800
Subject: MIPS: Change definition of cpu_relax() for Loongson-3

Linux expects that if a CPU modifies a memory location, then that
modification will eventually become visible to other CPUs in the system.

Loongson 3 CPUs include a Store Fill Buffer (SFB) which sits between a
core & its L1 data cache, queueing memory accesses & allowing for faster
forwarding of data from pending stores to younger loads from the core.
Unfortunately the SFB prioritizes loads such that a continuous stream of
loads may cause a pending write to be buffered indefinitely. This is
problematic if we end up with 2 CPUs which each perform a store that the
other polls for - one or both CPUs may end up with their stores buffered
in the SFB, never reaching cache due to the continuous reads from the
poll loop. Such a deadlock condition has been observed whilst running
qspinlock code.

This patch changes the definition of cpu_relax() to smp_mb() for
Loongson-3, forcing a flush of the SFB on SMP systems which will cause
any pending writes to make it as far as the L1 caches where they will
become visible to other CPUs. If the kernel is not compiled for SMP
support, this will expand to a barrier() as before.

This workaround matches that currently implemented for ARM when
CONFIG_ARM_ERRATA_754327=y, which was introduced by commit 534be1d5a2da
("ARM: 6194/1: change definition of cpu_relax() for ARM11MPCore").

Although the workaround is only required when the Loongson 3 SFB
functionality is enabled, and we only began explicitly enabling that
functionality in v4.7 with commit 1e820da3c9af ("MIPS: Loongson-3:
Introduce CONFIG_LOONGSON3_ENHANCEMENT"), existing or future firmware
may enable the SFB which means we may need the workaround backported to
earlier kernels too.

[paul.burton@mips.com:
  - Reword commit message & comment.
  - Limit stable backport to v3.15+ where we support Loongson 3 CPUs.]

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
References: 534be1d5a2da ("ARM: 6194/1: change definition of cpu_relax() for ARM11MPCore")
References: 1e820da3c9af ("MIPS: Loongson-3: Introduce CONFIG_LOONGSON3_ENHANCEMENT")
Patchwork: https://patchwork.linux-mips.org/patch/19830/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: Huacai Chen <chenhuacai@gmail.com>
Cc: stable@vger.kernel.org # v3.15+
---
 arch/mips/include/asm/processor.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index d8a5951433fc..b2fa62922d88 100644
--- a/arch/mips/include/asm/processor.h
+++ b/arch/mips/include/asm/processor.h
@@ -386,7 +386,20 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk) (task_pt_regs(tsk)->regs[29])
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
+#ifdef CONFIG_CPU_LOONGSON3
+/*
+ * Loongson-3's SFB (Store-Fill-Buffer) may buffer writes indefinitely when a
+ * tight read loop is executed, because reads take priority over writes & the
+ * hardware (incorrectly) doesn't ensure that writes will eventually occur.
+ *
+ * Since spin loops of any kind should have a cpu_relax() in them, force an SFB
+ * flush from cpu_relax() such that any pending writes will become visible as
+ * expected.
+ */
+#define cpu_relax()	smp_mb()
+#else
 #define cpu_relax()	barrier()
+#endif
 
 /*
  * Return_address is a replacement for __builtin_return_address(count)
-- 
cgit v1.2.3


From c601171d7a60b5b09d7c2fe0579953323a80744e Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Mon, 23 Jul 2018 13:53:08 +0200
Subject: net/smc: provide smc mode in smc_diag.c

Rename field diag_fallback into diag_mode and set the smc mode of a
connection explicitly.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/smc_diag.h | 9 ++++++++-
 net/smc/smc_diag.c            | 7 ++++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h
index 92be255e534c..48ae3ee22b2d 100644
--- a/include/uapi/linux/smc_diag.h
+++ b/include/uapi/linux/smc_diag.h
@@ -20,7 +20,7 @@ struct smc_diag_req {
 struct smc_diag_msg {
 	__u8	diag_family;
 	__u8	diag_state;
-	__u8	diag_fallback;
+	__u8	diag_mode;
 	__u8	diag_shutdown;
 	struct inet_diag_sockid id;
 
@@ -28,6 +28,13 @@ struct smc_diag_msg {
 	__u64	diag_inode;
 };
 
+/* Mode of a connection */
+enum {
+	SMC_DIAG_MODE_SMCR,
+	SMC_DIAG_MODE_FALLBACK_TCP,
+	SMC_DIAG_MODE_SMCD,
+};
+
 /* Extensions */
 
 enum {
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index 6d83eef1b743..d772cd10297e 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -91,7 +91,12 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	r = nlmsg_data(nlh);
 	smc_diag_msg_common_fill(r, sk);
 	r->diag_state = sk->sk_state;
-	r->diag_fallback = smc->use_fallback;
+	if (smc->use_fallback)
+		r->diag_mode = SMC_DIAG_MODE_FALLBACK_TCP;
+	else if (smc->conn.lgr && smc->conn.lgr->is_smcd)
+		r->diag_mode = SMC_DIAG_MODE_SMCD;
+	else
+		r->diag_mode = SMC_DIAG_MODE_SMCR;
 	user_ns = sk_user_ns(NETLINK_CB(cb->skb).sk);
 	if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns))
 		goto errout;
-- 
cgit v1.2.3


From bac6de7b637018f4caacfdf2b4ad8c8749de7420 Mon Sep 17 00:00:00 2001
From: Stefan Raspl <raspl@linux.ibm.com>
Date: Mon, 23 Jul 2018 13:53:09 +0200
Subject: net/smc: eliminate cursor read and write calls

The functions to read and write cursors are exclusively used to copy
cursors. Therefore switch to a respective function instead.

Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c  |  8 ++------
 net/smc/smc_cdc.c | 33 ++++++++++++---------------------
 net/smc/smc_cdc.h | 43 +++++++++++++++----------------------------
 net/smc/smc_rx.c  | 15 ++++-----------
 net/smc/smc_tx.c  | 46 +++++++++++++---------------------------------
 net/smc/smc_tx.h  |  4 ++--
 6 files changed, 48 insertions(+), 101 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 143b2220c0c8..7fc810ec31c5 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1755,12 +1755,8 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd,
 		    smc->sk.sk_state == SMC_CLOSED) {
 			answ = 0;
 		} else {
-			smc_curs_write(&cons,
-			       smc_curs_read(&conn->local_tx_ctrl.cons, conn),
-				       conn);
-			smc_curs_write(&urg,
-				       smc_curs_read(&conn->urg_curs, conn),
-				       conn);
+			smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+			smc_curs_copy(&urg, &conn->urg_curs, conn);
 			answ = smc_curs_diff(conn->rmb_desc->len,
 					     &cons, &urg) == 1;
 		}
diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index 621d8cca570b..f3a1497953ee 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -34,14 +34,15 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 			       enum ib_wc_status wc_status)
 {
 	struct smc_cdc_tx_pend *cdcpend = (struct smc_cdc_tx_pend *)pnd_snd;
+	struct smc_connection *conn = cdcpend->conn;
 	struct smc_sock *smc;
 	int diff;
 
-	if (!cdcpend->conn)
+	if (!conn)
 		/* already dismissed */
 		return;
 
-	smc = container_of(cdcpend->conn, struct smc_sock, conn);
+	smc = container_of(conn, struct smc_sock, conn);
 	bh_lock_sock(&smc->sk);
 	if (!wc_status) {
 		diff = smc_curs_diff(cdcpend->conn->sndbuf_desc->len,
@@ -52,9 +53,7 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 		atomic_add(diff, &cdcpend->conn->sndbuf_space);
 		/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
 		smp_mb__after_atomic();
-		smc_curs_write(&cdcpend->conn->tx_curs_fin,
-			       smc_curs_read(&cdcpend->cursor, cdcpend->conn),
-			       cdcpend->conn);
+		smc_curs_copy(&conn->tx_curs_fin, &cdcpend->cursor, conn);
 	}
 	smc_tx_sndbuf_nonfull(smc);
 	bh_unlock_sock(&smc->sk);
@@ -110,9 +109,8 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 			    &conn->local_tx_ctrl, conn);
 	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
 	if (!rc)
-		smc_curs_write(&conn->rx_curs_confirmed,
-			       smc_curs_read(&conn->local_tx_ctrl.cons, conn),
-			       conn);
+		smc_curs_copy(&conn->rx_curs_confirmed,
+			      &conn->local_tx_ctrl.cons, conn);
 
 	return rc;
 }
@@ -194,8 +192,8 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
 	rc = smcd_tx_ism_write(conn, &cdc, sizeof(cdc), 0, 1);
 	if (rc)
 		return rc;
-	smc_curs_write(&conn->rx_curs_confirmed,
-		       smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn);
+	smc_curs_copy(&conn->rx_curs_confirmed, &conn->local_tx_ctrl.cons,
+		      conn);
 	/* Calculate transmitted data and increment free send buffer space */
 	diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin,
 			     &conn->tx_curs_sent);
@@ -204,8 +202,7 @@ int smcd_cdc_msg_send(struct smc_connection *conn)
 	atomic_add(diff, &conn->sndbuf_space);
 	/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
 	smp_mb__after_atomic();
-	smc_curs_write(&conn->tx_curs_fin,
-		       smc_curs_read(&conn->tx_curs_sent, conn), conn);
+	smc_curs_copy(&conn->tx_curs_fin, &conn->tx_curs_sent, conn);
 
 	smc_tx_sndbuf_nonfull(smc);
 	return rc;
@@ -225,9 +222,7 @@ static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc,
 	char *base;
 
 	/* new data included urgent business */
-	smc_curs_write(&conn->urg_curs,
-		       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
-		       conn);
+	smc_curs_copy(&conn->urg_curs, &conn->local_rx_ctrl.prod, conn);
 	conn->urg_state = SMC_URG_VALID;
 	if (!sock_flag(&smc->sk, SOCK_URGINLINE))
 		/* we'll skip the urgent byte, so don't account for it */
@@ -247,12 +242,8 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 	struct smc_connection *conn = &smc->conn;
 	int diff_cons, diff_prod;
 
-	smc_curs_write(&prod_old,
-		       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
-		       conn);
-	smc_curs_write(&cons_old,
-		       smc_curs_read(&conn->local_rx_ctrl.cons, conn),
-		       conn);
+	smc_curs_copy(&prod_old, &conn->local_rx_ctrl.prod, conn);
+	smc_curs_copy(&cons_old, &conn->local_rx_ctrl.cons, conn);
 	smc_cdc_msg_to_host(&conn->local_rx_ctrl, cdc, conn);
 
 	diff_cons = smc_curs_diff(conn->peer_rmbe_size, &cons_old,
diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h
index 8fbce4fee3e4..934df4473a7c 100644
--- a/net/smc/smc_cdc.h
+++ b/net/smc/smc_cdc.h
@@ -104,47 +104,34 @@ static inline u64 smc_curs_read(union smc_host_cursor *curs,
 #endif
 }
 
-static inline u64 smc_curs_read_net(union smc_cdc_cursor *curs,
-				    struct smc_connection *conn)
-{
-#ifndef KERNEL_HAS_ATOMIC64
-	unsigned long flags;
-	u64 ret;
-
-	spin_lock_irqsave(&conn->acurs_lock, flags);
-	ret = curs->acurs;
-	spin_unlock_irqrestore(&conn->acurs_lock, flags);
-	return ret;
-#else
-	return atomic64_read(&curs->acurs);
-#endif
-}
-
-static inline void smc_curs_write(union smc_host_cursor *curs, u64 val,
-				  struct smc_connection *conn)
+/* Copy cursor src into tgt */
+static inline void smc_curs_copy(union smc_host_cursor *tgt,
+				 union smc_host_cursor *src,
+				 struct smc_connection *conn)
 {
 #ifndef KERNEL_HAS_ATOMIC64
 	unsigned long flags;
 
 	spin_lock_irqsave(&conn->acurs_lock, flags);
-	curs->acurs = val;
+	tgt->acurs = src->acurs;
 	spin_unlock_irqrestore(&conn->acurs_lock, flags);
 #else
-	atomic64_set(&curs->acurs, val);
+	atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
 #endif
 }
 
-static inline void smc_curs_write_net(union smc_cdc_cursor *curs, u64 val,
-				      struct smc_connection *conn)
+static inline void smc_curs_copy_net(union smc_cdc_cursor *tgt,
+				     union smc_cdc_cursor *src,
+				     struct smc_connection *conn)
 {
 #ifndef KERNEL_HAS_ATOMIC64
 	unsigned long flags;
 
 	spin_lock_irqsave(&conn->acurs_lock, flags);
-	curs->acurs = val;
+	tgt->acurs = src->acurs;
 	spin_unlock_irqrestore(&conn->acurs_lock, flags);
 #else
-	atomic64_set(&curs->acurs, val);
+	atomic64_set(&tgt->acurs, atomic64_read(&src->acurs));
 #endif
 }
 
@@ -179,7 +166,7 @@ static inline void smc_host_cursor_to_cdc(union smc_cdc_cursor *peer,
 {
 	union smc_host_cursor temp;
 
-	smc_curs_write(&temp, smc_curs_read(local, conn), conn);
+	smc_curs_copy(&temp, local, conn);
 	peer->count = htonl(temp.count);
 	peer->wrap = htons(temp.wrap);
 	/* peer->reserved = htons(0); must be ensured by caller */
@@ -206,8 +193,8 @@ static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local,
 	union smc_host_cursor temp, old;
 	union smc_cdc_cursor net;
 
-	smc_curs_write(&old, smc_curs_read(local, conn), conn);
-	smc_curs_write_net(&net, smc_curs_read_net(peer, conn), conn);
+	smc_curs_copy(&old, local, conn);
+	smc_curs_copy_net(&net, peer, conn);
 	temp.count = ntohl(net.count);
 	temp.wrap = ntohs(net.wrap);
 	if ((old.wrap > temp.wrap) && temp.wrap)
@@ -215,7 +202,7 @@ static inline void smc_cdc_cursor_to_host(union smc_host_cursor *local,
 	if ((old.wrap == temp.wrap) &&
 	    (old.count > temp.count))
 		return;
-	smc_curs_write(local, smc_curs_read(&temp, conn), conn);
+	smc_curs_copy(local, &temp, conn);
 }
 
 static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local,
diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index b329803c8339..c99c987097b1 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -82,8 +82,7 @@ static int smc_rx_update_consumer(struct smc_sock *smc,
 		}
 	}
 
-	smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn),
-		       conn);
+	smc_curs_copy(&conn->local_tx_ctrl.cons, &cons, conn);
 
 	/* send consumer cursor update if required */
 	/* similar to advertising new TCP rcv_wnd if required */
@@ -97,8 +96,7 @@ static void smc_rx_update_cons(struct smc_sock *smc, size_t len)
 	struct smc_connection *conn = &smc->conn;
 	union smc_host_cursor cons;
 
-	smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn),
-		       conn);
+	smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
 	smc_rx_update_consumer(smc, cons, len);
 }
 
@@ -245,10 +243,7 @@ static int smc_rx_recv_urg(struct smc_sock *smc, struct msghdr *msg, int len,
 			if (!(flags & MSG_TRUNC))
 				rc = memcpy_to_msg(msg, &conn->urg_rx_byte, 1);
 			len = 1;
-			smc_curs_write(&cons,
-				       smc_curs_read(&conn->local_tx_ctrl.cons,
-						     conn),
-				       conn);
+			smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
 			if (smc_curs_diff(conn->rmb_desc->len, &cons,
 					  &conn->urg_curs) > 1)
 				conn->urg_rx_skip_pend = true;
@@ -370,9 +365,7 @@ copy:
 			continue;
 		}
 
-		smc_curs_write(&cons,
-			       smc_curs_read(&conn->local_tx_ctrl.cons, conn),
-			       conn);
+		smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
 		/* subsequent splice() calls pick up where previous left */
 		if (splbytes)
 			smc_curs_add(conn->rmb_desc->len, &cons, splbytes);
diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c
index 142bcb134dd6..2f5e324e54b9 100644
--- a/net/smc/smc_tx.c
+++ b/net/smc/smc_tx.c
@@ -181,9 +181,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 		copylen = min_t(size_t, send_remaining, writespace);
 		/* determine start of sndbuf */
 		sndbuf_base = conn->sndbuf_desc->cpu_addr;
-		smc_curs_write(&prep,
-			       smc_curs_read(&conn->tx_curs_prep, conn),
-			       conn);
+		smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
 		tx_cnt_prep = prep.count;
 		/* determine chunks where to write into sndbuf */
 		/* either unwrapped case, or 1st chunk of wrapped case */
@@ -214,9 +212,7 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len)
 		smc_sndbuf_sync_sg_for_device(conn);
 		/* update cursors */
 		smc_curs_add(conn->sndbuf_desc->len, &prep, copylen);
-		smc_curs_write(&conn->tx_curs_prep,
-			       smc_curs_read(&prep, conn),
-			       conn);
+		smc_curs_copy(&conn->tx_curs_prep, &prep, conn);
 		/* increased in send tasklet smc_cdc_tx_handler() */
 		smp_mb__before_atomic();
 		atomic_sub(copylen, &conn->sndbuf_space);
@@ -417,8 +413,8 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 	int rc;
 
 	/* source: sndbuf */
-	smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
-	smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
+	smc_curs_copy(&sent, &conn->tx_curs_sent, conn);
+	smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
 	/* cf. wmem_alloc - (snd_max - snd_una) */
 	to_send = smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
 	if (to_send <= 0)
@@ -429,12 +425,8 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 	rmbespace = atomic_read(&conn->peer_rmbe_space);
 	if (rmbespace <= 0)
 		return 0;
-	smc_curs_write(&prod,
-		       smc_curs_read(&conn->local_tx_ctrl.prod, conn),
-		       conn);
-	smc_curs_write(&cons,
-		       smc_curs_read(&conn->local_rx_ctrl.cons, conn),
-		       conn);
+	smc_curs_copy(&prod, &conn->local_tx_ctrl.prod, conn);
+	smc_curs_copy(&cons, &conn->local_rx_ctrl.cons, conn);
 
 	/* if usable snd_wnd closes ask peer to advertise once it opens again */
 	pflags = &conn->local_tx_ctrl.prod_flags;
@@ -481,14 +473,9 @@ static int smc_tx_rdma_writes(struct smc_connection *conn)
 		pflags->urg_data_present = 1;
 	smc_tx_advance_cursors(conn, &prod, &sent, len);
 	/* update connection's cursors with advanced local cursors */
-	smc_curs_write(&conn->local_tx_ctrl.prod,
-		       smc_curs_read(&prod, conn),
-		       conn);
+	smc_curs_copy(&conn->local_tx_ctrl.prod, &prod, conn);
 							/* dst: peer RMBE */
-	smc_curs_write(&conn->tx_curs_sent,
-		       smc_curs_read(&sent, conn),
-		       conn);
-							/* src: local sndbuf */
+	smc_curs_copy(&conn->tx_curs_sent, &sent, conn);/* src: local sndbuf */
 
 	return 0;
 }
@@ -606,17 +593,11 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 	int sender_free = conn->rmb_desc->len;
 	int to_confirm;
 
-	smc_curs_write(&cons,
-		       smc_curs_read(&conn->local_tx_ctrl.cons, conn),
-		       conn);
-	smc_curs_write(&cfed,
-		       smc_curs_read(&conn->rx_curs_confirmed, conn),
-		       conn);
+	smc_curs_copy(&cons, &conn->local_tx_ctrl.cons, conn);
+	smc_curs_copy(&cfed, &conn->rx_curs_confirmed, conn);
 	to_confirm = smc_curs_diff(conn->rmb_desc->len, &cfed, &cons);
 	if (to_confirm > conn->rmbe_update_limit) {
-		smc_curs_write(&prod,
-			       smc_curs_read(&conn->local_rx_ctrl.prod, conn),
-			       conn);
+		smc_curs_copy(&prod, &conn->local_rx_ctrl.prod, conn);
 		sender_free = conn->rmb_desc->len -
 			      smc_curs_diff(conn->rmb_desc->len, &prod, &cfed);
 	}
@@ -632,9 +613,8 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force)
 					      SMC_TX_WORK_DELAY);
 			return;
 		}
-		smc_curs_write(&conn->rx_curs_confirmed,
-			       smc_curs_read(&conn->local_tx_ctrl.cons, conn),
-			       conn);
+		smc_curs_copy(&conn->rx_curs_confirmed,
+			      &conn->local_tx_ctrl.cons, conn);
 		conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
 	}
 	if (conn->local_rx_ctrl.prod_flags.write_blocked &&
diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h
index b22bdc5694c4..07e6ad76224a 100644
--- a/net/smc/smc_tx.h
+++ b/net/smc/smc_tx.h
@@ -22,8 +22,8 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn)
 {
 	union smc_host_cursor sent, prep;
 
-	smc_curs_write(&sent, smc_curs_read(&conn->tx_curs_sent, conn), conn);
-	smc_curs_write(&prep, smc_curs_read(&conn->tx_curs_prep, conn), conn);
+	smc_curs_copy(&sent, &conn->tx_curs_sent, conn);
+	smc_curs_copy(&prep, &conn->tx_curs_prep, conn);
 	return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep);
 }
 
-- 
cgit v1.2.3


From 00e5fb263f9f5f2af60754b79b7dcec0d5e88154 Mon Sep 17 00:00:00 2001
From: Stefan Raspl <raspl@linux.ibm.com>
Date: Mon, 23 Jul 2018 13:53:10 +0200
Subject: net/smc: add function to get link group from link

Replace a frequently used construct with a more readable variant,
reducing the code. Also might come handy when we start to support
more than a single per link group.

Signed-off-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_cdc.c  |  2 +-
 net/smc/smc_core.h |  5 +++++
 net/smc/smc_ib.c   |  3 +--
 net/smc/smc_llc.c  | 30 ++++++++----------------------
 net/smc/smc_wr.c   | 27 +++++----------------------
 5 files changed, 20 insertions(+), 47 deletions(-)

diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c
index f3a1497953ee..a7af2289cdff 100644
--- a/net/smc/smc_cdc.c
+++ b/net/smc/smc_cdc.c
@@ -365,7 +365,7 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
 		return; /* invalid message */
 
 	/* lookup connection */
-	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+	lgr = smc_get_lgr(link);
 	read_lock_bh(&lgr->conns_lock);
 	conn = smc_lgr_find_conn(ntohl(cdc->token), lgr);
 	read_unlock_bh(&lgr->conns_lock);
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 8b47e0168fc3..8807865483bb 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -266,4 +266,9 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 		    u64 peer_gid);
 void smcd_conn_free(struct smc_connection *conn);
 void smc_core_exit(void);
+
+static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
+{
+	return container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
+}
 #endif
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 36de2fd76170..4706ab7092a9 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -112,8 +112,7 @@ int smc_ib_modify_qp_reset(struct smc_link *lnk)
 
 int smc_ib_ready_link(struct smc_link *lnk)
 {
-	struct smc_link_group *lgr =
-		container_of(lnk, struct smc_link_group, lnk[0]);
+	struct smc_link_group *lgr = smc_get_lgr(lnk);
 	int rc = 0;
 
 	rc = smc_ib_modify_qp_init(lnk);
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index 5800a6b43d83..b7944aa1ffc3 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -186,8 +186,7 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[],
 			      union ib_gid *gid,
 			      enum smc_llc_reqresp reqresp)
 {
-	struct smc_link_group *lgr = container_of(link, struct smc_link_group,
-						  lnk[SMC_SINGLE_LINK]);
+	struct smc_link_group *lgr = smc_get_lgr(link);
 	struct smc_llc_msg_confirm_link *confllc;
 	struct smc_wr_tx_pend_priv *pend;
 	struct smc_wr_buf *wr_buf;
@@ -381,11 +380,9 @@ static int smc_llc_send_message(struct smc_link *link, void *llcbuf, int llclen)
 static void smc_llc_rx_confirm_link(struct smc_link *link,
 				    struct smc_llc_msg_confirm_link *llc)
 {
-	struct smc_link_group *lgr;
+	struct smc_link_group *lgr = smc_get_lgr(link);
 	int conf_rc;
 
-	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
-
 	/* RMBE eyecatchers are not supported */
 	if (llc->hd.flags & SMC_LLC_FLAG_NO_RMBE_EYEC)
 		conf_rc = 0;
@@ -411,8 +408,7 @@ static void smc_llc_rx_confirm_link(struct smc_link *link,
 static void smc_llc_rx_add_link(struct smc_link *link,
 				struct smc_llc_msg_add_link *llc)
 {
-	struct smc_link_group *lgr = container_of(link, struct smc_link_group,
-						  lnk[SMC_SINGLE_LINK]);
+	struct smc_link_group *lgr = smc_get_lgr(link);
 
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
 		if (link->state == SMC_LNK_ACTIVATING)
@@ -442,8 +438,7 @@ static void smc_llc_rx_add_link(struct smc_link *link,
 static void smc_llc_rx_delete_link(struct smc_link *link,
 				   struct smc_llc_msg_del_link *llc)
 {
-	struct smc_link_group *lgr = container_of(link, struct smc_link_group,
-						  lnk[SMC_SINGLE_LINK]);
+	struct smc_link_group *lgr = smc_get_lgr(link);
 
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
 		if (lgr->role == SMC_SERV)
@@ -476,17 +471,14 @@ static void smc_llc_rx_test_link(struct smc_link *link,
 static void smc_llc_rx_confirm_rkey(struct smc_link *link,
 				    struct smc_llc_msg_confirm_rkey *llc)
 {
-	struct smc_link_group *lgr;
 	int rc;
 
-	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
-
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
 		link->llc_confirm_rkey_rc = llc->hd.flags &
 					    SMC_LLC_FLAG_RKEY_NEG;
 		complete(&link->llc_confirm_rkey);
 	} else {
-		rc = smc_rtoken_add(lgr,
+		rc = smc_rtoken_add(smc_get_lgr(link),
 				    llc->rtoken[0].rmb_vaddr,
 				    llc->rtoken[0].rmb_key);
 
@@ -514,18 +506,15 @@ static void smc_llc_rx_confirm_rkey_cont(struct smc_link *link,
 static void smc_llc_rx_delete_rkey(struct smc_link *link,
 				   struct smc_llc_msg_delete_rkey *llc)
 {
-	struct smc_link_group *lgr;
 	u8 err_mask = 0;
 	int i, max;
 
-	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
-
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
 		/* unused as long as we don't send this type of msg */
 	} else {
 		max = min_t(u8, llc->num_rkeys, SMC_LLC_DEL_RKEY_MAX);
 		for (i = 0; i < max; i++) {
-			if (smc_rtoken_delete(lgr, llc->rkey[i]))
+			if (smc_rtoken_delete(smc_get_lgr(link), llc->rkey[i]))
 				err_mask |= 1 << (SMC_LLC_DEL_RKEY_MAX - 1 - i);
 		}
 
@@ -583,12 +572,10 @@ static void smc_llc_testlink_work(struct work_struct *work)
 	struct smc_link *link = container_of(to_delayed_work(work),
 					     struct smc_link, llc_testlink_wrk);
 	unsigned long next_interval;
-	struct smc_link_group *lgr;
 	unsigned long expire_time;
 	u8 user_data[16] = { 0 };
 	int rc;
 
-	lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
 	if (link->state != SMC_LNK_ACTIVE)
 		return;		/* don't reschedule worker */
 	expire_time = link->wr_rx_tstamp + link->llc_testlink_time;
@@ -602,7 +589,7 @@ static void smc_llc_testlink_work(struct work_struct *work)
 	rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp,
 						       SMC_LLC_WAIT_TIME);
 	if (rc <= 0) {
-		smc_lgr_terminate(lgr);
+		smc_lgr_terminate(smc_get_lgr(link));
 		return;
 	}
 	next_interval = link->llc_testlink_time;
@@ -613,8 +600,7 @@ out:
 
 int smc_llc_link_init(struct smc_link *link)
 {
-	struct smc_link_group *lgr = container_of(link, struct smc_link_group,
-						  lnk[SMC_SINGLE_LINK]);
+	struct smc_link_group *lgr = smc_get_lgr(link);
 	link->llc_wq = alloc_ordered_workqueue("llc_wq-%x:%x)", WQ_MEM_RECLAIM,
 					       *((u32 *)lgr->id),
 					       link->link_id);
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index dbd2605d1962..b6df69756bef 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -92,8 +92,6 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 	if (!test_and_clear_bit(pnd_snd_idx, link->wr_tx_mask))
 		return;
 	if (wc->status) {
-		struct smc_link_group *lgr;
-
 		for_each_set_bit(i, link->wr_tx_mask, link->wr_tx_cnt) {
 			/* clear full struct smc_wr_tx_pend including .priv */
 			memset(&link->wr_tx_pends[i], 0,
@@ -103,9 +101,7 @@ static inline void smc_wr_tx_process_cqe(struct ib_wc *wc)
 			clear_bit(i, link->wr_tx_mask);
 		}
 		/* terminate connections of this link group abnormally */
-		lgr = container_of(link, struct smc_link_group,
-				   lnk[SMC_SINGLE_LINK]);
-		smc_lgr_terminate(lgr);
+		smc_lgr_terminate(smc_get_lgr(link));
 	}
 	if (pnd_snd.handler)
 		pnd_snd.handler(&pnd_snd.priv, link, wc->status);
@@ -188,8 +184,7 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
 	} else {
 		struct smc_link_group *lgr;
 
-		lgr = container_of(link, struct smc_link_group,
-				   lnk[SMC_SINGLE_LINK]);
+		lgr = smc_get_lgr(link);
 		rc = wait_event_timeout(
 			link->wr_tx_wait,
 			list_empty(&lgr->list) || /* lgr terminated */
@@ -250,12 +245,8 @@ int smc_wr_tx_send(struct smc_link *link, struct smc_wr_tx_pend_priv *priv)
 	rc = ib_post_send(link->roce_qp, &link->wr_tx_ibs[pend->idx],
 			  &failed_wr);
 	if (rc) {
-		struct smc_link_group *lgr =
-			container_of(link, struct smc_link_group,
-				     lnk[SMC_SINGLE_LINK]);
-
 		smc_wr_tx_put_slot(link, priv);
-		smc_lgr_terminate(lgr);
+		smc_lgr_terminate(smc_get_lgr(link));
 	}
 	return rc;
 }
@@ -283,11 +274,7 @@ int smc_wr_reg_send(struct smc_link *link, struct ib_mr *mr)
 					      SMC_WR_REG_MR_WAIT_TIME);
 	if (!rc) {
 		/* timeout - terminate connections */
-		struct smc_link_group *lgr;
-
-		lgr = container_of(link, struct smc_link_group,
-				   lnk[SMC_SINGLE_LINK]);
-		smc_lgr_terminate(lgr);
+		smc_lgr_terminate(smc_get_lgr(link));
 		return -EPIPE;
 	}
 	if (rc == -ERESTARTSYS)
@@ -380,8 +367,6 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
 			smc_wr_rx_demultiplex(&wc[i]);
 			smc_wr_rx_post(link); /* refill WR RX */
 		} else {
-			struct smc_link_group *lgr;
-
 			/* handle status errors */
 			switch (wc[i].status) {
 			case IB_WC_RETRY_EXC_ERR:
@@ -390,9 +375,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num)
 				/* terminate connections of this link group
 				 * abnormally
 				 */
-				lgr = container_of(link, struct smc_link_group,
-						   lnk[SMC_SINGLE_LINK]);
-				smc_lgr_terminate(lgr);
+				smc_lgr_terminate(smc_get_lgr(link));
 				break;
 			default:
 				smc_wr_rx_post(link); /* refill WR RX */
-- 
cgit v1.2.3


From 144ce4b9b5a788953b5373162a1921267497fb38 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ursula.braun@de.ibm.com>
Date: Mon, 23 Jul 2018 13:53:11 +0200
Subject: net/smc: use DECLARE_BITMAP for rtokens_used_mask

Link group field tokens_used_mask is a bitmap. Use macro
DECLARE_BITMAP for its definition.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 8807865483bb..1e8974c50550 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -192,8 +192,7 @@ struct smc_link_group {
 			struct smc_rtoken	rtokens[SMC_RMBS_PER_LGR_MAX]
 						[SMC_LINKS_PER_LGR_MAX];
 						/* remote addr/key pairs */
-			unsigned long		rtokens_used_mask[BITS_TO_LONGS
-							(SMC_RMBS_PER_LGR_MAX)];
+			DECLARE_BITMAP(rtokens_used_mask, SMC_RMBS_PER_LGR_MAX);
 						/* used rtoken elements */
 		};
 		struct { /* SMC-D */
-- 
cgit v1.2.3


From 48bf5231771c7e3961c8326353b6027b1bed6eb5 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ursula.braun@de.ibm.com>
Date: Mon, 23 Jul 2018 13:53:12 +0200
Subject: net/smc: remove local variable page in smc_rx_splice()

The page map address is already stored in the RMB descriptor.
There is no need to derive it from the cpu_addr value.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_rx.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c
index c99c987097b1..bbcf0fe4ae10 100644
--- a/net/smc/smc_rx.c
+++ b/net/smc/smc_rx.c
@@ -155,10 +155,8 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
 	struct splice_pipe_desc spd;
 	struct partial_page partial;
 	struct smc_spd_priv *priv;
-	struct page *page;
 	int bytes;
 
-	page = virt_to_page(smc->conn.rmb_desc->cpu_addr);
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -170,7 +168,7 @@ static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len,
 
 	spd.nr_pages_max = 1;
 	spd.nr_pages = 1;
-	spd.pages = &page;
+	spd.pages = &smc->conn.rmb_desc->pages;
 	spd.partial = &partial;
 	spd.ops = &smc_pipe_ops;
 	spd.spd_release = smc_rx_spd_release;
-- 
cgit v1.2.3


From 2b5c49131fc4e709910c07444f0befd21ad28bcf Mon Sep 17 00:00:00 2001
From: Hauke Mehrtens <hauke@hauke-m.de>
Date: Sun, 22 Jul 2018 01:30:57 +0200
Subject: MIPS: lantiq: Use dma_zalloc_coherent() in dma code

Instead of using dma_alloc_coherent() and memset() directly use
dma_zalloc_coherent().

Signed-off-by: Hauke Mehrtens <hauke@hauke-m.de>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19962/
Cc: ralf@linux-mips.org
Cc: jhogan@kernel.org
Cc: john@phrozen.org
Cc: linux-mips@linux-mips.org
Cc: dev@kresin.me
---
 arch/mips/lantiq/xway/dma.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/mips/lantiq/xway/dma.c b/arch/mips/lantiq/xway/dma.c
index 805b3a6ab2d6..4b9fbb6744ad 100644
--- a/arch/mips/lantiq/xway/dma.c
+++ b/arch/mips/lantiq/xway/dma.c
@@ -130,10 +130,9 @@ ltq_dma_alloc(struct ltq_dma_channel *ch)
 	unsigned long flags;
 
 	ch->desc = 0;
-	ch->desc_base = dma_alloc_coherent(NULL,
+	ch->desc_base = dma_zalloc_coherent(NULL,
 				LTQ_DESC_NUM * LTQ_DESC_SIZE,
 				&ch->phys, GFP_ATOMIC);
-	memset(ch->desc_base, 0, LTQ_DESC_NUM * LTQ_DESC_SIZE);
 
 	spin_lock_irqsave(&ltq_dma_lock, flags);
 	ltq_dma_w32(ch->nr, LTQ_DMA_CS);
-- 
cgit v1.2.3


From fd800f646402c0f85547166b59ca065175928b7b Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 23 Jul 2018 22:12:33 +0800
Subject: wan/fsl_ucc_hdlc: use IS_ERR_VALUE() to check return value of
 qe_muram_alloc

qe_muram_alloc return a unsigned long integer,which should not
compared with zero. check it using IS_ERR_VALUE() to fix this.

Fixes: c19b6d246a35 ("drivers/net: support hdlc function for QE-UCC")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wan/fsl_ucc_hdlc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wan/fsl_ucc_hdlc.c b/drivers/net/wan/fsl_ucc_hdlc.c
index 9b09c9d0d0fb..5f0366a125e2 100644
--- a/drivers/net/wan/fsl_ucc_hdlc.c
+++ b/drivers/net/wan/fsl_ucc_hdlc.c
@@ -192,7 +192,7 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 	priv->ucc_pram_offset = qe_muram_alloc(sizeof(struct ucc_hdlc_param),
 				ALIGNMENT_OF_UCC_HDLC_PRAM);
 
-	if (priv->ucc_pram_offset < 0) {
+	if (IS_ERR_VALUE(priv->ucc_pram_offset)) {
 		dev_err(priv->dev, "Can not allocate MURAM for hdlc parameter.\n");
 		ret = -ENOMEM;
 		goto free_tx_bd;
@@ -230,14 +230,14 @@ static int uhdlc_init(struct ucc_hdlc_private *priv)
 
 	/* Alloc riptr, tiptr */
 	riptr = qe_muram_alloc(32, 32);
-	if (riptr < 0) {
+	if (IS_ERR_VALUE(riptr)) {
 		dev_err(priv->dev, "Cannot allocate MURAM mem for Receive internal temp data pointer\n");
 		ret = -ENOMEM;
 		goto free_tx_skbuff;
 	}
 
 	tiptr = qe_muram_alloc(32, 32);
-	if (tiptr < 0) {
+	if (IS_ERR_VALUE(tiptr)) {
 		dev_err(priv->dev, "Cannot allocate MURAM mem for Transmit internal temp data pointer\n");
 		ret = -ENOMEM;
 		goto free_riptr;
-- 
cgit v1.2.3


From 12005ec33f3a7eac0d508dde52cc9eeea2595ee9 Mon Sep 17 00:00:00 2001
From: Maxime Roussin-Bélanger <maxime.roussinbelanger@gmail.com>
Date: Sun, 22 Jul 2018 23:33:29 -0400
Subject: hwmon: (iio_hwmon) Use devm functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use devm_iio_channel_get_all() to automatically release
channels.

Use devm_hwmon_device_register_with_groups() to
automatically unregister the device.

Signed-off-by: Maxime Roussin-Bélanger <maxime.roussinbelanger@gmail.com>
[groeck: Dropped now unnecessary platform_set_drvdata() and hwmon_dev]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/iio_hwmon.c | 67 +++++++++++++----------------------------------
 1 file changed, 18 insertions(+), 49 deletions(-)

diff --git a/drivers/hwmon/iio_hwmon.c b/drivers/hwmon/iio_hwmon.c
index 69031a0f7ed2..2f3f875c06ac 100644
--- a/drivers/hwmon/iio_hwmon.c
+++ b/drivers/hwmon/iio_hwmon.c
@@ -22,7 +22,6 @@
  * struct iio_hwmon_state - device instance state
  * @channels:		filled with array of channels from iio
  * @num_channels:	number of channels in channels (saves counting twice)
- * @hwmon_dev:		associated hwmon device
  * @attr_group:		the group of attributes
  * @groups:		null terminated array of attribute groups
  * @attrs:		null terminated array of attribute pointers.
@@ -30,7 +29,6 @@
 struct iio_hwmon_state {
 	struct iio_channel *channels;
 	int num_channels;
-	struct device *hwmon_dev;
 	struct attribute_group attr_group;
 	const struct attribute_group *groups[2];
 	struct attribute **attrs;
@@ -68,12 +66,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	enum iio_chan_type type;
 	struct iio_channel *channels;
 	const char *name = "iio_hwmon";
+	struct device *hwmon_dev;
 	char *sname;
 
 	if (dev->of_node && dev->of_node->name)
 		name = dev->of_node->name;
 
-	channels = iio_channel_get_all(dev);
+	channels = devm_iio_channel_get_all(dev);
 	if (IS_ERR(channels)) {
 		if (PTR_ERR(channels) == -ENODEV)
 			return -EPROBE_DEFER;
@@ -81,10 +80,8 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	}
 
 	st = devm_kzalloc(dev, sizeof(*st), GFP_KERNEL);
-	if (st == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st == NULL)
+		return -ENOMEM;
 
 	st->channels = channels;
 
@@ -95,22 +92,18 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->attrs = devm_kcalloc(dev,
 				 st->num_channels + 1, sizeof(*st->attrs),
 				 GFP_KERNEL);
-	if (st->attrs == NULL) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (st->attrs == NULL)
+		return -ENOMEM;
 
 	for (i = 0; i < st->num_channels; i++) {
 		a = devm_kzalloc(dev, sizeof(*a), GFP_KERNEL);
-		if (a == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
-		}
+		if (a == NULL)
+			return -ENOMEM;
 
 		sysfs_attr_init(&a->dev_attr.attr);
 		ret = iio_get_channel_type(&st->channels[i], &type);
 		if (ret < 0)
-			goto error_release_channels;
+			return ret;
 
 		switch (type) {
 		case IIO_VOLTAGE:
@@ -134,13 +127,11 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 							       humidity_i++);
 			break;
 		default:
-			ret = -EINVAL;
-			goto error_release_channels;
-		}
-		if (a->dev_attr.attr.name == NULL) {
-			ret = -ENOMEM;
-			goto error_release_channels;
+			return -EINVAL;
 		}
+		if (a->dev_attr.attr.name == NULL)
+			return -ENOMEM;
+
 		a->dev_attr.show = iio_hwmon_read_val;
 		a->dev_attr.attr.mode = S_IRUGO;
 		a->index = i;
@@ -151,34 +142,13 @@ static int iio_hwmon_probe(struct platform_device *pdev)
 	st->groups[0] = &st->attr_group;
 
 	sname = devm_kstrdup(dev, name, GFP_KERNEL);
-	if (!sname) {
-		ret = -ENOMEM;
-		goto error_release_channels;
-	}
+	if (!sname)
+		return -ENOMEM;
 
 	strreplace(sname, '-', '_');
-	st->hwmon_dev = hwmon_device_register_with_groups(dev, sname, st,
-							  st->groups);
-	if (IS_ERR(st->hwmon_dev)) {
-		ret = PTR_ERR(st->hwmon_dev);
-		goto error_release_channels;
-	}
-	platform_set_drvdata(pdev, st);
-	return 0;
-
-error_release_channels:
-	iio_channel_release_all(channels);
-	return ret;
-}
-
-static int iio_hwmon_remove(struct platform_device *pdev)
-{
-	struct iio_hwmon_state *st = platform_get_drvdata(pdev);
-
-	hwmon_device_unregister(st->hwmon_dev);
-	iio_channel_release_all(st->channels);
-
-	return 0;
+	hwmon_dev = devm_hwmon_device_register_with_groups(dev, sname, st,
+							   st->groups);
+	return PTR_ERR_OR_ZERO(hwmon_dev);
 }
 
 static const struct of_device_id iio_hwmon_of_match[] = {
@@ -193,7 +163,6 @@ static struct platform_driver __refdata iio_hwmon_driver = {
 		.of_match_table = iio_hwmon_of_match,
 	},
 	.probe = iio_hwmon_probe,
-	.remove = iio_hwmon_remove,
 };
 
 module_platform_driver(iio_hwmon_driver);
-- 
cgit v1.2.3


From 78170811a2048de8e77a27a053be8b3eb3d4e556 Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Mon, 23 Jul 2018 09:47:46 +0200
Subject: regulator: pfuze100: add optional disable switch-regulators binding

This binding is used to keep the backward compatibility with the current
dtb's [1]. The binding informs the driver that the unused switch regulators
can be disabled.
If it is not specified, the driver doesn't disable the switch regulators.

[1] https://patchwork.kernel.org/patch/10490381/

Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/regulator/pfuze100.txt | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/devicetree/bindings/regulator/pfuze100.txt b/Documentation/devicetree/bindings/regulator/pfuze100.txt
index 672c939045ff..c7610718adff 100644
--- a/Documentation/devicetree/bindings/regulator/pfuze100.txt
+++ b/Documentation/devicetree/bindings/regulator/pfuze100.txt
@@ -4,6 +4,15 @@ Required properties:
 - compatible: "fsl,pfuze100", "fsl,pfuze200", "fsl,pfuze3000", "fsl,pfuze3001"
 - reg: I2C slave address
 
+Optional properties:
+- fsl,pfuze-support-disable-sw: Boolean, if present disable all unused switch
+  regulators to save power consumption. Attention, ensure that all important
+  regulators (e.g. DDR ref, DDR supply) has set the "regulator-always-on"
+  property. If not present, the switched regualtors are always on and can't be
+  disabled. This binding is a workaround to keep backward compatibility with
+  old dtb's which rely on the fact that the switched regulators are always on
+  and don't mark them explicit as "regulator-always-on".
+
 Required child node:
 - regulators: This is the list of child nodes that specify the regulator
   initialization data for defined regulators. Please refer to below doc
-- 
cgit v1.2.3


From 9d2fd4f0ddfbc4aa1135000df34caebc02793a26 Mon Sep 17 00:00:00 2001
From: Marco Felsch <m.felsch@pengutronix.de>
Date: Mon, 23 Jul 2018 09:47:47 +0200
Subject: regulator: pfuze100: add support to en-/disable switch regulators

Add enable/disable support for switch regulators on pfuze100.

Based on commit 5fe156f1cab4 ("regulator: pfuze100: add enable/disable for
switch") which is reverted due to boot regressions by commit 464a5686e6c9
("regulator: Revert "regulator: pfuze100: add enable/disable for switch"").
Disabling the switch regulators will only be done if the user specifies
"fsl,pfuze-support-disable-sw" in its device tree to keep backward
compatibility with current dtb's [1].

[1] https://patchwork.kernel.org/patch/10490381/

Signed-off-by: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/pfuze100-regulator.c | 36 ++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/drivers/regulator/pfuze100-regulator.c b/drivers/regulator/pfuze100-regulator.c
index cde6eda1d283..31c3a236120a 100644
--- a/drivers/regulator/pfuze100-regulator.c
+++ b/drivers/regulator/pfuze100-regulator.c
@@ -17,6 +17,8 @@
 #include <linux/slab.h>
 #include <linux/regmap.h>
 
+#define PFUZE_FLAG_DISABLE_SW	BIT(1)
+
 #define PFUZE_NUMREGS		128
 #define PFUZE100_VOL_OFFSET	0
 #define PFUZE100_STANDBY_OFFSET	1
@@ -50,10 +52,12 @@ struct pfuze_regulator {
 	struct regulator_desc desc;
 	unsigned char stby_reg;
 	unsigned char stby_mask;
+	bool sw_reg;
 };
 
 struct pfuze_chip {
 	int	chip_id;
+	int     flags;
 	struct regmap *regmap;
 	struct device *dev;
 	struct pfuze_regulator regulator_descs[PFUZE100_MAX_REGULATOR];
@@ -170,6 +174,17 @@ static const struct regulator_ops pfuze100_sw_regulator_ops = {
 	.set_ramp_delay = pfuze100_set_ramp_delay,
 };
 
+static const struct regulator_ops pfuze100_sw_disable_regulator_ops = {
+	.enable = regulator_enable_regmap,
+	.disable = regulator_disable_regmap,
+	.is_enabled = regulator_is_enabled_regmap,
+	.list_voltage = regulator_list_voltage_linear,
+	.set_voltage_sel = regulator_set_voltage_sel_regmap,
+	.get_voltage_sel = regulator_get_voltage_sel_regmap,
+	.set_voltage_time_sel = regulator_set_voltage_time_sel,
+	.set_ramp_delay = pfuze100_set_ramp_delay,
+};
+
 static const struct regulator_ops pfuze100_swb_regulator_ops = {
 	.enable = regulator_enable_regmap,
 	.disable = regulator_disable_regmap,
@@ -209,9 +224,12 @@ static const struct regulator_ops pfuze100_swb_regulator_ops = {
 			.uV_step = (step),	\
 			.vsel_reg = (base) + PFUZE100_VOL_OFFSET,	\
 			.vsel_mask = 0x3f,	\
+			.enable_reg = (base) + PFUZE100_MODE_OFFSET,	\
+			.enable_mask = 0xf,	\
 		},	\
 		.stby_reg = (base) + PFUZE100_STANDBY_OFFSET,	\
 		.stby_mask = 0x3f,	\
+		.sw_reg = true,		\
 	}
 
 #define PFUZE100_SWB_REG(_chip, _name, base, mask, voltages)	\
@@ -471,6 +489,9 @@ static int pfuze_parse_regulators_dt(struct pfuze_chip *chip)
 	if (!np)
 		return -EINVAL;
 
+	if (of_property_read_bool(np, "fsl,pfuze-support-disable-sw"))
+		chip->flags |= PFUZE_FLAG_DISABLE_SW;
+
 	parent = of_get_child_by_name(np, "regulators");
 	if (!parent) {
 		dev_err(dev, "regulators node not found\n");
@@ -703,6 +724,21 @@ static int pfuze100_regulator_probe(struct i2c_client *client,
 			}
 		}
 
+		/*
+		 * Allow SW regulators to turn off. Checking it trough a flag is
+		 * a workaround to keep the backward compatibility with existing
+		 * old dtb's which may relay on the fact that we didn't disable
+		 * the switched regulator till yet.
+		 */
+		if (pfuze_chip->flags & PFUZE_FLAG_DISABLE_SW) {
+			if (pfuze_chip->regulator_descs[i].sw_reg) {
+				desc->ops = &pfuze100_sw_disable_regulator_ops;
+				desc->enable_val = 0x8;
+				desc->disable_val = 0x0;
+				desc->enable_time = 500;
+			}
+		}
+
 		config.dev = &client->dev;
 		config.init_data = init_data;
 		config.driver_data = pfuze_chip;
-- 
cgit v1.2.3


From 2f562a4739602d96928de0b040ce46b00d8d3adc Mon Sep 17 00:00:00 2001
From: Liang Chen <cl@rock-chips.com>
Date: Mon, 23 Jul 2018 17:25:21 +0800
Subject: ASoC: rockchip-i2s: add description for px30

Add "rockchip,px30-i2s", "rockchip,rk3066-i2s" for i2s on px30 platform.

Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Liang Chen <cl@rock-chips.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/rockchip-i2s.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
index b208a752576c..54aefab71f2c 100644
--- a/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
+++ b/Documentation/devicetree/bindings/sound/rockchip-i2s.txt
@@ -7,6 +7,7 @@ Required properties:
 
 - compatible: should be one of the following:
    - "rockchip,rk3066-i2s": for rk3066
+   - "rockchip,px30-i2s", "rockchip,rk3066-i2s": for px30
    - "rockchip,rk3036-i2s", "rockchip,rk3066-i2s": for rk3036
    - "rockchip,rk3188-i2s", "rockchip,rk3066-i2s": for rk3188
    - "rockchip,rk3228-i2s", "rockchip,rk3066-i2s": for rk3228
-- 
cgit v1.2.3


From 388c4bb4dc1fc861dff425d37b0d6438f0e694bb Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 23 Jul 2018 21:10:02 +0300
Subject: sh_eth: uninline sh_eth_tsu_get_offset()

sh_eth_tsu_get_offset() is called several  times  by the driver, remove
*inline* and move  that function  from the header to the driver  itself
to let gcc decide  whether to expand it inline or not...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 5 +++++
 drivers/net/ethernet/renesas/sh_eth.h | 6 ------
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 314aeb5dd921..1f8d5a08bdce 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -439,6 +439,11 @@ static void sh_eth_modify(struct net_device *ndev, int enum_index, u32 clear,
 		     enum_index);
 }
 
+static void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp, int enum_index)
+{
+	return mdp->tsu_addr + mdp->reg_offset[enum_index];
+}
+
 static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data,
 			     int enum_index)
 {
diff --git a/drivers/net/ethernet/renesas/sh_eth.h b/drivers/net/ethernet/renesas/sh_eth.h
index 140ad2c57095..f94be99cf400 100644
--- a/drivers/net/ethernet/renesas/sh_eth.h
+++ b/drivers/net/ethernet/renesas/sh_eth.h
@@ -558,10 +558,4 @@ struct sh_eth_private {
 	unsigned wol_enabled:1;
 };
 
-static inline void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp,
-					  int enum_index)
-{
-	return mdp->tsu_addr + mdp->reg_offset[enum_index];
-}
-
 #endif	/* #ifndef __SH_ETH_H__ */
-- 
cgit v1.2.3


From 41414f0a8568d1f395d823bc65e68ee0805d794f Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 23 Jul 2018 21:11:19 +0300
Subject: sh_eth: make sh_eth_tsu_get_offset() match its name

sh_eth_tsu_get_offset(), despite its name, returns a TSU register's address,
not its offset.  Make this  function match its name and return a register's
offset  from the TSU  registers base address instead.

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 24 ++++++++++++++----------
 1 file changed, 14 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index 1f8d5a08bdce..b813ef4ea51a 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -439,9 +439,9 @@ static void sh_eth_modify(struct net_device *ndev, int enum_index, u32 clear,
 		     enum_index);
 }
 
-static void *sh_eth_tsu_get_offset(struct sh_eth_private *mdp, int enum_index)
+static u16 sh_eth_tsu_get_offset(struct sh_eth_private *mdp, int enum_index)
 {
-	return mdp->tsu_addr + mdp->reg_offset[enum_index];
+	return mdp->reg_offset[enum_index];
 }
 
 static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data,
@@ -2712,12 +2712,12 @@ static void sh_eth_tsu_read_entry(void *reg, u8 *addr)
 static int sh_eth_tsu_find_entry(struct net_device *ndev, const u8 *addr)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int i;
 	u8 c_addr[ETH_ALEN];
 
 	for (i = 0; i < SH_ETH_TSU_CAM_ENTRIES; i++, reg_offset += 8) {
-		sh_eth_tsu_read_entry(reg_offset, c_addr);
+		sh_eth_tsu_read_entry(mdp->tsu_addr + reg_offset, c_addr);
 		if (ether_addr_equal(addr, c_addr))
 			return i;
 	}
@@ -2739,7 +2739,7 @@ static int sh_eth_tsu_disable_cam_entry_table(struct net_device *ndev,
 					      int entry)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int ret;
 	u8 blank[ETH_ALEN];
 
@@ -2747,7 +2747,9 @@ static int sh_eth_tsu_disable_cam_entry_table(struct net_device *ndev,
 			 ~(1 << (31 - entry)), TSU_TEN);
 
 	memset(blank, 0, sizeof(blank));
-	ret = sh_eth_tsu_write_entry(ndev, reg_offset + entry * 8, blank);
+	ret = sh_eth_tsu_write_entry(ndev,
+				     mdp->tsu_addr + reg_offset + entry * 8,
+				     blank);
 	if (ret < 0)
 		return ret;
 	return 0;
@@ -2756,7 +2758,7 @@ static int sh_eth_tsu_disable_cam_entry_table(struct net_device *ndev,
 static int sh_eth_tsu_add_entry(struct net_device *ndev, const u8 *addr)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int i, ret;
 
 	if (!mdp->cd->tsu)
@@ -2768,7 +2770,9 @@ static int sh_eth_tsu_add_entry(struct net_device *ndev, const u8 *addr)
 		i = sh_eth_tsu_find_empty(ndev);
 		if (i < 0)
 			return -ENOMEM;
-		ret = sh_eth_tsu_write_entry(ndev, reg_offset + i * 8, addr);
+		ret = sh_eth_tsu_write_entry(ndev,
+					     mdp->tsu_addr + reg_offset + i * 8,
+					     addr);
 		if (ret < 0)
 			return ret;
 
@@ -2830,15 +2834,15 @@ static int sh_eth_tsu_purge_all(struct net_device *ndev)
 static void sh_eth_tsu_purge_mcast(struct net_device *ndev)
 {
 	struct sh_eth_private *mdp = netdev_priv(ndev);
+	u16 reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	u8 addr[ETH_ALEN];
-	void *reg_offset = sh_eth_tsu_get_offset(mdp, TSU_ADRH0);
 	int i;
 
 	if (!mdp->cd->tsu)
 		return;
 
 	for (i = 0; i < SH_ETH_TSU_CAM_ENTRIES; i++, reg_offset += 8) {
-		sh_eth_tsu_read_entry(reg_offset, addr);
+		sh_eth_tsu_read_entry(mdp->tsu_addr + reg_offset, addr);
 		if (is_multicast_ether_addr(addr))
 			sh_eth_tsu_del_entry(ndev, addr);
 	}
-- 
cgit v1.2.3


From ecbecb0a90fbc318163dd1747bd325e08aee4b12 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 23 Jul 2018 21:12:38 +0300
Subject: sh_eth: call sh_eth_tsu_get_offset() from TSU register accessors

With sh_eth_tsu_get_offset() now actually returning TSU register's offset,
we  can at last use it in sh_eth_tsu_{read|write}(). Somehow this saves 248
bytes of object code with AArch64 gcc 4.8.5... :-)

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index b813ef4ea51a..bf002c2b5d79 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -447,7 +447,7 @@ static u16 sh_eth_tsu_get_offset(struct sh_eth_private *mdp, int enum_index)
 static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data,
 			     int enum_index)
 {
-	u16 offset = mdp->reg_offset[enum_index];
+	u16 offset = sh_eth_tsu_get_offset(mdp, enum_index);
 
 	if (WARN_ON(offset == SH_ETH_OFFSET_INVALID))
 		return;
@@ -457,7 +457,7 @@ static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data,
 
 static u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index)
 {
-	u16 offset = mdp->reg_offset[enum_index];
+	u16 offset = sh_eth_tsu_get_offset(mdp, enum_index);
 
 	if (WARN_ON(offset == SH_ETH_OFFSET_INVALID))
 		return ~0U;
-- 
cgit v1.2.3


From 7a54c867bad601406d71f375362048d8ccfb5fae Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 23 Jul 2018 21:14:38 +0300
Subject: sh_eth: make sh_eth_tsu_write_entry() take 'offset' parameter

We can add the TSU register base address to a TSU register offset right
in sh_eth_tsu_write_entry(),  no need to do it in its callers...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index bf002c2b5d79..b3434109e5e1 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2676,18 +2676,19 @@ static int sh_eth_tsu_busy(struct net_device *ndev)
 	return 0;
 }
 
-static int sh_eth_tsu_write_entry(struct net_device *ndev, void *reg,
+static int sh_eth_tsu_write_entry(struct net_device *ndev, u16 offset,
 				  const u8 *addr)
 {
+	struct sh_eth_private *mdp = netdev_priv(ndev);
 	u32 val;
 
 	val = addr[0] << 24 | addr[1] << 16 | addr[2] << 8 | addr[3];
-	iowrite32(val, reg);
+	iowrite32(val, mdp->tsu_addr + offset);
 	if (sh_eth_tsu_busy(ndev) < 0)
 		return -EBUSY;
 
 	val = addr[4] << 8 | addr[5];
-	iowrite32(val, reg + 4);
+	iowrite32(val, mdp->tsu_addr + offset + 4);
 	if (sh_eth_tsu_busy(ndev) < 0)
 		return -EBUSY;
 
@@ -2747,9 +2748,7 @@ static int sh_eth_tsu_disable_cam_entry_table(struct net_device *ndev,
 			 ~(1 << (31 - entry)), TSU_TEN);
 
 	memset(blank, 0, sizeof(blank));
-	ret = sh_eth_tsu_write_entry(ndev,
-				     mdp->tsu_addr + reg_offset + entry * 8,
-				     blank);
+	ret = sh_eth_tsu_write_entry(ndev, reg_offset + entry * 8, blank);
 	if (ret < 0)
 		return ret;
 	return 0;
@@ -2770,9 +2769,7 @@ static int sh_eth_tsu_add_entry(struct net_device *ndev, const u8 *addr)
 		i = sh_eth_tsu_find_empty(ndev);
 		if (i < 0)
 			return -ENOMEM;
-		ret = sh_eth_tsu_write_entry(ndev,
-					     mdp->tsu_addr + reg_offset + i * 8,
-					     addr);
+		ret = sh_eth_tsu_write_entry(ndev, reg_offset + i * 8, addr);
 		if (ret < 0)
 			return ret;
 
-- 
cgit v1.2.3


From 51459d4c76e551d006a7e22ce54ba4039480cd19 Mon Sep 17 00:00:00 2001
From: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Date: Mon, 23 Jul 2018 21:15:47 +0300
Subject: sh_eth: make sh_eth_tsu_{read|write}_entry() prototypes symmetric

sh_eth_tsu_read_entry() is still asymmetric with sh_eth_tsu_write_entry()
WRT their prototypes -- make them symmetric by passing to the former a TSU
register offset instead of its address and also adding the (now necessary)
'ndev' parameter...

Signed-off-by: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/renesas/sh_eth.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
index b3434109e5e1..5573199c4536 100644
--- a/drivers/net/ethernet/renesas/sh_eth.c
+++ b/drivers/net/ethernet/renesas/sh_eth.c
@@ -2695,16 +2695,17 @@ static int sh_eth_tsu_write_entry(struct net_device *ndev, u16 offset,
 	return 0;
 }
 
-static void sh_eth_tsu_read_entry(void *reg, u8 *addr)
+static void sh_eth_tsu_read_entry(struct net_device *ndev, u16 offset, u8 *addr)
 {
+	struct sh_eth_private *mdp = netdev_priv(ndev);
 	u32 val;
 
-	val = ioread32(reg);
+	val = ioread32(mdp->tsu_addr + offset);
 	addr[0] = (val >> 24) & 0xff;
 	addr[1] = (val >> 16) & 0xff;
 	addr[2] = (val >> 8) & 0xff;
 	addr[3] = val & 0xff;
-	val = ioread32(reg + 4);
+	val = ioread32(mdp->tsu_addr + offset + 4);
 	addr[4] = (val >> 8) & 0xff;
 	addr[5] = val & 0xff;
 }
@@ -2718,7 +2719,7 @@ static int sh_eth_tsu_find_entry(struct net_device *ndev, const u8 *addr)
 	u8 c_addr[ETH_ALEN];
 
 	for (i = 0; i < SH_ETH_TSU_CAM_ENTRIES; i++, reg_offset += 8) {
-		sh_eth_tsu_read_entry(mdp->tsu_addr + reg_offset, c_addr);
+		sh_eth_tsu_read_entry(ndev, reg_offset, c_addr);
 		if (ether_addr_equal(addr, c_addr))
 			return i;
 	}
@@ -2839,7 +2840,7 @@ static void sh_eth_tsu_purge_mcast(struct net_device *ndev)
 		return;
 
 	for (i = 0; i < SH_ETH_TSU_CAM_ENTRIES; i++, reg_offset += 8) {
-		sh_eth_tsu_read_entry(mdp->tsu_addr + reg_offset, addr);
+		sh_eth_tsu_read_entry(ndev, reg_offset, addr);
 		if (is_multicast_ether_addr(addr))
 			sh_eth_tsu_del_entry(ndev, addr);
 	}
-- 
cgit v1.2.3


From 129a99890936766f4b69b9da7ed88366313a9210 Mon Sep 17 00:00:00 2001
From: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Date: Thu, 19 Jul 2018 11:42:58 +0200
Subject: Smack: Fix handling of IPv4 traffic received by PF_INET6 sockets

A socket which has sk_family set to PF_INET6 is able to receive not
only IPv6 but also IPv4 traffic (IPv4-mapped IPv6 addresses).

Prior to this patch, the smk_skb_to_addr_ipv6() could have been
called for socket buffers containing IPv4 packets, in result such
traffic was allowed.

Signed-off-by: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
---
 security/smack/smack_lsm.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index 7ad226018f51..c4feb954d53f 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3923,15 +3923,19 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	struct smack_known *skp = NULL;
 	int rc = 0;
 	struct smk_audit_info ad;
+	u16 family = sk->sk_family;
 #ifdef CONFIG_AUDIT
 	struct lsm_network_audit net;
 #endif
 #if IS_ENABLED(CONFIG_IPV6)
 	struct sockaddr_in6 sadd;
 	int proto;
+
+	if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
+		family = PF_INET;
 #endif /* CONFIG_IPV6 */
 
-	switch (sk->sk_family) {
+	switch (family) {
 	case PF_INET:
 #ifdef CONFIG_SECURITY_SMACK_NETFILTER
 		/*
@@ -3949,7 +3953,7 @@ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		 */
 		netlbl_secattr_init(&secattr);
 
-		rc = netlbl_skbuff_getattr(skb, sk->sk_family, &secattr);
+		rc = netlbl_skbuff_getattr(skb, family, &secattr);
 		if (rc == 0)
 			skp = smack_from_secattr(&secattr, ssp);
 		else
@@ -3962,7 +3966,7 @@ access_check:
 #endif
 #ifdef CONFIG_AUDIT
 		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
-		ad.a.u.net->family = sk->sk_family;
+		ad.a.u.net->family = family;
 		ad.a.u.net->netif = skb->skb_iif;
 		ipv4_skb_to_auditdata(skb, &ad.a, NULL);
 #endif
@@ -3976,7 +3980,7 @@ access_check:
 		rc = smk_bu_note("IPv4 delivery", skp, ssp->smk_in,
 					MAY_WRITE, rc);
 		if (rc != 0)
-			netlbl_skbuff_err(skb, sk->sk_family, rc, 0);
+			netlbl_skbuff_err(skb, family, rc, 0);
 		break;
 #if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6:
@@ -3992,7 +3996,7 @@ access_check:
 			skp = smack_net_ambient;
 #ifdef CONFIG_AUDIT
 		smk_ad_init_net(&ad, __func__, LSM_AUDIT_DATA_NET, &net);
-		ad.a.u.net->family = sk->sk_family;
+		ad.a.u.net->family = family;
 		ad.a.u.net->netif = skb->skb_iif;
 		ipv6_skb_to_auditdata(skb, &ad.a, NULL);
 #endif /* CONFIG_AUDIT */
-- 
cgit v1.2.3


From a07ef9516477aef2d052d75129a48f9f94d3b3f3 Mon Sep 17 00:00:00 2001
From: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Date: Thu, 19 Jul 2018 11:45:16 +0200
Subject: Smack: Check UDP-Lite and DCCP protocols during IPv6 handling

The smack_socket_sock_rcv_skb() function is checking smack labels
only for UDP and TCP frames carried in IPv6 packets. From now on,
it is able also to handle UDP-Lite and DCCP protocols.

Signed-off-by: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
---
 security/smack/smack_lsm.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index c4feb954d53f..aff8397e8c7e 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -3895,6 +3895,7 @@ static int smk_skb_to_addr_ipv6(struct sk_buff *skb, struct sockaddr_in6 *sip)
 			sip->sin6_port = th->source;
 		break;
 	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
 		uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph);
 		if (uh != NULL)
 			sip->sin6_port = uh->source;
@@ -3985,7 +3986,8 @@ access_check:
 #if IS_ENABLED(CONFIG_IPV6)
 	case PF_INET6:
 		proto = smk_skb_to_addr_ipv6(skb, &sadd);
-		if (proto != IPPROTO_UDP && proto != IPPROTO_TCP)
+		if (proto != IPPROTO_UDP && proto != IPPROTO_UDPLITE &&
+		    proto != IPPROTO_TCP && proto != IPPROTO_DCCP)
 			break;
 #ifdef SMACK_IPV6_SECMARK_LABELING
 		if (skb && skb->secmark != 0)
-- 
cgit v1.2.3


From d66a8acbda926fa2398ae930f50787e8663bce96 Mon Sep 17 00:00:00 2001
From: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Date: Thu, 19 Jul 2018 11:47:31 +0200
Subject: Smack: Inform peer that IPv6 traffic has been blocked

In this patch we're sending an ICMPv6 message to a peer to
immediately inform it that making a connection is not possible.
In case of TCP connections, without this change, the peer
will be waiting until a connection timeout is exceeded.

Signed-off-by: Piotr Sawicki <p.sawicki2@partner.samsung.com>
Signed-off-by: Casey Schaufler <casey@schaufler-ca.com>
---
 security/smack/smack_lsm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
index aff8397e8c7e..91750205a5de 100644
--- a/security/smack/smack_lsm.c
+++ b/security/smack/smack_lsm.c
@@ -28,6 +28,7 @@
 #include <linux/tcp.h>
 #include <linux/udp.h>
 #include <linux/dccp.h>
+#include <linux/icmpv6.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
 #include <linux/pipe_fs_i.h>
@@ -4009,6 +4010,9 @@ access_check:
 #ifdef SMACK_IPV6_PORT_LABELING
 		rc = smk_ipv6_port_check(sk, &sadd, SMK_RECEIVING);
 #endif /* SMACK_IPV6_PORT_LABELING */
+		if (rc != 0)
+			icmpv6_send(skb, ICMPV6_DEST_UNREACH,
+					ICMPV6_ADM_PROHIBITED, 0);
 		break;
 #endif /* CONFIG_IPV6 */
 	}
-- 
cgit v1.2.3


From 0cf632265d6753e9bcdf2bc196999ea40c02f2dd Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:26 -0400
Subject: lan743x: Add support for ethtool get_drvinfo

Implement ethtool get_drvinfo

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/Makefile          |  2 +-
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 21 +++++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_ethtool.h | 11 +++++++++++
 drivers/net/ethernet/microchip/lan743x_main.c    |  2 ++
 4 files changed, 35 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/microchip/lan743x_ethtool.c
 create mode 100644 drivers/net/ethernet/microchip/lan743x_ethtool.h

diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile
index 2e982cc249fb..43f47cb45fe2 100644
--- a/drivers/net/ethernet/microchip/Makefile
+++ b/drivers/net/ethernet/microchip/Makefile
@@ -6,4 +6,4 @@ obj-$(CONFIG_ENC28J60) += enc28j60.o
 obj-$(CONFIG_ENCX24J600) += encx24j600.o encx24j600-regmap.o
 obj-$(CONFIG_LAN743X) += lan743x.o
 
-lan743x-objs := lan743x_main.o
+lan743x-objs := lan743x_main.o lan743x_ethtool.o
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
new file mode 100644
index 000000000000..0e20758b54de
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#include <linux/netdevice.h>
+#include "lan743x_main.h"
+#include "lan743x_ethtool.h"
+#include <linux/pci.h>
+
+static void lan743x_ethtool_get_drvinfo(struct net_device *netdev,
+					struct ethtool_drvinfo *info)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	strlcpy(info->driver, DRIVER_NAME, sizeof(info->driver));
+	strlcpy(info->bus_info,
+		pci_name(adapter->pdev), sizeof(info->bus_info));
+}
+
+const struct ethtool_ops lan743x_ethtool_ops = {
+	.get_drvinfo = lan743x_ethtool_get_drvinfo,
+};
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.h b/drivers/net/ethernet/microchip/lan743x_ethtool.h
new file mode 100644
index 000000000000..d0d11a777a58
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#ifndef _LAN743X_ETHTOOL_H
+#define _LAN743X_ETHTOOL_H
+
+#include "linux/ethtool.h"
+
+extern const struct ethtool_ops lan743x_ethtool_ops;
+
+#endif /* _LAN743X_ETHTOOL_H */
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index e1747a490066..ade3b04b2de6 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -12,6 +12,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/iopoll.h>
 #include "lan743x_main.h"
+#include "lan743x_ethtool.h"
 
 static void lan743x_pci_cleanup(struct lan743x_adapter *adapter)
 {
@@ -2689,6 +2690,7 @@ static int lan743x_pcidev_probe(struct pci_dev *pdev,
 		goto cleanup_hardware;
 
 	adapter->netdev->netdev_ops = &lan743x_netdev_ops;
+	adapter->netdev->ethtool_ops = &lan743x_ethtool_ops;
 	adapter->netdev->features = NETIF_F_SG | NETIF_F_TSO | NETIF_F_HW_CSUM;
 	adapter->netdev->hw_features = adapter->netdev->features;
 
-- 
cgit v1.2.3


From 63b92a91a49f23728721e95a363d8dbaf526e4ed Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:27 -0400
Subject: lan743x: Add support for ethtool link settings

Use default link setting functions

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 0e20758b54de..5c4582c209af 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -5,6 +5,7 @@
 #include "lan743x_main.h"
 #include "lan743x_ethtool.h"
 #include <linux/pci.h>
+#include <linux/phy.h>
 
 static void lan743x_ethtool_get_drvinfo(struct net_device *netdev,
 					struct ethtool_drvinfo *info)
@@ -18,4 +19,8 @@ static void lan743x_ethtool_get_drvinfo(struct net_device *netdev,
 
 const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_drvinfo = lan743x_ethtool_get_drvinfo,
+	.get_link = ethtool_op_get_link,
+
+	.get_link_ksettings = phy_ethtool_get_link_ksettings,
+	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
-- 
cgit v1.2.3


From 8114e8a2f1dbad34804e0de6ab15728cf3566578 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:28 -0400
Subject: lan743x: Add support for ethtool statistics

Implement ethtool statistics

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 180 +++++++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_main.c    |   6 +-
 drivers/net/ethernet/microchip/lan743x_main.h    |  31 ++++
 3 files changed, 214 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 5c4582c209af..9ed9711c7df0 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -17,10 +17,190 @@ static void lan743x_ethtool_get_drvinfo(struct net_device *netdev,
 		pci_name(adapter->pdev), sizeof(info->bus_info));
 }
 
+static const char lan743x_set0_hw_cnt_strings[][ETH_GSTRING_LEN] = {
+	"RX FCS Errors",
+	"RX Alignment Errors",
+	"Rx Fragment Errors",
+	"RX Jabber Errors",
+	"RX Undersize Frame Errors",
+	"RX Oversize Frame Errors",
+	"RX Dropped Frames",
+	"RX Unicast Byte Count",
+	"RX Broadcast Byte Count",
+	"RX Multicast Byte Count",
+	"RX Unicast Frames",
+	"RX Broadcast Frames",
+	"RX Multicast Frames",
+	"RX Pause Frames",
+	"RX 64 Byte Frames",
+	"RX 65 - 127 Byte Frames",
+	"RX 128 - 255 Byte Frames",
+	"RX 256 - 511 Bytes Frames",
+	"RX 512 - 1023 Byte Frames",
+	"RX 1024 - 1518 Byte Frames",
+	"RX Greater 1518 Byte Frames",
+};
+
+static const char lan743x_set1_sw_cnt_strings[][ETH_GSTRING_LEN] = {
+	"RX Queue 0 Frames",
+	"RX Queue 1 Frames",
+	"RX Queue 2 Frames",
+	"RX Queue 3 Frames",
+};
+
+static const char lan743x_set2_hw_cnt_strings[][ETH_GSTRING_LEN] = {
+	"RX Total Frames",
+	"EEE RX LPI Transitions",
+	"EEE RX LPI Time",
+	"RX Counter Rollover Status",
+	"TX FCS Errors",
+	"TX Excess Deferral Errors",
+	"TX Carrier Errors",
+	"TX Bad Byte Count",
+	"TX Single Collisions",
+	"TX Multiple Collisions",
+	"TX Excessive Collision",
+	"TX Late Collisions",
+	"TX Unicast Byte Count",
+	"TX Broadcast Byte Count",
+	"TX Multicast Byte Count",
+	"TX Unicast Frames",
+	"TX Broadcast Frames",
+	"TX Multicast Frames",
+	"TX Pause Frames",
+	"TX 64 Byte Frames",
+	"TX 65 - 127 Byte Frames",
+	"TX 128 - 255 Byte Frames",
+	"TX 256 - 511 Bytes Frames",
+	"TX 512 - 1023 Byte Frames",
+	"TX 1024 - 1518 Byte Frames",
+	"TX Greater 1518 Byte Frames",
+	"TX Total Frames",
+	"EEE TX LPI Transitions",
+	"EEE TX LPI Time",
+	"TX Counter Rollover Status",
+};
+
+static const u32 lan743x_set0_hw_cnt_addr[] = {
+	STAT_RX_FCS_ERRORS,
+	STAT_RX_ALIGNMENT_ERRORS,
+	STAT_RX_FRAGMENT_ERRORS,
+	STAT_RX_JABBER_ERRORS,
+	STAT_RX_UNDERSIZE_FRAME_ERRORS,
+	STAT_RX_OVERSIZE_FRAME_ERRORS,
+	STAT_RX_DROPPED_FRAMES,
+	STAT_RX_UNICAST_BYTE_COUNT,
+	STAT_RX_BROADCAST_BYTE_COUNT,
+	STAT_RX_MULTICAST_BYTE_COUNT,
+	STAT_RX_UNICAST_FRAMES,
+	STAT_RX_BROADCAST_FRAMES,
+	STAT_RX_MULTICAST_FRAMES,
+	STAT_RX_PAUSE_FRAMES,
+	STAT_RX_64_BYTE_FRAMES,
+	STAT_RX_65_127_BYTE_FRAMES,
+	STAT_RX_128_255_BYTE_FRAMES,
+	STAT_RX_256_511_BYTES_FRAMES,
+	STAT_RX_512_1023_BYTE_FRAMES,
+	STAT_RX_1024_1518_BYTE_FRAMES,
+	STAT_RX_GREATER_1518_BYTE_FRAMES,
+};
+
+static const u32 lan743x_set2_hw_cnt_addr[] = {
+	STAT_RX_TOTAL_FRAMES,
+	STAT_EEE_RX_LPI_TRANSITIONS,
+	STAT_EEE_RX_LPI_TIME,
+	STAT_RX_COUNTER_ROLLOVER_STATUS,
+	STAT_TX_FCS_ERRORS,
+	STAT_TX_EXCESS_DEFERRAL_ERRORS,
+	STAT_TX_CARRIER_ERRORS,
+	STAT_TX_BAD_BYTE_COUNT,
+	STAT_TX_SINGLE_COLLISIONS,
+	STAT_TX_MULTIPLE_COLLISIONS,
+	STAT_TX_EXCESSIVE_COLLISION,
+	STAT_TX_LATE_COLLISIONS,
+	STAT_TX_UNICAST_BYTE_COUNT,
+	STAT_TX_BROADCAST_BYTE_COUNT,
+	STAT_TX_MULTICAST_BYTE_COUNT,
+	STAT_TX_UNICAST_FRAMES,
+	STAT_TX_BROADCAST_FRAMES,
+	STAT_TX_MULTICAST_FRAMES,
+	STAT_TX_PAUSE_FRAMES,
+	STAT_TX_64_BYTE_FRAMES,
+	STAT_TX_65_127_BYTE_FRAMES,
+	STAT_TX_128_255_BYTE_FRAMES,
+	STAT_TX_256_511_BYTES_FRAMES,
+	STAT_TX_512_1023_BYTE_FRAMES,
+	STAT_TX_1024_1518_BYTE_FRAMES,
+	STAT_TX_GREATER_1518_BYTE_FRAMES,
+	STAT_TX_TOTAL_FRAMES,
+	STAT_EEE_TX_LPI_TRANSITIONS,
+	STAT_EEE_TX_LPI_TIME,
+	STAT_TX_COUNTER_ROLLOVER_STATUS
+};
+
+static void lan743x_ethtool_get_strings(struct net_device *netdev,
+					u32 stringset, u8 *data)
+{
+	switch (stringset) {
+	case ETH_SS_STATS:
+		memcpy(data, lan743x_set0_hw_cnt_strings,
+		       sizeof(lan743x_set0_hw_cnt_strings));
+		memcpy(&data[sizeof(lan743x_set0_hw_cnt_strings)],
+		       lan743x_set1_sw_cnt_strings,
+		       sizeof(lan743x_set1_sw_cnt_strings));
+		memcpy(&data[sizeof(lan743x_set0_hw_cnt_strings) +
+		       sizeof(lan743x_set1_sw_cnt_strings)],
+		       lan743x_set2_hw_cnt_strings,
+		       sizeof(lan743x_set2_hw_cnt_strings));
+		break;
+	}
+}
+
+static void lan743x_ethtool_get_ethtool_stats(struct net_device *netdev,
+					      struct ethtool_stats *stats,
+					      u64 *data)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int data_index = 0;
+	u32 buf;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lan743x_set0_hw_cnt_addr); i++) {
+		buf = lan743x_csr_read(adapter, lan743x_set0_hw_cnt_addr[i]);
+		data[data_index++] = (u64)buf;
+	}
+	for (i = 0; i < ARRAY_SIZE(adapter->rx); i++)
+		data[data_index++] = (u64)(adapter->rx[i].frame_count);
+	for (i = 0; i < ARRAY_SIZE(lan743x_set2_hw_cnt_addr); i++) {
+		buf = lan743x_csr_read(adapter, lan743x_set2_hw_cnt_addr[i]);
+		data[data_index++] = (u64)buf;
+	}
+}
+
+static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
+{
+	switch (sset) {
+	case ETH_SS_STATS:
+	{
+		int ret;
+
+		ret = ARRAY_SIZE(lan743x_set0_hw_cnt_strings);
+		ret += ARRAY_SIZE(lan743x_set1_sw_cnt_strings);
+		ret += ARRAY_SIZE(lan743x_set2_hw_cnt_strings);
+		return ret;
+	}
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_drvinfo = lan743x_ethtool_get_drvinfo,
 	.get_link = ethtool_op_get_link,
 
+	.get_strings = lan743x_ethtool_get_strings,
+	.get_ethtool_stats = lan743x_ethtool_get_ethtool_stats,
+	.get_sset_count = lan743x_ethtool_get_sset_count,
 	.get_link_ksettings = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 };
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index ade3b04b2de6..1e2f8c67d022 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -54,13 +54,13 @@ return_error:
 	return ret;
 }
 
-static u32 lan743x_csr_read(struct lan743x_adapter *adapter, int offset)
+u32 lan743x_csr_read(struct lan743x_adapter *adapter, int offset)
 {
 	return ioread32(&adapter->csr.csr_address[offset]);
 }
 
-static void lan743x_csr_write(struct lan743x_adapter *adapter, int offset,
-			      u32 data)
+void lan743x_csr_write(struct lan743x_adapter *adapter, int offset,
+		       u32 data)
 {
 	iowrite32(data, &adapter->csr.csr_address[offset]);
 }
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 73b463a9df61..de4f2cceaad1 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -291,6 +291,7 @@
 /* MAC statistics registers */
 #define STAT_RX_FCS_ERRORS			(0x1200)
 #define STAT_RX_ALIGNMENT_ERRORS		(0x1204)
+#define STAT_RX_FRAGMENT_ERRORS			(0x1208)
 #define STAT_RX_JABBER_ERRORS			(0x120C)
 #define STAT_RX_UNDERSIZE_FRAME_ERRORS		(0x1210)
 #define STAT_RX_OVERSIZE_FRAME_ERRORS		(0x1214)
@@ -298,12 +299,26 @@
 #define STAT_RX_UNICAST_BYTE_COUNT		(0x121C)
 #define STAT_RX_BROADCAST_BYTE_COUNT		(0x1220)
 #define STAT_RX_MULTICAST_BYTE_COUNT		(0x1224)
+#define STAT_RX_UNICAST_FRAMES			(0x1228)
+#define STAT_RX_BROADCAST_FRAMES		(0x122C)
 #define STAT_RX_MULTICAST_FRAMES		(0x1230)
+#define STAT_RX_PAUSE_FRAMES			(0x1234)
+#define STAT_RX_64_BYTE_FRAMES			(0x1238)
+#define STAT_RX_65_127_BYTE_FRAMES		(0x123C)
+#define STAT_RX_128_255_BYTE_FRAMES		(0x1240)
+#define STAT_RX_256_511_BYTES_FRAMES		(0x1244)
+#define STAT_RX_512_1023_BYTE_FRAMES		(0x1248)
+#define STAT_RX_1024_1518_BYTE_FRAMES		(0x124C)
+#define STAT_RX_GREATER_1518_BYTE_FRAMES	(0x1250)
 #define STAT_RX_TOTAL_FRAMES			(0x1254)
+#define STAT_EEE_RX_LPI_TRANSITIONS		(0x1258)
+#define STAT_EEE_RX_LPI_TIME			(0x125C)
+#define STAT_RX_COUNTER_ROLLOVER_STATUS		(0x127C)
 
 #define STAT_TX_FCS_ERRORS			(0x1280)
 #define STAT_TX_EXCESS_DEFERRAL_ERRORS		(0x1284)
 #define STAT_TX_CARRIER_ERRORS			(0x1288)
+#define STAT_TX_BAD_BYTE_COUNT			(0x128C)
 #define STAT_TX_SINGLE_COLLISIONS		(0x1290)
 #define STAT_TX_MULTIPLE_COLLISIONS		(0x1294)
 #define STAT_TX_EXCESSIVE_COLLISION		(0x1298)
@@ -311,8 +326,21 @@
 #define STAT_TX_UNICAST_BYTE_COUNT		(0x12A0)
 #define STAT_TX_BROADCAST_BYTE_COUNT		(0x12A4)
 #define STAT_TX_MULTICAST_BYTE_COUNT		(0x12A8)
+#define STAT_TX_UNICAST_FRAMES			(0x12AC)
+#define STAT_TX_BROADCAST_FRAMES		(0x12B0)
 #define STAT_TX_MULTICAST_FRAMES		(0x12B4)
+#define STAT_TX_PAUSE_FRAMES			(0x12B8)
+#define STAT_TX_64_BYTE_FRAMES			(0x12BC)
+#define STAT_TX_65_127_BYTE_FRAMES		(0x12C0)
+#define STAT_TX_128_255_BYTE_FRAMES		(0x12C4)
+#define STAT_TX_256_511_BYTES_FRAMES		(0x12C8)
+#define STAT_TX_512_1023_BYTE_FRAMES		(0x12CC)
+#define STAT_TX_1024_1518_BYTE_FRAMES		(0x12D0)
+#define STAT_TX_GREATER_1518_BYTE_FRAMES	(0x12D4)
 #define STAT_TX_TOTAL_FRAMES			(0x12D8)
+#define STAT_EEE_TX_LPI_TRANSITIONS		(0x12DC)
+#define STAT_EEE_TX_LPI_TIME			(0x12E0)
+#define STAT_TX_COUNTER_ROLLOVER_STATUS		(0x12FC)
 
 /* End of Register definitions */
 
@@ -594,4 +622,7 @@ struct lan743x_rx_buffer_info {
 #define RX_PROCESS_RESULT_PACKET_RECEIVED   (1)
 #define RX_PROCESS_RESULT_PACKET_DROPPED    (2)
 
+u32 lan743x_csr_read(struct lan743x_adapter *adapter, int offset);
+void lan743x_csr_write(struct lan743x_adapter *adapter, int offset, u32 data);
+
 #endif /* _LAN743X_H */
-- 
cgit v1.2.3


From 2958337d686cdcc0940a3ab38cea2b3aaebea9da Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:29 -0400
Subject: lan743x: Add support for ethtool message level

Implement ethtool message level

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 9ed9711c7df0..bab1344106f1 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -17,6 +17,21 @@ static void lan743x_ethtool_get_drvinfo(struct net_device *netdev,
 		pci_name(adapter->pdev), sizeof(info->bus_info));
 }
 
+static u32 lan743x_ethtool_get_msglevel(struct net_device *netdev)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return adapter->msg_enable;
+}
+
+static void lan743x_ethtool_set_msglevel(struct net_device *netdev,
+					 u32 msglevel)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	adapter->msg_enable = msglevel;
+}
+
 static const char lan743x_set0_hw_cnt_strings[][ETH_GSTRING_LEN] = {
 	"RX FCS Errors",
 	"RX Alignment Errors",
@@ -196,6 +211,8 @@ static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 
 const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_drvinfo = lan743x_ethtool_get_drvinfo,
+	.get_msglevel = lan743x_ethtool_get_msglevel,
+	.set_msglevel = lan743x_ethtool_set_msglevel,
 	.get_link = ethtool_op_get_link,
 
 	.get_strings = lan743x_ethtool_get_strings,
-- 
cgit v1.2.3


From 695846047aa9b4bb387473a9fd227a51ae7de5e9 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:30 -0400
Subject: lan743x: Add support for ethtool eeprom access

Implement ethtool eeprom access
Also provides access to OTP (One Time Programming)

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 209 +++++++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_main.h    |  33 ++++
 2 files changed, 242 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index bab1344106f1..f9ad2374c413 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -7,6 +7,178 @@
 #include <linux/pci.h>
 #include <linux/phy.h>
 
+/* eeprom */
+#define LAN743X_EEPROM_MAGIC		    (0x74A5)
+#define LAN743X_OTP_MAGIC		    (0x74F3)
+#define EEPROM_INDICATOR_1		    (0xA5)
+#define EEPROM_INDICATOR_2		    (0xAA)
+#define EEPROM_MAC_OFFSET		    (0x01)
+#define MAX_EEPROM_SIZE			    512
+#define OTP_INDICATOR_1			    (0xF3)
+#define OTP_INDICATOR_2			    (0xF7)
+
+static int lan743x_otp_write(struct lan743x_adapter *adapter, u32 offset,
+			     u32 length, u8 *data)
+{
+	unsigned long timeout;
+	u32 buf;
+	int i;
+
+	buf = lan743x_csr_read(adapter, OTP_PWR_DN);
+
+	if (buf & OTP_PWR_DN_PWRDN_N_) {
+		/* clear it and wait to be cleared */
+		lan743x_csr_write(adapter, OTP_PWR_DN, 0);
+
+		timeout = jiffies + HZ;
+		do {
+			udelay(1);
+			buf = lan743x_csr_read(adapter, OTP_PWR_DN);
+			if (time_after(jiffies, timeout)) {
+				netif_warn(adapter, drv, adapter->netdev,
+					   "timeout on OTP_PWR_DN completion\n");
+				return -EIO;
+			}
+		} while (buf & OTP_PWR_DN_PWRDN_N_);
+	}
+
+	/* set to BYTE program mode */
+	lan743x_csr_write(adapter, OTP_PRGM_MODE, OTP_PRGM_MODE_BYTE_);
+
+	for (i = 0; i < length; i++) {
+		lan743x_csr_write(adapter, OTP_ADDR1,
+				  ((offset + i) >> 8) &
+				  OTP_ADDR1_15_11_MASK_);
+		lan743x_csr_write(adapter, OTP_ADDR2,
+				  ((offset + i) &
+				  OTP_ADDR2_10_3_MASK_));
+		lan743x_csr_write(adapter, OTP_PRGM_DATA, data[i]);
+		lan743x_csr_write(adapter, OTP_TST_CMD, OTP_TST_CMD_PRGVRFY_);
+		lan743x_csr_write(adapter, OTP_CMD_GO, OTP_CMD_GO_GO_);
+
+		timeout = jiffies + HZ;
+		do {
+			udelay(1);
+			buf = lan743x_csr_read(adapter, OTP_STATUS);
+			if (time_after(jiffies, timeout)) {
+				netif_warn(adapter, drv, adapter->netdev,
+					   "Timeout on OTP_STATUS completion\n");
+				return -EIO;
+			}
+		} while (buf & OTP_STATUS_BUSY_);
+	}
+
+	return 0;
+}
+
+static int lan743x_eeprom_wait(struct lan743x_adapter *adapter)
+{
+	unsigned long start_time = jiffies;
+	u32 val;
+
+	do {
+		val = lan743x_csr_read(adapter, E2P_CMD);
+
+		if (!(val & E2P_CMD_EPC_BUSY_) ||
+		    (val & E2P_CMD_EPC_TIMEOUT_))
+			break;
+		usleep_range(40, 100);
+	} while (!time_after(jiffies, start_time + HZ));
+
+	if (val & (E2P_CMD_EPC_TIMEOUT_ | E2P_CMD_EPC_BUSY_)) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "EEPROM read operation timeout\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static int lan743x_eeprom_confirm_not_busy(struct lan743x_adapter *adapter)
+{
+	unsigned long start_time = jiffies;
+	u32 val;
+
+	do {
+		val = lan743x_csr_read(adapter, E2P_CMD);
+
+		if (!(val & E2P_CMD_EPC_BUSY_))
+			return 0;
+
+		usleep_range(40, 100);
+	} while (!time_after(jiffies, start_time + HZ));
+
+	netif_warn(adapter, drv, adapter->netdev, "EEPROM is busy\n");
+	return -EIO;
+}
+
+static int lan743x_eeprom_read(struct lan743x_adapter *adapter,
+			       u32 offset, u32 length, u8 *data)
+{
+	int retval;
+	u32 val;
+	int i;
+
+	retval = lan743x_eeprom_confirm_not_busy(adapter);
+	if (retval)
+		return retval;
+
+	for (i = 0; i < length; i++) {
+		val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_READ_;
+		val |= (offset & E2P_CMD_EPC_ADDR_MASK_);
+		lan743x_csr_write(adapter, E2P_CMD, val);
+
+		retval = lan743x_eeprom_wait(adapter);
+		if (retval < 0)
+			return retval;
+
+		val = lan743x_csr_read(adapter, E2P_DATA);
+		data[i] = val & 0xFF;
+		offset++;
+	}
+
+	return 0;
+}
+
+static int lan743x_eeprom_write(struct lan743x_adapter *adapter,
+				u32 offset, u32 length, u8 *data)
+{
+	int retval;
+	u32 val;
+	int i;
+
+	retval = lan743x_eeprom_confirm_not_busy(adapter);
+	if (retval)
+		return retval;
+
+	/* Issue write/erase enable command */
+	val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_EWEN_;
+	lan743x_csr_write(adapter, E2P_CMD, val);
+
+	retval = lan743x_eeprom_wait(adapter);
+	if (retval < 0)
+		return retval;
+
+	for (i = 0; i < length; i++) {
+		/* Fill data register */
+		val = data[i];
+		lan743x_csr_write(adapter, E2P_DATA, val);
+
+		/* Send "write" command */
+		val = E2P_CMD_EPC_BUSY_ | E2P_CMD_EPC_CMD_WRITE_;
+		val |= (offset & E2P_CMD_EPC_ADDR_MASK_);
+		lan743x_csr_write(adapter, E2P_CMD, val);
+
+		retval = lan743x_eeprom_wait(adapter);
+		if (retval < 0)
+			return retval;
+
+		offset++;
+	}
+
+	return 0;
+}
+
 static void lan743x_ethtool_get_drvinfo(struct net_device *netdev,
 					struct ethtool_drvinfo *info)
 {
@@ -32,6 +204,40 @@ static void lan743x_ethtool_set_msglevel(struct net_device *netdev,
 	adapter->msg_enable = msglevel;
 }
 
+static int lan743x_ethtool_get_eeprom_len(struct net_device *netdev)
+{
+	return MAX_EEPROM_SIZE;
+}
+
+static int lan743x_ethtool_get_eeprom(struct net_device *netdev,
+				      struct ethtool_eeprom *ee, u8 *data)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	return lan743x_eeprom_read(adapter, ee->offset, ee->len, data);
+}
+
+static int lan743x_ethtool_set_eeprom(struct net_device *netdev,
+				      struct ethtool_eeprom *ee, u8 *data)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret = -EINVAL;
+
+	if (ee->magic == LAN743X_EEPROM_MAGIC)
+		ret = lan743x_eeprom_write(adapter, ee->offset, ee->len,
+					   data);
+	/* Beware!  OTP is One Time Programming ONLY!
+	 * So do some strict condition check before messing up
+	 */
+	else if ((ee->magic == LAN743X_OTP_MAGIC) &&
+		 (ee->offset == 0) &&
+		 (ee->len == MAX_EEPROM_SIZE) &&
+		 (data[0] == OTP_INDICATOR_1))
+		ret = lan743x_otp_write(adapter, ee->offset, ee->len, data);
+
+	return ret;
+}
+
 static const char lan743x_set0_hw_cnt_strings[][ETH_GSTRING_LEN] = {
 	"RX FCS Errors",
 	"RX Alignment Errors",
@@ -215,6 +421,9 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.set_msglevel = lan743x_ethtool_set_msglevel,
 	.get_link = ethtool_op_get_link,
 
+	.get_eeprom_len = lan743x_ethtool_get_eeprom_len,
+	.get_eeprom = lan743x_ethtool_get_eeprom,
+	.set_eeprom = lan743x_ethtool_set_eeprom,
 	.get_strings = lan743x_ethtool_get_strings,
 	.get_ethtool_stats = lan743x_ethtool_get_ethtool_stats,
 	.get_sset_count = lan743x_ethtool_get_sset_count,
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index de4f2cceaad1..c026b8d2ba70 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -42,6 +42,16 @@
 
 #define DP_DATA_0			(0x030)
 
+#define E2P_CMD				(0x040)
+#define E2P_CMD_EPC_BUSY_		BIT(31)
+#define E2P_CMD_EPC_CMD_WRITE_		(0x30000000)
+#define E2P_CMD_EPC_CMD_EWEN_		(0x20000000)
+#define E2P_CMD_EPC_CMD_READ_		(0x00000000)
+#define E2P_CMD_EPC_TIMEOUT_		BIT(10)
+#define E2P_CMD_EPC_ADDR_MASK_		(0x000001FF)
+
+#define E2P_DATA			(0x044)
+
 #define FCT_RX_CTL			(0xAC)
 #define FCT_RX_CTL_EN_(channel)		BIT(28 + (channel))
 #define FCT_RX_CTL_DIS_(channel)	BIT(24 + (channel))
@@ -288,6 +298,29 @@
 #define TX_CFG_C_TX_DMA_INT_STS_AUTO_CLR_	BIT(3)
 #define TX_CFG_C_TX_INT_STS_R2C_MODE_MASK_	(0x00000007)
 
+#define OTP_PWR_DN				(0x1000)
+#define OTP_PWR_DN_PWRDN_N_			BIT(0)
+
+#define OTP_ADDR1				(0x1004)
+#define OTP_ADDR1_15_11_MASK_			(0x1F)
+
+#define OTP_ADDR2				(0x1008)
+#define OTP_ADDR2_10_3_MASK_			(0xFF)
+
+#define OTP_PRGM_DATA				(0x1010)
+
+#define OTP_PRGM_MODE				(0x1014)
+#define OTP_PRGM_MODE_BYTE_			BIT(0)
+
+#define OTP_TST_CMD				(0x1024)
+#define OTP_TST_CMD_PRGVRFY_			BIT(3)
+
+#define OTP_CMD_GO				(0x1028)
+#define OTP_CMD_GO_GO_				BIT(0)
+
+#define OTP_STATUS				(0x1030)
+#define OTP_STATUS_BUSY_			BIT(0)
+
 /* MAC statistics registers */
 #define STAT_RX_FCS_ERRORS			(0x1200)
 #define STAT_RX_ALIGNMENT_ERRORS		(0x1204)
-- 
cgit v1.2.3


From 4d94282afd957a31bce51778cc31fc3b32099e79 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:31 -0400
Subject: lan743x: Add power management support

Implement power management
Supports suspend, resume, and Wake on LAN

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c |  47 ++++++
 drivers/net/ethernet/microchip/lan743x_main.c    | 176 +++++++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_main.h    |  47 ++++++
 3 files changed, 270 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index f9ad2374c413..56b45aa94632 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -415,6 +415,49 @@ static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
+#ifdef CONFIG_PM
+static void lan743x_ethtool_get_wol(struct net_device *netdev,
+				    struct ethtool_wolinfo *wol)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	wol->supported = 0;
+	wol->wolopts = 0;
+	phy_ethtool_get_wol(netdev->phydev, wol);
+
+	wol->supported |= WAKE_BCAST | WAKE_UCAST | WAKE_MCAST |
+		WAKE_MAGIC | WAKE_PHY | WAKE_ARP;
+
+	wol->wolopts |= adapter->wolopts;
+}
+
+static int lan743x_ethtool_set_wol(struct net_device *netdev,
+				   struct ethtool_wolinfo *wol)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	adapter->wolopts = 0;
+	if (wol->wolopts & WAKE_UCAST)
+		adapter->wolopts |= WAKE_UCAST;
+	if (wol->wolopts & WAKE_MCAST)
+		adapter->wolopts |= WAKE_MCAST;
+	if (wol->wolopts & WAKE_BCAST)
+		adapter->wolopts |= WAKE_BCAST;
+	if (wol->wolopts & WAKE_MAGIC)
+		adapter->wolopts |= WAKE_MAGIC;
+	if (wol->wolopts & WAKE_PHY)
+		adapter->wolopts |= WAKE_PHY;
+	if (wol->wolopts & WAKE_ARP)
+		adapter->wolopts |= WAKE_ARP;
+
+	device_set_wakeup_enable(&adapter->pdev->dev, (bool)wol->wolopts);
+
+	phy_ethtool_set_wol(netdev->phydev, wol);
+
+	return 0;
+}
+#endif /* CONFIG_PM */
+
 const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_drvinfo = lan743x_ethtool_get_drvinfo,
 	.get_msglevel = lan743x_ethtool_get_msglevel,
@@ -429,4 +472,8 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_sset_count = lan743x_ethtool_get_sset_count,
 	.get_link_ksettings = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
+#ifdef CONFIG_PM
+	.get_wol = lan743x_ethtool_get_wol,
+	.set_wol = lan743x_ethtool_set_wol,
+#endif
 };
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 1e2f8c67d022..30178f87fe5c 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -11,6 +11,7 @@
 #include <linux/phy.h>
 #include <linux/rtnetlink.h>
 #include <linux/iopoll.h>
+#include <linux/crc16.h>
 #include "lan743x_main.h"
 #include "lan743x_ethtool.h"
 
@@ -2749,10 +2750,182 @@ static void lan743x_pcidev_shutdown(struct pci_dev *pdev)
 		lan743x_netdev_close(netdev);
 	rtnl_unlock();
 
+#ifdef CONFIG_PM
+	pci_save_state(pdev);
+#endif
+
 	/* clean up lan743x portion */
 	lan743x_hardware_cleanup(adapter);
 }
 
+#ifdef CONFIG_PM
+static u16 lan743x_pm_wakeframe_crc16(const u8 *buf, int len)
+{
+	return bitrev16(crc16(0xFFFF, buf, len));
+}
+
+static void lan743x_pm_set_wol(struct lan743x_adapter *adapter)
+{
+	const u8 ipv4_multicast[3] = { 0x01, 0x00, 0x5E };
+	const u8 ipv6_multicast[3] = { 0x33, 0x33 };
+	const u8 arp_type[2] = { 0x08, 0x06 };
+	int mask_index;
+	u32 pmtctl;
+	u32 wucsr;
+	u32 macrx;
+	u16 crc;
+
+	for (mask_index = 0; mask_index < MAC_NUM_OF_WUF_CFG; mask_index++)
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index), 0);
+
+	/* clear wake settings */
+	pmtctl = lan743x_csr_read(adapter, PMT_CTL);
+	pmtctl |= PMT_CTL_WUPS_MASK_;
+	pmtctl &= ~(PMT_CTL_GPIO_WAKEUP_EN_ | PMT_CTL_EEE_WAKEUP_EN_ |
+		PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_ |
+		PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_ | PMT_CTL_ETH_PHY_WAKE_EN_);
+
+	macrx = lan743x_csr_read(adapter, MAC_RX);
+
+	wucsr = 0;
+	mask_index = 0;
+
+	pmtctl |= PMT_CTL_ETH_PHY_D3_COLD_OVR_ | PMT_CTL_ETH_PHY_D3_OVR_;
+
+	if (adapter->wolopts & WAKE_PHY) {
+		pmtctl |= PMT_CTL_ETH_PHY_EDPD_PLL_CTL_;
+		pmtctl |= PMT_CTL_ETH_PHY_WAKE_EN_;
+	}
+	if (adapter->wolopts & WAKE_MAGIC) {
+		wucsr |= MAC_WUCSR_MPEN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_UCAST) {
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_PFDA_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_BCAST) {
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_BCST_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_MCAST) {
+		/* IPv4 multicast */
+		crc = lan743x_pm_wakeframe_crc16(ipv4_multicast, 3);
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index),
+				  MAC_WUF_CFG_EN_ | MAC_WUF_CFG_TYPE_MCAST_ |
+				  (0 << MAC_WUF_CFG_OFFSET_SHIFT_) |
+				  (crc & MAC_WUF_CFG_CRC16_MASK_));
+		lan743x_csr_write(adapter, MAC_WUF_MASK0(mask_index), 7);
+		lan743x_csr_write(adapter, MAC_WUF_MASK1(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK2(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK3(mask_index), 0);
+		mask_index++;
+
+		/* IPv6 multicast */
+		crc = lan743x_pm_wakeframe_crc16(ipv6_multicast, 2);
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index),
+				  MAC_WUF_CFG_EN_ | MAC_WUF_CFG_TYPE_MCAST_ |
+				  (0 << MAC_WUF_CFG_OFFSET_SHIFT_) |
+				  (crc & MAC_WUF_CFG_CRC16_MASK_));
+		lan743x_csr_write(adapter, MAC_WUF_MASK0(mask_index), 3);
+		lan743x_csr_write(adapter, MAC_WUF_MASK1(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK2(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK3(mask_index), 0);
+		mask_index++;
+
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_WAKE_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+	if (adapter->wolopts & WAKE_ARP) {
+		/* set MAC_WUF_CFG & WUF_MASK
+		 * for packettype (offset 12,13) = ARP (0x0806)
+		 */
+		crc = lan743x_pm_wakeframe_crc16(arp_type, 2);
+		lan743x_csr_write(adapter, MAC_WUF_CFG(mask_index),
+				  MAC_WUF_CFG_EN_ | MAC_WUF_CFG_TYPE_ALL_ |
+				  (0 << MAC_WUF_CFG_OFFSET_SHIFT_) |
+				  (crc & MAC_WUF_CFG_CRC16_MASK_));
+		lan743x_csr_write(adapter, MAC_WUF_MASK0(mask_index), 0x3000);
+		lan743x_csr_write(adapter, MAC_WUF_MASK1(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK2(mask_index), 0);
+		lan743x_csr_write(adapter, MAC_WUF_MASK3(mask_index), 0);
+		mask_index++;
+
+		wucsr |= MAC_WUCSR_RFE_WAKE_EN_ | MAC_WUCSR_WAKE_EN_;
+		macrx |= MAC_RX_RXEN_;
+		pmtctl |= PMT_CTL_WOL_EN_ | PMT_CTL_MAC_D3_RX_CLK_OVR_;
+		pmtctl |= PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_;
+	}
+
+	lan743x_csr_write(adapter, MAC_WUCSR, wucsr);
+	lan743x_csr_write(adapter, PMT_CTL, pmtctl);
+	lan743x_csr_write(adapter, MAC_RX, macrx);
+}
+
+static int lan743x_pm_suspend(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret;
+
+	lan743x_pcidev_shutdown(pdev);
+
+	/* clear all wakes */
+	lan743x_csr_write(adapter, MAC_WUCSR, 0);
+	lan743x_csr_write(adapter, MAC_WUCSR2, 0);
+	lan743x_csr_write(adapter, MAC_WK_SRC, 0xFFFFFFFF);
+
+	if (adapter->wolopts)
+		lan743x_pm_set_wol(adapter);
+
+	/* Host sets PME_En, put D3hot */
+	ret = pci_prepare_to_sleep(pdev);
+
+	return 0;
+}
+
+static int lan743x_pm_resume(struct device *dev)
+{
+	struct pci_dev *pdev = to_pci_dev(dev);
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	int ret;
+
+	pci_set_power_state(pdev, PCI_D0);
+	pci_restore_state(pdev);
+	pci_save_state(pdev);
+
+	ret = lan743x_hardware_init(adapter, pdev);
+	if (ret) {
+		netif_err(adapter, probe, adapter->netdev,
+			  "lan743x_hardware_init returned %d\n", ret);
+	}
+
+	/* open netdev when netdev is at running state while resume.
+	 * For instance, it is true when system wakesup after pm-suspend
+	 * However, it is false when system wakes up after suspend GUI menu
+	 */
+	if (netif_running(netdev))
+		lan743x_netdev_open(netdev);
+
+	netif_device_attach(netdev);
+
+	return 0;
+}
+
+const struct dev_pm_ops lan743x_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume)
+};
+#endif /*CONFIG_PM */
+
 static const struct pci_device_id lan743x_pcidev_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_SMSC, PCI_DEVICE_ID_SMSC_LAN7430) },
 	{ 0, }
@@ -2763,6 +2936,9 @@ static struct pci_driver lan743x_pcidev_driver = {
 	.id_table = lan743x_pcidev_tbl,
 	.probe    = lan743x_pcidev_probe,
 	.remove   = lan743x_pcidev_remove,
+#ifdef CONFIG_PM
+	.driver.pm = &lan743x_pm_ops,
+#endif
 	.shutdown = lan743x_pcidev_shutdown,
 };
 
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index c026b8d2ba70..72b9beba92d0 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -24,8 +24,18 @@
 #define HW_CFG_LRST_				BIT(1)
 
 #define PMT_CTL					(0x014)
+#define PMT_CTL_ETH_PHY_D3_COLD_OVR_		BIT(27)
+#define PMT_CTL_MAC_D3_RX_CLK_OVR_		BIT(25)
+#define PMT_CTL_ETH_PHY_EDPD_PLL_CTL_		BIT(24)
+#define PMT_CTL_ETH_PHY_D3_OVR_			BIT(23)
+#define PMT_CTL_RX_FCT_RFE_D3_CLK_OVR_		BIT(18)
+#define PMT_CTL_GPIO_WAKEUP_EN_			BIT(15)
+#define PMT_CTL_EEE_WAKEUP_EN_			BIT(13)
 #define PMT_CTL_READY_				BIT(7)
 #define PMT_CTL_ETH_PHY_RST_			BIT(4)
+#define PMT_CTL_WOL_EN_				BIT(3)
+#define PMT_CTL_ETH_PHY_WAKE_EN_		BIT(2)
+#define PMT_CTL_WUPS_MASK_			(0x00000003)
 
 #define DP_SEL				(0x024)
 #define DP_SEL_DPRDY_			BIT(31)
@@ -107,6 +117,38 @@
 
 #define MAC_MII_DATA			(0x124)
 
+#define MAC_WUCSR				(0x140)
+#define MAC_WUCSR_RFE_WAKE_EN_			BIT(14)
+#define MAC_WUCSR_PFDA_EN_			BIT(3)
+#define MAC_WUCSR_WAKE_EN_			BIT(2)
+#define MAC_WUCSR_MPEN_				BIT(1)
+#define MAC_WUCSR_BCST_EN_			BIT(0)
+
+#define MAC_WK_SRC				(0x144)
+
+#define MAC_WUF_CFG0			(0x150)
+#define MAC_NUM_OF_WUF_CFG		(32)
+#define MAC_WUF_CFG_BEGIN		(MAC_WUF_CFG0)
+#define MAC_WUF_CFG(index)		(MAC_WUF_CFG_BEGIN + (4 * (index)))
+#define MAC_WUF_CFG_EN_			BIT(31)
+#define MAC_WUF_CFG_TYPE_MCAST_		(0x02000000)
+#define MAC_WUF_CFG_TYPE_ALL_		(0x01000000)
+#define MAC_WUF_CFG_OFFSET_SHIFT_	(16)
+#define MAC_WUF_CFG_CRC16_MASK_		(0x0000FFFF)
+
+#define MAC_WUF_MASK0_0			(0x200)
+#define MAC_WUF_MASK0_1			(0x204)
+#define MAC_WUF_MASK0_2			(0x208)
+#define MAC_WUF_MASK0_3			(0x20C)
+#define MAC_WUF_MASK0_BEGIN		(MAC_WUF_MASK0_0)
+#define MAC_WUF_MASK1_BEGIN		(MAC_WUF_MASK0_1)
+#define MAC_WUF_MASK2_BEGIN		(MAC_WUF_MASK0_2)
+#define MAC_WUF_MASK3_BEGIN		(MAC_WUF_MASK0_3)
+#define MAC_WUF_MASK0(index)		(MAC_WUF_MASK0_BEGIN + (0x10 * (index)))
+#define MAC_WUF_MASK1(index)		(MAC_WUF_MASK1_BEGIN + (0x10 * (index)))
+#define MAC_WUF_MASK2(index)		(MAC_WUF_MASK2_BEGIN + (0x10 * (index)))
+#define MAC_WUF_MASK3(index)		(MAC_WUF_MASK3_BEGIN + (0x10 * (index)))
+
 /* offset 0x400 - 0x500, x may range from 0 to 32, for a total of 33 entries */
 #define RFE_ADDR_FILT_HI(x)		(0x400 + (8 * (x)))
 #define RFE_ADDR_FILT_HI_VALID_		BIT(31)
@@ -121,6 +163,8 @@
 #define RFE_CTL_MCAST_HASH_		BIT(3)
 #define RFE_CTL_DA_PERFECT_		BIT(1)
 
+#define MAC_WUCSR2			(0x600)
+
 #define INT_STS				(0x780)
 #define INT_BIT_DMA_RX_(channel)	BIT(24 + (channel))
 #define INT_BIT_ALL_RX_			(0x0F000000)
@@ -534,6 +578,9 @@ struct lan743x_adapter {
 	struct net_device       *netdev;
 	struct mii_bus		*mdiobus;
 	int                     msg_enable;
+#ifdef CONFIG_PM
+	u32			wolopts;
+#endif
 	struct pci_dev		*pdev;
 	struct lan743x_csr      csr;
 	struct lan743x_intr     intr;
-- 
cgit v1.2.3


From c9cf96bb5ff8004219c0df0426fe4d70f0cf3842 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:32 -0400
Subject: lan743x: Add EEE support

Implement EEE support

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 85 ++++++++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_main.h    |  3 +
 2 files changed, 88 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 56b45aa94632..86134d4fadc0 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -415,6 +415,89 @@ static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
+static int lan743x_ethtool_get_eee(struct net_device *netdev,
+				   struct ethtool_eee *eee)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	struct phy_device *phydev = netdev->phydev;
+	u32 buf;
+	int ret;
+
+	if (!phydev)
+		return -EIO;
+	if (!phydev->drv) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Missing PHY Driver\n");
+		return -EIO;
+	}
+
+	ret = phy_ethtool_get_eee(phydev, eee);
+	if (ret < 0)
+		return ret;
+
+	buf = lan743x_csr_read(adapter, MAC_CR);
+	if (buf & MAC_CR_EEE_EN_) {
+		eee->eee_enabled = true;
+		eee->eee_active = !!(eee->advertised & eee->lp_advertised);
+		eee->tx_lpi_enabled = true;
+		/* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */
+		buf = lan743x_csr_read(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT);
+		eee->tx_lpi_timer = buf;
+	} else {
+		eee->eee_enabled = false;
+		eee->eee_active = false;
+		eee->tx_lpi_enabled = false;
+		eee->tx_lpi_timer = 0;
+	}
+
+	return 0;
+}
+
+static int lan743x_ethtool_set_eee(struct net_device *netdev,
+				   struct ethtool_eee *eee)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	struct phy_device *phydev = NULL;
+	u32 buf = 0;
+	int ret = 0;
+
+	if (!netdev)
+		return -EINVAL;
+	adapter = netdev_priv(netdev);
+	if (!adapter)
+		return -EINVAL;
+	phydev = netdev->phydev;
+	if (!phydev)
+		return -EIO;
+	if (!phydev->drv) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Missing PHY Driver\n");
+		return -EIO;
+	}
+
+	if (eee->eee_enabled) {
+		ret = phy_init_eee(phydev, 0);
+		if (ret) {
+			netif_err(adapter, drv, adapter->netdev,
+				  "EEE initialization failed\n");
+			return ret;
+		}
+
+		buf = (u32)eee->tx_lpi_timer;
+		lan743x_csr_write(adapter, MAC_EEE_TX_LPI_REQ_DLY_CNT, buf);
+
+		buf = lan743x_csr_read(adapter, MAC_CR);
+		buf |= MAC_CR_EEE_EN_;
+		lan743x_csr_write(adapter, MAC_CR, buf);
+	} else {
+		buf = lan743x_csr_read(adapter, MAC_CR);
+		buf &= ~MAC_CR_EEE_EN_;
+		lan743x_csr_write(adapter, MAC_CR, buf);
+	}
+
+	return phy_ethtool_set_eee(phydev, eee);
+}
+
 #ifdef CONFIG_PM
 static void lan743x_ethtool_get_wol(struct net_device *netdev,
 				    struct ethtool_wolinfo *wol)
@@ -470,6 +553,8 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_strings = lan743x_ethtool_get_strings,
 	.get_ethtool_stats = lan743x_ethtool_get_ethtool_stats,
 	.get_sset_count = lan743x_ethtool_get_sset_count,
+	.get_eee = lan743x_ethtool_get_eee,
+	.set_eee = lan743x_ethtool_set_eee,
 	.get_link_ksettings = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings = phy_ethtool_set_link_ksettings,
 #ifdef CONFIG_PM
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 72b9beba92d0..93cb60a4eaca 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -82,6 +82,7 @@
 	((value << 0) & FCT_FLOW_CTL_ON_THRESHOLD_)
 
 #define MAC_CR				(0x100)
+#define MAC_CR_EEE_EN_			BIT(17)
 #define MAC_CR_ADD_			BIT(12)
 #define MAC_CR_ASD_			BIT(11)
 #define MAC_CR_CNTR_RST_		BIT(5)
@@ -117,6 +118,8 @@
 
 #define MAC_MII_DATA			(0x124)
 
+#define MAC_EEE_TX_LPI_REQ_DLY_CNT		(0x130)
+
 #define MAC_WUCSR				(0x140)
 #define MAC_WUCSR_RFE_WAKE_EN_			BIT(14)
 #define MAC_WUCSR_PFDA_EN_			BIT(3)
-- 
cgit v1.2.3


From 43e8fe9b844bcecbf2916a599dd744c1018c08cb Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Mon, 23 Jul 2018 16:16:33 -0400
Subject: lan743x: Add RSS support

Implement RSS support

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ethtool.c | 132 +++++++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_main.c    |  20 ++++
 drivers/net/ethernet/microchip/lan743x_main.h    |  19 ++++
 3 files changed, 171 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index 86134d4fadc0..c25b3e97ae26 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -415,6 +415,133 @@ static int lan743x_ethtool_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
+static int lan743x_ethtool_get_rxnfc(struct net_device *netdev,
+				     struct ethtool_rxnfc *rxnfc,
+				     u32 *rule_locs)
+{
+	switch (rxnfc->cmd) {
+	case ETHTOOL_GRXFH:
+		rxnfc->data = 0;
+		switch (rxnfc->flow_type) {
+		case TCP_V4_FLOW:case UDP_V4_FLOW:
+		case TCP_V6_FLOW:case UDP_V6_FLOW:
+			rxnfc->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+			/* fall through */
+		case IPV4_FLOW: case IPV6_FLOW:
+			rxnfc->data |= RXH_IP_SRC | RXH_IP_DST;
+			return 0;
+		}
+		break;
+	case ETHTOOL_GRXRINGS:
+		rxnfc->data = LAN743X_USED_RX_CHANNELS;
+		return 0;
+	}
+	return -EOPNOTSUPP;
+}
+
+static u32 lan743x_ethtool_get_rxfh_key_size(struct net_device *netdev)
+{
+	return 40;
+}
+
+static u32 lan743x_ethtool_get_rxfh_indir_size(struct net_device *netdev)
+{
+	return 128;
+}
+
+static int lan743x_ethtool_get_rxfh(struct net_device *netdev,
+				    u32 *indir, u8 *key, u8 *hfunc)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	if (indir) {
+		int dw_index;
+		int byte_index = 0;
+
+		for (dw_index = 0; dw_index < 32; dw_index++) {
+			u32 four_entries =
+				lan743x_csr_read(adapter, RFE_INDX(dw_index));
+
+			byte_index = dw_index << 2;
+			indir[byte_index + 0] =
+				((four_entries >> 0) & 0x000000FF);
+			indir[byte_index + 1] =
+				((four_entries >> 8) & 0x000000FF);
+			indir[byte_index + 2] =
+				((four_entries >> 16) & 0x000000FF);
+			indir[byte_index + 3] =
+				((four_entries >> 24) & 0x000000FF);
+		}
+	}
+	if (key) {
+		int dword_index;
+		int byte_index = 0;
+
+		for (dword_index = 0; dword_index < 10; dword_index++) {
+			u32 four_entries =
+				lan743x_csr_read(adapter,
+						 RFE_HASH_KEY(dword_index));
+
+			byte_index = dword_index << 2;
+			key[byte_index + 0] =
+				((four_entries >> 0) & 0x000000FF);
+			key[byte_index + 1] =
+				((four_entries >> 8) & 0x000000FF);
+			key[byte_index + 2] =
+				((four_entries >> 16) & 0x000000FF);
+			key[byte_index + 3] =
+				((four_entries >> 24) & 0x000000FF);
+		}
+	}
+	if (hfunc)
+		(*hfunc) = ETH_RSS_HASH_TOP;
+	return 0;
+}
+
+static int lan743x_ethtool_set_rxfh(struct net_device *netdev,
+				    const u32 *indir, const u8 *key,
+				    const u8 hfunc)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP)
+		return -EOPNOTSUPP;
+
+	if (indir) {
+		u32 indir_value = 0;
+		int dword_index = 0;
+		int byte_index = 0;
+
+		for (dword_index = 0; dword_index < 32; dword_index++) {
+			byte_index = dword_index << 2;
+			indir_value =
+				(((indir[byte_index + 0] & 0x000000FF) << 0) |
+				((indir[byte_index + 1] & 0x000000FF) << 8) |
+				((indir[byte_index + 2] & 0x000000FF) << 16) |
+				((indir[byte_index + 3] & 0x000000FF) << 24));
+			lan743x_csr_write(adapter, RFE_INDX(dword_index),
+					  indir_value);
+		}
+	}
+	if (key) {
+		int dword_index = 0;
+		int byte_index = 0;
+		u32 key_value = 0;
+
+		for (dword_index = 0; dword_index < 10; dword_index++) {
+			byte_index = dword_index << 2;
+			key_value =
+				((((u32)(key[byte_index + 0])) << 0) |
+				(((u32)(key[byte_index + 1])) << 8) |
+				(((u32)(key[byte_index + 2])) << 16) |
+				(((u32)(key[byte_index + 3])) << 24));
+			lan743x_csr_write(adapter, RFE_HASH_KEY(dword_index),
+					  key_value);
+		}
+	}
+	return 0;
+}
+
 static int lan743x_ethtool_get_eee(struct net_device *netdev,
 				   struct ethtool_eee *eee)
 {
@@ -553,6 +680,11 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_strings = lan743x_ethtool_get_strings,
 	.get_ethtool_stats = lan743x_ethtool_get_ethtool_stats,
 	.get_sset_count = lan743x_ethtool_get_sset_count,
+	.get_rxnfc = lan743x_ethtool_get_rxnfc,
+	.get_rxfh_key_size = lan743x_ethtool_get_rxfh_key_size,
+	.get_rxfh_indir_size = lan743x_ethtool_get_rxfh_indir_size,
+	.get_rxfh = lan743x_ethtool_get_rxfh,
+	.set_rxfh = lan743x_ethtool_set_rxfh,
 	.get_eee = lan743x_ethtool_get_eee,
 	.set_eee = lan743x_ethtool_set_eee,
 	.get_link_ksettings = phy_ethtool_get_link_ksettings,
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 30178f87fe5c..cd41911013e9 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1025,6 +1025,24 @@ return_error:
 	return ret;
 }
 
+static void lan743x_rfe_open(struct lan743x_adapter *adapter)
+{
+	lan743x_csr_write(adapter, RFE_RSS_CFG,
+		RFE_RSS_CFG_UDP_IPV6_EX_ |
+		RFE_RSS_CFG_TCP_IPV6_EX_ |
+		RFE_RSS_CFG_IPV6_EX_ |
+		RFE_RSS_CFG_UDP_IPV6_ |
+		RFE_RSS_CFG_TCP_IPV6_ |
+		RFE_RSS_CFG_IPV6_ |
+		RFE_RSS_CFG_UDP_IPV4_ |
+		RFE_RSS_CFG_TCP_IPV4_ |
+		RFE_RSS_CFG_IPV4_ |
+		RFE_RSS_CFG_VALID_HASH_BITS_ |
+		RFE_RSS_CFG_RSS_QUEUE_ENABLE_ |
+		RFE_RSS_CFG_RSS_HASH_STORE_ |
+		RFE_RSS_CFG_RSS_ENABLE_);
+}
+
 static void lan743x_rfe_update_mac_address(struct lan743x_adapter *adapter)
 {
 	u8 *mac_addr;
@@ -2419,6 +2437,8 @@ static int lan743x_netdev_open(struct net_device *netdev)
 	if (ret)
 		goto close_mac;
 
+	lan743x_rfe_open(adapter);
+
 	for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++) {
 		ret = lan743x_rx_open(&adapter->rx[index]);
 		if (ret)
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 93cb60a4eaca..4fa7a5e027f4 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -166,6 +166,25 @@
 #define RFE_CTL_MCAST_HASH_		BIT(3)
 #define RFE_CTL_DA_PERFECT_		BIT(1)
 
+#define RFE_RSS_CFG			(0x554)
+#define RFE_RSS_CFG_UDP_IPV6_EX_	BIT(16)
+#define RFE_RSS_CFG_TCP_IPV6_EX_	BIT(15)
+#define RFE_RSS_CFG_IPV6_EX_		BIT(14)
+#define RFE_RSS_CFG_UDP_IPV6_		BIT(13)
+#define RFE_RSS_CFG_TCP_IPV6_		BIT(12)
+#define RFE_RSS_CFG_IPV6_		BIT(11)
+#define RFE_RSS_CFG_UDP_IPV4_		BIT(10)
+#define RFE_RSS_CFG_TCP_IPV4_		BIT(9)
+#define RFE_RSS_CFG_IPV4_		BIT(8)
+#define RFE_RSS_CFG_VALID_HASH_BITS_	(0x000000E0)
+#define RFE_RSS_CFG_RSS_QUEUE_ENABLE_	BIT(2)
+#define RFE_RSS_CFG_RSS_HASH_STORE_	BIT(1)
+#define RFE_RSS_CFG_RSS_ENABLE_		BIT(0)
+
+#define RFE_HASH_KEY(index)		(0x558 + (index << 2))
+
+#define RFE_INDX(index)			(0x580 + (index << 2))
+
 #define MAC_WUCSR2			(0x600)
 
 #define INT_STS				(0x780)
-- 
cgit v1.2.3


From f53aaa31cce7b543e407da7e97690a700206f7b9 Mon Sep 17 00:00:00 2001
From: Feras Daoud <ferasda@mellanox.com>
Date: Mon, 16 Jul 2018 15:22:01 -0700
Subject: net/mlx5: FW tracer, implement tracer logic

Implement FW tracer logic and registers access, initialization and
cleanup flows.

Initializing the tracer will be part of load one flow, as multiple
PFs will try to acquire ownership but only one will succeed and will
be the tracer owner.

Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 196 +++++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  66 +++++++
 include/linux/mlx5/driver.h                        |   3 +
 3 files changed, 265 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
new file mode 100644
index 000000000000..3ecbf06b4d71
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -0,0 +1,196 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include "fw_tracer.h"
+
+static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer)
+{
+	u32 *string_db_base_address_out = tracer->str_db.base_address_out;
+	u32 *string_db_size_out = tracer->str_db.size_out;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	void *mtrc_cap_sp;
+	int err, i;
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CAP, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Error reading tracer caps %d\n",
+			       err);
+		return err;
+	}
+
+	if (!MLX5_GET(mtrc_cap, out, trace_to_memory)) {
+		mlx5_core_dbg(dev, "FWTracer: Device does not support logging traces to memory\n");
+		return -ENOTSUPP;
+	}
+
+	tracer->trc_ver = MLX5_GET(mtrc_cap, out, trc_ver);
+	tracer->str_db.first_string_trace =
+			MLX5_GET(mtrc_cap, out, first_string_trace);
+	tracer->str_db.num_string_trace =
+			MLX5_GET(mtrc_cap, out, num_string_trace);
+	tracer->str_db.num_string_db = MLX5_GET(mtrc_cap, out, num_string_db);
+	tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner);
+
+	for (i = 0; i < tracer->str_db.num_string_db; i++) {
+		mtrc_cap_sp = MLX5_ADDR_OF(mtrc_cap, out, string_db_param[i]);
+		string_db_base_address_out[i] = MLX5_GET(mtrc_string_db_param,
+							 mtrc_cap_sp,
+							 string_db_base_address);
+		string_db_size_out[i] = MLX5_GET(mtrc_string_db_param,
+						 mtrc_cap_sp, string_db_size);
+	}
+
+	return err;
+}
+
+static int mlx5_set_mtrc_caps_trace_owner(struct mlx5_fw_tracer *tracer,
+					  u32 *out, u32 out_size,
+					  u8 trace_owner)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+
+	MLX5_SET(mtrc_cap, in, trace_owner, trace_owner);
+
+	return mlx5_core_access_reg(dev, in, sizeof(in), out, out_size,
+				    MLX5_REG_MTRC_CAP, 0, 1);
+}
+
+static int mlx5_fw_tracer_ownership_acquire(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	int err;
+
+	err = mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out),
+					     MLX5_FW_TRACER_ACQUIRE_OWNERSHIP);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Acquire tracer ownership failed %d\n",
+			       err);
+		return err;
+	}
+
+	tracer->owner = !!MLX5_GET(mtrc_cap, out, trace_owner);
+
+	if (!tracer->owner)
+		return -EBUSY;
+
+	return 0;
+}
+
+static void mlx5_fw_tracer_ownership_release(struct mlx5_fw_tracer *tracer)
+{
+	u32 out[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+
+	mlx5_set_mtrc_caps_trace_owner(tracer, out, sizeof(out),
+				       MLX5_FW_TRACER_RELEASE_OWNERSHIP);
+	tracer->owner = false;
+}
+
+static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer,
+						     ownership_change_work);
+	struct mlx5_core_dev *dev = tracer->dev;
+	int err;
+
+	if (tracer->owner) {
+		mlx5_fw_tracer_ownership_release(tracer);
+		return;
+	}
+
+	err = mlx5_fw_tracer_ownership_acquire(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
+		return;
+	}
+}
+
+struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
+{
+	struct mlx5_fw_tracer *tracer = NULL;
+	int err;
+
+	if (!MLX5_CAP_MCAM_REG(dev, tracer_registers)) {
+		mlx5_core_dbg(dev, "FWTracer: Tracer capability not present\n");
+		return NULL;
+	}
+
+	tracer = kzalloc(sizeof(*tracer), GFP_KERNEL);
+	if (!tracer)
+		return ERR_PTR(-ENOMEM);
+
+	tracer->work_queue = create_singlethread_workqueue("mlx5_fw_tracer");
+	if (!tracer->work_queue) {
+		err = -ENOMEM;
+		goto free_tracer;
+	}
+
+	tracer->dev = dev;
+
+	INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change);
+
+	err = mlx5_query_mtrc_caps(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Failed to query capabilities %d\n", err);
+		goto destroy_workqueue;
+	}
+
+	mlx5_fw_tracer_ownership_change(&tracer->ownership_change_work);
+
+	return tracer;
+
+destroy_workqueue:
+	tracer->dev = NULL;
+	destroy_workqueue(tracer->work_queue);
+free_tracer:
+	kfree(tracer);
+	return ERR_PTR(err);
+}
+
+void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
+{
+	if (!tracer)
+		return;
+
+	cancel_work_sync(&tracer->ownership_change_work);
+
+	if (tracer->owner)
+		mlx5_fw_tracer_ownership_release(tracer);
+
+	flush_workqueue(tracer->work_queue);
+	destroy_workqueue(tracer->work_queue);
+	kfree(tracer);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
new file mode 100644
index 000000000000..721c41a5e827
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -0,0 +1,66 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#ifndef __LIB_TRACER_H__
+#define __LIB_TRACER_H__
+
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+
+#define STRINGS_DB_SECTIONS_NUM 8
+
+struct mlx5_fw_tracer {
+	struct mlx5_core_dev *dev;
+	bool owner;
+	u8   trc_ver;
+	struct workqueue_struct *work_queue;
+	struct work_struct ownership_change_work;
+
+	/* Strings DB */
+	struct {
+		u8 first_string_trace;
+		u8 num_string_trace;
+		u32 num_string_db;
+		u32 base_address_out[STRINGS_DB_SECTIONS_NUM];
+		u32 size_out[STRINGS_DB_SECTIONS_NUM];
+	} str_db;
+};
+
+enum mlx5_fw_tracer_ownership_state {
+	MLX5_FW_TRACER_RELEASE_OWNERSHIP,
+	MLX5_FW_TRACER_ACQUIRE_OWNERSHIP,
+};
+
+struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
+void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
+
+#endif
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 957199c20a0f..86cb0ebf92fa 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -816,6 +816,8 @@ struct mlx5_clock {
 	struct mlx5_pps            pps_info;
 };
 
+struct mlx5_fw_tracer;
+
 struct mlx5_core_dev {
 	struct pci_dev	       *pdev;
 	/* sync pci state */
@@ -860,6 +862,7 @@ struct mlx5_core_dev {
 	struct mlx5_clock        clock;
 	struct mlx5_ib_clock_info  *clock_info;
 	struct page             *clock_info_page;
+	struct mlx5_fw_tracer   *tracer;
 };
 
 struct mlx5_db {
-- 
cgit v1.2.3


From 48967ffdeb210266423be11f395c5dc26d3e4eda Mon Sep 17 00:00:00 2001
From: Feras Daoud <ferasda@mellanox.com>
Date: Tue, 6 Feb 2018 17:45:57 +0200
Subject: net/mlx5: FW tracer, create trace buffer and copy strings database

For each PF do the following:
1- Allocate memory for the tracer strings database and read the
strings from the FW to the SW. These strings will be used later for
parsing traces.
2- Allocate and dma map tracer buffers.

Traces that will be written into the buffer will be parsed as a group
of one or more traces, referred to as trace message. The trace message
represents a C-like printf string.
First trace of a message holds the pointer to the correct string in
strings database. The following traces holds the variables of the
message.

Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 209 ++++++++++++++++++++-
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  18 ++
 2 files changed, 224 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 3ecbf06b4d71..35107b8f76df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -119,6 +119,163 @@ static void mlx5_fw_tracer_ownership_release(struct mlx5_fw_tracer *tracer)
 	tracer->owner = false;
 }
 
+static int mlx5_fw_tracer_create_log_buf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct device *ddev = &dev->pdev->dev;
+	dma_addr_t dma;
+	void *buff;
+	gfp_t gfp;
+	int err;
+
+	tracer->buff.size = TRACE_BUFFER_SIZE_BYTE;
+
+	gfp = GFP_KERNEL | __GFP_ZERO;
+	buff = (void *)__get_free_pages(gfp,
+					get_order(tracer->buff.size));
+	if (!buff) {
+		err = -ENOMEM;
+		mlx5_core_warn(dev, "FWTracer: Failed to allocate pages, %d\n", err);
+		return err;
+	}
+	tracer->buff.log_buf = buff;
+
+	dma = dma_map_single(ddev, buff, tracer->buff.size, DMA_FROM_DEVICE);
+	if (dma_mapping_error(ddev, dma)) {
+		mlx5_core_warn(dev, "FWTracer: Unable to map DMA: %d\n",
+			       dma_mapping_error(ddev, dma));
+		err = -ENOMEM;
+		goto free_pages;
+	}
+	tracer->buff.dma = dma;
+
+	return 0;
+
+free_pages:
+	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
+
+	return err;
+}
+
+static void mlx5_fw_tracer_destroy_log_buf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	struct device *ddev = &dev->pdev->dev;
+
+	if (!tracer->buff.log_buf)
+		return;
+
+	dma_unmap_single(ddev, tracer->buff.dma, tracer->buff.size, DMA_FROM_DEVICE);
+	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
+}
+
+static void mlx5_fw_tracer_free_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	u32 num_string_db = tracer->str_db.num_string_db;
+	int i;
+
+	for (i = 0; i < num_string_db; i++) {
+		kfree(tracer->str_db.buffer[i]);
+		tracer->str_db.buffer[i] = NULL;
+	}
+}
+
+static int mlx5_fw_tracer_allocate_strings_db(struct mlx5_fw_tracer *tracer)
+{
+	u32 *string_db_size_out = tracer->str_db.size_out;
+	u32 num_string_db = tracer->str_db.num_string_db;
+	int i;
+
+	for (i = 0; i < num_string_db; i++) {
+		tracer->str_db.buffer[i] = kzalloc(string_db_size_out[i], GFP_KERNEL);
+		if (!tracer->str_db.buffer[i])
+			goto free_strings_db;
+	}
+
+	return 0;
+
+free_strings_db:
+	mlx5_fw_tracer_free_strings_db(tracer);
+	return -ENOMEM;
+}
+
+static void mlx5_tracer_read_strings_db(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer,
+						     read_fw_strings_work);
+	u32 num_of_reads, num_string_db = tracer->str_db.num_string_db;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 in[MLX5_ST_SZ_DW(mtrc_cap)] = {0};
+	u32 leftovers, offset;
+	int err = 0, i, j;
+	u32 *out, outlen;
+	void *out_value;
+
+	outlen = MLX5_ST_SZ_BYTES(mtrc_stdb) + STRINGS_DB_READ_SIZE_BYTES;
+	out = kzalloc(outlen, GFP_KERNEL);
+	if (!out) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < num_string_db; i++) {
+		offset = 0;
+		MLX5_SET(mtrc_stdb, in, string_db_index, i);
+		num_of_reads = tracer->str_db.size_out[i] /
+				STRINGS_DB_READ_SIZE_BYTES;
+		leftovers = (tracer->str_db.size_out[i] %
+				STRINGS_DB_READ_SIZE_BYTES) /
+					STRINGS_DB_LEFTOVER_SIZE_BYTES;
+
+		MLX5_SET(mtrc_stdb, in, read_size, STRINGS_DB_READ_SIZE_BYTES);
+		for (j = 0; j < num_of_reads; j++) {
+			MLX5_SET(mtrc_stdb, in, start_offset, offset);
+
+			err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+						   outlen, MLX5_REG_MTRC_STDB,
+						   0, 1);
+			if (err) {
+				mlx5_core_dbg(dev, "FWTracer: Failed to read strings DB %d\n",
+					      err);
+				goto out_free;
+			}
+
+			out_value = MLX5_ADDR_OF(mtrc_stdb, out, string_db_data);
+			memcpy(tracer->str_db.buffer[i] + offset, out_value,
+			       STRINGS_DB_READ_SIZE_BYTES);
+			offset += STRINGS_DB_READ_SIZE_BYTES;
+		}
+
+		/* Strings database is aligned to 64, need to read leftovers*/
+		MLX5_SET(mtrc_stdb, in, read_size,
+			 STRINGS_DB_LEFTOVER_SIZE_BYTES);
+		for (j = 0; j < leftovers; j++) {
+			MLX5_SET(mtrc_stdb, in, start_offset, offset);
+
+			err = mlx5_core_access_reg(dev, in, sizeof(in), out,
+						   outlen, MLX5_REG_MTRC_STDB,
+						   0, 1);
+			if (err) {
+				mlx5_core_dbg(dev, "FWTracer: Failed to read strings DB %d\n",
+					      err);
+				goto out_free;
+			}
+
+			out_value = MLX5_ADDR_OF(mtrc_stdb, out, string_db_data);
+			memcpy(tracer->str_db.buffer[i] + offset, out_value,
+			       STRINGS_DB_LEFTOVER_SIZE_BYTES);
+			offset += STRINGS_DB_LEFTOVER_SIZE_BYTES;
+		}
+	}
+
+	tracer->str_db.loaded = true;
+
+out_free:
+	kfree(out);
+out:
+	return;
+}
+
 static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
 {
 	struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer,
@@ -161,6 +318,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 	tracer->dev = dev;
 
 	INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change);
+	INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db);
 
 	err = mlx5_query_mtrc_caps(tracer);
 	if (err) {
@@ -168,10 +326,22 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 		goto destroy_workqueue;
 	}
 
-	mlx5_fw_tracer_ownership_change(&tracer->ownership_change_work);
+	err = mlx5_fw_tracer_create_log_buf(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Create log buffer failed %d\n", err);
+		goto destroy_workqueue;
+	}
+
+	err = mlx5_fw_tracer_allocate_strings_db(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Allocate strings database failed %d\n", err);
+		goto free_log_buf;
+	}
 
 	return tracer;
 
+free_log_buf:
+	mlx5_fw_tracer_destroy_log_buf(tracer);
 destroy_workqueue:
 	tracer->dev = NULL;
 	destroy_workqueue(tracer->work_queue);
@@ -180,17 +350,50 @@ free_tracer:
 	return ERR_PTR(err);
 }
 
-void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
+int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 {
-	if (!tracer)
+	struct mlx5_core_dev *dev;
+	int err;
+
+	if (IS_ERR_OR_NULL(tracer))
+		return 0;
+
+	dev = tracer->dev;
+
+	if (!tracer->str_db.loaded)
+		queue_work(tracer->work_queue, &tracer->read_fw_strings_work);
+
+	err = mlx5_fw_tracer_ownership_acquire(tracer);
+	if (err) {
+		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
+		return 0; /* return 0 since ownership can be acquired on a later FW event */
+	}
+
+	return 0;
+}
+
+void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
+{
+	if (IS_ERR_OR_NULL(tracer))
 		return;
 
 	cancel_work_sync(&tracer->ownership_change_work);
 
 	if (tracer->owner)
 		mlx5_fw_tracer_ownership_release(tracer);
+}
 
+void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
+{
+	if (IS_ERR_OR_NULL(tracer))
+		return;
+
+	cancel_work_sync(&tracer->read_fw_strings_work);
+	mlx5_fw_tracer_free_strings_db(tracer);
+	mlx5_fw_tracer_destroy_log_buf(tracer);
 	flush_workqueue(tracer->work_queue);
 	destroy_workqueue(tracer->work_queue);
 	kfree(tracer);
 }
+
+EXPORT_TRACEPOINT_SYMBOL(mlx5_fw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 721c41a5e827..66cb7e7ada28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -37,6 +37,11 @@
 #include "mlx5_core.h"
 
 #define STRINGS_DB_SECTIONS_NUM 8
+#define STRINGS_DB_READ_SIZE_BYTES 256
+#define STRINGS_DB_LEFTOVER_SIZE_BYTES 64
+#define TRACER_BUFFER_PAGE_NUM 64
+#define TRACER_BUFFER_CHUNK 4096
+#define TRACE_BUFFER_SIZE_BYTE (TRACER_BUFFER_PAGE_NUM * TRACER_BUFFER_CHUNK)
 
 struct mlx5_fw_tracer {
 	struct mlx5_core_dev *dev;
@@ -44,6 +49,7 @@ struct mlx5_fw_tracer {
 	u8   trc_ver;
 	struct workqueue_struct *work_queue;
 	struct work_struct ownership_change_work;
+	struct work_struct read_fw_strings_work;
 
 	/* Strings DB */
 	struct {
@@ -52,7 +58,19 @@ struct mlx5_fw_tracer {
 		u32 num_string_db;
 		u32 base_address_out[STRINGS_DB_SECTIONS_NUM];
 		u32 size_out[STRINGS_DB_SECTIONS_NUM];
+		void *buffer[STRINGS_DB_SECTIONS_NUM];
+		bool loaded;
 	} str_db;
+
+	/* Log Buffer */
+	struct {
+		u32 pdn;
+		void *log_buf;
+		dma_addr_t dma;
+		u32 size;
+		struct mlx5_core_mkey mkey;
+
+	} buff;
 };
 
 enum mlx5_fw_tracer_ownership_state {
-- 
cgit v1.2.3


From e9cad2cea7f0b2bea253e2681a0a3f5d3940af3c Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 1 May 2018 16:04:45 -0700
Subject: net/mlx5: FW tracer, register log buffer memory key

Create a memory key and protection domain for the tracer log buffer.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 64 +++++++++++++++++++++-
 1 file changed, 61 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 35107b8f76df..d6cc27b0ff34 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -169,6 +169,48 @@ static void mlx5_fw_tracer_destroy_log_buf(struct mlx5_fw_tracer *tracer)
 	free_pages((unsigned long)tracer->buff.log_buf, get_order(tracer->buff.size));
 }
 
+static int mlx5_fw_tracer_create_mkey(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	int err, inlen, i;
+	__be64 *mtt;
+	void *mkc;
+	u32 *in;
+
+	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
+			sizeof(*mtt) * round_up(TRACER_BUFFER_PAGE_NUM, 2);
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	MLX5_SET(create_mkey_in, in, translations_octword_actual_size,
+		 DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2));
+	mtt = (u64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt);
+	for (i = 0 ; i < TRACER_BUFFER_PAGE_NUM ; i++)
+		mtt[i] = cpu_to_be64(tracer->buff.dma + i * PAGE_SIZE);
+
+	mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry);
+	MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT);
+	MLX5_SET(mkc, mkc, lr, 1);
+	MLX5_SET(mkc, mkc, lw, 1);
+	MLX5_SET(mkc, mkc, pd, tracer->buff.pdn);
+	MLX5_SET(mkc, mkc, bsf_octword_size, 0);
+	MLX5_SET(mkc, mkc, qpn, 0xffffff);
+	MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT);
+	MLX5_SET(mkc, mkc, translations_octword_size,
+		 DIV_ROUND_UP(TRACER_BUFFER_PAGE_NUM, 2));
+	MLX5_SET64(mkc, mkc, start_addr, tracer->buff.dma);
+	MLX5_SET64(mkc, mkc, len, tracer->buff.size);
+	err = mlx5_core_create_mkey(dev, &tracer->buff.mkey, in, inlen);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to create mkey, %d\n", err);
+
+	kvfree(in);
+
+	return err;
+}
+
 static void mlx5_fw_tracer_free_strings_db(struct mlx5_fw_tracer *tracer)
 {
 	u32 num_string_db = tracer->str_db.num_string_db;
@@ -363,13 +405,26 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 	if (!tracer->str_db.loaded)
 		queue_work(tracer->work_queue, &tracer->read_fw_strings_work);
 
-	err = mlx5_fw_tracer_ownership_acquire(tracer);
+	err = mlx5_core_alloc_pd(dev, &tracer->buff.pdn);
 	if (err) {
-		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
-		return 0; /* return 0 since ownership can be acquired on a later FW event */
+		mlx5_core_warn(dev, "FWTracer: Failed to allocate PD %d\n", err);
+		return err;
 	}
 
+	err = mlx5_fw_tracer_create_mkey(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to create mkey %d\n", err);
+		goto err_dealloc_pd;
+	}
+
+	err = mlx5_fw_tracer_ownership_acquire(tracer);
+	if (err) /* Don't fail since ownership can be acquired on a later FW event */
+		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
+
 	return 0;
+err_dealloc_pd:
+	mlx5_core_dealloc_pd(dev, tracer->buff.pdn);
+	return err;
 }
 
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
@@ -381,6 +436,9 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 
 	if (tracer->owner)
 		mlx5_fw_tracer_ownership_release(tracer);
+
+	mlx5_core_destroy_mkey(tracer->dev, &tracer->buff.mkey);
+	mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn);
 }
 
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
-- 
cgit v1.2.3


From c71ad41ccb0c29fce95149b74786574b354c9dda Mon Sep 17 00:00:00 2001
From: Feras Daoud <ferasda@mellanox.com>
Date: Wed, 7 Feb 2018 11:08:56 +0200
Subject: net/mlx5: FW tracer, events handling

The tracer has one event, event 0x26, with two subtypes:
- Subtype 0: Ownership change
- Subtype 1: Traces available

An ownership change occurs in the following cases:
1- Owner releases his ownership, in this case, an event will be
sent to inform others to reattempt acquire ownership.
2- Ownership was taken by a higher priority tool, in this case
the owner should understand that it lost ownership, and go through
tear down flow.

The second subtype indicates that there are traces in the trace buffer,
in this case, the driver polls the tracer buffer for new traces, parse
them and prepares the messages for printing.

The HW starts tracing from the first address in the tracer buffer.
Driver receives an event notifying that new trace block exists.
HW posts a timestamp event at the last 8B of every 256B block.
Comparing the timestamp to the last handled timestamp would indicate
that this is a new trace block. Once the new timestamp is detected,
the entire block is considered valid.

Block validation and parsing, should be done after copying the current
block to a different location, in order to avoid block overwritten
during processing.

Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 268 ++++++++++++++++++++-
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  71 +++++-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  11 +
 include/linux/mlx5/device.h                        |   7 +
 4 files changed, 347 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index d6cc27b0ff34..bd887d1d3396 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -318,25 +318,244 @@ out:
 	return;
 }
 
-static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
+static void mlx5_fw_tracer_arm(struct mlx5_core_dev *dev)
 {
-	struct mlx5_fw_tracer *tracer = container_of(work, struct mlx5_fw_tracer,
-						     ownership_change_work);
-	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
 	int err;
 
-	if (tracer->owner) {
-		mlx5_fw_tracer_ownership_release(tracer);
+	MLX5_SET(mtrc_ctrl, in, arm_event, 1);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CTRL, 0, 1);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to arm tracer event %d\n", err);
+}
+
+static void poll_trace(struct mlx5_fw_tracer *tracer,
+		       struct tracer_event *tracer_event, u64 *trace)
+{
+	u32 timestamp_low, timestamp_mid, timestamp_high, urts;
+
+	tracer_event->event_id = MLX5_GET(tracer_event, trace, event_id);
+	tracer_event->lost_event = MLX5_GET(tracer_event, trace, lost);
+
+	switch (tracer_event->event_id) {
+	case TRACER_EVENT_TYPE_TIMESTAMP:
+		tracer_event->type = TRACER_EVENT_TYPE_TIMESTAMP;
+		urts = MLX5_GET(tracer_timestamp_event, trace, urts);
+		if (tracer->trc_ver == 0)
+			tracer_event->timestamp_event.unreliable = !!(urts >> 2);
+		else
+			tracer_event->timestamp_event.unreliable = !!(urts & 1);
+
+		timestamp_low = MLX5_GET(tracer_timestamp_event,
+					 trace, timestamp7_0);
+		timestamp_mid = MLX5_GET(tracer_timestamp_event,
+					 trace, timestamp39_8);
+		timestamp_high = MLX5_GET(tracer_timestamp_event,
+					  trace, timestamp52_40);
+
+		tracer_event->timestamp_event.timestamp =
+				((u64)timestamp_high << 40) |
+				((u64)timestamp_mid << 8) |
+				(u64)timestamp_low;
+		break;
+	default:
+		if (tracer_event->event_id >= tracer->str_db.first_string_trace ||
+		    tracer_event->event_id <= tracer->str_db.first_string_trace +
+					      tracer->str_db.num_string_trace) {
+			tracer_event->type = TRACER_EVENT_TYPE_STRING;
+			tracer_event->string_event.timestamp =
+				MLX5_GET(tracer_string_event, trace, timestamp);
+			tracer_event->string_event.string_param =
+				MLX5_GET(tracer_string_event, trace, string_param);
+			tracer_event->string_event.tmsn =
+				MLX5_GET(tracer_string_event, trace, tmsn);
+			tracer_event->string_event.tdsn =
+				MLX5_GET(tracer_string_event, trace, tdsn);
+		} else {
+			tracer_event->type = TRACER_EVENT_TYPE_UNRECOGNIZED;
+		}
+		break;
+	}
+}
+
+static u64 get_block_timestamp(struct mlx5_fw_tracer *tracer, u64 *ts_event)
+{
+	struct tracer_event tracer_event;
+	u8 event_id;
+
+	event_id = MLX5_GET(tracer_event, ts_event, event_id);
+
+	if (event_id == TRACER_EVENT_TYPE_TIMESTAMP)
+		poll_trace(tracer, &tracer_event, ts_event);
+	else
+		tracer_event.timestamp_event.timestamp = 0;
+
+	return tracer_event.timestamp_event.timestamp;
+}
+
+static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer =
+			container_of(work, struct mlx5_fw_tracer, handle_traces_work);
+	u64 block_timestamp, last_block_timestamp, tmp_trace_block[TRACES_PER_BLOCK];
+	u32 block_count, start_offset, prev_start_offset, prev_consumer_index;
+	u32 trace_event_size = MLX5_ST_SZ_BYTES(tracer_event);
+	struct tracer_event tracer_event;
+	struct mlx5_core_dev *dev;
+	int i;
+
+	if (!tracer->owner)
 		return;
+
+	dev = tracer->dev;
+	block_count = tracer->buff.size / TRACER_BLOCK_SIZE_BYTE;
+	start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
+
+	/* Copy the block to local buffer to avoid HW override while being processed*/
+	memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset,
+	       TRACER_BLOCK_SIZE_BYTE);
+
+	block_timestamp =
+		get_block_timestamp(tracer, &tmp_trace_block[TRACES_PER_BLOCK - 1]);
+
+	while (block_timestamp > tracer->last_timestamp) {
+		/* Check block override if its not the first block */
+		if (!tracer->last_timestamp) {
+			u64 *ts_event;
+			/* To avoid block override be the HW in case of buffer
+			 * wraparound, the time stamp of the previous block
+			 * should be compared to the last timestamp handled
+			 * by the driver.
+			 */
+			prev_consumer_index =
+				(tracer->buff.consumer_index - 1) & (block_count - 1);
+			prev_start_offset = prev_consumer_index * TRACER_BLOCK_SIZE_BYTE;
+
+			ts_event = tracer->buff.log_buf + prev_start_offset +
+				   (TRACES_PER_BLOCK - 1) * trace_event_size;
+			last_block_timestamp = get_block_timestamp(tracer, ts_event);
+			/* If previous timestamp different from last stored
+			 * timestamp then there is a good chance that the
+			 * current buffer is overwritten and therefore should
+			 * not be parsed.
+			 */
+			if (tracer->last_timestamp != last_block_timestamp) {
+				mlx5_core_warn(dev, "FWTracer: Events were lost\n");
+				tracer->last_timestamp = block_timestamp;
+				tracer->buff.consumer_index =
+					(tracer->buff.consumer_index + 1) & (block_count - 1);
+				break;
+			}
+		}
+
+		/* Parse events */
+		for (i = 0; i < TRACES_PER_BLOCK ; i++)
+			poll_trace(tracer, &tracer_event, &tmp_trace_block[i]);
+
+		tracer->buff.consumer_index =
+			(tracer->buff.consumer_index + 1) & (block_count - 1);
+
+		tracer->last_timestamp = block_timestamp;
+		start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
+		memcpy(tmp_trace_block, tracer->buff.log_buf + start_offset,
+		       TRACER_BLOCK_SIZE_BYTE);
+		block_timestamp = get_block_timestamp(tracer,
+						      &tmp_trace_block[TRACES_PER_BLOCK - 1]);
 	}
 
+	mlx5_fw_tracer_arm(dev);
+}
+
+static int mlx5_fw_tracer_set_mtrc_conf(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_conf)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_conf)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_conf, in, trace_mode, TRACE_TO_MEMORY);
+	MLX5_SET(mtrc_conf, in, log_trace_buffer_size,
+		 ilog2(TRACER_BUFFER_PAGE_NUM));
+	MLX5_SET(mtrc_conf, in, trace_mkey, tracer->buff.mkey.key);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CONF, 0, 1);
+	if (err)
+		mlx5_core_warn(dev, "FWTracer: Failed to set tracer configurations %d\n", err);
+
+	return err;
+}
+
+static int mlx5_fw_tracer_set_mtrc_ctrl(struct mlx5_fw_tracer *tracer, u8 status, u8 arm)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	u32 out[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	u32 in[MLX5_ST_SZ_DW(mtrc_ctrl)] = {0};
+	int err;
+
+	MLX5_SET(mtrc_ctrl, in, modify_field_select, TRACE_STATUS);
+	MLX5_SET(mtrc_ctrl, in, trace_status, status);
+	MLX5_SET(mtrc_ctrl, in, arm_event, arm);
+
+	err = mlx5_core_access_reg(dev, in, sizeof(in), out, sizeof(out),
+				   MLX5_REG_MTRC_CTRL, 0, 1);
+
+	if (!err && status)
+		tracer->last_timestamp = 0;
+
+	return err;
+}
+
+static int mlx5_fw_tracer_start(struct mlx5_fw_tracer *tracer)
+{
+	struct mlx5_core_dev *dev = tracer->dev;
+	int err;
+
 	err = mlx5_fw_tracer_ownership_acquire(tracer);
 	if (err) {
 		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
+		/* Don't fail since ownership can be acquired on a later FW event */
+		return 0;
+	}
+
+	err = mlx5_fw_tracer_set_mtrc_conf(tracer);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to set tracer configuration %d\n", err);
+		goto release_ownership;
+	}
+
+	/* enable tracer & trace events */
+	err = mlx5_fw_tracer_set_mtrc_ctrl(tracer, 1, 1);
+	if (err) {
+		mlx5_core_warn(dev, "FWTracer: Failed to enable tracer %d\n", err);
+		goto release_ownership;
+	}
+
+	return 0;
+
+release_ownership:
+	mlx5_fw_tracer_ownership_release(tracer);
+	return err;
+}
+
+static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
+{
+	struct mlx5_fw_tracer *tracer =
+		container_of(work, struct mlx5_fw_tracer, ownership_change_work);
+
+	if (tracer->owner) {
+		tracer->owner = false;
+		tracer->buff.consumer_index = 0;
 		return;
 	}
+
+	mlx5_fw_tracer_start(tracer);
 }
 
+/* Create software resources (Buffers, etc ..) */
 struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 {
 	struct mlx5_fw_tracer *tracer = NULL;
@@ -361,6 +580,8 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 
 	INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change);
 	INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db);
+	INIT_WORK(&tracer->handle_traces_work, mlx5_fw_tracer_handle_traces);
+
 
 	err = mlx5_query_mtrc_caps(tracer);
 	if (err) {
@@ -392,6 +613,9 @@ free_tracer:
 	return ERR_PTR(err);
 }
 
+/* Create HW resources + start tracer
+ * must be called before Async EQ is created
+ */
 int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 {
 	struct mlx5_core_dev *dev;
@@ -417,22 +641,25 @@ int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer)
 		goto err_dealloc_pd;
 	}
 
-	err = mlx5_fw_tracer_ownership_acquire(tracer);
-	if (err) /* Don't fail since ownership can be acquired on a later FW event */
-		mlx5_core_dbg(dev, "FWTracer: Ownership was not granted %d\n", err);
+	mlx5_fw_tracer_start(tracer);
 
 	return 0;
+
 err_dealloc_pd:
 	mlx5_core_dealloc_pd(dev, tracer->buff.pdn);
 	return err;
 }
 
+/* Stop tracer + Cleanup HW resources
+ * must be called after Async EQ is destroyed
+ */
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 {
 	if (IS_ERR_OR_NULL(tracer))
 		return;
 
 	cancel_work_sync(&tracer->ownership_change_work);
+	cancel_work_sync(&tracer->handle_traces_work);
 
 	if (tracer->owner)
 		mlx5_fw_tracer_ownership_release(tracer);
@@ -441,6 +668,7 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 	mlx5_core_dealloc_pd(tracer->dev, tracer->buff.pdn);
 }
 
+/* Free software resources (Buffers, etc ..) */
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 {
 	if (IS_ERR_OR_NULL(tracer))
@@ -454,4 +682,26 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	kfree(tracer);
 }
 
+void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe)
+{
+	struct mlx5_fw_tracer *tracer = dev->tracer;
+
+	if (!tracer)
+		return;
+
+	switch (eqe->sub_type) {
+	case MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE:
+		if (test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state))
+			queue_work(tracer->work_queue, &tracer->ownership_change_work);
+		break;
+	case MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE:
+		if (likely(tracer->str_db.loaded))
+			queue_work(tracer->work_queue, &tracer->handle_traces_work);
+		break;
+	default:
+		mlx5_core_dbg(dev, "FWTracer: Event with unrecognized subtype: sub_type %d\n",
+			      eqe->sub_type);
+	}
+}
+
 EXPORT_TRACEPOINT_SYMBOL(mlx5_fw);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 66cb7e7ada28..3915e91486b2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -43,6 +43,9 @@
 #define TRACER_BUFFER_CHUNK 4096
 #define TRACE_BUFFER_SIZE_BYTE (TRACER_BUFFER_PAGE_NUM * TRACER_BUFFER_CHUNK)
 
+#define TRACER_BLOCK_SIZE_BYTE 256
+#define TRACES_PER_BLOCK 32
+
 struct mlx5_fw_tracer {
 	struct mlx5_core_dev *dev;
 	bool owner;
@@ -69,8 +72,11 @@ struct mlx5_fw_tracer {
 		dma_addr_t dma;
 		u32 size;
 		struct mlx5_core_mkey mkey;
-
+		u32 consumer_index;
 	} buff;
+
+	u64 last_timestamp;
+	struct work_struct handle_traces_work;
 };
 
 enum mlx5_fw_tracer_ownership_state {
@@ -78,7 +84,70 @@ enum mlx5_fw_tracer_ownership_state {
 	MLX5_FW_TRACER_ACQUIRE_OWNERSHIP,
 };
 
+enum tracer_ctrl_fields_select {
+	TRACE_STATUS = 1 << 0,
+};
+
+enum tracer_event_type {
+	TRACER_EVENT_TYPE_STRING,
+	TRACER_EVENT_TYPE_TIMESTAMP = 0xFF,
+	TRACER_EVENT_TYPE_UNRECOGNIZED,
+};
+
+enum tracing_mode {
+	TRACE_TO_MEMORY = 1 << 0,
+};
+
+struct tracer_timestamp_event {
+	u64        timestamp;
+	u8         unreliable;
+};
+
+struct tracer_string_event {
+	u32        timestamp;
+	u32        tmsn;
+	u32        tdsn;
+	u32        string_param;
+};
+
+struct tracer_event {
+	bool      lost_event;
+	u32       type;
+	u8        event_id;
+	union {
+		struct tracer_string_event string_event;
+		struct tracer_timestamp_event timestamp_event;
+	};
+};
+
+struct mlx5_ifc_tracer_event_bits {
+	u8         lost[0x1];
+	u8         timestamp[0x7];
+	u8         event_id[0x8];
+	u8         event_data[0x30];
+};
+
+struct mlx5_ifc_tracer_string_event_bits {
+	u8         lost[0x1];
+	u8         timestamp[0x7];
+	u8         event_id[0x8];
+	u8         tmsn[0xd];
+	u8         tdsn[0x3];
+	u8         string_param[0x20];
+};
+
+struct mlx5_ifc_tracer_timestamp_event_bits {
+	u8         timestamp7_0[0x8];
+	u8         event_id[0x8];
+	u8         urts[0x3];
+	u8         timestamp52_40[0xd];
+	u8         timestamp39_8[0x20];
+};
+
 struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
+int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
+void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) { return; }
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 406c23862f5f..7669b4380779 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -40,6 +40,7 @@
 #include "mlx5_core.h"
 #include "fpga/core.h"
 #include "eswitch.h"
+#include "diag/fw_tracer.h"
 
 enum {
 	MLX5_EQE_SIZE		= sizeof(struct mlx5_eqe),
@@ -168,6 +169,8 @@ static const char *eqe_type_str(u8 type)
 		return "MLX5_EVENT_TYPE_FPGA_QP_ERROR";
 	case MLX5_EVENT_TYPE_GENERAL_EVENT:
 		return "MLX5_EVENT_TYPE_GENERAL_EVENT";
+	case MLX5_EVENT_TYPE_DEVICE_TRACER:
+		return "MLX5_EVENT_TYPE_DEVICE_TRACER";
 	default:
 		return "Unrecognized event";
 	}
@@ -576,6 +579,11 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 		case MLX5_EVENT_TYPE_GENERAL_EVENT:
 			general_event_handler(dev, eqe);
 			break;
+
+		case MLX5_EVENT_TYPE_DEVICE_TRACER:
+			mlx5_fw_tracer_event(dev, eqe);
+			break;
+
 		default:
 			mlx5_core_warn(dev, "Unhandled event 0x%x on EQ 0x%x\n",
 				       eqe->type, eq->eqn);
@@ -853,6 +861,9 @@ int mlx5_start_eqs(struct mlx5_core_dev *dev)
 	if (MLX5_CAP_GEN(dev, temp_warn_event))
 		async_event_mask |= (1ull << MLX5_EVENT_TYPE_TEMP_WARN_EVENT);
 
+	if (MLX5_CAP_MCAM_REG(dev, tracer_registers))
+		async_event_mask |= (1ull << MLX5_EVENT_TYPE_DEVICE_TRACER);
+
 	err = mlx5_create_map_eq(dev, &table->cmd_eq, MLX5_EQ_VEC_CMD,
 				 MLX5_NUM_CMD_EQE, 1ull << MLX5_EVENT_TYPE_CMD,
 				 "mlx5_cmd_eq", MLX5_EQ_TYPE_ASYNC);
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0566c6a94805..d489494b0a84 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -332,6 +332,13 @@ enum mlx5_event {
 
 	MLX5_EVENT_TYPE_FPGA_ERROR         = 0x20,
 	MLX5_EVENT_TYPE_FPGA_QP_ERROR      = 0x21,
+
+	MLX5_EVENT_TYPE_DEVICE_TRACER      = 0x26,
+};
+
+enum {
+	MLX5_TRACER_SUBTYPE_OWNERSHIP_CHANGE = 0x0,
+	MLX5_TRACER_SUBTYPE_TRACES_AVAILABLE = 0x1,
 };
 
 enum {
-- 
cgit v1.2.3


From 70dd6fdb8987b14f7b6105f6be0617299e459398 Mon Sep 17 00:00:00 2001
From: Feras Daoud <ferasda@mellanox.com>
Date: Sun, 18 Feb 2018 10:06:35 +0200
Subject: net/mlx5: FW tracer, parse traces and kernel tracing support

For each message the driver should do the following:
1- Find the message string in the strings database
2- Count the param number of each message
3- Wait for the param events and accumulate them
4- Calculate the event timestamp using the local event timestamp
and the first timestamp event following it.
5- Print message to trace log

Enable the tracing by:
echo 1 > /sys/kernel/debug/tracing/events/mlx5/mlx5_fw/enable

Read traces by:
cat /sys/kernel/debug/tracing/trace

Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.c   | 235 ++++++++++++++++++++-
 .../ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  22 ++
 .../mellanox/mlx5/core/diag/fw_tracer_tracepoint.h |  78 +++++++
 3 files changed, 333 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index bd887d1d3396..309842de272c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -29,8 +29,9 @@
  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  * SOFTWARE.
  */
-
+#define CREATE_TRACE_POINTS
 #include "fw_tracer.h"
+#include "fw_tracer_tracepoint.h"
 
 static int mlx5_query_mtrc_caps(struct mlx5_fw_tracer *tracer)
 {
@@ -332,6 +333,109 @@ static void mlx5_fw_tracer_arm(struct mlx5_core_dev *dev)
 		mlx5_core_warn(dev, "FWTracer: Failed to arm tracer event %d\n", err);
 }
 
+static const char *VAL_PARM		= "%llx";
+static const char *REPLACE_64_VAL_PARM	= "%x%x";
+static const char *PARAM_CHAR		= "%";
+
+static int mlx5_tracer_message_hash(u32 message_id)
+{
+	return jhash_1word(message_id, 0) & (MESSAGE_HASH_SIZE - 1);
+}
+
+static struct tracer_string_format *mlx5_tracer_message_insert(struct mlx5_fw_tracer *tracer,
+							       struct tracer_event *tracer_event)
+{
+	struct hlist_head *head =
+		&tracer->hash[mlx5_tracer_message_hash(tracer_event->string_event.tmsn)];
+	struct tracer_string_format *cur_string;
+
+	cur_string = kzalloc(sizeof(*cur_string), GFP_KERNEL);
+	if (!cur_string)
+		return NULL;
+
+	hlist_add_head(&cur_string->hlist, head);
+
+	return cur_string;
+}
+
+static struct tracer_string_format *mlx5_tracer_get_string(struct mlx5_fw_tracer *tracer,
+							   struct tracer_event *tracer_event)
+{
+	struct tracer_string_format *cur_string;
+	u32 str_ptr, offset;
+	int i;
+
+	str_ptr = tracer_event->string_event.string_param;
+
+	for (i = 0; i < tracer->str_db.num_string_db; i++) {
+		if (str_ptr > tracer->str_db.base_address_out[i] &&
+		    str_ptr < tracer->str_db.base_address_out[i] +
+		    tracer->str_db.size_out[i]) {
+			offset = str_ptr - tracer->str_db.base_address_out[i];
+			/* add it to the hash */
+			cur_string = mlx5_tracer_message_insert(tracer, tracer_event);
+			if (!cur_string)
+				return NULL;
+			cur_string->string = (char *)(tracer->str_db.buffer[i] +
+							offset);
+			return cur_string;
+		}
+	}
+
+	return NULL;
+}
+
+static void mlx5_tracer_clean_message(struct tracer_string_format *str_frmt)
+{
+	hlist_del(&str_frmt->hlist);
+	kfree(str_frmt);
+}
+
+static int mlx5_tracer_get_num_of_params(char *str)
+{
+	char *substr, *pstr = str;
+	int num_of_params = 0;
+
+	/* replace %llx with %x%x */
+	substr = strstr(pstr, VAL_PARM);
+	while (substr) {
+		memcpy(substr, REPLACE_64_VAL_PARM, 4);
+		pstr = substr;
+		substr = strstr(pstr, VAL_PARM);
+	}
+
+	/* count all the % characters */
+	substr = strstr(str, PARAM_CHAR);
+	while (substr) {
+		num_of_params += 1;
+		str = substr + 1;
+		substr = strstr(str, PARAM_CHAR);
+	}
+
+	return num_of_params;
+}
+
+static struct tracer_string_format *mlx5_tracer_message_find(struct hlist_head *head,
+							     u8 event_id, u32 tmsn)
+{
+	struct tracer_string_format *message;
+
+	hlist_for_each_entry(message, head, hlist)
+		if (message->event_id == event_id && message->tmsn == tmsn)
+			return message;
+
+	return NULL;
+}
+
+static struct tracer_string_format *mlx5_tracer_message_get(struct mlx5_fw_tracer *tracer,
+							    struct tracer_event *tracer_event)
+{
+	struct hlist_head *head =
+		&tracer->hash[mlx5_tracer_message_hash(tracer_event->string_event.tmsn)];
+
+	return mlx5_tracer_message_find(head, tracer_event->event_id, tracer_event->string_event.tmsn);
+}
+
 static void poll_trace(struct mlx5_fw_tracer *tracer,
 		       struct tracer_event *tracer_event, u64 *trace)
 {
@@ -396,6 +500,128 @@ static u64 get_block_timestamp(struct mlx5_fw_tracer *tracer, u64 *ts_event)
 	return tracer_event.timestamp_event.timestamp;
 }
 
+static void mlx5_fw_tracer_clean_print_hash(struct mlx5_fw_tracer *tracer)
+{
+	struct tracer_string_format *str_frmt;
+	struct hlist_node *n;
+	int i;
+
+	for (i = 0; i < MESSAGE_HASH_SIZE; i++) {
+		hlist_for_each_entry_safe(str_frmt, n, &tracer->hash[i], hlist)
+			mlx5_tracer_clean_message(str_frmt);
+	}
+}
+
+static void mlx5_fw_tracer_clean_ready_list(struct mlx5_fw_tracer *tracer)
+{
+	struct tracer_string_format *str_frmt, *tmp_str;
+
+	list_for_each_entry_safe(str_frmt, tmp_str, &tracer->ready_strings_list,
+				 list)
+		list_del(&str_frmt->list);
+}
+
+static void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt,
+				    struct mlx5_core_dev *dev,
+				    u64 trace_timestamp)
+{
+	char	tmp[512];
+
+	snprintf(tmp, sizeof(tmp), str_frmt->string,
+		 str_frmt->params[0],
+		 str_frmt->params[1],
+		 str_frmt->params[2],
+		 str_frmt->params[3],
+		 str_frmt->params[4],
+		 str_frmt->params[5],
+		 str_frmt->params[6]);
+
+	trace_mlx5_fw(dev->tracer, trace_timestamp, str_frmt->lost,
+		      str_frmt->event_id, tmp);
+
+	/* remove it from hash */
+	mlx5_tracer_clean_message(str_frmt);
+}
+
+static int mlx5_tracer_handle_string_trace(struct mlx5_fw_tracer *tracer,
+					   struct tracer_event *tracer_event)
+{
+	struct tracer_string_format *cur_string;
+
+	if (tracer_event->string_event.tdsn == 0) {
+		cur_string = mlx5_tracer_get_string(tracer, tracer_event);
+		if (!cur_string)
+			return -1;
+
+		cur_string->num_of_params = mlx5_tracer_get_num_of_params(cur_string->string);
+		cur_string->last_param_num = 0;
+		cur_string->event_id = tracer_event->event_id;
+		cur_string->tmsn = tracer_event->string_event.tmsn;
+		cur_string->timestamp = tracer_event->string_event.timestamp;
+		cur_string->lost = tracer_event->lost_event;
+		if (cur_string->num_of_params == 0) /* trace with no params */
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+	} else {
+		cur_string = mlx5_tracer_message_get(tracer, tracer_event);
+		if (!cur_string) {
+			pr_debug("%s Got string event for unknown string tdsm: %d\n",
+				 __func__, tracer_event->string_event.tmsn);
+			return -1;
+		}
+		cur_string->last_param_num += 1;
+		if (cur_string->last_param_num > TRACER_MAX_PARAMS) {
+			pr_debug("%s Number of params exceeds the max (%d)\n",
+				 __func__, TRACER_MAX_PARAMS);
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+			return 0;
+		}
+		/* keep the new parameter */
+		cur_string->params[cur_string->last_param_num - 1] =
+			tracer_event->string_event.string_param;
+		if (cur_string->last_param_num == cur_string->num_of_params)
+			list_add_tail(&cur_string->list, &tracer->ready_strings_list);
+	}
+
+	return 0;
+}
+
+static void mlx5_tracer_handle_timestamp_trace(struct mlx5_fw_tracer *tracer,
+					       struct tracer_event *tracer_event)
+{
+	struct tracer_timestamp_event timestamp_event =
+						tracer_event->timestamp_event;
+	struct tracer_string_format *str_frmt, *tmp_str;
+	struct mlx5_core_dev *dev = tracer->dev;
+	u64 trace_timestamp;
+
+	list_for_each_entry_safe(str_frmt, tmp_str, &tracer->ready_strings_list, list) {
+		list_del(&str_frmt->list);
+		if (str_frmt->timestamp < (timestamp_event.timestamp & MASK_6_0))
+			trace_timestamp = (timestamp_event.timestamp & MASK_52_7) |
+					  (str_frmt->timestamp & MASK_6_0);
+		else
+			trace_timestamp = ((timestamp_event.timestamp & MASK_52_7) - 1) |
+					  (str_frmt->timestamp & MASK_6_0);
+
+		mlx5_tracer_print_trace(str_frmt, dev, trace_timestamp);
+	}
+}
+
+static int mlx5_tracer_handle_trace(struct mlx5_fw_tracer *tracer,
+				    struct tracer_event *tracer_event)
+{
+	if (tracer_event->type == TRACER_EVENT_TYPE_STRING) {
+		mlx5_tracer_handle_string_trace(tracer, tracer_event);
+	} else if (tracer_event->type == TRACER_EVENT_TYPE_TIMESTAMP) {
+		if (!tracer_event->timestamp_event.unreliable)
+			mlx5_tracer_handle_timestamp_trace(tracer, tracer_event);
+	} else {
+		pr_debug("%s Got unrecognised type %d for parsing, exiting..\n",
+			 __func__, tracer_event->type);
+	}
+	return 0;
+}
+
 static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 {
 	struct mlx5_fw_tracer *tracer =
@@ -452,8 +678,10 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 		}
 
 		/* Parse events */
-		for (i = 0; i < TRACES_PER_BLOCK ; i++)
+		for (i = 0; i < TRACES_PER_BLOCK ; i++) {
 			poll_trace(tracer, &tracer_event, &tmp_trace_block[i]);
+			mlx5_tracer_handle_trace(tracer, &tracer_event);
+		}
 
 		tracer->buff.consumer_index =
 			(tracer->buff.consumer_index + 1) & (block_count - 1);
@@ -578,6 +806,7 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 
 	tracer->dev = dev;
 
+	INIT_LIST_HEAD(&tracer->ready_strings_list);
 	INIT_WORK(&tracer->ownership_change_work, mlx5_fw_tracer_ownership_change);
 	INIT_WORK(&tracer->read_fw_strings_work, mlx5_tracer_read_strings_db);
 	INIT_WORK(&tracer->handle_traces_work, mlx5_fw_tracer_handle_traces);
@@ -675,6 +904,8 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 		return;
 
 	cancel_work_sync(&tracer->read_fw_strings_work);
+	mlx5_fw_tracer_clean_ready_list(tracer);
+	mlx5_fw_tracer_clean_print_hash(tracer);
 	mlx5_fw_tracer_free_strings_db(tracer);
 	mlx5_fw_tracer_destroy_log_buf(tracer);
 	flush_workqueue(tracer->work_queue);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 3915e91486b2..8d310e7d6743 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -46,6 +46,13 @@
 #define TRACER_BLOCK_SIZE_BYTE 256
 #define TRACES_PER_BLOCK 32
 
+#define TRACER_MAX_PARAMS 7
+#define MESSAGE_HASH_BITS 6
+#define MESSAGE_HASH_SIZE BIT(MESSAGE_HASH_BITS)
+
+#define MASK_52_7 (0x1FFFFFFFFFFF80)
+#define MASK_6_0  (0x7F)
+
 struct mlx5_fw_tracer {
 	struct mlx5_core_dev *dev;
 	bool owner;
@@ -77,6 +84,21 @@ struct mlx5_fw_tracer {
 
 	u64 last_timestamp;
 	struct work_struct handle_traces_work;
+	struct hlist_head hash[MESSAGE_HASH_SIZE];
+	struct list_head ready_strings_list;
+};
+
+struct tracer_string_format {
+	char *string;
+	int params[TRACER_MAX_PARAMS];
+	int num_of_params;
+	int last_param_num;
+	u8 event_id;
+	u32 tmsn;
+	struct hlist_node hlist;
+	struct list_head list;
+	u32 timestamp;
+	bool lost;
 };
 
 enum mlx5_fw_tracer_ownership_state {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
new file mode 100644
index 000000000000..83f90e9aff45
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer_tracepoint.h
@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#if !defined(__LIB_TRACER_TRACEPOINT_H__) || defined(TRACE_HEADER_MULTI_READ)
+#define __LIB_TRACER_TRACEPOINT_H__
+
+#include <linux/tracepoint.h>
+#include "fw_tracer.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mlx5
+
+/* Tracepoint for FWTracer messages: */
+TRACE_EVENT(mlx5_fw,
+	TP_PROTO(const struct mlx5_fw_tracer *tracer, u64 trace_timestamp,
+		 bool lost, u8 event_id, const char *msg),
+
+	TP_ARGS(tracer, trace_timestamp, lost, event_id, msg),
+
+	TP_STRUCT__entry(
+		__string(dev_name, dev_name(&tracer->dev->pdev->dev))
+		__field(u64, trace_timestamp)
+		__field(bool, lost)
+		__field(u8, event_id)
+		__string(msg, msg)
+	),
+
+	TP_fast_assign(
+		__assign_str(dev_name, dev_name(&tracer->dev->pdev->dev));
+		__entry->trace_timestamp = trace_timestamp;
+		__entry->lost = lost;
+		__entry->event_id = event_id;
+		__assign_str(msg, msg);
+	),
+
+	TP_printk("%s [0x%llx] %d [0x%x] %s",
+		  __get_str(dev_name),
+		  __entry->trace_timestamp,
+		  __entry->lost, __entry->event_id,
+		  __get_str(msg))
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_PATH ./diag
+#define TRACE_INCLUDE_FILE fw_tracer_tracepoint
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From 244069532fa25183c37305e002d6e26396dadeb0 Mon Sep 17 00:00:00 2001
From: Feras Daoud <ferasda@mellanox.com>
Date: Thu, 22 Feb 2018 10:01:35 +0200
Subject: net/mlx5: FW tracer, Enable tracing

Add the tracer file to the makefile and add the init
function to the load one flow.

Signed-off-by: Feras Daoud <ferasda@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile       |  2 +-
 .../net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h   |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/main.c         | 18 ++++++++++++++++--
 3 files changed, 18 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d923f2f58608..55d5a5c2e9d8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -6,7 +6,7 @@ mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
 		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \
-		diag/fs_tracepoint.o
+		diag/fs_tracepoint.o diag/fw_tracer.o
 
 mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
index 8d310e7d6743..0347f2dd5cee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.h
@@ -170,6 +170,6 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev);
 int mlx5_fw_tracer_init(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer);
 void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer);
-void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) { return; }
+void mlx5_fw_tracer_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index f9b950e1bd85..6ddbb70e95de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -62,6 +62,7 @@
 #include "accel/ipsec.h"
 #include "accel/tls.h"
 #include "lib/clock.h"
+#include "diag/fw_tracer.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
 MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver");
@@ -990,6 +991,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 		goto err_sriov_cleanup;
 	}
 
+	dev->tracer = mlx5_fw_tracer_create(dev);
+
 	return 0;
 
 err_sriov_cleanup:
@@ -1015,6 +1018,7 @@ out:
 
 static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 {
+	mlx5_fw_tracer_destroy(dev->tracer);
 	mlx5_fpga_cleanup(dev);
 	mlx5_sriov_cleanup(dev);
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
@@ -1167,10 +1171,16 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_put_uars;
 	}
 
+	err = mlx5_fw_tracer_init(dev->tracer);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to init FW tracer\n");
+		goto err_fw_tracer;
+	}
+
 	err = alloc_comp_eqs(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to alloc completion EQs\n");
-		goto err_stop_eqs;
+		goto err_comp_eqs;
 	}
 
 	err = mlx5_irq_set_affinity_hints(dev);
@@ -1252,7 +1262,10 @@ err_fpga_start:
 err_affinity_hints:
 	free_comp_eqs(dev);
 
-err_stop_eqs:
+err_comp_eqs:
+	mlx5_fw_tracer_cleanup(dev->tracer);
+
+err_fw_tracer:
 	mlx5_stop_eqs(dev);
 
 err_put_uars:
@@ -1320,6 +1333,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_fpga_device_stop(dev);
 	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
+	mlx5_fw_tracer_cleanup(dev->tracer);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
 	mlx5_free_irq_vectors(dev);
-- 
cgit v1.2.3


From 3101d1fc6b8678f45f703293441715a9b5b86cad Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 3 May 2018 16:44:46 -0700
Subject: net/mlx5: FW tracer, Add debug prints

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
index 309842de272c..d4ec93bde4de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c
@@ -629,14 +629,14 @@ static void mlx5_fw_tracer_handle_traces(struct work_struct *work)
 	u64 block_timestamp, last_block_timestamp, tmp_trace_block[TRACES_PER_BLOCK];
 	u32 block_count, start_offset, prev_start_offset, prev_consumer_index;
 	u32 trace_event_size = MLX5_ST_SZ_BYTES(tracer_event);
+	struct mlx5_core_dev *dev = tracer->dev;
 	struct tracer_event tracer_event;
-	struct mlx5_core_dev *dev;
 	int i;
 
+	mlx5_core_dbg(dev, "FWTracer: Handle Trace event, owner=(%d)\n", tracer->owner);
 	if (!tracer->owner)
 		return;
 
-	dev = tracer->dev;
 	block_count = tracer->buff.size / TRACER_BLOCK_SIZE_BYTE;
 	start_offset = tracer->buff.consumer_index * TRACER_BLOCK_SIZE_BYTE;
 
@@ -762,6 +762,7 @@ static int mlx5_fw_tracer_start(struct mlx5_fw_tracer *tracer)
 		goto release_ownership;
 	}
 
+	mlx5_core_dbg(dev, "FWTracer: Ownership granted and active\n");
 	return 0;
 
 release_ownership:
@@ -774,6 +775,7 @@ static void mlx5_fw_tracer_ownership_change(struct work_struct *work)
 	struct mlx5_fw_tracer *tracer =
 		container_of(work, struct mlx5_fw_tracer, ownership_change_work);
 
+	mlx5_core_dbg(tracer->dev, "FWTracer: ownership changed, current=(%d)\n", tracer->owner);
 	if (tracer->owner) {
 		tracer->owner = false;
 		tracer->buff.consumer_index = 0;
@@ -830,6 +832,8 @@ struct mlx5_fw_tracer *mlx5_fw_tracer_create(struct mlx5_core_dev *dev)
 		goto free_log_buf;
 	}
 
+	mlx5_core_dbg(dev, "FWTracer: Tracer created\n");
+
 	return tracer;
 
 free_log_buf:
@@ -887,6 +891,9 @@ void mlx5_fw_tracer_cleanup(struct mlx5_fw_tracer *tracer)
 	if (IS_ERR_OR_NULL(tracer))
 		return;
 
+	mlx5_core_dbg(tracer->dev, "FWTracer: Cleanup, is owner ? (%d)\n",
+		      tracer->owner);
+
 	cancel_work_sync(&tracer->ownership_change_work);
 	cancel_work_sync(&tracer->handle_traces_work);
 
@@ -903,6 +910,8 @@ void mlx5_fw_tracer_destroy(struct mlx5_fw_tracer *tracer)
 	if (IS_ERR_OR_NULL(tracer))
 		return;
 
+	mlx5_core_dbg(tracer->dev, "FWTracer: Destroy\n");
+
 	cancel_work_sync(&tracer->read_fw_strings_work);
 	mlx5_fw_tracer_clean_ready_list(tracer);
 	mlx5_fw_tracer_clean_print_hash(tracer);
-- 
cgit v1.2.3


From c7f7ba8df872018054967d052f3368e13de72b73 Mon Sep 17 00:00:00 2001
From: Roi Dayan <roid@mellanox.com>
Date: Mon, 4 Dec 2017 16:46:30 +0200
Subject: net/mlx5e: Remove redundant WARN when we cannot find neigh entry

It is possible for neigh entry not to exist if it was cleaned already.
When we bring down an interface the neigh gets deleted but it could be
that our listener for neigh event to clear the encap valid bit didn't
start yet and the neigh update last used work is started first.
In this scenario the encap entry has valid bit set but the neigh entry
doesn't exist.

Signed-off-by: Roi Dayan <roid@mellanox.com>
Reviewed-by: Paul Blakey <paulb@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 0edf4751a8ba..335a08bc381d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1032,10 +1032,8 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe)
 		 * dst ip pair
 		 */
 		n = neigh_lookup(tbl, &m_neigh->dst_ip, m_neigh->dev);
-		if (!n) {
-			WARN(1, "The neighbour already freed\n");
+		if (!n)
 			return;
-		}
 
 		neigh_event_send(n, NULL);
 		neigh_release(n);
-- 
cgit v1.2.3


From 699e96ddf47fe67e28522e511f6e1bce8a20b4e1 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Tue, 1 May 2018 08:48:03 +0000
Subject: net/mlx5e: Support offloading tc double vlan headers match

We can match on both outer and inner vlan tags, add support for
offloading that.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 55 +++++++++++++++++++++++--
 1 file changed, 52 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 335a08bc381d..dcb8c4993811 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1235,6 +1235,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 				       outer_headers);
 	void *headers_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				       outer_headers);
+	void *misc_c = MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    misc_parameters);
+	void *misc_v = MLX5_ADDR_OF(fte_match_param, spec->match_value,
+				    misc_parameters);
 	u16 addr_type = 0;
 	u8 ip_proto = 0;
 
@@ -1245,6 +1249,7 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
 	      BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_VLAN) |
+	      BIT(FLOW_DISSECTOR_KEY_CVLAN) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
 	      BIT(FLOW_DISSECTOR_KEY_PORTS) |
@@ -1325,9 +1330,18 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_VLAN,
 						  f->mask);
-		if (mask->vlan_id || mask->vlan_priority) {
-			MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1);
-			MLX5_SET(fte_match_set_lyr_2_4, headers_v, cvlan_tag, 1);
+		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
+			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+					 svlan_tag, 1);
+				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+					 svlan_tag, 1);
+			} else {
+				MLX5_SET(fte_match_set_lyr_2_4, headers_c,
+					 cvlan_tag, 1);
+				MLX5_SET(fte_match_set_lyr_2_4, headers_v,
+					 cvlan_tag, 1);
+			}
 
 			MLX5_SET(fte_match_set_lyr_2_4, headers_c, first_vid, mask->vlan_id);
 			MLX5_SET(fte_match_set_lyr_2_4, headers_v, first_vid, key->vlan_id);
@@ -1339,6 +1353,41 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 		}
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_CVLAN)) {
+		struct flow_dissector_key_vlan *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_CVLAN,
+						  f->key);
+		struct flow_dissector_key_vlan *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_CVLAN,
+						  f->mask);
+		if (mask->vlan_id || mask->vlan_priority || mask->vlan_tpid) {
+			if (key->vlan_tpid == htons(ETH_P_8021AD)) {
+				MLX5_SET(fte_match_set_misc, misc_c,
+					 outer_second_svlan_tag, 1);
+				MLX5_SET(fte_match_set_misc, misc_v,
+					 outer_second_svlan_tag, 1);
+			} else {
+				MLX5_SET(fte_match_set_misc, misc_c,
+					 outer_second_cvlan_tag, 1);
+				MLX5_SET(fte_match_set_misc, misc_v,
+					 outer_second_cvlan_tag, 1);
+			}
+
+			MLX5_SET(fte_match_set_misc, misc_c, outer_second_vid,
+				 mask->vlan_id);
+			MLX5_SET(fte_match_set_misc, misc_v, outer_second_vid,
+				 key->vlan_id);
+			MLX5_SET(fte_match_set_misc, misc_c, outer_second_prio,
+				 mask->vlan_priority);
+			MLX5_SET(fte_match_set_misc, misc_v, outer_second_prio,
+				 key->vlan_priority);
+
+			*match_level = MLX5_MATCH_L2;
+		}
+	}
+
 	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
 		struct flow_dissector_key_basic *key =
 			skb_flow_dissector_target(f->dissector,
-- 
cgit v1.2.3


From 1482bd3d50d77d28961999ade98854b31b342156 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Tue, 3 Jul 2018 05:46:13 +0000
Subject: net/mlx5e: Refactor tc vlan push/pop actions offloading

Extract actions offloading code to a new function, and also extend data
structures for double vlan actions.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 51 ++++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  |  6 +--
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 12 ++---
 3 files changed, 41 insertions(+), 28 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index dcb8c4993811..35b3e135ae1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2578,6 +2578,32 @@ out_err:
 	return err;
 }
 
+static int parse_tc_vlan_action(struct mlx5e_priv *priv,
+				const struct tc_action *a,
+				struct mlx5_esw_flow_attr *attr,
+				u32 *action)
+{
+	if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
+		*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+	} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
+		*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
+		attr->vlan_vid[0] = tcf_vlan_push_vid(a);
+		if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) {
+			attr->vlan_prio[0] = tcf_vlan_push_prio(a);
+			attr->vlan_proto[0] = tcf_vlan_push_proto(a);
+			if (!attr->vlan_proto[0])
+				attr->vlan_proto[0] = htons(ETH_P_8021Q);
+		} else if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
+			   tcf_vlan_push_prio(a)) {
+			return -EOPNOTSUPP;
+		}
+	} else { /* action is TCA_VLAN_ACT_MODIFY */
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 				struct mlx5e_tc_flow_parse_attr *parse_attr,
 				struct mlx5e_tc_flow *flow)
@@ -2589,6 +2615,7 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 	LIST_HEAD(actions);
 	bool encap = false;
 	u32 action = 0;
+	int err;
 
 	if (!tcf_exts_has_actions(exts))
 		return -EINVAL;
@@ -2605,8 +2632,6 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_pedit(a)) {
-			int err;
-
 			err = parse_tc_pedit_action(priv, a, MLX5_FLOW_NAMESPACE_FDB,
 						    parse_attr);
 			if (err)
@@ -2673,23 +2698,11 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, struct tcf_exts *exts,
 		}
 
 		if (is_tcf_vlan(a)) {
-			if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
-			} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
-				action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
-				attr->vlan_vid = tcf_vlan_push_vid(a);
-				if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) {
-					attr->vlan_prio = tcf_vlan_push_prio(a);
-					attr->vlan_proto = tcf_vlan_push_proto(a);
-					if (!attr->vlan_proto)
-						attr->vlan_proto = htons(ETH_P_8021Q);
-				} else if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
-					   tcf_vlan_push_prio(a)) {
-					return -EOPNOTSUPP;
-				}
-			} else { /* action is TCA_VLAN_ACT_MODIFY */
-				return -EOPNOTSUPP;
-			}
+			err = parse_tc_vlan_action(priv, a, attr, &action);
+
+			if (err)
+				return err;
+
 			attr->mirror_count = attr->out_count;
 			continue;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index b174da2884c5..befa0011efee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -256,9 +256,9 @@ struct mlx5_esw_flow_attr {
 	int out_count;
 
 	int	action;
-	__be16	vlan_proto;
-	u16	vlan_vid;
-	u8	vlan_prio;
+	__be16	vlan_proto[1];
+	u16	vlan_vid[1];
+	u8	vlan_prio[1];
 	bool	vlan_handled;
 	u32	encap_id;
 	u32	mod_hdr_id;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index f32e69170b30..552954d7184e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -70,9 +70,9 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 		flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
 				     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
 	else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
-		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto);
-		flow_act.vlan[0].vid = attr->vlan_vid;
-		flow_act.vlan[0].prio = attr->vlan_prio;
+		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto[0]);
+		flow_act.vlan[0].vid = attr->vlan_vid[0];
+		flow_act.vlan[0].prio = attr->vlan_prio[0];
 	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
@@ -266,7 +266,7 @@ static int esw_add_vlan_action_check(struct mlx5_esw_flow_attr *attr,
 	/* protects against (1) setting rules with different vlans to push and
 	 * (2) setting rules w.o vlans (attr->vlan = 0) && w. vlans to push (!= 0)
 	 */
-	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid))
+	if (push && in_rep->vlan_refcount && (in_rep->vlan != attr->vlan_vid[0]))
 		goto out_notsupp;
 
 	return 0;
@@ -324,11 +324,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 		if (vport->vlan_refcount)
 			goto skip_set_push;
 
-		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid, 0,
+		err = __mlx5_eswitch_set_vport_vlan(esw, vport->vport, attr->vlan_vid[0], 0,
 						    SET_VLAN_INSERT | SET_VLAN_STRIP);
 		if (err)
 			goto out;
-		vport->vlan = attr->vlan_vid;
+		vport->vlan = attr->vlan_vid[0];
 skip_set_push:
 		vport->vlan_refcount++;
 	}
-- 
cgit v1.2.3


From cc495188a8ff0d169ad7c0182acd9c08b90e29ea Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Wed, 25 Apr 2018 09:57:26 +0000
Subject: net/mlx5e: Support offloading double vlan push/pop tc actions

As we can configure two push/pop actions in one flow table entry,
add support to offload those double vlan actions in a rule to HW.

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    | 46 ++++++++++++++++------
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.h  | 21 +++++++---
 .../ethernet/mellanox/mlx5/core/eswitch_offloads.c | 11 ++++--
 3 files changed, 58 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 35b3e135ae1d..e9888d6c1f7c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2583,24 +2583,48 @@ static int parse_tc_vlan_action(struct mlx5e_priv *priv,
 				struct mlx5_esw_flow_attr *attr,
 				u32 *action)
 {
+	u8 vlan_idx = attr->total_vlan;
+
+	if (vlan_idx >= MLX5_FS_VLAN_DEPTH)
+		return -EOPNOTSUPP;
+
 	if (tcf_vlan_action(a) == TCA_VLAN_ACT_POP) {
-		*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+		if (vlan_idx) {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
+								 MLX5_FS_VLAN_DEPTH))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2;
+		} else {
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_POP;
+		}
 	} else if (tcf_vlan_action(a) == TCA_VLAN_ACT_PUSH) {
-		*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
-		attr->vlan_vid[0] = tcf_vlan_push_vid(a);
-		if (mlx5_eswitch_vlan_actions_supported(priv->mdev)) {
-			attr->vlan_prio[0] = tcf_vlan_push_prio(a);
-			attr->vlan_proto[0] = tcf_vlan_push_proto(a);
-			if (!attr->vlan_proto[0])
-				attr->vlan_proto[0] = htons(ETH_P_8021Q);
-		} else if (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
-			   tcf_vlan_push_prio(a)) {
-			return -EOPNOTSUPP;
+		attr->vlan_vid[vlan_idx] = tcf_vlan_push_vid(a);
+		attr->vlan_prio[vlan_idx] = tcf_vlan_push_prio(a);
+		attr->vlan_proto[vlan_idx] = tcf_vlan_push_proto(a);
+		if (!attr->vlan_proto[vlan_idx])
+			attr->vlan_proto[vlan_idx] = htons(ETH_P_8021Q);
+
+		if (vlan_idx) {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev,
+								 MLX5_FS_VLAN_DEPTH))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2;
+		} else {
+			if (!mlx5_eswitch_vlan_actions_supported(priv->mdev, 1) &&
+			    (tcf_vlan_push_proto(a) != htons(ETH_P_8021Q) ||
+			     tcf_vlan_push_prio(a)))
+				return -EOPNOTSUPP;
+
+			*action |= MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH;
 		}
 	} else { /* action is TCA_VLAN_ACT_MODIFY */
 		return -EOPNOTSUPP;
 	}
 
+	attr->total_vlan = vlan_idx + 1;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
index befa0011efee..c17bfcab517c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h
@@ -38,6 +38,7 @@
 #include <net/devlink.h>
 #include <linux/mlx5/device.h>
 #include <linux/mlx5/eswitch.h>
+#include <linux/mlx5/fs.h>
 #include "lib/mpfs.h"
 
 #ifdef CONFIG_MLX5_ESWITCH
@@ -256,9 +257,10 @@ struct mlx5_esw_flow_attr {
 	int out_count;
 
 	int	action;
-	__be16	vlan_proto[1];
-	u16	vlan_vid[1];
-	u8	vlan_prio[1];
+	__be16	vlan_proto[MLX5_FS_VLAN_DEPTH];
+	u16	vlan_vid[MLX5_FS_VLAN_DEPTH];
+	u8	vlan_prio[MLX5_FS_VLAN_DEPTH];
+	u8	total_vlan;
 	bool	vlan_handled;
 	u32	encap_id;
 	u32	mod_hdr_id;
@@ -282,10 +284,17 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw,
 				  int vport, u16 vlan, u8 qos, u8 set_flags);
 
-static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev)
+static inline bool mlx5_eswitch_vlan_actions_supported(struct mlx5_core_dev *dev,
+						       u8 vlan_depth)
 {
-	return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan) &&
-	       MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan);
+	bool ret = MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan) &&
+		   MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan);
+
+	if (vlan_depth == 1)
+		return ret;
+
+	return  ret && MLX5_CAP_ESW_FLOWTABLE_FDB(dev, pop_vlan_2) &&
+		MLX5_CAP_ESW_FLOWTABLE_FDB(dev, push_vlan_2);
 }
 
 #define MLX5_DEBUG_ESWITCH_MASK BIT(3)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 552954d7184e..f72b5c9dcfe9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -66,13 +66,18 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw,
 
 	flow_act.action = attr->action;
 	/* if per flow vlan pop/push is emulated, don't set that into the firmware */
-	if (!mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (!mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		flow_act.action &= ~(MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH |
 				     MLX5_FLOW_CONTEXT_ACTION_VLAN_POP);
 	else if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) {
 		flow_act.vlan[0].ethtype = ntohs(attr->vlan_proto[0]);
 		flow_act.vlan[0].vid = attr->vlan_vid[0];
 		flow_act.vlan[0].prio = attr->vlan_prio[0];
+		if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) {
+			flow_act.vlan[1].ethtype = ntohs(attr->vlan_proto[1]);
+			flow_act.vlan[1].vid = attr->vlan_vid[1];
+			flow_act.vlan[1].prio = attr->vlan_prio[1];
+		}
 	}
 
 	if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) {
@@ -284,7 +289,7 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw,
 	int err = 0;
 
 	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		return 0;
 
 	push = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH);
@@ -347,7 +352,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw,
 	int err = 0;
 
 	/* nop if we're on the vlan push/pop non emulation mode */
-	if (mlx5_eswitch_vlan_actions_supported(esw->dev))
+	if (mlx5_eswitch_vlan_actions_supported(esw->dev, 1))
 		return 0;
 
 	if (!attr->vlan_handled)
-- 
cgit v1.2.3


From 3f44899ef2ce0c9da49feb0d6f08098a08cb96ae Mon Sep 17 00:00:00 2001
From: Boris Pismenny <borisp@mellanox.com>
Date: Sat, 30 Jun 2018 22:14:27 +0300
Subject: net/mlx5e: Use PARTIAL_GSO for UDP segmentation

This patch removes the splitting of UDP_GSO_L4 packets in the driver,
and exposes UDP_GSO_L4 as a PARTIAL_GSO feature. Thus, the network stack
is not responsible for splitting the packet into two.

Signed-off-by: Boris Pismenny <borisp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   4 +-
 .../mellanox/mlx5/core/en_accel/en_accel.h         |  27 ++---
 .../ethernet/mellanox/mlx5/core/en_accel/rxtx.c    | 109 ---------------------
 .../ethernet/mellanox/mlx5/core/en_accel/rxtx.h    |  14 ---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |   9 +-
 5 files changed, 23 insertions(+), 140 deletions(-)
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 55d5a5c2e9d8..fa7fcca5dc78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en_accel/rxtx.o en_stats.o  \
-		vxlan.o en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
+		en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o          \
+		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
index 39a5d13ba459..1dd225380a66 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h
@@ -38,14 +38,22 @@
 #include <linux/netdevice.h>
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
-#include "en_accel/rxtx.h"
 #include "en.h"
 
-static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
-						    struct mlx5e_txqsq *sq,
-						    struct net_device *dev,
-						    struct mlx5e_tx_wqe **wqe,
-						    u16 *pi)
+static inline void
+mlx5e_udp_gso_handle_tx_skb(struct sk_buff *skb)
+{
+	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
+
+	udp_hdr(skb)->len = htons(payload_len);
+}
+
+static inline struct sk_buff *
+mlx5e_accel_handle_tx(struct sk_buff *skb,
+		      struct mlx5e_txqsq *sq,
+		      struct net_device *dev,
+		      struct mlx5e_tx_wqe **wqe,
+		      u16 *pi)
 {
 #ifdef CONFIG_MLX5_EN_TLS
 	if (test_bit(MLX5E_SQ_STATE_TLS, &sq->state)) {
@@ -63,11 +71,8 @@ static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb,
 	}
 #endif
 
-	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) {
-		skb = mlx5e_udp_gso_handle_tx_skb(dev, sq, skb, wqe, pi);
-		if (unlikely(!skb))
-			return NULL;
-	}
+	if (skb_is_gso(skb) && skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+		mlx5e_udp_gso_handle_tx_skb(skb);
 
 	return skb;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
deleted file mode 100644
index 7b7ec3998e84..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.c
+++ /dev/null
@@ -1,109 +0,0 @@
-#include "en_accel/rxtx.h"
-
-static void mlx5e_udp_gso_prepare_last_skb(struct sk_buff *skb,
-					   struct sk_buff *nskb,
-					   int remaining)
-{
-	int bytes_needed = remaining, remaining_headlen, remaining_page_offset;
-	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
-	int payload_len = remaining + sizeof(struct udphdr);
-	int k = 0, i, j;
-
-	skb_copy_bits(skb, 0, nskb->data, headlen);
-	nskb->dev = skb->dev;
-	skb_reset_mac_header(nskb);
-	skb_set_network_header(nskb, skb_network_offset(skb));
-	skb_set_transport_header(nskb, skb_transport_offset(skb));
-	skb_set_tail_pointer(nskb, headlen);
-
-	/* How many frags do we need? */
-	for (i = skb_shinfo(skb)->nr_frags - 1; i >= 0; i--) {
-		bytes_needed -= skb_frag_size(&skb_shinfo(skb)->frags[i]);
-		k++;
-		if (bytes_needed <= 0)
-			break;
-	}
-
-	/* Fill the first frag and split it if necessary */
-	j = skb_shinfo(skb)->nr_frags - k;
-	remaining_page_offset = -bytes_needed;
-	skb_fill_page_desc(nskb, 0,
-			   skb_shinfo(skb)->frags[j].page.p,
-			   skb_shinfo(skb)->frags[j].page_offset + remaining_page_offset,
-			   skb_shinfo(skb)->frags[j].size - remaining_page_offset);
-
-	skb_frag_ref(skb, j);
-
-	/* Fill the rest of the frags */
-	for (i = 1; i < k; i++) {
-		j = skb_shinfo(skb)->nr_frags - k + i;
-
-		skb_fill_page_desc(nskb, i,
-				   skb_shinfo(skb)->frags[j].page.p,
-				   skb_shinfo(skb)->frags[j].page_offset,
-				   skb_shinfo(skb)->frags[j].size);
-		skb_frag_ref(skb, j);
-	}
-	skb_shinfo(nskb)->nr_frags = k;
-
-	remaining_headlen = remaining - skb->data_len;
-
-	/* headlen contains remaining data? */
-	if (remaining_headlen > 0)
-		skb_copy_bits(skb, skb->len - remaining, nskb->data + headlen,
-			      remaining_headlen);
-	nskb->len = remaining + headlen;
-	nskb->data_len =  payload_len - sizeof(struct udphdr) +
-		max_t(int, 0, remaining_headlen);
-	nskb->protocol = skb->protocol;
-	if (nskb->protocol == htons(ETH_P_IP)) {
-		ip_hdr(nskb)->id = htons(ntohs(ip_hdr(nskb)->id) +
-					 skb_shinfo(skb)->gso_segs);
-		ip_hdr(nskb)->tot_len =
-			htons(payload_len + sizeof(struct iphdr));
-	} else {
-		ipv6_hdr(nskb)->payload_len = htons(payload_len);
-	}
-	udp_hdr(nskb)->len = htons(payload_len);
-	skb_shinfo(nskb)->gso_size = 0;
-	nskb->ip_summed = skb->ip_summed;
-	nskb->csum_start = skb->csum_start;
-	nskb->csum_offset = skb->csum_offset;
-	nskb->queue_mapping = skb->queue_mapping;
-}
-
-/* might send skbs and update wqe and pi */
-struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
-					    struct mlx5e_txqsq *sq,
-					    struct sk_buff *skb,
-					    struct mlx5e_tx_wqe **wqe,
-					    u16 *pi)
-{
-	int payload_len = skb_shinfo(skb)->gso_size + sizeof(struct udphdr);
-	int headlen = skb_transport_offset(skb) + sizeof(struct udphdr);
-	int remaining = (skb->len - headlen) % skb_shinfo(skb)->gso_size;
-	struct sk_buff *nskb;
-
-	if (skb->protocol == htons(ETH_P_IP))
-		ip_hdr(skb)->tot_len = htons(payload_len + sizeof(struct iphdr));
-	else
-		ipv6_hdr(skb)->payload_len = htons(payload_len);
-	udp_hdr(skb)->len = htons(payload_len);
-	if (!remaining)
-		return skb;
-
-	sq->stats->udp_seg_rem++;
-	nskb = alloc_skb(max_t(int, headlen, headlen + remaining - skb->data_len), GFP_ATOMIC);
-	if (unlikely(!nskb)) {
-		sq->stats->dropped++;
-		return NULL;
-	}
-
-	mlx5e_udp_gso_prepare_last_skb(skb, nskb, remaining);
-
-	skb_shinfo(skb)->gso_segs--;
-	pskb_trim(skb, skb->len - remaining);
-	mlx5e_sq_xmit(sq, skb, *wqe, *pi);
-	mlx5e_sq_fetch_wqe(sq, wqe, pi);
-	return nskb;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
deleted file mode 100644
index ed42699a78b3..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/rxtx.h
+++ /dev/null
@@ -1,14 +0,0 @@
-
-#ifndef __MLX5E_EN_ACCEL_RX_TX_H__
-#define __MLX5E_EN_ACCEL_RX_TX_H__
-
-#include <linux/skbuff.h>
-#include "en.h"
-
-struct sk_buff *mlx5e_udp_gso_handle_tx_skb(struct net_device *netdev,
-					    struct mlx5e_txqsq *sq,
-					    struct sk_buff *skb,
-					    struct mlx5e_tx_wqe **wqe,
-					    u16 *pi);
-
-#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 712b9766485f..dccde18f6170 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4538,7 +4538,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
 	if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
-		netdev->hw_features     |= NETIF_F_GSO_PARTIAL;
 		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
 		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -4563,6 +4562,11 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 						NETIF_F_GSO_GRE_CSUM;
 	}
 
+	netdev->hw_features	                 |= NETIF_F_GSO_PARTIAL;
+	netdev->gso_partial_features             |= NETIF_F_GSO_UDP_L4;
+	netdev->hw_features                      |= NETIF_F_GSO_UDP_L4;
+	netdev->features                         |= NETIF_F_GSO_UDP_L4;
+
 	mlx5_query_port_fcs(mdev, &fcs_supported, &fcs_enabled);
 
 	if (fcs_supported)
@@ -4595,9 +4599,6 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->features         |= NETIF_F_HIGHDMA;
 	netdev->features         |= NETIF_F_HW_VLAN_STAG_FILTER;
 
-	netdev->features         |= NETIF_F_GSO_UDP_L4;
-	netdev->hw_features      |= NETIF_F_GSO_UDP_L4;
-
 	netdev->priv_flags       |= IFF_UNICAST_FLT;
 
 	mlx5e_set_netdev_dev_addr(netdev);
-- 
cgit v1.2.3


From b4efce5c4715ae9b82e5314d7324a412f06a6a5a Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Tue, 19 Jun 2018 16:26:50 +0200
Subject: PCI: hotplug: Delete skeleton driver

Ten years ago, commit 58319b802a61 ("PCI: Hotplug core: remove 'name'")
dropped the name element from struct hotplug_slot but neglected to update
the skeleton driver.

That same year, commit f46753c5e354 ("PCI: introduce pci_slot") raised the
number of arguments to pci_hp_register() from one to four.

Fourteen years ago, historic commit 7ab60fc1b8e7 ("PCI Hotplug skeleton:
final cleanups") removed all usages of the retval variable from
pcihp_skel_init() but not the variable itself, provoking a compiler
warning: https://git.kernel.org/tglx/history/c/7ab60fc1b8e7

It seems fair to assume the driver hasn't been used as a template for a new
driver in a while.  Per Bjorn's and Christoph's preference, delete it.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Christoph Hellwig <hch@lst.de>
---
 drivers/pci/hotplug/pcihp_skeleton.c | 348 -----------------------------------
 1 file changed, 348 deletions(-)
 delete mode 100644 drivers/pci/hotplug/pcihp_skeleton.c

diff --git a/drivers/pci/hotplug/pcihp_skeleton.c b/drivers/pci/hotplug/pcihp_skeleton.c
deleted file mode 100644
index c19694a04d2c..000000000000
--- a/drivers/pci/hotplug/pcihp_skeleton.c
+++ /dev/null
@@ -1,348 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- * PCI Hot Plug Controller Skeleton Driver - 0.3
- *
- * Copyright (C) 2001,2003 Greg Kroah-Hartman (greg@kroah.com)
- * Copyright (C) 2001,2003 IBM Corp.
- *
- * All rights reserved.
- *
- * This driver is to be used as a skeleton driver to show how to interface
- * with the pci hotplug core easily.
- *
- * Send feedback to <greg@kroah.com>
- *
- */
-
-#include <linux/module.h>
-#include <linux/moduleparam.h>
-#include <linux/kernel.h>
-#include <linux/slab.h>
-#include <linux/pci.h>
-#include <linux/pci_hotplug.h>
-#include <linux/init.h>
-
-#define SLOT_NAME_SIZE	10
-struct slot {
-	u8 number;
-	struct hotplug_slot *hotplug_slot;
-	struct list_head slot_list;
-	char name[SLOT_NAME_SIZE];
-};
-
-static LIST_HEAD(slot_list);
-
-#define MY_NAME	"pcihp_skeleton"
-
-#define dbg(format, arg...)					\
-	do {							\
-		if (debug)					\
-			printk(KERN_DEBUG "%s: " format "\n",	\
-				MY_NAME, ## arg);		\
-	} while (0)
-#define err(format, arg...) printk(KERN_ERR "%s: " format "\n", MY_NAME, ## arg)
-#define info(format, arg...) printk(KERN_INFO "%s: " format "\n", MY_NAME, ## arg)
-#define warn(format, arg...) printk(KERN_WARNING "%s: " format "\n", MY_NAME, ## arg)
-
-/* local variables */
-static bool debug;
-static int num_slots;
-
-#define DRIVER_VERSION	"0.3"
-#define DRIVER_AUTHOR	"Greg Kroah-Hartman <greg@kroah.com>"
-#define DRIVER_DESC	"Hot Plug PCI Controller Skeleton Driver"
-
-MODULE_AUTHOR(DRIVER_AUTHOR);
-MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_LICENSE("GPL");
-module_param(debug, bool, 0644);
-MODULE_PARM_DESC(debug, "Debugging mode enabled or not");
-
-static int enable_slot(struct hotplug_slot *slot);
-static int disable_slot(struct hotplug_slot *slot);
-static int set_attention_status(struct hotplug_slot *slot, u8 value);
-static int hardware_test(struct hotplug_slot *slot, u32 value);
-static int get_power_status(struct hotplug_slot *slot, u8 *value);
-static int get_attention_status(struct hotplug_slot *slot, u8 *value);
-static int get_latch_status(struct hotplug_slot *slot, u8 *value);
-static int get_adapter_status(struct hotplug_slot *slot, u8 *value);
-
-static struct hotplug_slot_ops skel_hotplug_slot_ops = {
-	.enable_slot =		enable_slot,
-	.disable_slot =		disable_slot,
-	.set_attention_status =	set_attention_status,
-	.hardware_test =	hardware_test,
-	.get_power_status =	get_power_status,
-	.get_attention_status =	get_attention_status,
-	.get_latch_status =	get_latch_status,
-	.get_adapter_status =	get_adapter_status,
-};
-
-static int enable_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in code here to enable the specified slot
-	 */
-
-	return retval;
-}
-
-static int disable_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in code here to disable the specified slot
-	 */
-
-	return retval;
-}
-
-static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	switch (status) {
-	case 0:
-		/*
-		 * Fill in code here to turn light off
-		 */
-		break;
-
-	case 1:
-	default:
-		/*
-		 * Fill in code here to turn light on
-		 */
-		break;
-	}
-
-	return retval;
-}
-
-static int hardware_test(struct hotplug_slot *hotplug_slot, u32 value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	switch (value) {
-	case 0:
-		/* Specify a test here */
-		break;
-	case 1:
-		/* Specify another test here */
-		break;
-	}
-
-	return retval;
-}
-
-static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current power status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current attention status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current latch status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
-{
-	struct slot *slot = hotplug_slot->private;
-	int retval = 0;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-
-	/*
-	 * Fill in logic to get the current adapter status of the specific
-	 * slot and store it in the *value location.
-	 */
-
-	return retval;
-}
-
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	dbg("%s - physical_slot = %s\n", __func__, hotplug_slot->name);
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
-static void make_slot_name(struct slot *slot)
-{
-	/*
-	 * Stupid way to make a filename out of the slot name.
-	 * replace this if your hardware provides a better way to name slots.
-	 */
-	snprintf(slot->hotplug_slot->name, SLOT_NAME_SIZE, "%d", slot->number);
-}
-
-/**
- * init_slots - initialize 'struct slot' structures for each slot
- *
- */
-static int __init init_slots(void)
-{
-	struct slot *slot;
-	struct hotplug_slot *hotplug_slot;
-	struct hotplug_slot_info *info;
-	int retval;
-	int i;
-
-	/*
-	 * Create a structure for each slot, and register that slot
-	 * with the pci_hotplug subsystem.
-	 */
-	for (i = 0; i < num_slots; ++i) {
-		slot = kzalloc(sizeof(*slot), GFP_KERNEL);
-		if (!slot) {
-			retval = -ENOMEM;
-			goto error;
-		}
-
-		hotplug_slot = kzalloc(sizeof(*hotplug_slot), GFP_KERNEL);
-		if (!hotplug_slot) {
-			retval = -ENOMEM;
-			goto error_slot;
-		}
-		slot->hotplug_slot = hotplug_slot;
-
-		info = kzalloc(sizeof(*info), GFP_KERNEL);
-		if (!info) {
-			retval = -ENOMEM;
-			goto error_hpslot;
-		}
-		hotplug_slot->info = info;
-
-		slot->number = i;
-
-		hotplug_slot->name = slot->name;
-		hotplug_slot->private = slot;
-		hotplug_slot->release = &release_slot;
-		make_slot_name(slot);
-		hotplug_slot->ops = &skel_hotplug_slot_ops;
-
-		/*
-		 * Initialize the slot info structure with some known
-		 * good values.
-		 */
-		get_power_status(hotplug_slot, &info->power_status);
-		get_attention_status(hotplug_slot, &info->attention_status);
-		get_latch_status(hotplug_slot, &info->latch_status);
-		get_adapter_status(hotplug_slot, &info->adapter_status);
-
-		dbg("registering slot %d\n", i);
-		retval = pci_hp_register(slot->hotplug_slot);
-		if (retval) {
-			err("pci_hp_register failed with error %d\n", retval);
-			goto error_info;
-		}
-
-		/* add slot to our internal list */
-		list_add(&slot->slot_list, &slot_list);
-	}
-
-	return 0;
-error_info:
-	kfree(info);
-error_hpslot:
-	kfree(hotplug_slot);
-error_slot:
-	kfree(slot);
-error:
-	return retval;
-}
-
-static void __exit cleanup_slots(void)
-{
-	struct slot *slot, *next;
-
-	/*
-	 * Unregister all of our slots with the pci_hotplug subsystem.
-	 * Memory will be freed in release_slot() callback after slot's
-	 * lifespan is finished.
-	 */
-	list_for_each_entry_safe(slot, next, &slot_list, slot_list) {
-		list_del(&slot->slot_list);
-		pci_hp_deregister(slot->hotplug_slot);
-	}
-}
-
-static int __init pcihp_skel_init(void)
-{
-	int retval;
-
-	info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
-	/*
-	 * Do specific initialization stuff for your driver here
-	 * like initializing your controller hardware (if any) and
-	 * determining the number of slots you have in the system
-	 * right now.
-	 */
-	num_slots = 5;
-
-	return init_slots();
-}
-
-static void __exit pcihp_skel_exit(void)
-{
-	/*
-	 * Clean everything up.
-	 */
-	cleanup_slots();
-}
-
-module_init(pcihp_skel_init);
-module_exit(pcihp_skel_exit);
-- 
cgit v1.2.3


From 4ce6435820d1f1cc2c2788e232735eb244bcc8a3 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:31 -0500
Subject: PCI: hotplug: Don't leak pci_slot on registration failure

If addition of sysfs files fails on registration of a hotplug slot, the
struct pci_slot as well as the entry in the slot_list is leaked.  The
issue has been present since the hotplug core was introduced in 2002:
https://git.kernel.org/tglx/history/c/a8a2069f432c

Perhaps the idea was that even though sysfs addition fails, the slot
should still be usable.  But that's not how drivers use the interface,
they abort probe if a non-zero value is returned.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org # v2.4.15+
Cc: Greg Kroah-Hartman <greg@kroah.com>
---
 drivers/pci/hotplug/pci_hotplug_core.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index af92fed46ab7..fd93783a87b0 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -438,8 +438,17 @@ int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus,
 	list_add(&slot->slot_list, &pci_hotplug_slot_list);
 
 	result = fs_add_slot(pci_slot);
+	if (result)
+		goto err_list_del;
+
 	kobject_uevent(&pci_slot->kobj, KOBJ_ADD);
 	dbg("Added slot %s to the list\n", name);
+	goto out;
+
+err_list_del:
+	list_del(&slot->slot_list);
+	pci_slot->hotplug = NULL;
+	pci_destroy_slot(pci_slot);
 out:
 	mutex_unlock(&pci_hp_mutex);
 	return result;
-- 
cgit v1.2.3


From 281e878eab191cce4259abbbf1a0322e3adae02c Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:32 -0500
Subject: PCI: pciehp: Fix use-after-free on unplug

When pciehp is unbound (e.g. on unplug of a Thunderbolt device), the
hotplug_slot struct is deregistered and thus freed before freeing the
IRQ.  The IRQ handler and the work items it schedules print the slot
name referenced from the freed structure in various informational and
debug log messages, each time resulting in a quadruple dereference of
freed pointers (hotplug_slot -> pci_slot -> kobject -> name).

At best the slot name is logged as "(null)", at worst kernel memory is
exposed in logs or the driver crashes:

  pciehp 0000:10:00.0:pcie204: Slot((null)): Card not present

An attacker may provoke the bug by unplugging multiple devices on a
Thunderbolt daisy chain at once.  Unplugging can also be simulated by
powering down slots via sysfs.  The bug is particularly easy to trigger
in poll mode.

It has been present since the driver's introduction in 2004:
https://git.kernel.org/tglx/history/c/c16b4b14d980

Fix by rearranging teardown such that the IRQ is freed first.  Run the
work items queued by the IRQ handler to completion before freeing the
hotplug_slot struct by draining the work queue from the ->release_slot
callback which is invoked by pci_hp_deregister().

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org # v2.6.4
---
 drivers/pci/hotplug/pciehp.h      | 1 +
 drivers/pci/hotplug/pciehp_core.c | 7 +++++++
 drivers/pci/hotplug/pciehp_hpc.c  | 5 ++---
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 5f892065585e..fca87a1a2b22 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -119,6 +119,7 @@ int pciehp_unconfigure_device(struct slot *p_slot);
 void pciehp_queue_pushbutton_work(struct work_struct *work);
 struct controller *pcie_init(struct pcie_device *dev);
 int pcie_init_notification(struct controller *ctrl);
+void pcie_shutdown_notification(struct controller *ctrl);
 int pciehp_enable_slot(struct slot *p_slot);
 int pciehp_disable_slot(struct slot *p_slot);
 void pcie_reenable_notification(struct controller *ctrl);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 44a6a63802d5..2ba59fc94827 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -62,6 +62,12 @@ static int reset_slot(struct hotplug_slot *slot, int probe);
  */
 static void release_slot(struct hotplug_slot *hotplug_slot)
 {
+	struct slot *slot = hotplug_slot->private;
+
+	/* queued work needs hotplug_slot name */
+	cancel_delayed_work(&slot->work);
+	drain_workqueue(slot->wq);
+
 	kfree(hotplug_slot->ops);
 	kfree(hotplug_slot->info);
 	kfree(hotplug_slot);
@@ -264,6 +270,7 @@ static void pciehp_remove(struct pcie_device *dev)
 {
 	struct controller *ctrl = get_service_data(dev);
 
+	pcie_shutdown_notification(ctrl);
 	cleanup_slot(ctrl);
 	pciehp_release_ctrl(ctrl);
 }
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 718b6073afad..84b3d421c083 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -765,7 +765,7 @@ int pcie_init_notification(struct controller *ctrl)
 	return 0;
 }
 
-static void pcie_shutdown_notification(struct controller *ctrl)
+void pcie_shutdown_notification(struct controller *ctrl)
 {
 	if (ctrl->notification_enabled) {
 		pcie_disable_notification(ctrl);
@@ -800,7 +800,7 @@ abort:
 static void pcie_cleanup_slot(struct controller *ctrl)
 {
 	struct slot *slot = ctrl->slot;
-	cancel_delayed_work(&slot->work);
+
 	destroy_workqueue(slot->wq);
 	kfree(slot);
 }
@@ -893,7 +893,6 @@ abort:
 
 void pciehp_release_ctrl(struct controller *ctrl)
 {
-	pcie_shutdown_notification(ctrl);
 	pcie_cleanup_slot(ctrl);
 	kfree(ctrl);
 }
-- 
cgit v1.2.3


From 1204e35bedf4e5015cda559ed8c84789a6dae24e Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:34 -0500
Subject: PCI: pciehp: Fix unprotected list iteration in IRQ handler

Commit b440bde74f04 ("PCI: Add pci_ignore_hotplug() to ignore hotplug
events for a device") iterates over the devices on a hotplug port's
subordinate bus in pciehp's IRQ handler without acquiring pci_bus_sem.
It is thus possible for a user to cause a crash by concurrently
manipulating the device list, e.g. by disabling slot power via sysfs
on a different CPU or by initiating a remove/rescan via sysfs.

This can't be fixed by acquiring pci_bus_sem because it may sleep.
The simplest fix is to avoid the list iteration altogether and just
check the ignore_hotplug flag on the port itself.  This works because
pci_ignore_hotplug() sets the flag both on the device as well as on its
parent bridge.

We do lose the ability to print the name of the device blocking hotplug
in the debug message, but that's probably bearable.

Fixes: b440bde74f04 ("PCI: Add pci_ignore_hotplug() to ignore hotplug events for a device")
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org
---
 drivers/pci/hotplug/pciehp_hpc.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 84b3d421c083..aff191b4552c 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -539,8 +539,6 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 {
 	struct controller *ctrl = (struct controller *)dev_id;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
-	struct pci_bus *subordinate = pdev->subordinate;
-	struct pci_dev *dev;
 	struct slot *slot = ctrl->slot;
 	u16 status, events;
 	u8 present;
@@ -588,14 +586,9 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 		wake_up(&ctrl->queue);
 	}
 
-	if (subordinate) {
-		list_for_each_entry(dev, &subordinate->devices, bus_list) {
-			if (dev->ignore_hotplug) {
-				ctrl_dbg(ctrl, "ignoring hotplug event %#06x (%s requested no hotplug)\n",
-					 events, pci_name(dev));
-				return IRQ_HANDLED;
-			}
-		}
+	if (pdev->ignore_hotplug) {
+		ctrl_dbg(ctrl, "ignoring hotplug event %#06x\n", events);
+		return IRQ_HANDLED;
 	}
 
 	/* Check Attention Button Pressed */
-- 
cgit v1.2.3


From 6641311df92d171648faeede6ec9ec612d32d15b Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:35 -0500
Subject: PCI: pciehp: Drop unnecessary NULL pointer check

pciehp_disable_slot() checks if the ctrl attribute of the slot is NULL
and bails out if so.  However the function is not called prior to the
attribute being set in pcie_init_slot(), and pcie_init_slot() is not
called if ctrl is NULL.  So the check is unnecessary.  Drop it.

It has been present ever since the driver was introduced in 2004, but it
was already unnecessary back then:
https://git.kernel.org/tglx/history/c/c16b4b14d980

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp_ctrl.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index c684faa43387..4a4639b7a479 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -412,9 +412,6 @@ int pciehp_disable_slot(struct slot *p_slot)
 	u8 getstatus = 0;
 	struct controller *ctrl = p_slot->ctrl;
 
-	if (!p_slot->ctrl)
-		return 1;
-
 	if (POWER_CTRL(p_slot->ctrl)) {
 		pciehp_get_power_status(p_slot, &getstatus);
 		if (!getstatus) {
-- 
cgit v1.2.3


From 1d2e2673dc5b9b374513fd58d5909f0332b47407 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:36 -0500
Subject: PCI: pciehp: Declare pciehp_unconfigure_device() void

Since commit 0f4bd8014db5 ("PCI: hotplug: Drop checking of PCI_BRIDGE_
CONTROL in *_unconfigure_device()"), pciehp_unconfigure_device() can no
longer fail, so declare it and its sole caller remove_board() void, in
keeping with the usual kernel pattern that enablement can fail, but
disablement cannot.  No functional change intended.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pci/hotplug/pciehp.h      |  2 +-
 drivers/pci/hotplug/pciehp_ctrl.c | 11 ++++-------
 drivers/pci/hotplug/pciehp_pci.c  |  4 +---
 3 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index fca87a1a2b22..acdeb08cbcba 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -115,7 +115,7 @@ int pciehp_sysfs_enable_slot(struct slot *slot);
 int pciehp_sysfs_disable_slot(struct slot *slot);
 void pciehp_queue_interrupt_event(struct slot *slot, u32 event_type);
 int pciehp_configure_device(struct slot *p_slot);
-int pciehp_unconfigure_device(struct slot *p_slot);
+void pciehp_unconfigure_device(struct slot *p_slot);
 void pciehp_queue_pushbutton_work(struct work_struct *work);
 struct controller *pcie_init(struct pcie_device *dev);
 int pcie_init_notification(struct controller *ctrl);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 4a4639b7a479..76a9b8c26d2b 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -119,14 +119,11 @@ err_exit:
  * remove_board - Turns off slot and LEDs
  * @p_slot: slot where board is being removed
  */
-static int remove_board(struct slot *p_slot)
+static void remove_board(struct slot *p_slot)
 {
-	int retval;
 	struct controller *ctrl = p_slot->ctrl;
 
-	retval = pciehp_unconfigure_device(p_slot);
-	if (retval)
-		return retval;
+	pciehp_unconfigure_device(p_slot);
 
 	if (POWER_CTRL(ctrl)) {
 		pciehp_power_off_slot(p_slot);
@@ -141,7 +138,6 @@ static int remove_board(struct slot *p_slot)
 
 	/* turn off Green LED */
 	pciehp_green_led_off(p_slot);
-	return 0;
 }
 
 struct power_work_info {
@@ -421,7 +417,8 @@ int pciehp_disable_slot(struct slot *p_slot)
 		}
 	}
 
-	return remove_board(p_slot);
+	remove_board(p_slot);
+	return 0;
 }
 
 int pciehp_sysfs_enable_slot(struct slot *p_slot)
diff --git a/drivers/pci/hotplug/pciehp_pci.c b/drivers/pci/hotplug/pciehp_pci.c
index 3f518dea856d..5c58c22e0c08 100644
--- a/drivers/pci/hotplug/pciehp_pci.c
+++ b/drivers/pci/hotplug/pciehp_pci.c
@@ -62,9 +62,8 @@ int pciehp_configure_device(struct slot *p_slot)
 	return ret;
 }
 
-int pciehp_unconfigure_device(struct slot *p_slot)
+void pciehp_unconfigure_device(struct slot *p_slot)
 {
-	int rc = 0;
 	u8 presence = 0;
 	struct pci_dev *dev, *temp;
 	struct pci_bus *parent = p_slot->ctrl->pcie->port->subordinate;
@@ -107,5 +106,4 @@ int pciehp_unconfigure_device(struct slot *p_slot)
 	}
 
 	pci_unlock_rescan_remove();
-	return rc;
 }
-- 
cgit v1.2.3


From 4aed1cd6fb957fa8de5a9416a9adab98775878e9 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:36 -0500
Subject: PCI: pciehp: Document struct slot and struct controller

Document the driver's data structures to lower the barrier to entry for
contributors.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp.h | 48 ++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 44 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index acdeb08cbcba..c3d63e5b650f 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -57,11 +57,26 @@ do {									\
 	dev_warn(&ctrl->pcie->device, format, ## arg)
 
 #define SLOT_NAME_SIZE 10
+
+/**
+ * struct slot - PCIe hotplug slot
+ * @state: current state machine position
+ * @ctrl: pointer to the slot's controller structure
+ * @hotplug_slot: pointer to the structure registered with the PCI hotplug core
+ * @work: work item to turn the slot on or off after 5 seconds in response to
+ *	an Attention Button press
+ * @lock: protects reads and writes of @state;
+ *	protects scheduling, execution and cancellation of @work
+ * @hotplug_lock: serializes calls to pciehp_enable_slot() and
+ *	pciehp_disable_slot()
+ * @wq: work queue on which @work is scheduled;
+ *	also used to queue interrupt events and slot enablement and disablement
+ */
 struct slot {
 	u8 state;
 	struct controller *ctrl;
 	struct hotplug_slot *hotplug_slot;
-	struct delayed_work work;	/* work for button event */
+	struct delayed_work work;
 	struct mutex lock;
 	struct mutex hotplug_lock;
 	struct workqueue_struct *wq;
@@ -73,11 +88,36 @@ struct event_info {
 	struct work_struct work;
 };
 
+/**
+ * struct controller - PCIe hotplug controller
+ * @ctrl_lock: serializes writes to the Slot Control register
+ * @pcie: pointer to the controller's PCIe port service device
+ * @slot: pointer to the controller's slot structure
+ * @queue: wait queue to wake up on reception of a Command Completed event,
+ *	used for synchronous writes to the Slot Control register
+ * @slot_cap: cached copy of the Slot Capabilities register
+ * @slot_ctrl: cached copy of the Slot Control register
+ * @poll_timer: timer to poll for slot events if no IRQ is available,
+ *	enabled with pciehp_poll_mode module parameter
+ * @cmd_started: jiffies when the Slot Control register was last written;
+ *	the next write is allowed 1 second later, absent a Command Completed
+ *	interrupt (PCIe r4.0, sec 6.7.3.2)
+ * @cmd_busy: flag set on Slot Control register write, cleared by IRQ handler
+ *	on reception of a Command Completed event
+ * @link_active_reporting: cached copy of Data Link Layer Link Active Reporting
+ *	Capable bit in Link Capabilities register; if this bit is zero, the
+ *	Data Link Layer Link Active bit in the Link Status register will never
+ *	be set and the driver is thus confined to wait 1 second before assuming
+ *	the link to a hotplugged device is up and accessing it
+ * @notification_enabled: whether the IRQ was requested successfully
+ * @power_fault_detected: whether a power fault was detected by the hardware
+ *	that has not yet been cleared by the user
+ */
 struct controller {
-	struct mutex ctrl_lock;		/* controller lock */
-	struct pcie_device *pcie;	/* PCI Express port service */
+	struct mutex ctrl_lock;
+	struct pcie_device *pcie;
 	struct slot *slot;
-	wait_queue_head_t queue;	/* sleep & wake process */
+	wait_queue_head_t queue;
 	u32 slot_cap;
 	u16 slot_ctrl;
 	struct timer_list poll_timer;
-- 
cgit v1.2.3


From 7b4ce26bcf697e3a4aa9ba2a5b456562e0fb7af4 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:38 -0500
Subject: PCI: pciehp: Convert to threaded IRQ

pciehp's IRQ handler queues up a work item for each event signaled by
the hardware.  A more modern alternative is to let a long running
kthread service the events.  The IRQ handler's sole job is then to check
whether the IRQ originated from the device in question, acknowledge its
receipt to the hardware to quiesce the interrupt and wake up the kthread.

One benefit is reduced latency to handle the IRQ, which is a necessity
for realtime environments.  Another benefit is that we can make pciehp
simpler and more robust by handling events synchronously in process
context, rather than asynchronously by queueing up work items.  pciehp's
usage of work items is a historic artifact, it predates the introduction
of threaded IRQ handlers by two years.  (The former was introduced in
2007 with commit 5d386e1ac402 ("pciehp: Event handling rework"), the
latter in 2009 with commit 3aa551c9b4c4 ("genirq: add threaded interrupt
handler support").)

Convert pciehp to threaded IRQ handling by retrieving the pending events
in pciehp_isr(), saving them for later consumption by the thread handler
pciehp_ist() and clearing them in the Slot Status register.

By clearing the Slot Status (and thereby acknowledging the events) in
pciehp_isr(), we can avoid requesting the IRQ with IRQF_ONESHOT, which
would have the unpleasant side effect of starving devices sharing the
IRQ until pciehp_ist() has finished.

pciehp_isr() does not count how many times each event occurred, but
merely records the fact *that* an event occurred.  If the same event
occurs a second time before pciehp_ist() is woken, that second event
will not be recorded separately, which is problematic according to
commit fad214b0aa72 ("PCI: pciehp: Process all hotplug events before
looking for new ones") because we may miss removal of a card in-between
two back-to-back insertions.  We're about to make pciehp_ist() resilient
to missed events.  The present commit regresses the driver's behavior
temporarily in order to separate the changes into reviewable chunks.
This doesn't affect regular slow-motion hotplug, only plug-unplug-plug
operations that happen in a timespan shorter than wakeup of the IRQ
thread.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Mayurkumar Patel <mayurkumar.patel@intel.com>
Cc: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
---
 drivers/pci/hotplug/pciehp.h     |  3 ++
 drivers/pci/hotplug/pciehp_hpc.c | 70 ++++++++++++++++++++++------------------
 2 files changed, 41 insertions(+), 32 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index c3d63e5b650f..ab1d97a1822d 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -112,6 +112,8 @@ struct event_info {
  * @notification_enabled: whether the IRQ was requested successfully
  * @power_fault_detected: whether a power fault was detected by the hardware
  *	that has not yet been cleared by the user
+ * @pending_events: used by the IRQ handler to save events retrieved from the
+ *	Slot Status register for later consumption by the IRQ thread
  */
 struct controller {
 	struct mutex ctrl_lock;
@@ -126,6 +128,7 @@ struct controller {
 	unsigned int link_active_reporting:1;
 	unsigned int notification_enabled:1;
 	unsigned int power_fault_detected;
+	atomic_t pending_events;
 };
 
 #define INT_PRESENCE_ON			1
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index aff191b4552c..4ffaa3dfeb89 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -31,7 +31,8 @@ static inline struct pci_dev *ctrl_dev(struct controller *ctrl)
 	return ctrl->pcie->port;
 }
 
-static irqreturn_t pcie_isr(int irq, void *dev_id);
+static irqreturn_t pciehp_isr(int irq, void *dev_id);
+static irqreturn_t pciehp_ist(int irq, void *dev_id);
 static void start_int_poll_timer(struct controller *ctrl, int sec);
 
 /* This is the interrupt polling timeout function. */
@@ -40,7 +41,8 @@ static void int_poll_timeout(struct timer_list *t)
 	struct controller *ctrl = from_timer(ctrl, t, poll_timer);
 
 	/* Poll for interrupt events.  regs == NULL => polling */
-	pcie_isr(0, ctrl);
+	while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD)
+		pciehp_ist(IRQ_NOTCONNECTED, ctrl);
 
 	if (!pciehp_poll_time)
 		pciehp_poll_time = 2; /* default polling interval is 2 sec */
@@ -71,7 +73,8 @@ static inline int pciehp_request_irq(struct controller *ctrl)
 	}
 
 	/* Installs the interrupt handler */
-	retval = request_irq(irq, pcie_isr, IRQF_SHARED, MY_NAME, ctrl);
+	retval = request_threaded_irq(irq, pciehp_isr, pciehp_ist,
+				      IRQF_SHARED, MY_NAME, ctrl);
 	if (retval)
 		ctrl_err(ctrl, "Cannot get irq %d for the hotplug controller\n",
 			 irq);
@@ -539,12 +542,11 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 {
 	struct controller *ctrl = (struct controller *)dev_id;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
-	struct slot *slot = ctrl->slot;
 	u16 status, events;
-	u8 present;
-	bool link;
 
-	/* Interrupts cannot originate from a controller that's asleep */
+	/*
+	 * Interrupts only occur in D3hot or shallower (PCIe r4.0, sec 6.7.3.4).
+	 */
 	if (pdev->current_state == PCI_D3cold)
 		return IRQ_NONE;
 
@@ -572,18 +574,22 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	if (!events)
 		return IRQ_NONE;
 
-	/* Capture link status before clearing interrupts */
-	if (events & PCI_EXP_SLTSTA_DLLSC)
-		link = pciehp_check_link_active(ctrl);
-
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, events);
 	ctrl_dbg(ctrl, "pending interrupts %#06x from Slot Status\n", events);
 
-	/* Check Command Complete Interrupt Pending */
+	/*
+	 * Command Completed notifications are not deferred to the
+	 * IRQ thread because it may be waiting for their arrival.
+	 */
 	if (events & PCI_EXP_SLTSTA_CC) {
 		ctrl->cmd_busy = 0;
 		smp_mb();
 		wake_up(&ctrl->queue);
+
+		if (events == PCI_EXP_SLTSTA_CC)
+			return IRQ_HANDLED;
+
+		events &= ~PCI_EXP_SLTSTA_CC;
 	}
 
 	if (pdev->ignore_hotplug) {
@@ -591,6 +597,24 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 		return IRQ_HANDLED;
 	}
 
+	/* Save pending events for consumption by IRQ thread. */
+	atomic_or(events, &ctrl->pending_events);
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t pciehp_ist(int irq, void *dev_id)
+{
+	struct controller *ctrl = (struct controller *)dev_id;
+	struct slot *slot = ctrl->slot;
+	u32 events;
+	u8 present;
+	bool link;
+
+	synchronize_hardirq(irq);
+	events = atomic_xchg(&ctrl->pending_events, 0);
+	if (!events)
+		return IRQ_NONE;
+
 	/* Check Attention Button Pressed */
 	if (events & PCI_EXP_SLTSTA_ABP) {
 		ctrl_info(ctrl, "Slot(%s): Attention button pressed\n",
@@ -605,12 +629,13 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	 * and cause the wrong event to queue.
 	 */
 	if (events & PCI_EXP_SLTSTA_DLLSC) {
+		link = pciehp_check_link_active(ctrl);
 		ctrl_info(ctrl, "Slot(%s): Link %s\n", slot_name(slot),
 			  link ? "Up" : "Down");
 		pciehp_queue_interrupt_event(slot, link ? INT_LINK_UP :
 					     INT_LINK_DOWN);
 	} else if (events & PCI_EXP_SLTSTA_PDC) {
-		present = !!(status & PCI_EXP_SLTSTA_PDS);
+		pciehp_get_adapter_status(slot, &present);
 		ctrl_info(ctrl, "Slot(%s): Card %spresent\n", slot_name(slot),
 			  present ? "" : "not ");
 		pciehp_queue_interrupt_event(slot, present ? INT_PRESENCE_ON :
@@ -627,25 +652,6 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t pcie_isr(int irq, void *dev_id)
-{
-	irqreturn_t rc, handled = IRQ_NONE;
-
-	/*
-	 * To guarantee that all interrupt events are serviced, we need to
-	 * re-inspect Slot Status register after clearing what is presumed
-	 * to be the last pending interrupt.
-	 */
-	do {
-		rc = pciehp_isr(irq, dev_id);
-		if (rc == IRQ_HANDLED)
-			handled = IRQ_HANDLED;
-	} while (rc == IRQ_HANDLED);
-
-	/* Return IRQ_HANDLED if we handled one or more events */
-	return handled;
-}
-
 static void pcie_enable_notification(struct controller *ctrl)
 {
 	u16 cmd, mask;
-- 
cgit v1.2.3


From ec07a4473072ff0607e3126ce26c31dbf81f9a15 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:39 -0500
Subject: PCI: pciehp: Convert to threaded polling

We've just converted pciehp to threaded IRQ handling, but still cannot
sleep in pciehp_ist() because the function is also called in poll mode,
which runs in softirq context (from a timer).

Convert poll mode to a kthread so that pciehp_ist() always runs in task
context.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/pci/hotplug/pciehp.h     |  4 +--
 drivers/pci/hotplug/pciehp_hpc.c | 67 +++++++++++++++++++---------------------
 2 files changed, 34 insertions(+), 37 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index ab1d97a1822d..9f11360e3318 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -97,7 +97,7 @@ struct event_info {
  *	used for synchronous writes to the Slot Control register
  * @slot_cap: cached copy of the Slot Capabilities register
  * @slot_ctrl: cached copy of the Slot Control register
- * @poll_timer: timer to poll for slot events if no IRQ is available,
+ * @poll_thread: thread to poll for slot events if no IRQ is available,
  *	enabled with pciehp_poll_mode module parameter
  * @cmd_started: jiffies when the Slot Control register was last written;
  *	the next write is allowed 1 second later, absent a Command Completed
@@ -122,7 +122,7 @@ struct controller {
 	wait_queue_head_t queue;
 	u32 slot_cap;
 	u16 slot_ctrl;
-	struct timer_list poll_timer;
+	struct task_struct *poll_thread;
 	unsigned long cmd_started;	/* jiffies */
 	unsigned int cmd_busy:1;
 	unsigned int link_active_reporting:1;
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 4ffaa3dfeb89..d36650f2d2bb 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -17,7 +17,7 @@
 #include <linux/types.h>
 #include <linux/signal.h>
 #include <linux/jiffies.h>
-#include <linux/timer.h>
+#include <linux/kthread.h>
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
@@ -33,43 +33,17 @@ static inline struct pci_dev *ctrl_dev(struct controller *ctrl)
 
 static irqreturn_t pciehp_isr(int irq, void *dev_id);
 static irqreturn_t pciehp_ist(int irq, void *dev_id);
-static void start_int_poll_timer(struct controller *ctrl, int sec);
-
-/* This is the interrupt polling timeout function. */
-static void int_poll_timeout(struct timer_list *t)
-{
-	struct controller *ctrl = from_timer(ctrl, t, poll_timer);
-
-	/* Poll for interrupt events.  regs == NULL => polling */
-	while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD)
-		pciehp_ist(IRQ_NOTCONNECTED, ctrl);
-
-	if (!pciehp_poll_time)
-		pciehp_poll_time = 2; /* default polling interval is 2 sec */
-
-	start_int_poll_timer(ctrl, pciehp_poll_time);
-}
-
-/* This function starts the interrupt polling timer. */
-static void start_int_poll_timer(struct controller *ctrl, int sec)
-{
-	/* Clamp to sane value */
-	if ((sec <= 0) || (sec > 60))
-		sec = 2;
-
-	ctrl->poll_timer.expires = jiffies + sec * HZ;
-	add_timer(&ctrl->poll_timer);
-}
+static int pciehp_poll(void *data);
 
 static inline int pciehp_request_irq(struct controller *ctrl)
 {
 	int retval, irq = ctrl->pcie->irq;
 
-	/* Install interrupt polling timer. Start with 10 sec delay */
 	if (pciehp_poll_mode) {
-		timer_setup(&ctrl->poll_timer, int_poll_timeout, 0);
-		start_int_poll_timer(ctrl, 10);
-		return 0;
+		ctrl->poll_thread = kthread_run(&pciehp_poll, ctrl,
+						"pciehp_poll-%s",
+						slot_name(ctrl->slot));
+		return PTR_ERR_OR_ZERO(ctrl->poll_thread);
 	}
 
 	/* Installs the interrupt handler */
@@ -84,7 +58,7 @@ static inline int pciehp_request_irq(struct controller *ctrl)
 static inline void pciehp_free_irq(struct controller *ctrl)
 {
 	if (pciehp_poll_mode)
-		del_timer_sync(&ctrl->poll_timer);
+		kthread_stop(ctrl->poll_thread);
 	else
 		free_irq(ctrl->pcie->irq, ctrl);
 }
@@ -652,6 +626,29 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int pciehp_poll(void *data)
+{
+	struct controller *ctrl = data;
+
+	schedule_timeout_idle(10 * HZ); /* start with 10 sec delay */
+
+	while (!kthread_should_stop()) {
+		if (kthread_should_park())
+			kthread_parkme();
+
+		/* poll for interrupt events */
+		while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD)
+			pciehp_ist(IRQ_NOTCONNECTED, ctrl);
+
+		if (pciehp_poll_time <= 0 || pciehp_poll_time > 60)
+			pciehp_poll_time = 2; /* clamp to sane value */
+
+		schedule_timeout_idle(pciehp_poll_time * HZ);
+	}
+
+	return 0;
+}
+
 static void pcie_enable_notification(struct controller *ctrl)
 {
 	u16 cmd, mask;
@@ -742,7 +739,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
 	if (pciehp_poll_mode)
-		del_timer_sync(&ctrl->poll_timer);
+		kthread_park(ctrl->poll_thread);
 
 	pci_reset_bridge_secondary_bus(ctrl->pcie->port);
 
@@ -751,7 +748,7 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
 	if (pciehp_poll_mode)
-		int_poll_timeout(&ctrl->poll_timer);
+		kthread_unpark(ctrl->poll_thread);
 	return 0;
 }
 
-- 
cgit v1.2.3


From b0ccd9dd5dc8bf348112bb97e4f7eef6be5cf469 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:40 -0500
Subject: PCI: pciehp: Stop blinking on slot enable failure

If the attention button is pressed to power on the slot AND the user
powers on the slot via sysfs before 5 seconds have elapsed AND powering
on the slot fails because either the slot is unoccupied OR the latch is
open, we neglect turning off the green LED so it keeps on blinking.

That's because the error path of pciehp_sysfs_enable_slot() doesn't call
pciehp_green_led_off(), unlike pciehp_power_thread() which does.
The bug has been present since 2004 when the driver was introduced.

Fix by deduplicating common code in pciehp_sysfs_enable_slot() and
pciehp_power_thread() into a wrapper function pciehp_enable_slot() and
renaming the existing function to __pciehp_enable_slot().  Same for
pciehp_disable_slot().  This will also simplify the upcoming rework of
pciehp's event handling.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp_core.c |  7 +---
 drivers/pci/hotplug/pciehp_ctrl.c | 73 ++++++++++++++++++++++-----------------
 2 files changed, 42 insertions(+), 38 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 2ba59fc94827..8a2133856dfd 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -248,11 +248,8 @@ static int pciehp_probe(struct pcie_device *dev)
 	slot = ctrl->slot;
 	pciehp_get_adapter_status(slot, &occupied);
 	pciehp_get_power_status(slot, &poweron);
-	if (occupied && pciehp_force) {
-		mutex_lock(&slot->hotplug_lock);
+	if (occupied && pciehp_force)
 		pciehp_enable_slot(slot);
-		mutex_unlock(&slot->hotplug_lock);
-	}
 	/* If empty slot's power status is on, turn power off */
 	if (!occupied && poweron && POWER_CTRL(ctrl))
 		pciehp_power_off_slot(slot);
@@ -296,12 +293,10 @@ static int pciehp_resume(struct pcie_device *dev)
 
 	/* Check if slot is occupied */
 	pciehp_get_adapter_status(slot, &status);
-	mutex_lock(&slot->hotplug_lock);
 	if (status)
 		pciehp_enable_slot(slot);
 	else
 		pciehp_disable_slot(slot);
-	mutex_unlock(&slot->hotplug_lock);
 	return 0;
 }
 #endif /* PM */
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 76a9b8c26d2b..9d6343a35db1 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -160,26 +160,13 @@ static void pciehp_power_thread(struct work_struct *work)
 	struct power_work_info *info =
 		container_of(work, struct power_work_info, work);
 	struct slot *p_slot = info->p_slot;
-	int ret;
 
 	switch (info->req) {
 	case DISABLE_REQ:
-		mutex_lock(&p_slot->hotplug_lock);
 		pciehp_disable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		mutex_unlock(&p_slot->lock);
 		break;
 	case ENABLE_REQ:
-		mutex_lock(&p_slot->hotplug_lock);
-		ret = pciehp_enable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		if (ret)
-			pciehp_green_led_off(p_slot);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		mutex_unlock(&p_slot->lock);
+		pciehp_enable_slot(p_slot);
 		break;
 	default:
 		break;
@@ -369,7 +356,7 @@ static void interrupt_event_handler(struct work_struct *work)
 /*
  * Note: This function must be called with slot->hotplug_lock held
  */
-int pciehp_enable_slot(struct slot *p_slot)
+static int __pciehp_enable_slot(struct slot *p_slot)
 {
 	u8 getstatus = 0;
 	struct controller *ctrl = p_slot->ctrl;
@@ -400,10 +387,29 @@ int pciehp_enable_slot(struct slot *p_slot)
 	return board_added(p_slot);
 }
 
+int pciehp_enable_slot(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+	int ret;
+
+	mutex_lock(&slot->hotplug_lock);
+	ret = __pciehp_enable_slot(slot);
+	mutex_unlock(&slot->hotplug_lock);
+
+	if (ret && ATTN_BUTTN(ctrl))
+		pciehp_green_led_off(slot); /* may be blinking */
+
+	mutex_lock(&slot->lock);
+	slot->state = STATIC_STATE;
+	mutex_unlock(&slot->lock);
+
+	return ret;
+}
+
 /*
  * Note: This function must be called with slot->hotplug_lock held
  */
-int pciehp_disable_slot(struct slot *p_slot)
+static int __pciehp_disable_slot(struct slot *p_slot)
 {
 	u8 getstatus = 0;
 	struct controller *ctrl = p_slot->ctrl;
@@ -421,9 +427,23 @@ int pciehp_disable_slot(struct slot *p_slot)
 	return 0;
 }
 
+int pciehp_disable_slot(struct slot *slot)
+{
+	int ret;
+
+	mutex_lock(&slot->hotplug_lock);
+	ret = __pciehp_disable_slot(slot);
+	mutex_unlock(&slot->hotplug_lock);
+
+	mutex_lock(&slot->lock);
+	slot->state = STATIC_STATE;
+	mutex_unlock(&slot->lock);
+
+	return ret;
+}
+
 int pciehp_sysfs_enable_slot(struct slot *p_slot)
 {
-	int retval = -ENODEV;
 	struct controller *ctrl = p_slot->ctrl;
 
 	mutex_lock(&p_slot->lock);
@@ -433,12 +453,7 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 	case STATIC_STATE:
 		p_slot->state = POWERON_STATE;
 		mutex_unlock(&p_slot->lock);
-		mutex_lock(&p_slot->hotplug_lock);
-		retval = pciehp_enable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		break;
+		return pciehp_enable_slot(p_slot);
 	case POWERON_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering on state\n",
 			  slot_name(p_slot));
@@ -455,12 +470,11 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 	}
 	mutex_unlock(&p_slot->lock);
 
-	return retval;
+	return -ENODEV;
 }
 
 int pciehp_sysfs_disable_slot(struct slot *p_slot)
 {
-	int retval = -ENODEV;
 	struct controller *ctrl = p_slot->ctrl;
 
 	mutex_lock(&p_slot->lock);
@@ -470,12 +484,7 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 	case STATIC_STATE:
 		p_slot->state = POWEROFF_STATE;
 		mutex_unlock(&p_slot->lock);
-		mutex_lock(&p_slot->hotplug_lock);
-		retval = pciehp_disable_slot(p_slot);
-		mutex_unlock(&p_slot->hotplug_lock);
-		mutex_lock(&p_slot->lock);
-		p_slot->state = STATIC_STATE;
-		break;
+		return pciehp_disable_slot(p_slot);
 	case POWEROFF_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering off state\n",
 			  slot_name(p_slot));
@@ -492,5 +501,5 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 	}
 	mutex_unlock(&p_slot->lock);
 
-	return retval;
+	return -ENODEV;
 }
-- 
cgit v1.2.3


From 0e94916e6091f48391b65110e71c87c583021640 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:41 -0500
Subject: PCI: pciehp: Handle events synchronously

Up until now, pciehp's IRQ handler schedules a work item for each event,
which in turn schedules a work item to enable or disable the slot.  This
double indirection was necessary because sleeping wasn't allowed in the
IRQ handler.

However it is now that pciehp has been converted to threaded IRQ handling
and polling, so handle events synchronously in pciehp_ist() and remove
the work item infrastructure (with the exception of work items to handle
a button press after the 5 second delay).

For link or presence change events, move the register read to determine
the current link or presence state behind acquisition of the slot lock
to prevent it from becoming stale while the lock is contended.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp.h      |  20 +----
 drivers/pci/hotplug/pciehp_ctrl.c | 178 ++++++++++++--------------------------
 drivers/pci/hotplug/pciehp_hpc.c  |  27 ++----
 3 files changed, 67 insertions(+), 158 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 9f11360e3318..82ff77cc92f5 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -69,8 +69,7 @@ do {									\
  *	protects scheduling, execution and cancellation of @work
  * @hotplug_lock: serializes calls to pciehp_enable_slot() and
  *	pciehp_disable_slot()
- * @wq: work queue on which @work is scheduled;
- *	also used to queue interrupt events and slot enablement and disablement
+ * @wq: work queue on which @work is scheduled
  */
 struct slot {
 	u8 state;
@@ -82,12 +81,6 @@ struct slot {
 	struct workqueue_struct *wq;
 };
 
-struct event_info {
-	u32 event_type;
-	struct slot *p_slot;
-	struct work_struct work;
-};
-
 /**
  * struct controller - PCIe hotplug controller
  * @ctrl_lock: serializes writes to the Slot Control register
@@ -131,13 +124,6 @@ struct controller {
 	atomic_t pending_events;
 };
 
-#define INT_PRESENCE_ON			1
-#define INT_PRESENCE_OFF		2
-#define INT_POWER_FAULT			3
-#define INT_BUTTON_PRESS		4
-#define INT_LINK_UP			5
-#define INT_LINK_DOWN			6
-
 #define STATIC_STATE			0
 #define BLINKINGON_STATE		1
 #define BLINKINGOFF_STATE		2
@@ -156,7 +142,9 @@ struct controller {
 
 int pciehp_sysfs_enable_slot(struct slot *slot);
 int pciehp_sysfs_disable_slot(struct slot *slot);
-void pciehp_queue_interrupt_event(struct slot *slot, u32 event_type);
+void pciehp_handle_button_press(struct slot *slot);
+void pciehp_handle_link_change(struct slot *slot);
+void pciehp_handle_presence_change(struct slot *slot);
 int pciehp_configure_device(struct slot *p_slot);
 void pciehp_unconfigure_device(struct slot *p_slot);
 void pciehp_queue_pushbutton_work(struct work_struct *work);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 9d6343a35db1..5763e81be2ed 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -21,24 +21,6 @@
 #include "../pci.h"
 #include "pciehp.h"
 
-static void interrupt_event_handler(struct work_struct *work);
-
-void pciehp_queue_interrupt_event(struct slot *p_slot, u32 event_type)
-{
-	struct event_info *info;
-
-	info = kmalloc(sizeof(*info), GFP_ATOMIC);
-	if (!info) {
-		ctrl_err(p_slot->ctrl, "dropped event %d (ENOMEM)\n", event_type);
-		return;
-	}
-
-	INIT_WORK(&info->work, interrupt_event_handler);
-	info->event_type = event_type;
-	info->p_slot = p_slot;
-	queue_work(p_slot->wq, &info->work);
-}
-
 /* The following routines constitute the bulk of the
    hotplug controller logic
  */
@@ -140,59 +122,6 @@ static void remove_board(struct slot *p_slot)
 	pciehp_green_led_off(p_slot);
 }
 
-struct power_work_info {
-	struct slot *p_slot;
-	struct work_struct work;
-	unsigned int req;
-#define DISABLE_REQ 0
-#define ENABLE_REQ  1
-};
-
-/**
- * pciehp_power_thread - handle pushbutton events
- * @work: &struct work_struct describing work to be done
- *
- * Scheduled procedure to handle blocking stuff for the pushbuttons.
- * Handles all pending events and exits.
- */
-static void pciehp_power_thread(struct work_struct *work)
-{
-	struct power_work_info *info =
-		container_of(work, struct power_work_info, work);
-	struct slot *p_slot = info->p_slot;
-
-	switch (info->req) {
-	case DISABLE_REQ:
-		pciehp_disable_slot(p_slot);
-		break;
-	case ENABLE_REQ:
-		pciehp_enable_slot(p_slot);
-		break;
-	default:
-		break;
-	}
-
-	kfree(info);
-}
-
-static void pciehp_queue_power_work(struct slot *p_slot, int req)
-{
-	struct power_work_info *info;
-
-	p_slot->state = (req == ENABLE_REQ) ? POWERON_STATE : POWEROFF_STATE;
-
-	info = kmalloc(sizeof(*info), GFP_KERNEL);
-	if (!info) {
-		ctrl_err(p_slot->ctrl, "no memory to queue %s request\n",
-			 (req == ENABLE_REQ) ? "poweron" : "poweroff");
-		return;
-	}
-	info->p_slot = p_slot;
-	INIT_WORK(&info->work, pciehp_power_thread);
-	info->req = req;
-	queue_work(p_slot->wq, &info->work);
-}
-
 void pciehp_queue_pushbutton_work(struct work_struct *work)
 {
 	struct slot *p_slot = container_of(work, struct slot, work.work);
@@ -200,25 +129,27 @@ void pciehp_queue_pushbutton_work(struct work_struct *work)
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
-		pciehp_queue_power_work(p_slot, DISABLE_REQ);
-		break;
+		p_slot->state = POWEROFF_STATE;
+		mutex_unlock(&p_slot->lock);
+		pciehp_disable_slot(p_slot);
+		return;
 	case BLINKINGON_STATE:
-		pciehp_queue_power_work(p_slot, ENABLE_REQ);
-		break;
+		p_slot->state = POWERON_STATE;
+		mutex_unlock(&p_slot->lock);
+		pciehp_enable_slot(p_slot);
+		return;
 	default:
 		break;
 	}
 	mutex_unlock(&p_slot->lock);
 }
 
-/*
- * Note: This function must be called with slot->lock held
- */
-static void handle_button_press_event(struct slot *p_slot)
+void pciehp_handle_button_press(struct slot *p_slot)
 {
 	struct controller *ctrl = p_slot->ctrl;
 	u8 getstatus;
 
+	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case STATIC_STATE:
 		pciehp_get_power_status(p_slot, &getstatus);
@@ -269,14 +200,16 @@ static void handle_button_press_event(struct slot *p_slot)
 			 slot_name(p_slot), p_slot->state);
 		break;
 	}
+	mutex_unlock(&p_slot->lock);
 }
 
-/*
- * Note: This function must be called with slot->lock held
- */
-static void handle_link_event(struct slot *p_slot, u32 event)
+void pciehp_handle_link_change(struct slot *p_slot)
 {
 	struct controller *ctrl = p_slot->ctrl;
+	bool link_active;
+
+	mutex_lock(&p_slot->lock);
+	link_active = pciehp_check_link_active(ctrl);
 
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
@@ -284,24 +217,40 @@ static void handle_link_event(struct slot *p_slot, u32 event)
 		cancel_delayed_work(&p_slot->work);
 		/* Fall through */
 	case STATIC_STATE:
-		pciehp_queue_power_work(p_slot, event == INT_LINK_UP ?
-					ENABLE_REQ : DISABLE_REQ);
+		if (link_active) {
+			p_slot->state = POWERON_STATE;
+			mutex_unlock(&p_slot->lock);
+			ctrl_info(ctrl, "Slot(%s): Link Up\n", slot_name(p_slot));
+			pciehp_enable_slot(p_slot);
+		} else {
+			p_slot->state = POWEROFF_STATE;
+			mutex_unlock(&p_slot->lock);
+			ctrl_info(ctrl, "Slot(%s): Link Down\n", slot_name(p_slot));
+			pciehp_disable_slot(p_slot);
+		}
+		return;
 		break;
 	case POWERON_STATE:
-		if (event == INT_LINK_UP) {
+		if (link_active) {
 			ctrl_info(ctrl, "Slot(%s): Link Up event ignored; already powering on\n",
 				  slot_name(p_slot));
 		} else {
+			p_slot->state = POWEROFF_STATE;
+			mutex_unlock(&p_slot->lock);
 			ctrl_info(ctrl, "Slot(%s): Link Down event queued; currently getting powered on\n",
 				  slot_name(p_slot));
-			pciehp_queue_power_work(p_slot, DISABLE_REQ);
+			pciehp_disable_slot(p_slot);
+			return;
 		}
 		break;
 	case POWEROFF_STATE:
-		if (event == INT_LINK_UP) {
+		if (link_active) {
+			p_slot->state = POWERON_STATE;
+			mutex_unlock(&p_slot->lock);
 			ctrl_info(ctrl, "Slot(%s): Link Up event queued; currently getting powered off\n",
 				  slot_name(p_slot));
-			pciehp_queue_power_work(p_slot, ENABLE_REQ);
+			pciehp_enable_slot(p_slot);
+			return;
 		} else {
 			ctrl_info(ctrl, "Slot(%s): Link Down event ignored; already powering off\n",
 				  slot_name(p_slot));
@@ -312,45 +261,28 @@ static void handle_link_event(struct slot *p_slot, u32 event)
 			 slot_name(p_slot), p_slot->state);
 		break;
 	}
+	mutex_unlock(&p_slot->lock);
 }
 
-static void interrupt_event_handler(struct work_struct *work)
+void pciehp_handle_presence_change(struct slot *slot)
 {
-	struct event_info *info = container_of(work, struct event_info, work);
-	struct slot *p_slot = info->p_slot;
-	struct controller *ctrl = p_slot->ctrl;
+	struct controller *ctrl = slot->ctrl;
+	u8 present;
 
-	mutex_lock(&p_slot->lock);
-	switch (info->event_type) {
-	case INT_BUTTON_PRESS:
-		handle_button_press_event(p_slot);
-		break;
-	case INT_POWER_FAULT:
-		if (!POWER_CTRL(ctrl))
-			break;
-		pciehp_set_attention_status(p_slot, 1);
-		pciehp_green_led_off(p_slot);
-		break;
-	case INT_PRESENCE_ON:
-		pciehp_queue_power_work(p_slot, ENABLE_REQ);
-		break;
-	case INT_PRESENCE_OFF:
-		/*
-		 * Regardless of surprise capability, we need to
-		 * definitely remove a card that has been pulled out!
-		 */
-		pciehp_queue_power_work(p_slot, DISABLE_REQ);
-		break;
-	case INT_LINK_UP:
-	case INT_LINK_DOWN:
-		handle_link_event(p_slot, info->event_type);
-		break;
-	default:
-		break;
+	mutex_lock(&slot->lock);
+	pciehp_get_adapter_status(slot, &present);
+	ctrl_info(ctrl, "Slot(%s): Card %spresent\n", slot_name(slot),
+		  present ? "" : "not ");
+
+	if (present) {
+		slot->state = POWERON_STATE;
+		mutex_unlock(&slot->lock);
+		pciehp_enable_slot(slot);
+	} else {
+		slot->state = POWEROFF_STATE;
+		mutex_unlock(&slot->lock);
+		pciehp_disable_slot(slot);
 	}
-	mutex_unlock(&p_slot->lock);
-
-	kfree(info);
 }
 
 /*
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index d36650f2d2bb..31544998e1bd 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -581,8 +581,6 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	struct controller *ctrl = (struct controller *)dev_id;
 	struct slot *slot = ctrl->slot;
 	u32 events;
-	u8 present;
-	bool link;
 
 	synchronize_hardirq(irq);
 	events = atomic_xchg(&ctrl->pending_events, 0);
@@ -593,34 +591,25 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	if (events & PCI_EXP_SLTSTA_ABP) {
 		ctrl_info(ctrl, "Slot(%s): Attention button pressed\n",
 			  slot_name(slot));
-		pciehp_queue_interrupt_event(slot, INT_BUTTON_PRESS);
+		pciehp_handle_button_press(slot);
 	}
 
 	/*
 	 * Check Link Status Changed at higher precedence than Presence
 	 * Detect Changed.  The PDS value may be set to "card present" from
-	 * out-of-band detection, which may be in conflict with a Link Down
-	 * and cause the wrong event to queue.
+	 * out-of-band detection, which may be in conflict with a Link Down.
 	 */
-	if (events & PCI_EXP_SLTSTA_DLLSC) {
-		link = pciehp_check_link_active(ctrl);
-		ctrl_info(ctrl, "Slot(%s): Link %s\n", slot_name(slot),
-			  link ? "Up" : "Down");
-		pciehp_queue_interrupt_event(slot, link ? INT_LINK_UP :
-					     INT_LINK_DOWN);
-	} else if (events & PCI_EXP_SLTSTA_PDC) {
-		pciehp_get_adapter_status(slot, &present);
-		ctrl_info(ctrl, "Slot(%s): Card %spresent\n", slot_name(slot),
-			  present ? "" : "not ");
-		pciehp_queue_interrupt_event(slot, present ? INT_PRESENCE_ON :
-					     INT_PRESENCE_OFF);
-	}
+	if (events & PCI_EXP_SLTSTA_DLLSC)
+		pciehp_handle_link_change(slot);
+	else if (events & PCI_EXP_SLTSTA_PDC)
+		pciehp_handle_presence_change(slot);
 
 	/* Check Power Fault Detected */
 	if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
 		ctrl->power_fault_detected = 1;
 		ctrl_err(ctrl, "Slot(%s): Power fault\n", slot_name(slot));
-		pciehp_queue_interrupt_event(slot, INT_POWER_FAULT);
+		pciehp_set_attention_status(slot, 1);
+		pciehp_green_led_off(slot);
 	}
 
 	return IRQ_HANDLED;
-- 
cgit v1.2.3


From 55a6b7a6576d6cba77bb2ce2bfb2126df83df58a Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:42 -0500
Subject: PCI: pciehp: Drop slot workqueue

Previously the slot workqueue was used to handle events and enable or
disable the slot.  That's no longer the case as those tasks are done
synchronously in the IRQ thread.  The slot workqueue is thus merely used
to handle a button press after the 5 second delay and only one such work
item may be in flight at any given time.  A separate workqueue isn't
necessary for this simple task, so use the system workqueue instead.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp.h      | 2 --
 drivers/pci/hotplug/pciehp_core.c | 6 ------
 drivers/pci/hotplug/pciehp_ctrl.c | 2 +-
 drivers/pci/hotplug/pciehp_hpc.c  | 9 +--------
 4 files changed, 2 insertions(+), 17 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 82ff77cc92f5..0d005c5fabfa 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -69,7 +69,6 @@ do {									\
  *	protects scheduling, execution and cancellation of @work
  * @hotplug_lock: serializes calls to pciehp_enable_slot() and
  *	pciehp_disable_slot()
- * @wq: work queue on which @work is scheduled
  */
 struct slot {
 	u8 state;
@@ -78,7 +77,6 @@ struct slot {
 	struct delayed_work work;
 	struct mutex lock;
 	struct mutex hotplug_lock;
-	struct workqueue_struct *wq;
 };
 
 /**
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 8a2133856dfd..b360645377c2 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -62,12 +62,6 @@ static int reset_slot(struct hotplug_slot *slot, int probe);
  */
 static void release_slot(struct hotplug_slot *hotplug_slot)
 {
-	struct slot *slot = hotplug_slot->private;
-
-	/* queued work needs hotplug_slot name */
-	cancel_delayed_work(&slot->work);
-	drain_workqueue(slot->wq);
-
 	kfree(hotplug_slot->ops);
 	kfree(hotplug_slot->info);
 	kfree(hotplug_slot);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 5763e81be2ed..a4a8a5457aca 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -165,7 +165,7 @@ void pciehp_handle_button_press(struct slot *p_slot)
 		/* blink green LED and turn off amber */
 		pciehp_green_led_blink(p_slot);
 		pciehp_set_attention_status(p_slot, 0);
-		queue_delayed_work(p_slot->wq, &p_slot->work, 5*HZ);
+		schedule_delayed_work(&p_slot->work, 5 * HZ);
 		break;
 	case BLINKINGOFF_STATE:
 	case BLINKINGON_STATE:
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 31544998e1bd..dcbdee50cd85 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -767,26 +767,19 @@ static int pcie_init_slot(struct controller *ctrl)
 	if (!slot)
 		return -ENOMEM;
 
-	slot->wq = alloc_ordered_workqueue("pciehp-%u", 0, PSN(ctrl));
-	if (!slot->wq)
-		goto abort;
-
 	slot->ctrl = ctrl;
 	mutex_init(&slot->lock);
 	mutex_init(&slot->hotplug_lock);
 	INIT_DELAYED_WORK(&slot->work, pciehp_queue_pushbutton_work);
 	ctrl->slot = slot;
 	return 0;
-abort:
-	kfree(slot);
-	return -ENOMEM;
 }
 
 static void pcie_cleanup_slot(struct controller *ctrl)
 {
 	struct slot *slot = ctrl->slot;
 
-	destroy_workqueue(slot->wq);
+	cancel_delayed_work_sync(&slot->work);
 	kfree(slot);
 }
 
-- 
cgit v1.2.3


From 51bbf9bee34ff5d4006d266f24a54dc9c1669eb5 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:43 -0500
Subject: PCI: hotplug: Demidlayer registration with the core

When a hotplug driver calls pci_hp_register(), all steps necessary for
registration are carried out in one go, including creation of a kobject
and addition to sysfs.  That's a problem for pciehp once it's converted
to enable/disable the slot exclusively from the IRQ thread:  The thread
needs to be spawned after creation of the kobject (because it uses the
kobject's name), but before addition to sysfs (because it will handle
enable/disable requests submitted via sysfs).

pci_hp_deregister() does offer a ->release callback that's invoked
after deletion from sysfs and before destruction of the kobject.  But
because pci_hp_register() doesn't offer a counterpart, hotplug drivers'
->probe and ->remove code becomes asymmetric, which is error prone
as recently discovered use-after-free bugs in pciehp's ->remove hook
have shown.

In a sense, this appears to be a case of the midlayer antipattern:

   "The core thesis of the "midlayer mistake" is that midlayers are
    bad and should not exist.  That common functionality which it is
    so tempting to put in a midlayer should instead be provided as
    library routines which can [be] used, augmented, or ignored by
    each bottom level driver independently.  Thus every subsystem
    that supports multiple implementations (or drivers) should
    provide a very thin top layer which calls directly into the
    bottom layer drivers, and a rich library of support code that
    eases the implementation of those drivers.  This library is
    available to, but not forced upon, those drivers."
        --  Neil Brown (2009), https://lwn.net/Articles/336262/

The presence of midlayer traits in the PCI hotplug core might be ascribed
to its age:  When it was introduced in February 2002, the blessings of a
library approach might not have been well known:
https://git.kernel.org/tglx/history/c/a8a2069f432c

For comparison, the driver core does offer split functions for creating
a kobject (device_initialize()) and addition to sysfs (device_add()) as
an alternative to carrying out everything at once (device_register()).
This was introduced in October 2002:
https://git.kernel.org/tglx/history/c/8b290eb19962

The odd ->release callback in the PCI hotplug core was added in 2003:
https://git.kernel.org/tglx/history/c/69f8d663b595

Clearly, a library approach would not force every hotplug driver to
implement a ->release callback, but rather allow the driver to remove
the sysfs files, release its data structures and finally destroy the
kobject.  Alternatively, a driver may choose to remove everything with
pci_hp_deregister(), then release its data structures.

To this end, offer drivers pci_hp_initialize() and pci_hp_add() as a
split-up version of pci_hp_register().  Likewise, offer pci_hp_del()
and pci_hp_destroy() as a split-up version of pci_hp_deregister().

Eliminate the ->release callback and move its code into each driver's
teardown routine.

Declare pci_hp_deregister() void, in keeping with the usual kernel
pattern that enablement can fail, but disablement cannot.  It only
returned an error if the caller passed in a NULL pointer or a slot which
has never or is no longer registered or is sharing its name with another
slot.  Those would be bugs, so WARN about them.  Few hotplug drivers
actually checked the return value and those that did only printed a
useless error message to dmesg.  Remove that.

For most drivers the conversion was straightforward since it doesn't
matter whether the code in the ->release callback is executed before or
after destruction of the kobject.  But in the case of ibmphp, it was
unclear to me whether setting slot_cur->ctrl and slot_cur->bus_on to
NULL needs to happen before the kobject is destroyed, so I erred on
the side of caution and ensured that the order stays the same.  Another
nontrivial case is pnv_php, I've found the list and kref logic difficult
to understand, however my impression was that it is safe to delete the
list element and drop the references until after the kobject is
destroyed.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>  # drivers/platform/x86
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Len Brown <lenb@kernel.org>
Cc: Scott Murray <scott@spiteful.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Gavin Shan <gwshan@linux.vnet.ibm.com>
Cc: Sebastian Ott <sebott@linux.vnet.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Cc: Corentin Chary <corentin.chary@gmail.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Andy Shevchenko <andy@infradead.org>
---
 drivers/pci/hotplug/acpiphp_core.c      |  22 +----
 drivers/pci/hotplug/cpci_hotplug_core.c |  14 +---
 drivers/pci/hotplug/cpqphp_core.c       |  16 +---
 drivers/pci/hotplug/ibmphp_core.c       |  15 +++-
 drivers/pci/hotplug/ibmphp_ebda.c       |  20 -----
 drivers/pci/hotplug/pci_hotplug_core.c  | 139 +++++++++++++++++++++++---------
 drivers/pci/hotplug/pciehp_core.c       |  19 ++---
 drivers/pci/hotplug/pnv_php.c           |   5 +-
 drivers/pci/hotplug/rpaphp_core.c       |   2 +-
 drivers/pci/hotplug/rpaphp_slot.c       |  13 +--
 drivers/pci/hotplug/s390_pci_hpc.c      |  13 +--
 drivers/pci/hotplug/sgi_hotplug.c       |   9 ++-
 drivers/pci/hotplug/shpchp_core.c       |  20 +----
 drivers/platform/x86/asus-wmi.c         |  12 +--
 drivers/platform/x86/eeepc-laptop.c     |  12 +--
 include/linux/pci_hotplug.h             |  15 +++-
 16 files changed, 168 insertions(+), 178 deletions(-)

diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c
index 12b5655fd390..ad32ffbc4b91 100644
--- a/drivers/pci/hotplug/acpiphp_core.c
+++ b/drivers/pci/hotplug/acpiphp_core.c
@@ -254,20 +254,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
-/**
- * release_slot - free up the memory used by a slot
- * @hotplug_slot: slot to free
- */
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	pr_debug("%s - physical_slot = %s\n", __func__, slot_name(slot));
-
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 /* callback routine to initialize 'struct slot' for each slot */
 int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot,
 				  unsigned int sun)
@@ -287,7 +273,6 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot,
 	slot->hotplug_slot->info = &slot->info;
 
 	slot->hotplug_slot->private = slot;
-	slot->hotplug_slot->release = &release_slot;
 	slot->hotplug_slot->ops = &acpi_hotplug_slot_ops;
 
 	slot->acpi_slot = acpiphp_slot;
@@ -324,13 +309,12 @@ error:
 void acpiphp_unregister_hotplug_slot(struct acpiphp_slot *acpiphp_slot)
 {
 	struct slot *slot = acpiphp_slot->slot;
-	int retval = 0;
 
 	pr_info("Slot [%s] unregistered\n", slot_name(slot));
 
-	retval = pci_hp_deregister(slot->hotplug_slot);
-	if (retval)
-		pr_err("pci_hp_deregister failed with error %d\n", retval);
+	pci_hp_deregister(slot->hotplug_slot);
+	kfree(slot->hotplug_slot);
+	kfree(slot);
 }
 
 
diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c
index 07b533adc9df..52a339baf06c 100644
--- a/drivers/pci/hotplug/cpci_hotplug_core.c
+++ b/drivers/pci/hotplug/cpci_hotplug_core.c
@@ -195,10 +195,8 @@ get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
+static void release_slot(struct slot *slot)
 {
-	struct slot *slot = hotplug_slot->private;
-
 	kfree(slot->hotplug_slot->info);
 	kfree(slot->hotplug_slot);
 	pci_dev_put(slot->dev);
@@ -253,7 +251,6 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last)
 		snprintf(name, SLOT_NAME_SIZE, "%02x:%02x", bus->number, i);
 
 		hotplug_slot->private = slot;
-		hotplug_slot->release = &release_slot;
 		hotplug_slot->ops = &cpci_hotplug_slot_ops;
 
 		/*
@@ -308,12 +305,8 @@ cpci_hp_unregister_bus(struct pci_bus *bus)
 			slots--;
 
 			dbg("deregistering slot %s", slot_name(slot));
-			status = pci_hp_deregister(slot->hotplug_slot);
-			if (status) {
-				err("pci_hp_deregister failed with error %d",
-				    status);
-				break;
-			}
+			pci_hp_deregister(slot->hotplug_slot);
+			release_slot(slot);
 		}
 	}
 	up_write(&list_rwsem);
@@ -623,6 +616,7 @@ cleanup_slots(void)
 	list_for_each_entry_safe(slot, tmp, &slot_list, slot_list) {
 		list_del(&slot->slot_list);
 		pci_hp_deregister(slot->hotplug_slot);
+		release_slot(slot);
 	}
 cleanup_null:
 	up_write(&list_rwsem);
diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c
index 1797e36ec586..5a06636e910a 100644
--- a/drivers/pci/hotplug/cpqphp_core.c
+++ b/drivers/pci/hotplug/cpqphp_core.c
@@ -266,17 +266,6 @@ static void __iomem *get_SMBIOS_entry(void __iomem *smbios_start,
 	return previous;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	dbg("%s - physical_slot = %s\n", __func__, slot_name(slot));
-
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 static int ctrl_slot_cleanup(struct controller *ctrl)
 {
 	struct slot *old_slot, *next_slot;
@@ -285,9 +274,11 @@ static int ctrl_slot_cleanup(struct controller *ctrl)
 	ctrl->slot = NULL;
 
 	while (old_slot) {
-		/* memory will be freed by the release_slot callback */
 		next_slot = old_slot->next;
 		pci_hp_deregister(old_slot->hotplug_slot);
+		kfree(old_slot->hotplug_slot->info);
+		kfree(old_slot->hotplug_slot);
+		kfree(old_slot);
 		old_slot = next_slot;
 	}
 
@@ -678,7 +669,6 @@ static int ctrl_slot_setup(struct controller *ctrl,
 			((read_slot_enable(ctrl) << 2) >> ctrl_slot) & 0x04;
 
 		/* register this slot with the hotplug pci core */
-		hotplug_slot->release = &release_slot;
 		hotplug_slot->private = slot;
 		snprintf(name, SLOT_NAME_SIZE, "%u", slot->number);
 		hotplug_slot->ops = &cpqphp_hotplug_slot_ops;
diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c
index 1869b0411ce0..4ea57e9019f1 100644
--- a/drivers/pci/hotplug/ibmphp_core.c
+++ b/drivers/pci/hotplug/ibmphp_core.c
@@ -673,7 +673,20 @@ static void free_slots(void)
 
 	list_for_each_entry_safe(slot_cur, next, &ibmphp_slot_head,
 				 ibm_slot_list) {
-		pci_hp_deregister(slot_cur->hotplug_slot);
+		pci_hp_del(slot_cur->hotplug_slot);
+		slot_cur->ctrl = NULL;
+		slot_cur->bus_on = NULL;
+
+		/*
+		 * We don't want to actually remove the resources,
+		 * since ibmphp_free_resources() will do just that.
+		 */
+		ibmphp_unconfigure_card(&slot_cur, -1);
+
+		pci_hp_destroy(slot_cur->hotplug_slot);
+		kfree(slot_cur->hotplug_slot->info);
+		kfree(slot_cur->hotplug_slot);
+		kfree(slot_cur);
 	}
 	debug("%s -- exit\n", __func__);
 }
diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c
index 64549aa24c0f..6f8e90e3ec08 100644
--- a/drivers/pci/hotplug/ibmphp_ebda.c
+++ b/drivers/pci/hotplug/ibmphp_ebda.c
@@ -699,25 +699,6 @@ static int fillslotinfo(struct hotplug_slot *hotplug_slot)
 	return rc;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot;
-
-	if (!hotplug_slot || !hotplug_slot->private)
-		return;
-
-	slot = hotplug_slot->private;
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	slot->ctrl = NULL;
-	slot->bus_on = NULL;
-
-	/* we don't want to actually remove the resources, since free_resources will do just that */
-	ibmphp_unconfigure_card(&slot, -1);
-
-	kfree(slot);
-}
-
 static struct pci_driver ibmphp_driver;
 
 /*
@@ -941,7 +922,6 @@ static int __init ebda_rsrc_controller(void)
 			tmp_slot->hotplug_slot = hp_slot_ptr;
 
 			hp_slot_ptr->private = tmp_slot;
-			hp_slot_ptr->release = release_slot;
 
 			rc = fillslotinfo(hp_slot_ptr);
 			if (rc)
diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c
index fd93783a87b0..90fde5f106d8 100644
--- a/drivers/pci/hotplug/pci_hotplug_core.c
+++ b/drivers/pci/hotplug/pci_hotplug_core.c
@@ -396,8 +396,9 @@ static struct hotplug_slot *get_slot_from_name(const char *name)
  * @owner: caller module owner
  * @mod_name: caller module name
  *
- * Registers a hotplug slot with the pci hotplug subsystem, which will allow
- * userspace interaction to the slot.
+ * Prepares a hotplug slot for in-kernel use and immediately publishes it to
+ * user space in one go.  Drivers may alternatively carry out the two steps
+ * separately by invoking pci_hp_initialize() and pci_hp_add().
  *
  * Returns 0 if successful, anything else for an error.
  */
@@ -406,54 +407,91 @@ int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *bus,
 		      struct module *owner, const char *mod_name)
 {
 	int result;
+
+	result = __pci_hp_initialize(slot, bus, devnr, name, owner, mod_name);
+	if (result)
+		return result;
+
+	result = pci_hp_add(slot);
+	if (result)
+		pci_hp_destroy(slot);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(__pci_hp_register);
+
+/**
+ * __pci_hp_initialize - prepare hotplug slot for in-kernel use
+ * @slot: pointer to the &struct hotplug_slot to initialize
+ * @bus: bus this slot is on
+ * @devnr: slot number
+ * @name: name registered with kobject core
+ * @owner: caller module owner
+ * @mod_name: caller module name
+ *
+ * Allocate and fill in a PCI slot for use by a hotplug driver.  Once this has
+ * been called, the driver may invoke hotplug_slot_name() to get the slot's
+ * unique name.  The driver must be prepared to handle a ->reset_slot callback
+ * from this point on.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus,
+			int devnr, const char *name, struct module *owner,
+			const char *mod_name)
+{
 	struct pci_slot *pci_slot;
 
 	if (slot == NULL)
 		return -ENODEV;
 	if ((slot->info == NULL) || (slot->ops == NULL))
 		return -EINVAL;
-	if (slot->release == NULL) {
-		dbg("Why are you trying to register a hotplug slot without a proper release function?\n");
-		return -EINVAL;
-	}
 
 	slot->ops->owner = owner;
 	slot->ops->mod_name = mod_name;
 
-	mutex_lock(&pci_hp_mutex);
 	/*
 	 * No problems if we call this interface from both ACPI_PCI_SLOT
 	 * driver and call it here again. If we've already created the
 	 * pci_slot, the interface will simply bump the refcount.
 	 */
 	pci_slot = pci_create_slot(bus, devnr, name, slot);
-	if (IS_ERR(pci_slot)) {
-		result = PTR_ERR(pci_slot);
-		goto out;
-	}
+	if (IS_ERR(pci_slot))
+		return PTR_ERR(pci_slot);
 
 	slot->pci_slot = pci_slot;
 	pci_slot->hotplug = slot;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__pci_hp_initialize);
 
-	list_add(&slot->slot_list, &pci_hotplug_slot_list);
+/**
+ * pci_hp_add - publish hotplug slot to user space
+ * @slot: pointer to the &struct hotplug_slot to publish
+ *
+ * Make a hotplug slot's sysfs interface available and inform user space of its
+ * addition by sending a uevent.  The hotplug driver must be prepared to handle
+ * all &struct hotplug_slot_ops callbacks from this point on.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+int pci_hp_add(struct hotplug_slot *slot)
+{
+	struct pci_slot *pci_slot = slot->pci_slot;
+	int result;
 
 	result = fs_add_slot(pci_slot);
 	if (result)
-		goto err_list_del;
+		return result;
 
 	kobject_uevent(&pci_slot->kobj, KOBJ_ADD);
-	dbg("Added slot %s to the list\n", name);
-	goto out;
-
-err_list_del:
-	list_del(&slot->slot_list);
-	pci_slot->hotplug = NULL;
-	pci_destroy_slot(pci_slot);
-out:
+	mutex_lock(&pci_hp_mutex);
+	list_add(&slot->slot_list, &pci_hotplug_slot_list);
 	mutex_unlock(&pci_hp_mutex);
-	return result;
+	dbg("Added slot %s to the list\n", hotplug_slot_name(slot));
+	return 0;
 }
-EXPORT_SYMBOL_GPL(__pci_hp_register);
+EXPORT_SYMBOL_GPL(pci_hp_add);
 
 /**
  * pci_hp_deregister - deregister a hotplug_slot with the PCI hotplug subsystem
@@ -464,35 +502,62 @@ EXPORT_SYMBOL_GPL(__pci_hp_register);
  *
  * Returns 0 if successful, anything else for an error.
  */
-int pci_hp_deregister(struct hotplug_slot *slot)
+void pci_hp_deregister(struct hotplug_slot *slot)
+{
+	pci_hp_del(slot);
+	pci_hp_destroy(slot);
+}
+EXPORT_SYMBOL_GPL(pci_hp_deregister);
+
+/**
+ * pci_hp_del - unpublish hotplug slot from user space
+ * @slot: pointer to the &struct hotplug_slot to unpublish
+ *
+ * Remove a hotplug slot's sysfs interface.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+void pci_hp_del(struct hotplug_slot *slot)
 {
 	struct hotplug_slot *temp;
-	struct pci_slot *pci_slot;
 
-	if (!slot)
-		return -ENODEV;
+	if (WARN_ON(!slot))
+		return;
 
 	mutex_lock(&pci_hp_mutex);
 	temp = get_slot_from_name(hotplug_slot_name(slot));
-	if (temp != slot) {
+	if (WARN_ON(temp != slot)) {
 		mutex_unlock(&pci_hp_mutex);
-		return -ENODEV;
+		return;
 	}
 
 	list_del(&slot->slot_list);
-
-	pci_slot = slot->pci_slot;
-	fs_remove_slot(pci_slot);
+	mutex_unlock(&pci_hp_mutex);
 	dbg("Removed slot %s from the list\n", hotplug_slot_name(slot));
+	fs_remove_slot(slot->pci_slot);
+}
+EXPORT_SYMBOL_GPL(pci_hp_del);
+
+/**
+ * pci_hp_destroy - remove hotplug slot from in-kernel use
+ * @slot: pointer to the &struct hotplug_slot to destroy
+ *
+ * Destroy a PCI slot used by a hotplug driver.  Once this has been called,
+ * the driver may no longer invoke hotplug_slot_name() to get the slot's
+ * unique name.  The driver no longer needs to handle a ->reset_slot callback
+ * from this point on.
+ *
+ * Returns 0 on success or a negative int on error.
+ */
+void pci_hp_destroy(struct hotplug_slot *slot)
+{
+	struct pci_slot *pci_slot = slot->pci_slot;
 
-	slot->release(slot);
+	slot->pci_slot = NULL;
 	pci_slot->hotplug = NULL;
 	pci_destroy_slot(pci_slot);
-	mutex_unlock(&pci_hp_mutex);
-
-	return 0;
 }
-EXPORT_SYMBOL_GPL(pci_hp_deregister);
+EXPORT_SYMBOL_GPL(pci_hp_destroy);
 
 /**
  * pci_hp_change_slot_info - changes the slot's information structure in the core
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index b360645377c2..37d8f81e548f 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -56,17 +56,6 @@ static int get_latch_status(struct hotplug_slot *slot, u8 *value);
 static int get_adapter_status(struct hotplug_slot *slot, u8 *value);
 static int reset_slot(struct hotplug_slot *slot, int probe);
 
-/**
- * release_slot - free up the memory used by a slot
- * @hotplug_slot: slot to free
- */
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	kfree(hotplug_slot->ops);
-	kfree(hotplug_slot->info);
-	kfree(hotplug_slot);
-}
-
 static int init_slot(struct controller *ctrl)
 {
 	struct slot *slot = ctrl->slot;
@@ -107,7 +96,6 @@ static int init_slot(struct controller *ctrl)
 	/* register this slot with the hotplug pci core */
 	hotplug->info = info;
 	hotplug->private = slot;
-	hotplug->release = &release_slot;
 	hotplug->ops = ops;
 	slot->hotplug_slot = hotplug;
 	snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl));
@@ -127,7 +115,12 @@ out:
 
 static void cleanup_slot(struct controller *ctrl)
 {
-	pci_hp_deregister(ctrl->slot->hotplug_slot);
+	struct hotplug_slot *hotplug_slot = ctrl->slot->hotplug_slot;
+
+	pci_hp_deregister(hotplug_slot);
+	kfree(hotplug_slot->ops);
+	kfree(hotplug_slot->info);
+	kfree(hotplug_slot);
 }
 
 /*
diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
index 6c2e8d7307c6..3276a5e4c430 100644
--- a/drivers/pci/hotplug/pnv_php.c
+++ b/drivers/pci/hotplug/pnv_php.c
@@ -538,9 +538,8 @@ static struct hotplug_slot_ops php_slot_ops = {
 	.disable_slot		= pnv_php_disable_slot,
 };
 
-static void pnv_php_release(struct hotplug_slot *slot)
+static void pnv_php_release(struct pnv_php_slot *php_slot)
 {
-	struct pnv_php_slot *php_slot = slot->private;
 	unsigned long flags;
 
 	/* Remove from global or child list */
@@ -596,7 +595,6 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn)
 	php_slot->power_state_check     = false;
 	php_slot->slot.ops              = &php_slot_ops;
 	php_slot->slot.info             = &php_slot->slot_info;
-	php_slot->slot.release          = pnv_php_release;
 	php_slot->slot.private          = php_slot;
 
 	INIT_LIST_HEAD(&php_slot->children);
@@ -924,6 +922,7 @@ static void pnv_php_unregister_one(struct device_node *dn)
 
 	php_slot->state = PNV_PHP_STATE_OFFLINE;
 	pci_hp_deregister(&php_slot->slot);
+	pnv_php_release(php_slot);
 	pnv_php_put_slot(php_slot);
 }
 
diff --git a/drivers/pci/hotplug/rpaphp_core.c b/drivers/pci/hotplug/rpaphp_core.c
index fb5e0845429d..857c358b727b 100644
--- a/drivers/pci/hotplug/rpaphp_core.c
+++ b/drivers/pci/hotplug/rpaphp_core.c
@@ -404,13 +404,13 @@ static void __exit cleanup_slots(void)
 	/*
 	 * Unregister all of our slots with the pci_hotplug subsystem,
 	 * and free up all memory that we had allocated.
-	 * memory will be freed in release_slot callback.
 	 */
 
 	list_for_each_entry_safe(slot, next, &rpaphp_slot_head,
 				 rpaphp_slot_list) {
 		list_del(&slot->rpaphp_slot_list);
 		pci_hp_deregister(slot->hotplug_slot);
+		dealloc_slot_struct(slot);
 	}
 	return;
 }
diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c
index 3840a2075e6a..b916c8e4372d 100644
--- a/drivers/pci/hotplug/rpaphp_slot.c
+++ b/drivers/pci/hotplug/rpaphp_slot.c
@@ -19,12 +19,6 @@
 #include "rpaphp.h"
 
 /* free up the memory used by a slot */
-static void rpaphp_release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = (struct slot *) hotplug_slot->private;
-	dealloc_slot_struct(slot);
-}
-
 void dealloc_slot_struct(struct slot *slot)
 {
 	kfree(slot->hotplug_slot->info);
@@ -56,7 +50,6 @@ struct slot *alloc_slot_struct(struct device_node *dn,
 	slot->power_domain = power_domain;
 	slot->hotplug_slot->private = slot;
 	slot->hotplug_slot->ops = &rpaphp_hotplug_slot_ops;
-	slot->hotplug_slot->release = &rpaphp_release_slot;
 
 	return (slot);
 
@@ -90,10 +83,8 @@ int rpaphp_deregister_slot(struct slot *slot)
 		__func__, slot->name);
 
 	list_del(&slot->rpaphp_slot_list);
-
-	retval = pci_hp_deregister(php_slot);
-	if (retval)
-		err("Problem unregistering a slot %s\n", slot->name);
+	pci_hp_deregister(php_slot);
+	dealloc_slot_struct(slot);
 
 	dbg("%s - Exit: rc[%d]\n", __func__, retval);
 	return retval;
diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c
index ffdc2977395d..93b5341d282c 100644
--- a/drivers/pci/hotplug/s390_pci_hpc.c
+++ b/drivers/pci/hotplug/s390_pci_hpc.c
@@ -130,15 +130,6 @@ static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 	return 0;
 }
 
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 static struct hotplug_slot_ops s390_hotplug_slot_ops = {
 	.enable_slot =		enable_slot,
 	.disable_slot =		disable_slot,
@@ -175,7 +166,6 @@ int zpci_init_slot(struct zpci_dev *zdev)
 	hotplug_slot->info = info;
 
 	hotplug_slot->ops = &s390_hotplug_slot_ops;
-	hotplug_slot->release = &release_slot;
 
 	get_power_status(hotplug_slot, &info->power_status);
 	get_adapter_status(hotplug_slot, &info->adapter_status);
@@ -209,5 +199,8 @@ void zpci_exit_slot(struct zpci_dev *zdev)
 			continue;
 		list_del(&slot->slot_list);
 		pci_hp_deregister(slot->hotplug_slot);
+		kfree(slot->hotplug_slot->info);
+		kfree(slot->hotplug_slot);
+		kfree(slot);
 	}
 }
diff --git a/drivers/pci/hotplug/sgi_hotplug.c b/drivers/pci/hotplug/sgi_hotplug.c
index 78b6bdbb3a39..babd23409f61 100644
--- a/drivers/pci/hotplug/sgi_hotplug.c
+++ b/drivers/pci/hotplug/sgi_hotplug.c
@@ -628,7 +628,6 @@ static int sn_hotplug_slot_register(struct pci_bus *pci_bus)
 			goto alloc_err;
 		}
 		bss_hotplug_slot->ops = &sn_hotplug_slot_ops;
-		bss_hotplug_slot->release = &sn_release_slot;
 
 		rc = pci_hp_register(bss_hotplug_slot, pci_bus, device, name);
 		if (rc)
@@ -656,8 +655,10 @@ alloc_err:
 		sn_release_slot(bss_hotplug_slot);
 
 	/* destroy anything else on the list */
-	while ((bss_hotplug_slot = sn_hp_destroy()))
+	while ((bss_hotplug_slot = sn_hp_destroy())) {
 		pci_hp_deregister(bss_hotplug_slot);
+		sn_release_slot(bss_hotplug_slot);
+	}
 
 	return rc;
 }
@@ -703,8 +704,10 @@ static void __exit sn_pci_hotplug_exit(void)
 {
 	struct hotplug_slot *bss_hotplug_slot;
 
-	while ((bss_hotplug_slot = sn_hp_destroy()))
+	while ((bss_hotplug_slot = sn_hp_destroy())) {
 		pci_hp_deregister(bss_hotplug_slot);
+		sn_release_slot(bss_hotplug_slot);
+	}
 
 	if (!list_empty(&sn_hp_list))
 		printk(KERN_ERR "%s: internal list is not empty\n", __FILE__);
diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c
index 8e3c6ce12f31..97cee23f3d51 100644
--- a/drivers/pci/hotplug/shpchp_core.c
+++ b/drivers/pci/hotplug/shpchp_core.c
@@ -61,22 +61,6 @@ static struct hotplug_slot_ops shpchp_hotplug_slot_ops = {
 	.get_adapter_status =	get_adapter_status,
 };
 
-/**
- * release_slot - free up the memory used by a slot
- * @hotplug_slot: slot to free
- */
-static void release_slot(struct hotplug_slot *hotplug_slot)
-{
-	struct slot *slot = hotplug_slot->private;
-
-	ctrl_dbg(slot->ctrl, "%s: physical_slot = %s\n",
-		 __func__, slot_name(slot));
-
-	kfree(slot->hotplug_slot->info);
-	kfree(slot->hotplug_slot);
-	kfree(slot);
-}
-
 static int init_slots(struct controller *ctrl)
 {
 	struct slot *slot;
@@ -125,7 +109,6 @@ static int init_slots(struct controller *ctrl)
 
 		/* register this slot with the hotplug pci core */
 		hotplug_slot->private = slot;
-		hotplug_slot->release = &release_slot;
 		snprintf(name, SLOT_NAME_SIZE, "%d", slot->number);
 		hotplug_slot->ops = &shpchp_hotplug_slot_ops;
 
@@ -171,6 +154,9 @@ void cleanup_slots(struct controller *ctrl)
 		cancel_delayed_work(&slot->work);
 		destroy_workqueue(slot->wq);
 		pci_hp_deregister(slot->hotplug_slot);
+		kfree(slot->hotplug_slot->info);
+		kfree(slot->hotplug_slot);
+		kfree(slot);
 	}
 }
 
diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 3d523ca64694..d67f32a29bb4 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -858,12 +858,6 @@ static int asus_get_adapter_status(struct hotplug_slot *hotplug_slot,
 	return 0;
 }
 
-static void asus_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot)
-{
-	kfree(hotplug_slot->info);
-	kfree(hotplug_slot);
-}
-
 static struct hotplug_slot_ops asus_hotplug_slot_ops = {
 	.owner = THIS_MODULE,
 	.get_adapter_status = asus_get_adapter_status,
@@ -905,7 +899,6 @@ static int asus_setup_pci_hotplug(struct asus_wmi *asus)
 		goto error_info;
 
 	asus->hotplug_slot->private = asus;
-	asus->hotplug_slot->release = &asus_cleanup_pci_hotplug;
 	asus->hotplug_slot->ops = &asus_hotplug_slot_ops;
 	asus_get_adapter_status(asus->hotplug_slot,
 				&asus->hotplug_slot->info->adapter_status);
@@ -1051,8 +1044,11 @@ static void asus_wmi_rfkill_exit(struct asus_wmi *asus)
 	 * asus_unregister_rfkill_notifier()
 	 */
 	asus_rfkill_hotplug(asus);
-	if (asus->hotplug_slot)
+	if (asus->hotplug_slot) {
 		pci_hp_deregister(asus->hotplug_slot);
+		kfree(asus->hotplug_slot->info);
+		kfree(asus->hotplug_slot);
+	}
 	if (asus->hotplug_workqueue)
 		destroy_workqueue(asus->hotplug_workqueue);
 
diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c
index 4c38904a8a32..a4bbf6ecd1f0 100644
--- a/drivers/platform/x86/eeepc-laptop.c
+++ b/drivers/platform/x86/eeepc-laptop.c
@@ -726,12 +726,6 @@ static int eeepc_get_adapter_status(struct hotplug_slot *hotplug_slot,
 	return 0;
 }
 
-static void eeepc_cleanup_pci_hotplug(struct hotplug_slot *hotplug_slot)
-{
-	kfree(hotplug_slot->info);
-	kfree(hotplug_slot);
-}
-
 static struct hotplug_slot_ops eeepc_hotplug_slot_ops = {
 	.owner = THIS_MODULE,
 	.get_adapter_status = eeepc_get_adapter_status,
@@ -758,7 +752,6 @@ static int eeepc_setup_pci_hotplug(struct eeepc_laptop *eeepc)
 		goto error_info;
 
 	eeepc->hotplug_slot->private = eeepc;
-	eeepc->hotplug_slot->release = &eeepc_cleanup_pci_hotplug;
 	eeepc->hotplug_slot->ops = &eeepc_hotplug_slot_ops;
 	eeepc_get_adapter_status(eeepc->hotplug_slot,
 				 &eeepc->hotplug_slot->info->adapter_status);
@@ -837,8 +830,11 @@ static void eeepc_rfkill_exit(struct eeepc_laptop *eeepc)
 		eeepc->wlan_rfkill = NULL;
 	}
 
-	if (eeepc->hotplug_slot)
+	if (eeepc->hotplug_slot) {
 		pci_hp_deregister(eeepc->hotplug_slot);
+		kfree(eeepc->hotplug_slot->info);
+		kfree(eeepc->hotplug_slot);
+	}
 
 	if (eeepc->bluetooth_rfkill) {
 		rfkill_unregister(eeepc->bluetooth_rfkill);
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index cf5e22103f68..a6d6650a0490 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -80,15 +80,12 @@ struct hotplug_slot_info {
  * @ops: pointer to the &struct hotplug_slot_ops to be used for this slot
  * @info: pointer to the &struct hotplug_slot_info for the initial values for
  * this slot.
- * @release: called during pci_hp_deregister to free memory allocated in a
- * hotplug_slot structure.
  * @private: used by the hotplug pci controller driver to store whatever it
  * needs.
  */
 struct hotplug_slot {
 	struct hotplug_slot_ops		*ops;
 	struct hotplug_slot_info	*info;
-	void (*release) (struct hotplug_slot *slot);
 	void				*private;
 
 	/* Variables below this are for use only by the hotplug pci core. */
@@ -104,13 +101,23 @@ static inline const char *hotplug_slot_name(const struct hotplug_slot *slot)
 int __pci_hp_register(struct hotplug_slot *slot, struct pci_bus *pbus, int nr,
 		      const char *name, struct module *owner,
 		      const char *mod_name);
-int pci_hp_deregister(struct hotplug_slot *slot);
+int __pci_hp_initialize(struct hotplug_slot *slot, struct pci_bus *bus, int nr,
+			const char *name, struct module *owner,
+			const char *mod_name);
+int pci_hp_add(struct hotplug_slot *slot);
+
+void pci_hp_del(struct hotplug_slot *slot);
+void pci_hp_destroy(struct hotplug_slot *slot);
+void pci_hp_deregister(struct hotplug_slot *slot);
+
 int __must_check pci_hp_change_slot_info(struct hotplug_slot *slot,
 					 struct hotplug_slot_info *info);
 
 /* use a define to avoid include chaining to get THIS_MODULE & friends */
 #define pci_hp_register(slot, pbus, devnr, name) \
 	__pci_hp_register(slot, pbus, devnr, name, THIS_MODULE, KBUILD_MODNAME)
+#define pci_hp_initialize(slot, bus, nr, name) \
+	__pci_hp_initialize(slot, bus, nr, name, THIS_MODULE, KBUILD_MODNAME)
 
 /* PCI Setting Record (Type 0) */
 struct hpp_type0 {
-- 
cgit v1.2.3


From 774d446b0f9222f46772dde8770d7c1c169c0284 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:43 -0500
Subject: PCI: pciehp: Publish to user space last on probe

The PCI hotplug core has just been refactored to separate slot
initialization for in-kernel use from publication to user space.

Take advantage of it in pciehp by publishing to user space last on
probe.  This will allow enable/disablement of the slot exclusively from
the IRQ thread because the IRQ is requested after initialization for
in-kernel use (thereby getting its unique name needed by the IRQ thread)
but before user space is able to submit enable/disable requests.

On teardown, the order is the same in reverse:  The user space interface
is removed prior to freeing the IRQ and destroying the slot.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp_core.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 37d8f81e548f..cde32e137f6c 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -100,10 +100,10 @@ static int init_slot(struct controller *ctrl)
 	slot->hotplug_slot = hotplug;
 	snprintf(name, SLOT_NAME_SIZE, "%u", PSN(ctrl));
 
-	retval = pci_hp_register(hotplug,
-				 ctrl->pcie->port->subordinate, 0, name);
+	retval = pci_hp_initialize(hotplug,
+				   ctrl->pcie->port->subordinate, 0, name);
 	if (retval)
-		ctrl_err(ctrl, "pci_hp_register failed: error %d\n", retval);
+		ctrl_err(ctrl, "pci_hp_initialize failed: error %d\n", retval);
 out:
 	if (retval) {
 		kfree(ops);
@@ -117,7 +117,7 @@ static void cleanup_slot(struct controller *ctrl)
 {
 	struct hotplug_slot *hotplug_slot = ctrl->slot->hotplug_slot;
 
-	pci_hp_deregister(hotplug_slot);
+	pci_hp_destroy(hotplug_slot);
 	kfree(hotplug_slot->ops);
 	kfree(hotplug_slot->info);
 	kfree(hotplug_slot);
@@ -231,8 +231,15 @@ static int pciehp_probe(struct pcie_device *dev)
 		goto err_out_free_ctrl_slot;
 	}
 
-	/* Check if slot is occupied */
+	/* Publish to user space */
 	slot = ctrl->slot;
+	rc = pci_hp_add(slot->hotplug_slot);
+	if (rc) {
+		ctrl_err(ctrl, "Publication to user space failed (%d)\n", rc);
+		goto err_out_shutdown_notification;
+	}
+
+	/* Check if slot is occupied */
 	pciehp_get_adapter_status(slot, &occupied);
 	pciehp_get_power_status(slot, &poweron);
 	if (occupied && pciehp_force)
@@ -243,6 +250,8 @@ static int pciehp_probe(struct pcie_device *dev)
 
 	return 0;
 
+err_out_shutdown_notification:
+	pcie_shutdown_notification(ctrl);
 err_out_free_ctrl_slot:
 	cleanup_slot(ctrl);
 err_out_release_ctlr:
@@ -254,6 +263,7 @@ static void pciehp_remove(struct pcie_device *dev)
 {
 	struct controller *ctrl = get_service_data(dev);
 
+	pci_hp_del(ctrl->slot->hotplug_slot);
 	pcie_shutdown_notification(ctrl);
 	cleanup_slot(ctrl);
 	pciehp_release_ctrl(ctrl);
-- 
cgit v1.2.3


From 9590192f2584c2cfc2fee88be22fe6e8921ed115 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:45 -0500
Subject: PCI: pciehp: Track enable/disable status

handle_button_press_event() currently determines whether the slot has
been turned on or off by looking at the Power Controller Control bit in
the Slot Control register.  This assumes that an attention button
implies presence of a power controller even though that's not mandated
by the spec.  Moreover the Power Controller Control bit is unreliable
when a power fault occurs (PCIe r4.0, sec 6.7.1.8).  This issue has
existed since the driver was introduced in 2004.

Fix by replacing STATIC_STATE with ON_STATE and OFF_STATE and tracking
whether the slot has been turned on or off.  This is also a required
ingredient to make pciehp resilient to missed events, which is the
object of an upcoming commit.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp.h      | 15 ++++++++++++++-
 drivers/pci/hotplug/pciehp_ctrl.c | 28 ++++++++++++++++------------
 drivers/pci/hotplug/pciehp_hpc.c  |  5 +++++
 3 files changed, 35 insertions(+), 13 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 0d005c5fabfa..1ba335d6563a 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -122,11 +122,24 @@ struct controller {
 	atomic_t pending_events;
 };
 
-#define STATIC_STATE			0
+/**
+ * DOC: Slot state
+ *
+ * @OFF_STATE: slot is powered off, no subordinate devices are enumerated
+ * @BLINKINGON_STATE: slot will be powered on after the 5 second delay,
+ *	green led is blinking
+ * @BLINKINGOFF_STATE: slot will be powered off after the 5 second delay,
+ *	green led is blinking
+ * @POWERON_STATE: slot is currently powering on
+ * @POWEROFF_STATE: slot is currently powering off
+ * @ON_STATE: slot is powered on, subordinate devices have been enumerated
+ */
+#define OFF_STATE			0
 #define BLINKINGON_STATE		1
 #define BLINKINGOFF_STATE		2
 #define POWERON_STATE			3
 #define POWEROFF_STATE			4
+#define ON_STATE			5
 
 #define ATTN_BUTTN(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_ABP)
 #define POWER_CTRL(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_PCP)
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index a4a8a5457aca..627e846df802 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -147,13 +147,12 @@ void pciehp_queue_pushbutton_work(struct work_struct *work)
 void pciehp_handle_button_press(struct slot *p_slot)
 {
 	struct controller *ctrl = p_slot->ctrl;
-	u8 getstatus;
 
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
-	case STATIC_STATE:
-		pciehp_get_power_status(p_slot, &getstatus);
-		if (getstatus) {
+	case OFF_STATE:
+	case ON_STATE:
+		if (p_slot->state == ON_STATE) {
 			p_slot->state = BLINKINGOFF_STATE;
 			ctrl_info(ctrl, "Slot(%s): Powering off due to button press\n",
 				  slot_name(p_slot));
@@ -176,14 +175,16 @@ void pciehp_handle_button_press(struct slot *p_slot)
 		 */
 		ctrl_info(ctrl, "Slot(%s): Button cancel\n", slot_name(p_slot));
 		cancel_delayed_work(&p_slot->work);
-		if (p_slot->state == BLINKINGOFF_STATE)
+		if (p_slot->state == BLINKINGOFF_STATE) {
+			p_slot->state = ON_STATE;
 			pciehp_green_led_on(p_slot);
-		else
+		} else {
+			p_slot->state = OFF_STATE;
 			pciehp_green_led_off(p_slot);
+		}
 		pciehp_set_attention_status(p_slot, 0);
 		ctrl_info(ctrl, "Slot(%s): Action canceled due to button press\n",
 			  slot_name(p_slot));
-		p_slot->state = STATIC_STATE;
 		break;
 	case POWEROFF_STATE:
 	case POWERON_STATE:
@@ -216,7 +217,8 @@ void pciehp_handle_link_change(struct slot *p_slot)
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&p_slot->work);
 		/* Fall through */
-	case STATIC_STATE:
+	case ON_STATE:
+	case OFF_STATE:
 		if (link_active) {
 			p_slot->state = POWERON_STATE;
 			mutex_unlock(&p_slot->lock);
@@ -332,7 +334,7 @@ int pciehp_enable_slot(struct slot *slot)
 		pciehp_green_led_off(slot); /* may be blinking */
 
 	mutex_lock(&slot->lock);
-	slot->state = STATIC_STATE;
+	slot->state = ret ? OFF_STATE : ON_STATE;
 	mutex_unlock(&slot->lock);
 
 	return ret;
@@ -368,7 +370,7 @@ int pciehp_disable_slot(struct slot *slot)
 	mutex_unlock(&slot->hotplug_lock);
 
 	mutex_lock(&slot->lock);
-	slot->state = STATIC_STATE;
+	slot->state = OFF_STATE;
 	mutex_unlock(&slot->lock);
 
 	return ret;
@@ -382,7 +384,7 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
 		cancel_delayed_work(&p_slot->work);
-	case STATIC_STATE:
+	case OFF_STATE:
 		p_slot->state = POWERON_STATE;
 		mutex_unlock(&p_slot->lock);
 		return pciehp_enable_slot(p_slot);
@@ -391,6 +393,7 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 			  slot_name(p_slot));
 		break;
 	case BLINKINGOFF_STATE:
+	case ON_STATE:
 	case POWEROFF_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already enabled\n",
 			  slot_name(p_slot));
@@ -413,7 +416,7 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&p_slot->work);
-	case STATIC_STATE:
+	case ON_STATE:
 		p_slot->state = POWEROFF_STATE;
 		mutex_unlock(&p_slot->lock);
 		return pciehp_disable_slot(p_slot);
@@ -422,6 +425,7 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 			  slot_name(p_slot));
 		break;
 	case BLINKINGON_STATE:
+	case OFF_STATE:
 	case POWERON_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already disabled\n",
 			  slot_name(p_slot));
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index dcbdee50cd85..9c6a18da1af5 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -761,12 +761,17 @@ void pcie_shutdown_notification(struct controller *ctrl)
 
 static int pcie_init_slot(struct controller *ctrl)
 {
+	struct pci_bus *subordinate = ctrl_dev(ctrl)->subordinate;
 	struct slot *slot;
 
 	slot = kzalloc(sizeof(*slot), GFP_KERNEL);
 	if (!slot)
 		return -ENOMEM;
 
+	down_read(&pci_bus_sem);
+	slot->state = list_empty(&subordinate->devices) ? OFF_STATE : ON_STATE;
+	up_read(&pci_bus_sem);
+
 	slot->ctrl = ctrl;
 	mutex_init(&slot->lock);
 	mutex_init(&slot->hotplug_lock);
-- 
cgit v1.2.3


From 32a8cef274feacd00b748a4f13b84d60aa6d82ff Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:46 -0500
Subject: PCI: pciehp: Enable/disable exclusively from IRQ thread

Besides the IRQ thread, there are several other places in the driver
which enable or disable the slot:

- pciehp_probe() enables the slot if it's occupied and the pciehp_force
  module parameter is used.

- pciehp_resume() enables or disables the slot after system sleep.

- pciehp_queue_pushbutton_work() enables or disables the slot after the
  5 second delay following an Attention Button press.

- pciehp_sysfs_enable_slot() and pciehp_sysfs_disable_slot() enable or
  disable the slot on sysfs write.

This requires locking and complicates pciehp's state machine.

A simplification can be achieved by enabling and disabling the slot
exclusively from the IRQ thread.

Amend the functions listed above to request slot enable/disablement from
the IRQ thread by either synthesizing a Presence Detect Changed event or,
in the case of a disable user request (via sysfs or an Attention Button
press), submitting a newly introduced force disable request.  The latter
is needed because the slot shall be forced off despite being occupied.
For this force disable request, avoid colliding with Slot Status register
bits by using a bit number greater than 16.

For synchronous execution of requests (on sysfs write), wait for the
request to finish and retrieve the result.  There can only ever be one
sysfs write in flight due to the locking in kernfs_fop_write(), hence
there is no risk of returning the result of a different sysfs request to
user space.

The POWERON_STATE and POWEROFF_STATE is now no longer entered by the
above-listed functions, but solely by the IRQ thread when it begins a
power transition.  Afterwards, it moves to STATIC_STATE.  The same
applies to canceling the Attention Button work, it likewise becomes an
IRQ thread only operation.

An immediate consequence is that the POWERON_STATE and POWEROFF_STATE is
never observed by the IRQ thread itself, only by functions called in a
different context, such as pciehp_sysfs_enable_slot().  So remove
handling of these states from pciehp_handle_button_press() and
pciehp_handle_link_change() which are exclusively called from the IRQ
thread.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp.h      | 18 +++++++
 drivers/pci/hotplug/pciehp_core.c | 22 ++++++---
 drivers/pci/hotplug/pciehp_ctrl.c | 99 +++++++++++++++++++--------------------
 drivers/pci/hotplug/pciehp_hpc.c  | 14 ++++--
 4 files changed, 93 insertions(+), 60 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 1ba335d6563a..ed42dde5f9ac 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -105,6 +105,9 @@ struct slot {
  *	that has not yet been cleared by the user
  * @pending_events: used by the IRQ handler to save events retrieved from the
  *	Slot Status register for later consumption by the IRQ thread
+ * @request_result: result of last user request submitted to the IRQ thread
+ * @requester: wait queue to wake up on completion of user request,
+ *	used for synchronous slot enable/disable request via sysfs
  */
 struct controller {
 	struct mutex ctrl_lock;
@@ -120,6 +123,8 @@ struct controller {
 	unsigned int notification_enabled:1;
 	unsigned int power_fault_detected;
 	atomic_t pending_events;
+	int request_result;
+	wait_queue_head_t requester;
 };
 
 /**
@@ -141,6 +146,17 @@ struct controller {
 #define POWEROFF_STATE			4
 #define ON_STATE			5
 
+/**
+ * DOC: Flags to request an action from the IRQ thread
+ *
+ * These are stored together with events read from the Slot Status register,
+ * hence must be greater than its 16-bit width.
+ *
+ * %DISABLE_SLOT: Disable the slot in response to a user request via sysfs or
+ *	an Attention Button press after the 5 second delay
+ */
+#define DISABLE_SLOT		(1 << 16)
+
 #define ATTN_BUTTN(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_ABP)
 #define POWER_CTRL(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_PCP)
 #define MRL_SENS(ctrl)		((ctrl)->slot_cap & PCI_EXP_SLTCAP_MRLSP)
@@ -153,7 +169,9 @@ struct controller {
 
 int pciehp_sysfs_enable_slot(struct slot *slot);
 int pciehp_sysfs_disable_slot(struct slot *slot);
+void pciehp_request(struct controller *ctrl, int action);
 void pciehp_handle_button_press(struct slot *slot);
+void pciehp_handle_disable_request(struct slot *slot);
 void pciehp_handle_link_change(struct slot *slot);
 void pciehp_handle_presence_change(struct slot *slot);
 int pciehp_configure_device(struct slot *p_slot);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index cde32e137f6c..b11f0db0695f 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -240,13 +240,19 @@ static int pciehp_probe(struct pcie_device *dev)
 	}
 
 	/* Check if slot is occupied */
+	mutex_lock(&slot->lock);
 	pciehp_get_adapter_status(slot, &occupied);
 	pciehp_get_power_status(slot, &poweron);
-	if (occupied && pciehp_force)
-		pciehp_enable_slot(slot);
+	if (pciehp_force &&
+	    ((occupied && (slot->state == OFF_STATE ||
+			   slot->state == BLINKINGON_STATE)) ||
+	     (!occupied && (slot->state == ON_STATE ||
+			    slot->state == BLINKINGOFF_STATE))))
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
 	/* If empty slot's power status is on, turn power off */
 	if (!occupied && poweron && POWER_CTRL(ctrl))
 		pciehp_power_off_slot(slot);
+	mutex_unlock(&slot->lock);
 
 	return 0;
 
@@ -290,10 +296,14 @@ static int pciehp_resume(struct pcie_device *dev)
 
 	/* Check if slot is occupied */
 	pciehp_get_adapter_status(slot, &status);
-	if (status)
-		pciehp_enable_slot(slot);
-	else
-		pciehp_disable_slot(slot);
+	mutex_lock(&slot->lock);
+	if ((status && (slot->state == OFF_STATE ||
+			slot->state == BLINKINGON_STATE)) ||
+	    (!status && (slot->state == ON_STATE ||
+			 slot->state == BLINKINGOFF_STATE)))
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
+	mutex_unlock(&slot->lock);
+
 	return 0;
 }
 #endif /* PM */
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 627e846df802..70bad847a450 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -122,22 +122,26 @@ static void remove_board(struct slot *p_slot)
 	pciehp_green_led_off(p_slot);
 }
 
+void pciehp_request(struct controller *ctrl, int action)
+{
+	atomic_or(action, &ctrl->pending_events);
+	if (!pciehp_poll_mode)
+		irq_wake_thread(ctrl->pcie->irq, ctrl);
+}
+
 void pciehp_queue_pushbutton_work(struct work_struct *work)
 {
 	struct slot *p_slot = container_of(work, struct slot, work.work);
+	struct controller *ctrl = p_slot->ctrl;
 
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
-		p_slot->state = POWEROFF_STATE;
-		mutex_unlock(&p_slot->lock);
-		pciehp_disable_slot(p_slot);
-		return;
+		pciehp_request(ctrl, DISABLE_SLOT);
+		break;
 	case BLINKINGON_STATE:
-		p_slot->state = POWERON_STATE;
-		mutex_unlock(&p_slot->lock);
-		pciehp_enable_slot(p_slot);
-		return;
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
+		break;
 	default:
 		break;
 	}
@@ -186,16 +190,6 @@ void pciehp_handle_button_press(struct slot *p_slot)
 		ctrl_info(ctrl, "Slot(%s): Action canceled due to button press\n",
 			  slot_name(p_slot));
 		break;
-	case POWEROFF_STATE:
-	case POWERON_STATE:
-		/*
-		 * Ignore if the slot is on power-on or power-off state;
-		 * this means that the previous attention button action
-		 * to hot-add or hot-remove is undergoing
-		 */
-		ctrl_info(ctrl, "Slot(%s): Button ignored\n",
-			  slot_name(p_slot));
-		break;
 	default:
 		ctrl_err(ctrl, "Slot(%s): Ignoring invalid state %#x\n",
 			 slot_name(p_slot), p_slot->state);
@@ -204,6 +198,22 @@ void pciehp_handle_button_press(struct slot *p_slot)
 	mutex_unlock(&p_slot->lock);
 }
 
+void pciehp_handle_disable_request(struct slot *slot)
+{
+	struct controller *ctrl = slot->ctrl;
+
+	mutex_lock(&slot->lock);
+	switch (slot->state) {
+	case BLINKINGON_STATE:
+	case BLINKINGOFF_STATE:
+		cancel_delayed_work(&slot->work);
+	}
+	slot->state = POWEROFF_STATE;
+	mutex_unlock(&slot->lock);
+
+	ctrl->request_result = pciehp_disable_slot(slot);
+}
+
 void pciehp_handle_link_change(struct slot *p_slot)
 {
 	struct controller *ctrl = p_slot->ctrl;
@@ -232,32 +242,6 @@ void pciehp_handle_link_change(struct slot *p_slot)
 		}
 		return;
 		break;
-	case POWERON_STATE:
-		if (link_active) {
-			ctrl_info(ctrl, "Slot(%s): Link Up event ignored; already powering on\n",
-				  slot_name(p_slot));
-		} else {
-			p_slot->state = POWEROFF_STATE;
-			mutex_unlock(&p_slot->lock);
-			ctrl_info(ctrl, "Slot(%s): Link Down event queued; currently getting powered on\n",
-				  slot_name(p_slot));
-			pciehp_disable_slot(p_slot);
-			return;
-		}
-		break;
-	case POWEROFF_STATE:
-		if (link_active) {
-			p_slot->state = POWERON_STATE;
-			mutex_unlock(&p_slot->lock);
-			ctrl_info(ctrl, "Slot(%s): Link Up event queued; currently getting powered off\n",
-				  slot_name(p_slot));
-			pciehp_enable_slot(p_slot);
-			return;
-		} else {
-			ctrl_info(ctrl, "Slot(%s): Link Down event ignored; already powering off\n",
-				  slot_name(p_slot));
-		}
-		break;
 	default:
 		ctrl_err(ctrl, "Slot(%s): Ignoring invalid state %#x\n",
 			 slot_name(p_slot), p_slot->state);
@@ -272,6 +256,12 @@ void pciehp_handle_presence_change(struct slot *slot)
 	u8 present;
 
 	mutex_lock(&slot->lock);
+	switch (slot->state) {
+	case BLINKINGON_STATE:
+	case BLINKINGOFF_STATE:
+		cancel_delayed_work(&slot->work);
+	}
+
 	pciehp_get_adapter_status(slot, &present);
 	ctrl_info(ctrl, "Slot(%s): Card %spresent\n", slot_name(slot),
 		  present ? "" : "not ");
@@ -279,7 +269,7 @@ void pciehp_handle_presence_change(struct slot *slot)
 	if (present) {
 		slot->state = POWERON_STATE;
 		mutex_unlock(&slot->lock);
-		pciehp_enable_slot(slot);
+		ctrl->request_result = pciehp_enable_slot(slot);
 	} else {
 		slot->state = POWEROFF_STATE;
 		mutex_unlock(&slot->lock);
@@ -383,11 +373,17 @@ int pciehp_sysfs_enable_slot(struct slot *p_slot)
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case BLINKINGON_STATE:
-		cancel_delayed_work(&p_slot->work);
 	case OFF_STATE:
-		p_slot->state = POWERON_STATE;
 		mutex_unlock(&p_slot->lock);
-		return pciehp_enable_slot(p_slot);
+		/*
+		 * The IRQ thread becomes a no-op if the user pulls out the
+		 * card before the thread wakes up, so initialize to -ENODEV.
+		 */
+		ctrl->request_result = -ENODEV;
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
+		wait_event(ctrl->requester,
+			   !atomic_read(&ctrl->pending_events));
+		return ctrl->request_result;
 	case POWERON_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering on state\n",
 			  slot_name(p_slot));
@@ -415,11 +411,12 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot)
 	mutex_lock(&p_slot->lock);
 	switch (p_slot->state) {
 	case BLINKINGOFF_STATE:
-		cancel_delayed_work(&p_slot->work);
 	case ON_STATE:
-		p_slot->state = POWEROFF_STATE;
 		mutex_unlock(&p_slot->lock);
-		return pciehp_disable_slot(p_slot);
+		pciehp_request(ctrl, DISABLE_SLOT);
+		wait_event(ctrl->requester,
+			   !atomic_read(&ctrl->pending_events));
+		return ctrl->request_result;
 	case POWEROFF_STATE:
 		ctrl_info(ctrl, "Slot(%s): Already in powering off state\n",
 			  slot_name(p_slot));
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 9c6a18da1af5..6951a0123e39 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -595,11 +595,16 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	}
 
 	/*
+	 * Disable requests have higher priority than Presence Detect Changed
+	 * or Data Link Layer State Changed events.
+	 *
 	 * Check Link Status Changed at higher precedence than Presence
 	 * Detect Changed.  The PDS value may be set to "card present" from
 	 * out-of-band detection, which may be in conflict with a Link Down.
 	 */
-	if (events & PCI_EXP_SLTSTA_DLLSC)
+	if (events & DISABLE_SLOT)
+		pciehp_handle_disable_request(slot);
+	else if (events & PCI_EXP_SLTSTA_DLLSC)
 		pciehp_handle_link_change(slot);
 	else if (events & PCI_EXP_SLTSTA_PDC)
 		pciehp_handle_presence_change(slot);
@@ -612,6 +617,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 		pciehp_green_led_off(slot);
 	}
 
+	wake_up(&ctrl->requester);
 	return IRQ_HANDLED;
 }
 
@@ -625,8 +631,9 @@ static int pciehp_poll(void *data)
 		if (kthread_should_park())
 			kthread_parkme();
 
-		/* poll for interrupt events */
-		while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD)
+		/* poll for interrupt events or user requests */
+		while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD ||
+		       atomic_read(&ctrl->pending_events))
 			pciehp_ist(IRQ_NOTCONNECTED, ctrl);
 
 		if (pciehp_poll_time <= 0 || pciehp_poll_time > 60)
@@ -830,6 +837,7 @@ struct controller *pcie_init(struct pcie_device *dev)
 
 	ctrl->slot_cap = slot_cap;
 	mutex_init(&ctrl->ctrl_lock);
+	init_waitqueue_head(&ctrl->requester);
 	init_waitqueue_head(&ctrl->queue);
 	dbg_ctrl(ctrl);
 
-- 
cgit v1.2.3


From 1656716d45d0aae8c0a21a0553b9d27cd98fda61 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:46 -0500
Subject: PCI: pciehp: Drop enable/disable lock

Previously slot enablement and disablement could happen concurrently.
But now it's under the exclusive control of the IRQ thread, rendering
the locking obsolete.  Drop it.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp.h      |  3 ---
 drivers/pci/hotplug/pciehp_ctrl.c | 11 -----------
 drivers/pci/hotplug/pciehp_hpc.c  |  1 -
 3 files changed, 15 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index ed42dde5f9ac..5417180c3aff 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -67,8 +67,6 @@ do {									\
  *	an Attention Button press
  * @lock: protects reads and writes of @state;
  *	protects scheduling, execution and cancellation of @work
- * @hotplug_lock: serializes calls to pciehp_enable_slot() and
- *	pciehp_disable_slot()
  */
 struct slot {
 	u8 state;
@@ -76,7 +74,6 @@ struct slot {
 	struct hotplug_slot *hotplug_slot;
 	struct delayed_work work;
 	struct mutex lock;
-	struct mutex hotplug_lock;
 };
 
 /**
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 70bad847a450..8ba937599fb3 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -277,9 +277,6 @@ void pciehp_handle_presence_change(struct slot *slot)
 	}
 }
 
-/*
- * Note: This function must be called with slot->hotplug_lock held
- */
 static int __pciehp_enable_slot(struct slot *p_slot)
 {
 	u8 getstatus = 0;
@@ -316,10 +313,7 @@ int pciehp_enable_slot(struct slot *slot)
 	struct controller *ctrl = slot->ctrl;
 	int ret;
 
-	mutex_lock(&slot->hotplug_lock);
 	ret = __pciehp_enable_slot(slot);
-	mutex_unlock(&slot->hotplug_lock);
-
 	if (ret && ATTN_BUTTN(ctrl))
 		pciehp_green_led_off(slot); /* may be blinking */
 
@@ -330,9 +324,6 @@ int pciehp_enable_slot(struct slot *slot)
 	return ret;
 }
 
-/*
- * Note: This function must be called with slot->hotplug_lock held
- */
 static int __pciehp_disable_slot(struct slot *p_slot)
 {
 	u8 getstatus = 0;
@@ -355,9 +346,7 @@ int pciehp_disable_slot(struct slot *slot)
 {
 	int ret;
 
-	mutex_lock(&slot->hotplug_lock);
 	ret = __pciehp_disable_slot(slot);
-	mutex_unlock(&slot->hotplug_lock);
 
 	mutex_lock(&slot->lock);
 	slot->state = OFF_STATE;
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 6951a0123e39..7f1a29cd6a17 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -781,7 +781,6 @@ static int pcie_init_slot(struct controller *ctrl)
 
 	slot->ctrl = ctrl;
 	mutex_init(&slot->lock);
-	mutex_init(&slot->hotplug_lock);
 	INIT_DELAYED_WORK(&slot->work, pciehp_queue_pushbutton_work);
 	ctrl->slot = slot;
 	return 0;
-- 
cgit v1.2.3


From 25c83b84b110f50efe6fcf62e329f1db2af4454a Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:47 -0500
Subject: PCI: pciehp: Declare pciehp_enable/disable_slot() static

No callers of pciehp_enable/disable_slot() outside of pciehp_ctrl.c
remain, so declare the functions static.  For now this requires forward
declarations.  Those can be eliminated by reshuffling functions once the
ongoing effort to refactor the driver has settled.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp.h      | 2 --
 drivers/pci/hotplug/pciehp_ctrl.c | 7 +++++--
 2 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 5417180c3aff..9c75acd291fb 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -177,8 +177,6 @@ void pciehp_queue_pushbutton_work(struct work_struct *work);
 struct controller *pcie_init(struct pcie_device *dev);
 int pcie_init_notification(struct controller *ctrl);
 void pcie_shutdown_notification(struct controller *ctrl);
-int pciehp_enable_slot(struct slot *p_slot);
-int pciehp_disable_slot(struct slot *p_slot);
 void pcie_reenable_notification(struct controller *ctrl);
 int pciehp_power_on_slot(struct slot *slot);
 void pciehp_power_off_slot(struct slot *slot);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 8ba937599fb3..4a12e70aacd0 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -122,6 +122,9 @@ static void remove_board(struct slot *p_slot)
 	pciehp_green_led_off(p_slot);
 }
 
+static int pciehp_enable_slot(struct slot *slot);
+static int pciehp_disable_slot(struct slot *slot);
+
 void pciehp_request(struct controller *ctrl, int action)
 {
 	atomic_or(action, &ctrl->pending_events);
@@ -308,7 +311,7 @@ static int __pciehp_enable_slot(struct slot *p_slot)
 	return board_added(p_slot);
 }
 
-int pciehp_enable_slot(struct slot *slot)
+static int pciehp_enable_slot(struct slot *slot)
 {
 	struct controller *ctrl = slot->ctrl;
 	int ret;
@@ -342,7 +345,7 @@ static int __pciehp_disable_slot(struct slot *p_slot)
 	return 0;
 }
 
-int pciehp_disable_slot(struct slot *slot)
+static int pciehp_disable_slot(struct slot *slot)
 {
 	int ret;
 
-- 
cgit v1.2.3


From 6c35a1ac3da63a7fe5b18b435a5a9d6b9fd3990a Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:49 -0500
Subject: PCI: pciehp: Tolerate initially unstable link

When a device is hotplugged, Presence Detect and Link Up events often do
not occur simultaneously, but with a lag of a few milliseconds.  Only
the first event received is relevant, the other one can be disregarded.

Moreover, Stefan Roese reports that on certain platforms, Link State and
Presence Detect may flap for up to 100 ms before stabilizing, suggesting
that such events should be disregarded for at least this long:
https://lkml.kernel.org/r/20180130084121.18653-1-sr@denx.de

On slot enablement, pciehp_check_link_status() waits for 100 ms per
PCIe r4.0, sec 6.7.3.3, then probes the hotplugged device's vendor
register for up to 1 second.

If this succeeds, the link is definitely up, so ignore any Presence
Detect or Link State events that occurred up to this point.

pciehp_check_link_status() then checks the Link Training bit in the
Link Status register.  This is the final opportunity to detect
inaccessibility of the device and abort slot enablement.  Any link
or presence change that occurs afterwards will cause the slot to be
disabled again immediately after attempting to enable it.

The astute reviewer may appreciate that achieving this behavior would be
more complicated had pciehp not just been converted to enable/disable
the slot exclusively from the IRQ thread:  When the slot is enabled via
sysfs, each link or presence flap would otherwise cause the IRQ thread
to run and it would have to sense that those events are belonging to a
concurrent slot enablement operation and disregard them.  It would be
much more difficult than this mere 3 line change.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Stefan Roese <sr@denx.de>
---
 drivers/pci/hotplug/pciehp_hpc.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 7f1a29cd6a17..6b8350a3875c 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -270,6 +270,11 @@ int pciehp_check_link_status(struct controller *ctrl)
 	found = pci_bus_check_dev(ctrl->pcie->port->subordinate,
 					PCI_DEVFN(0, 0));
 
+	/* ignore link or presence changes up to this point */
+	if (found)
+		atomic_and(~(PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC),
+			   &ctrl->pending_events);
+
 	pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status);
 	ctrl_dbg(ctrl, "%s: lnk_status = %x\n", __func__, lnk_status);
 	if ((lnk_status & PCI_EXP_LNKSTA_LT) ||
-- 
cgit v1.2.3


From d331710ea78fea8b10624c87546d8bc0cd0389c9 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:49 -0500
Subject: PCI: pciehp: Become resilient to missed events

A hotplug port's Slot Status register does not count how often each type
of event occurred, it only records the fact *that* an event has occurred.

Previously pciehp queued a work item for each event.  But if it missed
an event, e.g. removal of a card in-between two back-to-back insertions,
it queued up the wrong work item or no work item at all.  Commit
fad214b0aa72 ("PCI: pciehp: Process all hotplug events before looking
for new ones") sought to improve the situation by shrinking the window
during which events may be missed.

But Stefan Roese reports unbalanced Card present and Link Up events,
suggesting that we're still missing events if they occur very rapidly.
Bjorn Helgaas responds that he considers pciehp's event handling
"baroque" and calls for its simplification and rationalization:
https://lkml.kernel.org/r/20180202192045.GA53759@bhelgaas-glaptop.roam.corp.google.com

It gets worse once a hotplug port is runtime suspended:  The port can
signal an interrupt while it and its parents are in D3hot, i.e. while
it is inaccessible.  By the time we've runtime resumed all parents to D0
and read the port's Slot Status register, we may have missed an arbitrary
number of events.  Event handling therefore needs to be reworked to
become resilient to missed events.

Assume that a Presence Detect Changed event has occurred.
Consider the following truth table:
- Slot is in OFF_STATE and is currently empty.    => Do nothing.
  (The event is trailing a Link Down or we've
  missed an insertion and subsequent removal.)
- Slot is in OFF_STATE and is currently occupied. => Turn the slot on.
- Slot is in ON_STATE  and is currently empty.    => Turn the slot off.
- Slot is in ON_STATE  and is currently occupied. => Turn the slot off,
  (Be cautious and assume the card in                then back on.
  the slot isn't the same as before.)

This leads to the following simple algorithm:
1 If the slot is in ON_STATE, turn it off unconditionally.
2 If the slot is currently occupied, turn it on.

Because those actions are now carried out synchronously, rather than by
scheduled work items, pciehp reacts to the *current* situation and
missed events no longer matter.

Data Link Layer State Changed events can be handled identically to
Presence Detect Changed events.  Note that in the above truth table,
a Link Up trailing a Card present event didn't have to be accounted for:
It is filtered out by pciehp_check_link_status().

As for Attention Button Pressed events, PCIe r4.0, sec 6.7.1.5 says:
"Once the Power Indicator begins blinking, a 5-second abort interval
exists during which a second depression of the Attention Button cancels
the operation."  In other words, the user can only expect the system to
react to a button press after it starts blinking.  Missed button presses
that occur in-between are irrelevant.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Stefan Roese <sr@denx.de>
Cc: Mayurkumar Patel <mayurkumar.patel@intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Kenji Kaneshige <kaneshige.kenji@jp.fujitsu.com>
---
 drivers/pci/hotplug/pciehp.h      |  3 +-
 drivers/pci/hotplug/pciehp_ctrl.c | 80 ++++++++++++++++++---------------------
 drivers/pci/hotplug/pciehp_hpc.c  | 10 +----
 3 files changed, 40 insertions(+), 53 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 9c75acd291fb..47cd9af5caf3 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -169,8 +169,7 @@ int pciehp_sysfs_disable_slot(struct slot *slot);
 void pciehp_request(struct controller *ctrl, int action);
 void pciehp_handle_button_press(struct slot *slot);
 void pciehp_handle_disable_request(struct slot *slot);
-void pciehp_handle_link_change(struct slot *slot);
-void pciehp_handle_presence_change(struct slot *slot);
+void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events);
 int pciehp_configure_device(struct slot *p_slot);
 void pciehp_unconfigure_device(struct slot *p_slot);
 void pciehp_queue_pushbutton_work(struct work_struct *work);
diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 4a12e70aacd0..811019902ada 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -217,66 +217,60 @@ void pciehp_handle_disable_request(struct slot *slot)
 	ctrl->request_result = pciehp_disable_slot(slot);
 }
 
-void pciehp_handle_link_change(struct slot *p_slot)
+void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events)
 {
-	struct controller *ctrl = p_slot->ctrl;
+	struct controller *ctrl = slot->ctrl;
 	bool link_active;
+	u8 present;
 
-	mutex_lock(&p_slot->lock);
-	link_active = pciehp_check_link_active(ctrl);
-
-	switch (p_slot->state) {
-	case BLINKINGON_STATE:
+	/*
+	 * If the slot is on and presence or link has changed, turn it off.
+	 * Even if it's occupied again, we cannot assume the card is the same.
+	 */
+	mutex_lock(&slot->lock);
+	switch (slot->state) {
 	case BLINKINGOFF_STATE:
-		cancel_delayed_work(&p_slot->work);
-		/* Fall through */
+		cancel_delayed_work(&slot->work);
 	case ON_STATE:
-	case OFF_STATE:
-		if (link_active) {
-			p_slot->state = POWERON_STATE;
-			mutex_unlock(&p_slot->lock);
-			ctrl_info(ctrl, "Slot(%s): Link Up\n", slot_name(p_slot));
-			pciehp_enable_slot(p_slot);
-		} else {
-			p_slot->state = POWEROFF_STATE;
-			mutex_unlock(&p_slot->lock);
-			ctrl_info(ctrl, "Slot(%s): Link Down\n", slot_name(p_slot));
-			pciehp_disable_slot(p_slot);
-		}
-		return;
+		slot->state = POWEROFF_STATE;
+		mutex_unlock(&slot->lock);
+		if (events & PCI_EXP_SLTSTA_DLLSC)
+			ctrl_info(ctrl, "Slot(%s): Link Down\n",
+				  slot_name(slot));
+		if (events & PCI_EXP_SLTSTA_PDC)
+			ctrl_info(ctrl, "Slot(%s): Card not present\n",
+				  slot_name(slot));
+		pciehp_disable_slot(slot);
 		break;
 	default:
-		ctrl_err(ctrl, "Slot(%s): Ignoring invalid state %#x\n",
-			 slot_name(p_slot), p_slot->state);
-		break;
+		mutex_unlock(&slot->lock);
 	}
-	mutex_unlock(&p_slot->lock);
-}
-
-void pciehp_handle_presence_change(struct slot *slot)
-{
-	struct controller *ctrl = slot->ctrl;
-	u8 present;
 
+	/* Turn the slot on if it's occupied or link is up */
 	mutex_lock(&slot->lock);
+	pciehp_get_adapter_status(slot, &present);
+	link_active = pciehp_check_link_active(ctrl);
+	if (!present && !link_active) {
+		mutex_unlock(&slot->lock);
+		return;
+	}
+
 	switch (slot->state) {
 	case BLINKINGON_STATE:
-	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&slot->work);
-	}
-
-	pciehp_get_adapter_status(slot, &present);
-	ctrl_info(ctrl, "Slot(%s): Card %spresent\n", slot_name(slot),
-		  present ? "" : "not ");
-
-	if (present) {
+	case OFF_STATE:
 		slot->state = POWERON_STATE;
 		mutex_unlock(&slot->lock);
+		if (present)
+			ctrl_info(ctrl, "Slot(%s): Card present\n",
+				  slot_name(slot));
+		if (link_active)
+			ctrl_info(ctrl, "Slot(%s): Link Up\n",
+				  slot_name(slot));
 		ctrl->request_result = pciehp_enable_slot(slot);
-	} else {
-		slot->state = POWEROFF_STATE;
+		break;
+	default:
 		mutex_unlock(&slot->lock);
-		pciehp_disable_slot(slot);
 	}
 }
 
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 6b8350a3875c..d588b3c1ffcc 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -602,17 +602,11 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	/*
 	 * Disable requests have higher priority than Presence Detect Changed
 	 * or Data Link Layer State Changed events.
-	 *
-	 * Check Link Status Changed at higher precedence than Presence
-	 * Detect Changed.  The PDS value may be set to "card present" from
-	 * out-of-band detection, which may be in conflict with a Link Down.
 	 */
 	if (events & DISABLE_SLOT)
 		pciehp_handle_disable_request(slot);
-	else if (events & PCI_EXP_SLTSTA_DLLSC)
-		pciehp_handle_link_change(slot);
-	else if (events & PCI_EXP_SLTSTA_PDC)
-		pciehp_handle_presence_change(slot);
+	else if (events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC))
+		pciehp_handle_presence_or_link_change(slot, events);
 
 	/* Check Power Fault Detected */
 	if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
-- 
cgit v1.2.3


From cdf6b7362108708cea83dea347b9acf81a652d5f Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:50 -0500
Subject: PCI: pciehp: Always enable occupied slot on probe

Per PCIe r4.0, sec 6.7.3.4, a "port may optionally send an MSI when
there are hot-plug events that occur while interrupt generation is
disabled, and interrupt generation is subsequently enabled."

On probe, we currently clear all event bits in the Slot Status register
with the notable exception of the Presence Detect Changed bit.  Thereby
we seek to receive an interrupt for an already occupied slot once event
notification is enabled.

But because the interrupt is optional, users may have to specify the
pciehp_force parameter on the command line, which is inconvenient.

Moreover, now that pciehp's event handling has become resilient to
missed events, a Presence Detect Changed interrupt for a slot which is
powered on is interpreted as removal of the card.  If the slot has
already been brought up by the BIOS, receiving such an interrupt on
probe causes the slot to be powered off and immediately back on, which
is likewise undesirable.

Avoid both issues by making the behavior of pciehp_force the default and
clearing the Presence Detect Changed bit on probe.

Note that the stated purpose of pciehp_force per the MODULE_PARM_DESC
("Force pciehp, even if OSHP is missing") seems nonsensical because the
OSHP control method is only relevant for SHCP slots according to the
PCI Firmware specification r3.0, sec 4.8.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pci/hotplug/pciehp_core.c | 12 ++++--------
 drivers/pci/hotplug/pciehp_hpc.c  |  9 ++-------
 2 files changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index b11f0db0695f..f4eaa9944699 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -30,7 +30,6 @@
 bool pciehp_debug;
 bool pciehp_poll_mode;
 int pciehp_poll_time;
-static bool pciehp_force;
 
 /*
  * not really modular, but the easiest way to keep compat with existing
@@ -39,11 +38,9 @@ static bool pciehp_force;
 module_param(pciehp_debug, bool, 0644);
 module_param(pciehp_poll_mode, bool, 0644);
 module_param(pciehp_poll_time, int, 0644);
-module_param(pciehp_force, bool, 0644);
 MODULE_PARM_DESC(pciehp_debug, "Debugging mode enabled or not");
 MODULE_PARM_DESC(pciehp_poll_mode, "Using polling mechanism for hot-plug events or not");
 MODULE_PARM_DESC(pciehp_poll_time, "Polling mechanism frequency, in seconds");
-MODULE_PARM_DESC(pciehp_force, "Force pciehp, even if OSHP is missing");
 
 #define PCIE_MODULE_NAME "pciehp"
 
@@ -243,11 +240,10 @@ static int pciehp_probe(struct pcie_device *dev)
 	mutex_lock(&slot->lock);
 	pciehp_get_adapter_status(slot, &occupied);
 	pciehp_get_power_status(slot, &poweron);
-	if (pciehp_force &&
-	    ((occupied && (slot->state == OFF_STATE ||
-			   slot->state == BLINKINGON_STATE)) ||
-	     (!occupied && (slot->state == ON_STATE ||
-			    slot->state == BLINKINGOFF_STATE))))
+	if ((occupied && (slot->state == OFF_STATE ||
+			  slot->state == BLINKINGON_STATE)) ||
+	    (!occupied && (slot->state == ON_STATE ||
+			   slot->state == BLINKINGOFF_STATE)))
 		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
 	/* If empty slot's power status is on, turn power off */
 	if (!occupied && poweron && POWER_CTRL(ctrl))
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index d588b3c1ffcc..712f3de78b09 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -844,16 +844,11 @@ struct controller *pcie_init(struct pcie_device *dev)
 	if (link_cap & PCI_EXP_LNKCAP_DLLLARC)
 		ctrl->link_active_reporting = 1;
 
-	/*
-	 * Clear all remaining event bits in Slot Status register except
-	 * Presence Detect Changed. We want to make sure possible
-	 * hotplug event is triggered when the interrupt is unmasked so
-	 * that we don't lose that event.
-	 */
+	/* Clear all remaining event bits in Slot Status register. */
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
 		PCI_EXP_SLTSTA_ABP | PCI_EXP_SLTSTA_PFD |
 		PCI_EXP_SLTSTA_MRLSC | PCI_EXP_SLTSTA_CC |
-		PCI_EXP_SLTSTA_DLLSC);
+		PCI_EXP_SLTSTA_DLLSC | PCI_EXP_SLTSTA_PDC);
 
 	ctrl_info(ctrl, "Slot #%d AttnBtn%c PwrCtrl%c MRL%c AttnInd%c PwrInd%c HotPlug%c Surprise%c Interlock%c NoCompl%c LLActRep%c%s\n",
 		(slot_cap & PCI_EXP_SLTCAP_PSN) >> 19,
-- 
cgit v1.2.3


From c6ea7e9747318e5a6774995f4f8e3e0f7c0fa8ba Mon Sep 17 00:00:00 2001
From: Paul Cercueil <paul@crapouillou.net>
Date: Sun, 8 Jul 2018 17:07:12 +0200
Subject: MIPS: jz4740: Bump zload address

Having the zload address at 0x8060.0000 means the size of the
uncompressed kernel cannot be bigger than around 6 MiB, as it is
deflated at address 0x8001.0000.

This limit is too small; a kernel with some built-in drivers and things
like debugfs enabled will already be over 6 MiB in size, and so will
fail to extract properly.

To fix this, we bump the zload address from 0x8060.0000 to 0x8100.0000.

This is fine, as all the boards featuring Ingenic JZ SoCs have at least
32 MiB of RAM, and use u-boot or compatible bootloaders which won't
hardcode the load address but read it from the uImage's header.

Signed-off-by: Paul Cercueil <paul@crapouillou.net>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19787/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/jz4740/Platform | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/jz4740/Platform b/arch/mips/jz4740/Platform
index 28448d358c10..a2a5a85ea1f9 100644
--- a/arch/mips/jz4740/Platform
+++ b/arch/mips/jz4740/Platform
@@ -1,4 +1,4 @@
 platform-$(CONFIG_MACH_INGENIC)	+= jz4740/
 cflags-$(CONFIG_MACH_INGENIC)	+= -I$(srctree)/arch/mips/include/asm/mach-jz4740
 load-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80010000
-zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff80600000
+zload-$(CONFIG_MACH_INGENIC)	+= 0xffffffff81000000
-- 
cgit v1.2.3


From 7cff3f168999fd1de4a41c5971363f42d49e961f Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Sat, 28 Apr 2018 11:21:25 +0800
Subject: MIPS: Loongson: Add Loongson-3A R3.1 basic support

Loongson-3A R3.1 is the bugfix revision of Loongson-3A R3.

All Loongson-3 CPU family:

Code-name         Brand-name       PRId
Loongson-3A R1    Loongson-3A1000  0x6305
Loongson-3A R2    Loongson-3A2000  0x6308
Loongson-3A R3    Loongson-3A3000  0x6309
Loongson-3A R3.1  Loongson-3A3000  0x630d
Loongson-3B R1    Loongson-3B1000  0x6306
Loongson-3B R2    Loongson-3B1500  0x6307

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19263/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <james.hogan@mips.com>
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: Huacai Chen <chenhuacai@gmail.com>
---
 arch/mips/include/asm/cpu.h           | 51 ++++++++++++++++++-----------------
 arch/mips/kernel/cpu-probe.c          |  3 ++-
 arch/mips/loongson64/common/env.c     |  3 ++-
 arch/mips/loongson64/loongson-3/smp.c |  3 ++-
 drivers/platform/mips/cpu_hwmon.c     |  3 ++-
 5 files changed, 34 insertions(+), 29 deletions(-)

diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 5b9d02ef4f60..dacbdb84516a 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -225,31 +225,32 @@
  * Definitions for 7:0 on legacy processors
  */
 
-#define PRID_REV_TX4927		0x0022
-#define PRID_REV_TX4937		0x0030
-#define PRID_REV_R4400		0x0040
-#define PRID_REV_R3000A		0x0030
-#define PRID_REV_R3000		0x0020
-#define PRID_REV_R2000A		0x0010
-#define PRID_REV_TX3912		0x0010
-#define PRID_REV_TX3922		0x0030
-#define PRID_REV_TX3927		0x0040
-#define PRID_REV_VR4111		0x0050
-#define PRID_REV_VR4181		0x0050	/* Same as VR4111 */
-#define PRID_REV_VR4121		0x0060
-#define PRID_REV_VR4122		0x0070
-#define PRID_REV_VR4181A	0x0070	/* Same as VR4122 */
-#define PRID_REV_VR4130		0x0080
-#define PRID_REV_34K_V1_0_2	0x0022
-#define PRID_REV_LOONGSON1B	0x0020
-#define PRID_REV_LOONGSON1C	0x0020	/* Same as Loongson-1B */
-#define PRID_REV_LOONGSON2E	0x0002
-#define PRID_REV_LOONGSON2F	0x0003
-#define PRID_REV_LOONGSON3A_R1	0x0005
-#define PRID_REV_LOONGSON3B_R1	0x0006
-#define PRID_REV_LOONGSON3B_R2	0x0007
-#define PRID_REV_LOONGSON3A_R2	0x0008
-#define PRID_REV_LOONGSON3A_R3	0x0009
+#define PRID_REV_TX4927			0x0022
+#define PRID_REV_TX4937			0x0030
+#define PRID_REV_R4400			0x0040
+#define PRID_REV_R3000A			0x0030
+#define PRID_REV_R3000			0x0020
+#define PRID_REV_R2000A			0x0010
+#define PRID_REV_TX3912			0x0010
+#define PRID_REV_TX3922			0x0030
+#define PRID_REV_TX3927			0x0040
+#define PRID_REV_VR4111			0x0050
+#define PRID_REV_VR4181			0x0050	/* Same as VR4111 */
+#define PRID_REV_VR4121			0x0060
+#define PRID_REV_VR4122			0x0070
+#define PRID_REV_VR4181A		0x0070	/* Same as VR4122 */
+#define PRID_REV_VR4130			0x0080
+#define PRID_REV_34K_V1_0_2		0x0022
+#define PRID_REV_LOONGSON1B		0x0020
+#define PRID_REV_LOONGSON1C		0x0020	/* Same as Loongson-1B */
+#define PRID_REV_LOONGSON2E		0x0002
+#define PRID_REV_LOONGSON2F		0x0003
+#define PRID_REV_LOONGSON3A_R1		0x0005
+#define PRID_REV_LOONGSON3B_R1		0x0006
+#define PRID_REV_LOONGSON3B_R2		0x0007
+#define PRID_REV_LOONGSON3A_R2		0x0008
+#define PRID_REV_LOONGSON3A_R3_0	0x0009
+#define PRID_REV_LOONGSON3A_R3_1	0x000d
 
 /*
  * Older processors used to encode processor version and revision in two
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index b2509c19cfb5..d535fc706a8b 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -1849,7 +1849,8 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
 			set_elf_platform(cpu, "loongson3a");
 			set_isa(c, MIPS_CPU_ISA_M64R2);
 			break;
-		case PRID_REV_LOONGSON3A_R3:
+		case PRID_REV_LOONGSON3A_R3_0:
+		case PRID_REV_LOONGSON3A_R3_1:
 			c->cputype = CPU_LOONGSON3;
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index 1e8a955ae5a8..8f68ee02a8c2 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -198,7 +198,8 @@ void __init prom_init_env(void)
 			break;
 		case PRID_REV_LOONGSON3A_R1:
 		case PRID_REV_LOONGSON3A_R2:
-		case PRID_REV_LOONGSON3A_R3:
+		case PRID_REV_LOONGSON3A_R3_0:
+		case PRID_REV_LOONGSON3A_R3_1:
 			cpu_clock_freq = 900000000;
 			break;
 		case PRID_REV_LOONGSON3B_R1:
diff --git a/arch/mips/loongson64/loongson-3/smp.c b/arch/mips/loongson64/loongson-3/smp.c
index 8501109bb0f0..fea95d003269 100644
--- a/arch/mips/loongson64/loongson-3/smp.c
+++ b/arch/mips/loongson64/loongson-3/smp.c
@@ -682,7 +682,8 @@ void play_dead(void)
 			(void *)CKSEG1ADDR((unsigned long)loongson3a_r1_play_dead);
 		break;
 	case PRID_REV_LOONGSON3A_R2:
-	case PRID_REV_LOONGSON3A_R3:
+	case PRID_REV_LOONGSON3A_R3_0:
+	case PRID_REV_LOONGSON3A_R3_1:
 		play_dead_at_ckseg1 =
 			(void *)CKSEG1ADDR((unsigned long)loongson3a_r2r3_play_dead);
 		break;
diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c
index 322de58eebaf..f66521c7f846 100644
--- a/drivers/platform/mips/cpu_hwmon.c
+++ b/drivers/platform/mips/cpu_hwmon.c
@@ -30,7 +30,8 @@ int loongson3_cpu_temp(int cpu)
 	case PRID_REV_LOONGSON3B_R2:
 		reg = ((reg >> 8) & 0xff) - 100;
 		break;
-	case PRID_REV_LOONGSON3A_R3:
+	case PRID_REV_LOONGSON3A_R3_0:
+	case PRID_REV_LOONGSON3A_R3_1:
 		reg = (reg & 0xffff)*731/0x4000 - 273;
 		break;
 	}
-- 
cgit v1.2.3


From 97ab1bb4901cb5e1e43f6f7effd44e03d0e7427d Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhc@lemote.com>
Date: Sat, 28 Apr 2018 11:21:26 +0800
Subject: MIPS: Loongson64: Define and use some CP0 registers

Defines CP0_CONFIG3, CP0_CONFIG6, CP0_PAGEGRAIN and use them in
kernel-entry-init.h for Loongson64.

Signed-off-by: Huacai Chen <chenhc@lemote.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19264/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <james.hogan@mips.com>
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Cc: Huacai Chen <chenhuacai@gmail.com>
---
 .../asm/mach-loongson64/kernel-entry-init.h        | 24 +++++++++++-----------
 arch/mips/include/asm/mipsregs.h                   |  2 ++
 2 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
index 8393bc548987..312739117bb0 100644
--- a/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
+++ b/arch/mips/include/asm/mach-loongson64/kernel-entry-init.h
@@ -19,18 +19,18 @@
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
-	mfc0	t0, $16, 3
+	mfc0	t0, CP0_CONFIG3
 	or	t0, (0x1 << 7)
-	mtc0	t0, $16, 3
+	mtc0	t0, CP0_CONFIG3
 	/* Set ELPA on LOONGSON3 pagegrain */
-	mfc0	t0, $5, 1
+	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
-	mtc0	t0, $5, 1
+	mtc0	t0, CP0_PAGEGRAIN
 #ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
-	mfc0	t0, $16, 6
+	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
-	mtc0	t0, $16, 6
+	mtc0	t0, CP0_CONFIG6
 #endif
 	_ehb
 	.set	pop
@@ -45,18 +45,18 @@
 	.set	push
 	.set	mips64
 	/* Set LPA on LOONGSON3 config3 */
-	mfc0	t0, $16, 3
+	mfc0	t0, CP0_CONFIG3
 	or	t0, (0x1 << 7)
-	mtc0	t0, $16, 3
+	mtc0	t0, CP0_CONFIG3
 	/* Set ELPA on LOONGSON3 pagegrain */
-	mfc0	t0, $5, 1
+	mfc0	t0, CP0_PAGEGRAIN
 	or	t0, (0x1 << 29)
-	mtc0	t0, $5, 1
+	mtc0	t0, CP0_PAGEGRAIN
 #ifdef CONFIG_LOONGSON3_ENHANCEMENT
 	/* Enable STFill Buffer */
-	mfc0	t0, $16, 6
+	mfc0	t0, CP0_CONFIG6
 	or	t0, 0x100
-	mtc0	t0, $16, 6
+	mtc0	t0, CP0_CONFIG6
 #endif
 	_ehb
 	.set	pop
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 0bc270806ec5..b6237ffbacf5 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -51,6 +51,7 @@
 #define CP0_GLOBALNUMBER $3, 1
 #define CP0_CONTEXT $4
 #define CP0_PAGEMASK $5
+#define CP0_PAGEGRAIN $5, 1
 #define CP0_SEGCTL0 $5, 2
 #define CP0_SEGCTL1 $5, 3
 #define CP0_SEGCTL2 $5, 4
@@ -77,6 +78,7 @@
 #define CP0_CONFIG $16
 #define CP0_CONFIG3 $16, 3
 #define CP0_CONFIG5 $16, 5
+#define CP0_CONFIG6 $16, 6
 #define CP0_LLADDR $17
 #define CP0_WATCHLO $18
 #define CP0_WATCHHI $19
-- 
cgit v1.2.3


From 79b3325d0d87a6b3af96485ff8029bcc26e070e3 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 24 Jul 2018 00:26:29 +0300
Subject: net: ethernet: ti: cpsw: use cpdma channels in backward order for txq

The cpdma channel highest priority is from hi to lo number.
The driver has limited number of descriptors that are shared between
number of cpdma channels. Number of queues can be tuned with ethtool,
that allows to not spend descriptors on not needed cpdma channels.
In AVB usually only 2 tx queues can be enough with rate limitation.
The rate limitation can be used only for hi priority queues. Thus, to
use only 2 queues the 8 has to be created. It's wasteful.

So, in order to allow using only needed number of rate limited
tx queues, save resources, and be able to set rate limitation for
them, let assign tx cpdma channels in backward order to queues.

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 00761fe59848..4425b537b9dd 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -968,8 +968,8 @@ static int cpsw_tx_mq_poll(struct napi_struct *napi_tx, int budget)
 
 	/* process every unprocessed channel */
 	ch_map = cpdma_ctrl_txchs_state(cpsw->dma);
-	for (ch = 0, num_tx = 0; ch_map; ch_map >>= 1, ch++) {
-		if (!(ch_map & 0x01))
+	for (ch = 0, num_tx = 0; ch_map & 0xff; ch_map <<= 1, ch++) {
+		if (!(ch_map & 0x80))
 			continue;
 
 		txv = &cpsw->txv[ch];
@@ -2432,7 +2432,7 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx)
 	void (*handler)(void *, int, int);
 	struct netdev_queue *queue;
 	struct cpsw_vector *vec;
-	int ret, *ch;
+	int ret, *ch, vch;
 
 	if (rx) {
 		ch = &cpsw->rx_ch_num;
@@ -2445,7 +2445,8 @@ static int cpsw_update_channels_res(struct cpsw_priv *priv, int ch_num, int rx)
 	}
 
 	while (*ch < ch_num) {
-		vec[*ch].ch = cpdma_chan_create(cpsw->dma, *ch, handler, rx);
+		vch = rx ? *ch : 7 - *ch;
+		vec[*ch].ch = cpdma_chan_create(cpsw->dma, vch, handler, rx);
 		queue = netdev_get_tx_queue(priv->ndev, *ch);
 		queue->tx_maxrate = 0;
 
@@ -2982,7 +2983,7 @@ static int cpsw_probe(struct platform_device *pdev)
 	u32 slave_offset, sliver_offset, slave_size;
 	const struct soc_device_attribute *soc;
 	struct cpsw_common		*cpsw;
-	int ret = 0, i;
+	int ret = 0, i, ch;
 	int irq;
 
 	cpsw = devm_kzalloc(&pdev->dev, sizeof(struct cpsw_common), GFP_KERNEL);
@@ -3157,7 +3158,8 @@ static int cpsw_probe(struct platform_device *pdev)
 	if (soc)
 		cpsw->quirk_irq = 1;
 
-	cpsw->txv[0].ch = cpdma_chan_create(cpsw->dma, 0, cpsw_tx_handler, 0);
+	ch = cpsw->quirk_irq ? 0 : 7;
+	cpsw->txv[0].ch = cpdma_chan_create(cpsw->dma, ch, cpsw_tx_handler, 0);
 	if (IS_ERR(cpsw->txv[0].ch)) {
 		dev_err(priv->dev, "error initializing tx dma channel\n");
 		ret = PTR_ERR(cpsw->txv[0].ch);
-- 
cgit v1.2.3


From 4bb6c356a0393fe7ff5741ede700ba99352640a0 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 24 Jul 2018 00:26:30 +0300
Subject: net: ethernet: ti: cpdma: fit rated channels in backward order

According to TRM tx rated channels should be in 7..0 order,
so correct it.

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/davinci_cpdma.c | 31 +++++++++++++++----------------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/ti/davinci_cpdma.c b/drivers/net/ethernet/ti/davinci_cpdma.c
index 4f1267477aa4..4236dcdd5634 100644
--- a/drivers/net/ethernet/ti/davinci_cpdma.c
+++ b/drivers/net/ethernet/ti/davinci_cpdma.c
@@ -406,37 +406,36 @@ static int cpdma_chan_fit_rate(struct cpdma_chan *ch, u32 rate,
 	struct cpdma_chan *chan;
 	u32 old_rate = ch->rate;
 	u32 new_rmask = 0;
-	int rlim = 1;
+	int rlim = 0;
 	int i;
 
-	*prio_mode = 0;
 	for (i = tx_chan_num(0); i < tx_chan_num(CPDMA_MAX_CHANNELS); i++) {
 		chan = ctlr->channels[i];
-		if (!chan) {
-			rlim = 0;
+		if (!chan)
 			continue;
-		}
 
 		if (chan == ch)
 			chan->rate = rate;
 
 		if (chan->rate) {
-			if (rlim) {
-				new_rmask |= chan->mask;
-			} else {
-				ch->rate = old_rate;
-				dev_err(ctlr->dev, "Prev channel of %dch is not rate limited\n",
-					chan->chan_num);
-				return -EINVAL;
-			}
-		} else {
-			*prio_mode = 1;
-			rlim = 0;
+			rlim = 1;
+			new_rmask |= chan->mask;
+			continue;
 		}
+
+		if (rlim)
+			goto err;
 	}
 
 	*rmask = new_rmask;
+	*prio_mode = rlim;
 	return 0;
+
+err:
+	ch->rate = old_rate;
+	dev_err(ctlr->dev, "Upper cpdma ch%d is not rate limited\n",
+		chan->chan_num);
+	return -EINVAL;
 }
 
 static u32 cpdma_chan_set_factors(struct cpdma_ctlr *ctlr,
-- 
cgit v1.2.3


From 7929a66871a131f692145599b6cc11c571dfbd71 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 24 Jul 2018 00:26:31 +0300
Subject: net: ethernet: ti: cpsw: add MQPRIO Qdisc offload
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

That's possible to offload vlan to tc priority mapping with
assumption sk_prio == L2 prio.

Example:
$ ethtool -L eth0 rx 1 tx 4

$ qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 1

$ tc -g class show dev eth0
+---(100:ffe2) mqprio
|    +---(100:3) mqprio
|    +---(100:4) mqprio
|    
+---(100:ffe1) mqprio
|    +---(100:2) mqprio
|    
+---(100:ffe0) mqprio
     +---(100:1) mqprio

Here, 100:1 is txq0, 100:2 is txq1, 100:3 is txq2, 100:4 is txq3
txq0 belongs to tc0, txq1 to tc1, txq2 and txq3 to tc2
The offload part only maps L2 prio to classes of traffic, but not
to transmit queues, so to direct traffic to traffic class vlan has
to be created with appropriate egress map.

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 82 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 82 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 4425b537b9dd..f099e0ed138d 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -39,6 +39,7 @@
 #include <linux/sys_soc.h>
 
 #include <linux/pinctrl/consumer.h>
+#include <net/pkt_cls.h>
 
 #include "cpsw.h"
 #include "cpsw_ale.h"
@@ -153,6 +154,8 @@ do {								\
 #define IRQ_NUM			2
 #define CPSW_MAX_QUEUES		8
 #define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256
+#define CPSW_TC_NUM			4
+#define CPSW_FIFO_SHAPERS_NUM		(CPSW_TC_NUM - 1)
 
 #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT	29
 #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK		GENMASK(2, 0)
@@ -454,6 +457,7 @@ struct cpsw_priv {
 	u8				mac_addr[ETH_ALEN];
 	bool				rx_pause;
 	bool				tx_pause;
+	bool				mqprio_hw;
 	u32 emac_port;
 	struct cpsw_common *cpsw;
 };
@@ -1578,6 +1582,14 @@ static void cpsw_slave_stop(struct cpsw_slave *slave, struct cpsw_common *cpsw)
 	soft_reset_slave(slave);
 }
 
+static int cpsw_tc_to_fifo(int tc, int num_tc)
+{
+	if (tc == num_tc - 1)
+		return 0;
+
+	return CPSW_FIFO_SHAPERS_NUM - tc;
+}
+
 static int cpsw_ndo_open(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
@@ -2191,6 +2203,75 @@ static int cpsw_ndo_set_tx_maxrate(struct net_device *ndev, int queue, u32 rate)
 	return ret;
 }
 
+static int cpsw_set_mqprio(struct net_device *ndev, void *type_data)
+{
+	struct tc_mqprio_qopt_offload *mqprio = type_data;
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	int fifo, num_tc, count, offset;
+	struct cpsw_slave *slave;
+	u32 tx_prio_map = 0;
+	int i, tc, ret;
+
+	num_tc = mqprio->qopt.num_tc;
+	if (num_tc > CPSW_TC_NUM)
+		return -EINVAL;
+
+	if (mqprio->mode != TC_MQPRIO_MODE_DCB)
+		return -EINVAL;
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	if (num_tc) {
+		for (i = 0; i < 8; i++) {
+			tc = mqprio->qopt.prio_tc_map[i];
+			fifo = cpsw_tc_to_fifo(tc, num_tc);
+			tx_prio_map |= fifo << (4 * i);
+		}
+
+		netdev_set_num_tc(ndev, num_tc);
+		for (i = 0; i < num_tc; i++) {
+			count = mqprio->qopt.count[i];
+			offset = mqprio->qopt.offset[i];
+			netdev_set_tc_queue(ndev, i, count, offset);
+		}
+	}
+
+	if (!mqprio->qopt.hw) {
+		/* restore default configuration */
+		netdev_reset_tc(ndev);
+		tx_prio_map = TX_PRIORITY_MAPPING;
+	}
+
+	priv->mqprio_hw = mqprio->qopt.hw;
+
+	offset = cpsw->version == CPSW_VERSION_1 ?
+		 CPSW1_TX_PRI_MAP : CPSW2_TX_PRI_MAP;
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	slave_write(slave, tx_prio_map, offset);
+
+	pm_runtime_put_sync(cpsw->dev);
+
+	return 0;
+}
+
+static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
+			     void *type_data)
+{
+	switch (type) {
+	case TC_SETUP_QDISC_MQPRIO:
+		return cpsw_set_mqprio(ndev, type_data);
+
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops cpsw_netdev_ops = {
 	.ndo_open		= cpsw_ndo_open,
 	.ndo_stop		= cpsw_ndo_stop,
@@ -2206,6 +2287,7 @@ static const struct net_device_ops cpsw_netdev_ops = {
 #endif
 	.ndo_vlan_rx_add_vid	= cpsw_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid	= cpsw_ndo_vlan_rx_kill_vid,
+	.ndo_setup_tc           = cpsw_ndo_setup_tc,
 };
 
 static int cpsw_get_regs_len(struct net_device *ndev)
-- 
cgit v1.2.3


From 57d901482546c0698ef8e11a6f7193432db6ec1c Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 24 Jul 2018 00:26:32 +0300
Subject: net: ethernet: ti: cpsw: add CBS Qdisc offload
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The cpsw has up to 4 FIFOs per port and upper 3 FIFOs can feed rate
limited queue with shaping. In order to set and enable shaping for
those 3 FIFOs queues the network device with CBS qdisc attached is
needed. The CBS configuration is added for dual-emac/single port mode
only, but potentially can be used in switch mode also, based on
switchdev for instance.

Despite the FIFO shapers can work w/o cpdma level shapers the base
usage must be in combine with cpdma level shapers as described in TRM,
that are set as maximum rates for interface queues with sysfs.

One of the possible configuration with txq shapers and CBS shapers:

                      Configured with echo RATE >
                  /sys/class/net/eth0/queues/tx-0/tx_maxrate
             /---------------------------------------------------
            /
           /            cpdma level shapers
        +----+ +----+ +----+ +----+ +----+ +----+ +----+ +----+
        | c7 | | c6 | | c5 | | c4 | | c3 | | c2 | | c1 | | c0 |
        \    / \    / \    / \    / \    / \    / \    / \    /
         \  /   \  /   \  /   \  /   \  /   \  /   \  /   \  /
          \/     \/     \/     \/     \/     \/     \/     \/
+---------|------|------|------|-------------------------------------+
|    +----+      |      |  +---+                                     |
|    |      +----+      |  |                                         |
|    v      v           v  v                                         |
| +----+ +----+ +----+ +----+ p        p+----+ +----+ +----+ +----+  |
| |    | |    | |    | |    | o        o|    | |    | |    | |    |  |
| | f3 | | f2 | | f1 | | f0 | r  CPSW  r| f3 | | f2 | | f1 | | f0 |  |
| |    | |    | |    | |    | t        t|    | |    | |    | |    |  |
| \    / \    / \    / \    / 0        1\    / \    / \    / \    /  |
|  \  X   \  /   \  /   \  /             \  /   \  /   \  /   \  /   |
|   \/ \   \/     \/     \/               \/     \/     \/     \/    |
+-------\------------------------------------------------------------+
         \
          \ FIFO shaper, set with CBS offload added in this patch,
           \ FIFO0 cannot be rate limited
            ------------------------------------------------------

CBS shaper configuration is supposed to be used with root MQPRIO Qdisc
offload allowing to add sk_prio->tc->txq maps that direct traffic to
appropriate tx queue and maps L2 priority to FIFO shaper.

The CBS shaper is intended to be used for AVB where L2 priority
(pcp field) is used to differentiate class of traffic. So additionally
vlan needs to be created with appropriate egress sk_prio->l2 prio map.

If CBS has several tx queues assigned to it, the sum of their
bandwidth has not overlap bandwidth set for CBS. It's recomended the
CBS bandwidth to be a little bit more.

The CBS shaper is configured with CBS qdisc offload interface using tc
tool from iproute2 packet.

For instance:

$ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 1

$ tc -g class show dev eth0
+---(100:ffe2) mqprio
|    +---(100:3) mqprio
|    +---(100:4) mqprio
|    
+---(100:ffe1) mqprio
|    +---(100:2) mqprio
|    
+---(100:ffe0) mqprio
     +---(100:1) mqprio

$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1440 \
hicredit 60 sendslope -960000 idleslope 40000 offload 1

$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1470 \
hicredit 62 sendslope -980000 idleslope 20000 offload 1

The above code set CBS shapers for tc0 and tc1, for that txq0 and
txq1 is used. Pay attention, the real set bandwidth can differ a bit
due to discreteness of configuration parameters.

Here parameters like locredit, hicredit and sendslope are ignored
internally and are supposed to be set with assumption that maximum
frame size for frame - 1500.

It's supposed that interface speed is not changed while reconnection,
not always is true, so inform user in case speed of interface was
changed, as it can impact on dependent shapers configuration.

For more examples see Documentation.

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 221 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 221 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index f099e0ed138d..449dc7f1e5f8 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -46,6 +46,8 @@
 #include "cpts.h"
 #include "davinci_cpdma.h"
 
+#include <net/pkt_sched.h>
+
 #define CPSW_DEBUG	(NETIF_MSG_HW		| NETIF_MSG_WOL		| \
 			 NETIF_MSG_DRV		| NETIF_MSG_LINK	| \
 			 NETIF_MSG_IFUP		| NETIF_MSG_INTR	| \
@@ -154,8 +156,12 @@ do {								\
 #define IRQ_NUM			2
 #define CPSW_MAX_QUEUES		8
 #define CPSW_CPDMA_DESCS_POOL_SIZE_DEFAULT 256
+#define CPSW_FIFO_QUEUE_TYPE_SHIFT	16
+#define CPSW_FIFO_SHAPE_EN_SHIFT	16
+#define CPSW_FIFO_RATE_EN_SHIFT		20
 #define CPSW_TC_NUM			4
 #define CPSW_FIFO_SHAPERS_NUM		(CPSW_TC_NUM - 1)
+#define CPSW_PCT_MASK			0x7f
 
 #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_SHIFT	29
 #define CPSW_RX_VLAN_ENCAP_HDR_PRIO_MSK		GENMASK(2, 0)
@@ -458,6 +464,8 @@ struct cpsw_priv {
 	bool				rx_pause;
 	bool				tx_pause;
 	bool				mqprio_hw;
+	int				fifo_bw[CPSW_TC_NUM];
+	int				shp_cfg_speed;
 	u32 emac_port;
 	struct cpsw_common *cpsw;
 };
@@ -1082,6 +1090,38 @@ static void cpsw_set_slave_mac(struct cpsw_slave *slave,
 	slave_write(slave, mac_lo(priv->mac_addr), SA_LO);
 }
 
+static bool cpsw_shp_is_off(struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	u32 shift, mask, val;
+
+	val = readl_relaxed(&cpsw->regs->ptype);
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	shift = CPSW_FIFO_SHAPE_EN_SHIFT + 3 * slave->slave_num;
+	mask = 7 << shift;
+	val = val & mask;
+
+	return !val;
+}
+
+static void cpsw_fifo_shp_on(struct cpsw_priv *priv, int fifo, int on)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	u32 shift, mask, val;
+
+	val = readl_relaxed(&cpsw->regs->ptype);
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	shift = CPSW_FIFO_SHAPE_EN_SHIFT + 3 * slave->slave_num;
+	mask = (1 << --fifo) << shift;
+	val = on ? val | mask : val & ~mask;
+
+	writel_relaxed(val, &cpsw->regs->ptype);
+}
+
 static void _cpsw_adjust_link(struct cpsw_slave *slave,
 			      struct cpsw_priv *priv, bool *link)
 {
@@ -1121,6 +1161,12 @@ static void _cpsw_adjust_link(struct cpsw_slave *slave,
 			mac_control |= BIT(4);
 
 		*link = true;
+
+		if (priv->shp_cfg_speed &&
+		    priv->shp_cfg_speed != slave->phy->speed &&
+		    !cpsw_shp_is_off(priv))
+			dev_warn(priv->dev,
+				 "Speed was changed, CBS shaper speeds are changed!");
 	} else {
 		mac_control = 0;
 		/* disable forwarding */
@@ -1590,6 +1636,178 @@ static int cpsw_tc_to_fifo(int tc, int num_tc)
 	return CPSW_FIFO_SHAPERS_NUM - tc;
 }
 
+static int cpsw_set_fifo_bw(struct cpsw_priv *priv, int fifo, int bw)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	u32 val = 0, send_pct, shift;
+	struct cpsw_slave *slave;
+	int pct = 0, i;
+
+	if (bw > priv->shp_cfg_speed * 1000)
+		goto err;
+
+	/* shaping has to stay enabled for highest fifos linearly
+	 * and fifo bw no more then interface can allow
+	 */
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	send_pct = slave_read(slave, SEND_PERCENT);
+	for (i = CPSW_FIFO_SHAPERS_NUM; i > 0; i--) {
+		if (!bw) {
+			if (i >= fifo || !priv->fifo_bw[i])
+				continue;
+
+			dev_warn(priv->dev, "Prev FIFO%d is shaped", i);
+			continue;
+		}
+
+		if (!priv->fifo_bw[i] && i > fifo) {
+			dev_err(priv->dev, "Upper FIFO%d is not shaped", i);
+			return -EINVAL;
+		}
+
+		shift = (i - 1) * 8;
+		if (i == fifo) {
+			send_pct &= ~(CPSW_PCT_MASK << shift);
+			val = DIV_ROUND_UP(bw, priv->shp_cfg_speed * 10);
+			if (!val)
+				val = 1;
+
+			send_pct |= val << shift;
+			pct += val;
+			continue;
+		}
+
+		if (priv->fifo_bw[i])
+			pct += (send_pct >> shift) & CPSW_PCT_MASK;
+	}
+
+	if (pct >= 100)
+		goto err;
+
+	slave_write(slave, send_pct, SEND_PERCENT);
+	priv->fifo_bw[fifo] = bw;
+
+	dev_warn(priv->dev, "set FIFO%d bw = %d\n", fifo,
+		 DIV_ROUND_CLOSEST(val * priv->shp_cfg_speed, 100));
+
+	return 0;
+err:
+	dev_err(priv->dev, "Bandwidth doesn't fit in tc configuration");
+	return -EINVAL;
+}
+
+static int cpsw_set_fifo_rlimit(struct cpsw_priv *priv, int fifo, int bw)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	u32 tx_in_ctl_rg, val;
+	int ret;
+
+	ret = cpsw_set_fifo_bw(priv, fifo, bw);
+	if (ret)
+		return ret;
+
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	tx_in_ctl_rg = cpsw->version == CPSW_VERSION_1 ?
+		       CPSW1_TX_IN_CTL : CPSW2_TX_IN_CTL;
+
+	if (!bw)
+		cpsw_fifo_shp_on(priv, fifo, bw);
+
+	val = slave_read(slave, tx_in_ctl_rg);
+	if (cpsw_shp_is_off(priv)) {
+		/* disable FIFOs rate limited queues */
+		val &= ~(0xf << CPSW_FIFO_RATE_EN_SHIFT);
+
+		/* set type of FIFO queues to normal priority mode */
+		val &= ~(3 << CPSW_FIFO_QUEUE_TYPE_SHIFT);
+
+		/* set type of FIFO queues to be rate limited */
+		if (bw)
+			val |= 2 << CPSW_FIFO_QUEUE_TYPE_SHIFT;
+		else
+			priv->shp_cfg_speed = 0;
+	}
+
+	/* toggle a FIFO rate limited queue */
+	if (bw)
+		val |= BIT(fifo + CPSW_FIFO_RATE_EN_SHIFT);
+	else
+		val &= ~BIT(fifo + CPSW_FIFO_RATE_EN_SHIFT);
+	slave_write(slave, val, tx_in_ctl_rg);
+
+	/* FIFO transmit shape enable */
+	cpsw_fifo_shp_on(priv, fifo, bw);
+	return 0;
+}
+
+/* Defaults:
+ * class A - prio 3
+ * class B - prio 2
+ * shaping for class A should be set first
+ */
+static int cpsw_set_cbs(struct net_device *ndev,
+			struct tc_cbs_qopt_offload *qopt)
+{
+	struct cpsw_priv *priv = netdev_priv(ndev);
+	struct cpsw_common *cpsw = priv->cpsw;
+	struct cpsw_slave *slave;
+	int prev_speed = 0;
+	int tc, ret, fifo;
+	u32 bw = 0;
+
+	tc = netdev_txq_to_tc(priv->ndev, qopt->queue);
+
+	/* enable channels in backward order, as highest FIFOs must be rate
+	 * limited first and for compliance with CPDMA rate limited channels
+	 * that also used in bacward order. FIFO0 cannot be rate limited.
+	 */
+	fifo = cpsw_tc_to_fifo(tc, ndev->num_tc);
+	if (!fifo) {
+		dev_err(priv->dev, "Last tc%d can't be rate limited", tc);
+		return -EINVAL;
+	}
+
+	/* do nothing, it's disabled anyway */
+	if (!qopt->enable && !priv->fifo_bw[fifo])
+		return 0;
+
+	/* shapers can be set if link speed is known */
+	slave = &cpsw->slaves[cpsw_slave_index(cpsw, priv)];
+	if (slave->phy && slave->phy->link) {
+		if (priv->shp_cfg_speed &&
+		    priv->shp_cfg_speed != slave->phy->speed)
+			prev_speed = priv->shp_cfg_speed;
+
+		priv->shp_cfg_speed = slave->phy->speed;
+	}
+
+	if (!priv->shp_cfg_speed) {
+		dev_err(priv->dev, "Link speed is not known");
+		return -1;
+	}
+
+	ret = pm_runtime_get_sync(cpsw->dev);
+	if (ret < 0) {
+		pm_runtime_put_noidle(cpsw->dev);
+		return ret;
+	}
+
+	bw = qopt->enable ? qopt->idleslope : 0;
+	ret = cpsw_set_fifo_rlimit(priv, fifo, bw);
+	if (ret) {
+		priv->shp_cfg_speed = prev_speed;
+		prev_speed = 0;
+	}
+
+	if (bw && prev_speed)
+		dev_warn(priv->dev,
+			 "Speed was changed, CBS shaper speeds are changed!");
+
+	pm_runtime_put_sync(cpsw->dev);
+	return ret;
+}
+
 static int cpsw_ndo_open(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
@@ -2264,6 +2482,9 @@ static int cpsw_ndo_setup_tc(struct net_device *ndev, enum tc_setup_type type,
 			     void *type_data)
 {
 	switch (type) {
+	case TC_SETUP_QDISC_CBS:
+		return cpsw_set_cbs(ndev, type_data);
+
 	case TC_SETUP_QDISC_MQPRIO:
 		return cpsw_set_mqprio(ndev, type_data);
 
-- 
cgit v1.2.3


From 4b4255ed068fd9e52eff01e1d90137222cce0e61 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 24 Jul 2018 00:26:33 +0300
Subject: net: ethernet: ti: cpsw: restore shaper configuration while down/up

Need to restore shapers configuration after interface was down/up.
This is needed as appropriate configuration is still replicated in
kernel settings. This only shapers context restore, so vlan
configuration should be restored by user if needed, especially for
devices with one port where vlan frames are sent via ALE.

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 47 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 449dc7f1e5f8..171abcfb6184 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -1808,6 +1808,51 @@ static int cpsw_set_cbs(struct net_device *ndev,
 	return ret;
 }
 
+static void cpsw_cbs_resume(struct cpsw_slave *slave, struct cpsw_priv *priv)
+{
+	int fifo, bw;
+
+	for (fifo = CPSW_FIFO_SHAPERS_NUM; fifo > 0; fifo--) {
+		bw = priv->fifo_bw[fifo];
+		if (!bw)
+			continue;
+
+		cpsw_set_fifo_rlimit(priv, fifo, bw);
+	}
+}
+
+static void cpsw_mqprio_resume(struct cpsw_slave *slave, struct cpsw_priv *priv)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+	u32 tx_prio_map = 0;
+	int i, tc, fifo;
+	u32 tx_prio_rg;
+
+	if (!priv->mqprio_hw)
+		return;
+
+	for (i = 0; i < 8; i++) {
+		tc = netdev_get_prio_tc_map(priv->ndev, i);
+		fifo = CPSW_FIFO_SHAPERS_NUM - tc;
+		tx_prio_map |= fifo << (4 * i);
+	}
+
+	tx_prio_rg = cpsw->version == CPSW_VERSION_1 ?
+		     CPSW1_TX_PRI_MAP : CPSW2_TX_PRI_MAP;
+
+	slave_write(slave, tx_prio_map, tx_prio_rg);
+}
+
+/* restore resources after port reset */
+static void cpsw_restore(struct cpsw_priv *priv)
+{
+	/* restore MQPRIO offload */
+	for_each_slave(priv, cpsw_mqprio_resume, priv);
+
+	/* restore CBS offload */
+	for_each_slave(priv, cpsw_cbs_resume, priv);
+}
+
 static int cpsw_ndo_open(struct net_device *ndev)
 {
 	struct cpsw_priv *priv = netdev_priv(ndev);
@@ -1887,6 +1932,8 @@ static int cpsw_ndo_open(struct net_device *ndev)
 
 	}
 
+	cpsw_restore(priv);
+
 	/* Enable Interrupt pacing if configured */
 	if (cpsw->coal_intvl != 0) {
 		struct ethtool_coalesce coal;
-- 
cgit v1.2.3


From ae62372f275c444b8363ddb6367684c573214c13 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 24 Jul 2018 00:26:34 +0300
Subject: Documentation: networking: cpsw: add MQPRIO & CBS offload examples

This document describes MQPRIO and CBS Qdisc offload configuration
for cpsw driver based on examples. It potentially can be used in
audio video bridging (AVB) and time sensitive networking (TSN).

Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ti-cpsw.txt | 540 +++++++++++++++++++++++++++++++++++
 1 file changed, 540 insertions(+)
 create mode 100644 Documentation/networking/ti-cpsw.txt

diff --git a/Documentation/networking/ti-cpsw.txt b/Documentation/networking/ti-cpsw.txt
new file mode 100644
index 000000000000..67039205bd69
--- /dev/null
+++ b/Documentation/networking/ti-cpsw.txt
@@ -0,0 +1,540 @@
+* Texas Instruments CPSW ethernet driver
+
+Multiqueue & CBS & MQPRIO
+=====================================================================
+=====================================================================
+
+The cpsw has 3 CBS shapers for each external ports. This document
+describes MQPRIO and CBS Qdisc offload configuration for cpsw driver
+based on examples. It potentially can be used in audio video bridging
+(AVB) and time sensitive networking (TSN).
+
+The following examples were tested on AM572x EVM and BBB boards.
+
+Test setup
+==========
+
+Under consideration two examples with AM572x EVM running cpsw driver
+in dual_emac mode.
+
+Several prerequisites:
+- TX queues must be rated starting from txq0 that has highest priority
+- Traffic classes are used starting from 0, that has highest priority
+- CBS shapers should be used with rated queues
+- The bandwidth for CBS shapers has to be set a little bit more then
+  potential incoming rate, thus, rate of all incoming tx queues has
+  to be a little less
+- Real rates can differ, due to discreetness
+- Map skb-priority to txq is not enough, also skb-priority to l2 prio
+  map has to be created with ip or vconfig tool
+- Any l2/socket prio (0 - 7) for classes can be used, but for
+  simplicity default values are used: 3 and 2
+- only 2 classes tested: A and B, but checked and can work with more,
+  maximum allowed 4, but only for 3 rate can be set.
+
+Test setup for examples
+=======================
+                                    +-------------------------------+
+                                    |--+                            |
+                                    |  |      Workstation0          |
+                                    |E |  MAC 18:03:73:66:87:42     |
++-----------------------------+  +--|t |                            |
+|                    | 1  | E |  |  |h |./tsn_listener -d \         |
+|  Target board:     | 0  | t |--+  |0 | 18:03:73:66:87:42 -i eth0 \|
+|  AM572x EVM        | 0  | h |     |  | -s 1500                    |
+|                    | 0  | 0 |     |--+                            |
+|  Only 2 classes:   |Mb  +---|     +-------------------------------+
+|  class A, class B  |        |
+|                    |    +---|     +-------------------------------+
+|                    | 1  | E |     |--+                            |
+|                    | 0  | t |     |  |      Workstation1          |
+|                    | 0  | h |--+  |E |  MAC 20:cf:30:85:7d:fd     |
+|                    |Mb  | 1 |  +--|t |                            |
++-----------------------------+     |h |./tsn_listener -d \         |
+                                    |0 | 20:cf:30:85:7d:fd -i eth0 \|
+                                    |  | -s 1500                    |
+                                    |--+                            |
+                                    +-------------------------------+
+
+*********************************************************************
+*********************************************************************
+*********************************************************************
+Example 1: One port tx AVB configuration scheme for target board
+----------------------------------------------------------------------
+(prints and scheme for AM572x evm, applicable for single port boards)
+
+tc - traffic class
+txq - transmit queue
+p - priority
+f - fifo (cpsw fifo)
+S - shaper configured
+
++------------------------------------------------------------------+ u
+| +---------------+  +---------------+  +------+ +------+          | s
+| |               |  |               |  |      | |      |          | e
+| | App 1         |  | App 2         |  | Apps | | Apps |          | r
+| | Class A       |  | Class B       |  | Rest | | Rest |          |
+| | Eth0          |  | Eth0          |  | Eth0 | | Eth1 |          | s
+| | VLAN100       |  | VLAN100       |  |   |  | |   |  |          | p
+| | 40 Mb/s       |  | 20 Mb/s       |  |   |  | |   |  |          | a
+| | SO_PRIORITY=3 |  | SO_PRIORITY=2 |  |   |  | |   |  |          | c
+| |   |           |  |   |           |  |   |  | |   |  |          | e
+| +---|-----------+  +---|-----------+  +---|--+ +---|--+          |
++-----|------------------|------------------|--------|-------------+
+    +-+     +------------+                  |        |
+    |       |             +-----------------+     +--+
+    |       |             |                       |
++---|-------|-------------|-----------------------|----------------+
+| +----+ +----+ +----+ +----+                   +----+             |
+| | p3 | | p2 | | p1 | | p0 |                   | p0 |             | k
+| \    / \    / \    / \    /                   \    /             | e
+|  \  /   \  /   \  /   \  /                     \  /              | r
+|   \/     \/     \/     \/                       \/               | n
+|    |     |             |                        |                | e
+|    |     |       +-----+                        |                | l
+|    |     |       |                              |                |
+| +----+ +----+ +----+                          +----+             | s
+| |tc0 | |tc1 | |tc2 |                          |tc0 |             | p
+| \    / \    / \    /                          \    /             | a
+|  \  /   \  /   \  /                            \  /              | c
+|   \/     \/     \/                              \/               | e
+|   |      |       +-----+                        |                |
+|   |      |       |     |                        |                |
+|   |      |       |     |                        |                |
+|   |      |       |     |                        |                |
+| +----+ +----+ +----+ +----+                   +----+             |
+| |txq0| |txq1| |txq2| |txq3|                   |txq4|             |
+| \    / \    / \    / \    /                   \    /             |
+|  \  /   \  /   \  /   \  /                     \  /              |
+|   \/     \/     \/     \/                       \/               |
+| +-|------|------|------|--+                  +--|--------------+ |
+| | |      |      |      |  | Eth0.100         |  |     Eth1     | |
++---|------|------|------|------------------------|----------------+
+    |      |      |      |                        |
+    p      p      p      p                        |
+    3      2      0-1, 4-7  <- L2 priority        |
+    |      |      |      |                        |
+    |      |      |      |                        |
++---|------|------|------|------------------------|----------------+
+|   |      |      |      |             |----------+                |
+| +----+ +----+ +----+ +----+       +----+                         |
+| |dma7| |dma6| |dma5| |dma4|       |dma3|                         |
+| \    / \    / \    / \    /       \    /                         | c
+|  \S /   \S /   \  /   \  /         \  /                          | p
+|   \/     \/     \/     \/           \/                           | s
+|   |      |      | +-----            |                            | w
+|   |      |      | |                 |                            |
+|   |      |      | |                 |                            | d
+| +----+ +----+ +----+p            p+----+                         | r
+| |    | |    | |    |o            o|    |                         | i
+| | f3 | | f2 | | f0 |r            r| f0 |                         | v
+| |tc0 | |tc1 | |tc2 |t            t|tc0 |                         | e
+| \CBS / \CBS / \CBS /1            2\CBS /                         | r
+|  \S /   \S /   \  /                \  /                          |
+|   \/     \/     \/                  \/                           |
++------------------------------------------------------------------+
+========================================Eth==========================>
+
+1)
+// Add 4 tx queues, for interface Eth0, and 1 tx queue for Eth1
+$ ethtool -L eth0 rx 1 tx 5
+rx unmodified, ignoring
+
+2)
+// Check if num of queues is set correctly:
+$ ethtool -l eth0
+Channel parameters for eth0:
+Pre-set maximums:
+RX:             8
+TX:             8
+Other:          0
+Combined:       0
+Current hardware settings:
+RX:             1
+TX:             5
+Other:          0
+Combined:       0
+
+3)
+// TX queues must be rated starting from 0, so set bws for tx0 and tx1
+// Set rates 40 and 20 Mb/s appropriately.
+// Pay attention, real speed can differ a bit due to discreetness.
+// Leave last 2 tx queues not rated.
+$ echo 40 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
+$ echo 20 > /sys/class/net/eth0/queues/tx-1/tx_maxrate
+
+4)
+// Check maximum rate of tx (cpdma) queues:
+$ cat /sys/class/net/eth0/queues/tx-*/tx_maxrate
+40
+20
+0
+0
+0
+
+5)
+// Map skb->priority to traffic class:
+// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
+// Map traffic class to transmit queue:
+// tc0 -> txq0, tc1 -> txq1, tc2 -> (txq2, txq3)
+$ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
+map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@2 hw 1
+
+5a)
+// As two interface sharing same set of tx queues, assign all traffic
+// coming to interface Eth1 to separate queue in order to not mix it
+// with traffic from interface Eth0, so use separate txq to send
+// packets to Eth1, so all prio -> tc0 and tc0 -> txq4
+// Here hw 0, so here still default configuration for eth1 in hw
+$ tc qdisc replace dev eth1 handle 100: parent root mqprio num_tc 1 \
+map 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 queues 1@4 hw 0
+
+6)
+// Check classes settings
+$ tc -g class show dev eth0
++---(100:ffe2) mqprio
+|    +---(100:3) mqprio
+|    +---(100:4) mqprio
+|
++---(100:ffe1) mqprio
+|    +---(100:2) mqprio
+|
++---(100:ffe0) mqprio
+     +---(100:1) mqprio
+
+$ tc -g class show dev eth1
++---(100:ffe0) mqprio
+     +---(100:5) mqprio
+
+7)
+// Set rate for class A - 41 Mbit (tc0, txq0) using CBS Qdisc
+// Set it +1 Mb for reserve (important!)
+// here only idle slope is important, others arg are ignored
+// Pay attention, real speed can differ a bit due to discreetness
+$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1438 \
+hicredit 62 sendslope -959000 idleslope 41000 offload 1
+net eth0: set FIFO3 bw = 50
+
+8)
+// Set rate for class B - 21 Mbit (tc1, txq1) using CBS Qdisc:
+// Set it +1 Mb for reserve (important!)
+$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1468 \
+hicredit 65 sendslope -979000 idleslope 21000 offload 1
+net eth0: set FIFO2 bw = 30
+
+9)
+// Create vlan 100 to map sk->priority to vlan qos
+$ ip link add link eth0 name eth0.100 type vlan id 100
+8021q: 802.1Q VLAN Support v1.8
+8021q: adding VLAN 0 to HW filter on device eth0
+8021q: adding VLAN 0 to HW filter on device eth1
+net eth0: Adding vlanid 100 to vlan filter
+
+10)
+// Map skb->priority to L2 prio, 1 to 1
+$ ip link set eth0.100 type vlan \
+egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+11)
+// Check egress map for vlan 100
+$ cat /proc/net/vlan/eth0.100
+[...]
+INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
+EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+12)
+// Run your appropriate tools with socket option "SO_PRIORITY"
+// to 3 for class A and/or to 2 for class B
+// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p3 -s 1500&
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p2 -s 1500&
+
+13)
+// run your listener on workstation (should be in same vlan)
+// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
+./tsn_listener -d 18:03:73:66:87:42 -i enp5s0 -s 1500
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39000 kbps
+
+14)
+// Restore default configuration if needed
+$ ip link del eth0.100
+$ tc qdisc del dev eth1 root
+$ tc qdisc del dev eth0 root
+net eth0: Prev FIFO2 is shaped
+net eth0: set FIFO3 bw = 0
+net eth0: set FIFO2 bw = 0
+$ ethtool -L eth0 rx 1 tx 1
+
+*********************************************************************
+*********************************************************************
+*********************************************************************
+Example 2: Two port tx AVB configuration scheme for target board
+----------------------------------------------------------------------
+(prints and scheme for AM572x evm, for dual emac boards only)
+
++------------------------------------------------------------------+ u
+| +----------+  +----------+  +------+  +----------+  +----------+ | s
+| |          |  |          |  |      |  |          |  |          | | e
+| | App 1    |  | App 2    |  | Apps |  | App 3    |  | App 4    | | r
+| | Class A  |  | Class B  |  | Rest |  | Class B  |  | Class A  | |
+| | Eth0     |  | Eth0     |  |   |  |  | Eth1     |  | Eth1     | | s
+| | VLAN100  |  | VLAN100  |  |   |  |  | VLAN100  |  | VLAN100  | | p
+| | 40 Mb/s  |  | 20 Mb/s  |  |   |  |  | 10 Mb/s  |  | 30 Mb/s  | | a
+| | SO_PRI=3 |  | SO_PRI=2 |  |   |  |  | SO_PRI=3 |  | SO_PRI=2 | | c
+| |   |      |  |   |      |  |   |  |  |   |      |  |   |      | | e
+| +---|------+  +---|------+  +---|--+  +---|------+  +---|------+ |
++-----|-------------|-------------|---------|-------------|--------+
+    +-+     +-------+             |         +----------+  +----+
+    |       |             +-------+------+             |       |
+    |       |             |              |             |       |
++---|-------|-------------|--------------|-------------|-------|---+
+| +----+ +----+ +----+ +----+          +----+ +----+ +----+ +----+ |
+| | p3 | | p2 | | p1 | | p0 |          | p0 | | p1 | | p2 | | p3 | | k
+| \    / \    / \    / \    /          \    / \    / \    / \    / | e
+|  \  /   \  /   \  /   \  /            \  /   \  /   \  /   \  /  | r
+|   \/     \/     \/     \/              \/     \/     \/     \/   | n
+|   |      |             |                |             |      |   | e
+|   |      |        +----+                +----+        |      |   | l
+|   |      |        |                          |        |      |   |
+| +----+ +----+ +----+                        +----+ +----+ +----+ | s
+| |tc0 | |tc1 | |tc2 |                        |tc2 | |tc1 | |tc0 | | p
+| \    / \    / \    /                        \    / \    / \    / | a
+|  \  /   \  /   \  /                          \  /   \  /   \  /  | c
+|   \/     \/     \/                            \/     \/     \/   | e
+|   |      |       +-----+                +-----+      |       |   |
+|   |      |       |     |                |     |      |       |   |
+|   |      |       |     |                |     |      |       |   |
+|   |      |       |     |    E      E    |     |      |       |   |
+| +----+ +----+ +----+ +----+ t      t +----+ +----+ +----+ +----+ |
+| |txq0| |txq1| |txq4| |txq5| h      h |txq6| |txq7| |txq3| |txq2| |
+| \    / \    / \    / \    / 0      1 \    / \    / \    / \    / |
+|  \  /   \  /   \  /   \  /  .      .  \  /   \  /   \  /   \  /  |
+|   \/     \/     \/     \/   1      1   \/     \/     \/     \/   |
+| +-|------|------|------|--+ 0      0 +-|------|------|------|--+ |
+| | |      |      |      |  | 0      0 | |      |      |      |  | |
++---|------|------|------|---------------|------|------|------|----+
+    |      |      |      |               |      |      |      |
+    p      p      p      p               p      p      p      p
+    3      2      0-1, 4-7   <-L2 pri->  0-1, 4-7      2      3
+    |      |      |      |               |      |      |      |
+    |      |      |      |               |      |      |      |
++---|------|------|------|---------------|------|------|------|----+
+|   |      |      |      |               |      |      |      |    |
+| +----+ +----+ +----+ +----+          +----+ +----+ +----+ +----+ |
+| |dma7| |dma6| |dma3| |dma2|          |dma1| |dma0| |dma4| |dma5| |
+| \    / \    / \    / \    /          \    / \    / \    / \    / | c
+|  \S /   \S /   \  /   \  /            \  /   \  /   \S /   \S /  | p
+|   \/     \/     \/     \/              \/     \/     \/     \/   | s
+|   |      |      | +-----                |      |      |      |   | w
+|   |      |      | |                     +----+ |      |      |   |
+|   |      |      | |                          | |      |      |   | d
+| +----+ +----+ +----+p                      p+----+ +----+ +----+ | r
+| |    | |    | |    |o                      o|    | |    | |    | | i
+| | f3 | | f2 | | f0 |r        CPSW          r| f3 | | f2 | | f0 | | v
+| |tc0 | |tc1 | |tc2 |t                      t|tc0 | |tc1 | |tc2 | | e
+| \CBS / \CBS / \CBS /1                      2\CBS / \CBS / \CBS / | r
+|  \S /   \S /   \  /                          \S /   \S /   \  /  |
+|   \/     \/     \/                            \/     \/     \/   |
++------------------------------------------------------------------+
+========================================Eth==========================>
+
+1)
+// Add 8 tx queues, for interface Eth0, but they are common, so are accessed
+// by two interfaces Eth0 and Eth1.
+$ ethtool -L eth1 rx 1 tx 8
+rx unmodified, ignoring
+
+2)
+// Check if num of queues is set correctly:
+$ ethtool -l eth0
+Channel parameters for eth0:
+Pre-set maximums:
+RX:             8
+TX:             8
+Other:          0
+Combined:       0
+Current hardware settings:
+RX:             1
+TX:             8
+Other:          0
+Combined:       0
+
+3)
+// TX queues must be rated starting from 0, so set bws for tx0 and tx1 for Eth0
+// and for tx2 and tx3 for Eth1. That is, rates 40 and 20 Mb/s appropriately
+// for Eth0 and 30 and 10 Mb/s for Eth1.
+// Real speed can differ a bit due to discreetness
+// Leave last 4 tx queues as not rated
+$ echo 40 > /sys/class/net/eth0/queues/tx-0/tx_maxrate
+$ echo 20 > /sys/class/net/eth0/queues/tx-1/tx_maxrate
+$ echo 30 > /sys/class/net/eth1/queues/tx-2/tx_maxrate
+$ echo 10 > /sys/class/net/eth1/queues/tx-3/tx_maxrate
+
+4)
+// Check maximum rate of tx (cpdma) queues:
+$ cat /sys/class/net/eth0/queues/tx-*/tx_maxrate
+40
+20
+30
+10
+0
+0
+0
+0
+
+5)
+// Map skb->priority to traffic class for Eth0:
+// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
+// Map traffic class to transmit queue:
+// tc0 -> txq0, tc1 -> txq1, tc2 -> (txq4, txq5)
+$ tc qdisc replace dev eth0 handle 100: parent root mqprio num_tc 3 \
+map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@0 1@1 2@4 hw 1
+
+6)
+// Check classes settings
+$ tc -g class show dev eth0
++---(100:ffe2) mqprio
+|    +---(100:5) mqprio
+|    +---(100:6) mqprio
+|
++---(100:ffe1) mqprio
+|    +---(100:2) mqprio
+|
++---(100:ffe0) mqprio
+     +---(100:1) mqprio
+
+7)
+// Set rate for class A - 41 Mbit (tc0, txq0) using CBS Qdisc for Eth0
+// here only idle slope is important, others ignored
+// Real speed can differ a bit due to discreetness
+$ tc qdisc add dev eth0 parent 100:1 cbs locredit -1470 \
+hicredit 62 sendslope -959000 idleslope 41000 offload 1
+net eth0: set FIFO3 bw = 50
+
+8)
+// Set rate for class B - 21 Mbit (tc1, txq1) using CBS Qdisc for Eth0
+$ tc qdisc add dev eth0 parent 100:2 cbs locredit -1470 \
+hicredit 65 sendslope -979000 idleslope 21000 offload 1
+net eth0: set FIFO2 bw = 30
+
+9)
+// Create vlan 100 to map sk->priority to vlan qos for Eth0
+$ ip link add link eth0 name eth0.100 type vlan id 100
+net eth0: Adding vlanid 100 to vlan filter
+
+10)
+// Map skb->priority to L2 prio for Eth0.100, one to one
+$ ip link set eth0.100 type vlan \
+egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+11)
+// Check egress map for vlan 100
+$ cat /proc/net/vlan/eth0.100
+[...]
+INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
+EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+12)
+// Map skb->priority to traffic class for Eth1:
+// 3pri -> tc0, 2pri -> tc1, (0,1,4-7)pri -> tc2
+// Map traffic class to transmit queue:
+// tc0 -> txq2, tc1 -> txq3, tc2 -> (txq6, txq7)
+$ tc qdisc replace dev eth1 handle 100: parent root mqprio num_tc 3 \
+map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 queues 1@2 1@3 2@6 hw 1
+
+13)
+// Check classes settings
+$ tc -g class show dev eth1
++---(100:ffe2) mqprio
+|    +---(100:7) mqprio
+|    +---(100:8) mqprio
+|
++---(100:ffe1) mqprio
+|    +---(100:4) mqprio
+|
++---(100:ffe0) mqprio
+     +---(100:3) mqprio
+
+14)
+// Set rate for class A - 31 Mbit (tc0, txq2) using CBS Qdisc for Eth1
+// here only idle slope is important, others ignored
+// Set it +1 Mb for reserve (important!)
+$ tc qdisc add dev eth1 parent 100:3 cbs locredit -1453 \
+hicredit 47 sendslope -969000 idleslope 31000 offload 1
+net eth1: set FIFO3 bw = 31
+
+15)
+// Set rate for class B - 11 Mbit (tc1, txq3) using CBS Qdisc for Eth1
+// Set it +1 Mb for reserve (important!)
+$ tc qdisc add dev eth1 parent 100:4 cbs locredit -1483 \
+hicredit 34 sendslope -989000 idleslope 11000 offload 1
+net eth1: set FIFO2 bw = 11
+
+16)
+// Create vlan 100 to map sk->priority to vlan qos for Eth1
+$ ip link add link eth1 name eth1.100 type vlan id 100
+net eth1: Adding vlanid 100 to vlan filter
+
+17)
+// Map skb->priority to L2 prio for Eth1.100, one to one
+$ ip link set eth1.100 type vlan \
+egress 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+18)
+// Check egress map for vlan 100
+$ cat /proc/net/vlan/eth1.100
+[...]
+INGRESS priority mappings: 0:0  1:0  2:0  3:0  4:0  5:0  6:0 7:0
+EGRESS priority mappings: 0:0 1:1 2:2 3:3 4:4 5:5 6:6 7:7
+
+19)
+// Run appropriate tools with socket option "SO_PRIORITY" to 3
+// for class A and to 2 for class B. For both interfaces
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p2 -s 1500&
+./tsn_talker -d 18:03:73:66:87:42 -i eth0.100 -p3 -s 1500&
+./tsn_talker -d 20:cf:30:85:7d:fd -i eth1.100 -p2 -s 1500&
+./tsn_talker -d 20:cf:30:85:7d:fd -i eth1.100 -p3 -s 1500&
+
+20)
+// run your listener on workstation (should be in same vlan)
+// (I took at https://www.spinics.net/lists/netdev/msg460869.html)
+./tsn_listener -d 18:03:73:66:87:42 -i enp5s0 -s 1500
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39012 kbps
+Receiving data rate: 39000 kbps
+
+21)
+// Restore default configuration if needed
+$ ip link del eth1.100
+$ ip link del eth0.100
+$ tc qdisc del dev eth1 root
+net eth1: Prev FIFO2 is shaped
+net eth1: set FIFO3 bw = 0
+net eth1: set FIFO2 bw = 0
+$ tc qdisc del dev eth0 root
+net eth0: Prev FIFO2 is shaped
+net eth0: set FIFO3 bw = 0
+net eth0: set FIFO2 bw = 0
+$ ethtool -L eth0 rx 1 tx 1
-- 
cgit v1.2.3


From f34e8bff58f071e1a3452a5a6e29dac218c83f69 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:04 +0200
Subject: net: sched: push ops lookup bits into tcf_proto_lookup_ops()

Push all bits that take care of ops lookup, including module loading
outside tcf_proto_create() function, into tcf_proto_lookup_ops()

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 53 +++++++++++++++++++++++++++++++----------------------
 1 file changed, 31 insertions(+), 22 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 620067209ba8..1e8d69790d82 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -39,7 +39,7 @@ static DEFINE_RWLOCK(cls_mod_lock);
 
 /* Find classifier type by string name */
 
-static const struct tcf_proto_ops *tcf_proto_lookup_ops(const char *kind)
+static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind)
 {
 	const struct tcf_proto_ops *t, *res = NULL;
 
@@ -57,6 +57,33 @@ static const struct tcf_proto_ops *tcf_proto_lookup_ops(const char *kind)
 	return res;
 }
 
+static const struct tcf_proto_ops *
+tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack)
+{
+	const struct tcf_proto_ops *ops;
+
+	ops = __tcf_proto_lookup_ops(kind);
+	if (ops)
+		return ops;
+#ifdef CONFIG_MODULES
+	rtnl_unlock();
+	request_module("cls_%s", kind);
+	rtnl_lock();
+	ops = __tcf_proto_lookup_ops(kind);
+	/* We dropped the RTNL semaphore in order to perform
+	 * the module load. So, even if we succeeded in loading
+	 * the module we have to replay the request. We indicate
+	 * this using -EAGAIN.
+	 */
+	if (ops) {
+		module_put(ops->owner);
+		return ERR_PTR(-EAGAIN);
+	}
+#endif
+	NL_SET_ERR_MSG(extack, "TC classifier not found");
+	return ERR_PTR(-ENOENT);
+}
+
 /* Register(unregister) new classifier type */
 
 int register_tcf_proto_ops(struct tcf_proto_ops *ops)
@@ -133,27 +160,9 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol,
 	if (!tp)
 		return ERR_PTR(-ENOBUFS);
 
-	err = -ENOENT;
-	tp->ops = tcf_proto_lookup_ops(kind);
-	if (!tp->ops) {
-#ifdef CONFIG_MODULES
-		rtnl_unlock();
-		request_module("cls_%s", kind);
-		rtnl_lock();
-		tp->ops = tcf_proto_lookup_ops(kind);
-		/* We dropped the RTNL semaphore in order to perform
-		 * the module load. So, even if we succeeded in loading
-		 * the module we have to replay the request. We indicate
-		 * this using -EAGAIN.
-		 */
-		if (tp->ops) {
-			module_put(tp->ops->owner);
-			err = -EAGAIN;
-		} else {
-			NL_SET_ERR_MSG(extack, "TC classifier not found");
-			err = -ENOENT;
-		}
-#endif
+	tp->ops = tcf_proto_lookup_ops(kind, extack);
+	if (IS_ERR(tp->ops)) {
+		err = PTR_ERR(tp->ops);
 		goto errout;
 	}
 	tp->classify = tp->ops->classify;
-- 
cgit v1.2.3


From f71e0ca4db187af7c44987e9d21e9042c3046070 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:05 +0200
Subject: net: sched: Avoid implicit chain 0 creation

Currently, chain 0 is implicitly created during block creation. However
that does not align with chain object exposure, creation and destruction
api introduced later on. So make the chain 0 behave the same way as any
other chain and only create it when it is needed. Since chain 0 is
somehow special as the qdiscs need to hold pointer to the first chain
tp, this requires to move the chain head change callback infra to the
block structure.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h |  5 ++-
 net/sched/cls_api.c       | 86 +++++++++++++++++++++--------------------------
 2 files changed, 43 insertions(+), 48 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 7432100027b7..86f4651784e8 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -300,7 +300,6 @@ typedef void tcf_chain_head_change_t(struct tcf_proto *tp_head, void *priv);
 
 struct tcf_chain {
 	struct tcf_proto __rcu *filter_chain;
-	struct list_head filter_chain_list;
 	struct list_head list;
 	struct tcf_block *block;
 	u32 index; /* chain index */
@@ -318,6 +317,10 @@ struct tcf_block {
 	bool keep_dst;
 	unsigned int offloadcnt; /* Number of oddloaded filters */
 	unsigned int nooffloaddevcnt; /* Number of devs unable to do offload */
+	struct {
+		struct tcf_chain *chain;
+		struct list_head filter_chain_list;
+	} chain0;
 };
 
 static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 1e8d69790d82..eb0bf9037ef9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -204,11 +204,12 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block,
 	chain = kzalloc(sizeof(*chain), GFP_KERNEL);
 	if (!chain)
 		return NULL;
-	INIT_LIST_HEAD(&chain->filter_chain_list);
 	list_add_tail(&chain->list, &block->chain_list);
 	chain->block = block;
 	chain->index = chain_index;
 	chain->refcnt = 1;
+	if (!chain->index)
+		block->chain0.chain = chain;
 	return chain;
 }
 
@@ -218,12 +219,16 @@ static void tcf_chain_head_change_item(struct tcf_filter_chain_list_item *item,
 	if (item->chain_head_change)
 		item->chain_head_change(tp_head, item->chain_head_change_priv);
 }
-static void tcf_chain_head_change(struct tcf_chain *chain,
-				  struct tcf_proto *tp_head)
+
+static void tcf_chain0_head_change(struct tcf_chain *chain,
+				   struct tcf_proto *tp_head)
 {
 	struct tcf_filter_chain_list_item *item;
+	struct tcf_block *block = chain->block;
 
-	list_for_each_entry(item, &chain->filter_chain_list, list)
+	if (chain->index)
+		return;
+	list_for_each_entry(item, &block->chain0.filter_chain_list, list)
 		tcf_chain_head_change_item(item, tp_head);
 }
 
@@ -231,7 +236,7 @@ static void tcf_chain_flush(struct tcf_chain *chain)
 {
 	struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);
 
-	tcf_chain_head_change(chain, NULL);
+	tcf_chain0_head_change(chain, NULL);
 	while (tp) {
 		RCU_INIT_POINTER(chain->filter_chain, tp->next);
 		tcf_proto_destroy(tp, NULL);
@@ -245,8 +250,10 @@ static void tcf_chain_destroy(struct tcf_chain *chain)
 	struct tcf_block *block = chain->block;
 
 	list_del(&chain->list);
+	if (!chain->index)
+		block->chain0.chain = NULL;
 	kfree(chain);
-	if (list_empty(&block->chain_list))
+	if (list_empty(&block->chain_list) && block->refcnt == 0)
 		kfree(block);
 }
 
@@ -346,10 +353,11 @@ no_offload_dev_dec:
 }
 
 static int
-tcf_chain_head_change_cb_add(struct tcf_chain *chain,
-			     struct tcf_block_ext_info *ei,
-			     struct netlink_ext_ack *extack)
+tcf_chain0_head_change_cb_add(struct tcf_block *block,
+			      struct tcf_block_ext_info *ei,
+			      struct netlink_ext_ack *extack)
 {
+	struct tcf_chain *chain0 = block->chain0.chain;
 	struct tcf_filter_chain_list_item *item;
 
 	item = kmalloc(sizeof(*item), GFP_KERNEL);
@@ -359,23 +367,25 @@ tcf_chain_head_change_cb_add(struct tcf_chain *chain,
 	}
 	item->chain_head_change = ei->chain_head_change;
 	item->chain_head_change_priv = ei->chain_head_change_priv;
-	if (chain->filter_chain)
-		tcf_chain_head_change_item(item, chain->filter_chain);
-	list_add(&item->list, &chain->filter_chain_list);
+	if (chain0 && chain0->filter_chain)
+		tcf_chain_head_change_item(item, chain0->filter_chain);
+	list_add(&item->list, &block->chain0.filter_chain_list);
 	return 0;
 }
 
 static void
-tcf_chain_head_change_cb_del(struct tcf_chain *chain,
-			     struct tcf_block_ext_info *ei)
+tcf_chain0_head_change_cb_del(struct tcf_block *block,
+			      struct tcf_block_ext_info *ei)
 {
+	struct tcf_chain *chain0 = block->chain0.chain;
 	struct tcf_filter_chain_list_item *item;
 
-	list_for_each_entry(item, &chain->filter_chain_list, list) {
+	list_for_each_entry(item, &block->chain0.filter_chain_list, list) {
 		if ((!ei->chain_head_change && !ei->chain_head_change_priv) ||
 		    (item->chain_head_change == ei->chain_head_change &&
 		     item->chain_head_change_priv == ei->chain_head_change_priv)) {
-			tcf_chain_head_change_item(item, NULL);
+			if (chain0)
+				tcf_chain_head_change_item(item, NULL);
 			list_del(&item->list);
 			kfree(item);
 			return;
@@ -411,8 +421,6 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 					  struct netlink_ext_ack *extack)
 {
 	struct tcf_block *block;
-	struct tcf_chain *chain;
-	int err;
 
 	block = kzalloc(sizeof(*block), GFP_KERNEL);
 	if (!block) {
@@ -422,14 +430,8 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	INIT_LIST_HEAD(&block->chain_list);
 	INIT_LIST_HEAD(&block->cb_list);
 	INIT_LIST_HEAD(&block->owner_list);
+	INIT_LIST_HEAD(&block->chain0.filter_chain_list);
 
-	/* Create chain 0 by default, it has to be always present. */
-	chain = tcf_chain_create(block, 0);
-	if (!chain) {
-		NL_SET_ERR_MSG(extack, "Failed to create new tcf chain");
-		err = -ENOMEM;
-		goto err_chain_create;
-	}
 	block->refcnt = 1;
 	block->net = net;
 	block->index = block_index;
@@ -438,10 +440,6 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q,
 	if (!tcf_block_shared(block))
 		block->q = q;
 	return block;
-
-err_chain_create:
-	kfree(block);
-	return ERR_PTR(err);
 }
 
 static struct tcf_block *tcf_block_lookup(struct net *net, u32 block_index)
@@ -523,11 +521,6 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
 	return block;
 }
 
-static struct tcf_chain *tcf_block_chain_zero(struct tcf_block *block)
-{
-	return list_first_entry(&block->chain_list, struct tcf_chain, list);
-}
-
 struct tcf_block_owner_item {
 	struct list_head list;
 	struct Qdisc *q;
@@ -621,10 +614,9 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 
 	tcf_block_owner_netif_keep_dst(block, q, ei->binder_type);
 
-	err = tcf_chain_head_change_cb_add(tcf_block_chain_zero(block),
-					   ei, extack);
+	err = tcf_chain0_head_change_cb_add(block, ei, extack);
 	if (err)
-		goto err_chain_head_change_cb_add;
+		goto err_chain0_head_change_cb_add;
 
 	err = tcf_block_offload_bind(block, q, ei, extack);
 	if (err)
@@ -634,15 +626,14 @@ int tcf_block_get_ext(struct tcf_block **p_block, struct Qdisc *q,
 	return 0;
 
 err_block_offload_bind:
-	tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei);
-err_chain_head_change_cb_add:
+	tcf_chain0_head_change_cb_del(block, ei);
+err_chain0_head_change_cb_add:
 	tcf_block_owner_del(block, q, ei->binder_type);
 err_block_owner_add:
 	if (created) {
 		if (tcf_block_shared(block))
 			tcf_block_remove(block, net);
 err_block_insert:
-		kfree(tcf_block_chain_zero(block));
 		kfree(block);
 	} else {
 		block->refcnt--;
@@ -682,10 +673,10 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 	if (!block)
 		return;
-	tcf_chain_head_change_cb_del(tcf_block_chain_zero(block), ei);
+	tcf_chain0_head_change_cb_del(block, ei);
 	tcf_block_owner_del(block, q, ei->binder_type);
 
-	if (--block->refcnt == 0) {
+	if (block->refcnt == 1) {
 		if (tcf_block_shared(block))
 			tcf_block_remove(block, block->net);
 
@@ -701,13 +692,14 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 	tcf_block_offload_unbind(block, q, ei);
 
-	if (block->refcnt == 0) {
+	if (block->refcnt == 1) {
 		/* At this point, all the chains should have refcnt >= 1. */
 		list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
 			tcf_chain_put(chain);
 
-		/* Finally, put chain 0 and allow block to be freed. */
-		tcf_chain_put(tcf_block_chain_zero(block));
+		block->refcnt--;
+		if (list_empty(&block->chain_list))
+			kfree(block);
 	}
 }
 EXPORT_SYMBOL(tcf_block_put_ext);
@@ -947,7 +939,7 @@ static void tcf_chain_tp_insert(struct tcf_chain *chain,
 				struct tcf_proto *tp)
 {
 	if (*chain_info->pprev == chain->filter_chain)
-		tcf_chain_head_change(chain, tp);
+		tcf_chain0_head_change(chain, tp);
 	RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info));
 	rcu_assign_pointer(*chain_info->pprev, tp);
 	tcf_chain_hold(chain);
@@ -960,7 +952,7 @@ static void tcf_chain_tp_remove(struct tcf_chain *chain,
 	struct tcf_proto *next = rtnl_dereference(chain_info->next);
 
 	if (tp == chain->filter_chain)
-		tcf_chain_head_change(chain, next);
+		tcf_chain0_head_change(chain, next);
 	RCU_INIT_POINTER(*chain_info->pprev, next);
 	tcf_chain_put(chain);
 }
-- 
cgit v1.2.3


From 32a4f5ecd7381f30ae3bb36dea77a150ba68af2e Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:06 +0200
Subject: net: sched: introduce chain object to uapi

Allow user to create, destroy, get and dump chain objects. Do that by
extending rtnl commands by the chain-specific ones. User will now be
able to explicitly create or destroy chains (so far this was done only
automatically according the filter/act needs and refcounting). Also, the
user will receive notification about any chain creation or destuction.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h      |   1 +
 include/uapi/linux/rtnetlink.h |   7 +
 net/sched/cls_api.c            | 308 +++++++++++++++++++++++++++++++++++++++--
 security/selinux/nlmsgtab.c    |   2 +-
 4 files changed, 309 insertions(+), 9 deletions(-)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 86f4651784e8..81ec8276db9c 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -304,6 +304,7 @@ struct tcf_chain {
 	struct tcf_block *block;
 	u32 index; /* chain index */
 	unsigned int refcnt;
+	bool explicitly_created;
 };
 
 struct tcf_block {
diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 7d8502313c99..46399367627f 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -150,6 +150,13 @@ enum {
 	RTM_NEWCACHEREPORT = 96,
 #define RTM_NEWCACHEREPORT RTM_NEWCACHEREPORT
 
+	RTM_NEWCHAIN = 100,
+#define RTM_NEWCHAIN RTM_NEWCHAIN
+	RTM_DELCHAIN,
+#define RTM_DELCHAIN RTM_DELCHAIN
+	RTM_GETCHAIN,
+#define RTM_GETCHAIN RTM_GETCHAIN
+
 	__RTM_MAX,
 #define RTM_MAX		(((__RTM_MAX + 3) & ~3) - 1)
 };
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index eb0bf9037ef9..e65b390336aa 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -262,29 +262,57 @@ static void tcf_chain_hold(struct tcf_chain *chain)
 	++chain->refcnt;
 }
 
-struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
-				bool create)
+static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
+					  u32 chain_index)
 {
 	struct tcf_chain *chain;
 
 	list_for_each_entry(chain, &block->chain_list, list) {
-		if (chain->index == chain_index) {
-			tcf_chain_hold(chain);
+		if (chain->index == chain_index)
 			return chain;
-		}
+	}
+	return NULL;
+}
+
+static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
+			   u32 seq, u16 flags, int event, bool unicast);
+
+struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
+				bool create)
+{
+	struct tcf_chain *chain = tcf_chain_lookup(block, chain_index);
+
+	if (chain) {
+		tcf_chain_hold(chain);
+		return chain;
 	}
 
-	return create ? tcf_chain_create(block, chain_index) : NULL;
+	if (!create)
+		return NULL;
+	chain = tcf_chain_create(block, chain_index);
+	if (!chain)
+		return NULL;
+	tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
+			RTM_NEWCHAIN, false);
+	return chain;
 }
 EXPORT_SYMBOL(tcf_chain_get);
 
 void tcf_chain_put(struct tcf_chain *chain)
 {
-	if (--chain->refcnt == 0)
+	if (--chain->refcnt == 0) {
+		tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false);
 		tcf_chain_destroy(chain);
+	}
 }
 EXPORT_SYMBOL(tcf_chain_put);
 
+static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
+{
+	if (chain->explicitly_created)
+		tcf_chain_put(chain);
+}
+
 static bool tcf_block_offload_in_use(struct tcf_block *block)
 {
 	return block->offloadcnt;
@@ -694,8 +722,10 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 
 	if (block->refcnt == 1) {
 		/* At this point, all the chains should have refcnt >= 1. */
-		list_for_each_entry_safe(chain, tmp, &block->chain_list, list)
+		list_for_each_entry_safe(chain, tmp, &block->chain_list, list) {
+			tcf_chain_put_explicitly_created(chain);
 			tcf_chain_put(chain);
+		}
 
 		block->refcnt--;
 		if (list_empty(&block->chain_list))
@@ -1609,6 +1639,264 @@ out:
 	return skb->len;
 }
 
+static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net,
+			      struct sk_buff *skb, struct tcf_block *block,
+			      u32 portid, u32 seq, u16 flags, int event)
+{
+	unsigned char *b = skb_tail_pointer(skb);
+	struct nlmsghdr *nlh;
+	struct tcmsg *tcm;
+
+	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
+	if (!nlh)
+		goto out_nlmsg_trim;
+	tcm = nlmsg_data(nlh);
+	tcm->tcm_family = AF_UNSPEC;
+	tcm->tcm__pad1 = 0;
+	tcm->tcm__pad2 = 0;
+	tcm->tcm_handle = 0;
+	if (block->q) {
+		tcm->tcm_ifindex = qdisc_dev(block->q)->ifindex;
+		tcm->tcm_parent = block->q->handle;
+	} else {
+		tcm->tcm_ifindex = TCM_IFINDEX_MAGIC_BLOCK;
+		tcm->tcm_block_index = block->index;
+	}
+
+	if (nla_put_u32(skb, TCA_CHAIN, chain->index))
+		goto nla_put_failure;
+
+	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+	return skb->len;
+
+out_nlmsg_trim:
+nla_put_failure:
+	nlmsg_trim(skb, b);
+	return -EMSGSIZE;
+}
+
+static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
+			   u32 seq, u16 flags, int event, bool unicast)
+{
+	u32 portid = oskb ? NETLINK_CB(oskb).portid : 0;
+	struct tcf_block *block = chain->block;
+	struct net *net = block->net;
+	struct sk_buff *skb;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return -ENOBUFS;
+
+	if (tc_chain_fill_node(chain, net, skb, block, portid,
+			       seq, flags, event) <= 0) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
+
+	if (unicast)
+		return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT);
+
+	return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
+}
+
+/* Add/delete/get a chain */
+
+static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
+			struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tca[TCA_MAX + 1];
+	struct tcmsg *t;
+	u32 parent;
+	u32 chain_index;
+	struct Qdisc *q = NULL;
+	struct tcf_chain *chain = NULL;
+	struct tcf_block *block;
+	unsigned long cl;
+	int err;
+
+	if (n->nlmsg_type != RTM_GETCHAIN &&
+	    !netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+replay:
+	err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, NULL, extack);
+	if (err < 0)
+		return err;
+
+	t = nlmsg_data(n);
+	parent = t->tcm_parent;
+	cl = 0;
+
+	block = tcf_block_find(net, &q, &parent, &cl,
+			       t->tcm_ifindex, t->tcm_block_index, extack);
+	if (IS_ERR(block))
+		return PTR_ERR(block);
+
+	chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
+	if (chain_index > TC_ACT_EXT_VAL_MASK) {
+		NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
+		return -EINVAL;
+	}
+	chain = tcf_chain_lookup(block, chain_index);
+	if (n->nlmsg_type == RTM_NEWCHAIN) {
+		if (chain) {
+			NL_SET_ERR_MSG(extack, "Filter chain already exists");
+			return -EEXIST;
+		}
+		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+			NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
+			return -ENOENT;
+		}
+		chain = tcf_chain_create(block, chain_index);
+		if (!chain) {
+			NL_SET_ERR_MSG(extack, "Failed to create filter chain");
+			return -ENOMEM;
+		}
+	} else {
+		if (!chain) {
+			NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
+			return -EINVAL;
+		}
+		tcf_chain_hold(chain);
+	}
+
+	switch (n->nlmsg_type) {
+	case RTM_NEWCHAIN:
+		/* In case the chain was successfully added, take a reference
+		 * to the chain. This ensures that an empty chain
+		 * does not disappear at the end of this function.
+		 */
+		tcf_chain_hold(chain);
+		chain->explicitly_created = true;
+		tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
+				RTM_NEWCHAIN, false);
+		break;
+	case RTM_DELCHAIN:
+		/* Flush the chain first as the user requested chain removal. */
+		tcf_chain_flush(chain);
+		/* In case the chain was successfully deleted, put a reference
+		 * to the chain previously taken during addition.
+		 */
+		tcf_chain_put_explicitly_created(chain);
+		break;
+	case RTM_GETCHAIN:
+		break;
+		err = tc_chain_notify(chain, skb, n->nlmsg_seq,
+				      n->nlmsg_seq, n->nlmsg_type, true);
+		if (err < 0)
+			NL_SET_ERR_MSG(extack, "Failed to send chain notify message");
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		NL_SET_ERR_MSG(extack, "Unsupported message type");
+		goto errout;
+	}
+
+errout:
+	tcf_chain_put(chain);
+	if (err == -EAGAIN)
+		/* Replay the request. */
+		goto replay;
+	return err;
+}
+
+/* called with RTNL */
+static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tca[TCA_MAX + 1];
+	struct Qdisc *q = NULL;
+	struct tcf_block *block;
+	struct tcf_chain *chain;
+	struct tcmsg *tcm = nlmsg_data(cb->nlh);
+	long index_start;
+	long index;
+	u32 parent;
+	int err;
+
+	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
+		return skb->len;
+
+	err = nlmsg_parse(cb->nlh, sizeof(*tcm), tca, TCA_MAX, NULL, NULL);
+	if (err)
+		return err;
+
+	if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
+		block = tcf_block_lookup(net, tcm->tcm_block_index);
+		if (!block)
+			goto out;
+		/* If we work with block index, q is NULL and parent value
+		 * will never be used in the following code. The check
+		 * in tcf_fill_node prevents it. However, compiler does not
+		 * see that far, so set parent to zero to silence the warning
+		 * about parent being uninitialized.
+		 */
+		parent = 0;
+	} else {
+		const struct Qdisc_class_ops *cops;
+		struct net_device *dev;
+		unsigned long cl = 0;
+
+		dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+		if (!dev)
+			return skb->len;
+
+		parent = tcm->tcm_parent;
+		if (!parent) {
+			q = dev->qdisc;
+			parent = q->handle;
+		} else {
+			q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent));
+		}
+		if (!q)
+			goto out;
+		cops = q->ops->cl_ops;
+		if (!cops)
+			goto out;
+		if (!cops->tcf_block)
+			goto out;
+		if (TC_H_MIN(tcm->tcm_parent)) {
+			cl = cops->find(q, tcm->tcm_parent);
+			if (cl == 0)
+				goto out;
+		}
+		block = cops->tcf_block(q, cl, NULL);
+		if (!block)
+			goto out;
+		if (tcf_block_shared(block))
+			q = NULL;
+	}
+
+	index_start = cb->args[0];
+	index = 0;
+
+	list_for_each_entry(chain, &block->chain_list, list) {
+		if ((tca[TCA_CHAIN] &&
+		     nla_get_u32(tca[TCA_CHAIN]) != chain->index))
+			continue;
+		if (index < index_start) {
+			index++;
+			continue;
+		}
+		err = tc_chain_fill_node(chain, net, skb, block,
+					 NETLINK_CB(cb->skb).portid,
+					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
+					 RTM_NEWCHAIN);
+		if (err <= 0)
+			break;
+		index++;
+	}
+
+	cb->args[0] = index;
+
+out:
+	/* If we did no progress, the error (EMSGSIZE) is real */
+	if (skb->len == 0 && err)
+		return err;
+	return skb->len;
+}
+
 void tcf_exts_destroy(struct tcf_exts *exts)
 {
 #ifdef CONFIG_NET_CLS_ACT
@@ -1825,6 +2113,10 @@ static int __init tc_filter_init(void)
 	rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0);
 	rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter,
 		      tc_dump_tfilter, 0);
+	rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0);
+	rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0);
+	rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain,
+		      tc_dump_chain, 0);
 
 	return 0;
 
diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c
index 7b7433a1a34c..74b951f55608 100644
--- a/security/selinux/nlmsgtab.c
+++ b/security/selinux/nlmsgtab.c
@@ -159,7 +159,7 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm)
 	switch (sclass) {
 	case SECCLASS_NETLINK_ROUTE_SOCKET:
 		/* RTM_MAX always point to RTM_SETxxxx, ie RTM_NEWxxx + 3 */
-		BUILD_BUG_ON(RTM_MAX != (RTM_NEWCACHEREPORT + 3));
+		BUILD_BUG_ON(RTM_MAX != (RTM_NEWCHAIN + 3));
 		err = nlmsg_perm(nlmsg_type, perm, nlmsg_route_perms,
 				 sizeof(nlmsg_route_perms));
 		break;
-- 
cgit v1.2.3


From 9f407f1768d3e1a5ddd7bd49fa4d1f5a26e10ed2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:07 +0200
Subject: net: sched: introduce chain templates

Allow user to set a template for newly created chains. Template lock
down the chain for particular classifier type/options combinations.
The classifier needs to support templates, otherwise kernel would
reply with error.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sch_generic.h | 12 +++++++++
 net/sched/cls_api.c       | 65 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 77 insertions(+)

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 81ec8276db9c..085c509c8674 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -238,6 +238,8 @@ struct tcf_result {
 	};
 };
 
+struct tcf_chain;
+
 struct tcf_proto_ops {
 	struct list_head	head;
 	char			kind[IFNAMSIZ];
@@ -263,10 +265,18 @@ struct tcf_proto_ops {
 					     tc_setup_cb_t *cb, void *cb_priv,
 					     struct netlink_ext_ack *extack);
 	void			(*bind_class)(void *, u32, unsigned long);
+	void *			(*tmplt_create)(struct net *net,
+						struct tcf_chain *chain,
+						struct nlattr **tca,
+						struct netlink_ext_ack *extack);
+	void			(*tmplt_destroy)(void *tmplt_priv);
 
 	/* rtnetlink specific */
 	int			(*dump)(struct net*, struct tcf_proto*, void *,
 					struct sk_buff *skb, struct tcmsg*);
+	int			(*tmplt_dump)(struct sk_buff *skb,
+					      struct net *net,
+					      void *tmplt_priv);
 
 	struct module		*owner;
 };
@@ -305,6 +315,8 @@ struct tcf_chain {
 	u32 index; /* chain index */
 	unsigned int refcnt;
 	bool explicitly_created;
+	const struct tcf_proto_ops *tmplt_ops;
+	void *tmplt_priv;
 };
 
 struct tcf_block {
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e65b390336aa..5f7098b5405e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -298,10 +298,13 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
 }
 EXPORT_SYMBOL(tcf_chain_get);
 
+static void tc_chain_tmplt_del(struct tcf_chain *chain);
+
 void tcf_chain_put(struct tcf_chain *chain)
 {
 	if (--chain->refcnt == 0) {
 		tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false);
+		tc_chain_tmplt_del(chain);
 		tcf_chain_destroy(chain);
 	}
 }
@@ -1258,6 +1261,12 @@ replay:
 		goto errout;
 	}
 
+	if (chain->tmplt_ops && chain->tmplt_ops != tp->ops) {
+		NL_SET_ERR_MSG(extack, "Chain template is set to a different filter kind");
+		err = -EINVAL;
+		goto errout;
+	}
+
 	err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh,
 			      n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE,
 			      extack);
@@ -1644,8 +1653,13 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net,
 			      u32 portid, u32 seq, u16 flags, int event)
 {
 	unsigned char *b = skb_tail_pointer(skb);
+	const struct tcf_proto_ops *ops;
 	struct nlmsghdr *nlh;
 	struct tcmsg *tcm;
+	void *priv;
+
+	ops = chain->tmplt_ops;
+	priv = chain->tmplt_priv;
 
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags);
 	if (!nlh)
@@ -1666,6 +1680,13 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net,
 	if (nla_put_u32(skb, TCA_CHAIN, chain->index))
 		goto nla_put_failure;
 
+	if (ops) {
+		if (nla_put_string(skb, TCA_KIND, ops->kind))
+			goto nla_put_failure;
+		if (ops->tmplt_dump(skb, net, priv) < 0)
+			goto nla_put_failure;
+	}
+
 	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
 	return skb->len;
 
@@ -1699,6 +1720,47 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
 	return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO);
 }
 
+static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net,
+			      struct nlattr **tca,
+			      struct netlink_ext_ack *extack)
+{
+	const struct tcf_proto_ops *ops;
+	void *tmplt_priv;
+
+	/* If kind is not set, user did not specify template. */
+	if (!tca[TCA_KIND])
+		return 0;
+
+	ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) {
+		NL_SET_ERR_MSG(extack, "Chain templates are not supported with specified classifier");
+		return -EOPNOTSUPP;
+	}
+
+	tmplt_priv = ops->tmplt_create(net, chain, tca, extack);
+	if (IS_ERR(tmplt_priv)) {
+		module_put(ops->owner);
+		return PTR_ERR(tmplt_priv);
+	}
+	chain->tmplt_ops = ops;
+	chain->tmplt_priv = tmplt_priv;
+	return 0;
+}
+
+static void tc_chain_tmplt_del(struct tcf_chain *chain)
+{
+	const struct tcf_proto_ops *ops = chain->tmplt_ops;
+
+	/* If template ops are set, no work to do for us. */
+	if (!ops)
+		return;
+
+	ops->tmplt_destroy(chain->tmplt_priv);
+	module_put(ops->owner);
+}
+
 /* Add/delete/get a chain */
 
 static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
@@ -1763,6 +1825,9 @@ replay:
 
 	switch (n->nlmsg_type) {
 	case RTM_NEWCHAIN:
+		err = tc_chain_tmplt_add(chain, net, tca, extack);
+		if (err)
+			goto errout;
 		/* In case the chain was successfully added, take a reference
 		 * to the chain. This ensures that an empty chain
 		 * does not disappear at the end of this function.
-- 
cgit v1.2.3


From f5749081f0d48ae585233232df6cfc4c7c9642f9 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:08 +0200
Subject: net: sched: cls_flower: move key/mask dumping into a separate
 function

Push key/mask dumping from fl_dump() into a separate function
fl_dump_key(), that will be reused for template dumping.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 62 ++++++++++++++++++++++++++++++--------------------
 1 file changed, 37 insertions(+), 25 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 38d74803e2df..ab10a7c88359 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1296,29 +1296,9 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
 	return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask);
 }
 
-static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
-		   struct sk_buff *skb, struct tcmsg *t)
+static int fl_dump_key(struct sk_buff *skb, struct net *net,
+		       struct fl_flow_key *key, struct fl_flow_key *mask)
 {
-	struct cls_fl_filter *f = fh;
-	struct nlattr *nest;
-	struct fl_flow_key *key, *mask;
-
-	if (!f)
-		return skb->len;
-
-	t->tcm_handle = f->handle;
-
-	nest = nla_nest_start(skb, TCA_OPTIONS);
-	if (!nest)
-		goto nla_put_failure;
-
-	if (f->res.classid &&
-	    nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
-		goto nla_put_failure;
-
-	key = &f->key;
-	mask = &f->mask->key;
-
 	if (mask->indev_ifindex) {
 		struct net_device *dev;
 
@@ -1327,9 +1307,6 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 			goto nla_put_failure;
 	}
 
-	if (!tc_skip_hw(f->flags))
-		fl_hw_update_stats(tp, f);
-
 	if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
 			    mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
 			    sizeof(key->eth.dst)) ||
@@ -1505,6 +1482,41 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
 	if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
 		goto nla_put_failure;
 
+	return 0;
+
+nla_put_failure:
+	return -EMSGSIZE;
+}
+
+static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh,
+		   struct sk_buff *skb, struct tcmsg *t)
+{
+	struct cls_fl_filter *f = fh;
+	struct nlattr *nest;
+	struct fl_flow_key *key, *mask;
+
+	if (!f)
+		return skb->len;
+
+	t->tcm_handle = f->handle;
+
+	nest = nla_nest_start(skb, TCA_OPTIONS);
+	if (!nest)
+		goto nla_put_failure;
+
+	if (f->res.classid &&
+	    nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
+		goto nla_put_failure;
+
+	key = &f->key;
+	mask = &f->mask->key;
+
+	if (fl_dump_key(skb, net, key, mask))
+		goto nla_put_failure;
+
+	if (!tc_skip_hw(f->flags))
+		fl_hw_update_stats(tp, f);
+
 	if (f->flags && nla_put_u32(skb, TCA_FLOWER_FLAGS, f->flags))
 		goto nla_put_failure;
 
-- 
cgit v1.2.3


From 33fb5cba11ff639c32f4f0104b04b2415fcd9ecc Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:09 +0200
Subject: net: sched: cls_flower: change fl_init_dissector to accept mask and
 dissector

This function is going to be used for templates as well, so we need to
pass the pointer separately.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 43 ++++++++++++++++++++++---------------------
 1 file changed, 22 insertions(+), 21 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index ab10a7c88359..bb7aa1e9d281 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -826,51 +826,52 @@ static int fl_init_mask_hashtable(struct fl_flow_mask *mask)
 			FL_KEY_SET(keys, cnt, id, member);			\
 	} while(0);
 
-static void fl_init_dissector(struct fl_flow_mask *mask)
+static void fl_init_dissector(struct flow_dissector *dissector,
+			      struct fl_flow_key *mask)
 {
 	struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
 	size_t cnt = 0;
 
 	FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
 	FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ETH_ADDRS, eth);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_PORTS, tp);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_IP, ip);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_TCP, tcp);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ICMP, icmp);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ARP, arp);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_MPLS, mpls);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_VLAN, vlan);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_CVLAN, cvlan);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_KEYID, enc_key_id);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, enc_ipv4);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, enc_ipv6);
-	if (FL_KEY_IS_MASKED(&mask->key, enc_ipv4) ||
-	    FL_KEY_IS_MASKED(&mask->key, enc_ipv6))
+	if (FL_KEY_IS_MASKED(mask, enc_ipv4) ||
+	    FL_KEY_IS_MASKED(mask, enc_ipv6))
 		FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_ENC_CONTROL,
 			   enc_control);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
-	FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt,
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
 
-	skb_flow_dissector_init(&mask->dissector, keys, cnt);
+	skb_flow_dissector_init(dissector, keys, cnt);
 }
 
 static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
@@ -889,7 +890,7 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
 	if (err)
 		goto errout_free;
 
-	fl_init_dissector(newmask);
+	fl_init_dissector(&newmask->dissector, &newmask->key);
 
 	INIT_LIST_HEAD_RCU(&newmask->filters);
 
-- 
cgit v1.2.3


From b95ec7eb3b4d2f158dd15c912cf670b546f09571 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:10 +0200
Subject: net: sched: cls_flower: implement chain templates

Use the previously introduced template extension and implement
callback to create, destroy and dump chain template. The existing
parsing and dumping functions are re-used. Also, check if newly added
filters fit the template if it is set.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 106 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 105 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index bb7aa1e9d281..f0c80758a594 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -72,6 +72,13 @@ struct fl_flow_mask {
 	struct list_head list;
 };
 
+struct fl_flow_tmplt {
+	struct fl_flow_key dummy_key;
+	struct fl_flow_key mask;
+	struct flow_dissector dissector;
+	struct tcf_chain *chain;
+};
+
 struct cls_fl_head {
 	struct rhashtable ht;
 	struct list_head masks;
@@ -147,6 +154,23 @@ static void fl_set_masked_key(struct fl_flow_key *mkey, struct fl_flow_key *key,
 		*lmkey++ = *lkey++ & *lmask++;
 }
 
+static bool fl_mask_fits_tmplt(struct fl_flow_tmplt *tmplt,
+			       struct fl_flow_mask *mask)
+{
+	const long *lmask = fl_key_get_start(&mask->key, mask);
+	const long *ltmplt;
+	int i;
+
+	if (!tmplt)
+		return true;
+	ltmplt = fl_key_get_start(&tmplt->mask, mask);
+	for (i = 0; i < fl_mask_range(mask); i += sizeof(long)) {
+		if (~*ltmplt++ & *lmask++)
+			return false;
+	}
+	return true;
+}
+
 static void fl_clear_masked_range(struct fl_flow_key *key,
 				  struct fl_flow_mask *mask)
 {
@@ -939,6 +963,7 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
 			struct cls_fl_filter *f, struct fl_flow_mask *mask,
 			unsigned long base, struct nlattr **tb,
 			struct nlattr *est, bool ovr,
+			struct fl_flow_tmplt *tmplt,
 			struct netlink_ext_ack *extack)
 {
 	int err;
@@ -959,6 +984,11 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp,
 	fl_mask_update_range(mask);
 	fl_set_masked_key(&f->mkey, &f->key, mask);
 
+	if (!fl_mask_fits_tmplt(tmplt, mask)) {
+		NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -1024,7 +1054,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	}
 
 	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr,
-			   extack);
+			   tp->chain->tmplt_priv, extack);
 	if (err)
 		goto errout_idr;
 
@@ -1164,6 +1194,52 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	return 0;
 }
 
+static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
+			     struct nlattr **tca,
+			     struct netlink_ext_ack *extack)
+{
+	struct fl_flow_tmplt *tmplt;
+	struct nlattr **tb;
+	int err;
+
+	if (!tca[TCA_OPTIONS])
+		return ERR_PTR(-EINVAL);
+
+	tb = kcalloc(TCA_FLOWER_MAX + 1, sizeof(struct nlattr *), GFP_KERNEL);
+	if (!tb)
+		return ERR_PTR(-ENOBUFS);
+	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS],
+			       fl_policy, NULL);
+	if (err)
+		goto errout_tb;
+
+	tmplt = kzalloc(sizeof(*tmplt), GFP_KERNEL);
+	if (!tmplt)
+		goto errout_tb;
+	tmplt->chain = chain;
+	err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack);
+	if (err)
+		goto errout_tmplt;
+	kfree(tb);
+
+	fl_init_dissector(&tmplt->dissector, &tmplt->mask);
+
+	return tmplt;
+
+errout_tmplt:
+	kfree(tmplt);
+errout_tb:
+	kfree(tb);
+	return ERR_PTR(err);
+}
+
+static void fl_tmplt_destroy(void *tmplt_priv)
+{
+	struct fl_flow_tmplt *tmplt = tmplt_priv;
+
+	kfree(tmplt);
+}
+
 static int fl_dump_key_val(struct sk_buff *skb,
 			   void *val, int val_type,
 			   void *mask, int mask_type, int len)
@@ -1536,6 +1612,31 @@ nla_put_failure:
 	return -1;
 }
 
+static int fl_tmplt_dump(struct sk_buff *skb, struct net *net, void *tmplt_priv)
+{
+	struct fl_flow_tmplt *tmplt = tmplt_priv;
+	struct fl_flow_key *key, *mask;
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, TCA_OPTIONS);
+	if (!nest)
+		goto nla_put_failure;
+
+	key = &tmplt->dummy_key;
+	mask = &tmplt->mask;
+
+	if (fl_dump_key(skb, net, key, mask))
+		goto nla_put_failure;
+
+	nla_nest_end(skb, nest);
+
+	return skb->len;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
 static void fl_bind_class(void *fh, u32 classid, unsigned long cl)
 {
 	struct cls_fl_filter *f = fh;
@@ -1556,6 +1657,9 @@ static struct tcf_proto_ops cls_fl_ops __read_mostly = {
 	.reoffload	= fl_reoffload,
 	.dump		= fl_dump,
 	.bind_class	= fl_bind_class,
+	.tmplt_create	= fl_tmplt_create,
+	.tmplt_destroy	= fl_tmplt_destroy,
+	.tmplt_dump	= fl_tmplt_dump,
 	.owner		= THIS_MODULE,
 };
 
-- 
cgit v1.2.3


From 34738452739069947e528123810533f28dd8332b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:11 +0200
Subject: net: sched: cls_flower: propagate chain teplate creation and
 destruction to drivers

Introduce a couple of flower offload commands in order to propagate
template creation/destruction events down to device drivers.
Drivers may use this information to prepare HW in an optimal way
for future filter insertions.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h  |  2 ++
 net/sched/cls_flower.c | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 4f405ca8346f..a3101582f642 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -721,6 +721,8 @@ enum tc_fl_command {
 	TC_CLSFLOWER_REPLACE,
 	TC_CLSFLOWER_DESTROY,
 	TC_CLSFLOWER_STATS,
+	TC_CLSFLOWER_TMPLT_CREATE,
+	TC_CLSFLOWER_TMPLT_DESTROY,
 };
 
 struct tc_cls_flower_offload {
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index f0c80758a594..6ccf60364297 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1194,6 +1194,42 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 	return 0;
 }
 
+static void fl_hw_create_tmplt(struct tcf_chain *chain,
+			       struct fl_flow_tmplt *tmplt)
+{
+	struct tc_cls_flower_offload cls_flower = {};
+	struct tcf_block *block = chain->block;
+	struct tcf_exts dummy_exts = { 0, };
+
+	cls_flower.common.chain_index = chain->index;
+	cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE;
+	cls_flower.cookie = (unsigned long) tmplt;
+	cls_flower.dissector = &tmplt->dissector;
+	cls_flower.mask = &tmplt->mask;
+	cls_flower.key = &tmplt->dummy_key;
+	cls_flower.exts = &dummy_exts;
+
+	/* We don't care if driver (any of them) fails to handle this
+	 * call. It serves just as a hint for it.
+	 */
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
+			 &cls_flower, false);
+}
+
+static void fl_hw_destroy_tmplt(struct tcf_chain *chain,
+				struct fl_flow_tmplt *tmplt)
+{
+	struct tc_cls_flower_offload cls_flower = {};
+	struct tcf_block *block = chain->block;
+
+	cls_flower.common.chain_index = chain->index;
+	cls_flower.command = TC_CLSFLOWER_TMPLT_DESTROY;
+	cls_flower.cookie = (unsigned long) tmplt;
+
+	tc_setup_cb_call(block, NULL, TC_SETUP_CLSFLOWER,
+			 &cls_flower, false);
+}
+
 static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
 			     struct nlattr **tca,
 			     struct netlink_ext_ack *extack)
@@ -1224,6 +1260,8 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
 
 	fl_init_dissector(&tmplt->dissector, &tmplt->mask);
 
+	fl_hw_create_tmplt(chain, tmplt);
+
 	return tmplt;
 
 errout_tmplt:
@@ -1237,6 +1275,7 @@ static void fl_tmplt_destroy(void *tmplt_priv)
 {
 	struct fl_flow_tmplt *tmplt = tmplt_priv;
 
+	fl_hw_destroy_tmplt(tmplt->chain, tmplt);
 	kfree(tmplt);
 }
 
-- 
cgit v1.2.3


From e2f2a1fd5b2ceadc1182fb20809664076d75beb2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:23:12 +0200
Subject: mlxsw: spectrum: Implement chain template hinting

Since cld_flower provides information about the filter template for
specific chain, use this information in order to prepare a region.
Use the template to find out what elements are going to be used
and pass that down to mlxsw_sp_acl_tcam_group_add(). Later on, when the
first filter is inserted, the mlxsw_sp_acl_tcam_group_use_patterns()
function would use this element usage information instead of looking
up a pattern.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     |  5 +++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |  9 ++++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 12 ++++--
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 25 ++++++++++--
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  3 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c  | 44 ++++++++++++++++++++--
 6 files changed, 86 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 317c92d6496e..039228525fb1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1455,6 +1455,11 @@ mlxsw_sp_setup_tc_cls_flower(struct mlxsw_sp_acl_block *acl_block,
 		return 0;
 	case TC_CLSFLOWER_STATS:
 		return mlxsw_sp_flower_stats(mlxsw_sp, acl_block, f);
+	case TC_CLSFLOWER_TMPLT_CREATE:
+		return mlxsw_sp_flower_tmplt_create(mlxsw_sp, acl_block, f);
+	case TC_CLSFLOWER_TMPLT_DESTROY:
+		mlxsw_sp_flower_tmplt_destroy(mlxsw_sp, acl_block, f);
+		return 0;
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 016058961542..3db386c2573f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -543,7 +543,8 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_block *block, u32 chain_index,
-			 enum mlxsw_sp_acl_profile profile);
+			 enum mlxsw_sp_acl_profile profile,
+			 struct mlxsw_afk_element_usage *tmplt_elusage);
 void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_acl_ruleset *ruleset);
 u16 mlxsw_sp_acl_ruleset_group_id(struct mlxsw_sp_acl_ruleset *ruleset);
@@ -667,6 +668,12 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_acl_block *block,
 			  struct tc_cls_flower_offload *f);
+int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_block *block,
+				 struct tc_cls_flower_offload *f);
+void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_block *block,
+				   struct tc_cls_flower_offload *f);
 
 /* spectrum_qdisc.c */
 int mlxsw_sp_tc_qdisc_init(struct mlxsw_sp_port *mlxsw_sp_port);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 217621d79e26..4a4739139d11 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -317,7 +317,8 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
 static struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block, u32 chain_index,
-			    const struct mlxsw_sp_acl_profile_ops *ops)
+			    const struct mlxsw_sp_acl_profile_ops *ops,
+			    struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
 	struct mlxsw_sp_acl_ruleset *ruleset;
@@ -337,7 +338,8 @@ mlxsw_sp_acl_ruleset_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_rhashtable_init;
 
-	err = ops->ruleset_add(mlxsw_sp, &acl->tcam, ruleset->priv);
+	err = ops->ruleset_add(mlxsw_sp, &acl->tcam, ruleset->priv,
+			       tmplt_elusage);
 	if (err)
 		goto err_ops_ruleset_add;
 
@@ -419,7 +421,8 @@ mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_block *block, u32 chain_index,
-			 enum mlxsw_sp_acl_profile profile)
+			 enum mlxsw_sp_acl_profile profile,
+			 struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	const struct mlxsw_sp_acl_profile_ops *ops;
 	struct mlxsw_sp_acl *acl = mlxsw_sp->acl;
@@ -434,7 +437,8 @@ mlxsw_sp_acl_ruleset_get(struct mlxsw_sp *mlxsw_sp,
 		mlxsw_sp_acl_ruleset_ref_inc(ruleset);
 		return ruleset;
 	}
-	return mlxsw_sp_acl_ruleset_create(mlxsw_sp, block, chain_index, ops);
+	return mlxsw_sp_acl_ruleset_create(mlxsw_sp, block, chain_index, ops,
+					   tmplt_elusage);
 }
 
 void mlxsw_sp_acl_ruleset_put(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index e06d7d9e5b7f..310fd87895b8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -189,6 +189,8 @@ struct mlxsw_sp_acl_tcam_group {
 	struct mlxsw_sp_acl_tcam_group_ops *ops;
 	const struct mlxsw_sp_acl_tcam_pattern *patterns;
 	unsigned int patterns_count;
+	bool tmplt_elusage_set;
+	struct mlxsw_afk_element_usage tmplt_elusage;
 };
 
 struct mlxsw_sp_acl_tcam_chunk {
@@ -234,13 +236,19 @@ mlxsw_sp_acl_tcam_group_add(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_tcam *tcam,
 			    struct mlxsw_sp_acl_tcam_group *group,
 			    const struct mlxsw_sp_acl_tcam_pattern *patterns,
-			    unsigned int patterns_count)
+			    unsigned int patterns_count,
+			    struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	int err;
 
 	group->tcam = tcam;
 	group->patterns = patterns;
 	group->patterns_count = patterns_count;
+	if (tmplt_elusage) {
+		group->tmplt_elusage_set = true;
+		memcpy(&group->tmplt_elusage, tmplt_elusage,
+		       sizeof(group->tmplt_elusage));
+	}
 	INIT_LIST_HEAD(&group->region_list);
 	err = mlxsw_sp_acl_tcam_group_id_get(tcam, &group->id);
 	if (err)
@@ -449,6 +457,15 @@ mlxsw_sp_acl_tcam_group_use_patterns(struct mlxsw_sp_acl_tcam_group *group,
 	const struct mlxsw_sp_acl_tcam_pattern *pattern;
 	int i;
 
+	/* In case the template is set, we don't have to look up the pattern
+	 * and just use the template.
+	 */
+	if (group->tmplt_elusage_set) {
+		memcpy(out, &group->tmplt_elusage, sizeof(*out));
+		WARN_ON(!mlxsw_afk_element_usage_subset(elusage, out));
+		return;
+	}
+
 	for (i = 0; i < group->patterns_count; i++) {
 		pattern = &group->patterns[i];
 		mlxsw_afk_element_usage_fill(out, pattern->elements,
@@ -865,13 +882,15 @@ struct mlxsw_sp_acl_tcam_flower_rule {
 static int
 mlxsw_sp_acl_tcam_flower_ruleset_add(struct mlxsw_sp *mlxsw_sp,
 				     struct mlxsw_sp_acl_tcam *tcam,
-				     void *ruleset_priv)
+				     void *ruleset_priv,
+				     struct mlxsw_afk_element_usage *tmplt_elusage)
 {
 	struct mlxsw_sp_acl_tcam_flower_ruleset *ruleset = ruleset_priv;
 
 	return mlxsw_sp_acl_tcam_group_add(mlxsw_sp, tcam, &ruleset->group,
 					   mlxsw_sp_acl_tcam_patterns,
-					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT);
+					   MLXSW_SP_ACL_TCAM_PATTERNS_COUNT,
+					   tmplt_elusage);
 }
 
 static void
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 68551da2221d..6403ec4f5267 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -64,7 +64,8 @@ int mlxsw_sp_acl_tcam_priority_get(struct mlxsw_sp *mlxsw_sp,
 struct mlxsw_sp_acl_profile_ops {
 	size_t ruleset_priv_size;
 	int (*ruleset_add)(struct mlxsw_sp *mlxsw_sp,
-			   struct mlxsw_sp_acl_tcam *tcam, void *ruleset_priv);
+			   struct mlxsw_sp_acl_tcam *tcam, void *ruleset_priv,
+			   struct mlxsw_afk_element_usage *tmplt_elusage);
 	void (*ruleset_del)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv);
 	int (*ruleset_bind)(struct mlxsw_sp *mlxsw_sp, void *ruleset_priv,
 			    struct mlxsw_sp_port *mlxsw_sp_port,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 201761a3539e..b3cb618775af 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -414,7 +414,7 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
 					   f->common.chain_index,
-					   MLXSW_SP_ACL_PROFILE_FLOWER);
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
 	if (IS_ERR(ruleset))
 		return PTR_ERR(ruleset);
 
@@ -458,7 +458,7 @@ void mlxsw_sp_flower_destroy(struct mlxsw_sp *mlxsw_sp,
 
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
 					   f->common.chain_index,
-					   MLXSW_SP_ACL_PROFILE_FLOWER);
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
 	if (IS_ERR(ruleset))
 		return;
 
@@ -484,7 +484,7 @@ int mlxsw_sp_flower_stats(struct mlxsw_sp *mlxsw_sp,
 
 	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
 					   f->common.chain_index,
-					   MLXSW_SP_ACL_PROFILE_FLOWER);
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
 	if (WARN_ON(IS_ERR(ruleset)))
 		return -EINVAL;
 
@@ -506,3 +506,41 @@ err_rule_get_stats:
 	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
 	return err;
 }
+
+int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_block *block,
+				 struct tc_cls_flower_offload *f)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset;
+	struct mlxsw_sp_acl_rule_info rulei;
+	int err;
+
+	memset(&rulei, 0, sizeof(rulei));
+	err = mlxsw_sp_flower_parse(mlxsw_sp, block, &rulei, f);
+	if (err)
+		return err;
+	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
+					   f->common.chain_index,
+					   MLXSW_SP_ACL_PROFILE_FLOWER,
+					   &rulei.values.elusage);
+	if (IS_ERR(ruleset))
+		return PTR_ERR(ruleset);
+	/* keep the reference to the ruleset */
+	return 0;
+}
+
+void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_block *block,
+				   struct tc_cls_flower_offload *f)
+{
+	struct mlxsw_sp_acl_ruleset *ruleset;
+
+	ruleset = mlxsw_sp_acl_ruleset_get(mlxsw_sp, block,
+					   f->common.chain_index,
+					   MLXSW_SP_ACL_PROFILE_FLOWER, NULL);
+	if (IS_ERR(ruleset))
+		return;
+	/* put the reference to the ruleset kept in create */
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+	mlxsw_sp_acl_ruleset_put(mlxsw_sp, ruleset);
+}
-- 
cgit v1.2.3


From 7f333cbf2b5bb48045e4f31de1c33fb701ffa45a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:24:05 +0200
Subject: selftests: forwarding: move shblock tc support check to a separate
 helper

The shared block support is only needed for tc_shblock.sh. No need to
require that for other test.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh         | 3 +++
 tools/testing/selftests/net/forwarding/tc_shblocks.sh | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 2bb9cf303c53..ec94395a54a7 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -33,7 +33,10 @@ check_tc_version()
 		echo "SKIP: iproute2 too old; tc is missing JSON support"
 		exit 1
 	fi
+}
 
+check_tc_shblock_support()
+{
 	tc filter help 2>&1 | grep block &> /dev/null
 	if [[ $? -ne 0 ]]; then
 		echo "SKIP: iproute2 too old; tc is missing shared block support"
diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
index b5b917203815..9826a446e2c0 100755
--- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh
+++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh
@@ -105,6 +105,8 @@ cleanup()
 	ip link set $swp2 address $swp2origmac
 }
 
+check_tc_shblock_support
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From 2d73c8871fae2da72f4717c15d4256ec6ba208c4 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:24:06 +0200
Subject: selftests: forwarding: add tests for TC chains creation adn
 destruction

Add basic sanity tests for TC chains.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh      |  9 +++++++++
 .../testing/selftests/net/forwarding/tc_chains.sh  | 23 +++++++++++++++++++++-
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ec94395a54a7..158d59ffee40 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -44,6 +44,15 @@ check_tc_shblock_support()
 	fi
 }
 
+check_tc_chain_support()
+{
+	tc help 2>&1|grep chain &> /dev/null
+	if [[ $? -ne 0 ]]; then
+		echo "SKIP: iproute2 too old; tc is missing chain support"
+		exit 1
+	fi
+}
+
 if [[ "$(id -u)" -ne 0 ]]; then
 	echo "SKIP: need root privileges"
 	exit 0
diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh
index d2c783e94df3..2730887a3b3a 100755
--- a/tools/testing/selftests/net/forwarding/tc_chains.sh
+++ b/tools/testing/selftests/net/forwarding/tc_chains.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="unreachable_chain_test gact_goto_chain_test"
+ALL_TESTS="unreachable_chain_test gact_goto_chain_test create_destroy_chain"
 NUM_NETIFS=2
 source tc_common.sh
 source lib.sh
@@ -80,6 +80,25 @@ gact_goto_chain_test()
 	log_test "gact goto chain ($tcflags)"
 }
 
+create_destroy_chain()
+{
+	RET=0
+
+	tc chain add dev $h2 ingress
+	check_err $? "Failed to create default chain"
+
+	tc chain add dev $h2 ingress chain 1
+	check_err $? "Failed to create chain 1"
+
+	tc chain del dev $h2 ingress
+	check_err $? "Failed to destroy default chain"
+
+	tc chain del dev $h2 ingress chain 1
+	check_err $? "Failed to destroy chain 1"
+
+	log_test "create destroy chain"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
@@ -103,6 +122,8 @@ cleanup()
 	vrf_cleanup
 }
 
+check_tc_chain_support
+
 trap cleanup EXIT
 
 setup_prepare
-- 
cgit v1.2.3


From d159b381795b138532436cce1229f5305c6f1a21 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Mon, 23 Jul 2018 09:24:07 +0200
Subject: selftests: forwarding: add tests for TC chain templates

Add basic sanity tests for TC chain templates.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../testing/selftests/net/forwarding/tc_chains.sh  | 44 +++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh
index 2730887a3b3a..031e322e28b3 100755
--- a/tools/testing/selftests/net/forwarding/tc_chains.sh
+++ b/tools/testing/selftests/net/forwarding/tc_chains.sh
@@ -1,7 +1,8 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="unreachable_chain_test gact_goto_chain_test create_destroy_chain"
+ALL_TESTS="unreachable_chain_test gact_goto_chain_test create_destroy_chain \
+	   template_filter_fits"
 NUM_NETIFS=2
 source tc_common.sh
 source lib.sh
@@ -99,6 +100,47 @@ create_destroy_chain()
 	log_test "create destroy chain"
 }
 
+template_filter_fits()
+{
+	RET=0
+
+	tc chain add dev $h2 ingress protocol ip \
+		flower dst_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+	tc chain add dev $h2 ingress chain 1 protocol ip \
+		flower src_mac 00:00:00:00:00:00/FF:FF:FF:FF:FF:FF &> /dev/null
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 1101 \
+		flower dst_mac $h2mac action drop
+	check_err $? "Failed to insert filter which fits template"
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 1102 \
+		flower src_mac $h2mac action drop &> /dev/null
+	check_fail $? "Incorrectly succeded to insert filter which does not template"
+
+	tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \
+		flower src_mac $h2mac action drop
+	check_err $? "Failed to insert filter which fits template"
+
+	tc filter add dev $h2 ingress chain 1 protocol ip pref 1 handle 1102 \
+		flower dst_mac $h2mac action drop &> /dev/null
+	check_fail $? "Incorrectly succeded to insert filter which does not template"
+
+	tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1102 \
+		flower &> /dev/null
+	tc filter del dev $h2 ingress chain 1 protocol ip pref 1 handle 1101 \
+		flower &> /dev/null
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 1102 \
+		flower &> /dev/null
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 1101 \
+		flower &> /dev/null
+
+	tc chain del dev $h2 ingress chain 1
+	tc chain del dev $h2 ingress
+
+	log_test "template filter fits"
+}
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
-- 
cgit v1.2.3


From eee2fa6ab3225192d6d894c54a6fb02ac9efdff6 Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Mon, 23 Jul 2018 20:51:21 -0700
Subject: rds: Changing IP address internal representation to struct in6_addr

This patch changes the internal representation of an IP address to use
struct in6_addr.  IPv4 address is stored as an IPv4 mapped address.
All the functions which take an IP address as argument are also
changed to use struct in6_addr.  But RDS socket layer is not modified
such that it still does not accept IPv6 address from an application.
And RDS layer does not accept nor initiate IPv6 connections.

v2: Fixed sparse warnings.

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/af_rds.c         | 138 +++++++++++++++-------
 net/rds/bind.c           |  91 ++++++++++-----
 net/rds/cong.c           |  23 ++--
 net/rds/connection.c     | 132 +++++++++++++--------
 net/rds/ib.c             |  17 +--
 net/rds/ib.h             |  51 ++++++--
 net/rds/ib_cm.c          | 299 ++++++++++++++++++++++++++++++++++-------------
 net/rds/ib_rdma.c        |  15 +--
 net/rds/ib_recv.c        |  18 +--
 net/rds/ib_send.c        |  10 +-
 net/rds/loop.c           |   7 +-
 net/rds/rdma.c           |   6 +-
 net/rds/rdma_transport.c |  56 ++++++---
 net/rds/rds.h            |  70 +++++++----
 net/rds/recv.c           |  51 +++++---
 net/rds/send.c           |  67 ++++++++---
 net/rds/tcp.c            |  32 ++++-
 net/rds/tcp_connect.c    |  34 +++---
 net/rds/tcp_listen.c     |  18 +--
 net/rds/tcp_recv.c       |   9 +-
 net/rds/tcp_send.c       |   4 +-
 net/rds/threads.c        |  69 +++++++++--
 net/rds/transport.c      |  15 ++-
 23 files changed, 863 insertions(+), 369 deletions(-)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index ab751a150f70..fc1a5c63b783 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/in.h>
+#include <linux/ipv6.h>
 #include <linux/poll.h>
 #include <net/sock.h>
 
@@ -113,26 +114,63 @@ void rds_wake_sk_sleep(struct rds_sock *rs)
 static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
 		       int peer)
 {
-	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
 	struct rds_sock *rs = rds_sk_to_rs(sock->sk);
-
-	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+	struct sockaddr_in6 *sin6;
+	struct sockaddr_in *sin;
+	int uaddr_len;
 
 	/* racey, don't care */
 	if (peer) {
-		if (!rs->rs_conn_addr)
+		if (ipv6_addr_any(&rs->rs_conn_addr))
 			return -ENOTCONN;
 
-		sin->sin_port = rs->rs_conn_port;
-		sin->sin_addr.s_addr = rs->rs_conn_addr;
+		if (ipv6_addr_v4mapped(&rs->rs_conn_addr)) {
+			sin = (struct sockaddr_in *)uaddr;
+			memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+			sin->sin_family = AF_INET;
+			sin->sin_port = rs->rs_conn_port;
+			sin->sin_addr.s_addr = rs->rs_conn_addr_v4;
+			uaddr_len = sizeof(*sin);
+		} else {
+			sin6 = (struct sockaddr_in6 *)uaddr;
+			sin6->sin6_family = AF_INET6;
+			sin6->sin6_port = rs->rs_conn_port;
+			sin6->sin6_addr = rs->rs_conn_addr;
+			sin6->sin6_flowinfo = 0;
+			/* scope_id is the same as in the bound address. */
+			sin6->sin6_scope_id = rs->rs_bound_scope_id;
+			uaddr_len = sizeof(*sin6);
+		}
 	} else {
-		sin->sin_port = rs->rs_bound_port;
-		sin->sin_addr.s_addr = rs->rs_bound_addr;
+		/* If socket is not yet bound, set the return address family
+		 * to be AF_UNSPEC (value 0) and the address size to be that
+		 * of an IPv4 address.
+		 */
+		if (ipv6_addr_any(&rs->rs_bound_addr)) {
+			sin = (struct sockaddr_in *)uaddr;
+			memset(sin, 0, sizeof(*sin));
+			sin->sin_family = AF_UNSPEC;
+			return sizeof(*sin);
+		}
+		if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
+			sin = (struct sockaddr_in *)uaddr;
+			memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+			sin->sin_family = AF_INET;
+			sin->sin_port = rs->rs_bound_port;
+			sin->sin_addr.s_addr = rs->rs_bound_addr_v4;
+			uaddr_len = sizeof(*sin);
+		} else {
+			sin6 = (struct sockaddr_in6 *)uaddr;
+			sin6->sin6_family = AF_INET6;
+			sin6->sin6_port = rs->rs_bound_port;
+			sin6->sin6_addr = rs->rs_bound_addr;
+			sin6->sin6_flowinfo = 0;
+			sin6->sin6_scope_id = rs->rs_bound_scope_id;
+			uaddr_len = sizeof(*sin6);
+		}
 	}
 
-	sin->sin_family = AF_INET;
-
-	return sizeof(*sin);
+	return uaddr_len;
 }
 
 /*
@@ -203,11 +241,12 @@ static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
 			      int len)
 {
+	struct sockaddr_in6 sin6;
 	struct sockaddr_in sin;
 	int ret = 0;
 
 	/* racing with another thread binding seems ok here */
-	if (rs->rs_bound_addr == 0) {
+	if (ipv6_addr_any(&rs->rs_bound_addr)) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}
@@ -215,14 +254,23 @@ static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
 	if (len < sizeof(struct sockaddr_in)) {
 		ret = -EINVAL;
 		goto out;
+	} else if (len < sizeof(struct sockaddr_in6)) {
+		/* Assume IPv4 */
+		if (copy_from_user(&sin, optval, sizeof(struct sockaddr_in))) {
+			ret = -EFAULT;
+			goto out;
+		}
+		ipv6_addr_set_v4mapped(sin.sin_addr.s_addr, &sin6.sin6_addr);
+		sin6.sin6_port = sin.sin_port;
+	} else {
+		if (copy_from_user(&sin6, optval,
+				   sizeof(struct sockaddr_in6))) {
+			ret = -EFAULT;
+			goto out;
+		}
 	}
 
-	if (copy_from_user(&sin, optval, sizeof(sin))) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	rds_send_drop_to(rs, &sin);
+	rds_send_drop_to(rs, &sin6);
 out:
 	return ret;
 }
@@ -435,31 +483,41 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 		       int addr_len, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
+	struct sockaddr_in *sin;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
 	int ret = 0;
 
 	lock_sock(sk);
 
-	if (addr_len != sizeof(struct sockaddr_in)) {
-		ret = -EINVAL;
-		goto out;
-	}
+	switch (addr_len) {
+	case sizeof(struct sockaddr_in):
+		sin = (struct sockaddr_in *)uaddr;
+		if (sin->sin_family != AF_INET) {
+			ret = -EAFNOSUPPORT;
+			break;
+		}
+		if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
+			ret = -EDESTADDRREQ;
+			break;
+		}
+		if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr)) ||
+		    sin->sin_addr.s_addr == htonl(INADDR_BROADCAST)) {
+			ret = -EINVAL;
+			break;
+		}
+		ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &rs->rs_conn_addr);
+		rs->rs_conn_port = sin->sin_port;
+		break;
 
-	if (sin->sin_family != AF_INET) {
-		ret = -EAFNOSUPPORT;
-		goto out;
-	}
+	case sizeof(struct sockaddr_in6):
+		ret = -EPROTONOSUPPORT;
+		break;
 
-	if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
-		ret = -EDESTADDRREQ;
-		goto out;
+	default:
+		ret = -EINVAL;
+		break;
 	}
 
-	rs->rs_conn_addr = sin->sin_addr.s_addr;
-	rs->rs_conn_port = sin->sin_port;
-
-out:
 	release_sock(sk);
 	return ret;
 }
@@ -578,8 +636,10 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len,
 		list_for_each_entry(inc, &rs->rs_recv_queue, i_item) {
 			total++;
 			if (total <= len)
-				rds_inc_info_copy(inc, iter, inc->i_saddr,
-						  rs->rs_bound_addr, 1);
+				rds_inc_info_copy(inc, iter,
+						  inc->i_saddr.s6_addr32[3],
+						  rs->rs_bound_addr_v4,
+						  1);
 		}
 
 		read_unlock(&rs->rs_recv_lock);
@@ -608,8 +668,8 @@ static void rds_sock_info(struct socket *sock, unsigned int len,
 	list_for_each_entry(rs, &rds_sock_list, rs_item) {
 		sinfo.sndbuf = rds_sk_sndbuf(rs);
 		sinfo.rcvbuf = rds_sk_rcvbuf(rs);
-		sinfo.bound_addr = rs->rs_bound_addr;
-		sinfo.connected_addr = rs->rs_conn_addr;
+		sinfo.bound_addr = rs->rs_bound_addr_v4;
+		sinfo.connected_addr = rs->rs_conn_addr_v4;
 		sinfo.bound_port = rs->rs_bound_port;
 		sinfo.connected_port = rs->rs_conn_port;
 		sinfo.inum = sock_i_ino(rds_rs_to_sk(rs));
diff --git a/net/rds/bind.c b/net/rds/bind.c
index 5aa3a64aa4f0..c401776ad938 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -33,6 +33,7 @@
 #include <linux/kernel.h>
 #include <net/sock.h>
 #include <linux/in.h>
+#include <linux/ipv6.h>
 #include <linux/if_arp.h>
 #include <linux/jhash.h>
 #include <linux/ratelimit.h>
@@ -42,42 +43,58 @@ static struct rhashtable bind_hash_table;
 
 static const struct rhashtable_params ht_parms = {
 	.nelem_hint = 768,
-	.key_len = sizeof(u64),
+	.key_len = RDS_BOUND_KEY_LEN,
 	.key_offset = offsetof(struct rds_sock, rs_bound_key),
 	.head_offset = offsetof(struct rds_sock, rs_bound_node),
 	.max_size = 16384,
 	.min_size = 1024,
 };
 
+/* Create a key for the bind hash table manipulation.  Port is in network byte
+ * order.
+ */
+static inline void __rds_create_bind_key(u8 *key, const struct in6_addr *addr,
+					 __be16 port, __u32 scope_id)
+{
+	memcpy(key, addr, sizeof(*addr));
+	key += sizeof(*addr);
+	memcpy(key, &port, sizeof(port));
+	key += sizeof(port);
+	memcpy(key, &scope_id, sizeof(scope_id));
+}
+
 /*
  * Return the rds_sock bound at the given local address.
  *
  * The rx path can race with rds_release.  We notice if rds_release() has
  * marked this socket and don't return a rs ref to the rx path.
  */
-struct rds_sock *rds_find_bound(__be32 addr, __be16 port)
+struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
+				__u32 scope_id)
 {
-	u64 key = ((u64)addr << 32) | port;
+	u8 key[RDS_BOUND_KEY_LEN];
 	struct rds_sock *rs;
 
-	rs = rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms);
+	__rds_create_bind_key(key, addr, port, scope_id);
+	rs = rhashtable_lookup_fast(&bind_hash_table, key, ht_parms);
 	if (rs && !sock_flag(rds_rs_to_sk(rs), SOCK_DEAD))
 		rds_sock_addref(rs);
 	else
 		rs = NULL;
 
-	rdsdebug("returning rs %p for %pI4:%u\n", rs, &addr,
-		ntohs(port));
+	rdsdebug("returning rs %p for %pI6c:%u\n", rs, addr,
+		 ntohs(port));
 
 	return rs;
 }
 
 /* returns -ve errno or +ve port */
-static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
+static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr,
+			 __be16 *port, __u32 scope_id)
 {
 	int ret = -EADDRINUSE;
 	u16 rover, last;
-	u64 key;
+	u8 key[RDS_BOUND_KEY_LEN];
 
 	if (*port != 0) {
 		rover = be16_to_cpu(*port);
@@ -95,12 +112,13 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
 
 		if (rover == RDS_FLAG_PROBE_PORT)
 			continue;
-		key = ((u64)addr << 32) | cpu_to_be16(rover);
-		if (rhashtable_lookup_fast(&bind_hash_table, &key, ht_parms))
+		__rds_create_bind_key(key, addr, cpu_to_be16(rover),
+				      scope_id);
+		if (rhashtable_lookup_fast(&bind_hash_table, key, ht_parms))
 			continue;
 
-		rs->rs_bound_key = key;
-		rs->rs_bound_addr = addr;
+		memcpy(rs->rs_bound_key, key, sizeof(rs->rs_bound_key));
+		rs->rs_bound_addr = *addr;
 		net_get_random_once(&rs->rs_hash_initval,
 				    sizeof(rs->rs_hash_initval));
 		rs->rs_bound_port = cpu_to_be16(rover);
@@ -114,7 +132,7 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
 			  rs, &addr, (int)ntohs(*port));
 			break;
 		} else {
-			rs->rs_bound_addr = 0;
+			rs->rs_bound_addr = in6addr_any;
 			rds_sock_put(rs);
 			ret = -ENOMEM;
 			break;
@@ -127,44 +145,61 @@ static int rds_add_bound(struct rds_sock *rs, __be32 addr, __be16 *port)
 void rds_remove_bound(struct rds_sock *rs)
 {
 
-	if (!rs->rs_bound_addr)
+	if (ipv6_addr_any(&rs->rs_bound_addr))
 		return;
 
-	rdsdebug("rs %p unbinding from %pI4:%d\n",
+	rdsdebug("rs %p unbinding from %pI6c:%d\n",
 		 rs, &rs->rs_bound_addr,
 		 ntohs(rs->rs_bound_port));
 
 	rhashtable_remove_fast(&bind_hash_table, &rs->rs_bound_node, ht_parms);
 	rds_sock_put(rs);
-	rs->rs_bound_addr = 0;
+	rs->rs_bound_addr = in6addr_any;
 }
 
 int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
+	struct in6_addr v6addr, *binding_addr;
 	struct rds_transport *trans;
+	__u32 scope_id = 0;
 	int ret = 0;
+	__be16 port;
 
+	/* We only allow an RDS socket to be bound to an IPv4 address. IPv6
+	 * address support will be added later.
+	 */
+	if (addr_len == sizeof(struct sockaddr_in)) {
+		struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
+
+		if (sin->sin_family != AF_INET ||
+		    sin->sin_addr.s_addr == htonl(INADDR_ANY))
+			return -EINVAL;
+		ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr);
+		binding_addr = &v6addr;
+		port = sin->sin_port;
+	} else if (addr_len == sizeof(struct sockaddr_in6)) {
+		return -EPROTONOSUPPORT;
+	} else {
+		return -EINVAL;
+	}
 	lock_sock(sk);
 
-	if (addr_len != sizeof(struct sockaddr_in) ||
-	    sin->sin_family != AF_INET ||
-	    rs->rs_bound_addr ||
-	    sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
+	/* RDS socket does not allow re-binding. */
+	if (!ipv6_addr_any(&rs->rs_bound_addr)) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	ret = rds_add_bound(rs, sin->sin_addr.s_addr, &sin->sin_port);
+	ret = rds_add_bound(rs, binding_addr, &port, scope_id);
 	if (ret)
 		goto out;
 
 	if (rs->rs_transport) { /* previously bound */
 		trans = rs->rs_transport;
 		if (trans->laddr_check(sock_net(sock->sk),
-				       sin->sin_addr.s_addr) != 0) {
+				       binding_addr, scope_id) != 0) {
 			ret = -ENOPROTOOPT;
 			rds_remove_bound(rs);
 		} else {
@@ -172,13 +207,13 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		}
 		goto out;
 	}
-	trans = rds_trans_get_preferred(sock_net(sock->sk),
-					sin->sin_addr.s_addr);
+	trans = rds_trans_get_preferred(sock_net(sock->sk), binding_addr,
+					scope_id);
 	if (!trans) {
 		ret = -EADDRNOTAVAIL;
 		rds_remove_bound(rs);
-		pr_info_ratelimited("RDS: %s could not find a transport for %pI4, load rds_tcp or rds_rdma?\n",
-				    __func__, &sin->sin_addr.s_addr);
+		pr_info_ratelimited("RDS: %s could not find a transport for %pI6c, load rds_tcp or rds_rdma?\n",
+				    __func__, binding_addr);
 		goto out;
 	}
 
diff --git a/net/rds/cong.c b/net/rds/cong.c
index 63da9d2f142d..ccdff09a79c8 100644
--- a/net/rds/cong.c
+++ b/net/rds/cong.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007 Oracle.  All rights reserved.
+ * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -101,7 +101,7 @@ static DEFINE_RWLOCK(rds_cong_monitor_lock);
 static DEFINE_SPINLOCK(rds_cong_lock);
 static struct rb_root rds_cong_tree = RB_ROOT;
 
-static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
+static struct rds_cong_map *rds_cong_tree_walk(const struct in6_addr *addr,
 					       struct rds_cong_map *insert)
 {
 	struct rb_node **p = &rds_cong_tree.rb_node;
@@ -109,12 +109,15 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
 	struct rds_cong_map *map;
 
 	while (*p) {
+		int diff;
+
 		parent = *p;
 		map = rb_entry(parent, struct rds_cong_map, m_rb_node);
 
-		if (addr < map->m_addr)
+		diff = rds_addr_cmp(addr, &map->m_addr);
+		if (diff < 0)
 			p = &(*p)->rb_left;
-		else if (addr > map->m_addr)
+		else if (diff > 0)
 			p = &(*p)->rb_right;
 		else
 			return map;
@@ -132,7 +135,7 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
  * these bitmaps in the process getting pointers to them.  The bitmaps are only
  * ever freed as the module is removed after all connections have been freed.
  */
-static struct rds_cong_map *rds_cong_from_addr(__be32 addr)
+static struct rds_cong_map *rds_cong_from_addr(const struct in6_addr *addr)
 {
 	struct rds_cong_map *map;
 	struct rds_cong_map *ret = NULL;
@@ -144,7 +147,7 @@ static struct rds_cong_map *rds_cong_from_addr(__be32 addr)
 	if (!map)
 		return NULL;
 
-	map->m_addr = addr;
+	map->m_addr = *addr;
 	init_waitqueue_head(&map->m_waitq);
 	INIT_LIST_HEAD(&map->m_conn_list);
 
@@ -171,7 +174,7 @@ out:
 		kfree(map);
 	}
 
-	rdsdebug("map %p for addr %x\n", ret, be32_to_cpu(addr));
+	rdsdebug("map %p for addr %pI6c\n", ret, addr);
 
 	return ret;
 }
@@ -202,8 +205,8 @@ void rds_cong_remove_conn(struct rds_connection *conn)
 
 int rds_cong_get_maps(struct rds_connection *conn)
 {
-	conn->c_lcong = rds_cong_from_addr(conn->c_laddr);
-	conn->c_fcong = rds_cong_from_addr(conn->c_faddr);
+	conn->c_lcong = rds_cong_from_addr(&conn->c_laddr);
+	conn->c_fcong = rds_cong_from_addr(&conn->c_faddr);
 
 	if (!(conn->c_lcong && conn->c_fcong))
 		return -ENOMEM;
@@ -353,7 +356,7 @@ void rds_cong_remove_socket(struct rds_sock *rs)
 
 	/* update congestion map for now-closed port */
 	spin_lock_irqsave(&rds_cong_lock, flags);
-	map = rds_cong_tree_walk(rs->rs_bound_addr, NULL);
+	map = rds_cong_tree_walk(&rs->rs_bound_addr, NULL);
 	spin_unlock_irqrestore(&rds_cong_lock, flags);
 
 	if (map && rds_cong_test_bit(map, rs->rs_bound_port)) {
diff --git a/net/rds/connection.c b/net/rds/connection.c
index cfb05953b0e5..3176ead0ab4d 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -34,7 +34,8 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/export.h>
-#include <net/inet_hashtables.h>
+#include <net/ipv6.h>
+#include <net/inet6_hashtables.h>
 
 #include "rds.h"
 #include "loop.h"
@@ -49,18 +50,21 @@ static unsigned long rds_conn_count;
 static struct hlist_head rds_conn_hash[RDS_CONNECTION_HASH_ENTRIES];
 static struct kmem_cache *rds_conn_slab;
 
-static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
+static struct hlist_head *rds_conn_bucket(const struct in6_addr *laddr,
+					  const struct in6_addr *faddr)
 {
+	static u32 rds6_hash_secret __read_mostly;
 	static u32 rds_hash_secret __read_mostly;
 
-	unsigned long hash;
+	u32 lhash, fhash, hash;
 
 	net_get_random_once(&rds_hash_secret, sizeof(rds_hash_secret));
+	net_get_random_once(&rds6_hash_secret, sizeof(rds6_hash_secret));
+
+	lhash = (__force u32)laddr->s6_addr32[3];
+	fhash = __ipv6_addr_jhash(faddr, rds6_hash_secret);
+	hash = __inet6_ehashfn(lhash, 0, fhash, 0, rds_hash_secret);
 
-	/* Pass NULL, don't need struct net for hash */
-	hash = __inet_ehashfn(be32_to_cpu(laddr), 0,
-			      be32_to_cpu(faddr), 0,
-			      rds_hash_secret);
 	return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
 }
 
@@ -72,20 +76,25 @@ static struct hlist_head *rds_conn_bucket(__be32 laddr, __be32 faddr)
 /* rcu read lock must be held or the connection spinlock */
 static struct rds_connection *rds_conn_lookup(struct net *net,
 					      struct hlist_head *head,
-					      __be32 laddr, __be32 faddr,
-					      struct rds_transport *trans)
+					      const struct in6_addr *laddr,
+					      const struct in6_addr *faddr,
+					      struct rds_transport *trans,
+					      int dev_if)
 {
 	struct rds_connection *conn, *ret = NULL;
 
 	hlist_for_each_entry_rcu(conn, head, c_hash_node) {
-		if (conn->c_faddr == faddr && conn->c_laddr == laddr &&
-		    conn->c_trans == trans && net == rds_conn_net(conn)) {
+		if (ipv6_addr_equal(&conn->c_faddr, faddr) &&
+		    ipv6_addr_equal(&conn->c_laddr, laddr) &&
+		    conn->c_trans == trans &&
+		    net == rds_conn_net(conn) &&
+		    conn->c_dev_if == dev_if) {
 			ret = conn;
 			break;
 		}
 	}
-	rdsdebug("returning conn %p for %pI4 -> %pI4\n", ret,
-		 &laddr, &faddr);
+	rdsdebug("returning conn %p for %pI6c -> %pI6c\n", ret,
+		 laddr, faddr);
 	return ret;
 }
 
@@ -99,8 +108,8 @@ static void rds_conn_path_reset(struct rds_conn_path *cp)
 {
 	struct rds_connection *conn = cp->cp_conn;
 
-	rdsdebug("connection %pI4 to %pI4 reset\n",
-	  &conn->c_laddr, &conn->c_faddr);
+	rdsdebug("connection %pI6c to %pI6c reset\n",
+		 &conn->c_laddr, &conn->c_faddr);
 
 	rds_stats_inc(s_conn_reset);
 	rds_send_path_reset(cp);
@@ -142,9 +151,12 @@ static void __rds_conn_path_init(struct rds_connection *conn,
  * are torn down as the module is removed, if ever.
  */
 static struct rds_connection *__rds_conn_create(struct net *net,
-						__be32 laddr, __be32 faddr,
-				       struct rds_transport *trans, gfp_t gfp,
-				       int is_outgoing)
+						const struct in6_addr *laddr,
+						const struct in6_addr *faddr,
+						struct rds_transport *trans,
+						gfp_t gfp,
+						int is_outgoing,
+						int dev_if)
 {
 	struct rds_connection *conn, *parent = NULL;
 	struct hlist_head *head = rds_conn_bucket(laddr, faddr);
@@ -154,9 +166,12 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1);
 
 	rcu_read_lock();
-	conn = rds_conn_lookup(net, head, laddr, faddr, trans);
-	if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport &&
-	    laddr == faddr && !is_outgoing) {
+	conn = rds_conn_lookup(net, head, laddr, faddr, trans, dev_if);
+	if (conn &&
+	    conn->c_loopback &&
+	    conn->c_trans != &rds_loop_transport &&
+	    ipv6_addr_equal(laddr, faddr) &&
+	    !is_outgoing) {
 		/* This is a looped back IB connection, and we're
 		 * called by the code handling the incoming connect.
 		 * We need a second connection object into which we
@@ -181,8 +196,10 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	}
 
 	INIT_HLIST_NODE(&conn->c_hash_node);
-	conn->c_laddr = laddr;
-	conn->c_faddr = faddr;
+	conn->c_laddr = *laddr;
+	conn->c_isv6 = !ipv6_addr_v4mapped(laddr);
+	conn->c_faddr = *faddr;
+	conn->c_dev_if = dev_if;
 
 	rds_conn_net_set(conn, net);
 
@@ -199,7 +216,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	 * can bind to the destination address then we'd rather the messages
 	 * flow through loopback rather than either transport.
 	 */
-	loop_trans = rds_trans_get_preferred(net, faddr);
+	loop_trans = rds_trans_get_preferred(net, faddr, conn->c_dev_if);
 	if (loop_trans) {
 		rds_trans_put(loop_trans);
 		conn->c_loopback = 1;
@@ -233,10 +250,10 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 		goto out;
 	}
 
-	rdsdebug("allocated conn %p for %pI4 -> %pI4 over %s %s\n",
-	  conn, &laddr, &faddr,
-	  strnlen(trans->t_name, sizeof(trans->t_name)) ? trans->t_name :
-	  "[unknown]", is_outgoing ? "(outgoing)" : "");
+	rdsdebug("allocated conn %p for %pI6c -> %pI6c over %s %s\n",
+		 conn, laddr, faddr,
+		 strnlen(trans->t_name, sizeof(trans->t_name)) ?
+		 trans->t_name : "[unknown]", is_outgoing ? "(outgoing)" : "");
 
 	/*
 	 * Since we ran without holding the conn lock, someone could
@@ -262,7 +279,8 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 		/* Creating normal conn */
 		struct rds_connection *found;
 
-		found = rds_conn_lookup(net, head, laddr, faddr, trans);
+		found = rds_conn_lookup(net, head, laddr, faddr, trans,
+					dev_if);
 		if (found) {
 			struct rds_conn_path *cp;
 			int i;
@@ -295,18 +313,22 @@ out:
 }
 
 struct rds_connection *rds_conn_create(struct net *net,
-				       __be32 laddr, __be32 faddr,
-				       struct rds_transport *trans, gfp_t gfp)
+				       const struct in6_addr *laddr,
+				       const struct in6_addr *faddr,
+				       struct rds_transport *trans, gfp_t gfp,
+				       int dev_if)
 {
-	return __rds_conn_create(net, laddr, faddr, trans, gfp, 0);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, 0, dev_if);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create);
 
 struct rds_connection *rds_conn_create_outgoing(struct net *net,
-						__be32 laddr, __be32 faddr,
-				       struct rds_transport *trans, gfp_t gfp)
+						const struct in6_addr *laddr,
+						const struct in6_addr *faddr,
+						struct rds_transport *trans,
+						gfp_t gfp, int dev_if)
 {
-	return __rds_conn_create(net, laddr, faddr, trans, gfp, 1);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, 1, dev_if);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
 
@@ -502,12 +524,17 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 
 				/* XXX too lazy to maintain counts.. */
 				list_for_each_entry(rm, list, m_conn_item) {
+					__be32 laddr;
+					__be32 faddr;
+
 					total++;
+					laddr = conn->c_laddr.s6_addr32[3];
+					faddr = conn->c_faddr.s6_addr32[3];
 					if (total <= len)
 						rds_inc_info_copy(&rm->m_inc,
 								  iter,
-								  conn->c_laddr,
-								  conn->c_faddr,
+								  laddr,
+								  faddr,
 								  0);
 				}
 
@@ -584,7 +611,6 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 	struct hlist_head *head;
 	struct rds_connection *conn;
 	size_t i;
-	int j;
 
 	rcu_read_lock();
 
@@ -595,17 +621,20 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 	     i++, head++) {
 		hlist_for_each_entry_rcu(conn, head, c_hash_node) {
 			struct rds_conn_path *cp;
-			int npaths;
 
-			npaths = (conn->c_trans->t_mp_capable ?
-				 RDS_MPATH_WORKERS : 1);
-			for (j = 0; j < npaths; j++) {
-				cp = &conn->c_path[j];
+			/* XXX We only copy the information from the first
+			 * path for now.  The problem is that if there are
+			 * more than one underlying paths, we cannot report
+			 * information of all of them using the existing
+			 * API.  For example, there is only one next_tx_seq,
+			 * which path's next_tx_seq should we report?  It is
+			 * a bug in the design of MPRDS.
+			 */
+			cp = conn->c_path;
 
-				/* XXX no cp_lock usage.. */
-				if (!visitor(cp, buffer))
-					continue;
-			}
+			/* XXX no cp_lock usage.. */
+			if (!visitor(cp, buffer))
+				continue;
 
 			/* We copy as much as we can fit in the buffer,
 			 * but we count all items so that the caller
@@ -624,12 +653,13 @@ static void rds_walk_conn_path_info(struct socket *sock, unsigned int len,
 static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 {
 	struct rds_info_connection *cinfo = buffer;
+	struct rds_connection *conn = cp->cp_conn;
 
 	cinfo->next_tx_seq = cp->cp_next_tx_seq;
 	cinfo->next_rx_seq = cp->cp_next_rx_seq;
-	cinfo->laddr = cp->cp_conn->c_laddr;
-	cinfo->faddr = cp->cp_conn->c_faddr;
-	strncpy(cinfo->transport, cp->cp_conn->c_trans->t_name,
+	cinfo->laddr = conn->c_laddr.s6_addr32[3];
+	cinfo->faddr = conn->c_faddr.s6_addr32[3];
+	strncpy(cinfo->transport, conn->c_trans->t_name,
 		sizeof(cinfo->transport));
 	cinfo->flags = 0;
 
diff --git a/net/rds/ib.c b/net/rds/ib.c
index b6ad38e48f62..c712a848957d 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -296,8 +296,8 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
 	if (conn->c_trans != &rds_ib_transport)
 		return 0;
 
-	iinfo->src_addr = conn->c_laddr;
-	iinfo->dst_addr = conn->c_faddr;
+	iinfo->src_addr = conn->c_laddr.s6_addr32[3];
+	iinfo->dst_addr = conn->c_faddr.s6_addr32[3];
 
 	memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid));
 	memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid));
@@ -341,7 +341,8 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
  * allowed to influence which paths have priority.  We could call userspace
  * asserting this policy "routing".
  */
-static int rds_ib_laddr_check(struct net *net, __be32 addr)
+static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
+			      __u32 scope_id)
 {
 	int ret;
 	struct rdma_cm_id *cm_id;
@@ -357,7 +358,7 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr)
 
 	memset(&sin, 0, sizeof(sin));
 	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = addr;
+	sin.sin_addr.s_addr = addr->s6_addr32[3];
 
 	/* rdma_bind_addr will only succeed for IB & iWARP devices */
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
@@ -367,9 +368,9 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr)
 	    cm_id->device->node_type != RDMA_NODE_IB_CA)
 		ret = -EADDRNOTAVAIL;
 
-	rdsdebug("addr %pI4 ret %d node type %d\n",
-		&addr, ret,
-		cm_id->device ? cm_id->device->node_type : -1);
+	rdsdebug("addr %pI6c ret %d node type %d\n",
+		 addr, ret,
+		 cm_id->device ? cm_id->device->node_type : -1);
 
 	rdma_destroy_id(cm_id);
 
diff --git a/net/rds/ib.h b/net/rds/ib.h
index a6f4d7d68e95..beb95b893f78 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -57,16 +57,44 @@ struct rds_ib_refill_cache {
 	struct list_head	 *ready;
 };
 
+/* This is the common structure for the IB private data exchange in setting up
+ * an RDS connection.  The exchange is different for IPv4 and IPv6 connections.
+ * The reason is that the address size is different and the addresses
+ * exchanged are in the beginning of the structure.  Hence it is not possible
+ * for interoperability if same structure is used.
+ */
+struct rds_ib_conn_priv_cmn {
+	u8			ricpc_protocol_major;
+	u8			ricpc_protocol_minor;
+	__be16			ricpc_protocol_minor_mask;	/* bitmask */
+	__be32			ricpc_reserved1;
+	__be64			ricpc_ack_seq;
+	__be32			ricpc_credit;	/* non-zero enables flow ctl */
+};
+
 struct rds_ib_connect_private {
 	/* Add new fields at the end, and don't permute existing fields. */
-	__be32			dp_saddr;
-	__be32			dp_daddr;
-	u8			dp_protocol_major;
-	u8			dp_protocol_minor;
-	__be16			dp_protocol_minor_mask; /* bitmask */
-	__be32			dp_reserved1;
-	__be64			dp_ack_seq;
-	__be32			dp_credit;		/* non-zero enables flow ctl */
+	__be32				dp_saddr;
+	__be32				dp_daddr;
+	struct rds_ib_conn_priv_cmn	dp_cmn;
+};
+
+struct rds6_ib_connect_private {
+	/* Add new fields at the end, and don't permute existing fields. */
+	struct in6_addr			dp_saddr;
+	struct in6_addr			dp_daddr;
+	struct rds_ib_conn_priv_cmn	dp_cmn;
+};
+
+#define dp_protocol_major	dp_cmn.ricpc_protocol_major
+#define dp_protocol_minor	dp_cmn.ricpc_protocol_minor
+#define dp_protocol_minor_mask	dp_cmn.ricpc_protocol_minor_mask
+#define dp_ack_seq		dp_cmn.ricpc_ack_seq
+#define dp_credit		dp_cmn.ricpc_credit
+
+union rds_ib_conn_priv {
+	struct rds_ib_connect_private	ricp_v4;
+	struct rds6_ib_connect_private	ricp_v6;
 };
 
 struct rds_ib_send_work {
@@ -351,8 +379,8 @@ void rds_ib_listen_stop(void);
 __printf(2, 3)
 void __rds_ib_conn_error(struct rds_connection *conn, const char *, ...);
 int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
-			     struct rdma_cm_event *event);
-int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id);
+			     struct rdma_cm_event *event, bool isv6);
+int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6);
 void rds_ib_cm_connect_complete(struct rds_connection *conn,
 				struct rdma_cm_event *event);
 
@@ -361,7 +389,8 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn,
 	__rds_ib_conn_error(conn, KERN_WARNING "RDS/IB: " fmt)
 
 /* ib_rdma.c */
-int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr);
+int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev,
+			 struct in6_addr *ipaddr);
 void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
 void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
 void rds_ib_destroy_nodev_conns(void);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index f1684ae6abfd..dd8a867e5a9c 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -35,6 +35,7 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/ratelimit.h>
+#include <net/addrconf.h>
 
 #include "rds_single_path.h"
 #include "rds.h"
@@ -95,25 +96,45 @@ rds_ib_tune_rnr(struct rds_ib_connection *ic, struct ib_qp_attr *attr)
  */
 void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_event *event)
 {
-	const struct rds_ib_connect_private *dp = NULL;
 	struct rds_ib_connection *ic = conn->c_transport_data;
+	const union rds_ib_conn_priv *dp = NULL;
 	struct ib_qp_attr qp_attr;
+	__be64 ack_seq = 0;
+	__be32 credit = 0;
+	u8 major = 0;
+	u8 minor = 0;
 	int err;
 
-	if (event->param.conn.private_data_len >= sizeof(*dp)) {
-		dp = event->param.conn.private_data;
-
-		/* make sure it isn't empty data */
-		if (dp->dp_protocol_major) {
-			rds_ib_set_protocol(conn,
-				RDS_PROTOCOL(dp->dp_protocol_major,
-				dp->dp_protocol_minor));
-			rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit));
+	dp = event->param.conn.private_data;
+	if (conn->c_isv6) {
+		if (event->param.conn.private_data_len >=
+		    sizeof(struct rds6_ib_connect_private)) {
+			major = dp->ricp_v6.dp_protocol_major;
+			minor = dp->ricp_v6.dp_protocol_minor;
+			credit = dp->ricp_v6.dp_credit;
+			/* dp structure start is not guaranteed to be 8 bytes
+			 * aligned.  Since dp_ack_seq is 64-bit extended load
+			 * operations can be used so go through get_unaligned
+			 * to avoid unaligned errors.
+			 */
+			ack_seq = get_unaligned(&dp->ricp_v6.dp_ack_seq);
 		}
+	} else if (event->param.conn.private_data_len >=
+		   sizeof(struct rds_ib_connect_private)) {
+		major = dp->ricp_v4.dp_protocol_major;
+		minor = dp->ricp_v4.dp_protocol_minor;
+		credit = dp->ricp_v4.dp_credit;
+		ack_seq = get_unaligned(&dp->ricp_v4.dp_ack_seq);
+	}
+
+	/* make sure it isn't empty data */
+	if (major) {
+		rds_ib_set_protocol(conn, RDS_PROTOCOL(major, minor));
+		rds_ib_set_flow_control(conn, be32_to_cpu(credit));
 	}
 
 	if (conn->c_version < RDS_PROTOCOL(3, 1)) {
-		pr_notice("RDS/IB: Connection <%pI4,%pI4> version %u.%u no longer supported\n",
+		pr_notice("RDS/IB: Connection <%pI6c,%pI6c> version %u.%u no longer supported\n",
 			  &conn->c_laddr, &conn->c_faddr,
 			  RDS_PROTOCOL_MAJOR(conn->c_version),
 			  RDS_PROTOCOL_MINOR(conn->c_version));
@@ -121,7 +142,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 		rds_conn_destroy(conn);
 		return;
 	} else {
-		pr_notice("RDS/IB: %s conn connected <%pI4,%pI4> version %u.%u%s\n",
+		pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c> version %u.%u%s\n",
 			  ic->i_active_side ? "Active" : "Passive",
 			  &conn->c_laddr, &conn->c_faddr,
 			  RDS_PROTOCOL_MAJOR(conn->c_version),
@@ -150,7 +171,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 		printk(KERN_NOTICE "ib_modify_qp(IB_QP_STATE, RTS): err=%d\n", err);
 
 	/* update ib_device with this local ipaddr */
-	err = rds_ib_update_ipaddr(ic->rds_ibdev, conn->c_laddr);
+	err = rds_ib_update_ipaddr(ic->rds_ibdev, &conn->c_laddr);
 	if (err)
 		printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n",
 			err);
@@ -158,14 +179,8 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 	/* If the peer gave us the last packet it saw, process this as if
 	 * we had received a regular ACK. */
 	if (dp) {
-		/* dp structure start is not guaranteed to be 8 bytes aligned.
-		 * Since dp_ack_seq is 64-bit extended load operations can be
-		 * used so go through get_unaligned to avoid unaligned errors.
-		 */
-		__be64 dp_ack_seq = get_unaligned(&dp->dp_ack_seq);
-
-		if (dp_ack_seq)
-			rds_send_drop_acked(conn, be64_to_cpu(dp_ack_seq),
+		if (ack_seq)
+			rds_send_drop_acked(conn, be64_to_cpu(ack_seq),
 					    NULL);
 	}
 
@@ -173,11 +188,12 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 }
 
 static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
-			struct rdma_conn_param *conn_param,
-			struct rds_ib_connect_private *dp,
-			u32 protocol_version,
-			u32 max_responder_resources,
-			u32 max_initiator_depth)
+				      struct rdma_conn_param *conn_param,
+				      union rds_ib_conn_priv *dp,
+				      u32 protocol_version,
+				      u32 max_responder_resources,
+				      u32 max_initiator_depth,
+				      bool isv6)
 {
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	struct rds_ib_device *rds_ibdev = ic->rds_ibdev;
@@ -193,24 +209,49 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn,
 
 	if (dp) {
 		memset(dp, 0, sizeof(*dp));
-		dp->dp_saddr = conn->c_laddr;
-		dp->dp_daddr = conn->c_faddr;
-		dp->dp_protocol_major = RDS_PROTOCOL_MAJOR(protocol_version);
-		dp->dp_protocol_minor = RDS_PROTOCOL_MINOR(protocol_version);
-		dp->dp_protocol_minor_mask = cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
-		dp->dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic));
+		if (isv6) {
+			dp->ricp_v6.dp_saddr = conn->c_laddr;
+			dp->ricp_v6.dp_daddr = conn->c_faddr;
+			dp->ricp_v6.dp_protocol_major =
+			    RDS_PROTOCOL_MAJOR(protocol_version);
+			dp->ricp_v6.dp_protocol_minor =
+			    RDS_PROTOCOL_MINOR(protocol_version);
+			dp->ricp_v6.dp_protocol_minor_mask =
+			    cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
+			dp->ricp_v6.dp_ack_seq =
+			    cpu_to_be64(rds_ib_piggyb_ack(ic));
+
+			conn_param->private_data = &dp->ricp_v6;
+			conn_param->private_data_len = sizeof(dp->ricp_v6);
+		} else {
+			dp->ricp_v4.dp_saddr = conn->c_laddr.s6_addr32[3];
+			dp->ricp_v4.dp_daddr = conn->c_faddr.s6_addr32[3];
+			dp->ricp_v4.dp_protocol_major =
+			    RDS_PROTOCOL_MAJOR(protocol_version);
+			dp->ricp_v4.dp_protocol_minor =
+			    RDS_PROTOCOL_MINOR(protocol_version);
+			dp->ricp_v4.dp_protocol_minor_mask =
+			    cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS);
+			dp->ricp_v4.dp_ack_seq =
+			    cpu_to_be64(rds_ib_piggyb_ack(ic));
+
+			conn_param->private_data = &dp->ricp_v4;
+			conn_param->private_data_len = sizeof(dp->ricp_v4);
+		}
 
 		/* Advertise flow control */
 		if (ic->i_flowctl) {
 			unsigned int credits;
 
-			credits = IB_GET_POST_CREDITS(atomic_read(&ic->i_credits));
-			dp->dp_credit = cpu_to_be32(credits);
-			atomic_sub(IB_SET_POST_CREDITS(credits), &ic->i_credits);
+			credits = IB_GET_POST_CREDITS
+				(atomic_read(&ic->i_credits));
+			if (isv6)
+				dp->ricp_v6.dp_credit = cpu_to_be32(credits);
+			else
+				dp->ricp_v4.dp_credit = cpu_to_be32(credits);
+			atomic_sub(IB_SET_POST_CREDITS(credits),
+				   &ic->i_credits);
 		}
-
-		conn_param->private_data = dp;
-		conn_param->private_data_len = sizeof(*dp);
 	}
 }
 
@@ -349,7 +390,7 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data)
 		break;
 	default:
 		rdsdebug("Fatal QP Event %u (%s) "
-			"- connection %pI4->%pI4, reconnecting\n",
+			"- connection %pI6c->%pI6c, reconnecting\n",
 			event->event, ib_event_msg(event->event),
 			&conn->c_laddr, &conn->c_faddr);
 		rds_conn_drop(conn);
@@ -580,11 +621,13 @@ out:
 	return ret;
 }
 
-static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event)
+static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
 {
-	const struct rds_ib_connect_private *dp = event->param.conn.private_data;
-	u16 common;
+	const union rds_ib_conn_priv *dp = event->param.conn.private_data;
+	u8 data_len, major, minor;
 	u32 version = 0;
+	__be16 mask;
+	u16 common;
 
 	/*
 	 * rdma_cm private data is odd - when there is any private data in the
@@ -603,51 +646,126 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event)
 		return 0;
 	}
 
+	if (isv6) {
+		data_len = sizeof(struct rds6_ib_connect_private);
+		major = dp->ricp_v6.dp_protocol_major;
+		minor = dp->ricp_v6.dp_protocol_minor;
+		mask = dp->ricp_v6.dp_protocol_minor_mask;
+	} else {
+		data_len = sizeof(struct rds_ib_connect_private);
+		major = dp->ricp_v4.dp_protocol_major;
+		minor = dp->ricp_v4.dp_protocol_minor;
+		mask = dp->ricp_v4.dp_protocol_minor_mask;
+	}
+
 	/* Even if len is crap *now* I still want to check it. -ASG */
-	if (event->param.conn.private_data_len < sizeof (*dp) ||
-	    dp->dp_protocol_major == 0)
+	if (event->param.conn.private_data_len < data_len || major == 0)
 		return RDS_PROTOCOL_3_0;
 
-	common = be16_to_cpu(dp->dp_protocol_minor_mask) & RDS_IB_SUPPORTED_PROTOCOLS;
-	if (dp->dp_protocol_major == 3 && common) {
+	common = be16_to_cpu(mask) & RDS_IB_SUPPORTED_PROTOCOLS;
+	if (major == 3 && common) {
 		version = RDS_PROTOCOL_3_0;
 		while ((common >>= 1) != 0)
 			version++;
-	} else
-		printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n",
-				&dp->dp_saddr,
-				dp->dp_protocol_major,
-				dp->dp_protocol_minor);
+	} else {
+		if (isv6)
+			printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI6c using incompatible protocol version %u.%u\n",
+					   &dp->ricp_v6.dp_saddr, major, minor);
+		else
+			printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI4 using incompatible protocol version %u.%u\n",
+					   &dp->ricp_v4.dp_saddr, major, minor);
+	}
 	return version;
 }
 
+/* Given an IPv6 address, find the IB net_device which hosts that address and
+ * return its index.  This is used by the rds_ib_cm_handle_connect() code to
+ * find the interface index of where an incoming request comes from when
+ * the request is using a link local address.
+ *
+ * Note one problem in this search.  It is possible that two interfaces have
+ * the same link local address.  Unfortunately, this cannot be solved unless
+ * the underlying layer gives us the interface which an incoming RDMA connect
+ * request comes from.
+ */
+static u32 __rds_find_ifindex(struct net *net, const struct in6_addr *addr)
+{
+	struct net_device *dev;
+	int idx = 0;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(net, dev) {
+		if (dev->type == ARPHRD_INFINIBAND &&
+		    ipv6_chk_addr(net, addr, dev, 0)) {
+			idx = dev->ifindex;
+			break;
+		}
+	}
+	rcu_read_unlock();
+
+	return idx;
+}
+
 int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
-				    struct rdma_cm_event *event)
+			     struct rdma_cm_event *event, bool isv6)
 {
 	__be64 lguid = cm_id->route.path_rec->sgid.global.interface_id;
 	__be64 fguid = cm_id->route.path_rec->dgid.global.interface_id;
-	const struct rds_ib_connect_private *dp = event->param.conn.private_data;
-	struct rds_ib_connect_private dp_rep;
+	const struct rds_ib_conn_priv_cmn *dp_cmn;
 	struct rds_connection *conn = NULL;
 	struct rds_ib_connection *ic = NULL;
 	struct rdma_conn_param conn_param;
+	const union rds_ib_conn_priv *dp;
+	union rds_ib_conn_priv dp_rep;
+	struct in6_addr s_mapped_addr;
+	struct in6_addr d_mapped_addr;
+	const struct in6_addr *saddr6;
+	const struct in6_addr *daddr6;
+	int destroy = 1;
+	u32 ifindex = 0;
 	u32 version;
-	int err = 1, destroy = 1;
+	int err = 1;
 
 	/* Check whether the remote protocol version matches ours. */
-	version = rds_ib_protocol_compatible(event);
+	version = rds_ib_protocol_compatible(event, isv6);
 	if (!version)
 		goto out;
 
-	rdsdebug("saddr %pI4 daddr %pI4 RDSv%u.%u lguid 0x%llx fguid "
-		 "0x%llx\n", &dp->dp_saddr, &dp->dp_daddr,
+	dp = event->param.conn.private_data;
+	if (isv6) {
+		dp_cmn = &dp->ricp_v6.dp_cmn;
+		saddr6 = &dp->ricp_v6.dp_saddr;
+		daddr6 = &dp->ricp_v6.dp_daddr;
+		/* If the local address is link local, need to find the
+		 * interface index in order to create a proper RDS
+		 * connection.
+		 */
+		if (ipv6_addr_type(daddr6) & IPV6_ADDR_LINKLOCAL) {
+			/* Using init_net for now ..  */
+			ifindex = __rds_find_ifindex(&init_net, daddr6);
+			/* No index found...  Need to bail out. */
+			if (ifindex == 0) {
+				err = -EOPNOTSUPP;
+				goto out;
+			}
+		}
+	} else {
+		dp_cmn = &dp->ricp_v4.dp_cmn;
+		ipv6_addr_set_v4mapped(dp->ricp_v4.dp_saddr, &s_mapped_addr);
+		ipv6_addr_set_v4mapped(dp->ricp_v4.dp_daddr, &d_mapped_addr);
+		saddr6 = &s_mapped_addr;
+		daddr6 = &d_mapped_addr;
+	}
+
+	rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid "
+		 "0x%llx\n", saddr6, daddr6,
 		 RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version),
 		 (unsigned long long)be64_to_cpu(lguid),
 		 (unsigned long long)be64_to_cpu(fguid));
 
 	/* RDS/IB is not currently netns aware, thus init_net */
-	conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr,
-			       &rds_ib_transport, GFP_KERNEL);
+	conn = rds_conn_create(&init_net, daddr6, saddr6,
+			       &rds_ib_transport, GFP_KERNEL, ifindex);
 	if (IS_ERR(conn)) {
 		rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn));
 		conn = NULL;
@@ -678,12 +796,13 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 	ic = conn->c_transport_data;
 
 	rds_ib_set_protocol(conn, version);
-	rds_ib_set_flow_control(conn, be32_to_cpu(dp->dp_credit));
+	rds_ib_set_flow_control(conn, be32_to_cpu(dp_cmn->ricpc_credit));
 
 	/* If the peer gave us the last packet it saw, process this as if
 	 * we had received a regular ACK. */
-	if (dp->dp_ack_seq)
-		rds_send_drop_acked(conn, be64_to_cpu(dp->dp_ack_seq), NULL);
+	if (dp_cmn->ricpc_ack_seq)
+		rds_send_drop_acked(conn, be64_to_cpu(dp_cmn->ricpc_ack_seq),
+				    NULL);
 
 	BUG_ON(cm_id->context);
 	BUG_ON(ic->i_cm_id);
@@ -702,8 +821,8 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 	}
 
 	rds_ib_cm_fill_conn_param(conn, &conn_param, &dp_rep, version,
-		event->param.conn.responder_resources,
-		event->param.conn.initiator_depth);
+				  event->param.conn.responder_resources,
+				  event->param.conn.initiator_depth, isv6);
 
 	/* rdma_accept() calls rdma_reject() internally if it fails */
 	if (rdma_accept(cm_id, &conn_param))
@@ -718,12 +837,12 @@ out:
 }
 
 
-int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id)
+int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6)
 {
 	struct rds_connection *conn = cm_id->context;
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	struct rdma_conn_param conn_param;
-	struct rds_ib_connect_private dp;
+	union rds_ib_conn_priv dp;
 	int ret;
 
 	/* If the peer doesn't do protocol negotiation, we must
@@ -738,7 +857,7 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id)
 	}
 
 	rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, RDS_PROTOCOL_VERSION,
-		UINT_MAX, UINT_MAX);
+				  UINT_MAX, UINT_MAX, isv6);
 	ret = rdma_connect(cm_id, &conn_param);
 	if (ret)
 		rds_ib_conn_error(conn, "rdma_connect failed (%d)\n", ret);
@@ -758,13 +877,17 @@ out:
 int rds_ib_conn_path_connect(struct rds_conn_path *cp)
 {
 	struct rds_connection *conn = cp->cp_conn;
-	struct rds_ib_connection *ic = conn->c_transport_data;
-	struct sockaddr_in src, dest;
+	struct sockaddr_storage src, dest;
+	rdma_cm_event_handler handler;
+	struct rds_ib_connection *ic;
 	int ret;
 
+	ic = conn->c_transport_data;
+
 	/* XXX I wonder what affect the port space has */
 	/* delegate cm event handler to rdma_transport */
-	ic->i_cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, conn,
+	handler = rds_rdma_cm_event_handler;
+	ic->i_cm_id = rdma_create_id(&init_net, handler, conn,
 				     RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(ic->i_cm_id)) {
 		ret = PTR_ERR(ic->i_cm_id);
@@ -775,13 +898,33 @@ int rds_ib_conn_path_connect(struct rds_conn_path *cp)
 
 	rdsdebug("created cm id %p for conn %p\n", ic->i_cm_id, conn);
 
-	src.sin_family = AF_INET;
-	src.sin_addr.s_addr = (__force u32)conn->c_laddr;
-	src.sin_port = (__force u16)htons(0);
+	if (ipv6_addr_v4mapped(&conn->c_faddr)) {
+		struct sockaddr_in *sin;
+
+		sin = (struct sockaddr_in *)&src;
+		sin->sin_family = AF_INET;
+		sin->sin_addr.s_addr = conn->c_laddr.s6_addr32[3];
+		sin->sin_port = 0;
 
-	dest.sin_family = AF_INET;
-	dest.sin_addr.s_addr = (__force u32)conn->c_faddr;
-	dest.sin_port = (__force u16)htons(RDS_PORT);
+		sin = (struct sockaddr_in *)&dest;
+		sin->sin_family = AF_INET;
+		sin->sin_addr.s_addr = conn->c_faddr.s6_addr32[3];
+		sin->sin_port = htons(RDS_PORT);
+	} else {
+		struct sockaddr_in6 *sin6;
+
+		sin6 = (struct sockaddr_in6 *)&src;
+		sin6->sin6_family = AF_INET6;
+		sin6->sin6_addr = conn->c_laddr;
+		sin6->sin6_port = 0;
+		sin6->sin6_scope_id = conn->c_dev_if;
+
+		sin6 = (struct sockaddr_in6 *)&dest;
+		sin6->sin6_family = AF_INET6;
+		sin6->sin6_addr = conn->c_faddr;
+		sin6->sin6_port = htons(RDS_CM_PORT);
+		sin6->sin6_scope_id = conn->c_dev_if;
+	}
 
 	ret = rdma_resolve_addr(ic->i_cm_id, (struct sockaddr *)&src,
 				(struct sockaddr *)&dest,
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e678699268a2..0ec9df043dd0 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -100,18 +100,19 @@ static void rds_ib_remove_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
 		kfree_rcu(to_free, rcu);
 }
 
-int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
+int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev,
+			 struct in6_addr *ipaddr)
 {
 	struct rds_ib_device *rds_ibdev_old;
 
-	rds_ibdev_old = rds_ib_get_device(ipaddr);
+	rds_ibdev_old = rds_ib_get_device(ipaddr->s6_addr32[3]);
 	if (!rds_ibdev_old)
-		return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
+		return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]);
 
 	if (rds_ibdev_old != rds_ibdev) {
-		rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr);
+		rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr->s6_addr32[3]);
 		rds_ib_dev_put(rds_ibdev_old);
-		return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
+		return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]);
 	}
 	rds_ib_dev_put(rds_ibdev_old);
 
@@ -544,7 +545,7 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 	struct rds_ib_connection *ic = rs->rs_conn->c_transport_data;
 	int ret;
 
-	rds_ibdev = rds_ib_get_device(rs->rs_bound_addr);
+	rds_ibdev = rds_ib_get_device(rs->rs_bound_addr.s6_addr32[3]);
 	if (!rds_ibdev) {
 		ret = -ENODEV;
 		goto out;
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 1eaf2550a9f8..557ccbb1ce00 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -266,7 +266,7 @@ static struct rds_ib_incoming *rds_ib_refill_one_inc(struct rds_ib_connection *i
 		rds_ib_stats_inc(s_ib_rx_total_incs);
 	}
 	INIT_LIST_HEAD(&ibinc->ii_frags);
-	rds_inc_init(&ibinc->ii_inc, ic->conn, ic->conn->c_faddr);
+	rds_inc_init(&ibinc->ii_inc, ic->conn, &ic->conn->c_faddr);
 
 	return ibinc;
 }
@@ -418,7 +418,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp)
 		ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr);
 		if (ret) {
 			rds_ib_conn_error(conn, "recv post on "
-			       "%pI4 returned %d, disconnecting and "
+			       "%pI6c returned %d, disconnecting and "
 			       "reconnecting\n", &conn->c_faddr,
 			       ret);
 			break;
@@ -848,7 +848,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 
 	if (data_len < sizeof(struct rds_header)) {
 		rds_ib_conn_error(conn, "incoming message "
-		       "from %pI4 didn't include a "
+		       "from %pI6c didn't include a "
 		       "header, disconnecting and "
 		       "reconnecting\n",
 		       &conn->c_faddr);
@@ -861,7 +861,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 	/* Validate the checksum. */
 	if (!rds_message_verify_checksum(ihdr)) {
 		rds_ib_conn_error(conn, "incoming message "
-		       "from %pI4 has corrupted header - "
+		       "from %pI6c has corrupted header - "
 		       "forcing a reconnect\n",
 		       &conn->c_faddr);
 		rds_stats_inc(s_recv_drop_bad_checksum);
@@ -941,10 +941,10 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 		ic->i_recv_data_rem = 0;
 		ic->i_ibinc = NULL;
 
-		if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP)
+		if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) {
 			rds_ib_cong_recv(conn, ibinc);
-		else {
-			rds_recv_incoming(conn, conn->c_faddr, conn->c_laddr,
+		} else {
+			rds_recv_incoming(conn, &conn->c_faddr, &conn->c_laddr,
 					  &ibinc->ii_inc, GFP_ATOMIC);
 			state->ack_next = be64_to_cpu(hdr->h_sequence);
 			state->ack_next_valid = 1;
@@ -988,7 +988,7 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
 	} else {
 		/* We expect errors as the qp is drained during shutdown */
 		if (rds_conn_up(conn) || rds_conn_connecting(conn))
-			rds_ib_conn_error(conn, "recv completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n",
+			rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
 					  &conn->c_laddr, &conn->c_faddr,
 					  wc->status,
 					  ib_wc_status_msg(wc->status));
diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index 8557a1cae041..c4cdfe491d96 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -305,7 +305,7 @@ void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
 
 	/* We expect errors as the qp is drained during shutdown */
 	if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) {
-		rds_ib_conn_error(conn, "send completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n",
+		rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
 				  &conn->c_laddr, &conn->c_faddr, wc->status,
 				  ib_wc_status_msg(wc->status));
 	}
@@ -730,7 +730,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
 		 first, &first->s_wr, ret, failed_wr);
 	BUG_ON(failed_wr != &first->s_wr);
 	if (ret) {
-		printk(KERN_WARNING "RDS/IB: ib_post_send to %pI4 "
+		printk(KERN_WARNING "RDS/IB: ib_post_send to %pI6c "
 		       "returned %d\n", &conn->c_faddr, ret);
 		rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
 		rds_ib_sub_signaled(ic, nr_sig);
@@ -827,7 +827,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op)
 		 send, &send->s_atomic_wr, ret, failed_wr);
 	BUG_ON(failed_wr != &send->s_atomic_wr.wr);
 	if (ret) {
-		printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI4 "
+		printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI6c "
 		       "returned %d\n", &conn->c_faddr, ret);
 		rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
 		rds_ib_sub_signaled(ic, nr_sig);
@@ -967,7 +967,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 		 first, &first->s_rdma_wr.wr, ret, failed_wr);
 	BUG_ON(failed_wr != &first->s_rdma_wr.wr);
 	if (ret) {
-		printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI4 "
+		printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI6c "
 		       "returned %d\n", &conn->c_faddr, ret);
 		rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
 		rds_ib_sub_signaled(ic, nr_sig);
diff --git a/net/rds/loop.c b/net/rds/loop.c
index feea1f96ee2a..1d73ad79c847 100644
--- a/net/rds/loop.c
+++ b/net/rds/loop.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -35,6 +35,7 @@
 #include <linux/in.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <linux/ipv6.h>
 
 #include "rds_single_path.h"
 #include "rds.h"
@@ -88,11 +89,11 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm,
 
 	BUG_ON(hdr_off || sg || off);
 
-	rds_inc_init(&rm->m_inc, conn, conn->c_laddr);
+	rds_inc_init(&rm->m_inc, conn, &conn->c_laddr);
 	/* For the embedded inc. Matching put is in loop_inc_free() */
 	rds_message_addref(rm);
 
-	rds_recv_incoming(conn, conn->c_laddr, conn->c_faddr, &rm->m_inc,
+	rds_recv_incoming(conn, &conn->c_laddr, &conn->c_faddr, &rm->m_inc,
 			  GFP_KERNEL);
 
 	rds_send_drop_acked(conn, be64_to_cpu(rm->m_inc.i_hdr.h_sequence),
diff --git a/net/rds/rdma.c b/net/rds/rdma.c
index 634cfcb7bba6..7b3998026825 100644
--- a/net/rds/rdma.c
+++ b/net/rds/rdma.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007 Oracle.  All rights reserved.
+ * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -183,7 +183,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 	long i;
 	int ret;
 
-	if (rs->rs_bound_addr == 0 || !rs->rs_transport) {
+	if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}
@@ -574,7 +574,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
 
 	args = CMSG_DATA(cmsg);
 
-	if (rs->rs_bound_addr == 0) {
+	if (ipv6_addr_any(&rs->rs_bound_addr)) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out_ret;
 	}
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index fc59821f0a27..f49abef69550 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2009 Oracle.  All rights reserved.
+ * Copyright (c) 2009, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -39,8 +39,9 @@
 
 static struct rdma_cm_id *rds_rdma_listen_id;
 
-int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
-			      struct rdma_cm_event *event)
+static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
+					 struct rdma_cm_event *event,
+					 bool isv6)
 {
 	/* this can be null in the listening path */
 	struct rds_connection *conn = cm_id->context;
@@ -72,7 +73,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 
 	switch (event->event) {
 	case RDMA_CM_EVENT_CONNECT_REQUEST:
-		ret = trans->cm_handle_connect(cm_id, event);
+		ret = trans->cm_handle_connect(cm_id, event, isv6);
 		break;
 
 	case RDMA_CM_EVENT_ADDR_RESOLVED:
@@ -90,7 +91,7 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 
 			ibic = conn->c_transport_data;
 			if (ibic && ibic->i_cm_id == cm_id)
-				ret = trans->cm_initiate_connect(cm_id);
+				ret = trans->cm_initiate_connect(cm_id, isv6);
 			else
 				rds_conn_drop(conn);
 		}
@@ -116,14 +117,14 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 
 	case RDMA_CM_EVENT_DISCONNECTED:
 		rdsdebug("DISCONNECT event - dropping connection "
-			"%pI4->%pI4\n", &conn->c_laddr,
+			 "%pI6c->%pI6c\n", &conn->c_laddr,
 			 &conn->c_faddr);
 		rds_conn_drop(conn);
 		break;
 
 	case RDMA_CM_EVENT_TIMEWAIT_EXIT:
 		if (conn) {
-			pr_info("RDS: RDMA_CM_EVENT_TIMEWAIT_EXIT event: dropping connection %pI4->%pI4\n",
+			pr_info("RDS: RDMA_CM_EVENT_TIMEWAIT_EXIT event: dropping connection %pI6c->%pI6c\n",
 				&conn->c_laddr, &conn->c_faddr);
 			rds_conn_drop(conn);
 		}
@@ -146,13 +147,20 @@ out:
 	return ret;
 }
 
-static int rds_rdma_listen_init(void)
+int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
+			      struct rdma_cm_event *event)
+{
+	return rds_rdma_cm_event_handler_cmn(cm_id, event, false);
+}
+
+static int rds_rdma_listen_init_common(rdma_cm_event_handler handler,
+				       struct sockaddr *sa,
+				       struct rdma_cm_id **ret_cm_id)
 {
-	struct sockaddr_in sin;
 	struct rdma_cm_id *cm_id;
 	int ret;
 
-	cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, NULL,
+	cm_id = rdma_create_id(&init_net, handler, NULL,
 			       RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(cm_id)) {
 		ret = PTR_ERR(cm_id);
@@ -161,15 +169,11 @@ static int rds_rdma_listen_init(void)
 		return ret;
 	}
 
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY);
-	sin.sin_port = (__force u16)htons(RDS_PORT);
-
 	/*
 	 * XXX I bet this binds the cm_id to a device.  If we want to support
 	 * fail-over we'll have to take this into consideration.
 	 */
-	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
+	ret = rdma_bind_addr(cm_id, sa);
 	if (ret) {
 		printk(KERN_ERR "RDS/RDMA: failed to setup listener, "
 		       "rdma_bind_addr() returned %d\n", ret);
@@ -185,7 +189,7 @@ static int rds_rdma_listen_init(void)
 
 	rdsdebug("cm %p listening on port %u\n", cm_id, RDS_PORT);
 
-	rds_rdma_listen_id = cm_id;
+	*ret_cm_id = cm_id;
 	cm_id = NULL;
 out:
 	if (cm_id)
@@ -193,6 +197,26 @@ out:
 	return ret;
 }
 
+/* Initialize the RDS RDMA listeners.  We create two listeners for
+ * compatibility reason.  The one on RDS_PORT is used for IPv4
+ * requests only.  The one on RDS_CM_PORT is used for IPv6 requests
+ * only.  So only IPv6 enabled RDS module will communicate using this
+ * port.
+ */
+static int rds_rdma_listen_init(void)
+{
+	int ret;
+	struct sockaddr_in sin;
+
+	sin.sin_family = PF_INET;
+	sin.sin_addr.s_addr = htonl(INADDR_ANY);
+	sin.sin_port = htons(RDS_PORT);
+	ret = rds_rdma_listen_init_common(rds_rdma_cm_event_handler,
+					  (struct sockaddr *)&sin,
+					  &rds_rdma_listen_id);
+	return ret;
+}
+
 static void rds_rdma_listen_stop(void)
 {
 	if (rds_rdma_listen_id) {
diff --git a/net/rds/rds.h b/net/rds/rds.h
index f2272fb8cd45..1bff26988a5e 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -10,6 +10,7 @@
 #include <linux/rds.h>
 #include <linux/rhashtable.h>
 #include <linux/refcount.h>
+#include <linux/in6.h>
 
 #include "info.h"
 
@@ -30,6 +31,7 @@
  * userspace from listening.
  */
 #define RDS_PORT	18634
+#define RDS_CM_PORT	16385
 
 #ifdef ATOMIC64_INIT
 #define KERNEL_HAS_ATOMIC64
@@ -61,7 +63,7 @@ void rdsdebug(char *fmt, ...)
 
 struct rds_cong_map {
 	struct rb_node		m_rb_node;
-	__be32			m_addr;
+	struct in6_addr		m_addr;
 	wait_queue_head_t	m_waitq;
 	struct list_head	m_conn_list;
 	unsigned long		m_page_addrs[RDS_CONG_MAP_PAGES];
@@ -136,11 +138,13 @@ struct rds_conn_path {
 /* One rds_connection per RDS address pair */
 struct rds_connection {
 	struct hlist_node	c_hash_node;
-	__be32			c_laddr;
-	__be32			c_faddr;
+	struct in6_addr		c_laddr;
+	struct in6_addr		c_faddr;
+	int			c_dev_if; /* c_laddrs's interface index */
 	unsigned int		c_loopback:1,
+				c_isv6:1,
 				c_ping_triggered:1,
-				c_pad_to_32:30;
+				c_pad_to_32:29;
 	int			c_npaths;
 	struct rds_connection	*c_passive;
 	struct rds_transport	*c_trans;
@@ -269,7 +273,7 @@ struct rds_incoming {
 	struct rds_conn_path	*i_conn_path;
 	struct rds_header	i_hdr;
 	unsigned long		i_rx_jiffies;
-	__be32			i_saddr;
+	struct in6_addr		i_saddr;
 
 	rds_rdma_cookie_t	i_rdma_cookie;
 	struct timeval		i_rx_tstamp;
@@ -386,7 +390,7 @@ struct rds_message {
 	struct list_head	m_conn_item;
 	struct rds_incoming	m_inc;
 	u64			m_ack_seq;
-	__be32			m_daddr;
+	struct in6_addr		m_daddr;
 	unsigned long		m_flags;
 
 	/* Never access m_rs without holding m_rs_lock.
@@ -519,7 +523,8 @@ struct rds_transport {
 				t_mp_capable:1;
 	unsigned int		t_type;
 
-	int (*laddr_check)(struct net *net, __be32 addr);
+	int (*laddr_check)(struct net *net, const struct in6_addr *addr,
+			   __u32 scope_id);
 	int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp);
 	void (*conn_free)(void *data);
 	int (*conn_path_connect)(struct rds_conn_path *cp);
@@ -535,8 +540,8 @@ struct rds_transport {
 	void (*inc_free)(struct rds_incoming *inc);
 
 	int (*cm_handle_connect)(struct rdma_cm_id *cm_id,
-				 struct rdma_cm_event *event);
-	int (*cm_initiate_connect)(struct rdma_cm_id *cm_id);
+				 struct rdma_cm_event *event, bool isv6);
+	int (*cm_initiate_connect)(struct rdma_cm_id *cm_id, bool isv6);
 	void (*cm_connect_complete)(struct rds_connection *conn,
 				    struct rdma_cm_event *event);
 
@@ -551,6 +556,12 @@ struct rds_transport {
 	bool (*t_unloading)(struct rds_connection *conn);
 };
 
+/* Bind hash table key length.  It is the sum of the size of a struct
+ * in6_addr, a scope_id  and a port.
+ */
+#define RDS_BOUND_KEY_LEN \
+	(sizeof(struct in6_addr) + sizeof(__u32) + sizeof(__be16))
+
 struct rds_sock {
 	struct sock		rs_sk;
 
@@ -562,10 +573,14 @@ struct rds_sock {
 	 * support.
 	 */
 	struct rhash_head	rs_bound_node;
-	u64			rs_bound_key;
-	__be32			rs_bound_addr;
-	__be32			rs_conn_addr;
-	__be16			rs_bound_port;
+	u8			rs_bound_key[RDS_BOUND_KEY_LEN];
+	struct sockaddr_in6	rs_bound_sin6;
+#define rs_bound_addr		rs_bound_sin6.sin6_addr
+#define rs_bound_addr_v4	rs_bound_sin6.sin6_addr.s6_addr32[3]
+#define rs_bound_port		rs_bound_sin6.sin6_port
+#define rs_bound_scope_id	rs_bound_sin6.sin6_scope_id
+	struct in6_addr		rs_conn_addr;
+#define rs_conn_addr_v4		rs_conn_addr.s6_addr32[3]
 	__be16			rs_conn_port;
 	struct rds_transport    *rs_transport;
 
@@ -701,7 +716,8 @@ extern wait_queue_head_t rds_poll_waitq;
 /* bind.c */
 int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len);
 void rds_remove_bound(struct rds_sock *rs);
-struct rds_sock *rds_find_bound(__be32 addr, __be16 port);
+struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
+				__u32 scope_id);
 int rds_bind_lock_init(void);
 void rds_bind_lock_destroy(void);
 
@@ -725,11 +741,15 @@ extern u32 rds_gen_num;
 int rds_conn_init(void);
 void rds_conn_exit(void);
 struct rds_connection *rds_conn_create(struct net *net,
-				       __be32 laddr, __be32 faddr,
-				       struct rds_transport *trans, gfp_t gfp);
+				       const struct in6_addr *laddr,
+				       const struct in6_addr *faddr,
+				       struct rds_transport *trans, gfp_t gfp,
+				       int dev_if);
 struct rds_connection *rds_conn_create_outgoing(struct net *net,
-						__be32 laddr, __be32 faddr,
-			       struct rds_transport *trans, gfp_t gfp);
+						const struct in6_addr *laddr,
+						const struct in6_addr *faddr,
+						struct rds_transport *trans,
+						gfp_t gfp, int dev_if);
 void rds_conn_shutdown(struct rds_conn_path *cpath);
 void rds_conn_destroy(struct rds_connection *conn);
 void rds_conn_drop(struct rds_connection *conn);
@@ -840,11 +860,12 @@ void rds_page_exit(void);
 
 /* recv.c */
 void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
-		  __be32 saddr);
+		  struct in6_addr *saddr);
 void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *conn,
-		       __be32 saddr);
+		       struct in6_addr *saddr);
 void rds_inc_put(struct rds_incoming *inc);
-void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
+void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr,
+		       struct in6_addr *daddr,
 		       struct rds_incoming *inc, gfp_t gfp);
 int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 		int msg_flags);
@@ -859,7 +880,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);
 void rds_send_path_reset(struct rds_conn_path *conn);
 int rds_send_xmit(struct rds_conn_path *cp);
 struct sockaddr_in;
-void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest);
+void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest);
 typedef int (*is_acked_func)(struct rds_message *rm, uint64_t ack);
 void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
 			 is_acked_func is_acked);
@@ -946,11 +967,14 @@ void rds_send_worker(struct work_struct *);
 void rds_recv_worker(struct work_struct *);
 void rds_connect_path_complete(struct rds_conn_path *conn, int curr);
 void rds_connect_complete(struct rds_connection *conn);
+int rds_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2);
 
 /* transport.c */
 void rds_trans_register(struct rds_transport *trans);
 void rds_trans_unregister(struct rds_transport *trans);
-struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr);
+struct rds_transport *rds_trans_get_preferred(struct net *net,
+					      const struct in6_addr *addr,
+					      __u32 scope_id);
 void rds_trans_put(struct rds_transport *trans);
 unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
 				       unsigned int avail);
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 192ac6f78ded..4217961fd130 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -41,14 +41,14 @@
 #include "rds.h"
 
 void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
-		  __be32 saddr)
+		 struct in6_addr *saddr)
 {
 	int i;
 
 	refcount_set(&inc->i_refcount, 1);
 	INIT_LIST_HEAD(&inc->i_item);
 	inc->i_conn = conn;
-	inc->i_saddr = saddr;
+	inc->i_saddr = *saddr;
 	inc->i_rdma_cookie = 0;
 	inc->i_rx_tstamp.tv_sec = 0;
 	inc->i_rx_tstamp.tv_usec = 0;
@@ -59,13 +59,13 @@ void rds_inc_init(struct rds_incoming *inc, struct rds_connection *conn,
 EXPORT_SYMBOL_GPL(rds_inc_init);
 
 void rds_inc_path_init(struct rds_incoming *inc, struct rds_conn_path *cp,
-		       __be32 saddr)
+		       struct in6_addr  *saddr)
 {
 	refcount_set(&inc->i_refcount, 1);
 	INIT_LIST_HEAD(&inc->i_item);
 	inc->i_conn = cp->cp_conn;
 	inc->i_conn_path = cp;
-	inc->i_saddr = saddr;
+	inc->i_saddr = *saddr;
 	inc->i_rdma_cookie = 0;
 	inc->i_rx_tstamp.tv_sec = 0;
 	inc->i_rx_tstamp.tv_usec = 0;
@@ -110,7 +110,7 @@ static void rds_recv_rcvbuf_delta(struct rds_sock *rs, struct sock *sk,
 
 	now_congested = rs->rs_rcv_bytes > rds_sk_rcvbuf(rs);
 
-	rdsdebug("rs %p (%pI4:%u) recv bytes %d buf %d "
+	rdsdebug("rs %p (%pI6c:%u) recv bytes %d buf %d "
 	  "now_cong %d delta %d\n",
 	  rs, &rs->rs_bound_addr,
 	  ntohs(rs->rs_bound_port), rs->rs_rcv_bytes,
@@ -260,7 +260,7 @@ static void rds_start_mprds(struct rds_connection *conn)
 	struct rds_conn_path *cp;
 
 	if (conn->c_npaths > 1 &&
-	    IS_CANONICAL(conn->c_laddr, conn->c_faddr)) {
+	    rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) < 0) {
 		for (i = 0; i < conn->c_npaths; i++) {
 			cp = &conn->c_path[i];
 			rds_conn_path_connect_if_down(cp);
@@ -284,7 +284,8 @@ static void rds_start_mprds(struct rds_connection *conn)
  * conn.  This lets loopback, who only has one conn for both directions,
  * tell us which roles the addrs in the conn are playing for this message.
  */
-void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
+void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr,
+		       struct in6_addr *daddr,
 		       struct rds_incoming *inc, gfp_t gfp)
 {
 	struct rds_sock *rs = NULL;
@@ -339,7 +340,8 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
 
 	if (rds_sysctl_ping_enable && inc->i_hdr.h_dport == 0) {
 		if (inc->i_hdr.h_sport == 0) {
-			rdsdebug("ignore ping with 0 sport from 0x%x\n", saddr);
+			rdsdebug("ignore ping with 0 sport from %pI6c\n",
+				 saddr);
 			goto out;
 		}
 		rds_stats_inc(s_recv_ping);
@@ -362,7 +364,7 @@ void rds_recv_incoming(struct rds_connection *conn, __be32 saddr, __be32 daddr,
 		goto out;
 	}
 
-	rs = rds_find_bound(daddr, inc->i_hdr.h_dport);
+	rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_dev_if);
 	if (!rs) {
 		rds_stats_inc(s_recv_drop_no_sock);
 		goto out;
@@ -625,6 +627,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 	struct rds_sock *rs = rds_sk_to_rs(sk);
 	long timeo;
 	int ret = 0, nonblock = msg_flags & MSG_DONTWAIT;
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
 	struct rds_incoming *inc = NULL;
 
@@ -673,7 +676,7 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 			break;
 		}
 
-		rdsdebug("copying inc %p from %pI4:%u to user\n", inc,
+		rdsdebug("copying inc %p from %pI6c:%u to user\n", inc,
 			 &inc->i_conn->c_faddr,
 			 ntohs(inc->i_hdr.h_sport));
 		ret = inc->i_conn->c_trans->inc_copy_to_user(inc, &msg->msg_iter);
@@ -707,12 +710,26 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 
 		rds_stats_inc(s_recv_delivered);
 
-		if (sin) {
-			sin->sin_family = AF_INET;
-			sin->sin_port = inc->i_hdr.h_sport;
-			sin->sin_addr.s_addr = inc->i_saddr;
-			memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
-			msg->msg_namelen = sizeof(*sin);
+		if (msg->msg_name) {
+			if (ipv6_addr_v4mapped(&inc->i_saddr)) {
+				sin = (struct sockaddr_in *)msg->msg_name;
+
+				sin->sin_family = AF_INET;
+				sin->sin_port = inc->i_hdr.h_sport;
+				sin->sin_addr.s_addr =
+				    inc->i_saddr.s6_addr32[3];
+				memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+				msg->msg_namelen = sizeof(*sin);
+			} else {
+				sin6 = (struct sockaddr_in6 *)msg->msg_name;
+
+				sin6->sin6_family = AF_INET6;
+				sin6->sin6_port = inc->i_hdr.h_sport;
+				sin6->sin6_addr = inc->i_saddr;
+				sin6->sin6_flowinfo = 0;
+				sin6->sin6_scope_id = rs->rs_bound_scope_id;
+				msg->msg_namelen = sizeof(*sin6);
+			}
 		}
 		break;
 	}
diff --git a/net/rds/send.c b/net/rds/send.c
index 94c7f74909be..6ed2e925c36a 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -709,7 +709,7 @@ void rds_send_drop_acked(struct rds_connection *conn, u64 ack,
 }
 EXPORT_SYMBOL_GPL(rds_send_drop_acked);
 
-void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
+void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in6 *dest)
 {
 	struct rds_message *rm, *tmp;
 	struct rds_connection *conn;
@@ -721,8 +721,9 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 	spin_lock_irqsave(&rs->rs_lock, flags);
 
 	list_for_each_entry_safe(rm, tmp, &rs->rs_send_queue, m_sock_item) {
-		if (dest && (dest->sin_addr.s_addr != rm->m_daddr ||
-			     dest->sin_port != rm->m_inc.i_hdr.h_dport))
+		if (dest &&
+		    (!ipv6_addr_equal(&dest->sin6_addr, &rm->m_daddr) ||
+		     dest->sin6_port != rm->m_inc.i_hdr.h_dport))
 			continue;
 
 		list_move(&rm->m_sock_item, &list);
@@ -1059,8 +1060,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 {
 	struct sock *sk = sock->sk;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
+	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
 	DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
-	__be32 daddr;
 	__be16 dport;
 	struct rds_message *rm = NULL;
 	struct rds_connection *conn;
@@ -1069,10 +1070,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	int nonblock = msg->msg_flags & MSG_DONTWAIT;
 	long timeo = sock_sndtimeo(sk, nonblock);
 	struct rds_conn_path *cpath;
+	struct in6_addr daddr;
+	__u32 scope_id = 0;
 	size_t total_payload_len = payload_len, rdma_payload_len = 0;
 	bool zcopy = ((msg->msg_flags & MSG_ZEROCOPY) &&
 		      sock_flag(rds_rs_to_sk(rs), SOCK_ZEROCOPY));
 	int num_sgs = ceil(payload_len, PAGE_SIZE);
+	int namelen;
 
 	/* Mirror Linux UDP mirror of BSD error message compatibility */
 	/* XXX: Perhaps MSG_MORE someday */
@@ -1081,27 +1085,59 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 		goto out;
 	}
 
-	if (msg->msg_namelen) {
-		/* XXX fail non-unicast destination IPs? */
-		if (msg->msg_namelen < sizeof(*usin) || usin->sin_family != AF_INET) {
+	namelen = msg->msg_namelen;
+	if (namelen != 0) {
+		if (namelen < sizeof(*usin)) {
+			ret = -EINVAL;
+			goto out;
+		}
+		switch (namelen) {
+		case sizeof(*usin):
+			if (usin->sin_family != AF_INET ||
+			    usin->sin_addr.s_addr == htonl(INADDR_ANY) ||
+			    usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) ||
+			    IN_MULTICAST(ntohl(usin->sin_addr.s_addr))) {
+				ret = -EINVAL;
+				goto out;
+			}
+			ipv6_addr_set_v4mapped(usin->sin_addr.s_addr, &daddr);
+			dport = usin->sin_port;
+			break;
+
+		case sizeof(*sin6): {
+			ret = -EPROTONOSUPPORT;
+			goto out;
+		}
+
+		default:
 			ret = -EINVAL;
 			goto out;
 		}
-		daddr = usin->sin_addr.s_addr;
-		dport = usin->sin_port;
 	} else {
 		/* We only care about consistency with ->connect() */
 		lock_sock(sk);
 		daddr = rs->rs_conn_addr;
 		dport = rs->rs_conn_port;
+		scope_id = rs->rs_bound_scope_id;
 		release_sock(sk);
 	}
 
 	lock_sock(sk);
-	if (daddr == 0 || rs->rs_bound_addr == 0) {
+	if (ipv6_addr_any(&rs->rs_bound_addr) || ipv6_addr_any(&daddr)) {
 		release_sock(sk);
-		ret = -ENOTCONN; /* XXX not a great errno */
+		ret = -ENOTCONN;
 		goto out;
+	} else if (namelen != 0) {
+		/* Cannot send to an IPv4 address using an IPv6 source
+		 * address and cannot send to an IPv6 address using an
+		 * IPv4 source address.
+		 */
+		if (ipv6_addr_v4mapped(&daddr) ^
+		    ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
+			release_sock(sk);
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
 	}
 	release_sock(sk);
 
@@ -1155,13 +1191,14 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 
 	/* rds_conn_create has a spinlock that runs with IRQ off.
 	 * Caching the conn in the socket helps a lot. */
-	if (rs->rs_conn && rs->rs_conn->c_faddr == daddr)
+	if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr))
 		conn = rs->rs_conn;
 	else {
 		conn = rds_conn_create_outgoing(sock_net(sock->sk),
-						rs->rs_bound_addr, daddr,
-					rs->rs_transport,
-					sock->sk->sk_allocation);
+						&rs->rs_bound_addr, &daddr,
+						rs->rs_transport,
+						sock->sk->sk_allocation,
+						scope_id);
 		if (IS_ERR(conn)) {
 			ret = PTR_ERR(conn);
 			goto out;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 351a28474667..dadb33790333 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -37,6 +37,8 @@
 #include <net/tcp.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/tcp.h>
+#include <net/addrconf.h>
 
 #include "rds.h"
 #include "tcp.h"
@@ -262,9 +264,33 @@ out:
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
 
-static int rds_tcp_laddr_check(struct net *net, __be32 addr)
+static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
+			       __u32 scope_id)
 {
-	if (inet_addr_type(net, addr) == RTN_LOCAL)
+	struct net_device *dev = NULL;
+	int ret;
+
+	if (ipv6_addr_v4mapped(addr)) {
+		if (inet_addr_type(net, addr->s6_addr32[3]) == RTN_LOCAL)
+			return 0;
+		return -EADDRNOTAVAIL;
+	}
+
+	/* If the scope_id is specified, check only those addresses
+	 * hosted on the specified interface.
+	 */
+	if (scope_id != 0) {
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(net, scope_id);
+		/* scope_id is not valid... */
+		if (!dev) {
+			rcu_read_unlock();
+			return -EADDRNOTAVAIL;
+		}
+		rcu_read_unlock();
+	}
+	ret = ipv6_chk_addr(net, addr, dev, 0);
+	if (ret)
 		return 0;
 	return -EADDRNOTAVAIL;
 }
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index d999e7075645..231ae927858e 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -66,7 +66,8 @@ void rds_tcp_state_change(struct sock *sk)
 		 * RDS connection as RDS_CONN_UP until the reconnect,
 		 * to avoid RDS datagram loss.
 		 */
-		if (!IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr) &&
+		if (rds_addr_cmp(&cp->cp_conn->c_laddr,
+				 &cp->cp_conn->c_faddr) >= 0 &&
 		    rds_conn_path_transition(cp, RDS_CONN_CONNECTING,
 					     RDS_CONN_ERROR)) {
 			rds_conn_path_drop(cp, false);
@@ -88,7 +89,9 @@ out:
 int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 {
 	struct socket *sock = NULL;
-	struct sockaddr_in src, dest;
+	struct sockaddr_in sin;
+	struct sockaddr *addr;
+	int addrlen;
 	int ret;
 	struct rds_connection *conn = cp->cp_conn;
 	struct rds_tcp_connection *tc = cp->cp_transport_data;
@@ -112,30 +115,33 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 
 	rds_tcp_tune(sock);
 
-	src.sin_family = AF_INET;
-	src.sin_addr.s_addr = (__force u32)conn->c_laddr;
-	src.sin_port = (__force u16)htons(0);
+	sin.sin_family = AF_INET;
+	sin.sin_addr.s_addr = conn->c_laddr.s6_addr32[3];
+	sin.sin_port = 0;
+	addr = (struct sockaddr *)&sin;
+	addrlen = sizeof(sin);
 
-	ret = sock->ops->bind(sock, (struct sockaddr *)&src, sizeof(src));
+	ret = sock->ops->bind(sock, addr, addrlen);
 	if (ret) {
-		rdsdebug("bind failed with %d at address %pI4\n",
+		rdsdebug("bind failed with %d at address %pI6c\n",
 			 ret, &conn->c_laddr);
 		goto out;
 	}
 
-	dest.sin_family = AF_INET;
-	dest.sin_addr.s_addr = (__force u32)conn->c_faddr;
-	dest.sin_port = (__force u16)htons(RDS_TCP_PORT);
+	sin.sin_family = AF_INET;
+	sin.sin_addr.s_addr = conn->c_faddr.s6_addr32[3];
+	sin.sin_port = htons(RDS_TCP_PORT);
+	addr = (struct sockaddr *)&sin;
+	addrlen = sizeof(sin);
 
 	/*
 	 * once we call connect() we can start getting callbacks and they
 	 * own the socket
 	 */
 	rds_tcp_set_callbacks(sock, cp);
-	ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest),
-				 O_NONBLOCK);
+	ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK);
 
-	rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret);
+	rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret);
 	if (ret == -EINPROGRESS)
 		ret = 0;
 	if (ret == 0) {
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 22571189f21e..4fdf5b3a47df 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2018 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -83,13 +83,12 @@ static
 struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)
 {
 	int i;
-	bool peer_is_smaller = IS_CANONICAL(conn->c_faddr, conn->c_laddr);
 	int npaths = max_t(int, 1, conn->c_npaths);
 
 	/* for mprds, all paths MUST be initiated by the peer
 	 * with the smaller address.
 	 */
-	if (!peer_is_smaller) {
+	if (rds_addr_cmp(&conn->c_faddr, &conn->c_laddr) >= 0) {
 		/* Make sure we initiate at least one path if this
 		 * has not already been done; rds_start_mprds() will
 		 * take care of additional paths, if necessary.
@@ -164,13 +163,16 @@ int rds_tcp_accept_one(struct socket *sock)
 
 	inet = inet_sk(new_sock->sk);
 
-	rdsdebug("accepted tcp %pI4:%u -> %pI4:%u\n",
-		 &inet->inet_saddr, ntohs(inet->inet_sport),
-		 &inet->inet_daddr, ntohs(inet->inet_dport));
+	rdsdebug("accepted tcp %pI6c:%u -> %pI6c:%u\n",
+		 &new_sock->sk->sk_v6_rcv_saddr, ntohs(inet->inet_sport),
+		 &new_sock->sk->sk_v6_daddr, ntohs(inet->inet_dport));
 
 	conn = rds_conn_create(sock_net(sock->sk),
-			       inet->inet_saddr, inet->inet_daddr,
-			       &rds_tcp_transport, GFP_KERNEL);
+			       &new_sock->sk->sk_v6_rcv_saddr,
+			       &new_sock->sk->sk_v6_daddr,
+			       &rds_tcp_transport, GFP_KERNEL,
+			       new_sock->sk->sk_bound_dev_if);
+
 	if (IS_ERR(conn)) {
 		ret = PTR_ERR(conn);
 		goto out;
diff --git a/net/rds/tcp_recv.c b/net/rds/tcp_recv.c
index b9fbd2ee74ef..42c5ff1eda95 100644
--- a/net/rds/tcp_recv.c
+++ b/net/rds/tcp_recv.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -179,7 +179,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			tc->t_tinc = tinc;
 			rdsdebug("alloced tinc %p\n", tinc);
 			rds_inc_path_init(&tinc->ti_inc, cp,
-					  cp->cp_conn->c_faddr);
+					  &cp->cp_conn->c_faddr);
 			tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] =
 					local_clock();
 
@@ -239,8 +239,9 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			if (tinc->ti_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP)
 				rds_tcp_cong_recv(conn, tinc);
 			else
-				rds_recv_incoming(conn, conn->c_faddr,
-						  conn->c_laddr, &tinc->ti_inc,
+				rds_recv_incoming(conn, &conn->c_faddr,
+						  &conn->c_laddr,
+						  &tinc->ti_inc,
 						  arg->gfp);
 
 			tc->t_tinc_hdr_rem = sizeof(struct rds_header);
diff --git a/net/rds/tcp_send.c b/net/rds/tcp_send.c
index 7df869d37afd..78a2554a4497 100644
--- a/net/rds/tcp_send.c
+++ b/net/rds/tcp_send.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -153,7 +153,7 @@ out:
 			 * an incoming RST.
 			 */
 			if (rds_conn_path_up(cp)) {
-				pr_warn("RDS/tcp: send to %pI4 on cp [%d]"
+				pr_warn("RDS/tcp: send to %pI6c on cp [%d]"
 					"returned %d, "
 					"disconnecting and reconnecting\n",
 					&conn->c_faddr, cp->cp_index, ret);
diff --git a/net/rds/threads.c b/net/rds/threads.c
index c52861d77a59..e64f9e4c3cda 100644
--- a/net/rds/threads.c
+++ b/net/rds/threads.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -82,8 +82,8 @@ void rds_connect_path_complete(struct rds_conn_path *cp, int curr)
 		return;
 	}
 
-	rdsdebug("conn %p for %pI4 to %pI4 complete\n",
-	  cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr);
+	rdsdebug("conn %p for %pI6c to %pI6c complete\n",
+		 cp->cp_conn, &cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr);
 
 	cp->cp_reconnect_jiffies = 0;
 	set_bit(0, &cp->cp_conn->c_map_queued);
@@ -125,13 +125,13 @@ void rds_queue_reconnect(struct rds_conn_path *cp)
 	unsigned long rand;
 	struct rds_connection *conn = cp->cp_conn;
 
-	rdsdebug("conn %p for %pI4 to %pI4 reconnect jiffies %lu\n",
-	  conn, &conn->c_laddr, &conn->c_faddr,
-	  cp->cp_reconnect_jiffies);
+	rdsdebug("conn %p for %pI6c to %pI6c reconnect jiffies %lu\n",
+		 conn, &conn->c_laddr, &conn->c_faddr,
+		 cp->cp_reconnect_jiffies);
 
 	/* let peer with smaller addr initiate reconnect, to avoid duels */
 	if (conn->c_trans->t_type == RDS_TRANS_TCP &&
-	    !IS_CANONICAL(conn->c_laddr, conn->c_faddr))
+	    rds_addr_cmp(&conn->c_laddr, &conn->c_faddr) >= 0)
 		return;
 
 	set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
@@ -145,7 +145,7 @@ void rds_queue_reconnect(struct rds_conn_path *cp)
 	}
 
 	get_random_bytes(&rand, sizeof(rand));
-	rdsdebug("%lu delay %lu ceil conn %p for %pI4 -> %pI4\n",
+	rdsdebug("%lu delay %lu ceil conn %p for %pI6c -> %pI6c\n",
 		 rand % cp->cp_reconnect_jiffies, cp->cp_reconnect_jiffies,
 		 conn, &conn->c_laddr, &conn->c_faddr);
 	rcu_read_lock();
@@ -167,14 +167,14 @@ void rds_connect_worker(struct work_struct *work)
 	int ret;
 
 	if (cp->cp_index > 0 &&
-	    !IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr))
+	    rds_addr_cmp(&cp->cp_conn->c_laddr, &cp->cp_conn->c_faddr) >= 0)
 		return;
 	clear_bit(RDS_RECONNECT_PENDING, &cp->cp_flags);
 	ret = rds_conn_path_transition(cp, RDS_CONN_DOWN, RDS_CONN_CONNECTING);
 	if (ret) {
 		ret = conn->c_trans->conn_path_connect(cp);
-		rdsdebug("conn %p for %pI4 to %pI4 dispatched, ret %d\n",
-			conn, &conn->c_laddr, &conn->c_faddr, ret);
+		rdsdebug("conn %p for %pI6c to %pI6c dispatched, ret %d\n",
+			 conn, &conn->c_laddr, &conn->c_faddr, ret);
 
 		if (ret) {
 			if (rds_conn_path_transition(cp,
@@ -259,3 +259,50 @@ int rds_threads_init(void)
 
 	return 0;
 }
+
+/* Compare two IPv6 addresses.  Return 0 if the two addresses are equal.
+ * Return 1 if the first is greater.  Return -1 if the second is greater.
+ */
+int rds_addr_cmp(const struct in6_addr *addr1,
+		 const struct in6_addr *addr2)
+{
+#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
+	const __be64 *a1, *a2;
+	u64 x, y;
+
+	a1 = (__be64 *)addr1;
+	a2 = (__be64 *)addr2;
+
+	if (*a1 != *a2) {
+		if (be64_to_cpu(*a1) < be64_to_cpu(*a2))
+			return -1;
+		else
+			return 1;
+	} else {
+		x = be64_to_cpu(*++a1);
+		y = be64_to_cpu(*++a2);
+		if (x < y)
+			return -1;
+		else if (x > y)
+			return 1;
+		else
+			return 0;
+	}
+#else
+	u32 a, b;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		if (addr1->s6_addr32[i] != addr2->s6_addr32[i]) {
+			a = ntohl(addr1->s6_addr32[i]);
+			b = ntohl(addr2->s6_addr32[i]);
+			if (a < b)
+				return -1;
+			else if (a > b)
+				return 1;
+		}
+	}
+	return 0;
+#endif
+}
+EXPORT_SYMBOL_GPL(rds_addr_cmp);
diff --git a/net/rds/transport.c b/net/rds/transport.c
index 0b188dd0a344..c9788dbce441 100644
--- a/net/rds/transport.c
+++ b/net/rds/transport.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -33,6 +33,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/in.h>
+#include <linux/ipv6.h>
 
 #include "rds.h"
 #include "loop.h"
@@ -75,20 +76,26 @@ void rds_trans_put(struct rds_transport *trans)
 		module_put(trans->t_owner);
 }
 
-struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr)
+struct rds_transport *rds_trans_get_preferred(struct net *net,
+					      const struct in6_addr *addr,
+					      __u32 scope_id)
 {
 	struct rds_transport *ret = NULL;
 	struct rds_transport *trans;
 	unsigned int i;
 
-	if (IN_LOOPBACK(ntohl(addr)))
+	if (ipv6_addr_v4mapped(addr)) {
+		if (*(u_int8_t *)&addr->s6_addr32[3] == IN_LOOPBACKNET)
+			return &rds_loop_transport;
+	} else if (ipv6_addr_loopback(addr)) {
 		return &rds_loop_transport;
+	}
 
 	down_read(&rds_trans_sem);
 	for (i = 0; i < RDS_TRANS_COUNT; i++) {
 		trans = transports[i];
 
-		if (trans && (trans->laddr_check(net, addr) == 0) &&
+		if (trans && (trans->laddr_check(net, addr, scope_id) == 0) &&
 		    (!trans->t_owner || try_module_get(trans->t_owner))) {
 			ret = trans;
 			break;
-- 
cgit v1.2.3


From 1e2b44e78eead7bcadfbf96f70d95773191541c9 Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Mon, 23 Jul 2018 20:51:22 -0700
Subject: rds: Enable RDS IPv6 support

This patch enables RDS to use IPv6 addresses. For RDS/TCP, the
listener is now an IPv6 endpoint which accepts both IPv4 and IPv6
connection requests.  RDS/RDMA/IB uses a private data (struct
rds_ib_connect_private) exchange between endpoints at RDS connection
establishment time to support RDMA. This private data exchange uses a
32 bit integer to represent an IP address. This needs to be changed in
order to support IPv6. A new private data struct
rds6_ib_connect_private is introduced to handle this. To ensure
backward compatibility, an IPv6 capable RDS stack uses another RDMA
listener port (RDS_CM_PORT) to accept IPv6 connection. And it
continues to use the original RDS_PORT for IPv4 RDS connections. When
it needs to communicate with an IPv6 peer, it uses the RDS_CM_PORT to
send the connection set up request.

v5: Fixed syntax problem (David Miller).

v4: Changed port history comments in rds.h (Sowmini Varadhan).

v3: Added support to set up IPv4 connection using mapped address
    (David Miller).
    Added support to set up connection between link local and non-link
    addresses.
    Various review comments from Santosh Shilimkar and Sowmini Varadhan.

v2: Fixed bound and peer address scope mismatched issue.
    Added back rds_connect() IPv6 changes.

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/af_rds.c         | 91 ++++++++++++++++++++++++++++++++++++++++--------
 net/rds/bind.c           | 59 ++++++++++++++++++++++++++-----
 net/rds/connection.c     | 54 ++++++++++++++++++++--------
 net/rds/ib.c             | 55 ++++++++++++++++++++++++-----
 net/rds/ib_cm.c          | 20 ++++++++---
 net/rds/rdma_transport.c | 30 +++++++++++++++-
 net/rds/rdma_transport.h |  5 +++
 net/rds/rds.h            | 22 +++++++-----
 net/rds/recv.c           |  2 +-
 net/rds/send.c           | 61 ++++++++++++++++++++++++++++----
 net/rds/tcp.c            | 54 +++++++++++++++++-----------
 net/rds/tcp.h            |  2 +-
 net/rds/tcp_connect.c    | 54 +++++++++++++++++++++-------
 net/rds/tcp_listen.c     | 64 +++++++++++++++++++++++++++-------
 14 files changed, 459 insertions(+), 114 deletions(-)

diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index fc1a5c63b783..fc5c48b248fe 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -142,15 +142,32 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
 			uaddr_len = sizeof(*sin6);
 		}
 	} else {
-		/* If socket is not yet bound, set the return address family
-		 * to be AF_UNSPEC (value 0) and the address size to be that
-		 * of an IPv4 address.
+		/* If socket is not yet bound and the socket is connected,
+		 * set the return address family to be the same as the
+		 * connected address, but with 0 address value.  If it is not
+		 * connected, set the family to be AF_UNSPEC (value 0) and
+		 * the address size to be that of an IPv4 address.
 		 */
 		if (ipv6_addr_any(&rs->rs_bound_addr)) {
-			sin = (struct sockaddr_in *)uaddr;
-			memset(sin, 0, sizeof(*sin));
-			sin->sin_family = AF_UNSPEC;
-			return sizeof(*sin);
+			if (ipv6_addr_any(&rs->rs_conn_addr)) {
+				sin = (struct sockaddr_in *)uaddr;
+				memset(sin, 0, sizeof(*sin));
+				sin->sin_family = AF_UNSPEC;
+				return sizeof(*sin);
+			}
+
+			if (ipv6_addr_type(&rs->rs_conn_addr) &
+			    IPV6_ADDR_MAPPED) {
+				sin = (struct sockaddr_in *)uaddr;
+				memset(sin, 0, sizeof(*sin));
+				sin->sin_family = AF_INET;
+				return sizeof(*sin);
+			}
+
+			sin6 = (struct sockaddr_in6 *)uaddr;
+			memset(sin6, 0, sizeof(*sin6));
+			sin6->sin6_family = AF_INET6;
+			return sizeof(*sin6);
 		}
 		if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
 			sin = (struct sockaddr_in *)uaddr;
@@ -484,16 +501,18 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_in *sin;
+	struct sockaddr_in6 *sin6;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
+	int addr_type;
 	int ret = 0;
 
 	lock_sock(sk);
 
-	switch (addr_len) {
-	case sizeof(struct sockaddr_in):
+	switch (uaddr->sa_family) {
+	case AF_INET:
 		sin = (struct sockaddr_in *)uaddr;
-		if (sin->sin_family != AF_INET) {
-			ret = -EAFNOSUPPORT;
+		if (addr_len < sizeof(struct sockaddr_in)) {
+			ret = -EINVAL;
 			break;
 		}
 		if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
@@ -509,12 +528,56 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 		rs->rs_conn_port = sin->sin_port;
 		break;
 
-	case sizeof(struct sockaddr_in6):
-		ret = -EPROTONOSUPPORT;
+	case AF_INET6:
+		sin6 = (struct sockaddr_in6 *)uaddr;
+		if (addr_len < sizeof(struct sockaddr_in6)) {
+			ret = -EINVAL;
+			break;
+		}
+		addr_type = ipv6_addr_type(&sin6->sin6_addr);
+		if (!(addr_type & IPV6_ADDR_UNICAST)) {
+			__be32 addr4;
+
+			if (!(addr_type & IPV6_ADDR_MAPPED)) {
+				ret = -EPROTOTYPE;
+				break;
+			}
+
+			/* It is a mapped address.  Need to do some sanity
+			 * checks.
+			 */
+			addr4 = sin6->sin6_addr.s6_addr32[3];
+			if (addr4 == htonl(INADDR_ANY) ||
+			    addr4 == htonl(INADDR_BROADCAST) ||
+			    IN_MULTICAST(ntohl(addr4))) {
+				ret = -EPROTOTYPE;
+				break;
+			}
+		}
+
+		if (addr_type & IPV6_ADDR_LINKLOCAL) {
+			/* If socket is arleady bound to a link local address,
+			 * the peer address must be on the same link.
+			 */
+			if (sin6->sin6_scope_id == 0 ||
+			    (!ipv6_addr_any(&rs->rs_bound_addr) &&
+			     rs->rs_bound_scope_id &&
+			     sin6->sin6_scope_id != rs->rs_bound_scope_id)) {
+				ret = -EINVAL;
+				break;
+			}
+			/* Remember the connected address scope ID.  It will
+			 * be checked against the binding local address when
+			 * the socket is bound.
+			 */
+			rs->rs_bound_scope_id = sin6->sin6_scope_id;
+		}
+		rs->rs_conn_addr = sin6->sin6_addr;
+		rs->rs_conn_port = sin6->sin6_port;
 		break;
 
 	default:
-		ret = -EINVAL;
+		ret = -EAFNOSUPPORT;
 		break;
 	}
 
diff --git a/net/rds/bind.c b/net/rds/bind.c
index c401776ad938..ba778760cbc2 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -127,9 +127,10 @@ static int rds_add_bound(struct rds_sock *rs, const struct in6_addr *addr,
 		if (!rhashtable_insert_fast(&bind_hash_table,
 					    &rs->rs_bound_node, ht_parms)) {
 			*port = rs->rs_bound_port;
+			rs->rs_bound_scope_id = scope_id;
 			ret = 0;
-			rdsdebug("rs %p binding to %pI4:%d\n",
-			  rs, &addr, (int)ntohs(*port));
+			rdsdebug("rs %p binding to %pI6c:%d\n",
+				 rs, addr, (int)ntohs(*port));
 			break;
 		} else {
 			rs->rs_bound_addr = in6addr_any;
@@ -164,23 +165,53 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct in6_addr v6addr, *binding_addr;
 	struct rds_transport *trans;
 	__u32 scope_id = 0;
+	int addr_type;
 	int ret = 0;
 	__be16 port;
 
-	/* We only allow an RDS socket to be bound to an IPv4 address. IPv6
-	 * address support will be added later.
+	/* We allow an RDS socket to be bound to either IPv4 or IPv6
+	 * address.
 	 */
-	if (addr_len == sizeof(struct sockaddr_in)) {
+	if (uaddr->sa_family == AF_INET) {
 		struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
 
-		if (sin->sin_family != AF_INET ||
-		    sin->sin_addr.s_addr == htonl(INADDR_ANY))
+		if (addr_len < sizeof(struct sockaddr_in) ||
+		    sin->sin_addr.s_addr == htonl(INADDR_ANY) ||
+		    sin->sin_addr.s_addr == htonl(INADDR_BROADCAST) ||
+		    IN_MULTICAST(ntohl(sin->sin_addr.s_addr)))
 			return -EINVAL;
 		ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr);
 		binding_addr = &v6addr;
 		port = sin->sin_port;
-	} else if (addr_len == sizeof(struct sockaddr_in6)) {
-		return -EPROTONOSUPPORT;
+	} else if (uaddr->sa_family == AF_INET6) {
+		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)uaddr;
+
+		if (addr_len < sizeof(struct sockaddr_in6))
+			return -EINVAL;
+		addr_type = ipv6_addr_type(&sin6->sin6_addr);
+		if (!(addr_type & IPV6_ADDR_UNICAST)) {
+			__be32 addr4;
+
+			if (!(addr_type & IPV6_ADDR_MAPPED))
+				return -EINVAL;
+
+			/* It is a mapped address.  Need to do some sanity
+			 * checks.
+			 */
+			addr4 = sin6->sin6_addr.s6_addr32[3];
+			if (addr4 == htonl(INADDR_ANY) ||
+			    addr4 == htonl(INADDR_BROADCAST) ||
+			    IN_MULTICAST(ntohl(addr4)))
+				return -EINVAL;
+		}
+		/* The scope ID must be specified for link local address. */
+		if (addr_type & IPV6_ADDR_LINKLOCAL) {
+			if (sin6->sin6_scope_id == 0)
+				return -EINVAL;
+			scope_id = sin6->sin6_scope_id;
+		}
+		binding_addr = &sin6->sin6_addr;
+		port = sin6->sin6_port;
 	} else {
 		return -EINVAL;
 	}
@@ -191,6 +222,16 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		ret = -EINVAL;
 		goto out;
 	}
+	/* Socket is connected.  The binding address should have the same
+	 * scope ID as the connected address, except the case when one is
+	 * non-link local address (scope_id is 0).
+	 */
+	if (!ipv6_addr_any(&rs->rs_conn_addr) && scope_id &&
+	    rs->rs_bound_scope_id &&
+	    scope_id != rs->rs_bound_scope_id) {
+		ret = -EINVAL;
+		goto out;
+	}
 
 	ret = rds_add_bound(rs, binding_addr, &port, scope_id);
 	if (ret)
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 3176ead0ab4d..5c9ceed55dae 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -36,6 +36,7 @@
 #include <linux/export.h>
 #include <net/ipv6.h>
 #include <net/inet6_hashtables.h>
+#include <net/addrconf.h>
 
 #include "rds.h"
 #include "loop.h"
@@ -200,6 +201,15 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	conn->c_isv6 = !ipv6_addr_v4mapped(laddr);
 	conn->c_faddr = *faddr;
 	conn->c_dev_if = dev_if;
+	/* If the local address is link local, set c_bound_if to be the
+	 * index used for this connection.  Otherwise, set it to 0 as
+	 * the socket is not bound to an interface.  c_bound_if is used
+	 * to look up a socket when a packet is received
+	 */
+	if (ipv6_addr_type(laddr) & IPV6_ADDR_LINKLOCAL)
+		conn->c_bound_if = dev_if;
+	else
+		conn->c_bound_if = 0;
 
 	rds_conn_net_set(conn, net);
 
@@ -486,10 +496,18 @@ void rds_conn_destroy(struct rds_connection *conn)
 }
 EXPORT_SYMBOL_GPL(rds_conn_destroy);
 
-static void rds_conn_message_info(struct socket *sock, unsigned int len,
-				  struct rds_info_iterator *iter,
-				  struct rds_info_lengths *lens,
-				  int want_send)
+static void __rds_inc_msg_cp(struct rds_incoming *inc,
+			     struct rds_info_iterator *iter,
+			     void *saddr, void *daddr, int flip)
+{
+	rds_inc_info_copy(inc, iter, *(__be32 *)saddr,
+			  *(__be32 *)daddr, flip);
+}
+
+static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
+				      struct rds_info_iterator *iter,
+				      struct rds_info_lengths *lens,
+				      int want_send)
 {
 	struct hlist_head *head;
 	struct list_head *list;
@@ -524,18 +542,13 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 
 				/* XXX too lazy to maintain counts.. */
 				list_for_each_entry(rm, list, m_conn_item) {
-					__be32 laddr;
-					__be32 faddr;
-
 					total++;
-					laddr = conn->c_laddr.s6_addr32[3];
-					faddr = conn->c_faddr.s6_addr32[3];
 					if (total <= len)
-						rds_inc_info_copy(&rm->m_inc,
-								  iter,
-								  laddr,
-								  faddr,
-								  0);
+						__rds_inc_msg_cp(&rm->m_inc,
+								 iter,
+								 &conn->c_laddr,
+								 &conn->c_faddr,
+								 0);
 				}
 
 				spin_unlock_irqrestore(&cp->cp_lock, flags);
@@ -548,6 +561,14 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 	lens->each = sizeof(struct rds_info_message);
 }
 
+static void rds_conn_message_info(struct socket *sock, unsigned int len,
+				  struct rds_info_iterator *iter,
+				  struct rds_info_lengths *lens,
+				  int want_send)
+{
+	rds_conn_message_info_cmn(sock, len, iter, lens, want_send);
+}
+
 static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
 				       struct rds_info_iterator *iter,
 				       struct rds_info_lengths *lens)
@@ -655,6 +676,9 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 	struct rds_info_connection *cinfo = buffer;
 	struct rds_connection *conn = cp->cp_conn;
 
+	if (conn->c_isv6)
+		return 0;
+
 	cinfo->next_tx_seq = cp->cp_next_tx_seq;
 	cinfo->next_rx_seq = cp->cp_next_rx_seq;
 	cinfo->laddr = conn->c_laddr.s6_addr32[3];
diff --git a/net/rds/ib.c b/net/rds/ib.c
index c712a848957d..756225c5540f 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -39,6 +39,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <net/addrconf.h>
 
 #include "rds_single_path.h"
 #include "rds.h"
@@ -295,6 +296,8 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
 	/* We will only ever look at IB transports */
 	if (conn->c_trans != &rds_ib_transport)
 		return 0;
+	if (conn->c_isv6)
+		return 0;
 
 	iinfo->src_addr = conn->c_laddr.s6_addr32[3];
 	iinfo->dst_addr = conn->c_faddr.s6_addr32[3];
@@ -330,7 +333,6 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
 				sizeof(struct rds_info_rdma_connection));
 }
 
-
 /*
  * Early RDS/IB was built to only bind to an address if there is an IPoIB
  * device with that address set.
@@ -346,8 +348,12 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
 {
 	int ret;
 	struct rdma_cm_id *cm_id;
+	struct sockaddr_in6 sin6;
 	struct sockaddr_in sin;
+	struct sockaddr *sa;
+	bool isv4;
 
+	isv4 = ipv6_addr_v4mapped(addr);
 	/* Create a CMA ID and try to bind it. This catches both
 	 * IB and iWARP capable NICs.
 	 */
@@ -356,20 +362,53 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
 	if (IS_ERR(cm_id))
 		return PTR_ERR(cm_id);
 
-	memset(&sin, 0, sizeof(sin));
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = addr->s6_addr32[3];
+	if (isv4) {
+		memset(&sin, 0, sizeof(sin));
+		sin.sin_family = AF_INET;
+		sin.sin_addr.s_addr = addr->s6_addr32[3];
+		sa = (struct sockaddr *)&sin;
+	} else {
+		memset(&sin6, 0, sizeof(sin6));
+		sin6.sin6_family = AF_INET6;
+		sin6.sin6_addr = *addr;
+		sin6.sin6_scope_id = scope_id;
+		sa = (struct sockaddr *)&sin6;
+
+		/* XXX Do a special IPv6 link local address check here.  The
+		 * reason is that rdma_bind_addr() always succeeds with IPv6
+		 * link local address regardless it is indeed configured in a
+		 * system.
+		 */
+		if (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL) {
+			struct net_device *dev;
+
+			if (scope_id == 0)
+				return -EADDRNOTAVAIL;
+
+			/* Use init_net for now as RDS is not network
+			 * name space aware.
+			 */
+			dev = dev_get_by_index(&init_net, scope_id);
+			if (!dev)
+				return -EADDRNOTAVAIL;
+			if (!ipv6_chk_addr(&init_net, addr, dev, 1)) {
+				dev_put(dev);
+				return -EADDRNOTAVAIL;
+			}
+			dev_put(dev);
+		}
+	}
 
 	/* rdma_bind_addr will only succeed for IB & iWARP devices */
-	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);
+	ret = rdma_bind_addr(cm_id, sa);
 	/* due to this, we will claim to support iWARP devices unless we
 	   check node_type. */
 	if (ret || !cm_id->device ||
 	    cm_id->device->node_type != RDMA_NODE_IB_CA)
 		ret = -EADDRNOTAVAIL;
 
-	rdsdebug("addr %pI6c ret %d node type %d\n",
-		 addr, ret,
+	rdsdebug("addr %pI6c%%%u ret %d node type %d\n",
+		 addr, scope_id, ret,
 		 cm_id->device ? cm_id->device->node_type : -1);
 
 	rdma_destroy_id(cm_id);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index dd8a867e5a9c..a33b82dc0804 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -678,7 +678,7 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
 	return version;
 }
 
-/* Given an IPv6 address, find the IB net_device which hosts that address and
+/* Given an IPv6 address, find the net_device which hosts that address and
  * return its index.  This is used by the rds_ib_cm_handle_connect() code to
  * find the interface index of where an incoming request comes from when
  * the request is using a link local address.
@@ -695,8 +695,7 @@ static u32 __rds_find_ifindex(struct net *net, const struct in6_addr *addr)
 
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
-		if (dev->type == ARPHRD_INFINIBAND &&
-		    ipv6_chk_addr(net, addr, dev, 0)) {
+		if (ipv6_chk_addr(net, addr, dev, 1)) {
 			idx = dev->ifindex;
 			break;
 		}
@@ -736,7 +735,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 		dp_cmn = &dp->ricp_v6.dp_cmn;
 		saddr6 = &dp->ricp_v6.dp_saddr;
 		daddr6 = &dp->ricp_v6.dp_daddr;
-		/* If the local address is link local, need to find the
+		/* If either address is link local, need to find the
 		 * interface index in order to create a proper RDS
 		 * connection.
 		 */
@@ -748,6 +747,14 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 				err = -EOPNOTSUPP;
 				goto out;
 			}
+		} else if (ipv6_addr_type(saddr6) & IPV6_ADDR_LINKLOCAL) {
+			/* Use our address to find the correct index. */
+			ifindex = __rds_find_ifindex(&init_net, daddr6);
+			/* No index found...  Need to bail out. */
+			if (ifindex == 0) {
+				err = -EOPNOTSUPP;
+				goto out;
+			}
 		}
 	} else {
 		dp_cmn = &dp->ricp_v4.dp_cmn;
@@ -886,7 +893,10 @@ int rds_ib_conn_path_connect(struct rds_conn_path *cp)
 
 	/* XXX I wonder what affect the port space has */
 	/* delegate cm event handler to rdma_transport */
-	handler = rds_rdma_cm_event_handler;
+	if (conn->c_isv6)
+		handler = rds6_rdma_cm_event_handler;
+	else
+		handler = rds_rdma_cm_event_handler;
 	ic->i_cm_id = rdma_create_id(&init_net, handler, conn,
 				     RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(ic->i_cm_id)) {
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index f49abef69550..bd67e55354f4 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -37,7 +37,9 @@
 #include "rdma_transport.h"
 #include "ib.h"
 
+/* Global IPv4 and IPv6 RDS RDMA listener cm_id */
 static struct rdma_cm_id *rds_rdma_listen_id;
+static struct rdma_cm_id *rds6_rdma_listen_id;
 
 static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 					 struct rdma_cm_event *event,
@@ -153,6 +155,12 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 	return rds_rdma_cm_event_handler_cmn(cm_id, event, false);
 }
 
+int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
+			       struct rdma_cm_event *event)
+{
+	return rds_rdma_cm_event_handler_cmn(cm_id, event, true);
+}
+
 static int rds_rdma_listen_init_common(rdma_cm_event_handler handler,
 				       struct sockaddr *sa,
 				       struct rdma_cm_id **ret_cm_id)
@@ -206,6 +214,7 @@ out:
 static int rds_rdma_listen_init(void)
 {
 	int ret;
+	struct sockaddr_in6 sin6;
 	struct sockaddr_in sin;
 
 	sin.sin_family = PF_INET;
@@ -214,7 +223,21 @@ static int rds_rdma_listen_init(void)
 	ret = rds_rdma_listen_init_common(rds_rdma_cm_event_handler,
 					  (struct sockaddr *)&sin,
 					  &rds_rdma_listen_id);
-	return ret;
+	if (ret != 0)
+		return ret;
+
+	sin6.sin6_family = PF_INET6;
+	sin6.sin6_addr = in6addr_any;
+	sin6.sin6_port = htons(RDS_CM_PORT);
+	sin6.sin6_scope_id = 0;
+	sin6.sin6_flowinfo = 0;
+	ret = rds_rdma_listen_init_common(rds6_rdma_cm_event_handler,
+					  (struct sockaddr *)&sin6,
+					  &rds6_rdma_listen_id);
+	/* Keep going even when IPv6 is not enabled in the system. */
+	if (ret != 0)
+		rdsdebug("Cannot set up IPv6 RDMA listener\n");
+	return 0;
 }
 
 static void rds_rdma_listen_stop(void)
@@ -224,6 +247,11 @@ static void rds_rdma_listen_stop(void)
 		rdma_destroy_id(rds_rdma_listen_id);
 		rds_rdma_listen_id = NULL;
 	}
+	if (rds6_rdma_listen_id) {
+		rdsdebug("cm %p\n", rds6_rdma_listen_id);
+		rdma_destroy_id(rds6_rdma_listen_id);
+		rds6_rdma_listen_id = NULL;
+	}
 }
 
 static int rds_rdma_init(void)
diff --git a/net/rds/rdma_transport.h b/net/rds/rdma_transport.h
index d309c4430124..200d3134aaae 100644
--- a/net/rds/rdma_transport.h
+++ b/net/rds/rdma_transport.h
@@ -6,11 +6,16 @@
 #include <rdma/rdma_cm.h>
 #include "rds.h"
 
+/* RDMA_CM also uses 16385 as the listener port. */
+#define RDS_CM_PORT	16385
+
 #define RDS_RDMA_RESOLVE_TIMEOUT_MS     5000
 
 int rds_rdma_conn_connect(struct rds_connection *conn);
 int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 			      struct rdma_cm_event *event);
+int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
+			       struct rdma_cm_event *event);
 
 /* from ib.c */
 extern struct rds_transport rds_ib_transport;
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 1bff26988a5e..ff537bb11411 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -24,14 +24,15 @@
 #define RDS_PROTOCOL_MINOR(v)	((v) & 255)
 #define RDS_PROTOCOL(maj, min)	(((maj) << 8) | min)
 
-/*
- * XXX randomly chosen, but at least seems to be unused:
- * #               18464-18768 Unassigned
- * We should do better.  We want a reserved port to discourage unpriv'ed
- * userspace from listening.
+/* The following ports, 16385, 18634, 18635, are registered with IANA as
+ * the ports to be used for RDS over TCP and UDP.  Currently, only RDS over
+ * TCP and RDS over IB/RDMA are implemented.  18634 is the historical value
+ * used for the RDMA_CM listener port.  RDS/TCP uses port 16385.  After
+ * IPv6 work, RDMA_CM also uses 16385 as the listener port.  18634 is kept
+ * to ensure compatibility with older RDS modules.  Those ports are defined
+ * in each transport's header file.
  */
 #define RDS_PORT	18634
-#define RDS_CM_PORT	16385
 
 #ifdef ATOMIC64_INIT
 #define KERNEL_HAS_ATOMIC64
@@ -140,7 +141,8 @@ struct rds_connection {
 	struct hlist_node	c_hash_node;
 	struct in6_addr		c_laddr;
 	struct in6_addr		c_faddr;
-	int			c_dev_if; /* c_laddrs's interface index */
+	int			c_dev_if; /* ifindex used for this conn */
+	int			c_bound_if; /* ifindex of c_laddr */
 	unsigned int		c_loopback:1,
 				c_isv6:1,
 				c_ping_triggered:1,
@@ -736,7 +738,7 @@ void rds_cong_remove_socket(struct rds_sock *);
 void rds_cong_exit(void);
 struct rds_message *rds_cong_update_alloc(struct rds_connection *conn);
 
-/* conn.c */
+/* connection.c */
 extern u32 rds_gen_num;
 int rds_conn_init(void);
 void rds_conn_exit(void);
@@ -874,6 +876,10 @@ int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msg);
 void rds_inc_info_copy(struct rds_incoming *inc,
 		       struct rds_info_iterator *iter,
 		       __be32 saddr, __be32 daddr, int flip);
+void rds6_inc_info_copy(struct rds_incoming *inc,
+			struct rds_info_iterator *iter,
+			struct in6_addr *saddr, struct in6_addr *daddr,
+			int flip);
 
 /* send.c */
 int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 4217961fd130..1402c21210b1 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -364,7 +364,7 @@ void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr,
 		goto out;
 	}
 
-	rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_dev_if);
+	rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_bound_if);
 	if (!rs) {
 		rds_stats_inc(s_recv_drop_no_sock);
 		goto out;
diff --git a/net/rds/send.c b/net/rds/send.c
index 6ed2e925c36a..9604e1faa564 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1091,10 +1091,9 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			ret = -EINVAL;
 			goto out;
 		}
-		switch (namelen) {
-		case sizeof(*usin):
-			if (usin->sin_family != AF_INET ||
-			    usin->sin_addr.s_addr == htonl(INADDR_ANY) ||
+		switch (usin->sin_family) {
+		case AF_INET:
+			if (usin->sin_addr.s_addr == htonl(INADDR_ANY) ||
 			    usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) ||
 			    IN_MULTICAST(ntohl(usin->sin_addr.s_addr))) {
 				ret = -EINVAL;
@@ -1104,9 +1103,44 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			dport = usin->sin_port;
 			break;
 
-		case sizeof(*sin6): {
-			ret = -EPROTONOSUPPORT;
-			goto out;
+		case AF_INET6: {
+			int addr_type;
+
+			if (namelen < sizeof(*sin6)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			addr_type = ipv6_addr_type(&sin6->sin6_addr);
+			if (!(addr_type & IPV6_ADDR_UNICAST)) {
+				__be32 addr4;
+
+				if (!(addr_type & IPV6_ADDR_MAPPED)) {
+					ret = -EINVAL;
+					goto out;
+				}
+
+				/* It is a mapped address.  Need to do some
+				 * sanity checks.
+				 */
+				addr4 = sin6->sin6_addr.s6_addr32[3];
+				if (addr4 == htonl(INADDR_ANY) ||
+				    addr4 == htonl(INADDR_BROADCAST) ||
+				    IN_MULTICAST(ntohl(addr4))) {
+					return -EINVAL;
+					goto out;
+				}
+			}
+			if (addr_type & IPV6_ADDR_LINKLOCAL) {
+				if (sin6->sin6_scope_id == 0) {
+					ret = -EINVAL;
+					goto out;
+				}
+				scope_id = sin6->sin6_scope_id;
+			}
+
+			daddr = sin6->sin6_addr;
+			dport = sin6->sin6_port;
+			break;
 		}
 
 		default:
@@ -1138,6 +1172,19 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			ret = -EOPNOTSUPP;
 			goto out;
 		}
+		/* If the socket is already bound to a link local address,
+		 * it can only send to peers on the same link.  But allow
+		 * communicating beween link local and non-link local address.
+		 */
+		if (scope_id != rs->rs_bound_scope_id) {
+			if (!scope_id) {
+				scope_id = rs->rs_bound_scope_id;
+			} else if (rs->rs_bound_scope_id) {
+				release_sock(sk);
+				ret = -EINVAL;
+				goto out;
+			}
+		}
 	}
 	release_sock(sk);
 
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index dadb33790333..890d0e1d8908 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -46,7 +46,12 @@
 /* only for info exporting */
 static DEFINE_SPINLOCK(rds_tcp_tc_list_lock);
 static LIST_HEAD(rds_tcp_tc_list);
+
+/* rds_tcp_tc_count counts only IPv4 connections.
+ * rds6_tcp_tc_count counts both IPv4 and IPv6 connections.
+ */
 static unsigned int rds_tcp_tc_count;
+static unsigned int rds6_tcp_tc_count;
 
 /* Track rds_tcp_connection structs so they can be cleaned up */
 static DEFINE_SPINLOCK(rds_tcp_conn_lock);
@@ -113,7 +118,9 @@ void rds_tcp_restore_callbacks(struct socket *sock,
 	/* done under the callback_lock to serialize with write_space */
 	spin_lock(&rds_tcp_tc_list_lock);
 	list_del_init(&tc->t_list_item);
-	rds_tcp_tc_count--;
+	rds6_tcp_tc_count--;
+	if (!tc->t_cpath->cp_conn->c_isv6)
+		rds_tcp_tc_count--;
 	spin_unlock(&rds_tcp_tc_list_lock);
 
 	tc->t_sock = NULL;
@@ -200,7 +207,9 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp)
 	/* done under the callback_lock to serialize with write_space */
 	spin_lock(&rds_tcp_tc_list_lock);
 	list_add_tail(&tc->t_list_item, &rds_tcp_tc_list);
-	rds_tcp_tc_count++;
+	rds6_tcp_tc_count++;
+	if (!tc->t_cpath->cp_conn->c_isv6)
+		rds_tcp_tc_count++;
 	spin_unlock(&rds_tcp_tc_list_lock);
 
 	/* accepted sockets need our listen data ready undone */
@@ -221,6 +230,9 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp)
 	write_unlock_bh(&sock->sk->sk_callback_lock);
 }
 
+/* Handle RDS_INFO_TCP_SOCKETS socket option.  It only returns IPv4
+ * connections for backward compatibility.
+ */
 static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 			    struct rds_info_iterator *iter,
 			    struct rds_info_lengths *lens)
@@ -228,8 +240,6 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 	struct rds_info_tcp_socket tsinfo;
 	struct rds_tcp_connection *tc;
 	unsigned long flags;
-	struct sockaddr_in sin;
-	struct socket *sock;
 
 	spin_lock_irqsave(&rds_tcp_tc_list_lock, flags);
 
@@ -237,16 +247,15 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 		goto out;
 
 	list_for_each_entry(tc, &rds_tcp_tc_list, t_list_item) {
+		struct inet_sock *inet = inet_sk(tc->t_sock->sk);
 
-		sock = tc->t_sock;
-		if (sock) {
-			sock->ops->getname(sock, (struct sockaddr *)&sin, 0);
-			tsinfo.local_addr = sin.sin_addr.s_addr;
-			tsinfo.local_port = sin.sin_port;
-			sock->ops->getname(sock, (struct sockaddr *)&sin, 1);
-			tsinfo.peer_addr = sin.sin_addr.s_addr;
-			tsinfo.peer_port = sin.sin_port;
-		}
+		if (tc->t_cpath->cp_conn->c_isv6)
+			continue;
+
+		tsinfo.local_addr = inet->inet_saddr;
+		tsinfo.local_port = inet->inet_sport;
+		tsinfo.peer_addr = inet->inet_daddr;
+		tsinfo.peer_port = inet->inet_dport;
 
 		tsinfo.hdr_rem = tc->t_tinc_hdr_rem;
 		tsinfo.data_rem = tc->t_tinc_data_rem;
@@ -494,13 +503,18 @@ static __net_init int rds_tcp_init_net(struct net *net)
 		err = -ENOMEM;
 		goto fail;
 	}
-	rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net);
+	rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, true);
 	if (!rtn->rds_tcp_listen_sock) {
-		pr_warn("could not set up listen sock\n");
-		unregister_net_sysctl_table(rtn->rds_tcp_sysctl);
-		rtn->rds_tcp_sysctl = NULL;
-		err = -EAFNOSUPPORT;
-		goto fail;
+		pr_warn("could not set up IPv6 listen sock\n");
+
+		/* Try IPv4 as some systems disable IPv6 */
+		rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, false);
+		if (!rtn->rds_tcp_listen_sock) {
+			unregister_net_sysctl_table(rtn->rds_tcp_sysctl);
+			rtn->rds_tcp_sysctl = NULL;
+			err = -EAFNOSUPPORT;
+			goto fail;
+		}
 	}
 	INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker);
 	return 0;
diff --git a/net/rds/tcp.h b/net/rds/tcp.h
index c6fa080e9b6d..3c69361d21c7 100644
--- a/net/rds/tcp.h
+++ b/net/rds/tcp.h
@@ -67,7 +67,7 @@ void rds_tcp_conn_path_shutdown(struct rds_conn_path *conn);
 void rds_tcp_state_change(struct sock *sk);
 
 /* tcp_listen.c */
-struct socket *rds_tcp_listen_init(struct net *);
+struct socket *rds_tcp_listen_init(struct net *net, bool isv6);
 void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor);
 void rds_tcp_listen_data_ready(struct sock *sk);
 int rds_tcp_accept_one(struct socket *sock);
diff --git a/net/rds/tcp_connect.c b/net/rds/tcp_connect.c
index 231ae927858e..008f50fb25dd 100644
--- a/net/rds/tcp_connect.c
+++ b/net/rds/tcp_connect.c
@@ -89,9 +89,11 @@ out:
 int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 {
 	struct socket *sock = NULL;
+	struct sockaddr_in6 sin6;
 	struct sockaddr_in sin;
 	struct sockaddr *addr;
 	int addrlen;
+	bool isv6;
 	int ret;
 	struct rds_connection *conn = cp->cp_conn;
 	struct rds_tcp_connection *tc = cp->cp_transport_data;
@@ -108,18 +110,36 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 		mutex_unlock(&tc->t_conn_path_lock);
 		return 0;
 	}
-	ret = sock_create_kern(rds_conn_net(conn), PF_INET,
-			       SOCK_STREAM, IPPROTO_TCP, &sock);
+	if (ipv6_addr_v4mapped(&conn->c_laddr)) {
+		ret = sock_create_kern(rds_conn_net(conn), PF_INET,
+				       SOCK_STREAM, IPPROTO_TCP, &sock);
+		isv6 = false;
+	} else {
+		ret = sock_create_kern(rds_conn_net(conn), PF_INET6,
+				       SOCK_STREAM, IPPROTO_TCP, &sock);
+		isv6 = true;
+	}
+
 	if (ret < 0)
 		goto out;
 
 	rds_tcp_tune(sock);
 
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = conn->c_laddr.s6_addr32[3];
-	sin.sin_port = 0;
-	addr = (struct sockaddr *)&sin;
-	addrlen = sizeof(sin);
+	if (isv6) {
+		sin6.sin6_family = AF_INET6;
+		sin6.sin6_addr = conn->c_laddr;
+		sin6.sin6_port = 0;
+		sin6.sin6_flowinfo = 0;
+		sin6.sin6_scope_id = conn->c_dev_if;
+		addr = (struct sockaddr *)&sin6;
+		addrlen = sizeof(sin6);
+	} else {
+		sin.sin_family = AF_INET;
+		sin.sin_addr.s_addr = conn->c_laddr.s6_addr32[3];
+		sin.sin_port = 0;
+		addr = (struct sockaddr *)&sin;
+		addrlen = sizeof(sin);
+	}
 
 	ret = sock->ops->bind(sock, addr, addrlen);
 	if (ret) {
@@ -128,11 +148,21 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 		goto out;
 	}
 
-	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = conn->c_faddr.s6_addr32[3];
-	sin.sin_port = htons(RDS_TCP_PORT);
-	addr = (struct sockaddr *)&sin;
-	addrlen = sizeof(sin);
+	if (isv6) {
+		sin6.sin6_family = AF_INET6;
+		sin6.sin6_addr = conn->c_faddr;
+		sin6.sin6_port = htons(RDS_TCP_PORT);
+		sin6.sin6_flowinfo = 0;
+		sin6.sin6_scope_id = conn->c_dev_if;
+		addr = (struct sockaddr *)&sin6;
+		addrlen = sizeof(sin6);
+	} else {
+		sin.sin_family = AF_INET;
+		sin.sin_addr.s_addr = conn->c_faddr.s6_addr32[3];
+		sin.sin_port = htons(RDS_TCP_PORT);
+		addr = (struct sockaddr *)&sin;
+		addrlen = sizeof(sin);
+	}
 
 	/*
 	 * once we call connect() we can start getting callbacks and they
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 4fdf5b3a47df..0cf0147117d8 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -131,6 +131,8 @@ int rds_tcp_accept_one(struct socket *sock)
 	struct rds_tcp_connection *rs_tcp = NULL;
 	int conn_state;
 	struct rds_conn_path *cp;
+	struct in6_addr *my_addr, *peer_addr;
+	int dev_if;
 
 	if (!sock) /* module unload or netns delete in progress */
 		return -ENETUNREACH;
@@ -163,15 +165,29 @@ int rds_tcp_accept_one(struct socket *sock)
 
 	inet = inet_sk(new_sock->sk);
 
+	my_addr = &new_sock->sk->sk_v6_rcv_saddr;
+	peer_addr = &new_sock->sk->sk_v6_daddr;
 	rdsdebug("accepted tcp %pI6c:%u -> %pI6c:%u\n",
-		 &new_sock->sk->sk_v6_rcv_saddr, ntohs(inet->inet_sport),
-		 &new_sock->sk->sk_v6_daddr, ntohs(inet->inet_dport));
+		 my_addr, ntohs(inet->inet_sport),
+		 peer_addr, ntohs(inet->inet_dport));
 
+	/* sk_bound_dev_if is not set if the peer address is not link local
+	 * address.  In this case, it happens that mcast_oif is set.  So
+	 * just use it.
+	 */
+	if ((ipv6_addr_type(my_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(peer_addr) & IPV6_ADDR_LINKLOCAL)) {
+		struct ipv6_pinfo *inet6;
+
+		inet6 = inet6_sk(new_sock->sk);
+		dev_if = inet6->mcast_oif;
+	} else {
+		dev_if = new_sock->sk->sk_bound_dev_if;
+	}
 	conn = rds_conn_create(sock_net(sock->sk),
 			       &new_sock->sk->sk_v6_rcv_saddr,
 			       &new_sock->sk->sk_v6_daddr,
-			       &rds_tcp_transport, GFP_KERNEL,
-			       new_sock->sk->sk_bound_dev_if);
+			       &rds_tcp_transport, GFP_KERNEL, dev_if);
 
 	if (IS_ERR(conn)) {
 		ret = PTR_ERR(conn);
@@ -256,15 +272,22 @@ out:
 		ready(sk);
 }
 
-struct socket *rds_tcp_listen_init(struct net *net)
+struct socket *rds_tcp_listen_init(struct net *net, bool isv6)
 {
-	struct sockaddr_in sin;
 	struct socket *sock = NULL;
+	struct sockaddr_storage ss;
+	struct sockaddr_in6 *sin6;
+	struct sockaddr_in *sin;
+	int addr_len;
 	int ret;
 
-	ret = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
-	if (ret < 0)
+	ret = sock_create_kern(net, isv6 ? PF_INET6 : PF_INET, SOCK_STREAM,
+			       IPPROTO_TCP, &sock);
+	if (ret < 0) {
+		rdsdebug("could not create %s listener socket: %d\n",
+			 isv6 ? "IPv6" : "IPv4", ret);
 		goto out;
+	}
 
 	sock->sk->sk_reuse = SK_CAN_REUSE;
 	rds_tcp_nonagle(sock);
@@ -274,13 +297,28 @@ struct socket *rds_tcp_listen_init(struct net *net)
 	sock->sk->sk_data_ready = rds_tcp_listen_data_ready;
 	write_unlock_bh(&sock->sk->sk_callback_lock);
 
-	sin.sin_family = PF_INET;
-	sin.sin_addr.s_addr = (__force u32)htonl(INADDR_ANY);
-	sin.sin_port = (__force u16)htons(RDS_TCP_PORT);
+	if (isv6) {
+		sin6 = (struct sockaddr_in6 *)&ss;
+		sin6->sin6_family = PF_INET6;
+		sin6->sin6_addr = in6addr_any;
+		sin6->sin6_port = (__force u16)htons(RDS_TCP_PORT);
+		sin6->sin6_scope_id = 0;
+		sin6->sin6_flowinfo = 0;
+		addr_len = sizeof(*sin6);
+	} else {
+		sin = (struct sockaddr_in *)&ss;
+		sin->sin_family = PF_INET;
+		sin->sin_addr.s_addr = INADDR_ANY;
+		sin->sin_port = (__force u16)htons(RDS_TCP_PORT);
+		addr_len = sizeof(*sin);
+	}
 
-	ret = sock->ops->bind(sock, (struct sockaddr *)&sin, sizeof(sin));
-	if (ret < 0)
+	ret = sock->ops->bind(sock, (struct sockaddr *)&ss, addr_len);
+	if (ret < 0) {
+		rdsdebug("could not bind %s listener socket: %d\n",
+			 isv6 ? "IPv6" : "IPv4", ret);
 		goto out;
+	}
 
 	ret = sock->ops->listen(sock, 64);
 	if (ret < 0)
-- 
cgit v1.2.3


From b7ff8b1036f0b0df1390ba6b5e9bc7ec458e857a Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Mon, 23 Jul 2018 20:51:23 -0700
Subject: rds: Extend RDS API for IPv6 support

There are many data structures (RDS socket options) used by RDS apps
which use a 32 bit integer to store IP address. To support IPv6,
struct in6_addr needs to be used. To ensure backward compatibility, a
new data structure is introduced for each of those data structures
which use a 32 bit integer to represent an IP address. And new socket
options are introduced to use those new structures. This means that
existing apps should work without a problem with the new RDS module.
For apps which want to use IPv6, those new data structures and socket
options can be used. IPv4 mapped address is used to represent IPv4
address in the new data structures.

v4: Revert changes to SO_RDS_TRANSPORT

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/rds.h |  69 +++++++++++++++++++++++++++++++-
 net/rds/connection.c     | 101 +++++++++++++++++++++++++++++++++++++++++++----
 net/rds/ib.c             |  52 ++++++++++++++++++++++++
 net/rds/ib_mr.h          |   2 +
 net/rds/ib_rdma.c        |  11 +++++-
 net/rds/recv.c           |  25 ++++++++++++
 net/rds/tcp.c            |  44 +++++++++++++++++++++
 7 files changed, 293 insertions(+), 11 deletions(-)

diff --git a/include/uapi/linux/rds.h b/include/uapi/linux/rds.h
index 20c6bd0b0007..dc520e1a4123 100644
--- a/include/uapi/linux/rds.h
+++ b/include/uapi/linux/rds.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
- * Copyright (c) 2008 Oracle.  All rights reserved.
+ * Copyright (c) 2008, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -118,7 +118,17 @@
 #define RDS_INFO_IB_CONNECTIONS		10008
 #define RDS_INFO_CONNECTION_STATS	10009
 #define RDS_INFO_IWARP_CONNECTIONS	10010
-#define RDS_INFO_LAST			10010
+
+/* PF_RDS6 options */
+#define RDS6_INFO_CONNECTIONS		10011
+#define RDS6_INFO_SEND_MESSAGES		10012
+#define RDS6_INFO_RETRANS_MESSAGES	10013
+#define RDS6_INFO_RECV_MESSAGES		10014
+#define RDS6_INFO_SOCKETS		10015
+#define RDS6_INFO_TCP_SOCKETS		10016
+#define RDS6_INFO_IB_CONNECTIONS	10017
+
+#define RDS_INFO_LAST			10017
 
 struct rds_info_counter {
 	__u8	name[32];
@@ -140,6 +150,15 @@ struct rds_info_connection {
 	__u8		flags;
 } __attribute__((packed));
 
+struct rds6_info_connection {
+	__u64		next_tx_seq;
+	__u64		next_rx_seq;
+	struct in6_addr	laddr;
+	struct in6_addr	faddr;
+	__u8		transport[TRANSNAMSIZ];		/* null term ascii */
+	__u8		flags;
+} __attribute__((packed));
+
 #define RDS_INFO_MESSAGE_FLAG_ACK               0x01
 #define RDS_INFO_MESSAGE_FLAG_FAST_ACK          0x02
 
@@ -153,6 +172,17 @@ struct rds_info_message {
 	__u8		flags;
 } __attribute__((packed));
 
+struct rds6_info_message {
+	__u64	seq;
+	__u32	len;
+	struct in6_addr	laddr;
+	struct in6_addr	faddr;
+	__be16		lport;
+	__be16		fport;
+	__u8		flags;
+	__u8		tos;
+} __attribute__((packed));
+
 struct rds_info_socket {
 	__u32		sndbuf;
 	__be32		bound_addr;
@@ -163,6 +193,16 @@ struct rds_info_socket {
 	__u64		inum;
 } __attribute__((packed));
 
+struct rds6_info_socket {
+	__u32		sndbuf;
+	struct in6_addr	bound_addr;
+	struct in6_addr	connected_addr;
+	__be16		bound_port;
+	__be16		connected_port;
+	__u32		rcvbuf;
+	__u64		inum;
+} __attribute__((packed));
+
 struct rds_info_tcp_socket {
 	__be32          local_addr;
 	__be16          local_port;
@@ -175,6 +215,18 @@ struct rds_info_tcp_socket {
 	__u32           last_seen_una;
 } __attribute__((packed));
 
+struct rds6_info_tcp_socket {
+	struct in6_addr	local_addr;
+	__be16		local_port;
+	struct in6_addr	peer_addr;
+	__be16		peer_port;
+	__u64		hdr_rem;
+	__u64		data_rem;
+	__u32		last_sent_nxt;
+	__u32		last_expected_una;
+	__u32		last_seen_una;
+} __attribute__((packed));
+
 #define RDS_IB_GID_LEN	16
 struct rds_info_rdma_connection {
 	__be32		src_addr;
@@ -189,6 +241,19 @@ struct rds_info_rdma_connection {
 	__u32		rdma_mr_size;
 };
 
+struct rds6_info_rdma_connection {
+	struct in6_addr	src_addr;
+	struct in6_addr	dst_addr;
+	__u8		src_gid[RDS_IB_GID_LEN];
+	__u8		dst_gid[RDS_IB_GID_LEN];
+
+	__u32		max_send_wr;
+	__u32		max_recv_wr;
+	__u32		max_send_sge;
+	__u32		rdma_mr_max;
+	__u32		rdma_mr_size;
+};
+
 /* RDS message Receive Path Latency points */
 enum rds_message_rxpath_latency {
 	RDS_MSG_RX_HDR_TO_DGRAM_START = 0,
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 5c9ceed55dae..051e35c1e7c6 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -498,16 +498,19 @@ EXPORT_SYMBOL_GPL(rds_conn_destroy);
 
 static void __rds_inc_msg_cp(struct rds_incoming *inc,
 			     struct rds_info_iterator *iter,
-			     void *saddr, void *daddr, int flip)
+			     void *saddr, void *daddr, int flip, bool isv6)
 {
-	rds_inc_info_copy(inc, iter, *(__be32 *)saddr,
-			  *(__be32 *)daddr, flip);
+	if (isv6)
+		rds6_inc_info_copy(inc, iter, saddr, daddr, flip);
+	else
+		rds_inc_info_copy(inc, iter, *(__be32 *)saddr,
+				  *(__be32 *)daddr, flip);
 }
 
 static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 				      struct rds_info_iterator *iter,
 				      struct rds_info_lengths *lens,
-				      int want_send)
+				      int want_send, bool isv6)
 {
 	struct hlist_head *head;
 	struct list_head *list;
@@ -518,7 +521,10 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 	size_t i;
 	int j;
 
-	len /= sizeof(struct rds_info_message);
+	if (isv6)
+		len /= sizeof(struct rds6_info_message);
+	else
+		len /= sizeof(struct rds_info_message);
 
 	rcu_read_lock();
 
@@ -528,6 +534,9 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 			struct rds_conn_path *cp;
 			int npaths;
 
+			if (!isv6 && conn->c_isv6)
+				continue;
+
 			npaths = (conn->c_trans->t_mp_capable ?
 				 RDS_MPATH_WORKERS : 1);
 
@@ -548,7 +557,7 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 								 iter,
 								 &conn->c_laddr,
 								 &conn->c_faddr,
-								 0);
+								 0, isv6);
 				}
 
 				spin_unlock_irqrestore(&cp->cp_lock, flags);
@@ -558,7 +567,10 @@ static void rds_conn_message_info_cmn(struct socket *sock, unsigned int len,
 	rcu_read_unlock();
 
 	lens->nr = total;
-	lens->each = sizeof(struct rds_info_message);
+	if (isv6)
+		lens->each = sizeof(struct rds6_info_message);
+	else
+		lens->each = sizeof(struct rds_info_message);
 }
 
 static void rds_conn_message_info(struct socket *sock, unsigned int len,
@@ -566,7 +578,15 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 				  struct rds_info_lengths *lens,
 				  int want_send)
 {
-	rds_conn_message_info_cmn(sock, len, iter, lens, want_send);
+	rds_conn_message_info_cmn(sock, len, iter, lens, want_send, false);
+}
+
+static void rds6_conn_message_info(struct socket *sock, unsigned int len,
+				   struct rds_info_iterator *iter,
+				   struct rds_info_lengths *lens,
+				   int want_send)
+{
+	rds_conn_message_info_cmn(sock, len, iter, lens, want_send, true);
 }
 
 static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
@@ -576,6 +596,13 @@ static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
 	rds_conn_message_info(sock, len, iter, lens, 1);
 }
 
+static void rds6_conn_message_info_send(struct socket *sock, unsigned int len,
+					struct rds_info_iterator *iter,
+					struct rds_info_lengths *lens)
+{
+	rds6_conn_message_info(sock, len, iter, lens, 1);
+}
+
 static void rds_conn_message_info_retrans(struct socket *sock,
 					  unsigned int len,
 					  struct rds_info_iterator *iter,
@@ -584,6 +611,14 @@ static void rds_conn_message_info_retrans(struct socket *sock,
 	rds_conn_message_info(sock, len, iter, lens, 0);
 }
 
+static void rds6_conn_message_info_retrans(struct socket *sock,
+					   unsigned int len,
+					   struct rds_info_iterator *iter,
+					   struct rds_info_lengths *lens)
+{
+	rds6_conn_message_info(sock, len, iter, lens, 0);
+}
+
 void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens,
@@ -699,6 +734,34 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 	return 1;
 }
 
+static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
+{
+	struct rds6_info_connection *cinfo6 = buffer;
+	struct rds_connection *conn = cp->cp_conn;
+
+	cinfo6->next_tx_seq = cp->cp_next_tx_seq;
+	cinfo6->next_rx_seq = cp->cp_next_rx_seq;
+	cinfo6->laddr = conn->c_laddr;
+	cinfo6->faddr = conn->c_faddr;
+	strncpy(cinfo6->transport, conn->c_trans->t_name,
+		sizeof(cinfo6->transport));
+	cinfo6->flags = 0;
+
+	rds_conn_info_set(cinfo6->flags, test_bit(RDS_IN_XMIT, &cp->cp_flags),
+			  SENDING);
+	/* XXX Future: return the state rather than these funky bits */
+	rds_conn_info_set(cinfo6->flags,
+			  atomic_read(&cp->cp_state) == RDS_CONN_CONNECTING,
+			  CONNECTING);
+	rds_conn_info_set(cinfo6->flags,
+			  atomic_read(&cp->cp_state) == RDS_CONN_UP,
+			  CONNECTED);
+	/* Just return 1 as there is no error case. This is a helper function
+	 * for rds_walk_conn_path_info() and it wants a return value.
+	 */
+	return 1;
+}
+
 static void rds_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
 			  struct rds_info_lengths *lens)
@@ -711,6 +774,18 @@ static void rds_conn_info(struct socket *sock, unsigned int len,
 				sizeof(struct rds_info_connection));
 }
 
+static void rds6_conn_info(struct socket *sock, unsigned int len,
+			   struct rds_info_iterator *iter,
+			   struct rds_info_lengths *lens)
+{
+	u64 buffer[(sizeof(struct rds6_info_connection) + 7) / 8];
+
+	rds_walk_conn_path_info(sock, len, iter, lens,
+				rds6_conn_info_visitor,
+				buffer,
+				sizeof(struct rds6_info_connection));
+}
+
 int rds_conn_init(void)
 {
 	int ret;
@@ -732,6 +807,11 @@ int rds_conn_init(void)
 			       rds_conn_message_info_send);
 	rds_info_register_func(RDS_INFO_RETRANS_MESSAGES,
 			       rds_conn_message_info_retrans);
+	rds_info_register_func(RDS6_INFO_CONNECTIONS, rds6_conn_info);
+	rds_info_register_func(RDS6_INFO_SEND_MESSAGES,
+			       rds6_conn_message_info_send);
+	rds_info_register_func(RDS6_INFO_RETRANS_MESSAGES,
+			       rds6_conn_message_info_retrans);
 
 	return 0;
 }
@@ -750,6 +830,11 @@ void rds_conn_exit(void)
 				 rds_conn_message_info_send);
 	rds_info_deregister_func(RDS_INFO_RETRANS_MESSAGES,
 				 rds_conn_message_info_retrans);
+	rds_info_deregister_func(RDS6_INFO_CONNECTIONS, rds6_conn_info);
+	rds_info_deregister_func(RDS6_INFO_SEND_MESSAGES,
+				 rds6_conn_message_info_send);
+	rds_info_deregister_func(RDS6_INFO_RETRANS_MESSAGES,
+				 rds6_conn_message_info_retrans);
 }
 
 /*
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 756225c5540f..63d95ea7cdff 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -321,6 +321,43 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
 	return 1;
 }
 
+/* IPv6 version of rds_ib_conn_info_visitor(). */
+static int rds6_ib_conn_info_visitor(struct rds_connection *conn,
+				     void *buffer)
+{
+	struct rds6_info_rdma_connection *iinfo6 = buffer;
+	struct rds_ib_connection *ic;
+
+	/* We will only ever look at IB transports */
+	if (conn->c_trans != &rds_ib_transport)
+		return 0;
+
+	iinfo6->src_addr = conn->c_laddr;
+	iinfo6->dst_addr = conn->c_faddr;
+
+	memset(&iinfo6->src_gid, 0, sizeof(iinfo6->src_gid));
+	memset(&iinfo6->dst_gid, 0, sizeof(iinfo6->dst_gid));
+
+	if (rds_conn_state(conn) == RDS_CONN_UP) {
+		struct rds_ib_device *rds_ibdev;
+		struct rdma_dev_addr *dev_addr;
+
+		ic = conn->c_transport_data;
+		dev_addr = &ic->i_cm_id->route.addr.dev_addr;
+		rdma_addr_get_sgid(dev_addr,
+				   (union ib_gid *)&iinfo6->src_gid);
+		rdma_addr_get_dgid(dev_addr,
+				   (union ib_gid *)&iinfo6->dst_gid);
+
+		rds_ibdev = ic->rds_ibdev;
+		iinfo6->max_send_wr = ic->i_send_ring.w_nr;
+		iinfo6->max_recv_wr = ic->i_recv_ring.w_nr;
+		iinfo6->max_send_sge = rds_ibdev->max_sge;
+		rds6_ib_get_mr_info(rds_ibdev, iinfo6);
+	}
+	return 1;
+}
+
 static void rds_ib_ic_info(struct socket *sock, unsigned int len,
 			   struct rds_info_iterator *iter,
 			   struct rds_info_lengths *lens)
@@ -333,6 +370,19 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
 				sizeof(struct rds_info_rdma_connection));
 }
 
+/* IPv6 version of rds_ib_ic_info(). */
+static void rds6_ib_ic_info(struct socket *sock, unsigned int len,
+			    struct rds_info_iterator *iter,
+			    struct rds_info_lengths *lens)
+{
+	u64 buffer[(sizeof(struct rds6_info_rdma_connection) + 7) / 8];
+
+	rds_for_each_conn_info(sock, len, iter, lens,
+			       rds6_ib_conn_info_visitor,
+			       buffer,
+			       sizeof(struct rds6_info_rdma_connection));
+}
+
 /*
  * Early RDS/IB was built to only bind to an address if there is an IPoIB
  * device with that address set.
@@ -441,6 +491,7 @@ void rds_ib_exit(void)
 	rds_ib_set_unloading();
 	synchronize_rcu();
 	rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
+	rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info);
 	rds_ib_unregister_client();
 	rds_ib_destroy_nodev_conns();
 	rds_ib_sysctl_exit();
@@ -502,6 +553,7 @@ int rds_ib_init(void)
 	rds_trans_register(&rds_ib_transport);
 
 	rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
+	rds_info_register_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info);
 
 	goto out;
 
diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h
index 0ea4ab017a8c..f440ace584c8 100644
--- a/net/rds/ib_mr.h
+++ b/net/rds/ib_mr.h
@@ -113,6 +113,8 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_dev,
 					     int npages);
 void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
 			struct rds_info_rdma_connection *iinfo);
+void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
+			 struct rds6_info_rdma_connection *iinfo6);
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
 void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		    struct rds_sock *rs, u32 *key_ret);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 0ec9df043dd0..e3c8bbbdb43f 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU
@@ -180,6 +180,15 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_co
 	iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages;
 }
 
+void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
+			 struct rds6_info_rdma_connection *iinfo6)
+{
+	struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool;
+
+	iinfo6->rdma_mr_max = pool_1m->max_items;
+	iinfo6->rdma_mr_size = pool_1m->fmr_attr.max_pages;
+}
+
 struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
 {
 	struct rds_ib_mr *ibmr = NULL;
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 1402c21210b1..03cd8df54c26 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -792,3 +792,28 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
+
+void rds6_inc_info_copy(struct rds_incoming *inc,
+			struct rds_info_iterator *iter,
+			struct in6_addr *saddr, struct in6_addr *daddr,
+			int flip)
+{
+	struct rds6_info_message minfo6;
+
+	minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence);
+	minfo6.len = be32_to_cpu(inc->i_hdr.h_len);
+
+	if (flip) {
+		minfo6.laddr = *daddr;
+		minfo6.faddr = *saddr;
+		minfo6.lport = inc->i_hdr.h_dport;
+		minfo6.fport = inc->i_hdr.h_sport;
+	} else {
+		minfo6.laddr = *saddr;
+		minfo6.faddr = *daddr;
+		minfo6.lport = inc->i_hdr.h_sport;
+		minfo6.fport = inc->i_hdr.h_dport;
+	}
+
+	rds_info_copy(iter, &minfo6, sizeof(minfo6));
+}
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 890d0e1d8908..7028d6e51947 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -273,6 +273,48 @@ out:
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
 
+/* Handle RDS6_INFO_TCP_SOCKETS socket option. It returns both IPv4 and
+ * IPv6 connections. IPv4 connection address is returned in an IPv4 mapped
+ * address.
+ */
+static void rds6_tcp_tc_info(struct socket *sock, unsigned int len,
+			     struct rds_info_iterator *iter,
+			     struct rds_info_lengths *lens)
+{
+	struct rds6_info_tcp_socket tsinfo6;
+	struct rds_tcp_connection *tc;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rds_tcp_tc_list_lock, flags);
+
+	if (len / sizeof(tsinfo6) < rds6_tcp_tc_count)
+		goto out;
+
+	list_for_each_entry(tc, &rds_tcp_tc_list, t_list_item) {
+		struct sock *sk = tc->t_sock->sk;
+		struct inet_sock *inet = inet_sk(sk);
+
+		tsinfo6.local_addr = sk->sk_v6_rcv_saddr;
+		tsinfo6.local_port = inet->inet_sport;
+		tsinfo6.peer_addr = sk->sk_v6_daddr;
+		tsinfo6.peer_port = inet->inet_dport;
+
+		tsinfo6.hdr_rem = tc->t_tinc_hdr_rem;
+		tsinfo6.data_rem = tc->t_tinc_data_rem;
+		tsinfo6.last_sent_nxt = tc->t_last_sent_nxt;
+		tsinfo6.last_expected_una = tc->t_last_expected_una;
+		tsinfo6.last_seen_una = tc->t_last_seen_una;
+
+		rds_info_copy(iter, &tsinfo6, sizeof(tsinfo6));
+	}
+
+out:
+	lens->nr = rds6_tcp_tc_count;
+	lens->each = sizeof(tsinfo6);
+
+	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
+}
+
 static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
 			       __u32 scope_id)
 {
@@ -628,6 +670,7 @@ static void rds_tcp_exit(void)
 	rds_tcp_set_unloading();
 	synchronize_rcu();
 	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+	rds_info_deregister_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info);
 	unregister_pernet_device(&rds_tcp_net_ops);
 	rds_tcp_destroy_conns();
 	rds_trans_unregister(&rds_tcp_transport);
@@ -659,6 +702,7 @@ static int rds_tcp_init(void)
 	rds_trans_register(&rds_tcp_transport);
 
 	rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+	rds_info_register_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info);
 
 	goto out;
 out_recv:
-- 
cgit v1.2.3


From 8c15e21c3508f48c291591fefa9beee0a08a3447 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Sat, 21 Jul 2018 13:55:09 +0200
Subject: mtd: lpddr: use mtd_device_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This driver doesn't specify parsers so it can use that little helper.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/lpddr/lpddr2_nvm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/lpddr/lpddr2_nvm.c b/drivers/mtd/lpddr/lpddr2_nvm.c
index 5d73db2a496d..c950c880ad59 100644
--- a/drivers/mtd/lpddr/lpddr2_nvm.c
+++ b/drivers/mtd/lpddr/lpddr2_nvm.c
@@ -476,7 +476,7 @@ static int lpddr2_nvm_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 	/* Parse partitions and register the MTD device */
-	return mtd_device_parse_register(mtd, NULL, NULL, NULL, 0);
+	return mtd_device_register(mtd, NULL, 0);
 }
 
 /*
-- 
cgit v1.2.3


From eb4d9796fa340495b519c75d0be44ae583e67ec3 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 9 Jul 2018 15:44:30 +0200
Subject: drm/exynos: g2d: Convert to driver component API

Exynos G2D driver is the last client of the custom Exynos 'sub-driver'
framework. In the current state it doesn't really resolve any of the
issues it has been designed for, as Exynos DRM is already built only
as a single kernel module. Remove the custom 'sub-driver' framework and
simply use generic component framework also in G2D driver.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/Makefile          |   2 +-
 drivers/gpu/drm/exynos/exynos_drm_core.c | 119 --------------
 drivers/gpu/drm/exynos/exynos_drm_drv.c  |  14 +-
 drivers/gpu/drm/exynos/exynos_drm_drv.h  |  47 +-----
 drivers/gpu/drm/exynos/exynos_drm_g2d.c  | 257 ++++++++++++-------------------
 drivers/gpu/drm/exynos/exynos_drm_g2d.h  |  11 ++
 6 files changed, 115 insertions(+), 335 deletions(-)
 delete mode 100644 drivers/gpu/drm/exynos/exynos_drm_core.c

diff --git a/drivers/gpu/drm/exynos/Makefile b/drivers/gpu/drm/exynos/Makefile
index 3b323f1e0475..2ad146bbf4f5 100644
--- a/drivers/gpu/drm/exynos/Makefile
+++ b/drivers/gpu/drm/exynos/Makefile
@@ -4,7 +4,7 @@
 # Direct Rendering Infrastructure (DRI) in XFree86 4.1.0 and higher.
 
 exynosdrm-y := exynos_drm_drv.o exynos_drm_crtc.o exynos_drm_fb.o \
-		exynos_drm_gem.o exynos_drm_core.o exynos_drm_plane.o
+		exynos_drm_gem.o exynos_drm_plane.o
 
 exynosdrm-$(CONFIG_DRM_FBDEV_EMULATION) += exynos_drm_fbdev.o
 exynosdrm-$(CONFIG_DRM_EXYNOS_IOMMU) += exynos_drm_iommu.o
diff --git a/drivers/gpu/drm/exynos/exynos_drm_core.c b/drivers/gpu/drm/exynos/exynos_drm_core.c
deleted file mode 100644
index b0c0621fcdf7..000000000000
--- a/drivers/gpu/drm/exynos/exynos_drm_core.c
+++ /dev/null
@@ -1,119 +0,0 @@
-/* exynos_drm_core.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd.
- * Author:
- *	Inki Dae <inki.dae@samsung.com>
- *	Joonyoung Shim <jy0922.shim@samsung.com>
- *	Seung-Woo Kim <sw0312.kim@samsung.com>
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
-
-#include <drm/drmP.h>
-
-#include "exynos_drm_drv.h"
-#include "exynos_drm_crtc.h"
-
-static LIST_HEAD(exynos_drm_subdrv_list);
-
-int exynos_drm_subdrv_register(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_add_tail(&subdrv->list, &exynos_drm_subdrv_list);
-
-	return 0;
-}
-
-int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *subdrv)
-{
-	if (!subdrv)
-		return -EINVAL;
-
-	list_del(&subdrv->list);
-
-	return 0;
-}
-
-int exynos_drm_device_subdrv_probe(struct drm_device *dev)
-{
-	struct exynos_drm_subdrv *subdrv, *n;
-	int err;
-
-	if (!dev)
-		return -EINVAL;
-
-	list_for_each_entry_safe(subdrv, n, &exynos_drm_subdrv_list, list) {
-		if (subdrv->probe) {
-			subdrv->drm_dev = dev;
-
-			/*
-			 * this probe callback would be called by sub driver
-			 * after setting of all resources to this sub driver,
-			 * such as clock, irq and register map are done.
-			 */
-			err = subdrv->probe(dev, subdrv->dev);
-			if (err) {
-				DRM_DEBUG("exynos drm subdrv probe failed.\n");
-				list_del(&subdrv->list);
-				continue;
-			}
-		}
-	}
-
-	return 0;
-}
-
-int exynos_drm_device_subdrv_remove(struct drm_device *dev)
-{
-	struct exynos_drm_subdrv *subdrv;
-
-	if (!dev) {
-		WARN(1, "Unexpected drm device unregister!\n");
-		return -EINVAL;
-	}
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->remove)
-			subdrv->remove(dev, subdrv->dev);
-	}
-
-	return 0;
-}
-
-int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file)
-{
-	struct exynos_drm_subdrv *subdrv;
-	int ret;
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->open) {
-			ret = subdrv->open(dev, subdrv->dev, file);
-			if (ret)
-				goto err;
-		}
-	}
-
-	return 0;
-
-err:
-	list_for_each_entry_continue_reverse(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->close)
-			subdrv->close(dev, subdrv->dev, file);
-	}
-	return ret;
-}
-
-void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file)
-{
-	struct exynos_drm_subdrv *subdrv;
-
-	list_for_each_entry(subdrv, &exynos_drm_subdrv_list, list) {
-		if (subdrv->close)
-			subdrv->close(dev, subdrv->dev, file);
-	}
-}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index ed3cc2989f93..7d0164aea36b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -55,8 +55,7 @@ static int exynos_drm_open(struct drm_device *dev, struct drm_file *file)
 		return -ENOMEM;
 
 	file->driver_priv = file_priv;
-
-	ret = exynos_drm_subdrv_open(dev, file);
+	ret = g2d_open(dev, file);
 	if (ret)
 		goto err_file_priv_free;
 
@@ -70,7 +69,7 @@ err_file_priv_free:
 
 static void exynos_drm_postclose(struct drm_device *dev, struct drm_file *file)
 {
-	exynos_drm_subdrv_close(dev, file);
+	g2d_close(dev, file);
 	kfree(file->driver_priv);
 	file->driver_priv = NULL;
 }
@@ -240,6 +239,7 @@ static struct exynos_drm_driver_info exynos_drm_drivers[] = {
 		DRM_COMPONENT_DRIVER | DRM_VIRTUAL_DEVICE
 	}, {
 		DRV_PTR(g2d_driver, CONFIG_DRM_EXYNOS_G2D),
+		DRM_COMPONENT_DRIVER
 	}, {
 		DRV_PTR(fimc_driver, CONFIG_DRM_EXYNOS_FIMC),
 		DRM_COMPONENT_DRIVER | DRM_FIMC_DEVICE,
@@ -376,11 +376,6 @@ static int exynos_drm_bind(struct device *dev)
 	if (ret)
 		goto err_unbind_all;
 
-	/* Probe non kms sub drivers and virtual display driver. */
-	ret = exynos_drm_device_subdrv_probe(drm);
-	if (ret)
-		goto err_unbind_all;
-
 	drm_mode_config_reset(drm);
 
 	/*
@@ -411,7 +406,6 @@ err_cleanup_fbdev:
 	exynos_drm_fbdev_fini(drm);
 err_cleanup_poll:
 	drm_kms_helper_poll_fini(drm);
-	exynos_drm_device_subdrv_remove(drm);
 err_unbind_all:
 	component_unbind_all(drm->dev, drm);
 err_mode_config_cleanup:
@@ -431,8 +425,6 @@ static void exynos_drm_unbind(struct device *dev)
 
 	drm_dev_unregister(drm);
 
-	exynos_drm_device_subdrv_remove(drm);
-
 	exynos_drm_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.h b/drivers/gpu/drm/exynos/exynos_drm_drv.h
index 0f6d079a55c9..c737c4bd2c19 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.h
@@ -179,17 +179,13 @@ static inline void exynos_drm_pipe_clk_enable(struct exynos_drm_crtc *crtc,
 		crtc->pipe_clk->enable(crtc->pipe_clk, enable);
 }
 
-struct exynos_drm_g2d_private {
-	struct device		*dev;
+struct drm_exynos_file_private {
+	/* for g2d api */
 	struct list_head	inuse_cmdlist;
 	struct list_head	event_list;
 	struct list_head	userptr_list;
 };
 
-struct drm_exynos_file_private {
-	struct exynos_drm_g2d_private	*g2d_priv;
-};
-
 /*
  * Exynos drm private structure.
  *
@@ -201,6 +197,7 @@ struct exynos_drm_private {
 	struct drm_fb_helper *fb_helper;
 	struct drm_atomic_state *suspend_state;
 
+	struct device *g2d_dev;
 	struct device *dma_dev;
 	void *mapping;
 
@@ -217,44 +214,6 @@ static inline struct device *to_dma_dev(struct drm_device *dev)
 	return priv->dma_dev;
 }
 
-/*
- * Exynos drm sub driver structure.
- *
- * @list: sub driver has its own list object to register to exynos drm driver.
- * @dev: pointer to device object for subdrv device driver.
- * @drm_dev: pointer to drm_device and this pointer would be set
- *	when sub driver calls exynos_drm_subdrv_register().
- * @probe: this callback would be called by exynos drm driver after
- *     subdrv is registered to it.
- * @remove: this callback is used to release resources created
- *     by probe callback.
- * @open: this would be called with drm device file open.
- * @close: this would be called with drm device file close.
- */
-struct exynos_drm_subdrv {
-	struct list_head list;
-	struct device *dev;
-	struct drm_device *drm_dev;
-
-	int (*probe)(struct drm_device *drm_dev, struct device *dev);
-	void (*remove)(struct drm_device *drm_dev, struct device *dev);
-	int (*open)(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file);
-	void (*close)(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file);
-};
-
- /* This function would be called by non kms drivers such as g2d and ipp. */
-int exynos_drm_subdrv_register(struct exynos_drm_subdrv *drm_subdrv);
-
-/* this function removes subdrv list from exynos drm driver */
-int exynos_drm_subdrv_unregister(struct exynos_drm_subdrv *drm_subdrv);
-
-int exynos_drm_device_subdrv_probe(struct drm_device *dev);
-int exynos_drm_device_subdrv_remove(struct drm_device *dev);
-int exynos_drm_subdrv_open(struct drm_device *dev, struct drm_file *file);
-void exynos_drm_subdrv_close(struct drm_device *dev, struct drm_file *file);
-
 #ifdef CONFIG_DRM_EXYNOS_DPI
 struct drm_encoder *exynos_dpi_probe(struct device *dev);
 int exynos_dpi_remove(struct drm_encoder *encoder);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index f68ef1b3a28c..27b929757b43 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -9,6 +9,7 @@
 
 #include <linux/kernel.h>
 #include <linux/clk.h>
+#include <linux/component.h>
 #include <linux/err.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
@@ -237,7 +238,7 @@ struct g2d_data {
 	int				irq;
 	struct workqueue_struct		*g2d_workq;
 	struct work_struct		runqueue_work;
-	struct exynos_drm_subdrv	subdrv;
+	struct drm_device		*drm_dev;
 	unsigned long			flags;
 
 	/* cmdlist */
@@ -268,14 +269,13 @@ static int g2d_init_cmdlist(struct g2d_data *g2d)
 {
 	struct device *dev = g2d->dev;
 	struct g2d_cmdlist_node *node = g2d->cmdlist_node;
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
 	int nr;
 	int ret;
 	struct g2d_buf_info *buf_info;
 
 	g2d->cmdlist_dma_attrs = DMA_ATTR_WRITE_COMBINE;
 
-	g2d->cmdlist_pool_virt = dma_alloc_attrs(to_dma_dev(subdrv->drm_dev),
+	g2d->cmdlist_pool_virt = dma_alloc_attrs(to_dma_dev(g2d->drm_dev),
 						G2D_CMDLIST_POOL_SIZE,
 						&g2d->cmdlist_pool, GFP_KERNEL,
 						g2d->cmdlist_dma_attrs);
@@ -308,7 +308,7 @@ static int g2d_init_cmdlist(struct g2d_data *g2d)
 	return 0;
 
 err:
-	dma_free_attrs(to_dma_dev(subdrv->drm_dev), G2D_CMDLIST_POOL_SIZE,
+	dma_free_attrs(to_dma_dev(g2d->drm_dev), G2D_CMDLIST_POOL_SIZE,
 			g2d->cmdlist_pool_virt,
 			g2d->cmdlist_pool, g2d->cmdlist_dma_attrs);
 	return ret;
@@ -316,12 +316,10 @@ err:
 
 static void g2d_fini_cmdlist(struct g2d_data *g2d)
 {
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
-
 	kfree(g2d->cmdlist_node);
 
 	if (g2d->cmdlist_pool_virt && g2d->cmdlist_pool) {
-		dma_free_attrs(to_dma_dev(subdrv->drm_dev),
+		dma_free_attrs(to_dma_dev(g2d->drm_dev),
 				G2D_CMDLIST_POOL_SIZE,
 				g2d->cmdlist_pool_virt,
 				g2d->cmdlist_pool, g2d->cmdlist_dma_attrs);
@@ -355,27 +353,27 @@ static void g2d_put_cmdlist(struct g2d_data *g2d, struct g2d_cmdlist_node *node)
 	mutex_unlock(&g2d->cmdlist_mutex);
 }
 
-static void g2d_add_cmdlist_to_inuse(struct exynos_drm_g2d_private *g2d_priv,
+static void g2d_add_cmdlist_to_inuse(struct drm_exynos_file_private *file_priv,
 				     struct g2d_cmdlist_node *node)
 {
 	struct g2d_cmdlist_node *lnode;
 
-	if (list_empty(&g2d_priv->inuse_cmdlist))
+	if (list_empty(&file_priv->inuse_cmdlist))
 		goto add_to_list;
 
 	/* this links to base address of new cmdlist */
-	lnode = list_entry(g2d_priv->inuse_cmdlist.prev,
+	lnode = list_entry(file_priv->inuse_cmdlist.prev,
 				struct g2d_cmdlist_node, list);
 	lnode->cmdlist->data[lnode->cmdlist->last] = node->dma_addr;
 
 add_to_list:
-	list_add_tail(&node->list, &g2d_priv->inuse_cmdlist);
+	list_add_tail(&node->list, &file_priv->inuse_cmdlist);
 
 	if (node->event)
-		list_add_tail(&node->event->base.link, &g2d_priv->event_list);
+		list_add_tail(&node->event->base.link, &file_priv->event_list);
 }
 
-static void g2d_userptr_put_dma_addr(struct drm_device *drm_dev,
+static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
 					unsigned long obj,
 					bool force)
 {
@@ -398,7 +396,7 @@ static void g2d_userptr_put_dma_addr(struct drm_device *drm_dev,
 		return;
 
 out:
-	dma_unmap_sg(to_dma_dev(drm_dev), g2d_userptr->sgt->sgl,
+	dma_unmap_sg(to_dma_dev(g2d->drm_dev), g2d_userptr->sgt->sgl,
 			g2d_userptr->sgt->nents, DMA_BIDIRECTIONAL);
 
 	pages = frame_vector_pages(g2d_userptr->vec);
@@ -419,16 +417,14 @@ out:
 	kfree(g2d_userptr);
 }
 
-static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
+static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 					unsigned long userptr,
 					unsigned long size,
 					struct drm_file *filp,
 					unsigned long *obj)
 {
 	struct drm_exynos_file_private *file_priv = filp->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
 	struct g2d_cmdlist_userptr *g2d_userptr;
-	struct g2d_data *g2d;
 	struct sg_table	*sgt;
 	unsigned long start, end;
 	unsigned int npages, offset;
@@ -439,10 +435,8 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 		return ERR_PTR(-EINVAL);
 	}
 
-	g2d = dev_get_drvdata(g2d_priv->dev);
-
 	/* check if userptr already exists in userptr_list. */
-	list_for_each_entry(g2d_userptr, &g2d_priv->userptr_list, list) {
+	list_for_each_entry(g2d_userptr, &file_priv->userptr_list, list) {
 		if (g2d_userptr->userptr == userptr) {
 			/*
 			 * also check size because there could be same address
@@ -517,7 +511,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 
 	g2d_userptr->sgt = sgt;
 
-	if (!dma_map_sg(to_dma_dev(drm_dev), sgt->sgl, sgt->nents,
+	if (!dma_map_sg(to_dma_dev(g2d->drm_dev), sgt->sgl, sgt->nents,
 				DMA_BIDIRECTIONAL)) {
 		DRM_ERROR("failed to map sgt with dma region.\n");
 		ret = -ENOMEM;
@@ -527,7 +521,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct drm_device *drm_dev,
 	g2d_userptr->dma_addr = sgt->sgl[0].dma_address;
 	g2d_userptr->userptr = userptr;
 
-	list_add_tail(&g2d_userptr->list, &g2d_priv->userptr_list);
+	list_add_tail(&g2d_userptr->list, &file_priv->userptr_list);
 
 	if (g2d->current_pool + (npages << PAGE_SHIFT) < g2d->max_pool) {
 		g2d->current_pool += npages << PAGE_SHIFT;
@@ -556,17 +550,14 @@ err_free:
 	return ERR_PTR(ret);
 }
 
-static void g2d_userptr_free_all(struct drm_device *drm_dev,
-					struct g2d_data *g2d,
-					struct drm_file *filp)
+static void g2d_userptr_free_all(struct g2d_data *g2d, struct drm_file *filp)
 {
 	struct drm_exynos_file_private *file_priv = filp->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
 	struct g2d_cmdlist_userptr *g2d_userptr, *n;
 
-	list_for_each_entry_safe(g2d_userptr, n, &g2d_priv->userptr_list, list)
+	list_for_each_entry_safe(g2d_userptr, n, &file_priv->userptr_list, list)
 		if (g2d_userptr->in_pool)
-			g2d_userptr_put_dma_addr(drm_dev,
+			g2d_userptr_put_dma_addr(g2d,
 						(unsigned long)g2d_userptr,
 						true);
 
@@ -758,7 +749,7 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 				goto err;
 			}
 
-			addr = g2d_userptr_get_dma_addr(drm_dev,
+			addr = g2d_userptr_get_dma_addr(g2d,
 							g2d_userptr.userptr,
 							g2d_userptr.size,
 							file,
@@ -785,7 +776,6 @@ static void g2d_unmap_cmdlist_gem(struct g2d_data *g2d,
 				  struct g2d_cmdlist_node *node,
 				  struct drm_file *filp)
 {
-	struct exynos_drm_subdrv *subdrv = &g2d->subdrv;
 	struct g2d_buf_info *buf_info = &node->buf_info;
 	int i;
 
@@ -800,11 +790,9 @@ static void g2d_unmap_cmdlist_gem(struct g2d_data *g2d,
 		handle = buf_info->handles[reg_type];
 
 		if (buf_info->types[reg_type] == BUF_TYPE_GEM)
-			exynos_drm_gem_put_dma_addr(subdrv->drm_dev, handle,
-							filp);
+			exynos_drm_gem_put_dma_addr(g2d->drm_dev, handle, filp);
 		else
-			g2d_userptr_put_dma_addr(subdrv->drm_dev, handle,
-							false);
+			g2d_userptr_put_dma_addr(g2d, handle, false);
 
 		buf_info->reg_types[i] = REG_TYPE_NONE;
 		buf_info->handles[reg_type] = 0;
@@ -922,7 +910,7 @@ static void g2d_runqueue_worker(struct work_struct *work)
 
 static void g2d_finish_event(struct g2d_data *g2d, u32 cmdlist_no)
 {
-	struct drm_device *drm_dev = g2d->subdrv.drm_dev;
+	struct drm_device *drm_dev = g2d->drm_dev;
 	struct g2d_runqueue_node *runqueue_node = g2d->runqueue_node;
 	struct drm_exynos_pending_g2d_event *e;
 	struct timespec64 now;
@@ -1031,7 +1019,7 @@ out:
 	mutex_unlock(&g2d->runqueue_mutex);
 }
 
-static int g2d_check_reg_offset(struct device *dev,
+static int g2d_check_reg_offset(struct g2d_data *g2d,
 				struct g2d_cmdlist_node *node,
 				int nr, bool for_addr)
 {
@@ -1131,7 +1119,7 @@ static int g2d_check_reg_offset(struct device *dev,
 	return 0;
 
 err:
-	dev_err(dev, "Bad register offset: 0x%lx\n", cmdlist->data[index]);
+	dev_err(g2d->dev, "Bad register offset: 0x%lx\n", cmdlist->data[index]);
 	return -EINVAL;
 }
 
@@ -1139,23 +1127,8 @@ err:
 int exynos_g2d_get_ver_ioctl(struct drm_device *drm_dev, void *data,
 			     struct drm_file *file)
 {
-	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
 	struct drm_exynos_g2d_get_ver *ver = data;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	ver->major = G2D_HW_MAJOR_VER;
 	ver->minor = G2D_HW_MINOR_VER;
 
@@ -1166,9 +1139,8 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 				 struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	struct g2d_data *g2d = dev_get_drvdata(priv->g2d_dev);
 	struct drm_exynos_g2d_set_cmdlist *req = data;
 	struct drm_exynos_g2d_cmd *cmd;
 	struct drm_exynos_pending_g2d_event *e;
@@ -1177,17 +1149,6 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	int size;
 	int ret;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	node = g2d_get_cmdlist(g2d);
 	if (!node)
 		return -ENOMEM;
@@ -1199,7 +1160,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	 */
 	if (req->cmd_nr > G2D_CMDLIST_DATA_NUM ||
 	    req->cmd_buf_nr > G2D_CMDLIST_DATA_NUM) {
-		dev_err(dev, "number of submitted G2D commands exceeds limit\n");
+		dev_err(g2d->dev, "number of submitted G2D commands exceeds limit\n");
 		return -EINVAL;
 	}
 
@@ -1267,7 +1228,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	 */
 	size = cmdlist->last + req->cmd_nr * 2 + req->cmd_buf_nr * 2 + 2;
 	if (size > G2D_CMDLIST_DATA_NUM) {
-		dev_err(dev, "cmdlist size is too big\n");
+		dev_err(g2d->dev, "cmdlist size is too big\n");
 		ret = -EINVAL;
 		goto err_free_event;
 	}
@@ -1282,7 +1243,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	}
 	cmdlist->last += req->cmd_nr * 2;
 
-	ret = g2d_check_reg_offset(dev, node, req->cmd_nr, false);
+	ret = g2d_check_reg_offset(g2d, node, req->cmd_nr, false);
 	if (ret < 0)
 		goto err_free_event;
 
@@ -1301,7 +1262,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 		}
 		cmdlist->last += req->cmd_buf_nr * 2;
 
-		ret = g2d_check_reg_offset(dev, node, req->cmd_buf_nr, true);
+		ret = g2d_check_reg_offset(g2d, node, req->cmd_buf_nr, true);
 		if (ret < 0)
 			goto err_free_event;
 
@@ -1319,7 +1280,7 @@ int exynos_g2d_set_cmdlist_ioctl(struct drm_device *drm_dev, void *data,
 	/* tail */
 	cmdlist->data[cmdlist->last] = 0;
 
-	g2d_add_cmdlist_to_inuse(g2d_priv, node);
+	g2d_add_cmdlist_to_inuse(file_priv, node);
 
 	return 0;
 
@@ -1337,25 +1298,13 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
 			  struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
-	struct device *dev;
-	struct g2d_data *g2d;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	struct g2d_data *g2d = dev_get_drvdata(priv->g2d_dev);
 	struct drm_exynos_g2d_exec *req = data;
 	struct g2d_runqueue_node *runqueue_node;
 	struct list_head *run_cmdlist;
 	struct list_head *event_list;
 
-	if (!g2d_priv)
-		return -ENODEV;
-
-	dev = g2d_priv->dev;
-	if (!dev)
-		return -ENODEV;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
 	runqueue_node = kmem_cache_alloc(g2d->runqueue_slab, GFP_KERNEL);
 	if (!runqueue_node)
 		return -ENOMEM;
@@ -1367,11 +1316,11 @@ int exynos_g2d_exec_ioctl(struct drm_device *drm_dev, void *data,
 	init_completion(&runqueue_node->complete);
 	runqueue_node->async = req->async;
 
-	list_splice_init(&g2d_priv->inuse_cmdlist, run_cmdlist);
-	list_splice_init(&g2d_priv->event_list, event_list);
+	list_splice_init(&file_priv->inuse_cmdlist, run_cmdlist);
+	list_splice_init(&file_priv->event_list, event_list);
 
 	if (list_empty(run_cmdlist)) {
-		dev_err(dev, "there is no inuse cmdlist\n");
+		dev_err(g2d->dev, "there is no inuse cmdlist\n");
 		kmem_cache_free(g2d->runqueue_slab, runqueue_node);
 		return -EPERM;
 	}
@@ -1395,71 +1344,28 @@ out:
 	return 0;
 }
 
-static int g2d_subdrv_probe(struct drm_device *drm_dev, struct device *dev)
-{
-	struct g2d_data *g2d;
-	int ret;
-
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return -EFAULT;
-
-	/* allocate dma-aware cmdlist buffer. */
-	ret = g2d_init_cmdlist(g2d);
-	if (ret < 0) {
-		dev_err(dev, "cmdlist init failed\n");
-		return ret;
-	}
-
-	ret = drm_iommu_attach_device(drm_dev, dev);
-	if (ret < 0) {
-		dev_err(dev, "failed to enable iommu.\n");
-		g2d_fini_cmdlist(g2d);
-	}
-
-	return ret;
-
-}
-
-static void g2d_subdrv_remove(struct drm_device *drm_dev, struct device *dev)
-{
-	drm_iommu_detach_device(drm_dev, dev);
-}
-
-static int g2d_open(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file)
+int g2d_open(struct drm_device *drm_dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv;
-
-	g2d_priv = kzalloc(sizeof(*g2d_priv), GFP_KERNEL);
-	if (!g2d_priv)
-		return -ENOMEM;
-
-	g2d_priv->dev = dev;
-	file_priv->g2d_priv = g2d_priv;
 
-	INIT_LIST_HEAD(&g2d_priv->inuse_cmdlist);
-	INIT_LIST_HEAD(&g2d_priv->event_list);
-	INIT_LIST_HEAD(&g2d_priv->userptr_list);
+	INIT_LIST_HEAD(&file_priv->inuse_cmdlist);
+	INIT_LIST_HEAD(&file_priv->event_list);
+	INIT_LIST_HEAD(&file_priv->userptr_list);
 
 	return 0;
 }
 
-static void g2d_close(struct drm_device *drm_dev, struct device *dev,
-			struct drm_file *file)
+void g2d_close(struct drm_device *drm_dev, struct drm_file *file)
 {
 	struct drm_exynos_file_private *file_priv = file->driver_priv;
-	struct exynos_drm_g2d_private *g2d_priv = file_priv->g2d_priv;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
 	struct g2d_data *g2d;
 	struct g2d_cmdlist_node *node, *n;
 
-	if (!dev)
+	if (!priv->g2d_dev)
 		return;
 
-	g2d = dev_get_drvdata(dev);
-	if (!g2d)
-		return;
+	g2d = dev_get_drvdata(priv->g2d_dev);
 
 	/* Remove the runqueue nodes that belong to us. */
 	mutex_lock(&g2d->runqueue_mutex);
@@ -1480,24 +1386,70 @@ static void g2d_close(struct drm_device *drm_dev, struct device *dev,
 	 * Properly unmap these buffers here.
 	 */
 	mutex_lock(&g2d->cmdlist_mutex);
-	list_for_each_entry_safe(node, n, &g2d_priv->inuse_cmdlist, list) {
+	list_for_each_entry_safe(node, n, &file_priv->inuse_cmdlist, list) {
 		g2d_unmap_cmdlist_gem(g2d, node, file);
 		list_move_tail(&node->list, &g2d->free_cmdlist);
 	}
 	mutex_unlock(&g2d->cmdlist_mutex);
 
 	/* release all g2d_userptr in pool. */
-	g2d_userptr_free_all(drm_dev, g2d, file);
+	g2d_userptr_free_all(g2d, file);
+}
+
+static int g2d_bind(struct device *dev, struct device *master, void *data)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+	int ret;
+
+	g2d->drm_dev = drm_dev;
+
+	/* allocate dma-aware cmdlist buffer. */
+	ret = g2d_init_cmdlist(g2d);
+	if (ret < 0) {
+		dev_err(dev, "cmdlist init failed\n");
+		return ret;
+	}
+
+	ret = drm_iommu_attach_device(drm_dev, dev);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable iommu.\n");
+		g2d_fini_cmdlist(g2d);
+		return ret;
+	}
+	priv->g2d_dev = dev;
 
-	kfree(file_priv->g2d_priv);
+	dev_info(dev, "The Exynos G2D (ver %d.%d) successfully registered.\n",
+			G2D_HW_MAJOR_VER, G2D_HW_MINOR_VER);
+	return 0;
 }
 
+static void g2d_unbind(struct device *dev, struct device *master, void *data)
+{
+	struct g2d_data *g2d = dev_get_drvdata(dev);
+	struct drm_device *drm_dev = data;
+	struct exynos_drm_private *priv = drm_dev->dev_private;
+
+	/* Suspend operation and wait for engine idle. */
+	set_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
+	g2d_wait_finish(g2d, NULL);
+	priv->g2d_dev = NULL;
+
+	cancel_work_sync(&g2d->runqueue_work);
+	drm_iommu_detach_device(g2d->drm_dev, dev);
+}
+
+static const struct component_ops g2d_component_ops = {
+	.bind	= g2d_bind,
+	.unbind = g2d_unbind,
+};
+
 static int g2d_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct resource *res;
 	struct g2d_data *g2d;
-	struct exynos_drm_subdrv *subdrv;
 	int ret;
 
 	g2d = devm_kzalloc(dev, sizeof(*g2d), GFP_KERNEL);
@@ -1564,22 +1516,12 @@ static int g2d_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, g2d);
 
-	subdrv = &g2d->subdrv;
-	subdrv->dev = dev;
-	subdrv->probe = g2d_subdrv_probe;
-	subdrv->remove = g2d_subdrv_remove;
-	subdrv->open = g2d_open;
-	subdrv->close = g2d_close;
-
-	ret = exynos_drm_subdrv_register(subdrv);
+	ret = component_add(dev, &g2d_component_ops);
 	if (ret < 0) {
 		dev_err(dev, "failed to register drm g2d device\n");
 		goto err_put_clk;
 	}
 
-	dev_info(dev, "The Exynos G2D (ver %d.%d) successfully probed.\n",
-			G2D_HW_MAJOR_VER, G2D_HW_MINOR_VER);
-
 	return 0;
 
 err_put_clk:
@@ -1595,12 +1537,7 @@ static int g2d_remove(struct platform_device *pdev)
 {
 	struct g2d_data *g2d = platform_get_drvdata(pdev);
 
-	/* Suspend operation and wait for engine idle. */
-	set_bit(G2D_BIT_SUSPEND_RUNQUEUE, &g2d->flags);
-	g2d_wait_finish(g2d, NULL);
-
-	cancel_work_sync(&g2d->runqueue_work);
-	exynos_drm_subdrv_unregister(&g2d->subdrv);
+	component_del(&pdev->dev, &g2d_component_ops);
 
 	/* There should be no locking needed here. */
 	g2d_remove_runqueue_nodes(g2d, NULL);
diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.h b/drivers/gpu/drm/exynos/exynos_drm_g2d.h
index 1a9c7ca8c15b..287b2ed8f178 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.h
@@ -14,6 +14,9 @@ extern int exynos_g2d_set_cmdlist_ioctl(struct drm_device *dev, void *data,
 					struct drm_file *file_priv);
 extern int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data,
 				 struct drm_file *file_priv);
+
+extern int g2d_open(struct drm_device *drm_dev, struct drm_file *file);
+extern void g2d_close(struct drm_device *drm_dev, struct drm_file *file);
 #else
 static inline int exynos_g2d_get_ver_ioctl(struct drm_device *dev, void *data,
 					   struct drm_file *file_priv)
@@ -33,4 +36,12 @@ static inline int exynos_g2d_exec_ioctl(struct drm_device *dev, void *data,
 {
 	return -ENODEV;
 }
+
+int g2d_open(struct drm_device *drm_dev, struct drm_file *file)
+{
+	return 0;
+}
+
+void g2d_close(struct drm_device *drm_dev, struct drm_file *file)
+{ }
 #endif
-- 
cgit v1.2.3


From 3aa2a5c14076e212fb3220d827c2e83806e7ce30 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 9 Jul 2018 15:44:31 +0200
Subject: drm/exynos: gem: Simplify access to exynos GEM objects

Replace all calls to exynos_drm_gem_get_{dma_addr,size}, by a simpler
function exynos_drm_gem_get(). This lets the caller to get access to
exynos_drm_gem object and extract any information about GEM object
without searching object tree for getting each parameter.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_g2d.c | 49 ++++++++++++----------------
 drivers/gpu/drm/exynos/exynos_drm_gem.c | 58 +++------------------------------
 drivers/gpu/drm/exynos/exynos_drm_gem.h | 24 +++++---------
 3 files changed, 35 insertions(+), 96 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_g2d.c b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
index 27b929757b43..f2481a2014bb 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_g2d.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_g2d.c
@@ -191,7 +191,7 @@ struct g2d_buf_desc {
 struct g2d_buf_info {
 	unsigned int		map_nr;
 	enum g2d_reg_type	reg_types[MAX_REG_TYPE_NR];
-	unsigned long		handles[MAX_REG_TYPE_NR];
+	void			*obj[MAX_REG_TYPE_NR];
 	unsigned int		types[MAX_REG_TYPE_NR];
 	struct g2d_buf_desc	descs[MAX_REG_TYPE_NR];
 };
@@ -374,11 +374,10 @@ add_to_list:
 }
 
 static void g2d_userptr_put_dma_addr(struct g2d_data *g2d,
-					unsigned long obj,
+					void *obj,
 					bool force)
 {
-	struct g2d_cmdlist_userptr *g2d_userptr =
-					(struct g2d_cmdlist_userptr *)obj;
+	struct g2d_cmdlist_userptr *g2d_userptr = obj;
 	struct page **pages;
 
 	if (!obj)
@@ -421,7 +420,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 					unsigned long userptr,
 					unsigned long size,
 					struct drm_file *filp,
-					unsigned long *obj)
+					void **obj)
 {
 	struct drm_exynos_file_private *file_priv = filp->driver_priv;
 	struct g2d_cmdlist_userptr *g2d_userptr;
@@ -444,7 +443,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 			 */
 			if (g2d_userptr->size == size) {
 				atomic_inc(&g2d_userptr->refcount);
-				*obj = (unsigned long)g2d_userptr;
+				*obj = g2d_userptr;
 
 				return &g2d_userptr->dma_addr;
 			}
@@ -528,7 +527,7 @@ static dma_addr_t *g2d_userptr_get_dma_addr(struct g2d_data *g2d,
 		g2d_userptr->in_pool = true;
 	}
 
-	*obj = (unsigned long)g2d_userptr;
+	*obj = g2d_userptr;
 
 	return &g2d_userptr->dma_addr;
 
@@ -557,9 +556,7 @@ static void g2d_userptr_free_all(struct g2d_data *g2d, struct drm_file *filp)
 
 	list_for_each_entry_safe(g2d_userptr, n, &file_priv->userptr_list, list)
 		if (g2d_userptr->in_pool)
-			g2d_userptr_put_dma_addr(g2d,
-						(unsigned long)g2d_userptr,
-						true);
+			g2d_userptr_put_dma_addr(g2d, g2d_userptr, true);
 
 	g2d->current_pool = 0;
 }
@@ -714,26 +711,23 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 		buf_desc = &buf_info->descs[reg_type];
 
 		if (buf_info->types[reg_type] == BUF_TYPE_GEM) {
-			unsigned long size;
+			struct exynos_drm_gem *exynos_gem;
 
-			size = exynos_drm_gem_get_size(drm_dev, handle, file);
-			if (!size) {
+			exynos_gem = exynos_drm_gem_get(file, handle);
+			if (!exynos_gem) {
 				ret = -EFAULT;
 				goto err;
 			}
 
-			if (!g2d_check_buf_desc_is_valid(buf_desc, reg_type,
-									size)) {
+			if (!g2d_check_buf_desc_is_valid(buf_desc,
+							 reg_type, exynos_gem->size)) {
+				exynos_drm_gem_put(exynos_gem);
 				ret = -EFAULT;
 				goto err;
 			}
 
-			addr = exynos_drm_gem_get_dma_addr(drm_dev, handle,
-								file);
-			if (IS_ERR(addr)) {
-				ret = -EFAULT;
-				goto err;
-			}
+			addr = &exynos_gem->dma_addr;
+			buf_info->obj[reg_type] = exynos_gem;
 		} else {
 			struct drm_exynos_g2d_userptr g2d_userptr;
 
@@ -753,7 +747,7 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 							g2d_userptr.userptr,
 							g2d_userptr.size,
 							file,
-							&handle);
+							&buf_info->obj[reg_type]);
 			if (IS_ERR(addr)) {
 				ret = -EFAULT;
 				goto err;
@@ -762,7 +756,6 @@ static int g2d_map_cmdlist_gem(struct g2d_data *g2d,
 
 		cmdlist->data[reg_pos + 1] = *addr;
 		buf_info->reg_types[i] = reg_type;
-		buf_info->handles[reg_type] = handle;
 	}
 
 	return 0;
@@ -782,20 +775,20 @@ static void g2d_unmap_cmdlist_gem(struct g2d_data *g2d,
 	for (i = 0; i < buf_info->map_nr; i++) {
 		struct g2d_buf_desc *buf_desc;
 		enum g2d_reg_type reg_type;
-		unsigned long handle;
+		void *obj;
 
 		reg_type = buf_info->reg_types[i];
 
 		buf_desc = &buf_info->descs[reg_type];
-		handle = buf_info->handles[reg_type];
+		obj = buf_info->obj[reg_type];
 
 		if (buf_info->types[reg_type] == BUF_TYPE_GEM)
-			exynos_drm_gem_put_dma_addr(g2d->drm_dev, handle, filp);
+			exynos_drm_gem_put(obj);
 		else
-			g2d_userptr_put_dma_addr(g2d, handle, false);
+			g2d_userptr_put_dma_addr(g2d, obj, false);
 
 		buf_info->reg_types[i] = REG_TYPE_NONE;
-		buf_info->handles[reg_type] = 0;
+		buf_info->obj[reg_type] = NULL;
 		buf_info->types[reg_type] = 0;
 		memset(buf_desc, 0x00, sizeof(*buf_desc));
 	}
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index bdf5a7655228..34ace85feb68 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -171,26 +171,6 @@ void exynos_drm_gem_destroy(struct exynos_drm_gem *exynos_gem)
 	kfree(exynos_gem);
 }
 
-unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
-						unsigned int gem_handle,
-						struct drm_file *file_priv)
-{
-	struct exynos_drm_gem *exynos_gem;
-	struct drm_gem_object *obj;
-
-	obj = drm_gem_object_lookup(file_priv, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return 0;
-	}
-
-	exynos_gem = to_exynos_gem(obj);
-
-	drm_gem_object_put_unlocked(obj);
-
-	return exynos_gem->size;
-}
-
 static struct exynos_drm_gem *exynos_drm_gem_init(struct drm_device *dev,
 						  unsigned long size)
 {
@@ -299,43 +279,15 @@ int exynos_drm_gem_map_ioctl(struct drm_device *dev, void *data,
 				       &args->offset);
 }
 
-dma_addr_t *exynos_drm_gem_get_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp)
+struct exynos_drm_gem *exynos_drm_gem_get(struct drm_file *filp,
+					  unsigned int gem_handle)
 {
-	struct exynos_drm_gem *exynos_gem;
 	struct drm_gem_object *obj;
 
 	obj = drm_gem_object_lookup(filp, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return ERR_PTR(-EINVAL);
-	}
-
-	exynos_gem = to_exynos_gem(obj);
-
-	return &exynos_gem->dma_addr;
-}
-
-void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp)
-{
-	struct drm_gem_object *obj;
-
-	obj = drm_gem_object_lookup(filp, gem_handle);
-	if (!obj) {
-		DRM_ERROR("failed to lookup gem object.\n");
-		return;
-	}
-
-	drm_gem_object_put_unlocked(obj);
-
-	/*
-	 * decrease obj->refcount one more time because we has already
-	 * increased it at exynos_drm_gem_get_dma_addr().
-	 */
-	drm_gem_object_put_unlocked(obj);
+	if (!obj)
+		return NULL;
+	return to_exynos_gem(obj);
 }
 
 static int exynos_drm_gem_mmap_buffer(struct exynos_drm_gem *exynos_gem,
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.h b/drivers/gpu/drm/exynos/exynos_drm_gem.h
index 9057d7f1d6ed..d46a62c30812 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.h
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.h
@@ -77,32 +77,26 @@ int exynos_drm_gem_map_ioctl(struct drm_device *dev, void *data,
 			     struct drm_file *file_priv);
 
 /*
- * get dma address from gem handle and this function could be used for
+ * get exynos drm object from gem handle, this function could be used for
  * other drivers such as 2d/3d acceleration drivers.
  * with this function call, gem object reference count would be increased.
  */
-dma_addr_t *exynos_drm_gem_get_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp);
+struct exynos_drm_gem *exynos_drm_gem_get(struct drm_file *filp,
+					  unsigned int gem_handle);
 
 /*
- * put dma address from gem handle and this function could be used for
- * other drivers such as 2d/3d acceleration drivers.
- * with this function call, gem object reference count would be decreased.
+ * put exynos drm object acquired from exynos_drm_gem_get(),
+ * gem object reference count would be decreased.
  */
-void exynos_drm_gem_put_dma_addr(struct drm_device *dev,
-					unsigned int gem_handle,
-					struct drm_file *filp);
+static inline void exynos_drm_gem_put(struct exynos_drm_gem *exynos_gem)
+{
+	drm_gem_object_put_unlocked(&exynos_gem->base);
+}
 
 /* get buffer information to memory region allocated by gem. */
 int exynos_drm_gem_get_ioctl(struct drm_device *dev, void *data,
 				      struct drm_file *file_priv);
 
-/* get buffer size to gem handle. */
-unsigned long exynos_drm_gem_get_size(struct drm_device *dev,
-						unsigned int gem_handle,
-						struct drm_file *file_priv);
-
 /* free gem object. */
 void exynos_drm_gem_free_object(struct drm_gem_object *obj);
 
-- 
cgit v1.2.3


From e978de54957f49333266f0212bb3c27e61f0bceb Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 9 Jul 2018 15:44:32 +0200
Subject: drm/exynos: Use common exynos_drm_gem_get()/put() functions for GEM
 lookup

Use recently introduced common helpers to unify GEM handling code.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_fb.c  | 10 ++++------
 drivers/gpu/drm/exynos/exynos_drm_ipp.c | 10 +++++-----
 2 files changed, 9 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_fb.c b/drivers/gpu/drm/exynos/exynos_drm_fb.c
index 27b7d34d776c..9f52382e19ee 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fb.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fb.c
@@ -101,7 +101,6 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 {
 	const struct drm_format_info *info = drm_get_format_info(dev, mode_cmd);
 	struct exynos_drm_gem *exynos_gem[MAX_FB_BUFFER];
-	struct drm_gem_object *obj;
 	struct drm_framebuffer *fb;
 	int i;
 	int ret;
@@ -112,15 +111,14 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 		unsigned long size = height * mode_cmd->pitches[i] +
 				     mode_cmd->offsets[i];
 
-		obj = drm_gem_object_lookup(file_priv, mode_cmd->handles[i]);
-		if (!obj) {
+		exynos_gem[i] = exynos_drm_gem_get(file_priv,
+						   mode_cmd->handles[i]);
+		if (!exynos_gem[i]) {
 			DRM_ERROR("failed to lookup gem object\n");
 			ret = -ENOENT;
 			goto err;
 		}
 
-		exynos_gem[i] = to_exynos_gem(obj);
-
 		if (size > exynos_gem[i]->size) {
 			i++;
 			ret = -EINVAL;
@@ -138,7 +136,7 @@ exynos_user_fb_create(struct drm_device *dev, struct drm_file *file_priv,
 
 err:
 	while (i--)
-		drm_gem_object_put_unlocked(&exynos_gem[i]->base);
+		exynos_drm_gem_put(exynos_gem[i]);
 
 	return ERR_PTR(ret);
 }
diff --git a/drivers/gpu/drm/exynos/exynos_drm_ipp.c b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
index b435db8fc916..23226a0212e8 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_ipp.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_ipp.c
@@ -350,13 +350,13 @@ static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
 		unsigned int height = (i == 0) ? buf->buf.height :
 			     DIV_ROUND_UP(buf->buf.height, buf->format->vsub);
 		unsigned long size = height * buf->buf.pitch[i];
-		struct drm_gem_object *obj = drm_gem_object_lookup(filp,
+		struct exynos_drm_gem *gem = exynos_drm_gem_get(filp,
 							    buf->buf.gem_id[i]);
-		if (!obj) {
+		if (!gem) {
 			ret = -ENOENT;
 			goto gem_free;
 		}
-		buf->exynos_gem[i] = to_exynos_gem(obj);
+		buf->exynos_gem[i] = gem;
 
 		if (size + buf->buf.offset[i] > buf->exynos_gem[i]->size) {
 			i++;
@@ -370,7 +370,7 @@ static int exynos_drm_ipp_task_setup_buffer(struct exynos_drm_ipp_buffer *buf,
 	return 0;
 gem_free:
 	while (i--) {
-		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+		exynos_drm_gem_put(buf->exynos_gem[i]);
 		buf->exynos_gem[i] = NULL;
 	}
 	return ret;
@@ -383,7 +383,7 @@ static void exynos_drm_ipp_task_release_buf(struct exynos_drm_ipp_buffer *buf)
 	if (!buf->exynos_gem[0])
 		return;
 	for (i = 0; i < buf->format->num_planes; i++)
-		drm_gem_object_put_unlocked(&buf->exynos_gem[i]->base);
+		exynos_drm_gem_put(buf->exynos_gem[i]);
 }
 
 static void exynos_drm_ipp_task_free(struct exynos_drm_ipp *ipp,
-- 
cgit v1.2.3


From d17504b16ea270ad858ce117447a8f4aa5a2de73 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Sun, 15 Jul 2018 20:52:26 -0700
Subject: wireless/lib80211: Convert from ahash to shash

In preparing to remove all stack VLA usage from the kernel[1], this
removes the discouraged use of AHASH_REQUEST_ON_STACK in favor of
the smaller SHASH_DESC_ON_STACK by converting from ahash-wrapped-shash
to direct shash. The stack allocation will be made a fixed size in a
later patch to the crypto subsystem.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/lib80211_crypt_tkip.c | 55 +++++++++++++++++++++-----------------
 1 file changed, 30 insertions(+), 25 deletions(-)

diff --git a/net/wireless/lib80211_crypt_tkip.c b/net/wireless/lib80211_crypt_tkip.c
index ba0a1f398ce5..e6bce1f130c9 100644
--- a/net/wireless/lib80211_crypt_tkip.c
+++ b/net/wireless/lib80211_crypt_tkip.c
@@ -65,9 +65,9 @@ struct lib80211_tkip_data {
 	int key_idx;
 
 	struct crypto_skcipher *rx_tfm_arc4;
-	struct crypto_ahash *rx_tfm_michael;
+	struct crypto_shash *rx_tfm_michael;
 	struct crypto_skcipher *tx_tfm_arc4;
-	struct crypto_ahash *tx_tfm_michael;
+	struct crypto_shash *tx_tfm_michael;
 
 	/* scratch buffers for virt_to_page() (crypto API) */
 	u8 rx_hdr[16], tx_hdr[16];
@@ -106,8 +106,7 @@ static void *lib80211_tkip_init(int key_idx)
 		goto fail;
 	}
 
-	priv->tx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
-						  CRYPTO_ALG_ASYNC);
+	priv->tx_tfm_michael = crypto_alloc_shash("michael_mic", 0, 0);
 	if (IS_ERR(priv->tx_tfm_michael)) {
 		priv->tx_tfm_michael = NULL;
 		goto fail;
@@ -120,8 +119,7 @@ static void *lib80211_tkip_init(int key_idx)
 		goto fail;
 	}
 
-	priv->rx_tfm_michael = crypto_alloc_ahash("michael_mic", 0,
-						  CRYPTO_ALG_ASYNC);
+	priv->rx_tfm_michael = crypto_alloc_shash("michael_mic", 0, 0);
 	if (IS_ERR(priv->rx_tfm_michael)) {
 		priv->rx_tfm_michael = NULL;
 		goto fail;
@@ -131,9 +129,9 @@ static void *lib80211_tkip_init(int key_idx)
 
       fail:
 	if (priv) {
-		crypto_free_ahash(priv->tx_tfm_michael);
+		crypto_free_shash(priv->tx_tfm_michael);
 		crypto_free_skcipher(priv->tx_tfm_arc4);
-		crypto_free_ahash(priv->rx_tfm_michael);
+		crypto_free_shash(priv->rx_tfm_michael);
 		crypto_free_skcipher(priv->rx_tfm_arc4);
 		kfree(priv);
 	}
@@ -145,9 +143,9 @@ static void lib80211_tkip_deinit(void *priv)
 {
 	struct lib80211_tkip_data *_priv = priv;
 	if (_priv) {
-		crypto_free_ahash(_priv->tx_tfm_michael);
+		crypto_free_shash(_priv->tx_tfm_michael);
 		crypto_free_skcipher(_priv->tx_tfm_arc4);
-		crypto_free_ahash(_priv->rx_tfm_michael);
+		crypto_free_shash(_priv->rx_tfm_michael);
 		crypto_free_skcipher(_priv->rx_tfm_arc4);
 	}
 	kfree(priv);
@@ -510,29 +508,36 @@ static int lib80211_tkip_decrypt(struct sk_buff *skb, int hdr_len, void *priv)
 	return keyidx;
 }
 
-static int michael_mic(struct crypto_ahash *tfm_michael, u8 * key, u8 * hdr,
-		       u8 * data, size_t data_len, u8 * mic)
+static int michael_mic(struct crypto_shash *tfm_michael, u8 *key, u8 *hdr,
+		       u8 *data, size_t data_len, u8 *mic)
 {
-	AHASH_REQUEST_ON_STACK(req, tfm_michael);
-	struct scatterlist sg[2];
+	SHASH_DESC_ON_STACK(desc, tfm_michael);
 	int err;
 
 	if (tfm_michael == NULL) {
 		pr_warn("%s(): tfm_michael == NULL\n", __func__);
 		return -1;
 	}
-	sg_init_table(sg, 2);
-	sg_set_buf(&sg[0], hdr, 16);
-	sg_set_buf(&sg[1], data, data_len);
 
-	if (crypto_ahash_setkey(tfm_michael, key, 8))
+	desc->tfm = tfm_michael;
+	desc->flags = 0;
+
+	if (crypto_shash_setkey(tfm_michael, key, 8))
 		return -1;
 
-	ahash_request_set_tfm(req, tfm_michael);
-	ahash_request_set_callback(req, 0, NULL, NULL);
-	ahash_request_set_crypt(req, sg, mic, data_len + 16);
-	err = crypto_ahash_digest(req);
-	ahash_request_zero(req);
+	err = crypto_shash_init(desc);
+	if (err)
+		goto out;
+	err = crypto_shash_update(desc, hdr, 16);
+	if (err)
+		goto out;
+	err = crypto_shash_update(desc, data, data_len);
+	if (err)
+		goto out;
+	err = crypto_shash_final(desc, mic);
+
+out:
+	shash_desc_zero(desc);
 	return err;
 }
 
@@ -654,9 +659,9 @@ static int lib80211_tkip_set_key(void *key, int len, u8 * seq, void *priv)
 {
 	struct lib80211_tkip_data *tkey = priv;
 	int keyidx;
-	struct crypto_ahash *tfm = tkey->tx_tfm_michael;
+	struct crypto_shash *tfm = tkey->tx_tfm_michael;
 	struct crypto_skcipher *tfm2 = tkey->tx_tfm_arc4;
-	struct crypto_ahash *tfm3 = tkey->rx_tfm_michael;
+	struct crypto_shash *tfm3 = tkey->rx_tfm_michael;
 	struct crypto_skcipher *tfm4 = tkey->rx_tfm_arc4;
 
 	keyidx = tkey->key_idx;
-- 
cgit v1.2.3


From eebdc3b49abbfc7ab574eaddebfec64df27a5cf4 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 11 Jun 2018 14:24:58 +0200
Subject: drm/exynos: Drop useless check from exynos_drm_{suspend,resume}

The virtual Exynos DRM device has no runtime PM enabled, so checking
for its runtime suspended state is useless.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_drv.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 7d0164aea36b..29fe6138e182 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -152,7 +152,7 @@ static int exynos_drm_suspend(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct exynos_drm_private *private;
 
-	if (pm_runtime_suspended(dev) || !drm_dev)
+	if (!drm_dev)
 		return 0;
 
 	private = drm_dev->dev_private;
@@ -174,7 +174,7 @@ static int exynos_drm_resume(struct device *dev)
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct exynos_drm_private *private;
 
-	if (pm_runtime_suspended(dev) || !drm_dev)
+	if (!drm_dev)
 		return 0;
 
 	private = drm_dev->dev_private;
-- 
cgit v1.2.3


From 133bf90dbb8b873286f8ec2e81ba26e863114b8c Mon Sep 17 00:00:00 2001
From: Manikanta Pubbisetty <mpubbise@codeaurora.org>
Date: Tue, 10 Jul 2018 16:48:27 +0530
Subject: mac80211: restrict delayed tailroom needed decrement

As explained in ieee80211_delayed_tailroom_dec(), during roam,
keys of the old AP will be destroyed and new keys will be
installed. Deletion of the old key causes
crypto_tx_tailroom_needed_cnt to go from 1 to 0 and the new key
installation causes a transition from 0 to 1.

Whenever crypto_tx_tailroom_needed_cnt transitions from 0 to 1,
we invoke synchronize_net(); the reason for doing this is to avoid
a race in the TX path as explained in increment_tailroom_need_count().
This synchronize_net() operation can be slow and can affect the station
roam time. To avoid this, decrementing the crypto_tx_tailroom_needed_cnt
is delayed for a while so that upon installation of new key the
transition would be from 1 to 2 instead of 0 to 1 and thereby
improving the roam time.

This is all correct for a STA iftype, but deferring the tailroom_needed
decrement for other iftypes may be unnecessary.

For example, let's consider the case of a 4-addr client connecting to
an AP for which AP_VLAN interface is also created, let the initial
value for tailroom_needed on the AP be 1.

* 4-addr client connects to the AP (AP: tailroom_needed = 1)
* AP will clear old keys, delay decrement of tailroom_needed count
* AP_VLAN is created, it takes the tailroom count from master
  (AP_VLAN: tailroom_needed = 1, AP: tailroom_needed = 1)
* Install new key for the station, assume key is plumbed in the HW,
  there won't be any change in tailroom_needed count on AP iface
* Delayed decrement of tailroom_needed count on AP
  (AP: tailroom_needed = 0, AP_VLAN: tailroom_needed = 1)

Because of the delayed decrement on AP iface, tailroom_needed count goes
out of sync between AP(master iface) and AP_VLAN(slave iface) and
there would be unnecessary tailroom created for the packets going
through AP_VLAN iface.

Also, WARN_ONs were observed while trying to bring down the AP_VLAN
interface:
(warn_slowpath_common) (warn_slowpath_null+0x18/0x20)
(warn_slowpath_null) (ieee80211_free_keys+0x114/0x1e4)
(ieee80211_free_keys) (ieee80211_del_virtual_monitor+0x51c/0x850)
(ieee80211_del_virtual_monitor) (ieee80211_stop+0x30/0x3c)
(ieee80211_stop) (__dev_close_many+0x94/0xb8)
(__dev_close_many) (dev_close_many+0x5c/0xc8)

Restricting delayed decrement to station interface alone fixes the problem
and it makes sense to do so because delayed decrement is done to improve
roam time which is applicable only for client devices.

Signed-off-by: Manikanta Pubbisetty <mpubbise@codeaurora.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c |  2 +-
 net/mac80211/key.c | 24 +++++++++++++++---------
 2 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 02f3672e7b5e..d25da0e66da1 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -495,7 +495,7 @@ static int ieee80211_del_key(struct wiphy *wiphy, struct net_device *dev,
 		goto out_unlock;
 	}
 
-	ieee80211_key_free(key, true);
+	ieee80211_key_free(key, sdata->vif.type == NL80211_IFTYPE_STATION);
 
 	ret = 0;
  out_unlock:
diff --git a/net/mac80211/key.c b/net/mac80211/key.c
index ee0d0cc8dc3b..c054ac85793c 100644
--- a/net/mac80211/key.c
+++ b/net/mac80211/key.c
@@ -656,11 +656,15 @@ int ieee80211_key_link(struct ieee80211_key *key,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_key *old_key;
-	int idx, ret;
-	bool pairwise;
-
-	pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE;
-	idx = key->conf.keyidx;
+	int idx = key->conf.keyidx;
+	bool pairwise = key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE;
+	/*
+	 * We want to delay tailroom updates only for station - in that
+	 * case it helps roaming speed, but in other cases it hurts and
+	 * can cause warnings to appear.
+	 */
+	bool delay_tailroom = sdata->vif.type == NL80211_IFTYPE_STATION;
+	int ret;
 
 	mutex_lock(&sdata->local->key_mtx);
 
@@ -688,14 +692,14 @@ int ieee80211_key_link(struct ieee80211_key *key,
 	increment_tailroom_need_count(sdata);
 
 	ieee80211_key_replace(sdata, sta, pairwise, old_key, key);
-	ieee80211_key_destroy(old_key, true);
+	ieee80211_key_destroy(old_key, delay_tailroom);
 
 	ieee80211_debugfs_key_add(key);
 
 	if (!local->wowlan) {
 		ret = ieee80211_key_enable_hw_accel(key);
 		if (ret)
-			ieee80211_key_free(key, true);
+			ieee80211_key_free(key, delay_tailroom);
 	} else {
 		ret = 0;
 	}
@@ -930,7 +934,8 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 		ieee80211_key_replace(key->sdata, key->sta,
 				key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE,
 				key, NULL);
-		__ieee80211_key_destroy(key, true);
+		__ieee80211_key_destroy(key, key->sdata->vif.type ==
+					NL80211_IFTYPE_STATION);
 	}
 
 	for (i = 0; i < NUM_DEFAULT_KEYS; i++) {
@@ -940,7 +945,8 @@ void ieee80211_free_sta_keys(struct ieee80211_local *local,
 		ieee80211_key_replace(key->sdata, key->sta,
 				key->conf.flags & IEEE80211_KEY_FLAG_PAIRWISE,
 				key, NULL);
-		__ieee80211_key_destroy(key, true);
+		__ieee80211_key_destroy(key, key->sdata->vif.type ==
+					NL80211_IFTYPE_STATION);
 	}
 
 	mutex_unlock(&local->key_mtx);
-- 
cgit v1.2.3


From dc684af6fc8d3b9be7fda67e380e91bfdc773aa5 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 11 Jun 2018 14:24:59 +0200
Subject: drm/exynos: Suspend/resume display pipeline as early/late as possible

In the current code, exynos_drm_suspend() function is called after all
real devices (CRTCs, Encoders, etc) are suspended, because Exynos DRM
virtual platform device is created as last device in the system (as
a part of DRM registration). None of the devices for real hardware
modules has its own system suspend/resume callbacks, so it doesn't
change any order of the executed code, but it has a side-effect:
runtime PM callbacks for real devices are not executed, because those
devices are considered by PM core as already suspended. This might
cause issues on boards with complex pipelines, where something
depends on the runtime PM state of the given device.

To ensure that exynos_drm_suspend() is called before any suspend
callback from the real devices, assign it to .prepare callback. Same
for exynos_drm_resume(), using .complete callback ensures that all
real devices have been resumed when calling it.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_drm_drv.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_drm_drv.c b/drivers/gpu/drm/exynos/exynos_drm_drv.c
index 29fe6138e182..b599f74692e5 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_drv.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_drv.c
@@ -146,7 +146,6 @@ static struct drm_driver exynos_drm_driver = {
 	.minor	= DRIVER_MINOR,
 };
 
-#ifdef CONFIG_PM_SLEEP
 static int exynos_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
@@ -169,25 +168,23 @@ static int exynos_drm_suspend(struct device *dev)
 	return 0;
 }
 
-static int exynos_drm_resume(struct device *dev)
+static void exynos_drm_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
 	struct exynos_drm_private *private;
 
 	if (!drm_dev)
-		return 0;
+		return;
 
 	private = drm_dev->dev_private;
 	drm_atomic_helper_resume(drm_dev, private->suspend_state);
 	exynos_drm_fbdev_resume(drm_dev);
 	drm_kms_helper_poll_enable(drm_dev);
-
-	return 0;
 }
-#endif
 
 static const struct dev_pm_ops exynos_drm_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(exynos_drm_suspend, exynos_drm_resume)
+	.prepare = exynos_drm_suspend,
+	.complete = exynos_drm_resume,
 };
 
 /* forward declaration */
-- 
cgit v1.2.3


From 7e915746de03e0e62d58491f22805cc5a80a581a Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Mon, 11 Jun 2018 14:25:00 +0200
Subject: drm/exynos: Ensure suspended runtime PM state during system suspend

Add calls to pm_runtime_force_{suspend,resume} as SYSTEM_SLEEP_PM_OPS for
all drivers for the real Exynos DRM hardware modules. This ensures that
the resources will be released for the system PM suspend/resume cycle.
Exynos DRM core already takes care of suspending the whole display pipeline
before PM callbacks of the real devices are called.

Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos5433_drm_decon.c | 2 ++
 drivers/gpu/drm/exynos/exynos7_drm_decon.c    | 2 ++
 drivers/gpu/drm/exynos/exynos_dp.c            | 3 +++
 drivers/gpu/drm/exynos/exynos_drm_dsi.c       | 2 ++
 drivers/gpu/drm/exynos/exynos_drm_fimd.c      | 2 ++
 drivers/gpu/drm/exynos/exynos_drm_mic.c       | 2 ++
 drivers/gpu/drm/exynos/exynos_hdmi.c          | 2 ++
 drivers/gpu/drm/exynos/exynos_mixer.c         | 2 ++
 8 files changed, 17 insertions(+)

diff --git a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
index e868773ea509..94529aa82339 100644
--- a/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos5433_drm_decon.c
@@ -673,6 +673,8 @@ err:
 static const struct dev_pm_ops exynos5433_decon_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos5433_decon_suspend, exynos5433_decon_resume,
 			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				     pm_runtime_force_resume)
 };
 
 static const struct of_device_id exynos5433_decon_driver_dt_match[] = {
diff --git a/drivers/gpu/drm/exynos/exynos7_drm_decon.c b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
index 3931d5e33fe0..88cbd000eb09 100644
--- a/drivers/gpu/drm/exynos/exynos7_drm_decon.c
+++ b/drivers/gpu/drm/exynos/exynos7_drm_decon.c
@@ -832,6 +832,8 @@ static int exynos7_decon_resume(struct device *dev)
 static const struct dev_pm_ops exynos7_decon_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos7_decon_suspend, exynos7_decon_resume,
 			   NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver decon_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_dp.c b/drivers/gpu/drm/exynos/exynos_dp.c
index af7ab1ceb50f..c8449ae4f4fe 100644
--- a/drivers/gpu/drm/exynos/exynos_dp.c
+++ b/drivers/gpu/drm/exynos/exynos_dp.c
@@ -16,6 +16,7 @@
 #include <linux/clk.h>
 #include <linux/of_graph.h>
 #include <linux/component.h>
+#include <linux/pm_runtime.h>
 #include <video/of_display_timing.h>
 #include <video/of_videomode.h>
 #include <video/videomode.h>
@@ -278,6 +279,8 @@ static int exynos_dp_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_dp_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_dp_suspend, exynos_dp_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static const struct of_device_id exynos_dp_match[] = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_dsi.c b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
index a1ed6146a3b5..781b82c2c579 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_dsi.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_dsi.c
@@ -1863,6 +1863,8 @@ err_clk:
 
 static const struct dev_pm_ops exynos_dsi_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_dsi_suspend, exynos_dsi_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver dsi_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_fimd.c b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
index 01b1570d0c3a..b7f56935a46b 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_fimd.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_fimd.c
@@ -1192,6 +1192,8 @@ static int exynos_fimd_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_fimd_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_fimd_suspend, exynos_fimd_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver fimd_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_drm_mic.c b/drivers/gpu/drm/exynos/exynos_drm_mic.c
index 2174814273e2..2fd299a58297 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_mic.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_mic.c
@@ -367,6 +367,8 @@ static int exynos_mic_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_mic_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_mic_suspend, exynos_mic_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 static int exynos_mic_probe(struct platform_device *pdev)
diff --git a/drivers/gpu/drm/exynos/exynos_hdmi.c b/drivers/gpu/drm/exynos/exynos_hdmi.c
index 3a11c719a580..2092a650df7d 100644
--- a/drivers/gpu/drm/exynos/exynos_hdmi.c
+++ b/drivers/gpu/drm/exynos/exynos_hdmi.c
@@ -2093,6 +2093,8 @@ static int __maybe_unused exynos_hdmi_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_hdmi_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_hdmi_suspend, exynos_hdmi_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver hdmi_driver = {
diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index 272c79f5f5bf..e45278e076da 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -1271,6 +1271,8 @@ static int __maybe_unused exynos_mixer_resume(struct device *dev)
 
 static const struct dev_pm_ops exynos_mixer_pm_ops = {
 	SET_RUNTIME_PM_OPS(exynos_mixer_suspend, exynos_mixer_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
 };
 
 struct platform_driver mixer_driver = {
-- 
cgit v1.2.3


From 3f2b78d630b46c7921cb415be35f686e5293c3a4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Wed, 18 Jul 2018 21:55:20 +0200
Subject: drm/exynos/mixer: Remove unused local variable priv

Remove local variable 'priv' to fix GCC warning:

    drivers/gpu/drm/exynos/exynos_mixer.c: In function 'mixer_initialize':
    drivers/gpu/drm/exynos/exynos_mixer.c:840:29: warning: variable 'priv' set but not used [-Wunused-but-set-variable]

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Inki Dae <inki.dae@samsung.com>
---
 drivers/gpu/drm/exynos/exynos_mixer.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/exynos/exynos_mixer.c b/drivers/gpu/drm/exynos/exynos_mixer.c
index e45278e076da..ffbf4a950f69 100644
--- a/drivers/gpu/drm/exynos/exynos_mixer.c
+++ b/drivers/gpu/drm/exynos/exynos_mixer.c
@@ -837,8 +837,6 @@ static int mixer_initialize(struct mixer_context *mixer_ctx,
 			struct drm_device *drm_dev)
 {
 	int ret;
-	struct exynos_drm_private *priv;
-	priv = drm_dev->dev_private;
 
 	mixer_ctx->drm_dev = drm_dev;
 
-- 
cgit v1.2.3


From 2397134ce2d73dcf1d4846579f594c9f3880b2ec Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 20 Jul 2018 15:32:13 +0800
Subject: x86/platform/pcspeaker: Use PTR_ERR_OR_ZERO() to fix ptr_ret.cocci
 warning

The ptr_ret.cocci script generates the following warning:

  arch/x86/kernel/pcspeaker.c:12:8-14: WARNING: PTR_ERR_OR_ZERO can be used

Use PTR_ERR_OR_ZERO() rather than an open-coded version to fix this.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: gregkh@linuxfoundation.org
Cc: kstewart@linuxfoundation.org
Cc: pombredanne@nexb.com
Link: http://lkml.kernel.org/r/20180720073213.14996-1-yuehaibing@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/kernel/pcspeaker.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/pcspeaker.c b/arch/x86/kernel/pcspeaker.c
index da5190a1ea16..4a710ffffd9a 100644
--- a/arch/x86/kernel/pcspeaker.c
+++ b/arch/x86/kernel/pcspeaker.c
@@ -9,6 +9,6 @@ static __init int add_pcspkr(void)
 
 	pd = platform_device_register_simple("pcspkr", -1, NULL, 0);
 
-	return IS_ERR(pd) ? PTR_ERR(pd) : 0;
+	return PTR_ERR_OR_ZERO(pd);
 }
 device_initcall(add_pcspkr);
-- 
cgit v1.2.3


From 387048f51aecaa083e660fe0f15ad339354b116e Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Sat, 21 Jul 2018 15:55:32 +0800
Subject: x86/mm/tlb: Make clear_asid_other() static

Fixes the following sparse warning:

  arch/x86/mm/tlb.c:38:6: warning: symbol 'clear_asid_other' was not declared. Should it be static?

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dave.hansen@linux.intel.com
Cc: kirill.shutemov@linux.intel.com
Cc: tim.c.chen@linux.intel.com
Link: http://lkml.kernel.org/r/1532159732-22939-1-git-send-email-zhongjiang@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/mm/tlb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index f086195f644c..752dbf4e0e50 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -36,7 +36,7 @@
  * necessary invalidation by clearing out the 'ctx_id' which
  * forces a TLB flush when the context is loaded.
  */
-void clear_asid_other(void)
+static void clear_asid_other(void)
 {
 	u16 asid;
 
-- 
cgit v1.2.3


From 82f2d30570b7ecdf1ce7e6376805f063ae86a7e5 Mon Sep 17 00:00:00 2001
From: Lucas Rangit Magasweran <lucas.magasweran@ieee.org>
Date: Sat, 14 Jul 2018 15:40:18 -0700
Subject: ACPI: battery: remove redundant old_present check on insertion

On removal battery_present changes from 1 to 0 after calling
acpi_battery_get_status() and battery->update_time is set to 0
before returning.

On insertion battery_present changes from 0 to 1 after calling
acpi_battery_get_status() and acpi_battery_get_info() is called
because battery->update_time is 0.

The old_present condition is therefore redundant.

This was added in the commit below when there was a path without
sysfs that would skip getting the newly inserted battery info.

commit 50b178512b7d ("Newly inserted battery might differ from one
just removed, so update of battery info fields is required.")

Signed-off-by: Lucas Rangit Magasweran <lucas.magasweran@ieee.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index d79ad844c78f..78e40a9f5e18 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -918,10 +918,11 @@ static void acpi_battery_quirks(struct acpi_battery *battery)
 
 static int acpi_battery_update(struct acpi_battery *battery, bool resume)
 {
-	int result, old_present = acpi_battery_present(battery);
-	result = acpi_battery_get_status(battery);
+	int result = acpi_battery_get_status(battery);
+
 	if (result)
 		return result;
+
 	if (!acpi_battery_present(battery)) {
 		sysfs_remove_battery(battery);
 		battery->update_time = 0;
@@ -931,8 +932,7 @@ static int acpi_battery_update(struct acpi_battery *battery, bool resume)
 	if (resume)
 		return 0;
 
-	if (!battery->update_time ||
-	    old_present != acpi_battery_present(battery)) {
+	if (!battery->update_time) {
 		result = acpi_battery_get_info(battery);
 		if (result)
 			return result;
-- 
cgit v1.2.3


From f9b54e1961c7052e7d7817d707826eb2b9a1ca09 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 11 Jul 2018 15:05:06 +0200
Subject: ALSA: hda/i915: Allow delayed i915 audio component binding

Currently HD-audio i915 audio binding doesn't support any delayed
binding, and supposes that the i915 driver registers the component
immediately.  This has been OK, so far, but the work-in-progress
change in i915 may introduce the asynchronous binding, which
effectively delays the component registration.

For addressing it, implement a completion to be synced with the master
binding.  The timeout is set to 10 seconds which should be long enough
and hopefully be not too annoying if anyone boots up a debugging
session with i915 KMS turned off.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/hdac_i915.c | 24 ++++++++++++++++++++++--
 1 file changed, 22 insertions(+), 2 deletions(-)

diff --git a/sound/hda/hdac_i915.c b/sound/hda/hdac_i915.c
index 8f2aa8bc1185..b5282cbbe489 100644
--- a/sound/hda/hdac_i915.c
+++ b/sound/hda/hdac_i915.c
@@ -20,6 +20,8 @@
 #include <sound/hda_i915.h>
 #include <sound/hda_register.h>
 
+static struct completion bind_complete;
+
 #define CONTROLLER_IN_GPU(pci) (((pci)->device == 0x0a0c) || \
 				((pci)->device == 0x0c0c) || \
 				((pci)->device == 0x0d0c) || \
@@ -97,6 +99,19 @@ static bool i915_gfx_present(void)
 	return pci_dev_present(ids);
 }
 
+static int i915_master_bind(struct device *dev,
+			    struct drm_audio_component *acomp)
+{
+	complete_all(&bind_complete);
+	/* clear audio_ops here as it was needed only for completion call */
+	acomp->audio_ops = NULL;
+	return 0;
+}
+
+static const struct drm_audio_component_audio_ops i915_init_ops = {
+	.master_bind = i915_master_bind
+};
+
 /**
  * snd_hdac_i915_init - Initialize i915 audio component
  * @bus: HDA core bus
@@ -117,7 +132,9 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 	if (!i915_gfx_present())
 		return -ENODEV;
 
-	err = snd_hdac_acomp_init(bus, NULL,
+	init_completion(&bind_complete);
+
+	err = snd_hdac_acomp_init(bus, &i915_init_ops,
 				  i915_component_master_match,
 				  sizeof(struct i915_audio_component) - sizeof(*acomp));
 	if (err < 0)
@@ -125,8 +142,11 @@ int snd_hdac_i915_init(struct hdac_bus *bus)
 	acomp = bus->audio_component;
 	if (!acomp)
 		return -ENODEV;
-	if (!acomp->ops)
+	if (!acomp->ops) {
 		request_module("i915");
+		/* 10s timeout */
+		wait_for_completion_timeout(&bind_complete, 10 * 1000);
+	}
 	if (!acomp->ops) {
 		snd_hdac_acomp_exit(bus);
 		return -ENODEV;
-- 
cgit v1.2.3


From a241c3d95b8b985834d218eedde3923ed683e862 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 24 Jul 2018 11:36:45 +0200
Subject: ASoC: meson: axg-spdifout: select SND_PCM_IEC958

When CONFIG_SND_PCM_IEC958 is disabled, we get a link error for the
new driver:

sound/soc/meson/axg-spdifout.o: In function `axg_spdifout_hw_params':
axg-spdifout.c:(.text+0x650): undefined reference to `snd_pcm_create_iec958_consumer_hw_params'

The other users use 'select', so we should do the same here.

Fixes: 53eb4b7aaa04 ("ASoC: meson: add axg spdif output")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/meson/Kconfig b/sound/soc/meson/Kconfig
index 4cf93c05a982..8af8bc358a90 100644
--- a/sound/soc/meson/Kconfig
+++ b/sound/soc/meson/Kconfig
@@ -56,6 +56,7 @@ config SND_MESON_AXG_SOUND_CARD
 
 config SND_MESON_AXG_SPDIFOUT
 	tristate "Amlogic AXG SPDIF Output Support"
+	select SND_PCM_IEC958
 	imply SND_SOC_SPDIF
 	help
 	  Select Y or M to add support for SPDIF output serializer embedded
-- 
cgit v1.2.3


From d96f8bd28cd0bae3e6702ae90df593628ef6906f Mon Sep 17 00:00:00 2001
From: Oder Chiou <oder_chiou@realtek.com>
Date: Tue, 24 Jul 2018 15:49:23 +0800
Subject: ASoC: rt5514: Fix the issue of the delay volume applied

The patch fixes the issue of the delay volume applied.

Signed-off-by: Oder Chiou <oder_chiou@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5514.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/rt5514.c b/sound/soc/codecs/rt5514.c
index 1570b91bf018..dca82dd6e3bf 100644
--- a/sound/soc/codecs/rt5514.c
+++ b/sound/soc/codecs/rt5514.c
@@ -64,8 +64,8 @@ static const struct reg_sequence rt5514_patch[] = {
 	{RT5514_ANA_CTRL_LDO10,		0x00028604},
 	{RT5514_ANA_CTRL_ADCFED,	0x00000800},
 	{RT5514_ASRC_IN_CTRL1,		0x00000003},
-	{RT5514_DOWNFILTER0_CTRL3,	0x10000362},
-	{RT5514_DOWNFILTER1_CTRL3,	0x10000362},
+	{RT5514_DOWNFILTER0_CTRL3,	0x10000352},
+	{RT5514_DOWNFILTER1_CTRL3,	0x10000352},
 };
 
 static const struct reg_default rt5514_reg[] = {
@@ -92,10 +92,10 @@ static const struct reg_default rt5514_reg[] = {
 	{RT5514_ASRC_IN_CTRL1,		0x00000003},
 	{RT5514_DOWNFILTER0_CTRL1,	0x00020c2f},
 	{RT5514_DOWNFILTER0_CTRL2,	0x00020c2f},
-	{RT5514_DOWNFILTER0_CTRL3,	0x10000362},
+	{RT5514_DOWNFILTER0_CTRL3,	0x10000352},
 	{RT5514_DOWNFILTER1_CTRL1,	0x00020c2f},
 	{RT5514_DOWNFILTER1_CTRL2,	0x00020c2f},
-	{RT5514_DOWNFILTER1_CTRL3,	0x10000362},
+	{RT5514_DOWNFILTER1_CTRL3,	0x10000352},
 	{RT5514_ANA_CTRL_LDO10,		0x00028604},
 	{RT5514_ANA_CTRL_LDO18_16,	0x02000345},
 	{RT5514_ANA_CTRL_ADC12,		0x0000a2a8},
-- 
cgit v1.2.3


From a70a4694ed38fb68407c142db0f53722553bedea Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Tue, 24 Jul 2018 06:32:59 +0000
Subject: regulator: bd9571mwv: Make symbol 'dev_attr_backup_mode' static

Fixes the following sparse warning:

drivers/regulator/bd9571mwv-regulator.c:220:1: warning:
 symbol 'dev_attr_backup_mode' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/bd9571mwv-regulator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/regulator/bd9571mwv-regulator.c b/drivers/regulator/bd9571mwv-regulator.c
index c44613b9423b..274c5ed7cd73 100644
--- a/drivers/regulator/bd9571mwv-regulator.c
+++ b/drivers/regulator/bd9571mwv-regulator.c
@@ -217,7 +217,7 @@ static ssize_t backup_mode_store(struct device *dev,
 	return count;
 }
 
-DEVICE_ATTR_RW(backup_mode);
+static DEVICE_ATTR_RW(backup_mode);
 
 static int bd9571mwv_suspend(struct device *dev)
 {
-- 
cgit v1.2.3


From 467b061f1ac80f323bedb56d20a24f7bc0d2cec5 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Mon, 23 Jul 2018 16:54:03 +0100
Subject: ASoC: core: add support to snd_soc_dai_get_channel_map()

On Qualcomm platforms, specifically with SLIMbus interfaced codecs,
the codec slim channel numbers are passed to DSP while configuring
the slim audio path. Having get_channel_map() would allow dais to
share such information across multiple dais.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc-dai.h |  8 ++++++++
 sound/soc/soc-core.c    | 22 ++++++++++++++++++++++
 2 files changed, 30 insertions(+)

diff --git a/include/sound/soc-dai.h b/include/sound/soc-dai.h
index a14bc0608ae9..f5d70041108f 100644
--- a/include/sound/soc-dai.h
+++ b/include/sound/soc-dai.h
@@ -138,6 +138,11 @@ int snd_soc_dai_set_tristate(struct snd_soc_dai *dai, int tristate);
 int snd_soc_dai_digital_mute(struct snd_soc_dai *dai, int mute,
 			     int direction);
 
+
+int snd_soc_dai_get_channel_map(struct snd_soc_dai *dai,
+		unsigned int *tx_num, unsigned int *tx_slot,
+		unsigned int *rx_num, unsigned int *rx_slot);
+
 int snd_soc_dai_is_dummy(struct snd_soc_dai *dai);
 
 struct snd_soc_dai_ops {
@@ -165,6 +170,9 @@ struct snd_soc_dai_ops {
 	int (*set_channel_map)(struct snd_soc_dai *dai,
 		unsigned int tx_num, unsigned int *tx_slot,
 		unsigned int rx_num, unsigned int *rx_slot);
+	int (*get_channel_map)(struct snd_soc_dai *dai,
+			unsigned int *tx_num, unsigned int *tx_slot,
+			unsigned int *rx_num, unsigned int *rx_slot);
 	int (*set_tristate)(struct snd_soc_dai *dai, int tristate);
 
 	int (*set_sdw_stream)(struct snd_soc_dai *dai,
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index ad5b0ef16d82..81b27923303d 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -2679,6 +2679,28 @@ int snd_soc_dai_set_channel_map(struct snd_soc_dai *dai,
 }
 EXPORT_SYMBOL_GPL(snd_soc_dai_set_channel_map);
 
+/**
+ * snd_soc_dai_get_channel_map - Get DAI audio channel map
+ * @dai: DAI
+ * @tx_num: how many TX channels
+ * @tx_slot: pointer to an array which imply the TX slot number channel
+ *           0~num-1 uses
+ * @rx_num: how many RX channels
+ * @rx_slot: pointer to an array which imply the RX slot number channel
+ *           0~num-1 uses
+ */
+int snd_soc_dai_get_channel_map(struct snd_soc_dai *dai,
+	unsigned int *tx_num, unsigned int *tx_slot,
+	unsigned int *rx_num, unsigned int *rx_slot)
+{
+	if (dai->driver->ops->get_channel_map)
+		return dai->driver->ops->get_channel_map(dai, tx_num, tx_slot,
+			rx_num, rx_slot);
+	else
+		return -ENOTSUPP;
+}
+EXPORT_SYMBOL_GPL(snd_soc_dai_get_channel_map);
+
 /**
  * snd_soc_dai_set_tristate - configure DAI system or master clock.
  * @dai: DAI
-- 
cgit v1.2.3


From 2c870e61132c082a03769d2ac0a2849ba33c10e3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 24 Jul 2018 11:48:45 +0200
Subject: arm64: fix ACPI dependencies

Kconfig reports a warning on x86 builds after the ARM64 dependency
was added.

drivers/acpi/Kconfig:6:error: recursive dependency detected!
drivers/acpi/Kconfig:6:       symbol ACPI depends on EFI

This rephrases the dependency to keep the ARM64 details out of the
shared Kconfig file, so Kconfig no longer gets confused by it.

For consistency, all three architectures that support ACPI now
select ARCH_SUPPORTS_ACPI in exactly the configuration in which
they allow it. We still need the 'default x86', as each one
wants a different default: default-y on x86, default-n on arm64,
and always-y on ia64.

Fixes: 5bcd44083a08 ("drivers: acpi: add dependency of EFI for arm64")
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig   | 1 +
 arch/ia64/Kconfig    | 1 +
 arch/x86/Kconfig     | 1 +
 drivers/acpi/Kconfig | 8 +++++---
 4 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index e2823362c324..27fd50e86dfe 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1262,6 +1262,7 @@ config EFI
 	bool "UEFI runtime support"
 	depends on OF && !CPU_BIG_ENDIAN
 	depends on KERNEL_MODE_NEON
+	select ARCH_SUPPORTS_ACPI
 	select LIBFDT
 	select UCS2_STRING
 	select EFI_PARAMS_FROM_FDT
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index ff861420b8f5..02eb68d5d1c0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -16,6 +16,7 @@ config IA64
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select PCI if (!IA64_HP_SIM)
 	select ACPI if (!IA64_HP_SIM)
+	select ARCH_SUPPORTS_ACPI if (!IA64_HP_SIM)
 	select ACPI_SYSTEM_POWER_STATES_SUPPORT if ACPI
 	select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
 	select HAVE_UNSTABLE_SCHED_CLOCK
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f1dbb4ee19d7..ee99f5296570 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -75,6 +75,7 @@ config X86
 	select ARCH_MIGHT_HAVE_ACPI_PDC		if ACPI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_SUPPORTS_ACPI
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_NUMA_BALANCING	if X86_64
 	select ARCH_USE_BUILTIN_BSWAP
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index 15ab1daaa808..4a46344bf0e3 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -5,11 +5,10 @@
 
 menuconfig ACPI
 	bool "ACPI (Advanced Configuration and Power Interface) Support"
-	depends on !IA64_HP_SIM
-	depends on IA64 || X86 || (ARM64 && EFI)
+	depends on ARCH_SUPPORTS_ACPI
 	depends on PCI
 	select PNP
-	default y if (IA64 || X86)
+	default y if X86
 	help
 	  Advanced Configuration and Power Interface (ACPI) support for 
 	  Linux requires an ACPI-compliant platform (hardware/firmware),
@@ -41,6 +40,9 @@ menuconfig ACPI
 	  <http://www.acpi.info>
 	  <http://www.uefi.org/acpi/specs>
 
+config ARCH_SUPPORTS_ACPI
+	bool
+
 if ACPI
 
 config ACPI_LEGACY_TABLES_LOOKUP
-- 
cgit v1.2.3


From b80a55e246a1b817cb254d79d077f364a2419578 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Mon, 2 Jul 2018 09:15:03 -0600
Subject: nvme: add controller name to trace events

This appends the controller instance to the nvme trace buffer to
distinguish which controller is dispatching and completing a command.

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/trace.h | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index e6362677447d..35b8c72478d5 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -82,6 +82,7 @@ TRACE_EVENT(nvme_setup_cmd,
 	    TP_PROTO(struct request *req, struct nvme_command *cmd),
 	    TP_ARGS(req, cmd),
 	    TP_STRUCT__entry(
+		__field(int, ctrl_id)
 		__field(int, qid)
 		__field(u8, opcode)
 		__field(u8, flags)
@@ -91,6 +92,7 @@ TRACE_EVENT(nvme_setup_cmd,
 		__array(u8, cdw10, 24)
 	    ),
 	    TP_fast_assign(
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
 		__entry->qid = nvme_req_qid(req);
 		__entry->opcode = cmd->common.opcode;
 		__entry->flags = cmd->common.flags;
@@ -100,9 +102,9 @@ TRACE_EVENT(nvme_setup_cmd,
 		memcpy(__entry->cdw10, cmd->common.cdw10,
 		       sizeof(__entry->cdw10));
 	    ),
-	    TP_printk("qid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->qid, __entry->cid, __entry->nsid,
-		      __entry->flags, __entry->metadata,
+	    TP_printk("nvme%d: qid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+		      __entry->ctrl_id, __entry->qid, __entry->cid,
+		      __entry->nsid, __entry->flags, __entry->metadata,
 		      show_opcode_name(__entry->qid, __entry->opcode),
 		      parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->cdw10))
 );
@@ -111,6 +113,7 @@ TRACE_EVENT(nvme_complete_rq,
 	    TP_PROTO(struct request *req),
 	    TP_ARGS(req),
 	    TP_STRUCT__entry(
+		__field(int, ctrl_id)
 		__field(int, qid)
 		__field(int, cid)
 		__field(u64, result)
@@ -119,6 +122,7 @@ TRACE_EVENT(nvme_complete_rq,
 		__field(u16, status)
 	    ),
 	    TP_fast_assign(
+		__entry->ctrl_id = nvme_req(req)->ctrl->instance;
 		__entry->qid = nvme_req_qid(req);
 		__entry->cid = req->tag;
 		__entry->result = le64_to_cpu(nvme_req(req)->result.u64);
@@ -126,9 +130,10 @@ TRACE_EVENT(nvme_complete_rq,
 		__entry->flags = nvme_req(req)->flags;
 		__entry->status = nvme_req(req)->status;
 	    ),
-	    TP_printk("qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
-		      __entry->qid, __entry->cid, __entry->result,
-		      __entry->retries, __entry->flags, __entry->status)
+	    TP_printk("nvme%d: qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+		      __entry->ctrl_id,  __entry->qid, __entry->cid,
+		      __entry->result, __entry->retries, __entry->flags,
+		      __entry->status)
 
 );
 
-- 
cgit v1.2.3


From 6268953e8977a23ca7512a2921e82a5d9252ec01 Mon Sep 17 00:00:00 2001
From: Keith Busch <keith.busch@intel.com>
Date: Fri, 29 Jun 2018 16:50:03 -0600
Subject: nvme: add disk name to trace events

This will print the disk name to the nvme event trace for io requests so
a user can better distinguish traffic to different disks. This can be used
to  create disk based filters. For example, to see only nvme0n2 traffic:

  echo "disk == \"nvme0n2\"" > /sys/kernel/debug/tracing/events/nvme/filter

Signed-off-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
[hch: turned __assign_disk_name into an inline function]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/trace.c | 11 +++++++++++
 drivers/nvme/host/trace.h | 33 ++++++++++++++++++++++++++-------
 2 files changed, 37 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/host/trace.c b/drivers/nvme/host/trace.c
index 41944bbef835..25b0e310f4a8 100644
--- a/drivers/nvme/host/trace.c
+++ b/drivers/nvme/host/trace.c
@@ -128,3 +128,14 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p,
 		return nvme_trace_common(p, cdw10);
 	}
 }
+
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name)
+{
+	const char *ret = trace_seq_buffer_ptr(p);
+
+	if (*name)
+		trace_seq_printf(p, "disk=%s, ", name);
+	trace_seq_putc(p, 0);
+
+	return ret;
+}
diff --git a/drivers/nvme/host/trace.h b/drivers/nvme/host/trace.h
index 35b8c72478d5..a490790d6691 100644
--- a/drivers/nvme/host/trace.h
+++ b/drivers/nvme/host/trace.h
@@ -78,10 +78,25 @@ const char *nvme_trace_parse_nvm_cmd(struct trace_seq *p, u8 opcode,
 	 nvme_trace_parse_nvm_cmd(p, opcode, cdw10) : 		\
 	 nvme_trace_parse_admin_cmd(p, opcode, cdw10))
 
+const char *nvme_trace_disk_name(struct trace_seq *p, char *name);
+#define __print_disk_name(name)				\
+	nvme_trace_disk_name(p, name)
+
+#ifndef TRACE_HEADER_MULTI_READ
+static inline void __assign_disk_name(char *name, struct gendisk *disk)
+{
+	if (disk)
+		memcpy(name, disk->disk_name, DISK_NAME_LEN);
+	else
+		memset(name, 0, DISK_NAME_LEN);
+}
+#endif
+
 TRACE_EVENT(nvme_setup_cmd,
 	    TP_PROTO(struct request *req, struct nvme_command *cmd),
 	    TP_ARGS(req, cmd),
 	    TP_STRUCT__entry(
+		__array(char, disk, DISK_NAME_LEN)
 		__field(int, ctrl_id)
 		__field(int, qid)
 		__field(u8, opcode)
@@ -99,12 +114,14 @@ TRACE_EVENT(nvme_setup_cmd,
 		__entry->cid = cmd->common.command_id;
 		__entry->nsid = le32_to_cpu(cmd->common.nsid);
 		__entry->metadata = le64_to_cpu(cmd->common.metadata);
+		__assign_disk_name(__entry->disk, req->rq_disk);
 		memcpy(__entry->cdw10, cmd->common.cdw10,
 		       sizeof(__entry->cdw10));
 	    ),
-	    TP_printk("nvme%d: qid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
-		      __entry->ctrl_id, __entry->qid, __entry->cid,
-		      __entry->nsid, __entry->flags, __entry->metadata,
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, nsid=%u, flags=0x%x, meta=0x%llx, cmd=(%s %s)",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
+		      __entry->qid, __entry->cid, __entry->nsid,
+		      __entry->flags, __entry->metadata,
 		      show_opcode_name(__entry->qid, __entry->opcode),
 		      parse_nvme_cmd(__entry->qid, __entry->opcode, __entry->cdw10))
 );
@@ -113,6 +130,7 @@ TRACE_EVENT(nvme_complete_rq,
 	    TP_PROTO(struct request *req),
 	    TP_ARGS(req),
 	    TP_STRUCT__entry(
+		__array(char, disk, DISK_NAME_LEN)
 		__field(int, ctrl_id)
 		__field(int, qid)
 		__field(int, cid)
@@ -129,11 +147,12 @@ TRACE_EVENT(nvme_complete_rq,
 		__entry->retries = nvme_req(req)->retries;
 		__entry->flags = nvme_req(req)->flags;
 		__entry->status = nvme_req(req)->status;
+		__assign_disk_name(__entry->disk, req->rq_disk);
 	    ),
-	    TP_printk("nvme%d: qid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
-		      __entry->ctrl_id,  __entry->qid, __entry->cid,
-		      __entry->result, __entry->retries, __entry->flags,
-		      __entry->status)
+	    TP_printk("nvme%d: %sqid=%d, cmdid=%u, res=%llu, retries=%u, flags=0x%x, status=%u",
+		      __entry->ctrl_id, __print_disk_name(__entry->disk),
+		      __entry->qid, __entry->cid, __entry->result,
+		      __entry->retries, __entry->flags, __entry->status)
 
 );
 
-- 
cgit v1.2.3


From 249090f9016b7d68a18fc4c79c42accca18d6961 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 5 Jul 2018 08:14:00 -0500
Subject: nvme-rdma: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/rdma.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index bb6e26fa8331..2d4a51a80e8f 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1591,6 +1591,7 @@ static int nvme_rdma_cm_handler(struct rdma_cm_id *cm_id,
 	case RDMA_CM_EVENT_CONNECT_ERROR:
 	case RDMA_CM_EVENT_UNREACHABLE:
 		nvme_rdma_destroy_queue_ib(queue);
+		/* fall through */
 	case RDMA_CM_EVENT_ADDR_ERROR:
 		dev_dbg(queue->ctrl->ctrl.device,
 			"CM error event %d\n", ev->event);
-- 
cgit v1.2.3


From 90140624e8face94207003ac9a9d2a329b309d68 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 9 Jul 2018 12:49:05 +0300
Subject: nvme-rdma: unquiesce queues when deleting the controller

If the controller is going away, we need to unquiesce the IO queues so
that all pending request can fail gracefully before moving forward with
controller deletion. Do that before we destroy the IO queues so
blk_cleanup_queue won't block in freeze.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/rdma.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 2d4a51a80e8f..2b683b8d4763 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -1759,6 +1759,8 @@ static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 		nvme_rdma_stop_io_queues(ctrl);
 		blk_mq_tagset_busy_iter(&ctrl->tag_set,
 					nvme_cancel_request, &ctrl->ctrl);
+		if (shutdown)
+			nvme_start_queues(&ctrl->ctrl);
 		nvme_rdma_destroy_io_queues(ctrl, shutdown);
 	}
 
-- 
cgit v1.2.3


From c66e2998c8ca4d5da85d4915612dca29e054ad21 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 9 Jul 2018 12:49:06 +0300
Subject: nvme-rdma: centralize controller setup sequence

Centralize controller sequence to a single routine that correctly cleans
up after failures instead of having multiple apperances in several flows
(create, reset, reconnect).

One thing that we also gain here are the sanity/boundary checks also
when connecting back to a dynamic controller.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/rdma.c | 130 +++++++++++++++++++----------------------------
 1 file changed, 53 insertions(+), 77 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index 2b683b8d4763..c22125c5661b 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -917,24 +917,44 @@ static void nvme_rdma_reconnect_or_remove(struct nvme_rdma_ctrl *ctrl)
 	}
 }
 
-static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+static int nvme_rdma_setup_ctrl(struct nvme_rdma_ctrl *ctrl, bool new)
 {
-	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
-			struct nvme_rdma_ctrl, reconnect_work);
+	int ret = -EINVAL;
 	bool changed;
-	int ret;
-
-	++ctrl->ctrl.nr_reconnects;
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
+	ret = nvme_rdma_configure_admin_queue(ctrl, new);
 	if (ret)
-		goto requeue;
+		return ret;
+
+	if (ctrl->ctrl.icdoff) {
+		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (!(ctrl->ctrl.sgls & (1 << 2))) {
+		dev_err(ctrl->ctrl.device,
+			"Mandatory keyed sgls are not supported!\n");
+		goto destroy_admin;
+	}
+
+	if (ctrl->ctrl.opts->queue_size > ctrl->ctrl.sqsize + 1) {
+		dev_warn(ctrl->ctrl.device,
+			"queue_size %zu > ctrl sqsize %u, clamping down\n",
+			ctrl->ctrl.opts->queue_size, ctrl->ctrl.sqsize + 1);
+	}
+
+	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
+		dev_warn(ctrl->ctrl.device,
+			"sqsize %u > ctrl maxcmd %u, clamping down\n",
+			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
+		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
+	}
 
 	if (ctrl->ctrl.sgls & (1 << 20))
 		ctrl->use_inline_data = true;
 
 	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
+		ret = nvme_rdma_configure_io_queues(ctrl, new);
 		if (ret)
 			goto destroy_admin;
 	}
@@ -943,10 +963,31 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 	if (!changed) {
 		/* state change failure is ok if we're in DELETING state */
 		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
+		ret = -EINVAL;
+		goto destroy_io;
 	}
 
 	nvme_start_ctrl(&ctrl->ctrl);
+	return 0;
+
+destroy_io:
+	if (ctrl->ctrl.queue_count > 1)
+		nvme_rdma_destroy_io_queues(ctrl, new);
+destroy_admin:
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	nvme_rdma_destroy_admin_queue(ctrl, new);
+	return ret;
+}
+
+static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
+{
+	struct nvme_rdma_ctrl *ctrl = container_of(to_delayed_work(work),
+			struct nvme_rdma_ctrl, reconnect_work);
+
+	++ctrl->ctrl.nr_reconnects;
+
+	if (nvme_rdma_setup_ctrl(ctrl, false))
+		goto requeue;
 
 	dev_info(ctrl->ctrl.device, "Successfully reconnected (%d attempts)\n",
 			ctrl->ctrl.nr_reconnects);
@@ -955,9 +996,6 @@ static void nvme_rdma_reconnect_ctrl_work(struct work_struct *work)
 
 	return;
 
-destroy_admin:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
 requeue:
 	dev_info(ctrl->ctrl.device, "Failed reconnect attempt %d\n",
 			ctrl->ctrl.nr_reconnects);
@@ -1786,8 +1824,6 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 {
 	struct nvme_rdma_ctrl *ctrl =
 		container_of(work, struct nvme_rdma_ctrl, ctrl.reset_work);
-	int ret;
-	bool changed;
 
 	nvme_stop_ctrl(&ctrl->ctrl);
 	nvme_rdma_shutdown_ctrl(ctrl, false);
@@ -1798,25 +1834,9 @@ static void nvme_rdma_reset_ctrl_work(struct work_struct *work)
 		return;
 	}
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, false);
-	if (ret)
+	if (nvme_rdma_setup_ctrl(ctrl, false))
 		goto out_fail;
 
-	if (ctrl->ctrl.queue_count > 1) {
-		ret = nvme_rdma_configure_io_queues(ctrl, false);
-		if (ret)
-			goto out_fail;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	if (!changed) {
-		/* state change failure is ok if we're in DELETING state */
-		WARN_ON_ONCE(ctrl->ctrl.state != NVME_CTRL_DELETING);
-		return;
-	}
-
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return;
 
 out_fail:
@@ -1979,49 +1999,10 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING);
 	WARN_ON_ONCE(!changed);
 
-	ret = nvme_rdma_configure_admin_queue(ctrl, true);
+	ret = nvme_rdma_setup_ctrl(ctrl, true);
 	if (ret)
 		goto out_uninit_ctrl;
 
-	/* sanity check icdoff */
-	if (ctrl->ctrl.icdoff) {
-		dev_err(ctrl->ctrl.device, "icdoff is not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* sanity check keyed sgls */
-	if (!(ctrl->ctrl.sgls & (1 << 2))) {
-		dev_err(ctrl->ctrl.device,
-			"Mandatory keyed sgls are not supported!\n");
-		ret = -EINVAL;
-		goto out_remove_admin_queue;
-	}
-
-	/* only warn if argument is too large here, will clamp later */
-	if (opts->queue_size > ctrl->ctrl.sqsize + 1) {
-		dev_warn(ctrl->ctrl.device,
-			"queue_size %zu > ctrl sqsize %u, clamping down\n",
-			opts->queue_size, ctrl->ctrl.sqsize + 1);
-	}
-
-	/* warn if maxcmd is lower than sqsize+1 */
-	if (ctrl->ctrl.sqsize + 1 > ctrl->ctrl.maxcmd) {
-		dev_warn(ctrl->ctrl.device,
-			"sqsize %u > ctrl maxcmd %u, clamping down\n",
-			ctrl->ctrl.sqsize + 1, ctrl->ctrl.maxcmd);
-		ctrl->ctrl.sqsize = ctrl->ctrl.maxcmd - 1;
-	}
-
-	if (opts->nr_io_queues) {
-		ret = nvme_rdma_configure_io_queues(ctrl, true);
-		if (ret)
-			goto out_remove_admin_queue;
-	}
-
-	changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	WARN_ON_ONCE(!changed);
-
 	dev_info(ctrl->ctrl.device, "new ctrl: NQN \"%s\", addr %pISpcs\n",
 		ctrl->ctrl.opts->subsysnqn, &ctrl->addr);
 
@@ -2031,13 +2012,8 @@ static struct nvme_ctrl *nvme_rdma_create_ctrl(struct device *dev,
 	list_add_tail(&ctrl->list, &nvme_rdma_ctrl_list);
 	mutex_unlock(&nvme_rdma_ctrl_mutex);
 
-	nvme_start_ctrl(&ctrl->ctrl);
-
 	return &ctrl->ctrl;
 
-out_remove_admin_queue:
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	nvme_rdma_destroy_admin_queue(ctrl, true);
 out_uninit_ctrl:
 	nvme_uninit_ctrl(&ctrl->ctrl);
 	nvme_put_ctrl(&ctrl->ctrl);
-- 
cgit v1.2.3


From 75862c72323e222656792370e2f240bc4029ff96 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Mon, 9 Jul 2018 12:49:07 +0300
Subject: nvme-rdma: centralize admin/io queue teardown sequence

We follow the same queue teardown sequence in delete, reset and error
recovery. Centralize the logic.  This patch does not change any
functionality.

Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/rdma.c | 66 +++++++++++++++++++++---------------------------
 1 file changed, 29 insertions(+), 37 deletions(-)

diff --git a/drivers/nvme/host/rdma.c b/drivers/nvme/host/rdma.c
index c22125c5661b..13a6064e4794 100644
--- a/drivers/nvme/host/rdma.c
+++ b/drivers/nvme/host/rdma.c
@@ -873,6 +873,31 @@ out_free_io_queues:
 	return ret;
 }
 
+static void nvme_rdma_teardown_admin_queue(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_stop_queue(&ctrl->queues[0]);
+	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set, nvme_cancel_request,
+			&ctrl->ctrl);
+	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_destroy_admin_queue(ctrl, remove);
+}
+
+static void nvme_rdma_teardown_io_queues(struct nvme_rdma_ctrl *ctrl,
+		bool remove)
+{
+	if (ctrl->ctrl.queue_count > 1) {
+		nvme_stop_queues(&ctrl->ctrl);
+		nvme_rdma_stop_io_queues(ctrl);
+		blk_mq_tagset_busy_iter(&ctrl->tag_set, nvme_cancel_request,
+				&ctrl->ctrl);
+		if (remove)
+			nvme_start_queues(&ctrl->ctrl);
+		nvme_rdma_destroy_io_queues(ctrl, remove);
+	}
+}
+
 static void nvme_rdma_stop_ctrl(struct nvme_ctrl *nctrl)
 {
 	struct nvme_rdma_ctrl *ctrl = to_rdma_ctrl(nctrl);
@@ -1008,27 +1033,9 @@ static void nvme_rdma_error_recovery_work(struct work_struct *work)
 			struct nvme_rdma_ctrl, err_work);
 
 	nvme_stop_keep_alive(&ctrl->ctrl);
-
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, false);
-	}
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	nvme_rdma_destroy_admin_queue(ctrl, false);
-
-	/*
-	 * queues are not a live anymore, so restart the queues to fail fast
-	 * new IO
-	 */
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
+	nvme_rdma_teardown_io_queues(ctrl, false);
 	nvme_start_queues(&ctrl->ctrl);
+	nvme_rdma_teardown_admin_queue(ctrl, false);
 
 	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_CONNECTING)) {
 		/* state change failure is ok if we're in DELETING state */
@@ -1792,27 +1799,12 @@ static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {
 
 static void nvme_rdma_shutdown_ctrl(struct nvme_rdma_ctrl *ctrl, bool shutdown)
 {
-	if (ctrl->ctrl.queue_count > 1) {
-		nvme_stop_queues(&ctrl->ctrl);
-		nvme_rdma_stop_io_queues(ctrl);
-		blk_mq_tagset_busy_iter(&ctrl->tag_set,
-					nvme_cancel_request, &ctrl->ctrl);
-		if (shutdown)
-			nvme_start_queues(&ctrl->ctrl);
-		nvme_rdma_destroy_io_queues(ctrl, shutdown);
-	}
-
+	nvme_rdma_teardown_io_queues(ctrl, shutdown);
 	if (shutdown)
 		nvme_shutdown_ctrl(&ctrl->ctrl);
 	else
 		nvme_disable_ctrl(&ctrl->ctrl, ctrl->ctrl.cap);
-
-	blk_mq_quiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_stop_queue(&ctrl->queues[0]);
-	blk_mq_tagset_busy_iter(&ctrl->admin_tag_set,
-				nvme_cancel_request, &ctrl->ctrl);
-	blk_mq_unquiesce_queue(ctrl->ctrl.admin_q);
-	nvme_rdma_destroy_admin_queue(ctrl, shutdown);
+	nvme_rdma_teardown_admin_queue(ctrl, shutdown);
 }
 
 static void nvme_rdma_delete_ctrl(struct nvme_ctrl *ctrl)
-- 
cgit v1.2.3


From 1b72b71faccee986e2128a271125177dfe91f7b7 Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Wed, 11 Jul 2018 12:43:16 +0300
Subject: nvmet: fix file discard return status

If nvmet_copy_from_sgl failed, we falsly return successful
completion status.

Fixes: d5eff33ee6f8 ("nvmet: add simple file backed ns support")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/io-cmd-file.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index 57c660e3245d..dad8d44bf90e 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -227,22 +227,24 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 {
 	int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
 	struct nvme_dsm_range range;
-	loff_t offset;
-	loff_t len;
-	int i, ret;
+	loff_t offset, len;
+	u16 ret;
+	int i;
 
 	for (i = 0; i <= le32_to_cpu(req->cmd->dsm.nr); i++) {
-		if (nvmet_copy_from_sgl(req, i * sizeof(range), &range,
-					sizeof(range)))
+		ret = nvmet_copy_from_sgl(req, i * sizeof(range), &range,
+					sizeof(range));
+		if (ret)
 			break;
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb) << req->ns->blksize_shift;
-		ret = vfs_fallocate(req->ns->file, mode, offset, len);
-		if (ret)
+		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
+			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
 			break;
+		}
 	}
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, ret);
 }
 
 static void nvmet_file_dsm_work(struct work_struct *w)
-- 
cgit v1.2.3


From 9c891c139894ce2ec0ca585a00e0bec5e6b4ccab Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Wed, 11 Jul 2018 16:13:04 +0300
Subject: nvmet: check fileio lba range access boundaries

Fail out-of-bounds with a proper status code.

Fixes: d5eff33ee6f8 ("nvmet: add simple file backed ns support")
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/io-cmd-file.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index dad8d44bf90e..c2d0d08b59c8 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -145,6 +145,12 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 		return;
 	}
 
+	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
+	if (unlikely(pos + req->data_len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	if (nr_bvec > NVMET_MAX_INLINE_BIOVEC)
 		req->f.bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec),
 				GFP_KERNEL);
@@ -160,8 +166,6 @@ static void nvmet_file_execute_rw(struct nvmet_req *req)
 			is_sync = true;
 	}
 
-	pos = le64_to_cpu(req->cmd->rw.slba) << req->ns->blksize_shift;
-
 	memset(&req->f.iocb, 0, sizeof(struct kiocb));
 	for_each_sg_page(req->sg, &sg_pg_iter, req->sg_cnt, 0) {
 		nvmet_file_init_bvec(&req->f.bvec[bv_cnt], &sg_pg_iter);
@@ -236,8 +240,14 @@ static void nvmet_file_execute_discard(struct nvmet_req *req)
 					sizeof(range));
 		if (ret)
 			break;
+
 		offset = le64_to_cpu(range.slba) << req->ns->blksize_shift;
 		len = le32_to_cpu(range.nlb) << req->ns->blksize_shift;
+		if (offset + len > req->ns->size) {
+			ret = NVME_SC_LBA_RANGE | NVME_SC_DNR;
+			break;
+		}
+
 		if (vfs_fallocate(req->ns->file, mode, offset, len)) {
 			ret = NVME_SC_INTERNAL | NVME_SC_DNR;
 			break;
@@ -283,6 +293,11 @@ static void nvmet_file_write_zeroes_work(struct work_struct *w)
 	len = (((sector_t)le16_to_cpu(write_zeroes->length) + 1) <<
 			req->ns->blksize_shift);
 
+	if (unlikely(offset + len > req->ns->size)) {
+		nvmet_req_complete(req, NVME_SC_LBA_RANGE | NVME_SC_DNR);
+		return;
+	}
+
 	ret = vfs_fallocate(req->ns->file, mode, offset, len);
 	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
 }
-- 
cgit v1.2.3


From 1b0d274523df5ef1caedc834da055ff721e4d4f0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 17 Jul 2018 17:17:36 +0300
Subject: nvmet: don't use uuid_le type

Don't use sizeof(uuid_le) where none of the parameters is type of uuid_le.
Since both arguments are u8 [16], use size of destination there.

Moreover, uuid_le is a deprecated type, and nvmet is using uuid_t
already.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/admin-cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 837bbdbfaa4b..16a9b24270f9 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -338,7 +338,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 */
 	id->nmic = (1 << 0);
 
-	memcpy(&id->nguid, &ns->nguid, sizeof(uuid_le));
+	memcpy(&id->nguid, &ns->nguid, sizeof(id->nguid));
 
 	id->lbaf[0].ds = ns->blksize_shift;
 
-- 
cgit v1.2.3


From ad66225dff3f30fece4f5133ea14058c95f4e29a Mon Sep 17 00:00:00 2001
From: Peter Geis <pgwipeout@gmail.com>
Date: Tue, 24 Jul 2018 09:25:40 -0400
Subject: regulator: Add sw2_sw4 voltage table to cpcap regulator.

SW2 and SW4 use a shared table to provide voltage to the cpu core and
devices on Tegra hardware.
Added this table to the cpcap regulator driver as the first step to
supporting this device on Tegra.

Signed-off-by: Peter Geis <pgwipeout@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/cpcap-regulator.c | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/regulator/cpcap-regulator.c b/drivers/regulator/cpcap-regulator.c
index bd910fe123d9..c0b1e04bd90f 100644
--- a/drivers/regulator/cpcap-regulator.c
+++ b/drivers/regulator/cpcap-regulator.c
@@ -271,6 +271,29 @@ static struct regulator_ops cpcap_regulator_ops = {
 };
 
 static const unsigned int unknown_val_tbl[] = { 0, };
+static const unsigned int sw2_sw4_val_tbl[] = { 612500, 625000, 637500,
+						650000, 662500, 675000,
+						687500, 700000, 712500,
+						725000, 737500, 750000,
+						762500, 775000, 787500,
+						800000, 812500, 825000,
+						837500, 850000, 862500,
+						875000, 887500, 900000,
+						912500, 925000, 937500,
+						950000, 962500, 975000,
+						987500, 1000000, 1012500,
+						1025000, 1037500, 1050000,
+						1062500, 1075000, 1087500,
+						1100000, 1112500, 1125000,
+						1137500, 1150000, 1162500,
+						1175000, 1187500, 1200000,
+						1212500, 1225000, 1237500,
+						1250000, 1262500, 1275000,
+						1287500, 1300000, 1312500,
+						1325000, 1337500, 1350000,
+						1362500, 1375000, 1387500,
+						1400000, 1412500, 1425000,
+						1437500, 1450000, 1462500, };
 static const unsigned int sw5_val_tbl[] = { 0, 5050000, };
 static const unsigned int vcam_val_tbl[] = { 2600000, 2700000, 2800000,
 					     2900000, };
-- 
cgit v1.2.3


From 6c0b319c0306accd92dc1601f8bf42adc147d4bf Mon Sep 17 00:00:00 2001
From: Peter Geis <pgwipeout@gmail.com>
Date: Tue, 24 Jul 2018 09:25:41 -0400
Subject: regulator: Add support for CPCAP regulators on Motorola Xoom devices.

Added support for the CPCAP power management regulator functions on
Tegra based Motorola Xoom devices.
Added sw2_sw4 value tables, which provide power to the Tegra core and
aux devices.
Added the Xoom init tables and device tree compatibility match.

Signed-off-by: Peter Geis <pgwipeout@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/regulator/cpcap-regulator.txt         |  1 +
 drivers/regulator/cpcap-regulator.c                | 80 ++++++++++++++++++++++
 2 files changed, 81 insertions(+)

diff --git a/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt b/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
index 675f4437ce92..36f5e2f5cc0f 100644
--- a/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/cpcap-regulator.txt
@@ -5,6 +5,7 @@ Requires node properties:
 - "compatible" value one of:
     "motorola,cpcap-regulator"
     "motorola,mapphone-cpcap-regulator"
+    "motorola,xoom-cpcap-regulator"
 
 Required regulator properties:
 - "regulator-name"
diff --git a/drivers/regulator/cpcap-regulator.c b/drivers/regulator/cpcap-regulator.c
index c0b1e04bd90f..2131457937b7 100644
--- a/drivers/regulator/cpcap-regulator.c
+++ b/drivers/regulator/cpcap-regulator.c
@@ -412,6 +412,82 @@ static struct cpcap_regulator omap4_regulators[] = {
 	{ /* sentinel */ },
 };
 
+static struct cpcap_regulator xoom_regulators[] = {
+	CPCAP_REG(SW1, CPCAP_REG_S1C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW1_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW2, CPCAP_REG_S2C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW2_SEL, sw2_sw4_val_tbl,
+		  0xf00, 0x7f, 0, 0x800, 0, 120),
+	CPCAP_REG(SW3, CPCAP_REG_S3C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW3_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(SW4, CPCAP_REG_S4C1, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW4_SEL, sw2_sw4_val_tbl,
+		  0xf00, 0x7f, 0, 0x900, 0, 100),
+	CPCAP_REG(SW5, CPCAP_REG_S5C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW5_SEL, sw5_val_tbl,
+		  0x2a, 0, 0, 0x22, 0, 0),
+	CPCAP_REG(SW6, CPCAP_REG_S6C, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_SW6_SEL, unknown_val_tbl,
+		  0, 0, 0, 0, 0, 0),
+	CPCAP_REG(VCAM, CPCAP_REG_VCAMC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VCAM_SEL, vcam_val_tbl,
+		  0x87, 0x30, 4, 0x7, 0, 420),
+	CPCAP_REG(VCSI, CPCAP_REG_VCSIC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VCSI_SEL, vcsi_val_tbl,
+		  0x47, 0x10, 4, 0x7, 0, 350),
+	CPCAP_REG(VDAC, CPCAP_REG_VDACC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VDAC_SEL, vdac_val_tbl,
+		  0x87, 0x30, 4, 0x3, 0, 420),
+	CPCAP_REG(VDIG, CPCAP_REG_VDIGC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VDIG_SEL, vdig_val_tbl,
+		  0x87, 0x30, 4, 0x5, 0, 420),
+	CPCAP_REG(VFUSE, CPCAP_REG_VFUSEC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VFUSE_SEL, vfuse_val_tbl,
+		  0x80, 0xf, 0, 0x80, 0, 420),
+	CPCAP_REG(VHVIO, CPCAP_REG_VHVIOC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VHVIO_SEL, vhvio_val_tbl,
+		  0x17, 0, 0, 0x2, 0, 0),
+	CPCAP_REG(VSDIO, CPCAP_REG_VSDIOC, CPCAP_REG_ASSIGN2,
+		  CPCAP_BIT_VSDIO_SEL, vsdio_val_tbl,
+		  0x87, 0x38, 3, 0x2, 0, 420),
+	CPCAP_REG(VPLL, CPCAP_REG_VPLLC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VPLL_SEL, vpll_val_tbl,
+		  0x43, 0x18, 3, 0x1, 0, 420),
+	CPCAP_REG(VRF1, CPCAP_REG_VRF1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF1_SEL, vrf1_val_tbl,
+		  0xac, 0x2, 1, 0xc, 0, 10),
+	CPCAP_REG(VRF2, CPCAP_REG_VRF2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRF2_SEL, vrf2_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 10),
+	CPCAP_REG(VRFREF, CPCAP_REG_VRFREFC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VRFREF_SEL, vrfref_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 420),
+	CPCAP_REG(VWLAN1, CPCAP_REG_VWLAN1C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN1_SEL, vwlan1_val_tbl,
+		  0x47, 0x10, 4, 0x5, 0, 420),
+	CPCAP_REG(VWLAN2, CPCAP_REG_VWLAN2C, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VWLAN2_SEL, vwlan2_val_tbl,
+		  0x20c, 0xc0, 6, 0x8, 0, 420),
+	CPCAP_REG(VSIM, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsim_val_tbl,
+		  0x23, 0x8, 3, 0x3, 0, 420),
+	CPCAP_REG(VSIMCARD, CPCAP_REG_VSIMC, CPCAP_REG_ASSIGN3,
+		  0xffff, vsimcard_val_tbl,
+		  0x1e80, 0x8, 3, 0x1e00, 0, 420),
+	CPCAP_REG(VVIB, CPCAP_REG_VVIBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VVIB_SEL, vvib_val_tbl,
+		  0x1, 0xc, 2, 0, 0x1, 500),
+	CPCAP_REG(VUSB, CPCAP_REG_VUSBC, CPCAP_REG_ASSIGN3,
+		  CPCAP_BIT_VUSB_SEL, vusb_val_tbl,
+		  0x11c, 0x40, 6, 0xc, 0, 0),
+	CPCAP_REG(VAUDIO, CPCAP_REG_VAUDIOC, CPCAP_REG_ASSIGN4,
+		  CPCAP_BIT_VAUDIO_SEL, vaudio_val_tbl,
+		  0x16, 0x1, 0, 0x4, 0, 0),
+	{ /* sentinel */ },
+};
+
 static const struct of_device_id cpcap_regulator_id_table[] = {
 	{
 		.compatible = "motorola,cpcap-regulator",
@@ -420,6 +496,10 @@ static const struct of_device_id cpcap_regulator_id_table[] = {
 		.compatible = "motorola,mapphone-cpcap-regulator",
 		.data = omap4_regulators,
 	},
+	{
+		.compatible = "motorola,xoom-cpcap-regulator",
+		.data = xoom_regulators,
+	},
 	{},
 };
 MODULE_DEVICE_TABLE(of, cpcap_regulator_id_table);
-- 
cgit v1.2.3


From 6576bf009aab00f8376efeb24628dd2b86f68200 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 24 Jul 2018 10:04:02 -0300
Subject: spi: spi-fsl-dspi: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-dspi.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 9e598642ca66..7cb3ab0a35a0 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -1,17 +1,9 @@
-/*
- * drivers/spi/spi-fsl-dspi.c
- *
- * Copyright 2013 Freescale Semiconductor, Inc.
- *
- * Freescale DSPI driver
- * This file contains a driver for the Freescale DSPI
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2013 Freescale Semiconductor, Inc.
+//
+// Freescale DSPI driver
+// This file contains a driver for the Freescale DSPI
 
 #include <linux/clk.h>
 #include <linux/delay.h>
-- 
cgit v1.2.3


From 06060ea7fb5b6b9b4c3251e0dcabbcca8ad91674 Mon Sep 17 00:00:00 2001
From: Shaokun Zhang <zhangshaokun@hisilicon.com>
Date: Thu, 19 Jul 2018 19:26:40 +0800
Subject: drivers/perf: hisi: update the sccl_id/ccl_id when MT is supported

MT bit in MPIDR_EL1 is now supported in certain HiSilicon platforms, so
the mapping between sccl_id/ccl_id and affinity level needs to be updated
from the generic encoding we originally used.

Cc: John Garry <john.garry@huawei.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
[will: fixed comment]
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/perf/hisilicon/hisi_uncore_pmu.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/perf/hisilicon/hisi_uncore_pmu.c b/drivers/perf/hisilicon/hisi_uncore_pmu.c
index 44df61397a38..9efd2413240c 100644
--- a/drivers/perf/hisilicon/hisi_uncore_pmu.c
+++ b/drivers/perf/hisilicon/hisi_uncore_pmu.c
@@ -350,19 +350,21 @@ void hisi_uncore_pmu_disable(struct pmu *pmu)
 
 /*
  * Read Super CPU cluster and CPU cluster ID from MPIDR_EL1.
- * If multi-threading is supported, SCCL_ID is in MPIDR[aff3] and CCL_ID
- * is in MPIDR[aff2]; if not, SCCL_ID is in MPIDR[aff2] and CCL_ID is
- * in MPIDR[aff1]. If this changes in future, this shall be updated.
+ * If multi-threading is supported, CCL_ID is the low 3-bits in MPIDR[Aff2]
+ * and SCCL_ID is the upper 5-bits of Aff2 field; if not, SCCL_ID
+ * is in MPIDR[Aff2] and CCL_ID is in MPIDR[Aff1].
  */
 static void hisi_read_sccl_and_ccl_id(int *sccl_id, int *ccl_id)
 {
 	u64 mpidr = read_cpuid_mpidr();
 
 	if (mpidr & MPIDR_MT_BITMASK) {
+		int aff2 = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+
 		if (sccl_id)
-			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 3);
+			*sccl_id = aff2 >> 3;
 		if (ccl_id)
-			*ccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
+			*ccl_id = aff2 & 0x7;
 	} else {
 		if (sccl_id)
 			*sccl_id = MPIDR_AFFINITY_LEVEL(mpidr, 2);
-- 
cgit v1.2.3


From a021cac420f8a3bd1c36c91af9dd3143c44101d7 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 17 Jul 2018 16:31:50 +0200
Subject: spi: imx: Remove duplicate variable assignments

Some fields in struct spi_imx_data are assigned a different value twice
in a row, in spi_imx_setupxfer.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-imx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index d3b21faf6b1f..d75153c995af 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -1106,8 +1106,6 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	if (spi_imx->devtype_data->dynamic_burst && !spi_imx->slave_mode) {
 		u32 mask;
 
-		spi_imx->dynamic_burst = 0;
-		spi_imx->remainder = 0;
 		spi_imx->read_u32  = 1;
 
 		mask = (1 << spi_imx->bits_per_word) - 1;
-- 
cgit v1.2.3


From 2801b2f5fad3d1e9ea0ac8484584051071065645 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 17 Jul 2018 16:31:51 +0200
Subject: spi: imx: Use dynamic bursts only when bits_per_word is 8, 16 or 32

The dynamic bursts mode allows to group together multiple words into a
single burst. To do so, it's necessary that words can be packed into the
32-bits FIFO entries, so we can't allow using this mode with bit_per_words
different to 8, 16 or 32.

This prevents shitfing out extra clock ticks for transfers with
bit_per_word values not aligned on 8 bits.

With that , we are sure that only the correct number of bits is
shifted out at each transfer, so we don't need to mask out the remaining
parts of the words.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-imx.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index d75153c995af..ecafbda5ec94 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -95,7 +95,6 @@ struct spi_imx_data {
 	const void *tx_buf;
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
 	unsigned int dynamic_burst, read_u32;
-	unsigned int word_mask;
 
 	/* Slave mode */
 	bool slave_mode;
@@ -291,7 +290,6 @@ static void spi_imx_buf_rx_swap_u32(struct spi_imx_data *spi_imx)
 		else if (bytes_per_word == 2)
 			val = (val << 16) | (val >> 16);
 #endif
-		val &= spi_imx->word_mask;
 		*(u32 *)spi_imx->rx_buf = val;
 		spi_imx->rx_buf += sizeof(u32);
 	}
@@ -322,7 +320,6 @@ static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
 
 	if (spi_imx->tx_buf) {
 		val = *(u32 *)spi_imx->tx_buf;
-		val &= spi_imx->word_mask;
 		spi_imx->tx_buf += sizeof(u32);
 	}
 
@@ -1102,25 +1099,23 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	spi_imx->bits_per_word = t->bits_per_word;
 	spi_imx->speed_hz  = t->speed_hz;
 
-	/* Initialize the functions for transfer */
-	if (spi_imx->devtype_data->dynamic_burst && !spi_imx->slave_mode) {
-		u32 mask;
+	/*
+	 * Initialize the functions for transfer. To transfer non byte-aligned
+	 * words, we have to use multiple word-size bursts, we can't use
+	 * dynamic_burst in that case.
+	 */
+	if (spi_imx->devtype_data->dynamic_burst && !spi_imx->slave_mode &&
+	    (spi_imx->bits_per_word == 8 ||
+	    spi_imx->bits_per_word == 16 ||
+	    spi_imx->bits_per_word == 32)) {
 
 		spi_imx->read_u32  = 1;
 
-		mask = (1 << spi_imx->bits_per_word) - 1;
 		spi_imx->rx = spi_imx_buf_rx_swap;
 		spi_imx->tx = spi_imx_buf_tx_swap;
 		spi_imx->dynamic_burst = 1;
 		spi_imx->remainder = t->len;
 
-		if (spi_imx->bits_per_word <= 8)
-			spi_imx->word_mask = mask << 24 | mask << 16
-					     | mask << 8 | mask;
-		else if (spi_imx->bits_per_word <= 16)
-			spi_imx->word_mask = mask << 16 | mask;
-		else
-			spi_imx->word_mask = mask;
 	} else {
 		if (spi_imx->bits_per_word <= 8) {
 			spi_imx->rx = spi_imx_buf_rx_u8;
-- 
cgit v1.2.3


From afb27208146af82b249e0cdc40142b4ffd211887 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 17 Jul 2018 16:31:52 +0200
Subject: spi: imx: Use correct number of bytes per words

The SPI core enforces that we always use the next power-of-two number of
bytes to store words. As a result, a 24 bits word will be stored in 4
bytes.

This commit fixes the spi_imx_bytes_per_word function to return the
correct number of bytes.

This also allows to get rid of unnecessary checks in the can_dma
function, since the SPI core validates that we always have a transfer
length that is a multiple of the number of bytes per word.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-imx.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index ecafbda5ec94..3ae706dac660 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -202,7 +202,12 @@ out:
 
 static int spi_imx_bytes_per_word(const int bits_per_word)
 {
-	return DIV_ROUND_UP(bits_per_word, BITS_PER_BYTE);
+	if (bits_per_word <= 8)
+		return 1;
+	else if (bits_per_word <= 16)
+		return 2;
+	else
+		return 4;
 }
 
 static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
@@ -219,9 +224,6 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 
 	bytes_per_word = spi_imx_bytes_per_word(transfer->bits_per_word);
 
-	if (bytes_per_word != 1 && bytes_per_word != 2 && bytes_per_word != 4)
-		return false;
-
 	for (i = spi_imx->devtype_data->fifo_size / 2; i > 0; i--) {
 		if (!(transfer->len % (i * bytes_per_word)))
 			break;
-- 
cgit v1.2.3


From 0486dd4d6111b969a81b9ce63bfaf22e414839a4 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 17 Jul 2018 16:31:53 +0200
Subject: spi: imx: remove unnecessary check in spi_imx_can_dma

The spi_imx_can_dma function computes the watermark level so that
the transfer will fit in exactly N bursts (without a remainder).

The smallest watermark level possible being one FIFO entry per burst, we
can't never have a case where the transfer size isn't divsiible by 1.

Remove the extra check for the wml being different than 0.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-imx.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 3ae706dac660..ef6d3648396a 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -229,9 +229,6 @@ static bool spi_imx_can_dma(struct spi_master *master, struct spi_device *spi,
 			break;
 	}
 
-	if (i == 0)
-		return false;
-
 	spi_imx->wml = i;
 	spi_imx->dynamic_burst = 0;
 
-- 
cgit v1.2.3


From 2ca300ac6e7b5143e0c03cfc91bb064dcad376f4 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Tue, 17 Jul 2018 16:31:54 +0200
Subject: spi: imx: Use the longuest possible burst size when in dynamic_burst

Dynamic burst mode allows to group together multiple words and send them
in one continuous burst. When the number of bytes to be sent is not a
strict multiple of the FIFO entry size (32 bits), the controller expects
the non aligned bits to be sent first.

This commit adds support for this particular constraint, avoiding the
need to send the non-aligned bytes one by one at the end of the
transfer, speeding-up transfer speed in that case.

With this method, a transfer is divided into multiple bursts, limited in
size by the maximum amount of data that the controller can transfer in
one continuous burst (which is 512 bytes).

The non-512 byte part of the transfer is sent first. The remaining bytes
to be transferred in the current burst is stored in the 'remainder'
field.

With this method, the read_u32 field is no longer necessary, and is
removed.

This was tested on imx6 solo and imx6 quad.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-imx.c | 122 +++++++++++++++++++++++++++++++++++---------------
 1 file changed, 85 insertions(+), 37 deletions(-)

diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index ef6d3648396a..08dd3a31a3e5 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -94,7 +94,7 @@ struct spi_imx_data {
 	void *rx_buf;
 	const void *tx_buf;
 	unsigned int txfifo; /* number of words pushed in tx FIFO */
-	unsigned int dynamic_burst, read_u32;
+	unsigned int dynamic_burst;
 
 	/* Slave mode */
 	bool slave_mode;
@@ -139,6 +139,8 @@ static void spi_imx_buf_rx_##type(struct spi_imx_data *spi_imx)		\
 		*(type *)spi_imx->rx_buf = val;				\
 		spi_imx->rx_buf += sizeof(type);			\
 	}								\
+									\
+	spi_imx->remainder -= sizeof(type);				\
 }
 
 #define MXC_SPI_BUF_TX(type)						\
@@ -292,22 +294,36 @@ static void spi_imx_buf_rx_swap_u32(struct spi_imx_data *spi_imx)
 		*(u32 *)spi_imx->rx_buf = val;
 		spi_imx->rx_buf += sizeof(u32);
 	}
+
+	spi_imx->remainder -= sizeof(u32);
 }
 
 static void spi_imx_buf_rx_swap(struct spi_imx_data *spi_imx)
 {
-	unsigned int bytes_per_word;
+	int unaligned;
+	u32 val;
 
-	bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
-	if (spi_imx->read_u32) {
+	unaligned = spi_imx->remainder % 4;
+
+	if (!unaligned) {
 		spi_imx_buf_rx_swap_u32(spi_imx);
 		return;
 	}
 
-	if (bytes_per_word == 1)
-		spi_imx_buf_rx_u8(spi_imx);
-	else if (bytes_per_word == 2)
+	if (spi_imx_bytes_per_word(spi_imx->bits_per_word) == 2) {
 		spi_imx_buf_rx_u16(spi_imx);
+		return;
+	}
+
+	val = readl(spi_imx->base + MXC_CSPIRXDATA);
+
+	while (unaligned--) {
+		if (spi_imx->rx_buf) {
+			*(u8 *)spi_imx->rx_buf = (val >> (8 * unaligned)) & 0xff;
+			spi_imx->rx_buf++;
+		}
+		spi_imx->remainder--;
+	}
 }
 
 static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
@@ -336,40 +352,30 @@ static void spi_imx_buf_tx_swap_u32(struct spi_imx_data *spi_imx)
 
 static void spi_imx_buf_tx_swap(struct spi_imx_data *spi_imx)
 {
-	u32 ctrl, val;
-	unsigned int bytes_per_word;
+	int unaligned;
+	u32 val = 0;
 
-	if (spi_imx->count == spi_imx->remainder) {
-		ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
-		ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
-		if (spi_imx->count > MX51_ECSPI_CTRL_MAX_BURST) {
-			spi_imx->remainder = spi_imx->count %
-					     MX51_ECSPI_CTRL_MAX_BURST;
-			val = MX51_ECSPI_CTRL_MAX_BURST * 8 - 1;
-		} else if (spi_imx->count >= sizeof(u32)) {
-			spi_imx->remainder = spi_imx->count % sizeof(u32);
-			val = (spi_imx->count - spi_imx->remainder) * 8 - 1;
-		} else {
-			spi_imx->remainder = 0;
-			val = spi_imx->bits_per_word - 1;
-			spi_imx->read_u32 = 0;
-		}
+	unaligned = spi_imx->count % 4;
 
-		ctrl |= (val << MX51_ECSPI_CTRL_BL_OFFSET);
-		writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
+	if (!unaligned) {
+		spi_imx_buf_tx_swap_u32(spi_imx);
+		return;
 	}
 
-	if (spi_imx->count >= sizeof(u32)) {
-		spi_imx_buf_tx_swap_u32(spi_imx);
+	if (spi_imx_bytes_per_word(spi_imx->bits_per_word) == 2) {
+		spi_imx_buf_tx_u16(spi_imx);
 		return;
 	}
 
-	bytes_per_word = spi_imx_bytes_per_word(spi_imx->bits_per_word);
+	while (unaligned--) {
+		if (spi_imx->tx_buf) {
+			val |= *(u8 *)spi_imx->tx_buf << (8 * unaligned);
+			spi_imx->tx_buf++;
+		}
+		spi_imx->count--;
+	}
 
-	if (bytes_per_word == 1)
-		spi_imx_buf_tx_u8(spi_imx);
-	else if (bytes_per_word == 2)
-		spi_imx_buf_tx_u16(spi_imx);
+	writel(val, spi_imx->base + MXC_CSPITXDATA);
 }
 
 static void mx53_ecspi_rx_slave(struct spi_imx_data *spi_imx)
@@ -388,6 +394,8 @@ static void mx53_ecspi_rx_slave(struct spi_imx_data *spi_imx)
 		spi_imx->rx_buf += n_bytes;
 		spi_imx->slave_burst -= n_bytes;
 	}
+
+	spi_imx->remainder -= sizeof(u32);
 }
 
 static void mx53_ecspi_tx_slave(struct spi_imx_data *spi_imx)
@@ -997,12 +1005,52 @@ static void spi_imx_chipselect(struct spi_device *spi, int is_active)
 	gpio_set_value(spi->cs_gpio, dev_is_lowactive ^ active);
 }
 
+static void spi_imx_set_burst_len(struct spi_imx_data *spi_imx, int n_bits)
+{
+	u32 ctrl;
+
+	ctrl = readl(spi_imx->base + MX51_ECSPI_CTRL);
+	ctrl &= ~MX51_ECSPI_CTRL_BL_MASK;
+	ctrl |= ((n_bits - 1) << MX51_ECSPI_CTRL_BL_OFFSET);
+	writel(ctrl, spi_imx->base + MX51_ECSPI_CTRL);
+}
+
 static void spi_imx_push(struct spi_imx_data *spi_imx)
 {
+	unsigned int burst_len, fifo_words;
+
+	if (spi_imx->dynamic_burst)
+		fifo_words = 4;
+	else
+		fifo_words = spi_imx_bytes_per_word(spi_imx->bits_per_word);
+	/*
+	 * Reload the FIFO when the remaining bytes to be transferred in the
+	 * current burst is 0. This only applies when bits_per_word is a
+	 * multiple of 8.
+	 */
+	if (!spi_imx->remainder) {
+		if (spi_imx->dynamic_burst) {
+
+			/* We need to deal unaligned data first */
+			burst_len = spi_imx->count % MX51_ECSPI_CTRL_MAX_BURST;
+
+			if (!burst_len)
+				burst_len = MX51_ECSPI_CTRL_MAX_BURST;
+
+			spi_imx_set_burst_len(spi_imx, burst_len * 8);
+
+			spi_imx->remainder = burst_len;
+		} else {
+			spi_imx->remainder = fifo_words;
+		}
+	}
+
 	while (spi_imx->txfifo < spi_imx->devtype_data->fifo_size) {
 		if (!spi_imx->count)
 			break;
-		if (spi_imx->txfifo && (spi_imx->count == spi_imx->remainder))
+		if (spi_imx->dynamic_burst &&
+		    spi_imx->txfifo >=  DIV_ROUND_UP(spi_imx->remainder,
+						     fifo_words))
 			break;
 		spi_imx->tx(spi_imx);
 		spi_imx->txfifo++;
@@ -1108,12 +1156,9 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 	    spi_imx->bits_per_word == 16 ||
 	    spi_imx->bits_per_word == 32)) {
 
-		spi_imx->read_u32  = 1;
-
 		spi_imx->rx = spi_imx_buf_rx_swap;
 		spi_imx->tx = spi_imx_buf_tx_swap;
 		spi_imx->dynamic_burst = 1;
-		spi_imx->remainder = t->len;
 
 	} else {
 		if (spi_imx->bits_per_word <= 8) {
@@ -1126,6 +1171,7 @@ static int spi_imx_setupxfer(struct spi_device *spi,
 			spi_imx->rx = spi_imx_buf_rx_u32;
 			spi_imx->tx = spi_imx_buf_tx_u32;
 		}
+		spi_imx->dynamic_burst = 0;
 	}
 
 	if (spi_imx_can_dma(spi_imx->bitbang.master, spi, t))
@@ -1309,6 +1355,7 @@ static int spi_imx_pio_transfer(struct spi_device *spi,
 	spi_imx->rx_buf = transfer->rx_buf;
 	spi_imx->count = transfer->len;
 	spi_imx->txfifo = 0;
+	spi_imx->remainder = 0;
 
 	reinit_completion(&spi_imx->xfer_done);
 
@@ -1346,6 +1393,7 @@ static int spi_imx_pio_transfer_slave(struct spi_device *spi,
 	spi_imx->rx_buf = transfer->rx_buf;
 	spi_imx->count = transfer->len;
 	spi_imx->txfifo = 0;
+	spi_imx->remainder = 0;
 
 	reinit_completion(&spi_imx->xfer_done);
 	spi_imx->slave_aborted = false;
-- 
cgit v1.2.3


From 76f17d8ba1cbc3d2786955b2f15e071da93527cd Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 23 Jul 2018 14:18:33 -0700
Subject: block: Rename the null_blk_mod kernel module back into null_blk

Commit ca4b2a011948 ("null_blk: add zone support") breaks several
blktests scripts because it renamed the null_blk kernel module into
null_blk_mod. Hence rename null_blk_mod back into null_blk.

Fixes: ca4b2a011948 ("null_blk: add zone support")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Matias Bjorling <matias.bjorling@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Damien Le Moal <damien.lemoal@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/Makefile        |    6 +-
 drivers/block/null_blk.c      | 1926 -----------------------------------------
 drivers/block/null_blk_main.c | 1926 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 1929 insertions(+), 1929 deletions(-)
 delete mode 100644 drivers/block/null_blk.c
 create mode 100644 drivers/block/null_blk_main.c

diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index a0d88aa0c05d..8566b188368b 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -38,9 +38,9 @@ obj-$(CONFIG_BLK_DEV_PCIESSD_MTIP32XX)	+= mtip32xx/
 obj-$(CONFIG_BLK_DEV_RSXX) += rsxx/
 obj-$(CONFIG_ZRAM) += zram/
 
-obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk_mod.o
-null_blk_mod-objs	:= null_blk.o
-null_blk_mod-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
+obj-$(CONFIG_BLK_DEV_NULL_BLK)	+= null_blk.o
+null_blk-objs	:= null_blk_main.o
+null_blk-$(CONFIG_BLK_DEV_ZONED) += null_blk_zoned.o
 
 skd-y		:= skd_main.o
 swim_mod-y	:= swim.o swim_asm.o
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
deleted file mode 100644
index 86cafa6d3b41..000000000000
--- a/drivers/block/null_blk.c
+++ /dev/null
@@ -1,1926 +0,0 @@
-/*
- * Add configfs and memory store: Kyungchan Koh <kkc6196@fb.com> and
- * Shaohua Li <shli@fb.com>
- */
-#include <linux/module.h>
-
-#include <linux/moduleparam.h>
-#include <linux/sched.h>
-#include <linux/fs.h>
-#include <linux/init.h>
-#include "null_blk.h"
-
-#define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
-#define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
-#define SECTOR_MASK		(PAGE_SECTORS - 1)
-
-#define FREE_BATCH		16
-
-#define TICKS_PER_SEC		50ULL
-#define TIMER_INTERVAL		(NSEC_PER_SEC / TICKS_PER_SEC)
-
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-static DECLARE_FAULT_ATTR(null_timeout_attr);
-static DECLARE_FAULT_ATTR(null_requeue_attr);
-#endif
-
-static inline u64 mb_per_tick(int mbps)
-{
-	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
-}
-
-/*
- * Status flags for nullb_device.
- *
- * CONFIGURED:	Device has been configured and turned on. Cannot reconfigure.
- * UP:		Device is currently on and visible in userspace.
- * THROTTLED:	Device is being throttled.
- * CACHE:	Device is using a write-back cache.
- */
-enum nullb_device_flags {
-	NULLB_DEV_FL_CONFIGURED	= 0,
-	NULLB_DEV_FL_UP		= 1,
-	NULLB_DEV_FL_THROTTLED	= 2,
-	NULLB_DEV_FL_CACHE	= 3,
-};
-
-#define MAP_SZ		((PAGE_SIZE >> SECTOR_SHIFT) + 2)
-/*
- * nullb_page is a page in memory for nullb devices.
- *
- * @page:	The page holding the data.
- * @bitmap:	The bitmap represents which sector in the page has data.
- *		Each bit represents one block size. For example, sector 8
- *		will use the 7th bit
- * The highest 2 bits of bitmap are for special purpose. LOCK means the cache
- * page is being flushing to storage. FREE means the cache page is freed and
- * should be skipped from flushing to storage. Please see
- * null_make_cache_space
- */
-struct nullb_page {
-	struct page *page;
-	DECLARE_BITMAP(bitmap, MAP_SZ);
-};
-#define NULLB_PAGE_LOCK (MAP_SZ - 1)
-#define NULLB_PAGE_FREE (MAP_SZ - 2)
-
-static LIST_HEAD(nullb_list);
-static struct mutex lock;
-static int null_major;
-static DEFINE_IDA(nullb_indexes);
-static struct blk_mq_tag_set tag_set;
-
-enum {
-	NULL_IRQ_NONE		= 0,
-	NULL_IRQ_SOFTIRQ	= 1,
-	NULL_IRQ_TIMER		= 2,
-};
-
-enum {
-	NULL_Q_BIO		= 0,
-	NULL_Q_RQ		= 1,
-	NULL_Q_MQ		= 2,
-};
-
-static int g_no_sched;
-module_param_named(no_sched, g_no_sched, int, 0444);
-MODULE_PARM_DESC(no_sched, "No io scheduler");
-
-static int g_submit_queues = 1;
-module_param_named(submit_queues, g_submit_queues, int, 0444);
-MODULE_PARM_DESC(submit_queues, "Number of submission queues");
-
-static int g_home_node = NUMA_NO_NODE;
-module_param_named(home_node, g_home_node, int, 0444);
-MODULE_PARM_DESC(home_node, "Home node for the device");
-
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-static char g_timeout_str[80];
-module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444);
-
-static char g_requeue_str[80];
-module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444);
-#endif
-
-static int g_queue_mode = NULL_Q_MQ;
-
-static int null_param_store_val(const char *str, int *val, int min, int max)
-{
-	int ret, new_val;
-
-	ret = kstrtoint(str, 10, &new_val);
-	if (ret)
-		return -EINVAL;
-
-	if (new_val < min || new_val > max)
-		return -EINVAL;
-
-	*val = new_val;
-	return 0;
-}
-
-static int null_set_queue_mode(const char *str, const struct kernel_param *kp)
-{
-	return null_param_store_val(str, &g_queue_mode, NULL_Q_BIO, NULL_Q_MQ);
-}
-
-static const struct kernel_param_ops null_queue_mode_param_ops = {
-	.set	= null_set_queue_mode,
-	.get	= param_get_int,
-};
-
-device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, 0444);
-MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
-
-static int g_gb = 250;
-module_param_named(gb, g_gb, int, 0444);
-MODULE_PARM_DESC(gb, "Size in GB");
-
-static int g_bs = 512;
-module_param_named(bs, g_bs, int, 0444);
-MODULE_PARM_DESC(bs, "Block size (in bytes)");
-
-static int nr_devices = 1;
-module_param(nr_devices, int, 0444);
-MODULE_PARM_DESC(nr_devices, "Number of devices to register");
-
-static bool g_blocking;
-module_param_named(blocking, g_blocking, bool, 0444);
-MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
-
-static bool shared_tags;
-module_param(shared_tags, bool, 0444);
-MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
-
-static int g_irqmode = NULL_IRQ_SOFTIRQ;
-
-static int null_set_irqmode(const char *str, const struct kernel_param *kp)
-{
-	return null_param_store_val(str, &g_irqmode, NULL_IRQ_NONE,
-					NULL_IRQ_TIMER);
-}
-
-static const struct kernel_param_ops null_irqmode_param_ops = {
-	.set	= null_set_irqmode,
-	.get	= param_get_int,
-};
-
-device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, 0444);
-MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
-
-static unsigned long g_completion_nsec = 10000;
-module_param_named(completion_nsec, g_completion_nsec, ulong, 0444);
-MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
-
-static int g_hw_queue_depth = 64;
-module_param_named(hw_queue_depth, g_hw_queue_depth, int, 0444);
-MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");
-
-static bool g_use_per_node_hctx;
-module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
-MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
-
-static bool g_zoned;
-module_param_named(zoned, g_zoned, bool, S_IRUGO);
-MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
-
-static unsigned long g_zone_size = 256;
-module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
-MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
-
-static struct nullb_device *null_alloc_dev(void);
-static void null_free_dev(struct nullb_device *dev);
-static void null_del_dev(struct nullb *nullb);
-static int null_add_dev(struct nullb_device *dev);
-static void null_free_device_storage(struct nullb_device *dev, bool is_cache);
-
-static inline struct nullb_device *to_nullb_device(struct config_item *item)
-{
-	return item ? container_of(item, struct nullb_device, item) : NULL;
-}
-
-static inline ssize_t nullb_device_uint_attr_show(unsigned int val, char *page)
-{
-	return snprintf(page, PAGE_SIZE, "%u\n", val);
-}
-
-static inline ssize_t nullb_device_ulong_attr_show(unsigned long val,
-	char *page)
-{
-	return snprintf(page, PAGE_SIZE, "%lu\n", val);
-}
-
-static inline ssize_t nullb_device_bool_attr_show(bool val, char *page)
-{
-	return snprintf(page, PAGE_SIZE, "%u\n", val);
-}
-
-static ssize_t nullb_device_uint_attr_store(unsigned int *val,
-	const char *page, size_t count)
-{
-	unsigned int tmp;
-	int result;
-
-	result = kstrtouint(page, 0, &tmp);
-	if (result)
-		return result;
-
-	*val = tmp;
-	return count;
-}
-
-static ssize_t nullb_device_ulong_attr_store(unsigned long *val,
-	const char *page, size_t count)
-{
-	int result;
-	unsigned long tmp;
-
-	result = kstrtoul(page, 0, &tmp);
-	if (result)
-		return result;
-
-	*val = tmp;
-	return count;
-}
-
-static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
-	size_t count)
-{
-	bool tmp;
-	int result;
-
-	result = kstrtobool(page,  &tmp);
-	if (result)
-		return result;
-
-	*val = tmp;
-	return count;
-}
-
-/* The following macro should only be used with TYPE = {uint, ulong, bool}. */
-#define NULLB_DEVICE_ATTR(NAME, TYPE)						\
-static ssize_t									\
-nullb_device_##NAME##_show(struct config_item *item, char *page)		\
-{										\
-	return nullb_device_##TYPE##_attr_show(					\
-				to_nullb_device(item)->NAME, page);		\
-}										\
-static ssize_t									\
-nullb_device_##NAME##_store(struct config_item *item, const char *page,		\
-			    size_t count)					\
-{										\
-	if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags))	\
-		return -EBUSY;							\
-	return nullb_device_##TYPE##_attr_store(				\
-			&to_nullb_device(item)->NAME, page, count);		\
-}										\
-CONFIGFS_ATTR(nullb_device_, NAME);
-
-NULLB_DEVICE_ATTR(size, ulong);
-NULLB_DEVICE_ATTR(completion_nsec, ulong);
-NULLB_DEVICE_ATTR(submit_queues, uint);
-NULLB_DEVICE_ATTR(home_node, uint);
-NULLB_DEVICE_ATTR(queue_mode, uint);
-NULLB_DEVICE_ATTR(blocksize, uint);
-NULLB_DEVICE_ATTR(irqmode, uint);
-NULLB_DEVICE_ATTR(hw_queue_depth, uint);
-NULLB_DEVICE_ATTR(index, uint);
-NULLB_DEVICE_ATTR(blocking, bool);
-NULLB_DEVICE_ATTR(use_per_node_hctx, bool);
-NULLB_DEVICE_ATTR(memory_backed, bool);
-NULLB_DEVICE_ATTR(discard, bool);
-NULLB_DEVICE_ATTR(mbps, uint);
-NULLB_DEVICE_ATTR(cache_size, ulong);
-NULLB_DEVICE_ATTR(zoned, bool);
-NULLB_DEVICE_ATTR(zone_size, ulong);
-
-static ssize_t nullb_device_power_show(struct config_item *item, char *page)
-{
-	return nullb_device_bool_attr_show(to_nullb_device(item)->power, page);
-}
-
-static ssize_t nullb_device_power_store(struct config_item *item,
-				     const char *page, size_t count)
-{
-	struct nullb_device *dev = to_nullb_device(item);
-	bool newp = false;
-	ssize_t ret;
-
-	ret = nullb_device_bool_attr_store(&newp, page, count);
-	if (ret < 0)
-		return ret;
-
-	if (!dev->power && newp) {
-		if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags))
-			return count;
-		if (null_add_dev(dev)) {
-			clear_bit(NULLB_DEV_FL_UP, &dev->flags);
-			return -ENOMEM;
-		}
-
-		set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
-		dev->power = newp;
-	} else if (dev->power && !newp) {
-		mutex_lock(&lock);
-		dev->power = newp;
-		null_del_dev(dev->nullb);
-		mutex_unlock(&lock);
-		clear_bit(NULLB_DEV_FL_UP, &dev->flags);
-		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
-	}
-
-	return count;
-}
-
-CONFIGFS_ATTR(nullb_device_, power);
-
-static ssize_t nullb_device_badblocks_show(struct config_item *item, char *page)
-{
-	struct nullb_device *t_dev = to_nullb_device(item);
-
-	return badblocks_show(&t_dev->badblocks, page, 0);
-}
-
-static ssize_t nullb_device_badblocks_store(struct config_item *item,
-				     const char *page, size_t count)
-{
-	struct nullb_device *t_dev = to_nullb_device(item);
-	char *orig, *buf, *tmp;
-	u64 start, end;
-	int ret;
-
-	orig = kstrndup(page, count, GFP_KERNEL);
-	if (!orig)
-		return -ENOMEM;
-
-	buf = strstrip(orig);
-
-	ret = -EINVAL;
-	if (buf[0] != '+' && buf[0] != '-')
-		goto out;
-	tmp = strchr(&buf[1], '-');
-	if (!tmp)
-		goto out;
-	*tmp = '\0';
-	ret = kstrtoull(buf + 1, 0, &start);
-	if (ret)
-		goto out;
-	ret = kstrtoull(tmp + 1, 0, &end);
-	if (ret)
-		goto out;
-	ret = -EINVAL;
-	if (start > end)
-		goto out;
-	/* enable badblocks */
-	cmpxchg(&t_dev->badblocks.shift, -1, 0);
-	if (buf[0] == '+')
-		ret = badblocks_set(&t_dev->badblocks, start,
-			end - start + 1, 1);
-	else
-		ret = badblocks_clear(&t_dev->badblocks, start,
-			end - start + 1);
-	if (ret == 0)
-		ret = count;
-out:
-	kfree(orig);
-	return ret;
-}
-CONFIGFS_ATTR(nullb_device_, badblocks);
-
-static struct configfs_attribute *nullb_device_attrs[] = {
-	&nullb_device_attr_size,
-	&nullb_device_attr_completion_nsec,
-	&nullb_device_attr_submit_queues,
-	&nullb_device_attr_home_node,
-	&nullb_device_attr_queue_mode,
-	&nullb_device_attr_blocksize,
-	&nullb_device_attr_irqmode,
-	&nullb_device_attr_hw_queue_depth,
-	&nullb_device_attr_index,
-	&nullb_device_attr_blocking,
-	&nullb_device_attr_use_per_node_hctx,
-	&nullb_device_attr_power,
-	&nullb_device_attr_memory_backed,
-	&nullb_device_attr_discard,
-	&nullb_device_attr_mbps,
-	&nullb_device_attr_cache_size,
-	&nullb_device_attr_badblocks,
-	&nullb_device_attr_zoned,
-	&nullb_device_attr_zone_size,
-	NULL,
-};
-
-static void nullb_device_release(struct config_item *item)
-{
-	struct nullb_device *dev = to_nullb_device(item);
-
-	null_free_device_storage(dev, false);
-	null_free_dev(dev);
-}
-
-static struct configfs_item_operations nullb_device_ops = {
-	.release	= nullb_device_release,
-};
-
-static const struct config_item_type nullb_device_type = {
-	.ct_item_ops	= &nullb_device_ops,
-	.ct_attrs	= nullb_device_attrs,
-	.ct_owner	= THIS_MODULE,
-};
-
-static struct
-config_item *nullb_group_make_item(struct config_group *group, const char *name)
-{
-	struct nullb_device *dev;
-
-	dev = null_alloc_dev();
-	if (!dev)
-		return ERR_PTR(-ENOMEM);
-
-	config_item_init_type_name(&dev->item, name, &nullb_device_type);
-
-	return &dev->item;
-}
-
-static void
-nullb_group_drop_item(struct config_group *group, struct config_item *item)
-{
-	struct nullb_device *dev = to_nullb_device(item);
-
-	if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
-		mutex_lock(&lock);
-		dev->power = false;
-		null_del_dev(dev->nullb);
-		mutex_unlock(&lock);
-	}
-
-	config_item_put(item);
-}
-
-static ssize_t memb_group_features_show(struct config_item *item, char *page)
-{
-	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
-}
-
-CONFIGFS_ATTR_RO(memb_group_, features);
-
-static struct configfs_attribute *nullb_group_attrs[] = {
-	&memb_group_attr_features,
-	NULL,
-};
-
-static struct configfs_group_operations nullb_group_ops = {
-	.make_item	= nullb_group_make_item,
-	.drop_item	= nullb_group_drop_item,
-};
-
-static const struct config_item_type nullb_group_type = {
-	.ct_group_ops	= &nullb_group_ops,
-	.ct_attrs	= nullb_group_attrs,
-	.ct_owner	= THIS_MODULE,
-};
-
-static struct configfs_subsystem nullb_subsys = {
-	.su_group = {
-		.cg_item = {
-			.ci_namebuf = "nullb",
-			.ci_type = &nullb_group_type,
-		},
-	},
-};
-
-static inline int null_cache_active(struct nullb *nullb)
-{
-	return test_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
-}
-
-static struct nullb_device *null_alloc_dev(void)
-{
-	struct nullb_device *dev;
-
-	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return NULL;
-	INIT_RADIX_TREE(&dev->data, GFP_ATOMIC);
-	INIT_RADIX_TREE(&dev->cache, GFP_ATOMIC);
-	if (badblocks_init(&dev->badblocks, 0)) {
-		kfree(dev);
-		return NULL;
-	}
-
-	dev->size = g_gb * 1024;
-	dev->completion_nsec = g_completion_nsec;
-	dev->submit_queues = g_submit_queues;
-	dev->home_node = g_home_node;
-	dev->queue_mode = g_queue_mode;
-	dev->blocksize = g_bs;
-	dev->irqmode = g_irqmode;
-	dev->hw_queue_depth = g_hw_queue_depth;
-	dev->blocking = g_blocking;
-	dev->use_per_node_hctx = g_use_per_node_hctx;
-	dev->zoned = g_zoned;
-	dev->zone_size = g_zone_size;
-	return dev;
-}
-
-static void null_free_dev(struct nullb_device *dev)
-{
-	if (!dev)
-		return;
-
-	null_zone_exit(dev);
-	badblocks_exit(&dev->badblocks);
-	kfree(dev);
-}
-
-static void put_tag(struct nullb_queue *nq, unsigned int tag)
-{
-	clear_bit_unlock(tag, nq->tag_map);
-
-	if (waitqueue_active(&nq->wait))
-		wake_up(&nq->wait);
-}
-
-static unsigned int get_tag(struct nullb_queue *nq)
-{
-	unsigned int tag;
-
-	do {
-		tag = find_first_zero_bit(nq->tag_map, nq->queue_depth);
-		if (tag >= nq->queue_depth)
-			return -1U;
-	} while (test_and_set_bit_lock(tag, nq->tag_map));
-
-	return tag;
-}
-
-static void free_cmd(struct nullb_cmd *cmd)
-{
-	put_tag(cmd->nq, cmd->tag);
-}
-
-static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
-
-static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	unsigned int tag;
-
-	tag = get_tag(nq);
-	if (tag != -1U) {
-		cmd = &nq->cmds[tag];
-		cmd->tag = tag;
-		cmd->nq = nq;
-		if (nq->dev->irqmode == NULL_IRQ_TIMER) {
-			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
-				     HRTIMER_MODE_REL);
-			cmd->timer.function = null_cmd_timer_expired;
-		}
-		return cmd;
-	}
-
-	return NULL;
-}
-
-static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
-{
-	struct nullb_cmd *cmd;
-	DEFINE_WAIT(wait);
-
-	cmd = __alloc_cmd(nq);
-	if (cmd || !can_wait)
-		return cmd;
-
-	do {
-		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
-		cmd = __alloc_cmd(nq);
-		if (cmd)
-			break;
-
-		io_schedule();
-	} while (1);
-
-	finish_wait(&nq->wait, &wait);
-	return cmd;
-}
-
-static void end_cmd(struct nullb_cmd *cmd)
-{
-	struct request_queue *q = NULL;
-	int queue_mode = cmd->nq->dev->queue_mode;
-
-	if (cmd->rq)
-		q = cmd->rq->q;
-
-	switch (queue_mode)  {
-	case NULL_Q_MQ:
-		blk_mq_end_request(cmd->rq, cmd->error);
-		return;
-	case NULL_Q_RQ:
-		INIT_LIST_HEAD(&cmd->rq->queuelist);
-		blk_end_request_all(cmd->rq, cmd->error);
-		break;
-	case NULL_Q_BIO:
-		cmd->bio->bi_status = cmd->error;
-		bio_endio(cmd->bio);
-		break;
-	}
-
-	free_cmd(cmd);
-
-	/* Restart queue if needed, as we are freeing a tag */
-	if (queue_mode == NULL_Q_RQ && blk_queue_stopped(q)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_start_queue_async(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-	}
-}
-
-static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
-{
-	end_cmd(container_of(timer, struct nullb_cmd, timer));
-
-	return HRTIMER_NORESTART;
-}
-
-static void null_cmd_end_timer(struct nullb_cmd *cmd)
-{
-	ktime_t kt = cmd->nq->dev->completion_nsec;
-
-	hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
-}
-
-static void null_softirq_done_fn(struct request *rq)
-{
-	struct nullb *nullb = rq->q->queuedata;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		end_cmd(blk_mq_rq_to_pdu(rq));
-	else
-		end_cmd(rq->special);
-}
-
-static struct nullb_page *null_alloc_page(gfp_t gfp_flags)
-{
-	struct nullb_page *t_page;
-
-	t_page = kmalloc(sizeof(struct nullb_page), gfp_flags);
-	if (!t_page)
-		goto out;
-
-	t_page->page = alloc_pages(gfp_flags, 0);
-	if (!t_page->page)
-		goto out_freepage;
-
-	memset(t_page->bitmap, 0, sizeof(t_page->bitmap));
-	return t_page;
-out_freepage:
-	kfree(t_page);
-out:
-	return NULL;
-}
-
-static void null_free_page(struct nullb_page *t_page)
-{
-	__set_bit(NULLB_PAGE_FREE, t_page->bitmap);
-	if (test_bit(NULLB_PAGE_LOCK, t_page->bitmap))
-		return;
-	__free_page(t_page->page);
-	kfree(t_page);
-}
-
-static bool null_page_empty(struct nullb_page *page)
-{
-	int size = MAP_SZ - 2;
-
-	return find_first_bit(page->bitmap, size) == size;
-}
-
-static void null_free_sector(struct nullb *nullb, sector_t sector,
-	bool is_cache)
-{
-	unsigned int sector_bit;
-	u64 idx;
-	struct nullb_page *t_page, *ret;
-	struct radix_tree_root *root;
-
-	root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
-	idx = sector >> PAGE_SECTORS_SHIFT;
-	sector_bit = (sector & SECTOR_MASK);
-
-	t_page = radix_tree_lookup(root, idx);
-	if (t_page) {
-		__clear_bit(sector_bit, t_page->bitmap);
-
-		if (null_page_empty(t_page)) {
-			ret = radix_tree_delete_item(root, idx, t_page);
-			WARN_ON(ret != t_page);
-			null_free_page(ret);
-			if (is_cache)
-				nullb->dev->curr_cache -= PAGE_SIZE;
-		}
-	}
-}
-
-static struct nullb_page *null_radix_tree_insert(struct nullb *nullb, u64 idx,
-	struct nullb_page *t_page, bool is_cache)
-{
-	struct radix_tree_root *root;
-
-	root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
-
-	if (radix_tree_insert(root, idx, t_page)) {
-		null_free_page(t_page);
-		t_page = radix_tree_lookup(root, idx);
-		WARN_ON(!t_page || t_page->page->index != idx);
-	} else if (is_cache)
-		nullb->dev->curr_cache += PAGE_SIZE;
-
-	return t_page;
-}
-
-static void null_free_device_storage(struct nullb_device *dev, bool is_cache)
-{
-	unsigned long pos = 0;
-	int nr_pages;
-	struct nullb_page *ret, *t_pages[FREE_BATCH];
-	struct radix_tree_root *root;
-
-	root = is_cache ? &dev->cache : &dev->data;
-
-	do {
-		int i;
-
-		nr_pages = radix_tree_gang_lookup(root,
-				(void **)t_pages, pos, FREE_BATCH);
-
-		for (i = 0; i < nr_pages; i++) {
-			pos = t_pages[i]->page->index;
-			ret = radix_tree_delete_item(root, pos, t_pages[i]);
-			WARN_ON(ret != t_pages[i]);
-			null_free_page(ret);
-		}
-
-		pos++;
-	} while (nr_pages == FREE_BATCH);
-
-	if (is_cache)
-		dev->curr_cache = 0;
-}
-
-static struct nullb_page *__null_lookup_page(struct nullb *nullb,
-	sector_t sector, bool for_write, bool is_cache)
-{
-	unsigned int sector_bit;
-	u64 idx;
-	struct nullb_page *t_page;
-	struct radix_tree_root *root;
-
-	idx = sector >> PAGE_SECTORS_SHIFT;
-	sector_bit = (sector & SECTOR_MASK);
-
-	root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
-	t_page = radix_tree_lookup(root, idx);
-	WARN_ON(t_page && t_page->page->index != idx);
-
-	if (t_page && (for_write || test_bit(sector_bit, t_page->bitmap)))
-		return t_page;
-
-	return NULL;
-}
-
-static struct nullb_page *null_lookup_page(struct nullb *nullb,
-	sector_t sector, bool for_write, bool ignore_cache)
-{
-	struct nullb_page *page = NULL;
-
-	if (!ignore_cache)
-		page = __null_lookup_page(nullb, sector, for_write, true);
-	if (page)
-		return page;
-	return __null_lookup_page(nullb, sector, for_write, false);
-}
-
-static struct nullb_page *null_insert_page(struct nullb *nullb,
-	sector_t sector, bool ignore_cache)
-{
-	u64 idx;
-	struct nullb_page *t_page;
-
-	t_page = null_lookup_page(nullb, sector, true, ignore_cache);
-	if (t_page)
-		return t_page;
-
-	spin_unlock_irq(&nullb->lock);
-
-	t_page = null_alloc_page(GFP_NOIO);
-	if (!t_page)
-		goto out_lock;
-
-	if (radix_tree_preload(GFP_NOIO))
-		goto out_freepage;
-
-	spin_lock_irq(&nullb->lock);
-	idx = sector >> PAGE_SECTORS_SHIFT;
-	t_page->page->index = idx;
-	t_page = null_radix_tree_insert(nullb, idx, t_page, !ignore_cache);
-	radix_tree_preload_end();
-
-	return t_page;
-out_freepage:
-	null_free_page(t_page);
-out_lock:
-	spin_lock_irq(&nullb->lock);
-	return null_lookup_page(nullb, sector, true, ignore_cache);
-}
-
-static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page)
-{
-	int i;
-	unsigned int offset;
-	u64 idx;
-	struct nullb_page *t_page, *ret;
-	void *dst, *src;
-
-	idx = c_page->page->index;
-
-	t_page = null_insert_page(nullb, idx << PAGE_SECTORS_SHIFT, true);
-
-	__clear_bit(NULLB_PAGE_LOCK, c_page->bitmap);
-	if (test_bit(NULLB_PAGE_FREE, c_page->bitmap)) {
-		null_free_page(c_page);
-		if (t_page && null_page_empty(t_page)) {
-			ret = radix_tree_delete_item(&nullb->dev->data,
-				idx, t_page);
-			null_free_page(t_page);
-		}
-		return 0;
-	}
-
-	if (!t_page)
-		return -ENOMEM;
-
-	src = kmap_atomic(c_page->page);
-	dst = kmap_atomic(t_page->page);
-
-	for (i = 0; i < PAGE_SECTORS;
-			i += (nullb->dev->blocksize >> SECTOR_SHIFT)) {
-		if (test_bit(i, c_page->bitmap)) {
-			offset = (i << SECTOR_SHIFT);
-			memcpy(dst + offset, src + offset,
-				nullb->dev->blocksize);
-			__set_bit(i, t_page->bitmap);
-		}
-	}
-
-	kunmap_atomic(dst);
-	kunmap_atomic(src);
-
-	ret = radix_tree_delete_item(&nullb->dev->cache, idx, c_page);
-	null_free_page(ret);
-	nullb->dev->curr_cache -= PAGE_SIZE;
-
-	return 0;
-}
-
-static int null_make_cache_space(struct nullb *nullb, unsigned long n)
-{
-	int i, err, nr_pages;
-	struct nullb_page *c_pages[FREE_BATCH];
-	unsigned long flushed = 0, one_round;
-
-again:
-	if ((nullb->dev->cache_size * 1024 * 1024) >
-	     nullb->dev->curr_cache + n || nullb->dev->curr_cache == 0)
-		return 0;
-
-	nr_pages = radix_tree_gang_lookup(&nullb->dev->cache,
-			(void **)c_pages, nullb->cache_flush_pos, FREE_BATCH);
-	/*
-	 * nullb_flush_cache_page could unlock before using the c_pages. To
-	 * avoid race, we don't allow page free
-	 */
-	for (i = 0; i < nr_pages; i++) {
-		nullb->cache_flush_pos = c_pages[i]->page->index;
-		/*
-		 * We found the page which is being flushed to disk by other
-		 * threads
-		 */
-		if (test_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap))
-			c_pages[i] = NULL;
-		else
-			__set_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap);
-	}
-
-	one_round = 0;
-	for (i = 0; i < nr_pages; i++) {
-		if (c_pages[i] == NULL)
-			continue;
-		err = null_flush_cache_page(nullb, c_pages[i]);
-		if (err)
-			return err;
-		one_round++;
-	}
-	flushed += one_round << PAGE_SHIFT;
-
-	if (n > flushed) {
-		if (nr_pages == 0)
-			nullb->cache_flush_pos = 0;
-		if (one_round == 0) {
-			/* give other threads a chance */
-			spin_unlock_irq(&nullb->lock);
-			spin_lock_irq(&nullb->lock);
-		}
-		goto again;
-	}
-	return 0;
-}
-
-static int copy_to_nullb(struct nullb *nullb, struct page *source,
-	unsigned int off, sector_t sector, size_t n, bool is_fua)
-{
-	size_t temp, count = 0;
-	unsigned int offset;
-	struct nullb_page *t_page;
-	void *dst, *src;
-
-	while (count < n) {
-		temp = min_t(size_t, nullb->dev->blocksize, n - count);
-
-		if (null_cache_active(nullb) && !is_fua)
-			null_make_cache_space(nullb, PAGE_SIZE);
-
-		offset = (sector & SECTOR_MASK) << SECTOR_SHIFT;
-		t_page = null_insert_page(nullb, sector,
-			!null_cache_active(nullb) || is_fua);
-		if (!t_page)
-			return -ENOSPC;
-
-		src = kmap_atomic(source);
-		dst = kmap_atomic(t_page->page);
-		memcpy(dst + offset, src + off + count, temp);
-		kunmap_atomic(dst);
-		kunmap_atomic(src);
-
-		__set_bit(sector & SECTOR_MASK, t_page->bitmap);
-
-		if (is_fua)
-			null_free_sector(nullb, sector, true);
-
-		count += temp;
-		sector += temp >> SECTOR_SHIFT;
-	}
-	return 0;
-}
-
-static int copy_from_nullb(struct nullb *nullb, struct page *dest,
-	unsigned int off, sector_t sector, size_t n)
-{
-	size_t temp, count = 0;
-	unsigned int offset;
-	struct nullb_page *t_page;
-	void *dst, *src;
-
-	while (count < n) {
-		temp = min_t(size_t, nullb->dev->blocksize, n - count);
-
-		offset = (sector & SECTOR_MASK) << SECTOR_SHIFT;
-		t_page = null_lookup_page(nullb, sector, false,
-			!null_cache_active(nullb));
-
-		dst = kmap_atomic(dest);
-		if (!t_page) {
-			memset(dst + off + count, 0, temp);
-			goto next;
-		}
-		src = kmap_atomic(t_page->page);
-		memcpy(dst + off + count, src + offset, temp);
-		kunmap_atomic(src);
-next:
-		kunmap_atomic(dst);
-
-		count += temp;
-		sector += temp >> SECTOR_SHIFT;
-	}
-	return 0;
-}
-
-static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n)
-{
-	size_t temp;
-
-	spin_lock_irq(&nullb->lock);
-	while (n > 0) {
-		temp = min_t(size_t, n, nullb->dev->blocksize);
-		null_free_sector(nullb, sector, false);
-		if (null_cache_active(nullb))
-			null_free_sector(nullb, sector, true);
-		sector += temp >> SECTOR_SHIFT;
-		n -= temp;
-	}
-	spin_unlock_irq(&nullb->lock);
-}
-
-static int null_handle_flush(struct nullb *nullb)
-{
-	int err;
-
-	if (!null_cache_active(nullb))
-		return 0;
-
-	spin_lock_irq(&nullb->lock);
-	while (true) {
-		err = null_make_cache_space(nullb,
-			nullb->dev->cache_size * 1024 * 1024);
-		if (err || nullb->dev->curr_cache == 0)
-			break;
-	}
-
-	WARN_ON(!radix_tree_empty(&nullb->dev->cache));
-	spin_unlock_irq(&nullb->lock);
-	return err;
-}
-
-static int null_transfer(struct nullb *nullb, struct page *page,
-	unsigned int len, unsigned int off, bool is_write, sector_t sector,
-	bool is_fua)
-{
-	int err = 0;
-
-	if (!is_write) {
-		err = copy_from_nullb(nullb, page, off, sector, len);
-		flush_dcache_page(page);
-	} else {
-		flush_dcache_page(page);
-		err = copy_to_nullb(nullb, page, off, sector, len, is_fua);
-	}
-
-	return err;
-}
-
-static int null_handle_rq(struct nullb_cmd *cmd)
-{
-	struct request *rq = cmd->rq;
-	struct nullb *nullb = cmd->nq->dev->nullb;
-	int err;
-	unsigned int len;
-	sector_t sector;
-	struct req_iterator iter;
-	struct bio_vec bvec;
-
-	sector = blk_rq_pos(rq);
-
-	if (req_op(rq) == REQ_OP_DISCARD) {
-		null_handle_discard(nullb, sector, blk_rq_bytes(rq));
-		return 0;
-	}
-
-	spin_lock_irq(&nullb->lock);
-	rq_for_each_segment(bvec, rq, iter) {
-		len = bvec.bv_len;
-		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
-				     op_is_write(req_op(rq)), sector,
-				     req_op(rq) & REQ_FUA);
-		if (err) {
-			spin_unlock_irq(&nullb->lock);
-			return err;
-		}
-		sector += len >> SECTOR_SHIFT;
-	}
-	spin_unlock_irq(&nullb->lock);
-
-	return 0;
-}
-
-static int null_handle_bio(struct nullb_cmd *cmd)
-{
-	struct bio *bio = cmd->bio;
-	struct nullb *nullb = cmd->nq->dev->nullb;
-	int err;
-	unsigned int len;
-	sector_t sector;
-	struct bio_vec bvec;
-	struct bvec_iter iter;
-
-	sector = bio->bi_iter.bi_sector;
-
-	if (bio_op(bio) == REQ_OP_DISCARD) {
-		null_handle_discard(nullb, sector,
-			bio_sectors(bio) << SECTOR_SHIFT);
-		return 0;
-	}
-
-	spin_lock_irq(&nullb->lock);
-	bio_for_each_segment(bvec, bio, iter) {
-		len = bvec.bv_len;
-		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
-				     op_is_write(bio_op(bio)), sector,
-				     bio_op(bio) & REQ_FUA);
-		if (err) {
-			spin_unlock_irq(&nullb->lock);
-			return err;
-		}
-		sector += len >> SECTOR_SHIFT;
-	}
-	spin_unlock_irq(&nullb->lock);
-	return 0;
-}
-
-static void null_stop_queue(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_stop_hw_queues(q);
-	else {
-		spin_lock_irq(q->queue_lock);
-		blk_stop_queue(q);
-		spin_unlock_irq(q->queue_lock);
-	}
-}
-
-static void null_restart_queue_async(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-	unsigned long flags;
-
-	if (nullb->dev->queue_mode == NULL_Q_MQ)
-		blk_mq_start_stopped_hw_queues(q, true);
-	else {
-		spin_lock_irqsave(q->queue_lock, flags);
-		blk_start_queue_async(q);
-		spin_unlock_irqrestore(q->queue_lock, flags);
-	}
-}
-
-static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
-{
-	struct nullb_device *dev = cmd->nq->dev;
-	struct nullb *nullb = dev->nullb;
-	int err = 0;
-
-	if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
-		cmd->error = null_zone_report(nullb, cmd);
-		goto out;
-	}
-
-	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
-		struct request *rq = cmd->rq;
-
-		if (!hrtimer_active(&nullb->bw_timer))
-			hrtimer_restart(&nullb->bw_timer);
-
-		if (atomic_long_sub_return(blk_rq_bytes(rq),
-				&nullb->cur_bytes) < 0) {
-			null_stop_queue(nullb);
-			/* race with timer */
-			if (atomic_long_read(&nullb->cur_bytes) > 0)
-				null_restart_queue_async(nullb);
-			if (dev->queue_mode == NULL_Q_RQ) {
-				struct request_queue *q = nullb->q;
-
-				spin_lock_irq(q->queue_lock);
-				rq->rq_flags |= RQF_DONTPREP;
-				blk_requeue_request(q, rq);
-				spin_unlock_irq(q->queue_lock);
-				return BLK_STS_OK;
-			} else
-				/* requeue request */
-				return BLK_STS_DEV_RESOURCE;
-		}
-	}
-
-	if (nullb->dev->badblocks.shift != -1) {
-		int bad_sectors;
-		sector_t sector, size, first_bad;
-		bool is_flush = true;
-
-		if (dev->queue_mode == NULL_Q_BIO &&
-				bio_op(cmd->bio) != REQ_OP_FLUSH) {
-			is_flush = false;
-			sector = cmd->bio->bi_iter.bi_sector;
-			size = bio_sectors(cmd->bio);
-		}
-		if (dev->queue_mode != NULL_Q_BIO &&
-				req_op(cmd->rq) != REQ_OP_FLUSH) {
-			is_flush = false;
-			sector = blk_rq_pos(cmd->rq);
-			size = blk_rq_sectors(cmd->rq);
-		}
-		if (!is_flush && badblocks_check(&nullb->dev->badblocks, sector,
-				size, &first_bad, &bad_sectors)) {
-			cmd->error = BLK_STS_IOERR;
-			goto out;
-		}
-	}
-
-	if (dev->memory_backed) {
-		if (dev->queue_mode == NULL_Q_BIO) {
-			if (bio_op(cmd->bio) == REQ_OP_FLUSH)
-				err = null_handle_flush(nullb);
-			else
-				err = null_handle_bio(cmd);
-		} else {
-			if (req_op(cmd->rq) == REQ_OP_FLUSH)
-				err = null_handle_flush(nullb);
-			else
-				err = null_handle_rq(cmd);
-		}
-	}
-	cmd->error = errno_to_blk_status(err);
-
-	if (!cmd->error && dev->zoned) {
-		if (req_op(cmd->rq) == REQ_OP_WRITE)
-			null_zone_write(cmd);
-		else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET)
-			null_zone_reset(cmd);
-	}
-out:
-	/* Complete IO by inline, softirq or timer */
-	switch (dev->irqmode) {
-	case NULL_IRQ_SOFTIRQ:
-		switch (dev->queue_mode)  {
-		case NULL_Q_MQ:
-			blk_mq_complete_request(cmd->rq);
-			break;
-		case NULL_Q_RQ:
-			blk_complete_request(cmd->rq);
-			break;
-		case NULL_Q_BIO:
-			/*
-			 * XXX: no proper submitting cpu information available.
-			 */
-			end_cmd(cmd);
-			break;
-		}
-		break;
-	case NULL_IRQ_NONE:
-		end_cmd(cmd);
-		break;
-	case NULL_IRQ_TIMER:
-		null_cmd_end_timer(cmd);
-		break;
-	}
-	return BLK_STS_OK;
-}
-
-static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer)
-{
-	struct nullb *nullb = container_of(timer, struct nullb, bw_timer);
-	ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL);
-	unsigned int mbps = nullb->dev->mbps;
-
-	if (atomic_long_read(&nullb->cur_bytes) == mb_per_tick(mbps))
-		return HRTIMER_NORESTART;
-
-	atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps));
-	null_restart_queue_async(nullb);
-
-	hrtimer_forward_now(&nullb->bw_timer, timer_interval);
-
-	return HRTIMER_RESTART;
-}
-
-static void nullb_setup_bwtimer(struct nullb *nullb)
-{
-	ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL);
-
-	hrtimer_init(&nullb->bw_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	nullb->bw_timer.function = nullb_bwtimer_fn;
-	atomic_long_set(&nullb->cur_bytes, mb_per_tick(nullb->dev->mbps));
-	hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL);
-}
-
-static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
-{
-	int index = 0;
-
-	if (nullb->nr_queues != 1)
-		index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues);
-
-	return &nullb->queues[index];
-}
-
-static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
-{
-	struct nullb *nullb = q->queuedata;
-	struct nullb_queue *nq = nullb_to_queue(nullb);
-	struct nullb_cmd *cmd;
-
-	cmd = alloc_cmd(nq, 1);
-	cmd->bio = bio;
-
-	null_handle_cmd(cmd);
-	return BLK_QC_T_NONE;
-}
-
-static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
-{
-	pr_info("null: rq %p timed out\n", rq);
-	__blk_complete_request(rq);
-	return BLK_EH_DONE;
-}
-
-static int null_rq_prep_fn(struct request_queue *q, struct request *req)
-{
-	struct nullb *nullb = q->queuedata;
-	struct nullb_queue *nq = nullb_to_queue(nullb);
-	struct nullb_cmd *cmd;
-
-	cmd = alloc_cmd(nq, 0);
-	if (cmd) {
-		cmd->rq = req;
-		req->special = cmd;
-		return BLKPREP_OK;
-	}
-	blk_stop_queue(q);
-
-	return BLKPREP_DEFER;
-}
-
-static bool should_timeout_request(struct request *rq)
-{
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-	if (g_timeout_str[0])
-		return should_fail(&null_timeout_attr, 1);
-#endif
-	return false;
-}
-
-static bool should_requeue_request(struct request *rq)
-{
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-	if (g_requeue_str[0])
-		return should_fail(&null_requeue_attr, 1);
-#endif
-	return false;
-}
-
-static void null_request_fn(struct request_queue *q)
-{
-	struct request *rq;
-
-	while ((rq = blk_fetch_request(q)) != NULL) {
-		struct nullb_cmd *cmd = rq->special;
-
-		/* just ignore the request */
-		if (should_timeout_request(rq))
-			continue;
-		if (should_requeue_request(rq)) {
-			blk_requeue_request(q, rq);
-			continue;
-		}
-
-		spin_unlock_irq(q->queue_lock);
-		null_handle_cmd(cmd);
-		spin_lock_irq(q->queue_lock);
-	}
-}
-
-static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
-{
-	pr_info("null: rq %p timed out\n", rq);
-	blk_mq_complete_request(rq);
-	return BLK_EH_DONE;
-}
-
-static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
-			 const struct blk_mq_queue_data *bd)
-{
-	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
-	struct nullb_queue *nq = hctx->driver_data;
-
-	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
-
-	if (nq->dev->irqmode == NULL_IRQ_TIMER) {
-		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-		cmd->timer.function = null_cmd_timer_expired;
-	}
-	cmd->rq = bd->rq;
-	cmd->nq = nq;
-
-	blk_mq_start_request(bd->rq);
-
-	if (should_requeue_request(bd->rq)) {
-		/*
-		 * Alternate between hitting the core BUSY path, and the
-		 * driver driven requeue path
-		 */
-		nq->requeue_selection++;
-		if (nq->requeue_selection & 1)
-			return BLK_STS_RESOURCE;
-		else {
-			blk_mq_requeue_request(bd->rq, true);
-			return BLK_STS_OK;
-		}
-	}
-	if (should_timeout_request(bd->rq))
-		return BLK_STS_OK;
-
-	return null_handle_cmd(cmd);
-}
-
-static const struct blk_mq_ops null_mq_ops = {
-	.queue_rq       = null_queue_rq,
-	.complete	= null_softirq_done_fn,
-	.timeout	= null_timeout_rq,
-};
-
-static void cleanup_queue(struct nullb_queue *nq)
-{
-	kfree(nq->tag_map);
-	kfree(nq->cmds);
-}
-
-static void cleanup_queues(struct nullb *nullb)
-{
-	int i;
-
-	for (i = 0; i < nullb->nr_queues; i++)
-		cleanup_queue(&nullb->queues[i]);
-
-	kfree(nullb->queues);
-}
-
-static void null_del_dev(struct nullb *nullb)
-{
-	struct nullb_device *dev = nullb->dev;
-
-	ida_simple_remove(&nullb_indexes, nullb->index);
-
-	list_del_init(&nullb->list);
-
-	del_gendisk(nullb->disk);
-
-	if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) {
-		hrtimer_cancel(&nullb->bw_timer);
-		atomic_long_set(&nullb->cur_bytes, LONG_MAX);
-		null_restart_queue_async(nullb);
-	}
-
-	blk_cleanup_queue(nullb->q);
-	if (dev->queue_mode == NULL_Q_MQ &&
-	    nullb->tag_set == &nullb->__tag_set)
-		blk_mq_free_tag_set(nullb->tag_set);
-	put_disk(nullb->disk);
-	cleanup_queues(nullb);
-	if (null_cache_active(nullb))
-		null_free_device_storage(nullb->dev, true);
-	kfree(nullb);
-	dev->nullb = NULL;
-}
-
-static void null_config_discard(struct nullb *nullb)
-{
-	if (nullb->dev->discard == false)
-		return;
-	nullb->q->limits.discard_granularity = nullb->dev->blocksize;
-	nullb->q->limits.discard_alignment = nullb->dev->blocksize;
-	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
-	blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q);
-}
-
-static int null_open(struct block_device *bdev, fmode_t mode)
-{
-	return 0;
-}
-
-static void null_release(struct gendisk *disk, fmode_t mode)
-{
-}
-
-static const struct block_device_operations null_fops = {
-	.owner =	THIS_MODULE,
-	.open =		null_open,
-	.release =	null_release,
-};
-
-static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
-{
-	BUG_ON(!nullb);
-	BUG_ON(!nq);
-
-	init_waitqueue_head(&nq->wait);
-	nq->queue_depth = nullb->queue_depth;
-	nq->dev = nullb->dev;
-}
-
-static void null_init_queues(struct nullb *nullb)
-{
-	struct request_queue *q = nullb->q;
-	struct blk_mq_hw_ctx *hctx;
-	struct nullb_queue *nq;
-	int i;
-
-	queue_for_each_hw_ctx(q, hctx, i) {
-		if (!hctx->nr_ctx || !hctx->tags)
-			continue;
-		nq = &nullb->queues[i];
-		hctx->driver_data = nq;
-		null_init_queue(nullb, nq);
-		nullb->nr_queues++;
-	}
-}
-
-static int setup_commands(struct nullb_queue *nq)
-{
-	struct nullb_cmd *cmd;
-	int i, tag_size;
-
-	nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL);
-	if (!nq->cmds)
-		return -ENOMEM;
-
-	tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG;
-	nq->tag_map = kcalloc(tag_size, sizeof(unsigned long), GFP_KERNEL);
-	if (!nq->tag_map) {
-		kfree(nq->cmds);
-		return -ENOMEM;
-	}
-
-	for (i = 0; i < nq->queue_depth; i++) {
-		cmd = &nq->cmds[i];
-		INIT_LIST_HEAD(&cmd->list);
-		cmd->ll_list.next = NULL;
-		cmd->tag = -1U;
-	}
-
-	return 0;
-}
-
-static int setup_queues(struct nullb *nullb)
-{
-	nullb->queues = kcalloc(nullb->dev->submit_queues,
-				sizeof(struct nullb_queue),
-				GFP_KERNEL);
-	if (!nullb->queues)
-		return -ENOMEM;
-
-	nullb->nr_queues = 0;
-	nullb->queue_depth = nullb->dev->hw_queue_depth;
-
-	return 0;
-}
-
-static int init_driver_queues(struct nullb *nullb)
-{
-	struct nullb_queue *nq;
-	int i, ret = 0;
-
-	for (i = 0; i < nullb->dev->submit_queues; i++) {
-		nq = &nullb->queues[i];
-
-		null_init_queue(nullb, nq);
-
-		ret = setup_commands(nq);
-		if (ret)
-			return ret;
-		nullb->nr_queues++;
-	}
-	return 0;
-}
-
-static int null_gendisk_register(struct nullb *nullb)
-{
-	struct gendisk *disk;
-	sector_t size;
-
-	disk = nullb->disk = alloc_disk_node(1, nullb->dev->home_node);
-	if (!disk)
-		return -ENOMEM;
-	size = (sector_t)nullb->dev->size * 1024 * 1024ULL;
-	set_capacity(disk, size >> 9);
-
-	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
-	disk->major		= null_major;
-	disk->first_minor	= nullb->index;
-	disk->fops		= &null_fops;
-	disk->private_data	= nullb;
-	disk->queue		= nullb->q;
-	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
-
-	add_disk(disk);
-	return 0;
-}
-
-static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
-{
-	set->ops = &null_mq_ops;
-	set->nr_hw_queues = nullb ? nullb->dev->submit_queues :
-						g_submit_queues;
-	set->queue_depth = nullb ? nullb->dev->hw_queue_depth :
-						g_hw_queue_depth;
-	set->numa_node = nullb ? nullb->dev->home_node : g_home_node;
-	set->cmd_size	= sizeof(struct nullb_cmd);
-	set->flags = BLK_MQ_F_SHOULD_MERGE;
-	if (g_no_sched)
-		set->flags |= BLK_MQ_F_NO_SCHED;
-	set->driver_data = NULL;
-
-	if ((nullb && nullb->dev->blocking) || g_blocking)
-		set->flags |= BLK_MQ_F_BLOCKING;
-
-	return blk_mq_alloc_tag_set(set);
-}
-
-static void null_validate_conf(struct nullb_device *dev)
-{
-	dev->blocksize = round_down(dev->blocksize, 512);
-	dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096);
-
-	if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) {
-		if (dev->submit_queues != nr_online_nodes)
-			dev->submit_queues = nr_online_nodes;
-	} else if (dev->submit_queues > nr_cpu_ids)
-		dev->submit_queues = nr_cpu_ids;
-	else if (dev->submit_queues == 0)
-		dev->submit_queues = 1;
-
-	dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ);
-	dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER);
-
-	/* Do memory allocation, so set blocking */
-	if (dev->memory_backed)
-		dev->blocking = true;
-	else /* cache is meaningless */
-		dev->cache_size = 0;
-	dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024,
-						dev->cache_size);
-	dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps);
-	/* can not stop a queue */
-	if (dev->queue_mode == NULL_Q_BIO)
-		dev->mbps = 0;
-}
-
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-static bool __null_setup_fault(struct fault_attr *attr, char *str)
-{
-	if (!str[0])
-		return true;
-
-	if (!setup_fault_attr(attr, str))
-		return false;
-
-	attr->verbose = 0;
-	return true;
-}
-#endif
-
-static bool null_setup_fault(void)
-{
-#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
-	if (!__null_setup_fault(&null_timeout_attr, g_timeout_str))
-		return false;
-	if (!__null_setup_fault(&null_requeue_attr, g_requeue_str))
-		return false;
-#endif
-	return true;
-}
-
-static int null_add_dev(struct nullb_device *dev)
-{
-	struct nullb *nullb;
-	int rv;
-
-	null_validate_conf(dev);
-
-	nullb = kzalloc_node(sizeof(*nullb), GFP_KERNEL, dev->home_node);
-	if (!nullb) {
-		rv = -ENOMEM;
-		goto out;
-	}
-	nullb->dev = dev;
-	dev->nullb = nullb;
-
-	spin_lock_init(&nullb->lock);
-
-	rv = setup_queues(nullb);
-	if (rv)
-		goto out_free_nullb;
-
-	if (dev->queue_mode == NULL_Q_MQ) {
-		if (shared_tags) {
-			nullb->tag_set = &tag_set;
-			rv = 0;
-		} else {
-			nullb->tag_set = &nullb->__tag_set;
-			rv = null_init_tag_set(nullb, nullb->tag_set);
-		}
-
-		if (rv)
-			goto out_cleanup_queues;
-
-		if (!null_setup_fault())
-			goto out_cleanup_queues;
-
-		nullb->tag_set->timeout = 5 * HZ;
-		nullb->q = blk_mq_init_queue(nullb->tag_set);
-		if (IS_ERR(nullb->q)) {
-			rv = -ENOMEM;
-			goto out_cleanup_tags;
-		}
-		null_init_queues(nullb);
-	} else if (dev->queue_mode == NULL_Q_BIO) {
-		nullb->q = blk_alloc_queue_node(GFP_KERNEL, dev->home_node,
-						NULL);
-		if (!nullb->q) {
-			rv = -ENOMEM;
-			goto out_cleanup_queues;
-		}
-		blk_queue_make_request(nullb->q, null_queue_bio);
-		rv = init_driver_queues(nullb);
-		if (rv)
-			goto out_cleanup_blk_queue;
-	} else {
-		nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock,
-						dev->home_node);
-		if (!nullb->q) {
-			rv = -ENOMEM;
-			goto out_cleanup_queues;
-		}
-
-		if (!null_setup_fault())
-			goto out_cleanup_blk_queue;
-
-		blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
-		blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
-		blk_queue_rq_timed_out(nullb->q, null_rq_timed_out_fn);
-		nullb->q->rq_timeout = 5 * HZ;
-		rv = init_driver_queues(nullb);
-		if (rv)
-			goto out_cleanup_blk_queue;
-	}
-
-	if (dev->mbps) {
-		set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags);
-		nullb_setup_bwtimer(nullb);
-	}
-
-	if (dev->cache_size > 0) {
-		set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
-		blk_queue_write_cache(nullb->q, true, true);
-		blk_queue_flush_queueable(nullb->q, true);
-	}
-
-	if (dev->zoned) {
-		rv = null_zone_init(dev);
-		if (rv)
-			goto out_cleanup_blk_queue;
-
-		blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
-		nullb->q->limits.zoned = BLK_ZONED_HM;
-	}
-
-	nullb->q->queuedata = nullb;
-	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
-	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
-
-	mutex_lock(&lock);
-	nullb->index = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
-	dev->index = nullb->index;
-	mutex_unlock(&lock);
-
-	blk_queue_logical_block_size(nullb->q, dev->blocksize);
-	blk_queue_physical_block_size(nullb->q, dev->blocksize);
-
-	null_config_discard(nullb);
-
-	sprintf(nullb->disk_name, "nullb%d", nullb->index);
-
-	rv = null_gendisk_register(nullb);
-	if (rv)
-		goto out_cleanup_zone;
-
-	mutex_lock(&lock);
-	list_add_tail(&nullb->list, &nullb_list);
-	mutex_unlock(&lock);
-
-	return 0;
-out_cleanup_zone:
-	if (dev->zoned)
-		null_zone_exit(dev);
-out_cleanup_blk_queue:
-	blk_cleanup_queue(nullb->q);
-out_cleanup_tags:
-	if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
-		blk_mq_free_tag_set(nullb->tag_set);
-out_cleanup_queues:
-	cleanup_queues(nullb);
-out_free_nullb:
-	kfree(nullb);
-out:
-	return rv;
-}
-
-static int __init null_init(void)
-{
-	int ret = 0;
-	unsigned int i;
-	struct nullb *nullb;
-	struct nullb_device *dev;
-
-	if (g_bs > PAGE_SIZE) {
-		pr_warn("null_blk: invalid block size\n");
-		pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE);
-		g_bs = PAGE_SIZE;
-	}
-
-	if (!is_power_of_2(g_zone_size)) {
-		pr_err("null_blk: zone_size must be power-of-two\n");
-		return -EINVAL;
-	}
-
-	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
-		if (g_submit_queues != nr_online_nodes) {
-			pr_warn("null_blk: submit_queues param is set to %u.\n",
-							nr_online_nodes);
-			g_submit_queues = nr_online_nodes;
-		}
-	} else if (g_submit_queues > nr_cpu_ids)
-		g_submit_queues = nr_cpu_ids;
-	else if (g_submit_queues <= 0)
-		g_submit_queues = 1;
-
-	if (g_queue_mode == NULL_Q_MQ && shared_tags) {
-		ret = null_init_tag_set(NULL, &tag_set);
-		if (ret)
-			return ret;
-	}
-
-	config_group_init(&nullb_subsys.su_group);
-	mutex_init(&nullb_subsys.su_mutex);
-
-	ret = configfs_register_subsystem(&nullb_subsys);
-	if (ret)
-		goto err_tagset;
-
-	mutex_init(&lock);
-
-	null_major = register_blkdev(0, "nullb");
-	if (null_major < 0) {
-		ret = null_major;
-		goto err_conf;
-	}
-
-	for (i = 0; i < nr_devices; i++) {
-		dev = null_alloc_dev();
-		if (!dev) {
-			ret = -ENOMEM;
-			goto err_dev;
-		}
-		ret = null_add_dev(dev);
-		if (ret) {
-			null_free_dev(dev);
-			goto err_dev;
-		}
-	}
-
-	pr_info("null: module loaded\n");
-	return 0;
-
-err_dev:
-	while (!list_empty(&nullb_list)) {
-		nullb = list_entry(nullb_list.next, struct nullb, list);
-		dev = nullb->dev;
-		null_del_dev(nullb);
-		null_free_dev(dev);
-	}
-	unregister_blkdev(null_major, "nullb");
-err_conf:
-	configfs_unregister_subsystem(&nullb_subsys);
-err_tagset:
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
-		blk_mq_free_tag_set(&tag_set);
-	return ret;
-}
-
-static void __exit null_exit(void)
-{
-	struct nullb *nullb;
-
-	configfs_unregister_subsystem(&nullb_subsys);
-
-	unregister_blkdev(null_major, "nullb");
-
-	mutex_lock(&lock);
-	while (!list_empty(&nullb_list)) {
-		struct nullb_device *dev;
-
-		nullb = list_entry(nullb_list.next, struct nullb, list);
-		dev = nullb->dev;
-		null_del_dev(nullb);
-		null_free_dev(dev);
-	}
-	mutex_unlock(&lock);
-
-	if (g_queue_mode == NULL_Q_MQ && shared_tags)
-		blk_mq_free_tag_set(&tag_set);
-}
-
-module_init(null_init);
-module_exit(null_exit);
-
-MODULE_AUTHOR("Jens Axboe <axboe@kernel.dk>");
-MODULE_LICENSE("GPL");
diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
new file mode 100644
index 000000000000..86cafa6d3b41
--- /dev/null
+++ b/drivers/block/null_blk_main.c
@@ -0,0 +1,1926 @@
+/*
+ * Add configfs and memory store: Kyungchan Koh <kkc6196@fb.com> and
+ * Shaohua Li <shli@fb.com>
+ */
+#include <linux/module.h>
+
+#include <linux/moduleparam.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/init.h>
+#include "null_blk.h"
+
+#define PAGE_SECTORS_SHIFT	(PAGE_SHIFT - SECTOR_SHIFT)
+#define PAGE_SECTORS		(1 << PAGE_SECTORS_SHIFT)
+#define SECTOR_MASK		(PAGE_SECTORS - 1)
+
+#define FREE_BATCH		16
+
+#define TICKS_PER_SEC		50ULL
+#define TIMER_INTERVAL		(NSEC_PER_SEC / TICKS_PER_SEC)
+
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+static DECLARE_FAULT_ATTR(null_timeout_attr);
+static DECLARE_FAULT_ATTR(null_requeue_attr);
+#endif
+
+static inline u64 mb_per_tick(int mbps)
+{
+	return (1 << 20) / TICKS_PER_SEC * ((u64) mbps);
+}
+
+/*
+ * Status flags for nullb_device.
+ *
+ * CONFIGURED:	Device has been configured and turned on. Cannot reconfigure.
+ * UP:		Device is currently on and visible in userspace.
+ * THROTTLED:	Device is being throttled.
+ * CACHE:	Device is using a write-back cache.
+ */
+enum nullb_device_flags {
+	NULLB_DEV_FL_CONFIGURED	= 0,
+	NULLB_DEV_FL_UP		= 1,
+	NULLB_DEV_FL_THROTTLED	= 2,
+	NULLB_DEV_FL_CACHE	= 3,
+};
+
+#define MAP_SZ		((PAGE_SIZE >> SECTOR_SHIFT) + 2)
+/*
+ * nullb_page is a page in memory for nullb devices.
+ *
+ * @page:	The page holding the data.
+ * @bitmap:	The bitmap represents which sector in the page has data.
+ *		Each bit represents one block size. For example, sector 8
+ *		will use the 7th bit
+ * The highest 2 bits of bitmap are for special purpose. LOCK means the cache
+ * page is being flushing to storage. FREE means the cache page is freed and
+ * should be skipped from flushing to storage. Please see
+ * null_make_cache_space
+ */
+struct nullb_page {
+	struct page *page;
+	DECLARE_BITMAP(bitmap, MAP_SZ);
+};
+#define NULLB_PAGE_LOCK (MAP_SZ - 1)
+#define NULLB_PAGE_FREE (MAP_SZ - 2)
+
+static LIST_HEAD(nullb_list);
+static struct mutex lock;
+static int null_major;
+static DEFINE_IDA(nullb_indexes);
+static struct blk_mq_tag_set tag_set;
+
+enum {
+	NULL_IRQ_NONE		= 0,
+	NULL_IRQ_SOFTIRQ	= 1,
+	NULL_IRQ_TIMER		= 2,
+};
+
+enum {
+	NULL_Q_BIO		= 0,
+	NULL_Q_RQ		= 1,
+	NULL_Q_MQ		= 2,
+};
+
+static int g_no_sched;
+module_param_named(no_sched, g_no_sched, int, 0444);
+MODULE_PARM_DESC(no_sched, "No io scheduler");
+
+static int g_submit_queues = 1;
+module_param_named(submit_queues, g_submit_queues, int, 0444);
+MODULE_PARM_DESC(submit_queues, "Number of submission queues");
+
+static int g_home_node = NUMA_NO_NODE;
+module_param_named(home_node, g_home_node, int, 0444);
+MODULE_PARM_DESC(home_node, "Home node for the device");
+
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+static char g_timeout_str[80];
+module_param_string(timeout, g_timeout_str, sizeof(g_timeout_str), 0444);
+
+static char g_requeue_str[80];
+module_param_string(requeue, g_requeue_str, sizeof(g_requeue_str), 0444);
+#endif
+
+static int g_queue_mode = NULL_Q_MQ;
+
+static int null_param_store_val(const char *str, int *val, int min, int max)
+{
+	int ret, new_val;
+
+	ret = kstrtoint(str, 10, &new_val);
+	if (ret)
+		return -EINVAL;
+
+	if (new_val < min || new_val > max)
+		return -EINVAL;
+
+	*val = new_val;
+	return 0;
+}
+
+static int null_set_queue_mode(const char *str, const struct kernel_param *kp)
+{
+	return null_param_store_val(str, &g_queue_mode, NULL_Q_BIO, NULL_Q_MQ);
+}
+
+static const struct kernel_param_ops null_queue_mode_param_ops = {
+	.set	= null_set_queue_mode,
+	.get	= param_get_int,
+};
+
+device_param_cb(queue_mode, &null_queue_mode_param_ops, &g_queue_mode, 0444);
+MODULE_PARM_DESC(queue_mode, "Block interface to use (0=bio,1=rq,2=multiqueue)");
+
+static int g_gb = 250;
+module_param_named(gb, g_gb, int, 0444);
+MODULE_PARM_DESC(gb, "Size in GB");
+
+static int g_bs = 512;
+module_param_named(bs, g_bs, int, 0444);
+MODULE_PARM_DESC(bs, "Block size (in bytes)");
+
+static int nr_devices = 1;
+module_param(nr_devices, int, 0444);
+MODULE_PARM_DESC(nr_devices, "Number of devices to register");
+
+static bool g_blocking;
+module_param_named(blocking, g_blocking, bool, 0444);
+MODULE_PARM_DESC(blocking, "Register as a blocking blk-mq driver device");
+
+static bool shared_tags;
+module_param(shared_tags, bool, 0444);
+MODULE_PARM_DESC(shared_tags, "Share tag set between devices for blk-mq");
+
+static int g_irqmode = NULL_IRQ_SOFTIRQ;
+
+static int null_set_irqmode(const char *str, const struct kernel_param *kp)
+{
+	return null_param_store_val(str, &g_irqmode, NULL_IRQ_NONE,
+					NULL_IRQ_TIMER);
+}
+
+static const struct kernel_param_ops null_irqmode_param_ops = {
+	.set	= null_set_irqmode,
+	.get	= param_get_int,
+};
+
+device_param_cb(irqmode, &null_irqmode_param_ops, &g_irqmode, 0444);
+MODULE_PARM_DESC(irqmode, "IRQ completion handler. 0-none, 1-softirq, 2-timer");
+
+static unsigned long g_completion_nsec = 10000;
+module_param_named(completion_nsec, g_completion_nsec, ulong, 0444);
+MODULE_PARM_DESC(completion_nsec, "Time in ns to complete a request in hardware. Default: 10,000ns");
+
+static int g_hw_queue_depth = 64;
+module_param_named(hw_queue_depth, g_hw_queue_depth, int, 0444);
+MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64");
+
+static bool g_use_per_node_hctx;
+module_param_named(use_per_node_hctx, g_use_per_node_hctx, bool, 0444);
+MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false");
+
+static bool g_zoned;
+module_param_named(zoned, g_zoned, bool, S_IRUGO);
+MODULE_PARM_DESC(zoned, "Make device as a host-managed zoned block device. Default: false");
+
+static unsigned long g_zone_size = 256;
+module_param_named(zone_size, g_zone_size, ulong, S_IRUGO);
+MODULE_PARM_DESC(zone_size, "Zone size in MB when block device is zoned. Must be power-of-two: Default: 256");
+
+static struct nullb_device *null_alloc_dev(void);
+static void null_free_dev(struct nullb_device *dev);
+static void null_del_dev(struct nullb *nullb);
+static int null_add_dev(struct nullb_device *dev);
+static void null_free_device_storage(struct nullb_device *dev, bool is_cache);
+
+static inline struct nullb_device *to_nullb_device(struct config_item *item)
+{
+	return item ? container_of(item, struct nullb_device, item) : NULL;
+}
+
+static inline ssize_t nullb_device_uint_attr_show(unsigned int val, char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%u\n", val);
+}
+
+static inline ssize_t nullb_device_ulong_attr_show(unsigned long val,
+	char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%lu\n", val);
+}
+
+static inline ssize_t nullb_device_bool_attr_show(bool val, char *page)
+{
+	return snprintf(page, PAGE_SIZE, "%u\n", val);
+}
+
+static ssize_t nullb_device_uint_attr_store(unsigned int *val,
+	const char *page, size_t count)
+{
+	unsigned int tmp;
+	int result;
+
+	result = kstrtouint(page, 0, &tmp);
+	if (result)
+		return result;
+
+	*val = tmp;
+	return count;
+}
+
+static ssize_t nullb_device_ulong_attr_store(unsigned long *val,
+	const char *page, size_t count)
+{
+	int result;
+	unsigned long tmp;
+
+	result = kstrtoul(page, 0, &tmp);
+	if (result)
+		return result;
+
+	*val = tmp;
+	return count;
+}
+
+static ssize_t nullb_device_bool_attr_store(bool *val, const char *page,
+	size_t count)
+{
+	bool tmp;
+	int result;
+
+	result = kstrtobool(page,  &tmp);
+	if (result)
+		return result;
+
+	*val = tmp;
+	return count;
+}
+
+/* The following macro should only be used with TYPE = {uint, ulong, bool}. */
+#define NULLB_DEVICE_ATTR(NAME, TYPE)						\
+static ssize_t									\
+nullb_device_##NAME##_show(struct config_item *item, char *page)		\
+{										\
+	return nullb_device_##TYPE##_attr_show(					\
+				to_nullb_device(item)->NAME, page);		\
+}										\
+static ssize_t									\
+nullb_device_##NAME##_store(struct config_item *item, const char *page,		\
+			    size_t count)					\
+{										\
+	if (test_bit(NULLB_DEV_FL_CONFIGURED, &to_nullb_device(item)->flags))	\
+		return -EBUSY;							\
+	return nullb_device_##TYPE##_attr_store(				\
+			&to_nullb_device(item)->NAME, page, count);		\
+}										\
+CONFIGFS_ATTR(nullb_device_, NAME);
+
+NULLB_DEVICE_ATTR(size, ulong);
+NULLB_DEVICE_ATTR(completion_nsec, ulong);
+NULLB_DEVICE_ATTR(submit_queues, uint);
+NULLB_DEVICE_ATTR(home_node, uint);
+NULLB_DEVICE_ATTR(queue_mode, uint);
+NULLB_DEVICE_ATTR(blocksize, uint);
+NULLB_DEVICE_ATTR(irqmode, uint);
+NULLB_DEVICE_ATTR(hw_queue_depth, uint);
+NULLB_DEVICE_ATTR(index, uint);
+NULLB_DEVICE_ATTR(blocking, bool);
+NULLB_DEVICE_ATTR(use_per_node_hctx, bool);
+NULLB_DEVICE_ATTR(memory_backed, bool);
+NULLB_DEVICE_ATTR(discard, bool);
+NULLB_DEVICE_ATTR(mbps, uint);
+NULLB_DEVICE_ATTR(cache_size, ulong);
+NULLB_DEVICE_ATTR(zoned, bool);
+NULLB_DEVICE_ATTR(zone_size, ulong);
+
+static ssize_t nullb_device_power_show(struct config_item *item, char *page)
+{
+	return nullb_device_bool_attr_show(to_nullb_device(item)->power, page);
+}
+
+static ssize_t nullb_device_power_store(struct config_item *item,
+				     const char *page, size_t count)
+{
+	struct nullb_device *dev = to_nullb_device(item);
+	bool newp = false;
+	ssize_t ret;
+
+	ret = nullb_device_bool_attr_store(&newp, page, count);
+	if (ret < 0)
+		return ret;
+
+	if (!dev->power && newp) {
+		if (test_and_set_bit(NULLB_DEV_FL_UP, &dev->flags))
+			return count;
+		if (null_add_dev(dev)) {
+			clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+			return -ENOMEM;
+		}
+
+		set_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
+		dev->power = newp;
+	} else if (dev->power && !newp) {
+		mutex_lock(&lock);
+		dev->power = newp;
+		null_del_dev(dev->nullb);
+		mutex_unlock(&lock);
+		clear_bit(NULLB_DEV_FL_UP, &dev->flags);
+		clear_bit(NULLB_DEV_FL_CONFIGURED, &dev->flags);
+	}
+
+	return count;
+}
+
+CONFIGFS_ATTR(nullb_device_, power);
+
+static ssize_t nullb_device_badblocks_show(struct config_item *item, char *page)
+{
+	struct nullb_device *t_dev = to_nullb_device(item);
+
+	return badblocks_show(&t_dev->badblocks, page, 0);
+}
+
+static ssize_t nullb_device_badblocks_store(struct config_item *item,
+				     const char *page, size_t count)
+{
+	struct nullb_device *t_dev = to_nullb_device(item);
+	char *orig, *buf, *tmp;
+	u64 start, end;
+	int ret;
+
+	orig = kstrndup(page, count, GFP_KERNEL);
+	if (!orig)
+		return -ENOMEM;
+
+	buf = strstrip(orig);
+
+	ret = -EINVAL;
+	if (buf[0] != '+' && buf[0] != '-')
+		goto out;
+	tmp = strchr(&buf[1], '-');
+	if (!tmp)
+		goto out;
+	*tmp = '\0';
+	ret = kstrtoull(buf + 1, 0, &start);
+	if (ret)
+		goto out;
+	ret = kstrtoull(tmp + 1, 0, &end);
+	if (ret)
+		goto out;
+	ret = -EINVAL;
+	if (start > end)
+		goto out;
+	/* enable badblocks */
+	cmpxchg(&t_dev->badblocks.shift, -1, 0);
+	if (buf[0] == '+')
+		ret = badblocks_set(&t_dev->badblocks, start,
+			end - start + 1, 1);
+	else
+		ret = badblocks_clear(&t_dev->badblocks, start,
+			end - start + 1);
+	if (ret == 0)
+		ret = count;
+out:
+	kfree(orig);
+	return ret;
+}
+CONFIGFS_ATTR(nullb_device_, badblocks);
+
+static struct configfs_attribute *nullb_device_attrs[] = {
+	&nullb_device_attr_size,
+	&nullb_device_attr_completion_nsec,
+	&nullb_device_attr_submit_queues,
+	&nullb_device_attr_home_node,
+	&nullb_device_attr_queue_mode,
+	&nullb_device_attr_blocksize,
+	&nullb_device_attr_irqmode,
+	&nullb_device_attr_hw_queue_depth,
+	&nullb_device_attr_index,
+	&nullb_device_attr_blocking,
+	&nullb_device_attr_use_per_node_hctx,
+	&nullb_device_attr_power,
+	&nullb_device_attr_memory_backed,
+	&nullb_device_attr_discard,
+	&nullb_device_attr_mbps,
+	&nullb_device_attr_cache_size,
+	&nullb_device_attr_badblocks,
+	&nullb_device_attr_zoned,
+	&nullb_device_attr_zone_size,
+	NULL,
+};
+
+static void nullb_device_release(struct config_item *item)
+{
+	struct nullb_device *dev = to_nullb_device(item);
+
+	null_free_device_storage(dev, false);
+	null_free_dev(dev);
+}
+
+static struct configfs_item_operations nullb_device_ops = {
+	.release	= nullb_device_release,
+};
+
+static const struct config_item_type nullb_device_type = {
+	.ct_item_ops	= &nullb_device_ops,
+	.ct_attrs	= nullb_device_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct
+config_item *nullb_group_make_item(struct config_group *group, const char *name)
+{
+	struct nullb_device *dev;
+
+	dev = null_alloc_dev();
+	if (!dev)
+		return ERR_PTR(-ENOMEM);
+
+	config_item_init_type_name(&dev->item, name, &nullb_device_type);
+
+	return &dev->item;
+}
+
+static void
+nullb_group_drop_item(struct config_group *group, struct config_item *item)
+{
+	struct nullb_device *dev = to_nullb_device(item);
+
+	if (test_and_clear_bit(NULLB_DEV_FL_UP, &dev->flags)) {
+		mutex_lock(&lock);
+		dev->power = false;
+		null_del_dev(dev->nullb);
+		mutex_unlock(&lock);
+	}
+
+	config_item_put(item);
+}
+
+static ssize_t memb_group_features_show(struct config_item *item, char *page)
+{
+	return snprintf(page, PAGE_SIZE, "memory_backed,discard,bandwidth,cache,badblocks,zoned,zone_size\n");
+}
+
+CONFIGFS_ATTR_RO(memb_group_, features);
+
+static struct configfs_attribute *nullb_group_attrs[] = {
+	&memb_group_attr_features,
+	NULL,
+};
+
+static struct configfs_group_operations nullb_group_ops = {
+	.make_item	= nullb_group_make_item,
+	.drop_item	= nullb_group_drop_item,
+};
+
+static const struct config_item_type nullb_group_type = {
+	.ct_group_ops	= &nullb_group_ops,
+	.ct_attrs	= nullb_group_attrs,
+	.ct_owner	= THIS_MODULE,
+};
+
+static struct configfs_subsystem nullb_subsys = {
+	.su_group = {
+		.cg_item = {
+			.ci_namebuf = "nullb",
+			.ci_type = &nullb_group_type,
+		},
+	},
+};
+
+static inline int null_cache_active(struct nullb *nullb)
+{
+	return test_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
+}
+
+static struct nullb_device *null_alloc_dev(void)
+{
+	struct nullb_device *dev;
+
+	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return NULL;
+	INIT_RADIX_TREE(&dev->data, GFP_ATOMIC);
+	INIT_RADIX_TREE(&dev->cache, GFP_ATOMIC);
+	if (badblocks_init(&dev->badblocks, 0)) {
+		kfree(dev);
+		return NULL;
+	}
+
+	dev->size = g_gb * 1024;
+	dev->completion_nsec = g_completion_nsec;
+	dev->submit_queues = g_submit_queues;
+	dev->home_node = g_home_node;
+	dev->queue_mode = g_queue_mode;
+	dev->blocksize = g_bs;
+	dev->irqmode = g_irqmode;
+	dev->hw_queue_depth = g_hw_queue_depth;
+	dev->blocking = g_blocking;
+	dev->use_per_node_hctx = g_use_per_node_hctx;
+	dev->zoned = g_zoned;
+	dev->zone_size = g_zone_size;
+	return dev;
+}
+
+static void null_free_dev(struct nullb_device *dev)
+{
+	if (!dev)
+		return;
+
+	null_zone_exit(dev);
+	badblocks_exit(&dev->badblocks);
+	kfree(dev);
+}
+
+static void put_tag(struct nullb_queue *nq, unsigned int tag)
+{
+	clear_bit_unlock(tag, nq->tag_map);
+
+	if (waitqueue_active(&nq->wait))
+		wake_up(&nq->wait);
+}
+
+static unsigned int get_tag(struct nullb_queue *nq)
+{
+	unsigned int tag;
+
+	do {
+		tag = find_first_zero_bit(nq->tag_map, nq->queue_depth);
+		if (tag >= nq->queue_depth)
+			return -1U;
+	} while (test_and_set_bit_lock(tag, nq->tag_map));
+
+	return tag;
+}
+
+static void free_cmd(struct nullb_cmd *cmd)
+{
+	put_tag(cmd->nq, cmd->tag);
+}
+
+static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer);
+
+static struct nullb_cmd *__alloc_cmd(struct nullb_queue *nq)
+{
+	struct nullb_cmd *cmd;
+	unsigned int tag;
+
+	tag = get_tag(nq);
+	if (tag != -1U) {
+		cmd = &nq->cmds[tag];
+		cmd->tag = tag;
+		cmd->nq = nq;
+		if (nq->dev->irqmode == NULL_IRQ_TIMER) {
+			hrtimer_init(&cmd->timer, CLOCK_MONOTONIC,
+				     HRTIMER_MODE_REL);
+			cmd->timer.function = null_cmd_timer_expired;
+		}
+		return cmd;
+	}
+
+	return NULL;
+}
+
+static struct nullb_cmd *alloc_cmd(struct nullb_queue *nq, int can_wait)
+{
+	struct nullb_cmd *cmd;
+	DEFINE_WAIT(wait);
+
+	cmd = __alloc_cmd(nq);
+	if (cmd || !can_wait)
+		return cmd;
+
+	do {
+		prepare_to_wait(&nq->wait, &wait, TASK_UNINTERRUPTIBLE);
+		cmd = __alloc_cmd(nq);
+		if (cmd)
+			break;
+
+		io_schedule();
+	} while (1);
+
+	finish_wait(&nq->wait, &wait);
+	return cmd;
+}
+
+static void end_cmd(struct nullb_cmd *cmd)
+{
+	struct request_queue *q = NULL;
+	int queue_mode = cmd->nq->dev->queue_mode;
+
+	if (cmd->rq)
+		q = cmd->rq->q;
+
+	switch (queue_mode)  {
+	case NULL_Q_MQ:
+		blk_mq_end_request(cmd->rq, cmd->error);
+		return;
+	case NULL_Q_RQ:
+		INIT_LIST_HEAD(&cmd->rq->queuelist);
+		blk_end_request_all(cmd->rq, cmd->error);
+		break;
+	case NULL_Q_BIO:
+		cmd->bio->bi_status = cmd->error;
+		bio_endio(cmd->bio);
+		break;
+	}
+
+	free_cmd(cmd);
+
+	/* Restart queue if needed, as we are freeing a tag */
+	if (queue_mode == NULL_Q_RQ && blk_queue_stopped(q)) {
+		unsigned long flags;
+
+		spin_lock_irqsave(q->queue_lock, flags);
+		blk_start_queue_async(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+}
+
+static enum hrtimer_restart null_cmd_timer_expired(struct hrtimer *timer)
+{
+	end_cmd(container_of(timer, struct nullb_cmd, timer));
+
+	return HRTIMER_NORESTART;
+}
+
+static void null_cmd_end_timer(struct nullb_cmd *cmd)
+{
+	ktime_t kt = cmd->nq->dev->completion_nsec;
+
+	hrtimer_start(&cmd->timer, kt, HRTIMER_MODE_REL);
+}
+
+static void null_softirq_done_fn(struct request *rq)
+{
+	struct nullb *nullb = rq->q->queuedata;
+
+	if (nullb->dev->queue_mode == NULL_Q_MQ)
+		end_cmd(blk_mq_rq_to_pdu(rq));
+	else
+		end_cmd(rq->special);
+}
+
+static struct nullb_page *null_alloc_page(gfp_t gfp_flags)
+{
+	struct nullb_page *t_page;
+
+	t_page = kmalloc(sizeof(struct nullb_page), gfp_flags);
+	if (!t_page)
+		goto out;
+
+	t_page->page = alloc_pages(gfp_flags, 0);
+	if (!t_page->page)
+		goto out_freepage;
+
+	memset(t_page->bitmap, 0, sizeof(t_page->bitmap));
+	return t_page;
+out_freepage:
+	kfree(t_page);
+out:
+	return NULL;
+}
+
+static void null_free_page(struct nullb_page *t_page)
+{
+	__set_bit(NULLB_PAGE_FREE, t_page->bitmap);
+	if (test_bit(NULLB_PAGE_LOCK, t_page->bitmap))
+		return;
+	__free_page(t_page->page);
+	kfree(t_page);
+}
+
+static bool null_page_empty(struct nullb_page *page)
+{
+	int size = MAP_SZ - 2;
+
+	return find_first_bit(page->bitmap, size) == size;
+}
+
+static void null_free_sector(struct nullb *nullb, sector_t sector,
+	bool is_cache)
+{
+	unsigned int sector_bit;
+	u64 idx;
+	struct nullb_page *t_page, *ret;
+	struct radix_tree_root *root;
+
+	root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
+	idx = sector >> PAGE_SECTORS_SHIFT;
+	sector_bit = (sector & SECTOR_MASK);
+
+	t_page = radix_tree_lookup(root, idx);
+	if (t_page) {
+		__clear_bit(sector_bit, t_page->bitmap);
+
+		if (null_page_empty(t_page)) {
+			ret = radix_tree_delete_item(root, idx, t_page);
+			WARN_ON(ret != t_page);
+			null_free_page(ret);
+			if (is_cache)
+				nullb->dev->curr_cache -= PAGE_SIZE;
+		}
+	}
+}
+
+static struct nullb_page *null_radix_tree_insert(struct nullb *nullb, u64 idx,
+	struct nullb_page *t_page, bool is_cache)
+{
+	struct radix_tree_root *root;
+
+	root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
+
+	if (radix_tree_insert(root, idx, t_page)) {
+		null_free_page(t_page);
+		t_page = radix_tree_lookup(root, idx);
+		WARN_ON(!t_page || t_page->page->index != idx);
+	} else if (is_cache)
+		nullb->dev->curr_cache += PAGE_SIZE;
+
+	return t_page;
+}
+
+static void null_free_device_storage(struct nullb_device *dev, bool is_cache)
+{
+	unsigned long pos = 0;
+	int nr_pages;
+	struct nullb_page *ret, *t_pages[FREE_BATCH];
+	struct radix_tree_root *root;
+
+	root = is_cache ? &dev->cache : &dev->data;
+
+	do {
+		int i;
+
+		nr_pages = radix_tree_gang_lookup(root,
+				(void **)t_pages, pos, FREE_BATCH);
+
+		for (i = 0; i < nr_pages; i++) {
+			pos = t_pages[i]->page->index;
+			ret = radix_tree_delete_item(root, pos, t_pages[i]);
+			WARN_ON(ret != t_pages[i]);
+			null_free_page(ret);
+		}
+
+		pos++;
+	} while (nr_pages == FREE_BATCH);
+
+	if (is_cache)
+		dev->curr_cache = 0;
+}
+
+static struct nullb_page *__null_lookup_page(struct nullb *nullb,
+	sector_t sector, bool for_write, bool is_cache)
+{
+	unsigned int sector_bit;
+	u64 idx;
+	struct nullb_page *t_page;
+	struct radix_tree_root *root;
+
+	idx = sector >> PAGE_SECTORS_SHIFT;
+	sector_bit = (sector & SECTOR_MASK);
+
+	root = is_cache ? &nullb->dev->cache : &nullb->dev->data;
+	t_page = radix_tree_lookup(root, idx);
+	WARN_ON(t_page && t_page->page->index != idx);
+
+	if (t_page && (for_write || test_bit(sector_bit, t_page->bitmap)))
+		return t_page;
+
+	return NULL;
+}
+
+static struct nullb_page *null_lookup_page(struct nullb *nullb,
+	sector_t sector, bool for_write, bool ignore_cache)
+{
+	struct nullb_page *page = NULL;
+
+	if (!ignore_cache)
+		page = __null_lookup_page(nullb, sector, for_write, true);
+	if (page)
+		return page;
+	return __null_lookup_page(nullb, sector, for_write, false);
+}
+
+static struct nullb_page *null_insert_page(struct nullb *nullb,
+	sector_t sector, bool ignore_cache)
+{
+	u64 idx;
+	struct nullb_page *t_page;
+
+	t_page = null_lookup_page(nullb, sector, true, ignore_cache);
+	if (t_page)
+		return t_page;
+
+	spin_unlock_irq(&nullb->lock);
+
+	t_page = null_alloc_page(GFP_NOIO);
+	if (!t_page)
+		goto out_lock;
+
+	if (radix_tree_preload(GFP_NOIO))
+		goto out_freepage;
+
+	spin_lock_irq(&nullb->lock);
+	idx = sector >> PAGE_SECTORS_SHIFT;
+	t_page->page->index = idx;
+	t_page = null_radix_tree_insert(nullb, idx, t_page, !ignore_cache);
+	radix_tree_preload_end();
+
+	return t_page;
+out_freepage:
+	null_free_page(t_page);
+out_lock:
+	spin_lock_irq(&nullb->lock);
+	return null_lookup_page(nullb, sector, true, ignore_cache);
+}
+
+static int null_flush_cache_page(struct nullb *nullb, struct nullb_page *c_page)
+{
+	int i;
+	unsigned int offset;
+	u64 idx;
+	struct nullb_page *t_page, *ret;
+	void *dst, *src;
+
+	idx = c_page->page->index;
+
+	t_page = null_insert_page(nullb, idx << PAGE_SECTORS_SHIFT, true);
+
+	__clear_bit(NULLB_PAGE_LOCK, c_page->bitmap);
+	if (test_bit(NULLB_PAGE_FREE, c_page->bitmap)) {
+		null_free_page(c_page);
+		if (t_page && null_page_empty(t_page)) {
+			ret = radix_tree_delete_item(&nullb->dev->data,
+				idx, t_page);
+			null_free_page(t_page);
+		}
+		return 0;
+	}
+
+	if (!t_page)
+		return -ENOMEM;
+
+	src = kmap_atomic(c_page->page);
+	dst = kmap_atomic(t_page->page);
+
+	for (i = 0; i < PAGE_SECTORS;
+			i += (nullb->dev->blocksize >> SECTOR_SHIFT)) {
+		if (test_bit(i, c_page->bitmap)) {
+			offset = (i << SECTOR_SHIFT);
+			memcpy(dst + offset, src + offset,
+				nullb->dev->blocksize);
+			__set_bit(i, t_page->bitmap);
+		}
+	}
+
+	kunmap_atomic(dst);
+	kunmap_atomic(src);
+
+	ret = radix_tree_delete_item(&nullb->dev->cache, idx, c_page);
+	null_free_page(ret);
+	nullb->dev->curr_cache -= PAGE_SIZE;
+
+	return 0;
+}
+
+static int null_make_cache_space(struct nullb *nullb, unsigned long n)
+{
+	int i, err, nr_pages;
+	struct nullb_page *c_pages[FREE_BATCH];
+	unsigned long flushed = 0, one_round;
+
+again:
+	if ((nullb->dev->cache_size * 1024 * 1024) >
+	     nullb->dev->curr_cache + n || nullb->dev->curr_cache == 0)
+		return 0;
+
+	nr_pages = radix_tree_gang_lookup(&nullb->dev->cache,
+			(void **)c_pages, nullb->cache_flush_pos, FREE_BATCH);
+	/*
+	 * nullb_flush_cache_page could unlock before using the c_pages. To
+	 * avoid race, we don't allow page free
+	 */
+	for (i = 0; i < nr_pages; i++) {
+		nullb->cache_flush_pos = c_pages[i]->page->index;
+		/*
+		 * We found the page which is being flushed to disk by other
+		 * threads
+		 */
+		if (test_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap))
+			c_pages[i] = NULL;
+		else
+			__set_bit(NULLB_PAGE_LOCK, c_pages[i]->bitmap);
+	}
+
+	one_round = 0;
+	for (i = 0; i < nr_pages; i++) {
+		if (c_pages[i] == NULL)
+			continue;
+		err = null_flush_cache_page(nullb, c_pages[i]);
+		if (err)
+			return err;
+		one_round++;
+	}
+	flushed += one_round << PAGE_SHIFT;
+
+	if (n > flushed) {
+		if (nr_pages == 0)
+			nullb->cache_flush_pos = 0;
+		if (one_round == 0) {
+			/* give other threads a chance */
+			spin_unlock_irq(&nullb->lock);
+			spin_lock_irq(&nullb->lock);
+		}
+		goto again;
+	}
+	return 0;
+}
+
+static int copy_to_nullb(struct nullb *nullb, struct page *source,
+	unsigned int off, sector_t sector, size_t n, bool is_fua)
+{
+	size_t temp, count = 0;
+	unsigned int offset;
+	struct nullb_page *t_page;
+	void *dst, *src;
+
+	while (count < n) {
+		temp = min_t(size_t, nullb->dev->blocksize, n - count);
+
+		if (null_cache_active(nullb) && !is_fua)
+			null_make_cache_space(nullb, PAGE_SIZE);
+
+		offset = (sector & SECTOR_MASK) << SECTOR_SHIFT;
+		t_page = null_insert_page(nullb, sector,
+			!null_cache_active(nullb) || is_fua);
+		if (!t_page)
+			return -ENOSPC;
+
+		src = kmap_atomic(source);
+		dst = kmap_atomic(t_page->page);
+		memcpy(dst + offset, src + off + count, temp);
+		kunmap_atomic(dst);
+		kunmap_atomic(src);
+
+		__set_bit(sector & SECTOR_MASK, t_page->bitmap);
+
+		if (is_fua)
+			null_free_sector(nullb, sector, true);
+
+		count += temp;
+		sector += temp >> SECTOR_SHIFT;
+	}
+	return 0;
+}
+
+static int copy_from_nullb(struct nullb *nullb, struct page *dest,
+	unsigned int off, sector_t sector, size_t n)
+{
+	size_t temp, count = 0;
+	unsigned int offset;
+	struct nullb_page *t_page;
+	void *dst, *src;
+
+	while (count < n) {
+		temp = min_t(size_t, nullb->dev->blocksize, n - count);
+
+		offset = (sector & SECTOR_MASK) << SECTOR_SHIFT;
+		t_page = null_lookup_page(nullb, sector, false,
+			!null_cache_active(nullb));
+
+		dst = kmap_atomic(dest);
+		if (!t_page) {
+			memset(dst + off + count, 0, temp);
+			goto next;
+		}
+		src = kmap_atomic(t_page->page);
+		memcpy(dst + off + count, src + offset, temp);
+		kunmap_atomic(src);
+next:
+		kunmap_atomic(dst);
+
+		count += temp;
+		sector += temp >> SECTOR_SHIFT;
+	}
+	return 0;
+}
+
+static void null_handle_discard(struct nullb *nullb, sector_t sector, size_t n)
+{
+	size_t temp;
+
+	spin_lock_irq(&nullb->lock);
+	while (n > 0) {
+		temp = min_t(size_t, n, nullb->dev->blocksize);
+		null_free_sector(nullb, sector, false);
+		if (null_cache_active(nullb))
+			null_free_sector(nullb, sector, true);
+		sector += temp >> SECTOR_SHIFT;
+		n -= temp;
+	}
+	spin_unlock_irq(&nullb->lock);
+}
+
+static int null_handle_flush(struct nullb *nullb)
+{
+	int err;
+
+	if (!null_cache_active(nullb))
+		return 0;
+
+	spin_lock_irq(&nullb->lock);
+	while (true) {
+		err = null_make_cache_space(nullb,
+			nullb->dev->cache_size * 1024 * 1024);
+		if (err || nullb->dev->curr_cache == 0)
+			break;
+	}
+
+	WARN_ON(!radix_tree_empty(&nullb->dev->cache));
+	spin_unlock_irq(&nullb->lock);
+	return err;
+}
+
+static int null_transfer(struct nullb *nullb, struct page *page,
+	unsigned int len, unsigned int off, bool is_write, sector_t sector,
+	bool is_fua)
+{
+	int err = 0;
+
+	if (!is_write) {
+		err = copy_from_nullb(nullb, page, off, sector, len);
+		flush_dcache_page(page);
+	} else {
+		flush_dcache_page(page);
+		err = copy_to_nullb(nullb, page, off, sector, len, is_fua);
+	}
+
+	return err;
+}
+
+static int null_handle_rq(struct nullb_cmd *cmd)
+{
+	struct request *rq = cmd->rq;
+	struct nullb *nullb = cmd->nq->dev->nullb;
+	int err;
+	unsigned int len;
+	sector_t sector;
+	struct req_iterator iter;
+	struct bio_vec bvec;
+
+	sector = blk_rq_pos(rq);
+
+	if (req_op(rq) == REQ_OP_DISCARD) {
+		null_handle_discard(nullb, sector, blk_rq_bytes(rq));
+		return 0;
+	}
+
+	spin_lock_irq(&nullb->lock);
+	rq_for_each_segment(bvec, rq, iter) {
+		len = bvec.bv_len;
+		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
+				     op_is_write(req_op(rq)), sector,
+				     req_op(rq) & REQ_FUA);
+		if (err) {
+			spin_unlock_irq(&nullb->lock);
+			return err;
+		}
+		sector += len >> SECTOR_SHIFT;
+	}
+	spin_unlock_irq(&nullb->lock);
+
+	return 0;
+}
+
+static int null_handle_bio(struct nullb_cmd *cmd)
+{
+	struct bio *bio = cmd->bio;
+	struct nullb *nullb = cmd->nq->dev->nullb;
+	int err;
+	unsigned int len;
+	sector_t sector;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+
+	sector = bio->bi_iter.bi_sector;
+
+	if (bio_op(bio) == REQ_OP_DISCARD) {
+		null_handle_discard(nullb, sector,
+			bio_sectors(bio) << SECTOR_SHIFT);
+		return 0;
+	}
+
+	spin_lock_irq(&nullb->lock);
+	bio_for_each_segment(bvec, bio, iter) {
+		len = bvec.bv_len;
+		err = null_transfer(nullb, bvec.bv_page, len, bvec.bv_offset,
+				     op_is_write(bio_op(bio)), sector,
+				     bio_op(bio) & REQ_FUA);
+		if (err) {
+			spin_unlock_irq(&nullb->lock);
+			return err;
+		}
+		sector += len >> SECTOR_SHIFT;
+	}
+	spin_unlock_irq(&nullb->lock);
+	return 0;
+}
+
+static void null_stop_queue(struct nullb *nullb)
+{
+	struct request_queue *q = nullb->q;
+
+	if (nullb->dev->queue_mode == NULL_Q_MQ)
+		blk_mq_stop_hw_queues(q);
+	else {
+		spin_lock_irq(q->queue_lock);
+		blk_stop_queue(q);
+		spin_unlock_irq(q->queue_lock);
+	}
+}
+
+static void null_restart_queue_async(struct nullb *nullb)
+{
+	struct request_queue *q = nullb->q;
+	unsigned long flags;
+
+	if (nullb->dev->queue_mode == NULL_Q_MQ)
+		blk_mq_start_stopped_hw_queues(q, true);
+	else {
+		spin_lock_irqsave(q->queue_lock, flags);
+		blk_start_queue_async(q);
+		spin_unlock_irqrestore(q->queue_lock, flags);
+	}
+}
+
+static blk_status_t null_handle_cmd(struct nullb_cmd *cmd)
+{
+	struct nullb_device *dev = cmd->nq->dev;
+	struct nullb *nullb = dev->nullb;
+	int err = 0;
+
+	if (req_op(cmd->rq) == REQ_OP_ZONE_REPORT) {
+		cmd->error = null_zone_report(nullb, cmd);
+		goto out;
+	}
+
+	if (test_bit(NULLB_DEV_FL_THROTTLED, &dev->flags)) {
+		struct request *rq = cmd->rq;
+
+		if (!hrtimer_active(&nullb->bw_timer))
+			hrtimer_restart(&nullb->bw_timer);
+
+		if (atomic_long_sub_return(blk_rq_bytes(rq),
+				&nullb->cur_bytes) < 0) {
+			null_stop_queue(nullb);
+			/* race with timer */
+			if (atomic_long_read(&nullb->cur_bytes) > 0)
+				null_restart_queue_async(nullb);
+			if (dev->queue_mode == NULL_Q_RQ) {
+				struct request_queue *q = nullb->q;
+
+				spin_lock_irq(q->queue_lock);
+				rq->rq_flags |= RQF_DONTPREP;
+				blk_requeue_request(q, rq);
+				spin_unlock_irq(q->queue_lock);
+				return BLK_STS_OK;
+			} else
+				/* requeue request */
+				return BLK_STS_DEV_RESOURCE;
+		}
+	}
+
+	if (nullb->dev->badblocks.shift != -1) {
+		int bad_sectors;
+		sector_t sector, size, first_bad;
+		bool is_flush = true;
+
+		if (dev->queue_mode == NULL_Q_BIO &&
+				bio_op(cmd->bio) != REQ_OP_FLUSH) {
+			is_flush = false;
+			sector = cmd->bio->bi_iter.bi_sector;
+			size = bio_sectors(cmd->bio);
+		}
+		if (dev->queue_mode != NULL_Q_BIO &&
+				req_op(cmd->rq) != REQ_OP_FLUSH) {
+			is_flush = false;
+			sector = blk_rq_pos(cmd->rq);
+			size = blk_rq_sectors(cmd->rq);
+		}
+		if (!is_flush && badblocks_check(&nullb->dev->badblocks, sector,
+				size, &first_bad, &bad_sectors)) {
+			cmd->error = BLK_STS_IOERR;
+			goto out;
+		}
+	}
+
+	if (dev->memory_backed) {
+		if (dev->queue_mode == NULL_Q_BIO) {
+			if (bio_op(cmd->bio) == REQ_OP_FLUSH)
+				err = null_handle_flush(nullb);
+			else
+				err = null_handle_bio(cmd);
+		} else {
+			if (req_op(cmd->rq) == REQ_OP_FLUSH)
+				err = null_handle_flush(nullb);
+			else
+				err = null_handle_rq(cmd);
+		}
+	}
+	cmd->error = errno_to_blk_status(err);
+
+	if (!cmd->error && dev->zoned) {
+		if (req_op(cmd->rq) == REQ_OP_WRITE)
+			null_zone_write(cmd);
+		else if (req_op(cmd->rq) == REQ_OP_ZONE_RESET)
+			null_zone_reset(cmd);
+	}
+out:
+	/* Complete IO by inline, softirq or timer */
+	switch (dev->irqmode) {
+	case NULL_IRQ_SOFTIRQ:
+		switch (dev->queue_mode)  {
+		case NULL_Q_MQ:
+			blk_mq_complete_request(cmd->rq);
+			break;
+		case NULL_Q_RQ:
+			blk_complete_request(cmd->rq);
+			break;
+		case NULL_Q_BIO:
+			/*
+			 * XXX: no proper submitting cpu information available.
+			 */
+			end_cmd(cmd);
+			break;
+		}
+		break;
+	case NULL_IRQ_NONE:
+		end_cmd(cmd);
+		break;
+	case NULL_IRQ_TIMER:
+		null_cmd_end_timer(cmd);
+		break;
+	}
+	return BLK_STS_OK;
+}
+
+static enum hrtimer_restart nullb_bwtimer_fn(struct hrtimer *timer)
+{
+	struct nullb *nullb = container_of(timer, struct nullb, bw_timer);
+	ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL);
+	unsigned int mbps = nullb->dev->mbps;
+
+	if (atomic_long_read(&nullb->cur_bytes) == mb_per_tick(mbps))
+		return HRTIMER_NORESTART;
+
+	atomic_long_set(&nullb->cur_bytes, mb_per_tick(mbps));
+	null_restart_queue_async(nullb);
+
+	hrtimer_forward_now(&nullb->bw_timer, timer_interval);
+
+	return HRTIMER_RESTART;
+}
+
+static void nullb_setup_bwtimer(struct nullb *nullb)
+{
+	ktime_t timer_interval = ktime_set(0, TIMER_INTERVAL);
+
+	hrtimer_init(&nullb->bw_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	nullb->bw_timer.function = nullb_bwtimer_fn;
+	atomic_long_set(&nullb->cur_bytes, mb_per_tick(nullb->dev->mbps));
+	hrtimer_start(&nullb->bw_timer, timer_interval, HRTIMER_MODE_REL);
+}
+
+static struct nullb_queue *nullb_to_queue(struct nullb *nullb)
+{
+	int index = 0;
+
+	if (nullb->nr_queues != 1)
+		index = raw_smp_processor_id() / ((nr_cpu_ids + nullb->nr_queues - 1) / nullb->nr_queues);
+
+	return &nullb->queues[index];
+}
+
+static blk_qc_t null_queue_bio(struct request_queue *q, struct bio *bio)
+{
+	struct nullb *nullb = q->queuedata;
+	struct nullb_queue *nq = nullb_to_queue(nullb);
+	struct nullb_cmd *cmd;
+
+	cmd = alloc_cmd(nq, 1);
+	cmd->bio = bio;
+
+	null_handle_cmd(cmd);
+	return BLK_QC_T_NONE;
+}
+
+static enum blk_eh_timer_return null_rq_timed_out_fn(struct request *rq)
+{
+	pr_info("null: rq %p timed out\n", rq);
+	__blk_complete_request(rq);
+	return BLK_EH_DONE;
+}
+
+static int null_rq_prep_fn(struct request_queue *q, struct request *req)
+{
+	struct nullb *nullb = q->queuedata;
+	struct nullb_queue *nq = nullb_to_queue(nullb);
+	struct nullb_cmd *cmd;
+
+	cmd = alloc_cmd(nq, 0);
+	if (cmd) {
+		cmd->rq = req;
+		req->special = cmd;
+		return BLKPREP_OK;
+	}
+	blk_stop_queue(q);
+
+	return BLKPREP_DEFER;
+}
+
+static bool should_timeout_request(struct request *rq)
+{
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+	if (g_timeout_str[0])
+		return should_fail(&null_timeout_attr, 1);
+#endif
+	return false;
+}
+
+static bool should_requeue_request(struct request *rq)
+{
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+	if (g_requeue_str[0])
+		return should_fail(&null_requeue_attr, 1);
+#endif
+	return false;
+}
+
+static void null_request_fn(struct request_queue *q)
+{
+	struct request *rq;
+
+	while ((rq = blk_fetch_request(q)) != NULL) {
+		struct nullb_cmd *cmd = rq->special;
+
+		/* just ignore the request */
+		if (should_timeout_request(rq))
+			continue;
+		if (should_requeue_request(rq)) {
+			blk_requeue_request(q, rq);
+			continue;
+		}
+
+		spin_unlock_irq(q->queue_lock);
+		null_handle_cmd(cmd);
+		spin_lock_irq(q->queue_lock);
+	}
+}
+
+static enum blk_eh_timer_return null_timeout_rq(struct request *rq, bool res)
+{
+	pr_info("null: rq %p timed out\n", rq);
+	blk_mq_complete_request(rq);
+	return BLK_EH_DONE;
+}
+
+static blk_status_t null_queue_rq(struct blk_mq_hw_ctx *hctx,
+			 const struct blk_mq_queue_data *bd)
+{
+	struct nullb_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
+	struct nullb_queue *nq = hctx->driver_data;
+
+	might_sleep_if(hctx->flags & BLK_MQ_F_BLOCKING);
+
+	if (nq->dev->irqmode == NULL_IRQ_TIMER) {
+		hrtimer_init(&cmd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+		cmd->timer.function = null_cmd_timer_expired;
+	}
+	cmd->rq = bd->rq;
+	cmd->nq = nq;
+
+	blk_mq_start_request(bd->rq);
+
+	if (should_requeue_request(bd->rq)) {
+		/*
+		 * Alternate between hitting the core BUSY path, and the
+		 * driver driven requeue path
+		 */
+		nq->requeue_selection++;
+		if (nq->requeue_selection & 1)
+			return BLK_STS_RESOURCE;
+		else {
+			blk_mq_requeue_request(bd->rq, true);
+			return BLK_STS_OK;
+		}
+	}
+	if (should_timeout_request(bd->rq))
+		return BLK_STS_OK;
+
+	return null_handle_cmd(cmd);
+}
+
+static const struct blk_mq_ops null_mq_ops = {
+	.queue_rq       = null_queue_rq,
+	.complete	= null_softirq_done_fn,
+	.timeout	= null_timeout_rq,
+};
+
+static void cleanup_queue(struct nullb_queue *nq)
+{
+	kfree(nq->tag_map);
+	kfree(nq->cmds);
+}
+
+static void cleanup_queues(struct nullb *nullb)
+{
+	int i;
+
+	for (i = 0; i < nullb->nr_queues; i++)
+		cleanup_queue(&nullb->queues[i]);
+
+	kfree(nullb->queues);
+}
+
+static void null_del_dev(struct nullb *nullb)
+{
+	struct nullb_device *dev = nullb->dev;
+
+	ida_simple_remove(&nullb_indexes, nullb->index);
+
+	list_del_init(&nullb->list);
+
+	del_gendisk(nullb->disk);
+
+	if (test_bit(NULLB_DEV_FL_THROTTLED, &nullb->dev->flags)) {
+		hrtimer_cancel(&nullb->bw_timer);
+		atomic_long_set(&nullb->cur_bytes, LONG_MAX);
+		null_restart_queue_async(nullb);
+	}
+
+	blk_cleanup_queue(nullb->q);
+	if (dev->queue_mode == NULL_Q_MQ &&
+	    nullb->tag_set == &nullb->__tag_set)
+		blk_mq_free_tag_set(nullb->tag_set);
+	put_disk(nullb->disk);
+	cleanup_queues(nullb);
+	if (null_cache_active(nullb))
+		null_free_device_storage(nullb->dev, true);
+	kfree(nullb);
+	dev->nullb = NULL;
+}
+
+static void null_config_discard(struct nullb *nullb)
+{
+	if (nullb->dev->discard == false)
+		return;
+	nullb->q->limits.discard_granularity = nullb->dev->blocksize;
+	nullb->q->limits.discard_alignment = nullb->dev->blocksize;
+	blk_queue_max_discard_sectors(nullb->q, UINT_MAX >> 9);
+	blk_queue_flag_set(QUEUE_FLAG_DISCARD, nullb->q);
+}
+
+static int null_open(struct block_device *bdev, fmode_t mode)
+{
+	return 0;
+}
+
+static void null_release(struct gendisk *disk, fmode_t mode)
+{
+}
+
+static const struct block_device_operations null_fops = {
+	.owner =	THIS_MODULE,
+	.open =		null_open,
+	.release =	null_release,
+};
+
+static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq)
+{
+	BUG_ON(!nullb);
+	BUG_ON(!nq);
+
+	init_waitqueue_head(&nq->wait);
+	nq->queue_depth = nullb->queue_depth;
+	nq->dev = nullb->dev;
+}
+
+static void null_init_queues(struct nullb *nullb)
+{
+	struct request_queue *q = nullb->q;
+	struct blk_mq_hw_ctx *hctx;
+	struct nullb_queue *nq;
+	int i;
+
+	queue_for_each_hw_ctx(q, hctx, i) {
+		if (!hctx->nr_ctx || !hctx->tags)
+			continue;
+		nq = &nullb->queues[i];
+		hctx->driver_data = nq;
+		null_init_queue(nullb, nq);
+		nullb->nr_queues++;
+	}
+}
+
+static int setup_commands(struct nullb_queue *nq)
+{
+	struct nullb_cmd *cmd;
+	int i, tag_size;
+
+	nq->cmds = kcalloc(nq->queue_depth, sizeof(*cmd), GFP_KERNEL);
+	if (!nq->cmds)
+		return -ENOMEM;
+
+	tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG;
+	nq->tag_map = kcalloc(tag_size, sizeof(unsigned long), GFP_KERNEL);
+	if (!nq->tag_map) {
+		kfree(nq->cmds);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < nq->queue_depth; i++) {
+		cmd = &nq->cmds[i];
+		INIT_LIST_HEAD(&cmd->list);
+		cmd->ll_list.next = NULL;
+		cmd->tag = -1U;
+	}
+
+	return 0;
+}
+
+static int setup_queues(struct nullb *nullb)
+{
+	nullb->queues = kcalloc(nullb->dev->submit_queues,
+				sizeof(struct nullb_queue),
+				GFP_KERNEL);
+	if (!nullb->queues)
+		return -ENOMEM;
+
+	nullb->nr_queues = 0;
+	nullb->queue_depth = nullb->dev->hw_queue_depth;
+
+	return 0;
+}
+
+static int init_driver_queues(struct nullb *nullb)
+{
+	struct nullb_queue *nq;
+	int i, ret = 0;
+
+	for (i = 0; i < nullb->dev->submit_queues; i++) {
+		nq = &nullb->queues[i];
+
+		null_init_queue(nullb, nq);
+
+		ret = setup_commands(nq);
+		if (ret)
+			return ret;
+		nullb->nr_queues++;
+	}
+	return 0;
+}
+
+static int null_gendisk_register(struct nullb *nullb)
+{
+	struct gendisk *disk;
+	sector_t size;
+
+	disk = nullb->disk = alloc_disk_node(1, nullb->dev->home_node);
+	if (!disk)
+		return -ENOMEM;
+	size = (sector_t)nullb->dev->size * 1024 * 1024ULL;
+	set_capacity(disk, size >> 9);
+
+	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
+	disk->major		= null_major;
+	disk->first_minor	= nullb->index;
+	disk->fops		= &null_fops;
+	disk->private_data	= nullb;
+	disk->queue		= nullb->q;
+	strncpy(disk->disk_name, nullb->disk_name, DISK_NAME_LEN);
+
+	add_disk(disk);
+	return 0;
+}
+
+static int null_init_tag_set(struct nullb *nullb, struct blk_mq_tag_set *set)
+{
+	set->ops = &null_mq_ops;
+	set->nr_hw_queues = nullb ? nullb->dev->submit_queues :
+						g_submit_queues;
+	set->queue_depth = nullb ? nullb->dev->hw_queue_depth :
+						g_hw_queue_depth;
+	set->numa_node = nullb ? nullb->dev->home_node : g_home_node;
+	set->cmd_size	= sizeof(struct nullb_cmd);
+	set->flags = BLK_MQ_F_SHOULD_MERGE;
+	if (g_no_sched)
+		set->flags |= BLK_MQ_F_NO_SCHED;
+	set->driver_data = NULL;
+
+	if ((nullb && nullb->dev->blocking) || g_blocking)
+		set->flags |= BLK_MQ_F_BLOCKING;
+
+	return blk_mq_alloc_tag_set(set);
+}
+
+static void null_validate_conf(struct nullb_device *dev)
+{
+	dev->blocksize = round_down(dev->blocksize, 512);
+	dev->blocksize = clamp_t(unsigned int, dev->blocksize, 512, 4096);
+
+	if (dev->queue_mode == NULL_Q_MQ && dev->use_per_node_hctx) {
+		if (dev->submit_queues != nr_online_nodes)
+			dev->submit_queues = nr_online_nodes;
+	} else if (dev->submit_queues > nr_cpu_ids)
+		dev->submit_queues = nr_cpu_ids;
+	else if (dev->submit_queues == 0)
+		dev->submit_queues = 1;
+
+	dev->queue_mode = min_t(unsigned int, dev->queue_mode, NULL_Q_MQ);
+	dev->irqmode = min_t(unsigned int, dev->irqmode, NULL_IRQ_TIMER);
+
+	/* Do memory allocation, so set blocking */
+	if (dev->memory_backed)
+		dev->blocking = true;
+	else /* cache is meaningless */
+		dev->cache_size = 0;
+	dev->cache_size = min_t(unsigned long, ULONG_MAX / 1024 / 1024,
+						dev->cache_size);
+	dev->mbps = min_t(unsigned int, 1024 * 40, dev->mbps);
+	/* can not stop a queue */
+	if (dev->queue_mode == NULL_Q_BIO)
+		dev->mbps = 0;
+}
+
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+static bool __null_setup_fault(struct fault_attr *attr, char *str)
+{
+	if (!str[0])
+		return true;
+
+	if (!setup_fault_attr(attr, str))
+		return false;
+
+	attr->verbose = 0;
+	return true;
+}
+#endif
+
+static bool null_setup_fault(void)
+{
+#ifdef CONFIG_BLK_DEV_NULL_BLK_FAULT_INJECTION
+	if (!__null_setup_fault(&null_timeout_attr, g_timeout_str))
+		return false;
+	if (!__null_setup_fault(&null_requeue_attr, g_requeue_str))
+		return false;
+#endif
+	return true;
+}
+
+static int null_add_dev(struct nullb_device *dev)
+{
+	struct nullb *nullb;
+	int rv;
+
+	null_validate_conf(dev);
+
+	nullb = kzalloc_node(sizeof(*nullb), GFP_KERNEL, dev->home_node);
+	if (!nullb) {
+		rv = -ENOMEM;
+		goto out;
+	}
+	nullb->dev = dev;
+	dev->nullb = nullb;
+
+	spin_lock_init(&nullb->lock);
+
+	rv = setup_queues(nullb);
+	if (rv)
+		goto out_free_nullb;
+
+	if (dev->queue_mode == NULL_Q_MQ) {
+		if (shared_tags) {
+			nullb->tag_set = &tag_set;
+			rv = 0;
+		} else {
+			nullb->tag_set = &nullb->__tag_set;
+			rv = null_init_tag_set(nullb, nullb->tag_set);
+		}
+
+		if (rv)
+			goto out_cleanup_queues;
+
+		if (!null_setup_fault())
+			goto out_cleanup_queues;
+
+		nullb->tag_set->timeout = 5 * HZ;
+		nullb->q = blk_mq_init_queue(nullb->tag_set);
+		if (IS_ERR(nullb->q)) {
+			rv = -ENOMEM;
+			goto out_cleanup_tags;
+		}
+		null_init_queues(nullb);
+	} else if (dev->queue_mode == NULL_Q_BIO) {
+		nullb->q = blk_alloc_queue_node(GFP_KERNEL, dev->home_node,
+						NULL);
+		if (!nullb->q) {
+			rv = -ENOMEM;
+			goto out_cleanup_queues;
+		}
+		blk_queue_make_request(nullb->q, null_queue_bio);
+		rv = init_driver_queues(nullb);
+		if (rv)
+			goto out_cleanup_blk_queue;
+	} else {
+		nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock,
+						dev->home_node);
+		if (!nullb->q) {
+			rv = -ENOMEM;
+			goto out_cleanup_queues;
+		}
+
+		if (!null_setup_fault())
+			goto out_cleanup_blk_queue;
+
+		blk_queue_prep_rq(nullb->q, null_rq_prep_fn);
+		blk_queue_softirq_done(nullb->q, null_softirq_done_fn);
+		blk_queue_rq_timed_out(nullb->q, null_rq_timed_out_fn);
+		nullb->q->rq_timeout = 5 * HZ;
+		rv = init_driver_queues(nullb);
+		if (rv)
+			goto out_cleanup_blk_queue;
+	}
+
+	if (dev->mbps) {
+		set_bit(NULLB_DEV_FL_THROTTLED, &dev->flags);
+		nullb_setup_bwtimer(nullb);
+	}
+
+	if (dev->cache_size > 0) {
+		set_bit(NULLB_DEV_FL_CACHE, &nullb->dev->flags);
+		blk_queue_write_cache(nullb->q, true, true);
+		blk_queue_flush_queueable(nullb->q, true);
+	}
+
+	if (dev->zoned) {
+		rv = null_zone_init(dev);
+		if (rv)
+			goto out_cleanup_blk_queue;
+
+		blk_queue_chunk_sectors(nullb->q, dev->zone_size_sects);
+		nullb->q->limits.zoned = BLK_ZONED_HM;
+	}
+
+	nullb->q->queuedata = nullb;
+	blk_queue_flag_set(QUEUE_FLAG_NONROT, nullb->q);
+	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, nullb->q);
+
+	mutex_lock(&lock);
+	nullb->index = ida_simple_get(&nullb_indexes, 0, 0, GFP_KERNEL);
+	dev->index = nullb->index;
+	mutex_unlock(&lock);
+
+	blk_queue_logical_block_size(nullb->q, dev->blocksize);
+	blk_queue_physical_block_size(nullb->q, dev->blocksize);
+
+	null_config_discard(nullb);
+
+	sprintf(nullb->disk_name, "nullb%d", nullb->index);
+
+	rv = null_gendisk_register(nullb);
+	if (rv)
+		goto out_cleanup_zone;
+
+	mutex_lock(&lock);
+	list_add_tail(&nullb->list, &nullb_list);
+	mutex_unlock(&lock);
+
+	return 0;
+out_cleanup_zone:
+	if (dev->zoned)
+		null_zone_exit(dev);
+out_cleanup_blk_queue:
+	blk_cleanup_queue(nullb->q);
+out_cleanup_tags:
+	if (dev->queue_mode == NULL_Q_MQ && nullb->tag_set == &nullb->__tag_set)
+		blk_mq_free_tag_set(nullb->tag_set);
+out_cleanup_queues:
+	cleanup_queues(nullb);
+out_free_nullb:
+	kfree(nullb);
+out:
+	return rv;
+}
+
+static int __init null_init(void)
+{
+	int ret = 0;
+	unsigned int i;
+	struct nullb *nullb;
+	struct nullb_device *dev;
+
+	if (g_bs > PAGE_SIZE) {
+		pr_warn("null_blk: invalid block size\n");
+		pr_warn("null_blk: defaults block size to %lu\n", PAGE_SIZE);
+		g_bs = PAGE_SIZE;
+	}
+
+	if (!is_power_of_2(g_zone_size)) {
+		pr_err("null_blk: zone_size must be power-of-two\n");
+		return -EINVAL;
+	}
+
+	if (g_queue_mode == NULL_Q_MQ && g_use_per_node_hctx) {
+		if (g_submit_queues != nr_online_nodes) {
+			pr_warn("null_blk: submit_queues param is set to %u.\n",
+							nr_online_nodes);
+			g_submit_queues = nr_online_nodes;
+		}
+	} else if (g_submit_queues > nr_cpu_ids)
+		g_submit_queues = nr_cpu_ids;
+	else if (g_submit_queues <= 0)
+		g_submit_queues = 1;
+
+	if (g_queue_mode == NULL_Q_MQ && shared_tags) {
+		ret = null_init_tag_set(NULL, &tag_set);
+		if (ret)
+			return ret;
+	}
+
+	config_group_init(&nullb_subsys.su_group);
+	mutex_init(&nullb_subsys.su_mutex);
+
+	ret = configfs_register_subsystem(&nullb_subsys);
+	if (ret)
+		goto err_tagset;
+
+	mutex_init(&lock);
+
+	null_major = register_blkdev(0, "nullb");
+	if (null_major < 0) {
+		ret = null_major;
+		goto err_conf;
+	}
+
+	for (i = 0; i < nr_devices; i++) {
+		dev = null_alloc_dev();
+		if (!dev) {
+			ret = -ENOMEM;
+			goto err_dev;
+		}
+		ret = null_add_dev(dev);
+		if (ret) {
+			null_free_dev(dev);
+			goto err_dev;
+		}
+	}
+
+	pr_info("null: module loaded\n");
+	return 0;
+
+err_dev:
+	while (!list_empty(&nullb_list)) {
+		nullb = list_entry(nullb_list.next, struct nullb, list);
+		dev = nullb->dev;
+		null_del_dev(nullb);
+		null_free_dev(dev);
+	}
+	unregister_blkdev(null_major, "nullb");
+err_conf:
+	configfs_unregister_subsystem(&nullb_subsys);
+err_tagset:
+	if (g_queue_mode == NULL_Q_MQ && shared_tags)
+		blk_mq_free_tag_set(&tag_set);
+	return ret;
+}
+
+static void __exit null_exit(void)
+{
+	struct nullb *nullb;
+
+	configfs_unregister_subsystem(&nullb_subsys);
+
+	unregister_blkdev(null_major, "nullb");
+
+	mutex_lock(&lock);
+	while (!list_empty(&nullb_list)) {
+		struct nullb_device *dev;
+
+		nullb = list_entry(nullb_list.next, struct nullb, list);
+		dev = nullb->dev;
+		null_del_dev(nullb);
+		null_free_dev(dev);
+	}
+	mutex_unlock(&lock);
+
+	if (g_queue_mode == NULL_Q_MQ && shared_tags)
+		blk_mq_free_tag_set(&tag_set);
+}
+
+module_init(null_init);
+module_exit(null_exit);
+
+MODULE_AUTHOR("Jens Axboe <axboe@kernel.dk>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From aa624a0a9243460b9037889a05663d3b9a9e8f99 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 24 Jul 2018 09:48:30 -0300
Subject: ASoC: fsl-asoc-card: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl-asoc-card.c | 18 +++++++-----------
 1 file changed, 7 insertions(+), 11 deletions(-)

diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 4a6750aa3637..07808c6d5461 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -1,14 +1,10 @@
-/*
- * Freescale Generic ASoC Sound Card driver with ASRC
- *
- * Copyright (C) 2014 Freescale Semiconductor, Inc.
- *
- * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale Generic ASoC Sound Card driver with ASRC
+//
+// Copyright (C) 2014 Freescale Semiconductor, Inc.
+//
+// Author: Nicolin Chen <nicoleotsuka@gmail.com>
 
 #include <linux/clk.h>
 #include <linux/i2c.h>
-- 
cgit v1.2.3


From 2ba28053686334075c8c8bff6c4f6e3fc9ac51ae Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 24 Jul 2018 09:48:31 -0300
Subject: ASoC: fsl_asrc: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_asrc.c     | 18 +++++++-----------
 sound/soc/fsl/fsl_asrc.h     |  5 +----
 sound/soc/fsl/fsl_asrc_dma.c | 18 +++++++-----------
 3 files changed, 15 insertions(+), 26 deletions(-)

diff --git a/sound/soc/fsl/fsl_asrc.c b/sound/soc/fsl/fsl_asrc.c
index adfb8135d739..528e8b108422 100644
--- a/sound/soc/fsl/fsl_asrc.c
+++ b/sound/soc/fsl/fsl_asrc.c
@@ -1,14 +1,10 @@
-/*
- * Freescale ASRC ALSA SoC Digital Audio Interface (DAI) driver
- *
- * Copyright (C) 2014 Freescale Semiconductor, Inc.
- *
- * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale ASRC ALSA SoC Digital Audio Interface (DAI) driver
+//
+// Copyright (C) 2014 Freescale Semiconductor, Inc.
+//
+// Author: Nicolin Chen <nicoleotsuka@gmail.com>
 
 #include <linux/clk.h>
 #include <linux/delay.h>
diff --git a/sound/soc/fsl/fsl_asrc.h b/sound/soc/fsl/fsl_asrc.h
index d558dd5499a5..c60075112570 100644
--- a/sound/soc/fsl/fsl_asrc.h
+++ b/sound/soc/fsl/fsl_asrc.h
@@ -1,13 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * fsl_asrc.h - Freescale ASRC ALSA SoC header file
  *
  * Copyright (C) 2014 Freescale Semiconductor, Inc.
  *
  * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #ifndef _FSL_ASRC_H
diff --git a/sound/soc/fsl/fsl_asrc_dma.c b/sound/soc/fsl/fsl_asrc_dma.c
index 565e16d8fe85..1033ac6631b0 100644
--- a/sound/soc/fsl/fsl_asrc_dma.c
+++ b/sound/soc/fsl/fsl_asrc_dma.c
@@ -1,14 +1,10 @@
-/*
- * Freescale ASRC ALSA SoC Platform (DMA) driver
- *
- * Copyright (C) 2014 Freescale Semiconductor, Inc.
- *
- * Author: Nicolin Chen <nicoleotsuka@gmail.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale ASRC ALSA SoC Platform (DMA) driver
+//
+// Copyright (C) 2014 Freescale Semiconductor, Inc.
+//
+// Author: Nicolin Chen <nicoleotsuka@gmail.com>
 
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
-- 
cgit v1.2.3


From ad47191a72ca0a95327e8bb16155e5e216f1d97d Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 24 Jul 2018 09:48:32 -0300
Subject: ASoC: fsl_utils: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_utils.c | 18 +++++++-----------
 sound/soc/fsl/fsl_utils.h |  7 ++-----
 2 files changed, 9 insertions(+), 16 deletions(-)

diff --git a/sound/soc/fsl/fsl_utils.c b/sound/soc/fsl/fsl_utils.c
index 7592b0406370..7f0fa4b52223 100644
--- a/sound/soc/fsl/fsl_utils.c
+++ b/sound/soc/fsl/fsl_utils.c
@@ -1,14 +1,10 @@
-/**
- * Freescale ALSA SoC Machine driver utility
- *
- * Author: Timur Tabi <timur@freescale.com>
- *
- * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// Freescale ALSA SoC Machine driver utility
+//
+// Author: Timur Tabi <timur@freescale.com>
+//
+// Copyright 2010 Freescale Semiconductor, Inc.
 
 #include <linux/module.h>
 #include <linux/of_address.h>
diff --git a/sound/soc/fsl/fsl_utils.h b/sound/soc/fsl/fsl_utils.h
index 1687b66ef18e..c5dc2a14b492 100644
--- a/sound/soc/fsl/fsl_utils.h
+++ b/sound/soc/fsl/fsl_utils.h
@@ -1,13 +1,10 @@
-/**
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
  * Freescale ALSA SoC Machine driver utility
  *
  * Author: Timur Tabi <timur@freescale.com>
  *
  * Copyright 2010 Freescale Semiconductor, Inc.
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2.  This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
  */
 
 #ifndef _FSL_UTILS_H
-- 
cgit v1.2.3


From 6b24e03ecf1ce188071d142115233b10ed8767b2 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 24 Jul 2018 09:48:33 -0300
Subject: ASoC: imx-sgtl5000: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/imx-sgtl5000.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/sound/soc/fsl/imx-sgtl5000.c b/sound/soc/fsl/imx-sgtl5000.c
index b99e0b5e00e9..c29200cf755a 100644
--- a/sound/soc/fsl/imx-sgtl5000.c
+++ b/sound/soc/fsl/imx-sgtl5000.c
@@ -1,14 +1,7 @@
-/*
- * Copyright 2012 Freescale Semiconductor, Inc.
- * Copyright 2012 Linaro Ltd.
- *
- * The code contained herein is licensed under the GNU General Public
- * License. You may obtain a copy of the GNU General Public License
- * Version 2 or later at the following locations:
- *
- * http://www.opensource.org/licenses/gpl-license.html
- * http://www.gnu.org/copyleft/gpl.html
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright 2012 Freescale Semiconductor, Inc.
+// Copyright 2012 Linaro Ltd.
 
 #include <linux/module.h>
 #include <linux/of.h>
-- 
cgit v1.2.3


From 73d5e2b472640b1fcdb61ae8be389912ef211bda Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Tue, 24 Jul 2018 18:17:40 +0200
Subject: cpu/hotplug: detect SMT disabled by BIOS

If SMT is disabled in BIOS, the CPU code doesn't properly detect it.
The /sys/devices/system/cpu/smt/control file shows 'on', and the 'l1tf'
vulnerabilities file shows SMT as vulnerable.

Fix it by forcing 'cpu_smt_control' to CPU_SMT_NOT_SUPPORTED in such a
case.  Unfortunately the detection can only be done after bringing all
the CPUs online, so we have to overwrite any previous writes to the
variable.

Reported-by: Joe Mario <jmario@redhat.com>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Fixes: f048c399e0f7 ("x86/topology: Provide topology_smt_supported()")
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
---
 kernel/cpu.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 37eec872042b..2bc3d2f5b2a5 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2125,6 +2125,15 @@ static const struct attribute_group cpuhp_smt_attr_group = {
 
 static int __init cpu_smt_state_init(void)
 {
+	/*
+	 * If SMT was disabled by BIOS, detect it here, after the CPUs have
+	 * been brought online.  This ensures the smt/l1tf sysfs entries are
+	 * consistent with reality.  Note this may overwrite cpu_smt_control's
+	 * previous setting.
+	 */
+	if (topology_max_smt_threads() == 1)
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+
 	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				  &cpuhp_smt_attr_group);
 }
-- 
cgit v1.2.3


From 34a4399f196c0dd72d1c0fef87bddb81938e3cfb Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Tue, 24 Jul 2018 13:52:08 +0200
Subject: mips: use asm-generic version of msi.h

This is necessary to be able to include <linux/msi.h> when
CONFIG_GENERIC_MSI_IRQ_DOMAIN is enabled. Without this, a build with
CONFIG_GENERIC_MSI_IRQ_DOMAIN fails with:

   In file included from include/linux/kvm_host.h:20:0,
                    from arch/mips/kernel/asm-offsets.c:24:
>> include/linux/msi.h:197:10: fatal error: asm/msi.h: No such file or directory
    #include <asm/msi.h>
             ^~~~~~~~~~~
   compilation terminated.
   make[2]: *** [arch/mips/kernel/asm-offsets.s] Error 1
   make[2]: Target '__build' not remade because of errors.
   make[1]: *** [prepare0] Error 2
   make[1]: Target 'prepare' not remade because of errors.
   make: *** [sub-make] Error 2

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19986/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: Marc Zyngier <marc.zyngier@arm.com>
Cc: Hanna Hawa <hannah@marvell.com>
---
 arch/mips/include/asm/Kbuild | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 45d541baf359..58351e48421e 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -8,6 +8,7 @@ generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
+generic-y += msi.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h
-- 
cgit v1.2.3


From 3730cf4dd70b6a36e48d58a862120311411b77f5 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 24 Jul 2018 12:47:56 +0200
Subject: netlink: do not store start function in netlink_cb

->start() is called once when dump is being initialized, there is no
need to store it in netlink_cb.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netlink.h  | 1 -
 net/netlink/af_netlink.c | 5 ++---
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index f3075d6c7e82..71f121b66ca8 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -170,7 +170,6 @@ netlink_skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 struct netlink_callback {
 	struct sk_buff		*skb;
 	const struct nlmsghdr	*nlh;
-	int			(*start)(struct netlink_callback *);
 	int			(*dump)(struct sk_buff * skb,
 					struct netlink_callback *cb);
 	int			(*done)(struct netlink_callback *cb);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 393573a99a5a..f6ac7693d2cc 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2300,7 +2300,6 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 
 	cb = &nlk->cb;
 	memset(cb, 0, sizeof(*cb));
-	cb->start = control->start;
 	cb->dump = control->dump;
 	cb->done = control->done;
 	cb->nlh = nlh;
@@ -2309,8 +2308,8 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	cb->min_dump_alloc = control->min_dump_alloc;
 	cb->skb = skb;
 
-	if (cb->start) {
-		ret = cb->start(cb);
+	if (control->start) {
+		ret = control->start(cb);
 		if (ret)
 			goto error_put;
 	}
-- 
cgit v1.2.3


From ad7769ca2d80c379f7441185a7a04de7511aeab1 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Tue, 24 Jul 2018 17:13:11 +0300
Subject: mlxsw: spectrum_acl: Propagate extack pointer

Propagate extack pointer in order to add extack messages for ACL.
In the follow-up patches, appropriate messages will be added
in various points.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/core_acl_flex_actions.c         | 15 +++++++----
 .../mellanox/mlxsw/core_acl_flex_actions.h         | 15 +++++++----
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 17 ++++++++-----
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 29 ++++++++++++++--------
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c  | 20 +++++++++------
 5 files changed, 61 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 9a473628831e..b09de724e9a1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -753,7 +753,8 @@ mlxsw_afa_vlan_pack(char *payload,
 }
 
 int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
-				       u16 vid, u8 pcp, u8 et)
+				       u16 vid, u8 pcp, u8 et,
+				       struct netlink_ext_ack *extack)
 {
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VLAN_CODE,
@@ -953,7 +954,8 @@ mlxsw_afa_block_append_allocated_mirror(struct mlxsw_afa_block *block,
 
 int
 mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, u8 local_in_port,
-			      const struct net_device *out_dev, bool ingress)
+			      const struct net_device *out_dev, bool ingress,
+			      struct netlink_ext_ack *extack)
 {
 	struct mlxsw_afa_mirror *mirror;
 	int err;
@@ -1015,7 +1017,8 @@ mlxsw_afa_forward_pack(char *payload, enum mlxsw_afa_forward_type type,
 }
 
 int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
-			       u8 local_port, bool in_port)
+			       u8 local_port, bool in_port,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_afa_fwd_entry_ref *fwd_entry_ref;
 	u32 kvdl_index;
@@ -1096,7 +1099,8 @@ int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block,
 EXPORT_SYMBOL(mlxsw_afa_block_append_allocated_counter);
 
 int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
-				   u32 *p_counter_index)
+				   u32 *p_counter_index,
+				   struct netlink_ext_ack *extack)
 {
 	struct mlxsw_afa_counter *counter;
 	u32 counter_index;
@@ -1153,7 +1157,8 @@ static inline void mlxsw_afa_virfwd_pack(char *payload,
 	mlxsw_afa_virfwd_fid_set(payload, fid);
 }
 
-int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid)
+int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
+				   struct netlink_ext_ack *extack)
 {
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VIRFWD_CODE,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index 69628582fb4b..a6ffadd30807 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -80,16 +80,21 @@ int mlxsw_afa_block_append_trap_and_forward(struct mlxsw_afa_block *block,
 int mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block,
 				  u8 local_in_port,
 				  const struct net_device *out_dev,
-				  bool ingress);
+				  bool ingress,
+				  struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
-			       u8 local_port, bool in_port);
+			       u8 local_port, bool in_port,
+			       struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
-				       u16 vid, u8 pcp, u8 et);
+				       u16 vid, u8 pcp, u8 et,
+				       struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_allocated_counter(struct mlxsw_afa_block *block,
 					     u32 counter_index);
 int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
-				   u32 *p_counter_index);
-int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid);
+				   u32 *p_counter_index,
+				   struct netlink_ext_ack *extack);
+int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
+				   struct netlink_ext_ack *extack);
 int mlxsw_afa_block_append_mcrouter(struct mlxsw_afa_block *block,
 				    u16 expected_irif, u16 min_mtu,
 				    bool rmid_valid, u32 kvdl_index);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 3db386c2573f..589c63daf085 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -571,25 +571,30 @@ int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei);
 int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
 				  struct mlxsw_sp_acl_block *block,
-				  struct net_device *out_dev);
+				  struct net_device *out_dev,
+				  struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule_info *rulei,
-			       struct net_device *out_dev);
+			       struct net_device *out_dev,
+			       struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_rule_info *rulei,
-				u32 action, u16 vid, u16 proto, u8 prio);
+				u32 action, u16 vid, u16 proto, u8 prio,
+				struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_acl_rule_info *rulei);
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 struct netlink_ext_ack *extack);
 int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_rule_info *rulei,
-				   u16 fid);
+				   u16 fid, struct netlink_ext_ack *extack);
 
 struct mlxsw_sp_acl_rule;
 
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
-			 unsigned long cookie);
+			 unsigned long cookie,
+			 struct netlink_ext_ack *extack);
 void mlxsw_sp_acl_rule_destroy(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule *rule);
 int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 4a4739139d11..c97d40ccf7ad 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -538,7 +538,8 @@ int mlxsw_sp_acl_rulei_act_trap(struct mlxsw_sp_acl_rule_info *rulei)
 
 int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 			       struct mlxsw_sp_acl_rule_info *rulei,
-			       struct net_device *out_dev)
+			       struct net_device *out_dev,
+			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	u8 local_port;
@@ -560,13 +561,14 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 		in_port = true;
 	}
 	return mlxsw_afa_block_append_fwd(rulei->act_block,
-					  local_port, in_port);
+					  local_port, in_port, extack);
 }
 
 int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_rule_info *rulei,
 				  struct mlxsw_sp_acl_block *block,
-				  struct net_device *out_dev)
+				  struct net_device *out_dev,
+				  struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_acl_block_binding *binding;
 	struct mlxsw_sp_port *in_port;
@@ -581,12 +583,14 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_afa_block_append_mirror(rulei->act_block,
 					     in_port->local_port,
 					     out_dev,
-					     binding->ingress);
+					     binding->ingress,
+					     extack);
 }
 
 int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 				struct mlxsw_sp_acl_rule_info *rulei,
-				u32 action, u16 vid, u16 proto, u8 prio)
+				u32 action, u16 vid, u16 proto, u8 prio,
+				struct netlink_ext_ack *extack)
 {
 	u8 ethertype;
 
@@ -605,7 +609,8 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 		}
 
 		return mlxsw_afa_block_append_vlan_modify(rulei->act_block,
-							  vid, prio, ethertype);
+							  vid, prio, ethertype,
+							  extack);
 	} else {
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n");
 		return -EINVAL;
@@ -613,23 +618,25 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp_acl_rulei_act_count(struct mlxsw_sp *mlxsw_sp,
-				 struct mlxsw_sp_acl_rule_info *rulei)
+				 struct mlxsw_sp_acl_rule_info *rulei,
+				 struct netlink_ext_ack *extack)
 {
 	return mlxsw_afa_block_append_counter(rulei->act_block,
-					      &rulei->counter_index);
+					      &rulei->counter_index, extack);
 }
 
 int mlxsw_sp_acl_rulei_act_fid_set(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_rule_info *rulei,
-				   u16 fid)
+				   u16 fid, struct netlink_ext_ack *extack)
 {
-	return mlxsw_afa_block_append_fid_set(rulei->act_block, fid);
+	return mlxsw_afa_block_append_fid_set(rulei->act_block, fid, extack);
 }
 
 struct mlxsw_sp_acl_rule *
 mlxsw_sp_acl_rule_create(struct mlxsw_sp *mlxsw_sp,
 			 struct mlxsw_sp_acl_ruleset *ruleset,
-			 unsigned long cookie)
+			 unsigned long cookie,
+			 struct netlink_ext_ack *extack)
 {
 	const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops;
 	struct mlxsw_sp_acl_rule *rule;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index b3cb618775af..ddcaa9c089a7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -48,7 +48,8 @@
 static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 					 struct mlxsw_sp_acl_block *block,
 					 struct mlxsw_sp_acl_rule_info *rulei,
-					 struct tcf_exts *exts)
+					 struct tcf_exts *exts,
+					 struct netlink_ext_ack *extack)
 {
 	const struct tc_action *a;
 	LIST_HEAD(actions);
@@ -58,7 +59,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	/* Count action is inserted first */
-	err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei);
+	err = mlxsw_sp_acl_rulei_act_count(mlxsw_sp, rulei, extack);
 	if (err)
 		return err;
 
@@ -99,20 +100,21 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 			fid = mlxsw_sp_acl_dummy_fid(mlxsw_sp);
 			fid_index = mlxsw_sp_fid_index(fid);
 			err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei,
-							     fid_index);
+							     fid_index, extack);
 			if (err)
 				return err;
 
 			out_dev = tcf_mirred_dev(a);
 			err = mlxsw_sp_acl_rulei_act_fwd(mlxsw_sp, rulei,
-							 out_dev);
+							 out_dev, extack);
 			if (err)
 				return err;
 		} else if (is_tcf_mirred_egress_mirror(a)) {
 			struct net_device *out_dev = tcf_mirred_dev(a);
 
 			err = mlxsw_sp_acl_rulei_act_mirror(mlxsw_sp, rulei,
-							    block, out_dev);
+							    block, out_dev,
+							    extack);
 			if (err)
 				return err;
 		} else if (is_tcf_vlan(a)) {
@@ -123,7 +125,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 
 			return mlxsw_sp_acl_rulei_act_vlan(mlxsw_sp, rulei,
 							   action, vid,
-							   proto, prio);
+							   proto, prio, extack);
 		} else {
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
 			return -EOPNOTSUPP;
@@ -400,7 +402,8 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, f->exts);
+	return mlxsw_sp_flower_parse_actions(mlxsw_sp, block, rulei, f->exts,
+					     f->common.extack);
 }
 
 int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
@@ -418,7 +421,8 @@ int mlxsw_sp_flower_replace(struct mlxsw_sp *mlxsw_sp,
 	if (IS_ERR(ruleset))
 		return PTR_ERR(ruleset);
 
-	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie);
+	rule = mlxsw_sp_acl_rule_create(mlxsw_sp, ruleset, f->cookie,
+					f->common.extack);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
 		goto err_rule_create;
-- 
cgit v1.2.3


From 9c10812afe3ad45325145787973bcf863d51b057 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Tue, 24 Jul 2018 17:13:12 +0300
Subject: mlxsw: core_acl_flex_actions: Add extack messages

Return extack messages for failures in action set creation.
Errors may occur when action is not currently supported or due
to lack of resources.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../mellanox/mlxsw/core_acl_flex_actions.c         | 35 +++++++++++++++-------
 1 file changed, 25 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index b09de724e9a1..a4669e79fdf9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -760,8 +760,10 @@ int mlxsw_afa_block_append_vlan_modify(struct mlxsw_afa_block *block,
 						  MLXSW_AFA_VLAN_CODE,
 						  MLXSW_AFA_VLAN_SIZE);
 
-	if (!act)
+	if (!act) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append vlan_modify action");
 		return -ENOBUFS;
+	}
 	mlxsw_afa_vlan_pack(act, MLXSW_AFA_VLAN_VLAN_TAG_CMD_NOP,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, vid,
 			    MLXSW_AFA_VLAN_CMD_SET_OUTER, pcp,
@@ -962,12 +964,15 @@ mlxsw_afa_block_append_mirror(struct mlxsw_afa_block *block, u8 local_in_port,
 
 	mirror = mlxsw_afa_mirror_create(block, local_in_port, out_dev,
 					 ingress);
-	if (IS_ERR(mirror))
+	if (IS_ERR(mirror)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot create mirror action");
 		return PTR_ERR(mirror);
-
+	}
 	err = mlxsw_afa_block_append_allocated_mirror(block, mirror->span_id);
-	if (err)
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append mirror action");
 		goto err_append_allocated_mirror;
+	}
 
 	return 0;
 
@@ -1025,17 +1030,22 @@ int mlxsw_afa_block_append_fwd(struct mlxsw_afa_block *block,
 	char *act;
 	int err;
 
-	if (in_port)
+	if (in_port) {
+		NL_SET_ERR_MSG_MOD(extack, "Forwarding to ingress port is not supported");
 		return -EOPNOTSUPP;
+	}
 	fwd_entry_ref = mlxsw_afa_fwd_entry_ref_create(block, local_port);
-	if (IS_ERR(fwd_entry_ref))
+	if (IS_ERR(fwd_entry_ref)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot create forward action");
 		return PTR_ERR(fwd_entry_ref);
+	}
 	kvdl_index = fwd_entry_ref->fwd_entry->kvdl_index;
 
 	act = mlxsw_afa_block_append_action(block, MLXSW_AFA_FORWARD_CODE,
 					    MLXSW_AFA_FORWARD_SIZE);
 	if (!act) {
 		err = -ENOBUFS;
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append forward action");
 		goto err_append_action;
 	}
 	mlxsw_afa_forward_pack(act, MLXSW_AFA_FORWARD_TYPE_PBS,
@@ -1107,14 +1117,17 @@ int mlxsw_afa_block_append_counter(struct mlxsw_afa_block *block,
 	int err;
 
 	counter = mlxsw_afa_counter_create(block);
-	if (IS_ERR(counter))
+	if (IS_ERR(counter)) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot create count action");
 		return PTR_ERR(counter);
+	}
 	counter_index = counter->counter_index;
 
 	err = mlxsw_afa_block_append_allocated_counter(block, counter_index);
-	if (err)
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append count action");
 		goto err_append_allocated_counter;
-
+	}
 	if (p_counter_index)
 		*p_counter_index = counter_index;
 	return 0;
@@ -1163,8 +1176,10 @@ int mlxsw_afa_block_append_fid_set(struct mlxsw_afa_block *block, u16 fid,
 	char *act = mlxsw_afa_block_append_action(block,
 						  MLXSW_AFA_VIRFWD_CODE,
 						  MLXSW_AFA_VIRFWD_SIZE);
-	if (!act)
+	if (!act) {
+		NL_SET_ERR_MSG_MOD(extack, "Cannot append fid_set action");
 		return -ENOBUFS;
+	}
 	mlxsw_afa_virfwd_pack(act, MLXSW_AFA_VIRFWD_FID_CMD_SET, fid);
 	return 0;
 }
-- 
cgit v1.2.3


From af1fe786436ae03f28d5797fc1e261f5f65a28cf Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Tue, 24 Jul 2018 17:13:13 +0300
Subject: mlxsw: spectrum_acl: Add extack messages

Return extack messages for failures in action set creation.
Messages provide reasons for not being able to implement
the action in HW.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index c97d40ccf7ad..6a38763ad261 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -546,11 +546,15 @@ int mlxsw_sp_acl_rulei_act_fwd(struct mlxsw_sp *mlxsw_sp,
 	bool in_port;
 
 	if (out_dev) {
-		if (!mlxsw_sp_port_dev_check(out_dev))
+		if (!mlxsw_sp_port_dev_check(out_dev)) {
+			NL_SET_ERR_MSG_MOD(extack, "Invalid output device");
 			return -EINVAL;
+		}
 		mlxsw_sp_port = netdev_priv(out_dev);
-		if (mlxsw_sp_port->mlxsw_sp != mlxsw_sp)
+		if (mlxsw_sp_port->mlxsw_sp != mlxsw_sp) {
+			NL_SET_ERR_MSG_MOD(extack, "Invalid output device");
 			return -EINVAL;
+		}
 		local_port = mlxsw_sp_port->local_port;
 		in_port = false;
 	} else {
@@ -573,9 +577,10 @@ int mlxsw_sp_acl_rulei_act_mirror(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp_acl_block_binding *binding;
 	struct mlxsw_sp_port *in_port;
 
-	if (!list_is_singular(&block->binding_list))
+	if (!list_is_singular(&block->binding_list)) {
+		NL_SET_ERR_MSG_MOD(extack, "Only a single mirror source is allowed");
 		return -EOPNOTSUPP;
-
+	}
 	binding = list_first_entry(&block->binding_list,
 				   struct mlxsw_sp_acl_block_binding, list);
 	in_port = binding->mlxsw_sp_port;
@@ -603,6 +608,7 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 			ethertype = 1;
 			break;
 		default:
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported VLAN protocol");
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN protocol %#04x\n",
 				proto);
 			return -EINVAL;
@@ -612,6 +618,7 @@ int mlxsw_sp_acl_rulei_act_vlan(struct mlxsw_sp *mlxsw_sp,
 							  vid, prio, ethertype,
 							  extack);
 	} else {
+		NL_SET_ERR_MSG_MOD(extack, "Unsupported VLAN action");
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported VLAN action\n");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 27c203cd148921618260cbbe3061ec290733d384 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Tue, 24 Jul 2018 17:13:14 +0300
Subject: mlxsw: spectrum_flower: Add extack messages

Return extack messages in order to explain failures
of unsupported actions, keys and invalid user input.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c   | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index ddcaa9c089a7..8213cb7190fa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -67,16 +67,22 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 	list_for_each_entry(a, &actions, list) {
 		if (is_tcf_gact_ok(a)) {
 			err = mlxsw_sp_acl_rulei_act_terminate(rulei);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append terminate action");
 				return err;
+			}
 		} else if (is_tcf_gact_shot(a)) {
 			err = mlxsw_sp_acl_rulei_act_drop(rulei);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append drop action");
 				return err;
+			}
 		} else if (is_tcf_gact_trap(a)) {
 			err = mlxsw_sp_acl_rulei_act_trap(rulei);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append trap action");
 				return err;
+			}
 		} else if (is_tcf_gact_goto_chain(a)) {
 			u32 chain_index = tcf_gact_goto_chain_index(a);
 			struct mlxsw_sp_acl_ruleset *ruleset;
@@ -90,8 +96,10 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 
 			group_id = mlxsw_sp_acl_ruleset_group_id(ruleset);
 			err = mlxsw_sp_acl_rulei_act_jump(rulei, group_id);
-			if (err)
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Cannot append jump action");
 				return err;
+			}
 		} else if (is_tcf_mirred_egress_redirect(a)) {
 			struct net_device *out_dev;
 			struct mlxsw_sp_fid *fid;
@@ -127,6 +135,7 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp,
 							   action, vid,
 							   proto, prio, extack);
 		} else {
+			NL_SET_ERR_MSG_MOD(extack, "Unsupported action");
 			dev_err(mlxsw_sp->bus_info->dev, "Unsupported action\n");
 			return -EOPNOTSUPP;
 		}
@@ -203,6 +212,7 @@ static int mlxsw_sp_flower_parse_ports(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Only UDP and TCP keys are supported");
 		dev_err(mlxsw_sp->bus_info->dev, "Only UDP and TCP keys are supported\n");
 		return -EINVAL;
 	}
@@ -231,6 +241,7 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	if (ip_proto != IPPROTO_TCP) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "TCP keys supported only for TCP");
 		dev_err(mlxsw_sp->bus_info->dev, "TCP keys supported only for TCP\n");
 		return -EINVAL;
 	}
@@ -257,6 +268,7 @@ static int mlxsw_sp_flower_parse_ip(struct mlxsw_sp *mlxsw_sp,
 		return 0;
 
 	if (n_proto != ETH_P_IP && n_proto != ETH_P_IPV6) {
+		NL_SET_ERR_MSG_MOD(f->common.extack, "IP keys supported only for IPv4/6");
 		dev_err(mlxsw_sp->bus_info->dev, "IP keys supported only for IPv4/6\n");
 		return -EINVAL;
 	}
@@ -301,6 +313,7 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 	      BIT(FLOW_DISSECTOR_KEY_IP) |
 	      BIT(FLOW_DISSECTOR_KEY_VLAN))) {
 		dev_err(mlxsw_sp->bus_info->dev, "Unsupported key\n");
+		NL_SET_ERR_MSG_MOD(f->common.extack, "Unsupported key");
 		return -EOPNOTSUPP;
 	}
 
-- 
cgit v1.2.3


From 9d0f180cd509aec0172ae15bf1aed54de34d1132 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Tue, 24 Jul 2018 20:17:09 +0530
Subject: cxgb4: collect number of free PSTRUCT page pointers

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h  |  3 +++
 drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c     | 15 +++++++++++++--
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c   |  3 ++-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c |  3 ++-
 drivers/net/ethernet/chelsio/cxgb4/t4_regs.h       |  5 +++++
 5 files changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
index aaf7985aef4c..84e0e71d9ad5 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -120,6 +120,8 @@ struct cudbg_mem_desc {
 	u32 idx;
 };
 
+#define CUDBG_MEMINFO_REV 1
+
 struct cudbg_meminfo {
 	struct cudbg_mem_desc avail[4];
 	struct cudbg_mem_desc mem[ARRAY_SIZE(cudbg_region) + 3];
@@ -137,6 +139,7 @@ struct cudbg_meminfo {
 	u32 port_alloc[4];
 	u32 loopback_used[NCHAN];
 	u32 loopback_alloc[NCHAN];
+	u32 p_structs_free_cnt;
 };
 
 struct cudbg_cim_pif_la {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index b1eb843035ee..e3ad733f690a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -364,6 +364,8 @@ int cudbg_fill_meminfo(struct adapter *padap,
 	meminfo_buff->tx_pages_data[3] = 1 << PMTXNUMCHN_G(lo);
 
 	meminfo_buff->p_structs = t4_read_reg(padap, TP_CMM_MM_MAX_PSTRUCT_A);
+	meminfo_buff->p_structs_free_cnt =
+		FREEPSTRUCTCOUNT_G(t4_read_reg(padap, TP_FLM_FREE_PS_CNT_A));
 
 	for (i = 0; i < 4; i++) {
 		if (CHELSIO_CHIP_VERSION(padap->params.chip) > CHELSIO_T5)
@@ -1465,14 +1467,23 @@ int cudbg_collect_meminfo(struct cudbg_init *pdbg_init,
 	struct adapter *padap = pdbg_init->adap;
 	struct cudbg_buffer temp_buff = { 0 };
 	struct cudbg_meminfo *meminfo_buff;
+	struct cudbg_ver_hdr *ver_hdr;
 	int rc;
 
-	rc = cudbg_get_buff(pdbg_init, dbg_buff, sizeof(struct cudbg_meminfo),
+	rc = cudbg_get_buff(pdbg_init, dbg_buff,
+			    sizeof(struct cudbg_ver_hdr) +
+			    sizeof(struct cudbg_meminfo),
 			    &temp_buff);
 	if (rc)
 		return rc;
 
-	meminfo_buff = (struct cudbg_meminfo *)temp_buff.data;
+	ver_hdr = (struct cudbg_ver_hdr *)temp_buff.data;
+	ver_hdr->signature = CUDBG_ENTITY_SIGNATURE;
+	ver_hdr->revision = CUDBG_MEMINFO_REV;
+	ver_hdr->size = sizeof(struct cudbg_meminfo);
+
+	meminfo_buff = (struct cudbg_meminfo *)(temp_buff.data +
+						sizeof(*ver_hdr));
 	rc = cudbg_fill_meminfo(padap, meminfo_buff);
 	if (rc) {
 		cudbg_err->sys_err = rc;
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
index 55b46592af28..5f01c0a7fd98 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_cudbg.c
@@ -224,7 +224,8 @@ static u32 cxgb4_get_entity_length(struct adapter *adap, u32 entity)
 		len = sizeof(struct cudbg_tp_la) + TPLA_SIZE * sizeof(u64);
 		break;
 	case CUDBG_MEMINFO:
-		len = sizeof(struct cudbg_meminfo);
+		len = sizeof(struct cudbg_ver_hdr) +
+		      sizeof(struct cudbg_meminfo);
 		break;
 	case CUDBG_CIM_PIF_LA:
 		len = sizeof(struct cudbg_cim_pif_la);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 631b78baedbb..218ee8e14249 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2905,7 +2905,8 @@ static int meminfo_show(struct seq_file *seq, void *v)
 		   meminfo.tx_pages_data[1], meminfo.tx_pages_data[2],
 		   meminfo.tx_pages_data[3]);
 
-	seq_printf(seq, "%u p-structs\n\n", meminfo.p_structs);
+	seq_printf(seq, "%u p-structs (%u free)\n\n",
+		   meminfo.p_structs, meminfo.p_structs_free_cnt);
 
 	for (i = 0; i < 4; i++)
 		/* For T6 these are MAC buffer groups */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
index da885881c02f..eb222d40ddbf 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_regs.h
@@ -1502,8 +1502,13 @@
 #define TP_MIB_DATA_A	0x7e54
 #define TP_INT_CAUSE_A	0x7e74
 
+#define TP_FLM_FREE_PS_CNT_A 0x7e80
 #define TP_FLM_FREE_RX_CNT_A 0x7e84
 
+#define FREEPSTRUCTCOUNT_S    0
+#define FREEPSTRUCTCOUNT_M    0x1fffffU
+#define FREEPSTRUCTCOUNT_G(x) (((x) >> FREEPSTRUCTCOUNT_S) & FREEPSTRUCTCOUNT_M)
+
 #define FREERXPAGECOUNT_S    0
 #define FREERXPAGECOUNT_M    0x1fffffU
 #define FREERXPAGECOUNT_V(x) ((x) << FREERXPAGECOUNT_S)
-- 
cgit v1.2.3


From ae2a922fae023164b3e0de62db3a2e6e93305c2e Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Tue, 24 Jul 2018 20:17:10 +0530
Subject: cxgb4: move Tx/Rx free pages collection to common code

This information needs to be collected in vmcore device dump as well.
So, move to common code.

Fixes: fa145d5dfd61 ("cxgb4: display number of rx and tx pages free")
Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h  |  2 ++
 drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c     | 10 ++++++++++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 11 ++---------
 3 files changed, 14 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
index 84e0e71d9ad5..36d25883d123 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_entity.h
@@ -140,6 +140,8 @@ struct cudbg_meminfo {
 	u32 loopback_used[NCHAN];
 	u32 loopback_alloc[NCHAN];
 	u32 p_structs_free_cnt;
+	u32 free_rx_cnt;
+	u32 free_tx_cnt;
 };
 
 struct cudbg_cim_pif_la {
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
index e3ad733f690a..d97e0d7e541a 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cudbg_lib.c
@@ -349,6 +349,11 @@ int cudbg_fill_meminfo(struct adapter *padap,
 	meminfo_buff->up_extmem2_hi = hi;
 
 	lo = t4_read_reg(padap, TP_PMM_RX_MAX_PAGE_A);
+	for (i = 0, meminfo_buff->free_rx_cnt = 0; i < 2; i++)
+		meminfo_buff->free_rx_cnt +=
+			FREERXPAGECOUNT_G(t4_read_reg(padap,
+						      TP_FLM_FREE_RX_CNT_A));
+
 	meminfo_buff->rx_pages_data[0] =  PMRXMAXPAGE_G(lo);
 	meminfo_buff->rx_pages_data[1] =
 		t4_read_reg(padap, TP_PMM_RX_PAGE_SIZE_A) >> 10;
@@ -356,6 +361,11 @@ int cudbg_fill_meminfo(struct adapter *padap,
 
 	lo = t4_read_reg(padap, TP_PMM_TX_MAX_PAGE_A);
 	hi = t4_read_reg(padap, TP_PMM_TX_PAGE_SIZE_A);
+	for (i = 0, meminfo_buff->free_tx_cnt = 0; i < 4; i++)
+		meminfo_buff->free_tx_cnt +=
+			FREETXPAGECOUNT_G(t4_read_reg(padap,
+						      TP_FLM_FREE_TX_CNT_A));
+
 	meminfo_buff->tx_pages_data[0] = PMTXMAXPAGE_G(lo);
 	meminfo_buff->tx_pages_data[1] =
 		hi >= (1 << 20) ? (hi >> 20) : (hi >> 10);
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 218ee8e14249..2320f7829a6b 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2858,7 +2858,6 @@ static int meminfo_show(struct seq_file *seq, void *v)
 {
 	static const char * const memory[] = { "EDC0:", "EDC1:", "MC:",
 					       "MC0:", "MC1:", "HMA:"};
-	unsigned int free_rx_cnt, free_tx_cnt;
 	struct adapter *adap = seq->private;
 	struct cudbg_meminfo meminfo;
 	int i, rc;
@@ -2890,18 +2889,12 @@ static int meminfo_show(struct seq_file *seq, void *v)
 	mem_region_show(seq, "uP Extmem2:", meminfo.up_extmem2_lo,
 			meminfo.up_extmem2_hi);
 
-	for (i = 0, free_rx_cnt = 0; i < 2; i++)
-		free_rx_cnt += FREERXPAGECOUNT_G
-				      (t4_read_reg(adap, TP_FLM_FREE_RX_CNT_A));
 	seq_printf(seq, "\n%u Rx pages (%u free) of size %uKiB for %u channels\n",
-		   meminfo.rx_pages_data[0], free_rx_cnt,
+		   meminfo.rx_pages_data[0], meminfo.free_rx_cnt,
 		   meminfo.rx_pages_data[1], meminfo.rx_pages_data[2]);
 
-	for (i = 0, free_tx_cnt = 0; i < 4; i++)
-		free_tx_cnt += FREETXPAGECOUNT_G
-				      (t4_read_reg(adap, TP_FLM_FREE_TX_CNT_A));
 	seq_printf(seq, "%u Tx pages (%u free) of size %u%ciB for %u channels\n",
-		   meminfo.tx_pages_data[0], free_tx_cnt,
+		   meminfo.tx_pages_data[0], meminfo.free_tx_cnt,
 		   meminfo.tx_pages_data[1], meminfo.tx_pages_data[2],
 		   meminfo.tx_pages_data[3]);
 
-- 
cgit v1.2.3


From fc5d988878942e9b42a4de5204bdd452f3f1ce47 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Tue, 24 Jul 2018 14:31:59 +0200
Subject: MIPS: Introduce HAS_RAPIDIO Kconfig option

Introduce the same option as PPC and ARM already have because
RAPIDIO can function in the absence of PCI.

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Acked-by: Alexandre Bounine <alex.bou9@gmail.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19987/
Cc: linux-mips@linux-mips.org
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Matt Porter <mporter@kernel.crashing.org>
---
 arch/mips/Kconfig | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index a6ce5087b729..b7fa44ddf452 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -3104,10 +3104,13 @@ config ZONE_DMA32
 
 source "drivers/pcmcia/Kconfig"
 
+config HAS_RAPIDIO
+	bool
+	default n
+
 config RAPIDIO
 	tristate "RapidIO support"
-	depends on PCI
-	default n
+	depends on HAS_RAPIDIO || PCI
 	help
 	  If you say Y here, the kernel will include drivers and
 	  infrastructure code to support RapidIO interconnect devices.
-- 
cgit v1.2.3


From 06dc5bf21f3f90750fcc073fbc6ce2a0324df051 Mon Sep 17 00:00:00 2001
From: Alexey Budankov <alexey.budankov@linux.intel.com>
Date: Tue, 19 Jun 2018 11:45:40 +0300
Subject: perf tests: Check that complex event name is parsed correctly

Extend regression testing to cover case of complex event names enabled
by the cset f92da71280fb ("perf record: Enable arbitrary event names
thru name= modifier").

Testing it:

  # perf test
   1: vmlinux symtab matches kallsyms                       : Skip
   2: Detect openat syscall event                           : Ok
   3: Detect openat syscall event on all cpus               : Ok
   4: Read samples using the mmap interface                 : Ok
   5: Test data source output                               : Ok
   6: Parse event definition strings                        : Ok		<===!
   7: Simple expression parser                              : Ok
...

Committer testing:

  # perf test "event definition"
   6: Parse event definition strings                        : Ok
  # perf test -v 6 2> /tmp/before
  # perf test -v 6 2> /tmp/after
  # diff -u /tmp/before /tmp/after
  --- /tmp/before	2018-06-19 10:50:21.485572638 -0300
  +++ /tmp/after	2018-06-19 10:50:40.886572896 -0300
  @@ -1,6 +1,6 @@
    6: Parse event definition strings                        :
   --- start ---
  -test child forked, pid 24259
  +test child forked, pid 24904
   running test 0 'syscalls:sys_enter_openat'Using CPUID GenuineIntel-6-3D
   registering plugin: /root/.traceevent/plugins/plugin_kvm.so
   registering plugin: /root/.traceevent/plugins/plugin_hrtimer.so
  @@ -136,9 +136,11 @@
   running test 50 '4:0x6530160/name=numpmu/'
   running test 51 'L1-dcache-misses/name=cachepmu/'
   running test 52 'intel_pt//u'
  +running test 53 'cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk'
   running test 0 'cpu/config=10,config1,config2=3,period=1000/u'
   running test 1 'cpu/config=1,name=krava/u,cpu/config=2/u'
   running test 2 'cpu/config=1,call-graph=fp,time,period=100000/,cpu/config=2,call-graph=no,time=0,period=2000/'
  +running test 3 'cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp'
   el-capacity -> cpu/event=0x54,umask=0x2/
   el-conflict -> cpu/event=0x54,umask=0x1/
   el-start -> cpu/event=0xc8,umask=0x1/
  #

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/ad30b774-219b-7b80-c610-4e9e298cf8a7@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/parse-events.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index 61211918bfba..a36313daec4e 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1322,6 +1322,14 @@ static int test__intel_pt(struct perf_evlist *evlist)
 	return 0;
 }
 
+static int test__checkevent_complex_name(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel = perf_evlist__first(evlist);
+
+	TEST_ASSERT_VAL("wrong complex name parsing", strcmp(evsel->name, "COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks") == 0);
+	return 0;
+}
+
 static int count_tracepoints(void)
 {
 	struct dirent *events_ent;
@@ -1658,6 +1666,11 @@ static struct evlist_test test__events[] = {
 		.check = test__intel_pt,
 		.id    = 52,
 	},
+	{
+		.name  = "cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk",
+		.check = test__checkevent_complex_name,
+		.id    = 53
+	}
 };
 
 static struct evlist_test test__events_pmu[] = {
@@ -1676,6 +1689,11 @@ static struct evlist_test test__events_pmu[] = {
 		.check = test__checkevent_pmu_partial_time_callgraph,
 		.id    = 2,
 	},
+	{
+		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp",
+		.check = test__checkevent_complex_name,
+		.id    = 3,
+	}
 };
 
 struct terms_test {
-- 
cgit v1.2.3


From e9de7e2f7e22989fefc760cf0920062c58b2b2b1 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 20 Jun 2018 15:58:20 -0300
Subject: perf hists: Clarify callchain disabling when available

We want to allow having mixed events with/without callchains, not
using a global flag to show callchains, but allowing supressing
callchains when they are present.

So invert the logic of the last parameter to hists__fprint() to
that effect.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ohqyisr6qge79qa95ojslptx@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-c2c.c    | 4 ++--
 tools/perf/builtin-diff.c   | 2 +-
 tools/perf/builtin-report.c | 4 ++--
 tools/perf/builtin-top.c    | 2 +-
 tools/perf/ui/stdio/hist.c  | 8 ++++----
 tools/perf/util/hist.h      | 2 +-
 6 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 6a8738f7ead3..f2ea85ee573f 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2193,7 +2193,7 @@ static void print_cacheline(struct c2c_hists *c2c_hists,
 	fprintf(out, "%s\n", bf);
 	fprintf(out, "  -------------------------------------------------------------\n");
 
-	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, true);
+	hists__fprintf(&c2c_hists->hists, false, 0, 0, 0, out, false);
 }
 
 static void print_pareto(FILE *out)
@@ -2268,7 +2268,7 @@ static void perf_c2c__hists_fprintf(FILE *out, struct perf_session *session)
 	fprintf(out, "=================================================\n");
 	fprintf(out, "#\n");
 
-	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, false);
+	hists__fprintf(&c2c.hists.hists, true, 0, 0, 0, stdout, true);
 
 	fprintf(out, "\n");
 	fprintf(out, "=================================================\n");
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index d660cb7b222b..39db2ee32d48 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -696,7 +696,7 @@ static void hists__process(struct hists *hists)
 	hists__output_resort(hists, NULL);
 
 	hists__fprintf(hists, !quiet, 0, 0, 0, stdout,
-		       symbol_conf.use_callchain);
+		       !symbol_conf.use_callchain);
 }
 
 static void data__fprintf(void)
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index c04dc7b53797..02f7a3c27761 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -478,8 +478,8 @@ static int perf_evlist__tty_browse_hists(struct perf_evlist *evlist,
 
 		hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
 		hists__fprintf(hists, !quiet, 0, 0, rep->min_percent, stdout,
-			       symbol_conf.use_callchain ||
-			       symbol_conf.show_branchflag_count);
+			       !(symbol_conf.use_callchain ||
+			         symbol_conf.show_branchflag_count));
 		fprintf(stdout, "\n\n");
 	}
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ffdc2769ff9f..d21d8751e749 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -307,7 +307,7 @@ static void perf_top__print_sym_table(struct perf_top *top)
 	hists__output_recalc_col_len(hists, top->print_entries - printed);
 	putchar('\n');
 	hists__fprintf(hists, false, top->print_entries - printed, win_width,
-		       top->min_percent, stdout, symbol_conf.use_callchain);
+		       top->min_percent, stdout, !symbol_conf.use_callchain);
 }
 
 static void prompt_integer(int *target, const char *msg)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 69b7a28f7a1c..74c4ae1f0a05 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -529,7 +529,7 @@ out:
 
 static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 			       char *bf, size_t bfsz, FILE *fp,
-			       bool use_callchain)
+			       bool ignore_callchains)
 {
 	int ret;
 	int callchain_ret = 0;
@@ -550,7 +550,7 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
 
 	ret = fprintf(fp, "%s\n", bf);
 
-	if (hist_entry__has_callchains(he) && use_callchain)
+	if (hist_entry__has_callchains(he) && !ignore_callchains)
 		callchain_ret = hist_entry_callchain__fprintf(he, total_period,
 							      0, fp);
 
@@ -755,7 +755,7 @@ int hists__fprintf_headers(struct hists *hists, FILE *fp)
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain)
+		      bool ignore_callchains)
 {
 	struct rb_node *nd;
 	size_t ret = 0;
@@ -799,7 +799,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		if (percent < min_pcnt)
 			continue;
 
-		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, use_callchain);
+		ret += hist_entry__fprintf(h, max_cols, line, linesz, fp, ignore_callchains);
 
 		if (max_rows && ++nr_rows >= max_rows)
 			break;
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 73049f7f0f60..3badd7f1e1b8 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -181,7 +181,7 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp);
 
 size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 		      int max_cols, float min_pcnt, FILE *fp,
-		      bool use_callchain);
+		      bool ignore_callchains);
 size_t perf_evlist__fprintf_nr_events(struct perf_evlist *evlist, FILE *fp);
 
 void hists__filter_by_dso(struct hists *hists);
-- 
cgit v1.2.3


From 491ec1553e0075f345fbe476a93775eabcbc40b6 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Date: Tue, 24 Jul 2018 14:32:00 +0200
Subject: MIPS: Octeon: Select HAS_RAPIDIO

All Octeons starting with Octeon II have RAPIDIO controller which
can function even with PCI disabled.

Signed-off-by: Alexander Sverdlin <alexander.sverdlin@nokia.com>
Acked-by: Alexandre Bounine <alex.bou9@gmail.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19988/
Cc: linux-mips@linux-mips.org
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: Matt Porter <mporter@kernel.crashing.org>
---
 arch/mips/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index b7fa44ddf452..235feb657b0b 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -890,6 +890,7 @@ config CAVIUM_OCTEON_SOC
 	bool "Cavium Networks Octeon SoC based boards"
 	select CEVT_R4K
 	select ARCH_HAS_PHYS_TO_DMA
+	select HAS_RAPIDIO
 	select PHYS_ADDR_T_64BIT
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_BIG_ENDIAN
-- 
cgit v1.2.3


From 6abf0f451087176caf0f9ad0cc2a79bcc5ebb443 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Mon, 18 Jun 2018 13:09:54 +0800
Subject: perf cs-etm: Introduce invalid address macro

This patch introduces invalid address macro and uses it to replace dummy
value '0xdeadbeefdeadbeefUL'.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1529298599-3876-2-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 4d5fc374e730..938def6d0bb9 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -31,6 +31,8 @@
 #endif
 #endif
 
+#define CS_ETM_INVAL_ADDR	0xdeadbeefdeadbeefUL
+
 struct cs_etm_decoder {
 	void *data;
 	void (*packet_printer)(const char *msg);
@@ -261,8 +263,8 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	decoder->tail = 0;
 	decoder->packet_count = 0;
 	for (i = 0; i < MAX_BUFFER; i++) {
-		decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].start_addr = CS_ETM_INVAL_ADDR;
+		decoder->packet_buffer[i].end_addr = CS_ETM_INVAL_ADDR;
 		decoder->packet_buffer[i].last_instr_taken_branch = false;
 		decoder->packet_buffer[i].exc = false;
 		decoder->packet_buffer[i].exc_ret = false;
@@ -295,8 +297,8 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	decoder->packet_buffer[et].exc = false;
 	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-	decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
-	decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
+	decoder->packet_buffer[et].start_addr = CS_ETM_INVAL_ADDR;
+	decoder->packet_buffer[et].end_addr = CS_ETM_INVAL_ADDR;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
-- 
cgit v1.2.3


From 6cd4ac6a02c9bc6560faf567ac013902ab9cd039 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Mon, 18 Jun 2018 13:09:55 +0800
Subject: perf cs-etm: Bail out immediately for instruction sample failure

If the instruction sample failure has happened, it isn't necessary to
execute to the end of the function cs_etm__flush().  This commit is to
bail out immediately and return the error code.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1529298599-3876-3-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 822ba915d144..8b2c099e750a 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -939,6 +939,9 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 		err = cs_etm__synth_instruction_sample(
 			etmq, addr,
 			etmq->period_instructions);
+		if (err)
+			return err;
+
 		etmq->period_instructions = 0;
 
 		/*
-- 
cgit v1.2.3


From b8b5ab52bc3a0423080783ae563801077f7ea400 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 21 Jun 2018 10:04:49 +0200
Subject: Revert "perf list: Add s390 support for detailed/verbose PMU event
 description"

This reverts commit 038586c34301578e538f6c5aa79ca82bce1b9152.

Fix the support of detailed/verbose PMU event description by using the
"Unit": keyword in the json files to address event names refering to the
/sys/devices/cpum_[cs]f devices.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180621080452.61012-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/pmu.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 3ba6a1742f91..afd68524ffa9 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -652,12 +652,6 @@ static int is_arm_pmu_core(const char *name)
 	if (stat(path, &st) == 0)
 		return 1;
 
-	/* Look for cpu sysfs (specific to s390) */
-	scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s",
-		  sysfs, name);
-	if (stat(path, &st) == 0 && !strncmp(name, "cpum_", 5))
-		return 1;
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 9bacbced0e32204deb8b9d011279f9beddd8c2ef Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 21 Jun 2018 10:04:50 +0200
Subject: perf list: Add s390 support for detailed PMU event description

Correct the support of detailed/verbose PMU event description by using
the "Unit": keyword in the json files to address event names refering to
the /sys/devices/cpum_[cs]f devices.

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180621080452.61012-2-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/s390/cf_z10/basic.json  | 12 +++++
 tools/perf/pmu-events/arch/s390/cf_z10/crypto.json | 16 +++++++
 .../perf/pmu-events/arch/s390/cf_z10/extended.json | 18 +++++++
 tools/perf/pmu-events/arch/s390/cf_z13/basic.json  | 12 +++++
 tools/perf/pmu-events/arch/s390/cf_z13/crypto.json | 16 +++++++
 .../perf/pmu-events/arch/s390/cf_z13/extended.json | 56 ++++++++++++++++++++++
 tools/perf/pmu-events/arch/s390/cf_z14/basic.json  |  8 ++++
 tools/perf/pmu-events/arch/s390/cf_z14/crypto.json | 16 +++++++
 .../perf/pmu-events/arch/s390/cf_z14/extended.json | 53 ++++++++++++++++++++
 tools/perf/pmu-events/arch/s390/cf_z196/basic.json | 12 +++++
 .../perf/pmu-events/arch/s390/cf_z196/crypto.json  | 16 +++++++
 .../pmu-events/arch/s390/cf_z196/extended.json     | 24 ++++++++++
 .../perf/pmu-events/arch/s390/cf_zec12/basic.json  | 12 +++++
 .../perf/pmu-events/arch/s390/cf_zec12/crypto.json | 16 +++++++
 .../pmu-events/arch/s390/cf_zec12/extended.json    | 35 ++++++++++++++
 tools/perf/pmu-events/jevents.c                    |  2 +
 16 files changed, 324 insertions(+)

diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
index 0feedb40f30f..b6b7f29ca831 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
@@ -1,107 +1,125 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1I_L3_LOCAL_WRITES",
 		"BriefDescription": "L1I L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1D_L3_LOCAL_WRITES",
 		"BriefDescription": "L1D L3 Local Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1I_L3_REMOTE_WRITES",
 		"BriefDescription": "L1I L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L3_REMOTE_WRITES",
 		"BriefDescription": "L1D L3 Remote Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_CACHELINE_INVALIDATES",
 		"BriefDescription": "L1I Cacheline Invalidates",
 		"PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
index 9a002b6967f1..436ce33f1182 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -1,335 +1,391 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB1_GPAGE_WRITES",
 		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
 		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB1_MISSES",
 		"BriefDescription": "L1C TLB1 Misses",
 		"PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "176",
 		"EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Node Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "218",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "219",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "220",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
index 8f653c9d899d..17fb5241928b 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
@@ -1,47 +1,55 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
index aa4dfb46b65b..e7a3524b748f 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -1,317 +1,370 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "DTLB2_WRITES",
 		"BriefDescription": "DTLB2 Writes",
 		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB2_MISSES",
 		"BriefDescription": "DTLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "DTLB2_HPAGE_WRITES",
 		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "DTLB2_GPAGE_WRITES",
 		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
 		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "ITLB2_WRITES",
 		"BriefDescription": "ITLB2 Writes",
 		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "ITLB2_MISSES",
 		"BriefDescription": "ITLB2 Misses",
 		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "TLB2_ENGINES_BUSY",
 		"BriefDescription": "TLB2 Engines Busy",
 		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1C_TLB2_MISSES",
 		"BriefDescription": "L1C TLB2 Misses",
 		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "162",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "163",
 		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "164",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "165",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "166",
 		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "167",
 		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "168",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "169",
 		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "170",
 		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "171",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "172",
 		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "173",
 		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "174",
 		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "175",
 		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "224",
 		"EventName": "BCD_DFP_EXECUTION_SLOTS",
 		"BriefDescription": "BCD DFP Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "225",
 		"EventName": "VX_BCD_EXECUTION_SLOTS",
 		"BriefDescription": "VX BCD Execution Slots",
 		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "226",
 		"EventName": "DECIMAL_INSTRUCTIONS",
 		"BriefDescription": "Decimal Instructions",
 		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "232",
 		"EventName": "LAST_HOST_TRANSLATIONS",
 		"BriefDescription": "Last host translation done",
 		"PublicDescription": "Last Host Translation done"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "243",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "244",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "245",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "448",
 		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
 		"BriefDescription": "Cycle count with one thread active",
 		"PublicDescription": "Cycle count with one thread active"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "449",
 		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
 		"BriefDescription": "Cycle count with two threads active",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
index b6d7fec7c2e7..b7b42a870bb0 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
@@ -1,143 +1,167 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "L1D_L2_SOURCED_WRITES",
 		"BriefDescription": "L1D L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "L1I_L2_SOURCED_WRITES",
 		"BriefDescription": "L1I L2 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "L2C_STORES_SENT",
 		"BriefDescription": "L2C Stores Sent",
 		"PublicDescription": "Incremented by one for every store sent to Level-2 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "134",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "136",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
index 8bf16759ca53..2dd8dafff2ef 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
@@ -1,71 +1,83 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "0",
 		"EventName": "CPU_CYCLES",
 		"BriefDescription": "CPU Cycles",
 		"PublicDescription": "Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "1",
 		"EventName": "INSTRUCTIONS",
 		"BriefDescription": "Instructions",
 		"PublicDescription": "Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "2",
 		"EventName": "L1I_DIR_WRITES",
 		"BriefDescription": "L1I Directory Writes",
 		"PublicDescription": "Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "3",
 		"EventName": "L1I_PENALTY_CYCLES",
 		"BriefDescription": "L1I Penalty Cycles",
 		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "4",
 		"EventName": "L1D_DIR_WRITES",
 		"BriefDescription": "L1D Directory Writes",
 		"PublicDescription": "Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "5",
 		"EventName": "L1D_PENALTY_CYCLES",
 		"BriefDescription": "L1D Penalty Cycles",
 		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "32",
 		"EventName": "PROBLEM_STATE_CPU_CYCLES",
 		"BriefDescription": "Problem-State CPU Cycles",
 		"PublicDescription": "Problem-State Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "33",
 		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
 		"BriefDescription": "Problem-State Instructions",
 		"PublicDescription": "Problem-State Instruction Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "34",
 		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
 		"BriefDescription": "Problem-State L1I Directory Writes",
 		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "35",
 		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1I Penalty Cycles",
 		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "36",
 		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
 		"BriefDescription": "Problem-State L1D Directory Writes",
 		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "37",
 		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
 		"BriefDescription": "Problem-State L1D Penalty Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
index 7e5b72492141..db286f19e7b6 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
@@ -1,95 +1,111 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "64",
 		"EventName": "PRNG_FUNCTIONS",
 		"BriefDescription": "PRNG Functions",
 		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "65",
 		"EventName": "PRNG_CYCLES",
 		"BriefDescription": "PRNG Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "66",
 		"EventName": "PRNG_BLOCKED_FUNCTIONS",
 		"BriefDescription": "PRNG Blocked Functions",
 		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "67",
 		"EventName": "PRNG_BLOCKED_CYCLES",
 		"BriefDescription": "PRNG Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "68",
 		"EventName": "SHA_FUNCTIONS",
 		"BriefDescription": "SHA Functions",
 		"PublicDescription": "Total number of SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "69",
 		"EventName": "SHA_CYCLES",
 		"BriefDescription": "SHA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "70",
 		"EventName": "SHA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "SHA Blocked Functions",
 		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "71",
 		"EventName": "SHA_BLOCKED_CYCLES",
 		"BriefDescription": "SHA Bloced Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "72",
 		"EventName": "DEA_FUNCTIONS",
 		"BriefDescription": "DEA Functions",
 		"PublicDescription": "Total number of the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "73",
 		"EventName": "DEA_CYCLES",
 		"BriefDescription": "DEA Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "74",
 		"EventName": "DEA_BLOCKED_FUNCTIONS",
 		"BriefDescription": "DEA Blocked Functions",
 		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "75",
 		"EventName": "DEA_BLOCKED_CYCLES",
 		"BriefDescription": "DEA Blocked Cycles",
 		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "76",
 		"EventName": "AES_FUNCTIONS",
 		"BriefDescription": "AES Functions",
 		"PublicDescription": "Total number of AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "77",
 		"EventName": "AES_CYCLES",
 		"BriefDescription": "AES Cycles",
 		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "78",
 		"EventName": "AES_BLOCKED_FUNCTIONS",
 		"BriefDescription": "AES Blocked Functions",
 		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "79",
 		"EventName": "AES_BLOCKED_CYCLES",
 		"BriefDescription": "AES Blocked Cycles",
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
index 8682126aabb2..162251037219 100644
--- a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
@@ -1,209 +1,244 @@
 [
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "128",
 		"EventName": "DTLB1_MISSES",
 		"BriefDescription": "DTLB1 Misses",
 		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "129",
 		"EventName": "ITLB1_MISSES",
 		"BriefDescription": "ITLB1 Misses",
 		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "130",
 		"EventName": "L1D_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1D L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "131",
 		"EventName": "L1I_L2I_SOURCED_WRITES",
 		"BriefDescription": "L1I L2I Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "132",
 		"EventName": "L1D_L2D_SOURCED_WRITES",
 		"BriefDescription": "L1D L2D Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "133",
 		"EventName": "DTLB1_WRITES",
 		"BriefDescription": "DTLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "135",
 		"EventName": "L1D_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1D Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "137",
 		"EventName": "L1I_LMEM_SOURCED_WRITES",
 		"BriefDescription": "L1I Local Memory Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "138",
 		"EventName": "L1D_RO_EXCL_WRITES",
 		"BriefDescription": "L1D Read-only Exclusive Writes",
 		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "139",
 		"EventName": "DTLB1_HPAGE_WRITES",
 		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "140",
 		"EventName": "ITLB1_WRITES",
 		"BriefDescription": "ITLB1 Writes",
 		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "141",
 		"EventName": "TLB2_PTE_WRITES",
 		"BriefDescription": "TLB2 PTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "142",
 		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
 		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "143",
 		"EventName": "TLB2_CRSTE_WRITES",
 		"BriefDescription": "TLB2 CRSTE Writes",
 		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "144",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "145",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "146",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "147",
 		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "148",
 		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "149",
 		"EventName": "TX_NC_TEND",
 		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "150",
 		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "151",
 		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "152",
 		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "153",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "154",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "155",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "156",
 		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I On-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "157",
 		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
 		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "158",
 		"EventName": "TX_C_TEND",
 		"BriefDescription": "Completed TEND instructions in constrained TX mode",
 		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "159",
 		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "160",
 		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "161",
 		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
 		"BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
 		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "177",
 		"EventName": "TX_NC_TABORT",
 		"BriefDescription": "Aborted transactions in non-constrained TX mode",
 		"PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "178",
 		"EventName": "TX_C_TABORT_NO_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
 		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
 	},
 	{
+		"Unit": "CPU-M-CF",
 		"EventCode": "179",
 		"EventName": "TX_C_TABORT_SPECIAL",
 		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index db3a594ee1e4..68c92bb599ee 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -233,6 +233,8 @@ static struct map {
 	{ "QPI LL", "uncore_qpi" },
 	{ "SBO", "uncore_sbox" },
 	{ "iMPH-U", "uncore_arb" },
+	{ "CPU-M-CF", "cpum_cf" },
+	{ "CPU-M-SF", "cpum_sf" },
 	{}
 };
 
-- 
cgit v1.2.3


From 83eb383e942bba7aab465a334d2c365d3f47a0ae Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 21 Jun 2018 10:04:51 +0200
Subject: perf json: Add s390 transaction counter definition

'perf stat' displays transactional counters using flag -T on x86.  On
s390 use a JSON file defined metric named transaction to achieve the
same result.

Output before:

  none

Output after:

  [root@s35lp76 perf]# ./perf stat -M transaction  -- \
			  ~/mytesttx 1 >/tmp/111

   Performance counter stats for '/root/mytesttx 1':

                   1      tx_c_tend           #     13.0 transaction
                   1      tx_nc_tend
                  11      tx_nc_tabort
                   0      tx_c_tabort_special
                   0      tx_c_tabort_no_special

         0.001061232 seconds time elapsed

  [root@s35lp76 perf]#

Suggested-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180621080452.61012-3-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/pmu-events/arch/s390/cf_z13/transaction.json   | 7 +++++++
 tools/perf/pmu-events/arch/s390/cf_z14/transaction.json   | 7 +++++++
 tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json | 7 +++++++
 3 files changed, 21 insertions(+)
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
 create mode 100644 tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json

diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
new file mode 100644
index 000000000000..1a0034f79f73
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/transaction.json
@@ -0,0 +1,7 @@
+[
+  {
+    "BriefDescription": "Transaction count",
+    "MetricName": "transaction",
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+  }
+]
-- 
cgit v1.2.3


From 742d92ff219f3aa7a67c184a57acfa8d88936cd6 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 26 Jun 2018 09:17:01 +0200
Subject: perf stat: Add transaction flag (-T) support for s390

The 'perf stat' command line flag -T to display transaction counters is
currently supported for x86 only.

Add support for s390. It is based on the metrics flag -M transaction
using the architecture dependent JSON files. This requires a metric
named "transaction" in the JSON files for the platform.

Introduce a new function metricgroup__has_metric() to check for the
existence of a metric_name transaction.

As suggested by Andi Kleen, this is the new approach to support
transactions counters. Other architectures will follow.

Output before:

  [root@p23lp27 perf]# ./perf stat -T -- sleep 1
  Cannot set up transaction events
  [root@p23lp27 perf]#

Output after:

  [root@s35lp76 perf]# ./perf stat -T -- ~/mytesttx 1 >/tmp/111

   Performance counter stats for '/root/mytesttx 1':

                   1      tx_c_tend           #     13.0 transaction
                   1      tx_nc_tend
                  11      tx_nc_tabort
                   0      tx_c_tabort_special
                   0      tx_c_tabort_no_special

         0.001070109 seconds time elapsed

  [root@s35lp76 perf]#

Suggested-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Acked-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180626071701.58190-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c     | 12 ++++++++++++
 tools/perf/util/metricgroup.c | 22 ++++++++++++++++++++++
 tools/perf/util/metricgroup.h |  1 +
 3 files changed, 35 insertions(+)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 05be023c3f0e..dfd13d6e2931 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -2449,6 +2449,18 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
+		/* Handle -T as -M transaction. Once platform specific metrics
+		 * support has been added to the json files, all archictures
+		 * will use this approach. To determine transaction support
+		 * on an architecture test for such a metric name.
+		 */
+		if (metricgroup__has_metric("transaction")) {
+			struct option opt = { .value = &evsel_list };
+
+			return metricgroup__parse_groups(&opt, "transaction",
+							 &metric_events);
+		}
+
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
 			err = parse_events(evsel_list, transaction_attrs,
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 1ddc3d1d0147..96eab4ec34ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -490,3 +490,25 @@ out:
 	metricgroup__free_egroups(&group_list);
 	return ret;
 }
+
+bool metricgroup__has_metric(const char *metric)
+{
+	struct pmu_events_map *map = perf_pmu__find_map(NULL);
+	struct pmu_event *pe;
+	int i;
+
+	if (!map)
+		return false;
+
+	for (i = 0; ; i++) {
+		pe = &map->table[i];
+
+		if (!pe->name && !pe->metric_group && !pe->metric_name)
+			break;
+		if (!pe->metric_expr)
+			continue;
+		if (match_metric(pe->metric_name, metric))
+			return true;
+	}
+	return false;
+}
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index 06854e125ee7..8a155dba0581 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -28,4 +28,5 @@ int metricgroup__parse_groups(const struct option *opt,
 			struct rblist *metric_events);
 
 void metricgroup__print(bool metrics, bool groups, char *filter, bool raw);
+bool metricgroup__has_metric(const char *metric);
 #endif
-- 
cgit v1.2.3


From 8a95c8994509c55abf1e38c0cc037b1205725e21 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Thu, 12 Jul 2018 09:09:36 +0200
Subject: perf kvm: Fix subcommands on s390

With commit eca0fa28cd0d ("perf record: Provide detailed information on
s390 CPU") s390 platform provides detailed type/model/capacity
information in the CPU identifier string instead of just "IBM/S390".

This breaks 'perf kvm' support which uses hard coded string IBM/S390 to
compare with the CPU identifier string. Fix this by changing the
comparison.

Reported-by: Stefan Raspl <raspl@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Tested-by: Stefan Raspl <raspl@linux.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: stable@vger.kernel.org
Fixes: eca0fa28cd0d ("perf record: Provide detailed information on s390 CPU")
Link: http://lkml.kernel.org/r/20180712070936.67547-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/s390/util/kvm-stat.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/s390/util/kvm-stat.c b/tools/perf/arch/s390/util/kvm-stat.c
index d233e2eb9592..aaabab5e2830 100644
--- a/tools/perf/arch/s390/util/kvm-stat.c
+++ b/tools/perf/arch/s390/util/kvm-stat.c
@@ -102,7 +102,7 @@ const char * const kvm_skip_events[] = {
 
 int cpu_isa_init(struct perf_kvm_stat *kvm, const char *cpuid)
 {
-	if (strstr(cpuid, "IBM/S390")) {
+	if (strstr(cpuid, "IBM")) {
 		kvm->exit_reasons = sie_exit_reasons;
 		kvm->exit_reasons_isa = "SIE";
 	} else
-- 
cgit v1.2.3


From 6feb3fec519ed112f7a77af4e51e51a35148d01c Mon Sep 17 00:00:00 2001
From: Sangwon Hong <qpakzk@gmail.com>
Date: Tue, 17 Jul 2018 20:07:38 +0900
Subject: perf list: Add missing documentation for --desc and --debug options

Add missing documentation for --desc and --debug options to the 'perf
list' man page.

Signed-off-by: Sangwon Hong <qpakzk@gmail.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/r/20180717110738.10779-1-qpakzk@gmail.com
[ Clarify that --desc is by default active ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Documentation/perf-list.txt | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 14e13512c05f..236b9b97dfdb 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -18,6 +18,10 @@ various perf commands with the -e option.
 
 OPTIONS
 -------
+-d::
+--desc::
+Print extra event descriptions. (default)
+
 --no-desc::
 Don't print descriptions.
 
@@ -25,11 +29,13 @@ Don't print descriptions.
 --long-desc::
 Print longer event descriptions.
 
+--debug::
+Enable debugging output.
+
 --details::
 Print how named events are resolved internally into perf events, and also
 any extra expressions computed by perf stat.
 
-
 [[EVENT_MODIFIERS]]
 EVENT MODIFIERS
 ---------------
-- 
cgit v1.2.3


From c715fcfda5a08edabaa15508742be926b7ee51db Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Tue, 10 Jul 2018 19:28:13 +0530
Subject: perf powerpc: Fix callchain ip filtering

For powerpc64, redundant entries in the callchain are filtered out by
determining the state of the return address and the stack frame using
DWARF debug information.

For making these filtering decisions we must analyze the debug
information for the location corresponding to the program counter value,
i.e. the first entry in the callchain, and not the LR value; otherwise,
perf may filter out either the second or the third entry in the
callchain incorrectly.

This can be observed on a powerpc64le system running Fedora 27 as shown
below.

Case 1 - Attaching a probe at inet_pton+0x8 (binary offset 0x15af28).
         Return address is still in LR and a new stack frame is not yet
         allocated. The LR value, i.e. the second entry, should not be
	 filtered out.

  # objdump -d /usr/lib64/libc-2.26.so | less
  ...
  000000000010eb10 <gaih_inet.constprop.7>:
  ...
    10fa48:       78 bb e4 7e     mr      r4,r23
    10fa4c:       0a 00 60 38     li      r3,10
    10fa50:       d9 b4 04 48     bl      15af28 <inet_pton+0x8>
    10fa54:       00 00 00 60     nop
    10fa58:       ac f4 ff 4b     b       10ef04 <gaih_inet.constprop.7+0x3f4>
  ...
  0000000000110450 <getaddrinfo>:
  ...
    1105a8:       54 00 ff 38     addi    r7,r31,84
    1105ac:       58 00 df 38     addi    r6,r31,88
    1105b0:       69 e5 ff 4b     bl      10eb18 <gaih_inet.constprop.7+0x8>
    1105b4:       78 1b 71 7c     mr      r17,r3
    1105b8:       50 01 7f e8     ld      r3,336(r31)
  ...
  000000000015af20 <inet_pton>:
    15af20:       0b 00 4c 3c     addis   r2,r12,11
    15af24:       e0 c1 42 38     addi    r2,r2,-15904
    15af28:       a6 02 08 7c     mflr    r0
    15af2c:       f0 ff c1 fb     std     r30,-16(r1)
    15af30:       f8 ff e1 fb     std     r31,-8(r1)
  ...

  # perf probe -x /usr/lib64/libc-2.26.so -a inet_pton+0x8
  # perf record -e probe_libc:inet_pton -g ping -6 -c 1 ::1
  # perf script

Before:

  ping  4507 [002] 514985.546540: probe_libc:inet_pton: (7fffa7dbaf28)
              7fffa7dbaf28 __GI___inet_pton+0x8 (/usr/lib64/libc-2.26.so)
              7fffa7d705b4 getaddrinfo+0x164 (/usr/lib64/libc-2.26.so)
                 13fb52d70 _init+0xbfc (/usr/bin/ping)
              7fffa7c836a0 generic_start_main.isra.0+0x140 (/usr/lib64/libc-2.26.so)
              7fffa7c83898 __libc_start_main+0xb8 (/usr/lib64/libc-2.26.so)
                         0 [unknown] ([unknown])

After:

  ping  4507 [002] 514985.546540: probe_libc:inet_pton: (7fffa7dbaf28)
              7fffa7dbaf28 __GI___inet_pton+0x8 (/usr/lib64/libc-2.26.so)
              7fffa7d6fa54 gaih_inet.constprop.7+0xf44 (/usr/lib64/libc-2.26.so)
              7fffa7d705b4 getaddrinfo+0x164 (/usr/lib64/libc-2.26.so)
                 13fb52d70 _init+0xbfc (/usr/bin/ping)
              7fffa7c836a0 generic_start_main.isra.0+0x140 (/usr/lib64/libc-2.26.so)
              7fffa7c83898 __libc_start_main+0xb8 (/usr/lib64/libc-2.26.so)
                         0 [unknown] ([unknown])

Case 2 - Attaching a probe at _int_malloc+0x180 (binary offset 0x9cf10).
         Return address in still in LR and a new stack frame has already
         been allocated but not used. The caller's caller, i.e. the third
	 entry, is invalid and should be filtered out and not the second
	 one.

  # objdump -d /usr/lib64/libc-2.26.so | less
  ...
  000000000009cd90 <_int_malloc>:
     9cd90:       17 00 4c 3c     addis   r2,r12,23
     9cd94:       70 a3 42 38     addi    r2,r2,-23696
     9cd98:       26 00 80 7d     mfcr    r12
     9cd9c:       f8 ff e1 fb     std     r31,-8(r1)
     9cda0:       17 00 e4 3b     addi    r31,r4,23
     9cda4:       d8 ff 61 fb     std     r27,-40(r1)
     9cda8:       78 23 9b 7c     mr      r27,r4
     9cdac:       1f 00 bf 2b     cmpldi  cr7,r31,31
     9cdb0:       f0 ff c1 fb     std     r30,-16(r1)
     9cdb4:       b0 ff c1 fa     std     r22,-80(r1)
     9cdb8:       78 1b 7e 7c     mr      r30,r3
     9cdbc:       08 00 81 91     stw     r12,8(r1)
     9cdc0:       11 ff 21 f8     stdu    r1,-240(r1)
     9cdc4:       4c 01 9d 41     bgt     cr7,9cf10 <_int_malloc+0x180>
     9cdc8:       20 00 a4 2b     cmpldi  cr7,r4,32
  ...
     9cf08:       00 00 00 60     nop
     9cf0c:       00 00 42 60     ori     r2,r2,0
     9cf10:       e4 06 ff 7b     rldicr  r31,r31,0,59
     9cf14:       40 f8 a4 7f     cmpld   cr7,r4,r31
     9cf18:       68 05 9d 41     bgt     cr7,9d480 <_int_malloc+0x6f0>
  ...
  000000000009e3c0 <tcache_init.part.4>:
  ...
     9e420:       40 02 80 38     li      r4,576
     9e424:       78 fb e3 7f     mr      r3,r31
     9e428:       71 e9 ff 4b     bl      9cd98 <_int_malloc+0x8>
     9e42c:       00 00 a3 2f     cmpdi   cr7,r3,0
     9e430:       78 1b 7e 7c     mr      r30,r3
  ...
  000000000009f7a0 <__libc_malloc>:
  ...
     9f8f8:       00 00 89 2f     cmpwi   cr7,r9,0
     9f8fc:       1c ff 9e 40     bne     cr7,9f818 <__libc_malloc+0x78>
     9f900:       c9 ea ff 4b     bl      9e3c8 <tcache_init.part.4+0x8>
     9f904:       00 00 00 60     nop
     9f908:       e8 90 22 e9     ld      r9,-28440(r2)
  ...

  # perf probe -x /usr/lib64/libc-2.26.so -a _int_malloc+0x180
  # perf record -e probe_libc:_int_malloc -g ./test-malloc
  # perf script

Before:

  test-malloc  6554 [009] 515975.797403: probe_libc:_int_malloc: (7fffa6e6cf10)
              7fffa6e6cf10 _int_malloc+0x180 (/usr/lib64/libc-2.26.so)
              7fffa6dd0000 [unknown] (/usr/lib64/libc-2.26.so)
              7fffa6e6f904 malloc+0x164 (/usr/lib64/libc-2.26.so)
              7fffa6e6f9fc malloc+0x25c (/usr/lib64/libc-2.26.so)
                  100006b4 main+0x38 (/home/testuser/test-malloc)
              7fffa6df36a0 generic_start_main.isra.0+0x140 (/usr/lib64/libc-2.26.so)
              7fffa6df3898 __libc_start_main+0xb8 (/usr/lib64/libc-2.26.so)
                         0 [unknown] ([unknown])

After:

  test-malloc  6554 [009] 515975.797403: probe_libc:_int_malloc: (7fffa6e6cf10)
              7fffa6e6cf10 _int_malloc+0x180 (/usr/lib64/libc-2.26.so)
              7fffa6e6e42c tcache_init.part.4+0x6c (/usr/lib64/libc-2.26.so)
              7fffa6e6f904 malloc+0x164 (/usr/lib64/libc-2.26.so)
              7fffa6e6f9fc malloc+0x25c (/usr/lib64/libc-2.26.so)
                  100006b4 main+0x38 (/home/sandipan/test-malloc)
              7fffa6df36a0 generic_start_main.isra.0+0x140 (/usr/lib64/libc-2.26.so)
              7fffa6df3898 __libc_start_main+0xb8 (/usr/lib64/libc-2.26.so)
                         0 [unknown] ([unknown])

Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Maynard Johnson <maynard@us.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Fixes: a60335ba3298 ("perf tools powerpc: Adjust callchain based on DWARF debug info")
Link: http://lkml.kernel.org/r/24bb726d91ed173aebc972ec3f41a2ef2249434e.1530724939.git.sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/powerpc/util/skip-callchain-idx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index ef5d59a5742e..264fc0158100 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -246,7 +246,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 	if (!chain || chain->nr < 3)
 		return skip_slot;
 
-	ip = chain->ips[2];
+	ip = chain->ips[1];
 
 	thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
 
-- 
cgit v1.2.3


From 9068533e4f470daf2b0f29c71d865990acd8826e Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Tue, 10 Jul 2018 19:28:14 +0530
Subject: perf powerpc: Fix callchain ip filtering when return address is in a
 register

For powerpc64, perf will filter out the second entry in the callchain,
i.e. the LR value, if the return address of the function corresponding
to the probed location has already been saved on its caller's stack.

The state of the return address is determined using debug information.
At any point within a function, if the return address is already saved
somewhere, a DWARF expression can tell us about its location. If the
return address in still in LR only, no DWARF expression would exist.

Typically, the instructions in a function's prologue first copy the LR
value to R0 and then pushes R0 on to the stack. If LR has already been
copied to R0 but R0 is yet to be pushed to the stack, we can still get a
DWARF expression that says that the return address is in R0. This is
indicating that getting a DWARF expression for the return address does
not guarantee the fact that it has already been saved on the stack.

This can be observed on a powerpc64le system running Fedora 27 as shown
below.

  # objdump -d /usr/lib64/libc-2.26.so | less
  ...
  000000000015af20 <inet_pton>:
    15af20:       0b 00 4c 3c     addis   r2,r12,11
    15af24:       e0 c1 42 38     addi    r2,r2,-15904
    15af28:       a6 02 08 7c     mflr    r0
    15af2c:       f0 ff c1 fb     std     r30,-16(r1)
    15af30:       f8 ff e1 fb     std     r31,-8(r1)
    15af34:       78 1b 7f 7c     mr      r31,r3
    15af38:       78 23 83 7c     mr      r3,r4
    15af3c:       78 2b be 7c     mr      r30,r5
    15af40:       10 00 01 f8     std     r0,16(r1)
    15af44:       c1 ff 21 f8     stdu    r1,-64(r1)
    15af48:       28 00 81 f8     std     r4,40(r1)
  ...

  # readelf --debug-dump=frames-interp /usr/lib64/libc-2.26.so | less
  ...
  00027024 0000000000000024 00027028 FDE cie=00000000 pc=000000000015af20..000000000015af88
     LOC           CFA      r30   r31   ra
  000000000015af20 r1+0     u     u     u
  000000000015af34 r1+0     c-16  c-8   r0
  000000000015af48 r1+64    c-16  c-8   c+16
  000000000015af5c r1+0     c-16  c-8   c+16
  000000000015af78 r1+0     u     u
  ...

  # perf probe -x /usr/lib64/libc-2.26.so -a inet_pton+0x18
  # perf record -e probe_libc:inet_pton -g ping -6 -c 1 ::1
  # perf script

Before:

  ping  2829 [005] 512917.460174: probe_libc:inet_pton: (7fff7e2baf38)
              7fff7e2baf38 __GI___inet_pton+0x18 (/usr/lib64/libc-2.26.so)
              7fff7e2705b4 getaddrinfo+0x164 (/usr/lib64/libc-2.26.so)
                 12f152d70 _init+0xbfc (/usr/bin/ping)
              7fff7e1836a0 generic_start_main.isra.0+0x140 (/usr/lib64/libc-2.26.so)
              7fff7e183898 __libc_start_main+0xb8 (/usr/lib64/libc-2.26.so)
                         0 [unknown] ([unknown])

After:

  ping  2829 [005] 512917.460174: probe_libc:inet_pton: (7fff7e2baf38)
              7fff7e2baf38 __GI___inet_pton+0x18 (/usr/lib64/libc-2.26.so)
              7fff7e26fa54 gaih_inet.constprop.7+0xf44 (/usr/lib64/libc-2.26.so)
              7fff7e2705b4 getaddrinfo+0x164 (/usr/lib64/libc-2.26.so)
                 12f152d70 _init+0xbfc (/usr/bin/ping)
              7fff7e1836a0 generic_start_main.isra.0+0x140 (/usr/lib64/libc-2.26.so)
              7fff7e183898 __libc_start_main+0xb8 (/usr/lib64/libc-2.26.so)
                         0 [unknown] ([unknown])

Reported-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Maynard Johnson <maynard@us.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/66e848a7bdf2d43b39210a705ff6d828a0865661.1530724939.git.sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/powerpc/util/skip-callchain-idx.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index 264fc0158100..7c6eeb4633fe 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -58,9 +58,13 @@ static int check_return_reg(int ra_regno, Dwarf_Frame *frame)
 	}
 
 	/*
-	 * Check if return address is on the stack.
+	 * Check if return address is on the stack. If return address
+	 * is in a register (typically R0), it is yet to be saved on
+	 * the stack.
 	 */
-	if (nops != 0 || ops != NULL)
+	if ((nops != 0 || ops != NULL) &&
+		!(nops == 1 && ops[0].atom == DW_OP_regx &&
+			ops[0].number2 == 0 && ops[0].offset == 0))
 		return 0;
 
 	/*
-- 
cgit v1.2.3


From 3eae52f842329a95f8549124079518231c0daba8 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Tue, 10 Jul 2018 19:28:15 +0530
Subject: perf tests: Fix record+probe_libc_inet_pton.sh for powerpc64

For powerpc64, this test currently fails due to a mismatch in the
expected output.

This can be observed on a powerpc64le system running Fedora 27 as shown
below.

  # perf test -v "probe libc's inet_pton & backtrace it with ping"

Before:

  62: probe libc's inet_pton & backtrace it with ping       :
  --- start ---
  test child forked, pid 23948
  ping 23965 [003] 71136.075084: probe_libc:inet_pton: (7fff996aaf28)
  7fff996aaf28 __GI___inet_pton+0x8 (/usr/lib64/libc-2.26.so)
  7fff9965fa54 gaih_inet.constprop.7+0xf44 (/usr/lib64/libc-2.26.so)
  FAIL: expected backtrace entry 2 "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/libc-2.26.so\)$" got "7fff9965fa54 gaih_inet.constprop.7+0xf44 (/usr/lib64/libc-2.26.so)"
  test child finished with -1
  ---- end ----
  probe libc's inet_pton & backtrace it with ping: FAILED!

After:

  62: probe libc's inet_pton & backtrace it with ping       :
  --- start ---
  test child forked, pid 24638
  ping 24655 [001] 71208.525396: probe_libc:inet_pton: (7fffa245af28)
  7fffa245af28 __GI___inet_pton+0x8 (/usr/lib64/libc-2.26.so)
  7fffa240fa54 gaih_inet.constprop.7+0xf44 (/usr/lib64/libc-2.26.so)
  7fffa24105b4 getaddrinfo+0x164 (/usr/lib64/libc-2.26.so)
  138d52d70 main+0x3e0 (/usr/bin/ping)
  test child finished with 0
  ---- end ----
  probe libc's inet_pton & backtrace it with ping: Ok

Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Maynard Johnson <maynard@us.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com>
Fixes: e07d585e2454 ("perf tests: Switch trace+probe_libc_inet_pton to use record")
Link: http://lkml.kernel.org/r/49621ec5f37109f0655e5a8c32287ad68d85a1e5.1530724939.git.sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 94e513e62b34..1220e5e052bb 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -26,6 +26,12 @@ trace_libc_inet_pton_backtrace() {
 		echo "(__GI_)?getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 		echo "main\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
 		;;
+	ppc64|ppc64le)
+		eventattr='max-stack=4'
+		echo "gaih_inet.*\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
+		echo ".*\+0x[[:xdigit:]]+[[:space:]]\(.*/bin/ping.*\)$" >> $expected
+		;;
 	*)
 		eventattr='max-stack=3'
 		echo "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\($libc\)$" >> $expected
-- 
cgit v1.2.3


From 83e3b6d73e66a10088f362b08b99c36fec3a14e7 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Tue, 10 Jul 2018 19:28:16 +0530
Subject: perf tests: Fix record+probe_libc_inet_pton.sh to ensure cleanups

If there is a mismatch in the perf script output, this test fails and
exits before the event and temporary files created during its execution
are cleaned up.

This can be observed on a powerpc64 system running Fedora 27 as shown
below.

  # perf test -v "probe libc's inet_pton & backtrace it with ping"

  62: probe libc's inet_pton & backtrace it with ping       :
  --- start ---
  test child forked, pid 18655
  ping 18674 [013] 24511.496995: probe_libc:inet_pton: (7fffa6b423b0)
  7fffa6b423b0 __GI___inet_pton+0x0 (/usr/lib64/power8/libc-2.26.so)
  7fffa6af90dc gaih_inet.constprop.7+0xf4c (/usr/lib64/power8/libc-2.26.so)
  FAIL: expected backtrace entry "getaddrinfo\+0x[[:xdigit:]]+[[:space:]]\(/usr/lib64/power8/libc-2.26.so\)$" got "7fffa6af90dc gaih_inet.constprop.7+0xf4c (/usr/lib64/power8/libc-2.26.so)"
  test child finished with -1
  ---- end ----
  probe libc's inet_pton & backtrace it with ping: FAILED!

  # ls /tmp/expected.* /tmp/perf.data.* /tmp/perf.script.*

  /tmp/expected.u31  /tmp/perf.data.Pki  /tmp/perf.script.Bhs

  # perf probe --list

    probe_libc:inet_pton (on __inet_pton@resolv/inet_pton.c in /usr/lib64/power8/libc-2.26.so)

Cleanup of the event and the temporary files are now ensured by allowing
the cleanup code to be executed even if the lines from the backtrace do
not match their expected patterns instead of simply exiting from the
point of failure.

Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/ce9fb091dd3028fba8749a1a267cfbcb264bbfb1.1530724939.git.sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/shell/record+probe_libc_inet_pton.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 1220e5e052bb..0502a9e04c79 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -52,7 +52,7 @@ trace_libc_inet_pton_backtrace() {
 		echo "$line" | egrep -q "$pattern"
 		if [ $? -ne 0 ] ; then
 			printf "FAIL: expected backtrace entry \"%s\" got \"%s\"\n" "$pattern" "$line"
-			exit 1
+			return 1
 		fi
 	done
 
-- 
cgit v1.2.3


From 60089e42d38438772e2f83334e3e5b7497009366 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Tue, 10 Jul 2018 19:28:17 +0530
Subject: perf tests: Fix record+probe_libc_inet_pton.sh when event exists

If the event 'probe_libc:inet_pton' already exists, this test fails and
deletes the existing event before exiting. This will then pass for any
subsequent executions.

Instead of skipping to deleting the existing event because of failing to
add a new event, a duplicate event is now created and the script
continues with the usual checks. Only the new duplicate event that is
created at the beginning of the test is deleted as a part of the
cleanups in the end. All existing events remain as it is.

This can be observed on a powerpc64 system running Fedora 27 as shown
below.

  # perf probe -x /usr/lib64/power8/libc-2.26.so -a inet_pton

  Added new event:
    probe_libc:inet_pton (on inet_pton in /usr/lib64/power8/libc-2.26.so)

Before:

  # perf test -v "probe libc's inet_pton & backtrace it with ping"

  62: probe libc's inet_pton & backtrace it with ping       :
  --- start ---
  test child forked, pid 21302
  test child finished with -1
  ---- end ----
  probe libc's inet_pton & backtrace it with ping: FAILED!

  # perf probe --list

After:

  # perf test -v "probe libc's inet_pton & backtrace it with ping"

  62: probe libc's inet_pton & backtrace it with ping       :
  --- start ---
  test child forked, pid 21490
  ping 21513 [035] 39357.565561: probe_libc:inet_pton_1: (7fffa4c623b0)
  7fffa4c623b0 __GI___inet_pton+0x0 (/usr/lib64/power8/libc-2.26.so)
  7fffa4c190dc gaih_inet.constprop.7+0xf4c (/usr/lib64/power8/libc-2.26.so)
  7fffa4c19c4c getaddrinfo+0x15c (/usr/lib64/power8/libc-2.26.so)
  111d93c20 main+0x3e0 (/usr/bin/ping)
  test child finished with 0
  ---- end ----
  probe libc's inet_pton & backtrace it with ping: Ok

  # perf probe --list

    probe_libc:inet_pton (on __inet_pton@resolv/inet_pton.c in /usr/lib64/power8/libc-2.26.so)

Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/e11fecff96e6cf4c65cdbd9012463513d7b8356c.1530724939.git.sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../tests/shell/record+probe_libc_inet_pton.sh     | 28 ++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index 0502a9e04c79..3013ac8f83d0 100755
--- a/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -13,11 +13,24 @@
 libc=$(grep -w libc /proc/self/maps | head -1 | sed -r 's/.*[[:space:]](\/.*)/\1/g')
 nm -Dg $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
+event_pattern='probe_libc:inet_pton(\_[[:digit:]]+)?'
+
+add_libc_inet_pton_event() {
+
+	event_name=$(perf probe -f -x $libc -a inet_pton 2>&1 | tail -n +2 | head -n -5 | \
+			grep -P -o "$event_pattern(?=[[:space:]]\(on inet_pton in $libc\))")
+
+	if [ $? -ne 0 -o -z "$event_name" ] ; then
+		printf "FAIL: could not add event\n"
+		return 1
+	fi
+}
+
 trace_libc_inet_pton_backtrace() {
 
 	expected=`mktemp -u /tmp/expected.XXX`
 
-	echo "ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)" > $expected
+	echo "ping[][0-9 \.:]+$event_name: \([[:xdigit:]]+\)" > $expected
 	echo ".*inet_pton\+0x[[:xdigit:]]+[[:space:]]\($libc|inlined\)$" >> $expected
 	case "$(uname -m)" in
 	s390x)
@@ -41,7 +54,7 @@ trace_libc_inet_pton_backtrace() {
 
 	perf_data=`mktemp -u /tmp/perf.data.XXX`
 	perf_script=`mktemp -u /tmp/perf.script.XXX`
-	perf record -e probe_libc:inet_pton/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf record -e $event_name/$eventattr/ -o $perf_data ping -6 -c 1 ::1 > /dev/null 2>&1
 	perf script -i $perf_data > $perf_script
 
 	exec 3<$perf_script
@@ -62,13 +75,20 @@ trace_libc_inet_pton_backtrace() {
 	# even if the perf script output does not match.
 }
 
+delete_libc_inet_pton_event() {
+
+	if [ -n "$event_name" ] ; then
+		perf probe -q -d $event_name
+	fi
+}
+
 # Check for IPv6 interface existence
 ip a sh lo | fgrep -q inet6 || exit 2
 
 skip_if_no_perf_probe && \
-perf probe -q $libc inet_pton && \
+add_libc_inet_pton_event && \
 trace_libc_inet_pton_backtrace
 err=$?
 rm -f ${perf_data} ${perf_script} ${expected}
-perf probe -q -d probe_libc:inet_pton
+delete_libc_inet_pton_event
 exit $err
-- 
cgit v1.2.3


From 34b009cfde2b8ce20a69c7bfd6bad4ce0e7cd970 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@arm.com>
Date: Fri, 6 Jul 2018 16:34:34 -0500
Subject: tools include: Grab copies of arm64 dependent unistd.h files

Will be used for generating the syscall id/string translation table.

The arm64 unistd.h file simply #includes the asm-generic/unistd.h, so,
since we will want to know whether either change, we grab both:

  arch/arm64/include/uapi/asm/unistd.h

and

  include/uapi/asm-generic/unistd.h

Signed-off-by: Kim Phillips <kim.phillips@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20180706163434.1b64ffbcc0284fb79982f53b@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm64/include/uapi/asm/unistd.h |  20 +
 tools/include/uapi/asm-generic/unistd.h    | 783 +++++++++++++++++++++++++++++
 tools/perf/check-headers.sh                |   2 +
 3 files changed, 805 insertions(+)
 create mode 100644 tools/arch/arm64/include/uapi/asm/unistd.h
 create mode 100644 tools/include/uapi/asm-generic/unistd.h

diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..5072cbd15c82
--- /dev/null
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/*
+ * Copyright (C) 2012 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define __ARCH_WANT_RENAMEAT
+
+#include <asm-generic/unistd.h>
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
new file mode 100644
index 000000000000..42990676a55e
--- /dev/null
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -0,0 +1,783 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#include <asm/bitsperlong.h>
+
+/*
+ * This file contains the system call numbers, based on the
+ * layout of the x86-64 architecture, which embeds the
+ * pointer to the syscall in the table.
+ *
+ * As a basic principle, no duplication of functionality
+ * should be added, e.g. we don't use lseek when llseek
+ * is present. New architectures should use this file
+ * and implement the less feature-full calls in user space.
+ */
+
+#ifndef __SYSCALL
+#define __SYSCALL(x, y)
+#endif
+
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
+#else
+#define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
+#endif
+
+#ifdef __SYSCALL_COMPAT
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _comp)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SYSCALL(_nr, _comp)
+#else
+#define __SC_COMP(_nr, _sys, _comp) __SYSCALL(_nr, _sys)
+#define __SC_COMP_3264(_nr, _32, _64, _comp) __SC_3264(_nr, _32, _64)
+#endif
+
+#define __NR_io_setup 0
+__SC_COMP(__NR_io_setup, sys_io_setup, compat_sys_io_setup)
+#define __NR_io_destroy 1
+__SYSCALL(__NR_io_destroy, sys_io_destroy)
+#define __NR_io_submit 2
+__SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
+#define __NR_io_cancel 3
+__SYSCALL(__NR_io_cancel, sys_io_cancel)
+#define __NR_io_getevents 4
+__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+
+/* fs/xattr.c */
+#define __NR_setxattr 5
+__SYSCALL(__NR_setxattr, sys_setxattr)
+#define __NR_lsetxattr 6
+__SYSCALL(__NR_lsetxattr, sys_lsetxattr)
+#define __NR_fsetxattr 7
+__SYSCALL(__NR_fsetxattr, sys_fsetxattr)
+#define __NR_getxattr 8
+__SYSCALL(__NR_getxattr, sys_getxattr)
+#define __NR_lgetxattr 9
+__SYSCALL(__NR_lgetxattr, sys_lgetxattr)
+#define __NR_fgetxattr 10
+__SYSCALL(__NR_fgetxattr, sys_fgetxattr)
+#define __NR_listxattr 11
+__SYSCALL(__NR_listxattr, sys_listxattr)
+#define __NR_llistxattr 12
+__SYSCALL(__NR_llistxattr, sys_llistxattr)
+#define __NR_flistxattr 13
+__SYSCALL(__NR_flistxattr, sys_flistxattr)
+#define __NR_removexattr 14
+__SYSCALL(__NR_removexattr, sys_removexattr)
+#define __NR_lremovexattr 15
+__SYSCALL(__NR_lremovexattr, sys_lremovexattr)
+#define __NR_fremovexattr 16
+__SYSCALL(__NR_fremovexattr, sys_fremovexattr)
+
+/* fs/dcache.c */
+#define __NR_getcwd 17
+__SYSCALL(__NR_getcwd, sys_getcwd)
+
+/* fs/cookies.c */
+#define __NR_lookup_dcookie 18
+__SC_COMP(__NR_lookup_dcookie, sys_lookup_dcookie, compat_sys_lookup_dcookie)
+
+/* fs/eventfd.c */
+#define __NR_eventfd2 19
+__SYSCALL(__NR_eventfd2, sys_eventfd2)
+
+/* fs/eventpoll.c */
+#define __NR_epoll_create1 20
+__SYSCALL(__NR_epoll_create1, sys_epoll_create1)
+#define __NR_epoll_ctl 21
+__SYSCALL(__NR_epoll_ctl, sys_epoll_ctl)
+#define __NR_epoll_pwait 22
+__SC_COMP(__NR_epoll_pwait, sys_epoll_pwait, compat_sys_epoll_pwait)
+
+/* fs/fcntl.c */
+#define __NR_dup 23
+__SYSCALL(__NR_dup, sys_dup)
+#define __NR_dup3 24
+__SYSCALL(__NR_dup3, sys_dup3)
+#define __NR3264_fcntl 25
+__SC_COMP_3264(__NR3264_fcntl, sys_fcntl64, sys_fcntl, compat_sys_fcntl64)
+
+/* fs/inotify_user.c */
+#define __NR_inotify_init1 26
+__SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_inotify_add_watch 27
+__SYSCALL(__NR_inotify_add_watch, sys_inotify_add_watch)
+#define __NR_inotify_rm_watch 28
+__SYSCALL(__NR_inotify_rm_watch, sys_inotify_rm_watch)
+
+/* fs/ioctl.c */
+#define __NR_ioctl 29
+__SC_COMP(__NR_ioctl, sys_ioctl, compat_sys_ioctl)
+
+/* fs/ioprio.c */
+#define __NR_ioprio_set 30
+__SYSCALL(__NR_ioprio_set, sys_ioprio_set)
+#define __NR_ioprio_get 31
+__SYSCALL(__NR_ioprio_get, sys_ioprio_get)
+
+/* fs/locks.c */
+#define __NR_flock 32
+__SYSCALL(__NR_flock, sys_flock)
+
+/* fs/namei.c */
+#define __NR_mknodat 33
+__SYSCALL(__NR_mknodat, sys_mknodat)
+#define __NR_mkdirat 34
+__SYSCALL(__NR_mkdirat, sys_mkdirat)
+#define __NR_unlinkat 35
+__SYSCALL(__NR_unlinkat, sys_unlinkat)
+#define __NR_symlinkat 36
+__SYSCALL(__NR_symlinkat, sys_symlinkat)
+#define __NR_linkat 37
+__SYSCALL(__NR_linkat, sys_linkat)
+#ifdef __ARCH_WANT_RENAMEAT
+/* renameat is superseded with flags by renameat2 */
+#define __NR_renameat 38
+__SYSCALL(__NR_renameat, sys_renameat)
+#endif /* __ARCH_WANT_RENAMEAT */
+
+/* fs/namespace.c */
+#define __NR_umount2 39
+__SYSCALL(__NR_umount2, sys_umount)
+#define __NR_mount 40
+__SC_COMP(__NR_mount, sys_mount, compat_sys_mount)
+#define __NR_pivot_root 41
+__SYSCALL(__NR_pivot_root, sys_pivot_root)
+
+/* fs/nfsctl.c */
+#define __NR_nfsservctl 42
+__SYSCALL(__NR_nfsservctl, sys_ni_syscall)
+
+/* fs/open.c */
+#define __NR3264_statfs 43
+__SC_COMP_3264(__NR3264_statfs, sys_statfs64, sys_statfs, \
+	       compat_sys_statfs64)
+#define __NR3264_fstatfs 44
+__SC_COMP_3264(__NR3264_fstatfs, sys_fstatfs64, sys_fstatfs, \
+	       compat_sys_fstatfs64)
+#define __NR3264_truncate 45
+__SC_COMP_3264(__NR3264_truncate, sys_truncate64, sys_truncate, \
+	       compat_sys_truncate64)
+#define __NR3264_ftruncate 46
+__SC_COMP_3264(__NR3264_ftruncate, sys_ftruncate64, sys_ftruncate, \
+	       compat_sys_ftruncate64)
+
+#define __NR_fallocate 47
+__SC_COMP(__NR_fallocate, sys_fallocate, compat_sys_fallocate)
+#define __NR_faccessat 48
+__SYSCALL(__NR_faccessat, sys_faccessat)
+#define __NR_chdir 49
+__SYSCALL(__NR_chdir, sys_chdir)
+#define __NR_fchdir 50
+__SYSCALL(__NR_fchdir, sys_fchdir)
+#define __NR_chroot 51
+__SYSCALL(__NR_chroot, sys_chroot)
+#define __NR_fchmod 52
+__SYSCALL(__NR_fchmod, sys_fchmod)
+#define __NR_fchmodat 53
+__SYSCALL(__NR_fchmodat, sys_fchmodat)
+#define __NR_fchownat 54
+__SYSCALL(__NR_fchownat, sys_fchownat)
+#define __NR_fchown 55
+__SYSCALL(__NR_fchown, sys_fchown)
+#define __NR_openat 56
+__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+#define __NR_close 57
+__SYSCALL(__NR_close, sys_close)
+#define __NR_vhangup 58
+__SYSCALL(__NR_vhangup, sys_vhangup)
+
+/* fs/pipe.c */
+#define __NR_pipe2 59
+__SYSCALL(__NR_pipe2, sys_pipe2)
+
+/* fs/quota.c */
+#define __NR_quotactl 60
+__SYSCALL(__NR_quotactl, sys_quotactl)
+
+/* fs/readdir.c */
+#define __NR_getdents64 61
+__SYSCALL(__NR_getdents64, sys_getdents64)
+
+/* fs/read_write.c */
+#define __NR3264_lseek 62
+__SC_3264(__NR3264_lseek, sys_llseek, sys_lseek)
+#define __NR_read 63
+__SYSCALL(__NR_read, sys_read)
+#define __NR_write 64
+__SYSCALL(__NR_write, sys_write)
+#define __NR_readv 65
+__SC_COMP(__NR_readv, sys_readv, compat_sys_readv)
+#define __NR_writev 66
+__SC_COMP(__NR_writev, sys_writev, compat_sys_writev)
+#define __NR_pread64 67
+__SC_COMP(__NR_pread64, sys_pread64, compat_sys_pread64)
+#define __NR_pwrite64 68
+__SC_COMP(__NR_pwrite64, sys_pwrite64, compat_sys_pwrite64)
+#define __NR_preadv 69
+__SC_COMP(__NR_preadv, sys_preadv, compat_sys_preadv)
+#define __NR_pwritev 70
+__SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
+
+/* fs/sendfile.c */
+#define __NR3264_sendfile 71
+__SYSCALL(__NR3264_sendfile, sys_sendfile64)
+
+/* fs/select.c */
+#define __NR_pselect6 72
+__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+#define __NR_ppoll 73
+__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+
+/* fs/signalfd.c */
+#define __NR_signalfd4 74
+__SC_COMP(__NR_signalfd4, sys_signalfd4, compat_sys_signalfd4)
+
+/* fs/splice.c */
+#define __NR_vmsplice 75
+__SC_COMP(__NR_vmsplice, sys_vmsplice, compat_sys_vmsplice)
+#define __NR_splice 76
+__SYSCALL(__NR_splice, sys_splice)
+#define __NR_tee 77
+__SYSCALL(__NR_tee, sys_tee)
+
+/* fs/stat.c */
+#define __NR_readlinkat 78
+__SYSCALL(__NR_readlinkat, sys_readlinkat)
+#define __NR3264_fstatat 79
+__SC_3264(__NR3264_fstatat, sys_fstatat64, sys_newfstatat)
+#define __NR3264_fstat 80
+__SC_3264(__NR3264_fstat, sys_fstat64, sys_newfstat)
+
+/* fs/sync.c */
+#define __NR_sync 81
+__SYSCALL(__NR_sync, sys_sync)
+#define __NR_fsync 82
+__SYSCALL(__NR_fsync, sys_fsync)
+#define __NR_fdatasync 83
+__SYSCALL(__NR_fdatasync, sys_fdatasync)
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SC_COMP(__NR_sync_file_range2, sys_sync_file_range2, \
+	  compat_sys_sync_file_range2)
+#else
+#define __NR_sync_file_range 84
+__SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
+	  compat_sys_sync_file_range)
+#endif
+
+/* fs/timerfd.c */
+#define __NR_timerfd_create 85
+__SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#define __NR_timerfd_settime 86
+__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
+	  compat_sys_timerfd_settime)
+#define __NR_timerfd_gettime 87
+__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
+	  compat_sys_timerfd_gettime)
+
+/* fs/utimes.c */
+#define __NR_utimensat 88
+__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+
+/* kernel/acct.c */
+#define __NR_acct 89
+__SYSCALL(__NR_acct, sys_acct)
+
+/* kernel/capability.c */
+#define __NR_capget 90
+__SYSCALL(__NR_capget, sys_capget)
+#define __NR_capset 91
+__SYSCALL(__NR_capset, sys_capset)
+
+/* kernel/exec_domain.c */
+#define __NR_personality 92
+__SYSCALL(__NR_personality, sys_personality)
+
+/* kernel/exit.c */
+#define __NR_exit 93
+__SYSCALL(__NR_exit, sys_exit)
+#define __NR_exit_group 94
+__SYSCALL(__NR_exit_group, sys_exit_group)
+#define __NR_waitid 95
+__SC_COMP(__NR_waitid, sys_waitid, compat_sys_waitid)
+
+/* kernel/fork.c */
+#define __NR_set_tid_address 96
+__SYSCALL(__NR_set_tid_address, sys_set_tid_address)
+#define __NR_unshare 97
+__SYSCALL(__NR_unshare, sys_unshare)
+
+/* kernel/futex.c */
+#define __NR_futex 98
+__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+#define __NR_set_robust_list 99
+__SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
+	  compat_sys_set_robust_list)
+#define __NR_get_robust_list 100
+__SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
+	  compat_sys_get_robust_list)
+
+/* kernel/hrtimer.c */
+#define __NR_nanosleep 101
+__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+
+/* kernel/itimer.c */
+#define __NR_getitimer 102
+__SC_COMP(__NR_getitimer, sys_getitimer, compat_sys_getitimer)
+#define __NR_setitimer 103
+__SC_COMP(__NR_setitimer, sys_setitimer, compat_sys_setitimer)
+
+/* kernel/kexec.c */
+#define __NR_kexec_load 104
+__SC_COMP(__NR_kexec_load, sys_kexec_load, compat_sys_kexec_load)
+
+/* kernel/module.c */
+#define __NR_init_module 105
+__SYSCALL(__NR_init_module, sys_init_module)
+#define __NR_delete_module 106
+__SYSCALL(__NR_delete_module, sys_delete_module)
+
+/* kernel/posix-timers.c */
+#define __NR_timer_create 107
+__SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#define __NR_timer_gettime 108
+__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+#define __NR_timer_getoverrun 109
+__SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#define __NR_timer_settime 110
+__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+#define __NR_timer_delete 111
+__SYSCALL(__NR_timer_delete, sys_timer_delete)
+#define __NR_clock_settime 112
+__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+#define __NR_clock_gettime 113
+__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+#define __NR_clock_getres 114
+__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+#define __NR_clock_nanosleep 115
+__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
+	  compat_sys_clock_nanosleep)
+
+/* kernel/printk.c */
+#define __NR_syslog 116
+__SYSCALL(__NR_syslog, sys_syslog)
+
+/* kernel/ptrace.c */
+#define __NR_ptrace 117
+__SYSCALL(__NR_ptrace, sys_ptrace)
+
+/* kernel/sched/core.c */
+#define __NR_sched_setparam 118
+__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
+#define __NR_sched_setscheduler 119
+__SYSCALL(__NR_sched_setscheduler, sys_sched_setscheduler)
+#define __NR_sched_getscheduler 120
+__SYSCALL(__NR_sched_getscheduler, sys_sched_getscheduler)
+#define __NR_sched_getparam 121
+__SYSCALL(__NR_sched_getparam, sys_sched_getparam)
+#define __NR_sched_setaffinity 122
+__SC_COMP(__NR_sched_setaffinity, sys_sched_setaffinity, \
+	  compat_sys_sched_setaffinity)
+#define __NR_sched_getaffinity 123
+__SC_COMP(__NR_sched_getaffinity, sys_sched_getaffinity, \
+	  compat_sys_sched_getaffinity)
+#define __NR_sched_yield 124
+__SYSCALL(__NR_sched_yield, sys_sched_yield)
+#define __NR_sched_get_priority_max 125
+__SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
+#define __NR_sched_get_priority_min 126
+__SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#define __NR_sched_rr_get_interval 127
+__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
+	  compat_sys_sched_rr_get_interval)
+
+/* kernel/signal.c */
+#define __NR_restart_syscall 128
+__SYSCALL(__NR_restart_syscall, sys_restart_syscall)
+#define __NR_kill 129
+__SYSCALL(__NR_kill, sys_kill)
+#define __NR_tkill 130
+__SYSCALL(__NR_tkill, sys_tkill)
+#define __NR_tgkill 131
+__SYSCALL(__NR_tgkill, sys_tgkill)
+#define __NR_sigaltstack 132
+__SC_COMP(__NR_sigaltstack, sys_sigaltstack, compat_sys_sigaltstack)
+#define __NR_rt_sigsuspend 133
+__SC_COMP(__NR_rt_sigsuspend, sys_rt_sigsuspend, compat_sys_rt_sigsuspend)
+#define __NR_rt_sigaction 134
+__SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
+#define __NR_rt_sigprocmask 135
+__SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
+#define __NR_rt_sigpending 136
+__SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#define __NR_rt_sigtimedwait 137
+__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
+	  compat_sys_rt_sigtimedwait)
+#define __NR_rt_sigqueueinfo 138
+__SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
+	  compat_sys_rt_sigqueueinfo)
+#define __NR_rt_sigreturn 139
+__SC_COMP(__NR_rt_sigreturn, sys_rt_sigreturn, compat_sys_rt_sigreturn)
+
+/* kernel/sys.c */
+#define __NR_setpriority 140
+__SYSCALL(__NR_setpriority, sys_setpriority)
+#define __NR_getpriority 141
+__SYSCALL(__NR_getpriority, sys_getpriority)
+#define __NR_reboot 142
+__SYSCALL(__NR_reboot, sys_reboot)
+#define __NR_setregid 143
+__SYSCALL(__NR_setregid, sys_setregid)
+#define __NR_setgid 144
+__SYSCALL(__NR_setgid, sys_setgid)
+#define __NR_setreuid 145
+__SYSCALL(__NR_setreuid, sys_setreuid)
+#define __NR_setuid 146
+__SYSCALL(__NR_setuid, sys_setuid)
+#define __NR_setresuid 147
+__SYSCALL(__NR_setresuid, sys_setresuid)
+#define __NR_getresuid 148
+__SYSCALL(__NR_getresuid, sys_getresuid)
+#define __NR_setresgid 149
+__SYSCALL(__NR_setresgid, sys_setresgid)
+#define __NR_getresgid 150
+__SYSCALL(__NR_getresgid, sys_getresgid)
+#define __NR_setfsuid 151
+__SYSCALL(__NR_setfsuid, sys_setfsuid)
+#define __NR_setfsgid 152
+__SYSCALL(__NR_setfsgid, sys_setfsgid)
+#define __NR_times 153
+__SC_COMP(__NR_times, sys_times, compat_sys_times)
+#define __NR_setpgid 154
+__SYSCALL(__NR_setpgid, sys_setpgid)
+#define __NR_getpgid 155
+__SYSCALL(__NR_getpgid, sys_getpgid)
+#define __NR_getsid 156
+__SYSCALL(__NR_getsid, sys_getsid)
+#define __NR_setsid 157
+__SYSCALL(__NR_setsid, sys_setsid)
+#define __NR_getgroups 158
+__SYSCALL(__NR_getgroups, sys_getgroups)
+#define __NR_setgroups 159
+__SYSCALL(__NR_setgroups, sys_setgroups)
+#define __NR_uname 160
+__SYSCALL(__NR_uname, sys_newuname)
+#define __NR_sethostname 161
+__SYSCALL(__NR_sethostname, sys_sethostname)
+#define __NR_setdomainname 162
+__SYSCALL(__NR_setdomainname, sys_setdomainname)
+#define __NR_getrlimit 163
+__SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
+#define __NR_setrlimit 164
+__SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#define __NR_getrusage 165
+__SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
+#define __NR_umask 166
+__SYSCALL(__NR_umask, sys_umask)
+#define __NR_prctl 167
+__SYSCALL(__NR_prctl, sys_prctl)
+#define __NR_getcpu 168
+__SYSCALL(__NR_getcpu, sys_getcpu)
+
+/* kernel/time.c */
+#define __NR_gettimeofday 169
+__SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
+#define __NR_settimeofday 170
+__SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
+#define __NR_adjtimex 171
+__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+
+/* kernel/timer.c */
+#define __NR_getpid 172
+__SYSCALL(__NR_getpid, sys_getpid)
+#define __NR_getppid 173
+__SYSCALL(__NR_getppid, sys_getppid)
+#define __NR_getuid 174
+__SYSCALL(__NR_getuid, sys_getuid)
+#define __NR_geteuid 175
+__SYSCALL(__NR_geteuid, sys_geteuid)
+#define __NR_getgid 176
+__SYSCALL(__NR_getgid, sys_getgid)
+#define __NR_getegid 177
+__SYSCALL(__NR_getegid, sys_getegid)
+#define __NR_gettid 178
+__SYSCALL(__NR_gettid, sys_gettid)
+#define __NR_sysinfo 179
+__SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
+
+/* ipc/mqueue.c */
+#define __NR_mq_open 180
+__SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
+#define __NR_mq_unlink 181
+__SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#define __NR_mq_timedsend 182
+__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+#define __NR_mq_timedreceive 183
+__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
+	  compat_sys_mq_timedreceive)
+#define __NR_mq_notify 184
+__SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
+#define __NR_mq_getsetattr 185
+__SC_COMP(__NR_mq_getsetattr, sys_mq_getsetattr, compat_sys_mq_getsetattr)
+
+/* ipc/msg.c */
+#define __NR_msgget 186
+__SYSCALL(__NR_msgget, sys_msgget)
+#define __NR_msgctl 187
+__SC_COMP(__NR_msgctl, sys_msgctl, compat_sys_msgctl)
+#define __NR_msgrcv 188
+__SC_COMP(__NR_msgrcv, sys_msgrcv, compat_sys_msgrcv)
+#define __NR_msgsnd 189
+__SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
+
+/* ipc/sem.c */
+#define __NR_semget 190
+__SYSCALL(__NR_semget, sys_semget)
+#define __NR_semctl 191
+__SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#define __NR_semtimedop 192
+__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+#define __NR_semop 193
+__SYSCALL(__NR_semop, sys_semop)
+
+/* ipc/shm.c */
+#define __NR_shmget 194
+__SYSCALL(__NR_shmget, sys_shmget)
+#define __NR_shmctl 195
+__SC_COMP(__NR_shmctl, sys_shmctl, compat_sys_shmctl)
+#define __NR_shmat 196
+__SC_COMP(__NR_shmat, sys_shmat, compat_sys_shmat)
+#define __NR_shmdt 197
+__SYSCALL(__NR_shmdt, sys_shmdt)
+
+/* net/socket.c */
+#define __NR_socket 198
+__SYSCALL(__NR_socket, sys_socket)
+#define __NR_socketpair 199
+__SYSCALL(__NR_socketpair, sys_socketpair)
+#define __NR_bind 200
+__SYSCALL(__NR_bind, sys_bind)
+#define __NR_listen 201
+__SYSCALL(__NR_listen, sys_listen)
+#define __NR_accept 202
+__SYSCALL(__NR_accept, sys_accept)
+#define __NR_connect 203
+__SYSCALL(__NR_connect, sys_connect)
+#define __NR_getsockname 204
+__SYSCALL(__NR_getsockname, sys_getsockname)
+#define __NR_getpeername 205
+__SYSCALL(__NR_getpeername, sys_getpeername)
+#define __NR_sendto 206
+__SYSCALL(__NR_sendto, sys_sendto)
+#define __NR_recvfrom 207
+__SC_COMP(__NR_recvfrom, sys_recvfrom, compat_sys_recvfrom)
+#define __NR_setsockopt 208
+__SC_COMP(__NR_setsockopt, sys_setsockopt, compat_sys_setsockopt)
+#define __NR_getsockopt 209
+__SC_COMP(__NR_getsockopt, sys_getsockopt, compat_sys_getsockopt)
+#define __NR_shutdown 210
+__SYSCALL(__NR_shutdown, sys_shutdown)
+#define __NR_sendmsg 211
+__SC_COMP(__NR_sendmsg, sys_sendmsg, compat_sys_sendmsg)
+#define __NR_recvmsg 212
+__SC_COMP(__NR_recvmsg, sys_recvmsg, compat_sys_recvmsg)
+
+/* mm/filemap.c */
+#define __NR_readahead 213
+__SC_COMP(__NR_readahead, sys_readahead, compat_sys_readahead)
+
+/* mm/nommu.c, also with MMU */
+#define __NR_brk 214
+__SYSCALL(__NR_brk, sys_brk)
+#define __NR_munmap 215
+__SYSCALL(__NR_munmap, sys_munmap)
+#define __NR_mremap 216
+__SYSCALL(__NR_mremap, sys_mremap)
+
+/* security/keys/keyctl.c */
+#define __NR_add_key 217
+__SYSCALL(__NR_add_key, sys_add_key)
+#define __NR_request_key 218
+__SYSCALL(__NR_request_key, sys_request_key)
+#define __NR_keyctl 219
+__SC_COMP(__NR_keyctl, sys_keyctl, compat_sys_keyctl)
+
+/* arch/example/kernel/sys_example.c */
+#define __NR_clone 220
+__SYSCALL(__NR_clone, sys_clone)
+#define __NR_execve 221
+__SC_COMP(__NR_execve, sys_execve, compat_sys_execve)
+
+#define __NR3264_mmap 222
+__SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
+/* mm/fadvise.c */
+#define __NR3264_fadvise64 223
+__SC_COMP(__NR3264_fadvise64, sys_fadvise64_64, compat_sys_fadvise64_64)
+
+/* mm/, CONFIG_MMU only */
+#ifndef __ARCH_NOMMU
+#define __NR_swapon 224
+__SYSCALL(__NR_swapon, sys_swapon)
+#define __NR_swapoff 225
+__SYSCALL(__NR_swapoff, sys_swapoff)
+#define __NR_mprotect 226
+__SYSCALL(__NR_mprotect, sys_mprotect)
+#define __NR_msync 227
+__SYSCALL(__NR_msync, sys_msync)
+#define __NR_mlock 228
+__SYSCALL(__NR_mlock, sys_mlock)
+#define __NR_munlock 229
+__SYSCALL(__NR_munlock, sys_munlock)
+#define __NR_mlockall 230
+__SYSCALL(__NR_mlockall, sys_mlockall)
+#define __NR_munlockall 231
+__SYSCALL(__NR_munlockall, sys_munlockall)
+#define __NR_mincore 232
+__SYSCALL(__NR_mincore, sys_mincore)
+#define __NR_madvise 233
+__SYSCALL(__NR_madvise, sys_madvise)
+#define __NR_remap_file_pages 234
+__SYSCALL(__NR_remap_file_pages, sys_remap_file_pages)
+#define __NR_mbind 235
+__SC_COMP(__NR_mbind, sys_mbind, compat_sys_mbind)
+#define __NR_get_mempolicy 236
+__SC_COMP(__NR_get_mempolicy, sys_get_mempolicy, compat_sys_get_mempolicy)
+#define __NR_set_mempolicy 237
+__SC_COMP(__NR_set_mempolicy, sys_set_mempolicy, compat_sys_set_mempolicy)
+#define __NR_migrate_pages 238
+__SC_COMP(__NR_migrate_pages, sys_migrate_pages, compat_sys_migrate_pages)
+#define __NR_move_pages 239
+__SC_COMP(__NR_move_pages, sys_move_pages, compat_sys_move_pages)
+#endif
+
+#define __NR_rt_tgsigqueueinfo 240
+__SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
+	  compat_sys_rt_tgsigqueueinfo)
+#define __NR_perf_event_open 241
+__SYSCALL(__NR_perf_event_open, sys_perf_event_open)
+#define __NR_accept4 242
+__SYSCALL(__NR_accept4, sys_accept4)
+#define __NR_recvmmsg 243
+__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#define __NR_wait4 260
+__SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+#define __NR_name_to_handle_at         264
+__SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
+#define __NR_open_by_handle_at         265
+__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
+	  compat_sys_open_by_handle_at)
+#define __NR_clock_adjtime 266
+__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+#define __NR_syncfs 267
+__SYSCALL(__NR_syncfs, sys_syncfs)
+#define __NR_setns 268
+__SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
+#define __NR_process_vm_readv 270
+__SC_COMP(__NR_process_vm_readv, sys_process_vm_readv, \
+          compat_sys_process_vm_readv)
+#define __NR_process_vm_writev 271
+__SC_COMP(__NR_process_vm_writev, sys_process_vm_writev, \
+          compat_sys_process_vm_writev)
+#define __NR_kcmp 272
+__SYSCALL(__NR_kcmp, sys_kcmp)
+#define __NR_finit_module 273
+__SYSCALL(__NR_finit_module, sys_finit_module)
+#define __NR_sched_setattr 274
+__SYSCALL(__NR_sched_setattr, sys_sched_setattr)
+#define __NR_sched_getattr 275
+__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
+#define __NR_renameat2 276
+__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_seccomp 277
+__SYSCALL(__NR_seccomp, sys_seccomp)
+#define __NR_getrandom 278
+__SYSCALL(__NR_getrandom, sys_getrandom)
+#define __NR_memfd_create 279
+__SYSCALL(__NR_memfd_create, sys_memfd_create)
+#define __NR_bpf 280
+__SYSCALL(__NR_bpf, sys_bpf)
+#define __NR_execveat 281
+__SC_COMP(__NR_execveat, sys_execveat, compat_sys_execveat)
+#define __NR_userfaultfd 282
+__SYSCALL(__NR_userfaultfd, sys_userfaultfd)
+#define __NR_membarrier 283
+__SYSCALL(__NR_membarrier, sys_membarrier)
+#define __NR_mlock2 284
+__SYSCALL(__NR_mlock2, sys_mlock2)
+#define __NR_copy_file_range 285
+__SYSCALL(__NR_copy_file_range, sys_copy_file_range)
+#define __NR_preadv2 286
+__SC_COMP(__NR_preadv2, sys_preadv2, compat_sys_preadv2)
+#define __NR_pwritev2 287
+__SC_COMP(__NR_pwritev2, sys_pwritev2, compat_sys_pwritev2)
+#define __NR_pkey_mprotect 288
+__SYSCALL(__NR_pkey_mprotect, sys_pkey_mprotect)
+#define __NR_pkey_alloc 289
+__SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
+#define __NR_pkey_free 290
+__SYSCALL(__NR_pkey_free,     sys_pkey_free)
+#define __NR_statx 291
+__SYSCALL(__NR_statx,     sys_statx)
+#define __NR_io_pgetevents 292
+__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+
+#undef __NR_syscalls
+#define __NR_syscalls 293
+
+/*
+ * 32 bit systems traditionally used different
+ * syscalls for off_t and loff_t arguments, while
+ * 64 bit systems only need the off_t version.
+ * For new 32 bit platforms, there is no need to
+ * implement the old 32 bit off_t syscalls, so
+ * they take different names.
+ * Here we map the numbers so that both versions
+ * use the same syscall table layout.
+ */
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
+#define __NR_fcntl __NR3264_fcntl
+#define __NR_statfs __NR3264_statfs
+#define __NR_fstatfs __NR3264_fstatfs
+#define __NR_truncate __NR3264_truncate
+#define __NR_ftruncate __NR3264_ftruncate
+#define __NR_lseek __NR3264_lseek
+#define __NR_sendfile __NR3264_sendfile
+#define __NR_newfstatat __NR3264_fstatat
+#define __NR_fstat __NR3264_fstat
+#define __NR_mmap __NR3264_mmap
+#define __NR_fadvise64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat __NR3264_stat
+#define __NR_lstat __NR3264_lstat
+#endif
+#else
+#define __NR_fcntl64 __NR3264_fcntl
+#define __NR_statfs64 __NR3264_statfs
+#define __NR_fstatfs64 __NR3264_fstatfs
+#define __NR_truncate64 __NR3264_truncate
+#define __NR_ftruncate64 __NR3264_ftruncate
+#define __NR_llseek __NR3264_lseek
+#define __NR_sendfile64 __NR3264_sendfile
+#define __NR_fstatat64 __NR3264_fstatat
+#define __NR_fstat64 __NR3264_fstat
+#define __NR_mmap2 __NR3264_mmap
+#define __NR_fadvise64_64 __NR3264_fadvise64
+#ifdef __NR3264_stat
+#define __NR_stat64 __NR3264_stat
+#define __NR_lstat64 __NR3264_lstat
+#endif
+#endif
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 10f333e2e825..814aaf269949 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -35,6 +35,7 @@ arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
+arch/arm64/include/uapi/asm/unistd.h
 arch/alpha/include/uapi/asm/errno.h
 arch/mips/include/asm/errno.h
 arch/mips/include/uapi/asm/errno.h
@@ -53,6 +54,7 @@ include/uapi/asm-generic/errno.h
 include/uapi/asm-generic/errno-base.h
 include/uapi/asm-generic/ioctls.h
 include/uapi/asm-generic/mman-common.h
+include/uapi/asm-generic/unistd.h
 '
 
 check_2 () {
-- 
cgit v1.2.3


From 2b5882435606c209ebc052230f03505ea477a252 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@arm.com>
Date: Fri, 6 Jul 2018 16:34:43 -0500
Subject: perf arm64: Generate system call table from asm/unistd.h

This should speed up accessing new system calls introduced with the
kernel rather than waiting for libaudit updates to include them.

Using the existing other arch scripts resulted in this error:

  tools/perf/arch/arm64/entry/syscalls//mksyscalltbl: 25: printf: __NR3264_ftruncate: expected numeric value

because, unlike other arches, asm-generic's unistd.h does things like:

  #define __NR_ftruncate __NR3264_ftruncate

Turning the scripts printf's %d into a %s resulted in this in the
generated syscalls.c file:

    static const char *syscalltbl_arm64[] = {
            [__NR3264_ftruncate] = "ftruncate",

So we use the host C compiler to fold the macros, and print them out
from within a temporary C program, in order to get the correct output:

    static const char *syscalltbl_arm64[] = {
            [46] = "ftruncate",

Committer notes:

Testing this with a container with an old toolchain breaks because it
ends up using the system's /usr/include/asm-generic/unistd.h, included
from tools/arch/arm64/include/uapi/asm/unistd.h when what is desired is
for it to include tools/include/uapi/asm-generic/unistd.h.

Since all that tools/arch/arm64/include/uapi/asm/unistd.h is to set a
define and then include asm-generic/unistd.h, do that directly and use
tools/include/uapi/asm-generic/unistd.h as the file to get the syscall
definitions to expand.

Testing it:

   tools/perf/arch/arm64/entry/syscalls/mksyscalltbl /gcc-linaro-5.4.1-2017.05-x86_64_aarch64-linux-gnu/bin/aarch64-linux-gnu-gcc gcc tools/include/uapi/asm-generic/unistd.h

Now works and generates in the syscall string table.

Before it ended up as:

  $ tools/perf/arch/arm64/entry/syscalls/mksyscalltbl /gcc-linaro-5.4.1-2017.05-x86_64_aarch64-linux-gnu/bin/aarch64-linux-gnu-gcc gcc tools/arch/arm64/include/uapi/asm/unistd.h
  static const char *syscalltbl_arm64[] = {
  <stdin>: In function 'main':
  <stdin>:257:38: error: '__NR_getrandom' undeclared (first use in this function)
  <stdin>:257:38: note: each undeclared identifier is reported only once for each function it appears in
  <stdin>:258:41: error: '__NR_memfd_create' undeclared (first use in this function)
  <stdin>:259:32: error: '__NR_bpf' undeclared (first use in this function)
  <stdin>:260:37: error: '__NR_execveat' undeclared (first use in this function)
  tools/perf/arch/arm64/entry/syscalls/mksyscalltbl: 47: tools/perf/arch/arm64/entry/syscalls/mksyscalltbl: /tmp/create-table-60liya: Permission denied
  };
  $

Signed-off-by: Kim Phillips <kim.phillips@arm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20180706163443.22626f5e9e10e5bab5e5c662@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/arm64/Makefile                    | 21 ++++++++
 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl | 62 +++++++++++++++++++++++
 2 files changed, 83 insertions(+)
 create mode 100755 tools/perf/arch/arm64/entry/syscalls/mksyscalltbl

diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
index 91de4860faad..f013b115dc86 100644
--- a/tools/perf/arch/arm64/Makefile
+++ b/tools/perf/arch/arm64/Makefile
@@ -4,3 +4,24 @@ PERF_HAVE_DWARF_REGS := 1
 endif
 PERF_HAVE_JITDUMP := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/arm64/include/generated/asm
+header := $(out)/syscalls.c
+sysdef := $(srctree)/tools/include/uapi/asm-generic/unistd.h
+sysprf := $(srctree)/tools/perf/arch/arm64/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '$(CC)' '$(HOSTCC)' $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, arm64) $(RM) $(header)
+
+archheaders: $(header)
diff --git a/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..52e197317d3e
--- /dev/null
+++ b/tools/perf/arch/arm64/entry/syscalls/mksyscalltbl
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# powerpc script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+# Changed by: Kim Phillips <kim.phillips@arm.com>
+
+gcc=$1
+hostcc=$2
+input=$3
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table_from_c()
+{
+	local sc nr last_sc
+
+	create_table_exe=`mktemp /tmp/create-table-XXXXXX`
+
+	{
+
+	cat <<-_EoHEADER
+		#include <stdio.h>
+		#define __ARCH_WANT_RENAMEAT
+		#include "$input"
+		int main(int argc, char *argv[])
+		{
+	_EoHEADER
+
+	while read sc nr; do
+		printf "%s\n" "	printf(\"\\t[%d] = \\\"$sc\\\",\\n\", __NR_$sc);"
+		last_sc=$sc
+	done
+
+	printf "%s\n" "	printf(\"#define SYSCALLTBL_ARM64_MAX_ID %d\\n\", __NR_$last_sc);"
+	printf "}\n"
+
+	} | $hostcc -o $create_table_exe -x c -
+
+	$create_table_exe
+
+	rm -f $create_table_exe
+}
+
+create_table()
+{
+	echo "static const char *syscalltbl_arm64[] = {"
+	create_table_from_c
+	echo "};"
+}
+
+$gcc -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table
-- 
cgit v1.2.3


From a7f660d6576a5f4504c8ab4f4956bba03d48bf52 Mon Sep 17 00:00:00 2001
From: Kim Phillips <kim.phillips@arm.com>
Date: Fri, 6 Jul 2018 16:34:54 -0500
Subject: perf trace arm64: Use generated syscall table

This should speed up accessing new system calls introduced with the
kernel rather than waiting for libaudit updates to include them.

It also enables users to specify wildcards, for example, perf trace -e
'open*', just like was already possible on x86, s390, and powerpc, which
means arm64 can now pass the "Check open filename arg using perf trace +
vfs_getname" test.

Signed-off-by: Kim Phillips <kim.phillips@arm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/20180706163454.f714b9ab49ecc8566a0b3565@arm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config   | 2 ++
 tools/perf/util/syscalltbl.c | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index f5a3b402589e..d3318f99006c 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -54,6 +54,8 @@ endif
 
 ifeq ($(SRCARCH),arm64)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/arm64/include/generated
   LIBUNWIND_LIBS = -lunwind -lunwind-aarch64
 endif
 
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 0ee7f568d60c..3393d7ee9401 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -38,6 +38,10 @@ static const char **syscalltbl_native = syscalltbl_powerpc_64;
 #include <asm/syscalls_32.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_powerpc_32;
+#elif defined(__aarch64__)
+#include <asm/syscalls.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_ARM64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_arm64;
 #endif
 
 struct syscall {
-- 
cgit v1.2.3


From 2a9d5050dc84fa2060f08a52f632976923e0fa7e Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Tue, 3 Jul 2018 17:35:55 +0530
Subject: perf script: Show correct offsets for DWARF-based unwinding

When perf/data is recorded with the dwarf call-graph option, the
callchain shown by 'perf script' still shows the binary offsets of the
userspace symbols instead of their virtual addresses. Since the symbol
offset calculation is based on using virtual address as the ip, we see
incorrect offsets as well.

The use of virtual addresses affects the ability to find out the
line number in the corresponding source file to which an address
maps to as described in commit 67540759151a ("perf unwind: Use
addr_location::addr instead of ip for entries").

This has also been addressed by temporarily converting the virtual
address to the correponding binary offset so that it can be mapped
to the source line number correctly.

This is a follow-up for commit 19610184693c ("perf script: Show
virtual addresses instead of offsets").

This can be verified on a powerpc64le system running Fedora 27 as
shown below:

  # perf probe -x /usr/lib64/libc-2.26.so -a inet_pton
  # perf record -e probe_libc:inet_pton --call-graph=dwarf ping -6 -c 1 ::1

Before:

  # perf report --stdio --no-children -s sym,srcline -g address

  # Samples: 1  of event 'probe_libc:inet_pton'
  # Event count (approx.): 1
  #
  # Overhead  Symbol                Source:Line
  # ........  ....................  ...........
  #
     100.00%  [.] __GI___inet_pton  inet_pton.c
              |
              ---gaih_inet getaddrinfo.c:537 (inlined)
                 __GI_getaddrinfo getaddrinfo.c:2304 (inlined)
                 main ping.c:519
                 generic_start_main libc-start.c:308 (inlined)
                 __libc_start_main libc-start.c:102
  ...

  # perf script -F comm,ip,sym,symoff,srcline,dso

  ping
                    15af28 __GI___inet_pton+0xffff000099160008 (/usr/lib64/libc-2.26.so)
    libc-2.26.so[ffff80004ca0af28]
                    10fa53 gaih_inet+0xffff000099160f43
    libc-2.26.so[ffff80004c9bfa53] (inlined)
                    1105b3 __GI_getaddrinfo+0xffff000099160163
    libc-2.26.so[ffff80004c9c05b3] (inlined)
                      2d6f main+0xfffffffd9f1003df (/usr/bin/ping)
    ping[fffffffecf882d6f]
                     2369f generic_start_main+0xffff00009916013f
    libc-2.26.so[ffff80004c8d369f] (inlined)
                     23897 __libc_start_main+0xffff0000991600b7 (/usr/lib64/libc-2.26.so)
    libc-2.26.so[ffff80004c8d3897]

After:

  # perf report --stdio --no-children -s sym,srcline -g address

  # Samples: 1  of event 'probe_libc:inet_pton'
  # Event count (approx.): 1
  #
  # Overhead  Symbol                Source:Line
  # ........  ....................  ...........
  #
     100.00%  [.] __GI___inet_pton  inet_pton.c
              |
              ---gaih_inet.constprop.7 getaddrinfo.c:537
                 getaddrinfo getaddrinfo.c:2304
                 main ping.c:519
                 generic_start_main.isra.0 libc-start.c:308
                 __libc_start_main libc-start.c:102
  ...

  # perf script -F comm,ip,sym,symoff,srcline,dso

  ping
              7fffb38aaf28 __GI___inet_pton+0x8 (/usr/lib64/libc-2.26.so)
    inet_pton.c:68
              7fffb385fa53 gaih_inet.constprop.7+0xf43 (/usr/lib64/libc-2.26.so)
    getaddrinfo.c:537
              7fffb38605b3 getaddrinfo+0x163 (/usr/lib64/libc-2.26.so)
    getaddrinfo.c:2304
                 130782d6f main+0x3df (/usr/bin/ping)
    ping.c:519
              7fffb377369f generic_start_main.isra.0+0x13f (/usr/lib64/libc-2.26.so)
    libc-start.c:308
              7fffb3773897 __libc_start_main+0xb7 (/usr/lib64/libc-2.26.so)
    libc-start.c:102

Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Fixes: 67540759151a ("perf unwind: Use addr_location::addr instead of ip for entries")
Link: http://lkml.kernel.org/r/20180703120555.32971-1-sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c                | 9 ++++++++-
 tools/perf/util/unwind-libdw.c           | 2 +-
 tools/perf/util/unwind-libunwind-local.c | 2 +-
 3 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index e7b4a8b513f2..22dbb6612b41 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -2272,6 +2272,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
 	const char *srcline = NULL;
+	u64 addr;
 
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
@@ -2279,7 +2280,13 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
 		return 0;
 
-	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
+	/*
+	 * Convert entry->ip from a virtual address to an offset in
+	 * its corresponding binary.
+	 */
+	addr = map__map_ip(entry->map, entry->ip);
+
+	srcline = callchain_srcline(entry->map, entry->sym, addr);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,
 				       false, NULL, 0, 0, 0, srcline);
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 538db4e5d1e6..6f318b15950e 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -77,7 +77,7 @@ static int entry(u64 ip, struct unwind_info *ui)
 	if (__report_module(&al, ip, ui))
 		return -1;
 
-	e->ip  = al.addr;
+	e->ip  = ip;
 	e->map = al.map;
 	e->sym = al.sym;
 
diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
index 6a11bc7e6b27..79f521a552cf 100644
--- a/tools/perf/util/unwind-libunwind-local.c
+++ b/tools/perf/util/unwind-libunwind-local.c
@@ -575,7 +575,7 @@ static int entry(u64 ip, struct thread *thread,
 	struct addr_location al;
 
 	e.sym = thread__find_symbol(thread, PERF_RECORD_MISC_USER, ip, &al);
-	e.ip = al.addr;
+	e.ip  = ip;
 	e.map = al.map;
 
 	pr_debug("unwind: %s:ip = 0x%" PRIx64 " (0x%" PRIx64 ")\n",
-- 
cgit v1.2.3


From e8fedff1cc729fd227924305152ccc6f580e8c83 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 12 Jul 2018 15:52:02 +0200
Subject: perf tools: Synthesize GROUP_DESC feature in pipe mode

Stephan reported, that pipe mode does not carry the group information
and thus the piped report won't display the grouped output for following
command:

  # perf record -e '{cycles,instructions,branches}' -a sleep 4 | perf report

It has no idea about the group setup, so it will display events
separately:

  # Overhead  Command          Shared Object             ...
  # ........  ...............  .......................
  #
       6.71%  swapper          [kernel.kallsyms]
       2.28%  offlineimap      libpython2.7.so.1.0
       0.78%  perf             [kernel.kallsyms]
  ...

Fix GROUP_DESC feature record to be synthesized in pipe mode, so the
report output is grouped if there are groups defined in record:

  #                 Overhead  Command          Shared    ...
  # ........................  ...............  .......
  #
       7.57%   0.16%   0.30%  swapper          [kernel
       1.87%   3.15%   2.46%  offlineimap      libpyth
       1.33%   0.00%   0.00%  perf             [kernel
  ...

Reported-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Stephane Eranian <eranian@google.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: David Carrillo-Cisneros <davidcc@google.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180712135202.14774-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/header.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 653ff65aa2c3..5af58aac91ad 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2587,7 +2587,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPR(NUMA_TOPOLOGY,	numa_topology,	true),
 	FEAT_OPN(BRANCH_STACK,	branch_stack,	false),
 	FEAT_OPR(PMU_MAPPINGS,	pmu_mappings,	false),
-	FEAT_OPN(GROUP_DESC,	group_desc,	false),
+	FEAT_OPR(GROUP_DESC,	group_desc,	false),
 	FEAT_OPN(AUXTRACE,	auxtrace,	false),
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
-- 
cgit v1.2.3


From f8b2ebb532e0553b60ae5ad1b84d1d4f0c285752 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 19 Jul 2018 16:33:42 +0200
Subject: perf machine: Add threads__get_last_match function

Separating threads::last_match cache read/check into separate
threads__get_last_match function. This will be useful in following
patch.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20180719143345.12963-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 39 ++++++++++++++++++++++++++-------------
 1 file changed, 26 insertions(+), 13 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 22dbb6612b41..df41aa1a4cf9 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -408,23 +408,16 @@ out_err:
 }
 
 /*
- * Caller must eventually drop thread->refcnt returned with a successful
- * lookup/new thread inserted.
+ * Front-end cache - TID lookups come in blocks,
+ * so most of the time we dont have to look up
+ * the full rbtree:
  */
-static struct thread *____machine__findnew_thread(struct machine *machine,
-						  struct threads *threads,
-						  pid_t pid, pid_t tid,
-						  bool create)
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+			int pid, int tid)
 {
-	struct rb_node **p = &threads->entries.rb_node;
-	struct rb_node *parent = NULL;
 	struct thread *th;
 
-	/*
-	 * Front-end cache - TID lookups come in blocks,
-	 * so most of the time we dont have to look up
-	 * the full rbtree:
-	 */
 	th = threads->last_match;
 	if (th != NULL) {
 		if (th->tid == tid) {
@@ -435,6 +428,26 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		threads->last_match = NULL;
 	}
 
+	return NULL;
+}
+
+/*
+ * Caller must eventually drop thread->refcnt returned with a successful
+ * lookup/new thread inserted.
+ */
+static struct thread *____machine__findnew_thread(struct machine *machine,
+						  struct threads *threads,
+						  pid_t pid, pid_t tid,
+						  bool create)
+{
+	struct rb_node **p = &threads->entries.rb_node;
+	struct rb_node *parent = NULL;
+	struct thread *th;
+
+	th = threads__get_last_match(threads, machine, pid, tid);
+	if (th)
+		return th;
+
 	while (*p != NULL) {
 		parent = *p;
 		th = rb_entry(parent, struct thread, rb_node);
-- 
cgit v1.2.3


From 67fda0f32cd9428cb9a3166796162097d7fcbcbf Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 19 Jul 2018 16:33:43 +0200
Subject: perf machine: Add threads__set_last_match function

Separating threads::last_match cache set into separate
threads__set_last_match function.  This will be useful in following
patch.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20180719143345.12963-3-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index df41aa1a4cf9..8992fcf42257 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -431,6 +431,12 @@ threads__get_last_match(struct threads *threads, struct machine *machine,
 	return NULL;
 }
 
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	threads->last_match = th;
+}
+
 /*
  * Caller must eventually drop thread->refcnt returned with a successful
  * lookup/new thread inserted.
@@ -453,7 +459,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		th = rb_entry(parent, struct thread, rb_node);
 
 		if (th->tid == tid) {
-			threads->last_match = th;
+			threads__set_last_match(threads, th);
 			machine__update_thread_pid(machine, th, pid);
 			return thread__get(th);
 		}
@@ -490,7 +496,7 @@ static struct thread *____machine__findnew_thread(struct machine *machine,
 		 * It is now in the rbtree, get a ref
 		 */
 		thread__get(th);
-		threads->last_match = th;
+		threads__set_last_match(threads, th);
 		++threads->nr;
 	}
 
@@ -1648,7 +1654,7 @@ static void __machine__remove_thread(struct machine *machine, struct thread *th,
 	struct threads *threads = machine__threads(machine, th->tid);
 
 	if (threads->last_match == th)
-		threads->last_match = NULL;
+		threads__set_last_match(threads, NULL);
 
 	BUG_ON(refcount_read(&th->refcnt) == 0);
 	if (lock)
-- 
cgit v1.2.3


From b57334b9453949bf81281321d14d86d60aee6fde Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Thu, 19 Jul 2018 16:33:44 +0200
Subject: perf machine: Use last_match threads cache only in single thread mode

There's an issue with using threads::last_match in multithread mode
which is enabled during the perf top synthesize. It might crash with
following assertion:

  perf: ...include/linux/refcount.h:109: refcount_inc:
        Assertion `!(!refcount_inc_not_zero(r))' failed.

The gdb backtrace looks like this:

  0x00007ffff50839fb in raise () from /lib64/libc.so.6
  (gdb)
  #0  0x00007ffff50839fb in raise () from /lib64/libc.so.6
  #1  0x00007ffff5085800 in abort () from /lib64/libc.so.6
  #2  0x00007ffff507c0da in __assert_fail_base () from /lib64/libc.so.6
  #3  0x00007ffff507c152 in __assert_fail () from /lib64/libc.so.6
  #4  0x0000000000535ff9 in refcount_inc (r=0x7fffe8009a70)
      at ...include/linux/refcount.h:109
  #5  0x0000000000536771 in thread__get (thread=0x7fffe8009a40)
      at util/thread.c:115
  #6  0x0000000000523cd0 in ____machine__findnew_thread (machine=0xbfde38,
      threads=0xbfdf28, pid=2, tid=2, create=true) at util/machine.c:432
  #7  0x0000000000523eb4 in __machine__findnew_thread (machine=0xbfde38,
      pid=2, tid=2) at util/machine.c:489
  #8  0x0000000000523f24 in machine__findnew_thread (machine=0xbfde38,
      pid=2, tid=2) at util/machine.c:499
  #9  0x0000000000526fbe in machine__process_fork_event (machine=0xbfde38,
  ...

The failing assertion is this one:

  REFCOUNT_WARN(!refcount_inc_not_zero(r), ...

the problem is that we don't serialize access to threads::last_match.
We serialize the access to the threads tree, but we don't care how's
threads::last_match being accessed. Both locked/unlocked paths use
that data and can set it. In multithreaded mode we can end up with
invalid object in thread__get call, like in following paths race:

  thread 1
    ...
    machine__findnew_thread
      down_write(&threads->lock);
      __machine__findnew_thread
        ____machine__findnew_thread
          th = threads->last_match;
          if (th->tid == tid) {
            thread__get

  thread 2
    ...
    machine__find_thread
      down_read(&threads->lock);
      __machine__findnew_thread
        ____machine__findnew_thread
          th = threads->last_match;
          if (th->tid == tid) {
            thread__get

  thread 3
    ...
    machine__process_fork_event
      machine__remove_thread
        __machine__remove_thread
          threads->last_match = NULL
          thread__put
      thread__put

Thread 1 and 2 might got stale last_match, before thread 3 clears
it. Thread 1 and 2 then race with thread 3's thread__put and they
might trigger the refcnt == 0 assertion above.

The patch is disabling the last_match cache for multiple thread
mode. It was originally meant for single thread scenarios, where
it's common to have multiple sequential searches of the same
thread.

In multithread mode this does not make sense, because top's threads
processes different /proc entries and so the 'struct threads' object
is queried for various threads. Moreover we'd need to add more locks
to make it work.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/20180719143345.12963-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/machine.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 8992fcf42257..b300a3973448 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -413,8 +413,8 @@ out_err:
  * the full rbtree:
  */
 static struct thread*
-threads__get_last_match(struct threads *threads, struct machine *machine,
-			int pid, int tid)
+__threads__get_last_match(struct threads *threads, struct machine *machine,
+			  int pid, int tid)
 {
 	struct thread *th;
 
@@ -431,12 +431,31 @@ threads__get_last_match(struct threads *threads, struct machine *machine,
 	return NULL;
 }
 
+static struct thread*
+threads__get_last_match(struct threads *threads, struct machine *machine,
+			int pid, int tid)
+{
+	struct thread *th = NULL;
+
+	if (perf_singlethreaded)
+		th = __threads__get_last_match(threads, machine, pid, tid);
+
+	return th;
+}
+
 static void
-threads__set_last_match(struct threads *threads, struct thread *th)
+__threads__set_last_match(struct threads *threads, struct thread *th)
 {
 	threads->last_match = th;
 }
 
+static void
+threads__set_last_match(struct threads *threads, struct thread *th)
+{
+	if (perf_singlethreaded)
+		__threads__set_last_match(threads, th);
+}
+
 /*
  * Caller must eventually drop thread->refcnt returned with a successful
  * lookup/new thread inserted.
-- 
cgit v1.2.3


From 46b3722cc7765582354488da633aafffcb138458 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Fri, 20 Jul 2018 12:17:40 +0200
Subject: perf tools: Fix struct comm_str removal crash

We occasionaly hit following assert failure in 'perf top', when processing the
/proc info in multiple threads.

  perf: ...include/linux/refcount.h:109: refcount_inc:
        Assertion `!(!refcount_inc_not_zero(r))' failed.

The gdb backtrace looks like this:

  [Switching to Thread 0x7ffff11ba700 (LWP 13749)]
  0x00007ffff50839fb in raise () from /lib64/libc.so.6
  (gdb)
  #0  0x00007ffff50839fb in raise () from /lib64/libc.so.6
  #1  0x00007ffff5085800 in abort () from /lib64/libc.so.6
  #2  0x00007ffff507c0da in __assert_fail_base () from /lib64/libc.so.6
  #3  0x00007ffff507c152 in __assert_fail () from /lib64/libc.so.6
  #4  0x0000000000535373 in refcount_inc (r=0x7fffdc009be0)
      at ...include/linux/refcount.h:109
  #5  0x00000000005354f1 in comm_str__get (cs=0x7fffdc009bc0)
      at util/comm.c:24
  #6  0x00000000005356bd in __comm_str__findnew (str=0x7fffd000b260 ":2",
      root=0xbed5c0 <comm_str_root>) at util/comm.c:72
  #7  0x000000000053579e in comm_str__findnew (str=0x7fffd000b260 ":2",
      root=0xbed5c0 <comm_str_root>) at util/comm.c:95
  #8  0x000000000053582e in comm__new (str=0x7fffd000b260 ":2",
      timestamp=0, exec=false) at util/comm.c:111
  #9  0x00000000005363bc in thread__new (pid=2, tid=2) at util/thread.c:57
  #10 0x0000000000523da0 in ____machine__findnew_thread (machine=0xbfde38,
      threads=0xbfdf28, pid=2, tid=2, create=true) at util/machine.c:457
  #11 0x0000000000523eb4 in __machine__findnew_thread (machine=0xbfde38,
  ...

The failing assertion is this one:

  REFCOUNT_WARN(!refcount_inc_not_zero(r), ...

The problem is that we keep global comm_str_root list, which
is accessed by multiple threads during the 'perf top' startup
and following 2 paths can race:

  thread 1:
    ...
    thread__new
      comm__new
        comm_str__findnew
          down_write(&comm_str_lock);
          __comm_str__findnew
            comm_str__get

  thread 2:
    ...
    comm__override or comm__free
      comm_str__put
        refcount_dec_and_test
          down_write(&comm_str_lock);
          rb_erase(&cs->rb_node, &comm_str_root);

Because thread 2 first decrements the refcnt and only after then it removes the
struct comm_str from the list, the thread 1 can find this object on the list
with refcnt equls to 0 and hit the assert.

This patch fixes the thread 1 __comm_str__findnew path, by ignoring objects
that already dropped the refcnt to 0. For the rest of the objects we take the
refcnt before comparing its name and release it afterwards with comm_str__put,
which can also release the object completely.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Lukasz Odzioba <lukasz.odzioba@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Wang Nan <wangnan0@huawei.com>
Cc: kernel-team@lge.com
Link: http://lkml.kernel.org/r/20180720101740.GA27176@krava
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/comm.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/tools/perf/util/comm.c b/tools/perf/util/comm.c
index 7798a2cc8a86..31279a7bd919 100644
--- a/tools/perf/util/comm.c
+++ b/tools/perf/util/comm.c
@@ -20,9 +20,10 @@ static struct rw_semaphore comm_str_lock = {.lock = PTHREAD_RWLOCK_INITIALIZER,}
 
 static struct comm_str *comm_str__get(struct comm_str *cs)
 {
-	if (cs)
-		refcount_inc(&cs->refcnt);
-	return cs;
+	if (cs && refcount_inc_not_zero(&cs->refcnt))
+		return cs;
+
+	return NULL;
 }
 
 static void comm_str__put(struct comm_str *cs)
@@ -67,9 +68,14 @@ struct comm_str *__comm_str__findnew(const char *str, struct rb_root *root)
 		parent = *p;
 		iter = rb_entry(parent, struct comm_str, rb_node);
 
+		/*
+		 * If we race with comm_str__put, iter->refcnt is 0
+		 * and it will be removed within comm_str__put call
+		 * shortly, ignore it in this search.
+		 */
 		cmp = strcmp(str, iter->str);
-		if (!cmp)
-			return comm_str__get(iter);
+		if (!cmp && comm_str__get(iter))
+			return iter;
 
 		if (cmp < 0)
 			p = &(*p)->rb_left;
-- 
cgit v1.2.3


From 2d6cae13f10d5d8b370038dbfdf60317c22b9f52 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 20 Jul 2018 13:00:33 +0200
Subject: perf tools: Use perf_evsel__match instead of open coded equivalent

Use perf_evsel__match() helper in perf_evsel__is_bpf_output().

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180720110036.32251-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.h | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index d277930b19a1..890babf9ce86 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -402,10 +402,7 @@ bool perf_evsel__is_function_event(struct perf_evsel *evsel);
 
 static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 {
-	struct perf_event_attr *attr = &evsel->attr;
-
-	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
-		(attr->type == PERF_TYPE_SOFTWARE);
+	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
 }
 
 struct perf_attr_details {
-- 
cgit v1.2.3


From 0aa802a79469a86ebe143019144cd4df8ae852e4 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Fri, 20 Jul 2018 13:00:34 +0200
Subject: perf stat: Get rid of extra clock display function

There's no reason to have separate function to display clock events.
It's only purpose was to convert the nanosecond value into microseconds.
We do that now in generic code, if the unit and scale values are
properly set, which this patch do for clock events.

The output differs in the unit field being displayed in its columns
rather than having it added as a suffix of the event name. Plus the
value is rounded into 2 decimal numbers as for any other event.

Before:

  # perf stat  -e cpu-clock,task-clock -C 0 sleep 3

   Performance counter stats for 'CPU(s) 0':

       3001.123137      cpu-clock (msec)          #    1.000 CPUs utilized
       3001.133250      task-clock (msec)         #    1.000 CPUs utilized

       3.001159813 seconds time elapsed

Now:

  # perf stat  -e cpu-clock,task-clock -C 0 sleep 3

   Performance counter stats for 'CPU(s) 0':

          3,001.05 msec cpu-clock                 #    1.000 CPUs utilized
          3,001.05 msec task-clock                #    1.000 CPUs utilized

       3.001077794 seconds time elapsed

There's a small difference in csv output, as we now output the unit
field, which was empty before. It's in the proper spot, so there's no
compatibility issue.

Before:

  # perf stat  -e cpu-clock,task-clock -C 0 -x, sleep 3
  3001.065177,,cpu-clock,3001064187,100.00,1.000,CPUs utilized
  3001.077085,,task-clock,3001077085,100.00,1.000,CPUs utilized

  # perf stat  -e cpu-clock,task-clock -C 0 -x, sleep 3
  3000.80,msec,cpu-clock,3000799026,100.00,1.000,CPUs utilized
  3000.80,msec,task-clock,3000799550,100.00,1.000,CPUs utilized

Add perf_evsel__is_clock to replace nsec_counter.

Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20180720110036.32251-2-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-stat.c     | 48 ++-----------------------------------------
 tools/perf/util/evsel.c       | 11 ++++++++++
 tools/perf/util/evsel.h       |  6 ++++++
 tools/perf/util/stat-shadow.c |  5 ++---
 4 files changed, 21 insertions(+), 49 deletions(-)

diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index dfd13d6e2931..d097b5b47eb8 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -296,18 +296,6 @@ static int create_perf_stat_counter(struct perf_evsel *evsel)
 	return perf_evsel__open_per_thread(evsel, evsel_list->threads);
 }
 
-/*
- * Does the counter have nsecs as a unit?
- */
-static inline int nsec_counter(struct perf_evsel *evsel)
-{
-	if (perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
-	    perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK))
-		return 1;
-
-	return 0;
-}
-
 static int process_synthesized_event(struct perf_tool *tool __maybe_unused,
 				     union perf_event *event,
 				     struct perf_sample *sample __maybe_unused,
@@ -1058,34 +1046,6 @@ static void print_metric_header(void *ctx, const char *color __maybe_unused,
 		fprintf(os->fh, "%*s ", metric_only_len, unit);
 }
 
-static void nsec_printout(int id, int nr, struct perf_evsel *evsel, double avg)
-{
-	FILE *output = stat_config.output;
-	double msecs = avg / NSEC_PER_MSEC;
-	const char *fmt_v, *fmt_n;
-	char name[25];
-
-	fmt_v = csv_output ? "%.6f%s" : "%18.6f%s";
-	fmt_n = csv_output ? "%s" : "%-25s";
-
-	aggr_printout(evsel, id, nr);
-
-	scnprintf(name, sizeof(name), "%s%s",
-		  perf_evsel__name(evsel), csv_output ? "" : " (msec)");
-
-	fprintf(output, fmt_v, msecs, csv_sep);
-
-	if (csv_output)
-		fprintf(output, "%s%s", evsel->unit, csv_sep);
-	else
-		fprintf(output, "%-*s%s", unit_width, evsel->unit, csv_sep);
-
-	fprintf(output, fmt_n, name);
-
-	if (evsel->cgrp)
-		fprintf(output, "%s%s", csv_sep, evsel->cgrp->name);
-}
-
 static int first_shadow_cpu(struct perf_evsel *evsel, int id)
 {
 	int i;
@@ -1241,11 +1201,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,
 		return;
 	}
 
-	if (metric_only)
-		/* nothing */;
-	else if (nsec_counter(counter))
-		nsec_printout(id, nr, counter, uval);
-	else
+	if (!metric_only)
 		abs_printout(id, nr, counter, uval);
 
 	out.print_metric = pm;
@@ -1331,7 +1287,7 @@ static void collect_all_aliases(struct perf_evsel *counter,
 		    alias->scale != counter->scale ||
 		    alias->cgrp != counter->cgrp ||
 		    strcmp(alias->unit, counter->unit) ||
-		    nsec_counter(alias) != nsec_counter(counter))
+		    perf_evsel__is_clock(alias) != perf_evsel__is_clock(counter))
 			break;
 		alias->merged_stat = true;
 		cb(alias, data, false);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 94fce4f537e9..5285da0417c5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -260,6 +260,17 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 		evsel->attr.sample_period = 1;
 	}
 
+	if (perf_evsel__is_clock(evsel)) {
+		/*
+		 * The evsel->unit points to static alias->unit
+		 * so it's ok to use static string in here.
+		 */
+		static const char *unit = "msec";
+
+		evsel->unit = unit;
+		evsel->scale = 1e-6;
+	}
+
 	return evsel;
 }
 
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 890babf9ce86..973c03167947 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -405,6 +405,12 @@ static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
 	return perf_evsel__match(evsel, SOFTWARE, SW_BPF_OUTPUT);
 }
 
+static inline bool perf_evsel__is_clock(struct perf_evsel *evsel)
+{
+	return perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK) ||
+	       perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK);
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 594d14a02b67..99990f5f2512 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -913,11 +913,10 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,
 			ratio = total / avg;
 
 		print_metric(ctxp, NULL, "%8.0f", "cycles / elision", ratio);
-	} else if (perf_evsel__match(evsel, SOFTWARE, SW_TASK_CLOCK) ||
-		   perf_evsel__match(evsel, SOFTWARE, SW_CPU_CLOCK)) {
+	} else if (perf_evsel__is_clock(evsel)) {
 		if ((ratio = avg_stats(&walltime_nsecs_stats)) != 0)
 			print_metric(ctxp, NULL, "%8.3f", "CPUs utilized",
-				     avg / ratio);
+				     avg / (ratio * evsel->scale));
 		else
 			print_metric(ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
-- 
cgit v1.2.3


From 9ef0112442bdddef5fb55adf20b3a5464b33de75 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 24 Jul 2018 15:48:58 +0200
Subject: perf test: Fix subtest number when showing results

Perf test 40 for example has several subtests numbered 1-4 when
displaying the start of the subtest. When the subtest results
are displayed the subtests are numbered 0-3.

Use this command to generate trace output:

  [root@s35lp76 perf]# ./perf test -Fv 40 2>/tmp/bpf1

Fix this by adjusting the subtest number when show the
subtest result.

Output before:

  [root@s35lp76 perf]# egrep '(^40\.[0-4]| subtest [0-4]:)' /tmp/bpf1
  40.1: Basic BPF filtering                                 :
  BPF filter subtest 0: Ok
  40.2: BPF pinning                                         :
  BPF filter subtest 1: Ok
  40.3: BPF prologue generation                             :
  BPF filter subtest 2: Ok
  40.4: BPF relocation checker                              :
  BPF filter subtest 3: Ok
  [root@s35lp76 perf]#

Output after:

  root@s35lp76 ~]# egrep '(^40\.[0-4]| subtest [0-4]:)' /tmp/bpf1
  40.1: Basic BPF filtering                                 :
  BPF filter subtest 1: Ok
  40.2: BPF pinning                                         :
  BPF filter subtest 2: Ok
  40.3: BPF prologue generation                             :
  BPF filter subtest 3: Ok
  40.4: BPF relocation checker                              :
  BPF filter subtest 4: Ok
  [root@s35lp76 ~]#

Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Link: http://lkml.kernel.org/r/20180724134858.100644-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/builtin-test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index dd850a26d579..4f5de8245b32 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -599,7 +599,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			for (subi = 0; subi < subn; subi++) {
 				pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
 					t->subtest.get_desc(subi));
-				err = test_and_print(t, skip, subi);
+				err = test_and_print(t, skip, subi + 1);
 				if (err != TEST_OK && t->subtest.skip_if_fail)
 					skip = true;
 			}
-- 
cgit v1.2.3


From e79e0e1428188b24c3b57309ffa54a33c4ae40c4 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Mon, 18 Jun 2018 13:24:13 -0500
Subject: gfs2: Don't reject a supposedly full bitmap if we have blocks
 reserved

Before this patch, you could get into situations like this:

1. Process 1 searches for X free blocks, finds them, makes a reservation
2. Process 2 searches for free blocks in the same rgrp, but now the
   bitmap is full because process 1's reservation is skipped over.
   So it marks the bitmap as GBF_FULL.
3. Process 1 tries to allocate blocks from its own reservation, but
   since the GBF_FULL bit is set, it skips over the rgrp and searches
   elsewhere, thus not using its own reservation.

This patch adds an additional check to allow processes to use their
own reservations.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/rgrp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 60c86532782e..bce75f25e53a 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1687,7 +1687,8 @@ static int gfs2_rbm_find(struct gfs2_rbm *rbm, u8 state, u32 *minext,
 
 	while(1) {
 		bi = rbm_bi(rbm);
-		if (test_bit(GBF_FULL, &bi->bi_flags) &&
+		if ((ip == NULL || !gfs2_rs_active(&ip->i_res)) &&
+		    test_bit(GBF_FULL, &bi->bi_flags) &&
 		    (state == GFS2_BLKST_FREE))
 			goto next_bitmap;
 
-- 
cgit v1.2.3


From 910f3d58d0d40691534b77cc01588ffa22ee7dee Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Fri, 22 Jun 2018 09:51:43 +0800
Subject: gfs2: using posix_acl_xattr_size instead of posix_acl_to_xattr

It seems better to get size by calling posix_acl_xattr_size() instead of
calling posix_acl_to_xattr() with NULL buffer argument.

posix_acl_xattr_size() never returns 0, so remove the unnecessary check.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/acl.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 776717f1eeea..af5f87a493d9 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -82,14 +82,12 @@ struct posix_acl *gfs2_get_acl(struct inode *inode, int type)
 int __gfs2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	int error;
-	int len;
+	size_t len;
 	char *data;
 	const char *name = gfs2_acl_name(type);
 
 	if (acl) {
-		len = posix_acl_to_xattr(&init_user_ns, acl, NULL, 0);
-		if (len == 0)
-			return 0;
+		len = posix_acl_xattr_size(acl->a_count);
 		data = kmalloc(len, GFP_NOFS);
 		if (data == NULL)
 			return -ENOMEM;
-- 
cgit v1.2.3


From 109dbb1e6f27fb8f80ee61953485c7c3b1717951 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Mon, 2 Jul 2018 22:16:13 +0530
Subject: fs: gfs2: Adding new return type vm_fault_t

Use new return type vm_fault_t for gfs2_page_mkwrite
handler.

see commit 1c8f422059ae ("mm: change return type to
vm_fault_t") for reference.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 7137db7b0119..8cb278ee9a0e 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -387,7 +387,7 @@ static int gfs2_allocate_page_backing(struct page *page)
  * blocks allocated on disk to back that page.
  */
 
-static int gfs2_page_mkwrite(struct vm_fault *vmf)
+static vm_fault_t gfs2_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
-- 
cgit v1.2.3


From 8dd30201ce66f2c81077e06056f4a865e512e854 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 24 Jul 2018 13:53:00 +0300
Subject: net: remove redundant input checks in SIOCSIFTXQLEN case of
 dev_ifsioc

The cited patch added a call to dev_change_tx_queue_len in
SIOCSIFTXQLEN case.
This obsoletes the new len comparison check done before the function call.
Remove it here.

For the desicion of keep/remove the negative value check, we examine the
range check in dev_change_tx_queue_len.
On 64-bit we will fail with -ERANGE.  The 32-bit int ifr_qlen will be sign
extended to 64-bits when it is passed into dev_change_tx_queue_len(). And
then for negative values this test triggers:

	if (new_len != (unsigned int)new_len)
		return -ERANGE;

because:
	if (0xffffffffWHATEVER != 0x00000000WHATEVER)

On 32-bit the signed value will be accepted, changing behavior.

Therefore, the negative value check is kept.

Fixes: 3f76df198288 ("net: use dev_change_tx_queue_len() for SIOCSIFTXQLEN")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev_ioctl.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 50537ff961a7..90e8aa36881e 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -284,12 +284,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
 	case SIOCSIFTXQLEN:
 		if (ifr->ifr_qlen < 0)
 			return -EINVAL;
-		if (dev->tx_queue_len ^ ifr->ifr_qlen) {
-			err = dev_change_tx_queue_len(dev, ifr->ifr_qlen);
-			if (err)
-				return err;
-		}
-		return 0;
+		return dev_change_tx_queue_len(dev, ifr->ifr_qlen);
 
 	case SIOCSIFNAME:
 		ifr->ifr_newname[IFNAMSIZ-1] = '\0';
-- 
cgit v1.2.3


From b5f6ec535f8f7ca3516adc0f34f2c3a5a388ad58 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 3 Jul 2018 09:54:39 -0400
Subject: media: smiapp: Set correct MODULE_LICENSE

The smiapp driver is licensed under GNU GPL v2 only, as stated by the
header. Reflect this in the MODULE_LICENSE macro.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/smiapp/smiapp-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index e9e0f21efc2a..f2daad49ff18 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -3187,4 +3187,4 @@ module_i2c_driver(smiapp_i2c_driver);
 
 MODULE_AUTHOR("Sakari Ailus <sakari.ailus@iki.fi>");
 MODULE_DESCRIPTION("Generic SMIA/SMIA++ camera module driver");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 6949d864776ef295ddc8f840d7d6a2dbe51bd9d1 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Wed, 4 Jul 2018 09:04:38 -0400
Subject: media: ov5640: do not change mode if format or frame interval is
 unchanged

Save load of mode registers array when V4L2 client sets a format or a
frame interval which selects the same mode than the current one.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov5640.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/media/i2c/ov5640.c b/drivers/media/i2c/ov5640.c
index 1ecbb7a4a2ee..071f4bc240ca 100644
--- a/drivers/media/i2c/ov5640.c
+++ b/drivers/media/i2c/ov5640.c
@@ -1966,9 +1966,11 @@ static int ov5640_set_fmt(struct v4l2_subdev *sd,
 		goto out;
 	}
 
-	sensor->current_mode = new_mode;
-	sensor->fmt = *mbus_fmt;
-	sensor->pending_mode_change = true;
+	if (new_mode != sensor->current_mode) {
+		sensor->current_mode = new_mode;
+		sensor->fmt = *mbus_fmt;
+		sensor->pending_mode_change = true;
+	}
 out:
 	mutex_unlock(&sensor->lock);
 	return ret;
@@ -2508,8 +2510,10 @@ static int ov5640_s_frame_interval(struct v4l2_subdev *sd,
 		goto out;
 	}
 
-	sensor->current_mode = mode;
-	sensor->pending_mode_change = true;
+	if (mode != sensor->current_mode) {
+		sensor->current_mode = mode;
+		sensor->pending_mode_change = true;
+	}
 out:
 	mutex_unlock(&sensor->lock);
 	return ret;
-- 
cgit v1.2.3


From 18d6a9b831985c7c646abd751509f52079420104 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Thu, 5 Jul 2018 10:41:11 -0400
Subject: media: smiapp: fix debug message

ask_h gets printed here instead of ask_w.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/smiapp/smiapp-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/smiapp/smiapp-core.c b/drivers/media/i2c/smiapp/smiapp-core.c
index f2daad49ff18..1236683da8f7 100644
--- a/drivers/media/i2c/smiapp/smiapp-core.c
+++ b/drivers/media/i2c/smiapp/smiapp-core.c
@@ -1892,7 +1892,7 @@ static int scaling_goodness(struct v4l2_subdev *subdev, int w, int ask_w,
 		val -= SCALING_GOODNESS_EXTREME;
 
 	dev_dbg(&client->dev, "w %d ask_w %d h %d ask_h %d goodness %d\n",
-		w, ask_h, h, ask_h, val);
+		w, ask_w, h, ask_h, val);
 
 	return val;
 }
-- 
cgit v1.2.3


From 4c471ffe2c5cb7f899cc8352d3d8fd9b6d58853b Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 9 Jul 2018 10:19:16 -0400
Subject: media: dt-bindings: media: rcar-vin: Align Gen2 and Gen3
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Align description of the Gen2 and Gen3 bindings for parallel input.
This commit prepares for description of optional endpoint properties in ports
subnodes accepting parallel video connections.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/rcar_vin.txt | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index e25ab07ded57..39c4e6a0485d 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -39,9 +39,11 @@ Additionally, an alias named vinX will need to be created to specify
 which video input device this is.
 
 The per-board settings Gen2 platforms:
- - port sub-node describing a single endpoint connected to the vin
-   as described in video-interfaces.txt[1]. Only the first one will
-   be considered as each vin interface has one input port.
+
+- port - sub-node describing a single endpoint connected to the VIN
+  from external SoC pins as described in video-interfaces.txt[1].
+  Only the first one will be considered as each vin interface has one
+  input port.
 
 The per-board settings Gen3 platforms:
 
@@ -52,7 +54,7 @@ from local SoC CSI-2 receivers (port@1) depending on SoC.
 - renesas,id - ID number of the VIN, VINx in the documentation.
 - ports
     - port@0 - sub-node describing a single endpoint connected to the VIN
-      from external SoC pins described in video-interfaces.txt[1].
+      from external SoC pins as described in video-interfaces.txt[1].
       Describing more than one endpoint in port@0 is invalid. Only VIN
       instances that are connected to external pins should have port@0.
     - port@1 - sub-nodes describing one or more endpoints connected to
-- 
cgit v1.2.3


From 3ab7801dfab998a2d1fba38b578bcaede4c9fcf3 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 9 Jul 2018 10:19:17 -0400
Subject: media: dt-bindings: media: rcar-vin: Describe optional ep properties
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Describe the optional endpoint properties for endpoint nodes of the R-Car
VIN interface device tree bindings documentation.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/rcar_vin.txt | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index 39c4e6a0485d..b41086340018 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -45,6 +45,17 @@ The per-board settings Gen2 platforms:
   Only the first one will be considered as each vin interface has one
   input port.
 
+  - Optional properties for endpoint nodes:
+    - hsync-active: see [1] for description. Default is active high.
+    - vsync-active: see [1] for description. Default is active high.
+      If both HSYNC and VSYNC polarities are not specified, embedded
+      synchronization is selected.
+    - field-active-even: see [1] for description. Default is active high.
+    - bus-width: see [1] for description. The selected bus width depends on
+      the SoC type and selected input image format.
+      Valid values are: 8, 10, 12, 16, 24 and 32.
+    - data-shift: see [1] for description. Valid values are 0 and 8.
+
 The per-board settings Gen3 platforms:
 
 Gen3 platforms can support both a single connected parallel input source
@@ -57,6 +68,10 @@ from local SoC CSI-2 receivers (port@1) depending on SoC.
       from external SoC pins as described in video-interfaces.txt[1].
       Describing more than one endpoint in port@0 is invalid. Only VIN
       instances that are connected to external pins should have port@0.
+
+      Endpoint nodes of port@0 support the optional properties listed in
+      the Gen2 per-board settings description.
+
     - port@1 - sub-nodes describing one or more endpoints connected to
       the VIN from local SoC CSI-2 receivers. The endpoint numbers must
       use the following schema.
@@ -66,6 +81,8 @@ from local SoC CSI-2 receivers (port@1) depending on SoC.
         - endpoint@2 - sub-node describing the endpoint connected to CSI40
         - endpoint@3 - sub-node describing the endpoint connected to CSI41
 
+      Endpoint nodes of port@1 do not support any optional endpoint property.
+
 Device node example for Gen2 platforms
 --------------------------------------
 
-- 
cgit v1.2.3


From 75571ee0e50da56ea45a9cea3a540dd0955fa7ce Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 9 Jul 2018 10:19:18 -0400
Subject: media: dt-bindings: media: Document data-enable-active property
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add 'data-enable-active' property to endpoint node properties list.

The property allows to specify the polarity of the data-enable signal,
which when in active state determinates when data lines have to sampled
for valid pixel data.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/video-interfaces.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/video-interfaces.txt b/Documentation/devicetree/bindings/media/video-interfaces.txt
index 52b7c7b57842..baf9d9756b3c 100644
--- a/Documentation/devicetree/bindings/media/video-interfaces.txt
+++ b/Documentation/devicetree/bindings/media/video-interfaces.txt
@@ -113,6 +113,8 @@ Optional endpoint properties
   Note, that if HSYNC and VSYNC polarities are not specified, embedded
   synchronization may be required, where supported.
 - data-active: similar to HSYNC and VSYNC, specifies data line polarity.
+- data-enable-active: similar to HSYNC and VSYNC, specifies the data enable
+  signal polarity.
 - field-even-active: field signal level during the even field data transmission.
 - pclk-sample: sample data on rising (1) or falling (0) edge of the pixel clock
   signal.
-- 
cgit v1.2.3


From 9b04fcc1d8a9b5480f9e7ec93072c3a1bc517256 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 9 Jul 2018 10:19:19 -0400
Subject: media: v4l2-fwnode: parse 'data-enable-active' prop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Parse the newly defined 'data-enable-active' property in parallel
endpoint parsing function.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-fwnode.c | 4 ++++
 include/media/v4l2-mediabus.h         | 2 ++
 2 files changed, 6 insertions(+)

diff --git a/drivers/media/v4l2-core/v4l2-fwnode.c b/drivers/media/v4l2-core/v4l2-fwnode.c
index 3f77aa318035..61051911e779 100644
--- a/drivers/media/v4l2-core/v4l2-fwnode.c
+++ b/drivers/media/v4l2-core/v4l2-fwnode.c
@@ -154,6 +154,10 @@ static void v4l2_fwnode_endpoint_parse_parallel_bus(
 		flags |= v ? V4L2_MBUS_VIDEO_SOG_ACTIVE_HIGH :
 			V4L2_MBUS_VIDEO_SOG_ACTIVE_LOW;
 
+	if (!fwnode_property_read_u32(fwnode, "data-enable-active", &v))
+		flags |= v ? V4L2_MBUS_DATA_ENABLE_HIGH :
+			V4L2_MBUS_DATA_ENABLE_LOW;
+
 	bus->flags = flags;
 
 }
diff --git a/include/media/v4l2-mediabus.h b/include/media/v4l2-mediabus.h
index 4d8626c468bc..4bbb5f3d2b02 100644
--- a/include/media/v4l2-mediabus.h
+++ b/include/media/v4l2-mediabus.h
@@ -45,6 +45,8 @@
 /* Active state of Sync-on-green (SoG) signal, 0/1 for LOW/HIGH respectively. */
 #define V4L2_MBUS_VIDEO_SOG_ACTIVE_HIGH		BIT(12)
 #define V4L2_MBUS_VIDEO_SOG_ACTIVE_LOW		BIT(13)
+#define V4L2_MBUS_DATA_ENABLE_HIGH		BIT(14)
+#define V4L2_MBUS_DATA_ENABLE_LOW		BIT(15)
 
 /* Serial flags */
 /* How many lanes the client can use */
-- 
cgit v1.2.3


From d9b3c77a145e1754e93c49b6f494498f7b49dd09 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 9 Jul 2018 10:19:20 -0400
Subject: media: dt-bindings: media: rcar-vin: Add 'data-enable-active'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Describe optional endpoint property 'data-enable-active' for R-Car VIN.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/devicetree/bindings/media/rcar_vin.txt | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/rcar_vin.txt b/Documentation/devicetree/bindings/media/rcar_vin.txt
index b41086340018..2f420050d57f 100644
--- a/Documentation/devicetree/bindings/media/rcar_vin.txt
+++ b/Documentation/devicetree/bindings/media/rcar_vin.txt
@@ -55,6 +55,8 @@ The per-board settings Gen2 platforms:
       the SoC type and selected input image format.
       Valid values are: 8, 10, 12, 16, 24 and 32.
     - data-shift: see [1] for description. Valid values are 0 and 8.
+    - data-enable-active: polarity of CLKENB signal, see [1] for
+      description. Default is active high.
 
 The per-board settings Gen3 platforms:
 
-- 
cgit v1.2.3


From 53cf3100dd3af5f4ffbbe272e34f2150157aa425 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Mon, 9 Jul 2018 10:19:21 -0400
Subject: media: rcar-vin: Handle data-enable polarity
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Handle data-enable signal polarity. If the polarity is not specifically
requested to be active low, use the active high default.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-dma.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
index 1de598120286..9146f63430c2 100644
--- a/drivers/media/platform/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -123,6 +123,7 @@
 /* Video n Data Mode Register 2 bits */
 #define VNDMR2_VPS		(1 << 30)
 #define VNDMR2_HPS		(1 << 29)
+#define VNDMR2_CES		(1 << 28)
 #define VNDMR2_FTEV		(1 << 17)
 #define VNDMR2_VLV(n)		((n & 0xf) << 12)
 
@@ -698,6 +699,10 @@ static int rvin_setup(struct rvin_dev *vin)
 		/* Vsync Signal Polarity Select */
 		if (!(vin->parallel->mbus_flags & V4L2_MBUS_VSYNC_ACTIVE_LOW))
 			dmr2 |= VNDMR2_VPS;
+
+		/* Data Enable Polarity Select */
+		if (vin->parallel->mbus_flags & V4L2_MBUS_DATA_ENABLE_LOW)
+			dmr2 |= VNDMR2_CES;
 	}
 
 	/*
-- 
cgit v1.2.3


From 4adb0a0432f489c5eb802b33dae7737f69e6fd7a Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Mon, 18 Jun 2018 04:06:58 -0400
Subject: media: ov5645: Supported external clock is 24MHz

The external clock frequency was set to 23.88MHz by mistake
because of a platform which cannot get closer to 24MHz.
The supported by the driver external clock is 24MHz so
set it correctly and also fix the values of the pixel
clock and link clock.
However allow 1% tolerance to the external clock as this
difference is small enough to be insignificant.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov5645.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/media/i2c/ov5645.c b/drivers/media/i2c/ov5645.c
index b3f762578f7f..1722cdab0daf 100644
--- a/drivers/media/i2c/ov5645.c
+++ b/drivers/media/i2c/ov5645.c
@@ -510,8 +510,8 @@ static const struct reg_value ov5645_setting_full[] = {
 };
 
 static const s64 link_freq[] = {
-	222880000,
-	334320000
+	224000000,
+	336000000
 };
 
 static const struct ov5645_mode_info ov5645_mode_info_data[] = {
@@ -520,7 +520,7 @@ static const struct ov5645_mode_info ov5645_mode_info_data[] = {
 		.height = 960,
 		.data = ov5645_setting_sxga,
 		.data_size = ARRAY_SIZE(ov5645_setting_sxga),
-		.pixel_clock = 111440000,
+		.pixel_clock = 112000000,
 		.link_freq = 0 /* an index in link_freq[] */
 	},
 	{
@@ -528,7 +528,7 @@ static const struct ov5645_mode_info ov5645_mode_info_data[] = {
 		.height = 1080,
 		.data = ov5645_setting_1080p,
 		.data_size = ARRAY_SIZE(ov5645_setting_1080p),
-		.pixel_clock = 167160000,
+		.pixel_clock = 168000000,
 		.link_freq = 1 /* an index in link_freq[] */
 	},
 	{
@@ -536,7 +536,7 @@ static const struct ov5645_mode_info ov5645_mode_info_data[] = {
 		.height = 1944,
 		.data = ov5645_setting_full,
 		.data_size = ARRAY_SIZE(ov5645_setting_full),
-		.pixel_clock = 167160000,
+		.pixel_clock = 168000000,
 		.link_freq = 1 /* an index in link_freq[] */
 	},
 };
@@ -1145,7 +1145,8 @@ static int ov5645_probe(struct i2c_client *client,
 		return ret;
 	}
 
-	if (xclk_freq != 23880000) {
+	/* external clock must be 24MHz, allow 1% tolerance */
+	if (xclk_freq < 23760000 || xclk_freq > 24240000) {
 		dev_err(dev, "external clock frequency %u is not supported\n",
 			xclk_freq);
 		return -EINVAL;
-- 
cgit v1.2.3


From 09a48f74e4e379af07aef7e2eb48a9be482aa8ff Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Thu, 31 May 2018 13:35:03 -0400
Subject: media: i2c: ov7670: Put ep fwnode after use

The just parsed endpoint fwnode has to be put after use.
Currently this is done only in error handling path. Fix that by
putting node unconditionally after use.

Fixes: 01b8444828fc ("media: v4l2: i2c: ov7670: Implement OF mbus configuration")

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ov7670.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/media/i2c/ov7670.c b/drivers/media/i2c/ov7670.c
index 3474ef832c1e..31bf577b0bd3 100644
--- a/drivers/media/i2c/ov7670.c
+++ b/drivers/media/i2c/ov7670.c
@@ -1744,14 +1744,12 @@ static int ov7670_parse_dt(struct device *dev,
 		return -EINVAL;
 
 	ret = v4l2_fwnode_endpoint_parse(ep, &bus_cfg);
-	if (ret) {
-		fwnode_handle_put(ep);
+	fwnode_handle_put(ep);
+	if (ret)
 		return ret;
-	}
 
 	if (bus_cfg.bus_type != V4L2_MBUS_PARALLEL) {
 		dev_err(dev, "Unsupported media bus type\n");
-		fwnode_handle_put(ep);
 		return ret;
 	}
 	info->mbus_config = bus_cfg.bus.parallel.flags;
-- 
cgit v1.2.3


From be9543ec9e7423894473ec9314023e505e26fc52 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 16 Jul 2018 11:20:33 -0400
Subject: media: v4l: i2c: Replace "sensor-level" by "sensor"

A lot of sensor drivers are labelled as "sensor-level" drivers. That's
odd and somewhat confusing as the term isn't used elsewhere: these are
just sensor drivers. Call them such.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/Kconfig | 62 +++++++++++++++++++++++------------------------
 1 file changed, 31 insertions(+), 31 deletions(-)

diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 8669853e1361..5ee7a09001a7 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -398,7 +398,7 @@ config VIDEO_TVP514X
 	depends on VIDEO_V4L2 && I2C
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the TI TVP5146/47
+	  This is a Video4Linux2 sensor driver for the TI TVP5146/47
 	  decoder. It is currently working with the TI OMAP3 camera
 	  controller.
 
@@ -600,7 +600,7 @@ config VIDEO_IMX258
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Sony
+	  This is a Video4Linux2 sensor driver for the Sony
 	  IMX258 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -611,7 +611,7 @@ config VIDEO_IMX274
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a V4L2 sensor-level driver for the Sony IMX274
+	  This is a V4L2 sensor driver for the Sony IMX274
 	  CMOS image sensor.
 
 config VIDEO_OV2640
@@ -619,7 +619,7 @@ config VIDEO_OV2640
 	depends on VIDEO_V4L2 && I2C
 	depends on MEDIA_CAMERA_SUPPORT
 	help
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV2640 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -631,7 +631,7 @@ config VIDEO_OV2659
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV2659 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -643,7 +643,7 @@ config VIDEO_OV2685
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV2685 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -656,7 +656,7 @@ config VIDEO_OV5640
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Omnivision
+	  This is a Video4Linux2 sensor driver for the Omnivision
 	  OV5640 camera sensor with a MIPI CSI-2 interface.
 
 config VIDEO_OV5645
@@ -666,7 +666,7 @@ config VIDEO_OV5645
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5645 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -678,7 +678,7 @@ config VIDEO_OV5647
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5647 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -689,7 +689,7 @@ config VIDEO_OV6650
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV6650 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -702,7 +702,7 @@ config VIDEO_OV5670
 	depends on MEDIA_CONTROLLER
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5670 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -713,7 +713,7 @@ config VIDEO_OV5695
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV5695 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -725,7 +725,7 @@ config VIDEO_OV7251
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	help
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7251 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -736,7 +736,7 @@ config VIDEO_OV772X
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV772x camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -747,7 +747,7 @@ config VIDEO_OV7640
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7640 camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -759,7 +759,7 @@ config VIDEO_OV7670
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7670 VGA camera.  It currently only works with the M88ALP01
 	  controller.
 
@@ -768,14 +768,14 @@ config VIDEO_OV7740
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV7740 VGA camera sensor.
 
 config VIDEO_OV9650
 	tristate "OmniVision OV9650/OV9652 sensor support"
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	---help---
-	  This is a V4L2 sensor-level driver for the Omnivision
+	  This is a V4L2 sensor driver for the Omnivision
 	  OV9650 and OV9652 camera sensors.
 
 config VIDEO_OV13858
@@ -784,7 +784,7 @@ config VIDEO_OV13858
 	depends on MEDIA_CAMERA_SUPPORT
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the OmniVision
+	  This is a Video4Linux2 sensor driver for the OmniVision
 	  OV13858 camera.
 
 config VIDEO_VS6624
@@ -792,7 +792,7 @@ config VIDEO_VS6624
 	depends on VIDEO_V4L2 && I2C
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the ST VS6624
+	  This is a Video4Linux2 sensor driver for the ST VS6624
 	  camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -820,7 +820,7 @@ config VIDEO_MT9P031
 	depends on MEDIA_CAMERA_SUPPORT
 	select VIDEO_APTINA_PLL
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Aptina
+	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) mt9p031 5 Mpixel camera.
 
 config VIDEO_MT9T001
@@ -828,7 +828,7 @@ config VIDEO_MT9T001
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Aptina
+	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) mt0t001 3 Mpixel camera.
 
 config VIDEO_MT9T112
@@ -836,7 +836,7 @@ config VIDEO_MT9T112
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Aptina
+	  This is a Video4Linux2 sensor driver for the Aptina
 	  (Micron) MT9T111 and MT9T112 3 Mpixel camera.
 
 	  To compile this driver as a module, choose M here: the
@@ -847,7 +847,7 @@ config VIDEO_MT9V011
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Micron
+	  This is a Video4Linux2 sensor driver for the Micron
 	  mt0v011 1.3 Mpixel camera.  It currently only works with the
 	  em28xx driver.
 
@@ -858,7 +858,7 @@ config VIDEO_MT9V032
 	select REGMAP_I2C
 	select V4L2_FWNODE
 	---help---
-	  This is a Video4Linux2 sensor-level driver for the Micron
+	  This is a Video4Linux2 sensor driver for the Micron
 	  MT9V032 752x480 CMOS sensor.
 
 config VIDEO_SR030PC30
@@ -882,7 +882,7 @@ config VIDEO_RJ54N1
 	depends on I2C && VIDEO_V4L2
 	depends on MEDIA_CAMERA_SUPPORT
 	help
-	  This is a V4L2 sensor-level driver for Sharp RJ54N1CB0C CMOS image
+	  This is a V4L2 sensor driver for Sharp RJ54N1CB0C CMOS image
 	  sensor.
 
 	  To compile this driver as a module, choose M here: the
@@ -893,7 +893,7 @@ config VIDEO_S5K6AA
 	depends on MEDIA_CAMERA_SUPPORT
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K6AA(FX) 1.3M
+	  This is a V4L2 sensor driver for Samsung S5K6AA(FX) 1.3M
 	  camera sensor with an embedded SoC image signal processor.
 
 config VIDEO_S5K6A3
@@ -901,7 +901,7 @@ config VIDEO_S5K6A3
 	depends on MEDIA_CAMERA_SUPPORT
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K6A3 raw
+	  This is a V4L2 sensor driver for Samsung S5K6A3 raw
 	  camera sensor.
 
 config VIDEO_S5K4ECGX
@@ -909,7 +909,7 @@ config VIDEO_S5K4ECGX
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	select CRC32
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K4ECGX 5M
+	  This is a V4L2 sensor driver for Samsung S5K4ECGX 5M
 	  camera sensor with an embedded SoC image signal processor.
 
 config VIDEO_S5K5BAF
@@ -917,7 +917,7 @@ config VIDEO_S5K5BAF
 	depends on I2C && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5K5BAF 2M
+	  This is a V4L2 sensor driver for Samsung S5K5BAF 2M
 	  camera sensor with an embedded SoC image signal processor.
 
 source "drivers/media/i2c/smiapp/Kconfig"
@@ -928,7 +928,7 @@ config VIDEO_S5C73M3
 	depends on I2C && SPI && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	select V4L2_FWNODE
 	---help---
-	  This is a V4L2 sensor-level driver for Samsung S5C73M3
+	  This is a V4L2 sensor driver for Samsung S5C73M3
 	  8 Mpixel camera.
 
 comment "Flash devices"
-- 
cgit v1.2.3


From cafec5a7e0cb6df1adff515e6ec69911d3362f89 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 19:52:53 +0200
Subject: pinctrl: samsung: Define suspend and resume callbacks for all banks
 and SoCs

Suspend and resume callbacks in Exynos/S5Pv210 pin controller drivers,
save and restore state of registers.  This operations should be done for
all banks which have external interrupts (as denoted by using
EXYNOS_PIN_BANK_EINTG/EINTW macros).

Add all banks of Exynos5260 and Exynos5420.  This is necessary step for
supporting suspend to RAM on these SoCs.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Tomasz Figa <tomasz.figa@gmail.com>
Cc: Sylwester Nawrocki <snawrocki@kernel.org>
Acked-by: Tomasz Figa <tomasz.figa@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 drivers/pinctrl/samsung/pinctrl-exynos-arm.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
index d82820fc349a..44c6b753f692 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos-arm.c
@@ -616,16 +616,22 @@ static const struct samsung_pin_ctrl exynos5260_pin_ctrl[] __initconst = {
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks0),
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	}, {
 		/* pin-controller instance 1 data */
 		.pin_banks	= exynos5260_pin_banks1,
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks1),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	}, {
 		/* pin-controller instance 2 data */
 		.pin_banks	= exynos5260_pin_banks2,
 		.nr_banks	= ARRAY_SIZE(exynos5260_pin_banks2),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 	},
 };
 
@@ -842,30 +848,40 @@ static const struct samsung_pin_ctrl exynos5420_pin_ctrl[] __initconst = {
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks0),
 		.eint_gpio_init = exynos_eint_gpio_init,
 		.eint_wkup_init = exynos_eint_wkup_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 1 data */
 		.pin_banks	= exynos5420_pin_banks1,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks1),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 2 data */
 		.pin_banks	= exynos5420_pin_banks2,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks2),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 3 data */
 		.pin_banks	= exynos5420_pin_banks3,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks3),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos5420_retention_data,
 	}, {
 		/* pin-controller instance 4 data */
 		.pin_banks	= exynos5420_pin_banks4,
 		.nr_banks	= ARRAY_SIZE(exynos5420_pin_banks4),
 		.eint_gpio_init = exynos_eint_gpio_init,
+		.suspend	= exynos_pinctrl_suspend,
+		.resume		= exynos_pinctrl_resume,
 		.retention_data	= &exynos4_audio_retention_data,
 	},
 };
-- 
cgit v1.2.3


From 00d6fff37066e96814796d05e1c6e8131f38576a Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 19:52:54 +0200
Subject: pinctrl: samsung: Document suspend and resume members

Add missing documentation for suspend and resume members of struct
samsung_pin_ctrl and samsung_pinctrl_drv_data.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Tomasz Figa <tomasz.figa@gmail.com>
Cc: Sylwester Nawrocki <snawrocki@kernel.org>
Acked-by: Tomasz Figa <tomasz.figa@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 drivers/pinctrl/samsung/pinctrl-samsung.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index f0cda9424dfe..aac16cc8362a 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -223,6 +223,10 @@ struct samsung_retention_data {
  *	interrupts for the controller.
  * @eint_wkup_init: platform specific callback to setup the external wakeup
  *	interrupts for the controller.
+ * @suspend: platform specific suspend callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_suspend()
+ * @resume: platform specific resume callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_resume()
  */
 struct samsung_pin_ctrl {
 	const struct samsung_pin_bank_data *pin_banks;
@@ -255,6 +259,10 @@ struct samsung_pin_ctrl {
  * @pin_base: starting system wide pin number.
  * @nr_pins: number of pins supported by the controller.
  * @retention_ctrl: retention control runtime data.
+ * @suspend: platform specific suspend callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_suspend()
+ * @resume: platform specific resume callback, executed during pin controller
+ *	device suspend, see samsung_pinctrl_resume()
  */
 struct samsung_pinctrl_drv_data {
 	struct list_head		node;
-- 
cgit v1.2.3


From 39a8883a2b989d1d21bd8dd99f5557f0c5e89694 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Tue, 17 Jul 2018 18:24:27 -0400
Subject: random: add a config option to trust the CPU's hwrng

This gives the user building their own kernel (or a Linux
distribution) the option of deciding whether or not to trust the CPU's
hardware random number generator (e.g., RDRAND for x86 CPU's) as being
correctly implemented and not having a back door introduced (perhaps
courtesy of a Nation State's law enforcement or intelligence
agencies).

This will prevent getrandom(2) from blocking, if there is a
willingness to trust the CPU manufacturer.

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/Kconfig  | 14 ++++++++++++++
 drivers/char/random.c | 11 ++++++++++-
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig
index 212f447938ae..ce277ee0a28a 100644
--- a/drivers/char/Kconfig
+++ b/drivers/char/Kconfig
@@ -554,3 +554,17 @@ config ADI
 
 endmenu
 
+config RANDOM_TRUST_CPU
+	bool "Trust the CPU manufacturer to initialize Linux's CRNG"
+	depends on X86 || S390 || PPC
+	default n
+	help
+	Assume that CPU manufacturer (e.g., Intel or AMD for RDSEED or
+	RDRAND, IBM for the S390 and Power PC architectures) is trustworthy
+	for the purposes of initializing Linux's CRNG.  Since this is not
+	something that can be independently audited, this amounts to trusting
+	that CPU manufacturer (perhaps with the insistence or mandate
+	of a Nation State's intelligence or law enforcement agencies)
+	has not installed a hidden back door to compromise the CPU's
+	random number generation facilities.
+
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 34ddfd57419b..f4013b8a711b 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -782,6 +782,7 @@ static void invalidate_batched_entropy(void);
 static void crng_initialize(struct crng_state *crng)
 {
 	int		i;
+	int		arch_init = 1;
 	unsigned long	rv;
 
 	memcpy(&crng->state[0], "expand 32-byte k", 16);
@@ -792,10 +793,18 @@ static void crng_initialize(struct crng_state *crng)
 		_get_random_bytes(&crng->state[4], sizeof(__u32) * 12);
 	for (i = 4; i < 16; i++) {
 		if (!arch_get_random_seed_long(&rv) &&
-		    !arch_get_random_long(&rv))
+		    !arch_get_random_long(&rv)) {
 			rv = random_get_entropy();
+			arch_init = 0;
+		}
 		crng->state[i] ^= rv;
 	}
+#ifdef CONFIG_RANDOM_TRUST_CPU
+	if (arch_init) {
+		crng_init = 2;
+		pr_notice("random: crng done (trusting CPU's manufacturer)\n");
+	}
+#endif
 	crng->init_time = jiffies - CRNG_RESEED_INTERVAL - 1;
 }
 
-- 
cgit v1.2.3


From 615a673ce9a99122a3a44e5dee2f61bae82a757c Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 19:52:55 +0200
Subject: pinctrl: samsung: Document hidden requirement about one external
 wakeup

ARMv7 hardware (S5Pv210 and Exynos SoCs) provides only 32 external
interrupts which can wakeup device from deep sleep modes.  On S5Pv210
these are gph0-gph3.  On all ARMv7 Exynos designs these are gpx0-gpx3.
There is only one 32-bit register for controlling the external wakeup
interrupt mask (masking and unmasking waking capability of these
interrupts).

This lead to implementation in pinctrl driver and machine code which was
using static memory for storing the mask value and not caring about
multiple devices of pin controller... because only one pin controller
device will be handling this.

Since each pin controller node in Device Tree maps onto one device, this
corresponds to hidden assumption in parsing the Device Tree: external
wakeup interrupts can be defined only once.  Make this assumption an
explicit requirement.

ARMv8 Exynos5433 and Exynos7 bring additional 32 external wakeup
interrupts (up to 64 total, banks gpa0-gpa3 and gpf1-gpf5) and another
32-bit wide register for controlling them.  Existing code does not
support it but anyway these additional interrupts will be belonging to
the same pin controller device/node.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Tomasz Figa <tomasz.figa@gmail.com>
Cc: Sylwester Nawrocki <snawrocki@kernel.org>
Acked-by: Tomasz Figa <tomasz.figa@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
index 5e00a21de2bf..f7700c9e0d0b 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
@@ -145,8 +145,13 @@ A. External GPIO Interrupts: For supporting external gpio interrupts, the
 
 B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
    child node representing the external wakeup interrupt controller should be
-   included in the pin-controller device node. This child node should include
-   the following properties.
+   included in the pin-controller device node.
+
+   Only one pin-controller device node can include external wakeup interrupts
+   child node (in other words, only one External Wakeup Interrupts
+   pin-controller is supported).
+
+   This child node should include following properties:
 
    - compatible: identifies the type of the external wakeup interrupt controller
      The possible values are:
-- 
cgit v1.2.3


From b34fbaa9289328c7aec67d2b8b8b7d02bc61c67d Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@elte.hu>
Date: Sun, 22 Jul 2018 10:51:50 -0400
Subject: random: remove preempt disabled region

No need to keep preemption disabled across the whole function.

mix_pool_bytes() uses a spin_lock() to protect the pool and there are
other places like write_pool() whhich invoke mix_pool_bytes() without
disabling preemption.
credit_entropy_bits() is invoked from other places like
add_hwgenerator_randomness() without disabling preemption.

Before commit 95b709b6be49 ("random: drop trickle mode") the function
used __this_cpu_inc_return() which would require disabled preemption.
The preempt_disable() section was added in commit 43d5d3018c37 ("[PATCH]
random driver preempt robustness", history tree).  It was claimed that
the code relied on "vt_ioctl() being called under BKL".

Cc: "Theodore Ts'o" <tytso@mit.edu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
[bigeasy: enhance the commit message]
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index f4013b8a711b..561082d46a82 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1131,8 +1131,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	} sample;
 	long delta, delta2, delta3;
 
-	preempt_disable();
-
 	sample.jiffies = jiffies;
 	sample.cycles = random_get_entropy();
 	sample.num = num;
@@ -1170,8 +1168,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
 	 * and limit entropy entimate to 12 bits.
 	 */
 	credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
-
-	preempt_enable();
 }
 
 void add_input_randomness(unsigned int type, unsigned int code,
-- 
cgit v1.2.3


From bb928dfd06e5e5cef0b090ba23e894b2f37ee14e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 19:52:56 +0200
Subject: pinctrl: samsung: Add dedicated compatible for S5Pv210 wakeup
 interrupts

The S5Pv210 external wakeup interrupts differ from Exynos therefore
separate compatible is needed.  Duplicate existing flavor specific data
from exynos4210_wkup_irq_chip and add new compatible for S5Pv210.
At this point this new compatible does not bring anything new and works
exactly as existing "samsung,exynos4210-wakeup-eint".

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Tomasz Figa <tomasz.figa@gmail.com>
Cc: Sylwester Nawrocki <snawrocki@kernel.org>
Acked-by: Tomasz Figa <tomasz.figa@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 .../devicetree/bindings/pinctrl/samsung-pinctrl.txt    |  2 ++
 drivers/pinctrl/samsung/pinctrl-exynos.c               | 18 ++++++++++++++++++
 2 files changed, 20 insertions(+)

diff --git a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
index f7700c9e0d0b..843a6cbf4774 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
@@ -161,6 +161,8 @@ B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
        found on Samsung S3C2412 and S3C2413 SoCs,
      - samsung,s3c64xx-wakeup-eint: represents wakeup interrupt controller
        found on Samsung S3C64xx SoCs,
+     - samsung,s5pv210-wakeup-eint: represents wakeup interrupt controller
+       found on Samsung S5Pv210 SoCs,
      - samsung,exynos4210-wakeup-eint: represents wakeup interrupt controller
        found on Samsung Exynos4210 and S5PC110/S5PV210 SoCs.
      - samsung,exynos7-wakeup-eint: represents wakeup interrupt controller
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index a263ddd94945..29d86d704b0c 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -346,6 +346,22 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 /*
  * irq_chip for wakeup interrupts
  */
+static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = {
+	.chip = {
+		.name = "s5pv210_wkup_irq_chip",
+		.irq_unmask = exynos_irq_unmask,
+		.irq_mask = exynos_irq_mask,
+		.irq_ack = exynos_irq_ack,
+		.irq_set_type = exynos_irq_set_type,
+		.irq_set_wake = exynos_wkup_irq_set_wake,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
+	},
+	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
+	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
+	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
+};
+
 static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.chip = {
 		.name = "exynos4210_wkup_irq_chip",
@@ -380,6 +396,8 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 
 /* list of external wakeup controllers supported */
 static const struct of_device_id exynos_wkup_irq_ids[] = {
+	{ .compatible = "samsung,s5pv210-wakeup-eint",
+			.data = &s5pv210_wkup_irq_chip },
 	{ .compatible = "samsung,exynos4210-wakeup-eint",
 			.data = &exynos4210_wkup_irq_chip },
 	{ .compatible = "samsung,exynos7-wakeup-eint",
-- 
cgit v1.2.3


From e5cda42c16d89720c29678f51d95a119490ef7d8 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 19:52:57 +0200
Subject: ARM: exynos: Define EINT_WAKEUP_MASK registers for S5Pv210 and
 Exynos5433

S5Pv210 and Exynos5433/Exynos7 have different address of
EINT_WAKEUP_MASK register.  Rename existing S5P_EINT_WAKEUP_MASK to
avoid confusion and add new ones.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Tomasz Figa <tomasz.figa@gmail.com>
Cc: Sylwester Nawrocki <snawrocki@kernel.org>
Acked-by: Tomasz Figa <tomasz.figa@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 arch/arm/mach-exynos/suspend.c              | 2 +-
 include/linux/soc/samsung/exynos-regs-pmu.h | 6 +++++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/arm/mach-exynos/suspend.c b/arch/arm/mach-exynos/suspend.c
index d3db306a5a70..f3384e3a675d 100644
--- a/arch/arm/mach-exynos/suspend.c
+++ b/arch/arm/mach-exynos/suspend.c
@@ -272,7 +272,7 @@ static int exynos5420_cpu_suspend(unsigned long arg)
 static void exynos_pm_set_wakeup_mask(void)
 {
 	/* Set wake-up mask registers */
-	pmu_raw_writel(exynos_get_eint_wake_mask(), S5P_EINT_WAKEUP_MASK);
+	pmu_raw_writel(exynos_get_eint_wake_mask(), EXYNOS_EINT_WAKEUP_MASK);
 	pmu_raw_writel(exynos_irqwake_intmask & ~(1 << 31), S5P_WAKEUP_MASK);
 }
 
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index 66dcb9ec273a..eb0d240df7a7 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -42,7 +42,7 @@
 #define EXYNOS_SWRESET				0x0400
 
 #define S5P_WAKEUP_STAT				0x0600
-#define S5P_EINT_WAKEUP_MASK			0x0604
+#define EXYNOS_EINT_WAKEUP_MASK			0x0604
 #define S5P_WAKEUP_MASK				0x0608
 #define S5P_WAKEUP_MASK2				0x0614
 
@@ -180,6 +180,9 @@
 #define S5P_CORE_WAKEUP_FROM_LOCAL_CFG		(0x3 << 8)
 #define S5P_CORE_AUTOWAKEUP_EN			(1 << 31)
 
+/* Only for S5Pv210 */
+#define S5PV210_EINT_WAKEUP_MASK	0xC004
+
 /* Only for EXYNOS4210 */
 #define S5P_CMU_CLKSTOP_LCD1_LOWPWR	0x1154
 #define S5P_CMU_RESET_LCD1_LOWPWR	0x1174
@@ -641,6 +644,7 @@
 					 | EXYNOS5420_KFC_USE_STANDBY_WFI3)
 
 /* For EXYNOS5433 */
+#define EXYNOS5433_EINT_WAKEUP_MASK				(0x060C)
 #define EXYNOS5433_USBHOST30_PHY_CONTROL			(0x0728)
 #define EXYNOS5433_PAD_RETENTION_AUD_OPTION			(0x3028)
 #define EXYNOS5433_PAD_RETENTION_MMC2_OPTION			(0x30C8)
-- 
cgit v1.2.3


From a8be2af0218cf037704dc2e733bf56d6560fa324 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 19:52:58 +0200
Subject: pinctrl: samsung: Write external wakeup interrupt mask

The pinctrl driver defines an IRQ chip which handles external wakeup
interrupts, therefore from logical point of view, it is the owner of
external interrupt mask.  The register controlling the mask belongs to
Power Management Unit address space so it has to be accessed with PMU
syscon regmap handle.

This mask should be written to hardware during system suspend.  Till now
ARMv7 machine code was responsible for this which created a dependency
between pin controller driver and arch/arm/mach code.

Try to rework this dependency so the pinctrl driver will write external
wakeup interrupt mask during late suspend.

Impact on ARMv7 designs (S5Pv210 and Exynos)
============================================
This duplicates setting mask with existing machine code
arch/arm/mach-exynos/suspend.c and arch/arm/mach-s5pv210/pm.c but it is
not a problem - the wakeup mask register will be written twice.  The
machine code will be cleaned up later.

The difference between implementation here and ARMv7 machine code
(arch/arm/mach-*) is the time of writing the mask:
1. The machine code is writing the mask quite late during system suspend
   path, after offlining secondary CPUs and just before doing actual
   suspend.
2. The implementation in pinctrl driver uses late suspend ops, therefore it
   will write the mask much earlier.  Hopefully late enough, after all
   drivers will enable or disable their interrupt wakeups
   (enable_irq_wake() etc).

Impact on ARMv8 designs (Exynos5433 and Exynos7)
================================================
The Suspend to RAM was not supported and external wakeup interrupt mask
was not written to HW.  This change brings us one step closer to
supporting Suspend to RAM.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Cc: Tomasz Figa <tomasz.figa@gmail.com>
Cc: Sylwester Nawrocki <snawrocki@kernel.org>
Acked-by: Tomasz Figa <tomasz.figa@gmail.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
---
 drivers/pinctrl/samsung/pinctrl-exynos.c    | 50 ++++++++++++++++++++++++++++-
 drivers/pinctrl/samsung/pinctrl-samsung.h   |  3 ++
 include/linux/soc/samsung/exynos-regs-pmu.h |  2 ++
 3 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 29d86d704b0c..40ef14956876 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -25,6 +25,7 @@
 #include <linux/regmap.h>
 #include <linux/err.h>
 #include <linux/soc/samsung/exynos-pmu.h>
+#include <linux/soc/samsung/exynos-regs-pmu.h>
 
 #include <dt-bindings/pinctrl/samsung.h>
 
@@ -37,6 +38,8 @@ struct exynos_irq_chip {
 	u32 eint_con;
 	u32 eint_mask;
 	u32 eint_pend;
+	u32 eint_wake_mask_value;
+	u32 eint_wake_mask_reg;
 };
 
 static inline struct exynos_irq_chip *to_exynos_irq_chip(struct irq_chip *chip)
@@ -215,6 +218,7 @@ static struct exynos_irq_chip exynos_gpio_irq_chip = {
 	.eint_con = EXYNOS_GPIO_ECON_OFFSET,
 	.eint_mask = EXYNOS_GPIO_EMASK_OFFSET,
 	.eint_pend = EXYNOS_GPIO_EPEND_OFFSET,
+	/* eint_wake_mask_value not used */
 };
 
 static int exynos_eint_irq_map(struct irq_domain *h, unsigned int virq,
@@ -330,6 +334,8 @@ u32 exynos_get_eint_wake_mask(void)
 
 static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 {
+	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
+	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
 	unsigned long bit = 1UL << (2 * bank->eint_offset + irqd->hwirq);
 
@@ -339,6 +345,7 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 		exynos_eint_wake_mask |= bit;
 	else
 		exynos_eint_wake_mask &= ~bit;
+	our_chip->eint_wake_mask_value = exynos_eint_wake_mask;
 
 	return 0;
 }
@@ -360,6 +367,9 @@ static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	/* Only difference with exynos4210_wkup_irq_chip: */
+	.eint_wake_mask_reg = S5PV210_EINT_WAKEUP_MASK,
 };
 
 static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
@@ -376,6 +386,8 @@ static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	.eint_wake_mask_reg = EXYNOS_EINT_WAKEUP_MASK,
 };
 
 static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
@@ -392,6 +404,8 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS7_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS7_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS7_WKUP_EPEND_OFFSET,
+	.eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
 };
 
 /* list of external wakeup controllers supported */
@@ -560,6 +574,27 @@ int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d)
 	return 0;
 }
 
+static void
+exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
+				    struct exynos_irq_chip *irq_chip)
+{
+	struct regmap *pmu_regs;
+
+	if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) {
+		dev_warn(drvdata->dev,
+			 "No retention data configured bank with external wakeup interrupt. Wake-up mask will not be set.\n");
+		return;
+	}
+
+	pmu_regs = drvdata->retention_ctrl->priv;
+	dev_info(drvdata->dev,
+		 "Setting external wakeup interrupt wakeup mask: 0x%x\n",
+		 irq_chip->eint_wake_mask_value);
+
+	regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg,
+		     irq_chip->eint_wake_mask_value);
+}
+
 static void exynos_pinctrl_suspend_bank(
 				struct samsung_pinctrl_drv_data *drvdata,
 				struct samsung_pin_bank *bank)
@@ -582,11 +617,24 @@ static void exynos_pinctrl_suspend_bank(
 void exynos_pinctrl_suspend(struct samsung_pinctrl_drv_data *drvdata)
 {
 	struct samsung_pin_bank *bank = drvdata->pin_banks;
+	struct exynos_irq_chip *irq_chip = NULL;
 	int i;
 
-	for (i = 0; i < drvdata->nr_banks; ++i, ++bank)
+	for (i = 0; i < drvdata->nr_banks; ++i, ++bank) {
 		if (bank->eint_type == EINT_TYPE_GPIO)
 			exynos_pinctrl_suspend_bank(drvdata, bank);
+		else if (bank->eint_type == EINT_TYPE_WKUP) {
+			if (!irq_chip) {
+				irq_chip = bank->irq_chip;
+				exynos_pinctrl_set_eint_wakeup_mask(drvdata,
+								    irq_chip);
+			} else if (bank->irq_chip != irq_chip) {
+				dev_warn(drvdata->dev,
+					 "More than one external wakeup interrupt chip configured (bank: %s). This is not supported by hardware nor by driver.\n",
+					 bank->name);
+			}
+		}
+	}
 }
 
 static void exynos_pinctrl_resume_bank(
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index aac16cc8362a..e571bbd7139b 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -227,6 +227,9 @@ struct samsung_retention_data {
  *	device suspend, see samsung_pinctrl_suspend()
  * @resume: platform specific resume callback, executed during pin controller
  *	device suspend, see samsung_pinctrl_resume()
+ *
+ * External wakeup interrupts must define at least eint_wkup_init,
+ * retention_data and suspend in order for proper suspend/resume to work.
  */
 struct samsung_pin_ctrl {
 	const struct samsung_pin_bank_data *pin_banks;
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index eb0d240df7a7..5addaf5ccbce 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -42,6 +42,8 @@
 #define EXYNOS_SWRESET				0x0400
 
 #define S5P_WAKEUP_STAT				0x0600
+/* Value for EXYNOS_EINT_WAKEUP_MASK disabling all external wakeup interrupts */
+#define EXYNOS_EINT_WAKEUP_MASK_DISABLED	0xffffffff
 #define EXYNOS_EINT_WAKEUP_MASK			0x0604
 #define S5P_WAKEUP_MASK				0x0608
 #define S5P_WAKEUP_MASK2				0x0614
-- 
cgit v1.2.3


From b3793159249bb091efce4b1515ce18cdfc4c6e41 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Wed, 18 Jul 2018 22:03:50 +0200
Subject: dt-bindings: pinctrl: samsung: Add SPDX license identifier

Replace GPL license statement with SPDX license identifier (GPL-2.0).

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
---
 include/dt-bindings/pinctrl/samsung.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/include/dt-bindings/pinctrl/samsung.h b/include/dt-bindings/pinctrl/samsung.h
index ceb672305f59..b1832506b923 100644
--- a/include/dt-bindings/pinctrl/samsung.h
+++ b/include/dt-bindings/pinctrl/samsung.h
@@ -1,14 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Samsung's Exynos pinctrl bindings
  *
  * Copyright (c) 2016 Samsung Electronics Co., Ltd.
  *		http://www.samsung.com
  * Author: Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
-*/
+ */
 
 #ifndef __DT_BINDINGS_PINCTRL_SAMSUNG_H__
 #define __DT_BINDINGS_PINCTRL_SAMSUNG_H__
-- 
cgit v1.2.3


From 226127a67e31a9518d9516d3e4890759b379d874 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Thu, 19 Jul 2018 18:33:39 +0200
Subject: drm/amdgpu: Fix RLC safe mode test in gfx_v9_0_enter_rlc_safe_mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We were testing the register offset, instead of the value stored in the
register, therefore always timing out the loop.

This reduces suspend time of the system in the bug report below by ~600
ms.

Cc: stable@vger.kernel.org
Bugzilla: https://bugs.freedesktop.org/107277
Tested-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
index 9ab39117cc4e..ef00d14f8645 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c
@@ -3490,7 +3490,7 @@ static void gfx_v9_0_enter_rlc_safe_mode(struct amdgpu_device *adev)
 
 		/* wait for RLC_SAFE_MODE */
 		for (i = 0; i < adev->usec_timeout; i++) {
-			if (!REG_GET_FIELD(SOC15_REG_OFFSET(GC, 0, mmRLC_SAFE_MODE), RLC_SAFE_MODE, CMD))
+			if (!REG_GET_FIELD(RREG32_SOC15(GC, 0, mmRLC_SAFE_MODE), RLC_SAFE_MODE, CMD))
 				break;
 			udelay(1);
 		}
-- 
cgit v1.2.3


From 59a8348fc5b363a0c19be73bc9f5790e0f8f803a Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Fri, 20 Jul 2018 10:13:19 +0800
Subject: drm/amd/powerplay: slow UCLK switch when multiple displays not in
 sync

Slow switch for UCLK when there is multiple displays and they are
not in sync.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Rex Zhu <rex.zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 6d93d52975ec..94e847e34b72 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3800,7 +3800,8 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 	uint32_t i;
 	struct pp_display_clock_request clock_req;
 
-	if (hwmgr->display_config->num_display > 1)
+	if ((hwmgr->display_config->num_display > 1) &&
+	     !hwmgr->display_config->multi_monitor_in_sync)
 		vega10_notify_smc_display_change(hwmgr, false);
 	else
 		vega10_notify_smc_display_change(hwmgr, true);
-- 
cgit v1.2.3


From f132d56162e670d2338902753b88ecbf29ca46a0 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 16 Jul 2018 17:23:19 +0800
Subject: drm/amd/powerplay: correct the argument for
 PPSMC_MSG_SetUclkFastSwitch

The argument was set wrongly. Fast/slow switch was asked when there is
actually a slow/fast switch needed.

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Rex Zhu <rex.zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 2 +-
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 94e847e34b72..9f5ceee0fa63 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3725,7 +3725,7 @@ static void vega10_notify_smc_display_change(struct pp_hwmgr *hwmgr,
 {
 	smum_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetUclkFastSwitch,
-			has_disp ? 0 : 1);
+			has_disp ? 1 : 0);
 }
 
 int vega10_display_clock_voltage_request(struct pp_hwmgr *hwmgr,
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 4ed218dd8ba7..35f96dacb50a 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1334,7 +1334,7 @@ static int vega12_notify_smc_display_change(struct pp_hwmgr *hwmgr,
 	if (data->smu_features[GNLD_DPM_UCLK].enabled)
 		return smum_send_msg_to_smc_with_parameter(hwmgr,
 			PPSMC_MSG_SetUclkFastSwitch,
-			has_disp ? 0 : 1);
+			has_disp ? 1 : 0);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 92859e0d5ce558df44eb05f7d5872edc96646b24 Mon Sep 17 00:00:00 2001
From: Evan Quan <evan.quan@amd.com>
Date: Mon, 16 Jul 2018 17:25:30 +0800
Subject: drm/amd/powerplay: allow slow switch only if NBPState enabled v2

Otherwise there may be potential SMU performance issues.

v2: fix commit description and coding style

Signed-off-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Rex Zhu <rex.zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 3 ++-
 drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
index 9f5ceee0fa63..fb86c24394ff 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c
@@ -3801,7 +3801,8 @@ static int vega10_notify_smc_display_config_after_ps_adjustment(
 	struct pp_display_clock_request clock_req;
 
 	if ((hwmgr->display_config->num_display > 1) &&
-	     !hwmgr->display_config->multi_monitor_in_sync)
+	     !hwmgr->display_config->multi_monitor_in_sync &&
+	     !hwmgr->display_config->nb_pstate_switch_disable)
 		vega10_notify_smc_display_change(hwmgr, false);
 	else
 		vega10_notify_smc_display_change(hwmgr, true);
diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
index 35f96dacb50a..0789d64246ca 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega12_hwmgr.c
@@ -1389,7 +1389,8 @@ static int vega12_notify_smc_display_config_after_ps_adjustment(
 	struct pp_display_clock_request clock_req;
 
 	if ((hwmgr->display_config->num_display > 1) &&
-		!hwmgr->display_config->multi_monitor_in_sync)
+	     !hwmgr->display_config->multi_monitor_in_sync &&
+	     !hwmgr->display_config->nb_pstate_switch_disable)
 		vega12_notify_smc_display_change(hwmgr, false);
 	else
 		vega12_notify_smc_display_change(hwmgr, true);
-- 
cgit v1.2.3


From 456607d816d89a442a3d5ec98b02c8bc950b5228 Mon Sep 17 00:00:00 2001
From: Michel Dänzer <michel.daenzer@amd.com>
Date: Thu, 19 Jul 2018 17:38:18 +0200
Subject: drm/amdgpu: Don't warn on destroying a pinned BO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The warning turned out to be not so useful, as BO destruction tends to
be deferred to a workqueue.

Also, we should be preventing any damage from this now, so not really
important anymore to fix code doing this.

Acked-by: Alex Deucher <alexander.deucher@amd.com>
Tested-by: Mike Lothian <mike@fireburn.co.uk>
Signed-off-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index b12526ce1a9d..3010f0136de9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -89,7 +89,7 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
 	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
 
-	if (WARN_ON_ONCE(bo->pin_count > 0))
+	if (bo->pin_count > 0)
 		amdgpu_bo_subtract_pin_size(bo);
 
 	if (bo->kfd_bo)
-- 
cgit v1.2.3


From 5f8181733f6e5f8a4447f844efe4bdab5ed6a30e Mon Sep 17 00:00:00 2001
From: Shirish S <shirish.s@amd.com>
Date: Mon, 23 Jul 2018 15:11:51 +0530
Subject: drm/amdgpu: move the amdgpu_fbdev_set_suspend() further up
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch moves amdgpu_fbdev_set_suspend() to the beginning
of suspend sequence.

This is to ensure fbcon does not to write to the VRAM
after GPU is powerd down.

Signed-off-by: Shirish S <shirish.s@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 61981d0701b5..ec53d8f96d06 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -2702,6 +2702,9 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 
 	drm_kms_helper_poll_disable(dev);
 
+	if (fbcon)
+		amdgpu_fbdev_set_suspend(adev, 1);
+
 	if (!amdgpu_device_has_dc_support(adev)) {
 		/* turn off display hw */
 		drm_modeset_lock_all(dev);
@@ -2767,9 +2770,6 @@ int amdgpu_device_suspend(struct drm_device *dev, bool suspend, bool fbcon)
 			DRM_ERROR("amdgpu asic reset failed\n");
 	}
 
-	if (fbcon)
-		amdgpu_fbdev_set_suspend(adev, 1);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 85344e75d0d18094789ce84f88e1c5762c74115d Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Wed, 4 Jul 2018 11:19:53 -0400
Subject: drm/amd/display: Remove unnecessary warning

[why]
The warning message floods the dmesg log on Tonga even
though it is expected to have a pix_clk set to zero,
when the pipe is not active.
[how]
remove the assert

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
index ec3221333011..74c05e878807 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_hw_sequencer.c
@@ -149,10 +149,6 @@ static uint32_t get_max_pixel_clock_for_all_paths(
 			max_pix_clk =
 				pipe_ctx->stream_res.pix_clk_params.requested_pix_clk;
 	}
-
-	if (max_pix_clk == 0)
-		ASSERT(0);
-
 	return max_pix_clk;
 }
 
-- 
cgit v1.2.3


From aafded888514ba2c6b613548081dedf289a71287 Mon Sep 17 00:00:00 2001
From: Tony Cheng <tony.cheng@amd.com>
Date: Wed, 11 Jul 2018 15:31:24 -0400
Subject: drm/amd/display: allow diags to skip initial link training

[why]
diag specify what the full config and is only concerned about pass/fail at the end

having inter-op code like verifiying we can actually train at reported link rate
slows down diag test and add complexity we don't need

[how]
add dc_debug option to skip capability link trianing

also  remove hbr in function name as verify is not specific to hbr

Signed-off-by: Tony Cheng <tony.cheng@amd.com>
Reviewed-by: Ken Chalmers <ken.chalmers@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c    | 2 +-
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c | 7 ++++++-
 drivers/gpu/drm/amd/display/dc/dc.h              | 1 +
 drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h  | 2 +-
 4 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index a4429c90c60c..388a0635c38d 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -760,7 +760,7 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 				 */
 
 				/* deal with non-mst cases */
-				dp_hbr_verify_link_cap(link, &link->reported_link_cap);
+				dp_verify_link_cap(link, &link->reported_link_cap);
 			}
 
 			/* HDMI-DVI Dongle */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 474cd3e01752..b8e6db4382ec 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1086,7 +1086,7 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 	return max_link_cap;
 }
 
-bool dp_hbr_verify_link_cap(
+bool dp_verify_link_cap(
 	struct dc_link *link,
 	struct dc_link_settings *known_limit_link_setting)
 {
@@ -1101,6 +1101,11 @@ bool dp_hbr_verify_link_cap(
 	enum clock_source_id dp_cs_id = CLOCK_SOURCE_ID_EXTERNAL;
 	enum link_training_result status;
 
+	if (link->dc->debug.skip_detection_link_training) {
+		link->verified_link_cap = *known_limit_link_setting;
+		return true;
+	}
+
 	success = false;
 	skip_link_training = false;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index ceb4c3725893..5e2a2acb5ad6 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -258,6 +258,7 @@ struct dc_debug {
 	bool avoid_vbios_exec_table;
 	bool scl_reset_length10;
 	bool hdmi20_disable;
+	bool skip_detection_link_training;
 
 	struct {
 		uint32_t ltFailCount;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
index 2f783c650084..697b5ee73845 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -33,7 +33,7 @@ struct dc_link;
 struct dc_stream_state;
 struct dc_link_settings;
 
-bool dp_hbr_verify_link_cap(
+bool dp_verify_link_cap(
 	struct dc_link *link,
 	struct dc_link_settings *known_limit_link_setting);
 
-- 
cgit v1.2.3


From 278ca8d677cf7bcecd2b2f287838e5f344f5911e Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Wed, 11 Jul 2018 16:20:13 -0400
Subject: drm/amd/display: On dce100, set clocks to 0 on suspend

[Why]
When a dce100 asic was suspended, the clocks were not set to 0.
Upon resume, the new clock was compared to the existing clock,
they were found to be the same, and so the clock was not set.
This resulted in a pernicious blackscreen.

[How]
In atomic commit, check to see if there are any active pipes.
If no, set clocks to 0

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../gpu/drm/amd/display/dc/dce100/dce100_resource.c   | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index 8ed8eace42be..ad8ad4e1437c 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -678,9 +678,22 @@ bool dce100_validate_bandwidth(
 	struct dc  *dc,
 	struct dc_state *context)
 {
-	/* TODO implement when needed but for now hardcode max value*/
-	context->bw.dce.dispclk_khz = 681000;
-	context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+	int i;
+	bool at_least_one_pipe = false;
+
+	for (i = 0; i < dc->res_pool->pipe_count; i++) {
+		if (context->res_ctx.pipe_ctx[i].stream)
+			at_least_one_pipe = true;
+	}
+
+	if (at_least_one_pipe) {
+		/* TODO implement when needed but for now hardcode max value*/
+		context->bw.dce.dispclk_khz = 681000;
+		context->bw.dce.yclk_khz = 250000 * MEMORY_TYPE_MULTIPLIER;
+	} else {
+		context->bw.dce.dispclk_khz = 0;
+		context->bw.dce.yclk_khz = 0;
+	}
 
 	return true;
 }
-- 
cgit v1.2.3


From 3fc9fc4cf5a1a8219ab5d9ab10dac26db78c38f4 Mon Sep 17 00:00:00 2001
From: vikrant mhaske <vikrant.mhaske@amd.com>
Date: Thu, 12 Jul 2018 16:04:43 +0800
Subject: drm/amd/display: DPP CM ICSC AYCRCB8888 format support

[why]
Diags has POR to run the video workload using AYCRCB8888 through DCN;
capture it through DWB and send it to VCN hardware to encode

[how]
added the code to support this format so that DPP ICSC will be able to
convert it from YUV444 to internal RGB and DWB OCSC will be able to
convert from internal RGB to YUV420

Signed-off-by: vikrant mhaske <vikrant.mhaske@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h      | 2 +-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 9cfd7ea845e3..1d1f2d5ece51 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -192,7 +192,7 @@ enum surface_pixel_format {
 	/*swaped & float*/
 	SURFACE_PIXEL_FORMAT_GRPH_ABGR16161616F,
 	/*grow graphics here if necessary */
-
+	SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888,
 	SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
 	SURFACE_PIXEL_FORMAT_VIDEO_420_YCbCr =
 		SURFACE_PIXEL_FORMAT_VIDEO_BEGIN,
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
index 332354ca6529..2138cd3c5d1d 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hubp.c
@@ -294,6 +294,10 @@ void hubp1_program_pixel_format(
 		REG_UPDATE(DCSURF_SURFACE_CONFIG,
 				SURFACE_PIXEL_FORMAT, 66);
 		break;
+	case SURFACE_PIXEL_FORMAT_VIDEO_AYCrCb8888:
+		REG_UPDATE(DCSURF_SURFACE_CONFIG,
+				SURFACE_PIXEL_FORMAT, 12);
+		break;
 	default:
 		BREAK_TO_DEBUGGER();
 		break;
-- 
cgit v1.2.3


From 5c6ac7112fb2b73a5e4e7ac1648cdaceb558f268 Mon Sep 17 00:00:00 2001
From: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Date: Tue, 10 Jul 2018 17:20:17 -0400
Subject: drm/amd/display: Decouple aux from i2c

[Why]
Aux engine is created from i2caux layer. We want to remove this layer
and use the engine directly.

[How]
Decouple aux engine from i2caux. Move aux engine related code to dce folder and use
dc resource pool to manage the engine. And use the engine functions directly

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c  |  22 +-
 drivers/gpu/drm/amd/display/dc/dce/Makefile        |   2 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_aux.c       | 942 +++++++++++++++++++++
 drivers/gpu/drm/amd/display/dc/dce/dce_aux.h       | 111 +++
 .../drm/amd/display/dc/dce100/dce100_resource.c    |  42 +
 .../drm/amd/display/dc/dce110/dce110_resource.c    |  45 +
 .../drm/amd/display/dc/dce112/dce112_resource.c    |  47 +
 .../drm/amd/display/dc/dce120/dce120_resource.c    |  42 +
 .../gpu/drm/amd/display/dc/dce80/dce80_resource.c  |  44 +
 .../gpu/drm/amd/display/dc/dcn10/dcn10_resource.c  |  44 +
 drivers/gpu/drm/amd/display/dc/i2caux/engine.h     |   1 +
 drivers/gpu/drm/amd/display/dc/inc/core_types.h    |   2 +-
 drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h | 113 +++
 drivers/gpu/drm/amd/display/dc/inc/hw/engine.h     | 106 +++
 14 files changed, 1549 insertions(+), 14 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
 create mode 100644 drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
 create mode 100644 drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
 create mode 100644 drivers/gpu/drm/amd/display/dc/inc/hw/engine.h

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 08c9d73b9ab7..4019fe07d291 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -33,10 +33,8 @@
 #include "include/vector.h"
 #include "core_types.h"
 #include "dc_link_ddc.h"
-#include "i2caux/engine.h"
-#include "i2caux/i2c_engine.h"
-#include "i2caux/aux_engine.h"
-#include "i2caux/i2caux.h"
+#include "engine.h"
+#include "aux_engine.h"
 
 #define AUX_POWER_UP_WA_DELAY 500
 #define I2C_OVER_AUX_DEFER_WA_DELAY 70
@@ -641,9 +639,9 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 			     enum aux_transaction_type type,
 			     enum i2caux_transaction_action action)
 {
-	struct i2caux *i2caux = ddc->ctx->i2caux;
 	struct ddc *ddc_pin = ddc->ddc_pin;
-	struct aux_engine *engine;
+	struct engine *engine;
+	struct aux_engine *aux_engine;
 	enum aux_channel_operation_result operation_result;
 	struct aux_request_transaction_data aux_req;
 	struct aux_reply_transaction_data aux_rep;
@@ -654,7 +652,8 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 	memset(&aux_req, 0, sizeof(aux_req));
 	memset(&aux_rep, 0, sizeof(aux_rep));
 
-	engine = i2caux->funcs->acquire_aux_engine(i2caux, ddc_pin);
+	engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
+	aux_engine = engine->funcs->acquire(engine, ddc_pin);
 
 	aux_req.type = type;
 	aux_req.action = action;
@@ -664,15 +663,15 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 	aux_req.length = size;
 	aux_req.data = buffer;
 
-	engine->funcs->submit_channel_request(engine, &aux_req);
-	operation_result = engine->funcs->get_channel_status(engine, &returned_bytes);
+	aux_engine->funcs->submit_channel_request(aux_engine, &aux_req);
+	operation_result = aux_engine->funcs->get_channel_status(aux_engine, &returned_bytes);
 
 	switch (operation_result) {
 	case AUX_CHANNEL_OPERATION_SUCCEEDED:
 		res = returned_bytes;
 
 		if (res <= size && res >= 0)
-			res = engine->funcs->read_channel_reply(engine, size,
+			res = aux_engine->funcs->read_channel_reply(aux_engine, size,
 								buffer, reply,
 								&status);
 
@@ -686,8 +685,7 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 		res = -1;
 		break;
 	}
-
-	i2caux->funcs->release_engine(i2caux, &engine->base);
+	aux_engine->base.funcs->release_engine(&aux_engine->base);
 	return res;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/Makefile b/drivers/gpu/drm/amd/display/dc/dce/Makefile
index 11401fd8e535..825537bd4545 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/Makefile
+++ b/drivers/gpu/drm/amd/display/dc/dce/Makefile
@@ -28,7 +28,7 @@
 
 DCE = dce_audio.o dce_stream_encoder.o dce_link_encoder.o dce_hwseq.o \
 dce_mem_input.o dce_clock_source.o dce_scl_filters.o dce_transform.o \
-dce_clocks.o dce_opp.o dce_dmcu.o dce_abm.o dce_ipp.o
+dce_clocks.o dce_opp.o dce_dmcu.o dce_abm.o dce_ipp.o dce_aux.o
 
 
 AMD_DAL_DCE = $(addprefix $(AMDDALPATH)/dc/dce/,$(DCE))
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
new file mode 100644
index 000000000000..b28e2120767e
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -0,0 +1,942 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#include "dm_services.h"
+#include "dce_aux.h"
+#include "dce/dce_11_0_sh_mask.h"
+
+#define CTX \
+	aux110->base.base.ctx
+#define REG(reg_name)\
+	(aux110->regs->reg_name)
+
+#define DC_LOGGER \
+	engine->base.ctx->logger
+
+#include "reg_helper.h"
+
+#define FROM_AUX_ENGINE(ptr) \
+	container_of((ptr), struct aux_engine_dce110, base)
+
+#define FROM_ENGINE(ptr) \
+	FROM_AUX_ENGINE(container_of((ptr), struct aux_engine, base))
+
+#define FROM_AUX_ENGINE_ENGINE(ptr) \
+	container_of((ptr), struct aux_engine, base)
+enum {
+	AUX_INVALID_REPLY_RETRY_COUNTER = 1,
+	AUX_TIMED_OUT_RETRY_COUNTER = 2,
+	AUX_DEFER_RETRY_COUNTER = 6
+};
+static void release_engine(
+	struct engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_ENGINE(engine);
+
+	dal_ddc_close(engine->ddc);
+
+	engine->ddc = NULL;
+
+	REG_UPDATE(AUX_ARB_CONTROL, AUX_SW_DONE_USING_AUX_REG, 1);
+}
+
+#define SW_CAN_ACCESS_AUX 1
+#define DMCU_CAN_ACCESS_AUX 2
+
+static bool is_engine_available(
+	struct aux_engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value = REG_READ(AUX_ARB_CONTROL);
+	uint32_t field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+
+	return (field != DMCU_CAN_ACCESS_AUX);
+}
+static bool acquire_engine(
+	struct aux_engine *engine)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value = REG_READ(AUX_ARB_CONTROL);
+	uint32_t field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+	if (field == DMCU_CAN_ACCESS_AUX)
+		return false;
+	/* enable AUX before request SW to access AUX */
+	value = REG_READ(AUX_CONTROL);
+	field = get_reg_field_value(value,
+				AUX_CONTROL,
+				AUX_EN);
+
+	if (field == 0) {
+		set_reg_field_value(
+				value,
+				1,
+				AUX_CONTROL,
+				AUX_EN);
+
+		if (REG(AUX_RESET_MASK)) {
+			/*DP_AUX block as part of the enable sequence*/
+			set_reg_field_value(
+				value,
+				1,
+				AUX_CONTROL,
+				AUX_RESET);
+		}
+
+		REG_WRITE(AUX_CONTROL, value);
+
+		if (REG(AUX_RESET_MASK)) {
+			/*poll HW to make sure reset it done*/
+
+			REG_WAIT(AUX_CONTROL, AUX_RESET_DONE, 1,
+					1, 11);
+
+			set_reg_field_value(
+				value,
+				0,
+				AUX_CONTROL,
+				AUX_RESET);
+
+			REG_WRITE(AUX_CONTROL, value);
+
+			REG_WAIT(AUX_CONTROL, AUX_RESET_DONE, 0,
+					1, 11);
+		}
+	} /*if (field)*/
+
+	/* request SW to access AUX */
+	REG_UPDATE(AUX_ARB_CONTROL, AUX_SW_USE_AUX_REG_REQ, 1);
+
+	value = REG_READ(AUX_ARB_CONTROL);
+	field = get_reg_field_value(
+			value,
+			AUX_ARB_CONTROL,
+			AUX_REG_RW_CNTL_STATUS);
+
+	return (field == SW_CAN_ACCESS_AUX);
+}
+
+#define COMPOSE_AUX_SW_DATA_16_20(command, address) \
+	((command) | ((0xF0000 & (address)) >> 16))
+
+#define COMPOSE_AUX_SW_DATA_8_15(address) \
+	((0xFF00 & (address)) >> 8)
+
+#define COMPOSE_AUX_SW_DATA_0_7(address) \
+	(0xFF & (address))
+
+static void submit_channel_request(
+	struct aux_engine *engine,
+	struct aux_request_transaction_data *request)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t value;
+	uint32_t length;
+
+	bool is_write =
+		((request->type == AUX_TRANSACTION_TYPE_DP) &&
+		 (request->action == I2CAUX_TRANSACTION_ACTION_DP_WRITE)) ||
+		((request->type == AUX_TRANSACTION_TYPE_I2C) &&
+		((request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE) ||
+		 (request->action == I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT)));
+	if (REG(AUXN_IMPCAL)) {
+		/* clear_aux_error */
+		REG_UPDATE_SEQ(AUXN_IMPCAL, AUXN_CALOUT_ERROR_AK,
+				1,
+				0);
+
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_CALOUT_ERROR_AK,
+				1,
+				0);
+
+		/* force_default_calibrate */
+		REG_UPDATE_1BY1_2(AUXN_IMPCAL,
+				AUXN_IMPCAL_ENABLE, 1,
+				AUXN_IMPCAL_OVERRIDE_ENABLE, 0);
+
+		/* bug? why AUXN update EN and OVERRIDE_EN 1 by 1 while AUX P toggles OVERRIDE? */
+
+		REG_UPDATE_SEQ(AUXP_IMPCAL, AUXP_IMPCAL_OVERRIDE_ENABLE,
+				1,
+				0);
+	}
+	/* set the delay and the number of bytes to write */
+
+	/* The length include
+	 * the 4 bit header and the 20 bit address
+	 * (that is 3 byte).
+	 * If the requested length is non zero this means
+	 * an addition byte specifying the length is required.
+	 */
+
+	length = request->length ? 4 : 3;
+	if (is_write)
+		length += request->length;
+
+	REG_UPDATE_2(AUX_SW_CONTROL,
+			AUX_SW_START_DELAY, request->delay,
+			AUX_SW_WR_BYTES, length);
+
+	/* program action and address and payload data (if 'is_write') */
+	value = REG_UPDATE_4(AUX_SW_DATA,
+			AUX_SW_INDEX, 0,
+			AUX_SW_DATA_RW, 0,
+			AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_16_20(request->action, request->address));
+
+	value = REG_SET_2(AUX_SW_DATA, value,
+			AUX_SW_AUTOINCREMENT_DISABLE, 0,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_8_15(request->address));
+
+	value = REG_SET(AUX_SW_DATA, value,
+			AUX_SW_DATA, COMPOSE_AUX_SW_DATA_0_7(request->address));
+
+	if (request->length) {
+		value = REG_SET(AUX_SW_DATA, value,
+				AUX_SW_DATA, request->length - 1);
+	}
+
+	if (is_write) {
+		/* Load the HW buffer with the Data to be sent.
+		 * This is relevant for write operation.
+		 * For read, the data recived data will be
+		 * processed in process_channel_reply().
+		 */
+		uint32_t i = 0;
+
+		while (i < request->length) {
+			value = REG_SET(AUX_SW_DATA, value,
+					AUX_SW_DATA, request->data[i]);
+
+			++i;
+		}
+	}
+
+	REG_UPDATE(AUX_INTERRUPT_CONTROL, AUX_SW_DONE_ACK, 1);
+	REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 0,
+				10, aux110->timeout_period/10);
+	REG_UPDATE(AUX_SW_CONTROL, AUX_SW_GO, 1);
+}
+
+static int read_channel_reply(struct aux_engine *engine, uint32_t size,
+			      uint8_t *buffer, uint8_t *reply_result,
+			      uint32_t *sw_status)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+	uint32_t bytes_replied;
+	uint32_t reply_result_32;
+
+	*sw_status = REG_GET(AUX_SW_STATUS, AUX_SW_REPLY_BYTE_COUNT,
+			     &bytes_replied);
+
+	/* In case HPD is LOW, exit AUX transaction */
+	if ((*sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return -1;
+
+	/* Need at least the status byte */
+	if (!bytes_replied)
+		return -1;
+
+	REG_UPDATE_1BY1_3(AUX_SW_DATA,
+			  AUX_SW_INDEX, 0,
+			  AUX_SW_AUTOINCREMENT_DISABLE, 1,
+			  AUX_SW_DATA_RW, 1);
+
+	REG_GET(AUX_SW_DATA, AUX_SW_DATA, &reply_result_32);
+	reply_result_32 = reply_result_32 >> 4;
+	*reply_result = (uint8_t)reply_result_32;
+
+	if (reply_result_32 == 0) { /* ACK */
+		uint32_t i = 0;
+
+		/* First byte was already used to get the command status */
+		--bytes_replied;
+
+		/* Do not overflow buffer */
+		if (bytes_replied > size)
+			return -1;
+
+		while (i < bytes_replied) {
+			uint32_t aux_sw_data_val;
+
+			REG_GET(AUX_SW_DATA, AUX_SW_DATA, &aux_sw_data_val);
+			buffer[i] = aux_sw_data_val;
+			++i;
+		}
+
+		return i;
+	}
+
+	return 0;
+}
+
+static void process_channel_reply(
+	struct aux_engine *engine,
+	struct aux_reply_transaction_data *reply)
+{
+	int bytes_replied;
+	uint8_t reply_result;
+	uint32_t sw_status;
+
+	bytes_replied = read_channel_reply(engine, reply->length, reply->data,
+					   &reply_result, &sw_status);
+
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+		reply->status = AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+		return;
+	}
+
+	if (bytes_replied < 0) {
+		/* Need to handle an error case...
+		 * Hopefully, upper layer function won't call this function if
+		 * the number of bytes in the reply was 0, because there was
+		 * surely an error that was asserted that should have been
+		 * handled for hot plug case, this could happens
+		 */
+		if (!(sw_status & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK)) {
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+			ASSERT_CRITICAL(false);
+			return;
+		}
+	} else {
+
+		switch (reply_result) {
+		case 0: /* ACK */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_ACK;
+		break;
+		case 1: /* NACK */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_NACK;
+		break;
+		case 2: /* DEFER */
+			reply->status = AUX_TRANSACTION_REPLY_AUX_DEFER;
+		break;
+		case 4: /* AUX ACK / I2C NACK */
+			reply->status = AUX_TRANSACTION_REPLY_I2C_NACK;
+		break;
+		case 8: /* AUX ACK / I2C DEFER */
+			reply->status = AUX_TRANSACTION_REPLY_I2C_DEFER;
+		break;
+		default:
+			reply->status = AUX_TRANSACTION_REPLY_INVALID;
+		}
+	}
+}
+
+static enum aux_channel_operation_result get_channel_status(
+	struct aux_engine *engine,
+	uint8_t *returned_bytes)
+{
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
+
+	uint32_t value;
+
+	if (returned_bytes == NULL) {
+		/*caller pass NULL pointer*/
+		ASSERT_CRITICAL(false);
+		return AUX_CHANNEL_OPERATION_FAILED_REASON_UNKNOWN;
+	}
+	*returned_bytes = 0;
+
+	/* poll to make sure that SW_DONE is asserted */
+	value = REG_WAIT(AUX_SW_STATUS, AUX_SW_DONE, 1,
+				10, aux110->timeout_period/10);
+
+	/* in case HPD is LOW, exit AUX transaction */
+	if ((value & AUX_SW_STATUS__AUX_SW_HPD_DISCON_MASK))
+		return AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON;
+
+	/* Note that the following bits are set in 'status.bits'
+	 * during CTS 4.2.1.2 (FW 3.3.1):
+	 * AUX_SW_RX_MIN_COUNT_VIOL, AUX_SW_RX_INVALID_STOP,
+	 * AUX_SW_RX_RECV_NO_DET, AUX_SW_RX_RECV_INVALID_H.
+	 *
+	 * AUX_SW_RX_MIN_COUNT_VIOL is an internal,
+	 * HW debugging bit and should be ignored.
+	 */
+	if (value & AUX_SW_STATUS__AUX_SW_DONE_MASK) {
+		if ((value & AUX_SW_STATUS__AUX_SW_RX_TIMEOUT_STATE_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_TIMEOUT_MASK))
+			return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
+
+		else if ((value & AUX_SW_STATUS__AUX_SW_RX_INVALID_STOP_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_RECV_NO_DET_MASK) ||
+			(value &
+				AUX_SW_STATUS__AUX_SW_RX_RECV_INVALID_H_MASK) ||
+			(value & AUX_SW_STATUS__AUX_SW_RX_RECV_INVALID_L_MASK))
+			return AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY;
+
+		*returned_bytes = get_reg_field_value(value,
+				AUX_SW_STATUS,
+				AUX_SW_REPLY_BYTE_COUNT);
+
+		if (*returned_bytes == 0)
+			return
+			AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY;
+		else {
+			*returned_bytes -= 1;
+			return AUX_CHANNEL_OPERATION_SUCCEEDED;
+		}
+	} else {
+		/*time_elapsed >= aux_engine->timeout_period
+		 *  AUX_SW_STATUS__AUX_SW_HPD_DISCON = at this point
+		 */
+		ASSERT_CRITICAL(false);
+		return AUX_CHANNEL_OPERATION_FAILED_TIMEOUT;
+	}
+}
+static void process_read_reply(
+	struct aux_engine *engine,
+	struct read_command_context *ctx)
+{
+	engine->funcs->process_channel_reply(engine, &ctx->reply);
+
+	switch (ctx->reply.status) {
+	case AUX_TRANSACTION_REPLY_AUX_ACK:
+		ctx->defer_retry_aux = 0;
+		if (ctx->returned_byte > ctx->current_read_length) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else if (ctx->returned_byte < ctx->current_read_length) {
+			ctx->current_read_length -= ctx->returned_byte;
+
+			ctx->offset += ctx->returned_byte;
+
+			++ctx->invalid_reply_retry_aux_on_ack;
+
+			if (ctx->invalid_reply_retry_aux_on_ack >
+				AUX_INVALID_REPLY_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+				ctx->operation_succeeded = false;
+			}
+		} else {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
+			ctx->transaction_complete = true;
+			ctx->operation_succeeded = true;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_NACK:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_NACK;
+		ctx->operation_succeeded = false;
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_DEFER:
+		++ctx->defer_retry_aux;
+
+		if (ctx->defer_retry_aux > AUX_DEFER_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_I2C_DEFER:
+		ctx->defer_retry_aux = 0;
+
+		++ctx->defer_retry_i2c;
+
+		if (ctx->defer_retry_i2c > AUX_DEFER_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static void process_read_request(
+	struct aux_engine *engine,
+	struct read_command_context *ctx)
+{
+	enum aux_channel_operation_result operation_result;
+
+	engine->funcs->submit_channel_request(engine, &ctx->request);
+
+	operation_result = engine->funcs->get_channel_status(
+		engine, &ctx->returned_byte);
+
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		if (ctx->returned_byte > ctx->current_read_length) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else {
+			ctx->timed_out_retry_aux = 0;
+			ctx->invalid_reply_retry_aux = 0;
+
+			ctx->reply.length = ctx->returned_byte;
+			ctx->reply.data = ctx->buffer;
+
+			process_read_reply(engine, ctx);
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+		++ctx->invalid_reply_retry_aux;
+
+		if (ctx->invalid_reply_retry_aux >
+			AUX_INVALID_REPLY_RETRY_COUNTER) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else
+			udelay(400);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		++ctx->timed_out_retry_aux;
+
+		if (ctx->timed_out_retry_aux > AUX_TIMED_OUT_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		} else {
+			/* DP 1.2a, table 2-58:
+			 * "S3: AUX Request CMD PENDING:
+			 * retry 3 times, with 400usec wait on each"
+			 * The HW timeout is set to 550usec,
+			 * so we should not wait here
+			 */
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static bool read_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct read_command_context ctx;
+
+	ctx.buffer = request->payload.data;
+	ctx.current_read_length = request->payload.length;
+	ctx.offset = 0;
+	ctx.timed_out_retry_aux = 0;
+	ctx.invalid_reply_retry_aux = 0;
+	ctx.defer_retry_aux = 0;
+	ctx.defer_retry_i2c = 0;
+	ctx.invalid_reply_retry_aux_on_ack = 0;
+	ctx.transaction_complete = false;
+	ctx.operation_succeeded = true;
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_DP;
+		ctx.request.action = I2CAUX_TRANSACTION_ACTION_DP_READ;
+		ctx.request.address = request->payload.address;
+	} else if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_I2C;
+		ctx.request.action = middle_of_transaction ?
+			I2CAUX_TRANSACTION_ACTION_I2C_READ_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_READ;
+		ctx.request.address = request->payload.address >> 1;
+	} else {
+		/* in DAL2, there was no return in such case */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	ctx.request.delay = 0;
+
+	do {
+		memset(ctx.buffer + ctx.offset, 0, ctx.current_read_length);
+
+		ctx.request.data = ctx.buffer + ctx.offset;
+		ctx.request.length = ctx.current_read_length;
+
+		process_read_request(engine, &ctx);
+
+		request->status = ctx.status;
+
+		if (ctx.operation_succeeded && !ctx.transaction_complete)
+			if (ctx.request.type == AUX_TRANSACTION_TYPE_I2C)
+				msleep(engine->delay);
+	} while (ctx.operation_succeeded && !ctx.transaction_complete);
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		DC_LOG_I2C_AUX("READ: addr:0x%x  value:0x%x Result:%d",
+				request->payload.address,
+				request->payload.data[0],
+				ctx.operation_succeeded);
+	}
+
+	return ctx.operation_succeeded;
+}
+
+static void process_write_reply(
+	struct aux_engine *engine,
+	struct write_command_context *ctx)
+{
+	engine->funcs->process_channel_reply(engine, &ctx->reply);
+
+	switch (ctx->reply.status) {
+	case AUX_TRANSACTION_REPLY_AUX_ACK:
+		ctx->operation_succeeded = true;
+
+		if (ctx->returned_byte) {
+			ctx->request.action = ctx->mot ?
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST;
+
+			ctx->current_write_length = 0;
+
+			++ctx->ack_m_retry;
+
+			if (ctx->ack_m_retry > AUX_DEFER_RETRY_COUNTER) {
+				ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+				ctx->operation_succeeded = false;
+			} else
+				udelay(300);
+		} else {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_SUCCEEDED;
+			ctx->defer_retry_aux = 0;
+			ctx->ack_m_retry = 0;
+			ctx->transaction_complete = true;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_NACK:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_NACK;
+		ctx->operation_succeeded = false;
+	break;
+	case AUX_TRANSACTION_REPLY_AUX_DEFER:
+		++ctx->defer_retry_aux;
+
+		if (ctx->defer_retry_aux > ctx->max_defer_retry) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_I2C_DEFER:
+		ctx->defer_retry_aux = 0;
+		ctx->current_write_length = 0;
+
+		ctx->request.action = ctx->mot ?
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_STATUS_REQUEST;
+
+		++ctx->defer_retry_i2c;
+
+		if (ctx->defer_retry_i2c > ctx->max_defer_retry) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		}
+	break;
+	case AUX_TRANSACTION_REPLY_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static void process_write_request(
+	struct aux_engine *engine,
+	struct write_command_context *ctx)
+{
+	enum aux_channel_operation_result operation_result;
+
+	engine->funcs->submit_channel_request(engine, &ctx->request);
+
+	operation_result = engine->funcs->get_channel_status(
+		engine, &ctx->returned_byte);
+
+	switch (operation_result) {
+	case AUX_CHANNEL_OPERATION_SUCCEEDED:
+		ctx->timed_out_retry_aux = 0;
+		ctx->invalid_reply_retry_aux = 0;
+
+		ctx->reply.length = ctx->returned_byte;
+		ctx->reply.data = ctx->reply_data;
+
+		process_write_reply(engine, ctx);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_INVALID_REPLY:
+		++ctx->invalid_reply_retry_aux;
+
+		if (ctx->invalid_reply_retry_aux >
+			AUX_INVALID_REPLY_RETRY_COUNTER) {
+			ctx->status =
+				I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR;
+			ctx->operation_succeeded = false;
+		} else
+			udelay(400);
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_TIMEOUT:
+		++ctx->timed_out_retry_aux;
+
+		if (ctx->timed_out_retry_aux > AUX_TIMED_OUT_RETRY_COUNTER) {
+			ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT;
+			ctx->operation_succeeded = false;
+		} else {
+			/* DP 1.2a, table 2-58:
+			 * "S3: AUX Request CMD PENDING:
+			 * retry 3 times, with 400usec wait on each"
+			 * The HW timeout is set to 550usec,
+			 * so we should not wait here
+			 */
+		}
+	break;
+	case AUX_CHANNEL_OPERATION_FAILED_HPD_DISCON:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON;
+		ctx->operation_succeeded = false;
+	break;
+	default:
+		ctx->status = I2CAUX_TRANSACTION_STATUS_UNKNOWN;
+		ctx->operation_succeeded = false;
+	}
+}
+static bool write_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct write_command_context ctx;
+
+	ctx.mot = middle_of_transaction;
+	ctx.buffer = request->payload.data;
+	ctx.current_write_length = request->payload.length;
+	ctx.timed_out_retry_aux = 0;
+	ctx.invalid_reply_retry_aux = 0;
+	ctx.defer_retry_aux = 0;
+	ctx.defer_retry_i2c = 0;
+	ctx.ack_m_retry = 0;
+	ctx.transaction_complete = false;
+	ctx.operation_succeeded = true;
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_DP;
+		ctx.request.action = I2CAUX_TRANSACTION_ACTION_DP_WRITE;
+		ctx.request.address = request->payload.address;
+	} else if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C) {
+		ctx.request.type = AUX_TRANSACTION_TYPE_I2C;
+		ctx.request.action = middle_of_transaction ?
+			I2CAUX_TRANSACTION_ACTION_I2C_WRITE_MOT :
+			I2CAUX_TRANSACTION_ACTION_I2C_WRITE;
+		ctx.request.address = request->payload.address >> 1;
+	} else {
+		/* in DAL2, there was no return in such case */
+		BREAK_TO_DEBUGGER();
+		return false;
+	}
+
+	ctx.request.delay = 0;
+
+	ctx.max_defer_retry =
+		(engine->max_defer_write_retry > AUX_DEFER_RETRY_COUNTER) ?
+			engine->max_defer_write_retry : AUX_DEFER_RETRY_COUNTER;
+
+	do {
+		ctx.request.data = ctx.buffer;
+		ctx.request.length = ctx.current_write_length;
+
+		process_write_request(engine, &ctx);
+
+		request->status = ctx.status;
+
+		if (ctx.operation_succeeded && !ctx.transaction_complete)
+			if (ctx.request.type == AUX_TRANSACTION_TYPE_I2C)
+				msleep(engine->delay);
+	} while (ctx.operation_succeeded && !ctx.transaction_complete);
+
+	if (request->payload.address_space ==
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD) {
+		DC_LOG_I2C_AUX("WRITE: addr:0x%x  value:0x%x Result:%d",
+				request->payload.address,
+				request->payload.data[0],
+				ctx.operation_succeeded);
+	}
+
+	return ctx.operation_succeeded;
+}
+static bool end_of_transaction_command(
+	struct aux_engine *engine,
+	struct i2caux_transaction_request *request)
+{
+	struct i2caux_transaction_request dummy_request;
+	uint8_t dummy_data;
+
+	/* [tcheng] We only need to send the stop (read with MOT = 0)
+	 * for I2C-over-Aux, not native AUX
+	 */
+
+	if (request->payload.address_space !=
+		I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C)
+		return false;
+
+	dummy_request.operation = request->operation;
+	dummy_request.payload.address_space = request->payload.address_space;
+	dummy_request.payload.address = request->payload.address;
+
+	/*
+	 * Add a dummy byte due to some receiver quirk
+	 * where one byte is sent along with MOT = 0.
+	 * Ideally this should be 0.
+	 */
+
+	dummy_request.payload.length = 0;
+	dummy_request.payload.data = &dummy_data;
+
+	if (request->operation == I2CAUX_TRANSACTION_READ)
+		return read_command(engine, &dummy_request, false);
+	else
+		return write_command(engine, &dummy_request, false);
+
+	/* according Syed, it does not need now DoDummyMOT */
+}
+bool submit_request(
+	struct engine *engine,
+	struct i2caux_transaction_request *request,
+	bool middle_of_transaction)
+{
+	struct aux_engine *aux_engine = FROM_AUX_ENGINE_ENGINE(engine);
+
+	bool result;
+	bool mot_used = true;
+
+	switch (request->operation) {
+	case I2CAUX_TRANSACTION_READ:
+		result = read_command(aux_engine, request, mot_used);
+	break;
+	case I2CAUX_TRANSACTION_WRITE:
+		result = write_command(aux_engine, request, mot_used);
+	break;
+	default:
+		result = false;
+	}
+
+	/* [tcheng]
+	 * need to send stop for the last transaction to free up the AUX
+	 * if the above command fails, this would be the last transaction
+	 */
+
+	if (!middle_of_transaction || !result)
+		end_of_transaction_command(aux_engine, request);
+
+	/* mask AUX interrupt */
+
+	return result;
+}
+enum i2caux_engine_type get_engine_type(
+		const struct engine *engine)
+{
+	return I2CAUX_ENGINE_TYPE_AUX;
+}
+
+static struct aux_engine *acquire(
+	struct engine *engine,
+	struct ddc *ddc)
+{
+	struct aux_engine *aux_engine = FROM_AUX_ENGINE_ENGINE(engine);
+	enum gpio_result result;
+
+	if (aux_engine->funcs->is_engine_available) {
+		/*check whether SW could use the engine*/
+		if (!aux_engine->funcs->is_engine_available(aux_engine))
+			return NULL;
+	}
+
+	result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE,
+		GPIO_DDC_CONFIG_TYPE_MODE_AUX);
+
+	if (result != GPIO_RESULT_OK)
+		return NULL;
+
+	if (!aux_engine->funcs->acquire_engine(aux_engine)) {
+		dal_ddc_close(ddc);
+		return NULL;
+	}
+
+	engine->ddc = ddc;
+
+	return aux_engine;
+}
+
+static const struct aux_engine_funcs aux_engine_funcs = {
+	.acquire_engine = acquire_engine,
+	.submit_channel_request = submit_channel_request,
+	.process_channel_reply = process_channel_reply,
+	.read_channel_reply = read_channel_reply,
+	.get_channel_status = get_channel_status,
+	.is_engine_available = is_engine_available,
+};
+
+static const struct engine_funcs engine_funcs = {
+	.release_engine = release_engine,
+	.destroy_engine = dce110_engine_destroy,
+	.submit_request = submit_request,
+	.get_engine_type = get_engine_type,
+	.acquire = acquire,
+};
+
+void dce110_engine_destroy(struct engine **engine)
+{
+
+	struct aux_engine_dce110 *engine110 = FROM_ENGINE(*engine);
+
+	kfree(engine110);
+	*engine = NULL;
+
+}
+struct aux_engine *dce110_aux_engine_construct(struct aux_engine_dce110 *aux_engine110,
+		struct dc_context *ctx,
+		uint32_t inst,
+		uint32_t timeout_period,
+		const struct dce110_aux_registers *regs)
+{
+	aux_engine110->base.base.ddc = NULL;
+	aux_engine110->base.base.ctx = ctx;
+	aux_engine110->base.delay = 0;
+	aux_engine110->base.max_defer_write_retry = 0;
+	aux_engine110->base.base.funcs = &engine_funcs;
+	aux_engine110->base.funcs = &aux_engine_funcs;
+	aux_engine110->base.base.inst = inst;
+	aux_engine110->timeout_period = timeout_period;
+	aux_engine110->regs = regs;
+
+	return &aux_engine110->base;
+}
+
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
new file mode 100644
index 000000000000..c6b2aec2e367
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -0,0 +1,111 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_AUX_ENGINE_DCE110_H__
+#define __DAL_AUX_ENGINE_DCE110_H__
+#include "aux_engine.h"
+
+#define AUX_COMMON_REG_LIST(id)\
+	SRI(AUX_CONTROL, DP_AUX, id), \
+	SRI(AUX_ARB_CONTROL, DP_AUX, id), \
+	SRI(AUX_SW_DATA, DP_AUX, id), \
+	SRI(AUX_SW_CONTROL, DP_AUX, id), \
+	SRI(AUX_INTERRUPT_CONTROL, DP_AUX, id), \
+	SRI(AUX_SW_STATUS, DP_AUX, id), \
+	SR(AUXN_IMPCAL), \
+	SR(AUXP_IMPCAL)
+
+struct dce110_aux_registers {
+	uint32_t AUX_CONTROL;
+	uint32_t AUX_ARB_CONTROL;
+	uint32_t AUX_SW_DATA;
+	uint32_t AUX_SW_CONTROL;
+	uint32_t AUX_INTERRUPT_CONTROL;
+	uint32_t AUX_SW_STATUS;
+	uint32_t AUXN_IMPCAL;
+	uint32_t AUXP_IMPCAL;
+
+	uint32_t AUX_RESET_MASK;
+};
+
+enum {	/* This is the timeout as defined in DP 1.2a,
+	 * 2.3.4 "Detailed uPacket TX AUX CH State Description".
+	 */
+	AUX_TIMEOUT_PERIOD = 400,
+
+	/* Ideally, the SW timeout should be just above 550usec
+	 * which is programmed in HW.
+	 * But the SW timeout of 600usec is not reliable,
+	 * because on some systems, delay_in_microseconds()
+	 * returns faster than it should.
+	 * EPR #379763: by trial-and-error on different systems,
+	 * 700usec is the minimum reliable SW timeout for polling
+	 * the AUX_SW_STATUS.AUX_SW_DONE bit.
+	 * This timeout expires *only* when there is
+	 * AUX Error or AUX Timeout conditions - not during normal operation.
+	 * During normal operation, AUX_SW_STATUS.AUX_SW_DONE bit is set
+	 * at most within ~240usec. That means,
+	 * increasing this timeout will not affect normal operation,
+	 * and we'll timeout after
+	 * SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD = 1600usec.
+	 * This timeout is especially important for
+	 * resume from S3 and CTS.
+	 */
+	SW_AUX_TIMEOUT_PERIOD_MULTIPLIER = 4
+};
+struct aux_engine_dce110 {
+	struct aux_engine base;
+	const struct dce110_aux_registers *regs;
+	struct {
+		uint32_t aux_control;
+		uint32_t aux_arb_control;
+		uint32_t aux_sw_data;
+		uint32_t aux_sw_control;
+		uint32_t aux_interrupt_control;
+		uint32_t aux_sw_status;
+	} addr;
+	uint32_t timeout_period;
+};
+
+struct aux_engine_dce110_init_data {
+	uint32_t engine_id;
+	uint32_t timeout_period;
+	struct dc_context *ctx;
+	const struct dce110_aux_registers *regs;
+};
+
+struct aux_engine *dce110_aux_engine_construct(
+		struct aux_engine_dce110 *aux_engine110,
+		struct dc_context *ctx,
+		uint32_t inst,
+		uint32_t timeout_period,
+		const struct dce110_aux_registers *regs);
+
+void dce110_engine_destroy(struct engine **engine);
+
+bool dce110_aux_engine_acquire(
+	struct engine *aux_engine,
+	struct ddc *ddc);
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index ad8ad4e1437c..c34c9531915e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -52,6 +52,7 @@
 #include "dce/dce_10_0_sh_mask.h"
 
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 
 #ifndef mmMC_HUB_RDREQ_DMIF_LIMIT
@@ -279,7 +280,20 @@ static const struct dce_opp_shift opp_shift = {
 static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_100(_MASK)
 };
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
 
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
 
 #define audio_regs(id)\
 [id] = {\
@@ -572,6 +586,23 @@ struct output_pixel_processor *dce100_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce100_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 struct clock_source *dce100_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -624,6 +655,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -928,6 +963,13 @@ static bool construct(
 				"DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+		pool->base.engines[i] = dce100_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 1c902e49a712..4a665a29191b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -49,6 +49,7 @@
 #include "dce/dce_clock_source.h"
 #include "dce/dce_hwseq.h"
 #include "dce110/dce110_hw_sequencer.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
 
@@ -306,6 +307,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_110(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -588,6 +604,23 @@ static struct output_pixel_processor *dce110_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce110_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 struct clock_source *dce110_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -651,6 +684,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -1258,6 +1295,14 @@ static bool construct(
 				"DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+
+		pool->base.engines[i] = dce110_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->fbc_compressor = dce110_compressor_create(ctx);
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 30d5b32892d6..caf90ae2cbb0 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -49,6 +49,7 @@
 #include "dce112/dce112_hw_sequencer.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 
 #include "reg_helper.h"
 
@@ -314,6 +315,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_112(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -588,6 +604,23 @@ struct output_pixel_processor *dce112_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce112_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 struct clock_source *dce112_clock_source_create(
 	struct dc_context *ctx,
 	struct dc_bios *bios,
@@ -625,6 +658,9 @@ static void destruct(struct dce110_resource_pool *pool)
 		if (pool->base.opps[i] != NULL)
 			dce110_opp_destroy(&pool->base.opps[i]);
 
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 		if (pool->base.transforms[i] != NULL)
 			dce112_transform_destroy(&pool->base.transforms[i]);
 
@@ -640,6 +676,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -1208,6 +1248,13 @@ static bool construct(
 				"DC:failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+		pool->base.engines[i] = dce112_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 8381f27a2361..e389832c96cc 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -53,6 +53,7 @@
 #include "dce/dce_hwseq.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 
 #include "dce/dce_12_0_offset.h"
 #include "dce/dce_12_0_sh_mask.h"
@@ -297,6 +298,20 @@ static const struct dce_opp_shift opp_shift = {
 static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_120(_MASK)
 };
+ #define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
 
 #define audio_regs(id)\
 [id] = {\
@@ -361,6 +376,22 @@ struct output_pixel_processor *dce120_opp_create(
 			     ctx, inst, &opp_regs[inst], &opp_shift, &opp_mask);
 	return &opp->base;
 }
+struct engine *dce120_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
 
 static const struct bios_registers bios_regs = {
 	.BIOS_SCRATCH_6 = mmBIOS_SCRATCH_6 + NBIO_BASE(mmBIOS_SCRATCH_6_BASE_IDX)
@@ -467,6 +498,10 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
+
 	}
 
 	for (i = 0; i < pool->base.audio_count; i++) {
@@ -984,6 +1019,13 @@ static bool construct(
 			dm_error(
 				"DC: failed to create output pixel processor!\n");
 		}
+		pool->base.engines[i] = dce120_aux_engine_create(ctx, i);
+				if (pool->base.engines[i] == NULL) {
+					BREAK_TO_DEBUGGER();
+					dm_error(
+						"DC:failed to create aux engine!!\n");
+					goto res_create_fail;
+				}
 
 		/* check next valid pipe */
 		j++;
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 2ac95ec2bf96..6fb33ad2d3c8 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -54,6 +54,7 @@
 #include "reg_helper.h"
 
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 #include "dce/dce_abm.h"
 /* TODO remove this include */
 
@@ -298,6 +299,21 @@ static const struct dce_opp_mask opp_mask = {
 	OPP_COMMON_MASK_SH_LIST_DCE_80(_MASK)
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define audio_regs(id)\
 [id] = {\
 	AUD_COMMON_REG_LIST(id)\
@@ -448,6 +464,23 @@ static struct output_pixel_processor *dce80_opp_create(
 	return &opp->base;
 }
 
+struct engine *dce80_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 static struct stream_encoder *dce80_stream_encoder_create(
 	enum engine_id eng_id,
 	struct dc_context *ctx)
@@ -655,6 +688,9 @@ static void destruct(struct dce110_resource_pool *pool)
 			kfree(DCE110TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			dce110_engine_destroy(&pool->base.engines[i]);
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
@@ -899,6 +935,14 @@ static bool dce80_construct(
 			dm_error("DC: failed to create output pixel processor!\n");
 			goto res_create_fail;
 		}
+
+		pool->base.engines[i] = dce80_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto res_create_fail;
+		}
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 84581b3c392b..ef8bb2735620 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -64,6 +64,7 @@
 #include "reg_helper.h"
 #include "dce/dce_abm.h"
 #include "dce/dce_dmcu.h"
+#include "dce/dce_aux.h"
 
 const struct _vcs_dpi_ip_params_st dcn1_0_ip = {
 	.rob_buffer_size_kbytes = 64,
@@ -356,6 +357,21 @@ static const struct dcn10_opp_mask opp_mask = {
 		OPP_MASK_SH_LIST_DCN10(_MASK),
 };
 
+#define aux_engine_regs(id)\
+[id] = {\
+	AUX_COMMON_REG_LIST(id), \
+	.AUX_RESET_MASK = 0 \
+}
+
+static const struct dce110_aux_registers aux_engine_regs[] = {
+		aux_engine_regs(0),
+		aux_engine_regs(1),
+		aux_engine_regs(2),
+		aux_engine_regs(3),
+		aux_engine_regs(4),
+		aux_engine_regs(5)
+};
+
 #define tf_regs(id)\
 [id] = {\
 	TF_REG_LIST_DCN10(id),\
@@ -578,6 +594,23 @@ static struct output_pixel_processor *dcn10_opp_create(
 	return &opp->base;
 }
 
+struct engine *dcn10_aux_engine_create(
+	struct dc_context *ctx,
+	uint32_t inst)
+{
+	struct aux_engine_dce110 *aux_engine =
+		kzalloc(sizeof(struct aux_engine_dce110), GFP_KERNEL);
+
+	if (!aux_engine)
+		return NULL;
+
+	dce110_aux_engine_construct(aux_engine, ctx, inst,
+				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
+				    &aux_engine_regs[inst]);
+
+	return &aux_engine->base.base;
+}
+
 static struct mpc *dcn10_mpc_create(struct dc_context *ctx)
 {
 	struct dcn10_mpc *mpc10 = kzalloc(sizeof(struct dcn10_mpc),
@@ -826,6 +859,9 @@ static void destruct(struct dcn10_resource_pool *pool)
 			kfree(DCN10TG_FROM_TG(pool->base.timing_generators[i]));
 			pool->base.timing_generators[i] = NULL;
 		}
+
+		if (pool->base.engines[i] != NULL)
+			pool->base.engines[i]->funcs->destroy_engine(&pool->base.engines[i]);
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++)
@@ -1255,6 +1291,14 @@ static bool construct(
 			goto fail;
 		}
 
+		pool->base.engines[i] = dcn10_aux_engine_create(ctx, i);
+		if (pool->base.engines[i] == NULL) {
+			BREAK_TO_DEBUGGER();
+			dm_error(
+				"DC:failed to create aux engine!!\n");
+			goto fail;
+		}
+
 		/* check next valid pipe */
 		j++;
 	}
diff --git a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
index 1e8a1585e401..b16fb1ff687d 100644
--- a/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
+++ b/drivers/gpu/drm/amd/display/dc/i2caux/engine.h
@@ -96,6 +96,7 @@ struct engine_funcs {
 
 struct engine {
 	const struct engine_funcs *funcs;
+	uint32_t inst;
 	struct ddc *ddc;
 	struct dc_context *ctx;
 };
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 4446652a9a9e..0fa385872ed3 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -138,7 +138,7 @@ struct resource_pool {
 	struct output_pixel_processor *opps[MAX_PIPES];
 	struct timing_generator *timing_generators[MAX_PIPES];
 	struct stream_encoder *stream_enc[MAX_PIPES * 2];
-
+	struct engine *engines[MAX_PIPES];
 	struct hubbub *hubbub;
 	struct mpc *mpc;
 	struct pp_smu_funcs_rv *pp_smu;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
new file mode 100644
index 000000000000..06d7e5d4cf21
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
@@ -0,0 +1,113 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_AUX_ENGINE_H__
+#define __DAL_AUX_ENGINE_H__
+
+#include "engine.h"
+#include "include/i2caux_interface.h"
+
+struct aux_engine;
+union aux_config;
+struct aux_engine_funcs {
+	void (*destroy)(
+		struct aux_engine **ptr);
+	bool (*acquire_engine)(
+		struct aux_engine *engine);
+	void (*configure)(
+		struct aux_engine *engine,
+		union aux_config cfg);
+	void (*submit_channel_request)(
+		struct aux_engine *engine,
+		struct aux_request_transaction_data *request);
+	void (*process_channel_reply)(
+		struct aux_engine *engine,
+		struct aux_reply_transaction_data *reply);
+	int (*read_channel_reply)(
+		struct aux_engine *engine,
+		uint32_t size,
+		uint8_t *buffer,
+		uint8_t *reply_result,
+		uint32_t *sw_status);
+	enum aux_channel_operation_result (*get_channel_status)(
+		struct aux_engine *engine,
+		uint8_t *returned_bytes);
+	bool (*is_engine_available)(struct aux_engine *engine);
+};
+struct engine;
+struct aux_engine {
+	struct engine base;
+	const struct aux_engine_funcs *funcs;
+	/* following values are expressed in milliseconds */
+	uint32_t delay;
+	uint32_t max_defer_write_retry;
+
+	bool acquire_reset;
+};
+struct read_command_context {
+	uint8_t *buffer;
+	uint32_t current_read_length;
+	uint32_t offset;
+	enum i2caux_transaction_status status;
+
+	struct aux_request_transaction_data request;
+	struct aux_reply_transaction_data reply;
+
+	uint8_t returned_byte;
+
+	uint32_t timed_out_retry_aux;
+	uint32_t invalid_reply_retry_aux;
+	uint32_t defer_retry_aux;
+	uint32_t defer_retry_i2c;
+	uint32_t invalid_reply_retry_aux_on_ack;
+
+	bool transaction_complete;
+	bool operation_succeeded;
+};
+struct write_command_context {
+	bool mot;
+
+	uint8_t *buffer;
+	uint32_t current_write_length;
+	enum i2caux_transaction_status status;
+
+	struct aux_request_transaction_data request;
+	struct aux_reply_transaction_data reply;
+
+	uint8_t returned_byte;
+
+	uint32_t timed_out_retry_aux;
+	uint32_t invalid_reply_retry_aux;
+	uint32_t defer_retry_aux;
+	uint32_t defer_retry_i2c;
+	uint32_t max_defer_retry;
+	uint32_t ack_m_retry;
+
+	uint8_t reply_data[DEFAULT_AUX_MAX_DATA_SIZE];
+
+	bool transaction_complete;
+	bool operation_succeeded;
+};
+#endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h b/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h
new file mode 100644
index 000000000000..1f5476f41236
--- /dev/null
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h
@@ -0,0 +1,106 @@
+/*
+ * Copyright 2012-15 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ * Authors: AMD
+ *
+ */
+
+#ifndef __DAL_ENGINE_H__
+#define __DAL_ENGINE_H__
+
+#include "dc_ddc_types.h"
+
+enum i2caux_transaction_operation {
+	I2CAUX_TRANSACTION_READ,
+	I2CAUX_TRANSACTION_WRITE
+};
+
+enum i2caux_transaction_address_space {
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C = 1,
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD
+};
+
+struct i2caux_transaction_payload {
+	enum i2caux_transaction_address_space address_space;
+	uint32_t address;
+	uint32_t length;
+	uint8_t *data;
+};
+
+enum i2caux_transaction_status {
+	I2CAUX_TRANSACTION_STATUS_UNKNOWN = (-1L),
+	I2CAUX_TRANSACTION_STATUS_SUCCEEDED,
+	I2CAUX_TRANSACTION_STATUS_FAILED_CHANNEL_BUSY,
+	I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT,
+	I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR,
+	I2CAUX_TRANSACTION_STATUS_FAILED_NACK,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INCOMPLETE,
+	I2CAUX_TRANSACTION_STATUS_FAILED_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INVALID_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW,
+	I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON
+};
+
+struct i2caux_transaction_request {
+	enum i2caux_transaction_operation operation;
+	struct i2caux_transaction_payload payload;
+	enum i2caux_transaction_status status;
+};
+
+enum i2caux_engine_type {
+	I2CAUX_ENGINE_TYPE_UNKNOWN = (-1L),
+	I2CAUX_ENGINE_TYPE_AUX,
+	I2CAUX_ENGINE_TYPE_I2C_DDC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_GENERIC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_SW
+};
+
+enum i2c_default_speed {
+	I2CAUX_DEFAULT_I2C_HW_SPEED = 50,
+	I2CAUX_DEFAULT_I2C_SW_SPEED = 50
+};
+
+struct engine;
+
+struct engine_funcs {
+	enum i2caux_engine_type (*get_engine_type)(
+		const struct engine *engine);
+	struct aux_engine* (*acquire)(
+		struct engine *engine,
+		struct ddc *ddc);
+	bool (*submit_request)(
+		struct engine *engine,
+		struct i2caux_transaction_request *request,
+		bool middle_of_transaction);
+	void (*release_engine)(
+		struct engine *engine);
+	void (*destroy_engine)(
+		struct engine **engine);
+};
+
+struct engine {
+	const struct engine_funcs *funcs;
+	uint32_t inst;
+	struct ddc *ddc;
+	struct dc_context *ctx;
+};
+
+#endif
-- 
cgit v1.2.3


From cfd84fd36531b2f1de01b3530b6953ed34ed2c95 Mon Sep 17 00:00:00 2001
From: Jun Lei <Jun.Lei@amd.com>
Date: Thu, 12 Jul 2018 10:35:01 -0400
Subject: drm/amd/display: separate dc_debug into dc_debug_options and dc_debug
 data

[why]
confusing as to which part of debug is informational, and which part causes behavioral change

Signed-off-by: Jun Lei <Jun.Lei@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c      |  2 +-
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c      |  2 +-
 drivers/gpu/drm/amd/display/dc/dc.h                   | 19 +++++++++++--------
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c       |  4 ++--
 .../gpu/drm/amd/display/dc/dce120/dce120_resource.c   |  2 +-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c |  4 ++--
 6 files changed, 18 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
index 080f777d705e..bd039322f697 100644
--- a/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
+++ b/drivers/gpu/drm/amd/display/dc/calcs/dcn_calcs.c
@@ -676,7 +676,7 @@ static void hack_force_pipe_split(struct dcn_bw_internal_vars *v,
 }
 
 static void hack_bounding_box(struct dcn_bw_internal_vars *v,
-		struct dc_debug *dbg,
+		struct dc_debug_options *dbg,
 		struct dc_state *context)
 {
 	if (dbg->pipe_split_policy == MPC_SPLIT_AVOID)
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index b8e6db4382ec..9d901ca70588 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1029,7 +1029,7 @@ enum link_training_result dc_link_dp_perform_link_training(
 			lt_settings.lane_settings[0].PRE_EMPHASIS);
 
 	if (status != LINK_TRAINING_SUCCESS)
-		link->ctx->dc->debug.debug_data.ltFailCount++;
+		link->ctx->dc->debug_data.ltFailCount++;
 
 	return status;
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 5e2a2acb5ad6..93b8bf030ba7 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -207,7 +207,7 @@ struct dc_clocks {
 	int phyclk_khz;
 };
 
-struct dc_debug {
+struct dc_debug_options {
 	enum visual_confirm visual_confirm;
 	bool sanity_checks;
 	bool max_disp_clk;
@@ -259,13 +259,15 @@ struct dc_debug {
 	bool scl_reset_length10;
 	bool hdmi20_disable;
 	bool skip_detection_link_training;
+};
 
-	struct {
-		uint32_t ltFailCount;
-		uint32_t i2cErrorCount;
-		uint32_t auxErrorCount;
-	} debug_data;
+struct dc_debug_data {
+	uint32_t ltFailCount;
+	uint32_t i2cErrorCount;
+	uint32_t auxErrorCount;
 };
+
+
 struct dc_state;
 struct resource_pool;
 struct dce_hwseq;
@@ -274,8 +276,7 @@ struct dc {
 	struct dc_caps caps;
 	struct dc_cap_funcs cap_funcs;
 	struct dc_config config;
-	struct dc_debug debug;
-
+	struct dc_debug_options debug;
 	struct dc_context *ctx;
 
 	uint8_t link_count;
@@ -311,6 +312,8 @@ struct dc {
 
 	/* FBC compressor */
 	struct compressor *fbc_compressor;
+
+	struct dc_debug_data debug_data;
 };
 
 enum frame_buffer_mode {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 8f8a2abac3f3..0db8d1da3d0e 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -337,7 +337,7 @@ static int dce112_set_clock(
 
 static void dce_clock_read_integrated_info(struct dce_dccg *clk_dce)
 {
-	struct dc_debug *debug = &clk_dce->base.ctx->dc->debug;
+	struct dc_debug_options *debug = &clk_dce->base.ctx->dc->debug;
 	struct dc_bios *bp = clk_dce->base.ctx->dc_bios;
 	struct integrated_info info = { { { 0 } } };
 	struct dc_firmware_info fw_info = { { 0 } };
@@ -824,7 +824,7 @@ struct dccg *dce120_dccg_create(struct dc_context *ctx)
 #ifdef CONFIG_X86
 struct dccg *dcn1_dccg_create(struct dc_context *ctx)
 {
-	struct dc_debug *debug = &ctx->dc->debug;
+	struct dc_debug_options *debug = &ctx->dc->debug;
 	struct dc_bios *bp = ctx->dc_bios;
 	struct dc_firmware_info fw_info = { { 0 } };
 	struct dce_dccg *clk_dce = kzalloc(sizeof(*clk_dce), GFP_KERNEL);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index e389832c96cc..f7d02f2190d3 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -404,7 +404,7 @@ static const struct resource_caps res_cap = {
 		.num_pll = 6,
 };
 
-static const struct dc_debug debug_defaults = {
+static const struct dc_debug_options debug_defaults = {
 		.disable_clock_gate = true,
 };
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index ef8bb2735620..cd8c22839227 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -502,7 +502,7 @@ static const struct resource_caps res_cap = {
 		.num_pll = 4,
 };
 
-static const struct dc_debug debug_defaults_drv = {
+static const struct dc_debug_options debug_defaults_drv = {
 		.sanity_checks = true,
 		.disable_dmcu = true,
 		.force_abm_enable = false,
@@ -530,7 +530,7 @@ static const struct dc_debug debug_defaults_drv = {
 		.max_downscale_src_width = 3840,
 };
 
-static const struct dc_debug debug_defaults_diags = {
+static const struct dc_debug_options debug_defaults_diags = {
 		.disable_dmcu = true,
 		.force_abm_enable = false,
 		.timing_trace = true,
-- 
cgit v1.2.3


From bb805f2b20e2200753bf0a69b3ef5332b37eb781 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Mon, 9 Jul 2018 17:25:42 -0400
Subject: drm/amd/display: DC 3.1.58

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 93b8bf030ba7..7515c0dcbdd2 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.56"
+#define DC_VER "3.1.58"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From 24d5493f207ce0ce38df80ce86c907417e04594a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 14:04:12 +0200
Subject: block: simplify bio_check_pages_dirty

bio_check_pages_dirty currently inviolates the invariant that bv_page of
a bio_vec inside bi_vcnt shouldn't be zero, and that is going to become
really annoying with multpath biovecs.  Fortunately there isn't any
all that good reason for it - once we decide to defer freeing the bio
to a workqueue holding onto a few additional pages isn't really an
issue anymore.  So just check if there is a clean page that needs
dirtying in the first path, and do a second pass to free them if there
was none, while the cache is still hot.

Also use the chance to micro-optimize bio_dirty_fn a bit by not saving
irq state - we know we are called from a workqueue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c | 56 +++++++++++++++++++++-----------------------------------
 1 file changed, 21 insertions(+), 35 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 8ecc95615941..504b42278099 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1649,19 +1649,15 @@ static void bio_release_pages(struct bio *bio)
 	struct bio_vec *bvec;
 	int i;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page)
-			put_page(page);
-	}
+	bio_for_each_segment_all(bvec, bio, i)
+		put_page(bvec->bv_page);
 }
 
 /*
  * bio_check_pages_dirty() will check that all the BIO's pages are still dirty.
  * If they are, then fine.  If, however, some pages are clean then they must
  * have been written out during the direct-IO read.  So we take another ref on
- * the BIO and the offending pages and re-dirty the pages in process context.
+ * the BIO and re-dirty the pages in process context.
  *
  * It is expected that bio_check_pages_dirty() will wholly own the BIO from
  * here on.  It will run one put_page() against each page and will run one
@@ -1679,52 +1675,42 @@ static struct bio *bio_dirty_list;
  */
 static void bio_dirty_fn(struct work_struct *work)
 {
-	unsigned long flags;
-	struct bio *bio;
+	struct bio *bio, *next;
 
-	spin_lock_irqsave(&bio_dirty_lock, flags);
-	bio = bio_dirty_list;
+	spin_lock_irq(&bio_dirty_lock);
+	next = bio_dirty_list;
 	bio_dirty_list = NULL;
-	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	spin_unlock_irq(&bio_dirty_lock);
 
-	while (bio) {
-		struct bio *next = bio->bi_private;
+	while ((bio = next) != NULL) {
+		next = bio->bi_private;
 
 		bio_set_pages_dirty(bio);
 		bio_release_pages(bio);
 		bio_put(bio);
-		bio = next;
 	}
 }
 
 void bio_check_pages_dirty(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int nr_clean_pages = 0;
+	unsigned long flags;
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (PageDirty(page) || PageCompound(page)) {
-			put_page(page);
-			bvec->bv_page = NULL;
-		} else {
-			nr_clean_pages++;
-		}
+		if (!PageDirty(bvec->bv_page) && !PageCompound(bvec->bv_page))
+			goto defer;
 	}
 
-	if (nr_clean_pages) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&bio_dirty_lock, flags);
-		bio->bi_private = bio_dirty_list;
-		bio_dirty_list = bio;
-		spin_unlock_irqrestore(&bio_dirty_lock, flags);
-		schedule_work(&bio_dirty_work);
-	} else {
-		bio_put(bio);
-	}
+	bio_release_pages(bio);
+	bio_put(bio);
+	return;
+defer:
+	spin_lock_irqsave(&bio_dirty_lock, flags);
+	bio->bi_private = bio_dirty_list;
+	bio_dirty_list = bio;
+	spin_unlock_irqrestore(&bio_dirty_lock, flags);
+	schedule_work(&bio_dirty_work);
 }
 EXPORT_SYMBOL_GPL(bio_check_pages_dirty);
 
-- 
cgit v1.2.3


From 3bb5098310317ca62304bd21af6ccea57d799b06 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 14:04:13 +0200
Subject: block: bio_set_pages_dirty can't see NULL bv_page in a valid bio_vec

So don't bother handling it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 504b42278099..07d3ffd95989 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -1636,10 +1636,8 @@ void bio_set_pages_dirty(struct bio *bio)
 	int i;
 
 	bio_for_each_segment_all(bvec, bio, i) {
-		struct page *page = bvec->bv_page;
-
-		if (page && !PageCompound(page))
-			set_page_dirty_lock(page);
+		if (!PageCompound(bvec->bv_page))
+			set_page_dirty_lock(bvec->bv_page);
 	}
 }
 EXPORT_SYMBOL_GPL(bio_set_pages_dirty);
-- 
cgit v1.2.3


From 1d25e3eeed1d987404e2d2e451eebac8c15cecc1 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 24 Jul 2018 11:29:01 -0700
Subject: mtd/maps: fix solutionengine.c printk format warnings

Fix 2 printk format warnings (this driver is currently only used by
arch/sh/) by using "%pap" instead of "%lx".

Fixes these build warnings:

../drivers/mtd/maps/solutionengine.c: In function 'init_soleng_maps':
../include/linux/kern_levels.h:5:18: warning: format '%lx' expects argument of type 'long unsigned int', but argument 2 has type 'resource_size_t' {aka 'unsigned int'} [-Wformat=]
../drivers/mtd/maps/solutionengine.c:62:54: note: format string is defined here
  printk(KERN_NOTICE "Solution Engine: Flash at 0x%08lx, EPROM at 0x%08lx\n",
                                                  ~~~~^
                                                  %08x
../include/linux/kern_levels.h:5:18: warning: format '%lx' expects argument of type 'long unsigned int', but argument 3 has type 'resource_size_t' {aka 'unsigned int'} [-Wformat=]
../drivers/mtd/maps/solutionengine.c:62:72: note: format string is defined here
  printk(KERN_NOTICE "Solution Engine: Flash at 0x%08lx, EPROM at 0x%08lx\n",
                                                                    ~~~~^
                                                                    %08x

Cc: David Woodhouse <dwmw2@infradead.org>
Cc: Brian Norris <computersforpeace@gmail.com>
Cc: Boris Brezillon <boris.brezillon@bootlin.com>
Cc: Marek Vasut <marek.vasut@gmail.com>
Cc: Richard Weinberger <richard@nod.at>
Cc: linux-mtd@lists.infradead.org
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: Rich Felker <dalias@libc.org>
Cc: linux-sh@vger.kernel.org
Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/maps/solutionengine.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/maps/solutionengine.c b/drivers/mtd/maps/solutionengine.c
index bb580bc16445..c07f21b20463 100644
--- a/drivers/mtd/maps/solutionengine.c
+++ b/drivers/mtd/maps/solutionengine.c
@@ -59,9 +59,9 @@ static int __init init_soleng_maps(void)
 			return -ENXIO;
 		}
 	}
-	printk(KERN_NOTICE "Solution Engine: Flash at 0x%08lx, EPROM at 0x%08lx\n",
-	       soleng_flash_map.phys & 0x1fffffff,
-	       soleng_eprom_map.phys & 0x1fffffff);
+	printk(KERN_NOTICE "Solution Engine: Flash at 0x%pap, EPROM at 0x%pap\n",
+	       &soleng_flash_map.phys,
+	       &soleng_eprom_map.phys);
 	flash_mtd->owner = THIS_MODULE;
 
 	eprom_mtd = do_map_probe("map_rom", &soleng_eprom_map);
-- 
cgit v1.2.3


From c8b27acc775990bbd01f067ee7616f7abf2c98a1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 09:52:30 +0200
Subject: bcache: don't clone bio in bch_data_verify

We immediately overwrite the biovec array, so instead just allocate
a new bio and copy over the disk, setor and size.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Acked-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/debug.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index d030ce3025a6..04d146711950 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -110,11 +110,15 @@ void bch_data_verify(struct cached_dev *dc, struct bio *bio)
 	struct bio_vec bv, cbv;
 	struct bvec_iter iter, citer = { 0 };
 
-	check = bio_clone_kmalloc(bio, GFP_NOIO);
+	check = bio_kmalloc(GFP_NOIO, bio_segments(bio));
 	if (!check)
 		return;
+	check->bi_disk = bio->bi_disk;
 	check->bi_opf = REQ_OP_READ;
+	check->bi_iter.bi_sector = bio->bi_iter.bi_sector;
+	check->bi_iter.bi_size = bio->bi_iter.bi_size;
 
+	bch_bio_map(check, NULL);
 	if (bch_bio_alloc_pages(check, GFP_NOIO))
 		goto out_put;
 
-- 
cgit v1.2.3


From 076ff2f0b877df4ace6604480f9b1278e61719b8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 09:52:31 +0200
Subject: exofs: use bio_clone_fast in _write_mirror

The mirroring code never changes the bio data or biovecs.  This means
we can reuse the biovec allocation easily instead of duplicating it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by Boaz Harrosh <ooo@electrozaur.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/exofs/ore.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/exofs/ore.c b/fs/exofs/ore.c
index 1b8b44637e70..5331a15a61f1 100644
--- a/fs/exofs/ore.c
+++ b/fs/exofs/ore.c
@@ -873,8 +873,8 @@ static int _write_mirror(struct ore_io_state *ios, int cur_comp)
 			struct bio *bio;
 
 			if (per_dev != master_dev) {
-				bio = bio_clone_kmalloc(master_dev->bio,
-							GFP_KERNEL);
+				bio = bio_clone_fast(master_dev->bio,
+						     GFP_KERNEL, NULL);
 				if (unlikely(!bio)) {
 					ORE_DBGMSG(
 					      "Failed to allocate BIO size=%u\n",
-- 
cgit v1.2.3


From 071f52fbce6161706d070ceada5accb81630bf02 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 09:52:32 +0200
Subject: block: remove bio_clone_kmalloc

Unused now.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/bio.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/include/linux/bio.h b/include/linux/bio.h
index ab221c517f4e..b861baa59454 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -443,12 +443,6 @@ static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs)
 	return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL);
 }
 
-static inline struct bio *bio_clone_kmalloc(struct bio *bio, gfp_t gfp_mask)
-{
-	return bio_clone_bioset(bio, gfp_mask, NULL);
-
-}
-
 extern blk_qc_t submit_bio(struct bio *);
 
 extern void bio_endio(struct bio *);
-- 
cgit v1.2.3


From 3ed122e68bb2dcab36b48109431341736e37ce85 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 09:52:33 +0200
Subject: md: remove a bogus comment

The function name mentioned doesn't exist, and the code next to it
doesn't match the description either.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/md.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/md/md.c b/drivers/md/md.c
index f6e58dbca0d4..cb4eb5faa519 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -204,10 +204,6 @@ static int start_readonly;
  */
 static bool create_on_open = true;
 
-/* bio_clone_mddev
- * like bio_clone_bioset, but with a local bio set
- */
-
 struct bio *bio_alloc_mddev(gfp_t gfp_mask, int nr_iovecs,
 			    struct mddev *mddev)
 {
-- 
cgit v1.2.3


From c55183c9aaa00d2bbb578169a480e31aff3d397c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 09:52:34 +0200
Subject: block: unexport bio_clone_bioset

Now only used by the bounce code, so move it there and mark the function
static.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c         | 77 -----------------------------------------------------
 block/bounce.c      | 69 ++++++++++++++++++++++++++++++++++++++++++++++-
 include/linux/bio.h |  1 -
 3 files changed, 68 insertions(+), 79 deletions(-)

diff --git a/block/bio.c b/block/bio.c
index 07d3ffd95989..b832151cd0bf 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -646,83 +646,6 @@ struct bio *bio_clone_fast(struct bio *bio, gfp_t gfp_mask, struct bio_set *bs)
 }
 EXPORT_SYMBOL(bio_clone_fast);
 
-/**
- * 	bio_clone_bioset - clone a bio
- * 	@bio_src: bio to clone
- *	@gfp_mask: allocation priority
- *	@bs: bio_set to allocate from
- *
- *	Clone bio. Caller will own the returned bio, but not the actual data it
- *	points to. Reference count of returned bio will be one.
- */
-struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask,
-			     struct bio_set *bs)
-{
-	struct bvec_iter iter;
-	struct bio_vec bv;
-	struct bio *bio;
-
-	/*
-	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
-	 * bio_src->bi_io_vec to bio->bi_io_vec.
-	 *
-	 * We can't do that anymore, because:
-	 *
-	 *  - The point of cloning the biovec is to produce a bio with a biovec
-	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
-	 *
-	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
-	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
-	 *    But the clone should succeed as long as the number of biovecs we
-	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
-	 *
-	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
-	 *    that does not own the bio - reason being drivers don't use it for
-	 *    iterating over the biovec anymore, so expecting it to be kept up
-	 *    to date (i.e. for clones that share the parent biovec) is just
-	 *    asking for trouble and would force extra work on
-	 *    __bio_clone_fast() anyways.
-	 */
-
-	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
-	if (!bio)
-		return NULL;
-	bio->bi_disk		= bio_src->bi_disk;
-	bio->bi_opf		= bio_src->bi_opf;
-	bio->bi_write_hint	= bio_src->bi_write_hint;
-	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
-	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
-
-	switch (bio_op(bio)) {
-	case REQ_OP_DISCARD:
-	case REQ_OP_SECURE_ERASE:
-	case REQ_OP_WRITE_ZEROES:
-		break;
-	case REQ_OP_WRITE_SAME:
-		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
-		break;
-	default:
-		bio_for_each_segment(bv, bio_src, iter)
-			bio->bi_io_vec[bio->bi_vcnt++] = bv;
-		break;
-	}
-
-	if (bio_integrity(bio_src)) {
-		int ret;
-
-		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
-		if (ret < 0) {
-			bio_put(bio);
-			return NULL;
-		}
-	}
-
-	bio_clone_blkcg_association(bio, bio_src);
-
-	return bio;
-}
-EXPORT_SYMBOL(bio_clone_bioset);
-
 /**
  *	bio_add_pc_page	-	attempt to add page to bio
  *	@q: the target queue
diff --git a/block/bounce.c b/block/bounce.c
index fd31347b7836..bc63b3a2d18c 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -195,6 +195,73 @@ static void bounce_end_io_read_isa(struct bio *bio)
 	__bounce_end_io_read(bio, &isa_page_pool);
 }
 
+static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask,
+		struct bio_set *bs)
+{
+	struct bvec_iter iter;
+	struct bio_vec bv;
+	struct bio *bio;
+
+	/*
+	 * Pre immutable biovecs, __bio_clone() used to just do a memcpy from
+	 * bio_src->bi_io_vec to bio->bi_io_vec.
+	 *
+	 * We can't do that anymore, because:
+	 *
+	 *  - The point of cloning the biovec is to produce a bio with a biovec
+	 *    the caller can modify: bi_idx and bi_bvec_done should be 0.
+	 *
+	 *  - The original bio could've had more than BIO_MAX_PAGES biovecs; if
+	 *    we tried to clone the whole thing bio_alloc_bioset() would fail.
+	 *    But the clone should succeed as long as the number of biovecs we
+	 *    actually need to allocate is fewer than BIO_MAX_PAGES.
+	 *
+	 *  - Lastly, bi_vcnt should not be looked at or relied upon by code
+	 *    that does not own the bio - reason being drivers don't use it for
+	 *    iterating over the biovec anymore, so expecting it to be kept up
+	 *    to date (i.e. for clones that share the parent biovec) is just
+	 *    asking for trouble and would force extra work on
+	 *    __bio_clone_fast() anyways.
+	 */
+
+	bio = bio_alloc_bioset(gfp_mask, bio_segments(bio_src), bs);
+	if (!bio)
+		return NULL;
+	bio->bi_disk		= bio_src->bi_disk;
+	bio->bi_opf		= bio_src->bi_opf;
+	bio->bi_write_hint	= bio_src->bi_write_hint;
+	bio->bi_iter.bi_sector	= bio_src->bi_iter.bi_sector;
+	bio->bi_iter.bi_size	= bio_src->bi_iter.bi_size;
+
+	switch (bio_op(bio)) {
+	case REQ_OP_DISCARD:
+	case REQ_OP_SECURE_ERASE:
+	case REQ_OP_WRITE_ZEROES:
+		break;
+	case REQ_OP_WRITE_SAME:
+		bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0];
+		break;
+	default:
+		bio_for_each_segment(bv, bio_src, iter)
+			bio->bi_io_vec[bio->bi_vcnt++] = bv;
+		break;
+	}
+
+	if (bio_integrity(bio_src)) {
+		int ret;
+
+		ret = bio_integrity_clone(bio, bio_src, gfp_mask);
+		if (ret < 0) {
+			bio_put(bio);
+			return NULL;
+		}
+	}
+
+	bio_clone_blkcg_association(bio, bio_src);
+
+	return bio;
+}
+
 static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 			       mempool_t *pool)
 {
@@ -222,7 +289,7 @@ static void __blk_queue_bounce(struct request_queue *q, struct bio **bio_orig,
 		generic_make_request(*bio_orig);
 		*bio_orig = bio;
 	}
-	bio = bio_clone_bioset(*bio_orig, GFP_NOIO, passthrough ? NULL :
+	bio = bounce_clone_bio(*bio_orig, GFP_NOIO, passthrough ? NULL :
 			&bounce_bio_set);
 
 	bio_for_each_segment_all(to, bio, i) {
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b861baa59454..51371740d2a8 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -429,7 +429,6 @@ extern void bio_put(struct bio *);
 
 extern void __bio_clone_fast(struct bio *, struct bio *);
 extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *);
-extern struct bio *bio_clone_bioset(struct bio *, gfp_t, struct bio_set *bs);
 
 extern struct bio_set fs_bio_set;
 
-- 
cgit v1.2.3


From 2e90396ad999327c153a6a129b3b683215e1ddea Mon Sep 17 00:00:00 2001
From: Mathieu Malaterre <malat@debian.org>
Date: Wed, 6 Jun 2018 21:37:29 +0200
Subject: MIPS: Ci20: Enable SPI/GPIO driver

Enable CONFIG_SPI_GPIO in ci20_defconfig, in order to make use of the
spi-gpio driver in a further commit.

[paul.burton@mips.com: Rewrite commit message.]

Signed-off-by: Mathieu Malaterre <malat@debian.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19488/
Cc: James Hogan <jhogan@kernel.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: devicetree@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/configs/ci20_defconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/mips/configs/ci20_defconfig b/arch/mips/configs/ci20_defconfig
index be23fd25eeaa..030ff9c205fb 100644
--- a/arch/mips/configs/ci20_defconfig
+++ b/arch/mips/configs/ci20_defconfig
@@ -92,6 +92,8 @@ CONFIG_SERIAL_OF_PLATFORM=y
 # CONFIG_HW_RANDOM is not set
 CONFIG_I2C=y
 CONFIG_I2C_JZ4780=y
+CONFIG_SPI=y
+CONFIG_SPI_GPIO=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_GPIO_INGENIC=y
 # CONFIG_HWMON is not set
-- 
cgit v1.2.3


From c24f5762d374b7f2aae31b7a393bdfa66ed06d8b Mon Sep 17 00:00:00 2001
From: Mathieu Malaterre <malat@debian.org>
Date: Wed, 6 Jun 2018 21:37:30 +0200
Subject: MIPS: jz4780: DTS: Probe the spi-gpio driver from devicetree

Make use of the spi-gpio driver to provide SPI support on the Ingenic
JZ4780 SoC using the pins that can be used with the SSI0 device as
GPIOs, until such time as we have support for the Ingenic SPI/SSI
controller.

[paul.burton@mips.com: Rewrite commit message.]

Signed-off-by: Mathieu Malaterre <malat@debian.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19489/
Cc: James Hogan <jhogan@kernel.org>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: devicetree@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/dts/ingenic/jz4780.dtsi | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/arch/mips/boot/dts/ingenic/jz4780.dtsi b/arch/mips/boot/dts/ingenic/jz4780.dtsi
index aa4e8f75ff5d..ce93d57f1b4d 100644
--- a/arch/mips/boot/dts/ingenic/jz4780.dtsi
+++ b/arch/mips/boot/dts/ingenic/jz4780.dtsi
@@ -155,6 +155,25 @@
 		};
 	};
 
+	spi_gpio {
+		compatible = "spi-gpio";
+		#address-cells = <1>;
+		#size-cells = <0>;
+		num-chipselects = <2>;
+
+		gpio-miso = <&gpe 14 0>;
+		gpio-sck = <&gpe 15 0>;
+		gpio-mosi = <&gpe 17 0>;
+		cs-gpios = <&gpe 16 0
+			    &gpe 18 0>;
+
+		spidev@0 {
+			compatible = "spidev";
+			reg = <0>;
+			spi-max-frequency = <1000000>;
+		};
+	};
+
 	uart0: serial@10030000 {
 		compatible = "ingenic,jz4780-uart";
 		reg = <0x10030000 0x100>;
-- 
cgit v1.2.3


From 42c9cdfe1e11e083dceb0f0c4977b758cf7403b9 Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@redhat.com>
Date: Fri, 20 Jul 2018 14:57:38 -0400
Subject: block: allow max_discard_segments to be stacked

Set max_discard_segments to USHRT_MAX in blk_set_stacking_limits() so
that blk_stack_limits() can stack up this limit for stacked devices.

before:

$ cat /sys/block/nvme0n1/queue/max_discard_segments
256
$ cat /sys/block/dm-0/queue/max_discard_segments
1

after:

$ cat /sys/block/nvme0n1/queue/max_discard_segments
256
$ cat /sys/block/dm-0/queue/max_discard_segments
256

Fixes: 1e739730c5b9e ("block: optionally merge discontiguous discard bios into a single request")
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mike Snitzer <snitzer@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-settings.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 053de87d1fda..ffd459969689 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -128,7 +128,7 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 
 	/* Inherit limits from component devices */
 	lim->max_segments = USHRT_MAX;
-	lim->max_discard_segments = 1;
+	lim->max_discard_segments = USHRT_MAX;
 	lim->max_hw_sectors = UINT_MAX;
 	lim->max_segment_size = UINT_MAX;
 	lim->max_sectors = UINT_MAX;
-- 
cgit v1.2.3


From d2ad00eb78792b396a6d012f15d6297a1701b8bc Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 13 Jul 2018 16:32:20 +0200
Subject: dt-bindings: mtd: explicitly document nesting partitions descriptions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Documentation was already saying that fixed and dynamic partitioning can
be mixed but was missing a clear description and examples. This commit
adds a proper documentation of how descriptions can be nested and how
layouts can be mixed.

This addition is important for partitions that contain subpartitions.
In such cases partitions have to be properly described in order to let
system handle them correctly.

Depending on situation, nesting descriptions may provide more accurate
logic/structure and/or allow mixing partitioning types (various
"compatible" values).

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 .../devicetree/bindings/mtd/partition.txt          | 46 ++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/Documentation/devicetree/bindings/mtd/partition.txt b/Documentation/devicetree/bindings/mtd/partition.txt
index a8f382642ba9..afbbd870496d 100644
--- a/Documentation/devicetree/bindings/mtd/partition.txt
+++ b/Documentation/devicetree/bindings/mtd/partition.txt
@@ -14,6 +14,13 @@ method is used for a given flash device. To describe the method there should be
 a subnode of the flash device that is named 'partitions'. It must have a
 'compatible' property, which is used to identify the method to use.
 
+When a single partition is represented with a DT node (it depends on a used
+format) it may also be described using above rules ('compatible' and optionally
+some extra properties / subnodes). It allows describing more complex,
+hierarchical (multi-level) layouts and should be used if there is some
+significant relation between partitions or some partition internally uses
+another partitioning method.
+
 Available bindings are listed in the "partitions" subdirectory.
 
 
@@ -109,3 +116,42 @@ flash@2 {
 		};
 	};
 };
+
+flash@3 {
+	partitions {
+		compatible = "fixed-partitions";
+		#address-cells = <1>;
+		#size-cells = <1>;
+
+		partition@0 {
+			label = "bootloader";
+			reg = <0x000000 0x100000>;
+			read-only;
+		};
+
+		firmware@100000 {
+			label = "firmware";
+			reg = <0x100000 0xe00000>;
+			compatible = "brcm,trx";
+		};
+
+		calibration@f00000 {
+			label = "calibration";
+			reg = <0xf00000 0x100000>;
+			compatible = "fixed-partitions";
+			ranges = <0 0xf00000 0x100000>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+
+			partition@0 {
+				label = "wifi0";
+				reg = <0x000000 0x080000>;
+			};
+
+			partition@80000 {
+				label = "wifi1";
+				reg = <0x080000 0x080000>;
+			};
+		};
+	};
+};
-- 
cgit v1.2.3


From 76a832254ab05502c9394cc51ded6f0abe0e0bee Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Fri, 13 Jul 2018 16:32:21 +0200
Subject: mtd: partitions: use DT info for parsing partitions with "compatible"
 prop
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

So far only flash devices could be described in DT regarding partitions
parsing. That could be done with "partitions" subnode and a proper
"compatible" string.

Some devices may use hierarchical (multi-level) layouts and may mix used
layouts (fixed and dynamic). Describing that in DT is done by specifying
"compatible" for DT-represented partition plus optionally more
properties and/or subnodes.

To support such layouts each DT partition has to be checked for
additional description.

Please note this implementation will work in parallel with support for
partition type specified for non-DT setups. That already works since
commit 1a0915be1926 ("mtd: partitions: add support for partition
parsers").

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/mtdpart.c | 33 +++++++++++++--------------------
 1 file changed, 13 insertions(+), 20 deletions(-)

diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index f8d3a015cdad..52e2cb35fc79 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -322,22 +322,6 @@ static inline void free_partition(struct mtd_part *p)
 	kfree(p);
 }
 
-/**
- * mtd_parse_part - parse MTD partition looking for subpartitions
- *
- * @slave: part that is supposed to be a container and should be parsed
- * @types: NULL-terminated array with names of partition parsers to try
- *
- * Some partitions are kind of containers with extra subpartitions (volumes).
- * There can be various formats of such containers. This function tries to use
- * specified parsers to analyze given partition and registers found
- * subpartitions on success.
- */
-static int mtd_parse_part(struct mtd_part *slave, const char *const *types)
-{
-	return parse_mtd_partitions(&slave->mtd, types, NULL);
-}
-
 static struct mtd_part *allocate_partition(struct mtd_info *parent,
 			const struct mtd_partition *part, int partno,
 			uint64_t cur_offset)
@@ -735,8 +719,8 @@ int add_mtd_partitions(struct mtd_info *master,
 
 		add_mtd_device(&slave->mtd);
 		mtd_add_partition_attrs(slave);
-		if (parts[i].types)
-			mtd_parse_part(slave, parts[i].types);
+		/* Look for subpartitions */
+		parse_mtd_partitions(&slave->mtd, parts[i].types, NULL);
 
 		cur_offset = slave->offset + slave->mtd.size;
 	}
@@ -812,6 +796,12 @@ static const char * const default_mtd_part_types[] = {
 	NULL
 };
 
+/* Check DT only when looking for subpartitions. */
+static const char * const default_subpartition_types[] = {
+	"ofpart",
+	NULL
+};
+
 static int mtd_part_do_parse(struct mtd_part_parser *parser,
 			     struct mtd_info *master,
 			     struct mtd_partitions *pparts,
@@ -882,7 +872,9 @@ static int mtd_part_of_parse(struct mtd_info *master,
 	const char *fixed = "fixed-partitions";
 	int ret, err = 0;
 
-	np = of_get_child_by_name(mtd_get_of_node(master), "partitions");
+	np = mtd_get_of_node(master);
+	if (!mtd_is_partition(master))
+		np = of_get_child_by_name(np, "partitions");
 	of_property_for_each_string(np, "compatible", prop, compat) {
 		parser = mtd_part_get_compatible_parser(compat);
 		if (!parser)
@@ -945,7 +937,8 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
 	int ret, err = 0;
 
 	if (!types)
-		types = default_mtd_part_types;
+		types = mtd_is_partition(master) ? default_subpartition_types :
+			default_mtd_part_types;
 
 	for ( ; *types; types++) {
 		/*
-- 
cgit v1.2.3


From 93e01942a6eb1ce730b42158d0d6c6531fe29ca0 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 12 Jun 2017 11:54:23 -0700
Subject: MIPS: Hardcode cpu_has_* where known at compile time due to ISA

Many architectural features have over time moved from being optional to
either be required or removed by newer architecture releases. This means
that in many cases we can know at compile time whether a feature will be
supported or not purely due to the knowledge we have about the ISA the
kernel build is targeting.

This patch introduces a bunch of utility macros for checking for
supported options, ASEs & combinations of those with ISA revisions. It
then makes use of these in the default definitions of cpu_has_* macros.
The result is that many of the macros become compile-time constant,
allowing more optimisation opportunities for the compiler - particularly
with kernels built for later ISA revisions.

To demonstrate the effect of this patch, the following table shows the
size in bytes of the kernel binary as reported by scripts/bloat-o-meter
for v4.12-rc4 maltasmvp_defconfig kernels with & without this patch. A
variant of maltasmvp_defconfig with CONFIG_CPU_MIPS32_R6 selected is
also shown, to demonstrate that MIPSr6 systems benefit more due to extra
features becoming required by that architecture revision. Builds of
pistachio_defconfig are also shown, as although this is a MIPSr2
platform it doesn't hardcode any features in a machine-specific
cpu-feature-overrides.h, which allows it to gain more from this patch
than the equivalent Malta r2 build.

     Config         | Before  | After   |  Change
    ----------------|---------|---------|---------
     maltasmvp      | 7248316 | 7247714 |    -602
     maltasmvp + r6 | 6955595 | 6950777 |   -4818
     pistachio      | 8650977 | 8363898 | -287079

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/16360/
Cc: Joshua Kinard <kumba@gentoo.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/cpu-features.h | 176 +++++++++++++++++++++--------------
 1 file changed, 107 insertions(+), 69 deletions(-)

diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 9cdb4e4ce258..0edba3e75747 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -14,39 +14,77 @@
 #include <asm/isa-rev.h>
 #include <cpu-feature-overrides.h>
 
+#define __ase(ase)			(cpu_data[0].ases & (ase))
+#define __opt(opt)			(cpu_data[0].options & (opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * Note that these should only be used in cases where a kernel built for an
+ * older ISA *cannot* run on a CPU which supports the feature in question. For
+ * example this may be used for features introduced with MIPSr6, since a kernel
+ * built for an older ISA cannot run on a MIPSr6 CPU. This should not be used
+ * for MIPSr2 features however, since a MIPSr1 or earlier kernel might run on a
+ * MIPSr2 CPU.
+ */
+#define __isa_ge_and_ase(isa, ase)	((MIPS_ISA_REV >= (isa)) && __ase(ase))
+#define __isa_ge_and_opt(isa, opt)	((MIPS_ISA_REV >= (isa)) && __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is >= isa *or* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & then become required.
+ */
+#define __isa_ge_or_ase(isa, ase)	((MIPS_ISA_REV >= (isa)) || __ase(ase))
+#define __isa_ge_or_opt(isa, opt)	((MIPS_ISA_REV >= (isa)) || __opt(opt))
+
+/*
+ * Check if MIPS_ISA_REV is < isa *and* an option or ASE is detected during
+ * boot (typically by cpu_probe()).
+ *
+ * These are for use with features that are optional up until a particular ISA
+ * revision & are then removed - ie. no longer present in any CPU implementing
+ * the given ISA revision.
+ */
+#define __isa_lt_and_ase(isa, ase)	((MIPS_ISA_REV < (isa)) && __ase(ase))
+#define __isa_lt_and_opt(isa, opt)	((MIPS_ISA_REV < (isa)) && __opt(opt))
+
 /*
  * SMP assumption: Options of CPU 0 are a superset of all processors.
  * This is true for all known MIPS systems.
  */
 #ifndef cpu_has_tlb
-#define cpu_has_tlb		(cpu_data[0].options & MIPS_CPU_TLB)
+#define cpu_has_tlb		__opt(MIPS_CPU_TLB)
 #endif
 #ifndef cpu_has_ftlb
-#define cpu_has_ftlb		(cpu_data[0].options & MIPS_CPU_FTLB)
+#define cpu_has_ftlb		__opt(MIPS_CPU_FTLB)
 #endif
 #ifndef cpu_has_tlbinv
-#define cpu_has_tlbinv		(cpu_data[0].options & MIPS_CPU_TLBINV)
+#define cpu_has_tlbinv		__opt(MIPS_CPU_TLBINV)
 #endif
 #ifndef cpu_has_segments
-#define cpu_has_segments	(cpu_data[0].options & MIPS_CPU_SEGMENTS)
+#define cpu_has_segments	__opt(MIPS_CPU_SEGMENTS)
 #endif
 #ifndef cpu_has_eva
-#define cpu_has_eva		(cpu_data[0].options & MIPS_CPU_EVA)
+#define cpu_has_eva		__opt(MIPS_CPU_EVA)
 #endif
 #ifndef cpu_has_htw
-#define cpu_has_htw		(cpu_data[0].options & MIPS_CPU_HTW)
+#define cpu_has_htw		__opt(MIPS_CPU_HTW)
 #endif
 #ifndef cpu_has_ldpte
-#define cpu_has_ldpte		(cpu_data[0].options & MIPS_CPU_LDPTE)
+#define cpu_has_ldpte		__opt(MIPS_CPU_LDPTE)
 #endif
 #ifndef cpu_has_rixiex
-#define cpu_has_rixiex		(cpu_data[0].options & MIPS_CPU_RIXIEX)
+#define cpu_has_rixiex		__isa_ge_or_opt(6, MIPS_CPU_RIXIEX)
 #endif
 #ifndef cpu_has_maar
-#define cpu_has_maar		(cpu_data[0].options & MIPS_CPU_MAAR)
+#define cpu_has_maar		__opt(MIPS_CPU_MAAR)
 #endif
 #ifndef cpu_has_rw_llb
-#define cpu_has_rw_llb		(cpu_data[0].options & MIPS_CPU_RW_LLB)
+#define cpu_has_rw_llb		__isa_ge_or_opt(6, MIPS_CPU_RW_LLB)
 #endif
 
 /*
@@ -59,18 +97,18 @@
 #define cpu_has_3kex		(!cpu_has_4kex)
 #endif
 #ifndef cpu_has_4kex
-#define cpu_has_4kex		(cpu_data[0].options & MIPS_CPU_4KEX)
+#define cpu_has_4kex		__isa_ge_or_opt(1, MIPS_CPU_4KEX)
 #endif
 #ifndef cpu_has_3k_cache
-#define cpu_has_3k_cache	(cpu_data[0].options & MIPS_CPU_3K_CACHE)
+#define cpu_has_3k_cache	__isa_lt_and_opt(1, MIPS_CPU_3K_CACHE)
 #endif
 #define cpu_has_6k_cache	0
 #define cpu_has_8k_cache	0
 #ifndef cpu_has_4k_cache
-#define cpu_has_4k_cache	(cpu_data[0].options & MIPS_CPU_4K_CACHE)
+#define cpu_has_4k_cache	__isa_ge_or_opt(1, MIPS_CPU_4K_CACHE)
 #endif
 #ifndef cpu_has_tx39_cache
-#define cpu_has_tx39_cache	(cpu_data[0].options & MIPS_CPU_TX39_CACHE)
+#define cpu_has_tx39_cache	__opt(MIPS_CPU_TX39_CACHE)
 #endif
 #ifndef cpu_has_octeon_cache
 #define cpu_has_octeon_cache	0
@@ -83,92 +121,92 @@
 #define raw_cpu_has_fpu		cpu_has_fpu
 #endif
 #ifndef cpu_has_32fpr
-#define cpu_has_32fpr		(cpu_data[0].options & MIPS_CPU_32FPR)
+#define cpu_has_32fpr		__isa_ge_or_opt(1, MIPS_CPU_32FPR)
 #endif
 #ifndef cpu_has_counter
-#define cpu_has_counter		(cpu_data[0].options & MIPS_CPU_COUNTER)
+#define cpu_has_counter		__opt(MIPS_CPU_COUNTER)
 #endif
 #ifndef cpu_has_watch
-#define cpu_has_watch		(cpu_data[0].options & MIPS_CPU_WATCH)
+#define cpu_has_watch		__opt(MIPS_CPU_WATCH)
 #endif
 #ifndef cpu_has_divec
-#define cpu_has_divec		(cpu_data[0].options & MIPS_CPU_DIVEC)
+#define cpu_has_divec		__isa_ge_or_opt(1, MIPS_CPU_DIVEC)
 #endif
 #ifndef cpu_has_vce
-#define cpu_has_vce		(cpu_data[0].options & MIPS_CPU_VCE)
+#define cpu_has_vce		__opt(MIPS_CPU_VCE)
 #endif
 #ifndef cpu_has_cache_cdex_p
-#define cpu_has_cache_cdex_p	(cpu_data[0].options & MIPS_CPU_CACHE_CDEX_P)
+#define cpu_has_cache_cdex_p	__opt(MIPS_CPU_CACHE_CDEX_P)
 #endif
 #ifndef cpu_has_cache_cdex_s
-#define cpu_has_cache_cdex_s	(cpu_data[0].options & MIPS_CPU_CACHE_CDEX_S)
+#define cpu_has_cache_cdex_s	__opt(MIPS_CPU_CACHE_CDEX_S)
 #endif
 #ifndef cpu_has_prefetch
-#define cpu_has_prefetch	(cpu_data[0].options & MIPS_CPU_PREFETCH)
+#define cpu_has_prefetch	__isa_ge_or_opt(1, MIPS_CPU_PREFETCH)
 #endif
 #ifndef cpu_has_mcheck
-#define cpu_has_mcheck		(cpu_data[0].options & MIPS_CPU_MCHECK)
+#define cpu_has_mcheck		__isa_ge_or_opt(1, MIPS_CPU_MCHECK)
 #endif
 #ifndef cpu_has_ejtag
-#define cpu_has_ejtag		(cpu_data[0].options & MIPS_CPU_EJTAG)
+#define cpu_has_ejtag		__opt(MIPS_CPU_EJTAG)
 #endif
 #ifndef cpu_has_llsc
-#define cpu_has_llsc		(cpu_data[0].options & MIPS_CPU_LLSC)
+#define cpu_has_llsc		__isa_ge_or_opt(1, MIPS_CPU_LLSC)
 #endif
 #ifndef cpu_has_bp_ghist
-#define cpu_has_bp_ghist	(cpu_data[0].options & MIPS_CPU_BP_GHIST)
+#define cpu_has_bp_ghist	__opt(MIPS_CPU_BP_GHIST)
 #endif
 #ifndef kernel_uses_llsc
 #define kernel_uses_llsc	cpu_has_llsc
 #endif
 #ifndef cpu_has_guestctl0ext
-#define cpu_has_guestctl0ext	(cpu_data[0].options & MIPS_CPU_GUESTCTL0EXT)
+#define cpu_has_guestctl0ext	__opt(MIPS_CPU_GUESTCTL0EXT)
 #endif
 #ifndef cpu_has_guestctl1
-#define cpu_has_guestctl1	(cpu_data[0].options & MIPS_CPU_GUESTCTL1)
+#define cpu_has_guestctl1	__opt(MIPS_CPU_GUESTCTL1)
 #endif
 #ifndef cpu_has_guestctl2
-#define cpu_has_guestctl2	(cpu_data[0].options & MIPS_CPU_GUESTCTL2)
+#define cpu_has_guestctl2	__opt(MIPS_CPU_GUESTCTL2)
 #endif
 #ifndef cpu_has_guestid
-#define cpu_has_guestid		(cpu_data[0].options & MIPS_CPU_GUESTID)
+#define cpu_has_guestid		__opt(MIPS_CPU_GUESTID)
 #endif
 #ifndef cpu_has_drg
-#define cpu_has_drg		(cpu_data[0].options & MIPS_CPU_DRG)
+#define cpu_has_drg		__opt(MIPS_CPU_DRG)
 #endif
 #ifndef cpu_has_mips16
-#define cpu_has_mips16		(cpu_data[0].ases & MIPS_ASE_MIPS16)
+#define cpu_has_mips16		__isa_lt_and_ase(6, MIPS_ASE_MIPS16)
 #endif
 #ifndef cpu_has_mips16e2
-#define cpu_has_mips16e2	(cpu_data[0].ases & MIPS_ASE_MIPS16E2)
+#define cpu_has_mips16e2	__isa_lt_and_ase(6, MIPS_ASE_MIPS16E2)
 #endif
 #ifndef cpu_has_mdmx
-#define cpu_has_mdmx		(cpu_data[0].ases & MIPS_ASE_MDMX)
+#define cpu_has_mdmx		__isa_lt_and_ase(6, MIPS_ASE_MDMX)
 #endif
 #ifndef cpu_has_mips3d
-#define cpu_has_mips3d		(cpu_data[0].ases & MIPS_ASE_MIPS3D)
+#define cpu_has_mips3d		__isa_lt_and_ase(6, MIPS_ASE_MIPS3D)
 #endif
 #ifndef cpu_has_smartmips
-#define cpu_has_smartmips	(cpu_data[0].ases & MIPS_ASE_SMARTMIPS)
+#define cpu_has_smartmips	__isa_lt_and_ase(6, MIPS_ASE_SMARTMIPS)
 #endif
 
 #ifndef cpu_has_rixi
-#define cpu_has_rixi		(cpu_data[0].options & MIPS_CPU_RIXI)
+#define cpu_has_rixi		__isa_ge_or_opt(6, MIPS_CPU_RIXI)
 #endif
 
 #ifndef cpu_has_mmips
 # ifdef CONFIG_SYS_SUPPORTS_MICROMIPS
-#  define cpu_has_mmips		(cpu_data[0].options & MIPS_CPU_MICROMIPS)
+#  define cpu_has_mmips		__opt(MIPS_CPU_MICROMIPS)
 # else
 #  define cpu_has_mmips		0
 # endif
 #endif
 
 #ifndef cpu_has_lpa
-#define cpu_has_lpa		(cpu_data[0].options & MIPS_CPU_LPA)
+#define cpu_has_lpa		__opt(MIPS_CPU_LPA)
 #endif
 #ifndef cpu_has_mvh
-#define cpu_has_mvh		(cpu_data[0].options & MIPS_CPU_MVH)
+#define cpu_has_mvh		__opt(MIPS_CPU_MVH)
 #endif
 #ifndef cpu_has_xpa
 #define cpu_has_xpa		(cpu_has_lpa && cpu_has_mvh)
@@ -338,32 +376,32 @@
 #endif
 
 #ifndef cpu_has_dsp
-#define cpu_has_dsp		(cpu_data[0].ases & MIPS_ASE_DSP)
+#define cpu_has_dsp		__ase(MIPS_ASE_DSP)
 #endif
 
 #ifndef cpu_has_dsp2
-#define cpu_has_dsp2		(cpu_data[0].ases & MIPS_ASE_DSP2P)
+#define cpu_has_dsp2		__ase(MIPS_ASE_DSP2P)
 #endif
 
 #ifndef cpu_has_dsp3
-#define cpu_has_dsp3		(cpu_data[0].ases & MIPS_ASE_DSP3)
+#define cpu_has_dsp3		__ase(MIPS_ASE_DSP3)
 #endif
 
 #ifndef cpu_has_mipsmt
-#define cpu_has_mipsmt		(cpu_data[0].ases & MIPS_ASE_MIPSMT)
+#define cpu_has_mipsmt		__isa_lt_and_ase(6, MIPS_ASE_MIPSMT)
 #endif
 
 #ifndef cpu_has_vp
-#define cpu_has_vp		(cpu_data[0].options & MIPS_CPU_VP)
+#define cpu_has_vp		__isa_ge_and_opt(6, MIPS_CPU_VP)
 #endif
 
 #ifndef cpu_has_userlocal
-#define cpu_has_userlocal	(cpu_data[0].options & MIPS_CPU_ULRI)
+#define cpu_has_userlocal	__isa_ge_or_opt(6, MIPS_CPU_ULRI)
 #endif
 
 #ifdef CONFIG_32BIT
 # ifndef cpu_has_nofpuex
-# define cpu_has_nofpuex	(cpu_data[0].options & MIPS_CPU_NOFPUEX)
+# define cpu_has_nofpuex	__isa_lt_and_opt(1, MIPS_CPU_NOFPUEX)
 # endif
 # ifndef cpu_has_64bits
 # define cpu_has_64bits		(cpu_data[0].isa_level & MIPS_CPU_ISA_64BIT)
@@ -405,19 +443,19 @@
 #endif
 
 #if defined(CONFIG_CPU_MIPSR2_IRQ_VI) && !defined(cpu_has_vint)
-# define cpu_has_vint		(cpu_data[0].options & MIPS_CPU_VINT)
+# define cpu_has_vint		__opt(MIPS_CPU_VINT)
 #elif !defined(cpu_has_vint)
 # define cpu_has_vint			0
 #endif
 
 #if defined(CONFIG_CPU_MIPSR2_IRQ_EI) && !defined(cpu_has_veic)
-# define cpu_has_veic		(cpu_data[0].options & MIPS_CPU_VEIC)
+# define cpu_has_veic		__opt(MIPS_CPU_VEIC)
 #elif !defined(cpu_has_veic)
 # define cpu_has_veic			0
 #endif
 
 #ifndef cpu_has_inclusive_pcaches
-#define cpu_has_inclusive_pcaches	(cpu_data[0].options & MIPS_CPU_INCLUSIVE_CACHES)
+#define cpu_has_inclusive_pcaches	__opt(MIPS_CPU_INCLUSIVE_CACHES)
 #endif
 
 #ifndef cpu_dcache_line_size
@@ -438,63 +476,63 @@
 #endif
 
 #ifndef cpu_has_perf_cntr_intr_bit
-#define cpu_has_perf_cntr_intr_bit	(cpu_data[0].options & MIPS_CPU_PCI)
+#define cpu_has_perf_cntr_intr_bit	__opt(MIPS_CPU_PCI)
 #endif
 
 #ifndef cpu_has_vz
-#define cpu_has_vz		(cpu_data[0].ases & MIPS_ASE_VZ)
+#define cpu_has_vz		__ase(MIPS_ASE_VZ)
 #endif
 
 #if defined(CONFIG_CPU_HAS_MSA) && !defined(cpu_has_msa)
-# define cpu_has_msa		(cpu_data[0].ases & MIPS_ASE_MSA)
+# define cpu_has_msa		__ase(MIPS_ASE_MSA)
 #elif !defined(cpu_has_msa)
 # define cpu_has_msa		0
 #endif
 
 #ifndef cpu_has_ufr
-# define cpu_has_ufr		(cpu_data[0].options & MIPS_CPU_UFR)
+# define cpu_has_ufr		__opt(MIPS_CPU_UFR)
 #endif
 
 #ifndef cpu_has_fre
-# define cpu_has_fre		(cpu_data[0].options & MIPS_CPU_FRE)
+# define cpu_has_fre		__opt(MIPS_CPU_FRE)
 #endif
 
 #ifndef cpu_has_cdmm
-# define cpu_has_cdmm		(cpu_data[0].options & MIPS_CPU_CDMM)
+# define cpu_has_cdmm		__opt(MIPS_CPU_CDMM)
 #endif
 
 #ifndef cpu_has_small_pages
-# define cpu_has_small_pages	(cpu_data[0].options & MIPS_CPU_SP)
+# define cpu_has_small_pages	__opt(MIPS_CPU_SP)
 #endif
 
 #ifndef cpu_has_nan_legacy
-#define cpu_has_nan_legacy	(cpu_data[0].options & MIPS_CPU_NAN_LEGACY)
+#define cpu_has_nan_legacy	__isa_lt_and_opt(6, MIPS_CPU_NAN_LEGACY)
 #endif
 #ifndef cpu_has_nan_2008
-#define cpu_has_nan_2008	(cpu_data[0].options & MIPS_CPU_NAN_2008)
+#define cpu_has_nan_2008	__isa_ge_or_opt(6, MIPS_CPU_NAN_2008)
 #endif
 
 #ifndef cpu_has_ebase_wg
-# define cpu_has_ebase_wg	(cpu_data[0].options & MIPS_CPU_EBASE_WG)
+# define cpu_has_ebase_wg	__opt(MIPS_CPU_EBASE_WG)
 #endif
 
 #ifndef cpu_has_badinstr
-# define cpu_has_badinstr	(cpu_data[0].options & MIPS_CPU_BADINSTR)
+# define cpu_has_badinstr	__isa_ge_or_opt(6, MIPS_CPU_BADINSTR)
 #endif
 
 #ifndef cpu_has_badinstrp
-# define cpu_has_badinstrp	(cpu_data[0].options & MIPS_CPU_BADINSTRP)
+# define cpu_has_badinstrp	__isa_ge_or_opt(6, MIPS_CPU_BADINSTRP)
 #endif
 
 #ifndef cpu_has_contextconfig
-# define cpu_has_contextconfig	(cpu_data[0].options & MIPS_CPU_CTXTC)
+# define cpu_has_contextconfig	__opt(MIPS_CPU_CTXTC)
 #endif
 
 #ifndef cpu_has_perf
-# define cpu_has_perf		(cpu_data[0].options & MIPS_CPU_PERF)
+# define cpu_has_perf		__opt(MIPS_CPU_PERF)
 #endif
 
-#if defined(CONFIG_SMP) && (MIPS_ISA_REV >= 6)
+#ifdef CONFIG_SMP
 /*
  * Some systems share FTLB RAMs between threads within a core (siblings in
  * kernel parlance). This means that FTLB entries may become invalid at almost
@@ -507,7 +545,7 @@
  */
 # ifndef cpu_has_shared_ftlb_ram
 #  define cpu_has_shared_ftlb_ram \
-	(current_cpu_data.options & MIPS_CPU_SHARED_FTLB_RAM)
+	__isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_RAM)
 # endif
 
 /*
@@ -524,9 +562,9 @@
  */
 # ifndef cpu_has_shared_ftlb_entries
 #  define cpu_has_shared_ftlb_entries \
-	(current_cpu_data.options & MIPS_CPU_SHARED_FTLB_ENTRIES)
+	__isa_ge_and_opt(6, MIPS_CPU_SHARED_FTLB_ENTRIES)
 # endif
-#endif /* SMP && MIPS_ISA_REV >= 6 */
+#endif /* SMP */
 
 #ifndef cpu_has_shared_ftlb_ram
 # define cpu_has_shared_ftlb_ram 0
@@ -537,7 +575,7 @@
 
 #ifdef CONFIG_MIPS_MT_SMP
 # define cpu_has_mipsmt_pertccounters \
-	(cpu_data[0].options & MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
+	__isa_lt_and_opt(6, MIPS_CPU_MT_PER_TC_PERF_COUNTERS)
 #else
 # define cpu_has_mipsmt_pertccounters 0
 #endif /* CONFIG_MIPS_MT_SMP */
-- 
cgit v1.2.3


From 50f699b1f8462959482251a6cd1b7bc6bbd20796 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:01 -0700
Subject: sched: fix trailing whitespace

Remove trailing whitespace and blank lines at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/Kconfig        | 4 ++--
 net/sched/Makefile       | 2 +-
 net/sched/act_connmark.c | 1 -
 net/sched/act_pedit.c    | 1 -
 net/sched/cls_basic.c    | 1 -
 5 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 7af246764a35..bba71225adbd 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -1,6 +1,6 @@
 #
 # Traffic control configuration.
-# 
+#
 
 menuconfig NET_SCHED
 	bool "QoS and/or fair queueing"
@@ -706,7 +706,7 @@ config NET_CLS_ACT
 
 config NET_ACT_POLICE
 	tristate "Traffic Policing"
-        depends on NET_CLS_ACT 
+        depends on NET_CLS_ACT
         ---help---
 	  Say Y here if you want to do traffic policing, i.e. strict
 	  bandwidth limiting. This action replaces the existing policing
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 673ee7d26ff2..910ec7463a36 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -33,7 +33,7 @@ obj-$(CONFIG_NET_SCH_HTB)	+= sch_htb.o
 obj-$(CONFIG_NET_SCH_HFSC)	+= sch_hfsc.o
 obj-$(CONFIG_NET_SCH_RED)	+= sch_red.o
 obj-$(CONFIG_NET_SCH_GRED)	+= sch_gred.o
-obj-$(CONFIG_NET_SCH_INGRESS)	+= sch_ingress.o 
+obj-$(CONFIG_NET_SCH_INGRESS)	+= sch_ingress.o
 obj-$(CONFIG_NET_SCH_DSMARK)	+= sch_dsmark.o
 obj-$(CONFIG_NET_SCH_SFB)	+= sch_sfb.o
 obj-$(CONFIG_NET_SCH_SFQ)	+= sch_sfq.o
diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 1e31f0e448e2..2f9bc833d046 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -252,4 +252,3 @@ module_exit(connmark_cleanup_module);
 MODULE_AUTHOR("Felix Fietkau <nbd@openwrt.org>");
 MODULE_DESCRIPTION("Connection tracking mark restoring");
 MODULE_LICENSE("GPL");
-
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index cc8ffcd1ddb5..9ab5d81aff1a 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -516,4 +516,3 @@ static void __exit pedit_cleanup_module(void)
 
 module_init(pedit_init_module);
 module_exit(pedit_cleanup_module);
-
diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c
index 95367f37098d..6a5dce8baf19 100644
--- a/net/sched/cls_basic.c
+++ b/net/sched/cls_basic.c
@@ -324,4 +324,3 @@ static void __exit exit_basic(void)
 module_init(init_basic)
 module_exit(exit_basic)
 MODULE_LICENSE("GPL");
-
-- 
cgit v1.2.3


From bf9b5567da548ec56c263e210f958fa923a79503 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:02 -0700
Subject: wimax: remove blank lines at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/wimax/Makefile  | 2 --
 net/wimax/debugfs.c | 2 --
 net/wimax/op-msg.c  | 1 -
 net/wimax/stack.c   | 1 -
 4 files changed, 6 deletions(-)

diff --git a/net/wimax/Makefile b/net/wimax/Makefile
index eb2db0d3b880..c2a71ae487ac 100644
--- a/net/wimax/Makefile
+++ b/net/wimax/Makefile
@@ -11,5 +11,3 @@ wimax-y :=		\
 	stack.o
 
 wimax-$(CONFIG_DEBUG_FS) += debugfs.o
-
-
diff --git a/net/wimax/debugfs.c b/net/wimax/debugfs.c
index 6c9bedb7431e..24514840746e 100644
--- a/net/wimax/debugfs.c
+++ b/net/wimax/debugfs.c
@@ -76,5 +76,3 @@ void wimax_debugfs_rm(struct wimax_dev *wimax_dev)
 {
 	debugfs_remove_recursive(wimax_dev->debugfs_dentry);
 }
-
-
diff --git a/net/wimax/op-msg.c b/net/wimax/op-msg.c
index 54aa146930bd..101b2fa3f32e 100644
--- a/net/wimax/op-msg.c
+++ b/net/wimax/op-msg.c
@@ -404,4 +404,3 @@ error_no_wimax_dev:
 	d_fnend(3, NULL, "(skb %p info %p) = %d\n", skb, info, result);
 	return result;
 }
-
diff --git a/net/wimax/stack.c b/net/wimax/stack.c
index 73dba9c077bb..a6307813b6d5 100644
--- a/net/wimax/stack.c
+++ b/net/wimax/stack.c
@@ -630,4 +630,3 @@ module_exit(wimax_subsys_exit);
 MODULE_AUTHOR("Intel Corporation <linux-wimax@intel.com>");
 MODULE_DESCRIPTION("Linux WiMAX stack");
 MODULE_LICENSE("GPL");
-
-- 
cgit v1.2.3


From 1cb1d977b41ad9fbcbd57ba24b203d6cb2f79952 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:03 -0700
Subject: rds: remove trailing whitespace and blank lines

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/Kconfig          | 1 -
 net/rds/Makefile         | 1 -
 net/rds/ib.c             | 1 -
 net/rds/message.c        | 1 -
 net/rds/rdma_transport.c | 1 -
 net/rds/tcp.c            | 1 -
 net/rds/transport.c      | 1 -
 7 files changed, 7 deletions(-)

diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index bffde4b46c5d..41f75563b54b 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -24,4 +24,3 @@ config RDS_DEBUG
         bool "RDS debugging messages"
 	depends on RDS
         default n
-
diff --git a/net/rds/Makefile b/net/rds/Makefile
index b5d568bd479c..e647f9de104a 100644
--- a/net/rds/Makefile
+++ b/net/rds/Makefile
@@ -15,4 +15,3 @@ rds_tcp-y :=		tcp.o tcp_connect.o tcp_listen.o tcp_recv.o \
 			tcp_send.o tcp_stats.o
 
 ccflags-$(CONFIG_RDS_DEBUG)	:=	-DRDS_DEBUG
-
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 63d95ea7cdff..a4245c42d43b 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -568,4 +568,3 @@ out:
 }
 
 MODULE_LICENSE("GPL");
-
diff --git a/net/rds/message.c b/net/rds/message.c
index a35f76971984..4b00b1152a5f 100644
--- a/net/rds/message.c
+++ b/net/rds/message.c
@@ -514,4 +514,3 @@ void rds_message_unmapped(struct rds_message *rm)
 	wake_up_interruptible(&rm->m_flush_wait);
 }
 EXPORT_SYMBOL_GPL(rds_message_unmapped);
-
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index bd67e55354f4..ad78929036ef 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -281,4 +281,3 @@ module_exit(rds_rdma_exit);
 MODULE_AUTHOR("Oracle Corporation <rds-devel@oss.oracle.com>");
 MODULE_DESCRIPTION("RDS: IB transport");
 MODULE_LICENSE("Dual BSD/GPL");
-
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 7028d6e51947..f23925af0b8d 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -717,4 +717,3 @@ module_init(rds_tcp_init);
 MODULE_AUTHOR("Oracle Corporation <rds-devel@oss.oracle.com>");
 MODULE_DESCRIPTION("RDS: TCP transport");
 MODULE_LICENSE("Dual BSD/GPL");
-
diff --git a/net/rds/transport.c b/net/rds/transport.c
index c9788dbce441..46f709a4b577 100644
--- a/net/rds/transport.c
+++ b/net/rds/transport.c
@@ -159,4 +159,3 @@ unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
 
 	return total;
 }
-
-- 
cgit v1.2.3


From a87e87dbf3926ab43b862cd90ec122ebf7d5aad3 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:04 -0700
Subject: llc: fix whitespace issues

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/Kconfig  | 2 +-
 net/llc/Makefile | 2 +-
 net/llc/llc_if.c | 1 -
 3 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/llc/Kconfig b/net/llc/Kconfig
index b91c65108162..176a6c1521a5 100644
--- a/net/llc/Kconfig
+++ b/net/llc/Kconfig
@@ -6,5 +6,5 @@ config LLC2
 	tristate "ANSI/IEEE 802.2 LLC type 2 Support"
 	select LLC
 	help
-	  This is a Logical Link Layer type 2, connection oriented support. 
+	  This is a Logical Link Layer type 2, connection oriented support.
 	  Select this if you want to have support for PF_LLC sockets.
diff --git a/net/llc/Makefile b/net/llc/Makefile
index 4e260cff3c5d..5e0ef436daae 100644
--- a/net/llc/Makefile
+++ b/net/llc/Makefile
@@ -4,7 +4,7 @@
 # Copyright (c) 1997 by Procom Technology,Inc.
 #		2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 #
-# This program can be redistributed or modified under the terms of the 
+# This program can be redistributed or modified under the terms of the
 # GNU General Public License as published by the Free Software Foundation.
 # This program is distributed without any warranty or implied warranty
 # of merchantability or fitness for a particular purpose.
diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c
index 6daf391b3e84..8db03c2d5440 100644
--- a/net/llc/llc_if.c
+++ b/net/llc/llc_if.c
@@ -151,4 +151,3 @@ out:
 	sock_put(sk);
 	return rc;
 }
-
-- 
cgit v1.2.3


From 04c6a3a40a22cff4e25d36eeda0ad590717022f0 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:05 -0700
Subject: mpls: remove trailing whitepace

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/mpls/mpls_iptunnel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c
index 6e558a419f60..94f53a9b7d1a 100644
--- a/net/mpls/mpls_iptunnel.c
+++ b/net/mpls/mpls_iptunnel.c
@@ -224,7 +224,7 @@ static int mpls_fill_encap_info(struct sk_buff *skb,
 				struct lwtunnel_state *lwtstate)
 {
 	struct mpls_iptunnel_encap *tun_encap_info;
-	
+
 	tun_encap_info = mpls_lwtunnel_encap(lwtstate);
 
 	if (nla_put_labels(skb, MPLS_IPTUNNEL_DST, tun_encap_info->labels,
-- 
cgit v1.2.3


From 2e13b580691cf1a3c4bafd723453dbbd7236a428 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:06 -0700
Subject: xfrm: remove blank lines at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/xfrm/Kconfig     | 1 -
 net/xfrm/xfrm_user.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/net/xfrm/Kconfig b/net/xfrm/Kconfig
index 286ed25c1a69..eab952cca7d0 100644
--- a/net/xfrm/Kconfig
+++ b/net/xfrm/Kconfig
@@ -87,4 +87,3 @@ config NET_KEY_MIGRATE
 	  <draft-sugimoto-mip6-pfkey-migrate>.
 
 	  If unsure, say N.
-
diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 080035f056d9..09cceab450b8 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -3280,4 +3280,3 @@ module_init(xfrm_user_init);
 module_exit(xfrm_user_exit);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_XFRM);
-
-- 
cgit v1.2.3


From aa46225235efc687d971351a309b734549ca5718 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:08 -0700
Subject: sctp: whitespace fixes

Remove blank line at EOF and trailing whitespace.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sctp/Kconfig         | 4 ++--
 net/sctp/sm_sideeffect.c | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sctp/Kconfig b/net/sctp/Kconfig
index c740b189d4ba..950ecf6e7439 100644
--- a/net/sctp/Kconfig
+++ b/net/sctp/Kconfig
@@ -41,8 +41,8 @@ config SCTP_DBG_OBJCNT
 	bool "SCTP: Debug object counts"
 	depends on PROC_FS
 	help
-	  If you say Y, this will enable debugging support for counting the 
-	  type of objects that are currently allocated.  This is useful for 
+	  If you say Y, this will enable debugging support for counting the
+	  type of objects that are currently allocated.  This is useful for
 	  identifying memory leaks. This debug information can be viewed by
 	  'cat /proc/net/sctp/sctp_dbg_objcnt'
 
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 298112ca8c06..85d393090238 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1827,4 +1827,3 @@ nomem:
 	error = -ENOMEM;
 	goto out;
 }
-
-- 
cgit v1.2.3


From ed976ea7307876a8557b4c069edf9314ed7459d0 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:09 -0700
Subject: ila: remove blank lines at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ila/ila_common.c | 1 -
 net/ipv6/ila/ila_xlat.c   | 1 -
 2 files changed, 2 deletions(-)

diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c
index 579310466eac..95e9146918cc 100644
--- a/net/ipv6/ila/ila_common.c
+++ b/net/ipv6/ila/ila_common.c
@@ -153,4 +153,3 @@ void ila_update_ipv6_locator(struct sk_buff *skb, struct ila_params *p,
 	/* Now change destination address */
 	iaddr->loc = p->locator;
 }
-
diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
index 51a15ce50a64..17c455ff69ff 100644
--- a/net/ipv6/ila/ila_xlat.c
+++ b/net/ipv6/ila/ila_xlat.c
@@ -663,4 +663,3 @@ static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila)
 
 	return 0;
 }
-
-- 
cgit v1.2.3


From 543de8881dfe759b304bbbcac8c360d1af52c6b3 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:11 -0700
Subject: atm: remove blank lines at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/atm/mpoa_proc.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/net/atm/mpoa_proc.c b/net/atm/mpoa_proc.c
index b93cc0f18292..46d6cd9a36ae 100644
--- a/net/atm/mpoa_proc.c
+++ b/net/atm/mpoa_proc.c
@@ -307,9 +307,3 @@ void mpc_proc_clean(void)
 }
 
 #endif /* CONFIG_PROC_FS */
-
-
-
-
-
-
-- 
cgit v1.2.3


From 9d82a1cdd391e84bfe5d70702ad4efe5be7d2236 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:12 -0700
Subject: ax25: remove blank line at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ax25/ax25_addr.c    | 1 -
 net/ax25/ax25_ds_in.c   | 1 -
 net/ax25/ax25_ds_subr.c | 1 -
 net/ax25/ax25_ip.c      | 1 -
 net/ax25/ax25_out.c     | 1 -
 5 files changed, 5 deletions(-)

diff --git a/net/ax25/ax25_addr.c b/net/ax25/ax25_addr.c
index ac2542b7be88..a14cfa736b63 100644
--- a/net/ax25/ax25_addr.c
+++ b/net/ax25/ax25_addr.c
@@ -304,4 +304,3 @@ void ax25_digi_invert(const ax25_digi *in, ax25_digi *out)
 		}
 	}
 }
-
diff --git a/net/ax25/ax25_ds_in.c b/net/ax25/ax25_ds_in.c
index 891596e74278..488fc2d7085a 100644
--- a/net/ax25/ax25_ds_in.c
+++ b/net/ax25/ax25_ds_in.c
@@ -299,4 +299,3 @@ int ax25_ds_frame_in(ax25_cb *ax25, struct sk_buff *skb, int type)
 
 	return queued;
 }
-
diff --git a/net/ax25/ax25_ds_subr.c b/net/ax25/ax25_ds_subr.c
index 28827e81ba2b..bc0329f43013 100644
--- a/net/ax25/ax25_ds_subr.c
+++ b/net/ax25/ax25_ds_subr.c
@@ -205,4 +205,3 @@ void ax25_dama_off(ax25_cb *ax25)
 	ax25->condition &= ~AX25_COND_DAMA_MODE;
 	ax25_dev_dama_off(ax25->ax25_dev);
 }
-
diff --git a/net/ax25/ax25_ip.c b/net/ax25/ax25_ip.c
index 183b1c583d56..70417e9b932d 100644
--- a/net/ax25/ax25_ip.c
+++ b/net/ax25/ax25_ip.c
@@ -249,4 +249,3 @@ const struct header_ops ax25_header_ops = {
 
 EXPORT_SYMBOL(ax25_header_ops);
 EXPORT_SYMBOL(ax25_ip_xmit);
-
diff --git a/net/ax25/ax25_out.c b/net/ax25/ax25_out.c
index b11a5f466fcc..3e5afc8dc93e 100644
--- a/net/ax25/ax25_out.c
+++ b/net/ax25/ax25_out.c
@@ -394,4 +394,3 @@ int ax25_check_iframes_acked(ax25_cb *ax25, unsigned short nr)
 	}
 	return 0;
 }
-
-- 
cgit v1.2.3


From 27782f403fbfe531442b80f59e7e42ccbe00eb9c Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:13 -0700
Subject: x25: remove blank lines at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/x25/Kconfig    | 2 --
 net/x25/x25_subr.c | 1 -
 2 files changed, 3 deletions(-)

diff --git a/net/x25/Kconfig b/net/x25/Kconfig
index e2fa133f9fba..59fcb41fc5e6 100644
--- a/net/x25/Kconfig
+++ b/net/x25/Kconfig
@@ -31,5 +31,3 @@ config X25
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called x25. If unsure, say N.
-
-
diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c
index 9c214ec681ac..743103786652 100644
--- a/net/x25/x25_subr.c
+++ b/net/x25/x25_subr.c
@@ -381,4 +381,3 @@ void x25_check_rbuf(struct sock *sk)
 		x25_stop_timer(sk);
 	}
 }
-
-- 
cgit v1.2.3


From 19c198d9c130d9a6f1427a2e50f1ed1779202f73 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:14 -0700
Subject: decnet: whitespace fixes

Remove trailing whitespace and extra lines at EOF

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/Kconfig              | 1 -
 net/decnet/Makefile             | 1 -
 net/decnet/TODO                 | 5 ++---
 net/decnet/dn_fib.c             | 2 --
 net/decnet/dn_nsp_in.c          | 1 -
 net/decnet/dn_nsp_out.c         | 1 -
 net/decnet/dn_route.c           | 1 -
 net/decnet/dn_rules.c           | 2 --
 net/decnet/netfilter/Makefile   | 1 -
 net/decnet/netfilter/dn_rtmsg.c | 1 -
 10 files changed, 2 insertions(+), 14 deletions(-)

diff --git a/net/decnet/Kconfig b/net/decnet/Kconfig
index f3393e154f0f..dcc74956badd 100644
--- a/net/decnet/Kconfig
+++ b/net/decnet/Kconfig
@@ -40,4 +40,3 @@ config DECNET_ROUTER
 	  to work.
 
 	  See <file:Documentation/networking/decnet.txt> for more information.
-
diff --git a/net/decnet/Makefile b/net/decnet/Makefile
index 9e38122d942b..07b38e441b2d 100644
--- a/net/decnet/Makefile
+++ b/net/decnet/Makefile
@@ -8,4 +8,3 @@ decnet-$(CONFIG_DECNET_ROUTER) += dn_fib.o dn_rules.o dn_table.o
 decnet-y += sysctl_net_decnet.o
 
 obj-$(CONFIG_NETFILTER) += netfilter/
-
diff --git a/net/decnet/TODO b/net/decnet/TODO
index ebb5ac69d128..358e9eb49016 100644
--- a/net/decnet/TODO
+++ b/net/decnet/TODO
@@ -16,14 +16,14 @@ Steve's quick list of things that need finishing off:
 
  o Verify errors etc. against POSIX 1003.1g (draft)
 
- o Using send/recvmsg() to get at connect/disconnect data (POSIX 1003.1g) 
+ o Using send/recvmsg() to get at connect/disconnect data (POSIX 1003.1g)
    [maybe this should be done at socket level... the control data in the
     send/recvmsg() calls should simply be a vector of set/getsockopt()
     calls]
 
  o check MSG_CTRUNC is set where it should be.
 
- o Find all the commonality between DECnet and IPv4 routing code and extract 
+ o Find all the commonality between DECnet and IPv4 routing code and extract
    it into a small library of routines. [probably a project for 2.7.xx]
 
  o Add perfect socket hashing - an idea suggested by Paul Koning. Currently
@@ -38,4 +38,3 @@ Steve's quick list of things that need finishing off:
  o DECnet sendpages() function
 
  o AIO for DECnet
-
diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c
index fce94cbd4378..f78fe58eafc8 100644
--- a/net/decnet/dn_fib.c
+++ b/net/decnet/dn_fib.c
@@ -797,5 +797,3 @@ void __init dn_fib_init(void)
 	rtnl_register_module(THIS_MODULE, PF_DECnet, RTM_DELROUTE,
 			     dn_fib_rtm_delroute, NULL, 0);
 }
-
-
diff --git a/net/decnet/dn_nsp_in.c b/net/decnet/dn_nsp_in.c
index 34aba55ed573..2fb5e055ba25 100644
--- a/net/decnet/dn_nsp_in.c
+++ b/net/decnet/dn_nsp_in.c
@@ -912,4 +912,3 @@ free_out:
 
 	return NET_RX_SUCCESS;
 }
-
diff --git a/net/decnet/dn_nsp_out.c b/net/decnet/dn_nsp_out.c
index 56a52a004c56..a1779de6bd9c 100644
--- a/net/decnet/dn_nsp_out.c
+++ b/net/decnet/dn_nsp_out.c
@@ -701,4 +701,3 @@ void dn_nsp_send_conninit(struct sock *sk, unsigned char msgflg)
 
 	dn_nsp_send(skb);
 }
-
diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index e74765024d88..3107a2e24e6b 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -1925,4 +1925,3 @@ void __exit dn_route_cleanup(void)
 	remove_proc_entry("decnet_cache", init_net.proc_net);
 	dst_entries_destroy(&dn_dst_ops);
 }
-
diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c
index 72236695db3d..4a4e3c17740c 100644
--- a/net/decnet/dn_rules.c
+++ b/net/decnet/dn_rules.c
@@ -256,5 +256,3 @@ void __exit dn_fib_rules_cleanup(void)
 	rtnl_unlock();
 	rcu_barrier();
 }
-
-
diff --git a/net/decnet/netfilter/Makefile b/net/decnet/netfilter/Makefile
index 255c1ae9daeb..b579e52130aa 100644
--- a/net/decnet/netfilter/Makefile
+++ b/net/decnet/netfilter/Makefile
@@ -3,4 +3,3 @@
 #
 
 obj-$(CONFIG_DECNET_NF_GRABULATOR) += dn_rtmsg.o
-
diff --git a/net/decnet/netfilter/dn_rtmsg.c b/net/decnet/netfilter/dn_rtmsg.c
index ab395e55cd78..a4faacadd8a8 100644
--- a/net/decnet/netfilter/dn_rtmsg.c
+++ b/net/decnet/netfilter/dn_rtmsg.c
@@ -158,4 +158,3 @@ MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_DNRTMSG);
 
 module_init(dn_rtmsg_init);
 module_exit(dn_rtmsg_fini);
-
-- 
cgit v1.2.3


From a17922def7ca6dba9f40b09a8b36f9cbe3b8bbf3 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:16 -0700
Subject: bpfilter: remove trailing newline

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bpfilter/Kconfig       | 1 -
 net/ipv4/bpfilter/Makefile | 1 -
 2 files changed, 2 deletions(-)

diff --git a/net/bpfilter/Kconfig b/net/bpfilter/Kconfig
index 76deb6615883..e558b46596c4 100644
--- a/net/bpfilter/Kconfig
+++ b/net/bpfilter/Kconfig
@@ -13,4 +13,3 @@ config BPFILTER_UMH
 	help
 	  This builds bpfilter kernel module with embedded user mode helper
 endif
-
diff --git a/net/ipv4/bpfilter/Makefile b/net/ipv4/bpfilter/Makefile
index ce262d76cc48..e9e42f99725e 100644
--- a/net/ipv4/bpfilter/Makefile
+++ b/net/ipv4/bpfilter/Makefile
@@ -1,2 +1 @@
 obj-$(CONFIG_BPFILTER) += sockopt.o
-
-- 
cgit v1.2.3


From c2df5603678b5b0d47ca70469934d1c146b29d9b Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:17 -0700
Subject: l2tp: remove trailing newline

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 1ea285bad84b..c8fc0f7f0b4b 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1795,4 +1795,3 @@ MODULE_AUTHOR("James Chapman <jchapman@katalix.com>");
 MODULE_DESCRIPTION("L2TP core");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(L2TP_DRV_VERSION);
-
-- 
cgit v1.2.3


From e446a2760f1e265192accd7ddebd3ca5ff1d57bb Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Tue, 24 Jul 2018 12:29:18 -0700
Subject: net: remove blank lines at end of file

Several files have extra line at end of file.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/8021q/Makefile              | 1 -
 net/Kconfig                     | 2 +-
 net/core/neighbour.c            | 1 -
 net/dns_resolver/dns_key.c      | 1 -
 net/ieee802154/core.c           | 1 -
 net/ieee802154/nl_policy.c      | 1 -
 net/ipv4/Kconfig                | 4 ++--
 net/ipv4/Makefile               | 2 +-
 net/ipv6/Kconfig                | 2 +-
 net/iucv/af_iucv.c              | 1 -
 net/kcm/Kconfig                 | 1 -
 net/kcm/kcmsock.c               | 1 -
 net/mac80211/rc80211_minstrel.c | 1 -
 13 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/net/8021q/Makefile b/net/8021q/Makefile
index 9b703454b93e..e05d4d7aab35 100644
--- a/net/8021q/Makefile
+++ b/net/8021q/Makefile
@@ -9,4 +9,3 @@ obj-$(CONFIG_VLAN_8021Q)		+= 8021q.o
 8021q-$(CONFIG_VLAN_8021Q_GVRP)		+= vlan_gvrp.o
 8021q-$(CONFIG_VLAN_8021Q_MVRP)		+= vlan_mvrp.o
 8021q-$(CONFIG_PROC_FS)			+= vlanproc.o
-
diff --git a/net/Kconfig b/net/Kconfig
index f738a6f27665..228dfa382eec 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -12,7 +12,7 @@ menuconfig NET
 	  The reason is that some programs need kernel networking support even
 	  when running on a stand-alone machine that isn't connected to any
 	  other computer.
-	  
+
 	  If you are upgrading from an older kernel, you
 	  should consider updating your networking tools too because changes
 	  in the kernel and the tools often go hand in hand. The tools are
diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index cbe85d8d4cc2..aa19d86937af 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -3274,4 +3274,3 @@ static int __init neigh_init(void)
 }
 
 subsys_initcall(neigh_init);
-
diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c
index 0c9478b91fa5..7f4534828f6c 100644
--- a/net/dns_resolver/dns_key.c
+++ b/net/dns_resolver/dns_key.c
@@ -320,4 +320,3 @@ static void __exit exit_dns_resolver(void)
 module_init(init_dns_resolver)
 module_exit(exit_dns_resolver)
 MODULE_LICENSE("GPL");
-
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index cb7176cd4cd6..fe225d9a1877 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -400,4 +400,3 @@ module_exit(wpan_phy_class_exit);
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("IEEE 802.15.4 configuration interface");
 MODULE_AUTHOR("Dmitry Eremin-Solenikov");
-
diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c
index 35c432668454..78f6f1233194 100644
--- a/net/ieee802154/nl_policy.c
+++ b/net/ieee802154/nl_policy.c
@@ -75,4 +75,3 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = {
 	[IEEE802154_ATTR_LLSEC_DEV_OVERRIDE] = { .type = NLA_U8, },
 	[IEEE802154_ATTR_LLSEC_DEV_KEY_MODE] = { .type = NLA_U8, },
 };
-
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 80dad301361d..32cae39cdff6 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -430,7 +430,7 @@ config INET_DIAG
 	  Support for INET (TCP, DCCP, etc) socket monitoring interface used by
 	  native Linux tools such as ss. ss is included in iproute2, currently
 	  downloadable at:
-	  
+
 	    http://www.linuxfoundation.org/collaborate/workgroups/networking/iproute2
 
 	  If unsure, say Y.
@@ -600,7 +600,7 @@ config TCP_CONG_VENO
 	distinguishing to circumvent the difficult judgment of the packet loss
 	type. TCP Veno cuts down less congestion window in response to random
 	loss packets.
-	See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186> 
+	See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186>
 
 config TCP_CONG_YEAH
 	tristate "YeAH TCP"
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index eec9569ffa5c..7446b98661d8 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -43,7 +43,7 @@ obj-$(CONFIG_INET_XFRM_MODE_TRANSPORT) += xfrm4_mode_transport.o
 obj-$(CONFIG_INET_XFRM_MODE_TUNNEL) += xfrm4_mode_tunnel.o
 obj-$(CONFIG_IP_PNP) += ipconfig.o
 obj-$(CONFIG_NETFILTER)	+= netfilter.o netfilter/
-obj-$(CONFIG_INET_DIAG) += inet_diag.o 
+obj-$(CONFIG_INET_DIAG) += inet_diag.o
 obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o
 obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o
 obj-$(CONFIG_INET_RAW_DIAG) += raw_diag.o
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index b3885ca22d6f..613282c65a10 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -15,7 +15,7 @@ menuconfig IPV6
 	  Documentation/networking/ipv6.txt and read the HOWTO at
 	  <http://www.tldp.org/HOWTO/Linux+IPv6-HOWTO/>
 
-	  To compile this protocol support as a module, choose M here: the 
+	  To compile this protocol support as a module, choose M here: the
 	  module will be called ipv6.
 
 if IPV6
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 893a022f9620..8d1c43f8fed4 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -2515,4 +2515,3 @@ MODULE_DESCRIPTION("IUCV Sockets ver " VERSION);
 MODULE_VERSION(VERSION);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(PF_IUCV);
-
diff --git a/net/kcm/Kconfig b/net/kcm/Kconfig
index 87fca36e6c47..9ca83f2ade6f 100644
--- a/net/kcm/Kconfig
+++ b/net/kcm/Kconfig
@@ -8,4 +8,3 @@ config AF_KCM
 	  KCM (Kernel Connection Multiplexor) sockets provide a method
 	  for multiplexing messages of a message based application
 	  protocol over kernel connectons (e.g. TCP connections).
-
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index d3601d421571..571d824e4e24 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -2104,4 +2104,3 @@ module_exit(kcm_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_NETPROTO(PF_KCM);
-
diff --git a/net/mac80211/rc80211_minstrel.c b/net/mac80211/rc80211_minstrel.c
index 76048b53c5b2..07fb219327d6 100644
--- a/net/mac80211/rc80211_minstrel.c
+++ b/net/mac80211/rc80211_minstrel.c
@@ -751,4 +751,3 @@ rc80211_minstrel_exit(void)
 {
 	ieee80211_rate_control_unregister(&mac80211_minstrel);
 }
-
-- 
cgit v1.2.3


From 56ab8cdbc1438507d79085fcc7e511327d84aeb8 Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Thu, 17 May 2018 10:30:16 -0400
Subject: media: v4l: Add support for STD ioctls on subdev nodes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no way to control the standard of subdevices which are part of
a media device. The ioctls which exists all target video devices
explicitly and the idea is that the video device should talk to the
subdevice. For subdevices part of a media graph this is not possible and
the standard must be controlled on the subdev device directly.

Add four new ioctls to be able to directly interact with subdevices and
control the video standard; VIDIOC_SUBDEV_ENUMSTD, VIDIOC_SUBDEV_G_STD,
VIDIOC_SUBDEV_S_STD and VIDIOC_SUBDEV_QUERYSTD.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/vidioc-enumstd.rst  | 11 +++++++----
 Documentation/media/uapi/v4l/vidioc-g-std.rst    | 14 ++++++++++----
 Documentation/media/uapi/v4l/vidioc-querystd.rst | 11 +++++++----
 drivers/media/v4l2-core/v4l2-subdev.c            | 22 ++++++++++++++++++++++
 include/uapi/linux/v4l2-subdev.h                 |  4 ++++
 5 files changed, 50 insertions(+), 12 deletions(-)

diff --git a/Documentation/media/uapi/v4l/vidioc-enumstd.rst b/Documentation/media/uapi/v4l/vidioc-enumstd.rst
index b7fda29f46a1..2644a62acd4b 100644
--- a/Documentation/media/uapi/v4l/vidioc-enumstd.rst
+++ b/Documentation/media/uapi/v4l/vidioc-enumstd.rst
@@ -2,14 +2,14 @@
 
 .. _VIDIOC_ENUMSTD:
 
-********************
-ioctl VIDIOC_ENUMSTD
-********************
+*******************************************
+ioctl VIDIOC_ENUMSTD, VIDIOC_SUBDEV_ENUMSTD
+*******************************************
 
 Name
 ====
 
-VIDIOC_ENUMSTD - Enumerate supported video standards
+VIDIOC_ENUMSTD - VIDIOC_SUBDEV_ENUMSTD - Enumerate supported video standards
 
 
 Synopsis
@@ -18,6 +18,9 @@ Synopsis
 .. c:function:: int ioctl( int fd, VIDIOC_ENUMSTD, struct v4l2_standard *argp )
     :name: VIDIOC_ENUMSTD
 
+.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_ENUMSTD, struct v4l2_standard *argp )
+    :name: VIDIOC_SUBDEV_ENUMSTD
+
 
 Arguments
 =========
diff --git a/Documentation/media/uapi/v4l/vidioc-g-std.rst b/Documentation/media/uapi/v4l/vidioc-g-std.rst
index 90791ab51a53..8d94f0404df2 100644
--- a/Documentation/media/uapi/v4l/vidioc-g-std.rst
+++ b/Documentation/media/uapi/v4l/vidioc-g-std.rst
@@ -2,14 +2,14 @@
 
 .. _VIDIOC_G_STD:
 
-********************************
-ioctl VIDIOC_G_STD, VIDIOC_S_STD
-********************************
+**************************************************************************
+ioctl VIDIOC_G_STD, VIDIOC_S_STD, VIDIOC_SUBDEV_G_STD, VIDIOC_SUBDEV_S_STD
+**************************************************************************
 
 Name
 ====
 
-VIDIOC_G_STD - VIDIOC_S_STD - Query or select the video standard of the current input
+VIDIOC_G_STD - VIDIOC_S_STD - VIDIOC_SUBDEV_G_STD - VIDIOC_SUBDEV_S_STD - Query or select the video standard of the current input
 
 
 Synopsis
@@ -21,6 +21,12 @@ Synopsis
 .. c:function:: int ioctl( int fd, VIDIOC_S_STD, const v4l2_std_id *argp )
     :name: VIDIOC_S_STD
 
+.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_G_STD, v4l2_std_id *argp )
+    :name: VIDIOC_SUBDEV_G_STD
+
+.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_S_STD, const v4l2_std_id *argp )
+    :name: VIDIOC_SUBDEV_S_STD
+
 
 Arguments
 =========
diff --git a/Documentation/media/uapi/v4l/vidioc-querystd.rst b/Documentation/media/uapi/v4l/vidioc-querystd.rst
index cf40bca19b9f..a8385cc74818 100644
--- a/Documentation/media/uapi/v4l/vidioc-querystd.rst
+++ b/Documentation/media/uapi/v4l/vidioc-querystd.rst
@@ -2,14 +2,14 @@
 
 .. _VIDIOC_QUERYSTD:
 
-*********************
-ioctl VIDIOC_QUERYSTD
-*********************
+*********************************************
+ioctl VIDIOC_QUERYSTD, VIDIOC_SUBDEV_QUERYSTD
+*********************************************
 
 Name
 ====
 
-VIDIOC_QUERYSTD - Sense the video standard received by the current input
+VIDIOC_QUERYSTD - VIDIOC_SUBDEV_QUERYSTD - Sense the video standard received by the current input
 
 
 Synopsis
@@ -18,6 +18,9 @@ Synopsis
 .. c:function:: int ioctl( int fd, VIDIOC_QUERYSTD, v4l2_std_id *argp )
     :name: VIDIOC_QUERYSTD
 
+.. c:function:: int ioctl( int fd, VIDIOC_SUBDEV_QUERYSTD, v4l2_std_id *argp )
+    :name: VIDIOC_SUBDEV_QUERYSTD
+
 
 Arguments
 =========
diff --git a/drivers/media/v4l2-core/v4l2-subdev.c b/drivers/media/v4l2-core/v4l2-subdev.c
index 6a7f7f75dfd7..2b63fa6b6fc9 100644
--- a/drivers/media/v4l2-core/v4l2-subdev.c
+++ b/drivers/media/v4l2-core/v4l2-subdev.c
@@ -494,6 +494,28 @@ static long subdev_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 
 	case VIDIOC_SUBDEV_S_DV_TIMINGS:
 		return v4l2_subdev_call(sd, video, s_dv_timings, arg);
+
+	case VIDIOC_SUBDEV_G_STD:
+		return v4l2_subdev_call(sd, video, g_std, arg);
+
+	case VIDIOC_SUBDEV_S_STD: {
+		v4l2_std_id *std = arg;
+
+		return v4l2_subdev_call(sd, video, s_std, *std);
+	}
+
+	case VIDIOC_SUBDEV_ENUMSTD: {
+		struct v4l2_standard *p = arg;
+		v4l2_std_id id;
+
+		if (v4l2_subdev_call(sd, video, g_tvnorms, &id))
+			return -EINVAL;
+
+		return v4l_video_std_enumstd(p, id);
+	}
+
+	case VIDIOC_SUBDEV_QUERYSTD:
+		return v4l2_subdev_call(sd, video, querystd, arg);
 #endif
 	default:
 		return v4l2_subdev_call(sd, core, ioctl, cmd, arg);
diff --git a/include/uapi/linux/v4l2-subdev.h b/include/uapi/linux/v4l2-subdev.h
index c95a53e6743c..03970ce30741 100644
--- a/include/uapi/linux/v4l2-subdev.h
+++ b/include/uapi/linux/v4l2-subdev.h
@@ -170,8 +170,12 @@ struct v4l2_subdev_selection {
 #define VIDIOC_SUBDEV_G_SELECTION		_IOWR('V', 61, struct v4l2_subdev_selection)
 #define VIDIOC_SUBDEV_S_SELECTION		_IOWR('V', 62, struct v4l2_subdev_selection)
 /* The following ioctls are identical to the ioctls in videodev2.h */
+#define VIDIOC_SUBDEV_G_STD			_IOR('V', 23, v4l2_std_id)
+#define VIDIOC_SUBDEV_S_STD			_IOW('V', 24, v4l2_std_id)
+#define VIDIOC_SUBDEV_ENUMSTD			_IOWR('V', 25, struct v4l2_standard)
 #define VIDIOC_SUBDEV_G_EDID			_IOWR('V', 40, struct v4l2_edid)
 #define VIDIOC_SUBDEV_S_EDID			_IOWR('V', 41, struct v4l2_edid)
+#define VIDIOC_SUBDEV_QUERYSTD			_IOR('V', 63, v4l2_std_id)
 #define VIDIOC_SUBDEV_S_DV_TIMINGS		_IOWR('V', 87, struct v4l2_dv_timings)
 #define VIDIOC_SUBDEV_G_DV_TIMINGS		_IOWR('V', 88, struct v4l2_dv_timings)
 #define VIDIOC_SUBDEV_ENUM_DV_TIMINGS		_IOWR('V', 98, struct v4l2_enum_dv_timings)
-- 
cgit v1.2.3


From efe1958ec41baba26e47a271b992b2bb524af61e Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 24 May 2018 10:50:44 -0400
Subject: media: video-mux: fix compliance failures

Limit frame sizes to the [1, 65536] interval, media bus formats to
the available list of formats, and initialize pad and try formats.

Reported-by: Rui Miguel Silva <rui.silva@linaro.org>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Tested-by: Rui Miguel Silva <rui.silva@linaro.org>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/video-mux.c | 119 +++++++++++++++++++++++++++++++++++--
 1 file changed, 115 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/video-mux.c b/drivers/media/platform/video-mux.c
index 1fb887293337..c01e1592ad0a 100644
--- a/drivers/media/platform/video-mux.c
+++ b/drivers/media/platform/video-mux.c
@@ -34,6 +34,13 @@ struct video_mux {
 	int active;
 };
 
+static const struct v4l2_mbus_framefmt video_mux_format_mbus_default = {
+	.width = 1,
+	.height = 1,
+	.code = MEDIA_BUS_FMT_Y8_1X8,
+	.field = V4L2_FIELD_NONE,
+};
+
 static inline struct video_mux *v4l2_subdev_to_video_mux(struct v4l2_subdev *sd)
 {
 	return container_of(sd, struct video_mux, subdev);
@@ -180,6 +187,88 @@ static int video_mux_set_format(struct v4l2_subdev *sd,
 	if (!source_mbusformat)
 		return -EINVAL;
 
+	/* No size limitations except V4L2 compliance requirements */
+	v4l_bound_align_image(&sdformat->format.width, 1, 65536, 0,
+			      &sdformat->format.height, 1, 65536, 0, 0);
+
+	/* All formats except LVDS and vendor specific formats are acceptable */
+	switch (sdformat->format.code) {
+	case MEDIA_BUS_FMT_RGB444_1X12:
+	case MEDIA_BUS_FMT_RGB444_2X8_PADHI_BE:
+	case MEDIA_BUS_FMT_RGB444_2X8_PADHI_LE:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_BE:
+	case MEDIA_BUS_FMT_RGB555_2X8_PADHI_LE:
+	case MEDIA_BUS_FMT_RGB565_1X16:
+	case MEDIA_BUS_FMT_BGR565_2X8_BE:
+	case MEDIA_BUS_FMT_BGR565_2X8_LE:
+	case MEDIA_BUS_FMT_RGB565_2X8_BE:
+	case MEDIA_BUS_FMT_RGB565_2X8_LE:
+	case MEDIA_BUS_FMT_RGB666_1X18:
+	case MEDIA_BUS_FMT_RBG888_1X24:
+	case MEDIA_BUS_FMT_RGB666_1X24_CPADHI:
+	case MEDIA_BUS_FMT_BGR888_1X24:
+	case MEDIA_BUS_FMT_GBR888_1X24:
+	case MEDIA_BUS_FMT_RGB888_1X24:
+	case MEDIA_BUS_FMT_RGB888_2X12_BE:
+	case MEDIA_BUS_FMT_RGB888_2X12_LE:
+	case MEDIA_BUS_FMT_ARGB8888_1X32:
+	case MEDIA_BUS_FMT_RGB888_1X32_PADHI:
+	case MEDIA_BUS_FMT_RGB101010_1X30:
+	case MEDIA_BUS_FMT_RGB121212_1X36:
+	case MEDIA_BUS_FMT_RGB161616_1X48:
+	case MEDIA_BUS_FMT_Y8_1X8:
+	case MEDIA_BUS_FMT_UV8_1X8:
+	case MEDIA_BUS_FMT_UYVY8_1_5X8:
+	case MEDIA_BUS_FMT_VYUY8_1_5X8:
+	case MEDIA_BUS_FMT_YUYV8_1_5X8:
+	case MEDIA_BUS_FMT_YVYU8_1_5X8:
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+	case MEDIA_BUS_FMT_Y10_1X10:
+	case MEDIA_BUS_FMT_UYVY10_2X10:
+	case MEDIA_BUS_FMT_VYUY10_2X10:
+	case MEDIA_BUS_FMT_YUYV10_2X10:
+	case MEDIA_BUS_FMT_YVYU10_2X10:
+	case MEDIA_BUS_FMT_Y12_1X12:
+	case MEDIA_BUS_FMT_UYVY12_2X12:
+	case MEDIA_BUS_FMT_VYUY12_2X12:
+	case MEDIA_BUS_FMT_YUYV12_2X12:
+	case MEDIA_BUS_FMT_YVYU12_2X12:
+	case MEDIA_BUS_FMT_UYVY8_1X16:
+	case MEDIA_BUS_FMT_VYUY8_1X16:
+	case MEDIA_BUS_FMT_YUYV8_1X16:
+	case MEDIA_BUS_FMT_YVYU8_1X16:
+	case MEDIA_BUS_FMT_YDYUYDYV8_1X16:
+	case MEDIA_BUS_FMT_UYVY10_1X20:
+	case MEDIA_BUS_FMT_VYUY10_1X20:
+	case MEDIA_BUS_FMT_YUYV10_1X20:
+	case MEDIA_BUS_FMT_YVYU10_1X20:
+	case MEDIA_BUS_FMT_VUY8_1X24:
+	case MEDIA_BUS_FMT_YUV8_1X24:
+	case MEDIA_BUS_FMT_UYYVYY8_0_5X24:
+	case MEDIA_BUS_FMT_UYVY12_1X24:
+	case MEDIA_BUS_FMT_VYUY12_1X24:
+	case MEDIA_BUS_FMT_YUYV12_1X24:
+	case MEDIA_BUS_FMT_YVYU12_1X24:
+	case MEDIA_BUS_FMT_YUV10_1X30:
+	case MEDIA_BUS_FMT_UYYVYY10_0_5X30:
+	case MEDIA_BUS_FMT_AYUV8_1X32:
+	case MEDIA_BUS_FMT_UYYVYY12_0_5X36:
+	case MEDIA_BUS_FMT_YUV12_1X36:
+	case MEDIA_BUS_FMT_YUV16_1X48:
+	case MEDIA_BUS_FMT_UYYVYY16_0_5X48:
+	case MEDIA_BUS_FMT_JPEG_1X8:
+	case MEDIA_BUS_FMT_AHSV8888_1X32:
+		break;
+	default:
+		sdformat->format.code = MEDIA_BUS_FMT_Y8_1X8;
+		break;
+	}
+	if (sdformat->format.field == V4L2_FIELD_ANY)
+		sdformat->format.field = V4L2_FIELD_NONE;
+
 	mutex_lock(&vmux->lock);
 
 	/* Source pad mirrors active sink pad, no limitations on sink pads */
@@ -197,7 +286,27 @@ static int video_mux_set_format(struct v4l2_subdev *sd,
 	return 0;
 }
 
+static int video_mux_init_cfg(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg)
+{
+	struct video_mux *vmux = v4l2_subdev_to_video_mux(sd);
+	struct v4l2_mbus_framefmt *mbusformat;
+	unsigned int i;
+
+	mutex_lock(&vmux->lock);
+
+	for (i = 0; i < sd->entity.num_pads; i++) {
+		mbusformat = v4l2_subdev_get_try_format(sd, cfg, i);
+		*mbusformat = video_mux_format_mbus_default;
+	}
+
+	mutex_unlock(&vmux->lock);
+
+	return 0;
+}
+
 static const struct v4l2_subdev_pad_ops video_mux_pad_ops = {
+	.init_cfg = video_mux_init_cfg,
 	.get_fmt = video_mux_get_format,
 	.set_fmt = video_mux_set_format,
 };
@@ -214,8 +323,8 @@ static int video_mux_probe(struct platform_device *pdev)
 	struct device_node *ep;
 	struct video_mux *vmux;
 	unsigned int num_pads = 0;
+	unsigned int i;
 	int ret;
-	int i;
 
 	vmux = devm_kzalloc(dev, sizeof(*vmux), GFP_KERNEL);
 	if (!vmux)
@@ -260,9 +369,11 @@ static int video_mux_probe(struct platform_device *pdev)
 					 sizeof(*vmux->format_mbus),
 					 GFP_KERNEL);
 
-	for (i = 0; i < num_pads - 1; i++)
-		vmux->pads[i].flags = MEDIA_PAD_FL_SINK;
-	vmux->pads[num_pads - 1].flags = MEDIA_PAD_FL_SOURCE;
+	for (i = 0; i < num_pads; i++) {
+		vmux->pads[i].flags = (i < num_pads - 1) ? MEDIA_PAD_FL_SINK
+							 : MEDIA_PAD_FL_SOURCE;
+		vmux->format_mbus[i] = video_mux_format_mbus_default;
+	}
 
 	vmux->subdev.entity.function = MEDIA_ENT_F_VID_MUX;
 	ret = media_entity_pads_init(&vmux->subdev.entity, num_pads,
-- 
cgit v1.2.3


From b8f8c8eb408b36ad55dd41a616b3f51998880fb6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 21 Jul 2018 15:48:47 +0200
Subject: net: phy: add GBit master / slave error detection

Certain PHY's have issues when operating in GBit slave mode and can
be forced to master mode. Examples are RTL8211C, also the Micrel PHY
driver has a DT setting to force master mode.
If two such chips are link partners the autonegotiation will fail.
Standard defines a self-clearing on read, latched-high bit to
indicate this error. Check this bit to inform the user.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_device.c | 8 ++++++++
 include/uapi/linux/mii.h     | 1 +
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b9f5f40a7ac1..db1172db1e7c 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1555,6 +1555,14 @@ int genphy_read_status(struct phy_device *phydev)
 			if (adv < 0)
 				return adv;
 
+			if (lpagb & LPA_1000MSFAIL) {
+				if (adv & CTL1000_ENABLE_MASTER)
+					phydev_err(phydev, "Master/Slave resolution failed, maybe conflicting manual settings?\n");
+				else
+					phydev_err(phydev, "Master/Slave resolution failed\n");
+				return -ENOLINK;
+			}
+
 			phydev->lp_advertising =
 				mii_stat1000_to_ethtool_lpa_t(lpagb);
 			common_adv_gb = lpagb & adv << 2;
diff --git a/include/uapi/linux/mii.h b/include/uapi/linux/mii.h
index b5c2fdcf23fd..a506216591d6 100644
--- a/include/uapi/linux/mii.h
+++ b/include/uapi/linux/mii.h
@@ -136,6 +136,7 @@
 #define CTL1000_ENABLE_MASTER	0x1000
 
 /* 1000BASE-T Status register */
+#define LPA_1000MSFAIL		0x8000	/* Master/Slave resolution failure */
 #define LPA_1000LOCALRXOK	0x2000	/* Link partner local receiver status */
 #define LPA_1000REMRXOK		0x1000	/* Link partner remote receiver status */
 #define LPA_1000FULL		0x0800	/* Link partner 1000BASE-T full duplex */
-- 
cgit v1.2.3


From 7a0167fb68e3c9ec2386f8abb326a4643ee8ef42 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Mon, 18 Jun 2018 00:38:50 -0400
Subject: media: rcar_jpu: Remove unrequired wait in .job_abort

As per the documentation, job_abort is not required
to wait until the current job finishes. It is redundant
to do so, as the core will perform the wait operation.

Remove the wait infrastructure completely.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Acked-by: Mikhail Ulyanov <mikhail.ulyanov@cogentembedded.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar_jpu.c | 11 -----------
 1 file changed, 11 deletions(-)

diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index 690631747c5e..90d40b2d6259 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -198,7 +198,6 @@
  * @vfd_decoder: video device node for decoder mem2mem mode
  * @m2m_dev: v4l2 mem2mem device data
  * @curr: pointer to current context
- * @irq_queue:	interrupt handler waitqueue
  * @regs: JPEG IP registers mapping
  * @irq: JPEG IP irq
  * @clk: JPEG IP clock
@@ -213,7 +212,6 @@ struct jpu {
 	struct video_device	vfd_decoder;
 	struct v4l2_m2m_dev	*m2m_dev;
 	struct jpu_ctx		*curr;
-	wait_queue_head_t	irq_queue;
 
 	void __iomem		*regs;
 	unsigned int		irq;
@@ -1496,11 +1494,6 @@ static void jpu_device_run(void *priv)
 
 static void jpu_job_abort(void *priv)
 {
-	struct jpu_ctx *ctx = priv;
-
-	if (!wait_event_timeout(ctx->jpu->irq_queue, !ctx->jpu->curr,
-				msecs_to_jiffies(JPU_JOB_TIMEOUT)))
-		jpu_cleanup(ctx, true);
 }
 
 static const struct v4l2_m2m_ops jpu_m2m_ops = {
@@ -1586,9 +1579,6 @@ static irqreturn_t jpu_irq_handler(int irq, void *dev_id)
 
 	v4l2_m2m_job_finish(jpu->m2m_dev, curr_ctx->fh.m2m_ctx);
 
-	/* ...wakeup abort routine if needed */
-	wake_up(&jpu->irq_queue);
-
 	return IRQ_HANDLED;
 
 handled:
@@ -1622,7 +1612,6 @@ static int jpu_probe(struct platform_device *pdev)
 	if (!jpu)
 		return -ENOMEM;
 
-	init_waitqueue_head(&jpu->irq_queue);
 	mutex_init(&jpu->mutex);
 	spin_lock_init(&jpu->lock);
 	jpu->dev = &pdev->dev;
-- 
cgit v1.2.3


From 774f1c912776330ece84540fac370ec201c878b4 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Mon, 18 Jun 2018 00:38:51 -0400
Subject: media: s5p-g2d: Remove unrequired wait in .job_abort

As per the documentation, job_abort is not required
to wait until the current job finishes. It is redundant
to do so, as the core will perform the wait operation.

Remove the wait infrastructure completely.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/s5p-g2d/g2d.c | 11 -----------
 drivers/media/platform/s5p-g2d/g2d.h |  1 -
 2 files changed, 12 deletions(-)

diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index 6b1c23463009..ee7322b33666 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -485,15 +485,6 @@ static int vidioc_s_crop(struct file *file, void *prv, const struct v4l2_crop *c
 
 static void job_abort(void *prv)
 {
-	struct g2d_ctx *ctx = prv;
-	struct g2d_dev *dev = ctx->dev;
-
-	if (dev->curr == NULL) /* No job currently running */
-		return;
-
-	wait_event_timeout(dev->irq_queue,
-			   dev->curr == NULL,
-			   msecs_to_jiffies(G2D_TIMEOUT));
 }
 
 static void device_run(void *prv)
@@ -565,7 +556,6 @@ static irqreturn_t g2d_isr(int irq, void *prv)
 	v4l2_m2m_job_finish(dev->m2m_dev, ctx->fh.m2m_ctx);
 
 	dev->curr = NULL;
-	wake_up(&dev->irq_queue);
 	return IRQ_HANDLED;
 }
 
@@ -635,7 +625,6 @@ static int g2d_probe(struct platform_device *pdev)
 	spin_lock_init(&dev->ctrl_lock);
 	mutex_init(&dev->mutex);
 	atomic_set(&dev->num_inst, 0);
-	init_waitqueue_head(&dev->irq_queue);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 
diff --git a/drivers/media/platform/s5p-g2d/g2d.h b/drivers/media/platform/s5p-g2d/g2d.h
index dd812b557e87..9ffb458a1b93 100644
--- a/drivers/media/platform/s5p-g2d/g2d.h
+++ b/drivers/media/platform/s5p-g2d/g2d.h
@@ -31,7 +31,6 @@ struct g2d_dev {
 	struct g2d_ctx		*curr;
 	struct g2d_variant	*variant;
 	int irq;
-	wait_queue_head_t	irq_queue;
 };
 
 struct g2d_frame {
-- 
cgit v1.2.3


From aea5f654e6b78a0c976f7a25950155932c77a53f Mon Sep 17 00:00:00 2001
From: Nishanth Devarajan <ndev2021@gmail.com>
Date: Mon, 23 Jul 2018 19:37:41 +0530
Subject: net/sched: add skbprio scheduler

Skbprio (SKB Priority Queue) is a queueing discipline that prioritizes packets
according to their skb->priority field. Under congestion, already-enqueued lower
priority packets will be dropped to make space available for higher priority
packets. Skbprio was conceived as a solution for denial-of-service defenses that
need to route packets with different priorities as a means to overcome DoS
attacks.

v5
*Do not reference qdisc_dev(sch)->tx_queue_len for setting limit. Instead set
default sch->limit to 64.

v4
*Drop Documentation/networking/sch_skbprio.txt doc file to move it to tc man
page for Skbprio, in iproute2.

v3
*Drop max_limit parameter in struct skbprio_sched_data and instead use
sch->limit.

*Reference qdisc_dev(sch)->tx_queue_len only once, during initialisation for
qdisc (previously being referenced every time qdisc changes).

*Move qdisc's detailed description from in-code to Documentation/networking.

*When qdisc is saturated, enqueue incoming packet first before dequeueing
lowest priority packet in queue - improves usage of call stack registers.

*Introduce and use overlimit stat to keep track of number of dropped packets.

v2
*Use skb->priority field rather than DS field. Rename queueing discipline as
SKB Priority Queue (previously Gatekeeper Priority Queue).

*Queueing discipline is made classful to expose Skbprio's internal priority
queues.

Signed-off-by: Nishanth Devarajan <ndev2021@gmail.com>
Reviewed-by: Sachin Paryani <sachin.paryani@gmail.com>
Reviewed-by: Cody Doucette <doucette@bu.edu>
Reviewed-by: Michel Machado <michel@digirati.com.br>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_sched.h |  15 ++
 net/sched/Kconfig              |  13 ++
 net/sched/Makefile             |   1 +
 net/sched/sch_skbprio.c        | 320 +++++++++++++++++++++++++++++++++++++++++
 4 files changed, 349 insertions(+)
 create mode 100644 net/sched/sch_skbprio.c

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index d9cc9dc4f547..8975fd1a1421 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -124,6 +124,21 @@ struct tc_fifo_qopt {
 	__u32	limit;	/* Queue length: bytes for bfifo, packets for pfifo */
 };
 
+/* SKBPRIO section */
+
+/*
+ * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1).
+ * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able
+ * to map one to one the DS field of IPV4 and IPV6 headers.
+ * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY.
+ */
+
+#define SKBPRIO_MAX_PRIORITY 64
+
+struct tc_skbprio_qopt {
+	__u32	limit;		/* Queue length in packets. */
+};
+
 /* PRIO section */
 
 #define TCQ_PRIO_BANDS	16
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index bba71225adbd..e95741388311 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -251,6 +251,19 @@ config NET_SCH_MQPRIO
 
 	  If unsure, say N.
 
+config NET_SCH_SKBPRIO
+	tristate "SKB priority queue scheduler (SKBPRIO)"
+	help
+	  Say Y here if you want to use the SKB priority queue
+	  scheduler. This schedules packets according to skb->priority,
+	  which is useful for request packets in DoS mitigation systems such
+	  as Gatekeeper.
+
+	  To compile this driver as a module, choose M here: the module will
+	  be called sch_skbprio.
+
+	  If unsure, say N.
+
 config NET_SCH_CHOKE
 	tristate "CHOose and Keep responsive flow scheduler (CHOKE)"
 	help
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 910ec7463a36..f0403f49edcb 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -46,6 +46,7 @@ obj-$(CONFIG_NET_SCH_NETEM)	+= sch_netem.o
 obj-$(CONFIG_NET_SCH_DRR)	+= sch_drr.o
 obj-$(CONFIG_NET_SCH_PLUG)	+= sch_plug.o
 obj-$(CONFIG_NET_SCH_MQPRIO)	+= sch_mqprio.o
+obj-$(CONFIG_NET_SCH_SKBPRIO)	+= sch_skbprio.o
 obj-$(CONFIG_NET_SCH_CHOKE)	+= sch_choke.o
 obj-$(CONFIG_NET_SCH_QFQ)	+= sch_qfq.o
 obj-$(CONFIG_NET_SCH_CODEL)	+= sch_codel.o
diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c
new file mode 100644
index 000000000000..52c0b6d8f1d7
--- /dev/null
+++ b/net/sched/sch_skbprio.c
@@ -0,0 +1,320 @@
+/*
+ * net/sched/sch_skbprio.c  SKB Priority Queue.
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Nishanth Devarajan, <ndev2021@gmail.com>
+ *		Cody Doucette, <doucette@bu.edu>
+ *	        original idea by Michel Machado, Cody Doucette, and Qiaobin Fu
+ */
+
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <net/pkt_sched.h>
+#include <net/sch_generic.h>
+#include <net/inet_ecn.h>
+
+/*		SKB Priority Queue
+ *	=================================
+ *
+ * Skbprio (SKB Priority Queue) is a queueing discipline that prioritizes
+ * packets according to their skb->priority field. Under congestion,
+ * Skbprio drops already-enqueued lower priority packets to make space
+ * available for higher priority packets; it was conceived as a solution
+ * for denial-of-service defenses that need to route packets with different
+ * priorities as a mean to overcome DoS attacks.
+ */
+
+struct skbprio_sched_data {
+	/* Queue state. */
+	struct sk_buff_head qdiscs[SKBPRIO_MAX_PRIORITY];
+	struct gnet_stats_queue qstats[SKBPRIO_MAX_PRIORITY];
+	u16 highest_prio;
+	u16 lowest_prio;
+};
+
+static u16 calc_new_high_prio(const struct skbprio_sched_data *q)
+{
+	int prio;
+
+	for (prio = q->highest_prio - 1; prio >= q->lowest_prio; prio--) {
+		if (!skb_queue_empty(&q->qdiscs[prio]))
+			return prio;
+	}
+
+	/* SKB queue is empty, return 0 (default highest priority setting). */
+	return 0;
+}
+
+static u16 calc_new_low_prio(const struct skbprio_sched_data *q)
+{
+	int prio;
+
+	for (prio = q->lowest_prio + 1; prio <= q->highest_prio; prio++) {
+		if (!skb_queue_empty(&q->qdiscs[prio]))
+			return prio;
+	}
+
+	/* SKB queue is empty, return SKBPRIO_MAX_PRIORITY - 1
+	 * (default lowest priority setting).
+	 */
+	return SKBPRIO_MAX_PRIORITY - 1;
+}
+
+static int skbprio_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			  struct sk_buff **to_free)
+{
+	const unsigned int max_priority = SKBPRIO_MAX_PRIORITY - 1;
+	struct skbprio_sched_data *q = qdisc_priv(sch);
+	struct sk_buff_head *qdisc;
+	struct sk_buff_head *lp_qdisc;
+	struct sk_buff *to_drop;
+	u16 prio, lp;
+
+	/* Obtain the priority of @skb. */
+	prio = min(skb->priority, max_priority);
+
+	qdisc = &q->qdiscs[prio];
+	if (sch->q.qlen < sch->limit) {
+		__skb_queue_tail(qdisc, skb);
+		qdisc_qstats_backlog_inc(sch, skb);
+		q->qstats[prio].backlog += qdisc_pkt_len(skb);
+
+		/* Check to update highest and lowest priorities. */
+		if (prio > q->highest_prio)
+			q->highest_prio = prio;
+
+		if (prio < q->lowest_prio)
+			q->lowest_prio = prio;
+
+		sch->q.qlen++;
+		return NET_XMIT_SUCCESS;
+	}
+
+	/* If this packet has the lowest priority, drop it. */
+	lp = q->lowest_prio;
+	if (prio <= lp) {
+		q->qstats[prio].drops++;
+		q->qstats[prio].overlimits++;
+		return qdisc_drop(skb, sch, to_free);
+	}
+
+	__skb_queue_tail(qdisc, skb);
+	qdisc_qstats_backlog_inc(sch, skb);
+	q->qstats[prio].backlog += qdisc_pkt_len(skb);
+
+	/* Drop the packet at the tail of the lowest priority qdisc. */
+	lp_qdisc = &q->qdiscs[lp];
+	to_drop = __skb_dequeue_tail(lp_qdisc);
+	BUG_ON(!to_drop);
+	qdisc_qstats_backlog_dec(sch, to_drop);
+	qdisc_drop(to_drop, sch, to_free);
+
+	q->qstats[lp].backlog -= qdisc_pkt_len(to_drop);
+	q->qstats[lp].drops++;
+	q->qstats[lp].overlimits++;
+
+	/* Check to update highest and lowest priorities. */
+	if (skb_queue_empty(lp_qdisc)) {
+		if (q->lowest_prio == q->highest_prio) {
+			/* The incoming packet is the only packet in queue. */
+			BUG_ON(sch->q.qlen != 1);
+			q->lowest_prio = prio;
+			q->highest_prio = prio;
+		} else {
+			q->lowest_prio = calc_new_low_prio(q);
+		}
+	}
+
+	if (prio > q->highest_prio)
+		q->highest_prio = prio;
+
+	return NET_XMIT_CN;
+}
+
+static struct sk_buff *skbprio_dequeue(struct Qdisc *sch)
+{
+	struct skbprio_sched_data *q = qdisc_priv(sch);
+	struct sk_buff_head *hpq = &q->qdiscs[q->highest_prio];
+	struct sk_buff *skb = __skb_dequeue(hpq);
+
+	if (unlikely(!skb))
+		return NULL;
+
+	sch->q.qlen--;
+	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_bstats_update(sch, skb);
+
+	q->qstats[q->highest_prio].backlog -= qdisc_pkt_len(skb);
+
+	/* Update highest priority field. */
+	if (skb_queue_empty(hpq)) {
+		if (q->lowest_prio == q->highest_prio) {
+			BUG_ON(sch->q.qlen);
+			q->highest_prio = 0;
+			q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1;
+		} else {
+			q->highest_prio = calc_new_high_prio(q);
+		}
+	}
+	return skb;
+}
+
+static int skbprio_change(struct Qdisc *sch, struct nlattr *opt,
+			struct netlink_ext_ack *extack)
+{
+	struct tc_skbprio_qopt *ctl = nla_data(opt);
+
+	sch->limit = ctl->limit;
+	return 0;
+}
+
+static int skbprio_init(struct Qdisc *sch, struct nlattr *opt,
+			struct netlink_ext_ack *extack)
+{
+	struct skbprio_sched_data *q = qdisc_priv(sch);
+	int prio;
+
+	/* Initialise all queues, one for each possible priority. */
+	for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++)
+		__skb_queue_head_init(&q->qdiscs[prio]);
+
+	memset(&q->qstats, 0, sizeof(q->qstats));
+	q->highest_prio = 0;
+	q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1;
+	sch->limit = 64;
+	if (!opt)
+		return 0;
+
+	return skbprio_change(sch, opt, extack);
+}
+
+static int skbprio_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct tc_skbprio_qopt opt;
+
+	opt.limit = sch->limit;
+
+	if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt))
+		return -1;
+
+	return skb->len;
+}
+
+static void skbprio_reset(struct Qdisc *sch)
+{
+	struct skbprio_sched_data *q = qdisc_priv(sch);
+	int prio;
+
+	sch->qstats.backlog = 0;
+	sch->q.qlen = 0;
+
+	for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++)
+		__skb_queue_purge(&q->qdiscs[prio]);
+
+	memset(&q->qstats, 0, sizeof(q->qstats));
+	q->highest_prio = 0;
+	q->lowest_prio = SKBPRIO_MAX_PRIORITY - 1;
+}
+
+static void skbprio_destroy(struct Qdisc *sch)
+{
+	struct skbprio_sched_data *q = qdisc_priv(sch);
+	int prio;
+
+	for (prio = 0; prio < SKBPRIO_MAX_PRIORITY; prio++)
+		__skb_queue_purge(&q->qdiscs[prio]);
+}
+
+static struct Qdisc *skbprio_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	return NULL;
+}
+
+static unsigned long skbprio_find(struct Qdisc *sch, u32 classid)
+{
+	return 0;
+}
+
+static int skbprio_dump_class(struct Qdisc *sch, unsigned long cl,
+			     struct sk_buff *skb, struct tcmsg *tcm)
+{
+	tcm->tcm_handle |= TC_H_MIN(cl);
+	return 0;
+}
+
+static int skbprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
+				   struct gnet_dump *d)
+{
+	struct skbprio_sched_data *q = qdisc_priv(sch);
+	if (gnet_stats_copy_queue(d, NULL, &q->qstats[cl - 1],
+		q->qstats[cl - 1].qlen) < 0)
+		return -1;
+	return 0;
+}
+
+static void skbprio_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	unsigned int i;
+
+	if (arg->stop)
+		return;
+
+	for (i = 0; i < SKBPRIO_MAX_PRIORITY; i++) {
+		if (arg->count < arg->skip) {
+			arg->count++;
+			continue;
+		}
+		if (arg->fn(sch, i + 1, arg) < 0) {
+			arg->stop = 1;
+			break;
+		}
+		arg->count++;
+	}
+}
+
+static const struct Qdisc_class_ops skbprio_class_ops = {
+	.leaf		=	skbprio_leaf,
+	.find		=	skbprio_find,
+	.dump		=	skbprio_dump_class,
+	.dump_stats	=	skbprio_dump_class_stats,
+	.walk		=	skbprio_walk,
+};
+
+static struct Qdisc_ops skbprio_qdisc_ops __read_mostly = {
+	.cl_ops		=	&skbprio_class_ops,
+	.id		=	"skbprio",
+	.priv_size	=	sizeof(struct skbprio_sched_data),
+	.enqueue	=	skbprio_enqueue,
+	.dequeue	=	skbprio_dequeue,
+	.peek		=	qdisc_peek_dequeued,
+	.init		=	skbprio_init,
+	.reset		=	skbprio_reset,
+	.change		=	skbprio_change,
+	.dump		=	skbprio_dump,
+	.destroy	=	skbprio_destroy,
+	.owner		=	THIS_MODULE,
+};
+
+static int __init skbprio_module_init(void)
+{
+	return register_qdisc(&skbprio_qdisc_ops);
+}
+
+static void __exit skbprio_module_exit(void)
+{
+	unregister_qdisc(&skbprio_qdisc_ops);
+}
+
+module_init(skbprio_module_init)
+module_exit(skbprio_module_exit)
+
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 5525b8314389a0c558d15464e86f438974b94e32 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Mon, 18 Jun 2018 00:38:52 -0400
Subject: media: mem2mem: Make .job_abort optional

Implementing job_abort() does not make sense on some drivers.
This is not a problem, as the abort is not required to
wait for the job to finish. Quite the opposite, drivers
are encouraged not to wait.

Demote v4l2_m2m_ops.job_abort from required to optional, and
clean all drivers with dummy implementations.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c | 5 -----
 drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c    | 5 -----
 drivers/media/platform/rcar_jpu.c               | 5 -----
 drivers/media/platform/rockchip/rga/rga.c       | 6 ------
 drivers/media/platform/s5p-g2d/g2d.c            | 5 -----
 drivers/media/platform/s5p-jpeg/jpeg-core.c     | 7 -------
 drivers/media/v4l2-core/v4l2-mem2mem.c          | 6 +++---
 include/media/v4l2-mem2mem.h                    | 2 +-
 8 files changed, 4 insertions(+), 37 deletions(-)

diff --git a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c
index 328e8f650d9b..4f24da8afecc 100644
--- a/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c
+++ b/drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c
@@ -861,14 +861,9 @@ static int mtk_jpeg_job_ready(void *priv)
 	return (ctx->state == MTK_JPEG_RUNNING) ? 1 : 0;
 }
 
-static void mtk_jpeg_job_abort(void *priv)
-{
-}
-
 static const struct v4l2_m2m_ops mtk_jpeg_m2m_ops = {
 	.device_run = mtk_jpeg_device_run,
 	.job_ready  = mtk_jpeg_job_ready,
-	.job_abort  = mtk_jpeg_job_abort,
 };
 
 static int mtk_jpeg_queue_init(void *priv, struct vb2_queue *src_vq,
diff --git a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
index c2e2f5f1ebf1..ceffc31cc6eb 100644
--- a/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
+++ b/drivers/media/platform/mtk-mdp/mtk_mdp_m2m.c
@@ -441,10 +441,6 @@ static void mtk_mdp_m2m_stop_streaming(struct vb2_queue *q)
 	pm_runtime_put(&ctx->mdp_dev->pdev->dev);
 }
 
-static void mtk_mdp_m2m_job_abort(void *priv)
-{
-}
-
 /* The color format (num_planes) must be already configured. */
 static void mtk_mdp_prepare_addr(struct mtk_mdp_ctx *ctx,
 				 struct vb2_buffer *vb,
@@ -1215,7 +1211,6 @@ static const struct v4l2_file_operations mtk_mdp_m2m_fops = {
 
 static const struct v4l2_m2m_ops mtk_mdp_m2m_ops = {
 	.device_run	= mtk_mdp_m2m_device_run,
-	.job_abort	= mtk_mdp_m2m_job_abort,
 };
 
 int mtk_mdp_register_m2m_device(struct mtk_mdp_dev *mdp)
diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index 90d40b2d6259..a808258a4180 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -1492,13 +1492,8 @@ static void jpu_device_run(void *priv)
 	spin_unlock_irqrestore(&ctx->jpu->lock, flags);
 }
 
-static void jpu_job_abort(void *priv)
-{
-}
-
 static const struct v4l2_m2m_ops jpu_m2m_ops = {
 	.device_run	= jpu_device_run,
-	.job_abort	= jpu_job_abort,
 };
 
 /*
diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
index 8ace1873202a..69a2797d7bbe 100644
--- a/drivers/media/platform/rockchip/rga/rga.c
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -39,11 +39,6 @@
 static int debug;
 module_param(debug, int, 0644);
 
-static void job_abort(void *prv)
-{
-	/* Can't do anything rational here */
-}
-
 static void device_run(void *prv)
 {
 	struct rga_ctx *ctx = prv;
@@ -104,7 +99,6 @@ static irqreturn_t rga_isr(int irq, void *prv)
 
 static struct v4l2_m2m_ops rga_m2m_ops = {
 	.device_run = device_run,
-	.job_abort = job_abort,
 };
 
 static int
diff --git a/drivers/media/platform/s5p-g2d/g2d.c b/drivers/media/platform/s5p-g2d/g2d.c
index ee7322b33666..e901201b6fcc 100644
--- a/drivers/media/platform/s5p-g2d/g2d.c
+++ b/drivers/media/platform/s5p-g2d/g2d.c
@@ -483,10 +483,6 @@ static int vidioc_s_crop(struct file *file, void *prv, const struct v4l2_crop *c
 	return 0;
 }
 
-static void job_abort(void *prv)
-{
-}
-
 static void device_run(void *prv)
 {
 	struct g2d_ctx *ctx = prv;
@@ -605,7 +601,6 @@ static const struct video_device g2d_videodev = {
 
 static const struct v4l2_m2m_ops g2d_m2m_ops = {
 	.device_run	= device_run,
-	.job_abort	= job_abort,
 };
 
 static const struct of_device_id exynos_g2d_match[];
diff --git a/drivers/media/platform/s5p-jpeg/jpeg-core.c b/drivers/media/platform/s5p-jpeg/jpeg-core.c
index 79b63da27f53..04fd2e0493c0 100644
--- a/drivers/media/platform/s5p-jpeg/jpeg-core.c
+++ b/drivers/media/platform/s5p-jpeg/jpeg-core.c
@@ -2467,26 +2467,19 @@ static int s5p_jpeg_job_ready(void *priv)
 	return 1;
 }
 
-static void s5p_jpeg_job_abort(void *priv)
-{
-}
-
 static struct v4l2_m2m_ops s5p_jpeg_m2m_ops = {
 	.device_run	= s5p_jpeg_device_run,
 	.job_ready	= s5p_jpeg_job_ready,
-	.job_abort	= s5p_jpeg_job_abort,
 };
 
 static struct v4l2_m2m_ops exynos3250_jpeg_m2m_ops = {
 	.device_run	= exynos3250_jpeg_device_run,
 	.job_ready	= s5p_jpeg_job_ready,
-	.job_abort	= s5p_jpeg_job_abort,
 };
 
 static struct v4l2_m2m_ops exynos4_jpeg_m2m_ops = {
 	.device_run	= exynos4_jpeg_device_run,
 	.job_ready	= s5p_jpeg_job_ready,
-	.job_abort	= s5p_jpeg_job_abort,
 };
 
 /*
diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 725da74d15d8..4aeedb91594a 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -322,7 +322,8 @@ static void v4l2_m2m_cancel_job(struct v4l2_m2m_ctx *m2m_ctx)
 	m2m_ctx->job_flags |= TRANS_ABORT;
 	if (m2m_ctx->job_flags & TRANS_RUNNING) {
 		spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
-		m2m_dev->m2m_ops->job_abort(m2m_ctx->priv);
+		if (m2m_dev->m2m_ops->job_abort)
+			m2m_dev->m2m_ops->job_abort(m2m_ctx->priv);
 		dprintk("m2m_ctx %p running, will wait to complete", m2m_ctx);
 		wait_event(m2m_ctx->finished,
 				!(m2m_ctx->job_flags & TRANS_RUNNING));
@@ -788,8 +789,7 @@ struct v4l2_m2m_dev *v4l2_m2m_init(const struct v4l2_m2m_ops *m2m_ops)
 {
 	struct v4l2_m2m_dev *m2m_dev;
 
-	if (!m2m_ops || WARN_ON(!m2m_ops->device_run) ||
-			WARN_ON(!m2m_ops->job_abort))
+	if (!m2m_ops || WARN_ON(!m2m_ops->device_run))
 		return ERR_PTR(-EINVAL);
 
 	m2m_dev = kzalloc(sizeof *m2m_dev, GFP_KERNEL);
diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index af48b1eca025..d60d3060f762 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -32,7 +32,7 @@
  *		assumed that one source and one destination buffer are all
  *		that is required for the driver to perform one full transaction.
  *		This method may not sleep.
- * @job_abort:	required. Informs the driver that it has to abort the currently
+ * @job_abort:	optional. Informs the driver that it has to abort the currently
  *		running transaction as soon as possible (i.e. as soon as it can
  *		stop the device safely; e.g. in the next interrupt handler),
  *		even if the transaction would not have been finished by then.
-- 
cgit v1.2.3


From a50c7738e8ae3276a4b224e321bbd40aee88e8fe Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Wed, 4 Jul 2018 06:15:46 -0400
Subject: media: sh: migor: Remove stale soc_camera include

Remove a stale inclusion for the soc_camera header.

Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 arch/sh/boards/mach-migor/setup.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/sh/boards/mach-migor/setup.c b/arch/sh/boards/mach-migor/setup.c
index 26543cc30d26..254f2c662703 100644
--- a/arch/sh/boards/mach-migor/setup.c
+++ b/arch/sh/boards/mach-migor/setup.c
@@ -28,7 +28,6 @@
 #include <video/sh_mobile_lcdc.h>
 #include <media/drv-intf/renesas-ceu.h>
 #include <media/i2c/ov772x.h>
-#include <media/soc_camera.h>
 #include <media/i2c/tw9910.h>
 #include <asm/clock.h>
 #include <asm/machvec.h>
-- 
cgit v1.2.3


From b509d733d337417bcb7fa4a35be3b9a49332b724 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Thu, 5 Jul 2018 04:25:19 -0400
Subject: media: videobuf2-core: check for q->error in vb2_core_qbuf()

The vb2_core_qbuf() function didn't check if q->error was set. It is
checked in __buf_prepare(), but that function isn't called if the buffer
was already prepared before with VIDIOC_PREPARE_BUF.

So check it at the start of vb2_core_qbuf() as well.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/common/videobuf2/videobuf2-core.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c
index f32ec7342ef0..5653e8eebe2b 100644
--- a/drivers/media/common/videobuf2/videobuf2-core.c
+++ b/drivers/media/common/videobuf2/videobuf2-core.c
@@ -1377,6 +1377,11 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb)
 	struct vb2_buffer *vb;
 	int ret;
 
+	if (q->error) {
+		dprintk(1, "fatal error occurred on queue\n");
+		return -EIO;
+	}
+
 	vb = q->bufs[index];
 
 	switch (vb->state) {
-- 
cgit v1.2.3


From 6479aa888222b344dfb087303e2f9e8d8394ef13 Mon Sep 17 00:00:00 2001
From: Neil Armstrong <narmstrong@baylibre.com>
Date: Tue, 10 Jul 2018 09:44:57 -0400
Subject: media: platform: meson-ao-cec: make busy TX warning silent

Switch to dev_dbg for the busy TX message to avoid having a flood of:
[  228.064570] meson-ao-cec c8100100.cec: meson_ao_cec_transmit: busy TX: aborting
[  230.368489] meson-ao-cec c8100100.cec: meson_ao_cec_transmit: busy TX: aborting
[  234.208655] meson-ao-cec c8100100.cec: meson_ao_cec_transmit: busy TX: aborting
[  236.512558] meson-ao-cec c8100100.cec: meson_ao_cec_transmit: busy TX: aborting

This message is only a debug hint and not an error.

Fixes: 7ec2c0f72cb1 ("media: platform: Add Amlogic Meson AO CEC Controller driver")

Signed-off-by: Neil Armstrong <narmstrong@baylibre.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/meson/ao-cec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/meson/ao-cec.c b/drivers/media/platform/meson/ao-cec.c
index 8040a6285c3f..cd4be38ab5ac 100644
--- a/drivers/media/platform/meson/ao-cec.c
+++ b/drivers/media/platform/meson/ao-cec.c
@@ -524,7 +524,7 @@ static int meson_ao_cec_transmit(struct cec_adapter *adap, u8 attempts,
 		return ret;
 
 	if (reg == TX_BUSY) {
-		dev_err(&ao_cec->pdev->dev, "%s: busy TX: aborting\n",
+		dev_dbg(&ao_cec->pdev->dev, "%s: busy TX: aborting\n",
 			__func__);
 		meson_ao_cec_write(ao_cec, CEC_TX_MSG_CMD, TX_ABORT, &ret);
 	}
-- 
cgit v1.2.3


From 231783073ebfc4acf02a45cb78a52ffa16e4e6d3 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Wed, 11 Jul 2018 10:23:32 -0400
Subject: media: v4l: rcar_fdp1: Enable compilation on Gen2 platforms

Commit 1d3897143815 ("[media] v4l: rcar_fdp1: add FCP dependency") fixed
a compilation breakage when the optional VIDEO_RENESAS_FCP dependency is
compiled as a module while the rcar_fdp1 driver is built in. As a side
effect it disabled compilation on Gen2 by disallowing the valid
combination ARCH_RENESAS && !VIDEO_RENESAS_FCP. Fix it by handling the
dependency the same way the vsp1 driver did in commit 199946731fa4
("[media] vsp1: clarify FCP dependency").

Fixes: 1d3897143815 ("[media] v4l: rcar_fdp1: add FCP dependency")

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 210b44a457eb..84cb97eccb2a 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -385,7 +385,7 @@ config VIDEO_RENESAS_FDP1
 	tristate "Renesas Fine Display Processor"
 	depends on VIDEO_DEV && VIDEO_V4L2
 	depends on ARCH_RENESAS || COMPILE_TEST
-	depends on (!ARCH_RENESAS && !VIDEO_RENESAS_FCP) || VIDEO_RENESAS_FCP
+	depends on (!ARM64 && !VIDEO_RENESAS_FCP) || VIDEO_RENESAS_FCP
 	select VIDEOBUF2_DMA_CONTIG
 	select V4L2_MEM2MEM_DEV
 	---help---
-- 
cgit v1.2.3


From 4a7727725dc7d73769c5ab24c566df454093285f Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 5 Jul 2018 14:40:46 -0500
Subject: GFS2: Fix recovery issues for spectators

This patch fixes a couple problems dealing with spectators who
remain with gfs2 mounts after the last non-spectator node fails.

Before this patch, spectator mounts would try to acquire the dlm's
mounted lock EX as part of its normal recovery sequence.
The mounted lock is only used to determine whether the node is
the first mounter, the first node to mount the file system, for
the purposes of file system recovery and journal replay.

It's not necessary for spectators: they should never do journal
recovery. If they acquire the lock it will prevent another "real"
first-mounter from acquiring the lock in EX mode, which means it
also cannot do journal recovery because it doesn't think it's the
first node to mount the file system.

This patch checks if the mounter is a spectator, and if so, avoids
grabbing the mounted lock. This allows a secondary mounter who is
really the first non-spectator mounter, to do journal recovery:
since the spectator doesn't acquire the lock, it can grab it in
EX mode, and therefore consider itself to be the first mounter
both as a "real" first mount, and as a first-real-after-spectator.

Note that the control lock still needs to be taken in PR mode
in order to fetch the lvb value so it has the current status of
all journal's recovery. This is used as it is today by a first
mounter to replay the journals. For spectators, it's merely
used to fetch the status bits. All recovery is bypassed and the
node waits until recovery is completed by a non-spectator node.

I also improved the cryptic message given by control_mount when
a spectator is waiting for a non-spectator to perform recovery.

It also fixes a problem in gfs2_recover_set whereby spectators
were never queueing recovery work for their own journal.
They cannot do recovery themselves, but they still need to queue
the work so they can check the recovery bits and clear the
DFL_BLOCK_LOCKS bit once the recovery happens on another node.

When the work queue runs on a spectator, it bypasses most of the
work so it won't print a bunch of annoying messages. All it will
print is a bunch of messages that look like this until recovery
completes on the non-spectator node:

GFS2: fsid=mycluster:scratch.s: recover generation 3 jid 0
GFS2: fsid=mycluster:scratch.s: recover jid 0 result busy

These continue every 1.5 seconds until the recovery is done by
the non-spectator, at which time it says:

GFS2: fsid=mycluster:scratch.s: recover generation 4 done

Then it proceeds with its mount.

If the file system is mounted in spectator node and the last
remaining non-spectator is fenced, any IO to the file system is
blocked by dlm and the spectator waits until recovery is
performed by a non-spectator.

If a spectator tries to mount the file system before any
non-spectators, it blocks and repeatedly gives this kernel
message:

GFS2: fsid=mycluster:scratch: Recovery is required. Waiting for a non-spectator to mount.
GFS2: fsid=mycluster:scratch: Recovery is required. Waiting for a non-spectator to mount.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/lock_dlm.c | 20 +++++++++++++++++---
 fs/gfs2/recovery.c |  7 ++++---
 fs/gfs2/sys.c      | 11 +++++++++--
 3 files changed, 30 insertions(+), 8 deletions(-)

diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 006c6164f759..ac7caa267ed6 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -821,6 +821,13 @@ restart:
 		goto fail;
 	}
 
+	/**
+	 * If we're a spectator, we don't want to take the lock in EX because
+	 * we cannot do the first-mount responsibility it implies: recovery.
+	 */
+	if (sdp->sd_args.ar_spectator)
+		goto locks_done;
+
 	error = mounted_lock(sdp, DLM_LOCK_EX, DLM_LKF_CONVERT|DLM_LKF_NOQUEUE);
 	if (!error) {
 		mounted_mode = DLM_LOCK_EX;
@@ -896,9 +903,16 @@ locks_done:
 	if (lvb_gen < mount_gen) {
 		/* wait for mounted nodes to update control_lock lvb to our
 		   generation, which might include new recovery bits set */
-		fs_info(sdp, "control_mount wait1 block %u start %u mount %u "
-			"lvb %u flags %lx\n", block_gen, start_gen, mount_gen,
-			lvb_gen, ls->ls_recover_flags);
+		if (sdp->sd_args.ar_spectator) {
+			fs_info(sdp, "Recovery is required. Waiting for a "
+				"non-spectator to mount.\n");
+			msleep_interruptible(1000);
+		} else {
+			fs_info(sdp, "control_mount wait1 block %u start %u "
+				"mount %u lvb %u flags %lx\n", block_gen,
+				start_gen, mount_gen, lvb_gen,
+				ls->ls_recover_flags);
+		}
 		spin_unlock(&ls->ls_recover_spin);
 		goto restart;
 	}
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index d8b622c375ab..0f501f938d1c 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -413,12 +413,13 @@ void gfs2_recover_func(struct work_struct *work)
 	ktime_t t_start, t_jlck, t_jhd, t_tlck, t_rep;
 	int ro = 0;
 	unsigned int pass;
-	int error;
+	int error = 0;
 	int jlocked = 0;
 
 	t_start = ktime_get();
-	if (sdp->sd_args.ar_spectator ||
-	    (jd->jd_jid != sdp->sd_lockstruct.ls_jid)) {
+	if (sdp->sd_args.ar_spectator)
+		goto fail;
+	if (jd->jd_jid != sdp->sd_lockstruct.ls_jid) {
 		fs_info(sdp, "jid=%u: Trying to acquire journal lock...\n",
 			jd->jd_jid);
 		jlocked = 1;
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index c191fa58a1df..1787d295834e 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -429,11 +429,18 @@ int gfs2_recover_set(struct gfs2_sbd *sdp, unsigned jid)
 
 	spin_lock(&sdp->sd_jindex_spin);
 	rv = -EBUSY;
-	if (sdp->sd_jdesc->jd_jid == jid)
+	/**
+	 * If we're a spectator, we use journal0, but it's not really ours.
+	 * So we need to wait for its recovery too. If we skip it we'd never
+	 * queue work to the recovery workqueue, and so its completion would
+	 * never clear the DFL_BLOCK_LOCKS flag, so all our locks would
+	 * permanently stop working.
+	 */
+	if (sdp->sd_jdesc->jd_jid == jid && !sdp->sd_args.ar_spectator)
 		goto out;
 	rv = -ENOENT;
 	list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
-		if (jd->jd_jid != jid)
+		if (jd->jd_jid != jid && !sdp->sd_args.ar_spectator)
 			continue;
 		rv = gfs2_recover_journal(jd, false);
 		break;
-- 
cgit v1.2.3


From c25892827c7996eb19ca2a5b1cf596218122e994 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 6 Jul 2018 23:05:41 +0100
Subject: gfs2: fallocate_chunk: Always initialize struct iomap

In fallocate_chunk, always initialize the iomap before calling
gfs2_iomap_get_alloc: future changes could otherwise cause things like
iomap.flags to leak across calls.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/file.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index f3c6d78659b1..6d895d39158a 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -877,7 +877,6 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	loff_t end = offset + len;
 	struct buffer_head *dibh;
-	struct iomap iomap = { };
 	int error;
 
 	error = gfs2_meta_inode_buffer(ip, &dibh);
@@ -893,6 +892,8 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
 	}
 
 	while (offset < end) {
+		struct iomap iomap = { };
+
 		error = gfs2_iomap_get_alloc(inode, offset, end - offset,
 					     &iomap);
 		if (error)
-- 
cgit v1.2.3


From 1d45bb7f9d2a5cbae1e5d9a5f72adad84db4d318 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 27 Jun 2018 01:59:18 +0100
Subject: gfs2: Use iomap for stuffed direct I/O reads

Remove the fallback code from direct to buffered I/O for stuffed reads.

For stuffed writes, we must keep the fallback code: the deferred glock
we are holding under direct I/O doesn't allow to write to the inode or
change the file size.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/file.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 6d895d39158a..08369c6cd127 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -706,14 +706,8 @@ static ssize_t gfs2_file_direct_read(struct kiocb *iocb, struct iov_iter *to)
 	if (ret)
 		goto out_uninit;
 
-	/* fall back to buffered I/O for stuffed files */
-	ret = -ENOTBLK;
-	if (gfs2_is_stuffed(ip))
-		goto out;
-
 	ret = iomap_dio_rw(iocb, to, &gfs2_iomap_ops, NULL);
 
-out:
 	gfs2_glock_dq(&gh);
 out_uninit:
 	gfs2_holder_uninit(&gh);
-- 
cgit v1.2.3


From f95cbb44abf9d6545769147d5abec4770c89872d Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 6 Jun 2018 20:30:38 +0100
Subject: gfs2: use iomap_readpage for blocksize == PAGE_SIZE

We only use iomap_readpage for pages that don't have buffer heads
attached yet: iomap_readpage would otherwise read pages from disk that
are marked buffer_uptodate() but not PageUptodate().  Those pages may
actually contain data more recent than what's on disk.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/aops.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index cc80fd71f3dd..31e8270d0b26 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -508,9 +508,13 @@ static int __gfs2_readpage(void *file, struct page *page)
 {
 	struct gfs2_inode *ip = GFS2_I(page->mapping->host);
 	struct gfs2_sbd *sdp = GFS2_SB(page->mapping->host);
+
 	int error;
 
-	if (gfs2_is_stuffed(ip)) {
+	if (i_blocksize(page->mapping->host) == PAGE_SIZE &&
+	    !page_has_buffers(page)) {
+		error = iomap_readpage(page, &gfs2_iomap_ops);
+	} else if (gfs2_is_stuffed(ip)) {
 		error = stuffed_readpage(ip, page);
 		unlock_page(page);
 	} else {
-- 
cgit v1.2.3


From d1b0cb933c8e638947ea72f3ab4e3dad4325bb96 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 17 Jul 2018 15:59:28 +0100
Subject: gfs2: remove redundant variable 'moved'

Variable 'moved' s being assigned but is never used hence it is
redundant and can be removed.  This has been the case ever since commit
c752666c.

Cleans up clang warning:
warning: variable 'moved' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/dir.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index d97ad89955d1..e37002560c11 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -1011,7 +1011,7 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 	u64 bn, leaf_no;
 	__be64 *lp;
 	u32 index;
-	int x, moved = 0;
+	int x;
 	int error;
 
 	index = name->hash >> (32 - dip->i_depth);
@@ -1113,8 +1113,6 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
 
 			if (!prev)
 				prev = dent;
-
-			moved = 1;
 		} else {
 			prev = dent;
 		}
-- 
cgit v1.2.3


From f6753df35c32f17b7abf0de37aa52850ca9733c9 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 30 May 2018 14:05:15 -0500
Subject: GFS2: rgrp free blocks used incorrectly

Before this patch, several functions in rgrp.c checked the value of
rgd->rd_free_clone. That does not take into account blocks that were
reserved by a multi-block reservation. This causes a problem when
space gets tight in the file system. For example, when function
gfs2_inplace_reserve checks to see if a rgrp has enough blocks to
satisfy the request, it can accept a rgrp that it should reject
because, although there are enough blocks to satisfy the request
_now_, those blocks may be reserved for another running process.

A second problem with this occurs when we've reserved the remaining
blocks in an rgrp: function rg_mblk_search() can reject an rgrp
improperly because it calculates:

   u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved;

But rd_reserved includes blocks that the current process just
reserved in its own call to inplace_reserve. For example, it can
reserve the last 128 blocks of an rgrp, then reject that same rgrp
because the above calculates out to free_blocks = 0;

Consequences include, but are not limited to, (1) leaving holes,
and thus increasing file system fragmentation, and (2) reporting
file system is full long before it actually is.

This patch introduces a new function, rgd_free, which returns the
number of clone-free blocks (blocks that are truly free as opposed
to blocks that are still being used because an unlinked file is
still open) minus the number of blocks reserved by processes, but
not counting the blocks we ourselves reserved (because obviously
we need to allocate them).

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/rgrp.c | 39 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 5 deletions(-)

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 0a484a009ba2..68a81afd3b4a 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1489,6 +1489,34 @@ static void rs_insert(struct gfs2_inode *ip)
 	trace_gfs2_rs(rs, TRACE_RS_INSERT);
 }
 
+/**
+ * rgd_free - return the number of free blocks we can allocate.
+ * @rgd: the resource group
+ *
+ * This function returns the number of free blocks for an rgrp.
+ * That's the clone-free blocks (blocks that are free, not including those
+ * still being used for unlinked files that haven't been deleted.)
+ *
+ * It also subtracts any blocks reserved by someone else, but does not
+ * include free blocks that are still part of our current reservation,
+ * because obviously we can (and will) allocate them.
+ */
+static inline u32 rgd_free(struct gfs2_rgrpd *rgd, struct gfs2_blkreserv *rs)
+{
+	u32 tot_reserved, tot_free;
+
+	if (WARN_ON_ONCE(rgd->rd_reserved < rs->rs_free))
+		return 0;
+	tot_reserved = rgd->rd_reserved - rs->rs_free;
+
+	if (rgd->rd_free_clone < tot_reserved)
+		tot_reserved = 0;
+
+	tot_free = rgd->rd_free_clone - tot_reserved;
+
+	return tot_free;
+}
+
 /**
  * rg_mblk_search - find a group of multiple free blocks to form a reservation
  * @rgd: the resource group descriptor
@@ -1504,7 +1532,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 	u64 goal;
 	struct gfs2_blkreserv *rs = &ip->i_res;
 	u32 extlen;
-	u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved;
+	u32 free_blocks = rgd_free(rgd, rs);
 	int ret;
 	struct inode *inode = &ip->i_inode;
 
@@ -1985,7 +2013,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 	int error = 0, rg_locked, flags = 0;
 	u64 last_unlinked = NO_BLOCK;
 	int loops = 0;
-	u32 skip = 0;
+	u32 free_blocks, skip = 0;
 
 	if (sdp->sd_args.ar_rgrplvb)
 		flags |= GL_SKIP;
@@ -2056,10 +2084,11 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 			goto check_rgrp;
 
 		/* If rgrp has enough free space, use it */
-		if (rs->rs_rbm.rgd->rd_free_clone >= ap->target ||
+		free_blocks = rgd_free(rs->rs_rbm.rgd, rs);
+		if (free_blocks >= ap->target ||
 		    (loops == 2 && ap->min_target &&
-		     rs->rs_rbm.rgd->rd_free_clone >= ap->min_target)) {
-			ap->allowed = rs->rs_rbm.rgd->rd_free_clone;
+		     free_blocks >= ap->min_target)) {
+			ap->allowed = free_blocks;
 			return 0;
 		}
 check_rgrp:
-- 
cgit v1.2.3


From 45332b1bdfdc8d63ae4a9d32cbb10e11bc20baab Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 5 Jul 2018 15:24:12 +0900
Subject: gcc-plugins: split out Kconfig entries to scripts/gcc-plugins/Kconfig

Collect relevant code into the scripts/gcc-plugins directory.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 arch/Kconfig                | 146 +-------------------------------------------
 scripts/gcc-plugins/Kconfig | 142 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 144 insertions(+), 144 deletions(-)
 create mode 100644 scripts/gcc-plugins/Kconfig

diff --git a/arch/Kconfig b/arch/Kconfig
index 1aa59063f1fd..b6d17877190f 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -405,150 +405,6 @@ config SECCOMP_FILTER
 
 	  See Documentation/userspace-api/seccomp_filter.rst for details.
 
-preferred-plugin-hostcc := $(if-success,[ $(gcc-version) -ge 40800 ],$(HOSTCXX),$(HOSTCC))
-
-config PLUGIN_HOSTCC
-	string
-	default "$(shell,$(srctree)/scripts/gcc-plugin.sh "$(preferred-plugin-hostcc)" "$(HOSTCXX)" "$(CC)")"
-	help
-	  Host compiler used to build GCC plugins.  This can be $(HOSTCXX),
-	  $(HOSTCC), or a null string if GCC plugin is unsupported.
-
-config HAVE_GCC_PLUGINS
-	bool
-	help
-	  An arch should select this symbol if it supports building with
-	  GCC plugins.
-
-menuconfig GCC_PLUGINS
-	bool "GCC plugins"
-	depends on HAVE_GCC_PLUGINS
-	depends on PLUGIN_HOSTCC != ""
-	help
-	  GCC plugins are loadable modules that provide extra features to the
-	  compiler. They are useful for runtime instrumentation and static analysis.
-
-	  See Documentation/gcc-plugins.txt for details.
-
-config GCC_PLUGIN_CYC_COMPLEXITY
-	bool "Compute the cyclomatic complexity of a function" if EXPERT
-	depends on GCC_PLUGINS
-	depends on !COMPILE_TEST	# too noisy
-	help
-	  The complexity M of a function's control flow graph is defined as:
-	   M = E - N + 2P
-	  where
-
-	  E = the number of edges
-	  N = the number of nodes
-	  P = the number of connected components (exit nodes).
-
-	  Enabling this plugin reports the complexity to stderr during the
-	  build. It mainly serves as a simple example of how to create a
-	  gcc plugin for the kernel.
-
-config GCC_PLUGIN_SANCOV
-	bool
-	depends on GCC_PLUGINS
-	help
-	  This plugin inserts a __sanitizer_cov_trace_pc() call at the start of
-	  basic blocks. It supports all gcc versions with plugin support (from
-	  gcc-4.5 on). It is based on the commit "Add fuzzing coverage support"
-	  by Dmitry Vyukov <dvyukov@google.com>.
-
-config GCC_PLUGIN_LATENT_ENTROPY
-	bool "Generate some entropy during boot and runtime"
-	depends on GCC_PLUGINS
-	help
-	  By saying Y here the kernel will instrument some kernel code to
-	  extract some entropy from both original and artificially created
-	  program state.  This will help especially embedded systems where
-	  there is little 'natural' source of entropy normally.  The cost
-	  is some slowdown of the boot process (about 0.5%) and fork and
-	  irq processing.
-
-	  Note that entropy extracted this way is not cryptographically
-	  secure!
-
-	  This plugin was ported from grsecurity/PaX. More information at:
-	   * https://grsecurity.net/
-	   * https://pax.grsecurity.net/
-
-config GCC_PLUGIN_STRUCTLEAK
-	bool "Force initialization of variables containing userspace addresses"
-	depends on GCC_PLUGINS
-	# Currently STRUCTLEAK inserts initialization out of live scope of
-	# variables from KASAN point of view. This leads to KASAN false
-	# positive reports. Prohibit this combination for now.
-	depends on !KASAN_EXTRA
-	help
-	  This plugin zero-initializes any structures containing a
-	  __user attribute. This can prevent some classes of information
-	  exposures.
-
-	  This plugin was ported from grsecurity/PaX. More information at:
-	   * https://grsecurity.net/
-	   * https://pax.grsecurity.net/
-
-config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL
-	bool "Force initialize all struct type variables passed by reference"
-	depends on GCC_PLUGIN_STRUCTLEAK
-	depends on !COMPILE_TEST
-	help
-	  Zero initialize any struct type local variable that may be passed by
-	  reference without having been initialized.
-
-config GCC_PLUGIN_STRUCTLEAK_VERBOSE
-	bool "Report forcefully initialized variables"
-	depends on GCC_PLUGIN_STRUCTLEAK
-	depends on !COMPILE_TEST	# too noisy
-	help
-	  This option will cause a warning to be printed each time the
-	  structleak plugin finds a variable it thinks needs to be
-	  initialized. Since not all existing initializers are detected
-	  by the plugin, this can produce false positive warnings.
-
-config GCC_PLUGIN_RANDSTRUCT
-	bool "Randomize layout of sensitive kernel structures"
-	depends on GCC_PLUGINS
-	select MODVERSIONS if MODULES
-	help
-	  If you say Y here, the layouts of structures that are entirely
-	  function pointers (and have not been manually annotated with
-	  __no_randomize_layout), or structures that have been explicitly
-	  marked with __randomize_layout, will be randomized at compile-time.
-	  This can introduce the requirement of an additional information
-	  exposure vulnerability for exploits targeting these structure
-	  types.
-
-	  Enabling this feature will introduce some performance impact,
-	  slightly increase memory usage, and prevent the use of forensic
-	  tools like Volatility against the system (unless the kernel
-	  source tree isn't cleaned after kernel installation).
-
-	  The seed used for compilation is located at
-	  scripts/gcc-plgins/randomize_layout_seed.h.  It remains after
-	  a make clean to allow for external modules to be compiled with
-	  the existing seed and will be removed by a make mrproper or
-	  make distclean.
-
-	  Note that the implementation requires gcc 4.7 or newer.
-
-	  This plugin was ported from grsecurity/PaX. More information at:
-	   * https://grsecurity.net/
-	   * https://pax.grsecurity.net/
-
-config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE
-	bool "Use cacheline-aware structure randomization"
-	depends on GCC_PLUGIN_RANDSTRUCT
-	depends on !COMPILE_TEST	# do not reduce test coverage
-	help
-	  If you say Y here, the RANDSTRUCT randomization will make a
-	  best effort at restricting randomization to cacheline-sized
-	  groups of elements.  It will further not randomize bitfields
-	  in structures.  This reduces the performance hit of RANDSTRUCT
-	  at the cost of weakened randomization.
-
 config HAVE_STACKPROTECTOR
 	bool
 	help
@@ -972,3 +828,5 @@ config REFCOUNT_FULL
 	  security flaw exploits.
 
 source "kernel/gcov/Kconfig"
+
+source "scripts/gcc-plugins/Kconfig"
diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig
new file mode 100644
index 000000000000..7430a7c77a4a
--- /dev/null
+++ b/scripts/gcc-plugins/Kconfig
@@ -0,0 +1,142 @@
+preferred-plugin-hostcc := $(if-success,[ $(gcc-version) -ge 40800 ],$(HOSTCXX),$(HOSTCC))
+
+config PLUGIN_HOSTCC
+	string
+	default "$(shell,$(srctree)/scripts/gcc-plugin.sh "$(preferred-plugin-hostcc)" "$(HOSTCXX)" "$(CC)")"
+	help
+	  Host compiler used to build GCC plugins.  This can be $(HOSTCXX),
+	  $(HOSTCC), or a null string if GCC plugin is unsupported.
+
+config HAVE_GCC_PLUGINS
+	bool
+	help
+	  An arch should select this symbol if it supports building with
+	  GCC plugins.
+
+menuconfig GCC_PLUGINS
+	bool "GCC plugins"
+	depends on HAVE_GCC_PLUGINS
+	depends on PLUGIN_HOSTCC != ""
+	help
+	  GCC plugins are loadable modules that provide extra features to the
+	  compiler. They are useful for runtime instrumentation and static analysis.
+
+	  See Documentation/gcc-plugins.txt for details.
+
+if GCC_PLUGINS
+
+config GCC_PLUGIN_CYC_COMPLEXITY
+	bool "Compute the cyclomatic complexity of a function" if EXPERT
+	depends on !COMPILE_TEST	# too noisy
+	help
+	  The complexity M of a function's control flow graph is defined as:
+	   M = E - N + 2P
+	  where
+
+	  E = the number of edges
+	  N = the number of nodes
+	  P = the number of connected components (exit nodes).
+
+	  Enabling this plugin reports the complexity to stderr during the
+	  build. It mainly serves as a simple example of how to create a
+	  gcc plugin for the kernel.
+
+config GCC_PLUGIN_SANCOV
+	bool
+	help
+	  This plugin inserts a __sanitizer_cov_trace_pc() call at the start of
+	  basic blocks. It supports all gcc versions with plugin support (from
+	  gcc-4.5 on). It is based on the commit "Add fuzzing coverage support"
+	  by Dmitry Vyukov <dvyukov@google.com>.
+
+config GCC_PLUGIN_LATENT_ENTROPY
+	bool "Generate some entropy during boot and runtime"
+	help
+	  By saying Y here the kernel will instrument some kernel code to
+	  extract some entropy from both original and artificially created
+	  program state.  This will help especially embedded systems where
+	  there is little 'natural' source of entropy normally.  The cost
+	  is some slowdown of the boot process (about 0.5%) and fork and
+	  irq processing.
+
+	  Note that entropy extracted this way is not cryptographically
+	  secure!
+
+	  This plugin was ported from grsecurity/PaX. More information at:
+	   * https://grsecurity.net/
+	   * https://pax.grsecurity.net/
+
+config GCC_PLUGIN_STRUCTLEAK
+	bool "Force initialization of variables containing userspace addresses"
+	# Currently STRUCTLEAK inserts initialization out of live scope of
+	# variables from KASAN point of view. This leads to KASAN false
+	# positive reports. Prohibit this combination for now.
+	depends on !KASAN_EXTRA
+	help
+	  This plugin zero-initializes any structures containing a
+	  __user attribute. This can prevent some classes of information
+	  exposures.
+
+	  This plugin was ported from grsecurity/PaX. More information at:
+	   * https://grsecurity.net/
+	   * https://pax.grsecurity.net/
+
+config GCC_PLUGIN_STRUCTLEAK_BYREF_ALL
+	bool "Force initialize all struct type variables passed by reference"
+	depends on GCC_PLUGIN_STRUCTLEAK
+	depends on !COMPILE_TEST
+	help
+	  Zero initialize any struct type local variable that may be passed by
+	  reference without having been initialized.
+
+config GCC_PLUGIN_STRUCTLEAK_VERBOSE
+	bool "Report forcefully initialized variables"
+	depends on GCC_PLUGIN_STRUCTLEAK
+	depends on !COMPILE_TEST	# too noisy
+	help
+	  This option will cause a warning to be printed each time the
+	  structleak plugin finds a variable it thinks needs to be
+	  initialized. Since not all existing initializers are detected
+	  by the plugin, this can produce false positive warnings.
+
+config GCC_PLUGIN_RANDSTRUCT
+	bool "Randomize layout of sensitive kernel structures"
+	select MODVERSIONS if MODULES
+	help
+	  If you say Y here, the layouts of structures that are entirely
+	  function pointers (and have not been manually annotated with
+	  __no_randomize_layout), or structures that have been explicitly
+	  marked with __randomize_layout, will be randomized at compile-time.
+	  This can introduce the requirement of an additional information
+	  exposure vulnerability for exploits targeting these structure
+	  types.
+
+	  Enabling this feature will introduce some performance impact,
+	  slightly increase memory usage, and prevent the use of forensic
+	  tools like Volatility against the system (unless the kernel
+	  source tree isn't cleaned after kernel installation).
+
+	  The seed used for compilation is located at
+	  scripts/gcc-plgins/randomize_layout_seed.h.  It remains after
+	  a make clean to allow for external modules to be compiled with
+	  the existing seed and will be removed by a make mrproper or
+	  make distclean.
+
+	  Note that the implementation requires gcc 4.7 or newer.
+
+	  This plugin was ported from grsecurity/PaX. More information at:
+	   * https://grsecurity.net/
+	   * https://pax.grsecurity.net/
+
+config GCC_PLUGIN_RANDSTRUCT_PERFORMANCE
+	bool "Use cacheline-aware structure randomization"
+	depends on GCC_PLUGIN_RANDSTRUCT
+	depends on !COMPILE_TEST	# do not reduce test coverage
+	help
+	  If you say Y here, the RANDSTRUCT randomization will make a
+	  best effort at restricting randomization to cacheline-sized
+	  groups of elements.  It will further not randomize bitfields
+	  in structures.  This reduces the performance hit of RANDSTRUCT
+	  at the cost of weakened randomization.
+
+endif
-- 
cgit v1.2.3


From 7ccb95e8fe9131b8fa14b947c60dfb30044fa002 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Wed, 11 Jul 2018 17:38:52 -0700
Subject: gcc-plugins: Regularize Makefile.gcc-plugins

The layout of Makefile.gcc-plugins had uneven tabs, and the long names
of things made this file a bit hard to quickly visually parse. This
breaks lines and moves options to the same tab depth. While we're at
it, this also adds some comments about the various sections.

Signed-off-by: Kees Cook <keescook@chromium.org>
---
 scripts/Makefile.gcc-plugins | 36 ++++++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 12 deletions(-)

diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index f9942d9ac3fc..0a482f341576 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -1,32 +1,44 @@
 # SPDX-License-Identifier: GPL-2.0
+
 gcc-plugin-$(CONFIG_GCC_PLUGIN_CYC_COMPLEXITY)	+= cyc_complexity_plugin.so
 
 gcc-plugin-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY)	+= latent_entropy_plugin.so
-gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY)	+= -DLATENT_ENTROPY_PLUGIN
+gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_LATENT_ENTROPY)		\
+		+= -DLATENT_ENTROPY_PLUGIN
 ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY
-    DISABLE_LATENT_ENTROPY_PLUGIN			+= -fplugin-arg-latent_entropy_plugin-disable
+    DISABLE_LATENT_ENTROPY_PLUGIN += -fplugin-arg-latent_entropy_plugin-disable
 endif
+export DISABLE_LATENT_ENTROPY_PLUGIN
 
 gcc-plugin-$(CONFIG_GCC_PLUGIN_SANCOV)		+= sancov_plugin.so
+
 gcc-plugin-$(CONFIG_GCC_PLUGIN_STRUCTLEAK)	+= structleak_plugin.so
-gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_VERBOSE)	+= -fplugin-arg-structleak_plugin-verbose
-gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL)	+= -fplugin-arg-structleak_plugin-byref-all
-gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK)	+= -DSTRUCTLEAK_PLUGIN
+gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_VERBOSE)	\
+		+= -fplugin-arg-structleak_plugin-verbose
+gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK_BYREF_ALL)	\
+		+= -fplugin-arg-structleak_plugin-byref-all
+gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STRUCTLEAK)		\
+		+= -DSTRUCTLEAK_PLUGIN
 
 gcc-plugin-$(CONFIG_GCC_PLUGIN_RANDSTRUCT)	+= randomize_layout_plugin.so
-gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT)	+= -DRANDSTRUCT_PLUGIN
-gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT_PERFORMANCE)	+= -fplugin-arg-randomize_layout_plugin-performance-mode
+gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT)		\
+		+= -DRANDSTRUCT_PLUGIN
+gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT_PERFORMANCE)	\
+		+= -fplugin-arg-randomize_layout_plugin-performance-mode
 
+# All the plugin CFLAGS are collected here in case a build target needs to
+# filter them out of the KBUILD_CFLAGS.
 GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y))
-
-export GCC_PLUGINS_CFLAGS GCC_PLUGIN
-export DISABLE_LATENT_ENTROPY_PLUGIN
-
-# sancov_plugin.so can be only in CFLAGS_KCOV because avoid duplication.
+# The sancov_plugin.so is included via CFLAGS_KCOV, so it is removed here.
 GCC_PLUGINS_CFLAGS := $(filter-out %/sancov_plugin.so, $(GCC_PLUGINS_CFLAGS))
+export GCC_PLUGINS_CFLAGS
 
+# Add the flags to the build!
 KBUILD_CFLAGS += $(GCC_PLUGINS_CFLAGS)
+
+# All enabled GCC plugins are collected here for building below.
 GCC_PLUGIN := $(gcc-plugin-y)
+export GCC_PLUGIN
 
 # Actually do the build, if requested.
 PHONY += gcc-plugins
-- 
cgit v1.2.3


From 45d9a1e3cc45efee6c0ef82b77269d6944d9d8a5 Mon Sep 17 00:00:00 2001
From: Alexander Popov <alex.popov@linux.com>
Date: Wed, 11 Jul 2018 23:36:35 +0300
Subject: gcc-plugins: Clean up the cgraph_create_edge* macros

Drop useless redefinitions of cgraph_create_edge* macros. Drop the unused
nest argument. Also support gcc-8, which doesn't have freq argument.

Signed-off-by: Alexander Popov <alex.popov@linux.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 scripts/gcc-plugins/gcc-common.h | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/scripts/gcc-plugins/gcc-common.h b/scripts/gcc-plugins/gcc-common.h
index f46750053377..552d5efd7cb7 100644
--- a/scripts/gcc-plugins/gcc-common.h
+++ b/scripts/gcc-plugins/gcc-common.h
@@ -392,13 +392,6 @@ static inline struct cgraph_node *cgraph_alias_target(struct cgraph_node *n)
 }
 #endif
 
-#if BUILDING_GCC_VERSION >= 4007 && BUILDING_GCC_VERSION <= 4009
-#define cgraph_create_edge(caller, callee, call_stmt, count, freq, nest) \
-	cgraph_create_edge((caller), (callee), (call_stmt), (count), (freq))
-#define cgraph_create_edge_including_clones(caller, callee, old_call_stmt, call_stmt, count, freq, nest, reason) \
-	cgraph_create_edge_including_clones((caller), (callee), (old_call_stmt), (call_stmt), (count), (freq), (reason))
-#endif
-
 #if BUILDING_GCC_VERSION <= 4008
 #define ENTRY_BLOCK_PTR_FOR_FN(FN)	ENTRY_BLOCK_PTR_FOR_FUNCTION(FN)
 #define EXIT_BLOCK_PTR_FOR_FN(FN)	EXIT_BLOCK_PTR_FOR_FUNCTION(FN)
@@ -723,10 +716,23 @@ static inline const char *get_decl_section_name(const_tree decl)
 #define varpool_get_node(decl) varpool_node::get(decl)
 #define dump_varpool_node(file, node) (node)->dump(file)
 
-#define cgraph_create_edge(caller, callee, call_stmt, count, freq, nest) \
+#if BUILDING_GCC_VERSION >= 8000
+#define cgraph_create_edge(caller, callee, call_stmt, count, freq) \
+	(caller)->create_edge((callee), (call_stmt), (count))
+
+#define cgraph_create_edge_including_clones(caller, callee,	\
+		old_call_stmt, call_stmt, count, freq, reason)	\
+	(caller)->create_edge_including_clones((callee),	\
+		(old_call_stmt), (call_stmt), (count), (reason))
+#else
+#define cgraph_create_edge(caller, callee, call_stmt, count, freq) \
 	(caller)->create_edge((callee), (call_stmt), (count), (freq))
-#define cgraph_create_edge_including_clones(caller, callee, old_call_stmt, call_stmt, count, freq, nest, reason) \
-	(caller)->create_edge_including_clones((callee), (old_call_stmt), (call_stmt), (count), (freq), (reason))
+
+#define cgraph_create_edge_including_clones(caller, callee,	\
+		old_call_stmt, call_stmt, count, freq, reason)	\
+	(caller)->create_edge_including_clones((callee),	\
+		(old_call_stmt), (call_stmt), (count), (freq), (reason))
+#endif
 
 typedef struct cgraph_node *cgraph_node_ptr;
 typedef struct cgraph_edge *cgraph_edge_p;
-- 
cgit v1.2.3


From b1c03f1ef48d36ff28afb06e8f0c1233ef072f1d Mon Sep 17 00:00:00 2001
From: Matt Redfearn <matt.redfearn@mips.com>
Date: Wed, 23 May 2018 14:39:58 +0100
Subject: MIPS: memset.S: Fix byte_fixup for MIPSr6

The __clear_user function is defined to return the number of bytes that
could not be cleared. From the underlying memset / bzero implementation
this means setting register a2 to that number on return. Currently if a
page fault is triggered within the MIPSr6 version of setting of initial
unaligned bytes, the value loaded into a2 on return is meaningless.

During the MIPSr6 version of the initial unaligned bytes block, register
a2 contains the number of bytes to be set beyond the initial unaligned
bytes. The t0 register is initally set to the number of unaligned bytes
- STORSIZE, effectively a negative version of the number of unaligned
bytes. This is then incremented before each byte is saved.

The label .Lbyte_fixup\@ is jumped to on page fault. Currently the value
in a2 is incorrectly replaced by 0 - t0 + 1, effectively the number of
unaligned bytes remaining. This leads to the failures being reported by
the following test code:

static int __init test_clear_user(void)
{
	int j, k;

	pr_info("\n\n\nTesting clear_user\n");
	for (j = 0; j < 512; j++) {
		if ((k = clear_user(NULL+3, j)) != j) {
			pr_err("clear_user (NULL %d) returned %d\n", j, k);
		}
	}
	return 0;
}
late_initcall(test_clear_user);

Which reports:
[    3.965439] Testing clear_user
[    3.973169] clear_user (NULL 8) returned 6
[    3.976782] clear_user (NULL 9) returned 6
[    3.980390] clear_user (NULL 10) returned 6
[    3.984052] clear_user (NULL 11) returned 6
[    3.987524] clear_user (NULL 12) returned 6

Fix this by subtracting t0 from a2 (rather than $0), effectivey giving:
unset_bytes = (#bytes - (#unaligned bytes)) - (-#unaligned bytes remaining + 1) + 1
     a2     =             a2                -              t0                   + 1

This fixes the value returned from __clear user when the number of bytes
to set is > LONGSIZE and the address is invalid and unaligned.

Unfortunately, this breaks the fixup handling for unaligned bytes after
the final long, where register a2 still contains the number of bytes
remaining to be set and the t0 register is to 0 - the number of
unaligned bytes remaining.

Because t0 is now is now subtracted from a2 rather than 0, the number of
bytes unset is reported incorrectly:

static int __init test_clear_user(void)
{
	char *test;
	int j, k;

	pr_info("\n\n\nTesting clear_user\n");
	test = vmalloc(PAGE_SIZE);

	for (j = 256; j < 512; j++) {
		if ((k = clear_user(test + PAGE_SIZE - 254, j)) != j - 254) {
			pr_err("clear_user (%px %d) returned %d\n",
				test + PAGE_SIZE - 254, j, k);
		}
	}
	return 0;
}
late_initcall(test_clear_user);

[    3.976775] clear_user (c00000000000df02 256) returned 4
[    3.981957] clear_user (c00000000000df02 257) returned 6
[    3.986425] clear_user (c00000000000df02 258) returned 8
[    3.990850] clear_user (c00000000000df02 259) returned 10
[    3.995332] clear_user (c00000000000df02 260) returned 12
[    3.999815] clear_user (c00000000000df02 261) returned 14

Fix this by ensuring that a2 is set to 0 during the set of final
unaligned bytes.

Signed-off-by: Matt Redfearn <matt.redfearn@mips.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Fixes: 8c56208aff77 ("MIPS: lib: memset: Add MIPS R6 support")
Patchwork: https://patchwork.linux-mips.org/patch/19338/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org # v4.0+
---
 arch/mips/lib/memset.S | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 1cc306520a55..fac26ce64b2f 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -195,6 +195,7 @@
 #endif
 #else
 	 PTR_SUBU	t0, $0, a2
+	move		a2, zero		/* No remaining longs */
 	PTR_ADDIU	t0, 1
 	STORE_BYTE(0)
 	STORE_BYTE(1)
@@ -231,7 +232,7 @@
 
 #ifdef CONFIG_CPU_MIPSR6
 .Lbyte_fixup\@:
-	PTR_SUBU	a2, $0, t0
+	PTR_SUBU	a2, t0
 	jr		ra
 	 PTR_ADDIU	a2, 1
 #endif /* CONFIG_CPU_MIPSR6 */
-- 
cgit v1.2.3


From 6312455a0437a64059bdeee5696b375593a09947 Mon Sep 17 00:00:00 2001
From: Matt Redfearn <matt.redfearn@mips.com>
Date: Wed, 23 May 2018 14:39:59 +0100
Subject: MIPS: memset.S: Add comments to fault fixup handlers

It is not immediately obvious what the expected inputs to these fault
handlers is and how they calculate the number of unset bytes. Having
stared deeply at this in order to fix some corner cases, add some
comments to assist those who follow.

Signed-off-by: Matt Redfearn <matt.redfearn@mips.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19339/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: <linux-mips@linux-mips.org>
Cc: <linux-kernel@vger.kernel.org>
---
 arch/mips/lib/memset.S | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index fac26ce64b2f..3a6f34ef5ffc 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -232,16 +232,25 @@
 
 #ifdef CONFIG_CPU_MIPSR6
 .Lbyte_fixup\@:
+	/*
+	 * unset_bytes = (#bytes - (#unaligned bytes)) - (-#unaligned bytes remaining + 1) + 1
+	 *      a2     =             a2                -              t0                   + 1
+	 */
 	PTR_SUBU	a2, t0
 	jr		ra
 	 PTR_ADDIU	a2, 1
 #endif /* CONFIG_CPU_MIPSR6 */
 
 .Lfirst_fixup\@:
+	/* unset_bytes already in a2 */
 	jr	ra
 	 nop
 
 .Lfwd_fixup\@:
+	/*
+	 * unset_bytes = partial_start_addr +  #bytes   -     fault_addr
+	 *      a2     =         t1         + (a2 & 3f) - $28->task->BUADDR
+	 */
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, 0x3f
 	LONG_L		t0, THREAD_BUADDR(t0)
@@ -250,6 +259,10 @@
 	 LONG_SUBU	a2, t0
 
 .Lpartial_fixup\@:
+	/*
+	 * unset_bytes = partial_end_addr +      #bytes     -     fault_addr
+	 *      a2     =       a0         + (a2 & STORMASK) - $28->task->BUADDR
+	 */
 	PTR_L		t0, TI_TASK($28)
 	andi		a2, STORMASK
 	LONG_L		t0, THREAD_BUADDR(t0)
@@ -258,10 +271,15 @@
 	 LONG_SUBU	a2, t0
 
 .Llast_fixup\@:
+	/* unset_bytes already in a2 */
 	jr		ra
 	 nop
 
 .Lsmall_fixup\@:
+	/*
+	 * unset_bytes = end_addr - current_addr + 1
+	 *      a2     =    t1    -      a0      + 1
+	 */
 	PTR_SUBU	a2, t1, a0
 	jr		ra
 	 PTR_ADDIU	a2, 1
-- 
cgit v1.2.3


From 840267e4466c72d48ca951a9678f48a322fade35 Mon Sep 17 00:00:00 2001
From: "Steven J. Hill" <steven.hill@cavium.com>
Date: Tue, 5 Jun 2018 00:24:51 -0500
Subject: MIPS: Octeon: Remove extern declarations.

Get rid of extern declarations in .c functions and included
the necessary header file. Also remove unused UART declares.

Signed-off-by: Steven J. Hill <steven.hill@cavium.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19477/
Cc: linux-mips@linux-mips.org
---
 arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c | 5 +----
 arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c | 7 ++-----
 arch/mips/cavium-octeon/executive/cvmx-helper-spi.c   | 8 +++-----
 arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c  | 7 ++-----
 arch/mips/cavium-octeon/setup.c                       | 4 ----
 arch/mips/include/asm/octeon/cvmx-asxx-defs.h         | 4 +++-
 arch/mips/include/asm/octeon/cvmx-gmxx-defs.h         | 4 +++-
 arch/mips/include/asm/octeon/cvmx-pcsx-defs.h         | 4 +++-
 arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h        | 4 +++-
 arch/mips/include/asm/octeon/cvmx-spxx-defs.h         | 4 +++-
 arch/mips/include/asm/octeon/cvmx-stxx-defs.h         | 4 +++-
 arch/mips/include/asm/octeon/octeon.h                 | 9 ++++-----
 12 files changed, 30 insertions(+), 34 deletions(-)

diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
index d18ed5af62f4..b8898e2b8a6f 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-rgmii.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -42,9 +42,6 @@
 #include <asm/octeon/cvmx-asxx-defs.h>
 #include <asm/octeon/cvmx-dbg-defs.h>
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_asxx_enable(int block);
-
 /**
  * Probe RGMII ports and determine the number present
  *
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
index 578283350776..a176358c5a21 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-sgmii.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -39,10 +39,7 @@
 
 #include <asm/octeon/cvmx-gmxx-defs.h>
 #include <asm/octeon/cvmx-pcsx-defs.h>
-
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+#include <asm/octeon/cvmx-pcsxx-defs.h>
 
 /**
  * Perform initialization required only once for an SGMII port.
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
index ef16aa00167b..2a574d272671 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-spi.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -25,10 +25,6 @@
  * Contact Cavium Networks for more information
  ***********************license end**************************************/
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_spxx_int_msk_enable(int index);
-void __cvmx_interrupt_stxx_int_msk_enable(int index);
-
 /*
  * Functions for SPI initialization, configuration,
  * and monitoring.
@@ -41,6 +37,8 @@ void __cvmx_interrupt_stxx_int_msk_enable(int index);
 
 #include <asm/octeon/cvmx-pip-defs.h>
 #include <asm/octeon/cvmx-pko-defs.h>
+#include <asm/octeon/cvmx-spxx-defs.h>
+#include <asm/octeon/cvmx-stxx-defs.h>
 
 /*
  * CVMX_HELPER_SPI_TIMEOUT is used to determine how long the SPI
diff --git a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
index 19d54e02c185..2bb6912a580d 100644
--- a/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
+++ b/arch/mips/cavium-octeon/executive/cvmx-helper-xaui.c
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2008 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -39,12 +39,9 @@
 
 #include <asm/octeon/cvmx-pko-defs.h>
 #include <asm/octeon/cvmx-gmxx-defs.h>
+#include <asm/octeon/cvmx-pcsx-defs.h>
 #include <asm/octeon/cvmx-pcsxx-defs.h>
 
-void __cvmx_interrupt_gmxx_enable(int interface);
-void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
-void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
-
 int __cvmx_helper_xaui_enumerate(int interface)
 {
 	union cvmx_gmxx_hg2_control gmx_hg2_control;
diff --git a/arch/mips/cavium-octeon/setup.c b/arch/mips/cavium-octeon/setup.c
index 6c437486af39..c2426232db06 100644
--- a/arch/mips/cavium-octeon/setup.c
+++ b/arch/mips/cavium-octeon/setup.c
@@ -1154,11 +1154,7 @@ void __init prom_free_prom_memory(void)
 }
 
 void __init octeon_fill_mac_addresses(void);
-int octeon_prune_device_tree(void);
 
-extern const char __appended_dtb;
-extern const char __dtb_octeon_3xxx_begin;
-extern const char __dtb_octeon_68xx_begin;
 void __init device_tree_init(void)
 {
 	const void *fdt;
diff --git a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
index a1e21a3854cf..1eef155979f3 100644
--- a/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-asxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -55,6 +55,8 @@
 #define CVMX_ASXX_TX_HI_WATERX(offset, block_id) (CVMX_ADD_IO_SEG(0x00011800B0000080ull) + (((offset) & 3) + ((block_id) & 1) * 0x1000000ull) * 8)
 #define CVMX_ASXX_TX_PRT_EN(block_id) (CVMX_ADD_IO_SEG(0x00011800B0000008ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_asxx_enable(int block);
+
 union cvmx_asxx_gmii_rx_clk_set {
 	uint64_t u64;
 	struct cvmx_asxx_gmii_rx_clk_set_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
index e347496a33c3..80e4f8358b81 100644
--- a/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-gmxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -2070,6 +2070,8 @@ static inline uint64_t CVMX_GMXX_XAUI_EXT_LOOPBACK(unsigned long block_id)
 	return CVMX_ADD_IO_SEG(0x0001180008000540ull) + (block_id) * 0x8000000ull;
 }
 
+void __cvmx_interrupt_gmxx_enable(int interface);
+
 union cvmx_gmxx_bad_reg {
 	uint64_t u64;
 	struct cvmx_gmxx_bad_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
index a5e8fd861c37..39da7f9d7b3f 100644
--- a/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-pcsx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -334,6 +334,8 @@ static inline uint64_t CVMX_PCSX_TX_RXX_POLARITY_REG(unsigned long offset, unsig
 	return CVMX_ADD_IO_SEG(0x00011800B0001048ull) + ((offset) + (block_id) * 0x20000ull) * 1024;
 }
 
+void __cvmx_interrupt_pcsx_intx_en_reg_enable(int index, int block);
+
 union cvmx_pcsx_anx_adv_reg {
 	uint64_t u64;
 	struct cvmx_pcsx_anx_adv_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
index b5b45d26f1c5..847dd9dca6ea 100644
--- a/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-pcsxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -268,6 +268,8 @@ static inline uint64_t CVMX_PCSXX_TX_RX_STATES_REG(unsigned long block_id)
 	return CVMX_ADD_IO_SEG(0x00011800B0000830ull) + (block_id) * 0x1000000ull;
 }
 
+void __cvmx_interrupt_pcsxx_int_en_reg_enable(int index);
+
 union cvmx_pcsxx_10gbx_status_reg {
 	uint64_t u64;
 	struct cvmx_pcsxx_10gbx_status_reg_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
index c7d601d9446e..f4c4e8051160 100644
--- a/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-spxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -45,6 +45,8 @@
 #define CVMX_SPXX_TPA_SEL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000328ull) + ((block_id) & 1) * 0x8000000ull)
 #define CVMX_SPXX_TRN4_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000360ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_spxx_int_msk_enable(int index);
+
 union cvmx_spxx_bckprs_cnt {
 	uint64_t u64;
 	struct cvmx_spxx_bckprs_cnt_s {
diff --git a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
index 146354005d3b..3c409a854d91 100644
--- a/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
+++ b/arch/mips/include/asm/octeon/cvmx-stxx-defs.h
@@ -4,7 +4,7 @@
  * Contact: support@caviumnetworks.com
  * This file is part of the OCTEON SDK
  *
- * Copyright (c) 2003-2012 Cavium Networks
+ * Copyright (C) 2003-2018 Cavium, Inc.
  *
  * This file is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License, Version 2, as
@@ -45,6 +45,8 @@
 #define CVMX_STXX_STAT_CTL(block_id) (CVMX_ADD_IO_SEG(0x0001180090000638ull) + ((block_id) & 1) * 0x8000000ull)
 #define CVMX_STXX_STAT_PKT_XMT(block_id) (CVMX_ADD_IO_SEG(0x0001180090000640ull) + ((block_id) & 1) * 0x8000000ull)
 
+void __cvmx_interrupt_stxx_int_msk_enable(int index);
+
 union cvmx_stxx_arb_ctl {
 	uint64_t u64;
 	struct cvmx_stxx_arb_ctl_s {
diff --git a/arch/mips/include/asm/octeon/octeon.h b/arch/mips/include/asm/octeon/octeon.h
index c99c4b6a79f4..60481502826a 100644
--- a/arch/mips/include/asm/octeon/octeon.h
+++ b/arch/mips/include/asm/octeon/octeon.h
@@ -279,13 +279,12 @@ union octeon_cvmemctl {
 	} s;
 };
 
-extern void octeon_write_lcd(const char *s);
 extern void octeon_check_cpu_bist(void);
-extern int octeon_get_boot_uart(void);
 
-struct uart_port;
-extern unsigned int octeon_serial_in(struct uart_port *, int);
-extern void octeon_serial_out(struct uart_port *, int, int);
+int octeon_prune_device_tree(void);
+extern const char __appended_dtb;
+extern const char __dtb_octeon_3xxx_begin;
+extern const char __dtb_octeon_68xx_begin;
 
 /**
  * Write a 32bit value to the Octeon NPI register space
-- 
cgit v1.2.3


From d5be4aeb5b36ba9cecd6ddbcce972e5d842c5df6 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 26 Jun 2018 13:57:11 +0200
Subject: mips: mscc: build FIT image for Ocelot

Ocelot now has a u-boot port, allow building FIT images instead of relying
on the legacy detection and builtin DTB.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: James Hogan <jhogan@kernel.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19632/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/dts/mscc/Makefile            |  2 +-
 arch/mips/generic/Kconfig                   | 12 ++++++++++--
 arch/mips/generic/Platform                  |  1 +
 arch/mips/generic/board-ocelot_pcb123.its.S | 23 +++++++++++++++++++++++
 4 files changed, 35 insertions(+), 3 deletions(-)
 create mode 100644 arch/mips/generic/board-ocelot_pcb123.its.S

diff --git a/arch/mips/boot/dts/mscc/Makefile b/arch/mips/boot/dts/mscc/Makefile
index 3c6aed9f5439..9a9bb7ea0503 100644
--- a/arch/mips/boot/dts/mscc/Makefile
+++ b/arch/mips/boot/dts/mscc/Makefile
@@ -1,3 +1,3 @@
-dtb-$(CONFIG_LEGACY_BOARD_OCELOT)	+= ocelot_pcb123.dtb
+dtb-$(CONFIG_MSCC_OCELOT)	+= ocelot_pcb123.dtb
 
 obj-$(CONFIG_BUILTIN_DTB)	+= $(addsuffix .o, $(dtb-y))
diff --git a/arch/mips/generic/Kconfig b/arch/mips/generic/Kconfig
index ba9b2c8cce68..08e33c6b2539 100644
--- a/arch/mips/generic/Kconfig
+++ b/arch/mips/generic/Kconfig
@@ -35,13 +35,13 @@ config LEGACY_BOARD_OCELOT
 	depends on LEGACY_BOARD_SEAD3=n
 	select LEGACY_BOARDS
 	select MSCC_OCELOT
+	select SYS_HAS_EARLY_PRINTK
+	select USE_GENERIC_EARLY_PRINTK_8250
 
 config MSCC_OCELOT
 	bool
 	select GPIOLIB
 	select MSCC_OCELOT_IRQ
-	select SYS_HAS_EARLY_PRINTK
-	select USE_GENERIC_EARLY_PRINTK_8250
 
 comment "FIT/UHI Boards"
 
@@ -65,6 +65,14 @@ config FIT_IMAGE_FDT_XILFPGA
 	  Enable this to include the FDT for the MIPSfpga platform
 	  from Imagination Technologies in the FIT kernel image.
 
+config FIT_IMAGE_FDT_OCELOT_PCB123
+	bool "Include FDT for Microsemi Ocelot PCB123"
+	select MSCC_OCELOT
+	help
+	  Enable this to include the FDT for the Ocelot PCB123 platform
+	  from Microsemi in the FIT kernel image.
+	  This requires u-boot on the platform.
+
 config VIRT_BOARD_RANCHU
 	bool "Support Ranchu platform for Android emulator"
 	help
diff --git a/arch/mips/generic/Platform b/arch/mips/generic/Platform
index 0dd0d5d460a5..879cb80396c8 100644
--- a/arch/mips/generic/Platform
+++ b/arch/mips/generic/Platform
@@ -16,4 +16,5 @@ all-$(CONFIG_MIPS_GENERIC)	:= vmlinux.gz.itb
 its-y					:= vmlinux.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_BOSTON)	+= board-boston.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_NI169445)	+= board-ni169445.its.S
+its-$(CONFIG_FIT_IMAGE_FDT_OCELOT_PCB123) += board-ocelot_pcb123.its.S
 its-$(CONFIG_FIT_IMAGE_FDT_XILFPGA)	+= board-xilfpga.its.S
diff --git a/arch/mips/generic/board-ocelot_pcb123.its.S b/arch/mips/generic/board-ocelot_pcb123.its.S
new file mode 100644
index 000000000000..5a7d5e1c878a
--- /dev/null
+++ b/arch/mips/generic/board-ocelot_pcb123.its.S
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */
+/ {
+	images {
+		fdt@ocelot_pcb123 {
+			description = "MSCC Ocelot PCB123 Device Tree";
+			data = /incbin/("boot/dts/mscc/ocelot_pcb123.dtb");
+			type = "flat_dt";
+			arch = "mips";
+			compression = "none";
+			hash@0 {
+				algo = "sha1";
+			};
+		};
+	};
+
+	configurations {
+		conf@ocelot_pcb123 {
+			description = "Ocelot Linux kernel";
+			kernel = "kernel@0";
+			fdt = "fdt@ocelot_pcb123";
+		};
+	};
+};
-- 
cgit v1.2.3


From a95f4b1c28932ca4194d81db60ecdf59152bb808 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <juhosg@openwrt.org>
Date: Fri, 20 Jul 2018 13:58:18 +0200
Subject: MIPS: ath79: add lots of missing registers

This patch adds many new registers for various QCA MIPS SoCs. The patch is
an aggragate of many contributions made to OpenWrt.

Signed-off-by: Gabor Juhos <juhosg@openwrt.org>
Signed-off-by: Henryk Heisig <hyniu@o2.pl>
Signed-off-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: Weijie Gao <hackpascal@gmail.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Julien Dusser <julien.dusser@free.fr>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19910/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/mach-ath79/ar71xx_regs.h | 771 ++++++++++++++++++++++++-
 1 file changed, 770 insertions(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
index d99ca862dae3..284b4fa23e03 100644
--- a/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
+++ b/arch/mips/include/asm/mach-ath79/ar71xx_regs.h
@@ -20,6 +20,10 @@
 #include <linux/bitops.h>
 
 #define AR71XX_APB_BASE		0x18000000
+#define AR71XX_GE0_BASE		0x19000000
+#define AR71XX_GE0_SIZE		0x10000
+#define AR71XX_GE1_BASE		0x1a000000
+#define AR71XX_GE1_SIZE		0x10000
 #define AR71XX_EHCI_BASE	0x1b000000
 #define AR71XX_EHCI_SIZE	0x1000
 #define AR71XX_OHCI_BASE	0x1c000000
@@ -39,6 +43,8 @@
 #define AR71XX_PLL_SIZE		0x100
 #define AR71XX_RESET_BASE	(AR71XX_APB_BASE + 0x00060000)
 #define AR71XX_RESET_SIZE	0x100
+#define AR71XX_MII_BASE		(AR71XX_APB_BASE + 0x00070000)
+#define AR71XX_MII_SIZE		0x100
 
 #define AR71XX_PCI_MEM_BASE	0x10000000
 #define AR71XX_PCI_MEM_SIZE	0x07000000
@@ -81,18 +87,39 @@
 
 #define AR933X_UART_BASE	(AR71XX_APB_BASE + 0x00020000)
 #define AR933X_UART_SIZE	0x14
+#define AR933X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define AR933X_GMAC_SIZE	0x04
 #define AR933X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define AR933X_WMAC_SIZE	0x20000
 #define AR933X_EHCI_BASE	0x1b000000
 #define AR933X_EHCI_SIZE	0x1000
 
+#define AR934X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define AR934X_GMAC_SIZE	0x14
 #define AR934X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define AR934X_WMAC_SIZE	0x20000
 #define AR934X_EHCI_BASE	0x1b000000
 #define AR934X_EHCI_SIZE	0x200
+#define AR934X_NFC_BASE		0x1b000200
+#define AR934X_NFC_SIZE		0xb8
 #define AR934X_SRIF_BASE	(AR71XX_APB_BASE + 0x00116000)
 #define AR934X_SRIF_SIZE	0x1000
 
+#define QCA953X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA953X_GMAC_SIZE	0x14
+#define QCA953X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
+#define QCA953X_WMAC_SIZE	0x20000
+#define QCA953X_EHCI_BASE	0x1b000000
+#define QCA953X_EHCI_SIZE	0x200
+#define QCA953X_SRIF_BASE	(AR71XX_APB_BASE + 0x00116000)
+#define QCA953X_SRIF_SIZE	0x1000
+
+#define QCA953X_PCI_CFG_BASE0	0x14000000
+#define QCA953X_PCI_CTRL_BASE0	(AR71XX_APB_BASE + 0x000f0000)
+#define QCA953X_PCI_CRP_BASE0	(AR71XX_APB_BASE + 0x000c0000)
+#define QCA953X_PCI_MEM_BASE0	0x10000000
+#define QCA953X_PCI_MEM_SIZE	0x02000000
+
 #define QCA955X_PCI_MEM_BASE0	0x10000000
 #define QCA955X_PCI_MEM_BASE1	0x12000000
 #define QCA955X_PCI_MEM_SIZE	0x02000000
@@ -106,11 +133,72 @@
 #define QCA955X_PCI_CTRL_BASE1	(AR71XX_APB_BASE + 0x00280000)
 #define QCA955X_PCI_CTRL_SIZE	0x100
 
+#define QCA955X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA955X_GMAC_SIZE	0x40
 #define QCA955X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
 #define QCA955X_WMAC_SIZE	0x20000
 #define QCA955X_EHCI0_BASE	0x1b000000
 #define QCA955X_EHCI1_BASE	0x1b400000
 #define QCA955X_EHCI_SIZE	0x1000
+#define QCA955X_NFC_BASE	0x1b800200
+#define QCA955X_NFC_SIZE	0xb8
+
+#define QCA956X_PCI_MEM_BASE1	0x12000000
+#define QCA956X_PCI_MEM_SIZE	0x02000000
+#define QCA956X_PCI_CFG_BASE1	0x16000000
+#define QCA956X_PCI_CFG_SIZE	0x1000
+#define QCA956X_PCI_CRP_BASE1	(AR71XX_APB_BASE + 0x00250000)
+#define QCA956X_PCI_CRP_SIZE	0x1000
+#define QCA956X_PCI_CTRL_BASE1	(AR71XX_APB_BASE + 0x00280000)
+#define QCA956X_PCI_CTRL_SIZE	0x100
+
+#define QCA956X_WMAC_BASE	(AR71XX_APB_BASE + 0x00100000)
+#define QCA956X_WMAC_SIZE	0x20000
+#define QCA956X_EHCI0_BASE	0x1b000000
+#define QCA956X_EHCI1_BASE	0x1b400000
+#define QCA956X_EHCI_SIZE	0x200
+#define QCA956X_GMAC_SGMII_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SGMII_SIZE	0x64
+#define QCA956X_PLL_BASE	(AR71XX_APB_BASE + 0x00050000)
+#define QCA956X_PLL_SIZE	0x50
+#define QCA956X_GMAC_BASE	(AR71XX_APB_BASE + 0x00070000)
+#define QCA956X_GMAC_SIZE	0x64
+
+/*
+ * Hidden Registers
+ */
+#define QCA956X_MAC_CFG_BASE		0xb9000000
+#define QCA956X_MAC_CFG_SIZE		0x64
+
+#define QCA956X_MAC_CFG1_REG		0x00
+#define QCA956X_MAC_CFG1_SOFT_RST	BIT(31)
+#define QCA956X_MAC_CFG1_RX_RST		BIT(19)
+#define QCA956X_MAC_CFG1_TX_RST		BIT(18)
+#define QCA956X_MAC_CFG1_LOOPBACK	BIT(8)
+#define QCA956X_MAC_CFG1_RX_EN		BIT(2)
+#define QCA956X_MAC_CFG1_TX_EN		BIT(0)
+
+#define QCA956X_MAC_CFG2_REG		0x04
+#define QCA956X_MAC_CFG2_IF_1000	BIT(9)
+#define QCA956X_MAC_CFG2_IF_10_100	BIT(8)
+#define QCA956X_MAC_CFG2_HUGE_FRAME_EN	BIT(5)
+#define QCA956X_MAC_CFG2_LEN_CHECK	BIT(4)
+#define QCA956X_MAC_CFG2_PAD_CRC_EN	BIT(2)
+#define QCA956X_MAC_CFG2_FDX		BIT(0)
+
+#define QCA956X_MAC_MII_MGMT_CFG_REG	0x20
+#define QCA956X_MGMT_CFG_CLK_DIV_20	0x07
+
+#define QCA956X_MAC_FIFO_CFG0_REG	0x48
+#define QCA956X_MAC_FIFO_CFG1_REG	0x4c
+#define QCA956X_MAC_FIFO_CFG2_REG	0x50
+#define QCA956X_MAC_FIFO_CFG3_REG	0x54
+#define QCA956X_MAC_FIFO_CFG4_REG	0x58
+#define QCA956X_MAC_FIFO_CFG5_REG	0x5c
+
+#define QCA956X_DAM_RESET_OFFSET	0xb90001bc
+#define QCA956X_DAM_RESET_SIZE		0x4
+#define QCA956X_INLINE_CHKSUM_ENG	BIT(27)
 
 /*
  * DDR_CTRL block
@@ -149,6 +237,12 @@
 #define AR934X_DDR_REG_FLUSH_PCIE	0xa8
 #define AR934X_DDR_REG_FLUSH_WMAC	0xac
 
+#define QCA953X_DDR_REG_FLUSH_GE0	0x9c
+#define QCA953X_DDR_REG_FLUSH_GE1	0xa0
+#define QCA953X_DDR_REG_FLUSH_USB	0xa4
+#define QCA953X_DDR_REG_FLUSH_PCIE	0xa8
+#define QCA953X_DDR_REG_FLUSH_WMAC	0xac
+
 /*
  * PLL block
  */
@@ -166,9 +260,15 @@
 #define AR71XX_AHB_DIV_SHIFT		20
 #define AR71XX_AHB_DIV_MASK		0x7
 
+#define AR71XX_ETH0_PLL_SHIFT		17
+#define AR71XX_ETH1_PLL_SHIFT		19
+
 #define AR724X_PLL_REG_CPU_CONFIG	0x00
 #define AR724X_PLL_REG_PCIE_CONFIG	0x10
 
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS	BIT(16)
+#define AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET	BIT(25)
+
 #define AR724X_PLL_FB_SHIFT		0
 #define AR724X_PLL_FB_MASK		0x3ff
 #define AR724X_PLL_REF_DIV_SHIFT	10
@@ -178,6 +278,8 @@
 #define AR724X_DDR_DIV_SHIFT		22
 #define AR724X_DDR_DIV_MASK		0x3
 
+#define AR7242_PLL_REG_ETH0_INT_CLOCK	0x2c
+
 #define AR913X_PLL_REG_CPU_CONFIG	0x00
 #define AR913X_PLL_REG_ETH_CONFIG	0x04
 #define AR913X_PLL_REG_ETH0_INT_CLOCK	0x14
@@ -190,6 +292,9 @@
 #define AR913X_AHB_DIV_SHIFT		19
 #define AR913X_AHB_DIV_MASK		0x1
 
+#define AR913X_ETH0_PLL_SHIFT		20
+#define AR913X_ETH1_PLL_SHIFT		22
+
 #define AR933X_PLL_CPU_CONFIG_REG	0x00
 #define AR933X_PLL_CLOCK_CTRL_REG	0x08
 
@@ -211,6 +316,8 @@
 #define AR934X_PLL_CPU_CONFIG_REG		0x00
 #define AR934X_PLL_DDR_CONFIG_REG		0x04
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_REG		0x08
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_REG	0x24
+#define AR934X_PLL_ETH_XMII_CONTROL_REG		0x2c
 
 #define AR934X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
 #define AR934X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
@@ -243,9 +350,52 @@
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_DDRCLK_FROM_DDRPLL	BIT(21)
 #define AR934X_PLL_CPU_DDR_CLK_CTRL_AHBCLK_FROM_DDRPLL	BIT(24)
 
+#define AR934X_PLL_SWITCH_CLOCK_CONTROL_MDIO_CLK_SEL	BIT(6)
+
+#define QCA953X_PLL_CPU_CONFIG_REG		0x00
+#define QCA953X_PLL_DDR_CONFIG_REG		0x04
+#define QCA953X_PLL_CLK_CTRL_REG		0x08
+#define QCA953X_PLL_SWITCH_CLOCK_CONTROL_REG	0x24
+#define QCA953X_PLL_ETH_XMII_CONTROL_REG	0x2c
+#define QCA953X_PLL_ETH_SGMII_CONTROL_REG	0x48
+
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
+#define QCA953X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
+#define QCA953X_PLL_CPU_CONFIG_NINT_SHIFT	6
+#define QCA953X_PLL_CPU_CONFIG_NINT_MASK	0x3f
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT	12
+#define QCA953X_PLL_CPU_CONFIG_REFDIV_MASK	0x1f
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT	19
+#define QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK	0x7
+
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT	0
+#define QCA953X_PLL_DDR_CONFIG_NFRAC_MASK	0x3ff
+#define QCA953X_PLL_DDR_CONFIG_NINT_SHIFT	10
+#define QCA953X_PLL_DDR_CONFIG_NINT_MASK	0x3f
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT	16
+#define QCA953X_PLL_DDR_CONFIG_REFDIV_MASK	0x1f
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT	23
+#define QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK	0x7
+
+#define QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS		BIT(2)
+#define QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS		BIT(3)
+#define QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS		BIT(4)
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT		5
+#define QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT		10
+#define QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT		15
+#define QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK		0x1f
+#define QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL		BIT(20)
+#define QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL		BIT(21)
+#define QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
+
 #define QCA955X_PLL_CPU_CONFIG_REG		0x00
 #define QCA955X_PLL_DDR_CONFIG_REG		0x04
 #define QCA955X_PLL_CLK_CTRL_REG		0x08
+#define QCA955X_PLL_ETH_XMII_CONTROL_REG	0x28
+#define QCA955X_PLL_ETH_SGMII_CONTROL_REG	0x48
+#define QCA955X_PLL_ETH_SGMII_SERDES_REG	0x4c
 
 #define QCA955X_PLL_CPU_CONFIG_NFRAC_SHIFT	0
 #define QCA955X_PLL_CPU_CONFIG_NFRAC_MASK	0x3f
@@ -278,6 +428,81 @@
 #define QCA955X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL		BIT(21)
 #define QCA955X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
 
+#define QCA955X_PLL_ETH_SGMII_SERDES_LOCK_DETECT	BIT(2)
+#define QCA955X_PLL_ETH_SGMII_SERDES_PLL_REFCLK		BIT(1)
+#define QCA955X_PLL_ETH_SGMII_SERDES_EN_PLL		BIT(0)
+
+#define QCA956X_PLL_CPU_CONFIG_REG			0x00
+#define QCA956X_PLL_CPU_CONFIG1_REG			0x04
+#define QCA956X_PLL_DDR_CONFIG_REG			0x08
+#define QCA956X_PLL_DDR_CONFIG1_REG			0x0c
+#define QCA956X_PLL_CLK_CTRL_REG			0x10
+#define QCA956X_PLL_SWITCH_CLOCK_CONTROL_REG		0x28
+#define QCA956X_PLL_ETH_XMII_CONTROL_REG		0x30
+#define QCA956X_PLL_ETH_SGMII_SERDES_REG		0x4c
+
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT		12
+#define QCA956X_PLL_CPU_CONFIG_REFDIV_MASK		0x1f
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT		19
+#define QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK		0x7
+
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT		0
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK		0x1f
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT		5
+#define QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK		0x1fff
+#define QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT		18
+#define QCA956X_PLL_CPU_CONFIG1_NINT_MASK		0x1ff
+
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT		16
+#define QCA956X_PLL_DDR_CONFIG_REFDIV_MASK		0x1f
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT		23
+#define QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK		0x7
+
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT		0
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK		0x1f
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT		5
+#define QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK		0x1fff
+#define QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT		18
+#define QCA956X_PLL_DDR_CONFIG1_NINT_MASK		0x1ff
+
+#define QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS		BIT(2)
+#define QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS		BIT(3)
+#define QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS		BIT(4)
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT		5
+#define QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT		10
+#define QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT		15
+#define QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK		0x1f
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL	BIT(20)
+#define QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL	BIT(21)
+#define QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL		BIT(24)
+
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_I2C_CLK_SELB		BIT(5)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_1		BIT(6)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_UART1_CLK_SEL		BIT(7)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_SHIFT 8
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_USB_REFCLK_FREQ_SEL_MASK	 0xf
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EN_PLL_TOP		BIT(12)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL0_2		BIT(13)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_1		BIT(14)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_MDIO_CLK_SEL1_2		BIT(15)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCH_FUNC_TST_MODE	BIT(16)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_EEE_ENABLE		BIT(17)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_OEN_CLK125M_PLL		BIT(18)
+#define QCA956X_PLL_SWITCH_CLOCK_SPARE_SWITCHCLK_SEL		BIT(19)
+
+#define QCA956X_PLL_ETH_XMII_TX_INVERT			BIT(1)
+#define QCA956X_PLL_ETH_XMII_GIGE			BIT(25)
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_SHIFT		28
+#define QCA956X_PLL_ETH_XMII_RX_DELAY_MASK		0x3
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_SHIFT		26
+#define QCA956X_PLL_ETH_XMII_TX_DELAY_MASK		3
+
+#define QCA956X_PLL_ETH_SGMII_SERDES_LOCK_DETECT		BIT(2)
+#define QCA956X_PLL_ETH_SGMII_SERDES_PLL_REFCLK			BIT(1)
+#define QCA956X_PLL_ETH_SGMII_SERDES_EN_PLL			BIT(0)
+
 /*
  * USB_CONFIG block
  */
@@ -317,10 +542,19 @@
 #define AR934X_RESET_REG_BOOTSTRAP		0xb0
 #define AR934X_RESET_REG_PCIE_WMAC_INT_STATUS	0xac
 
+#define QCA953X_RESET_REG_RESET_MODULE		0x1c
+#define QCA953X_RESET_REG_BOOTSTRAP		0xb0
+#define QCA953X_RESET_REG_PCIE_WMAC_INT_STATUS	0xac
+
 #define QCA955X_RESET_REG_RESET_MODULE		0x1c
 #define QCA955X_RESET_REG_BOOTSTRAP		0xb0
 #define QCA955X_RESET_REG_EXT_INT_STATUS	0xac
 
+#define QCA956X_RESET_REG_RESET_MODULE		0x1c
+#define QCA956X_RESET_REG_BOOTSTRAP		0xb0
+#define QCA956X_RESET_REG_EXT_INT_STATUS	0xac
+
+#define MISC_INT_MIPS_SI_TIMERINT_MASK	BIT(28)
 #define MISC_INT_ETHSW			BIT(12)
 #define MISC_INT_TIMER4			BIT(10)
 #define MISC_INT_TIMER3			BIT(9)
@@ -370,16 +604,123 @@
 #define AR913X_RESET_USB_HOST		BIT(5)
 #define AR913X_RESET_USB_PHY		BIT(4)
 
+#define AR933X_RESET_GE1_MDIO		BIT(23)
+#define AR933X_RESET_GE0_MDIO		BIT(22)
+#define AR933X_RESET_GE1_MAC		BIT(13)
 #define AR933X_RESET_WMAC		BIT(11)
+#define AR933X_RESET_GE0_MAC		BIT(9)
 #define AR933X_RESET_USB_HOST		BIT(5)
 #define AR933X_RESET_USB_PHY		BIT(4)
 #define AR933X_RESET_USBSUS_OVERRIDE	BIT(3)
 
+#define AR934X_RESET_HOST		BIT(31)
+#define AR934X_RESET_SLIC		BIT(30)
+#define AR934X_RESET_HDMA		BIT(29)
+#define AR934X_RESET_EXTERNAL		BIT(28)
+#define AR934X_RESET_RTC		BIT(27)
+#define AR934X_RESET_PCIE_EP_INT	BIT(26)
+#define AR934X_RESET_CHKSUM_ACC		BIT(25)
+#define AR934X_RESET_FULL_CHIP		BIT(24)
+#define AR934X_RESET_GE1_MDIO		BIT(23)
+#define AR934X_RESET_GE0_MDIO		BIT(22)
+#define AR934X_RESET_CPU_NMI		BIT(21)
+#define AR934X_RESET_CPU_COLD		BIT(20)
+#define AR934X_RESET_HOST_RESET_INT	BIT(19)
+#define AR934X_RESET_PCIE_EP		BIT(18)
+#define AR934X_RESET_UART1		BIT(17)
+#define AR934X_RESET_DDR		BIT(16)
+#define AR934X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define AR934X_RESET_NANDF		BIT(14)
+#define AR934X_RESET_GE1_MAC		BIT(13)
+#define AR934X_RESET_ETH_SWITCH_ANALOG	BIT(12)
 #define AR934X_RESET_USB_PHY_ANALOG	BIT(11)
+#define AR934X_RESET_HOST_DMA_INT	BIT(10)
+#define AR934X_RESET_GE0_MAC		BIT(9)
+#define AR934X_RESET_ETH_SWITCH		BIT(8)
+#define AR934X_RESET_PCIE_PHY		BIT(7)
+#define AR934X_RESET_PCIE		BIT(6)
 #define AR934X_RESET_USB_HOST		BIT(5)
 #define AR934X_RESET_USB_PHY		BIT(4)
 #define AR934X_RESET_USBSUS_OVERRIDE	BIT(3)
-
+#define AR934X_RESET_LUT		BIT(2)
+#define AR934X_RESET_MBOX		BIT(1)
+#define AR934X_RESET_I2S		BIT(0)
+
+#define QCA953X_RESET_USB_EXT_PWR	BIT(29)
+#define QCA953X_RESET_EXTERNAL		BIT(28)
+#define QCA953X_RESET_RTC		BIT(27)
+#define QCA953X_RESET_FULL_CHIP		BIT(24)
+#define QCA953X_RESET_GE1_MDIO		BIT(23)
+#define QCA953X_RESET_GE0_MDIO		BIT(22)
+#define QCA953X_RESET_CPU_NMI		BIT(21)
+#define QCA953X_RESET_CPU_COLD		BIT(20)
+#define QCA953X_RESET_DDR		BIT(16)
+#define QCA953X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA953X_RESET_GE1_MAC		BIT(13)
+#define QCA953X_RESET_ETH_SWITCH_ANALOG	BIT(12)
+#define QCA953X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA953X_RESET_GE0_MAC		BIT(9)
+#define QCA953X_RESET_ETH_SWITCH	BIT(8)
+#define QCA953X_RESET_PCIE_PHY		BIT(7)
+#define QCA953X_RESET_PCIE		BIT(6)
+#define QCA953X_RESET_USB_HOST		BIT(5)
+#define QCA953X_RESET_USB_PHY		BIT(4)
+#define QCA953X_RESET_USBSUS_OVERRIDE	BIT(3)
+
+#define QCA955X_RESET_HOST		BIT(31)
+#define QCA955X_RESET_SLIC		BIT(30)
+#define QCA955X_RESET_HDMA		BIT(29)
+#define QCA955X_RESET_EXTERNAL		BIT(28)
+#define QCA955X_RESET_RTC		BIT(27)
+#define QCA955X_RESET_PCIE_EP_INT	BIT(26)
+#define QCA955X_RESET_CHKSUM_ACC	BIT(25)
+#define QCA955X_RESET_FULL_CHIP		BIT(24)
+#define QCA955X_RESET_GE1_MDIO		BIT(23)
+#define QCA955X_RESET_GE0_MDIO		BIT(22)
+#define QCA955X_RESET_CPU_NMI		BIT(21)
+#define QCA955X_RESET_CPU_COLD		BIT(20)
+#define QCA955X_RESET_HOST_RESET_INT	BIT(19)
+#define QCA955X_RESET_PCIE_EP		BIT(18)
+#define QCA955X_RESET_UART1		BIT(17)
+#define QCA955X_RESET_DDR		BIT(16)
+#define QCA955X_RESET_USB_PHY_PLL_PWD_EXT BIT(15)
+#define QCA955X_RESET_NANDF		BIT(14)
+#define QCA955X_RESET_GE1_MAC		BIT(13)
+#define QCA955X_RESET_SGMII_ANALOG	BIT(12)
+#define QCA955X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA955X_RESET_HOST_DMA_INT	BIT(10)
+#define QCA955X_RESET_GE0_MAC		BIT(9)
+#define QCA955X_RESET_SGMII		BIT(8)
+#define QCA955X_RESET_PCIE_PHY		BIT(7)
+#define QCA955X_RESET_PCIE		BIT(6)
+#define QCA955X_RESET_USB_HOST		BIT(5)
+#define QCA955X_RESET_USB_PHY		BIT(4)
+#define QCA955X_RESET_USBSUS_OVERRIDE	BIT(3)
+#define QCA955X_RESET_LUT		BIT(2)
+#define QCA955X_RESET_MBOX		BIT(1)
+#define QCA955X_RESET_I2S		BIT(0)
+
+#define QCA956X_RESET_EXTERNAL		BIT(28)
+#define QCA956X_RESET_FULL_CHIP		BIT(24)
+#define QCA956X_RESET_GE1_MDIO		BIT(23)
+#define QCA956X_RESET_GE0_MDIO		BIT(22)
+#define QCA956X_RESET_CPU_NMI		BIT(21)
+#define QCA956X_RESET_CPU_COLD		BIT(20)
+#define QCA956X_RESET_DMA		BIT(19)
+#define QCA956X_RESET_DDR		BIT(16)
+#define QCA956X_RESET_GE1_MAC		BIT(13)
+#define QCA956X_RESET_SGMII_ANALOG	BIT(12)
+#define QCA956X_RESET_USB_PHY_ANALOG	BIT(11)
+#define QCA956X_RESET_GE0_MAC		BIT(9)
+#define QCA956X_RESET_SGMII		BIT(8)
+#define QCA956X_RESET_USB_HOST		BIT(5)
+#define QCA956X_RESET_USB_PHY		BIT(4)
+#define QCA956X_RESET_USBSUS_OVERRIDE	BIT(3)
+#define QCA956X_RESET_SWITCH_ANALOG	BIT(2)
+#define QCA956X_RESET_SWITCH		BIT(0)
+
+#define AR933X_BOOTSTRAP_MDIO_GPIO_EN	BIT(18)
+#define AR933X_BOOTSTRAP_EEPBUSY	BIT(4)
 #define AR933X_BOOTSTRAP_REF_CLK_40	BIT(0)
 
 #define AR934X_BOOTSTRAP_SW_OPTION8	BIT(23)
@@ -398,8 +739,17 @@
 #define AR934X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
 #define AR934X_BOOTSTRAP_DDR1		BIT(0)
 
+#define QCA953X_BOOTSTRAP_SW_OPTION2	BIT(12)
+#define QCA953X_BOOTSTRAP_SW_OPTION1	BIT(11)
+#define QCA953X_BOOTSTRAP_EJTAG_MODE	BIT(5)
+#define QCA953X_BOOTSTRAP_REF_CLK_40	BIT(4)
+#define QCA953X_BOOTSTRAP_SDRAM_DISABLED BIT(1)
+#define QCA953X_BOOTSTRAP_DDR1		BIT(0)
+
 #define QCA955X_BOOTSTRAP_REF_CLK_40	BIT(4)
 
+#define QCA956X_BOOTSTRAP_REF_CLK_40	BIT(2)
+
 #define AR934X_PCIE_WMAC_INT_WMAC_MISC		BIT(0)
 #define AR934X_PCIE_WMAC_INT_WMAC_TX		BIT(1)
 #define AR934X_PCIE_WMAC_INT_WMAC_RXLP		BIT(2)
@@ -418,6 +768,24 @@
 	 AR934X_PCIE_WMAC_INT_PCIE_RC1 | AR934X_PCIE_WMAC_INT_PCIE_RC2 | \
 	 AR934X_PCIE_WMAC_INT_PCIE_RC3)
 
+#define QCA953X_PCIE_WMAC_INT_WMAC_MISC		BIT(0)
+#define QCA953X_PCIE_WMAC_INT_WMAC_TX		BIT(1)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXLP		BIT(2)
+#define QCA953X_PCIE_WMAC_INT_WMAC_RXHP		BIT(3)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC		BIT(4)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC0		BIT(5)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC1		BIT(6)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC2		BIT(7)
+#define QCA953X_PCIE_WMAC_INT_PCIE_RC3		BIT(8)
+#define QCA953X_PCIE_WMAC_INT_WMAC_ALL \
+	(QCA953X_PCIE_WMAC_INT_WMAC_MISC | QCA953X_PCIE_WMAC_INT_WMAC_TX | \
+	 QCA953X_PCIE_WMAC_INT_WMAC_RXLP | QCA953X_PCIE_WMAC_INT_WMAC_RXHP)
+
+#define QCA953X_PCIE_WMAC_INT_PCIE_ALL \
+	(QCA953X_PCIE_WMAC_INT_PCIE_RC | QCA953X_PCIE_WMAC_INT_PCIE_RC0 | \
+	 QCA953X_PCIE_WMAC_INT_PCIE_RC1 | QCA953X_PCIE_WMAC_INT_PCIE_RC2 | \
+	 QCA953X_PCIE_WMAC_INT_PCIE_RC3)
+
 #define QCA955X_EXT_INT_WMAC_MISC		BIT(0)
 #define QCA955X_EXT_INT_WMAC_TX			BIT(1)
 #define QCA955X_EXT_INT_WMAC_RXLP		BIT(2)
@@ -449,6 +817,37 @@
 	 QCA955X_EXT_INT_PCIE_RC2_INT1 | QCA955X_EXT_INT_PCIE_RC2_INT2 | \
 	 QCA955X_EXT_INT_PCIE_RC2_INT3)
 
+#define QCA956X_EXT_INT_WMAC_MISC		BIT(0)
+#define QCA956X_EXT_INT_WMAC_TX			BIT(1)
+#define QCA956X_EXT_INT_WMAC_RXLP		BIT(2)
+#define QCA956X_EXT_INT_WMAC_RXHP		BIT(3)
+#define QCA956X_EXT_INT_PCIE_RC1		BIT(4)
+#define QCA956X_EXT_INT_PCIE_RC1_INT0		BIT(5)
+#define QCA956X_EXT_INT_PCIE_RC1_INT1		BIT(6)
+#define QCA956X_EXT_INT_PCIE_RC1_INT2		BIT(7)
+#define QCA956X_EXT_INT_PCIE_RC1_INT3		BIT(8)
+#define QCA956X_EXT_INT_PCIE_RC2		BIT(12)
+#define QCA956X_EXT_INT_PCIE_RC2_INT0		BIT(13)
+#define QCA956X_EXT_INT_PCIE_RC2_INT1		BIT(14)
+#define QCA956X_EXT_INT_PCIE_RC2_INT2		BIT(15)
+#define QCA956X_EXT_INT_PCIE_RC2_INT3		BIT(16)
+#define QCA956X_EXT_INT_USB1			BIT(24)
+#define QCA956X_EXT_INT_USB2			BIT(28)
+
+#define QCA956X_EXT_INT_WMAC_ALL \
+	(QCA956X_EXT_INT_WMAC_MISC | QCA956X_EXT_INT_WMAC_TX | \
+	 QCA956X_EXT_INT_WMAC_RXLP | QCA956X_EXT_INT_WMAC_RXHP)
+
+#define QCA956X_EXT_INT_PCIE_RC1_ALL \
+	(QCA956X_EXT_INT_PCIE_RC1 | QCA956X_EXT_INT_PCIE_RC1_INT0 | \
+	 QCA956X_EXT_INT_PCIE_RC1_INT1 | QCA956X_EXT_INT_PCIE_RC1_INT2 | \
+	 QCA956X_EXT_INT_PCIE_RC1_INT3)
+
+#define QCA956X_EXT_INT_PCIE_RC2_ALL \
+	(QCA956X_EXT_INT_PCIE_RC2 | QCA956X_EXT_INT_PCIE_RC2_INT0 | \
+	 QCA956X_EXT_INT_PCIE_RC2_INT1 | QCA956X_EXT_INT_PCIE_RC2_INT2 | \
+	 QCA956X_EXT_INT_PCIE_RC2_INT3)
+
 #define REV_ID_MAJOR_MASK		0xfff0
 #define REV_ID_MAJOR_AR71XX		0x00a0
 #define REV_ID_MAJOR_AR913X		0x00b0
@@ -460,8 +859,12 @@
 #define REV_ID_MAJOR_AR9341		0x0120
 #define REV_ID_MAJOR_AR9342		0x1120
 #define REV_ID_MAJOR_AR9344		0x2120
+#define REV_ID_MAJOR_QCA9533		0x0140
+#define REV_ID_MAJOR_QCA9533_V2		0x0160
 #define REV_ID_MAJOR_QCA9556		0x0130
 #define REV_ID_MAJOR_QCA9558		0x1130
+#define REV_ID_MAJOR_TP9343		0x0150
+#define REV_ID_MAJOR_QCA956X		0x1150
 
 #define AR71XX_REV_ID_MINOR_MASK	0x3
 #define AR71XX_REV_ID_MINOR_AR7130	0x0
@@ -482,8 +885,12 @@
 
 #define AR934X_REV_ID_REVISION_MASK	0xf
 
+#define QCA953X_REV_ID_REVISION_MASK	0xf
+
 #define QCA955X_REV_ID_REVISION_MASK	0xf
 
+#define QCA956X_REV_ID_REVISION_MASK	0xf
+
 /*
  * SPI block
  */
@@ -521,15 +928,63 @@
 #define AR71XX_GPIO_REG_INT_ENABLE	0x24
 #define AR71XX_GPIO_REG_FUNC		0x28
 
+#define AR934X_GPIO_REG_OUT_FUNC0	0x2c
+#define AR934X_GPIO_REG_OUT_FUNC1	0x30
+#define AR934X_GPIO_REG_OUT_FUNC2	0x34
+#define AR934X_GPIO_REG_OUT_FUNC3	0x38
+#define AR934X_GPIO_REG_OUT_FUNC4	0x3c
+#define AR934X_GPIO_REG_OUT_FUNC5	0x40
 #define AR934X_GPIO_REG_FUNC		0x6c
 
+#define QCA953X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA953X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA953X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA953X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA953X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA953X_GPIO_REG_IN_ENABLE0	0x44
+#define QCA953X_GPIO_REG_FUNC		0x6c
+
+#define QCA953X_GPIO_OUT_MUX_SPI_CS1		10
+#define QCA953X_GPIO_OUT_MUX_SPI_CS2		11
+#define QCA953X_GPIO_OUT_MUX_SPI_CS0		9
+#define QCA953X_GPIO_OUT_MUX_SPI_CLK		8
+#define QCA953X_GPIO_OUT_MUX_SPI_MOSI		12
+#define QCA953X_GPIO_OUT_MUX_LED_LINK1		41
+#define QCA953X_GPIO_OUT_MUX_LED_LINK2		42
+#define QCA953X_GPIO_OUT_MUX_LED_LINK3		43
+#define QCA953X_GPIO_OUT_MUX_LED_LINK4		44
+#define QCA953X_GPIO_OUT_MUX_LED_LINK5		45
+
+#define QCA955X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA955X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA955X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA955X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA955X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA955X_GPIO_REG_OUT_FUNC5	0x40
+#define QCA955X_GPIO_REG_FUNC		0x6c
+
+#define QCA956X_GPIO_REG_OUT_FUNC0	0x2c
+#define QCA956X_GPIO_REG_OUT_FUNC1	0x30
+#define QCA956X_GPIO_REG_OUT_FUNC2	0x34
+#define QCA956X_GPIO_REG_OUT_FUNC3	0x38
+#define QCA956X_GPIO_REG_OUT_FUNC4	0x3c
+#define QCA956X_GPIO_REG_OUT_FUNC5	0x40
+#define QCA956X_GPIO_REG_IN_ENABLE0	0x44
+#define QCA956X_GPIO_REG_IN_ENABLE3	0x50
+#define QCA956X_GPIO_REG_FUNC		0x6c
+
+#define QCA956X_GPIO_OUT_MUX_GE0_MDO	32
+#define QCA956X_GPIO_OUT_MUX_GE0_MDC	33
+
 #define AR71XX_GPIO_COUNT		16
 #define AR7240_GPIO_COUNT		18
 #define AR7241_GPIO_COUNT		20
 #define AR913X_GPIO_COUNT		22
 #define AR933X_GPIO_COUNT		30
 #define AR934X_GPIO_COUNT		23
+#define QCA953X_GPIO_COUNT		18
 #define QCA955X_GPIO_COUNT		24
+#define QCA956X_GPIO_COUNT		23
 
 /*
  * SRIF block
@@ -552,4 +1007,318 @@
 #define AR934X_SRIF_DPLL2_OUTDIV_SHIFT	13
 #define AR934X_SRIF_DPLL2_OUTDIV_MASK	0x7
 
+#define QCA953X_SRIF_CPU_DPLL1_REG	0x1c0
+#define QCA953X_SRIF_CPU_DPLL2_REG	0x1c4
+#define QCA953X_SRIF_CPU_DPLL3_REG	0x1c8
+
+#define QCA953X_SRIF_DDR_DPLL1_REG	0x240
+#define QCA953X_SRIF_DDR_DPLL2_REG	0x244
+#define QCA953X_SRIF_DDR_DPLL3_REG	0x248
+
+#define QCA953X_SRIF_DPLL1_REFDIV_SHIFT	27
+#define QCA953X_SRIF_DPLL1_REFDIV_MASK	0x1f
+#define QCA953X_SRIF_DPLL1_NINT_SHIFT	18
+#define QCA953X_SRIF_DPLL1_NINT_MASK	0x1ff
+#define QCA953X_SRIF_DPLL1_NFRAC_MASK	0x0003ffff
+
+#define QCA953X_SRIF_DPLL2_LOCAL_PLL	BIT(30)
+#define QCA953X_SRIF_DPLL2_OUTDIV_SHIFT	13
+#define QCA953X_SRIF_DPLL2_OUTDIV_MASK	0x7
+
+#define AR71XX_GPIO_FUNC_STEREO_EN		BIT(17)
+#define AR71XX_GPIO_FUNC_SLIC_EN		BIT(16)
+#define AR71XX_GPIO_FUNC_SPI_CS2_EN		BIT(13)
+#define AR71XX_GPIO_FUNC_SPI_CS1_EN		BIT(12)
+#define AR71XX_GPIO_FUNC_UART_EN		BIT(8)
+#define AR71XX_GPIO_FUNC_USB_OC_EN		BIT(4)
+#define AR71XX_GPIO_FUNC_USB_CLK_EN		BIT(0)
+
+#define AR724X_GPIO_FUNC_GE0_MII_CLK_EN		BIT(19)
+#define AR724X_GPIO_FUNC_SPI_EN			BIT(18)
+#define AR724X_GPIO_FUNC_SPI_CS_EN2		BIT(14)
+#define AR724X_GPIO_FUNC_SPI_CS_EN1		BIT(13)
+#define AR724X_GPIO_FUNC_CLK_OBS5_EN		BIT(12)
+#define AR724X_GPIO_FUNC_CLK_OBS4_EN		BIT(11)
+#define AR724X_GPIO_FUNC_CLK_OBS3_EN		BIT(10)
+#define AR724X_GPIO_FUNC_CLK_OBS2_EN		BIT(9)
+#define AR724X_GPIO_FUNC_CLK_OBS1_EN		BIT(8)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED4_EN	BIT(7)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED3_EN	BIT(6)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED2_EN	BIT(5)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED1_EN	BIT(4)
+#define AR724X_GPIO_FUNC_ETH_SWITCH_LED0_EN	BIT(3)
+#define AR724X_GPIO_FUNC_UART_RTS_CTS_EN	BIT(2)
+#define AR724X_GPIO_FUNC_UART_EN		BIT(1)
+#define AR724X_GPIO_FUNC_JTAG_DISABLE		BIT(0)
+
+#define AR913X_GPIO_FUNC_WMAC_LED_EN		BIT(22)
+#define AR913X_GPIO_FUNC_EXP_PORT_CS_EN		BIT(21)
+#define AR913X_GPIO_FUNC_I2S_REFCLKEN		BIT(20)
+#define AR913X_GPIO_FUNC_I2S_MCKEN		BIT(19)
+#define AR913X_GPIO_FUNC_I2S1_EN		BIT(18)
+#define AR913X_GPIO_FUNC_I2S0_EN		BIT(17)
+#define AR913X_GPIO_FUNC_SLIC_EN		BIT(16)
+#define AR913X_GPIO_FUNC_UART_RTSCTS_EN		BIT(9)
+#define AR913X_GPIO_FUNC_UART_EN		BIT(8)
+#define AR913X_GPIO_FUNC_USB_CLK_EN		BIT(4)
+
+#define AR933X_GPIO_FUNC_SPDIF2TCK		BIT(31)
+#define AR933X_GPIO_FUNC_SPDIF_EN		BIT(30)
+#define AR933X_GPIO_FUNC_I2SO_22_18_EN		BIT(29)
+#define AR933X_GPIO_FUNC_I2S_MCK_EN		BIT(27)
+#define AR933X_GPIO_FUNC_I2SO_EN		BIT(26)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_DUPL	BIT(25)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_COLL	BIT(24)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED_ACT	BIT(23)
+#define AR933X_GPIO_FUNC_SPI_EN			BIT(18)
+#define AR933X_GPIO_FUNC_SPI_CS_EN2		BIT(14)
+#define AR933X_GPIO_FUNC_SPI_CS_EN1		BIT(13)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED4_EN	BIT(7)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED3_EN	BIT(6)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED2_EN	BIT(5)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED1_EN	BIT(4)
+#define AR933X_GPIO_FUNC_ETH_SWITCH_LED0_EN	BIT(3)
+#define AR933X_GPIO_FUNC_UART_RTS_CTS_EN	BIT(2)
+#define AR933X_GPIO_FUNC_UART_EN		BIT(1)
+#define AR933X_GPIO_FUNC_JTAG_DISABLE		BIT(0)
+
+#define AR934X_GPIO_FUNC_CLK_OBS7_EN		BIT(9)
+#define AR934X_GPIO_FUNC_CLK_OBS6_EN		BIT(8)
+#define AR934X_GPIO_FUNC_CLK_OBS5_EN		BIT(7)
+#define AR934X_GPIO_FUNC_CLK_OBS4_EN		BIT(6)
+#define AR934X_GPIO_FUNC_CLK_OBS3_EN		BIT(5)
+#define AR934X_GPIO_FUNC_CLK_OBS2_EN		BIT(4)
+#define AR934X_GPIO_FUNC_CLK_OBS1_EN		BIT(3)
+#define AR934X_GPIO_FUNC_CLK_OBS0_EN		BIT(2)
+#define AR934X_GPIO_FUNC_JTAG_DISABLE		BIT(1)
+
+#define AR934X_GPIO_OUT_GPIO		0
+#define AR934X_GPIO_OUT_SPI_CS1	7
+#define AR934X_GPIO_OUT_LED_LINK0	41
+#define AR934X_GPIO_OUT_LED_LINK1	42
+#define AR934X_GPIO_OUT_LED_LINK2	43
+#define AR934X_GPIO_OUT_LED_LINK3	44
+#define AR934X_GPIO_OUT_LED_LINK4	45
+#define AR934X_GPIO_OUT_EXT_LNA0	46
+#define AR934X_GPIO_OUT_EXT_LNA1	47
+
+#define QCA955X_GPIO_FUNC_CLK_OBS7_EN		BIT(9)
+#define QCA955X_GPIO_FUNC_CLK_OBS6_EN		BIT(8)
+#define QCA955X_GPIO_FUNC_CLK_OBS5_EN		BIT(7)
+#define QCA955X_GPIO_FUNC_CLK_OBS4_EN		BIT(6)
+#define QCA955X_GPIO_FUNC_CLK_OBS3_EN		BIT(5)
+#define QCA955X_GPIO_FUNC_CLK_OBS2_EN		BIT(4)
+#define QCA955X_GPIO_FUNC_CLK_OBS1_EN		BIT(3)
+#define QCA955X_GPIO_FUNC_JTAG_DISABLE		BIT(1)
+
+#define QCA955X_GPIO_OUT_GPIO		0
+#define QCA955X_MII_EXT_MDI		1
+#define QCA955X_SLIC_DATA_OUT		3
+#define QCA955X_SLIC_PCM_FS		4
+#define QCA955X_SLIC_PCM_CLK		5
+#define QCA955X_SPI_CLK			8
+#define QCA955X_SPI_CS_0		9
+#define QCA955X_SPI_CS_1		10
+#define QCA955X_SPI_CS_2		11
+#define QCA955X_SPI_MISO		12
+#define QCA955X_I2S_CLK			13
+#define QCA955X_I2S_WS			14
+#define QCA955X_I2S_SD			15
+#define QCA955X_I2S_MCK			16
+#define QCA955X_SPDIF_OUT		17
+#define QCA955X_UART1_TD		18
+#define QCA955X_UART1_RTS		19
+#define QCA955X_UART1_RD		20
+#define QCA955X_UART1_CTS		21
+#define QCA955X_UART0_SOUT		22
+#define QCA955X_SPDIF2_OUT		23
+#define QCA955X_LED_SGMII_SPEED0	24
+#define QCA955X_LED_SGMII_SPEED1	25
+#define QCA955X_LED_SGMII_DUPLEX	26
+#define QCA955X_LED_SGMII_LINK_UP	27
+#define QCA955X_SGMII_SPEED0_INVERT	28
+#define QCA955X_SGMII_SPEED1_INVERT	29
+#define QCA955X_SGMII_DUPLEX_INVERT	30
+#define QCA955X_SGMII_LINK_UP_INVERT	31
+#define QCA955X_GE1_MII_MDO		32
+#define QCA955X_GE1_MII_MDC		33
+#define QCA955X_SWCOM2			38
+#define QCA955X_SWCOM3			39
+#define QCA955X_MAC2_GPIO		40
+#define QCA955X_MAC3_GPIO		41
+#define QCA955X_ATT_LED			42
+#define QCA955X_PWR_LED			43
+#define QCA955X_TX_FRAME		44
+#define QCA955X_RX_CLEAR_EXTERNAL	45
+#define QCA955X_LED_NETWORK_EN		46
+#define QCA955X_LED_POWER_EN		47
+#define QCA955X_WMAC_GLUE_WOW		68
+#define QCA955X_RX_CLEAR_EXTENSION	70
+#define QCA955X_CP_NAND_CS1		73
+#define QCA955X_USB_SUSPEND		74
+#define QCA955X_ETH_TX_ERR		75
+#define QCA955X_DDR_DQ_OE		76
+#define QCA955X_CLKREQ_N_EP		77
+#define QCA955X_CLKREQ_N_RC		78
+#define QCA955X_CLK_OBS0		79
+#define QCA955X_CLK_OBS1		80
+#define QCA955X_CLK_OBS2		81
+#define QCA955X_CLK_OBS3		82
+#define QCA955X_CLK_OBS4		83
+#define QCA955X_CLK_OBS5		84
+
+/*
+ * MII_CTRL block
+ */
+#define AR71XX_MII_REG_MII0_CTRL	0x00
+#define AR71XX_MII_REG_MII1_CTRL	0x04
+
+#define AR71XX_MII_CTRL_IF_MASK		3
+#define AR71XX_MII_CTRL_SPEED_SHIFT	4
+#define AR71XX_MII_CTRL_SPEED_MASK	3
+#define AR71XX_MII_CTRL_SPEED_10	0
+#define AR71XX_MII_CTRL_SPEED_100	1
+#define AR71XX_MII_CTRL_SPEED_1000	2
+
+#define AR71XX_MII0_CTRL_IF_GMII	0
+#define AR71XX_MII0_CTRL_IF_MII		1
+#define AR71XX_MII0_CTRL_IF_RGMII	2
+#define AR71XX_MII0_CTRL_IF_RMII	3
+
+#define AR71XX_MII1_CTRL_IF_RGMII	0
+#define AR71XX_MII1_CTRL_IF_RMII	1
+
+/*
+ * AR933X GMAC interface
+ */
+#define AR933X_GMAC_REG_ETH_CFG		0x00
+
+#define AR933X_ETH_CFG_RGMII_GE0	BIT(0)
+#define AR933X_ETH_CFG_MII_GE0		BIT(1)
+#define AR933X_ETH_CFG_GMII_GE0		BIT(2)
+#define AR933X_ETH_CFG_MII_GE0_MASTER	BIT(3)
+#define AR933X_ETH_CFG_MII_GE0_SLAVE	BIT(4)
+#define AR933X_ETH_CFG_MII_GE0_ERR_EN	BIT(5)
+#define AR933X_ETH_CFG_SW_PHY_SWAP	BIT(7)
+#define AR933X_ETH_CFG_SW_PHY_ADDR_SWAP	BIT(8)
+#define AR933X_ETH_CFG_RMII_GE0		BIT(9)
+#define AR933X_ETH_CFG_RMII_GE0_SPD_10	0
+#define AR933X_ETH_CFG_RMII_GE0_SPD_100	BIT(10)
+
+/*
+ * AR934X GMAC Interface
+ */
+#define AR934X_GMAC_REG_ETH_CFG		0x00
+
+#define AR934X_ETH_CFG_RGMII_GMAC0	BIT(0)
+#define AR934X_ETH_CFG_MII_GMAC0	BIT(1)
+#define AR934X_ETH_CFG_GMII_GMAC0	BIT(2)
+#define AR934X_ETH_CFG_MII_GMAC0_MASTER	BIT(3)
+#define AR934X_ETH_CFG_MII_GMAC0_SLAVE	BIT(4)
+#define AR934X_ETH_CFG_MII_GMAC0_ERR_EN	BIT(5)
+#define AR934X_ETH_CFG_SW_ONLY_MODE	BIT(6)
+#define AR934X_ETH_CFG_SW_PHY_SWAP	BIT(7)
+#define AR934X_ETH_CFG_SW_APB_ACCESS	BIT(9)
+#define AR934X_ETH_CFG_RMII_GMAC0	BIT(10)
+#define AR933X_ETH_CFG_MII_CNTL_SPEED	BIT(11)
+#define AR934X_ETH_CFG_RMII_GMAC0_MASTER BIT(12)
+#define AR933X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+#define AR934X_ETH_CFG_RXD_DELAY        BIT(14)
+#define AR934X_ETH_CFG_RXD_DELAY_MASK   0x3
+#define AR934X_ETH_CFG_RXD_DELAY_SHIFT  14
+#define AR934X_ETH_CFG_RDV_DELAY        BIT(16)
+#define AR934X_ETH_CFG_RDV_DELAY_MASK   0x3
+#define AR934X_ETH_CFG_RDV_DELAY_SHIFT  16
+
+/*
+ * QCA953X GMAC Interface
+ */
+#define QCA953X_GMAC_REG_ETH_CFG		0x00
+
+#define QCA953X_ETH_CFG_SW_ONLY_MODE		BIT(6)
+#define QCA953X_ETH_CFG_SW_PHY_SWAP		BIT(7)
+#define QCA953X_ETH_CFG_SW_APB_ACCESS		BIT(9)
+#define QCA953X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+
+/*
+ * QCA955X GMAC Interface
+ */
+
+#define QCA955X_GMAC_REG_ETH_CFG	0x00
+#define QCA955X_GMAC_REG_SGMII_SERDES	0x18
+
+#define QCA955X_ETH_CFG_RGMII_EN	BIT(0)
+#define QCA955X_ETH_CFG_MII_GE0		BIT(1)
+#define QCA955X_ETH_CFG_GMII_GE0	BIT(2)
+#define QCA955X_ETH_CFG_MII_GE0_MASTER	BIT(3)
+#define QCA955X_ETH_CFG_MII_GE0_SLAVE	BIT(4)
+#define QCA955X_ETH_CFG_GE0_ERR_EN	BIT(5)
+#define QCA955X_ETH_CFG_GE0_SGMII	BIT(6)
+#define QCA955X_ETH_CFG_RMII_GE0	BIT(10)
+#define QCA955X_ETH_CFG_MII_CNTL_SPEED	BIT(11)
+#define QCA955X_ETH_CFG_RMII_GE0_MASTER	BIT(12)
+#define QCA955X_ETH_CFG_RXD_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_RXD_DELAY_SHIFT	14
+#define QCA955X_ETH_CFG_RDV_DELAY	BIT(16)
+#define QCA955X_ETH_CFG_RDV_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_RDV_DELAY_SHIFT	16
+#define QCA955X_ETH_CFG_TXD_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_TXD_DELAY_SHIFT	18
+#define QCA955X_ETH_CFG_TXE_DELAY_MASK	0x3
+#define QCA955X_ETH_CFG_TXE_DELAY_SHIFT	20
+
+#define QCA955X_SGMII_SERDES_LOCK_DETECT_STATUS	BIT(15)
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA955X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+/*
+ * QCA956X GMAC Interface
+ */
+
+#define QCA956X_GMAC_REG_ETH_CFG	0x00
+#define QCA956X_GMAC_REG_SGMII_RESET	0x14
+#define QCA956X_GMAC_REG_SGMII_SERDES	0x18
+#define QCA956X_GMAC_REG_MR_AN_CONTROL	0x1c
+#define QCA956X_GMAC_REG_SGMII_CONFIG	0x34
+#define QCA956X_GMAC_REG_SGMII_DEBUG	0x58
+
+#define QCA956X_ETH_CFG_RGMII_EN		BIT(0)
+#define QCA956X_ETH_CFG_GE0_SGMII		BIT(6)
+#define QCA956X_ETH_CFG_SW_ONLY_MODE		BIT(7)
+#define QCA956X_ETH_CFG_SW_PHY_SWAP		BIT(8)
+#define QCA956X_ETH_CFG_SW_PHY_ADDR_SWAP	BIT(9)
+#define QCA956X_ETH_CFG_SW_APB_ACCESS		BIT(10)
+#define QCA956X_ETH_CFG_SW_ACC_MSB_FIRST	BIT(13)
+#define QCA956X_ETH_CFG_RXD_DELAY_MASK		0x3
+#define QCA956X_ETH_CFG_RXD_DELAY_SHIFT		14
+#define QCA956X_ETH_CFG_RDV_DELAY_MASK		0x3
+#define QCA956X_ETH_CFG_RDV_DELAY_SHIFT		16
+
+#define QCA956X_SGMII_RESET_RX_CLK_N_RESET	0x0
+#define QCA956X_SGMII_RESET_RX_CLK_N		BIT(0)
+#define QCA956X_SGMII_RESET_TX_CLK_N		BIT(1)
+#define QCA956X_SGMII_RESET_RX_125M_N		BIT(2)
+#define QCA956X_SGMII_RESET_TX_125M_N		BIT(3)
+#define QCA956X_SGMII_RESET_HW_RX_125M_N	BIT(4)
+
+#define QCA956X_SGMII_SERDES_CDR_BW_MASK	0x3
+#define QCA956X_SGMII_SERDES_CDR_BW_SHIFT	1
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_MASK	0x7
+#define QCA956X_SGMII_SERDES_TX_DR_CTRL_SHIFT	4
+#define QCA956X_SGMII_SERDES_PLL_BW		BIT(8)
+#define QCA956X_SGMII_SERDES_VCO_FAST		BIT(9)
+#define QCA956X_SGMII_SERDES_VCO_SLOW		BIT(10)
+#define QCA956X_SGMII_SERDES_LOCK_DETECT_STATUS	BIT(15)
+#define QCA956X_SGMII_SERDES_EN_SIGNAL_DETECT	BIT(16)
+#define QCA956X_SGMII_SERDES_FIBER_SDO		BIT(17)
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_SHIFT 23
+#define QCA956X_SGMII_SERDES_RES_CALIBRATION_MASK 0xf
+#define QCA956X_SGMII_SERDES_VCO_REG_SHIFT	27
+#define QCA956X_SGMII_SERDES_VCO_REG_MASK	0xf
+
+#define QCA956X_MR_AN_CONTROL_AN_ENABLE		BIT(12)
+#define QCA956X_MR_AN_CONTROL_PHY_RESET		BIT(15)
+
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_SHIFT	0
+#define QCA956X_SGMII_CONFIG_MODE_CTRL_MASK	0x7
+
 #endif /* __ASM_MACH_AR71XX_REGS_H */
-- 
cgit v1.2.3


From af2d1b521bfbc57560e63602575265c0e0f62f04 Mon Sep 17 00:00:00 2001
From: Matthias Schiffer <mschiffer@universe-factory.net>
Date: Fri, 20 Jul 2018 13:58:19 +0200
Subject: MIPS: ath79: add support for QCA953x QCA956x TP9343

This patch adds support for 2 new types of QCA silicon. TP9343 is
essentially the same as the QCA956X but is licensed by TPLink.

Signed-off-by: Weijie Gao <hackpascal@gmail.com>
Signed-off-by: Matthias Schiffer <mschiffer@universe-factory.net>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19911/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/ath79/clock.c                  | 193 +++++++++++++++++++++++++++++++
 arch/mips/ath79/common.c                 |   8 ++
 arch/mips/ath79/early_printk.c           |   4 +
 arch/mips/ath79/setup.c                  |  34 +++++-
 arch/mips/include/asm/mach-ath79/ath79.h |  33 ++++++
 5 files changed, 269 insertions(+), 3 deletions(-)

diff --git a/arch/mips/ath79/clock.c b/arch/mips/ath79/clock.c
index 6b1000b6a6a6..cf9158e3c2d9 100644
--- a/arch/mips/ath79/clock.c
+++ b/arch/mips/ath79/clock.c
@@ -355,6 +355,91 @@ static void __init ar934x_clocks_init(void)
 	iounmap(dpll_base);
 }
 
+static void __init qca953x_clocks_init(void)
+{
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
+	u32 pll, out_div, ref_div, nint, frac, clk_ctrl, postdiv;
+	u32 cpu_pll, ddr_pll;
+	u32 bootstrap;
+
+	bootstrap = ath79_reset_rr(QCA953X_RESET_REG_BOOTSTRAP);
+	if (bootstrap &	QCA953X_BOOTSTRAP_REF_CLK_40)
+		ref_rate = 40 * 1000 * 1000;
+	else
+		ref_rate = 25 * 1000 * 1000;
+
+	pll = ath79_pll_rr(QCA953X_PLL_CPU_CONFIG_REG);
+	out_div = (pll >> QCA953X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+		  QCA953X_PLL_CPU_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA953X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+		  QCA953X_PLL_CPU_CONFIG_REFDIV_MASK;
+	nint = (pll >> QCA953X_PLL_CPU_CONFIG_NINT_SHIFT) &
+	       QCA953X_PLL_CPU_CONFIG_NINT_MASK;
+	frac = (pll >> QCA953X_PLL_CPU_CONFIG_NFRAC_SHIFT) &
+	       QCA953X_PLL_CPU_CONFIG_NFRAC_MASK;
+
+	cpu_pll = nint * ref_rate / ref_div;
+	cpu_pll += frac * (ref_rate >> 6) / ref_div;
+	cpu_pll /= (1 << out_div);
+
+	pll = ath79_pll_rr(QCA953X_PLL_DDR_CONFIG_REG);
+	out_div = (pll >> QCA953X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+		  QCA953X_PLL_DDR_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA953X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+		  QCA953X_PLL_DDR_CONFIG_REFDIV_MASK;
+	nint = (pll >> QCA953X_PLL_DDR_CONFIG_NINT_SHIFT) &
+	       QCA953X_PLL_DDR_CONFIG_NINT_MASK;
+	frac = (pll >> QCA953X_PLL_DDR_CONFIG_NFRAC_SHIFT) &
+	       QCA953X_PLL_DDR_CONFIG_NFRAC_MASK;
+
+	ddr_pll = nint * ref_rate / ref_div;
+	ddr_pll += frac * (ref_rate >> 6) / (ref_div << 4);
+	ddr_pll /= (1 << out_div);
+
+	clk_ctrl = ath79_pll_rr(QCA953X_PLL_CLK_CTRL_REG);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+		cpu_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_CPUCLK_FROM_CPUPLL)
+		cpu_rate = cpu_pll / (postdiv + 1);
+	else
+		cpu_rate = ddr_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+		ddr_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_DDRCLK_FROM_DDRPLL)
+		ddr_rate = ddr_pll / (postdiv + 1);
+	else
+		ddr_rate = cpu_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+		  QCA953X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+		ahb_rate = ref_rate;
+	else if (clk_ctrl & QCA953X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+		ahb_rate = ddr_pll / (postdiv + 1);
+	else
+		ahb_rate = cpu_pll / (postdiv + 1);
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
+}
+
 static void __init qca955x_clocks_init(void)
 {
 	unsigned long ref_rate;
@@ -440,6 +525,110 @@ static void __init qca955x_clocks_init(void)
 	clk_add_alias("uart", NULL, "ref", NULL);
 }
 
+static void __init qca956x_clocks_init(void)
+{
+	unsigned long ref_rate;
+	unsigned long cpu_rate;
+	unsigned long ddr_rate;
+	unsigned long ahb_rate;
+	u32 pll, out_div, ref_div, nint, hfrac, lfrac, clk_ctrl, postdiv;
+	u32 cpu_pll, ddr_pll;
+	u32 bootstrap;
+
+	/*
+	 * QCA956x timer init workaround has to be applied right before setting
+	 * up the clock. Else, there will be no jiffies
+	 */
+	u32 misc;
+
+	misc = ath79_reset_rr(AR71XX_RESET_REG_MISC_INT_ENABLE);
+	misc |= MISC_INT_MIPS_SI_TIMERINT_MASK;
+	ath79_reset_wr(AR71XX_RESET_REG_MISC_INT_ENABLE, misc);
+
+	bootstrap = ath79_reset_rr(QCA956X_RESET_REG_BOOTSTRAP);
+	if (bootstrap &	QCA956X_BOOTSTRAP_REF_CLK_40)
+		ref_rate = 40 * 1000 * 1000;
+	else
+		ref_rate = 25 * 1000 * 1000;
+
+	pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG_REG);
+	out_div = (pll >> QCA956X_PLL_CPU_CONFIG_OUTDIV_SHIFT) &
+		  QCA956X_PLL_CPU_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA956X_PLL_CPU_CONFIG_REFDIV_SHIFT) &
+		  QCA956X_PLL_CPU_CONFIG_REFDIV_MASK;
+
+	pll = ath79_pll_rr(QCA956X_PLL_CPU_CONFIG1_REG);
+	nint = (pll >> QCA956X_PLL_CPU_CONFIG1_NINT_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NINT_MASK;
+	hfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_H_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NFRAC_H_MASK;
+	lfrac = (pll >> QCA956X_PLL_CPU_CONFIG1_NFRAC_L_SHIFT) &
+	       QCA956X_PLL_CPU_CONFIG1_NFRAC_L_MASK;
+
+	cpu_pll = nint * ref_rate / ref_div;
+	cpu_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+	cpu_pll += (hfrac >> 13) * ref_rate / ref_div;
+	cpu_pll /= (1 << out_div);
+
+	pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG_REG);
+	out_div = (pll >> QCA956X_PLL_DDR_CONFIG_OUTDIV_SHIFT) &
+		  QCA956X_PLL_DDR_CONFIG_OUTDIV_MASK;
+	ref_div = (pll >> QCA956X_PLL_DDR_CONFIG_REFDIV_SHIFT) &
+		  QCA956X_PLL_DDR_CONFIG_REFDIV_MASK;
+	pll = ath79_pll_rr(QCA956X_PLL_DDR_CONFIG1_REG);
+	nint = (pll >> QCA956X_PLL_DDR_CONFIG1_NINT_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NINT_MASK;
+	hfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_H_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NFRAC_H_MASK;
+	lfrac = (pll >> QCA956X_PLL_DDR_CONFIG1_NFRAC_L_SHIFT) &
+	       QCA956X_PLL_DDR_CONFIG1_NFRAC_L_MASK;
+
+	ddr_pll = nint * ref_rate / ref_div;
+	ddr_pll += (lfrac * ref_rate) / ((ref_div * 25) << 13);
+	ddr_pll += (hfrac >> 13) * ref_rate / ref_div;
+	ddr_pll /= (1 << out_div);
+
+	clk_ctrl = ath79_pll_rr(QCA956X_PLL_CLK_CTRL_REG);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_CPU_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_PLL_BYPASS)
+		cpu_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_CPUPLL)
+		cpu_rate = ddr_pll / (postdiv + 1);
+	else
+		cpu_rate = cpu_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_DDR_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_DDR_PLL_BYPASS)
+		ddr_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_CPU_DDRCLK_FROM_DDRPLL)
+		ddr_rate = cpu_pll / (postdiv + 1);
+	else
+		ddr_rate = ddr_pll / (postdiv + 1);
+
+	postdiv = (clk_ctrl >> QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_SHIFT) &
+		  QCA956X_PLL_CLK_CTRL_AHB_POST_DIV_MASK;
+
+	if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHB_PLL_BYPASS)
+		ahb_rate = ref_rate;
+	else if (clk_ctrl & QCA956X_PLL_CLK_CTRL_AHBCLK_FROM_DDRPLL)
+		ahb_rate = ddr_pll / (postdiv + 1);
+	else
+		ahb_rate = cpu_pll / (postdiv + 1);
+
+	ath79_add_sys_clkdev("ref", ref_rate);
+	ath79_add_sys_clkdev("cpu", cpu_rate);
+	ath79_add_sys_clkdev("ddr", ddr_rate);
+	ath79_add_sys_clkdev("ahb", ahb_rate);
+
+	clk_add_alias("wdt", NULL, "ref", NULL);
+	clk_add_alias("uart", NULL, "ref", NULL);
+}
+
 void __init ath79_clocks_init(void)
 {
 	if (soc_is_ar71xx())
@@ -450,8 +639,12 @@ void __init ath79_clocks_init(void)
 		ar933x_clocks_init();
 	else if (soc_is_ar934x())
 		ar934x_clocks_init();
+	else if (soc_is_qca953x())
+		qca953x_clocks_init();
 	else if (soc_is_qca955x())
 		qca955x_clocks_init();
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		qca956x_clocks_init();
 	else
 		BUG();
 }
diff --git a/arch/mips/ath79/common.c b/arch/mips/ath79/common.c
index 10a405d593df..fad32543a968 100644
--- a/arch/mips/ath79/common.c
+++ b/arch/mips/ath79/common.c
@@ -103,8 +103,12 @@ void ath79_device_reset_set(u32 mask)
 		reg = AR933X_RESET_REG_RESET_MODULE;
 	else if (soc_is_ar934x())
 		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
 	else if (soc_is_qca955x())
 		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
 	else
 		BUG();
 
@@ -131,8 +135,12 @@ void ath79_device_reset_clear(u32 mask)
 		reg = AR933X_RESET_REG_RESET_MODULE;
 	else if (soc_is_ar934x())
 		reg = AR934X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca953x())
+		reg = QCA953X_RESET_REG_RESET_MODULE;
 	else if (soc_is_qca955x())
 		reg = QCA955X_RESET_REG_RESET_MODULE;
+	else if (soc_is_qca956x() || soc_is_tp9343())
+		reg = QCA956X_RESET_REG_RESET_MODULE;
 	else
 		BUG();
 
diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c
index de8c91198ac5..20e2c315c007 100644
--- a/arch/mips/ath79/early_printk.c
+++ b/arch/mips/ath79/early_printk.c
@@ -78,8 +78,12 @@ static void prom_putchar_init(void)
 	case REV_ID_MAJOR_AR9341:
 	case REV_ID_MAJOR_AR9342:
 	case REV_ID_MAJOR_AR9344:
+	case REV_ID_MAJOR_QCA9533:
+	case REV_ID_MAJOR_QCA9533_V2:
 	case REV_ID_MAJOR_QCA9556:
 	case REV_ID_MAJOR_QCA9558:
+	case REV_ID_MAJOR_TP9343:
+	case REV_ID_MAJOR_QCA956X:
 		_prom_putchar = prom_putchar_ar71xx;
 		break;
 
diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index f206dafbb0a3..fed49cdc5fdf 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -59,6 +59,7 @@ static void __init ath79_detect_sys_type(void)
 	u32 major;
 	u32 minor;
 	u32 rev = 0;
+	u32 ver = 1;
 
 	id = ath79_reset_rr(AR71XX_RESET_REG_REV_ID);
 	major = id & REV_ID_MAJOR_MASK;
@@ -151,6 +152,17 @@ static void __init ath79_detect_sys_type(void)
 		rev = id & AR934X_REV_ID_REVISION_MASK;
 		break;
 
+	case REV_ID_MAJOR_QCA9533_V2:
+		ver = 2;
+		ath79_soc_rev = 2;
+		/* drop through */
+
+	case REV_ID_MAJOR_QCA9533:
+		ath79_soc = ATH79_SOC_QCA9533;
+		chip = "9533";
+		rev = id & QCA953X_REV_ID_REVISION_MASK;
+		break;
+
 	case REV_ID_MAJOR_QCA9556:
 		ath79_soc = ATH79_SOC_QCA9556;
 		chip = "9556";
@@ -163,14 +175,30 @@ static void __init ath79_detect_sys_type(void)
 		rev = id & QCA955X_REV_ID_REVISION_MASK;
 		break;
 
+	case REV_ID_MAJOR_QCA956X:
+		ath79_soc = ATH79_SOC_QCA956X;
+		chip = "956X";
+		rev = id & QCA956X_REV_ID_REVISION_MASK;
+		break;
+
+	case REV_ID_MAJOR_TP9343:
+		ath79_soc = ATH79_SOC_TP9343;
+		chip = "9343";
+		rev = id & QCA956X_REV_ID_REVISION_MASK;
+		break;
+
 	default:
 		panic("ath79: unknown SoC, id:0x%08x", id);
 	}
 
-	ath79_soc_rev = rev;
+	if (ver == 1)
+		ath79_soc_rev = rev;
 
-	if (soc_is_qca955x())
-		sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s rev %u",
+	if (soc_is_qca953x() || soc_is_qca955x() || soc_is_qca956x())
+		sprintf(ath79_sys_type, "Qualcomm Atheros QCA%s ver %u rev %u",
+			chip, ver, rev);
+	else if (soc_is_tp9343())
+		sprintf(ath79_sys_type, "Qualcomm Atheros TP%s rev %u",
 			chip, rev);
 	else
 		sprintf(ath79_sys_type, "Atheros AR%s rev %u", chip, rev);
diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h
index 441faa92c3cd..f54c9b0c6325 100644
--- a/arch/mips/include/asm/mach-ath79/ath79.h
+++ b/arch/mips/include/asm/mach-ath79/ath79.h
@@ -32,8 +32,11 @@ enum ath79_soc_type {
 	ATH79_SOC_AR9341,
 	ATH79_SOC_AR9342,
 	ATH79_SOC_AR9344,
+	ATH79_SOC_QCA9533,
 	ATH79_SOC_QCA9556,
 	ATH79_SOC_QCA9558,
+	ATH79_SOC_TP9343,
+	ATH79_SOC_QCA956X,
 };
 
 extern enum ath79_soc_type ath79_soc;
@@ -100,6 +103,16 @@ static inline int soc_is_ar934x(void)
 	return soc_is_ar9341() || soc_is_ar9342() || soc_is_ar9344();
 }
 
+static inline int soc_is_qca9533(void)
+{
+	return ath79_soc == ATH79_SOC_QCA9533;
+}
+
+static inline int soc_is_qca953x(void)
+{
+	return soc_is_qca9533();
+}
+
 static inline int soc_is_qca9556(void)
 {
 	return ath79_soc == ATH79_SOC_QCA9556;
@@ -115,6 +128,26 @@ static inline int soc_is_qca955x(void)
 	return soc_is_qca9556() || soc_is_qca9558();
 }
 
+static inline int soc_is_tp9343(void)
+{
+	return ath79_soc == ATH79_SOC_TP9343;
+}
+
+static inline int soc_is_qca9561(void)
+{
+	return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca9563(void)
+{
+	return ath79_soc == ATH79_SOC_QCA956X;
+}
+
+static inline int soc_is_qca956x(void)
+{
+	return soc_is_qca9561() || soc_is_qca9563();
+}
+
 void ath79_ddr_wb_flush(unsigned int reg);
 void ath79_ddr_set_pci_windows(void);
 
-- 
cgit v1.2.3


From a08227a206b8df79c2a6dd7f62796ccf35c578de Mon Sep 17 00:00:00 2001
From: John Crispin <john@phrozen.org>
Date: Fri, 20 Jul 2018 13:58:20 +0200
Subject: MIPS: ath79: select the PINCTRL subsystem

The pinmux on QCA SoCs is controlled by a single register. The
"pinctrl-single" driver can be used but requires the target
to select PINCTRL.

Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19909/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 235feb657b0b..10256056647c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -194,6 +194,7 @@ config ATH79
 	select CSRC_R4K
 	select DMA_NONCOHERENT
 	select GPIOLIB
+	select PINCTRL
 	select HAVE_CLK
 	select COMMON_CLK
 	select CLKDEV_LOOKUP
-- 
cgit v1.2.3


From f8a7bfe1cb2c1ebfa07775c9c8ac0ad3ba8e5ff5 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 20 Jul 2018 13:58:22 +0200
Subject: MIPS: ath79: fix system restart

This patch disables irq on reboot to fix hang issues that were observed
due to pending interrupts.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19913/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/ath79/setup.c                  | 1 +
 arch/mips/include/asm/mach-ath79/ath79.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c
index fed49cdc5fdf..4c7a93f4039a 100644
--- a/arch/mips/ath79/setup.c
+++ b/arch/mips/ath79/setup.c
@@ -40,6 +40,7 @@ static char ath79_sys_type[ATH79_SYS_TYPE_LEN];
 
 static void ath79_restart(char *command)
 {
+	local_irq_disable();
 	ath79_device_reset_set(AR71XX_RESET_FULL_CHIP);
 	for (;;)
 		if (cpu_wait)
diff --git a/arch/mips/include/asm/mach-ath79/ath79.h b/arch/mips/include/asm/mach-ath79/ath79.h
index f54c9b0c6325..73dcd63b8243 100644
--- a/arch/mips/include/asm/mach-ath79/ath79.h
+++ b/arch/mips/include/asm/mach-ath79/ath79.h
@@ -167,6 +167,7 @@ static inline u32 ath79_pll_rr(unsigned reg)
 static inline void ath79_reset_wr(unsigned reg, u32 val)
 {
 	__raw_writel(val, ath79_reset_base + reg);
+	(void) __raw_readl(ath79_reset_base + reg); /* flush */
 }
 
 static inline u32 ath79_reset_rr(unsigned reg)
-- 
cgit v1.2.3


From e16343708eec32cb331f6c0dc71e5c52af741385 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Fri, 20 Jul 2018 13:58:23 +0200
Subject: MIPS: ath79: finetune cpu-overrides

This patch adds a few additional cpu feature overrides so that they do not
need to be probed at runtime.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19914/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
index 0089a740e5ae..026ad90c8ac0 100644
--- a/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
+++ b/arch/mips/include/asm/mach-ath79/cpu-feature-overrides.h
@@ -36,6 +36,7 @@
 #define cpu_has_mdmx		0
 #define cpu_has_mips3d		0
 #define cpu_has_smartmips	0
+#define cpu_has_rixi		0
 
 #define cpu_has_mips32r1	1
 #define cpu_has_mips32r2	1
@@ -43,6 +44,7 @@
 #define cpu_has_mips64r2	0
 
 #define cpu_has_mipsmt		0
+#define cpu_has_userlocal	0
 
 #define cpu_has_64bits		0
 #define cpu_has_64bit_zero_reg	0
@@ -51,5 +53,9 @@
 
 #define cpu_dcache_line_size()	32
 #define cpu_icache_line_size()	32
+#define cpu_has_vtag_icache	0
+#define cpu_has_dc_aliases	1
+#define cpu_has_ic_fills_f_dc	0
+#define cpu_has_pindexed_dcache	0
 
 #endif /* __ASM_MACH_ATH79_CPU_FEATURE_OVERRIDES_H */
-- 
cgit v1.2.3


From ffc2058189223a2625ff55dfe1676df86ed03ee3 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <juhosg@openwrt.org>
Date: Fri, 20 Jul 2018 13:58:24 +0200
Subject: MIPS: ath79: enable uart during early_prink

This patch ensures, that the pinmux register is properly setup for the
boot console UART when early_printk is enabled.

[paul.burton@mips.com:
  - s/poinmux/pinmux/
  - s/uart/UART/
  - Drop extraneous parentheses.]

Signed-off-by: Gabor Juhos <juhosg@openwrt.org>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/ath79/early_printk.c | 44 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)

diff --git a/arch/mips/ath79/early_printk.c b/arch/mips/ath79/early_printk.c
index 20e2c315c007..4b1063117ef7 100644
--- a/arch/mips/ath79/early_printk.c
+++ b/arch/mips/ath79/early_printk.c
@@ -60,6 +60,46 @@ static void prom_putchar_dummy(char ch)
 	/* nothing to do */
 }
 
+static void prom_enable_uart(u32 id)
+{
+	void __iomem *gpio_base;
+	u32 uart_en;
+	u32 t;
+
+	switch (id) {
+	case REV_ID_MAJOR_AR71XX:
+		uart_en = AR71XX_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR7240:
+	case REV_ID_MAJOR_AR7241:
+	case REV_ID_MAJOR_AR7242:
+		uart_en = AR724X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR913X:
+		uart_en = AR913X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR9330:
+	case REV_ID_MAJOR_AR9331:
+		uart_en = AR933X_GPIO_FUNC_UART_EN;
+		break;
+
+	case REV_ID_MAJOR_AR9341:
+	case REV_ID_MAJOR_AR9342:
+	case REV_ID_MAJOR_AR9344:
+		/* TODO */
+	default:
+		return;
+	}
+
+	gpio_base = (void __iomem *)KSEG1ADDR(AR71XX_GPIO_BASE);
+	t = __raw_readl(gpio_base + AR71XX_GPIO_REG_FUNC);
+	t |= uart_en;
+	__raw_writel(t, gpio_base + AR71XX_GPIO_REG_FUNC);
+}
+
 static void prom_putchar_init(void)
 {
 	void __iomem *base;
@@ -94,8 +134,10 @@ static void prom_putchar_init(void)
 
 	default:
 		_prom_putchar = prom_putchar_dummy;
-		break;
+		return;
 	}
+
+	prom_enable_uart(id);
 }
 
 void prom_putchar(char ch)
-- 
cgit v1.2.3


From 0316b05311e777f8044c72a88b966ebae7c7a39f Mon Sep 17 00:00:00 2001
From: Mathias Kresin <dev@kresin.me>
Date: Fri, 20 Jul 2018 13:58:25 +0200
Subject: MIPS: ath79: get PCIe controller out of reset

The ar724x pci driver expects the PCIe controller to be brought out of
reset by the bootloader.

At least the AVM Fritz 300E bootloader doesn't take care of releasing
the different PCIe controller related resets which causes an endless
hang as soon as either the PCIE Reset register (0x180f0018) or the PCI
Application Control register (0x180f0000) is read from.

Do the full "PCIE Root Complex Initialization Sequence" if the PCIe
host controller is still in reset during probing.

The QCA u-boot sleeps 10ms after the PCIE Application Control bit is
set to ready. It has been shown that 10ms might not be enough time if
PCIe should be used right after setting the bit. During my tests it
took up to 20ms till the link was up. Giving the link up to 100ms
should work for all cases.

Signed-off-by: Mathias Kresin <dev@kresin.me>
Signed-off-by: John Crispin <john@phrozen.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19916/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/pci/pci-ar724x.c | 42 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 42 insertions(+)

diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 1e23c8d587bd..64b58cc48a91 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -12,14 +12,18 @@
 #include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/init.h>
+#include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <asm/mach-ath79/ath79.h>
 #include <asm/mach-ath79/ar71xx_regs.h>
 
+#define AR724X_PCI_REG_APP		0x00
 #define AR724X_PCI_REG_RESET		0x18
 #define AR724X_PCI_REG_INT_STATUS	0x4c
 #define AR724X_PCI_REG_INT_MASK		0x50
 
+#define AR724X_PCI_APP_LTSSM_ENABLE	BIT(0)
+
 #define AR724X_PCI_RESET_LINK_UP	BIT(0)
 
 #define AR724X_PCI_INT_DEV0		BIT(14)
@@ -325,6 +329,37 @@ static void ar724x_pci_irq_init(struct ar724x_pci_controller *apc,
 					 apc);
 }
 
+static void ar724x_pci_hw_init(struct ar724x_pci_controller *apc)
+{
+	u32 ppl, app;
+	int wait = 0;
+
+	/* deassert PCIe host controller and PCIe PHY reset */
+	ath79_device_reset_clear(AR724X_RESET_PCIE);
+	ath79_device_reset_clear(AR724X_RESET_PCIE_PHY);
+
+	/* remove the reset of the PCIE PLL */
+	ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+	ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_RESET;
+	ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+	/* deassert bypass for the PCIE PLL */
+	ppl = ath79_pll_rr(AR724X_PLL_REG_PCIE_CONFIG);
+	ppl &= ~AR724X_PLL_REG_PCIE_CONFIG_PPL_BYPASS;
+	ath79_pll_wr(AR724X_PLL_REG_PCIE_CONFIG, ppl);
+
+	/* set PCIE Application Control to ready */
+	app = __raw_readl(apc->ctrl_base + AR724X_PCI_REG_APP);
+	app |= AR724X_PCI_APP_LTSSM_ENABLE;
+	__raw_writel(app, apc->ctrl_base + AR724X_PCI_REG_APP);
+
+	/* wait up to 100ms for PHY link up */
+	do {
+		mdelay(10);
+		wait++;
+	} while (wait < 10 && !ar724x_pci_check_link(apc));
+}
+
 static int ar724x_pci_probe(struct platform_device *pdev)
 {
 	struct ar724x_pci_controller *apc;
@@ -383,6 +418,13 @@ static int ar724x_pci_probe(struct platform_device *pdev)
 	apc->pci_controller.io_resource = &apc->io_res;
 	apc->pci_controller.mem_resource = &apc->mem_res;
 
+	/*
+	 * Do the full PCIE Root Complex Initialization Sequence if the PCIe
+	 * host controller is in reset.
+	 */
+	if (ath79_reset_rr(AR724X_RESET_REG_RESET_MODULE) & AR724X_RESET_PCIE)
+		ar724x_pci_hw_init(apc);
+
 	apc->link_up = ar724x_pci_check_link(apc);
 	if (!apc->link_up)
 		dev_warn(&pdev->dev, "PCIe link is down\n");
-- 
cgit v1.2.3


From 2cc512c1fa1ee99879d55d1cb4e3fd0e6eab35b3 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 24 Jul 2018 10:55:24 +0800
Subject: bpf: btf: fix inconsistent IS_ERR and PTR_ERR

Fix inconsistent IS_ERR and PTR_ERR in get_btf,
the proper pointer to be passed as argument is '*btf'

This issue was detected with the help of Coccinelle.

Fixes: 2d3feca8c44f ("bpf: btf: print map dump and lookup with btf info")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 9c8191845585..0ee3ba479d87 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -230,7 +230,7 @@ static int get_btf(struct bpf_map_info *map_info, struct btf **btf)
 
 	*btf = btf__new((__u8 *)btf_info.btf, btf_info.btf_size, NULL);
 	if (IS_ERR(*btf)) {
-		err = PTR_ERR(btf);
+		err = PTR_ERR(*btf);
 		*btf = NULL;
 	}
 
-- 
cgit v1.2.3


From e66565f3bee141748d2c3b2ed0d4ecd455f634fa Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jcline@redhat.com>
Date: Tue, 24 Jul 2018 15:53:34 -0400
Subject: bpf: Add Python 3 support to selftests scripts for bpf

Adjust tcp_client.py and tcp_server.py to work with Python 3 by using
the print function, marking string literals as bytes, and using the
newer exception syntax. This should be functionally equivalent and
supports Python 3+.

Signed-off-by: Jeremy Cline <jcline@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/tcp_client.py | 12 ++++++------
 tools/testing/selftests/bpf/tcp_server.py | 16 ++++++++--------
 2 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/bpf/tcp_client.py b/tools/testing/selftests/bpf/tcp_client.py
index 481dccdf140c..7f8200a8702b 100755
--- a/tools/testing/selftests/bpf/tcp_client.py
+++ b/tools/testing/selftests/bpf/tcp_client.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python2
+#!/usr/bin/env python3
 #
 # SPDX-License-Identifier: GPL-2.0
 #
@@ -9,11 +9,11 @@ import subprocess
 import select
 
 def read(sock, n):
-    buf = ''
+    buf = b''
     while len(buf) < n:
         rem = n - len(buf)
         try: s = sock.recv(rem)
-        except (socket.error), e: return ''
+        except (socket.error) as e: return b''
         buf += s
     return buf
 
@@ -22,7 +22,7 @@ def send(sock, s):
     count = 0
     while count < total:
         try: n = sock.send(s)
-        except (socket.error), e: n = 0
+        except (socket.error) as e: n = 0
         if n == 0:
             return count;
         count += n
@@ -39,10 +39,10 @@ try:
 except socket.error as e:
     sys.exit(1)
 
-buf = ''
+buf = b''
 n = 0
 while n < 1000:
-    buf += '+'
+    buf += b'+'
     n += 1
 
 sock.settimeout(1);
diff --git a/tools/testing/selftests/bpf/tcp_server.py b/tools/testing/selftests/bpf/tcp_server.py
index bc454d7d0be2..b39903fca4c8 100755
--- a/tools/testing/selftests/bpf/tcp_server.py
+++ b/tools/testing/selftests/bpf/tcp_server.py
@@ -1,4 +1,4 @@
-#!/usr/bin/env python2
+#!/usr/bin/env python3
 #
 # SPDX-License-Identifier: GPL-2.0
 #
@@ -9,11 +9,11 @@ import subprocess
 import select
 
 def read(sock, n):
-    buf = ''
+    buf = b''
     while len(buf) < n:
         rem = n - len(buf)
         try: s = sock.recv(rem)
-        except (socket.error), e: return ''
+        except (socket.error) as e: return b''
         buf += s
     return buf
 
@@ -22,7 +22,7 @@ def send(sock, s):
     count = 0
     while count < total:
         try: n = sock.send(s)
-        except (socket.error), e: n = 0
+        except (socket.error) as e: n = 0
         if n == 0:
             return count;
         count += n
@@ -43,7 +43,7 @@ host = socket.gethostname()
 
 try: serverSocket.bind((host, 0))
 except socket.error as msg:
-    print 'bind fails: ', msg
+    print('bind fails: ' + str(msg))
 
 sn = serverSocket.getsockname()
 serverPort = sn[1]
@@ -51,10 +51,10 @@ serverPort = sn[1]
 cmdStr = ("./tcp_client.py %d &") % (serverPort)
 os.system(cmdStr)
 
-buf = ''
+buf = b''
 n = 0
 while n < 500:
-    buf += '.'
+    buf += b'.'
     n += 1
 
 serverSocket.listen(MAX_PORTS)
@@ -79,5 +79,5 @@ while True:
                 serverSocket.close()
                 sys.exit(0)
     else:
-        print 'Select timeout!'
+        print('Select timeout!')
         sys.exit(1)
-- 
cgit v1.2.3


From 2a6777a118406858ad02bce8e4dc8302cba5a290 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 24 Jul 2018 07:55:18 +0200
Subject: s390: disable gcc plugins

The s390 build currently fails with the latent entropy plugin:

arch/s390/kernel/als.o: In function `verify_facilities':
als.c:(.init.text+0x24): undefined reference to `latent_entropy'
als.c:(.init.text+0xae): undefined reference to `latent_entropy'
make[3]: *** [arch/s390/boot/compressed/vmlinux] Error 1
make[2]: *** [arch/s390/boot/compressed/vmlinux] Error 2
make[1]: *** [bzImage] Error 2

This will be fixed with the early boot rework from Vasily, which
is planned for the 4.19 merge window.

For 4.18 the simplest solution is to disable the gcc plugins and
reenable them after the early boot rework is upstream.

Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
(cherry picked from commit 2fba3573f1cf876ad94992c256c5c410039e60b4)
---
 arch/s390/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 3023fa00e4b5..f9b6036f1c16 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -140,7 +140,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_GCC_PLUGINS
+	select HAVE_GCC_PLUGINS if BROKEN
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
-- 
cgit v1.2.3


From 6eedfaac712d7a1ebcfa34085fbae91f19d33bf3 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 24 Jul 2018 08:23:29 +0200
Subject: s390: reenable gcc plugins

Now that the early boot rework is upstream we can enable the gcc plugins
again. See git commit 72f108b308707f21499e0ac05bf7370360cf06d8
"s390: disable gcc plugins" for reference.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f9b6036f1c16..3023fa00e4b5 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -140,7 +140,7 @@ config S390
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_GCC_PLUGINS if BROKEN
+	select HAVE_GCC_PLUGINS
 	select HAVE_KERNEL_BZIP2
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZ4
-- 
cgit v1.2.3


From 190bd6e98afc512fb16d4a471acd488e36141637 Mon Sep 17 00:00:00 2001
From: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Date: Tue, 24 Jul 2018 15:02:13 -0400
Subject: EDAC, sb_edac: Add support for systems with segmented PCI buses

Extend the driver to check whether segment number and bus number matches
when deciding how to group memory controller PCI devices to CPU sockets.

Signed-off-by: Masayoshi Mizuma <m.mizuma@jp.fujitsu.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Cc: Mauro Carvalho Chehab <mchehab@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/20180724190213.26359-1-msys.mizuma@gmail.com
[ Cleanup commit message. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
---
 drivers/edac/sb_edac.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index 4a89c8093307..07726fb00321 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -352,6 +352,7 @@ struct pci_id_table {
 
 struct sbridge_dev {
 	struct list_head	list;
+	int			seg;
 	u8			bus, mc;
 	u8			node_id, source_id;
 	struct pci_dev		**pdev;
@@ -729,7 +730,8 @@ static inline int numcol(u32 mtr)
 	return 1 << cols;
 }
 
-static struct sbridge_dev *get_sbridge_dev(u8 bus, enum domain dom, int multi_bus,
+static struct sbridge_dev *get_sbridge_dev(int seg, u8 bus, enum domain dom,
+					   int multi_bus,
 					   struct sbridge_dev *prev)
 {
 	struct sbridge_dev *sbridge_dev;
@@ -747,14 +749,15 @@ static struct sbridge_dev *get_sbridge_dev(u8 bus, enum domain dom, int multi_bu
 				      : sbridge_edac_list.next, struct sbridge_dev, list);
 
 	list_for_each_entry_from(sbridge_dev, &sbridge_edac_list, list) {
-		if (sbridge_dev->bus == bus && (dom == SOCK || dom == sbridge_dev->dom))
+		if ((sbridge_dev->seg == seg) && (sbridge_dev->bus == bus) &&
+				(dom == SOCK || dom == sbridge_dev->dom))
 			return sbridge_dev;
 	}
 
 	return NULL;
 }
 
-static struct sbridge_dev *alloc_sbridge_dev(u8 bus, enum domain dom,
+static struct sbridge_dev *alloc_sbridge_dev(int seg, u8 bus, enum domain dom,
 					     const struct pci_id_table *table)
 {
 	struct sbridge_dev *sbridge_dev;
@@ -771,6 +774,7 @@ static struct sbridge_dev *alloc_sbridge_dev(u8 bus, enum domain dom,
 		return NULL;
 	}
 
+	sbridge_dev->seg = seg;
 	sbridge_dev->bus = bus;
 	sbridge_dev->dom = dom;
 	sbridge_dev->n_devs = table->n_devs_per_imc;
@@ -2246,6 +2250,7 @@ static int sbridge_get_onedevice(struct pci_dev **prev,
 	struct sbridge_dev *sbridge_dev = NULL;
 	const struct pci_id_descr *dev_descr = &table->descr[devno];
 	struct pci_dev *pdev = NULL;
+	int seg = 0;
 	u8 bus = 0;
 	int i = 0;
 
@@ -2276,10 +2281,12 @@ static int sbridge_get_onedevice(struct pci_dev **prev,
 		/* End of list, leave */
 		return -ENODEV;
 	}
+	seg = pci_domain_nr(pdev->bus);
 	bus = pdev->bus->number;
 
 next_imc:
-	sbridge_dev = get_sbridge_dev(bus, dev_descr->dom, multi_bus, sbridge_dev);
+	sbridge_dev = get_sbridge_dev(seg, bus, dev_descr->dom,
+				      multi_bus, sbridge_dev);
 	if (!sbridge_dev) {
 		/* If the HA1 wasn't found, don't create EDAC second memory controller */
 		if (dev_descr->dom == IMC1 && devno != 1) {
@@ -2292,7 +2299,7 @@ next_imc:
 		if (dev_descr->dom == SOCK)
 			goto out_imc;
 
-		sbridge_dev = alloc_sbridge_dev(bus, dev_descr->dom, table);
+		sbridge_dev = alloc_sbridge_dev(seg, bus, dev_descr->dom, table);
 		if (!sbridge_dev) {
 			pci_dev_put(pdev);
 			return -ENOMEM;
-- 
cgit v1.2.3


From 2e62c4743adc4c7bfcbc1f45118fc7bec58cf30a Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Thu, 19 Jul 2018 14:00:06 +0200
Subject: sched/fair: Remove #ifdefs from scale_rt_capacity()

Reuse cpu_util_irq() that has been defined for schedutil and set irq util
to 0 when !CONFIG_IRQ_TIME_ACCOUNTING.

But the compiler is not able to optimize the sequence (at least with
aarch64 GCC 7.2.1):

	free *= (max - irq);
	free /= max;

when irq is fixed to 0

Add a new inline function scale_irq_capacity() that will scale utilization
when irq is accounted. Reuse this funciton in schedutil which applies
similar formula.

Suggested-by: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: rjw@rjwysocki.net
Link: http://lkml.kernel.org/r/1532001606-6689-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c              |  2 +-
 kernel/sched/cpufreq_schedutil.c |  3 +--
 kernel/sched/fair.c              | 13 +++----------
 kernel/sched/sched.h             | 20 ++++++++++++++++++--
 4 files changed, 23 insertions(+), 15 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c3cf7d992159..fc177c06e490 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -177,7 +177,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	rq->clock_task += delta;
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef HAVE_SCHED_AVG_IRQ
 	if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY))
 		update_irq_load_avg(rq, irq_delta + steal);
 #endif
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 97dcd4472a0e..3fffad3bc8a8 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -247,8 +247,7 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
 	 *   U' = irq + ------- * U
 	 *                max
 	 */
-	util *= (max - irq);
-	util /= max;
+	util = scale_irq_capacity(util, irq, max);
 	util += irq;
 
 	/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d5f7d521e448..14c3fddf822a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7551,16 +7551,12 @@ static unsigned long scale_rt_capacity(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
 	unsigned long used, free;
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
 	unsigned long irq;
-#endif
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	irq = READ_ONCE(rq->avg_irq.util_avg);
+	irq = cpu_util_irq(rq);
 
 	if (unlikely(irq >= max))
 		return 1;
-#endif
 
 	used = READ_ONCE(rq->avg_rt.util_avg);
 	used += READ_ONCE(rq->avg_dl.util_avg);
@@ -7569,11 +7565,8 @@ static unsigned long scale_rt_capacity(int cpu)
 		return 1;
 
 	free = max - used;
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
-	free *= (max - irq);
-	free /= max;
-#endif
-	return free;
+
+	return scale_irq_capacity(free, irq, max);
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ebb4b3c3ece7..614170d9b1aa 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -856,6 +856,7 @@ struct rq {
 	struct sched_avg	avg_rt;
 	struct sched_avg	avg_dl;
 #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#define HAVE_SCHED_AVG_IRQ
 	struct sched_avg	avg_irq;
 #endif
 	u64			idle_stamp;
@@ -2210,17 +2211,32 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 {
 	return READ_ONCE(rq->avg_rt.util_avg);
 }
+#endif
 
-#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+#ifdef HAVE_SCHED_AVG_IRQ
 static inline unsigned long cpu_util_irq(struct rq *rq)
 {
 	return rq->avg_irq.util_avg;
 }
+
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	util *= (max - irq);
+	util /= max;
+
+	return util;
+
+}
 #else
 static inline unsigned long cpu_util_irq(struct rq *rq)
 {
 	return 0;
 }
 
-#endif
+static inline
+unsigned long scale_irq_capacity(unsigned long util, unsigned long irq, unsigned long max)
+{
+	return util;
+}
 #endif
-- 
cgit v1.2.3


From 3d6c50c27bd6418dceb51642540ecfcb8ca708c2 Mon Sep 17 00:00:00 2001
From: Yun Wang <yun.wang@linux.alibaba.com>
Date: Wed, 4 Jul 2018 11:27:27 +0800
Subject: sched/debug: Show the sum wait time of a task group

Although we can rely on cpuacct to present the CPU usage of task
groups, it is hard to tell how intense the competition is between
these groups on CPU resources.

Monitoring the wait time or sched_debug of each process could be
very expensive, and there is no good way to accurately represent the
conflict with these info, we need the wait time on group dimension.

Thus we introduce group's wait_sum to represent the resource conflict
between task groups, which is simply the sum of the wait time of
the group's cfs_rq.

The 'cpu.stat' is modified to show the statistic, like:

   nr_periods 0
   nr_throttled 0
   throttled_time 0
   wait_sum 2035098795584

Now we can monitor the changes of wait_sum to tell how much a
a task group is suffering in the fight of CPU resources.

For example:

   (wait_sum - last_wait_sum) * 100 / (nr_cpu * period_ns) == X%

means the task group paid X percentage of period on waiting
for the CPU.

Signed-off-by: Michael Wang <yun.wang@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/ff7dae3b-e5f9-7157-1caa-ff02c6b23dc1@linux.alibaba.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fc177c06e490..2bc391a574e6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6748,6 +6748,16 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
 	seq_printf(sf, "nr_throttled %d\n", cfs_b->nr_throttled);
 	seq_printf(sf, "throttled_time %llu\n", cfs_b->throttled_time);
 
+	if (schedstat_enabled() && tg != &root_task_group) {
+		u64 ws = 0;
+		int i;
+
+		for_each_possible_cpu(i)
+			ws += schedstat_val(tg->se[i]->statistics.wait_sum);
+
+		seq_printf(sf, "wait_sum %llu\n", ws);
+	}
+
 	return 0;
 }
 #endif /* CONFIG_CFS_BANDWIDTH */
-- 
cgit v1.2.3


From 6e30396767508101eacec8b93b068e8905e660dc Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:42 +0530
Subject: sched/numa: Remove redundant field

'numa_entry' is a struct list_head defined in task_struct, but never used.

No functional change.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-2-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/sched.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 43731fe51c97..e0f4f56c9310 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1017,7 +1017,6 @@ struct task_struct {
 	u64				last_sum_exec_runtime;
 	struct callback_head		numa_work;
 
-	struct list_head		numa_entry;
 	struct numa_group		*numa_group;
 
 	/*
-- 
cgit v1.2.3


From 305c1fac3225dfa7eeb89bfe91b7335a6edd5172 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:43 +0530
Subject: sched/numa: Evaluate move once per node

task_numa_compare() helps choose the best CPU to move or swap the
selected task. To achieve this task_numa_compare() is called for every
CPU in the node. Currently it evaluates if the task can be moved/swapped
for each of the CPUs. However the move evaluation is mostly independent
of the CPU. Evaluating the move logic once per node, provides scope for
simplifying task_numa_compare().

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25705.2     25058.2     -2.51
1     74433       72950       -1.99

Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
8     96589.6     105930      9.670
1     181830      178624      -1.76

(numbers from v1 based on v4.17-rc5)
Testcase       Time:         Min         Max         Avg      StdDev
numa01.sh      Real:      440.65      941.32      758.98      189.17
numa01.sh       Sys:      183.48      320.07      258.42       50.09
numa01.sh      User:    37384.65    71818.14    60302.51    13798.96
numa02.sh      Real:       61.24       65.35       62.49        1.49
numa02.sh       Sys:       16.83       24.18       21.40        2.60
numa02.sh      User:     5219.59     5356.34     5264.03       49.07
numa03.sh      Real:      822.04      912.40      873.55       37.35
numa03.sh       Sys:      118.80      140.94      132.90        7.60
numa03.sh      User:    62485.19    70025.01    67208.33     2967.10
numa04.sh      Real:      690.66      872.12      778.49       65.44
numa04.sh       Sys:      459.26      563.03      494.03       42.39
numa04.sh      User:    51116.44    70527.20    58849.44     8461.28
numa05.sh      Real:      418.37      562.28      525.77       54.27
numa05.sh       Sys:      299.45      481.00      392.49       64.27
numa05.sh      User:    34115.09    41324.02    39105.30     2627.68

Testcase       Time:         Min         Max         Avg      StdDev 	 %Change
numa01.sh      Real:      516.14      892.41      739.84      151.32 	 2.587%
numa01.sh       Sys:      153.16      192.99      177.70       14.58 	 45.42%
numa01.sh      User:    39821.04    69528.92    57193.87    10989.48 	 5.435%
numa02.sh      Real:       60.91       62.35       61.58        0.63 	 1.477%
numa02.sh       Sys:       16.47       26.16       21.20        3.85 	 0.943%
numa02.sh      User:     5227.58     5309.61     5265.17       31.04 	 -0.02%
numa03.sh      Real:      739.07      917.73      795.75       64.45 	 9.776%
numa03.sh       Sys:       94.46      136.08      109.48       14.58 	 21.39%
numa03.sh      User:    57478.56    72014.09    61764.48     5343.69 	 8.813%
numa04.sh      Real:      442.61      715.43      530.31       96.12 	 46.79%
numa04.sh       Sys:      224.90      348.63      285.61       48.83 	 72.97%
numa04.sh      User:    35836.84    47522.47    40235.41     3985.26 	 46.26%
numa05.sh      Real:      386.13      489.17      434.94       43.59 	 20.88%
numa05.sh       Sys:      144.29      438.56      278.80      105.78 	 40.77%
numa05.sh      User:    33255.86    36890.82    34879.31     1641.98 	 12.11%

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-3-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 128 +++++++++++++++++++++++-----------------------------
 1 file changed, 57 insertions(+), 71 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 14c3fddf822a..b10e0663a49e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1580,9 +1580,8 @@ static bool load_too_imbalanced(long src_load, long dst_load,
  * be exchanged with the source task
  */
 static void task_numa_compare(struct task_numa_env *env,
-			      long taskimp, long groupimp)
+			      long taskimp, long groupimp, bool maymove)
 {
-	struct rq *src_rq = cpu_rq(env->src_cpu);
 	struct rq *dst_rq = cpu_rq(env->dst_cpu);
 	struct task_struct *cur;
 	long src_load, dst_load;
@@ -1603,97 +1602,73 @@ static void task_numa_compare(struct task_numa_env *env,
 	if (cur == env->p)
 		goto unlock;
 
+	if (!cur) {
+		if (maymove || imp > env->best_imp)
+			goto assign;
+		else
+			goto unlock;
+	}
+
 	/*
 	 * "imp" is the fault differential for the source task between the
 	 * source and destination node. Calculate the total differential for
 	 * the source task and potential destination task. The more negative
-	 * the value is, the more rmeote accesses that would be expected to
+	 * the value is, the more remote accesses that would be expected to
 	 * be incurred if the tasks were swapped.
 	 */
-	if (cur) {
-		/* Skip this swap candidate if cannot move to the source CPU: */
-		if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
-			goto unlock;
+	/* Skip this swap candidate if cannot move to the source cpu */
+	if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+		goto unlock;
 
+	/*
+	 * If dst and source tasks are in the same NUMA group, or not
+	 * in any group then look only at task weights.
+	 */
+	if (cur->numa_group == env->p->numa_group) {
+		imp = taskimp + task_weight(cur, env->src_nid, dist) -
+		      task_weight(cur, env->dst_nid, dist);
 		/*
-		 * If dst and source tasks are in the same NUMA group, or not
-		 * in any group then look only at task weights.
+		 * Add some hysteresis to prevent swapping the
+		 * tasks within a group over tiny differences.
 		 */
-		if (cur->numa_group == env->p->numa_group) {
-			imp = taskimp + task_weight(cur, env->src_nid, dist) -
-			      task_weight(cur, env->dst_nid, dist);
-			/*
-			 * Add some hysteresis to prevent swapping the
-			 * tasks within a group over tiny differences.
-			 */
-			if (cur->numa_group)
-				imp -= imp/16;
-		} else {
-			/*
-			 * Compare the group weights. If a task is all by
-			 * itself (not part of a group), use the task weight
-			 * instead.
-			 */
-			if (cur->numa_group)
-				imp += group_weight(cur, env->src_nid, dist) -
-				       group_weight(cur, env->dst_nid, dist);
-			else
-				imp += task_weight(cur, env->src_nid, dist) -
-				       task_weight(cur, env->dst_nid, dist);
-		}
+		if (cur->numa_group)
+			imp -= imp / 16;
+	} else {
+		/*
+		 * Compare the group weights. If a task is all by itself
+		 * (not part of a group), use the task weight instead.
+		 */
+		if (cur->numa_group && env->p->numa_group)
+			imp += group_weight(cur, env->src_nid, dist) -
+			       group_weight(cur, env->dst_nid, dist);
+		else
+			imp += task_weight(cur, env->src_nid, dist) -
+			       task_weight(cur, env->dst_nid, dist);
 	}
 
-	if (imp <= env->best_imp && moveimp <= env->best_imp)
+	if (imp <= env->best_imp)
 		goto unlock;
 
-	if (!cur) {
-		/* Is there capacity at our destination? */
-		if (env->src_stats.nr_running <= env->src_stats.task_capacity &&
-		    !env->dst_stats.has_free_capacity)
-			goto unlock;
-
-		goto balance;
-	}
-
-	/* Balance doesn't matter much if we're running a task per CPU: */
-	if (imp > env->best_imp && src_rq->nr_running == 1 &&
-			dst_rq->nr_running == 1)
+	if (maymove && moveimp > imp && moveimp > env->best_imp) {
+		imp = moveimp - 1;
+		cur = NULL;
 		goto assign;
+	}
 
 	/*
 	 * In the overloaded case, try and keep the load balanced.
 	 */
-balance:
-	load = task_h_load(env->p);
+	load = task_h_load(env->p) - task_h_load(cur);
+	if (!load)
+		goto assign;
+
 	dst_load = env->dst_stats.load + load;
 	src_load = env->src_stats.load - load;
 
-	if (moveimp > imp && moveimp > env->best_imp) {
-		/*
-		 * If the improvement from just moving env->p direction is
-		 * better than swapping tasks around, check if a move is
-		 * possible. Store a slightly smaller score than moveimp,
-		 * so an actually idle CPU will win.
-		 */
-		if (!load_too_imbalanced(src_load, dst_load, env)) {
-			imp = moveimp - 1;
-			cur = NULL;
-			goto assign;
-		}
-	}
-
-	if (imp <= env->best_imp)
-		goto unlock;
-
-	if (cur) {
-		load = task_h_load(cur);
-		dst_load -= load;
-		src_load += load;
-	}
-
 	if (load_too_imbalanced(src_load, dst_load, env))
 		goto unlock;
 
+assign:
 	/*
 	 * One idle CPU per node is evaluated for a task numa move.
 	 * Call select_idle_sibling to maybe find a better one.
@@ -1709,7 +1684,6 @@ balance:
 		local_irq_enable();
 	}
 
-assign:
 	task_numa_assign(env, cur, imp);
 unlock:
 	rcu_read_unlock();
@@ -1718,15 +1692,27 @@ unlock:
 static void task_numa_find_cpu(struct task_numa_env *env,
 				long taskimp, long groupimp)
 {
+	long src_load, dst_load, load;
+	bool maymove = false;
 	int cpu;
 
+	load = task_h_load(env->p);
+	dst_load = env->dst_stats.load + load;
+	src_load = env->src_stats.load - load;
+
+	/*
+	 * If the improvement from just moving env->p direction is better
+	 * than swapping tasks around, check if a move is possible.
+	 */
+	maymove = !load_too_imbalanced(src_load, dst_load, env);
+
 	for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
 		/* Skip this CPU if the source task cannot migrate */
 		if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
 			continue;
 
 		env->dst_cpu = cpu;
-		task_numa_compare(env, taskimp, groupimp);
+		task_numa_compare(env, taskimp, groupimp, maymove);
 	}
 }
 
-- 
cgit v1.2.3


From 5f95ba7a43057f28a349ea1f03ee8d04e0f445ea Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:44 +0530
Subject: sched/numa: Simplify load_too_imbalanced()

Currently load_too_imbalance() cares about the slope of imbalance.
It doesn't care of the direction of the imbalance.

However this may not work if nodes that are being compared have
dissimilar capacities. Few nodes might have more cores than other nodes
in the system. Also unlike traditional load balance at a NUMA sched
domain, multiple requests to migrate from the same source node to same
destination node may run in parallel. This can cause huge load
imbalance. This is specially true on a larger machines with either large
cores per node or more number of nodes in the system. Hence allow
move/swap only if the imbalance is going to reduce.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25058.2     25122.9     0.25
1     72950       73850       1.23

(numbers from v1 based on v4.17-rc5)
Testcase       Time:         Min         Max         Avg      StdDev
numa01.sh      Real:      516.14      892.41      739.84      151.32
numa01.sh       Sys:      153.16      192.99      177.70       14.58
numa01.sh      User:    39821.04    69528.92    57193.87    10989.48
numa02.sh      Real:       60.91       62.35       61.58        0.63
numa02.sh       Sys:       16.47       26.16       21.20        3.85
numa02.sh      User:     5227.58     5309.61     5265.17       31.04
numa03.sh      Real:      739.07      917.73      795.75       64.45
numa03.sh       Sys:       94.46      136.08      109.48       14.58
numa03.sh      User:    57478.56    72014.09    61764.48     5343.69
numa04.sh      Real:      442.61      715.43      530.31       96.12
numa04.sh       Sys:      224.90      348.63      285.61       48.83
numa04.sh      User:    35836.84    47522.47    40235.41     3985.26
numa05.sh      Real:      386.13      489.17      434.94       43.59
numa05.sh       Sys:      144.29      438.56      278.80      105.78
numa05.sh      User:    33255.86    36890.82    34879.31     1641.98

Testcase       Time:         Min         Max         Avg      StdDev 	 %Change
numa01.sh      Real:      435.78      653.81      534.58       83.20 	 38.39%
numa01.sh       Sys:      121.93      187.18      145.90       23.47 	 21.79%
numa01.sh      User:    37082.81    51402.80    43647.60     5409.75 	 31.03%
numa02.sh      Real:       60.64       61.63       61.19        0.40 	 0.637%
numa02.sh       Sys:       14.72       25.68       19.06        4.03 	 11.22%
numa02.sh      User:     5210.95     5266.69     5233.30       20.82 	 0.608%
numa03.sh      Real:      746.51      808.24      780.36       23.88 	 1.972%
numa03.sh       Sys:       97.26      108.48      105.07        4.28 	 4.197%
numa03.sh      User:    58956.30    61397.05    60162.95     1050.82 	 2.661%
numa04.sh      Real:      465.97      519.27      484.81       19.62 	 9.385%
numa04.sh       Sys:      304.43      359.08      334.68       20.64 	 -14.6%
numa04.sh      User:    37544.16    41186.15    39262.44     1314.91 	 2.478%
numa05.sh      Real:      411.57      457.20      433.29       16.58 	 0.380%
numa05.sh       Sys:      230.05      435.48      339.95       67.58 	 -17.9%
numa05.sh      User:    33325.54    36896.31    35637.84     1222.64 	 -2.12%

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-4-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 20 ++------------------
 1 file changed, 2 insertions(+), 18 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index b10e0663a49e..226837960ec0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1546,28 +1546,12 @@ static bool load_too_imbalanced(long src_load, long dst_load,
 	src_capacity = env->src_stats.compute_capacity;
 	dst_capacity = env->dst_stats.compute_capacity;
 
-	/* We care about the slope of the imbalance, not the direction. */
-	if (dst_load < src_load)
-		swap(dst_load, src_load);
-
-	/* Is the difference below the threshold? */
-	imb = dst_load * src_capacity * 100 -
-	      src_load * dst_capacity * env->imbalance_pct;
-	if (imb <= 0)
-		return false;
+	imb = abs(dst_load * src_capacity - src_load * dst_capacity);
 
-	/*
-	 * The imbalance is above the allowed threshold.
-	 * Compare it with the old imbalance.
-	 */
 	orig_src_load = env->src_stats.load;
 	orig_dst_load = env->dst_stats.load;
 
-	if (orig_dst_load < orig_src_load)
-		swap(orig_dst_load, orig_src_load);
-
-	old_imb = orig_dst_load * src_capacity * 100 -
-		  orig_src_load * dst_capacity * env->imbalance_pct;
+	old_imb = abs(orig_dst_load * src_capacity - orig_src_load * dst_capacity);
 
 	/* Would this change make things worse? */
 	return (imb > old_imb);
-- 
cgit v1.2.3


From 8cd45eee43bd46b933158b25aa7c742e0f3e811f Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:45 +0530
Subject: sched/numa: Set preferred_node based on best_cpu

Currently preferred node is set to dst_nid which is the last node in the
iteration whose group weight or task weight is greater than the current
node. However it doesn't guarantee that dst_nid has the numa capacity
to move. It also doesn't guarantee that dst_nid has the best_cpu which
is the CPU/node ideal for node migration.

Lets consider faults on a 4 node system with group weight numbers
in different nodes being in 0 < 1 < 2 < 3 proportion. Consider the task
is running on 3 and 0 is its preferred node but its capacity is full.
Consider nodes 1, 2 and 3 have capacity. Then the task should be
migrated to node 1. Currently the task gets moved to node 2. env.dst_nid
points to the last node whose faults were greater than current node.

Modify to set the preferred node based of best_cpu. Earlier setting
preferred node was skipped if nr_active_nodes is 1. This could result in
the task being moved out of the preferred node to a random node during
regular load balancing.

Also while modifying task_numa_migrate(), use sched_setnuma to set
preferred node. This ensures out numa accounting is correct.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25122.9     25549.6     1.698
1     73850       73190       -0.89

Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
8     105930      113437      7.08676
1     178624      196130      9.80047

(numbers from v1 based on v4.17-rc5)
Testcase       Time:         Min         Max         Avg      StdDev
numa01.sh      Real:      435.78      653.81      534.58       83.20
numa01.sh       Sys:      121.93      187.18      145.90       23.47
numa01.sh      User:    37082.81    51402.80    43647.60     5409.75
numa02.sh      Real:       60.64       61.63       61.19        0.40
numa02.sh       Sys:       14.72       25.68       19.06        4.03
numa02.sh      User:     5210.95     5266.69     5233.30       20.82
numa03.sh      Real:      746.51      808.24      780.36       23.88
numa03.sh       Sys:       97.26      108.48      105.07        4.28
numa03.sh      User:    58956.30    61397.05    60162.95     1050.82
numa04.sh      Real:      465.97      519.27      484.81       19.62
numa04.sh       Sys:      304.43      359.08      334.68       20.64
numa04.sh      User:    37544.16    41186.15    39262.44     1314.91
numa05.sh      Real:      411.57      457.20      433.29       16.58
numa05.sh       Sys:      230.05      435.48      339.95       67.58
numa05.sh      User:    33325.54    36896.31    35637.84     1222.64

Testcase       Time:         Min         Max         Avg      StdDev 	 %Change
numa01.sh      Real:      506.35      794.46      599.06      104.26 	 -10.76%
numa01.sh       Sys:      150.37      223.56      195.99       24.94 	 -25.55%
numa01.sh      User:    43450.69    61752.04    49281.50     6635.33 	 -11.43%
numa02.sh      Real:       60.33       62.40       61.31        0.90 	 -0.195%
numa02.sh       Sys:       18.12       31.66       24.28        5.89 	 -21.49%
numa02.sh      User:     5203.91     5325.32     5260.29       49.98 	 -0.513%
numa03.sh      Real:      696.47      853.62      745.80       57.28 	 4.6339%
numa03.sh       Sys:       85.68      123.71       97.89       13.48 	 7.3347%
numa03.sh      User:    55978.45    66418.63    59254.94     3737.97 	 1.5323%
numa04.sh      Real:      444.05      514.83      497.06       26.85 	 -2.464%
numa04.sh       Sys:      230.39      375.79      316.23       48.58 	 5.8343%
numa04.sh      User:    35403.12    41004.10    39720.80     2163.08 	 -1.153%
numa05.sh      Real:      423.09      460.41      439.57       13.92 	 -1.428%
numa05.sh       Sys:      287.38      480.15      369.37       68.52 	 -7.964%
numa05.sh      User:    34732.12    38016.80    36255.85     1070.51 	 -1.704%

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-5-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 226837960ec0..0532195c38d0 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1765,7 +1765,7 @@ static int task_numa_migrate(struct task_struct *p)
 	 * elsewhere, so there is no point in (re)trying.
 	 */
 	if (unlikely(!sd)) {
-		p->numa_preferred_nid = task_node(p);
+		sched_setnuma(p, task_node(p));
 		return -EINVAL;
 	}
 
@@ -1824,15 +1824,13 @@ static int task_numa_migrate(struct task_struct *p)
 	 * trying for a better one later. Do not set the preferred node here.
 	 */
 	if (p->numa_group) {
-		struct numa_group *ng = p->numa_group;
-
 		if (env.best_cpu == -1)
 			nid = env.src_nid;
 		else
-			nid = env.dst_nid;
+			nid = cpu_to_node(env.best_cpu);
 
-		if (ng->active_nodes > 1 && numa_is_active_node(env.dst_nid, ng))
-			sched_setnuma(p, env.dst_nid);
+		if (nid != p->numa_preferred_nid)
+			sched_setnuma(p, nid);
 	}
 
 	/* No better CPU than the current one was found. */
-- 
cgit v1.2.3


From f03bb6760b8e5e2bcecc88d2a2ef41c09adcab39 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:46 +0530
Subject: sched/numa: Use task faults only if numa_group is not yet set up

When numa_group faults are available, task_numa_placement only uses
numa_group faults to evaluate preferred node. However it still accounts
task faults and even evaluates the preferred node just based on task
faults just to discard it in favour of preferred node chosen on the
basis of numa_group.

Instead use task faults only if numa_group is not set.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25549.6     25215.7     -1.30
1     73190       72107       -1.47

Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
8     113437      113372      -0.05
1     196130      177403      -9.54

(numbers from v1 based on v4.17-rc5)
Testcase       Time:         Min         Max         Avg      StdDev
numa01.sh      Real:      506.35      794.46      599.06      104.26
numa01.sh       Sys:      150.37      223.56      195.99       24.94
numa01.sh      User:    43450.69    61752.04    49281.50     6635.33
numa02.sh      Real:       60.33       62.40       61.31        0.90
numa02.sh       Sys:       18.12       31.66       24.28        5.89
numa02.sh      User:     5203.91     5325.32     5260.29       49.98
numa03.sh      Real:      696.47      853.62      745.80       57.28
numa03.sh       Sys:       85.68      123.71       97.89       13.48
numa03.sh      User:    55978.45    66418.63    59254.94     3737.97
numa04.sh      Real:      444.05      514.83      497.06       26.85
numa04.sh       Sys:      230.39      375.79      316.23       48.58
numa04.sh      User:    35403.12    41004.10    39720.80     2163.08
numa05.sh      Real:      423.09      460.41      439.57       13.92
numa05.sh       Sys:      287.38      480.15      369.37       68.52
numa05.sh      User:    34732.12    38016.80    36255.85     1070.51

Testcase       Time:         Min         Max         Avg      StdDev 	 %Change
numa01.sh      Real:      478.45      565.90      515.11       30.87 	 16.29%
numa01.sh       Sys:      207.79      271.04      232.94       21.33 	 -15.8%
numa01.sh      User:    39763.93    47303.12    43210.73     2644.86 	 14.04%
numa02.sh      Real:       60.00       61.46       60.78        0.49 	 0.871%
numa02.sh       Sys:       15.71       25.31       20.69        3.42 	 17.35%
numa02.sh      User:     5175.92     5265.86     5235.97       32.82 	 0.464%
numa03.sh      Real:      776.42      834.85      806.01       23.22 	 -7.47%
numa03.sh       Sys:      114.43      128.75      121.65        5.49 	 -19.5%
numa03.sh      User:    60773.93    64855.25    62616.91     1576.39 	 -5.36%
numa04.sh      Real:      456.93      511.95      482.91       20.88 	 2.930%
numa04.sh       Sys:      178.09      460.89      356.86       94.58 	 -11.3%
numa04.sh      User:    36312.09    42553.24    39623.21     2247.96 	 0.246%
numa05.sh      Real:      393.98      493.48      436.61       35.59 	 0.677%
numa05.sh       Sys:      164.49      329.15      265.87       61.78 	 38.92%
numa05.sh      User:    33182.65    36654.53    35074.51     1187.71 	 3.368%

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-6-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0532195c38d0..a10c4f8f47e8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2110,8 +2110,8 @@ static int preferred_group_nid(struct task_struct *p, int nid)
 
 static void task_numa_placement(struct task_struct *p)
 {
-	int seq, nid, max_nid = -1, max_group_nid = -1;
-	unsigned long max_faults = 0, max_group_faults = 0;
+	int seq, nid, max_nid = -1;
+	unsigned long max_faults = 0;
 	unsigned long fault_types[2] = { 0, 0 };
 	unsigned long total_faults;
 	u64 runtime, period;
@@ -2190,15 +2190,15 @@ static void task_numa_placement(struct task_struct *p)
 			}
 		}
 
-		if (faults > max_faults) {
-			max_faults = faults;
+		if (!p->numa_group) {
+			if (faults > max_faults) {
+				max_faults = faults;
+				max_nid = nid;
+			}
+		} else if (group_faults > max_faults) {
+			max_faults = group_faults;
 			max_nid = nid;
 		}
-
-		if (group_faults > max_group_faults) {
-			max_group_faults = group_faults;
-			max_group_nid = nid;
-		}
 	}
 
 	update_task_scan_period(p, fault_types[0], fault_types[1]);
@@ -2206,7 +2206,7 @@ static void task_numa_placement(struct task_struct *p)
 	if (p->numa_group) {
 		numa_group_count_active_nodes(p->numa_group);
 		spin_unlock_irq(group_lock);
-		max_nid = preferred_group_nid(p, max_group_nid);
+		max_nid = preferred_group_nid(p, max_nid);
 	}
 
 	if (max_faults) {
-- 
cgit v1.2.3


From 67d9f6c256cd66e15f85c92670f52a7ad4689cff Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:47 +0530
Subject: sched/debug: Reverse the order of printing faults

Fix the order in which the private and shared numa faults are getting
printed.

No functional changes.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25215.7     25375.3     0.63
1     72107       72617       0.70

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-7-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/debug.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index c96e89cc4bc7..870d4f3da285 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -842,8 +842,8 @@ void print_numa_stats(struct seq_file *m, int node, unsigned long tsf,
 		unsigned long tpf, unsigned long gsf, unsigned long gpf)
 {
 	SEQ_printf(m, "numa_faults node=%d ", node);
-	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tsf, tpf);
-	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gsf, gpf);
+	SEQ_printf(m, "task_private=%lu task_shared=%lu ", tpf, tsf);
+	SEQ_printf(m, "group_private=%lu group_shared=%lu\n", gpf, gsf);
 }
 #endif
 
-- 
cgit v1.2.3


From 0ee7e74dc0dc64d9900751d03c5c22dfdd173fb8 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:48 +0530
Subject: sched/numa: Skip nodes that are at 'hoplimit'

When comparing two nodes at a distance of 'hoplimit', we should consider
nodes only up to 'hoplimit'. Currently we also consider nodes at 'oplimit'
distance too. Hence two nodes at a distance of 'hoplimit' will have same
groupweight. Fix this by skipping nodes at hoplimit.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25375.3     25308.6     -0.26
1     72617       72964       0.477

Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
8     113372      108750      -4.07684
1     177403      183115      3.21979

(numbers from v1 based on v4.17-rc5)
Testcase       Time:         Min         Max         Avg      StdDev
numa01.sh      Real:      478.45      565.90      515.11       30.87
numa01.sh       Sys:      207.79      271.04      232.94       21.33
numa01.sh      User:    39763.93    47303.12    43210.73     2644.86
numa02.sh      Real:       60.00       61.46       60.78        0.49
numa02.sh       Sys:       15.71       25.31       20.69        3.42
numa02.sh      User:     5175.92     5265.86     5235.97       32.82
numa03.sh      Real:      776.42      834.85      806.01       23.22
numa03.sh       Sys:      114.43      128.75      121.65        5.49
numa03.sh      User:    60773.93    64855.25    62616.91     1576.39
numa04.sh      Real:      456.93      511.95      482.91       20.88
numa04.sh       Sys:      178.09      460.89      356.86       94.58
numa04.sh      User:    36312.09    42553.24    39623.21     2247.96
numa05.sh      Real:      393.98      493.48      436.61       35.59
numa05.sh       Sys:      164.49      329.15      265.87       61.78
numa05.sh      User:    33182.65    36654.53    35074.51     1187.71

Testcase       Time:         Min         Max         Avg      StdDev 	 %Change
numa01.sh      Real:      414.64      819.20      556.08      147.70 	 -7.36%
numa01.sh       Sys:       77.52      205.04      139.40       52.05 	 67.10%
numa01.sh      User:    37043.24    61757.88    45517.48     9290.38 	 -5.06%
numa02.sh      Real:       60.80       63.32       61.63        0.88 	 -1.37%
numa02.sh       Sys:       17.35       39.37       25.71        7.33 	 -19.5%
numa02.sh      User:     5213.79     5374.73     5268.90       55.09 	 -0.62%
numa03.sh      Real:      780.09      948.64      831.43       63.02 	 -3.05%
numa03.sh       Sys:      104.96      136.92      116.31       11.34 	 4.591%
numa03.sh      User:    60465.42    73339.78    64368.03     4700.14 	 -2.72%
numa04.sh      Real:      412.60      681.92      521.29       96.64 	 -7.36%
numa04.sh       Sys:      210.32      314.10      251.77       37.71 	 41.74%
numa04.sh      User:    34026.38    45581.20    38534.49     4198.53 	 2.825%
numa05.sh      Real:      394.79      439.63      411.35       16.87 	 6.140%
numa05.sh       Sys:      238.32      330.09      292.31       38.32 	 -9.04%
numa05.sh      User:    33456.45    34876.07    34138.62      609.45 	 2.741%

While there is a regression with this change, this change is needed from a
correctness perspective. Also it helps consolidation as seen from perf bench
output.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-8-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index a10c4f8f47e8..e5f39e8dfe53 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1312,7 +1312,7 @@ static unsigned long score_nearby_nodes(struct task_struct *p, int nid,
 		 * of each group. Skip other nodes.
 		 */
 		if (sched_numa_topology_type == NUMA_BACKPLANE &&
-					dist > maxdist)
+					dist >= maxdist)
 			continue;
 
 		/* Add up the faults from nearby nodes. */
-- 
cgit v1.2.3


From 10864a9e222048a862da2c21efa28929a4dfed15 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:49 +0530
Subject: sched/numa: Remove unused task_capacity from 'struct numa_stats'

The task_capacity field in 'struct numa_stats' is redundant.
Also move nr_running for better packing within the struct.

No functional changes.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25308.6     25377.3     0.271
1     72964       72287       -0.92

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Rik van Riel <riel@surriel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-9-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e5f39e8dfe53..4ac60b296d96 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1450,14 +1450,12 @@ static unsigned long capacity_of(int cpu);
 
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
-	unsigned long nr_running;
 	unsigned long load;
 
 	/* Total compute capacity of CPUs on a node */
 	unsigned long compute_capacity;
 
-	/* Approximate capacity in terms of runnable tasks on a node */
-	unsigned long task_capacity;
+	unsigned int nr_running;
 	int has_free_capacity;
 };
 
@@ -1495,9 +1493,9 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, ns->compute_capacity);
 	capacity = cpus / smt; /* cores */
 
-	ns->task_capacity = min_t(unsigned, capacity,
+	capacity = min_t(unsigned, capacity,
 		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
-	ns->has_free_capacity = (ns->nr_running < ns->task_capacity);
+	ns->has_free_capacity = (ns->nr_running < capacity);
 }
 
 struct task_numa_env {
-- 
cgit v1.2.3


From 0ad4e3dfe6cf3f207e61cbd8e3e4a943f8c1ad20 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:50 +0530
Subject: sched/numa: Modify migrate_swap() to accept additional parameters

There are checks in migrate_swap_stop() that check if the task/CPU
combination is as per migrate_swap_arg before migrating.

However atleast one of the two tasks to be swapped by migrate_swap() could
have migrated to a completely different CPU before updating the
migrate_swap_arg. The new CPU where the task is currently running could
be a different node too. If the task has migrated, numa balancer might
end up placing a task in a wrong node.  Instead of achieving node
consolidation, it may end up spreading the load across nodes.

To avoid that pass the CPUs as additional parameters.

While here, place migrate_swap under CONFIG_NUMA_BALANCING.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25377.3     25226.6     -0.59
1     72287       73326       1.437

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-10-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/core.c  | 9 ++++++---
 kernel/sched/fair.c  | 3 ++-
 kernel/sched/sched.h | 3 ++-
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2bc391a574e6..deafa9fe602b 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1176,6 +1176,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 	__set_task_cpu(p, new_cpu);
 }
 
+#ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
 	if (task_on_rq_queued(p)) {
@@ -1257,16 +1258,17 @@ unlock:
 /*
  * Cross migrate two tasks
  */
-int migrate_swap(struct task_struct *cur, struct task_struct *p)
+int migrate_swap(struct task_struct *cur, struct task_struct *p,
+		int target_cpu, int curr_cpu)
 {
 	struct migration_swap_arg arg;
 	int ret = -EINVAL;
 
 	arg = (struct migration_swap_arg){
 		.src_task = cur,
-		.src_cpu = task_cpu(cur),
+		.src_cpu = curr_cpu,
 		.dst_task = p,
-		.dst_cpu = task_cpu(p),
+		.dst_cpu = target_cpu,
 	};
 
 	if (arg.src_cpu == arg.dst_cpu)
@@ -1291,6 +1293,7 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p)
 out:
 	return ret;
 }
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * wait_task_inactive - wait for a thread to unschedule.
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4ac60b296d96..7b4eddec3ccc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1848,7 +1848,8 @@ static int task_numa_migrate(struct task_struct *p)
 		return ret;
 	}
 
-	ret = migrate_swap(p, env.best_task);
+	ret = migrate_swap(p, env.best_task, env.best_cpu, env.src_cpu);
+
 	if (ret != 0)
 		trace_sched_stick_numa(p, env.src_cpu, task_cpu(env.best_task));
 	put_task_struct(env.best_task);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 614170d9b1aa..4a2e8cae63c4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1099,7 +1099,8 @@ enum numa_faults_stats {
 };
 extern void sched_setnuma(struct task_struct *p, int node);
 extern int migrate_task_to(struct task_struct *p, int cpu);
-extern int migrate_swap(struct task_struct *, struct task_struct *);
+extern int migrate_swap(struct task_struct *p, struct task_struct *t,
+			int cpu, int scpu);
 extern void init_numa_balancing(unsigned long clone_flags, struct task_struct *p);
 #else
 static inline void
-- 
cgit v1.2.3


From 2d4056fafa196e1ab4e7161bae4df76f9602d56d Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:53 +0530
Subject: sched/numa: Remove numa_has_capacity()

task_numa_find_cpu() helps to find the CPU to swap/move the task to.
It's guarded by numa_has_capacity(). However node not having capacity
shouldn't deter a task swapping if it helps NUMA placement.

Further load_too_imbalanced(), which evaluates possibilities of move/swap,
provides similar checks as numa_has_capacity.

Hence remove numa_has_capacity() to enhance possibilities of task
swapping even if load is imbalanced.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25657.9     25804.1     0.569
1     74435       73413       -1.37

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Rik van Riel <riel@surriel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-13-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 36 +++---------------------------------
 1 file changed, 3 insertions(+), 33 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7b4eddec3ccc..3bcf0e864613 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1456,7 +1456,6 @@ struct numa_stats {
 	unsigned long compute_capacity;
 
 	unsigned int nr_running;
-	int has_free_capacity;
 };
 
 /*
@@ -1483,8 +1482,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 	 * the @ns structure is NULL'ed and task_numa_compare() will
 	 * not find this node attractive.
 	 *
-	 * We'll either bail at !has_free_capacity, or we'll detect a huge
-	 * imbalance and bail there.
+	 * We'll detect a huge imbalance and bail there.
 	 */
 	if (!cpus)
 		return;
@@ -1495,7 +1493,6 @@ static void update_numa_stats(struct numa_stats *ns, int nid)
 
 	capacity = min_t(unsigned, capacity,
 		DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE));
-	ns->has_free_capacity = (ns->nr_running < capacity);
 }
 
 struct task_numa_env {
@@ -1698,31 +1695,6 @@ static void task_numa_find_cpu(struct task_numa_env *env,
 	}
 }
 
-/* Only move tasks to a NUMA node less busy than the current node. */
-static bool numa_has_capacity(struct task_numa_env *env)
-{
-	struct numa_stats *src = &env->src_stats;
-	struct numa_stats *dst = &env->dst_stats;
-
-	if (src->has_free_capacity && !dst->has_free_capacity)
-		return false;
-
-	/*
-	 * Only consider a task move if the source has a higher load
-	 * than the destination, corrected for CPU capacity on each node.
-	 *
-	 *      src->load                dst->load
-	 * --------------------- vs ---------------------
-	 * src->compute_capacity    dst->compute_capacity
-	 */
-	if (src->load * dst->compute_capacity * env->imbalance_pct >
-
-	    dst->load * src->compute_capacity * 100)
-		return true;
-
-	return false;
-}
-
 static int task_numa_migrate(struct task_struct *p)
 {
 	struct task_numa_env env = {
@@ -1777,8 +1749,7 @@ static int task_numa_migrate(struct task_struct *p)
 	update_numa_stats(&env.dst_stats, env.dst_nid);
 
 	/* Try to find a spot on the preferred nid. */
-	if (numa_has_capacity(&env))
-		task_numa_find_cpu(&env, taskimp, groupimp);
+	task_numa_find_cpu(&env, taskimp, groupimp);
 
 	/*
 	 * Look at other nodes in these cases:
@@ -1808,8 +1779,7 @@ static int task_numa_migrate(struct task_struct *p)
 			env.dist = dist;
 			env.dst_nid = nid;
 			update_numa_stats(&env.dst_stats, env.dst_nid);
-			if (numa_has_capacity(&env))
-				task_numa_find_cpu(&env, taskimp, groupimp);
+			task_numa_find_cpu(&env, taskimp, groupimp);
 		}
 	}
 
-- 
cgit v1.2.3


From 30619c89b17d46808b4cdf5b3f81b6a01ade1473 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:55 +0530
Subject: sched/numa: Update the scan period without holding the numa_group
 lock

The metrics for updating scan periods are local or task specific.
Currently this update happens under the numa_group lock, which seems
unnecessary. Hence move this update outside the lock.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25355.9     25645.4     1.141
1     72812       72142       -0.92

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Rik van Riel <riel@surriel.com>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-15-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3bcf0e864613..fc33a4b40a09 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2170,8 +2170,6 @@ static void task_numa_placement(struct task_struct *p)
 		}
 	}
 
-	update_task_scan_period(p, fault_types[0], fault_types[1]);
-
 	if (p->numa_group) {
 		numa_group_count_active_nodes(p->numa_group);
 		spin_unlock_irq(group_lock);
@@ -2186,6 +2184,8 @@ static void task_numa_placement(struct task_struct *p)
 		if (task_node(p) != p->numa_preferred_nid)
 			numa_migrate_preferred(p);
 	}
+
+	update_task_scan_period(p, fault_types[0], fault_types[1]);
 }
 
 static inline int get_numa_group(struct numa_group *grp)
-- 
cgit v1.2.3


From f35678b6a17063f3b0d391af5ab8f8c83cf31b0c Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:32:56 +0530
Subject: sched/numa: Use group_weights to identify if migration degrades
 locality

On NUMA_BACKPLANE and NUMA_GLUELESS_MESH systems, tasks/memory should be
consolidated to the closest group of nodes. In such a case, relying on
group_fault metric may not always help to consolidate. There can always
be a case where a node closer to the preferred node may have lesser
faults than a node further away from the preferred node. In such a case,
moving to node with more faults might avoid numa consolidation.

Using group_weight would help to consolidate task/memory around the
preferred_node.

While here, to be on the conservative side, don't override migrate thread
degrades locality logic for CPU_NEWLY_IDLE load balancing.

Note: Similar problems exist with should_numa_migrate_memory and will be
dealt separately.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25645.4     25960       1.22
1     72142       73550       1.95

Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
8     110199      120071      8.958
1     176303      176249      -0.03

(numbers from v1 based on v4.17-rc5)
Testcase       Time:         Min         Max         Avg      StdDev
numa01.sh      Real:      490.04      774.86      596.26       96.46
numa01.sh       Sys:      151.52      242.88      184.82       31.71
numa01.sh      User:    41418.41    60844.59    48776.09     6564.27
numa02.sh      Real:       60.14       62.94       60.98        1.00
numa02.sh       Sys:       16.11       30.77       21.20        5.28
numa02.sh      User:     5184.33     5311.09     5228.50       44.24
numa03.sh      Real:      790.95      856.35      826.41       24.11
numa03.sh       Sys:      114.93      118.85      117.05        1.63
numa03.sh      User:    60990.99    64959.28    63470.43     1415.44
numa04.sh      Real:      434.37      597.92      504.87       59.70
numa04.sh       Sys:      237.63      397.40      289.74       55.98
numa04.sh      User:    34854.87    41121.83    38572.52     2615.84
numa05.sh      Real:      386.77      448.90      417.22       22.79
numa05.sh       Sys:      149.23      379.95      303.04       79.55
numa05.sh      User:    32951.76    35959.58    34562.18     1034.05

Testcase       Time:         Min         Max         Avg      StdDev 	 %Change
numa01.sh      Real:      493.19      672.88      597.51       59.38 	 -0.20%
numa01.sh       Sys:      150.09      245.48      207.76       34.26 	 -11.0%
numa01.sh      User:    41928.51    53779.17    48747.06     3901.39 	 0.059%
numa02.sh      Real:       60.63       62.87       61.22        0.83 	 -0.39%
numa02.sh       Sys:       16.64       27.97       20.25        4.06 	 4.691%
numa02.sh      User:     5222.92     5309.60     5254.03       29.98 	 -0.48%
numa03.sh      Real:      821.52      902.15      863.60       32.41 	 -4.30%
numa03.sh       Sys:      112.04      130.66      118.35        7.08 	 -1.09%
numa03.sh      User:    62245.16    69165.14    66443.04     2450.32 	 -4.47%
numa04.sh      Real:      414.53      519.57      476.25       37.00 	 6.009%
numa04.sh       Sys:      181.84      335.67      280.41       54.07 	 3.327%
numa04.sh      User:    33924.50    39115.39    37343.78     1934.26 	 3.290%
numa05.sh      Real:      408.30      441.45      417.90       12.05 	 -0.16%
numa05.sh       Sys:      233.41      381.60      295.58       57.37 	 2.523%
numa05.sh      User:    33301.31    35972.50    34335.19      938.94 	 0.661%

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-16-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fc33a4b40a09..9c9e54ea65d9 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6899,8 +6899,8 @@ static int task_hot(struct task_struct *p, struct lb_env *env)
 static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 {
 	struct numa_group *numa_group = rcu_dereference(p->numa_group);
-	unsigned long src_faults, dst_faults;
-	int src_nid, dst_nid;
+	unsigned long src_weight, dst_weight;
+	int src_nid, dst_nid, dist;
 
 	if (!static_branch_likely(&sched_numa_balancing))
 		return -1;
@@ -6927,18 +6927,19 @@ static int migrate_degrades_locality(struct task_struct *p, struct lb_env *env)
 		return 0;
 
 	/* Leaving a core idle is often worse than degrading locality. */
-	if (env->idle != CPU_NOT_IDLE)
+	if (env->idle == CPU_IDLE)
 		return -1;
 
+	dist = node_distance(src_nid, dst_nid);
 	if (numa_group) {
-		src_faults = group_faults(p, src_nid);
-		dst_faults = group_faults(p, dst_nid);
+		src_weight = group_weight(p, src_nid, dist);
+		dst_weight = group_weight(p, dst_nid, dist);
 	} else {
-		src_faults = task_faults(p, src_nid);
-		dst_faults = task_faults(p, dst_nid);
+		src_weight = task_weight(p, src_nid, dist);
+		dst_weight = task_weight(p, dst_nid, dist);
 	}
 
-	return dst_faults < src_faults;
+	return dst_weight < src_weight;
 }
 
 #else
-- 
cgit v1.2.3


From b6a60cf36d497e7fbde9dd5b86fabd96850249f6 Mon Sep 17 00:00:00 2001
From: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Date: Wed, 20 Jun 2018 22:33:00 +0530
Subject: sched/numa: Move task_numa_placement() closer to
 numa_migrate_preferred()

numa_migrate_preferred() is called periodically or when task preferred
node changes. Preferred node evaluations happen once per scan sequence.

If the scan completion happens just after the periodic NUMA migration,
then we try to migrate to the preferred node and the preferred node might
change, needing another node migration.

Avoid this by checking for scan sequence completion only when checking
for periodic migration.

Running SPECjbb2005 on a 4 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
16    25862.6     26158.1     1.14258
1     74357       72725       -2.19482

Running SPECjbb2005 on a 16 node machine and comparing bops/JVM
JVMS  LAST_PATCH  WITH_PATCH  %CHANGE
8     117019      113992      -2.58
1     179095      174947      -2.31

(numbers from v1 based on v4.17-rc5)
Testcase       Time:         Min         Max         Avg      StdDev
numa01.sh      Real:      449.46      770.77      615.22      101.70
numa01.sh       Sys:      132.72      208.17      170.46       24.96
numa01.sh      User:    39185.26    60290.89    50066.76     6807.84
numa02.sh      Real:       60.85       61.79       61.28        0.37
numa02.sh       Sys:       15.34       24.71       21.08        3.61
numa02.sh      User:     5204.41     5249.85     5231.21       17.60
numa03.sh      Real:      785.50      916.97      840.77       44.98
numa03.sh       Sys:      108.08      133.60      119.43        8.82
numa03.sh      User:    61422.86    70919.75    64720.87     3310.61
numa04.sh      Real:      429.57      587.37      480.80       57.40
numa04.sh       Sys:      240.61      321.97      290.84       33.58
numa04.sh      User:    34597.65    40498.99    37079.48     2060.72
numa05.sh      Real:      392.09      431.25      414.65       13.82
numa05.sh       Sys:      229.41      372.48      297.54       53.14
numa05.sh      User:    33390.86    34697.49    34222.43      556.42

Testcase       Time:         Min         Max         Avg      StdDev 	%Change
numa01.sh      Real:      424.63      566.18      498.12       59.26 	 23.50%
numa01.sh       Sys:      160.19      256.53      208.98       37.02 	 -18.4%
numa01.sh      User:    37320.00    46225.58    42001.57     3482.45 	 19.20%
numa02.sh      Real:       60.17       62.47       60.91        0.85 	 0.607%
numa02.sh       Sys:       15.30       22.82       17.04        2.90 	 23.70%
numa02.sh      User:     5202.13     5255.51     5219.08       20.14 	 0.232%
numa03.sh      Real:      823.91      844.89      833.86        8.46 	 0.828%
numa03.sh       Sys:      130.69      148.29      140.47        6.21 	 -14.9%
numa03.sh      User:    62519.15    64262.20    63613.38      620.05 	 1.740%
numa04.sh      Real:      515.30      603.74      548.56       30.93 	 -12.3%
numa04.sh       Sys:      459.73      525.48      489.18       21.63 	 -40.5%
numa04.sh      User:    40561.96    44919.18    42047.87     1526.85 	 -11.8%
numa05.sh      Real:      396.58      454.37      421.13       19.71 	 -1.53%
numa05.sh       Sys:      208.72      422.02      348.90       73.60 	 -14.7%
numa05.sh      User:    33124.08    36109.35    34846.47     1089.74 	 -1.79%

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1529514181-9842-20-git-send-email-srikar@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/sched/fair.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9c9e54ea65d9..309c93fcc604 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2180,9 +2180,6 @@ static void task_numa_placement(struct task_struct *p)
 		/* Set the new preferred node */
 		if (max_nid != p->numa_preferred_nid)
 			sched_setnuma(p, max_nid);
-
-		if (task_node(p) != p->numa_preferred_nid)
-			numa_migrate_preferred(p);
 	}
 
 	update_task_scan_period(p, fault_types[0], fault_types[1]);
@@ -2385,14 +2382,14 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags)
 				numa_is_active_node(mem_node, ng))
 		local = 1;
 
-	task_numa_placement(p);
-
 	/*
 	 * Retry task to preferred node migration periodically, in case it
 	 * case it previously failed, or the scheduler moved us.
 	 */
-	if (time_after(jiffies, p->numa_migrate_retry))
+	if (time_after(jiffies, p->numa_migrate_retry)) {
+		task_numa_placement(p);
 		numa_migrate_preferred(p);
+	}
 
 	if (migrated)
 		p->numa_pages_migrated += pages;
-- 
cgit v1.2.3


From 3196234039155a33c80e52d7aa41a29dce9a5c51 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 8 Mar 2018 18:15:39 -0800
Subject: perf/x86/intel: Introduce PMU flag for Extended PEBS

The Extended PEBS feature, introduced in the Goldmont Plus
microarchitecture, supports all events as "Extended PEBS".

Introduce flag PMU_FL_PEBS_ALL to indicate the platforms which support
extended PEBS.

To support all events, it needs to support all constraints for PEBS. To
avoid duplicating all the constraints in the PEBS table, making the PEBS
code search the normal constraints too.

Based-on-code-from: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Link: http://lkml.kernel.org/r/20180309021542.11374-1-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/ds.c   | 7 +++++++
 arch/x86/events/perf_event.h | 1 +
 2 files changed, 8 insertions(+)

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8dbba77e0518..9fd9cb1d2cc8 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -871,6 +871,13 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event)
 		}
 	}
 
+	/*
+	 * Extended PEBS support
+	 * Makes the PEBS code search the normal constraints.
+	 */
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		return NULL;
+
 	return &emptyconstraint;
 }
 
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 2430398befd8..156286335351 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -673,6 +673,7 @@ do {									\
 #define PMU_FL_HAS_RSP_1	0x2 /* has 2 equivalent offcore_rsp regs   */
 #define PMU_FL_EXCL_CNTRS	0x4 /* has exclusive counter requirements  */
 #define PMU_FL_EXCL_ENABLED	0x8 /* exclusive counter active */
+#define PMU_FL_PEBS_ALL		0x10 /* all events are valid PEBS events */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
-- 
cgit v1.2.3


From 4f08b6255adb1e379b4fcc8d304ec1263d465677 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 8 Mar 2018 18:15:40 -0800
Subject: perf/x86/intel: Support PEBS on fixed counters

The Extended PEBS feature supports PEBS on fixed-function performance
counters as well as all four general purpose counters.

It has to change the order of PEBS and fixed counter enabling to make
sure PEBS is enabled for the fixed counters.

The change of the order doesn't impact the behavior of current code on
other platforms which don't support extended PEBS.
Because there is no dependency among those enable/disable functions.

Don't enable IRQ generation (0x8) for MSR_ARCH_PERFMON_FIXED_CTR_CTRL.
The PEBS ucode will handle the interrupt generation.

Based-on-code-from: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Link: http://lkml.kernel.org/r/20180309021542.11374-2-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/core.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 86f0c15dcc2d..d5a3124605f5 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2041,15 +2041,15 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	cpuc->intel_ctrl_host_mask &= ~(1ull << hwc->idx);
 	cpuc->intel_cp_status &= ~(1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_disable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
 		intel_pmu_disable_fixed(hwc);
 		return;
 	}
 
 	x86_pmu_disable_event(event);
-
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
 }
 
 static void intel_pmu_del_event(struct perf_event *event)
@@ -2068,17 +2068,19 @@ static void intel_pmu_read_event(struct perf_event *event)
 		x86_perf_event_update(event);
 }
 
-static void intel_pmu_enable_fixed(struct hw_perf_event *hwc)
+static void intel_pmu_enable_fixed(struct perf_event *event)
 {
+	struct hw_perf_event *hwc = &event->hw;
 	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
-	u64 ctrl_val, bits, mask;
+	u64 ctrl_val, mask, bits = 0;
 
 	/*
-	 * Enable IRQ generation (0x8),
+	 * Enable IRQ generation (0x8), if not PEBS,
 	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
 	 * if requested:
 	 */
-	bits = 0x8ULL;
+	if (!event->attr.precise_ip)
+		bits |= 0x8;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
 		bits |= 0x2;
 	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
@@ -2120,14 +2122,14 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	if (unlikely(event_is_checkpointed(event)))
 		cpuc->intel_cp_status |= (1ull << hwc->idx);
 
+	if (unlikely(event->attr.precise_ip))
+		intel_pmu_pebs_enable(event);
+
 	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
-		intel_pmu_enable_fixed(hwc);
+		intel_pmu_enable_fixed(event);
 		return;
 	}
 
-	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_enable(event);
-
 	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
 }
 
-- 
cgit v1.2.3


From ec71a398c1bf6d8188cb24ebab6f5202523d95e1 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 8 Mar 2018 18:15:41 -0800
Subject: perf/x86/intel/ds: Handle PEBS overflow for fixed counters

The pebs_drain() need to support fixed counters. The DS Save Area now
include "counter reset value" fields for each fixed counters.

Extend the related variables (e.g. mask, counters, error) to support
fixed counters. There is no extended PEBS in PEBS v2 and earlier PEBS
format. Only need to change the code for PEBS v3 and later PEBS format.

Extend the pebs_event_reset[] logic to support new "counter reset value" fields.

Increase the reserve space for fixed counters.

Based-on-code-from: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Link: http://lkml.kernel.org/r/20180309021542.11374-3-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/core.c    |  5 ++++-
 arch/x86/events/intel/ds.c      | 36 +++++++++++++++++++++++++++---------
 arch/x86/include/asm/intel_ds.h |  3 ++-
 3 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index d5a3124605f5..b1a49a108a59 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2282,7 +2282,10 @@ again:
 	 * counters from the GLOBAL_STATUS mask and we always process PEBS
 	 * events via drain_pebs().
 	 */
-	status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		status &= ~cpuc->pebs_enabled;
+	else
+		status &= ~(cpuc->pebs_enabled & PEBS_COUNTER_MASK);
 
 	/*
 	 * PEBS overflow sets bit 62 in the global status register
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 9fd9cb1d2cc8..595b96ae8a00 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -903,10 +903,16 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
 {
 	struct debug_store *ds = cpuc->ds;
 	u64 threshold;
+	int reserved;
+
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+		reserved = x86_pmu.max_pebs_events + x86_pmu.num_counters_fixed;
+	else
+		reserved = x86_pmu.max_pebs_events;
 
 	if (cpuc->n_pebs == cpuc->n_large_pebs) {
 		threshold = ds->pebs_absolute_maximum -
-			x86_pmu.max_pebs_events * x86_pmu.pebs_record_size;
+			reserved * x86_pmu.pebs_record_size;
 	} else {
 		threshold = ds->pebs_buffer_base + x86_pmu.pebs_record_size;
 	}
@@ -970,7 +976,11 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	 * This must be done in pmu::start(), because PERF_EVENT_IOC_PERIOD.
 	 */
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
-		ds->pebs_event_reset[hwc->idx] =
+		unsigned int idx = hwc->idx;
+
+		if (idx >= INTEL_PMC_IDX_FIXED)
+			idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED);
+		ds->pebs_event_reset[idx] =
 			(u64)(-hwc->sample_period) & x86_pmu.cntval_mask;
 	} else {
 		ds->pebs_event_reset[hwc->idx] = 0;
@@ -1488,9 +1498,10 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 	struct debug_store *ds = cpuc->ds;
 	struct perf_event *event;
 	void *base, *at, *top;
-	short counts[MAX_PEBS_EVENTS] = {};
-	short error[MAX_PEBS_EVENTS] = {};
-	int bit, i;
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	int bit, i, size;
+	u64 mask;
 
 	if (!x86_pmu.pebs_active)
 		return;
@@ -1500,6 +1511,13 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 
 	ds->pebs_index = ds->pebs_buffer_base;
 
+	mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+	size = x86_pmu.max_pebs_events;
+	if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+		mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
+		size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
+	}
+
 	if (unlikely(base >= top)) {
 		/*
 		 * The drain_pebs() could be called twice in a short period
@@ -1509,7 +1527,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		 * update the event->count for this case.
 		 */
 		for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled,
-				 x86_pmu.max_pebs_events) {
+				 size) {
 			event = cpuc->events[bit];
 			if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)
 				intel_pmu_save_and_restart_reload(event, 0);
@@ -1522,12 +1540,12 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		u64 pebs_status;
 
 		pebs_status = p->status & cpuc->pebs_enabled;
-		pebs_status &= (1ULL << x86_pmu.max_pebs_events) - 1;
+		pebs_status &= mask;
 
 		/* PEBS v3 has more accurate status bits */
 		if (x86_pmu.intel_cap.pebs_format >= 3) {
 			for_each_set_bit(bit, (unsigned long *)&pebs_status,
-					 x86_pmu.max_pebs_events)
+					 size)
 				counts[bit]++;
 
 			continue;
@@ -1575,7 +1593,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs)
 		counts[bit]++;
 	}
 
-	for (bit = 0; bit < x86_pmu.max_pebs_events; bit++) {
+	for (bit = 0; bit < size; bit++) {
 		if ((counts[bit] == 0) && (error[bit] == 0))
 			continue;
 
diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 62a9f4966b42..ae26df1c2789 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -8,6 +8,7 @@
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS		8
+#define MAX_FIXED_PEBS_EVENTS	3
 
 /*
  * A debug store configuration.
@@ -23,7 +24,7 @@ struct debug_store {
 	u64	pebs_index;
 	u64	pebs_absolute_maximum;
 	u64	pebs_interrupt_threshold;
-	u64	pebs_event_reset[MAX_PEBS_EVENTS];
+	u64	pebs_event_reset[MAX_PEBS_EVENTS + MAX_FIXED_PEBS_EVENTS];
 } __aligned(PAGE_SIZE);
 
 DECLARE_PER_CPU_PAGE_ALIGNED(struct debug_store, cpu_debug_store);
-- 
cgit v1.2.3


From a38b0ba1b7d2e7a6d19877540240e8a4352fc93c Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Thu, 8 Mar 2018 18:15:42 -0800
Subject: perf/x86/intel: Support Extended PEBS for Goldmont Plus

Enable the extended PEBS for Goldmont Plus.

There is no specific PEBS constrains for Goldmont Plus. Removing the
pebs_constraints for Goldmont Plus.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: acme@kernel.org
Link: http://lkml.kernel.org/r/20180309021542.11374-4-kan.liang@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/events/intel/core.c | 2 +-
 arch/x86/events/intel/ds.c   | 6 ------
 2 files changed, 1 insertion(+), 7 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index b1a49a108a59..035c37481f57 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4077,7 +4077,6 @@ __init int intel_pmu_init(void)
 		intel_pmu_lbr_init_skl();
 
 		x86_pmu.event_constraints = intel_slm_event_constraints;
-		x86_pmu.pebs_constraints = intel_glp_pebs_event_constraints;
 		x86_pmu.extra_regs = intel_glm_extra_regs;
 		/*
 		 * It's recommended to use CPU_CLK_UNHALTED.CORE_P + NPEBS
@@ -4087,6 +4086,7 @@ __init int intel_pmu_init(void)
 		x86_pmu.pebs_prec_dist = true;
 		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+		x86_pmu.flags |= PMU_FL_PEBS_ALL;
 		x86_pmu.get_event_constraints = glp_get_event_constraints;
 		x86_pmu.cpu_events = glm_events_attrs;
 		/* Goldmont Plus has 4-wide pipeline */
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 595b96ae8a00..b7b01d762d32 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -713,12 +713,6 @@ struct event_constraint intel_glm_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_glp_pebs_event_constraints[] = {
-	/* Allow all events as PEBS with no flags */
-	INTEL_ALL_EVENT_CONSTRAINT(0, 0xf),
-	EVENT_CONSTRAINT_END
-};
-
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
-- 
cgit v1.2.3


From 00d5551cc4eec0fc39c3871c25c613553acfb866 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 16 Jul 2018 12:30:07 +0100
Subject: locking/atomics/x86: Reduce arch_cmpxchg64*() instrumentation

Currently x86's arch_cmpxchg64() and arch_cmpxchg64_local() are
instrumented twice, as they call into instrumented atomics rather than
their arch_ equivalents.

A call to cmpxchg64() results in:

  cmpxchg64()
    kasan_check_write()
    arch_cmpxchg64()
      cmpxchg()
        kasan_check_write()
        arch_cmpxchg()

Let's fix this up and call the arch_ equivalents, resulting in:

  cmpxchg64()
    kasan_check_write()
    arch_cmpxchg64()
      arch_cmpxchg()

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: andy.shevchenko@gmail.com
Cc: arnd@arndb.de
Cc: aryabinin@virtuozzo.com
Cc: catalin.marinas@arm.com
Cc: glider@google.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: parri.andrea@gmail.com
Cc: peter@hurleysoftware.com
Link: http://lkml.kernel.org/r/20180716113017.3909-3-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/cmpxchg_64.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index bfca3b346c74..072e5459fe2f 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -10,13 +10,13 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 #define arch_cmpxchg64(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg((ptr), (o), (n));					\
+	arch_cmpxchg((ptr), (o), (n));					\
 })
 
 #define arch_cmpxchg64_local(ptr, o, n)					\
 ({									\
 	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
-	cmpxchg_local((ptr), (o), (n));					\
+	arch_cmpxchg_local((ptr), (o), (n));				\
 })
 
 #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
-- 
cgit v1.2.3


From df79ed2c064363cdc7d2d896923c1885d4e30520 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 16 Jul 2018 12:30:08 +0100
Subject: locking/atomics: Simplify cmpxchg() instrumentation

Currently we define some fairly verbose wrappers for the cmpxchg()
family so that we can pass a pointer and size into kasan_check_write().

The wrappers duplicate the size-switching logic necessary in arch code,
and only work for scalar types. On some architectures, (cmp)xchg are
used on non-scalar types, and thus the instrumented wrappers need to be
able to handle this.

We could take the type-punning logic from {READ,WRITE}_ONCE(), but this
makes the wrappers even more verbose, and requires several local
variables in the macros.

Instead, let's simplify the wrappers into simple macros which:

* snapshot the pointer into a single local variable, called __ai_ptr to
  avoid conflicts with variables in the scope of the caller.

* call kasan_check_write() on __ai_ptr.

* invoke the relevant arch_*() function, passing the original arguments,
  bar __ai_ptr being substituted for ptr.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: andy.shevchenko@gmail.com
Cc: arnd@arndb.de
Cc: aryabinin@virtuozzo.com
Cc: catalin.marinas@arm.com
Cc: glider@google.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: parri.andrea@gmail.com
Cc: peter@hurleysoftware.com
Link: http://lkml.kernel.org/r/20180716113017.3909-4-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/atomic-instrumented.h | 100 +++++-------------------------
 1 file changed, 15 insertions(+), 85 deletions(-)

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 3c64e95d5ed0..c7c3e4cdd942 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -408,109 +408,39 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 }
 #endif
 
-static __always_inline unsigned long
-cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new, int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define cmpxchg(ptr, old, new)						\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_size((ptr), (unsigned long)(old),	\
-		(unsigned long)(new), sizeof(*(ptr))));			\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline unsigned long
-sync_cmpxchg_size(volatile void *ptr, unsigned long old, unsigned long new,
-		  int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_sync_cmpxchg((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_sync_cmpxchg((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_sync_cmpxchg((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_sync_cmpxchg((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define sync_cmpxchg(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))sync_cmpxchg_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_sync_cmpxchg(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline unsigned long
-cmpxchg_local_size(volatile void *ptr, unsigned long old, unsigned long new,
-		   int size)
-{
-	kasan_check_write(ptr, size);
-	switch (size) {
-	case 1:
-		return arch_cmpxchg_local((u8 *)ptr, (u8)old, (u8)new);
-	case 2:
-		return arch_cmpxchg_local((u16 *)ptr, (u16)old, (u16)new);
-	case 4:
-		return arch_cmpxchg_local((u32 *)ptr, (u32)old, (u32)new);
-	case 8:
-		BUILD_BUG_ON(sizeof(unsigned long) != 8);
-		return arch_cmpxchg_local((u64 *)ptr, (u64)old, (u64)new);
-	}
-	BUILD_BUG();
-	return 0;
-}
-
 #define cmpxchg_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg_local_size((ptr),			\
-		(unsigned long)(old), (unsigned long)(new),		\
-		sizeof(*(ptr))));					\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg_local(__ai_ptr, (old), (new));			\
 })
 
-static __always_inline u64
-cmpxchg64_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64(ptr, old, new);
-}
-
 #define cmpxchg64(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_size((ptr), (u64)(old),		\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64(__ai_ptr, (old), (new));				\
 })
 
-static __always_inline u64
-cmpxchg64_local_size(volatile u64 *ptr, u64 old, u64 new)
-{
-	kasan_check_write(ptr, sizeof(*ptr));
-	return arch_cmpxchg64_local(ptr, old, new);
-}
-
 #define cmpxchg64_local(ptr, old, new)					\
 ({									\
-	((__typeof__(*(ptr)))cmpxchg64_local_size((ptr), (u64)(old),	\
-		(u64)(new)));						\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_cmpxchg64_local(__ai_ptr, (old), (new));			\
 })
 
 /*
-- 
cgit v1.2.3


From f9881cc43b118efc6f82fef2d121166113ee9f8e Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 16 Jul 2018 12:30:09 +0100
Subject: locking/atomics: Instrument xchg()

While we instrument all of the (non-relaxed) atomic_*() functions and
cmpxchg(), we missed xchg().

Let's add instrumentation for xchg(), fixing up x86 to implement
arch_xchg().

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: andy.shevchenko@gmail.com
Cc: arnd@arndb.de
Cc: aryabinin@virtuozzo.com
Cc: catalin.marinas@arm.com
Cc: glider@google.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: parri.andrea@gmail.com
Cc: peter@hurleysoftware.com
Link: http://lkml.kernel.org/r/20180716113017.3909-5-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/x86/include/asm/atomic.h             | 2 +-
 arch/x86/include/asm/atomic64_64.h        | 2 +-
 arch/x86/include/asm/cmpxchg.h            | 2 +-
 include/asm-generic/atomic-instrumented.h | 7 +++++++
 4 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 823fd2f320cf..b143717b92b3 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -202,7 +202,7 @@ static __always_inline bool arch_atomic_try_cmpxchg(atomic_t *v, int *old, int n
 
 static inline int arch_atomic_xchg(atomic_t *v, int new)
 {
-	return xchg(&v->counter, new);
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic_and(int i, atomic_t *v)
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 849f1c566a11..4343d9b4f30e 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -188,7 +188,7 @@ static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, l
 
 static inline long arch_atomic64_xchg(atomic64_t *v, long new)
 {
-	return xchg(&v->counter, new);
+	return arch_xchg(&v->counter, new);
 }
 
 static inline void arch_atomic64_and(long i, atomic64_t *v)
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index e3efd8a06066..a55d79b233d3 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -75,7 +75,7 @@ extern void __add_wrong_size(void)
  * use "asm volatile" and "memory" clobbers to prevent gcc from moving
  * information around.
  */
-#define xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
+#define arch_xchg(ptr, v)	__xchg_op((ptr), (v), xchg, "")
 
 /*
  * Atomic compare and exchange.  Compare OLD with MEM, if identical,
diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index c7c3e4cdd942..53481b6eacdf 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -408,6 +408,13 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 }
 #endif
 
+#define xchg(ptr, new)							\
+({									\
+	typeof(ptr) __ai_ptr = (ptr);					\
+	kasan_check_write(__ai_ptr, sizeof(*__ai_ptr));			\
+	arch_xchg(__ai_ptr, (new));					\
+})
+
 #define cmpxchg(ptr, old, new)						\
 ({									\
 	typeof(ptr) __ai_ptr = (ptr);					\
-- 
cgit v1.2.3


From 4d2b25f630c731218d04f72580b4de68cb7a6e00 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 16 Jul 2018 12:30:10 +0100
Subject: locking/atomics: Instrument cmpxchg_double*()

We currently don't instrument cmpxchg_double() and
cmpxchg_double_local() due to compilation issues reported in the past,
which are supposedly related to GCC bug 72873 [1], reported when GCC 7
was not yet released. This bug only applies to x86-64, and does not
apply to other architectures.

While the test case for GCC bug 72873 triggers issues with released
versions of GCC, the instrumented kernel code compiles fine for all
configurations I have tried, and it is unclear how the two cases
are/were related.

As we can't reproduce the kernel build failures, let's instrument
cmpxchg_double*() again. We can revisit the issue if build failures
reappear.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Dmitry Vyukov <dvyukov@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: andy.shevchenko@gmail.com
Cc: aryabinin@virtuozzo.com
Cc: catalin.marinas@arm.com
Cc: glider@google.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: parri.andrea@gmail.com
Cc: peter@hurleysoftware.com
Link: http://lkml.kernel.org/r/20180716113017.3909-6-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/asm-generic/atomic-instrumented.h | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/include/asm-generic/atomic-instrumented.h b/include/asm-generic/atomic-instrumented.h
index 53481b6eacdf..0d4b1d3dbc1e 100644
--- a/include/asm-generic/atomic-instrumented.h
+++ b/include/asm-generic/atomic-instrumented.h
@@ -450,23 +450,18 @@ static __always_inline bool atomic64_add_negative(s64 i, atomic64_t *v)
 	arch_cmpxchg64_local(__ai_ptr, (old), (new));			\
 })
 
-/*
- * Originally we had the following code here:
- *     __typeof__(p1) ____p1 = (p1);
- *     kasan_check_write(____p1, 2 * sizeof(*____p1));
- *     arch_cmpxchg_double(____p1, (p2), (o1), (o2), (n1), (n2));
- * But it leads to compilation failures (see gcc issue 72873).
- * So for now it's left non-instrumented.
- * There are few callers of cmpxchg_double(), so it's not critical.
- */
 #define cmpxchg_double(p1, p2, o1, o2, n1, n2)				\
 ({									\
-	arch_cmpxchg_double((p1), (p2), (o1), (o2), (n1), (n2));	\
+	typeof(p1) __ai_p1 = (p1);					\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));		\
+	arch_cmpxchg_double(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
-#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)			\
-({									\
-	arch_cmpxchg_double_local((p1), (p2), (o1), (o2), (n1), (n2));	\
+#define cmpxchg_double_local(p1, p2, o1, o2, n1, n2)				\
+({										\
+	typeof(p1) __ai_p1 = (p1);						\
+	kasan_check_write(__ai_p1, 2 * sizeof(*__ai_p1));			\
+	arch_cmpxchg_double_local(__ai_p1, (p2), (o1), (o2), (n1), (n2));	\
 })
 
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-- 
cgit v1.2.3


From fd2efaa4eb5317c3a86357a83a7d456a1b86a0ac Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Mon, 16 Jul 2018 12:30:11 +0100
Subject: locking/atomics: Rework ordering barriers

Currently architectures can override __atomic_op_*() to define the barriers
used before/after a relaxed atomic when used to build acquire/release/fence
variants.

This has the unfortunate property of requiring the architecture to define the
full wrapper for the atomics, rather than just the barriers they care about,
and gets in the way of generating atomics which can be easily read.

Instead, this patch has architectures define an optional set of barriers:

* __atomic_acquire_fence()
* __atomic_release_fence()
* __atomic_pre_full_fence()
* __atomic_post_full_fence()

... which <linux/atomic.h> uses to build the wrappers.

It would be nice if we could undef these, along with the __atomic_op_*()
wrappers, but that would break the cmpxchg() wrappers, which are written
in preprocessor. Undefs would have been nice, but alas.

There should be no functional change as a result of this patch.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Cc: Andrea Parri <parri.andrea@gmail.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: andy.shevchenko@gmail.com
Cc: arnd@arndb.de
Cc: aryabinin@virtuozzo.com
Cc: catalin.marinas@arm.com
Cc: dvyukov@google.com
Cc: glider@google.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: peter@hurleysoftware.com
Link: http://lkml.kernel.org/r/20180716113017.3909-7-mark.rutland@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/alpha/include/asm/atomic.h   |  8 ++++----
 arch/powerpc/include/asm/atomic.h | 17 +++++------------
 arch/riscv/include/asm/atomic.h   | 17 +++++------------
 include/linux/atomic.h            | 38 ++++++++++++++++++++++----------------
 4 files changed, 36 insertions(+), 44 deletions(-)

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 4a6a8f58c9c9..150a1c5d6a2c 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -18,11 +18,11 @@
  * To ensure dependency ordering is preserved for the _relaxed and
  * _release atomics, an smp_read_barrier_depends() is unconditionally
  * inserted into the _relaxed variants, which are used to build the
- * barriered versions. To avoid redundant back-to-back fences, we can
- * define the _acquire and _fence versions explicitly.
+ * barriered versions. Avoid redundant back-to-back fences in the
+ * _acquire and _fence versions.
  */
-#define __atomic_op_acquire(op, args...)	op##_relaxed(args)
-#define __atomic_op_fence			__atomic_op_release
+#define __atomic_acquire_fence()
+#define __atomic_post_full_fence()
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index a0156cb43d1f..963abf8bf1c0 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -18,18 +18,11 @@
  * a "bne-" instruction at the end, so an isync is enough as a acquire barrier
  * on the platform without lwsync.
  */
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(PPC_ACQUIRE_BARRIER "" : : : "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(PPC_RELEASE_BARRIER "" : : : "memory")
 
 static __inline__ int atomic_read(const atomic_t *v)
 {
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 512b89485790..c452359c9cb8 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -25,18 +25,11 @@
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define __atomic_op_acquire(op, args...)				\
-({									\
-	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory");	\
-	__ret;								\
-})
-
-#define __atomic_op_release(op, args...)				\
-({									\
-	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");	\
-	op##_relaxed(args);						\
-})
+#define __atomic_acquire_fence()					\
+	__asm__ __volatile__(RISCV_ACQUIRE_BARRIER "" ::: "memory")
+
+#define __atomic_release_fence()					\
+	__asm__ __volatile__(RISCV_RELEASE_BARRIER "" ::: "memory");
 
 static __always_inline int atomic_read(const atomic_t *v)
 {
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 8e04f1f69bd9..1e8e88bdaf09 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -38,40 +38,46 @@
  * barriers on top of the relaxed variant. In the case where the relaxed
  * variant is already fully ordered, no additional barriers are needed.
  *
- * Besides, if an arch has a special barrier for acquire/release, it could
- * implement its own __atomic_op_* and use the same framework for building
- * variants
- *
- * If an architecture overrides __atomic_op_acquire() it will probably want
- * to define smp_mb__after_spinlock().
+ * If an architecture overrides __atomic_acquire_fence() it will probably
+ * want to define smp_mb__after_spinlock().
  */
-#ifndef __atomic_op_acquire
+#ifndef __atomic_acquire_fence
+#define __atomic_acquire_fence		smp_mb__after_atomic
+#endif
+
+#ifndef __atomic_release_fence
+#define __atomic_release_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_pre_full_fence
+#define __atomic_pre_full_fence		smp_mb__before_atomic
+#endif
+
+#ifndef __atomic_post_full_fence
+#define __atomic_post_full_fence	smp_mb__after_atomic
+#endif
+
 #define __atomic_op_acquire(op, args...)				\
 ({									\
 	typeof(op##_relaxed(args)) __ret  = op##_relaxed(args);		\
-	smp_mb__after_atomic();						\
+	__atomic_acquire_fence();					\
 	__ret;								\
 })
-#endif
 
-#ifndef __atomic_op_release
 #define __atomic_op_release(op, args...)				\
 ({									\
-	smp_mb__before_atomic();					\
+	__atomic_release_fence();					\
 	op##_relaxed(args);						\
 })
-#endif
 
-#ifndef __atomic_op_fence
 #define __atomic_op_fence(op, args...)					\
 ({									\
 	typeof(op##_relaxed(args)) __ret;				\
-	smp_mb__before_atomic();					\
+	__atomic_pre_full_fence();					\
 	__ret = op##_relaxed(args);					\
-	smp_mb__after_atomic();						\
+	__atomic_post_full_fence();					\
 	__ret;								\
 })
-#endif
 
 /* atomic_add_return_relaxed */
 #ifndef atomic_add_return_relaxed
-- 
cgit v1.2.3


From 063daa8129f94d651c4d30a8333b577c5bbf8090 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Wed, 25 Jul 2018 11:55:57 +0200
Subject: arm/asm/tlb.h: Fix build error implicit func declaration
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Building on arm 32 with LPAE enabled we don't include asm-generic/tlb.h,
where we have tlb_flush_remove_tables_local and tlb_flush_remove_tables
defined.

The build fails with:

  mm/memory.c: In function ‘tlb_remove_table_smp_sync’:
  mm/memory.c:339:2: error: implicit declaration of function ‘tlb_flush_remove_tables_local’; did you mean ‘tlb_remove_table’? [-Werror=implicit-function-declaration]
  ...

This bug got introduced in:

  2ff6ddf19c0e ("x86/mm/tlb: Leave lazy TLB mode at page table free time")

To fix this issue we define them in arm 32's specific asm/tlb.h file as well.

Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dave.hansen@intel.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: linux@armlinux.org.uk
Cc: riel@surriel.com
Cc: songliubraving@fb.com
Fixes: 2ff6ddf19c0e ("x86/mm/tlb: Leave lazy TLB mode at page table free time")
Link: http://lkml.kernel.org/r/20180725095557.19668-1-anders.roxell@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 arch/arm/include/asm/tlb.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/arch/arm/include/asm/tlb.h b/arch/arm/include/asm/tlb.h
index d5562f9ce600..f854148c8d7c 100644
--- a/arch/arm/include/asm/tlb.h
+++ b/arch/arm/include/asm/tlb.h
@@ -292,5 +292,13 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb,
 {
 }
 
+static inline void tlb_flush_remove_tables(struct mm_struct *mm)
+{
+}
+
+static inline void tlb_flush_remove_tables_local(void *arg)
+{
+}
+
 #endif /* CONFIG_MMU */
 #endif
-- 
cgit v1.2.3


From fbf8ad7ef40aeb4cd8ee70503cd7cbeb4144051f Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 28 Jun 2018 07:42:57 -0400
Subject: media: cec-gpio.txt: add v5-gpios for testing the 5V line

In order to debug the HDMI 5V line we need to add a new v5-gpios
property.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../devicetree/bindings/media/cec-gpio.txt         | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/cec-gpio.txt b/Documentation/devicetree/bindings/media/cec-gpio.txt
index 12fcd55ed153..47e8d73d32a3 100644
--- a/Documentation/devicetree/bindings/media/cec-gpio.txt
+++ b/Documentation/devicetree/bindings/media/cec-gpio.txt
@@ -4,8 +4,8 @@ The HDMI CEC GPIO module supports CEC implementations where the CEC line
 is hooked up to a pull-up GPIO line and - optionally - the HPD line is
 hooked up to another GPIO line.
 
-Please note: the maximum voltage for the CEC line is 3.63V, for the HPD
-line it is 5.3V. So you may need some sort of level conversion circuitry
+Please note: the maximum voltage for the CEC line is 3.63V, for the HPD and
+5V lines it is 5.3V. So you may need some sort of level conversion circuitry
 when connecting them to a GPIO line.
 
 Required properties:
@@ -19,18 +19,24 @@ following property is also required:
   - hdmi-phandle - phandle to the HDMI controller, see also cec.txt.
 
 If the CEC line is not associated with an HDMI receiver/transmitter, then
-the following property is optional:
+the following property is optional and can be used for debugging HPD changes:
 
   - hpd-gpios: gpio that the HPD line is connected to.
 
+This property is optional and can be used for debugging changes on the 5V line:
+
+  - v5-gpios: gpio that the 5V line is connected to.
+
 Example for the Raspberry Pi 3 where the CEC line is connected to
-pin 26 aka BCM7 aka CE1 on the GPIO pin header and the HPD line is
-connected to pin 11 aka BCM17 (some level shifter is needed for this!):
+pin 26 aka BCM7 aka CE1 on the GPIO pin header, the HPD line is
+connected to pin 11 aka BCM17 and the 5V line is connected to pin
+15 aka BCM22 (some level shifter is needed for the HPD and 5V lines!):
 
 #include <dt-bindings/gpio/gpio.h>
 
 cec-gpio {
-       compatible = "cec-gpio";
-       cec-gpios = <&gpio 7 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
-       hpd-gpios = <&gpio 17 GPIO_ACTIVE_HIGH>;
+	compatible = "cec-gpio";
+	cec-gpios = <&gpio 7 (GPIO_ACTIVE_HIGH|GPIO_OPEN_DRAIN)>;
+	hpd-gpios = <&gpio 17 GPIO_ACTIVE_HIGH>;
+	v5-gpios = <&gpio 22 GPIO_ACTIVE_HIGH>;
 };
-- 
cgit v1.2.3


From 5105b484cc0be4ba34d49ed054863e16bc85edd2 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 28 Jun 2018 10:07:41 -0400
Subject: media: cec-ioc-dqevent.rst: document the new 5V events

Document the two new 5V events.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/cec/cec-ioc-dqevent.rst | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
index b6fd86424fbb..8d5633e6ae04 100644
--- a/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
+++ b/Documentation/media/uapi/cec/cec-ioc-dqevent.rst
@@ -179,6 +179,24 @@ it is guaranteed that the state did change in between the two events.
 	capability set. When open() is called, the HPD pin can be read and
 	if the HPD is high, then an initial event will be generated for that
 	filehandle.
+    * .. _`CEC-EVENT-PIN-5V-LOW`:
+
+      - ``CEC_EVENT_PIN_5V_LOW``
+      - 6
+      - Generated if the 5V pin goes from a high voltage to a low voltage.
+	Only applies to adapters that have the ``CEC_CAP_MONITOR_PIN``
+	capability set. When open() is called, the 5V pin can be read and
+	if the 5V is low, then an initial event will be generated for that
+	filehandle.
+    * .. _`CEC-EVENT-PIN-5V-HIGH`:
+
+      - ``CEC_EVENT_PIN_5V_HIGH``
+      - 7
+      - Generated if the 5V pin goes from a low voltage to a high voltage.
+	Only applies to adapters that have the ``CEC_CAP_MONITOR_PIN``
+	capability set. When open() is called, the 5V pin can be read and
+	if the 5V is high, then an initial event will be generated for that
+	filehandle.
 
 
 .. tabularcolumns:: |p{6.0cm}|p{0.6cm}|p{10.9cm}|
-- 
cgit v1.2.3


From f48a534adbd321362c3199140008c9e2f2a81b3a Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 28 Jun 2018 07:43:26 -0400
Subject: media: uapi/linux/cec.h: add 5V events

Add two new events to signal when the 5V line goes high or low.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 include/uapi/linux/cec.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/uapi/linux/cec.h b/include/uapi/linux/cec.h
index 20fe091b7e96..097fcd812471 100644
--- a/include/uapi/linux/cec.h
+++ b/include/uapi/linux/cec.h
@@ -384,6 +384,8 @@ struct cec_log_addrs {
 #define CEC_EVENT_PIN_CEC_HIGH		4
 #define CEC_EVENT_PIN_HPD_LOW		5
 #define CEC_EVENT_PIN_HPD_HIGH		6
+#define CEC_EVENT_PIN_5V_LOW		7
+#define CEC_EVENT_PIN_5V_HIGH		8
 
 #define CEC_EVENT_FL_INITIAL_STATE	(1 << 0)
 #define CEC_EVENT_FL_DROPPED_EVENTS	(1 << 1)
-- 
cgit v1.2.3


From 4786b0d6f3ca6da8db02b0a58cd2b785cb0b80ab Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 28 Jun 2018 07:43:46 -0400
Subject: media: cec: add support for 5V signal testing

Add support for the new 5V CEC events

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/cec/cec-adap.c | 18 +++++++++++++++++-
 drivers/media/cec/cec-api.c  |  8 ++++++++
 include/media/cec-pin.h      |  4 ++++
 include/media/cec.h          | 12 +++++++++++-
 4 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/media/cec/cec-adap.c b/drivers/media/cec/cec-adap.c
index b7fad0ec5710..030b2602faf0 100644
--- a/drivers/media/cec/cec-adap.c
+++ b/drivers/media/cec/cec-adap.c
@@ -74,7 +74,7 @@ void cec_queue_event_fh(struct cec_fh *fh,
 			const struct cec_event *new_ev, u64 ts)
 {
 	static const u16 max_events[CEC_NUM_EVENTS] = {
-		1, 1, 800, 800, 8, 8,
+		1, 1, 800, 800, 8, 8, 8, 8
 	};
 	struct cec_event_entry *entry;
 	unsigned int ev_idx = new_ev->event - 1;
@@ -176,6 +176,22 @@ void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts)
 }
 EXPORT_SYMBOL_GPL(cec_queue_pin_hpd_event);
 
+/* Notify userspace that the 5V pin changed state at the given time. */
+void cec_queue_pin_5v_event(struct cec_adapter *adap, bool is_high, ktime_t ts)
+{
+	struct cec_event ev = {
+		.event = is_high ? CEC_EVENT_PIN_5V_HIGH :
+				   CEC_EVENT_PIN_5V_LOW,
+	};
+	struct cec_fh *fh;
+
+	mutex_lock(&adap->devnode.lock);
+	list_for_each_entry(fh, &adap->devnode.fhs, list)
+		cec_queue_event_fh(fh, &ev, ktime_to_ns(ts));
+	mutex_unlock(&adap->devnode.lock);
+}
+EXPORT_SYMBOL_GPL(cec_queue_pin_5v_event);
+
 /*
  * Queue a new message for this filehandle.
  *
diff --git a/drivers/media/cec/cec-api.c b/drivers/media/cec/cec-api.c
index 10b67fc40318..b6536bbad530 100644
--- a/drivers/media/cec/cec-api.c
+++ b/drivers/media/cec/cec-api.c
@@ -579,6 +579,14 @@ static int cec_open(struct inode *inode, struct file *filp)
 			cec_queue_event_fh(fh, &ev, 0);
 		}
 	}
+	if (adap->pin && adap->pin->ops->read_5v) {
+		err = adap->pin->ops->read_5v(adap);
+		if (err >= 0) {
+			ev.event = err ? CEC_EVENT_PIN_5V_HIGH :
+					 CEC_EVENT_PIN_5V_LOW;
+			cec_queue_event_fh(fh, &ev, 0);
+		}
+	}
 #endif
 
 	list_add(&fh->list, &devnode->fhs);
diff --git a/include/media/cec-pin.h b/include/media/cec-pin.h
index ed16c6dde0ba..604e79cb6cbf 100644
--- a/include/media/cec-pin.h
+++ b/include/media/cec-pin.h
@@ -25,6 +25,9 @@
  * @read_hpd:	read the HPD pin. Return true if high, false if low or
  *		an error if negative. If NULL or -ENOTTY is returned,
  *		then this is not supported.
+ * @read_5v:	read the 5V pin. Return true if high, false if low or
+ *		an error if negative. If NULL or -ENOTTY is returned,
+ *		then this is not supported.
  *
  * These operations are used by the cec pin framework to manipulate
  * the CEC pin.
@@ -38,6 +41,7 @@ struct cec_pin_ops {
 	void (*free)(struct cec_adapter *adap);
 	void (*status)(struct cec_adapter *adap, struct seq_file *file);
 	int  (*read_hpd)(struct cec_adapter *adap);
+	int  (*read_5v)(struct cec_adapter *adap);
 };
 
 /**
diff --git a/include/media/cec.h b/include/media/cec.h
index 580ab1042898..ff9847f7f99d 100644
--- a/include/media/cec.h
+++ b/include/media/cec.h
@@ -79,7 +79,7 @@ struct cec_event_entry {
 };
 
 #define CEC_NUM_CORE_EVENTS 2
-#define CEC_NUM_EVENTS CEC_EVENT_PIN_HPD_HIGH
+#define CEC_NUM_EVENTS CEC_EVENT_PIN_5V_HIGH
 
 struct cec_fh {
 	struct list_head	list;
@@ -308,6 +308,16 @@ void cec_queue_pin_cec_event(struct cec_adapter *adap, bool is_high,
  */
 void cec_queue_pin_hpd_event(struct cec_adapter *adap, bool is_high, ktime_t ts);
 
+/**
+ * cec_queue_pin_5v_event() - queue a pin event with a given timestamp.
+ *
+ * @adap:	pointer to the cec adapter
+ * @is_high:	when true the 5V pin is high, otherwise it is low
+ * @ts:		the timestamp for this event
+ *
+ */
+void cec_queue_pin_5v_event(struct cec_adapter *adap, bool is_high, ktime_t ts);
+
 /**
  * cec_get_edid_phys_addr() - find and return the physical address
  *
-- 
cgit v1.2.3


From 76e464888b1c367fddaf67f23ee3e0aa4ca8cef4 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Thu, 28 Jun 2018 07:44:03 -0400
Subject: media: cec-gpio: support 5v testing

Add support for the new (optional) 5V gpio in order to debug 5V
changes. Some displays turn off CEC if the 5V is not detected,
so it is useful to be able to monitor this line.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/cec-gpio/cec-gpio.c | 54 ++++++++++++++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/drivers/media/platform/cec-gpio/cec-gpio.c b/drivers/media/platform/cec-gpio/cec-gpio.c
index 69f8242209c2..d2861749d640 100644
--- a/drivers/media/platform/cec-gpio/cec-gpio.c
+++ b/drivers/media/platform/cec-gpio/cec-gpio.c
@@ -23,6 +23,11 @@ struct cec_gpio {
 	int			hpd_irq;
 	bool			hpd_is_high;
 	ktime_t			hpd_ts;
+
+	struct gpio_desc	*v5_gpio;
+	int			v5_irq;
+	bool			v5_is_high;
+	ktime_t			v5_ts;
 };
 
 static bool cec_gpio_read(struct cec_adapter *adap)
@@ -65,6 +70,26 @@ static irqreturn_t cec_hpd_gpio_irq_handler_thread(int irq, void *priv)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t cec_5v_gpio_irq_handler(int irq, void *priv)
+{
+	struct cec_gpio *cec = priv;
+	bool is_high = gpiod_get_value(cec->v5_gpio);
+
+	if (is_high == cec->v5_is_high)
+		return IRQ_HANDLED;
+	cec->v5_ts = ktime_get();
+	cec->v5_is_high = is_high;
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t cec_5v_gpio_irq_handler_thread(int irq, void *priv)
+{
+	struct cec_gpio *cec = priv;
+
+	cec_queue_pin_5v_event(cec->adap, cec->v5_is_high, cec->v5_ts);
+	return IRQ_HANDLED;
+}
+
 static irqreturn_t cec_hpd_gpio_irq_handler(int irq, void *priv)
 {
 	struct cec_gpio *cec = priv;
@@ -119,6 +144,9 @@ static void cec_gpio_status(struct cec_adapter *adap, struct seq_file *file)
 	if (cec->hpd_gpio)
 		seq_printf(file, "hpd: %s\n",
 			   cec->hpd_is_high ? "high" : "low");
+	if (cec->v5_gpio)
+		seq_printf(file, "5V: %s\n",
+			   cec->v5_is_high ? "high" : "low");
 }
 
 static int cec_gpio_read_hpd(struct cec_adapter *adap)
@@ -130,6 +158,15 @@ static int cec_gpio_read_hpd(struct cec_adapter *adap)
 	return gpiod_get_value(cec->hpd_gpio);
 }
 
+static int cec_gpio_read_5v(struct cec_adapter *adap)
+{
+	struct cec_gpio *cec = cec_get_drvdata(adap);
+
+	if (!cec->v5_gpio)
+		return -ENOTTY;
+	return gpiod_get_value(cec->v5_gpio);
+}
+
 static void cec_gpio_free(struct cec_adapter *adap)
 {
 	cec_gpio_disable_irq(adap);
@@ -144,6 +181,7 @@ static const struct cec_pin_ops cec_gpio_pin_ops = {
 	.status = cec_gpio_status,
 	.free = cec_gpio_free,
 	.read_hpd = cec_gpio_read_hpd,
+	.read_5v = cec_gpio_read_5v,
 };
 
 static int cec_gpio_probe(struct platform_device *pdev)
@@ -167,6 +205,10 @@ static int cec_gpio_probe(struct platform_device *pdev)
 	if (IS_ERR(cec->hpd_gpio))
 		return PTR_ERR(cec->hpd_gpio);
 
+	cec->v5_gpio = devm_gpiod_get_optional(dev, "v5", GPIOD_IN);
+	if (IS_ERR(cec->v5_gpio))
+		return PTR_ERR(cec->v5_gpio);
+
 	cec->adap = cec_pin_allocate_adapter(&cec_gpio_pin_ops,
 		cec, pdev->name, CEC_CAP_DEFAULTS | CEC_CAP_PHYS_ADDR |
 				 CEC_CAP_MONITOR_ALL | CEC_CAP_MONITOR_PIN);
@@ -185,6 +227,18 @@ static int cec_gpio_probe(struct platform_device *pdev)
 			return ret;
 	}
 
+	if (cec->v5_gpio) {
+		cec->v5_irq = gpiod_to_irq(cec->v5_gpio);
+		ret = devm_request_threaded_irq(dev, cec->v5_irq,
+			cec_5v_gpio_irq_handler,
+			cec_5v_gpio_irq_handler_thread,
+			IRQF_ONESHOT |
+			IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
+			"v5-gpio", cec);
+		if (ret)
+			return ret;
+	}
+
 	ret = cec_register_adapter(cec->adap, &pdev->dev);
 	if (ret) {
 		cec_delete_adapter(cec->adap);
-- 
cgit v1.2.3


From d27fb99f62af7b79c542d161aa5155ed57271ddc Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 22:42:48 +0100
Subject: dma-mapping: relax warning for per-device areas

The reasons why dma_free_attrs() should not be called from IRQ context
are not necessarily obvious and somewhat buried in the development
history, so let's start by documenting the warning itself to help anyone
who does happen to hit it and wonder what the deal is.

However, this check turns out to be slightly over-restrictive for the
way that per-device memory has been spliced into the general API, since
for that case we know that dma_declare_coherent_memory() has created an
appropriate CPU mapping for the entire area and nothing dynamic should
be happening. Given that the usage model for per-device memory is often
more akin to streaming DMA than 'real' coherent DMA (e.g. allocating and
freeing space to copy short-lived packets in and out), it is also
somewhat more reasonable for those operations to happen in IRQ handlers
for such devices.

Therefore, let's move the irqs_disabled() check down past the per-device
area hook, so that that gets a chance to resolve the request before we
reach definite "you're doing it wrong" territory.

Reported-by: Fredrik Noring <noring@nocrew.org>
Tested-by: Fredrik Noring <noring@nocrew.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/dma-mapping.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index f9cc309507d9..1db6a6b46d0d 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -538,10 +538,17 @@ static inline void dma_free_attrs(struct device *dev, size_t size,
 	const struct dma_map_ops *ops = get_dma_ops(dev);
 
 	BUG_ON(!ops);
-	WARN_ON(irqs_disabled());
 
 	if (dma_release_from_dev_coherent(dev, get_order(size), cpu_addr))
 		return;
+	/*
+	 * On non-coherent platforms which implement DMA-coherent buffers via
+	 * non-cacheable remaps, ops->free() may call vunmap(). Thus getting
+	 * this far in IRQ context is a) at risk of a BUG_ON() or trying to
+	 * sleep on some machines, and b) an indication that the driver is
+	 * probably misusing the coherent API anyway.
+	 */
+	WARN_ON(irqs_disabled());
 
 	if (!ops->free || !cpu_addr)
 		return;
-- 
cgit v1.2.3


From 7d63fb3af87aa67aa7d24466e792f9d7c57d8e79 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 10 Jul 2018 16:22:22 -0700
Subject: swiotlb: clean up reporting

This removes needless use of '%p', and refactors the printk calls to
use pr_*() helpers instead.

Signed-off-by: Kees Cook <keescook@chromium.org>
Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 kernel/dma/swiotlb.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 904541055792..4f8a6dbf0b60 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -17,6 +17,8 @@
  * 08/12/11 beckyb	Add highmem support
  */
 
+#define pr_fmt(fmt) "software IO TLB: " fmt
+
 #include <linux/cache.h>
 #include <linux/dma-direct.h>
 #include <linux/mm.h>
@@ -162,20 +164,16 @@ static bool no_iotlb_memory;
 void swiotlb_print_info(void)
 {
 	unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
-	unsigned char *vstart, *vend;
 
 	if (no_iotlb_memory) {
-		pr_warn("software IO TLB: No low mem\n");
+		pr_warn("No low mem\n");
 		return;
 	}
 
-	vstart = phys_to_virt(io_tlb_start);
-	vend = phys_to_virt(io_tlb_end);
-
-	printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+	pr_info("mapped [mem %#010llx-%#010llx] (%luMB)\n",
 	       (unsigned long long)io_tlb_start,
 	       (unsigned long long)io_tlb_end,
-	       bytes >> 20, vstart, vend - 1);
+	       bytes >> 20);
 }
 
 /*
@@ -275,7 +273,7 @@ swiotlb_init(int verbose)
 	if (io_tlb_start)
 		memblock_free_early(io_tlb_start,
 				    PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
-	pr_warn("Cannot allocate SWIOTLB buffer");
+	pr_warn("Cannot allocate buffer");
 	no_iotlb_memory = true;
 }
 
@@ -317,8 +315,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
 		return -ENOMEM;
 	}
 	if (order != get_order(bytes)) {
-		printk(KERN_WARNING "Warning: only able to allocate %ld MB "
-		       "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+		pr_warn("only able to allocate %ld MB\n",
+			(PAGE_SIZE << order) >> 20);
 		io_tlb_nslabs = SLABS_PER_PAGE << order;
 	}
 	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
-- 
cgit v1.2.3


From 25622e045a6aed45c9b12d1977fcb3fc3b349a73 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Apr 2018 19:27:22 +0200
Subject: nios2: use generic dma_noncoherent_ops

Switch to the generic noncoherent direct mapping implementation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ley Foon Tan <ley.foon.tan@intel.com>
Tested-by: Ley Foon Tan <ley.foon.tan@intel.com>
---
 arch/nios2/Kconfig                   |   3 +
 arch/nios2/include/asm/Kbuild        |   1 +
 arch/nios2/include/asm/dma-mapping.h |  20 -----
 arch/nios2/mm/dma-mapping.c          | 139 ++++-------------------------------
 4 files changed, 17 insertions(+), 146 deletions(-)
 delete mode 100644 arch/nios2/include/asm/dma-mapping.h

diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 3d4ec88f1db1..92035042cf62 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -1,6 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
 config NIOS2
 	def_bool y
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
 	select TIMER_OF
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/nios2/include/asm/Kbuild b/arch/nios2/include/asm/Kbuild
index 64ed3d656956..8fde4fa2c34f 100644
--- a/arch/nios2/include/asm/Kbuild
+++ b/arch/nios2/include/asm/Kbuild
@@ -9,6 +9,7 @@ generic-y += current.h
 generic-y += device.h
 generic-y += div64.h
 generic-y += dma.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += extable.h
diff --git a/arch/nios2/include/asm/dma-mapping.h b/arch/nios2/include/asm/dma-mapping.h
deleted file mode 100644
index 6ceb92251da0..000000000000
--- a/arch/nios2/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * Copyright (C) 2011 Tobias Klauser <tklauser@distanz.ch>
- * Copyright (C) 2009 Wind River Systems Inc
- *
- * This file is subject to the terms and conditions of the GNU General
- * Public License.  See the file COPYING in the main directory of this
- * archive for more details.
- */
-
-#ifndef _ASM_NIOS2_DMA_MAPPING_H
-#define _ASM_NIOS2_DMA_MAPPING_H
-
-extern const struct dma_map_ops nios2_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-	return &nios2_dma_ops;
-}
-
-#endif /* _ASM_NIOS2_DMA_MAPPING_H */
diff --git a/arch/nios2/mm/dma-mapping.c b/arch/nios2/mm/dma-mapping.c
index 4be815519dd4..4af9e5b5ba1c 100644
--- a/arch/nios2/mm/dma-mapping.c
+++ b/arch/nios2/mm/dma-mapping.c
@@ -12,18 +12,18 @@
 
 #include <linux/types.h>
 #include <linux/mm.h>
-#include <linux/export.h>
 #include <linux/string.h>
-#include <linux/scatterlist.h>
 #include <linux/dma-mapping.h>
 #include <linux/io.h>
 #include <linux/cache.h>
 #include <asm/cacheflush.h>
 
-static inline void __dma_sync_for_device(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	switch (direction) {
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
 	case DMA_FROM_DEVICE:
 		invalidate_dcache_range((unsigned long)vaddr,
 			(unsigned long)(vaddr + size));
@@ -42,10 +42,12 @@ static inline void __dma_sync_for_device(void *vaddr, size_t size,
 	}
 }
 
-static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
-			      enum dma_data_direction direction)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	switch (direction) {
+	void *vaddr = phys_to_virt(paddr);
+
+	switch (dir) {
 	case DMA_BIDIRECTIONAL:
 	case DMA_FROM_DEVICE:
 		invalidate_dcache_range((unsigned long)vaddr,
@@ -58,8 +60,8 @@ static inline void __dma_sync_for_cpu(void *vaddr, size_t size,
 	}
 }
 
-static void *nios2_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	void *ret;
 
@@ -80,125 +82,10 @@ static void *nios2_dma_alloc(struct device *dev, size_t size,
 	return ret;
 }
 
-static void nios2_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	unsigned long addr = (unsigned long) CAC_ADDR((unsigned long) vaddr);
 
 	free_pages(addr, get_order(size));
 }
-
-static int nios2_dma_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-
-	for_each_sg(sg, sg, nents, i) {
-		void *addr = sg_virt(sg);
-
-		if (!addr)
-			continue;
-
-		sg->dma_address = sg_phys(sg);
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		__dma_sync_for_device(addr, sg->length, direction);
-	}
-
-	return nents;
-}
-
-static dma_addr_t nios2_dma_map_page(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction direction,
-			unsigned long attrs)
-{
-	void *addr = page_address(page) + offset;
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_for_device(addr, size, direction);
-
-	return page_to_phys(page) + offset;
-}
-
-static void nios2_dma_unmap_page(struct device *dev, dma_addr_t dma_address,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		__dma_sync_for_cpu(phys_to_virt(dma_address), size, direction);
-}
-
-static void nios2_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-		int nhwentries, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	void *addr;
-	int i;
-
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	for_each_sg(sg, sg, nhwentries, i) {
-		addr = sg_virt(sg);
-		if (addr)
-			__dma_sync_for_cpu(addr, sg->length, direction);
-	}
-}
-
-static void nios2_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	__dma_sync_for_cpu(phys_to_virt(dma_handle), size, direction);
-}
-
-static void nios2_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	__dma_sync_for_device(phys_to_virt(dma_handle), size, direction);
-}
-
-static void nios2_dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sg, int nelems,
-		enum dma_data_direction direction)
-{
-	int i;
-
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for_each_sg(sg, sg, nelems, i)
-		__dma_sync_for_cpu(sg_virt(sg), sg->length, direction);
-}
-
-static void nios2_dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sg, int nelems,
-		enum dma_data_direction direction)
-{
-	int i;
-
-	/* Make sure that gcc doesn't leave the empty loop body.  */
-	for_each_sg(sg, sg, nelems, i)
-		__dma_sync_for_device(sg_virt(sg), sg->length, direction);
-
-}
-
-const struct dma_map_ops nios2_dma_ops = {
-	.alloc			= nios2_dma_alloc,
-	.free			= nios2_dma_free,
-	.map_page		= nios2_dma_map_page,
-	.unmap_page		= nios2_dma_unmap_page,
-	.map_sg			= nios2_dma_map_sg,
-	.unmap_sg		= nios2_dma_unmap_sg,
-	.sync_single_for_device	= nios2_dma_sync_single_for_device,
-	.sync_single_for_cpu	= nios2_dma_sync_single_for_cpu,
-	.sync_sg_for_cpu	= nios2_dma_sync_sg_for_cpu,
-	.sync_sg_for_device	= nios2_dma_sync_sg_for_device,
-};
-EXPORT_SYMBOL(nios2_dma_ops);
-- 
cgit v1.2.3


From 3461dfbabcc40d48c7b4b3ebb26a4ec927303e16 Mon Sep 17 00:00:00 2001
From: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Date: Tue, 24 Jul 2018 14:27:31 +0300
Subject: ACPI / battery: drop inclusion of init.h

The driver can be built as a module thus inclusion of init.h is
redundant in battery.c since it's always included by module.h.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 78e40a9f5e18..642e51f8f412 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -27,7 +27,6 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/init.h>
 #include <linux/types.h>
 #include <linux/jiffies.h>
 #include <linux/async.h>
-- 
cgit v1.2.3


From 53dd200a2eed1413f2ef980dd5a193a3d45cc9a9 Mon Sep 17 00:00:00 2001
From: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Date: Tue, 24 Jul 2018 14:27:32 +0300
Subject: ACPI / battery: reorder headers alphabetically

Headers ordered alphabetically as easier to maintain.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 642e51f8f412..321b5f98b63c 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -23,17 +23,18 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/async.h>
+#include <linux/delay.h>
+#include <linux/dmi.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/types.h>
-#include <linux/jiffies.h>
-#include <linux/async.h>
-#include <linux/dmi.h>
-#include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
+#include <linux/types.h>
+
 #include <asm/unaligned.h>
 
 #ifdef CONFIG_ACPI_PROCFS_POWER
-- 
cgit v1.2.3


From dd1fca9e6cd4c5c179f4e854ceddbc22890109ce Mon Sep 17 00:00:00 2001
From: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Date: Tue, 24 Jul 2018 14:27:33 +0300
Subject: ACPI / battery: use specialized print macros

The kernel provides specialized macros for printing
info and warning messages which make the code shorter.

Use the specialized macros instead of bare printk()'s.

Also format one user visible string literal into a searchable one
line string.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 321b5f98b63c..6d302bb2f51b 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -577,8 +577,7 @@ static int acpi_battery_get_state(struct acpi_battery *battery)
 		battery->rate_now != ACPI_BATTERY_VALUE_UNKNOWN &&
 		(s16)(battery->rate_now) < 0) {
 		battery->rate_now = abs((s16)battery->rate_now);
-		printk_once(KERN_WARNING FW_BUG
-			    "battery: (dis)charge rate invalid.\n");
+		pr_warn_once(FW_BUG "battery: (dis)charge rate invalid.\n");
 	}
 
 	if (test_bit(ACPI_BATTERY_QUIRK_PERCENTAGE_CAPACITY, &battery->flags)
@@ -1170,8 +1169,7 @@ static const struct file_operations acpi_battery_alarm_fops = {
 
 static int acpi_battery_add_fs(struct acpi_device *device)
 {
-	printk(KERN_WARNING PREFIX "Deprecated procfs I/F for battery is loaded,"
-			" please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
+	pr_warning(PREFIX "Deprecated procfs I/F for battery is loaded, please retry with CONFIG_ACPI_PROCFS_POWER cleared\n");
 	if (!acpi_device_dir(device)) {
 		acpi_device_dir(device) = proc_mkdir(acpi_device_bid(device),
 						     acpi_battery_dir);
@@ -1398,7 +1396,7 @@ static int acpi_battery_add(struct acpi_device *device)
 	}
 #endif
 
-	printk(KERN_INFO PREFIX "%s Slot [%s] (battery %s)\n",
+	pr_info(PREFIX "%s Slot [%s] (battery %s)\n",
 		ACPI_BATTERY_DEVICE_NAME, acpi_device_bid(device),
 		device->status.battery_present ? "present" : "absent");
 
-- 
cgit v1.2.3


From 2754435d4c820875412785da9bfa017a74fe51a7 Mon Sep 17 00:00:00 2001
From: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Date: Tue, 24 Jul 2018 14:27:34 +0300
Subject: ACPI / battery: get rid of negations in conditions

Simple conditions without negations inflict less cognitive load
on readers.

Rework conditional branches not to use negations. Also add braces
around single statement branches where their counterpart else-branches
consist of more than one statement as suggested in the paragraph 3 of
the coding style.

Suggested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Dmitry Rozhkov <dmitry.rozhkov@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index 6d302bb2f51b..cb664e87cde8 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -1020,7 +1020,7 @@ static int acpi_battery_info_proc_show(struct seq_file *seq, void *offset)
 			   acpi_battery_units(battery));
 
 	seq_printf(seq, "battery technology:      %srechargeable\n",
-		   (!battery->technology)?"non-":"");
+		   battery->technology ? "" : "non-");
 
 	if (battery->design_voltage == ACPI_BATTERY_VALUE_UNKNOWN)
 		seq_printf(seq, "design voltage:          unknown\n");
@@ -1111,11 +1111,12 @@ static int acpi_battery_alarm_proc_show(struct seq_file *seq, void *offset)
 		goto end;
 	}
 	seq_printf(seq, "alarm:                   ");
-	if (!battery->alarm)
-		seq_printf(seq, "unsupported\n");
-	else
+	if (battery->alarm) {
 		seq_printf(seq, "%u %sh\n", battery->alarm,
 				acpi_battery_units(battery));
+	} else {
+		seq_printf(seq, "unsupported\n");
+	}
       end:
 	if (result)
 		seq_printf(seq, "ERROR: Unable to read battery alarm\n");
@@ -1148,9 +1149,9 @@ static ssize_t acpi_battery_write_alarm(struct file *file,
 	}
 	result = acpi_battery_set_alarm(battery);
       end:
-	if (!result)
-		return count;
-	return result;
+	if (result)
+		return result;
+	return count;
 }
 
 static int acpi_battery_alarm_proc_open(struct inode *inode, struct file *file)
@@ -1245,7 +1246,9 @@ static int battery_notify(struct notifier_block *nb,
 		if (!acpi_battery_present(battery))
 			return 0;
 
-		if (!battery->bat) {
+		if (battery->bat) {
+			acpi_battery_refresh(battery);
+		} else {
 			result = acpi_battery_get_info(battery);
 			if (result)
 				return result;
@@ -1253,8 +1256,7 @@ static int battery_notify(struct notifier_block *nb,
 			result = sysfs_add_battery(battery);
 			if (result)
 				return result;
-		} else
-			acpi_battery_refresh(battery);
+		}
 
 		acpi_battery_init_alarm(battery);
 		acpi_battery_get_state(battery);
-- 
cgit v1.2.3


From 30b914c8d825da7d4c651ade34667cef05e3ee27 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Tue, 27 Feb 2018 07:24:09 -0500
Subject: media: add 'index' to struct media_v2_pad

The v2 pad structure never exposed the pad index, which made it impossible
to call the MEDIA_IOC_SETUP_LINK ioctl, which needs that information.

It is really trivial to just expose this information, so implement this.

Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/media-device.c |  1 +
 include/uapi/linux/media.h   | 12 +++++++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 47bb2254fbfd..047d38372a27 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -331,6 +331,7 @@ static long media_device_get_topology(struct media_device *mdev, void *arg)
 		kpad.id = pad->graph_obj.id;
 		kpad.entity_id = pad->entity->graph_obj.id;
 		kpad.flags = pad->flags;
+		kpad.index = pad->index;
 
 		if (copy_to_user(upad, &kpad, sizeof(kpad)))
 			ret = -EFAULT;
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index 86c7dcc9cba3..f6338bd57929 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -305,11 +305,21 @@ struct media_v2_interface {
 	};
 } __attribute__ ((packed));
 
+/*
+ * Appeared in 4.19.0.
+ *
+ * The media_version argument comes from the media_version field in
+ * struct media_device_info.
+ */
+#define MEDIA_V2_PAD_HAS_INDEX(media_version) \
+	((media_version) >= ((4 << 16) | (19 << 8) | 0))
+
 struct media_v2_pad {
 	__u32 id;
 	__u32 entity_id;
 	__u32 flags;
-	__u32 reserved[5];
+	__u32 index;
+	__u32 reserved[4];
 } __attribute__ ((packed));
 
 struct media_v2_link {
-- 
cgit v1.2.3


From b0549006263efd59e22518eda230040ffee71b93 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 19 Mar 2018 11:11:10 -0400
Subject: media: media-ioc-g-topology.rst: document new 'index' field

Document the new struct media_v2_pad 'index' field.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-ioc-g-topology.rst | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
index a3f259f83b25..725961198143 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
@@ -176,7 +176,7 @@ desired arrays with the media graph elements.
     *  -  struct media_v2_intf_devnode
        -  ``devnode``
        -  Used only for device node interfaces. See
-	  :c:type:`media_v2_intf_devnode` for details..
+	  :c:type:`media_v2_intf_devnode` for details.
 
 
 .. tabularcolumns:: |p{1.6cm}|p{3.2cm}|p{12.7cm}|
@@ -218,7 +218,14 @@ desired arrays with the media graph elements.
        -  Pad flags, see :ref:`media-pad-flag` for more details.
 
     *  -  __u32
-       -  ``reserved``\ [5]
+       -  ``index``
+       -  Pad index, starts at 0. Only valid if ``MEDIA_V2_PAD_HAS_INDEX(media_version)``
+	  returns true. The ``media_version`` is defined in struct
+	  :c:type:`media_device_info` and can be retrieved using
+	  :ref:`MEDIA_IOC_DEVICE_INFO`.
+
+    *  -  __u32
+       -  ``reserved``\ [4]
        -  Reserved for future extensions. Drivers and applications must set
 	  this array to zero.
 
-- 
cgit v1.2.3


From 588f4ee7e6fc5c9a0fb07c7051cdd341949e0feb Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Wed, 28 Feb 2018 05:41:11 -0500
Subject: media: add flags field to struct media_v2_entity

The v2 entity structure never exposed the entity flags, which made it
impossible to detect connector or default entities.

It is really trivial to just expose this information, so implement this.

Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/media-device.c |  1 +
 include/uapi/linux/media.h   | 12 +++++++++++-
 2 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 047d38372a27..14959b19a342 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -266,6 +266,7 @@ static long media_device_get_topology(struct media_device *mdev, void *arg)
 		memset(&kentity, 0, sizeof(kentity));
 		kentity.id = entity->graph_obj.id;
 		kentity.function = entity->function;
+		kentity.flags = entity->flags;
 		strlcpy(kentity.name, entity->name,
 			sizeof(kentity.name));
 
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index f6338bd57929..ebd2cda67833 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -280,11 +280,21 @@ struct media_links_enum {
  * MC next gen API definitions
  */
 
+/*
+ * Appeared in 4.19.0.
+ *
+ * The media_version argument comes from the media_version field in
+ * struct media_device_info.
+ */
+#define MEDIA_V2_ENTITY_HAS_FLAGS(media_version) \
+	((media_version) >= ((4 << 16) | (19 << 8) | 0))
+
 struct media_v2_entity {
 	__u32 id;
 	char name[64];
 	__u32 function;		/* Main function of the entity */
-	__u32 reserved[6];
+	__u32 flags;
+	__u32 reserved[5];
 } __attribute__ ((packed));
 
 /* Should match the specific fields at media_intf_devnode */
-- 
cgit v1.2.3


From d2dc644adf81f3f5bbebda81e378cf250b03ed52 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 19 Mar 2018 11:17:17 -0400
Subject: media: media-ioc-g-topology.rst: document new 'flags' field

Document the new struct media_v2_entity 'flags' field.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-ioc-g-topology.rst | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
index 725961198143..d6f41a8e307f 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
@@ -142,7 +142,15 @@ desired arrays with the media graph elements.
        -  Entity main function, see :ref:`media-entity-functions` for details.
 
     *  -  __u32
-       -  ``reserved``\ [6]
+       -  ``flags``
+       -  Entity flags, see :ref:`media-entity-flag` for details.
+	  Only valid if ``MEDIA_V2_ENTITY_HAS_FLAGS(media_version)``
+	  returns true. The ``media_version`` is defined in struct
+	  :c:type:`media_device_info` and can be retrieved using
+	  :ref:`MEDIA_IOC_DEVICE_INFO`.
+
+    *  -  __u32
+       -  ``reserved``\ [5]
        -  Reserved for future extensions. Drivers and applications must set
 	  this array to zero.
 
-- 
cgit v1.2.3


From d272bc92c4a4fcec4102c011eaa85630bd2d8d38 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Thu, 28 Jun 2018 08:56:02 -0400
Subject: media: rename MEDIA_ENT_F_DTV_DECODER to MEDIA_ENT_F_DV_DECODER

The use of 'DTV' is very confusing since it normally refers to Digital
TV e.g. DVB etc.

Instead use 'DV' (Digital Video), which nicely corresponds to the
DV Timings API used to configure such receivers and transmitters.

We keep an alias to avoid breaking userspace applications.

Since this alias is only available if __KERNEL__ is *not* defined
(i.e. it is only available for userspace, not kernelspace), any
drivers that use it also have to be converted to the new define.
These drivers are adv7604, adv7842 and tda1997x.

Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-types.rst | 2 +-
 drivers/media/i2c/adv7604.c                       | 1 +
 drivers/media/i2c/adv7842.c                       | 1 +
 drivers/media/i2c/tda1997x.c                      | 2 +-
 include/uapi/linux/media.h                        | 4 +++-
 5 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst
index 96910cf2eaaa..c11b0c7e890b 100644
--- a/Documentation/media/uapi/mediactl/media-types.rst
+++ b/Documentation/media/uapi/mediactl/media-types.rst
@@ -200,7 +200,7 @@ Types and flags used to represent the media graph elements
          MIPI CSI-2, etc.), and outputs them on its source pad to an output
          video bus of another type (eDP, MIPI CSI-2, parallel, etc.).
 
-    *  -  ``MEDIA_ENT_F_DTV_DECODER``
+    *  -  ``MEDIA_ENT_F_DV_DECODER``
        -  Digital video decoder. The basic function of the video decoder is
 	  to accept digital video from a wide variety of sources
 	  and output it in some digital video standard, with appropriate
diff --git a/drivers/media/i2c/adv7604.c b/drivers/media/i2c/adv7604.c
index 1a3b2c04d9f9..668be2bca57a 100644
--- a/drivers/media/i2c/adv7604.c
+++ b/drivers/media/i2c/adv7604.c
@@ -3499,6 +3499,7 @@ static int adv76xx_probe(struct i2c_client *client,
 	for (i = 0; i < state->source_pad; ++i)
 		state->pads[i].flags = MEDIA_PAD_FL_SINK;
 	state->pads[state->source_pad].flags = MEDIA_PAD_FL_SOURCE;
+	sd->entity.function = MEDIA_ENT_F_DV_DECODER;
 
 	err = media_entity_pads_init(&sd->entity, state->source_pad + 1,
 				state->pads);
diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index fddac32e5051..99d781343fb1 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -3541,6 +3541,7 @@ static int adv7842_probe(struct i2c_client *client,
 	INIT_DELAYED_WORK(&state->delayed_work_enable_hotplug,
 			adv7842_delayed_work_enable_hotplug);
 
+	sd->entity.function = MEDIA_ENT_F_DV_DECODER;
 	state->pad.flags = MEDIA_PAD_FL_SOURCE;
 	err = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (err)
diff --git a/drivers/media/i2c/tda1997x.c b/drivers/media/i2c/tda1997x.c
index 039a92c3294a..d114ac5243ec 100644
--- a/drivers/media/i2c/tda1997x.c
+++ b/drivers/media/i2c/tda1997x.c
@@ -2570,7 +2570,7 @@ static int tda1997x_probe(struct i2c_client *client,
 		 id->name, i2c_adapter_id(client->adapter),
 		 client->addr);
 	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE | V4L2_SUBDEV_FL_HAS_EVENTS;
-	sd->entity.function = MEDIA_ENT_F_DTV_DECODER;
+	sd->entity.function = MEDIA_ENT_F_DV_DECODER;
 	sd->entity.ops = &tda1997x_media_ops;
 
 	/* set allowed mbus modes based on chip, bus-type, and bus-width */
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index ebd2cda67833..99f5e0978ebb 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -93,7 +93,7 @@ struct media_device_info {
  * Video decoder functions
  */
 #define MEDIA_ENT_F_ATV_DECODER			(MEDIA_ENT_F_OLD_SUBDEV_BASE + 4)
-#define MEDIA_ENT_F_DTV_DECODER			(MEDIA_ENT_F_BASE + 0x6001)
+#define MEDIA_ENT_F_DV_DECODER			(MEDIA_ENT_F_BASE + 0x6001)
 
 /*
  * Digital TV, analog TV, radio and/or software defined radio tuner functions.
@@ -400,6 +400,8 @@ struct media_v2_topology {
 #define MEDIA_ENT_T_V4L2_SUBDEV_DECODER		MEDIA_ENT_F_ATV_DECODER
 #define MEDIA_ENT_T_V4L2_SUBDEV_TUNER		MEDIA_ENT_F_TUNER
 
+#define MEDIA_ENT_F_DTV_DECODER			MEDIA_ENT_F_DV_DECODER
+
 /*
  * There is still no ALSA support in the media controller. These
  * defines should not have been added and we leave them here only
-- 
cgit v1.2.3


From 7c8362c4b9eb7e4e9cbebc71ab529dc455c21b6b Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 18 Jun 2018 05:07:43 -0400
Subject: media: media.h: add MEDIA_ENT_F_DV_ENCODER

Add a new function for digital video encoders such as HDMI transmitters.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-types.rst | 7 +++++++
 include/uapi/linux/media.h                        | 3 ++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst
index c11b0c7e890b..e90d4d0a7f8b 100644
--- a/Documentation/media/uapi/mediactl/media-types.rst
+++ b/Documentation/media/uapi/mediactl/media-types.rst
@@ -206,6 +206,13 @@ Types and flags used to represent the media graph elements
 	  and output it in some digital video standard, with appropriate
 	  timing signals.
 
+    *  -  ``MEDIA_ENT_F_DV_ENCODER``
+       -  Digital video encoder. The basic function of the video encoder is
+	  to accept digital video from some digital video standard with
+	  appropriate timing signals (usually a parallel video bus with sync
+	  signals) and output this to a digital video output connector such
+	  as HDMI or DisplayPort.
+
 ..  tabularcolumns:: |p{5.5cm}|p{12.0cm}|
 
 .. _media-entity-flag:
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index 99f5e0978ebb..6f594fa238c2 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -90,10 +90,11 @@ struct media_device_info {
 #define MEDIA_ENT_F_LENS			(MEDIA_ENT_F_OLD_SUBDEV_BASE + 3)
 
 /*
- * Video decoder functions
+ * Video decoder/encoder functions
  */
 #define MEDIA_ENT_F_ATV_DECODER			(MEDIA_ENT_F_OLD_SUBDEV_BASE + 4)
 #define MEDIA_ENT_F_DV_DECODER			(MEDIA_ENT_F_BASE + 0x6001)
+#define MEDIA_ENT_F_DV_ENCODER			(MEDIA_ENT_F_BASE + 0x6002)
 
 /*
  * Digital TV, analog TV, radio and/or software defined radio tuner functions.
-- 
cgit v1.2.3


From ec446d09366cea199214b30810e368c5178841cd Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Mon, 28 May 2018 21:53:38 +0200
Subject: drm/msm: call drm_atomic_helper_suspend() and
 drm_atomic_helper_resume()

To make suspend and resume work on msm8916 platforms, call into the generic
helpers and preserve the state across suspends.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_drv.c | 9 +++++++++
 drivers/gpu/drm/msm/msm_drv.h | 1 +
 2 files changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 021a0b6f9a59..7f7321eb5312 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -894,16 +894,25 @@ static struct drm_driver msm_driver = {
 static int msm_pm_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
 
 	drm_kms_helper_poll_disable(ddev);
 
+	priv->pm_state = drm_atomic_helper_suspend(ddev);
+	if (IS_ERR(priv->pm_state)) {
+		drm_kms_helper_poll_enable(ddev);
+		return PTR_ERR(priv->pm_state);
+	}
+
 	return 0;
 }
 
 static int msm_pm_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
 
+	drm_atomic_helper_resume(ddev, priv->pm_state);
 	drm_kms_helper_poll_enable(ddev);
 
 	return 0;
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index b2da1fbf81e0..17cefca1d566 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -150,6 +150,7 @@ struct msm_drm_private {
 	struct shrinker shrinker;
 
 	struct msm_vblank_ctrl vblank_ctrl;
+	struct drm_atomic_state *pm_state;
 };
 
 struct msm_format {
-- 
cgit v1.2.3


From 6666e1a66f92988e8c85a7ac0c34f47dc7d412a0 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Mon, 28 May 2018 21:53:39 +0200
Subject: drm/msm/adreno: Add power management functions for system sleep

When a msm8016 based system is woken up from suspend, the firmware in
the adreno device hangs.

[   83.903416] qcom-iommu-ctx 1f09000.iommu-ctx: Unhandled context fault: fsr=0x202, iova=0x0000000000000000, fsynr=0x2, cb=1
[   85.853633] msm 1a00000.mdss: A306: hangcheck detected gpu lockup rb 0!
[   85.853661] msm 1a00000.mdss: A306:     completed fence: 370
[   85.859073] msm 1a00000.mdss: A306:     submitted fence: 372
[   85.865113] msm 1a00000.mdss: A306: hangcheck recover!

Fix this by adding pm_runtime_force_suspend/pm_runtime_force_resume
as sleep ops.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/adreno_device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 0ae5ace65462..01d4e09cdf85 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -316,6 +316,7 @@ static int adreno_suspend(struct device *dev)
 #endif
 
 static const struct dev_pm_ops adreno_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
 	SET_RUNTIME_PM_OPS(adreno_suspend, adreno_resume, NULL)
 };
 
-- 
cgit v1.2.3


From 64709686dbb38f32045e117ec5a1aaf2e3a0a3c4 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Mon, 7 May 2018 16:47:50 -0600
Subject: drm/msm/gpu: Increase the pm runtime autosuspend for 5xx

Experimentation shows that resuming power quickly after suspending
ends up forcing a system hang for unknown reasons on 5xx targets.
To avoid cycling the power too much (especially during init)
turn up the autosuspend time for a5xx to 250ms and use
pm_runtime_put_autosuspend() when applicable.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/adreno_device.c | 13 ++++++++++++-
 drivers/gpu/drm/msm/adreno/adreno_gpu.c    |  3 ++-
 drivers/gpu/drm/msm/adreno/adreno_gpu.h    |  1 +
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_device.c b/drivers/gpu/drm/msm/adreno/adreno_device.c
index 01d4e09cdf85..44813624a286 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_device.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_device.c
@@ -35,6 +35,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_256K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 0, 6, 0),
@@ -45,6 +46,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_128K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 2, ANY_ID, ANY_ID),
@@ -55,6 +57,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a300_pfp.fw",
 		},
 		.gmem  = SZ_512K,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(3, 3, 0, ANY_ID),
@@ -65,6 +68,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a330_pfp.fw",
 		},
 		.gmem  = SZ_1M,
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a3xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(4, 2, 0, ANY_ID),
@@ -75,6 +79,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a420_pfp.fw",
 		},
 		.gmem  = (SZ_1M + SZ_512K),
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
 		.rev   = ADRENO_REV(4, 3, 0, ANY_ID),
@@ -85,6 +90,7 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_PFP] = "a420_pfp.fw",
 		},
 		.gmem  = (SZ_1M + SZ_512K),
+		.inactive_period = DRM_MSM_INACTIVE_PERIOD,
 		.init  = a4xx_gpu_init,
 	}, {
 		.rev = ADRENO_REV(5, 3, 0, 2),
@@ -96,6 +102,11 @@ static const struct adreno_info gpulist[] = {
 			[ADRENO_FW_GPMU] = "a530v3_gpmu.fw2",
 		},
 		.gmem = SZ_1M,
+		/*
+		 * Increase inactive period to 250 to avoid bouncing
+		 * the GDSC which appears to make it grumpy
+		 */
+		.inactive_period = 250,
 		.quirks = ADRENO_QUIRK_TWO_PASS_USE_WFI |
 			ADRENO_QUIRK_FAULT_DETECT_MASK,
 		.init = a5xx_gpu_init,
@@ -158,7 +169,7 @@ struct msm_gpu *adreno_load_gpu(struct drm_device *dev)
 	mutex_lock(&dev->struct_mutex);
 	ret = msm_gpu_hw_init(gpu);
 	mutex_unlock(&dev->struct_mutex);
-	pm_runtime_put_sync(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
 	if (ret) {
 		dev_err(dev->dev, "gpu hw init failed: %d\n", ret);
 		return NULL;
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 17d0506d058c..bcbf9f2a29f9 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -565,7 +565,8 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 
 	adreno_get_pwrlevels(&pdev->dev, gpu);
 
-	pm_runtime_set_autosuspend_delay(&pdev->dev, DRM_MSM_INACTIVE_PERIOD);
+	pm_runtime_set_autosuspend_delay(&pdev->dev,
+		adreno_gpu->info->inactive_period);
 	pm_runtime_use_autosuspend(&pdev->dev);
 	pm_runtime_enable(&pdev->dev);
 
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index d6b0e7b813f4..bc9ec27e9ed8 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -84,6 +84,7 @@ struct adreno_info {
 	enum adreno_quirks quirks;
 	struct msm_gpu *(*init)(struct drm_device *dev);
 	const char *zapfw;
+	u32 inactive_period;
 };
 
 const struct adreno_info *adreno_info(struct adreno_rev rev);
-- 
cgit v1.2.3


From 6e8bed6a3e2fd6f1e82ea9b1f705bbc82060a2b7 Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@gmail.com>
Date: Tue, 3 Jul 2018 08:14:32 -0400
Subject: drm/msm/mdp5: fix missing CTL flush

f9cb8d8d836e fixed various race conditions with CTL flush, in particular
flushing and sending the START signal before encoder state was updated.
But it did this a little too well in some cases that don't trigger
encoder->enable(), and CTL[n].FLUSH would never be set.  When page flips
happen it would paper over the bug, since the first plag flip would
flush out the state to the hardware.

The issue could be reproduced with, for example, modetest (without the
'-v' argument).

Fixes: f9cb8d8d836e drm/msm/mdp5: rework CTL START signal handling
Signed-off-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
---
 drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
index 9af94e35f678..fcd44d1d1068 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_encoder.c
@@ -319,7 +319,17 @@ static int mdp5_encoder_atomic_check(struct drm_encoder *encoder,
 
 	mdp5_cstate->ctl = ctl;
 	mdp5_cstate->pipeline.intf = intf;
-	mdp5_cstate->defer_start = true;
+
+	/*
+	 * This is a bit awkward, but we want to flush the CTL and hit the
+	 * START bit at most once for an atomic update.  In the non-full-
+	 * modeset case, this is done from crtc->atomic_flush(), but that
+	 * is too early in the case of full modeset, in which case we
+	 * defer to encoder->enable().  But we need to *know* whether
+	 * encoder->enable() will be called to do this:
+	 */
+	if (drm_atomic_crtc_needs_modeset(crtc_state))
+		mdp5_cstate->defer_start = true;
 
 	return 0;
 }
-- 
cgit v1.2.3


From e18177cc572939ad9526bae141fc4c8f5f006de4 Mon Sep 17 00:00:00 2001
From: Sibi Sankar <sibis@codeaurora.org>
Date: Tue, 29 May 2018 19:50:31 +0530
Subject: drm/msm/dsi: add dsi host helper functions support

Add dsi host helper functions support for DSI v2 and DSI 6G 1.x
controllers that are under version checks

Signed-off-by: Sibi Sankar <sibis@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi.h     |  1 +
 drivers/gpu/drm/msm/dsi/dsi_cfg.h | 12 ++++++++++++
 2 files changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index 70d9a9a47acd..80be83e8fdec 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -149,6 +149,7 @@ static inline int msm_dsi_pll_set_usecase(struct msm_dsi_pll *pll,
 #endif
 
 /* dsi host */
+struct msm_dsi_host;
 int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 					const struct mipi_dsi_msg *msg);
 void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index 9cfdcf1c95d5..a795a062b779 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -40,10 +40,22 @@ struct msm_dsi_config {
 	const int num_dsi;
 };
 
+struct msm_dsi_host_cfg_ops {
+	int (*link_clk_enable)(struct msm_dsi_host *msm_host);
+	void (*link_clk_disable)(struct msm_dsi_host *msm_host);
+	int (*clk_init_ver)(struct msm_dsi_host *msm_host);
+	int (*tx_buf_alloc)(struct msm_dsi_host *msm_host, int size);
+	void* (*tx_buf_get)(struct msm_dsi_host *msm_host);
+	void (*tx_buf_put)(struct msm_dsi_host *msm_host);
+	int (*dma_base_get)(struct msm_dsi_host *msm_host, uint64_t *iova);
+	int (*calc_clk_rate)(struct msm_dsi_host *msm_host);
+};
+
 struct msm_dsi_cfg_handler {
 	u32 major;
 	u32 minor;
 	const struct msm_dsi_config *cfg;
+	const struct msm_dsi_host_cfg_ops *ops;
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor);
-- 
cgit v1.2.3


From c4d8cfe516dc54bac8837bc90ccbd878ad26c59e Mon Sep 17 00:00:00 2001
From: Sibi Sankar <sibis@codeaurora.org>
Date: Tue, 29 May 2018 19:50:32 +0530
Subject: drm/msm/dsi: add implementation for helper functions

Add dsi host helper function implementation for DSI v2
DSI 6G 1.x and DSI 6G v2.0+ controllers

Signed-off-by: Sibi Sankar <sibis@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi.h      |  15 +++
 drivers/gpu/drm/msm/dsi/dsi_cfg.c  |  56 ++++++++--
 drivers/gpu/drm/msm/dsi/dsi_host.c | 218 ++++++++++++++++++++++++++++++++++++-
 3 files changed, 278 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index 80be83e8fdec..dfa049d876bd 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -183,6 +183,21 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 int msm_dsi_host_init(struct msm_dsi *msm_dsi);
 int msm_dsi_runtime_suspend(struct device *dev);
 int msm_dsi_runtime_resume(struct device *dev);
+int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host);
+int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host);
+void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host);
+void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host);
+int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size);
+int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size);
+void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host);
+void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host);
+void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host);
+int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *iova);
+int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *iova);
+int dsi_clk_init_v2(struct msm_dsi_host *msm_host);
+int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host);
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host);
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host);
 
 /* dsi phy */
 struct msm_dsi_phy;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.c b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
index 0327bb54b01b..dcdfb1bb54f9 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.c
@@ -136,20 +136,58 @@ static const struct msm_dsi_config sdm845_dsi_cfg = {
 	.num_dsi = 2,
 };
 
+const static struct msm_dsi_host_cfg_ops msm_dsi_v2_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_v2,
+	.link_clk_disable = dsi_link_clk_disable_v2,
+	.clk_init_ver = dsi_clk_init_v2,
+	.tx_buf_alloc = dsi_tx_buf_alloc_v2,
+	.tx_buf_get = dsi_tx_buf_get_v2,
+	.tx_buf_put = NULL,
+	.dma_base_get = dsi_dma_base_get_v2,
+	.calc_clk_rate = dsi_calc_clk_rate_v2,
+};
+
+const static struct msm_dsi_host_cfg_ops msm_dsi_6g_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_6g,
+	.link_clk_disable = dsi_link_clk_disable_6g,
+	.clk_init_ver = NULL,
+	.tx_buf_alloc = dsi_tx_buf_alloc_6g,
+	.tx_buf_get = dsi_tx_buf_get_6g,
+	.tx_buf_put = dsi_tx_buf_put_6g,
+	.dma_base_get = dsi_dma_base_get_6g,
+	.calc_clk_rate = dsi_calc_clk_rate_6g,
+};
+
+const static struct msm_dsi_host_cfg_ops msm_dsi_6g_v2_host_ops = {
+	.link_clk_enable = dsi_link_clk_enable_6g,
+	.link_clk_disable = dsi_link_clk_disable_6g,
+	.clk_init_ver = dsi_clk_init_6g_v2,
+	.tx_buf_alloc = dsi_tx_buf_alloc_6g,
+	.tx_buf_get = dsi_tx_buf_get_6g,
+	.tx_buf_put = dsi_tx_buf_put_6g,
+	.dma_base_get = dsi_dma_base_get_6g,
+	.calc_clk_rate = dsi_calc_clk_rate_6g,
+};
+
 static const struct msm_dsi_cfg_handler dsi_cfg_handlers[] = {
-	{MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064, &apq8064_dsi_cfg},
+	{MSM_DSI_VER_MAJOR_V2, MSM_DSI_V2_VER_MINOR_8064,
+		&apq8064_dsi_cfg, &msm_dsi_v2_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_0,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_1_1,
-						&msm8974_apq8084_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
 	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_2,
-						&msm8974_apq8084_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3, &msm8994_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1, &msm8916_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1, &msm8996_dsi_cfg},
-	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1, &sdm845_dsi_cfg},
+		&msm8974_apq8084_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3,
+		&msm8994_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_3_1,
+		&msm8916_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V1_4_1,
+		&msm8996_dsi_cfg, &msm_dsi_6g_host_ops},
+	{MSM_DSI_VER_MAJOR_6G, MSM_DSI_6G_VER_MINOR_V2_2_1,
+		&sdm845_dsi_cfg, &msm_dsi_6g_v2_host_ops},
 };
 
 const struct msm_dsi_cfg_handler *msm_dsi_cfg_get(u32 major, u32 minor)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 29841f440111..414a95424d7c 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -332,6 +332,54 @@ static int dsi_regulator_init(struct msm_dsi_host *msm_host)
 	return 0;
 }
 
+int dsi_clk_init_v2(struct msm_dsi_host *msm_host)
+{
+	struct platform_device *pdev = msm_host->pdev;
+	int ret = 0;
+
+	msm_host->src_clk = msm_clk_get(pdev, "src");
+
+	if (IS_ERR(msm_host->src_clk)) {
+		ret = PTR_ERR(msm_host->src_clk);
+		pr_err("%s: can't find src clock. ret=%d\n",
+			__func__, ret);
+		msm_host->src_clk = NULL;
+		return ret;
+	}
+
+	msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk);
+	if (!msm_host->esc_clk_src) {
+		ret = -ENODEV;
+		pr_err("%s: can't get esc clock parent. ret=%d\n",
+			__func__, ret);
+		return ret;
+	}
+
+	msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk);
+	if (!msm_host->dsi_clk_src) {
+		ret = -ENODEV;
+		pr_err("%s: can't get src clock parent. ret=%d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
+int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host)
+{
+	struct platform_device *pdev = msm_host->pdev;
+	int ret = 0;
+
+	msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf");
+	if (IS_ERR(msm_host->byte_intf_clk)) {
+		ret = PTR_ERR(msm_host->byte_intf_clk);
+		pr_err("%s: can't find byte_intf clock. ret=%d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
 static int dsi_clk_init(struct msm_dsi_host *msm_host)
 {
 	struct platform_device *pdev = msm_host->pdev;
@@ -498,7 +546,7 @@ int msm_dsi_runtime_resume(struct device *dev)
 	return dsi_bus_clk_enable(msm_host);
 }
 
-static int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
+int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -566,7 +614,7 @@ error:
 	return ret;
 }
 
-static int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
+int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 {
 	int ret;
 
@@ -644,6 +692,23 @@ static int dsi_link_clk_enable(struct msm_dsi_host *msm_host)
 		return dsi_link_clk_enable_v2(msm_host);
 }
 
+void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host)
+{
+	clk_disable_unprepare(msm_host->esc_clk);
+	clk_disable_unprepare(msm_host->pixel_clk);
+	if (msm_host->byte_intf_clk)
+		clk_disable_unprepare(msm_host->byte_intf_clk);
+	clk_disable_unprepare(msm_host->byte_clk);
+}
+
+void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
+{
+	clk_disable_unprepare(msm_host->pixel_clk);
+	clk_disable_unprepare(msm_host->src_clk);
+	clk_disable_unprepare(msm_host->esc_clk);
+	clk_disable_unprepare(msm_host->byte_clk);
+}
+
 static void dsi_link_clk_disable(struct msm_dsi_host *msm_host)
 {
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
@@ -662,6 +727,84 @@ static void dsi_link_clk_disable(struct msm_dsi_host *msm_host)
 	}
 }
 
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host)
+{
+	struct drm_display_mode *mode = msm_host->mode;
+	u8 lanes = msm_host->lanes;
+	u32 bpp = dsi_get_bpp(msm_host->format);
+	u32 pclk_rate;
+
+	pclk_rate = mode->clock * 1000;
+	if (lanes > 0) {
+		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
+	} else {
+		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
+		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
+	}
+
+	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
+
+	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
+
+	return 0;
+}
+
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host)
+{
+	struct drm_display_mode *mode = msm_host->mode;
+	u8 lanes = msm_host->lanes;
+	u32 bpp = dsi_get_bpp(msm_host->format);
+	u32 pclk_rate;
+	unsigned int esc_mhz, esc_div;
+	unsigned long byte_mhz;
+
+	pclk_rate = mode->clock * 1000;
+	if (lanes > 0) {
+		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
+	} else {
+		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
+		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
+	}
+
+	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
+
+	msm_host->src_clk_rate = (pclk_rate * bpp) / 8;
+
+	/*
+	 * esc clock is byte clock followed by a 4 bit divider,
+	 * we need to find an escape clock frequency within the
+	 * mipi DSI spec range within the maximum divider limit
+	 * We iterate here between an escape clock frequencey
+	 * between 20 Mhz to 5 Mhz and pick up the first one
+	 * that can be supported by our divider
+	 */
+
+	byte_mhz = msm_host->byte_clk_rate / 1000000;
+
+	for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) {
+		esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz);
+
+		/*
+		 * TODO: Ideally, we shouldn't know what sort of divider
+		 * is available in mmss_cc, we're just assuming that
+		 * it'll always be a 4 bit divider. Need to come up with
+		 * a better way here.
+		 */
+		if (esc_div >= 1 && esc_div <= 16)
+			break;
+	}
+
+	if (esc_mhz < 5)
+		return -EINVAL;
+
+	msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div;
+
+	DBG("esc=%d, src=%d", msm_host->esc_clk_rate,
+		msm_host->src_clk_rate);
+
+	return 0;
+}
+
 static int dsi_calc_clk_rate(struct msm_dsi_host *msm_host)
 {
 	struct drm_display_mode *mode = msm_host->mode;
@@ -1015,6 +1158,41 @@ static void dsi_wait4video_eng_busy(struct msm_dsi_host *msm_host)
 	}
 }
 
+int dsi_tx_buf_alloc_6g(struct msm_dsi_host *msm_host, int size)
+{
+	struct drm_device *dev = msm_host->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+	uint64_t iova;
+	u8 *data;
+
+	data = msm_gem_kernel_new(dev, size, MSM_BO_UNCACHED,
+					priv->kms->aspace,
+					&msm_host->tx_gem_obj, &iova);
+
+	if (IS_ERR(data)) {
+		msm_host->tx_gem_obj = NULL;
+		return PTR_ERR(data);
+	}
+
+	msm_host->tx_size = msm_host->tx_gem_obj->size;
+
+	return 0;
+}
+
+int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size)
+{
+	struct drm_device *dev = msm_host->dev;
+
+	msm_host->tx_buf = dma_alloc_coherent(dev->dev, size,
+					&msm_host->tx_buf_paddr, GFP_KERNEL);
+	if (!msm_host->tx_buf)
+		return -ENOMEM;
+
+	msm_host->tx_size = size;
+
+	return 0;
+}
+
 /* dsi_cmd */
 static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
 {
@@ -1089,6 +1267,21 @@ static void dsi_tx_buf_free(struct msm_dsi_host *msm_host)
 			msm_host->tx_buf_paddr);
 }
 
+void *dsi_tx_buf_get_6g(struct msm_dsi_host *msm_host)
+{
+	return msm_gem_get_vaddr(msm_host->tx_gem_obj);
+}
+
+void *dsi_tx_buf_get_v2(struct msm_dsi_host *msm_host)
+{
+	return msm_host->tx_buf;
+}
+
+void dsi_tx_buf_put_6g(struct msm_dsi_host *msm_host)
+{
+	msm_gem_put_vaddr(msm_host->tx_gem_obj);
+}
+
 /*
  * prepare cmd buffer to be txed
  */
@@ -1190,6 +1383,27 @@ static int dsi_long_read_resp(u8 *buf, const struct mipi_dsi_msg *msg)
 	return msg->rx_len;
 }
 
+int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *dma_base)
+{
+	struct drm_device *dev = msm_host->dev;
+	struct msm_drm_private *priv = dev->dev_private;
+
+	if (!dma_base)
+		return -EINVAL;
+
+	return msm_gem_get_iova(msm_host->tx_gem_obj,
+				priv->kms->aspace, dma_base);
+}
+
+int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *dma_base)
+{
+	if (!dma_base)
+		return -EINVAL;
+
+	*dma_base = msm_host->tx_buf_paddr;
+	return 0;
+}
+
 static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 {
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-- 
cgit v1.2.3


From 8f7ca5409063ade228a8ea0cc77b5fe9877f8cf0 Mon Sep 17 00:00:00 2001
From: Sibi Sankar <sibis@codeaurora.org>
Date: Tue, 29 May 2018 19:50:33 +0530
Subject: drm/msm/dsi: replace version checks with helper functions

Replace version checks with the helper functions bound to
cfg_handler for DSI v2, DSI 6G 1.x and DSI 6G v2.0+ controllers

Signed-off-by: Sibi Sankar <sibis@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 241 +++++--------------------------------
 1 file changed, 29 insertions(+), 212 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 414a95424d7c..24dfae5b01a2 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -427,19 +427,6 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G &&
-	    cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V2_2_1) {
-		msm_host->byte_intf_clk = msm_clk_get(pdev, "byte_intf");
-		if (IS_ERR(msm_host->byte_intf_clk)) {
-			ret = PTR_ERR(msm_host->byte_intf_clk);
-			pr_err("%s: can't find byte_intf clock. ret=%d\n",
-			        __func__, ret);
-			goto exit;
-		}
-	} else {
-		msm_host->byte_intf_clk = NULL;
-	}
-
 	msm_host->byte_clk_src = clk_get_parent(msm_host->byte_clk);
 	if (!msm_host->byte_clk_src) {
 		ret = -ENODEV;
@@ -454,31 +441,8 @@ static int dsi_clk_init(struct msm_dsi_host *msm_host)
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
-		msm_host->src_clk = msm_clk_get(pdev, "src");
-		if (IS_ERR(msm_host->src_clk)) {
-			ret = PTR_ERR(msm_host->src_clk);
-			pr_err("%s: can't find src clock. ret=%d\n",
-				__func__, ret);
-			msm_host->src_clk = NULL;
-			goto exit;
-		}
-
-		msm_host->esc_clk_src = clk_get_parent(msm_host->esc_clk);
-		if (!msm_host->esc_clk_src) {
-			ret = -ENODEV;
-			pr_err("%s: can't get esc clock parent. ret=%d\n",
-				__func__, ret);
-			goto exit;
-		}
-
-		msm_host->dsi_clk_src = clk_get_parent(msm_host->src_clk);
-		if (!msm_host->dsi_clk_src) {
-			ret = -ENODEV;
-			pr_err("%s: can't get src clock parent. ret=%d\n",
-				__func__, ret);
-		}
-	}
+	if (cfg_hnd->ops->clk_init_ver)
+		ret = cfg_hnd->ops->clk_init_ver(msm_host);
 exit:
 	return ret;
 }
@@ -682,16 +646,6 @@ error:
 	return ret;
 }
 
-static int dsi_link_clk_enable(struct msm_dsi_host *msm_host)
-{
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
-		return dsi_link_clk_enable_6g(msm_host);
-	else
-		return dsi_link_clk_enable_v2(msm_host);
-}
-
 void dsi_link_clk_disable_6g(struct msm_dsi_host *msm_host)
 {
 	clk_disable_unprepare(msm_host->esc_clk);
@@ -709,24 +663,6 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
 	clk_disable_unprepare(msm_host->byte_clk);
 }
 
-static void dsi_link_clk_disable(struct msm_dsi_host *msm_host)
-{
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		clk_disable_unprepare(msm_host->esc_clk);
-		clk_disable_unprepare(msm_host->pixel_clk);
-		if (msm_host->byte_intf_clk)
-			clk_disable_unprepare(msm_host->byte_intf_clk);
-		clk_disable_unprepare(msm_host->byte_clk);
-	} else {
-		clk_disable_unprepare(msm_host->pixel_clk);
-		clk_disable_unprepare(msm_host->src_clk);
-		clk_disable_unprepare(msm_host->esc_clk);
-		clk_disable_unprepare(msm_host->byte_clk);
-	}
-}
-
 int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host)
 {
 	struct drm_display_mode *mode = msm_host->mode;
@@ -805,73 +741,6 @@ int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host)
 	return 0;
 }
 
-static int dsi_calc_clk_rate(struct msm_dsi_host *msm_host)
-{
-	struct drm_display_mode *mode = msm_host->mode;
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-	u8 lanes = msm_host->lanes;
-	u32 bpp = dsi_get_bpp(msm_host->format);
-	u32 pclk_rate;
-
-	if (!mode) {
-		pr_err("%s: mode not set\n", __func__);
-		return -EINVAL;
-	}
-
-	pclk_rate = mode->clock * 1000;
-	if (lanes > 0) {
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
-	} else {
-		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
-	}
-
-	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
-
-	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
-
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
-		unsigned int esc_mhz, esc_div;
-		unsigned long byte_mhz;
-
-		msm_host->src_clk_rate = (pclk_rate * bpp) / 8;
-
-		/*
-		 * esc clock is byte clock followed by a 4 bit divider,
-		 * we need to find an escape clock frequency within the
-		 * mipi DSI spec range within the maximum divider limit
-		 * We iterate here between an escape clock frequencey
-		 * between 20 Mhz to 5 Mhz and pick up the first one
-		 * that can be supported by our divider
-		 */
-
-		byte_mhz = msm_host->byte_clk_rate / 1000000;
-
-		for (esc_mhz = 20; esc_mhz >= 5; esc_mhz--) {
-			esc_div = DIV_ROUND_UP(byte_mhz, esc_mhz);
-
-			/*
-			 * TODO: Ideally, we shouldn't know what sort of divider
-			 * is available in mmss_cc, we're just assuming that
-			 * it'll always be a 4 bit divider. Need to come up with
-			 * a better way here.
-			 */
-			if (esc_div >= 1 && esc_div <= 16)
-				break;
-		}
-
-		if (esc_mhz < 5)
-			return -EINVAL;
-
-		msm_host->esc_clk_rate = msm_host->byte_clk_rate / esc_div;
-
-		DBG("esc=%d, src=%d", msm_host->esc_clk_rate,
-			msm_host->src_clk_rate);
-	}
-
-	return 0;
-}
-
 static void dsi_intr_ctrl(struct msm_dsi_host *msm_host, u32 mask, int enable)
 {
 	u32 intr;
@@ -1193,54 +1062,6 @@ int dsi_tx_buf_alloc_v2(struct msm_dsi_host *msm_host, int size)
 	return 0;
 }
 
-/* dsi_cmd */
-static int dsi_tx_buf_alloc(struct msm_dsi_host *msm_host, int size)
-{
-	struct drm_device *dev = msm_host->dev;
-	struct msm_drm_private *priv = dev->dev_private;
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-	int ret;
-	uint64_t iova;
-
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		msm_host->tx_gem_obj = msm_gem_new(dev, size, MSM_BO_UNCACHED);
-		if (IS_ERR(msm_host->tx_gem_obj)) {
-			ret = PTR_ERR(msm_host->tx_gem_obj);
-			pr_err("%s: failed to allocate gem, %d\n",
-				__func__, ret);
-			msm_host->tx_gem_obj = NULL;
-			return ret;
-		}
-
-		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
-				priv->kms->aspace, &iova);
-		if (ret) {
-			pr_err("%s: failed to get iova, %d\n", __func__, ret);
-			return ret;
-		}
-
-		if (iova & 0x07) {
-			pr_err("%s: buf NOT 8 bytes aligned\n", __func__);
-			return -EINVAL;
-		}
-
-		msm_host->tx_size = msm_host->tx_gem_obj->size;
-	} else {
-		msm_host->tx_buf = dma_alloc_coherent(dev->dev, size,
-					&msm_host->tx_buf_paddr, GFP_KERNEL);
-		if (!msm_host->tx_buf) {
-			ret = -ENOMEM;
-			pr_err("%s: failed to allocate tx buf, %d\n",
-				__func__, ret);
-			return ret;
-		}
-
-		msm_host->tx_size = size;
-	}
-
-	return 0;
-}
-
 static void dsi_tx_buf_free(struct msm_dsi_host *msm_host)
 {
 	struct drm_device *dev = msm_host->dev;
@@ -1306,15 +1127,11 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 		return -EINVAL;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		data = msm_gem_get_vaddr(msm_host->tx_gem_obj);
-		if (IS_ERR(data)) {
-			ret = PTR_ERR(data);
-			pr_err("%s: get vaddr failed, %d\n", __func__, ret);
-			return ret;
-		}
-	} else {
-		data = msm_host->tx_buf;
+	data = cfg_hnd->ops->tx_buf_get(msm_host);
+	if (IS_ERR(data)) {
+		ret = PTR_ERR(data);
+		pr_err("%s: get vaddr failed, %d\n", __func__, ret);
+		return ret;
 	}
 
 	/* MSM specific command format in memory */
@@ -1335,8 +1152,8 @@ static int dsi_cmd_dma_add(struct msm_dsi_host *msm_host,
 	if (packet.size < len)
 		memset(data + packet.size, 0xff, len - packet.size);
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G)
-		msm_gem_put_vaddr(msm_host->tx_gem_obj);
+	if (cfg_hnd->ops->tx_buf_put)
+		cfg_hnd->ops->tx_buf_put(msm_host);
 
 	return len;
 }
@@ -1407,21 +1224,14 @@ int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *dma_base)
 static int dsi_cmd_dma_tx(struct msm_dsi_host *msm_host, int len)
 {
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
-	struct drm_device *dev = msm_host->dev;
-	struct msm_drm_private *priv = dev->dev_private;
 	int ret;
 	uint64_t dma_base;
 	bool triggered;
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_6G) {
-		ret = msm_gem_get_iova(msm_host->tx_gem_obj,
-				priv->kms->aspace, &dma_base);
-		if (ret) {
-			pr_err("%s: failed to get iova: %d\n", __func__, ret);
-			return ret;
-		}
-	} else {
-		dma_base = msm_host->tx_buf_paddr;
+	ret = cfg_hnd->ops->dma_base_get(msm_host, &dma_base);
+	if (ret) {
+		pr_err("%s: failed to get iova: %d\n", __func__, ret);
+		return ret;
 	}
 
 	reinit_completion(&msm_host->dma_comp);
@@ -2059,6 +1869,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 					struct drm_device *dev)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct platform_device *pdev = msm_host->pdev;
 	int ret;
 
@@ -2079,7 +1890,7 @@ int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 	}
 
 	msm_host->dev = dev;
-	ret = dsi_tx_buf_alloc(msm_host, SZ_4K);
+	ret = cfg_hnd->ops->tx_buf_alloc(msm_host, SZ_4K);
 	if (ret) {
 		pr_err("%s: alloc tx gem obj failed, %d\n", __func__, ret);
 		return ret;
@@ -2137,6 +1948,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 				const struct mipi_dsi_msg *msg)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	/* TODO: make sure dsi_cmd_mdp is idle.
 	 * Since DSI6G v1.2.0, we can set DSI_TRIG_CTRL.BLOCK_DMA_WITHIN_FRAME
@@ -2149,7 +1961,7 @@ int msm_dsi_host_xfer_prepare(struct mipi_dsi_host *host,
 	 * mdp clock need to be enabled to receive dsi interrupt
 	 */
 	pm_runtime_get_sync(&msm_host->pdev->dev);
-	dsi_link_clk_enable(msm_host);
+	cfg_hnd->ops->link_clk_enable(msm_host);
 
 	/* TODO: vote for bus bandwidth */
 
@@ -2170,6 +1982,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
 				const struct mipi_dsi_msg *msg)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	dsi_intr_ctrl(msm_host, DSI_IRQ_MASK_CMD_DMA_DONE, 0);
 	dsi_write(msm_host, REG_DSI_CTRL, msm_host->dma_cmd_ctrl_restore);
@@ -2179,7 +1992,7 @@ void msm_dsi_host_xfer_restore(struct mipi_dsi_host *host,
 
 	/* TODO: unvote for bus bandwidth */
 
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 }
 
@@ -2343,7 +2156,6 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 	struct msm_dsi_pll *src_pll)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
-	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	struct clk *byte_clk_provider, *pixel_clk_provider;
 	int ret;
 
@@ -2369,14 +2181,16 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 		goto exit;
 	}
 
-	if (cfg_hnd->major == MSM_DSI_VER_MAJOR_V2) {
+	if (msm_host->dsi_clk_src) {
 		ret = clk_set_parent(msm_host->dsi_clk_src, pixel_clk_provider);
 		if (ret) {
 			pr_err("%s: can't set parent to dsi_clk_src. ret=%d\n",
 				__func__, ret);
 			goto exit;
 		}
+	}
 
+	if (msm_host->esc_clk_src) {
 		ret = clk_set_parent(msm_host->esc_clk_src, byte_clk_provider);
 		if (ret) {
 			pr_err("%s: can't set parent to esc_clk_src. ret=%d\n",
@@ -2406,9 +2220,10 @@ void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
 	struct msm_dsi_phy_clk_request *clk_req)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 
-	ret = dsi_calc_clk_rate(msm_host);
+	ret = cfg_hnd->ops->calc_clk_rate(msm_host);
 	if (ret) {
 		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
 		return;
@@ -2473,6 +2288,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 			struct msm_dsi_phy_shared_timings *phy_shared_timings)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret = 0;
 
 	mutex_lock(&msm_host->dev_mutex);
@@ -2491,7 +2307,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	}
 
 	pm_runtime_get_sync(&msm_host->pdev->dev);
-	ret = dsi_link_clk_enable(msm_host);
+	ret = cfg_hnd->ops->link_clk_enable(msm_host);
 	if (ret) {
 		pr_err("%s: failed to enable link clocks. ret=%d\n",
 		       __func__, ret);
@@ -2518,7 +2334,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 	return 0;
 
 fail_disable_clk:
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 fail_disable_reg:
 	dsi_host_regulator_disable(msm_host);
@@ -2530,6 +2346,7 @@ unlock_ret:
 int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
+	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 
 	mutex_lock(&msm_host->dev_mutex);
 	if (!msm_host->power_on) {
@@ -2544,7 +2361,7 @@ int msm_dsi_host_power_off(struct mipi_dsi_host *host)
 
 	pinctrl_pm_select_sleep_state(&msm_host->pdev->dev);
 
-	dsi_link_clk_disable(msm_host);
+	cfg_hnd->ops->link_clk_disable(msm_host);
 	pm_runtime_put_autosuspend(&msm_host->pdev->dev);
 
 	dsi_host_regulator_disable(msm_host);
-- 
cgit v1.2.3


From 23f9455157f62e2fc7fbe7654717bcb70eee543d Mon Sep 17 00:00:00 2001
From: Carsten Behling <carsten.behling@googlemail.com>
Date: Mon, 16 Jul 2018 19:49:56 +0200
Subject: drm/msm/mdp5: negative x/y in cursor move

modesetting X11 driver may provide negative x/y cordinates in
mdp5_crtc_cursor_move call when rotation is enabled.

Cursor buffer can overlap down to its negative width/height.

ROI has to be recalculated for negative x/y indicating using the
lower/right corner of the cursor buffer and hotspot must be set
in MDP5_LM_CURSOR_XY_SRC_Y MDP5_LM_CURSOR_XY_SRC_X.

Signed-off-by: Carsten Behling <carsten.behling@gmail.com>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c | 51 ++++++++++++++++++++++++++-----
 1 file changed, 43 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
index 24e00274844b..b1da9ce54379 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_crtc.c
@@ -65,7 +65,7 @@ struct mdp5_crtc {
 		struct drm_gem_object *scanout_bo;
 		uint64_t iova;
 		uint32_t width, height;
-		uint32_t x, y;
+		int x, y;
 	} cursor;
 };
 #define to_mdp5_crtc(x) container_of(x, struct mdp5_crtc, base)
@@ -760,20 +760,31 @@ static void get_roi(struct drm_crtc *crtc, uint32_t *roi_w, uint32_t *roi_h)
 	 * Cursor Region Of Interest (ROI) is a plane read from cursor
 	 * buffer to render. The ROI region is determined by the visibility of
 	 * the cursor point. In the default Cursor image the cursor point will
-	 * be at the top left of the cursor image, unless it is specified
-	 * otherwise using hotspot feature.
+	 * be at the top left of the cursor image.
 	 *
+	 * Without rotation:
 	 * If the cursor point reaches the right (xres - x < cursor.width) or
 	 * bottom (yres - y < cursor.height) boundary of the screen, then ROI
 	 * width and ROI height need to be evaluated to crop the cursor image
 	 * accordingly.
 	 * (xres-x) will be new cursor width when x > (xres - cursor.width)
 	 * (yres-y) will be new cursor height when y > (yres - cursor.height)
+	 *
+	 * With rotation:
+	 * We get negative x and/or y coordinates.
+	 * (cursor.width - abs(x)) will be new cursor width when x < 0
+	 * (cursor.height - abs(y)) will be new cursor width when y < 0
 	 */
-	*roi_w = min(mdp5_crtc->cursor.width, xres -
+	if (mdp5_crtc->cursor.x >= 0)
+		*roi_w = min(mdp5_crtc->cursor.width, xres -
 			mdp5_crtc->cursor.x);
-	*roi_h = min(mdp5_crtc->cursor.height, yres -
+	else
+		*roi_w = mdp5_crtc->cursor.width - abs(mdp5_crtc->cursor.x);
+	if (mdp5_crtc->cursor.y >= 0)
+		*roi_h = min(mdp5_crtc->cursor.height, yres -
 			mdp5_crtc->cursor.y);
+	else
+		*roi_h = mdp5_crtc->cursor.height - abs(mdp5_crtc->cursor.y);
 }
 
 static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
@@ -783,7 +794,7 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 	struct mdp5_kms *mdp5_kms = get_kms(crtc);
 	const enum mdp5_cursor_alpha cur_alpha = CURSOR_ALPHA_PER_PIXEL;
 	uint32_t blendcfg, stride;
-	uint32_t x, y, width, height;
+	uint32_t x, y, src_x, src_y, width, height;
 	uint32_t roi_w, roi_h;
 	int lm;
 
@@ -800,6 +811,26 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 
 	get_roi(crtc, &roi_w, &roi_h);
 
+	/* If cusror buffer overlaps due to rotation on the
+	 * upper or left screen border the pixel offset inside
+	 * the cursor buffer of the ROI is the positive overlap
+	 * distance.
+	 */
+	if (mdp5_crtc->cursor.x < 0) {
+		src_x = abs(mdp5_crtc->cursor.x);
+		x = 0;
+	} else {
+		src_x = 0;
+	}
+	if (mdp5_crtc->cursor.y < 0) {
+		src_y = abs(mdp5_crtc->cursor.y);
+		y = 0;
+	} else {
+		src_y = 0;
+	}
+	DBG("%s: x=%d, y=%d roi_w=%d roi_h=%d src_x=%d src_y=%d",
+		crtc->name, x, y, roi_w, roi_h, src_x, src_y);
+
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_STRIDE(lm), stride);
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_FORMAT(lm),
 			MDP5_LM_CURSOR_FORMAT_FORMAT(CURSOR_FMT_ARGB8888));
@@ -812,6 +843,9 @@ static void mdp5_crtc_restore_cursor(struct drm_crtc *crtc)
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_START_XY(lm),
 			MDP5_LM_CURSOR_START_XY_Y_START(y) |
 			MDP5_LM_CURSOR_START_XY_X_START(x));
+	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_XY(lm),
+			MDP5_LM_CURSOR_XY_SRC_Y(src_y) |
+			MDP5_LM_CURSOR_XY_SRC_X(src_x));
 	mdp5_write(mdp5_kms, REG_MDP5_LM_CURSOR_BASE_ADDR(lm),
 			mdp5_crtc->cursor.iova);
 
@@ -932,8 +966,9 @@ static int mdp5_crtc_cursor_move(struct drm_crtc *crtc, int x, int y)
 	if (unlikely(!crtc->state->enable))
 		return 0;
 
-	mdp5_crtc->cursor.x = x = max(x, 0);
-	mdp5_crtc->cursor.y = y = max(y, 0);
+	/* accept negative x/y coordinates up to maximum cursor overlap */
+	mdp5_crtc->cursor.x = x = max(x, -(int)mdp5_crtc->cursor.width);
+	mdp5_crtc->cursor.y = y = max(y, -(int)mdp5_crtc->cursor.height);
 
 	get_roi(crtc, &roi_w, &roi_h);
 
-- 
cgit v1.2.3


From f2399f7522ac2a255f6502537609a51974be84be Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Thu, 28 Jun 2018 09:03:42 -0400
Subject: media: media.h: reorder video en/decoder functions

Keep the function defines in numerical order: 0x6000 comes after
0x2000, so move it back.

Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 include/uapi/linux/media.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index 6f594fa238c2..76d9bd64c116 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -89,13 +89,6 @@ struct media_device_info {
 #define MEDIA_ENT_F_FLASH			(MEDIA_ENT_F_OLD_SUBDEV_BASE + 2)
 #define MEDIA_ENT_F_LENS			(MEDIA_ENT_F_OLD_SUBDEV_BASE + 3)
 
-/*
- * Video decoder/encoder functions
- */
-#define MEDIA_ENT_F_ATV_DECODER			(MEDIA_ENT_F_OLD_SUBDEV_BASE + 4)
-#define MEDIA_ENT_F_DV_DECODER			(MEDIA_ENT_F_BASE + 0x6001)
-#define MEDIA_ENT_F_DV_ENCODER			(MEDIA_ENT_F_BASE + 0x6002)
-
 /*
  * Digital TV, analog TV, radio and/or software defined radio tuner functions.
  *
@@ -140,6 +133,13 @@ struct media_device_info {
 #define MEDIA_ENT_F_VID_MUX			(MEDIA_ENT_F_BASE + 0x5001)
 #define MEDIA_ENT_F_VID_IF_BRIDGE		(MEDIA_ENT_F_BASE + 0x5002)
 
+/*
+ * Video decoder/encoder functions
+ */
+#define MEDIA_ENT_F_ATV_DECODER			(MEDIA_ENT_F_OLD_SUBDEV_BASE + 4)
+#define MEDIA_ENT_F_DV_DECODER			(MEDIA_ENT_F_BASE + 0x6001)
+#define MEDIA_ENT_F_DV_ENCODER			(MEDIA_ENT_F_BASE + 0x6002)
+
 /* Entity flags */
 #define MEDIA_ENT_FL_DEFAULT			(1 << 0)
 #define MEDIA_ENT_FL_CONNECTOR			(1 << 1)
-- 
cgit v1.2.3


From ea107a183be1d6e69448d7100121c479e24b7c1d Mon Sep 17 00:00:00 2001
From: vkorjani <vikas.korjani@intel.com>
Date: Tue, 10 Apr 2018 10:12:45 -0400
Subject: drm: Add support for pps and compression mode command packet

After enabling DSC we need to send compression mode command packet
and pps data packet, for which 2 new data types are added
07h  Compression Mode Data Type Write , short write, 2 parameters
0Ah  PPS Long Write (word count determines number of bytes)
This patch adds support to send these packets.

Cc: David Airlie <airlied@linux.ie>
Cc: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
Cc: Tomi Valkeinen <tomi.valkeinen@ti.com>
Cc: dri-devel@lists.freedesktop.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-fbdev@vger.kernel.org

Changes in v3:
- None

Signed-off-by: vkorjani <vikas.korjani@intel.com>
[seanpaul removed pps_write_buffer fn, added types to packet_format helpers]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/drm_mipi_dsi.c | 2 ++
 include/video/mipi_display.h   | 3 +++
 2 files changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/drm_mipi_dsi.c b/drivers/gpu/drm/drm_mipi_dsi.c
index bc73b7f5b9fc..80b75501f5c6 100644
--- a/drivers/gpu/drm/drm_mipi_dsi.c
+++ b/drivers/gpu/drm/drm_mipi_dsi.c
@@ -392,6 +392,7 @@ bool mipi_dsi_packet_format_is_short(u8 type)
 	case MIPI_DSI_DCS_SHORT_WRITE:
 	case MIPI_DSI_DCS_SHORT_WRITE_PARAM:
 	case MIPI_DSI_DCS_READ:
+	case MIPI_DSI_DCS_COMPRESSION_MODE:
 	case MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE:
 		return true;
 	}
@@ -410,6 +411,7 @@ EXPORT_SYMBOL(mipi_dsi_packet_format_is_short);
 bool mipi_dsi_packet_format_is_long(u8 type)
 {
 	switch (type) {
+	case MIPI_DSI_PPS_LONG_WRITE:
 	case MIPI_DSI_NULL_PACKET:
 	case MIPI_DSI_BLANKING_PACKET:
 	case MIPI_DSI_GENERIC_LONG_WRITE:
diff --git a/include/video/mipi_display.h b/include/video/mipi_display.h
index 19aa65a35546..49a53ef8da96 100644
--- a/include/video/mipi_display.h
+++ b/include/video/mipi_display.h
@@ -38,6 +38,9 @@ enum {
 
 	MIPI_DSI_DCS_READ				= 0x06,
 
+	MIPI_DSI_DCS_COMPRESSION_MODE                   = 0x07,
+	MIPI_DSI_PPS_LONG_WRITE                         = 0x0A,
+
 	MIPI_DSI_SET_MAXIMUM_RETURN_PACKET_SIZE		= 0x37,
 
 	MIPI_DSI_END_OF_TRANSMISSION			= 0x08,
-- 
cgit v1.2.3


From a20a82b8642145a8d8decc6cd71e68f04647ed23 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 18 Jun 2018 05:08:20 -0400
Subject: media: ad9389b/adv7511: set proper media entity function

These two drivers both have function MEDIA_ENT_F_DV_ENCODER.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/ad9389b.c | 1 +
 drivers/media/i2c/adv7511.c | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/media/i2c/ad9389b.c b/drivers/media/i2c/ad9389b.c
index 91ff06088572..5b008b0002c0 100644
--- a/drivers/media/i2c/ad9389b.c
+++ b/drivers/media/i2c/ad9389b.c
@@ -1134,6 +1134,7 @@ static int ad9389b_probe(struct i2c_client *client, const struct i2c_device_id *
 		goto err_hdl;
 	}
 	state->pad.flags = MEDIA_PAD_FL_SINK;
+	sd->entity.function = MEDIA_ENT_F_DV_ENCODER;
 	err = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (err)
 		goto err_hdl;
diff --git a/drivers/media/i2c/adv7511.c b/drivers/media/i2c/adv7511.c
index 5731751d3f2a..55c2ea0720d9 100644
--- a/drivers/media/i2c/adv7511.c
+++ b/drivers/media/i2c/adv7511.c
@@ -1847,6 +1847,7 @@ static int adv7511_probe(struct i2c_client *client, const struct i2c_device_id *
 		goto err_hdl;
 	}
 	state->pad.flags = MEDIA_PAD_FL_SINK;
+	sd->entity.function = MEDIA_ENT_F_DV_ENCODER;
 	err = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (err)
 		goto err_hdl;
-- 
cgit v1.2.3


From ca0fa5f04f33eea010fc1f9dfc87ff58f3a2433f Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 18 Jun 2018 05:09:45 -0400
Subject: media: adv7180/tvp514x/tvp7002: fix entity function

The entity function was ORed with the flags field instead of
assigned to the function field. Correct this.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/adv7180.c | 2 +-
 drivers/media/i2c/tvp514x.c | 2 +-
 drivers/media/i2c/tvp7002.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index 25d24a3f10a7..a727d7f806a1 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -1335,7 +1335,7 @@ static int adv7180_probe(struct i2c_client *client,
 		goto err_unregister_vpp_client;
 
 	state->pad.flags = MEDIA_PAD_FL_SOURCE;
-	sd->entity.flags |= MEDIA_ENT_F_ATV_DECODER;
+	sd->entity.function = MEDIA_ENT_F_ATV_DECODER;
 	ret = media_entity_pads_init(&sd->entity, 1, &state->pad);
 	if (ret)
 		goto err_free_ctrl;
diff --git a/drivers/media/i2c/tvp514x.c b/drivers/media/i2c/tvp514x.c
index 6a9890531d01..675b9ae212ab 100644
--- a/drivers/media/i2c/tvp514x.c
+++ b/drivers/media/i2c/tvp514x.c
@@ -1084,7 +1084,7 @@ tvp514x_probe(struct i2c_client *client, const struct i2c_device_id *id)
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	decoder->pad.flags = MEDIA_PAD_FL_SOURCE;
 	decoder->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-	decoder->sd.entity.flags |= MEDIA_ENT_F_ATV_DECODER;
+	decoder->sd.entity.function = MEDIA_ENT_F_ATV_DECODER;
 
 	ret = media_entity_pads_init(&decoder->sd.entity, 1, &decoder->pad);
 	if (ret < 0) {
diff --git a/drivers/media/i2c/tvp7002.c b/drivers/media/i2c/tvp7002.c
index 4599b7e28a8d..4f5c627579c7 100644
--- a/drivers/media/i2c/tvp7002.c
+++ b/drivers/media/i2c/tvp7002.c
@@ -1010,7 +1010,7 @@ static int tvp7002_probe(struct i2c_client *c, const struct i2c_device_id *id)
 #if defined(CONFIG_MEDIA_CONTROLLER)
 	device->pad.flags = MEDIA_PAD_FL_SOURCE;
 	device->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-	device->sd.entity.flags |= MEDIA_ENT_F_ATV_DECODER;
+	device->sd.entity.function = MEDIA_ENT_F_ATV_DECODER;
 
 	error = media_entity_pads_init(&device->sd.entity, 1, &device->pad);
 	if (error < 0)
-- 
cgit v1.2.3


From 173bf6e51ba5845fbfcbdd281b837870fb033bc2 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Mon, 18 Jun 2018 05:10:28 -0400
Subject: media: media/i2c: add missing entity functions

Several drivers in media/i2c do not set the entity function.
Correct this.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/et8ek8/et8ek8_driver.c | 1 +
 drivers/media/i2c/mt9m032.c              | 1 +
 drivers/media/i2c/mt9p031.c              | 1 +
 drivers/media/i2c/mt9t001.c              | 1 +
 drivers/media/i2c/mt9v032.c              | 1 +
 5 files changed, 5 insertions(+)

diff --git a/drivers/media/i2c/et8ek8/et8ek8_driver.c b/drivers/media/i2c/et8ek8/et8ek8_driver.c
index e9eff9039ef5..37ef38947e01 100644
--- a/drivers/media/i2c/et8ek8/et8ek8_driver.c
+++ b/drivers/media/i2c/et8ek8/et8ek8_driver.c
@@ -1446,6 +1446,7 @@ static int et8ek8_probe(struct i2c_client *client,
 	sensor->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 	sensor->subdev.internal_ops = &et8ek8_internal_ops;
 
+	sensor->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&sensor->subdev.entity, 1, &sensor->pad);
 	if (ret < 0) {
diff --git a/drivers/media/i2c/mt9m032.c b/drivers/media/i2c/mt9m032.c
index 6a9e068462fd..b385f2b632ad 100644
--- a/drivers/media/i2c/mt9m032.c
+++ b/drivers/media/i2c/mt9m032.c
@@ -793,6 +793,7 @@ static int mt9m032_probe(struct i2c_client *client,
 	v4l2_ctrl_cluster(2, &sensor->hflip);
 
 	sensor->subdev.ctrl_handler = &sensor->ctrls;
+	sensor->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&sensor->subdev.entity, 1, &sensor->pad);
 	if (ret < 0)
diff --git a/drivers/media/i2c/mt9p031.c b/drivers/media/i2c/mt9p031.c
index 91d822fc4443..715be3632b01 100644
--- a/drivers/media/i2c/mt9p031.c
+++ b/drivers/media/i2c/mt9p031.c
@@ -1111,6 +1111,7 @@ static int mt9p031_probe(struct i2c_client *client,
 	v4l2_i2c_subdev_init(&mt9p031->subdev, client, &mt9p031_subdev_ops);
 	mt9p031->subdev.internal_ops = &mt9p031_subdev_internal_ops;
 
+	mt9p031->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	mt9p031->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&mt9p031->subdev.entity, 1, &mt9p031->pad);
 	if (ret < 0)
diff --git a/drivers/media/i2c/mt9t001.c b/drivers/media/i2c/mt9t001.c
index 9d981d9f5686..f683d2cb0486 100644
--- a/drivers/media/i2c/mt9t001.c
+++ b/drivers/media/i2c/mt9t001.c
@@ -943,6 +943,7 @@ static int mt9t001_probe(struct i2c_client *client,
 	mt9t001->subdev.internal_ops = &mt9t001_subdev_internal_ops;
 	mt9t001->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
+	mt9t001->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	mt9t001->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&mt9t001->subdev.entity, 1, &mt9t001->pad);
 
diff --git a/drivers/media/i2c/mt9v032.c b/drivers/media/i2c/mt9v032.c
index 4de63b2df334..f74730d24d8f 100644
--- a/drivers/media/i2c/mt9v032.c
+++ b/drivers/media/i2c/mt9v032.c
@@ -1162,6 +1162,7 @@ static int mt9v032_probe(struct i2c_client *client,
 	mt9v032->subdev.internal_ops = &mt9v032_subdev_internal_ops;
 	mt9v032->subdev.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
 
+	mt9v032->subdev.entity.function = MEDIA_ENT_F_CAM_SENSOR;
 	mt9v032->pad.flags = MEDIA_PAD_FL_SOURCE;
 	ret = media_entity_pads_init(&mt9v032->subdev.entity, 1, &mt9v032->pad);
 	if (ret < 0)
-- 
cgit v1.2.3


From e5def285688f8935b3ad208459abb384f7912f34 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Fri, 29 Jun 2018 07:29:52 -0400
Subject: media: media-ioc-enum-links.rst: improve pad index description

Make it clearer that the index starts at 0.

Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-ioc-enum-links.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst b/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst
index 17abdeed1a9c..f158c134e9b0 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-enum-links.rst
@@ -92,7 +92,7 @@ returned during the enumeration process.
 
     *  -  __u16
        -  ``index``
-       -  0-based pad index.
+       -  Pad index, starts at 0.
 
     *  -  __u32
        -  ``flags``
-- 
cgit v1.2.3


From 8601494e0ec0a7697230b2abca25d786b793341b Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hansverk@cisco.com>
Date: Fri, 29 Jun 2018 07:31:20 -0400
Subject: media: media-ioc-enum-entities.rst/-g-topology.rst: clarify ID/name
 usage

Mention that IDs should not be hardcoded in applications and that the
entity name must be unique within the media topology.

Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../media/uapi/mediactl/media-ioc-enum-entities.rst   |  9 ++++++---
 .../media/uapi/mediactl/media-ioc-g-topology.rst      | 19 ++++++++++++++-----
 2 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst b/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst
index 961466ae821d..fc2e39c070c9 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-enum-entities.rst
@@ -62,15 +62,18 @@ id's until they get an error.
        -  ``id``
        -
        -
-       -  Entity id, set by the application. When the id is or'ed with
+       -  Entity ID, set by the application. When the ID is or'ed with
 	  ``MEDIA_ENT_ID_FLAG_NEXT``, the driver clears the flag and returns
-	  the first entity with a larger id.
+	  the first entity with a larger ID. Do not expect that the ID will
+	  always be the same for each instance of the device. In other words,
+	  do not hardcode entity IDs in an application.
 
     *  -  char
        -  ``name``\ [32]
        -
        -
-       -  Entity name as an UTF-8 NULL-terminated string.
+       -  Entity name as an UTF-8 NULL-terminated string. This name must be unique
+          within the media topology.
 
     *  -  __u32
        -  ``type``
diff --git a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
index d6f41a8e307f..bac128c7eda9 100644
--- a/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
+++ b/Documentation/media/uapi/mediactl/media-ioc-g-topology.rst
@@ -131,11 +131,14 @@ desired arrays with the media graph elements.
 
     *  -  __u32
        -  ``id``
-       -  Unique ID for the entity.
+       -  Unique ID for the entity. Do not expect that the ID will
+	  always be the same for each instance of the device. In other words,
+	  do not hardcode entity IDs in an application.
 
     *  -  char
        -  ``name``\ [64]
-       -  Entity name as an UTF-8 NULL-terminated string.
+       -  Entity name as an UTF-8 NULL-terminated string. This name must be unique
+          within the media topology.
 
     *  -  __u32
        -  ``function``
@@ -166,7 +169,9 @@ desired arrays with the media graph elements.
 
     *  -  __u32
        -  ``id``
-       -  Unique ID for the interface.
+       -  Unique ID for the interface. Do not expect that the ID will
+	  always be the same for each instance of the device. In other words,
+	  do not hardcode interface IDs in an application.
 
     *  -  __u32
        -  ``intf_type``
@@ -215,7 +220,9 @@ desired arrays with the media graph elements.
 
     *  -  __u32
        -  ``id``
-       -  Unique ID for the pad.
+       -  Unique ID for the pad. Do not expect that the ID will
+	  always be the same for each instance of the device. In other words,
+	  do not hardcode pad IDs in an application.
 
     *  -  __u32
        -  ``entity_id``
@@ -249,7 +256,9 @@ desired arrays with the media graph elements.
 
     *  -  __u32
        -  ``id``
-       -  Unique ID for the link.
+       -  Unique ID for the link. Do not expect that the ID will
+	  always be the same for each instance of the device. In other words,
+	  do not hardcode link IDs in an application.
 
     *  -  __u32
        -  ``source_id``
-- 
cgit v1.2.3


From 45841a977391f24b9bf713548c588d148a576d22 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Wed, 4 Jul 2018 10:13:47 -0400
Subject: media: media.h: add encoder/decoder functions for codecs

Add MEDIA_ENT_F_PROC_VIDEO_EN/DECODER to be used for the encoder
and decoder entities of codec hardware.

[mchehab+samsung@kernel.org: split description on two senteces by adding dots]
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-types.rst | 11 +++++++++++
 include/uapi/linux/media.h                        |  2 ++
 2 files changed, 13 insertions(+)

diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst
index e90d4d0a7f8b..7b17acc049cf 100644
--- a/Documentation/media/uapi/mediactl/media-types.rst
+++ b/Documentation/media/uapi/mediactl/media-types.rst
@@ -37,6 +37,8 @@ Types and flags used to represent the media graph elements
 .. _MEDIA-ENT-F-PROC-VIDEO-LUT:
 .. _MEDIA-ENT-F-PROC-VIDEO-SCALER:
 .. _MEDIA-ENT-F-PROC-VIDEO-STATISTICS:
+.. _MEDIA-ENT-F-PROC-VIDEO-ENCODER:
+.. _MEDIA-ENT-F-PROC-VIDEO-DECODER:
 .. _MEDIA-ENT-F-VID-MUX:
 .. _MEDIA-ENT-F-VID-IF-BRIDGE:
 .. _MEDIA-ENT-F-DTV-DECODER:
@@ -188,6 +190,15 @@ Types and flags used to represent the media graph elements
 	  received on its sink pad and outputs the statistics data on
 	  its source pad.
 
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_ENCODER``
+       -  Video (MPEG, HEVC, VPx, etc.) encoder. An entity capable of
+          compressing video frames. Must have one sink pad and one source pad.
+
+    *  -  ``MEDIA_ENT_F_PROC_VIDEO_DECODER``
+       -  Video (MPEG, HEVC, VPx, etc.) decoder. An entity capable of
+          decompressing a compressed video stream into uncompressed video
+	  frames. Must have one sink pad and one source pad.
+
     *  -  ``MEDIA_ENT_F_VID_MUX``
        - Video multiplexer. An entity capable of multiplexing must have at
          least two sink pads and one source pad, and must pass the video
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index 76d9bd64c116..82ec9f132a53 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -126,6 +126,8 @@ struct media_device_info {
 #define MEDIA_ENT_F_PROC_VIDEO_LUT		(MEDIA_ENT_F_BASE + 0x4004)
 #define MEDIA_ENT_F_PROC_VIDEO_SCALER		(MEDIA_ENT_F_BASE + 0x4005)
 #define MEDIA_ENT_F_PROC_VIDEO_STATISTICS	(MEDIA_ENT_F_BASE + 0x4006)
+#define MEDIA_ENT_F_PROC_VIDEO_ENCODER		(MEDIA_ENT_F_BASE + 0x4007)
+#define MEDIA_ENT_F_PROC_VIDEO_DECODER		(MEDIA_ENT_F_BASE + 0x4008)
 
 /*
  * Switch and bridge entity functions
-- 
cgit v1.2.3


From 62c3fce04154777e6a3ce3a27f123b645d36dcff Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Wed, 4 Jul 2018 10:13:47 -0400
Subject: media: videodev.h: add PIX_FMT_FWHT for use with vicodec

Add a new pixelformat for the vicodec software codec using the
Fast Walsh Hadamard Transform.

Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/pixfmt-compressed.rst | 7 +++++++
 drivers/media/v4l2-core/v4l2-ioctl.c               | 1 +
 include/uapi/linux/videodev2.h                     | 1 +
 3 files changed, 9 insertions(+)

diff --git a/Documentation/media/uapi/v4l/pixfmt-compressed.rst b/Documentation/media/uapi/v4l/pixfmt-compressed.rst
index abec03937bb3..d382e7a5c38e 100644
--- a/Documentation/media/uapi/v4l/pixfmt-compressed.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-compressed.rst
@@ -95,3 +95,10 @@ Compressed Formats
       - ``V4L2_PIX_FMT_HEVC``
       - 'HEVC'
       - HEVC/H.265 video elementary stream.
+    * .. _V4L2-PIX-FMT-FWHT:
+
+      - ``V4L2_PIX_FMT_FWHT``
+      - 'FWHT'
+      - Video elementary stream using a codec based on the Fast Walsh Hadamard
+        Transform. This codec is implemented by the vicodec ('Virtual Codec')
+	driver. See the vicodec-codec.h header for more details.
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 01670567641a..26d9702069fd 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -1311,6 +1311,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 		case V4L2_PIX_FMT_VP8:		descr = "VP8"; break;
 		case V4L2_PIX_FMT_VP9:		descr = "VP9"; break;
 		case V4L2_PIX_FMT_HEVC:		descr = "HEVC"; break; /* aka H.265 */
+		case V4L2_PIX_FMT_FWHT:		descr = "FWHT"; break; /* used in vicodec */
 		case V4L2_PIX_FMT_CPIA1:	descr = "GSPCA CPiA YUV"; break;
 		case V4L2_PIX_FMT_WNVA:		descr = "WNVA"; break;
 		case V4L2_PIX_FMT_SN9C10X:	descr = "GSPCA SN9C10X"; break;
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 600877be5c22..3ea8097c2470 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -636,6 +636,7 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_VP8      v4l2_fourcc('V', 'P', '8', '0') /* VP8 */
 #define V4L2_PIX_FMT_VP9      v4l2_fourcc('V', 'P', '9', '0') /* VP9 */
 #define V4L2_PIX_FMT_HEVC     v4l2_fourcc('H', 'E', 'V', 'C') /* HEVC aka H.265 */
+#define V4L2_PIX_FMT_FWHT     v4l2_fourcc('F', 'W', 'H', 'T') /* Fast Walsh Hadamard Transform (vicodec) */
 
 /*  Vendor-specific formats   */
 #define V4L2_PIX_FMT_CPIA1    v4l2_fourcc('C', 'P', 'I', 'A') /* cpia1 YUV */
-- 
cgit v1.2.3


From ee1228cca15ce097b7badebfdd0fef23a2cca9e1 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Tue, 26 Jun 2018 09:26:52 -0400
Subject: media: v4l2-mem2mem: add v4l2_m2m_last_buf()

This can be used to mark the last queued source buffer as the last
buffer.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-mem2mem.c | 18 ++++++++++++++++++
 include/media/v4l2-mem2mem.h           | 29 +++++++++++++++++++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 4aeedb91594a..d9565ee44578 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -129,6 +129,24 @@ void *v4l2_m2m_next_buf(struct v4l2_m2m_queue_ctx *q_ctx)
 }
 EXPORT_SYMBOL_GPL(v4l2_m2m_next_buf);
 
+void *v4l2_m2m_last_buf(struct v4l2_m2m_queue_ctx *q_ctx)
+{
+	struct v4l2_m2m_buffer *b;
+	unsigned long flags;
+
+	spin_lock_irqsave(&q_ctx->rdy_spinlock, flags);
+
+	if (list_empty(&q_ctx->rdy_queue)) {
+		spin_unlock_irqrestore(&q_ctx->rdy_spinlock, flags);
+		return NULL;
+	}
+
+	b = list_last_entry(&q_ctx->rdy_queue, struct v4l2_m2m_buffer, list);
+	spin_unlock_irqrestore(&q_ctx->rdy_spinlock, flags);
+	return &b->vb;
+}
+EXPORT_SYMBOL_GPL(v4l2_m2m_last_buf);
+
 void *v4l2_m2m_buf_remove(struct v4l2_m2m_queue_ctx *q_ctx)
 {
 	struct v4l2_m2m_buffer *b;
diff --git a/include/media/v4l2-mem2mem.h b/include/media/v4l2-mem2mem.h
index d60d3060f762..d655720e16a1 100644
--- a/include/media/v4l2-mem2mem.h
+++ b/include/media/v4l2-mem2mem.h
@@ -449,6 +449,35 @@ static inline void *v4l2_m2m_next_dst_buf(struct v4l2_m2m_ctx *m2m_ctx)
 	return v4l2_m2m_next_buf(&m2m_ctx->cap_q_ctx);
 }
 
+/**
+ * v4l2_m2m_last_buf() - return last buffer from the list of ready buffers
+ *
+ * @q_ctx: pointer to struct @v4l2_m2m_queue_ctx
+ */
+void *v4l2_m2m_last_buf(struct v4l2_m2m_queue_ctx *q_ctx);
+
+/**
+ * v4l2_m2m_last_src_buf() - return last destination buffer from the list of
+ * ready buffers
+ *
+ * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx
+ */
+static inline void *v4l2_m2m_last_src_buf(struct v4l2_m2m_ctx *m2m_ctx)
+{
+	return v4l2_m2m_last_buf(&m2m_ctx->out_q_ctx);
+}
+
+/**
+ * v4l2_m2m_last_dst_buf() - return last destination buffer from the list of
+ * ready buffers
+ *
+ * @m2m_ctx: m2m context assigned to the instance given by struct &v4l2_m2m_ctx
+ */
+static inline void *v4l2_m2m_last_dst_buf(struct v4l2_m2m_ctx *m2m_ctx)
+{
+	return v4l2_m2m_last_buf(&m2m_ctx->cap_q_ctx);
+}
+
 /**
  * v4l2_m2m_for_each_dst_buf() - iterate over a list of destination ready
  * buffers
-- 
cgit v1.2.3


From 251d6fe9a6753f8d2b5b7565c7044dbd82d63d62 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Fri, 20 Jul 2018 03:49:21 -0400
Subject: media: vicodec: add the FWHT software codec

Add a software codec based on the Fast Walsh Hadamard Transform.

The original FWHT codec was developed by Tom aan de Wiel, and it was
turned into 'proper' kernel code by Hans Verkuil, with a lot of
performance and memory improvements.

Signed-off-by: Tom aan de Wiel <tom.aandewiel@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vicodec/vicodec-codec.c | 797 +++++++++++++++++++++++++
 drivers/media/platform/vicodec/vicodec-codec.h | 129 ++++
 2 files changed, 926 insertions(+)
 create mode 100644 drivers/media/platform/vicodec/vicodec-codec.c
 create mode 100644 drivers/media/platform/vicodec/vicodec-codec.h

diff --git a/drivers/media/platform/vicodec/vicodec-codec.c b/drivers/media/platform/vicodec/vicodec-codec.c
new file mode 100644
index 000000000000..e880a6c5747f
--- /dev/null
+++ b/drivers/media/platform/vicodec/vicodec-codec.c
@@ -0,0 +1,797 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright 2016 Tom aan de Wiel
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * 8x8 Fast Walsh Hadamard Transform in sequency order based on the paper:
+ *
+ * A Recursive Algorithm for Sequency-Ordered Fast Walsh Transforms,
+ * R.D. Brown, 1977
+ */
+
+#include <linux/string.h>
+#include "vicodec-codec.h"
+
+#define ALL_ZEROS 15
+#define DEADZONE_WIDTH 20
+
+static const uint8_t zigzag[64] = {
+	0,
+	1,  8,
+	2,  9, 16,
+	3, 10, 17, 24,
+	4, 11, 18, 25, 32,
+	5, 12, 19, 26, 33, 40,
+	6, 13, 20, 27, 34, 41, 48,
+	7, 14, 21, 28, 35, 42, 49, 56,
+	15, 22, 29, 36, 43, 50, 57,
+	23, 30, 37, 44, 51, 58,
+	31, 38, 45, 52, 59,
+	39, 46, 53, 60,
+	47, 54, 61,
+	55, 62,
+	63,
+};
+
+
+static int rlc(const s16 *in, __be16 *output, int blocktype)
+{
+	s16 block[8 * 8];
+	s16 *wp = block;
+	int i = 0;
+	int x, y;
+	int ret = 0;
+
+	/* read in block from framebuffer */
+	int lastzero_run = 0;
+	int to_encode;
+
+	for (y = 0; y < 8; y++) {
+		for (x = 0; x < 8; x++) {
+			*wp = in[x + y * 8];
+			wp++;
+		}
+	}
+
+	/* keep track of amount of trailing zeros */
+	for (i = 63; i >= 0 && !block[zigzag[i]]; i--)
+		lastzero_run++;
+
+	*output++ = (blocktype == PBLOCK ? htons(PFRAME_BIT) : 0);
+	ret++;
+
+	to_encode = 8 * 8 - (lastzero_run > 14 ? lastzero_run : 0);
+
+	i = 0;
+	while (i < to_encode) {
+		int cnt = 0;
+		int tmp;
+
+		/* count leading zeros */
+		while ((tmp = block[zigzag[i]]) == 0 && cnt < 14) {
+			cnt++;
+			i++;
+			if (i == to_encode) {
+				cnt--;
+				break;
+			}
+		}
+		/* 4 bits for run, 12 for coefficient (quantization by 4) */
+		*output++ = htons((cnt | tmp << 4));
+		i++;
+		ret++;
+	}
+	if (lastzero_run > 14) {
+		*output = htons(ALL_ZEROS | 0);
+		ret++;
+	}
+
+	return ret;
+}
+
+/*
+ * This function will worst-case increase rlc_in by 65*2 bytes:
+ * one s16 value for the header and 8 * 8 coefficients of type s16.
+ */
+static s16 derlc(const __be16 **rlc_in, s16 *dwht_out)
+{
+	/* header */
+	const __be16 *input = *rlc_in;
+	s16 ret = ntohs(*input++);
+	int dec_count = 0;
+	s16 block[8 * 8 + 16];
+	s16 *wp = block;
+	int i;
+
+	/*
+	 * Now de-compress, it expands one byte to up to 15 bytes
+	 * (or fills the remainder of the 64 bytes with zeroes if it
+	 * is the last byte to expand).
+	 *
+	 * So block has to be 8 * 8 + 16 bytes, the '+ 16' is to
+	 * allow for overflow if the incoming data was malformed.
+	 */
+	while (dec_count < 8 * 8) {
+		s16 in = ntohs(*input++);
+		int length = in & 0xf;
+		int coeff = in >> 4;
+
+		/* fill remainder with zeros */
+		if (length == 15) {
+			for (i = 0; i < 64 - dec_count; i++)
+				*wp++ = 0;
+			break;
+		}
+
+		for (i = 0; i < length; i++)
+			*wp++ = 0;
+		*wp++ = coeff;
+		dec_count += length + 1;
+	}
+
+	wp = block;
+
+	for (i = 0; i < 64; i++) {
+		int pos = zigzag[i];
+		int y = pos / 8;
+		int x = pos % 8;
+
+		dwht_out[x + y * 8] = *wp++;
+	}
+	*rlc_in = input;
+	return ret;
+}
+
+static const int quant_table[] = {
+	2, 2, 2, 2, 2, 2,  2,  2,
+	2, 2, 2, 2, 2, 2,  2,  2,
+	2, 2, 2, 2, 2, 2,  2,  3,
+	2, 2, 2, 2, 2, 2,  3,  6,
+	2, 2, 2, 2, 2, 3,  6,  6,
+	2, 2, 2, 2, 3, 6,  6,  6,
+	2, 2, 2, 3, 6, 6,  6,  6,
+	2, 2, 3, 6, 6, 6,  6,  8,
+};
+
+static const int quant_table_p[] = {
+	3, 3, 3, 3, 3, 3,  3,  3,
+	3, 3, 3, 3, 3, 3,  3,  3,
+	3, 3, 3, 3, 3, 3,  3,  3,
+	3, 3, 3, 3, 3, 3,  3,  6,
+	3, 3, 3, 3, 3, 3,  6,  6,
+	3, 3, 3, 3, 3, 6,  6,  9,
+	3, 3, 3, 3, 6, 6,  9,  9,
+	3, 3, 3, 6, 6, 9,  9,  10,
+};
+
+static void quantize_intra(s16 *coeff, s16 *de_coeff)
+{
+	const int *quant = quant_table;
+	int i, j;
+
+	for (j = 0; j < 8; j++) {
+		for (i = 0; i < 8; i++, quant++, coeff++, de_coeff++) {
+			*coeff >>= *quant;
+			if (*coeff >= -DEADZONE_WIDTH &&
+			    *coeff <= DEADZONE_WIDTH)
+				*coeff = *de_coeff = 0;
+			else
+				*de_coeff = *coeff << *quant;
+		}
+	}
+}
+
+static void dequantize_intra(s16 *coeff)
+{
+	const int *quant = quant_table;
+	int i, j;
+
+	for (j = 0; j < 8; j++)
+		for (i = 0; i < 8; i++, quant++, coeff++)
+			*coeff <<= *quant;
+}
+
+static void quantize_inter(s16 *coeff, s16 *de_coeff)
+{
+	const int *quant = quant_table_p;
+	int i, j;
+
+	for (j = 0; j < 8; j++) {
+		for (i = 0; i < 8; i++, quant++, coeff++, de_coeff++) {
+			*coeff >>= *quant;
+			if (*coeff >= -DEADZONE_WIDTH &&
+			    *coeff <= DEADZONE_WIDTH)
+				*coeff = *de_coeff = 0;
+			else
+				*de_coeff = *coeff << *quant;
+		}
+	}
+}
+
+static void dequantize_inter(s16 *coeff)
+{
+	const int *quant = quant_table_p;
+	int i, j;
+
+	for (j = 0; j < 8; j++)
+		for (i = 0; i < 8; i++, quant++, coeff++)
+			*coeff <<= *quant;
+}
+
+static void fwht(const u8 *block, s16 *output_block, unsigned int stride,
+		 unsigned int input_step, bool intra)
+{
+	/* we'll need more than 8 bits for the transformed coefficients */
+	s32 workspace1[8], workspace2[8];
+	const u8 *tmp = block;
+	s16 *out = output_block;
+	int add = intra ? 256 : 0;
+	unsigned int i;
+
+	/* stage 1 */
+	stride *= input_step;
+
+	for (i = 0; i < 8; i++, tmp += stride, out += 8) {
+		if (input_step == 1) {
+			workspace1[0]  = tmp[0] + tmp[1] - add;
+			workspace1[1]  = tmp[0] - tmp[1];
+
+			workspace1[2]  = tmp[2] + tmp[3] - add;
+			workspace1[3]  = tmp[2] - tmp[3];
+
+			workspace1[4]  = tmp[4] + tmp[5] - add;
+			workspace1[5]  = tmp[4] - tmp[5];
+
+			workspace1[6]  = tmp[6] + tmp[7] - add;
+			workspace1[7]  = tmp[6] - tmp[7];
+		} else {
+			workspace1[0]  = tmp[0] + tmp[2] - add;
+			workspace1[1]  = tmp[0] - tmp[2];
+
+			workspace1[2]  = tmp[4] + tmp[6] - add;
+			workspace1[3]  = tmp[4] - tmp[6];
+
+			workspace1[4]  = tmp[8] + tmp[10] - add;
+			workspace1[5]  = tmp[8] - tmp[10];
+
+			workspace1[6]  = tmp[12] + tmp[14] - add;
+			workspace1[7]  = tmp[12] - tmp[14];
+		}
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0] = workspace2[0] + workspace2[4];
+		out[1] = workspace2[0] - workspace2[4];
+		out[2] = workspace2[1] - workspace2[5];
+		out[3] = workspace2[1] + workspace2[5];
+		out[4] = workspace2[2] + workspace2[6];
+		out[5] = workspace2[2] - workspace2[6];
+		out[6] = workspace2[3] - workspace2[7];
+		out[7] = workspace2[3] + workspace2[7];
+	}
+
+	out = output_block;
+
+	for (i = 0; i < 8; i++, out++) {
+		/* stage 1 */
+		workspace1[0]  = out[0] + out[1 * 8];
+		workspace1[1]  = out[0] - out[1 * 8];
+
+		workspace1[2]  = out[2 * 8] + out[3 * 8];
+		workspace1[3]  = out[2 * 8] - out[3 * 8];
+
+		workspace1[4]  = out[4 * 8] + out[5 * 8];
+		workspace1[5]  = out[4 * 8] - out[5 * 8];
+
+		workspace1[6]  = out[6 * 8] + out[7 * 8];
+		workspace1[7]  = out[6 * 8] - out[7 * 8];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+		/* stage 3 */
+		out[0 * 8] = workspace2[0] + workspace2[4];
+		out[1 * 8] = workspace2[0] - workspace2[4];
+		out[2 * 8] = workspace2[1] - workspace2[5];
+		out[3 * 8] = workspace2[1] + workspace2[5];
+		out[4 * 8] = workspace2[2] + workspace2[6];
+		out[5 * 8] = workspace2[2] - workspace2[6];
+		out[6 * 8] = workspace2[3] - workspace2[7];
+		out[7 * 8] = workspace2[3] + workspace2[7];
+	}
+}
+
+/*
+ * Not the nicest way of doing it, but P-blocks get twice the range of
+ * that of the I-blocks. Therefore we need a type bigger than 8 bits.
+ * Furthermore values can be negative... This is just a version that
+ * works with 16 signed data
+ */
+static void fwht16(const s16 *block, s16 *output_block, int stride, int intra)
+{
+	/* we'll need more than 8 bits for the transformed coefficients */
+	s32 workspace1[8], workspace2[8];
+	const s16 *tmp = block;
+	s16 *out = output_block;
+	int i;
+
+	for (i = 0; i < 8; i++, tmp += stride, out += 8) {
+		/* stage 1 */
+		workspace1[0]  = tmp[0] + tmp[1];
+		workspace1[1]  = tmp[0] - tmp[1];
+
+		workspace1[2]  = tmp[2] + tmp[3];
+		workspace1[3]  = tmp[2] - tmp[3];
+
+		workspace1[4]  = tmp[4] + tmp[5];
+		workspace1[5]  = tmp[4] - tmp[5];
+
+		workspace1[6]  = tmp[6] + tmp[7];
+		workspace1[7]  = tmp[6] - tmp[7];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0] = workspace2[0] + workspace2[4];
+		out[1] = workspace2[0] - workspace2[4];
+		out[2] = workspace2[1] - workspace2[5];
+		out[3] = workspace2[1] + workspace2[5];
+		out[4] = workspace2[2] + workspace2[6];
+		out[5] = workspace2[2] - workspace2[6];
+		out[6] = workspace2[3] - workspace2[7];
+		out[7] = workspace2[3] + workspace2[7];
+	}
+
+	out = output_block;
+
+	for (i = 0; i < 8; i++, out++) {
+		/* stage 1 */
+		workspace1[0]  = out[0] + out[1*8];
+		workspace1[1]  = out[0] - out[1*8];
+
+		workspace1[2]  = out[2*8] + out[3*8];
+		workspace1[3]  = out[2*8] - out[3*8];
+
+		workspace1[4]  = out[4*8] + out[5*8];
+		workspace1[5]  = out[4*8] - out[5*8];
+
+		workspace1[6]  = out[6*8] + out[7*8];
+		workspace1[7]  = out[6*8] - out[7*8];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0*8] = workspace2[0] + workspace2[4];
+		out[1*8] = workspace2[0] - workspace2[4];
+		out[2*8] = workspace2[1] - workspace2[5];
+		out[3*8] = workspace2[1] + workspace2[5];
+		out[4*8] = workspace2[2] + workspace2[6];
+		out[5*8] = workspace2[2] - workspace2[6];
+		out[6*8] = workspace2[3] - workspace2[7];
+		out[7*8] = workspace2[3] + workspace2[7];
+	}
+}
+
+static void ifwht(const s16 *block, s16 *output_block, int intra)
+{
+	/*
+	 * we'll need more than 8 bits for the transformed coefficients
+	 * use native unit of cpu
+	 */
+	int workspace1[8], workspace2[8];
+	int inter = intra ? 0 : 1;
+	const s16 *tmp = block;
+	s16 *out = output_block;
+	int i;
+
+	for (i = 0; i < 8; i++, tmp += 8, out += 8) {
+		/* stage 1 */
+		workspace1[0]  = tmp[0] + tmp[1];
+		workspace1[1]  = tmp[0] - tmp[1];
+
+		workspace1[2]  = tmp[2] + tmp[3];
+		workspace1[3]  = tmp[2] - tmp[3];
+
+		workspace1[4]  = tmp[4] + tmp[5];
+		workspace1[5]  = tmp[4] - tmp[5];
+
+		workspace1[6]  = tmp[6] + tmp[7];
+		workspace1[7]  = tmp[6] - tmp[7];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		out[0] = workspace2[0] + workspace2[4];
+		out[1] = workspace2[0] - workspace2[4];
+		out[2] = workspace2[1] - workspace2[5];
+		out[3] = workspace2[1] + workspace2[5];
+		out[4] = workspace2[2] + workspace2[6];
+		out[5] = workspace2[2] - workspace2[6];
+		out[6] = workspace2[3] - workspace2[7];
+		out[7] = workspace2[3] + workspace2[7];
+	}
+
+	out = output_block;
+
+	for (i = 0; i < 8; i++, out++) {
+		/* stage 1 */
+		workspace1[0]  = out[0] + out[1 * 8];
+		workspace1[1]  = out[0] - out[1 * 8];
+
+		workspace1[2]  = out[2 * 8] + out[3 * 8];
+		workspace1[3]  = out[2 * 8] - out[3 * 8];
+
+		workspace1[4]  = out[4 * 8] + out[5 * 8];
+		workspace1[5]  = out[4 * 8] - out[5 * 8];
+
+		workspace1[6]  = out[6 * 8] + out[7 * 8];
+		workspace1[7]  = out[6 * 8] - out[7 * 8];
+
+		/* stage 2 */
+		workspace2[0] = workspace1[0] + workspace1[2];
+		workspace2[1] = workspace1[0] - workspace1[2];
+		workspace2[2] = workspace1[1] - workspace1[3];
+		workspace2[3] = workspace1[1] + workspace1[3];
+
+		workspace2[4] = workspace1[4] + workspace1[6];
+		workspace2[5] = workspace1[4] - workspace1[6];
+		workspace2[6] = workspace1[5] - workspace1[7];
+		workspace2[7] = workspace1[5] + workspace1[7];
+
+		/* stage 3 */
+		if (inter) {
+			int d;
+
+			out[0 * 8] = workspace2[0] + workspace2[4];
+			out[1 * 8] = workspace2[0] - workspace2[4];
+			out[2 * 8] = workspace2[1] - workspace2[5];
+			out[3 * 8] = workspace2[1] + workspace2[5];
+			out[4 * 8] = workspace2[2] + workspace2[6];
+			out[5 * 8] = workspace2[2] - workspace2[6];
+			out[6 * 8] = workspace2[3] - workspace2[7];
+			out[7 * 8] = workspace2[3] + workspace2[7];
+
+			for (d = 0; d < 8; d++)
+				out[8 * d] >>= 6;
+		} else {
+			int d;
+
+			out[0 * 8] = workspace2[0] + workspace2[4];
+			out[1 * 8] = workspace2[0] - workspace2[4];
+			out[2 * 8] = workspace2[1] - workspace2[5];
+			out[3 * 8] = workspace2[1] + workspace2[5];
+			out[4 * 8] = workspace2[2] + workspace2[6];
+			out[5 * 8] = workspace2[2] - workspace2[6];
+			out[6 * 8] = workspace2[3] - workspace2[7];
+			out[7 * 8] = workspace2[3] + workspace2[7];
+
+			for (d = 0; d < 8; d++) {
+				out[8 * d] >>= 6;
+				out[8 * d] += 128;
+			}
+		}
+	}
+}
+
+static void fill_encoder_block(const u8 *input, s16 *dst,
+			       unsigned int stride, unsigned int input_step)
+{
+	int i, j;
+
+	for (i = 0; i < 8; i++) {
+		for (j = 0; j < 8; j++, input += input_step)
+			*dst++ = *input;
+		input += (stride - 8) * input_step;
+	}
+}
+
+static int var_intra(const s16 *input)
+{
+	int32_t mean = 0;
+	int32_t ret = 0;
+	const s16 *tmp = input;
+	int i;
+
+	for (i = 0; i < 8 * 8; i++, tmp++)
+		mean += *tmp;
+	mean /= 64;
+	tmp = input;
+	for (i = 0; i < 8 * 8; i++, tmp++)
+		ret += (*tmp - mean) < 0 ? -(*tmp - mean) : (*tmp - mean);
+	return ret;
+}
+
+static int var_inter(const s16 *old, const s16 *new)
+{
+	int32_t ret = 0;
+	int i;
+
+	for (i = 0; i < 8 * 8; i++, old++, new++)
+		ret += (*old - *new) < 0 ? -(*old - *new) : (*old - *new);
+	return ret;
+}
+
+static int decide_blocktype(const u8 *current, const u8 *reference,
+			    s16 *deltablock, unsigned int stride,
+			    unsigned int input_step)
+{
+	s16 tmp[64];
+	s16 old[64];
+	s16 *work = tmp;
+	unsigned int k, l;
+	int vari;
+	int vard;
+
+	fill_encoder_block(current, tmp, stride, input_step);
+	fill_encoder_block(reference, old, 8, 1);
+	vari = var_intra(tmp);
+
+	for (k = 0; k < 8; k++) {
+		for (l = 0; l < 8; l++) {
+			*deltablock = *work - *reference;
+			deltablock++;
+			work++;
+			reference++;
+		}
+	}
+	deltablock -= 64;
+	vard = var_inter(old, tmp);
+	return vari <= vard ? IBLOCK : PBLOCK;
+}
+
+static void fill_decoder_block(u8 *dst, const s16 *input, int stride)
+{
+	int i, j;
+
+	for (i = 0; i < 8; i++) {
+		for (j = 0; j < 8; j++)
+			*dst++ = *input++;
+		dst += stride - 8;
+	}
+}
+
+static void add_deltas(s16 *deltas, const u8 *ref, int stride)
+{
+	int k, l;
+
+	for (k = 0; k < 8; k++) {
+		for (l = 0; l < 8; l++) {
+			*deltas += *ref++;
+			/*
+			 * Due to quantizing, it might possible that the
+			 * decoded coefficients are slightly out of range
+			 */
+			if (*deltas < 0)
+				*deltas = 0;
+			else if (*deltas > 255)
+				*deltas = 255;
+			deltas++;
+		}
+		ref += stride - 8;
+	}
+}
+
+static u32 encode_plane(u8 *input, u8 *refp, __be16 **rlco, __be16 *rlco_max,
+			struct cframe *cf, u32 height, u32 width,
+			unsigned int input_step,
+			bool is_intra, bool next_is_intra)
+{
+	u8 *input_start = input;
+	__be16 *rlco_start = *rlco;
+	s16 deltablock[64];
+	__be16 pframe_bit = htons(PFRAME_BIT);
+	u32 encoding = 0;
+	unsigned int last_size = 0;
+	unsigned int i, j;
+
+	for (j = 0; j < height / 8; j++) {
+		for (i = 0; i < width / 8; i++) {
+			/* intra code, first frame is always intra coded. */
+			int blocktype = IBLOCK;
+			unsigned int size;
+
+			if (!is_intra)
+				blocktype = decide_blocktype(input, refp,
+					deltablock, width, input_step);
+			if (is_intra || blocktype == IBLOCK) {
+				fwht(input, cf->coeffs, width, input_step, 1);
+				quantize_intra(cf->coeffs, cf->de_coeffs);
+				blocktype = IBLOCK;
+			} else {
+				/* inter code */
+				encoding |= FRAME_PCODED;
+				fwht16(deltablock, cf->coeffs, 8, 0);
+				quantize_inter(cf->coeffs, cf->de_coeffs);
+			}
+			if (!next_is_intra) {
+				ifwht(cf->de_coeffs, cf->de_fwht, blocktype);
+
+				if (blocktype == PBLOCK)
+					add_deltas(cf->de_fwht, refp, 8);
+				fill_decoder_block(refp, cf->de_fwht, 8);
+			}
+
+			input += 8 * input_step;
+			refp += 8 * 8;
+
+			if (encoding & FRAME_UNENCODED)
+				continue;
+
+			size = rlc(cf->coeffs, *rlco, blocktype);
+			if (last_size == size &&
+			    !memcmp(*rlco + 1, *rlco - size + 1, 2 * size - 2)) {
+				__be16 *last_rlco = *rlco - size;
+				s16 hdr = ntohs(*last_rlco);
+
+				if (!((*last_rlco ^ **rlco) & pframe_bit) &&
+				    (hdr & DUPS_MASK) < DUPS_MASK)
+					*last_rlco = htons(hdr + 2);
+				else
+					*rlco += size;
+			} else {
+				*rlco += size;
+			}
+			if (*rlco >= rlco_max)
+				encoding |= FRAME_UNENCODED;
+			last_size = size;
+		}
+		input += width * 7 * input_step;
+	}
+	if (encoding & FRAME_UNENCODED) {
+		u8 *out = (u8 *)rlco_start;
+
+		input = input_start;
+		/*
+		 * The compressed stream should never contain the magic
+		 * header, so when we copy the YUV data we replace 0xff
+		 * by 0xfe. Since YUV is limited range such values
+		 * shouldn't appear anyway.
+		 */
+		for (i = 0; i < height * width; i++, input += input_step)
+			*out++ = (*input == 0xff) ? 0xfe : *input;
+		*rlco = (__be16 *)out;
+	}
+	return encoding;
+}
+
+u32 encode_frame(struct raw_frame *frm, struct raw_frame *ref_frm,
+		 struct cframe *cf, bool is_intra, bool next_is_intra)
+{
+	unsigned int size = frm->height * frm->width;
+	__be16 *rlco = cf->rlc_data;
+	__be16 *rlco_max;
+	u32 encoding;
+
+	rlco_max = rlco + size / 2 - 256;
+	encoding = encode_plane(frm->luma, ref_frm->luma, &rlco, rlco_max, cf,
+				  frm->height, frm->width,
+				  1, is_intra, next_is_intra);
+	if (encoding & FRAME_UNENCODED)
+		encoding |= LUMA_UNENCODED;
+	encoding &= ~FRAME_UNENCODED;
+	rlco_max = rlco + size / 8 - 256;
+	encoding |= encode_plane(frm->cb, ref_frm->cb, &rlco, rlco_max, cf,
+				   frm->height / 2, frm->width / 2,
+				   frm->chroma_step, is_intra, next_is_intra);
+	if (encoding & FRAME_UNENCODED)
+		encoding |= CB_UNENCODED;
+	encoding &= ~FRAME_UNENCODED;
+	rlco_max = rlco + size / 8 - 256;
+	encoding |= encode_plane(frm->cr, ref_frm->cr, &rlco, rlco_max, cf,
+				   frm->height / 2, frm->width / 2,
+				   frm->chroma_step, is_intra, next_is_intra);
+	if (encoding & FRAME_UNENCODED)
+		encoding |= CR_UNENCODED;
+	encoding &= ~FRAME_UNENCODED;
+	cf->size = (rlco - cf->rlc_data) * sizeof(*rlco);
+	return encoding;
+}
+
+static void decode_plane(struct cframe *cf, const __be16 **rlco, u8 *ref,
+			 u32 height, u32 width, bool uncompressed)
+{
+	unsigned int copies = 0;
+	s16 copy[8 * 8];
+	s16 stat;
+	unsigned int i, j;
+
+	if (uncompressed) {
+		memcpy(ref, *rlco, width * height);
+		*rlco += width * height / 2;
+		return;
+	}
+
+	/*
+	 * When decoding each macroblock the rlco pointer will be increased
+	 * by 65 * 2 bytes worst-case.
+	 * To avoid overflow the buffer has to be 65/64th of the actual raw
+	 * image size, just in case someone feeds it malicious data.
+	 */
+	for (j = 0; j < height / 8; j++) {
+		for (i = 0; i < width / 8; i++) {
+			u8 *refp = ref + j * 8 * width + i * 8;
+
+			if (copies) {
+				memcpy(cf->de_fwht, copy, sizeof(copy));
+				if (stat & PFRAME_BIT)
+					add_deltas(cf->de_fwht, refp, width);
+				fill_decoder_block(refp, cf->de_fwht, width);
+				copies--;
+				continue;
+			}
+
+			stat = derlc(rlco, cf->coeffs);
+
+			if (stat & PFRAME_BIT)
+				dequantize_inter(cf->coeffs);
+			else
+				dequantize_intra(cf->coeffs);
+
+			ifwht(cf->coeffs, cf->de_fwht,
+			      (stat & PFRAME_BIT) ? 0 : 1);
+
+			copies = (stat & DUPS_MASK) >> 1;
+			if (copies)
+				memcpy(copy, cf->de_fwht, sizeof(copy));
+			if (stat & PFRAME_BIT)
+				add_deltas(cf->de_fwht, refp, width);
+			fill_decoder_block(refp, cf->de_fwht, width);
+		}
+	}
+}
+
+void decode_frame(struct cframe *cf, struct raw_frame *ref, u32 hdr_flags)
+{
+	const __be16 *rlco = cf->rlc_data;
+
+	decode_plane(cf, &rlco, ref->luma, cf->height, cf->width,
+		     hdr_flags & VICODEC_FL_LUMA_IS_UNCOMPRESSED);
+	decode_plane(cf, &rlco, ref->cb, cf->height / 2, cf->width / 2,
+		     hdr_flags & VICODEC_FL_CB_IS_UNCOMPRESSED);
+	decode_plane(cf, &rlco, ref->cr, cf->height / 2, cf->width / 2,
+		     hdr_flags & VICODEC_FL_CR_IS_UNCOMPRESSED);
+}
diff --git a/drivers/media/platform/vicodec/vicodec-codec.h b/drivers/media/platform/vicodec/vicodec-codec.h
new file mode 100644
index 000000000000..cdfad1332a3e
--- /dev/null
+++ b/drivers/media/platform/vicodec/vicodec-codec.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2016 Tom aan de Wiel
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ */
+
+#ifndef VICODEC_RLC_H
+#define VICODEC_RLC_H
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <asm/byteorder.h>
+
+/*
+ * The compressed format consists of a cframe_hdr struct followed by the
+ * compressed frame data. The header contains the size of that data.
+ * Each Y, Cb and Cr plane is compressed separately. If the compressed
+ * size of each plane becomes larger than the uncompressed size, then
+ * that plane is stored uncompressed and the corresponding bit is set
+ * in the flags field of the header.
+ *
+ * Each compressed plane consists of macroblocks and each macroblock
+ * is run-length-encoded. Each macroblock starts with a 16 bit value.
+ * Bit 15 indicates if this is a P-coded macroblock (1) or not (0).
+ * P-coded macroblocks contain a delta against the previous frame.
+ *
+ * Bits 1-12 contain a number. If non-zero, then this same macroblock
+ * repeats that number of times. This results in a high degree of
+ * compression for generated images like colorbars.
+ *
+ * Following this macroblock header the MB coefficients are run-length
+ * encoded: the top 12 bits contain the coefficient, the bottom 4 bits
+ * tell how many times this coefficient occurs. The value 0xf indicates
+ * that the remainder of the macroblock should be filled with zeroes.
+ *
+ * All 16 and 32 bit values are stored in big-endian (network) order.
+ *
+ * Each cframe_hdr starts with an 8 byte magic header that is
+ * guaranteed not to occur in the compressed frame data. This header
+ * can be used to sync to the next frame.
+ *
+ * This codec uses the Fast Walsh Hadamard Transform. Tom aan de Wiel
+ * developed this as part of a university project, specifically for use
+ * with this driver. His project report can be found here:
+ *
+ * https://hverkuil.home.xs4all.nl/fwht.pdf
+ */
+
+/*
+ * Note: bit 0 of the header must always be 0. Otherwise it cannot
+ * be guaranteed that the magic 8 byte sequence (see below) can
+ * never occur in the rlc output.
+ */
+#define PFRAME_BIT (1 << 15)
+#define DUPS_MASK 0x1ffe
+
+/*
+ * This is a sequence of 8 bytes with the low 4 bits set to 0xf.
+ *
+ * This sequence cannot occur in the encoded data
+ */
+#define VICODEC_MAGIC1 0x4f4f4f4f
+#define VICODEC_MAGIC2 0xffffffff
+
+#define VICODEC_VERSION 1
+
+#define VICODEC_MAX_WIDTH 3840
+#define VICODEC_MAX_HEIGHT 2160
+#define VICODEC_MIN_WIDTH 640
+#define VICODEC_MIN_HEIGHT 480
+
+#define PBLOCK 0
+#define IBLOCK 1
+
+/* Set if this is an interlaced format */
+#define VICODEC_FL_IS_INTERLACED	BIT(0)
+/* Set if this is a bottom-first (NTSC) interlaced format */
+#define VICODEC_FL_IS_BOTTOM_FIRST	BIT(1)
+/* Set if each 'frame' contains just one field */
+#define VICODEC_FL_IS_ALTERNATE		BIT(2)
+/*
+ * If VICODEC_FL_IS_ALTERNATE was set, then this is set if this
+ * 'frame' is the bottom field, else it is the top field.
+ */
+#define VICODEC_FL_IS_BOTTOM_FIELD	BIT(3)
+/* Set if this frame is uncompressed */
+#define VICODEC_FL_LUMA_IS_UNCOMPRESSED	BIT(4)
+#define VICODEC_FL_CB_IS_UNCOMPRESSED	BIT(5)
+#define VICODEC_FL_CR_IS_UNCOMPRESSED	BIT(6)
+
+struct cframe_hdr {
+	u32 magic1;
+	u32 magic2;
+	__be32 version;
+	__be32 width, height;
+	__be32 flags;
+	__be32 colorspace;
+	__be32 xfer_func;
+	__be32 ycbcr_enc;
+	__be32 quantization;
+	__be32 size;
+};
+
+struct cframe {
+	unsigned int width, height;
+	__be16 *rlc_data;
+	s16 coeffs[8 * 8];
+	s16 de_coeffs[8 * 8];
+	s16 de_fwht[8 * 8];
+	u32 size;
+};
+
+struct raw_frame {
+	unsigned int width, height;
+	unsigned int chroma_step;
+	u8 *luma, *cb, *cr;
+};
+
+#define FRAME_PCODED	BIT(0)
+#define FRAME_UNENCODED	BIT(1)
+#define LUMA_UNENCODED	BIT(2)
+#define CB_UNENCODED	BIT(3)
+#define CR_UNENCODED	BIT(4)
+
+u32 encode_frame(struct raw_frame *frm, struct raw_frame *ref_frm,
+		 struct cframe *cf, bool is_intra, bool next_is_intra);
+void decode_frame(struct cframe *cf, struct raw_frame *ref, u32 hdr_flags);
+
+#endif
-- 
cgit v1.2.3


From 256bf813ba39f7f9277a5cd05b5c152dbbaf4aae Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hans.verkuil@cisco.com>
Date: Fri, 20 Jul 2018 03:52:50 -0400
Subject: media: vicodec: add the virtual codec driver

Add the virtual codec driver that uses the Fast Walsh Hadamard Transform.

Keiichi Watanabe contributed the multiplanar support.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Co-Developed-by: Keiichi Watanabe <keiichiw@chromium.org>
Signed-off-by: Keiichi Watanabe <keiichiw@chromium.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 MAINTAINERS                                   |    8 +
 drivers/media/platform/Kconfig                |    3 +
 drivers/media/platform/Makefile               |    1 +
 drivers/media/platform/vicodec/Kconfig        |   13 +
 drivers/media/platform/vicodec/Makefile       |    4 +
 drivers/media/platform/vicodec/vicodec-core.c | 1506 +++++++++++++++++++++++++
 6 files changed, 1535 insertions(+)
 create mode 100644 drivers/media/platform/vicodec/Kconfig
 create mode 100644 drivers/media/platform/vicodec/Makefile
 create mode 100644 drivers/media/platform/vicodec/vicodec-core.c

diff --git a/MAINTAINERS b/MAINTAINERS
index bbd9b9b3d74f..67781db8b077 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15153,6 +15153,14 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	drivers/net/ethernet/via/via-velocity.*
 
+VICODEC VIRTUAL CODEC DRIVER
+M:	Hans Verkuil <hans.verkuil@cisco.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+W:	https://linuxtv.org
+S:	Maintained
+F:	drivers/media/platform/vicodec/*
+
 VIDEO MULTIPLEXER DRIVER
 M:	Philipp Zabel <p.zabel@pengutronix.de>
 L:	linux-media@vger.kernel.org
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 84cb97eccb2a..40bd3d96ca82 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -514,6 +514,9 @@ config VIDEO_VIM2M
 	---help---
 	  This is a virtual test device for the memory-to-memory driver
 	  framework.
+
+source "drivers/media/platform/vicodec/Kconfig"
+
 endif #V4L_TEST_DRIVERS
 
 menuconfig DVB_PLATFORM_DRIVERS
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index 04bc1502a30e..8e5f88eb7559 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -16,6 +16,7 @@ obj-$(CONFIG_VIDEO_VIU) += fsl-viu.o
 obj-$(CONFIG_VIDEO_VIMC)		+= vimc/
 obj-$(CONFIG_VIDEO_VIVID)		+= vivid/
 obj-$(CONFIG_VIDEO_VIM2M)		+= vim2m.o
+obj-$(CONFIG_VIDEO_VICODEC)		+= vicodec/
 
 obj-$(CONFIG_VIDEO_TI_VPE)		+= ti-vpe/
 
diff --git a/drivers/media/platform/vicodec/Kconfig b/drivers/media/platform/vicodec/Kconfig
new file mode 100644
index 000000000000..2503bcb1529f
--- /dev/null
+++ b/drivers/media/platform/vicodec/Kconfig
@@ -0,0 +1,13 @@
+config VIDEO_VICODEC
+	tristate "Virtual Codec Driver"
+	depends on VIDEO_DEV && VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
+	select VIDEOBUF2_VMALLOC
+	select V4L2_MEM2MEM_DEV
+	default n
+	help
+	  Driver for a Virtual Codec
+
+	  This driver can be compared to the vim2m driver for emulating
+	  a video device node that exposes an emulated hardware codec.
+
+	  When in doubt, say N.
diff --git a/drivers/media/platform/vicodec/Makefile b/drivers/media/platform/vicodec/Makefile
new file mode 100644
index 000000000000..197229428953
--- /dev/null
+++ b/drivers/media/platform/vicodec/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+vicodec-objs := vicodec-core.o vicodec-codec.o
+
+obj-$(CONFIG_VIDEO_VICODEC) += vicodec.o
diff --git a/drivers/media/platform/vicodec/vicodec-core.c b/drivers/media/platform/vicodec/vicodec-core.c
new file mode 100644
index 000000000000..408cd55d3580
--- /dev/null
+++ b/drivers/media/platform/vicodec/vicodec-core.c
@@ -0,0 +1,1506 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * A virtual codec example device.
+ *
+ * Copyright 2018 Cisco Systems, Inc. and/or its affiliates. All rights reserved.
+ *
+ * This is a virtual codec device driver for testing the codec framework.
+ * It simulates a device that uses memory buffers for both source and
+ * destination and encodes or decodes the data.
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+
+#include <linux/platform_device.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-event.h>
+#include <media/videobuf2-vmalloc.h>
+
+#include "vicodec-codec.h"
+
+MODULE_DESCRIPTION("Virtual codec device");
+MODULE_AUTHOR("Hans Verkuil <hans.verkuil@cisco.com>");
+MODULE_LICENSE("GPL v2");
+
+static bool multiplanar;
+module_param(multiplanar, bool, 0444);
+MODULE_PARM_DESC(multiplanar,
+		 " use multi-planar API instead of single-planar API");
+
+static unsigned int debug;
+module_param(debug, uint, 0644);
+MODULE_PARM_DESC(debug, " activates debug info");
+
+#define VICODEC_NAME		"vicodec"
+#define MAX_WIDTH		4096U
+#define MIN_WIDTH		640U
+#define MAX_HEIGHT		2160U
+#define MIN_HEIGHT		480U
+
+#define dprintk(dev, fmt, arg...) \
+	v4l2_dbg(1, debug, &dev->v4l2_dev, "%s: " fmt, __func__, ## arg)
+
+
+static void vicodec_dev_release(struct device *dev)
+{
+}
+
+static struct platform_device vicodec_pdev = {
+	.name		= VICODEC_NAME,
+	.dev.release	= vicodec_dev_release,
+};
+
+/* Per-queue, driver-specific private data */
+struct vicodec_q_data {
+	unsigned int		width;
+	unsigned int		height;
+	unsigned int		flags;
+	unsigned int		sizeimage;
+	unsigned int		sequence;
+	u32			fourcc;
+};
+
+enum {
+	V4L2_M2M_SRC = 0,
+	V4L2_M2M_DST = 1,
+};
+
+struct vicodec_dev {
+	struct v4l2_device	v4l2_dev;
+	struct video_device	enc_vfd;
+	struct video_device	dec_vfd;
+#ifdef CONFIG_MEDIA_CONTROLLER
+	struct media_device	mdev;
+#endif
+
+	struct mutex		enc_mutex;
+	struct mutex		dec_mutex;
+	spinlock_t		enc_lock;
+	spinlock_t		dec_lock;
+
+	struct v4l2_m2m_dev	*enc_dev;
+	struct v4l2_m2m_dev	*dec_dev;
+};
+
+struct vicodec_ctx {
+	struct v4l2_fh		fh;
+	struct vicodec_dev	*dev;
+	bool			is_enc;
+	spinlock_t		*lock;
+
+	struct v4l2_ctrl_handler hdl;
+	struct v4l2_ctrl	*ctrl_gop_size;
+	unsigned int		gop_size;
+	unsigned int		gop_cnt;
+
+	/* Abort requested by m2m */
+	int			aborting;
+	struct vb2_v4l2_buffer *last_src_buf;
+	struct vb2_v4l2_buffer *last_dst_buf;
+
+	enum v4l2_colorspace	colorspace;
+	enum v4l2_ycbcr_encoding ycbcr_enc;
+	enum v4l2_xfer_func	xfer_func;
+	enum v4l2_quantization	quantization;
+
+	/* Source and destination queue data */
+	struct vicodec_q_data   q_data[2];
+	struct raw_frame	ref_frame;
+	u8			*compressed_frame;
+	u32			cur_buf_offset;
+	u32			comp_max_size;
+	u32			comp_size;
+	u32			comp_magic_cnt;
+	u32			comp_frame_size;
+	bool			comp_has_frame;
+	bool			comp_has_next_frame;
+};
+
+static const u32 pixfmts_yuv[] = {
+	V4L2_PIX_FMT_YUV420,
+	V4L2_PIX_FMT_YVU420,
+	V4L2_PIX_FMT_NV12,
+	V4L2_PIX_FMT_NV21,
+};
+
+static inline struct vicodec_ctx *file2ctx(struct file *file)
+{
+	return container_of(file->private_data, struct vicodec_ctx, fh);
+}
+
+static struct vicodec_q_data *get_q_data(struct vicodec_ctx *ctx,
+					 enum v4l2_buf_type type)
+{
+	switch (type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		return &ctx->q_data[V4L2_M2M_SRC];
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		return &ctx->q_data[V4L2_M2M_DST];
+	default:
+		WARN_ON(1);
+		break;
+	}
+	return NULL;
+}
+
+static void encode(struct vicodec_ctx *ctx,
+		   struct vicodec_q_data *q_data,
+		   u8 *p_in, u8 *p_out)
+{
+	unsigned int size = q_data->width * q_data->height;
+	struct cframe_hdr *p_hdr;
+	struct cframe cf;
+	struct raw_frame rf;
+	u32 encoding;
+
+	rf.width = q_data->width;
+	rf.height = q_data->height;
+	rf.luma = p_in;
+
+	switch (q_data->fourcc) {
+	case V4L2_PIX_FMT_YUV420:
+		rf.cb = rf.luma + size;
+		rf.cr = rf.cb + size / 4;
+		rf.chroma_step = 1;
+		break;
+	case V4L2_PIX_FMT_YVU420:
+		rf.cr = rf.luma + size;
+		rf.cb = rf.cr + size / 4;
+		rf.chroma_step = 1;
+		break;
+	case V4L2_PIX_FMT_NV12:
+		rf.cb = rf.luma + size;
+		rf.cr = rf.cb + 1;
+		rf.chroma_step = 2;
+		break;
+	case V4L2_PIX_FMT_NV21:
+		rf.cr = rf.luma + size;
+		rf.cb = rf.cr + 1;
+		rf.chroma_step = 2;
+		break;
+	}
+
+	cf.width = q_data->width;
+	cf.height = q_data->height;
+	cf.rlc_data = (__be16 *)(p_out + sizeof(*p_hdr));
+
+	encoding = encode_frame(&rf, &ctx->ref_frame, &cf, !ctx->gop_cnt,
+				ctx->gop_cnt == ctx->gop_size - 1);
+	if (encoding != FRAME_PCODED)
+		ctx->gop_cnt = 0;
+	if (++ctx->gop_cnt == ctx->gop_size)
+		ctx->gop_cnt = 0;
+
+	p_hdr = (struct cframe_hdr *)p_out;
+	p_hdr->magic1 = VICODEC_MAGIC1;
+	p_hdr->magic2 = VICODEC_MAGIC2;
+	p_hdr->version = htonl(VICODEC_VERSION);
+	p_hdr->width = htonl(cf.width);
+	p_hdr->height = htonl(cf.height);
+	p_hdr->flags = htonl(q_data->flags);
+	if (encoding & LUMA_UNENCODED)
+		p_hdr->flags |= htonl(VICODEC_FL_LUMA_IS_UNCOMPRESSED);
+	if (encoding & CB_UNENCODED)
+		p_hdr->flags |= htonl(VICODEC_FL_CB_IS_UNCOMPRESSED);
+	if (encoding & CR_UNENCODED)
+		p_hdr->flags |= htonl(VICODEC_FL_CR_IS_UNCOMPRESSED);
+	p_hdr->colorspace = htonl(ctx->colorspace);
+	p_hdr->xfer_func = htonl(ctx->xfer_func);
+	p_hdr->ycbcr_enc = htonl(ctx->ycbcr_enc);
+	p_hdr->quantization = htonl(ctx->quantization);
+	p_hdr->size = htonl(cf.size);
+	ctx->ref_frame.width = cf.width;
+	ctx->ref_frame.height = cf.height;
+}
+
+static int decode(struct vicodec_ctx *ctx,
+		  struct vicodec_q_data *q_data,
+		  u8 *p_in, u8 *p_out)
+{
+	unsigned int size = q_data->width * q_data->height;
+	unsigned int i;
+	struct cframe_hdr *p_hdr;
+	struct cframe cf;
+	u8 *p;
+
+	p_hdr = (struct cframe_hdr *)p_in;
+	cf.width = ntohl(p_hdr->width);
+	cf.height = ntohl(p_hdr->height);
+	q_data->flags = ntohl(p_hdr->flags);
+	ctx->colorspace = ntohl(p_hdr->colorspace);
+	ctx->xfer_func = ntohl(p_hdr->xfer_func);
+	ctx->ycbcr_enc = ntohl(p_hdr->ycbcr_enc);
+	ctx->quantization = ntohl(p_hdr->quantization);
+	cf.rlc_data = (__be16 *)(p_in + sizeof(*p_hdr));
+
+	if (p_hdr->magic1 != VICODEC_MAGIC1 ||
+	    p_hdr->magic2 != VICODEC_MAGIC2 ||
+	    ntohl(p_hdr->version) != VICODEC_VERSION ||
+	    cf.width < VICODEC_MIN_WIDTH ||
+	    cf.width > VICODEC_MAX_WIDTH ||
+	    cf.height < VICODEC_MIN_HEIGHT ||
+	    cf.height > VICODEC_MAX_HEIGHT ||
+	    (cf.width & 7) || (cf.height & 7))
+		return -EINVAL;
+
+	/* TODO: support resolution changes */
+	if (cf.width != q_data->width || cf.height != q_data->height)
+		return -EINVAL;
+
+	decode_frame(&cf, &ctx->ref_frame, q_data->flags);
+	memcpy(p_out, ctx->ref_frame.luma, size);
+	p_out += size;
+
+	switch (q_data->fourcc) {
+	case V4L2_PIX_FMT_YUV420:
+		memcpy(p_out, ctx->ref_frame.cb, size / 4);
+		p_out += size / 4;
+		memcpy(p_out, ctx->ref_frame.cr, size / 4);
+		break;
+	case V4L2_PIX_FMT_YVU420:
+		memcpy(p_out, ctx->ref_frame.cr, size / 4);
+		p_out += size / 4;
+		memcpy(p_out, ctx->ref_frame.cb, size / 4);
+		break;
+	case V4L2_PIX_FMT_NV12:
+		for (i = 0, p = p_out; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cb[i];
+		for (i = 0, p = p_out + 1; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cr[i];
+		break;
+	case V4L2_PIX_FMT_NV21:
+		for (i = 0, p = p_out; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cr[i];
+		for (i = 0, p = p_out + 1; i < size / 4; i++, p += 2)
+			*p = ctx->ref_frame.cb[i];
+		break;
+	}
+	return 0;
+}
+
+static int device_process(struct vicodec_ctx *ctx,
+			  struct vb2_v4l2_buffer *in_vb,
+			  struct vb2_v4l2_buffer *out_vb)
+{
+	struct vicodec_dev *dev = ctx->dev;
+	struct vicodec_q_data *q_out, *q_cap;
+	u8 *p_in, *p_out;
+	int ret;
+
+	q_out = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	q_cap = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	if (ctx->is_enc)
+		p_in = vb2_plane_vaddr(&in_vb->vb2_buf, 0);
+	else
+		p_in = ctx->compressed_frame;
+	p_out = vb2_plane_vaddr(&out_vb->vb2_buf, 0);
+	if (!p_in || !p_out) {
+		v4l2_err(&dev->v4l2_dev,
+			 "Acquiring kernel pointers to buffers failed\n");
+		return -EFAULT;
+	}
+
+	if (ctx->is_enc) {
+		struct cframe_hdr *p_hdr = (struct cframe_hdr *)p_out;
+
+		encode(ctx, q_out, p_in, p_out);
+		vb2_set_plane_payload(&out_vb->vb2_buf, 0,
+				      sizeof(*p_hdr) + ntohl(p_hdr->size));
+	} else {
+		ret = decode(ctx, q_cap, p_in, p_out);
+		if (ret)
+			return ret;
+		vb2_set_plane_payload(&out_vb->vb2_buf, 0,
+				      q_cap->width * q_cap->height * 3 / 2);
+	}
+
+	out_vb->sequence = q_cap->sequence++;
+	out_vb->vb2_buf.timestamp = in_vb->vb2_buf.timestamp;
+
+	if (in_vb->flags & V4L2_BUF_FLAG_TIMECODE)
+		out_vb->timecode = in_vb->timecode;
+	out_vb->field = in_vb->field;
+	out_vb->flags &= ~V4L2_BUF_FLAG_LAST;
+	out_vb->flags |= in_vb->flags &
+		(V4L2_BUF_FLAG_TIMECODE |
+		 V4L2_BUF_FLAG_KEYFRAME |
+		 V4L2_BUF_FLAG_PFRAME |
+		 V4L2_BUF_FLAG_BFRAME |
+		 V4L2_BUF_FLAG_TSTAMP_SRC_MASK);
+
+	return 0;
+}
+
+/*
+ * mem2mem callbacks
+ */
+
+/* device_run() - prepares and starts the device */
+static void device_run(void *priv)
+{
+	static const struct v4l2_event eos_event = {
+		.type = V4L2_EVENT_EOS
+	};
+	struct vicodec_ctx *ctx = priv;
+	struct vicodec_dev *dev = ctx->dev;
+	struct vb2_v4l2_buffer *src_buf, *dst_buf;
+	struct vicodec_q_data *q_out;
+	u32 state;
+
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	dst_buf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+	q_out = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+
+	state = VB2_BUF_STATE_DONE;
+	if (device_process(ctx, src_buf, dst_buf))
+		state = VB2_BUF_STATE_ERROR;
+	ctx->last_dst_buf = dst_buf;
+
+	spin_lock(ctx->lock);
+	if (!ctx->comp_has_next_frame && src_buf == ctx->last_src_buf) {
+		dst_buf->flags |= V4L2_BUF_FLAG_LAST;
+		v4l2_event_queue_fh(&ctx->fh, &eos_event);
+	}
+	if (ctx->is_enc) {
+		src_buf->sequence = q_out->sequence++;
+		src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		v4l2_m2m_buf_done(src_buf, state);
+	} else if (vb2_get_plane_payload(&src_buf->vb2_buf, 0) == ctx->cur_buf_offset) {
+		src_buf->sequence = q_out->sequence++;
+		src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		v4l2_m2m_buf_done(src_buf, state);
+		ctx->cur_buf_offset = 0;
+		ctx->comp_has_next_frame = false;
+	}
+	v4l2_m2m_buf_done(dst_buf, state);
+	ctx->comp_size = 0;
+	ctx->comp_magic_cnt = 0;
+	ctx->comp_has_frame = false;
+	spin_unlock(ctx->lock);
+
+	if (ctx->is_enc)
+		v4l2_m2m_job_finish(dev->enc_dev, ctx->fh.m2m_ctx);
+	else
+		v4l2_m2m_job_finish(dev->dec_dev, ctx->fh.m2m_ctx);
+}
+
+static void job_remove_out_buf(struct vicodec_ctx *ctx, u32 state)
+{
+	struct vb2_v4l2_buffer *src_buf;
+	struct vicodec_q_data *q_out;
+
+	q_out = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	spin_lock(ctx->lock);
+	src_buf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+	src_buf->sequence = q_out->sequence++;
+	v4l2_m2m_buf_done(src_buf, state);
+	ctx->cur_buf_offset = 0;
+	spin_unlock(ctx->lock);
+}
+
+static int job_ready(void *priv)
+{
+	static const u8 magic[] = {
+		0x4f, 0x4f, 0x4f, 0x4f, 0xff, 0xff, 0xff, 0xff
+	};
+	struct vicodec_ctx *ctx = priv;
+	struct vb2_v4l2_buffer *src_buf;
+	u8 *p_out;
+	u8 *p;
+	u32 sz;
+	u32 state;
+
+	if (ctx->is_enc || ctx->comp_has_frame)
+		return 1;
+
+restart:
+	ctx->comp_has_next_frame = false;
+	src_buf = v4l2_m2m_next_src_buf(ctx->fh.m2m_ctx);
+	if (!src_buf)
+		return 0;
+	p_out = vb2_plane_vaddr(&src_buf->vb2_buf, 0);
+	sz = vb2_get_plane_payload(&src_buf->vb2_buf, 0);
+	p = p_out + ctx->cur_buf_offset;
+
+	state = VB2_BUF_STATE_DONE;
+
+	if (!ctx->comp_size) {
+		state = VB2_BUF_STATE_ERROR;
+		for (; p < p_out + sz; p++) {
+			u32 copy;
+
+			p = memchr(p, magic[ctx->comp_magic_cnt], sz);
+			if (!p) {
+				ctx->comp_magic_cnt = 0;
+				break;
+			}
+			copy = sizeof(magic) - ctx->comp_magic_cnt;
+			if (p_out + sz - p < copy)
+				copy = p_out + sz - p;
+			memcpy(ctx->compressed_frame + ctx->comp_magic_cnt,
+			       p, copy);
+			ctx->comp_magic_cnt += copy;
+			if (!memcmp(ctx->compressed_frame, magic, ctx->comp_magic_cnt)) {
+				p += copy;
+				state = VB2_BUF_STATE_DONE;
+				break;
+			}
+			ctx->comp_magic_cnt = 0;
+		}
+		if (ctx->comp_magic_cnt < sizeof(magic)) {
+			job_remove_out_buf(ctx, state);
+			goto restart;
+		}
+		ctx->comp_size = sizeof(magic);
+	}
+	if (ctx->comp_size < sizeof(struct cframe_hdr)) {
+		struct cframe_hdr *p_hdr = (struct cframe_hdr *)ctx->compressed_frame;
+		u32 copy = sizeof(struct cframe_hdr) - ctx->comp_size;
+
+		if (copy > p_out + sz - p)
+			copy = p_out + sz - p;
+		memcpy(ctx->compressed_frame + ctx->comp_size,
+		       p, copy);
+		p += copy;
+		ctx->comp_size += copy;
+		if (ctx->comp_size < sizeof(struct cframe_hdr)) {
+			job_remove_out_buf(ctx, state);
+			goto restart;
+		}
+		ctx->comp_frame_size = ntohl(p_hdr->size) + sizeof(*p_hdr);
+		if (ctx->comp_frame_size > ctx->comp_max_size)
+			ctx->comp_frame_size = ctx->comp_max_size;
+	}
+	if (ctx->comp_size < ctx->comp_frame_size) {
+		u32 copy = ctx->comp_frame_size - ctx->comp_size;
+
+		if (copy > p_out + sz - p)
+			copy = p_out + sz - p;
+		memcpy(ctx->compressed_frame + ctx->comp_size,
+		       p, copy);
+		p += copy;
+		ctx->comp_size += copy;
+		if (ctx->comp_size < ctx->comp_frame_size) {
+			job_remove_out_buf(ctx, state);
+			goto restart;
+		}
+	}
+	ctx->cur_buf_offset = p - p_out;
+	ctx->comp_has_frame = true;
+	ctx->comp_has_next_frame = false;
+	if (sz - ctx->cur_buf_offset >= sizeof(struct cframe_hdr)) {
+		struct cframe_hdr *p_hdr = (struct cframe_hdr *)p;
+		u32 frame_size = ntohl(p_hdr->size);
+		u32 remaining = sz - ctx->cur_buf_offset - sizeof(*p_hdr);
+
+		if (!memcmp(p, magic, sizeof(magic)))
+			ctx->comp_has_next_frame = remaining >= frame_size;
+	}
+	return 1;
+}
+
+static void job_abort(void *priv)
+{
+	struct vicodec_ctx *ctx = priv;
+
+	/* Will cancel the transaction in the next interrupt handler */
+	ctx->aborting = 1;
+}
+
+/*
+ * video ioctls
+ */
+
+static u32 find_fmt(u32 fmt)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(pixfmts_yuv); i++)
+		if (pixfmts_yuv[i] == fmt)
+			return fmt;
+	return pixfmts_yuv[0];
+}
+
+static int vidioc_querycap(struct file *file, void *priv,
+			   struct v4l2_capability *cap)
+{
+	strncpy(cap->driver, VICODEC_NAME, sizeof(cap->driver) - 1);
+	strncpy(cap->card, VICODEC_NAME, sizeof(cap->card) - 1);
+	snprintf(cap->bus_info, sizeof(cap->bus_info),
+			"platform:%s", VICODEC_NAME);
+	cap->device_caps =  V4L2_CAP_STREAMING |
+			    (multiplanar ?
+			     V4L2_CAP_VIDEO_M2M_MPLANE :
+			     V4L2_CAP_VIDEO_M2M);
+	cap->capabilities = cap->device_caps | V4L2_CAP_DEVICE_CAPS;
+	return 0;
+}
+
+static int enum_fmt(struct v4l2_fmtdesc *f, bool is_enc, bool is_out)
+{
+	bool is_yuv = (is_enc && is_out) || (!is_enc && !is_out);
+
+	if (V4L2_TYPE_IS_MULTIPLANAR(f->type) && !multiplanar)
+		return -EINVAL;
+	if (!V4L2_TYPE_IS_MULTIPLANAR(f->type) && multiplanar)
+		return -EINVAL;
+	if (f->index >= (is_yuv ? ARRAY_SIZE(pixfmts_yuv) : 1))
+		return -EINVAL;
+
+	if (is_yuv)
+		f->pixelformat = pixfmts_yuv[f->index];
+	else
+		f->pixelformat = V4L2_PIX_FMT_FWHT;
+	return 0;
+}
+
+static int vidioc_enum_fmt_vid_cap(struct file *file, void *priv,
+				   struct v4l2_fmtdesc *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+
+	return enum_fmt(f, ctx->is_enc, false);
+}
+
+static int vidioc_enum_fmt_vid_out(struct file *file, void *priv,
+				   struct v4l2_fmtdesc *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+
+	return enum_fmt(f, ctx->is_enc, true);
+}
+
+static int vidioc_g_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f)
+{
+	struct vb2_queue *vq;
+	struct vicodec_q_data *q_data;
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, f->type);
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		if (multiplanar)
+			return -EINVAL;
+		pix = &f->fmt.pix;
+		pix->width = q_data->width;
+		pix->height = q_data->height;
+		pix->field = V4L2_FIELD_NONE;
+		pix->pixelformat = q_data->fourcc;
+		if (q_data->fourcc == V4L2_PIX_FMT_FWHT)
+			pix->bytesperline = 0;
+		else
+			pix->bytesperline = q_data->width;
+		pix->sizeimage = q_data->sizeimage;
+		pix->colorspace = ctx->colorspace;
+		pix->xfer_func = ctx->xfer_func;
+		pix->ycbcr_enc = ctx->ycbcr_enc;
+		pix->quantization = ctx->quantization;
+		break;
+
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		if (!multiplanar)
+			return -EINVAL;
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->width = q_data->width;
+		pix_mp->height = q_data->height;
+		pix_mp->field = V4L2_FIELD_NONE;
+		pix_mp->pixelformat = q_data->fourcc;
+		pix_mp->num_planes = 1;
+		if (q_data->fourcc == V4L2_PIX_FMT_FWHT)
+			pix_mp->plane_fmt[0].bytesperline = 0;
+		else
+			pix_mp->plane_fmt[0].bytesperline = q_data->width;
+		pix_mp->plane_fmt[0].sizeimage = q_data->sizeimage;
+		pix_mp->colorspace = ctx->colorspace;
+		pix_mp->xfer_func = ctx->xfer_func;
+		pix_mp->ycbcr_enc = ctx->ycbcr_enc;
+		pix_mp->quantization = ctx->quantization;
+		memset(pix_mp->reserved, 0, sizeof(pix_mp->reserved));
+		memset(pix_mp->plane_fmt[0].reserved, 0,
+		       sizeof(pix_mp->plane_fmt[0].reserved));
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int vidioc_g_fmt_vid_out(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	return vidioc_g_fmt(file2ctx(file), f);
+}
+
+static int vidioc_g_fmt_vid_cap(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	return vidioc_g_fmt(file2ctx(file), f);
+}
+
+static int vidioc_try_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		pix = &f->fmt.pix;
+		pix->width = clamp(pix->width, MIN_WIDTH, MAX_WIDTH) & ~7;
+		pix->height = clamp(pix->height, MIN_HEIGHT, MAX_HEIGHT) & ~7;
+		pix->bytesperline = pix->width;
+		pix->sizeimage = pix->width * pix->height * 3 / 2;
+		pix->field = V4L2_FIELD_NONE;
+		if (pix->pixelformat == V4L2_PIX_FMT_FWHT) {
+			pix->bytesperline = 0;
+			pix->sizeimage += sizeof(struct cframe_hdr);
+		}
+		break;
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->width = clamp(pix_mp->width, MIN_WIDTH, MAX_WIDTH) & ~7;
+		pix_mp->height =
+			clamp(pix_mp->height, MIN_HEIGHT, MAX_HEIGHT) & ~7;
+		pix_mp->plane_fmt[0].bytesperline = pix_mp->width;
+		pix_mp->plane_fmt[0].sizeimage =
+			pix_mp->width * pix_mp->height * 3 / 2;
+		pix_mp->field = V4L2_FIELD_NONE;
+		pix_mp->num_planes = 1;
+		if (pix_mp->pixelformat == V4L2_PIX_FMT_FWHT) {
+			pix_mp->plane_fmt[0].bytesperline = 0;
+			pix_mp->plane_fmt[0].sizeimage +=
+					sizeof(struct cframe_hdr);
+		}
+		memset(pix_mp->reserved, 0, sizeof(pix_mp->reserved));
+		memset(pix_mp->plane_fmt[0].reserved, 0,
+		       sizeof(pix_mp->plane_fmt[0].reserved));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int vidioc_try_fmt_vid_cap(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+		if (multiplanar)
+			return -EINVAL;
+		pix = &f->fmt.pix;
+		pix->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				   find_fmt(f->fmt.pix.pixelformat);
+		pix->colorspace = ctx->colorspace;
+		pix->xfer_func = ctx->xfer_func;
+		pix->ycbcr_enc = ctx->ycbcr_enc;
+		pix->quantization = ctx->quantization;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		if (!multiplanar)
+			return -EINVAL;
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->pixelformat = ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				      find_fmt(pix_mp->pixelformat);
+		pix_mp->colorspace = ctx->colorspace;
+		pix_mp->xfer_func = ctx->xfer_func;
+		pix_mp->ycbcr_enc = ctx->ycbcr_enc;
+		pix_mp->quantization = ctx->quantization;
+		memset(pix_mp->reserved, 0, sizeof(pix_mp->reserved));
+		memset(pix_mp->plane_fmt[0].reserved, 0,
+		       sizeof(pix_mp->plane_fmt[0].reserved));
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return vidioc_try_fmt(ctx, f);
+}
+
+static int vidioc_try_fmt_vid_out(struct file *file, void *priv,
+				  struct v4l2_format *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		if (multiplanar)
+			return -EINVAL;
+		pix = &f->fmt.pix;
+		pix->pixelformat = !ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				   find_fmt(pix->pixelformat);
+		if (!pix->colorspace)
+			pix->colorspace = V4L2_COLORSPACE_REC709;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		if (!multiplanar)
+			return -EINVAL;
+		pix_mp = &f->fmt.pix_mp;
+		pix_mp->pixelformat = !ctx->is_enc ? V4L2_PIX_FMT_FWHT :
+				      find_fmt(pix_mp->pixelformat);
+		if (!pix_mp->colorspace)
+			pix_mp->colorspace = V4L2_COLORSPACE_REC709;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return vidioc_try_fmt(ctx, f);
+}
+
+static int vidioc_s_fmt(struct vicodec_ctx *ctx, struct v4l2_format *f)
+{
+	struct vicodec_q_data *q_data;
+	struct vb2_queue *vq;
+	bool fmt_changed = true;
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+
+	vq = v4l2_m2m_get_vq(ctx->fh.m2m_ctx, f->type);
+	if (!vq)
+		return -EINVAL;
+
+	q_data = get_q_data(ctx, f->type);
+	if (!q_data)
+		return -EINVAL;
+
+	switch (f->type) {
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+		pix = &f->fmt.pix;
+		if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type))
+			fmt_changed =
+				q_data->fourcc != pix->pixelformat ||
+				q_data->width != pix->width ||
+				q_data->height != pix->height;
+
+		if (vb2_is_busy(vq) && fmt_changed)
+			return -EBUSY;
+
+		q_data->fourcc = pix->pixelformat;
+		q_data->width = pix->width;
+		q_data->height = pix->height;
+		q_data->sizeimage = pix->sizeimage;
+		break;
+	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+		pix_mp = &f->fmt.pix_mp;
+		if (ctx->is_enc && V4L2_TYPE_IS_OUTPUT(f->type))
+			fmt_changed =
+				q_data->fourcc != pix_mp->pixelformat ||
+				q_data->width != pix_mp->width ||
+				q_data->height != pix_mp->height;
+
+		if (vb2_is_busy(vq) && fmt_changed)
+			return -EBUSY;
+
+		q_data->fourcc = pix_mp->pixelformat;
+		q_data->width = pix_mp->width;
+		q_data->height = pix_mp->height;
+		q_data->sizeimage = pix_mp->plane_fmt[0].sizeimage;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	dprintk(ctx->dev,
+		"Setting format for type %d, wxh: %dx%d, fourcc: %08x\n",
+		f->type, q_data->width, q_data->height, q_data->fourcc);
+
+	return 0;
+}
+
+static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	int ret;
+
+	ret = vidioc_try_fmt_vid_cap(file, priv, f);
+	if (ret)
+		return ret;
+
+	return vidioc_s_fmt(file2ctx(file), f);
+}
+
+static int vidioc_s_fmt_vid_out(struct file *file, void *priv,
+				struct v4l2_format *f)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	struct v4l2_pix_format_mplane *pix_mp;
+	struct v4l2_pix_format *pix;
+	int ret;
+
+	ret = vidioc_try_fmt_vid_out(file, priv, f);
+	if (ret)
+		return ret;
+
+	ret = vidioc_s_fmt(file2ctx(file), f);
+	if (!ret) {
+		switch (f->type) {
+		case V4L2_BUF_TYPE_VIDEO_CAPTURE:
+		case V4L2_BUF_TYPE_VIDEO_OUTPUT:
+			pix = &f->fmt.pix;
+			ctx->colorspace = pix->colorspace;
+			ctx->xfer_func = pix->xfer_func;
+			ctx->ycbcr_enc = pix->ycbcr_enc;
+			ctx->quantization = pix->quantization;
+			break;
+		case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
+		case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
+			pix_mp = &f->fmt.pix_mp;
+			ctx->colorspace = pix_mp->colorspace;
+			ctx->xfer_func = pix_mp->xfer_func;
+			ctx->ycbcr_enc = pix_mp->ycbcr_enc;
+			ctx->quantization = pix_mp->quantization;
+			break;
+		default:
+			break;
+		}
+	}
+	return ret;
+}
+
+static void vicodec_mark_last_buf(struct vicodec_ctx *ctx)
+{
+	static const struct v4l2_event eos_event = {
+		.type = V4L2_EVENT_EOS
+	};
+
+	spin_lock(ctx->lock);
+	ctx->last_src_buf = v4l2_m2m_last_src_buf(ctx->fh.m2m_ctx);
+	if (!ctx->last_src_buf && ctx->last_dst_buf) {
+		ctx->last_dst_buf->flags |= V4L2_BUF_FLAG_LAST;
+		v4l2_event_queue_fh(&ctx->fh, &eos_event);
+	}
+	spin_unlock(ctx->lock);
+}
+
+static int vicodec_try_encoder_cmd(struct file *file, void *fh,
+				struct v4l2_encoder_cmd *ec)
+{
+	if (ec->cmd != V4L2_ENC_CMD_STOP)
+		return -EINVAL;
+
+	if (ec->flags & V4L2_ENC_CMD_STOP_AT_GOP_END)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int vicodec_encoder_cmd(struct file *file, void *fh,
+			    struct v4l2_encoder_cmd *ec)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	int ret;
+
+	ret = vicodec_try_encoder_cmd(file, fh, ec);
+	if (ret < 0)
+		return ret;
+
+	vicodec_mark_last_buf(ctx);
+	return 0;
+}
+
+static int vicodec_try_decoder_cmd(struct file *file, void *fh,
+				struct v4l2_decoder_cmd *dc)
+{
+	if (dc->cmd != V4L2_DEC_CMD_STOP)
+		return -EINVAL;
+
+	if (dc->flags & V4L2_DEC_CMD_STOP_TO_BLACK)
+		return -EINVAL;
+
+	if (!(dc->flags & V4L2_DEC_CMD_STOP_IMMEDIATELY) && (dc->stop.pts != 0))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int vicodec_decoder_cmd(struct file *file, void *fh,
+			    struct v4l2_decoder_cmd *dc)
+{
+	struct vicodec_ctx *ctx = file2ctx(file);
+	int ret;
+
+	ret = vicodec_try_decoder_cmd(file, fh, dc);
+	if (ret < 0)
+		return ret;
+
+	vicodec_mark_last_buf(ctx);
+	return 0;
+}
+
+static int vicodec_enum_framesizes(struct file *file, void *fh,
+				   struct v4l2_frmsizeenum *fsize)
+{
+	switch (fsize->pixel_format) {
+	case V4L2_PIX_FMT_FWHT:
+		break;
+	default:
+		if (find_fmt(fsize->pixel_format) == fsize->pixel_format)
+			break;
+		return -EINVAL;
+	}
+
+	if (fsize->index)
+		return -EINVAL;
+
+	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
+
+	fsize->stepwise.min_width = MIN_WIDTH;
+	fsize->stepwise.max_width = MAX_WIDTH;
+	fsize->stepwise.step_width = 8;
+	fsize->stepwise.min_height = MIN_HEIGHT;
+	fsize->stepwise.max_height = MAX_HEIGHT;
+	fsize->stepwise.step_height = 8;
+
+	return 0;
+}
+
+static int vicodec_subscribe_event(struct v4l2_fh *fh,
+				const struct v4l2_event_subscription *sub)
+{
+	switch (sub->type) {
+	case V4L2_EVENT_EOS:
+		return v4l2_event_subscribe(fh, sub, 0, NULL);
+	default:
+		return v4l2_ctrl_subscribe_event(fh, sub);
+	}
+}
+
+static const struct v4l2_ioctl_ops vicodec_ioctl_ops = {
+	.vidioc_querycap	= vidioc_querycap,
+
+	.vidioc_enum_fmt_vid_cap = vidioc_enum_fmt_vid_cap,
+	.vidioc_g_fmt_vid_cap	= vidioc_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap	= vidioc_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap	= vidioc_s_fmt_vid_cap,
+
+	.vidioc_enum_fmt_vid_cap_mplane = vidioc_enum_fmt_vid_cap,
+	.vidioc_g_fmt_vid_cap_mplane	= vidioc_g_fmt_vid_cap,
+	.vidioc_try_fmt_vid_cap_mplane	= vidioc_try_fmt_vid_cap,
+	.vidioc_s_fmt_vid_cap_mplane	= vidioc_s_fmt_vid_cap,
+
+	.vidioc_enum_fmt_vid_out = vidioc_enum_fmt_vid_out,
+	.vidioc_g_fmt_vid_out	= vidioc_g_fmt_vid_out,
+	.vidioc_try_fmt_vid_out	= vidioc_try_fmt_vid_out,
+	.vidioc_s_fmt_vid_out	= vidioc_s_fmt_vid_out,
+
+	.vidioc_enum_fmt_vid_out_mplane = vidioc_enum_fmt_vid_out,
+	.vidioc_g_fmt_vid_out_mplane	= vidioc_g_fmt_vid_out,
+	.vidioc_try_fmt_vid_out_mplane	= vidioc_try_fmt_vid_out,
+	.vidioc_s_fmt_vid_out_mplane	= vidioc_s_fmt_vid_out,
+
+	.vidioc_reqbufs		= v4l2_m2m_ioctl_reqbufs,
+	.vidioc_querybuf	= v4l2_m2m_ioctl_querybuf,
+	.vidioc_qbuf		= v4l2_m2m_ioctl_qbuf,
+	.vidioc_dqbuf		= v4l2_m2m_ioctl_dqbuf,
+	.vidioc_prepare_buf	= v4l2_m2m_ioctl_prepare_buf,
+	.vidioc_create_bufs	= v4l2_m2m_ioctl_create_bufs,
+	.vidioc_expbuf		= v4l2_m2m_ioctl_expbuf,
+
+	.vidioc_streamon	= v4l2_m2m_ioctl_streamon,
+	.vidioc_streamoff	= v4l2_m2m_ioctl_streamoff,
+
+	.vidioc_try_encoder_cmd	= vicodec_try_encoder_cmd,
+	.vidioc_encoder_cmd	= vicodec_encoder_cmd,
+	.vidioc_try_decoder_cmd	= vicodec_try_decoder_cmd,
+	.vidioc_decoder_cmd	= vicodec_decoder_cmd,
+	.vidioc_enum_framesizes = vicodec_enum_framesizes,
+
+	.vidioc_subscribe_event = vicodec_subscribe_event,
+	.vidioc_unsubscribe_event = v4l2_event_unsubscribe,
+};
+
+
+/*
+ * Queue operations
+ */
+
+static int vicodec_queue_setup(struct vb2_queue *vq, unsigned int *nbuffers,
+			       unsigned int *nplanes, unsigned int sizes[],
+			       struct device *alloc_devs[])
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(vq);
+	struct vicodec_q_data *q_data = get_q_data(ctx, vq->type);
+	unsigned int size = q_data->sizeimage;
+
+	if (*nplanes)
+		return sizes[0] < size ? -EINVAL : 0;
+
+	*nplanes = 1;
+	sizes[0] = size;
+	return 0;
+}
+
+static int vicodec_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct vicodec_q_data *q_data;
+
+	dprintk(ctx->dev, "type: %d\n", vb->vb2_queue->type);
+
+	q_data = get_q_data(ctx, vb->vb2_queue->type);
+	if (V4L2_TYPE_IS_OUTPUT(vb->vb2_queue->type)) {
+		if (vbuf->field == V4L2_FIELD_ANY)
+			vbuf->field = V4L2_FIELD_NONE;
+		if (vbuf->field != V4L2_FIELD_NONE) {
+			dprintk(ctx->dev, "%s field isn't supported\n",
+					__func__);
+			return -EINVAL;
+		}
+	}
+
+	if (vb2_plane_size(vb, 0) < q_data->sizeimage) {
+		dprintk(ctx->dev,
+			"%s data will not fit into plane (%lu < %lu)\n",
+			__func__, vb2_plane_size(vb, 0),
+			(long)q_data->sizeimage);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void vicodec_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_m2m_buf_queue(ctx->fh.m2m_ctx, vbuf);
+}
+
+static void vicodec_return_bufs(struct vb2_queue *q, u32 state)
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(q);
+	struct vb2_v4l2_buffer *vbuf;
+
+	for (;;) {
+		if (V4L2_TYPE_IS_OUTPUT(q->type))
+			vbuf = v4l2_m2m_src_buf_remove(ctx->fh.m2m_ctx);
+		else
+			vbuf = v4l2_m2m_dst_buf_remove(ctx->fh.m2m_ctx);
+		if (vbuf == NULL)
+			return;
+		spin_lock(ctx->lock);
+		v4l2_m2m_buf_done(vbuf, state);
+		spin_unlock(ctx->lock);
+	}
+}
+
+static int vicodec_start_streaming(struct vb2_queue *q,
+				   unsigned int count)
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(q);
+	struct vicodec_q_data *q_data = get_q_data(ctx, q->type);
+	unsigned int size = q_data->width * q_data->height;
+
+	q_data->sequence = 0;
+
+	if (!V4L2_TYPE_IS_OUTPUT(q->type))
+		return 0;
+
+	ctx->ref_frame.width = ctx->ref_frame.height = 0;
+	ctx->ref_frame.luma = kvmalloc(size * 3 / 2, GFP_KERNEL);
+	ctx->comp_max_size = size * 3 / 2 + sizeof(struct cframe_hdr);
+	ctx->compressed_frame = kvmalloc(ctx->comp_max_size, GFP_KERNEL);
+	if (!ctx->ref_frame.luma || !ctx->compressed_frame) {
+		kvfree(ctx->ref_frame.luma);
+		kvfree(ctx->compressed_frame);
+		vicodec_return_bufs(q, VB2_BUF_STATE_QUEUED);
+		return -ENOMEM;
+	}
+	ctx->ref_frame.cb = ctx->ref_frame.luma + size;
+	ctx->ref_frame.cr = ctx->ref_frame.cb + size / 4;
+	ctx->last_src_buf = NULL;
+	ctx->last_dst_buf = NULL;
+	v4l2_ctrl_grab(ctx->ctrl_gop_size, true);
+	ctx->gop_size = v4l2_ctrl_g_ctrl(ctx->ctrl_gop_size);
+	ctx->gop_cnt = 0;
+	ctx->cur_buf_offset = 0;
+	ctx->comp_size = 0;
+	ctx->comp_magic_cnt = 0;
+	ctx->comp_has_frame = false;
+
+	return 0;
+}
+
+static void vicodec_stop_streaming(struct vb2_queue *q)
+{
+	struct vicodec_ctx *ctx = vb2_get_drv_priv(q);
+
+	vicodec_return_bufs(q, VB2_BUF_STATE_ERROR);
+
+	if (!V4L2_TYPE_IS_OUTPUT(q->type))
+		return;
+
+	kvfree(ctx->ref_frame.luma);
+	kvfree(ctx->compressed_frame);
+	v4l2_ctrl_grab(ctx->ctrl_gop_size, false);
+}
+
+static const struct vb2_ops vicodec_qops = {
+	.queue_setup	 = vicodec_queue_setup,
+	.buf_prepare	 = vicodec_buf_prepare,
+	.buf_queue	 = vicodec_buf_queue,
+	.start_streaming = vicodec_start_streaming,
+	.stop_streaming  = vicodec_stop_streaming,
+	.wait_prepare	 = vb2_ops_wait_prepare,
+	.wait_finish	 = vb2_ops_wait_finish,
+};
+
+static int queue_init(void *priv, struct vb2_queue *src_vq,
+		      struct vb2_queue *dst_vq)
+{
+	struct vicodec_ctx *ctx = priv;
+	int ret;
+
+	src_vq->type = (multiplanar ?
+			V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE :
+			V4L2_BUF_TYPE_VIDEO_OUTPUT);
+	src_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
+	src_vq->drv_priv = ctx;
+	src_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	src_vq->ops = &vicodec_qops;
+	src_vq->mem_ops = &vb2_vmalloc_memops;
+	src_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	src_vq->lock = ctx->is_enc ? &ctx->dev->enc_mutex :
+		&ctx->dev->dec_mutex;
+
+	ret = vb2_queue_init(src_vq);
+	if (ret)
+		return ret;
+
+	dst_vq->type = (multiplanar ?
+			V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE :
+			V4L2_BUF_TYPE_VIDEO_CAPTURE);
+	dst_vq->io_modes = VB2_MMAP | VB2_USERPTR | VB2_DMABUF;
+	dst_vq->drv_priv = ctx;
+	dst_vq->buf_struct_size = sizeof(struct v4l2_m2m_buffer);
+	dst_vq->ops = &vicodec_qops;
+	dst_vq->mem_ops = &vb2_vmalloc_memops;
+	dst_vq->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_COPY;
+	dst_vq->lock = src_vq->lock;
+
+	return vb2_queue_init(dst_vq);
+}
+
+/*
+ * File operations
+ */
+static int vicodec_open(struct file *file)
+{
+	struct video_device *vfd = video_devdata(file);
+	struct vicodec_dev *dev = video_drvdata(file);
+	struct vicodec_ctx *ctx = NULL;
+	struct v4l2_ctrl_handler *hdl;
+	unsigned int size;
+	int rc = 0;
+
+	if (mutex_lock_interruptible(vfd->lock))
+		return -ERESTARTSYS;
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	if (!ctx) {
+		rc = -ENOMEM;
+		goto open_unlock;
+	}
+
+	if (vfd == &dev->enc_vfd)
+		ctx->is_enc = true;
+
+	v4l2_fh_init(&ctx->fh, video_devdata(file));
+	file->private_data = &ctx->fh;
+	ctx->dev = dev;
+	hdl = &ctx->hdl;
+	v4l2_ctrl_handler_init(hdl, 4);
+	ctx->ctrl_gop_size = v4l2_ctrl_new_std(hdl, NULL,
+					       V4L2_CID_MPEG_VIDEO_GOP_SIZE,
+					       1, 16, 1, 10);
+	if (hdl->error) {
+		rc = hdl->error;
+		v4l2_ctrl_handler_free(hdl);
+		kfree(ctx);
+		goto open_unlock;
+	}
+	ctx->fh.ctrl_handler = hdl;
+	v4l2_ctrl_handler_setup(hdl);
+
+	ctx->q_data[V4L2_M2M_SRC].fourcc =
+		ctx->is_enc ? V4L2_PIX_FMT_YUV420 : V4L2_PIX_FMT_FWHT;
+	ctx->q_data[V4L2_M2M_SRC].width = 1280;
+	ctx->q_data[V4L2_M2M_SRC].height = 720;
+	size = 1280 * 720 * 3 / 2;
+	ctx->q_data[V4L2_M2M_SRC].sizeimage = size;
+	ctx->q_data[V4L2_M2M_DST] = ctx->q_data[V4L2_M2M_SRC];
+	ctx->q_data[V4L2_M2M_DST].fourcc =
+		ctx->is_enc ? V4L2_PIX_FMT_FWHT : V4L2_PIX_FMT_YUV420;
+	ctx->colorspace = V4L2_COLORSPACE_REC709;
+
+	size += sizeof(struct cframe_hdr);
+	if (ctx->is_enc) {
+		ctx->q_data[V4L2_M2M_DST].sizeimage = size;
+		ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->enc_dev, ctx,
+						    &queue_init);
+		ctx->lock = &dev->enc_lock;
+	} else {
+		ctx->q_data[V4L2_M2M_SRC].sizeimage = size;
+		ctx->fh.m2m_ctx = v4l2_m2m_ctx_init(dev->dec_dev, ctx,
+						    &queue_init);
+		ctx->lock = &dev->dec_lock;
+	}
+
+	if (IS_ERR(ctx->fh.m2m_ctx)) {
+		rc = PTR_ERR(ctx->fh.m2m_ctx);
+
+		v4l2_ctrl_handler_free(hdl);
+		v4l2_fh_exit(&ctx->fh);
+		kfree(ctx);
+		goto open_unlock;
+	}
+
+	v4l2_fh_add(&ctx->fh);
+
+open_unlock:
+	mutex_unlock(vfd->lock);
+	return rc;
+}
+
+static int vicodec_release(struct file *file)
+{
+	struct video_device *vfd = video_devdata(file);
+	struct vicodec_ctx *ctx = file2ctx(file);
+
+	v4l2_fh_del(&ctx->fh);
+	v4l2_fh_exit(&ctx->fh);
+	v4l2_ctrl_handler_free(&ctx->hdl);
+	mutex_lock(vfd->lock);
+	v4l2_m2m_ctx_release(ctx->fh.m2m_ctx);
+	mutex_unlock(vfd->lock);
+	kfree(ctx);
+
+	return 0;
+}
+
+static const struct v4l2_file_operations vicodec_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vicodec_open,
+	.release	= vicodec_release,
+	.poll		= v4l2_m2m_fop_poll,
+	.unlocked_ioctl	= video_ioctl2,
+	.mmap		= v4l2_m2m_fop_mmap,
+};
+
+static const struct video_device vicodec_videodev = {
+	.name		= VICODEC_NAME,
+	.vfl_dir	= VFL_DIR_M2M,
+	.fops		= &vicodec_fops,
+	.ioctl_ops	= &vicodec_ioctl_ops,
+	.minor		= -1,
+	.release	= video_device_release_empty,
+};
+
+static const struct v4l2_m2m_ops m2m_ops = {
+	.device_run	= device_run,
+	.job_abort	= job_abort,
+	.job_ready	= job_ready,
+};
+
+static int vicodec_probe(struct platform_device *pdev)
+{
+	struct vicodec_dev *dev;
+	struct video_device *vfd;
+	int ret;
+
+	dev = devm_kzalloc(&pdev->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	spin_lock_init(&dev->enc_lock);
+	spin_lock_init(&dev->dec_lock);
+
+	ret = v4l2_device_register(&pdev->dev, &dev->v4l2_dev);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	dev->mdev.dev = &pdev->dev;
+	strlcpy(dev->mdev.model, "vicodec", sizeof(dev->mdev.model));
+	media_device_init(&dev->mdev);
+	dev->v4l2_dev.mdev = &dev->mdev;
+#endif
+
+	mutex_init(&dev->enc_mutex);
+	mutex_init(&dev->dec_mutex);
+
+	platform_set_drvdata(pdev, dev);
+
+	dev->enc_dev = v4l2_m2m_init(&m2m_ops);
+	if (IS_ERR(dev->enc_dev)) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init vicodec device\n");
+		ret = PTR_ERR(dev->enc_dev);
+		goto unreg_dev;
+	}
+
+	dev->dec_dev = v4l2_m2m_init(&m2m_ops);
+	if (IS_ERR(dev->dec_dev)) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init vicodec device\n");
+		ret = PTR_ERR(dev->dec_dev);
+		goto err_enc_m2m;
+	}
+
+	dev->enc_vfd = vicodec_videodev;
+	vfd = &dev->enc_vfd;
+	vfd->lock = &dev->enc_mutex;
+	vfd->v4l2_dev = &dev->v4l2_dev;
+	strlcpy(vfd->name, "vicodec-enc", sizeof(vfd->name));
+	v4l2_disable_ioctl(vfd, VIDIOC_DECODER_CMD);
+	v4l2_disable_ioctl(vfd, VIDIOC_TRY_DECODER_CMD);
+	video_set_drvdata(vfd, dev);
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
+		goto err_dec_m2m;
+	}
+	v4l2_info(&dev->v4l2_dev,
+			"Device registered as /dev/video%d\n", vfd->num);
+
+	dev->dec_vfd = vicodec_videodev;
+	vfd = &dev->dec_vfd;
+	vfd->lock = &dev->dec_mutex;
+	vfd->v4l2_dev = &dev->v4l2_dev;
+	strlcpy(vfd->name, "vicodec-dec", sizeof(vfd->name));
+	v4l2_disable_ioctl(vfd, VIDIOC_ENCODER_CMD);
+	v4l2_disable_ioctl(vfd, VIDIOC_TRY_ENCODER_CMD);
+	video_set_drvdata(vfd, dev);
+
+	ret = video_register_device(vfd, VFL_TYPE_GRABBER, 0);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register video device\n");
+		goto unreg_enc;
+	}
+	v4l2_info(&dev->v4l2_dev,
+			"Device registered as /dev/video%d\n", vfd->num);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	ret = v4l2_m2m_register_media_controller(dev->enc_dev,
+			&dev->enc_vfd, MEDIA_ENT_F_PROC_VIDEO_ENCODER);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller\n");
+		goto unreg_m2m;
+	}
+
+	ret = v4l2_m2m_register_media_controller(dev->dec_dev,
+			&dev->dec_vfd, MEDIA_ENT_F_PROC_VIDEO_DECODER);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to init mem2mem media controller\n");
+		goto unreg_m2m_enc_mc;
+	}
+
+	ret = media_device_register(&dev->mdev);
+	if (ret) {
+		v4l2_err(&dev->v4l2_dev, "Failed to register mem2mem media device\n");
+		goto unreg_m2m_dec_mc;
+	}
+#endif
+	return 0;
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+unreg_m2m_dec_mc:
+	v4l2_m2m_unregister_media_controller(dev->dec_dev);
+unreg_m2m_enc_mc:
+	v4l2_m2m_unregister_media_controller(dev->enc_dev);
+unreg_m2m:
+	video_unregister_device(&dev->dec_vfd);
+#endif
+unreg_enc:
+	video_unregister_device(&dev->enc_vfd);
+err_dec_m2m:
+	v4l2_m2m_release(dev->dec_dev);
+err_enc_m2m:
+	v4l2_m2m_release(dev->enc_dev);
+unreg_dev:
+	v4l2_device_unregister(&dev->v4l2_dev);
+
+	return ret;
+}
+
+static int vicodec_remove(struct platform_device *pdev)
+{
+	struct vicodec_dev *dev = platform_get_drvdata(pdev);
+
+	v4l2_info(&dev->v4l2_dev, "Removing " VICODEC_NAME);
+
+#ifdef CONFIG_MEDIA_CONTROLLER
+	media_device_unregister(&dev->mdev);
+	v4l2_m2m_unregister_media_controller(dev->enc_dev);
+	v4l2_m2m_unregister_media_controller(dev->dec_dev);
+	media_device_cleanup(&dev->mdev);
+#endif
+
+	v4l2_m2m_release(dev->enc_dev);
+	v4l2_m2m_release(dev->dec_dev);
+	video_unregister_device(&dev->enc_vfd);
+	video_unregister_device(&dev->dec_vfd);
+	v4l2_device_unregister(&dev->v4l2_dev);
+
+	return 0;
+}
+
+static struct platform_driver vicodec_pdrv = {
+	.probe		= vicodec_probe,
+	.remove		= vicodec_remove,
+	.driver		= {
+		.name	= VICODEC_NAME,
+	},
+};
+
+static void __exit vicodec_exit(void)
+{
+	platform_driver_unregister(&vicodec_pdrv);
+	platform_device_unregister(&vicodec_pdev);
+}
+
+static int __init vicodec_init(void)
+{
+	int ret;
+
+	ret = platform_device_register(&vicodec_pdev);
+	if (ret)
+		return ret;
+
+	ret = platform_driver_register(&vicodec_pdrv);
+	if (ret)
+		platform_device_unregister(&vicodec_pdev);
+
+	return ret;
+}
+
+module_init(vicodec_init);
+module_exit(vicodec_exit);
-- 
cgit v1.2.3


From 5c9072e8458f937a9c0a38736989d128ef990fc5 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 28 Jun 2018 06:57:52 -0400
Subject: media: coda: move framebuffer size calculation out of loop

All internal YCbCr frame buffers are the same size, calculate ycbcr_size
once before the allocation loop.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 26d14e6a64cc..033abb03722b 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -391,7 +391,7 @@ static int coda_alloc_framebuffers(struct coda_ctx *ctx,
 {
 	struct coda_dev *dev = ctx->dev;
 	int width, height;
-	int ysize;
+	unsigned int ysize, ycbcr_size;
 	int ret;
 	int i;
 
@@ -407,15 +407,16 @@ static int coda_alloc_framebuffers(struct coda_ctx *ctx,
 	}
 	ysize = width * height;
 
+	if (ctx->tiled_map_type == GDI_TILED_FRAME_MB_RASTER_MAP)
+		ycbcr_size = round_up(ysize, 4096) + ysize / 2;
+	else
+		ycbcr_size = ysize + ysize / 2;
+
 	/* Allocate frame buffers */
 	for (i = 0; i < ctx->num_internal_frames; i++) {
-		size_t size;
+		size_t size = ycbcr_size;
 		char *name;
 
-		if (ctx->tiled_map_type == GDI_TILED_FRAME_MB_RASTER_MAP)
-			size = round_up(ysize, 4096) + ysize / 2;
-		else
-			size = ysize + ysize / 2;
 		/* Add space for mvcol buffers */
 		if (dev->devtype->product != CODA_DX6 &&
 		    (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 ||
-- 
cgit v1.2.3


From 9e49ca530eebd6775410317aac8a68f88171f89c Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 28 Jun 2018 06:57:53 -0400
Subject: media: coda: streamline framebuffer size calculation a bit

Remove the intermediate width and height variables, the calculation is
simple enough.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c | 14 +++++---------
 1 file changed, 5 insertions(+), 9 deletions(-)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 033abb03722b..bf8d8489f827 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -390,7 +390,6 @@ static int coda_alloc_framebuffers(struct coda_ctx *ctx,
 				   struct coda_q_data *q_data, u32 fourcc)
 {
 	struct coda_dev *dev = ctx->dev;
-	int width, height;
 	unsigned int ysize, ycbcr_size;
 	int ret;
 	int i;
@@ -398,14 +397,11 @@ static int coda_alloc_framebuffers(struct coda_ctx *ctx,
 	if (ctx->codec->src_fourcc == V4L2_PIX_FMT_H264 ||
 	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264 ||
 	    ctx->codec->src_fourcc == V4L2_PIX_FMT_MPEG4 ||
-	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_MPEG4) {
-		width = round_up(q_data->width, 16);
-		height = round_up(q_data->height, 16);
-	} else {
-		width = round_up(q_data->width, 8);
-		height = q_data->height;
-	}
-	ysize = width * height;
+	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_MPEG4)
+		ysize = round_up(q_data->width, 16) *
+			round_up(q_data->height, 16);
+	else
+		ysize = round_up(q_data->width, 8) * q_data->height;
 
 	if (ctx->tiled_map_type == GDI_TILED_FRAME_MB_RASTER_MAP)
 		ycbcr_size = round_up(ysize, 4096) + ysize / 2;
-- 
cgit v1.2.3


From 40fa8df63ce48d43f229d4dc6d43b3b9105abb20 Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 28 Jun 2018 06:57:54 -0400
Subject: media: coda: use encoder crop rectangle to set visible width and
 height

Allow to set a crop rectangle on the encoder output queue to set the
visible resolution as required by the V4L2 codec API.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c    | 24 ++++++++---------
 drivers/media/platform/coda/coda-common.c | 45 +++++++++++++++++++++++++++----
 2 files changed, 52 insertions(+), 17 deletions(-)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index bf8d8489f827..529fc187ccfd 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -398,10 +398,10 @@ static int coda_alloc_framebuffers(struct coda_ctx *ctx,
 	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264 ||
 	    ctx->codec->src_fourcc == V4L2_PIX_FMT_MPEG4 ||
 	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_MPEG4)
-		ysize = round_up(q_data->width, 16) *
-			round_up(q_data->height, 16);
+		ysize = round_up(q_data->rect.width, 16) *
+			round_up(q_data->rect.height, 16);
 	else
-		ysize = round_up(q_data->width, 8) * q_data->height;
+		ysize = round_up(q_data->rect.width, 8) * q_data->rect.height;
 
 	if (ctx->tiled_map_type == GDI_TILED_FRAME_MB_RASTER_MAP)
 		ycbcr_size = round_up(ysize, 4096) + ysize / 2;
@@ -497,8 +497,8 @@ static int coda_alloc_context_buffers(struct coda_ctx *ctx,
 
 	if (!ctx->slicebuf.vaddr && q_data->fourcc == V4L2_PIX_FMT_H264) {
 		/* worst case slice size */
-		size = (DIV_ROUND_UP(q_data->width, 16) *
-			DIV_ROUND_UP(q_data->height, 16)) * 3200 / 8 + 512;
+		size = (DIV_ROUND_UP(q_data->rect.width, 16) *
+			DIV_ROUND_UP(q_data->rect.height, 16)) * 3200 / 8 + 512;
 		ret = coda_alloc_context_buf(ctx, &ctx->slicebuf, size,
 					     "slicebuf");
 		if (ret < 0)
@@ -630,7 +630,7 @@ static void coda_setup_iram(struct coda_ctx *ctx)
 		struct coda_q_data *q_data_src;
 
 		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
-		mb_width = DIV_ROUND_UP(q_data_src->width, 16);
+		mb_width = DIV_ROUND_UP(q_data_src->rect.width, 16);
 		w128 = mb_width * 128;
 		w64 = mb_width * 64;
 
@@ -927,25 +927,25 @@ static int coda_start_encoding(struct coda_ctx *ctx)
 	value = 0;
 	switch (dev->devtype->product) {
 	case CODA_DX6:
-		value = (q_data_src->width & CODADX6_PICWIDTH_MASK)
+		value = (q_data_src->rect.width & CODADX6_PICWIDTH_MASK)
 			<< CODADX6_PICWIDTH_OFFSET;
-		value |= (q_data_src->height & CODADX6_PICHEIGHT_MASK)
+		value |= (q_data_src->rect.height & CODADX6_PICHEIGHT_MASK)
 			 << CODA_PICHEIGHT_OFFSET;
 		break;
 	case CODA_HX4:
 	case CODA_7541:
 		if (dst_fourcc == V4L2_PIX_FMT_H264) {
-			value = (round_up(q_data_src->width, 16) &
+			value = (round_up(q_data_src->rect.width, 16) &
 				 CODA7_PICWIDTH_MASK) << CODA7_PICWIDTH_OFFSET;
-			value |= (round_up(q_data_src->height, 16) &
+			value |= (round_up(q_data_src->rect.height, 16) &
 				 CODA7_PICHEIGHT_MASK) << CODA_PICHEIGHT_OFFSET;
 			break;
 		}
 		/* fallthrough */
 	case CODA_960:
-		value = (q_data_src->width & CODA7_PICWIDTH_MASK)
+		value = (q_data_src->rect.width & CODA7_PICWIDTH_MASK)
 			<< CODA7_PICWIDTH_OFFSET;
-		value |= (q_data_src->height & CODA7_PICHEIGHT_MASK)
+		value |= (q_data_src->rect.height & CODA7_PICHEIGHT_MASK)
 			 << CODA_PICHEIGHT_OFFSET;
 	}
 	coda_write(dev, value, CODA_CMD_ENC_SEQ_SRC_SIZE);
diff --git a/drivers/media/platform/coda/coda-common.c b/drivers/media/platform/coda/coda-common.c
index f25f1417b4fa..726b3b93a486 100644
--- a/drivers/media/platform/coda/coda-common.c
+++ b/drivers/media/platform/coda/coda-common.c
@@ -933,6 +933,40 @@ static int coda_g_selection(struct file *file, void *fh,
 	return 0;
 }
 
+static int coda_s_selection(struct file *file, void *fh,
+			    struct v4l2_selection *s)
+{
+	struct coda_ctx *ctx = fh_to_ctx(fh);
+	struct coda_q_data *q_data;
+
+	if (ctx->inst_type == CODA_INST_ENCODER &&
+	    s->type == V4L2_BUF_TYPE_VIDEO_OUTPUT &&
+	    s->target == V4L2_SEL_TGT_CROP) {
+		q_data = get_q_data(ctx, s->type);
+		if (!q_data)
+			return -EINVAL;
+
+		s->r.left = 0;
+		s->r.top = 0;
+		s->r.width = clamp(s->r.width, 2U, q_data->width);
+		s->r.height = clamp(s->r.height, 2U, q_data->height);
+
+		if (s->flags & V4L2_SEL_FLAG_LE) {
+			s->r.width = round_up(s->r.width, 2);
+			s->r.height = round_up(s->r.height, 2);
+		} else {
+			s->r.width = round_down(s->r.width, 2);
+			s->r.height = round_down(s->r.height, 2);
+		}
+
+		q_data->rect = s->r;
+
+		return 0;
+	}
+
+	return coda_g_selection(file, fh, s);
+}
+
 static int coda_try_encoder_cmd(struct file *file, void *fh,
 				struct v4l2_encoder_cmd *ec)
 {
@@ -1146,6 +1180,7 @@ static const struct v4l2_ioctl_ops coda_ioctl_ops = {
 	.vidioc_streamoff	= v4l2_m2m_ioctl_streamoff,
 
 	.vidioc_g_selection	= coda_g_selection,
+	.vidioc_s_selection	= coda_s_selection,
 
 	.vidioc_try_encoder_cmd	= coda_try_encoder_cmd,
 	.vidioc_encoder_cmd	= coda_encoder_cmd,
@@ -1587,12 +1622,12 @@ static int coda_start_streaming(struct vb2_queue *q, unsigned int count)
 		goto out;
 
 	q_data_dst = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE);
-	if ((q_data_src->width != q_data_dst->width &&
-	     round_up(q_data_src->width, 16) != q_data_dst->width) ||
-	    (q_data_src->height != q_data_dst->height &&
-	     round_up(q_data_src->height, 16) != q_data_dst->height)) {
+	if ((q_data_src->rect.width != q_data_dst->width &&
+	     round_up(q_data_src->rect.width, 16) != q_data_dst->width) ||
+	    (q_data_src->rect.height != q_data_dst->height &&
+	     round_up(q_data_src->rect.height, 16) != q_data_dst->height)) {
 		v4l2_err(v4l2_dev, "can't convert %dx%d to %dx%d\n",
-			 q_data_src->width, q_data_src->height,
+			 q_data_src->rect.width, q_data_src->rect.height,
 			 q_data_dst->width, q_data_dst->height);
 		ret = -EINVAL;
 		goto err;
-- 
cgit v1.2.3


From 22fb5f0f8604a1e5b7d66637e5e85c195cc85cde Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 28 Jun 2018 07:01:47 -0400
Subject: media: coda: add missing h.264 levels

This enables reordering support for h.264 main profile level 4.2,
5.0, and 5.1 streams. Even though we likely can't play back such
streams at full speed, we should still recognize them correctly.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-h264.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/media/platform/coda/coda-h264.c b/drivers/media/platform/coda/coda-h264.c
index 0e27412e01f5..07b4c706504f 100644
--- a/drivers/media/platform/coda/coda-h264.c
+++ b/drivers/media/platform/coda/coda-h264.c
@@ -108,6 +108,9 @@ int coda_h264_level(int level_idc)
 	case 32: return V4L2_MPEG_VIDEO_H264_LEVEL_3_2;
 	case 40: return V4L2_MPEG_VIDEO_H264_LEVEL_4_0;
 	case 41: return V4L2_MPEG_VIDEO_H264_LEVEL_4_1;
+	case 42: return V4L2_MPEG_VIDEO_H264_LEVEL_4_2;
+	case 50: return V4L2_MPEG_VIDEO_H264_LEVEL_5_0;
+	case 51: return V4L2_MPEG_VIDEO_H264_LEVEL_5_1;
 	default: return -EINVAL;
 	}
 }
-- 
cgit v1.2.3


From acbea6798955e92eefa5fb84ecaa677a763c8762 Mon Sep 17 00:00:00 2001
From: Matt Ranostay <matt.ranostay@konsulko.com>
Date: Thu, 28 Jun 2018 14:11:04 -0400
Subject: media: video-i2c: add hwmon support for amg88xx

AMG88xx has an on-board thermistor which is used for more accurate
processing of its temperature readings from the 8x8 thermopile array

Cc: linux-hwmon@vger.kernel.org
Signed-off-by: Matt Ranostay <matt.ranostay@konsulko.com>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/Kconfig     |  1 +
 drivers/media/i2c/video-i2c.c | 81 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 82 insertions(+)

diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 5ee7a09001a7..439f6be08b95 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -1033,6 +1033,7 @@ config VIDEO_I2C
 	tristate "I2C transport video support"
 	depends on VIDEO_V4L2 && I2C
 	select VIDEOBUF2_VMALLOC
+	imply HWMON
 	---help---
 	  Enable the I2C transport video support which supports the
 	  following:
diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c
index 0b347cc19aa5..7dc9338502e5 100644
--- a/drivers/media/i2c/video-i2c.c
+++ b/drivers/media/i2c/video-i2c.c
@@ -10,6 +10,7 @@
 
 #include <linux/delay.h>
 #include <linux/freezer.h>
+#include <linux/hwmon.h>
 #include <linux/kthread.h>
 #include <linux/i2c.h>
 #include <linux/list.h>
@@ -77,6 +78,9 @@ struct video_i2c_chip {
 
 	/* xfer function */
 	int (*xfer)(struct video_i2c_data *data, char *buf);
+
+	/* hwmon init function */
+	int (*hwmon_init)(struct video_i2c_data *data);
 };
 
 static int amg88xx_xfer(struct video_i2c_data *data, char *buf)
@@ -101,6 +105,74 @@ static int amg88xx_xfer(struct video_i2c_data *data, char *buf)
 	return (ret == 2) ? 0 : -EIO;
 }
 
+#if IS_ENABLED(CONFIG_HWMON)
+
+static const u32 amg88xx_temp_config[] = {
+	HWMON_T_INPUT,
+	0
+};
+
+static const struct hwmon_channel_info amg88xx_temp = {
+	.type = hwmon_temp,
+	.config = amg88xx_temp_config,
+};
+
+static const struct hwmon_channel_info *amg88xx_info[] = {
+	&amg88xx_temp,
+	NULL
+};
+
+static umode_t amg88xx_is_visible(const void *drvdata,
+				  enum hwmon_sensor_types type,
+				  u32 attr, int channel)
+{
+	return 0444;
+}
+
+static int amg88xx_read(struct device *dev, enum hwmon_sensor_types type,
+			u32 attr, int channel, long *val)
+{
+	struct video_i2c_data *data = dev_get_drvdata(dev);
+	struct i2c_client *client = data->client;
+	int tmp = i2c_smbus_read_word_data(client, 0x0e);
+
+	if (tmp < 0)
+		return tmp;
+
+	/*
+	 * Check for sign bit, this isn't a two's complement value but an
+	 * absolute temperature that needs to be inverted in the case of being
+	 * negative.
+	 */
+	if (tmp & BIT(11))
+		tmp = -(tmp & 0x7ff);
+
+	*val = (tmp * 625) / 10;
+
+	return 0;
+}
+
+static const struct hwmon_ops amg88xx_hwmon_ops = {
+	.is_visible = amg88xx_is_visible,
+	.read = amg88xx_read,
+};
+
+static const struct hwmon_chip_info amg88xx_chip_info = {
+	.ops = &amg88xx_hwmon_ops,
+	.info = amg88xx_info,
+};
+
+static int amg88xx_hwmon_init(struct video_i2c_data *data)
+{
+	void *hwmon = devm_hwmon_device_register_with_info(&data->client->dev,
+				"amg88xx", data, &amg88xx_chip_info, NULL);
+
+	return PTR_ERR(hwmon);
+}
+#else
+#define	amg88xx_hwmon_init	NULL
+#endif
+
 #define AMG88XX		0
 
 static const struct video_i2c_chip video_i2c_chip[] = {
@@ -111,6 +183,7 @@ static const struct video_i2c_chip video_i2c_chip[] = {
 		.buffer_size	= 128,
 		.bpp		= 16,
 		.xfer		= &amg88xx_xfer,
+		.hwmon_init	= amg88xx_hwmon_init,
 	},
 };
 
@@ -505,6 +578,14 @@ static int video_i2c_probe(struct i2c_client *client,
 	video_set_drvdata(&data->vdev, data);
 	i2c_set_clientdata(client, data);
 
+	if (data->chip->hwmon_init) {
+		ret = data->chip->hwmon_init(data);
+		if (ret < 0) {
+			dev_warn(&client->dev,
+				 "failed to register hwmon device\n");
+		}
+	}
+
 	ret = video_register_device(&data->vdev, VFL_TYPE_GRABBER, -1);
 	if (ret < 0)
 		goto error_unregister_device;
-- 
cgit v1.2.3


From 5a1a2f63d840dc2631505b607e11ff65ac1b7d3c Mon Sep 17 00:00:00 2001
From: Krzysztof Ha?asa <khalasa@piap.pl>
Date: Thu, 28 Jun 2018 17:45:07 -0400
Subject: media: tw686x: Fix oops on buffer alloc failure

The error path currently calls tw686x_video_free() which requires
vc->dev to be initialized, causing a NULL dereference on uninitizalized
channels.

Fix this by setting the vc->dev fields for all the channels first.

Fixes: f8afaa8dbc0d ("[media] tw686x: Introduce an interface to support multiple DMA modes")

Signed-off-by: Krzysztof Ha?asa <khalasa@piap.pl>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/tw686x/tw686x-video.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/drivers/media/pci/tw686x/tw686x-video.c b/drivers/media/pci/tw686x/tw686x-video.c
index 0ea8dd44026c..3a06c000f97b 100644
--- a/drivers/media/pci/tw686x/tw686x-video.c
+++ b/drivers/media/pci/tw686x/tw686x-video.c
@@ -1190,6 +1190,14 @@ int tw686x_video_init(struct tw686x_dev *dev)
 			return err;
 	}
 
+	/* Initialize vc->dev and vc->ch for the error path */
+	for (ch = 0; ch < max_channels(dev); ch++) {
+		struct tw686x_video_channel *vc = &dev->video_channels[ch];
+
+		vc->dev = dev;
+		vc->ch = ch;
+	}
+
 	for (ch = 0; ch < max_channels(dev); ch++) {
 		struct tw686x_video_channel *vc = &dev->video_channels[ch];
 		struct video_device *vdev;
@@ -1198,9 +1206,6 @@ int tw686x_video_init(struct tw686x_dev *dev)
 		spin_lock_init(&vc->qlock);
 		INIT_LIST_HEAD(&vc->vidq_queued);
 
-		vc->dev = dev;
-		vc->ch = ch;
-
 		/* default settings */
 		err = tw686x_set_standard(vc, V4L2_STD_NTSC);
 		if (err)
-- 
cgit v1.2.3


From 2e3134caf63694bf1dbb2e68829871e14d543613 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Sun, 1 Jul 2018 13:32:05 -0400
Subject: media: gspca_kinect: cast sizeof to int for comparison

Comparing an int to a size, which is unsigned, causes the int to become
unsigned, giving the wrong result.  kinect_read returns the result of
usb_control_msg, which can return a negtive error code.

A simplified version of the semantic match that finds this problem is as
follows: (http://coccinelle.lip6.fr/)

// <smpl>
@@
int x;
expression e,e1;
identifier f;
@@

*x = f(...);
... when != x = e1
    when != if (x < 0 || ...) { ... return ...; }
*x < sizeof(e)
// </smpl>

Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/gspca/kinect.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/gspca/kinect.c b/drivers/media/usb/gspca/kinect.c
index 0cfdf8a1e19d..f993f6280c56 100644
--- a/drivers/media/usb/gspca/kinect.c
+++ b/drivers/media/usb/gspca/kinect.c
@@ -163,7 +163,7 @@ static int send_cmd(struct gspca_dev *gspca_dev, uint16_t cmd, void *cmdbuf,
 		actual_len = kinect_read(udev, ibuf, 0x200);
 	} while (actual_len == 0);
 	gspca_dbg(gspca_dev, D_USBO, "Control reply: %d\n", actual_len);
-	if (actual_len < sizeof(*rhdr)) {
+	if (actual_len < (int)sizeof(*rhdr)) {
 		pr_err("send_cmd: Input control transfer failed (%d)\n",
 		       actual_len);
 		return actual_len < 0 ? actual_len : -EREMOTEIO;
-- 
cgit v1.2.3


From d4de804e02a3bff973a91b13784ecd5376baf9c1 Mon Sep 17 00:00:00 2001
From: Hugues Fruchet <hugues.fruchet@st.com>
Date: Thu, 5 Jul 2018 05:01:42 -0400
Subject: media: MAINTAINERS: Add entry for STM32 DCMI media driver

Add an entry to make myself a maintainer of STM32 DCMI media driver.

Signed-off-by: Hugues Fruchet <hugues.fruchet@st.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 MAINTAINERS | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 67781db8b077..59a9e92caed9 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8969,6 +8969,14 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/dvb-frontends/stv6111*
 
+MEDIA DRIVERS FOR STM32 - DCMI
+M:	Hugues Fruchet <hugues.fruchet@st.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Supported
+F:	Documentation/devicetree/bindings/media/st,stm32-dcmi.txt
+F:	drivers/media/platform/stm32/stm32-dcmi.c
+
 MEDIA DRIVERS FOR NVIDIA TEGRA - VDE
 M:	Dmitry Osipenko <digetx@gmail.com>
 L:	linux-media@vger.kernel.org
-- 
cgit v1.2.3


From bf7b70482704bb0785e6b65ee30a6383ab22bbc6 Mon Sep 17 00:00:00 2001
From: Baruch Siach <baruch@tkos.co.il>
Date: Thu, 5 Jul 2018 05:38:00 -0400
Subject: media: v4l2-ctrls.h: fix v4l2_ctrl field description typos

Signed-off-by: Baruch Siach <baruch@tkos.co.il>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 include/media/v4l2-ctrls.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/media/v4l2-ctrls.h b/include/media/v4l2-ctrls.h
index 5b445b5654f7..f615ba1b29dd 100644
--- a/include/media/v4l2-ctrls.h
+++ b/include/media/v4l2-ctrls.h
@@ -181,10 +181,10 @@ typedef void (*v4l2_ctrl_notify_fnc)(struct v4l2_ctrl *ctrl, void *priv);
  *		not freed when the control is deleted. Should this be needed
  *		then a new internal bitfield can be added to tell the framework
  *		to free this pointer.
- * @p_cur:	The control's current value represented via a union with
+ * @p_cur:	The control's current value represented via a union which
  *		provides a standard way of accessing control types
  *		through a pointer.
- * @p_new:	The control's new value represented via a union with provides
+ * @p_new:	The control's new value represented via a union which provides
  *		a standard way of accessing control types
  *		through a pointer.
  */
-- 
cgit v1.2.3


From ea8afbabc25ade9aa34da01ffbba8085ab46ca48 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:35 -0400
Subject: media: venus: hfi_msgs: correct pointer increment

Data pointer should be incremented by size of the structure not
the size of a pointer, correct the mistake.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi_msgs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/hfi_msgs.c b/drivers/media/platform/qcom/venus/hfi_msgs.c
index 90c93d9603dc..589e1a6b36a9 100644
--- a/drivers/media/platform/qcom/venus/hfi_msgs.c
+++ b/drivers/media/platform/qcom/venus/hfi_msgs.c
@@ -60,14 +60,14 @@ static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 			frame_sz = (struct hfi_framesize *)data_ptr;
 			event.width = frame_sz->width;
 			event.height = frame_sz->height;
-			data_ptr += sizeof(frame_sz);
+			data_ptr += sizeof(*frame_sz);
 			break;
 		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_CURRENT:
 			data_ptr += sizeof(u32);
 			profile_level = (struct hfi_profile_level *)data_ptr;
 			event.profile = profile_level->profile;
 			event.level = profile_level->level;
-			data_ptr += sizeof(profile_level);
+			data_ptr += sizeof(*profile_level);
 			break;
 		default:
 			break;
-- 
cgit v1.2.3


From f04997bdca34221c5e953df40999c4c92edb4e0b Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:36 -0400
Subject: media: venus: hfi: preparation to support venus 4xx

This covers the differences between 1xx,3xx and 4xx.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/core.h         |  4 ++
 drivers/media/platform/qcom/venus/helpers.c      | 56 ++++++++++++++++--------
 drivers/media/platform/qcom/venus/hfi_helper.h   | 56 +++++++++++++++++++++---
 drivers/media/platform/qcom/venus/hfi_venus_io.h |  7 +++
 drivers/media/platform/qcom/venus/vdec.c         |  5 ++-
 drivers/media/platform/qcom/venus/venc.c         |  5 ++-
 6 files changed, 104 insertions(+), 29 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index 0360d295f4c8..8d3e150800c9 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -305,6 +305,10 @@ struct venus_inst {
 	struct hfi_buffer_requirements bufreq[HFI_BUFFER_TYPE_MAX];
 };
 
+#define IS_V1(core)	((core)->res->hfi_version == HFI_VERSION_1XX)
+#define IS_V3(core)	((core)->res->hfi_version == HFI_VERSION_3XX)
+#define IS_V4(core)	((core)->res->hfi_version == HFI_VERSION_4XX)
+
 #define ctrl_to_inst(ctrl)	\
 	container_of((ctrl)->handler, struct venus_inst, ctrl_handler)
 
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 0ce9559a2924..a08ecd263e73 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -166,21 +166,38 @@ static int intbufs_unset_buffers(struct venus_inst *inst)
 	return ret;
 }
 
-static const unsigned int intbuf_types[] = {
-	HFI_BUFFER_INTERNAL_SCRATCH,
-	HFI_BUFFER_INTERNAL_SCRATCH_1,
-	HFI_BUFFER_INTERNAL_SCRATCH_2,
+static const unsigned int intbuf_types_1xx[] = {
+	HFI_BUFFER_INTERNAL_SCRATCH(HFI_VERSION_1XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_1(HFI_VERSION_1XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_2(HFI_VERSION_1XX),
+	HFI_BUFFER_INTERNAL_PERSIST,
+	HFI_BUFFER_INTERNAL_PERSIST_1,
+};
+
+static const unsigned int intbuf_types_4xx[] = {
+	HFI_BUFFER_INTERNAL_SCRATCH(HFI_VERSION_4XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_1(HFI_VERSION_4XX),
+	HFI_BUFFER_INTERNAL_SCRATCH_2(HFI_VERSION_4XX),
 	HFI_BUFFER_INTERNAL_PERSIST,
 	HFI_BUFFER_INTERNAL_PERSIST_1,
 };
 
 static int intbufs_alloc(struct venus_inst *inst)
 {
-	unsigned int i;
+	const unsigned int *intbuf;
+	size_t arr_sz, i;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(intbuf_types); i++) {
-		ret = intbufs_set_buffer(inst, intbuf_types[i]);
+	if (IS_V4(inst->core)) {
+		arr_sz = ARRAY_SIZE(intbuf_types_4xx);
+		intbuf = intbuf_types_4xx;
+	} else {
+		arr_sz = ARRAY_SIZE(intbuf_types_1xx);
+		intbuf = intbuf_types_1xx;
+	}
+
+	for (i = 0; i < arr_sz; i++) {
+		ret = intbufs_set_buffer(inst, intbuf[i]);
 		if (ret)
 			goto error;
 	}
@@ -257,20 +274,23 @@ static int load_scale_clocks(struct venus_core *core)
 
 set_freq:
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
-		ret = clk_set_rate(clk, freq);
-		ret |= clk_set_rate(core->core0_clk, freq);
-		ret |= clk_set_rate(core->core1_clk, freq);
-	} else {
-		ret = clk_set_rate(clk, freq);
-	}
+	ret = clk_set_rate(clk, freq);
+	if (ret)
+		goto err;
 
-	if (ret) {
-		dev_err(dev, "failed to set clock rate %lu (%d)\n", freq, ret);
-		return ret;
-	}
+	ret = clk_set_rate(core->core0_clk, freq);
+	if (ret)
+		goto err;
+
+	ret = clk_set_rate(core->core1_clk, freq);
+	if (ret)
+		goto err;
 
 	return 0;
+
+err:
+	dev_err(dev, "failed to set clock rate %lu (%d)\n", freq, ret);
+	return ret;
 }
 
 static void fill_buffer_desc(const struct venus_buffer *buf,
diff --git a/drivers/media/platform/qcom/venus/hfi_helper.h b/drivers/media/platform/qcom/venus/hfi_helper.h
index 55d8eb21403a..f5f1557b1176 100644
--- a/drivers/media/platform/qcom/venus/hfi_helper.h
+++ b/drivers/media/platform/qcom/venus/hfi_helper.h
@@ -121,6 +121,7 @@
 #define HFI_EXTRADATA_METADATA_FILLER			0x7fe00002
 
 #define HFI_INDEX_EXTRADATA_INPUT_CROP			0x0700000e
+#define HFI_INDEX_EXTRADATA_OUTPUT_CROP			0x0700000f
 #define HFI_INDEX_EXTRADATA_DIGITAL_ZOOM		0x07000010
 #define HFI_INDEX_EXTRADATA_ASPECT_RATIO		0x7f100003
 
@@ -376,13 +377,18 @@
 #define HFI_BUFFER_OUTPUT2			0x3
 #define HFI_BUFFER_INTERNAL_PERSIST		0x4
 #define HFI_BUFFER_INTERNAL_PERSIST_1		0x5
-#define HFI_BUFFER_INTERNAL_SCRATCH		0x1000001
-#define HFI_BUFFER_EXTRADATA_INPUT		0x1000002
-#define HFI_BUFFER_EXTRADATA_OUTPUT		0x1000003
-#define HFI_BUFFER_EXTRADATA_OUTPUT2		0x1000004
-#define HFI_BUFFER_INTERNAL_SCRATCH_1		0x1000005
-#define HFI_BUFFER_INTERNAL_SCRATCH_2		0x1000006
-
+#define HFI_BUFFER_INTERNAL_SCRATCH(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0x6 : 0x1000001)
+#define HFI_BUFFER_INTERNAL_SCRATCH_1(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0x7 : 0x1000005)
+#define HFI_BUFFER_INTERNAL_SCRATCH_2(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0x8 : 0x1000006)
+#define HFI_BUFFER_EXTRADATA_INPUT(ver)		\
+	(((ver) == HFI_VERSION_4XX) ? 0xc : 0x1000002)
+#define HFI_BUFFER_EXTRADATA_OUTPUT(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0xa : 0x1000003)
+#define HFI_BUFFER_EXTRADATA_OUTPUT2(ver)	\
+	(((ver) == HFI_VERSION_4XX) ? 0xb : 0x1000004)
 #define HFI_BUFFER_TYPE_MAX			11
 
 #define HFI_BUFFER_MODE_STATIC			0x1000001
@@ -424,12 +430,14 @@
 #define HFI_PROPERTY_PARAM_CODEC_MASK_SUPPORTED			0x100e
 #define HFI_PROPERTY_PARAM_MVC_BUFFER_LAYOUT			0x100f
 #define HFI_PROPERTY_PARAM_MAX_SESSIONS_SUPPORTED		0x1010
+#define HFI_PROPERTY_PARAM_WORK_MODE				0x1015
 
 /*
  * HFI_PROPERTY_CONFIG_COMMON_START
  * HFI_DOMAIN_BASE_COMMON + HFI_ARCH_COMMON_OFFSET + 0x2000
  */
 #define HFI_PROPERTY_CONFIG_FRAME_RATE				0x2001
+#define HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE			0x2002
 
 /*
  * HFI_PROPERTY_PARAM_VDEC_COMMON_START
@@ -438,6 +446,9 @@
 #define HFI_PROPERTY_PARAM_VDEC_MULTI_STREAM			0x1003001
 #define HFI_PROPERTY_PARAM_VDEC_CONCEAL_COLOR			0x1003002
 #define HFI_PROPERTY_PARAM_VDEC_NONCP_OUTPUT2			0x1003003
+#define HFI_PROPERTY_PARAM_VDEC_PIXEL_BITDEPTH			0x1003007
+#define HFI_PROPERTY_PARAM_VDEC_PIC_STRUCT			0x1003009
+#define HFI_PROPERTY_PARAM_VDEC_COLOUR_SPACE			0x100300a
 
 /*
  * HFI_PROPERTY_CONFIG_VDEC_COMMON_START
@@ -518,6 +529,7 @@
 enum hfi_version {
 	HFI_VERSION_1XX,
 	HFI_VERSION_3XX,
+	HFI_VERSION_4XX
 };
 
 struct hfi_buffer_info {
@@ -767,6 +779,22 @@ struct hfi_framesize {
 	u32 height;
 };
 
+#define VIDC_CORE_ID_DEFAULT	0
+#define VIDC_CORE_ID_1		1
+#define VIDC_CORE_ID_2		2
+#define VIDC_CORE_ID_3		3
+
+struct hfi_videocores_usage_type {
+	u32 video_core_enable_mask;
+};
+
+#define VIDC_WORK_MODE_1	1
+#define VIDC_WORK_MODE_2	2
+
+struct hfi_video_work_mode {
+	u32 video_work_mode;
+};
+
 struct hfi_h264_vui_timing_info {
 	u32 enable;
 	u32 fixed_framerate;
@@ -961,6 +989,12 @@ struct hfi_buffer_count_actual {
 	u32 count_actual;
 };
 
+struct hfi_buffer_count_actual_4xx {
+	u32 type;
+	u32 count_actual;
+	u32 count_min_host;
+};
+
 struct hfi_buffer_size_actual {
 	u32 type;
 	u32 size;
@@ -971,6 +1005,14 @@ struct hfi_buffer_display_hold_count_actual {
 	u32 hold_count;
 };
 
+/* HFI 4XX reorder the fields, use these macros */
+#define HFI_BUFREQ_HOLD_COUNT(bufreq, ver)	\
+	((ver) == HFI_VERSION_4XX ? 0 : (bufreq)->hold_count)
+#define HFI_BUFREQ_COUNT_MIN(bufreq, ver)	\
+	((ver) == HFI_VERSION_4XX ? (bufreq)->hold_count : (bufreq)->count_min)
+#define HFI_BUFREQ_COUNT_MIN_HOST(bufreq, ver)	\
+	((ver) == HFI_VERSION_4XX ? (bufreq)->count_min : 0)
+
 struct hfi_buffer_requirements {
 	u32 type;
 	u32 size;
diff --git a/drivers/media/platform/qcom/venus/hfi_venus_io.h b/drivers/media/platform/qcom/venus/hfi_venus_io.h
index 98cc350113ab..d327b5cea334 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus_io.h
+++ b/drivers/media/platform/qcom/venus/hfi_venus_io.h
@@ -110,4 +110,11 @@
 #define WRAPPER_CPU_STATUS			(WRAPPER_BASE + 0x2014)
 #define WRAPPER_SW_RESET			(WRAPPER_BASE + 0x3000)
 
+/* Venus 4xx */
+#define WRAPPER_VCODEC0_MMCC_POWER_STATUS	(WRAPPER_BASE + 0x90)
+#define WRAPPER_VCODEC0_MMCC_POWER_CONTROL	(WRAPPER_BASE + 0x94)
+
+#define WRAPPER_VCODEC1_MMCC_POWER_STATUS	(WRAPPER_BASE + 0x110)
+#define WRAPPER_VCODEC1_MMCC_POWER_CONTROL	(WRAPPER_BASE + 0x114)
+
 #endif
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index f89a91d43cc9..6da0c4e832e0 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -687,6 +687,7 @@ static int vdec_queue_setup(struct vb2_queue *q,
 
 static int vdec_verify_conf(struct venus_inst *inst)
 {
+	enum hfi_version ver = inst->core->res->hfi_version;
 	struct hfi_buffer_requirements bufreq;
 	int ret;
 
@@ -698,14 +699,14 @@ static int vdec_verify_conf(struct venus_inst *inst)
 		return ret;
 
 	if (inst->num_output_bufs < bufreq.count_actual ||
-	    inst->num_output_bufs < bufreq.count_min)
+	    inst->num_output_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_INPUT, &bufreq);
 	if (ret)
 		return ret;
 
-	if (inst->num_input_bufs < bufreq.count_min)
+	if (inst->num_input_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	return 0;
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index f7a87a3dbb46..14bd95c52810 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -890,6 +890,7 @@ static int venc_queue_setup(struct vb2_queue *q,
 
 static int venc_verify_conf(struct venus_inst *inst)
 {
+	enum hfi_version ver = inst->core->res->hfi_version;
 	struct hfi_buffer_requirements bufreq;
 	int ret;
 
@@ -901,7 +902,7 @@ static int venc_verify_conf(struct venus_inst *inst)
 		return ret;
 
 	if (inst->num_output_bufs < bufreq.count_actual ||
-	    inst->num_output_bufs < bufreq.count_min)
+	    inst->num_output_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_INPUT, &bufreq);
@@ -909,7 +910,7 @@ static int venc_verify_conf(struct venus_inst *inst)
 		return ret;
 
 	if (inst->num_input_bufs < bufreq.count_actual ||
-	    inst->num_input_bufs < bufreq.count_min)
+	    inst->num_input_bufs < HFI_BUFREQ_COUNT_MIN(&bufreq, ver))
 		return -EINVAL;
 
 	return 0;
-- 
cgit v1.2.3


From 9eb2146ecb5f1617c8a2946f7a7d02968f4c01a2 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:37 -0400
Subject: media: venus: hfi: update sequence event to handle more properties

HFI version 4xx can pass more properties in the sequence change
event, extend the event structure with them.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi.h        | 10 ++++++
 drivers/media/platform/qcom/venus/hfi_helper.h | 28 ++++++++++++++++
 drivers/media/platform/qcom/venus/hfi_msgs.c   | 44 ++++++++++++++++++++++++++
 3 files changed, 82 insertions(+)

diff --git a/drivers/media/platform/qcom/venus/hfi.h b/drivers/media/platform/qcom/venus/hfi.h
index 5466b7d60dd0..6038d8e0ab22 100644
--- a/drivers/media/platform/qcom/venus/hfi.h
+++ b/drivers/media/platform/qcom/venus/hfi.h
@@ -74,6 +74,16 @@ struct hfi_event_data {
 	u32 tag;
 	u32 profile;
 	u32 level;
+	/* the following properties start appear from v4 onwards */
+	u32 bit_depth;
+	u32 pic_struct;
+	u32 colour_space;
+	u32 entropy_mode;
+	u32 buf_count;
+	struct {
+		u32 left, top;
+		u32 width, height;
+	} input_crop;
 };
 
 /* define core states */
diff --git a/drivers/media/platform/qcom/venus/hfi_helper.h b/drivers/media/platform/qcom/venus/hfi_helper.h
index f5f1557b1176..1bc5aab1ce6b 100644
--- a/drivers/media/platform/qcom/venus/hfi_helper.h
+++ b/drivers/media/platform/qcom/venus/hfi_helper.h
@@ -801,6 +801,34 @@ struct hfi_h264_vui_timing_info {
 	u32 time_scale;
 };
 
+struct hfi_bit_depth {
+	u32 buffer_type;
+	u32 bit_depth;
+};
+
+struct hfi_picture_type {
+	u32 is_sync_frame;
+	u32 picture_type;
+};
+
+struct hfi_pic_struct {
+	u32 progressive_only;
+};
+
+struct hfi_colour_space {
+	u32 colour_space;
+};
+
+struct hfi_extradata_input_crop {
+	u32 size;
+	u32 version;
+	u32 port_index;
+	u32 left;
+	u32 top;
+	u32 width;
+	u32 height;
+};
+
 #define HFI_COLOR_FORMAT_MONOCHROME		0x01
 #define HFI_COLOR_FORMAT_NV12			0x02
 #define HFI_COLOR_FORMAT_NV21			0x03
diff --git a/drivers/media/platform/qcom/venus/hfi_msgs.c b/drivers/media/platform/qcom/venus/hfi_msgs.c
index 589e1a6b36a9..54cd41e5837c 100644
--- a/drivers/media/platform/qcom/venus/hfi_msgs.c
+++ b/drivers/media/platform/qcom/venus/hfi_msgs.c
@@ -25,10 +25,16 @@
 static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 			      struct hfi_msg_event_notify_pkt *pkt)
 {
+	enum hfi_version ver = core->res->hfi_version;
 	struct hfi_event_data event = {0};
 	int num_properties_changed;
 	struct hfi_framesize *frame_sz;
 	struct hfi_profile_level *profile_level;
+	struct hfi_bit_depth *pixel_depth;
+	struct hfi_pic_struct *pic_struct;
+	struct hfi_colour_space *colour_info;
+	struct hfi_buffer_requirements *bufreq;
+	struct hfi_extradata_input_crop *crop;
 	u8 *data_ptr;
 	u32 ptype;
 
@@ -69,6 +75,44 @@ static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 			event.level = profile_level->level;
 			data_ptr += sizeof(*profile_level);
 			break;
+		case HFI_PROPERTY_PARAM_VDEC_PIXEL_BITDEPTH:
+			data_ptr += sizeof(u32);
+			pixel_depth = (struct hfi_bit_depth *)data_ptr;
+			event.bit_depth = pixel_depth->bit_depth;
+			data_ptr += sizeof(*pixel_depth);
+			break;
+		case HFI_PROPERTY_PARAM_VDEC_PIC_STRUCT:
+			data_ptr += sizeof(u32);
+			pic_struct = (struct hfi_pic_struct *)data_ptr;
+			event.pic_struct = pic_struct->progressive_only;
+			data_ptr += sizeof(*pic_struct);
+			break;
+		case HFI_PROPERTY_PARAM_VDEC_COLOUR_SPACE:
+			data_ptr += sizeof(u32);
+			colour_info = (struct hfi_colour_space *)data_ptr;
+			event.colour_space = colour_info->colour_space;
+			data_ptr += sizeof(*colour_info);
+			break;
+		case HFI_PROPERTY_CONFIG_VDEC_ENTROPY:
+			data_ptr += sizeof(u32);
+			event.entropy_mode = *(u32 *)data_ptr;
+			data_ptr += sizeof(u32);
+			break;
+		case HFI_PROPERTY_CONFIG_BUFFER_REQUIREMENTS:
+			data_ptr += sizeof(u32);
+			bufreq = (struct hfi_buffer_requirements *)data_ptr;
+			event.buf_count = HFI_BUFREQ_COUNT_MIN(bufreq, ver);
+			data_ptr += sizeof(*bufreq);
+			break;
+		case HFI_INDEX_EXTRADATA_INPUT_CROP:
+			data_ptr += sizeof(u32);
+			crop = (struct hfi_extradata_input_crop *)data_ptr;
+			event.input_crop.left = crop->left;
+			event.input_crop.top = crop->top;
+			event.input_crop.width = crop->width;
+			event.input_crop.height = crop->height;
+			data_ptr += sizeof(*crop);
+			break;
 		default:
 			break;
 		}
-- 
cgit v1.2.3


From 6b183680dd8b9ce0aca9ad5d4dd18b5861dcf59d Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:38 -0400
Subject: media: venus: hfi_cmds: add set_properties for 4xx version

Adds set_properties method to handle newer 4xx properties and
fall-back to 3xx for the rest.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi_cmds.c | 62 +++++++++++++++++++++++++++-
 1 file changed, 61 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/venus/hfi_cmds.c b/drivers/media/platform/qcom/venus/hfi_cmds.c
index 1cfeb7743041..e8389d8d8c48 100644
--- a/drivers/media/platform/qcom/venus/hfi_cmds.c
+++ b/drivers/media/platform/qcom/venus/hfi_cmds.c
@@ -1166,6 +1166,63 @@ pkt_session_set_property_3xx(struct hfi_session_set_property_pkt *pkt,
 	return ret;
 }
 
+static int
+pkt_session_set_property_4xx(struct hfi_session_set_property_pkt *pkt,
+			     void *cookie, u32 ptype, void *pdata)
+{
+	void *prop_data;
+
+	if (!pkt || !cookie || !pdata)
+		return -EINVAL;
+
+	prop_data = &pkt->data[1];
+
+	pkt->shdr.hdr.size = sizeof(*pkt);
+	pkt->shdr.hdr.pkt_type = HFI_CMD_SESSION_SET_PROPERTY;
+	pkt->shdr.session_id = hash32_ptr(cookie);
+	pkt->num_properties = 1;
+	pkt->data[0] = ptype;
+
+	/*
+	 * Any session set property which is different in 3XX packetization
+	 * should be added as a new case below. All unchanged session set
+	 * properties will be handled in the default case.
+	 */
+	switch (ptype) {
+	case HFI_PROPERTY_PARAM_BUFFER_COUNT_ACTUAL: {
+		struct hfi_buffer_count_actual *in = pdata;
+		struct hfi_buffer_count_actual_4xx *count = prop_data;
+
+		count->count_actual = in->count_actual;
+		count->type = in->type;
+		count->count_min_host = in->count_actual;
+		pkt->shdr.hdr.size += sizeof(u32) + sizeof(*count);
+		break;
+	}
+	case HFI_PROPERTY_PARAM_WORK_MODE: {
+		struct hfi_video_work_mode *in = pdata, *wm = prop_data;
+
+		wm->video_work_mode = in->video_work_mode;
+		pkt->shdr.hdr.size += sizeof(u32) + sizeof(*wm);
+		break;
+	}
+	case HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE: {
+		struct hfi_videocores_usage_type *in = pdata, *cu = prop_data;
+
+		cu->video_core_enable_mask = in->video_core_enable_mask;
+		pkt->shdr.hdr.size += sizeof(u32) + sizeof(*cu);
+		break;
+	}
+	case HFI_PROPERTY_CONFIG_VENC_MAX_BITRATE:
+		/* not implemented on Venus 4xx */
+		break;
+	default:
+		return pkt_session_set_property_3xx(pkt, cookie, ptype, pdata);
+	}
+
+	return 0;
+}
+
 int pkt_session_get_property(struct hfi_session_get_property_pkt *pkt,
 			     void *cookie, u32 ptype)
 {
@@ -1181,7 +1238,10 @@ int pkt_session_set_property(struct hfi_session_set_property_pkt *pkt,
 	if (hfi_ver == HFI_VERSION_1XX)
 		return pkt_session_set_property_1x(pkt, cookie, ptype, pdata);
 
-	return pkt_session_set_property_3xx(pkt, cookie, ptype, pdata);
+	if (hfi_ver == HFI_VERSION_3XX)
+		return pkt_session_set_property_3xx(pkt, cookie, ptype, pdata);
+
+	return pkt_session_set_property_4xx(pkt, cookie, ptype, pdata);
 }
 
 void pkt_set_version(enum hfi_version version)
-- 
cgit v1.2.3


From 2074b9bed635ce96f16847d75f653f3bdb9905a6 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:39 -0400
Subject: media: venus: hfi: support session continue for 4xx version

This makes possible to handle session_continue for 4xx as well.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/venus/hfi.c b/drivers/media/platform/qcom/venus/hfi.c
index bca894a00c07..cbc6fad05e47 100644
--- a/drivers/media/platform/qcom/venus/hfi.c
+++ b/drivers/media/platform/qcom/venus/hfi.c
@@ -312,7 +312,7 @@ int hfi_session_continue(struct venus_inst *inst)
 {
 	struct venus_core *core = inst->core;
 
-	if (core->res->hfi_version != HFI_VERSION_3XX)
+	if (core->res->hfi_version == HFI_VERSION_1XX)
 		return 0;
 
 	return core->ops->session_continue(inst);
-- 
cgit v1.2.3


From 5f43f90a99ade6db0c05e2bb45883256649c9164 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:40 -0400
Subject: media: venus: hfi: handle buffer output2 type as well

This adds handling of buffers of type OUTPUT2 which is needed to
support Venus 4xx version.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi.c      | 3 ++-
 drivers/media/platform/qcom/venus/hfi_msgs.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/hfi.c b/drivers/media/platform/qcom/venus/hfi.c
index cbc6fad05e47..a570fdad0de0 100644
--- a/drivers/media/platform/qcom/venus/hfi.c
+++ b/drivers/media/platform/qcom/venus/hfi.c
@@ -473,7 +473,8 @@ int hfi_session_process_buf(struct venus_inst *inst, struct hfi_frame_data *fd)
 
 	if (fd->buffer_type == HFI_BUFFER_INPUT)
 		return ops->session_etb(inst, fd);
-	else if (fd->buffer_type == HFI_BUFFER_OUTPUT)
+	else if (fd->buffer_type == HFI_BUFFER_OUTPUT ||
+		 fd->buffer_type == HFI_BUFFER_OUTPUT2)
 		return ops->session_ftb(inst, fd);
 
 	return -EINVAL;
diff --git a/drivers/media/platform/qcom/venus/hfi_msgs.c b/drivers/media/platform/qcom/venus/hfi_msgs.c
index 54cd41e5837c..c0f3bef8299f 100644
--- a/drivers/media/platform/qcom/venus/hfi_msgs.c
+++ b/drivers/media/platform/qcom/venus/hfi_msgs.c
@@ -823,7 +823,8 @@ static void hfi_session_ftb_done(struct venus_core *core,
 		error = HFI_ERR_SESSION_INVALID_PARAMETER;
 	}
 
-	if (buffer_type != HFI_BUFFER_OUTPUT)
+	if (buffer_type != HFI_BUFFER_OUTPUT &&
+	    buffer_type != HFI_BUFFER_OUTPUT2)
 		goto done;
 
 	if (hfi_flags & HFI_BUFFERFLAG_EOS)
-- 
cgit v1.2.3


From eb72356e7de23d744d89e8c9408607c0fd71368c Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:41 -0400
Subject: media: venus: hfi_venus: add halt AXI support for Venus 4xx

Add AXI halt support for version 4xx by using venus wrapper
registers.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi_venus.c    | 18 ++++++++++++++++++
 drivers/media/platform/qcom/venus/hfi_venus_io.h |  2 ++
 2 files changed, 20 insertions(+)

diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c
index 734ce11b0ed0..784b3ad1a9f6 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus.c
+++ b/drivers/media/platform/qcom/venus/hfi_venus.c
@@ -532,6 +532,24 @@ static int venus_halt_axi(struct venus_hfi_device *hdev)
 	u32 val;
 	int ret;
 
+	if (IS_V4(hdev->core)) {
+		val = venus_readl(hdev, WRAPPER_CPU_AXI_HALT);
+		val |= WRAPPER_CPU_AXI_HALT_HALT;
+		venus_writel(hdev, WRAPPER_CPU_AXI_HALT, val);
+
+		ret = readl_poll_timeout(base + WRAPPER_CPU_AXI_HALT_STATUS,
+					 val,
+					 val & WRAPPER_CPU_AXI_HALT_STATUS_IDLE,
+					 POLL_INTERVAL_US,
+					 VBIF_AXI_HALT_ACK_TIMEOUT_US);
+		if (ret) {
+			dev_err(dev, "AXI bus port halt timeout\n");
+			return ret;
+		}
+
+		return 0;
+	}
+
 	/* Halt AXI and AXI IMEM VBIF Access */
 	val = venus_readl(hdev, VBIF_AXI_HALT_CTRL0);
 	val |= VBIF_AXI_HALT_CTRL0_HALT_REQ;
diff --git a/drivers/media/platform/qcom/venus/hfi_venus_io.h b/drivers/media/platform/qcom/venus/hfi_venus_io.h
index d327b5cea334..c0b18de1e396 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus_io.h
+++ b/drivers/media/platform/qcom/venus/hfi_venus_io.h
@@ -104,7 +104,9 @@
 
 #define WRAPPER_CPU_CLOCK_CONFIG		(WRAPPER_BASE + 0x2000)
 #define WRAPPER_CPU_AXI_HALT			(WRAPPER_BASE + 0x2008)
+#define WRAPPER_CPU_AXI_HALT_HALT		BIT(16)
 #define WRAPPER_CPU_AXI_HALT_STATUS		(WRAPPER_BASE + 0x200c)
+#define WRAPPER_CPU_AXI_HALT_STATUS_IDLE	BIT(24)
 
 #define WRAPPER_CPU_CGC_DIS			(WRAPPER_BASE + 0x2010)
 #define WRAPPER_CPU_STATUS			(WRAPPER_BASE + 0x2014)
-- 
cgit v1.2.3


From bc897723467a7d56f1da81accc703429dcee5632 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:42 -0400
Subject: media: venus: hfi_venus: fix suspend function for venus 3xx versions

This fixes the suspend function for Venus 3xx versions by
add a check for WFI (wait for interrupt) bit. This bit
is on when the ARM9 is idle and entered in low power mode.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi_venus.c    | 72 ++++++++++++++++--------
 drivers/media/platform/qcom/venus/hfi_venus_io.h |  1 +
 2 files changed, 51 insertions(+), 22 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c
index 784b3ad1a9f6..72a8547eab39 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus.c
+++ b/drivers/media/platform/qcom/venus/hfi_venus.c
@@ -1444,13 +1444,40 @@ static int venus_suspend_1xx(struct venus_core *core)
 	return 0;
 }
 
+static bool venus_cpu_and_video_core_idle(struct venus_hfi_device *hdev)
+{
+	u32 ctrl_status, cpu_status;
+
+	cpu_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
+	ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
+
+	if (cpu_status & WRAPPER_CPU_STATUS_WFI &&
+	    ctrl_status & CPU_CS_SCIACMDARG0_INIT_IDLE_MSG_MASK)
+		return true;
+
+	return false;
+}
+
+static bool venus_cpu_idle_and_pc_ready(struct venus_hfi_device *hdev)
+{
+	u32 ctrl_status, cpu_status;
+
+	cpu_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
+	ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
+
+	if (cpu_status & WRAPPER_CPU_STATUS_WFI &&
+	    ctrl_status & CPU_CS_SCIACMDARG0_PC_READY)
+		return true;
+
+	return false;
+}
+
 static int venus_suspend_3xx(struct venus_core *core)
 {
 	struct venus_hfi_device *hdev = to_hfi_priv(core);
 	struct device *dev = core->dev;
-	u32 ctrl_status, wfi_status;
+	bool val;
 	int ret;
-	int cnt = 100;
 
 	if (!hdev->power_enabled || hdev->suspended)
 		return 0;
@@ -1464,29 +1491,30 @@ static int venus_suspend_3xx(struct venus_core *core)
 		return -EINVAL;
 	}
 
-	ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
-	if (!(ctrl_status & CPU_CS_SCIACMDARG0_PC_READY)) {
-		wfi_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
-		ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
-
-		ret = venus_prepare_power_collapse(hdev, false);
-		if (ret) {
-			dev_err(dev, "prepare for power collapse fail (%d)\n",
-				ret);
-			return ret;
-		}
+	/*
+	 * Power collapse sequence for Venus 3xx and 4xx versions:
+	 * 1. Check for ARM9 and video core to be idle by checking WFI bit
+	 *    (bit 0) in CPU status register and by checking Idle (bit 30) in
+	 *    Control status register for video core.
+	 * 2. Send a command to prepare for power collapse.
+	 * 3. Check for WFI and PC_READY bits.
+	 */
+	ret = readx_poll_timeout(venus_cpu_and_video_core_idle, hdev, val, val,
+				 1500, 100 * 1500);
+	if (ret)
+		return ret;
 
-		cnt = 100;
-		while (cnt--) {
-			wfi_status = venus_readl(hdev, WRAPPER_CPU_STATUS);
-			ctrl_status = venus_readl(hdev, CPU_CS_SCIACMDARG0);
-			if (ctrl_status & CPU_CS_SCIACMDARG0_PC_READY &&
-			    wfi_status & BIT(0))
-				break;
-			usleep_range(1000, 1500);
-		}
+	ret = venus_prepare_power_collapse(hdev, false);
+	if (ret) {
+		dev_err(dev, "prepare for power collapse fail (%d)\n", ret);
+		return ret;
 	}
 
+	ret = readx_poll_timeout(venus_cpu_idle_and_pc_ready, hdev, val, val,
+				 1500, 100 * 1500);
+	if (ret)
+		return ret;
+
 	mutex_lock(&hdev->lock);
 
 	ret = venus_power_off(hdev);
diff --git a/drivers/media/platform/qcom/venus/hfi_venus_io.h b/drivers/media/platform/qcom/venus/hfi_venus_io.h
index c0b18de1e396..def0926a6dee 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus_io.h
+++ b/drivers/media/platform/qcom/venus/hfi_venus_io.h
@@ -110,6 +110,7 @@
 
 #define WRAPPER_CPU_CGC_DIS			(WRAPPER_BASE + 0x2010)
 #define WRAPPER_CPU_STATUS			(WRAPPER_BASE + 0x2014)
+#define WRAPPER_CPU_STATUS_WFI			BIT(0)
 #define WRAPPER_SW_RESET			(WRAPPER_BASE + 0x3000)
 
 /* Venus 4xx */
-- 
cgit v1.2.3


From 4dde81d720dcd68e439081092035a24ee20fa09c Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:43 -0400
Subject: media: venus: hfi_venus: move set of default properties to core init

This moves setting of default properties (firmware debug, idle
indicator and low power mode) from session init to core init.
All of those properties are need to be enabled/disabled early
so that they could be used before the clients are even initialized.

The other reason is to set idle indicator property early before
we enter into venus_suspend function where we need to check for
ARM9 WFI.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi_venus.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c
index 72a8547eab39..7a83e967a8ea 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus.c
+++ b/drivers/media/platform/qcom/venus/hfi_venus.c
@@ -1091,6 +1091,10 @@ static int venus_core_init(struct venus_core *core)
 	if (ret)
 		dev_warn(dev, "failed to send image version pkt to fw\n");
 
+	ret = venus_sys_set_default_properties(hdev);
+	if (ret)
+		return ret;
+
 	return 0;
 }
 
@@ -1135,10 +1139,6 @@ static int venus_session_init(struct venus_inst *inst, u32 session_type,
 	struct hfi_session_init_pkt pkt;
 	int ret;
 
-	ret = venus_sys_set_default_properties(hdev);
-	if (ret)
-		return ret;
-
 	ret = pkt_session_init(&pkt, inst, session_type, codec);
 	if (ret)
 		goto err;
-- 
cgit v1.2.3


From 17cd3d1d2e5249c58510b0c8689c45cacc201480 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:44 -0400
Subject: media: venus: hfi_venus: add suspend functionality for Venus 4xx

This adds suspend (power collapse) functionality by reusing
the suspend function for Venus 3xx and also enables idle indicator
property for Venus 4xx (where it is disabled by default).

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/hfi_venus.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/venus/hfi_venus.c b/drivers/media/platform/qcom/venus/hfi_venus.c
index 7a83e967a8ea..124085556b94 100644
--- a/drivers/media/platform/qcom/venus/hfi_venus.c
+++ b/drivers/media/platform/qcom/venus/hfi_venus.c
@@ -879,6 +879,14 @@ static int venus_sys_set_default_properties(struct venus_hfi_device *hdev)
 	if (ret)
 		dev_warn(dev, "setting fw debug msg ON failed (%d)\n", ret);
 
+	/*
+	 * Idle indicator is disabled by default on some 4xx firmware versions,
+	 * enable it explicitly in order to make suspend functional by checking
+	 * WFI (wait-for-interrupt) bit.
+	 */
+	if (IS_V4(hdev->core))
+		venus_sys_idle_indicator = true;
+
 	ret = venus_sys_set_idle_message(hdev, venus_sys_idle_indicator);
 	if (ret)
 		dev_warn(dev, "setting idle response ON failed (%d)\n", ret);
@@ -1533,7 +1541,7 @@ static int venus_suspend_3xx(struct venus_core *core)
 
 static int venus_suspend(struct venus_core *core)
 {
-	if (core->res->hfi_version == HFI_VERSION_3XX)
+	if (IS_V3(core) || IS_V4(core))
 		return venus_suspend_3xx(core);
 
 	return venus_suspend_1xx(core);
-- 
cgit v1.2.3


From aa3a8414ccea5b9412419db11f5d76ae9a4997a4 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:45 -0400
Subject: media: venus: core, helpers: add two more clocks found in Venus 4xx

Add two more clocks for Venus 4xx in core structure and create
a new power enable function to handle it for 3xx/4xx versions.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/core.h    |  4 +++
 drivers/media/platform/qcom/venus/helpers.c | 51 +++++++++++++++++++++++++++++
 drivers/media/platform/qcom/venus/helpers.h |  2 ++
 drivers/media/platform/qcom/venus/vdec.c    | 44 ++++++++++++++++++++-----
 drivers/media/platform/qcom/venus/venc.c    | 44 ++++++++++++++++++++-----
 5 files changed, 129 insertions(+), 16 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index 8d3e150800c9..2bf8839784fa 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -65,6 +65,8 @@ struct venus_format {
  * @clks:	an array of struct clk pointers
  * @core0_clk:	a struct clk pointer for core0
  * @core1_clk:	a struct clk pointer for core1
+ * @core0_bus_clk: a struct clk pointer for core0 bus clock
+ * @core1_bus_clk: a struct clk pointer for core1 bus clock
  * @vdev_dec:	a reference to video device structure for decoder instances
  * @vdev_enc:	a reference to video device structure for encoder instances
  * @v4l2_dev:	a holder for v4l2 device structure
@@ -94,6 +96,8 @@ struct venus_core {
 	struct clk *clks[VIDC_CLKS_NUM_MAX];
 	struct clk *core0_clk;
 	struct clk *core1_clk;
+	struct clk *core0_bus_clk;
+	struct clk *core1_bus_clk;
 	struct video_device *vdev_dec;
 	struct video_device *vdev_enc;
 	struct v4l2_device v4l2_dev;
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index a08ecd263e73..c8c4a4be78e3 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -13,6 +13,7 @@
  *
  */
 #include <linux/clk.h>
+#include <linux/iopoll.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/pm_runtime.h>
@@ -24,6 +25,7 @@
 #include "core.h"
 #include "helpers.h"
 #include "hfi_helper.h"
+#include "hfi_venus_io.h"
 
 struct intbuf {
 	struct list_head list;
@@ -786,3 +788,52 @@ void venus_helper_init_instance(struct venus_inst *inst)
 	}
 }
 EXPORT_SYMBOL_GPL(venus_helper_init_instance);
+
+int venus_helper_power_enable(struct venus_core *core, u32 session_type,
+			      bool enable)
+{
+	void __iomem *ctrl, *stat;
+	u32 val;
+	int ret;
+
+	if (!IS_V3(core) && !IS_V4(core))
+		return 0;
+
+	if (IS_V3(core)) {
+		if (session_type == VIDC_SESSION_TYPE_DEC)
+			ctrl = core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL;
+		else
+			ctrl = core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL;
+		if (enable)
+			writel(0, ctrl);
+		else
+			writel(1, ctrl);
+
+		return 0;
+	}
+
+	if (session_type == VIDC_SESSION_TYPE_DEC) {
+		ctrl = core->base + WRAPPER_VCODEC0_MMCC_POWER_CONTROL;
+		stat = core->base + WRAPPER_VCODEC0_MMCC_POWER_STATUS;
+	} else {
+		ctrl = core->base + WRAPPER_VCODEC1_MMCC_POWER_CONTROL;
+		stat = core->base + WRAPPER_VCODEC1_MMCC_POWER_STATUS;
+	}
+
+	if (enable) {
+		writel(0, ctrl);
+
+		ret = readl_poll_timeout(stat, val, val & BIT(1), 1, 100);
+		if (ret)
+			return ret;
+	} else {
+		writel(1, ctrl);
+
+		ret = readl_poll_timeout(stat, val, !(val & BIT(1)), 1, 100);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(venus_helper_power_enable);
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 971392be5df5..0e64aa95624a 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -43,4 +43,6 @@ int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
 void venus_helper_acquire_buf_ref(struct vb2_v4l2_buffer *vbuf);
 void venus_helper_release_buf_ref(struct venus_inst *inst, unsigned int idx);
 void venus_helper_init_instance(struct venus_inst *inst);
+int venus_helper_power_enable(struct venus_core *core, u32 session_type,
+			      bool enable);
 #endif
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 6da0c4e832e0..0529976b4069 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -1079,12 +1079,18 @@ static int vdec_probe(struct platform_device *pdev)
 	if (!core)
 		return -EPROBE_DEFER;
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
+	if (IS_V3(core) || IS_V4(core)) {
 		core->core0_clk = devm_clk_get(dev, "core");
 		if (IS_ERR(core->core0_clk))
 			return PTR_ERR(core->core0_clk);
 	}
 
+	if (IS_V4(core)) {
+		core->core0_bus_clk = devm_clk_get(dev, "bus");
+		if (IS_ERR(core->core0_bus_clk))
+			return PTR_ERR(core->core0_bus_clk);
+	}
+
 	platform_set_drvdata(pdev, core);
 
 	vdev = video_device_alloc();
@@ -1129,15 +1135,21 @@ static int vdec_remove(struct platform_device *pdev)
 static __maybe_unused int vdec_runtime_suspend(struct device *dev)
 {
 	struct venus_core *core = dev_get_drvdata(dev);
+	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, true);
+	if (ret)
+		return ret;
+
+	if (IS_V4(core))
+		clk_disable_unprepare(core->core0_bus_clk);
+
 	clk_disable_unprepare(core->core0_clk);
-	writel(1, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
 
-	return 0;
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, false);
 }
 
 static __maybe_unused int vdec_runtime_resume(struct device *dev)
@@ -1145,13 +1157,29 @@ static __maybe_unused int vdec_runtime_resume(struct device *dev)
 	struct venus_core *core = dev_get_drvdata(dev);
 	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, true);
+	if (ret)
+		return ret;
+
 	ret = clk_prepare_enable(core->core0_clk);
-	writel(1, core->base + WRAPPER_VDEC_VCODEC_POWER_CONTROL);
+	if (ret)
+		goto err_power_disable;
+
+	if (IS_V4(core))
+		ret = clk_prepare_enable(core->core0_bus_clk);
 
+	if (ret)
+		goto err_unprepare_core0;
+
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, false);
+
+err_unprepare_core0:
+	clk_disable_unprepare(core->core0_clk);
+err_power_disable:
+	venus_helper_power_enable(core, VIDC_SESSION_TYPE_DEC, false);
 	return ret;
 }
 
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 14bd95c52810..7c6be9d37d99 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -1223,12 +1223,18 @@ static int venc_probe(struct platform_device *pdev)
 	if (!core)
 		return -EPROBE_DEFER;
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
+	if (IS_V3(core) || IS_V4(core)) {
 		core->core1_clk = devm_clk_get(dev, "core");
 		if (IS_ERR(core->core1_clk))
 			return PTR_ERR(core->core1_clk);
 	}
 
+	if (IS_V4(core)) {
+		core->core1_bus_clk = devm_clk_get(dev, "bus");
+		if (IS_ERR(core->core1_bus_clk))
+			return PTR_ERR(core->core1_bus_clk);
+	}
+
 	platform_set_drvdata(pdev, core);
 
 	vdev = video_device_alloc();
@@ -1273,15 +1279,21 @@ static int venc_remove(struct platform_device *pdev)
 static __maybe_unused int venc_runtime_suspend(struct device *dev)
 {
 	struct venus_core *core = dev_get_drvdata(dev);
+	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, true);
+	if (ret)
+		return ret;
+
+	if (IS_V4(core))
+		clk_disable_unprepare(core->core1_bus_clk);
+
 	clk_disable_unprepare(core->core1_clk);
-	writel(1, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
 
-	return 0;
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, false);
 }
 
 static __maybe_unused int venc_runtime_resume(struct device *dev)
@@ -1289,13 +1301,29 @@ static __maybe_unused int venc_runtime_resume(struct device *dev)
 	struct venus_core *core = dev_get_drvdata(dev);
 	int ret;
 
-	if (core->res->hfi_version == HFI_VERSION_1XX)
+	if (IS_V1(core))
 		return 0;
 
-	writel(0, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
+	ret = venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, true);
+	if (ret)
+		return ret;
+
 	ret = clk_prepare_enable(core->core1_clk);
-	writel(1, core->base + WRAPPER_VENC_VCODEC_POWER_CONTROL);
+	if (ret)
+		goto err_power_disable;
+
+	if (IS_V4(core))
+		ret = clk_prepare_enable(core->core1_bus_clk);
 
+	if (ret)
+		goto err_unprepare_core1;
+
+	return venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, false);
+
+err_unprepare_core1:
+	clk_disable_unprepare(core->core1_clk);
+err_power_disable:
+	venus_helper_power_enable(core, VIDC_SESSION_TYPE_ENC, false);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 1a73374a04e555103e5369429a30999114001dda Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Fri, 6 Jul 2018 08:47:58 -0400
Subject: media: venus: hfi_parser: add common capability parser

This adds common capability parser for all supported Venus
versions. Having it will help to enumerate better the supported
raw formats and codecs and also the capabilities for every
codec like max/min width/height, framerate, bitrate and so on.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/Makefile     |   3 +-
 drivers/media/platform/qcom/venus/core.c       |  85 ++++++
 drivers/media/platform/qcom/venus/core.h       |  74 ++---
 drivers/media/platform/qcom/venus/hfi.c        |   5 +-
 drivers/media/platform/qcom/venus/hfi_helper.h |  28 +-
 drivers/media/platform/qcom/venus/hfi_msgs.c   | 356 ++-----------------------
 drivers/media/platform/qcom/venus/hfi_parser.c | 283 ++++++++++++++++++++
 drivers/media/platform/qcom/venus/hfi_parser.h | 110 ++++++++
 drivers/media/platform/qcom/venus/vdec.c       |  38 +--
 drivers/media/platform/qcom/venus/venc.c       |  52 ++--
 10 files changed, 590 insertions(+), 444 deletions(-)
 create mode 100644 drivers/media/platform/qcom/venus/hfi_parser.c
 create mode 100644 drivers/media/platform/qcom/venus/hfi_parser.h

diff --git a/drivers/media/platform/qcom/venus/Makefile b/drivers/media/platform/qcom/venus/Makefile
index bfd4edf7c83f..b44b11b03e12 100644
--- a/drivers/media/platform/qcom/venus/Makefile
+++ b/drivers/media/platform/qcom/venus/Makefile
@@ -2,7 +2,8 @@
 # Makefile for Qualcomm Venus driver
 
 venus-core-objs += core.o helpers.o firmware.o \
-		   hfi_venus.o hfi_msgs.o hfi_cmds.o hfi.o
+		   hfi_venus.o hfi_msgs.o hfi_cmds.o hfi.o \
+		   hfi_parser.o
 
 venus-dec-objs += vdec.o vdec_ctrls.o
 venus-enc-objs += venc.o venc_ctrls.o
diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c
index 41eef376eb2d..381bfdd688db 100644
--- a/drivers/media/platform/qcom/venus/core.c
+++ b/drivers/media/platform/qcom/venus/core.c
@@ -152,6 +152,83 @@ static void venus_clks_disable(struct venus_core *core)
 		clk_disable_unprepare(core->clks[i]);
 }
 
+static u32 to_v4l2_codec_type(u32 codec)
+{
+	switch (codec) {
+	case HFI_VIDEO_CODEC_H264:
+		return V4L2_PIX_FMT_H264;
+	case HFI_VIDEO_CODEC_H263:
+		return V4L2_PIX_FMT_H263;
+	case HFI_VIDEO_CODEC_MPEG1:
+		return V4L2_PIX_FMT_MPEG1;
+	case HFI_VIDEO_CODEC_MPEG2:
+		return V4L2_PIX_FMT_MPEG2;
+	case HFI_VIDEO_CODEC_MPEG4:
+		return V4L2_PIX_FMT_MPEG4;
+	case HFI_VIDEO_CODEC_VC1:
+		return V4L2_PIX_FMT_VC1_ANNEX_G;
+	case HFI_VIDEO_CODEC_VP8:
+		return V4L2_PIX_FMT_VP8;
+	case HFI_VIDEO_CODEC_VP9:
+		return V4L2_PIX_FMT_VP9;
+	case HFI_VIDEO_CODEC_DIVX:
+	case HFI_VIDEO_CODEC_DIVX_311:
+		return V4L2_PIX_FMT_XVID;
+	default:
+		return 0;
+	}
+}
+
+static int venus_enumerate_codecs(struct venus_core *core, u32 type)
+{
+	const struct hfi_inst_ops dummy_ops = {};
+	struct venus_inst *inst;
+	u32 codec, codecs;
+	unsigned int i;
+	int ret;
+
+	if (core->res->hfi_version != HFI_VERSION_1XX)
+		return 0;
+
+	inst = kzalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	mutex_init(&inst->lock);
+	inst->core = core;
+	inst->session_type = type;
+	if (type == VIDC_SESSION_TYPE_DEC)
+		codecs = core->dec_codecs;
+	else
+		codecs = core->enc_codecs;
+
+	ret = hfi_session_create(inst, &dummy_ops);
+	if (ret)
+		goto err;
+
+	for (i = 0; i < MAX_CODEC_NUM; i++) {
+		codec = (1 << i) & codecs;
+		if (!codec)
+			continue;
+
+		ret = hfi_session_init(inst, to_v4l2_codec_type(codec));
+		if (ret)
+			goto done;
+
+		ret = hfi_session_deinit(inst);
+		if (ret)
+			goto done;
+	}
+
+done:
+	hfi_session_destroy(inst);
+err:
+	mutex_destroy(&inst->lock);
+	kfree(inst);
+
+	return ret;
+}
+
 static int venus_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -219,6 +296,14 @@ static int venus_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_venus_shutdown;
 
+	ret = venus_enumerate_codecs(core, VIDC_SESSION_TYPE_DEC);
+	if (ret)
+		goto err_venus_shutdown;
+
+	ret = venus_enumerate_codecs(core, VIDC_SESSION_TYPE_ENC);
+	if (ret)
+		goto err_venus_shutdown;
+
 	ret = v4l2_device_register(dev, &core->v4l2_dev);
 	if (ret)
 		goto err_core_deinit;
diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index 2bf8839784fa..b995d1601c87 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -57,6 +57,30 @@ struct venus_format {
 	u32 type;
 };
 
+#define MAX_PLANES		4
+#define MAX_FMT_ENTRIES		32
+#define MAX_CAP_ENTRIES		32
+#define MAX_ALLOC_MODE_ENTRIES	16
+#define MAX_CODEC_NUM		32
+
+struct raw_formats {
+	u32 buftype;
+	u32 fmt;
+};
+
+struct venus_caps {
+	u32 codec;
+	u32 domain;
+	bool cap_bufs_mode_dynamic;
+	unsigned int num_caps;
+	struct hfi_capability caps[MAX_CAP_ENTRIES];
+	unsigned int num_pl;
+	struct hfi_profile_level pl[HFI_MAX_PROFILE_COUNT];
+	unsigned int num_fmts;
+	struct raw_formats fmts[MAX_FMT_ENTRIES];
+	bool valid;	/* used only for Venus v1xx */
+};
+
 /**
  * struct venus_core - holds core parameters valid for all instances
  *
@@ -113,8 +137,8 @@ struct venus_core {
 	unsigned int error;
 	bool sys_error;
 	const struct hfi_core_ops *core_ops;
-	u32 enc_codecs;
-	u32 dec_codecs;
+	unsigned long enc_codecs;
+	unsigned long dec_codecs;
 	unsigned int max_sessions_supported;
 #define ENC_ROTATION_CAPABILITY		0x1
 #define ENC_SCALING_CAPABILITY		0x2
@@ -124,6 +148,8 @@ struct venus_core {
 	void *priv;
 	const struct hfi_ops *ops;
 	struct delayed_work work;
+	struct venus_caps caps[MAX_CODEC_NUM];
+	unsigned int codecs_count;
 };
 
 struct vdec_controls {
@@ -216,6 +242,7 @@ struct venus_buffer {
  * @reconfig:	a flag raised by decoder when the stream resolution changed
  * @reconfig_width:	holds the new width
  * @reconfig_height:	holds the new height
+ * @hfi_codec:		current codec for this instance in HFI space
  * @sequence_cap:	a sequence counter for capture queue
  * @sequence_out:	a sequence counter for output queue
  * @m2m_dev:	a reference to m2m device structure
@@ -228,22 +255,8 @@ struct venus_buffer {
  * @priv:	a private for HFI operations callbacks
  * @session_type:	the type of the session (decoder or encoder)
  * @hprop:	a union used as a holder by get property
- * @cap_width:	width capability
- * @cap_height:	height capability
- * @cap_mbs_per_frame:	macroblocks per frame capability
- * @cap_mbs_per_sec:	macroblocks per second capability
- * @cap_framerate:	framerate capability
- * @cap_scale_x:		horizontal scaling capability
- * @cap_scale_y:		vertical scaling capability
- * @cap_bitrate:		bitrate capability
- * @cap_hier_p:		hier capability
- * @cap_ltr_count:	LTR count capability
- * @cap_secure_output2_threshold: secure OUTPUT2 threshold capability
  * @cap_bufs_mode_static:	buffers allocation mode capability
  * @cap_bufs_mode_dynamic:	buffers allocation mode capability
- * @pl_count:	count of supported profiles/levels
- * @pl:		supported profiles/levels
- * @bufreq:	holds buffer requirements
  */
 struct venus_inst {
 	struct list_head list;
@@ -280,6 +293,7 @@ struct venus_inst {
 	bool reconfig;
 	u32 reconfig_width;
 	u32 reconfig_height;
+	u32 hfi_codec;
 	u32 sequence_cap;
 	u32 sequence_out;
 	struct v4l2_m2m_dev *m2m_dev;
@@ -291,22 +305,8 @@ struct venus_inst {
 	const struct hfi_inst_ops *ops;
 	u32 session_type;
 	union hfi_get_property hprop;
-	struct hfi_capability cap_width;
-	struct hfi_capability cap_height;
-	struct hfi_capability cap_mbs_per_frame;
-	struct hfi_capability cap_mbs_per_sec;
-	struct hfi_capability cap_framerate;
-	struct hfi_capability cap_scale_x;
-	struct hfi_capability cap_scale_y;
-	struct hfi_capability cap_bitrate;
-	struct hfi_capability cap_hier_p;
-	struct hfi_capability cap_ltr_count;
-	struct hfi_capability cap_secure_output2_threshold;
 	bool cap_bufs_mode_static;
 	bool cap_bufs_mode_dynamic;
-	unsigned int pl_count;
-	struct hfi_profile_level pl[HFI_MAX_PROFILE_COUNT];
-	struct hfi_buffer_requirements bufreq[HFI_BUFFER_TYPE_MAX];
 };
 
 #define IS_V1(core)	((core)->res->hfi_version == HFI_VERSION_1XX)
@@ -326,4 +326,18 @@ static inline void *to_hfi_priv(struct venus_core *core)
 	return core->priv;
 }
 
+static inline struct venus_caps *
+venus_caps_by_codec(struct venus_core *core, u32 codec, u32 domain)
+{
+	unsigned int c;
+
+	for (c = 0; c < core->codecs_count; c++) {
+		if (core->caps[c].codec == codec &&
+		    core->caps[c].domain == domain)
+			return &core->caps[c];
+	}
+
+	return NULL;
+}
+
 #endif
diff --git a/drivers/media/platform/qcom/venus/hfi.c b/drivers/media/platform/qcom/venus/hfi.c
index a570fdad0de0..94ca27b0bb99 100644
--- a/drivers/media/platform/qcom/venus/hfi.c
+++ b/drivers/media/platform/qcom/venus/hfi.c
@@ -203,13 +203,12 @@ int hfi_session_init(struct venus_inst *inst, u32 pixfmt)
 {
 	struct venus_core *core = inst->core;
 	const struct hfi_ops *ops = core->ops;
-	u32 codec;
 	int ret;
 
-	codec = to_codec_type(pixfmt);
+	inst->hfi_codec = to_codec_type(pixfmt);
 	reinit_completion(&inst->done);
 
-	ret = ops->session_init(inst, inst->session_type, codec);
+	ret = ops->session_init(inst, inst->session_type, inst->hfi_codec);
 	if (ret)
 		return ret;
 
diff --git a/drivers/media/platform/qcom/venus/hfi_helper.h b/drivers/media/platform/qcom/venus/hfi_helper.h
index 1bc5aab1ce6b..15804ad7e65d 100644
--- a/drivers/media/platform/qcom/venus/hfi_helper.h
+++ b/drivers/media/platform/qcom/venus/hfi_helper.h
@@ -858,10 +858,23 @@ struct hfi_uncompressed_format_select {
 	u32 format;
 };
 
+struct hfi_uncompressed_plane_constraints {
+	u32 stride_multiples;
+	u32 max_stride;
+	u32 min_plane_buffer_height_multiple;
+	u32 buffer_alignment;
+};
+
+struct hfi_uncompressed_plane_info {
+	u32 format;
+	u32 num_planes;
+	struct hfi_uncompressed_plane_constraints plane_constraints[1];
+};
+
 struct hfi_uncompressed_format_supported {
 	u32 buffer_type;
 	u32 format_entries;
-	u32 format_info[1];
+	struct hfi_uncompressed_plane_info plane_info[1];
 };
 
 struct hfi_uncompressed_plane_actual {
@@ -875,19 +888,6 @@ struct hfi_uncompressed_plane_actual_info {
 	struct hfi_uncompressed_plane_actual plane_format[1];
 };
 
-struct hfi_uncompressed_plane_constraints {
-	u32 stride_multiples;
-	u32 max_stride;
-	u32 min_plane_buffer_height_multiple;
-	u32 buffer_alignment;
-};
-
-struct hfi_uncompressed_plane_info {
-	u32 format;
-	u32 num_planes;
-	struct hfi_uncompressed_plane_constraints plane_format[1];
-};
-
 struct hfi_uncompressed_plane_actual_constraints_info {
 	u32 buffer_type;
 	u32 num_planes;
diff --git a/drivers/media/platform/qcom/venus/hfi_msgs.c b/drivers/media/platform/qcom/venus/hfi_msgs.c
index c0f3bef8299f..0ecdaa15c296 100644
--- a/drivers/media/platform/qcom/venus/hfi_msgs.c
+++ b/drivers/media/platform/qcom/venus/hfi_msgs.c
@@ -21,6 +21,7 @@
 #include "hfi.h"
 #include "hfi_helper.h"
 #include "hfi_msgs.h"
+#include "hfi_parser.h"
 
 static void event_seq_changed(struct venus_core *core, struct venus_inst *inst,
 			      struct hfi_msg_event_notify_pkt *pkt)
@@ -217,81 +218,28 @@ static void hfi_sys_init_done(struct venus_core *core, struct venus_inst *inst,
 			      void *packet)
 {
 	struct hfi_msg_sys_init_done_pkt *pkt = packet;
-	u32 rem_bytes, read_bytes = 0, num_properties;
-	u32 error, ptype;
-	u8 *data;
+	int rem_bytes;
+	u32 error;
 
 	error = pkt->error_type;
 	if (error != HFI_ERR_NONE)
-		goto err_no_prop;
-
-	num_properties = pkt->num_properties;
+		goto done;
 
-	if (!num_properties) {
+	if (!pkt->num_properties) {
 		error = HFI_ERR_SYS_INVALID_PARAMETER;
-		goto err_no_prop;
+		goto done;
 	}
 
 	rem_bytes = pkt->hdr.size - sizeof(*pkt) + sizeof(u32);
-
-	if (!rem_bytes) {
+	if (rem_bytes <= 0) {
 		/* missing property data */
 		error = HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
-		goto err_no_prop;
+		goto done;
 	}
 
-	data = (u8 *)&pkt->data[0];
-
-	if (core->res->hfi_version == HFI_VERSION_3XX)
-		goto err_no_prop;
-
-	while (num_properties && rem_bytes >= sizeof(u32)) {
-		ptype = *((u32 *)data);
-		data += sizeof(u32);
-
-		switch (ptype) {
-		case HFI_PROPERTY_PARAM_CODEC_SUPPORTED: {
-			struct hfi_codec_supported *prop;
-
-			prop = (struct hfi_codec_supported *)data;
-
-			if (rem_bytes < sizeof(*prop)) {
-				error = HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
-				break;
-			}
-
-			read_bytes += sizeof(*prop) + sizeof(u32);
-			core->dec_codecs = prop->dec_codecs;
-			core->enc_codecs = prop->enc_codecs;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_MAX_SESSIONS_SUPPORTED: {
-			struct hfi_max_sessions_supported *prop;
-
-			if (rem_bytes < sizeof(*prop)) {
-				error = HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
-				break;
-			}
-
-			prop = (struct hfi_max_sessions_supported *)data;
-			read_bytes += sizeof(*prop) + sizeof(u32);
-			core->max_sessions_supported = prop->max_sessions;
-			break;
-		}
-		default:
-			error = HFI_ERR_SYS_INVALID_PARAMETER;
-			break;
-		}
-
-		if (error)
-			break;
+	error = hfi_parser(core, inst, pkt->data, rem_bytes);
 
-		rem_bytes -= read_bytes;
-		data += read_bytes;
-		num_properties--;
-	}
-
-err_no_prop:
+done:
 	core->error = error;
 	complete(&core->done);
 }
@@ -369,51 +317,6 @@ static void hfi_sys_pc_prepare_done(struct venus_core *core,
 	dev_dbg(core->dev, "pc prepare done (error %x)\n", pkt->error_type);
 }
 
-static void
-hfi_copy_cap_prop(struct hfi_capability *in, struct venus_inst *inst)
-{
-	if (!in || !inst)
-		return;
-
-	switch (in->capability_type) {
-	case HFI_CAPABILITY_FRAME_WIDTH:
-		inst->cap_width = *in;
-		break;
-	case HFI_CAPABILITY_FRAME_HEIGHT:
-		inst->cap_height = *in;
-		break;
-	case HFI_CAPABILITY_MBS_PER_FRAME:
-		inst->cap_mbs_per_frame = *in;
-		break;
-	case HFI_CAPABILITY_MBS_PER_SECOND:
-		inst->cap_mbs_per_sec = *in;
-		break;
-	case HFI_CAPABILITY_FRAMERATE:
-		inst->cap_framerate = *in;
-		break;
-	case HFI_CAPABILITY_SCALE_X:
-		inst->cap_scale_x = *in;
-		break;
-	case HFI_CAPABILITY_SCALE_Y:
-		inst->cap_scale_y = *in;
-		break;
-	case HFI_CAPABILITY_BITRATE:
-		inst->cap_bitrate = *in;
-		break;
-	case HFI_CAPABILITY_HIER_P_NUM_ENH_LAYERS:
-		inst->cap_hier_p = *in;
-		break;
-	case HFI_CAPABILITY_ENC_LTR_COUNT:
-		inst->cap_ltr_count = *in;
-		break;
-	case HFI_CAPABILITY_CP_OUTPUT2_THRESH:
-		inst->cap_secure_output2_threshold = *in;
-		break;
-	default:
-		break;
-	}
-}
-
 static unsigned int
 session_get_prop_profile_level(struct hfi_msg_session_property_info_pkt *pkt,
 			       struct hfi_profile_level *profile_level)
@@ -503,248 +406,27 @@ done:
 	complete(&inst->done);
 }
 
-static u32 init_done_read_prop(struct venus_core *core, struct venus_inst *inst,
-			       struct hfi_msg_session_init_done_pkt *pkt)
-{
-	struct device *dev = core->dev;
-	u32 rem_bytes, num_props;
-	u32 ptype, next_offset = 0;
-	u32 err;
-	u8 *data;
-
-	rem_bytes = pkt->shdr.hdr.size - sizeof(*pkt) + sizeof(u32);
-	if (!rem_bytes) {
-		dev_err(dev, "%s: missing property info\n", __func__);
-		return HFI_ERR_SESSION_INSUFFICIENT_RESOURCES;
-	}
-
-	err = pkt->error_type;
-	if (err)
-		return err;
-
-	data = (u8 *)&pkt->data[0];
-	num_props = pkt->num_properties;
-
-	while (err == HFI_ERR_NONE && num_props && rem_bytes >= sizeof(u32)) {
-		ptype = *((u32 *)data);
-		next_offset = sizeof(u32);
-
-		switch (ptype) {
-		case HFI_PROPERTY_PARAM_CODEC_MASK_SUPPORTED: {
-			struct hfi_codec_mask_supported *masks =
-				(struct hfi_codec_mask_supported *)
-				(data + next_offset);
-
-			next_offset += sizeof(*masks);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_CAPABILITY_SUPPORTED: {
-			struct hfi_capabilities *caps;
-			struct hfi_capability *cap;
-			u32 num_caps;
-
-			if ((rem_bytes - next_offset) < sizeof(*cap)) {
-				err = HFI_ERR_SESSION_INVALID_PARAMETER;
-				break;
-			}
-
-			caps = (struct hfi_capabilities *)(data + next_offset);
-
-			num_caps = caps->num_capabilities;
-			cap = &caps->data[0];
-			next_offset += sizeof(u32);
-
-			while (num_caps &&
-			       (rem_bytes - next_offset) >= sizeof(u32)) {
-				hfi_copy_cap_prop(cap, inst);
-				cap++;
-				next_offset += sizeof(*cap);
-				num_caps--;
-			}
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SUPPORTED: {
-			struct hfi_uncompressed_format_supported *prop =
-				(struct hfi_uncompressed_format_supported *)
-				(data + next_offset);
-			u32 num_fmt_entries;
-			u8 *fmt;
-			struct hfi_uncompressed_plane_info *inf;
-
-			if ((rem_bytes - next_offset) < sizeof(*prop)) {
-				err = HFI_ERR_SESSION_INVALID_PARAMETER;
-				break;
-			}
-
-			num_fmt_entries = prop->format_entries;
-			next_offset = sizeof(*prop) - sizeof(u32);
-			fmt = (u8 *)&prop->format_info[0];
-
-			dev_dbg(dev, "uncomm format support num entries:%u\n",
-				num_fmt_entries);
-
-			while (num_fmt_entries) {
-				struct hfi_uncompressed_plane_constraints *cnts;
-				u32 bytes_to_skip;
-
-				inf = (struct hfi_uncompressed_plane_info *)fmt;
-
-				if ((rem_bytes - next_offset) < sizeof(*inf)) {
-					err = HFI_ERR_SESSION_INVALID_PARAMETER;
-					break;
-				}
-
-				dev_dbg(dev, "plane info: fmt:%x, planes:%x\n",
-					inf->format, inf->num_planes);
-
-				cnts = &inf->plane_format[0];
-				dev_dbg(dev, "%u %u %u %u\n",
-					cnts->stride_multiples,
-					cnts->max_stride,
-					cnts->min_plane_buffer_height_multiple,
-					cnts->buffer_alignment);
-
-				bytes_to_skip = sizeof(*inf) - sizeof(*cnts) +
-						inf->num_planes * sizeof(*cnts);
-
-				fmt += bytes_to_skip;
-				next_offset += bytes_to_skip;
-				num_fmt_entries--;
-			}
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_PROPERTIES_SUPPORTED: {
-			struct hfi_properties_supported *prop =
-				(struct hfi_properties_supported *)
-				(data + next_offset);
-
-			next_offset += sizeof(*prop) - sizeof(u32)
-					+ prop->num_properties * sizeof(u32);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_SUPPORTED: {
-			struct hfi_profile_level_supported *prop =
-				(struct hfi_profile_level_supported *)
-				(data + next_offset);
-			struct hfi_profile_level *pl;
-			unsigned int prop_count = 0;
-			unsigned int count = 0;
-			u8 *ptr;
-
-			ptr = (u8 *)&prop->profile_level[0];
-			prop_count = prop->profile_count;
-
-			if (prop_count > HFI_MAX_PROFILE_COUNT)
-				prop_count = HFI_MAX_PROFILE_COUNT;
-
-			while (prop_count) {
-				ptr++;
-				pl = (struct hfi_profile_level *)ptr;
-
-				inst->pl[count].profile = pl->profile;
-				inst->pl[count].level = pl->level;
-				prop_count--;
-				count++;
-				ptr += sizeof(*pl) / sizeof(u32);
-			}
-
-			inst->pl_count = count;
-			next_offset += sizeof(*prop) - sizeof(*pl) +
-				       prop->profile_count * sizeof(*pl);
-
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_INTERLACE_FORMAT_SUPPORTED: {
-			next_offset +=
-				sizeof(struct hfi_interlace_format_supported);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_NAL_STREAM_FORMAT_SUPPORTED: {
-			struct hfi_nal_stream_format *nal =
-				(struct hfi_nal_stream_format *)
-				(data + next_offset);
-			dev_dbg(dev, "NAL format: %x\n", nal->format);
-			next_offset += sizeof(*nal);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_NAL_STREAM_FORMAT_SELECT: {
-			next_offset += sizeof(u32);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_MAX_SEQUENCE_HEADER_SIZE: {
-			u32 *max_seq_sz = (u32 *)(data + next_offset);
-
-			dev_dbg(dev, "max seq header sz: %x\n", *max_seq_sz);
-			next_offset += sizeof(u32);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_VENC_INTRA_REFRESH: {
-			next_offset += sizeof(struct hfi_intra_refresh);
-			num_props--;
-			break;
-		}
-		case HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE_SUPPORTED: {
-			struct hfi_buffer_alloc_mode_supported *prop =
-				(struct hfi_buffer_alloc_mode_supported *)
-				(data + next_offset);
-			unsigned int i;
-
-			for (i = 0; i < prop->num_entries; i++) {
-				if (prop->buffer_type == HFI_BUFFER_OUTPUT ||
-				    prop->buffer_type == HFI_BUFFER_OUTPUT2) {
-					switch (prop->data[i]) {
-					case HFI_BUFFER_MODE_STATIC:
-						inst->cap_bufs_mode_static = true;
-						break;
-					case HFI_BUFFER_MODE_DYNAMIC:
-						inst->cap_bufs_mode_dynamic = true;
-						break;
-					default:
-						break;
-					}
-				}
-			}
-			next_offset += sizeof(*prop) -
-				sizeof(u32) + prop->num_entries * sizeof(u32);
-			num_props--;
-			break;
-		}
-		default:
-			dev_dbg(dev, "%s: default case %#x\n", __func__, ptype);
-			break;
-		}
-
-		rem_bytes -= next_offset;
-		data += next_offset;
-	}
-
-	return err;
-}
-
 static void hfi_session_init_done(struct venus_core *core,
 				  struct venus_inst *inst, void *packet)
 {
 	struct hfi_msg_session_init_done_pkt *pkt = packet;
-	unsigned int error;
+	int rem_bytes;
+	u32 error;
 
 	error = pkt->error_type;
 	if (error != HFI_ERR_NONE)
 		goto done;
 
-	if (core->res->hfi_version != HFI_VERSION_1XX)
+	if (!IS_V1(core))
 		goto done;
 
-	error = init_done_read_prop(core, inst, pkt);
+	rem_bytes = pkt->shdr.hdr.size - sizeof(*pkt) + sizeof(u32);
+	if (rem_bytes <= 0) {
+		error = HFI_ERR_SESSION_INSUFFICIENT_RESOURCES;
+		goto done;
+	}
 
+	error = hfi_parser(core, inst, pkt->data, rem_bytes);
 done:
 	inst->error = error;
 	complete(&inst->done);
diff --git a/drivers/media/platform/qcom/venus/hfi_parser.c b/drivers/media/platform/qcom/venus/hfi_parser.c
new file mode 100644
index 000000000000..afc0db3b5dc3
--- /dev/null
+++ b/drivers/media/platform/qcom/venus/hfi_parser.c
@@ -0,0 +1,283 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Linaro Ltd.
+ *
+ * Author: Stanimir Varbanov <stanimir.varbanov@linaro.org>
+ */
+#include <linux/bitops.h>
+#include <linux/kernel.h>
+
+#include "core.h"
+#include "hfi_helper.h"
+#include "hfi_parser.h"
+
+typedef void (*func)(struct venus_caps *cap, const void *data,
+		     unsigned int size);
+
+static void init_codecs(struct venus_core *core)
+{
+	struct venus_caps *caps = core->caps, *cap;
+	unsigned long bit;
+
+	for_each_set_bit(bit, &core->dec_codecs, MAX_CODEC_NUM) {
+		cap = &caps[core->codecs_count++];
+		cap->codec = BIT(bit);
+		cap->domain = VIDC_SESSION_TYPE_DEC;
+		cap->valid = false;
+	}
+
+	for_each_set_bit(bit, &core->enc_codecs, MAX_CODEC_NUM) {
+		cap = &caps[core->codecs_count++];
+		cap->codec = BIT(bit);
+		cap->domain = VIDC_SESSION_TYPE_ENC;
+		cap->valid = false;
+	}
+}
+
+static void for_each_codec(struct venus_caps *caps, unsigned int caps_num,
+			   u32 codecs, u32 domain, func cb, void *data,
+			   unsigned int size)
+{
+	struct venus_caps *cap;
+	unsigned int i;
+
+	for (i = 0; i < caps_num; i++) {
+		cap = &caps[i];
+		if (cap->valid && cap->domain == domain)
+			continue;
+		if (cap->codec & codecs && cap->domain == domain)
+			cb(cap, data, size);
+	}
+}
+
+static void
+fill_buf_mode(struct venus_caps *cap, const void *data, unsigned int num)
+{
+	const u32 *type = data;
+
+	if (*type == HFI_BUFFER_MODE_DYNAMIC)
+		cap->cap_bufs_mode_dynamic = true;
+}
+
+static void
+parse_alloc_mode(struct venus_core *core, struct venus_inst *inst, u32 codecs,
+		 u32 domain, void *data)
+{
+	struct hfi_buffer_alloc_mode_supported *mode = data;
+	u32 num_entries = mode->num_entries;
+	u32 *type;
+
+	if (num_entries > MAX_ALLOC_MODE_ENTRIES)
+		return;
+
+	type = mode->data;
+
+	while (num_entries--) {
+		if (mode->buffer_type == HFI_BUFFER_OUTPUT ||
+		    mode->buffer_type == HFI_BUFFER_OUTPUT2) {
+			if (*type == HFI_BUFFER_MODE_DYNAMIC && inst)
+				inst->cap_bufs_mode_dynamic = true;
+
+			for_each_codec(core->caps, ARRAY_SIZE(core->caps),
+				       codecs, domain, fill_buf_mode, type, 1);
+		}
+
+		type++;
+	}
+}
+
+static void fill_profile_level(struct venus_caps *cap, const void *data,
+			       unsigned int num)
+{
+	const struct hfi_profile_level *pl = data;
+
+	memcpy(&cap->pl[cap->num_pl], pl, num * sizeof(*pl));
+	cap->num_pl += num;
+}
+
+static void
+parse_profile_level(struct venus_core *core, u32 codecs, u32 domain, void *data)
+{
+	struct hfi_profile_level_supported *pl = data;
+	struct hfi_profile_level *proflevel = pl->profile_level;
+	struct hfi_profile_level pl_arr[HFI_MAX_PROFILE_COUNT] = {};
+
+	if (pl->profile_count > HFI_MAX_PROFILE_COUNT)
+		return;
+
+	memcpy(pl_arr, proflevel, pl->profile_count * sizeof(*proflevel));
+
+	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
+		       fill_profile_level, pl_arr, pl->profile_count);
+}
+
+static void
+fill_caps(struct venus_caps *cap, const void *data, unsigned int num)
+{
+	const struct hfi_capability *caps = data;
+
+	memcpy(&cap->caps[cap->num_caps], caps, num * sizeof(*caps));
+	cap->num_caps += num;
+}
+
+static void
+parse_caps(struct venus_core *core, u32 codecs, u32 domain, void *data)
+{
+	struct hfi_capabilities *caps = data;
+	struct hfi_capability *cap = caps->data;
+	u32 num_caps = caps->num_capabilities;
+	struct hfi_capability caps_arr[MAX_CAP_ENTRIES] = {};
+
+	if (num_caps > MAX_CAP_ENTRIES)
+		return;
+
+	memcpy(caps_arr, cap, num_caps * sizeof(*cap));
+
+	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
+		       fill_caps, caps_arr, num_caps);
+}
+
+static void fill_raw_fmts(struct venus_caps *cap, const void *fmts,
+			  unsigned int num_fmts)
+{
+	const struct raw_formats *formats = fmts;
+
+	memcpy(&cap->fmts[cap->num_fmts], formats, num_fmts * sizeof(*formats));
+	cap->num_fmts += num_fmts;
+}
+
+static void
+parse_raw_formats(struct venus_core *core, u32 codecs, u32 domain, void *data)
+{
+	struct hfi_uncompressed_format_supported *fmt = data;
+	struct hfi_uncompressed_plane_info *pinfo = fmt->plane_info;
+	struct hfi_uncompressed_plane_constraints *constr;
+	struct raw_formats rawfmts[MAX_FMT_ENTRIES] = {};
+	u32 entries = fmt->format_entries;
+	unsigned int i = 0;
+	u32 num_planes;
+
+	while (entries) {
+		num_planes = pinfo->num_planes;
+
+		rawfmts[i].fmt = pinfo->format;
+		rawfmts[i].buftype = fmt->buffer_type;
+		i++;
+
+		if (pinfo->num_planes > MAX_PLANES)
+			break;
+
+		pinfo = (void *)pinfo + sizeof(*constr) * num_planes +
+			2 * sizeof(u32);
+		entries--;
+	}
+
+	for_each_codec(core->caps, ARRAY_SIZE(core->caps), codecs, domain,
+		       fill_raw_fmts, rawfmts, i);
+}
+
+static void parse_codecs(struct venus_core *core, void *data)
+{
+	struct hfi_codec_supported *codecs = data;
+
+	core->dec_codecs = codecs->dec_codecs;
+	core->enc_codecs = codecs->enc_codecs;
+
+	if (IS_V1(core)) {
+		core->dec_codecs &= ~HFI_VIDEO_CODEC_HEVC;
+		core->dec_codecs &= ~HFI_VIDEO_CODEC_SPARK;
+	}
+}
+
+static void parse_max_sessions(struct venus_core *core, const void *data)
+{
+	const struct hfi_max_sessions_supported *sessions = data;
+
+	core->max_sessions_supported = sessions->max_sessions;
+}
+
+static void parse_codecs_mask(u32 *codecs, u32 *domain, void *data)
+{
+	struct hfi_codec_mask_supported *mask = data;
+
+	*codecs = mask->codecs;
+	*domain = mask->video_domains;
+}
+
+static void parser_init(struct venus_inst *inst, u32 *codecs, u32 *domain)
+{
+	if (!inst || !IS_V1(inst->core))
+		return;
+
+	*codecs = inst->hfi_codec;
+	*domain = inst->session_type;
+}
+
+static void parser_fini(struct venus_inst *inst, u32 codecs, u32 domain)
+{
+	struct venus_caps *caps, *cap;
+	unsigned int i;
+	u32 dom;
+
+	if (!inst || !IS_V1(inst->core))
+		return;
+
+	caps = inst->core->caps;
+	dom = inst->session_type;
+
+	for (i = 0; i < MAX_CODEC_NUM; i++) {
+		cap = &caps[i];
+		if (cap->codec & codecs && cap->domain == dom)
+			cap->valid = true;
+	}
+}
+
+u32 hfi_parser(struct venus_core *core, struct venus_inst *inst, void *buf,
+	       u32 size)
+{
+	unsigned int words_count = size >> 2;
+	u32 *word = buf, *data, codecs = 0, domain = 0;
+
+	if (size % 4)
+		return HFI_ERR_SYS_INSUFFICIENT_RESOURCES;
+
+	parser_init(inst, &codecs, &domain);
+
+	while (words_count) {
+		data = word + 1;
+
+		switch (*word) {
+		case HFI_PROPERTY_PARAM_CODEC_SUPPORTED:
+			parse_codecs(core, data);
+			init_codecs(core);
+			break;
+		case HFI_PROPERTY_PARAM_MAX_SESSIONS_SUPPORTED:
+			parse_max_sessions(core, data);
+			break;
+		case HFI_PROPERTY_PARAM_CODEC_MASK_SUPPORTED:
+			parse_codecs_mask(&codecs, &domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SUPPORTED:
+			parse_raw_formats(core, codecs, domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_CAPABILITY_SUPPORTED:
+			parse_caps(core, codecs, domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_PROFILE_LEVEL_SUPPORTED:
+			parse_profile_level(core, codecs, domain, data);
+			break;
+		case HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE_SUPPORTED:
+			parse_alloc_mode(core, inst, codecs, domain, data);
+			break;
+		default:
+			break;
+		}
+
+		word++;
+		words_count--;
+	}
+
+	parser_fini(inst, codecs, domain);
+
+	return HFI_ERR_NONE;
+}
diff --git a/drivers/media/platform/qcom/venus/hfi_parser.h b/drivers/media/platform/qcom/venus/hfi_parser.h
new file mode 100644
index 000000000000..3e931c747e19
--- /dev/null
+++ b/drivers/media/platform/qcom/venus/hfi_parser.h
@@ -0,0 +1,110 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2018 Linaro Ltd. */
+#ifndef __VENUS_HFI_PARSER_H__
+#define __VENUS_HFI_PARSER_H__
+
+#include "core.h"
+
+u32 hfi_parser(struct venus_core *core, struct venus_inst *inst,
+	       void *buf, u32 size);
+
+#define WHICH_CAP_MIN	0
+#define WHICH_CAP_MAX	1
+#define WHICH_CAP_STEP	2
+
+static inline u32 get_cap(struct venus_inst *inst, u32 type, u32 which)
+{
+	struct venus_core *core = inst->core;
+	struct hfi_capability *cap = NULL;
+	struct venus_caps *caps;
+	unsigned int i;
+
+	caps = venus_caps_by_codec(core, inst->hfi_codec, inst->session_type);
+	if (!caps)
+		return 0;
+
+	for (i = 0; i < caps->num_caps; i++) {
+		if (caps->caps[i].capability_type == type) {
+			cap = &caps->caps[i];
+			break;
+		}
+	}
+
+	if (!cap)
+		return 0;
+
+	switch (which) {
+	case WHICH_CAP_MIN:
+		return cap->min;
+	case WHICH_CAP_MAX:
+		return cap->max;
+	case WHICH_CAP_STEP:
+		return cap->step_size;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static inline u32 cap_min(struct venus_inst *inst, u32 type)
+{
+	return get_cap(inst, type, WHICH_CAP_MIN);
+}
+
+static inline u32 cap_max(struct venus_inst *inst, u32 type)
+{
+	return get_cap(inst, type, WHICH_CAP_MAX);
+}
+
+static inline u32 cap_step(struct venus_inst *inst, u32 type)
+{
+	return get_cap(inst, type, WHICH_CAP_STEP);
+}
+
+static inline u32 frame_width_min(struct venus_inst *inst)
+{
+	return cap_min(inst, HFI_CAPABILITY_FRAME_WIDTH);
+}
+
+static inline u32 frame_width_max(struct venus_inst *inst)
+{
+	return cap_max(inst, HFI_CAPABILITY_FRAME_WIDTH);
+}
+
+static inline u32 frame_width_step(struct venus_inst *inst)
+{
+	return cap_step(inst, HFI_CAPABILITY_FRAME_WIDTH);
+}
+
+static inline u32 frame_height_min(struct venus_inst *inst)
+{
+	return cap_min(inst, HFI_CAPABILITY_FRAME_HEIGHT);
+}
+
+static inline u32 frame_height_max(struct venus_inst *inst)
+{
+	return cap_max(inst, HFI_CAPABILITY_FRAME_HEIGHT);
+}
+
+static inline u32 frame_height_step(struct venus_inst *inst)
+{
+	return cap_step(inst, HFI_CAPABILITY_FRAME_HEIGHT);
+}
+
+static inline u32 frate_min(struct venus_inst *inst)
+{
+	return cap_min(inst, HFI_CAPABILITY_FRAMERATE);
+}
+
+static inline u32 frate_max(struct venus_inst *inst)
+{
+	return cap_max(inst, HFI_CAPABILITY_FRAMERATE);
+}
+
+static inline u32 frate_step(struct venus_inst *inst)
+{
+	return cap_step(inst, HFI_CAPABILITY_FRAMERATE);
+}
+
+#endif
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 0529976b4069..b97d386b3a7a 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -24,6 +24,7 @@
 #include <media/videobuf2-dma-sg.h>
 
 #include "hfi_venus_io.h"
+#include "hfi_parser.h"
 #include "core.h"
 #include "helpers.h"
 #include "vdec.h"
@@ -175,10 +176,10 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 		fmt = find_format(inst, pixmp->pixelformat, f->type);
 	}
 
-	pixmp->width = clamp(pixmp->width, inst->cap_width.min,
-			     inst->cap_width.max);
-	pixmp->height = clamp(pixmp->height, inst->cap_height.min,
-			      inst->cap_height.max);
+	pixmp->width = clamp(pixmp->width, frame_width_min(inst),
+			     frame_width_max(inst));
+	pixmp->height = clamp(pixmp->height, frame_height_min(inst),
+			      frame_height_max(inst));
 
 	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)
 		pixmp->height = ALIGN(pixmp->height, 32);
@@ -440,12 +441,12 @@ static int vdec_enum_framesizes(struct file *file, void *fh,
 
 	fsize->type = V4L2_FRMSIZE_TYPE_STEPWISE;
 
-	fsize->stepwise.min_width = inst->cap_width.min;
-	fsize->stepwise.max_width = inst->cap_width.max;
-	fsize->stepwise.step_width = inst->cap_width.step_size;
-	fsize->stepwise.min_height = inst->cap_height.min;
-	fsize->stepwise.max_height = inst->cap_height.max;
-	fsize->stepwise.step_height = inst->cap_height.step_size;
+	fsize->stepwise.min_width = frame_width_min(inst);
+	fsize->stepwise.max_width = frame_width_max(inst);
+	fsize->stepwise.step_width = frame_width_step(inst);
+	fsize->stepwise.min_height = frame_height_min(inst);
+	fsize->stepwise.max_height = frame_height_max(inst);
+	fsize->stepwise.step_height = frame_height_step(inst);
 
 	return 0;
 }
@@ -900,22 +901,7 @@ static void vdec_inst_init(struct venus_inst *inst)
 	inst->fps = 30;
 	inst->timeperframe.numerator = 1;
 	inst->timeperframe.denominator = 30;
-
-	inst->cap_width.min = 64;
-	inst->cap_width.max = 1920;
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_width.max = 3840;
-	inst->cap_width.step_size = 1;
-	inst->cap_height.min = 64;
-	inst->cap_height.max = ALIGN(1080, 32);
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_height.max = ALIGN(2160, 32);
-	inst->cap_height.step_size = 1;
-	inst->cap_framerate.min = 1;
-	inst->cap_framerate.max = 30;
-	inst->cap_framerate.step_size = 1;
-	inst->cap_mbs_per_frame.min = 16;
-	inst->cap_mbs_per_frame.max = 8160;
+	inst->hfi_codec = HFI_VIDEO_CODEC_H264;
 }
 
 static const struct v4l2_m2m_ops vdec_m2m_ops = {
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 7c6be9d37d99..4edca7e2cb14 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -24,6 +24,7 @@
 #include <media/v4l2-ctrls.h>
 
 #include "hfi_venus_io.h"
+#include "hfi_parser.h"
 #include "core.h"
 #include "helpers.h"
 #include "venc.h"
@@ -299,10 +300,10 @@ venc_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 		fmt = find_format(inst, pixmp->pixelformat, f->type);
 	}
 
-	pixmp->width = clamp(pixmp->width, inst->cap_width.min,
-			     inst->cap_width.max);
-	pixmp->height = clamp(pixmp->height, inst->cap_height.min,
-			      inst->cap_height.max);
+	pixmp->width = clamp(pixmp->width, frame_width_min(inst),
+			     frame_width_max(inst));
+	pixmp->height = clamp(pixmp->height, frame_height_min(inst),
+			      frame_height_max(inst));
 
 	if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
 		pixmp->height = ALIGN(pixmp->height, 32);
@@ -551,12 +552,12 @@ static int venc_enum_framesizes(struct file *file, void *fh,
 	if (fsize->index)
 		return -EINVAL;
 
-	fsize->stepwise.min_width = inst->cap_width.min;
-	fsize->stepwise.max_width = inst->cap_width.max;
-	fsize->stepwise.step_width = inst->cap_width.step_size;
-	fsize->stepwise.min_height = inst->cap_height.min;
-	fsize->stepwise.max_height = inst->cap_height.max;
-	fsize->stepwise.step_height = inst->cap_height.step_size;
+	fsize->stepwise.min_width = frame_width_min(inst);
+	fsize->stepwise.max_width = frame_width_max(inst);
+	fsize->stepwise.step_width = frame_width_step(inst);
+	fsize->stepwise.min_height = frame_height_min(inst);
+	fsize->stepwise.max_height = frame_height_max(inst);
+	fsize->stepwise.step_height = frame_height_step(inst);
 
 	return 0;
 }
@@ -584,18 +585,18 @@ static int venc_enum_frameintervals(struct file *file, void *fh,
 	if (!fival->width || !fival->height)
 		return -EINVAL;
 
-	if (fival->width > inst->cap_width.max ||
-	    fival->width < inst->cap_width.min ||
-	    fival->height > inst->cap_height.max ||
-	    fival->height < inst->cap_height.min)
+	if (fival->width > frame_width_max(inst) ||
+	    fival->width < frame_width_min(inst) ||
+	    fival->height > frame_height_max(inst) ||
+	    fival->height < frame_height_min(inst))
 		return -EINVAL;
 
 	fival->stepwise.min.numerator = 1;
-	fival->stepwise.min.denominator = inst->cap_framerate.max;
+	fival->stepwise.min.denominator = frate_max(inst);
 	fival->stepwise.max.numerator = 1;
-	fival->stepwise.max.denominator = inst->cap_framerate.min;
+	fival->stepwise.max.denominator = frate_min(inst);
 	fival->stepwise.step.numerator = 1;
-	fival->stepwise.step.denominator = inst->cap_framerate.max;
+	fival->stepwise.step.denominator = frate_max(inst);
 
 	return 0;
 }
@@ -1089,22 +1090,7 @@ static void venc_inst_init(struct venus_inst *inst)
 	inst->fps = 15;
 	inst->timeperframe.numerator = 1;
 	inst->timeperframe.denominator = 15;
-
-	inst->cap_width.min = 96;
-	inst->cap_width.max = 1920;
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_width.max = 3840;
-	inst->cap_width.step_size = 2;
-	inst->cap_height.min = 64;
-	inst->cap_height.max = ALIGN(1080, 32);
-	if (inst->core->res->hfi_version == HFI_VERSION_3XX)
-		inst->cap_height.max = ALIGN(2160, 32);
-	inst->cap_height.step_size = 2;
-	inst->cap_framerate.min = 1;
-	inst->cap_framerate.max = 30;
-	inst->cap_framerate.step_size = 1;
-	inst->cap_mbs_per_frame.min = 24;
-	inst->cap_mbs_per_frame.max = 8160;
+	inst->hfi_codec = HFI_VIDEO_CODEC_H264;
 }
 
 static int venc_open(struct file *file)
-- 
cgit v1.2.3


From f03835204f7085a18777c1419fd5b3b6217b00ad Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:47 -0400
Subject: media: venus: helpers: rename a helper function and use buffer mode
 from caps

Rename is_reg_unreg_needed() to better name is_dynamic_bufmode() and
use buffer mode from enumerated per codec capabilities.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index c8c4a4be78e3..27c4a4060c4e 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -359,18 +359,16 @@ session_process_buf(struct venus_inst *inst, struct vb2_v4l2_buffer *vbuf)
 	return 0;
 }
 
-static inline int is_reg_unreg_needed(struct venus_inst *inst)
+static bool is_dynamic_bufmode(struct venus_inst *inst)
 {
-	if (inst->session_type == VIDC_SESSION_TYPE_DEC &&
-	    inst->core->res->hfi_version == HFI_VERSION_3XX)
-		return 0;
+	struct venus_core *core = inst->core;
+	struct venus_caps *caps;
 
-	if (inst->session_type == VIDC_SESSION_TYPE_DEC &&
-	    inst->cap_bufs_mode_dynamic &&
-	    inst->core->res->hfi_version == HFI_VERSION_1XX)
+	caps = venus_caps_by_codec(core, inst->hfi_codec, inst->session_type);
+	if (!caps)
 		return 0;
 
-	return 1;
+	return caps->cap_bufs_mode_dynamic;
 }
 
 static int session_unregister_bufs(struct venus_inst *inst)
@@ -379,7 +377,7 @@ static int session_unregister_bufs(struct venus_inst *inst)
 	struct hfi_buffer_desc bd;
 	int ret = 0;
 
-	if (!is_reg_unreg_needed(inst))
+	if (is_dynamic_bufmode(inst))
 		return 0;
 
 	list_for_each_entry_safe(buf, n, &inst->registeredbufs, reg_list) {
@@ -399,7 +397,7 @@ static int session_register_bufs(struct venus_inst *inst)
 	struct venus_buffer *buf;
 	int ret = 0;
 
-	if (!is_reg_unreg_needed(inst))
+	if (is_dynamic_bufmode(inst))
 		return 0;
 
 	list_for_each_entry(buf, &inst->registeredbufs, reg_list) {
-- 
cgit v1.2.3


From 2b0a8517fbfdbd8a2080404a5fe19ff0eb17e2e0 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:48 -0400
Subject: media: venus: helpers: add a helper function to set dynamic buffer
 mode

Adds a new helper function to set dynamic buffer mode if it is
supported by current HFI version. The dynamic buffer mode is
set unconditionally for both decoder outputs.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 22 ++++++++++++++++++++++
 drivers/media/platform/qcom/venus/helpers.h |  1 +
 drivers/media/platform/qcom/venus/vdec.c    | 15 +++------------
 3 files changed, 26 insertions(+), 12 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 27c4a4060c4e..29cc84777125 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -524,6 +524,28 @@ int venus_helper_set_color_format(struct venus_inst *inst, u32 pixfmt)
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_color_format);
 
+int venus_helper_set_dyn_bufmode(struct venus_inst *inst)
+{
+	const u32 ptype = HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE;
+	struct hfi_buffer_alloc_mode mode;
+	int ret;
+
+	if (!is_dynamic_bufmode(inst))
+		return 0;
+
+	mode.type = HFI_BUFFER_OUTPUT;
+	mode.mode = HFI_BUFFER_MODE_DYNAMIC;
+
+	ret = hfi_session_set_property(inst, ptype, &mode);
+	if (ret)
+		return ret;
+
+	mode.type = HFI_BUFFER_OUTPUT2;
+
+	return hfi_session_set_property(inst, ptype, &mode);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_dyn_bufmode);
+
 static void delayed_process_buf_func(struct work_struct *work)
 {
 	struct venus_buffer *buf, *n;
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 0e64aa95624a..52b961ed491e 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -40,6 +40,7 @@ int venus_helper_set_output_resolution(struct venus_inst *inst,
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs);
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
+int venus_helper_set_dyn_bufmode(struct venus_inst *inst);
 void venus_helper_acquire_buf_ref(struct vb2_v4l2_buffer *vbuf);
 void venus_helper_release_buf_ref(struct venus_inst *inst, unsigned int idx);
 void venus_helper_init_instance(struct venus_inst *inst);
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index b97d386b3a7a..ef5b14bfdde0 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -555,18 +555,9 @@ static int vdec_set_properties(struct venus_inst *inst)
 			return ret;
 	}
 
-	if (core->res->hfi_version == HFI_VERSION_3XX ||
-	    inst->cap_bufs_mode_dynamic) {
-		struct hfi_buffer_alloc_mode mode;
-
-		ptype = HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE;
-		mode.type = HFI_BUFFER_OUTPUT;
-		mode.mode = HFI_BUFFER_MODE_DYNAMIC;
-
-		ret = hfi_session_set_property(inst, ptype, &mode);
-		if (ret)
-			return ret;
-	}
+	ret = venus_helper_set_dyn_bufmode(inst);
+	if (ret)
+		return ret;
 
 	if (ctr->post_loop_deb_mode) {
 		ptype = HFI_PROPERTY_CONFIG_VDEC_POST_LOOP_DEBLOCKER;
-- 
cgit v1.2.3


From d4a5b0a6657bab12408b792cc111bc3b7c17b39b Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:49 -0400
Subject: media: venus: helpers: add helper function to set actual buffer size

Add and use a helper function to set actual buffer size for
particular buffer type. This is also preparation to use
the second decoder output.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 12 ++++++++++++
 drivers/media/platform/qcom/venus/helpers.h |  1 +
 drivers/media/platform/qcom/venus/vdec.c    | 10 ++--------
 3 files changed, 15 insertions(+), 8 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 29cc84777125..6fd7458f390a 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -546,6 +546,18 @@ int venus_helper_set_dyn_bufmode(struct venus_inst *inst)
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_dyn_bufmode);
 
+int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype)
+{
+	const u32 ptype = HFI_PROPERTY_PARAM_BUFFER_SIZE_ACTUAL;
+	struct hfi_buffer_size_actual bufsz;
+
+	bufsz.type = buftype;
+	bufsz.size = bufsize;
+
+	return hfi_session_set_property(inst, ptype, &bufsz);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_bufsize);
+
 static void delayed_process_buf_func(struct work_struct *work)
 {
 	struct venus_buffer *buf, *n;
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 52b961ed491e..cd306bd8978f 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -41,6 +41,7 @@ int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs);
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
 int venus_helper_set_dyn_bufmode(struct venus_inst *inst);
+int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype);
 void venus_helper_acquire_buf_ref(struct vb2_v4l2_buffer *vbuf);
 void venus_helper_release_buf_ref(struct venus_inst *inst, unsigned int idx);
 void venus_helper_init_instance(struct venus_inst *inst);
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index ef5b14bfdde0..b30f10b229d8 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -708,7 +708,6 @@ static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
 	struct venus_core *core = inst->core;
-	u32 ptype;
 	int ret;
 
 	mutex_lock(&inst->lock);
@@ -738,13 +737,8 @@ static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 		goto deinit_sess;
 
 	if (core->res->hfi_version == HFI_VERSION_3XX) {
-		struct hfi_buffer_size_actual buf_sz;
-
-		ptype = HFI_PROPERTY_PARAM_BUFFER_SIZE_ACTUAL;
-		buf_sz.type = HFI_BUFFER_OUTPUT;
-		buf_sz.size = inst->output_buf_size;
-
-		ret = hfi_session_set_property(inst, ptype, &buf_sz);
+		ret = venus_helper_set_bufsize(inst, inst->output_buf_size,
+					       HFI_BUFFER_OUTPUT);
 		if (ret)
 			goto deinit_sess;
 	}
-- 
cgit v1.2.3


From bf26670aeae8f7f407e05f5da044e48cf9854a1b Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:50 -0400
Subject: media: venus: core: delete not used buffer mode flags

Delete not used flag for capture buffer allocation mode and
no longer used cap_bufs_mode_dynamic from instance structure.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/core.h       |  4 ----
 drivers/media/platform/qcom/venus/hfi_parser.c | 11 +++--------
 2 files changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index b995d1601c87..1d1a59a5d343 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -255,8 +255,6 @@ struct venus_buffer {
  * @priv:	a private for HFI operations callbacks
  * @session_type:	the type of the session (decoder or encoder)
  * @hprop:	a union used as a holder by get property
- * @cap_bufs_mode_static:	buffers allocation mode capability
- * @cap_bufs_mode_dynamic:	buffers allocation mode capability
  */
 struct venus_inst {
 	struct list_head list;
@@ -305,8 +303,6 @@ struct venus_inst {
 	const struct hfi_inst_ops *ops;
 	u32 session_type;
 	union hfi_get_property hprop;
-	bool cap_bufs_mode_static;
-	bool cap_bufs_mode_dynamic;
 };
 
 #define IS_V1(core)	((core)->res->hfi_version == HFI_VERSION_1XX)
diff --git a/drivers/media/platform/qcom/venus/hfi_parser.c b/drivers/media/platform/qcom/venus/hfi_parser.c
index afc0db3b5dc3..2293d936e49c 100644
--- a/drivers/media/platform/qcom/venus/hfi_parser.c
+++ b/drivers/media/platform/qcom/venus/hfi_parser.c
@@ -60,8 +60,7 @@ fill_buf_mode(struct venus_caps *cap, const void *data, unsigned int num)
 }
 
 static void
-parse_alloc_mode(struct venus_core *core, struct venus_inst *inst, u32 codecs,
-		 u32 domain, void *data)
+parse_alloc_mode(struct venus_core *core, u32 codecs, u32 domain, void *data)
 {
 	struct hfi_buffer_alloc_mode_supported *mode = data;
 	u32 num_entries = mode->num_entries;
@@ -74,13 +73,9 @@ parse_alloc_mode(struct venus_core *core, struct venus_inst *inst, u32 codecs,
 
 	while (num_entries--) {
 		if (mode->buffer_type == HFI_BUFFER_OUTPUT ||
-		    mode->buffer_type == HFI_BUFFER_OUTPUT2) {
-			if (*type == HFI_BUFFER_MODE_DYNAMIC && inst)
-				inst->cap_bufs_mode_dynamic = true;
-
+		    mode->buffer_type == HFI_BUFFER_OUTPUT2)
 			for_each_codec(core->caps, ARRAY_SIZE(core->caps),
 				       codecs, domain, fill_buf_mode, type, 1);
-		}
 
 		type++;
 	}
@@ -267,7 +262,7 @@ u32 hfi_parser(struct venus_core *core, struct venus_inst *inst, void *buf,
 			parse_profile_level(core, codecs, domain, data);
 			break;
 		case HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE_SUPPORTED:
-			parse_alloc_mode(core, inst, codecs, domain, data);
+			parse_alloc_mode(core, codecs, domain, data);
 			break;
 		default:
 			break;
-- 
cgit v1.2.3


From 404054e1777a01ac93d9767b300f6ffb41bf5972 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:51 -0400
Subject: media: venus: helpers: add buffer type argument to a helper

This adds one more function argument to pass buffer type to
set_output_resolution() helper function. That is a preparation
to support secondary decoder output.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 5 +++--
 drivers/media/platform/qcom/venus/helpers.h | 3 ++-
 drivers/media/platform/qcom/venus/venc.c    | 3 ++-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 6fd7458f390a..7e764eeeb07c 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -458,12 +458,13 @@ int venus_helper_set_input_resolution(struct venus_inst *inst,
 EXPORT_SYMBOL_GPL(venus_helper_set_input_resolution);
 
 int venus_helper_set_output_resolution(struct venus_inst *inst,
-				       unsigned int width, unsigned int height)
+				       unsigned int width, unsigned int height,
+				       u32 buftype)
 {
 	u32 ptype = HFI_PROPERTY_PARAM_FRAME_SIZE;
 	struct hfi_framesize fs;
 
-	fs.buffer_type = HFI_BUFFER_OUTPUT;
+	fs.buffer_type = buftype;
 	fs.width = width;
 	fs.height = height;
 
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index cd306bd8978f..0de9989adcdb 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -36,7 +36,8 @@ int venus_helper_get_bufreq(struct venus_inst *inst, u32 type,
 int venus_helper_set_input_resolution(struct venus_inst *inst,
 				      unsigned int width, unsigned int height);
 int venus_helper_set_output_resolution(struct venus_inst *inst,
-				       unsigned int width, unsigned int height);
+				       unsigned int width, unsigned int height,
+				       u32 buftype);
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs);
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 4edca7e2cb14..75527db76ac1 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -793,7 +793,8 @@ static int venc_init_session(struct venus_inst *inst)
 		goto deinit;
 
 	ret = venus_helper_set_output_resolution(inst, inst->width,
-						 inst->height);
+						 inst->height,
+						 HFI_BUFFER_OUTPUT);
 	if (ret)
 		goto deinit;
 
-- 
cgit v1.2.3


From ab97a3fb904d7f50855d707c89529d8d50193dcb Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:52 -0400
Subject: media: venus: helpers: add a new helper to set raw format

The new helper will has one more argument for buffer type, that
way the decoder can configure the format on it's secondary
output.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 52 ++++++++++++++++++-----------
 drivers/media/platform/qcom/venus/helpers.h |  2 ++
 2 files changed, 35 insertions(+), 19 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 7e764eeeb07c..4e4109e80988 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -412,6 +412,20 @@ static int session_register_bufs(struct venus_inst *inst)
 	return ret;
 }
 
+static u32 to_hfi_raw_fmt(u32 v4l2_fmt)
+{
+	switch (v4l2_fmt) {
+	case V4L2_PIX_FMT_NV12:
+		return HFI_COLOR_FORMAT_NV12;
+	case V4L2_PIX_FMT_NV21:
+		return HFI_COLOR_FORMAT_NV21;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 int venus_helper_get_bufreq(struct venus_inst *inst, u32 type,
 			    struct hfi_buffer_requirements *req)
 {
@@ -493,35 +507,35 @@ int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_num_bufs);
 
-int venus_helper_set_color_format(struct venus_inst *inst, u32 pixfmt)
+int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
+				u32 buftype)
 {
+	const u32 ptype = HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SELECT;
 	struct hfi_uncompressed_format_select fmt;
-	u32 ptype = HFI_PROPERTY_PARAM_UNCOMPRESSED_FORMAT_SELECT;
-	int ret;
+
+	fmt.buffer_type = buftype;
+	fmt.format = hfi_format;
+
+	return hfi_session_set_property(inst, ptype, &fmt);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_raw_format);
+
+int venus_helper_set_color_format(struct venus_inst *inst, u32 pixfmt)
+{
+	u32 hfi_format, buftype;
 
 	if (inst->session_type == VIDC_SESSION_TYPE_DEC)
-		fmt.buffer_type = HFI_BUFFER_OUTPUT;
+		buftype = HFI_BUFFER_OUTPUT;
 	else if (inst->session_type == VIDC_SESSION_TYPE_ENC)
-		fmt.buffer_type = HFI_BUFFER_INPUT;
+		buftype = HFI_BUFFER_INPUT;
 	else
 		return -EINVAL;
 
-	switch (pixfmt) {
-	case V4L2_PIX_FMT_NV12:
-		fmt.format = HFI_COLOR_FORMAT_NV12;
-		break;
-	case V4L2_PIX_FMT_NV21:
-		fmt.format = HFI_COLOR_FORMAT_NV21;
-		break;
-	default:
+	hfi_format = to_hfi_raw_fmt(pixfmt);
+	if (!hfi_format)
 		return -EINVAL;
-	}
 
-	ret = hfi_session_set_property(inst, ptype, &fmt);
-	if (ret)
-		return ret;
-
-	return 0;
+	return venus_helper_set_raw_format(inst, hfi_format, buftype);
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_color_format);
 
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 0de9989adcdb..79af7845efbd 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -40,6 +40,8 @@ int venus_helper_set_output_resolution(struct venus_inst *inst,
 				       u32 buftype);
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs);
+int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
+				u32 buftype);
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
 int venus_helper_set_dyn_bufmode(struct venus_inst *inst);
 int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype);
-- 
cgit v1.2.3


From 01165b8484973da047fecd082a9c67da9c988ebe Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:53 -0400
Subject: media: venus: helpers, vdec, venc: add helpers to set work mode and
 core usage

These are new properties applicable to Venus version 4xx. Add the
helpers and call them from decoder and encoder drivers.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 28 ++++++++++++++++++++++++++++
 drivers/media/platform/qcom/venus/helpers.h |  2 ++
 drivers/media/platform/qcom/venus/vdec.c    |  8 ++++++++
 drivers/media/platform/qcom/venus/venc.c    |  8 ++++++++
 4 files changed, 46 insertions(+)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 4e4109e80988..3cd25e25aa70 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -486,6 +486,34 @@ int venus_helper_set_output_resolution(struct venus_inst *inst,
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_output_resolution);
 
+int venus_helper_set_work_mode(struct venus_inst *inst, u32 mode)
+{
+	const u32 ptype = HFI_PROPERTY_PARAM_WORK_MODE;
+	struct hfi_video_work_mode wm;
+
+	if (!IS_V4(inst->core))
+		return 0;
+
+	wm.video_work_mode = mode;
+
+	return hfi_session_set_property(inst, ptype, &wm);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_work_mode);
+
+int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage)
+{
+	const u32 ptype = HFI_PROPERTY_CONFIG_VIDEOCORES_USAGE;
+	struct hfi_videocores_usage_type cu;
+
+	if (!IS_V4(inst->core))
+		return 0;
+
+	cu.video_core_enable_mask = usage;
+
+	return hfi_session_set_property(inst, ptype, &cu);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_core_usage);
+
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs)
 {
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 79af7845efbd..d5e727e1ecab 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -38,6 +38,8 @@ int venus_helper_set_input_resolution(struct venus_inst *inst,
 int venus_helper_set_output_resolution(struct venus_inst *inst,
 				       unsigned int width, unsigned int height,
 				       u32 buftype);
+int venus_helper_set_work_mode(struct venus_inst *inst, u32 mode);
+int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage);
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 			      unsigned int output_bufs);
 int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index b30f10b229d8..99d9459e0643 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -548,6 +548,14 @@ static int vdec_set_properties(struct venus_inst *inst)
 	u32 ptype;
 	int ret;
 
+	ret = venus_helper_set_work_mode(inst, VIDC_WORK_MODE_2);
+	if (ret)
+		return ret;
+
+	ret = venus_helper_set_core_usage(inst, VIDC_CORE_ID_1);
+	if (ret)
+		return ret;
+
 	if (core->res->hfi_version == HFI_VERSION_1XX) {
 		ptype = HFI_PROPERTY_PARAM_VDEC_CONTINUE_DATA_TRANSFER;
 		ret = hfi_session_set_property(inst, ptype, &en);
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 75527db76ac1..5175786a8547 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -641,6 +641,14 @@ static int venc_set_properties(struct venus_inst *inst)
 	u32 ptype, rate_control, bitrate, profile = 0, level = 0;
 	int ret;
 
+	ret = venus_helper_set_work_mode(inst, VIDC_WORK_MODE_2);
+	if (ret)
+		return ret;
+
+	ret = venus_helper_set_core_usage(inst, VIDC_CORE_ID_2);
+	if (ret)
+		return ret;
+
 	ptype = HFI_PROPERTY_CONFIG_FRAME_RATE;
 	frate.buffer_type = HFI_BUFFER_OUTPUT;
 	frate.framerate = inst->fps * (1 << 16);
-- 
cgit v1.2.3


From 1eb04b2ef4dc27f465325892bcbd19274775108e Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:54 -0400
Subject: media: venus: helpers: extend set_num_bufs helper with one more
 argument

Extend venus_helper_set_num_bufs() helper function with one more
argument to set number of output buffers for the secondary decoder
output.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 16 ++++++++++++++--
 drivers/media/platform/qcom/venus/helpers.h |  3 ++-
 drivers/media/platform/qcom/venus/vdec.c    |  2 +-
 drivers/media/platform/qcom/venus/venc.c    |  2 +-
 4 files changed, 18 insertions(+), 5 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 3cd25e25aa70..13f0bc4e5ffa 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -515,7 +515,8 @@ int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage)
 EXPORT_SYMBOL_GPL(venus_helper_set_core_usage);
 
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
-			      unsigned int output_bufs)
+			      unsigned int output_bufs,
+			      unsigned int output2_bufs)
 {
 	u32 ptype = HFI_PROPERTY_PARAM_BUFFER_COUNT_ACTUAL;
 	struct hfi_buffer_count_actual buf_count;
@@ -531,7 +532,18 @@ int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
 	buf_count.type = HFI_BUFFER_OUTPUT;
 	buf_count.count_actual = output_bufs;
 
-	return hfi_session_set_property(inst, ptype, &buf_count);
+	ret = hfi_session_set_property(inst, ptype, &buf_count);
+	if (ret)
+		return ret;
+
+	if (output2_bufs) {
+		buf_count.type = HFI_BUFFER_OUTPUT2;
+		buf_count.count_actual = output2_bufs;
+
+		ret = hfi_session_set_property(inst, ptype, &buf_count);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_num_bufs);
 
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index d5e727e1ecab..8ff4bd3ef958 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -41,7 +41,8 @@ int venus_helper_set_output_resolution(struct venus_inst *inst,
 int venus_helper_set_work_mode(struct venus_inst *inst, u32 mode);
 int venus_helper_set_core_usage(struct venus_inst *inst, u32 usage);
 int venus_helper_set_num_bufs(struct venus_inst *inst, unsigned int input_bufs,
-			      unsigned int output_bufs);
+			      unsigned int output_bufs,
+			      unsigned int output2_bufs);
 int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
 				u32 buftype);
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 99d9459e0643..abbdb8ac1e42 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -756,7 +756,7 @@ static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 		goto deinit_sess;
 
 	ret = venus_helper_set_num_bufs(inst, inst->num_input_bufs,
-					VB2_MAX_FRAME);
+					VB2_MAX_FRAME, VB2_MAX_FRAME);
 	if (ret)
 		goto deinit_sess;
 
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 5175786a8547..b1d6ac7853cf 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -961,7 +961,7 @@ static int venc_start_streaming(struct vb2_queue *q, unsigned int count)
 		goto deinit_sess;
 
 	ret = venus_helper_set_num_bufs(inst, inst->num_input_bufs,
-					inst->num_output_bufs);
+					inst->num_output_bufs, 0);
 	if (ret)
 		goto deinit_sess;
 
-- 
cgit v1.2.3


From 130c0117e853a3561d083fd4039b630ca35ce167 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:55 -0400
Subject: media: venus: helpers: add a helper to return opb buffer sizes

Add a helper function to return current output picture buffer size.
OPB sizes can vary depending on the selected decoder output(s).

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/core.h    |  6 ++++++
 drivers/media/platform/qcom/venus/helpers.c | 15 +++++++++++++++
 drivers/media/platform/qcom/venus/helpers.h |  1 +
 3 files changed, 22 insertions(+)

diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index 1d1a59a5d343..f8e4d92ff0e1 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -239,6 +239,9 @@ struct venus_buffer {
  * @num_output_bufs:	holds number of output buffers
  * @input_buf_size	holds input buffer size
  * @output_buf_size:	holds output buffer size
+ * @output2_buf_size:	holds secondary decoder output buffer size
+ * @opb_buftype:	output picture buffer type
+ * @opb_fmt:		output picture buffer raw format
  * @reconfig:	a flag raised by decoder when the stream resolution changed
  * @reconfig_width:	holds the new width
  * @reconfig_height:	holds the new height
@@ -288,6 +291,9 @@ struct venus_inst {
 	unsigned int num_output_bufs;
 	unsigned int input_buf_size;
 	unsigned int output_buf_size;
+	unsigned int output2_buf_size;
+	u32 opb_buftype;
+	u32 opb_fmt;
 	bool reconfig;
 	u32 reconfig_width;
 	u32 reconfig_height;
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 13f0bc4e5ffa..8d2f4db52e48 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -613,6 +613,21 @@ int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype)
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_bufsize);
 
+unsigned int venus_helper_get_opb_size(struct venus_inst *inst)
+{
+	/* the encoder has only one output */
+	if (inst->session_type == VIDC_SESSION_TYPE_ENC)
+		return inst->output_buf_size;
+
+	if (inst->opb_buftype == HFI_BUFFER_OUTPUT)
+		return inst->output_buf_size;
+	else if (inst->opb_buftype == HFI_BUFFER_OUTPUT2)
+		return inst->output2_buf_size;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(venus_helper_get_opb_size);
+
 static void delayed_process_buf_func(struct work_struct *work)
 {
 	struct venus_buffer *buf, *n;
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 8ff4bd3ef958..92be45894a69 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -48,6 +48,7 @@ int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
 int venus_helper_set_dyn_bufmode(struct venus_inst *inst);
 int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype);
+unsigned int venus_helper_get_opb_size(struct venus_inst *inst);
 void venus_helper_acquire_buf_ref(struct vb2_v4l2_buffer *vbuf);
 void venus_helper_release_buf_ref(struct venus_inst *inst, unsigned int idx);
 void venus_helper_init_instance(struct venus_inst *inst);
-- 
cgit v1.2.3


From 7094af54c5167990a46abd26c83891188e8934b8 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:56 -0400
Subject: media: venus: vdec: get required input buffers as well

Rework and rename vdec_cap_num_buffers() to get the number of
input buffers too.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/vdec.c | 41 +++++++++++++++++++-------------
 1 file changed, 24 insertions(+), 17 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index abbdb8ac1e42..927b9d97fe4d 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -601,19 +601,32 @@ deinit:
 	return ret;
 }
 
-static int vdec_cap_num_buffers(struct venus_inst *inst, unsigned int *num)
+static int vdec_num_buffers(struct venus_inst *inst, unsigned int *in_num,
+			    unsigned int *out_num)
 {
+	enum hfi_version ver = inst->core->res->hfi_version;
 	struct hfi_buffer_requirements bufreq;
 	int ret;
 
+	*in_num = *out_num = 0;
+
 	ret = vdec_init_session(inst);
 	if (ret)
 		return ret;
 
+	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_INPUT, &bufreq);
+	if (ret)
+		goto deinit;
+
+	*in_num = HFI_BUFREQ_COUNT_MIN(&bufreq, ver);
+
 	ret = venus_helper_get_bufreq(inst, HFI_BUFFER_OUTPUT, &bufreq);
+	if (ret)
+		goto deinit;
 
-	*num = bufreq.count_actual;
+	*out_num = HFI_BUFREQ_COUNT_MIN(&bufreq, ver);
 
+deinit:
 	hfi_session_deinit(inst);
 
 	return ret;
@@ -624,7 +637,7 @@ static int vdec_queue_setup(struct vb2_queue *q,
 			    unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
-	unsigned int p, num;
+	unsigned int p, in_num, out_num;
 	int ret = 0;
 
 	if (*num_planes) {
@@ -647,35 +660,29 @@ static int vdec_queue_setup(struct vb2_queue *q,
 		return 0;
 	}
 
+	ret = vdec_num_buffers(inst, &in_num, &out_num);
+	if (ret)
+		return ret;
+
 	switch (q->type) {
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
 		*num_planes = inst->fmt_out->num_planes;
 		sizes[0] = get_framesize_compressed(inst->out_width,
 						    inst->out_height);
 		inst->input_buf_size = sizes[0];
+		*num_buffers = max(*num_buffers, in_num);
 		inst->num_input_bufs = *num_buffers;
-
-		ret = vdec_cap_num_buffers(inst, &num);
-		if (ret)
-			break;
-
-		inst->num_output_bufs = num;
+		inst->num_output_bufs = out_num;
 		break;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 		*num_planes = inst->fmt_cap->num_planes;
 
-		ret = vdec_cap_num_buffers(inst, &num);
-		if (ret)
-			break;
-
-		*num_buffers = max(*num_buffers, num);
-
 		for (p = 0; p < *num_planes; p++)
 			sizes[p] = get_framesize_uncompressed(p, inst->width,
 							      inst->height);
-
-		inst->num_output_bufs = *num_buffers;
 		inst->output_buf_size = sizes[0];
+		*num_buffers = max(*num_buffers, out_num);
+		inst->num_output_bufs = *num_buffers;
 		break;
 	default:
 		ret = -EINVAL;
-- 
cgit v1.2.3


From ea8ce23513afec48c690b408ac06a6fd695d057a Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:57 -0400
Subject: media: venus: vdec: a new function for output configuration

Make a new function vdec_output_conf() for decoder output
configuration. vdec_output_conf() will set properties via
HFI interface related to the output configuration, and
keep vdec_set_properties() which will set properties
related to decoding parameters.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/vdec.c | 34 ++++++++++++++++++--------------
 1 file changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 927b9d97fe4d..125f56e7ab1c 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -543,6 +543,22 @@ static const struct v4l2_ioctl_ops vdec_ioctl_ops = {
 static int vdec_set_properties(struct venus_inst *inst)
 {
 	struct vdec_controls *ctr = &inst->controls.dec;
+	struct hfi_enable en = { .enable = 1 };
+	u32 ptype;
+	int ret;
+
+	if (ctr->post_loop_deb_mode) {
+		ptype = HFI_PROPERTY_CONFIG_VDEC_POST_LOOP_DEBLOCKER;
+		ret = hfi_session_set_property(inst, ptype, &en);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int vdec_output_conf(struct venus_inst *inst)
+{
 	struct venus_core *core = inst->core;
 	struct hfi_enable en = { .enable = 1 };
 	u32 ptype;
@@ -567,14 +583,6 @@ static int vdec_set_properties(struct venus_inst *inst)
 	if (ret)
 		return ret;
 
-	if (ctr->post_loop_deb_mode) {
-		ptype = HFI_PROPERTY_CONFIG_VDEC_POST_LOOP_DEBLOCKER;
-		en.enable = 1;
-		ret = hfi_session_set_property(inst, ptype, &en);
-		if (ret)
-			return ret;
-	}
-
 	return 0;
 }
 
@@ -722,7 +730,6 @@ static int vdec_verify_conf(struct venus_inst *inst)
 static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
-	struct venus_core *core = inst->core;
 	int ret;
 
 	mutex_lock(&inst->lock);
@@ -751,12 +758,9 @@ static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 	if (ret)
 		goto deinit_sess;
 
-	if (core->res->hfi_version == HFI_VERSION_3XX) {
-		ret = venus_helper_set_bufsize(inst, inst->output_buf_size,
-					       HFI_BUFFER_OUTPUT);
-		if (ret)
-			goto deinit_sess;
-	}
+	ret = vdec_output_conf(inst);
+	if (ret)
+		goto deinit_sess;
 
 	ret = vdec_verify_conf(inst);
 	if (ret)
-- 
cgit v1.2.3


From e1cb72de702ad56bf0eb79264d9e95313d34b407 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:58 -0400
Subject: media: venus: helpers: move frame size calculations on common place

This move the calculations of raw and compressed buffer sizes
on common helper and make it identical for encoder and decoder.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/helpers.c | 98 +++++++++++++++++++++++++++++
 drivers/media/platform/qcom/venus/helpers.h |  2 +
 drivers/media/platform/qcom/venus/vdec.c    | 54 ++++------------
 drivers/media/platform/qcom/venus/venc.c    | 56 ++++-------------
 4 files changed, 126 insertions(+), 84 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 8d2f4db52e48..1e4d18448f7b 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -457,6 +457,104 @@ int venus_helper_get_bufreq(struct venus_inst *inst, u32 type,
 }
 EXPORT_SYMBOL_GPL(venus_helper_get_bufreq);
 
+static u32 get_framesize_raw_nv12(u32 width, u32 height)
+{
+	u32 y_stride, uv_stride, y_plane;
+	u32 y_sclines, uv_sclines, uv_plane;
+	u32 size;
+
+	y_stride = ALIGN(width, 128);
+	uv_stride = ALIGN(width, 128);
+	y_sclines = ALIGN(height, 32);
+	uv_sclines = ALIGN(((height + 1) >> 1), 16);
+
+	y_plane = y_stride * y_sclines;
+	uv_plane = uv_stride * uv_sclines + SZ_4K;
+	size = y_plane + uv_plane + SZ_8K;
+
+	return ALIGN(size, SZ_4K);
+}
+
+static u32 get_framesize_raw_nv12_ubwc(u32 width, u32 height)
+{
+	u32 y_meta_stride, y_meta_plane;
+	u32 y_stride, y_plane;
+	u32 uv_meta_stride, uv_meta_plane;
+	u32 uv_stride, uv_plane;
+	u32 extradata = SZ_16K;
+
+	y_meta_stride = ALIGN(DIV_ROUND_UP(width, 32), 64);
+	y_meta_plane = y_meta_stride * ALIGN(DIV_ROUND_UP(height, 8), 16);
+	y_meta_plane = ALIGN(y_meta_plane, SZ_4K);
+
+	y_stride = ALIGN(width, 128);
+	y_plane = ALIGN(y_stride * ALIGN(height, 32), SZ_4K);
+
+	uv_meta_stride = ALIGN(DIV_ROUND_UP(width / 2, 16), 64);
+	uv_meta_plane = uv_meta_stride * ALIGN(DIV_ROUND_UP(height / 2, 8), 16);
+	uv_meta_plane = ALIGN(uv_meta_plane, SZ_4K);
+
+	uv_stride = ALIGN(width, 128);
+	uv_plane = ALIGN(uv_stride * ALIGN(height / 2, 32), SZ_4K);
+
+	return ALIGN(y_meta_plane + y_plane + uv_meta_plane + uv_plane +
+		     max(extradata, y_stride * 48), SZ_4K);
+}
+
+u32 venus_helper_get_framesz_raw(u32 hfi_fmt, u32 width, u32 height)
+{
+	switch (hfi_fmt) {
+	case HFI_COLOR_FORMAT_NV12:
+	case HFI_COLOR_FORMAT_NV21:
+		return get_framesize_raw_nv12(width, height);
+	case HFI_COLOR_FORMAT_NV12_UBWC:
+		return get_framesize_raw_nv12_ubwc(width, height);
+	default:
+		return 0;
+	}
+}
+EXPORT_SYMBOL_GPL(venus_helper_get_framesz_raw);
+
+u32 venus_helper_get_framesz(u32 v4l2_fmt, u32 width, u32 height)
+{
+	u32 hfi_fmt, sz;
+	bool compressed;
+
+	switch (v4l2_fmt) {
+	case V4L2_PIX_FMT_MPEG:
+	case V4L2_PIX_FMT_H264:
+	case V4L2_PIX_FMT_H264_NO_SC:
+	case V4L2_PIX_FMT_H264_MVC:
+	case V4L2_PIX_FMT_H263:
+	case V4L2_PIX_FMT_MPEG1:
+	case V4L2_PIX_FMT_MPEG2:
+	case V4L2_PIX_FMT_MPEG4:
+	case V4L2_PIX_FMT_XVID:
+	case V4L2_PIX_FMT_VC1_ANNEX_G:
+	case V4L2_PIX_FMT_VC1_ANNEX_L:
+	case V4L2_PIX_FMT_VP8:
+	case V4L2_PIX_FMT_VP9:
+	case V4L2_PIX_FMT_HEVC:
+		compressed = true;
+		break;
+	default:
+		compressed = false;
+		break;
+	}
+
+	if (compressed) {
+		sz = ALIGN(height, 32) * ALIGN(width, 32) * 3 / 2 / 2;
+		return ALIGN(sz, SZ_4K);
+	}
+
+	hfi_fmt = to_hfi_raw_fmt(v4l2_fmt);
+	if (!hfi_fmt)
+		return 0;
+
+	return venus_helper_get_framesz_raw(hfi_fmt, width, height);
+}
+EXPORT_SYMBOL_GPL(venus_helper_get_framesz);
+
 int venus_helper_set_input_resolution(struct venus_inst *inst,
 				      unsigned int width, unsigned int height)
 {
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 92be45894a69..92b167a47166 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -33,6 +33,8 @@ void venus_helper_m2m_device_run(void *priv);
 void venus_helper_m2m_job_abort(void *priv);
 int venus_helper_get_bufreq(struct venus_inst *inst, u32 type,
 			    struct hfi_buffer_requirements *req);
+u32 venus_helper_get_framesz_raw(u32 hfi_fmt, u32 width, u32 height);
+u32 venus_helper_get_framesz(u32 v4l2_fmt, u32 width, u32 height);
 int venus_helper_set_input_resolution(struct venus_inst *inst,
 				      unsigned int width, unsigned int height);
 int venus_helper_set_output_resolution(struct venus_inst *inst,
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 125f56e7ab1c..caed49d25fda 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -29,29 +29,6 @@
 #include "helpers.h"
 #include "vdec.h"
 
-static u32 get_framesize_uncompressed(unsigned int plane, u32 width, u32 height)
-{
-	u32 y_stride, uv_stride, y_plane;
-	u32 y_sclines, uv_sclines, uv_plane;
-	u32 size;
-
-	y_stride = ALIGN(width, 128);
-	uv_stride = ALIGN(width, 128);
-	y_sclines = ALIGN(height, 32);
-	uv_sclines = ALIGN(((height + 1) >> 1), 16);
-
-	y_plane = y_stride * y_sclines;
-	uv_plane = uv_stride * uv_sclines + SZ_4K;
-	size = y_plane + uv_plane + SZ_8K;
-
-	return ALIGN(size, SZ_4K);
-}
-
-static u32 get_framesize_compressed(unsigned int width, unsigned int height)
-{
-	return ((width * height * 3 / 2) / 2) + 128;
-}
-
 /*
  * Three resons to keep MPLANE formats (despite that the number of planes
  * currently is one):
@@ -160,7 +137,6 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	struct v4l2_pix_format_mplane *pixmp = &f->fmt.pix_mp;
 	struct v4l2_plane_pix_format *pfmt = pixmp->plane_fmt;
 	const struct venus_format *fmt;
-	unsigned int p;
 
 	memset(pfmt[0].reserved, 0, sizeof(pfmt[0].reserved));
 	memset(pixmp->reserved, 0, sizeof(pixmp->reserved));
@@ -189,18 +165,14 @@ vdec_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	pixmp->num_planes = fmt->num_planes;
 	pixmp->flags = 0;
 
-	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		for (p = 0; p < pixmp->num_planes; p++) {
-			pfmt[p].sizeimage =
-				get_framesize_uncompressed(p, pixmp->width,
-							   pixmp->height);
-			pfmt[p].bytesperline = ALIGN(pixmp->width, 128);
-		}
-	} else {
-		pfmt[0].sizeimage = get_framesize_compressed(pixmp->width,
-							     pixmp->height);
+	pfmt[0].sizeimage = venus_helper_get_framesz(pixmp->pixelformat,
+						     pixmp->width,
+						     pixmp->height);
+
+	if (f->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE)
+		pfmt[0].bytesperline = ALIGN(pixmp->width, 128);
+	else
 		pfmt[0].bytesperline = 0;
-	}
 
 	return fmt;
 }
@@ -645,7 +617,7 @@ static int vdec_queue_setup(struct vb2_queue *q,
 			    unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
-	unsigned int p, in_num, out_num;
+	unsigned int in_num, out_num;
 	int ret = 0;
 
 	if (*num_planes) {
@@ -675,7 +647,8 @@ static int vdec_queue_setup(struct vb2_queue *q,
 	switch (q->type) {
 	case V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE:
 		*num_planes = inst->fmt_out->num_planes;
-		sizes[0] = get_framesize_compressed(inst->out_width,
+		sizes[0] = venus_helper_get_framesz(inst->fmt_out->pixfmt,
+						    inst->out_width,
 						    inst->out_height);
 		inst->input_buf_size = sizes[0];
 		*num_buffers = max(*num_buffers, in_num);
@@ -684,10 +657,9 @@ static int vdec_queue_setup(struct vb2_queue *q,
 		break;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 		*num_planes = inst->fmt_cap->num_planes;
-
-		for (p = 0; p < *num_planes; p++)
-			sizes[p] = get_framesize_uncompressed(p, inst->width,
-							      inst->height);
+		sizes[0] = venus_helper_get_framesz(inst->fmt_cap->pixfmt,
+						    inst->width,
+						    inst->height);
 		inst->output_buf_size = sizes[0];
 		*num_buffers = max(*num_buffers, out_num);
 		inst->num_output_bufs = *num_buffers;
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index b1d6ac7853cf..701e5c9bc98b 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -31,32 +31,6 @@
 
 #define NUM_B_FRAMES_MAX	4
 
-static u32 get_framesize_uncompressed(unsigned int plane, u32 width, u32 height)
-{
-	u32 y_stride, uv_stride, y_plane;
-	u32 y_sclines, uv_sclines, uv_plane;
-	u32 size;
-
-	y_stride = ALIGN(width, 128);
-	uv_stride = ALIGN(width, 128);
-	y_sclines = ALIGN(height, 32);
-	uv_sclines = ALIGN(((height + 1) >> 1), 16);
-
-	y_plane = y_stride * y_sclines;
-	uv_plane = uv_stride * uv_sclines + SZ_4K;
-	size = y_plane + uv_plane + SZ_8K;
-	size = ALIGN(size, SZ_4K);
-
-	return size;
-}
-
-static u32 get_framesize_compressed(u32 width, u32 height)
-{
-	u32 sz = ALIGN(height, 32) * ALIGN(width, 32) * 3 / 2 / 2;
-
-	return ALIGN(sz, SZ_4K);
-}
-
 /*
  * Three resons to keep MPLANE formats (despite that the number of planes
  * currently is one):
@@ -284,7 +258,6 @@ venc_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	struct v4l2_pix_format_mplane *pixmp = &f->fmt.pix_mp;
 	struct v4l2_plane_pix_format *pfmt = pixmp->plane_fmt;
 	const struct venus_format *fmt;
-	unsigned int p;
 
 	memset(pfmt[0].reserved, 0, sizeof(pfmt[0].reserved));
 	memset(pixmp->reserved, 0, sizeof(pixmp->reserved));
@@ -316,19 +289,14 @@ venc_try_fmt_common(struct venus_inst *inst, struct v4l2_format *f)
 	pixmp->num_planes = fmt->num_planes;
 	pixmp->flags = 0;
 
-	if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) {
-		for (p = 0; p < pixmp->num_planes; p++) {
-			pfmt[p].sizeimage =
-				get_framesize_uncompressed(p, pixmp->width,
-							   pixmp->height);
+	pfmt[0].sizeimage = venus_helper_get_framesz(pixmp->pixelformat,
+						     pixmp->width,
+						     pixmp->height);
 
-			pfmt[p].bytesperline = ALIGN(pixmp->width, 128);
-		}
-	} else {
-		pfmt[0].sizeimage = get_framesize_compressed(pixmp->width,
-							     pixmp->height);
+	if (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
+		pfmt[0].bytesperline = ALIGN(pixmp->width, 128);
+	else
 		pfmt[0].bytesperline = 0;
-	}
 
 	return fmt;
 }
@@ -843,7 +811,7 @@ static int venc_queue_setup(struct vb2_queue *q,
 			    unsigned int sizes[], struct device *alloc_devs[])
 {
 	struct venus_inst *inst = vb2_get_drv_priv(q);
-	unsigned int p, num, min = 4;
+	unsigned int num, min = 4;
 	int ret = 0;
 
 	if (*num_planes) {
@@ -878,16 +846,18 @@ static int venc_queue_setup(struct vb2_queue *q,
 		*num_buffers = max(*num_buffers, num);
 		inst->num_input_bufs = *num_buffers;
 
-		for (p = 0; p < *num_planes; ++p)
-			sizes[p] = get_framesize_uncompressed(p, inst->width,
-							      inst->height);
+		sizes[0] = venus_helper_get_framesz(inst->fmt_out->pixfmt,
+						    inst->width,
+						    inst->height);
 		inst->input_buf_size = sizes[0];
 		break;
 	case V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE:
 		*num_planes = inst->fmt_cap->num_planes;
 		*num_buffers = max(*num_buffers, min);
 		inst->num_output_bufs = *num_buffers;
-		sizes[0] = get_framesize_compressed(inst->width, inst->height);
+		sizes[0] = venus_helper_get_framesz(inst->fmt_cap->pixfmt,
+						    inst->width,
+						    inst->height);
 		inst->output_buf_size = sizes[0];
 		break;
 	default:
-- 
cgit v1.2.3


From f012b23d64e9879eca987627d9b9da3d9de56746 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:03:59 -0400
Subject: media: venus: implementing multi-stream support

This is implementing multi-stream decoder support. The multi-stream
will be used to enable/disable the primary/secondary decoder
outputs. Depending on formats on both decoder outputs we could
implement downscale, dithering and supporting UBWC (universal
bandwidth compression) formats. The UBWC compressed raw format is
used to optimize interconnect bandwidth for bigger resolutions
like 4K and hence we will get some power-saving benefits as well.

Both decoder outputs are distinguished by buffer_type field in
the HFI packets. For example HFI_BUFFER_OUTPUT is the buffer type
for primary decoder output and HFI_BUFFER_OUTPUT2 is for secondary
decoder output.

Starting from Venus 4xx the DPB buffers format must be UBWC, so
the multi-stream becomes mandatory for this Venus version. That
means that we need to allocate internally in the driver a set of
DPB buffers (with UBWC NV12 format) and give them to the firmware.
The other decoder output (we called it OPB) format will be NV12
linear format and with the same resolution (or smaller in case
the user wants to downscale).

The DPB buffers are used for decoder reference frames and those
have to be in a specific format (UBWC). So one decoder output is
used to fill those reference buffers while the other output is
used to fill the userspace buffers with the user requested format.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/core.h    |   6 +
 drivers/media/platform/qcom/venus/helpers.c | 198 +++++++++++++++++++++++++++-
 drivers/media/platform/qcom/venus/helpers.h |   6 +
 drivers/media/platform/qcom/venus/vdec.c    |  93 ++++++++++++-
 drivers/media/platform/qcom/venus/venc.c    |   1 +
 5 files changed, 300 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index f8e4d92ff0e1..8cc49f30a363 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -215,6 +215,7 @@ struct venus_buffer {
  * @list:	used for attach an instance to the core
  * @lock:	instance lock
  * @core:	a reference to the core struct
+ * @dpbbufs:	a list of decoded picture buffers
  * @internalbufs:	a list of internal bufferes
  * @registeredbufs:	a list of registered capture bufferes
  * @delayed_process	a list of delayed buffers
@@ -240,6 +241,8 @@ struct venus_buffer {
  * @input_buf_size	holds input buffer size
  * @output_buf_size:	holds output buffer size
  * @output2_buf_size:	holds secondary decoder output buffer size
+ * @dpb_buftype:	decoded picture buffer type
+ * @dpb_fmt:		decoded picture buffer raw format
  * @opb_buftype:	output picture buffer type
  * @opb_fmt:		output picture buffer raw format
  * @reconfig:	a flag raised by decoder when the stream resolution changed
@@ -263,6 +266,7 @@ struct venus_inst {
 	struct list_head list;
 	struct mutex lock;
 	struct venus_core *core;
+	struct list_head dpbbufs;
 	struct list_head internalbufs;
 	struct list_head registeredbufs;
 	struct list_head delayed_process;
@@ -292,6 +296,8 @@ struct venus_inst {
 	unsigned int input_buf_size;
 	unsigned int output_buf_size;
 	unsigned int output2_buf_size;
+	u32 dpb_buftype;
+	u32 dpb_fmt;
 	u32 opb_buftype;
 	u32 opb_fmt;
 	bool reconfig;
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index 1e4d18448f7b..cea5b506dd51 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -85,6 +85,106 @@ bool venus_helper_check_codec(struct venus_inst *inst, u32 v4l2_pixfmt)
 }
 EXPORT_SYMBOL_GPL(venus_helper_check_codec);
 
+static int venus_helper_queue_dpb_bufs(struct venus_inst *inst)
+{
+	struct intbuf *buf;
+	int ret = 0;
+
+	list_for_each_entry(buf, &inst->dpbbufs, list) {
+		struct hfi_frame_data fdata;
+
+		memset(&fdata, 0, sizeof(fdata));
+		fdata.alloc_len = buf->size;
+		fdata.device_addr = buf->da;
+		fdata.buffer_type = buf->type;
+
+		ret = hfi_session_process_buf(inst, &fdata);
+		if (ret)
+			goto fail;
+	}
+
+fail:
+	return ret;
+}
+
+int venus_helper_free_dpb_bufs(struct venus_inst *inst)
+{
+	struct intbuf *buf, *n;
+
+	list_for_each_entry_safe(buf, n, &inst->dpbbufs, list) {
+		list_del_init(&buf->list);
+		dma_free_attrs(inst->core->dev, buf->size, buf->va, buf->da,
+			       buf->attrs);
+		kfree(buf);
+	}
+
+	INIT_LIST_HEAD(&inst->dpbbufs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(venus_helper_free_dpb_bufs);
+
+int venus_helper_alloc_dpb_bufs(struct venus_inst *inst)
+{
+	struct venus_core *core = inst->core;
+	struct device *dev = core->dev;
+	enum hfi_version ver = core->res->hfi_version;
+	struct hfi_buffer_requirements bufreq;
+	u32 buftype = inst->dpb_buftype;
+	unsigned int dpb_size = 0;
+	struct intbuf *buf;
+	unsigned int i;
+	u32 count;
+	int ret;
+
+	/* no need to allocate dpb buffers */
+	if (!inst->dpb_fmt)
+		return 0;
+
+	if (inst->dpb_buftype == HFI_BUFFER_OUTPUT)
+		dpb_size = inst->output_buf_size;
+	else if (inst->dpb_buftype == HFI_BUFFER_OUTPUT2)
+		dpb_size = inst->output2_buf_size;
+
+	if (!dpb_size)
+		return 0;
+
+	ret = venus_helper_get_bufreq(inst, buftype, &bufreq);
+	if (ret)
+		return ret;
+
+	count = HFI_BUFREQ_COUNT_MIN(&bufreq, ver);
+
+	for (i = 0; i < count; i++) {
+		buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+		if (!buf) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		buf->type = buftype;
+		buf->size = dpb_size;
+		buf->attrs = DMA_ATTR_WRITE_COMBINE |
+			     DMA_ATTR_NO_KERNEL_MAPPING;
+		buf->va = dma_alloc_attrs(dev, buf->size, &buf->da, GFP_KERNEL,
+					  buf->attrs);
+		if (!buf->va) {
+			kfree(buf);
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		list_add_tail(&buf->list, &inst->dpbbufs);
+	}
+
+	return 0;
+
+fail:
+	venus_helper_free_dpb_bufs(inst);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(venus_helper_alloc_dpb_bufs);
+
 static int intbufs_set_buffer(struct venus_inst *inst, u32 type)
 {
 	struct venus_core *core = inst->core;
@@ -347,7 +447,10 @@ session_process_buf(struct venus_inst *inst, struct vb2_v4l2_buffer *vbuf)
 		if (vbuf->flags & V4L2_BUF_FLAG_LAST || !fdata.filled_len)
 			fdata.flags |= HFI_BUFFERFLAG_EOS;
 	} else if (type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
-		fdata.buffer_type = HFI_BUFFER_OUTPUT;
+		if (inst->session_type == VIDC_SESSION_TYPE_ENC)
+			fdata.buffer_type = HFI_BUFFER_OUTPUT;
+		else
+			fdata.buffer_type = inst->opb_buftype;
 		fdata.filled_len = 0;
 		fdata.offset = 0;
 	}
@@ -677,6 +780,27 @@ int venus_helper_set_color_format(struct venus_inst *inst, u32 pixfmt)
 }
 EXPORT_SYMBOL_GPL(venus_helper_set_color_format);
 
+int venus_helper_set_multistream(struct venus_inst *inst, bool out_en,
+				 bool out2_en)
+{
+	struct hfi_multi_stream multi = {0};
+	u32 ptype = HFI_PROPERTY_PARAM_VDEC_MULTI_STREAM;
+	int ret;
+
+	multi.buffer_type = HFI_BUFFER_OUTPUT;
+	multi.enable = out_en;
+
+	ret = hfi_session_set_property(inst, ptype, &multi);
+	if (ret)
+		return ret;
+
+	multi.buffer_type = HFI_BUFFER_OUTPUT2;
+	multi.enable = out2_en;
+
+	return hfi_session_set_property(inst, ptype, &multi);
+}
+EXPORT_SYMBOL_GPL(venus_helper_set_multistream);
+
 int venus_helper_set_dyn_bufmode(struct venus_inst *inst)
 {
 	const u32 ptype = HFI_PROPERTY_PARAM_BUFFER_ALLOC_MODE;
@@ -824,9 +948,10 @@ EXPORT_SYMBOL_GPL(venus_helper_vb2_buf_init);
 int venus_helper_vb2_buf_prepare(struct vb2_buffer *vb)
 {
 	struct venus_inst *inst = vb2_get_drv_priv(vb->vb2_queue);
+	unsigned int out_buf_size = venus_helper_get_opb_size(inst);
 
 	if (vb->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE &&
-	    vb2_plane_size(vb, 0) < inst->output_buf_size)
+	    vb2_plane_size(vb, 0) < out_buf_size)
 		return -EINVAL;
 	if (vb->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE &&
 	    vb2_plane_size(vb, 0) < inst->input_buf_size)
@@ -896,6 +1021,8 @@ void venus_helper_vb2_stop_streaming(struct vb2_queue *q)
 		if (ret)
 			hfi_session_abort(inst);
 
+		venus_helper_free_dpb_bufs(inst);
+
 		load_scale_clocks(core);
 		INIT_LIST_HEAD(&inst->registeredbufs);
 	}
@@ -934,8 +1061,14 @@ int venus_helper_vb2_start_streaming(struct venus_inst *inst)
 	if (ret)
 		goto err_unload_res;
 
+	ret = venus_helper_queue_dpb_bufs(inst);
+	if (ret)
+		goto err_session_stop;
+
 	return 0;
 
+err_session_stop:
+	hfi_session_stop(inst);
 err_unload_res:
 	hfi_session_unload_res(inst);
 err_unreg_bufs:
@@ -989,6 +1122,67 @@ void venus_helper_init_instance(struct venus_inst *inst)
 }
 EXPORT_SYMBOL_GPL(venus_helper_init_instance);
 
+static bool find_fmt_from_caps(struct venus_caps *caps, u32 buftype, u32 fmt)
+{
+	unsigned int i;
+
+	for (i = 0; i < caps->num_fmts; i++) {
+		if (caps->fmts[i].buftype == buftype &&
+		    caps->fmts[i].fmt == fmt)
+			return true;
+	}
+
+	return false;
+}
+
+int venus_helper_get_out_fmts(struct venus_inst *inst, u32 v4l2_fmt,
+			      u32 *out_fmt, u32 *out2_fmt, bool ubwc)
+{
+	struct venus_core *core = inst->core;
+	struct venus_caps *caps;
+	u32 ubwc_fmt, fmt = to_hfi_raw_fmt(v4l2_fmt);
+	bool found, found_ubwc;
+
+	*out_fmt = *out2_fmt = 0;
+
+	if (!fmt)
+		return -EINVAL;
+
+	caps = venus_caps_by_codec(core, inst->hfi_codec, inst->session_type);
+	if (!caps)
+		return -EINVAL;
+
+	if (ubwc) {
+		ubwc_fmt = fmt | HFI_COLOR_FORMAT_UBWC_BASE;
+		found_ubwc = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT,
+						ubwc_fmt);
+		found = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT2, fmt);
+
+		if (found_ubwc && found) {
+			*out_fmt = ubwc_fmt;
+			*out2_fmt = fmt;
+			return 0;
+		}
+	}
+
+	found = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT, fmt);
+	if (found) {
+		*out_fmt = fmt;
+		*out2_fmt = 0;
+		return 0;
+	}
+
+	found = find_fmt_from_caps(caps, HFI_BUFFER_OUTPUT2, fmt);
+	if (found) {
+		*out_fmt = 0;
+		*out2_fmt = fmt;
+		return 0;
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(venus_helper_get_out_fmts);
+
 int venus_helper_power_enable(struct venus_core *core, u32 session_type,
 			      bool enable)
 {
diff --git a/drivers/media/platform/qcom/venus/helpers.h b/drivers/media/platform/qcom/venus/helpers.h
index 92b167a47166..2475f284f396 100644
--- a/drivers/media/platform/qcom/venus/helpers.h
+++ b/drivers/media/platform/qcom/venus/helpers.h
@@ -50,10 +50,16 @@ int venus_helper_set_raw_format(struct venus_inst *inst, u32 hfi_format,
 int venus_helper_set_color_format(struct venus_inst *inst, u32 fmt);
 int venus_helper_set_dyn_bufmode(struct venus_inst *inst);
 int venus_helper_set_bufsize(struct venus_inst *inst, u32 bufsize, u32 buftype);
+int venus_helper_set_multistream(struct venus_inst *inst, bool out_en,
+				 bool out2_en);
 unsigned int venus_helper_get_opb_size(struct venus_inst *inst);
 void venus_helper_acquire_buf_ref(struct vb2_v4l2_buffer *vbuf);
 void venus_helper_release_buf_ref(struct venus_inst *inst, unsigned int idx);
 void venus_helper_init_instance(struct venus_inst *inst);
+int venus_helper_get_out_fmts(struct venus_inst *inst, u32 fmt, u32 *out_fmt,
+			      u32 *out2_fmt, bool ubwc);
+int venus_helper_alloc_dpb_bufs(struct venus_inst *inst);
+int venus_helper_free_dpb_bufs(struct venus_inst *inst);
 int venus_helper_power_enable(struct venus_core *core, u32 session_type,
 			      bool enable);
 #endif
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index caed49d25fda..698ba4c5bce4 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -529,10 +529,16 @@ static int vdec_set_properties(struct venus_inst *inst)
 	return 0;
 }
 
+#define is_ubwc_fmt(fmt) (!!((fmt) & HFI_COLOR_FORMAT_UBWC_BASE))
+
 static int vdec_output_conf(struct venus_inst *inst)
 {
 	struct venus_core *core = inst->core;
 	struct hfi_enable en = { .enable = 1 };
+	u32 width = inst->out_width;
+	u32 height = inst->out_height;
+	u32 out_fmt, out2_fmt;
+	bool ubwc = false;
 	u32 ptype;
 	int ret;
 
@@ -551,6 +557,80 @@ static int vdec_output_conf(struct venus_inst *inst)
 			return ret;
 	}
 
+	/* Force searching UBWC formats for bigger then HD resolutions */
+	if (width > 1920 && height > ALIGN(1080, 32))
+		ubwc = true;
+
+	/* For Venus v4 UBWC format is mandatory */
+	if (IS_V4(core))
+		ubwc = true;
+
+	ret = venus_helper_get_out_fmts(inst, inst->fmt_cap->pixfmt, &out_fmt,
+					&out2_fmt, ubwc);
+	if (ret)
+		return ret;
+
+	inst->output_buf_size =
+			venus_helper_get_framesz_raw(out_fmt, width, height);
+	inst->output2_buf_size =
+			venus_helper_get_framesz_raw(out2_fmt, width, height);
+
+	if (is_ubwc_fmt(out_fmt)) {
+		inst->opb_buftype = HFI_BUFFER_OUTPUT2;
+		inst->opb_fmt = out2_fmt;
+		inst->dpb_buftype = HFI_BUFFER_OUTPUT;
+		inst->dpb_fmt = out_fmt;
+	} else if (is_ubwc_fmt(out2_fmt)) {
+		inst->opb_buftype = HFI_BUFFER_OUTPUT;
+		inst->opb_fmt = out_fmt;
+		inst->dpb_buftype = HFI_BUFFER_OUTPUT2;
+		inst->dpb_fmt = out2_fmt;
+	} else {
+		inst->opb_buftype = HFI_BUFFER_OUTPUT;
+		inst->opb_fmt = out_fmt;
+		inst->dpb_buftype = 0;
+		inst->dpb_fmt = 0;
+	}
+
+	ret = venus_helper_set_raw_format(inst, inst->opb_fmt,
+					  inst->opb_buftype);
+	if (ret)
+		return ret;
+
+	if (inst->dpb_fmt) {
+		ret = venus_helper_set_multistream(inst, false, true);
+		if (ret)
+			return ret;
+
+		ret = venus_helper_set_raw_format(inst, inst->dpb_fmt,
+						  inst->dpb_buftype);
+		if (ret)
+			return ret;
+
+		ret = venus_helper_set_output_resolution(inst, width, height,
+							 HFI_BUFFER_OUTPUT2);
+		if (ret)
+			return ret;
+	}
+
+	if (IS_V3(core) || IS_V4(core)) {
+		if (inst->output2_buf_size) {
+			ret = venus_helper_set_bufsize(inst,
+						       inst->output2_buf_size,
+						       HFI_BUFFER_OUTPUT2);
+			if (ret)
+				return ret;
+		}
+
+		if (inst->output_buf_size) {
+			ret = venus_helper_set_bufsize(inst,
+						       inst->output_buf_size,
+						       HFI_BUFFER_OUTPUT);
+			if (ret)
+				return ret;
+		}
+	}
+
 	ret = venus_helper_set_dyn_bufmode(inst);
 	if (ret)
 		return ret;
@@ -621,6 +701,8 @@ static int vdec_queue_setup(struct vb2_queue *q,
 	int ret = 0;
 
 	if (*num_planes) {
+		unsigned int output_buf_size = venus_helper_get_opb_size(inst);
+
 		if (q->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE &&
 		    *num_planes != inst->fmt_out->num_planes)
 			return -EINVAL;
@@ -634,7 +716,7 @@ static int vdec_queue_setup(struct vb2_queue *q,
 			return -EINVAL;
 
 		if (q->type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE &&
-		    sizes[0] < inst->output_buf_size)
+		    sizes[0] < output_buf_size)
 			return -EINVAL;
 
 		return 0;
@@ -743,6 +825,10 @@ static int vdec_start_streaming(struct vb2_queue *q, unsigned int count)
 	if (ret)
 		goto deinit_sess;
 
+	ret = venus_helper_alloc_dpb_bufs(inst);
+	if (ret)
+		goto deinit_sess;
+
 	ret = venus_helper_vb2_start_streaming(inst);
 	if (ret)
 		goto deinit_sess;
@@ -794,9 +880,11 @@ static void vdec_buf_done(struct venus_inst *inst, unsigned int buf_type,
 	vbuf->field = V4L2_FIELD_NONE;
 
 	if (type == V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE) {
+		unsigned int opb_sz = venus_helper_get_opb_size(inst);
+
 		vb = &vbuf->vb2_buf;
 		vb->planes[0].bytesused =
-			max_t(unsigned int, inst->output_buf_size, bytesused);
+			max_t(unsigned int, opb_sz, bytesused);
 		vb->planes[0].data_offset = data_offset;
 		vb->timestamp = timestamp_us * NSEC_PER_USEC;
 		vbuf->sequence = inst->sequence_cap++;
@@ -934,6 +1022,7 @@ static int vdec_open(struct file *file)
 	if (!inst)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&inst->dpbbufs);
 	INIT_LIST_HEAD(&inst->registeredbufs);
 	INIT_LIST_HEAD(&inst->internalbufs);
 	INIT_LIST_HEAD(&inst->list);
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 701e5c9bc98b..8fe9c1b1d211 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -1082,6 +1082,7 @@ static int venc_open(struct file *file)
 	if (!inst)
 		return -ENOMEM;
 
+	INIT_LIST_HEAD(&inst->dpbbufs);
 	INIT_LIST_HEAD(&inst->registeredbufs);
 	INIT_LIST_HEAD(&inst->internalbufs);
 	INIT_LIST_HEAD(&inst->list);
-- 
cgit v1.2.3


From 0e8954a415b862f8fb4a9f9e6689c8ea5522aa47 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:04:00 -0400
Subject: media: venus: core: add sdm845 DT compatible and resource data

This adds sdm845 DT compatible string with it's resource
data table.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../devicetree/bindings/media/qcom,venus.txt       |  1 +
 drivers/media/platform/qcom/venus/core.c           | 22 ++++++++++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/Documentation/devicetree/bindings/media/qcom,venus.txt b/Documentation/devicetree/bindings/media/qcom,venus.txt
index 2693449daf73..00d0d1bf7647 100644
--- a/Documentation/devicetree/bindings/media/qcom,venus.txt
+++ b/Documentation/devicetree/bindings/media/qcom,venus.txt
@@ -6,6 +6,7 @@
 	Definition: Value should contain one of:
 		- "qcom,msm8916-venus"
 		- "qcom,msm8996-venus"
+		- "qcom,sdm845-venus"
 - reg:
 	Usage: required
 	Value type: <prop-encoded-array>
diff --git a/drivers/media/platform/qcom/venus/core.c b/drivers/media/platform/qcom/venus/core.c
index 381bfdd688db..bb6add9d340e 100644
--- a/drivers/media/platform/qcom/venus/core.c
+++ b/drivers/media/platform/qcom/venus/core.c
@@ -450,9 +450,31 @@ static const struct venus_resources msm8996_res = {
 	.fwname = "qcom/venus-4.2/venus.mdt",
 };
 
+static const struct freq_tbl sdm845_freq_table[] = {
+	{ 1944000, 380000000 },	/* 4k UHD @ 60 */
+	{  972000, 320000000 },	/* 4k UHD @ 30 */
+	{  489600, 200000000 },	/* 1080p @ 60 */
+	{  244800, 100000000 },	/* 1080p @ 30 */
+};
+
+static const struct venus_resources sdm845_res = {
+	.freq_tbl = sdm845_freq_table,
+	.freq_tbl_size = ARRAY_SIZE(sdm845_freq_table),
+	.clks = {"core", "iface", "bus" },
+	.clks_num = 3,
+	.max_load = 2563200,
+	.hfi_version = HFI_VERSION_4XX,
+	.vmem_id = VIDC_RESOURCE_NONE,
+	.vmem_size = 0,
+	.vmem_addr = 0,
+	.dma_mask = 0xe0000000 - 1,
+	.fwname = "qcom/venus-5.2/venus.mdt",
+};
+
 static const struct of_device_id venus_dt_match[] = {
 	{ .compatible = "qcom,msm8916-venus", .data = &msm8916_res, },
 	{ .compatible = "qcom,msm8996-venus", .data = &msm8996_res, },
+	{ .compatible = "qcom,sdm845-venus", .data = &sdm845_res, },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, venus_dt_match);
-- 
cgit v1.2.3


From 1fb9a6055561c1e77e1660aba51b1075a4a06475 Mon Sep 17 00:00:00 2001
From: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Date: Thu, 5 Jul 2018 09:04:01 -0400
Subject: media: venus: add HEVC codec support

This add HEVC codec support for venus versions 3xx and 4xx.

Signed-off-by: Stanimir Varbanov <stanimir.varbanov@linaro.org>
Reviewed-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Alexandre Courbot <acourbot@chromium.org>
Tested-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/venus/core.h    |  2 ++
 drivers/media/platform/qcom/venus/helpers.c |  3 ++
 drivers/media/platform/qcom/venus/hfi.c     |  2 ++
 drivers/media/platform/qcom/venus/vdec.c    |  4 +++
 drivers/media/platform/qcom/venus/venc.c    | 49 +++++++++++++++++++++++++++++
 5 files changed, 60 insertions(+)

diff --git a/drivers/media/platform/qcom/venus/core.h b/drivers/media/platform/qcom/venus/core.h
index 8cc49f30a363..2f02365f4818 100644
--- a/drivers/media/platform/qcom/venus/core.h
+++ b/drivers/media/platform/qcom/venus/core.h
@@ -190,10 +190,12 @@ struct venc_controls {
 		u32 mpeg4;
 		u32 h264;
 		u32 vpx;
+		u32 hevc;
 	} profile;
 	struct {
 		u32 mpeg4;
 		u32 h264;
+		u32 hevc;
 	} level;
 };
 
diff --git a/drivers/media/platform/qcom/venus/helpers.c b/drivers/media/platform/qcom/venus/helpers.c
index cea5b506dd51..cd3b96e6f24b 100644
--- a/drivers/media/platform/qcom/venus/helpers.c
+++ b/drivers/media/platform/qcom/venus/helpers.c
@@ -71,6 +71,9 @@ bool venus_helper_check_codec(struct venus_inst *inst, u32 v4l2_pixfmt)
 	case V4L2_PIX_FMT_XVID:
 		codec = HFI_VIDEO_CODEC_DIVX;
 		break;
+	case V4L2_PIX_FMT_HEVC:
+		codec = HFI_VIDEO_CODEC_HEVC;
+		break;
 	default:
 		return false;
 	}
diff --git a/drivers/media/platform/qcom/venus/hfi.c b/drivers/media/platform/qcom/venus/hfi.c
index 94ca27b0bb99..24207829982f 100644
--- a/drivers/media/platform/qcom/venus/hfi.c
+++ b/drivers/media/platform/qcom/venus/hfi.c
@@ -49,6 +49,8 @@ static u32 to_codec_type(u32 pixfmt)
 		return HFI_VIDEO_CODEC_VP9;
 	case V4L2_PIX_FMT_XVID:
 		return HFI_VIDEO_CODEC_DIVX;
+	case V4L2_PIX_FMT_HEVC:
+		return HFI_VIDEO_CODEC_HEVC;
 	default:
 		return 0;
 	}
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 698ba4c5bce4..0d043c33cd83 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -77,6 +77,10 @@ static const struct venus_format vdec_formats[] = {
 		.pixfmt = V4L2_PIX_FMT_XVID,
 		.num_planes = 1,
 		.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE,
+	}, {
+		.pixfmt = V4L2_PIX_FMT_HEVC,
+		.num_planes = 1,
+		.type = V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE,
 	},
 };
 
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 8fe9c1b1d211..20d7246a3ef9 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -59,6 +59,10 @@ static const struct venus_format venc_formats[] = {
 		.pixfmt = V4L2_PIX_FMT_VP8,
 		.num_planes = 1,
 		.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE,
+	}, {
+		.pixfmt = V4L2_PIX_FMT_HEVC,
+		.num_planes = 1,
+		.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE,
 	},
 };
 
@@ -220,6 +224,46 @@ static int venc_v4l2_to_hfi(int id, int value)
 		case V4L2_MPEG_VIDEO_H264_LOOP_FILTER_MODE_DISABLED_AT_SLICE_BOUNDARY:
 			return HFI_H264_DB_MODE_SKIP_SLICE_BOUNDARY;
 		}
+	case V4L2_CID_MPEG_VIDEO_HEVC_PROFILE:
+		switch (value) {
+		case V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN:
+		default:
+			return HFI_HEVC_PROFILE_MAIN;
+		case V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN_STILL_PICTURE:
+			return HFI_HEVC_PROFILE_MAIN_STILL_PIC;
+		case V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN_10:
+			return HFI_HEVC_PROFILE_MAIN10;
+		}
+	case V4L2_CID_MPEG_VIDEO_HEVC_LEVEL:
+		switch (value) {
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_1:
+		default:
+			return HFI_HEVC_LEVEL_1;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_2:
+			return HFI_HEVC_LEVEL_2;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_2_1:
+			return HFI_HEVC_LEVEL_21;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_3:
+			return HFI_HEVC_LEVEL_3;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_3_1:
+			return HFI_HEVC_LEVEL_31;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_4:
+			return HFI_HEVC_LEVEL_4;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_4_1:
+			return HFI_HEVC_LEVEL_41;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_5:
+			return HFI_HEVC_LEVEL_5;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_5_1:
+			return HFI_HEVC_LEVEL_51;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_5_2:
+			return HFI_HEVC_LEVEL_52;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_6:
+			return HFI_HEVC_LEVEL_6;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_6_1:
+			return HFI_HEVC_LEVEL_61;
+		case V4L2_MPEG_VIDEO_HEVC_LEVEL_6_2:
+			return HFI_HEVC_LEVEL_62;
+		}
 	}
 
 	return 0;
@@ -742,6 +786,11 @@ static int venc_set_properties(struct venus_inst *inst)
 	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_H263) {
 		profile = 0;
 		level = 0;
+	} else if (inst->fmt_cap->pixfmt == V4L2_PIX_FMT_HEVC) {
+		profile = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_HEVC_PROFILE,
+					   ctr->profile.hevc);
+		level = venc_v4l2_to_hfi(V4L2_CID_MPEG_VIDEO_HEVC_LEVEL,
+					 ctr->level.hevc);
 	}
 
 	ptype = HFI_PROPERTY_PARAM_PROFILE_LEVEL_CURRENT;
-- 
cgit v1.2.3


From 5accd7f3360e891bd552312515387dbaa2bb4bf3 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 5 Jul 2018 11:46:12 +0900
Subject: kconfig: handle format string before calling conf_message_callback()

As you see in mconf.c and nconf.c, conf_message_callback() hooks are
likely to end up with the boilerplate of vsnprintf().  Process the
string format before calling conf_message_callback() so that it
receives a simple string.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Dirk Gouders <dirk@gouders.net>
---
 scripts/kconfig/confdata.c  | 17 +++++++++++------
 scripts/kconfig/lkc_proto.h |  2 +-
 scripts/kconfig/mconf.c     |  9 +++------
 scripts/kconfig/nconf.c     |  7 ++-----
 4 files changed, 17 insertions(+), 18 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index d1216e4ade2f..629ad32d4708 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -43,16 +43,16 @@ static void conf_warning(const char *fmt, ...)
 	conf_warnings++;
 }
 
-static void conf_default_message_callback(const char *fmt, va_list ap)
+static void conf_default_message_callback(const char *s)
 {
 	printf("#\n# ");
-	vprintf(fmt, ap);
+	printf("%s", s);
 	printf("\n#\n");
 }
 
-static void (*conf_message_callback) (const char *fmt, va_list ap) =
+static void (*conf_message_callback)(const char *s) =
 	conf_default_message_callback;
-void conf_set_message_callback(void (*fn) (const char *fmt, va_list ap))
+void conf_set_message_callback(void (*fn)(const char *s))
 {
 	conf_message_callback = fn;
 }
@@ -60,10 +60,15 @@ void conf_set_message_callback(void (*fn) (const char *fmt, va_list ap))
 static void conf_message(const char *fmt, ...)
 {
 	va_list ap;
+	char buf[4096];
+
+	if (!conf_message_callback)
+		return;
 
 	va_start(ap, fmt);
-	if (conf_message_callback)
-		conf_message_callback(fmt, ap);
+
+	vsnprintf(buf, sizeof(buf), fmt, ap);
+	conf_message_callback(buf);
 	va_end(ap);
 }
 
diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h
index a8b7a330587e..cf4510a2bdc7 100644
--- a/scripts/kconfig/lkc_proto.h
+++ b/scripts/kconfig/lkc_proto.h
@@ -10,7 +10,7 @@ int conf_write(const char *name);
 int conf_write_autoconf(void);
 bool conf_get_changed(void);
 void conf_set_changed_callback(void (*fn)(void));
-void conf_set_message_callback(void (*fn)(const char *fmt, va_list ap));
+void conf_set_message_callback(void (*fn)(const char *s));
 
 /* menu.c */
 extern struct menu rootmenu;
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index 5294ed159b98..b8f3b607962a 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -772,16 +772,13 @@ static void show_helptext(const char *title, const char *text)
 	show_textbox(title, text, 0, 0);
 }
 
-static void conf_message_callback(const char *fmt, va_list ap)
+static void conf_message_callback(const char *s)
 {
-	char buf[PATH_MAX+1];
-
-	vsnprintf(buf, sizeof(buf), fmt, ap);
 	if (save_and_exit) {
 		if (!silent)
-			printf("%s", buf);
+			printf("%s", s);
 	} else {
-		show_textbox(NULL, buf, 6, 60);
+		show_textbox(NULL, s, 6, 60);
 	}
 }
 
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 97b78445584b..5cbdb92e11b3 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -1210,12 +1210,9 @@ static void conf(struct menu *menu)
 	}
 }
 
-static void conf_message_callback(const char *fmt, va_list ap)
+static void conf_message_callback(const char *s)
 {
-	char buf[1024];
-
-	vsnprintf(buf, sizeof(buf), fmt, ap);
-	btn_dialog(main_window, buf, 1, "<OK>");
+	btn_dialog(main_window, s, 1, "<OK>");
 }
 
 static void show_help(struct menu *menu)
-- 
cgit v1.2.3


From 08b220b37ffe9ae8f2f0fe4618d03f7c25805fb3 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Wed, 18 Jul 2018 22:46:36 -0700
Subject: kconfig: fix typos in description of "choice" in kconfig-language.txt

Fix a couple of punctuation "typos" in the description of the
"choice" keyword.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Documentation/kbuild/kconfig-language.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/kbuild/kconfig-language.txt b/Documentation/kbuild/kconfig-language.txt
index 64e0775a62d4..c54cb7cb9ff4 100644
--- a/Documentation/kbuild/kconfig-language.txt
+++ b/Documentation/kbuild/kconfig-language.txt
@@ -370,7 +370,7 @@ choices:
 
 This defines a choice group and accepts any of the above attributes as
 options. A choice can only be of type bool or tristate.  If no type is
-specified for a choice, it's type will be determined by the type of
+specified for a choice, its type will be determined by the type of
 the first choice element in the group or remain unknown if none of the
 choice elements have a type specified, as well.
 
@@ -384,7 +384,7 @@ A choice accepts another option "optional", which allows to set the
 choice to 'n' and no entry needs to be selected.
 If no [symbol] is associated with a choice, then you can not have multiple
 definitions of that choice. If a [symbol] is associated to the choice,
-then you may define the same choice (ie. with the same entries) in another
+then you may define the same choice (i.e. with the same entries) in another
 place.
 
 comment:
-- 
cgit v1.2.3


From a2ff4040151ace5be20e4de34220468b9e842e4d Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:26 +0900
Subject: kconfig: rename file_write_dep and move it to confdata.c

file_write_dep() is called only from conf_write_autoconf().
Move it from util.c to confdata.c to make it static.
Also, rename it to conf_write_dep() since it should belong to
the group of conf_write* functions.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/confdata.c | 31 ++++++++++++++++++++++++++++++-
 scripts/kconfig/lkc.h      |  1 -
 scripts/kconfig/util.c     | 30 ------------------------------
 3 files changed, 30 insertions(+), 32 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 629ad32d4708..c553f1f30c36 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -818,6 +818,35 @@ next:
 	return 0;
 }
 
+/* write a dependency file as used by kbuild to track dependencies */
+static int conf_write_dep(const char *name)
+{
+	struct file *file;
+	FILE *out;
+
+	if (!name)
+		name = ".kconfig.d";
+	out = fopen("..config.tmp", "w");
+	if (!out)
+		return 1;
+	fprintf(out, "deps_config := \\\n");
+	for (file = file_list; file; file = file->next) {
+		if (file->next)
+			fprintf(out, "\t%s \\\n", file->name);
+		else
+			fprintf(out, "\t%s\n", file->name);
+	}
+	fprintf(out, "\n%s: \\\n"
+		     "\t$(deps_config)\n\n", conf_get_autoconfig_name());
+
+	env_write_dep(out, conf_get_autoconfig_name());
+
+	fprintf(out, "\n$(deps_config): ;\n");
+	fclose(out);
+	rename("..config.tmp", name);
+	return 0;
+}
+
 static int conf_split_config(void)
 {
 	const char *name;
@@ -940,7 +969,7 @@ int conf_write_autoconf(void)
 
 	sym_clear_all_valid();
 
-	file_write_dep("include/config/auto.conf.cmd");
+	conf_write_dep("include/config/auto.conf.cmd");
 
 	if (conf_split_config())
 		return 1;
diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index ed3ff88e60ba..6b7bbc6238e3 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -97,7 +97,6 @@ void menu_set_type(int type);
 
 /* util.c */
 struct file *file_lookup(const char *name);
-int file_write_dep(const char *name);
 void *xmalloc(size_t size);
 void *xcalloc(size_t nmemb, size_t size);
 void *xrealloc(void *p, size_t size);
diff --git a/scripts/kconfig/util.c b/scripts/kconfig/util.c
index a365594770d9..d999683bb2a7 100644
--- a/scripts/kconfig/util.c
+++ b/scripts/kconfig/util.c
@@ -29,36 +29,6 @@ struct file *file_lookup(const char *name)
 	return file;
 }
 
-/* write a dependency file as used by kbuild to track dependencies */
-int file_write_dep(const char *name)
-{
-	struct file *file;
-	FILE *out;
-
-	if (!name)
-		name = ".kconfig.d";
-	out = fopen("..config.tmp", "w");
-	if (!out)
-		return 1;
-	fprintf(out, "deps_config := \\\n");
-	for (file = file_list; file; file = file->next) {
-		if (file->next)
-			fprintf(out, "\t%s \\\n", file->name);
-		else
-			fprintf(out, "\t%s\n", file->name);
-	}
-	fprintf(out, "\n%s: \\\n"
-		     "\t$(deps_config)\n\n", conf_get_autoconfig_name());
-
-	env_write_dep(out, conf_get_autoconfig_name());
-
-	fprintf(out, "\n$(deps_config): ;\n");
-	fclose(out);
-	rename("..config.tmp", name);
-	return 0;
-}
-
-
 /* Allocate initial growable string */
 struct gstr str_new(void)
 {
-- 
cgit v1.2.3


From 0608182ad54293f6f617c1cc9fb34467db5515c7 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:27 +0900
Subject: kconfig: split out useful helpers in confdata.c

Split out helpers:
 is_present() - check if the given path exists
 is_dir() - check if the given path exists and it is a directory
 make_parent_dir() - create the parent directories of the given path

These helpers will be reused in later commits.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/confdata.c | 81 ++++++++++++++++++++++++++++++++++++----------
 1 file changed, 64 insertions(+), 17 deletions(-)

diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index c553f1f30c36..88429d723c9c 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -16,6 +16,64 @@
 
 #include "lkc.h"
 
+/* return true if 'path' exists, false otherwise */
+static bool is_present(const char *path)
+{
+	struct stat st;
+
+	return !stat(path, &st);
+}
+
+/* return true if 'path' exists and it is a directory, false otherwise */
+static bool is_dir(const char *path)
+{
+	struct stat st;
+
+	if (stat(path, &st))
+		return 0;
+
+	return S_ISDIR(st.st_mode);
+}
+
+/*
+ * Create the parent directory of the given path.
+ *
+ * For example, if 'include/config/auto.conf' is given, create 'include/config'.
+ */
+static int make_parent_dir(const char *path)
+{
+	char tmp[PATH_MAX + 1];
+	char *p;
+
+	strncpy(tmp, path, sizeof(tmp));
+	tmp[sizeof(tmp) - 1] = 0;
+
+	/* Remove the base name. Just return if nothing is left */
+	p = strrchr(tmp, '/');
+	if (!p)
+		return 0;
+	*(p + 1) = 0;
+
+	/* Just in case it is an absolute path */
+	p = tmp;
+	while (*p == '/')
+		p++;
+
+	while ((p = strchr(p, '/'))) {
+		*p = 0;
+
+		/* skip if the directory exists */
+		if (!is_dir(tmp) && mkdir(tmp, 0755))
+			return -1;
+
+		*p = '/';
+		while (*p == '/')
+			p++;
+	}
+
+	return 0;
+}
+
 struct conf_printer {
 	void (*print_symbol)(FILE *, struct symbol *, const char *, void *);
 	void (*print_comment)(FILE *, const char *, void *);
@@ -88,7 +146,6 @@ const char *conf_get_autoconfig_name(void)
 
 char *conf_get_default_confname(void)
 {
-	struct stat buf;
 	static char fullname[PATH_MAX+1];
 	char *env, *name;
 
@@ -96,7 +153,7 @@ char *conf_get_default_confname(void)
 	env = getenv(SRCTREE);
 	if (env) {
 		sprintf(fullname, "%s/%s", env, name);
-		if (!stat(fullname, &buf))
+		if (is_present(fullname))
 			return fullname;
 	}
 	return name;
@@ -730,10 +787,9 @@ int conf_write(const char *name)
 
 	dirname[0] = 0;
 	if (name && name[0]) {
-		struct stat st;
 		char *slash;
 
-		if (!stat(name, &st) && S_ISDIR(st.st_mode)) {
+		if (is_dir(name)) {
 			strcpy(dirname, name);
 			strcat(dirname, "/");
 			basename = conf_get_configname();
@@ -853,7 +909,6 @@ static int conf_split_config(void)
 	char path[PATH_MAX+1];
 	char *s, *d, c;
 	struct symbol *sym;
-	struct stat sb;
 	int res, i, fd;
 
 	name = conf_get_autoconfig_name();
@@ -931,18 +986,10 @@ static int conf_split_config(void)
 				res = 1;
 				break;
 			}
-			/*
-			 * Create directory components,
-			 * unless they exist already.
-			 */
-			d = path;
-			while ((d = strchr(d, '/'))) {
-				*d = 0;
-				if (stat(path, &sb) && mkdir(path, 0755)) {
-					res = 1;
-					goto out;
-				}
-				*d++ = '/';
+
+			if (make_parent_dir(path)) {
+				res = 1;
+				goto out;
 			}
 			/* Try it again. */
 			fd = open(path, O_WRONLY | O_CREAT | O_TRUNC, 0644);
-- 
cgit v1.2.3


From adc18acf42a1e738c4c58090e0efe7977e812779 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:28 +0900
Subject: kconfig: remove unneeded directory generation from local*config

Commit 17263baf958b ("kconfig: Create include/generated for
localmodconfig") added the 'mkdir' line because local{yes,mod}config
ran streamline_config.pl followed by silentoldconfig at that time.

Since commit 81d2bc227305 ("kconfig: invoke oldconfig instead of
silentoldconfig from local*config"), no sub-directory is required.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/Makefile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index 49edb9cc9410..bd8da651c814 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -41,7 +41,6 @@ syncconfig: $(obj)/conf
 	$< $(silent) --$@ $(Kconfig)
 
 localyesconfig localmodconfig: $(obj)/conf
-	$(Q)mkdir -p include/config include/generated
 	$(Q)perl $(srctree)/$(src)/streamline_config.pl --$@ $(srctree) $(Kconfig) > .tmp.config
 	$(Q)if [ -f .config ]; then 					\
 			cmp -s .tmp.config .config ||			\
-- 
cgit v1.2.3


From 79123b1389cc775d8e60cb026256f79f0daef173 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:29 +0900
Subject: kconfig: create directories needed for syncconfig by itself

'make syncconfig' creates some files such as include/config/auto.conf,
include/generate/autoconf.h, etc. but the necessary directory creation
relies on scripts/kconfig/Makefile.

To make Kconfig self-contained, create directories as needed in
conf_write_autoconf().

This change allows scripts/kconfig/Makefile cleanups; syncconfig can
be merged into simple-targets.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/Makefile   | 15 ++++++---------
 scripts/kconfig/confdata.c | 14 ++++++++++++++
 2 files changed, 20 insertions(+), 9 deletions(-)

diff --git a/scripts/kconfig/Makefile b/scripts/kconfig/Makefile
index bd8da651c814..7f3eeca27ed4 100644
--- a/scripts/kconfig/Makefile
+++ b/scripts/kconfig/Makefile
@@ -3,8 +3,7 @@
 # Kernel configuration targets
 # These targets are used from top-level makefile
 
-PHONY += xconfig gconfig menuconfig config syncconfig \
-	localmodconfig localyesconfig
+PHONY += xconfig gconfig menuconfig config localmodconfig localyesconfig
 
 ifdef KBUILD_KCONFIG
 Kconfig := $(KBUILD_KCONFIG)
@@ -34,12 +33,6 @@ config: $(obj)/conf
 nconfig: $(obj)/nconf
 	$< $(silent) $(Kconfig)
 
-# This has become an internal implementation detail and is now deprecated
-# for external use.
-syncconfig: $(obj)/conf
-	$(Q)mkdir -p include/config include/generated
-	$< $(silent) --$@ $(Kconfig)
-
 localyesconfig localmodconfig: $(obj)/conf
 	$(Q)perl $(srctree)/$(src)/streamline_config.pl --$@ $(srctree) $(Kconfig) > .tmp.config
 	$(Q)if [ -f .config ]; then 					\
@@ -55,8 +48,12 @@ localyesconfig localmodconfig: $(obj)/conf
 	$(Q)rm -f .tmp.config
 
 # These targets map 1:1 to the commandline options of 'conf'
+#
+# Note:
+#  syncconfig has become an internal implementation detail and is now
+#  deprecated for external use
 simple-targets := oldconfig allnoconfig allyesconfig allmodconfig \
-	alldefconfig randconfig listnewconfig olddefconfig
+	alldefconfig randconfig listnewconfig olddefconfig syncconfig
 PHONY += $(simple-targets)
 
 $(simple-targets): $(obj)/conf
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index 88429d723c9c..fad403dfa508 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -899,6 +899,9 @@ static int conf_write_dep(const char *name)
 
 	fprintf(out, "\n$(deps_config): ;\n");
 	fclose(out);
+
+	if (make_parent_dir(name))
+		return 1;
 	rename("..config.tmp", name);
 	return 0;
 }
@@ -915,6 +918,8 @@ static int conf_split_config(void)
 	conf_read_simple(name, S_DEF_AUTO);
 	sym_calc_value(modules_sym);
 
+	if (make_parent_dir("include/config/foo.h"))
+		return 1;
 	if (chdir("include/config"))
 		return 1;
 
@@ -991,6 +996,7 @@ static int conf_split_config(void)
 				res = 1;
 				goto out;
 			}
+
 			/* Try it again. */
 			fd = open(path, O_WRONLY | O_CREAT | O_TRUNC, 0644);
 			if (fd == -1) {
@@ -1063,14 +1069,22 @@ int conf_write_autoconf(void)
 	name = getenv("KCONFIG_AUTOHEADER");
 	if (!name)
 		name = "include/generated/autoconf.h";
+	if (make_parent_dir(name))
+		return 1;
 	if (rename(".tmpconfig.h", name))
 		return 1;
+
 	name = getenv("KCONFIG_TRISTATE");
 	if (!name)
 		name = "include/config/tristate.conf";
+	if (make_parent_dir(name))
+		return 1;
 	if (rename(".tmpconfig_tristate", name))
 		return 1;
+
 	name = conf_get_autoconfig_name();
+	if (make_parent_dir(name))
+		return 1;
 	/*
 	 * This must be the last step, kbuild has a dependency on auto.conf
 	 * and this marks the successful completion of the previous steps.
-- 
cgit v1.2.3


From 16952b77d8b542fe5f3d73065a50842885b2ba0b Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:30 +0900
Subject: kconfig: make syncconfig update .config regardless of
 sym_change_count

syncconfig updates the .config only when sym_change_count > 0, i.e.
any change in config symbols has been detected.

Not only symbols but also comments are contained in the .config file.
If only comments are updated, they are not fed back to the .config,
then the stale comments are left-over.  Of course, this is just a
matter of comments, but why not fix it.

I see some scenarios where this happens.

Scenario A:

 1. You have a source tree that has already been configured.

 2. Linus increments the version number in the top-level Makefile
    (i.e. he commits a new release)

 3. You pull it, and run 'make'

 4. syncconfig is invoked because the environment variable,
    KERNELVERSION is updated, but the .config is not updated since
    no config symbol is changed.

 5. The .config file contains a kernel version in the top line:

    # Automatically generated file; DO NOT EDIT.
    # Linux/arm64 4.18.0-rc2 Kernel Configuration

    ... which points to a previous version.

Scenario B:

 1. You have a source tree that has already been configured.

 2. You upgrade the compiler, but it still has the same version number.
    This may happen if you regularly build the latest compiler from
    the source code.

 3. You run 'make'

 4. syncconfig is invoked because the environment variable,
    CC_VERSION_TEXT is updated, but the .config is not updated since
    no config symbol is changed.

 5. The .config file contains the version string of the compiler:

    #
    # Compiler: aarch64-linux-gcc (GCC) 9.0.0 20180628 (experimental)
    #

    ... which carries the information of the old compiler.

If KCONFIG_NOSILENTUPDATE is set, syncconfig is not allowed to update
the .config file.  Otherwise, it is fine to update it regardless of
sym_change_count.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/conf.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 671ff5364497..5af899112cae 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -496,6 +496,7 @@ int main(int ac, char **av)
 	int opt;
 	const char *name, *defconfig_file = NULL /* gcc uninit */;
 	struct stat tmpstat;
+	int no_conf_write = 0;
 
 	tty_stdio = isatty(0) && isatty(1);
 
@@ -633,13 +634,14 @@ int main(int ac, char **av)
 	}
 
 	if (sync_kconfig) {
-		if (conf_get_changed()) {
-			name = getenv("KCONFIG_NOSILENTUPDATE");
-			if (name && *name) {
+		name = getenv("KCONFIG_NOSILENTUPDATE");
+		if (name && *name) {
+			if (conf_get_changed()) {
 				fprintf(stderr,
 					"\n*** The configuration requires explicit update.\n\n");
 				return 1;
 			}
+			no_conf_write = 1;
 		}
 	}
 
@@ -688,7 +690,7 @@ int main(int ac, char **av)
 		/* syncconfig is used during the build so we shall update autoconf.
 		 * All other commands are only used to generate a config.
 		 */
-		if (conf_get_changed() && conf_write(NULL)) {
+		if (!no_conf_write && conf_write(NULL)) {
 			fprintf(stderr, "\n*** Error during writing of the configuration.\n\n");
 			exit(1);
 		}
-- 
cgit v1.2.3


From 00c864f8903dd357471e8ee48f4d57aaa9a1a0de Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:31 +0900
Subject: kconfig: allow all config targets to write auto.conf if missing

Currently, only syncconfig creates or updates include/config/auto.conf
and some other files.  Other config targets create or update only the
.config file.

When you configure and build the kernel from a pristine source tree,
any config target is followed by syncconfig in the build stage since
include/config/auto.conf is missing.

We are moving compiler tests from Makefile to Kconfig.  It means that
parsing Kconfig files will be more costly since Kconfig invokes the
compiler commands internally.  Thus, we want to avoid invoking Kconfig
twice (one for *config to create the .config, and one for syncconfig
to synchronize the auto.conf).  If auto.conf does not exist, we can
generate all configuration files in the first configuration stage,
which will save the syncconfig in the build stage.

Please note this should be done only when auto.conf is missing.  If
*config blindly did this, time stamp files under include/config/ would
be unnecessarily touched, triggering unneeded rebuild of objects.

I assume a scenario like this:

 1. You have a source tree that has already been built
    with CONFIG_FOO disabled

 2. Run "make menuconfig" to enable CONFIG_FOO

 3. CONFIG_FOO turns out to be unnecessary.
    Run "make menuconfig" again to disable CONFIG_FOO

 4. Run "make"

In this case, include/config/foo.h should not be touched since there
is no change in CONFIG_FOO.  The sync process should be delayed until
the user really attempts to build the kernel.

This commit has another motivation; I want to suppress the 'No such
file or directory' warning from the 'include' directive.

The top-level Makefile includes auto.conf with '-include' directive,
like this:

  ifeq ($(dot-config),1)
  -include include/config/auto.conf
  endif

This looks strange because auto.conf is mandatory when dot-config is 1.
I guess only the reason of using '-include' is to suppress the warning
'include/config/auto.conf: No such file or directory' when building
from a clean tree.  However, this has a side-effect; Make considers
the files included by '-include' are optional.  Hence, Make continues
to build even if it fails to generate include/config/auto.conf.  I will
change this in the next commit, but the warning message is annoying.
(At least, kbuild test robot reports it as a regression.)

With this commit, Kconfig will generate all configuration files together
with the .config and I guess it is a solution good enough to suppress
the warning.

Note:
GNU Make 4.2 or later does not display the warning from the 'include'
directive if include files are successfully generated.  See GNU Make
commit 87a5f98d248f ("[SV 102] Don't show unnecessary include file
errors.")  However, older GNU Make versions are still widely used.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/conf.c      | 31 +++++++++++++++++--------------
 scripts/kconfig/confdata.c  | 11 +++++++----
 scripts/kconfig/gconf.c     |  1 +
 scripts/kconfig/lkc_proto.h |  2 +-
 scripts/kconfig/mconf.c     |  1 +
 scripts/kconfig/nconf.c     |  1 +
 scripts/kconfig/qconf.cc    |  2 ++
 7 files changed, 30 insertions(+), 19 deletions(-)

diff --git a/scripts/kconfig/conf.c b/scripts/kconfig/conf.c
index 5af899112cae..b35cc9303979 100644
--- a/scripts/kconfig/conf.c
+++ b/scripts/kconfig/conf.c
@@ -686,29 +686,32 @@ int main(int ac, char **av)
 		break;
 	}
 
-	if (sync_kconfig) {
-		/* syncconfig is used during the build so we shall update autoconf.
-		 * All other commands are only used to generate a config.
-		 */
-		if (!no_conf_write && conf_write(NULL)) {
-			fprintf(stderr, "\n*** Error during writing of the configuration.\n\n");
-			exit(1);
-		}
-		if (conf_write_autoconf()) {
-			fprintf(stderr, "\n*** Error during update of the configuration.\n\n");
-			return 1;
-		}
-	} else if (input_mode == savedefconfig) {
+	if (input_mode == savedefconfig) {
 		if (conf_write_defconfig(defconfig_file)) {
 			fprintf(stderr, "n*** Error while saving defconfig to: %s\n\n",
 				defconfig_file);
 			return 1;
 		}
 	} else if (input_mode != listnewconfig) {
-		if (conf_write(NULL)) {
+		if (!no_conf_write && conf_write(NULL)) {
 			fprintf(stderr, "\n*** Error during writing of the configuration.\n\n");
 			exit(1);
 		}
+
+		/*
+		 * Create auto.conf if it does not exist.
+		 * This prevents GNU Make 4.1 or older from emitting
+		 * "include/config/auto.conf: No such file or directory"
+		 * in the top-level Makefile
+		 *
+		 * syncconfig always creates or updates auto.conf because it is
+		 * used during the build.
+		 */
+		if (conf_write_autoconf(sync_kconfig) && sync_kconfig) {
+			fprintf(stderr,
+				"\n*** Error during sync of the configuration.\n\n");
+			return 1;
+		}
 	}
 	return 0;
 }
diff --git a/scripts/kconfig/confdata.c b/scripts/kconfig/confdata.c
index fad403dfa508..91d0a5c014ac 100644
--- a/scripts/kconfig/confdata.c
+++ b/scripts/kconfig/confdata.c
@@ -1013,13 +1013,17 @@ out:
 	return res;
 }
 
-int conf_write_autoconf(void)
+int conf_write_autoconf(int overwrite)
 {
 	struct symbol *sym;
 	const char *name;
+	const char *autoconf_name = conf_get_autoconfig_name();
 	FILE *out, *tristate, *out_h;
 	int i;
 
+	if (!overwrite && is_present(autoconf_name))
+		return 0;
+
 	sym_clear_all_valid();
 
 	conf_write_dep("include/config/auto.conf.cmd");
@@ -1082,14 +1086,13 @@ int conf_write_autoconf(void)
 	if (rename(".tmpconfig_tristate", name))
 		return 1;
 
-	name = conf_get_autoconfig_name();
-	if (make_parent_dir(name))
+	if (make_parent_dir(autoconf_name))
 		return 1;
 	/*
 	 * This must be the last step, kbuild has a dependency on auto.conf
 	 * and this marks the successful completion of the previous steps.
 	 */
-	if (rename(".tmpconfig", name))
+	if (rename(".tmpconfig", autoconf_name))
 		return 1;
 
 	return 0;
diff --git a/scripts/kconfig/gconf.c b/scripts/kconfig/gconf.c
index a9e48cc7b50a..36f578415c4a 100644
--- a/scripts/kconfig/gconf.c
+++ b/scripts/kconfig/gconf.c
@@ -525,6 +525,7 @@ void on_save_activate(GtkMenuItem * menuitem, gpointer user_data)
 {
 	if (conf_write(NULL))
 		text_insert_msg("Error", "Unable to save configuration !");
+	conf_write_autoconf(0);
 }
 
 
diff --git a/scripts/kconfig/lkc_proto.h b/scripts/kconfig/lkc_proto.h
index cf4510a2bdc7..86c267540ccc 100644
--- a/scripts/kconfig/lkc_proto.h
+++ b/scripts/kconfig/lkc_proto.h
@@ -7,7 +7,7 @@ int conf_read(const char *name);
 int conf_read_simple(const char *name, int);
 int conf_write_defconfig(const char *name);
 int conf_write(const char *name);
-int conf_write_autoconf(void);
+int conf_write_autoconf(int overwrite);
 bool conf_get_changed(void);
 void conf_set_changed_callback(void (*fn)(void));
 void conf_set_message_callback(void (*fn)(const char *s));
diff --git a/scripts/kconfig/mconf.c b/scripts/kconfig/mconf.c
index b8f3b607962a..83b5836615fb 100644
--- a/scripts/kconfig/mconf.c
+++ b/scripts/kconfig/mconf.c
@@ -974,6 +974,7 @@ static int handle_exit(void)
 					  "\n\n");
 			return 1;
 		}
+		conf_write_autoconf(0);
 		/* fall through */
 	case -1:
 		if (!silent)
diff --git a/scripts/kconfig/nconf.c b/scripts/kconfig/nconf.c
index 5cbdb92e11b3..1ef232ae5ab9 100644
--- a/scripts/kconfig/nconf.c
+++ b/scripts/kconfig/nconf.c
@@ -674,6 +674,7 @@ static int do_exit(void)
 				  "Your configuration changes were NOT saved.",
 				  1,
 				  "<OK>");
+		conf_write_autoconf(0);
 		break;
 	default:
 		btn_dialog(
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index ad9c22dd04f5..62261b3a13c7 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -1535,6 +1535,8 @@ bool ConfigMainWindow::saveConfig(void)
 		QMessageBox::information(this, "qconf", "Unable to save configuration!");
 		return false;
 	}
+	conf_write_autoconf(0);
+
 	return true;
 }
 
-- 
cgit v1.2.3


From 0a16d2e8cb7e6310debc208d42ff725361ae1911 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:32 +0900
Subject: kbuild: use 'include' directive to load auto.conf from top Makefile

When you build targets that require the kernel configuration, dot-config
is set to 1, then the top-level Makefile includes auto.conf.  However,
Make considers its inclusion is optional because the '-include' directive
is used here.

If a necessary configuration file is missing for the external module
building, the following error message is displayed:

  ERROR: Kernel configuration is invalid.
         include/generated/autoconf.h or include/config/auto.conf are missing.
         Run 'make oldconfig && make prepare' on kernel src to fix it.

However, Make still continues building; /bin/false let the creation of
'include/config/auto.config' fail, but Make can ignore the error since
it is included by the '-include' directive.

I guess the reason of using '-include' directive was to suppress
the warning when you build the kernel from a pristine source tree:

  Makefile:605: include/config/auto.conf: No such file or directory

The previous commit made sure include/config/auto.conf exists after
the 'make *config' stage.  Now, we can use the 'include' directive
without showing the warning.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index a89d8a0d3ee1..6a222e21ca6d 100644
--- a/Makefile
+++ b/Makefile
@@ -584,7 +584,7 @@ virt-y		:= virt/
 endif # KBUILD_EXTMOD
 
 ifeq ($(dot-config),1)
--include include/config/auto.conf
+include include/config/auto.conf
 endif
 
 # The all: target is the default when no target is given on the
-- 
cgit v1.2.3


From 9c2af1c7377a8a6ef86e5cabf80978f3dbbb25c0 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:33 +0900
Subject: kbuild: add .DELETE_ON_ERROR special target
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If Make gets a fatal signal while a shell is executing, it may delete
the target file that the recipe was supposed to update.  This is needed
to make sure that it is remade from scratch when Make is next run; if
Make is interrupted after the recipe has begun to write the target file,
it results in an incomplete file whose time stamp is newer than that
of the prerequisites files.  Make automatically deletes the incomplete
file on interrupt unless the target is marked .PRECIOUS.

The situation is just the same as when the shell fails for some reasons.
Usually when a recipe line fails, if it has changed the target file at
all, the file is corrupted, or at least it is not completely updated.
Yet the file’s time stamp says that it is now up to date, so the next
time Make runs, it will not try to update that file.

However, Make does not cater to delete the incomplete target file in
this case.  We need to add .DELETE_ON_ERROR somewhere in the Makefile
to request it.

scripts/Kbuild.include seems a suitable place to add it because it is
included from almost all sub-makes.

Please note .DELETE_ON_ERROR is not effective for phony targets.

The external module building should never ever touch the kernel tree.
The following recipe fails if include/generated/autoconf.h is missing.
However, include/config/auto.conf is not deleted since it is a phony
target.

 PHONY += include/config/auto.conf

 include/config/auto.conf:
         $(Q)test -e include/generated/autoconf.h -a -e $@ || (          \
         echo >&2;                                                       \
         echo >&2 "  ERROR: Kernel configuration is invalid.";           \
         echo >&2 "         include/generated/autoconf.h or $@ are missing.";\
         echo >&2 "         Run 'make oldconfig && make prepare' on kernel src to fix it."; \
         echo >&2 ;                                                      \
         /bin/false)

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/Kbuild.include | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 86321f06461e..ed303f552f9d 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -400,3 +400,6 @@ endif
 endef
 #
 ###############################################################################
+
+# delete partially updated (i.e. corrupted) files on error
+.DELETE_ON_ERROR:
-- 
cgit v1.2.3


From d79424137a7312d381d131d707a462440c0e8df9 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:34 +0900
Subject: kbuild: do not update config when running install targets

"make syncconfig" is automatically invoked when any of the following
happens:

 - .config is updated
 - any of Kconfig files is updated
 - any of environment variables referenced in Kconfig is changed

Then, it updates configuration files such as include/config/auto.conf
include/generated/autoconf.h, etc.

Even install targets (install, modules_install, etc.) are no exception.
However, they should never ever modify the source tree.  Install
targets are often run with root privileges.  Once those configuration
files are owned by root, "make mrproper" would end up with permission
error.

Install targets should just copy things blindly.  They should not care
whether the configuration is up-to-date or not.  This makes more sense
because we are interested in the configuration that was used in the
previous kernel building.

This issue has existed since before, but rarely happened.  I expect
more chance where people are hit by this; with the new Kconfig syntax
extension, the .config now contains the compiler information.  If you
cross-compile the kernel with CROSS_COMPILE, but forget to pass it
for "make install", you meet "any of environment variables referenced
in Kconfig is changed" because $(CC) is referenced in Kconfig.
Another scenario is the compiler upgrade before the installation.

Install targets need the configuration.  "make modules_install" refer
to CONFIG_MODULES etc.  "make dtbs_install" also needs CONFIG_ARCH_*
to decide which dtb files to install.  However, the auto-update of
the configuration files should be avoided.  We already do this for
external modules.

Now, Make targets are categorized into 3 groups:

[1] Do not need the kernel configuration at all

    help, coccicheck, headers_install etc.

[2] Need the latest kernel configuration

    If new config options are added, Kconfig will show prompt to
    ask user's selection.

    Build targets such as vmlinux, in-kernel modules are the cases.

[3] Need the kernel configuration, but do not want to update it

    Install targets except headers_install, and external modules
    are the cases.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile | 27 ++++++++++++++++++++-------
 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/Makefile b/Makefile
index 6a222e21ca6d..8ca9e0b114f1 100644
--- a/Makefile
+++ b/Makefile
@@ -225,10 +225,12 @@ no-dot-config-targets := $(clean-targets) \
 			 cscope gtags TAGS tags help% %docs check% coccicheck \
 			 $(version_h) headers_% archheaders archscripts \
 			 kernelversion %src-pkg
+no-sync-config-targets := $(no-dot-config-targets) install %install
 
-config-targets := 0
-mixed-targets  := 0
-dot-config     := 1
+config-targets  := 0
+mixed-targets   := 0
+dot-config      := 1
+may-sync-config := 1
 
 ifneq ($(filter $(no-dot-config-targets), $(MAKECMDGOALS)),)
 	ifeq ($(filter-out $(no-dot-config-targets), $(MAKECMDGOALS)),)
@@ -236,6 +238,16 @@ ifneq ($(filter $(no-dot-config-targets), $(MAKECMDGOALS)),)
 	endif
 endif
 
+ifneq ($(filter $(no-sync-config-targets), $(MAKECMDGOALS)),)
+	ifeq ($(filter-out $(no-sync-config-targets), $(MAKECMDGOALS)),)
+		may-sync-config := 0
+	endif
+endif
+
+ifneq ($(KBUILD_EXTMOD),)
+	may-sync-config := 0
+endif
+
 ifeq ($(KBUILD_EXTMOD),)
         ifneq ($(filter config %config,$(MAKECMDGOALS)),)
                 config-targets := 1
@@ -606,7 +618,7 @@ ARCH_CFLAGS :=
 include arch/$(SRCARCH)/Makefile
 
 ifeq ($(dot-config),1)
-ifeq ($(KBUILD_EXTMOD),)
+ifeq ($(may-sync-config),1)
 # Read in dependencies to all Kconfig* files, make sure to run syncconfig if
 # changes are detected. This should be included after arch/$(SRCARCH)/Makefile
 # because some architectures define CROSS_COMPILE there.
@@ -621,8 +633,9 @@ $(KCONFIG_CONFIG) include/config/auto.conf.cmd: ;
 include/config/%.conf: $(KCONFIG_CONFIG) include/config/auto.conf.cmd
 	$(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
 else
-# external modules needs include/generated/autoconf.h and include/config/auto.conf
-# but do not care if they are up-to-date. Use auto.conf to trigger the test
+# External modules and some install targets need include/generated/autoconf.h
+# and include/config/auto.conf but do not care if they are up-to-date.
+# Use auto.conf to trigger the test
 PHONY += include/config/auto.conf
 
 include/config/auto.conf:
@@ -634,7 +647,7 @@ include/config/auto.conf:
 	echo >&2 ;							\
 	/bin/false)
 
-endif # KBUILD_EXTMOD
+endif # may-sync-config
 
 else
 # Dummy target needed, because used as prerequisite
-- 
cgit v1.2.3


From a29d4d8c5669a658b5a091b38205c13084967ce7 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:35 +0900
Subject: kbuild: do not update config for 'make kernelrelease'

'make kernelrelease' depends on CONFIG_LOCALVERSION(_AUTO), but
for the same reason as install targets, we do not want to update
the configuration just for printing the kernelrelease string.

This is likely to happen when you compiled the kernel with
CROSS_COMPILE, but forget to pass it to 'make kernelrelease'.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 8ca9e0b114f1..060874d85e0d 100644
--- a/Makefile
+++ b/Makefile
@@ -225,7 +225,8 @@ no-dot-config-targets := $(clean-targets) \
 			 cscope gtags TAGS tags help% %docs check% coccicheck \
 			 $(version_h) headers_% archheaders archscripts \
 			 kernelversion %src-pkg
-no-sync-config-targets := $(no-dot-config-targets) install %install
+no-sync-config-targets := $(no-dot-config-targets) install %install \
+			   kernelrelease
 
 config-targets  := 0
 mixed-targets   := 0
-- 
cgit v1.2.3


From 2063945fdc3d4c0ac8f9319d942eda720d02aabe Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 16:46:36 +0900
Subject: kbuild: remove auto.conf from prerequisite of phony targets

The top-level Makefile adds include/config/auto.conf as
prerequisites of 'scripts', 'prepare1', etc.

They were needed to terminate the build when include/config/auto.conf
is missing.

Now that the inclusion of include/config/auto.conf is mandatory
in the top-level Makefile if dot-config is 1 (Note 'include' directive
is used instead of '-include').

Make terminates the build by itself if it fails to create or update
include/config/auto.conf so we are sure that include/config/auto.conf
exists in the very first stage of make.

I am still keeping include/config/auto.conf as the prerequisite of
%/modules.builtin because modules.builtin is a real file.  According
to commit a6c366324cac ("kbuild: Do not unnecessarily regenerate
modules.builtin"), it is intentional to compare time-stamps between
%/modules.builtin and include/config/auto.conf .  I moved tristate.conf
here because it is only included from scripts/Makefile.modbuiltin.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/Makefile b/Makefile
index 060874d85e0d..f17dd994e01d 100644
--- a/Makefile
+++ b/Makefile
@@ -649,10 +649,6 @@ include/config/auto.conf:
 	/bin/false)
 
 endif # may-sync-config
-
-else
-# Dummy target needed, because used as prerequisite
-include/config/auto.conf: ;
 endif # $(dot-config)
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
@@ -1047,15 +1043,14 @@ define filechk_kernel.release
 endef
 
 # Store (new) KERNELRELEASE string in include/config/kernel.release
-include/config/kernel.release: include/config/auto.conf FORCE
+include/config/kernel.release: $(srctree)/Makefile FORCE
 	$(call filechk,kernel.release)
 
 # Additional helpers built in scripts/
 # Carefully list dependencies so we do not try to build scripts twice
 # in parallel
 PHONY += scripts
-scripts: scripts_basic include/config/auto.conf include/config/tristate.conf \
-	 asm-generic gcc-plugins $(autoksyms_h)
+scripts: scripts_basic asm-generic gcc-plugins $(autoksyms_h)
 	$(Q)$(MAKE) $(build)=$(@)
 
 # Things we need to do before we recursively start building the kernel
@@ -1085,8 +1080,7 @@ endif
 # that need to depend on updated CONFIG_* values can be checked here.
 prepare2: prepare3 outputmakefile asm-generic
 
-prepare1: prepare2 $(version_h) $(autoksyms_h) include/generated/utsrelease.h \
-                   include/config/auto.conf
+prepare1: prepare2 $(version_h) $(autoksyms_h) include/generated/utsrelease.h
 	$(cmd_crmodverdir)
 
 archprepare: archheaders archscripts prepare1 scripts_basic
@@ -1224,7 +1218,7 @@ modules: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) modules.builtin
 modules.builtin: $(vmlinux-dirs:%=%/modules.builtin)
 	$(Q)$(AWK) '!x[$$0]++' $^ > $(objtree)/modules.builtin
 
-%/modules.builtin: include/config/auto.conf
+%/modules.builtin: include/config/auto.conf include/config/tristate.conf
 	$(Q)$(MAKE) $(modbuiltin)=$*
 
 
-- 
cgit v1.2.3


From d3df0ac09654e9db82a882031ccae010f1b7575b Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Wed, 25 Jul 2018 09:42:07 +0200
Subject: xen/blkfront: remove unused macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove some macros not used anywhere.

Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/xen-blkfront.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index b5cedccb5d7d..94300dbe358b 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -251,14 +251,9 @@ static DEFINE_SPINLOCK(minor_lock);
 #define GRANTS_PER_INDIRECT_FRAME \
 	(XEN_PAGE_SIZE / sizeof(struct blkif_request_segment))
 
-#define PSEGS_PER_INDIRECT_FRAME	\
-	(GRANTS_INDIRECT_FRAME / GRANTS_PSEGS)
-
 #define INDIRECT_GREFS(_grants)		\
 	DIV_ROUND_UP(_grants, GRANTS_PER_INDIRECT_FRAME)
 
-#define GREFS(_psegs)	((_psegs) * GRANTS_PER_PSEG)
-
 static int blkfront_setup_indirect(struct blkfront_ring_info *rinfo);
 static void blkfront_gather_backend_features(struct blkfront_info *info);
 static int negotiate_mq(struct blkfront_info *info);
-- 
cgit v1.2.3


From d77a760842751eb620a7e74f74e5a5ad6b3d6cef Mon Sep 17 00:00:00 2001
From: Bard Liao <bardliao@realtek.com>
Date: Fri, 20 Jul 2018 09:48:20 +0800
Subject: ASoC: rt5631: add Volume to the name of volume control

add Volume to the name of volume control.

Signed-off-by: Bard Liao <bardliao@realtek.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5631.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/rt5631.c b/sound/soc/codecs/rt5631.c
index cf6dce69eb2a..e52e4670cf65 100644
--- a/sound/soc/codecs/rt5631.c
+++ b/sound/soc/codecs/rt5631.c
@@ -229,10 +229,10 @@ static SOC_ENUM_SINGLE_DECL(rt5631_spk_ratio_enum, RT5631_GEN_PUR_CTRL_REG,
 static const struct snd_kcontrol_new rt5631_snd_controls[] = {
 	/* MIC */
 	SOC_ENUM("MIC1 Mode Control",  rt5631_mic1_mode_enum),
-	SOC_SINGLE_TLV("MIC1 Boost", RT5631_MIC_CTRL_2,
+	SOC_SINGLE_TLV("MIC1 Boost Volume", RT5631_MIC_CTRL_2,
 		RT5631_MIC1_BOOST_SHIFT, 8, 0, mic_bst_tlv),
 	SOC_ENUM("MIC2 Mode Control", rt5631_mic2_mode_enum),
-	SOC_SINGLE_TLV("MIC2 Boost", RT5631_MIC_CTRL_2,
+	SOC_SINGLE_TLV("MIC2 Boost Volume", RT5631_MIC_CTRL_2,
 		RT5631_MIC2_BOOST_SHIFT, 8, 0, mic_bst_tlv),
 	/* MONO IN */
 	SOC_ENUM("MONOIN Mode Control", rt5631_monoin_mode_enum),
-- 
cgit v1.2.3


From 92beb0a26975c6459794d885d27f48357c1aefd0 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 24 Jul 2018 16:12:44 -0500
Subject: ASoC: Intel: Haswell: fix endianness handling

Make all Sparse warnings go away by using le16/32_to_cpu.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/haswell/sst-haswell-dsp.c | 53 +++++++++++++++++--------------
 1 file changed, 29 insertions(+), 24 deletions(-)

diff --git a/sound/soc/intel/haswell/sst-haswell-dsp.c b/sound/soc/intel/haswell/sst-haswell-dsp.c
index b2bec36d074c..a28220e67cdf 100644
--- a/sound/soc/intel/haswell/sst-haswell-dsp.c
+++ b/sound/soc/intel/haswell/sst-haswell-dsp.c
@@ -93,29 +93,31 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 	struct sst_module_template template;
 	int count, ret;
 	void __iomem *ram;
+	int type = le16_to_cpu(module->type);
+	int entry_point = le32_to_cpu(module->entry_point);
 
 	/* TODO: allowed module types need to be configurable */
-	if (module->type != SST_HSW_MODULE_BASE_FW
-		&& module->type != SST_HSW_MODULE_PCM_SYSTEM
-		&& module->type != SST_HSW_MODULE_PCM
-		&& module->type != SST_HSW_MODULE_PCM_REFERENCE
-		&& module->type != SST_HSW_MODULE_PCM_CAPTURE
-		&& module->type != SST_HSW_MODULE_WAVES
-		&& module->type != SST_HSW_MODULE_LPAL)
+	if (type != SST_HSW_MODULE_BASE_FW &&
+	    type != SST_HSW_MODULE_PCM_SYSTEM &&
+	    type != SST_HSW_MODULE_PCM &&
+	    type != SST_HSW_MODULE_PCM_REFERENCE &&
+	    type != SST_HSW_MODULE_PCM_CAPTURE &&
+	    type != SST_HSW_MODULE_WAVES &&
+	    type != SST_HSW_MODULE_LPAL)
 		return 0;
 
 	dev_dbg(dsp->dev, "new module sign 0x%s size 0x%x blocks 0x%x type 0x%x\n",
 		module->signature, module->mod_size,
-		module->blocks, module->type);
-	dev_dbg(dsp->dev, " entrypoint 0x%x\n", module->entry_point);
+		module->blocks, type);
+	dev_dbg(dsp->dev, " entrypoint 0x%x\n", entry_point);
 	dev_dbg(dsp->dev, " persistent 0x%x scratch 0x%x\n",
 		module->info.persistent_size, module->info.scratch_size);
 
 	memset(&template, 0, sizeof(template));
-	template.id = module->type;
-	template.entry = module->entry_point - 4;
-	template.persistent_size = module->info.persistent_size;
-	template.scratch_size = module->info.scratch_size;
+	template.id = type;
+	template.entry = entry_point - 4;
+	template.persistent_size = le32_to_cpu(module->info.persistent_size);
+	template.scratch_size = le32_to_cpu(module->info.scratch_size);
 
 	mod = sst_module_new(fw, &template, NULL);
 	if (mod == NULL)
@@ -123,26 +125,26 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 
 	block = (void *)module + sizeof(*module);
 
-	for (count = 0; count < module->blocks; count++) {
+	for (count = 0; count < le32_to_cpu(module->blocks); count++) {
 
-		if (block->size <= 0) {
+		if (le32_to_cpu(block->size) <= 0) {
 			dev_err(dsp->dev,
 				"error: block %d size invalid\n", count);
 			sst_module_free(mod);
 			return -EINVAL;
 		}
 
-		switch (block->type) {
+		switch (le32_to_cpu(block->type)) {
 		case SST_HSW_IRAM:
 			ram = dsp->addr.lpe;
-			mod->offset =
-				block->ram_offset + dsp->addr.iram_offset;
+			mod->offset = le32_to_cpu(block->ram_offset) +
+				dsp->addr.iram_offset;
 			mod->type = SST_MEM_IRAM;
 			break;
 		case SST_HSW_DRAM:
 		case SST_HSW_REGS:
 			ram = dsp->addr.lpe;
-			mod->offset = block->ram_offset;
+			mod->offset = le32_to_cpu(block->ram_offset);
 			mod->type = SST_MEM_DRAM;
 			break;
 		default:
@@ -152,7 +154,7 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 			return -EINVAL;
 		}
 
-		mod->size = block->size;
+		mod->size = le32_to_cpu(block->size);
 		mod->data = (void *)block + sizeof(*block);
 		mod->data_offset = mod->data - fw->dma_buf;
 
@@ -169,7 +171,8 @@ static int hsw_parse_module(struct sst_dsp *dsp, struct sst_fw *fw,
 			return ret;
 		}
 
-		block = (void *)block + sizeof(*block) + block->size;
+		block = (void *)block + sizeof(*block) +
+			le32_to_cpu(block->size);
 	}
 	mod->state = SST_MODULE_STATE_LOADED;
 
@@ -188,7 +191,8 @@ static int hsw_parse_fw_image(struct sst_fw *sst_fw)
 
 	/* verify FW */
 	if ((strncmp(header->signature, SST_HSW_FW_SIGN, 4) != 0) ||
-		(sst_fw->size != header->file_size + sizeof(*header))) {
+	    (sst_fw->size !=
+	     le32_to_cpu(header->file_size) + sizeof(*header))) {
 		dev_err(dsp->dev, "error: invalid fw sign/filesize mismatch\n");
 		return -EINVAL;
 	}
@@ -199,7 +203,7 @@ static int hsw_parse_fw_image(struct sst_fw *sst_fw)
 
 	/* parse each module */
 	module = (void *)sst_fw->dma_buf + sizeof(*header);
-	for (count = 0; count < header->modules; count++) {
+	for (count = 0; count < le32_to_cpu(header->modules); count++) {
 
 		/* module */
 		ret = hsw_parse_module(dsp, sst_fw, module);
@@ -207,7 +211,8 @@ static int hsw_parse_fw_image(struct sst_fw *sst_fw)
 			dev_err(dsp->dev, "error: invalid module %d\n", count);
 			return ret;
 		}
-		module = (void *)module + sizeof(*module) + module->mod_size;
+		module = (void *)module + sizeof(*module) +
+			le32_to_cpu(module->mod_size);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 86efd35ec1e34094914494dacb83077e5df2d1b8 Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 24 Jul 2018 16:12:45 -0500
Subject: ASoC: Intel: Skylake: BDL definitions should be __le32

Make sure definitions are consistent with usage.
Detected with Sparse.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/skylake/skl-sst-cldma.c | 8 ++++----
 sound/soc/intel/skylake/skl-sst-cldma.h | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/sound/soc/intel/skylake/skl-sst-cldma.c b/sound/soc/intel/skylake/skl-sst-cldma.c
index d2b1d60fec02..5bc0d38da7e3 100644
--- a/sound/soc/intel/skylake/skl-sst-cldma.c
+++ b/sound/soc/intel/skylake/skl-sst-cldma.c
@@ -83,9 +83,9 @@ static void skl_cldma_stream_clear(struct sst_dsp  *ctx)
 /* Code loader helper APIs */
 static void skl_cldma_setup_bdle(struct sst_dsp *ctx,
 		struct snd_dma_buffer *dmab_data,
-		u32 **bdlp, int size, int with_ioc)
+		__le32 **bdlp, int size, int with_ioc)
 {
-	u32 *bdl = *bdlp;
+	__le32 *bdl = *bdlp;
 
 	ctx->cl_dev.frags = 0;
 	while (size > 0) {
@@ -330,7 +330,7 @@ void skl_cldma_process_intr(struct sst_dsp *ctx)
 int skl_cldma_prepare(struct sst_dsp *ctx)
 {
 	int ret;
-	u32 *bdl;
+	__le32 *bdl;
 
 	ctx->cl_dev.bufsize = SKL_MAX_BUFFER_SIZE;
 
@@ -359,7 +359,7 @@ int skl_cldma_prepare(struct sst_dsp *ctx)
 		ctx->dsp_ops.free_dma_buf(ctx->dev, &ctx->cl_dev.dmab_data);
 		return ret;
 	}
-	bdl = (u32 *)ctx->cl_dev.dmab_bdl.area;
+	bdl = (__le32 *)ctx->cl_dev.dmab_bdl.area;
 
 	/* Allocate BDLs */
 	ctx->cl_dev.ops.cl_setup_bdle(ctx, &ctx->cl_dev.dmab_data,
diff --git a/sound/soc/intel/skylake/skl-sst-cldma.h b/sound/soc/intel/skylake/skl-sst-cldma.h
index 5b730a1a0ae4..ec736921a083 100644
--- a/sound/soc/intel/skylake/skl-sst-cldma.h
+++ b/sound/soc/intel/skylake/skl-sst-cldma.h
@@ -203,7 +203,7 @@ struct sst_dsp;
 struct skl_cl_dev_ops {
 	void (*cl_setup_bdle)(struct sst_dsp *ctx,
 			struct snd_dma_buffer *dmab_data,
-			u32 **bdlp, int size, int with_ioc);
+			__le32 **bdlp, int size, int with_ioc);
 	void (*cl_setup_controller)(struct sst_dsp *ctx,
 			struct snd_dma_buffer *dmab_bdl,
 			unsigned int max_size, u32 page_count);
-- 
cgit v1.2.3


From ef3cb7423358ff0cadacb76f26e3e1f4da8be4ce Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 24 Jul 2018 16:12:46 -0500
Subject: ASoC: Intel: common: make sst_dma functions static

sst_dma_new and sst_dma_free are not used in any other file and don't
have a prototype. Move to static functions and remove
EXPORT_SYMBOL_GPL statement.

Reported by sparse warnings.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/common/sst-firmware.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/sound/soc/intel/common/sst-firmware.c b/sound/soc/intel/common/sst-firmware.c
index 657afc02f1c4..11041aedea31 100644
--- a/sound/soc/intel/common/sst-firmware.c
+++ b/sound/soc/intel/common/sst-firmware.c
@@ -270,7 +270,7 @@ void sst_dsp_dma_put_channel(struct sst_dsp *dsp)
 }
 EXPORT_SYMBOL_GPL(sst_dsp_dma_put_channel);
 
-int sst_dma_new(struct sst_dsp *sst)
+static int sst_dma_new(struct sst_dsp *sst)
 {
 	struct sst_pdata *sst_pdata = sst->pdata;
 	struct sst_dma *dma;
@@ -320,9 +320,8 @@ err_dma_dev:
 	devm_kfree(sst->dev, dma);
 	return ret;
 }
-EXPORT_SYMBOL(sst_dma_new);
 
-void sst_dma_free(struct sst_dma *dma)
+static void sst_dma_free(struct sst_dma *dma)
 {
 
 	if (dma == NULL)
@@ -335,7 +334,6 @@ void sst_dma_free(struct sst_dma *dma)
 		dw_remove(dma->chip);
 
 }
-EXPORT_SYMBOL(sst_dma_free);
 
 /* create new generic firmware object */
 struct sst_fw *sst_fw_new(struct sst_dsp *dsp, 
-- 
cgit v1.2.3


From ce1cfe295abaa7436f9049bcb2562c843089abfc Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 24 Jul 2018 16:12:47 -0500
Subject: ASoC: Intel: Atom: simplify iomem address and casts

Simplify code and add relevant casts to make Sparse warnings go away

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/atom/sst/sst_drv_interface.c | 29 ++++++++++++++--------------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/sound/soc/intel/atom/sst/sst_drv_interface.c b/sound/soc/intel/atom/sst/sst_drv_interface.c
index 6a8b253c58d2..5455d6e0ab53 100644
--- a/sound/soc/intel/atom/sst/sst_drv_interface.c
+++ b/sound/soc/intel/atom/sst/sst_drv_interface.c
@@ -266,17 +266,15 @@ static int sst_cdev_ack(struct device *dev, unsigned int str_id,
 	stream->cumm_bytes += bytes;
 	dev_dbg(dev, "bytes copied %d inc by %ld\n", stream->cumm_bytes, bytes);
 
-	memcpy_fromio(&fw_tstamp,
-		((void *)(ctx->mailbox + ctx->tstamp)
-		+(str_id * sizeof(fw_tstamp))),
-		sizeof(fw_tstamp));
+	addr =  ((void __iomem *)(ctx->mailbox + ctx->tstamp)) +
+		(str_id * sizeof(fw_tstamp));
+
+	memcpy_fromio(&fw_tstamp, addr, sizeof(fw_tstamp));
 
 	fw_tstamp.bytes_copied = stream->cumm_bytes;
 	dev_dbg(dev, "bytes sent to fw %llu inc by %ld\n",
 			fw_tstamp.bytes_copied, bytes);
 
-	addr =  ((void *)(ctx->mailbox + ctx->tstamp)) +
-			(str_id * sizeof(fw_tstamp));
 	offset =  offsetof(struct snd_sst_tstamp, bytes_copied);
 	sst_shim_write(addr, offset, fw_tstamp.bytes_copied);
 	return 0;
@@ -360,11 +358,12 @@ static int sst_cdev_tstamp(struct device *dev, unsigned int str_id,
 	struct snd_sst_tstamp fw_tstamp = {0,};
 	struct stream_info *stream;
 	struct intel_sst_drv *ctx = dev_get_drvdata(dev);
+	void __iomem *addr;
+
+	addr = (void __iomem *)(ctx->mailbox + ctx->tstamp) +
+		(str_id * sizeof(fw_tstamp));
 
-	memcpy_fromio(&fw_tstamp,
-		((void *)(ctx->mailbox + ctx->tstamp)
-		+(str_id * sizeof(fw_tstamp))),
-		sizeof(fw_tstamp));
+	memcpy_fromio(&fw_tstamp, addr, sizeof(fw_tstamp));
 
 	stream = get_stream_info(ctx, str_id);
 	if (!stream)
@@ -530,6 +529,7 @@ static int sst_read_timestamp(struct device *dev, struct pcm_stream_info *info)
 	struct snd_sst_tstamp fw_tstamp;
 	unsigned int str_id;
 	struct intel_sst_drv *ctx = dev_get_drvdata(dev);
+	void __iomem *addr;
 
 	str_id = info->str_id;
 	stream = get_stream_info(ctx, str_id);
@@ -540,10 +540,11 @@ static int sst_read_timestamp(struct device *dev, struct pcm_stream_info *info)
 		return -EINVAL;
 	substream = stream->pcm_substream;
 
-	memcpy_fromio(&fw_tstamp,
-		((void *)(ctx->mailbox + ctx->tstamp)
-			+ (str_id * sizeof(fw_tstamp))),
-		sizeof(fw_tstamp));
+	addr = (void __iomem *)(ctx->mailbox + ctx->tstamp) +
+		(str_id * sizeof(fw_tstamp));
+
+	memcpy_fromio(&fw_tstamp, addr, sizeof(fw_tstamp));
+
 	return sst_calc_tstamp(ctx, info, substream, &fw_tstamp);
 }
 
-- 
cgit v1.2.3


From 9a0daaab31e9e39047ced79409313c34dae4635a Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Tue, 24 Jul 2018 16:12:48 -0500
Subject: ASoC: Intel: Atom: fix inversion between __iowrite32 and __ioread32

This looks like a copy/paste issue, but clearly there is an inversion
that is obvious when checking the arguments.

Detected with Sparse - now that we have fewer warnings this one was
easy to find.

Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/atom/sst/sst_loader.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/soc/intel/atom/sst/sst_loader.c b/sound/soc/intel/atom/sst/sst_loader.c
index a686eef2cf7f..27413ebae956 100644
--- a/sound/soc/intel/atom/sst/sst_loader.c
+++ b/sound/soc/intel/atom/sst/sst_loader.c
@@ -44,15 +44,15 @@ void memcpy32_toio(void __iomem *dst, const void *src, int count)
 	/* __iowrite32_copy uses 32-bit count values so divide by 4 for
 	 * right count in words
 	 */
-	__iowrite32_copy(dst, src, count/4);
+	__iowrite32_copy(dst, src, count / 4);
 }
 
 void memcpy32_fromio(void *dst, const void __iomem *src, int count)
 {
-	/* __iowrite32_copy uses 32-bit count values so divide by 4 for
+	/* __ioread32_copy uses 32-bit count values so divide by 4 for
 	 * right count in words
 	 */
-	__iowrite32_copy(dst, src, count/4);
+	__ioread32_copy(dst, src, count / 4);
 }
 
 /**
-- 
cgit v1.2.3


From f9419783a6b45a7198ea22f2997cf1a85fda8458 Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Mon, 16 Jul 2018 11:24:32 +0530
Subject: clk: qcom: Update SPDX headers for common files

SPDX headers updated for common/branch/pll/regmap files.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/clk-alpha-pll.c | 10 +---------
 drivers/clk/qcom/clk-alpha-pll.h | 14 ++------------
 drivers/clk/qcom/clk-branch.c    | 10 +---------
 drivers/clk/qcom/clk-branch.h    | 14 ++------------
 drivers/clk/qcom/clk-regmap.c    | 10 +---------
 drivers/clk/qcom/clk-regmap.h    | 14 ++------------
 drivers/clk/qcom/common.c        | 10 +---------
 drivers/clk/qcom/common.h        | 15 +++------------
 8 files changed, 13 insertions(+), 84 deletions(-)

diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
index 3c49a60072f1..a91d97cecbad 100644
--- a/drivers/clk/qcom/clk-alpha-pll.c
+++ b/drivers/clk/qcom/clk-alpha-pll.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
index f981b486c468..66755f0f84fc 100644
--- a/drivers/clk/qcom/clk-alpha-pll.h
+++ b/drivers/clk/qcom/clk-alpha-pll.h
@@ -1,15 +1,5 @@
-/*
- * Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015, 2018, The Linux Foundation. All rights reserved. */
 
 #ifndef __QCOM_CLK_ALPHA_PLL_H__
 #define __QCOM_CLK_ALPHA_PLL_H__
diff --git a/drivers/clk/qcom/clk-branch.c b/drivers/clk/qcom/clk-branch.c
index c58c5538b1b6..bc2205c450b6 100644
--- a/drivers/clk/qcom/clk-branch.c
+++ b/drivers/clk/qcom/clk-branch.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2013, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/clk/qcom/clk-branch.h b/drivers/clk/qcom/clk-branch.h
index 1702efb1c511..b3561e0a3984 100644
--- a/drivers/clk/qcom/clk-branch.h
+++ b/drivers/clk/qcom/clk-branch.h
@@ -1,15 +1,5 @@
-/*
- * Copyright (c) 2013, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2013, The Linux Foundation. All rights reserved. */
 
 #ifndef __QCOM_CLK_BRANCH_H__
 #define __QCOM_CLK_BRANCH_H__
diff --git a/drivers/clk/qcom/clk-regmap.c b/drivers/clk/qcom/clk-regmap.c
index 1c856d330733..ce80db27ccf2 100644
--- a/drivers/clk/qcom/clk-regmap.c
+++ b/drivers/clk/qcom/clk-regmap.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/device.h>
diff --git a/drivers/clk/qcom/clk-regmap.h b/drivers/clk/qcom/clk-regmap.h
index 90d95cd11ec6..6cfc1bccb255 100644
--- a/drivers/clk/qcom/clk-regmap.h
+++ b/drivers/clk/qcom/clk-regmap.h
@@ -1,15 +1,5 @@
-/*
- * Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2014, The Linux Foundation. All rights reserved. */
 
 #ifndef __QCOM_CLK_REGMAP_H__
 #define __QCOM_CLK_REGMAP_H__
diff --git a/drivers/clk/qcom/common.c b/drivers/clk/qcom/common.c
index 39ce64c2783b..db9b2471ac40 100644
--- a/drivers/clk/qcom/common.c
+++ b/drivers/clk/qcom/common.c
@@ -1,14 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 
 #include <linux/export.h>
diff --git a/drivers/clk/qcom/common.h b/drivers/clk/qcom/common.h
index 00196ee15e73..4aa33ee70bae 100644
--- a/drivers/clk/qcom/common.h
+++ b/drivers/clk/qcom/common.h
@@ -1,15 +1,6 @@
-/*
- * Copyright (c) 2014, The Linux Foundation. All rights reserved.
- *
- * This software is licensed under the terms of the GNU General Public
- * License version 2, as published by the Free Software Foundation, and
- * may be copied, distributed, and modified under those terms.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2014, The Linux Foundation. All rights reserved. */
+
 #ifndef __QCOM_CLK_COMMON_H__
 #define __QCOM_CLK_COMMON_H__
 
-- 
cgit v1.2.3


From 365f7a89c881e84f1ebc925f65f899d5d7ce547e Mon Sep 17 00:00:00 2001
From: Mikko Perttunen <mperttunen@nvidia.com>
Date: Wed, 11 Jul 2018 11:21:04 +0300
Subject: clk: core: Potentially free connection id

Patch "clk: core: Copy connection id" made it so that the connector id
'con_id' is kstrdup_const()ed to cater to drivers that pass non-constant
connection ids. The patch added the corresponding kfree_const to
__clk_free_clk(), but struct clk's can be freed also via __clk_put().
Add the kfree_const call to __clk_put() and add comments to both
functions to remind that the logic in them should be kept in sync.

Fixes: 253160a8ad06 ("clk: core: Copy connection id")
Signed-off-by: Mikko Perttunen <mperttunen@nvidia.com>
Reviewed-by: Leonard Crestez <leonard.crestez@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 9760b526ca31..eeec6885c302 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2934,6 +2934,7 @@ struct clk *__clk_create_clk(struct clk_hw *hw, const char *dev_id,
 	return clk;
 }
 
+/* keep in sync with __clk_put */
 void __clk_free_clk(struct clk *clk)
 {
 	clk_prepare_lock();
@@ -3313,6 +3314,7 @@ int __clk_get(struct clk *clk)
 	return 1;
 }
 
+/* keep in sync with __clk_free_clk */
 void __clk_put(struct clk *clk)
 {
 	struct module *owner;
@@ -3346,6 +3348,7 @@ void __clk_put(struct clk *clk)
 
 	module_put(owner);
 
+	kfree_const(clk->con_id);
 	kfree(clk);
 }
 
-- 
cgit v1.2.3


From fe65324e3f5205072a2d55ac9c63ec77155fa528 Mon Sep 17 00:00:00 2001
From: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Date: Tue, 24 Jul 2018 19:50:48 -0500
Subject: ASoC: Intel: Skylake: fix widget handling

include DAPM Mux and output widgets into the list.

Signed-off-by: Rakesh Ughreja <rakesh.a.ughreja@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/skylake/skl-topology.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/intel/skylake/skl-topology.c b/sound/soc/intel/skylake/skl-topology.c
index 647e52aecdc3..9845d853644c 100644
--- a/sound/soc/intel/skylake/skl-topology.c
+++ b/sound/soc/intel/skylake/skl-topology.c
@@ -108,6 +108,9 @@ static int is_skl_dsp_widget_type(struct snd_soc_dapm_widget *w,
 	case snd_soc_dapm_aif_out:
 	case snd_soc_dapm_dai_out:
 	case snd_soc_dapm_switch:
+	case snd_soc_dapm_output:
+	case snd_soc_dapm_mux:
+
 		return false;
 	default:
 		return true;
-- 
cgit v1.2.3


From f6dab4233d6b64d719109040503b567f71fbfa01 Mon Sep 17 00:00:00 2001
From: Rajan Vaja <rajan.vaja@xilinx.com>
Date: Tue, 17 Jul 2018 06:17:00 -0700
Subject: clk: clk-fixed-factor: Clear OF_POPULATED flag in case of failure

Fixed factor clock has two initializations at of_clk_init() time
and during platform driver probe. Before of_clk_init() call,
node is marked as populated and so its probe never gets called.

During of_clk_init() fixed factor clock registration may fail if
any of its parent clock is not registered. In this case, it doesn't
get chance to retry registration from probe. Clear OF_POPULATED
flag if fixed factor clock registration fails so that clock
registration is attempted again from probe.

Signed-off-by: Rajan Vaja <rajan.vaja@xilinx.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-fixed-factor.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/clk-fixed-factor.c b/drivers/clk/clk-fixed-factor.c
index a5d402de5584..20724abd38bd 100644
--- a/drivers/clk/clk-fixed-factor.c
+++ b/drivers/clk/clk-fixed-factor.c
@@ -177,8 +177,15 @@ static struct clk *_of_fixed_factor_clk_setup(struct device_node *node)
 
 	clk = clk_register_fixed_factor(NULL, clk_name, parent_name, flags,
 					mult, div);
-	if (IS_ERR(clk))
+	if (IS_ERR(clk)) {
+		/*
+		 * If parent clock is not registered, registration would fail.
+		 * Clear OF_POPULATED flag so that clock registration can be
+		 * attempted again from probe function.
+		 */
+		of_node_clear_flag(node, OF_POPULATED);
 		return clk;
+	}
 
 	ret = of_clk_add_provider(node, of_clk_src_simple_get, clk);
 	if (ret) {
-- 
cgit v1.2.3


From 616bf80d381da13fbb392ebff06f46f946e3ee84 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Fri, 13 Jul 2018 12:27:26 +0200
Subject: clk: mvebu: armada-37xx-periph: Fix wrong return value in get_parent

The return value of the get_parent operation is a u8, whereas a -EINVAL
was returned. This wrong value was return if the value was bigger that
the number of parent but this case was already handled by the core.

So we can just remove this chunk of code to fix the issue.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: 9818a7a4fd10 ("clk: mvebu: armada-37xx-periph: prepare cpu clk to
be used with DVFS")
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/mvebu/armada-37xx-periph.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 6860bd5a37c5..5cf0a52b87e8 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -428,9 +428,6 @@ static u8 clk_pm_cpu_get_parent(struct clk_hw *hw)
 		val &= pm_cpu->mask_mux;
 	}
 
-	if (val >= num_parents)
-		return -EINVAL;
-
 	return val;
 }
 
-- 
cgit v1.2.3


From d7b7c00dad79f7cc78dac87a3ff2f06358518384 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Wed, 11 Jul 2018 08:58:58 +0800
Subject: clk: imx: add ocram_s clock for i.mx6sx

i.MX6SX has a 16KB always-on ocram bank called
ocram_s, and its clock gate in CCM CCGR1 CG14
needs to be enabled before access, add it to
clock tree.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6sx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/imx/clk-imx6sx.c b/drivers/clk/imx/clk-imx6sx.c
index 10c771b91ef6..691db26bd09a 100644
--- a/drivers/clk/imx/clk-imx6sx.c
+++ b/drivers/clk/imx/clk-imx6sx.c
@@ -411,6 +411,7 @@ static void __init imx6sx_clocks_init(struct device_node *ccm_node)
 	clks[IMX6SX_CLK_GPT_BUS]      = imx_clk_gate2("gpt_bus",       "perclk",            base + 0x6c, 20);
 	clks[IMX6SX_CLK_GPT_SERIAL]   = imx_clk_gate2("gpt_serial",    "perclk",            base + 0x6c, 22);
 	clks[IMX6SX_CLK_GPU]          = imx_clk_gate2("gpu",           "gpu_core_podf",     base + 0x6c, 26);
+	clks[IMX6SX_CLK_OCRAM_S]      = imx_clk_gate2("ocram_s",       "ahb",               base + 0x6c, 28);
 	clks[IMX6SX_CLK_CANFD]        = imx_clk_gate2("canfd",         "can_podf",          base + 0x6c, 30);
 
 	/* CCGR2 */
-- 
cgit v1.2.3


From 7d9d60fd4ab69604015b094c07ad8490039bb2a4 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 23 Jul 2018 23:36:04 +0900
Subject: virtio_net: Fix incosistent received bytes counter

When received packets are dropped in virtio_net driver, received packets
counter is incremented but bytes counter is not.
As a result, for instance if we drop all packets by XDP, only received
is counted and bytes stays 0, which looks inconsistent.
IMHO received packets/bytes should be counted if packets are produced by
the hypervisor, like what common NICs on physical machines are doing.
So fix the bytes counter.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 41 +++++++++++++++++++++++------------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 2ff08bc103a9..abbd3bc83b62 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -586,7 +586,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     struct receive_queue *rq,
 				     void *buf, void *ctx,
 				     unsigned int len,
-				     unsigned int *xdp_xmit)
+				     unsigned int *xdp_xmit,
+				     unsigned int *rbytes)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -601,6 +602,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	int err;
 
 	len -= vi->hdr_len;
+	*rbytes += len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -705,11 +707,13 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct virtnet_info *vi,
 				   struct receive_queue *rq,
 				   void *buf,
-				   unsigned int len)
+				   unsigned int len,
+				   unsigned int *rbytes)
 {
 	struct page *page = buf;
 	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
 
+	*rbytes += len - vi->hdr_len;
 	if (unlikely(!skb))
 		goto err;
 
@@ -727,7 +731,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *buf,
 					 void *ctx,
 					 unsigned int len,
-					 unsigned int *xdp_xmit)
+					 unsigned int *xdp_xmit,
+					 unsigned int *rbytes)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -740,6 +745,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	int err;
 
 	head_skb = NULL;
+	*rbytes += len - vi->hdr_len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -877,6 +883,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto err_buf;
 		}
 
+		*rbytes += len;
 		page = virt_to_head_page(buf);
 
 		truesize = mergeable_ctx_to_truesize(ctx);
@@ -932,6 +939,7 @@ err_skb:
 			dev->stats.rx_length_errors++;
 			break;
 		}
+		*rbytes += len;
 		page = virt_to_head_page(buf);
 		put_page(page);
 	}
@@ -942,14 +950,13 @@ xdp_xmit:
 	return NULL;
 }
 
-static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
-		       void *buf, unsigned int len, void **ctx,
-		       unsigned int *xdp_xmit)
+static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
+			void *buf, unsigned int len, void **ctx,
+			unsigned int *xdp_xmit, unsigned int *rbytes)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
 	struct virtio_net_hdr_mrg_rxbuf *hdr;
-	int ret;
 
 	if (unlikely(len < vi->hdr_len + ETH_HLEN)) {
 		pr_debug("%s: short packet %i\n", dev->name, len);
@@ -961,23 +968,22 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		} else {
 			put_page(virt_to_head_page(buf));
 		}
-		return 0;
+		return;
 	}
 
 	if (vi->mergeable_rx_bufs)
-		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit);
+		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
+					rbytes);
 	else if (vi->big_packets)
-		skb = receive_big(dev, vi, rq, buf, len);
+		skb = receive_big(dev, vi, rq, buf, len, rbytes);
 	else
-		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit);
+		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes);
 
 	if (unlikely(!skb))
-		return 0;
+		return;
 
 	hdr = skb_vnet_hdr(skb);
 
-	ret = skb->len;
-
 	if (hdr->hdr.flags & VIRTIO_NET_HDR_F_DATA_VALID)
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 
@@ -994,12 +1000,11 @@ static int receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 		 ntohs(skb->protocol), skb->len, skb->pkt_type);
 
 	napi_gro_receive(&rq->napi, skb);
-	return ret;
+	return;
 
 frame_err:
 	dev->stats.rx_frame_errors++;
 	dev_kfree_skb(skb);
-	return 0;
 }
 
 /* Unlike mergeable buffers, all buffers are allocated to the
@@ -1249,13 +1254,13 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 
 		while (received < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
-			bytes += receive_buf(vi, rq, buf, len, ctx, xdp_xmit);
+			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes);
 			received++;
 		}
 	} else {
 		while (received < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-			bytes += receive_buf(vi, rq, buf, len, NULL, xdp_xmit);
+			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes);
 			received++;
 		}
 	}
-- 
cgit v1.2.3


From a0929a44c2065da33c17b1b8015a88401d71ca7b Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 23 Jul 2018 23:36:05 +0900
Subject: virtio_net: Use temporary storage for accounting rx stats

The purpose is to keep receive_buf arguments simple when more per-queue
counter items are added later.
Also XDP_TX related sq counters will be updated in the following changes
so create a container struct virtnet_rx_stats which will includes both
rq and sq statistics. For now it only covers rq stats.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 72 +++++++++++++++++++++++++++++-------------------
 1 file changed, 44 insertions(+), 28 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index abbd3bc83b62..d03bfc4fce8e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -84,14 +84,22 @@ struct virtnet_sq_stats {
 	u64 bytes;
 };
 
-struct virtnet_rq_stats {
-	struct u64_stats_sync syncp;
+struct virtnet_rq_stat_items {
 	u64 packets;
 	u64 bytes;
 };
 
+struct virtnet_rq_stats {
+	struct u64_stats_sync syncp;
+	struct virtnet_rq_stat_items items;
+};
+
+struct virtnet_rx_stats {
+	struct virtnet_rq_stat_items rx;
+};
+
 #define VIRTNET_SQ_STAT(m)	offsetof(struct virtnet_sq_stats, m)
-#define VIRTNET_RQ_STAT(m)	offsetof(struct virtnet_rq_stats, m)
+#define VIRTNET_RQ_STAT(m)	offsetof(struct virtnet_rq_stat_items, m)
 
 static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
 	{ "packets",	VIRTNET_SQ_STAT(packets) },
@@ -587,7 +595,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     void *buf, void *ctx,
 				     unsigned int len,
 				     unsigned int *xdp_xmit,
-				     unsigned int *rbytes)
+				     struct virtnet_rx_stats *stats)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -602,7 +610,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	int err;
 
 	len -= vi->hdr_len;
-	*rbytes += len;
+	stats->rx.bytes += len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -708,12 +716,12 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct receive_queue *rq,
 				   void *buf,
 				   unsigned int len,
-				   unsigned int *rbytes)
+				   struct virtnet_rx_stats *stats)
 {
 	struct page *page = buf;
 	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
 
-	*rbytes += len - vi->hdr_len;
+	stats->rx.bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
 		goto err;
 
@@ -732,7 +740,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *ctx,
 					 unsigned int len,
 					 unsigned int *xdp_xmit,
-					 unsigned int *rbytes)
+					 struct virtnet_rx_stats *stats)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -745,7 +753,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	int err;
 
 	head_skb = NULL;
-	*rbytes += len - vi->hdr_len;
+	stats->rx.bytes += len - vi->hdr_len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -883,7 +891,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto err_buf;
 		}
 
-		*rbytes += len;
+		stats->rx.bytes += len;
 		page = virt_to_head_page(buf);
 
 		truesize = mergeable_ctx_to_truesize(ctx);
@@ -939,7 +947,7 @@ err_skb:
 			dev->stats.rx_length_errors++;
 			break;
 		}
-		*rbytes += len;
+		stats->rx.bytes += len;
 		page = virt_to_head_page(buf);
 		put_page(page);
 	}
@@ -952,7 +960,8 @@ xdp_xmit:
 
 static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 			void *buf, unsigned int len, void **ctx,
-			unsigned int *xdp_xmit, unsigned int *rbytes)
+			unsigned int *xdp_xmit,
+			struct virtnet_rx_stats *stats)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -973,11 +982,11 @@ static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 
 	if (vi->mergeable_rx_bufs)
 		skb = receive_mergeable(dev, vi, rq, buf, ctx, len, xdp_xmit,
-					rbytes);
+					stats);
 	else if (vi->big_packets)
-		skb = receive_big(dev, vi, rq, buf, len, rbytes);
+		skb = receive_big(dev, vi, rq, buf, len, stats);
 	else
-		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, rbytes);
+		skb = receive_small(dev, vi, rq, buf, ctx, len, xdp_xmit, stats);
 
 	if (unlikely(!skb))
 		return;
@@ -1246,22 +1255,24 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 			   unsigned int *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
-	unsigned int len, received = 0, bytes = 0;
+	struct virtnet_rx_stats stats = {};
+	unsigned int len;
 	void *buf;
+	int i;
 
 	if (!vi->big_packets || vi->mergeable_rx_bufs) {
 		void *ctx;
 
-		while (received < budget &&
+		while (stats.rx.packets < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
-			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &bytes);
-			received++;
+			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats);
+			stats.rx.packets++;
 		}
 	} else {
-		while (received < budget &&
+		while (stats.rx.packets < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
-			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &bytes);
-			received++;
+			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
+			stats.rx.packets++;
 		}
 	}
 
@@ -1271,11 +1282,16 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 
 	u64_stats_update_begin(&rq->stats.syncp);
-	rq->stats.bytes += bytes;
-	rq->stats.packets += received;
+	for (i = 0; i < VIRTNET_RQ_STATS_LEN; i++) {
+		size_t offset = virtnet_rq_stats_desc[i].offset;
+		u64 *item;
+
+		item = (u64 *)((u8 *)&rq->stats.items + offset);
+		*item += *(u64 *)((u8 *)&stats.rx + offset);
+	}
 	u64_stats_update_end(&rq->stats.syncp);
 
-	return received;
+	return stats.rx.packets;
 }
 
 static void free_old_xmit_skbs(struct send_queue *sq)
@@ -1628,8 +1644,8 @@ static void virtnet_stats(struct net_device *dev,
 
 		do {
 			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
-			rpackets = rq->stats.packets;
-			rbytes   = rq->stats.bytes;
+			rpackets = rq->stats.items.packets;
+			rbytes   = rq->stats.items.bytes;
 		} while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start));
 
 		tot->rx_packets += rpackets;
@@ -2019,7 +2035,7 @@ static void virtnet_get_ethtool_stats(struct net_device *dev,
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		struct receive_queue *rq = &vi->rq[i];
 
-		stats_base = (u8 *)&rq->stats;
+		stats_base = (u8 *)&rq->stats.items;
 		do {
 			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
 			for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) {
-- 
cgit v1.2.3


From 2c4a2f7d826329966e8ab86f842a95d3234c64da Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 23 Jul 2018 23:36:06 +0900
Subject: virtio_net: Make drop counter per-queue

Since when XDP was introduced, drop counter has been able to be updated
much more frequently than before, as XDP_DROP increments the counter.
Thus for performance analysis per-queue drop counter would be useful.

Also this avoids cache contention and race on updating the counter. It
is currently racy because napi handlers read-modify-write it without any
locks.

There are more counters in dev->stats that are racy, but I left them
per-device, because they are rarely updated and does not worth being
per-queue counters IMHO. To fix them we need atomic ops or some kind of
locks.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index d03bfc4fce8e..7a47ce750a43 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -87,6 +87,7 @@ struct virtnet_sq_stats {
 struct virtnet_rq_stat_items {
 	u64 packets;
 	u64 bytes;
+	u64 drops;
 };
 
 struct virtnet_rq_stats {
@@ -109,6 +110,7 @@ static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
 static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
 	{ "packets",	VIRTNET_RQ_STAT(packets) },
 	{ "bytes",	VIRTNET_RQ_STAT(bytes) },
+	{ "drops",	VIRTNET_RQ_STAT(drops) },
 };
 
 #define VIRTNET_SQ_STATS_LEN	ARRAY_SIZE(virtnet_sq_stats_desc)
@@ -705,7 +707,7 @@ err:
 
 err_xdp:
 	rcu_read_unlock();
-	dev->stats.rx_dropped++;
+	stats->rx.drops++;
 	put_page(page);
 xdp_xmit:
 	return NULL;
@@ -728,7 +730,7 @@ static struct sk_buff *receive_big(struct net_device *dev,
 	return skb;
 
 err:
-	dev->stats.rx_dropped++;
+	stats->rx.drops++;
 	give_pages(rq, page);
 	return NULL;
 }
@@ -952,7 +954,7 @@ err_skb:
 		put_page(page);
 	}
 err_buf:
-	dev->stats.rx_dropped++;
+	stats->rx.drops++;
 	dev_kfree_skb(head_skb);
 xdp_xmit:
 	return NULL;
@@ -1632,7 +1634,7 @@ static void virtnet_stats(struct net_device *dev,
 	int i;
 
 	for (i = 0; i < vi->max_queue_pairs; i++) {
-		u64 tpackets, tbytes, rpackets, rbytes;
+		u64 tpackets, tbytes, rpackets, rbytes, rdrops;
 		struct receive_queue *rq = &vi->rq[i];
 		struct send_queue *sq = &vi->sq[i];
 
@@ -1646,17 +1648,18 @@ static void virtnet_stats(struct net_device *dev,
 			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
 			rpackets = rq->stats.items.packets;
 			rbytes   = rq->stats.items.bytes;
+			rdrops   = rq->stats.items.drops;
 		} while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start));
 
 		tot->rx_packets += rpackets;
 		tot->tx_packets += tpackets;
 		tot->rx_bytes   += rbytes;
 		tot->tx_bytes   += tbytes;
+		tot->rx_dropped += rdrops;
 	}
 
 	tot->tx_dropped = dev->stats.tx_dropped;
 	tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
-	tot->rx_dropped = dev->stats.rx_dropped;
 	tot->rx_length_errors = dev->stats.rx_length_errors;
 	tot->rx_frame_errors = dev->stats.rx_frame_errors;
 }
-- 
cgit v1.2.3


From 2a43565c06465323e33b117bcf2ce604c0594659 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 23 Jul 2018 23:36:07 +0900
Subject: virtio_net: Factor out the logic to determine xdp sq

Make sure to use the same logic in all places to determine xdp sq. This
is useful for xdp counters which the following commit will introduce as
well.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7a47ce750a43..eca9b13b859e 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -457,16 +457,22 @@ static int __virtnet_xdp_xmit_one(struct virtnet_info *vi,
 	return 0;
 }
 
+static struct send_queue *virtnet_xdp_sq(struct virtnet_info *vi)
+{
+	unsigned int qp;
+
+	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
+	return &vi->sq[qp];
+}
+
 static int __virtnet_xdp_tx_xmit(struct virtnet_info *vi,
 				   struct xdp_frame *xdpf)
 {
 	struct xdp_frame *xdpf_sent;
 	struct send_queue *sq;
 	unsigned int len;
-	unsigned int qp;
 
-	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
-	sq = &vi->sq[qp];
+	sq = virtnet_xdp_sq(vi);
 
 	/* Free up any pending old buffers before queueing new ones. */
 	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
@@ -484,7 +490,6 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	struct bpf_prog *xdp_prog;
 	struct send_queue *sq;
 	unsigned int len;
-	unsigned int qp;
 	int drops = 0;
 	int err;
 	int i;
@@ -492,8 +497,7 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
 		return -EINVAL;
 
-	qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id();
-	sq = &vi->sq[qp];
+	sq = virtnet_xdp_sq(vi);
 
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
 	 * indicate XDP resources have been successfully allocated.
@@ -1349,7 +1353,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 		container_of(napi, struct receive_queue, napi);
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct send_queue *sq;
-	unsigned int received, qp;
+	unsigned int received;
 	unsigned int xdp_xmit = 0;
 
 	virtnet_poll_cleantx(rq);
@@ -1364,9 +1368,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 		xdp_do_flush_map();
 
 	if (xdp_xmit & VIRTIO_XDP_TX) {
-		qp = vi->curr_queue_pairs - vi->xdp_queue_pairs +
-		     smp_processor_id();
-		sq = &vi->sq[qp];
+		sq = virtnet_xdp_sq(vi);
 		virtqueue_kick(sq->vq);
 	}
 
-- 
cgit v1.2.3


From 5b8f3c8d30a6176c6be35c6ac75e22b0a60a3c43 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 23 Jul 2018 23:36:08 +0900
Subject: virtio_net: Add XDP related stats

Add counters below:
* Tx
 - xdp_tx: frames sent by ndo_xdp_xmit or XDP_TX.
 - xdp_tx_drops: dropped frames out of xdp_tx ones.
* Rx
 - xdp_packets: frames went through xdp program.
 - xdp_tx: XDP_TX frames.
 - xdp_redirects: XDP_REDIRECT frames.
 - xdp_drops: any dropped frames out of xdp_packets ones.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 71 ++++++++++++++++++++++++++++++++++++++++--------
 1 file changed, 59 insertions(+), 12 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index eca9b13b859e..cb4ef331567c 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -82,12 +82,18 @@ struct virtnet_sq_stats {
 	struct u64_stats_sync syncp;
 	u64 packets;
 	u64 bytes;
+	u64 xdp_tx;
+	u64 xdp_tx_drops;
 };
 
 struct virtnet_rq_stat_items {
 	u64 packets;
 	u64 bytes;
 	u64 drops;
+	u64 xdp_packets;
+	u64 xdp_tx;
+	u64 xdp_redirects;
+	u64 xdp_drops;
 };
 
 struct virtnet_rq_stats {
@@ -97,20 +103,30 @@ struct virtnet_rq_stats {
 
 struct virtnet_rx_stats {
 	struct virtnet_rq_stat_items rx;
+	struct {
+		unsigned int xdp_tx;
+		unsigned int xdp_tx_drops;
+	} tx;
 };
 
 #define VIRTNET_SQ_STAT(m)	offsetof(struct virtnet_sq_stats, m)
 #define VIRTNET_RQ_STAT(m)	offsetof(struct virtnet_rq_stat_items, m)
 
 static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
-	{ "packets",	VIRTNET_SQ_STAT(packets) },
-	{ "bytes",	VIRTNET_SQ_STAT(bytes) },
+	{ "packets",		VIRTNET_SQ_STAT(packets) },
+	{ "bytes",		VIRTNET_SQ_STAT(bytes) },
+	{ "xdp_tx",		VIRTNET_SQ_STAT(xdp_tx) },
+	{ "xdp_tx_drops",	VIRTNET_SQ_STAT(xdp_tx_drops) },
 };
 
 static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
-	{ "packets",	VIRTNET_RQ_STAT(packets) },
-	{ "bytes",	VIRTNET_RQ_STAT(bytes) },
-	{ "drops",	VIRTNET_RQ_STAT(drops) },
+	{ "packets",		VIRTNET_RQ_STAT(packets) },
+	{ "bytes",		VIRTNET_RQ_STAT(bytes) },
+	{ "drops",		VIRTNET_RQ_STAT(drops) },
+	{ "xdp_packets",	VIRTNET_RQ_STAT(xdp_packets) },
+	{ "xdp_tx",		VIRTNET_RQ_STAT(xdp_tx) },
+	{ "xdp_redirects",	VIRTNET_RQ_STAT(xdp_redirects) },
+	{ "xdp_drops",		VIRTNET_RQ_STAT(xdp_drops) },
 };
 
 #define VIRTNET_SQ_STATS_LEN	ARRAY_SIZE(virtnet_sq_stats_desc)
@@ -491,20 +507,26 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	struct send_queue *sq;
 	unsigned int len;
 	int drops = 0;
-	int err;
+	int ret, err;
 	int i;
 
-	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
-		return -EINVAL;
-
 	sq = virtnet_xdp_sq(vi);
 
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK)) {
+		ret = -EINVAL;
+		drops = n;
+		goto out;
+	}
+
 	/* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this
 	 * indicate XDP resources have been successfully allocated.
 	 */
 	xdp_prog = rcu_dereference(rq->xdp_prog);
-	if (!xdp_prog)
-		return -ENXIO;
+	if (!xdp_prog) {
+		ret = -ENXIO;
+		drops = n;
+		goto out;
+	}
 
 	/* Free up any pending old buffers before queueing new ones. */
 	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
@@ -519,11 +541,17 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 			drops++;
 		}
 	}
+	ret = n - drops;
 
 	if (flags & XDP_XMIT_FLUSH)
 		virtqueue_kick(sq->vq);
+out:
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.xdp_tx += n;
+	sq->stats.xdp_tx_drops += drops;
+	u64_stats_update_end(&sq->stats.syncp);
 
-	return n - drops;
+	return ret;
 }
 
 static unsigned int virtnet_get_headroom(struct virtnet_info *vi)
@@ -658,6 +686,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		xdp.rxq = &rq->xdp_rxq;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+		stats->rx.xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
@@ -666,11 +695,14 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			len = xdp.data_end - xdp.data;
 			break;
 		case XDP_TX:
+			stats->rx.xdp_tx++;
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
+			stats->tx.xdp_tx++;
 			err = __virtnet_xdp_tx_xmit(vi, xdpf);
 			if (unlikely(err)) {
+				stats->tx.xdp_tx_drops++;
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				goto err_xdp;
 			}
@@ -678,6 +710,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
+			stats->rx.xdp_redirects++;
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err)
 				goto err_xdp;
@@ -711,6 +744,7 @@ err:
 
 err_xdp:
 	rcu_read_unlock();
+	stats->rx.xdp_drops++;
 	stats->rx.drops++;
 	put_page(page);
 xdp_xmit:
@@ -808,6 +842,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		xdp.rxq = &rq->xdp_rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+		stats->rx.xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
@@ -832,11 +867,14 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			break;
 		case XDP_TX:
+			stats->rx.xdp_tx++;
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
+			stats->tx.xdp_tx++;
 			err = __virtnet_xdp_tx_xmit(vi, xdpf);
 			if (unlikely(err)) {
+				stats->tx.xdp_tx_drops++;
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				if (unlikely(xdp_page != page))
 					put_page(xdp_page);
@@ -848,6 +886,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
+			stats->rx.xdp_redirects++;
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err) {
 				if (unlikely(xdp_page != page))
@@ -943,6 +982,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 
 err_xdp:
 	rcu_read_unlock();
+	stats->rx.xdp_drops++;
 err_skb:
 	put_page(page);
 	while (num_buf-- > 1) {
@@ -1262,6 +1302,7 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct virtnet_rx_stats stats = {};
+	struct send_queue *sq;
 	unsigned int len;
 	void *buf;
 	int i;
@@ -1297,6 +1338,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 	u64_stats_update_end(&rq->stats.syncp);
 
+	sq = virtnet_xdp_sq(vi);
+	u64_stats_update_begin(&sq->stats.syncp);
+	sq->stats.xdp_tx += stats.tx.xdp_tx;
+	sq->stats.xdp_tx_drops += stats.tx.xdp_tx_drops;
+	u64_stats_update_end(&sq->stats.syncp);
+
 	return stats.rx.packets;
 }
 
-- 
cgit v1.2.3


From 461f03dc99cf6afcc3c70aaac56c4a7eee5a62bd Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Mon, 23 Jul 2018 23:36:09 +0900
Subject: virtio_net: Add kick stats

So we can infer the number of VM-Exits.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 34 ++++++++++++++++++++++++++++------
 1 file changed, 28 insertions(+), 6 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index cb4ef331567c..1880c86e84b4 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -84,6 +84,7 @@ struct virtnet_sq_stats {
 	u64 bytes;
 	u64 xdp_tx;
 	u64 xdp_tx_drops;
+	u64 kicks;
 };
 
 struct virtnet_rq_stat_items {
@@ -94,6 +95,7 @@ struct virtnet_rq_stat_items {
 	u64 xdp_tx;
 	u64 xdp_redirects;
 	u64 xdp_drops;
+	u64 kicks;
 };
 
 struct virtnet_rq_stats {
@@ -117,6 +119,7 @@ static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
 	{ "bytes",		VIRTNET_SQ_STAT(bytes) },
 	{ "xdp_tx",		VIRTNET_SQ_STAT(xdp_tx) },
 	{ "xdp_tx_drops",	VIRTNET_SQ_STAT(xdp_tx_drops) },
+	{ "kicks",		VIRTNET_SQ_STAT(kicks) },
 };
 
 static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
@@ -127,6 +130,7 @@ static const struct virtnet_stat_desc virtnet_rq_stats_desc[] = {
 	{ "xdp_tx",		VIRTNET_RQ_STAT(xdp_tx) },
 	{ "xdp_redirects",	VIRTNET_RQ_STAT(xdp_redirects) },
 	{ "xdp_drops",		VIRTNET_RQ_STAT(xdp_drops) },
+	{ "kicks",		VIRTNET_RQ_STAT(kicks) },
 };
 
 #define VIRTNET_SQ_STATS_LEN	ARRAY_SIZE(virtnet_sq_stats_desc)
@@ -507,6 +511,7 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	struct send_queue *sq;
 	unsigned int len;
 	int drops = 0;
+	int kicks = 0;
 	int ret, err;
 	int i;
 
@@ -543,12 +548,15 @@ static int virtnet_xdp_xmit(struct net_device *dev,
 	}
 	ret = n - drops;
 
-	if (flags & XDP_XMIT_FLUSH)
-		virtqueue_kick(sq->vq);
+	if (flags & XDP_XMIT_FLUSH) {
+		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq))
+			kicks = 1;
+	}
 out:
 	u64_stats_update_begin(&sq->stats.syncp);
 	sq->stats.xdp_tx += n;
 	sq->stats.xdp_tx_drops += drops;
+	sq->stats.kicks += kicks;
 	u64_stats_update_end(&sq->stats.syncp);
 
 	return ret;
@@ -1226,7 +1234,12 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 		if (err)
 			break;
 	} while (rq->vq->num_free);
-	virtqueue_kick(rq->vq);
+	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
+		u64_stats_update_begin(&rq->stats.syncp);
+		rq->stats.items.kicks++;
+		u64_stats_update_end(&rq->stats.syncp);
+	}
+
 	return !oom;
 }
 
@@ -1416,7 +1429,11 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 
 	if (xdp_xmit & VIRTIO_XDP_TX) {
 		sq = virtnet_xdp_sq(vi);
-		virtqueue_kick(sq->vq);
+		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
+			u64_stats_update_begin(&sq->stats.syncp);
+			sq->stats.kicks++;
+			u64_stats_update_end(&sq->stats.syncp);
+		}
 	}
 
 	return received;
@@ -1578,8 +1595,13 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
-	if (kick || netif_xmit_stopped(txq))
-		virtqueue_kick(sq->vq);
+	if (kick || netif_xmit_stopped(txq)) {
+		if (virtqueue_kick_prepare(sq->vq) && virtqueue_notify(sq->vq)) {
+			u64_stats_update_begin(&sq->stats.syncp);
+			sq->stats.kicks++;
+			u64_stats_update_end(&sq->stats.syncp);
+		}
+	}
 
 	return NETDEV_TX_OK;
 }
-- 
cgit v1.2.3


From 34786005eca3b53cffa95d686bf3b7da1305867c Mon Sep 17 00:00:00 2001
From: Camelia Groza <camelia.groza@nxp.com>
Date: Mon, 23 Jul 2018 18:06:15 +0300
Subject: net: phy: prevent PHYs w/o Clause 22 regs from calling
 genphy_config_aneg

genphy_config_aneg() should be called only by PHYs that implement
the Clause 22 register set. Prevent Clause 45 PHYs that don't implement
the register set from calling the genphy function.

Signed-off-by: Camelia Groza <camelia.groza@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 914fe8e6ac86..04780db4c963 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -471,8 +471,14 @@ static int phy_config_aneg(struct phy_device *phydev)
 {
 	if (phydev->drv->config_aneg)
 		return phydev->drv->config_aneg(phydev);
-	else
-		return genphy_config_aneg(phydev);
+
+	/* Clause 45 PHYs that don't implement Clause 22 registers are not
+	 * allowed to call genphy_config_aneg()
+	 */
+	if (phydev->is_c45 && !(phydev->c45_ids.devices_in_package & BIT(0)))
+		return -EOPNOTSUPP;
+
+	return genphy_config_aneg(phydev);
 }
 
 /**
-- 
cgit v1.2.3


From f8a91d45553ab581964f40b1e46bdf3d0974d339 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 13:58:16 +0200
Subject: drm/amdgpu: clean up coding style a bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

No need to bitcast a boolean and even if we should use "!!" instead.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 207f238649b4..053d31017c26 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -328,35 +328,35 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 		case AMDGPU_HW_IP_GFX:
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_gfx_rings; i++)
-				ring_mask |= ((adev->gfx.gfx_ring[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->gfx.gfx_ring[i].ready << i;
 			ib_start_alignment = 32;
 			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_COMPUTE:
 			type = AMD_IP_BLOCK_TYPE_GFX;
 			for (i = 0; i < adev->gfx.num_compute_rings; i++)
-				ring_mask |= ((adev->gfx.compute_ring[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->gfx.compute_ring[i].ready << i;
 			ib_start_alignment = 32;
 			ib_size_alignment = 32;
 			break;
 		case AMDGPU_HW_IP_DMA:
 			type = AMD_IP_BLOCK_TYPE_SDMA;
 			for (i = 0; i < adev->sdma.num_instances; i++)
-				ring_mask |= ((adev->sdma.instance[i].ring.ready ? 1 : 0) << i);
+				ring_mask |= adev->sdma.instance[i].ring.ready << i;
 			ib_start_alignment = 256;
 			ib_size_alignment = 4;
 			break;
 		case AMDGPU_HW_IP_UVD:
 			type = AMD_IP_BLOCK_TYPE_UVD;
 			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
-				ring_mask |= ((adev->uvd.inst[i].ring.ready ? 1 : 0) << i);
+				ring_mask |= adev->uvd.inst[i].ring.ready << i;
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCE:
 			type = AMD_IP_BLOCK_TYPE_VCE;
 			for (i = 0; i < adev->vce.num_rings; i++)
-				ring_mask |= ((adev->vce.ring[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->vce.ring[i].ready << i;
 			ib_start_alignment = 4;
 			ib_size_alignment = 1;
 			break;
@@ -365,27 +365,27 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
 				for (j = 0; j < adev->uvd.num_enc_rings; j++)
 					ring_mask |=
-					((adev->uvd.inst[i].ring_enc[j].ready ? 1 : 0) <<
-					(j + i * adev->uvd.num_enc_rings));
+					adev->uvd.inst[i].ring_enc[j].ready <<
+					(j + i * adev->uvd.num_enc_rings);
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
 		case AMDGPU_HW_IP_VCN_DEC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
-			ring_mask = adev->vcn.ring_dec.ready ? 1 : 0;
+			ring_mask = adev->vcn.ring_dec.ready;
 			ib_start_alignment = 16;
 			ib_size_alignment = 16;
 			break;
 		case AMDGPU_HW_IP_VCN_ENC:
 			type = AMD_IP_BLOCK_TYPE_VCN;
 			for (i = 0; i < adev->vcn.num_enc_rings; i++)
-				ring_mask |= ((adev->vcn.ring_enc[i].ready ? 1 : 0) << i);
+				ring_mask |= adev->vcn.ring_enc[i].ready << i;
 			ib_start_alignment = 64;
 			ib_size_alignment = 1;
 			break;
 		case AMDGPU_HW_IP_VCN_JPEG:
 			type = AMD_IP_BLOCK_TYPE_VCN;
-			ring_mask = adev->vcn.ring_jpeg.ready ? 1 : 0;
+			ring_mask = adev->vcn.ring_jpeg.ready;
 			ib_start_alignment = 16;
 			ib_size_alignment = 16;
 			break;
-- 
cgit v1.2.3


From 4d4831a3dae3161ab5a96694462eff708dfefc71 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 14:17:59 +0200
Subject: drm/amdgpu: expose only the first UVD instance for now
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Going to completely rework the context to ring mapping with Nayan's GSoC
work, but for now just stopping to expose the second UVD instance should
do it.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c       | 13 +++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c |  9 ++-------
 2 files changed, 7 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 053d31017c26..c7dce14fd47d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -286,7 +286,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	struct drm_crtc *crtc;
 	uint32_t ui32 = 0;
 	uint64_t ui64 = 0;
-	int i, j, found;
+	int i, found;
 	int ui32_size = sizeof(ui32);
 
 	if (!info->return_size || !info->return_pointer)
@@ -348,8 +348,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_UVD:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
-				ring_mask |= adev->uvd.inst[i].ring.ready << i;
+			ring_mask |= adev->uvd.inst[0].ring.ready;
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
@@ -362,11 +361,9 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_uvd_inst; i++)
-				for (j = 0; j < adev->uvd.num_enc_rings; j++)
-					ring_mask |=
-					adev->uvd.inst[i].ring_enc[j].ready <<
-					(j + i * adev->uvd.num_enc_rings);
+			for (i = 0; i < adev->uvd.num_enc_rings; i++)
+				ring_mask |=
+					adev->uvd.inst[0].ring_enc[i].ready << i;
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index ea9850c9224d..d8357290ad09 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -66,8 +66,6 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 			       u32 ring,
 			       struct amdgpu_ring **out_ring)
 {
-	u32 instance;
-
 	switch (mapper->hw_ip) {
 	case AMDGPU_HW_IP_GFX:
 		*out_ring = &adev->gfx.gfx_ring[ring];
@@ -79,16 +77,13 @@ static int amdgpu_identity_map(struct amdgpu_device *adev,
 		*out_ring = &adev->sdma.instance[ring].ring;
 		break;
 	case AMDGPU_HW_IP_UVD:
-		instance = ring;
-		*out_ring = &adev->uvd.inst[instance].ring;
+		*out_ring = &adev->uvd.inst[0].ring;
 		break;
 	case AMDGPU_HW_IP_VCE:
 		*out_ring = &adev->vce.ring[ring];
 		break;
 	case AMDGPU_HW_IP_UVD_ENC:
-		instance = ring / adev->uvd.num_enc_rings;
-		*out_ring =
-		&adev->uvd.inst[instance].ring_enc[ring%adev->uvd.num_enc_rings];
+		*out_ring = &adev->uvd.inst[0].ring_enc[ring];
 		break;
 	case AMDGPU_HW_IP_VCN_DEC:
 		*out_ring = &adev->vcn.ring_dec;
-- 
cgit v1.2.3


From 122b5a05987c8bcc0f88df2fdfa39397b6002737 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 13:06:02 +0200
Subject: MAINTAINERS: add new TTM maintainers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Roger unfortunately doesn't work for AMD any longer. So add Rui and
Jerry as co-maintainer as well.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 MAINTAINERS | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 07d1576fc766..646f40f8c691 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4883,7 +4883,8 @@ F:	Documentation/gpu/xen-front.rst
 
 DRM TTM SUBSYSTEM
 M:	Christian Koenig <christian.koenig@amd.com>
-M:	Roger He <Hongbo.He@amd.com>
+M:	Huang Rui <ray.huang@amd.com>
+M:	Junwei Zhang <Jerry.Zhang@amd.com>
 T:	git git://people.freedesktop.org/~agd5f/linux
 S:	Maintained
 L:	dri-devel@lists.freedesktop.org
-- 
cgit v1.2.3


From dbae59466f3737acbdecaa565faf3edb8c8c4f67 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 13:16:06 +0200
Subject: MAINTAINERS: Add separate section for DC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Note that Harry and Leo Li are maintainers for that stuff.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 MAINTAINERS | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 646f40f8c691..2ba4cf8f5eef 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -728,6 +728,14 @@ S:	Supported
 F:	drivers/crypto/ccp/
 F:	include/linux/ccp.h
 
+AMD DISPLAY CORE
+M:	Harry Wentland <harry.wentland@amd.com>
+M:	Leo Li <sunpeng.li@amd.com>
+L:	amd-gfx@lists.freedesktop.org
+T:	git git://people.freedesktop.org/~agd5f/linux
+S:	Supported
+F:	drivers/gpu/drm/amd/display/
+
 AMD FAM15H PROCESSOR POWER MONITORING DRIVER
 M:	Huang Rui <ray.huang@amd.com>
 L:	linux-hwmon@vger.kernel.org
-- 
cgit v1.2.3


From 6beccb15c447356c40972da825e0c1ed803cfb10 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 19 Jul 2018 11:39:37 +0200
Subject: MAINTAINERS: add entry for AMD PP code
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add separate entry for the power managent code on AMD GPUs.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Rex Zhu <rezhu@amd.com>
Reviewed-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 MAINTAINERS | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 2ba4cf8f5eef..93f189f0d60d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -785,6 +785,14 @@ F:	drivers/gpu/drm/amd/include/vi_structs.h
 F:	drivers/gpu/drm/amd/include/v9_structs.h
 F:	include/uapi/linux/kfd_ioctl.h
 
+AMD POWERPLAY
+M:	Rex Zhu <rex.zhu@amd.com>
+M:	Evan Quan <evan.quan@amd.com>
+L:	amd-gfx@lists.freedesktop.org
+S:	Supported
+F:	drivers/gpu/drm/amd/powerplay/
+T:	git git://people.freedesktop.org/~agd5f/linux
+
 AMD SEATTLE DEVICE TREE SUPPORT
 M:	Brijesh Singh <brijeshkumar.singh@amd.com>
 M:	Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
-- 
cgit v1.2.3


From c704ab18e0a26a5dc7e947af6e8e01585380518b Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 16 Jul 2018 16:12:24 +0200
Subject: drm/amdgpu: consistenly name amdgpu_bo_ functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just rename functions, no functional change.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h              |  2 --
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c |  8 +++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c           | 10 +++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c          |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c       | 34 ++++++++++++------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h       |  3 +++
 drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c        |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h        |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c          | 10 +++----
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c          |  4 +--
 10 files changed, 39 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 44f62fda4022..0283e2b3c851 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1801,8 +1801,6 @@ void amdgpu_display_update_priority(struct amdgpu_device *adev);
 
 void amdgpu_cs_report_moved_bytes(struct amdgpu_device *adev, u64 num_bytes,
 				  u64 num_vis_bytes);
-void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
-bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
 void amdgpu_device_vram_location(struct amdgpu_device *adev,
 				 struct amdgpu_gmc *mc, u64 base);
 void amdgpu_device_gart_location(struct amdgpu_device *adev,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index 079af8ac2636..fa38a960ce00 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -334,7 +334,7 @@ static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
 		 "Called with userptr BO"))
 		return -EINVAL;
 
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 
 	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (ret)
@@ -622,7 +622,7 @@ static int init_user_pages(struct kgd_mem *mem, struct mm_struct *mm,
 		pr_err("%s: Failed to reserve BO\n", __func__);
 		goto release_out;
 	}
-	amdgpu_ttm_placement_from_domain(bo, mem->domain);
+	amdgpu_bo_placement_from_domain(bo, mem->domain);
 	ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (ret)
 		pr_err("%s: failed to validate BO\n", __func__);
@@ -1680,7 +1680,7 @@ static int update_invalid_user_pages(struct amdkfd_process_info *process_info,
 
 		if (amdgpu_bo_reserve(bo, true))
 			return -EAGAIN;
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_CPU);
 		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
 		if (ret) {
@@ -1824,7 +1824,7 @@ static int validate_invalid_user_pages(struct amdkfd_process_info *process_info)
 		if (mem->user_pages[0]) {
 			amdgpu_ttm_tt_set_user_pages(bo->tbo.ttm,
 						     mem->user_pages);
-			amdgpu_ttm_placement_from_domain(bo, mem->domain);
+			amdgpu_bo_placement_from_domain(bo, mem->domain);
 			ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (ret) {
 				pr_err("%s: failed to validate BO\n", __func__);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 7c5cc33d0cda..c5d81d6a90e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -419,7 +419,7 @@ static int amdgpu_cs_bo_validate(struct amdgpu_cs_parser *p,
 	}
 
 retry:
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 
 	p->bytes_moved += ctx.bytes_moved;
@@ -478,7 +478,7 @@ static bool amdgpu_cs_try_evict(struct amdgpu_cs_parser *p,
 		update_bytes_moved_vis =
 				!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 				amdgpu_bo_in_cpu_visible_vram(bo);
-		amdgpu_ttm_placement_from_domain(bo, other);
+		amdgpu_bo_placement_from_domain(bo, other);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		p->bytes_moved += ctx.bytes_moved;
 		if (update_bytes_moved_vis)
@@ -532,8 +532,8 @@ static int amdgpu_cs_list_validate(struct amdgpu_cs_parser *p,
 		/* Check if we have user pages and nobody bound the BO already */
 		if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm) &&
 		    lobj->user_pages) {
-			amdgpu_ttm_placement_from_domain(bo,
-							 AMDGPU_GEM_DOMAIN_CPU);
+			amdgpu_bo_placement_from_domain(bo,
+							AMDGPU_GEM_DOMAIN_CPU);
 			r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 			if (r)
 				return r;
@@ -1655,7 +1655,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
 
 	if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
 		(*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
-		amdgpu_ttm_placement_from_domain(*bo, (*bo)->allowed_domains);
+		amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
 		r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
 		if (r)
 			return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index bcbdcf997d20..71792d820ae0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -344,7 +344,7 @@ int amdgpu_gem_userptr_ioctl(struct drm_device *dev, void *data,
 		if (r)
 			goto free_pages;
 
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		amdgpu_bo_unreserve(bo);
 		if (r)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 3010f0136de9..7b3398c337f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -51,7 +51,7 @@
  *
  */
 
-static bool amdgpu_need_backup(struct amdgpu_device *adev)
+static bool amdgpu_bo_need_backup(struct amdgpu_device *adev)
 {
 	if (adev->flags & AMD_IS_APU)
 		return false;
@@ -84,7 +84,7 @@ static void amdgpu_bo_subtract_pin_size(struct amdgpu_bo *bo)
 	}
 }
 
-static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
+static void amdgpu_bo_destroy(struct ttm_buffer_object *tbo)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(tbo->bdev);
 	struct amdgpu_bo *bo = ttm_to_amdgpu_bo(tbo);
@@ -111,7 +111,7 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
 }
 
 /**
- * amdgpu_ttm_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo
+ * amdgpu_bo_is_amdgpu_bo - check if the buffer object is an &amdgpu_bo
  * @bo: buffer object to be checked
  *
  * Uses destroy function associated with the object to determine if this is
@@ -120,22 +120,22 @@ static void amdgpu_ttm_bo_destroy(struct ttm_buffer_object *tbo)
  * Returns:
  * true if the object belongs to &amdgpu_bo, false if not.
  */
-bool amdgpu_ttm_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
+bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo)
 {
-	if (bo->destroy == &amdgpu_ttm_bo_destroy)
+	if (bo->destroy == &amdgpu_bo_destroy)
 		return true;
 	return false;
 }
 
 /**
- * amdgpu_ttm_placement_from_domain - set buffer's placement
+ * amdgpu_bo_placement_from_domain - set buffer's placement
  * @abo: &amdgpu_bo buffer object whose placement is to be set
  * @domain: requested domain
  *
  * Sets buffer's placement according to requested domain and the buffer's
  * flags.
  */
-void amdgpu_ttm_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
+void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 {
 	struct amdgpu_device *adev = amdgpu_ttm_adev(abo->tbo.bdev);
 	struct ttm_placement *placement = &abo->placement;
@@ -488,13 +488,13 @@ static int amdgpu_bo_do_create(struct amdgpu_device *adev,
 #endif
 
 	bo->tbo.bdev = &adev->mman.bdev;
-	amdgpu_ttm_placement_from_domain(bo, bp->domain);
+	amdgpu_bo_placement_from_domain(bo, bp->domain);
 	if (bp->type == ttm_bo_type_kernel)
 		bo->tbo.priority = 1;
 
 	r = ttm_bo_init_reserved(&adev->mman.bdev, &bo->tbo, size, bp->type,
 				 &bo->placement, page_align, &ctx, acc_size,
-				 NULL, bp->resv, &amdgpu_ttm_bo_destroy);
+				 NULL, bp->resv, &amdgpu_bo_destroy);
 	if (unlikely(r != 0))
 		return r;
 
@@ -594,7 +594,7 @@ int amdgpu_bo_create(struct amdgpu_device *adev,
 	if (r)
 		return r;
 
-	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_need_backup(adev)) {
+	if ((flags & AMDGPU_GEM_CREATE_SHADOW) && amdgpu_bo_need_backup(adev)) {
 		if (!bp->resv)
 			WARN_ON(reservation_object_lock((*bo_ptr)->tbo.resv,
 							NULL));
@@ -682,7 +682,7 @@ int amdgpu_bo_validate(struct amdgpu_bo *bo)
 	domain = bo->preferred_domains;
 
 retry:
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	if (unlikely(r == -ENOMEM) && domain != bo->allowed_domains) {
 		domain = bo->allowed_domains;
@@ -915,7 +915,7 @@ int amdgpu_bo_pin_restricted(struct amdgpu_bo *bo, u32 domain,
 	/* force to pin into visible video ram */
 	if (!(bo->flags & AMDGPU_GEM_CREATE_NO_CPU_ACCESS))
 		bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
-	amdgpu_ttm_placement_from_domain(bo, domain);
+	amdgpu_bo_placement_from_domain(bo, domain);
 	for (i = 0; i < bo->placement.num_placement; i++) {
 		unsigned fpfn, lpfn;
 
@@ -1246,7 +1246,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 	struct amdgpu_bo *abo;
 	struct ttm_mem_reg *old_mem = &bo->mem;
 
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return;
 
 	abo = ttm_to_amdgpu_bo(bo);
@@ -1263,7 +1263,7 @@ void amdgpu_bo_move_notify(struct ttm_buffer_object *bo,
 		return;
 
 	/* move_notify is called before move happens */
-	trace_amdgpu_ttm_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
+	trace_amdgpu_bo_move(abo, new_mem->mem_type, old_mem->mem_type);
 }
 
 /**
@@ -1285,7 +1285,7 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 	unsigned long offset, size;
 	int r;
 
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo))
+	if (!amdgpu_bo_is_amdgpu_bo(bo))
 		return 0;
 
 	abo = ttm_to_amdgpu_bo(bo);
@@ -1307,8 +1307,8 @@ int amdgpu_bo_fault_reserve_notify(struct ttm_buffer_object *bo)
 
 	/* hurrah the memory is not visible ! */
 	atomic64_inc(&adev->num_vram_cpu_page_faults);
-	amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
-					 AMDGPU_GEM_DOMAIN_GTT);
+	amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
+					AMDGPU_GEM_DOMAIN_GTT);
 
 	/* Avoid costly evictions; only set GTT as a busy placement */
 	abo->placement.num_busy_placement = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 9c3e29a04eb1..345fcd176992 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -234,6 +234,9 @@ static inline bool amdgpu_bo_explicit_sync(struct amdgpu_bo *bo)
 	return bo->flags & AMDGPU_GEM_CREATE_EXPLICIT_SYNC;
 }
 
+bool amdgpu_bo_is_amdgpu_bo(struct ttm_buffer_object *bo);
+void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain);
+
 int amdgpu_bo_create(struct amdgpu_device *adev,
 		     struct amdgpu_bo_param *bp,
 		     struct amdgpu_bo **bo_ptr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
index 3ed02f472003..1c5d97f4b4dd 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -323,7 +323,7 @@ static int amdgpu_gem_begin_cpu_access(struct dma_buf *dma_buf,
 		return ret;
 
 	if (!bo->pin_count && (bo->allowed_domains & AMDGPU_GEM_DOMAIN_GTT)) {
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_GTT);
 		ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 	}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 76920035eb22..11f262f15200 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -436,7 +436,7 @@ TRACE_EVENT(amdgpu_cs_bo_status,
 			__entry->total_bo, __entry->total_size)
 );
 
-TRACE_EVENT(amdgpu_ttm_bo_move,
+TRACE_EVENT(amdgpu_bo_move,
 	    TP_PROTO(struct amdgpu_bo* bo, uint32_t new_placement, uint32_t old_placement),
 	    TP_ARGS(bo, new_placement, old_placement),
 	    TP_STRUCT__entry(
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 8ed102933ca2..6039f8e21358 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -248,7 +248,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	}
 
 	/* Object isn't an AMDGPU object so ignore */
-	if (!amdgpu_ttm_bo_is_amdgpu_bo(bo)) {
+	if (!amdgpu_bo_is_amdgpu_bo(bo)) {
 		placement->placement = &placements;
 		placement->busy_placement = &placements;
 		placement->num_placement = 1;
@@ -261,7 +261,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 	case TTM_PL_VRAM:
 		if (!adev->mman.buffer_funcs_enabled) {
 			/* Move to system memory */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
 		} else if (!amdgpu_gmc_vram_full_visible(&adev->gmc) &&
 			   !(abo->flags & AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED) &&
 			   amdgpu_bo_in_cpu_visible_vram(abo)) {
@@ -271,7 +271,7 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			 * BO will be evicted to GTT rather than causing other
 			 * BOs to be evicted from VRAM
 			 */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_VRAM |
 							 AMDGPU_GEM_DOMAIN_GTT);
 			abo->placements[0].fpfn = adev->gmc.visible_vram_size >> PAGE_SHIFT;
 			abo->placements[0].lpfn = 0;
@@ -279,12 +279,12 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 			abo->placement.num_busy_placement = 1;
 		} else {
 			/* Move to GTT memory */
-			amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
+			amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_GTT);
 		}
 		break;
 	case TTM_PL_TT:
 	default:
-		amdgpu_ttm_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
+		amdgpu_bo_placement_from_domain(abo, AMDGPU_GEM_DOMAIN_CPU);
 	}
 	*placement = abo->placement;
 }
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index 80b5c453f8c1..e1e4810b9d9e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -473,7 +473,7 @@ static int amdgpu_uvd_cs_pass1(struct amdgpu_uvd_cs_ctx *ctx)
 		if (cmd == 0x0 || cmd == 0x3) {
 			/* yes, force it into VRAM */
 			uint32_t domain = AMDGPU_GEM_DOMAIN_VRAM;
-			amdgpu_ttm_placement_from_domain(bo, domain);
+			amdgpu_bo_placement_from_domain(bo, domain);
 		}
 		amdgpu_uvd_force_into_uvd_segment(bo);
 
@@ -1014,7 +1014,7 @@ static int amdgpu_uvd_send_msg(struct amdgpu_ring *ring, struct amdgpu_bo *bo,
 	if (!ring->adev->uvd.address_64_bit) {
 		struct ttm_operation_ctx ctx = { true, false };
 
-		amdgpu_ttm_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
+		amdgpu_bo_placement_from_domain(bo, AMDGPU_GEM_DOMAIN_VRAM);
 		amdgpu_uvd_force_into_uvd_segment(bo);
 		r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
 		if (r)
-- 
cgit v1.2.3


From bf314ca3f10d4ba4335808dc678631908881db8b Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 11:16:35 +0200
Subject: drm/amdgpu: reduce the number of placements for a BO
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make struct amdgpu_bo a bit smaller.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 7b3398c337f1..21bfa2d8039e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -216,6 +216,8 @@ void amdgpu_bo_placement_from_domain(struct amdgpu_bo *abo, u32 domain)
 		c++;
 	}
 
+	BUG_ON(c >= AMDGPU_BO_MAX_PLACEMENTS);
+
 	placement->num_placement = c;
 	placement->placement = places;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
index 345fcd176992..18945dd6982d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -32,6 +32,7 @@
 #include "amdgpu.h"
 
 #define AMDGPU_BO_INVALID_OFFSET	LONG_MAX
+#define AMDGPU_BO_MAX_PLACEMENTS	3
 
 struct amdgpu_bo_param {
 	unsigned long			size;
@@ -77,7 +78,7 @@ struct amdgpu_bo {
 	/* Protected by tbo.reserved */
 	u32				preferred_domains;
 	u32				allowed_domains;
-	struct ttm_place		placements[AMDGPU_GEM_DOMAIN_MAX + 1];
+	struct ttm_place		placements[AMDGPU_BO_MAX_PLACEMENTS];
 	struct ttm_placement		placement;
 	struct ttm_buffer_object	tbo;
 	struct ttm_bo_kmap_obj		kmap;
-- 
cgit v1.2.3


From cdc50176597cb44ce25eb7331c450058775b8d2a Mon Sep 17 00:00:00 2001
From: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Date: Fri, 20 Jul 2018 17:51:05 +0530
Subject: drm/scheduler: modify API to avoid redundancy
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

entity has a scheduler field and we don't need the sched argument
in any of the functions where entity is provided.

Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c   | 13 +++++--------
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c   |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c   |  3 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c   |  3 +--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c   |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c    |  4 ++--
 drivers/gpu/drm/etnaviv/etnaviv_drv.c     |  3 +--
 drivers/gpu/drm/etnaviv/etnaviv_sched.c   |  4 ++--
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 20 +++++++++++---------
 drivers/gpu/drm/v3d/v3d_drv.c             |  4 +---
 drivers/gpu/drm/v3d/v3d_gem.c             |  2 --
 include/drm/gpu_scheduler.h               | 10 +++-------
 13 files changed, 30 insertions(+), 42 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index c5d81d6a90e0..4d4575b3bba7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1232,7 +1232,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	job = p->job;
 	p->job = NULL;
 
-	r = drm_sched_job_init(&job->base, &ring->sched, entity, p->filp);
+	r = drm_sched_job_init(&job->base, entity, p->filp);
 	if (r) {
 		amdgpu_job_free(job);
 		amdgpu_mn_unlock(p->mn);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
index 83e3b320a793..df6965761046 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -104,8 +104,7 @@ static int amdgpu_ctx_init(struct amdgpu_device *adev,
 
 failed:
 	for (j = 0; j < i; j++)
-		drm_sched_entity_destroy(&adev->rings[j]->sched,
-				      &ctx->rings[j].entity);
+		drm_sched_entity_destroy(&ctx->rings[j].entity);
 	kfree(ctx->fences);
 	ctx->fences = NULL;
 	return r;
@@ -178,8 +177,7 @@ static void amdgpu_ctx_do_release(struct kref *ref)
 		if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 			continue;
 
-		drm_sched_entity_destroy(&ctx->adev->rings[i]->sched,
-			&ctx->rings[i].entity);
+		drm_sched_entity_destroy(&ctx->rings[i].entity);
 	}
 
 	amdgpu_ctx_fini(ref);
@@ -466,8 +464,8 @@ void amdgpu_ctx_mgr_entity_flush(struct amdgpu_ctx_mgr *mgr)
 			if (ctx->adev->rings[i] == &ctx->adev->gfx.kiq.ring)
 				continue;
 
-			max_wait = drm_sched_entity_flush(&ctx->adev->rings[i]->sched,
-					  &ctx->rings[i].entity, max_wait);
+			max_wait = drm_sched_entity_flush(&ctx->rings[i].entity,
+							  max_wait);
 		}
 	}
 	mutex_unlock(&mgr->lock);
@@ -492,8 +490,7 @@ void amdgpu_ctx_mgr_entity_fini(struct amdgpu_ctx_mgr *mgr)
 				continue;
 
 			if (kref_read(&ctx->refcount) == 1)
-				drm_sched_entity_fini(&ctx->adev->rings[i]->sched,
-					&ctx->rings[i].entity);
+				drm_sched_entity_fini(&ctx->rings[i].entity);
 			else
 				DRM_ERROR("ctx %p is still alive\n", ctx);
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 5a2c26a85984..631481a730e0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -133,7 +133,7 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 	if (!f)
 		return -EINVAL;
 
-	r = drm_sched_job_init(&job->base, entity->sched, entity, owner);
+	r = drm_sched_job_init(&job->base, entity, owner);
 	if (r)
 		return r;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 6039f8e21358..8c4358e36c87 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -1925,8 +1925,7 @@ void amdgpu_ttm_set_buffer_funcs_status(struct amdgpu_device *adev, bool enable)
 			return;
 		}
 	} else {
-		drm_sched_entity_destroy(adev->mman.entity.sched,
-					 &adev->mman.entity);
+		drm_sched_entity_destroy(&adev->mman.entity);
 		dma_fence_put(man->move);
 		man->move = NULL;
 	}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index e1e4810b9d9e..fca86d71fafc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -305,8 +305,7 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 {
 	int i, j;
 
-	drm_sched_entity_destroy(&adev->uvd.inst->ring.sched,
-				 &adev->uvd.entity);
+	drm_sched_entity_destroy(&adev->uvd.entity);
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
 		kfree(adev->uvd.inst[j].saved_bo);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
index 86182c966ed6..b6ab4f5350c8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -221,7 +221,7 @@ int amdgpu_vce_sw_fini(struct amdgpu_device *adev)
 	if (adev->vce.vcpu_bo == NULL)
 		return 0;
 
-	drm_sched_entity_destroy(&adev->vce.ring[0].sched, &adev->vce.entity);
+	drm_sched_entity_destroy(&adev->vce.entity);
 
 	amdgpu_bo_free_kernel(&adev->vce.vcpu_bo, &adev->vce.gpu_addr,
 		(void **)&adev->vce.cpu_addr);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 098dd1ba751a..74b4a28a41d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2642,7 +2642,7 @@ error_free_root:
 	vm->root.base.bo = NULL;
 
 error_free_sched_entity:
-	drm_sched_entity_destroy(&ring->sched, &vm->entity);
+	drm_sched_entity_destroy(&vm->entity);
 
 	return r;
 }
@@ -2779,7 +2779,7 @@ void amdgpu_vm_fini(struct amdgpu_device *adev, struct amdgpu_vm *vm)
 		spin_unlock_irqrestore(&adev->vm_manager.pasid_lock, flags);
 	}
 
-	drm_sched_entity_destroy(vm->entity.sched, &vm->entity);
+	drm_sched_entity_destroy(&vm->entity);
 
 	if (!RB_EMPTY_ROOT(&vm->va.rb_root)) {
 		dev_err(adev->dev, "still active bo inside vm\n");
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.c b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
index 36414ba56b22..207532c05eb8 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.c
@@ -78,8 +78,7 @@ static void etnaviv_postclose(struct drm_device *dev, struct drm_file *file)
 				gpu->lastctx = NULL;
 			mutex_unlock(&gpu->lock);
 
-			drm_sched_entity_destroy(&gpu->sched,
-						&ctx->sched_entity[i]);
+			drm_sched_entity_destroy(&ctx->sched_entity[i]);
 		}
 	}
 
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index a74eb57af15b..590e44b0d963 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -118,8 +118,8 @@ int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity,
 {
 	int ret;
 
-	ret = drm_sched_job_init(&submit->sched_job, &submit->gpu->sched,
-				 sched_entity, submit->cmdbuf.ctx);
+	ret = drm_sched_job_init(&submit->sched_job, sched_entity,
+				 submit->cmdbuf.ctx);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index dac71e3b4514..a3b55c542025 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -273,11 +273,12 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
  *
  * Returns the remaining time in jiffies left from the input timeout
  */
-long drm_sched_entity_flush(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity, long timeout)
+long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 {
+	struct drm_gpu_scheduler *sched;
 	long ret = timeout;
 
+	sched = entity->sched;
 	if (!drm_sched_entity_is_initialized(sched, entity))
 		return ret;
 	/**
@@ -312,10 +313,11 @@ EXPORT_SYMBOL(drm_sched_entity_flush);
  * entity and signals all jobs with an error code if the process was killed.
  *
  */
-void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity)
+void drm_sched_entity_fini(struct drm_sched_entity *entity)
 {
+	struct drm_gpu_scheduler *sched;
 
+	sched = entity->sched;
 	drm_sched_entity_set_rq(entity, NULL);
 
 	/* Consumption of existing IBs wasn't completed. Forcefully
@@ -373,11 +375,10 @@ EXPORT_SYMBOL(drm_sched_entity_fini);
  *
  * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup()
  */
-void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched,
-				struct drm_sched_entity *entity)
+void drm_sched_entity_destroy(struct drm_sched_entity *entity)
 {
-	drm_sched_entity_flush(sched, entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
-	drm_sched_entity_fini(sched, entity);
+	drm_sched_entity_flush(entity, MAX_WAIT_SCHED_ENTITY_Q_EMPTY);
+	drm_sched_entity_fini(entity);
 }
 EXPORT_SYMBOL(drm_sched_entity_destroy);
 
@@ -740,10 +741,11 @@ EXPORT_SYMBOL(drm_sched_job_recovery);
  * Returns 0 for success, negative error code otherwise.
  */
 int drm_sched_job_init(struct drm_sched_job *job,
-		       struct drm_gpu_scheduler *sched,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
+	struct drm_gpu_scheduler *sched = entity->sched;
+
 	job->sched = sched;
 	job->entity = entity;
 	job->s_priority = entity->rq - sched->sched_rq;
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index 1dceba2b42fd..2a85fa68ffea 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -145,13 +145,11 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 static void
 v3d_postclose(struct drm_device *dev, struct drm_file *file)
 {
-	struct v3d_dev *v3d = to_v3d_dev(dev);
 	struct v3d_file_priv *v3d_priv = file->driver_priv;
 	enum v3d_queue q;
 
 	for (q = 0; q < V3D_MAX_QUEUES; q++) {
-		drm_sched_entity_destroy(&v3d->queue[q].sched,
-				      &v3d_priv->sched_entity[q]);
+		drm_sched_entity_destroy(&v3d_priv->sched_entity[q]);
 	}
 
 	kfree(v3d_priv);
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index e1fcbb4cd0ae..5ce24098a5fd 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -553,7 +553,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	mutex_lock(&v3d->sched_lock);
 	if (exec->bin.start != exec->bin.end) {
 		ret = drm_sched_job_init(&exec->bin.base,
-					 &v3d->queue[V3D_BIN].sched,
 					 &v3d_priv->sched_entity[V3D_BIN],
 					 v3d_priv);
 		if (ret)
@@ -568,7 +567,6 @@ v3d_submit_cl_ioctl(struct drm_device *dev, void *data,
 	}
 
 	ret = drm_sched_job_init(&exec->render.base,
-				 &v3d->queue[V3D_RENDER].sched,
 				 &v3d_priv->sched_entity[V3D_RENDER],
 				 v3d_priv);
 	if (ret)
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 2205e89722f6..728346abcc81 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -286,12 +286,9 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 			  struct drm_sched_rq **rq_list,
 			  unsigned int num_rq_list,
 			  atomic_t *guilty);
-long drm_sched_entity_flush(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity, long timeout);
-void drm_sched_entity_fini(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity);
-void drm_sched_entity_destroy(struct drm_gpu_scheduler *sched,
-			   struct drm_sched_entity *entity);
+long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout);
+void drm_sched_entity_fini(struct drm_sched_entity *entity);
+void drm_sched_entity_destroy(struct drm_sched_entity *entity);
 void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 			       struct drm_sched_entity *entity);
 void drm_sched_entity_set_rq(struct drm_sched_entity *entity,
@@ -302,7 +299,6 @@ struct drm_sched_fence *drm_sched_fence_create(
 void drm_sched_fence_scheduled(struct drm_sched_fence *fence);
 void drm_sched_fence_finished(struct drm_sched_fence *fence);
 int drm_sched_job_init(struct drm_sched_job *job,
-		       struct drm_gpu_scheduler *sched,
 		       struct drm_sched_entity *entity,
 		       void *owner);
 void drm_sched_hw_job_reset(struct drm_gpu_scheduler *sched,
-- 
cgit v1.2.3


From 068c330419ffb3422a43cb7d34351f1ef033950f Mon Sep 17 00:00:00 2001
From: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Date: Fri, 20 Jul 2018 17:51:06 +0530
Subject: drm/scheduler: remove sched field from the entity
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The scheduler of the entity is decided by the run queue on which
it is queued. This patch avoids us the effort required to maintain
a sync between rq and sched field when we start shifting entites
among different rqs.

Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c    |  2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu_job.c   |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c    |  6 +++---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 19 +++++++++----------
 drivers/gpu/drm/scheduler/sched_fence.c   |  2 +-
 include/drm/gpu_scheduler.h               |  2 --
 6 files changed, 16 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 4d4575b3bba7..178d9ce4eba1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1262,7 +1262,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
-	ring = to_amdgpu_ring(entity->sched);
+	ring = to_amdgpu_ring(entity->rq->sched);
 	amdgpu_ring_priority_get(ring, priority);
 
 	ttm_eu_fence_buffer_objects(&p->ticket, &p->validated, p->fence);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
index 631481a730e0..391e2f7c03aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
@@ -143,7 +143,7 @@ int amdgpu_job_submit(struct amdgpu_job *job, struct drm_sched_entity *entity,
 	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
-	ring = to_amdgpu_ring(entity->sched);
+	ring = to_amdgpu_ring(entity->rq->sched);
 	amdgpu_ring_priority_get(ring, priority);
 
 	return 0;
@@ -167,7 +167,7 @@ int amdgpu_job_submit_direct(struct amdgpu_job *job, struct amdgpu_ring *ring,
 static struct dma_fence *amdgpu_job_dependency(struct drm_sched_job *sched_job,
 					       struct drm_sched_entity *s_entity)
 {
-	struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->sched);
+	struct amdgpu_ring *ring = to_amdgpu_ring(s_entity->rq->sched);
 	struct amdgpu_job *job = to_amdgpu_job(sched_job);
 	struct amdgpu_vm *vm = job->vm;
 	struct dma_fence *fence;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 74b4a28a41d6..5d7d7900ccab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -387,7 +387,7 @@ static int amdgpu_vm_clear_bo(struct amdgpu_device *adev,
 		ats_entries = 0;
 	}
 
-	ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
+	ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched);
 
 	r = reservation_object_reserve_shared(bo->tbo.resv);
 	if (r)
@@ -1113,7 +1113,7 @@ restart:
 		struct amdgpu_ring *ring;
 		struct dma_fence *fence;
 
-		ring = container_of(vm->entity.sched, struct amdgpu_ring,
+		ring = container_of(vm->entity.rq->sched, struct amdgpu_ring,
 				    sched);
 
 		amdgpu_ring_pad_ib(ring, params.ib);
@@ -1403,7 +1403,7 @@ static int amdgpu_vm_bo_update_mapping(struct amdgpu_device *adev,
 					   addr, flags);
 	}
 
-	ring = container_of(vm->entity.sched, struct amdgpu_ring, sched);
+	ring = container_of(vm->entity.rq->sched, struct amdgpu_ring, sched);
 
 	nptes = last - start + 1;
 
diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index a3b55c542025..3f2fc5e8242a 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -185,7 +185,6 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 	memset(entity, 0, sizeof(struct drm_sched_entity));
 	INIT_LIST_HEAD(&entity->list);
 	entity->rq = rq_list[0];
-	entity->sched = rq_list[0]->sched;
 	entity->guilty = guilty;
 	entity->last_scheduled = NULL;
 
@@ -210,8 +209,8 @@ EXPORT_SYMBOL(drm_sched_entity_init);
 static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched,
 					    struct drm_sched_entity *entity)
 {
-	return entity->sched == sched &&
-		entity->rq != NULL;
+	return entity->rq != NULL &&
+		entity->rq->sched == sched;
 }
 
 /**
@@ -278,7 +277,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 	struct drm_gpu_scheduler *sched;
 	long ret = timeout;
 
-	sched = entity->sched;
+	sched = entity->rq->sched;
 	if (!drm_sched_entity_is_initialized(sched, entity))
 		return ret;
 	/**
@@ -317,7 +316,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
 {
 	struct drm_gpu_scheduler *sched;
 
-	sched = entity->sched;
+	sched = entity->rq->sched;
 	drm_sched_entity_set_rq(entity, NULL);
 
 	/* Consumption of existing IBs wasn't completed. Forcefully
@@ -388,7 +387,7 @@ static void drm_sched_entity_wakeup(struct dma_fence *f, struct dma_fence_cb *cb
 		container_of(cb, struct drm_sched_entity, cb);
 	entity->dependency = NULL;
 	dma_fence_put(f);
-	drm_sched_wakeup(entity->sched);
+	drm_sched_wakeup(entity->rq->sched);
 }
 
 static void drm_sched_entity_clear_dep(struct dma_fence *f, struct dma_fence_cb *cb)
@@ -438,7 +437,7 @@ EXPORT_SYMBOL(drm_sched_entity_set_rq);
 bool drm_sched_dependency_optimized(struct dma_fence* fence,
 				    struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct drm_sched_fence *s_fence;
 
 	if (!fence || dma_fence_is_signaled(fence))
@@ -455,7 +454,7 @@ EXPORT_SYMBOL(drm_sched_dependency_optimized);
 
 static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct dma_fence * fence = entity->dependency;
 	struct drm_sched_fence *s_fence;
 
@@ -500,7 +499,7 @@ static bool drm_sched_entity_add_dependency_cb(struct drm_sched_entity *entity)
 static struct drm_sched_job *
 drm_sched_entity_pop_job(struct drm_sched_entity *entity)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 	struct drm_sched_job *sched_job = to_drm_sched_job(
 						spsc_queue_peek(&entity->job_queue));
 
@@ -744,7 +743,7 @@ int drm_sched_job_init(struct drm_sched_job *job,
 		       struct drm_sched_entity *entity,
 		       void *owner)
 {
-	struct drm_gpu_scheduler *sched = entity->sched;
+	struct drm_gpu_scheduler *sched = entity->rq->sched;
 
 	job->sched = sched;
 	job->entity = entity;
diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c
index 45d9c3affbea..d8d2dff9ea2f 100644
--- a/drivers/gpu/drm/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/scheduler/sched_fence.c
@@ -161,7 +161,7 @@ struct drm_sched_fence *drm_sched_fence_create(struct drm_sched_entity *entity,
 		return NULL;
 
 	fence->owner = owner;
-	fence->sched = entity->sched;
+	fence->sched = entity->rq->sched;
 	spin_lock_init(&fence->lock);
 
 	seq = atomic_inc_return(&entity->fence_seq);
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 728346abcc81..091b9afcd184 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -52,7 +52,6 @@ enum drm_sched_priority {
  *        runqueue.
  * @rq: runqueue to which this entity belongs.
  * @rq_lock: lock to modify the runqueue to which this entity belongs.
- * @sched: the scheduler instance to which this entity is enqueued.
  * @job_queue: the list of jobs of this entity.
  * @fence_seq: a linearly increasing seqno incremented with each
  *             new &drm_sched_fence which is part of the entity.
@@ -76,7 +75,6 @@ struct drm_sched_entity {
 	struct list_head		list;
 	struct drm_sched_rq		*rq;
 	spinlock_t			rq_lock;
-	struct drm_gpu_scheduler	*sched;
 
 	struct spsc_queue		job_queue;
 
-- 
cgit v1.2.3


From 6cdf4e87b454d1f26ef557307345dadce71d1f94 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 24 Jul 2018 11:52:58 -0500
Subject: drm/amdgpu/gmc9: clarify GPUVM fault error message
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The address printed is the actual address, not the page.

Reviewed-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
index 9df94b45d17d..399a5db27649 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
@@ -269,7 +269,7 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
 			entry->src_id, entry->ring_id, entry->vmid,
 			entry->pasid, task_info.process_name, task_info.tgid,
 			task_info.task_name, task_info.pid);
-		dev_err(adev->dev, "  at page 0x%016llx from %d\n",
+		dev_err(adev->dev, "  at address 0x%016llx from %d\n",
 			addr, entry->client_id);
 		if (!amdgpu_sriov_vf(adev))
 			dev_err(adev->dev,
-- 
cgit v1.2.3


From 586092ab4b768b01b3184d9a2541e2cf9a8d9740 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 22:29:56 +0800
Subject: gpu: drm: amdgpu: Replace mdelay with msleep in
 cik_pcie_gen3_enable()

cik_pcie_gen3_enable() is only called by cik_common_hw_init(), which is
never called in atomic context.
cik_pcie_gen3_enable() calls mdelay() to busily wait, which is not
necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/cik.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/cik.c b/drivers/gpu/drm/amd/amdgpu/cik.c
index 702e257a483f..78ab939ae5d8 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik.c
@@ -1476,7 +1476,7 @@ static void cik_pcie_gen3_enable(struct amdgpu_device *adev)
 				tmp |= PCIE_LC_CNTL4__LC_REDO_EQ_MASK;
 				WREG32_PCIE(ixPCIE_LC_CNTL4, tmp);
 
-				mdelay(100);
+				msleep(100);
 
 				/* linkctl */
 				pci_read_config_word(root, bridge_pos + PCI_EXP_LNKCTL, &tmp16);
-- 
cgit v1.2.3


From 13d6753f1d250885749386867c4a4e8c06c905da Mon Sep 17 00:00:00 2001
From: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Date: Fri, 20 Jul 2018 10:22:57 +0200
Subject: pinctrl: tegra: fix spelling in devicetree binding document

This fixes a spelling mistake.

Signed-off-by: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt | 2 +-
 Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
index ecb5c0d25218..f4d06bb0b55a 100644
--- a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra124-pinmux.txt
@@ -17,7 +17,7 @@ Tegra124 adds the following optional properties for pin configuration subnodes.
 The macros for options are defined in the
 	include/dt-binding/pinctrl/pinctrl-tegra.h.
 - nvidia,enable-input: Integer. Enable the pin's input path.
-		enable :TEGRA_PIN_ENABLE0 and
+		enable :TEGRA_PIN_ENABLE and
 		disable or output only: TEGRA_PIN_DISABLE.
 - nvidia,open-drain: Integer.
 		enable: TEGRA_PIN_ENABLE.
diff --git a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt
index a62d82d5fbe9..85f211436b8e 100644
--- a/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt
+++ b/Documentation/devicetree/bindings/pinctrl/nvidia,tegra210-pinmux.txt
@@ -44,7 +44,7 @@ Optional subnode-properties:
 - nvidia,tristate: Integer.
     0: drive, 1: tristate.
 - nvidia,enable-input: Integer. Enable the pin's input path.
-    enable :TEGRA_PIN_ENABLE0 and
+    enable :TEGRA_PIN_ENABLE and
     disable or output only: TEGRA_PIN_DISABLE.
 - nvidia,open-drain: Integer.
     enable: TEGRA_PIN_ENABLE.
-- 
cgit v1.2.3


From 791d3ef2e11100449837dc0b6fe884e60ca3a484 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 23 Jul 2018 15:59:44 -0600
Subject: dt-bindings: remove 'interrupt-parent' from bindings

'interrupt-parent' is often documented as part of define bindings, but
it is really outside the scope of a device binding. It's never required
in a given node as it is often inherited from a parent node. Or it can
be implicit if a parent node is an 'interrupt-controller' node. So
remove it from all the binding files.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: devicetree@vger.kernel.org
Signed-off-by: Rob Herring <robh@kernel.org>
---
 .../bindings/arm/freescale/fsl,vf610-mscm-ir.txt    |  3 ---
 .../devicetree/bindings/arm/omap/crossbar.txt       |  1 -
 .../devicetree/bindings/arm/samsung/pmu.txt         |  3 ---
 Documentation/devicetree/bindings/ata/fsl-sata.txt  |  1 -
 .../devicetree/bindings/ata/pata-arasan.txt         |  2 --
 .../devicetree/bindings/board/fsl-board.txt         |  1 -
 .../devicetree/bindings/bus/brcm,gisb-arb.txt       |  2 --
 .../devicetree/bindings/clock/at91-clock.txt        |  7 -------
 .../bindings/cpufreq/brcm,stb-avs-cpu-freq.txt      |  2 --
 .../devicetree/bindings/crypto/amd-ccp.txt          |  2 --
 .../devicetree/bindings/crypto/arm-cryptocell.txt   |  2 --
 .../devicetree/bindings/crypto/fsl-sec2.txt         |  5 -----
 .../devicetree/bindings/crypto/fsl-sec4.txt         | 21 ---------------------
 .../devicetree/bindings/crypto/picochip-spacc.txt   |  2 --
 .../bindings/display/bridge/analogix_dp.txt         |  2 --
 .../devicetree/bindings/display/bridge/anx7814.txt  |  2 --
 .../bridge/megachips-stdpxxxx-ge-b850v3-fw.txt      |  2 --
 .../devicetree/bindings/display/bridge/sii902x.txt  |  4 ++--
 .../devicetree/bindings/display/bridge/sii9234.txt  |  2 +-
 .../bindings/display/bridge/sil-sii8620.txt         |  2 +-
 .../bindings/display/exynos/exynos7-decon.txt       |  3 ---
 .../bindings/display/exynos/exynos_dp.txt           |  2 --
 .../bindings/display/exynos/samsung-fimd.txt        |  3 ---
 .../devicetree/bindings/display/ht16k33.txt         |  2 --
 .../devicetree/bindings/display/msm/dsi.txt         |  2 --
 .../devicetree/bindings/display/msm/edp.txt         |  4 ----
 .../devicetree/bindings/display/msm/mdp5.txt        |  2 --
 .../devicetree/bindings/display/renesas,du.txt      |  1 -
 .../devicetree/bindings/display/sm501fb.txt         |  2 --
 .../devicetree/bindings/display/tilcdc/tilcdc.txt   |  2 --
 .../devicetree/bindings/dma/jz4780-dma.txt          |  1 -
 .../bindings/dma/nvidia,tegra210-adma.txt           |  1 -
 .../devicetree/bindings/dma/snps,dw-axi-dmac.txt    |  2 --
 Documentation/devicetree/bindings/dma/snps-dma.txt  |  2 --
 Documentation/devicetree/bindings/dma/ti-edma.txt   |  1 -
 .../devicetree/bindings/dma/xilinx/zynqmp_dma.txt   |  1 -
 .../devicetree/bindings/extcon/extcon-rt8973a.txt   |  2 --
 .../devicetree/bindings/extcon/extcon-sm5502.txt    |  2 --
 .../devicetree/bindings/gpio/8xxx_gpio.txt          |  2 --
 .../devicetree/bindings/gpio/abilis,tb10x-gpio.txt  |  1 -
 .../devicetree/bindings/gpio/brcm,brcmstb-gpio.txt  |  3 ---
 .../devicetree/bindings/gpio/gpio-adnp.txt          |  1 -
 .../devicetree/bindings/gpio/gpio-aspeed.txt        |  1 -
 .../devicetree/bindings/gpio/gpio-ath79.txt         |  1 -
 .../devicetree/bindings/gpio/gpio-davinci.txt       |  2 --
 .../devicetree/bindings/gpio/gpio-max732x.txt       |  1 -
 .../devicetree/bindings/gpio/gpio-pcf857x.txt       |  1 -
 .../devicetree/bindings/gpio/gpio-uniphier.txt      |  1 -
 .../devicetree/bindings/gpio/gpio-xgene-sb.txt      |  1 -
 .../devicetree/bindings/gpio/gpio-xilinx.txt        |  2 --
 Documentation/devicetree/bindings/gpio/gpio-xlp.txt |  1 -
 .../devicetree/bindings/gpio/gpio-zynq.txt          |  1 -
 .../bindings/gpio/nintendo,hollywood-gpio.txt       |  1 -
 .../devicetree/bindings/gpio/renesas,gpio-rcar.txt  |  1 -
 .../devicetree/bindings/gpio/snps-dwapb-gpio.txt    |  1 -
 Documentation/devicetree/bindings/hsi/omap-ssi.txt  |  1 -
 .../devicetree/bindings/i2c/i2c-aspeed.txt          |  3 ---
 .../devicetree/bindings/i2c/i2c-brcmstb.txt         |  2 --
 .../devicetree/bindings/i2c/i2c-imx-lpi2c.txt       |  1 -
 .../devicetree/bindings/i2c/i2c-jz4780.txt          |  4 ----
 Documentation/devicetree/bindings/i2c/i2c-mpc.txt   |  2 --
 .../devicetree/bindings/i2c/i2c-mux-pca954x.txt     |  2 --
 .../devicetree/bindings/i2c/i2c-pca-platform.txt    |  2 --
 Documentation/devicetree/bindings/i2c/i2c-pnx.txt   |  2 --
 Documentation/devicetree/bindings/i2c/i2c-pxa.txt   |  3 ---
 .../devicetree/bindings/iio/accel/adxl345.txt       |  2 --
 .../devicetree/bindings/iio/accel/bma180.txt        |  2 --
 .../devicetree/bindings/iio/accel/mma8452.txt       |  2 --
 .../devicetree/bindings/iio/adc/cpcap-adc.txt       |  1 -
 .../devicetree/bindings/iio/adc/fsl,imx25-gcq.txt   |  1 -
 .../devicetree/bindings/iio/adc/max1027-adc.txt     |  2 --
 .../devicetree/bindings/iio/adc/st,stm32-adc.txt    |  1 -
 .../devicetree/bindings/iio/adc/xilinx-xadc.txt     |  1 -
 .../bindings/iio/chemical/atlas,ec-sm.txt           |  1 -
 .../bindings/iio/chemical/atlas,orp-sm.txt          |  1 -
 .../bindings/iio/chemical/atlas,ph-sm.txt           |  1 -
 .../bindings/iio/gyroscope/invensense,mpu3050.txt   |  1 -
 .../devicetree/bindings/iio/health/afe4403.txt      |  1 -
 .../devicetree/bindings/iio/health/afe4404.txt      |  1 -
 .../devicetree/bindings/iio/health/max30100.txt     |  1 -
 .../devicetree/bindings/iio/health/max30102.txt     |  1 -
 .../devicetree/bindings/iio/humidity/hts221.txt     |  1 -
 .../devicetree/bindings/iio/imu/bmi160.txt          |  1 -
 .../devicetree/bindings/iio/imu/inv_mpu6050.txt     |  1 -
 .../devicetree/bindings/iio/imu/st_lsm6dsx.txt      |  1 -
 .../devicetree/bindings/iio/light/apds9300.txt      |  1 -
 .../devicetree/bindings/iio/light/apds9960.txt      |  1 -
 .../devicetree/bindings/iio/light/isl29018.txt      |  1 -
 .../devicetree/bindings/iio/light/opt3001.txt       |  1 -
 .../devicetree/bindings/iio/light/tsl2583.txt       |  1 -
 .../devicetree/bindings/iio/light/uvis25.txt        |  1 -
 .../bindings/iio/magnetometer/bmc150_magn.txt       |  1 -
 .../devicetree/bindings/iio/pressure/bmp085.txt     |  1 -
 .../devicetree/bindings/iio/pressure/zpa2326.txt    |  2 --
 .../devicetree/bindings/iio/proximity/as3935.txt    |  1 -
 .../devicetree/bindings/iio/proximity/sx9500.txt    |  1 -
 Documentation/devicetree/bindings/iio/sensorhub.txt |  1 -
 .../devicetree/bindings/iio/temperature/tmp007.txt  |  2 --
 .../bindings/infiniband/hisilicon-hns-roce.txt      |  1 -
 .../devicetree/bindings/input/cypress,cyapa.txt     |  2 --
 .../bindings/input/cypress,tm2-touchkey.txt         |  2 --
 .../devicetree/bindings/input/e3x0-button.txt       |  2 --
 .../devicetree/bindings/input/elan_i2c.txt          |  2 --
 .../devicetree/bindings/input/elants_i2c.txt        |  2 --
 .../devicetree/bindings/input/hid-over-i2c.txt      |  1 -
 .../devicetree/bindings/input/raydium_i2c_ts.txt    |  1 -
 .../devicetree/bindings/input/rmi4/rmi_i2c.txt      |  1 -
 .../devicetree/bindings/input/rmi4/rmi_spi.txt      |  1 -
 .../bindings/input/ti,palmas-pwrbutton.txt          |  1 -
 .../bindings/input/touchscreen/ad7879.txt           |  1 -
 .../bindings/input/touchscreen/ads7846.txt          |  1 -
 .../bindings/input/touchscreen/ar1021.txt           |  1 -
 .../bindings/input/touchscreen/chipone_icn8318.txt  |  2 --
 .../bindings/input/touchscreen/colibri-vf50-ts.txt  |  1 -
 .../bindings/input/touchscreen/cyttsp.txt           |  2 --
 .../bindings/input/touchscreen/edt-ft5x06.txt       |  2 --
 .../bindings/input/touchscreen/egalax-ts.txt        |  1 -
 .../bindings/input/touchscreen/ektf2127.txt         |  2 --
 .../bindings/input/touchscreen/exc3000.txt          |  1 -
 .../bindings/input/touchscreen/fsl-mx25-tcq.txt     |  1 -
 .../bindings/input/touchscreen/goodix.txt           |  1 -
 .../bindings/input/touchscreen/hideep.txt           |  1 -
 .../bindings/input/touchscreen/max11801-ts.txt      |  1 -
 .../bindings/input/touchscreen/melfas_mip4.txt      |  1 -
 .../bindings/input/touchscreen/samsung,s6sy761.txt  |  2 --
 .../bindings/input/touchscreen/silead_gsl1680.txt   |  2 --
 .../bindings/input/touchscreen/sis_i2c.txt          |  2 --
 .../bindings/input/touchscreen/st,stmfts.txt        |  2 --
 .../bindings/input/touchscreen/sx8654.txt           |  1 -
 .../bindings/input/touchscreen/tsc2007.txt          |  2 --
 .../bindings/input/touchscreen/zet6223.txt          |  2 --
 .../interrupt-controller/abilis,tb10x-ictl.txt      |  1 -
 .../interrupt-controller/al,alpine-msix.txt         |  1 -
 .../interrupt-controller/allwinner,sunxi-nmi.txt    |  1 -
 .../amlogic,meson-gpio-intc.txt                     |  3 ---
 .../bindings/interrupt-controller/atmel,aic.txt     |  2 --
 .../brcm,bcm2835-armctrl-ic.txt                     |  2 --
 .../interrupt-controller/brcm,bcm3380-l2-intc.txt   |  2 --
 .../interrupt-controller/brcm,bcm6345-l1-intc.txt   |  2 --
 .../interrupt-controller/brcm,bcm7038-l1-intc.txt   |  2 --
 .../interrupt-controller/brcm,bcm7120-l2-intc.txt   |  2 --
 .../bindings/interrupt-controller/brcm,l2-intc.txt  |  2 --
 .../interrupt-controller/fsl,ls-scfg-msi.txt        |  3 ---
 .../interrupt-controller/hisilicon,mbigen-v2.txt    |  2 --
 .../bindings/interrupt-controller/ingenic,intc.txt  |  1 -
 .../marvell,odmi-controller.txt                     |  2 --
 .../bindings/interrupt-controller/mediatek,cirq.txt |  2 --
 .../interrupt-controller/mediatek,sysirq.txt        |  2 --
 .../interrupt-controller/mscc,ocelot-icpu-intr.txt  |  1 -
 .../interrupt-controller/nvidia,tegra20-ictlr.txt   |  2 --
 .../interrupt-controller/nxp,lpc3220-mic.txt        |  2 --
 .../interrupt-controller/qca,ath79-misc-intc.txt    |  1 -
 .../bindings/interrupt-controller/qcom,pdc.txt      |  6 ------
 .../samsung,exynos4210-combiner.txt                 |  2 --
 .../interrupt-controller/sigma,smp8642-intc.txt     |  1 -
 .../interrupt-controller/snps,archs-idu-intc.txt    |  1 -
 .../interrupt-controller/snps,dw-apb-ictl.txt       |  1 -
 .../socionext,synquacer-exiu.txt                    |  1 -
 .../interrupt-controller/st,spear3xx-shirq.txt      |  4 ----
 .../interrupt-controller/technologic,ts4800.txt     |  2 --
 .../interrupt-controller/ti,c64x+megamod-pic.txt    |  1 -
 .../interrupt-controller/ti,omap4-wugen-mpu         |  2 --
 .../devicetree/bindings/iommu/samsung,sysmmu.txt    |  1 -
 .../devicetree/bindings/mailbox/altera-mailbox.txt  |  1 -
 .../devicetree/bindings/media/i2c/tc358743.txt      |  2 +-
 .../devicetree/bindings/media/sh_mobile_ceu.txt     |  1 -
 Documentation/devicetree/bindings/mfd/ac100.txt     |  4 ----
 .../devicetree/bindings/mfd/altera-a10sr.txt        |  1 -
 Documentation/devicetree/bindings/mfd/arizona.txt   |  1 -
 Documentation/devicetree/bindings/mfd/axp20x.txt    |  1 -
 Documentation/devicetree/bindings/mfd/bd9571mwv.txt |  1 -
 Documentation/devicetree/bindings/mfd/bfticu.txt    |  1 -
 Documentation/devicetree/bindings/mfd/da9055.txt    |  2 --
 Documentation/devicetree/bindings/mfd/da9062.txt    |  2 --
 Documentation/devicetree/bindings/mfd/da9063.txt    |  2 --
 Documentation/devicetree/bindings/mfd/da9150.txt    |  2 --
 Documentation/devicetree/bindings/mfd/max14577.txt  |  1 -
 Documentation/devicetree/bindings/mfd/max77686.txt  |  1 -
 Documentation/devicetree/bindings/mfd/max77693.txt  |  1 -
 Documentation/devicetree/bindings/mfd/max77802.txt  |  1 -
 Documentation/devicetree/bindings/mfd/max8998.txt   |  2 --
 .../devicetree/bindings/mfd/motorola-cpcap.txt      |  1 -
 Documentation/devicetree/bindings/mfd/palmas.txt    |  1 -
 Documentation/devicetree/bindings/mfd/retu.txt      |  1 -
 Documentation/devicetree/bindings/mfd/rk808.txt     |  1 -
 .../devicetree/bindings/mfd/samsung,sec-core.txt    |  2 --
 Documentation/devicetree/bindings/mfd/stmpe.txt     |  1 -
 Documentation/devicetree/bindings/mfd/tc3589x.txt   |  1 -
 Documentation/devicetree/bindings/mfd/tps65086.txt  |  1 -
 Documentation/devicetree/bindings/mfd/tps65912.txt  |  1 -
 .../devicetree/bindings/mfd/twl-familly.txt         |  1 -
 Documentation/devicetree/bindings/mfd/twl6040.txt   |  1 -
 Documentation/devicetree/bindings/mfd/wm831x.txt    |  1 -
 .../devicetree/bindings/mips/cavium/cib.txt         |  2 --
 .../devicetree/bindings/mmc/arasan,sdhci.txt        |  2 --
 Documentation/devicetree/bindings/mmc/fsl-esdhc.txt |  1 -
 .../devicetree/bindings/mmc/mmc-spi-slot.txt        |  2 --
 .../devicetree/bindings/mtd/brcm,brcmnand.txt       |  1 -
 Documentation/devicetree/bindings/mtd/gpmc-nand.txt |  1 -
 Documentation/devicetree/bindings/mtd/spear_smi.txt |  2 --
 Documentation/devicetree/bindings/net/amd-xgbe.txt  |  2 --
 Documentation/devicetree/bindings/net/btusb.txt     |  1 -
 .../devicetree/bindings/net/can/holt_hi311x.txt     |  1 -
 .../bindings/net/can/microchip,mcp251x.txt          |  1 -
 .../devicetree/bindings/net/can/xilinx_can.txt      |  1 -
 Documentation/devicetree/bindings/net/cpsw.txt      |  1 -
 .../devicetree/bindings/net/davicom-dm9000.txt      |  1 -
 .../devicetree/bindings/net/dsa/marvell.txt         |  1 -
 .../devicetree/bindings/net/hisilicon-hns-dsaf.txt  |  1 -
 Documentation/devicetree/bindings/net/ibm,emac.txt  |  1 -
 .../devicetree/bindings/net/marvell-bt-8xxx.txt     |  1 -
 .../devicetree/bindings/net/mediatek,mt7620-gsw.txt |  2 --
 .../devicetree/bindings/net/mediatek-net.txt        |  3 ---
 .../devicetree/bindings/net/microchip,enc28j60.txt  |  3 ---
 .../devicetree/bindings/net/nfc/nxp-nci.txt         |  1 -
 .../devicetree/bindings/net/nfc/pn533-i2c.txt       |  1 -
 Documentation/devicetree/bindings/net/nfc/pn544.txt |  1 -
 .../devicetree/bindings/net/nfc/s3fwrn5.txt         |  1 -
 .../devicetree/bindings/net/nfc/st-nci-i2c.txt      |  1 -
 .../devicetree/bindings/net/nfc/st-nci-spi.txt      |  1 -
 .../devicetree/bindings/net/nfc/st21nfca.txt        |  2 --
 .../devicetree/bindings/net/nfc/st95hf.txt          |  3 ---
 .../devicetree/bindings/net/nfc/trf7970a.txt        |  1 -
 Documentation/devicetree/bindings/net/phy.txt       |  2 --
 .../devicetree/bindings/net/qca,qca7000.txt         |  1 -
 .../devicetree/bindings/net/ralink,rt2880-net.txt   |  2 --
 .../devicetree/bindings/net/ralink,rt3050-esw.txt   |  2 --
 .../devicetree/bindings/net/renesas,ravb.txt        |  2 --
 .../devicetree/bindings/net/samsung-sxgbe.txt       |  2 --
 Documentation/devicetree/bindings/net/sh_eth.txt    |  2 --
 .../bindings/net/snps,dwc-qos-ethernet.txt          |  2 --
 Documentation/devicetree/bindings/net/stmmac.txt    |  2 --
 .../bindings/net/wireless/brcm,bcm43xx-fmac.txt     |  2 --
 .../bindings/net/wireless/marvell-8xxx.txt          |  1 -
 .../devicetree/bindings/net/wireless/ti,wl1251.txt  |  2 --
 .../bindings/net/wireless/ti,wlcore,spi.txt         |  4 +---
 .../devicetree/bindings/net/wireless/ti,wlcore.txt  |  2 --
 .../devicetree/bindings/pci/altera-pcie-msi.txt     |  1 -
 .../devicetree/bindings/pci/altera-pcie.txt         |  1 -
 .../devicetree/bindings/pci/brcm,iproc-pcie.txt     |  1 -
 .../devicetree/bindings/pci/faraday,ftpci100.txt    |  1 -
 .../devicetree/bindings/pci/mobiveil-pcie.txt       |  3 ---
 .../devicetree/bindings/pci/pci-keystone.txt        |  3 ---
 .../devicetree/bindings/pci/ralink,rt3883-pci.txt   |  3 ---
 .../devicetree/bindings/pinctrl/pinctrl-mt7622.txt  |  2 --
 .../devicetree/bindings/pinctrl/pinctrl-sx150x.txt  |  2 --
 .../devicetree/bindings/pinctrl/samsung-pinctrl.txt |  6 ------
 .../bindings/pinctrl/st,stm32-pinctrl.txt           |  2 --
 .../bindings/power/supply/act8945a-charger.txt      |  2 --
 .../devicetree/bindings/power/supply/bq24257.txt    |  2 --
 .../bindings/power/supply/lp8727_charger.txt        |  1 -
 .../bindings/power/supply/maxim,max14656.txt        |  1 -
 .../bindings/power/supply/rt9455_charger.txt        |  2 --
 .../bindings/power/supply/sbs_sbs-charger.txt       |  2 --
 .../devicetree/bindings/powerpc/4xx/akebono.txt     |  2 --
 .../devicetree/bindings/powerpc/4xx/hsta.txt        |  1 -
 .../bindings/powerpc/4xx/ppc440spe-adma.txt         |  2 --
 .../devicetree/bindings/powerpc/fsl/dcsr.txt        |  7 -------
 .../devicetree/bindings/powerpc/fsl/diu.txt         |  2 --
 .../devicetree/bindings/powerpc/fsl/dma.txt         |  4 ----
 .../devicetree/bindings/powerpc/fsl/ecm.txt         |  4 ----
 .../devicetree/bindings/powerpc/fsl/mcm.txt         |  4 ----
 .../devicetree/bindings/powerpc/fsl/mpc5121-psc.txt |  4 ----
 .../devicetree/bindings/powerpc/fsl/msi-pic.txt     |  5 -----
 .../devicetree/bindings/powerpc/fsl/pamu.txt        |  2 --
 .../devicetree/bindings/powerpc/nintendo/wii.txt    |  1 -
 .../bindings/regulator/max8997-regulator.txt        |  2 --
 .../devicetree/bindings/regulator/palmas-pmic.txt   |  1 -
 .../bindings/remoteproc/ti,davinci-rproc.txt        |  6 ------
 .../bindings/remoteproc/ti,keystone-rproc.txt       |  6 ------
 .../bindings/rtc/brcm,brcmstb-waketimer.txt         |  2 --
 .../devicetree/bindings/rtc/isil,isl12057.txt       |  3 ---
 Documentation/devicetree/bindings/rtc/rtc-cmos.txt  |  1 -
 .../devicetree/bindings/rtc/rtc-ds1307.txt          |  1 -
 .../devicetree/bindings/rtc/rtc-m41t80.txt          |  1 -
 Documentation/devicetree/bindings/rtc/rtc-omap.txt  |  1 -
 .../devicetree/bindings/rtc/rtc-palmas.txt          |  1 -
 Documentation/devicetree/bindings/rtc/spear-rtc.txt |  2 --
 .../devicetree/bindings/rtc/sprd,sc27xx-rtc.txt     |  1 -
 .../devicetree/bindings/rtc/st,stm32-rtc.txt        |  2 --
 .../bindings/rtc/stericsson,coh901331.txt           |  1 -
 .../bindings/security/tpm/st33zp24-i2c.txt          |  1 -
 .../bindings/security/tpm/st33zp24-spi.txt          |  1 -
 .../bindings/security/tpm/tpm_tis_mmio.txt          |  2 +-
 .../devicetree/bindings/serial/maxim,max310x.txt    |  2 --
 .../devicetree/bindings/serial/nxp,sc16is7xx.txt    |  4 ----
 .../devicetree/bindings/serial/qca,ar9330-uart.txt  |  3 ---
 .../devicetree/bindings/soc/fsl/cpm_qe/gpio.txt     |  1 -
 .../devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt   |  2 --
 .../devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt   |  1 -
 Documentation/devicetree/bindings/sound/cs35l33.txt |  2 --
 Documentation/devicetree/bindings/sound/cs35l34.txt |  2 --
 Documentation/devicetree/bindings/sound/cs35l35.txt |  2 --
 Documentation/devicetree/bindings/sound/cs42l42.txt |  5 +----
 Documentation/devicetree/bindings/sound/da7218.txt  |  2 --
 Documentation/devicetree/bindings/sound/da7219.txt  |  2 --
 Documentation/devicetree/bindings/sound/fsl,ssi.txt |  2 --
 .../devicetree/bindings/sound/omap-dmic.txt         |  1 -
 .../devicetree/bindings/sound/omap-mcbsp.txt        |  1 -
 .../devicetree/bindings/sound/omap-mcpdm.txt        |  1 -
 .../bindings/sound/qcom,msm8916-wcd-analog.txt      |  1 -
 Documentation/devicetree/bindings/sound/rt5514.txt  |  1 -
 .../devicetree/bindings/sound/ts3a227e.txt          |  1 -
 .../devicetree/bindings/sound/ux500-msp.txt         |  1 -
 Documentation/devicetree/bindings/sound/wm8994.txt  |  1 -
 Documentation/devicetree/bindings/spi/fsl-spi.txt   |  2 --
 Documentation/devicetree/bindings/spi/sh-hspi.txt   |  2 --
 Documentation/devicetree/bindings/spi/sh-msiof.txt  |  2 --
 .../devicetree/bindings/spi/spi-cadence.txt         |  1 -
 .../devicetree/bindings/spi/spi-fsl-lpspi.txt       |  1 -
 Documentation/devicetree/bindings/spi/spi-rspi.txt  |  2 --
 .../devicetree/bindings/spi/spi-xilinx.txt          |  1 -
 Documentation/devicetree/bindings/spi/spi-xlp.txt   |  1 -
 .../devicetree/bindings/spi/spi-zynqmp-qspi.txt     |  1 -
 .../bindings/staging/iio/adc/spear-adc.txt          |  2 --
 .../devicetree/bindings/thermal/brcm,avs-tmon.txt   |  1 -
 .../devicetree/bindings/thermal/exynos-thermal.txt  |  1 -
 .../devicetree/bindings/timer/altr,timer-1.0.txt    |  1 -
 Documentation/devicetree/bindings/timer/fsl,gtm.txt |  1 -
 .../bindings/timer/marvell,orion-timer.txt          |  1 -
 .../devicetree/bindings/timer/snps,arc-timer.txt    |  4 ----
 .../devicetree/bindings/timer/st,spear-timer.txt    |  2 --
 .../devicetree/bindings/timer/ti,c64x+timer64.txt   |  1 -
 Documentation/devicetree/bindings/usb/fsl-usb.txt   |  2 --
 .../devicetree/bindings/usb/maxim,max3421.txt       |  3 ---
 .../devicetree/bindings/usb/richtek,rt1711h.txt     |  2 --
 .../devicetree/bindings/usb/samsung-hsotg.txt       |  2 --
 Documentation/devicetree/bindings/usb/spear-usb.txt |  4 ----
 .../devicetree/bindings/watchdog/cadence-wdt.txt    |  1 -
 .../devicetree/bindings/watchdog/rt2880-wdt.txt     |  1 -
 Documentation/devicetree/bindings/xilinx.txt        |  2 +-
 .../devicetree/bindings/xillybus/xillybus.txt       |  2 --
 332 files changed, 9 insertions(+), 588 deletions(-)

diff --git a/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt b/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt
index 669808b2af49..6dd6f399236d 100644
--- a/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt
+++ b/Documentation/devicetree/bindings/arm/freescale/fsl,vf610-mscm-ir.txt
@@ -18,9 +18,6 @@ Required properties:
 			assignment of the interrupt router is required.
 			Flags get passed only when using GIC as parent. Flags
 			encoding as documented by the GIC bindings.
-- interrupt-parent:	Should be the phandle for the interrupt controller of
-			the CPU the device tree is intended to be used on. This
-			is either the node of the GIC or NVIC controller.
 
 Example:
 	mscm_ir: interrupt-controller@40001800 {
diff --git a/Documentation/devicetree/bindings/arm/omap/crossbar.txt b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
index ecb360ed0e33..4cd5d873fc3a 100644
--- a/Documentation/devicetree/bindings/arm/omap/crossbar.txt
+++ b/Documentation/devicetree/bindings/arm/omap/crossbar.txt
@@ -10,7 +10,6 @@ Required properties:
 - compatible : Should be "ti,irq-crossbar"
 - reg: Base address and the size of the crossbar registers.
 - interrupt-controller: indicates that this block is an interrupt controller.
-- interrupt-parent: the interrupt controller this block is connected to.
 - ti,max-irqs: Total number of irqs available at the parent interrupt controller.
 - ti,max-crossbar-sources: Maximum number of crossbar sources that can be routed.
 - ti,reg-size: Size of a individual register in bytes. Every individual
diff --git a/Documentation/devicetree/bindings/arm/samsung/pmu.txt b/Documentation/devicetree/bindings/arm/samsung/pmu.txt
index 16685787d2bd..433bfd7593ac 100644
--- a/Documentation/devicetree/bindings/arm/samsung/pmu.txt
+++ b/Documentation/devicetree/bindings/arm/samsung/pmu.txt
@@ -40,9 +40,6 @@ following properties:
 - #interrupt-cells: must be identical to the that of the parent interrupt
   controller.
 
-- interrupt-parent: a phandle indicating which interrupt controller
-  this PMU signals interrupts to.
-
 
 Optional nodes:
 
diff --git a/Documentation/devicetree/bindings/ata/fsl-sata.txt b/Documentation/devicetree/bindings/ata/fsl-sata.txt
index b46bcf46c3d8..fd63bb3becc9 100644
--- a/Documentation/devicetree/bindings/ata/fsl-sata.txt
+++ b/Documentation/devicetree/bindings/ata/fsl-sata.txt
@@ -16,7 +16,6 @@ Required properties:
                           4 for controller @ 0x1b000
 
 Optional properties:
-- interrupt-parent  : optional, if needed for interrupt mapping
 - reg               : <registers mapping>
 
 Example:
diff --git a/Documentation/devicetree/bindings/ata/pata-arasan.txt b/Documentation/devicetree/bindings/ata/pata-arasan.txt
index 2aff154be84e..872edc105680 100644
--- a/Documentation/devicetree/bindings/ata/pata-arasan.txt
+++ b/Documentation/devicetree/bindings/ata/pata-arasan.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: "arasan,cf-spear1340"
 - reg: Address range of the CF registers
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupt: Should contain the CF interrupt number
 - clock-frequency: Interface clock rate, in Hz, one of
        25000000
diff --git a/Documentation/devicetree/bindings/board/fsl-board.txt b/Documentation/devicetree/bindings/board/fsl-board.txt
index fb7b03ec2071..eb52f6b35159 100644
--- a/Documentation/devicetree/bindings/board/fsl-board.txt
+++ b/Documentation/devicetree/bindings/board/fsl-board.txt
@@ -29,7 +29,6 @@ Required properties:
 - reg: should contain the address and the length of the FPGA register set.
 
 Optional properties:
-- interrupt-parent: should specify phandle for the interrupt controller.
 - interrupts: should specify event (wakeup) IRQ.
 
 Example (P1022DS):
diff --git a/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt b/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt
index 8a6c3c2e58fe..729def62f0c5 100644
--- a/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt
+++ b/Documentation/devicetree/bindings/bus/brcm,gisb-arb.txt
@@ -9,8 +9,6 @@ Required properties:
     "brcm,bcm7400-gisb-arb" for older 40nm chips and all 65nm chips
     "brcm,bcm7038-gisb-arb" for 130nm chips
 - reg: specifies the base physical address and size of the registers
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this arbiter gets interrupt line from
 - interrupts: specifies the two interrupts (timeout and TEA) to be used from
   the parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/clock/at91-clock.txt b/Documentation/devicetree/bindings/clock/at91-clock.txt
index 51c259a92d02..33fe9591e904 100644
--- a/Documentation/devicetree/bindings/clock/at91-clock.txt
+++ b/Documentation/devicetree/bindings/clock/at91-clock.txt
@@ -180,7 +180,6 @@ For example:
 	};
 
 Required properties for main clock internal RC oscillator:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<0>".
 - clock-frequency : define the internal RC oscillator frequency.
 
@@ -197,7 +196,6 @@ For example:
 	};
 
 Required properties for main clock oscillator:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<0>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall encode the main osc source clk sources (see atmel datasheet).
@@ -218,7 +216,6 @@ For example:
 	};
 
 Required properties for main clock:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<0>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall encode the main clk sources (see atmel datasheet).
@@ -233,7 +230,6 @@ For example:
 	};
 
 Required properties for master clock:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<3>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall be the master clock sources (see atmel datasheet) phandles.
@@ -292,7 +288,6 @@ For example:
 
 
 Required properties for pll clocks:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<1>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall be the main clock phandle.
@@ -348,7 +343,6 @@ For example:
 	};
 
 Required properties for programmable clocks:
-- interrupt-parent : must reference the PMC node.
 - #size-cells : shall be 0 (reg is used to encode clk id).
 - #address-cells : shall be 1 (reg is used to encode clk id).
 - clocks : shall be the programmable clock source phandles.
@@ -451,7 +445,6 @@ For example:
 
 
 Required properties for utmi clock:
-- interrupt-parent : must reference the PMC node.
 - interrupts : shall be set to "<AT91_PMC_LOCKU IRQ_TYPE_LEVEL_HIGH>".
 - #clock-cells : from common clock binding; shall be set to 0.
 - clocks : shall be the main clock source phandle.
diff --git a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt
index af2385795d78..73470ecd1f12 100644
--- a/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt
+++ b/Documentation/devicetree/bindings/cpufreq/brcm,stb-avs-cpu-freq.txt
@@ -29,8 +29,6 @@ Required properties:
 - reg: Specifies base physical address and size of the registers.
 - interrupts: The interrupt that the AVS CPU will use to interrupt the host
               when a command completed.
-- interrupt-parent: The interrupt controller the above interrupt is routed
-                    through.
 - interrupt-names: The name of the interrupt used to interrupt the host.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/crypto/amd-ccp.txt b/Documentation/devicetree/bindings/crypto/amd-ccp.txt
index 8c61183b41e0..d87579d63da6 100644
--- a/Documentation/devicetree/bindings/crypto/amd-ccp.txt
+++ b/Documentation/devicetree/bindings/crypto/amd-ccp.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: Should be "amd,ccp-seattle-v1a"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the CCP interrupt
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
index c2598ab27f2e..999fb2a810f6 100644
--- a/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
+++ b/Documentation/devicetree/bindings/crypto/arm-cryptocell.txt
@@ -7,8 +7,6 @@ Required properties:
 - interrupts: Interrupt number for the device.
 
 Optional properties:
-- interrupt-parent: The phandle for the interrupt controller that services
-  interrupts for this device.
 - clocks: Reference to the crypto engine clock.
 - dma-coherent: Present if dma operations are coherent.
 
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
index f0d926bf9f36..125f155d00d0 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec2.txt
@@ -50,11 +50,6 @@ remaining bits are reserved for future SEC EUs.
 
   ..and so on and so forth.
 
-Optional properties:
-
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
-
 Example:
 
 	/* MPC8548E */
diff --git a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
index 3c1f3a229eab..2fe245ca816a 100644
--- a/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
+++ b/Documentation/devicetree/bindings/crypto/fsl-sec4.txt
@@ -99,13 +99,6 @@ PROPERTIES
            of the specifier is defined by the binding document
            describing the node's interrupt parent.
 
-   - interrupt-parent
-      Usage: (required if interrupt property is defined)
-      Value type: <phandle>
-      Definition: A single <phandle> value that points
-          to the interrupt parent to which the child domain
-          is being mapped.
-
    - clocks
       Usage: required if SEC 4.0 requires explicit enablement of clocks
       Value type: <prop_encoded-array>
@@ -199,13 +192,6 @@ Job Ring (JR) Node
            of the specifier is defined by the binding document
            describing the node's interrupt parent.
 
-   - interrupt-parent
-      Usage: (required if interrupt property is defined)
-      Value type: <phandle>
-      Definition: A single <phandle> value that points
-          to the interrupt parent to which the child domain
-          is being mapped.
-
 EXAMPLE
 	jr@1000 {
 		compatible = "fsl,sec-v4.0-job-ring";
@@ -370,13 +356,6 @@ Secure Non-Volatile Storage (SNVS) Node
            of the specifier is defined by the binding document
            describing the node's interrupt parent.
 
-   - interrupt-parent
-      Usage: (required if interrupt property is defined)
-      Value type: <phandle>
-      Definition: A single <phandle> value that points
-          to the interrupt parent to which the child domain
-          is being mapped.
-
 EXAMPLE
 	sec_mon@314000 {
 		compatible = "fsl,sec-v4.0-mon", "syscon";
diff --git a/Documentation/devicetree/bindings/crypto/picochip-spacc.txt b/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
index d8609ece1f4c..df1151f87745 100644
--- a/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
+++ b/Documentation/devicetree/bindings/crypto/picochip-spacc.txt
@@ -7,8 +7,6 @@ Required properties:
   - compatible : "picochip,spacc-ipsec" for the IPSEC offload engine
     "picochip,spacc-l2" for the femtocell layer 2 ciphering engine.
   - reg : Offset and length of the register set for this device
-  - interrupt-parent : The interrupt controller that controls the SPAcc
-    interrupt.
   - interrupts : The interrupt line from the SPAcc.
   - ref-clock : The input clock that drives the SPAcc.
 
diff --git a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
index 0c7473dd0e51..027d76c27a41 100644
--- a/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
+++ b/Documentation/devicetree/bindings/display/bridge/analogix_dp.txt
@@ -15,8 +15,6 @@ Required properties for dp-controller:
 		from common clock binding: handle to dp clock.
 	-clock-names:
 		from common clock binding: Shall be "dp".
-	-interrupt-parent:
-		phandle to Interrupt combiner node.
 	-phys:
 		from general PHY binding: the phandle for the PHY device.
 	-phy-names:
diff --git a/Documentation/devicetree/bindings/display/bridge/anx7814.txt b/Documentation/devicetree/bindings/display/bridge/anx7814.txt
index b2a22c28c9b3..dbd7c84ee584 100644
--- a/Documentation/devicetree/bindings/display/bridge/anx7814.txt
+++ b/Documentation/devicetree/bindings/display/bridge/anx7814.txt
@@ -8,8 +8,6 @@ Required properties:
 
  - compatible		: "analogix,anx7814"
  - reg			: I2C address of the device
- - interrupt-parent	: Should be the phandle of the interrupt controller
-			  that services interrupts for this device
  - interrupts		: Should contain the INTP interrupt
  - hpd-gpios		: Which GPIO to use for hpd
  - pd-gpios		: Which GPIO to use for power down
diff --git a/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt b/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
index aacc8b92968c..09e0a21f705e 100644
--- a/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
+++ b/Documentation/devicetree/bindings/display/bridge/megachips-stdpxxxx-ge-b850v3-fw.txt
@@ -19,8 +19,6 @@ hardware are EDID, HPD, and interrupts.
 stdp4028-ge-b850v3-fw required properties:
   - compatible : "megachips,stdp4028-ge-b850v3-fw"
   - reg : I2C bus address
-  - interrupt-parent : phandle of the interrupt controller that services
-    interrupts to the device
   - interrupts : one interrupt should be described here, as in
     <0 IRQ_TYPE_LEVEL_HIGH>
   - ports : One input port(reg = <0>) and one output port(reg = <1>)
diff --git a/Documentation/devicetree/bindings/display/bridge/sii902x.txt b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
index 56a3e68ccb80..72d2dc6c3e6b 100644
--- a/Documentation/devicetree/bindings/display/bridge/sii902x.txt
+++ b/Documentation/devicetree/bindings/display/bridge/sii902x.txt
@@ -5,8 +5,8 @@ Required properties:
 	- reg: i2c address of the bridge
 
 Optional properties:
-	- interrupts-extended or interrupt-parent + interrupts: describe
-	  the interrupt line used to inform the host about hotplug events.
+	- interrupts: describe the interrupt line used to inform the host 
+	  about hotplug events.
 	- reset-gpios: OF device-tree gpio specification for RST_N pin.
 
 Optional subnodes:
diff --git a/Documentation/devicetree/bindings/display/bridge/sii9234.txt b/Documentation/devicetree/bindings/display/bridge/sii9234.txt
index 88041ba23d56..a55bf77bd960 100644
--- a/Documentation/devicetree/bindings/display/bridge/sii9234.txt
+++ b/Documentation/devicetree/bindings/display/bridge/sii9234.txt
@@ -7,7 +7,7 @@ Required properties:
 	- iovcc18-supply : I/O Supply Voltage (1.8V)
 	- avcc12-supply : TMDS Analog Supply Voltage (1.2V)
 	- cvcc12-supply : Digital Core Supply Voltage (1.2V)
-	- interrupts, interrupt-parent: interrupt specifier of INT pin
+	- interrupts: interrupt specifier of INT pin
 	- reset-gpios: gpio specifier of RESET pin (active low)
 	- video interfaces: Device node can contain two video interface port
 			    nodes for HDMI encoder and connector according to [1].
diff --git a/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt b/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt
index 9409d9c6a260..b05052f7d62f 100644
--- a/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt
+++ b/Documentation/devicetree/bindings/display/bridge/sil-sii8620.txt
@@ -5,7 +5,7 @@ Required properties:
 	- reg: i2c address of the bridge
 	- cvcc10-supply: Digital Core Supply Voltage (1.0V)
 	- iovcc18-supply: I/O Supply Voltage (1.8V)
-	- interrupts, interrupt-parent: interrupt specifier of INT pin
+	- interrupts: interrupt specifier of INT pin
 	- reset-gpios: gpio specifier of RESET pin
 	- clocks, clock-names: specification and name of "xtal" clock
 	- video interfaces: Device node can contain video interface port
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt b/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt
index 9e2e7f6f7609..53912c99ec38 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos7-decon.txt
@@ -9,9 +9,6 @@ Required properties:
 
 - reg: physical base address and length of the DECON registers set.
 
-- interrupt-parent: should be the phandle of the decon controller's
-		parent interrupt controller.
-
 - interrupts: should contain a list of all DECON IP block interrupts in the
 		 order: FIFO Level, VSYNC, LCD_SYSTEM. The interrupt specifier
 		 format depends on the interrupt controller used.
diff --git a/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt b/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
index ade5d8eebf85..9b6cba3f82af 100644
--- a/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
+++ b/Documentation/devicetree/bindings/display/exynos/exynos_dp.txt
@@ -25,8 +25,6 @@ Required properties for dp-controller:
 		from common clock binding: handle to dp clock.
 	-clock-names:
 		from common clock binding: Shall be "dp".
-	-interrupt-parent:
-		phandle to Interrupt combiner node.
 	-phys:
 		from general PHY binding: the phandle for the PHY device.
 	-phy-names:
diff --git a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
index 5837402c3ade..b3096421d42b 100644
--- a/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
+++ b/Documentation/devicetree/bindings/display/exynos/samsung-fimd.txt
@@ -16,9 +16,6 @@ Required properties:
 
 - reg: physical base address and length of the FIMD registers set.
 
-- interrupt-parent: should be the phandle of the fimd controller's
-		parent interrupt controller.
-
 - interrupts: should contain a list of all FIMD IP block interrupts in the
 		 order: FIFO Level, VSYNC, LCD_SYSTEM. The interrupt specifier
 		 format depends on the interrupt controller used.
diff --git a/Documentation/devicetree/bindings/display/ht16k33.txt b/Documentation/devicetree/bindings/display/ht16k33.txt
index 8e5b30b87754..d5a8b070b467 100644
--- a/Documentation/devicetree/bindings/display/ht16k33.txt
+++ b/Documentation/devicetree/bindings/display/ht16k33.txt
@@ -4,8 +4,6 @@ Holtek ht16k33 RAM mapping 16*8 LED controller driver with keyscan
 Required properties:
 - compatible:		"holtek,ht16k33"
 - reg:			I2C slave address of the chip.
-- interrupt-parent:	A phandle pointing to the interrupt controller
-			serving the interrupt for this chip.
 - interrupts:		Interrupt specification for the key pressed interrupt.
 - refresh-rate-hz:	Display update interval in HZ.
 - debounce-delay-ms:	Debouncing interval time in milliseconds.
diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt
index 518e9cdf0d4b..5eaffca2e28c 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi.txt
+++ b/Documentation/devicetree/bindings/display/msm/dsi.txt
@@ -43,8 +43,6 @@ Optional properties:
   the master link of the 2-DSI panel.
 - qcom,sync-dual-dsi: Boolean value indicating if the DSI controller is
   driving a 2-DSI panel whose 2 links need receive command simultaneously.
-- interrupt-parent: phandle to the MDP block if the interrupt signal is routed
-  through MDP block
 - pinctrl-names: the pin control state names; should contain "default"
 - pinctrl-0: the default pinctrl state (active)
 - pinctrl-n: the "sleep" pinctrl state
diff --git a/Documentation/devicetree/bindings/display/msm/edp.txt b/Documentation/devicetree/bindings/display/msm/edp.txt
index 95ce19ca7bc5..eff9daff418c 100644
--- a/Documentation/devicetree/bindings/display/msm/edp.txt
+++ b/Documentation/devicetree/bindings/display/msm/edp.txt
@@ -25,10 +25,6 @@ Required properties:
 - panel-hpd-gpios: GPIO pin used for eDP hpd.
 
 
-Optional properties:
-- interrupt-parent: phandle to the MDP block if the interrupt signal is routed
-  through MDP block
-
 Example:
 	mdss_edp: qcom,mdss_edp@fd923400 {
 			compatible = "qcom,mdss-edp";
diff --git a/Documentation/devicetree/bindings/display/msm/mdp5.txt b/Documentation/devicetree/bindings/display/msm/mdp5.txt
index 1b31977a68ba..4e11338548aa 100644
--- a/Documentation/devicetree/bindings/display/msm/mdp5.txt
+++ b/Documentation/devicetree/bindings/display/msm/mdp5.txt
@@ -41,8 +41,6 @@ Required properties:
 - reg-names: The names of register regions. The following regions are required:
   * "mdp_phys"
 - interrupts: Interrupt line from MDP5 to MDSS interrupt controller.
-- interrupt-parent: phandle to the MDSS block
-  through MDP block
 - clocks: device clocks. See ../clocks/clock-bindings.txt for details.
 - clock-names: the following clocks are required.
 -   * "bus"
diff --git a/Documentation/devicetree/bindings/display/renesas,du.txt b/Documentation/devicetree/bindings/display/renesas,du.txt
index 7c6854bd0a04..ec9d34be2ff7 100644
--- a/Documentation/devicetree/bindings/display/renesas,du.txt
+++ b/Documentation/devicetree/bindings/display/renesas,du.txt
@@ -19,7 +19,6 @@ Required Properties:
 
   - reg: the memory-mapped I/O registers base address and length
 
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifiers for the DU interrupts.
 
   - clocks: A list of phandles + clock-specifier pairs, one for each entry in
diff --git a/Documentation/devicetree/bindings/display/sm501fb.txt b/Documentation/devicetree/bindings/display/sm501fb.txt
index 9d9f0098092b..1c79c267a57f 100644
--- a/Documentation/devicetree/bindings/display/sm501fb.txt
+++ b/Documentation/devicetree/bindings/display/sm501fb.txt
@@ -9,8 +9,6 @@ Required properties:
     - First entry: System Configuration register
     - Second entry: IO space (Display Controller register)
 - interrupts : SMI interrupt to the cpu should be described here.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 
 Optional properties:
 - mode : select a video mode:
diff --git a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
index 3055d5c2c04e..7bf1bb444812 100644
--- a/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
+++ b/Documentation/devicetree/bindings/display/tilcdc/tilcdc.txt
@@ -8,8 +8,6 @@ Required properties:
  - reg: base address and size of the LCDC device
 
 Recommended properties:
- - interrupt-parent: the phandle for the interrupt controller that
-   services interrupts for this device.
  - ti,hwmods: Name of the hwmod associated to the LCDC
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/dma/jz4780-dma.txt b/Documentation/devicetree/bindings/dma/jz4780-dma.txt
index f25feee62b15..03e9cf7b42e0 100644
--- a/Documentation/devicetree/bindings/dma/jz4780-dma.txt
+++ b/Documentation/devicetree/bindings/dma/jz4780-dma.txt
@@ -5,7 +5,6 @@ Required properties:
 - compatible: Should be "ingenic,jz4780-dma"
 - reg: Should contain the DMA controller registers location and length.
 - interrupts: Should contain the interrupt specifier of the DMA controller.
-- interrupt-parent: Should be the phandle of the interrupt controller that
 - clocks: Should contain a clock specifier for the JZ4780 PDMA clock.
 - #dma-cells: Must be <2>. Number of integer cells in the dmas property of
   DMA clients (see below).
diff --git a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt
index 1e1dc8f972e4..2f35b047f772 100644
--- a/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt
+++ b/Documentation/devicetree/bindings/dma/nvidia,tegra210-adma.txt
@@ -8,7 +8,6 @@ Required properties:
 - reg: Should contain DMA registers location and length. This should be
   a single entry that includes all of the per-channel registers in one
   contiguous bank.
-- interrupt-parent: Phandle to the interrupt parent controller.
 - interrupts: Should contain all of the per-channel DMA interrupts in
   ascending order with respect to the DMA channel index.
 - clocks: Must contain one entry for the ADMA module clock
diff --git a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt
index f237b7928283..dbe160400adc 100644
--- a/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt
+++ b/Documentation/devicetree/bindings/dma/snps,dw-axi-dmac.txt
@@ -5,8 +5,6 @@ Required properties:
 - reg: Address range of the DMAC registers. This should include
   all of the per-channel registers.
 - interrupt: Should contain the DMAC interrupt number.
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device.
 - dma-channels: Number of channels supported by hardware.
 - snps,dma-masters: Number of AXI masters supported by the hardware.
 - snps,data-width: Maximum AXI data width supported by hardware.
diff --git a/Documentation/devicetree/bindings/dma/snps-dma.txt b/Documentation/devicetree/bindings/dma/snps-dma.txt
index 99acc712f83a..39e2b26be344 100644
--- a/Documentation/devicetree/bindings/dma/snps-dma.txt
+++ b/Documentation/devicetree/bindings/dma/snps-dma.txt
@@ -23,8 +23,6 @@ Deprecated properties:
 
 
 Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - is_private: The device channels should be marked as private and not for by the
   general purpose DMA channel allocator. False if not passed.
 - multi-block: Multi block transfers supported by hardware. Array property with
diff --git a/Documentation/devicetree/bindings/dma/ti-edma.txt b/Documentation/devicetree/bindings/dma/ti-edma.txt
index 3f15f6644527..4bbc94d829c8 100644
--- a/Documentation/devicetree/bindings/dma/ti-edma.txt
+++ b/Documentation/devicetree/bindings/dma/ti-edma.txt
@@ -201,7 +201,6 @@ Required properties:
 - #dma-cells: Should be set to <1>
               Clients should use a single channel number per DMA request.
 - reg: Memory map for accessing module
-- interrupt-parent: Interrupt controller the interrupt is routed through
 - interrupts: Exactly 3 interrupts need to be specified in the order:
               1. Transfer completion interrupt.
               2. Memory protection interrupt.
diff --git a/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt b/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt
index a784cdd94790..07a5a7aa9ea0 100644
--- a/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt
+++ b/Documentation/devicetree/bindings/dma/xilinx/zynqmp_dma.txt
@@ -5,7 +5,6 @@ control and rate control support for slave/peripheral dma access.
 Required properties:
 - compatible		: Should be "xlnx,zynqmp-dma-1.0"
 - reg			: Memory map for gdma/adma module access.
-- interrupt-parent	: Interrupt controller the interrupt is routed through
 - interrupts		: Should contain DMA channel interrupt.
 - xlnx,bus-width	: Axi buswidth in bits. Should contain 128 or 64
 - clock-names		: List of input clocks "clk_main", "clk_apb"
diff --git a/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt b/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt
index 6dede7d11532..cfcf455ad4de 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-rt8973a.txt
@@ -11,8 +11,6 @@ for USB D-/D+ switching.
 Required properties:
 - compatible: Should be "richtek,rt8973a-muic"
 - reg: Specifies the I2C slave address of the MUIC block. It should be 0x14
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from rt8973a are delivered to.
 - interrupts: Interrupt specifiers for detection interrupt sources.
 
 Example:
diff --git a/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt b/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt
index 4ecda224955f..fc3888e09549 100644
--- a/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt
+++ b/Documentation/devicetree/bindings/extcon/extcon-sm5502.txt
@@ -9,8 +9,6 @@ the host controller using an I2C interface.
 Required properties:
 - compatible: Should be "siliconmitus,sm5502-muic"
 - reg: Specifies the I2C slave address of the MUIC block. It should be 0x25
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from sm5502 are delivered to.
 - interrupts: Interrupt specifiers for detection interrupt sources.
 
 Example:
diff --git a/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt b/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt
index 798cfc9d3839..973362eb3f1e 100644
--- a/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/8xxx_gpio.txt
@@ -25,8 +25,6 @@ Required properties:
 - #gpio-cells:		Should be two. The first cell is the pin number
 			and the second cell is used to specify optional
 			parameters (currently unused).
-- interrupt-parent:	Phandle for the interrupt controller that
-			services interrupts for this device.
 - interrupts:		Interrupt mapping for GPIO IRQ.
 - gpio-controller:	Marks the port as GPIO controller.
 
diff --git a/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt b/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
index a25c87b650e5..ce19c5660aca 100644
--- a/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/abilis,tb10x-gpio.txt
@@ -14,7 +14,6 @@ Optional Properties:
 - #interrupt-cells: Should be <1>. Interrupts are triggered on both edges.
 - interrupts: Defines the interrupt line connecting this GPIO controller to
   its parent interrupt controller.
-- interrupt-parent: Defines the parent interrupt controller.
 
 GPIO ranges are specified as described in
 Documentation/devicetree/bindings/gpio/gpio.txt
diff --git a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
index b405b4410bfb..5d468ecd1809 100644
--- a/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/brcm,brcmstb-gpio.txt
@@ -30,9 +30,6 @@ Optional properties:
 - interrupts:
     The interrupt shared by all GPIO lines for this controller.
 
-- interrupt-parent:
-    phandle of the parent interrupt controller
-
 - interrupts-extended:
     Alternate form of specifying interrupts and parents that allows for
     multiple parents.  This takes precedence over 'interrupts' and
diff --git a/Documentation/devicetree/bindings/gpio/gpio-adnp.txt b/Documentation/devicetree/bindings/gpio/gpio-adnp.txt
index af66b2724837..a28902a65a62 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-adnp.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-adnp.txt
@@ -3,7 +3,6 @@ Avionic Design N-bit GPIO expander bindings
 Required properties:
 - compatible: should be "ad,gpio-adnp"
 - reg: The I2C slave address for this device.
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupts: Interrupt specifier for the controllers interrupt.
 - #gpio-cells: Should be 2. The first cell is the GPIO number and the
   second cell is used to specify optional parameters:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt b/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt
index fc6378c778c5..7e9b586770b0 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-aspeed.txt
@@ -17,7 +17,6 @@ Required properties:
 
 Optional properties:
 
-- interrupt-parent      : The parent interrupt controller, optional if inherited
 - clocks                : A phandle to the clock to use for debounce timings
 
 The gpio and interrupt properties are further described in their respective
diff --git a/Documentation/devicetree/bindings/gpio/gpio-ath79.txt b/Documentation/devicetree/bindings/gpio/gpio-ath79.txt
index c522851017ae..cf71f3ec969d 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-ath79.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-ath79.txt
@@ -12,7 +12,6 @@ Required properties:
 - ngpios: Should be set to the number of GPIOs available on the SoC.
 
 Optional properties:
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupts: Interrupt specifier for the controllers interrupt.
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode interrupt
diff --git a/Documentation/devicetree/bindings/gpio/gpio-davinci.txt b/Documentation/devicetree/bindings/gpio/gpio-davinci.txt
index 8beb0539b6d8..553b92a7e87b 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-davinci.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-davinci.txt
@@ -15,8 +15,6 @@ Required Properties:
   - first cell is the pin number
   - second cell is used to specify optional parameters (unused)
 
-- interrupt-parent: phandle of the parent interrupt controller.
-
 - interrupts: Array of GPIO interrupt number. Only banked or unbanked IRQs are
 	      supported at a time.
 
diff --git a/Documentation/devicetree/bindings/gpio/gpio-max732x.txt b/Documentation/devicetree/bindings/gpio/gpio-max732x.txt
index 5fdc843b4542..b3a9c0c32823 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-max732x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-max732x.txt
@@ -30,7 +30,6 @@ Optional properties:
   - #interrupt-cells: Number of cells to encode an interrupt source, shall be 2.
     - first cell is the pin number
     - second cell is used to specify flags
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifier for the controllers interrupt.
 
 Please refer to gpio.txt in this directory for details of the common GPIO
diff --git a/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt b/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt
index 7d3bd631d011..a482455a205b 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-pcf857x.txt
@@ -49,7 +49,6 @@ Optional Properties:
 
   - interrupt-controller: Identifies the node as an interrupt controller.
   - #interrupt-cells: Number of cells to encode an interrupt source, shall be 2.
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifier for the controllers interrupt.
 
 
diff --git a/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt b/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt
index fed9158dd913..f281f12dac18 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-uniphier.txt
@@ -6,7 +6,6 @@ Required properties:
 - gpio-controller: Marks the device node as a GPIO controller.
 - #gpio-cells: Should be 2.  The first cell is the pin number and the second
   cell is used to specify optional parameters.
-- interrupt-parent: Specifies the parent interrupt controller.
 - interrupt-controller: Marks the device node as an interrupt controller.
 - #interrupt-cells: Should be 2.  The first cell defines the interrupt number.
   The second cell bits[3:0] is used to specify trigger type as follows:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt b/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt
index 5490c1d68981..e90fb987e25f 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-xgene-sb.txt
@@ -26,7 +26,6 @@ Required properties:
 		1 = active low
 - gpio-controller: Marks the device node as a GPIO controller.
 - interrupts: The EXT_INT_0 parent interrupt resource must be listed first.
-- interrupt-parent: Phandle of the parent interrupt controller.
 - interrupt-cells: Should be two.
        - first cell is 0-N coresponding for EXT_INT_0 to EXT_INT_N.
        - second cell is used to specify flags.
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt b/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt
index 63bf4becd5f0..08eed2335db0 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-xilinx.txt
@@ -14,8 +14,6 @@ Required properties:
 
 Optional properties:
 - interrupts : Interrupt mapping for GPIO IRQ.
-- interrupt-parent : Phandle for the interrupt controller that
-  services interrupts for this device.
 - xlnx,all-inputs : if n-th bit is setup, GPIO-n is input
 - xlnx,dout-default : if n-th bit is 1, GPIO-n default value is 1
 - xlnx,gpio-width : gpio width
diff --git a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
index 28662d83a43e..47fc64922fe0 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-xlp.txt
@@ -30,7 +30,6 @@ Required properties:
 	4 = active high level-sensitive.
 	8 = active low level-sensitive.
 - interrupts: Interrupt number for this device.
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupt-controller: Identifies the node as an interrupt controller.
 
 Example:
diff --git a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
index 7b542657f259..4fa4eb5507cd 100644
--- a/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio-zynq.txt
@@ -11,7 +11,6 @@ Required properties:
 - gpio-controller	: Marks the device node as a GPIO controller.
 - interrupts		: Interrupt specifier (see interrupt bindings for
 			  details)
-- interrupt-parent	: Must be core interrupt controller
 - interrupt-controller	: Marks the device node as an interrupt controller.
 - #interrupt-cells 	: Should be 2.  The first cell is the GPIO number.
 			  The second cell bits[3:0] is used to specify trigger type and level flags:
diff --git a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
index 20fc72d9e61e..8c9e4c3d788d 100644
--- a/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/nintendo,hollywood-gpio.txt
@@ -14,7 +14,6 @@ Optional properties:
 - #interrupt-cells: Should be two.
 - interrupts: Interrupt specifier for the controller's Broadway (PowerPC)
   interrupt.
-- interrupt-parent: phandle of the parent interrupt controller.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
index 378f1322211e..fe1bf24104d3 100644
--- a/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
+++ b/Documentation/devicetree/bindings/gpio/renesas,gpio-rcar.txt
@@ -31,7 +31,6 @@ Required Properties:
   - reg: Base address and length of each memory resource used by the GPIO
     controller hardware module.
 
-  - interrupt-parent: phandle of the parent interrupt controller.
   - interrupts: Interrupt specifier for the controllers interrupt.
 
   - gpio-controller: Marks the device node as a gpio controller.
diff --git a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
index 3c1118bc67f5..7276b50c3506 100644
--- a/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/snps-dwapb-gpio.txt
@@ -25,7 +25,6 @@ controller.
   interrupt.  Shall be set to 2.  The first cell defines the interrupt number,
   the second encodes the triger flags encoded as described in
   Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
-- interrupt-parent : The parent interrupt controller.
 - interrupts : The interrupts to the parent controller raised when GPIOs
   generate the interrupts. If the controller provides one combined interrupt
   for all GPIOs, specify a single interrupt. If the controller provides one
diff --git a/Documentation/devicetree/bindings/hsi/omap-ssi.txt b/Documentation/devicetree/bindings/hsi/omap-ssi.txt
index 955e335e7e56..77a0c3c3036e 100644
--- a/Documentation/devicetree/bindings/hsi/omap-ssi.txt
+++ b/Documentation/devicetree/bindings/hsi/omap-ssi.txt
@@ -33,7 +33,6 @@ Required Port sub-node properties:
 - reg-names:		Contains the values "tx" and "rx" (in this order).
 - reg:			Contains a matching register specifier for each entry
 			in reg-names.
-- interrupt-parent	Should be a phandle for the interrupt controller
 - interrupts:		Should contain interrupt specifiers for mpu interrupts
 			0 and 1 (in this order).
 - ti,ssi-cawake-gpio:	Defines which GPIO pin is used to signify CAWAKE
diff --git a/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt b/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt
index e7106bfc1f13..8fbd8633a387 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-aspeed.txt
@@ -11,9 +11,6 @@ Required Properties:
 - resets		: phandle to reset controller with the reset number in
 			  the second cell
 - interrupts		: interrupt number
-- interrupt-parent	: interrupt controller for bus, should reference a
-			  aspeed,ast2400-i2c-ic or aspeed,ast2500-i2c-ic
-			  interrupt controller
 
 Optional Properties:
 - bus-frequency	: frequency of the bus clock in Hz defaults to 100 kHz when not
diff --git a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
index aeceaceba3c5..0380609b177a 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-brcmstb.txt
@@ -10,8 +10,6 @@ Required properties:
 
 Optional properties :
 
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this one is cascaded from
 - interrupts: specifies the interrupt number, the irq line to be used
 - interrupt-names: Interrupt name string
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
index 60fe90d69f4e..00e4365d7206 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-imx-lpi2c.txt
@@ -5,7 +5,6 @@ Required properties:
   - "fsl,imx7ulp-lpi2c" for LPI2C compatible with the one integrated on i.MX7ULP soc
   - "fsl,imx8dv-lpi2c" for LPI2C compatible with the one integrated on i.MX8DV soc
 - reg : address and length of the lpi2c master registers
-- interrupt-parent : core interrupt controller
 - interrupts : lpi2c interrupt
 - clocks : lpi2c clock specifier
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt b/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
index d4a082acf92f..3738cfbf863f 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-jz4780.txt
@@ -11,10 +11,6 @@ Recommended properties:
 - pinctrl-names: should be "default";
 - pinctrl-0: phandle to pinctrl function
 
-Optional properties:
-- interrupt-parent: Should be the phandle of the interrupt controller that
-  delivers interrupts to the I2C block.
-
 Example
 
 / {
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mpc.txt b/Documentation/devicetree/bindings/i2c/i2c-mpc.txt
index 1eacd6b20ed5..42a390526957 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mpc.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mpc.txt
@@ -15,8 +15,6 @@ Recommended properties :
    information for the interrupt.  This should be encoded based on
    the information in section 2) depending on the type of interrupt
    controller you have.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
  - fsl,preserve-clocking : boolean; if defined, the clock settings
    from the bootloader are preserved (not touched).
  - clock-frequency : desired I2C bus clock frequency in Hz.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
index 34d91501342e..ccf6c86ed076 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-mux-pca954x.txt
@@ -28,8 +28,6 @@ Optional Properties:
   - i2c-mux-idle-disconnect: Boolean; if defined, forces mux to disconnect all
     children in idle state. This is necessary for example, if there are several
     multiplexers on the bus and the devices behind them use same I2C addresses.
-  - interrupt-parent: Phandle for the interrupt controller that services
-    interrupts for this device.
   - interrupts: Interrupt mapping for IRQ.
   - interrupt-controller: Marks the device node as an interrupt controller.
   - #interrupt-cells : Should be two.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt b/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt
index f1f3876bb8e8..73a693d66ef7 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-pca-platform.txt
@@ -12,8 +12,6 @@ Required properties :
 
 Optional properties
  - interrupts : the interrupt number
- - interrupt-parent : the phandle for the interrupt controller.
-   If an interrupt is not specified polling will be used.
  - reset-gpios : gpio specifier for gpio connected to RESET_N pin. As the line
    is active low, it should be marked GPIO_ACTIVE_LOW.
  - clock-frequency : I2C bus frequency.
diff --git a/Documentation/devicetree/bindings/i2c/i2c-pnx.txt b/Documentation/devicetree/bindings/i2c/i2c-pnx.txt
index fe98ada33ee4..2a59006cf79e 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-pnx.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-pnx.txt
@@ -7,8 +7,6 @@ Required properties:
  - interrupts: configure one interrupt line
  - #address-cells: always 1 (for i2c addresses)
  - #size-cells: always 0
- - interrupt-parent: the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Optional properties:
 
diff --git a/Documentation/devicetree/bindings/i2c/i2c-pxa.txt b/Documentation/devicetree/bindings/i2c/i2c-pxa.txt
index d30f0b11d853..c30783c0eca0 100644
--- a/Documentation/devicetree/bindings/i2c/i2c-pxa.txt
+++ b/Documentation/devicetree/bindings/i2c/i2c-pxa.txt
@@ -12,9 +12,6 @@ Required properties :
 Recommended properties :
 
  - interrupts : the interrupt number
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device. If the parent is the default
-   interrupt controller in device tree, it could be ignored.
  - mrvl,i2c-polling : Disable interrupt of i2c controller. Polling
    status register of i2c controller instead.
  - mrvl,i2c-fast-mode : Enable fast mode of i2c controller.
diff --git a/Documentation/devicetree/bindings/iio/accel/adxl345.txt b/Documentation/devicetree/bindings/iio/accel/adxl345.txt
index e7111b02c02c..ae09a046bc72 100644
--- a/Documentation/devicetree/bindings/iio/accel/adxl345.txt
+++ b/Documentation/devicetree/bindings/iio/accel/adxl345.txt
@@ -11,8 +11,6 @@ Required properties for SPI bus usage:
  - spi-cpol and spi-cpha : must be defined for adxl345 to enable SPI mode 3
 
 Optional properties:
- - interrupt-parent : phandle to the parent interrupt controller as documented
-   in Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
  - interrupts: interrupt mapping for IRQ as documented in
    Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
diff --git a/Documentation/devicetree/bindings/iio/accel/bma180.txt b/Documentation/devicetree/bindings/iio/accel/bma180.txt
index 4a3679d54457..3b25b4c4d446 100644
--- a/Documentation/devicetree/bindings/iio/accel/bma180.txt
+++ b/Documentation/devicetree/bindings/iio/accel/bma180.txt
@@ -10,8 +10,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent : should be the phandle for the interrupt controller
-
   - interrupts : interrupt mapping for GPIO IRQ, it should by configured with
 		flags IRQ_TYPE_LEVEL_HIGH | IRQ_TYPE_EDGE_RISING
 		For the bma250 the first interrupt listed must be the one
diff --git a/Documentation/devicetree/bindings/iio/accel/mma8452.txt b/Documentation/devicetree/bindings/iio/accel/mma8452.txt
index 45f5c5c5929c..2100e9af379c 100644
--- a/Documentation/devicetree/bindings/iio/accel/mma8452.txt
+++ b/Documentation/devicetree/bindings/iio/accel/mma8452.txt
@@ -15,8 +15,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
-
   - interrupts: interrupt mapping for GPIO IRQ
 
   - interrupt-names: should contain "INT1" and/or "INT2", the accelerometer's
diff --git a/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt b/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
index 487ea966858e..ec04008e8f4f 100644
--- a/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/cpcap-adc.txt
@@ -2,7 +2,6 @@ Motorola CPCAP PMIC ADC binding
 
 Required properties:
 - compatible: Should be "motorola,cpcap-adc" or "motorola,mapphone-cpcap-adc"
-- interrupt-parent: The interrupt controller
 - interrupts: The interrupt number for the ADC device
 - interrupt-names: Should be "adcdone"
 - #io-channel-cells: Number of cells in an IIO specifier
diff --git a/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt b/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt
index b0866d36a307..eebdcec3dab5 100644
--- a/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt
+++ b/Documentation/devicetree/bindings/iio/adc/fsl,imx25-gcq.txt
@@ -8,7 +8,6 @@ Required properties:
  - reg: Should be the register range of the module.
  - interrupts: Should be the interrupt number of the module.
    Typically this is <1>.
- - interrupt-parent: phandle to the tsadc module of the i.MX25.
  - #address-cells: Should be <1> (setting for the subnodes)
  - #size-cells: Should be <0> (setting for the subnodes)
 
diff --git a/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt b/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt
index a8770cc6bcad..e680c61dfb84 100644
--- a/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/max1027-adc.txt
@@ -3,8 +3,6 @@
 Required properties:
   - compatible: Should be "maxim,max1027" or "maxim,max1029" or "maxim,max1031"
   - reg: SPI chip select number for the device
-  - interrupt-parent: phandle to the parent interrupt controller
-  see: Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
   - interrupts: IRQ line for the ADC
   see: Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
diff --git a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
index f1ead43a1a95..8346bcb04ad7 100644
--- a/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/st,stm32-adc.txt
@@ -60,7 +60,6 @@ Required properties:
 - reg: Offset of ADC instance in ADC block (e.g. may be 0x0, 0x100, 0x200).
 - clocks: Input clock private to this ADC instance. It's required only on
   stm32f4, that has per instance clock input for registers access.
-- interrupt-parent: Phandle to the parent interrupt controller.
 - interrupts: IRQ Line for the ADC (e.g. may be 0 for adc@0, 1 for adc@100 or
   2 for adc@200).
 - st,adc-channels: List of single-ended channels muxed for this ADC.
diff --git a/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt b/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt
index d71258e2d456..e0e0755cabd8 100644
--- a/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt
+++ b/Documentation/devicetree/bindings/iio/adc/xilinx-xadc.txt
@@ -22,7 +22,6 @@ Required properties:
 	  clock to the AXI bus interface of the core.
 
 Optional properties:
-	- interrupt-parent: phandle to the parent interrupt controller
 	- xlnx,external-mux:
 		* "none": No external multiplexer is used, this is the default
 		  if the property is omitted.
diff --git a/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt b/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt
index 2962bd9a2b3d..f4320595b851 100644
--- a/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt
+++ b/Documentation/devicetree/bindings/iio/chemical/atlas,ec-sm.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "atlas,ec-sm"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt b/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt
index 5d8b687d5edc..af1f5a9aa4da 100644
--- a/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt
+++ b/Documentation/devicetree/bindings/iio/chemical/atlas,orp-sm.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "atlas,orp-sm"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt b/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt
index cffa1907463a..79d90f060327 100644
--- a/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt
+++ b/Documentation/devicetree/bindings/iio/chemical/atlas,ph-sm.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "atlas,ph-sm"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt
index b0d3b59966bc..233fe207aded 100644
--- a/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt
+++ b/Documentation/devicetree/bindings/iio/gyroscope/invensense,mpu3050.txt
@@ -5,7 +5,6 @@ Required properties:
   - reg : the I2C address of the sensor
 
 Optional properties:
-  - interrupt-parent : should be the phandle for the interrupt controller
   - interrupts : interrupt mapping for the trigger interrupt from the
     internal oscillator. The following IRQ modes are supported:
     IRQ_TYPE_EDGE_RISING, IRQ_TYPE_EDGE_FALLING, IRQ_TYPE_LEVEL_HIGH and
diff --git a/Documentation/devicetree/bindings/iio/health/afe4403.txt b/Documentation/devicetree/bindings/iio/health/afe4403.txt
index 2fffd70336ba..8e412054d6d5 100644
--- a/Documentation/devicetree/bindings/iio/health/afe4403.txt
+++ b/Documentation/devicetree/bindings/iio/health/afe4403.txt
@@ -4,7 +4,6 @@ Required properties:
  - compatible		: Should be "ti,afe4403".
  - reg			: SPI chip select address of device.
  - tx-supply		: Regulator supply to transmitting LEDs.
- - interrupt-parent	: Phandle to he parent interrupt controller.
  - interrupts		: The interrupt line the device ADC_RDY pin is
 			  connected to. For details refer to,
 			  ../../interrupt-controller/interrupts.txt.
diff --git a/Documentation/devicetree/bindings/iio/health/afe4404.txt b/Documentation/devicetree/bindings/iio/health/afe4404.txt
index de69f203edfa..0b52830a0d9c 100644
--- a/Documentation/devicetree/bindings/iio/health/afe4404.txt
+++ b/Documentation/devicetree/bindings/iio/health/afe4404.txt
@@ -4,7 +4,6 @@ Required properties:
  - compatible		: Should be "ti,afe4404".
  - reg			: I2C address of the device.
  - tx-supply		: Regulator supply to transmitting LEDs.
- - interrupt-parent	: Phandle to he parent interrupt controller.
  - interrupts		: The interrupt line the device ADC_RDY pin is
 			  connected to. For details refer to,
 			  ../interrupt-controller/interrupts.txt.
diff --git a/Documentation/devicetree/bindings/iio/health/max30100.txt b/Documentation/devicetree/bindings/iio/health/max30100.txt
index 8d8176459d09..0054908a6e74 100644
--- a/Documentation/devicetree/bindings/iio/health/max30100.txt
+++ b/Documentation/devicetree/bindings/iio/health/max30100.txt
@@ -5,7 +5,6 @@ Maxim MAX30100 heart rate and pulse oximeter sensor
 Required properties:
   - compatible: must be "maxim,max30100"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/health/max30102.txt b/Documentation/devicetree/bindings/iio/health/max30102.txt
index ef2ca0a0306f..7ef7ae40ae4f 100644
--- a/Documentation/devicetree/bindings/iio/health/max30102.txt
+++ b/Documentation/devicetree/bindings/iio/health/max30102.txt
@@ -7,7 +7,6 @@ Maxim MAX30105 optical particle-sensing module
 Required properties:
   - compatible: must be "maxim,max30102" or "maxim,max30105"
   - reg: the I2C address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/humidity/hts221.txt b/Documentation/devicetree/bindings/iio/humidity/hts221.txt
index 10adeb0d703d..84d029372260 100644
--- a/Documentation/devicetree/bindings/iio/humidity/hts221.txt
+++ b/Documentation/devicetree/bindings/iio/humidity/hts221.txt
@@ -13,7 +13,6 @@ Optional properties:
   when it is not active, whereas a pull-up one is needed when interrupt
   line is configured as IRQ_TYPE_LEVEL_LOW or IRQ_TYPE_EDGE_FALLING.
   Refer to pinctrl/pinctrl-bindings.txt for the property description.
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ. It should be configured with
   flags IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
   IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/imu/bmi160.txt b/Documentation/devicetree/bindings/iio/imu/bmi160.txt
index ae0112c7debc..0c1c105fb503 100644
--- a/Documentation/devicetree/bindings/iio/imu/bmi160.txt
+++ b/Documentation/devicetree/bindings/iio/imu/bmi160.txt
@@ -9,7 +9,6 @@ Required properties:
  - spi-max-frequency : set maximum clock frequency (only for SPI)
 
 Optional properties:
- - interrupt-parent : should be the phandle of the interrupt controller
  - interrupts : interrupt mapping for IRQ, must be IRQ_TYPE_LEVEL_LOW
  - interrupt-names : set to "INT1" if INT1 pin should be used as interrupt
    input, set to "INT2" if INT2 pin should be used instead
diff --git a/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt b/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt
index 5f4777e8cc9e..d33c19d68de3 100644
--- a/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt
+++ b/Documentation/devicetree/bindings/iio/imu/inv_mpu6050.txt
@@ -11,7 +11,6 @@ Required properties:
 		"invensense,mpu9255"
 		"invensense,icm20608"
  - reg : the I2C address of the sensor
- - interrupt-parent : should be the phandle for the interrupt controller
  - interrupts: interrupt mapping for IRQ. It should be configured with flags
    IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
    IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt b/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt
index ef8a8566c63f..ea2d6e0ae4c5 100644
--- a/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt
+++ b/Documentation/devicetree/bindings/iio/imu/st_lsm6dsx.txt
@@ -20,7 +20,6 @@ Optional properties:
   IRQ_TYPE_EDGE_RISING a pull-down resistor is needed to drive the line
   when it is not active, whereas a pull-up one is needed when interrupt
   line is configured as IRQ_TYPE_LEVEL_LOW or IRQ_TYPE_EDGE_FALLING.
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ. It should be configured with
   flags IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
   IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/light/apds9300.txt b/Documentation/devicetree/bindings/iio/light/apds9300.txt
index d6f66c73ddbf..aa199e09a493 100644
--- a/Documentation/devicetree/bindings/iio/light/apds9300.txt
+++ b/Documentation/devicetree/bindings/iio/light/apds9300.txt
@@ -9,7 +9,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent : should be the phandle for the interrupt controller
   - interrupts : interrupt mapping for GPIO IRQ
 
 Example:
diff --git a/Documentation/devicetree/bindings/iio/light/apds9960.txt b/Documentation/devicetree/bindings/iio/light/apds9960.txt
index 174b709f16db..3af325ad194b 100644
--- a/Documentation/devicetree/bindings/iio/light/apds9960.txt
+++ b/Documentation/devicetree/bindings/iio/light/apds9960.txt
@@ -6,7 +6,6 @@ Required properties:
 
   - compatible: must be "avago,apds9960"
   - reg: the I2c address of the sensor
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts : the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/light/isl29018.txt b/Documentation/devicetree/bindings/iio/light/isl29018.txt
index 425ab459e209..b9bbde3e13ed 100644
--- a/Documentation/devicetree/bindings/iio/light/isl29018.txt
+++ b/Documentation/devicetree/bindings/iio/light/isl29018.txt
@@ -10,7 +10,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/light/opt3001.txt b/Documentation/devicetree/bindings/iio/light/opt3001.txt
index eac30d508849..47b13eb8f4ec 100644
--- a/Documentation/devicetree/bindings/iio/light/opt3001.txt
+++ b/Documentation/devicetree/bindings/iio/light/opt3001.txt
@@ -13,7 +13,6 @@ Required properties:
   - reg: the I2C address of the sensor
 
 Optional properties:
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: interrupt mapping for GPIO IRQ (configure for falling edge)
 
 Example:
diff --git a/Documentation/devicetree/bindings/iio/light/tsl2583.txt b/Documentation/devicetree/bindings/iio/light/tsl2583.txt
index 8e2066c83f70..059dffa1829a 100644
--- a/Documentation/devicetree/bindings/iio/light/tsl2583.txt
+++ b/Documentation/devicetree/bindings/iio/light/tsl2583.txt
@@ -10,7 +10,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
   - interrupts: the sole interrupt generated by the device
 
   Refer to interrupt-controller/interrupts.txt for generic interrupt client
diff --git a/Documentation/devicetree/bindings/iio/light/uvis25.txt b/Documentation/devicetree/bindings/iio/light/uvis25.txt
index 3041207e3f3c..043c139d91e6 100644
--- a/Documentation/devicetree/bindings/iio/light/uvis25.txt
+++ b/Documentation/devicetree/bindings/iio/light/uvis25.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg: i2c address of the sensor / spi cs line
 
 Optional properties:
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ. It should be configured with
   flags IRQ_TYPE_LEVEL_HIGH, IRQ_TYPE_EDGE_RISING, IRQ_TYPE_LEVEL_LOW or
   IRQ_TYPE_EDGE_FALLING.
diff --git a/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt b/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt
index 9f263b7df162..fd5fca90fb39 100644
--- a/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt
+++ b/Documentation/devicetree/bindings/iio/magnetometer/bmc150_magn.txt
@@ -9,7 +9,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent : phandle to the parent interrupt controller
   - interrupts : interrupt mapping for GPIO IRQ
 
 Example:
diff --git a/Documentation/devicetree/bindings/iio/pressure/bmp085.txt b/Documentation/devicetree/bindings/iio/pressure/bmp085.txt
index c7198a03c906..5498b0688b6f 100644
--- a/Documentation/devicetree/bindings/iio/pressure/bmp085.txt
+++ b/Documentation/devicetree/bindings/iio/pressure/bmp085.txt
@@ -12,7 +12,6 @@ Optional properties:
 - temp-measurement-period: temperature measurement period (milliseconds)
 - default-oversampling: default oversampling value to be used at startup,
   value range is 0-3 with rising sensitivity.
-- interrupt-parent: should be the phandle for the interrupt controller
 - interrupts: interrupt mapping for IRQ
 - reset-gpios: a GPIO line handling reset of the sensor: as the line is
   active low, it should be marked GPIO_ACTIVE_LOW (see gpio/gpio.txt)
diff --git a/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt b/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt
index fb85de676e03..a36ab3e0c3f7 100644
--- a/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt
+++ b/Documentation/devicetree/bindings/iio/pressure/zpa2326.txt
@@ -15,8 +15,6 @@ Optional properties:
   power to the sensor
 - vdd-supply: an optional regulator that needs to be on to provide VDD
   power to the sensor
-- interrupt-parent: phandle to the parent interrupt controller as documented in
-  Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 - interrupts: interrupt mapping for IRQ as documented in
   Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
diff --git a/Documentation/devicetree/bindings/iio/proximity/as3935.txt b/Documentation/devicetree/bindings/iio/proximity/as3935.txt
index b6c1afa6f02d..849115585d55 100644
--- a/Documentation/devicetree/bindings/iio/proximity/as3935.txt
+++ b/Documentation/devicetree/bindings/iio/proximity/as3935.txt
@@ -6,7 +6,6 @@ Required properties:
 	- spi-max-frequency: specifies maximum SPI clock frequency
 	- spi-cpha: SPI Mode 1. Refer to spi/spi-bus.txt for generic SPI
 	slave node bindings.
-	- interrupt-parent : should be the phandle for the interrupt controller
 	- interrupts : the sole interrupt generated by the device
 
 	Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/proximity/sx9500.txt b/Documentation/devicetree/bindings/iio/proximity/sx9500.txt
index b301dd2b35da..c54455db3bec 100644
--- a/Documentation/devicetree/bindings/iio/proximity/sx9500.txt
+++ b/Documentation/devicetree/bindings/iio/proximity/sx9500.txt
@@ -3,7 +3,6 @@ Semtech's SX9500 capacitive proximity button device driver
 Required properties:
 	- compatible: must be "semtech,sx9500"
 	- reg: i2c address where to find the device
-	- interrupt-parent : should be the phandle for the interrupt controller
 	- interrupts : the sole interrupt generated by the device
 
 	Refer to interrupt-controller/interrupts.txt for generic
diff --git a/Documentation/devicetree/bindings/iio/sensorhub.txt b/Documentation/devicetree/bindings/iio/sensorhub.txt
index 8d57571d5c0b..b6ac0457d4ea 100644
--- a/Documentation/devicetree/bindings/iio/sensorhub.txt
+++ b/Documentation/devicetree/bindings/iio/sensorhub.txt
@@ -6,7 +6,6 @@ of a virtual sensor device.
 Required properties:
 - compatible: "samsung,sensorhub-rinato" or "samsung,sensorhub-thermostat"
 - spi-max-frequency: max SPI clock frequency
-- interrupt-parent: interrupt parent
 - interrupts: communication interrupt
 - ap-mcu-gpios: [out] ap to sensorhub line - used during communication
 - mcu-ap-gpios: [in] sensorhub to ap - used during communication
diff --git a/Documentation/devicetree/bindings/iio/temperature/tmp007.txt b/Documentation/devicetree/bindings/iio/temperature/tmp007.txt
index b63aba91ef03..da0af234a357 100644
--- a/Documentation/devicetree/bindings/iio/temperature/tmp007.txt
+++ b/Documentation/devicetree/bindings/iio/temperature/tmp007.txt
@@ -20,8 +20,6 @@ Required properties:
 
 Optional properties:
 
-  - interrupt-parent: should be the phandle for the interrupt controller
-
   - interrupts: interrupt mapping for GPIO IRQ (level active low)
 
 Example:
diff --git a/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt b/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
index d3b273e4336a..84f1a1b505d2 100644
--- a/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
+++ b/Documentation/devicetree/bindings/infiniband/hisilicon-hns-roce.txt
@@ -19,7 +19,6 @@ representing a dsaf device.
 - #size-cells: must be 2
 Optional properties:
 - dma-coherent: Present if DMA operations are coherent.
-- interrupt-parent: the interrupt parent of this device.
 - interrupts: should contain 32 completion event irq,1 async event irq
 and 1 event overflow irq.
 - interrupt-names:should be one of 34 irqs for roce device
diff --git a/Documentation/devicetree/bindings/input/cypress,cyapa.txt b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
index 8d91ba9ff2fd..d3db65916a36 100644
--- a/Documentation/devicetree/bindings/input/cypress,cyapa.txt
+++ b/Documentation/devicetree/bindings/input/cypress,cyapa.txt
@@ -3,8 +3,6 @@ Cypress I2C Touchpad
 Required properties:
 - compatible: must be "cypress,cyapa".
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-	binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
 	binding[0]).
 
diff --git a/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt b/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt
index 635f62c756ee..0c252d9306da 100644
--- a/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt
+++ b/Documentation/devicetree/bindings/input/cypress,tm2-touchkey.txt
@@ -3,8 +3,6 @@ Samsung tm2-touchkey
 Required properties:
 - compatible: must be "cypress,tm2-touchkey"
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-	binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
 	binding[0]).
 - vcc-supply : internal regulator output. 1.8V
diff --git a/Documentation/devicetree/bindings/input/e3x0-button.txt b/Documentation/devicetree/bindings/input/e3x0-button.txt
index 751665e8e47a..907b195f2eaa 100644
--- a/Documentation/devicetree/bindings/input/e3x0-button.txt
+++ b/Documentation/devicetree/bindings/input/e3x0-button.txt
@@ -7,8 +7,6 @@ This module provides a simple power button event via two interrupts.
 Required properties:
 - compatible: should be one of the following
   - "ettus,e3x0-button": For devices such as the NI Ettus Research USRP E3x0
-- interrupt-parent:
-  - a phandle to the interrupt controller that it is attached to.
 - interrupts: should be one of the following
   - <0 30 1>, <0 31 1>: For devices such as the NI Ettus Research USRP E3x0
 - interrupt-names: should be one of the following
diff --git a/Documentation/devicetree/bindings/input/elan_i2c.txt b/Documentation/devicetree/bindings/input/elan_i2c.txt
index d80a83583238..797607460735 100644
--- a/Documentation/devicetree/bindings/input/elan_i2c.txt
+++ b/Documentation/devicetree/bindings/input/elan_i2c.txt
@@ -3,8 +3,6 @@ Elantech I2C Touchpad
 Required properties:
 - compatible: must be "elan,ekth3000".
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-  binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
   binding[0]).
 
diff --git a/Documentation/devicetree/bindings/input/elants_i2c.txt b/Documentation/devicetree/bindings/input/elants_i2c.txt
index 8a71038f3489..5edac8be0802 100644
--- a/Documentation/devicetree/bindings/input/elants_i2c.txt
+++ b/Documentation/devicetree/bindings/input/elants_i2c.txt
@@ -3,8 +3,6 @@ Elantech I2C Touchscreen
 Required properties:
 - compatible: must be "elan,ekth3500".
 - reg: I2C address of the chip.
-- interrupt-parent: a phandle for the interrupt controller (see interrupt
-  binding[0]).
 - interrupts: interrupt to which the chip is connected (see interrupt
   binding[0]).
 
diff --git a/Documentation/devicetree/bindings/input/hid-over-i2c.txt b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
index 4d3da9d91de4..f1cb9f8d7692 100644
--- a/Documentation/devicetree/bindings/input/hid-over-i2c.txt
+++ b/Documentation/devicetree/bindings/input/hid-over-i2c.txt
@@ -14,7 +14,6 @@ Required properties:
 - compatible: must be "hid-over-i2c"
 - reg: i2c slave address
 - hid-descr-addr: HID descriptor address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: interrupt line
 
 Additional optional properties:
diff --git a/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt b/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt
index 5b6232db7c61..99a4f2ab5557 100644
--- a/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt
+++ b/Documentation/devicetree/bindings/input/raydium_i2c_ts.txt
@@ -3,7 +3,6 @@ Raydium I2C touchscreen
 Required properties:
 - compatible: must be "raydium,rm32380"
 - reg: The I2C address of the device
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: interrupt to which the chip is connected
     See ../interrupt-controller/interrupts.txt
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt b/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt
index ec908b91fd90..dcb012f5b3ee 100644
--- a/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt
+++ b/Documentation/devicetree/bindings/input/rmi4/rmi_i2c.txt
@@ -16,7 +16,6 @@ Required Properties:
 
 Optional Properties:
 - interrupts: interrupt which the rmi device is connected to.
-- interrupt-parent: The interrupt controller.
 See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
 - syna,reset-delay-ms: The number of milliseconds to wait after resetting the
diff --git a/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt b/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt
index a4ca7828f21d..632f473db65b 100644
--- a/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt
+++ b/Documentation/devicetree/bindings/input/rmi4/rmi_spi.txt
@@ -16,7 +16,6 @@ Required Properties:
 
 Optional Properties:
 - interrupts: interrupt which the rmi device is connected to.
-- interrupt-parent: The interrupt controller.
 See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
 
 - spi-rx-delay-us: microsecond delay after a read transfer.
diff --git a/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt b/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt
index a3dde8c30e67..c829e18e1a05 100644
--- a/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt
+++ b/Documentation/devicetree/bindings/input/ti,palmas-pwrbutton.txt
@@ -9,7 +9,6 @@ This module provides a simple power button event via an Interrupt.
 Required properties:
 - compatible: should be one of the following
    - "ti,palmas-pwrbutton": For Palmas compatible power on button
-- interrupt-parent: Parent interrupt device, must be handle of palmas node.
 - interrupts: Interrupt number of power button submodule on device.
 
 Optional Properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt b/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt
index 3c8614c451f2..cdd743a1f2d5 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ad7879.txt
@@ -5,7 +5,6 @@ Required properties:
 				  for I2C slave, use "adi,ad7879-1"
 - reg				: SPI chipselect/I2C slave address
 				  See spi-bus.txt for more SPI slave properties
-- interrupt-parent		: the phandle for the interrupt controller
 - interrupts			: touch controller interrupt
 - touchscreen-max-pressure	: maximum reported pressure
 - adi,resistance-plate-x	: total resistance of X-plate (for pressure
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt b/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt
index 9fc47b006fd1..04413da51391 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ads7846.txt
@@ -18,7 +18,6 @@ Additional required properties:
 					"ti,ads7846"
 					"ti,ads7873"
 
-	interrupt-parent
 	interrupts		An interrupt node describing the IRQ line the chip's
 				!PENIRQ pin is connected to.
 	vcc-supply		A regulator node for the supply voltage.
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt b/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt
index e459e8546f34..82019bd6094e 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ar1021.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible		: "microchip,ar1021-i2c"
 - reg			: I2C slave address
-- interrupt-parent	: the phandle for the interrupt controller
 - interrupts		: touch controller interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt b/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
index d11f8d615b5d..38b0603f65f3 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/chipone_icn8318.txt
@@ -3,8 +3,6 @@
 Required properties:
  - compatible		  : "chipone,icn8318"
  - reg			  : I2C slave address of the chip (0x40)
- - interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
  - interrupts		  : interrupt specification for the icn8318 interrupt
  - wake-gpios		  : GPIO specification for the WAKE input
  - touchscreen-size-x	  : horizontal resolution of touchscreen (in pixels)
diff --git a/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt
index df531b5b6a0d..2e1490a8fe74 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/colibri-vf50-ts.txt
@@ -7,7 +7,6 @@ Required Properties:
 - xm-gpios: FET gate driver for input of X-
 - yp-gpios: FET gate driver for input of Y+
 - ym-gpios: FET gate driver for input of Y-
-- interrupt-parent: phandle for the interrupt controller
 - interrupts: pen irq interrupt for touch detection
 - pinctrl-names: "idle", "default", "gpios"
 - pinctrl-0: pinctrl node for pen/touch detection state pinmux
diff --git a/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt b/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt
index b75d4cfd2c36..6ee274aa8b03 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/cyttsp.txt
@@ -4,8 +4,6 @@ Required properties:
  - compatible		: must be "cypress,cyttsp-i2c" or "cypress,cyttsp-spi"
  - reg			: Device I2C address or SPI chip select number
  - spi-max-frequency	: Maximum SPI clocking speed of the device (for cyttsp-spi)
- - interrupt-parent	: the phandle for the gpio controller
-			  (see interrupt binding[0]).
  - interrupts		: (gpio) interrupt to which the chip is connected
 			  (see interrupt binding[0]).
  - bootloader-key	: the 8-byte bootloader key that is required to switch
diff --git a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
index 025cf8c9324a..da2dc5d6c98b 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/edt-ft5x06.txt
@@ -22,8 +22,6 @@ Required properties:
            or:  "focaltech,ft6236"
 
  - reg:         I2C slave address of the chip (0x38)
- - interrupt-parent: a phandle pointing to the interrupt controller
-                     serving the interrupt for this chip
  - interrupts:       interrupt specification for the touchdetect
                      interrupt
 
diff --git a/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
index 298e3442f143..92fb2620f5e2 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/egalax-ts.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "eeti,egalax_ts"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 - wakeup-gpios: the gpio pin to be used for waking up the controller
   and also used as irq pin
diff --git a/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt b/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt
index 5a19f4c3e9d7..94c4fc644940 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/ektf2127.txt
@@ -3,8 +3,6 @@
 Required properties:
  - compatible		  : "elan,ektf2127"
  - reg			  : I2C slave address of the chip (0x40)
- - interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
  - interrupts		  : interrupt specification for the ektf2127 interrupt
  - power-gpios		  : GPIO specification for the pin connected to the
 			    ektf2127's wake input. This needs to be driven high
diff --git a/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt b/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt
index 1dcff4a43eaa..68291b94fec2 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/exc3000.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "eeti,exc3000"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 - touchscreen-size-x: See touchscreen.txt
 - touchscreen-size-y: See touchscreen.txt
diff --git a/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt b/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt
index abfcab3edc66..99d6f9d25335 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/fsl-mx25-tcq.txt
@@ -8,7 +8,6 @@ Required properties:
  - reg: Memory range of the device.
  - interrupts: Should be the interrupt number associated with this module within
    the tscadc unit (<0>).
- - interrupt-parent: Should be a phandle to the tscadc unit.
  - fsl,wires: Should be '<4>' or '<5>'
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt b/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
index 0c369d8ebcab..f7e95c52f3c7 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/goodix.txt
@@ -11,7 +11,6 @@ Required properties:
 				 or "goodix,gt928"
 				 or "goodix,gt967"
  - reg			: I2C address of the chip. Should be 0x5d or 0x14
- - interrupt-parent	: Interrupt controller to which the chip is connected
  - interrupts		: Interrupt to which the chip is connected
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
index 121d9b7c79a2..b0c4cfdf7cd6 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/hideep.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible		: must be "hideep,hideep-ts"
 - reg			: I2C slave address, (e.g. 0x6C).
-- interrupt-parent : Interrupt controller to which the chip is connected.
 - interrupts : Interrupt to which the chip is connected.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt b/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt
index 40ac0fe94df6..05e982c3454e 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/max11801-ts.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "maxim,max11801"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt b/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
index 7b8944c2cb31..b2ab5498e519 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/melfas_mip4.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "melfas,mip4_ts"
 - reg: I2C slave address of the chip (0x48 or 0x34)
-- interrupt-parent: interrupt controller to which the chip is connected
 - interrupts: interrupt to which the chip is connected
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
index d9b7c2ff611e..6805d10d226d 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/samsung,s6sy761.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible		: must be "samsung,s6sy761"
 - reg			: I2C slave address, (e.g. 0x48)
-- interrupt-parent	: the phandle to the interrupt controller which provides
-			  the interrupt
 - interrupts		: interrupt specification
 - avdd-supply		: analogic power supply
 - vdd-supply		: power supply
diff --git a/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt b/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
index 84752de12412..d67e558e5ab5 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/silead_gsl1680.txt
@@ -8,8 +8,6 @@ Required properties:
 			    "silead,gsl3675"
 			    "silead,gsl3692"
 - reg			  : I2C slave address of the chip (0x40)
-- interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
 - interrupts		  : interrupt specification for the gsl1680 interrupt
 - power-gpios		  : Specification for the pin connected to the gsl1680's
 			    shutdown input. This needs to be driven high to take the
diff --git a/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt b/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt
index d87ad14f1efe..8f5322e01024 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: must be "sis,9200-ts"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
-  (see interrupt binding [0])
 - interrupts: touch controller interrupt (see interrupt
   binding [0])
 
diff --git a/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt b/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt
index 9683595cd0f5..0a5d0cb4a280 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/st,stmfts.txt
@@ -10,8 +10,6 @@ coordinates.
 Required properties:
 - compatible		: must be "st,stmfts"
 - reg			: I2C slave address, (e.g. 0x49)
-- interrupt-parent	: the phandle to the interrupt controller which provides
-			  the interrupt
 - interrupts		: interrupt specification
 - avdd-supply		: analogic power supply
 - vdd-supply		: power supply
diff --git a/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt b/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt
index 5aaa6b3aa90c..4886c4aa2906 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/sx8654.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: must be "semtech,sx8654"
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: touch controller interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt b/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt
index ec365e172236..ed00f61b8c08 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/tsc2007.txt
@@ -9,8 +9,6 @@ Optional properties:
 - gpios: the interrupt gpio the chip is connected to (trough the penirq pin).
   The penirq pin goes to low when the panel is touched.
   (see GPIO binding[1] for more details).
-- interrupt-parent: the phandle for the gpio controller
-  (see interrupt binding[0]).
 - interrupts: (gpio) interrupt to which the chip is connected
   (see interrupt binding[0]).
 - ti,max-rt: maximum pressure.
diff --git a/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt b/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt
index fe6a1feef703..27d55a506f18 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt
+++ b/Documentation/devicetree/bindings/input/touchscreen/zet6223.txt
@@ -3,8 +3,6 @@ Zeitec ZET6223 I2C touchscreen controller
 Required properties:
 - compatible		  : "zeitec,zet6223"
 - reg			  : I2C slave address of the chip (0x76)
-- interrupt-parent	  : a phandle pointing to the interrupt controller
-			    serving the interrupt for this chip
 - interrupts		  : interrupt specification for the zet6223 interrupt
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt b/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt
index 9d52d5afe3e9..5a4dd263fc12 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/abilis,tb10x-ictl.txt
@@ -13,7 +13,6 @@ Required properties
 - interrupt-congroller: Identifies the node as an interrupt controller.
 - #interrupt cells: Specifies the number of cells used to encode an interrupt
   source connected to this controller. The value shall be 2.
-- interrupt-parent: Specifies the parent interrupt controller.
 - interrupts: Specifies the list of interrupt lines which are handled by
   the interrupt controller in the parent controller's notation. Interrupts
   are mapped one-to-one to parent interrupts.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
index f6f1c14bf99b..5669764f9cc9 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/al,alpine-msix.txt
@@ -6,7 +6,6 @@ Required properties:
 
 - compatible: should be "al,alpine-msix"
 - reg: physical base address and size of the registers
-- interrupt-parent: specifies the parent interrupt controller.
 - interrupt-controller: identifies the node as an interrupt controller
 - msi-controller: identifies the node as an PCI Message Signaled Interrupt
 		  controller
diff --git a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
index 4903fb72d883..24beadf7ba83 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/allwinner,sunxi-nmi.txt
@@ -13,7 +13,6 @@ Required properties:
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value shall be 2. The first cell is the IRQ number, the
   second cell the trigger type as defined in interrupt.txt in this directory.
-- interrupt-parent: Specifies the parent interrupt controller.
 - interrupts: Specifies the interrupt line (NMI) which is handled by
   the interrupt controller in the parent controller's notation. This value
   shall be the NMI.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
index 89674ad8a097..1502a51548bb 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/amlogic,meson-gpio-intc.txt
@@ -15,9 +15,6 @@ Required properties:
     "amlogic,meson-gxbb-gpio-intc" for GXBB SoCs (S905) or
     "amlogic,meson-gxl-gpio-intc" for GXL SoCs (S905X, S912)
     "amlogic,meson-axg-gpio-intc" for AXG SoCs (A113D, A113X)
-- interrupt-parent : a phandle to the GIC the interrupts are routed to.
-   Usually this is provided at the root level of the device tree as it is
-   common to most of the SoC.
 - reg : Specifies base physical address and size of the registers.
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
diff --git a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
index 0e9f09a6a2fe..f4c5d34c4111 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/atmel,aic.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "atmel,<chip>-aic"
   <chip> can be "at91rm9200", "sama5d2", "sama5d3" or "sama5d4"
 - interrupt-controller: Identifies the node as an interrupt controller.
-- interrupt-parent: For single AIC system, it is an empty property.
 - #interrupt-cells: The number of cells to define the interrupts. It should be 3.
   The first cell is the IRQ number (aka "Peripheral IDentifier" on datasheet).
   The second cell is used to specify flags:
@@ -27,7 +26,6 @@ Examples:
 	aic: interrupt-controller@fffff000 {
 		compatible = "atmel,at91rm9200-aic";
 		interrupt-controller;
-		interrupt-parent;
 		#interrupt-cells = <3>;
 		reg = <0xfffff000 0x200>;
 	};
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
index 6428a6ba9f4a..0f1af5a1c12e 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm2835-armctrl-ic.txt
@@ -26,8 +26,6 @@ Required properties:
   are 0..7 for bank 0, and 0..31 for bank 1.
 
 Additional required properties for brcm,bcm2836-armctrl-ic:
-- interrupt-parent : Specifies the parent interrupt controller when this
-  controller is the second level.
 - interrupts : Specifies the interrupt on the parent for this interrupt
   controller to handle.
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt
index 8f48aad50868..37aea40d5430 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm3380-l2-intc.txt
@@ -18,8 +18,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this one is cascaded from
 - interrupts: specifies the interrupt line in the interrupt-parent controller
   node, valid values depend on the type of parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt
index 4040905388d9..2bc19b1ac877 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm6345-l1-intc.txt
@@ -29,8 +29,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller(s)
-  this one is cascaded from
 - interrupts: specifies the interrupt line(s) in the interrupt-parent controller
   node; valid values depend on the type of parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt
index cc217b22dccd..2117d4ac1ae5 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7038-l1-intc.txt
@@ -28,8 +28,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller(s)
-  this one is cascaded from
 - interrupts: specifies the interrupt line(s) in the interrupt-parent controller
   node; valid values depend on the type of parent interrupt controller
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
index 44a9bb15dd56..addd86b6ca2f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,bcm7120-l2-intc.txt
@@ -56,8 +56,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this one is cascaded from
 - interrupts: specifies the interrupt line(s) in the interrupt-parent controller
   node, valid values depend on the type of parent interrupt controller
 - brcm,int-map-mask: 32-bits bit mask describing how many and which interrupts
diff --git a/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt
index 36df06c5c567..d514ec060a4a 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/brcm,l2-intc.txt
@@ -8,8 +8,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an
   interrupt source. Should be 1.
-- interrupt-parent: specifies the phandle to the parent interrupt controller
-  this controller is cacaded from
 - interrupts: specifies the interrupt line in the interrupt-parent irq space
   to be used for cascading
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt b/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt
index a4ff93d6b7f3..454ce04d6787 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/fsl,ls-scfg-msi.txt
@@ -13,9 +13,6 @@ Required properties:
 - reg: physical base address of the controller and length of memory mapped.
 - interrupts: an interrupt to the parent interrupt controller.
 
-Optional properties:
-- interrupt-parent: the phandle to the parent interrupt controller.
-
 This interrupt controller hardware is a second level interrupt controller that
 is hooked to a parent interrupt controller: e.g: ARM GIC for ARM-based
 platforms. If interrupt-parent is not provided, the default parent interrupt
diff --git a/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
index 3b2f4c43ad8d..a6813a071f15 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/hisilicon,mbigen-v2.txt
@@ -68,8 +68,6 @@ Examples:
 
 Devices connect to mbigen required properties:
 ----------------------------------------------------
--interrupt-parent: Specifies the mbigen device node which device connected.
-
 -interrupts:Specifies the interrupt source.
  For the specific information of each cell in this property,please refer to
  the "interrupt-cells" description mentioned above.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
index 5f89fb635a1b..ecebaf19d4fd 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/ingenic,intc.txt
@@ -11,7 +11,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value shall be 1.
-- interrupt-parent : phandle of the CPU interrupt controller.
 - interrupts : Specifies the CPU interrupt the controller is connected to.
 
 Example:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
index 3f6442c7f867..930fb462fd9f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/marvell,odmi-controller.txt
@@ -26,8 +26,6 @@ Required properties:
                          See Documentation/devicetree/bindings/interrupt-controller/arm,gic.txt
                          for details about the GIC Device Tree binding.
 
-- interrupt-parent     : Reference to the parent interrupt controller.
-
 Example:
 
 	odmi: odmi@300000 {
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
index a7efdbc3de5b..5865f4f2c69d 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,cirq.txt
@@ -16,8 +16,6 @@ Required properties:
   and "mediatek,cirq" as a fallback.
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Use the same format as specified by GIC in arm,gic.txt.
-- interrupt-parent: phandle of irq parent for cirq. The parent must
-  use the same interrupt-cells format as GIC.
 - reg: Physical base address of the cirq registers and length of memory
   mapped region.
 - mediatek,ext-irq-range: Identifies external irq number range in different
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
index 07bf0b9a5139..6a32922a55b8 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mediatek,sysirq.txt
@@ -21,8 +21,6 @@ Required properties:
 	"mediatek,mt2701-sysirq", "mediatek,mt6577-sysirq": for MT2701
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Use the same format as specified by GIC in arm,gic.txt.
-- interrupt-parent: phandle of irq parent for sysirq. The parent must
-  use the same interrupt-cells format as GIC.
 - reg: Physical base address of the intpol registers and length of memory
   mapped region. Could be multiple bases here. Ex: mt6797 needs 2 reg, others
   need 1.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt b/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt
index b47a8a02b17b..f5baeccb689f 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/mscc,ocelot-icpu-intr.txt
@@ -7,7 +7,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value shall be 1.
-- interrupt-parent : phandle of the CPU interrupt controller.
 - interrupts : Specifies the CPU interrupt the controller is connected to.
 
 Example:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
index 1099fe0788fa..803d35de9aac 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/nvidia,tegra20-ictlr.txt
@@ -19,8 +19,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value must be 3.
-- interrupt-parent : a phandle to the GIC these interrupts are routed
-  to.
 
 Notes:
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt b/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt
index 38211f344dc8..0bfb3ba55f4c 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/nxp,lpc3220-mic.txt
@@ -14,8 +14,6 @@ Required properties:
   Reset value is IRQ_TYPE_LEVEL_LOW.
 
 Optional properties:
-- interrupt-parent: empty for MIC interrupt controller, link to parent
-  MIC interrupt controller for SIC1 and SIC2
 - interrupts: empty for MIC interrupt controller, cascaded MIC
   hardware interrupts for SIC1 and SIC2
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
index 475ae9bd562b..ad70006c1848 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
@@ -7,7 +7,6 @@ Required Properties:
 - compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc" or
   "qca,<soctype>-cpu-intc", "qca,ar7240-misc-intc"
 - reg: Base address and size of the controllers memory area
-- interrupt-parent: phandle of the parent interrupt controller.
 - interrupts: Interrupt specifier for the controllers interrupt.
 - interrupt-controller : Identifies the node as an interrupt controller
 - #interrupt-cells : Specifies the number of cells needed to encode interrupt
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt
index 0b2c97ddb520..8e0797cb1487 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/qcom,pdc.txt
@@ -35,12 +35,6 @@ Properties:
 		    interrupt.
 		    The second element is the trigger type.
 
-- interrupt-parent:
-	Usage: required
-	Value type: <phandle>
-	Definition: Specifies the interrupt parent necessary for hierarchical
-		    domain to operate.
-
 - interrupt-controller:
 	Usage: required
 	Value type: <bool>
diff --git a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt
index 9e5f73412cd7..19af687858a1 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/samsung,exynos4210-combiner.txt
@@ -32,8 +32,6 @@ Optional properties:
 - samsung,combiner-nr: The number of interrupt combiners supported. If this
   property is not specified, the default number of combiners is assumed
   to be 16.
-- interrupt-parent: pHandle of the parent interrupt controller, if not
-  inherited from the parent node.
 
 
 Example:
diff --git a/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
index 1f441fa0ad40..355c18a3a4d3 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/sigma,smp8642-intc.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: should be "sigma,smp8642-intc"
 - reg: physical address of MMIO region
 - ranges: address space mapping of child nodes
-- interrupt-parent: phandle of parent interrupt controller
 - interrupt-controller: boolean
 - #address-cells: should be <1>
 - #size-cells: should be <1>
diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
index 8b46a34e05f1..09fc02b99845 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/snps,archs-idu-intc.txt
@@ -7,7 +7,6 @@ Properties:
 
 - compatible: "snps,archs-idu-intc"
 - interrupt-controller: This is an interrupt controller.
-- interrupt-parent: <reference to parent core intc>
 - #interrupt-cells: Must be <1>.
 
   Value of the cell specifies the "common" IRQ from peripheral to IDU. Number N
diff --git a/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt b/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt
index 492911744ca3..086ff08322db 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/snps,dw-apb-ictl.txt
@@ -11,7 +11,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: number of cells to encode an interrupt-specifier, shall be 1
 - interrupts: interrupt reference to primary interrupt controller
-- interrupt-parent: (optional) reference specific primary interrupt controller
 
 The interrupt sources map to the corresponding bits in the interrupt
 registers, i.e.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt b/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt
index 8b2faefe29ca..dac0846fe789 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/socionext,synquacer-exiu.txt
@@ -12,7 +12,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells     : Specifies the number of cells needed to encode an
                          interrupt source. The value must be 3.
-- interrupt-parent     : phandle of the GIC these interrupts are routed to.
 - socionext,spi-base   : The SPI number of the first SPI of the 32 adjacent
                          ones the EXIU forwards its interrups to.
 
diff --git a/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt b/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
index 2ab0ea39867b..a407c499b3cc 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/st,spear3xx-shirq.txt
@@ -31,10 +31,6 @@ Required properties:
     parent) is equal to number of groups. The format of the interrupt
     specifier depends in the interrupt parent controller.
 
-  Optional properties:
-  - interrupt-parent: pHandle of the parent interrupt controller, if not
-    inherited from the parent node.
-
 Example:
 
 The following is an example from the SPEAr320 SoC dtsi file.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
index 7f15f1b0325b..341ae5909333 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/technologic,ts4800.txt
@@ -11,6 +11,4 @@ Required properties:
   region
 - #interrupt-cells: specifies the number of cells needed to encode an interrupt
   source, should be 1.
-- interrupt-parent: phandle to the parent interrupt controller this one is
-  cascaded from
 - interrupts: specifies the interrupt line in the interrupt-parent controller
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt b/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt
index 42bb796cc4ad..ee3f9c351501 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,c64x+megamod-pic.txt
@@ -46,7 +46,6 @@ C6X Interrupt Chips
   - interrupt-controller
   - #interrupt-cells: <1>
   - reg: base address and size of register area
-  - interrupt-parent: must be core interrupt controller
   - interrupts: This should have four cells; one for each interrupt combiner.
                 The cells contain the core priority interrupt to which the
                 corresponding combiner output is wired.
diff --git a/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu b/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu
index 18d4f407bf0e..422d6908f8b2 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu
+++ b/Documentation/devicetree/bindings/interrupt-controller/ti,omap4-wugen-mpu
@@ -12,8 +12,6 @@ Required properties:
 - interrupt-controller : Identifies the node as an interrupt controller.
 - #interrupt-cells : Specifies the number of cells needed to encode an
   interrupt source. The value must be 3.
-- interrupt-parent : a phandle to the GIC these interrupts are routed
-  to.
 
 Notes:
 
diff --git a/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt b/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
index b1682c80b490..525ec82615a6 100644
--- a/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
+++ b/Documentation/devicetree/bindings/iommu/samsung,sysmmu.txt
@@ -31,7 +31,6 @@ Required properties:
 - compatible: Should be "samsung,exynos-sysmmu"
 - reg: A tuple of base address and size of System MMU registers.
 - #iommu-cells: Should be <0>.
-- interrupt-parent: The phandle of the interrupt controller of System MMU
 - interrupts: An interrupt specifier for interrupt signal of System MMU,
 	      according to the format defined by a particular interrupt
 	      controller.
diff --git a/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt b/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
index 49cfc8c337c4..c4dd93f1fed2 100644
--- a/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
+++ b/Documentation/devicetree/bindings/mailbox/altera-mailbox.txt
@@ -9,7 +9,6 @@ Required properties:
 		of cells required for the mailbox specifier. Should be 1.
 
 Optional properties:
-- interrupt-parent :	interrupt source phandle.
 - interrupts :		interrupt number. The interrupt specifier format
 			depends on the interrupt controller parent.
 
diff --git a/Documentation/devicetree/bindings/media/i2c/tc358743.txt b/Documentation/devicetree/bindings/media/i2c/tc358743.txt
index 49f8bcc2ea4d..59102edcf01e 100644
--- a/Documentation/devicetree/bindings/media/i2c/tc358743.txt
+++ b/Documentation/devicetree/bindings/media/i2c/tc358743.txt
@@ -12,7 +12,7 @@ Required Properties:
 Optional Properties:
 
 - reset-gpios: gpio phandle GPIO connected to the reset pin
-- interrupts, interrupt-parent: GPIO connected to the interrupt pin
+- interrupts: GPIO connected to the interrupt pin
 - data-lanes: should be <1 2 3 4> for four-lane operation,
 	      or <1 2> for two-lane operation
 - clock-lanes: should be <0>
diff --git a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt b/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
index 17a8e81ca0cc..cfa4ffada8ae 100644
--- a/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
+++ b/Documentation/devicetree/bindings/media/sh_mobile_ceu.txt
@@ -2,7 +2,6 @@ Bindings, specific for the sh_mobile_ceu_camera.c driver:
  - compatible: Should be "renesas,sh-mobile-ceu"
  - reg: register base and size
  - interrupts: the interrupt number
- - interrupt-parent: the interrupt controller
  - renesas,max-width: maximum image width, supported on this SoC
  - renesas,max-height: maximum image height, supported on this SoC
 
diff --git a/Documentation/devicetree/bindings/mfd/ac100.txt b/Documentation/devicetree/bindings/mfd/ac100.txt
index b8ef00667599..dff219f07493 100644
--- a/Documentation/devicetree/bindings/mfd/ac100.txt
+++ b/Documentation/devicetree/bindings/mfd/ac100.txt
@@ -10,7 +10,6 @@ Required properties:
 - sub-nodes:
   - codec
     - compatible:		"x-powers,ac100-codec"
-    - interrupt-parent:		The parent interrupt controller
     - interrupts:		SoC NMI / GPIO interrupt connected to the
     				IRQ_AUDIO pin
     - #clock-cells:		Shall be 0
@@ -20,9 +19,6 @@ Required properties:
 
   - rtc
     - compatible:		"x-powers,ac100-rtc"
-    - interrupt-parent:		The parent interrupt controller
-    - interrupts:		SoC NMI / GPIO interrupt connected to the
-    				IRQ_RTC pin
     - clocks:			A phandle to the codec's "4M_adda" clock
     - #clock-cells:		Shall be 1
     - clock-output-names:	"cko1_rtc", "cko2_rtc", "cko3_rtc"
diff --git a/Documentation/devicetree/bindings/mfd/altera-a10sr.txt b/Documentation/devicetree/bindings/mfd/altera-a10sr.txt
index c8a736554b4b..a688520dd87d 100644
--- a/Documentation/devicetree/bindings/mfd/altera-a10sr.txt
+++ b/Documentation/devicetree/bindings/mfd/altera-a10sr.txt
@@ -5,7 +5,6 @@ Required parent device properties:
 - spi-max-frequency	: Maximum SPI frequency.
 - reg			: The SPI Chip Select address for the Arria10
 			  System Resource chip
-- interrupt-parent	: The parent interrupt controller.
 - interrupts		: The interrupt line the device is connected to.
 - interrupt-controller	: Marks the device node as an interrupt controller.
 - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/arizona.txt b/Documentation/devicetree/bindings/mfd/arizona.txt
index a014afb07902..9b62831fdf3e 100644
--- a/Documentation/devicetree/bindings/mfd/arizona.txt
+++ b/Documentation/devicetree/bindings/mfd/arizona.txt
@@ -22,7 +22,6 @@ Required properties:
     connected to.
   - interrupt-controller : Arizona class devices contain interrupt controllers
     and may provide interrupt services to other devices.
-  - interrupt-parent : The parent interrupt controller.
   - #interrupt-cells: the number of cells to describe an IRQ, this should be 2.
     The first cell is the IRQ number.
     The second cell is the flags, encoded as the trigger masks from
diff --git a/Documentation/devicetree/bindings/mfd/axp20x.txt b/Documentation/devicetree/bindings/mfd/axp20x.txt
index d1762f3b30af..62091f6b025e 100644
--- a/Documentation/devicetree/bindings/mfd/axp20x.txt
+++ b/Documentation/devicetree/bindings/mfd/axp20x.txt
@@ -28,7 +28,6 @@ Required properties:
     * "x-powers,axp809"
     * "x-powers,axp813"
 - reg: The I2C slave address or RSB hardware address for the AXP chip
-- interrupt-parent: The parent interrupt controller
 - interrupts: SoC NMI / GPIO interrupt connected to the PMIC's IRQ pin
 - interrupt-controller: The PMIC has its own internal IRQs
 - #interrupt-cells: Should be set to 1
diff --git a/Documentation/devicetree/bindings/mfd/bd9571mwv.txt b/Documentation/devicetree/bindings/mfd/bd9571mwv.txt
index 25d1f697eb25..8c4678650d1a 100644
--- a/Documentation/devicetree/bindings/mfd/bd9571mwv.txt
+++ b/Documentation/devicetree/bindings/mfd/bd9571mwv.txt
@@ -3,7 +3,6 @@
 Required properties:
  - compatible		: Should be "rohm,bd9571mwv".
  - reg			: I2C slave address.
- - interrupt-parent	: Phandle to the parent interrupt controller.
  - interrupts		: The interrupt line the device is connected to.
  - interrupt-controller	: Marks the device node as an interrupt controller.
  - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/bfticu.txt b/Documentation/devicetree/bindings/mfd/bfticu.txt
index 65c90776c620..538192fda9ae 100644
--- a/Documentation/devicetree/bindings/mfd/bfticu.txt
+++ b/Documentation/devicetree/bindings/mfd/bfticu.txt
@@ -10,7 +10,6 @@ Required properties:
 - interrupts: the main IRQ line to signal the collected IRQs
 - #interrupt-cells : is 2 and their usage is compliant to the 2 cells variant
   of Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
-- interrupt-parent: the parent IRQ ctrl the main IRQ is connected to
 - reg: access on the parent local bus (chip select, offset in chip select, size)
 
 Example:
diff --git a/Documentation/devicetree/bindings/mfd/da9055.txt b/Documentation/devicetree/bindings/mfd/da9055.txt
index 6dab34d34fce..131a53283e17 100644
--- a/Documentation/devicetree/bindings/mfd/da9055.txt
+++ b/Documentation/devicetree/bindings/mfd/da9055.txt
@@ -22,8 +22,6 @@ Documentation/devicetree/bindings/sound/da9055.txt
 Required properties:
 - compatible : Should be "dlg,da9055-pmic"
 - reg: Specifies the I2C slave address (defaults to 0x5a but can be modified)
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the IRQs from da9055 are delivered to.
 - interrupts: IRQ line info for da9055 chip.
 - interrupt-controller: da9055 has internal IRQs (has own IRQ domain).
 - #interrupt-cells: Should be 1, is the local IRQ number for da9055.
diff --git a/Documentation/devicetree/bindings/mfd/da9062.txt b/Documentation/devicetree/bindings/mfd/da9062.txt
index c0a418c27e9d..edca653a5777 100644
--- a/Documentation/devicetree/bindings/mfd/da9062.txt
+++ b/Documentation/devicetree/bindings/mfd/da9062.txt
@@ -32,8 +32,6 @@ Required properties:
     "dlg,da9061" for DA9061
 - reg : Specifies the I2C slave address (this defaults to 0x58 but it can be
   modified to match the chip's OTP settings).
-- interrupt-parent : Specifies the reference to the interrupt controller for
-  the DA9062 or DA9061.
 - interrupts : IRQ line information.
 - interrupt-controller
 
diff --git a/Documentation/devicetree/bindings/mfd/da9063.txt b/Documentation/devicetree/bindings/mfd/da9063.txt
index 443e68286957..8da879935c59 100644
--- a/Documentation/devicetree/bindings/mfd/da9063.txt
+++ b/Documentation/devicetree/bindings/mfd/da9063.txt
@@ -16,8 +16,6 @@ Required properties:
 - compatible : Should be "dlg,da9063" or "dlg,da9063l"
 - reg : Specifies the I2C slave address (this defaults to 0x58 but it can be
   modified to match the chip's OTP settings).
-- interrupt-parent : Specifies the reference to the interrupt controller for
-  the DA9063.
 - interrupts : IRQ line information.
 - interrupt-controller
 
diff --git a/Documentation/devicetree/bindings/mfd/da9150.txt b/Documentation/devicetree/bindings/mfd/da9150.txt
index fd4dca7f4aba..f09b41fbdf47 100644
--- a/Documentation/devicetree/bindings/mfd/da9150.txt
+++ b/Documentation/devicetree/bindings/mfd/da9150.txt
@@ -13,8 +13,6 @@ da9150-fg		: Battery Fuel-Gauge
 Required properties:
 - compatible : Should be "dlg,da9150"
 - reg: Specifies the I2C slave address
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the IRQs from da9150 are delivered to.
 - interrupts: IRQ line info for da9150 chip.
 - interrupt-controller: da9150 has internal IRQs (own IRQ domain).
   (See ../interrupt-controller/interrupts.txt for
diff --git a/Documentation/devicetree/bindings/mfd/max14577.txt b/Documentation/devicetree/bindings/mfd/max14577.txt
index 236264c10b92..fc6f0f4e8beb 100644
--- a/Documentation/devicetree/bindings/mfd/max14577.txt
+++ b/Documentation/devicetree/bindings/mfd/max14577.txt
@@ -11,7 +11,6 @@ Required properties:
 - compatible : Must be "maxim,max14577" or "maxim,max77836".
 - reg : I2C slave address for the max14577 chip (0x25 for max14577/max77836)
 - interrupts : IRQ line for the chip.
-- interrupt-parent :  The parent interrupt controller.
 
 
 Required nodes:
diff --git a/Documentation/devicetree/bindings/mfd/max77686.txt b/Documentation/devicetree/bindings/mfd/max77686.txt
index 0f2587fa42cb..42968b7144e0 100644
--- a/Documentation/devicetree/bindings/mfd/max77686.txt
+++ b/Documentation/devicetree/bindings/mfd/max77686.txt
@@ -15,7 +15,6 @@ Required properties:
 - compatible : Must be "maxim,max77686";
 - reg : Specifies the i2c slave address of PMIC block.
 - interrupts : This i2c device has an IRQ line connected to the main SoC.
-- interrupt-parent : The parent interrupt controller.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/max77693.txt b/Documentation/devicetree/bindings/mfd/max77693.txt
index e6754974a745..a3c60a7a3be1 100644
--- a/Documentation/devicetree/bindings/mfd/max77693.txt
+++ b/Documentation/devicetree/bindings/mfd/max77693.txt
@@ -14,7 +14,6 @@ Required properties:
 - compatible : Must be "maxim,max77693".
 - reg : Specifies the i2c slave address of PMIC block.
 - interrupts : This i2c device has an IRQ line connected to the main SoC.
-- interrupt-parent :  The parent interrupt controller.
 
 Optional properties:
 - regulators : The regulators of max77693 have to be instantiated under subnode
diff --git a/Documentation/devicetree/bindings/mfd/max77802.txt b/Documentation/devicetree/bindings/mfd/max77802.txt
index f2f3fe75901c..09decac20d91 100644
--- a/Documentation/devicetree/bindings/mfd/max77802.txt
+++ b/Documentation/devicetree/bindings/mfd/max77802.txt
@@ -14,7 +14,6 @@ Required properties:
 - compatible		: Must be "maxim,max77802"
 - reg			: Specifies the I2C slave address of PMIC block.
 - interrupts		: I2C device IRQ line connected to the main SoC.
-- interrupt-parent	: The parent interrupt controller.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/max8998.txt b/Documentation/devicetree/bindings/mfd/max8998.txt
index 23a3650ff2a2..5f2f07c09c90 100644
--- a/Documentation/devicetree/bindings/mfd/max8998.txt
+++ b/Documentation/devicetree/bindings/mfd/max8998.txt
@@ -20,8 +20,6 @@ Required properties:
 - reg: Specifies the i2c slave address of the pmic block. It should be 0x66.
 
 Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from MAX8998 are routed to.
 - interrupts: Interrupt specifiers for two interrupt sources.
   - First interrupt specifier is for main interrupt.
   - Second interrupt specifier is for power-on/-off interrupt.
diff --git a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
index c639705a98ef..5ddcc8f4febc 100644
--- a/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
+++ b/Documentation/devicetree/bindings/mfd/motorola-cpcap.txt
@@ -3,7 +3,6 @@ Motorola CPCAP PMIC device tree binding
 Required properties:
 - compatible		: One or both of "motorola,cpcap" or "ste,6556002"
 - reg			: SPI chip select
-- interrupt-parent	: The parent interrupt controller
 - interrupts		: The interrupt line the device is connected to
 - interrupt-controller	: Marks the device node as an interrupt controller
 - #interrupt-cells	: The number of cells to describe an IRQ, should be 2
diff --git a/Documentation/devicetree/bindings/mfd/palmas.txt b/Documentation/devicetree/bindings/mfd/palmas.txt
index 8ae1a32bfb7e..e736ab3012a6 100644
--- a/Documentation/devicetree/bindings/mfd/palmas.txt
+++ b/Documentation/devicetree/bindings/mfd/palmas.txt
@@ -25,7 +25,6 @@ and also the generic series names
   The first cell is the IRQ number.
   The second cell is the flags, encoded as the trigger masks from
   Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
-- interrupt-parent : The parent interrupt controller.
 
 Optional properties:
   ti,mux-padX : set the pad register X (1-2) to the correct muxing for the
diff --git a/Documentation/devicetree/bindings/mfd/retu.txt b/Documentation/devicetree/bindings/mfd/retu.txt
index 876242394a16..df3005dd3e3c 100644
--- a/Documentation/devicetree/bindings/mfd/retu.txt
+++ b/Documentation/devicetree/bindings/mfd/retu.txt
@@ -9,7 +9,6 @@ Required properties:
 - compatible:		"nokia,retu" or "nokia,tahvo"
 - reg:			Specifies the CBUS slave address of the ASIC chip
 - interrupts: 		The interrupt line the device is connected to
-- interrupt-parent:	The parent interrupt controller
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mfd/rk808.txt b/Documentation/devicetree/bindings/mfd/rk808.txt
index 91b65227afeb..1683ec3245bc 100644
--- a/Documentation/devicetree/bindings/mfd/rk808.txt
+++ b/Documentation/devicetree/bindings/mfd/rk808.txt
@@ -10,7 +10,6 @@ Required properties:
 - compatible: "rockchip,rk808"
 - compatible: "rockchip,rk818"
 - reg: I2C slave address
-- interrupt-parent: The parent interrupt controller.
 - interrupts: the interrupt outputs of the controller.
 - #clock-cells: from common clock binding; shall be set to 1 (multiple clock
   outputs). See <dt-bindings/clock/rockchip,rk808.h> for clock IDs.
diff --git a/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
index cdd079bfc287..c68cdd365153 100644
--- a/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
+++ b/Documentation/devicetree/bindings/mfd/samsung,sec-core.txt
@@ -31,8 +31,6 @@ Required properties:
  - reg: Specifies the I2C slave address of the pmic block. It should be 0x66.
 
 Optional properties:
- - interrupt-parent: Specifies the phandle of the interrupt controller to which
-   the interrupts from s2mps11 are delivered to.
  - interrupts: Interrupt specifiers for interrupt sources.
  - samsung,s2mps11-wrstbi-ground: Indicates that WRSTBI pin of PMIC is pulled
    down. When the system is suspended it will always go down thus triggerring
diff --git a/Documentation/devicetree/bindings/mfd/stmpe.txt b/Documentation/devicetree/bindings/mfd/stmpe.txt
index f9065a5781a2..c797c05cd3c2 100644
--- a/Documentation/devicetree/bindings/mfd/stmpe.txt
+++ b/Documentation/devicetree/bindings/mfd/stmpe.txt
@@ -10,7 +10,6 @@ Required properties:
 Optional properties:
  - interrupts                   : The interrupt outputs from the controller
  - interrupt-controller         : Marks the device node as an interrupt controller
- - interrupt-parent             : Specifies which IRQ controller we're connected to
  - wakeup-source                : Marks the input device as wakable
  - st,autosleep-timeout         : Valid entries (ms); 4, 16, 32, 64, 128, 256, 512 and 1024
  - irq-gpio                     : If present, which GPIO to use for event IRQ
diff --git a/Documentation/devicetree/bindings/mfd/tc3589x.txt b/Documentation/devicetree/bindings/mfd/tc3589x.txt
index 23fc2f21f5a4..4f22b2b07dc5 100644
--- a/Documentation/devicetree/bindings/mfd/tc3589x.txt
+++ b/Documentation/devicetree/bindings/mfd/tc3589x.txt
@@ -15,7 +15,6 @@ Required properties:
  - compatible : must be "toshiba,tc35890", "toshiba,tc35892", "toshiba,tc35893",
    "toshiba,tc35894", "toshiba,tc35895" or "toshiba,tc35896"
  - reg : I2C address of the device
- - interrupt-parent : specifies which IRQ controller we're connected to
  - interrupts : the interrupt on the parent the controller is connected to
  - interrupt-controller : marks the device node as an interrupt controller
  - #interrupt-cells : should be <1>, the first cell is the IRQ offset on this
diff --git a/Documentation/devicetree/bindings/mfd/tps65086.txt b/Documentation/devicetree/bindings/mfd/tps65086.txt
index 9cfa886fe99f..67eac0ed32df 100644
--- a/Documentation/devicetree/bindings/mfd/tps65086.txt
+++ b/Documentation/devicetree/bindings/mfd/tps65086.txt
@@ -3,7 +3,6 @@
 Required properties:
  - compatible		: Should be "ti,tps65086".
  - reg			: I2C slave address.
- - interrupt-parent	: Phandle to the parent interrupt controller.
  - interrupts		: The interrupt line the device is connected to.
  - interrupt-controller	: Marks the device node as an interrupt controller.
  - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/tps65912.txt b/Documentation/devicetree/bindings/mfd/tps65912.txt
index 717e66d23142..8becb183a48e 100644
--- a/Documentation/devicetree/bindings/mfd/tps65912.txt
+++ b/Documentation/devicetree/bindings/mfd/tps65912.txt
@@ -3,7 +3,6 @@
 Required properties:
  - compatible		: Should be "ti,tps65912".
  - reg			: Slave address or chip select number (I2C / SPI).
- - interrupt-parent	: The parent interrupt controller.
  - interrupts		: The interrupt line the device is connected to.
  - interrupt-controller	: Marks the device node as an interrupt controller.
  - #interrupt-cells	: The number of cells to describe an IRQ, should be 2.
diff --git a/Documentation/devicetree/bindings/mfd/twl-familly.txt b/Documentation/devicetree/bindings/mfd/twl-familly.txt
index a66fcf946759..56f244b5d8a4 100644
--- a/Documentation/devicetree/bindings/mfd/twl-familly.txt
+++ b/Documentation/devicetree/bindings/mfd/twl-familly.txt
@@ -16,7 +16,6 @@ Required properties:
 - interrupt-controller : Since the twl support several interrupts internally,
   it is considered as an interrupt controller cascaded to the SoC one.
 - #interrupt-cells = <1>;
-- interrupt-parent : The parent interrupt controller.
 
 Optional node:
 - Child nodes contain in the twl. The twl family is made of several variants
diff --git a/Documentation/devicetree/bindings/mfd/twl6040.txt b/Documentation/devicetree/bindings/mfd/twl6040.txt
index 9a98ee7c323d..06e9dd7a0d96 100644
--- a/Documentation/devicetree/bindings/mfd/twl6040.txt
+++ b/Documentation/devicetree/bindings/mfd/twl6040.txt
@@ -9,7 +9,6 @@ Required properties:
 - compatible : "ti,twl6040" for twl6040, "ti,twl6041" for twl6041
 - reg: must be 0x4b for i2c address
 - interrupts: twl6040 has one interrupt line connecteded to the main SoC
-- interrupt-parent: The parent interrupt controller
 - gpio-controller:
 - #gpio-cells = <1>: twl6040 provides GPO lines.
 - #clock-cells = <0>; twl6040 is a provider of pdmclk which is used by McPDM
diff --git a/Documentation/devicetree/bindings/mfd/wm831x.txt b/Documentation/devicetree/bindings/mfd/wm831x.txt
index 505709403d3f..6b84b1b0d018 100644
--- a/Documentation/devicetree/bindings/mfd/wm831x.txt
+++ b/Documentation/devicetree/bindings/mfd/wm831x.txt
@@ -22,7 +22,6 @@ Required properties:
 
   - interrupts : The interrupt line the IRQ signal for the device is
     connected to.
-  - interrupt-parent : The parent interrupt controller.
 
   - interrupt-controller : wm831x devices contain interrupt controllers and
     may provide interrupt services to other devices.
diff --git a/Documentation/devicetree/bindings/mips/cavium/cib.txt b/Documentation/devicetree/bindings/mips/cavium/cib.txt
index f39a1aa2852b..410efa322254 100644
--- a/Documentation/devicetree/bindings/mips/cavium/cib.txt
+++ b/Documentation/devicetree/bindings/mips/cavium/cib.txt
@@ -13,8 +13,6 @@ Properties:
 - cavium,max-bits: The index (zero based) of the highest numbered bit
   in the CIB block.
 
-- interrupt-parent:  Always the CIU on the SoC.
-
 - interrupts: The CIU line to which the CIB block is connected.
 
 - #interrupt-cells: Must be <2>.  The first cell is the bit within the
diff --git a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
index 60481bfc3d31..5f3c02522c17 100644
--- a/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/arasan,sdhci.txt
@@ -19,8 +19,6 @@ Required Properties:
   - clocks: From clock bindings: Handles to clock inputs.
   - clock-names: From clock bindings: Tuple including "clk_xin" and "clk_ahb"
   - interrupts: Interrupt specifier
-  - interrupt-parent: Phandle for the interrupt controller that services
-		      interrupts for this device.
 
 Required Properties for "arasan,sdhci-5.1":
   - phys: From PHY bindings: Phandle for the Generic PHY for arasan.
diff --git a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
index a2cf5e1c87d8..99c5cf8507e8 100644
--- a/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
+++ b/Documentation/devicetree/bindings/mmc/fsl-esdhc.txt
@@ -21,7 +21,6 @@ Required properties:
 	"fsl,ls1043a-esdhc"
 	"fsl,ls1046a-esdhc"
 	"fsl,ls2080a-esdhc"
-  - interrupt-parent : interrupt source phandle.
   - clock-frequency : specifies eSDHC base clock frequency.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt
index 0e5e2ec4001d..75486cca8054 100644
--- a/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt
+++ b/Documentation/devicetree/bindings/mmc/mmc-spi-slot.txt
@@ -13,8 +13,6 @@ Optional properties:
 - gpios : may specify GPIOs in this order: Card-Detect GPIO,
   Write-Protect GPIO. Note that this does not follow the
   binding from mmc.txt, for historical reasons.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
index b40f3a492800..bcda1dfc4bac 100644
--- a/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
+++ b/Documentation/devicetree/bindings/mtd/brcm,brcmnand.txt
@@ -42,7 +42,6 @@ Required properties:
                      May be "nand", if the SoC has the individual NAND
                      interrupts multiplexed behind another custom piece of
                      hardware
-- interrupt-parent : See standard interrupt bindings
 - #address-cells   : <1> - subnodes give the chip-select number
 - #size-cells      : <0>
 
diff --git a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
index dd559045593d..c059ab74ed88 100644
--- a/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
+++ b/Documentation/devicetree/bindings/mtd/gpmc-nand.txt
@@ -16,7 +16,6 @@ Required properties:
  - compatible:	"ti,omap2-nand"
  - reg:		range id (CS number), base offset and length of the
 		NAND I/O space
- - interrupt-parent: must point to gpmc node
  - interrupts:	Two interrupt specifiers, one for fifoevent, one for termcount.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/mtd/spear_smi.txt b/Documentation/devicetree/bindings/mtd/spear_smi.txt
index 7248aadd89e4..c41873e92d26 100644
--- a/Documentation/devicetree/bindings/mtd/spear_smi.txt
+++ b/Documentation/devicetree/bindings/mtd/spear_smi.txt
@@ -5,8 +5,6 @@ Required properties:
 - reg : Address range of the mtd chip
 - #address-cells, #size-cells : Must be present if the device has sub-nodes
   representing partitions.
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the STMMAC interrupts
 - clock-rate : Functional clock rate of SMI in Hz
 
diff --git a/Documentation/devicetree/bindings/net/amd-xgbe.txt b/Documentation/devicetree/bindings/net/amd-xgbe.txt
index 4bb624a73b54..93dcb79a5f16 100644
--- a/Documentation/devicetree/bindings/net/amd-xgbe.txt
+++ b/Documentation/devicetree/bindings/net/amd-xgbe.txt
@@ -8,8 +8,6 @@ Required properties:
    - SerDes Rx/Tx registers
    - SerDes integration registers (1/2)
    - SerDes integration registers (2/2)
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the amd-xgbe interrupt(s). The first interrupt
   listed is required and is the general device interrupt. If the optional
   amd,per-channel-interrupt property is specified, then one additional
diff --git a/Documentation/devicetree/bindings/net/btusb.txt b/Documentation/devicetree/bindings/net/btusb.txt
index 9c5e663fa1af..37d67926dd6d 100644
--- a/Documentation/devicetree/bindings/net/btusb.txt
+++ b/Documentation/devicetree/bindings/net/btusb.txt
@@ -15,7 +15,6 @@ Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
 
 Optional properties:
 
-  - interrupt-parent: phandle of the parent interrupt controller
   - interrupt-names: (see below)
   - interrupts : The interrupt specified by the name "wakeup" is the interrupt
 		 that shall be used for out-of-band wake-on-bt. Driver will
diff --git a/Documentation/devicetree/bindings/net/can/holt_hi311x.txt b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
index 23aa94eab207..903a78da65be 100644
--- a/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
+++ b/Documentation/devicetree/bindings/net/can/holt_hi311x.txt
@@ -5,7 +5,6 @@ Required properties:
    - "holt,hi3110" for HI-3110
  - reg: SPI chip select.
  - clocks: The clock feeding the CAN controller.
- - interrupt-parent: The parent interrupt controller.
  - interrupts: Should contain IRQ line for the CAN controller.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
index ee3723beb701..188c8bd4eb67 100644
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251x.txt
@@ -6,7 +6,6 @@ Required properties:
    - "microchip,mcp2515" for MCP2515.
  - reg: SPI chip select.
  - clocks: The clock feeding the CAN controller.
- - interrupt-parent: The parent interrupt controller.
  - interrupts: Should contain IRQ line for the CAN controller.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/net/can/xilinx_can.txt b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
index fe38847d8e26..9264d2f6a89d 100644
--- a/Documentation/devicetree/bindings/net/can/xilinx_can.txt
+++ b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
@@ -9,7 +9,6 @@ Required properties:
 			  CANPS registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller
 - clock-names		: List of input clock names - "can_clk", "pclk"
 			  (For CANPS), "can_clk" , "s_axi_aclk"(For AXI CAN)
 			  (See clock bindings for details).
diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt
index 4cb4925a28ab..41089369f891 100644
--- a/Documentation/devicetree/bindings/net/cpsw.txt
+++ b/Documentation/devicetree/bindings/net/cpsw.txt
@@ -11,7 +11,6 @@ Required properties:
 			  registers map
 - interrupts		: property with a value describing the interrupt
 			  number
-- interrupt-parent	: The parent interrupt controller
 - cpdma_channels 	: Specifies number of channels in CPDMA
 - ale_entries		: Specifies No of entries ALE can hold
 - bd_ram_size		: Specifies internal descriptor RAM size
diff --git a/Documentation/devicetree/bindings/net/davicom-dm9000.txt b/Documentation/devicetree/bindings/net/davicom-dm9000.txt
index 5224bf05f6f8..64c159e9cbf7 100644
--- a/Documentation/devicetree/bindings/net/davicom-dm9000.txt
+++ b/Documentation/devicetree/bindings/net/davicom-dm9000.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg : physical addresses and sizes of registers, must contain 2 entries:
     first entry : address register,
     second entry : data register.
-- interrupt-parent : interrupt controller to which the device is connected
 - interrupts : interrupt specifier specific to interrupt controller
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/net/dsa/marvell.txt b/Documentation/devicetree/bindings/net/dsa/marvell.txt
index 60d50a2b0323..feb007af13cb 100644
--- a/Documentation/devicetree/bindings/net/dsa/marvell.txt
+++ b/Documentation/devicetree/bindings/net/dsa/marvell.txt
@@ -30,7 +30,6 @@ Required properties:
 Optional properties:
 
 - reset-gpios		: Should be a gpio specifier for a reset line
-- interrupt-parent	: Parent interrupt controller
 - interrupts		: Interrupt from the switch
 - interrupt-controller	: Indicates the switch is itself an interrupt
 			  controller. This is used for the PHY interrupts.
diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
index abfbeecbcf39..8ee4b1cedae8 100644
--- a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
+++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt
@@ -9,7 +9,6 @@ Required properties:
 		"6port-16rss",
 		"6port-16vf",
 		"single-port".
-- interrupt-parent: the interrupt parent of this device.
 - interrupts: should contain the DSA Fabric and rcb interrupt.
 - reg: specifies base physical address(es) and size of the device registers.
   The first region is external interface control register base and size(optional,
diff --git a/Documentation/devicetree/bindings/net/ibm,emac.txt b/Documentation/devicetree/bindings/net/ibm,emac.txt
index 44b842b6ca15..c0c14aa3f97c 100644
--- a/Documentation/devicetree/bindings/net/ibm,emac.txt
+++ b/Documentation/devicetree/bindings/net/ibm,emac.txt
@@ -18,7 +18,6 @@
 			  "ibm,emac4".  For Axon, thus, we have: "ibm,emac-axon",
 			  "ibm,emac4"
     - interrupts        : <interrupt mapping for EMAC IRQ and WOL IRQ>
-    - interrupt-parent  : optional, if needed for interrupt mapping
     - reg               : <registers mapping>
     - local-mac-address : 6 bytes, MAC address
     - mal-device        : phandle of the associated McMAL node
diff --git a/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt b/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
index 3d27c68613a6..957e5e5c2927 100644
--- a/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
+++ b/Documentation/devicetree/bindings/net/marvell-bt-8xxx.txt
@@ -22,7 +22,6 @@ Optional properties:
   - marvell,wakeup-gap-ms: wakeup gap represents wakeup latency of the host
 		      platform. The value will be configured to firmware. This
 		      is needed to work chip's sleep feature as expected (u16).
-  - interrupt-parent: phandle of the parent interrupt controller
   - interrupt-names: Used only for USB based devices (See below)
   - interrupts : specifies the interrupt pin number to the cpu. For SDIO, the
 		 driver will use the first interrupt specified in the interrupt
diff --git a/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt b/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
index aa6313024176..358fed2fab43 100644
--- a/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
+++ b/Documentation/devicetree/bindings/net/mediatek,mt7620-gsw.txt
@@ -6,8 +6,6 @@ The mediatek gigabit switch can be found on Mediatek SoCs (mt7620, mt7621).
 Required properties:
 - compatible: Should be "mediatek,mt7620-gsw" or "mediatek,mt7621-gsw"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the gigabit switches interrupt
 - resets: Should contain the gigabit switches resets
 - reset-names: Should contain the reset names "gsw"
diff --git a/Documentation/devicetree/bindings/net/mediatek-net.txt b/Documentation/devicetree/bindings/net/mediatek-net.txt
index 53c13ee384a4..503f2b9194e2 100644
--- a/Documentation/devicetree/bindings/net/mediatek-net.txt
+++ b/Documentation/devicetree/bindings/net/mediatek-net.txt
@@ -30,9 +30,6 @@ Required properties:
 - mediatek,pctl: phandle to the syscon node that handles the ports slew rate
 	and driver current: only for MT2701 and MT7623 SoC
 
-Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 * Ethernet MAC node
 
 Required properties:
diff --git a/Documentation/devicetree/bindings/net/microchip,enc28j60.txt b/Documentation/devicetree/bindings/net/microchip,enc28j60.txt
index 44dff53d4dda..24626e082b83 100644
--- a/Documentation/devicetree/bindings/net/microchip,enc28j60.txt
+++ b/Documentation/devicetree/bindings/net/microchip,enc28j60.txt
@@ -8,9 +8,6 @@ the SPI master node.
 Required properties:
 - compatible: Should be "microchip,enc28j60"
 - reg: Specify the SPI chip select the ENC28J60 is wired to
-- interrupt-parent: Specify the phandle of the source interrupt, see interrupt
-                    binding documentation for details. Usually this is the GPIO bank
-                    the interrupt line is wired to.
 - interrupts: Specify the interrupt index within the interrupt controller (referred
               to above in interrupt-parent) and interrupt type. The ENC28J60 natively
               generates falling edge interrupts, however, additional board logic
diff --git a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt
index 92486733df71..cfaf88998918 100644
--- a/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt
+++ b/Documentation/devicetree/bindings/net/nfc/nxp-nci.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "nxp,nxp-nci-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - enable-gpios: Output GPIO pin used for enabling/disabling the chip
 - firmware-gpios: Output GPIO pin used to enter firmware download mode
diff --git a/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt b/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt
index 122460e42e3c..2efe3886b95b 100644
--- a/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt
+++ b/Documentation/devicetree/bindings/net/nfc/pn533-i2c.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "nxp,pn532-i2c" or "nxp,pn533-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 
 Optional SoC Specific Properties:
diff --git a/Documentation/devicetree/bindings/net/nfc/pn544.txt b/Documentation/devicetree/bindings/net/nfc/pn544.txt
index 538a86f7b2b0..5b937403fed6 100644
--- a/Documentation/devicetree/bindings/net/nfc/pn544.txt
+++ b/Documentation/devicetree/bindings/net/nfc/pn544.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "nxp,pn544-i2c".
 - clock-frequency: I�C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - enable-gpios: Output GPIO pin used for enabling/disabling the PN544
 - firmware-gpios: Output GPIO pin used to enter firmware download mode
diff --git a/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt b/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
index ed5b3eaadb39..f02f6fb7f81c 100644
--- a/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
+++ b/Documentation/devicetree/bindings/net/nfc/s3fwrn5.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: Should be "samsung,s3fwrn5-i2c".
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - s3fwrn5,en-gpios: Output GPIO pin used for enabling/disabling the chip
 - s3fwrn5,fw-gpios: Output GPIO pin used to enter firmware mode and
diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
index b46d473be425..baa8f8133d19 100644
--- a/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible: Should be "st,st21nfcb-i2c" or "st,st21nfcc-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - reset-gpios: Output GPIO pin used to reset the ST21NFCB
 
diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
index 54ce8e7ac681..d33343330b94 100644
--- a/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: Should be "st,st21nfcb-spi"
 - spi-max-frequency: Maximum SPI frequency (<= 4000000).
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - reset-gpios: Output GPIO pin used to reset the ST21NFCB
 
diff --git a/Documentation/devicetree/bindings/net/nfc/st21nfca.txt b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
index 5ee9440fa9ad..b8bd90f80e12 100644
--- a/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st21nfca.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible: Should be "st,st21nfca-i2c".
 - clock-frequency: I²C work frequency.
 - reg: address on the bus
-- interrupt-parent: phandle for the interrupt gpio controller
-- interrupts: GPIO interrupt to which the chip is connected
 - enable-gpios: Output GPIO pin used for enabling/disabling the ST21NFCA
 
 Optional SoC Specific Properties:
diff --git a/Documentation/devicetree/bindings/net/nfc/st95hf.txt b/Documentation/devicetree/bindings/net/nfc/st95hf.txt
index 08a202e00d47..3f373a1e20ff 100644
--- a/Documentation/devicetree/bindings/net/nfc/st95hf.txt
+++ b/Documentation/devicetree/bindings/net/nfc/st95hf.txt
@@ -17,9 +17,6 @@ Required properties:
 
 - enable-gpio: GPIO line to enable ST95HF transceiver.
 
-- interrupt-parent : Standard way to specify the controller to which
-	ST95HF transceiver's interrupt is routed.
-
 - interrupts : Standard way to define ST95HF transceiver's out
 	interrupt.
 
diff --git a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
index 5ca9362ef127..ba1934b950e5 100644
--- a/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
+++ b/Documentation/devicetree/bindings/net/nfc/trf7970a.txt
@@ -3,7 +3,6 @@
 Required properties:
 - compatible: Should be "ti,trf7970a".
 - spi-max-frequency: Maximum SPI frequency (<= 2000000).
-- interrupt-parent: phandle of parent interrupt handler.
 - interrupts: A single interrupt specifier.
 - ti,enable-gpios: One or two GPIO entries used for 'EN' and 'EN2' pins on the
   TRF7970A. EN2 is optional.
diff --git a/Documentation/devicetree/bindings/net/phy.txt b/Documentation/devicetree/bindings/net/phy.txt
index d2169a56f5e3..17c1d2bd00f6 100644
--- a/Documentation/devicetree/bindings/net/phy.txt
+++ b/Documentation/devicetree/bindings/net/phy.txt
@@ -3,8 +3,6 @@ PHY nodes
 Required properties:
 
  - interrupts : interrupt specifier for the sole interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
  - reg : The ID number for the phy, usually a small integer
 
 Optional Properties:
diff --git a/Documentation/devicetree/bindings/net/qca,qca7000.txt b/Documentation/devicetree/bindings/net/qca,qca7000.txt
index 3987846b3fd3..e4a8a51086df 100644
--- a/Documentation/devicetree/bindings/net/qca,qca7000.txt
+++ b/Documentation/devicetree/bindings/net/qca,qca7000.txt
@@ -19,7 +19,6 @@ Required properties:
 - spi-cpol	    : Must be set
 
 Optional properties:
-- interrupt-parent  : Specify the pHandle of the source interrupt
 - spi-max-frequency : Maximum frequency of the SPI bus the chip can operate at.
 		      Numbers smaller than 1000000 or greater than 16000000
 		      are invalid. Missing the property will set the SPI
diff --git a/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt b/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
index 88b095d1f13b..9fe1a0a22e44 100644
--- a/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
+++ b/Documentation/devicetree/bindings/net/ralink,rt2880-net.txt
@@ -14,8 +14,6 @@ Required properties:
   "ralink,rt3050-eth", "ralink,rt3883-eth", "ralink,rt5350-eth",
   "mediatek,mt7620-eth", "mediatek,mt7621-eth"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the frame engines interrupt
 - resets: Should contain the frame engines resets
 - reset-names: Should contain the reset names "fe". If a switch is present
diff --git a/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt b/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
index 2e79bd376c56..87e315856efa 100644
--- a/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
+++ b/Documentation/devicetree/bindings/net/ralink,rt3050-esw.txt
@@ -7,8 +7,6 @@ SoCs (RT3x5x, RT5350, MT76x8).
 Required properties:
 - compatible: Should be "ralink,rt3050-esw"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the embedded switches interrupt
 - resets: Should contain the embedded switches resets
 - reset-names: Should contain the reset names "esw"
diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt
index fac897d54423..19740d01cab0 100644
--- a/Documentation/devicetree/bindings/net/renesas,ravb.txt
+++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt
@@ -47,8 +47,6 @@ Required properties:
 - pinctrl-0: phandle, referring to a default pin configuration node.
 
 Optional properties:
-- interrupt-parent: the phandle for the interrupt controller that services
-		    interrupts for this device.
 - interrupt-names: A list of interrupt names.
 		   For the R-Car Gen 3 SoCs this property is mandatory;
 		   it should include one entry per channel, named "ch%u",
diff --git a/Documentation/devicetree/bindings/net/samsung-sxgbe.txt b/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
index 888c250197fe..46e591178911 100644
--- a/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
+++ b/Documentation/devicetree/bindings/net/samsung-sxgbe.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: Should be "samsung,sxgbe-v2.0a"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the SXGBE interrupts
   These interrupts are ordered by fixed and follows variable
   trasmit DMA interrupts, receive DMA interrupts and lpi interrupt.
diff --git a/Documentation/devicetree/bindings/net/sh_eth.txt b/Documentation/devicetree/bindings/net/sh_eth.txt
index 82a4cf2c145d..76db9f13ad96 100644
--- a/Documentation/devicetree/bindings/net/sh_eth.txt
+++ b/Documentation/devicetree/bindings/net/sh_eth.txt
@@ -35,8 +35,6 @@ Required properties:
 - pinctrl-0: phandle, referring to a default pin configuration node.
 
 Optional properties:
-- interrupt-parent: the phandle for the interrupt controller that services
-		    interrupts for this device.
 - pinctrl-names: pin configuration state name ("default").
 - renesas,no-ether-link: boolean, specify when a board does not provide a proper
 			 Ether LINK signal.
diff --git a/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
index 21d27aa4c68c..36f1aef585f0 100644
--- a/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
+++ b/Documentation/devicetree/bindings/net/snps,dwc-qos-ethernet.txt
@@ -83,8 +83,6 @@ Required properties:
   - "snps,dwc-qos-ethernet-4.10" (deprecated):
     - "phy_ref_clk"
     - "apb_clk"
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the core's combined interrupt signal
 - phy-mode: See ethernet.txt file in the same directory
 - resets: Phandle and reset specifiers for each entry in reset-names, in the
diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 3a28a5d8857d..8bdb1c231d08 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible: Should be "snps,dwmac-<ip_version>", "snps,dwmac"
 	For backwards compatibility: "st,spear600-gmac" is also supported.
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the STMMAC interrupts
 - interrupt-names: Should contain a list of interrupt names corresponding to
 	the interrupts in the interrupts property, if available.
diff --git a/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt b/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
index 86602f264dce..cffb2d6876e3 100644
--- a/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
+++ b/Documentation/devicetree/bindings/net/wireless/brcm,bcm43xx-fmac.txt
@@ -11,8 +11,6 @@ Required properties:
 Optional properties:
  - brcm,drive-strength : drive strength used for SDIO pins on device in mA
 	(default = 6).
- - interrupt-parent : the phandle for the interrupt controller to which the
-	device interrupts are connected.
  - interrupts : specifies attributes for the out-of-band interrupt (host-wake).
 	When not specified the device will use in-band SDIO interrupts.
  - interrupt-names : name of the out-of-band interrupt, which must be set
diff --git a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
index 59de8646862d..9bf9bbac16e2 100644
--- a/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
+++ b/Documentation/devicetree/bindings/net/wireless/marvell-8xxx.txt
@@ -29,7 +29,6 @@ Optional properties:
   - marvell,wakeup-pin : a wakeup pin number of wifi chip which will be configured
 		      to firmware. Firmware will wakeup the host using this pin
 		      during suspend/resume.
-  - interrupt-parent: phandle of the parent interrupt controller
   - interrupts : interrupt pin number to the cpu. driver will request an irq based on
 		 this interrupt number. during system suspend, the irq will be enabled
 		 so that the wifi chip can wakeup host platform under certain condition.
diff --git a/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt b/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt
index 189ae5cad8f7..bb2fcde6f7ff 100644
--- a/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt
+++ b/Documentation/devicetree/bindings/net/wireless/ti,wl1251.txt
@@ -8,8 +8,6 @@ Required properties:
 - reg :               Chip select address of device
 - spi-max-frequency : Maximum SPI clocking speed of device in Hz
 - interrupts :        Should contain interrupt line
-- interrupt-parent :  Should be the phandle for the interrupt controller
-                      that services interrupts for this device
 - vio-supply :        phandle to regulator providing VIO
 - ti,power-gpio :     GPIO connected to chip's PMEN pin
 
diff --git a/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt b/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt
index 8f9ced076fe1..cb5c9e1569ca 100644
--- a/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt
+++ b/Documentation/devicetree/bindings/net/wireless/ti,wlcore,spi.txt
@@ -17,9 +17,7 @@ Required properties:
     * "ti,wl1837"
 - reg :                 Chip select address of device
 - spi-max-frequency :   Maximum SPI clocking speed of device in Hz
-- interrupt-parent, interrupts :
-                        Should contain parameters for 1 interrupt line.
-                        Interrupt parameters: parent, line number, type.
+- interrupts :          Should contain parameters for 1 interrupt line.
 - vwlan-supply :        Point the node of the regulator that powers/enable the
                         wl12xx/wl18xx chip
 
diff --git a/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt b/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt
index f42f6b0f1bc7..9306c4dadd46 100644
--- a/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt
+++ b/Documentation/devicetree/bindings/net/wireless/ti,wlcore.txt
@@ -20,8 +20,6 @@ Required properties:
  - interrupts : specifies attributes for the out-of-band interrupt.
 
 Optional properties:
- - interrupt-parent : the phandle for the interrupt controller to which the
-	device interrupts are connected.
  - ref-clock-frequency : ref clock frequency in Hz
  - tcxo-clock-frequency : tcxo clock frequency in Hz
 
diff --git a/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt b/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt
index 09cd3bc4d038..9514c327d31b 100644
--- a/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt
+++ b/Documentation/devicetree/bindings/pci/altera-pcie-msi.txt
@@ -7,7 +7,6 @@ Required properties:
 - reg-names:	must include the following entries:
 		"csr": CSR registers
 		"vector_slave": vectors slave port region
-- interrupt-parent:	interrupt source phandle.
 - interrupts:	specifies the interrupt source of the parent interrupt
 		controller. The format of the interrupt specifier depends on the
 		parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/pci/altera-pcie.txt b/Documentation/devicetree/bindings/pci/altera-pcie.txt
index a1dc9366a8fc..6c396f17c91a 100644
--- a/Documentation/devicetree/bindings/pci/altera-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/altera-pcie.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg-names:	must include the following entries:
 		"Txs": TX slave port region
 		"Cra": Control register access region
-- interrupt-parent:	interrupt source phandle.
 - interrupts:	specifies the interrupt source of the parent interrupt
 		controller.  The format of the interrupt specifier depends
 		on the parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
index b8e48b4762b2..df065aa53a83 100644
--- a/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/brcm,iproc-pcie.txt
@@ -65,7 +65,6 @@ When the iProc event queue based MSI is used, one needs to define the
 following properties in the MSI device node:
 - compatible: Must be "brcm,iproc-msi"
 - msi-controller: claims itself as an MSI controller
-- interrupt-parent: Link to its parent interrupt device
 - interrupts: List of interrupt IDs from its parent interrupt device
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt b/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt
index 89a84f8aa621..5f8cb4962f8d 100644
--- a/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt
+++ b/Documentation/devicetree/bindings/pci/faraday,ftpci100.txt
@@ -41,7 +41,6 @@ Mandatory subnodes:
 - For "faraday,ftpci100" a node representing the interrupt-controller inside the
   host bridge is mandatory. It has the following mandatory properties:
   - interrupt: see interrupt-controller/interrupts.txt
-  - interrupt-parent: see interrupt-controller/interrupts.txt
   - interrupt-controller: see interrupt-controller/interrupts.txt
   - #address-cells: set to <0>
   - #interrupt-cells: set to <1>
diff --git a/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt b/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
index 65038aa642e5..a618d4787dd7 100644
--- a/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/mobiveil-pcie.txt
@@ -26,9 +26,6 @@ Required properties:
 - interrupt-controller: identifies the node as an interrupt controller
 - #interrupt-cells: specifies the number of cells needed to encode an
 	interrupt source. The value must be 1.
-- interrupt-parent : phandle to the interrupt controller that
-		it is attached to, it should be set to gic to point to
-		ARM's Generic Interrupt Controller node in system DT.
 - interrupts: The interrupt line of the PCIe controller
 		last cell of this field is set to 4 to
 		denote it as IRQ_TYPE_LEVEL_HIGH type interrupt.
diff --git a/Documentation/devicetree/bindings/pci/pci-keystone.txt b/Documentation/devicetree/bindings/pci/pci-keystone.txt
index 3d4a209b0fd0..4dd17de549a7 100644
--- a/Documentation/devicetree/bindings/pci/pci-keystone.txt
+++ b/Documentation/devicetree/bindings/pci/pci-keystone.txt
@@ -17,7 +17,6 @@ reg:	index 1 is the base address and length of DW application registers.
 
 pcie_msi_intc : Interrupt controller device node for MSI IRQ chip
 	interrupt-cells: should be set to 1
-	interrupt-parent: Parent interrupt controller phandle
 	interrupts: GIC interrupt lines connected to PCI MSI interrupt lines
 
  Example:
@@ -37,8 +36,6 @@ pcie_msi_intc : Interrupt controller device node for MSI IRQ chip
 
 pcie_intc: Interrupt controller device node for Legacy IRQ chip
 	interrupt-cells: should be set to 1
-	interrupt-parent: Parent interrupt controller phandle
-	interrupts: GIC interrupt lines connected to PCI Legacy interrupt lines
 
  Example:
 	pcie_intc: legacy-interrupt-controller {
diff --git a/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
index a04ab1b76211..ffba4f63d71f 100644
--- a/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
+++ b/Documentation/devicetree/bindings/pci/ralink,rt3883-pci.txt
@@ -41,9 +41,6 @@
    - #interrupt-cells: specifies the number of cells needed to encode an
      interrupt source. The value must be 1.
 
-   - interrupt-parent: the phandle for the interrupt controller that
-     services interrupts for this device.
-
    - interrupts: specifies the interrupt source of the parent interrupt
      controller. The format of the interrupt specifier depends on the
      parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt
index def8fcad8941..3b695131c51b 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-mt7622.txt
@@ -16,8 +16,6 @@ If the property interrupt-controller is defined, following property is required
 - reg-names: A string describing the "reg" entries. Must contain "eint".
 - interrupts : The interrupt output from the controller.
 - #interrupt-cells: Should be two.
-- interrupt-parent: Phandle of the interrupt parent to which the external
-  GPIO interrupts are forwarded to.
 
 Please refer to pinctrl-bindings.txt in this directory for details of the
 common pinctrl bindings used by client devices, including the meaning of the
diff --git a/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt b/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt
index bf76867168e9..4023bad2fe39 100644
--- a/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt
+++ b/Documentation/devicetree/bindings/pinctrl/pinctrl-sx150x.txt
@@ -25,8 +25,6 @@ Required properties:
 - gpio-controller: Marks the device as a GPIO controller.
 
 Optional properties :
-- interrupt-parent: phandle of the parent interrupt controller.
-
 - interrupts: Interrupt specifier for the controllers interrupt.
 
 - interrupt-controller: Marks the device as a interrupt controller.
diff --git a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
index 5e00a21de2bf..decc16abd379 100644
--- a/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/samsung-pinctrl.txt
@@ -124,8 +124,6 @@ used as system wakeup events.
 A. External GPIO Interrupts: For supporting external gpio interrupts, the
    following properties should be specified in the pin-controller device node.
 
-   - interrupt-parent: phandle of the interrupt parent to which the external
-     GPIO interrupts are forwarded to.
    - interrupts: interrupt specifier for the controller. The format and value of
      the interrupt specifier depends on the interrupt parent for the controller.
 
@@ -160,8 +158,6 @@ B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
        found on Samsung Exynos4210 and S5PC110/S5PV210 SoCs.
      - samsung,exynos7-wakeup-eint: represents wakeup interrupt controller
        found on Samsung Exynos7 SoC.
-   - interrupt-parent: phandle of the interrupt parent to which the external
-     wakeup interrupts are forwarded to.
    - interrupts: interrupt used by multiplexed wakeup interrupts.
 
    In addition, following properties must be present in node of every bank
@@ -181,8 +177,6 @@ B. External Wakeup Interrupts: For supporting external wakeup interrupts, a
    Node of every bank of pins supporting direct wake-up interrupts (without
    multiplexing) must contain following properties:
 
-   - interrupt-parent: phandle of the interrupt parent to which the external
-     wakeup interrupts are forwarded to.
    - interrupts: interrupts of the interrupt parent which are used for external
      wakeup interrupts from pins of the bank, must contain interrupts for all
      pins of the bank.
diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
index 9a06e1fdbc42..a8bb36b4f9fd 100644
--- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
@@ -37,8 +37,6 @@ Required properties:
 
 Optional properties:
  - reset:	  : Reference to the reset controller
- - interrupt-parent: phandle of the interrupt parent to which the external
-   GPIO interrupts are forwarded to.
  - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
    which includes IRQ mux selection register, and the offset of the IRQ mux
    selection register.
diff --git a/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt b/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt
index b86ecada4f84..c7dfb7cecf40 100644
--- a/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/act8945a-charger.txt
@@ -9,8 +9,6 @@ Required properties:
  - interrupts: <a b> where a is the interrupt number and b is a
    field that represents an encoding of the sense and level
    information for the interrupt.
- - interrupt-parent: the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Optional properties:
  - active-semi,input-voltage-threshold-microvolt: unit: mV;
diff --git a/Documentation/devicetree/bindings/power/supply/bq24257.txt b/Documentation/devicetree/bindings/power/supply/bq24257.txt
index d693702c9c1e..f8f5a1685bb9 100644
--- a/Documentation/devicetree/bindings/power/supply/bq24257.txt
+++ b/Documentation/devicetree/bindings/power/supply/bq24257.txt
@@ -6,8 +6,6 @@ Required properties:
  * "ti,bq24251"
  * "ti,bq24257"
 - reg: integer, i2c address of the device.
-- interrupt-parent: Should be the phandle for the interrupt controller. Use in
-    conjunction with "interrupts".
 - interrupts: Interrupt mapping for GPIO IRQ (configure for both edges). Use in
     conjunction with "interrupt-parent".
 - ti,battery-regulation-voltage: integer, maximum charging voltage in uV.
diff --git a/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt b/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt
index 2246bc5c874b..0355a4b68f79 100644
--- a/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/lp8727_charger.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg: I2C slave address 27h
 
 Optional properties:
-- interrupt-parent: interrupt controller node (see interrupt binding[0])
 - interrupts: interrupt specifier (see interrupt binding[0])
 - debounce-ms: interrupt debounce time. (u32)
 
diff --git a/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt b/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt
index d6e8dfd0a581..f956247d493e 100644
--- a/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt
+++ b/Documentation/devicetree/bindings/power/supply/maxim,max14656.txt
@@ -3,7 +3,6 @@ Maxim MAX14656 / AL32 USB Charger Detector
 Required properties :
 - compatible : "maxim,max14656";
 - reg: i2c slave address
-- interrupt-parent: the phandle for the interrupt controller
 - interrupts: interrupt line
 
 Example:
diff --git a/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt b/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt
index 5d9ad5cf2c5a..1e6107c7578e 100644
--- a/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/rt9455_charger.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible:				it should contain one of the following:
 					"richtek,rt9455".
 - reg:					integer, i2c address of the device.
-- interrupt-parent:			the phandle for the interrupt controller that
-					services interrupts for this device.
 - interrupts:				interrupt mapping for GPIO IRQ, it should be
 					configured with IRQ_TYPE_LEVEL_LOW flag.
 - richtek,output-charge-current:	integer, output current from the charger to the
diff --git a/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
index a3719623a94f..84e74151eef2 100644
--- a/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
+++ b/Documentation/devicetree/bindings/power/supply/sbs_sbs-charger.txt
@@ -7,8 +7,6 @@ Required properties:
      specific registers.
 
 Optional properties:
-- interrupt-parent: Should be the phandle for the interrupt controller. Use in
-    conjunction with "interrupts".
 - interrupts: Interrupt mapping for GPIO IRQ. Use in conjunction with
     "interrupt-parent". If an interrupt is not provided the driver will switch
     automatically to polling.
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt b/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
index db939210e29d..940fd78e3363 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/akebono.txt
@@ -19,7 +19,6 @@ The IBM Akebono board is a development board for the PPC476GTR SoC.
 
    - compatible : should be "ibm,476gtr-sdhci","generic-sdhci".
    - reg : should contain the SDHCI registers location and length.
-   - interrupt-parent : a phandle for the interrupt controller.
    - interrupts : should contain the SDHCI interrupt.
 
 1.b) The Advanced Host Controller Interface (AHCI) SATA node
@@ -30,7 +29,6 @@ The IBM Akebono board is a development board for the PPC476GTR SoC.
 
    - compatible : should be "ibm,476gtr-ahci".
    - reg : should contain the AHCI registers location and length.
-   - interrupt-parent : a phandle for the interrupt controller.
    - interrupts : should contain the AHCI interrupt.
 
 1.c) The FPGA node
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt b/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
index c737c8338705..66dbd9ff56f7 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/hsta.txt
@@ -13,7 +13,6 @@ device tree entries:
 Require properties:
 - compatible		: "ibm,476gtr-hsta-msi", "ibm,hsta-msi"
 - reg			: register mapping for the HSTA MSI space
-- interrupt-parent	: parent controller for mapping interrupts
 - interrupts		: ordered interrupt mapping for each MSI in the register
 			  space. The first interrupt should be associated with a
 			  register offset of 0x00, the second to 0x10, etc.
diff --git a/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt b/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt
index 515ebcf1b97d..de6a5f7d4aa4 100644
--- a/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt
+++ b/Documentation/devicetree/bindings/powerpc/4xx/ppc440spe-adma.txt
@@ -38,7 +38,6 @@ DMA devices.
 			   2 sources: DMAx CS FIFO Needs Service IRQ (on UIC0)
 			   and DMA Error IRQ (on UIC1). The latter is common
 			   for both DMA engines>.
- - interrupt-parent	: needed for interrupt mapping
 
  Example:
 
@@ -65,7 +64,6 @@ DMA devices.
  - compatible		: "amcc,xor-accelerator";
  - reg			: <registers mapping>
  - interrupts		: <interrupt mapping for XOR interrupt source>
- - interrupt-parent	: for interrupt mapping
 
  Example:
 
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt b/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt
index 18a88100af94..4b01e1afafda 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/dcsr.txt
@@ -84,13 +84,6 @@ PROPERTIES
 
 	Interrupt numbers are listed in order (perfmon, event0, event1).
 
-	- interrupt-parent
-	Usage: required
-	Value type: <phandle>
-	Definition: A single <phandle> value that points
-	to the interrupt parent to which the child domain
-	is being mapped. Value must be "&mpic"
-
 	- reg
 	Usage: required
 	Value type: <prop-encoded-array>
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/diu.txt b/Documentation/devicetree/bindings/powerpc/fsl/diu.txt
index b66cb6d31d69..eb45db1ecee5 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/diu.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/diu.txt
@@ -8,8 +8,6 @@ Required properties:
 - reg : should contain at least address and length of the DIU register
   set.
 - interrupts : one DIU interrupt should be described here.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 
 Optional properties:
 - edid : verbatim EDID data block describing attached display.
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
index 7fc1b010fa75..c11ad5c6db21 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/dma.txt
@@ -13,7 +13,6 @@ Required properties:
                       DMA channels and the address space of the DMA controller
 - cell-index        : controller index.  0 for controller @ 0x8100
 - interrupts        : interrupt specifier for DMA IRQ
-- interrupt-parent  : optional, if needed for interrupt mapping
 
 - DMA channel nodes:
         - compatible        : must include "fsl,elo-dma-channel"
@@ -25,7 +24,6 @@ Optional properties:
         - interrupts        : interrupt specifier for DMA channel IRQ
                               (on 83xx this is expected to be identical to
                               the interrupts property of the parent node)
-        - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
 	dma@82a8 {
@@ -88,7 +86,6 @@ Required properties:
         - cell-index        : DMA channel index starts at 0.
         - reg               : DMA channel specific registers
         - interrupts        : interrupt specifier for DMA channel IRQ
-        - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
 	dma@21300 {
@@ -146,7 +143,6 @@ Required properties:
         - compatible        : must include "fsl,eloplus-dma-channel"
         - reg               : DMA channel specific registers
         - interrupts        : interrupt specifier for DMA channel IRQ
-        - interrupt-parent  : optional, if needed for interrupt mapping
 
 Example:
 dma@100300 {
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt b/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt
index f514f29c67d6..76dc547bc492 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/ecm.txt
@@ -57,8 +57,4 @@ PROPERTIES
       Usage: required
       Value type: <prop-encoded-array>
 
-   - interrupt-parent
-      Usage: required
-      Value type: <phandle>
-
 =====================================================================
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt b/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt
index 4ceda9b3b413..a5dae6b1f545 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/mcm.txt
@@ -57,8 +57,4 @@ PROPERTIES
       Usage: required
       Value type: <prop-encoded-array>
 
-   - interrupt-parent
-      Usage: required
-      Value type: <phandle>
-
 =====================================================================
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
index 647817527c88..5dfd68f1a423 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/mpc5121-psc.txt
@@ -18,8 +18,6 @@ Required properties :
  - interrupts : <a b> where a is the interrupt number of the
    PSC FIFO Controller and b is a field that represents an
    encoding of the sense and level information for the interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Recommended properties :
  - fsl,rx-fifo-size : the size of the RX fifo slice (a multiple of 4)
@@ -45,8 +43,6 @@ Required properties :
  - interrupts : <a b> where a is the interrupt number of the
    PSC FIFO Controller and b is a field that represents an
    encoding of the sense and level information for the interrupt.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Recommended properties :
  - clocks : specifies the clock needed to operate the fifo controller
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
index 82dd5b65cf48..f8d2b7fe06d6 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/msi-pic.txt
@@ -21,11 +21,6 @@ Required properties:
   be set as edge sensitive.  If msi-available-ranges is present, only
   the interrupts that correspond to available ranges shall be present.
 
-- interrupt-parent: the phandle for the interrupt controller
-  that services interrupts for this device. for 83xx cpu, the interrupts
-  are routed to IPIC, and for 85xx/86xx cpu the interrupts are routed
-  to MPIC.
-
 Optional properties:
 - msi-available-ranges: use <start count> style section to define which
   msi interrupt can be used in the 256 msi interrupts. This property is
diff --git a/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt b/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
index c2b2899885f2..b21ab85de6e7 100644
--- a/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
+++ b/Documentation/devicetree/bindings/powerpc/fsl/pamu.txt
@@ -32,8 +32,6 @@ Optional properties:
 		  A standard property.   It represents the CCSR registers of
 		  all child PAMUs combined.  Include it to provide support
 		  for legacy drivers.
-- interrupt-parent : <phandle>
-		  Phandle to interrupt controller
 - fsl,portid-mapping : <u32>
 		  The Coherency Subdomain ID Port Mapping Registers and
 		  Snoop ID Port Mapping registers, which are part of the
diff --git a/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt b/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt
index a3dc4b9fa11a..c4d78f28d23c 100644
--- a/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt
+++ b/Documentation/devicetree/bindings/powerpc/nintendo/wii.txt
@@ -148,7 +148,6 @@ Nintendo Wii device tree
   - reg : should contain the controller registers location and length
   - interrupt-controller
   - interrupts : should contain the cascade interrupt of the "flipper" pic
-  - interrupt-parent: should contain the phandle of the "flipper" pic
 
 1.l) The General Purpose I/O (GPIO) controller node
 
diff --git a/Documentation/devicetree/bindings/regulator/max8997-regulator.txt b/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
index 5c186a7a77ba..6fe825b8ac1b 100644
--- a/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/max8997-regulator.txt
@@ -32,8 +32,6 @@ Required properties:
     'max8997,pmic-buck[1/2/5]-dvs-voltage' should be specified.
 
 Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the interrupts from max8997 are delivered to.
 - interrupts: Interrupt specifiers for two interrupt sources.
   - First interrupt specifier is for 'irq1' interrupt.
   - Second interrupt specifier is for 'alert' interrupt.
diff --git a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
index 99872819604f..84bc76a7c39e 100644
--- a/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
+++ b/Documentation/devicetree/bindings/regulator/palmas-pmic.txt
@@ -18,7 +18,6 @@ Required properties:
   ti,tps659038-pmic
 and also the generic series names
   ti,palmas-pmic
-- interrupt-parent : The parent interrupt controller which is palmas.
 - interrupts : The interrupt number and the type which can be looked up here:
 	       arch/arm/boot/dts/include/dt-bindings/interrupt-controller/irq.h
 - interrupts-name: The names of the individual interrupts.
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
index e44a97e21164..25f8658e216f 100644
--- a/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
+++ b/Documentation/devicetree/bindings/remoteproc/ti,davinci-rproc.txt
@@ -45,12 +45,6 @@ The following are the mandatory properties:
 			per the bindings in
 			Documentation/devicetree/bindings/reserved-memory/reserved-memory.txt
 
-Optional properties:
---------------------
-- interrupt-parent:	phandle to the interrupt controller node. This property
-			is needed if the device node hierarchy doesn't have an
-			interrupt controller.
-
 
 Example:
 --------
diff --git a/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt b/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt
index 1eb72874130b..461dc1d8d570 100644
--- a/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt
+++ b/Documentation/devicetree/bindings/remoteproc/ti,keystone-rproc.txt
@@ -51,12 +51,6 @@ The following are the mandatory properties:
 			Documentation/devicetree/bindings/reset/ti,sci-reset.txt
 			    for 66AK2G SoCs
 
-- interrupt-parent:	Should contain a phandle to the Keystone 2 IRQ controller
-			IP node that is used by the ARM CorePac processor to
-			receive interrupts from the DSP remote processors. See
-			Documentation/devicetree/bindings/interrupt-controller/ti,keystone-irq.txt
-			for details.
-
 - interrupts: 		Should contain an entry for each value in 'interrupt-names'.
 			Each entry should have the interrupt source number used by
 			the remote processor to the host processor. The values should
diff --git a/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt
index 1d990bcc0baf..d946f28502b3 100644
--- a/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt
+++ b/Documentation/devicetree/bindings/rtc/brcm,brcmstb-waketimer.txt
@@ -7,8 +7,6 @@ Required properties:
 - compatible     : should contain "brcm,brcmstb-waketimer"
 - reg            : the register start and length for the WKTMR block
 - interrupts     : The TIMER interrupt
-- interrupt-parent: The phandle to the Always-On (AON) Power Management (PM) L2
-                    interrupt controller node
 - clocks	 : The phandle to the UPG fixed clock (27Mhz domain)
 
 Example:
diff --git a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt b/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
index fbbdd92e5af9..ff7c43555199 100644
--- a/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
+++ b/Documentation/devicetree/bindings/rtc/isil,isl12057.txt
@@ -25,9 +25,6 @@ Optional properties:
  - "wakeup-source": mark the chip as a wakeup source, independently of
     the availability of an IRQ line connected to the SoC.
 
- - "interrupt-parent", "interrupts": for passing the interrupt line
-   of the SoC connected to IRQ#2 of the RTC chip.
-
 
 Example isl12057 node without IRQ#2 pin connected (no alarm support):
 
diff --git a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
index 7382989b3052..b94b35f3600b 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-cmos.txt
@@ -7,7 +7,6 @@ Required properties:
 
 Optional properties:
   - interrupts : should contain interrupt.
-  - interrupt-parent : interrupt source phandle.
   - ctrl-reg : Contains the initial value of the control register also
     called "Register B".
   - freq-reg : Contains the initial value of the frequency register also
diff --git a/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt b/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt
index d28d6e7f6ae8..226cc93df875 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-ds1307.txt
@@ -21,7 +21,6 @@ Required properties:
 - reg: I2C bus address of the device
 
 Optional properties:
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 - clock-output-names: From common clock binding to override the default output
                       clock name
diff --git a/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt b/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt
index 717d93860af1..c746cb221210 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-m41t80.txt
@@ -16,7 +16,6 @@ Required properties:
 - reg: I2C bus address of the device
 
 Optional properties:
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 - clock-output-names: From common clock binding to override the default output
                       clock name
diff --git a/Documentation/devicetree/bindings/rtc/rtc-omap.txt b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
index bee41f97044e..062ebb14cecf 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-omap.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-omap.txt
@@ -11,7 +11,6 @@ Required properties:
 	- "ti,am4372-rtc" - for RTC IP used similar to that on AM437X SoC family.
 - reg: Address range of rtc register set
 - interrupts: rtc timer, alarm interrupts in order
-- interrupt-parent: phandle for the interrupt controller
 
 Optional properties:
 - system-power-controller: whether the rtc is controlling the system power
diff --git a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
index eb1c7fdeb413..c6cf37758a77 100644
--- a/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
+++ b/Documentation/devicetree/bindings/rtc/rtc-palmas.txt
@@ -3,7 +3,6 @@ Palmas RTC controller bindings
 Required properties:
 - compatible:
   - "ti,palmas-rtc" for palma series of the RTC controller
-- interrupt-parent: Parent interrupt device, must be handle of palmas node.
 - interrupts: Interrupt number of RTC submodule on device.
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/rtc/spear-rtc.txt b/Documentation/devicetree/bindings/rtc/spear-rtc.txt
index ca67ac62108e..fecf8e4ad4b4 100644
--- a/Documentation/devicetree/bindings/rtc/spear-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/spear-rtc.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible : "st,spear600-rtc"
 - reg : Address range of the rtc registers
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupt: Should contain the rtc interrupt number
 
 Example:
diff --git a/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt b/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt
index 7c170da0d4b7..1f5754299d31 100644
--- a/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/sprd,sc27xx-rtc.txt
@@ -3,7 +3,6 @@ Spreadtrum SC27xx Real Time Clock
 Required properties:
 - compatible: should be "sprd,sc2731-rtc".
 - reg: address offset of rtc register.
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 
 Example:
diff --git a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
index c920e2736991..130ca5b98253 100644
--- a/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
+++ b/Documentation/devicetree/bindings/rtc/st,stm32-rtc.txt
@@ -13,8 +13,6 @@ Required properties:
     It is required on stm32(h7/mp1).
 - clock-names: must be "rtc_ck" and "pclk".
     It is required on stm32(h7/mp1).
-- interrupt-parent: phandle for the interrupt controller.
-    It is required on stm32(f4/f7/h7).
 - interrupts: rtc alarm interrupt. On stm32mp1, a second interrupt is required
   for rtc alarm wakeup interrupt.
 - st,syscfg: phandle/offset/mask triplet. The phandle to pwrcfg used to
diff --git a/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt b/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt
index 3ebeb311335f..e615a897b20e 100644
--- a/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt
+++ b/Documentation/devicetree/bindings/rtc/stericsson,coh901331.txt
@@ -3,7 +3,6 @@ ST-Ericsson COH 901 331 Real Time Clock
 Required properties:
 - compatible: must be "stericsson,coh901331"
 - reg: address range of rtc register set.
-- interrupt-parent: phandle for the interrupt controller.
 - interrupts: rtc alarm interrupt.
 - clocks: phandle to the rtc clock source
 
diff --git a/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt b/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
index 6a4e0d30d8c4..0dc121b6eace 100644
--- a/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
+++ b/Documentation/devicetree/bindings/security/tpm/st33zp24-i2c.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg: address on the bus
 
 Optional ST33ZP24 Properties:
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - lpcpd-gpios: Output GPIO pin used for ST33ZP24 power management D1/D2 state.
 If set, power must be present when the platform is going into sleep/hibernate mode.
diff --git a/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt b/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
index 604dce901b60..37198971f17b 100644
--- a/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
+++ b/Documentation/devicetree/bindings/security/tpm/st33zp24-spi.txt
@@ -5,7 +5,6 @@ Required properties:
 - spi-max-frequency: Maximum SPI frequency (<= 10000000).
 
 Optional ST33ZP24 Properties:
-- interrupt-parent: phandle for the interrupt gpio controller
 - interrupts: GPIO interrupt to which the chip is connected
 - lpcpd-gpios: Output GPIO pin used for ST33ZP24 power management D1/D2 state.
 If set, power must be present when the platform is going into sleep/hibernate mode.
diff --git a/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt b/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
index 41d740545189..7c6304426da1 100644
--- a/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
+++ b/Documentation/devicetree/bindings/security/tpm/tpm_tis_mmio.txt
@@ -13,7 +13,7 @@ Required properties:
               "tcg,tpm-tis-mmio". Valid chip strings are:
 	          * "atmel,at97sc3204"
 - reg: The location of the MMIO registers, should be at least 0x5000 bytes
-- interrupt-parent/interrupts: An optional interrupt indicating command completion.
+- interrupts: An optional interrupt indicating command completion.
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/serial/maxim,max310x.txt b/Documentation/devicetree/bindings/serial/maxim,max310x.txt
index 823f77dd7978..79e10a05a96a 100644
--- a/Documentation/devicetree/bindings/serial/maxim,max310x.txt
+++ b/Documentation/devicetree/bindings/serial/maxim,max310x.txt
@@ -7,8 +7,6 @@ Required properties:
   - "maxim,max3109" for Maxim MAX3109,
   - "maxim,max14830" for Maxim MAX14830.
 - reg: SPI chip select number.
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this IC.
 - interrupts: Specifies the interrupt source of the parent interrupt
   controller. The format of the interrupt specifier depends on the
   parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt
index fbfe53635a3a..e7921a8e276b 100644
--- a/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt
+++ b/Documentation/devicetree/bindings/serial/nxp,sc16is7xx.txt
@@ -10,8 +10,6 @@ Required properties:
   - "nxp,sc16is760" for NXP SC16IS760,
   - "nxp,sc16is762" for NXP SC16IS762.
 - reg: I2C address of the SC16IS7xx device.
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this IC.
 - interrupts: Should contain the UART interrupt
 - clocks: Reference to the IC source clock.
 
@@ -44,8 +42,6 @@ Required properties:
   - "nxp,sc16is760" for NXP SC16IS760,
   - "nxp,sc16is762" for NXP SC16IS762.
 - reg: SPI chip select number.
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this IC.
 - interrupts: Specifies the interrupt source of the parent interrupt
   controller. The format of the interrupt specifier depends on the
   parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
index c5e032c85bf9..7d65126bd1d7 100644
--- a/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
+++ b/Documentation/devicetree/bindings/serial/qca,ar9330-uart.txt
@@ -7,9 +7,6 @@ Required properties:
 - reg: Specifies the physical base address of the controller and
   the length of the memory mapped region.
 
-- interrupt-parent: The phandle for the interrupt controller that
-  services interrupts for this device.
-
 - interrupts: Specifies the interrupt source of the parent interrupt
   controller. The format of the interrupt specifier depends on the
   parent interrupt controller.
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
index 626e1afa64a6..cce3cd71e85a 100644
--- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/gpio.txt
@@ -21,7 +21,6 @@ Optional properties:
   one as described by the fsl,cpm1-gpio-irq-mask property. There should be as
   many interrupts as number of ones in the mask property. The first interrupt in
   the list corresponds to the most significant bit of the mask.
-- interrupt-parent : Parent for the above interrupt property.
 
 Example of four SOC GPIO banks defined as gpio-controller nodes:
 
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
index e47734bee3f0..5efb7ac94c79 100644
--- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/ucc.txt
@@ -11,8 +11,6 @@ Required properties:
   information for the interrupt.  This should be encoded based on
   the information in section 2) depending on the type of interrupt
   controller you have.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 - pio-handle : The phandle for the Parallel I/O port configuration.
 - port-number : for UART drivers, the port number to use, between 0 and 3.
   This usually corresponds to the /dev/ttyQE device, e.g. <0> = /dev/ttyQE0.
diff --git a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
index 9ccd5f30405b..da13999337a4 100644
--- a/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
+++ b/Documentation/devicetree/bindings/soc/fsl/cpm_qe/qe/usb.txt
@@ -6,7 +6,6 @@ Required properties:
   length, the next two two cells should contain PRAM location and
   length.
 - interrupts : should contain USB interrupt.
-- interrupt-parent : interrupt source phandle.
 - fsl,fullspeed-clock : specifies the full speed USB clock source:
   "none": clock source is disabled
   "brg1" through "brg16": clock source is BRG1-BRG16, respectively
diff --git a/Documentation/devicetree/bindings/sound/cs35l33.txt b/Documentation/devicetree/bindings/sound/cs35l33.txt
index acfb47525b49..dc5a355d1a19 100644
--- a/Documentation/devicetree/bindings/sound/cs35l33.txt
+++ b/Documentation/devicetree/bindings/sound/cs35l33.txt
@@ -14,8 +14,6 @@ Optional properties:
 
   - reset-gpios : gpio used to reset the amplifier
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-    which the IRQs from CS35L33 are delivered to.
  -  interrupts : IRQ line info CS35L33.
     (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
     for further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/cs35l34.txt b/Documentation/devicetree/bindings/sound/cs35l34.txt
index b218ead2e68e..2f7606b7d542 100644
--- a/Documentation/devicetree/bindings/sound/cs35l34.txt
+++ b/Documentation/devicetree/bindings/sound/cs35l34.txt
@@ -21,8 +21,6 @@ Optional properties:
 
   - reset-gpios: GPIO used to reset the amplifier.
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-    which the IRQs from CS35L34 are delivered to.
   - interrupts : IRQ line info CS35L34.
     (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
     for further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/cs35l35.txt b/Documentation/devicetree/bindings/sound/cs35l35.txt
index 77ee75c39233..7915897f8a81 100644
--- a/Documentation/devicetree/bindings/sound/cs35l35.txt
+++ b/Documentation/devicetree/bindings/sound/cs35l35.txt
@@ -10,8 +10,6 @@ Required properties:
     as covered in
     Documentation/devicetree/bindings/regulator/regulator.txt.
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-    which the IRQs from CS35L35 are delivered to.
   - interrupts : IRQ line info CS35L35.
     (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
     for further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/cs42l42.txt b/Documentation/devicetree/bindings/sound/cs42l42.txt
index 9a2c5e2423d5..7dfaa2ab906f 100644
--- a/Documentation/devicetree/bindings/sound/cs42l42.txt
+++ b/Documentation/devicetree/bindings/sound/cs42l42.txt
@@ -15,9 +15,6 @@ Optional properties:
   - reset-gpios : a GPIO spec for the reset pin. If specified, it will be
   deasserted before communication to the codec starts.
 
-  - interrupt-parent : Specifies the phandle of the interrupt controller to
-  which the IRQs from CS42L42 are delivered to.
-
   - interrupts : IRQ line info CS42L42.
   (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt
   for further information relating to interrupt properties)
@@ -107,4 +104,4 @@ cs42l42: cs42l42@48 {
 	cirrus,btn-det-event-dbnce = <10>;
 	cirrus,bias-lvls = <0x0F 0x08 0x04 0x01>;
 	cirrus,hs-bias-ramp-rate = <0x02>;
-};
\ No newline at end of file
+};
diff --git a/Documentation/devicetree/bindings/sound/da7218.txt b/Documentation/devicetree/bindings/sound/da7218.txt
index 3ab9dfef38d1..2cf30899bd0d 100644
--- a/Documentation/devicetree/bindings/sound/da7218.txt
+++ b/Documentation/devicetree/bindings/sound/da7218.txt
@@ -15,8 +15,6 @@ Required properties:
    information relating to regulators)
 
 Optional properties:
-- interrupt-parent: Specifies the phandle of the interrupt controller to which
-  the IRQs from DA7218 are delivered to.
 - interrupts: IRQ line info for DA7218 chip.
   (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt for
    further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/da7219.txt b/Documentation/devicetree/bindings/sound/da7219.txt
index c3df92d31c4b..e9d0baeb94e2 100644
--- a/Documentation/devicetree/bindings/sound/da7219.txt
+++ b/Documentation/devicetree/bindings/sound/da7219.txt
@@ -8,8 +8,6 @@ Required properties:
 - compatible : Should be "dlg,da7219"
 - reg: Specifies the I2C slave address
 
-- interrupt-parent : Specifies the phandle of the interrupt controller to which
-  the IRQs from DA7219 are delivered to.
 - interrupts : IRQ line info for DA7219.
   (See Documentation/devicetree/bindings/interrupt-controller/interrupts.txt for
    further information relating to interrupt properties)
diff --git a/Documentation/devicetree/bindings/sound/fsl,ssi.txt b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
index d415888e1316..7e15a85cecd2 100644
--- a/Documentation/devicetree/bindings/sound/fsl,ssi.txt
+++ b/Documentation/devicetree/bindings/sound/fsl,ssi.txt
@@ -18,8 +18,6 @@ Required properties:
                     encoded based on the information in section 2)
                     depending on the type of interrupt controller you
                     have.
-- interrupt-parent: The phandle for the interrupt controller that
-                    services interrupts for this device.
 - fsl,fifo-depth:   The number of elements in the transmit and receive FIFOs.
                     This number is the maximum allowed value for SFCSR[TFWM0].
  - clocks:          "ipg" - Required clock for the SSI unit
diff --git a/Documentation/devicetree/bindings/sound/omap-dmic.txt b/Documentation/devicetree/bindings/sound/omap-dmic.txt
index fd8105f18978..418e30e72e89 100644
--- a/Documentation/devicetree/bindings/sound/omap-dmic.txt
+++ b/Documentation/devicetree/bindings/sound/omap-dmic.txt
@@ -6,7 +6,6 @@ Required properties:
        <MPU access base address, size>,
        <L3 interconnect address, size>;
 - interrupts: Interrupt number for DMIC
-- interrupt-parent: The parent interrupt controller
 - ti,hwmods: Name of the hwmod associated with OMAP dmic IP
 
 Example:
diff --git a/Documentation/devicetree/bindings/sound/omap-mcbsp.txt b/Documentation/devicetree/bindings/sound/omap-mcbsp.txt
index 17cce4490456..ae8bf703ce7a 100644
--- a/Documentation/devicetree/bindings/sound/omap-mcbsp.txt
+++ b/Documentation/devicetree/bindings/sound/omap-mcbsp.txt
@@ -15,7 +15,6 @@ Required properties:
 	<TX irq>,
 	<RX irq>;
 - interrupt-names: Array of strings associated with the interrupt numbers
-- interrupt-parent: The parent interrupt controller
 - ti,buffer-size: Size of the FIFO on the port (OMAP2430 and newer SoC)
 - ti,hwmods: Name of the hwmod associated to the McBSP port
 
diff --git a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
index 0741dff048dd..5f4e68ca228c 100644
--- a/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
+++ b/Documentation/devicetree/bindings/sound/omap-mcpdm.txt
@@ -6,7 +6,6 @@ Required properties:
        <MPU access base address, size>,
        <L3 interconnect address, size>;
 - interrupts: Interrupt number for McPDM
-- interrupt-parent: The parent interrupt controller
 - ti,hwmods: Name of the hwmod associated to the McPDM
 
 Example:
diff --git a/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt b/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt
index 551ecab67efe..fdcea3d12ee5 100644
--- a/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,msm8916-wcd-analog.txt
@@ -7,7 +7,6 @@ Bindings for codec Analog IP which is integrated in pmic pm8916,
 Required properties
  - compatible = "qcom,pm8916-wcd-analog-codec";
  - reg: represents the slave base address provided to the peripheral.
- - interrupt-parent : The parent interrupt controller.
  - interrupts: List of interrupts in given SPMI peripheral.
  - interrupt-names: Names specified to above list of interrupts in same
 		    order. List of supported interrupt names are:
diff --git a/Documentation/devicetree/bindings/sound/rt5514.txt b/Documentation/devicetree/bindings/sound/rt5514.txt
index b25ed08c7a5a..d2cc171f22f2 100644
--- a/Documentation/devicetree/bindings/sound/rt5514.txt
+++ b/Documentation/devicetree/bindings/sound/rt5514.txt
@@ -14,7 +14,6 @@ Optional properties:
 - clocks: The phandle of the master clock to the CODEC
 - clock-names: Should be "mclk"
 
-- interrupt-parent: The phandle for the interrupt controller.
 - interrupts: The interrupt number to the cpu. The interrupt specifier format
 	      depends on the interrupt controller.
 
diff --git a/Documentation/devicetree/bindings/sound/ts3a227e.txt b/Documentation/devicetree/bindings/sound/ts3a227e.txt
index a836881d9608..3ed8359144d3 100644
--- a/Documentation/devicetree/bindings/sound/ts3a227e.txt
+++ b/Documentation/devicetree/bindings/sound/ts3a227e.txt
@@ -10,7 +10,6 @@ Required properties:
 
  - compatible:		Should contain "ti,ts3a227e".
  - reg:			The i2c address. Should contain <0x3b>.
- - interrupt-parent:	The parent interrupt controller
  - interrupts:		Interrupt number for /INT pin from the 227e
 
 Optional properies:
diff --git a/Documentation/devicetree/bindings/sound/ux500-msp.txt b/Documentation/devicetree/bindings/sound/ux500-msp.txt
index 99acd9c774e1..7dd1b96160f5 100644
--- a/Documentation/devicetree/bindings/sound/ux500-msp.txt
+++ b/Documentation/devicetree/bindings/sound/ux500-msp.txt
@@ -6,7 +6,6 @@ Required properties:
 
 Optional properties:
  - interrupts       : The interrupt output from the device.
- - interrupt-parent : The parent interrupt controller.
  - <name>-supply    : Phandle to the regulator <name> supply
 
 Example:
diff --git a/Documentation/devicetree/bindings/sound/wm8994.txt b/Documentation/devicetree/bindings/sound/wm8994.txt
index 0795931c38a2..68cccc4653ba 100644
--- a/Documentation/devicetree/bindings/sound/wm8994.txt
+++ b/Documentation/devicetree/bindings/sound/wm8994.txt
@@ -26,7 +26,6 @@ Optional properties:
   - interrupt-controller : These devices contain interrupt controllers
     and may provide interrupt services to other devices if they have an
     interrupt line connected.
-  - interrupt-parent : The parent interrupt controller.
   - #interrupt-cells: the number of cells to describe an IRQ, this should be 2.
     The first cell is the IRQ number.
     The second cell is the flags, encoded as the trigger masks from
diff --git a/Documentation/devicetree/bindings/spi/fsl-spi.txt b/Documentation/devicetree/bindings/spi/fsl-spi.txt
index a2331372068c..8854004a1d3a 100644
--- a/Documentation/devicetree/bindings/spi/fsl-spi.txt
+++ b/Documentation/devicetree/bindings/spi/fsl-spi.txt
@@ -12,8 +12,6 @@ Required properties:
   information for the interrupt.  This should be encoded based on
   the information in section 2) depending on the type of interrupt
   controller you have.
-- interrupt-parent : the phandle for the interrupt controller that
-  services interrupts for this device.
 - clock-frequency : input clock frequency to non FSL_SOC cores
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/spi/sh-hspi.txt b/Documentation/devicetree/bindings/spi/sh-hspi.txt
index 585fed90376e..b9d1e4d11a77 100644
--- a/Documentation/devicetree/bindings/spi/sh-hspi.txt
+++ b/Documentation/devicetree/bindings/spi/sh-hspi.txt
@@ -6,8 +6,6 @@ Required properties:
 		       - "renesas,hspi-r8a7778" (R-Car M1)
 		       - "renesas,hspi-r8a7779" (R-Car H1)
 - reg              : Offset and length of the register set for the device
-- interrupt-parent : The phandle for the interrupt controller that
-		     services interrupts for this device
 - interrupts       : Interrupt specifier
 - #address-cells   : Must be <1>
 - #size-cells      : Must be <0>
diff --git a/Documentation/devicetree/bindings/spi/sh-msiof.txt b/Documentation/devicetree/bindings/spi/sh-msiof.txt
index 39806329c193..bfbc2035fb6b 100644
--- a/Documentation/devicetree/bindings/spi/sh-msiof.txt
+++ b/Documentation/devicetree/bindings/spi/sh-msiof.txt
@@ -29,8 +29,6 @@ Required properties:
 			 If two register sets are present, the first is to be
 			 used by the CPU, and the second is to be used by the
 			 DMA engine.
-- interrupt-parent     : The phandle for the interrupt controller that
-			 services interrupts for this device
 - interrupts           : Interrupt specifier
 - #address-cells       : Must be <1>
 - #size-cells          : Must be <0>
diff --git a/Documentation/devicetree/bindings/spi/spi-cadence.txt b/Documentation/devicetree/bindings/spi/spi-cadence.txt
index 94f09141a4f0..05a2ef945664 100644
--- a/Documentation/devicetree/bindings/spi/spi-cadence.txt
+++ b/Documentation/devicetree/bindings/spi/spi-cadence.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg			: Physical base address and size of SPI registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller
 - clock-names		: List of input clock names - "ref_clk", "pclk"
 			  (See clock bindings for details).
 - clocks		: Clock phandles (see clock bindings for details).
diff --git a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
index 225ace1d0c65..4af132606b37 100644
--- a/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-fsl-lpspi.txt
@@ -4,7 +4,6 @@ Required properties:
 - compatible :
   - "fsl,imx7ulp-spi" for LPSPI compatible with the one integrated on i.MX7ULP soc
 - reg : address and length of the lpspi master registers
-- interrupt-parent : core interrupt controller
 - interrupts : lpspi interrupt
 - clocks : lpspi clock specifier
 
diff --git a/Documentation/devicetree/bindings/spi/spi-rspi.txt b/Documentation/devicetree/bindings/spi/spi-rspi.txt
index 3b02b3a7cfb2..96fd58548f69 100644
--- a/Documentation/devicetree/bindings/spi/spi-rspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-rspi.txt
@@ -28,8 +28,6 @@ Required properties:
 		       - "rx" for SPRI,
 		       - "tx" to SPTI,
 		       - "mux" for a single muxed interrupt.
-- interrupt-parent : The phandle for the interrupt controller that
-		     services interrupts for this device.
 - num-cs	   : Number of chip selects. Some RSPI cores have more than 1.
 - #address-cells   : Must be <1>
 - #size-cells      : Must be <0>
diff --git a/Documentation/devicetree/bindings/spi/spi-xilinx.txt b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
index 7bf61efc66c8..dc924a5f71db 100644
--- a/Documentation/devicetree/bindings/spi/spi-xilinx.txt
+++ b/Documentation/devicetree/bindings/spi/spi-xilinx.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg			: Physical base address and size of SPI registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller
 
 Optional properties:
 - xlnx,num-ss-bits	: Number of chip selects used.
diff --git a/Documentation/devicetree/bindings/spi/spi-xlp.txt b/Documentation/devicetree/bindings/spi/spi-xlp.txt
index 40e82d51efec..f4925ec0ed33 100644
--- a/Documentation/devicetree/bindings/spi/spi-xlp.txt
+++ b/Documentation/devicetree/bindings/spi/spi-xlp.txt
@@ -13,7 +13,6 @@ Required properties:
 - reg			: Should contain register location and length.
 - clocks		: Phandle of the spi clock
 - interrupts		: Interrupt number used by this controller.
-- interrupt-parent	: Phandle of the parent interrupt controller.
 
 SPI slave nodes must be children of the SPI master node and can contain
 properties described in Documentation/devicetree/bindings/spi/spi-bus.txt.
diff --git a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
index c8f50e5cf70b..0f6d37ff541c 100644
--- a/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
+++ b/Documentation/devicetree/bindings/spi/spi-zynqmp-qspi.txt
@@ -6,7 +6,6 @@ Required properties:
 - reg			: Physical base address and size of GQSPI registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
-- interrupt-parent	: Must be core interrupt controller.
 - clock-names		: List of input clock names - "ref_clk", "pclk"
 			  (See clock bindings for details).
 - clocks		: Clock phandles (see clock bindings for details).
diff --git a/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt b/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt
index 02ea23a63f20..88bc94fe1f6d 100644
--- a/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt
+++ b/Documentation/devicetree/bindings/staging/iio/adc/spear-adc.txt
@@ -3,8 +3,6 @@
 Required properties:
 - compatible: Should be "st,spear600-adc"
 - reg: Address and length of the register set for the device
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the ADC interrupt
 - sampling-frequency: Default sampling frequency
 
diff --git a/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt b/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt
index 9d43553a8d39..43a9ed545944 100644
--- a/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt
+++ b/Documentation/devicetree/bindings/thermal/brcm,avs-tmon.txt
@@ -7,7 +7,6 @@ Required properties:
 - reg: address range for the AVS TMON registers
 - interrupts: temperature monitor interrupt, for high/low threshold triggers
 - interrupt-names: should be "tmon"
-- interrupt-parent: the parent interrupt controller
 
 Example:
 
diff --git a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
index ad648d93d961..33004ce7e5df 100644
--- a/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/exynos-thermal.txt
@@ -13,7 +13,6 @@
 			Exynos5420 (Must pass triminfo base and triminfo clock)
                "samsung,exynos5433-tmu"
 	       "samsung,exynos7-tmu"
-- interrupt-parent : The phandle for the interrupt controller
 - reg : Address range of the thermal registers. For soc's which has multiple
 	instances of TMU and some registers are shared across all TMU's like
 	interrupt related then 2 set of register has to supplied. First set
diff --git a/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt b/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt
index 904a5846d7ac..e698e3488735 100644
--- a/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt
+++ b/Documentation/devicetree/bindings/timer/altr,timer-1.0.txt
@@ -4,7 +4,6 @@ Required properties:
 
 - compatible : should be "altr,timer-1.0"
 - reg : Specifies base physical address and size of the registers.
-- interrupt-parent: phandle of the interrupt controller
 - interrupts : Should contain the timer interrupt number
 - clock-frequency : The frequency of the clock that drives the counter, in Hz.
 
diff --git a/Documentation/devicetree/bindings/timer/fsl,gtm.txt b/Documentation/devicetree/bindings/timer/fsl,gtm.txt
index 9a33efded4bc..fc1c571f7412 100644
--- a/Documentation/devicetree/bindings/timer/fsl,gtm.txt
+++ b/Documentation/devicetree/bindings/timer/fsl,gtm.txt
@@ -7,7 +7,6 @@ Required properties:
     "fsl,<chip>-cpm2-gtm", "fsl,cpm2-gtm", "fsl,gtm" for CPM2 GTMs
   - reg : should contain gtm registers location and length (0x40).
   - interrupts : should contain four interrupts.
-  - interrupt-parent : interrupt source phandle.
   - clock-frequency : specifies the frequency driving the timer.
 
 Example:
diff --git a/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt b/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt
index 62bb8260cf6a..cd1a0c256f94 100644
--- a/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt
+++ b/Documentation/devicetree/bindings/timer/marvell,orion-timer.txt
@@ -3,7 +3,6 @@ Marvell Orion SoC timer
 Required properties:
 - compatible: shall be "marvell,orion-timer"
 - reg: base address of the timer register starting with TIMERS CONTROL register
-- interrupt-parent: phandle of the bridge interrupt controller
 - interrupts: should contain the interrupts for Timer0 and Timer1
 - clocks: phandle of timer reference clock (tclk)
 
diff --git a/Documentation/devicetree/bindings/timer/snps,arc-timer.txt b/Documentation/devicetree/bindings/timer/snps,arc-timer.txt
index 4ef024630d61..147ef3e74452 100644
--- a/Documentation/devicetree/bindings/timer/snps,arc-timer.txt
+++ b/Documentation/devicetree/bindings/timer/snps,arc-timer.txt
@@ -12,10 +12,6 @@ Required properties:
 	       (16 for ARCHS cores, 3 for ARC700 cores)
 - clocks     : phandle to the source clock
 
-Optional properties:
-
-- interrupt-parent : phandle to parent intc
-
 Example:
 
 	timer0 {
diff --git a/Documentation/devicetree/bindings/timer/st,spear-timer.txt b/Documentation/devicetree/bindings/timer/st,spear-timer.txt
index c0017221cf55..b5238a07da17 100644
--- a/Documentation/devicetree/bindings/timer/st,spear-timer.txt
+++ b/Documentation/devicetree/bindings/timer/st,spear-timer.txt
@@ -5,8 +5,6 @@
 - compatible : Should be:
 	"st,spear-timer"
 - reg: Address range of the timer registers
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupt: Should contain the timer interrupt number
 
 Example:
diff --git a/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt b/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt
index 95911fe70224..d96c1e283e73 100644
--- a/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt
+++ b/Documentation/devicetree/bindings/timer/ti,c64x+timer64.txt
@@ -7,7 +7,6 @@ Required properties:
 
 - compatible: must be "ti,c64x+timer64"
 - reg: base address and size of register region
-- interrupt-parent: interrupt controller
 - interrupts: interrupt id
 
 Optional properties:
diff --git a/Documentation/devicetree/bindings/usb/fsl-usb.txt b/Documentation/devicetree/bindings/usb/fsl-usb.txt
index 4779c029b675..0b08b006c5ea 100644
--- a/Documentation/devicetree/bindings/usb/fsl-usb.txt
+++ b/Documentation/devicetree/bindings/usb/fsl-usb.txt
@@ -33,8 +33,6 @@ Recommended properties :
    information for the interrupt.  This should be encoded based on
    the information in section 2) depending on the type of interrupt
    controller you have.
- - interrupt-parent : the phandle for the interrupt controller that
-   services interrupts for this device.
 
 Optional properties :
  - fsl,invert-drvvbus : boolean; for MPC5121 USB0 only. Indicates the
diff --git a/Documentation/devicetree/bindings/usb/maxim,max3421.txt b/Documentation/devicetree/bindings/usb/maxim,max3421.txt
index 8cdbe0c85188..90495b1aeec2 100644
--- a/Documentation/devicetree/bindings/usb/maxim,max3421.txt
+++ b/Documentation/devicetree/bindings/usb/maxim,max3421.txt
@@ -11,9 +11,6 @@ Required properties:
    The driver configures MAX3421E for active low level triggered interrupts,
    configure your interrupt line accordingly.
 
-Optional property:
- - interrupt-parent: the phandle to the associated interrupt controller.
-
 Example:
 
 	usb@0 {
diff --git a/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt b/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
index 09e847e92e5e..d4cf53c071d9 100644
--- a/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
+++ b/Documentation/devicetree/bindings/usb/richtek,rt1711h.txt
@@ -3,8 +3,6 @@ Richtek RT1711H TypeC PD Controller.
 Required properties:
  - compatible : Must be "richtek,rt1711h".
  - reg : Must be 0x4e, it's slave address of RT1711H.
- - interrupt-parent : the phandle for the interrupt controller that
-   provides interrupts for this device.
  - interrupts : <a b> where a is the interrupt number and b represents an
    encoding of the sense and level information for the interrupt.
 
diff --git a/Documentation/devicetree/bindings/usb/samsung-hsotg.txt b/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
index b83d428a265e..0388634598ce 100644
--- a/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
+++ b/Documentation/devicetree/bindings/usb/samsung-hsotg.txt
@@ -14,8 +14,6 @@ Binding details
 Required properties:
 - compatible: "samsung,s3c6400-hsotg" should be used for all currently
     supported SoC,
-- interrupt-parent: phandle for the interrupt controller to which the
-    interrupt signal of the HSOTG block is routed,
 - interrupts: specifier of interrupt signal of interrupt controller,
     according to bindings of interrupt controller,
 - clocks: contains an array of clock specifiers:
diff --git a/Documentation/devicetree/bindings/usb/spear-usb.txt b/Documentation/devicetree/bindings/usb/spear-usb.txt
index f8a464a25653..1dc91cc459c0 100644
--- a/Documentation/devicetree/bindings/usb/spear-usb.txt
+++ b/Documentation/devicetree/bindings/usb/spear-usb.txt
@@ -6,8 +6,6 @@ EHCI:
 
 Required properties:
 - compatible: "st,spear600-ehci"
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the EHCI interrupt
 
 Example:
@@ -25,8 +23,6 @@ OHCI:
 
 Required properties:
 - compatible: "st,spear600-ohci"
-- interrupt-parent: Should be the phandle for the interrupt controller
-  that services interrupts for this device
 - interrupts: Should contain the OHCI interrupt
 
 Example:
diff --git a/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt b/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt
index c3a36ee45552..750a87657448 100644
--- a/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/cadence-wdt.txt
@@ -5,7 +5,6 @@ Required properties:
 - compatible		: Should be "cdns,wdt-r1p2".
 - clocks		: This is pclk (APB clock).
 - interrupts		: This is wd_irq - watchdog timeout interrupt.
-- interrupt-parent	: Must be core interrupt controller.
 
 Optional properties
 - reset-on-timeout	: If this property exists, then a reset is done
diff --git a/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt b/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt
index d7bab3db9d1f..05b95bfa2a89 100644
--- a/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt
+++ b/Documentation/devicetree/bindings/watchdog/rt2880-wdt.txt
@@ -5,7 +5,6 @@ Required properties:
 - reg: physical base address of the controller and length of the register range
 
 Optional properties:
-- interrupt-parent: phandle to the INTC device node
 - interrupts: Specify the INTC interrupt number
 
 Example:
diff --git a/Documentation/devicetree/bindings/xilinx.txt b/Documentation/devicetree/bindings/xilinx.txt
index 1d11b9002ef8..d058ace29345 100644
--- a/Documentation/devicetree/bindings/xilinx.txt
+++ b/Documentation/devicetree/bindings/xilinx.txt
@@ -49,7 +49,7 @@
    followed by an older IP core version which implements the same
    interface or any other device with the same interface.
 
-   'reg', 'interrupt-parent' and 'interrupts' are all optional properties.
+   'reg' and 'interrupts' are all optional properties.
 
    For example, the following block from system.mhs:
 
diff --git a/Documentation/devicetree/bindings/xillybus/xillybus.txt b/Documentation/devicetree/bindings/xillybus/xillybus.txt
index 9e316dc2e40f..e65d1f94b49c 100644
--- a/Documentation/devicetree/bindings/xillybus/xillybus.txt
+++ b/Documentation/devicetree/bindings/xillybus/xillybus.txt
@@ -4,8 +4,6 @@ Required properties:
 - compatible: Should be "xillybus,xillybus-1.00.a"
 - reg: Address and length of the register set for the device
 - interrupts: Contains one interrupt node, typically consisting of three cells.
-- interrupt-parent: the phandle for the interrupt controller that
-                    services interrupts for this device.
 
 Optional properties:
 - dma-coherent: Present if DMA operations are coherent
-- 
cgit v1.2.3


From 11177e7a7aaef95935592072985526ebf0a3df43 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Fri, 13 Jul 2018 13:13:20 +0200
Subject: clk: imx6ul: fix missing of_node_put()

of_find_compatible_node() is returning a device node with refcount
incremented and must be explicitly decremented after the last use
which is right after the us in of_iomap() here.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Fixes: 787b4271a6a0 ("clk: imx: add imx6ul clk tree support")
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6ul.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
index ba563ba50b40..9f1a40498642 100644
--- a/drivers/clk/imx/clk-imx6ul.c
+++ b/drivers/clk/imx/clk-imx6ul.c
@@ -142,6 +142,7 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-anatop");
 	base = of_iomap(np, 0);
+	of_node_put(np);
 	WARN_ON(!base);
 
 	clks[IMX6UL_PLL1_BYPASS_SRC] = imx_clk_mux("pll1_bypass_src", base + 0x00, 14, 1, pll_bypass_src_sels, ARRAY_SIZE(pll_bypass_src_sels));
-- 
cgit v1.2.3


From 7f5eac5934d747535f9ffc997792a0a6eb289374 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Fri, 13 Jul 2018 18:40:04 +0200
Subject: clk: imx6sll: fix missing of_node_put()

of_find_compatible_node() is returning a device node with refcount
incremented and must be explicitly decremented after the last use
which is right after the us in of_iomap() here.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Fixes: 4a5f720b6542 ("clk: imx: add clock driver for imx6sll")
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/imx/clk-imx6sll.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/imx/clk-imx6sll.c b/drivers/clk/imx/clk-imx6sll.c
index 3651c77fbabe..645d8a42007c 100644
--- a/drivers/clk/imx/clk-imx6sll.c
+++ b/drivers/clk/imx/clk-imx6sll.c
@@ -92,6 +92,7 @@ static void __init imx6sll_clocks_init(struct device_node *ccm_node)
 
 	np = of_find_compatible_node(NULL, NULL, "fsl,imx6sll-anatop");
 	base = of_iomap(np, 0);
+	of_node_put(np);
 	WARN_ON(!base);
 
 	/* Do not bypass PLLs initially */
-- 
cgit v1.2.3


From 16f6e9835bcd33adac49bc2cad2ec7bbf5dfa356 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 18:19:14 +0200
Subject: net: ethernet: freescale: Use generic CRC32 implementation

Use generic kernel CRC32 implementation because it:
1. Should be faster (uses lookup tables),
2. Removes duplicated CRC generation code,
3. Uses well-proven algorithm instead of coding it one more time.

Suggested-by: Eric Biggers <ebiggers3@gmail.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 13 +++----------
 1 file changed, 3 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c729665107f5..98ad34192255 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -48,6 +48,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/clk.h>
+#include <linux/crc32.h>
 #include <linux/platform_device.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
@@ -2955,7 +2956,7 @@ static void set_multicast_list(struct net_device *ndev)
 {
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	struct netdev_hw_addr *ha;
-	unsigned int i, bit, data, crc, tmp;
+	unsigned int crc, tmp;
 	unsigned char hash;
 	unsigned int hash_high = 0, hash_low = 0;
 
@@ -2983,15 +2984,7 @@ static void set_multicast_list(struct net_device *ndev)
 	/* Add the addresses in hash register */
 	netdev_for_each_mc_addr(ha, ndev) {
 		/* calculate crc32 value of mac address */
-		crc = 0xffffffff;
-
-		for (i = 0; i < ndev->addr_len; i++) {
-			data = ha->addr[i];
-			for (bit = 0; bit < 8; bit++, data >>= 1) {
-				crc = (crc >> 1) ^
-				(((crc ^ data) & 1) ? CRC32_POLY : 0);
-			}
-		}
+		crc = ether_crc_le(ndev->addr_len, ha->addr);
 
 		/* only upper 6 bits (FEC_HASH_BITS) are used
 		 * which point to specific bit in the hash registers
-- 
cgit v1.2.3


From d805f6a8682937d7f8136fe7561659b13f5aaa49 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 23 Jul 2018 18:20:20 +0200
Subject: net: ethernet: fs-enet: Use generic CRC32 implementation

Use generic kernel CRC32 implementation because it:
1. Should be faster (uses lookup tables),
2. Removes duplicated CRC generation code,
3. Uses well-proven algorithm instead of coding it one more time.

Suggested-by: Eric Biggers <ebiggers3@gmail.com>
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c | 18 ++++--------------
 1 file changed, 4 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index 1fc27c97e3b2..99fe2c210d0f 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -18,6 +18,7 @@
 #include <linux/string.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
+#include <linux/crc32.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
@@ -176,21 +177,10 @@ static void set_multicast_start(struct net_device *dev)
 static void set_multicast_one(struct net_device *dev, const u8 *mac)
 {
 	struct fs_enet_private *fep = netdev_priv(dev);
-	int temp, hash_index, i, j;
+	int temp, hash_index;
 	u32 crc, csrVal;
-	u8 byte, msb;
-
-	crc = 0xffffffff;
-	for (i = 0; i < 6; i++) {
-		byte = mac[i];
-		for (j = 0; j < 8; j++) {
-			msb = crc >> 31;
-			crc <<= 1;
-			if (msb ^ (byte & 0x1))
-				crc ^= FEC_CRC_POLY;
-			byte >>= 1;
-		}
-	}
+
+	crc = ether_crc(6, mac);
 
 	temp = (crc & 0x3f) >> 1;
 	hash_index = ((temp & 0x01) << 4) |
-- 
cgit v1.2.3


From 3c507b8af638c67d4a80d70091d2057ecb01e8a6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 23 Jul 2018 21:40:07 +0200
Subject: net: phy: add helper phy_polling_mode

Add a helper for checking whether polling is used to detect PHY status
changes.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy.c |  8 ++++----
 include/linux/phy.h   | 10 ++++++++++
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 04780db4c963..1ee25877c4d1 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -525,7 +525,7 @@ static int phy_start_aneg_priv(struct phy_device *phydev, bool sync)
 	 * negotiation may already be done and aneg interrupt may not be
 	 * generated.
 	 */
-	if (phydev->irq != PHY_POLL && phydev->state == PHY_AN) {
+	if (!phy_polling_mode(phydev) && phydev->state == PHY_AN) {
 		err = phy_aneg_done(phydev);
 		if (err > 0) {
 			trigger = true;
@@ -983,7 +983,7 @@ void phy_state_machine(struct work_struct *work)
 			needs_aneg = true;
 		break;
 	case PHY_NOLINK:
-		if (phydev->irq != PHY_POLL)
+		if (!phy_polling_mode(phydev))
 			break;
 
 		err = phy_read_status(phydev);
@@ -1024,7 +1024,7 @@ void phy_state_machine(struct work_struct *work)
 		/* Only register a CHANGE if we are polling and link changed
 		 * since latest checking.
 		 */
-		if (phydev->irq == PHY_POLL) {
+		if (phy_polling_mode(phydev)) {
 			old_link = phydev->link;
 			err = phy_read_status(phydev);
 			if (err)
@@ -1123,7 +1123,7 @@ void phy_state_machine(struct work_struct *work)
 	 * PHY, if PHY_IGNORE_INTERRUPT is set, then we will be moving
 	 * between states from phy_mac_interrupt()
 	 */
-	if (phydev->irq == PHY_POLL)
+	if (phy_polling_mode(phydev))
 		queue_delayed_work(system_power_efficient_wq, &phydev->state_queue,
 				   PHY_STATE_TIME * HZ);
 }
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 075c2f770d3e..cd6f637cbbfb 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -824,6 +824,16 @@ static inline bool phy_interrupt_is_valid(struct phy_device *phydev)
 	return phydev->irq != PHY_POLL && phydev->irq != PHY_IGNORE_INTERRUPT;
 }
 
+/**
+ * phy_polling_mode - Convenience function for testing whether polling is
+ * used to detect PHY status changes
+ * @phydev: the phy_device struct
+ */
+static inline bool phy_polling_mode(struct phy_device *phydev)
+{
+	return phydev->irq == PHY_POLL;
+}
+
 /**
  * phy_is_internal - Convenience function for testing if a PHY is internal
  * @phydev: the phy_device struct
-- 
cgit v1.2.3


From 0cbb61a313979b53d6b2dc838a92f07471440708 Mon Sep 17 00:00:00 2001
From: Aapo Vienamo <avienamo@nvidia.com>
Date: Thu, 12 Jul 2018 14:52:59 +0300
Subject: clk: tegra: Fix includes required by fence_udelay()

Add the missing linux/delay.h include statement for udelay() used by
fence_udelay() macro.

Signed-off-by: Aapo Vienamo <avienamo@nvidia.com>
Acked-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index e1f88463b600..e3b9c22ad8b2 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -19,6 +19,7 @@
 
 #include <linux/clk-provider.h>
 #include <linux/clkdev.h>
+#include <linux/delay.h>
 
 /**
  * struct tegra_clk_sync_source - external clock source from codec
-- 
cgit v1.2.3


From cb3ac5947afb3bb7e2f89c1b59f61dcf3e115fe1 Mon Sep 17 00:00:00 2001
From: Peter De Schrijver <pdeschrijver@nvidia.com>
Date: Thu, 12 Jul 2018 14:53:00 +0300
Subject: clk: tegra: Refactor fractional divider calculation

Move this to a separate file so it can be used to calculate the sdmmc
clock dividers.

Signed-off-by: Peter De-Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Aapo Vienamo <avienamo@nvidia.com>
Acked-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/Makefile      |  1 +
 drivers/clk/tegra/clk-divider.c | 30 +++++-----------------------
 drivers/clk/tegra/clk-utils.c   | 43 +++++++++++++++++++++++++++++++++++++++++
 drivers/clk/tegra/clk.h         |  3 +++
 4 files changed, 52 insertions(+), 25 deletions(-)
 create mode 100644 drivers/clk/tegra/clk-utils.c

diff --git a/drivers/clk/tegra/Makefile b/drivers/clk/tegra/Makefile
index b71692391bd6..c77d072eb333 100644
--- a/drivers/clk/tegra/Makefile
+++ b/drivers/clk/tegra/Makefile
@@ -24,3 +24,4 @@ obj-$(CONFIG_ARCH_TEGRA_132_SOC)	+= clk-tegra124.o
 obj-y					+= cvb.o
 obj-$(CONFIG_ARCH_TEGRA_210_SOC)	+= clk-tegra210.o
 obj-$(CONFIG_CLK_TEGRA_BPMP)		+= clk-bpmp.o
+obj-y					+= clk-utils.o
diff --git a/drivers/clk/tegra/clk-divider.c b/drivers/clk/tegra/clk-divider.c
index 16e0aee14773..8f175ff62f73 100644
--- a/drivers/clk/tegra/clk-divider.c
+++ b/drivers/clk/tegra/clk-divider.c
@@ -32,35 +32,15 @@
 static int get_div(struct tegra_clk_frac_div *divider, unsigned long rate,
 		   unsigned long parent_rate)
 {
-	u64 divider_ux1 = parent_rate;
-	u8 flags = divider->flags;
-	int mul;
-
-	if (!rate)
-		return 0;
-
-	mul = get_mul(divider);
-
-	if (!(flags & TEGRA_DIVIDER_INT))
-		divider_ux1 *= mul;
-
-	if (flags & TEGRA_DIVIDER_ROUND_UP)
-		divider_ux1 += rate - 1;
-
-	do_div(divider_ux1, rate);
-
-	if (flags & TEGRA_DIVIDER_INT)
-		divider_ux1 *= mul;
+	int div;
 
-	divider_ux1 -= mul;
+	div = div_frac_get(rate, parent_rate, divider->width,
+			   divider->frac_width, divider->flags);
 
-	if ((s64)divider_ux1 < 0)
+	if (div < 0)
 		return 0;
 
-	if (divider_ux1 > get_max_div(divider))
-		return get_max_div(divider);
-
-	return divider_ux1;
+	return div;
 }
 
 static unsigned long clk_frac_div_recalc_rate(struct clk_hw *hw,
diff --git a/drivers/clk/tegra/clk-utils.c b/drivers/clk/tegra/clk-utils.c
new file mode 100644
index 000000000000..1a5daae4e501
--- /dev/null
+++ b/drivers/clk/tegra/clk-utils.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, NVIDIA CORPORATION.  All rights reserved.
+ */
+
+#include <asm/div64.h>
+
+#include "clk.h"
+
+#define div_mask(w) ((1 << (w)) - 1)
+
+int div_frac_get(unsigned long rate, unsigned parent_rate, u8 width,
+		 u8 frac_width, u8 flags)
+{
+	u64 divider_ux1 = parent_rate;
+	int mul;
+
+	if (!rate)
+		return 0;
+
+	mul = 1 << frac_width;
+
+	if (!(flags & TEGRA_DIVIDER_INT))
+		divider_ux1 *= mul;
+
+	if (flags & TEGRA_DIVIDER_ROUND_UP)
+		divider_ux1 += rate - 1;
+
+	do_div(divider_ux1, rate);
+
+	if (flags & TEGRA_DIVIDER_INT)
+		divider_ux1 *= mul;
+
+	if (divider_ux1 < mul)
+		return 0;
+
+	divider_ux1 -= mul;
+
+	if (divider_ux1 > div_mask(width))
+		return div_mask(width);
+
+	return divider_ux1;
+}
diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index e3b9c22ad8b2..c733841aa6db 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -812,6 +812,9 @@ extern tegra_clk_apply_init_table_func tegra_clk_apply_init_table;
 int tegra_pll_wait_for_lock(struct tegra_clk_pll *pll);
 u16 tegra_pll_get_fixed_mdiv(struct clk_hw *hw, unsigned long input_rate);
 int tegra_pll_p_div_to_hw(struct tegra_clk_pll *pll, u8 p_div);
+int div_frac_get(unsigned long rate, unsigned parent_rate, u8 width,
+		 u8 frac_width, u8 flags);
+
 
 /* Combined read fence with delay */
 #define fence_udelay(delay, reg)	\
-- 
cgit v1.2.3


From 633e79650b4f0ed8cd26076a376b5372c413b0f8 Mon Sep 17 00:00:00 2001
From: Peter De-Schrijver <pdeschrijver@nvidia.com>
Date: Thu, 12 Jul 2018 14:53:01 +0300
Subject: clk: tegra: Add sdmmc mux divider clock

Add a clock type to model the sdmmc switch divider clocks which have paths
to source clocks bypassing the divider (Low Jitter paths). These
are handled by selecting the lj path when the divider is 1 (ie the
rate is the parent rate), otherwise the normal path with divider
will be selected. Otherwise this clock behaves as a normal peripheral
clock.

Signed-off-by: Peter De-Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Aapo Vienamo <avienamo@nvidia.com>
Acked-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/Makefile        |   1 +
 drivers/clk/tegra/clk-sdmmc-mux.c | 251 ++++++++++++++++++++++++++++++++++++++
 drivers/clk/tegra/clk.h           |  26 ++++
 3 files changed, 278 insertions(+)
 create mode 100644 drivers/clk/tegra/clk-sdmmc-mux.c

diff --git a/drivers/clk/tegra/Makefile b/drivers/clk/tegra/Makefile
index c77d072eb333..6507acc843c7 100644
--- a/drivers/clk/tegra/Makefile
+++ b/drivers/clk/tegra/Makefile
@@ -8,6 +8,7 @@ obj-y					+= clk-periph-fixed.o
 obj-y					+= clk-periph-gate.o
 obj-y					+= clk-pll.o
 obj-y					+= clk-pll-out.o
+obj-y					+= clk-sdmmc-mux.o
 obj-y					+= clk-super.o
 obj-y					+= clk-tegra-audio.o
 obj-y					+= clk-tegra-periph.o
diff --git a/drivers/clk/tegra/clk-sdmmc-mux.c b/drivers/clk/tegra/clk-sdmmc-mux.c
new file mode 100644
index 000000000000..473d418533cb
--- /dev/null
+++ b/drivers/clk/tegra/clk-sdmmc-mux.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 NVIDIA CORPORATION.  All rights reserved.
+ *
+ * based on clk-mux.c
+ *
+ * Copyright (C) 2011 Sascha Hauer, Pengutronix <s.hauer@pengutronix.de>
+ * Copyright (C) 2011 Richard Zhao, Linaro <richard.zhao@linaro.org>
+ * Copyright (C) 2011-2012 Mike Turquette, Linaro Ltd <mturquette@linaro.org>
+ *
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/err.h>
+#include <linux/types.h>
+
+#include "clk.h"
+
+#define DIV_MASK GENMASK(7, 0)
+#define MUX_SHIFT 29
+#define MUX_MASK GENMASK(MUX_SHIFT + 2, MUX_SHIFT)
+#define SDMMC_MUL 2
+
+#define get_max_div(d) DIV_MASK
+#define get_div_field(val) ((val) & DIV_MASK)
+#define get_mux_field(val) (((val) & MUX_MASK) >> MUX_SHIFT)
+
+static const char * const mux_sdmmc_parents[] = {
+	"pll_p", "pll_c4_out2", "pll_c4_out0", "pll_c4_out1", "clk_m"
+};
+
+static const u8 mux_lj_idx[] = {
+	[0] = 0, [1] = 1, [2] = 2, [3] = 5, [4] = 6
+};
+
+static const u8 mux_non_lj_idx[] = {
+	[0] = 0, [1] = 3, [2] = 7, [3] = 4, [4] = 6
+};
+
+static u8 clk_sdmmc_mux_get_parent(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	int num_parents, i;
+	u32 src, val;
+	const u8 *mux_idx;
+
+	num_parents = clk_hw_get_num_parents(hw);
+
+	val = readl_relaxed(sdmmc_mux->reg);
+	src = get_mux_field(val);
+	if (get_div_field(val))
+		mux_idx = mux_non_lj_idx;
+	else
+		mux_idx = mux_lj_idx;
+
+	for (i = 0; i < num_parents; i++) {
+		if (mux_idx[i] == src)
+			return i;
+	}
+
+	WARN(1, "Unknown parent selector %d\n", src);
+
+	return 0;
+}
+
+static int clk_sdmmc_mux_set_parent(struct clk_hw *hw, u8 index)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	u32 val;
+
+
+	val = readl_relaxed(sdmmc_mux->reg);
+	if (get_div_field(val))
+		index = mux_non_lj_idx[index];
+	else
+		index = mux_lj_idx[index];
+
+	val &= ~MUX_MASK;
+	val |= index << MUX_SHIFT;
+
+	writel(val, sdmmc_mux->reg);
+
+	return 0;
+}
+
+static unsigned long clk_sdmmc_mux_recalc_rate(struct clk_hw *hw,
+					       unsigned long parent_rate)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	u32 val;
+	int div;
+	u64 rate = parent_rate;
+
+	val = readl_relaxed(sdmmc_mux->reg);
+	div = get_div_field(val);
+
+	div += SDMMC_MUL;
+
+	rate *= SDMMC_MUL;
+	rate += div - 1;
+	do_div(rate, div);
+
+	return rate;
+}
+
+static int clk_sdmmc_mux_determine_rate(struct clk_hw *hw,
+					struct clk_rate_request *req)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	int div;
+	unsigned long output_rate = req->best_parent_rate;
+
+	req->rate = max(req->rate, req->min_rate);
+	req->rate = min(req->rate, req->max_rate);
+
+	if (!req->rate)
+		return output_rate;
+
+	div = div_frac_get(req->rate, output_rate, 8, 1, sdmmc_mux->div_flags);
+	if (div < 0)
+		div = 0;
+
+	if (sdmmc_mux->div_flags & TEGRA_DIVIDER_ROUND_UP)
+		req->rate =  DIV_ROUND_UP(output_rate * SDMMC_MUL,
+					  div + SDMMC_MUL);
+	else
+		req->rate =  output_rate * SDMMC_MUL / (div + SDMMC_MUL);
+
+	return 0;
+}
+
+static int clk_sdmmc_mux_set_rate(struct clk_hw *hw, unsigned long rate,
+				  unsigned long parent_rate)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	int div;
+	unsigned long flags = 0;
+	u32 val;
+	u8 src;
+
+	div = div_frac_get(rate, parent_rate, 8, 1, sdmmc_mux->div_flags);
+	if (div < 0)
+		return div;
+
+	if (sdmmc_mux->lock)
+		spin_lock_irqsave(sdmmc_mux->lock, flags);
+
+	src = clk_sdmmc_mux_get_parent(hw);
+	if (div)
+		src = mux_non_lj_idx[src];
+	else
+		src = mux_lj_idx[src];
+
+	val = src << MUX_SHIFT;
+	val |= div;
+	writel(val, sdmmc_mux->reg);
+	fence_udelay(2, sdmmc_mux->reg);
+
+	if (sdmmc_mux->lock)
+		spin_unlock_irqrestore(sdmmc_mux->lock, flags);
+
+	return 0;
+}
+
+static int clk_sdmmc_mux_is_enabled(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+	struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+	__clk_hw_set_clk(gate_hw, hw);
+
+	return gate_ops->is_enabled(gate_hw);
+}
+
+static int clk_sdmmc_mux_enable(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+	struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+	__clk_hw_set_clk(gate_hw, hw);
+
+	return gate_ops->enable(gate_hw);
+}
+
+static void clk_sdmmc_mux_disable(struct clk_hw *hw)
+{
+	struct tegra_sdmmc_mux *sdmmc_mux = to_clk_sdmmc_mux(hw);
+	const struct clk_ops *gate_ops = sdmmc_mux->gate_ops;
+	struct clk_hw *gate_hw = &sdmmc_mux->gate.hw;
+
+	gate_ops->disable(gate_hw);
+}
+
+static const struct clk_ops tegra_clk_sdmmc_mux_ops = {
+	.get_parent = clk_sdmmc_mux_get_parent,
+	.set_parent = clk_sdmmc_mux_set_parent,
+	.determine_rate = clk_sdmmc_mux_determine_rate,
+	.recalc_rate = clk_sdmmc_mux_recalc_rate,
+	.set_rate = clk_sdmmc_mux_set_rate,
+	.is_enabled = clk_sdmmc_mux_is_enabled,
+	.enable = clk_sdmmc_mux_enable,
+	.disable = clk_sdmmc_mux_disable,
+};
+
+struct clk *tegra_clk_register_sdmmc_mux_div(const char *name,
+	void __iomem *clk_base, u32 offset, u32 clk_num, u8 div_flags,
+	unsigned long flags, void *lock)
+{
+	struct clk *clk;
+	struct clk_init_data init;
+	const struct tegra_clk_periph_regs *bank;
+	struct tegra_sdmmc_mux *sdmmc_mux;
+
+	init.ops = &tegra_clk_sdmmc_mux_ops;
+	init.name = name;
+	init.flags = flags;
+	init.parent_names = mux_sdmmc_parents;
+	init.num_parents = ARRAY_SIZE(mux_sdmmc_parents);
+
+	bank = get_reg_bank(clk_num);
+	if (!bank)
+		return ERR_PTR(-EINVAL);
+
+	sdmmc_mux = kzalloc(sizeof(*sdmmc_mux), GFP_KERNEL);
+	if (!sdmmc_mux)
+		return ERR_PTR(-ENOMEM);
+
+	/* Data in .init is copied by clk_register(), so stack variable OK */
+	sdmmc_mux->hw.init = &init;
+	sdmmc_mux->reg = clk_base + offset;
+	sdmmc_mux->lock = lock;
+	sdmmc_mux->gate.clk_base = clk_base;
+	sdmmc_mux->gate.regs = bank;
+	sdmmc_mux->gate.enable_refcnt = periph_clk_enb_refcnt;
+	sdmmc_mux->gate.clk_num = clk_num;
+	sdmmc_mux->gate.flags = TEGRA_PERIPH_ON_APB;
+	sdmmc_mux->div_flags = div_flags;
+	sdmmc_mux->gate_ops = &tegra_clk_periph_gate_ops;
+
+	clk = clk_register(NULL, &sdmmc_mux->hw);
+	if (IS_ERR(clk)) {
+		kfree(sdmmc_mux);
+		return clk;
+	}
+
+	sdmmc_mux->gate.hw.clk = clk;
+
+	return clk;
+}
diff --git a/drivers/clk/tegra/clk.h b/drivers/clk/tegra/clk.h
index c733841aa6db..d2c3a010f8e9 100644
--- a/drivers/clk/tegra/clk.h
+++ b/drivers/clk/tegra/clk.h
@@ -706,6 +706,32 @@ struct clk *tegra_clk_register_super_clk(const char *name,
 		const char * const *parent_names, u8 num_parents,
 		unsigned long flags, void __iomem *reg, u8 clk_super_flags,
 		spinlock_t *lock);
+
+/**
+ * struct tegra_sdmmc_mux - switch divider with Low Jitter inputs for SDMMC
+ *
+ * @hw:		handle between common and hardware-specific interfaces
+ * @reg:	register controlling mux and divider
+ * @flags:	hardware-specific flags
+ * @lock:	optional register lock
+ * @gate:	gate clock
+ * @gate_ops:	gate clock ops
+ */
+struct tegra_sdmmc_mux {
+	struct clk_hw		hw;
+	void __iomem		*reg;
+	spinlock_t		*lock;
+	const struct clk_ops	*gate_ops;
+	struct tegra_clk_periph_gate	gate;
+	u8			div_flags;
+};
+
+#define to_clk_sdmmc_mux(_hw) container_of(_hw, struct tegra_sdmmc_mux, hw)
+
+struct clk *tegra_clk_register_sdmmc_mux_div(const char *name,
+		void __iomem *clk_base, u32 offset, u32 clk_num, u8 div_flags,
+		unsigned long flags, void *lock);
+
 /**
  * struct clk_init_table - clock initialization table
  * @clk_id:	clock id as mentioned in device tree bindings
-- 
cgit v1.2.3


From bc510d59cf173d9b239173580fc9f44523256135 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 23 Jul 2018 15:59:46 -0500
Subject: vxge: Remove unnecessary include of <linux/pci_hotplug.h>

The vxge driver doesn't need anything provided by pci_hotplug.h, so remove
the unnecessary include of it.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jon Mason <jdmason@kudzu.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/neterion/vxge/vxge-config.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index 358ed6118881..a2c0a93ca8b6 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -14,7 +14,6 @@
 #include <linux/vmalloc.h>
 #include <linux/etherdevice.h>
 #include <linux/pci.h>
-#include <linux/pci_hotplug.h>
 #include <linux/slab.h>
 
 #include "vxge-traffic.h"
-- 
cgit v1.2.3


From 776125785a87ff05d49938bd5b9f336f2a05bff6 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Wed, 25 Jul 2018 18:45:08 +0100
Subject: gfs2: Special-case rindex for gfs2_grow

To speed up the common case of appending to a file,
gfs2_write_alloc_required presumes that writing beyond the end of a file
will always require additional blocks to be allocated.  This assumption
is incorrect for preallocates files, but there are no negative
consequences as long as *some* space is still left on the filesystem.

One special file that always has some space preallocated beyond the end
of the file is the rindex: when growing a filesystem, gfs2_grow adds one
or more new resource groups and appends records describing those
resource groups to the rindex; the preallocated space ensures that this
is always possible.

However, when a filesystem is completely full, gfs2_write_alloc_required
will indicate that an additional allocation is required, and appending
the next record to the rindex will fail even though space for that
record has already been preallocated.  To fix that, skip the incorrect
optimization in gfs2_write_alloc_required, but for the rindex only.
Other writes to preallocated space beyond the end of the file are still
allowed to fail on completely full filesystems.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/bmap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 89f1f7d3186d..03128ed1f34e 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -2316,7 +2316,7 @@ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
 	end_of_file = (i_size_read(&ip->i_inode) + sdp->sd_sb.sb_bsize - 1) >> shift;
 	lblock = offset >> shift;
 	lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
-	if (lblock_stop > end_of_file)
+	if (lblock_stop > end_of_file && ip != GFS2_I(sdp->sd_rindex))
 		return 1;
 
 	size = (lblock_stop - lblock) << shift;
-- 
cgit v1.2.3


From c76a69e477b88f259bcc118129874011abcaae86 Mon Sep 17 00:00:00 2001
From: Peter De-Schrijver <pdeschrijver@nvidia.com>
Date: Thu, 12 Jul 2018 14:53:02 +0300
Subject: clk: tegra: make sdmmc2 and sdmmc4 as sdmmc clocks

These clocks have low jitter paths to certain parents. To model these
correctly, use the sdmmc mux divider clock type.

Signed-off-by: Peter De-Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Aapo Vienamo <avienamo@nvidia.com>
Acked-by: Peter De Schrijver <pdeschrijver@nvidia.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/tegra/clk-id.h           |  2 --
 drivers/clk/tegra/clk-tegra-periph.c | 11 -----------
 drivers/clk/tegra/clk-tegra210.c     | 14 ++++++++++++--
 3 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/clk/tegra/clk-id.h b/drivers/clk/tegra/clk-id.h
index b616e33c5255..de466b4446da 100644
--- a/drivers/clk/tegra/clk-id.h
+++ b/drivers/clk/tegra/clk-id.h
@@ -227,13 +227,11 @@ enum clk_id {
 	tegra_clk_sdmmc1_9,
 	tegra_clk_sdmmc2,
 	tegra_clk_sdmmc2_8,
-	tegra_clk_sdmmc2_9,
 	tegra_clk_sdmmc3,
 	tegra_clk_sdmmc3_8,
 	tegra_clk_sdmmc3_9,
 	tegra_clk_sdmmc4,
 	tegra_clk_sdmmc4_8,
-	tegra_clk_sdmmc4_9,
 	tegra_clk_se,
 	tegra_clk_soc_therm,
 	tegra_clk_soc_therm_8,
diff --git a/drivers/clk/tegra/clk-tegra-periph.c b/drivers/clk/tegra/clk-tegra-periph.c
index 2acba2986bc6..38c4eb28c8bf 100644
--- a/drivers/clk/tegra/clk-tegra-periph.c
+++ b/drivers/clk/tegra/clk-tegra-periph.c
@@ -451,15 +451,6 @@ static u32 mux_pllp_pllc4_out2_pllc4_out1_clkm_pllc4_out0_idx[] = {
 	[0] = 0, [1] = 3, [2] = 4, [3] = 6, [4] = 7,
 };
 
-static const char *mux_pllp_clkm_pllc4_out2_out1_out0_lj[] = {
-	"pll_p",
-	"pll_c4_out2", "pll_c4_out0",	/* LJ input */
-	"pll_c4_out2", "pll_c4_out1",
-	"pll_c4_out1",			/* LJ input */
-	"clk_m", "pll_c4_out0"
-};
-#define mux_pllp_clkm_pllc4_out2_out1_out0_lj_idx NULL
-
 static const char *mux_pllp_pllc2_c_c3_clkm[] = {
 	"pll_p", "pll_c2", "pll_c", "pll_c3", "clk_m"
 };
@@ -686,9 +677,7 @@ static struct tegra_periph_init_data periph_clks[] = {
 	MUX("sdmmc3", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_SDMMC3, 69, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc3),
 	MUX("sdmmc4", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_SDMMC4, 15, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc4),
 	MUX8("sdmmc1", mux_pllp_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_SDMMC1, 14, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc1_9),
-	MUX8("sdmmc2", mux_pllp_clkm_pllc4_out2_out1_out0_lj, CLK_SOURCE_SDMMC2, 9, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc2_9),
 	MUX8("sdmmc3", mux_pllp_pllc4_out2_pllc4_out1_clkm_pllc4_out0, CLK_SOURCE_SDMMC3, 69, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc3_9),
-	MUX8("sdmmc4", mux_pllp_clkm_pllc4_out2_out1_out0_lj, CLK_SOURCE_SDMMC4, 15, TEGRA_PERIPH_ON_APB, tegra_clk_sdmmc4_9),
 	MUX("la", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_LA, 76, TEGRA_PERIPH_ON_APB, tegra_clk_la),
 	MUX("trace", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_TRACE, 77, TEGRA_PERIPH_ON_APB, tegra_clk_trace),
 	MUX("owr", mux_pllp_pllc_pllm_clkm, CLK_SOURCE_OWR, 71, TEGRA_PERIPH_ON_APB, tegra_clk_owr),
diff --git a/drivers/clk/tegra/clk-tegra210.c b/drivers/clk/tegra/clk-tegra210.c
index 5435d01c636a..9eb1cb14fce1 100644
--- a/drivers/clk/tegra/clk-tegra210.c
+++ b/drivers/clk/tegra/clk-tegra210.c
@@ -44,6 +44,8 @@
 #define CLK_SOURCE_EMC 0x19c
 #define CLK_SOURCE_SOR1 0x410
 #define CLK_SOURCE_LA 0x1f8
+#define CLK_SOURCE_SDMMC2 0x154
+#define CLK_SOURCE_SDMMC4 0x164
 
 #define PLLC_BASE 0x80
 #define PLLC_OUT 0x84
@@ -2286,11 +2288,9 @@ static struct tegra_clk tegra210_clks[tegra_clk_max] __initdata = {
 	[tegra_clk_rtc] = { .dt_id = TEGRA210_CLK_RTC, .present = true },
 	[tegra_clk_timer] = { .dt_id = TEGRA210_CLK_TIMER, .present = true },
 	[tegra_clk_uarta_8] = { .dt_id = TEGRA210_CLK_UARTA, .present = true },
-	[tegra_clk_sdmmc2_9] = { .dt_id = TEGRA210_CLK_SDMMC2, .present = true },
 	[tegra_clk_i2s1] = { .dt_id = TEGRA210_CLK_I2S1, .present = true },
 	[tegra_clk_i2c1] = { .dt_id = TEGRA210_CLK_I2C1, .present = true },
 	[tegra_clk_sdmmc1_9] = { .dt_id = TEGRA210_CLK_SDMMC1, .present = true },
-	[tegra_clk_sdmmc4_9] = { .dt_id = TEGRA210_CLK_SDMMC4, .present = true },
 	[tegra_clk_pwm] = { .dt_id = TEGRA210_CLK_PWM, .present = true },
 	[tegra_clk_i2s2] = { .dt_id = TEGRA210_CLK_I2S2, .present = true },
 	[tegra_clk_usbd] = { .dt_id = TEGRA210_CLK_USBD, .present = true },
@@ -3030,6 +3030,16 @@ static __init void tegra210_periph_clk_init(void __iomem *clk_base,
 				0, NULL);
 	clks[TEGRA210_CLK_ACLK] = clk;
 
+	clk = tegra_clk_register_sdmmc_mux_div("sdmmc2", clk_base,
+					    CLK_SOURCE_SDMMC2, 9,
+					    TEGRA_DIVIDER_ROUND_UP, 0, NULL);
+	clks[TEGRA210_CLK_SDMMC2] = clk;
+
+	clk = tegra_clk_register_sdmmc_mux_div("sdmmc4", clk_base,
+					    CLK_SOURCE_SDMMC4, 15,
+					    TEGRA_DIVIDER_ROUND_UP, 0, NULL);
+	clks[TEGRA210_CLK_SDMMC4] = clk;
+
 	for (i = 0; i < ARRAY_SIZE(tegra210_periph); i++) {
 		struct tegra_periph_init_data *init = &tegra210_periph[i];
 		struct clk **clkp;
-- 
cgit v1.2.3


From 0316c018c5a84d4e0b43123057adada3cddb3e00 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 17:37:35 +0900
Subject: clk: uniphier: add NAND 200MHz clock

The Denali NAND controller IP needs three clocks:

 - clk: controller core clock

 - clk_x: bus interface clock

 - ecc_clk: clock at which ECC circuitry is run

Currently, only the first one (50MHz) is provided.  The rest of the
two clock ports must be connected to the 200MHz clock line.  Add this.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/uniphier/clk-uniphier-sys.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/clk/uniphier/clk-uniphier-sys.c b/drivers/clk/uniphier/clk-uniphier-sys.c
index 4f5ff9fa11fd..a582446735b7 100644
--- a/drivers/clk/uniphier/clk-uniphier-sys.c
+++ b/drivers/clk/uniphier/clk-uniphier-sys.c
@@ -29,18 +29,20 @@
 	UNIPHIER_CLK_FACTOR("sd-200m", -1, "spll", 1, 10),		\
 	UNIPHIER_CLK_FACTOR("sd-133m", -1, "spll", 1, 15)
 
-/* Denali driver requires clk_x rate (clk: 50MHz, clk_x & ecc_clk: 200MHz) */
 #define UNIPHIER_LD4_SYS_CLK_NAND(idx)					\
-	UNIPHIER_CLK_FACTOR("nand-200m", -1, "spll", 1, 8),		\
-	UNIPHIER_CLK_GATE("nand", (idx), "nand-200m", 0x2104, 2)
+	UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 32),		\
+	UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x2104, 2)
 
 #define UNIPHIER_PRO5_SYS_CLK_NAND(idx)					\
-	UNIPHIER_CLK_FACTOR("nand-200m", -1, "spll", 1, 12),		\
-	UNIPHIER_CLK_GATE("nand", (idx), "nand-200m", 0x2104, 2)
+	UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 48),		\
+	UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x2104, 2)
 
 #define UNIPHIER_LD11_SYS_CLK_NAND(idx)					\
-	UNIPHIER_CLK_FACTOR("nand-200m", -1, "spll", 1, 10),		\
-	UNIPHIER_CLK_GATE("nand", (idx), "nand-200m", 0x210c, 0)
+	UNIPHIER_CLK_FACTOR("nand-50m", -1, "spll", 1, 40),		\
+	UNIPHIER_CLK_GATE("nand", (idx), "nand-50m", 0x210c, 0)
+
+#define UNIPHIER_SYS_CLK_NAND_4X(idx)					\
+	UNIPHIER_CLK_FACTOR("nand-4x", (idx), "nand", 4, 1)
 
 #define UNIPHIER_LD11_SYS_CLK_EMMC(idx)					\
 	UNIPHIER_CLK_GATE("emmc", (idx), NULL, 0x210c, 2)
@@ -94,6 +96,7 @@ const struct uniphier_clk_data uniphier_ld4_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("uart", 0, "a2pll", 1, 16),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
 	UNIPHIER_CLK_FACTOR("usb2", -1, "upll", 1, 12),
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),			/* Ether, HSC, MIO */
@@ -109,6 +112,7 @@ const struct uniphier_clk_data uniphier_pro4_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("uart", 0, "a2pll", 1, 8),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 32),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
 	UNIPHIER_CLK_FACTOR("usb2", -1, "upll", 1, 12),
 	UNIPHIER_PRO4_SYS_CLK_ETHER(6),
@@ -131,6 +135,7 @@ const struct uniphier_clk_data uniphier_sld8_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 20),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
 	UNIPHIER_CLK_FACTOR("usb2", -1, "upll", 1, 12),
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),			/* Ether, HSC, MIO */
@@ -144,6 +149,7 @@ const struct uniphier_clk_data uniphier_pro5_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("uart", 0, "dapll2", 1, 40),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 48),
 	UNIPHIER_PRO5_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_PRO5_SYS_CLK_SD,
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),				/* HSC */
 	UNIPHIER_PRO4_SYS_CLK_GIO(12),				/* PCIe, USB3 */
@@ -159,6 +165,7 @@ const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 27),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 48),
 	UNIPHIER_PRO5_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_PRO5_SYS_CLK_SD,
 	UNIPHIER_PRO4_SYS_CLK_ETHER(6),
 	UNIPHIER_LD4_SYS_CLK_STDMAC(8),				/* HSC, RLE */
@@ -181,6 +188,7 @@ const struct uniphier_clk_data uniphier_ld11_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
 	/* Index 5 reserved for eMMC PHY */
 	UNIPHIER_LD11_SYS_CLK_ETHER(6),
@@ -214,6 +222,7 @@ const struct uniphier_clk_data uniphier_ld20_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
 	/* Index 5 reserved for eMMC PHY */
 	UNIPHIER_LD20_SYS_CLK_SD,
@@ -256,6 +265,7 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
 	UNIPHIER_LD20_SYS_CLK_SD,
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
+	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
 	UNIPHIER_CLK_GATE("ether0", 6, NULL, 0x210c, 9),
 	UNIPHIER_CLK_GATE("ether1", 7, NULL, 0x210c, 10),
-- 
cgit v1.2.3


From 9d222574ef72216bd8332708750bbe743db9bea3 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 20 Jul 2018 17:37:36 +0900
Subject: clk: uniphier: add more USB3 PHY clocks

Add USB3 PHY clocks where missing.  Use fixed-factor clocks for those
without gating.

For clarification, prefix clock names with 'ss' or 'hs'.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/uniphier/clk-uniphier-sys.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/drivers/clk/uniphier/clk-uniphier-sys.c b/drivers/clk/uniphier/clk-uniphier-sys.c
index a582446735b7..1c5a998e6c21 100644
--- a/drivers/clk/uniphier/clk-uniphier-sys.c
+++ b/drivers/clk/uniphier/clk-uniphier-sys.c
@@ -122,6 +122,9 @@ const struct uniphier_clk_data uniphier_pro4_sys_clk_data[] = {
 	UNIPHIER_PRO4_SYS_CLK_GIO(12),			/* Ether, SATA, USB3 */
 	UNIPHIER_PRO4_SYS_CLK_USB3(14, 0),
 	UNIPHIER_PRO4_SYS_CLK_USB3(15, 1),
+	UNIPHIER_CLK_FACTOR("usb30-hsphy0", 16, "upll", 1, 12),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy0", 17, "ref", 1, 1),
+	UNIPHIER_CLK_FACTOR("usb31-ssphy0", 20, "ref", 1, 1),
 	UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x2104, 18),
 	UNIPHIER_CLK_GATE("sata1", 29, NULL, 0x2104, 19),
 	UNIPHIER_PRO4_SYS_CLK_AIO(40),
@@ -173,8 +176,11 @@ const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[] = {
 	UNIPHIER_PRO4_SYS_CLK_USB3(14, 0),
 	UNIPHIER_PRO4_SYS_CLK_USB3(15, 1),
 	/* The document mentions 0x2104 bit 18, but not functional */
-	UNIPHIER_CLK_GATE("usb30-phy", 16, NULL, 0x2104, 19),
-	UNIPHIER_CLK_GATE("usb31-phy", 20, NULL, 0x2104, 20),
+	UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x2104, 19),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy0", 17, "ref", 1, 1),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy1", 18, "ref", 1, 1),
+	UNIPHIER_CLK_GATE("usb31-hsphy0", 20, NULL, 0x2104, 20),
+	UNIPHIER_CLK_FACTOR("usb31-ssphy0", 21, "ref", 1, 1),
 	UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x2104, 22),
 	UNIPHIER_PRO5_SYS_CLK_AIO(40),
 	{ /* sentinel */ }
@@ -235,8 +241,10 @@ const struct uniphier_clk_data uniphier_ld20_sys_clk_data[] = {
 	 * We do not use bit 15 here.
 	 */
 	UNIPHIER_CLK_GATE("usb30", 14, NULL, 0x210c, 14),
-	UNIPHIER_CLK_GATE("usb30-phy0", 16, NULL, 0x210c, 12),
-	UNIPHIER_CLK_GATE("usb30-phy1", 17, NULL, 0x210c, 13),
+	UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x210c, 12),
+	UNIPHIER_CLK_GATE("usb30-hsphy1", 17, NULL, 0x210c, 13),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy0", 18, "ref", 1, 1),
+	UNIPHIER_CLK_FACTOR("usb30-ssphy1", 19, "ref", 1, 1),
 	UNIPHIER_CLK_GATE("pcie", 24, NULL, 0x210c, 4),
 	UNIPHIER_LD11_SYS_CLK_AIO(40),
 	UNIPHIER_LD11_SYS_CLK_EVEA(41),
@@ -272,11 +280,11 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = {
 	UNIPHIER_CLK_GATE("usb30", 12, NULL, 0x210c, 4),	/* =GIO0 */
 	UNIPHIER_CLK_GATE("usb31-0", 13, NULL, 0x210c, 5),	/* =GIO1 */
 	UNIPHIER_CLK_GATE("usb31-1", 14, NULL, 0x210c, 6),	/* =GIO1-1 */
-	UNIPHIER_CLK_GATE("usb30-phy0", 16, NULL, 0x210c, 16),
-	UNIPHIER_CLK_GATE("usb30-phy1", 17, NULL, 0x210c, 18),
-	UNIPHIER_CLK_GATE("usb30-phy2", 18, NULL, 0x210c, 20),
-	UNIPHIER_CLK_GATE("usb31-phy0", 20, NULL, 0x210c, 17),
-	UNIPHIER_CLK_GATE("usb31-phy1", 21, NULL, 0x210c, 19),
+	UNIPHIER_CLK_GATE("usb30-hsphy0", 16, NULL, 0x210c, 16),
+	UNIPHIER_CLK_GATE("usb30-ssphy0", 17, NULL, 0x210c, 18),
+	UNIPHIER_CLK_GATE("usb30-ssphy1", 18, NULL, 0x210c, 20),
+	UNIPHIER_CLK_GATE("usb31-hsphy0", 20, NULL, 0x210c, 17),
+	UNIPHIER_CLK_GATE("usb31-ssphy0", 21, NULL, 0x210c, 19),
 	UNIPHIER_CLK_GATE("pcie", 24, NULL, 0x210c, 3),
 	UNIPHIER_CLK_GATE("sata0", 28, NULL, 0x210c, 7),
 	UNIPHIER_CLK_GATE("sata1", 29, NULL, 0x210c, 8),
-- 
cgit v1.2.3


From ff388ee3651642d7fdc837b4434a1c7d80b243e4 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Thu, 19 Jul 2018 14:23:48 +0900
Subject: clk: uniphier: add clock frequency support for SPI

Add clock control for SPI controller on UniPhier SoCs.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/uniphier/clk-uniphier-peri.c | 9 +++++++++
 drivers/clk/uniphier/clk-uniphier-sys.c  | 8 ++++++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/clk/uniphier/clk-uniphier-peri.c b/drivers/clk/uniphier/clk-uniphier-peri.c
index 521c80e9a06f..89b3ac378b3f 100644
--- a/drivers/clk/uniphier/clk-uniphier-peri.c
+++ b/drivers/clk/uniphier/clk-uniphier-peri.c
@@ -27,6 +27,12 @@
 #define UNIPHIER_PERI_CLK_FI2C(idx, ch)					\
 	UNIPHIER_CLK_GATE("i2c" #ch, (idx), "i2c", 0x24, 24 + (ch))
 
+#define UNIPHIER_PERI_CLK_SCSSI(idx)					\
+	UNIPHIER_CLK_GATE("scssi", (idx), "spi", 0x20, 17)
+
+#define UNIPHIER_PERI_CLK_MCSSI(idx)					\
+	UNIPHIER_CLK_GATE("mcssi", (idx), "spi", 0x24, 14)
+
 const struct uniphier_clk_data uniphier_ld4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_UART(0, 0),
 	UNIPHIER_PERI_CLK_UART(1, 1),
@@ -38,6 +44,7 @@ const struct uniphier_clk_data uniphier_ld4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_I2C(6, 2),
 	UNIPHIER_PERI_CLK_I2C(7, 3),
 	UNIPHIER_PERI_CLK_I2C(8, 4),
+	UNIPHIER_PERI_CLK_SCSSI(11),
 	{ /* sentinel */ }
 };
 
@@ -53,5 +60,7 @@ const struct uniphier_clk_data uniphier_pro4_peri_clk_data[] = {
 	UNIPHIER_PERI_CLK_FI2C(8, 4),
 	UNIPHIER_PERI_CLK_FI2C(9, 5),
 	UNIPHIER_PERI_CLK_FI2C(10, 6),
+	UNIPHIER_PERI_CLK_SCSSI(11),
+	UNIPHIER_PERI_CLK_MCSSI(12),
 	{ /* sentinel */ }
 };
diff --git a/drivers/clk/uniphier/clk-uniphier-sys.c b/drivers/clk/uniphier/clk-uniphier-sys.c
index 1c5a998e6c21..2bb5a8570adc 100644
--- a/drivers/clk/uniphier/clk-uniphier-sys.c
+++ b/drivers/clk/uniphier/clk-uniphier-sys.c
@@ -95,6 +95,7 @@ const struct uniphier_clk_data uniphier_ld4_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vpll27a", -1, "ref", 5625, 512),	/* 270 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "a2pll", 1, 16),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 32),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
@@ -111,6 +112,7 @@ const struct uniphier_clk_data uniphier_pro4_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("gpll", -1, "ref", 10, 1),		/* 250 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "a2pll", 1, 8),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 32),
+	UNIPHIER_CLK_FACTOR("spi", 1, "spll", 1, 32),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
@@ -137,6 +139,7 @@ const struct uniphier_clk_data uniphier_sld8_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vpll27a", -1, "ref", 270, 25),	/* 270 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 20),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 16),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 32),
 	UNIPHIER_LD4_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD4_SYS_CLK_SD,
@@ -151,6 +154,7 @@ const struct uniphier_clk_data uniphier_pro5_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("dapll2", -1, "dapll1", 144, 125),	/* 2949.12 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "dapll2", 1, 40),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 48),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 48),
 	UNIPHIER_PRO5_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_PRO5_SYS_CLK_SD,
@@ -167,6 +171,7 @@ const struct uniphier_clk_data uniphier_pxs2_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("spll", -1, "ref", 96, 1),		/* 2400 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 27),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 48),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 48),
 	UNIPHIER_PRO5_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_PRO5_SYS_CLK_SD,
@@ -193,6 +198,7 @@ const struct uniphier_clk_data uniphier_ld11_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vspll", -1, "ref", 80, 1),		/* 2000 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 40),
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
@@ -227,6 +233,7 @@ const struct uniphier_clk_data uniphier_ld20_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("vppll", -1, "ref", 504, 5),	/* 2520 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 40),
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
 	UNIPHIER_LD11_SYS_CLK_EMMC(4),
@@ -271,6 +278,7 @@ const struct uniphier_clk_data uniphier_pxs3_sys_clk_data[] = {
 	UNIPHIER_CLK_FACTOR("s2pll", -1, "ref", 88, 1),		/* IPP: 2400 MHz */
 	UNIPHIER_CLK_FACTOR("uart", 0, "spll", 1, 34),
 	UNIPHIER_CLK_FACTOR("i2c", 1, "spll", 1, 40),
+	UNIPHIER_CLK_FACTOR("spi", -1, "spll", 1, 40),
 	UNIPHIER_LD20_SYS_CLK_SD,
 	UNIPHIER_LD11_SYS_CLK_NAND(2),
 	UNIPHIER_SYS_CLK_NAND_4X(3),
-- 
cgit v1.2.3


From 6360cd625e88a557f823001a796ca9e6065b3f0e Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 24 Jul 2018 13:59:33 +0300
Subject: net/mlx5e: Use ttl from route lookup on tc encap offload only if
 needed

Currnetly, the ttl for the encapsulation headers is taken from the
route lookup result. As a pre-step to allow for an offload case when
the user specifies the ttl, take it from the route lookup only if
not zero. While here, also move to use u8 instead int for the ttl.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 27 ++++++++++++++++---------
 1 file changed, 17 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 04fe20716bd1..86af92aabf1d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2129,7 +2129,7 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 				   struct net_device **out_dev,
 				   struct flowi4 *fl4,
 				   struct neighbour **out_n,
-				   int *out_ttl)
+				   u8 *out_ttl)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
 	struct mlx5e_rep_priv *uplink_rpriv;
@@ -2153,7 +2153,8 @@ static int mlx5e_route_lookup_ipv4(struct mlx5e_priv *priv,
 	else
 		*out_dev = rt->dst.dev;
 
-	*out_ttl = ip4_dst_hoplimit(&rt->dst);
+	if (!(*out_ttl))
+		*out_ttl = ip4_dst_hoplimit(&rt->dst);
 	n = dst_neigh_lookup(&rt->dst, &fl4->daddr);
 	ip_rt_put(rt);
 	if (!n)
@@ -2182,7 +2183,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 				   struct net_device **out_dev,
 				   struct flowi6 *fl6,
 				   struct neighbour **out_n,
-				   int *out_ttl)
+				   u8 *out_ttl)
 {
 	struct neighbour *n = NULL;
 	struct dst_entry *dst;
@@ -2197,7 +2198,8 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 	if (ret < 0)
 		return ret;
 
-	*out_ttl = ip6_dst_hoplimit(dst);
+	if (!(*out_ttl))
+		*out_ttl = ip6_dst_hoplimit(dst);
 
 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
 	/* if the egress device isn't on the same HW e-switch, we use the uplink */
@@ -2221,7 +2223,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  int ttl,
+				  u8 ttl,
 				  __be32 daddr,
 				  __be32 saddr,
 				  __be16 udp_dst_port,
@@ -2254,7 +2256,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 static void gen_vxlan_header_ipv6(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  int ttl,
+				  u8 ttl,
 				  struct in6_addr *daddr,
 				  struct in6_addr *saddr,
 				  __be16 udp_dst_port,
@@ -2294,8 +2296,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
 	char *encap_header;
-	int ttl, err;
-	u8 nud_state;
+	u8 nud_state, ttl;
+	int err;
 
 	if (max_encap_size < ipv4_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -2316,6 +2318,9 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 		err = -EOPNOTSUPP;
 		goto free_encap;
 	}
+
+	ttl = 0;
+
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
 	fl4.saddr = tun_key->u.ipv4.src;
@@ -2399,8 +2404,8 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
 	char *encap_header;
-	int err, ttl = 0;
-	u8 nud_state;
+	u8 ttl, nud_state;
+	int err;
 
 	if (max_encap_size < ipv6_encap_size) {
 		mlx5_core_warn(priv->mdev, "encap size %d too big, max supported is %d\n",
@@ -2422,6 +2427,8 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 		goto free_encap;
 	}
 
+	ttl = 0;
+
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
 	fl6.daddr = tun_key->u.ipv6.dst;
 	fl6.saddr = tun_key->u.ipv6.src;
-- 
cgit v1.2.3


From f35f800d3591e163bbc9df062081b403f7071b56 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 24 Jul 2018 13:59:34 +0300
Subject: net/mlx5e: Support setup of tos and ttl for tunnel key TC action
 offload

Use the values provided by user-space for the encapsulation headers.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 86af92aabf1d..a6e84772f7f9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -2223,7 +2223,7 @@ static int mlx5e_route_lookup_ipv6(struct mlx5e_priv *priv,
 static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  u8 ttl,
+				  u8 tos, u8 ttl,
 				  __be32 daddr,
 				  __be32 saddr,
 				  __be16 udp_dst_port,
@@ -2243,6 +2243,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 	ip->daddr = daddr;
 	ip->saddr = saddr;
 
+	ip->tos = tos;
 	ip->ttl = ttl;
 	ip->protocol = IPPROTO_UDP;
 	ip->version = 0x4;
@@ -2256,7 +2257,7 @@ static void gen_vxlan_header_ipv4(struct net_device *out_dev,
 static void gen_vxlan_header_ipv6(struct net_device *out_dev,
 				  char buf[], int encap_size,
 				  unsigned char h_dest[ETH_ALEN],
-				  u8 ttl,
+				  u8 tos, u8 ttl,
 				  struct in6_addr *daddr,
 				  struct in6_addr *saddr,
 				  __be16 udp_dst_port,
@@ -2273,7 +2274,7 @@ static void gen_vxlan_header_ipv6(struct net_device *out_dev,
 	ether_addr_copy(eth->h_source, out_dev->dev_addr);
 	eth->h_proto = htons(ETH_P_IPV6);
 
-	ip6_flow_hdr(ip6h, 0, 0);
+	ip6_flow_hdr(ip6h, tos, 0);
 	/* the HW fills up ipv6 payload len */
 	ip6h->nexthdr     = IPPROTO_UDP;
 	ip6h->hop_limit   = ttl;
@@ -2295,8 +2296,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi4 fl4 = {};
+	u8 nud_state, tos, ttl;
 	char *encap_header;
-	u8 nud_state, ttl;
 	int err;
 
 	if (max_encap_size < ipv4_encap_size) {
@@ -2319,7 +2320,8 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 		goto free_encap;
 	}
 
-	ttl = 0;
+	tos = tun_key->tos;
+	ttl = tun_key->ttl;
 
 	fl4.flowi4_tos = tun_key->tos;
 	fl4.daddr = tun_key->u.ipv4.dst;
@@ -2355,7 +2357,7 @@ static int mlx5e_create_encap_header_ipv4(struct mlx5e_priv *priv,
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
 		gen_vxlan_header_ipv4(out_dev, encap_header,
-				      ipv4_encap_size, e->h_dest, ttl,
+				      ipv4_encap_size, e->h_dest, tos, ttl,
 				      fl4.daddr,
 				      fl4.saddr, tun_key->tp_dst,
 				      tunnel_id_to_key32(tun_key->tun_id));
@@ -2403,8 +2405,8 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	struct net_device *out_dev;
 	struct neighbour *n = NULL;
 	struct flowi6 fl6 = {};
+	u8 nud_state, tos, ttl;
 	char *encap_header;
-	u8 ttl, nud_state;
 	int err;
 
 	if (max_encap_size < ipv6_encap_size) {
@@ -2427,7 +2429,8 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 		goto free_encap;
 	}
 
-	ttl = 0;
+	tos = tun_key->tos;
+	ttl = tun_key->ttl;
 
 	fl6.flowlabel = ip6_make_flowinfo(RT_TOS(tun_key->tos), tun_key->label);
 	fl6.daddr = tun_key->u.ipv6.dst;
@@ -2463,7 +2466,7 @@ static int mlx5e_create_encap_header_ipv6(struct mlx5e_priv *priv,
 	switch (e->tunnel_type) {
 	case MLX5_HEADER_TYPE_VXLAN:
 		gen_vxlan_header_ipv6(out_dev, encap_header,
-				      ipv6_encap_size, e->h_dest, ttl,
+				      ipv6_encap_size, e->h_dest, tos, ttl,
 				      &fl6.daddr,
 				      &fl6.saddr, tun_key->tp_dst,
 				      tunnel_id_to_key32(tun_key->tun_id));
-- 
cgit v1.2.3


From bcef735c59f2e46897bd9fd144bdbc0a237dec78 Mon Sep 17 00:00:00 2001
From: Or Gerlitz <ogerlitz@mellanox.com>
Date: Tue, 24 Jul 2018 13:59:35 +0300
Subject: net/mlx5e: Offload TC matching on tos/ttl for ip tunnels

Enable offloading of TC matching on tos/ttl for ipv4/6 tunnels.

Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Roi Dayan <roid@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 23 ++++++++++++++++++++++-
 1 file changed, 22 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index a6e84772f7f9..1010ee983ab7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1211,6 +1211,26 @@ vxlan_match_offload_err:
 		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ethertype, ETH_P_IPV6);
 	}
 
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		struct flow_dissector_key_ip *key =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_IP,
+						  f->key);
+		struct flow_dissector_key_ip *mask =
+			skb_flow_dissector_target(f->dissector,
+						  FLOW_DISSECTOR_KEY_ENC_IP,
+						  f->mask);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_ecn, mask->tos & 0x3);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_ecn, key->tos & 0x3);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ip_dscp, mask->tos >> 2);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ip_dscp, key->tos  >> 2);
+
+		MLX5_SET(fte_match_set_lyr_2_4, headers_c, ttl_hoplimit, mask->ttl);
+		MLX5_SET(fte_match_set_lyr_2_4, headers_v, ttl_hoplimit, key->ttl);
+	}
+
 	/* Enforce DMAC when offloading incoming tunneled flows.
 	 * Flow counters require a match on the DMAC.
 	 */
@@ -1259,7 +1279,8 @@ static int __parse_cls_flower(struct mlx5e_priv *priv,
 	      BIT(FLOW_DISSECTOR_KEY_ENC_PORTS)	|
 	      BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) |
 	      BIT(FLOW_DISSECTOR_KEY_TCP) |
-	      BIT(FLOW_DISSECTOR_KEY_IP))) {
+	      BIT(FLOW_DISSECTOR_KEY_IP)  |
+	      BIT(FLOW_DISSECTOR_KEY_ENC_IP))) {
 		netdev_warn(priv->netdev, "Unsupported key used: 0x%x\n",
 			    f->dissector->used_keys);
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 7cc77bf4c29c88af8d3d02d6dc88a71f85ecb1b6 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 24 Jul 2018 14:31:45 +0300
Subject: net/mlx4_core: Allow MTTs starting at any index

Allow obtaining MTTs starting at any index,
thus give a better cache utilization.

For this, allow setting log_mtts_per_seg to 0, and use
this in default.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Anaty Rahamim Bar Kat <anaty@mellanox.com>
Reviewed-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/main.c    | 7 ++++---
 drivers/net/ethernet/mellanox/mlx4/mlx4.h    | 1 -
 drivers/net/ethernet/mellanox/mlx4/profile.c | 3 ++-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 2d979a652b7b..d2d59444f562 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -159,9 +159,10 @@ static bool use_prio;
 module_param_named(use_prio, use_prio, bool, 0444);
 MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports (deprecated)");
 
-int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
+int log_mtts_per_seg = ilog2(1);
 module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
-MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");
+MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment "
+		 "(0-7) (default: 0)");
 
 static int port_type_array[2] = {MLX4_PORT_TYPE_NONE, MLX4_PORT_TYPE_NONE};
 static int arr_argc = 2;
@@ -4410,7 +4411,7 @@ static int __init mlx4_verify_params(void)
 	if (use_prio != 0)
 		pr_warn("mlx4_core: use_prio - obsolete module param, ignored\n");
 
-	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
+	if ((log_mtts_per_seg < 0) || (log_mtts_per_seg > 7)) {
 		pr_warn("mlx4_core: bad log_mtts_per_seg: %d\n",
 			log_mtts_per_seg);
 		return -1;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 6e016092a6f1..ebcd2778eeb3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -84,7 +84,6 @@ enum {
 	MLX4_MIN_MGM_LOG_ENTRY_SIZE = 7,
 	MLX4_MAX_MGM_LOG_ENTRY_SIZE = 12,
 	MLX4_MAX_QP_PER_MGM = 4 * ((1 << MLX4_MAX_MGM_LOG_ENTRY_SIZE) / 16 - 2),
-	MLX4_MTT_ENTRY_PER_SEG	= 8,
 };
 
 enum {
diff --git a/drivers/net/ethernet/mellanox/mlx4/profile.c b/drivers/net/ethernet/mellanox/mlx4/profile.c
index bae8b22edbb7..ba361c5fbda3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/profile.c
+++ b/drivers/net/ethernet/mellanox/mlx4/profile.c
@@ -105,7 +105,8 @@ u64 mlx4_make_profile(struct mlx4_dev *dev,
 	request->num_mtt =
 		roundup_pow_of_two(max_t(unsigned, request->num_mtt,
 					 min(1UL << (31 - log_mtts_per_seg),
-					     si.totalram >> (log_mtts_per_seg - 1))));
+					     (si.totalram << 1) >> log_mtts_per_seg)));
+
 
 	profile[MLX4_RES_QP].size     = dev_cap->qpc_entry_sz;
 	profile[MLX4_RES_RDMARC].size = dev_cap->rdmarc_entry_sz;
-- 
cgit v1.2.3


From 158abbf170ecfc6d56abeddd0c66da753b3435df Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@mellanox.com>
Date: Wed, 25 Jul 2018 02:31:25 +0000
Subject: net/sched: cls_flower: Use correct inline function for assignment of
 vlan tpid

This fixes the following sparse warning:

net/sched/cls_flower.c:1356:36: warning: incorrect type in argument 3 (different base types)
net/sched/cls_flower.c:1356:36: expected unsigned short [unsigned] [usertype] value
net/sched/cls_flower.c:1356:36: got restricted __be16 [usertype] vlan_tpid

Signed-off-by: Jianbo Liu <jianbol@mellanox.com>
Reported-by: Or Gerlitz <ogerlitz@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 6ccf60364297..e8bd08ba998a 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1445,8 +1445,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 			     TCA_FLOWER_KEY_CVLAN_PRIO,
 			     &key->cvlan, &mask->cvlan) ||
 	    (mask->cvlan.vlan_tpid &&
-	     nla_put_u16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
-			 key->cvlan.vlan_tpid)))
+	     nla_put_be16(skb, TCA_FLOWER_KEY_VLAN_ETH_TYPE,
+			  key->cvlan.vlan_tpid)))
 		goto nla_put_failure;
 
 	if (mask->basic.n_proto) {
-- 
cgit v1.2.3


From 55477206f15cf725178be23344179bd83f773c7b Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 25 Jul 2018 06:06:07 +0000
Subject: tcp: make function tcp_retransmit_stamp() static

Fixes the following sparse warnings:

net/ipv4/tcp_timer.c:25:5: warning:
 symbol 'tcp_retransmit_stamp' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index a242f8874629..7fdf222a0bdf 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -22,7 +22,7 @@
 #include <linux/gfp.h>
 #include <net/tcp.h>
 
-u32 tcp_retransmit_stamp(const struct sock *sk)
+static u32 tcp_retransmit_stamp(const struct sock *sk)
 {
 	u32 start_ts = tcp_sk(sk)->retrans_stamp;
 
-- 
cgit v1.2.3


From 41147bb18a38a9c9e805dac3d82cef7f1cb24eef Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 25 Jul 2018 06:11:16 +0000
Subject: lan743x: Make symbol lan743x_pm_ops static

Fixes the following sparse warning:

drivers/net/ethernet/microchip/lan743x_main.c:2944:25: warning:
 symbol 'lan743x_pm_ops' was not declared. Should it be static?

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index cd41911013e9..bb323f269839 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -2941,7 +2941,7 @@ static int lan743x_pm_resume(struct device *dev)
 	return 0;
 }
 
-const struct dev_pm_ops lan743x_pm_ops = {
+static const struct dev_pm_ops lan743x_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(lan743x_pm_suspend, lan743x_pm_resume)
 };
 #endif /*CONFIG_PM */
-- 
cgit v1.2.3


From d017c1f16a798397ebc79be57f7a5e5ea788f837 Mon Sep 17 00:00:00 2001
From: Saravanan Sekar <sravanhome@gmail.com>
Date: Thu, 19 Jul 2018 11:06:45 +0200
Subject: clk: actions: Add missing REGMAP_MMIO dependency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add REGMAP_MMIO as dependency to avoid undefined
reference to regmap symbols.

Fixes: d85d20053e19 ("clk: actions: Add S900 SoC clock support")
Signed-off-by: Saravanan Sekar <sravanhome@gmail.com>
Reviewed-by: Andreas Färber <afaerber@suse.de>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/actions/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/actions/Kconfig b/drivers/clk/actions/Kconfig
index 8854adb37847..39491154abbf 100644
--- a/drivers/clk/actions/Kconfig
+++ b/drivers/clk/actions/Kconfig
@@ -1,6 +1,7 @@
 config CLK_ACTIONS
 	bool "Clock driver for Actions Semi SoCs"
 	depends on ARCH_ACTIONS || COMPILE_TEST
+	select REGMAP_MMIO
 	default ARCH_ACTIONS
 
 if CLK_ACTIONS
-- 
cgit v1.2.3


From d0e45d686a3ef18a20d4eac6675b76d3656c4727 Mon Sep 17 00:00:00 2001
From: Saravanan Sekar <sravanhome@gmail.com>
Date: Thu, 19 Jul 2018 11:06:46 +0200
Subject: dt-bindings: clock: Add S700 support for Actions Semi Soc's

Add clock bindings constants for action S700
Maintain common clock dt-bindings for Actions Semi SoC's
S700 and S900.

Signed-off-by: Parthiban Nallathambi <pn@denx.de>
Signed-off-by: Saravanan Sekar <sravanhome@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 .../devicetree/bindings/clock/actions,owl-cmu.txt  |  49 +++++++++
 .../devicetree/bindings/clock/actions,s900-cmu.txt |  47 --------
 include/dt-bindings/clock/actions,s700-cmu.h       | 118 +++++++++++++++++++++
 3 files changed, 167 insertions(+), 47 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/clock/actions,owl-cmu.txt
 delete mode 100644 Documentation/devicetree/bindings/clock/actions,s900-cmu.txt
 create mode 100644 include/dt-bindings/clock/actions,s700-cmu.h

diff --git a/Documentation/devicetree/bindings/clock/actions,owl-cmu.txt b/Documentation/devicetree/bindings/clock/actions,owl-cmu.txt
new file mode 100644
index 000000000000..d1e60d297387
--- /dev/null
+++ b/Documentation/devicetree/bindings/clock/actions,owl-cmu.txt
@@ -0,0 +1,49 @@
+* Actions Semi Owl Clock Management Unit (CMU)
+
+The Actions Semi Owl Clock Management Unit generates and supplies clock
+to various controllers within the SoC. The clock binding described here is
+applicable to S900 and S700 SoC's.
+
+Required Properties:
+
+- compatible: should be one of the following,
+	"actions,s900-cmu"
+	"actions,s700-cmu"
+- reg: physical base address of the controller and length of memory mapped
+  region.
+- clocks: Reference to the parent clocks ("hosc", "losc")
+- #clock-cells: should be 1.
+
+Each clock is assigned an identifier, and client nodes can use this identifier
+to specify the clock which they consume.
+
+All available clocks are defined as preprocessor macros in corresponding
+dt-bindings/clock/actions,s900-cmu.h or actions,s700-cmu.h header and can be
+used in device tree sources.
+
+External clocks:
+
+The hosc clock used as input for the plls is generated outside the SoC. It is
+expected that it is defined using standard clock bindings as "hosc".
+
+Actions Semi S900 CMU also requires one more clock:
+ - "losc" - internal low frequency oscillator
+
+Example: Clock Management Unit node:
+
+        cmu: clock-controller@e0160000 {
+                compatible = "actions,s900-cmu";
+                reg = <0x0 0xe0160000 0x0 0x1000>;
+                clocks = <&hosc>, <&losc>;
+                #clock-cells = <1>;
+        };
+
+Example: UART controller node that consumes clock generated by the clock
+management unit:
+
+        uart: serial@e012a000 {
+                compatible = "actions,s900-uart", "actions,owl-uart";
+                reg = <0x0 0xe012a000 0x0 0x2000>;
+                interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
+                clocks = <&cmu CLK_UART5>;
+        };
diff --git a/Documentation/devicetree/bindings/clock/actions,s900-cmu.txt b/Documentation/devicetree/bindings/clock/actions,s900-cmu.txt
deleted file mode 100644
index 93e4fb827cd6..000000000000
--- a/Documentation/devicetree/bindings/clock/actions,s900-cmu.txt
+++ /dev/null
@@ -1,47 +0,0 @@
-* Actions S900 Clock Management Unit (CMU)
-
-The Actions S900 clock management unit generates and supplies clock to various
-controllers within the SoC. The clock binding described here is applicable to
-S900 SoC.
-
-Required Properties:
-
-- compatible: should be "actions,s900-cmu"
-- reg: physical base address of the controller and length of memory mapped
-  region.
-- clocks: Reference to the parent clocks ("hosc", "losc")
-- #clock-cells: should be 1.
-
-Each clock is assigned an identifier, and client nodes can use this identifier
-to specify the clock which they consume.
-
-All available clocks are defined as preprocessor macros in
-dt-bindings/clock/actions,s900-cmu.h header and can be used in device
-tree sources.
-
-External clocks:
-
-The hosc clock used as input for the plls is generated outside the SoC. It is
-expected that it is defined using standard clock bindings as "hosc".
-
-Actions S900 CMU also requires one more clock:
- - "losc" - internal low frequency oscillator
-
-Example: Clock Management Unit node:
-
-        cmu: clock-controller@e0160000 {
-                compatible = "actions,s900-cmu";
-                reg = <0x0 0xe0160000 0x0 0x1000>;
-                clocks = <&hosc>, <&losc>;
-                #clock-cells = <1>;
-        };
-
-Example: UART controller node that consumes clock generated by the clock
-management unit:
-
-        uart: serial@e012a000 {
-                compatible = "actions,s900-uart", "actions,owl-uart";
-                reg = <0x0 0xe012a000 0x0 0x2000>;
-                interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
-                clocks = <&cmu CLK_UART5>;
-        };
diff --git a/include/dt-bindings/clock/actions,s700-cmu.h b/include/dt-bindings/clock/actions,s700-cmu.h
new file mode 100644
index 000000000000..3e1942996724
--- /dev/null
+++ b/include/dt-bindings/clock/actions,s700-cmu.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Device Tree binding constants for Actions Semi S700 Clock Management Unit
+ *
+ * Copyright (c) 2014 Actions Semi Inc.
+ * Author: David Liu <liuwei@actions-semi.com>
+ *
+ * Author: Pathiban Nallathambi <pn@denx.de>
+ * Author: Saravanan Sekar <sravanhome@gmail.com>
+ */
+
+#ifndef __DT_BINDINGS_CLOCK_S700_H
+#define __DT_BINDINGS_CLOCK_S700_H
+
+#define CLK_NONE			0
+
+/* pll clocks */
+#define CLK_CORE_PLL			1
+#define CLK_DEV_PLL			2
+#define CLK_DDR_PLL			3
+#define CLK_NAND_PLL			4
+#define CLK_DISPLAY_PLL			5
+#define CLK_TVOUT_PLL			6
+#define CLK_CVBS_PLL			7
+#define CLK_AUDIO_PLL			8
+#define CLK_ETHERNET_PLL		9
+
+/* system clock */
+#define CLK_CPU				10
+#define CLK_DEV				11
+#define CLK_AHB				12
+#define CLK_APB				13
+#define CLK_DMAC			14
+#define CLK_NOC0_CLK_MUX		15
+#define CLK_NOC1_CLK_MUX		16
+#define CLK_HP_CLK_MUX			17
+#define CLK_HP_CLK_DIV			18
+#define CLK_NOC1_CLK_DIV		19
+#define CLK_NOC0			20
+#define CLK_NOC1			21
+#define CLK_SENOR_SRC			22
+
+/* peripheral device clock */
+#define CLK_GPIO			23
+#define CLK_TIMER			24
+#define CLK_DSI				25
+#define CLK_CSI				26
+#define CLK_SI				27
+#define CLK_DE				28
+#define CLK_HDE				29
+#define CLK_VDE				30
+#define CLK_VCE				31
+#define CLK_NAND			32
+#define CLK_SD0				33
+#define CLK_SD1				34
+#define CLK_SD2				35
+
+#define CLK_UART0			36
+#define CLK_UART1			37
+#define CLK_UART2			38
+#define CLK_UART3			39
+#define CLK_UART4			40
+#define CLK_UART5			41
+#define CLK_UART6			42
+
+#define CLK_PWM0			43
+#define CLK_PWM1			44
+#define CLK_PWM2			45
+#define CLK_PWM3			46
+#define CLK_PWM4			47
+#define CLK_PWM5			48
+#define CLK_GPU3D			49
+
+#define CLK_I2C0			50
+#define CLK_I2C1			51
+#define CLK_I2C2			52
+#define CLK_I2C3			53
+
+#define CLK_SPI0			54
+#define CLK_SPI1			55
+#define CLK_SPI2			56
+#define CLK_SPI3			57
+
+#define CLK_USB3_480MPLL0		58
+#define CLK_USB3_480MPHY0		59
+#define CLK_USB3_5GPHY			60
+#define CLK_USB3_CCE			61
+#define CLK_USB3_MAC			62
+
+#define CLK_LCD				63
+#define CLK_HDMI_AUDIO			64
+#define CLK_I2SRX			65
+#define CLK_I2STX			66
+
+#define CLK_SENSOR0			67
+#define CLK_SENSOR1			68
+
+#define CLK_HDMI_DEV			69
+
+#define CLK_ETHERNET			70
+#define CLK_RMII_REF			71
+
+#define CLK_USB2H0_PLLEN		72
+#define CLK_USB2H0_PHY			73
+#define CLK_USB2H0_CCE			74
+#define CLK_USB2H1_PLLEN		75
+#define CLK_USB2H1_PHY			76
+#define CLK_USB2H1_CCE			77
+
+#define CLK_TVOUT			78
+
+#define CLK_THERMAL_SENSOR		79
+
+#define CLK_IRC_SWITCH			80
+#define CLK_PCM1			81
+#define CLK_NR_CLKS			(CLK_PCM1 + 1)
+
+#endif /* __DT_BINDINGS_CLOCK_S700_H */
-- 
cgit v1.2.3


From d47317ca4ade1a9a1c69c596defb273f29e263b3 Mon Sep 17 00:00:00 2001
From: Saravanan Sekar <sravanhome@gmail.com>
Date: Thu, 19 Jul 2018 11:06:47 +0200
Subject: clk: actions: Add S700 SoC clock support

Add Actions Semi S700 SoC clock support

Signed-off-by: Parthiban Nallathambi <pn@denx.de>
Signed-off-by: Saravanan Sekar <sravanhome@gmail.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/actions/Kconfig    |   6 +
 drivers/clk/actions/Makefile   |   1 +
 drivers/clk/actions/owl-s700.c | 606 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 613 insertions(+)
 create mode 100644 drivers/clk/actions/owl-s700.c

diff --git a/drivers/clk/actions/Kconfig b/drivers/clk/actions/Kconfig
index 39491154abbf..dc38c85a4833 100644
--- a/drivers/clk/actions/Kconfig
+++ b/drivers/clk/actions/Kconfig
@@ -8,8 +8,14 @@ if CLK_ACTIONS
 
 # SoC Drivers
 
+config CLK_OWL_S700
+	bool "Support for the Actions Semi OWL S700 clocks"
+	depends on (ARM64 && ARCH_ACTIONS) || COMPILE_TEST
+	default ARM64 && ARCH_ACTIONS
+
 config CLK_OWL_S900
 	bool "Support for the Actions Semi OWL S900 clocks"
 	depends on (ARM64 && ARCH_ACTIONS) || COMPILE_TEST
 	default ARM64 && ARCH_ACTIONS
+
 endif
diff --git a/drivers/clk/actions/Makefile b/drivers/clk/actions/Makefile
index 76e431434d10..78c17d56f991 100644
--- a/drivers/clk/actions/Makefile
+++ b/drivers/clk/actions/Makefile
@@ -9,4 +9,5 @@ clk-owl-y			+= owl-composite.o
 clk-owl-y			+= owl-pll.o
 
 # SoC support
+obj-$(CONFIG_CLK_OWL_S700)	+= owl-s700.o
 obj-$(CONFIG_CLK_OWL_S900)	+= owl-s900.o
diff --git a/drivers/clk/actions/owl-s700.c b/drivers/clk/actions/owl-s700.c
new file mode 100644
index 000000000000..5e9531392ee5
--- /dev/null
+++ b/drivers/clk/actions/owl-s700.c
@@ -0,0 +1,606 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Actions Semi S700 clock driver
+ *
+ * Copyright (c) 2014 Actions Semi Inc.
+ * Author: David Liu <liuwei@actions-semi.com>
+ *
+ * Author: Pathiban Nallathambi <pn@denx.de>
+ * Author: Saravanan Sekar <sravanhome@gmail.com>
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/platform_device.h>
+
+#include "owl-common.h"
+#include "owl-composite.h"
+#include "owl-divider.h"
+#include "owl-factor.h"
+#include "owl-fixed-factor.h"
+#include "owl-gate.h"
+#include "owl-mux.h"
+#include "owl-pll.h"
+
+#include <dt-bindings/clock/actions,s700-cmu.h>
+
+#define CMU_COREPLL		(0x0000)
+#define CMU_DEVPLL		(0x0004)
+#define CMU_DDRPLL		(0x0008)
+#define CMU_NANDPLL		(0x000C)
+#define CMU_DISPLAYPLL		(0x0010)
+#define CMU_AUDIOPLL		(0x0014)
+#define CMU_TVOUTPLL		(0x0018)
+#define CMU_BUSCLK		(0x001C)
+#define CMU_SENSORCLK		(0x0020)
+#define CMU_LCDCLK		(0x0024)
+#define CMU_DSIPLLCLK		(0x0028)
+#define CMU_CSICLK		(0x002C)
+#define CMU_DECLK		(0x0030)
+#define CMU_SICLK		(0x0034)
+#define CMU_BUSCLK1		(0x0038)
+#define CMU_HDECLK		(0x003C)
+#define CMU_VDECLK		(0x0040)
+#define CMU_VCECLK		(0x0044)
+#define CMU_NANDCCLK		(0x004C)
+#define CMU_SD0CLK		(0x0050)
+#define CMU_SD1CLK		(0x0054)
+#define CMU_SD2CLK		(0x0058)
+#define CMU_UART0CLK		(0x005C)
+#define CMU_UART1CLK		(0x0060)
+#define CMU_UART2CLK		(0x0064)
+#define CMU_UART3CLK		(0x0068)
+#define CMU_UART4CLK		(0x006C)
+#define CMU_UART5CLK		(0x0070)
+#define CMU_UART6CLK		(0x0074)
+#define CMU_PWM0CLK		(0x0078)
+#define CMU_PWM1CLK		(0x007C)
+#define CMU_PWM2CLK		(0x0080)
+#define CMU_PWM3CLK		(0x0084)
+#define CMU_PWM4CLK		(0x0088)
+#define CMU_PWM5CLK		(0x008C)
+#define CMU_GPU3DCLK		(0x0090)
+#define CMU_CORECTL		(0x009C)
+#define CMU_DEVCLKEN0		(0x00A0)
+#define CMU_DEVCLKEN1		(0x00A4)
+#define CMU_DEVRST0		(0x00A8)
+#define CMU_DEVRST1		(0x00AC)
+#define CMU_USBPLL		(0x00B0)
+#define CMU_ETHERNETPLL		(0x00B4)
+#define CMU_CVBSPLL		(0x00B8)
+#define CMU_SSTSCLK		(0x00C0)
+
+static struct clk_pll_table clk_audio_pll_table[] = {
+	{0, 45158400}, {1, 49152000},
+	{0, 0},
+};
+
+static struct clk_pll_table clk_cvbs_pll_table[] = {
+	{27, 29 * 12000000}, {28, 30 * 12000000}, {29, 31 * 12000000},
+	{30, 32 * 12000000}, {31, 33 * 12000000}, {32, 34 * 12000000},
+	{33, 35 * 12000000}, {34, 36 * 12000000}, {35, 37 * 12000000},
+	{36, 38 * 12000000}, {37, 39 * 12000000}, {38, 40 * 12000000},
+	{39, 41 * 12000000}, {40, 42 * 12000000}, {41, 43 * 12000000},
+	{42, 44 * 12000000}, {43, 45 * 12000000}, {0, 0},
+};
+
+/* pll clocks */
+static OWL_PLL_NO_PARENT(clk_core_pll,   "core_pll", CMU_COREPLL, 12000000, 9, 0, 8,  4, 174, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_dev_pll,    "dev_pll", CMU_DEVPLL,  6000000, 8, 0, 8, 8, 126, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_ddr_pll,    "ddr_pll", CMU_DDRPLL, 6000000, 8, 0, 8,  2,  180, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_nand_pll,   "nand_pll", CMU_NANDPLL,  6000000, 8, 0, 8,  2, 86, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_display_pll, "display_pll", CMU_DISPLAYPLL, 6000000, 8, 0, 8, 2, 140, NULL, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_cvbs_pll, "cvbs_pll", CMU_CVBSPLL, 0, 8, 0, 8, 27, 43, clk_cvbs_pll_table, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_audio_pll,  "audio_pll", CMU_AUDIOPLL, 0, 4, 0, 1, 0, 0, clk_audio_pll_table, CLK_IGNORE_UNUSED);
+static OWL_PLL_NO_PARENT(clk_ethernet_pll, "ethernet_pll", CMU_ETHERNETPLL, 500000000, 0, 0, 0, 0, 0, NULL, CLK_IGNORE_UNUSED);
+
+static const char *cpu_clk_mux_p[] = {"losc", "hosc", "core_pll", "noc1_clk_div"};
+static const char *dev_clk_p[] = { "hosc", "dev_pll"};
+static const char *noc_clk_mux_p[] = { "dev_clk", "display_pll", "nand_pll", "ddr_pll", "cvbs_pll"};
+
+static const char *csi_clk_mux_p[] = { "display_pll", "dev_clk"};
+static const char *de_clk_mux_p[] = { "display_pll", "dev_clk"};
+static const char *hde_clk_mux_p[] = { "dev_clk", "display_pll", "nand_pll", "ddr_pll"};
+static const char *nand_clk_mux_p[] = { "nand_pll", "display_pll", "dev_clk", "ddr_pll"};
+static const char *sd_clk_mux_p[] = { "dev_clk", "nand_pll", };
+static const char *uart_clk_mux_p[] = { "hosc", "dev_pll"};
+static const char *pwm_clk_mux_p[] = { "losc", "hosc"};
+static const char *gpu_clk_mux_p[] = { "dev_clk", "display_pll", "nand_pll", "ddr_clk", "cvbs_pll"};
+static const char *lcd_clk_mux_p[] = { "display_pll", "dev_clk" };
+static const char *i2s_clk_mux_p[] = { "audio_pll" };
+static const char *sensor_clk_mux_p[] = { "hosc", "si"};
+
+/* mux clocks */
+static OWL_MUX(clk_cpu, "cpu_clk", cpu_clk_mux_p,  CMU_BUSCLK, 0, 2, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_dev, "dev_clk", dev_clk_p, CMU_DEVPLL, 12, 1, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_noc0_clk_mux, "noc0_clk_mux", noc_clk_mux_p, CMU_BUSCLK, 4, 3, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_noc1_clk_mux, "noc1_clk_mux", noc_clk_mux_p, CMU_BUSCLK1, 4, 3, CLK_SET_RATE_PARENT);
+static OWL_MUX(clk_hp_clk_mux, "hp_clk_mux", noc_clk_mux_p, CMU_BUSCLK1, 8, 3, CLK_SET_RATE_PARENT);
+
+static struct clk_factor_table sd_factor_table[] = {
+	/* bit0 ~ 4 */
+	{0, 1, 1}, {1, 1, 2}, {2, 1, 3}, {3, 1, 4},
+	{4, 1, 5}, {5, 1, 6}, {6, 1, 7}, {7, 1, 8},
+	{8, 1, 9}, {9, 1, 10}, {10, 1, 11}, {11, 1, 12},
+	{12, 1, 13}, {13, 1, 14}, {14, 1, 15}, {15, 1, 16},
+	{16, 1, 17}, {17, 1, 18}, {18, 1, 19}, {19, 1, 20},
+	{20, 1, 21}, {21, 1, 22}, {22, 1, 23}, {23, 1, 24},
+	{24, 1, 25}, {25, 1, 26},
+
+	/* bit8: /128 */
+	{256, 1, 1 * 128}, {257, 1, 2 * 128}, {258, 1, 3 * 128}, {259, 1, 4 * 128},
+	{260, 1, 5 * 128}, {261, 1, 6 * 128}, {262, 1, 7 * 128}, {263, 1, 8 * 128},
+	{264, 1, 9 * 128}, {265, 1, 10 * 128}, {266, 1, 11 * 128}, {267, 1, 12 * 128},
+	{268, 1, 13 * 128}, {269, 1, 14 * 128}, {270, 1, 15 * 128}, {271, 1, 16 * 128},
+	{272, 1, 17 * 128}, {273, 1, 18 * 128}, {274, 1, 19 * 128}, {275, 1, 20 * 128},
+	{276, 1, 21 * 128}, {277, 1, 22 * 128}, {278, 1, 23 * 128}, {279, 1, 24 * 128},
+	{280, 1, 25 * 128}, {281, 1, 26 * 128},
+
+	{0, 0},
+};
+
+static struct clk_factor_table lcd_factor_table[] = {
+	/* bit0 ~ 3 */
+	{0, 1, 1}, {1, 1, 2}, {2, 1, 3}, {3, 1, 4},
+	{4, 1, 5}, {5, 1, 6}, {6, 1, 7}, {7, 1, 8},
+	{8, 1, 9}, {9, 1, 10}, {10, 1, 11}, {11, 1, 12},
+
+	/* bit8: /7 */
+	{256, 1, 1 * 7}, {257, 1, 2 * 7}, {258, 1, 3 * 7}, {259, 1, 4 * 7},
+	{260, 1, 5 * 7}, {261, 1, 6 * 7}, {262, 1, 7 * 7}, {263, 1, 8 * 7},
+	{264, 1, 9 * 7}, {265, 1, 10 * 7}, {266, 1, 11 * 7}, {267, 1, 12 * 7},
+	{0, 0},
+};
+
+static struct clk_div_table hdmia_div_table[] = {
+	{0, 1},   {1, 2},   {2, 3},   {3, 4},
+	{4, 6},   {5, 8},   {6, 12},  {7, 16},
+	{8, 24},
+	{0, 0},
+};
+
+static struct clk_div_table rmii_div_table[] = {
+	{0, 4},   {1, 10},
+};
+
+/* divider clocks */
+static OWL_DIVIDER(clk_noc0, "noc0_clk", "noc0_clk_mux", CMU_BUSCLK, 16, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_noc1, "noc1_clk", "noc1_clk_mux", CMU_BUSCLK1, 16, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_noc1_clk_div, "noc1_clk_div", "noc1_clk", CMU_BUSCLK1, 20, 1, NULL, 0, 0);
+static OWL_DIVIDER(clk_hp_clk_div, "hp_clk_div", "hp_clk_mux", CMU_BUSCLK1, 12, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_ahb, "ahb_clk", "hp_clk_div", CMU_BUSCLK1, 2, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_apb, "apb_clk", "ahb_clk", CMU_BUSCLK1, 14, 2, NULL, 0, 0);
+static OWL_DIVIDER(clk_sensor0, "sensor0", "sensor_src", CMU_SENSORCLK, 0, 4, NULL, 0, 0);
+static OWL_DIVIDER(clk_sensor1, "sensor1", "sensor_src", CMU_SENSORCLK, 8, 4, NULL, 0, 0);
+static OWL_DIVIDER(clk_rmii_ref, "rmii_ref", "ethernet_pll", CMU_ETHERNETPLL, 2, 1, rmii_div_table, 0, 0);
+
+static struct clk_factor_table de_factor_table[] = {
+	{0, 1, 1}, {1, 2, 3}, {2, 1, 2}, {3, 2, 5},
+	{4, 1, 3}, {5, 1, 4}, {6, 1, 6}, {7, 1, 8},
+	{8, 1, 12}, {0, 0, 0},
+};
+
+static struct clk_factor_table hde_factor_table[] = {
+	{0, 1, 1}, {1, 2, 3}, {2, 1, 2}, {3, 2, 5},
+	{4, 1, 3}, {5, 1, 4}, {6, 1, 6}, {7, 1, 8},
+	{0, 0, 0},
+};
+
+/* gate clocks */
+static OWL_GATE(clk_gpio, "gpio", "apb_clk", CMU_DEVCLKEN1, 25, 0, 0);
+static OWL_GATE(clk_dmac, "dmac", "hp_clk_div", CMU_DEVCLKEN0, 17, 0, 0);
+static OWL_GATE(clk_timer, "timer", "hosc", CMU_DEVCLKEN1, 22, 0, 0);
+static OWL_GATE_NO_PARENT(clk_dsi, "dsi_clk", CMU_DEVCLKEN0, 2, 0, 0);
+static OWL_GATE_NO_PARENT(clk_tvout, "tvout_clk", CMU_DEVCLKEN0, 3, 0, 0);
+static OWL_GATE_NO_PARENT(clk_hdmi_dev, "hdmi_dev", CMU_DEVCLKEN0, 5, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_480mpll0, "usb3_480mpll0", CMU_USBPLL, 3, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_480mphy0, "usb3_480mphy0", CMU_USBPLL, 2, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_5gphy, "usb3_5gphy", CMU_USBPLL, 1, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb3_cce, "usb3_cce", CMU_DEVCLKEN0, 25, 0, 0);
+static OWL_GATE(clk_i2c0, "i2c0", "hosc", CMU_DEVCLKEN1, 0, 0, 0);
+static OWL_GATE(clk_i2c1, "i2c1", "hosc", CMU_DEVCLKEN1, 1, 0, 0);
+static OWL_GATE(clk_i2c2, "i2c2", "hosc", CMU_DEVCLKEN1, 2, 0, 0);
+static OWL_GATE(clk_i2c3, "i2c3", "hosc", CMU_DEVCLKEN1, 3, 0, 0);
+static OWL_GATE(clk_spi0, "spi0", "ahb_clk", CMU_DEVCLKEN1, 4, 0, 0);
+static OWL_GATE(clk_spi1, "spi1", "ahb_clk", CMU_DEVCLKEN1, 5, 0, 0);
+static OWL_GATE(clk_spi2, "spi2", "ahb_clk", CMU_DEVCLKEN1, 6, 0, 0);
+static OWL_GATE(clk_spi3, "spi3", "ahb_clk", CMU_DEVCLKEN1, 7, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h0_pllen, "usbh0_pllen", CMU_USBPLL, 12, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h0_phy, "usbh0_phy", CMU_USBPLL, 10, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h0_cce, "usbh0_cce", CMU_DEVCLKEN0, 26, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h1_pllen, "usbh1_pllen", CMU_USBPLL, 13, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h1_phy, "usbh1_phy", CMU_USBPLL, 11, 0, 0);
+static OWL_GATE_NO_PARENT(clk_usb2h1_cce, "usbh1_cce", CMU_DEVCLKEN0, 27, 0, 0);
+static OWL_GATE_NO_PARENT(clk_irc_switch, "irc_switch", CMU_DEVCLKEN1, 15, 0, 0);
+
+/* composite clocks */
+
+static OWL_COMP_DIV(clk_csi, "csi", csi_clk_mux_p,
+			OWL_MUX_HW(CMU_CSICLK, 4, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 13, 0),
+			OWL_DIVIDER_HW(CMU_CSICLK, 0, 4, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_si, "si", csi_clk_mux_p,
+			OWL_MUX_HW(CMU_SICLK, 4, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 14,  0),
+			OWL_DIVIDER_HW(CMU_SICLK, 0, 4, 0, NULL),
+			0);
+
+static OWL_COMP_FACTOR(clk_de, "de", de_clk_mux_p,
+			OWL_MUX_HW(CMU_DECLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 0,  0),
+			OWL_FACTOR_HW(CMU_DECLK, 0, 3, 0, de_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_hde, "hde", hde_clk_mux_p,
+			OWL_MUX_HW(CMU_HDECLK, 4, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 9, 0),
+			OWL_FACTOR_HW(CMU_HDECLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_vde, "vde", hde_clk_mux_p,
+			OWL_MUX_HW(CMU_VDECLK, 4, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 10,  0),
+			OWL_FACTOR_HW(CMU_VDECLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_vce, "vce", hde_clk_mux_p,
+			OWL_MUX_HW(CMU_VCECLK, 4, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 11, 0),
+			OWL_FACTOR_HW(CMU_VCECLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_DIV(clk_nand, "nand", nand_clk_mux_p,
+			OWL_MUX_HW(CMU_NANDCCLK, 8, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 21, 0),
+			OWL_DIVIDER_HW(CMU_NANDCCLK, 0, 3, 0, NULL),
+			CLK_SET_RATE_PARENT);
+
+static OWL_COMP_FACTOR(clk_sd0, "sd0", sd_clk_mux_p,
+			OWL_MUX_HW(CMU_SD0CLK, 9, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 22, 0),
+			OWL_FACTOR_HW(CMU_SD0CLK, 0, 9, 0, sd_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_sd1, "sd1", sd_clk_mux_p,
+			OWL_MUX_HW(CMU_SD1CLK, 9, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 23, 0),
+			OWL_FACTOR_HW(CMU_SD1CLK, 0, 9, 0, sd_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_sd2, "sd2", sd_clk_mux_p,
+			OWL_MUX_HW(CMU_SD2CLK, 9, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 24, 0),
+			OWL_FACTOR_HW(CMU_SD2CLK, 0, 9, 0, sd_factor_table),
+			0);
+
+static OWL_COMP_DIV(clk_uart0, "uart0", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART0CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 8, 0),
+			OWL_DIVIDER_HW(CMU_UART0CLK, 0, 9, CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart1, "uart1", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART1CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 9, 0),
+			OWL_DIVIDER_HW(CMU_UART1CLK, 0, 9, CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart2, "uart2", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART2CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 10, 0),
+			OWL_DIVIDER_HW(CMU_UART2CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart3, "uart3", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART3CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 11, 0),
+			OWL_DIVIDER_HW(CMU_UART3CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart4, "uart4", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART4CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 12, 0),
+			OWL_DIVIDER_HW(CMU_UART4CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart5, "uart5", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART5CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 13, 0),
+			OWL_DIVIDER_HW(CMU_UART5CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_uart6, "uart6", uart_clk_mux_p,
+			OWL_MUX_HW(CMU_UART6CLK, 16, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 14, 0),
+			OWL_DIVIDER_HW(CMU_UART6CLK, 0, 9,  CLK_DIVIDER_ROUND_CLOSEST, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm0, "pwm0", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM0CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 16, 0),
+			OWL_DIVIDER_HW(CMU_PWM0CLK, 0, 10, 0, NULL),
+			CLK_IGNORE_UNUSED);
+
+static OWL_COMP_DIV(clk_pwm1, "pwm1", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM1CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 17, 0),
+			OWL_DIVIDER_HW(CMU_PWM1CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm2, "pwm2", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM2CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 18, 0),
+			OWL_DIVIDER_HW(CMU_PWM2CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm3, "pwm3", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM3CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 19, 0),
+			OWL_DIVIDER_HW(CMU_PWM3CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm4, "pwm4", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM4CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 20, 0),
+			OWL_DIVIDER_HW(CMU_PWM4CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_DIV(clk_pwm5, "pwm5", pwm_clk_mux_p,
+			OWL_MUX_HW(CMU_PWM5CLK, 12, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 21, 0),
+			OWL_DIVIDER_HW(CMU_PWM5CLK, 0, 10, 0, NULL),
+			0);
+
+static OWL_COMP_FACTOR(clk_gpu3d, "gpu3d", gpu_clk_mux_p,
+			OWL_MUX_HW(CMU_GPU3DCLK, 4, 3),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 8, 0),
+			OWL_FACTOR_HW(CMU_GPU3DCLK, 0, 3, 0, hde_factor_table),
+			0);
+
+static OWL_COMP_FACTOR(clk_lcd, "lcd", lcd_clk_mux_p,
+			OWL_MUX_HW(CMU_LCDCLK, 12, 2),
+			OWL_GATE_HW(CMU_DEVCLKEN0, 1, 0),
+			OWL_FACTOR_HW(CMU_LCDCLK, 0, 9, 0, lcd_factor_table),
+			0);
+
+static OWL_COMP_DIV(clk_hdmi_audio, "hdmia", i2s_clk_mux_p,
+			OWL_MUX_HW(CMU_AUDIOPLL, 24, 1), /*CMU_AUDIOPLL 24,1 unused*/
+			OWL_GATE_HW(CMU_DEVCLKEN1, 28, 0),
+			OWL_DIVIDER_HW(CMU_AUDIOPLL, 24, 4, 0, hdmia_div_table),
+			0);
+
+static OWL_COMP_DIV(clk_i2srx, "i2srx", i2s_clk_mux_p,
+			OWL_MUX_HW(CMU_AUDIOPLL, 24, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 27, 0),
+			OWL_DIVIDER_HW(CMU_AUDIOPLL, 20, 4, 0, hdmia_div_table),
+			0);
+
+static OWL_COMP_DIV(clk_i2stx, "i2stx", i2s_clk_mux_p,
+			OWL_MUX_HW(CMU_AUDIOPLL, 24, 1),
+			OWL_GATE_HW(CMU_DEVCLKEN1, 26, 0),
+			OWL_DIVIDER_HW(CMU_AUDIOPLL, 16, 4, 0, hdmia_div_table),
+			0);
+
+/* for bluetooth pcm communication */
+static OWL_COMP_FIXED_FACTOR(clk_pcm1, "pcm1", "audio_pll",
+			OWL_GATE_HW(CMU_DEVCLKEN1, 31, 0),
+			1, 2, 0);
+
+static OWL_COMP_DIV(clk_sensor_src, "sensor_src", sensor_clk_mux_p,
+			OWL_MUX_HW(CMU_SENSORCLK, 4, 1),
+			{0},
+			OWL_DIVIDER_HW(CMU_SENSORCLK, 5, 2, 0, NULL),
+			0);
+
+static OWL_COMP_FIXED_FACTOR(clk_ethernet, "ethernet", "ethernet_pll",
+			OWL_GATE_HW(CMU_DEVCLKEN1, 23, 0),
+			1, 20, 0);
+
+static OWL_COMP_DIV_FIXED(clk_thermal_sensor, "thermal_sensor", "hosc",
+				OWL_GATE_HW(CMU_DEVCLKEN0, 31, 0),
+				OWL_DIVIDER_HW(CMU_SSTSCLK, 20, 10, 0, NULL),
+				0);
+
+static struct owl_clk_common *s700_clks[] = {
+	&clk_core_pll.common,
+	&clk_dev_pll.common,
+	&clk_ddr_pll.common,
+	&clk_nand_pll.common,
+	&clk_display_pll.common,
+	&clk_cvbs_pll .common,
+	&clk_audio_pll.common,
+	&clk_ethernet_pll.common,
+	&clk_cpu.common,
+	&clk_dev.common,
+	&clk_ahb.common,
+	&clk_apb.common,
+	&clk_dmac.common,
+	&clk_noc0_clk_mux.common,
+	&clk_noc1_clk_mux.common,
+	&clk_hp_clk_mux.common,
+	&clk_hp_clk_div.common,
+	&clk_noc1_clk_div.common,
+	&clk_noc0.common,
+	&clk_noc1.common,
+	&clk_sensor_src.common,
+	&clk_gpio.common,
+	&clk_timer.common,
+	&clk_dsi.common,
+	&clk_csi.common,
+	&clk_si.common,
+	&clk_de.common,
+	&clk_hde.common,
+	&clk_vde.common,
+	&clk_vce.common,
+	&clk_nand.common,
+	&clk_sd0.common,
+	&clk_sd1.common,
+	&clk_sd2.common,
+	&clk_uart0.common,
+	&clk_uart1.common,
+	&clk_uart2.common,
+	&clk_uart3.common,
+	&clk_uart4.common,
+	&clk_uart5.common,
+	&clk_uart6.common,
+	&clk_pwm0.common,
+	&clk_pwm1.common,
+	&clk_pwm2.common,
+	&clk_pwm3.common,
+	&clk_pwm4.common,
+	&clk_pwm5.common,
+	&clk_gpu3d.common,
+	&clk_i2c0.common,
+	&clk_i2c1.common,
+	&clk_i2c2.common,
+	&clk_i2c3.common,
+	&clk_spi0.common,
+	&clk_spi1.common,
+	&clk_spi2.common,
+	&clk_spi3.common,
+	&clk_usb3_480mpll0.common,
+	&clk_usb3_480mphy0.common,
+	&clk_usb3_5gphy.common,
+	&clk_usb3_cce.common,
+	&clk_lcd.common,
+	&clk_hdmi_audio.common,
+	&clk_i2srx.common,
+	&clk_i2stx.common,
+	&clk_sensor0.common,
+	&clk_sensor1.common,
+	&clk_hdmi_dev.common,
+	&clk_ethernet.common,
+	&clk_rmii_ref.common,
+	&clk_usb2h0_pllen.common,
+	&clk_usb2h0_phy.common,
+	&clk_usb2h0_cce.common,
+	&clk_usb2h1_pllen.common,
+	&clk_usb2h1_phy.common,
+	&clk_usb2h1_cce.common,
+	&clk_tvout.common,
+	&clk_thermal_sensor.common,
+	&clk_irc_switch.common,
+	&clk_pcm1.common,
+};
+
+static struct clk_hw_onecell_data s700_hw_clks = {
+	.hws    = {
+			[CLK_CORE_PLL]				= &clk_core_pll.common.hw,
+			[CLK_DEV_PLL]				= &clk_dev_pll.common.hw,
+			[CLK_DDR_PLL]				= &clk_ddr_pll.common.hw,
+			[CLK_NAND_PLL]				= &clk_nand_pll.common.hw,
+			[CLK_DISPLAY_PLL]			= &clk_display_pll.common.hw,
+			[CLK_CVBS_PLL]				= &clk_cvbs_pll .common.hw,
+			[CLK_AUDIO_PLL]				= &clk_audio_pll.common.hw,
+			[CLK_ETHERNET_PLL]			= &clk_ethernet_pll.common.hw,
+			[CLK_CPU]				= &clk_cpu.common.hw,
+			[CLK_DEV]				= &clk_dev.common.hw,
+			[CLK_AHB]				= &clk_ahb.common.hw,
+			[CLK_APB]				= &clk_apb.common.hw,
+			[CLK_DMAC]				= &clk_dmac.common.hw,
+			[CLK_NOC0_CLK_MUX]			= &clk_noc0_clk_mux.common.hw,
+			[CLK_NOC1_CLK_MUX]			= &clk_noc1_clk_mux.common.hw,
+			[CLK_HP_CLK_MUX]			= &clk_hp_clk_mux.common.hw,
+			[CLK_HP_CLK_DIV]			= &clk_hp_clk_div.common.hw,
+			[CLK_NOC1_CLK_DIV]			= &clk_noc1_clk_div.common.hw,
+			[CLK_NOC0]				= &clk_noc0.common.hw,
+			[CLK_NOC1]				= &clk_noc1.common.hw,
+			[CLK_SENOR_SRC]				= &clk_sensor_src.common.hw,
+			[CLK_GPIO]				= &clk_gpio.common.hw,
+			[CLK_TIMER]				= &clk_timer.common.hw,
+			[CLK_DSI]				= &clk_dsi.common.hw,
+			[CLK_CSI]				= &clk_csi.common.hw,
+			[CLK_SI]				= &clk_si.common.hw,
+			[CLK_DE]				= &clk_de.common.hw,
+			[CLK_HDE]				= &clk_hde.common.hw,
+			[CLK_VDE]				= &clk_vde.common.hw,
+			[CLK_VCE]				= &clk_vce.common.hw,
+			[CLK_NAND]				= &clk_nand.common.hw,
+			[CLK_SD0]				= &clk_sd0.common.hw,
+			[CLK_SD1]				= &clk_sd1.common.hw,
+			[CLK_SD2]				= &clk_sd2.common.hw,
+			[CLK_UART0]				= &clk_uart0.common.hw,
+			[CLK_UART1]				= &clk_uart1.common.hw,
+			[CLK_UART2]				= &clk_uart2.common.hw,
+			[CLK_UART3]				= &clk_uart3.common.hw,
+			[CLK_UART4]				= &clk_uart4.common.hw,
+			[CLK_UART5]				= &clk_uart5.common.hw,
+			[CLK_UART6]				= &clk_uart6.common.hw,
+			[CLK_PWM0]				= &clk_pwm0.common.hw,
+			[CLK_PWM1]				= &clk_pwm1.common.hw,
+			[CLK_PWM2]				= &clk_pwm2.common.hw,
+			[CLK_PWM3]				= &clk_pwm3.common.hw,
+			[CLK_PWM4]				= &clk_pwm4.common.hw,
+			[CLK_PWM5]				= &clk_pwm5.common.hw,
+			[CLK_GPU3D]				= &clk_gpu3d.common.hw,
+			[CLK_I2C0]				= &clk_i2c0.common.hw,
+			[CLK_I2C1]				= &clk_i2c1.common.hw,
+			[CLK_I2C2]				= &clk_i2c2.common.hw,
+			[CLK_I2C3]				= &clk_i2c3.common.hw,
+			[CLK_SPI0]				= &clk_spi0.common.hw,
+			[CLK_SPI1]				= &clk_spi1.common.hw,
+			[CLK_SPI2]				= &clk_spi2.common.hw,
+			[CLK_SPI3]				= &clk_spi3.common.hw,
+			[CLK_USB3_480MPLL0]			= &clk_usb3_480mpll0.common.hw,
+			[CLK_USB3_480MPHY0]			= &clk_usb3_480mphy0.common.hw,
+			[CLK_USB3_5GPHY]			= &clk_usb3_5gphy.common.hw,
+			[CLK_USB3_CCE]				= &clk_usb3_cce.common.hw,
+			[CLK_LCD]				= &clk_lcd.common.hw,
+			[CLK_HDMI_AUDIO]			= &clk_hdmi_audio.common.hw,
+			[CLK_I2SRX]				= &clk_i2srx.common.hw,
+			[CLK_I2STX]				= &clk_i2stx.common.hw,
+			[CLK_SENSOR0]				= &clk_sensor0.common.hw,
+			[CLK_SENSOR1]				= &clk_sensor1.common.hw,
+			[CLK_HDMI_DEV]				= &clk_hdmi_dev.common.hw,
+			[CLK_ETHERNET]				= &clk_ethernet.common.hw,
+			[CLK_RMII_REF]				= &clk_rmii_ref.common.hw,
+			[CLK_USB2H0_PLLEN]			= &clk_usb2h0_pllen.common.hw,
+			[CLK_USB2H0_PHY]			= &clk_usb2h0_phy.common.hw,
+			[CLK_USB2H0_CCE]			= &clk_usb2h0_cce.common.hw,
+			[CLK_USB2H1_PLLEN]			= &clk_usb2h1_pllen.common.hw,
+			[CLK_USB2H1_PHY]			= &clk_usb2h1_phy.common.hw,
+			[CLK_USB2H1_CCE]			= &clk_usb2h1_cce.common.hw,
+			[CLK_TVOUT]				= &clk_tvout.common.hw,
+			[CLK_THERMAL_SENSOR]			= &clk_thermal_sensor.common.hw,
+			[CLK_IRC_SWITCH]			= &clk_irc_switch.common.hw,
+			[CLK_PCM1]				= &clk_pcm1.common.hw,
+		},
+		.num    = CLK_NR_CLKS,
+};
+
+static const struct owl_clk_desc s700_clk_desc = {
+	.clks       = s700_clks,
+	.num_clks   = ARRAY_SIZE(s700_clks),
+
+	.hw_clks    = &s700_hw_clks,
+};
+
+static int s700_clk_probe(struct platform_device *pdev)
+{
+	const struct owl_clk_desc *desc;
+
+	desc = &s700_clk_desc;
+	owl_clk_regmap_init(pdev, desc);
+
+	return owl_clk_probe(&pdev->dev, desc->hw_clks);
+}
+
+static const struct of_device_id s700_clk_of_match[] = {
+	{ .compatible = "actions,s700-cmu", },
+	{ /* sentinel */ }
+};
+
+static struct platform_driver s700_clk_driver = {
+	.probe = s700_clk_probe,
+	.driver = {
+		.name = "s700-cmu",
+		.of_match_table = s700_clk_of_match
+	},
+};
+
+static int __init s700_clk_init(void)
+{
+	return platform_driver_register(&s700_clk_driver);
+}
+core_initcall(s700_clk_init);
-- 
cgit v1.2.3


From 91329e27f36d7008402fb4d5e853e731a200f19b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:50 +0300
Subject: mlxsw: reg: Prepare PERERP register for A-TCAM usage

Before introducing A-TCAM support we need to make sure all the necessary
fields are configurable and not hard coded to values that worked for the
C-TCAM only use case.

This includes - for example - the ability to configure the eRP table
used by the TCAM region.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          | 22 +++++++++++++++++++---
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   |  2 +-
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 596fddfb3850..f4e16ac20fea 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2663,12 +2663,28 @@ MLXSW_ITEM_BIT_ARRAY(reg, pererp, erpt_vector, 0x14, 4, 1);
  */
 MLXSW_ITEM32(reg, pererp, master_rp_id, 0x18, 0, 4);
 
-static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id)
+static inline void mlxsw_reg_pererp_erp_vector_pack(char *payload,
+						    unsigned long *erp_vector,
+						    unsigned long size)
+{
+	unsigned long bit;
+
+	for_each_set_bit(bit, erp_vector, size)
+		mlxsw_reg_pererp_erpt_vector_set(payload, bit, true);
+}
+
+static inline void mlxsw_reg_pererp_pack(char *payload, u16 region_id,
+					 bool ctcam_le, bool erpt_pointer_valid,
+					 u8 erpt_bank_pointer, u8 erpt_pointer,
+					 u8 master_rp_id)
 {
 	MLXSW_REG_ZERO(pererp, payload);
 	mlxsw_reg_pererp_region_id_set(payload, region_id);
-	mlxsw_reg_pererp_ctcam_le_set(payload, true);
-	mlxsw_reg_pererp_erpt_pointer_valid_set(payload, true);
+	mlxsw_reg_pererp_ctcam_le_set(payload, ctcam_le);
+	mlxsw_reg_pererp_erpt_pointer_valid_set(payload, erpt_pointer_valid);
+	mlxsw_reg_pererp_erpt_bank_pointer_set(payload, erpt_bank_pointer);
+	mlxsw_reg_pererp_erpt_pointer_set(payload, erpt_pointer);
+	mlxsw_reg_pererp_master_rp_id_set(payload, master_rp_id);
 }
 
 /* IEDR - Infrastructure Entry Delete Register
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index b1b3b0e0c00e..a27d3b0f9fcb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -72,7 +72,7 @@ mlxsw_sp_acl_atcam_region_erp_init(struct mlxsw_sp *mlxsw_sp,
 {
 	char pererp_pl[MLXSW_REG_PERERP_LEN];
 
-	mlxsw_reg_pererp_pack(pererp_pl, region_id);
+	mlxsw_reg_pererp_pack(pererp_pl, region_id, true, true, 0, 0, 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
 }
 
-- 
cgit v1.2.3


From aecefac903ce3c7cb09e88a1f628778b47eb069e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:51 +0300
Subject: mlxsw: reg: Add Policy-Engine TCAM Entry Register Version 3

The register is used to configure rules in the A-TCAM.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 165 +++++++++++++++++++++++++++++-
 1 file changed, 162 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index f4e16ac20fea..cf07436c911b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2466,14 +2466,14 @@ MLXSW_ITEM32(reg, ptce2, priority, 0x04, 0, 24);
 MLXSW_ITEM_BUF(reg, ptce2, tcam_region_info, 0x10,
 	       MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN);
 
-#define MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN 96
+#define MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN 96
 
 /* reg_ptce2_flex_key_blocks
  * ACL Key.
  * Access: RW
  */
 MLXSW_ITEM_BUF(reg, ptce2, flex_key_blocks, 0x20,
-	       MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN);
+	       MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 
 /* reg_ptce2_mask
  * mask- in the same size as key. A bit that is set directs the TCAM
@@ -2482,7 +2482,7 @@ MLXSW_ITEM_BUF(reg, ptce2, flex_key_blocks, 0x20,
  * Access: RW
  */
 MLXSW_ITEM_BUF(reg, ptce2, mask, 0x80,
-	       MLXSW_REG_PTCE2_FLEX_KEY_BLOCKS_LEN);
+	       MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 
 /* reg_ptce2_flex_action_set
  * ACL action set.
@@ -2545,6 +2545,164 @@ static inline void mlxsw_reg_perar_pack(char *payload, u16 region_id,
 	mlxsw_reg_perar_hw_region_set(payload, hw_region);
 }
 
+/* PTCE-V3 - Policy-Engine TCAM Entry Register Version 3
+ * -----------------------------------------------------
+ * This register is a new version of PTCE-V2 in order to support the
+ * A-TCAM. This register is not supported by SwitchX/-2 and Spectrum.
+ */
+#define MLXSW_REG_PTCE3_ID 0x3027
+#define MLXSW_REG_PTCE3_LEN 0xF0
+
+MLXSW_REG_DEFINE(ptce3, MLXSW_REG_PTCE3_ID, MLXSW_REG_PTCE3_LEN);
+
+/* reg_ptce3_v
+ * Valid.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, v, 0x00, 31, 1);
+
+enum mlxsw_reg_ptce3_op {
+	/* Write operation. Used to write a new entry to the table.
+	 * All R/W fields are relevant for new entry. Activity bit is set
+	 * for new entries. Write with v = 0 will delete the entry. Must
+	 * not be used if an entry exists.
+	 */
+	 MLXSW_REG_PTCE3_OP_WRITE_WRITE = 0,
+	 /* Update operation */
+	 MLXSW_REG_PTCE3_OP_WRITE_UPDATE = 1,
+	 /* Read operation */
+	 MLXSW_REG_PTCE3_OP_QUERY_READ = 0,
+};
+
+/* reg_ptce3_op
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, ptce3, op, 0x00, 20, 3);
+
+/* reg_ptce3_priority
+ * Priority of the rule. Higher values win.
+ * For Spectrum-2 range is 1..cap_kvd_size - 1
+ * Note: Priority does not have to be unique per rule.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, priority, 0x04, 0, 24);
+
+/* reg_ptce3_tcam_region_info
+ * Opaque object that represents the TCAM region.
+ * Access: Index
+ */
+MLXSW_ITEM_BUF(reg, ptce3, tcam_region_info, 0x10,
+	       MLXSW_REG_PXXX_TCAM_REGION_INFO_LEN);
+
+/* reg_ptce3_flex2_key_blocks
+ * ACL key. The key must be masked according to eRP (if exists) or
+ * according to master mask.
+ * Access: Index
+ */
+MLXSW_ITEM_BUF(reg, ptce3, flex2_key_blocks, 0x20,
+	       MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+
+/* reg_ptce3_erp_id
+ * eRP ID.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, erp_id, 0x80, 0, 4);
+
+/* reg_ptce3_delta_start
+ * Start point of delta_value and delta_mask, in bits. Must not exceed
+ * num_key_blocks * 36 - 8. Reserved when delta_mask = 0.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, delta_start, 0x84, 0, 10);
+
+/* reg_ptce3_delta_mask
+ * Delta mask.
+ * 0 - Ignore relevant bit in delta_value
+ * 1 - Compare relevant bit in delta_value
+ * Delta mask must not be set for reserved fields in the key blocks.
+ * Note: No delta when no eRPs. Thus, for regions with
+ * PERERP.erpt_pointer_valid = 0 the delta mask must be 0.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, delta_mask, 0x88, 16, 8);
+
+/* reg_ptce3_delta_value
+ * Delta value.
+ * Bits which are masked by delta_mask must be 0.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, ptce3, delta_value, 0x88, 0, 8);
+
+/* reg_ptce3_prune_vector
+ * Pruning vector relative to the PERPT.erp_id.
+ * Used for reducing lookups.
+ * 0 - NEED: Do a lookup using the eRP.
+ * 1 - PRUNE: Do not perform a lookup using the eRP.
+ * Maybe be modified by PEAPBL and PEAPBM.
+ * Note: In Spectrum-2, a region of 8 key blocks must be set to either
+ * all 1's or all 0's.
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, ptce3, prune_vector, 0x90, 4, 1);
+
+/* reg_ptce3_prune_ctcam
+ * Pruning on C-TCAM. Used for reducing lookups.
+ * 0 - NEED: Do a lookup in the C-TCAM.
+ * 1 - PRUNE: Do not perform a lookup in the C-TCAM.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, prune_ctcam, 0x94, 31, 1);
+
+/* reg_ptce3_large_exists
+ * Large entry key ID exists.
+ * Within the region:
+ * 0 - SINGLE: The large_entry_key_id is not currently in use.
+ * For rule insert: The MSB of the key (blocks 6..11) will be added.
+ * For rule delete: The MSB of the key will be removed.
+ * 1 - NON_SINGLE: The large_entry_key_id is currently in use.
+ * For rule insert: The MSB of the key (blocks 6..11) will not be added.
+ * For rule delete: The MSB of the key will not be removed.
+ * Access: WO
+ */
+MLXSW_ITEM32(reg, ptce3, large_exists, 0x98, 31, 1);
+
+/* reg_ptce3_large_entry_key_id
+ * Large entry key ID.
+ * A key for 12 key blocks rules. Reserved when region has less than 12 key
+ * blocks. Must be different for different keys which have the same common
+ * 6 key blocks (MSB, blocks 6..11) key within a region.
+ * Range is 0..cap_max_pe_large_key_id - 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, large_entry_key_id, 0x98, 0, 24);
+
+/* reg_ptce3_action_pointer
+ * Pointer to action.
+ * Range is 0..cap_max_kvd_action_sets - 1
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, ptce3, action_pointer, 0xA0, 0, 24);
+
+static inline void mlxsw_reg_ptce3_pack(char *payload, bool valid,
+					enum mlxsw_reg_ptce3_op op,
+					u32 priority,
+					const char *tcam_region_info,
+					const char *key, u8 erp_id,
+					bool large_exists, u32 lkey_id,
+					u32 action_pointer)
+{
+	MLXSW_REG_ZERO(ptce3, payload);
+	mlxsw_reg_ptce3_v_set(payload, valid);
+	mlxsw_reg_ptce3_op_set(payload, op);
+	mlxsw_reg_ptce3_priority_set(payload, priority);
+	mlxsw_reg_ptce3_tcam_region_info_memcpy_to(payload, tcam_region_info);
+	mlxsw_reg_ptce3_flex2_key_blocks_memcpy_to(payload, key);
+	mlxsw_reg_ptce3_erp_id_set(payload, erp_id);
+	mlxsw_reg_ptce3_large_exists_set(payload, large_exists);
+	mlxsw_reg_ptce3_large_entry_key_id_set(payload, lkey_id);
+	mlxsw_reg_ptce3_action_pointer_set(payload, action_pointer);
+}
+
 /* PERCR - Policy-Engine Region Configuration Register
  * ---------------------------------------------------
  * This register configures the region parameters. The region_id must be
@@ -8265,6 +8423,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(pefa),
 	MLXSW_REG(ptce2),
 	MLXSW_REG(perar),
+	MLXSW_REG(ptce3),
 	MLXSW_REG(percr),
 	MLXSW_REG(pererp),
 	MLXSW_REG(iedr),
-- 
cgit v1.2.3


From 8c0d1cdd052a4469cf7a53553299bd38596947dc Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:52 +0300
Subject: mlxsw: reg: Add Policy-Engine eRP Table Register

The register is used to add and delete eRPs from the eRP table.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 113 ++++++++++++++++++++++++++++++
 1 file changed, 113 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index cf07436c911b..5acef249e776 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2504,6 +2504,118 @@ static inline void mlxsw_reg_ptce2_pack(char *payload, bool valid,
 	mlxsw_reg_ptce2_tcam_region_info_memcpy_to(payload, tcam_region_info);
 }
 
+/* PERPT - Policy-Engine ERP Table Register
+ * ----------------------------------------
+ * This register adds and removes eRPs from the eRP table.
+ */
+#define MLXSW_REG_PERPT_ID 0x3021
+#define MLXSW_REG_PERPT_LEN 0x80
+
+MLXSW_REG_DEFINE(perpt, MLXSW_REG_PERPT_ID, MLXSW_REG_PERPT_LEN);
+
+/* reg_perpt_erpt_bank
+ * eRP table bank.
+ * Range 0 .. cap_max_erp_table_banks - 1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, perpt, erpt_bank, 0x00, 16, 4);
+
+/* reg_perpt_erpt_index
+ * Index to eRP table within the eRP bank.
+ * Range is 0 .. cap_max_erp_table_bank_size - 1
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, perpt, erpt_index, 0x00, 0, 8);
+
+enum mlxsw_reg_perpt_key_size {
+	MLXSW_REG_PERPT_KEY_SIZE_2KB,
+	MLXSW_REG_PERPT_KEY_SIZE_4KB,
+	MLXSW_REG_PERPT_KEY_SIZE_8KB,
+	MLXSW_REG_PERPT_KEY_SIZE_12KB,
+};
+
+/* reg_perpt_key_size
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, key_size, 0x04, 0, 4);
+
+/* reg_perpt_bf_bypass
+ * 0 - The eRP is used only if bloom filter state is set for the given
+ * rule.
+ * 1 - The eRP is used regardless of bloom filter state.
+ * The bypass is an OR condition of region_id or eRP. See PERCR.bf_bypass
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, perpt, bf_bypass, 0x08, 8, 1);
+
+/* reg_perpt_erp_id
+ * eRP ID for use by the rules.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, perpt, erp_id, 0x08, 0, 4);
+
+/* reg_perpt_erpt_base_bank
+ * Base eRP table bank, points to head of erp_vector
+ * Range is 0 .. cap_max_erp_table_banks - 1
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, erpt_base_bank, 0x0C, 16, 4);
+
+/* reg_perpt_erpt_base_index
+ * Base index to eRP table within the eRP bank
+ * Range is 0 .. cap_max_erp_table_bank_size - 1
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, erpt_base_index, 0x0C, 0, 8);
+
+/* reg_perpt_erp_index_in_vector
+ * eRP index in the vector.
+ * Access: OP
+ */
+MLXSW_ITEM32(reg, perpt, erp_index_in_vector, 0x10, 0, 4);
+
+/* reg_perpt_erp_vector
+ * eRP vector.
+ * Access: OP
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, perpt, erp_vector, 0x14, 4, 1);
+
+/* reg_perpt_mask
+ * Mask
+ * 0 - A-TCAM will ignore the bit in key
+ * 1 - A-TCAM will compare the bit in key
+ * Access: RW
+ */
+MLXSW_ITEM_BUF(reg, perpt, mask, 0x20, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+
+static inline void mlxsw_reg_perpt_erp_vector_pack(char *payload,
+						   unsigned long *erp_vector,
+						   unsigned long size)
+{
+	unsigned long bit;
+
+	for_each_set_bit(bit, erp_vector, size)
+		mlxsw_reg_perpt_erp_vector_set(payload, bit, true);
+}
+
+static inline void
+mlxsw_reg_perpt_pack(char *payload, u8 erpt_bank, u8 erpt_index,
+		     enum mlxsw_reg_perpt_key_size key_size, u8 erp_id,
+		     u8 erpt_base_bank, u8 erpt_base_index, u8 erp_index,
+		     char *mask)
+{
+	MLXSW_REG_ZERO(perpt, payload);
+	mlxsw_reg_perpt_erpt_bank_set(payload, erpt_bank);
+	mlxsw_reg_perpt_erpt_index_set(payload, erpt_index);
+	mlxsw_reg_perpt_key_size_set(payload, key_size);
+	mlxsw_reg_perpt_bf_bypass_set(payload, true);
+	mlxsw_reg_perpt_erp_id_set(payload, erp_id);
+	mlxsw_reg_perpt_erpt_base_bank_set(payload, erpt_base_bank);
+	mlxsw_reg_perpt_erpt_base_index_set(payload, erpt_base_index);
+	mlxsw_reg_perpt_erp_index_in_vector_set(payload, erp_index);
+	mlxsw_reg_perpt_mask_memcpy_to(payload, mask);
+}
+
 /* PERAR - Policy-Engine Region Association Register
  * -------------------------------------------------
  * This register associates a hw region for region_id's. Changing on the fly
@@ -8422,6 +8534,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(prcr),
 	MLXSW_REG(pefa),
 	MLXSW_REG(ptce2),
+	MLXSW_REG(perpt),
 	MLXSW_REG(perar),
 	MLXSW_REG(ptce3),
 	MLXSW_REG(percr),
-- 
cgit v1.2.3


From 541e249cdcc4d305c39a3cbc6bb6fe0eaaa6cf07 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:53 +0300
Subject: mlxsw: resources: Add Spectrum-2 maximum large key ID resource

Add a resource to make sure we do not exceed the maximum number of
supported large key IDs in a region.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/resources.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index f672a7b71de7..4f84c7c8117b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -65,6 +65,7 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_ACL_FLEX_KEYS,
 	MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE,
 	MLXSW_RES_ID_ACL_ACTIONS_PER_SET,
+	MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID,
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
@@ -108,6 +109,7 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910,
 	[MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911,
 	[MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912,
+	[MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID] = 0x2942,
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
-- 
cgit v1.2.3


From 489142eca9b530219dab77e86c0545e93ebf606a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:54 +0300
Subject: mlxsw: resources: Add Spectrum-2 eRP resources

Add the following resources to be used by A-TCAM code:
* Maximum number of eRP banks
* Maximum size of eRP bank
* Number of eRP entries required for a 2/4/8/12 key blocks mask

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/resources.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index 4f84c7c8117b..bf650f2cd5af 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -65,7 +65,13 @@ enum mlxsw_res_id {
 	MLXSW_RES_ID_ACL_FLEX_KEYS,
 	MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE,
 	MLXSW_RES_ID_ACL_ACTIONS_PER_SET,
+	MLXSW_RES_ID_ACL_MAX_ERPT_BANKS,
+	MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE,
 	MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_2KB,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB,
+	MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB,
 	MLXSW_RES_ID_MAX_CPU_POLICERS,
 	MLXSW_RES_ID_MAX_VRS,
 	MLXSW_RES_ID_MAX_RIFS,
@@ -109,7 +115,13 @@ static u16 mlxsw_res_ids[] = {
 	[MLXSW_RES_ID_ACL_FLEX_KEYS] = 0x2910,
 	[MLXSW_RES_ID_ACL_MAX_ACTION_PER_RULE] = 0x2911,
 	[MLXSW_RES_ID_ACL_ACTIONS_PER_SET] = 0x2912,
+	[MLXSW_RES_ID_ACL_MAX_ERPT_BANKS] = 0x2940,
+	[MLXSW_RES_ID_ACL_MAX_ERPT_BANK_SIZE] = 0x2941,
 	[MLXSW_RES_ID_ACL_MAX_LARGE_KEY_ID] = 0x2942,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_2KB] = 0x2950,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_4KB] = 0x2951,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_8KB] = 0x2952,
+	[MLXSW_RES_ID_ACL_ERPT_ENTRIES_12KB] = 0x2953,
 	[MLXSW_RES_ID_MAX_CPU_POLICERS] = 0x2A13,
 	[MLXSW_RES_ID_MAX_VRS] = 0x2C01,
 	[MLXSW_RES_ID_MAX_RIFS] = 0x2C02,
-- 
cgit v1.2.3


From f465261aa1052bbcb5d1fdba3e9168f2ad86858f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:55 +0300
Subject: mlxsw: spectrum_acl: Implement common eRP core

When rules are inserted into the A-TCAM they are associated with a mask,
which is part of the lookup key: { masked key, mask ID, region ID }.

These masks are called rule patterns (RP) and the aggregation of several
masks into one (to be introduced in follow-up patch sets) is called an
extended RP (eRP).

When a packet undergoes a lookup in an ACL region it is masked by the
current set of eRPs used by the region, looking for an exact match.
Eventually, the rule with the highest priority is picked.

These eRPs are stored in several global banks to allow for lookup to
occur using several eRPs simultaneously.

At first, an ACL region will only require a single mask - upon the
insertion of the first rule. In this case, the region can use the
"master RP" which is composed by OR-ing all the masks used by the
region. This mask is a property of the region and thus there is no need
to use the above mentioned banks.

At some point, a second mask will be needed. In this case, the region
will need to allocate an eRP table from the above mentioned banks and
insert its masks there.

>From now on, upon lookup, the eRP table used by the region will be
fetched from the eRP banks - using {eRP bank, Index within the bank} -
and the eRPs present in the table will be used to mask the packet. Note
that masks with consecutive indexes are inserted into consecutive banks.

When rules are deleted and a region only needs a single mask once again
it can free its eRP table and use the master RP.

The above logic is implemented in the eRP core and represented using the
following state machine:

    +------------+   create mask - as master RP   +---------------+
    |            +-------------------------------->               |
    |  no masks  |                                |  single mask  |
    |            <--------------------------------+               |
    +------------+          delete mask           +-----+--^------+
                                                        |  |
                                                        |  |
                                  create mask -         |  |  delete mask -
    create mask                   transition to use eRP |  |  transition to
     +--------+                   table                 |  |  use master RP
     |        |                                         |  |
     |        |                                         |  |
+----v--------+----+         create mask           +----v--+-----+
|                  <-------------------------------+             |
|  multiple masks  |                               |  two masks  |
|                  +------------------------------->             |
+------------------+      delete mask - if two     +-------------+
                          remaining

The code that actually configures rules in the A-TCAM will interface
with the eRP core by getting or putting an eRP based on the required
mask used by the rule.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/Kconfig        |    1 +
 drivers/net/ethernet/mellanox/mlxsw/Makefile       |    2 +-
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 1019 ++++++++++++++++++++
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |   40 +
 4 files changed, 1061 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c

diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
index 82827a8d3d67..8a291eb36c64 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig
@@ -78,6 +78,7 @@ config MLXSW_SPECTRUM
 	depends on IPV6 || IPV6=n
 	depends on NET_IPGRE || NET_IPGRE=n
 	depends on IPV6_GRE || IPV6_GRE=n
+	select GENERIC_ALLOCATOR
 	select PARMAN
 	select MLXFW
 	default m
diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile
index 4a1069166119..68fa44a41485 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/Makefile
+++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile
@@ -18,7 +18,7 @@ mlxsw_spectrum-objs		:= spectrum.o spectrum_buffers.o \
 				   spectrum1_kvdl.o spectrum2_kvdl.o \
 				   spectrum_kvdl.o \
 				   spectrum_acl_tcam.o spectrum_acl_ctcam.o \
-				   spectrum_acl_atcam.o \
+				   spectrum_acl_atcam.o spectrum_acl_erp.o \
 				   spectrum1_acl_tcam.o spectrum2_acl_tcam.o \
 				   spectrum_acl.o \
 				   spectrum_flower.o spectrum_cnt.o \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
new file mode 100644
index 000000000000..960f29140b43
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -0,0 +1,1019 @@
+/*
+ * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+ * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2018 Ido Schimmel <idosch@mellanox.com>
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <linux/bitmap.h>
+#include <linux/errno.h>
+#include <linux/genalloc.h>
+#include <linux/gfp.h>
+#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/rhashtable.h>
+#include <linux/rtnetlink.h>
+#include <linux/slab.h>
+
+#include "core.h"
+#include "reg.h"
+#include "spectrum.h"
+#include "spectrum_acl_tcam.h"
+
+/* gen_pool_alloc() returns 0 when allocation fails, so use an offset */
+#define MLXSW_SP_ACL_ERP_GENALLOC_OFFSET 0x100
+#define MLXSW_SP_ACL_ERP_MAX_PER_REGION 16
+
+struct mlxsw_sp_acl_erp_core {
+	unsigned int erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX + 1];
+	struct gen_pool *erp_tables;
+	struct mlxsw_sp *mlxsw_sp;
+	unsigned int num_erp_banks;
+};
+
+struct mlxsw_sp_acl_erp_key {
+	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN];
+};
+
+struct mlxsw_sp_acl_erp {
+	struct mlxsw_sp_acl_erp_key key;
+	u8 id;
+	u8 index;
+	refcount_t refcnt;
+	DECLARE_BITMAP(mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
+	struct list_head list;
+	struct rhash_head ht_node;
+	struct mlxsw_sp_acl_erp_table *erp_table;
+};
+
+struct mlxsw_sp_acl_erp_master_mask {
+	DECLARE_BITMAP(bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN);
+	unsigned int count[MLXSW_SP_ACL_TCAM_MASK_LEN];
+};
+
+struct mlxsw_sp_acl_erp_table {
+	struct mlxsw_sp_acl_erp_master_mask master_mask;
+	DECLARE_BITMAP(erp_id_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	DECLARE_BITMAP(erp_index_bitmap, MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	struct list_head atcam_erps_list;
+	struct rhashtable erp_ht;
+	struct mlxsw_sp_acl_erp_core *erp_core;
+	struct mlxsw_sp_acl_atcam_region *aregion;
+	const struct mlxsw_sp_acl_erp_table_ops *ops;
+	unsigned long base_index;
+	unsigned int num_atcam_erps;
+	unsigned int num_max_atcam_erps;
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_erp_ht_params = {
+	.key_len = sizeof(struct mlxsw_sp_acl_erp_key),
+	.key_offset = offsetof(struct mlxsw_sp_acl_erp, key),
+	.head_offset = offsetof(struct mlxsw_sp_acl_erp, ht_node),
+};
+
+struct mlxsw_sp_acl_erp_table_ops {
+	struct mlxsw_sp_acl_erp *
+		(*erp_create)(struct mlxsw_sp_acl_erp_table *erp_table,
+			      struct mlxsw_sp_acl_erp_key *key);
+	void (*erp_destroy)(struct mlxsw_sp_acl_erp_table *erp_table,
+			    struct mlxsw_sp_acl_erp *erp);
+};
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+			     struct mlxsw_sp_acl_erp_key *key);
+static void
+mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+			      struct mlxsw_sp_acl_erp *erp);
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_second_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp_key *key);
+static void
+mlxsw_sp_acl_erp_second_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				     struct mlxsw_sp_acl_erp *erp);
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_first_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key);
+static void
+mlxsw_sp_acl_erp_first_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp *erp);
+static void
+mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				 struct mlxsw_sp_acl_erp *erp);
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_multiple_masks_ops = {
+	.erp_create = mlxsw_sp_acl_erp_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_mask_destroy,
+};
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_two_masks_ops = {
+	.erp_create = mlxsw_sp_acl_erp_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_second_mask_destroy,
+};
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_single_mask_ops = {
+	.erp_create = mlxsw_sp_acl_erp_second_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_first_mask_destroy,
+};
+
+static const struct mlxsw_sp_acl_erp_table_ops erp_no_mask_ops = {
+	.erp_create = mlxsw_sp_acl_erp_first_mask_create,
+	.erp_destroy = mlxsw_sp_acl_erp_no_mask_destroy,
+};
+
+u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp)
+{
+	return erp->id;
+}
+
+static unsigned int
+mlxsw_sp_acl_erp_table_entry_size(const struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion = erp_table->aregion;
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+
+	return erp_core->erpt_entries_size[aregion->type];
+}
+
+static int mlxsw_sp_acl_erp_id_get(struct mlxsw_sp_acl_erp_table *erp_table,
+				   u8 *p_id)
+{
+	u8 id;
+
+	id = find_first_zero_bit(erp_table->erp_id_bitmap,
+				 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	if (id < MLXSW_SP_ACL_ERP_MAX_PER_REGION) {
+		__set_bit(id, erp_table->erp_id_bitmap);
+		*p_id = id;
+		return 0;
+	}
+
+	return -ENOBUFS;
+}
+
+static void mlxsw_sp_acl_erp_id_put(struct mlxsw_sp_acl_erp_table *erp_table,
+				    u8 id)
+{
+	__clear_bit(id, erp_table->erp_id_bitmap);
+}
+
+static void
+mlxsw_sp_acl_erp_master_mask_bit_set(unsigned long bit,
+				     struct mlxsw_sp_acl_erp_master_mask *mask)
+{
+	if (mask->count[bit]++ == 0)
+		__set_bit(bit, mask->bitmap);
+}
+
+static void
+mlxsw_sp_acl_erp_master_mask_bit_clear(unsigned long bit,
+				       struct mlxsw_sp_acl_erp_master_mask *mask)
+{
+	if (--mask->count[bit] == 0)
+		__clear_bit(bit, mask->bitmap);
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_update(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+	char percr_pl[MLXSW_REG_PERCR_LEN];
+	char *master_mask;
+
+	mlxsw_reg_percr_pack(percr_pl, region->id);
+	master_mask = mlxsw_reg_percr_master_mask_data(percr_pl);
+	bitmap_to_arr32((u32 *) master_mask, erp_table->master_mask.bitmap,
+			MLXSW_SP_ACL_TCAM_MASK_LEN);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_set(struct mlxsw_sp_acl_erp_table *erp_table,
+				 const struct mlxsw_sp_acl_erp *erp)
+{
+	unsigned long bit;
+	int err;
+
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
+						     &erp_table->master_mask);
+
+	err = mlxsw_sp_acl_erp_master_mask_update(erp_table);
+	if (err)
+		goto err_master_mask_update;
+
+	return 0;
+
+err_master_mask_update:
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
+						       &erp_table->master_mask);
+	return err;
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_clear(struct mlxsw_sp_acl_erp_table *erp_table,
+				   const struct mlxsw_sp_acl_erp *erp)
+{
+	unsigned long bit;
+	int err;
+
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_clear(bit,
+						       &erp_table->master_mask);
+
+	err = mlxsw_sp_acl_erp_master_mask_update(erp_table);
+	if (err)
+		goto err_master_mask_update;
+
+	return 0;
+
+err_master_mask_update:
+	for_each_set_bit(bit, erp->mask_bitmap, MLXSW_SP_ACL_TCAM_MASK_LEN)
+		mlxsw_sp_acl_erp_master_mask_bit_set(bit,
+						     &erp_table->master_mask);
+	return err;
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_generic_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	erp = kzalloc(sizeof(*erp), GFP_KERNEL);
+	if (!erp)
+		return ERR_PTR(-ENOMEM);
+
+	err = mlxsw_sp_acl_erp_id_get(erp_table, &erp->id);
+	if (err)
+		goto err_erp_id_get;
+
+	memcpy(&erp->key, key, sizeof(*key));
+	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	list_add(&erp->list, &erp_table->atcam_erps_list);
+	refcount_set(&erp->refcnt, 1);
+	erp_table->num_atcam_erps++;
+	erp->erp_table = erp_table;
+
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	if (err)
+		goto err_master_mask_set;
+
+	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
+				     mlxsw_sp_acl_erp_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	return erp;
+
+err_rhashtable_insert:
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+err_master_mask_set:
+	erp_table->num_atcam_erps--;
+	list_del(&erp->list);
+	mlxsw_sp_acl_erp_id_put(erp_table, erp->id);
+err_erp_id_get:
+	kfree(erp);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_generic_destroy(struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+
+	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
+			       mlxsw_sp_acl_erp_ht_params);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	erp_table->num_atcam_erps--;
+	list_del(&erp->list);
+	mlxsw_sp_acl_erp_id_put(erp_table, erp->id);
+	kfree(erp);
+}
+
+static int
+mlxsw_sp_acl_erp_table_alloc(struct mlxsw_sp_acl_erp_core *erp_core,
+			     unsigned int num_erps,
+			     enum mlxsw_sp_acl_atcam_region_type region_type,
+			     unsigned long *p_index)
+{
+	unsigned int num_rows, entry_size;
+
+	/* We only allow allocations of entire rows */
+	if (num_erps % erp_core->num_erp_banks != 0)
+		return -EINVAL;
+
+	entry_size = erp_core->erpt_entries_size[region_type];
+	num_rows = num_erps / erp_core->num_erp_banks;
+
+	*p_index = gen_pool_alloc(erp_core->erp_tables, num_rows * entry_size);
+	if (*p_index == 0)
+		return -ENOBUFS;
+	*p_index -= MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_erp_table_free(struct mlxsw_sp_acl_erp_core *erp_core,
+			    unsigned int num_erps,
+			    enum mlxsw_sp_acl_atcam_region_type region_type,
+			    unsigned long index)
+{
+	unsigned long base_index;
+	unsigned int entry_size;
+	size_t size;
+
+	entry_size = erp_core->erpt_entries_size[region_type];
+	base_index = index + MLXSW_SP_ACL_ERP_GENALLOC_OFFSET;
+	size = num_erps / erp_core->num_erp_banks * entry_size;
+	gen_pool_free(erp_core->erp_tables, base_index, size);
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_table_master_rp(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	if (!list_is_singular(&erp_table->atcam_erps_list))
+		return NULL;
+
+	return list_first_entry(&erp_table->atcam_erps_list,
+				struct mlxsw_sp_acl_erp, list);
+}
+
+static int mlxsw_sp_acl_erp_index_get(struct mlxsw_sp_acl_erp_table *erp_table,
+				      u8 *p_index)
+{
+	u8 index;
+
+	index = find_first_zero_bit(erp_table->erp_index_bitmap,
+				    erp_table->num_max_atcam_erps);
+	if (index < erp_table->num_max_atcam_erps) {
+		__set_bit(index, erp_table->erp_index_bitmap);
+		*p_index = index;
+		return 0;
+	}
+
+	return -ENOBUFS;
+}
+
+static void mlxsw_sp_acl_erp_index_put(struct mlxsw_sp_acl_erp_table *erp_table,
+				       u8 index)
+{
+	__clear_bit(index, erp_table->erp_index_bitmap);
+}
+
+static void
+mlxsw_sp_acl_erp_table_locate(const struct mlxsw_sp_acl_erp_table *erp_table,
+			      const struct mlxsw_sp_acl_erp *erp,
+			      u8 *p_erpt_bank, u8 *p_erpt_index)
+{
+	unsigned int entry_size = mlxsw_sp_acl_erp_table_entry_size(erp_table);
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	unsigned int row;
+
+	*p_erpt_bank = erp->index % erp_core->num_erp_banks;
+	row = erp->index / erp_core->num_erp_banks;
+	*p_erpt_index = erp_table->base_index + row * entry_size;
+}
+
+static int
+mlxsw_sp_acl_erp_table_erp_add(struct mlxsw_sp_acl_erp_table *erp_table,
+			       struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	enum mlxsw_reg_perpt_key_size key_size;
+	char perpt_pl[MLXSW_REG_PERPT_LEN];
+	u8 erpt_bank, erpt_index;
+
+	mlxsw_sp_acl_erp_table_locate(erp_table, erp, &erpt_bank, &erpt_index);
+	key_size = (enum mlxsw_reg_perpt_key_size) erp_table->aregion->type;
+	mlxsw_reg_perpt_pack(perpt_pl, erpt_bank, erpt_index, key_size, erp->id,
+			     0, erp_table->base_index, erp->index,
+			     erp->key.mask);
+	mlxsw_reg_perpt_erp_vector_pack(perpt_pl, erp_table->erp_index_bitmap,
+					MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_perpt_erp_vector_set(perpt_pl, erp->index, true);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perpt), perpt_pl);
+}
+
+static void mlxsw_sp_acl_erp_table_erp_del(struct mlxsw_sp_acl_erp *erp)
+{
+	char empty_mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	enum mlxsw_reg_perpt_key_size key_size;
+	char perpt_pl[MLXSW_REG_PERPT_LEN];
+	u8 erpt_bank, erpt_index;
+
+	mlxsw_sp_acl_erp_table_locate(erp_table, erp, &erpt_bank, &erpt_index);
+	key_size = (enum mlxsw_reg_perpt_key_size) erp_table->aregion->type;
+	mlxsw_reg_perpt_pack(perpt_pl, erpt_bank, erpt_index, key_size, erp->id,
+			     0, erp_table->base_index, erp->index, empty_mask);
+	mlxsw_reg_perpt_erp_vector_pack(perpt_pl, erp_table->erp_index_bitmap,
+					MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_perpt_erp_vector_set(perpt_pl, erp->index, false);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perpt), perpt_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_table_enable(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, true, 0,
+			      erp_table->base_index, 0);
+	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
+					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static void
+mlxsw_sp_acl_erp_table_disable(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+	struct mlxsw_sp_acl_erp *master_rp;
+
+	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
+	if (!master_rp)
+		return;
+
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, false, 0, 0,
+			      master_rp->id);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_table_relocate(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	list_for_each_entry(erp, &erp_table->atcam_erps_list, list) {
+		err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp);
+		if (err)
+			goto err_table_erp_add;
+	}
+
+	return 0;
+
+err_table_erp_add:
+	list_for_each_entry_continue_reverse(erp, &erp_table->atcam_erps_list,
+					     list)
+		mlxsw_sp_acl_erp_table_erp_del(erp);
+	return err;
+}
+
+static int
+mlxsw_sp_acl_erp_table_expand(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	unsigned int num_erps, old_num_erps = erp_table->num_max_atcam_erps;
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	unsigned long old_base_index = erp_table->base_index;
+	int err;
+
+	if (erp_table->num_atcam_erps < erp_table->num_max_atcam_erps)
+		return 0;
+
+	if (erp_table->num_max_atcam_erps == MLXSW_SP_ACL_ERP_MAX_PER_REGION)
+		return -ENOBUFS;
+
+	num_erps = old_num_erps + erp_core->num_erp_banks;
+	err = mlxsw_sp_acl_erp_table_alloc(erp_core, num_erps,
+					   erp_table->aregion->type,
+					   &erp_table->base_index);
+	if (err)
+		return err;
+	erp_table->num_max_atcam_erps = num_erps;
+
+	err = mlxsw_sp_acl_erp_table_relocate(erp_table);
+	if (err)
+		goto err_table_relocate;
+
+	err = mlxsw_sp_acl_erp_table_enable(erp_table);
+	if (err)
+		goto err_table_enable;
+
+	mlxsw_sp_acl_erp_table_free(erp_core, old_num_erps,
+				    erp_table->aregion->type, old_base_index);
+
+	return 0;
+
+err_table_enable:
+err_table_relocate:
+	erp_table->num_max_atcam_erps = old_num_erps;
+	mlxsw_sp_acl_erp_table_free(erp_core, num_erps,
+				    erp_table->aregion->type,
+				    erp_table->base_index);
+	erp_table->base_index = old_base_index;
+	return err;
+}
+
+static int
+mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	struct mlxsw_sp_acl_erp *master_rp;
+	int err;
+
+	/* Initially, allocate a single eRP row. Expand later as needed */
+	err = mlxsw_sp_acl_erp_table_alloc(erp_core, erp_core->num_erp_banks,
+					   erp_table->aregion->type,
+					   &erp_table->base_index);
+	if (err)
+		return err;
+	erp_table->num_max_atcam_erps = erp_core->num_erp_banks;
+
+	/* Transition the sole RP currently configured (the master RP)
+	 * to the eRP table
+	 */
+	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
+	if (!master_rp) {
+		err = -EINVAL;
+		goto err_table_master_rp;
+	}
+
+	/* Maintain the same eRP bank for the master RP, so that we
+	 * wouldn't need to update the bloom filter
+	 */
+	master_rp->index = master_rp->index % erp_core->num_erp_banks;
+	__set_bit(master_rp->index, erp_table->erp_index_bitmap);
+
+	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, master_rp);
+	if (err)
+		goto err_table_master_rp_add;
+
+	err = mlxsw_sp_acl_erp_table_enable(erp_table);
+	if (err)
+		goto err_table_enable;
+
+	return 0;
+
+err_table_enable:
+	mlxsw_sp_acl_erp_table_erp_del(master_rp);
+err_table_master_rp_add:
+	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
+err_table_master_rp:
+	mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps,
+				    erp_table->aregion->type,
+				    erp_table->base_index);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_erp_region_master_mask_trans(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
+	struct mlxsw_sp_acl_erp *master_rp;
+
+	mlxsw_sp_acl_erp_table_disable(erp_table);
+	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
+	if (!master_rp)
+		return;
+	mlxsw_sp_acl_erp_table_erp_del(master_rp);
+	__clear_bit(master_rp->index, erp_table->erp_index_bitmap);
+	mlxsw_sp_acl_erp_table_free(erp_core, erp_table->num_max_atcam_erps,
+				    erp_table->aregion->type,
+				    erp_table->base_index);
+}
+
+static int
+mlxsw_sp_acl_erp_region_erp_add(struct mlxsw_sp_acl_erp_table *erp_table,
+				struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, true, 0,
+			      erp_table->base_index, 0);
+	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
+					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_pererp_erpt_vector_set(pererp_pl, erp->index, true);
+
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static void mlxsw_sp_acl_erp_region_erp_del(struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
+	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, true, 0,
+			      erp_table->base_index, 0);
+	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
+					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
+	mlxsw_reg_pererp_erpt_vector_set(pererp_pl, erp->index, false);
+
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+			     struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	/* Expand the eRP table for the new eRP, if needed */
+	err = mlxsw_sp_acl_erp_table_expand(erp_table);
+	if (err)
+		return ERR_PTR(err);
+
+	erp = mlxsw_sp_acl_erp_generic_create(erp_table, key);
+	if (IS_ERR(erp))
+		return erp;
+
+	err = mlxsw_sp_acl_erp_index_get(erp_table, &erp->index);
+	if (err)
+		goto err_erp_index_get;
+
+	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp);
+	if (err)
+		goto err_table_erp_add;
+
+	err = mlxsw_sp_acl_erp_region_erp_add(erp_table, erp);
+	if (err)
+		goto err_region_erp_add;
+
+	erp_table->ops = &erp_multiple_masks_ops;
+
+	return erp;
+
+err_region_erp_add:
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+err_table_erp_add:
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+err_erp_index_get:
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+			      struct mlxsw_sp_acl_erp *erp)
+{
+	mlxsw_sp_acl_erp_region_erp_del(erp);
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+
+	if (erp_table->num_atcam_erps == 2)
+		erp_table->ops = &erp_two_masks_ops;
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_second_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	/* Transition to use eRP table instead of master mask */
+	err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
+	if (err)
+		return ERR_PTR(err);
+
+	erp = mlxsw_sp_acl_erp_generic_create(erp_table, key);
+	if (IS_ERR(erp)) {
+		err = PTR_ERR(erp);
+		goto err_erp_create;
+	}
+
+	err = mlxsw_sp_acl_erp_index_get(erp_table, &erp->index);
+	if (err)
+		goto err_erp_index_get;
+
+	err = mlxsw_sp_acl_erp_table_erp_add(erp_table, erp);
+	if (err)
+		goto err_table_erp_add;
+
+	err = mlxsw_sp_acl_erp_region_erp_add(erp_table, erp);
+	if (err)
+		goto err_region_erp_add;
+
+	erp_table->ops = &erp_two_masks_ops;
+
+	return erp;
+
+err_region_erp_add:
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+err_table_erp_add:
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+err_erp_index_get:
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+err_erp_create:
+	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_second_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				     struct mlxsw_sp_acl_erp *erp)
+{
+	mlxsw_sp_acl_erp_region_erp_del(erp);
+	mlxsw_sp_acl_erp_table_erp_del(erp);
+	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+	/* Transition to use master mask instead of eRP table */
+	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+
+	erp_table->ops = &erp_single_mask_ops;
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_first_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+
+	erp = mlxsw_sp_acl_erp_generic_create(erp_table, key);
+	if (IS_ERR(erp))
+		return erp;
+
+	erp_table->ops = &erp_single_mask_ops;
+
+	return erp;
+}
+
+static void
+mlxsw_sp_acl_erp_first_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				    struct mlxsw_sp_acl_erp *erp)
+{
+	mlxsw_sp_acl_erp_generic_destroy(erp);
+	erp_table->ops = &erp_no_mask_ops;
+}
+
+static void
+mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
+				 struct mlxsw_sp_acl_erp *erp)
+{
+	WARN_ON(1);
+}
+
+struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
+		     const char *mask)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+	struct mlxsw_sp_acl_erp_key key;
+	struct mlxsw_sp_acl_erp *erp;
+
+	/* eRPs are allocated from a shared resource, but currently all
+	 * allocations are done under RTNL.
+	 */
+	ASSERT_RTNL();
+
+	memcpy(key.mask, mask, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+	erp = rhashtable_lookup_fast(&erp_table->erp_ht, &key,
+				     mlxsw_sp_acl_erp_ht_params);
+	if (erp) {
+		refcount_inc(&erp->refcnt);
+		return erp;
+	}
+
+	return erp_table->ops->erp_create(erp_table, &key);
+}
+
+void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			  struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
+
+	ASSERT_RTNL();
+
+	if (!refcount_dec_and_test(&erp->refcnt))
+		return;
+
+	erp_table->ops->erp_destroy(erp_table, erp);
+}
+
+static struct mlxsw_sp_acl_erp_table *
+mlxsw_sp_acl_erp_table_create(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table;
+	int err;
+
+	erp_table = kzalloc(sizeof(*erp_table), GFP_KERNEL);
+	if (!erp_table)
+		return ERR_PTR(-ENOMEM);
+
+	err = rhashtable_init(&erp_table->erp_ht, &mlxsw_sp_acl_erp_ht_params);
+	if (err)
+		goto err_rhashtable_init;
+
+	erp_table->erp_core = aregion->atcam->erp_core;
+	erp_table->ops = &erp_no_mask_ops;
+	INIT_LIST_HEAD(&erp_table->atcam_erps_list);
+	erp_table->aregion = aregion;
+
+	return erp_table;
+
+err_rhashtable_init:
+	kfree(erp_table);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_table_destroy(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	WARN_ON(!list_empty(&erp_table->atcam_erps_list));
+	rhashtable_destroy(&erp_table->erp_ht);
+	kfree(erp_table);
+}
+
+static int
+mlxsw_sp_acl_erp_master_mask_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	char percr_pl[MLXSW_REG_PERCR_LEN];
+	char *master_mask;
+
+	mlxsw_reg_percr_pack(percr_pl, aregion->region->id);
+	master_mask = mlxsw_reg_percr_master_mask_data(percr_pl);
+	memset(master_mask, 0, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl);
+}
+
+static int
+mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	char pererp_pl[MLXSW_REG_PERERP_LEN];
+
+	mlxsw_reg_pererp_pack(pererp_pl, aregion->region->id, false, false, 0,
+			      0, 0);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+}
+
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table;
+	int err;
+
+	erp_table = mlxsw_sp_acl_erp_table_create(aregion);
+	if (IS_ERR(erp_table))
+		return PTR_ERR(erp_table);
+	aregion->erp_table = erp_table;
+
+	/* Initialize the region's master mask to all zeroes */
+	err = mlxsw_sp_acl_erp_master_mask_init(aregion);
+	if (err)
+		goto err_erp_master_mask_init;
+
+	/* Initialize the region to not use the eRP table */
+	err = mlxsw_sp_acl_erp_region_param_init(aregion);
+	if (err)
+		goto err_erp_region_param_init;
+
+	return 0;
+
+err_erp_region_param_init:
+err_erp_master_mask_init:
+	mlxsw_sp_acl_erp_table_destroy(erp_table);
+	return err;
+}
+
+void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	mlxsw_sp_acl_erp_table_destroy(aregion->erp_table);
+}
+
+static int
+mlxsw_sp_acl_erp_tables_sizes_query(struct mlxsw_sp *mlxsw_sp,
+				    struct mlxsw_sp_acl_erp_core *erp_core)
+{
+	unsigned int size;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_2KB) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_4KB) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_8KB) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_ERPT_ENTRIES_12KB))
+		return -EIO;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_2KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB] = size;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_4KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB] = size;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_8KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB] = size;
+
+	size = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_ERPT_ENTRIES_12KB);
+	erp_core->erpt_entries_size[MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB] = size;
+
+	return 0;
+}
+
+static int mlxsw_sp_acl_erp_tables_init(struct mlxsw_sp *mlxsw_sp,
+					struct mlxsw_sp_acl_erp_core *erp_core)
+{
+	unsigned int erpt_bank_size;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_ERPT_BANK_SIZE) ||
+	    !MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_ERPT_BANKS))
+		return -EIO;
+	erpt_bank_size = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+					    ACL_MAX_ERPT_BANK_SIZE);
+	erp_core->num_erp_banks = MLXSW_CORE_RES_GET(mlxsw_sp->core,
+						     ACL_MAX_ERPT_BANKS);
+
+	erp_core->erp_tables = gen_pool_create(0, -1);
+	if (!erp_core->erp_tables)
+		return -ENOMEM;
+	gen_pool_set_algo(erp_core->erp_tables, gen_pool_best_fit, NULL);
+
+	err = gen_pool_add(erp_core->erp_tables,
+			   MLXSW_SP_ACL_ERP_GENALLOC_OFFSET, erpt_bank_size,
+			   -1);
+	if (err)
+		goto err_gen_pool_add;
+
+	/* Different regions require masks of different sizes */
+	err = mlxsw_sp_acl_erp_tables_sizes_query(mlxsw_sp, erp_core);
+	if (err)
+		goto err_erp_tables_sizes_query;
+
+	return 0;
+
+err_erp_tables_sizes_query:
+err_gen_pool_add:
+	gen_pool_destroy(erp_core->erp_tables);
+	return err;
+}
+
+static void mlxsw_sp_acl_erp_tables_fini(struct mlxsw_sp *mlxsw_sp,
+					 struct mlxsw_sp_acl_erp_core *erp_core)
+{
+	gen_pool_destroy(erp_core->erp_tables);
+}
+
+int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_atcam *atcam)
+{
+	struct mlxsw_sp_acl_erp_core *erp_core;
+	int err;
+
+	erp_core = kzalloc(sizeof(*erp_core), GFP_KERNEL);
+	if (!erp_core)
+		return -ENOMEM;
+	erp_core->mlxsw_sp = mlxsw_sp;
+	atcam->erp_core = erp_core;
+
+	err = mlxsw_sp_acl_erp_tables_init(mlxsw_sp, erp_core);
+	if (err)
+		goto err_erp_tables_init;
+
+	return 0;
+
+err_erp_tables_init:
+	kfree(erp_core);
+	return err;
+}
+
+void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam)
+{
+	mlxsw_sp_acl_erp_tables_fini(mlxsw_sp, atcam->erp_core);
+	kfree(atcam->erp_core);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 6403ec4f5267..af21f7c6c6df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -92,6 +92,9 @@ mlxsw_sp_acl_tcam_profile_ops(struct mlxsw_sp *mlxsw_sp,
 
 #define MLXSW_SP_ACL_TCAM_CATCHALL_PRIO (~0U)
 
+#define MLXSW_SP_ACL_TCAM_MASK_LEN \
+	(MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN * BITS_PER_BYTE)
+
 struct mlxsw_sp_acl_tcam_group;
 
 struct mlxsw_sp_acl_tcam_region {
@@ -144,9 +147,46 @@ mlxsw_sp_acl_ctcam_entry_offset(struct mlxsw_sp_acl_ctcam_entry *centry)
 	return centry->parman_item.index;
 }
 
+enum mlxsw_sp_acl_atcam_region_type {
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB,
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB,
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB,
+	MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB,
+	__MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX,
+};
+
+#define MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX \
+	(__MLXSW_SP_ACL_ATCAM_REGION_TYPE_MAX - 1)
+
+struct mlxsw_sp_acl_atcam {
+	struct mlxsw_sp_acl_erp_core *erp_core;
+};
+
+struct mlxsw_sp_acl_atcam_region {
+	struct mlxsw_sp_acl_tcam_region *region;
+	struct mlxsw_sp_acl_atcam *atcam;
+	enum mlxsw_sp_acl_atcam_region_type type;
+	struct mlxsw_sp_acl_erp_table *erp_table;
+};
+
 int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 					u16 region_id);
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_tcam_region *region);
 
+struct mlxsw_sp_acl_erp;
+
+u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp);
+struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
+		     const char *mask);
+void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
+			  struct mlxsw_sp_acl_erp *erp);
+int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_erp_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
+int mlxsw_sp_acl_erps_init(struct mlxsw_sp *mlxsw_sp,
+			   struct mlxsw_sp_acl_atcam *atcam);
+void mlxsw_sp_acl_erps_fini(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam);
+
 #endif
-- 
cgit v1.2.3


From c19df1d88d83f42d916cfd39230730b3b8c719a9 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:56 +0300
Subject: mlxsw: spectrum_acl: Enable C-TCAM only mode in eRP core

Currently, no calls are performed into the eRP core, but in order to
make review easier we would like to gradually add these calls.

Have the eRP core initialize a region's master mask to all ones and
allow it to use an empty eRP table. This directs the lookup to the
C-TCAM and allows the C-TCAM only mode to continue working.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 960f29140b43..86600c780c95 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -879,7 +879,7 @@ mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion)
 	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
 	char pererp_pl[MLXSW_REG_PERERP_LEN];
 
-	mlxsw_reg_pererp_pack(pererp_pl, aregion->region->id, false, false, 0,
+	mlxsw_reg_pererp_pack(pererp_pl, aregion->region->id, true, true, 0,
 			      0, 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
 }
@@ -894,12 +894,16 @@ int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion)
 		return PTR_ERR(erp_table);
 	aregion->erp_table = erp_table;
 
-	/* Initialize the region's master mask to all zeroes */
+	/* Initialize the region's master mask to all ones for C-TCAM
+	 * only mode
+	 */
 	err = mlxsw_sp_acl_erp_master_mask_init(aregion);
 	if (err)
 		goto err_erp_master_mask_init;
 
-	/* Initialize the region to not use the eRP table */
+	/* Initialize the region to use the eRP table and enable C-TCAM
+	 * lookup
+	 */
 	err = mlxsw_sp_acl_erp_region_param_init(aregion);
 	if (err)
 		goto err_erp_region_param_init;
-- 
cgit v1.2.3


From b17b113e0c38e94c2f8c0763926c6a2168293201 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:57 +0300
Subject: mlxsw: spectrum_acl: Add support for C-TCAM eRPs

The number of eRPs that can be used by a single A-TCAM region is limited
to 16. When more eRPs are needed, an ordinary circuit TCAM (C-TCAM) can
be used to hold the extra eRPs.

Unlike the A-TCAM, only a single (last) lookup is performed in the
C-TCAM and not a lookup per-eRP. However, modeling the C-TCAM as extra
eRPs will allow us to easily introduce support for pruning in a
follow-up patch set and is also logically correct.

The following diagram depicts the relation between both TCAMs:
                                                                 C-TCAM
+-------------------+               +--------------------+    +-----------+
|                   |               |                    |    |           |
|  eRP #1 (A-TCAM)  +----> ... +----+  eRP #16 (A-TCAM)  +----+  eRP #17  |
|                   |               |                    |    |    ...    |
+-------------------+               +--------------------+    |  eRP #N   |
                                                              |           |
                                                              +-----------+
Lookup order is from left to right.

Extend the eRP core APIs with a C-TCAM parameter which indicates whether
the requested eRP is to be used with the C-TCAM or not.

Since the C-TCAM is only meant to absorb rules that can't fit in the
A-TCAM due to exceeded number of eRPs or key collision, an error is
returned when a C-TCAM eRP needs to be created when the eRP state
machine is in its initial state (i.e., 'no masks'). This should only
happen in the face of very unlikely errors when trying to push rules
into the A-TCAM.

In order not to perform unnecessary lookups, the eRP core will only
enable a C-TCAM lookup for a given region if it knows there are C-TCAM
eRPs present.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 202 +++++++++++++++++++--
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |   2 +-
 2 files changed, 191 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 86600c780c95..e26efa451d4a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -60,6 +60,7 @@ struct mlxsw_sp_acl_erp_core {
 
 struct mlxsw_sp_acl_erp_key {
 	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN];
+	bool ctcam;
 };
 
 struct mlxsw_sp_acl_erp {
@@ -90,6 +91,7 @@ struct mlxsw_sp_acl_erp_table {
 	unsigned long base_index;
 	unsigned int num_atcam_erps;
 	unsigned int num_max_atcam_erps;
+	unsigned int num_ctcam_erps;
 };
 
 static const struct rhashtable_params mlxsw_sp_acl_erp_ht_params = {
@@ -448,13 +450,14 @@ static void mlxsw_sp_acl_erp_table_erp_del(struct mlxsw_sp_acl_erp *erp)
 }
 
 static int
-mlxsw_sp_acl_erp_table_enable(struct mlxsw_sp_acl_erp_table *erp_table)
+mlxsw_sp_acl_erp_table_enable(struct mlxsw_sp_acl_erp_table *erp_table,
+			      bool ctcam_le)
 {
 	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
 	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
 	char pererp_pl[MLXSW_REG_PERERP_LEN];
 
-	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, true, 0,
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0,
 			      erp_table->base_index, 0);
 	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
 					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
@@ -471,11 +474,12 @@ mlxsw_sp_acl_erp_table_disable(struct mlxsw_sp_acl_erp_table *erp_table)
 	struct mlxsw_sp_acl_erp *master_rp;
 
 	master_rp = mlxsw_sp_acl_erp_table_master_rp(erp_table);
-	if (!master_rp)
-		return;
-
+	/* It is possible we do not have a master RP when we disable the
+	 * table when there are no rules in the A-TCAM and the last C-TCAM
+	 * rule is deleted
+	 */
 	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, false, 0, 0,
-			      master_rp->id);
+			      master_rp ? master_rp->id : 0);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
 }
 
@@ -506,6 +510,7 @@ mlxsw_sp_acl_erp_table_expand(struct mlxsw_sp_acl_erp_table *erp_table)
 	unsigned int num_erps, old_num_erps = erp_table->num_max_atcam_erps;
 	struct mlxsw_sp_acl_erp_core *erp_core = erp_table->erp_core;
 	unsigned long old_base_index = erp_table->base_index;
+	bool ctcam_le = erp_table->num_ctcam_erps > 0;
 	int err;
 
 	if (erp_table->num_atcam_erps < erp_table->num_max_atcam_erps)
@@ -526,7 +531,7 @@ mlxsw_sp_acl_erp_table_expand(struct mlxsw_sp_acl_erp_table *erp_table)
 	if (err)
 		goto err_table_relocate;
 
-	err = mlxsw_sp_acl_erp_table_enable(erp_table);
+	err = mlxsw_sp_acl_erp_table_enable(erp_table, ctcam_le);
 	if (err)
 		goto err_table_enable;
 
@@ -579,7 +584,7 @@ mlxsw_sp_acl_erp_region_table_trans(struct mlxsw_sp_acl_erp_table *erp_table)
 	if (err)
 		goto err_table_master_rp_add;
 
-	err = mlxsw_sp_acl_erp_table_enable(erp_table);
+	err = mlxsw_sp_acl_erp_table_enable(erp_table, false);
 	if (err)
 		goto err_table_enable;
 
@@ -619,9 +624,10 @@ mlxsw_sp_acl_erp_region_erp_add(struct mlxsw_sp_acl_erp_table *erp_table,
 {
 	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
 	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	bool ctcam_le = erp_table->num_ctcam_erps > 0;
 	char pererp_pl[MLXSW_REG_PERERP_LEN];
 
-	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, true, 0,
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0,
 			      erp_table->base_index, 0);
 	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
 					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
@@ -635,9 +641,10 @@ static void mlxsw_sp_acl_erp_region_erp_del(struct mlxsw_sp_acl_erp *erp)
 	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
 	struct mlxsw_sp_acl_tcam_region *region = erp_table->aregion->region;
 	struct mlxsw_sp *mlxsw_sp = erp_table->erp_core->mlxsw_sp;
+	bool ctcam_le = erp_table->num_ctcam_erps > 0;
 	char pererp_pl[MLXSW_REG_PERERP_LEN];
 
-	mlxsw_reg_pererp_pack(pererp_pl, region->id, false, true, 0,
+	mlxsw_reg_pererp_pack(pererp_pl, region->id, ctcam_le, true, 0,
 			      erp_table->base_index, 0);
 	mlxsw_reg_pererp_erp_vector_pack(pererp_pl, erp_table->erp_index_bitmap,
 					 MLXSW_SP_ACL_ERP_MAX_PER_REGION);
@@ -646,6 +653,161 @@ static void mlxsw_sp_acl_erp_region_erp_del(struct mlxsw_sp_acl_erp *erp)
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
 }
 
+static int
+mlxsw_sp_acl_erp_region_ctcam_enable(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	/* No need to re-enable lookup in the C-TCAM */
+	if (erp_table->num_ctcam_erps > 1)
+		return 0;
+
+	return mlxsw_sp_acl_erp_table_enable(erp_table, true);
+}
+
+static void
+mlxsw_sp_acl_erp_region_ctcam_disable(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	/* Only disable C-TCAM lookup when last C-TCAM eRP is deleted */
+	if (erp_table->num_ctcam_erps > 1)
+		return;
+
+	mlxsw_sp_acl_erp_table_enable(erp_table, false);
+}
+
+static void
+mlxsw_sp_acl_erp_ctcam_table_ops_set(struct mlxsw_sp_acl_erp_table *erp_table)
+{
+	switch (erp_table->num_atcam_erps) {
+	case 2:
+		/* Keep using the eRP table, but correctly set the
+		 * operations pointer so that when an A-TCAM eRP is
+		 * deleted we will transition to use the master mask
+		 */
+		erp_table->ops = &erp_two_masks_ops;
+		break;
+	case 1:
+		/* We only kept the eRP table because we had C-TCAM
+		 * eRPs in use. Now that the last C-TCAM eRP is gone we
+		 * can stop using the table and transition to use the
+		 * master mask
+		 */
+		mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+		erp_table->ops = &erp_single_mask_ops;
+		break;
+	case 0:
+		/* There are no more eRPs of any kind used by the region
+		 * so free its eRP table and transition to initial state
+		 */
+		mlxsw_sp_acl_erp_table_disable(erp_table);
+		mlxsw_sp_acl_erp_table_free(erp_table->erp_core,
+					    erp_table->num_max_atcam_erps,
+					    erp_table->aregion->type,
+					    erp_table->base_index);
+		erp_table->ops = &erp_no_mask_ops;
+		break;
+	default:
+		break;
+	}
+}
+
+static struct mlxsw_sp_acl_erp *
+__mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				     struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	erp = kzalloc(sizeof(*erp), GFP_KERNEL);
+	if (!erp)
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(&erp->key, key, sizeof(*key));
+	bitmap_from_arr32(erp->mask_bitmap, (u32 *) key->mask,
+			  MLXSW_SP_ACL_TCAM_MASK_LEN);
+	refcount_set(&erp->refcnt, 1);
+	erp_table->num_ctcam_erps++;
+	erp->erp_table = erp_table;
+
+	err = mlxsw_sp_acl_erp_master_mask_set(erp_table, erp);
+	if (err)
+		goto err_master_mask_set;
+
+	err = rhashtable_insert_fast(&erp_table->erp_ht, &erp->ht_node,
+				     mlxsw_sp_acl_erp_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	err = mlxsw_sp_acl_erp_region_ctcam_enable(erp_table);
+	if (err)
+		goto err_erp_region_ctcam_enable;
+
+	/* When C-TCAM is used, the eRP table must be used */
+	erp_table->ops = &erp_multiple_masks_ops;
+
+	return erp;
+
+err_erp_region_ctcam_enable:
+	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
+			       mlxsw_sp_acl_erp_ht_params);
+err_rhashtable_insert:
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+err_master_mask_set:
+	erp_table->num_ctcam_erps--;
+	kfree(erp);
+	return ERR_PTR(err);
+}
+
+static struct mlxsw_sp_acl_erp *
+mlxsw_sp_acl_erp_ctcam_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
+				   struct mlxsw_sp_acl_erp_key *key)
+{
+	struct mlxsw_sp_acl_erp *erp;
+	int err;
+
+	/* There is a special situation where we need to spill rules
+	 * into the C-TCAM, yet the region is still using a master
+	 * mask and thus not performing a lookup in the C-TCAM. This
+	 * can happen when two rules that only differ in priority - and
+	 * thus sharing the same key - are programmed. In this case
+	 * we transition the region to use an eRP table
+	 */
+	err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
+	if (err)
+		return ERR_PTR(err);
+
+	erp = __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+	if (IS_ERR(erp)) {
+		err = PTR_ERR(erp);
+		goto err_erp_create;
+	}
+
+	return erp;
+
+err_erp_create:
+	mlxsw_sp_acl_erp_region_master_mask_trans(erp_table);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_erp_ctcam_mask_destroy(struct mlxsw_sp_acl_erp *erp)
+{
+	struct mlxsw_sp_acl_erp_table *erp_table = erp->erp_table;
+
+	mlxsw_sp_acl_erp_region_ctcam_disable(erp_table);
+	rhashtable_remove_fast(&erp_table->erp_ht, &erp->ht_node,
+			       mlxsw_sp_acl_erp_ht_params);
+	mlxsw_sp_acl_erp_master_mask_clear(erp_table, erp);
+	erp_table->num_ctcam_erps--;
+	kfree(erp);
+
+	/* Once the last C-TCAM eRP was destroyed, the state we
+	 * transition to depends on the number of A-TCAM eRPs currently
+	 * in use
+	 */
+	if (erp_table->num_ctcam_erps > 0)
+		return;
+	mlxsw_sp_acl_erp_ctcam_table_ops_set(erp_table);
+}
+
 static struct mlxsw_sp_acl_erp *
 mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 			     struct mlxsw_sp_acl_erp_key *key)
@@ -653,6 +815,9 @@ mlxsw_sp_acl_erp_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	struct mlxsw_sp_acl_erp *erp;
 	int err;
 
+	if (key->ctcam)
+		return __mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+
 	/* Expand the eRP table for the new eRP, if needed */
 	err = mlxsw_sp_acl_erp_table_expand(erp_table);
 	if (err)
@@ -691,12 +856,15 @@ static void
 mlxsw_sp_acl_erp_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
 			      struct mlxsw_sp_acl_erp *erp)
 {
+	if (erp->key.ctcam)
+		return mlxsw_sp_acl_erp_ctcam_mask_destroy(erp);
+
 	mlxsw_sp_acl_erp_region_erp_del(erp);
 	mlxsw_sp_acl_erp_table_erp_del(erp);
 	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
 	mlxsw_sp_acl_erp_generic_destroy(erp);
 
-	if (erp_table->num_atcam_erps == 2)
+	if (erp_table->num_atcam_erps == 2 && erp_table->num_ctcam_erps == 0)
 		erp_table->ops = &erp_two_masks_ops;
 }
 
@@ -707,6 +875,9 @@ mlxsw_sp_acl_erp_second_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 	struct mlxsw_sp_acl_erp *erp;
 	int err;
 
+	if (key->ctcam)
+		return mlxsw_sp_acl_erp_ctcam_mask_create(erp_table, key);
+
 	/* Transition to use eRP table instead of master mask */
 	err = mlxsw_sp_acl_erp_region_table_trans(erp_table);
 	if (err)
@@ -749,6 +920,9 @@ static void
 mlxsw_sp_acl_erp_second_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
 				     struct mlxsw_sp_acl_erp *erp)
 {
+	if (erp->key.ctcam)
+		return mlxsw_sp_acl_erp_ctcam_mask_destroy(erp);
+
 	mlxsw_sp_acl_erp_region_erp_del(erp);
 	mlxsw_sp_acl_erp_table_erp_del(erp);
 	mlxsw_sp_acl_erp_index_put(erp_table, erp->index);
@@ -765,6 +939,9 @@ mlxsw_sp_acl_erp_first_mask_create(struct mlxsw_sp_acl_erp_table *erp_table,
 {
 	struct mlxsw_sp_acl_erp *erp;
 
+	if (key->ctcam)
+		return ERR_PTR(-EINVAL);
+
 	erp = mlxsw_sp_acl_erp_generic_create(erp_table, key);
 	if (IS_ERR(erp))
 		return erp;
@@ -791,7 +968,7 @@ mlxsw_sp_acl_erp_no_mask_destroy(struct mlxsw_sp_acl_erp_table *erp_table,
 
 struct mlxsw_sp_acl_erp *
 mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
-		     const char *mask)
+		     const char *mask, bool ctcam)
 {
 	struct mlxsw_sp_acl_erp_table *erp_table = aregion->erp_table;
 	struct mlxsw_sp_acl_erp_key key;
@@ -803,6 +980,7 @@ mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
 	ASSERT_RTNL();
 
 	memcpy(key.mask, mask, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
+	key.ctcam = ctcam;
 	erp = rhashtable_lookup_fast(&erp_table->erp_ht, &key,
 				     mlxsw_sp_acl_erp_ht_params);
 	if (erp) {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index af21f7c6c6df..70094936ca43 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -179,7 +179,7 @@ struct mlxsw_sp_acl_erp;
 u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp);
 struct mlxsw_sp_acl_erp *
 mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
-		     const char *mask);
+		     const char *mask, bool ctcam);
 void mlxsw_sp_acl_erp_put(struct mlxsw_sp_acl_atcam_region *aregion,
 			  struct mlxsw_sp_acl_erp *erp);
 int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion);
-- 
cgit v1.2.3


From befc7747df2071845ae2c3b97c759a4df032ae5e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:58 +0300
Subject: mlxsw: spectrum_acl: Extend Spectrum-2 region struct

In a similar fashion to Spectrum-1's region struct, Spectrum-2's struct
needs to store a pointer to the common region struct.

The pointer will be used in follow-up patches that implement rules
insertion and deletion.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index d7f1fb35ea2a..33787b154e74 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -45,6 +45,7 @@ struct mlxsw_sp2_acl_tcam {
 
 struct mlxsw_sp2_acl_tcam_region {
 	struct mlxsw_sp_acl_ctcam_region cregion;
+	struct mlxsw_sp_acl_tcam_region *region;
 };
 
 struct mlxsw_sp2_acl_tcam_chunk {
@@ -127,6 +128,8 @@ mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
 	int err;
 
+	region->region = _region;
+
 	err = mlxsw_sp_acl_atcam_region_init(mlxsw_sp, _region);
 	if (err)
 		return err;
-- 
cgit v1.2.3


From ca49544ed6ace7a1aee942a9f8e2553f9b1ddf2b Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:23:59 +0300
Subject: mlxsw: spectrum_acl: Allow encoding a partial key

When working with 12 key blocks in the A-TCAM, rules are split into two
records, which constitute two lookups. The two records are linked using
a "large entry key ID". The ID is assigned to key blocks 6 to 11 and
resolved during the first lookup. The second lookup is performed using
the ID and the remaining key blocks.

Allow encoding a partial key so that it can be later used to check if an
ID can be reused.

This is done by adding two arguments to the existing encode function
that specify the range of the block indexes we would like to encode. The
key and mask arguments become optional, as we will not need to encode
both of them all the time.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c | 10 ++++++----
 drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c |  5 ++++-
 3 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index 5f8485c7640e..9649b4d9349a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -457,7 +457,7 @@ mlxsw_sp_afk_encode_one(const struct mlxsw_afk_element_inst *elinst,
 void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask)
+		      char *key, char *mask, int block_start, int block_end)
 {
 	char block_mask[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
 	char block_key[MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE];
@@ -465,7 +465,7 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 	enum mlxsw_afk_element element;
 	int block_index, i;
 
-	for (i = 0; i < key_info->blocks_count; i++) {
+	for (i = block_start; i <= block_end; i++) {
 		memset(block_key, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
 		memset(block_mask, 0, MLXSW_SP_AFK_KEY_BLOCK_MAX_SIZE);
 
@@ -482,8 +482,10 @@ void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 						values->storage.mask);
 		}
 
-		mlxsw_afk->ops->encode_block(block_key, i, key);
-		mlxsw_afk->ops->encode_block(block_mask, i, mask);
+		if (key)
+			mlxsw_afk->ops->encode_block(block_key, i, key);
+		if (mask)
+			mlxsw_afk->ops->encode_block(block_mask, i, mask);
 	}
 }
 EXPORT_SYMBOL(mlxsw_afk_encode);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 2ffde915349b..18d9bfed6001 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -259,6 +259,6 @@ void mlxsw_afk_values_add_buf(struct mlxsw_afk_element_values *values,
 void mlxsw_afk_encode(struct mlxsw_afk *mlxsw_afk,
 		      struct mlxsw_afk_key_info *key_info,
 		      struct mlxsw_afk_element_values *values,
-		      char *key, char *mask);
+		      char *key, char *mask, int block_start, int block_end);
 
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index ef0d4c0a5a1f..11b19272ab13 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -76,6 +76,7 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 {
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
+	unsigned int blocks_count;
 	char *act_set;
 	u32 priority;
 	char *mask;
@@ -91,7 +92,9 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 			     region->tcam_region_info, offset, priority);
 	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
 	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
-	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask);
+	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask, 0,
+			 blocks_count - 1);
 
 	/* Only the first action set belongs here, the rest is in KVD */
 	act_set = mlxsw_afa_block_first_set(rulei->act_block);
-- 
cgit v1.2.3


From 174c0adb69a56bf098d9eb50cd3a78ec14657817 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:24:00 +0300
Subject: mlxsw: spectrum_acl: Add A-TCAM initialization

Initialize the A-TCAM as part of the driver's initialization routine.

Specifically, initialize the eRP tables so that A-TCAM regions will be
able to perform allocations of eRP tables upon rule insertion in
subsequent patches.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c |  7 +++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c | 12 ++++++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h  |  4 ++++
 3 files changed, 23 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 33787b154e74..2442decd0652 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -39,6 +39,7 @@
 #include "core_acl_flex_actions.h"
 
 struct mlxsw_sp2_acl_tcam {
+	struct mlxsw_sp_acl_atcam atcam;
 	u32 kvdl_index;
 	unsigned int kvdl_count;
 };
@@ -100,9 +101,14 @@ static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
 	if (err)
 		goto err_pgcr_write;
 
+	err = mlxsw_sp_acl_atcam_init(mlxsw_sp, &tcam->atcam);
+	if (err)
+		goto err_atcam_init;
+
 	mlxsw_afa_block_destroy(afa_block);
 	return 0;
 
+err_atcam_init:
 err_pgcr_write:
 err_pefa_write:
 err_afa_block_continue:
@@ -117,6 +123,7 @@ static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
 {
 	struct mlxsw_sp2_acl_tcam *tcam = priv;
 
+	mlxsw_sp_acl_atcam_fini(mlxsw_sp, &tcam->atcam);
 	mlxsw_sp_kvdl_free(mlxsw_sp, MLXSW_SP_KVDL_ENTRY_TYPE_ACTSET,
 			   tcam->kvdl_count, tcam->kvdl_index);
 }
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index a27d3b0f9fcb..89c78c62e7e5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -93,3 +93,15 @@ int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 
 	return 0;
 }
+
+int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam)
+{
+	return mlxsw_sp_acl_erps_init(mlxsw_sp, atcam);
+}
+
+void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_atcam *atcam)
+{
+	mlxsw_sp_acl_erps_fini(mlxsw_sp, atcam);
+}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 70094936ca43..ac6bdffd99a7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -173,6 +173,10 @@ int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 					u16 region_id);
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_tcam_region *region);
+int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
+			    struct mlxsw_sp_acl_atcam *atcam);
+void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
+			     struct mlxsw_sp_acl_atcam *atcam);
 
 struct mlxsw_sp_acl_erp;
 
-- 
cgit v1.2.3


From 57e56d369914996ed81581da04af7b04a256a20a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:24:01 +0300
Subject: mlxsw: spectrum_acl: Encapsulate C-TCAM region in A-TCAM region

In Spectrum-2 the C-TCAM is only used for rules that can't fit in the
A-TCAM due to a limited number of masks per A-TCAM region.

In addition, rules inserted into the C-TCAM may affect rules residing in
the A-TCAM, by clearing their C-TCAM prune bit.

The two regions are thus closely related and can be thought of as if the
C-TCAM region is encapsulated in the A-TCAM one.

Change the data structures to reflect that before introducing A-TCAM
support and make C-TCAM region initialization part of the A-TCAM region
initialization sequence.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c | 16 ++++++----------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c |  8 +++++++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h  |  3 +++
 3 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 2442decd0652..7e392529a896 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -45,7 +45,7 @@ struct mlxsw_sp2_acl_tcam {
 };
 
 struct mlxsw_sp2_acl_tcam_region {
-	struct mlxsw_sp_acl_ctcam_region cregion;
+	struct mlxsw_sp_acl_atcam_region aregion;
 	struct mlxsw_sp_acl_tcam_region *region;
 };
 
@@ -133,14 +133,10 @@ mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 			       struct mlxsw_sp_acl_tcam_region *_region)
 {
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
-	int err;
 
 	region->region = _region;
 
-	err = mlxsw_sp_acl_atcam_region_init(mlxsw_sp, _region);
-	if (err)
-		return err;
-	return mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &region->cregion,
+	return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &region->aregion,
 					      _region);
 }
 
@@ -149,7 +145,7 @@ mlxsw_sp2_acl_tcam_region_fini(struct mlxsw_sp *mlxsw_sp, void *region_priv)
 {
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
 
-	mlxsw_sp_acl_ctcam_region_fini(&region->cregion);
+	mlxsw_sp_acl_atcam_region_fini(&region->aregion);
 }
 
 static int
@@ -165,7 +161,7 @@ static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
 	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
 
-	mlxsw_sp_acl_ctcam_chunk_init(&region->cregion, &chunk->cchunk,
+	mlxsw_sp_acl_ctcam_chunk_init(&region->aregion.cregion, &chunk->cchunk,
 				      priority);
 }
 
@@ -186,7 +182,7 @@ static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
 
 	entry->act_block = rulei->act_block;
-	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->cregion,
+	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->aregion.cregion,
 					    &chunk->cchunk, &entry->centry,
 					    rulei, true);
 }
@@ -199,7 +195,7 @@ static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
 	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
 
-	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->cregion,
+	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->aregion.cregion,
 				     &chunk->cchunk, &entry->centry);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 89c78c62e7e5..e45172850ed3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -77,6 +77,7 @@ mlxsw_sp_acl_atcam_region_erp_init(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_atcam_region *aregion,
 				   struct mlxsw_sp_acl_tcam_region *region)
 {
 	int err;
@@ -90,8 +91,13 @@ int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 	err = mlxsw_sp_acl_atcam_region_erp_init(mlxsw_sp, region->id);
 	if (err)
 		return err;
+	return mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
+					      region);
+}
 
-	return 0;
+void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	mlxsw_sp_acl_ctcam_region_fini(&aregion->cregion);
 }
 
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index ac6bdffd99a7..17187e5fc3f2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -163,6 +163,7 @@ struct mlxsw_sp_acl_atcam {
 };
 
 struct mlxsw_sp_acl_atcam_region {
+	struct mlxsw_sp_acl_ctcam_region cregion;
 	struct mlxsw_sp_acl_tcam_region *region;
 	struct mlxsw_sp_acl_atcam *atcam;
 	enum mlxsw_sp_acl_atcam_region_type type;
@@ -172,7 +173,9 @@ struct mlxsw_sp_acl_atcam_region {
 int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 					u16 region_id);
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_atcam_region *aregion,
 				   struct mlxsw_sp_acl_tcam_region *region);
+void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam);
 void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
-- 
cgit v1.2.3


From f58df510f899e4560c4e2d397f05a53f0d343fc0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:24:02 +0300
Subject: mlxsw: spectrum_acl: Make global TCAM resources available to regions

Each TCAM region currently uses its own resources and there is no
sharing between the different regions.

This is going to change with A-TCAM as each region will need to allocate
an eRP table from the global eRP tables array.

Make the global TCAM resources available to each region by passing the
TCAM private data to the region initialization routine.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h           | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c | 6 ++++--
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c | 1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c  | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h  | 1 +
 6 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 589c63daf085..bc2704193666 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -628,6 +628,7 @@ struct mlxsw_sp_acl_tcam_ops {
 	void (*fini)(struct mlxsw_sp *mlxsw_sp, void *priv);
 	size_t region_priv_size;
 	int (*region_init)(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			   void *tcam_priv,
 			   struct mlxsw_sp_acl_tcam_region *region);
 	void (*region_fini)(struct mlxsw_sp *mlxsw_sp, void *region_priv);
 	int (*region_associate)(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index d339ec43d79c..926483434e99 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -122,6 +122,7 @@ mlxsw_sp1_acl_ctcam_region_catchall_del(struct mlxsw_sp *mlxsw_sp,
 
 static int
 mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			       void *tcam_priv,
 			       struct mlxsw_sp_acl_tcam_region *_region)
 {
 	struct mlxsw_sp1_acl_tcam_region *region = region_priv;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 7e392529a896..bef2329bb233 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -130,14 +130,16 @@ static void mlxsw_sp2_acl_tcam_fini(struct mlxsw_sp *mlxsw_sp, void *priv)
 
 static int
 mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
+			       void *tcam_priv,
 			       struct mlxsw_sp_acl_tcam_region *_region)
 {
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
+	struct mlxsw_sp2_acl_tcam *tcam = tcam_priv;
 
 	region->region = _region;
 
-	return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &region->aregion,
-					      _region);
+	return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam,
+					      &region->aregion, _region);
 }
 
 static void
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index e45172850ed3..abe8194d50f1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -77,6 +77,7 @@ mlxsw_sp_acl_atcam_region_erp_init(struct mlxsw_sp *mlxsw_sp,
 }
 
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_atcam *atcam,
 				   struct mlxsw_sp_acl_atcam_region *aregion,
 				   struct mlxsw_sp_acl_tcam_region *region)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 310fd87895b8..245e2f473c6f 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -577,7 +577,7 @@ mlxsw_sp_acl_tcam_region_create(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_tcam_region_enable;
 
-	err = ops->region_init(mlxsw_sp, region->priv, region);
+	err = ops->region_init(mlxsw_sp, region->priv, tcam->priv, region);
 	if (err)
 		goto err_tcam_region_init;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 17187e5fc3f2..718e96de2860 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -173,6 +173,7 @@ struct mlxsw_sp_acl_atcam_region {
 int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 					u16 region_id);
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+				   struct mlxsw_sp_acl_atcam *atcam,
 				   struct mlxsw_sp_acl_atcam_region *aregion,
 				   struct mlxsw_sp_acl_tcam_region *region);
 void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
-- 
cgit v1.2.3


From 6d240650bcfdba2860ab2691b5fd4352105d95a0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:24:03 +0300
Subject: mlxsw: spectrum_acl: Add A-TCAM region initialization

Before we start using the A-TCAM we need to make sure the region is
properly initialized.

This includes the setting of its type (which affects the size of its eRP
table, for example) and its registration with the eRP core.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   | 55 +++++++++++++---------
 1 file changed, 33 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index abe8194d50f1..50b4576b4921 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -57,23 +57,27 @@ int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(perar), perar_pl);
 }
 
-static int mlxsw_sp_acl_atcam_region_param_init(struct mlxsw_sp *mlxsw_sp,
-						u16 region_id)
+static void
+mlxsw_sp_acl_atcam_region_type_init(struct mlxsw_sp_acl_atcam_region *aregion)
 {
-	char percr_pl[MLXSW_REG_PERCR_LEN];
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	enum mlxsw_sp_acl_atcam_region_type region_type;
+	unsigned int blocks_count;
 
-	mlxsw_reg_percr_pack(percr_pl, region_id);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl);
-}
-
-static int
-mlxsw_sp_acl_atcam_region_erp_init(struct mlxsw_sp *mlxsw_sp,
-				   u16 region_id)
-{
-	char pererp_pl[MLXSW_REG_PERERP_LEN];
+	/* We already know the blocks count can not exceed the maximum
+	 * blocks count.
+	 */
+	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
+	if (blocks_count <= 2)
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB;
+	else if (blocks_count <= 4)
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB;
+	else if (blocks_count <= 8)
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB;
+	else
+		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB;
 
-	mlxsw_reg_pererp_pack(pererp_pl, region_id, true, true, 0, 0, 0);
-	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
+	aregion->type = region_type;
 }
 
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
@@ -83,22 +87,29 @@ int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 {
 	int err;
 
-	err = mlxsw_sp_acl_atcam_region_associate(mlxsw_sp, region->id);
-	if (err)
-		return err;
-	err = mlxsw_sp_acl_atcam_region_param_init(mlxsw_sp, region->id);
+	aregion->region = region;
+	aregion->atcam = atcam;
+	mlxsw_sp_acl_atcam_region_type_init(aregion);
+
+	err = mlxsw_sp_acl_erp_region_init(aregion);
 	if (err)
 		return err;
-	err = mlxsw_sp_acl_atcam_region_erp_init(mlxsw_sp, region->id);
+	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
+					     region);
 	if (err)
-		return err;
-	return mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
-					      region);
+		goto err_ctcam_region_init;
+
+	return 0;
+
+err_ctcam_region_init:
+	mlxsw_sp_acl_erp_region_fini(aregion);
+	return err;
 }
 
 void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
 {
 	mlxsw_sp_acl_ctcam_region_fini(&aregion->cregion);
+	mlxsw_sp_acl_erp_region_fini(aregion);
 }
 
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
-- 
cgit v1.2.3


From a20ff8eb3f15c8adcae60fc467697b442f6267eb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:24:04 +0300
Subject: mlxsw: spectrum_acl: Pass C-TCAM region and entry to insert function

When A-TCAM will be used together with C-TCAM, the C-TCAM code will need
to call into the eRP core in order to get an eRP for an inserted entry.

The eRP core takes an A-TCAM region as one of its arguments, so pass the
C-TCAM region to the insertion function which will later allow us to
derive the A-TCAM region, given it contains the C-TCAM one.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c    | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index 11b19272ab13..7ff31247cac7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -69,11 +69,12 @@ mlxsw_sp_acl_ctcam_region_move(struct mlxsw_sp *mlxsw_sp,
 
 static int
 mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
-				       struct mlxsw_sp_acl_tcam_region *region,
-				       unsigned int offset,
+				       struct mlxsw_sp_acl_ctcam_region *cregion,
+				       struct mlxsw_sp_acl_ctcam_entry *centry,
 				       struct mlxsw_sp_acl_rule_info *rulei,
 				       bool fillup_priority)
 {
+	struct mlxsw_sp_acl_tcam_region *region = cregion->region;
 	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
 	unsigned int blocks_count;
@@ -89,7 +90,8 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 		return err;
 
 	mlxsw_reg_ptce2_pack(ptce2_pl, true, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset, priority);
+			     region->tcam_region_info,
+			     centry->parman_item.index, priority);
 	key = mlxsw_reg_ptce2_flex_key_blocks_data(ptce2_pl);
 	mask = mlxsw_reg_ptce2_mask_data(ptce2_pl);
 	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
@@ -105,13 +107,14 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 
 static void
 mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
-				       struct mlxsw_sp_acl_tcam_region *region,
-				       unsigned int offset)
+				       struct mlxsw_sp_acl_ctcam_region *cregion,
+				       struct mlxsw_sp_acl_ctcam_entry *centry)
 {
 	char ptce2_pl[MLXSW_REG_PTCE2_LEN];
 
 	mlxsw_reg_ptce2_pack(ptce2_pl, false, MLXSW_REG_PTCE2_OP_WRITE_WRITE,
-			     region->tcam_region_info, offset, 0);
+			     cregion->region->tcam_region_info,
+			     centry->parman_item.index, 0);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
 }
 
@@ -193,8 +196,7 @@ int mlxsw_sp_acl_ctcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		return err;
 
-	err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion->region,
-						     centry->parman_item.index,
+	err = mlxsw_sp_acl_ctcam_region_entry_insert(mlxsw_sp, cregion, centry,
 						     rulei, fillup_priority);
 	if (err)
 		goto err_rule_insert;
@@ -211,8 +213,7 @@ void mlxsw_sp_acl_ctcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 				  struct mlxsw_sp_acl_ctcam_chunk *cchunk,
 				  struct mlxsw_sp_acl_ctcam_entry *centry)
 {
-	mlxsw_sp_acl_ctcam_region_entry_remove(mlxsw_sp, cregion->region,
-					       centry->parman_item.index);
+	mlxsw_sp_acl_ctcam_region_entry_remove(mlxsw_sp, cregion, centry);
 	parman_item_remove(cregion->parman, &cchunk->parman_prio,
 			   &centry->parman_item);
 }
-- 
cgit v1.2.3


From a8758b67bf37ceb50e5b8c2b9138231c76461d20 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:24:05 +0300
Subject: mlxsw: spectrum_acl: Add A-TCAM rule insertion and deletion

Implement rule insertion and deletion into the A-TCAM before we flip the
driver to start using the A-TCAM.

Rule insertion into the A-TCAM is very similar to C-TCAM, but there are
subtle differences between regions of different sizes (i.e., different
number of key blocks).

Specifically, as explained in "mlxsw: spectrum_acl: Allow encoding a
partial key", in 12 key blocks regions a rule is split into two and the
two halves of the rule are linked using a "large entry key ID".

Such differences are abstracted away by using different region
operations per region type.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c   |   8 +-
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   | 443 ++++++++++++++++++++-
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c |   5 +
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    |  34 ++
 4 files changed, 485 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index bef2329bb233..aef366148cc3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -54,7 +54,7 @@ struct mlxsw_sp2_acl_tcam_chunk {
 };
 
 struct mlxsw_sp2_acl_tcam_entry {
-	struct mlxsw_sp_acl_ctcam_entry centry;
+	struct mlxsw_sp_acl_atcam_entry aentry;
 	struct mlxsw_afa_block *act_block;
 };
 
@@ -185,8 +185,8 @@ static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 
 	entry->act_block = rulei->act_block;
 	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->aregion.cregion,
-					    &chunk->cchunk, &entry->centry,
-					    rulei, true);
+					    &chunk->cchunk,
+					    &entry->aentry.centry, rulei, true);
 }
 
 static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
@@ -198,7 +198,7 @@ static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
 
 	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->aregion.cregion,
-				     &chunk->cchunk, &entry->centry);
+				     &chunk->cchunk, &entry->aentry.centry);
 }
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 50b4576b4921..d551f0431248 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -34,12 +34,275 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/err.h>
 #include <linux/errno.h>
+#include <linux/gfp.h>
+#include <linux/refcount.h>
+#include <linux/rhashtable.h>
 
 #include "reg.h"
 #include "core.h"
 #include "spectrum.h"
 #include "spectrum_acl_tcam.h"
+#include "core_acl_flex_keys.h"
+
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START	6
+#define MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END	11
+
+struct mlxsw_sp_acl_atcam_lkey_id_ht_key {
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* MSB blocks */
+	u8 erp_id;
+};
+
+struct mlxsw_sp_acl_atcam_lkey_id {
+	struct rhash_head ht_node;
+	struct mlxsw_sp_acl_atcam_lkey_id_ht_key ht_key;
+	refcount_t refcnt;
+	u32 id;
+};
+
+struct mlxsw_sp_acl_atcam_region_ops {
+	int (*init)(struct mlxsw_sp_acl_atcam_region *aregion);
+	void (*fini)(struct mlxsw_sp_acl_atcam_region *aregion);
+	struct mlxsw_sp_acl_atcam_lkey_id *
+		(*lkey_id_get)(struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_rule_info *rulei, u8 erp_id);
+	void (*lkey_id_put)(struct mlxsw_sp_acl_atcam_region *aregion,
+			    struct mlxsw_sp_acl_atcam_lkey_id *lkey_id);
+};
+
+struct mlxsw_sp_acl_atcam_region_generic {
+	struct mlxsw_sp_acl_atcam_lkey_id dummy_lkey_id;
+};
+
+struct mlxsw_sp_acl_atcam_region_12kb {
+	struct rhashtable lkey_ht;
+	unsigned int max_lkey_id;
+	unsigned long *used_lkey_id;
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_atcam_lkey_id_ht_params = {
+	.key_len = sizeof(struct mlxsw_sp_acl_atcam_lkey_id_ht_key),
+	.key_offset = offsetof(struct mlxsw_sp_acl_atcam_lkey_id, ht_key),
+	.head_offset = offsetof(struct mlxsw_sp_acl_atcam_lkey_id, ht_node),
+};
+
+static const struct rhashtable_params mlxsw_sp_acl_atcam_entries_ht_params = {
+	.key_len = sizeof(struct mlxsw_sp_acl_atcam_entry_ht_key),
+	.key_offset = offsetof(struct mlxsw_sp_acl_atcam_entry, ht_key),
+	.head_offset = offsetof(struct mlxsw_sp_acl_atcam_entry, ht_node),
+};
+
+static bool
+mlxsw_sp_acl_atcam_is_centry(const struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	return mlxsw_sp_acl_erp_is_ctcam_erp(aentry->erp);
+}
+
+static int
+mlxsw_sp_acl_atcam_region_generic_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_atcam_region_generic *region_generic;
+
+	region_generic = kzalloc(sizeof(*region_generic), GFP_KERNEL);
+	if (!region_generic)
+		return -ENOMEM;
+
+	refcount_set(&region_generic->dummy_lkey_id.refcnt, 1);
+	aregion->priv = region_generic;
+
+	return 0;
+}
+
+static void
+mlxsw_sp_acl_atcam_region_generic_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	kfree(aregion->priv);
+}
+
+static struct mlxsw_sp_acl_atcam_lkey_id *
+mlxsw_sp_acl_atcam_generic_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_rule_info *rulei,
+				       u8 erp_id)
+{
+	struct mlxsw_sp_acl_atcam_region_generic *region_generic;
+
+	region_generic = aregion->priv;
+	return &region_generic->dummy_lkey_id;
+}
+
+static void
+mlxsw_sp_acl_atcam_generic_lkey_id_put(struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_atcam_lkey_id *lkey_id)
+{
+}
+
+static const struct mlxsw_sp_acl_atcam_region_ops
+mlxsw_sp_acl_atcam_region_generic_ops = {
+	.init		= mlxsw_sp_acl_atcam_region_generic_init,
+	.fini		= mlxsw_sp_acl_atcam_region_generic_fini,
+	.lkey_id_get	= mlxsw_sp_acl_atcam_generic_lkey_id_get,
+	.lkey_id_put	= mlxsw_sp_acl_atcam_generic_lkey_id_put,
+};
+
+static int
+mlxsw_sp_acl_atcam_region_12kb_init(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb;
+	size_t alloc_size;
+	u64 max_lkey_id;
+	int err;
+
+	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, ACL_MAX_LARGE_KEY_ID))
+		return -EIO;
+
+	max_lkey_id = MLXSW_CORE_RES_GET(mlxsw_sp->core, ACL_MAX_LARGE_KEY_ID);
+	region_12kb = kzalloc(sizeof(*region_12kb), GFP_KERNEL);
+	if (!region_12kb)
+		return -ENOMEM;
+
+	alloc_size = BITS_TO_LONGS(max_lkey_id) * sizeof(unsigned long);
+	region_12kb->used_lkey_id = kzalloc(alloc_size, GFP_KERNEL);
+	if (!region_12kb->used_lkey_id) {
+		err = -ENOMEM;
+		goto err_used_lkey_id_alloc;
+	}
+
+	err = rhashtable_init(&region_12kb->lkey_ht,
+			      &mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	if (err)
+		goto err_rhashtable_init;
+
+	region_12kb->max_lkey_id = max_lkey_id;
+	aregion->priv = region_12kb;
+
+	return 0;
+
+err_rhashtable_init:
+	kfree(region_12kb->used_lkey_id);
+err_used_lkey_id_alloc:
+	kfree(region_12kb);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_atcam_region_12kb_fini(struct mlxsw_sp_acl_atcam_region *aregion)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+
+	rhashtable_destroy(&region_12kb->lkey_ht);
+	kfree(region_12kb->used_lkey_id);
+	kfree(region_12kb);
+}
+
+static struct mlxsw_sp_acl_atcam_lkey_id *
+mlxsw_sp_acl_atcam_lkey_id_create(struct mlxsw_sp_acl_atcam_region *aregion,
+				  struct mlxsw_sp_acl_atcam_lkey_id_ht_key *ht_key)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+	u32 id;
+	int err;
+
+	id = find_first_zero_bit(region_12kb->used_lkey_id,
+				 region_12kb->max_lkey_id);
+	if (id < region_12kb->max_lkey_id)
+		__set_bit(id, region_12kb->used_lkey_id);
+	else
+		return ERR_PTR(-ENOBUFS);
+
+	lkey_id = kzalloc(sizeof(*lkey_id), GFP_KERNEL);
+	if (!lkey_id) {
+		err = -ENOMEM;
+		goto err_lkey_id_alloc;
+	}
+
+	lkey_id->id = id;
+	memcpy(&lkey_id->ht_key, ht_key, sizeof(*ht_key));
+	refcount_set(&lkey_id->refcnt, 1);
+
+	err = rhashtable_insert_fast(&region_12kb->lkey_ht,
+				     &lkey_id->ht_node,
+				     mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	return lkey_id;
+
+err_rhashtable_insert:
+	kfree(lkey_id);
+err_lkey_id_alloc:
+	__clear_bit(id, region_12kb->used_lkey_id);
+	return ERR_PTR(err);
+}
+
+static void
+mlxsw_sp_acl_atcam_lkey_id_destroy(struct mlxsw_sp_acl_atcam_region *aregion,
+				   struct mlxsw_sp_acl_atcam_lkey_id *lkey_id)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+	u32 id = lkey_id->id;
+
+	rhashtable_remove_fast(&region_12kb->lkey_ht, &lkey_id->ht_node,
+			       mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	kfree(lkey_id);
+	__clear_bit(id, region_12kb->used_lkey_id);
+}
+
+static struct mlxsw_sp_acl_atcam_lkey_id *
+mlxsw_sp_acl_atcam_12kb_lkey_id_get(struct mlxsw_sp_acl_atcam_region *aregion,
+				    struct mlxsw_sp_acl_rule_info *rulei,
+				    u8 erp_id)
+{
+	struct mlxsw_sp_acl_atcam_region_12kb *region_12kb = aregion->priv;
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	struct mlxsw_sp_acl_atcam_lkey_id_ht_key ht_key = {{ 0 } };
+	struct mlxsw_sp *mlxsw_sp = region->mlxsw_sp;
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values, ht_key.enc_key,
+			 NULL, MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_START,
+			 MLXSW_SP_ACL_ATCAM_LKEY_ID_BLOCK_END);
+	ht_key.erp_id = erp_id;
+	lkey_id = rhashtable_lookup_fast(&region_12kb->lkey_ht, &ht_key,
+					 mlxsw_sp_acl_atcam_lkey_id_ht_params);
+	if (lkey_id) {
+		refcount_inc(&lkey_id->refcnt);
+		return lkey_id;
+	}
+
+	return mlxsw_sp_acl_atcam_lkey_id_create(aregion, &ht_key);
+}
+
+static void
+mlxsw_sp_acl_atcam_12kb_lkey_id_put(struct mlxsw_sp_acl_atcam_region *aregion,
+				    struct mlxsw_sp_acl_atcam_lkey_id *lkey_id)
+{
+	if (refcount_dec_and_test(&lkey_id->refcnt))
+		mlxsw_sp_acl_atcam_lkey_id_destroy(aregion, lkey_id);
+}
+
+static const struct mlxsw_sp_acl_atcam_region_ops
+mlxsw_sp_acl_atcam_region_12kb_ops = {
+	.init		= mlxsw_sp_acl_atcam_region_12kb_init,
+	.fini		= mlxsw_sp_acl_atcam_region_12kb_fini,
+	.lkey_id_get	= mlxsw_sp_acl_atcam_12kb_lkey_id_get,
+	.lkey_id_put	= mlxsw_sp_acl_atcam_12kb_lkey_id_put,
+};
+
+static const struct mlxsw_sp_acl_atcam_region_ops *
+mlxsw_sp_acl_atcam_region_ops_arr[] = {
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_2KB]	=
+		&mlxsw_sp_acl_atcam_region_generic_ops,
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_4KB]	=
+		&mlxsw_sp_acl_atcam_region_generic_ops,
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_8KB]	=
+		&mlxsw_sp_acl_atcam_region_generic_ops,
+	[MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB]	=
+		&mlxsw_sp_acl_atcam_region_12kb_ops,
+};
 
 int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 					u16 region_id)
@@ -78,6 +341,7 @@ mlxsw_sp_acl_atcam_region_type_init(struct mlxsw_sp_acl_atcam_region *aregion)
 		region_type = MLXSW_SP_ACL_ATCAM_REGION_TYPE_12KB;
 
 	aregion->type = region_type;
+	aregion->ops = mlxsw_sp_acl_atcam_region_ops_arr[region_type];
 }
 
 int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
@@ -91,9 +355,16 @@ int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 	aregion->atcam = atcam;
 	mlxsw_sp_acl_atcam_region_type_init(aregion);
 
-	err = mlxsw_sp_acl_erp_region_init(aregion);
+	err = rhashtable_init(&aregion->entries_ht,
+			      &mlxsw_sp_acl_atcam_entries_ht_params);
 	if (err)
 		return err;
+	err = aregion->ops->init(aregion);
+	if (err)
+		goto err_ops_init;
+	err = mlxsw_sp_acl_erp_region_init(aregion);
+	if (err)
+		goto err_erp_region_init;
 	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
 					     region);
 	if (err)
@@ -103,6 +374,10 @@ int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 
 err_ctcam_region_init:
 	mlxsw_sp_acl_erp_region_fini(aregion);
+err_erp_region_init:
+	aregion->ops->fini(aregion);
+err_ops_init:
+	rhashtable_destroy(&aregion->entries_ht);
 	return err;
 }
 
@@ -110,6 +385,172 @@ void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion)
 {
 	mlxsw_sp_acl_ctcam_region_fini(&aregion->cregion);
 	mlxsw_sp_acl_erp_region_fini(aregion);
+	aregion->ops->fini(aregion);
+	rhashtable_destroy(&aregion->entries_ht);
+}
+
+void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				   struct mlxsw_sp_acl_atcam_chunk *achunk,
+				   unsigned int priority)
+{
+	mlxsw_sp_acl_ctcam_chunk_init(&aregion->cregion, &achunk->cchunk,
+				      priority);
+}
+
+void mlxsw_sp_acl_atcam_chunk_fini(struct mlxsw_sp_acl_atcam_chunk *achunk)
+{
+	mlxsw_sp_acl_ctcam_chunk_fini(&achunk->cchunk);
+}
+
+static int
+mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_atcam_entry *aentry,
+				       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
+	u32 kvdl_index, priority;
+	int err;
+
+	err = mlxsw_sp_acl_tcam_priority_get(mlxsw_sp, rulei, &priority, true);
+	if (err)
+		return err;
+
+	lkey_id = aregion->ops->lkey_id_get(aregion, rulei, erp_id);
+	if (IS_ERR(lkey_id))
+		return PTR_ERR(lkey_id);
+	aentry->lkey_id = lkey_id;
+
+	kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
+	mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
+			     priority, region->tcam_region_info,
+			     aentry->ht_key.enc_key, erp_id,
+			     refcount_read(&lkey_id->refcnt) != 1, lkey_id->id,
+			     kvdl_index);
+	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
+	if (err)
+		goto err_ptce3_write;
+
+	return 0;
+
+err_ptce3_write:
+	aregion->ops->lkey_id_put(aregion, lkey_id);
+	return err;
+}
+
+static void
+mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
+				       struct mlxsw_sp_acl_atcam_region *aregion,
+				       struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id = aentry->lkey_id;
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	u8 erp_id = mlxsw_sp_acl_erp_id(aentry->erp);
+	char ptce3_pl[MLXSW_REG_PTCE3_LEN];
+
+	mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
+			     region->tcam_region_info, aentry->ht_key.enc_key,
+			     erp_id, refcount_read(&lkey_id->refcnt) != 1,
+			     lkey_id->id, 0);
+	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce3), ptce3_pl);
+	aregion->ops->lkey_id_put(aregion, lkey_id);
+}
+
+static int
+__mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_atcam_entry *aentry,
+			       struct mlxsw_sp_acl_rule_info *rulei)
+{
+	struct mlxsw_sp_acl_tcam_region *region = aregion->region;
+	char mask[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN] = { 0 };
+	struct mlxsw_afk *afk = mlxsw_sp_acl_afk(mlxsw_sp->acl);
+	struct mlxsw_sp_acl_erp *erp;
+	unsigned int blocks_count;
+	int err;
+
+	blocks_count = mlxsw_afk_key_info_blocks_count_get(region->key_info);
+	mlxsw_afk_encode(afk, region->key_info, &rulei->values,
+			 aentry->ht_key.enc_key, mask, 0, blocks_count - 1);
+
+	erp = mlxsw_sp_acl_erp_get(aregion, mask, false);
+	if (IS_ERR(erp))
+		return PTR_ERR(erp);
+	aentry->erp = erp;
+	aentry->ht_key.erp_id = mlxsw_sp_acl_erp_id(erp);
+
+	/* We can't insert identical rules into the A-TCAM, so fail and
+	 * let the rule spill into C-TCAM
+	 */
+	err = rhashtable_lookup_insert_fast(&aregion->entries_ht,
+					    &aentry->ht_node,
+					    mlxsw_sp_acl_atcam_entries_ht_params);
+	if (err)
+		goto err_rhashtable_insert;
+
+	err = mlxsw_sp_acl_atcam_region_entry_insert(mlxsw_sp, aregion, aentry,
+						     rulei);
+	if (err)
+		goto err_rule_insert;
+
+	return 0;
+
+err_rule_insert:
+	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
+			       mlxsw_sp_acl_atcam_entries_ht_params);
+err_rhashtable_insert:
+	mlxsw_sp_acl_erp_put(aregion, erp);
+	return err;
+}
+
+static void
+__mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	mlxsw_sp_acl_atcam_region_entry_remove(mlxsw_sp, aregion, aentry);
+	rhashtable_remove_fast(&aregion->entries_ht, &aentry->ht_node,
+			       mlxsw_sp_acl_atcam_entries_ht_params);
+	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+}
+
+int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_atcam_region *aregion,
+				 struct mlxsw_sp_acl_atcam_chunk *achunk,
+				 struct mlxsw_sp_acl_atcam_entry *aentry,
+				 struct mlxsw_sp_acl_rule_info *rulei)
+{
+	int err;
+
+	err = __mlxsw_sp_acl_atcam_entry_add(mlxsw_sp, aregion, aentry, rulei);
+	if (!err)
+		return 0;
+
+	/* It is possible we failed to add the rule to the A-TCAM due to
+	 * exceeded number of masks. Try to spill into C-TCAM.
+	 */
+	err = mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &aregion->cregion,
+					   &achunk->cchunk, &aentry->centry,
+					   rulei, true);
+	if (!err)
+		return 0;
+
+	return err;
+}
+
+void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_atcam_region *aregion,
+				  struct mlxsw_sp_acl_atcam_chunk *achunk,
+				  struct mlxsw_sp_acl_atcam_entry *aentry)
+{
+	if (mlxsw_sp_acl_atcam_is_centry(aentry))
+		mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &aregion->cregion,
+					     &achunk->cchunk, &aentry->centry);
+	else
+		__mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, aregion, aentry);
 }
 
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index e26efa451d4a..bb07723a0577 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -150,6 +150,11 @@ static const struct mlxsw_sp_acl_erp_table_ops erp_no_mask_ops = {
 	.erp_destroy = mlxsw_sp_acl_erp_no_mask_destroy,
 };
 
+bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp)
+{
+	return erp->key.ctcam;
+}
+
 u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp)
 {
 	return erp->id;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 718e96de2860..fb6f9a521ddb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -163,11 +163,31 @@ struct mlxsw_sp_acl_atcam {
 };
 
 struct mlxsw_sp_acl_atcam_region {
+	struct rhashtable entries_ht; /* A-TCAM only */
 	struct mlxsw_sp_acl_ctcam_region cregion;
+	const struct mlxsw_sp_acl_atcam_region_ops *ops;
 	struct mlxsw_sp_acl_tcam_region *region;
 	struct mlxsw_sp_acl_atcam *atcam;
 	enum mlxsw_sp_acl_atcam_region_type type;
 	struct mlxsw_sp_acl_erp_table *erp_table;
+	void *priv;
+};
+
+struct mlxsw_sp_acl_atcam_entry_ht_key {
+	char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key */
+	u8 erp_id;
+};
+
+struct mlxsw_sp_acl_atcam_chunk {
+	struct mlxsw_sp_acl_ctcam_chunk cchunk;
+};
+
+struct mlxsw_sp_acl_atcam_entry {
+	struct rhash_head ht_node;
+	struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
+	struct mlxsw_sp_acl_ctcam_entry centry;
+	struct mlxsw_sp_acl_atcam_lkey_id *lkey_id;
+	struct mlxsw_sp_acl_erp *erp;
 };
 
 int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
@@ -177,6 +197,19 @@ int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 				   struct mlxsw_sp_acl_atcam_region *aregion,
 				   struct mlxsw_sp_acl_tcam_region *region);
 void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
+void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
+				   struct mlxsw_sp_acl_atcam_chunk *achunk,
+				   unsigned int priority);
+void mlxsw_sp_acl_atcam_chunk_fini(struct mlxsw_sp_acl_atcam_chunk *achunk);
+int mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+				 struct mlxsw_sp_acl_atcam_region *aregion,
+				 struct mlxsw_sp_acl_atcam_chunk *achunk,
+				 struct mlxsw_sp_acl_atcam_entry *aentry,
+				 struct mlxsw_sp_acl_rule_info *rulei);
+void mlxsw_sp_acl_atcam_entry_del(struct mlxsw_sp *mlxsw_sp,
+				  struct mlxsw_sp_acl_atcam_region *aregion,
+				  struct mlxsw_sp_acl_atcam_chunk *achunk,
+				  struct mlxsw_sp_acl_atcam_entry *aentry);
 int mlxsw_sp_acl_atcam_init(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_atcam *atcam);
 void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
@@ -184,6 +217,7 @@ void mlxsw_sp_acl_atcam_fini(struct mlxsw_sp *mlxsw_sp,
 
 struct mlxsw_sp_acl_erp;
 
+bool mlxsw_sp_acl_erp_is_ctcam_erp(const struct mlxsw_sp_acl_erp *erp);
 u8 mlxsw_sp_acl_erp_id(const struct mlxsw_sp_acl_erp *erp);
 struct mlxsw_sp_acl_erp *
 mlxsw_sp_acl_erp_get(struct mlxsw_sp_acl_atcam_region *aregion,
-- 
cgit v1.2.3


From a0a777b9409fdb61ec4a752f8f9e88f5916e0a70 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Wed, 25 Jul 2018 09:24:06 +0300
Subject: mlxsw: spectrum_acl: Start using A-TCAM

Now that all the pieces are in place we can start using the A-TCAM
instead of only using the C-TCAM. This allows for much higher scale and
better performance (to be improved further by follow-up patch sets).

Perform the integration with the A-TCAM and the eRP core by reverting
the changes introduced by "mlxsw: spectrum_acl: Enable C-TCAM only mode
in eRP core" and add calls from the C-TCAM code into the eRP core.

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h          |  1 -
 .../ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c   | 23 ++++++++-
 .../ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c   | 58 ++++++++++++++++++----
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   | 12 +++--
 .../ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c   | 14 ++++--
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 13 ++---
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    | 39 ++++++++++++---
 7 files changed, 124 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 5acef249e776..fd2e3dd166d2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -2868,7 +2868,6 @@ static inline void mlxsw_reg_percr_pack(char *payload, u16 region_id)
 	mlxsw_reg_percr_atcam_ignore_prune_set(payload, false);
 	mlxsw_reg_percr_ctcam_ignore_prune_set(payload, false);
 	mlxsw_reg_percr_bf_bypass_set(payload, true);
-	memset(payload + 0x20, 0xff, 96);
 }
 
 /* PERERP - Policy-Engine Region eRP Register
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 926483434e99..5c8956573632 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -58,6 +58,26 @@ struct mlxsw_sp1_acl_tcam_entry {
 	struct mlxsw_sp_acl_ctcam_entry centry;
 };
 
+static int
+mlxsw_sp1_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry,
+					const char *mask)
+{
+	return 0;
+}
+
+static void
+mlxsw_sp1_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+}
+
+static const struct mlxsw_sp_acl_ctcam_region_ops
+mlxsw_sp1_acl_ctcam_region_ops = {
+	.entry_insert = mlxsw_sp1_acl_ctcam_region_entry_insert,
+	.entry_remove = mlxsw_sp1_acl_ctcam_region_entry_remove,
+};
+
 static int mlxsw_sp1_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
 				   struct mlxsw_sp_acl_tcam *tcam)
 {
@@ -129,7 +149,8 @@ mlxsw_sp1_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 	int err;
 
 	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &region->cregion,
-					     _region);
+					     _region,
+					     &mlxsw_sp1_acl_ctcam_region_ops);
 	if (err)
 		return err;
 	err = mlxsw_sp1_acl_ctcam_region_catchall_add(mlxsw_sp, region);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index aef366148cc3..22c876496379 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -50,7 +50,7 @@ struct mlxsw_sp2_acl_tcam_region {
 };
 
 struct mlxsw_sp2_acl_tcam_chunk {
-	struct mlxsw_sp_acl_ctcam_chunk cchunk;
+	struct mlxsw_sp_acl_atcam_chunk achunk;
 };
 
 struct mlxsw_sp2_acl_tcam_entry {
@@ -58,6 +58,45 @@ struct mlxsw_sp2_acl_tcam_entry {
 	struct mlxsw_afa_block *act_block;
 };
 
+static int
+mlxsw_sp2_acl_ctcam_region_entry_insert(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry,
+					const char *mask)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion;
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+	struct mlxsw_sp_acl_erp *erp;
+
+	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
+	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
+
+	erp = mlxsw_sp_acl_erp_get(aregion, mask, true);
+	if (IS_ERR(erp))
+		return PTR_ERR(erp);
+	aentry->erp = erp;
+
+	return 0;
+}
+
+static void
+mlxsw_sp2_acl_ctcam_region_entry_remove(struct mlxsw_sp_acl_ctcam_region *cregion,
+					struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	struct mlxsw_sp_acl_atcam_region *aregion;
+	struct mlxsw_sp_acl_atcam_entry *aentry;
+
+	aregion = mlxsw_sp_acl_tcam_cregion_aregion(cregion);
+	aentry = mlxsw_sp_acl_tcam_centry_aentry(centry);
+
+	mlxsw_sp_acl_erp_put(aregion, aentry->erp);
+}
+
+static const struct mlxsw_sp_acl_ctcam_region_ops
+mlxsw_sp2_acl_ctcam_region_ops = {
+	.entry_insert = mlxsw_sp2_acl_ctcam_region_entry_insert,
+	.entry_remove = mlxsw_sp2_acl_ctcam_region_entry_remove,
+};
+
 static int mlxsw_sp2_acl_tcam_init(struct mlxsw_sp *mlxsw_sp, void *priv,
 				   struct mlxsw_sp_acl_tcam *_tcam)
 {
@@ -139,7 +178,8 @@ mlxsw_sp2_acl_tcam_region_init(struct mlxsw_sp *mlxsw_sp, void *region_priv,
 	region->region = _region;
 
 	return mlxsw_sp_acl_atcam_region_init(mlxsw_sp, &tcam->atcam,
-					      &region->aregion, _region);
+					      &region->aregion, _region,
+					      &mlxsw_sp2_acl_ctcam_region_ops);
 }
 
 static void
@@ -163,7 +203,7 @@ static void mlxsw_sp2_acl_tcam_chunk_init(void *region_priv, void *chunk_priv,
 	struct mlxsw_sp2_acl_tcam_region *region = region_priv;
 	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
 
-	mlxsw_sp_acl_ctcam_chunk_init(&region->aregion.cregion, &chunk->cchunk,
+	mlxsw_sp_acl_atcam_chunk_init(&region->aregion, &chunk->achunk,
 				      priority);
 }
 
@@ -171,7 +211,7 @@ static void mlxsw_sp2_acl_tcam_chunk_fini(void *chunk_priv)
 {
 	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
 
-	mlxsw_sp_acl_ctcam_chunk_fini(&chunk->cchunk);
+	mlxsw_sp_acl_atcam_chunk_fini(&chunk->achunk);
 }
 
 static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
@@ -184,9 +224,9 @@ static int mlxsw_sp2_acl_tcam_entry_add(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
 
 	entry->act_block = rulei->act_block;
-	return mlxsw_sp_acl_ctcam_entry_add(mlxsw_sp, &region->aregion.cregion,
-					    &chunk->cchunk,
-					    &entry->aentry.centry, rulei, true);
+	return mlxsw_sp_acl_atcam_entry_add(mlxsw_sp, &region->aregion,
+					    &chunk->achunk, &entry->aentry,
+					    rulei);
 }
 
 static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
@@ -197,8 +237,8 @@ static void mlxsw_sp2_acl_tcam_entry_del(struct mlxsw_sp *mlxsw_sp,
 	struct mlxsw_sp2_acl_tcam_chunk *chunk = chunk_priv;
 	struct mlxsw_sp2_acl_tcam_entry *entry = entry_priv;
 
-	mlxsw_sp_acl_ctcam_entry_del(mlxsw_sp, &region->aregion.cregion,
-				     &chunk->cchunk, &entry->aentry.centry);
+	mlxsw_sp_acl_atcam_entry_del(mlxsw_sp, &region->aregion, &chunk->achunk,
+				     &entry->aentry);
 }
 
 static int
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index d551f0431248..3a05e0b3f730 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -344,10 +344,12 @@ mlxsw_sp_acl_atcam_region_type_init(struct mlxsw_sp_acl_atcam_region *aregion)
 	aregion->ops = mlxsw_sp_acl_atcam_region_ops_arr[region_type];
 }
 
-int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_acl_atcam *atcam,
-				   struct mlxsw_sp_acl_atcam_region *aregion,
-				   struct mlxsw_sp_acl_tcam_region *region)
+int
+mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam *atcam,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops)
 {
 	int err;
 
@@ -366,7 +368,7 @@ int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
 	if (err)
 		goto err_erp_region_init;
 	err = mlxsw_sp_acl_ctcam_region_init(mlxsw_sp, &aregion->cregion,
-					     region);
+					     region, ops);
 	if (err)
 		goto err_ctcam_region_init;
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index 7ff31247cac7..7440a1189250 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -98,6 +98,10 @@ mlxsw_sp_acl_ctcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_afk_encode(afk, region->key_info, &rulei->values, key, mask, 0,
 			 blocks_count - 1);
 
+	err = cregion->ops->entry_insert(cregion, centry, mask);
+	if (err)
+		return err;
+
 	/* Only the first action set belongs here, the rest is in KVD */
 	act_set = mlxsw_afa_block_first_set(rulei->act_block);
 	mlxsw_reg_ptce2_flex_action_set_memcpy_to(ptce2_pl, act_set);
@@ -116,6 +120,7 @@ mlxsw_sp_acl_ctcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
 			     cregion->region->tcam_region_info,
 			     centry->parman_item.index, 0);
 	mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(ptce2), ptce2_pl);
+	cregion->ops->entry_remove(cregion, centry);
 }
 
 static int mlxsw_sp_acl_ctcam_region_parman_resize(void *priv,
@@ -153,11 +158,14 @@ static const struct parman_ops mlxsw_sp_acl_ctcam_region_parman_ops = {
 	.algo		= PARMAN_ALGO_TYPE_LSORT,
 };
 
-int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_acl_ctcam_region *cregion,
-				   struct mlxsw_sp_acl_tcam_region *region)
+int
+mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_ctcam_region *cregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops)
 {
 	cregion->region = region;
+	cregion->ops = ops;
 	cregion->parman = parman_create(&mlxsw_sp_acl_ctcam_region_parman_ops,
 					cregion);
 	if (!cregion->parman)
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index bb07723a0577..463590bbb348 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -1048,11 +1048,8 @@ mlxsw_sp_acl_erp_master_mask_init(struct mlxsw_sp_acl_atcam_region *aregion)
 {
 	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
 	char percr_pl[MLXSW_REG_PERCR_LEN];
-	char *master_mask;
 
 	mlxsw_reg_percr_pack(percr_pl, aregion->region->id);
-	master_mask = mlxsw_reg_percr_master_mask_data(percr_pl);
-	memset(master_mask, 0, MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(percr), percr_pl);
 }
 
@@ -1062,7 +1059,7 @@ mlxsw_sp_acl_erp_region_param_init(struct mlxsw_sp_acl_atcam_region *aregion)
 	struct mlxsw_sp *mlxsw_sp = aregion->region->mlxsw_sp;
 	char pererp_pl[MLXSW_REG_PERERP_LEN];
 
-	mlxsw_reg_pererp_pack(pererp_pl, aregion->region->id, true, true, 0,
+	mlxsw_reg_pererp_pack(pererp_pl, aregion->region->id, false, false, 0,
 			      0, 0);
 	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(pererp), pererp_pl);
 }
@@ -1077,16 +1074,12 @@ int mlxsw_sp_acl_erp_region_init(struct mlxsw_sp_acl_atcam_region *aregion)
 		return PTR_ERR(erp_table);
 	aregion->erp_table = erp_table;
 
-	/* Initialize the region's master mask to all ones for C-TCAM
-	 * only mode
-	 */
+	/* Initialize the region's master mask to all zeroes */
 	err = mlxsw_sp_acl_erp_master_mask_init(aregion);
 	if (err)
 		goto err_erp_master_mask_init;
 
-	/* Initialize the region to use the eRP table and enable C-TCAM
-	 * lookup
-	 */
+	/* Initialize the region to not use the eRP table */
 	err = mlxsw_sp_acl_erp_region_param_init(aregion);
 	if (err)
 		goto err_erp_region_param_init;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index fb6f9a521ddb..881ade760ace 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -112,6 +112,7 @@ struct mlxsw_sp_acl_tcam_region {
 
 struct mlxsw_sp_acl_ctcam_region {
 	struct parman *parman;
+	const struct mlxsw_sp_acl_ctcam_region_ops *ops;
 	struct mlxsw_sp_acl_tcam_region *region;
 };
 
@@ -123,9 +124,19 @@ struct mlxsw_sp_acl_ctcam_entry {
 	struct parman_item parman_item;
 };
 
-int mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_acl_ctcam_region *cregion,
-				   struct mlxsw_sp_acl_tcam_region *region);
+struct mlxsw_sp_acl_ctcam_region_ops {
+	int (*entry_insert)(struct mlxsw_sp_acl_ctcam_region *cregion,
+			    struct mlxsw_sp_acl_ctcam_entry *centry,
+			    const char *mask);
+	void (*entry_remove)(struct mlxsw_sp_acl_ctcam_region *cregion,
+			     struct mlxsw_sp_acl_ctcam_entry *centry);
+};
+
+int
+mlxsw_sp_acl_ctcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_ctcam_region *cregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops);
 void mlxsw_sp_acl_ctcam_region_fini(struct mlxsw_sp_acl_ctcam_region *cregion);
 void mlxsw_sp_acl_ctcam_chunk_init(struct mlxsw_sp_acl_ctcam_region *cregion,
 				   struct mlxsw_sp_acl_ctcam_chunk *cchunk,
@@ -190,12 +201,26 @@ struct mlxsw_sp_acl_atcam_entry {
 	struct mlxsw_sp_acl_erp *erp;
 };
 
+static inline struct mlxsw_sp_acl_atcam_region *
+mlxsw_sp_acl_tcam_cregion_aregion(struct mlxsw_sp_acl_ctcam_region *cregion)
+{
+	return container_of(cregion, struct mlxsw_sp_acl_atcam_region, cregion);
+}
+
+static inline struct mlxsw_sp_acl_atcam_entry *
+mlxsw_sp_acl_tcam_centry_aentry(struct mlxsw_sp_acl_ctcam_entry *centry)
+{
+	return container_of(centry, struct mlxsw_sp_acl_atcam_entry, centry);
+}
+
 int mlxsw_sp_acl_atcam_region_associate(struct mlxsw_sp *mlxsw_sp,
 					u16 region_id);
-int mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
-				   struct mlxsw_sp_acl_atcam *atcam,
-				   struct mlxsw_sp_acl_atcam_region *aregion,
-				   struct mlxsw_sp_acl_tcam_region *region);
+int
+mlxsw_sp_acl_atcam_region_init(struct mlxsw_sp *mlxsw_sp,
+			       struct mlxsw_sp_acl_atcam *atcam,
+			       struct mlxsw_sp_acl_atcam_region *aregion,
+			       struct mlxsw_sp_acl_tcam_region *region,
+			       const struct mlxsw_sp_acl_ctcam_region_ops *ops);
 void mlxsw_sp_acl_atcam_region_fini(struct mlxsw_sp_acl_atcam_region *aregion);
 void mlxsw_sp_acl_atcam_chunk_init(struct mlxsw_sp_acl_atcam_region *aregion,
 				   struct mlxsw_sp_acl_atcam_chunk *achunk,
-- 
cgit v1.2.3


From 08a852528e9678f0854af331f19747f2b2a73c06 Mon Sep 17 00:00:00 2001
From: Taeung Song <treeze.taeung@gmail.com>
Date: Wed, 25 Jul 2018 15:36:51 +0900
Subject: tools/bpftool: ignore build products

For untracked things of tools/bpf, add this.

Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/.gitignore         | 5 +++++
 tools/bpf/bpftool/.gitignore | 2 ++
 2 files changed, 7 insertions(+)
 create mode 100644 tools/bpf/.gitignore

diff --git a/tools/bpf/.gitignore b/tools/bpf/.gitignore
new file mode 100644
index 000000000000..dfe2bd5a4b95
--- /dev/null
+++ b/tools/bpf/.gitignore
@@ -0,0 +1,5 @@
+FEATURE-DUMP.bpf
+bpf_asm
+bpf_dbg
+bpf_exp.yacc.*
+bpf_jit_disasm
diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore
index d7e678c2d396..67167e44b726 100644
--- a/tools/bpf/bpftool/.gitignore
+++ b/tools/bpf/bpftool/.gitignore
@@ -1,3 +1,5 @@
 *.d
 bpftool
+bpftool*.8
+bpf-helpers.*
 FEATURE-DUMP.bpftool
-- 
cgit v1.2.3


From b24dbfe9ce03d9f83306616f22fb0e04e8960abe Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 26 Jul 2018 09:51:27 +0800
Subject: amd-xgbe: use dma_mapping_error to check map errors

The dma_mapping_error() returns true or false, but we want
to return -ENOMEM if there was an error.

Fixes: 174fd2597b0b ("amd-xgbe: Implement split header receive support")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/xgbe/xgbe-desc.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
index cc1e4f820e64..533094233659 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c
@@ -289,7 +289,7 @@ static int xgbe_alloc_pages(struct xgbe_prv_data *pdata,
 	struct page *pages = NULL;
 	dma_addr_t pages_dma;
 	gfp_t gfp;
-	int order, ret;
+	int order;
 
 again:
 	order = alloc_order;
@@ -316,10 +316,9 @@ again:
 	/* Map the pages */
 	pages_dma = dma_map_page(pdata->dev, pages, 0,
 				 PAGE_SIZE << order, DMA_FROM_DEVICE);
-	ret = dma_mapping_error(pdata->dev, pages_dma);
-	if (ret) {
+	if (dma_mapping_error(pdata->dev, pages_dma)) {
 		put_page(pages);
-		return ret;
+		return -ENOMEM;
 	}
 
 	pa->pages = pages;
-- 
cgit v1.2.3


From 934ffce1343f22ed5e2d0bd6da4440f4848074de Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 25 Jul 2018 16:54:33 +0800
Subject: xfrm: fix 'passing zero to ERR_PTR()' warning

Fix a static code checker warning:

  net/xfrm/xfrm_policy.c:1836 xfrm_resolve_and_create_bundle() warn: passing zero to 'ERR_PTR'

xfrm_tmpl_resolve return 0 just means no xdst found, return NULL
instead of passing zero to ERR_PTR.

Fixes: d809ec895505 ("xfrm: do not assume that template resolving always returns xfrms")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_policy.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 2f70fe68b9b0..69f06f879091 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -1752,7 +1752,10 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols,
 	/* Try to instantiate a bundle */
 	err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family);
 	if (err <= 0) {
-		if (err != 0 && err != -EAGAIN)
+		if (err == 0)
+			return NULL;
+
+		if (err != -EAGAIN)
 			XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR);
 		return ERR_PTR(err);
 	}
-- 
cgit v1.2.3


From 44e2b838c24d883dae8496dc7b6ddac7956ba53c Mon Sep 17 00:00:00 2001
From: Benedict Wong <benedictwong@google.com>
Date: Wed, 25 Jul 2018 13:45:29 -0700
Subject: xfrm: Return detailed errors from xfrmi_newlink

Currently all failure modes of xfrm interface creation return EEXIST.
This change improves the granularity of errnos provided by also
returning ENODEV or EINVAL if failures happen in looking up the
underlying interface, or a required parameter is not provided.

This change has been tested against the Android Kernel Networking Tests,
with additional xfrmi_newlink tests here:

https://android-review.googlesource.com/c/kernel/tests/+/715755

Signed-off-by: Benedict Wong <benedictwong@google.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_interface.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index ccfe18d67e98..481d7307ab51 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -149,14 +149,18 @@ static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p)
 	char name[IFNAMSIZ];
 	int err;
 
-	if (p->name[0])
+	if (p->name[0]) {
 		strlcpy(name, p->name, IFNAMSIZ);
-	else
+	} else {
+		err = -EINVAL;
 		goto failed;
+	}
 
 	dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup);
-	if (!dev)
+	if (!dev) {
+		err = -EAGAIN;
 		goto failed;
+	}
 
 	dev_net_set(dev, net);
 
@@ -165,8 +169,10 @@ static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p)
 	xi->net = net;
 	xi->dev = dev;
 	xi->phydev = dev_get_by_index(net, p->link);
-	if (!xi->phydev)
+	if (!xi->phydev) {
+		err = -ENODEV;
 		goto failed_free;
+	}
 
 	err = xfrmi_create2(dev);
 	if (err < 0)
@@ -179,7 +185,7 @@ failed_dev_put:
 failed_free:
 	free_netdev(dev);
 failed:
-	return NULL;
+	return ERR_PTR(err);
 }
 
 static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p,
@@ -194,13 +200,13 @@ static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p,
 	     xip = &xi->next) {
 		if (xi->p.if_id == p->if_id) {
 			if (create)
-				return NULL;
+				return ERR_PTR(-EEXIST);
 
 			return xi;
 		}
 	}
 	if (!create)
-		return NULL;
+		return ERR_PTR(-ENODEV);
 	return xfrmi_create(net, p);
 }
 
@@ -682,8 +688,9 @@ static int xfrmi_newlink(struct net *src_net, struct net_device *dev,
 
 	nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ);
 
-	if (!xfrmi_locate(net, p, 1))
-		return -EEXIST;
+	xi = xfrmi_locate(net, p, 1);
+	if (IS_ERR(xi))
+		return PTR_ERR(xi);
 
 	return 0;
 }
@@ -704,11 +711,12 @@ static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[],
 
 	xi = xfrmi_locate(net, &xi->p, 0);
 
-	if (xi) {
+	if (IS_ERR_OR_NULL(xi)) {
+		xi = netdev_priv(dev);
+	} else {
 		if (xi->dev != dev)
 			return -EEXIST;
-	} else
-		xi = netdev_priv(dev);
+	}
 
 	return xfrmi_update(xi, &xi->p);
 }
-- 
cgit v1.2.3


From 5b0ced17edc5710d4e946392d0f2934a9e07b37f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:40:34 -0700
Subject: nfp: don't fail probe on pci_sriov_set_totalvfs() errors

On machines with buggy ACPI tables or when SR-IOV is already enabled
we may not be able to set the SR-IOV VF limit in sysfs, it's not fatal
because the limit is imposed by the driver anyway.  Only the sysfs
'sriov_totalvfs' attribute will be too high.  Print an error to inform
user about the failure but allow probe to continue.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_main.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c
index 152283d7e59c..4a540c5e27fe 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_main.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c
@@ -236,16 +236,20 @@ static int nfp_pcie_sriov_read_nfd_limit(struct nfp_pf *pf)
 	int err;
 
 	pf->limit_vfs = nfp_rtsym_read_le(pf->rtbl, "nfd_vf_cfg_max_vfs", &err);
-	if (!err)
-		return pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
+	if (err) {
+		/* For backwards compatibility if symbol not found allow all */
+		pf->limit_vfs = ~0;
+		if (err == -ENOENT)
+			return 0;
 
-	pf->limit_vfs = ~0;
-	/* Allow any setting for backwards compatibility if symbol not found */
-	if (err == -ENOENT)
-		return 0;
+		nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err);
+		return err;
+	}
 
-	nfp_warn(pf->cpp, "Warning: VF limit read failed: %d\n", err);
-	return err;
+	err = pci_sriov_set_totalvfs(pf->pdev, pf->limit_vfs);
+	if (err)
+		nfp_warn(pf->cpp, "Failed to set VF count in sysfs: %d\n", err);
+	return 0;
 }
 
 static int nfp_pcie_sriov_enable(struct pci_dev *pdev, int num_vfs)
-- 
cgit v1.2.3


From 4662717038679520af832fcb8c4fefadb97facf8 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:40:35 -0700
Subject: nfp: use kvcalloc() to allocate SW buffer descriptor arrays

Use kvcalloc() instead of tmp variable + kzalloc() when allocating
SW buffer information to allow falling back to vmalloc and to protect
from theoretical integer overflow.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index cf1704e972b7..d02baefcb350 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -53,6 +53,7 @@
 #include <linux/interrupt.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/mm.h>
 #include <linux/page_ref.h>
 #include <linux/pci.h>
 #include <linux/pci_regs.h>
@@ -2126,7 +2127,7 @@ static void nfp_net_tx_ring_free(struct nfp_net_tx_ring *tx_ring)
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
 	struct nfp_net_dp *dp = &r_vec->nfp_net->dp;
 
-	kfree(tx_ring->txbufs);
+	kvfree(tx_ring->txbufs);
 
 	if (tx_ring->txds)
 		dma_free_coherent(dp->dev, tx_ring->size,
@@ -2150,7 +2151,6 @@ static int
 nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 {
 	struct nfp_net_r_vector *r_vec = tx_ring->r_vec;
-	int sz;
 
 	tx_ring->cnt = dp->txd_cnt;
 
@@ -2160,8 +2160,8 @@ nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 	if (!tx_ring->txds)
 		goto err_alloc;
 
-	sz = sizeof(*tx_ring->txbufs) * tx_ring->cnt;
-	tx_ring->txbufs = kzalloc(sz, GFP_KERNEL);
+	tx_ring->txbufs = kvcalloc(tx_ring->cnt, sizeof(*tx_ring->txbufs),
+				   GFP_KERNEL);
 	if (!tx_ring->txbufs)
 		goto err_alloc;
 
@@ -2275,7 +2275,7 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 
 	if (dp->netdev)
 		xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
-	kfree(rx_ring->rxbufs);
+	kvfree(rx_ring->rxbufs);
 
 	if (rx_ring->rxds)
 		dma_free_coherent(dp->dev, rx_ring->size,
@@ -2298,7 +2298,7 @@ static void nfp_net_rx_ring_free(struct nfp_net_rx_ring *rx_ring)
 static int
 nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 {
-	int sz, err;
+	int err;
 
 	if (dp->netdev) {
 		err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, dp->netdev,
@@ -2314,8 +2314,8 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 	if (!rx_ring->rxds)
 		goto err_alloc;
 
-	sz = sizeof(*rx_ring->rxbufs) * rx_ring->cnt;
-	rx_ring->rxbufs = kzalloc(sz, GFP_KERNEL);
+	rx_ring->rxbufs = kvcalloc(rx_ring->cnt, sizeof(*rx_ring->rxbufs),
+				   GFP_KERNEL);
 	if (!rx_ring->rxbufs)
 		goto err_alloc;
 
-- 
cgit v1.2.3


From e76c1d3d2a8313040d8316f760e9476028a27758 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:40:36 -0700
Subject: nfp: restore correct ordering of fields in rx ring structure

Commit 7f1c684a8966 ("nfp: setup xdp_rxq_info") mixed the cache
cold and cache hot data in the nfp_net_rx_ring structure (ignoring
the feedback), to try to fit the structure into 2 cache lines
after struct xdp_rxq_info was added.  Now that we are about to add
a new field the structure will grow back to 3 cache lines, so
order the members correctly.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 8970ec981e11..607896910fb0 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -350,9 +350,9 @@ struct nfp_net_rx_buf {
  * @qcp_fl:     Pointer to base of the QCP freelist queue
  * @rxbufs:     Array of transmitted FL/RX buffers
  * @rxds:       Virtual address of FL/RX ring in host memory
+ * @xdp_rxq:    RX-ring info avail for XDP
  * @dma:        DMA address of the FL/RX ring
  * @size:       Size, in bytes, of the FL/RX ring (needed to free)
- * @xdp_rxq:    RX-ring info avail for XDP
  */
 struct nfp_net_rx_ring {
 	struct nfp_net_r_vector *r_vec;
@@ -364,14 +364,15 @@ struct nfp_net_rx_ring {
 	u32 idx;
 
 	int fl_qcidx;
-	unsigned int size;
 	u8 __iomem *qcp_fl;
 
 	struct nfp_net_rx_buf *rxbufs;
 	struct nfp_net_rx_desc *rxds;
 
-	dma_addr_t dma;
 	struct xdp_rxq_info xdp_rxq;
+
+	dma_addr_t dma;
+	unsigned int size;
 } ____cacheline_aligned;
 
 /**
-- 
cgit v1.2.3


From 5ea14712d7a22703645217c5296e72cb5adba0a6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:40:37 -0700
Subject: nfp: protect from theoretical size overflows on HW descriptor ring

Use array_size() and store the size as full size_t to protect from
theoretical size overflow when handling HW descriptor rings.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net.h        | 4 ++--
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 9 +++++----
 2 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h
index 607896910fb0..439e6ffe2f05 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h
@@ -250,7 +250,7 @@ struct nfp_net_tx_ring {
 	struct nfp_net_tx_desc *txds;
 
 	dma_addr_t dma;
-	unsigned int size;
+	size_t size;
 	bool is_xdp;
 } ____cacheline_aligned;
 
@@ -372,7 +372,7 @@ struct nfp_net_rx_ring {
 	struct xdp_rxq_info xdp_rxq;
 
 	dma_addr_t dma;
-	unsigned int size;
+	size_t size;
 } ____cacheline_aligned;
 
 /**
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index d02baefcb350..7c1a921d178d 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -54,6 +54,7 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/mm.h>
+#include <linux/overflow.h>
 #include <linux/page_ref.h>
 #include <linux/pci.h>
 #include <linux/pci_regs.h>
@@ -1121,7 +1122,7 @@ nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 		tx_ring->rd_p++;
 	}
 
-	memset(tx_ring->txds, 0, sizeof(*tx_ring->txds) * tx_ring->cnt);
+	memset(tx_ring->txds, 0, tx_ring->size);
 	tx_ring->wr_p = 0;
 	tx_ring->rd_p = 0;
 	tx_ring->qcp_rd_p = 0;
@@ -1301,7 +1302,7 @@ static void nfp_net_rx_ring_reset(struct nfp_net_rx_ring *rx_ring)
 	rx_ring->rxbufs[last_idx].dma_addr = 0;
 	rx_ring->rxbufs[last_idx].frag = NULL;
 
-	memset(rx_ring->rxds, 0, sizeof(*rx_ring->rxds) * rx_ring->cnt);
+	memset(rx_ring->rxds, 0, rx_ring->size);
 	rx_ring->wr_p = 0;
 	rx_ring->rd_p = 0;
 }
@@ -2154,7 +2155,7 @@ nfp_net_tx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring)
 
 	tx_ring->cnt = dp->txd_cnt;
 
-	tx_ring->size = sizeof(*tx_ring->txds) * tx_ring->cnt;
+	tx_ring->size = array_size(tx_ring->cnt, sizeof(*tx_ring->txds));
 	tx_ring->txds = dma_zalloc_coherent(dp->dev, tx_ring->size,
 					    &tx_ring->dma, GFP_KERNEL);
 	if (!tx_ring->txds)
@@ -2308,7 +2309,7 @@ nfp_net_rx_ring_alloc(struct nfp_net_dp *dp, struct nfp_net_rx_ring *rx_ring)
 	}
 
 	rx_ring->cnt = dp->rxd_cnt;
-	rx_ring->size = sizeof(*rx_ring->rxds) * rx_ring->cnt;
+	rx_ring->size = array_size(rx_ring->cnt, sizeof(*rx_ring->rxds));
 	rx_ring->rxds = dma_zalloc_coherent(dp->dev, rx_ring->size,
 					    &rx_ring->dma, GFP_KERNEL);
 	if (!rx_ring->rxds)
-- 
cgit v1.2.3


From 947541f36c561b5e0ca639ffc450a8c5221de467 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Wed, 25 Jul 2018 16:35:30 +0200
Subject: net/smc: fewer parameters for smc_llc_send_confirm_link()

Link confirmation will always be sent across the new link being
confirmed. This allows to shrink the parameter list.
No functional change.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c  | 10 ++--------
 net/smc/smc_llc.c |  9 +++++----
 net/smc/smc_llc.h |  2 +-
 3 files changed, 8 insertions(+), 13 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 7fc810ec31c5..7883f70f7c6d 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -352,10 +352,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 		return SMC_CLC_DECL_INTERR;
 
 	/* send CONFIRM LINK response over RoCE fabric */
-	rc = smc_llc_send_confirm_link(link,
-				       link->smcibdev->mac[link->ibport - 1],
-				       &link->smcibdev->gid[link->ibport - 1],
-				       SMC_LLC_RESP);
+	rc = smc_llc_send_confirm_link(link, SMC_LLC_RESP);
 	if (rc < 0)
 		return SMC_CLC_DECL_TCL;
 
@@ -951,10 +948,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 		return SMC_CLC_DECL_INTERR;
 
 	/* send CONFIRM LINK request to client over the RoCE fabric */
-	rc = smc_llc_send_confirm_link(link,
-				       link->smcibdev->mac[link->ibport - 1],
-				       &link->smcibdev->gid[link->ibport - 1],
-				       SMC_LLC_REQ);
+	rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ);
 	if (rc < 0)
 		return SMC_CLC_DECL_TCL;
 
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index b7944aa1ffc3..f2ba99c2e69a 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -182,8 +182,7 @@ static int smc_llc_add_pending_send(struct smc_link *link,
 }
 
 /* high-level API to send LLC confirm link */
-int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[],
-			      union ib_gid *gid,
+int smc_llc_send_confirm_link(struct smc_link *link,
 			      enum smc_llc_reqresp reqresp)
 {
 	struct smc_link_group *lgr = smc_get_lgr(link);
@@ -202,8 +201,10 @@ int smc_llc_send_confirm_link(struct smc_link *link, u8 mac[],
 	confllc->hd.flags |= SMC_LLC_FLAG_NO_RMBE_EYEC;
 	if (reqresp == SMC_LLC_RESP)
 		confllc->hd.flags |= SMC_LLC_FLAG_RESP;
-	memcpy(confllc->sender_mac, mac, ETH_ALEN);
-	memcpy(confllc->sender_gid, gid, SMC_GID_SIZE);
+	memcpy(confllc->sender_mac, link->smcibdev->mac[link->ibport - 1],
+	       ETH_ALEN);
+	memcpy(confllc->sender_gid, &link->smcibdev->gid[link->ibport - 1],
+	       SMC_GID_SIZE);
 	hton24(confllc->sender_qp_num, link->roce_qp->qp_num);
 	confllc->link_num = link->link_id;
 	memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE);
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 65c8645e96a1..9a29fcbbcea8 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -36,7 +36,7 @@ enum smc_llc_msg_type {
 };
 
 /* transmit */
-int smc_llc_send_confirm_link(struct smc_link *lnk, u8 mac[], union ib_gid *gid,
+int smc_llc_send_confirm_link(struct smc_link *lnk,
 			      enum smc_llc_reqresp reqresp);
 int smc_llc_send_add_link(struct smc_link *link, u8 mac[], union ib_gid *gid,
 			  enum smc_llc_reqresp reqresp);
-- 
cgit v1.2.3


From 7005ada68d1774d7c1109deaba0c2cd8e46f5091 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Wed, 25 Jul 2018 16:35:31 +0200
Subject: net/smc: use correct vlan gid of RoCE device

SMC code uses the base gid for VLAN traffic. The gids exchanged in
the CLC handshake and the gid index used for the QP have to switch
from the base gid to the appropriate vlan gid.

When searching for a matching IB device port for a certain vlan
device, it does not make sense to return an IB device port, which
is not enabled for the used vlan_id. Add another check whether a
vlan gid exists for a certain IB device port.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/af_smc.c   | 24 +++++++++++++-----------
 net/smc/smc_clc.c  | 10 ++++------
 net/smc/smc_clc.h  |  2 +-
 net/smc/smc_core.c | 37 ++++---------------------------------
 net/smc/smc_core.h |  5 +++--
 net/smc/smc_diag.c |  2 +-
 net/smc/smc_ib.c   | 41 ++++++++++++++++++++++++++++++++++++-----
 net/smc/smc_ib.h   |  3 ++-
 net/smc/smc_llc.c  | 15 +++++----------
 net/smc/smc_llc.h  |  2 +-
 net/smc/smc_pnet.c | 30 +++++++++++++++++++++---------
 net/smc/smc_pnet.h |  3 ++-
 12 files changed, 93 insertions(+), 81 deletions(-)

diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index 7883f70f7c6d..b81797103260 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -370,8 +370,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 	/* send add link reject message, only one link supported for now */
 	rc = smc_llc_send_add_link(link,
 				   link->smcibdev->mac[link->ibport - 1],
-				   &link->smcibdev->gid[link->ibport - 1],
-				   SMC_LLC_RESP);
+				   link->gid, SMC_LLC_RESP);
 	if (rc < 0)
 		return SMC_CLC_DECL_TCL;
 
@@ -469,7 +468,7 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code,
 /* check if there is a rdma device available for this connection. */
 /* called for connect and listen */
 static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
-			  u8 *ibport)
+			  u8 *ibport, unsigned short vlan_id, u8 gid[])
 {
 	int reason_code = 0;
 
@@ -477,7 +476,8 @@ static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
 	 * within same PNETID that also contains the ethernet device
 	 * used for the internal TCP socket
 	 */
-	smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport);
+	smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport, vlan_id,
+				    gid);
 	if (!(*ibdev))
 		reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
 
@@ -523,12 +523,12 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
 static int smc_connect_clc(struct smc_sock *smc, int smc_type,
 			   struct smc_clc_msg_accept_confirm *aclc,
 			   struct smc_ib_device *ibdev, u8 ibport,
-			   struct smcd_dev *ismdev)
+			   u8 gid[], struct smcd_dev *ismdev)
 {
 	int rc = 0;
 
 	/* do inband token exchange */
-	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, ismdev);
+	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev);
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
@@ -650,6 +650,7 @@ static int __smc_connect(struct smc_sock *smc)
 	struct smc_clc_msg_accept_confirm aclc;
 	struct smc_ib_device *ibdev;
 	struct smcd_dev *ismdev;
+	u8 gid[SMC_GID_SIZE];
 	unsigned short vlan;
 	int smc_type;
 	int rc = 0;
@@ -681,7 +682,7 @@ static int __smc_connect(struct smc_sock *smc)
 	}
 
 	/* check if there is a rdma device available */
-	if (!smc_check_rdma(smc, &ibdev, &ibport)) {
+	if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) {
 		/* RDMA is supported for this connection */
 		rdma_supported = true;
 		if (ism_supported)
@@ -695,7 +696,7 @@ static int __smc_connect(struct smc_sock *smc)
 		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
 
 	/* perform CLC handshake */
-	rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, ismdev);
+	rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
 	if (rc) {
 		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
 		return smc_connect_decline_fallback(smc, rc);
@@ -970,8 +971,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 	/* send ADD LINK request to client over the RoCE fabric */
 	rc = smc_llc_send_add_link(link,
 				   link->smcibdev->mac[link->ibport - 1],
-				   &link->smcibdev->gid[link->ibport - 1],
-				   SMC_LLC_REQ);
+				   link->gid, SMC_LLC_REQ);
 	if (rc < 0)
 		return SMC_CLC_DECL_TCL;
 
@@ -1193,6 +1193,7 @@ static void smc_listen_work(struct work_struct *work)
 	struct smcd_dev *ismdev;
 	u8 buf[SMC_CLC_MAX_LEN];
 	int local_contact = 0;
+	unsigned short vlan;
 	int reason_code = 0;
 	int rc = 0;
 	u8 ibport;
@@ -1241,7 +1242,8 @@ static void smc_listen_work(struct work_struct *work)
 	/* check if RDMA is available */
 	if (!ism_supported &&
 	    ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
-	     smc_check_rdma(new_smc, &ibdev, &ibport) ||
+	     smc_vlan_by_tcpsk(new_smc->clcsock, &vlan) ||
+	     smc_check_rdma(new_smc, &ibdev, &ibport, vlan, NULL) ||
 	     smc_listen_rdma_check(new_smc, pclc) ||
 	     smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
 				  &local_contact) ||
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index ad39efdb4f1c..78d74938a9d9 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 
 /* send CLC PROPOSAL message across internal TCP socket */
 int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_ib_device *ibdev, u8 ibport,
+			  struct smc_ib_device *ibdev, u8 ibport, u8 gid[],
 			  struct smcd_dev *ismdev)
 {
 	struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
@@ -409,7 +409,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
 		/* add SMC-R specifics */
 		memcpy(pclc.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&pclc.lcl.gid, &ibdev->gid[ibport - 1], SMC_GID_SIZE);
+		memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE);
 		memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
 		pclc.iparea_offset = htons(0);
 	}
@@ -492,8 +492,7 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 		cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
 		memcpy(cclc.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
-		       SMC_GID_SIZE);
+		memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE);
 		memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
 		       ETH_ALEN);
 		hton24(cclc.qpn, link->roce_qp->qp_num);
@@ -566,8 +565,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 		link = &conn->lgr->lnk[SMC_SINGLE_LINK];
 		memcpy(aclc.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
-		       SMC_GID_SIZE);
+		memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE);
 		memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
 		       ETH_ALEN);
 		hton24(aclc.qpn, link->roce_qp->qp_num);
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 100e988ad1a8..6bdc63352d6a 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -179,7 +179,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type);
 int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
 int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_ib_device *smcibdev, u8 ibport,
+			  struct smc_ib_device *smcibdev, u8 ibport, u8 gid[],
 			  struct smcd_dev *ismdev);
 int smc_clc_send_confirm(struct smc_sock *smc);
 int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);
diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 66741e61a3b0..90c10ae9ae09 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -219,6 +219,10 @@ static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
 		get_random_bytes(rndvec, sizeof(rndvec));
 		lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
 			(rndvec[2] << 16);
+		rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport,
+					  vlan_id, lnk->gid, &lnk->sgid_index);
+		if (rc)
+			goto free_lgr;
 		rc = smc_llc_link_init(lnk);
 		if (rc)
 			goto free_lgr;
@@ -522,37 +526,6 @@ out:
 	return rc;
 }
 
-/* determine the link gid matching the vlan id of the link group */
-static int smc_link_determine_gid(struct smc_link_group *lgr)
-{
-	struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
-	struct ib_gid_attr gattr;
-	union ib_gid gid;
-	int i;
-
-	if (!lgr->vlan_id) {
-		lnk->gid = lnk->smcibdev->gid[lnk->ibport - 1];
-		return 0;
-	}
-
-	for (i = 0; i < lnk->smcibdev->pattr[lnk->ibport - 1].gid_tbl_len;
-	     i++) {
-		if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid,
-				 &gattr))
-			continue;
-		if (gattr.ndev) {
-			if (is_vlan_dev(gattr.ndev) &&
-			    vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) {
-				lnk->gid = gid;
-				dev_put(gattr.ndev);
-				return 0;
-			}
-			dev_put(gattr.ndev);
-		}
-	}
-	return -ENODEV;
-}
-
 static bool smcr_lgr_match(struct smc_link_group *lgr,
 			   struct smc_clc_msg_local *lcl,
 			   enum smc_lgr_role role)
@@ -631,8 +604,6 @@ create:
 		if (rc)
 			goto out;
 		smc_lgr_register_conn(conn); /* add smc conn to lgr */
-		if (!is_smcd)
-			rc = smc_link_determine_gid(conn->lgr);
 	}
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index 1e8974c50550..a4f0cc4e0270 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -84,14 +84,15 @@ struct smc_link {
 	wait_queue_head_t	wr_reg_wait;	/* wait for wr_reg result */
 	enum smc_wr_reg_state	wr_reg_state;	/* state of wr_reg request */
 
-	union ib_gid		gid;		/* gid matching used vlan id */
+	u8			gid[SMC_GID_SIZE];/* gid matching used vlan id*/
+	u8			sgid_index;	/* gid index for vlan id      */
 	u32			peer_qpn;	/* QP number of peer */
 	enum ib_mtu		path_mtu;	/* used mtu */
 	enum ib_mtu		peer_mtu;	/* mtu size of peer */
 	u32			psn_initial;	/* QP tx initial packet seqno */
 	u32			peer_psn;	/* QP rx initial packet seqno */
 	u8			peer_mac[ETH_ALEN];	/* = gid[8:10||13:15] */
-	u8			peer_gid[sizeof(union ib_gid)];	/* gid of peer*/
+	u8			peer_gid[SMC_GID_SIZE];	/* gid of peer*/
 	u8			link_id;	/* unique # within link group */
 
 	enum smc_link_state	state;		/* state of link */
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index d772cd10297e..a3cf7313a2d3 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -154,7 +154,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 		       smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
 		       sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name));
 		smc_gid_be16_convert(linfo.lnk[0].gid,
-				     smc->conn.lgr->lnk[0].gid.raw);
+				     smc->conn.lgr->lnk[0].gid);
 		smc_gid_be16_convert(linfo.lnk[0].peer_gid,
 				     smc->conn.lgr->lnk[0].peer_gid);
 
diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c
index 4706ab7092a9..2cc64bc8ae20 100644
--- a/net/smc/smc_ib.c
+++ b/net/smc/smc_ib.c
@@ -68,7 +68,7 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
 	qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu);
 	qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
 	rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport);
-	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, 0, 1, 0);
+	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
 	rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
 	memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
 	       sizeof(lnk->peer_mac));
@@ -142,13 +142,13 @@ out:
 	return rc;
 }
 
-static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
+static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	struct ib_gid_attr gattr;
+	union ib_gid gid;
 	int rc;
 
-	rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
-			  &smcibdev->gid[ibport - 1], &gattr);
+	rc = ib_query_gid(smcibdev->ibdev, ibport, 0, &gid, &gattr);
 	if (rc || !gattr.ndev)
 		return -ENODEV;
 
@@ -175,6 +175,37 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
 	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
 }
 
+/* determine the gid for an ib-device port and vlan id */
+int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
+			 unsigned short vlan_id, u8 gid[], u8 *sgid_index)
+{
+	struct ib_gid_attr gattr;
+	union ib_gid _gid;
+	int i;
+
+	for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
+		memset(&_gid, 0, SMC_GID_SIZE);
+		memset(&gattr, 0, sizeof(gattr));
+		if (ib_query_gid(smcibdev->ibdev, ibport, i, &_gid, &gattr))
+			continue;
+		if (!gattr.ndev)
+			continue;
+		if (((!vlan_id && !is_vlan_dev(gattr.ndev)) ||
+		     (vlan_id && is_vlan_dev(gattr.ndev) &&
+		      vlan_dev_vlan_id(gattr.ndev) == vlan_id)) &&
+		    gattr.gid_type == IB_GID_TYPE_IB) {
+			if (gid)
+				memcpy(gid, &_gid, SMC_GID_SIZE);
+			if (sgid_index)
+				*sgid_index = i;
+			dev_put(gattr.ndev);
+			return 0;
+		}
+		dev_put(gattr.ndev);
+	}
+	return -ENODEV;
+}
+
 static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	int rc;
@@ -186,7 +217,7 @@ static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
 	if (rc)
 		goto out;
 	/* the SMC protocol requires specification of the RoCE MAC address */
-	rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
+	rc = smc_ib_fill_mac(smcibdev, ibport);
 	if (rc)
 		goto out;
 	if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
diff --git a/net/smc/smc_ib.h b/net/smc/smc_ib.h
index 7c1223c91229..bac7fd65a4c0 100644
--- a/net/smc/smc_ib.h
+++ b/net/smc/smc_ib.h
@@ -40,7 +40,6 @@ struct smc_ib_device {				/* ib-device infos for smc */
 	struct tasklet_struct	recv_tasklet;	/* called by recv cq handler */
 	char			mac[SMC_MAX_PORTS][ETH_ALEN];
 						/* mac address per port*/
-	union ib_gid		gid[SMC_MAX_PORTS]; /* gid per port */
 	u8			pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
 						/* pnetid per port */
 	u8			initialized : 1; /* ib dev CQ, evthdl done */
@@ -77,4 +76,6 @@ void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
 void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
 			       struct smc_buf_desc *buf_slot,
 			       enum dma_data_direction data_direction);
+int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
+			 unsigned short vlan_id, u8 gid[], u8 *sgid_index);
 #endif
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index f2ba99c2e69a..a88c01029fa6 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -203,8 +203,7 @@ int smc_llc_send_confirm_link(struct smc_link *link,
 		confllc->hd.flags |= SMC_LLC_FLAG_RESP;
 	memcpy(confllc->sender_mac, link->smcibdev->mac[link->ibport - 1],
 	       ETH_ALEN);
-	memcpy(confllc->sender_gid, &link->smcibdev->gid[link->ibport - 1],
-	       SMC_GID_SIZE);
+	memcpy(confllc->sender_gid, link->gid, SMC_GID_SIZE);
 	hton24(confllc->sender_qp_num, link->roce_qp->qp_num);
 	confllc->link_num = link->link_id;
 	memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE);
@@ -241,8 +240,7 @@ static int smc_llc_send_confirm_rkey(struct smc_link *link,
 
 /* prepare an add link message */
 static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
-				  struct smc_link *link, u8 mac[],
-				  union ib_gid *gid,
+				  struct smc_link *link, u8 mac[], u8 gid[],
 				  enum smc_llc_reqresp reqresp)
 {
 	memset(addllc, 0, sizeof(*addllc));
@@ -259,8 +257,7 @@ static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
 }
 
 /* send ADD LINK request or response */
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
-			  union ib_gid *gid,
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
 			  enum smc_llc_reqresp reqresp)
 {
 	struct smc_llc_msg_add_link *addllc;
@@ -423,14 +420,12 @@ static void smc_llc_rx_add_link(struct smc_link *link,
 		if (lgr->role == SMC_SERV) {
 			smc_llc_prep_add_link(llc, link,
 					link->smcibdev->mac[link->ibport - 1],
-					&link->smcibdev->gid[link->ibport - 1],
-					SMC_LLC_REQ);
+					link->gid, SMC_LLC_REQ);
 
 		} else {
 			smc_llc_prep_add_link(llc, link,
 					link->smcibdev->mac[link->ibport - 1],
-					&link->smcibdev->gid[link->ibport - 1],
-					SMC_LLC_RESP);
+					link->gid, SMC_LLC_RESP);
 		}
 		smc_llc_send_message(link, llc, sizeof(*llc));
 	}
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 9a29fcbbcea8..95a7f3662e59 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -38,7 +38,7 @@ enum smc_llc_msg_type {
 /* transmit */
 int smc_llc_send_confirm_link(struct smc_link *lnk,
 			      enum smc_llc_reqresp reqresp);
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[], union ib_gid *gid,
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
 			  enum smc_llc_reqresp reqresp);
 int smc_llc_send_delete_link(struct smc_link *link,
 			     enum smc_llc_reqresp reqresp);
diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 1b6c066d3495..01c6ce042a1c 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -535,11 +535,13 @@ static struct net_device *pnet_find_base_ndev(struct net_device *ndev)
 }
 
 /* Determine the corresponding IB device port based on the hardware PNETID.
- * Searching stops at the first matching active IB device port.
+ * Searching stops at the first matching active IB device port with vlan_id
+ * configured.
  */
 static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
 					 struct smc_ib_device **smcibdev,
-					 u8 *ibport)
+					 u8 *ibport, unsigned short vlan_id,
+					 u8 gid[])
 {
 	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
 	struct smc_ib_device *ibdev;
@@ -553,15 +555,20 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
 	spin_lock(&smc_ib_devices.lock);
 	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
 		for (i = 1; i <= SMC_MAX_PORTS; i++) {
+			if (!rdma_is_port_valid(ibdev->ibdev, i))
+				continue;
 			if (!memcmp(ibdev->pnetid[i - 1], ndev_pnetid,
 				    SMC_MAX_PNETID_LEN) &&
-			    smc_ib_port_active(ibdev, i)) {
+			    smc_ib_port_active(ibdev, i) &&
+			    !smc_ib_determine_gid(ibdev, i, vlan_id, gid,
+						  NULL))  {
 				*smcibdev = ibdev;
 				*ibport = i;
-				break;
+				goto out;
 			}
 		}
 	}
+out:
 	spin_unlock(&smc_ib_devices.lock);
 }
 
@@ -589,7 +596,8 @@ static void smc_pnet_find_ism_by_pnetid(struct net_device *ndev,
 /* Lookup of coupled ib_device via SMC pnet table */
 static void smc_pnet_find_roce_by_table(struct net_device *netdev,
 					struct smc_ib_device **smcibdev,
-					u8 *ibport)
+					u8 *ibport, unsigned short vlan_id,
+					u8 gid[])
 {
 	struct smc_pnetentry *pnetelem;
 
@@ -597,7 +605,10 @@ static void smc_pnet_find_roce_by_table(struct net_device *netdev,
 	list_for_each_entry(pnetelem, &smc_pnettable.pnetlist, list) {
 		if (netdev == pnetelem->ndev) {
 			if (smc_ib_port_active(pnetelem->smcibdev,
-					       pnetelem->ib_port)) {
+					       pnetelem->ib_port) &&
+			    !smc_ib_determine_gid(pnetelem->smcibdev,
+						  pnetelem->ib_port, vlan_id,
+						  gid, NULL)) {
 				*smcibdev = pnetelem->smcibdev;
 				*ibport = pnetelem->ib_port;
 			}
@@ -612,7 +623,8 @@ static void smc_pnet_find_roce_by_table(struct net_device *netdev,
  * ethernet interface.
  */
 void smc_pnet_find_roce_resource(struct sock *sk,
-				 struct smc_ib_device **smcibdev, u8 *ibport)
+				 struct smc_ib_device **smcibdev, u8 *ibport,
+				 unsigned short vlan_id, u8 gid[])
 {
 	struct dst_entry *dst = sk_dst_get(sk);
 
@@ -625,12 +637,12 @@ void smc_pnet_find_roce_resource(struct sock *sk,
 		goto out_rel;
 
 	/* if possible, lookup via hardware-defined pnetid */
-	smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport);
+	smc_pnet_find_roce_by_pnetid(dst->dev, smcibdev, ibport, vlan_id, gid);
 	if (*smcibdev)
 		goto out_rel;
 
 	/* lookup via SMC PNET table */
-	smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport);
+	smc_pnet_find_roce_by_table(dst->dev, smcibdev, ibport, vlan_id, gid);
 
 out_rel:
 	dst_release(dst);
diff --git a/net/smc/smc_pnet.h b/net/smc/smc_pnet.h
index 1e94fd4df7bc..8ff777636e32 100644
--- a/net/smc/smc_pnet.h
+++ b/net/smc/smc_pnet.h
@@ -33,7 +33,8 @@ int smc_pnet_init(void) __init;
 void smc_pnet_exit(void);
 int smc_pnet_remove_by_ibdev(struct smc_ib_device *ibdev);
 void smc_pnet_find_roce_resource(struct sock *sk,
-				 struct smc_ib_device **smcibdev, u8 *ibport);
+				 struct smc_ib_device **smcibdev, u8 *ibport,
+				 unsigned short vlan_id, u8 gid[]);
 void smc_pnet_find_ism_resource(struct sock *sk, struct smcd_dev **smcismdev);
 
 #endif
-- 
cgit v1.2.3


From 603cc1498455cf57f5ca4483b600efb37ea2c56c Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Wed, 25 Jul 2018 16:35:32 +0200
Subject: net/smc: provide fallback reason code

Remember the fallback reason code and the peer diagnosis code for
smc sockets, and provide them in smc_diag.c to the netlink interface.
And add more detailed reason codes.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/smc_diag.h |  6 +++++
 net/smc/af_smc.c              | 52 +++++++++++++++++++++++++------------------
 net/smc/smc.h                 |  2 ++
 net/smc/smc_clc.c             |  6 ++++-
 net/smc/smc_clc.h             | 18 ++++++++++-----
 net/smc/smc_diag.c            |  6 +++++
 6 files changed, 61 insertions(+), 29 deletions(-)

diff --git a/include/uapi/linux/smc_diag.h b/include/uapi/linux/smc_diag.h
index 48ae3ee22b2d..ac9e8c96d9bd 100644
--- a/include/uapi/linux/smc_diag.h
+++ b/include/uapi/linux/smc_diag.h
@@ -43,6 +43,7 @@ enum {
 	SMC_DIAG_LGRINFO,
 	SMC_DIAG_SHUTDOWN,
 	SMC_DIAG_DMBINFO,
+	SMC_DIAG_FALLBACK,
 	__SMC_DIAG_MAX,
 };
 
@@ -92,6 +93,11 @@ struct smc_diag_lgrinfo {
 	__u8				role;
 };
 
+struct smc_diag_fallback {
+	__u32 reason;
+	__u32 peer_diagnosis;
+};
+
 struct smcd_diag_dmbinfo {		/* SMC-D Socket internals */
 	__u32 linkid;			/* Link identifier */
 	__u64 peer_gid;			/* Peer GID */
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index b81797103260..fce7e4751151 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -344,17 +344,17 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 
 	rc = smc_ib_modify_qp_rts(link);
 	if (rc)
-		return SMC_CLC_DECL_INTERR;
+		return SMC_CLC_DECL_ERR_RDYLNK;
 
 	smc_wr_remember_qp_attr(link);
 
 	if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
-		return SMC_CLC_DECL_INTERR;
+		return SMC_CLC_DECL_ERR_REGRMB;
 
 	/* send CONFIRM LINK response over RoCE fabric */
 	rc = smc_llc_send_confirm_link(link, SMC_LLC_RESP);
 	if (rc < 0)
-		return SMC_CLC_DECL_TCL;
+		return SMC_CLC_DECL_TIMEOUT_CL;
 
 	/* receive ADD LINK request from server over RoCE fabric */
 	rest = wait_for_completion_interruptible_timeout(&link->llc_add,
@@ -372,7 +372,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 				   link->smcibdev->mac[link->ibport - 1],
 				   link->gid, SMC_LLC_RESP);
 	if (rc < 0)
-		return SMC_CLC_DECL_TCL;
+		return SMC_CLC_DECL_TIMEOUT_AL;
 
 	smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time);
 
@@ -424,9 +424,10 @@ static void smc_link_save_peer_info(struct smc_link *link,
 }
 
 /* fall back during connect */
-static int smc_connect_fallback(struct smc_sock *smc)
+static int smc_connect_fallback(struct smc_sock *smc, int reason_code)
 {
 	smc->use_fallback = true;
+	smc->fallback_rsn = reason_code;
 	smc_copy_sock_settings_to_clc(smc);
 	if (smc->sk.sk_state == SMC_INIT)
 		smc->sk.sk_state = SMC_ACTIVE;
@@ -443,7 +444,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 			sock_put(&smc->sk); /* passive closing */
 		return reason_code;
 	}
-	if (reason_code != SMC_CLC_DECL_REPLY) {
+	if (reason_code != SMC_CLC_DECL_PEERDECL) {
 		rc = smc_clc_send_decline(smc, reason_code);
 		if (rc < 0) {
 			if (smc->sk.sk_state == SMC_INIT)
@@ -451,7 +452,7 @@ static int smc_connect_decline_fallback(struct smc_sock *smc, int reason_code)
 			return rc;
 		}
 	}
-	return smc_connect_fallback(smc);
+	return smc_connect_fallback(smc, reason_code);
 }
 
 /* abort connecting */
@@ -568,7 +569,7 @@ static int smc_connect_rdma(struct smc_sock *smc,
 		smc_link_save_peer_info(link, aclc);
 
 	if (smc_rmb_rtoken_handling(&smc->conn, aclc))
-		return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+		return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RTOK,
 					 local_contact);
 
 	smc_close_init(smc);
@@ -576,12 +577,12 @@ static int smc_connect_rdma(struct smc_sock *smc,
 
 	if (local_contact == SMC_FIRST_CONTACT) {
 		if (smc_ib_ready_link(link))
-			return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_RDYLNK,
 						 local_contact);
 	} else {
 		if (!smc->conn.rmb_desc->reused &&
 		    smc_reg_rmb(link, smc->conn.rmb_desc, true))
-			return smc_connect_abort(smc, SMC_CLC_DECL_INTERR,
+			return smc_connect_abort(smc, SMC_CLC_DECL_ERR_REGRMB,
 						 local_contact);
 	}
 	smc_rmb_sync_sg_for_device(&smc->conn);
@@ -659,11 +660,11 @@ static int __smc_connect(struct smc_sock *smc)
 	sock_hold(&smc->sk); /* sock put in passive closing */
 
 	if (smc->use_fallback)
-		return smc_connect_fallback(smc);
+		return smc_connect_fallback(smc, smc->fallback_rsn);
 
 	/* if peer has not signalled SMC-capability, fall back */
 	if (!tcp_sk(smc->clcsock->sk)->syn_smc)
-		return smc_connect_fallback(smc);
+		return smc_connect_fallback(smc, SMC_CLC_DECL_PEERNOSMC);
 
 	/* IPSec connections opt out of SMC-R optimizations */
 	if (using_ipsec(smc))
@@ -693,7 +694,7 @@ static int __smc_connect(struct smc_sock *smc)
 
 	/* if neither ISM nor RDMA are supported, fallback */
 	if (!rdma_supported && !ism_supported)
-		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
+		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_NOSMCDEV);
 
 	/* perform CLC handshake */
 	rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
@@ -708,7 +709,7 @@ static int __smc_connect(struct smc_sock *smc)
 	else if (ism_supported && aclc.hdr.path == SMC_TYPE_D)
 		rc = smc_connect_ism(smc, &aclc, ismdev);
 	else
-		rc = SMC_CLC_DECL_CNFERR;
+		rc = SMC_CLC_DECL_MODEUNSUPP;
 	if (rc) {
 		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
 		return smc_connect_decline_fallback(smc, rc);
@@ -946,12 +947,12 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 	link = &lgr->lnk[SMC_SINGLE_LINK];
 
 	if (smc_reg_rmb(link, smc->conn.rmb_desc, false))
-		return SMC_CLC_DECL_INTERR;
+		return SMC_CLC_DECL_ERR_REGRMB;
 
 	/* send CONFIRM LINK request to client over the RoCE fabric */
 	rc = smc_llc_send_confirm_link(link, SMC_LLC_REQ);
 	if (rc < 0)
-		return SMC_CLC_DECL_TCL;
+		return SMC_CLC_DECL_TIMEOUT_CL;
 
 	/* receive CONFIRM LINK response from client over the RoCE fabric */
 	rest = wait_for_completion_interruptible_timeout(
@@ -973,7 +974,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 				   link->smcibdev->mac[link->ibport - 1],
 				   link->gid, SMC_LLC_REQ);
 	if (rc < 0)
-		return SMC_CLC_DECL_TCL;
+		return SMC_CLC_DECL_TIMEOUT_AL;
 
 	/* receive ADD LINK response from client over the RoCE fabric */
 	rest = wait_for_completion_interruptible_timeout(&link->llc_add_resp,
@@ -1048,7 +1049,8 @@ static void smc_listen_decline(struct smc_sock *new_smc, int reason_code,
 	}
 	smc_conn_free(&new_smc->conn);
 	new_smc->use_fallback = true;
-	if (reason_code && reason_code != SMC_CLC_DECL_REPLY) {
+	new_smc->fallback_rsn = reason_code;
+	if (reason_code && reason_code != SMC_CLC_DECL_PEERDECL) {
 		if (smc_clc_send_decline(new_smc, reason_code) < 0) {
 			smc_listen_out_err(new_smc);
 			return;
@@ -1139,7 +1141,7 @@ static int smc_listen_rdma_reg(struct smc_sock *new_smc, int local_contact)
 	if (local_contact != SMC_FIRST_CONTACT) {
 		if (!new_smc->conn.rmb_desc->reused) {
 			if (smc_reg_rmb(link, new_smc->conn.rmb_desc, true))
-				return SMC_CLC_DECL_INTERR;
+				return SMC_CLC_DECL_ERR_REGRMB;
 		}
 	}
 	smc_rmb_sync_sg_for_device(&new_smc->conn);
@@ -1159,13 +1161,13 @@ static void smc_listen_rdma_finish(struct smc_sock *new_smc,
 		smc_link_save_peer_info(link, cclc);
 
 	if (smc_rmb_rtoken_handling(&new_smc->conn, cclc)) {
-		reason_code = SMC_CLC_DECL_INTERR;
+		reason_code = SMC_CLC_DECL_ERR_RTOK;
 		goto decline;
 	}
 
 	if (local_contact == SMC_FIRST_CONTACT) {
 		if (smc_ib_ready_link(link)) {
-			reason_code = SMC_CLC_DECL_INTERR;
+			reason_code = SMC_CLC_DECL_ERR_RDYLNK;
 			goto decline;
 		}
 		/* QP confirmation over RoCE fabric */
@@ -1206,6 +1208,7 @@ static void smc_listen_work(struct work_struct *work)
 	/* check if peer is smc capable */
 	if (!tcp_sk(newclcsock->sk)->syn_smc) {
 		new_smc->use_fallback = true;
+		new_smc->fallback_rsn = SMC_CLC_DECL_PEERNOSMC;
 		smc_listen_out_connected(new_smc);
 		return;
 	}
@@ -1250,7 +1253,8 @@ static void smc_listen_work(struct work_struct *work)
 	     smc_listen_rdma_reg(new_smc, local_contact))) {
 		/* SMC not supported, decline */
 		mutex_unlock(&smc_create_lgr_pending);
-		smc_listen_decline(new_smc, SMC_CLC_DECL_CNFERR, local_contact);
+		smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP,
+				   local_contact);
 		return;
 	}
 
@@ -1297,6 +1301,7 @@ static void smc_tcp_listen_work(struct work_struct *work)
 
 		new_smc->listen_smc = lsmc;
 		new_smc->use_fallback = lsmc->use_fallback;
+		new_smc->fallback_rsn = lsmc->fallback_rsn;
 		sock_hold(lsk); /* sock_put in smc_listen_work */
 		INIT_WORK(&new_smc->smc_listen_work, smc_listen_work);
 		smc_copy_sock_settings_to_smc(new_smc);
@@ -1451,6 +1456,7 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	if (msg->msg_flags & MSG_FASTOPEN) {
 		if (sk->sk_state == SMC_INIT) {
 			smc->use_fallback = true;
+			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
 			rc = -EINVAL;
 			goto out;
@@ -1648,6 +1654,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname,
 		/* option not supported by SMC */
 		if (sk->sk_state == SMC_INIT) {
 			smc->use_fallback = true;
+			smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP;
 		} else {
 			if (!smc->use_fallback)
 				rc = -EINVAL;
@@ -1885,6 +1892,7 @@ static int smc_create(struct net *net, struct socket *sock, int protocol,
 	/* create internal TCP socket for CLC handshake and fallback */
 	smc = smc_sk(sk);
 	smc->use_fallback = false; /* assume rdma capability first */
+	smc->fallback_rsn = 0;
 	rc = sock_create_kern(net, family, SOCK_STREAM, IPPROTO_TCP,
 			      &smc->clcsock);
 	if (rc) {
diff --git a/net/smc/smc.h b/net/smc/smc.h
index be20acd7b5ab..08786ace6010 100644
--- a/net/smc/smc.h
+++ b/net/smc/smc.h
@@ -208,6 +208,8 @@ struct smc_sock {				/* smc sock container */
 	struct list_head	accept_q;	/* sockets to be accepted */
 	spinlock_t		accept_q_lock;	/* protects accept_q */
 	bool			use_fallback;	/* fallback to tcp */
+	int			fallback_rsn;	/* reason for fallback */
+	u32			peer_diagnosis; /* decline reason from peer */
 	int			sockopt_defer_accept;
 						/* sockopt TCP_DEFER_ACCEPT
 						 * value
diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c
index 78d74938a9d9..83aba9ade060 100644
--- a/net/smc/smc_clc.c
+++ b/net/smc/smc_clc.c
@@ -334,7 +334,11 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		goto out;
 	}
 	if (clcm->type == SMC_CLC_DECLINE) {
-		reason_code = SMC_CLC_DECL_REPLY;
+		struct smc_clc_msg_decline *dclc;
+
+		dclc = (struct smc_clc_msg_decline *)clcm;
+		reason_code = SMC_CLC_DECL_PEERDECL;
+		smc->peer_diagnosis = ntohl(dclc->peer_diagnosis);
 		if (((struct smc_clc_msg_decline *)buf)->hdr.flag) {
 			smc->conn.lgr->sync_err = 1;
 			smc_lgr_terminate(smc->conn.lgr);
diff --git a/net/smc/smc_clc.h b/net/smc/smc_clc.h
index 6bdc63352d6a..18da89b681c2 100644
--- a/net/smc/smc_clc.h
+++ b/net/smc/smc_clc.h
@@ -28,15 +28,21 @@
 #define SMC_TYPE_B		3		/* SMC-R and SMC-D	      */
 #define CLC_WAIT_TIME		(6 * HZ)	/* max. wait time on clcsock  */
 #define SMC_CLC_DECL_MEM	0x01010000  /* insufficient memory resources  */
-#define SMC_CLC_DECL_TIMEOUT	0x02000000  /* timeout                        */
+#define SMC_CLC_DECL_TIMEOUT_CL	0x02010000  /* timeout w4 QP confirm link     */
+#define SMC_CLC_DECL_TIMEOUT_AL	0x02020000  /* timeout w4 QP add link	      */
 #define SMC_CLC_DECL_CNFERR	0x03000000  /* configuration error            */
-#define SMC_CLC_DECL_IPSEC	0x03030000  /* IPsec usage                    */
+#define SMC_CLC_DECL_PEERNOSMC	0x03010000  /* peer did not indicate SMC      */
+#define SMC_CLC_DECL_IPSEC	0x03020000  /* IPsec usage		      */
+#define SMC_CLC_DECL_NOSMCDEV	0x03030000  /* no SMC device found	      */
+#define SMC_CLC_DECL_MODEUNSUPP	0x03040000  /* smc modes do not match (R or D)*/
+#define SMC_CLC_DECL_RMBE_EC	0x03050000  /* peer has eyecatcher in RMBE    */
+#define SMC_CLC_DECL_OPTUNSUPP	0x03060000  /* fastopen sockopt not supported */
 #define SMC_CLC_DECL_SYNCERR	0x04000000  /* synchronization error          */
-#define SMC_CLC_DECL_REPLY	0x06000000  /* reply to a received decline    */
+#define SMC_CLC_DECL_PEERDECL	0x05000000  /* peer declined during handshake */
 #define SMC_CLC_DECL_INTERR	0x99990000  /* internal error                 */
-#define SMC_CLC_DECL_TCL	0x02040000  /* timeout w4 QP confirm          */
-#define SMC_CLC_DECL_SEND	0x07000000  /* sending problem                */
-#define SMC_CLC_DECL_RMBE_EC	0x08000000  /* peer has eyecatcher in RMBE    */
+#define SMC_CLC_DECL_ERR_RTOK	0x99990001  /*	 rtoken handling failed       */
+#define SMC_CLC_DECL_ERR_RDYLNK	0x99990002  /*	 ib ready link failed	      */
+#define SMC_CLC_DECL_ERR_REGRMB	0x99990003  /*	 reg rmb failed		      */
 
 struct smc_clc_msg_hdr {	/* header1 of clc messages */
 	u8 eyecatcher[4];	/* eye catcher */
diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c
index a3cf7313a2d3..dbf64a93d68a 100644
--- a/net/smc/smc_diag.c
+++ b/net/smc/smc_diag.c
@@ -79,6 +79,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 			   struct nlattr *bc)
 {
 	struct smc_sock *smc = smc_sk(sk);
+	struct smc_diag_fallback fallback;
 	struct user_namespace *user_ns;
 	struct smc_diag_msg *r;
 	struct nlmsghdr *nlh;
@@ -101,6 +102,11 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 	if (smc_diag_msg_attrs_fill(sk, skb, r, user_ns))
 		goto errout;
 
+	fallback.reason = smc->fallback_rsn;
+	fallback.peer_diagnosis = smc->peer_diagnosis;
+	if (nla_put(skb, SMC_DIAG_FALLBACK, sizeof(fallback), &fallback) < 0)
+		goto errout;
+
 	if ((req->diag_ext & (1 << (SMC_DIAG_CONNINFO - 1))) &&
 	    smc->conn.alert_token_local) {
 		struct smc_connection *conn = &smc->conn;
-- 
cgit v1.2.3


From 0d18a0cb4b1585d9e5a3b300d5df9ed866561ffb Mon Sep 17 00:00:00 2001
From: Karsten Graul <kgraul@linux.ibm.com>
Date: Wed, 25 Jul 2018 16:35:33 +0200
Subject: net/smc: improve delete link processing

Send an orderly DELETE LINK request before termination of a link group,
add support for client triggered DELETE LINK processing. And send a
disorderly DELETE LINK before module is unloaded.

Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_core.c | 47 ++++++++++++++++++++++++++++++++++++++++++-----
 net/smc/smc_core.h |  4 +++-
 net/smc/smc_llc.c  | 30 +++++++++++++++++++-----------
 net/smc/smc_llc.h  |  3 ++-
 net/smc/smc_wr.c   |  7 ++-----
 5 files changed, 68 insertions(+), 23 deletions(-)

diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
index 90c10ae9ae09..a46418f45ecd 100644
--- a/net/smc/smc_core.c
+++ b/net/smc/smc_core.c
@@ -30,6 +30,7 @@
 #define SMC_LGR_NUM_INCR		256
 #define SMC_LGR_FREE_DELAY_SERV		(600 * HZ)
 #define SMC_LGR_FREE_DELAY_CLNT		(SMC_LGR_FREE_DELAY_SERV + 10 * HZ)
+#define SMC_LGR_FREE_DELAY_FAST		(8 * HZ)
 
 static struct smc_lgr_list smc_lgr_list = {	/* established link groups */
 	.lock = __SPIN_LOCK_UNLOCKED(smc_lgr_list.lock),
@@ -51,6 +52,11 @@ static void smc_lgr_schedule_free_work(struct smc_link_group *lgr)
 			 SMC_LGR_FREE_DELAY_CLNT : SMC_LGR_FREE_DELAY_SERV);
 }
 
+void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr)
+{
+	mod_delayed_work(system_wq, &lgr->free_work, SMC_LGR_FREE_DELAY_FAST);
+}
+
 /* Register connection's alert token in our lookup structure.
  * To use rbtrees we have to implement our own insert core.
  * Requires @conns_lock
@@ -133,6 +139,20 @@ static void smc_lgr_unregister_conn(struct smc_connection *conn)
 	smc_lgr_schedule_free_work(lgr);
 }
 
+/* Send delete link, either as client to request the initiation
+ * of the DELETE LINK sequence from server; or as server to
+ * initiate the delete processing. See smc_llc_rx_delete_link().
+ */
+static int smc_link_send_delete(struct smc_link *lnk)
+{
+	if (lnk->state == SMC_LNK_ACTIVE &&
+	    !smc_llc_send_delete_link(lnk, SMC_LLC_REQ, true)) {
+		smc_llc_link_deleting(lnk);
+		return 0;
+	}
+	return -ENOTCONN;
+}
+
 static void smc_lgr_free_work(struct work_struct *work)
 {
 	struct smc_link_group *lgr = container_of(to_delayed_work(work),
@@ -153,10 +173,21 @@ static void smc_lgr_free_work(struct work_struct *work)
 	list_del_init(&lgr->list); /* remove from smc_lgr_list */
 free:
 	spin_unlock_bh(&smc_lgr_list.lock);
+
+	if (!lgr->is_smcd && !lgr->terminating)	{
+		/* try to send del link msg, on error free lgr immediately */
+		if (!smc_link_send_delete(&lgr->lnk[SMC_SINGLE_LINK])) {
+			/* reschedule in case we never receive a response */
+			smc_lgr_schedule_free_work(lgr);
+			return;
+		}
+	}
+
 	if (!delayed_work_pending(&lgr->free_work)) {
-		if (!lgr->is_smcd &&
-		    lgr->lnk[SMC_SINGLE_LINK].state != SMC_LNK_INACTIVE)
-			smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+		struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
+		if (!lgr->is_smcd && lnk->state != SMC_LNK_INACTIVE)
+			smc_llc_link_inactive(lnk);
 		smc_lgr_free(lgr);
 	}
 }
@@ -984,8 +1015,14 @@ void smc_core_exit(void)
 	spin_unlock_bh(&smc_lgr_list.lock);
 	list_for_each_entry_safe(lgr, lg, &lgr_freeing_list, list) {
 		list_del_init(&lgr->list);
-		if (!lgr->is_smcd)
-			smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]);
+		if (!lgr->is_smcd) {
+			struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
+
+			if (lnk->state == SMC_LNK_ACTIVE)
+				smc_llc_send_delete_link(lnk, SMC_LLC_REQ,
+							 false);
+			smc_llc_link_inactive(lnk);
+		}
 		cancel_delayed_work_sync(&lgr->free_work);
 		smc_lgr_free(lgr); /* free link group */
 	}
diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h
index a4f0cc4e0270..c156674733c9 100644
--- a/net/smc/smc_core.h
+++ b/net/smc/smc_core.h
@@ -34,7 +34,8 @@ enum smc_lgr_role {		/* possible roles of a link group */
 enum smc_link_state {			/* possible states of a link */
 	SMC_LNK_INACTIVE,	/* link is inactive */
 	SMC_LNK_ACTIVATING,	/* link is being activated */
-	SMC_LNK_ACTIVE		/* link is active */
+	SMC_LNK_ACTIVE,		/* link is active */
+	SMC_LNK_DELETING,	/* link is being deleted */
 };
 
 #define SMC_WR_BUF_SIZE		48	/* size of work request buffer */
@@ -265,6 +266,7 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 		    struct smc_clc_msg_local *lcl, struct smcd_dev *smcd,
 		    u64 peer_gid);
 void smcd_conn_free(struct smc_connection *conn);
+void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
 void smc_core_exit(void);
 
 static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c
index a88c01029fa6..9c916c709ca7 100644
--- a/net/smc/smc_llc.c
+++ b/net/smc/smc_llc.c
@@ -278,7 +278,7 @@ int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
 /* prepare a delete link message */
 static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc,
 				     struct smc_link *link,
-				     enum smc_llc_reqresp reqresp)
+				     enum smc_llc_reqresp reqresp, bool orderly)
 {
 	memset(delllc, 0, sizeof(*delllc));
 	delllc->hd.common.type = SMC_LLC_DELETE_LINK;
@@ -287,13 +287,14 @@ static void smc_llc_prep_delete_link(struct smc_llc_msg_del_link *delllc,
 		delllc->hd.flags |= SMC_LLC_FLAG_RESP;
 	/* DEL_LINK_ALL because only 1 link supported */
 	delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ALL;
-	delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
+	if (orderly)
+		delllc->hd.flags |= SMC_LLC_FLAG_DEL_LINK_ORDERLY;
 	delllc->link_num = link->link_id;
 }
 
 /* send DELETE LINK request or response */
 int smc_llc_send_delete_link(struct smc_link *link,
-			     enum smc_llc_reqresp reqresp)
+			     enum smc_llc_reqresp reqresp, bool orderly)
 {
 	struct smc_llc_msg_del_link *delllc;
 	struct smc_wr_tx_pend_priv *pend;
@@ -304,7 +305,7 @@ int smc_llc_send_delete_link(struct smc_link *link,
 	if (rc)
 		return rc;
 	delllc = (struct smc_llc_msg_del_link *)wr_buf;
-	smc_llc_prep_delete_link(delllc, link, reqresp);
+	smc_llc_prep_delete_link(delllc, link, reqresp, orderly);
 	/* send llc message */
 	rc = smc_wr_tx_send(link, pend);
 	return rc;
@@ -438,17 +439,19 @@ static void smc_llc_rx_delete_link(struct smc_link *link,
 
 	if (llc->hd.flags & SMC_LLC_FLAG_RESP) {
 		if (lgr->role == SMC_SERV)
-			smc_lgr_terminate(lgr);
+			smc_lgr_schedule_free_work_fast(lgr);
 	} else {
+		smc_lgr_forget(lgr);
+		smc_llc_link_deleting(link);
 		if (lgr->role == SMC_SERV) {
-			smc_lgr_forget(lgr);
-			smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ);
-			smc_llc_send_message(link, llc, sizeof(*llc));
+			/* client asks to delete this link, send request */
+			smc_llc_prep_delete_link(llc, link, SMC_LLC_REQ, true);
 		} else {
-			smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP);
-			smc_llc_send_message(link, llc, sizeof(*llc));
-			smc_lgr_terminate(lgr);
+			/* server requests to delete this link, send response */
+			smc_llc_prep_delete_link(llc, link, SMC_LLC_RESP, true);
 		}
+		smc_llc_send_message(link, llc, sizeof(*llc));
+		smc_lgr_schedule_free_work_fast(lgr);
 	}
 }
 
@@ -622,6 +625,11 @@ void smc_llc_link_active(struct smc_link *link, int testlink_time)
 	}
 }
 
+void smc_llc_link_deleting(struct smc_link *link)
+{
+	link->state = SMC_LNK_DELETING;
+}
+
 /* called in tasklet context */
 void smc_llc_link_inactive(struct smc_link *link)
 {
diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h
index 95a7f3662e59..9e2ff088e301 100644
--- a/net/smc/smc_llc.h
+++ b/net/smc/smc_llc.h
@@ -41,9 +41,10 @@ int smc_llc_send_confirm_link(struct smc_link *lnk,
 int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
 			  enum smc_llc_reqresp reqresp);
 int smc_llc_send_delete_link(struct smc_link *link,
-			     enum smc_llc_reqresp reqresp);
+			     enum smc_llc_reqresp reqresp, bool orderly);
 int smc_llc_link_init(struct smc_link *link);
 void smc_llc_link_active(struct smc_link *link, int testlink_time);
+void smc_llc_link_deleting(struct smc_link *link);
 void smc_llc_link_inactive(struct smc_link *link);
 void smc_llc_link_clear(struct smc_link *link);
 int smc_llc_do_confirm_rkey(struct smc_link *link,
diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index b6df69756bef..f856b8402b3f 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -182,17 +182,14 @@ int smc_wr_tx_get_free_slot(struct smc_link *link,
 		if (rc)
 			return rc;
 	} else {
-		struct smc_link_group *lgr;
-
-		lgr = smc_get_lgr(link);
 		rc = wait_event_timeout(
 			link->wr_tx_wait,
-			list_empty(&lgr->list) || /* lgr terminated */
+			link->state == SMC_LNK_INACTIVE ||
 			(smc_wr_tx_get_free_slot_index(link, &idx) != -EBUSY),
 			SMC_WR_TX_WAIT_FREE_SLOT_TIME);
 		if (!rc) {
 			/* timeout - terminate connections */
-			smc_lgr_terminate(lgr);
+			smc_lgr_terminate(smc_get_lgr(link));
 			return -EPIPE;
 		}
 		if (idx == link->wr_tx_cnt)
-- 
cgit v1.2.3


From ba7d7e2677c0953b251c36588b15f5f442e59c84 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Thu, 26 Jul 2018 00:20:08 +0200
Subject: net/rds/Kconfig: RDS should depend on IPV6
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Build error, implicit declaration of function __inet6_ehashfn shows up
When RDS is enabled but not IPV6.
net/rds/connection.c: In function ‘rds_conn_bucket’:
net/rds/connection.c:67:9: error: implicit declaration of function ‘__inet6_ehashfn’; did you mean ‘__inet_ehashfn’? [-Werror=implicit-function-declaration]
  hash = __inet6_ehashfn(lhash, 0, fhash, 0, rds_hash_secret);
         ^~~~~~~~~~~~~~~
         __inet_ehashfn

Current code adds IPV6 as a depends on in config RDS.

Fixes: eee2fa6ab322 ("rds: Changing IP address internal representation to struct in6_addr")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index 41f75563b54b..607128f10bcd 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -1,7 +1,7 @@
 
 config RDS
 	tristate "The RDS Protocol"
-	depends on INET
+	depends on INET && CONFIG_IPV6
 	---help---
 	  The RDS (Reliable Datagram Sockets) protocol provides reliable,
 	  sequenced delivery of datagrams over Infiniband or TCP.
-- 
cgit v1.2.3


From dc66fe43b7ebdb53628dcbc1f8f15de3e000aacf Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 25 Jul 2018 10:22:27 -0500
Subject: rds: send: Fix dead code in rds_sendmsg

Currently, code at label *out* is unreachable. Fix this by updating
variable *ret* with -EINVAL, so the jump to *out* can be properly
executed instead of directly returning from function.

Addresses-Coverity-ID: 1472059 ("Structurally dead code")
Fixes: 1e2b44e78eea ("rds: Enable RDS IPv6 support")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/send.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/send.c b/net/rds/send.c
index 9604e1faa564..18e2b4d3931f 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1126,7 +1126,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 				if (addr4 == htonl(INADDR_ANY) ||
 				    addr4 == htonl(INADDR_BROADCAST) ||
 				    IN_MULTICAST(ntohl(addr4))) {
-					return -EINVAL;
+					ret = -EINVAL;
 					goto out;
 				}
 			}
-- 
cgit v1.2.3


From a49a71f6e25da2acc637fcd31e73debd96ca18f8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 16:34:12 +0200
Subject: ALSA: seq: Fix poll() error return

The sanity checks in ALSA sequencer and OSS sequencer emulation codes
return falsely -ENXIO from poll callback.  They should be EPOLLERR
instead.

This was caught thanks to the recent change to the return value.

Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/oss/seq_oss.c   | 2 +-
 sound/core/seq/seq_clientmgr.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/core/seq/oss/seq_oss.c b/sound/core/seq/oss/seq_oss.c
index 5f64d0d88320..e1f44fc86885 100644
--- a/sound/core/seq/oss/seq_oss.c
+++ b/sound/core/seq/oss/seq_oss.c
@@ -203,7 +203,7 @@ odev_poll(struct file *file, poll_table * wait)
 	struct seq_oss_devinfo *dp;
 	dp = file->private_data;
 	if (snd_BUG_ON(!dp))
-		return -ENXIO;
+		return EPOLLERR;
 	return snd_seq_oss_poll(dp, file, wait);
 }
 
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 56ca78423040..6fd4b074b206 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -1101,7 +1101,7 @@ static __poll_t snd_seq_poll(struct file *file, poll_table * wait)
 
 	/* check client structures are in place */
 	if (snd_BUG_ON(!client))
-		return -ENXIO;
+		return EPOLLERR;
 
 	if ((snd_seq_file_flags(file) & SNDRV_SEQ_LFLG_INPUT) &&
 	    client->data.user.fifo) {
-- 
cgit v1.2.3


From fff71a4c050ba46e305d910c837b99ba1728135e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 17:10:11 +0200
Subject: ALSA: vx222: Fix invalid endian conversions

The endian conversions used in vx2_dma_read() and vx2_dma_write() are
superfluous and even wrong on big-endian machines, as inl() and outl()
already do conversions.  Kill them.

Spotted by sparse, a warning like:
  sound/pci/vx222/vx222_ops.c:278:30: warning: incorrect type in argument 1 (different base types)

Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/vx222/vx222_ops.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/pci/vx222/vx222_ops.c b/sound/pci/vx222/vx222_ops.c
index d4298af6d3ee..c0d0bf44f365 100644
--- a/sound/pci/vx222/vx222_ops.c
+++ b/sound/pci/vx222/vx222_ops.c
@@ -275,7 +275,7 @@ static void vx2_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 2; /* in 32bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--) {
-			outl(cpu_to_le32(*addr), port);
+			outl(*addr, port);
 			addr++;
 		}
 		addr = (u32 *)runtime->dma_area;
@@ -285,7 +285,7 @@ static void vx2_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 2; /* in 32bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 0; count--) {
-		outl(cpu_to_le32(*addr), port);
+		outl(*addr, port);
 		addr++;
 	}
 
@@ -313,7 +313,7 @@ static void vx2_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 2; /* in 32bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--)
-			*addr++ = le32_to_cpu(inl(port));
+			*addr++ = inl(port);
 		addr = (u32 *)runtime->dma_area;
 		pipe->hw_ptr = 0;
 	}
@@ -321,7 +321,7 @@ static void vx2_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 2; /* in 32bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 0; count--)
-		*addr++ = le32_to_cpu(inl(port));
+		*addr++ = inl(port);
 
 	vx2_release_pseudo_dma(chip);
 }
-- 
cgit v1.2.3


From 3acd3e3bab95ec3622ff98da313290ee823a0f68 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 17:11:38 +0200
Subject: ALSA: vxpocket: Fix invalid endian conversions

The endian conversions used in vxp_dma_read() and vxp_dma_write() are
superfluous and even wrong on big-endian machines, as inw() and outw()
already do conversions.  Kill them.

Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pcmcia/vx/vxp_ops.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/sound/pcmcia/vx/vxp_ops.c b/sound/pcmcia/vx/vxp_ops.c
index 8cde40226355..4c4ef1fec69f 100644
--- a/sound/pcmcia/vx/vxp_ops.c
+++ b/sound/pcmcia/vx/vxp_ops.c
@@ -375,7 +375,7 @@ static void vxp_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 1; /* in 16bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--) {
-			outw(cpu_to_le16(*addr), port);
+			outw(*addr, port);
 			addr++;
 		}
 		addr = (unsigned short *)runtime->dma_area;
@@ -385,7 +385,7 @@ static void vxp_dma_write(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 1; /* in 16bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 0; count--) {
-		outw(cpu_to_le16(*addr), port);
+		outw(*addr, port);
 		addr++;
 	}
 	vx_release_pseudo_dma(chip);
@@ -417,7 +417,7 @@ static void vxp_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 		length >>= 1; /* in 16bit words */
 		/* Transfer using pseudo-dma. */
 		for (; length > 0; length--)
-			*addr++ = le16_to_cpu(inw(port));
+			*addr++ = inw(port);
 		addr = (unsigned short *)runtime->dma_area;
 		pipe->hw_ptr = 0;
 	}
@@ -425,12 +425,12 @@ static void vxp_dma_read(struct vx_core *chip, struct snd_pcm_runtime *runtime,
 	count >>= 1; /* in 16bit words */
 	/* Transfer using pseudo-dma. */
 	for (; count > 1; count--)
-		*addr++ = le16_to_cpu(inw(port));
+		*addr++ = inw(port);
 	/* Disable DMA */
 	pchip->regDIALOG &= ~VXP_DLG_DMAREAD_SEL_MASK;
 	vx_outb(chip, DIALOG, pchip->regDIALOG);
 	/* Read the last word (16 bits) */
-	*addr = le16_to_cpu(inw(port));
+	*addr = inw(port);
 	/* Disable 16-bit accesses */
 	pchip->regDIALOG &= ~VXP_DLG_DMA16_SEL_MASK;
 	vx_outb(chip, DIALOG, pchip->regDIALOG);
-- 
cgit v1.2.3


From 69756930f2de0457d51db7d505a1e4f40e9fd116 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 17:59:26 +0200
Subject: ALSA: cs5535audio: Fix invalid endian conversion

One place in cs5535audio_build_dma_packets() does an extra conversion
via cpu_to_le32(); namely jmpprd_addr is passed to setup_prd() ops,
which writes the value via cs_writel().  That is, the callback does
the conversion by itself, and we don't need to convert beforehand.

This patch fixes that bogus conversion.

Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/cs5535audio/cs5535audio.h     | 6 +++---
 sound/pci/cs5535audio/cs5535audio_pcm.c | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/sound/pci/cs5535audio/cs5535audio.h b/sound/pci/cs5535audio/cs5535audio.h
index f4fcdf93f3c8..d84620a0c26c 100644
--- a/sound/pci/cs5535audio/cs5535audio.h
+++ b/sound/pci/cs5535audio/cs5535audio.h
@@ -67,9 +67,9 @@ struct cs5535audio_dma_ops {
 };
 
 struct cs5535audio_dma_desc {
-	u32 addr;
-	u16 size;
-	u16 ctlreserved;
+	__le32 addr;
+	__le16 size;
+	__le16 ctlreserved;
 };
 
 struct cs5535audio_dma {
diff --git a/sound/pci/cs5535audio/cs5535audio_pcm.c b/sound/pci/cs5535audio/cs5535audio_pcm.c
index ee7065f6e162..326caec854e1 100644
--- a/sound/pci/cs5535audio/cs5535audio_pcm.c
+++ b/sound/pci/cs5535audio/cs5535audio_pcm.c
@@ -158,8 +158,8 @@ static int cs5535audio_build_dma_packets(struct cs5535audio *cs5535au,
 	lastdesc->addr = cpu_to_le32((u32) dma->desc_buf.addr);
 	lastdesc->size = 0;
 	lastdesc->ctlreserved = cpu_to_le16(PRD_JMP);
-	jmpprd_addr = cpu_to_le32(lastdesc->addr +
-				  (sizeof(struct cs5535audio_dma_desc)*periods));
+	jmpprd_addr = (u32)dma->desc_buf.addr +
+		sizeof(struct cs5535audio_dma_desc) * periods;
 
 	dma->substream = substream;
 	dma->period_bytes = period_bytes;
-- 
cgit v1.2.3


From b080dc5bd0dfc0b33c6cfc31f909c93d5e63c186 Mon Sep 17 00:00:00 2001
From: Jeff Crukley <jcrukley@gmail.com>
Date: Wed, 25 Jul 2018 15:05:01 -0400
Subject: ALSA: usb-audio: Add support for Encore mDSD USB DAC

This patch adds native DSD playback support for the Encore mDSD USB DAC by
specifying the vendor and product ID's

Signed-off-by: Jeff Crukley <jcrukley@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 06ae3f5adf4b..dde87d64bc32 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1373,6 +1373,7 @@ u64 snd_usb_interface_dsd_format_quirks(struct snd_usb_audio *chip,
 			return SNDRV_PCM_FMTBIT_DSD_U32_BE;
 		break;
 
+	case USB_ID(0x16d0, 0x09dd): /* Encore mDSD */
 	case USB_ID(0x0d8c, 0x0316): /* Hegel HD12 DSD */
 	case USB_ID(0x16b0, 0x06b2): /* NuPrime DAC-10 */
 	case USB_ID(0x16d0, 0x0733): /* Furutech ADL Stratos */
-- 
cgit v1.2.3


From bd1cd0eb2ce9141100628d476ead4de485501b29 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:46 +0200
Subject: ALSA: usb-audio: Fix multiple definitions in AU0828_DEVICE() macro

AU0828_DEVICE() macro in quirks-table.h uses USB_DEVICE_VENDOR_SPEC()
for expanding idVendor and idProduct fields.  However, the latter
macro adds also match_flags and bInterfaceClass, which are different
from the values AU0828_DEVICE() macro sets after that.

For fixing them, just expand idVendor and idProduct fields manually in
AU0828_DEVICE().

This fixes sparse warnings like:
  sound/usb/quirks-table.h:2892:1: warning: Initializer entry defined twice

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks-table.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
index 8aac48f9c322..08aa78007020 100644
--- a/sound/usb/quirks-table.h
+++ b/sound/usb/quirks-table.h
@@ -2875,7 +2875,8 @@ YAMAHA_DEVICE(0x7010, "UB99"),
  */
 
 #define AU0828_DEVICE(vid, pid, vname, pname) { \
-	USB_DEVICE_VENDOR_SPEC(vid, pid), \
+	.idVendor = vid, \
+	.idProduct = pid, \
 	.match_flags = USB_DEVICE_ID_MATCH_DEVICE | \
 		       USB_DEVICE_ID_MATCH_INT_CLASS | \
 		       USB_DEVICE_ID_MATCH_INT_SUBCLASS, \
-- 
cgit v1.2.3


From ab647a2d62f70cf45d7c64bf9f1574b8c52406e4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:47 +0200
Subject: ALSA: msnd: Add missing __iomem annotations

The io-mapped buffers used in msnd drivers need __iomem annotations.

This fixes sparse warnings like:
  sound/isa/msnd/msnd_pinnacle.c:172:45: warning: incorrect type in initializer (different address spaces)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/msnd/msnd.c          | 18 +++++++++---------
 sound/isa/msnd/msnd.h          |  2 +-
 sound/isa/msnd/msnd_midi.c     |  2 +-
 sound/isa/msnd/msnd_pinnacle.c |  2 +-
 4 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/sound/isa/msnd/msnd.c b/sound/isa/msnd/msnd.c
index 569897f64fda..7c3203fe4869 100644
--- a/sound/isa/msnd/msnd.c
+++ b/sound/isa/msnd/msnd.c
@@ -54,7 +54,7 @@
 #define LOGNAME			"msnd"
 
 
-void snd_msnd_init_queue(void *base, int start, int size)
+void snd_msnd_init_queue(void __iomem *base, int start, int size)
 {
 	writew(PCTODSP_BASED(start), base + JQS_wStart);
 	writew(PCTODSP_OFFSET(size) - 1, base + JQS_wSize);
@@ -270,7 +270,7 @@ int snd_msnd_DARQ(struct snd_msnd *chip, int bank)
 		udelay(1);
 
 	if (chip->capturePeriods == 2) {
-		void *pDAQ = chip->mappedbase + DARQ_DATA_BUFF +
+		void __iomem *pDAQ = chip->mappedbase + DARQ_DATA_BUFF +
 			     bank * DAQDS__size + DAQDS_wStart;
 		unsigned short offset = 0x3000 + chip->capturePeriodBytes;
 
@@ -309,7 +309,7 @@ int snd_msnd_DAPQ(struct snd_msnd *chip, int start)
 {
 	u16	DAPQ_tail;
 	int	protect = start, nbanks = 0;
-	void	*DAQD;
+	void	__iomem *DAQD;
 	static int play_banks_submitted;
 	/* unsigned long flags;
 	spin_lock_irqsave(&chip->lock, flags); not necessary */
@@ -370,7 +370,7 @@ static void snd_msnd_play_reset_queue(struct snd_msnd *chip,
 				      unsigned int pcm_count)
 {
 	int	n;
-	void	*pDAQ = chip->mappedbase + DAPQ_DATA_BUFF;
+	void	__iomem *pDAQ = chip->mappedbase + DAPQ_DATA_BUFF;
 
 	chip->last_playbank = -1;
 	chip->playLimit = pcm_count * (pcm_periods - 1);
@@ -398,7 +398,7 @@ static void snd_msnd_capture_reset_queue(struct snd_msnd *chip,
 					 unsigned int pcm_count)
 {
 	int		n;
-	void		*pDAQ;
+	void		__iomem *pDAQ;
 	/* unsigned long	flags; */
 
 	/* snd_msnd_init_queue(chip->DARQ, DARQ_DATA_BUFF, DARQ_BUFF_SIZE); */
@@ -485,7 +485,7 @@ static int snd_msnd_playback_open(struct snd_pcm_substream *substream)
 	clear_bit(F_WRITING, &chip->flags);
 	snd_msnd_enable_irq(chip);
 
-	runtime->dma_area = chip->mappedbase;
+	runtime->dma_area = (__force void *)chip->mappedbase;
 	runtime->dma_bytes = 0x3000;
 
 	chip->playback_substream = substream;
@@ -508,7 +508,7 @@ static int snd_msnd_playback_hw_params(struct snd_pcm_substream *substream,
 {
 	int	i;
 	struct snd_msnd *chip = snd_pcm_substream_chip(substream);
-	void	*pDAQ =	chip->mappedbase + DAPQ_DATA_BUFF;
+	void	__iomem *pDAQ =	chip->mappedbase + DAPQ_DATA_BUFF;
 
 	chip->play_sample_size = snd_pcm_format_width(params_format(params));
 	chip->play_channels = params_channels(params);
@@ -589,7 +589,7 @@ static int snd_msnd_capture_open(struct snd_pcm_substream *substream)
 
 	set_bit(F_AUDIO_READ_INUSE, &chip->flags);
 	snd_msnd_enable_irq(chip);
-	runtime->dma_area = chip->mappedbase + 0x3000;
+	runtime->dma_area = (__force void *)chip->mappedbase + 0x3000;
 	runtime->dma_bytes = 0x3000;
 	memset(runtime->dma_area, 0, runtime->dma_bytes);
 	chip->capture_substream = substream;
@@ -654,7 +654,7 @@ static int snd_msnd_capture_hw_params(struct snd_pcm_substream *substream,
 {
 	int		i;
 	struct snd_msnd *chip = snd_pcm_substream_chip(substream);
-	void		*pDAQ = chip->mappedbase + DARQ_DATA_BUFF;
+	void		__iomem *pDAQ = chip->mappedbase + DARQ_DATA_BUFF;
 
 	chip->capture_sample_size = snd_pcm_format_width(params_format(params));
 	chip->capture_channels = params_channels(params);
diff --git a/sound/isa/msnd/msnd.h b/sound/isa/msnd/msnd.h
index 5f3c7dcd9f9d..80c718757eef 100644
--- a/sound/isa/msnd/msnd.h
+++ b/sound/isa/msnd/msnd.h
@@ -283,7 +283,7 @@ struct snd_msnd {
 
 };
 
-void snd_msnd_init_queue(void *base, int start, int size);
+void snd_msnd_init_queue(void __iomem *base, int start, int size);
 
 int snd_msnd_send_dsp_cmd(struct snd_msnd *chip, u8 cmd);
 int snd_msnd_send_word(struct snd_msnd *chip,
diff --git a/sound/isa/msnd/msnd_midi.c b/sound/isa/msnd/msnd_midi.c
index 013d8d1170fe..42876b0cb68b 100644
--- a/sound/isa/msnd/msnd_midi.c
+++ b/sound/isa/msnd/msnd_midi.c
@@ -119,7 +119,7 @@ void snd_msndmidi_input_read(void *mpuv)
 {
 	unsigned long flags;
 	struct snd_msndmidi *mpu = mpuv;
-	void *pwMIDQData = mpu->dev->mappedbase + MIDQ_DATA_BUFF;
+	void __iomem *pwMIDQData = mpu->dev->mappedbase + MIDQ_DATA_BUFF;
 	u16 head, tail, size;
 
 	spin_lock_irqsave(&mpu->input_lock, flags);
diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index 6c584d9b6c42..642609f7eda9 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -169,7 +169,7 @@ static void snd_msnd_eval_dsp_msg(struct snd_msnd *chip, u16 wMessage)
 static irqreturn_t snd_msnd_interrupt(int irq, void *dev_id)
 {
 	struct snd_msnd *chip = dev_id;
-	void *pwDSPQData = chip->mappedbase + DSPQ_DATA_BUFF;
+	void __iomem *pwDSPQData = chip->mappedbase + DSPQ_DATA_BUFF;
 	u16 head, tail, size;
 
 	/* Send ack to DSP */
-- 
cgit v1.2.3


From 7c500f9ea139d0c9b80fdea5a9c911db3166ea54 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:48 +0200
Subject: ALSA: msnd: Fix the default sample sizes

The default sample sizes set by msnd driver are bogus; it sets ALSA
PCM format, not the actual bit width.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/msnd/msnd_pinnacle.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index 642609f7eda9..7e3f52c8a6c6 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -82,10 +82,10 @@
 
 static void set_default_audio_parameters(struct snd_msnd *chip)
 {
-	chip->play_sample_size = DEFSAMPLESIZE;
+	chip->play_sample_size = snd_pcm_format_width(DEFSAMPLESIZE);
 	chip->play_sample_rate = DEFSAMPLERATE;
 	chip->play_channels = DEFCHANNELS;
-	chip->capture_sample_size = DEFSAMPLESIZE;
+	chip->capture_sample_size = snd_pcm_format_width(DEFSAMPLESIZE);
 	chip->capture_sample_rate = DEFSAMPLERATE;
 	chip->capture_channels = DEFCHANNELS;
 }
-- 
cgit v1.2.3


From bb86124c80780d9d2a2d9bef7f0840e61007ebb7 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:49 +0200
Subject: ALSA: hda/ca0132 - Use NULL instead of 0

Use NULL for initializing the snd_kcontrol_new.tlv field, instead of
0, as warned by sparse:
  sound/pci/hda/patch_ca0132.c:5519:22: warning: Using plain integer as NULL pointer

Also, the driver does the same initialization twice, once for
knew.tlv.c and another for knew.tlv.p while both point to the same
address (these are union).  Drop the latter superfluous one.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 321e95c409c1..27d3388cd2a2 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -5516,8 +5516,7 @@ static int ca0132_alt_add_effect_slider(struct hda_codec *codec, hda_nid_t nid,
 
 	sprintf(namestr, "FX: %s %s Volume", pfx, dirstr[dir]);
 
-	knew.tlv.c = 0;
-	knew.tlv.p = 0;
+	knew.tlv.c = NULL;
 
 	switch (nid) {
 	case XBASS_XOVER:
-- 
cgit v1.2.3


From dcda6f7853c52c42d242b474bfbd1d17d02c8870 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:50 +0200
Subject: ALSA: msnd: Use NULL instead of 0

Fix a sparse warning:
  sound/isa/msnd/msnd_pinnacle.c:813:1: warning: Using plain integer as NULL pointer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/msnd/msnd_pinnacle.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/isa/msnd/msnd_pinnacle.c b/sound/isa/msnd/msnd_pinnacle.c
index 7e3f52c8a6c6..11af9c40bc05 100644
--- a/sound/isa/msnd/msnd_pinnacle.c
+++ b/sound/isa/msnd/msnd_pinnacle.c
@@ -810,7 +810,7 @@ module_param(calibrate_signal, int, 0444);
 #ifndef MSND_CLASSIC
 module_param_array(digital, int, NULL, 0444);
 module_param_hw_array(cfg, long, ioport, NULL, 0444);
-module_param_array(reset, int, 0, 0444);
+module_param_array(reset, int, NULL, 0444);
 module_param_hw_array(mpu_io, long, ioport, NULL, 0444);
 module_param_hw_array(mpu_irq, int, irq, NULL, 0444);
 module_param_hw_array(ide_io0, long, ioport, NULL, 0444);
-- 
cgit v1.2.3


From ebd836edfc4324da016ce0c09f809f882a133f50 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:51 +0200
Subject: ALSA: hda - Fix a sparse warning about snd_ctl_elem_iface_t

The knew->iface field is in snd_ctl_elem_iface_t, which is with
__bitwise, hence it can't be converted implicitly from integer.
Give an explicit cast for the invalid type.

Spotted by sparse:
  sound/pci/hda/hda_codec.c:3280:25: warning: restricted snd_ctl_elem_iface_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_codec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/hda_codec.c b/sound/pci/hda/hda_codec.c
index 6d0c0b143270..0a5085537034 100644
--- a/sound/pci/hda/hda_codec.c
+++ b/sound/pci/hda/hda_codec.c
@@ -3277,8 +3277,8 @@ int snd_hda_add_new_ctls(struct hda_codec *codec,
 	for (; knew->name; knew++) {
 		struct snd_kcontrol *kctl;
 		int addr = 0, idx = 0;
-		if (knew->iface == -1)	/* skip this codec private value */
-			continue;
+		if (knew->iface == (__force snd_ctl_elem_iface_t)-1)
+			continue; /* skip this codec private value */
 		for (;;) {
 			kctl = snd_ctl_new1(knew, codec);
 			if (!kctl)
-- 
cgit v1.2.3


From 7e9c20f40304a16d5f69dbdc44a551cc48252266 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:52 +0200
Subject: ALSA: opl3: Declare common variables properly

Move the declarations of common variables into opl3_voice.h instead of
declaring at each file multiple times, which was error-prone.

This fixes sparse warnings like:
  sound/drivers/opl3/opl3_synth.c:51:6: warning: symbol 'snd_opl3_regmap' was not declared. Should it be static?

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/drivers/opl3/opl3_drums.c | 2 --
 sound/drivers/opl3/opl3_lib.c   | 3 +--
 sound/drivers/opl3/opl3_midi.c  | 4 ----
 sound/drivers/opl3/opl3_oss.c   | 2 --
 sound/drivers/opl3/opl3_synth.c | 1 +
 sound/drivers/opl3/opl3_voice.h | 4 ++++
 6 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/sound/drivers/opl3/opl3_drums.c b/sound/drivers/opl3/opl3_drums.c
index 73694380734a..14929822956c 100644
--- a/sound/drivers/opl3/opl3_drums.c
+++ b/sound/drivers/opl3/opl3_drums.c
@@ -21,8 +21,6 @@
 
 #include "opl3_voice.h"
 
-extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
-
 static char snd_opl3_drum_table[47] =
 {
 	OPL3_BASSDRUM_ON,  OPL3_BASSDRUM_ON,  OPL3_HIHAT_ON,	/* 35 - 37 */
diff --git a/sound/drivers/opl3/opl3_lib.c b/sound/drivers/opl3/opl3_lib.c
index 588963d6be28..1a5355b747ec 100644
--- a/sound/drivers/opl3/opl3_lib.c
+++ b/sound/drivers/opl3/opl3_lib.c
@@ -31,13 +31,12 @@
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <sound/minors.h>
+#include "opl3_voice.h"
 
 MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>, Hannu Savolainen 1993-1996, Rob Hooft");
 MODULE_DESCRIPTION("Routines for control of AdLib FM cards (OPL2/OPL3/OPL4 chips)");
 MODULE_LICENSE("GPL");
 
-extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
-
 static void snd_opl2_command(struct snd_opl3 * opl3, unsigned short cmd, unsigned char val)
 {
 	unsigned long flags;
diff --git a/sound/drivers/opl3/opl3_midi.c b/sound/drivers/opl3/opl3_midi.c
index 71cd5a2fbe82..471916ca0b6b 100644
--- a/sound/drivers/opl3/opl3_midi.c
+++ b/sound/drivers/opl3/opl3_midi.c
@@ -25,10 +25,6 @@
 #include "opl3_voice.h"
 #include <sound/asoundef.h>
 
-extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
-
-extern bool use_internal_drums;
-
 static void snd_opl3_note_off_unsafe(void *p, int note, int vel,
 				     struct snd_midi_channel *chan);
 /*
diff --git a/sound/drivers/opl3/opl3_oss.c b/sound/drivers/opl3/opl3_oss.c
index 8a0ce3f43f42..869220ced4ed 100644
--- a/sound/drivers/opl3/opl3_oss.c
+++ b/sound/drivers/opl3/opl3_oss.c
@@ -29,8 +29,6 @@ static int snd_opl3_reset_seq_oss(struct snd_seq_oss_arg *arg);
 
 /* operators */
 
-extern struct snd_midi_op opl3_ops;
-
 static struct snd_seq_oss_callback oss_callback = {
 	.owner = 	THIS_MODULE,
 	.open =		snd_opl3_open_seq_oss,
diff --git a/sound/drivers/opl3/opl3_synth.c b/sound/drivers/opl3/opl3_synth.c
index 42920a243328..d522925fc5c0 100644
--- a/sound/drivers/opl3/opl3_synth.c
+++ b/sound/drivers/opl3/opl3_synth.c
@@ -24,6 +24,7 @@
 #include <linux/nospec.h>
 #include <sound/opl3.h>
 #include <sound/asound_fm.h>
+#include "opl3_voice.h"
 
 #if IS_ENABLED(CONFIG_SND_SEQUENCER)
 #define OPL3_SUPPORT_SYNTH
diff --git a/sound/drivers/opl3/opl3_voice.h b/sound/drivers/opl3/opl3_voice.h
index a2445163008e..5b02bd49fde4 100644
--- a/sound/drivers/opl3/opl3_voice.h
+++ b/sound/drivers/opl3/opl3_voice.h
@@ -52,4 +52,8 @@ void snd_opl3_free_seq_oss(struct snd_opl3 *opl3);
 #define snd_opl3_free_seq_oss(opl3) /* NOP */
 #endif
 
+extern char snd_opl3_regmap[MAX_OPL2_VOICES][4];
+extern bool use_internal_drums;
+extern struct snd_midi_op opl3_ops;
+
 #endif
-- 
cgit v1.2.3


From 00966dcdf0e324e10ab79d505732c339f72417d9 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:53 +0200
Subject: ALSA: usb-audio: Declare the common variable in header file

Declare snd_usb_feature_unit_ctl properly in mixer.h.  Otherwise it's
error-prone.

This fixes the sparse warning:
  sound/usb/mixer.c:1464:25: warning: symbol 'snd_usb_feature_unit_ctl' was not declared. Should it be static?

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer.h        | 2 ++
 sound/usb/mixer_quirks.c | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/usb/mixer.h b/sound/usb/mixer.h
index e02653465e29..3d12af8bf191 100644
--- a/sound/usb/mixer.h
+++ b/sound/usb/mixer.h
@@ -109,4 +109,6 @@ int snd_usb_get_cur_mix_value(struct usb_mixer_elem_info *cval,
 
 extern void snd_usb_mixer_elem_free(struct snd_kcontrol *kctl);
 
+extern struct snd_kcontrol_new *snd_usb_feature_unit_ctl;
+
 #endif /* __USBMIXER_H */
diff --git a/sound/usb/mixer_quirks.c b/sound/usb/mixer_quirks.c
index e82a72fea9a1..cbfb48bdea51 100644
--- a/sound/usb/mixer_quirks.c
+++ b/sound/usb/mixer_quirks.c
@@ -47,8 +47,6 @@
 #include "mixer_us16x08.h"
 #include "helper.h"
 
-extern struct snd_kcontrol_new *snd_usb_feature_unit_ctl;
-
 struct std_mono_table {
 	unsigned int unitid, control, cmask;
 	int val_type;
-- 
cgit v1.2.3


From 95a48b7d4459948b6bacf809809cf01a7dc06d1d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:54 +0200
Subject: ALSA: pcm: Add __force to cast in snd_pcm_lib_read/write()

The snd_pcm_lib_read() and snd_pcm_lib_write() inline functions have
the explicit cast from a user pointer to a kernel pointer, but they
lacks of __force prefix.

This fixes sparse warnings like:
  ./include/sound/pcm.h:1093:47: warning: cast removes address space of expression

Fixes: 68541213720d ("ALSA: pcm: Direct in-kernel read/write support")
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/pcm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/sound/pcm.h b/include/sound/pcm.h
index 1206045ccf03..d6bd3caf6878 100644
--- a/include/sound/pcm.h
+++ b/include/sound/pcm.h
@@ -1090,14 +1090,14 @@ static inline snd_pcm_sframes_t
 snd_pcm_lib_write(struct snd_pcm_substream *substream,
 		  const void __user *buf, snd_pcm_uframes_t frames)
 {
-	return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, false);
+	return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false);
 }
 
 static inline snd_pcm_sframes_t
 snd_pcm_lib_read(struct snd_pcm_substream *substream,
 		 void __user *buf, snd_pcm_uframes_t frames)
 {
-	return __snd_pcm_lib_xfer(substream, (void *)buf, true, frames, false);
+	return __snd_pcm_lib_xfer(substream, (void __force *)buf, true, frames, false);
 }
 
 static inline snd_pcm_sframes_t
-- 
cgit v1.2.3


From 191bb51e72c3b2b1ed1b2bd7ac30dd9f7ccea306 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:55 +0200
Subject: ALSA: pcm: Use standard lower_32_bits() and upper_32_bits()

Instead of open codes, use the standard macros for obtaining the lower
and upper 32bit values.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/oss/pcm_plugin.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c
index 85a56af104bd..85bab922ce69 100644
--- a/sound/core/oss/pcm_plugin.c
+++ b/sound/core/oss/pcm_plugin.c
@@ -281,10 +281,10 @@ static int snd_pcm_plug_formats(const struct snd_mask *mask,
 		       SNDRV_PCM_FMTBIT_U32_BE | SNDRV_PCM_FMTBIT_S32_BE);
 	snd_mask_set(&formats, (__force int)SNDRV_PCM_FORMAT_MU_LAW);
 	
-	if (formats.bits[0] & (u32)linfmts)
-		formats.bits[0] |= (u32)linfmts;
-	if (formats.bits[1] & (u32)(linfmts >> 32))
-		formats.bits[1] |= (u32)(linfmts >> 32);
+	if (formats.bits[0] & lower_32_bits(linfmts))
+		formats.bits[0] |= lower_32_bits(linfmts);
+	if (formats.bits[1] & upper_32_bits(linfmts))
+		formats.bits[1] |= upper_32_bits(linfmts);
 	return snd_mask_test(&formats, (__force int)format);
 }
 
-- 
cgit v1.2.3


From 0701492c86ac0446a834da35ef4991bcf8adb6c4 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:56 +0200
Subject: ALSA: korg1212: Add __force annotation to cast in user-copy callbacks

The user-copy callbacks in korg1212 driver contain the explicit cast
from a user pointer to a kernel pointer, but they missed __force
prefix.  It's mandatory for converting between them.

Spotted by sparse, a warning like:
  sound/pci/korg1212/korg1212.c:1329:33: warning: cast removes address space of expression

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/korg1212/korg1212.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/korg1212/korg1212.c b/sound/pci/korg1212/korg1212.c
index 4206ba44d8bb..4e189a93f475 100644
--- a/sound/pci/korg1212/korg1212.c
+++ b/sound/pci/korg1212/korg1212.c
@@ -1326,7 +1326,7 @@ static int snd_korg1212_copy_to(struct snd_pcm_substream *substream,
 		}
 #endif
 		if (in_kernel)
-			memcpy((void *)dst, src, size);
+			memcpy((__force void *)dst, src, size);
 		else if (copy_to_user(dst, src, size))
 			return -EFAULT;
 		src++;
@@ -1365,7 +1365,7 @@ static int snd_korg1212_copy_from(struct snd_pcm_substream *substream,
 		}
 #endif
 		if (in_kernel)
-			memcpy((void *)dst, src, size);
+			memcpy(dst, (__force void *)src, size);
 		else if (copy_from_user(dst, src, size))
 			return -EFAULT;
 		dst++;
-- 
cgit v1.2.3


From 63623646a06358833766016d8c1fe14d6576b3d0 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:00:57 +0200
Subject: ALSA: emu10k1: Fix missing __force annotation for user/kernel pointer
 cast

The cast between user-space and kernel-space needs an explicit __force
prefix, but it's missing in many places in emu10k1 driver code.

Spotted by sparse as a warning like:
  sound/pci/emu10k1/emufx.c:529:33: warning: cast removes address space of expression

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/emu10k1/emufx.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/sound/pci/emu10k1/emufx.c b/sound/pci/emu10k1/emufx.c
index de2ecbe95d6c..90713741c2dc 100644
--- a/sound/pci/emu10k1/emufx.c
+++ b/sound/pci/emu10k1/emufx.c
@@ -526,7 +526,7 @@ static int snd_emu10k1_gpr_poke(struct snd_emu10k1 *emu,
 		if (!test_bit(gpr, icode->gpr_valid))
 			continue;
 		if (in_kernel)
-			val = *(u32 *)&icode->gpr_map[gpr];
+			val = *(__force u32 *)&icode->gpr_map[gpr];
 		else if (get_user(val, &icode->gpr_map[gpr]))
 			return -EFAULT;
 		snd_emu10k1_ptr_write(emu, emu->gpr_base + gpr, 0, val);
@@ -560,8 +560,8 @@ static int snd_emu10k1_tram_poke(struct snd_emu10k1 *emu,
 		if (!test_bit(tram, icode->tram_valid))
 			continue;
 		if (in_kernel) {
-			val = *(u32 *)&icode->tram_data_map[tram];
-			addr = *(u32 *)&icode->tram_addr_map[tram];
+			val = *(__force u32 *)&icode->tram_data_map[tram];
+			addr = *(__force u32 *)&icode->tram_addr_map[tram];
 		} else {
 			if (get_user(val, &icode->tram_data_map[tram]) ||
 			    get_user(addr, &icode->tram_addr_map[tram]))
@@ -611,8 +611,8 @@ static int snd_emu10k1_code_poke(struct snd_emu10k1 *emu,
 		if (!test_bit(pc / 2, icode->code_valid))
 			continue;
 		if (in_kernel) {
-			lo = *(u32 *)&icode->code[pc + 0];
-			hi = *(u32 *)&icode->code[pc + 1];
+			lo = *(__force u32 *)&icode->code[pc + 0];
+			hi = *(__force u32 *)&icode->code[pc + 1];
 		} else {
 			if (get_user(lo, &icode->code[pc + 0]) ||
 			    get_user(hi, &icode->code[pc + 1]))
@@ -666,7 +666,7 @@ static unsigned int *copy_tlv(const unsigned int __user *_tlv, bool in_kernel)
 	if (!_tlv)
 		return NULL;
 	if (in_kernel)
-		memcpy(data, (void *)_tlv, sizeof(data));
+		memcpy(data, (__force void *)_tlv, sizeof(data));
 	else if (copy_from_user(data, _tlv, sizeof(data)))
 		return NULL;
 	if (data[1] >= MAX_TLV_SIZE)
@@ -676,7 +676,7 @@ static unsigned int *copy_tlv(const unsigned int __user *_tlv, bool in_kernel)
 		return NULL;
 	memcpy(tlv, data, sizeof(data));
 	if (in_kernel) {
-		memcpy(tlv + 2, (void *)(_tlv + 2),  data[1]);
+		memcpy(tlv + 2, (__force void *)(_tlv + 2),  data[1]);
 	} else if (copy_from_user(tlv + 2, _tlv + 2, data[1])) {
 		kfree(tlv);
 		return NULL;
@@ -693,7 +693,7 @@ static int copy_gctl(struct snd_emu10k1 *emu,
 
 	if (emu->support_tlv) {
 		if (in_kernel)
-			memcpy(gctl, (void *)&_gctl[idx], sizeof(*gctl));
+			memcpy(gctl, (__force void *)&_gctl[idx], sizeof(*gctl));
 		else if (copy_from_user(gctl, &_gctl[idx], sizeof(*gctl)))
 			return -EFAULT;
 		return 0;
@@ -701,7 +701,7 @@ static int copy_gctl(struct snd_emu10k1 *emu,
 
 	octl = (struct snd_emu10k1_fx8010_control_old_gpr __user *)_gctl;
 	if (in_kernel)
-		memcpy(gctl, (void *)&octl[idx], sizeof(*octl));
+		memcpy(gctl, (__force void *)&octl[idx], sizeof(*octl));
 	else if (copy_from_user(gctl, &octl[idx], sizeof(*octl)))
 		return -EFAULT;
 	gctl->tlv = NULL;
@@ -735,7 +735,7 @@ static int snd_emu10k1_verify_controls(struct snd_emu10k1 *emu,
 	for (i = 0, _id = icode->gpr_del_controls;
 	     i < icode->gpr_del_control_count; i++, _id++) {
 		if (in_kernel)
-			id = *(struct snd_ctl_elem_id *)_id;
+			id = *(__force struct snd_ctl_elem_id *)_id;
 		else if (copy_from_user(&id, _id, sizeof(id)))
 	     		return -EFAULT;
 		if (snd_emu10k1_look_for_ctl(emu, &id) == NULL)
@@ -833,7 +833,7 @@ static int snd_emu10k1_add_controls(struct snd_emu10k1 *emu,
 		knew.device = gctl->id.device;
 		knew.subdevice = gctl->id.subdevice;
 		knew.info = snd_emu10k1_gpr_ctl_info;
-		knew.tlv.p = copy_tlv(gctl->tlv, in_kernel);
+		knew.tlv.p = copy_tlv((__force const unsigned int __user *)gctl->tlv, in_kernel);
 		if (knew.tlv.p)
 			knew.access = SNDRV_CTL_ELEM_ACCESS_READWRITE |
 				SNDRV_CTL_ELEM_ACCESS_TLV_READ;
@@ -897,7 +897,7 @@ static int snd_emu10k1_del_controls(struct snd_emu10k1 *emu,
 	for (i = 0, _id = icode->gpr_del_controls;
 	     i < icode->gpr_del_control_count; i++, _id++) {
 		if (in_kernel)
-			id = *(struct snd_ctl_elem_id *)_id;
+			id = *(__force struct snd_ctl_elem_id *)_id;
 		else if (copy_from_user(&id, _id, sizeof(id)))
 			return -EFAULT;
 		down_write(&card->controls_rwsem);
-- 
cgit v1.2.3


From 96455f734b2f6491b07a9a5b0c94513f0f4c9144 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Wed, 18 Jul 2018 21:56:20 +0200
Subject: clk: samsung: Remove unused mout_user_aclk400_mcuisp_p4x12 variable

Remove unused 'mout_user_aclk400_mcuisp_p4x12' variable to fix GCC warning:

    drivers/clk/samsung/clk-exynos4412-isp.c:40:27: warning:
        'mout_user_aclk400_mcuisp_p4x12' defined but not used [-Wunused-const-variable=]

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/samsung/clk-exynos4412-isp.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/clk/samsung/clk-exynos4412-isp.c b/drivers/clk/samsung/clk-exynos4412-isp.c
index d5f1ccb36300..cfaa057035ad 100644
--- a/drivers/clk/samsung/clk-exynos4412-isp.c
+++ b/drivers/clk/samsung/clk-exynos4412-isp.c
@@ -37,8 +37,6 @@ static const unsigned long exynos4x12_clk_isp_save[] __initconst = {
 	E4X12_GATE_ISP1,
 };
 
-PNAME(mout_user_aclk400_mcuisp_p4x12) = { "fin_pll", "div_aclk400_mcuisp", };
-
 static struct samsung_div_clock exynos4x12_isp_div_clks[] = {
 	DIV(CLK_ISP_DIV_ISP0, "div_isp0", "aclk200", E4X12_DIV_ISP0, 0, 3),
 	DIV(CLK_ISP_DIV_ISP1, "div_isp1", "aclk200", E4X12_DIV_ISP0, 4, 3),
-- 
cgit v1.2.3


From 601b218568a107370086dc5c7a1b283f8d463268 Mon Sep 17 00:00:00 2001
From: Ruchi Kandoi <kandoiruchi@google.com>
Date: Tue, 24 Jul 2018 10:35:44 -0700
Subject: cpufreq: trace frequency limits change

systrace used for tracing for Android systems has carried a patch for
many years in the Android tree that traces when the cpufreq limits
change.  With the help of this information, systrace can know when the
policy limits change and can visually display the data. Lets add
upstream support for the same.

Signed-off-by: Ruchi Kandoi <kandoiruchi@google.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/trace/events-power.rst |  1 +
 drivers/cpufreq/cpufreq.c            |  1 +
 include/trace/events/power.h         | 25 +++++++++++++++++++++++++
 3 files changed, 27 insertions(+)

diff --git a/Documentation/trace/events-power.rst b/Documentation/trace/events-power.rst
index a77daca75e30..2ef318962e29 100644
--- a/Documentation/trace/events-power.rst
+++ b/Documentation/trace/events-power.rst
@@ -27,6 +27,7 @@ cpufreq.
 
   cpu_idle		"state=%lu cpu_id=%lu"
   cpu_frequency		"state=%lu cpu_id=%lu"
+  cpu_frequency_limits	"min=%lu max=%lu cpu_id=%lu"
 
 A suspend event is used to indicate the system going in and out of the
 suspend mode:
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b0dfd3222013..52566f1f1050 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2236,6 +2236,7 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	policy->min = new_policy->min;
 	policy->max = new_policy->max;
+	trace_cpu_frequency_limits(policy);
 
 	policy->cached_target_freq = UINT_MAX;
 
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 908977d69783..f7aece721aed 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -5,6 +5,7 @@
 #if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_POWER_H
 
+#include <linux/cpufreq.h>
 #include <linux/ktime.h>
 #include <linux/pm_qos.h>
 #include <linux/tracepoint.h>
@@ -148,6 +149,30 @@ DEFINE_EVENT(cpu, cpu_frequency,
 	TP_ARGS(frequency, cpu_id)
 );
 
+TRACE_EVENT(cpu_frequency_limits,
+
+	TP_PROTO(struct cpufreq_policy *policy),
+
+	TP_ARGS(policy),
+
+	TP_STRUCT__entry(
+		__field(u32, min_freq)
+		__field(u32, max_freq)
+		__field(u32, cpu_id)
+	),
+
+	TP_fast_assign(
+		__entry->min_freq = policy->min;
+		__entry->max_freq = policy->max;
+		__entry->cpu_id = policy->cpu;
+	),
+
+	TP_printk("min=%lu max=%lu cpu_id=%lu",
+		  (unsigned long)__entry->min_freq,
+		  (unsigned long)__entry->max_freq,
+		  (unsigned long)__entry->cpu_id)
+);
+
 TRACE_EVENT(device_pm_callback_start,
 
 	TP_PROTO(struct device *dev, const char *pm_ops, int event),
-- 
cgit v1.2.3


From c2cd0b08e1efd9ee58d09049a6c77e5efa0ef627 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 24 Jul 2018 09:49:28 -0700
Subject: x86/power/hibernate_64: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel [1], this
removes the discouraged use of AHASH_REQUEST_ON_STACK by switching to
shash directly and allocating the descriptor in heap memory (which should
be fine: the tfm has already been allocated there too).

Link: https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com # [1]
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/x86/power/hibernate_64.c | 36 +++++++++++++++++++++---------------
 1 file changed, 21 insertions(+), 15 deletions(-)

diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 67ccf64c8bd8..f8e3b668d20b 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -233,29 +233,35 @@ struct restore_data_record {
  */
 static int get_e820_md5(struct e820_table *table, void *buf)
 {
-	struct scatterlist sg;
-	struct crypto_ahash *tfm;
+	struct crypto_shash *tfm;
+	struct shash_desc *desc;
 	int size;
 	int ret = 0;
 
-	tfm = crypto_alloc_ahash("md5", 0, CRYPTO_ALG_ASYNC);
+	tfm = crypto_alloc_shash("md5", 0, 0);
 	if (IS_ERR(tfm))
 		return -ENOMEM;
 
-	{
-		AHASH_REQUEST_ON_STACK(req, tfm);
-		size = offsetof(struct e820_table, entries) + sizeof(struct e820_entry) * table->nr_entries;
-		ahash_request_set_tfm(req, tfm);
-		sg_init_one(&sg, (u8 *)table, size);
-		ahash_request_set_callback(req, 0, NULL, NULL);
-		ahash_request_set_crypt(req, &sg, buf, size);
-
-		if (crypto_ahash_digest(req))
-			ret = -EINVAL;
-		ahash_request_zero(req);
+	desc = kmalloc(sizeof(struct shash_desc) + crypto_shash_descsize(tfm),
+		       GFP_KERNEL);
+	if (!desc) {
+		ret = -ENOMEM;
+		goto free_tfm;
 	}
-	crypto_free_ahash(tfm);
 
+	desc->tfm = tfm;
+	desc->flags = 0;
+
+	size = offsetof(struct e820_table, entries) +
+		sizeof(struct e820_entry) * table->nr_entries;
+
+	if (crypto_shash_digest(desc, (u8 *)table, size, buf))
+		ret = -EINVAL;
+
+	kzfree(desc);
+
+free_tfm:
+	crypto_free_shash(tfm);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 6f4ceee9305dc3fe74099159b460f4b56b506f1d Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 24 Jul 2018 14:26:04 -0400
Subject: cpu/hotplug: Add a cpus_read_trylock() function

There are use cases where it can be useful to have a cpus_read_trylock()
function to work around circular lock dependency problem involving
the cpu_hotplug_lock.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/cpu.h | 2 ++
 kernel/cpu.c        | 6 ++++++
 2 files changed, 8 insertions(+)

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index a97a63eef59f..e850bfea3e84 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -103,6 +103,7 @@ extern void cpus_write_lock(void);
 extern void cpus_write_unlock(void);
 extern void cpus_read_lock(void);
 extern void cpus_read_unlock(void);
+extern int  cpus_read_trylock(void);
 extern void lockdep_assert_cpus_held(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
@@ -115,6 +116,7 @@ static inline void cpus_write_lock(void) { }
 static inline void cpus_write_unlock(void) { }
 static inline void cpus_read_lock(void) { }
 static inline void cpus_read_unlock(void) { }
+static inline int  cpus_read_trylock(void) { return true; }
 static inline void lockdep_assert_cpus_held(void) { }
 static inline void cpu_hotplug_disable(void) { }
 static inline void cpu_hotplug_enable(void) { }
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..307486baa477 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -290,6 +290,12 @@ void cpus_read_lock(void)
 }
 EXPORT_SYMBOL_GPL(cpus_read_lock);
 
+int cpus_read_trylock(void)
+{
+	return percpu_down_read_trylock(&cpu_hotplug_lock);
+}
+EXPORT_SYMBOL_GPL(cpus_read_trylock);
+
 void cpus_read_unlock(void)
 {
 	percpu_up_read(&cpu_hotplug_lock);
-- 
cgit v1.2.3


From 9b3d9bb3e4deef41095e513c2ffbebab20f9a982 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Tue, 24 Jul 2018 14:26:05 -0400
Subject: cpufreq: Fix a circular lock dependency problem

With lockdep turned on, the following circular lock dependency problem
was reported:

[   57.470040] ======================================================
[   57.502900] WARNING: possible circular locking dependency detected
[   57.535208] 4.18.0-0.rc3.1.el8+7.x86_64+debug #1 Tainted: G
[   57.577761] ------------------------------------------------------
[   57.609714] tuned/1505 is trying to acquire lock:
[   57.633808] 00000000559deec5 (cpu_hotplug_lock.rw_sem){++++}, at: store+0x27/0x120
[   57.672880]
[   57.672880] but task is already holding lock:
[   57.702184] 000000002136ca64 (kn->count#118){++++}, at: kernfs_fop_write+0x1d0/0x410
[   57.742176]
[   57.742176] which lock already depends on the new lock.
[   57.742176]
[   57.785220]
[   57.785220] the existing dependency chain (in reverse order) is:
    :
[   58.932512] other info that might help us debug this:
[   58.932512]
[   58.973344] Chain exists of:
[   58.973344]   cpu_hotplug_lock.rw_sem --> subsys mutex#5 --> kn->count#118
[   58.973344]
[   59.030795]  Possible unsafe locking scenario:
[   59.030795]
[   59.061248]        CPU0                    CPU1
[   59.085377]        ----                    ----
[   59.108160]   lock(kn->count#118);
[   59.124935]                                lock(subsys mutex#5);
[   59.156330]                                lock(kn->count#118);
[   59.186088]   lock(cpu_hotplug_lock.rw_sem);
[   59.208541]
[   59.208541]  *** DEADLOCK ***

In the cpufreq_register_driver() function, the lock sequence is:

  cpus_read_lock --> kn->count

For the cpufreq sysfs store method, the lock sequence is:

  kn->count --> cpus_read_lock

These sequences are actually safe as they are taking a share lock on
cpu_hotplug_lock. However, the current lockdep code doesn't check for
share locking when detecting circular lock dependency.  Fixing that
could be a substantial effort.

Instead, we can work around this problem by using cpus_read_trylock()
in the store method which is much simpler. The chance of not getting
the read lock is very small. If that happens, the userspace application
that writes the sysfs file will get an error.

Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/cpufreq.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 52566f1f1050..f53fb41efb7b 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -923,7 +923,12 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 
-	cpus_read_lock();
+	/*
+	 * cpus_read_trylock() is used here to work around a circular lock
+	 * dependency problem with respect to the cpufreq_register_driver().
+	 */
+	if (!cpus_read_trylock())
+		return -EBUSY;
 
 	if (cpu_online(policy->cpu)) {
 		down_write(&policy->rwsem);
-- 
cgit v1.2.3


From f8f5fe86f7e10ecc784b53537edbe3fcf0c00884 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 11 Jul 2018 12:24:22 +0100
Subject: clocksource/drivers: Set clockevent device cpumask to
 cpu_possible_mask

Currently, quite a few clockevent devices have cpumask set to
cpu_all_mask which should be fine. However, cpu_possible_mask is more
accurate and if there are any other clockevent devices in the system
which have cpumask set to cpu_possible_mask, then having cpu_all_mask
may result in issues (mostly boot hang with forever loops in
clockevents_notify_released).

So, lets replace all the clockevent device cpu_all_mask to
cpu_possible_mask in order to prevent above mentioned possible issue.

Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thierry Reding <thierry.reding@gmail.com>
Cc: Jonathan Hunter <jonathanh@nvidia.com>
Cc: Santosh Shilimkar <ssantosh@kernel.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/tegra20_timer.c   | 2 +-
 drivers/clocksource/timer-atcpit100.c | 2 +-
 drivers/clocksource/timer-keystone.c  | 2 +-
 drivers/clocksource/zevio-timer.c     | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/clocksource/tegra20_timer.c b/drivers/clocksource/tegra20_timer.c
index c337a8100a7b..dabf0a103567 100644
--- a/drivers/clocksource/tegra20_timer.c
+++ b/drivers/clocksource/tegra20_timer.c
@@ -230,7 +230,7 @@ static int __init tegra20_init_timer(struct device_node *np)
 		return ret;
 	}
 
-	tegra_clockevent.cpumask = cpu_all_mask;
+	tegra_clockevent.cpumask = cpu_possible_mask;
 	tegra_clockevent.irq = tegra_timer_irq.irq;
 	clockevents_config_and_register(&tegra_clockevent, 1000000,
 					0x1, 0x1fffffff);
diff --git a/drivers/clocksource/timer-atcpit100.c b/drivers/clocksource/timer-atcpit100.c
index 5e23d7b4a722..b4bd2f5b801d 100644
--- a/drivers/clocksource/timer-atcpit100.c
+++ b/drivers/clocksource/timer-atcpit100.c
@@ -185,7 +185,7 @@ static struct timer_of to = {
 		.set_state_oneshot = atcpit100_clkevt_set_oneshot,
 		.tick_resume = atcpit100_clkevt_shutdown,
 		.set_next_event = atcpit100_clkevt_next_event,
-		.cpumask = cpu_all_mask,
+		.cpumask = cpu_possible_mask,
 	},
 
 	.of_irq = {
diff --git a/drivers/clocksource/timer-keystone.c b/drivers/clocksource/timer-keystone.c
index 0eee03250cfc..f5b2eda30bf3 100644
--- a/drivers/clocksource/timer-keystone.c
+++ b/drivers/clocksource/timer-keystone.c
@@ -211,7 +211,7 @@ static int __init keystone_timer_init(struct device_node *np)
 	event_dev->set_state_shutdown = keystone_shutdown;
 	event_dev->set_state_periodic = keystone_set_periodic;
 	event_dev->set_state_oneshot = keystone_shutdown;
-	event_dev->cpumask = cpu_all_mask;
+	event_dev->cpumask = cpu_possible_mask;
 	event_dev->owner = THIS_MODULE;
 	event_dev->name = TIMER_NAME;
 	event_dev->irq = irq;
diff --git a/drivers/clocksource/zevio-timer.c b/drivers/clocksource/zevio-timer.c
index a6a0338eea77..f74689334f7c 100644
--- a/drivers/clocksource/zevio-timer.c
+++ b/drivers/clocksource/zevio-timer.c
@@ -162,7 +162,7 @@ static int __init zevio_timer_add(struct device_node *node)
 		timer->clkevt.set_state_oneshot = zevio_timer_set_oneshot;
 		timer->clkevt.tick_resume	= zevio_timer_set_oneshot;
 		timer->clkevt.rating		= 200;
-		timer->clkevt.cpumask		= cpu_all_mask;
+		timer->clkevt.cpumask		= cpu_possible_mask;
 		timer->clkevt.features		= CLOCK_EVT_FEAT_ONESHOT;
 		timer->clkevt.irq		= irqnr;
 
-- 
cgit v1.2.3


From 59311b19d7f632397a98e8194de8e871867069db Mon Sep 17 00:00:00 2001
From: Stanley Chu <stanley.chu@mediatek.com>
Date: Fri, 6 Jul 2018 07:11:24 +0800
Subject: clocksource/drivers/timer-mediatek: Add system timer bindings

This patch adds bindings of new "System Timer" on Mediatek SoCs.

Remove RTC clock in the same time because it is not used by
both "General Purpose Timer" and "System Timer" now.

Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 .../bindings/timer/mediatek,mtk-timer.txt          | 34 +++++++++++++---------
 1 file changed, 20 insertions(+), 14 deletions(-)

diff --git a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
index b1fe7e9de1b4..18d4d0166c76 100644
--- a/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
+++ b/Documentation/devicetree/bindings/timer/mediatek,mtk-timer.txt
@@ -1,19 +1,25 @@
-Mediatek MT6577, MT6572 and MT6589 Timers
----------------------------------------
+Mediatek Timers
+---------------
+
+Mediatek SoCs have two different timers on different platforms,
+- GPT (General Purpose Timer)
+- SYST (System Timer)
+
+The proper timer will be selected automatically by driver.
 
 Required properties:
 - compatible should contain:
-	* "mediatek,mt2701-timer" for MT2701 compatible timers
-	* "mediatek,mt6580-timer" for MT6580 compatible timers
-	* "mediatek,mt6589-timer" for MT6589 compatible timers
-	* "mediatek,mt7623-timer" for MT7623 compatible timers
-	* "mediatek,mt8127-timer" for MT8127 compatible timers
-	* "mediatek,mt8135-timer" for MT8135 compatible timers
-	* "mediatek,mt8173-timer" for MT8173 compatible timers
-	* "mediatek,mt6577-timer" for MT6577 and all above compatible timers
-- reg: Should contain location and length for timers register.
-- clocks: Clocks driving the timer hardware. This list should include two
-	clocks. The order is system clock and as second clock the RTC clock.
+	* "mediatek,mt2701-timer" for MT2701 compatible timers (GPT)
+	* "mediatek,mt6580-timer" for MT6580 compatible timers (GPT)
+	* "mediatek,mt6589-timer" for MT6589 compatible timers (GPT)
+	* "mediatek,mt7623-timer" for MT7623 compatible timers (GPT)
+	* "mediatek,mt8127-timer" for MT8127 compatible timers (GPT)
+	* "mediatek,mt8135-timer" for MT8135 compatible timers (GPT)
+	* "mediatek,mt8173-timer" for MT8173 compatible timers (GPT)
+	* "mediatek,mt6577-timer" for MT6577 and all above compatible timers (GPT)
+	* "mediatek,mt6765-timer" for MT6765 compatible timers (SYST)
+- reg: Should contain location and length for timer register.
+- clocks: Should contain system clock.
 
 Examples:
 
@@ -21,5 +27,5 @@ Examples:
 		compatible = "mediatek,mt6577-timer";
 		reg = <0x10008000 0x80>;
 		interrupts = <GIC_SPI 113 IRQ_TYPE_LEVEL_LOW>;
-		clocks = <&system_clk>, <&rtc_clk>;
+		clocks = <&system_clk>;
 	};
-- 
cgit v1.2.3


From 7ec58e5244b7a7aa41f792968208239a43e5ade7 Mon Sep 17 00:00:00 2001
From: Stanley Chu <stanley.chu@mediatek.com>
Date: Fri, 6 Jul 2018 07:11:25 +0800
Subject: clocksource/drivers/timer-mediatek: Rename mtk_timer to
 timer-mediatek

Rename mtk_timer to timer-mediatek to apply new naming convention
in clocksource folder.

Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/Makefile         |   2 +-
 drivers/clocksource/mtk_timer.c      | 268 -----------------------------------
 drivers/clocksource/timer-mediatek.c | 268 +++++++++++++++++++++++++++++++++++
 3 files changed, 269 insertions(+), 269 deletions(-)
 delete mode 100644 drivers/clocksource/mtk_timer.c
 create mode 100644 drivers/clocksource/timer-mediatek.c

diff --git a/drivers/clocksource/Makefile b/drivers/clocksource/Makefile
index 00caf37e52f9..c070cc7992e9 100644
--- a/drivers/clocksource/Makefile
+++ b/drivers/clocksource/Makefile
@@ -49,7 +49,7 @@ obj-$(CONFIG_CLKSRC_SAMSUNG_PWM)	+= samsung_pwm_timer.o
 obj-$(CONFIG_FSL_FTM_TIMER)	+= fsl_ftm_timer.o
 obj-$(CONFIG_VF_PIT_TIMER)	+= vf_pit_timer.o
 obj-$(CONFIG_CLKSRC_QCOM)	+= qcom-timer.o
-obj-$(CONFIG_MTK_TIMER)		+= mtk_timer.o
+obj-$(CONFIG_MTK_TIMER)		+= timer-mediatek.o
 obj-$(CONFIG_CLKSRC_PISTACHIO)	+= time-pistachio.o
 obj-$(CONFIG_CLKSRC_TI_32K)	+= timer-ti-32k.o
 obj-$(CONFIG_CLKSRC_NPS)	+= timer-nps.o
diff --git a/drivers/clocksource/mtk_timer.c b/drivers/clocksource/mtk_timer.c
deleted file mode 100644
index f9b724fd9950..000000000000
--- a/drivers/clocksource/mtk_timer.c
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Mediatek SoCs General-Purpose Timer handling.
- *
- * Copyright (C) 2014 Matthias Brugger
- *
- * Matthias Brugger <matthias.bgg@gmail.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
-
-#include <linux/clk.h>
-#include <linux/clockchips.h>
-#include <linux/interrupt.h>
-#include <linux/irq.h>
-#include <linux/irqreturn.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/sched_clock.h>
-#include <linux/slab.h>
-
-#define GPT_IRQ_EN_REG		0x00
-#define GPT_IRQ_ENABLE(val)	BIT((val) - 1)
-#define GPT_IRQ_ACK_REG		0x08
-#define GPT_IRQ_ACK(val)	BIT((val) - 1)
-
-#define TIMER_CTRL_REG(val)	(0x10 * (val))
-#define TIMER_CTRL_OP(val)	(((val) & 0x3) << 4)
-#define TIMER_CTRL_OP_ONESHOT	(0)
-#define TIMER_CTRL_OP_REPEAT	(1)
-#define TIMER_CTRL_OP_FREERUN	(3)
-#define TIMER_CTRL_CLEAR	(2)
-#define TIMER_CTRL_ENABLE	(1)
-#define TIMER_CTRL_DISABLE	(0)
-
-#define TIMER_CLK_REG(val)	(0x04 + (0x10 * (val)))
-#define TIMER_CLK_SRC(val)	(((val) & 0x1) << 4)
-#define TIMER_CLK_SRC_SYS13M	(0)
-#define TIMER_CLK_SRC_RTC32K	(1)
-#define TIMER_CLK_DIV1		(0x0)
-#define TIMER_CLK_DIV2		(0x1)
-
-#define TIMER_CNT_REG(val)	(0x08 + (0x10 * (val)))
-#define TIMER_CMP_REG(val)	(0x0C + (0x10 * (val)))
-
-#define GPT_CLK_EVT	1
-#define GPT_CLK_SRC	2
-
-struct mtk_clock_event_device {
-	void __iomem *gpt_base;
-	u32 ticks_per_jiffy;
-	struct clock_event_device dev;
-};
-
-static void __iomem *gpt_sched_reg __read_mostly;
-
-static u64 notrace mtk_read_sched_clock(void)
-{
-	return readl_relaxed(gpt_sched_reg);
-}
-
-static inline struct mtk_clock_event_device *to_mtk_clk(
-				struct clock_event_device *c)
-{
-	return container_of(c, struct mtk_clock_event_device, dev);
-}
-
-static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-	writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base +
-			TIMER_CTRL_REG(timer));
-}
-
-static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt,
-				unsigned long delay, u8 timer)
-{
-	writel(delay, evt->gpt_base + TIMER_CMP_REG(timer));
-}
-
-static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
-		bool periodic, u8 timer)
-{
-	u32 val;
-
-	/* Acknowledge interrupt */
-	writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	/* Clear 2 bit timer operation mode field */
-	val &= ~TIMER_CTRL_OP(0x3);
-
-	if (periodic)
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT);
-	else
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT);
-
-	writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR,
-	       evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static int mtk_clkevt_shutdown(struct clock_event_device *clk)
-{
-	mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
-	return 0;
-}
-
-static int mtk_clkevt_next_event(unsigned long event,
-				   struct clock_event_device *clk)
-{
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
-
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, false, GPT_CLK_EVT);
-
-	return 0;
-}
-
-static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id)
-{
-	struct mtk_clock_event_device *evt = dev_id;
-
-	/* Acknowledge timer0 irq */
-	writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
-	evt->dev.event_handler(&evt->dev);
-
-	return IRQ_HANDLED;
-}
-
-static void
-__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
-{
-	writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE,
-		evt->gpt_base + TIMER_CTRL_REG(timer));
-
-	writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1,
-			evt->gpt_base + TIMER_CLK_REG(timer));
-
-	writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer));
-
-	writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE,
-			evt->gpt_base + TIMER_CTRL_REG(timer));
-}
-
-static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
-{
-	u32 val;
-
-	/* Disable all interrupts */
-	writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG);
-
-	/* Acknowledge all spurious pending interrupts */
-	writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG);
-
-	val = readl(evt->gpt_base + GPT_IRQ_EN_REG);
-	writel(val | GPT_IRQ_ENABLE(timer),
-			evt->gpt_base + GPT_IRQ_EN_REG);
-}
-
-static int __init mtk_timer_init(struct device_node *node)
-{
-	struct mtk_clock_event_device *evt;
-	struct resource res;
-	unsigned long rate = 0;
-	struct clk *clk;
-
-	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
-	if (!evt)
-		return -ENOMEM;
-
-	evt->dev.name = "mtk_tick";
-	evt->dev.rating = 300;
-	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
-	evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
-	evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
-	evt->dev.tick_resume = mtk_clkevt_shutdown;
-	evt->dev.set_next_event = mtk_clkevt_next_event;
-	evt->dev.cpumask = cpu_possible_mask;
-
-	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
-	if (IS_ERR(evt->gpt_base)) {
-		pr_err("Can't get resource\n");
-		goto err_kzalloc;
-	}
-
-	evt->dev.irq = irq_of_parse_and_map(node, 0);
-	if (evt->dev.irq <= 0) {
-		pr_err("Can't parse IRQ\n");
-		goto err_mem;
-	}
-
-	clk = of_clk_get(node, 0);
-	if (IS_ERR(clk)) {
-		pr_err("Can't get timer clock\n");
-		goto err_irq;
-	}
-
-	if (clk_prepare_enable(clk)) {
-		pr_err("Can't prepare clock\n");
-		goto err_clk_put;
-	}
-	rate = clk_get_rate(clk);
-
-	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
-			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
-		pr_err("failed to setup irq %d\n", evt->dev.irq);
-		goto err_clk_disable;
-	}
-
-	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
-
-	/* Configure clock source */
-	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
-	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
-			node->name, rate, 300, 32, clocksource_mmio_readl_up);
-	gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC);
-	sched_clock_register(mtk_read_sched_clock, 32, rate);
-
-	/* Configure clock event */
-	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	clockevents_config_and_register(&evt->dev, rate, 0x3,
-					0xffffffff);
-
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
-
-	return 0;
-
-err_clk_disable:
-	clk_disable_unprepare(clk);
-err_clk_put:
-	clk_put(clk);
-err_irq:
-	irq_dispose_mapping(evt->dev.irq);
-err_mem:
-	iounmap(evt->gpt_base);
-	of_address_to_resource(node, 0, &res);
-	release_mem_region(res.start, resource_size(&res));
-err_kzalloc:
-	kfree(evt);
-
-	return -EINVAL;
-}
-TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
new file mode 100644
index 000000000000..f9b724fd9950
--- /dev/null
+++ b/drivers/clocksource/timer-mediatek.c
@@ -0,0 +1,268 @@
+/*
+ * Mediatek SoCs General-Purpose Timer handling.
+ *
+ * Copyright (C) 2014 Matthias Brugger
+ *
+ * Matthias Brugger <matthias.bgg@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/sched_clock.h>
+#include <linux/slab.h>
+
+#define GPT_IRQ_EN_REG		0x00
+#define GPT_IRQ_ENABLE(val)	BIT((val) - 1)
+#define GPT_IRQ_ACK_REG		0x08
+#define GPT_IRQ_ACK(val)	BIT((val) - 1)
+
+#define TIMER_CTRL_REG(val)	(0x10 * (val))
+#define TIMER_CTRL_OP(val)	(((val) & 0x3) << 4)
+#define TIMER_CTRL_OP_ONESHOT	(0)
+#define TIMER_CTRL_OP_REPEAT	(1)
+#define TIMER_CTRL_OP_FREERUN	(3)
+#define TIMER_CTRL_CLEAR	(2)
+#define TIMER_CTRL_ENABLE	(1)
+#define TIMER_CTRL_DISABLE	(0)
+
+#define TIMER_CLK_REG(val)	(0x04 + (0x10 * (val)))
+#define TIMER_CLK_SRC(val)	(((val) & 0x1) << 4)
+#define TIMER_CLK_SRC_SYS13M	(0)
+#define TIMER_CLK_SRC_RTC32K	(1)
+#define TIMER_CLK_DIV1		(0x0)
+#define TIMER_CLK_DIV2		(0x1)
+
+#define TIMER_CNT_REG(val)	(0x08 + (0x10 * (val)))
+#define TIMER_CMP_REG(val)	(0x0C + (0x10 * (val)))
+
+#define GPT_CLK_EVT	1
+#define GPT_CLK_SRC	2
+
+struct mtk_clock_event_device {
+	void __iomem *gpt_base;
+	u32 ticks_per_jiffy;
+	struct clock_event_device dev;
+};
+
+static void __iomem *gpt_sched_reg __read_mostly;
+
+static u64 notrace mtk_read_sched_clock(void)
+{
+	return readl_relaxed(gpt_sched_reg);
+}
+
+static inline struct mtk_clock_event_device *to_mtk_clk(
+				struct clock_event_device *c)
+{
+	return container_of(c, struct mtk_clock_event_device, dev);
+}
+
+static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
+{
+	u32 val;
+
+	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
+	writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base +
+			TIMER_CTRL_REG(timer));
+}
+
+static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt,
+				unsigned long delay, u8 timer)
+{
+	writel(delay, evt->gpt_base + TIMER_CMP_REG(timer));
+}
+
+static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
+		bool periodic, u8 timer)
+{
+	u32 val;
+
+	/* Acknowledge interrupt */
+	writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
+
+	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
+
+	/* Clear 2 bit timer operation mode field */
+	val &= ~TIMER_CTRL_OP(0x3);
+
+	if (periodic)
+		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT);
+	else
+		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT);
+
+	writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR,
+	       evt->gpt_base + TIMER_CTRL_REG(timer));
+}
+
+static int mtk_clkevt_shutdown(struct clock_event_device *clk)
+{
+	mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
+	return 0;
+}
+
+static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
+{
+	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
+
+	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
+	mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
+	mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
+	return 0;
+}
+
+static int mtk_clkevt_next_event(unsigned long event,
+				   struct clock_event_device *clk)
+{
+	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
+
+	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
+	mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT);
+	mtk_clkevt_time_start(evt, false, GPT_CLK_EVT);
+
+	return 0;
+}
+
+static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id)
+{
+	struct mtk_clock_event_device *evt = dev_id;
+
+	/* Acknowledge timer0 irq */
+	writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
+	evt->dev.event_handler(&evt->dev);
+
+	return IRQ_HANDLED;
+}
+
+static void
+__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
+{
+	writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE,
+		evt->gpt_base + TIMER_CTRL_REG(timer));
+
+	writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1,
+			evt->gpt_base + TIMER_CLK_REG(timer));
+
+	writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer));
+
+	writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE,
+			evt->gpt_base + TIMER_CTRL_REG(timer));
+}
+
+static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
+{
+	u32 val;
+
+	/* Disable all interrupts */
+	writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG);
+
+	/* Acknowledge all spurious pending interrupts */
+	writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG);
+
+	val = readl(evt->gpt_base + GPT_IRQ_EN_REG);
+	writel(val | GPT_IRQ_ENABLE(timer),
+			evt->gpt_base + GPT_IRQ_EN_REG);
+}
+
+static int __init mtk_timer_init(struct device_node *node)
+{
+	struct mtk_clock_event_device *evt;
+	struct resource res;
+	unsigned long rate = 0;
+	struct clk *clk;
+
+	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
+	if (!evt)
+		return -ENOMEM;
+
+	evt->dev.name = "mtk_tick";
+	evt->dev.rating = 300;
+	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
+	evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
+	evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
+	evt->dev.tick_resume = mtk_clkevt_shutdown;
+	evt->dev.set_next_event = mtk_clkevt_next_event;
+	evt->dev.cpumask = cpu_possible_mask;
+
+	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
+	if (IS_ERR(evt->gpt_base)) {
+		pr_err("Can't get resource\n");
+		goto err_kzalloc;
+	}
+
+	evt->dev.irq = irq_of_parse_and_map(node, 0);
+	if (evt->dev.irq <= 0) {
+		pr_err("Can't parse IRQ\n");
+		goto err_mem;
+	}
+
+	clk = of_clk_get(node, 0);
+	if (IS_ERR(clk)) {
+		pr_err("Can't get timer clock\n");
+		goto err_irq;
+	}
+
+	if (clk_prepare_enable(clk)) {
+		pr_err("Can't prepare clock\n");
+		goto err_clk_put;
+	}
+	rate = clk_get_rate(clk);
+
+	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
+			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
+		pr_err("failed to setup irq %d\n", evt->dev.irq);
+		goto err_clk_disable;
+	}
+
+	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
+
+	/* Configure clock source */
+	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
+	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
+			node->name, rate, 300, 32, clocksource_mmio_readl_up);
+	gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC);
+	sched_clock_register(mtk_read_sched_clock, 32, rate);
+
+	/* Configure clock event */
+	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
+	clockevents_config_and_register(&evt->dev, rate, 0x3,
+					0xffffffff);
+
+	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
+
+	return 0;
+
+err_clk_disable:
+	clk_disable_unprepare(clk);
+err_clk_put:
+	clk_put(clk);
+err_irq:
+	irq_dispose_mapping(evt->dev.irq);
+err_mem:
+	iounmap(evt->gpt_base);
+	of_address_to_resource(node, 0, &res);
+	release_mem_region(res.start, resource_size(&res));
+err_kzalloc:
+	kfree(evt);
+
+	return -EINVAL;
+}
+TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
-- 
cgit v1.2.3


From 56d52d3f56192049221105efa6ee76251a949c0e Mon Sep 17 00:00:00 2001
From: Stanley Chu <stanley.chu@mediatek.com>
Date: Fri, 6 Jul 2018 07:11:26 +0800
Subject: clocksource/drivers/timer-mediatek: Use specific prefix for GPT

Use specific prefix to specify the name of supported
timer hardware: "General Purpose Timer (GPT)".

Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/timer-mediatek.c | 157 ++++++++++++++++++-----------------
 1 file changed, 80 insertions(+), 77 deletions(-)

diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
index f9b724fd9950..e3657d29e765 100644
--- a/drivers/clocksource/timer-mediatek.c
+++ b/drivers/clocksource/timer-mediatek.c
@@ -29,32 +29,35 @@
 #include <linux/sched_clock.h>
 #include <linux/slab.h>
 
-#define GPT_IRQ_EN_REG		0x00
-#define GPT_IRQ_ENABLE(val)	BIT((val) - 1)
-#define GPT_IRQ_ACK_REG		0x08
-#define GPT_IRQ_ACK(val)	BIT((val) - 1)
-
-#define TIMER_CTRL_REG(val)	(0x10 * (val))
-#define TIMER_CTRL_OP(val)	(((val) & 0x3) << 4)
-#define TIMER_CTRL_OP_ONESHOT	(0)
-#define TIMER_CTRL_OP_REPEAT	(1)
-#define TIMER_CTRL_OP_FREERUN	(3)
-#define TIMER_CTRL_CLEAR	(2)
-#define TIMER_CTRL_ENABLE	(1)
-#define TIMER_CTRL_DISABLE	(0)
-
-#define TIMER_CLK_REG(val)	(0x04 + (0x10 * (val)))
-#define TIMER_CLK_SRC(val)	(((val) & 0x1) << 4)
-#define TIMER_CLK_SRC_SYS13M	(0)
-#define TIMER_CLK_SRC_RTC32K	(1)
-#define TIMER_CLK_DIV1		(0x0)
-#define TIMER_CLK_DIV2		(0x1)
-
-#define TIMER_CNT_REG(val)	(0x08 + (0x10 * (val)))
-#define TIMER_CMP_REG(val)	(0x0C + (0x10 * (val)))
-
-#define GPT_CLK_EVT	1
-#define GPT_CLK_SRC	2
+#define TIMER_CLK_EVT           (1)
+#define TIMER_CLK_SRC           (2)
+
+#define TIMER_SYNC_TICKS        (3)
+
+/* gpt */
+#define GPT_IRQ_EN_REG          0x00
+#define GPT_IRQ_ENABLE(val)     BIT((val) - 1)
+#define GPT_IRQ_ACK_REG	        0x08
+#define GPT_IRQ_ACK(val)        BIT((val) - 1)
+
+#define GPT_CTRL_REG(val)       (0x10 * (val))
+#define GPT_CTRL_OP(val)        (((val) & 0x3) << 4)
+#define GPT_CTRL_OP_ONESHOT     (0)
+#define GPT_CTRL_OP_REPEAT      (1)
+#define GPT_CTRL_OP_FREERUN     (3)
+#define GPT_CTRL_CLEAR          (2)
+#define GPT_CTRL_ENABLE         (1)
+#define GPT_CTRL_DISABLE        (0)
+
+#define GPT_CLK_REG(val)        (0x04 + (0x10 * (val)))
+#define GPT_CLK_SRC(val)        (((val) & 0x1) << 4)
+#define GPT_CLK_SRC_SYS13M      (0)
+#define GPT_CLK_SRC_RTC32K      (1)
+#define GPT_CLK_DIV1            (0x0)
+#define GPT_CLK_DIV2            (0x1)
+
+#define GPT_CNT_REG(val)        (0x08 + (0x10 * (val)))
+#define GPT_CMP_REG(val)        (0x0C + (0x10 * (val)))
 
 struct mtk_clock_event_device {
 	void __iomem *gpt_base;
@@ -64,7 +67,7 @@ struct mtk_clock_event_device {
 
 static void __iomem *gpt_sched_reg __read_mostly;
 
-static u64 notrace mtk_read_sched_clock(void)
+static u64 notrace mtk_gpt_read_sched_clock(void)
 {
 	return readl_relaxed(gpt_sched_reg);
 }
@@ -75,22 +78,22 @@ static inline struct mtk_clock_event_device *to_mtk_clk(
 	return container_of(c, struct mtk_clock_event_device, dev);
 }
 
-static void mtk_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
+static void mtk_gpt_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
 {
 	u32 val;
 
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
-	writel(val & ~TIMER_CTRL_ENABLE, evt->gpt_base +
-			TIMER_CTRL_REG(timer));
+	val = readl(evt->gpt_base + GPT_CTRL_REG(timer));
+	writel(val & ~GPT_CTRL_ENABLE, evt->gpt_base +
+			GPT_CTRL_REG(timer));
 }
 
-static void mtk_clkevt_time_setup(struct mtk_clock_event_device *evt,
+static void mtk_gpt_clkevt_time_setup(struct mtk_clock_event_device *evt,
 				unsigned long delay, u8 timer)
 {
-	writel(delay, evt->gpt_base + TIMER_CMP_REG(timer));
+	writel(delay, evt->gpt_base + GPT_CMP_REG(timer));
 }
 
-static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
+static void mtk_gpt_clkevt_time_start(struct mtk_clock_event_device *evt,
 		bool periodic, u8 timer)
 {
 	u32 val;
@@ -98,75 +101,75 @@ static void mtk_clkevt_time_start(struct mtk_clock_event_device *evt,
 	/* Acknowledge interrupt */
 	writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
 
-	val = readl(evt->gpt_base + TIMER_CTRL_REG(timer));
+	val = readl(evt->gpt_base + GPT_CTRL_REG(timer));
 
 	/* Clear 2 bit timer operation mode field */
-	val &= ~TIMER_CTRL_OP(0x3);
+	val &= ~GPT_CTRL_OP(0x3);
 
 	if (periodic)
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_REPEAT);
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_REPEAT);
 	else
-		val |= TIMER_CTRL_OP(TIMER_CTRL_OP_ONESHOT);
+		val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT);
 
-	writel(val | TIMER_CTRL_ENABLE | TIMER_CTRL_CLEAR,
-	       evt->gpt_base + TIMER_CTRL_REG(timer));
+	writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR,
+	       evt->gpt_base + GPT_CTRL_REG(timer));
 }
 
-static int mtk_clkevt_shutdown(struct clock_event_device *clk)
+static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk)
 {
-	mtk_clkevt_time_stop(to_mtk_clk(clk), GPT_CLK_EVT);
+	mtk_gpt_clkevt_time_stop(to_mtk_clk(clk), TIMER_CLK_EVT);
 	return 0;
 }
 
-static int mtk_clkevt_set_periodic(struct clock_event_device *clk)
+static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk)
 {
 	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
 
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, evt->ticks_per_jiffy, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, true, GPT_CLK_EVT);
+	mtk_gpt_clkevt_time_stop(evt, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(evt, evt->ticks_per_jiffy, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(evt, true, TIMER_CLK_EVT);
 	return 0;
 }
 
-static int mtk_clkevt_next_event(unsigned long event,
+static int mtk_gpt_clkevt_next_event(unsigned long event,
 				   struct clock_event_device *clk)
 {
 	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
 
-	mtk_clkevt_time_stop(evt, GPT_CLK_EVT);
-	mtk_clkevt_time_setup(evt, event, GPT_CLK_EVT);
-	mtk_clkevt_time_start(evt, false, GPT_CLK_EVT);
+	mtk_gpt_clkevt_time_stop(evt, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(evt, event, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(evt, false, TIMER_CLK_EVT);
 
 	return 0;
 }
 
-static irqreturn_t mtk_timer_interrupt(int irq, void *dev_id)
+static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id)
 {
 	struct mtk_clock_event_device *evt = dev_id;
 
 	/* Acknowledge timer0 irq */
-	writel(GPT_IRQ_ACK(GPT_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
+	writel(GPT_IRQ_ACK(TIMER_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
 	evt->dev.event_handler(&evt->dev);
 
 	return IRQ_HANDLED;
 }
 
 static void
-__init mtk_timer_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
+__init mtk_gpt_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
 {
-	writel(TIMER_CTRL_CLEAR | TIMER_CTRL_DISABLE,
-		evt->gpt_base + TIMER_CTRL_REG(timer));
+	writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE,
+		evt->gpt_base + GPT_CTRL_REG(timer));
 
-	writel(TIMER_CLK_SRC(TIMER_CLK_SRC_SYS13M) | TIMER_CLK_DIV1,
-			evt->gpt_base + TIMER_CLK_REG(timer));
+	writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1,
+			evt->gpt_base + GPT_CLK_REG(timer));
 
-	writel(0x0, evt->gpt_base + TIMER_CMP_REG(timer));
+	writel(0x0, evt->gpt_base + GPT_CMP_REG(timer));
 
-	writel(TIMER_CTRL_OP(option) | TIMER_CTRL_ENABLE,
-			evt->gpt_base + TIMER_CTRL_REG(timer));
+	writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE,
+			evt->gpt_base + GPT_CTRL_REG(timer));
 }
 
-static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
+static void mtk_gpt_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
 {
 	u32 val;
 
@@ -181,7 +184,7 @@ static void mtk_timer_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
 			evt->gpt_base + GPT_IRQ_EN_REG);
 }
 
-static int __init mtk_timer_init(struct device_node *node)
+static int __init mtk_gpt_init(struct device_node *node)
 {
 	struct mtk_clock_event_device *evt;
 	struct resource res;
@@ -195,14 +198,14 @@ static int __init mtk_timer_init(struct device_node *node)
 	evt->dev.name = "mtk_tick";
 	evt->dev.rating = 300;
 	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->dev.set_state_shutdown = mtk_clkevt_shutdown;
-	evt->dev.set_state_periodic = mtk_clkevt_set_periodic;
-	evt->dev.set_state_oneshot = mtk_clkevt_shutdown;
-	evt->dev.tick_resume = mtk_clkevt_shutdown;
-	evt->dev.set_next_event = mtk_clkevt_next_event;
+	evt->dev.set_state_shutdown = mtk_gpt_clkevt_shutdown;
+	evt->dev.set_state_periodic = mtk_gpt_clkevt_set_periodic;
+	evt->dev.set_state_oneshot = mtk_gpt_clkevt_shutdown;
+	evt->dev.tick_resume = mtk_gpt_clkevt_shutdown;
+	evt->dev.set_next_event = mtk_gpt_clkevt_next_event;
 	evt->dev.cpumask = cpu_possible_mask;
 
-	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer");
+	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer-gpt");
 	if (IS_ERR(evt->gpt_base)) {
 		pr_err("Can't get resource\n");
 		goto err_kzalloc;
@@ -226,7 +229,7 @@ static int __init mtk_timer_init(struct device_node *node)
 	}
 	rate = clk_get_rate(clk);
 
-	if (request_irq(evt->dev.irq, mtk_timer_interrupt,
+	if (request_irq(evt->dev.irq, mtk_gpt_interrupt,
 			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
 		pr_err("failed to setup irq %d\n", evt->dev.irq);
 		goto err_clk_disable;
@@ -235,18 +238,18 @@ static int __init mtk_timer_init(struct device_node *node)
 	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
 
 	/* Configure clock source */
-	mtk_timer_setup(evt, GPT_CLK_SRC, TIMER_CTRL_OP_FREERUN);
-	clocksource_mmio_init(evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC),
+	mtk_gpt_setup(evt, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
+	clocksource_mmio_init(evt->gpt_base + GPT_CNT_REG(TIMER_CLK_SRC),
 			node->name, rate, 300, 32, clocksource_mmio_readl_up);
-	gpt_sched_reg = evt->gpt_base + TIMER_CNT_REG(GPT_CLK_SRC);
-	sched_clock_register(mtk_read_sched_clock, 32, rate);
+	gpt_sched_reg = evt->gpt_base + GPT_CNT_REG(TIMER_CLK_SRC);
+	sched_clock_register(mtk_gpt_read_sched_clock, 32, rate);
 
 	/* Configure clock event */
-	mtk_timer_setup(evt, GPT_CLK_EVT, TIMER_CTRL_OP_REPEAT);
-	clockevents_config_and_register(&evt->dev, rate, 0x3,
+	mtk_gpt_setup(evt, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT);
+	clockevents_config_and_register(&evt->dev, rate, TIMER_SYNC_TICKS,
 					0xffffffff);
 
-	mtk_timer_enable_irq(evt, GPT_CLK_EVT);
+	mtk_gpt_enable_irq(evt, TIMER_CLK_EVT);
 
 	return 0;
 
@@ -265,4 +268,4 @@ err_kzalloc:
 
 	return -EINVAL;
 }
-TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_timer_init);
+TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
-- 
cgit v1.2.3


From a0858f937960d24e05cedf43d5cbcb95cf088434 Mon Sep 17 00:00:00 2001
From: Stanley Chu <stanley.chu@mediatek.com>
Date: Fri, 6 Jul 2018 07:11:27 +0800
Subject: clocksource/drivers/timer-mediatek: Convert the driver to timer-of

Convert the driver to use the timer_of helpers.
This allows to remove custom proprietary structure,
factors out and simplifies the code.

Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/timer-mediatek.c | 205 ++++++++++++++---------------------
 1 file changed, 80 insertions(+), 125 deletions(-)

diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
index e3657d29e765..e57c4d7414a4 100644
--- a/drivers/clocksource/timer-mediatek.c
+++ b/drivers/clocksource/timer-mediatek.c
@@ -18,16 +18,13 @@
 
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
-#include <linux/clk.h>
 #include <linux/clockchips.h>
+#include <linux/clocksource.h>
 #include <linux/interrupt.h>
-#include <linux/irq.h>
 #include <linux/irqreturn.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
 #include <linux/sched_clock.h>
 #include <linux/slab.h>
+#include "timer-of.h"
 
 #define TIMER_CLK_EVT           (1)
 #define TIMER_CLK_SRC           (2)
@@ -59,12 +56,6 @@
 #define GPT_CNT_REG(val)        (0x08 + (0x10 * (val)))
 #define GPT_CMP_REG(val)        (0x0C + (0x10 * (val)))
 
-struct mtk_clock_event_device {
-	void __iomem *gpt_base;
-	u32 ticks_per_jiffy;
-	struct clock_event_device dev;
-};
-
 static void __iomem *gpt_sched_reg __read_mostly;
 
 static u64 notrace mtk_gpt_read_sched_clock(void)
@@ -72,36 +63,30 @@ static u64 notrace mtk_gpt_read_sched_clock(void)
 	return readl_relaxed(gpt_sched_reg);
 }
 
-static inline struct mtk_clock_event_device *to_mtk_clk(
-				struct clock_event_device *c)
-{
-	return container_of(c, struct mtk_clock_event_device, dev);
-}
-
-static void mtk_gpt_clkevt_time_stop(struct mtk_clock_event_device *evt, u8 timer)
+static void mtk_gpt_clkevt_time_stop(struct timer_of *to, u8 timer)
 {
 	u32 val;
 
-	val = readl(evt->gpt_base + GPT_CTRL_REG(timer));
-	writel(val & ~GPT_CTRL_ENABLE, evt->gpt_base +
-			GPT_CTRL_REG(timer));
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
+	writel(val & ~GPT_CTRL_ENABLE, timer_of_base(to) +
+	       GPT_CTRL_REG(timer));
 }
 
-static void mtk_gpt_clkevt_time_setup(struct mtk_clock_event_device *evt,
-				unsigned long delay, u8 timer)
+static void mtk_gpt_clkevt_time_setup(struct timer_of *to,
+				      unsigned long delay, u8 timer)
 {
-	writel(delay, evt->gpt_base + GPT_CMP_REG(timer));
+	writel(delay, timer_of_base(to) + GPT_CMP_REG(timer));
 }
 
-static void mtk_gpt_clkevt_time_start(struct mtk_clock_event_device *evt,
-		bool periodic, u8 timer)
+static void mtk_gpt_clkevt_time_start(struct timer_of *to,
+				      bool periodic, u8 timer)
 {
 	u32 val;
 
 	/* Acknowledge interrupt */
-	writel(GPT_IRQ_ACK(timer), evt->gpt_base + GPT_IRQ_ACK_REG);
+	writel(GPT_IRQ_ACK(timer), timer_of_base(to) + GPT_IRQ_ACK_REG);
 
-	val = readl(evt->gpt_base + GPT_CTRL_REG(timer));
+	val = readl(timer_of_base(to) + GPT_CTRL_REG(timer));
 
 	/* Clear 2 bit timer operation mode field */
 	val &= ~GPT_CTRL_OP(0x3);
@@ -112,160 +97,130 @@ static void mtk_gpt_clkevt_time_start(struct mtk_clock_event_device *evt,
 		val |= GPT_CTRL_OP(GPT_CTRL_OP_ONESHOT);
 
 	writel(val | GPT_CTRL_ENABLE | GPT_CTRL_CLEAR,
-	       evt->gpt_base + GPT_CTRL_REG(timer));
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
 }
 
 static int mtk_gpt_clkevt_shutdown(struct clock_event_device *clk)
 {
-	mtk_gpt_clkevt_time_stop(to_mtk_clk(clk), TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_stop(to_timer_of(clk), TIMER_CLK_EVT);
+
 	return 0;
 }
 
 static int mtk_gpt_clkevt_set_periodic(struct clock_event_device *clk)
 {
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
+	struct timer_of *to = to_timer_of(clk);
+
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, to->of_clk.period, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, true, TIMER_CLK_EVT);
 
-	mtk_gpt_clkevt_time_stop(evt, TIMER_CLK_EVT);
-	mtk_gpt_clkevt_time_setup(evt, evt->ticks_per_jiffy, TIMER_CLK_EVT);
-	mtk_gpt_clkevt_time_start(evt, true, TIMER_CLK_EVT);
 	return 0;
 }
 
 static int mtk_gpt_clkevt_next_event(unsigned long event,
-				   struct clock_event_device *clk)
+				     struct clock_event_device *clk)
 {
-	struct mtk_clock_event_device *evt = to_mtk_clk(clk);
+	struct timer_of *to = to_timer_of(clk);
 
-	mtk_gpt_clkevt_time_stop(evt, TIMER_CLK_EVT);
-	mtk_gpt_clkevt_time_setup(evt, event, TIMER_CLK_EVT);
-	mtk_gpt_clkevt_time_start(evt, false, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_stop(to, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_setup(to, event, TIMER_CLK_EVT);
+	mtk_gpt_clkevt_time_start(to, false, TIMER_CLK_EVT);
 
 	return 0;
 }
 
 static irqreturn_t mtk_gpt_interrupt(int irq, void *dev_id)
 {
-	struct mtk_clock_event_device *evt = dev_id;
+	struct clock_event_device *clkevt = (struct clock_event_device *)dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
 
 	/* Acknowledge timer0 irq */
-	writel(GPT_IRQ_ACK(TIMER_CLK_EVT), evt->gpt_base + GPT_IRQ_ACK_REG);
-	evt->dev.event_handler(&evt->dev);
+	writel(GPT_IRQ_ACK(TIMER_CLK_EVT), timer_of_base(to) + GPT_IRQ_ACK_REG);
+	clkevt->event_handler(clkevt);
 
 	return IRQ_HANDLED;
 }
 
 static void
-__init mtk_gpt_setup(struct mtk_clock_event_device *evt, u8 timer, u8 option)
+__init mtk_gpt_setup(struct timer_of *to, u8 timer, u8 option)
 {
 	writel(GPT_CTRL_CLEAR | GPT_CTRL_DISABLE,
-		evt->gpt_base + GPT_CTRL_REG(timer));
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
 
 	writel(GPT_CLK_SRC(GPT_CLK_SRC_SYS13M) | GPT_CLK_DIV1,
-			evt->gpt_base + GPT_CLK_REG(timer));
+	       timer_of_base(to) + GPT_CLK_REG(timer));
 
-	writel(0x0, evt->gpt_base + GPT_CMP_REG(timer));
+	writel(0x0, timer_of_base(to) + GPT_CMP_REG(timer));
 
 	writel(GPT_CTRL_OP(option) | GPT_CTRL_ENABLE,
-			evt->gpt_base + GPT_CTRL_REG(timer));
+	       timer_of_base(to) + GPT_CTRL_REG(timer));
 }
 
-static void mtk_gpt_enable_irq(struct mtk_clock_event_device *evt, u8 timer)
+static void mtk_gpt_enable_irq(struct timer_of *to, u8 timer)
 {
 	u32 val;
 
 	/* Disable all interrupts */
-	writel(0x0, evt->gpt_base + GPT_IRQ_EN_REG);
+	writel(0x0, timer_of_base(to) + GPT_IRQ_EN_REG);
 
 	/* Acknowledge all spurious pending interrupts */
-	writel(0x3f, evt->gpt_base + GPT_IRQ_ACK_REG);
+	writel(0x3f, timer_of_base(to) + GPT_IRQ_ACK_REG);
 
-	val = readl(evt->gpt_base + GPT_IRQ_EN_REG);
+	val = readl(timer_of_base(to) + GPT_IRQ_EN_REG);
 	writel(val | GPT_IRQ_ENABLE(timer),
-			evt->gpt_base + GPT_IRQ_EN_REG);
+	       timer_of_base(to) + GPT_IRQ_EN_REG);
 }
 
+static struct timer_of to = {
+	.flags = TIMER_OF_IRQ | TIMER_OF_BASE | TIMER_OF_CLOCK,
+
+	.clkevt = {
+		.name = "mtk-clkevt",
+		.rating = 300,
+		.cpumask = cpu_possible_mask,
+	},
+
+	.of_irq = {
+		.flags = IRQF_TIMER | IRQF_IRQPOLL,
+	},
+};
+
 static int __init mtk_gpt_init(struct device_node *node)
 {
-	struct mtk_clock_event_device *evt;
-	struct resource res;
-	unsigned long rate = 0;
-	struct clk *clk;
-
-	evt = kzalloc(sizeof(*evt), GFP_KERNEL);
-	if (!evt)
-		return -ENOMEM;
-
-	evt->dev.name = "mtk_tick";
-	evt->dev.rating = 300;
-	evt->dev.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
-	evt->dev.set_state_shutdown = mtk_gpt_clkevt_shutdown;
-	evt->dev.set_state_periodic = mtk_gpt_clkevt_set_periodic;
-	evt->dev.set_state_oneshot = mtk_gpt_clkevt_shutdown;
-	evt->dev.tick_resume = mtk_gpt_clkevt_shutdown;
-	evt->dev.set_next_event = mtk_gpt_clkevt_next_event;
-	evt->dev.cpumask = cpu_possible_mask;
-
-	evt->gpt_base = of_io_request_and_map(node, 0, "mtk-timer-gpt");
-	if (IS_ERR(evt->gpt_base)) {
-		pr_err("Can't get resource\n");
-		goto err_kzalloc;
-	}
-
-	evt->dev.irq = irq_of_parse_and_map(node, 0);
-	if (evt->dev.irq <= 0) {
-		pr_err("Can't parse IRQ\n");
-		goto err_mem;
-	}
-
-	clk = of_clk_get(node, 0);
-	if (IS_ERR(clk)) {
-		pr_err("Can't get timer clock\n");
-		goto err_irq;
-	}
-
-	if (clk_prepare_enable(clk)) {
-		pr_err("Can't prepare clock\n");
-		goto err_clk_put;
-	}
-	rate = clk_get_rate(clk);
-
-	if (request_irq(evt->dev.irq, mtk_gpt_interrupt,
-			IRQF_TIMER | IRQF_IRQPOLL, "mtk_timer", evt)) {
-		pr_err("failed to setup irq %d\n", evt->dev.irq);
-		goto err_clk_disable;
-	}
-
-	evt->ticks_per_jiffy = DIV_ROUND_UP(rate, HZ);
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_state_periodic = mtk_gpt_clkevt_set_periodic;
+	to.clkevt.set_state_oneshot = mtk_gpt_clkevt_shutdown;
+	to.clkevt.tick_resume = mtk_gpt_clkevt_shutdown;
+	to.clkevt.set_next_event = mtk_gpt_clkevt_next_event;
+	to.of_irq.handler = mtk_gpt_interrupt;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
 
 	/* Configure clock source */
-	mtk_gpt_setup(evt, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
-	clocksource_mmio_init(evt->gpt_base + GPT_CNT_REG(TIMER_CLK_SRC),
-			node->name, rate, 300, 32, clocksource_mmio_readl_up);
-	gpt_sched_reg = evt->gpt_base + GPT_CNT_REG(TIMER_CLK_SRC);
-	sched_clock_register(mtk_gpt_read_sched_clock, 32, rate);
+	mtk_gpt_setup(&to, TIMER_CLK_SRC, GPT_CTRL_OP_FREERUN);
+	clocksource_mmio_init(timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC),
+			      node->name, timer_of_rate(&to), 300, 32,
+			      clocksource_mmio_readl_up);
+	gpt_sched_reg = timer_of_base(&to) + GPT_CNT_REG(TIMER_CLK_SRC);
+	sched_clock_register(mtk_gpt_read_sched_clock, 32, timer_of_rate(&to));
 
 	/* Configure clock event */
-	mtk_gpt_setup(evt, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT);
-	clockevents_config_and_register(&evt->dev, rate, TIMER_SYNC_TICKS,
-					0xffffffff);
+	mtk_gpt_setup(&to, TIMER_CLK_EVT, GPT_CTRL_OP_REPEAT);
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
 
-	mtk_gpt_enable_irq(evt, TIMER_CLK_EVT);
+	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
 
 	return 0;
 
-err_clk_disable:
-	clk_disable_unprepare(clk);
-err_clk_put:
-	clk_put(clk);
-err_irq:
-	irq_dispose_mapping(evt->dev.irq);
-err_mem:
-	iounmap(evt->gpt_base);
-	of_address_to_resource(node, 0, &res);
-	release_mem_region(res.start, resource_size(&res));
-err_kzalloc:
-	kfree(evt);
-
-	return -EINVAL;
+err:
+	timer_of_cleanup(&to);
+	return ret;
 }
 TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
-- 
cgit v1.2.3


From e3af677607d9daca9825bc98edfb5cedda5718a9 Mon Sep 17 00:00:00 2001
From: Stanley Chu <stanley.chu@mediatek.com>
Date: Fri, 6 Jul 2018 07:11:28 +0800
Subject: clocksource/drivers/timer-mediatek: Add support for system timer

This patch adds a new "System Timer" on the Mediatek SoCs.

The System Timer is introduced as an always-on timer being
clockevent device for tick-broadcasting.

For clock, it is driven by 13 MHz system clock.
The implementation uses the system clock with no clock
source divider.

For interrupt, the clock event timer can be used by all cores.

Signed-off-by: Stanley Chu <stanley.chu@mediatek.com>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/timer-mediatek.c | 104 ++++++++++++++++++++++++++++++++++-
 1 file changed, 103 insertions(+), 1 deletion(-)

diff --git a/drivers/clocksource/timer-mediatek.c b/drivers/clocksource/timer-mediatek.c
index e57c4d7414a4..eb10321f8517 100644
--- a/drivers/clocksource/timer-mediatek.c
+++ b/drivers/clocksource/timer-mediatek.c
@@ -56,8 +56,86 @@
 #define GPT_CNT_REG(val)        (0x08 + (0x10 * (val)))
 #define GPT_CMP_REG(val)        (0x0C + (0x10 * (val)))
 
+/* system timer */
+#define SYST_BASE               (0x40)
+
+#define SYST_CON                (SYST_BASE + 0x0)
+#define SYST_VAL                (SYST_BASE + 0x4)
+
+#define SYST_CON_REG(to)        (timer_of_base(to) + SYST_CON)
+#define SYST_VAL_REG(to)        (timer_of_base(to) + SYST_VAL)
+
+/*
+ * SYST_CON_EN: Clock enable. Shall be set to
+ *   - Start timer countdown.
+ *   - Allow timeout ticks being updated.
+ *   - Allow changing interrupt functions.
+ *
+ * SYST_CON_IRQ_EN: Set to allow interrupt.
+ *
+ * SYST_CON_IRQ_CLR: Set to clear interrupt.
+ */
+#define SYST_CON_EN              BIT(0)
+#define SYST_CON_IRQ_EN          BIT(1)
+#define SYST_CON_IRQ_CLR         BIT(4)
+
 static void __iomem *gpt_sched_reg __read_mostly;
 
+static void mtk_syst_ack_irq(struct timer_of *to)
+{
+	/* Clear and disable interrupt */
+	writel(SYST_CON_IRQ_CLR | SYST_CON_EN, SYST_CON_REG(to));
+}
+
+static irqreturn_t mtk_syst_handler(int irq, void *dev_id)
+{
+	struct clock_event_device *clkevt = dev_id;
+	struct timer_of *to = to_timer_of(clkevt);
+
+	mtk_syst_ack_irq(to);
+	clkevt->event_handler(clkevt);
+
+	return IRQ_HANDLED;
+}
+
+static int mtk_syst_clkevt_next_event(unsigned long ticks,
+				      struct clock_event_device *clkevt)
+{
+	struct timer_of *to = to_timer_of(clkevt);
+
+	/* Enable clock to allow timeout tick update later */
+	writel(SYST_CON_EN, SYST_CON_REG(to));
+
+	/*
+	 * Write new timeout ticks. Timer shall start countdown
+	 * after timeout ticks are updated.
+	 */
+	writel(ticks, SYST_VAL_REG(to));
+
+	/* Enable interrupt */
+	writel(SYST_CON_EN | SYST_CON_IRQ_EN, SYST_CON_REG(to));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_shutdown(struct clock_event_device *clkevt)
+{
+	/* Disable timer */
+	writel(0, SYST_CON_REG(to_timer_of(clkevt)));
+
+	return 0;
+}
+
+static int mtk_syst_clkevt_resume(struct clock_event_device *clkevt)
+{
+	return mtk_syst_clkevt_shutdown(clkevt);
+}
+
+static int mtk_syst_clkevt_oneshot(struct clock_event_device *clkevt)
+{
+	return 0;
+}
+
 static u64 notrace mtk_gpt_read_sched_clock(void)
 {
 	return readl_relaxed(gpt_sched_reg);
@@ -186,6 +264,30 @@ static struct timer_of to = {
 	},
 };
 
+static int __init mtk_syst_init(struct device_node *node)
+{
+	int ret;
+
+	to.clkevt.features = CLOCK_EVT_FEAT_DYNIRQ | CLOCK_EVT_FEAT_ONESHOT;
+	to.clkevt.set_state_shutdown = mtk_syst_clkevt_shutdown;
+	to.clkevt.set_state_oneshot = mtk_syst_clkevt_oneshot;
+	to.clkevt.tick_resume = mtk_syst_clkevt_resume;
+	to.clkevt.set_next_event = mtk_syst_clkevt_next_event;
+	to.of_irq.handler = mtk_syst_handler;
+
+	ret = timer_of_init(node, &to);
+	if (ret)
+		goto err;
+
+	clockevents_config_and_register(&to.clkevt, timer_of_rate(&to),
+					TIMER_SYNC_TICKS, 0xffffffff);
+
+	return 0;
+err:
+	timer_of_cleanup(&to);
+	return ret;
+}
+
 static int __init mtk_gpt_init(struct device_node *node)
 {
 	int ret;
@@ -218,9 +320,9 @@ static int __init mtk_gpt_init(struct device_node *node)
 	mtk_gpt_enable_irq(&to, TIMER_CLK_EVT);
 
 	return 0;
-
 err:
 	timer_of_cleanup(&to);
 	return ret;
 }
 TIMER_OF_DECLARE(mtk_mt6577, "mediatek,mt6577-timer", mtk_gpt_init);
+TIMER_OF_DECLARE(mtk_mt6765, "mediatek,mt6765-timer", mtk_syst_init);
-- 
cgit v1.2.3


From 1569557549697207e52310cc5b7dbc8e64bef504 Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linaro.org>
Date: Tue, 17 Jul 2018 15:55:17 +0800
Subject: clocksource/drivers/sprd: Register one always-on timer to compensate
 suspend time

Since the clocksource framework has introduced one suspend clocksource to
compensate the suspend time, this patch registers one always-on timer as
the suspend clocksource.

Signed-off-by: Baolin Wang <baolin.wang@linaro.org>
Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/timer-sprd.c | 50 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/drivers/clocksource/timer-sprd.c b/drivers/clocksource/timer-sprd.c
index ef9ebeafb3ed..430cb99d8d79 100644
--- a/drivers/clocksource/timer-sprd.c
+++ b/drivers/clocksource/timer-sprd.c
@@ -156,4 +156,54 @@ static int __init sprd_timer_init(struct device_node *np)
 	return 0;
 }
 
+static struct timer_of suspend_to = {
+	.flags = TIMER_OF_BASE | TIMER_OF_CLOCK,
+};
+
+static u64 sprd_suspend_timer_read(struct clocksource *cs)
+{
+	return ~(u64)readl_relaxed(timer_of_base(&suspend_to) +
+				   TIMER_VALUE_SHDW_LO) & cs->mask;
+}
+
+static int sprd_suspend_timer_enable(struct clocksource *cs)
+{
+	sprd_timer_update_counter(timer_of_base(&suspend_to),
+				  TIMER_VALUE_LO_MASK);
+	sprd_timer_enable(timer_of_base(&suspend_to), TIMER_CTL_PERIOD_MODE);
+
+	return 0;
+}
+
+static void sprd_suspend_timer_disable(struct clocksource *cs)
+{
+	sprd_timer_disable(timer_of_base(&suspend_to));
+}
+
+static struct clocksource suspend_clocksource = {
+	.name	= "sprd_suspend_timer",
+	.rating	= 200,
+	.read	= sprd_suspend_timer_read,
+	.enable = sprd_suspend_timer_enable,
+	.disable = sprd_suspend_timer_disable,
+	.mask	= CLOCKSOURCE_MASK(32),
+	.flags	= CLOCK_SOURCE_IS_CONTINUOUS | CLOCK_SOURCE_SUSPEND_NONSTOP,
+};
+
+static int __init sprd_suspend_timer_init(struct device_node *np)
+{
+	int ret;
+
+	ret = timer_of_init(np, &suspend_to);
+	if (ret)
+		return ret;
+
+	clocksource_register_hz(&suspend_clocksource,
+				timer_of_rate(&suspend_to));
+
+	return 0;
+}
+
 TIMER_OF_DECLARE(sc9860_timer, "sprd,sc9860-timer", sprd_timer_init);
+TIMER_OF_DECLARE(sc9860_persistent_timer, "sprd,sc9860-suspend-timer",
+		 sprd_suspend_timer_init);
-- 
cgit v1.2.3


From 8a6171a7b601e37596d543efadae1d3913ac084e Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Tue, 26 Jun 2018 10:13:20 +0300
Subject: iwlwifi: fw: add FW APIs for HE

Add the FW API definitions for HE support.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/datapath.h   |   5 +
 drivers/net/wireless/intel/iwlwifi/fw/api/mac.h    | 172 +++++++++++++++++++++
 .../net/wireless/intel/iwlwifi/fw/api/nvm-reg.h    |   4 +-
 drivers/net/wireless/intel/iwlwifi/fw/api/rs.h     |  36 ++++-
 drivers/net/wireless/intel/iwlwifi/fw/api/rx.h     |  53 ++++++-
 5 files changed, 257 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
index 5f6e855006dd..c1bf3898f8b6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
@@ -82,6 +82,11 @@ enum iwl_data_path_subcmd_ids {
 	 */
 	TRIGGER_RX_QUEUES_NOTIF_CMD = 0x2,
 
+	/**
+	 * @STA_HE_CTXT_CMD: &struct iwl_he_sta_context_cmd
+	 */
+	STA_HE_CTXT_CMD = 0x7,
+
 	/**
 	 * @TLC_MNG_CONFIG_CMD: &struct iwl_tlc_config_cmd
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
index f2e31e040a7b..55594c93b014 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017        Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,6 +29,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2017        Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -279,6 +281,10 @@ enum iwl_mac_filter_flags {
 	MAC_FILTER_OUT_BCAST		= BIT(8),
 	MAC_FILTER_IN_CRC32		= BIT(11),
 	MAC_FILTER_IN_PROBE_REQUEST	= BIT(12),
+	/**
+	 * @MAC_FILTER_IN_11AX: mark BSS as supporting 802.11ax
+	 */
+	MAC_FILTER_IN_11AX		= BIT(14),
 };
 
 /**
@@ -406,4 +412,170 @@ struct iwl_missed_beacons_notif {
 	__le32 num_recvd_beacons;
 } __packed; /* MISSED_BEACON_NTFY_API_S_VER_3 */
 
+/**
+ * struct iwl_he_backoff_conf - used for backoff configuration
+ * Per each trigger-based AC, (set by MU EDCA Parameter set info-element)
+ * used for backoff configuration of TXF5..TXF8 trigger based.
+ * The MU-TIMER is reloaded w/ MU_TIME each time a frame from the AC is sent via
+ * trigger-based TX.
+ * @cwmin: CW min
+ * @cwmax: CW max
+ * @aifsn: AIFSN
+ *	AIFSN=0, means that no backoff from the specified TRIG-BASED AC is
+ *	allowed till the MU-TIMER is 0
+ * @mu_time: MU time in 8TU units
+ */
+struct iwl_he_backoff_conf {
+	__le16 cwmin;
+	__le16 cwmax;
+	__le16 aifsn;
+	__le16 mu_time;
+} __packed; /* AC_QOS_DOT11AX_API_S */
+
+#define MAX_HE_SUPP_NSS	2
+#define MAX_HE_CHANNEL_BW_INDX	4
+
+/**
+ * struct iwl_he_pkt_ext - QAM thresholds
+ * The required PPE is set via HE Capabilities IE, per Nss x BW x MCS
+ * The IE is organized in the following way:
+ * Support for Nss x BW (or RU) matrix:
+ *	(0=SISO, 1=MIMO2) x (0-20MHz, 1-40MHz, 2-80MHz, 3-160MHz)
+ * Each entry contains 2 QAM thresholds for 8us and 16us:
+ *	0=BPSK, 1=QPSK, 2=16QAM, 3=64QAM, 4=256QAM, 5=1024QAM, 6/7=RES
+ * i.e. QAM_th1 < QAM_th2 such if TX uses QAM_tx:
+ *	QAM_tx < QAM_th1            --> PPE=0us
+ *	QAM_th1 <= QAM_tx < QAM_th2 --> PPE=8us
+ *	QAM_th2 <= QAM_tx           --> PPE=16us
+ * @pkt_ext_qam_th: QAM thresholds
+ *	For each Nss/Bw define 2 QAM thrsholds (0..5)
+ *	For rates below the low_th, no need for PPE
+ *	For rates between low_th and high_th, need 8us PPE
+ *	For rates equal or higher then the high_th, need 16us PPE
+ *	Nss (0-siso, 1-mimo2) x BW (0-20MHz, 1-40MHz, 2-80MHz, 3-160MHz) x
+ *		(0-low_th, 1-high_th)
+ */
+struct iwl_he_pkt_ext {
+	u8 pkt_ext_qam_th[MAX_HE_SUPP_NSS][MAX_HE_CHANNEL_BW_INDX][2];
+} __packed; /* PKT_EXT_DOT11AX_API_S */
+
+/**
+ * enum iwl_he_sta_ctxt_flags - HE STA context flags
+ * @STA_CTXT_HE_REF_BSSID_VALID: ref bssid addr valid (for receiving specific
+ *	control frames such as TRIG, NDPA, BACK)
+ * @STA_CTXT_HE_BSS_COLOR_DIS: BSS color disable, don't use the BSS
+ *	color for RX filter but use MAC header
+ * @STA_CTXT_HE_PARTIAL_BSS_COLOR: partial BSS color allocation
+ * @STA_CTXT_HE_32BIT_BA_BITMAP: indicates the receiver supports BA bitmap
+ *	of 32-bits
+ * @STA_CTXT_HE_PACKET_EXT: indicates that the packet-extension info is valid
+ *	and should be used
+ * @STA_CTXT_HE_TRIG_RND_ALLOC: indicates that trigger based random allocation
+ *	is enabled according to UORA element existence
+ * @STA_CTXT_HE_CONST_TRIG_RND_ALLOC: used for AV testing
+ * @STA_CTXT_HE_ACK_ENABLED: indicates that the AP supports receiving ACK-
+ *	enabled AGG, i.e. both BACK and non-BACK frames in a single AGG
+ * @STA_CTXT_HE_MU_EDCA_CW: indicates that there is an element of MU EDCA
+ *	parameter set, i.e. the backoff counters for trig-based ACs
+ */
+enum iwl_he_sta_ctxt_flags {
+	STA_CTXT_HE_REF_BSSID_VALID		= BIT(4),
+	STA_CTXT_HE_BSS_COLOR_DIS		= BIT(5),
+	STA_CTXT_HE_PARTIAL_BSS_COLOR		= BIT(6),
+	STA_CTXT_HE_32BIT_BA_BITMAP		= BIT(7),
+	STA_CTXT_HE_PACKET_EXT			= BIT(8),
+	STA_CTXT_HE_TRIG_RND_ALLOC		= BIT(9),
+	STA_CTXT_HE_CONST_TRIG_RND_ALLOC	= BIT(10),
+	STA_CTXT_HE_ACK_ENABLED			= BIT(11),
+	STA_CTXT_HE_MU_EDCA_CW			= BIT(12),
+};
+
+/**
+ * enum iwl_he_htc_flags - HE HTC support flags
+ * @IWL_HE_HTC_SUPPORT: HE-HTC support
+ * @IWL_HE_HTC_UL_MU_RESP_SCHED: HE UL MU response schedule
+ *	support via A-control field
+ * @IWL_HE_HTC_BSR_SUPP: BSR support in A-control field
+ * @IWL_HE_HTC_OMI_SUPP: A-OMI support in A-control field
+ * @IWL_HE_HTC_BQR_SUPP: A-BQR support in A-control field
+ */
+enum iwl_he_htc_flags {
+	IWL_HE_HTC_SUPPORT			= BIT(0),
+	IWL_HE_HTC_UL_MU_RESP_SCHED		= BIT(3),
+	IWL_HE_HTC_BSR_SUPP			= BIT(4),
+	IWL_HE_HTC_OMI_SUPP			= BIT(5),
+	IWL_HE_HTC_BQR_SUPP			= BIT(6),
+};
+
+/*
+ * @IWL_HE_HTC_LINK_ADAP_NO_FEEDBACK: the STA does not provide HE MFB
+ * @IWL_HE_HTC_LINK_ADAP_UNSOLICITED: the STA provides only unsolicited HE MFB
+ * @IWL_HE_HTC_LINK_ADAP_BOTH: the STA is capable of providing HE MFB in
+ *      response to HE MRQ and if the STA provides unsolicited HE MFB
+ */
+#define IWL_HE_HTC_LINK_ADAP_POS		(1)
+#define IWL_HE_HTC_LINK_ADAP_NO_FEEDBACK	(0)
+#define IWL_HE_HTC_LINK_ADAP_UNSOLICITED	(2 << IWL_HE_HTC_LINK_ADAP_POS)
+#define IWL_HE_HTC_LINK_ADAP_BOTH		(3 << IWL_HE_HTC_LINK_ADAP_POS)
+
+/**
+ * struct iwl_he_sta_context_cmd - configure FW to work with HE AP
+ * @sta_id: STA id
+ * @tid_limit: max num of TIDs in TX HE-SU multi-TID agg
+ *	0 - bad value, 1 - multi-tid not supported, 2..8 - tid limit
+ * @reserved1: reserved byte for future use
+ * @reserved2: reserved byte for future use
+ * @flags: see %iwl_11ax_sta_ctxt_flags
+ * @ref_bssid_addr: reference BSSID used by the AP
+ * @reserved0: reserved 2 bytes for aligning the ref_bssid_addr field to 8 bytes
+ * @htc_flags: which features are supported in HTC
+ * @frag_flags: frag support in A-MSDU
+ * @frag_level: frag support level
+ * @frag_max_num: max num of "open" MSDUs in the receiver (in power of 2)
+ * @frag_min_size: min frag size (except last frag)
+ * @pkt_ext: optional, exists according to PPE-present bit in the HE-PHY capa
+ * @bss_color: 11ax AP ID that is used in the HE SIG-A to mark inter BSS frame
+ * @htc_trig_based_pkt_ext: default PE in 4us units
+ * @frame_time_rts_th: HE duration RTS threshold, in units of 32us
+ * @rand_alloc_ecwmin: random CWmin = 2**ECWmin-1
+ * @rand_alloc_ecwmax: random CWmax = 2**ECWmax-1
+ * @reserved3: reserved byte for future use
+ * @trig_based_txf: MU EDCA Parameter set for the trigger based traffic queues
+ */
+struct iwl_he_sta_context_cmd {
+	u8 sta_id;
+	u8 tid_limit;
+	u8 reserved1;
+	u8 reserved2;
+	__le32 flags;
+
+	/* The below fields are set via Multiple BSSID IE */
+	u8 ref_bssid_addr[6];
+	__le16 reserved0;
+
+	/* The below fields are set via HE-capabilities IE */
+	__le32 htc_flags;
+
+	u8 frag_flags;
+	u8 frag_level;
+	u8 frag_max_num;
+	u8 frag_min_size;
+
+	/* The below fields are set via PPE thresholds element */
+	struct iwl_he_pkt_ext pkt_ext;
+
+	/* The below fields are set via HE-Operation IE */
+	u8 bss_color;
+	u8 htc_trig_based_pkt_ext;
+	__le16 frame_time_rts_th;
+
+	/* Random access parameter set (i.e. RAPS) */
+	u8 rand_alloc_ecwmin;
+	u8 rand_alloc_ecwmax;
+	__le16 reserved3;
+
+	/* The below fields are set via MU EDCA parameter set element */
+	struct iwl_he_backoff_conf trig_based_txf[AC_NUM];
+} __packed; /* STA_CONTEXT_DOT11AX_API_S */
+
 #endif /* __iwl_fw_api_mac_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
index 8d6dc9189985..6c5338364794 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/nvm-reg.h
@@ -195,7 +195,6 @@ struct iwl_nvm_get_info_general {
  * @NVM_MAC_SKU_FLAGS_BAND_5_2_ENABLED: true if 5.2 band enabled
  * @NVM_MAC_SKU_FLAGS_802_11N_ENABLED: true if 11n enabled
  * @NVM_MAC_SKU_FLAGS_802_11AC_ENABLED: true if 11ac enabled
- * @NVM_MAC_SKU_FLAGS_802_11AX_ENABLED: true if 11ax enabled
  * @NVM_MAC_SKU_FLAGS_MIMO_DISABLED: true if MIMO disabled
  * @NVM_MAC_SKU_FLAGS_WAPI_ENABLED: true if WAPI enabled
  * @NVM_MAC_SKU_FLAGS_REG_CHECK_ENABLED: true if regulatory checker enabled
@@ -206,6 +205,9 @@ enum iwl_nvm_mac_sku_flags {
 	NVM_MAC_SKU_FLAGS_BAND_5_2_ENABLED	= BIT(1),
 	NVM_MAC_SKU_FLAGS_802_11N_ENABLED	= BIT(2),
 	NVM_MAC_SKU_FLAGS_802_11AC_ENABLED	= BIT(3),
+	/**
+	 * @NVM_MAC_SKU_FLAGS_802_11AX_ENABLED: true if 11ax enabled
+	 */
 	NVM_MAC_SKU_FLAGS_802_11AX_ENABLED	= BIT(4),
 	NVM_MAC_SKU_FLAGS_MIMO_DISABLED		= BIT(5),
 	NVM_MAC_SKU_FLAGS_WAPI_ENABLED		= BIT(8),
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
index 21e13a315421..087fae91baef 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
@@ -314,8 +314,11 @@ enum {
 	IWL_RATE_MCS_8_INDEX,
 	IWL_RATE_MCS_9_INDEX,
 	IWL_LAST_VHT_RATE = IWL_RATE_MCS_9_INDEX,
+	IWL_RATE_MCS_10_INDEX,
+	IWL_RATE_MCS_11_INDEX,
+	IWL_LAST_HE_RATE = IWL_RATE_MCS_11_INDEX,
 	IWL_RATE_COUNT_LEGACY = IWL_LAST_NON_HT_RATE + 1,
-	IWL_RATE_COUNT = IWL_LAST_VHT_RATE + 1,
+	IWL_RATE_COUNT = IWL_LAST_HE_RATE + 1,
 };
 
 #define IWL_RATE_BIT_MSK(r) BIT(IWL_RATE_##r##M_INDEX)
@@ -440,8 +443,8 @@ enum {
 #define RATE_LEGACY_RATE_MSK 0xff
 
 /* Bit 10 - OFDM HE */
-#define RATE_MCS_OFDM_HE_POS		10
-#define RATE_MCS_OFDM_HE_MSK		BIT(RATE_MCS_OFDM_HE_POS)
+#define RATE_MCS_HE_POS		10
+#define RATE_MCS_HE_MSK		BIT(RATE_MCS_HE_POS)
 
 /*
  * Bit 11-12: (0) 20MHz, (1) 40MHz, (2) 80MHz, (3) 160MHz
@@ -482,15 +485,33 @@ enum {
 #define RATE_MCS_BF_MSK			(1 << RATE_MCS_BF_POS)
 
 /*
- * Bit 20-21: HE guard interval and LTF type.
- * (0) 1xLTF+1.6us, (1) 2xLTF+0.8us,
- * (2) 2xLTF+1.6us, (3) 4xLTF+3.2us
+ * Bit 20-21: HE LTF type and guard interval
+ * HE (ext) SU:
+ *	0			1xLTF+0.8us
+ *	1			2xLTF+0.8us
+ *	2			2xLTF+1.6us
+ *	3 & SGI (bit 13) clear	4xLTF+3.2us
+ *	3 & SGI (bit 13) set	4xLTF+0.8us
+ * HE MU:
+ *	0			4xLTF+0.8us
+ *	1			2xLTF+0.8us
+ *	2			2xLTF+1.6us
+ *	3			4xLTF+3.2us
+ * HE TRIG:
+ *	0			1xLTF+1.6us
+ *	1			2xLTF+1.6us
+ *	2			4xLTF+3.2us
+ *	3			(does not occur)
  */
 #define RATE_MCS_HE_GI_LTF_POS		20
 #define RATE_MCS_HE_GI_LTF_MSK		(3 << RATE_MCS_HE_GI_LTF_POS)
 
 /* Bit 22-23: HE type. (0) SU, (1) SU_EXT, (2) MU, (3) trigger based */
 #define RATE_MCS_HE_TYPE_POS		22
+#define RATE_MCS_HE_TYPE_SU		(0 << RATE_MCS_HE_TYPE_POS)
+#define RATE_MCS_HE_TYPE_EXT_SU		(1 << RATE_MCS_HE_TYPE_POS)
+#define RATE_MCS_HE_TYPE_MU		(2 << RATE_MCS_HE_TYPE_POS)
+#define RATE_MCS_HE_TYPE_TRIG		(3 << RATE_MCS_HE_TYPE_POS)
 #define RATE_MCS_HE_TYPE_MSK		(3 << RATE_MCS_HE_TYPE_POS)
 
 /* Bit 24-25: (0) 20MHz (no dup), (1) 2x20MHz, (2) 4x20MHz, 3 8x20MHz */
@@ -501,6 +522,9 @@ enum {
 #define RATE_MCS_LDPC_POS		27
 #define RATE_MCS_LDPC_MSK		(1 << RATE_MCS_LDPC_POS)
 
+/* Bit 28: (1) 106-tone RX (8 MHz RU), (0) normal bandwidth */
+#define RATE_MCS_HE_106T_POS		28
+#define RATE_MCS_HE_106T_MSK		(1 << RATE_MCS_HE_106T_POS)
 
 /* Link Quality definitions */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index 7e570c4a9df0..0daa09c94b0f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -343,6 +345,37 @@ enum iwl_rx_mpdu_mac_info {
 	IWL_RX_MPDU_PHY_PHY_INDEX_MASK		= 0xf0,
 };
 
+/*
+ * enum iwl_rx_he_phy - HE PHY data
+ */
+enum iwl_rx_he_phy {
+	IWL_RX_HE_PHY_BEAM_CHNG			= BIT(0),
+	IWL_RX_HE_PHY_UPLINK			= BIT(1),
+	IWL_RX_HE_PHY_BSS_COLOR_MASK		= 0xfc,
+	IWL_RX_HE_PHY_SPATIAL_REUSE_MASK	= 0xf00,
+	IWL_RX_HE_PHY_SU_EXT_BW10		= BIT(12),
+	IWL_RX_HE_PHY_TXOP_DUR_MASK		= 0xfe000,
+	IWL_RX_HE_PHY_LDPC_EXT_SYM		= BIT(20),
+	IWL_RX_HE_PHY_PRE_FEC_PAD_MASK		= 0x600000,
+	IWL_RX_HE_PHY_PE_DISAMBIG		= BIT(23),
+	IWL_RX_HE_PHY_DOPPLER			= BIT(24),
+	/* 6 bits reserved */
+	IWL_RX_HE_PHY_DELIM_EOF			= BIT(31),
+
+	/* second dword - MU data */
+	IWL_RX_HE_PHY_SIGB_COMPRESSION		= BIT_ULL(32 + 0),
+	IWL_RX_HE_PHY_SIBG_SYM_OR_USER_NUM_MASK	= 0x1e00000000ULL,
+	IWL_RX_HE_PHY_HE_LTF_NUM_MASK		= 0xe000000000ULL,
+	IWL_RX_HE_PHY_RU_ALLOC_SEC80		= BIT_ULL(32 + 8),
+	/* trigger encoded */
+	IWL_RX_HE_PHY_RU_ALLOC_MASK		= 0xfe0000000000ULL,
+	IWL_RX_HE_PHY_SIGB_MCS_MASK		= 0xf000000000000ULL,
+	/* 1 bit reserved */
+	IWL_RX_HE_PHY_SIGB_DCM			= BIT_ULL(32 + 21),
+	IWL_RX_HE_PHY_PREAMBLE_PUNC_TYPE_MASK	= 0xc0000000000000ULL,
+	/* 8 bits reserved */
+};
+
 /**
  * struct iwl_rx_mpdu_desc - RX MPDU descriptor
  */
@@ -438,12 +471,20 @@ struct iwl_rx_mpdu_desc {
 	 */
 	__le32 gp2_on_air_rise;
 	/* DW12 & DW13 */
-	/**
-	 * @tsf_on_air_rise:
-	 * TSF value on air rise (INA), only valid if
-	 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
-	 */
-	__le64 tsf_on_air_rise;
+	union {
+		/**
+		 * @tsf_on_air_rise:
+		 * TSF value on air rise (INA), only valid if
+		 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
+		 */
+		__le64 tsf_on_air_rise;
+		/**
+		 * @he_phy_data:
+		 * HE PHY data, see &enum iwl_rx_he_phy, valid
+		 * only if %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set
+		 */
+		__le64 he_phy_data;
+	};
 } __packed;
 
 struct iwl_frame_release {
-- 
cgit v1.2.3


From 514c30696fbc2598a088f8c5e201d305d157b99a Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sun, 24 Jun 2018 11:59:54 +0300
Subject: iwlwifi: add support for IEEE802.11ax

Add support for the HE in the iwlwifi driver conforming with
P802.11ax_D2.0.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 103 +++++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c  |   3 +
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  | 197 ++++++++++++++++++++-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h       |   2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       |   1 +
 drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c     |  44 ++++-
 drivers/net/wireless/intel/iwlwifi/mvm/rs.c        |  39 +++-
 drivers/net/wireless/intel/iwlwifi/mvm/rs.h        |  21 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c      | 122 ++++++++++++-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c       |   8 +-
 drivers/net/wireless/intel/iwlwifi/mvm/sta.h       |   6 +-
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    |   2 +-
 12 files changed, 525 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index b815ba38dbdb..941604c24fa1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -463,6 +463,101 @@ static void iwl_init_vht_hw_capab(const struct iwl_cfg *cfg,
 	vht_cap->vht_mcs.tx_mcs_map = vht_cap->vht_mcs.rx_mcs_map;
 }
 
+static struct ieee80211_sband_iftype_data iwl_he_capa = {
+	.types_mask = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP),
+	.he_cap = {
+		.has_he = true,
+		.he_cap_elem = {
+			.mac_cap_info[0] =
+				IEEE80211_HE_MAC_CAP0_HTC_HE,
+			.mac_cap_info[1] =
+				IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US |
+				IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_QOS_8,
+			.mac_cap_info[2] =
+				IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP |
+				IEEE80211_HE_MAC_CAP2_ACK_EN,
+			.mac_cap_info[3] =
+				IEEE80211_HE_MAC_CAP3_GRP_ADDR_MULTI_STA_BA_DL_MU |
+				IEEE80211_HE_MAC_CAP3_MAX_A_AMPDU_LEN_EXP_VHT_2,
+			.mac_cap_info[4] = IEEE80211_HE_MAC_CAP4_AMDSU_IN_AMPDU,
+			.phy_cap_info[0] =
+				IEEE80211_HE_PHY_CAP0_DUAL_BAND |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
+				IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G,
+			.phy_cap_info[1] =
+				IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A |
+				IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD |
+				IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS,
+			.phy_cap_info[2] =
+				IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US |
+				IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ |
+				IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ,
+			.phy_cap_info[3] =
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK |
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1 |
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK |
+				IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1,
+			.phy_cap_info[4] =
+				IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE |
+				IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8 |
+				IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8,
+			.phy_cap_info[5] =
+				IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2 |
+				IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2,
+			.phy_cap_info[6] =
+				IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT,
+			.phy_cap_info[7] =
+				IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_AR |
+				IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI |
+				IEEE80211_HE_PHY_CAP7_MAX_NC_7,
+			.phy_cap_info[8] =
+				IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI |
+				IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G |
+				IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU |
+				IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU,
+		},
+		/*
+		 * Set default Tx/Rx HE MCS NSS Support field. Indicate support
+		 * for up to 2 spatial streams and all MCS, without any special
+		 * cases
+		 */
+		.he_mcs_nss_supp = {
+			.rx_mcs_80 = cpu_to_le16(0xfffa),
+			.tx_mcs_80 = cpu_to_le16(0xfffa),
+			.rx_mcs_160 = cpu_to_le16(0xfffa),
+			.tx_mcs_160 = cpu_to_le16(0xfffa),
+			.rx_mcs_80p80 = cpu_to_le16(0xffff),
+			.tx_mcs_80p80 = cpu_to_le16(0xffff),
+		},
+		/*
+		 * Set default PPE thresholds, with PPET16 set to 0, PPET8 set
+		 * to 7
+		 */
+		.ppe_thres = {0x61, 0x1c, 0xc7, 0x71},
+	},
+};
+
+static void iwl_init_he_hw_capab(struct ieee80211_supported_band *sband,
+				 u8 tx_chains, u8 rx_chains)
+{
+	if (sband->band == NL80211_BAND_2GHZ ||
+	    sband->band == NL80211_BAND_5GHZ)
+		sband->iftype_data = &iwl_he_capa;
+	else
+		return;
+
+	sband->n_iftype_data = 1;
+
+	/* If not 2x2, we need to indicate 1x1 in the Midamble RX Max NSTS */
+	if ((tx_chains & rx_chains) != ANT_AB) {
+		iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[1] &=
+			~IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_MAX_NSTS;
+		iwl_he_capa.he_cap.he_cap_elem.phy_cap_info[2] &=
+			~IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_MAX_NSTS;
+	}
+}
+
 static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 			    struct iwl_nvm_data *data,
 			    const __le16 *nvm_ch_flags, u8 tx_chains,
@@ -483,6 +578,9 @@ static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 	iwl_init_ht_hw_capab(cfg, data, &sband->ht_cap, NL80211_BAND_2GHZ,
 			     tx_chains, rx_chains);
 
+	if (data->sku_cap_11ax_enable)
+		iwl_init_he_hw_capab(sband, tx_chains, rx_chains);
+
 	sband = &data->bands[NL80211_BAND_5GHZ];
 	sband->band = NL80211_BAND_5GHZ;
 	sband->bitrates = &iwl_cfg80211_rates[RATES_52_OFFS];
@@ -495,6 +593,9 @@ static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 		iwl_init_vht_hw_capab(cfg, data, &sband->vht_cap,
 				      tx_chains, rx_chains);
 
+	if (data->sku_cap_11ax_enable)
+		iwl_init_he_hw_capab(sband, tx_chains, rx_chains);
+
 	if (n_channels != n_used)
 		IWL_ERR_DEV(dev, "NVM: used only %d of %d channels\n",
 			    n_used, n_channels);
@@ -1293,6 +1394,8 @@ struct iwl_nvm_data *iwl_get_nvm(struct iwl_trans *trans,
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_802_11AC_ENABLED);
 	nvm->sku_cap_11n_enable =
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_802_11N_ENABLED);
+	nvm->sku_cap_11ax_enable =
+		!!(mac_flags & NVM_MAC_SKU_FLAGS_802_11AX_ENABLED);
 	nvm->sku_cap_band_24ghz_enable =
 		!!(mac_flags & NVM_MAC_SKU_FLAGS_BAND_2_4_ENABLED);
 	nvm->sku_cap_band_52ghz_enable =
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 8ba16fc24e3a..362e9b77974d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -780,6 +780,9 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
 	if (vif->probe_req_reg && vif->bss_conf.assoc && vif->p2p)
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST);
 
+	if (vif->bss_conf.assoc && vif->bss_conf.he_support)
+		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX);
+
 	return iwl_mvm_mac_ctxt_send_cmd(mvm, &cmd);
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 26021bc55e98..5ad98359789b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -36,6 +36,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -914,7 +915,7 @@ static int iwl_mvm_mac_ampdu_action(struct ieee80211_hw *hw,
 	enum ieee80211_ampdu_mlme_action action = params->action;
 	u16 tid = params->tid;
 	u16 *ssn = &params->ssn;
-	u8 buf_size = params->buf_size;
+	u16 buf_size = params->buf_size;
 	bool amsdu = params->amsdu;
 	u16 timeout = params->timeout;
 
@@ -1897,6 +1898,194 @@ void iwl_mvm_mu_mimo_grp_notif(struct iwl_mvm *mvm,
 			iwl_mvm_mu_mimo_iface_iterator, notif);
 }
 
+static u8 iwl_mvm_he_get_ppe_val(u8 *ppe, u8 ppe_pos_bit)
+{
+	u8 byte_num = ppe_pos_bit / 8;
+	u8 bit_num = ppe_pos_bit % 8;
+	u8 residue_bits;
+	u8 res;
+
+	if (bit_num <= 5)
+		return (ppe[byte_num] >> bit_num) &
+		       (BIT(IEEE80211_PPE_THRES_INFO_PPET_SIZE) - 1);
+
+	/*
+	 * If bit_num > 5, we have to combine bits with next byte.
+	 * Calculate how many bits we need to take from current byte (called
+	 * here "residue_bits"), and add them to bits from next byte.
+	 */
+
+	residue_bits = 8 - bit_num;
+
+	res = (ppe[byte_num + 1] &
+	       (BIT(IEEE80211_PPE_THRES_INFO_PPET_SIZE - residue_bits) - 1)) <<
+	      residue_bits;
+	res += (ppe[byte_num] >> bit_num) & (BIT(residue_bits) - 1);
+
+	return res;
+}
+
+static void iwl_mvm_cfg_he_sta(struct iwl_mvm *mvm,
+			       struct ieee80211_vif *vif, u8 sta_id)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+	struct iwl_he_sta_context_cmd sta_ctxt_cmd = {
+		.sta_id = sta_id,
+		.tid_limit = IWL_MAX_TID_COUNT,
+		.bss_color = vif->bss_conf.bss_color,
+		.htc_trig_based_pkt_ext = vif->bss_conf.htc_trig_based_pkt_ext,
+		.frame_time_rts_th =
+			cpu_to_le16(vif->bss_conf.frame_time_rts_th),
+	};
+	struct ieee80211_sta *sta;
+	u32 flags;
+	int i;
+
+	rcu_read_lock();
+
+	sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_ctxt_cmd.sta_id]);
+	if (IS_ERR(sta)) {
+		rcu_read_unlock();
+		WARN(1, "Can't find STA to configure HE\n");
+		return;
+	}
+
+	if (!sta->he_cap.has_he) {
+		rcu_read_unlock();
+		return;
+	}
+
+	flags = 0;
+
+	/* HTC flags */
+	if (sta->he_cap.he_cap_elem.mac_cap_info[0] &
+	    IEEE80211_HE_MAC_CAP0_HTC_HE)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_SUPPORT);
+	if ((sta->he_cap.he_cap_elem.mac_cap_info[1] &
+	      IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION) ||
+	    (sta->he_cap.he_cap_elem.mac_cap_info[2] &
+	      IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION)) {
+		u8 link_adap =
+			((sta->he_cap.he_cap_elem.mac_cap_info[2] &
+			  IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION) << 1) +
+			 (sta->he_cap.he_cap_elem.mac_cap_info[1] &
+			  IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION);
+
+		if (link_adap == 2)
+			sta_ctxt_cmd.htc_flags |=
+				cpu_to_le32(IWL_HE_HTC_LINK_ADAP_UNSOLICITED);
+		else if (link_adap == 3)
+			sta_ctxt_cmd.htc_flags |=
+				cpu_to_le32(IWL_HE_HTC_LINK_ADAP_BOTH);
+	}
+	if (sta->he_cap.he_cap_elem.mac_cap_info[2] &
+	    IEEE80211_HE_MAC_CAP2_UL_MU_RESP_SCHED)
+		sta_ctxt_cmd.htc_flags |=
+			cpu_to_le32(IWL_HE_HTC_UL_MU_RESP_SCHED);
+	if (sta->he_cap.he_cap_elem.mac_cap_info[2] & IEEE80211_HE_MAC_CAP2_BSR)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_BSR_SUPP);
+	if (sta->he_cap.he_cap_elem.mac_cap_info[3] &
+	    IEEE80211_HE_MAC_CAP3_OMI_CONTROL)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_OMI_SUPP);
+	if (sta->he_cap.he_cap_elem.mac_cap_info[4] & IEEE80211_HE_MAC_CAP4_BQR)
+		sta_ctxt_cmd.htc_flags |= cpu_to_le32(IWL_HE_HTC_BQR_SUPP);
+
+	/* If PPE Thresholds exist, parse them into a FW-familiar format */
+	if (sta->he_cap.he_cap_elem.phy_cap_info[6] &
+	    IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) {
+		u8 nss = (sta->he_cap.ppe_thres[0] &
+			  IEEE80211_PPE_THRES_NSS_MASK) + 1;
+		u8 ru_index_bitmap =
+			(sta->he_cap.ppe_thres[0] &
+			 IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK) >>
+			IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS;
+		u8 *ppe = &sta->he_cap.ppe_thres[0];
+		u8 ppe_pos_bit = 7; /* Starting after PPE header */
+
+		/*
+		 * FW currently supports only nss == MAX_HE_SUPP_NSS
+		 *
+		 * If nss > MAX: we can ignore values we don't support
+		 * If nss < MAX: we can set zeros in other streams
+		 */
+		if (nss > MAX_HE_SUPP_NSS) {
+			IWL_INFO(mvm, "Got NSS = %d - trimming to %d\n", nss,
+				 MAX_HE_SUPP_NSS);
+			nss = MAX_HE_SUPP_NSS;
+		}
+
+		for (i = 0; i < nss; i++) {
+			u8 ru_index_tmp = ru_index_bitmap << 1;
+			u8 bw;
+
+			for (bw = 0; bw < MAX_HE_CHANNEL_BW_INDX; bw++) {
+				ru_index_tmp >>= 1;
+				if (!(ru_index_tmp & 1))
+					continue;
+
+				sta_ctxt_cmd.pkt_ext.pkt_ext_qam_th[i][bw][1] =
+					iwl_mvm_he_get_ppe_val(ppe,
+							       ppe_pos_bit);
+				ppe_pos_bit +=
+					IEEE80211_PPE_THRES_INFO_PPET_SIZE;
+				sta_ctxt_cmd.pkt_ext.pkt_ext_qam_th[i][bw][0] =
+					iwl_mvm_he_get_ppe_val(ppe,
+							       ppe_pos_bit);
+				ppe_pos_bit +=
+					IEEE80211_PPE_THRES_INFO_PPET_SIZE;
+			}
+		}
+
+		flags |= STA_CTXT_HE_PACKET_EXT;
+	}
+	rcu_read_unlock();
+
+	/* Mark MU EDCA as enabled, unless none detected on some AC */
+	flags |= STA_CTXT_HE_MU_EDCA_CW;
+	for (i = 0; i < AC_NUM; i++) {
+		struct ieee80211_he_mu_edca_param_ac_rec *mu_edca =
+			&mvmvif->queue_params[i].mu_edca_param_rec;
+
+		if (!mvmvif->queue_params[i].mu_edca) {
+			flags &= ~STA_CTXT_HE_MU_EDCA_CW;
+			break;
+		}
+
+		sta_ctxt_cmd.trig_based_txf[i].cwmin =
+			cpu_to_le16(mu_edca->ecw_min_max & 0xf);
+		sta_ctxt_cmd.trig_based_txf[i].cwmax =
+			cpu_to_le16((mu_edca->ecw_min_max & 0xf0) >> 4);
+		sta_ctxt_cmd.trig_based_txf[i].aifsn =
+			cpu_to_le16(mu_edca->aifsn);
+		sta_ctxt_cmd.trig_based_txf[i].mu_time =
+			cpu_to_le16(mu_edca->mu_edca_timer);
+	}
+
+	if (vif->bss_conf.multi_sta_back_32bit)
+		flags |= STA_CTXT_HE_32BIT_BA_BITMAP;
+
+	if (vif->bss_conf.ack_enabled)
+		flags |= STA_CTXT_HE_ACK_ENABLED;
+
+	if (vif->bss_conf.uora_exists) {
+		flags |= STA_CTXT_HE_TRIG_RND_ALLOC;
+
+		sta_ctxt_cmd.rand_alloc_ecwmin =
+			vif->bss_conf.uora_ocw_range & 0x7;
+		sta_ctxt_cmd.rand_alloc_ecwmax =
+			(vif->bss_conf.uora_ocw_range >> 3) & 0x7;
+	}
+
+	/* TODO: support Multi BSSID IE */
+
+	sta_ctxt_cmd.flags = cpu_to_le32(flags);
+
+	if (iwl_mvm_send_cmd_pdu(mvm, iwl_cmd_id(STA_HE_CTXT_CMD,
+						 DATA_PATH_GROUP, 0),
+				 0, sizeof(sta_ctxt_cmd), &sta_ctxt_cmd))
+		IWL_ERR(mvm, "Failed to config FW to work HE!\n");
+}
+
 static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 					     struct ieee80211_vif *vif,
 					     struct ieee80211_bss_conf *bss_conf,
@@ -1910,8 +2099,12 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 	 * beacon interval, which was not known when the station interface was
 	 * added.
 	 */
-	if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc)
+	if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc) {
+		if (vif->bss_conf.he_support)
+			iwl_mvm_cfg_he_sta(mvm, vif, mvmvif->ap_sta_id);
+
 		iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif);
+	}
 
 	/*
 	 * If we're not associated yet, take the (new) BSSID before associating
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 6a4ba160c59e..b3987a0a7018 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -654,7 +654,7 @@ struct iwl_mvm_tcm {
 struct iwl_mvm_reorder_buffer {
 	u16 head_sn;
 	u16 num_stored;
-	u8 buf_size;
+	u16 buf_size;
 	int queue;
 	u16 last_amsdu;
 	u8 last_sub_index;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index ff1e518096c5..aa11b35d6f51 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -448,6 +448,7 @@ static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = {
 	HCMD_NAME(DQA_ENABLE_CMD),
 	HCMD_NAME(UPDATE_MU_GROUPS_CMD),
 	HCMD_NAME(TRIGGER_RX_QUEUES_NOTIF_CMD),
+	HCMD_NAME(STA_HE_CTXT_CMD),
 	HCMD_NAME(STA_PM_NOTIF),
 	HCMD_NAME(MU_GROUP_MGMT_NOTIF),
 	HCMD_NAME(RX_QUEUES_NOTIFICATION),
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
index b8b2b819e8e7..8169d1450b3b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs-fw.c
@@ -183,6 +183,43 @@ rs_fw_vht_set_enabled_rates(const struct ieee80211_sta *sta,
 	}
 }
 
+static u16 rs_fw_he_ieee80211_mcs_to_rs_mcs(u16 mcs)
+{
+	switch (mcs) {
+	case IEEE80211_HE_MCS_SUPPORT_0_7:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS7 + 1) - 1;
+	case IEEE80211_HE_MCS_SUPPORT_0_9:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS9 + 1) - 1;
+	case IEEE80211_HE_MCS_SUPPORT_0_11:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS11 + 1) - 1;
+	case IEEE80211_HE_MCS_NOT_SUPPORTED:
+		return 0;
+	}
+
+	WARN(1, "invalid HE MCS %d\n", mcs);
+	return 0;
+}
+
+static void
+rs_fw_he_set_enabled_rates(const struct ieee80211_sta *sta,
+			   const struct ieee80211_sta_he_cap *he_cap,
+			   struct iwl_tlc_config_cmd *cmd)
+{
+	u16 mcs_160 = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_160);
+	u16 mcs_80 = le16_to_cpu(sta->he_cap.he_mcs_nss_supp.rx_mcs_80);
+	int i;
+
+	for (i = 0; i < sta->rx_nss && i < MAX_NSS; i++) {
+		u16 _mcs_160 = (mcs_160 >> (2 * i)) & 0x3;
+		u16 _mcs_80 = (mcs_80 >> (2 * i)) & 0x3;
+
+		cmd->ht_rates[i][0] =
+			cpu_to_le16(rs_fw_he_ieee80211_mcs_to_rs_mcs(_mcs_80));
+		cmd->ht_rates[i][1] =
+			cpu_to_le16(rs_fw_he_ieee80211_mcs_to_rs_mcs(_mcs_160));
+	}
+}
+
 static void rs_fw_set_supp_rates(struct ieee80211_sta *sta,
 				 struct ieee80211_supported_band *sband,
 				 struct iwl_tlc_config_cmd *cmd)
@@ -192,6 +229,7 @@ static void rs_fw_set_supp_rates(struct ieee80211_sta *sta,
 	unsigned long supp; /* must be unsigned long for for_each_set_bit */
 	const struct ieee80211_sta_ht_cap *ht_cap = &sta->ht_cap;
 	const struct ieee80211_sta_vht_cap *vht_cap = &sta->vht_cap;
+	const struct ieee80211_sta_he_cap *he_cap = &sta->he_cap;
 
 	/* non HT rates */
 	supp = 0;
@@ -202,7 +240,11 @@ static void rs_fw_set_supp_rates(struct ieee80211_sta *sta,
 	cmd->non_ht_rates = cpu_to_le16(supp);
 	cmd->mode = IWL_TLC_MNG_MODE_NON_HT;
 
-	if (vht_cap && vht_cap->vht_supported) {
+	/* HT/VHT rates */
+	if (he_cap && he_cap->has_he) {
+		cmd->mode = IWL_TLC_MNG_MODE_HE;
+		rs_fw_he_set_enabled_rates(sta, he_cap, cmd);
+	} else if (vht_cap && vht_cap->vht_supported) {
 		cmd->mode = IWL_TLC_MNG_MODE_VHT;
 		rs_fw_vht_set_enabled_rates(sta, vht_cap, cmd);
 	} else if (ht_cap && ht_cap->ht_supported) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index 642da10b0b7f..30cfd7d50bc9 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -363,7 +363,8 @@ static int iwl_hwrate_to_plcp_idx(u32 rate_n_flags)
 			idx += 1;
 		if ((idx >= IWL_FIRST_HT_RATE) && (idx <= IWL_LAST_HT_RATE))
 			return idx;
-	} else if (rate_n_flags & RATE_MCS_VHT_MSK) {
+	} else if (rate_n_flags & RATE_MCS_VHT_MSK ||
+		   rate_n_flags & RATE_MCS_HE_MSK) {
 		idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
 		idx += IWL_RATE_MCS_0_INDEX;
 
@@ -372,6 +373,9 @@ static int iwl_hwrate_to_plcp_idx(u32 rate_n_flags)
 			idx++;
 		if ((idx >= IWL_FIRST_VHT_RATE) && (idx <= IWL_LAST_VHT_RATE))
 			return idx;
+		if ((rate_n_flags & RATE_MCS_HE_MSK) &&
+		    (idx <= IWL_LAST_HE_RATE))
+			return idx;
 	} else {
 		/* legacy rate format, search for match in table */
 
@@ -516,6 +520,8 @@ static const char *rs_pretty_lq_type(enum iwl_table_type type)
 		[LQ_HT_MIMO2] = "HT MIMO",
 		[LQ_VHT_SISO] = "VHT SISO",
 		[LQ_VHT_MIMO2] = "VHT MIMO",
+		[LQ_HE_SISO] = "HE SISO",
+		[LQ_HE_MIMO2] = "HE MIMO",
 	};
 
 	if (type < LQ_NONE || type >= LQ_MAX)
@@ -900,7 +906,8 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 
 	/* Legacy */
 	if (!(ucode_rate & RATE_MCS_HT_MSK) &&
-	    !(ucode_rate & RATE_MCS_VHT_MSK)) {
+	    !(ucode_rate & RATE_MCS_VHT_MSK) &&
+	    !(ucode_rate & RATE_MCS_HE_MSK)) {
 		if (num_of_ant == 1) {
 			if (band == NL80211_BAND_5GHZ)
 				rate->type = LQ_LEGACY_A;
@@ -911,7 +918,7 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 		return 0;
 	}
 
-	/* HT or VHT */
+	/* HT, VHT or HE */
 	if (ucode_rate & RATE_MCS_SGI_MSK)
 		rate->sgi = true;
 	if (ucode_rate & RATE_MCS_LDPC_MSK)
@@ -953,10 +960,24 @@ static int rs_rate_from_ucode_rate(const u32 ucode_rate,
 		} else {
 			WARN_ON_ONCE(1);
 		}
+	} else if (ucode_rate & RATE_MCS_HE_MSK) {
+		nss = ((ucode_rate & RATE_VHT_MCS_NSS_MSK) >>
+		      RATE_VHT_MCS_NSS_POS) + 1;
+
+		if (nss == 1) {
+			rate->type = LQ_HE_SISO;
+			WARN_ONCE(!rate->stbc && !rate->bfer && num_of_ant != 1,
+				  "stbc %d bfer %d", rate->stbc, rate->bfer);
+		} else if (nss == 2) {
+			rate->type = LQ_HE_MIMO2;
+			WARN_ON_ONCE(num_of_ant != 2);
+		} else {
+			WARN_ON_ONCE(1);
+		}
 	}
 
 	WARN_ON_ONCE(rate->bw == RATE_MCS_CHAN_WIDTH_80 &&
-		     !is_vht(rate));
+		     !is_he(rate) && !is_vht(rate));
 
 	return 0;
 }
@@ -3606,7 +3627,8 @@ int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate)
 	u8 ant = (rate & RATE_MCS_ANT_ABC_MSK) >> RATE_MCS_ANT_POS;
 
 	if (!(rate & RATE_MCS_HT_MSK) &&
-	    !(rate & RATE_MCS_VHT_MSK)) {
+	    !(rate & RATE_MCS_VHT_MSK) &&
+	    !(rate & RATE_MCS_HE_MSK)) {
 		int index = iwl_hwrate_to_plcp_idx(rate);
 
 		return scnprintf(buf, bufsz, "Legacy | ANT: %s Rate: %s Mbps\n",
@@ -3625,6 +3647,11 @@ int rs_pretty_print_rate(char *buf, int bufsz, const u32 rate)
 		mcs = rate & RATE_HT_MCS_INDEX_MSK;
 		nss = ((rate & RATE_HT_MCS_NSS_MSK)
 		       >> RATE_HT_MCS_NSS_POS) + 1;
+	} else if (rate & RATE_MCS_HE_MSK) {
+		type = "HE";
+		mcs = rate & RATE_VHT_MCS_RATE_CODE_MSK;
+		nss = ((rate & RATE_VHT_MCS_NSS_MSK)
+		       >> RATE_VHT_MCS_NSS_POS) + 1;
 	} else {
 		type = "Unknown"; /* shouldn't happen */
 	}
@@ -3886,6 +3913,8 @@ static ssize_t rs_sta_dbgfs_drv_tx_stats_read(struct file *file,
 		[IWL_RATE_MCS_7_INDEX] = "MCS7",
 		[IWL_RATE_MCS_8_INDEX] = "MCS8",
 		[IWL_RATE_MCS_9_INDEX] = "MCS9",
+		[IWL_RATE_MCS_10_INDEX] = "MCS10",
+		[IWL_RATE_MCS_11_INDEX] = "MCS11",
 	};
 
 	char *buff, *pos, *endpos;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
index cffb8c852934..d2cf484e2b73 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.h
@@ -144,8 +144,13 @@ enum {
 
 #define LINK_QUAL_AGG_FRAME_LIMIT_DEF	(63)
 #define LINK_QUAL_AGG_FRAME_LIMIT_MAX	(63)
-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF	(64)
-#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX	(64)
+/*
+ * FIXME - various places in firmware API still use u8,
+ * e.g. LQ command and SCD config command.
+ * This should be 256 instead.
+ */
+#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_DEF	(255)
+#define LINK_QUAL_AGG_FRAME_LIMIT_GEN2_MAX	(255)
 #define LINK_QUAL_AGG_FRAME_LIMIT_MIN	(0)
 
 #define LQ_SIZE		2	/* 2 mode tables:  "Active" and "Search" */
@@ -162,6 +167,8 @@ enum iwl_table_type {
 	LQ_HT_MIMO2,
 	LQ_VHT_SISO,    /* VHT types */
 	LQ_VHT_MIMO2,
+	LQ_HE_SISO,     /* HE types */
+	LQ_HE_MIMO2,
 	LQ_MAX,
 };
 
@@ -183,11 +190,16 @@ struct rs_rate {
 #define is_type_ht_mimo2(type) ((type) == LQ_HT_MIMO2)
 #define is_type_vht_siso(type) ((type) == LQ_VHT_SISO)
 #define is_type_vht_mimo2(type) ((type) == LQ_VHT_MIMO2)
-#define is_type_siso(type) (is_type_ht_siso(type) || is_type_vht_siso(type))
-#define is_type_mimo2(type) (is_type_ht_mimo2(type) || is_type_vht_mimo2(type))
+#define is_type_he_siso(type) ((type) == LQ_HE_SISO)
+#define is_type_he_mimo2(type) ((type) == LQ_HE_MIMO2)
+#define is_type_siso(type) (is_type_ht_siso(type) || is_type_vht_siso(type) || \
+			    is_type_he_siso(type))
+#define is_type_mimo2(type) (is_type_ht_mimo2(type) || \
+			     is_type_vht_mimo2(type) || is_type_he_mimo2(type))
 #define is_type_mimo(type) (is_type_mimo2(type))
 #define is_type_ht(type) (is_type_ht_siso(type) || is_type_ht_mimo2(type))
 #define is_type_vht(type) (is_type_vht_siso(type) || is_type_vht_mimo2(type))
+#define is_type_he(type) (is_type_he_siso(type) || is_type_he_mimo2(type))
 #define is_type_a_band(type) ((type) == LQ_LEGACY_A)
 #define is_type_g_band(type) ((type) == LQ_LEGACY_G)
 
@@ -201,6 +213,7 @@ struct rs_rate {
 #define is_mimo(rate)         is_type_mimo((rate)->type)
 #define is_ht(rate)           is_type_ht((rate)->type)
 #define is_vht(rate)          is_type_vht((rate)->type)
+#define is_he(rate)           is_type_he((rate)->type)
 #define is_a_band(rate)       is_type_a_band((rate)->type)
 #define is_g_band(rate)       is_type_g_band((rate)->type)
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 129c4c09648d..0d66cb232cf1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -857,6 +859,10 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	struct ieee80211_sta *sta = NULL;
 	struct sk_buff *skb;
 	u8 crypt_len = 0;
+	u32 he_type = 0xffffffff;
+	/* this is invalid e.g. because puncture type doesn't allow 0b11 */
+#define HE_PHY_DATA_INVAL ((u64)-1)
+	u64 he_phy_data = HE_PHY_DATA_INVAL;
 
 	if (unlikely(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)))
 		return;
@@ -882,6 +888,13 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 
 	rx_status = IEEE80211_SKB_RXCB(skb);
 
+	if (rate_n_flags & RATE_MCS_HE_MSK) {
+		if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
+			he_phy_data =
+				le64_to_cpu(desc->he_phy_data);
+		he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
+	}
+
 	if (iwl_mvm_rx_crypto(mvm, hdr, rx_status, phy_info, desc,
 			      le32_to_cpu(pkt->len_n_flags), queue,
 			      &crypt_len)) {
@@ -907,7 +920,19 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		rx_status->mactime = le64_to_cpu(desc->tsf_on_air_rise);
 		/* TSF as indicated by the firmware is at INA time */
 		rx_status->flag |= RX_FLAG_MACTIME_PLCP_START;
+	} else if (he_type == RATE_MCS_HE_TYPE_SU) {
+		if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
+			rx_status->ampdu_reference = mvm->ampdu_ref;
+			mvm->ampdu_ref++;
+
+			rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
+			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
+			if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF,
+				      le64_to_cpu(desc->he_phy_data)))
+				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
+		}
 	}
+
 	rx_status->device_timestamp = le32_to_cpu(desc->gp2_on_air_rise);
 	rx_status->band = desc->channel > 14 ? NL80211_BAND_5GHZ :
 					       NL80211_BAND_2GHZ;
@@ -925,6 +950,15 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		if (toggle_bit != mvm->ampdu_toggle) {
 			mvm->ampdu_ref++;
 			mvm->ampdu_toggle = toggle_bit;
+
+			if (he_phy_data != HE_PHY_DATA_INVAL &&
+			    he_type == RATE_MCS_HE_TYPE_MU) {
+				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
+				if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF,
+					      le64_to_cpu(desc->he_phy_data)))
+					rx_status->flag |=
+						RX_FLAG_AMPDU_EOF_BIT;
+			}
 		}
 	}
 
@@ -1033,7 +1067,6 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		}
 	}
 
-	/* Set up the HT phy flags */
 	switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) {
 	case RATE_MCS_CHAN_WIDTH_20:
 		break;
@@ -1048,6 +1081,59 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		break;
 	}
 
+	if (he_type == RATE_MCS_HE_TYPE_EXT_SU &&
+	    rate_n_flags & RATE_MCS_HE_106T_MSK) {
+		rx_status->bw = RATE_INFO_BW_HE_RU;
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+	}
+
+	if (rate_n_flags & RATE_MCS_HE_MSK &&
+	    phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD &&
+	    he_type == RATE_MCS_HE_TYPE_MU) {
+		/*
+		 * Unfortunately, we have to leave the mac80211 data
+		 * incorrect for the case that we receive an HE-MU
+		 * transmission and *don't* have the he_mu pointer,
+		 * i.e. we don't have the phy data (due to the bits
+		 * being used for TSF). This shouldn't happen though
+		 * as management frames where we need the TSF/timers
+		 * are not be transmitted in HE-MU, I think.
+		 */
+		u8 ru = FIELD_GET(IWL_RX_HE_PHY_RU_ALLOC_MASK, he_phy_data);
+		u8 offs = 0;
+
+		rx_status->bw = RATE_INFO_BW_HE_RU;
+
+		switch (ru) {
+		case 0 ... 36:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_26;
+			offs = ru;
+			break;
+		case 37 ... 52:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_52;
+			offs = ru - 37;
+			break;
+		case 53 ... 60:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+			offs = ru - 53;
+			break;
+		case 61 ... 64:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_242;
+			offs = ru - 61;
+			break;
+		case 65 ... 66:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_484;
+			offs = ru - 65;
+			break;
+		case 67:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_996;
+			break;
+		case 68:
+			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
+			break;
+		}
+	}
+
 	if (!(rate_n_flags & RATE_MCS_CCK_MSK) &&
 	    rate_n_flags & RATE_MCS_SGI_MSK)
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
@@ -1072,6 +1158,39 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		if (rate_n_flags & RATE_MCS_BF_MSK)
 			rx_status->enc_flags |= RX_ENC_FLAG_BF;
+	} else if (rate_n_flags & RATE_MCS_HE_MSK) {
+		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
+				RATE_MCS_STBC_POS;
+		rx_status->nss =
+			((rate_n_flags & RATE_VHT_MCS_NSS_MSK) >>
+						RATE_VHT_MCS_NSS_POS) + 1;
+		rx_status->rate_idx = rate_n_flags & RATE_VHT_MCS_RATE_CODE_MSK;
+		rx_status->encoding = RX_ENC_HE;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
+		if (rate_n_flags & RATE_MCS_BF_MSK)
+			rx_status->enc_flags |= RX_ENC_FLAG_BF;
+
+		rx_status->he_dcm =
+			!!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK);
+
+		switch ((rate_n_flags & RATE_MCS_HE_GI_LTF_MSK) >>
+			RATE_MCS_HE_GI_LTF_POS) {
+		case 0:
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			break;
+		case 1:
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			break;
+		case 2:
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			break;
+		case 3:
+			if (rate_n_flags & RATE_MCS_SGI_MSK)
+				rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			else
+				rx_status->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			break;
+		}
 	} else {
 		int rate = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
 							       rx_status->band);
@@ -1083,7 +1202,6 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			goto out;
 		}
 		rx_status->rate_idx = rate;
-
 	}
 
 	/* management stuff on default queue */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 9263b9aa8b72..18db1ed92d9b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -2184,7 +2184,7 @@ static void iwl_mvm_free_reorder(struct iwl_mvm *mvm,
 
 static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm,
 					struct iwl_mvm_baid_data *data,
-					u16 ssn, u8 buf_size)
+					u16 ssn, u16 buf_size)
 {
 	int i;
 
@@ -2211,7 +2211,7 @@ static void iwl_mvm_init_reorder_buffer(struct iwl_mvm *mvm,
 }
 
 int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-		       int tid, u16 ssn, bool start, u8 buf_size, u16 timeout)
+		       int tid, u16 ssn, bool start, u16 buf_size, u16 timeout)
 {
 	struct iwl_mvm_sta *mvm_sta = iwl_mvm_sta_from_mac80211(sta);
 	struct iwl_mvm_add_sta_cmd cmd = {};
@@ -2273,7 +2273,7 @@ int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
 	if (start) {
 		cmd.add_immediate_ba_tid = (u8) tid;
 		cmd.add_immediate_ba_ssn = cpu_to_le16(ssn);
-		cmd.rx_ba_window = cpu_to_le16((u16)buf_size);
+		cmd.rx_ba_window = cpu_to_le16(buf_size);
 	} else {
 		cmd.remove_immediate_ba_tid = (u8) tid;
 	}
@@ -2559,7 +2559,7 @@ out:
 }
 
 int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			    struct ieee80211_sta *sta, u16 tid, u8 buf_size,
+			    struct ieee80211_sta *sta, u16 tid, u16 buf_size,
 			    bool amsdu)
 {
 	struct iwl_mvm_sta *mvmsta = iwl_mvm_sta_from_mac80211(sta);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 1c43ea8dd8cc..0fc211108149 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -412,7 +412,7 @@ struct iwl_mvm_sta {
 	u32 tfd_queue_msk;
 	u32 mac_id_n_color;
 	u16 tid_disable_agg;
-	u8 max_agg_bufsize;
+	u16 max_agg_bufsize;
 	enum iwl_sta_type sta_type;
 	enum ieee80211_sta_state sta_state;
 	bool bt_reduced_txpower;
@@ -518,11 +518,11 @@ void iwl_mvm_rx_eosp_notif(struct iwl_mvm *mvm,
 
 /* AMPDU */
 int iwl_mvm_sta_rx_agg(struct iwl_mvm *mvm, struct ieee80211_sta *sta,
-		       int tid, u16 ssn, bool start, u8 buf_size, u16 timeout);
+		       int tid, u16 ssn, bool start, u16 buf_size, u16 timeout);
 int iwl_mvm_sta_tx_agg_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			struct ieee80211_sta *sta, u16 tid, u16 *ssn);
 int iwl_mvm_sta_tx_agg_oper(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			    struct ieee80211_sta *sta, u16 tid, u8 buf_size,
+			    struct ieee80211_sta *sta, u16 tid, u16 buf_size,
 			    bool amsdu);
 int iwl_mvm_sta_tx_agg_stop(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			    struct ieee80211_sta *sta, u16 tid);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 7229991ae70d..57f5d8f3bdf6 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2934,7 +2934,7 @@ static struct iwl_trans_dump_data
 	struct iwl_txq *cmdq = trans_pcie->txq[trans_pcie->cmd_queue];
 	struct iwl_fw_error_dump_txcmd *txcmd;
 	struct iwl_trans_dump_data *dump_data;
-	u32 len, num_rbs;
+	u32 len, num_rbs = 0;
 	u32 monitor_len;
 	int i, ptr;
 	bool dump_rbs = test_bit(STATUS_FW_ERROR, &trans->status) &&
-- 
cgit v1.2.3


From 230ba6c5a9df33bbd6ad5980a3f8dc446c3e881f Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sun, 24 Jun 2018 12:07:28 +0300
Subject: iwlwifi: add module parameter to disable 802.11ax

Add a module parameter to disable 802.11ax features in supported
devices.  This is useful for testing or if there are interoperability
issues with some APs.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c       | 4 ++++
 drivers/net/wireless/intel/iwlwifi/iwl-modparams.h | 4 ++++
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c  | 3 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  | 3 ++-
 5 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index c59ce4f8a5ed..650214ff0a1c 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1856,3 +1856,7 @@ module_param_named(remove_when_gone,
 		   0444);
 MODULE_PARM_DESC(remove_when_gone,
 		 "Remove dev from PCIe bus if it is deemed inaccessible (default: false)");
+
+module_param_named(disable_11ax, iwlwifi_mod_params.disable_11ax, bool,
+		   S_IRUGO);
+MODULE_PARM_DESC(disable_11ax, "Disable HE capabilities (default: false)");
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
index a7dd8a8cddf9..5dd848cb9d20 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
@@ -144,6 +144,10 @@ struct iwl_mod_params {
 	bool lar_disable;
 	bool fw_monitor;
 	bool disable_11ac;
+	/**
+	 * @disable_11ax: disable HE capabilities, default = false
+	 */
+	bool disable_11ax;
 	bool remove_when_gone;
 };
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 941604c24fa1..7bb0360d6807 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -578,7 +578,7 @@ static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 	iwl_init_ht_hw_capab(cfg, data, &sband->ht_cap, NL80211_BAND_2GHZ,
 			     tx_chains, rx_chains);
 
-	if (data->sku_cap_11ax_enable)
+	if (data->sku_cap_11ax_enable && !iwlwifi_mod_params.disable_11ax)
 		iwl_init_he_hw_capab(sband, tx_chains, rx_chains);
 
 	sband = &data->bands[NL80211_BAND_5GHZ];
@@ -593,7 +593,7 @@ static void iwl_init_sbands(struct device *dev, const struct iwl_cfg *cfg,
 		iwl_init_vht_hw_capab(cfg, data, &sband->vht_cap,
 				      tx_chains, rx_chains);
 
-	if (data->sku_cap_11ax_enable)
+	if (data->sku_cap_11ax_enable && !iwlwifi_mod_params.disable_11ax)
 		iwl_init_he_hw_capab(sband, tx_chains, rx_chains);
 
 	if (n_channels != n_used)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 362e9b77974d..b3fd20502abb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -780,7 +780,8 @@ static int iwl_mvm_mac_ctxt_cmd_sta(struct iwl_mvm *mvm,
 	if (vif->probe_req_reg && vif->bss_conf.assoc && vif->p2p)
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_PROBE_REQUEST);
 
-	if (vif->bss_conf.assoc && vif->bss_conf.he_support)
+	if (vif->bss_conf.assoc && vif->bss_conf.he_support &&
+	    !iwlwifi_mod_params.disable_11ax)
 		cmd.filter_flags |= cpu_to_le32(MAC_FILTER_IN_11AX);
 
 	return iwl_mvm_mac_ctxt_send_cmd(mvm, &cmd);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 5ad98359789b..9779db31ab30 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -2100,7 +2100,8 @@ static void iwl_mvm_bss_info_changed_station(struct iwl_mvm *mvm,
 	 * added.
 	 */
 	if (changes & BSS_CHANGED_ASSOC && bss_conf->assoc) {
-		if (vif->bss_conf.he_support)
+		if (vif->bss_conf.he_support &&
+		    !iwlwifi_mod_params.disable_11ax)
 			iwl_mvm_cfg_he_sta(mvm, vif, mvmvif->ap_sta_id);
 
 		iwl_mvm_mac_ctxt_recalc_tsf_id(mvm, vif);
-- 
cgit v1.2.3


From e5721e3f770f0ca527c6232c7d19e8cabd1f79b8 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Tue, 26 Jun 2018 10:03:04 +0300
Subject: iwlwifi: mvm: add radiotap data for HE

Add HE information to the radiotap data.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 169 +++++++++++++++++++++++++-
 1 file changed, 163 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 0d66cb232cf1..d82eeb7e0de7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -198,10 +198,20 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 					    struct sk_buff *skb, int queue,
 					    struct ieee80211_sta *sta)
 {
-	if (iwl_mvm_check_pn(mvm, skb, queue, sta))
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+
+	if (iwl_mvm_check_pn(mvm, skb, queue, sta)) {
 		kfree_skb(skb);
-	else
+	} else {
+		unsigned int radiotap_len = 0;
+
+		if (rx_status->flag & RX_FLAG_RADIOTAP_HE)
+			radiotap_len += sizeof(struct ieee80211_radiotap_he);
+		if (rx_status->flag & RX_FLAG_RADIOTAP_HE_MU)
+			radiotap_len += sizeof(struct ieee80211_radiotap_he_mu);
+		__skb_push(skb, radiotap_len);
 		ieee80211_rx_napi(mvm->hw, sta, skb, napi);
+	}
 }
 
 static void iwl_mvm_get_signal_strength(struct iwl_mvm *mvm,
@@ -859,6 +869,8 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	struct ieee80211_sta *sta = NULL;
 	struct sk_buff *skb;
 	u8 crypt_len = 0;
+	struct ieee80211_radiotap_he *he = NULL;
+	struct ieee80211_radiotap_he_mu *he_mu = NULL;
 	u32 he_type = 0xffffffff;
 	/* this is invalid e.g. because puncture type doesn't allow 0b11 */
 #define HE_PHY_DATA_INVAL ((u64)-1)
@@ -889,10 +901,43 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	rx_status = IEEE80211_SKB_RXCB(skb);
 
 	if (rate_n_flags & RATE_MCS_HE_MSK) {
-		if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
+		static const struct ieee80211_radiotap_he known = {
+			.data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN),
+			.data2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN |
+					     IEEE80211_RADIOTAP_HE_DATA2_TXBF_KNOWN),
+		};
+		static const struct ieee80211_radiotap_he_mu mu_known = {
+			.flags1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS_KNOWN |
+					      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM_KNOWN |
+					      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN |
+					      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_COMP_KNOWN),
+			.flags2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN),
+		};
+		unsigned int radiotap_len = 0;
+
+		he = skb_put_data(skb, &known, sizeof(known));
+		radiotap_len += sizeof(known);
+		rx_status->flag |= RX_FLAG_RADIOTAP_HE;
+
+		he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
+
+		if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) {
 			he_phy_data =
 				le64_to_cpu(desc->he_phy_data);
-		he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
+
+			if (he_type == RATE_MCS_HE_TYPE_MU) {
+				he_mu = skb_put_data(skb, &mu_known,
+						     sizeof(mu_known));
+				radiotap_len += sizeof(mu_known);
+				rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU;
+			}
+		}
+
+		/* temporarily hide the radiotap data */
+		__skb_pull(skb, radiotap_len);
 	}
 
 	if (iwl_mvm_rx_crypto(mvm, hdr, rx_status, phy_info, desc,
@@ -921,6 +966,13 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		/* TSF as indicated by the firmware is at INA time */
 		rx_status->flag |= RX_FLAG_MACTIME_PLCP_START;
 	} else if (he_type == RATE_MCS_HE_TYPE_SU) {
+		he->data1 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN);
+		if (FIELD_GET(IWL_RX_HE_PHY_UPLINK,
+			      le64_to_cpu(desc->he_phy_data)))
+			he->data3 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
+
 		if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
 			rx_status->ampdu_reference = mvm->ampdu_ref;
 			mvm->ampdu_ref++;
@@ -931,8 +983,28 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 				      le64_to_cpu(desc->he_phy_data)))
 				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
 		}
+	} else if (he_mu && he_phy_data != HE_PHY_DATA_INVAL) {
+		he_mu->flags1 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIBG_SYM_OR_USER_NUM_MASK,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS);
+		he_mu->flags1 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIGB_DCM,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM);
+		he_mu->flags1 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIGB_MCS_MASK,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS);
+		he_mu->flags2 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_SIGB_COMPRESSION,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP);
+		he_mu->flags2 |=
+			le16_encode_bits(FIELD_GET(IWL_RX_HE_PHY_PREAMBLE_PUNC_TYPE_MASK,
+						   he_phy_data),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW);
 	}
-
 	rx_status->device_timestamp = le32_to_cpu(desc->gp2_on_air_rise);
 	rx_status->band = desc->channel > 14 ? NL80211_BAND_5GHZ :
 					       NL80211_BAND_2GHZ;
@@ -1132,6 +1204,17 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
 			break;
 		}
+		he->data2 |=
+			le16_encode_bits(offs,
+					 IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET);
+		he->data2 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN);
+		if (he_phy_data & IWL_RX_HE_PHY_RU_ALLOC_SEC80)
+			he->data2 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC);
+	} else if (he) {
+		he->data1 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN);
 	}
 
 	if (!(rate_n_flags & RATE_MCS_CCK_MSK) &&
@@ -1158,7 +1241,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
 		if (rate_n_flags & RATE_MCS_BF_MSK)
 			rx_status->enc_flags |= RX_ENC_FLAG_BF;
-	} else if (rate_n_flags & RATE_MCS_HE_MSK) {
+	} else if (he) {
 		u8 stbc = (rate_n_flags & RATE_MCS_STBC_MSK) >>
 				RATE_MCS_STBC_POS;
 		rx_status->nss =
@@ -1173,6 +1256,20 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		rx_status->he_dcm =
 			!!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK);
 
+#define CHECK_TYPE(F)							\
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_ ## F !=	\
+		     (RATE_MCS_HE_TYPE_ ## F >> RATE_MCS_HE_TYPE_POS))
+
+		CHECK_TYPE(SU);
+		CHECK_TYPE(EXT_SU);
+		CHECK_TYPE(MU);
+		CHECK_TYPE(TRIG);
+
+		he->data1 |= cpu_to_le16(he_type >> RATE_MCS_HE_TYPE_POS);
+
+		if (rate_n_flags & RATE_MCS_BF_POS)
+			he->data5 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA5_TXBF);
+
 		switch ((rate_n_flags & RATE_MCS_HE_GI_LTF_MSK) >>
 			RATE_MCS_HE_GI_LTF_POS) {
 		case 0:
@@ -1191,6 +1288,65 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 				rx_status->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
 			break;
 		}
+
+		switch (he_type) {
+		case RATE_MCS_HE_TYPE_SU: {
+			u16 val;
+
+			/* LTF syms correspond to streams */
+			he->data2 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
+			switch (rx_status->nss) {
+			case 1:
+				val = 0;
+				break;
+			case 2:
+				val = 1;
+				break;
+			case 3:
+			case 4:
+				val = 2;
+				break;
+			case 5:
+			case 6:
+				val = 3;
+				break;
+			case 7:
+			case 8:
+				val = 4;
+				break;
+			default:
+				WARN_ONCE(1, "invalid nss: %d\n",
+					  rx_status->nss);
+				val = 0;
+			}
+			he->data5 |=
+				le16_encode_bits(val,
+						 IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS);
+			}
+			break;
+		case RATE_MCS_HE_TYPE_MU: {
+			u16 val;
+
+			if (he_phy_data == HE_PHY_DATA_INVAL)
+				break;
+
+			val = FIELD_GET(IWL_RX_HE_PHY_HE_LTF_NUM_MASK,
+					le64_to_cpu(desc->he_phy_data));
+
+			he->data2 |=
+				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
+			he->data5 |=
+				cpu_to_le16(FIELD_PREP(
+					IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS,
+					val));
+			}
+			break;
+		case RATE_MCS_HE_TYPE_EXT_SU:
+		case RATE_MCS_HE_TYPE_TRIG:
+			/* not supported yet */
+			break;
+		}
 	} else {
 		int rate = iwl_mvm_legacy_rate_to_mac80211_idx(rate_n_flags,
 							       rx_status->band);
@@ -1202,6 +1358,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			goto out;
 		}
 		rx_status->rate_idx = rate;
+
 	}
 
 	/* management stuff on default queue */
-- 
cgit v1.2.3


From 2693de9f82f1f3b47b55d383ddcee63e3927571f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 28 Sep 2017 14:15:20 +0200
Subject: iwlwifi: 22000 devices: restrict to HT A-MPDU size

Our current HE devices don't support BlockAck with the large bitmap,
so can't do TX aggregation with 256 frames. Restrict to the lower HT
size.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index d4ba66aecdc9..6eb0894bd910 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -179,6 +179,12 @@ const struct iwl_cfg iwl22000_2ax_cfg_hr = {
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_f0 = {
@@ -190,6 +196,12 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_f0 = {
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0 = {
@@ -201,6 +213,12 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0 = {
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
@@ -212,6 +230,12 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 MODULE_FIRMWARE(IWL_22000_HR_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
-- 
cgit v1.2.3


From 33708052993ceed27a67669a5badf2efb2841bd0 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Sun, 24 Jun 2018 11:36:52 +0300
Subject: iwlwifi: add support for 22560 devices

Add support for the new 22560 family of devices and, while at it,
reorganize the 22000 family so it fits better with the new one.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c  | 63 ++++++++++++++++---------
 drivers/net/wireless/intel/iwlwifi/iwl-config.h |  4 +-
 drivers/net/wireless/intel/iwlwifi/iwl-csr.h    |  3 ++
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c   |  2 -
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 20 ++++++--
 5 files changed, 62 insertions(+), 30 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 6eb0894bd910..aafd8cab86b0 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -73,23 +73,29 @@
 #define IWL_22000_SMEM_OFFSET		0x400000
 #define IWL_22000_SMEM_LEN		0xD0000
 
-#define IWL_22000_JF_FW_PRE	"iwlwifi-Qu-a0-jf-b0-"
-#define IWL_22000_HR_FW_PRE	"iwlwifi-Qu-a0-hr-a0-"
-#define IWL_22000_HR_CDB_FW_PRE	"iwlwifi-QuIcp-z0-hrcdb-a0-"
-#define IWL_22000_HR_F0_FW_PRE	"iwlwifi-QuQnj-f0-hr-a0-"
-#define IWL_22000_JF_B0_FW_PRE	"iwlwifi-QuQnj-a0-jf-b0-"
-#define IWL_22000_HR_A0_FW_PRE	"iwlwifi-QuQnj-a0-hr-a0-"
+#define IWL_22000_JF_FW_PRE		"iwlwifi-Qu-a0-jf-b0-"
+#define IWL_22000_HR_FW_PRE		"iwlwifi-Qu-a0-hr-a0-"
+#define IWL_22000_HR_CDB_FW_PRE		"iwlwifi-QuIcp-z0-hrcdb-a0-"
+#define IWL_22000_HR_A_F0_FW_PRE	"iwlwifi-QuQnj-f0-hr-a0-"
+#define IWL_22000_HR_B_FW_PRE		"iwlwifi-Qu-b0-hr-b0-"
+#define IWL_22000_JF_B0_FW_PRE		"iwlwifi-QuQnj-a0-jf-b0-"
+#define IWL_22000_HR_A0_FW_PRE		"iwlwifi-QuQnj-a0-hr-a0-"
+#define IWL_22000_SU_Z0_FW_PRE		"iwlwifi-su-z0-"
 
 #define IWL_22000_HR_MODULE_FIRMWARE(api) \
 	IWL_22000_HR_FW_PRE __stringify(api) ".ucode"
 #define IWL_22000_JF_MODULE_FIRMWARE(api) \
 	IWL_22000_JF_FW_PRE __stringify(api) ".ucode"
-#define IWL_22000_HR_F0_QNJ_MODULE_FIRMWARE(api) \
-	IWL_22000_HR_F0_FW_PRE __stringify(api) ".ucode"
+#define IWL_22000_HR_A_F0_QNJ_MODULE_FIRMWARE(api) \
+	IWL_22000_HR_A_F0_FW_PRE __stringify(api) ".ucode"
+#define IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(api) \
+	IWL_22000_HR_B_FW_PRE __stringify(api) ".ucode"
 #define IWL_22000_JF_B0_QNJ_MODULE_FIRMWARE(api) \
 	IWL_22000_JF_B0_FW_PRE __stringify(api) ".ucode"
 #define IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(api) \
 	IWL_22000_HR_A0_FW_PRE __stringify(api) ".ucode"
+#define IWL_22000_SU_Z0_MODULE_FIRMWARE(api) \
+	IWL_22000_SU_Z0_FW_PRE __stringify(api) ".ucode"
 
 #define NVM_HW_SECTION_NUM_FAMILY_22000		10
 
@@ -179,6 +185,16 @@ const struct iwl_cfg iwl22000_2ax_cfg_hr = {
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+};
+
+const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0 = {
+	.name = "Intel(R) Dual Band Wireless AX 22000",
+	.fw_name_pre = IWL_22000_HR_A_F0_FW_PRE,
+	IWL_DEVICE_22000,
+	.ht_params = &iwl_22000_ht_params,
+	.nvm_ver = IWL_22000_NVM_VERSION,
+	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 	/*
 	 * This device doesn't support receiving BlockAck with a large bitmap
 	 * so we need to restrict the size of transmitted aggregation to the
@@ -187,21 +203,15 @@ const struct iwl_cfg iwl22000_2ax_cfg_hr = {
 	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
-const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_f0 = {
+const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_b0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
-	.fw_name_pre = IWL_22000_HR_F0_FW_PRE,
+	.fw_name_pre = IWL_22000_HR_B_FW_PRE,
 	IWL_DEVICE_22000,
 	.csr = &iwl_csr_v1,
 	.ht_params = &iwl_22000_ht_params,
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0 = {
@@ -213,12 +223,6 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0 = {
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
-	/*
-	 * This device doesn't support receiving BlockAck with a large bitmap
-	 * so we need to restrict the size of transmitted aggregation to the
-	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
-	 */
-	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
@@ -230,6 +234,17 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+};
+
+const struct iwl_cfg iwl22000_2ax_cfg_hr_cdb = {
+	.name = "Intel(R) Dual Band Wireless AX 22560",
+	.fw_name_pre = IWL_22000_SU_Z0_FW_PRE,
+	IWL_DEVICE_22000,
+	.ht_params = &iwl_22000_ht_params,
+	.nvm_ver = IWL_22000_NVM_VERSION,
+	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	.cdb = true,
 	/*
 	 * This device doesn't support receiving BlockAck with a large bitmap
 	 * so we need to restrict the size of transmitted aggregation to the
@@ -240,6 +255,8 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
 
 MODULE_FIRMWARE(IWL_22000_HR_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_JF_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
-MODULE_FIRMWARE(IWL_22000_HR_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_22000_HR_A_F0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_22000_HR_B_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_JF_B0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
 MODULE_FIRMWARE(IWL_22000_HR_A0_QNJ_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
+MODULE_FIRMWARE(IWL_22000_SU_Z0_MODULE_FIRMWARE(IWL_22000_UCODE_API_MAX));
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index c503b26793f6..ede491be7aac 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -566,9 +566,11 @@ extern const struct iwl_cfg iwl22000_2ac_cfg_hr;
 extern const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb;
 extern const struct iwl_cfg iwl22000_2ac_cfg_jf;
 extern const struct iwl_cfg iwl22000_2ax_cfg_hr;
-extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_f0;
+extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0;
+extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_b0;
 extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0;
 extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0;
+extern const struct iwl_cfg iwl22000_2ax_cfg_hr_cdb;
 #endif /* CONFIG_IWLMVM */
 
 #endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index ba971d3946e2..3ef71c22bcaa 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -339,6 +339,9 @@ enum {
 /* HW_RF CHIP ID  */
 #define CSR_HW_RF_ID_TYPE_CHIP_ID(_val) (((_val) >> 12) & 0xFFF)
 
+/* HW_RF CHIP STEP  */
+#define CSR_HW_RF_STEP(_val) (((_val) >> 8) & 0xF)
+
 /* EEPROM REG */
 #define CSR_EEPROM_REG_READ_VALID_MSK	(0x00000001)
 #define CSR_EEPROM_REG_BIT_CMD		(0x00000002)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 38234bda9017..0358b406be81 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -816,8 +816,6 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0x2720, 0x1080, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0090, iwl22000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x0310, iwl22000_2ac_cfg_hr_cdb)},
-	{IWL_PCI_DEVICE(0x40C0, 0x0000, iwl22000_2ax_cfg_hr)},
-	{IWL_PCI_DEVICE(0x40C0, 0x0A10, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x0000, iwl22000_2ax_cfg_hr)},
 
 #endif /* CONFIG_IWLMVM */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 57f5d8f3bdf6..e0398ef07388 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -3349,14 +3349,26 @@ struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
 
 #if IS_ENABLED(CONFIG_IWLMVM)
 	trans->hw_rf_id = iwl_read32(trans, CSR_HW_RF_ID);
-	if (trans->hw_rf_id == CSR_HW_RF_ID_TYPE_HR) {
+
+	if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) ==
+	    CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) {
 		u32 hw_status;
 
 		hw_status = iwl_read_prph(trans, UMAG_GEN_HW_STATUS);
-		if (hw_status & UMAG_GEN_HW_IS_FPGA)
-			trans->cfg = &iwl22000_2ax_cfg_qnj_hr_f0;
-		else
+		if (CSR_HW_RF_STEP(trans->hw_rf_id) == SILICON_B_STEP)
+			/*
+			* b step fw is the same for physical card and fpga
+			*/
+			trans->cfg = &iwl22000_2ax_cfg_qnj_hr_b0;
+		else if ((hw_status & UMAG_GEN_HW_IS_FPGA) &&
+			 CSR_HW_RF_STEP(trans->hw_rf_id) == SILICON_A_STEP) {
+			trans->cfg = &iwl22000_2ax_cfg_qnj_hr_a0_f0;
+		} else {
+			/*
+			* a step no FPGA
+			*/
 			trans->cfg = &iwl22000_2ac_cfg_hr;
+		}
 	}
 #endif
 
-- 
cgit v1.2.3


From c8f1b51e506dec74e671ed61f67e639754da322f Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 22 Oct 2017 15:58:26 +0300
Subject: iwlwifi: allow different csr flags for different device families

Different device families may have different flag values
for passing a message to the fw (i.e. SW_RESET).
In order to keep the code readable, and avoid conditioning
upon the family, store a value for each flag, which indicates
the bit that needs to be enabled.

Additionally, support 22560 device csr flags and addresses.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c  | 4 +++-
 drivers/net/wireless/intel/iwlwifi/iwl-config.h | 2 +-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index aafd8cab86b0..2768c2b15acb 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -191,6 +191,7 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_HR_A_F0_FW_PRE,
 	IWL_DEVICE_22000,
+	.csr = &iwl_csr_v1,
 	.ht_params = &iwl_22000_ht_params,
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
@@ -236,10 +237,11 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
 	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
 };
 
-const struct iwl_cfg iwl22000_2ax_cfg_hr_cdb = {
+const struct iwl_cfg iwl22560_2ax_cfg_su_cdb = {
 	.name = "Intel(R) Dual Band Wireless AX 22560",
 	.fw_name_pre = IWL_22000_SU_Z0_FW_PRE,
 	IWL_DEVICE_22000,
+	.csr = &iwl_csr_v2,
 	.ht_params = &iwl_22000_ht_params,
 	.nvm_ver = IWL_22000_NVM_VERSION,
 	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index ede491be7aac..b7389f1aa3af 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -570,7 +570,7 @@ extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0;
 extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_b0;
 extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0;
 extern const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0;
-extern const struct iwl_cfg iwl22000_2ax_cfg_hr_cdb;
+extern const struct iwl_cfg iwl22560_2ax_cfg_su_cdb;
 #endif /* CONFIG_IWLMVM */
 
 #endif /* __IWL_CONFIG_H__ */
-- 
cgit v1.2.3


From 5f01df3f58ab25cffb6b2577339fde1dfe696bf2 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Wed, 7 Feb 2018 20:08:56 +0200
Subject: iwlwifi: introduce device family 22560

Device 22560 have many different hw and sw features than 22000 family,
so introduce a new family of devices - 22560.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c    | 104 ++++++++++------------
 drivers/net/wireless/intel/iwlwifi/fw/smem.c      |   4 +-
 drivers/net/wireless/intel/iwlwifi/iwl-config.h   |   1 +
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c       |   4 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c |   2 +-
 5 files changed, 55 insertions(+), 60 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 2768c2b15acb..e39df74f49ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -116,10 +116,9 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ),
 };
 
-#define IWL_DEVICE_22000						\
+#define IWL_DEVICE_22000_COMMON						\
 	.ucode_api_max = IWL_22000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL_22000_UCODE_API_MIN,			\
-	.device_family = IWL_DEVICE_FAMILY_22000,			\
 	.base_params = &iwl_22000_base_params,				\
 	.led_mode = IWL_LED_RF_STATE,					\
 	.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_22000,		\
@@ -135,6 +134,10 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.mq_rx_supported = true,					\
 	.vht_mu_mimo_supported = true,					\
 	.mac_addr_from_csr = true,					\
+	.ht_params = &iwl_22000_ht_params,				\
+	.nvm_ver = IWL_22000_NVM_VERSION,				\
+	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,			\
+	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,		\
 	.use_tfh = true,						\
 	.rf_id = true,							\
 	.gen2 = true,							\
@@ -142,60 +145,51 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 	.dbgc_supported = true,						\
 	.min_umac_error_event_table = 0x400000
 
+#define IWL_DEVICE_22500						\
+	IWL_DEVICE_22000_COMMON,					\
+	.device_family = IWL_DEVICE_FAMILY_22000,			\
+	.csr = &iwl_csr_v1
+
+#define IWL_DEVICE_22560						\
+	IWL_DEVICE_22000_COMMON,					\
+	.device_family = IWL_DEVICE_FAMILY_22560,			\
+	.csr = &iwl_csr_v2
+
 const struct iwl_cfg iwl22000_2ac_cfg_hr = {
 	.name = "Intel(R) Dual Band Wireless AC 22000",
 	.fw_name_pre = IWL_22000_HR_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
 };
 
 const struct iwl_cfg iwl22000_2ac_cfg_hr_cdb = {
 	.name = "Intel(R) Dual Band Wireless AC 22000",
 	.fw_name_pre = IWL_22000_HR_CDB_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
 	.cdb = true,
 };
 
 const struct iwl_cfg iwl22000_2ac_cfg_jf = {
 	.name = "Intel(R) Dual Band Wireless AC 22000",
 	.fw_name_pre = IWL_22000_JF_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_hr = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_HR_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_HR_A_F0_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
 	/*
 	 * This device doesn't support receiving BlockAck with a large bitmap
 	 * so we need to restrict the size of transmitted aggregation to the
@@ -207,45 +201,43 @@ const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0_f0 = {
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_b0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_HR_B_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_jf_b0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_JF_B0_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22000_2ax_cfg_qnj_hr_a0 = {
 	.name = "Intel(R) Dual Band Wireless AX 22000",
 	.fw_name_pre = IWL_22000_HR_A0_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v1,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22500,
+	/*
+	 * This device doesn't support receiving BlockAck with a large bitmap
+	 * so we need to restrict the size of transmitted aggregation to the
+	 * HT size; mac80211 would otherwise pick the HE max (256) by default.
+	 */
+	.max_tx_agg_size = IEEE80211_MAX_AMPDU_BUF_HT,
 };
 
 const struct iwl_cfg iwl22560_2ax_cfg_su_cdb = {
 	.name = "Intel(R) Dual Band Wireless AX 22560",
 	.fw_name_pre = IWL_22000_SU_Z0_FW_PRE,
-	IWL_DEVICE_22000,
-	.csr = &iwl_csr_v2,
-	.ht_params = &iwl_22000_ht_params,
-	.nvm_ver = IWL_22000_NVM_VERSION,
-	.nvm_calib_ver = IWL_22000_TX_POWER_VERSION,
-	.max_ht_ampdu_exponent = IEEE80211_HT_MAX_AMPDU_64K,
+	IWL_DEVICE_22560,
 	.cdb = true,
 	/*
 	 * This device doesn't support receiving BlockAck with a large bitmap
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/smem.c b/drivers/net/wireless/intel/iwlwifi/fw/smem.c
index fb4b6442b4d7..ff85d69c2a8c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/smem.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/smem.c
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -143,7 +145,7 @@ void iwl_get_shared_mem_conf(struct iwl_fw_runtime *fwrt)
 		return;
 
 	pkt = cmd.resp_pkt;
-	if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_22000)
+	if (fwrt->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000)
 		iwl_parse_shared_mem_22000(fwrt, pkt);
 	else
 		iwl_parse_shared_mem(fwrt, pkt);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index b7389f1aa3af..c28e550fe3db 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -93,6 +93,7 @@ enum iwl_device_family {
 	IWL_DEVICE_FAMILY_8000,
 	IWL_DEVICE_FAMILY_9000,
 	IWL_DEVICE_FAMILY_22000,
+	IWL_DEVICE_FAMILY_22560,
 };
 
 /*
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 866c91c923be..5fe2b460234b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -301,7 +301,7 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	if (ret) {
 		struct iwl_trans *trans = mvm->trans;
 
-		if (trans->cfg->device_family == IWL_DEVICE_FAMILY_22000)
+		if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000)
 			IWL_ERR(mvm,
 				"SecBoot CPU1 Status: 0x%x, CPU2 Status: 0x%x\n",
 				iwl_read_prph(trans, UMAG_SB_CPU_1_STATUS),
@@ -1009,7 +1009,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	/* Init RSS configuration */
 	/* TODO - remove 22000 disablement when we have RXQ config API */
 	if (iwl_mvm_has_new_rx_api(mvm) &&
-	    mvm->trans->cfg->device_family != IWL_DEVICE_FAMILY_22000) {
+	    mvm->trans->cfg->device_family < IWL_DEVICE_FAMILY_22000) {
 		ret = iwl_send_rss_cfg_cmd(mvm);
 		if (ret) {
 			IWL_ERR(mvm, "Failed to configure RSS queues: %d\n",
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 9779db31ab30..a3b634ae3838 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4559,7 +4559,7 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 			   mvm->trans->num_rx_queues);
 
 	/* TODO - remove this when we have RXQ config API */
-	if (mvm->trans->cfg->device_family == IWL_DEVICE_FAMILY_22000) {
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
 		qmask = BIT(0);
 		if (notif->sync)
 			atomic_set(&mvm->queue_sync_counter, 1);
-- 
cgit v1.2.3


From 1b493e30a19540438a9944683aa9310b8077bc80 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 11 Feb 2018 10:48:32 +0200
Subject: iwlwifi: pcie: allocate and free rx cr's and tr's tails

The hw now refers to two new blocks:
* rx tr tail - The Tail index on the free buffers queue TR,
which is update by the device after reading the free buffer
from the tr.
* rx cr tail - Updated by the driver when completing
processing a new completion descriptor in the cr.

Add these two new struct to the rxq, allocate and free them
when needed.

In addition, the register for rx write pointer had been changed
to HBUS_TARG_WRPTR. The way to differentiate tx from rx is the
queue number. TX range is 0-511, and RX's is 512-527.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |  13 +-
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c       | 201 ++++++++++++---------
 2 files changed, 131 insertions(+), 83 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 45ea32796cda..d944c6ec0b87 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -3,6 +3,7 @@
  * Copyright(c) 2003 - 2015 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * Portions of this file are derived from the ipw3945 project, as well
  * as portions of the ieee80211 subsystem header files.
@@ -17,8 +18,7 @@
  * more details.
  *
  * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110, USA
+ * this program.
  *
  * The full GNU General Public License is included in this distribution in the
  * file called LICENSE.
@@ -59,6 +59,7 @@
 #define RX_POST_REQ_ALLOC 2
 #define RX_CLAIM_REQ_ALLOC 8
 #define RX_PENDING_WATERMARK 16
+#define FIRST_RX_QUEUE 512
 
 struct iwl_host_cmd;
 
@@ -106,6 +107,10 @@ struct isr_statistics {
  * @bd_dma: bus address of buffer of receive buffer descriptors (rbd)
  * @ubd: driver's pointer to buffer of used receive buffer descriptors (rbd)
  * @ubd_dma: physical address of buffer of used receive buffer descriptors (rbd)
+ * @tr_tail: driver's pointer to the transmission ring tail buffer
+ * @tr_tail_dma: physical address of the buffer for the transmission ring tail
+ * @cr_tail: driver's pointer to the completion ring tail buffer
+ * @cr_tail_dma: physical address of the buffer for the completion ring tail
  * @read: Shared index to newest available Rx buffer
  * @write: Shared index to oldest written Rx packet
  * @free_count: Number of pre-allocated buffers in rx_free
@@ -127,6 +132,10 @@ struct iwl_rxq {
 	dma_addr_t bd_dma;
 	__le32 *used_bd;
 	dma_addr_t used_bd_dma;
+	__le16 *tr_tail;
+	dma_addr_t tr_tail_dma;
+	__le16 *cr_tail;
+	dma_addr_t cr_tail_dma;
 	u32 read;
 	u32 write;
 	u32 free_count;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index d15f5ba2dc77..24ce2d6beb0f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -209,7 +209,11 @@ static void iwl_pcie_rxq_inc_wr_ptr(struct iwl_trans *trans,
 	}
 
 	rxq->write_actual = round_down(rxq->write, 8);
-	if (trans->cfg->mq_rx_supported)
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		iwl_write32(trans, HBUS_TARG_WRPTR,
+			    (rxq->write_actual |
+			     ((FIRST_RX_QUEUE + rxq->id) << 16)));
+	else if (trans->cfg->mq_rx_supported)
 		iwl_write32(trans, RFH_Q_FRBDCB_WIDX_TRG(rxq->id),
 			    rxq->write_actual);
 	else
@@ -608,89 +612,146 @@ void iwl_pcie_rx_allocator_work(struct work_struct *data)
 	iwl_pcie_rx_allocator(trans_pcie->trans);
 }
 
-static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
+static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans,
+				  struct iwl_rxq *rxq)
+{
+	struct device *dev = trans->dev;
+	int free_size = trans->cfg->mq_rx_supported ? sizeof(__le64) :
+						      sizeof(__le32);
+
+	if (rxq->bd)
+		dma_free_coherent(dev, free_size * rxq->queue_size,
+				  rxq->bd, rxq->bd_dma);
+	rxq->bd_dma = 0;
+	rxq->bd = NULL;
+
+	if (rxq->rb_stts)
+		dma_free_coherent(trans->dev,
+				  sizeof(struct iwl_rb_status),
+				  rxq->rb_stts, rxq->rb_stts_dma);
+	rxq->rb_stts_dma = 0;
+	rxq->rb_stts = NULL;
+
+	if (rxq->used_bd)
+		dma_free_coherent(dev, sizeof(__le32) * rxq->queue_size,
+				  rxq->used_bd, rxq->used_bd_dma);
+	rxq->used_bd_dma = 0;
+	rxq->used_bd = NULL;
+
+	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
+		return;
+
+	if (rxq->tr_tail)
+		dma_free_coherent(dev, sizeof(__le16),
+				  rxq->tr_tail, rxq->tr_tail_dma);
+	rxq->tr_tail_dma = 0;
+	rxq->tr_tail = NULL;
+
+	if (rxq->cr_tail)
+		dma_free_coherent(dev, sizeof(__le16),
+				  rxq->cr_tail, rxq->cr_tail_dma);
+	rxq->cr_tail_dma = 0;
+	rxq->cr_tail = NULL;
+}
+
+static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
+				  struct iwl_rxq *rxq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_rb_allocator *rba = &trans_pcie->rba;
 	struct device *dev = trans->dev;
 	int i;
 	int free_size = trans->cfg->mq_rx_supported ? sizeof(__le64) :
 						      sizeof(__le32);
 
-	if (WARN_ON(trans_pcie->rxq))
-		return -EINVAL;
+	spin_lock_init(&rxq->lock);
+	if (trans->cfg->mq_rx_supported)
+		rxq->queue_size = MQ_RX_TABLE_SIZE;
+	else
+		rxq->queue_size = RX_QUEUE_SIZE;
 
-	trans_pcie->rxq = kcalloc(trans->num_rx_queues, sizeof(struct iwl_rxq),
-				  GFP_KERNEL);
-	if (!trans_pcie->rxq)
-		return -EINVAL;
+	/*
+	 * Allocate the circular buffer of Read Buffer Descriptors
+	 * (RBDs)
+	 */
+	rxq->bd = dma_zalloc_coherent(dev,
+				      free_size * rxq->queue_size,
+				      &rxq->bd_dma, GFP_KERNEL);
+	if (!rxq->bd)
+		goto err;
 
-	spin_lock_init(&rba->lock);
+	if (trans->cfg->mq_rx_supported) {
+		rxq->used_bd = dma_zalloc_coherent(dev,
+						   sizeof(__le32) *
+						   rxq->queue_size,
+						   &rxq->used_bd_dma,
+						   GFP_KERNEL);
+		if (!rxq->used_bd)
+			goto err;
+	}
 
-	for (i = 0; i < trans->num_rx_queues; i++) {
-		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
+	/* Allocate the driver's pointer to receive buffer status */
+	rxq->rb_stts = dma_zalloc_coherent(dev, sizeof(*rxq->rb_stts),
+					   &rxq->rb_stts_dma,
+					   GFP_KERNEL);
+	if (!rxq->rb_stts)
+		goto err;
 
-		spin_lock_init(&rxq->lock);
-		if (trans->cfg->mq_rx_supported)
-			rxq->queue_size = MQ_RX_TABLE_SIZE;
-		else
-			rxq->queue_size = RX_QUEUE_SIZE;
+	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
+		return 0;
 
-		/*
-		 * Allocate the circular buffer of Read Buffer Descriptors
-		 * (RBDs)
-		 */
-		rxq->bd = dma_zalloc_coherent(dev,
-					     free_size * rxq->queue_size,
-					     &rxq->bd_dma, GFP_KERNEL);
-		if (!rxq->bd)
-			goto err;
+	/* Allocate the driver's pointer to TR tail */
+	rxq->tr_tail = dma_zalloc_coherent(dev, sizeof(__le16),
+					   &rxq->tr_tail_dma,
+					   GFP_KERNEL);
+	if (!rxq->tr_tail)
+		goto err;
 
-		if (trans->cfg->mq_rx_supported) {
-			rxq->used_bd = dma_zalloc_coherent(dev,
-							   sizeof(__le32) *
-							   rxq->queue_size,
-							   &rxq->used_bd_dma,
-							   GFP_KERNEL);
-			if (!rxq->used_bd)
-				goto err;
-		}
+	/* Allocate the driver's pointer to CR tail */
+	rxq->cr_tail = dma_zalloc_coherent(dev, sizeof(__le16),
+					   &rxq->cr_tail_dma,
+					   GFP_KERNEL);
+	if (!rxq->cr_tail)
+		goto err;
 
-		/*Allocate the driver's pointer to receive buffer status */
-		rxq->rb_stts = dma_zalloc_coherent(dev, sizeof(*rxq->rb_stts),
-						   &rxq->rb_stts_dma,
-						   GFP_KERNEL);
-		if (!rxq->rb_stts)
-			goto err;
-	}
 	return 0;
 
 err:
 	for (i = 0; i < trans->num_rx_queues; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
-		if (rxq->bd)
-			dma_free_coherent(dev, free_size * rxq->queue_size,
-					  rxq->bd, rxq->bd_dma);
-		rxq->bd_dma = 0;
-		rxq->bd = NULL;
-
-		if (rxq->rb_stts)
-			dma_free_coherent(trans->dev,
-					  sizeof(struct iwl_rb_status),
-					  rxq->rb_stts, rxq->rb_stts_dma);
-
-		if (rxq->used_bd)
-			dma_free_coherent(dev, sizeof(__le32) * rxq->queue_size,
-					  rxq->used_bd, rxq->used_bd_dma);
-		rxq->used_bd_dma = 0;
-		rxq->used_bd = NULL;
+		iwl_pcie_free_rxq_dma(trans, rxq);
 	}
 	kfree(trans_pcie->rxq);
 
 	return -ENOMEM;
 }
 
+static int iwl_pcie_rx_alloc(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_rb_allocator *rba = &trans_pcie->rba;
+	int i, ret;
+
+	if (WARN_ON(trans_pcie->rxq))
+		return -EINVAL;
+
+	trans_pcie->rxq = kcalloc(trans->num_rx_queues, sizeof(struct iwl_rxq),
+				  GFP_KERNEL);
+	if (!trans_pcie->rxq)
+		return -EINVAL;
+
+	spin_lock_init(&rba->lock);
+
+	for (i = 0; i < trans->num_rx_queues; i++) {
+		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
+
+		ret = iwl_pcie_alloc_rxq_dma(trans, rxq);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 static void iwl_pcie_rx_hw_init(struct iwl_trans *trans, struct iwl_rxq *rxq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -1002,8 +1063,6 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rb_allocator *rba = &trans_pcie->rba;
-	int free_size = trans->cfg->mq_rx_supported ? sizeof(__le64) :
-					      sizeof(__le32);
 	int i;
 
 	/*
@@ -1022,27 +1081,7 @@ void iwl_pcie_rx_free(struct iwl_trans *trans)
 	for (i = 0; i < trans->num_rx_queues; i++) {
 		struct iwl_rxq *rxq = &trans_pcie->rxq[i];
 
-		if (rxq->bd)
-			dma_free_coherent(trans->dev,
-					  free_size * rxq->queue_size,
-					  rxq->bd, rxq->bd_dma);
-		rxq->bd_dma = 0;
-		rxq->bd = NULL;
-
-		if (rxq->rb_stts)
-			dma_free_coherent(trans->dev,
-					  sizeof(struct iwl_rb_status),
-					  rxq->rb_stts, rxq->rb_stts_dma);
-		else
-			IWL_DEBUG_INFO(trans,
-				       "Free rxq->rb_stts which is NULL\n");
-
-		if (rxq->used_bd)
-			dma_free_coherent(trans->dev,
-					  sizeof(__le32) * rxq->queue_size,
-					  rxq->used_bd, rxq->used_bd_dma);
-		rxq->used_bd_dma = 0;
-		rxq->used_bd = NULL;
+		iwl_pcie_free_rxq_dma(trans, rxq);
 
 		if (rxq->napi.poll)
 			netif_napi_del(&rxq->napi);
-- 
cgit v1.2.3


From 2ee824026288eb7068e6327c5f34b8ddbea74094 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 11 Feb 2018 10:57:18 +0200
Subject: iwlwifi: pcie: support context information for 22560 devices

Context information structure was added to 22000 devices for
firmware self init.

In the next generation of devices the context information
changes significantly, and the original context information
is divided roughly to three data structures: context information gen3,
prph information and prph scratch.

In addition, the init flow changes so the firmware is loaded
by the IML, and so we must allocate the IML on the DRAM and
give the ROM the IML's address before kicking the firmware's
self init.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/Makefile        |   3 +-
 .../wireless/intel/iwlwifi/iwl-context-info-gen3.h | 285 +++++++++++++++++++++
 .../net/wireless/intel/iwlwifi/iwl-context-info.h  |   5 +
 .../wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c   | 202 +++++++++++++++
 .../net/wireless/intel/iwlwifi/pcie/ctxt-info.c    |  62 +----
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |  70 ++++-
 .../net/wireless/intel/iwlwifi/pcie/trans-gen2.c   |  11 +-
 7 files changed, 578 insertions(+), 60 deletions(-)
 create mode 100644 drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c

diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 4d08d78c6b71..d619995b8bc2 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -7,7 +7,8 @@ iwlwifi-objs		+= iwl-debug.o
 iwlwifi-objs		+= iwl-eeprom-read.o iwl-eeprom-parse.o
 iwlwifi-objs		+= iwl-phy-db.o iwl-nvm-parse.o
 iwlwifi-objs		+= pcie/drv.o pcie/rx.o pcie/tx.o pcie/trans.o
-iwlwifi-objs		+= pcie/ctxt-info.o pcie/trans-gen2.o pcie/tx-gen2.o
+iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
+iwlwifi-objs		+= pcie/trans-gen2.o pcie/tx-gen2.o
 iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o
 iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
 iwlwifi-objs		+= iwl-trans.o
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
new file mode 100644
index 000000000000..8969dcc0d2db
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
@@ -0,0 +1,285 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2018 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2018 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+#ifndef __iwl_context_info_file_gen3_h__
+#define __iwl_context_info_file_gen3_h__
+
+#include "iwl-context-info.h"
+
+#define CSR_CTXT_INFO_BOOT_CTRL         0x0
+#define CSR_CTXT_INFO_ADDR              0x118
+#define CSR_IML_DATA_ADDR               0x120
+#define CSR_IML_SIZE_ADDR               0x128
+
+/* Set bit for enabling automatic function boot */
+#define CSR_AUTO_FUNC_BOOT_ENA          BIT(1)
+/* Set bit for initiating function boot */
+#define CSR_AUTO_FUNC_INIT              BIT(7)
+
+/**
+ * enum iwl_prph_scratch_mtr_format - tfd size configuration
+ * @IWL_PRPH_MTR_FORMAT_16B: 16 bit tfd
+ * @IWL_PRPH_MTR_FORMAT_32B: 32 bit tfd
+ * @IWL_PRPH_MTR_FORMAT_64B: 64 bit tfd
+ * @IWL_PRPH_MTR_FORMAT_256B: 256 bit tfd
+ */
+enum iwl_prph_scratch_mtr_format {
+	IWL_PRPH_MTR_FORMAT_16B = 0x0,
+	IWL_PRPH_MTR_FORMAT_32B = 0x40000,
+	IWL_PRPH_MTR_FORMAT_64B = 0x80000,
+	IWL_PRPH_MTR_FORMAT_256B = 0xC0000,
+};
+
+/**
+ * enum iwl_prph_scratch_flags - PRPH scratch control flags
+ * @IWL_PRPH_SCRATCH_EARLY_DEBUG_EN: enable early debug conf
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_DRAM: use DRAM, with size allocated
+ *	in hwm config.
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_INTERNAL: use buffer on SRAM
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_ST_ARBITER: use st arbiter, mainly for
+ *	multicomm.
+ * @IWL_PRPH_SCRATCH_EDBG_DEST_TB22DTF: route debug data to SoC HW
+ * @IWL_PRPH_SCTATCH_RB_SIZE_4K: Use 4K RB size (the default is 2K)
+ * @IWL_PRPH_SCRATCH_MTR_MODE: format used for completion - 0: for
+ *	completion descriptor, 1 for responses (legacy)
+ * @IWL_PRPH_SCRATCH_MTR_FORMAT: a mask for the size of the tfd.
+ *	There are 4 optional values: 0: 16 bit, 1: 32 bit, 2: 64 bit,
+ *	3: 256 bit.
+ */
+enum iwl_prph_scratch_flags {
+	IWL_PRPH_SCRATCH_EARLY_DEBUG_EN		= BIT(4),
+	IWL_PRPH_SCRATCH_EDBG_DEST_DRAM		= BIT(8),
+	IWL_PRPH_SCRATCH_EDBG_DEST_INTERNAL	= BIT(9),
+	IWL_PRPH_SCRATCH_EDBG_DEST_ST_ARBITER	= BIT(10),
+	IWL_PRPH_SCRATCH_EDBG_DEST_TB22DTF	= BIT(11),
+	IWL_PRPH_SCRATCH_RB_SIZE_4K		= BIT(16),
+	IWL_PRPH_SCRATCH_MTR_MODE		= BIT(17),
+	IWL_PRPH_SCRATCH_MTR_FORMAT		= BIT(18) | BIT(19),
+};
+
+/*
+ * struct iwl_prph_scratch_version - version structure
+ * @mac_id: SKU and revision id
+ * @version: prph scratch information version id
+ * @size: the size of the context information in DWs
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_version {
+	__le16 mac_id;
+	__le16 version;
+	__le16 size;
+	__le16 reserved;
+} __packed; /* PERIPH_SCRATCH_VERSION_S */
+
+/*
+ * struct iwl_prph_scratch_control - control structure
+ * @control_flags: context information flags see &enum iwl_prph_scratch_flags
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_control {
+	__le32 control_flags;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_CONTROL_S */
+
+/*
+ * struct iwl_prph_scratch_ror_cfg - ror config
+ * @ror_base_addr: ror start address
+ * @ror_size: ror size in DWs
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_ror_cfg {
+	__le64 ror_base_addr;
+	__le32 ror_size;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_ROR_CFG_S */
+
+/*
+ * struct iwl_prph_scratch_hwm_cfg - hwm config
+ * @hwm_base_addr: hwm start address
+ * @hwm_size: hwm size in DWs
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_hwm_cfg {
+	__le64 hwm_base_addr;
+	__le32 hwm_size;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_HWM_CFG_S */
+
+/*
+ * struct iwl_prph_scratch_rbd_cfg - RBDs configuration
+ * @free_rbd_addr: default queue free RB CB base address
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch_rbd_cfg {
+	__le64 free_rbd_addr;
+	__le32 reserved;
+} __packed; /* PERIPH_SCRATCH_RBD_CFG_S */
+
+/*
+ * struct iwl_prph_scratch_ctrl_cfg - prph scratch ctrl and config
+ * @version: version information of context info and HW
+ * @control: control flags of FH configurations
+ * @ror_cfg: ror configuration
+ * @hwm_cfg: hwm configuration
+ * @rbd_cfg: default RX queue configuration
+ */
+struct iwl_prph_scratch_ctrl_cfg {
+	struct iwl_prph_scratch_version version;
+	struct iwl_prph_scratch_control control;
+	struct iwl_prph_scratch_ror_cfg ror_cfg;
+	struct iwl_prph_scratch_hwm_cfg hwm_cfg;
+	struct iwl_prph_scratch_rbd_cfg rbd_cfg;
+} __packed; /* PERIPH_SCRATCH_CTRL_CFG_S */
+
+/*
+ * struct iwl_prph_scratch - peripheral scratch mapping
+ * @ctrl_cfg: control and configuration of prph scratch
+ * @dram: firmware images addresses in DRAM
+ * @reserved: reserved
+ */
+struct iwl_prph_scratch {
+	struct iwl_prph_scratch_ctrl_cfg ctrl_cfg;
+	__le32 reserved[16];
+	struct iwl_context_info_dram dram;
+} __packed; /* PERIPH_SCRATCH_S */
+
+/*
+ * struct iwl_prph_info - peripheral information
+ * @boot_stage_mirror: reflects the value in the Boot Stage CSR register
+ * @ipc_status_mirror: reflects the value in the IPC Status CSR register
+ * @sleep_notif: indicates the peripheral sleep status
+ * @reserved: reserved
+ */
+struct iwl_prph_info {
+	__le32 boot_stage_mirror;
+	__le32 ipc_status_mirror;
+	__le32 sleep_notif;
+	__le32 reserved;
+} __packed; /* PERIPH_INFO_S */
+
+/*
+ * struct iwl_context_info_gen3 - device INIT configuration
+ * @version: version of the context information
+ * @size: size of context information in DWs
+ * @config: context in which the peripheral would execute - a subset of
+ *	capability csr register published by the peripheral
+ * @prph_info_base_addr: the peripheral information structure start address
+ * @cr_head_idx_arr_base_addr: the completion ring head index array
+ *	start address
+ * @tr_tail_idx_arr_base_addr: the transfer ring tail index array
+ *	start address
+ * @cr_tail_idx_arr_base_addr: the completion ring tail index array
+ *	start address
+ * @tr_head_idx_arr_base_addr: the transfer ring head index array
+ *	start address
+ * @cr_idx_arr_size: number of entries in the completion ring index array
+ * @tr_idx_arr_size: number of entries in the transfer ring index array
+ * @mtr_base_addr: the message transfer ring start address
+ * @mcr_base_addr: the message completion ring start address
+ * @mtr_size: number of entries which the message transfer ring can hold
+ * @mcr_size: number of entries which the message completion ring can hold
+ * @mtr_doorbell_vec: the doorbell vector associated with the message
+ *	transfer ring
+ * @mcr_doorbell_vec: the doorbell vector associated with the message
+ *	completion ring
+ * @mtr_msi_vec: the MSI which shall be generated by the peripheral after
+ *	completing a transfer descriptor in the message transfer ring
+ * @mcr_msi_vec: the MSI which shall be generated by the peripheral after
+ *	completing a completion descriptor in the message completion ring
+ * @mtr_opt_header_size: the size of the optional header in the transfer
+ *	descriptor associated with the message transfer ring in DWs
+ * @mtr_opt_footer_size: the size of the optional footer in the transfer
+ *	descriptor associated with the message transfer ring in DWs
+ * @mcr_opt_header_size: the size of the optional header in the completion
+ *	descriptor associated with the message completion ring in DWs
+ * @mcr_opt_footer_size: the size of the optional footer in the completion
+ *	descriptor associated with the message completion ring in DWs
+ * @msg_rings_ctrl_flags: message rings control flags
+ * @prph_info_msi_vec: the MSI which shall be generated by the peripheral
+ *	after updating the Peripheral Information structure
+ * @prph_scratch_base_addr: the peripheral scratch structure start address
+ * @prph_scratch_size: the size of the peripheral scratch structure in DWs
+ * @reserved: reserved
+ */
+struct iwl_context_info_gen3 {
+	__le16 version;
+	__le16 size;
+	__le32 config;
+	__le64 prph_info_base_addr;
+	__le64 cr_head_idx_arr_base_addr;
+	__le64 tr_tail_idx_arr_base_addr;
+	__le64 cr_tail_idx_arr_base_addr;
+	__le64 tr_head_idx_arr_base_addr;
+	__le16 cr_idx_arr_size;
+	__le16 tr_idx_arr_size;
+	__le64 mtr_base_addr;
+	__le64 mcr_base_addr;
+	__le16 mtr_size;
+	__le16 mcr_size;
+	__le16 mtr_doorbell_vec;
+	__le16 mcr_doorbell_vec;
+	__le16 mtr_msi_vec;
+	__le16 mcr_msi_vec;
+	u8 mtr_opt_header_size;
+	u8 mtr_opt_footer_size;
+	u8 mcr_opt_header_size;
+	u8 mcr_opt_footer_size;
+	__le16 msg_rings_ctrl_flags;
+	__le16 prph_info_msi_vec;
+	__le64 prph_scratch_base_addr;
+	__le32 prph_scratch_size;
+	__le32 reserved;
+} __packed; /* IPC_CONTEXT_INFO_S */
+
+int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
+				 const struct fw_img *fw);
+void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans);
+
+#endif /* __iwl_context_info_file_gen3_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
index b870c0986744..4b6fdf3b15fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info.h
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -19,6 +20,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -199,5 +201,8 @@ struct iwl_context_info {
 int iwl_pcie_ctxt_info_init(struct iwl_trans *trans, const struct fw_img *fw);
 void iwl_pcie_ctxt_info_free(struct iwl_trans *trans);
 void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans);
+int iwl_pcie_init_fw_sec(struct iwl_trans *trans,
+			 const struct fw_img *fw,
+			 struct iwl_context_info_dram *ctxt_dram);
 
 #endif /* __iwl_context_info_file_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
new file mode 100644
index 000000000000..fc926354e573
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -0,0 +1,202 @@
+/******************************************************************************
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2018 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2018 Intel Corporation
+ * All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *  * Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ *  * Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in
+ *    the documentation and/or other materials provided with the
+ *    distribution.
+ *  * Neither the name Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ *****************************************************************************/
+
+#include "iwl-trans.h"
+#include "iwl-fh.h"
+#include "iwl-context-info-gen3.h"
+#include "internal.h"
+#include "iwl-prph.h"
+
+int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
+				 const struct fw_img *fw)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_context_info_gen3 *ctxt_info_gen3;
+	struct iwl_prph_scratch *prph_scratch;
+	struct iwl_prph_scratch_ctrl_cfg *prph_sc_ctrl;
+	struct iwl_prph_info *prph_info;
+	void *iml_img;
+	u32 control_flags = 0;
+	int ret;
+
+	/* Allocate prph scratch */
+	prph_scratch = dma_alloc_coherent(trans->dev, sizeof(*prph_scratch),
+					  &trans_pcie->prph_scratch_dma_addr,
+					  GFP_KERNEL);
+	if (!prph_scratch)
+		return -ENOMEM;
+
+	prph_sc_ctrl = &prph_scratch->ctrl_cfg;
+
+	prph_sc_ctrl->version.version = 0;
+	prph_sc_ctrl->version.mac_id =
+		cpu_to_le16((u16)iwl_read32(trans, CSR_HW_REV));
+	prph_sc_ctrl->version.size = cpu_to_le16(sizeof(*prph_scratch) / 4);
+
+	control_flags = IWL_PRPH_SCRATCH_RB_SIZE_4K |
+			IWL_PRPH_SCRATCH_MTR_MODE |
+			(IWL_PRPH_MTR_FORMAT_256B &
+			 IWL_PRPH_SCRATCH_MTR_FORMAT);
+	prph_sc_ctrl->control.control_flags = cpu_to_le32(control_flags);
+
+	/* initialize RX default queue */
+	prph_sc_ctrl->rbd_cfg.free_rbd_addr =
+		cpu_to_le64(trans_pcie->rxq->bd_dma);
+
+	/* allocate ucode sections in dram and set addresses */
+	ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram);
+	if (ret) {
+		dma_free_coherent(trans->dev,
+				  sizeof(*prph_scratch),
+				  prph_scratch,
+				  trans_pcie->prph_scratch_dma_addr);
+		return ret;
+	}
+
+	/* Allocate prph information
+	 * currently we don't assign to the prph info anything, but it would get
+	 * assigned later */
+	prph_info = dma_alloc_coherent(trans->dev, sizeof(*prph_info),
+				       &trans_pcie->prph_info_dma_addr,
+				       GFP_KERNEL);
+	if (!prph_info)
+		return -ENOMEM;
+
+	/* Allocate context info */
+	ctxt_info_gen3 = dma_alloc_coherent(trans->dev,
+					    sizeof(*ctxt_info_gen3),
+					    &trans_pcie->ctxt_info_dma_addr,
+					    GFP_KERNEL);
+	if (!ctxt_info_gen3)
+		return -ENOMEM;
+
+	ctxt_info_gen3->prph_info_base_addr =
+		cpu_to_le64(trans_pcie->prph_info_dma_addr);
+	ctxt_info_gen3->prph_scratch_base_addr =
+		cpu_to_le64(trans_pcie->prph_scratch_dma_addr);
+	ctxt_info_gen3->prph_scratch_size =
+		cpu_to_le32(sizeof(*prph_scratch));
+	ctxt_info_gen3->cr_head_idx_arr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->rb_stts_dma);
+	ctxt_info_gen3->tr_tail_idx_arr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->tr_tail_dma);
+	ctxt_info_gen3->cr_tail_idx_arr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->cr_tail_dma);
+	ctxt_info_gen3->cr_idx_arr_size =
+		cpu_to_le16(IWL_NUM_OF_COMPLETION_RINGS);
+	ctxt_info_gen3->tr_idx_arr_size =
+		cpu_to_le16(IWL_NUM_OF_TRANSFER_RINGS);
+	ctxt_info_gen3->mtr_base_addr =
+		cpu_to_le64(trans_pcie->txq[trans_pcie->cmd_queue]->dma_addr);
+	ctxt_info_gen3->mcr_base_addr =
+		cpu_to_le64(trans_pcie->rxq->used_bd_dma);
+	ctxt_info_gen3->mtr_size =
+		cpu_to_le16(TFD_QUEUE_CB_SIZE(TFD_CMD_SLOTS));
+	ctxt_info_gen3->mcr_size =
+		cpu_to_le16(RX_QUEUE_CB_SIZE(MQ_RX_TABLE_SIZE));
+
+	trans_pcie->ctxt_info_gen3 = ctxt_info_gen3;
+	trans_pcie->prph_info = prph_info;
+	trans_pcie->prph_scratch = prph_scratch;
+
+	/* Allocate IML */
+	iml_img = dma_alloc_coherent(trans->dev, trans->iml_len,
+				     &trans_pcie->iml_dma_addr, GFP_KERNEL);
+	if (!iml_img)
+		return -ENOMEM;
+
+	memcpy(iml_img, trans->iml, trans->iml_len);
+
+	iwl_enable_interrupts(trans);
+
+	/* Configure debug, if exists */
+	if (trans->dbg_dest_tlv)
+		iwl_pcie_apply_destination(trans);
+
+	/* kick FW self load */
+	iwl_write64(trans, CSR_CTXT_INFO_ADDR,
+		    trans_pcie->ctxt_info_dma_addr);
+	iwl_write64(trans, CSR_IML_DATA_ADDR,
+		    trans_pcie->iml_dma_addr);
+	iwl_write32(trans, CSR_IML_SIZE_ADDR, trans->iml_len);
+	iwl_set_bit(trans, CSR_CTXT_INFO_BOOT_CTRL, CSR_AUTO_FUNC_BOOT_ENA);
+	iwl_set_bit(trans, CSR_GP_CNTRL, CSR_AUTO_FUNC_INIT);
+
+	return 0;
+}
+
+void iwl_pcie_ctxt_info_gen3_free(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	if (!trans_pcie->ctxt_info_gen3)
+		return;
+
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info_gen3),
+			  trans_pcie->ctxt_info_gen3,
+			  trans_pcie->ctxt_info_dma_addr);
+	trans_pcie->ctxt_info_dma_addr = 0;
+	trans_pcie->ctxt_info_gen3 = NULL;
+
+	iwl_pcie_ctxt_info_free_fw_img(trans);
+
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->prph_scratch),
+			  trans_pcie->prph_scratch,
+			  trans_pcie->prph_scratch_dma_addr);
+	trans_pcie->prph_scratch_dma_addr = 0;
+	trans_pcie->prph_scratch = NULL;
+
+	dma_free_coherent(trans->dev, sizeof(*trans_pcie->prph_info),
+			  trans_pcie->prph_info,
+			  trans_pcie->prph_info_dma_addr);
+	trans_pcie->prph_info_dma_addr = 0;
+	trans_pcie->prph_info = NULL;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
index 3fc4343581ee..b2cd7ef5fc3a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info.c
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -19,6 +20,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -55,57 +57,6 @@
 #include "internal.h"
 #include "iwl-prph.h"
 
-static int iwl_pcie_get_num_sections(const struct fw_img *fw,
-				     int start)
-{
-	int i = 0;
-
-	while (start < fw->num_sec &&
-	       fw->sec[start].offset != CPU1_CPU2_SEPARATOR_SECTION &&
-	       fw->sec[start].offset != PAGING_SEPARATOR_SECTION) {
-		start++;
-		i++;
-	}
-
-	return i;
-}
-
-static int iwl_pcie_ctxt_info_alloc_dma(struct iwl_trans *trans,
-					const struct fw_desc *sec,
-					struct iwl_dram_data *dram)
-{
-	dram->block = dma_alloc_coherent(trans->dev, sec->len,
-					 &dram->physical,
-					 GFP_KERNEL);
-	if (!dram->block)
-		return -ENOMEM;
-
-	dram->size = sec->len;
-	memcpy(dram->block, sec->data, sec->len);
-
-	return 0;
-}
-
-static void iwl_pcie_ctxt_info_free_fw_img(struct iwl_trans *trans)
-{
-	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
-	int i;
-
-	if (!dram->fw) {
-		WARN_ON(dram->fw_cnt);
-		return;
-	}
-
-	for (i = 0; i < dram->fw_cnt; i++)
-		dma_free_coherent(trans->dev, dram->fw[i].size,
-				  dram->fw[i].block, dram->fw[i].physical);
-
-	kfree(dram->fw);
-	dram->fw_cnt = 0;
-	dram->fw = NULL;
-}
-
 void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -128,13 +79,12 @@ void iwl_pcie_ctxt_info_free_paging(struct iwl_trans *trans)
 	dram->paging = NULL;
 }
 
-static int iwl_pcie_ctxt_info_init_fw_sec(struct iwl_trans *trans,
-					  const struct fw_img *fw,
-					  struct iwl_context_info *ctxt_info)
+int iwl_pcie_init_fw_sec(struct iwl_trans *trans,
+			 const struct fw_img *fw,
+			 struct iwl_context_info_dram *ctxt_dram)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
-	struct iwl_context_info_dram *ctxt_dram = &ctxt_info->dram;
 	int i, ret, lmac_cnt, umac_cnt, paging_cnt;
 
 	if (WARN(dram->paging,
@@ -247,7 +197,7 @@ int iwl_pcie_ctxt_info_init(struct iwl_trans *trans,
 		TFD_QUEUE_CB_SIZE(TFD_CMD_SLOTS);
 
 	/* allocate ucode sections in dram and set addresses */
-	ret = iwl_pcie_ctxt_info_init_fw_sec(trans, fw, ctxt_info);
+	ret = iwl_pcie_init_fw_sec(trans, fw, &ctxt_info->dram);
 	if (ret) {
 		dma_free_coherent(trans->dev, sizeof(*trans_pcie->ctxt_info),
 				  ctxt_info, trans_pcie->ctxt_info_dma_addr);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index d944c6ec0b87..5db9ded4bb23 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -356,6 +356,12 @@ struct iwl_self_init_dram {
  * @global_table: table mapping received VID from hw to rxb
  * @rba: allocator for RX replenishing
  * @ctxt_info: context information for FW self init
+ * @ctxt_info_gen3: context information for gen3 devices
+ * @prph_info: prph info for self init
+ * @prph_scratch: prph scratch for self init
+ * @ctxt_info_dma_addr: dma addr of context information
+ * @prph_info_dma_addr: dma addr of prph info
+ * @prph_scratch_dma_addr: dma addr of prph scratch
  * @ctxt_info_dma_addr: dma addr of context information
  * @init_dram: DRAM data of firmware image (including paging).
  *	Context information addresses will be taken from here.
@@ -400,8 +406,16 @@ struct iwl_trans_pcie {
 	struct iwl_rx_mem_buffer rx_pool[RX_POOL_SIZE];
 	struct iwl_rx_mem_buffer *global_table[RX_POOL_SIZE];
 	struct iwl_rb_allocator rba;
-	struct iwl_context_info *ctxt_info;
+	union {
+		struct iwl_context_info *ctxt_info;
+		struct iwl_context_info_gen3 *ctxt_info_gen3;
+	};
+	struct iwl_prph_info *prph_info;
+	struct iwl_prph_scratch *prph_scratch;
 	dma_addr_t ctxt_info_dma_addr;
+	dma_addr_t prph_info_dma_addr;
+	dma_addr_t prph_scratch_dma_addr;
+	dma_addr_t iml_dma_addr;
 	struct iwl_self_init_dram init_dram;
 	struct iwl_trans *trans;
 
@@ -597,6 +611,60 @@ static inline void _iwl_disable_interrupts(struct iwl_trans *trans)
 	IWL_DEBUG_ISR(trans, "Disabled interrupts\n");
 }
 
+#define IWL_NUM_OF_COMPLETION_RINGS	31
+#define IWL_NUM_OF_TRANSFER_RINGS	527
+
+static inline int iwl_pcie_get_num_sections(const struct fw_img *fw,
+					    int start)
+{
+	int i = 0;
+
+	while (start < fw->num_sec &&
+	       fw->sec[start].offset != CPU1_CPU2_SEPARATOR_SECTION &&
+	       fw->sec[start].offset != PAGING_SEPARATOR_SECTION) {
+		start++;
+		i++;
+	}
+
+	return i;
+}
+
+static inline int iwl_pcie_ctxt_info_alloc_dma(struct iwl_trans *trans,
+					       const struct fw_desc *sec,
+					       struct iwl_dram_data *dram)
+{
+	dram->block = dma_alloc_coherent(trans->dev, sec->len,
+					 &dram->physical,
+					 GFP_KERNEL);
+	if (!dram->block)
+		return -ENOMEM;
+
+	dram->size = sec->len;
+	memcpy(dram->block, sec->data, sec->len);
+
+	return 0;
+}
+
+static inline void iwl_pcie_ctxt_info_free_fw_img(struct iwl_trans *trans)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_self_init_dram *dram = &trans_pcie->init_dram;
+	int i;
+
+	if (!dram->fw) {
+		WARN_ON(dram->fw_cnt);
+		return;
+	}
+
+	for (i = 0; i < dram->fw_cnt; i++)
+		dma_free_coherent(trans->dev, dram->fw[i].size,
+				  dram->fw[i].block, dram->fw[i].physical);
+
+	kfree(dram->fw);
+	dram->fw_cnt = 0;
+	dram->fw = NULL;
+}
+
 static inline void iwl_disable_interrupts(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index b8e8dac2895d..2bc67219ed3e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -53,6 +53,7 @@
 #include "iwl-trans.h"
 #include "iwl-prph.h"
 #include "iwl-context-info.h"
+#include "iwl-context-info-gen3.h"
 #include "internal.h"
 
 /*
@@ -188,7 +189,10 @@ void _iwl_trans_pcie_gen2_stop_device(struct iwl_trans *trans, bool low_power)
 	}
 
 	iwl_pcie_ctxt_info_free_paging(trans);
-	iwl_pcie_ctxt_info_free(trans);
+	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_22560)
+		iwl_pcie_ctxt_info_gen3_free(trans);
+	else
+		iwl_pcie_ctxt_info_free(trans);
 
 	/* Make sure (redundant) we've released our request to stay awake */
 	iwl_clear_bit(trans, CSR_GP_CNTRL,
@@ -346,7 +350,10 @@ int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 		goto out;
 	}
 
-	ret = iwl_pcie_ctxt_info_init(trans, fw);
+	if (trans->cfg->device_family == IWL_DEVICE_FAMILY_22560)
+		ret = iwl_pcie_ctxt_info_gen3_init(trans, fw);
+	else
+		ret = iwl_pcie_ctxt_info_init(trans, fw);
 	if (ret)
 		goto out;
 
-- 
cgit v1.2.3


From 2a182fbb29607249244dda0a85131e249799c904 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Tue, 2 Jan 2018 12:08:31 +0200
Subject: iwlwifi: pcie: update bytes in the byte count table

For devices which use the image loader image, the length of the frame
must be updated in the byte count in bytes, and not dwords as today.
Avoid dividing the input length by 4.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c      |  3 ++-
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 10 +++++++---
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index aa11b35d6f51..5d9b9306ea1c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -708,7 +708,8 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
 
 	trans->wide_cmd_header = true;
-	trans_cfg.bc_table_dword = true;
+	trans_cfg.bc_table_dword =
+		mvm->trans->cfg->device_family < IWL_DEVICE_FAMILY_22560;
 
 	trans_cfg.command_groups = iwl_mvm_groups;
 	trans_cfg.command_groups_size = ARRAY_SIZE(iwl_mvm_groups);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 48890a1c825f..5f05bcb26776 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -19,6 +20,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018        Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -84,7 +86,8 @@ void iwl_pcie_gen2_tx_stop(struct iwl_trans *trans)
 /*
  * iwl_pcie_txq_update_byte_tbl - Set up entry in Tx byte-count array
  */
-static void iwl_pcie_gen2_update_byte_tbl(struct iwl_txq *txq, u16 byte_cnt,
+static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans_pcie *trans_pcie,
+					  struct iwl_txq *txq, u16 byte_cnt,
 					  int num_tbs)
 {
 	struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
@@ -93,7 +96,8 @@ static void iwl_pcie_gen2_update_byte_tbl(struct iwl_txq *txq, u16 byte_cnt,
 	u16 len = byte_cnt;
 	__le16 bc_ent;
 
-	len = DIV_ROUND_UP(len, 4);
+	if (trans_pcie->bc_table_dword)
+		len = DIV_ROUND_UP(len, 4);
 
 	if (WARN_ON(len > 0xFFF || idx >= txq->n_window))
 		return;
@@ -526,7 +530,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Set up entry for this TFD in Tx byte-count array */
-	iwl_pcie_gen2_update_byte_tbl(txq, le16_to_cpu(tx_cmd->len),
+	iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, le16_to_cpu(tx_cmd->len),
 				      iwl_pcie_gen2_get_num_tbs(trans, tfd));
 
 	/* start timer if queue currently empty */
-- 
cgit v1.2.3


From 9f358c1716ba2d4da15aa09835d0a86bc504963a Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Tue, 26 Dec 2017 14:49:30 +0200
Subject: iwlwifi: pcie: start early debug for 22560 devices

In 22560 devices we can start debug using context info gen3. Configure
the fw to start collecting logs to the dram before init.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c | 15 ++++++++++-----
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h       |  3 +++
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c          |  2 +-
 3 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
index fc926354e573..2146fda8da2f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -84,13 +84,22 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	control_flags = IWL_PRPH_SCRATCH_RB_SIZE_4K |
 			IWL_PRPH_SCRATCH_MTR_MODE |
 			(IWL_PRPH_MTR_FORMAT_256B &
-			 IWL_PRPH_SCRATCH_MTR_FORMAT);
+			 IWL_PRPH_SCRATCH_MTR_FORMAT) |
+			IWL_PRPH_SCRATCH_EARLY_DEBUG_EN |
+			IWL_PRPH_SCRATCH_EDBG_DEST_DRAM;
 	prph_sc_ctrl->control.control_flags = cpu_to_le32(control_flags);
 
 	/* initialize RX default queue */
 	prph_sc_ctrl->rbd_cfg.free_rbd_addr =
 		cpu_to_le64(trans_pcie->rxq->bd_dma);
 
+	/* Configure debug, for integration */
+	iwl_pcie_alloc_fw_monitor(trans, 0);
+	prph_sc_ctrl->hwm_cfg.hwm_base_addr =
+		cpu_to_le64(trans_pcie->fw_mon_phys);
+	prph_sc_ctrl->hwm_cfg.hwm_size =
+		cpu_to_le32(trans_pcie->fw_mon_size);
+
 	/* allocate ucode sections in dram and set addresses */
 	ret = iwl_pcie_init_fw_sec(trans, fw, &prph_scratch->dram);
 	if (ret) {
@@ -157,10 +166,6 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 
 	iwl_enable_interrupts(trans);
 
-	/* Configure debug, if exists */
-	if (trans->dbg_dest_tlv)
-		iwl_pcie_apply_destination(trans);
-
 	/* kick FW self load */
 	iwl_write64(trans, CSR_CTXT_INFO_ADDR,
 		    trans_pcie->ctxt_info_dma_addr);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 5db9ded4bb23..e14d2003244f 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -895,6 +895,9 @@ void iwl_pcie_free_tso_page(struct iwl_trans_pcie *trans_pcie,
 struct iwl_tso_hdr_page *get_page_hdr(struct iwl_trans *trans, size_t len);
 #endif
 
+/* common functions that are used by gen3 transport */
+void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power);
+
 /* transport gen 2 exported functions */
 int iwl_trans_pcie_gen2_start_fw(struct iwl_trans *trans,
 				 const struct fw_img *fw, bool run_in_rfkill);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index e0398ef07388..bc14227c95ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -203,7 +203,7 @@ static void iwl_pcie_free_fw_monitor(struct iwl_trans *trans)
 	trans_pcie->fw_mon_size = 0;
 }
 
-static void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power)
+void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct page *page = NULL;
-- 
cgit v1.2.3


From 9b58419e511a8b7c3ae1cebe1926fc3a7c59a31c Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Thu, 1 Feb 2018 17:54:48 +0200
Subject: iwlwifi: update gen3 interrupts - sw error and image response

In 22560 devices the ROM sendis an interrupt to the host
once the IML reading is done.
Handle this interrupt, and indicate sw error in case the
value is fail.

Additionally, the cause for sw error in 22560 devices
have been changed, so update the cause list.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 .../wireless/intel/iwlwifi/iwl-context-info-gen3.h |  1 +
 drivers/net/wireless/intel/iwlwifi/iwl-csr.h       |  2 ++
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h | 12 ++++++++
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c       | 21 ++++++++++----
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    | 33 ++++++++++++++++++----
 5 files changed, 59 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
index 8969dcc0d2db..ebea99189ca9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
@@ -57,6 +57,7 @@
 #define CSR_CTXT_INFO_ADDR              0x118
 #define CSR_IML_DATA_ADDR               0x120
 #define CSR_IML_SIZE_ADDR               0x128
+#define CSR_IML_RESP_ADDR               0x12c
 
 /* Set bit for enabling automatic function boot */
 #define CSR_AUTO_FUNC_BOOT_ENA          BIT(1)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
index 3ef71c22bcaa..9019de99f077 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-csr.h
@@ -595,6 +595,8 @@ enum msix_fh_int_causes {
 enum msix_hw_int_causes {
 	MSIX_HW_INT_CAUSES_REG_ALIVE		= BIT(0),
 	MSIX_HW_INT_CAUSES_REG_WAKEUP		= BIT(1),
+	MSIX_HW_INT_CAUSES_REG_IPC		= BIT(1),
+	MSIX_HW_INT_CAUSES_REG_SW_ERR_V2	= BIT(5),
 	MSIX_HW_INT_CAUSES_REG_CT_KILL		= BIT(6),
 	MSIX_HW_INT_CAUSES_REG_RF_KILL		= BIT(7),
 	MSIX_HW_INT_CAUSES_REG_PERIODIC		= BIT(8),
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index e14d2003244f..76fd3ee61720 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -323,6 +323,18 @@ enum iwl_shared_irq_flags {
 	IWL_SHARED_IRQ_FIRST_RSS	= BIT(1),
 };
 
+/**
+ * enum iwl_image_response_code - image response values
+ * @IWL_IMAGE_RESP_DEF: the default value of the register
+ * @IWL_IMAGE_RESP_SUCCESS: iml was read successfully
+ * @IWL_IMAGE_RESP_FAIL: iml reading failed
+ */
+enum iwl_image_response_code {
+	IWL_IMAGE_RESP_DEF		= 0,
+	IWL_IMAGE_RESP_SUCCESS		= 1,
+	IWL_IMAGE_RESP_FAIL		= 2,
+};
+
 /**
  * struct iwl_dram_data
  * @physical: page phy pointer
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 24ce2d6beb0f..707242f1ff0b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -18,8 +18,7 @@
  * more details.
  *
  * You should have received a copy of the GNU General Public License along with
- * this program; if not, write to the Free Software Foundation, Inc.,
- * 51 Franklin Street, Fifth Floor, Boston, MA 02110, USA
+ * this program.
  *
  * The full GNU General Public License is included in this distribution in the
  * file called LICENSE.
@@ -37,6 +36,7 @@
 #include "iwl-io.h"
 #include "internal.h"
 #include "iwl-op-mode.h"
+#include "iwl-context-info-gen3.h"
 
 /******************************************************************************
  *
@@ -2009,7 +2009,8 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 
 	/* Error detected by uCode */
 	if ((inta_fh & MSIX_FH_INT_CAUSES_FH_ERR) ||
-	    (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR)) {
+	    (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR) ||
+	    (inta_hw & MSIX_HW_INT_CAUSES_REG_SW_ERR_V2)) {
 		IWL_ERR(trans,
 			"Microcode SW error detected. Restarting 0x%X.\n",
 			inta_fh);
@@ -2034,8 +2035,18 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id)
 		}
 	}
 
-	/* uCode wakes up after power-down sleep */
-	if (inta_hw & MSIX_HW_INT_CAUSES_REG_WAKEUP) {
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560 &&
+	    inta_hw & MSIX_HW_INT_CAUSES_REG_IPC) {
+		/* Reflect IML transfer status */
+		int res = iwl_read32(trans, CSR_IML_RESP_ADDR);
+
+		IWL_DEBUG_ISR(trans, "IML transfer status: %d\n", res);
+		if (res == IWL_IMAGE_RESP_FAIL) {
+			isr_stats->sw++;
+			iwl_pcie_irq_handle_error(trans);
+		}
+	} else if (inta_hw & MSIX_HW_INT_CAUSES_REG_WAKEUP) {
+		/* uCode wakes up after power-down sleep */
 		IWL_DEBUG_ISR(trans, "Wakeup interrupt\n");
 		iwl_pcie_rxq_check_wrptr(trans);
 		iwl_pcie_txq_check_wrptrs(trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index bc14227c95ac..efde21580166 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1132,21 +1132,44 @@ static struct iwl_causes_list causes_list[] = {
 	{MSIX_HW_INT_CAUSES_REG_HAP,		CSR_MSIX_HW_INT_MASK_AD, 0x2E},
 };
 
+static struct iwl_causes_list causes_list_v2[] = {
+	{MSIX_FH_INT_CAUSES_D2S_CH0_NUM,	CSR_MSIX_FH_INT_MASK_AD, 0},
+	{MSIX_FH_INT_CAUSES_D2S_CH1_NUM,	CSR_MSIX_FH_INT_MASK_AD, 0x1},
+	{MSIX_FH_INT_CAUSES_S2D,		CSR_MSIX_FH_INT_MASK_AD, 0x3},
+	{MSIX_FH_INT_CAUSES_FH_ERR,		CSR_MSIX_FH_INT_MASK_AD, 0x5},
+	{MSIX_HW_INT_CAUSES_REG_ALIVE,		CSR_MSIX_HW_INT_MASK_AD, 0x10},
+	{MSIX_HW_INT_CAUSES_REG_IPC,		CSR_MSIX_HW_INT_MASK_AD, 0x11},
+	{MSIX_HW_INT_CAUSES_REG_SW_ERR_V2,	CSR_MSIX_HW_INT_MASK_AD, 0x15},
+	{MSIX_HW_INT_CAUSES_REG_CT_KILL,	CSR_MSIX_HW_INT_MASK_AD, 0x16},
+	{MSIX_HW_INT_CAUSES_REG_RF_KILL,	CSR_MSIX_HW_INT_MASK_AD, 0x17},
+	{MSIX_HW_INT_CAUSES_REG_PERIODIC,	CSR_MSIX_HW_INT_MASK_AD, 0x18},
+	{MSIX_HW_INT_CAUSES_REG_SCD,		CSR_MSIX_HW_INT_MASK_AD, 0x2A},
+	{MSIX_HW_INT_CAUSES_REG_FH_TX,		CSR_MSIX_HW_INT_MASK_AD, 0x2B},
+	{MSIX_HW_INT_CAUSES_REG_HW_ERR,		CSR_MSIX_HW_INT_MASK_AD, 0x2D},
+	{MSIX_HW_INT_CAUSES_REG_HAP,		CSR_MSIX_HW_INT_MASK_AD, 0x2E},
+};
+
 static void iwl_pcie_map_non_rx_causes(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie =  IWL_TRANS_GET_PCIE_TRANS(trans);
 	int val = trans_pcie->def_irq | MSIX_NON_AUTO_CLEAR_CAUSE;
-	int i;
+	int i, arr_size =
+		(trans->cfg->device_family < IWL_DEVICE_FAMILY_22560) ?
+		ARRAY_SIZE(causes_list) : ARRAY_SIZE(causes_list_v2);
 
 	/*
 	 * Access all non RX causes and map them to the default irq.
 	 * In case we are missing at least one interrupt vector,
 	 * the first interrupt vector will serve non-RX and FBQ causes.
 	 */
-	for (i = 0; i < ARRAY_SIZE(causes_list); i++) {
-		iwl_write8(trans, CSR_MSIX_IVAR(causes_list[i].addr), val);
-		iwl_clear_bit(trans, causes_list[i].mask_reg,
-			      causes_list[i].cause_num);
+	for (i = 0; i < arr_size; i++) {
+		struct iwl_causes_list *causes =
+			(trans->cfg->device_family < IWL_DEVICE_FAMILY_22560) ?
+			causes_list : causes_list_v2;
+
+		iwl_write8(trans, CSR_MSIX_IVAR(causes[i].addr), val);
+		iwl_clear_bit(trans, causes[i].mask_reg,
+			      causes[i].cause_num);
 	}
 }
 
-- 
cgit v1.2.3


From f5955a6cc3862a02d46f50b723c3172d24d749a5 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 4 Feb 2018 10:50:05 +0200
Subject: iwlwifi: cancel the injective function between hw pointers to tfd
 entry index

Nowadays, the tfd queue max size is 2^8, and the reserved size in the
command header sequence field for the tfd entry index is 8 bits,
allowing an injective function from the hw pointers to the tfd entry index
in the sequence field.

In 22560 devices the tfd queue max size is 2^16, meaning that
the hw pointers are 16 bit long (allowing to point to each entry
in the tfd queue). However, the reserved space in the sequence field for
the tfd entry doesn't change, and we are limited to 8 bit.
This requires cancelling the injective function from hw pointer to
tfd entry in the sequence number.

Use iwl_pcie_get_cmd_index to wrap the hw pointer's to the n_window
size, which is maximum 256 in tx queues, and so, keep the injective
function between the window wrapped hw pointers to tfd entry index in
the sequence.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h | 12 ++++++++----
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c       | 11 ++++++++---
 2 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 76fd3ee61720..b4e998747e04 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -749,7 +749,7 @@ static inline void iwl_enable_fw_load_int(struct iwl_trans *trans)
 	}
 }
 
-static inline u8 iwl_pcie_get_cmd_index(struct iwl_txq *q, u32 index)
+static inline u8 iwl_pcie_get_cmd_index(const struct iwl_txq *q, u32 index)
 {
 	return index & (q->n_window - 1);
 }
@@ -819,9 +819,13 @@ static inline void iwl_stop_queue(struct iwl_trans *trans,
 
 static inline bool iwl_queue_used(const struct iwl_txq *q, int i)
 {
-	return q->write_ptr >= q->read_ptr ?
-		(i >= q->read_ptr && i < q->write_ptr) :
-		!(i < q->read_ptr && i >= q->write_ptr);
+	int index = iwl_pcie_get_cmd_index(q, i);
+	int r = iwl_pcie_get_cmd_index(q, q->read_ptr);
+	int w = iwl_pcie_get_cmd_index(q, q->write_ptr);
+
+	return w >= r ?
+		(index >= r && index < w) :
+		!(index < r && index >= w);
 }
 
 static inline bool iwl_is_rfkill_set(struct iwl_trans *trans)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 473fe7ccb07c..11bd7ce2be8e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1225,9 +1225,13 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 	struct iwl_txq *txq = trans_pcie->txq[txq_id];
 	unsigned long flags;
 	int nfreed = 0;
+	u16 r;
 
 	lockdep_assert_held(&txq->lock);
 
+	idx = iwl_pcie_get_cmd_index(txq, idx);
+	r = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
+
 	if ((idx >= TFD_QUEUE_SIZE_MAX) || (!iwl_queue_used(txq, idx))) {
 		IWL_ERR(trans,
 			"%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
@@ -1236,12 +1240,13 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 		return;
 	}
 
-	for (idx = iwl_queue_inc_wrap(idx); txq->read_ptr != idx;
-	     txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr)) {
+	for (idx = iwl_queue_inc_wrap(idx); r != idx;
+	     r = iwl_queue_inc_wrap(r)) {
+		txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr);
 
 		if (nfreed++ > 0) {
 			IWL_ERR(trans, "HCMD skipped: index (%d) %d %d\n",
-				idx, txq->write_ptr, txq->read_ptr);
+				idx, txq->write_ptr, r);
 			iwl_force_nmi(trans);
 		}
 	}
-- 
cgit v1.2.3


From 7b3e42ea2eadd41cc9d6363a9813b8ba8ab6f0e6 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 4 Feb 2018 12:51:45 +0200
Subject: iwlwifi: support multiple tfd queue max sizes for different devices

22560 devices tfd queue max size is 2^16. Allow a configurable
max size in the driver for supporting different devices.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/2000.c      |  2 +
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c     | 16 +++-
 drivers/net/wireless/intel/iwlwifi/cfg/5000.c      |  1 +
 drivers/net/wireless/intel/iwlwifi/cfg/6000.c      |  3 +
 drivers/net/wireless/intel/iwlwifi/cfg/7000.c      |  1 +
 drivers/net/wireless/intel/iwlwifi/cfg/8000.c      |  1 +
 drivers/net/wireless/intel/iwlwifi/cfg/9000.c      |  1 +
 drivers/net/wireless/intel/iwlwifi/iwl-config.h    |  2 +
 drivers/net/wireless/intel/iwlwifi/iwl-fh.h        | 22 +++++-
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h | 12 +--
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    |  6 +-
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c  | 24 ++++--
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c       | 87 +++++++++++++---------
 13 files changed, 119 insertions(+), 59 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
index a63ca8820568..fedb108db68f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/2000.c
@@ -63,6 +63,7 @@
 static const struct iwl_base_params iwl2000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_2x00,
 	.shadow_ram_support = true,
 	.led_compensation = 51,
@@ -76,6 +77,7 @@ static const struct iwl_base_params iwl2000_base_params = {
 static const struct iwl_base_params iwl2030_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_2x00,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index e39df74f49ad..e5d5578f8b92 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -102,6 +102,19 @@
 static const struct iwl_base_params iwl_22000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_22000,
 	.num_of_queues = 512,
+	.max_tfd_queue_size = 256,
+	.shadow_ram_support = true,
+	.led_compensation = 57,
+	.wd_timeout = IWL_LONG_WD_TIMEOUT,
+	.max_event_log_size = 512,
+	.shadow_reg_enable = true,
+	.pcie_l1_allowed = true,
+};
+
+static const struct iwl_base_params iwl_22560_base_params = {
+	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_22000,
+	.num_of_queues = 512,
+	.max_tfd_queue_size = 65536,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
@@ -119,7 +132,6 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 #define IWL_DEVICE_22000_COMMON						\
 	.ucode_api_max = IWL_22000_UCODE_API_MAX,			\
 	.ucode_api_min = IWL_22000_UCODE_API_MIN,			\
-	.base_params = &iwl_22000_base_params,				\
 	.led_mode = IWL_LED_RF_STATE,					\
 	.nvm_hw_section_num = NVM_HW_SECTION_NUM_FAMILY_22000,		\
 	.non_shared_ant = ANT_A,					\
@@ -148,11 +160,13 @@ static const struct iwl_ht_params iwl_22000_ht_params = {
 #define IWL_DEVICE_22500						\
 	IWL_DEVICE_22000_COMMON,					\
 	.device_family = IWL_DEVICE_FAMILY_22000,			\
+	.base_params = &iwl_22000_base_params,				\
 	.csr = &iwl_csr_v1
 
 #define IWL_DEVICE_22560						\
 	IWL_DEVICE_22000_COMMON,					\
 	.device_family = IWL_DEVICE_FAMILY_22560,			\
+	.base_params = &iwl_22560_base_params,				\
 	.csr = &iwl_csr_v2
 
 const struct iwl_cfg iwl22000_2ac_cfg_hr = {
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
index a224f1be1ec2..36151e61a26f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/5000.c
@@ -53,6 +53,7 @@
 static const struct iwl_base_params iwl5000_base_params = {
 	.eeprom_size = IWLAGN_EEPROM_IMG_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.pll_cfg = true,
 	.led_compensation = 51,
 	.wd_timeout = IWL_WATCHDOG_DISABLED,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
index dbcec7ce7863..b5d8274761d8 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/6000.c
@@ -72,6 +72,7 @@
 static const struct iwl_base_params iwl6000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x00,
 	.shadow_ram_support = true,
 	.led_compensation = 51,
@@ -84,6 +85,7 @@ static const struct iwl_base_params iwl6000_base_params = {
 static const struct iwl_base_params iwl6050_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x50,
 	.shadow_ram_support = true,
 	.led_compensation = 51,
@@ -96,6 +98,7 @@ static const struct iwl_base_params iwl6050_base_params = {
 static const struct iwl_base_params iwl6000_g2_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE,
 	.num_of_queues = IWLAGN_NUM_QUEUES,
+	.max_tfd_queue_size = 256,
 	.max_ll_items = OTP_MAX_LL_ITEMS_6x00,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
index 69bfa827e82a..a62c8346f13a 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/7000.c
@@ -123,6 +123,7 @@
 static const struct iwl_base_params iwl7000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_7000,
 	.num_of_queues = 31,
+	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
index 7262e973e0d6..c46fa712985b 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/8000.c
@@ -104,6 +104,7 @@
 static const struct iwl_base_params iwl8000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_8000,
 	.num_of_queues = 31,
+	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
index e20c30b29c03..db176954cf34 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/9000.c
@@ -95,6 +95,7 @@
 static const struct iwl_base_params iwl9000_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_FAMILY_9000,
 	.num_of_queues = 31,
+	.max_tfd_queue_size = 256,
 	.shadow_ram_support = true,
 	.led_compensation = 57,
 	.wd_timeout = IWL_LONG_WD_TIMEOUT,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index c28e550fe3db..72fbf97229b9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -177,6 +177,7 @@ static inline u8 num_of_ant(u8 mask)
  * @apmg_wake_up_wa: should the MAC access REQ be asserted when a command
  *	is in flight. This is due to a HW bug in 7260, 3160 and 7265.
  * @scd_chain_ext_wa: should the chain extension feature in SCD be disabled.
+ * @max_tfd_queue_size: max number of entries in tfd queue.
  */
 struct iwl_base_params {
 	unsigned int wd_timeout;
@@ -192,6 +193,7 @@ struct iwl_base_params {
 	   scd_chain_ext_wa:1;
 
 	u16 num_of_queues;	/* def: HW dependent */
+	u32 max_tfd_queue_size;	/* def: HW dependent */
 
 	u8 max_ll_items;
 	u8 led_compensation;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
index 11789ffb6512..f286fc7db7fd 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -18,9 +19,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110,
- * USA
+ * along with this program.
  *
  * The full GNU General Public License is included in this distribution
  * in the file called COPYING.
@@ -33,6 +32,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -643,10 +643,13 @@ struct iwl_rb_status {
 
 
 #define TFD_QUEUE_SIZE_MAX      (256)
+#define TFD_QUEUE_SIZE_MAX_GEN3 (65536)
 /* cb size is the exponent - 3 */
 #define TFD_QUEUE_CB_SIZE(x)	(ilog2(x) - 3)
 #define TFD_QUEUE_SIZE_BC_DUP	(64)
 #define TFD_QUEUE_BC_SIZE	(TFD_QUEUE_SIZE_MAX + TFD_QUEUE_SIZE_BC_DUP)
+#define TFD_QUEUE_BC_SIZE_GEN3	(TFD_QUEUE_SIZE_MAX_GEN3 + \
+				 TFD_QUEUE_SIZE_BC_DUP)
 #define IWL_TX_DMA_MASK        DMA_BIT_MASK(36)
 #define IWL_NUM_OF_TBS		20
 #define IWL_TFH_NUM_TBS		25
@@ -753,7 +756,7 @@ struct iwl_tfh_tfd {
  * For devices up to 22000:
  * @tfd_offset  0-12 - tx command byte count
  *		12-16 - station index
- * For 22000 and on:
+ * For 22000:
  * @tfd_offset  0-12 - tx command byte count
  *		12-13 - number of 64 byte chunks
  *		14-16 - reserved
@@ -762,4 +765,15 @@ struct iwlagn_scd_bc_tbl {
 	__le16 tfd_offset[TFD_QUEUE_BC_SIZE];
 } __packed;
 
+/**
+ * struct iwl_gen3_bc_tbl scheduler byte count table gen3
+ * For 22560 and on:
+ * @tfd_offset: 0-12 - tx command byte count
+ *		12-13 - number of 64 byte chunks
+ *		14-16 - reserved
+ */
+struct iwl_gen3_bc_tbl {
+	__le16 tfd_offset[TFD_QUEUE_BC_SIZE_GEN3];
+} __packed;
+
 #endif /* !__iwl_fh_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index b4e998747e04..3b86e50965f4 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -184,18 +184,18 @@ struct iwl_dma_ptr {
  * iwl_queue_inc_wrap - increment queue index, wrap back to beginning
  * @index -- current index
  */
-static inline int iwl_queue_inc_wrap(int index)
+static inline int iwl_queue_inc_wrap(struct iwl_trans *trans, int index)
 {
-	return ++index & (TFD_QUEUE_SIZE_MAX - 1);
+	return ++index & (trans->cfg->base_params->max_tfd_queue_size - 1);
 }
 
 /**
  * iwl_queue_dec_wrap - decrement queue index, wrap back to end
  * @index -- current index
  */
-static inline int iwl_queue_dec_wrap(int index)
+static inline int iwl_queue_dec_wrap(struct iwl_trans *trans, int index)
 {
-	return --index & (TFD_QUEUE_SIZE_MAX - 1);
+	return --index & (trans->cfg->base_params->max_tfd_queue_size - 1);
 }
 
 struct iwl_cmd_meta {
@@ -749,7 +749,7 @@ static inline void iwl_enable_fw_load_int(struct iwl_trans *trans)
 	}
 }
 
-static inline u8 iwl_pcie_get_cmd_index(const struct iwl_txq *q, u32 index)
+static inline u16 iwl_pcie_get_cmd_index(const struct iwl_txq *q, u32 index)
 {
 	return index & (q->n_window - 1);
 }
@@ -894,7 +894,7 @@ bool iwl_pcie_check_hw_rf_kill(struct iwl_trans *trans);
 void iwl_trans_pcie_handle_stop_rfkill(struct iwl_trans *trans,
 				       bool was_in_rfkill);
 void iwl_pcie_txq_free_tfd(struct iwl_trans *trans, struct iwl_txq *txq);
-int iwl_queue_space(const struct iwl_txq *q);
+int iwl_queue_space(struct iwl_trans *trans, const struct iwl_txq *q);
 void iwl_pcie_apm_stop_master(struct iwl_trans *trans);
 void iwl_pcie_conf_msix_hw(struct iwl_trans_pcie *trans_pcie);
 int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index efde21580166..9588b67110d1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2259,9 +2259,9 @@ void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
 		jiffies_to_msecs(txq->wd_timeout),
 		txq->read_ptr, txq->write_ptr,
 		iwl_read_prph(trans, SCD_QUEUE_RDPTR(txq_id)) &
-			(TFD_QUEUE_SIZE_MAX - 1),
+			(trans->cfg->base_params->max_tfd_queue_size - 1),
 		iwl_read_prph(trans, SCD_QUEUE_WRPTR(txq_id)) &
-			(TFD_QUEUE_SIZE_MAX - 1),
+			(trans->cfg->base_params->max_tfd_queue_size - 1),
 		iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
 }
 
@@ -3080,7 +3080,7 @@ static struct iwl_trans_dump_data
 			txcmd = (void *)((u8 *)txcmd->data + caplen);
 		}
 
-		ptr = iwl_queue_dec_wrap(ptr);
+		ptr = iwl_queue_dec_wrap(trans, ptr);
 	}
 	spin_unlock_bh(&cmdq->lock);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 5f05bcb26776..70dfa80b3d60 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -91,6 +91,8 @@ static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans_pcie *trans_pcie,
 					  int num_tbs)
 {
 	struct iwlagn_scd_bc_tbl *scd_bc_tbl = txq->bc_tbl.addr;
+	struct iwl_trans *trans = iwl_trans_pcie_get_trans(trans_pcie);
+	struct iwl_gen3_bc_tbl *scd_bc_tbl_gen3 = txq->bc_tbl.addr;
 	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
 	u8 filled_tfd_size, num_fetch_chunks;
 	u16 len = byte_cnt;
@@ -115,7 +117,10 @@ static void iwl_pcie_gen2_update_byte_tbl(struct iwl_trans_pcie *trans_pcie,
 	num_fetch_chunks = DIV_ROUND_UP(filled_tfd_size, 64) - 1;
 
 	bc_ent = cpu_to_le16(len | (num_fetch_chunks << 12));
-	scd_bc_tbl->tfd_offset[idx] = bc_ent;
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		scd_bc_tbl_gen3->tfd_offset[idx] = bc_ent;
+	else
+		scd_bc_tbl->tfd_offset[idx] = bc_ent;
 }
 
 /*
@@ -492,11 +497,11 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
-	if (iwl_queue_space(txq) < txq->high_mark) {
+	if (iwl_queue_space(trans, txq) < txq->high_mark) {
 		iwl_stop_queue(trans, txq);
 
 		/* don't put the packet on the ring, if there is no room */
-		if (unlikely(iwl_queue_space(txq) < 3)) {
+		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
 			struct iwl_device_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
@@ -542,7 +547,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Tell device the write index *just past* this latest filled TFD */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
 	/*
 	 * At this point the frame is "transmitted" successfully
@@ -654,7 +659,7 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 	tfd = iwl_pcie_get_tfd(trans, txq, txq->write_ptr);
 	memset(tfd, 0, sizeof(*tfd));
 
-	if (iwl_queue_space(txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
+	if (iwl_queue_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
 		spin_unlock_bh(&txq->lock);
 
 		IWL_ERR(trans, "No space in command queue\n");
@@ -791,7 +796,7 @@ static int iwl_pcie_gen2_enqueue_hcmd(struct iwl_trans *trans,
 		iwl_trans_ref(trans);
 	}
 	/* Increment and update queue's write index */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_gen2_txq_inc_wr_ptr(trans, txq);
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
 
@@ -958,7 +963,7 @@ void iwl_pcie_gen2_txq_unmap(struct iwl_trans *trans, int txq_id)
 			iwl_pcie_free_tso_page(trans_pcie, skb);
 		}
 		iwl_pcie_gen2_free_tfd(trans, txq);
-		txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr);
+		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
 
 		if (txq->read_ptr == txq->write_ptr) {
 			unsigned long flags;
@@ -1066,6 +1071,9 @@ int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
 	if (!txq)
 		return -ENOMEM;
 	ret = iwl_pcie_alloc_dma_ptr(trans, &txq->bc_tbl,
+				     (trans->cfg->device_family >=
+				      IWL_DEVICE_FAMILY_22560) ?
+				     sizeof(struct iwl_gen3_bc_tbl) :
 				     sizeof(struct iwlagn_scd_bc_tbl));
 	if (ret) {
 		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
@@ -1117,7 +1125,7 @@ int iwl_trans_pcie_dyn_txq_alloc(struct iwl_trans *trans,
 
 	txq->id = qid;
 	trans_pcie->txq[qid] = txq;
-	wr_ptr &= (TFD_QUEUE_SIZE_MAX - 1);
+	wr_ptr &= (trans->cfg->base_params->max_tfd_queue_size - 1);
 
 	/* Place first TFD at index corresponding to start sequence number */
 	txq->read_ptr = wr_ptr;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 11bd7ce2be8e..93f0d387688a 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -71,27 +71,28 @@
  *
  ***************************************************/
 
-int iwl_queue_space(const struct iwl_txq *q)
+int iwl_queue_space(struct iwl_trans *trans, const struct iwl_txq *q)
 {
 	unsigned int max;
 	unsigned int used;
 
 	/*
 	 * To avoid ambiguity between empty and completely full queues, there
-	 * should always be less than TFD_QUEUE_SIZE_MAX elements in the queue.
-	 * If q->n_window is smaller than TFD_QUEUE_SIZE_MAX, there is no need
+	 * should always be less than max_tfd_queue_size elements in the queue.
+	 * If q->n_window is smaller than max_tfd_queue_size, there is no need
 	 * to reserve any queue entries for this purpose.
 	 */
-	if (q->n_window < TFD_QUEUE_SIZE_MAX)
+	if (q->n_window < trans->cfg->base_params->max_tfd_queue_size)
 		max = q->n_window;
 	else
-		max = TFD_QUEUE_SIZE_MAX - 1;
+		max = trans->cfg->base_params->max_tfd_queue_size - 1;
 
 	/*
-	 * TFD_QUEUE_SIZE_MAX is a power of 2, so the following is equivalent to
-	 * modulo by TFD_QUEUE_SIZE_MAX and is well defined.
+	 * max_tfd_queue_size is a power of 2, so the following is equivalent to
+	 * modulo by max_tfd_queue_size and is well defined.
 	 */
-	used = (q->write_ptr - q->read_ptr) & (TFD_QUEUE_SIZE_MAX - 1);
+	used = (q->write_ptr - q->read_ptr) &
+		(trans->cfg->base_params->max_tfd_queue_size - 1);
 
 	if (WARN_ON(used > max))
 		return 0;
@@ -489,7 +490,8 @@ int iwl_pcie_txq_alloc(struct iwl_trans *trans, struct iwl_txq *txq,
 		       int slots_num, bool cmd_queue)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	size_t tfd_sz = trans_pcie->tfd_size * TFD_QUEUE_SIZE_MAX;
+	size_t tfd_sz = trans_pcie->tfd_size *
+		trans->cfg->base_params->max_tfd_queue_size;
 	size_t tb0_buf_sz;
 	int i;
 
@@ -555,12 +557,16 @@ int iwl_pcie_txq_init(struct iwl_trans *trans, struct iwl_txq *txq,
 		      int slots_num, bool cmd_queue)
 {
 	int ret;
+	u32 tfd_queue_max_size = trans->cfg->base_params->max_tfd_queue_size;
 
 	txq->need_update = false;
 
-	/* TFD_QUEUE_SIZE_MAX must be power-of-two size, otherwise
+	/* max_tfd_queue_size must be power-of-two size, otherwise
 	 * iwl_queue_inc_wrap and iwl_queue_dec_wrap are broken. */
-	BUILD_BUG_ON(TFD_QUEUE_SIZE_MAX & (TFD_QUEUE_SIZE_MAX - 1));
+	if (WARN_ONCE(tfd_queue_max_size & (tfd_queue_max_size - 1),
+		      "Max tfd queue size must be a power of two, but is %d",
+		      tfd_queue_max_size))
+		return -EINVAL;
 
 	/* Initialize queue's high/low-water marks, and head/tail indexes */
 	ret = iwl_queue_init(txq, slots_num);
@@ -637,7 +643,7 @@ static void iwl_pcie_txq_unmap(struct iwl_trans *trans, int txq_id)
 			iwl_pcie_free_tso_page(trans_pcie, skb);
 		}
 		iwl_pcie_txq_free_tfd(trans, txq);
-		txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr);
+		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
 
 		if (txq->read_ptr == txq->write_ptr) {
 			unsigned long flags;
@@ -696,7 +702,8 @@ static void iwl_pcie_txq_free(struct iwl_trans *trans, int txq_id)
 	/* De-alloc circular buffer of TFDs */
 	if (txq->tfds) {
 		dma_free_coherent(dev,
-				  trans_pcie->tfd_size * TFD_QUEUE_SIZE_MAX,
+				  trans_pcie->tfd_size *
+				  trans->cfg->base_params->max_tfd_queue_size,
 				  txq->tfds, txq->dma_addr);
 		txq->dma_addr = 0;
 		txq->tfds = NULL;
@@ -916,9 +923,11 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	int ret;
 	int txq_id, slots_num;
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	u16 bc_tbls_size = trans->cfg->base_params->num_of_queues;
 
-	u16 scd_bc_tbls_size = trans->cfg->base_params->num_of_queues *
-			sizeof(struct iwlagn_scd_bc_tbl);
+	bc_tbls_size *= (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) ?
+		sizeof(struct iwl_gen3_bc_tbl) :
+		sizeof(struct iwlagn_scd_bc_tbl);
 
 	/*It is not allowed to alloc twice, so warn when this happens.
 	 * We cannot rely on the previous allocation, so free and fail */
@@ -928,7 +937,7 @@ static int iwl_pcie_tx_alloc(struct iwl_trans *trans)
 	}
 
 	ret = iwl_pcie_alloc_dma_ptr(trans, &trans_pcie->scd_bc_tbls,
-				   scd_bc_tbls_size);
+				     bc_tbls_size);
 	if (ret) {
 		IWL_ERR(trans, "Scheduler BC Table allocation failed\n");
 		goto error;
@@ -1064,7 +1073,8 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_txq *txq = trans_pcie->txq[txq_id];
-	int tfd_num = ssn & (TFD_QUEUE_SIZE_MAX - 1);
+	int tfd_num = iwl_pcie_get_cmd_index(txq, ssn);
+	int read_ptr = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
 	int last_to_free;
 
 	/* This function is not meant to release cmd queue*/
@@ -1079,7 +1089,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 		goto out;
 	}
 
-	if (txq->read_ptr == tfd_num)
+	if (read_ptr == tfd_num)
 		goto out;
 
 	IWL_DEBUG_TX_REPLY(trans, "[Q %d] %d -> %d (%d)\n",
@@ -1087,12 +1097,13 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	/*Since we free until index _not_ inclusive, the one before index is
 	 * the last we will free. This one must be used */
-	last_to_free = iwl_queue_dec_wrap(tfd_num);
+	last_to_free = iwl_queue_dec_wrap(trans, tfd_num);
 
 	if (!iwl_queue_used(txq, last_to_free)) {
 		IWL_ERR(trans,
 			"%s: Read index for DMA queue txq id (%d), last_to_free %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, last_to_free, TFD_QUEUE_SIZE_MAX,
+			__func__, txq_id, last_to_free,
+			trans->cfg->base_params->max_tfd_queue_size,
 			txq->write_ptr, txq->read_ptr);
 		goto out;
 	}
@@ -1101,10 +1112,10 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 		goto out;
 
 	for (;
-	     txq->read_ptr != tfd_num;
-	     txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr)) {
-		int idx = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
-		struct sk_buff *skb = txq->entries[idx].skb;
+	     read_ptr != tfd_num;
+	     txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr),
+	     read_ptr = iwl_pcie_get_cmd_index(txq, txq->read_ptr)) {
+		struct sk_buff *skb = txq->entries[read_ptr].skb;
 
 		if (WARN_ON_ONCE(!skb))
 			continue;
@@ -1113,7 +1124,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 		__skb_queue_tail(skbs, skb);
 
-		txq->entries[idx].skb = NULL;
+		txq->entries[read_ptr].skb = NULL;
 
 		if (!trans->cfg->use_tfh)
 			iwl_pcie_txq_inval_byte_cnt_tbl(trans, txq);
@@ -1123,7 +1134,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 
 	iwl_pcie_txq_progress(txq);
 
-	if (iwl_queue_space(txq) > txq->low_mark &&
+	if (iwl_queue_space(trans, txq) > txq->low_mark &&
 	    test_bit(txq_id, trans_pcie->queue_stopped)) {
 		struct sk_buff_head overflow_skbs;
 
@@ -1155,7 +1166,7 @@ void iwl_trans_pcie_reclaim(struct iwl_trans *trans, int txq_id, int ssn,
 		}
 		spin_lock_bh(&txq->lock);
 
-		if (iwl_queue_space(txq) > txq->low_mark)
+		if (iwl_queue_space(trans, txq) > txq->low_mark)
 			iwl_wake_queue(trans, txq);
 	}
 
@@ -1232,17 +1243,19 @@ static void iwl_pcie_cmdq_reclaim(struct iwl_trans *trans, int txq_id, int idx)
 	idx = iwl_pcie_get_cmd_index(txq, idx);
 	r = iwl_pcie_get_cmd_index(txq, txq->read_ptr);
 
-	if ((idx >= TFD_QUEUE_SIZE_MAX) || (!iwl_queue_used(txq, idx))) {
+	if (idx >= trans->cfg->base_params->max_tfd_queue_size ||
+	    (!iwl_queue_used(txq, idx))) {
 		IWL_ERR(trans,
 			"%s: Read index for DMA queue txq id (%d), index %d is out of range [0-%d] %d %d.\n",
-			__func__, txq_id, idx, TFD_QUEUE_SIZE_MAX,
+			__func__, txq_id, idx,
+			trans->cfg->base_params->max_tfd_queue_size,
 			txq->write_ptr, txq->read_ptr);
 		return;
 	}
 
-	for (idx = iwl_queue_inc_wrap(idx); r != idx;
-	     r = iwl_queue_inc_wrap(r)) {
-		txq->read_ptr = iwl_queue_inc_wrap(txq->read_ptr);
+	for (idx = iwl_queue_inc_wrap(trans, idx); r != idx;
+	     r = iwl_queue_inc_wrap(trans, r)) {
+		txq->read_ptr = iwl_queue_inc_wrap(trans, txq->read_ptr);
 
 		if (nfreed++ > 0) {
 			IWL_ERR(trans, "HCMD skipped: index (%d) %d %d\n",
@@ -1560,7 +1573,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 
 	spin_lock_bh(&txq->lock);
 
-	if (iwl_queue_space(txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
+	if (iwl_queue_space(trans, txq) < ((cmd->flags & CMD_ASYNC) ? 2 : 1)) {
 		spin_unlock_bh(&txq->lock);
 
 		IWL_ERR(trans, "No space in command queue\n");
@@ -1716,7 +1729,7 @@ static int iwl_pcie_enqueue_hcmd(struct iwl_trans *trans,
 	}
 
 	/* Increment and update queue's write index */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
 	spin_unlock_irqrestore(&trans_pcie->reg_lock, flags);
@@ -2316,11 +2329,11 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
-	if (iwl_queue_space(txq) < txq->high_mark) {
+	if (iwl_queue_space(trans, txq) < txq->high_mark) {
 		iwl_stop_queue(trans, txq);
 
 		/* don't put the packet on the ring, if there is no room */
-		if (unlikely(iwl_queue_space(txq) < 3)) {
+		if (unlikely(iwl_queue_space(trans, txq) < 3)) {
 			struct iwl_device_cmd **dev_cmd_ptr;
 
 			dev_cmd_ptr = (void *)((u8 *)skb->cb +
@@ -2449,7 +2462,7 @@ int iwl_trans_pcie_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Tell device the write index *just past* this latest filled TFD */
-	txq->write_ptr = iwl_queue_inc_wrap(txq->write_ptr);
+	txq->write_ptr = iwl_queue_inc_wrap(trans, txq->write_ptr);
 	if (!wait_write_ptr)
 		iwl_pcie_txq_inc_wr_ptr(trans, txq);
 
-- 
cgit v1.2.3


From a0ec0169b7a9e0e6050e1699276801dee8c6ca84 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 4 Feb 2018 15:46:17 +0200
Subject: iwlwifi: support new tx api

22560 devices use a new tx cmd api. Update the code to use
the new api.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/commands.h   |  3 +-
 drivers/net/wireless/intel/iwlwifi/fw/api/tx.h     | 25 +++++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/tx.c        | 48 +++++++++++++++-------
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c  | 26 ++++++++++--
 4 files changed, 83 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index f285bacc8726..d71a6a837ec5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -193,7 +193,8 @@ enum iwl_legacy_cmds {
 	FW_GET_ITEM_CMD = 0x1a,
 
 	/**
-	 * @TX_CMD: uses &struct iwl_tx_cmd or &struct iwl_tx_cmd_gen2,
+	 * @TX_CMD: uses &struct iwl_tx_cmd or &struct iwl_tx_cmd_gen2 or
+	 *	&struct iwl_tx_cmd_gen3,
 	 *	response in &struct iwl_mvm_tx_resp or
 	 *	&struct iwl_mvm_tx_resp_v3
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
index a2a40b515a3c..514b86123d3d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/tx.h
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -28,6 +29,7 @@
  *
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -320,6 +322,29 @@ struct iwl_tx_cmd_gen2 {
 	struct ieee80211_hdr hdr[0];
 } __packed; /* TX_CMD_API_S_VER_7 */
 
+/**
+ * struct iwl_tx_cmd_gen3 - TX command struct to FW for 22560 devices
+ * ( TX_CMD = 0x1c )
+ * @len: in bytes of the payload, see below for details
+ * @flags: combination of &enum iwl_tx_cmd_flags
+ * @offload_assist: TX offload configuration
+ * @dram_info: FW internal DRAM storage
+ * @rate_n_flags: rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is
+ *	cleared. Combination of RATE_MCS_*
+ * @ttl: time to live - packet lifetime limit. The FW should drop if
+ *	passed.
+ * @hdr: 802.11 header
+ */
+struct iwl_tx_cmd_gen3 {
+	__le16 len;
+	__le16 flags;
+	__le32 offload_assist;
+	struct iwl_dram_sec_info dram_info;
+	__le32 rate_n_flags;
+	__le64 ttl;
+	struct ieee80211_hdr hdr[0];
+} __packed; /* TX_CMD_API_S_VER_8 */
+
 /*
  * TX response related data
  */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
index cf2591f2ac23..ff193dca2020 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tx.c
@@ -484,13 +484,15 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 
 	/* Make sure we zero enough of dev_cmd */
 	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) > sizeof(*tx_cmd));
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen3) > sizeof(*tx_cmd));
 
 	memset(dev_cmd, 0, sizeof(dev_cmd->hdr) + sizeof(*tx_cmd));
 	dev_cmd->hdr.cmd = TX_CMD;
 
 	if (iwl_mvm_has_new_tx_api(mvm)) {
-		struct iwl_tx_cmd_gen2 *cmd = (void *)dev_cmd->payload;
 		u16 offload_assist = 0;
+		u32 rate_n_flags = 0;
+		u16 flags = 0;
 
 		if (ieee80211_is_data_qos(hdr->frame_control)) {
 			u8 *qc = ieee80211_get_qos_ctl(hdr);
@@ -507,25 +509,43 @@ iwl_mvm_set_tx_params(struct iwl_mvm *mvm, struct sk_buff *skb,
 		    !(offload_assist & BIT(TX_CMD_OFFLD_AMSDU)))
 			offload_assist |= BIT(TX_CMD_OFFLD_PAD);
 
-		cmd->offload_assist |= cpu_to_le16(offload_assist);
+		if (!info->control.hw_key)
+			flags |= IWL_TX_FLAGS_ENCRYPT_DIS;
 
-		/* Total # bytes to be transmitted */
-		cmd->len = cpu_to_le16((u16)skb->len);
+		/* For data packets rate info comes from the fw */
+		if (!(ieee80211_is_data(hdr->frame_control) && sta)) {
+			flags |= IWL_TX_FLAGS_CMD_RATE;
+			rate_n_flags = iwl_mvm_get_tx_rate(mvm, info, sta);
+		}
 
-		/* Copy MAC header from skb into command buffer */
-		memcpy(cmd->hdr, hdr, hdrlen);
+		if (mvm->trans->cfg->device_family >=
+		    IWL_DEVICE_FAMILY_22560) {
+			struct iwl_tx_cmd_gen3 *cmd = (void *)dev_cmd->payload;
 
-		if (!info->control.hw_key)
-			cmd->flags |= cpu_to_le32(IWL_TX_FLAGS_ENCRYPT_DIS);
+			cmd->offload_assist |= cpu_to_le32(offload_assist);
 
-		/* For data packets rate info comes from the fw */
-		if (ieee80211_is_data(hdr->frame_control) && sta)
-			goto out;
+			/* Total # bytes to be transmitted */
+			cmd->len = cpu_to_le16((u16)skb->len);
 
-		cmd->flags |= cpu_to_le32(IWL_TX_FLAGS_CMD_RATE);
-		cmd->rate_n_flags =
-			cpu_to_le32(iwl_mvm_get_tx_rate(mvm, info, sta));
+			/* Copy MAC header from skb into command buffer */
+			memcpy(cmd->hdr, hdr, hdrlen);
 
+			cmd->flags = cpu_to_le16(flags);
+			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+		} else {
+			struct iwl_tx_cmd_gen2 *cmd = (void *)dev_cmd->payload;
+
+			cmd->offload_assist |= cpu_to_le16(offload_assist);
+
+			/* Total # bytes to be transmitted */
+			cmd->len = cpu_to_le16((u16)skb->len);
+
+			/* Copy MAC header from skb into command buffer */
+			memcpy(cmd->hdr, hdr, hdrlen);
+
+			cmd->flags = cpu_to_le32(flags);
+			cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+		}
 		goto out;
 	}
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 70dfa80b3d60..e3ae7f91206b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -402,8 +402,14 @@ struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
 	 * (This calculation modifies the TX command, so do it before the
 	 * setup of the first TB)
 	 */
-	len = sizeof(struct iwl_tx_cmd_gen2) + sizeof(struct iwl_cmd_header) +
-	      ieee80211_hdrlen(hdr->frame_control) - IWL_FIRST_TB_SIZE;
+	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
+		len = sizeof(struct iwl_tx_cmd_gen2);
+	else
+		len = sizeof(struct iwl_tx_cmd_gen3);
+
+	len += sizeof(struct iwl_cmd_header) +
+		ieee80211_hdrlen(hdr->frame_control) -
+		IWL_FIRST_TB_SIZE;
 
 	/* do not align A-MSDU to dword as the subframe header aligns it */
 	if (amsdu)
@@ -480,9 +486,9 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 			   struct iwl_device_cmd *dev_cmd, int txq_id)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
-	struct iwl_tx_cmd_gen2 *tx_cmd = (void *)dev_cmd->payload;
 	struct iwl_cmd_meta *out_meta;
 	struct iwl_txq *txq = trans_pcie->txq[txq_id];
+	u16 cmd_len;
 	int idx;
 	void *tfd;
 
@@ -497,6 +503,18 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 
 	spin_lock(&txq->lock);
 
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		struct iwl_tx_cmd_gen3 *tx_cmd_gen3 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen3->len);
+	} else {
+		struct iwl_tx_cmd_gen2 *tx_cmd_gen2 =
+			(void *)dev_cmd->payload;
+
+		cmd_len = le16_to_cpu(tx_cmd_gen2->len);
+	}
+
 	if (iwl_queue_space(trans, txq) < txq->high_mark) {
 		iwl_stop_queue(trans, txq);
 
@@ -535,7 +553,7 @@ int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 	}
 
 	/* Set up entry for this TFD in Tx byte-count array */
-	iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, le16_to_cpu(tx_cmd->len),
+	iwl_pcie_gen2_update_byte_tbl(trans_pcie, txq, cmd_len,
 				      iwl_pcie_gen2_get_num_tbs(trans, tfd));
 
 	/* start timer if queue currently empty */
-- 
cgit v1.2.3


From cf495496b688cd4672bf87aaaf0c833bda8825f3 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 4 Feb 2018 16:38:10 +0200
Subject: iwlwifi: introduce new rx structures used by 22560 RFH

22560 devices RFH uses different structures, which act similar
to the legacy rxq management lists - free and used list.

The iwl_rx_transfer_desc struct is part of the free list,
and consists of pointers to the empty rb's the driver wants to
pass to the fw.

The iwl_rx_completion_desc struct is part of the used list,
and consists of pointers to the buffer the fw filled up
with new rx, both commands and data, for the host.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h | 100 +++++++++++++++++++++
 1 file changed, 100 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 3b86e50965f4..11687dc4039d 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -99,6 +99,106 @@ struct isr_statistics {
 	u32 unhandled;
 };
 
+#define IWL_CD_STTS_OPTIMIZED_POS	0
+#define IWL_CD_STTS_OPTIMIZED_MSK	0x01
+#define IWL_CD_STTS_TRANSFER_STATUS_POS	1
+#define IWL_CD_STTS_TRANSFER_STATUS_MSK	0x0E
+#define IWL_CD_STTS_WIFI_STATUS_POS	4
+#define IWL_CD_STTS_WIFI_STATUS_MSK	0xF0
+
+/**
+ * enum iwl_completion_desc_transfer_status -  transfer status (bits 1-3)
+ * @IWL_CD_STTS_END_TRANSFER: successful transfer complete.
+ *	In sniffer mode, when split is used, set in last CD completion. (RX)
+ * @IWL_CD_STTS_OVERFLOW: In sniffer mode, when using split - used for
+ *	all CD completion. (RX)
+ * @IWL_CD_STTS_ABORTED: CR abort / close flow. (RX)
+ */
+enum iwl_completion_desc_transfer_status {
+	IWL_CD_STTS_UNUSED,
+	IWL_CD_STTS_UNUSED_2,
+	IWL_CD_STTS_END_TRANSFER,
+	IWL_CD_STTS_OVERFLOW,
+	IWL_CD_STTS_ABORTED,
+	IWL_CD_STTS_ERROR,
+};
+
+/**
+ * enum iwl_completion_desc_wifi_status - wifi status (bits 4-7)
+ * @IWL_CD_STTS_VALID: the packet is valid (RX)
+ * @IWL_CD_STTS_FCS_ERR: frame check sequence error (RX)
+ * @IWL_CD_STTS_SEC_KEY_ERR: error handling the security key of rx (RX)
+ * @IWL_CD_STTS_DECRYPTION_ERR: error decrypting the frame (RX)
+ * @IWL_CD_STTS_DUP: duplicate packet (RX)
+ * @IWL_CD_STTS_ICV_MIC_ERR: MIC error (RX)
+ * @IWL_CD_STTS_INTERNAL_SNAP_ERR: problems removing the snap (RX)
+ * @IWL_CD_STTS_SEC_PORT_FAIL: security port fail (RX)
+ * @IWL_CD_STTS_BA_OLD_SN: block ack received old SN (RX)
+ * @IWL_CD_STTS_QOS_NULL: QoS null packet (RX)
+ * @IWL_CD_STTS_MAC_HDR_ERR: MAC header conversion error (RX)
+ * @IWL_CD_STTS_MAX_RETRANS: reached max number of retransmissions (TX)
+ * @IWL_CD_STTS_EX_LIFETIME: exceeded lifetime (TX)
+ * @IWL_CD_STTS_NOT_USED: completed but not used (RX)
+ * @IWL_CD_STTS_REPLAY_ERR: pn check failed, replay error (RX)
+ */
+enum iwl_completion_desc_wifi_status {
+	IWL_CD_STTS_VALID,
+	IWL_CD_STTS_FCS_ERR,
+	IWL_CD_STTS_SEC_KEY_ERR,
+	IWL_CD_STTS_DECRYPTION_ERR,
+	IWL_CD_STTS_DUP,
+	IWL_CD_STTS_ICV_MIC_ERR,
+	IWL_CD_STTS_INTERNAL_SNAP_ERR,
+	IWL_CD_STTS_SEC_PORT_FAIL,
+	IWL_CD_STTS_BA_OLD_SN,
+	IWL_CD_STTS_QOS_NULL,
+	IWL_CD_STTS_MAC_HDR_ERR,
+	IWL_CD_STTS_MAX_RETRANS,
+	IWL_CD_STTS_EX_LIFETIME,
+	IWL_CD_STTS_NOT_USED,
+	IWL_CD_STTS_REPLAY_ERR,
+};
+
+#define IWL_RX_TD_TYPE		0xff000000
+#define IWL_RX_TD_SIZE		0x00ffffff
+
+/**
+ * struct iwl_rx_transfer_desc - transfer descriptor
+ * @type_n_size: buffer type (bit 0: external buff valid,
+ *	bit 1: optional footer valid, bit 2-7: reserved)
+ *	and buffer size
+ * @addr: ptr to free buffer start address
+ * @rbid: unique tag of the buffer
+ * @reserved: reserved
+ */
+struct iwl_rx_transfer_desc {
+	__le32 type_n_size;
+	__le64 addr;
+	__le16 rbid;
+	__le16 reserved;
+} __packed;
+
+#define IWL_RX_CD_SIZE		0xffffff00
+
+/**
+ * struct iwl_rx_completion_desc - completion descriptor
+ * @type: buffer type (bit 0: external buff valid,
+ *	bit 1: optional footer valid, bit 2-7: reserved)
+ * @status: status of the completion
+ * @reserved1: reserved
+ * @rbid: unique tag of the received buffer
+ * @size: buffer size, masked by IWL_RX_CD_SIZE
+ * @reserved2: reserved
+ */
+struct iwl_rx_completion_desc {
+	u8 type;
+	u8 status;
+	__le16 reserved1;
+	__le16 rbid;
+	__le32 size;
+	u8 reserved2[22];
+} __packed;
+
 /**
  * struct iwl_rxq - Rx queue
  * @id: queue index
-- 
cgit v1.2.3


From d0158235f44e1e8a7db89380e77c3520386267b7 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 4 Feb 2018 17:04:31 +0200
Subject: iwlwifi: update registers changed for 22560 devices

In 22560 devices the firmware will do all the hw configurations,
but that's not ready yet.
Update the correct registers in the driver until the FW is ready
and does it by itself.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-fh.h  | 6 ++++--
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 7 ++++++-
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
index f286fc7db7fd..df0e9ffff706 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-fh.h
@@ -434,13 +434,15 @@ static inline unsigned int FH_MEM_CBBC_QUEUE(struct iwl_trans *trans,
  * RXF to DRAM.
  * Once the RXF-to-DRAM DMA is active, this flag is immediately turned off.
  */
-#define RFH_GEN_STATUS 0xA09808
+#define RFH_GEN_STATUS		0xA09808
+#define RFH_GEN_STATUS_GEN3	0xA07824
 #define RBD_FETCH_IDLE	BIT(29)
 #define SRAM_DMA_IDLE	BIT(30)
 #define RXF_DMA_IDLE	BIT(31)
 
 /* DMA configuration */
-#define RFH_RXF_DMA_CFG 0xA09820
+#define RFH_RXF_DMA_CFG		0xA09820
+#define RFH_RXF_DMA_CFG_GEN3	0xA07880
 /* RB size */
 #define RFH_RXF_DMA_RB_SIZE_MASK (0x000F0000) /* bits 16-19 */
 #define RFH_RXF_DMA_RB_SIZE_POS 16
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 707242f1ff0b..8cd0c3dac0ab 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -167,7 +167,12 @@ static inline __le32 iwl_pcie_dma_addr2rbd_ptr(dma_addr_t dma_addr)
  */
 int iwl_pcie_rx_stop(struct iwl_trans *trans)
 {
-	if (trans->cfg->mq_rx_supported) {
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		/* TODO: remove this for 22560 once fw does it */
+		iwl_write_prph(trans, RFH_RXF_DMA_CFG_GEN3, 0);
+		return iwl_poll_prph_bit(trans, RFH_GEN_STATUS_GEN3,
+					 RXF_DMA_IDLE, RXF_DMA_IDLE, 1000);
+	} else if (trans->cfg->mq_rx_supported) {
 		iwl_write_prph(trans, RFH_RXF_DMA_CFG, 0);
 		return iwl_poll_prph_bit(trans, RFH_GEN_STATUS,
 					   RXF_DMA_IDLE, RXF_DMA_IDLE, 1000);
-- 
cgit v1.2.3


From 1a4968d1230c9233f50a89abb3b32d94f81146d0 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 4 Feb 2018 17:41:51 +0200
Subject: iwlwifi: pcie: support 2k rx buffers

The smallest rb size supported today is 4k rx buffers.
22560 devices use 2k rxb's, so allow using 2k buffers.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c          | 3 ++-
 drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c | 8 ++++----
 drivers/net/wireless/intel/iwlwifi/iwl-modparams.h    | 8 +++++---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c    | 7 +++++++
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h        | 2 ++
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c          | 5 ++++-
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c          | 3 +++
 7 files changed, 27 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 650214ff0a1c..38fcc6a9d421 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1787,7 +1787,8 @@ MODULE_PARM_DESC(11n_disable,
 	"disable 11n functionality, bitmap: 1: full, 2: disable agg TX, 4: disable agg RX, 8 enable agg TX");
 module_param_named(amsdu_size, iwlwifi_mod_params.amsdu_size, int, 0444);
 MODULE_PARM_DESC(amsdu_size,
-		 "amsdu size 0: 12K for multi Rx queue devices, 4K for other devices 1:4K 2:8K 3:12K (default 0)");
+		 "amsdu size 0: 12K for multi Rx queue devices, 2K for 22560 devices, "
+		 "4K for other devices 1:4K 2:8K 3:12K 4: 2K (default 0)");
 module_param_named(fw_restart, iwlwifi_mod_params.fw_restart, bool, 0444);
 MODULE_PARM_DESC(fw_restart, "restart firmware in case of error (default true)");
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
index 777f5df8a0c6..a4c96215933b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-eeprom-parse.c
@@ -7,6 +7,7 @@
  *
  * Copyright(c) 2008 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -18,9 +19,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110,
- * USA
+ * along with this program;
  *
  * The full GNU General Public License is included in this distribution
  * in the file called COPYING.
@@ -33,6 +32,7 @@
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2015 Intel Mobile Communications GmbH
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -767,7 +767,7 @@ void iwl_init_ht_hw_capab(const struct iwl_cfg *cfg,
 		ht_info->cap |= IEEE80211_HT_CAP_LDPC_CODING;
 
 	if ((cfg->mq_rx_supported &&
-	     iwlwifi_mod_params.amsdu_size != IWL_AMSDU_4K) ||
+	     iwlwifi_mod_params.amsdu_size == IWL_AMSDU_DEF) ||
 	     iwlwifi_mod_params.amsdu_size >= IWL_AMSDU_8K)
 		ht_info->cap |= IEEE80211_HT_CAP_MAX_AMSDU;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
index 5dd848cb9d20..97072cf75bca 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-modparams.h
@@ -6,6 +6,7 @@
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2007 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -17,9 +18,7 @@
  * General Public License for more details.
  *
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110,
- * USA
+ * along with this program;
  *
  * The full GNU General Public License is included in this distribution
  * in the file called COPYING.
@@ -31,6 +30,7 @@
  * BSD LICENSE
  *
  * Copyright(c) 2005 - 2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -90,6 +90,8 @@ enum iwl_amsdu_size {
 	IWL_AMSDU_4K = 1,
 	IWL_AMSDU_8K = 2,
 	IWL_AMSDU_12K = 3,
+	/* Add 2K at the end to avoid breaking current API */
+	IWL_AMSDU_2K = 4,
 };
 
 enum iwl_uapsd_disable {
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 7bb0360d6807..b4c3a957c102 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -430,6 +430,13 @@ static void iwl_init_vht_hw_capab(const struct iwl_cfg *cfg,
 		else
 			vht_cap->cap |= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895;
 		break;
+	case IWL_AMSDU_2K:
+		if (cfg->mq_rx_supported)
+			vht_cap->cap |=
+				IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454;
+		else
+			WARN(1, "RB size of 2K is not supported by this device\n");
+		break;
 	case IWL_AMSDU_4K:
 		vht_cap->cap |= IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895;
 		break;
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 1b9c627ee34d..4229992073b6 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -350,6 +350,8 @@ static inline int
 iwl_trans_get_rb_size_order(enum iwl_amsdu_size rb_size)
 {
 	switch (rb_size) {
+	case IWL_AMSDU_2K:
+		return get_order(2 * 1024);
 	case IWL_AMSDU_4K:
 		return get_order(4 * 1024);
 	case IWL_AMSDU_8K:
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 5d9b9306ea1c..d966262e0819 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -704,7 +704,10 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	}
 
 	/* the hardware splits the A-MSDU */
-	if (mvm->cfg->mq_rx_supported)
+	if (mvm->trans->cfg->device_family >=
+	    IWL_DEVICE_FAMILY_22560)
+		trans_cfg.rx_buf_size = IWL_AMSDU_2K;
+	else if (mvm->cfg->mq_rx_supported)
 		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
 
 	trans->wide_cmd_header = true;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 8cd0c3dac0ab..f509e55f27b1 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -858,6 +858,9 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans)
 	int i;
 
 	switch (trans_pcie->rx_buf_size) {
+	case IWL_AMSDU_2K:
+		rb_size = RFH_RXF_DMA_RB_SIZE_2K;
+		break;
 	case IWL_AMSDU_4K:
 		rb_size = RFH_RXF_DMA_RB_SIZE_4K;
 		break;
-- 
cgit v1.2.3


From 8a1ccfbc9e0256baafbbce85ccdb72ec89af2aab Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Fri, 20 Jul 2018 14:41:53 -0700
Subject: arm64: Add stack information to on_accessible_stack

In preparation for enabling the stackleak plugin on arm64,
we need a way to get the bounds of the current stack. Extend
on_accessible_stack to get this information.

Acked-by: Alexander Popov <alex.popov@linux.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Laura Abbott <labbott@redhat.com>
[will: folded in fix for allmodconfig build breakage w/ sdei]
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/sdei.h       |  9 +++--
 arch/arm64/include/asm/stacktrace.h | 73 +++++++++++++++++++++++++++++++------
 arch/arm64/kernel/ptrace.c          |  2 +-
 arch/arm64/kernel/sdei.c            | 51 +++++++++++++++++++++-----
 arch/arm64/kernel/stacktrace.c      |  2 +-
 5 files changed, 111 insertions(+), 26 deletions(-)

diff --git a/arch/arm64/include/asm/sdei.h b/arch/arm64/include/asm/sdei.h
index e073e6886685..ffe47d766c25 100644
--- a/arch/arm64/include/asm/sdei.h
+++ b/arch/arm64/include/asm/sdei.h
@@ -40,15 +40,18 @@ asmlinkage unsigned long __sdei_handler(struct pt_regs *regs,
 unsigned long sdei_arch_get_entry_point(int conduit);
 #define sdei_arch_get_entry_point(x)	sdei_arch_get_entry_point(x)
 
-bool _on_sdei_stack(unsigned long sp);
-static inline bool on_sdei_stack(unsigned long sp)
+struct stack_info;
+
+bool _on_sdei_stack(unsigned long sp, struct stack_info *info);
+static inline bool on_sdei_stack(unsigned long sp,
+				struct stack_info *info)
 {
 	if (!IS_ENABLED(CONFIG_VMAP_STACK))
 		return false;
 	if (!IS_ENABLED(CONFIG_ARM_SDE_INTERFACE))
 		return false;
 	if (in_nmi())
-		return _on_sdei_stack(sp);
+		return _on_sdei_stack(sp, info);
 
 	return false;
 }
diff --git a/arch/arm64/include/asm/stacktrace.h b/arch/arm64/include/asm/stacktrace.h
index 902f9edacbea..e86737b7c924 100644
--- a/arch/arm64/include/asm/stacktrace.h
+++ b/arch/arm64/include/asm/stacktrace.h
@@ -32,6 +32,21 @@ struct stackframe {
 #endif
 };
 
+enum stack_type {
+	STACK_TYPE_UNKNOWN,
+	STACK_TYPE_TASK,
+	STACK_TYPE_IRQ,
+	STACK_TYPE_OVERFLOW,
+	STACK_TYPE_SDEI_NORMAL,
+	STACK_TYPE_SDEI_CRITICAL,
+};
+
+struct stack_info {
+	unsigned long low;
+	unsigned long high;
+	enum stack_type type;
+};
+
 extern int unwind_frame(struct task_struct *tsk, struct stackframe *frame);
 extern void walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 			    int (*fn)(struct stackframe *, void *), void *data);
@@ -39,7 +54,8 @@ extern void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk);
 
 DECLARE_PER_CPU(unsigned long *, irq_stack_ptr);
 
-static inline bool on_irq_stack(unsigned long sp)
+static inline bool on_irq_stack(unsigned long sp,
+				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(irq_stack_ptr);
 	unsigned long high = low + IRQ_STACK_SIZE;
@@ -47,46 +63,79 @@ static inline bool on_irq_stack(unsigned long sp)
 	if (!low)
 		return false;
 
-	return (low <= sp && sp < high);
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_IRQ;
+	}
+
+	return true;
 }
 
-static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp)
+static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp,
+				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)task_stack_page(tsk);
 	unsigned long high = low + THREAD_SIZE;
 
-	return (low <= sp && sp < high);
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_TASK;
+	}
+
+	return true;
 }
 
 #ifdef CONFIG_VMAP_STACK
 DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
 
-static inline bool on_overflow_stack(unsigned long sp)
+static inline bool on_overflow_stack(unsigned long sp,
+				struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
 	unsigned long high = low + OVERFLOW_STACK_SIZE;
 
-	return (low <= sp && sp < high);
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_OVERFLOW;
+	}
+
+	return true;
 }
 #else
-static inline bool on_overflow_stack(unsigned long sp) { return false; }
+static inline bool on_overflow_stack(unsigned long sp,
+			struct stack_info *info) { return false; }
 #endif
 
+
 /*
  * We can only safely access per-cpu stacks from current in a non-preemptible
  * context.
  */
-static inline bool on_accessible_stack(struct task_struct *tsk, unsigned long sp)
+static inline bool on_accessible_stack(struct task_struct *tsk,
+					unsigned long sp,
+					struct stack_info *info)
 {
-	if (on_task_stack(tsk, sp))
+	if (on_task_stack(tsk, sp, info))
 		return true;
 	if (tsk != current || preemptible())
 		return false;
-	if (on_irq_stack(sp))
+	if (on_irq_stack(sp, info))
 		return true;
-	if (on_overflow_stack(sp))
+	if (on_overflow_stack(sp, info))
 		return true;
-	if (on_sdei_stack(sp))
+	if (on_sdei_stack(sp, info))
 		return true;
 
 	return false;
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 299758f9b9c4..6219486fa25f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -132,7 +132,7 @@ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
 {
 	return ((addr & ~(THREAD_SIZE - 1))  ==
 		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) ||
-		on_irq_stack(addr);
+		on_irq_stack(addr, NULL);
 }
 
 /**
diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index 6b8d90d5ceae..a94a868f0532 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -13,6 +13,7 @@
 #include <asm/mmu.h>
 #include <asm/ptrace.h>
 #include <asm/sections.h>
+#include <asm/stacktrace.h>
 #include <asm/sysreg.h>
 #include <asm/vmap_stack.h>
 
@@ -88,23 +89,55 @@ static int init_sdei_stacks(void)
 	return err;
 }
 
-bool _on_sdei_stack(unsigned long sp)
+bool on_sdei_normal_stack(unsigned long sp,
+			struct stack_info *info)
 {
-	unsigned long low, high;
+	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
+	unsigned long high = low + SDEI_STACK_SIZE;
 
-	if (!IS_ENABLED(CONFIG_VMAP_STACK))
+	if (sp < low || sp >= high)
 		return false;
 
-	low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
-	high = low + SDEI_STACK_SIZE;
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_SDEI_NORMAL;
+	}
 
-	if (low <= sp && sp < high)
+	return true;
+}
+
+bool on_sdei_critical_stack(unsigned long sp,
+			struct stack_info *info)
+{
+	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
+	unsigned long high = low + SDEI_STACK_SIZE;
+
+	if (sp < low || sp >= high)
+		return false;
+
+	if (info) {
+		info->low = low;
+		info->high = high;
+		info->type = STACK_TYPE_SDEI_CRITICAL;
+	}
+
+	return true;
+}
+
+bool _on_sdei_stack(unsigned long sp,
+		struct stack_info *info)
+{
+	if (!IS_ENABLED(CONFIG_VMAP_STACK))
+		return false;
+
+	if (on_sdei_critical_stack(sp, info))
 		return true;
 
-	low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
-	high = low + SDEI_STACK_SIZE;
+	if (on_sdei_normal_stack(sp, info))
+		return true;
 
-	return (low <= sp && sp < high);
+	return false;
 }
 
 unsigned long sdei_arch_get_entry_point(int conduit)
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index d5718a060672..4989f7ea1e59 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -50,7 +50,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	if (!tsk)
 		tsk = current;
 
-	if (!on_accessible_stack(tsk, fp))
+	if (!on_accessible_stack(tsk, fp, NULL))
 		return -EINVAL;
 
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
-- 
cgit v1.2.3


From 0b3e336601b82c6afa0e9cf21db9cb8793e25399 Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Fri, 20 Jul 2018 14:41:54 -0700
Subject: arm64: Add support for STACKLEAK gcc plugin

This adds support for the STACKLEAK gcc plugin to arm64 by implementing
stackleak_check_alloca(), based heavily on the x86 version, and adding the
two helpers used by the stackleak common code: current_top_of_stack() and
on_thread_stack(). The stack erasure calls are made at syscall returns.
Additionally, this disables the plugin in hypervisor and EFI stub code,
which are out of scope for the protection.

Acked-by: Alexander Popov <alex.popov@linux.com>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/Kconfig                    |  1 +
 arch/arm64/include/asm/processor.h    | 15 +++++++++++++++
 arch/arm64/kernel/entry.S             |  3 +++
 arch/arm64/kernel/process.c           | 22 ++++++++++++++++++++++
 arch/arm64/kvm/hyp/Makefile           |  3 ++-
 drivers/firmware/efi/libstub/Makefile |  3 ++-
 6 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 27fd50e86dfe..1494d5cfd681 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -108,6 +108,7 @@ config ARM64
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index e02612105d78..79657ad91397 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -266,5 +266,20 @@ extern void __init minsigstksz_setup(void);
 #define SVE_SET_VL(arg)	sve_set_current_vl(arg)
 #define SVE_GET_VL()	sve_get_current_vl()
 
+/*
+ * For CONFIG_GCC_PLUGIN_STACKLEAK
+ *
+ * These need to be macros because otherwise we get stuck in a nightmare
+ * of header definitions for the use of task_stack_page.
+ */
+
+#define current_top_of_stack()							\
+({										\
+	struct stack_info _info;						\
+	BUG_ON(!on_accessible_stack(current, current_stack_pointer, &_info));	\
+	_info.high;								\
+})
+#define on_thread_stack()	(on_task_stack(current, current_stack_pointer, NULL))
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_PROCESSOR_H */
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index d1440f84668b..09dbea221a27 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -902,6 +902,9 @@ ret_to_user:
 	cbnz	x2, work_pending
 finish_ret_to_user:
 	enable_step_tsk x1, x2
+#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+	bl	stackleak_erase
+#endif
 	kernel_exit 0
 ENDPROC(ret_to_user)
 
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 740b31f77ade..7f1628effe6d 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -493,3 +493,25 @@ void arch_setup_new_exec(void)
 {
 	current->mm->context.flags = is_compat_task() ? MMCF_AARCH32 : 0;
 }
+
+#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+void __used stackleak_check_alloca(unsigned long size)
+{
+	unsigned long stack_left;
+	unsigned long current_sp = current_stack_pointer;
+	struct stack_info info;
+
+	BUG_ON(!on_accessible_stack(current, current_sp, &info));
+
+	stack_left = current_sp - info.low;
+
+	/*
+	 * There's a good chance we're almost out of stack space if this
+	 * is true. Using panic() over BUG() is more likely to give
+	 * reliable debugging output.
+	 */
+	if (size >= stack_left)
+		panic("alloca() over the kernel stack boundary\n");
+}
+EXPORT_SYMBOL(stackleak_check_alloca);
+#endif
diff --git a/arch/arm64/kvm/hyp/Makefile b/arch/arm64/kvm/hyp/Makefile
index 4313f7475333..2fabc2dc1966 100644
--- a/arch/arm64/kvm/hyp/Makefile
+++ b/arch/arm64/kvm/hyp/Makefile
@@ -3,7 +3,8 @@
 # Makefile for Kernel-based Virtual Machine module, HYP part
 #
 
-ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING
+ccflags-y += -fno-stack-protector -DDISABLE_BRANCH_PROFILING \
+		$(DISABLE_STACKLEAK_PLUGIN)
 
 KVM=../../../../virt/kvm
 
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index a34e9290a699..25dd2a14560d 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -20,7 +20,8 @@ cflags-$(CONFIG_EFI_ARMSTUB)	+= -I$(srctree)/scripts/dtc/libfdt
 KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
 				   -D__NO_FORTIFY \
 				   $(call cc-option,-ffreestanding) \
-				   $(call cc-option,-fno-stack-protector)
+				   $(call cc-option,-fno-stack-protector) \
+				   $(DISABLE_STACKLEAK_PLUGIN)
 
 GCOV_PROFILE			:= n
 KASAN_SANITIZE			:= n
-- 
cgit v1.2.3


From 014562071c96524b518d4d3513fcde072c8e63b5 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 5 Jul 2018 12:45:39 +0300
Subject: PCI: mobiveil: Integer overflow in IB_WIN_SIZE

IB_WIN_SIZE is larger than INT_MAX so we need to cast it to u64.

Fixes: 9af6bcb11e12 ("PCI: mobiveil: Add Mobiveil PCIe Host Bridge IP driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pcie-mobiveil.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index 4d6c20e47bed..cf0aa7cee5b0 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -107,7 +107,7 @@
 #define CFG_WINDOW_TYPE	0
 #define IO_WINDOW_TYPE		1
 #define MEM_WINDOW_TYPE	2
-#define IB_WIN_SIZE		(256 * 1024 * 1024 * 1024)
+#define IB_WIN_SIZE		((u64)256 * 1024 * 1024 * 1024)
 #define MAX_PIO_WINDOWS	8
 
 /* Parameters for the waiting for link up routine */
-- 
cgit v1.2.3


From 809092dc3e606f3508b53baa624b27bfff8f0e7f Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Thu, 26 Jul 2018 12:23:31 +0100
Subject: drivers/perf: arm-ccn: Use devm_ioremap_resource() to map memory

Instead of checking the return value of platform_get_resource(), we can
use devm_ioremap_resource() which has the NULL pointer check and the
memory region requesting. devm_ioremap_resource is designed to replace
calls to devm_request_mem_region followed by devm_ioremap, so let's use
the same.

Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/perf/arm-ccn.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/perf/arm-ccn.c b/drivers/perf/arm-ccn.c
index b416ee18e6bb..4b15c36f4631 100644
--- a/drivers/perf/arm-ccn.c
+++ b/drivers/perf/arm-ccn.c
@@ -1485,17 +1485,9 @@ static int arm_ccn_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ccn);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!res)
-		return -EINVAL;
-
-	if (!devm_request_mem_region(ccn->dev, res->start,
-			resource_size(res), pdev->name))
-		return -EBUSY;
-
-	ccn->base = devm_ioremap(ccn->dev, res->start,
-				resource_size(res));
-	if (!ccn->base)
-		return -EFAULT;
+	ccn->base = devm_ioremap_resource(ccn->dev, res);
+	if (IS_ERR(ccn->base))
+		return PTR_ERR(ccn->base);
 
 	res = platform_get_resource(pdev, IORESOURCE_IRQ, 0);
 	if (!res)
-- 
cgit v1.2.3


From d6b340d7cb33c816ef4abe8143764ec5ab14a5cc Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Jul 2018 14:58:03 +0200
Subject: ALSA: trident: Suppress gcc string warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The meddlesome gcc warns about the possible shortname string in
trident driver code:
  sound/pci/trident/trident.c: In function ‘snd_trident_probe’:
  sound/pci/trident/trident.c:126:2: warning: ‘strcat’ accessing 17 or more bytes at offsets 36 and 20 may overlap 1 byte at offset 36 [-Wrestrict]
  strcat(card->shortname, card->driver);

It happens since gcc calculates the possible string size from
card->driver, but this can't be true since we did set the string just
before that, and they are much shorter.

For shutting it up, use the exactly same string set to card->driver
for strcat() to card->shortname, too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/trident/trident.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/trident/trident.c b/sound/pci/trident/trident.c
index cedf13b64803..2f18b1cdc2cd 100644
--- a/sound/pci/trident/trident.c
+++ b/sound/pci/trident/trident.c
@@ -123,7 +123,7 @@ static int snd_trident_probe(struct pci_dev *pci,
 	} else {
 		strcpy(card->shortname, "Trident ");
 	}
-	strcat(card->shortname, card->driver);
+	strcat(card->shortname, str);
 	sprintf(card->longname, "%s PCI Audio at 0x%lx, irq %d",
 		card->shortname, trident->port, trident->irq);
 
-- 
cgit v1.2.3


From c183fec10ae6b3d1dfb77471d4158e576f6b43ae Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Wed, 25 Jul 2018 17:00:59 +0800
Subject: ASoC: AMD: Add a fix voltage regulator for DA7219 and ADAU7002

DA7219 for our platform need to be configured for 1.8V.
Hence, we add a volatge regulator with supplies
of 1.8V in the machine driver.

Signed-off-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/Kconfig                |  1 +
 sound/soc/amd/acp-da7219-max98357a.c | 43 ++++++++++++++++++++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/sound/soc/amd/Kconfig b/sound/soc/amd/Kconfig
index 6cbf9cf4d1a4..58c1dcb4d255 100644
--- a/sound/soc/amd/Kconfig
+++ b/sound/soc/amd/Kconfig
@@ -8,6 +8,7 @@ config SND_SOC_AMD_CZ_DA7219MX98357_MACH
 	select SND_SOC_DA7219
 	select SND_SOC_MAX98357A
 	select SND_SOC_ADAU7002
+	select REGULATOR
 	depends on SND_SOC_AMD_ACP && I2C
 	help
 	 This option enables machine driver for DA7219 and MAX9835.
diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index f42606e5879e..cd3cf6e691a9 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -32,6 +32,8 @@
 #include <linux/clk.h>
 #include <linux/gpio.h>
 #include <linux/module.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/driver.h>
 #include <linux/i2c.h>
 #include <linux/input.h>
 #include <linux/acpi.h>
@@ -320,11 +322,52 @@ static struct snd_soc_card cz_card = {
 	.num_controls = ARRAY_SIZE(cz_mc_controls),
 };
 
+static struct regulator_consumer_supply acp_da7219_supplies[] = {
+	REGULATOR_SUPPLY("VDD", "i2c-DLGS7219:00"),
+	REGULATOR_SUPPLY("VDDMIC", "i2c-DLGS7219:00"),
+	REGULATOR_SUPPLY("VDDIO", "i2c-DLGS7219:00"),
+	REGULATOR_SUPPLY("IOVDD", "ADAU7002:00"),
+};
+
+static struct regulator_init_data acp_da7219_data = {
+	.constraints = {
+		.always_on = 1,
+	},
+	.num_consumer_supplies = ARRAY_SIZE(acp_da7219_supplies),
+	.consumer_supplies = acp_da7219_supplies,
+};
+
+static struct regulator_config acp_da7219_cfg = {
+	.init_data = &acp_da7219_data,
+};
+
+static struct regulator_ops acp_da7219_ops = {
+};
+
+static struct regulator_desc acp_da7219_desc = {
+	.name = "reg-fixed-1.8V",
+	.type = REGULATOR_VOLTAGE,
+	.owner = THIS_MODULE,
+	.ops = &acp_da7219_ops,
+	.fixed_uV = 1800000, /* 1.8V */
+	.n_voltages = 1,
+};
+
 static int cz_probe(struct platform_device *pdev)
 {
 	int ret;
 	struct snd_soc_card *card;
 	struct acp_platform_info *machine;
+	struct regulator_dev *rdev;
+
+	acp_da7219_cfg.dev = &pdev->dev;
+	rdev = devm_regulator_register(&pdev->dev, &acp_da7219_desc,
+				       &acp_da7219_cfg);
+	if (IS_ERR(rdev)) {
+		dev_err(&pdev->dev, "Failed to register regulator: %d\n",
+			ret);
+		return -EINVAL;
+	}
 
 	machine = devm_kzalloc(&pdev->dev, sizeof(struct acp_platform_info),
 			       GFP_KERNEL);
-- 
cgit v1.2.3


From 7699676081ded2e149e798f9205f1f089aa3a6bc Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Thu, 26 Jul 2018 14:04:08 +0800
Subject: ASoC: AMD: Fix build warning

Fixes
sound/soc/amd/acp-da7219-max98357a.c: In function 'cz_probe':
sound/soc/amd/acp-da7219-max98357a.c:367:3: warning: 'ret' may
be used uninitialized in this function [-Wmaybe-uninitialized]
   dev_err(&pdev->dev, "Failed to register regulator: %d\n",
ret);

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-da7219-max98357a.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/amd/acp-da7219-max98357a.c b/sound/soc/amd/acp-da7219-max98357a.c
index cd3cf6e691a9..8e3275a96a82 100644
--- a/sound/soc/amd/acp-da7219-max98357a.c
+++ b/sound/soc/amd/acp-da7219-max98357a.c
@@ -365,7 +365,7 @@ static int cz_probe(struct platform_device *pdev)
 				       &acp_da7219_cfg);
 	if (IS_ERR(rdev)) {
 		dev_err(&pdev->dev, "Failed to register regulator: %d\n",
-			ret);
+			(int)PTR_ERR(rdev));
 		return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From 2a8536f6e8464b8988baa7db881f30721616b0da Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Tue, 5 Jun 2018 19:00:54 -0700
Subject: drm: add msm compressed format modifiers

Qualcomm Snapdragon chipsets uses compressed format
to optimize BW across multiple IP's. This change adds
needed modifier support in drm for a simple 4x4 tile
based compressed variants of base formats.

Changes in v3:
- Removed duplicate entry for DRM_FORMAT_MOD_QCOM_COMPRESSED (Rob Clark)
Changes in v4:
- Remove all modifiers aside from COMPRESSED, this includes tiled and
  10-bit

Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 include/uapi/drm/drm_fourcc.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
index d43949b5bb3e..721ab7e54d96 100644
--- a/include/uapi/drm/drm_fourcc.h
+++ b/include/uapi/drm/drm_fourcc.h
@@ -299,6 +299,19 @@ extern "C" {
  */
 #define DRM_FORMAT_MOD_SAMSUNG_64_32_TILE	fourcc_mod_code(SAMSUNG, 1)
 
+/*
+ * Qualcomm Compressed Format
+ *
+ * Refers to a compressed variant of the base format that is compressed.
+ * Implementation may be platform and base-format specific.
+ *
+ * Each macrotile consists of m x n (mostly 4 x 4) tiles.
+ * Pixel data pitch/stride is aligned with macrotile width.
+ * Pixel data height is aligned with macrotile height.
+ * Entire pixel data buffer is aligned with 4k(bytes).
+ */
+#define DRM_FORMAT_MOD_QCOM_COMPRESSED	fourcc_mod_code(QCOM, 1)
+
 /* Vivante framebuffer modifiers */
 
 /*
-- 
cgit v1.2.3


From ed9976a09b486d85ae537b5cd73e947d7dfbb136 Mon Sep 17 00:00:00 2001
From: Chandan Uddaraju <chandanu@codeaurora.org>
Date: Wed, 18 Apr 2018 12:45:14 -0700
Subject: drm/msm/dsi: adjust dsi timing for dual dsi mode

For dual dsi mode, the horizontal timing needs
to be divided by half since both the dsi controllers
will be driving this panel. Adjust the pixel clock and
DSI timing accordingly.

Changes in v3:
- Added Archit's R-b
- Rebase on dsi cleanup set in msm-next

Cc: Sibi Sankar <sibis@codeaurora.org>
Reviewed-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Chandan Uddaraju <chandanu@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi.h         | 10 +++---
 drivers/gpu/drm/msm/dsi/dsi_cfg.h     |  2 +-
 drivers/gpu/drm/msm/dsi/dsi_host.c    | 65 ++++++++++++++++++++++++++++-------
 drivers/gpu/drm/msm/dsi/dsi_manager.c |  7 ++--
 4 files changed, 64 insertions(+), 20 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index dfa049d876bd..d3f613c76ffa 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -163,7 +163,8 @@ void msm_dsi_host_cmd_xfer_commit(struct mipi_dsi_host *host,
 int msm_dsi_host_enable(struct mipi_dsi_host *host);
 int msm_dsi_host_disable(struct mipi_dsi_host *host);
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
-			struct msm_dsi_phy_shared_timings *phy_shared_timings);
+			struct msm_dsi_phy_shared_timings *phy_shared_timings,
+			bool is_dual_dsi);
 int msm_dsi_host_power_off(struct mipi_dsi_host *host);
 int msm_dsi_host_set_display_mode(struct mipi_dsi_host *host,
 					struct drm_display_mode *mode);
@@ -176,7 +177,8 @@ int msm_dsi_host_set_src_pll(struct mipi_dsi_host *host,
 			struct msm_dsi_pll *src_pll);
 void msm_dsi_host_reset_phy(struct mipi_dsi_host *host);
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
-	struct msm_dsi_phy_clk_request *clk_req);
+	struct msm_dsi_phy_clk_request *clk_req,
+	bool is_dual_dsi);
 void msm_dsi_host_destroy(struct mipi_dsi_host *host);
 int msm_dsi_host_modeset_init(struct mipi_dsi_host *host,
 					struct drm_device *dev);
@@ -196,8 +198,8 @@ int dsi_dma_base_get_6g(struct msm_dsi_host *msm_host, uint64_t *iova);
 int dsi_dma_base_get_v2(struct msm_dsi_host *msm_host, uint64_t *iova);
 int dsi_clk_init_v2(struct msm_dsi_host *msm_host);
 int dsi_clk_init_6g_v2(struct msm_dsi_host *msm_host);
-int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host);
-int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host);
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi);
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi);
 
 /* dsi phy */
 struct msm_dsi_phy;
diff --git a/drivers/gpu/drm/msm/dsi/dsi_cfg.h b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
index a795a062b779..16c507911110 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_cfg.h
+++ b/drivers/gpu/drm/msm/dsi/dsi_cfg.h
@@ -48,7 +48,7 @@ struct msm_dsi_host_cfg_ops {
 	void* (*tx_buf_get)(struct msm_dsi_host *msm_host);
 	void (*tx_buf_put)(struct msm_dsi_host *msm_host);
 	int (*dma_base_get)(struct msm_dsi_host *msm_host, uint64_t *iova);
-	int (*calc_clk_rate)(struct msm_dsi_host *msm_host);
+	int (*calc_clk_rate)(struct msm_dsi_host *msm_host, bool is_dual_dsi);
 };
 
 struct msm_dsi_cfg_handler {
diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 24dfae5b01a2..cba42ad05fb3 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -118,6 +118,7 @@ struct msm_dsi_host {
 	struct clk *byte_intf_clk;
 
 	u32 byte_clk_rate;
+	u32 pixel_clk_rate;
 	u32 esc_clk_rate;
 
 	/* DSI v2 specific clocks */
@@ -523,7 +524,7 @@ int dsi_link_clk_enable_6g(struct msm_dsi_host *msm_host)
 		goto error;
 	}
 
-	ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000);
+	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
 		goto error;
@@ -604,7 +605,7 @@ int dsi_link_clk_enable_v2(struct msm_dsi_host *msm_host)
 		goto error;
 	}
 
-	ret = clk_set_rate(msm_host->pixel_clk, msm_host->mode->clock * 1000);
+	ret = clk_set_rate(msm_host->pixel_clk, msm_host->pixel_clk_rate);
 	if (ret) {
 		pr_err("%s: Failed to set rate pixel clk, %d\n", __func__, ret);
 		goto error;
@@ -663,7 +664,7 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
 	clk_disable_unprepare(msm_host->byte_clk);
 }
 
-int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host)
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
 	u8 lanes = msm_host->lanes;
@@ -671,6 +672,16 @@ int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host)
 	u32 pclk_rate;
 
 	pclk_rate = mode->clock * 1000;
+
+	/*
+	 * For dual DSI mode, the current DRM mode has the complete width of the
+	 * panel. Since, the complete panel is driven by two DSI controllers,
+	 * theclock rates have to be split between the two dsi controllers.
+	 * Adjust the byte and pixel clock rates for each dsi host accordingly.
+	 */
+	if (is_dual_dsi)
+		pclk_rate /= 2;
+
 	if (lanes > 0) {
 		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
 	} else {
@@ -685,7 +696,7 @@ int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host)
 	return 0;
 }
 
-int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host)
+int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
 	u8 lanes = msm_host->lanes;
@@ -695,14 +706,26 @@ int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host)
 	unsigned long byte_mhz;
 
 	pclk_rate = mode->clock * 1000;
+
+	/*
+	 * For dual DSI mode, the current DRM mode has the complete width of the
+	 * panel. Since, the complete panel is driven by two DSI controllers,
+	 * theclock rates have to be split between the two dsi controllers.
+	 * Adjust the byte and pixel clock rates for each dsi host accordingly.
+	 */
+	if (is_dual_dsi)
+		pclk_rate /= 2;
+
 	if (lanes > 0) {
 		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
 	} else {
 		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
 		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
 	}
+	msm_host->pixel_clk_rate = pclk_rate;
 
-	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
+	DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate,
+				msm_host->byte_clk_rate);
 
 	msm_host->src_clk_rate = (pclk_rate * bpp) / 8;
 
@@ -897,7 +920,7 @@ static void dsi_ctrl_config(struct msm_dsi_host *msm_host, bool enable,
 	dsi_write(msm_host, REG_DSI_CTRL, data);
 }
 
-static void dsi_timing_setup(struct msm_dsi_host *msm_host)
+static void dsi_timing_setup(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
 	u32 hs_start = 0, vs_start = 0; /* take sync start as 0 */
@@ -909,10 +932,26 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 	u32 ha_end = ha_start + mode->hdisplay;
 	u32 va_start = v_total - mode->vsync_start;
 	u32 va_end = va_start + mode->vdisplay;
+	u32 hdisplay = mode->hdisplay;
 	u32 wc;
 
 	DBG("");
 
+	/*
+	 * For dual DSI mode, the current DRM mode has
+	 * the complete width of the panel. Since, the complete
+	 * panel is driven by two DSI controllers, the horizontal
+	 * timings have to be split between the two dsi controllers.
+	 * Adjust the DSI host timing values accordingly.
+	 */
+	if (is_dual_dsi) {
+		h_total /= 2;
+		hs_end /= 2;
+		ha_start /= 2;
+		ha_end /= 2;
+		hdisplay /= 2;
+	}
+
 	if (msm_host->mode_flags & MIPI_DSI_MODE_VIDEO) {
 		dsi_write(msm_host, REG_DSI_ACTIVE_H,
 			DSI_ACTIVE_H_START(ha_start) |
@@ -933,7 +972,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 			DSI_ACTIVE_VSYNC_VPOS_END(vs_end));
 	} else {		/* command mode */
 		/* image data and 1 byte write_memory_start cmd */
-		wc = mode->hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1;
+		wc = hdisplay * dsi_get_bpp(msm_host->format) / 8 + 1;
 
 		dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_CTRL,
 			DSI_CMD_MDP_STREAM_CTRL_WORD_COUNT(wc) |
@@ -943,7 +982,7 @@ static void dsi_timing_setup(struct msm_dsi_host *msm_host)
 					MIPI_DSI_DCS_LONG_WRITE));
 
 		dsi_write(msm_host, REG_DSI_CMD_MDP_STREAM_TOTAL,
-			DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(mode->hdisplay) |
+			DSI_CMD_MDP_STREAM_TOTAL_H_TOTAL(hdisplay) |
 			DSI_CMD_MDP_STREAM_TOTAL_V_TOTAL(mode->vdisplay));
 	}
 }
@@ -2217,13 +2256,14 @@ void msm_dsi_host_reset_phy(struct mipi_dsi_host *host)
 }
 
 void msm_dsi_host_get_phy_clk_req(struct mipi_dsi_host *host,
-	struct msm_dsi_phy_clk_request *clk_req)
+			struct msm_dsi_phy_clk_request *clk_req,
+			bool is_dual_dsi)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
 	int ret;
 
-	ret = cfg_hnd->ops->calc_clk_rate(msm_host);
+	ret = cfg_hnd->ops->calc_clk_rate(msm_host, is_dual_dsi);
 	if (ret) {
 		pr_err("%s: unable to calc clk rate, %d\n", __func__, ret);
 		return;
@@ -2285,7 +2325,8 @@ static void msm_dsi_sfpb_config(struct msm_dsi_host *msm_host, bool enable)
 }
 
 int msm_dsi_host_power_on(struct mipi_dsi_host *host,
-			struct msm_dsi_phy_shared_timings *phy_shared_timings)
+			struct msm_dsi_phy_shared_timings *phy_shared_timings,
+			bool is_dual_dsi)
 {
 	struct msm_dsi_host *msm_host = to_msm_dsi_host(host);
 	const struct msm_dsi_cfg_handler *cfg_hnd = msm_host->cfg_hnd;
@@ -2321,7 +2362,7 @@ int msm_dsi_host_power_on(struct mipi_dsi_host *host,
 		goto fail_disable_clk;
 	}
 
-	dsi_timing_setup(msm_host);
+	dsi_timing_setup(msm_host, is_dual_dsi);
 	dsi_sw_reset(msm_host);
 	dsi_ctrl_config(msm_host, true, phy_shared_timings);
 
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index d5006d6923e0..601de7012cae 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -134,8 +134,9 @@ static int enable_phy(struct msm_dsi *msm_dsi, int src_pll_id,
 {
 	struct msm_dsi_phy_clk_request clk_req;
 	int ret;
+	bool is_dual_dsi = IS_DUAL_DSI();
 
-	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req);
+	msm_dsi_host_get_phy_clk_req(msm_dsi->host, &clk_req, is_dual_dsi);
 
 	ret = msm_dsi_phy_enable(msm_dsi->phy, src_pll_id, &clk_req);
 	msm_dsi_phy_get_shared_timings(msm_dsi->phy, shared_timings);
@@ -458,7 +459,7 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 	if (is_dual_dsi && (DSI_1 == id))
 		return;
 
-	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id]);
+	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id], is_dual_dsi);
 	if (ret) {
 		pr_err("%s: power on host %d failed, %d\n", __func__, id, ret);
 		goto host_on_fail;
@@ -466,7 +467,7 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 
 	if (is_dual_dsi && msm_dsi1) {
 		ret = msm_dsi_host_power_on(msm_dsi1->host,
-					    &phy_shared_timings[DSI_1]);
+				&phy_shared_timings[DSI_1], is_dual_dsi);
 		if (ret) {
 			pr_err("%s: power on host1 failed, %d\n",
 							__func__, ret);
-- 
cgit v1.2.3


From 8b03ad30e314691f7bfccc0f9fae0dffd498b667 Mon Sep 17 00:00:00 2001
From: Chandan Uddaraju <chandanu@codeaurora.org>
Date: Wed, 18 Apr 2018 12:45:15 -0700
Subject: drm/msm/dsi: Use one connector for dual DSI mode

Current DSI driver uses two connectors for dual DSI case even
though we only have one panel. Fix this by implementing one
connector/bridge for dual DSI use case. Use master DSI
controllers to register one connector/bridge.

Changes in v3:
- None

Reviewed-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Chandan Uddaraju <chandanu@codeaurora.org>
[seanpaul removed unused local var causing a build warning]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi.c         |   3 +
 drivers/gpu/drm/msm/dsi/dsi.h         |   1 +
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 112 ++++++++--------------------------
 3 files changed, 30 insertions(+), 86 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi.c b/drivers/gpu/drm/msm/dsi/dsi.c
index b744bcc7d8ad..ff8164cc6738 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.c
+++ b/drivers/gpu/drm/msm/dsi/dsi.c
@@ -208,6 +208,9 @@ int msm_dsi_modeset_init(struct msm_dsi *msm_dsi, struct drm_device *dev,
 		goto fail;
 	}
 
+	if (!msm_dsi_manager_validate_current_config(msm_dsi->id))
+		goto fail;
+
 	msm_dsi->encoder = encoder;
 
 	msm_dsi->bridge = msm_dsi_manager_bridge_init(msm_dsi->id);
diff --git a/drivers/gpu/drm/msm/dsi/dsi.h b/drivers/gpu/drm/msm/dsi/dsi.h
index d3f613c76ffa..08f3fc6771b7 100644
--- a/drivers/gpu/drm/msm/dsi/dsi.h
+++ b/drivers/gpu/drm/msm/dsi/dsi.h
@@ -100,6 +100,7 @@ bool msm_dsi_manager_cmd_xfer_trigger(int id, u32 dma_base, u32 len);
 void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags);
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi);
 void msm_dsi_manager_unregister(struct msm_dsi *msm_dsi);
+bool msm_dsi_manager_validate_current_config(u8 id);
 
 /* msm dsi */
 static inline bool msm_dsi_device_connected(struct msm_dsi *msm_dsi)
diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 601de7012cae..8422b8753eb9 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -306,102 +306,25 @@ static void dsi_mgr_connector_destroy(struct drm_connector *connector)
 	kfree(dsi_connector);
 }
 
-static void dsi_dual_connector_fix_modes(struct drm_connector *connector)
-{
-	struct drm_display_mode *mode, *m;
-
-	/* Only support left-right mode */
-	list_for_each_entry_safe(mode, m, &connector->probed_modes, head) {
-		mode->clock >>= 1;
-		mode->hdisplay >>= 1;
-		mode->hsync_start >>= 1;
-		mode->hsync_end >>= 1;
-		mode->htotal >>= 1;
-		drm_mode_set_name(mode);
-	}
-}
-
-static int dsi_dual_connector_tile_init(
-			struct drm_connector *connector, int id)
-{
-	struct drm_display_mode *mode;
-	/* Fake topology id */
-	char topo_id[8] = {'M', 'S', 'M', 'D', 'U', 'D', 'S', 'I'};
-
-	if (connector->tile_group) {
-		DBG("Tile property has been initialized");
-		return 0;
-	}
-
-	/* Use the first mode only for now */
-	mode = list_first_entry(&connector->probed_modes,
-				struct drm_display_mode,
-				head);
-	if (!mode)
-		return -EINVAL;
-
-	connector->tile_group = drm_mode_get_tile_group(
-					connector->dev, topo_id);
-	if (!connector->tile_group)
-		connector->tile_group = drm_mode_create_tile_group(
-					connector->dev, topo_id);
-	if (!connector->tile_group) {
-		pr_err("%s: failed to create tile group\n", __func__);
-		return -ENOMEM;
-	}
-
-	connector->has_tile = true;
-	connector->tile_is_single_monitor = true;
-
-	/* mode has been fixed */
-	connector->tile_h_size = mode->hdisplay;
-	connector->tile_v_size = mode->vdisplay;
-
-	/* Only support left-right mode */
-	connector->num_h_tile = 2;
-	connector->num_v_tile = 1;
-
-	connector->tile_v_loc = 0;
-	connector->tile_h_loc = (id == DSI_RIGHT) ? 1 : 0;
-
-	return 0;
-}
-
 static int dsi_mgr_connector_get_modes(struct drm_connector *connector)
 {
 	int id = dsi_mgr_connector_get_id(connector);
 	struct msm_dsi *msm_dsi = dsi_mgr_get_dsi(id);
 	struct drm_panel *panel = msm_dsi->panel;
-	int ret, num;
+	int num;
 
 	if (!panel)
 		return 0;
 
-	/* Since we have 2 connectors, but only 1 drm_panel in dual DSI mode,
-	 * panel should not attach to any connector.
-	 * Only temporarily attach panel to the current connector here,
-	 * to let panel set mode to this connector.
+	/*
+	 * In dual DSI mode, we have one connector that can be
+	 * attached to the drm_panel.
 	 */
 	drm_panel_attach(panel, connector);
 	num = drm_panel_get_modes(panel);
-	drm_panel_detach(panel);
 	if (!num)
 		return 0;
 
-	if (IS_DUAL_DSI()) {
-		/* report half resolution to user */
-		dsi_dual_connector_fix_modes(connector);
-		ret = dsi_dual_connector_tile_init(connector, id);
-		if (ret)
-			return ret;
-		ret = drm_connector_set_tile_property(connector);
-		if (ret) {
-			pr_err("%s: set tile property failed, %d\n",
-					__func__, ret);
-			return ret;
-		}
-	}
-
 	return num;
 }
 
@@ -455,8 +378,8 @@ static void dsi_mgr_bridge_pre_enable(struct drm_bridge *bridge)
 	if (ret)
 		goto phy_en_fail;
 
-	/* Do nothing with the host if it is DSI 1 in case of dual DSI */
-	if (is_dual_dsi && (DSI_1 == id))
+	/* Do nothing with the host if it is slave-DSI in case of dual DSI */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	ret = msm_dsi_host_power_on(host, &phy_shared_timings[id], is_dual_dsi);
@@ -557,11 +480,11 @@ static void dsi_mgr_bridge_post_disable(struct drm_bridge *bridge)
 		return;
 
 	/*
-	 * Do nothing with the host if it is DSI 1 in case of dual DSI.
+	 * Do nothing with the host if it is slave-DSI in case of dual DSI.
 	 * It is safe to call dsi_mgr_phy_disable() here because a single PHY
 	 * won't be diabled until both PHYs request disable.
 	 */
-	if (is_dual_dsi && (DSI_1 == id))
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		goto disable_phy;
 
 	if (panel) {
@@ -622,7 +545,7 @@ static void dsi_mgr_bridge_mode_set(struct drm_bridge *bridge,
 			mode->vsync_end, mode->vtotal,
 			mode->type, mode->flags);
 
-	if (is_dual_dsi && (DSI_1 == id))
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id))
 		return;
 
 	msm_dsi_host_set_display_mode(host, adjusted_mode);
@@ -690,6 +613,23 @@ struct drm_connector *msm_dsi_manager_connector_init(u8 id)
 	return connector;
 }
 
+bool msm_dsi_manager_validate_current_config(u8 id)
+{
+	bool is_dual_dsi = IS_DUAL_DSI();
+
+	/*
+	 * For dual DSI, we only have one drm panel. For this
+	 * use case, we register only one bridge/connector.
+	 * Skip bridge/connector initialisation if it is
+	 * slave-DSI for dual DSI configuration.
+	 */
+	if (is_dual_dsi && !IS_MASTER_DSI_LINK(id)) {
+		DBG("Skip bridge registration for slave DSI->id: %d\n", id);
+		return false;
+	}
+	return true;
+}
+
 /* initialize bridge */
 struct drm_bridge *msm_dsi_manager_bridge_init(u8 id)
 {
-- 
cgit v1.2.3


From 7a296796fd0b28dc229d65dd90a6b392852d9631 Mon Sep 17 00:00:00 2001
From: Rajesh Yadav <ryadav@codeaurora.org>
Date: Mon, 25 Jun 2018 19:12:03 +0530
Subject: drm/msm/dsi: initialize postdiv_lock before use for 10nm pll

postdiv_lock spinlock was used before initialization
for 10nm pll. It causes following spin_bug:
	"BUG: spinlock bad magic on CPU#0".
Initialize spinlock before its usage.

Changes in v3:
- Added Archit's R-b

Reviewed-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Rajesh Yadav <ryadav@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
index c4c37a7df637..4c03f0b7343e 100644
--- a/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
+++ b/drivers/gpu/drm/msm/dsi/pll/dsi_pll_10nm.c
@@ -798,6 +798,8 @@ struct msm_dsi_pll *msm_dsi_pll_10nm_init(struct platform_device *pdev, int id)
 		return ERR_PTR(-ENOMEM);
 	}
 
+	spin_lock_init(&pll_10nm->postdiv_lock);
+
 	pll = &pll_10nm->base;
 	pll->min_rate = 1000000000UL;
 	pll->max_rate = 3500000000UL;
-- 
cgit v1.2.3


From 425a2d24d5b3ee9efc7f490440bfa20ba9166548 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <abhinavk@codeaurora.org>
Date: Fri, 15 Jun 2018 22:56:59 -0700
Subject: drm/msm/dsi: set encoder mode for DRM bridge explicitly

Currently, DRM bridge for DPU relies on the default video
mode setting to set the encoder mode.

Add an explicit call to set the encoder mode for bridges.

Changes in v3:
- None

Reviewed-by: Archit Taneja <architt@codeauorora.org>
Signed-off-by: Abhinav Kumar <abhinavk@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi_manager.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_manager.c b/drivers/gpu/drm/msm/dsi/dsi_manager.c
index 8422b8753eb9..5224010d90e4 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_manager.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_manager.c
@@ -773,6 +773,7 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
 	struct drm_encoder *encoder;
+	bool cmd_mode;
 
 	/*
 	 * drm_device pointer is assigned to msm_dsi only in the modeset_init
@@ -787,10 +788,11 @@ void msm_dsi_manager_attach_dsi_device(int id, u32 device_flags)
 	priv = dev->dev_private;
 	kms = priv->kms;
 	encoder = msm_dsi_get_encoder(msm_dsi);
+	cmd_mode = !(device_flags &
+				 MIPI_DSI_MODE_VIDEO);
 
 	if (encoder && kms->funcs->set_encoder_mode)
-		if (!(device_flags & MIPI_DSI_MODE_VIDEO))
-			kms->funcs->set_encoder_mode(kms, encoder, true);
+		kms->funcs->set_encoder_mode(kms, encoder, cmd_mode);
 }
 
 int msm_dsi_manager_register(struct msm_dsi *msm_dsi)
-- 
cgit v1.2.3


From a5c6b59904222ffe2eee37e5951d1f57ac1e530f Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Fri, 13 Apr 2018 10:09:11 -0400
Subject: drm/msm: Move wait_for_vblanks into mdp complete_commit() hooks

DPU doesn't use this, so push it into the mdp drivers.

Changes in v3:
- None

Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rajesh Yadav <ryadav@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c | 2 ++
 drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c | 2 ++
 drivers/gpu/drm/msm/msm_atomic.c         | 2 --
 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
index 4b646bf9c214..44d1cda56974 100644
--- a/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp4/mdp4_kms.c
@@ -125,6 +125,8 @@ static void mdp4_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s
 	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 
+	drm_atomic_helper_wait_for_vblanks(mdp4_kms->dev, state);
+
 	/* see 119ecb7fd */
 	for_each_new_crtc_in_state(state, crtc, crtc_state, i)
 		drm_crtc_vblank_put(crtc);
diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
index 6e12e275deba..bddd625ab91b 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_kms.c
@@ -170,6 +170,8 @@ static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *s
 	struct device *dev = &mdp5_kms->pdev->dev;
 	struct mdp5_global_state *global_state;
 
+	drm_atomic_helper_wait_for_vblanks(mdp5_kms->dev, state);
+
 	global_state = mdp5_get_existing_global_state(mdp5_kms);
 
 	if (mdp5_kms->smp)
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index f0635c3da7f4..e6f1e25c60af 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -75,8 +75,6 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	kms->funcs->complete_commit(kms, state);
 
-	drm_atomic_helper_wait_for_vblanks(dev, state);
-
 	drm_atomic_helper_commit_hw_done(state);
 
 	drm_atomic_helper_cleanup_planes(dev, state);
-- 
cgit v1.2.3


From bc3220be22577e199452edbb6a24a980a4ab5c73 Mon Sep 17 00:00:00 2001
From: Rajesh Yadav <ryadav@codeaurora.org>
Date: Thu, 21 Jun 2018 16:06:10 -0400
Subject: drm/msm/mdp5: subclass msm_mdss for mdp5

SoCs having mdp5 or dpu have identical tree like
device hierarchy where MDSS top level wrapper manages
common power resources for all child devices.

Subclass msm_mdss so that msm_mdss includes common defines
and mdp5/dpu mdss derivations to include any extensions.

Add mdss helper interface (msm_mdss_funcs) to msm_mdss
base for mdp5/dpu mdss specific implementation calls.

This change subclasses msm_mdss for mdp5, dpu specific
changes will be done separately.

Changes in v3:
- Added Archit's R-b

Reviewed-by: Archit Taneja <architt@codeaurora.org>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rajesh Yadav <ryadav@codeaurora.org>
[seanpaul rebased on msm-next and resolved conflicts]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c | 154 ++++++++++++++++--------------
 drivers/gpu/drm/msm/msm_drv.c             |  22 +++--
 drivers/gpu/drm/msm/msm_kms.h             |  17 +++-
 3 files changed, 109 insertions(+), 84 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
index f2a0db7a8a03..1cc4e57f0226 100644
--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
+++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_mdss.c
@@ -20,12 +20,10 @@
 #include "msm_drv.h"
 #include "mdp5_kms.h"
 
-/*
- * If needed, this can become more specific: something like struct mdp5_mdss,
- * which contains a 'struct msm_mdss base' member.
- */
-struct msm_mdss {
-	struct drm_device *dev;
+#define to_mdp5_mdss(x) container_of(x, struct mdp5_mdss, base)
+
+struct mdp5_mdss {
+	struct msm_mdss base;
 
 	void __iomem *mmio, *vbif;
 
@@ -41,22 +39,22 @@ struct msm_mdss {
 	} irqcontroller;
 };
 
-static inline void mdss_write(struct msm_mdss *mdss, u32 reg, u32 data)
+static inline void mdss_write(struct mdp5_mdss *mdp5_mdss, u32 reg, u32 data)
 {
-	msm_writel(data, mdss->mmio + reg);
+	msm_writel(data, mdp5_mdss->mmio + reg);
 }
 
-static inline u32 mdss_read(struct msm_mdss *mdss, u32 reg)
+static inline u32 mdss_read(struct mdp5_mdss *mdp5_mdss, u32 reg)
 {
-	return msm_readl(mdss->mmio + reg);
+	return msm_readl(mdp5_mdss->mmio + reg);
 }
 
 static irqreturn_t mdss_irq(int irq, void *arg)
 {
-	struct msm_mdss *mdss = arg;
+	struct mdp5_mdss *mdp5_mdss = arg;
 	u32 intr;
 
-	intr = mdss_read(mdss, REG_MDSS_HW_INTR_STATUS);
+	intr = mdss_read(mdp5_mdss, REG_MDSS_HW_INTR_STATUS);
 
 	VERB("intr=%08x", intr);
 
@@ -64,7 +62,7 @@ static irqreturn_t mdss_irq(int irq, void *arg)
 		irq_hw_number_t hwirq = fls(intr) - 1;
 
 		generic_handle_irq(irq_find_mapping(
-				mdss->irqcontroller.domain, hwirq));
+				mdp5_mdss->irqcontroller.domain, hwirq));
 		intr &= ~(1 << hwirq);
 	}
 
@@ -84,19 +82,19 @@ static irqreturn_t mdss_irq(int irq, void *arg)
 
 static void mdss_hw_mask_irq(struct irq_data *irqd)
 {
-	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+	struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd);
 
 	smp_mb__before_atomic();
-	clear_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	clear_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask);
 	smp_mb__after_atomic();
 }
 
 static void mdss_hw_unmask_irq(struct irq_data *irqd)
 {
-	struct msm_mdss *mdss = irq_data_get_irq_chip_data(irqd);
+	struct mdp5_mdss *mdp5_mdss = irq_data_get_irq_chip_data(irqd);
 
 	smp_mb__before_atomic();
-	set_bit(irqd->hwirq, &mdss->irqcontroller.enabled_mask);
+	set_bit(irqd->hwirq, &mdp5_mdss->irqcontroller.enabled_mask);
 	smp_mb__after_atomic();
 }
 
@@ -109,13 +107,13 @@ static struct irq_chip mdss_hw_irq_chip = {
 static int mdss_hw_irqdomain_map(struct irq_domain *d, unsigned int irq,
 				 irq_hw_number_t hwirq)
 {
-	struct msm_mdss *mdss = d->host_data;
+	struct mdp5_mdss *mdp5_mdss = d->host_data;
 
 	if (!(VALID_IRQS & (1 << hwirq)))
 		return -EPERM;
 
 	irq_set_chip_and_handler(irq, &mdss_hw_irq_chip, handle_level_irq);
-	irq_set_chip_data(irq, mdss);
+	irq_set_chip_data(irq, mdp5_mdss);
 
 	return 0;
 }
@@ -126,90 +124,99 @@ static const struct irq_domain_ops mdss_hw_irqdomain_ops = {
 };
 
 
-static int mdss_irq_domain_init(struct msm_mdss *mdss)
+static int mdss_irq_domain_init(struct mdp5_mdss *mdp5_mdss)
 {
-	struct device *dev = mdss->dev->dev;
+	struct device *dev = mdp5_mdss->base.dev->dev;
 	struct irq_domain *d;
 
 	d = irq_domain_add_linear(dev->of_node, 32, &mdss_hw_irqdomain_ops,
-				  mdss);
+				  mdp5_mdss);
 	if (!d) {
 		dev_err(dev, "mdss irq domain add failed\n");
 		return -ENXIO;
 	}
 
-	mdss->irqcontroller.enabled_mask = 0;
-	mdss->irqcontroller.domain = d;
+	mdp5_mdss->irqcontroller.enabled_mask = 0;
+	mdp5_mdss->irqcontroller.domain = d;
 
 	return 0;
 }
 
-int msm_mdss_enable(struct msm_mdss *mdss)
+static int mdp5_mdss_enable(struct msm_mdss *mdss)
 {
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss);
 	DBG("");
 
-	clk_prepare_enable(mdss->ahb_clk);
-	if (mdss->axi_clk)
-		clk_prepare_enable(mdss->axi_clk);
-	if (mdss->vsync_clk)
-		clk_prepare_enable(mdss->vsync_clk);
+	clk_prepare_enable(mdp5_mdss->ahb_clk);
+	if (mdp5_mdss->axi_clk)
+		clk_prepare_enable(mdp5_mdss->axi_clk);
+	if (mdp5_mdss->vsync_clk)
+		clk_prepare_enable(mdp5_mdss->vsync_clk);
 
 	return 0;
 }
 
-int msm_mdss_disable(struct msm_mdss *mdss)
+static int mdp5_mdss_disable(struct msm_mdss *mdss)
 {
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(mdss);
 	DBG("");
 
-	if (mdss->vsync_clk)
-		clk_disable_unprepare(mdss->vsync_clk);
-	if (mdss->axi_clk)
-		clk_disable_unprepare(mdss->axi_clk);
-	clk_disable_unprepare(mdss->ahb_clk);
+	if (mdp5_mdss->vsync_clk)
+		clk_disable_unprepare(mdp5_mdss->vsync_clk);
+	if (mdp5_mdss->axi_clk)
+		clk_disable_unprepare(mdp5_mdss->axi_clk);
+	clk_disable_unprepare(mdp5_mdss->ahb_clk);
 
 	return 0;
 }
 
-static int msm_mdss_get_clocks(struct msm_mdss *mdss)
+static int msm_mdss_get_clocks(struct mdp5_mdss *mdp5_mdss)
 {
-	struct platform_device *pdev = to_platform_device(mdss->dev->dev);
+	struct platform_device *pdev =
+			to_platform_device(mdp5_mdss->base.dev->dev);
 
-	mdss->ahb_clk = msm_clk_get(pdev, "iface");
-	if (IS_ERR(mdss->ahb_clk))
-		mdss->ahb_clk = NULL;
+	mdp5_mdss->ahb_clk = msm_clk_get(pdev, "iface");
+	if (IS_ERR(mdp5_mdss->ahb_clk))
+		mdp5_mdss->ahb_clk = NULL;
 
-	mdss->axi_clk = msm_clk_get(pdev, "bus");
-	if (IS_ERR(mdss->axi_clk))
-		mdss->axi_clk = NULL;
+	mdp5_mdss->axi_clk = msm_clk_get(pdev, "bus");
+	if (IS_ERR(mdp5_mdss->axi_clk))
+		mdp5_mdss->axi_clk = NULL;
 
-	mdss->vsync_clk = msm_clk_get(pdev, "vsync");
-	if (IS_ERR(mdss->vsync_clk))
-		mdss->vsync_clk = NULL;
+	mdp5_mdss->vsync_clk = msm_clk_get(pdev, "vsync");
+	if (IS_ERR(mdp5_mdss->vsync_clk))
+		mdp5_mdss->vsync_clk = NULL;
 
 	return 0;
 }
 
-void msm_mdss_destroy(struct drm_device *dev)
+static void mdp5_mdss_destroy(struct drm_device *dev)
 {
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_mdss *mdss = priv->mdss;
+	struct mdp5_mdss *mdp5_mdss = to_mdp5_mdss(priv->mdss);
 
-	if (!mdss)
+	if (!mdp5_mdss)
 		return;
 
-	irq_domain_remove(mdss->irqcontroller.domain);
-	mdss->irqcontroller.domain = NULL;
+	irq_domain_remove(mdp5_mdss->irqcontroller.domain);
+	mdp5_mdss->irqcontroller.domain = NULL;
 
-	regulator_disable(mdss->vdd);
+	regulator_disable(mdp5_mdss->vdd);
 
 	pm_runtime_disable(dev->dev);
 }
 
-int msm_mdss_init(struct drm_device *dev)
+static const struct msm_mdss_funcs mdss_funcs = {
+	.enable	= mdp5_mdss_enable,
+	.disable = mdp5_mdss_disable,
+	.destroy = mdp5_mdss_destroy,
+};
+
+int mdp5_mdss_init(struct drm_device *dev)
 {
 	struct platform_device *pdev = to_platform_device(dev->dev);
 	struct msm_drm_private *priv = dev->dev_private;
-	struct msm_mdss *mdss;
+	struct mdp5_mdss *mdp5_mdss;
 	int ret;
 
 	DBG("");
@@ -217,40 +224,40 @@ int msm_mdss_init(struct drm_device *dev)
 	if (!of_device_is_compatible(dev->dev->of_node, "qcom,mdss"))
 		return 0;
 
-	mdss = devm_kzalloc(dev->dev, sizeof(*mdss), GFP_KERNEL);
-	if (!mdss) {
+	mdp5_mdss = devm_kzalloc(dev->dev, sizeof(*mdp5_mdss), GFP_KERNEL);
+	if (!mdp5_mdss) {
 		ret = -ENOMEM;
 		goto fail;
 	}
 
-	mdss->dev = dev;
+	mdp5_mdss->base.dev = dev;
 
-	mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS");
-	if (IS_ERR(mdss->mmio)) {
-		ret = PTR_ERR(mdss->mmio);
+	mdp5_mdss->mmio = msm_ioremap(pdev, "mdss_phys", "MDSS");
+	if (IS_ERR(mdp5_mdss->mmio)) {
+		ret = PTR_ERR(mdp5_mdss->mmio);
 		goto fail;
 	}
 
-	mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
-	if (IS_ERR(mdss->vbif)) {
-		ret = PTR_ERR(mdss->vbif);
+	mdp5_mdss->vbif = msm_ioremap(pdev, "vbif_phys", "VBIF");
+	if (IS_ERR(mdp5_mdss->vbif)) {
+		ret = PTR_ERR(mdp5_mdss->vbif);
 		goto fail;
 	}
 
-	ret = msm_mdss_get_clocks(mdss);
+	ret = msm_mdss_get_clocks(mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to get clocks: %d\n", ret);
 		goto fail;
 	}
 
 	/* Regulator to enable GDSCs in downstream kernels */
-	mdss->vdd = devm_regulator_get(dev->dev, "vdd");
-	if (IS_ERR(mdss->vdd)) {
-		ret = PTR_ERR(mdss->vdd);
+	mdp5_mdss->vdd = devm_regulator_get(dev->dev, "vdd");
+	if (IS_ERR(mdp5_mdss->vdd)) {
+		ret = PTR_ERR(mdp5_mdss->vdd);
 		goto fail;
 	}
 
-	ret = regulator_enable(mdss->vdd);
+	ret = regulator_enable(mdp5_mdss->vdd);
 	if (ret) {
 		dev_err(dev->dev, "failed to enable regulator vdd: %d\n",
 			ret);
@@ -258,25 +265,26 @@ int msm_mdss_init(struct drm_device *dev)
 	}
 
 	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
-			       mdss_irq, 0, "mdss_isr", mdss);
+			       mdss_irq, 0, "mdss_isr", mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to init irq: %d\n", ret);
 		goto fail_irq;
 	}
 
-	ret = mdss_irq_domain_init(mdss);
+	ret = mdss_irq_domain_init(mdp5_mdss);
 	if (ret) {
 		dev_err(dev->dev, "failed to init sub-block irqs: %d\n", ret);
 		goto fail_irq;
 	}
 
-	priv->mdss = mdss;
+	mdp5_mdss->base.funcs = &mdss_funcs;
+	priv->mdss = &mdp5_mdss->base;
 
 	pm_runtime_enable(dev->dev);
 
 	return 0;
 fail_irq:
-	regulator_disable(mdss->vdd);
+	regulator_disable(mdp5_mdss->vdd);
 fail:
 	return ret;
 }
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 7f7321eb5312..2608d3f77956 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -208,6 +208,7 @@ static int msm_drm_uninit(struct device *dev)
 	struct drm_device *ddev = platform_get_drvdata(pdev);
 	struct msm_drm_private *priv = ddev->dev_private;
 	struct msm_kms *kms = priv->kms;
+	struct msm_mdss *mdss = priv->mdss;
 	struct msm_vblank_ctrl *vbl_ctrl = &priv->vblank_ctrl;
 	struct vblank_event *vbl_ev, *tmp;
 
@@ -258,7 +259,8 @@ static int msm_drm_uninit(struct device *dev)
 
 	component_unbind_all(dev, ddev);
 
-	msm_mdss_destroy(ddev);
+	if (mdss && mdss->funcs)
+		mdss->funcs->destroy(ddev);
 
 	ddev->dev_private = NULL;
 	drm_dev_unref(ddev);
@@ -357,6 +359,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	struct drm_device *ddev;
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
+	struct msm_mdss *mdss;
 	int ret;
 
 	ddev = drm_dev_alloc(drv, dev);
@@ -376,13 +379,15 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	ddev->dev_private = priv;
 	priv->dev = ddev;
 
-	ret = msm_mdss_init(ddev);
+	ret = mdp5_mdss_init(ddev);
 	if (ret) {
 		kfree(priv);
 		drm_dev_unref(ddev);
 		return ret;
 	}
 
+	mdss = priv->mdss;
+
 	priv->wq = alloc_ordered_workqueue("msm", 0);
 	priv->atomic_wq = alloc_ordered_workqueue("msm:atomic", 0);
 
@@ -396,7 +401,8 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	/* Bind all our sub-components: */
 	ret = component_bind_all(dev, ddev);
 	if (ret) {
-		msm_mdss_destroy(ddev);
+		if (mdss && mdss->funcs)
+			mdss->funcs->destroy(ddev);
 		kfree(priv);
 		drm_dev_unref(ddev);
 		return ret;
@@ -924,11 +930,12 @@ static int msm_runtime_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_mdss *mdss = priv->mdss;
 
 	DBG("");
 
-	if (priv->mdss)
-		return msm_mdss_disable(priv->mdss);
+	if (mdss && mdss->funcs)
+		return mdss->funcs->disable(mdss);
 
 	return 0;
 }
@@ -937,11 +944,12 @@ static int msm_runtime_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_mdss *mdss = priv->mdss;
 
 	DBG("");
 
-	if (priv->mdss)
-		return msm_mdss_enable(priv->mdss);
+	if (mdss && mdss->funcs)
+		return mdss->funcs->enable(mdss);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index dfd92947de2c..76c14221ffdf 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -86,9 +86,18 @@ static inline void msm_kms_init(struct msm_kms *kms,
 
 struct msm_kms *mdp4_kms_init(struct drm_device *dev);
 struct msm_kms *mdp5_kms_init(struct drm_device *dev);
-int msm_mdss_init(struct drm_device *dev);
-void msm_mdss_destroy(struct drm_device *dev);
-int msm_mdss_enable(struct msm_mdss *mdss);
-int msm_mdss_disable(struct msm_mdss *mdss);
+
+struct msm_mdss_funcs {
+	int (*enable)(struct msm_mdss *mdss);
+	int (*disable)(struct msm_mdss *mdss);
+	void (*destroy)(struct drm_device *dev);
+};
+
+struct msm_mdss {
+	struct drm_device *dev;
+	const struct msm_mdss_funcs *funcs;
+};
+
+int mdp5_mdss_init(struct drm_device *dev);
 
 #endif /* __MSM_KMS_H__ */
-- 
cgit v1.2.3


From bb676df12b5e81cab57d1a212a6e9cfc343875a7 Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Mon, 11 Jun 2018 14:13:20 -0700
Subject: drm/msm: enable zpos normalization

Enable drm core zpos normalization for planes.

Changes in v3:
- None

Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
Reviewed-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_drv.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 2608d3f77956..9c760cee5156 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -439,6 +439,9 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		goto fail;
 	}
 
+	/* Enable normalization of plane zpos */
+	ddev->mode_config.normalize_zpos = true;
+
 	if (kms) {
 		ret = kms->funcs->hw_init(kms);
 		if (ret) {
-- 
cgit v1.2.3


From 2d0b10fc5111bb4a902e9be378496d04c401ab81 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <abhinavk@codeaurora.org>
Date: Thu, 7 Jun 2018 13:50:29 -0700
Subject: drm/msm: higher values of pclk can exceed 32 bits when multiplied by
 a factor

Make the pclk_rate u64 to accommodate higher pixel clock
rates.

Changes in v3:
- Converted pclk_rate to u32 (Archit)
- Rebase on dsi cleanup set in msm-next

Cc: Sibi Sankar <sibis@codeaurora.org>
Cc: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Abhinav Kumar <abhinavk@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index cba42ad05fb3..319501dcc083 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -702,6 +702,7 @@ int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 	u8 lanes = msm_host->lanes;
 	u32 bpp = dsi_get_bpp(msm_host->format);
 	u32 pclk_rate;
+	u64 pclk_bpp;
 	unsigned int esc_mhz, esc_div;
 	unsigned long byte_mhz;
 
@@ -716,13 +717,15 @@ int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 	if (is_dual_dsi)
 		pclk_rate /= 2;
 
+	pclk_bpp = pclk_rate * bpp;
 	if (lanes > 0) {
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
+		do_div(pclk_bpp, (8 * lanes));
 	} else {
 		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
+		do_div(pclk_bpp, 8);
 	}
 	msm_host->pixel_clk_rate = pclk_rate;
+	msm_host->byte_clk_rate = pclk_bpp;
 
 	DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate,
 				msm_host->byte_clk_rate);
-- 
cgit v1.2.3


From 74312fc7343efbfd95fc5e75c5c7547e9f751c22 Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Wed, 27 Jun 2018 15:15:49 -0400
Subject: drm/msm: Clean up dangling atomic_wq

I missed this during the atomic conversion

Changes in v3:
- None

Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_drv.c | 4 ----
 drivers/gpu/drm/msm/msm_drv.h | 1 -
 2 files changed, 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 9c760cee5156..b73acdd52931 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -244,9 +244,6 @@ static int msm_drm_uninit(struct device *dev)
 	flush_workqueue(priv->wq);
 	destroy_workqueue(priv->wq);
 
-	flush_workqueue(priv->atomic_wq);
-	destroy_workqueue(priv->atomic_wq);
-
 	if (kms && kms->funcs)
 		kms->funcs->destroy(kms);
 
@@ -389,7 +386,6 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	mdss = priv->mdss;
 
 	priv->wq = alloc_ordered_workqueue("msm", 0);
-	priv->atomic_wq = alloc_ordered_workqueue("msm:atomic", 0);
 
 	INIT_LIST_HEAD(&priv->inactive_list);
 	INIT_LIST_HEAD(&priv->vblank_ctrl.event_list);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 17cefca1d566..fa0376b0f42b 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -115,7 +115,6 @@ struct msm_drm_private {
 	struct list_head inactive_list;
 
 	struct workqueue_struct *wq;
-	struct workqueue_struct *atomic_wq;
 
 	unsigned int num_planes;
 	struct drm_plane *planes[16];
-- 
cgit v1.2.3


From aaded2e3a1f6b776a5afd7c1168610d51f9a6a15 Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Wed, 27 Jun 2018 14:26:24 -0400
Subject: drm/msm: #define MDP version numbers

Useful for incoming DPU support

Changes in v3:
- None

Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
[seanpaul split this from the dpu megapatch]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_drv.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index b73acdd52931..67816543a0d7 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -267,6 +267,9 @@ static int msm_drm_uninit(struct device *dev)
 	return 0;
 }
 
+#define KMS_MDP4 4
+#define KMS_MDP5 5
+
 static int get_mdp_ver(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -411,11 +414,11 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	msm_gem_shrinker_init(ddev);
 
 	switch (get_mdp_ver(pdev)) {
-	case 4:
+	case KMS_MDP4:
 		kms = mdp4_kms_init(ddev);
 		priv->kms = kms;
 		break;
-	case 5:
+	case KMS_MDP5:
 		kms = mdp5_kms_init(ddev);
 		break;
 	default:
@@ -1162,8 +1165,8 @@ static int msm_pdev_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id dt_match[] = {
-	{ .compatible = "qcom,mdp4", .data = (void *)4 },	/* MDP4 */
-	{ .compatible = "qcom,mdss", .data = (void *)5 },	/* MDP5 MDSS */
+	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
+	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
-- 
cgit v1.2.3


From 77050c3febb1808ed6a0f7e9f0994278f06967ca Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Wed, 27 Jun 2018 14:35:28 -0400
Subject: drm/msm: Use labels for unwinding in the error path

This simplifies cleanup, to make sure nothing drops out in case of
error.

Changes in v3:
- None

Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
[seanpaul split out of dpu megapatch and renamed labels]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_drv.c | 44 +++++++++++++++++++++----------------------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 67816543a0d7..8bd9fe831968 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -372,19 +372,16 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
-		drm_dev_unref(ddev);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto err_unref_drm_dev;
 	}
 
 	ddev->dev_private = priv;
 	priv->dev = ddev;
 
 	ret = mdp5_mdss_init(ddev);
-	if (ret) {
-		kfree(priv);
-		drm_dev_unref(ddev);
-		return ret;
-	}
+	if (ret)
+		goto err_free_priv;
 
 	mdss = priv->mdss;
 
@@ -399,17 +396,12 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	/* Bind all our sub-components: */
 	ret = component_bind_all(dev, ddev);
-	if (ret) {
-		if (mdss && mdss->funcs)
-			mdss->funcs->destroy(ddev);
-		kfree(priv);
-		drm_dev_unref(ddev);
-		return ret;
-	}
+	if (ret)
+		goto err_destroy_mdss;
 
 	ret = msm_init_vram(ddev);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	msm_gem_shrinker_init(ddev);
 
@@ -435,7 +427,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		 */
 		dev_err(dev, "failed to load kms\n");
 		ret = PTR_ERR(kms);
-		goto fail;
+		goto err_msm_uninit;
 	}
 
 	/* Enable normalization of plane zpos */
@@ -445,7 +437,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		ret = kms->funcs->hw_init(kms);
 		if (ret) {
 			dev_err(dev, "kms hw init failed: %d\n", ret);
-			goto fail;
+			goto err_msm_uninit;
 		}
 	}
 
@@ -455,7 +447,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	ret = drm_vblank_init(ddev, priv->num_crtcs);
 	if (ret < 0) {
 		dev_err(dev, "failed to initialize vblank\n");
-		goto fail;
+		goto err_msm_uninit;
 	}
 
 	if (kms) {
@@ -464,13 +456,13 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 		pm_runtime_put_sync(dev);
 		if (ret < 0) {
 			dev_err(dev, "failed to install IRQ handler\n");
-			goto fail;
+			goto err_msm_uninit;
 		}
 	}
 
 	ret = drm_dev_register(ddev, 0);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	drm_mode_config_reset(ddev);
 
@@ -481,15 +473,23 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	ret = msm_debugfs_late_init(ddev);
 	if (ret)
-		goto fail;
+		goto err_msm_uninit;
 
 	drm_kms_helper_poll_init(ddev);
 
 	return 0;
 
-fail:
+err_msm_uninit:
 	msm_drm_uninit(dev);
 	return ret;
+err_destroy_mdss:
+	if (mdss && mdss->funcs)
+		mdss->funcs->destroy(ddev);
+err_free_priv:
+	kfree(priv);
+err_unref_drm_dev:
+	drm_dev_unref(ddev);
+	return ret;
 }
 
 /*
-- 
cgit v1.2.3


From 7305a0ceec78f34ce328845cdd6980d8eda99485 Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Wed, 27 Jun 2018 14:55:25 -0400
Subject: drm/msm: #define MAX_<OBJECT> in msm_drv.h

dpu uses these elsewhere in the driver (in addition to increasing
MAX_PLANES, that'll come later), so pull them out into #define.

Changes in v3:
- None

Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
[seanpaul pulled this out of the dpu megapatch]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_drv.h | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index fa0376b0f42b..3b206ae6423f 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -54,6 +54,12 @@ struct msm_fence_context;
 struct msm_gem_address_space;
 struct msm_gem_vma;
 
+#define MAX_CRTCS      8
+#define MAX_PLANES     16
+#define MAX_ENCODERS   8
+#define MAX_BRIDGES    8
+#define MAX_CONNECTORS 8
+
 struct msm_file_private {
 	rwlock_t queuelock;
 	struct list_head submitqueues;
@@ -117,19 +123,19 @@ struct msm_drm_private {
 	struct workqueue_struct *wq;
 
 	unsigned int num_planes;
-	struct drm_plane *planes[16];
+	struct drm_plane *planes[MAX_PLANES];
 
 	unsigned int num_crtcs;
-	struct drm_crtc *crtcs[8];
+	struct drm_crtc *crtcs[MAX_CRTCS];
 
 	unsigned int num_encoders;
-	struct drm_encoder *encoders[8];
+	struct drm_encoder *encoders[MAX_ENCODERS];
 
 	unsigned int num_bridges;
-	struct drm_bridge *bridges[8];
+	struct drm_bridge *bridges[MAX_BRIDGES];
 
 	unsigned int num_connectors;
-	struct drm_connector *connectors[8];
+	struct drm_connector *connectors[MAX_CONNECTORS];
 
 	/* Properties */
 	struct drm_property *plane_property[PLANE_PROP_MAX_NUM];
-- 
cgit v1.2.3


From 2b7ac1a8989829b085fae9750817ca3304047c04 Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Wed, 27 Jun 2018 13:49:23 -0400
Subject: drm/msm: Add .commit() callback to msm_kms functions

Called right before wait_for_commit_done() to perform kickoff for
active crtcs.

Changes in v3:
- None

Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
[seanpaul split this out of the megapatch]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_atomic.c | 5 +++++
 drivers/gpu/drm/msm/msm_kms.h    | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index e6f1e25c60af..c1f1779c980f 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -71,6 +71,11 @@ void msm_atomic_commit_tail(struct drm_atomic_state *state)
 
 	drm_atomic_helper_commit_modeset_enables(dev, state);
 
+	if (kms->funcs->commit) {
+		DRM_DEBUG_ATOMIC("triggering commit\n");
+		kms->funcs->commit(kms, state);
+	}
+
 	msm_atomic_wait_for_commit_done(dev, state);
 
 	kms->funcs->complete_commit(kms, state);
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 76c14221ffdf..761bb07cd7bf 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -42,6 +42,7 @@ struct msm_kms_funcs {
 	void (*disable_vblank)(struct msm_kms *kms, struct drm_crtc *crtc);
 	/* modeset, bracketing atomic_commit(): */
 	void (*prepare_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
+	void (*commit)(struct msm_kms *kms, struct drm_atomic_state *state);
 	void (*complete_commit)(struct msm_kms *kms, struct drm_atomic_state *state);
 	/* functions to wait for atomic commit completed on each CRTC */
 	void (*wait_for_crtc_commit_done)(struct msm_kms *kms,
-- 
cgit v1.2.3


From 036bfeb33b89578ab924fa198213260659e08dc8 Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Wed, 27 Jun 2018 15:24:17 -0400
Subject: drm/msm: Add pm_suspend/resume callbacks to msm_kms

Used by the dpu driver for custom suspend/resume.

Changes in v3:
- None

Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
[seanpaul split this out of the megapatch]
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_drv.c | 10 ++++++++++
 drivers/gpu/drm/msm/msm_kms.h |  3 +++
 2 files changed, 13 insertions(+)

diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index 8bd9fe831968..e79ad74ca98c 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -903,6 +903,11 @@ static int msm_pm_suspend(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	/* TODO: Use atomic helper suspend/resume */
+	if (kms && kms->funcs && kms->funcs->pm_suspend)
+		return kms->funcs->pm_suspend(dev);
 
 	drm_kms_helper_poll_disable(ddev);
 
@@ -919,6 +924,11 @@ static int msm_pm_resume(struct device *dev)
 {
 	struct drm_device *ddev = dev_get_drvdata(dev);
 	struct msm_drm_private *priv = ddev->dev_private;
+	struct msm_kms *kms = priv->kms;
+
+	/* TODO: Use atomic helper suspend/resume */
+	if (kms && kms->funcs && kms->funcs->pm_resume)
+		return kms->funcs->pm_resume(dev);
 
 	drm_atomic_helper_resume(ddev, priv->pm_state);
 	drm_kms_helper_poll_enable(ddev);
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index 761bb07cd7bf..c15de28ae2dd 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -61,6 +61,9 @@ struct msm_kms_funcs {
 	void (*set_encoder_mode)(struct msm_kms *kms,
 				 struct drm_encoder *encoder,
 				 bool cmd_mode);
+	/* pm suspend/resume hooks */
+	int (*pm_suspend)(struct device *dev);
+	int (*pm_resume)(struct device *dev);
 	/* cleanup: */
 	void (*destroy)(struct msm_kms *kms);
 #ifdef CONFIG_DEBUG_FS
-- 
cgit v1.2.3


From 516ddd79068dc02b9101bf9551a9ef7dce217b5b Mon Sep 17 00:00:00 2001
From: Tiago Brusamarello <tiago.brusamarello@datacom.ind.br>
Date: Thu, 26 Jul 2018 11:12:11 -0300
Subject: spi: spi-fsl-espi: Log fifo counters on error

Log RX and TX fifo counters when a transfer is done and these are not
zero.

Signed-off-by: Tiago Brusamarello <tiago.brusamarello@datacom.ind.br>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-fsl-espi.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-fsl-espi.c b/drivers/spi/spi-fsl-espi.c
index 1d332e23f6ed..1e8ff6256079 100644
--- a/drivers/spi/spi-fsl-espi.c
+++ b/drivers/spi/spi-fsl-espi.c
@@ -547,8 +547,11 @@ static void fsl_espi_cpu_irq(struct fsl_espi *espi, u32 events)
 		dev_err(espi->dev,
 			"Transfer done but SPIE_DON isn't set!\n");
 
-	if (SPIE_RXCNT(events) || SPIE_TXCNT(events) != FSL_ESPI_FIFO_SIZE)
+	if (SPIE_RXCNT(events) || SPIE_TXCNT(events) != FSL_ESPI_FIFO_SIZE) {
 		dev_err(espi->dev, "Transfer done but rx/tx fifo's aren't empty!\n");
+		dev_err(espi->dev, "SPIE_RXCNT = %d, SPIE_TXCNT = %d\n",
+			SPIE_RXCNT(events), SPIE_TXCNT(events));
+	}
 
 	complete(&espi->done);
 }
-- 
cgit v1.2.3


From 25fdd5933e4c0f5fe2ea5cd59994f8ac5fbe90ef Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Wed, 27 Jun 2018 15:26:09 -0400
Subject: drm/msm: Add SDM845 DPU support

SDM845 SoC includes the Mobile Display Sub System (MDSS) which is a
top level wrapper consisting of Display Processing Unit (DPU) and
display peripheral modules such as Display Serial Interface (DSI)
and DisplayPort (DP).

MDSS functions essentially as a back-end composition engine. It blends
video and graphic images stored in the frame buffers and scans out the
composed image to a display sink (over DSI/DP).

The following diagram represents hardware blocks for a simple pipeline
(two planes are present on a given crtc which is connected to a DSI
connector):

       MDSS
      +---------------------------------+
      | +-----------------------------+ |
      | | DPU                         | |
      | |  +--------+  +--------+     | |
      | |  |  SSPP  |  |  SSPP  |     | |
      | |  +----+---+  +----+---+     | |
      | |       |           |         | |
      | |  +----v-----------v---+     | |
      | |  |  Layer Mixer (LM)  |     | |
      | |  +--------------------+     | |
      | |  +--------------------+     | |
      | |  |    PingPong (PP)   |     | |
      | |  +--------------------+     | |
      | |  +--------------------+     | |
      | |  |  INTERFACE (VIDEO) |     | |
      | |  +---+----------------+     | |
      | +------|----------------------+ |
      |        |                        |
      | +------|---------------------+  |
      | |      | DISPLAY PERIPHERALS |  |
      | |  +---v-+      +-----+      |  |
      | |  | DSI |      |  DP |      |  |
      | |  +-----+      +-----+      |  |
      | +----------------------------+  |
      +---------------------------------+

The number of DPU sub-blocks (i.e. SSPPs, LMs, PP blocks and INTFs)
depends on SoC capabilities.

Overview of DPU sub-blocks:
---------------------------
* Source Surface Processor (SSPP):
 Refers to any of hardware pipes like ViG, DMA etc. Only ViG pipes are
 capable of performing format conversion, scaling and quality improvement
 for source surfaces.

* Layer Mixer (LM):
 Blend source surfaces together (in requested zorder)

* PingPong (PP):
 This block controls frame done interrupt output, EOL and EOF generation,
 overflow/underflow control.

* Display interface (INTF):
 Timing generator and interface connecting the display peripherals.

DRM components mapping to DPU architecture:
------------------------------------------
PLANEs maps to SSPPs
CRTC maps to LMs
Encoder maps to PPs, INTFs

Data flow setup:
---------------
MDSS hardware can support various data flows (e.g.):
  - Dual pipe: Output from two LMs combined to single display.
  - Split display: Output from two LMs connected to two separate
                   interfaces.

The hardware capabilities determine the number of concurrent data paths
possible. Any control path (i.e. pipeline w/i DPU) can be routed to any
of the hardware data paths. A given control path can be triggered,
flushed and controlled independently.

Changes in v3:
- Move msm_media_info.h from uapi to dpu/ subdir
- Remove preclose callback dpu (it's handled in core)
- Fix kbuild warnings with parent_ops
- Remove unused functions from dpu_core_irq
- Rename mdss_phys to mdss
- Rename mdp_phys address space to mdp
- Drop _phys from vbif and regdma binding names

Signed-off-by: Abhinav Kumar <abhinavk@codeaurora.org>
Signed-off-by: Archit Taneja <architt@codeaurora.org>
Signed-off-by: Chandan Uddaraju <chandanu@codeaurora.org>
Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rajesh Yadav <ryadav@codeaurora.org>
Signed-off-by: Sravanthi Kollukuduru <skolluku@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
[robclark minor rebase]
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/Makefile                       |   32 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c       |  479 ++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h       |  153 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c      |  637 +++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h      |  133 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c           | 2504 +++++++++++++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h           |  484 ++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c            | 2393 ++++++++++++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h            |  103 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c        | 2575 ++++++++++++++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h        |  191 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h   |  453 ++++
 .../gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c   |  905 +++++++
 .../gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c   |  922 +++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c        | 1214 +++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h        |  136 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c         |  155 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h         |   53 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c     |  511 ++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h     |  804 ++++++
 .../gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h  |  168 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c         |  323 +++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h         |  139 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c         |  540 ++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h         |  218 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c  | 1183 +++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h  |  257 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c        |  349 +++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h        |  128 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c          |  261 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h          |  122 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h        |  465 ++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c    |  250 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h    |  136 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c        |  753 ++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h        |  424 ++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c         |  398 +++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h         |  202 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c        |  452 ++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h        |  358 +++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c        |  275 +++
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h        |  128 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h           |   56 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c        |  204 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h        |   57 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c            |   66 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h            |   59 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c            | 1345 ++++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h            |  402 +++
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c      |  153 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c           |  245 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c          | 1963 +++++++++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h          |  175 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c   |  249 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h   |  225 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c             | 1079 ++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h             |  199 ++
 drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h          | 1007 ++++++++
 drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c           |  384 +++
 drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h           |   94 +
 drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h     | 1376 +++++++++++
 drivers/gpu/drm/msm/msm_drv.c                      |  135 +-
 drivers/gpu/drm/msm/msm_drv.h                      |   81 +-
 drivers/gpu/drm/msm/msm_kms.h                      |    8 +
 64 files changed, 31913 insertions(+), 15 deletions(-)
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
 create mode 100644 drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h

diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index cd40c050b2d7..1639ea8c0d13 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -1,5 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 ccflags-y := -Idrivers/gpu/drm/msm
+ccflags-y += -Idrivers/gpu/drm/msm/disp/dpu1
 ccflags-$(CONFIG_DRM_MSM_DSI) += -Idrivers/gpu/drm/msm/dsi
 
 msm-y := \
@@ -45,6 +46,34 @@ msm-y := \
 	disp/mdp5/mdp5_mixer.o \
 	disp/mdp5/mdp5_plane.o \
 	disp/mdp5/mdp5_smp.o \
+	disp/dpu1/dpu_core_irq.o \
+	disp/dpu1/dpu_core_perf.o \
+	disp/dpu1/dpu_crtc.o \
+	disp/dpu1/dpu_encoder.o \
+	disp/dpu1/dpu_encoder_phys_cmd.o \
+	disp/dpu1/dpu_encoder_phys_vid.o \
+	disp/dpu1/dpu_formats.o \
+	disp/dpu1/dpu_hw_blk.o \
+	disp/dpu1/dpu_hw_catalog.o \
+	disp/dpu1/dpu_hw_cdm.o \
+	disp/dpu1/dpu_hw_ctl.o \
+	disp/dpu1/dpu_hw_interrupts.o \
+	disp/dpu1/dpu_hw_intf.o \
+	disp/dpu1/dpu_hw_lm.o \
+	disp/dpu1/dpu_hw_pingpong.o \
+	disp/dpu1/dpu_hw_sspp.o \
+	disp/dpu1/dpu_hw_top.o \
+	disp/dpu1/dpu_hw_util.o \
+	disp/dpu1/dpu_hw_vbif.o \
+	disp/dpu1/dpu_io_util.o \
+	disp/dpu1/dpu_irq.o \
+	disp/dpu1/dpu_kms.o \
+	disp/dpu1/dpu_kms_utils.o \
+	disp/dpu1/dpu_mdss.o \
+	disp/dpu1/dpu_plane.o \
+	disp/dpu1/dpu_power_handle.o \
+	disp/dpu1/dpu_rm.o \
+	disp/dpu1/dpu_vbif.o \
 	msm_atomic.o \
 	msm_debugfs.o \
 	msm_drv.o \
@@ -62,7 +91,8 @@ msm-y := \
 	msm_ringbuffer.o \
 	msm_submitqueue.o
 
-msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o
+msm-$(CONFIG_DEBUG_FS) += adreno/a5xx_debugfs.o \
+			  disp/dpu1/dpu_dbg.o
 
 msm-$(CONFIG_DRM_FBDEV_EMULATION) += msm_fbdev.o
 msm-$(CONFIG_COMMON_CLK) += disp/mdp4/mdp4_lvds_pll.o
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
new file mode 100644
index 000000000000..879c13fe74e0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.c
@@ -0,0 +1,479 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kthread.h>
+
+#include "dpu_core_irq.h"
+#include "dpu_trace.h"
+
+/**
+ * dpu_core_irq_callback_handler - dispatch core interrupts
+ * @arg:		private data of callback handler
+ * @irq_idx:		interrupt index
+ */
+static void dpu_core_irq_callback_handler(void *arg, int irq_idx)
+{
+	struct dpu_kms *dpu_kms = arg;
+	struct dpu_irq *irq_obj = &dpu_kms->irq_obj;
+	struct dpu_irq_callback *cb;
+	unsigned long irq_flags;
+
+	pr_debug("irq_idx=%d\n", irq_idx);
+
+	if (list_empty(&irq_obj->irq_cb_tbl[irq_idx])) {
+		DRM_ERROR("no registered cb, idx:%d enable_count:%d\n", irq_idx,
+			atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]));
+	}
+
+	atomic_inc(&irq_obj->irq_counts[irq_idx]);
+
+	/*
+	 * Perform registered function callback
+	 */
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	list_for_each_entry(cb, &irq_obj->irq_cb_tbl[irq_idx], list)
+		if (cb->func)
+			cb->func(cb->arg, irq_idx);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	/*
+	 * Clear pending interrupt status in HW.
+	 * NOTE: dpu_core_irq_callback_handler is protected by top-level
+	 *       spinlock, so it is safe to clear any interrupt status here.
+	 */
+	dpu_kms->hw_intr->ops.clear_intr_status_nolock(
+			dpu_kms->hw_intr,
+			irq_idx);
+}
+
+int dpu_core_irq_idx_lookup(struct dpu_kms *dpu_kms,
+		enum dpu_intr_type intr_type, u32 instance_idx)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.irq_idx_lookup)
+		return -EINVAL;
+
+	return dpu_kms->hw_intr->ops.irq_idx_lookup(intr_type,
+			instance_idx);
+}
+
+/**
+ * _dpu_core_irq_enable - enable core interrupt given by the index
+ * @dpu_kms:		Pointer to dpu kms context
+ * @irq_idx:		interrupt index
+ */
+static int _dpu_core_irq_enable(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	unsigned long irq_flags;
+	int ret = 0, enable_count;
+
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->irq_obj.enable_counts ||
+			!dpu_kms->irq_obj.irq_counts) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]);
+	DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count);
+	trace_dpu_core_irq_enable_idx(irq_idx, enable_count);
+
+	if (atomic_inc_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 1) {
+		ret = dpu_kms->hw_intr->ops.enable_irq(
+				dpu_kms->hw_intr,
+				irq_idx);
+		if (ret)
+			DPU_ERROR("Fail to enable IRQ for irq_idx:%d\n",
+					irq_idx);
+
+		DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret);
+
+		spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+		/* empty callback list but interrupt is enabled */
+		if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]))
+			DPU_ERROR("irq_idx=%d enabled with no callback\n",
+					irq_idx);
+		spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	}
+
+	return ret;
+}
+
+int dpu_core_irq_enable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
+{
+	int i, ret = 0, counts;
+
+	if (!dpu_kms || !irq_idxs || !irq_count) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]);
+	if (counts)
+		DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts);
+
+	for (i = 0; (i < irq_count) && !ret; i++)
+		ret = _dpu_core_irq_enable(dpu_kms, irq_idxs[i]);
+
+	return ret;
+}
+
+/**
+ * _dpu_core_irq_disable - disable core interrupt given by the index
+ * @dpu_kms:		Pointer to dpu kms context
+ * @irq_idx:		interrupt index
+ */
+static int _dpu_core_irq_disable(struct dpu_kms *dpu_kms, int irq_idx)
+{
+	int ret = 0, enable_count;
+
+	if (!dpu_kms || !dpu_kms->hw_intr || !dpu_kms->irq_obj.enable_counts) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	enable_count = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]);
+	DRM_DEBUG_KMS("irq_idx=%d enable_count=%d\n", irq_idx, enable_count);
+	trace_dpu_core_irq_disable_idx(irq_idx, enable_count);
+
+	if (atomic_dec_return(&dpu_kms->irq_obj.enable_counts[irq_idx]) == 0) {
+		ret = dpu_kms->hw_intr->ops.disable_irq(
+				dpu_kms->hw_intr,
+				irq_idx);
+		if (ret)
+			DPU_ERROR("Fail to disable IRQ for irq_idx:%d\n",
+					irq_idx);
+		DPU_DEBUG("irq_idx=%d ret=%d\n", irq_idx, ret);
+	}
+
+	return ret;
+}
+
+int dpu_core_irq_disable(struct dpu_kms *dpu_kms, int *irq_idxs, u32 irq_count)
+{
+	int i, ret = 0, counts;
+
+	if (!dpu_kms || !irq_idxs || !irq_count) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	counts = atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idxs[0]]);
+	if (counts == 2)
+		DRM_ERROR("irq_idx=%d enable_count=%d\n", irq_idxs[0], counts);
+
+	for (i = 0; (i < irq_count) && !ret; i++)
+		ret = _dpu_core_irq_disable(dpu_kms, irq_idxs[i]);
+
+	return ret;
+}
+
+u32 dpu_core_irq_read(struct dpu_kms *dpu_kms, int irq_idx, bool clear)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.get_interrupt_status)
+		return 0;
+
+	if (irq_idx < 0) {
+		DPU_ERROR("[%pS] invalid irq_idx=%d\n",
+				__builtin_return_address(0), irq_idx);
+		return 0;
+	}
+
+	return dpu_kms->hw_intr->ops.get_interrupt_status(dpu_kms->hw_intr,
+			irq_idx, clear);
+}
+
+int dpu_core_irq_register_callback(struct dpu_kms *dpu_kms, int irq_idx,
+		struct dpu_irq_callback *register_irq_cb)
+{
+	unsigned long irq_flags;
+
+	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (!register_irq_cb || !register_irq_cb->func) {
+		DPU_ERROR("invalid irq_cb:%d func:%d\n",
+				register_irq_cb != NULL,
+				register_irq_cb ?
+					register_irq_cb->func != NULL : -1);
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	trace_dpu_core_irq_register_callback(irq_idx, register_irq_cb);
+	list_del_init(&register_irq_cb->list);
+	list_add_tail(&register_irq_cb->list,
+			&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	return 0;
+}
+
+int dpu_core_irq_unregister_callback(struct dpu_kms *dpu_kms, int irq_idx,
+		struct dpu_irq_callback *register_irq_cb)
+{
+	unsigned long irq_flags;
+
+	if (!dpu_kms || !dpu_kms->irq_obj.irq_cb_tbl) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+
+	if (!register_irq_cb || !register_irq_cb->func) {
+		DPU_ERROR("invalid irq_cb:%d func:%d\n",
+				register_irq_cb != NULL,
+				register_irq_cb ?
+					register_irq_cb->func != NULL : -1);
+		return -EINVAL;
+	}
+
+	if (irq_idx < 0 || irq_idx >= dpu_kms->hw_intr->irq_idx_tbl_size) {
+		DPU_ERROR("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	DPU_DEBUG("[%pS] irq_idx=%d\n", __builtin_return_address(0), irq_idx);
+
+	spin_lock_irqsave(&dpu_kms->irq_obj.cb_lock, irq_flags);
+	trace_dpu_core_irq_unregister_callback(irq_idx, register_irq_cb);
+	list_del_init(&register_irq_cb->list);
+	/* empty callback list but interrupt is still enabled */
+	if (list_empty(&dpu_kms->irq_obj.irq_cb_tbl[irq_idx]) &&
+			atomic_read(&dpu_kms->irq_obj.enable_counts[irq_idx]))
+		DPU_ERROR("irq_idx=%d enabled with no callback\n", irq_idx);
+	spin_unlock_irqrestore(&dpu_kms->irq_obj.cb_lock, irq_flags);
+
+	return 0;
+}
+
+static void dpu_clear_all_irqs(struct dpu_kms *dpu_kms)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.clear_all_irqs)
+		return;
+
+	dpu_kms->hw_intr->ops.clear_all_irqs(dpu_kms->hw_intr);
+}
+
+static void dpu_disable_all_irqs(struct dpu_kms *dpu_kms)
+{
+	if (!dpu_kms || !dpu_kms->hw_intr ||
+			!dpu_kms->hw_intr->ops.disable_all_irqs)
+		return;
+
+	dpu_kms->hw_intr->ops.disable_all_irqs(dpu_kms->hw_intr);
+}
+
+#ifdef CONFIG_DEBUG_FS
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)				\
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_debugfs_core_irq_show(struct seq_file *s, void *v)
+{
+	struct dpu_irq *irq_obj = s->private;
+	struct dpu_irq_callback *cb;
+	unsigned long irq_flags;
+	int i, irq_count, enable_count, cb_count;
+
+	if (!irq_obj || !irq_obj->enable_counts || !irq_obj->irq_cb_tbl) {
+		DPU_ERROR("invalid parameters\n");
+		return 0;
+	}
+
+	for (i = 0; i < irq_obj->total_irqs; i++) {
+		spin_lock_irqsave(&irq_obj->cb_lock, irq_flags);
+		cb_count = 0;
+		irq_count = atomic_read(&irq_obj->irq_counts[i]);
+		enable_count = atomic_read(&irq_obj->enable_counts[i]);
+		list_for_each_entry(cb, &irq_obj->irq_cb_tbl[i], list)
+			cb_count++;
+		spin_unlock_irqrestore(&irq_obj->cb_lock, irq_flags);
+
+		if (irq_count || enable_count || cb_count)
+			seq_printf(s, "idx:%d irq:%d enable:%d cb:%d\n",
+					i, irq_count, enable_count, cb_count);
+	}
+
+	return 0;
+}
+
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_core_irq);
+
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	dpu_kms->irq_obj.debugfs_file = debugfs_create_file("core_irq", 0600,
+			parent, &dpu_kms->irq_obj,
+			&dpu_debugfs_core_irq_fops);
+
+	return 0;
+}
+
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove(dpu_kms->irq_obj.debugfs_file);
+	dpu_kms->irq_obj.debugfs_file = NULL;
+}
+
+#else
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	return 0;
+}
+
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+
+void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid drm device\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	dpu_clear_all_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	spin_lock_init(&dpu_kms->irq_obj.cb_lock);
+
+	/* Create irq callbacks for all possible irq_idx */
+	dpu_kms->irq_obj.total_irqs = dpu_kms->hw_intr->irq_idx_tbl_size;
+	dpu_kms->irq_obj.irq_cb_tbl = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(struct list_head), GFP_KERNEL);
+	dpu_kms->irq_obj.enable_counts = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(atomic_t), GFP_KERNEL);
+	dpu_kms->irq_obj.irq_counts = kcalloc(dpu_kms->irq_obj.total_irqs,
+			sizeof(atomic_t), GFP_KERNEL);
+	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++) {
+		INIT_LIST_HEAD(&dpu_kms->irq_obj.irq_cb_tbl[i]);
+		atomic_set(&dpu_kms->irq_obj.enable_counts[i], 0);
+		atomic_set(&dpu_kms->irq_obj.irq_counts[i], 0);
+	}
+}
+
+int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms)
+{
+	return 0;
+}
+
+void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid drm device\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	for (i = 0; i < dpu_kms->irq_obj.total_irqs; i++)
+		if (atomic_read(&dpu_kms->irq_obj.enable_counts[i]) ||
+				!list_empty(&dpu_kms->irq_obj.irq_cb_tbl[i]))
+			DPU_ERROR("irq_idx=%d still enabled/registered\n", i);
+
+	dpu_clear_all_irqs(dpu_kms);
+	dpu_disable_all_irqs(dpu_kms);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	kfree(dpu_kms->irq_obj.irq_cb_tbl);
+	kfree(dpu_kms->irq_obj.enable_counts);
+	kfree(dpu_kms->irq_obj.irq_counts);
+	dpu_kms->irq_obj.irq_cb_tbl = NULL;
+	dpu_kms->irq_obj.enable_counts = NULL;
+	dpu_kms->irq_obj.irq_counts = NULL;
+	dpu_kms->irq_obj.total_irqs = 0;
+}
+
+irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms)
+{
+	/*
+	 * Read interrupt status from all sources. Interrupt status are
+	 * stored within hw_intr.
+	 * Function will also clear the interrupt status after reading.
+	 * Individual interrupt status bit will only get stored if it
+	 * is enabled.
+	 */
+	dpu_kms->hw_intr->ops.get_interrupt_statuses(dpu_kms->hw_intr);
+
+	/*
+	 * Dispatch to HW driver to handle interrupt lookup that is being
+	 * fired. When matching interrupt is located, HW driver will call to
+	 * dpu_core_irq_callback_handler with the irq_idx from the lookup table.
+	 * dpu_core_irq_callback_handler will perform the registered function
+	 * callback, and do the interrupt status clearing once the registered
+	 * callback is finished.
+	 */
+	dpu_kms->hw_intr->ops.dispatch_irqs(
+			dpu_kms->hw_intr,
+			dpu_core_irq_callback_handler,
+			dpu_kms);
+
+	return IRQ_HANDLED;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
new file mode 100644
index 000000000000..5e98bba46af5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_irq.h
@@ -0,0 +1,153 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_CORE_IRQ_H__
+#define __DPU_CORE_IRQ_H__
+
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+
+/**
+ * dpu_core_irq_preinstall - perform pre-installation of core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		none
+ */
+void dpu_core_irq_preinstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_postinstall - perform post-installation of core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		0 if success; error code otherwise
+ */
+int dpu_core_irq_postinstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_uninstall - uninstall core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		none
+ */
+void dpu_core_irq_uninstall(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq - core IRQ handler
+ * @dpu_kms:		DPU handle
+ * @return:		interrupt handling status
+ */
+irqreturn_t dpu_core_irq(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_core_irq_idx_lookup - IRQ helper function for lookup irq_idx from HW
+ *                      interrupt mapping table.
+ * @dpu_kms:		DPU handle
+ * @intr_type:		DPU HW interrupt type for lookup
+ * @instance_idx:	DPU HW block instance defined in dpu_hw_mdss.h
+ * @return:		irq_idx or -EINVAL when fail to lookup
+ */
+int dpu_core_irq_idx_lookup(
+		struct dpu_kms *dpu_kms,
+		enum dpu_intr_type intr_type,
+		uint32_t instance_idx);
+
+/**
+ * dpu_core_irq_enable - IRQ helper function for enabling one or more IRQs
+ * @dpu_kms:		DPU handle
+ * @irq_idxs:		Array of irq index
+ * @irq_count:		Number of irq_idx provided in the array
+ * @return:		0 for success enabling IRQ, otherwise failure
+ *
+ * This function increments count on each enable and decrements on each
+ * disable.  Interrupts is enabled if count is 0 before increment.
+ */
+int dpu_core_irq_enable(
+		struct dpu_kms *dpu_kms,
+		int *irq_idxs,
+		uint32_t irq_count);
+
+/**
+ * dpu_core_irq_disable - IRQ helper function for disabling one of more IRQs
+ * @dpu_kms:		DPU handle
+ * @irq_idxs:		Array of irq index
+ * @irq_count:		Number of irq_idx provided in the array
+ * @return:		0 for success disabling IRQ, otherwise failure
+ *
+ * This function increments count on each enable and decrements on each
+ * disable.  Interrupts is disabled if count is 0 after decrement.
+ */
+int dpu_core_irq_disable(
+		struct dpu_kms *dpu_kms,
+		int *irq_idxs,
+		uint32_t irq_count);
+
+/**
+ * dpu_core_irq_read - IRQ helper function for reading IRQ status
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @clear:		True to clear the irq after read
+ * @return:		non-zero if irq detected; otherwise no irq detected
+ */
+u32 dpu_core_irq_read(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		bool clear);
+
+/**
+ * dpu_core_irq_register_callback - For registering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @irq_cb:		IRQ callback structure, containing callback function
+ *			and argument. Passing NULL for irq_cb will unregister
+ *			the callback for the given irq_idx
+ *			This must exist until un-registration.
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_register_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		struct dpu_irq_callback *irq_cb);
+
+/**
+ * dpu_core_irq_unregister_callback - For unregistering callback function on IRQ
+ *                             interrupt
+ * @dpu_kms:		DPU handle
+ * @irq_idx:		irq index
+ * @irq_cb:		IRQ callback structure, containing callback function
+ *			and argument. Passing NULL for irq_cb will unregister
+ *			the callback for the given irq_idx
+ *			This must match with registration.
+ * @return:		0 for success registering callback, otherwise failure
+ *
+ * This function supports registration of multiple callbacks for each interrupt.
+ */
+int dpu_core_irq_unregister_callback(
+		struct dpu_kms *dpu_kms,
+		int irq_idx,
+		struct dpu_irq_callback *irq_cb);
+
+/**
+ * dpu_debugfs_core_irq_init - register core irq debugfs
+ * @dpu_kms: pointer to kms
+ * @parent: debugfs directory root
+ * @Return: 0 on success
+ */
+int dpu_debugfs_core_irq_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent);
+
+/**
+ * dpu_debugfs_core_irq_destroy - deregister core irq debugfs
+ * @dpu_kms: pointer to kms
+ */
+void dpu_debugfs_core_irq_destroy(struct dpu_kms *dpu_kms);
+
+#endif /* __DPU_CORE_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
new file mode 100644
index 000000000000..41c5191f9056
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.c
@@ -0,0 +1,637 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/sort.h>
+#include <linux/clk.h>
+#include <linux/bitmap.h>
+
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_core_perf.h"
+
+#define DPU_PERF_MODE_STRING_SIZE	128
+
+/**
+ * enum dpu_perf_mode - performance tuning mode
+ * @DPU_PERF_MODE_NORMAL: performance controlled by user mode client
+ * @DPU_PERF_MODE_MINIMUM: performance bounded by minimum setting
+ * @DPU_PERF_MODE_FIXED: performance bounded by fixed setting
+ */
+enum dpu_perf_mode {
+	DPU_PERF_MODE_NORMAL,
+	DPU_PERF_MODE_MINIMUM,
+	DPU_PERF_MODE_FIXED,
+	DPU_PERF_MODE_MAX
+};
+
+static struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv;
+
+	if (!crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid device\n");
+		return NULL;
+	}
+
+	priv = crtc->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return NULL;
+	}
+
+	return to_dpu_kms(priv->kms);
+}
+
+static bool _dpu_core_perf_crtc_is_power_on(struct drm_crtc *crtc)
+{
+	return dpu_crtc_is_enabled(crtc);
+}
+
+static bool _dpu_core_video_mode_intf_connected(struct drm_crtc *crtc)
+{
+	struct drm_crtc *tmp_crtc;
+	bool intf_connected = false;
+
+	if (!crtc)
+		goto end;
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if ((dpu_crtc_get_intf_mode(tmp_crtc) == INTF_MODE_VIDEO) &&
+				_dpu_core_perf_crtc_is_power_on(tmp_crtc)) {
+			DPU_DEBUG("video interface connected crtc:%d\n",
+				tmp_crtc->base.id);
+			intf_connected = true;
+			goto end;
+		}
+	}
+
+end:
+	return intf_connected;
+}
+
+static void _dpu_core_perf_calc_crtc(struct dpu_kms *kms,
+		struct drm_crtc *crtc,
+		struct drm_crtc_state *state,
+		struct dpu_core_perf_params *perf)
+{
+	struct dpu_crtc_state *dpu_cstate;
+	int i;
+
+	if (!kms || !kms->catalog || !crtc || !state || !perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_cstate = to_dpu_crtc_state(state);
+	memset(perf, 0, sizeof(struct dpu_core_perf_params));
+
+	if (!dpu_cstate->bw_control) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = kms->catalog->perf.max_bw_high *
+					1000ULL;
+			perf->max_per_pipe_ib[i] = perf->bw_ctl[i];
+		}
+		perf->core_clk_rate = kms->perf.max_core_clk_rate;
+	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_MINIMUM) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = 0;
+			perf->max_per_pipe_ib[i] = 0;
+		}
+		perf->core_clk_rate = 0;
+	} else if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			perf->bw_ctl[i] = kms->perf.fix_core_ab_vote;
+			perf->max_per_pipe_ib[i] = kms->perf.fix_core_ib_vote;
+		}
+		perf->core_clk_rate = kms->perf.fix_core_clk_rate;
+	}
+
+	DPU_DEBUG(
+		"crtc=%d clk_rate=%llu core_ib=%llu core_ab=%llu llcc_ib=%llu llcc_ab=%llu mem_ib=%llu mem_ab=%llu\n",
+			crtc->base.id, perf->core_clk_rate,
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+			perf->max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_EBI],
+			perf->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI]);
+}
+
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	u32 bw, threshold;
+	u64 bw_sum_of_intfs = 0;
+	enum dpu_crtc_client_type curr_client_type;
+	bool is_video_mode;
+	struct dpu_crtc_state *dpu_cstate;
+	struct drm_crtc *tmp_crtc;
+	struct dpu_kms *kms;
+	int i;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid parameters\n");
+		return 0;
+	}
+
+	/* we only need bandwidth check on real-time clients (interfaces) */
+	if (dpu_crtc_get_client_type(crtc) == NRT_CLIENT)
+		return 0;
+
+	dpu_cstate = to_dpu_crtc_state(state);
+
+	/* obtain new values */
+	_dpu_core_perf_calc_crtc(kms, crtc, state, &dpu_cstate->new_perf);
+
+	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
+			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		bw_sum_of_intfs = dpu_cstate->new_perf.bw_ctl[i];
+		curr_client_type = dpu_crtc_get_client_type(crtc);
+
+		drm_for_each_crtc(tmp_crtc, crtc->dev) {
+			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			    (dpu_crtc_get_client_type(tmp_crtc) ==
+					    curr_client_type) &&
+			    (tmp_crtc != crtc)) {
+				struct dpu_crtc_state *tmp_cstate =
+					to_dpu_crtc_state(tmp_crtc->state);
+
+				DPU_DEBUG("crtc:%d bw:%llu ctrl:%d\n",
+					tmp_crtc->base.id,
+					tmp_cstate->new_perf.bw_ctl[i],
+					tmp_cstate->bw_control);
+				/*
+				 * For bw check only use the bw if the
+				 * atomic property has been already set
+				 */
+				if (tmp_cstate->bw_control)
+					bw_sum_of_intfs +=
+						tmp_cstate->new_perf.bw_ctl[i];
+			}
+		}
+
+		/* convert bandwidth to kb */
+		bw = DIV_ROUND_UP_ULL(bw_sum_of_intfs, 1000);
+		DPU_DEBUG("calculated bandwidth=%uk\n", bw);
+
+		is_video_mode = dpu_crtc_get_intf_mode(crtc) == INTF_MODE_VIDEO;
+		threshold = (is_video_mode ||
+			_dpu_core_video_mode_intf_connected(crtc)) ?
+			kms->catalog->perf.max_bw_low :
+			kms->catalog->perf.max_bw_high;
+
+		DPU_DEBUG("final threshold bw limit = %d\n", threshold);
+
+		if (!dpu_cstate->bw_control) {
+			DPU_DEBUG("bypass bandwidth check\n");
+		} else if (!threshold) {
+			DPU_ERROR("no bandwidth limits specified\n");
+			return -E2BIG;
+		} else if (bw > threshold) {
+			DPU_ERROR("exceeds bandwidth: %ukb > %ukb\n", bw,
+					threshold);
+			return -E2BIG;
+		}
+	}
+
+	return 0;
+}
+
+static int _dpu_core_perf_crtc_update_bus(struct dpu_kms *kms,
+		struct drm_crtc *crtc, u32 bus_id)
+{
+	struct dpu_core_perf_params perf = { { 0 } };
+	enum dpu_crtc_client_type curr_client_type
+					= dpu_crtc_get_client_type(crtc);
+	struct drm_crtc *tmp_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	int ret = 0;
+
+	drm_for_each_crtc(tmp_crtc, crtc->dev) {
+		if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+			curr_client_type ==
+				dpu_crtc_get_client_type(tmp_crtc)) {
+			dpu_cstate = to_dpu_crtc_state(tmp_crtc->state);
+
+			perf.max_per_pipe_ib[bus_id] =
+				max(perf.max_per_pipe_ib[bus_id],
+				dpu_cstate->new_perf.max_per_pipe_ib[bus_id]);
+
+			DPU_DEBUG("crtc=%d bus_id=%d bw=%llu\n",
+				tmp_crtc->base.id, bus_id,
+				dpu_cstate->new_perf.bw_ctl[bus_id]);
+		}
+	}
+	return ret;
+}
+
+/**
+ * @dpu_core_perf_crtc_release_bw() - request zero bandwidth
+ * @crtc - pointer to a crtc
+ *
+ * Function checks a state variable for the crtc, if all pending commit
+ * requests are done, meaning no more bandwidth is needed, release
+ * bandwidth request.
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc)
+{
+	struct drm_crtc *tmp_crtc;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	struct dpu_kms *kms;
+	int i;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_cstate = to_dpu_crtc_state(crtc->state);
+
+	/* only do this for command mode rt client */
+	if (dpu_crtc_get_intf_mode(crtc) != INTF_MODE_CMD)
+		return;
+
+	/*
+	 * If video interface present, cmd panel bandwidth cannot be
+	 * released.
+	 */
+	if (dpu_crtc_get_intf_mode(crtc) == INTF_MODE_CMD)
+		drm_for_each_crtc(tmp_crtc, crtc->dev) {
+			if (_dpu_core_perf_crtc_is_power_on(tmp_crtc) &&
+				dpu_crtc_get_intf_mode(tmp_crtc) ==
+						INTF_MODE_VIDEO)
+				return;
+		}
+
+	/* Release the bandwidth */
+	if (kms->perf.enable_bw_release) {
+		trace_dpu_cmd_release_bw(crtc->base.id);
+		DPU_DEBUG("Release BW crtc=%d\n", crtc->base.id);
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			dpu_crtc->cur_perf.bw_ctl[i] = 0;
+			_dpu_core_perf_crtc_update_bus(kms, crtc, i);
+		}
+	}
+}
+
+static int _dpu_core_perf_set_core_clk_rate(struct dpu_kms *kms, u64 rate)
+{
+	struct dss_clk *core_clk = kms->perf.core_clk;
+
+	if (core_clk->max_rate && (rate > core_clk->max_rate))
+		rate = core_clk->max_rate;
+
+	core_clk->rate = rate;
+	return msm_dss_clk_set_rate(core_clk, 1);
+}
+
+static u64 _dpu_core_perf_get_core_clk_rate(struct dpu_kms *kms)
+{
+	u64 clk_rate = kms->perf.perf_tune.min_core_clk;
+	struct drm_crtc *crtc;
+	struct dpu_crtc_state *dpu_cstate;
+
+	drm_for_each_crtc(crtc, kms->dev) {
+		if (_dpu_core_perf_crtc_is_power_on(crtc)) {
+			dpu_cstate = to_dpu_crtc_state(crtc->state);
+			clk_rate = max(dpu_cstate->new_perf.core_clk_rate,
+							clk_rate);
+			clk_rate = clk_round_rate(kms->perf.core_clk->clk,
+					clk_rate);
+		}
+	}
+
+	if (kms->perf.perf_tune.mode == DPU_PERF_MODE_FIXED)
+		clk_rate = kms->perf.fix_core_clk_rate;
+
+	DPU_DEBUG("clk:%llu\n", clk_rate);
+
+	return clk_rate;
+}
+
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req)
+{
+	struct dpu_core_perf_params *new, *old;
+	int update_bus = 0, update_clk = 0;
+	u64 clk_rate = 0;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_cstate;
+	int i;
+	struct msm_drm_private *priv;
+	struct dpu_kms *kms;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_crtc_get_kms(crtc);
+	if (!kms || !kms->catalog) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+	priv = kms->dev->dev_private;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_cstate = to_dpu_crtc_state(crtc->state);
+
+	DPU_DEBUG("crtc:%d stop_req:%d core_clk:%llu\n",
+			crtc->base.id, stop_req, kms->perf.core_clk_rate);
+
+	old = &dpu_crtc->cur_perf;
+	new = &dpu_cstate->new_perf;
+
+	if (_dpu_core_perf_crtc_is_power_on(crtc) && !stop_req) {
+		for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+			/*
+			 * cases for bus bandwidth update.
+			 * 1. new bandwidth vote - "ab or ib vote" is higher
+			 *    than current vote for update request.
+			 * 2. new bandwidth vote - "ab or ib vote" is lower
+			 *    than current vote at end of commit or stop.
+			 */
+			if ((params_changed && ((new->bw_ctl[i] >
+						old->bw_ctl[i]) ||
+				  (new->max_per_pipe_ib[i] >
+						old->max_per_pipe_ib[i]))) ||
+			    (!params_changed && ((new->bw_ctl[i] <
+						old->bw_ctl[i]) ||
+				  (new->max_per_pipe_ib[i] <
+						old->max_per_pipe_ib[i])))) {
+				DPU_DEBUG(
+					"crtc=%d p=%d new_bw=%llu,old_bw=%llu\n",
+					crtc->base.id, params_changed,
+					new->bw_ctl[i], old->bw_ctl[i]);
+				old->bw_ctl[i] = new->bw_ctl[i];
+				old->max_per_pipe_ib[i] =
+						new->max_per_pipe_ib[i];
+				update_bus |= BIT(i);
+			}
+		}
+
+		if ((params_changed &&
+				(new->core_clk_rate > old->core_clk_rate)) ||
+				(!params_changed &&
+				(new->core_clk_rate < old->core_clk_rate))) {
+			old->core_clk_rate = new->core_clk_rate;
+			update_clk = 1;
+		}
+	} else {
+		DPU_DEBUG("crtc=%d disable\n", crtc->base.id);
+		memset(old, 0, sizeof(*old));
+		memset(new, 0, sizeof(*new));
+		update_bus = ~0;
+		update_clk = 1;
+	}
+	trace_dpu_perf_crtc_update(crtc->base.id,
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MNOC],
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_LLCC],
+				new->bw_ctl[DPU_POWER_HANDLE_DBUS_ID_EBI],
+				new->core_clk_rate, stop_req,
+				update_bus, update_clk);
+
+	for (i = 0; i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		if (update_bus & BIT(i)) {
+			ret = _dpu_core_perf_crtc_update_bus(kms, crtc, i);
+			if (ret) {
+				DPU_ERROR("crtc-%d: failed to update bw vote for bus-%d\n",
+					  crtc->base.id, i);
+				return ret;
+			}
+		}
+	}
+
+	/*
+	 * Update the clock after bandwidth vote to ensure
+	 * bandwidth is available before clock rate is increased.
+	 */
+	if (update_clk) {
+		clk_rate = _dpu_core_perf_get_core_clk_rate(kms);
+
+		trace_dpu_core_perf_update_clk(kms->dev, stop_req, clk_rate);
+
+		ret = _dpu_core_perf_set_core_clk_rate(kms, clk_rate);
+		if (ret) {
+			DPU_ERROR("failed to set %s clock rate %llu\n",
+					kms->perf.core_clk->clk_name, clk_rate);
+			return ret;
+		}
+
+		kms->perf.core_clk_rate = clk_rate;
+		DPU_DEBUG("update clk rate = %lld HZ\n", clk_rate);
+	}
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+
+static ssize_t _dpu_core_perf_mode_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	struct dpu_perf_cfg *cfg = &perf->catalog->perf;
+	u32 perf_mode = 0;
+	char buf[10];
+
+	if (!perf)
+		return -ENODEV;
+
+	if (count >= sizeof(buf))
+		return -EFAULT;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[count] = 0;	/* end of string */
+
+	if (kstrtouint(buf, 0, &perf_mode))
+		return -EFAULT;
+
+	if (perf_mode >= DPU_PERF_MODE_MAX)
+		return -EFAULT;
+
+	if (perf_mode == DPU_PERF_MODE_FIXED) {
+		DRM_INFO("fix performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_MINIMUM) {
+		/* run the driver with max clk and BW vote */
+		perf->perf_tune.min_core_clk = perf->max_core_clk_rate;
+		perf->perf_tune.min_bus_vote =
+				(u64) cfg->max_bw_high * 1000;
+		DRM_INFO("minimum performance mode\n");
+	} else if (perf_mode == DPU_PERF_MODE_NORMAL) {
+		/* reset the perf tune params to 0 */
+		perf->perf_tune.min_core_clk = 0;
+		perf->perf_tune.min_bus_vote = 0;
+		DRM_INFO("normal performance mode\n");
+	}
+	perf->perf_tune.mode = perf_mode;
+
+	return count;
+}
+
+static ssize_t _dpu_core_perf_mode_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_core_perf *perf = file->private_data;
+	int len = 0;
+	char buf[DPU_PERF_MODE_STRING_SIZE] = {'\0'};
+
+	if (!perf)
+		return -ENODEV;
+
+	if (*ppos)
+		return 0;	/* the end */
+
+	len = snprintf(buf, sizeof(buf),
+			"mode %d min_mdp_clk %llu min_bus_vote %llu\n",
+			perf->perf_tune.mode,
+			perf->perf_tune.min_core_clk,
+			perf->perf_tune.min_bus_vote);
+	if (len < 0 || len >= sizeof(buf))
+		return 0;
+
+	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
+		return -EFAULT;
+
+	*ppos += len;   /* increase offset */
+
+	return len;
+}
+
+static const struct file_operations dpu_core_perf_mode_fops = {
+	.open = simple_open,
+	.read = _dpu_core_perf_mode_read,
+	.write = _dpu_core_perf_mode_write,
+};
+
+static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
+{
+	debugfs_remove_recursive(perf->debugfs_root);
+	perf->debugfs_root = NULL;
+}
+
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent)
+{
+	struct dpu_mdss_cfg *catalog = perf->catalog;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	priv = perf->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	perf->debugfs_root = debugfs_create_dir("core_perf", parent);
+	if (!perf->debugfs_root) {
+		DPU_ERROR("failed to create core perf debugfs\n");
+		return -EINVAL;
+	}
+
+	debugfs_create_u64("max_core_clk_rate", 0600, perf->debugfs_root,
+			&perf->max_core_clk_rate);
+	debugfs_create_u64("core_clk_rate", 0600, perf->debugfs_root,
+			&perf->core_clk_rate);
+	debugfs_create_u32("enable_bw_release", 0600, perf->debugfs_root,
+			(u32 *)&perf->enable_bw_release);
+	debugfs_create_u32("threshold_low", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.max_bw_low);
+	debugfs_create_u32("threshold_high", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.max_bw_high);
+	debugfs_create_u32("min_core_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_core_ib);
+	debugfs_create_u32("min_llcc_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_llcc_ib);
+	debugfs_create_u32("min_dram_ib", 0600, perf->debugfs_root,
+			(u32 *)&catalog->perf.min_dram_ib);
+	debugfs_create_file("perf_mode", 0600, perf->debugfs_root,
+			(u32 *)perf, &dpu_core_perf_mode_fops);
+	debugfs_create_u64("fix_core_clk_rate", 0600, perf->debugfs_root,
+			&perf->fix_core_clk_rate);
+	debugfs_create_u64("fix_core_ib_vote", 0600, perf->debugfs_root,
+			&perf->fix_core_ib_vote);
+	debugfs_create_u64("fix_core_ab_vote", 0600, perf->debugfs_root,
+			&perf->fix_core_ab_vote);
+
+	return 0;
+}
+#else
+static void dpu_core_perf_debugfs_destroy(struct dpu_core_perf *perf)
+{
+}
+
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent)
+{
+	return 0;
+}
+#endif
+
+void dpu_core_perf_destroy(struct dpu_core_perf *perf)
+{
+	if (!perf) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_core_perf_debugfs_destroy(perf);
+	perf->max_core_clk_rate = 0;
+	perf->core_clk = NULL;
+	perf->phandle = NULL;
+	perf->catalog = NULL;
+	perf->dev = NULL;
+}
+
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_power_handle *phandle,
+		struct dss_clk *core_clk)
+{
+	perf->dev = dev;
+	perf->catalog = catalog;
+	perf->phandle = phandle;
+	perf->core_clk = core_clk;
+
+	perf->max_core_clk_rate = core_clk->max_rate;
+	if (!perf->max_core_clk_rate) {
+		DPU_DEBUG("optional max core clk rate, use default\n");
+		perf->max_core_clk_rate = DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE;
+	}
+
+	return 0;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
new file mode 100644
index 000000000000..fbcbe0c7527a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_core_perf.h
@@ -0,0 +1,133 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_CORE_PERF_H_
+#define _DPU_CORE_PERF_H_
+
+#include <linux/types.h>
+#include <linux/dcache.h>
+#include <linux/mutex.h>
+#include <drm/drm_crtc.h>
+
+#include "dpu_hw_catalog.h"
+#include "dpu_power_handle.h"
+
+#define	DPU_PERF_DEFAULT_MAX_CORE_CLK_RATE	412500000
+
+/**
+ * struct dpu_core_perf_params - definition of performance parameters
+ * @max_per_pipe_ib: maximum instantaneous bandwidth request
+ * @bw_ctl: arbitrated bandwidth request
+ * @core_clk_rate: core clock rate request
+ */
+struct dpu_core_perf_params {
+	u64 max_per_pipe_ib[DPU_POWER_HANDLE_DBUS_ID_MAX];
+	u64 bw_ctl[DPU_POWER_HANDLE_DBUS_ID_MAX];
+	u64 core_clk_rate;
+};
+
+/**
+ * struct dpu_core_perf_tune - definition of performance tuning control
+ * @mode: performance mode
+ * @min_core_clk: minimum core clock
+ * @min_bus_vote: minimum bus vote
+ */
+struct dpu_core_perf_tune {
+	u32 mode;
+	u64 min_core_clk;
+	u64 min_bus_vote;
+};
+
+/**
+ * struct dpu_core_perf - definition of core performance context
+ * @dev: Pointer to drm device
+ * @debugfs_root: top level debug folder
+ * @catalog: Pointer to catalog configuration
+ * @phandle: Pointer to power handler
+ * @core_clk: Pointer to core clock structure
+ * @core_clk_rate: current core clock rate
+ * @max_core_clk_rate: maximum allowable core clock rate
+ * @perf_tune: debug control for performance tuning
+ * @enable_bw_release: debug control for bandwidth release
+ * @fix_core_clk_rate: fixed core clock request in Hz used in mode 2
+ * @fix_core_ib_vote: fixed core ib vote in bps used in mode 2
+ * @fix_core_ab_vote: fixed core ab vote in bps used in mode 2
+ */
+struct dpu_core_perf {
+	struct drm_device *dev;
+	struct dentry *debugfs_root;
+	struct dpu_mdss_cfg *catalog;
+	struct dpu_power_handle *phandle;
+	struct dss_clk *core_clk;
+	u64 core_clk_rate;
+	u64 max_core_clk_rate;
+	struct dpu_core_perf_tune perf_tune;
+	u32 enable_bw_release;
+	u64 fix_core_clk_rate;
+	u64 fix_core_ib_vote;
+	u64 fix_core_ab_vote;
+};
+
+/**
+ * dpu_core_perf_crtc_check - validate performance of the given crtc state
+ * @crtc: Pointer to crtc
+ * @state: Pointer to new crtc state
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state);
+
+/**
+ * dpu_core_perf_crtc_update - update performance of the given crtc
+ * @crtc: Pointer to crtc
+ * @params_changed: true if crtc parameters are modified
+ * @stop_req: true if this is a stop request
+ * return: zero if success, or error code otherwise
+ */
+int dpu_core_perf_crtc_update(struct drm_crtc *crtc,
+		int params_changed, bool stop_req);
+
+/**
+ * dpu_core_perf_crtc_release_bw - release bandwidth of the given crtc
+ * @crtc: Pointer to crtc
+ */
+void dpu_core_perf_crtc_release_bw(struct drm_crtc *crtc);
+
+/**
+ * dpu_core_perf_destroy - destroy the given core performance context
+ * @perf: Pointer to core performance context
+ */
+void dpu_core_perf_destroy(struct dpu_core_perf *perf);
+
+/**
+ * dpu_core_perf_init - initialize the given core performance context
+ * @perf: Pointer to core performance context
+ * @dev: Pointer to drm device
+ * @catalog: Pointer to catalog
+ * @phandle: Pointer to power handle
+ * @core_clk: pointer to core clock
+ */
+int dpu_core_perf_init(struct dpu_core_perf *perf,
+		struct drm_device *dev,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_power_handle *phandle,
+		struct dss_clk *core_clk);
+
+/**
+ * dpu_core_perf_debugfs_init - initialize debugfs for core performance context
+ * @perf: Pointer to core performance context
+ * @debugfs_parent: Pointer to parent debugfs
+ */
+int dpu_core_perf_debugfs_init(struct dpu_core_perf *perf,
+		struct dentry *parent);
+
+#endif /* _DPU_CORE_PERF_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
new file mode 100644
index 000000000000..bcc4796cb5da
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -0,0 +1,2504 @@
+/*
+ * Copyright (c) 2014-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/sort.h>
+#include <linux/debugfs.h>
+#include <linux/ktime.h>
+#include <drm/drm_mode.h>
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include <drm/drm_flip_work.h>
+#include <drm/drm_rect.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_crtc.h"
+#include "dpu_plane.h"
+#include "dpu_encoder.h"
+#include "dpu_vbif.h"
+#include "dpu_power_handle.h"
+#include "dpu_core_perf.h"
+#include "dpu_trace.h"
+
+#define DPU_DRM_BLEND_OP_NOT_DEFINED    0
+#define DPU_DRM_BLEND_OP_OPAQUE         1
+#define DPU_DRM_BLEND_OP_PREMULTIPLIED  2
+#define DPU_DRM_BLEND_OP_COVERAGE       3
+#define DPU_DRM_BLEND_OP_MAX            4
+
+/* layer mixer index on dpu_crtc */
+#define LEFT_MIXER 0
+#define RIGHT_MIXER 1
+
+#define MISR_BUFF_SIZE			256
+
+static inline struct dpu_kms *_dpu_crtc_get_kms(struct drm_crtc *crtc)
+{
+	struct msm_drm_private *priv;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return NULL;
+	}
+	priv = crtc->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return NULL;
+	}
+
+	return to_dpu_kms(priv->kms);
+}
+
+static inline int _dpu_crtc_power_enable(struct dpu_crtc *dpu_crtc, bool enable)
+{
+	struct drm_crtc *crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!dpu_crtc) {
+		DPU_ERROR("invalid dpu crtc\n");
+		return -EINVAL;
+	}
+
+	crtc = &dpu_crtc->base;
+	if (!crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid drm device\n");
+		return -EINVAL;
+	}
+
+	priv = crtc->dev->dev_private;
+	if (!priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	if (enable)
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	else
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+/**
+ * _dpu_crtc_rp_to_crtc - get crtc from resource pool object
+ * @rp: Pointer to resource pool
+ * return: Pointer to drm crtc if success; null otherwise
+ */
+static struct drm_crtc *_dpu_crtc_rp_to_crtc(struct dpu_crtc_respool *rp)
+{
+	if (!rp)
+		return NULL;
+
+	return container_of(rp, struct dpu_crtc_state, rp)->base.crtc;
+}
+
+/**
+ * _dpu_crtc_rp_reclaim - reclaim unused, or all if forced, resources in pool
+ * @rp: Pointer to resource pool
+ * @force: True to reclaim all resources; otherwise, reclaim only unused ones
+ * return: None
+ */
+static void _dpu_crtc_rp_reclaim(struct dpu_crtc_respool *rp, bool force)
+{
+	struct dpu_crtc_res *res, *next;
+	struct drm_crtc *crtc;
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	DPU_DEBUG("crtc%d.%u %s\n", crtc->base.id, rp->sequence_id,
+			force ? "destroy" : "free_unused");
+
+	list_for_each_entry_safe(res, next, &rp->res_list, list) {
+		if (!force && !(res->flags & DPU_CRTC_RES_FLAG_FREE))
+			continue;
+		DPU_DEBUG("crtc%d.%u reclaim res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, rp->sequence_id,
+				res->type, res->tag, res->val,
+				atomic_read(&res->refcount));
+		list_del(&res->list);
+		if (res->ops.put)
+			res->ops.put(res->val);
+		kfree(res);
+	}
+}
+
+/**
+ * _dpu_crtc_rp_free_unused - free unused resource in pool
+ * @rp: Pointer to resource pool
+ * return: none
+ */
+static void _dpu_crtc_rp_free_unused(struct dpu_crtc_respool *rp)
+{
+	mutex_lock(rp->rp_lock);
+	_dpu_crtc_rp_reclaim(rp, false);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_rp_destroy - destroy resource pool
+ * @rp: Pointer to resource pool
+ * return: None
+ */
+static void _dpu_crtc_rp_destroy(struct dpu_crtc_respool *rp)
+{
+	mutex_lock(rp->rp_lock);
+	list_del_init(&rp->rp_list);
+	_dpu_crtc_rp_reclaim(rp, true);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_hw_blk_get - get callback for hardware block
+ * @val: Resource handle
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * return: Resource handle
+ */
+static void *_dpu_crtc_hw_blk_get(void *val, u32 type, u64 tag)
+{
+	DPU_DEBUG("res:%d/0x%llx/%pK\n", type, tag, val);
+	return dpu_hw_blk_get(val, type, tag);
+}
+
+/**
+ * _dpu_crtc_hw_blk_put - put callback for hardware block
+ * @val: Resource handle
+ * return: None
+ */
+static void _dpu_crtc_hw_blk_put(void *val)
+{
+	DPU_DEBUG("res://%pK\n", val);
+	dpu_hw_blk_put(val);
+}
+
+/**
+ * _dpu_crtc_rp_duplicate - duplicate resource pool and reset reference count
+ * @rp: Pointer to original resource pool
+ * @dup_rp: Pointer to duplicated resource pool
+ * return: None
+ */
+static void _dpu_crtc_rp_duplicate(struct dpu_crtc_respool *rp,
+		struct dpu_crtc_respool *dup_rp)
+{
+	struct dpu_crtc_res *res, *dup_res;
+	struct drm_crtc *crtc;
+
+	if (!rp || !dup_rp || !rp->rp_head) {
+		DPU_ERROR("invalid resource pool\n");
+		return;
+	}
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	DPU_DEBUG("crtc%d.%u duplicate\n", crtc->base.id, rp->sequence_id);
+
+	mutex_lock(rp->rp_lock);
+	dup_rp->sequence_id = rp->sequence_id + 1;
+	INIT_LIST_HEAD(&dup_rp->res_list);
+	dup_rp->ops = rp->ops;
+	list_for_each_entry(res, &rp->res_list, list) {
+		dup_res = kzalloc(sizeof(struct dpu_crtc_res), GFP_KERNEL);
+		if (!dup_res) {
+			mutex_unlock(rp->rp_lock);
+			return;
+		}
+		INIT_LIST_HEAD(&dup_res->list);
+		atomic_set(&dup_res->refcount, 0);
+		dup_res->type = res->type;
+		dup_res->tag = res->tag;
+		dup_res->val = res->val;
+		dup_res->ops = res->ops;
+		dup_res->flags = DPU_CRTC_RES_FLAG_FREE;
+		DPU_DEBUG("crtc%d.%u dup res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, dup_rp->sequence_id,
+				dup_res->type, dup_res->tag, dup_res->val,
+				atomic_read(&dup_res->refcount));
+		list_add_tail(&dup_res->list, &dup_rp->res_list);
+		if (dup_res->ops.get)
+			dup_res->ops.get(dup_res->val, 0, -1);
+	}
+
+	dup_rp->rp_lock = rp->rp_lock;
+	dup_rp->rp_head = rp->rp_head;
+	INIT_LIST_HEAD(&dup_rp->rp_list);
+	list_add_tail(&dup_rp->rp_list, rp->rp_head);
+	mutex_unlock(rp->rp_lock);
+}
+
+/**
+ * _dpu_crtc_rp_reset - reset resource pool after allocation
+ * @rp: Pointer to original resource pool
+ * @rp_lock: Pointer to serialization resource pool lock
+ * @rp_head: Pointer to crtc resource pool head
+ * return: None
+ */
+static void _dpu_crtc_rp_reset(struct dpu_crtc_respool *rp,
+		struct mutex *rp_lock, struct list_head *rp_head)
+{
+	if (!rp || !rp_lock || !rp_head) {
+		DPU_ERROR("invalid resource pool\n");
+		return;
+	}
+
+	mutex_lock(rp_lock);
+	rp->rp_lock = rp_lock;
+	rp->rp_head = rp_head;
+	INIT_LIST_HEAD(&rp->rp_list);
+	rp->sequence_id = 0;
+	INIT_LIST_HEAD(&rp->res_list);
+	rp->ops.get = _dpu_crtc_hw_blk_get;
+	rp->ops.put = _dpu_crtc_hw_blk_put;
+	list_add_tail(&rp->rp_list, rp->rp_head);
+	mutex_unlock(rp_lock);
+}
+
+/**
+ * _dpu_crtc_rp_add_no_lock - add given resource to resource pool without lock
+ * @rp: Pointer to original resource pool
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * @val: Resource handle
+ * @ops: Resource callback operations
+ * return: 0 if success; error code otherwise
+ */
+static int _dpu_crtc_rp_add_no_lock(struct dpu_crtc_respool *rp, u32 type,
+		u64 tag, void *val, struct dpu_crtc_res_ops *ops)
+{
+	struct dpu_crtc_res *res;
+	struct drm_crtc *crtc;
+
+	if (!rp || !ops) {
+		DPU_ERROR("invalid resource pool/ops\n");
+		return -EINVAL;
+	}
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	list_for_each_entry(res, &rp->res_list, list) {
+		if (res->type != type || res->tag != tag)
+			continue;
+		DPU_ERROR("crtc%d.%u already exist res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, rp->sequence_id,
+				res->type, res->tag, res->val,
+				atomic_read(&res->refcount));
+		return -EEXIST;
+	}
+	res = kzalloc(sizeof(struct dpu_crtc_res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+	INIT_LIST_HEAD(&res->list);
+	atomic_set(&res->refcount, 1);
+	res->type = type;
+	res->tag = tag;
+	res->val = val;
+	res->ops = *ops;
+	list_add_tail(&res->list, &rp->res_list);
+	DPU_DEBUG("crtc%d.%u added res:0x%x/0x%llx\n",
+			crtc->base.id, rp->sequence_id, type, tag);
+	return 0;
+}
+
+/**
+ * _dpu_crtc_rp_add - add given resource to resource pool
+ * @rp: Pointer to original resource pool
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * @val: Resource handle
+ * @ops: Resource callback operations
+ * return: 0 if success; error code otherwise
+ */
+static int _dpu_crtc_rp_add(struct dpu_crtc_respool *rp, u32 type, u64 tag,
+		void *val, struct dpu_crtc_res_ops *ops)
+{
+	int rc;
+
+	if (!rp) {
+		DPU_ERROR("invalid resource pool\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(rp->rp_lock);
+	rc = _dpu_crtc_rp_add_no_lock(rp, type, tag, val, ops);
+	mutex_unlock(rp->rp_lock);
+	return rc;
+}
+
+/**
+ * _dpu_crtc_rp_get - lookup the resource from given resource pool and obtain
+ *	if available; otherwise, obtain resource from global pool
+ * @rp: Pointer to original resource pool
+ * @type: Resource type
+ * @tag:  Search tag for given resource
+ * return: Resource handle if success; pointer error or null otherwise
+ */
+static void *_dpu_crtc_rp_get(struct dpu_crtc_respool *rp, u32 type, u64 tag)
+{
+	struct dpu_crtc_respool *old_rp;
+	struct dpu_crtc_res *res;
+	void *val = NULL;
+	int rc;
+	struct drm_crtc *crtc;
+
+	if (!rp) {
+		DPU_ERROR("invalid resource pool\n");
+		return NULL;
+	}
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return NULL;
+	}
+
+	mutex_lock(rp->rp_lock);
+	list_for_each_entry(res, &rp->res_list, list) {
+		if (res->type != type || res->tag != tag)
+			continue;
+		DPU_DEBUG("crtc%d.%u found res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, rp->sequence_id,
+				res->type, res->tag, res->val,
+				atomic_read(&res->refcount));
+		atomic_inc(&res->refcount);
+		res->flags &= ~DPU_CRTC_RES_FLAG_FREE;
+		mutex_unlock(rp->rp_lock);
+		return res->val;
+	}
+	list_for_each_entry(res, &rp->res_list, list) {
+		if (res->type != type || !(res->flags & DPU_CRTC_RES_FLAG_FREE))
+			continue;
+		DPU_DEBUG("crtc%d.%u retag res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, rp->sequence_id,
+				res->type, res->tag, res->val,
+				atomic_read(&res->refcount));
+		atomic_inc(&res->refcount);
+		res->tag = tag;
+		res->flags &= ~DPU_CRTC_RES_FLAG_FREE;
+		mutex_unlock(rp->rp_lock);
+		return res->val;
+	}
+	/* not in this rp, try to grab from global pool */
+	if (rp->ops.get)
+		val = rp->ops.get(NULL, type, -1);
+	if (!IS_ERR_OR_NULL(val))
+		goto add_res;
+	/*
+	 * Search older resource pools for hw blk with matching type,
+	 * necessary when resource is being used by this object,
+	 * but in previous states not yet cleaned up.
+	 *
+	 * This enables searching of all resources currently owned
+	 * by this crtc even though the resource might not be used
+	 * in the current atomic state. This allows those resources
+	 * to be re-acquired by the new atomic state immediately
+	 * without waiting for the resources to be fully released.
+	 */
+	else if (IS_ERR_OR_NULL(val) && (type < DPU_HW_BLK_MAX)) {
+		list_for_each_entry(old_rp, rp->rp_head, rp_list) {
+			if (old_rp == rp)
+				continue;
+
+			list_for_each_entry(res, &old_rp->res_list, list) {
+				if (res->type != type)
+					continue;
+				DRM_DEBUG_KMS("crtc%d.%u found res:0x%x//%pK/ "
+					      "in crtc%d.%d\n",
+					      crtc->base.id, rp->sequence_id,
+					      res->type, res->val,
+					      crtc->base.id,
+					      old_rp->sequence_id);
+				if (res->ops.get)
+					res->ops.get(res->val, 0, -1);
+				val = res->val;
+				break;
+			}
+
+			if (!IS_ERR_OR_NULL(val))
+				break;
+		}
+	}
+	if (IS_ERR_OR_NULL(val)) {
+		DPU_DEBUG("crtc%d.%u failed to get res:0x%x//\n",
+				crtc->base.id, rp->sequence_id, type);
+		mutex_unlock(rp->rp_lock);
+		return NULL;
+	}
+add_res:
+	rc = _dpu_crtc_rp_add_no_lock(rp, type, tag, val, &rp->ops);
+	if (rc) {
+		DPU_ERROR("crtc%d.%u failed to add res:0x%x/0x%llx\n",
+				crtc->base.id, rp->sequence_id, type, tag);
+		if (rp->ops.put)
+			rp->ops.put(val);
+		val = NULL;
+	}
+	mutex_unlock(rp->rp_lock);
+	return val;
+}
+
+/**
+ * _dpu_crtc_rp_put - return given resource to resource pool
+ * @rp: Pointer to original resource pool
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * return: None
+ */
+static void _dpu_crtc_rp_put(struct dpu_crtc_respool *rp, u32 type, u64 tag)
+{
+	struct dpu_crtc_res *res, *next;
+	struct drm_crtc *crtc;
+
+	if (!rp) {
+		DPU_ERROR("invalid resource pool\n");
+		return;
+	}
+
+	crtc = _dpu_crtc_rp_to_crtc(rp);
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	mutex_lock(rp->rp_lock);
+	list_for_each_entry_safe(res, next, &rp->res_list, list) {
+		if (res->type != type || res->tag != tag)
+			continue;
+		DPU_DEBUG("crtc%d.%u found res:0x%x/0x%llx/%pK/%d\n",
+				crtc->base.id, rp->sequence_id,
+				res->type, res->tag, res->val,
+				atomic_read(&res->refcount));
+		if (res->flags & DPU_CRTC_RES_FLAG_FREE)
+			DPU_ERROR(
+				"crtc%d.%u already free res:0x%x/0x%llx/%pK/%d\n",
+					crtc->base.id, rp->sequence_id,
+					res->type, res->tag, res->val,
+					atomic_read(&res->refcount));
+		else if (atomic_dec_return(&res->refcount) == 0)
+			res->flags |= DPU_CRTC_RES_FLAG_FREE;
+
+		mutex_unlock(rp->rp_lock);
+		return;
+	}
+	DPU_ERROR("crtc%d.%u not found res:0x%x/0x%llx\n",
+			crtc->base.id, rp->sequence_id, type, tag);
+	mutex_unlock(rp->rp_lock);
+}
+
+int dpu_crtc_res_add(struct drm_crtc_state *state, u32 type, u64 tag,
+		void *val, struct dpu_crtc_res_ops *ops)
+{
+	struct dpu_crtc_respool *rp;
+
+	if (!state) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	rp = &to_dpu_crtc_state(state)->rp;
+	return _dpu_crtc_rp_add(rp, type, tag, val, ops);
+}
+
+void *dpu_crtc_res_get(struct drm_crtc_state *state, u32 type, u64 tag)
+{
+	struct dpu_crtc_respool *rp;
+	void *val;
+
+	if (!state) {
+		DPU_ERROR("invalid parameters\n");
+		return NULL;
+	}
+
+	rp = &to_dpu_crtc_state(state)->rp;
+	val = _dpu_crtc_rp_get(rp, type, tag);
+	if (IS_ERR(val)) {
+		DPU_ERROR("failed to get res type:0x%x:0x%llx\n",
+				type, tag);
+		return NULL;
+	}
+
+	return val;
+}
+
+void dpu_crtc_res_put(struct drm_crtc_state *state, u32 type, u64 tag)
+{
+	struct dpu_crtc_respool *rp;
+
+	if (!state) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	rp = &to_dpu_crtc_state(state)->rp;
+	_dpu_crtc_rp_put(rp, type, tag);
+}
+
+static void dpu_crtc_destroy(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	DPU_DEBUG("\n");
+
+	if (!crtc)
+		return;
+
+	dpu_crtc->phandle = NULL;
+
+	drm_crtc_cleanup(crtc);
+	mutex_destroy(&dpu_crtc->crtc_lock);
+	kfree(dpu_crtc);
+}
+
+static void _dpu_crtc_setup_blend_cfg(struct dpu_crtc_mixer *mixer,
+		struct dpu_plane_state *pstate)
+{
+	struct dpu_hw_mixer *lm = mixer->hw_lm;
+
+	/* default to opaque blending */
+	lm->ops.setup_blend_config(lm, pstate->stage, 0XFF, 0,
+				DPU_BLEND_FG_ALPHA_FG_CONST |
+				DPU_BLEND_BG_ALPHA_BG_CONST);
+}
+
+static void _dpu_crtc_program_lm_output_roi(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *crtc_state;
+	int lm_idx, lm_horiz_position;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	crtc_state = to_dpu_crtc_state(crtc->state);
+
+	lm_horiz_position = 0;
+	for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) {
+		const struct drm_rect *lm_roi = &crtc_state->lm_bounds[lm_idx];
+		struct dpu_hw_mixer *hw_lm = dpu_crtc->mixers[lm_idx].hw_lm;
+		struct dpu_hw_mixer_cfg cfg;
+
+		if (!lm_roi || !drm_rect_visible(lm_roi))
+			continue;
+
+		cfg.out_width = drm_rect_width(lm_roi);
+		cfg.out_height = drm_rect_height(lm_roi);
+		cfg.right_mixer = lm_horiz_position++;
+		cfg.flags = 0;
+		hw_lm->ops.setup_mixer_out(hw_lm, &cfg);
+	}
+}
+
+static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
+	struct dpu_crtc *dpu_crtc, struct dpu_crtc_mixer *mixer)
+{
+	struct drm_plane *plane;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate;
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_format *format;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_mixer *lm;
+	struct dpu_hw_stage_cfg *stage_cfg;
+
+	u32 flush_mask;
+	uint32_t stage_idx, lm_idx;
+	int zpos_cnt[DPU_STAGE_MAX + 1] = { 0 };
+	bool bg_alpha_enable = false;
+
+	if (!dpu_crtc || !mixer) {
+		DPU_ERROR("invalid dpu_crtc or mixer\n");
+		return;
+	}
+
+	ctl = mixer->hw_ctl;
+	lm = mixer->hw_lm;
+	stage_cfg = &dpu_crtc->stage_cfg;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		state = plane->state;
+		if (!state)
+			continue;
+
+		pstate = to_dpu_plane_state(state);
+		fb = state->fb;
+
+		dpu_plane_get_ctl_flush(plane, ctl, &flush_mask);
+
+		DPU_DEBUG("crtc %d stage:%d - plane %d sspp %d fb %d\n",
+				crtc->base.id,
+				pstate->stage,
+				plane->base.id,
+				dpu_plane_pipe(plane) - SSPP_VIG0,
+				state->fb ? state->fb->base.id : -1);
+
+		format = to_dpu_format(msm_framebuffer_format(pstate->base.fb));
+		if (!format) {
+			DPU_ERROR("invalid format\n");
+			return;
+		}
+
+		if (pstate->stage == DPU_STAGE_BASE && format->alpha_enable)
+			bg_alpha_enable = true;
+
+		stage_idx = zpos_cnt[pstate->stage]++;
+		stage_cfg->stage[pstate->stage][stage_idx] =
+					dpu_plane_pipe(plane);
+		stage_cfg->multirect_index[pstate->stage][stage_idx] =
+					pstate->multirect_index;
+
+		trace_dpu_crtc_setup_mixer(DRMID(crtc), DRMID(plane),
+					   state, pstate, stage_idx,
+					   dpu_plane_pipe(plane) - SSPP_VIG0,
+					   format->base.pixel_format,
+					   fb ? fb->modifier : 0);
+
+		/* blend config update */
+		for (lm_idx = 0; lm_idx < dpu_crtc->num_mixers; lm_idx++) {
+			_dpu_crtc_setup_blend_cfg(mixer + lm_idx, pstate);
+
+			mixer[lm_idx].flush_mask |= flush_mask;
+
+			if (bg_alpha_enable && !format->alpha_enable)
+				mixer[lm_idx].mixer_op_mode = 0;
+			else
+				mixer[lm_idx].mixer_op_mode |=
+						1 << pstate->stage;
+		}
+	}
+
+	 _dpu_crtc_program_lm_output_roi(crtc);
+}
+
+/**
+ * _dpu_crtc_blend_setup - configure crtc mixers
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_blend_setup(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *dpu_crtc_state;
+	struct dpu_crtc_mixer *mixer;
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_mixer *lm;
+
+	int i;
+
+	if (!crtc)
+		return;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_crtc_state = to_dpu_crtc_state(crtc->state);
+	mixer = dpu_crtc->mixers;
+
+	DPU_DEBUG("%s\n", dpu_crtc->name);
+
+	if (dpu_crtc->num_mixers > CRTC_DUAL_MIXERS) {
+		DPU_ERROR("invalid number mixers: %d\n", dpu_crtc->num_mixers);
+		return;
+	}
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		if (!mixer[i].hw_lm || !mixer[i].hw_ctl) {
+			DPU_ERROR("invalid lm or ctl assigned to mixer\n");
+			return;
+		}
+		mixer[i].mixer_op_mode = 0;
+		mixer[i].flush_mask = 0;
+		if (mixer[i].hw_ctl->ops.clear_all_blendstages)
+			mixer[i].hw_ctl->ops.clear_all_blendstages(
+					mixer[i].hw_ctl);
+	}
+
+	/* initialize stage cfg */
+	memset(&dpu_crtc->stage_cfg, 0, sizeof(struct dpu_hw_stage_cfg));
+
+	_dpu_crtc_blend_setup_mixer(crtc, dpu_crtc, mixer);
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		ctl = mixer[i].hw_ctl;
+		lm = mixer[i].hw_lm;
+
+		lm->ops.setup_alpha_out(lm, mixer[i].mixer_op_mode);
+
+		mixer[i].flush_mask |= ctl->ops.get_bitmask_mixer(ctl,
+			mixer[i].hw_lm->idx);
+
+		/* stage config flush mask */
+		ctl->ops.update_pending_flush(ctl, mixer[i].flush_mask);
+
+		DPU_DEBUG("lm %d, op_mode 0x%X, ctl %d, flush mask 0x%x\n",
+			mixer[i].hw_lm->idx - LM_0,
+			mixer[i].mixer_op_mode,
+			ctl->idx - CTL_0,
+			mixer[i].flush_mask);
+
+		ctl->ops.setup_blendstage(ctl, mixer[i].hw_lm->idx,
+			&dpu_crtc->stage_cfg);
+	}
+}
+
+/**
+ *  _dpu_crtc_complete_flip - signal pending page_flip events
+ * Any pending vblank events are added to the vblank_event_list
+ * so that the next vblank interrupt shall signal them.
+ * However PAGE_FLIP events are not handled through the vblank_event_list.
+ * This API signals any pending PAGE_FLIP events requested through
+ * DRM_IOCTL_MODE_PAGE_FLIP and are cached in the dpu_crtc->event.
+ * @crtc: Pointer to drm crtc structure
+ */
+static void _dpu_crtc_complete_flip(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_device *dev = crtc->dev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->event_lock, flags);
+	if (dpu_crtc->event) {
+		DRM_DEBUG_VBL("%s: send event: %pK\n", dpu_crtc->name,
+			      dpu_crtc->event);
+		trace_dpu_crtc_complete_flip(DRMID(crtc));
+		drm_crtc_send_vblank_event(crtc, dpu_crtc->event);
+		dpu_crtc->event = NULL;
+	}
+	spin_unlock_irqrestore(&dev->event_lock, flags);
+}
+
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+
+	if (!crtc || !crtc->dev) {
+		DPU_ERROR("invalid crtc\n");
+		return INTF_MODE_NONE;
+	}
+
+	drm_for_each_encoder(encoder, crtc->dev)
+		if (encoder->crtc == crtc)
+			return dpu_encoder_get_intf_mode(encoder);
+
+	return INTF_MODE_NONE;
+}
+
+static void dpu_crtc_vblank_cb(void *data)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *)data;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+
+	/* keep statistics on vblank callback - with auto reset via debugfs */
+	if (ktime_compare(dpu_crtc->vblank_cb_time, ktime_set(0, 0)) == 0)
+		dpu_crtc->vblank_cb_time = ktime_get();
+	else
+		dpu_crtc->vblank_cb_count++;
+	_dpu_crtc_complete_flip(crtc);
+	drm_crtc_handle_vblank(crtc);
+	trace_dpu_crtc_vblank_cb(DRMID(crtc));
+}
+
+static void dpu_crtc_frame_event_work(struct kthread_work *work)
+{
+	struct msm_drm_private *priv;
+	struct dpu_crtc_frame_event *fevent;
+	struct drm_crtc *crtc;
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_kms *dpu_kms;
+	unsigned long flags;
+	bool frame_done = false;
+
+	if (!work) {
+		DPU_ERROR("invalid work handle\n");
+		return;
+	}
+
+	fevent = container_of(work, struct dpu_crtc_frame_event, work);
+	if (!fevent->crtc || !fevent->crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	crtc = fevent->crtc;
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid kms handle\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+	DPU_ATRACE_BEGIN("crtc_frame_event");
+
+	DRM_DEBUG_KMS("crtc%d event:%u ts:%lld\n", crtc->base.id, fevent->event,
+			ktime_to_ns(fevent->ts));
+
+	if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+				| DPU_ENCODER_FRAME_EVENT_ERROR
+				| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (atomic_read(&dpu_crtc->frame_pending) < 1) {
+			/* this should not happen */
+			DRM_ERROR("crtc%d ev:%u ts:%lld frame_pending:%d\n",
+					crtc->base.id,
+					fevent->event,
+					ktime_to_ns(fevent->ts),
+					atomic_read(&dpu_crtc->frame_pending));
+		} else if (atomic_dec_return(&dpu_crtc->frame_pending) == 0) {
+			/* release bandwidth and other resources */
+			trace_dpu_crtc_frame_event_done(DRMID(crtc),
+							fevent->event);
+			dpu_core_perf_crtc_release_bw(crtc);
+		} else {
+			trace_dpu_crtc_frame_event_more_pending(DRMID(crtc),
+								fevent->event);
+		}
+
+		if (fevent->event & DPU_ENCODER_FRAME_EVENT_DONE)
+			dpu_core_perf_crtc_update(crtc, 0, false);
+
+		if (fevent->event & (DPU_ENCODER_FRAME_EVENT_DONE
+					| DPU_ENCODER_FRAME_EVENT_ERROR))
+			frame_done = true;
+	}
+
+	if (fevent->event & DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)
+		DPU_ERROR("crtc%d ts:%lld received panel dead event\n",
+				crtc->base.id, ktime_to_ns(fevent->ts));
+
+	if (frame_done)
+		complete_all(&dpu_crtc->frame_done_comp);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	list_add_tail(&fevent->list, &dpu_crtc->frame_event_list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+	DPU_ATRACE_END("crtc_frame_event");
+}
+
+/*
+ * dpu_crtc_frame_event_cb - crtc frame event callback API. CRTC module
+ * registers this API to encoder for all frame event callbacks like
+ * frame_error, frame_done, idle_timeout, etc. Encoder may call different events
+ * from different context - IRQ, user thread, commit_thread, etc. Each event
+ * should be carefully reviewed and should be processed in proper task context
+ * to avoid schedulin delay or properly manage the irq context's bottom half
+ * processing.
+ */
+static void dpu_crtc_frame_event_cb(void *data, u32 event)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *)data;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_crtc_frame_event *fevent;
+	unsigned long flags;
+	u32 crtc_id;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	/* Nothing to do on idle event */
+	if (event & DPU_ENCODER_FRAME_EVENT_IDLE)
+		return;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+	crtc_id = drm_crtc_index(crtc);
+
+	trace_dpu_crtc_frame_event_cb(DRMID(crtc), event);
+
+	spin_lock_irqsave(&dpu_crtc->spin_lock, flags);
+	fevent = list_first_entry_or_null(&dpu_crtc->frame_event_list,
+			struct dpu_crtc_frame_event, list);
+	if (fevent)
+		list_del_init(&fevent->list);
+	spin_unlock_irqrestore(&dpu_crtc->spin_lock, flags);
+
+	if (!fevent) {
+		DRM_ERROR("crtc%d event %d overflow\n", crtc->base.id, event);
+		return;
+	}
+
+	fevent->event = event;
+	fevent->crtc = crtc;
+	fevent->ts = ktime_get();
+	kthread_queue_work(&priv->event_thread[crtc_id].worker, &fevent->work);
+}
+
+void dpu_crtc_complete_commit(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state)
+{
+	if (!crtc || !crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	trace_dpu_crtc_complete_commit(DRMID(crtc));
+}
+
+static void _dpu_crtc_setup_mixer_for_encoder(
+		struct drm_crtc *crtc,
+		struct drm_encoder *enc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_kms *dpu_kms = _dpu_crtc_get_kms(crtc);
+	struct dpu_rm *rm = &dpu_kms->rm;
+	struct dpu_crtc_mixer *mixer;
+	struct dpu_hw_ctl *last_valid_ctl = NULL;
+	int i;
+	struct dpu_rm_hw_iter lm_iter, ctl_iter;
+
+	dpu_rm_init_hw_iter(&lm_iter, enc->base.id, DPU_HW_BLK_LM);
+	dpu_rm_init_hw_iter(&ctl_iter, enc->base.id, DPU_HW_BLK_CTL);
+
+	/* Set up all the mixers and ctls reserved by this encoder */
+	for (i = dpu_crtc->num_mixers; i < ARRAY_SIZE(dpu_crtc->mixers); i++) {
+		mixer = &dpu_crtc->mixers[i];
+
+		if (!dpu_rm_get_hw(rm, &lm_iter))
+			break;
+		mixer->hw_lm = (struct dpu_hw_mixer *)lm_iter.hw;
+
+		/* CTL may be <= LMs, if <, multiple LMs controlled by 1 CTL */
+		if (!dpu_rm_get_hw(rm, &ctl_iter)) {
+			DPU_DEBUG("no ctl assigned to lm %d, using previous\n",
+					mixer->hw_lm->idx - LM_0);
+			mixer->hw_ctl = last_valid_ctl;
+		} else {
+			mixer->hw_ctl = (struct dpu_hw_ctl *)ctl_iter.hw;
+			last_valid_ctl = mixer->hw_ctl;
+		}
+
+		/* Shouldn't happen, mixers are always >= ctls */
+		if (!mixer->hw_ctl) {
+			DPU_ERROR("no valid ctls found for lm %d\n",
+					mixer->hw_lm->idx - LM_0);
+			return;
+		}
+
+		mixer->encoder = enc;
+
+		dpu_crtc->num_mixers++;
+		DPU_DEBUG("setup mixer %d: lm %d\n",
+				i, mixer->hw_lm->idx - LM_0);
+		DPU_DEBUG("setup mixer %d: ctl %d\n",
+				i, mixer->hw_ctl->idx - CTL_0);
+	}
+}
+
+static void _dpu_crtc_setup_mixers(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct drm_encoder *enc;
+
+	dpu_crtc->num_mixers = 0;
+	dpu_crtc->mixers_swapped = false;
+	memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers));
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	/* Check for mixers on all encoders attached to this crtc */
+	list_for_each_entry(enc, &crtc->dev->mode_config.encoder_list, head) {
+		if (enc->crtc != crtc)
+			continue;
+
+		_dpu_crtc_setup_mixer_for_encoder(crtc, enc);
+	}
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+static void _dpu_crtc_setup_lm_bounds(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+	struct drm_display_mode *adj_mode;
+	u32 crtc_split_width;
+	int i;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	adj_mode = &state->adjusted_mode;
+	crtc_split_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, adj_mode);
+
+	for (i = 0; i < dpu_crtc->num_mixers; i++) {
+		struct drm_rect *r = &cstate->lm_bounds[i];
+		r->x1 = crtc_split_width * i;
+		r->y1 = 0;
+		r->x2 = r->x1 + crtc_split_width;
+		r->y2 = dpu_crtc_get_mixer_height(dpu_crtc, cstate, adj_mode);
+
+		trace_dpu_crtc_setup_lm_bounds(DRMID(crtc), i, r);
+	}
+
+	drm_mode_debug_printmodeline(adj_mode);
+}
+
+static void dpu_crtc_atomic_begin(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	unsigned long flags;
+	struct dpu_crtc_smmu_state_data *smmu_state;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("crtc%d -> enable %d, skip atomic_begin\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	dev = crtc->dev;
+	smmu_state = &dpu_crtc->smmu_state;
+
+	if (!dpu_crtc->num_mixers) {
+		_dpu_crtc_setup_mixers(crtc);
+		_dpu_crtc_setup_lm_bounds(crtc, crtc->state);
+	}
+
+	if (dpu_crtc->event) {
+		WARN_ON(dpu_crtc->event);
+	} else {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		dpu_crtc->event = crtc->state->event;
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+
+		/* encoder will trigger pending mask now */
+		dpu_encoder_trigger_kickoff_pending(encoder);
+	}
+
+	/*
+	 * If no mixers have been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	_dpu_crtc_blend_setup(crtc);
+
+	/*
+	 * PP_DONE irq is only used by command mode for now.
+	 * It is better to request pending before FLUSH and START trigger
+	 * to make sure no pp_done irq missed.
+	 * This is safe because no pp_done will happen before SW trigger
+	 * in command mode.
+	 */
+}
+
+static void dpu_crtc_atomic_flush(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_crtc_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_device *dev;
+	struct drm_plane *plane;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *event_thread;
+	unsigned long flags;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("crtc%d -> enable %d, skip atomic_flush\n",
+				crtc->base.id, crtc->state->enable);
+		return;
+	}
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(crtc->state);
+	dev = crtc->dev;
+	priv = dev->dev_private;
+
+	if (crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index[%d]\n", crtc->index);
+		return;
+	}
+
+	event_thread = &priv->event_thread[crtc->index];
+
+	if (dpu_crtc->event) {
+		DPU_DEBUG("already received dpu_crtc->event\n");
+	} else {
+		spin_lock_irqsave(&dev->event_lock, flags);
+		dpu_crtc->event = crtc->state->event;
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&dev->event_lock, flags);
+	}
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to flush a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	/*
+	 * For planes without commit update, drm framework will not add
+	 * those planes to current state since hardware update is not
+	 * required. However, if those planes were power collapsed since
+	 * last commit cycle, driver has to restore the hardware state
+	 * of those planes explicitly here prior to plane flush.
+	 */
+	drm_atomic_crtc_for_each_plane(plane, crtc)
+		dpu_plane_restore(plane);
+
+	/* update performance setting before crtc kickoff */
+	dpu_core_perf_crtc_update(crtc, 1, false);
+
+	/*
+	 * Final plane updates: Give each plane a chance to complete all
+	 *                      required writes/flushing before crtc's "flush
+	 *                      everything" call below.
+	 */
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		if (dpu_crtc->smmu_state.transition_error)
+			dpu_plane_set_error(plane, true);
+		dpu_plane_flush(plane);
+	}
+
+	/* Kickoff will be scheduled by outer layer */
+}
+
+/**
+ * dpu_crtc_destroy_state - state destroy hook
+ * @crtc: drm CRTC
+ * @state: CRTC state object to release
+ */
+static void dpu_crtc_destroy_state(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc || !state) {
+		DPU_ERROR("invalid argument(s)\n");
+		return;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	DPU_DEBUG("crtc%d\n", crtc->base.id);
+
+	_dpu_crtc_rp_destroy(&cstate->rp);
+
+	__drm_atomic_helper_crtc_destroy_state(state);
+
+	kfree(cstate);
+}
+
+static int _dpu_crtc_wait_for_frame_done(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	int ret, rc = 0;
+
+	if (!crtc) {
+		DPU_ERROR("invalid argument\n");
+		return -EINVAL;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	if (!atomic_read(&dpu_crtc->frame_pending)) {
+		DPU_DEBUG("no frames pending\n");
+		return 0;
+	}
+
+	DPU_ATRACE_BEGIN("frame done completion wait");
+	ret = wait_for_completion_timeout(&dpu_crtc->frame_done_comp,
+			msecs_to_jiffies(DPU_FRAME_DONE_TIMEOUT));
+	if (!ret) {
+		DRM_ERROR("frame done wait timed out, ret:%d\n", ret);
+		rc = -ETIMEDOUT;
+	}
+	DPU_ATRACE_END("frame done completion wait");
+
+	return rc;
+}
+
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_crtc_state *cstate;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+	dev = crtc->dev;
+	dpu_crtc = to_dpu_crtc(crtc);
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	priv = dpu_kms->dev->dev_private;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	/*
+	 * If no mixers has been allocated in dpu_crtc_atomic_check(),
+	 * it means we are trying to start a CRTC whose state is disabled:
+	 * nothing else needs to be done.
+	 */
+	if (unlikely(!dpu_crtc->num_mixers))
+		return;
+
+	DPU_ATRACE_BEGIN("crtc_commit");
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		struct dpu_encoder_kickoff_params params = { 0 };
+
+		if (encoder->crtc != crtc)
+			continue;
+
+		/*
+		 * Encoder will flush/start now, unless it has a tx pending.
+		 * If so, it may delay and flush at an irq event (e.g. ppdone)
+		 */
+		dpu_encoder_prepare_for_kickoff(encoder, &params);
+	}
+
+	/* wait for frame_event_done completion */
+	DPU_ATRACE_BEGIN("wait_for_frame_done_event");
+	ret = _dpu_crtc_wait_for_frame_done(crtc);
+	DPU_ATRACE_END("wait_for_frame_done_event");
+	if (ret) {
+		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+				crtc->base.id,
+				atomic_read(&dpu_crtc->frame_pending));
+		goto end;
+	}
+
+	if (atomic_inc_return(&dpu_crtc->frame_pending) == 1) {
+		/* acquire bandwidth and other resources */
+		DPU_DEBUG("crtc%d first commit\n", crtc->base.id);
+	} else
+		DPU_DEBUG("crtc%d commit\n", crtc->base.id);
+
+	dpu_crtc->play_count++;
+
+	dpu_vbif_clear_errors(dpu_kms);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+
+		dpu_encoder_kickoff(encoder);
+	}
+
+end:
+	reinit_completion(&dpu_crtc->frame_done_comp);
+	DPU_ATRACE_END("crtc_commit");
+}
+
+/**
+ * _dpu_crtc_vblank_enable_no_lock - update power resource and vblank request
+ * @dpu_crtc: Pointer to dpu crtc structure
+ * @enable: Whether to enable/disable vblanks
+ *
+ * @Return: error code
+ */
+static int _dpu_crtc_vblank_enable_no_lock(
+		struct dpu_crtc *dpu_crtc, bool enable)
+{
+	struct drm_device *dev;
+	struct drm_crtc *crtc;
+	struct drm_encoder *enc;
+
+	if (!dpu_crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	crtc = &dpu_crtc->base;
+	dev = crtc->dev;
+
+	if (enable) {
+		int ret;
+
+		/* drop lock since power crtc cb may try to re-acquire lock */
+		mutex_unlock(&dpu_crtc->crtc_lock);
+		ret = _dpu_crtc_power_enable(dpu_crtc, true);
+		mutex_lock(&dpu_crtc->crtc_lock);
+		if (ret)
+			return ret;
+
+		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
+			if (enc->crtc != crtc)
+				continue;
+
+			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
+						     DRMID(enc), enable,
+						     dpu_crtc);
+
+			dpu_encoder_register_vblank_callback(enc,
+					dpu_crtc_vblank_cb, (void *)crtc);
+		}
+	} else {
+		list_for_each_entry(enc, &dev->mode_config.encoder_list, head) {
+			if (enc->crtc != crtc)
+				continue;
+
+			trace_dpu_crtc_vblank_enable(DRMID(&dpu_crtc->base),
+						     DRMID(enc), enable,
+						     dpu_crtc);
+
+			dpu_encoder_register_vblank_callback(enc, NULL, NULL);
+		}
+
+		/* drop lock since power crtc cb may try to re-acquire lock */
+		mutex_unlock(&dpu_crtc->crtc_lock);
+		_dpu_crtc_power_enable(dpu_crtc, false);
+		mutex_lock(&dpu_crtc->crtc_lock);
+	}
+
+	return 0;
+}
+
+/**
+ * _dpu_crtc_set_suspend - notify crtc of suspend enable/disable
+ * @crtc: Pointer to drm crtc object
+ * @enable: true to enable suspend, false to indicate resume
+ */
+static void _dpu_crtc_set_suspend(struct drm_crtc *crtc, bool enable)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int ret = 0;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+
+	if (!priv->kms) {
+		DPU_ERROR("invalid crtc kms\n");
+		return;
+	}
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	DRM_DEBUG_KMS("crtc%d suspend = %d\n", crtc->base.id, enable);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	/*
+	 * If the vblank is enabled, release a power reference on suspend
+	 * and take it back during resume (if it is still enabled).
+	 */
+	trace_dpu_crtc_set_suspend(DRMID(&dpu_crtc->base), enable, dpu_crtc);
+	if (dpu_crtc->suspend == enable)
+		DPU_DEBUG("crtc%d suspend already set to %d, ignoring update\n",
+				crtc->base.id, enable);
+	else if (dpu_crtc->enabled && dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, !enable);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+
+	dpu_crtc->suspend = enable;
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+/**
+ * dpu_crtc_duplicate_state - state duplicate hook
+ * @crtc: Pointer to drm crtc structure
+ * @Returns: Pointer to new drm_crtc_state structure
+ */
+static struct drm_crtc_state *dpu_crtc_duplicate_state(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate, *old_cstate;
+
+	if (!crtc || !crtc->state) {
+		DPU_ERROR("invalid argument(s)\n");
+		return NULL;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	old_cstate = to_dpu_crtc_state(crtc->state);
+	cstate = kmemdup(old_cstate, sizeof(*old_cstate), GFP_KERNEL);
+	if (!cstate) {
+		DPU_ERROR("failed to allocate state\n");
+		return NULL;
+	}
+
+	/* duplicate base helper */
+	__drm_atomic_helper_crtc_duplicate_state(crtc, &cstate->base);
+
+	_dpu_crtc_rp_duplicate(&old_cstate->rp, &cstate->rp);
+
+	return &cstate->base;
+}
+
+/**
+ * dpu_crtc_reset - reset hook for CRTCs
+ * Resets the atomic state for @crtc by freeing the state pointer (which might
+ * be NULL, e.g. at driver load time) and allocating a new empty state object.
+ * @crtc: Pointer to drm crtc structure
+ */
+static void dpu_crtc_reset(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+
+	/* revert suspend actions, if necessary */
+	if (dpu_kms_is_suspend_state(crtc->dev))
+		_dpu_crtc_set_suspend(crtc, false);
+
+	/* remove previous state, if present */
+	if (crtc->state) {
+		dpu_crtc_destroy_state(crtc, crtc->state);
+		crtc->state = 0;
+	}
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = kzalloc(sizeof(*cstate), GFP_KERNEL);
+	if (!cstate) {
+		DPU_ERROR("failed to allocate state\n");
+		return;
+	}
+
+	_dpu_crtc_rp_reset(&cstate->rp, &dpu_crtc->rp_lock,
+			&dpu_crtc->rp_head);
+
+	cstate->base.crtc = crtc;
+	crtc->state = &cstate->base;
+}
+
+static void dpu_crtc_handle_power_event(u32 event_type, void *arg)
+{
+	struct drm_crtc *crtc = arg;
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct dpu_crtc_mixer *m;
+	u32 i, misr_status;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	trace_dpu_crtc_handle_power_event(DRMID(crtc), event_type);
+
+	switch (event_type) {
+	case DPU_POWER_EVENT_POST_ENABLE:
+		/* restore encoder; crtc will be programmed during commit */
+		drm_for_each_encoder(encoder, crtc->dev) {
+			if (encoder->crtc != crtc)
+				continue;
+
+			dpu_encoder_virt_restore(encoder);
+		}
+
+		for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+			m = &dpu_crtc->mixers[i];
+			if (!m->hw_lm || !m->hw_lm->ops.setup_misr ||
+					!dpu_crtc->misr_enable)
+				continue;
+
+			m->hw_lm->ops.setup_misr(m->hw_lm, true,
+					dpu_crtc->misr_frame_count);
+		}
+		break;
+	case DPU_POWER_EVENT_PRE_DISABLE:
+		for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+			m = &dpu_crtc->mixers[i];
+			if (!m->hw_lm || !m->hw_lm->ops.collect_misr ||
+					!dpu_crtc->misr_enable)
+				continue;
+
+			misr_status = m->hw_lm->ops.collect_misr(m->hw_lm);
+			dpu_crtc->misr_data[i] = misr_status ? misr_status :
+							dpu_crtc->misr_data[i];
+		}
+		break;
+	case DPU_POWER_EVENT_POST_DISABLE:
+		/**
+		 * Nothing to do. All the planes on the CRTC will be
+		 * programmed for every frame
+		 */
+		break;
+	default:
+		DPU_DEBUG("event:%d not handled\n", event_type);
+		break;
+	}
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+static void dpu_crtc_disable(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_state *cstate;
+	struct drm_display_mode *mode;
+	struct drm_encoder *encoder;
+	struct msm_drm_private *priv;
+	int ret;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(crtc->state);
+	mode = &cstate->base.adjusted_mode;
+	priv = crtc->dev->dev_private;
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+
+	if (dpu_kms_is_suspend_state(crtc->dev))
+		_dpu_crtc_set_suspend(crtc, true);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+
+	/* wait for frame_event_done completion */
+	if (_dpu_crtc_wait_for_frame_done(crtc))
+		DPU_ERROR("crtc%d wait for frame done failed;frame_pending%d\n",
+				crtc->base.id,
+				atomic_read(&dpu_crtc->frame_pending));
+
+	trace_dpu_crtc_disable(DRMID(crtc), false, dpu_crtc);
+	if (dpu_crtc->enabled && !dpu_crtc->suspend &&
+			dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, false);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->enabled = false;
+
+	if (atomic_read(&dpu_crtc->frame_pending)) {
+		trace_dpu_crtc_disable_frame_pending(DRMID(crtc),
+				     atomic_read(&dpu_crtc->frame_pending));
+		dpu_core_perf_crtc_release_bw(crtc);
+		atomic_set(&dpu_crtc->frame_pending, 0);
+	}
+
+	dpu_core_perf_crtc_update(crtc, 0, true);
+
+	drm_for_each_encoder(encoder, crtc->dev) {
+		if (encoder->crtc != crtc)
+			continue;
+		dpu_encoder_register_frame_event_callback(encoder, NULL, NULL);
+	}
+
+	if (dpu_crtc->power_event)
+		dpu_power_handle_unregister_event(dpu_crtc->phandle,
+				dpu_crtc->power_event);
+
+
+	memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers));
+	dpu_crtc->num_mixers = 0;
+	dpu_crtc->mixers_swapped = false;
+
+	/* disable clk & bw control until clk & bw properties are set */
+	cstate->bw_control = false;
+	cstate->bw_split_vote = false;
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+}
+
+static void dpu_crtc_enable(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_crtc_state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct drm_encoder *encoder;
+	struct msm_drm_private *priv;
+	int ret;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private) {
+		DPU_ERROR("invalid crtc\n");
+		return;
+	}
+	priv = crtc->dev->dev_private;
+
+	DRM_DEBUG_KMS("crtc%d\n", crtc->base.id);
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	drm_for_each_encoder(encoder, crtc->dev) {
+		if (encoder->crtc != crtc)
+			continue;
+		dpu_encoder_register_frame_event_callback(encoder,
+				dpu_crtc_frame_event_cb, (void *)crtc);
+	}
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	trace_dpu_crtc_enable(DRMID(crtc), true, dpu_crtc);
+	if (!dpu_crtc->enabled && !dpu_crtc->suspend &&
+			dpu_crtc->vblank_requested) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, true);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->enabled = true;
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	dpu_crtc->power_event = dpu_power_handle_register_event(
+		dpu_crtc->phandle,
+		DPU_POWER_EVENT_POST_ENABLE | DPU_POWER_EVENT_POST_DISABLE |
+		DPU_POWER_EVENT_PRE_DISABLE,
+		dpu_crtc_handle_power_event, crtc, dpu_crtc->name);
+
+}
+
+struct plane_state {
+	struct dpu_plane_state *dpu_pstate;
+	const struct drm_plane_state *drm_pstate;
+	int stage;
+	u32 pipe_id;
+};
+
+static int dpu_crtc_atomic_check(struct drm_crtc *crtc,
+		struct drm_crtc_state *state)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct plane_state *pstates;
+	struct dpu_crtc_state *cstate;
+
+	const struct drm_plane_state *pstate;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+
+	int cnt = 0, rc = 0, mixer_width, i, z_pos;
+
+	struct dpu_multirect_plane_states multirect_plane[DPU_STAGE_MAX * 2];
+	int multirect_count = 0;
+	const struct drm_plane_state *pipe_staged[SSPP_MAX];
+	int left_zpos_cnt = 0, right_zpos_cnt = 0;
+	struct drm_rect crtc_rect = { 0 };
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL);
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	cstate = to_dpu_crtc_state(state);
+
+	if (!state->enable || !state->active) {
+		DPU_DEBUG("crtc%d -> enable %d, active %d, skip atomic_check\n",
+				crtc->base.id, state->enable, state->active);
+		goto end;
+	}
+
+	mode = &state->adjusted_mode;
+	DPU_DEBUG("%s: check", dpu_crtc->name);
+
+	/* force a full mode set if active state changed */
+	if (state->active_changed)
+		state->mode_changed = true;
+
+	memset(pipe_staged, 0, sizeof(pipe_staged));
+
+	mixer_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode);
+
+	_dpu_crtc_setup_lm_bounds(crtc, state);
+
+	crtc_rect.x2 = mode->hdisplay;
+	crtc_rect.y2 = mode->vdisplay;
+
+	 /* get plane state for all drm planes associated with crtc state */
+	drm_atomic_crtc_state_for_each_plane_state(plane, pstate, state) {
+		struct drm_rect dst, clip = crtc_rect;
+
+		if (IS_ERR_OR_NULL(pstate)) {
+			rc = PTR_ERR(pstate);
+			DPU_ERROR("%s: failed to get plane%d state, %d\n",
+					dpu_crtc->name, plane->base.id, rc);
+			goto end;
+		}
+		if (cnt >= DPU_STAGE_MAX * 4)
+			continue;
+
+		pstates[cnt].dpu_pstate = to_dpu_plane_state(pstate);
+		pstates[cnt].drm_pstate = pstate;
+		pstates[cnt].stage = pstate->normalized_zpos;
+		pstates[cnt].pipe_id = dpu_plane_pipe(plane);
+
+		if (pipe_staged[pstates[cnt].pipe_id]) {
+			multirect_plane[multirect_count].r0 =
+				pipe_staged[pstates[cnt].pipe_id];
+			multirect_plane[multirect_count].r1 = pstate;
+			multirect_count++;
+
+			pipe_staged[pstates[cnt].pipe_id] = NULL;
+		} else {
+			pipe_staged[pstates[cnt].pipe_id] = pstate;
+		}
+
+		cnt++;
+
+		dst = drm_plane_state_dest(pstate);
+		if (!drm_rect_intersect(&clip, &dst) ||
+		    !drm_rect_equals(&clip, &dst)) {
+			DPU_ERROR("invalid vertical/horizontal destination\n");
+			DPU_ERROR("display: " DRM_RECT_FMT " plane: "
+				  DRM_RECT_FMT "\n", DRM_RECT_ARG(&crtc_rect),
+				  DRM_RECT_ARG(&dst));
+			rc = -E2BIG;
+			goto end;
+		}
+	}
+
+	for (i = 1; i < SSPP_MAX; i++) {
+		if (pipe_staged[i]) {
+			dpu_plane_clear_multirect(pipe_staged[i]);
+
+			if (is_dpu_plane_virtual(pipe_staged[i]->plane)) {
+				DPU_ERROR(
+					"r1 only virt plane:%d not supported\n",
+					pipe_staged[i]->plane->base.id);
+				rc  = -EINVAL;
+				goto end;
+			}
+		}
+	}
+
+	z_pos = -1;
+	for (i = 0; i < cnt; i++) {
+		/* reset counts at every new blend stage */
+		if (pstates[i].stage != z_pos) {
+			left_zpos_cnt = 0;
+			right_zpos_cnt = 0;
+			z_pos = pstates[i].stage;
+		}
+
+		/* verify z_pos setting before using it */
+		if (z_pos >= DPU_STAGE_MAX - DPU_STAGE_0) {
+			DPU_ERROR("> %d plane stages assigned\n",
+					DPU_STAGE_MAX - DPU_STAGE_0);
+			rc = -EINVAL;
+			goto end;
+		} else if (pstates[i].drm_pstate->crtc_x < mixer_width) {
+			if (left_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on left\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			left_zpos_cnt++;
+
+		} else {
+			if (right_zpos_cnt == 2) {
+				DPU_ERROR("> 2 planes @ stage %d on right\n",
+					z_pos);
+				rc = -EINVAL;
+				goto end;
+			}
+			right_zpos_cnt++;
+		}
+
+		pstates[i].dpu_pstate->stage = z_pos + DPU_STAGE_0;
+		DPU_DEBUG("%s: zpos %d", dpu_crtc->name, z_pos);
+	}
+
+	for (i = 0; i < multirect_count; i++) {
+		if (dpu_plane_validate_multirect_v2(&multirect_plane[i])) {
+			DPU_ERROR(
+			"multirect validation failed for planes (%d - %d)\n",
+					multirect_plane[i].r0->plane->base.id,
+					multirect_plane[i].r1->plane->base.id);
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+	rc = dpu_core_perf_crtc_check(crtc, state);
+	if (rc) {
+		DPU_ERROR("crtc%d failed performance check %d\n",
+				crtc->base.id, rc);
+		goto end;
+	}
+
+	/* validate source split:
+	 * use pstates sorted by stage to check planes on same stage
+	 * we assume that all pipes are in source split so its valid to compare
+	 * without taking into account left/right mixer placement
+	 */
+	for (i = 1; i < cnt; i++) {
+		struct plane_state *prv_pstate, *cur_pstate;
+		struct drm_rect left_rect, right_rect;
+		int32_t left_pid, right_pid;
+		int32_t stage;
+
+		prv_pstate = &pstates[i - 1];
+		cur_pstate = &pstates[i];
+		if (prv_pstate->stage != cur_pstate->stage)
+			continue;
+
+		stage = cur_pstate->stage;
+
+		left_pid = prv_pstate->dpu_pstate->base.plane->base.id;
+		left_rect = drm_plane_state_dest(prv_pstate->drm_pstate);
+
+		right_pid = cur_pstate->dpu_pstate->base.plane->base.id;
+		right_rect = drm_plane_state_dest(cur_pstate->drm_pstate);
+
+		if (right_rect.x1 < left_rect.x1) {
+			swap(left_pid, right_pid);
+			swap(left_rect, right_rect);
+		}
+
+		/**
+		 * - planes are enumerated in pipe-priority order such that
+		 *   planes with lower drm_id must be left-most in a shared
+		 *   blend-stage when using source split.
+		 * - planes in source split must be contiguous in width
+		 * - planes in source split must have same dest yoff and height
+		 */
+		if (right_pid < left_pid) {
+			DPU_ERROR(
+				"invalid src split cfg. priority mismatch. stage: %d left: %d right: %d\n",
+				stage, left_pid, right_pid);
+			rc = -EINVAL;
+			goto end;
+		} else if (right_rect.x1 != drm_rect_width(&left_rect)) {
+			DPU_ERROR("non-contiguous coordinates for src split. "
+				  "stage: %d left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		} else if (left_rect.y1 != right_rect.y1 ||
+			   drm_rect_height(&left_rect) != drm_rect_height(&right_rect)) {
+			DPU_ERROR("source split at stage: %d. invalid "
+				  "yoff/height: left: " DRM_RECT_FMT " right: "
+				  DRM_RECT_FMT "\n", stage,
+				  DRM_RECT_ARG(&left_rect),
+				  DRM_RECT_ARG(&right_rect));
+			rc = -EINVAL;
+			goto end;
+		}
+	}
+
+end:
+	_dpu_crtc_rp_free_unused(&cstate->rp);
+	kfree(pstates);
+	return rc;
+}
+
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en)
+{
+	struct dpu_crtc *dpu_crtc;
+	int ret;
+
+	if (!crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	trace_dpu_crtc_vblank(DRMID(&dpu_crtc->base), en, dpu_crtc);
+	if (dpu_crtc->enabled && !dpu_crtc->suspend) {
+		ret = _dpu_crtc_vblank_enable_no_lock(dpu_crtc, en);
+		if (ret)
+			DPU_ERROR("%s vblank enable failed: %d\n",
+					dpu_crtc->name, ret);
+	}
+	dpu_crtc->vblank_requested = en;
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	return 0;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_debugfs_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_plane_state *pstate = NULL;
+	struct dpu_crtc_mixer *m;
+
+	struct drm_crtc *crtc;
+	struct drm_plane *plane;
+	struct drm_display_mode *mode;
+	struct drm_framebuffer *fb;
+	struct drm_plane_state *state;
+	struct dpu_crtc_state *cstate;
+
+	int i, out_width;
+
+	if (!s || !s->private)
+		return -EINVAL;
+
+	dpu_crtc = s->private;
+	crtc = &dpu_crtc->base;
+	cstate = to_dpu_crtc_state(crtc->state);
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	mode = &crtc->state->adjusted_mode;
+	out_width = dpu_crtc_get_mixer_width(dpu_crtc, cstate, mode);
+
+	seq_printf(s, "crtc:%d width:%d height:%d\n", crtc->base.id,
+				mode->hdisplay, mode->vdisplay);
+
+	seq_puts(s, "\n");
+
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm)
+			seq_printf(s, "\tmixer[%d] has no lm\n", i);
+		else if (!m->hw_ctl)
+			seq_printf(s, "\tmixer[%d] has no ctl\n", i);
+		else
+			seq_printf(s, "\tmixer:%d ctl:%d width:%d height:%d\n",
+				m->hw_lm->idx - LM_0, m->hw_ctl->idx - CTL_0,
+				out_width, mode->vdisplay);
+	}
+
+	seq_puts(s, "\n");
+
+	drm_atomic_crtc_for_each_plane(plane, crtc) {
+		pstate = to_dpu_plane_state(plane->state);
+		state = plane->state;
+
+		if (!pstate || !state)
+			continue;
+
+		seq_printf(s, "\tplane:%u stage:%d\n", plane->base.id,
+			pstate->stage);
+
+		if (plane->state->fb) {
+			fb = plane->state->fb;
+
+			seq_printf(s, "\tfb:%d image format:%4.4s wxh:%ux%u ",
+				fb->base.id, (char *) &fb->format->format,
+				fb->width, fb->height);
+			for (i = 0; i < ARRAY_SIZE(fb->format->cpp); ++i)
+				seq_printf(s, "cpp[%d]:%u ",
+						i, fb->format->cpp[i]);
+			seq_puts(s, "\n\t");
+
+			seq_printf(s, "modifier:%8llu ", fb->modifier);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->pitches); i++)
+				seq_printf(s, "pitches[%d]:%8u ", i,
+							fb->pitches[i]);
+			seq_puts(s, "\n");
+
+			seq_puts(s, "\t");
+			for (i = 0; i < ARRAY_SIZE(fb->offsets); i++)
+				seq_printf(s, "offsets[%d]:%8u ", i,
+							fb->offsets[i]);
+			seq_puts(s, "\n");
+		}
+
+		seq_printf(s, "\tsrc_x:%4d src_y:%4d src_w:%4d src_h:%4d\n",
+			state->src_x, state->src_y, state->src_w, state->src_h);
+
+		seq_printf(s, "\tdst x:%4d dst_y:%4d dst_w:%4d dst_h:%4d\n",
+			state->crtc_x, state->crtc_y, state->crtc_w,
+			state->crtc_h);
+		seq_printf(s, "\tmultirect: mode: %d index: %d\n",
+			pstate->multirect_mode, pstate->multirect_index);
+
+		seq_puts(s, "\n");
+	}
+	if (dpu_crtc->vblank_cb_count) {
+		ktime_t diff = ktime_sub(ktime_get(), dpu_crtc->vblank_cb_time);
+		s64 diff_ms = ktime_to_ms(diff);
+		s64 fps = diff_ms ? div_s64(
+				dpu_crtc->vblank_cb_count * 1000, diff_ms) : 0;
+
+		seq_printf(s,
+			"vblank fps:%lld count:%u total:%llums total_framecount:%llu\n",
+				fps, dpu_crtc->vblank_cb_count,
+				ktime_to_ms(diff), dpu_crtc->play_count);
+
+		/* reset time & count for next measurement */
+		dpu_crtc->vblank_cb_count = 0;
+		dpu_crtc->vblank_cb_time = ktime_set(0, 0);
+	}
+
+	seq_printf(s, "vblank_enable:%d\n", dpu_crtc->vblank_requested);
+
+	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	return 0;
+}
+
+static int _dpu_debugfs_status_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, _dpu_debugfs_status_show, inode->i_private);
+}
+
+static ssize_t _dpu_crtc_misr_setup(struct file *file,
+		const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_mixer *m;
+	int i = 0, rc;
+	char buf[MISR_BUFF_SIZE + 1];
+	u32 frame_count, enable;
+	size_t buff_copy;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_crtc = file->private_data;
+	buff_copy = min_t(size_t, count, MISR_BUFF_SIZE);
+	if (copy_from_user(buf, user_buf, buff_copy)) {
+		DPU_ERROR("buffer copy failed\n");
+		return -EINVAL;
+	}
+
+	buf[buff_copy] = 0; /* end of string */
+
+	if (sscanf(buf, "%u %u", &enable, &frame_count) != 2)
+		return -EINVAL;
+
+	rc = _dpu_crtc_power_enable(dpu_crtc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	dpu_crtc->misr_enable = enable;
+	dpu_crtc->misr_frame_count = frame_count;
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		dpu_crtc->misr_data[i] = 0;
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm || !m->hw_lm->ops.setup_misr)
+			continue;
+
+		m->hw_lm->ops.setup_misr(m->hw_lm, enable, frame_count);
+	}
+	mutex_unlock(&dpu_crtc->crtc_lock);
+	_dpu_crtc_power_enable(dpu_crtc, false);
+
+	return count;
+}
+
+static ssize_t _dpu_crtc_misr_read(struct file *file,
+		char __user *user_buff, size_t count, loff_t *ppos)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_crtc_mixer *m;
+	int i = 0, rc;
+	u32 misr_status;
+	ssize_t len = 0;
+	char buf[MISR_BUFF_SIZE + 1] = {'\0'};
+
+	if (*ppos)
+		return 0;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_crtc = file->private_data;
+	rc = _dpu_crtc_power_enable(dpu_crtc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_crtc->crtc_lock);
+	if (!dpu_crtc->misr_enable) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"disabled\n");
+		goto buff_check;
+	}
+
+	for (i = 0; i < dpu_crtc->num_mixers; ++i) {
+		m = &dpu_crtc->mixers[i];
+		if (!m->hw_lm || !m->hw_lm->ops.collect_misr)
+			continue;
+
+		misr_status = m->hw_lm->ops.collect_misr(m->hw_lm);
+		dpu_crtc->misr_data[i] = misr_status ? misr_status :
+							dpu_crtc->misr_data[i];
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "lm idx:%d\n",
+					m->hw_lm->idx - LM_0);
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n",
+							dpu_crtc->misr_data[i]);
+	}
+
+buff_check:
+	if (count <= len) {
+		len = 0;
+		goto end;
+	}
+
+	if (copy_to_user(user_buff, buf, len)) {
+		len = -EFAULT;
+		goto end;
+	}
+
+	*ppos += len;   /* increase offset */
+
+end:
+	mutex_unlock(&dpu_crtc->crtc_lock);
+	_dpu_crtc_power_enable(dpu_crtc, false);
+	return len;
+}
+
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)                          \
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_crtc_debugfs_state_show(struct seq_file *s, void *v)
+{
+	struct drm_crtc *crtc = (struct drm_crtc *) s->private;
+	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
+	struct dpu_crtc_res *res;
+	struct dpu_crtc_respool *rp;
+	int i;
+
+	seq_printf(s, "client type: %d\n", dpu_crtc_get_client_type(crtc));
+	seq_printf(s, "intf_mode: %d\n", dpu_crtc_get_intf_mode(crtc));
+	seq_printf(s, "core_clk_rate: %llu\n",
+			dpu_crtc->cur_perf.core_clk_rate);
+	for (i = DPU_POWER_HANDLE_DBUS_ID_MNOC;
+			i < DPU_POWER_HANDLE_DBUS_ID_MAX; i++) {
+		seq_printf(s, "bw_ctl[%s]: %llu\n",
+				dpu_power_handle_get_dbus_name(i),
+				dpu_crtc->cur_perf.bw_ctl[i]);
+		seq_printf(s, "max_per_pipe_ib[%s]: %llu\n",
+				dpu_power_handle_get_dbus_name(i),
+				dpu_crtc->cur_perf.max_per_pipe_ib[i]);
+	}
+
+	mutex_lock(&dpu_crtc->rp_lock);
+	list_for_each_entry(rp, &dpu_crtc->rp_head, rp_list) {
+		seq_printf(s, "rp.%d: ", rp->sequence_id);
+		list_for_each_entry(res, &rp->res_list, list)
+			seq_printf(s, "0x%x/0x%llx/%pK/%d ",
+					res->type, res->tag, res->val,
+					atomic_read(&res->refcount));
+		seq_puts(s, "\n");
+	}
+	mutex_unlock(&dpu_crtc->rp_lock);
+
+	return 0;
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_crtc_debugfs_state);
+
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+	struct dpu_kms *dpu_kms;
+
+	static const struct file_operations debugfs_status_fops = {
+		.open =		_dpu_debugfs_status_open,
+		.read =		seq_read,
+		.llseek =	seq_lseek,
+		.release =	single_release,
+	};
+	static const struct file_operations debugfs_misr_fops = {
+		.open =		simple_open,
+		.read =		_dpu_crtc_misr_read,
+		.write =	_dpu_crtc_misr_setup,
+	};
+
+	if (!crtc)
+		return -EINVAL;
+	dpu_crtc = to_dpu_crtc(crtc);
+
+	dpu_kms = _dpu_crtc_get_kms(crtc);
+	if (!dpu_kms)
+		return -EINVAL;
+
+	dpu_crtc->debugfs_root = debugfs_create_dir(dpu_crtc->name,
+			crtc->dev->primary->debugfs_root);
+	if (!dpu_crtc->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_file("status", 0400,
+			dpu_crtc->debugfs_root,
+			dpu_crtc, &debugfs_status_fops);
+	debugfs_create_file("state", 0600,
+			dpu_crtc->debugfs_root,
+			&dpu_crtc->base,
+			&dpu_crtc_debugfs_state_fops);
+	debugfs_create_file("misr_data", 0600, dpu_crtc->debugfs_root,
+					dpu_crtc, &debugfs_misr_fops);
+
+	return 0;
+}
+
+static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+
+	if (!crtc)
+		return;
+	dpu_crtc = to_dpu_crtc(crtc);
+	debugfs_remove_recursive(dpu_crtc->debugfs_root);
+}
+#else
+static int _dpu_crtc_init_debugfs(struct drm_crtc *crtc)
+{
+	return 0;
+}
+
+static void _dpu_crtc_destroy_debugfs(struct drm_crtc *crtc)
+{
+}
+#endif /* CONFIG_DEBUG_FS */
+
+static int dpu_crtc_late_register(struct drm_crtc *crtc)
+{
+	return _dpu_crtc_init_debugfs(crtc);
+}
+
+static void dpu_crtc_early_unregister(struct drm_crtc *crtc)
+{
+	_dpu_crtc_destroy_debugfs(crtc);
+}
+
+static const struct drm_crtc_funcs dpu_crtc_funcs = {
+	.set_config = drm_atomic_helper_set_config,
+	.destroy = dpu_crtc_destroy,
+	.page_flip = drm_atomic_helper_page_flip,
+	.reset = dpu_crtc_reset,
+	.atomic_duplicate_state = dpu_crtc_duplicate_state,
+	.atomic_destroy_state = dpu_crtc_destroy_state,
+	.late_register = dpu_crtc_late_register,
+	.early_unregister = dpu_crtc_early_unregister,
+};
+
+static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
+	.disable = dpu_crtc_disable,
+	.atomic_enable = dpu_crtc_enable,
+	.atomic_check = dpu_crtc_atomic_check,
+	.atomic_begin = dpu_crtc_atomic_begin,
+	.atomic_flush = dpu_crtc_atomic_flush,
+};
+
+static void _dpu_crtc_event_cb(struct kthread_work *work)
+{
+	struct dpu_crtc_event *event;
+	struct dpu_crtc *dpu_crtc;
+	unsigned long irq_flags;
+
+	if (!work) {
+		DPU_ERROR("invalid work item\n");
+		return;
+	}
+
+	event = container_of(work, struct dpu_crtc_event, kt_work);
+
+	/* set dpu_crtc to NULL for static work structures */
+	dpu_crtc = event->dpu_crtc;
+	if (!dpu_crtc)
+		return;
+
+	if (event->cb_func)
+		event->cb_func(&dpu_crtc->base, event->usr);
+
+	spin_lock_irqsave(&dpu_crtc->event_lock, irq_flags);
+	list_add_tail(&event->list, &dpu_crtc->event_free_list);
+	spin_unlock_irqrestore(&dpu_crtc->event_lock, irq_flags);
+}
+
+int dpu_crtc_event_queue(struct drm_crtc *crtc,
+		void (*func)(struct drm_crtc *crtc, void *usr), void *usr)
+{
+	unsigned long irq_flags;
+	struct dpu_crtc *dpu_crtc;
+	struct msm_drm_private *priv;
+	struct dpu_crtc_event *event = NULL;
+	u32 crtc_id;
+
+	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !func) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+	dpu_crtc = to_dpu_crtc(crtc);
+	priv = crtc->dev->dev_private;
+	crtc_id = drm_crtc_index(crtc);
+
+	/*
+	 * Obtain an event struct from the private cache. This event
+	 * queue may be called from ISR contexts, so use a private
+	 * cache to avoid calling any memory allocation functions.
+	 */
+	spin_lock_irqsave(&dpu_crtc->event_lock, irq_flags);
+	if (!list_empty(&dpu_crtc->event_free_list)) {
+		event = list_first_entry(&dpu_crtc->event_free_list,
+				struct dpu_crtc_event, list);
+		list_del_init(&event->list);
+	}
+	spin_unlock_irqrestore(&dpu_crtc->event_lock, irq_flags);
+
+	if (!event)
+		return -ENOMEM;
+
+	/* populate event node */
+	event->dpu_crtc = dpu_crtc;
+	event->cb_func = func;
+	event->usr = usr;
+
+	/* queue new event request */
+	kthread_init_work(&event->kt_work, _dpu_crtc_event_cb);
+	kthread_queue_work(&priv->event_thread[crtc_id].worker,
+			&event->kt_work);
+
+	return 0;
+}
+
+static int _dpu_crtc_init_events(struct dpu_crtc *dpu_crtc)
+{
+	int i, rc = 0;
+
+	if (!dpu_crtc) {
+		DPU_ERROR("invalid crtc\n");
+		return -EINVAL;
+	}
+
+	spin_lock_init(&dpu_crtc->event_lock);
+
+	INIT_LIST_HEAD(&dpu_crtc->event_free_list);
+	for (i = 0; i < DPU_CRTC_MAX_EVENT_COUNT; ++i)
+		list_add_tail(&dpu_crtc->event_cache[i].list,
+				&dpu_crtc->event_free_list);
+
+	return rc;
+}
+
+/* initialize crtc */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane)
+{
+	struct drm_crtc *crtc = NULL;
+	struct dpu_crtc *dpu_crtc = NULL;
+	struct msm_drm_private *priv = NULL;
+	struct dpu_kms *kms = NULL;
+	int i, rc;
+
+	priv = dev->dev_private;
+	kms = to_dpu_kms(priv->kms);
+
+	dpu_crtc = kzalloc(sizeof(*dpu_crtc), GFP_KERNEL);
+	if (!dpu_crtc)
+		return ERR_PTR(-ENOMEM);
+
+	crtc = &dpu_crtc->base;
+	crtc->dev = dev;
+
+	mutex_init(&dpu_crtc->crtc_lock);
+	spin_lock_init(&dpu_crtc->spin_lock);
+	atomic_set(&dpu_crtc->frame_pending, 0);
+
+	mutex_init(&dpu_crtc->rp_lock);
+	INIT_LIST_HEAD(&dpu_crtc->rp_head);
+
+	init_completion(&dpu_crtc->frame_done_comp);
+
+	INIT_LIST_HEAD(&dpu_crtc->frame_event_list);
+
+	for (i = 0; i < ARRAY_SIZE(dpu_crtc->frame_events); i++) {
+		INIT_LIST_HEAD(&dpu_crtc->frame_events[i].list);
+		list_add(&dpu_crtc->frame_events[i].list,
+				&dpu_crtc->frame_event_list);
+		kthread_init_work(&dpu_crtc->frame_events[i].work,
+				dpu_crtc_frame_event_work);
+	}
+
+	drm_crtc_init_with_planes(dev, crtc, plane, NULL, &dpu_crtc_funcs,
+				NULL);
+
+	drm_crtc_helper_add(crtc, &dpu_crtc_helper_funcs);
+	plane->crtc = crtc;
+
+	/* save user friendly CRTC name for later */
+	snprintf(dpu_crtc->name, DPU_CRTC_NAME_SIZE, "crtc%u", crtc->base.id);
+
+	/* initialize event handling */
+	rc = _dpu_crtc_init_events(dpu_crtc);
+	if (rc) {
+		drm_crtc_cleanup(crtc);
+		kfree(dpu_crtc);
+		return ERR_PTR(rc);
+	}
+
+	dpu_crtc->phandle = &kms->phandle;
+
+	DPU_DEBUG("%s: successfully initialized crtc\n", dpu_crtc->name);
+	return crtc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
new file mode 100644
index 000000000000..4a97ba16735f
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
@@ -0,0 +1,484 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DPU_CRTC_H_
+#define _DPU_CRTC_H_
+
+#include <linux/kthread.h>
+#include <drm/drm_crtc.h>
+#include "dpu_kms.h"
+#include "dpu_core_perf.h"
+#include "dpu_hw_blk.h"
+
+#define DPU_CRTC_NAME_SIZE	12
+
+/* define the maximum number of in-flight frame events */
+#define DPU_CRTC_FRAME_EVENT_SIZE	4
+
+/**
+ * enum dpu_crtc_client_type: crtc client type
+ * @RT_CLIENT:	RealTime client like video/cmd mode display
+ *              voting through apps rsc
+ * @NRT_CLIENT:	Non-RealTime client like WB display
+ *              voting through apps rsc
+ */
+enum dpu_crtc_client_type {
+	RT_CLIENT,
+	NRT_CLIENT,
+};
+
+/**
+ * enum dpu_crtc_smmu_state:	smmu state
+ * @ATTACHED:	 all the context banks are attached.
+ * @DETACHED:	 all the context banks are detached.
+ * @ATTACH_ALL_REQ:	 transient state of attaching context banks.
+ * @DETACH_ALL_REQ:	 transient state of detaching context banks.
+ */
+enum dpu_crtc_smmu_state {
+	ATTACHED = 0,
+	DETACHED,
+	ATTACH_ALL_REQ,
+	DETACH_ALL_REQ,
+};
+
+/**
+ * enum dpu_crtc_smmu_state_transition_type: state transition type
+ * @NONE: no pending state transitions
+ * @PRE_COMMIT: state transitions should be done before processing the commit
+ * @POST_COMMIT: state transitions to be done after processing the commit.
+ */
+enum dpu_crtc_smmu_state_transition_type {
+	NONE,
+	PRE_COMMIT,
+	POST_COMMIT
+};
+
+/**
+ * struct dpu_crtc_smmu_state_data: stores the smmu state and transition type
+ * @state: current state of smmu context banks
+ * @transition_type: transition request type
+ * @transition_error: whether there is error while transitioning the state
+ */
+struct dpu_crtc_smmu_state_data {
+	uint32_t state;
+	uint32_t transition_type;
+	uint32_t transition_error;
+};
+
+/**
+ * struct dpu_crtc_mixer: stores the map for each virtual pipeline in the CRTC
+ * @hw_lm:	LM HW Driver context
+ * @hw_ctl:	CTL Path HW driver context
+ * @encoder:	Encoder attached to this lm & ctl
+ * @mixer_op_mode:	mixer blending operation mode
+ * @flush_mask:	mixer flush mask for ctl, mixer and pipe
+ */
+struct dpu_crtc_mixer {
+	struct dpu_hw_mixer *hw_lm;
+	struct dpu_hw_ctl *hw_ctl;
+	struct drm_encoder *encoder;
+	u32 mixer_op_mode;
+	u32 flush_mask;
+};
+
+/**
+ * struct dpu_crtc_frame_event: stores crtc frame event for crtc processing
+ * @work:	base work structure
+ * @crtc:	Pointer to crtc handling this event
+ * @list:	event list
+ * @ts:		timestamp at queue entry
+ * @event:	event identifier
+ */
+struct dpu_crtc_frame_event {
+	struct kthread_work work;
+	struct drm_crtc *crtc;
+	struct list_head list;
+	ktime_t ts;
+	u32 event;
+};
+
+/**
+ * struct dpu_crtc_event - event callback tracking structure
+ * @list:     Linked list tracking node
+ * @kt_work:  Kthread worker structure
+ * @dpu_crtc: Pointer to associated dpu_crtc structure
+ * @cb_func:  Pointer to callback function
+ * @usr:      Pointer to user data to be provided to the callback
+ */
+struct dpu_crtc_event {
+	struct list_head list;
+	struct kthread_work kt_work;
+	void *dpu_crtc;
+
+	void (*cb_func)(struct drm_crtc *crtc, void *usr);
+	void *usr;
+};
+
+/*
+ * Maximum number of free event structures to cache
+ */
+#define DPU_CRTC_MAX_EVENT_COUNT	16
+
+/**
+ * struct dpu_crtc - virtualized CRTC data structure
+ * @base          : Base drm crtc structure
+ * @name          : ASCII description of this crtc
+ * @num_ctls      : Number of ctl paths in use
+ * @num_mixers    : Number of mixers in use
+ * @mixers_swapped: Whether the mixers have been swapped for left/right update
+ *                  especially in the case of DSC Merge.
+ * @mixers        : List of active mixers
+ * @event         : Pointer to last received drm vblank event. If there is a
+ *                  pending vblank event, this will be non-null.
+ * @vsync_count   : Running count of received vsync events
+ * @drm_requested_vblank : Whether vblanks have been enabled in the encoder
+ * @property_info : Opaque structure for generic property support
+ * @property_defaults : Array of default values for generic property support
+ * @stage_cfg     : H/w mixer stage configuration
+ * @debugfs_root  : Parent of debugfs node
+ * @vblank_cb_count : count of vblank callback since last reset
+ * @play_count    : frame count between crtc enable and disable
+ * @vblank_cb_time  : ktime at vblank count reset
+ * @vblank_requested : whether the user has requested vblank events
+ * @suspend         : whether or not a suspend operation is in progress
+ * @enabled       : whether the DPU CRTC is currently enabled. updated in the
+ *                  commit-thread, not state-swap time which is earlier, so
+ *                  safe to make decisions on during VBLANK on/off work
+ * @feature_list  : list of color processing features supported on a crtc
+ * @active_list   : list of color processing features are active
+ * @dirty_list    : list of color processing features are dirty
+ * @ad_dirty: list containing ad properties that are dirty
+ * @ad_active: list containing ad properties that are active
+ * @crtc_lock     : crtc lock around create, destroy and access.
+ * @frame_pending : Whether or not an update is pending
+ * @frame_events  : static allocation of in-flight frame events
+ * @frame_event_list : available frame event list
+ * @spin_lock     : spin lock for frame event, transaction status, etc...
+ * @frame_done_comp    : for frame_event_done synchronization
+ * @event_thread  : Pointer to event handler thread
+ * @event_worker  : Event worker queue
+ * @event_cache   : Local cache of event worker structures
+ * @event_free_list : List of available event structures
+ * @event_lock    : Spinlock around event handling code
+ * @misr_enable   : boolean entry indicates misr enable/disable status.
+ * @misr_frame_count  : misr frame count provided by client
+ * @misr_data     : store misr data before turning off the clocks.
+ * @phandle: Pointer to power handler
+ * @power_event   : registered power event handle
+ * @cur_perf      : current performance committed to clock/bandwidth driver
+ * @rp_lock       : serialization lock for resource pool
+ * @rp_head       : list of active resource pool
+ * @scl3_cfg_lut  : qseed3 lut config
+ */
+struct dpu_crtc {
+	struct drm_crtc base;
+	char name[DPU_CRTC_NAME_SIZE];
+
+	/* HW Resources reserved for the crtc */
+	u32 num_ctls;
+	u32 num_mixers;
+	bool mixers_swapped;
+	struct dpu_crtc_mixer mixers[CRTC_DUAL_MIXERS];
+	struct dpu_hw_scaler3_lut_cfg *scl3_lut_cfg;
+
+	struct drm_pending_vblank_event *event;
+	u32 vsync_count;
+
+	struct dpu_hw_stage_cfg stage_cfg;
+	struct dentry *debugfs_root;
+
+	u32 vblank_cb_count;
+	u64 play_count;
+	ktime_t vblank_cb_time;
+	bool vblank_requested;
+	bool suspend;
+	bool enabled;
+
+	struct list_head feature_list;
+	struct list_head active_list;
+	struct list_head dirty_list;
+	struct list_head ad_dirty;
+	struct list_head ad_active;
+
+	struct mutex crtc_lock;
+
+	atomic_t frame_pending;
+	struct dpu_crtc_frame_event frame_events[DPU_CRTC_FRAME_EVENT_SIZE];
+	struct list_head frame_event_list;
+	spinlock_t spin_lock;
+	struct completion frame_done_comp;
+
+	/* for handling internal event thread */
+	struct dpu_crtc_event event_cache[DPU_CRTC_MAX_EVENT_COUNT];
+	struct list_head event_free_list;
+	spinlock_t event_lock;
+	bool misr_enable;
+	u32 misr_frame_count;
+	u32 misr_data[CRTC_DUAL_MIXERS];
+
+	struct dpu_power_handle *phandle;
+	struct dpu_power_event *power_event;
+
+	struct dpu_core_perf_params cur_perf;
+
+	struct mutex rp_lock;
+	struct list_head rp_head;
+
+	struct dpu_crtc_smmu_state_data smmu_state;
+};
+
+#define to_dpu_crtc(x) container_of(x, struct dpu_crtc, base)
+
+/**
+ * struct dpu_crtc_res_ops - common operations for crtc resources
+ * @get: get given resource
+ * @put: put given resource
+ */
+struct dpu_crtc_res_ops {
+	void *(*get)(void *val, u32 type, u64 tag);
+	void (*put)(void *val);
+};
+
+#define DPU_CRTC_RES_FLAG_FREE		BIT(0)
+
+/**
+ * struct dpu_crtc_res - definition of crtc resources
+ * @list: list of crtc resource
+ * @type: crtc resource type
+ * @tag: unique identifier per type
+ * @refcount: reference/usage count
+ * @ops: callback operations
+ * @val: resource handle associated with type/tag
+ * @flags: customization flags
+ */
+struct dpu_crtc_res {
+	struct list_head list;
+	u32 type;
+	u64 tag;
+	atomic_t refcount;
+	struct dpu_crtc_res_ops ops;
+	void *val;
+	u32 flags;
+};
+
+/**
+ * dpu_crtc_respool - crtc resource pool
+ * @rp_lock: pointer to serialization lock
+ * @rp_head: pointer to head of active resource pools of this crtc
+ * @rp_list: list of crtc resource pool
+ * @sequence_id: sequence identifier, incremented per state duplication
+ * @res_list: list of resource managed by this resource pool
+ * @ops: resource operations for parent resource pool
+ */
+struct dpu_crtc_respool {
+	struct mutex *rp_lock;
+	struct list_head *rp_head;
+	struct list_head rp_list;
+	u32 sequence_id;
+	struct list_head res_list;
+	struct dpu_crtc_res_ops ops;
+};
+
+/**
+ * struct dpu_crtc_state - dpu container for atomic crtc state
+ * @base: Base drm crtc state structure
+ * @is_ppsplit    : Whether current topology requires PPSplit special handling
+ * @bw_control    : true if bw/clk controlled by core bw/clk properties
+ * @bw_split_vote : true if bw controlled by llcc/dram bw properties
+ * @lm_bounds     : LM boundaries based on current mode full resolution, no ROI.
+ *                  Origin top left of CRTC.
+ * @property_state: Local storage for msm_prop properties
+ * @property_values: Current crtc property values
+ * @input_fence_timeout_ns : Cached input fence timeout, in ns
+ * @new_perf: new performance state being requested
+ */
+struct dpu_crtc_state {
+	struct drm_crtc_state base;
+
+	bool bw_control;
+	bool bw_split_vote;
+
+	bool is_ppsplit;
+	struct drm_rect lm_bounds[CRTC_DUAL_MIXERS];
+
+	uint64_t input_fence_timeout_ns;
+
+	struct dpu_core_perf_params new_perf;
+	struct dpu_crtc_respool rp;
+};
+
+#define to_dpu_crtc_state(x) \
+	container_of(x, struct dpu_crtc_state, base)
+
+/**
+ * dpu_crtc_get_mixer_width - get the mixer width
+ * Mixer width will be same as panel width(/2 for split)
+ */
+static inline int dpu_crtc_get_mixer_width(struct dpu_crtc *dpu_crtc,
+	struct dpu_crtc_state *cstate, struct drm_display_mode *mode)
+{
+	u32 mixer_width;
+
+	if (!dpu_crtc || !cstate || !mode)
+		return 0;
+
+	mixer_width = (dpu_crtc->num_mixers == CRTC_DUAL_MIXERS ?
+			mode->hdisplay / CRTC_DUAL_MIXERS : mode->hdisplay);
+
+	return mixer_width;
+}
+
+/**
+ * dpu_crtc_get_mixer_height - get the mixer height
+ * Mixer height will be same as panel height
+ */
+static inline int dpu_crtc_get_mixer_height(struct dpu_crtc *dpu_crtc,
+		struct dpu_crtc_state *cstate, struct drm_display_mode *mode)
+{
+	if (!dpu_crtc || !cstate || !mode)
+		return 0;
+
+	return mode->vdisplay;
+}
+
+/**
+ * dpu_crtc_frame_pending - retun the number of pending frames
+ * @crtc: Pointer to drm crtc object
+ */
+static inline int dpu_crtc_frame_pending(struct drm_crtc *crtc)
+{
+	struct dpu_crtc *dpu_crtc;
+
+	if (!crtc)
+		return -EINVAL;
+
+	dpu_crtc = to_dpu_crtc(crtc);
+	return atomic_read(&dpu_crtc->frame_pending);
+}
+
+/**
+ * dpu_crtc_vblank - enable or disable vblanks for this crtc
+ * @crtc: Pointer to drm crtc object
+ * @en: true to enable vblanks, false to disable
+ */
+int dpu_crtc_vblank(struct drm_crtc *crtc, bool en);
+
+/**
+ * dpu_crtc_commit_kickoff - trigger kickoff of the commit for this crtc
+ * @crtc: Pointer to drm crtc object
+ */
+void dpu_crtc_commit_kickoff(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_complete_commit - callback signalling completion of current commit
+ * @crtc: Pointer to drm crtc object
+ * @old_state: Pointer to drm crtc old state object
+ */
+void dpu_crtc_complete_commit(struct drm_crtc *crtc,
+		struct drm_crtc_state *old_state);
+
+/**
+ * dpu_crtc_init - create a new crtc object
+ * @dev: dpu device
+ * @plane: base plane
+ * @Return: new crtc object or error
+ */
+struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane);
+
+/**
+ * dpu_crtc_register_custom_event - api for enabling/disabling crtc event
+ * @kms: Pointer to dpu_kms
+ * @crtc_drm: Pointer to crtc object
+ * @event: Event that client is interested
+ * @en: Flag to enable/disable the event
+ */
+int dpu_crtc_register_custom_event(struct dpu_kms *kms,
+		struct drm_crtc *crtc_drm, u32 event, bool en);
+
+/**
+ * dpu_crtc_get_intf_mode - get interface mode of the given crtc
+ * @crtc: Pointert to crtc
+ */
+enum dpu_intf_mode dpu_crtc_get_intf_mode(struct drm_crtc *crtc);
+
+/**
+ * dpu_crtc_get_client_type - check the crtc type- rt, nrt etc.
+ * @crtc: Pointer to crtc
+ */
+static inline enum dpu_crtc_client_type dpu_crtc_get_client_type(
+						struct drm_crtc *crtc)
+{
+	struct dpu_crtc_state *cstate =
+			crtc ? to_dpu_crtc_state(crtc->state) : NULL;
+
+	if (!cstate)
+		return NRT_CLIENT;
+
+	return RT_CLIENT;
+}
+
+/**
+ * dpu_crtc_is_enabled - check if dpu crtc is enabled or not
+ * @crtc: Pointer to crtc
+ */
+static inline bool dpu_crtc_is_enabled(struct drm_crtc *crtc)
+{
+	return crtc ? crtc->enabled : false;
+}
+
+/**
+ * dpu_crtc_event_queue - request event callback
+ * @crtc: Pointer to drm crtc structure
+ * @func: Pointer to callback function
+ * @usr: Pointer to user data to be passed to callback
+ * Returns: Zero on success
+ */
+int dpu_crtc_event_queue(struct drm_crtc *crtc,
+		void (*func)(struct drm_crtc *crtc, void *usr), void *usr);
+
+/**
+ * dpu_crtc_res_add - add given resource to resource pool in crtc state
+ * @state: Pointer to drm crtc state
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * @val: Resource handle
+ * @ops: Resource callback operations
+ * return: 0 if success; error code otherwise
+ */
+int dpu_crtc_res_add(struct drm_crtc_state *state, u32 type, u64 tag,
+		void *val, struct dpu_crtc_res_ops *ops);
+
+/**
+ * dpu_crtc_res_get - get given resource from resource pool in crtc state
+ * @state: Pointer to drm crtc state
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * return: Resource handle if success; pointer error or null otherwise
+ */
+void *dpu_crtc_res_get(struct drm_crtc_state *state, u32 type, u64 tag);
+
+/**
+ * dpu_crtc_res_put - return given resource to resource pool in crtc state
+ * @state: Pointer to drm crtc state
+ * @type: Resource type
+ * @tag: Search tag for given resource
+ * return: None
+ */
+void dpu_crtc_res_put(struct drm_crtc_state *state, u32 type, u64 tag);
+
+#endif /* _DPU_CRTC_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
new file mode 100644
index 000000000000..ae2aee7ed9e1
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.c
@@ -0,0 +1,2393 @@
+/* Copyright (c) 2009-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/ktime.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/dma-buf.h>
+#include <linux/slab.h>
+#include <linux/list_sort.h>
+#include <linux/pm_runtime.h>
+
+#include "dpu_dbg.h"
+#include "disp/dpu1/dpu_hw_catalog.h"
+
+
+#define DEFAULT_DBGBUS_DPU	DPU_DBG_DUMP_IN_MEM
+#define DEFAULT_DBGBUS_VBIFRT	DPU_DBG_DUMP_IN_MEM
+#define REG_BASE_NAME_LEN	80
+
+#define DBGBUS_FLAGS_DSPP	BIT(0)
+#define DBGBUS_DSPP_STATUS	0x34C
+
+#define DBGBUS_NAME_DPU		"dpu"
+#define DBGBUS_NAME_VBIF_RT	"vbif_rt"
+
+/* offsets from dpu top address for the debug buses */
+#define DBGBUS_SSPP0	0x188
+#define DBGBUS_AXI_INTF	0x194
+#define DBGBUS_SSPP1	0x298
+#define DBGBUS_DSPP	0x348
+#define DBGBUS_PERIPH	0x418
+
+#define TEST_MASK(id, tp)	((id << 4) | (tp << 1) | BIT(0))
+
+/* following offsets are with respect to MDP VBIF base for DBG BUS access */
+#define MMSS_VBIF_CLKON			0x4
+#define MMSS_VBIF_TEST_BUS_OUT_CTRL	0x210
+#define MMSS_VBIF_TEST_BUS_OUT		0x230
+
+/* Vbif error info */
+#define MMSS_VBIF_PND_ERR		0x190
+#define MMSS_VBIF_SRC_ERR		0x194
+#define MMSS_VBIF_XIN_HALT_CTRL1	0x204
+#define MMSS_VBIF_ERR_INFO		0X1a0
+#define MMSS_VBIF_ERR_INFO_1		0x1a4
+#define MMSS_VBIF_CLIENT_NUM		14
+
+/**
+ * struct dpu_dbg_reg_base - register region base.
+ *	may sub-ranges: sub-ranges are used for dumping
+ *	or may not have sub-ranges: dumping is base -> max_offset
+ * @reg_base_head: head of this node
+ * @name: register base name
+ * @base: base pointer
+ * @off: cached offset of region for manual register dumping
+ * @cnt: cached range of region for manual register dumping
+ * @max_offset: length of region
+ * @buf: buffer used for manual register dumping
+ * @buf_len:  buffer length used for manual register dumping
+ * @cb: callback for external dump function, null if not defined
+ * @cb_ptr: private pointer to callback function
+ */
+struct dpu_dbg_reg_base {
+	struct list_head reg_base_head;
+	char name[REG_BASE_NAME_LEN];
+	void __iomem *base;
+	size_t off;
+	size_t cnt;
+	size_t max_offset;
+	char *buf;
+	size_t buf_len;
+	void (*cb)(void *ptr);
+	void *cb_ptr;
+};
+
+struct dpu_debug_bus_entry {
+	u32 wr_addr;
+	u32 block_id;
+	u32 test_id;
+	void (*analyzer)(void __iomem *mem_base,
+				struct dpu_debug_bus_entry *entry, u32 val);
+};
+
+struct vbif_debug_bus_entry {
+	u32 disable_bus_addr;
+	u32 block_bus_addr;
+	u32 bit_offset;
+	u32 block_cnt;
+	u32 test_pnt_start;
+	u32 test_pnt_cnt;
+};
+
+struct dpu_dbg_debug_bus_common {
+	char *name;
+	u32 enable_mask;
+	bool include_in_deferred_work;
+	u32 flags;
+	u32 entries_size;
+	u32 *dumped_content;
+};
+
+struct dpu_dbg_dpu_debug_bus {
+	struct dpu_dbg_debug_bus_common cmn;
+	struct dpu_debug_bus_entry *entries;
+	u32 top_blk_off;
+};
+
+struct dpu_dbg_vbif_debug_bus {
+	struct dpu_dbg_debug_bus_common cmn;
+	struct vbif_debug_bus_entry *entries;
+};
+
+/**
+ * struct dpu_dbg_base - global dpu debug base structure
+ * @reg_base_list: list of register dumping regions
+ * @dev: device pointer
+ * @dump_work: work struct for deferring register dump work to separate thread
+ * @dbgbus_dpu: debug bus structure for the dpu
+ * @dbgbus_vbif_rt: debug bus structure for the realtime vbif
+ */
+static struct dpu_dbg_base {
+	struct list_head reg_base_list;
+	struct device *dev;
+
+	struct work_struct dump_work;
+
+	struct dpu_dbg_dpu_debug_bus dbgbus_dpu;
+	struct dpu_dbg_vbif_debug_bus dbgbus_vbif_rt;
+} dpu_dbg_base;
+
+static void _dpu_debug_bus_xbar_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	dev_err(dpu_dbg_base.dev, "xbar 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_lm_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & 0xFFF000))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "lm 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_ppb0_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & BIT(15)))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "ppb0 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static void _dpu_debug_bus_ppb1_dump(void __iomem *mem_base,
+		struct dpu_debug_bus_entry *entry, u32 val)
+{
+	if (!(val & BIT(15)))
+		return;
+
+	dev_err(dpu_dbg_base.dev, "ppb1 0x%x %d %d 0x%x\n",
+			entry->wr_addr, entry->block_id, entry->test_id, val);
+}
+
+static struct dpu_debug_bus_entry dbg_bus_dpu_8998[] = {
+
+	/* Unpack 0 sspp 0*/
+	{ DBGBUS_SSPP0, 50, 2 },
+	{ DBGBUS_SSPP0, 60, 2 },
+	{ DBGBUS_SSPP0, 70, 2 },
+	{ DBGBUS_SSPP0, 85, 2 },
+
+	/* Upack 0 sspp 1*/
+	{ DBGBUS_SSPP1, 50, 2 },
+	{ DBGBUS_SSPP1, 60, 2 },
+	{ DBGBUS_SSPP1, 70, 2 },
+	{ DBGBUS_SSPP1, 85, 2 },
+
+	/* scheduler */
+	{ DBGBUS_DSPP, 130, 0 },
+	{ DBGBUS_DSPP, 130, 1 },
+	{ DBGBUS_DSPP, 130, 2 },
+	{ DBGBUS_DSPP, 130, 3 },
+	{ DBGBUS_DSPP, 130, 4 },
+	{ DBGBUS_DSPP, 130, 5 },
+
+	/* qseed */
+	{ DBGBUS_SSPP0, 6, 0},
+	{ DBGBUS_SSPP0, 6, 1},
+	{ DBGBUS_SSPP0, 26, 0},
+	{ DBGBUS_SSPP0, 26, 1},
+	{ DBGBUS_SSPP1, 6, 0},
+	{ DBGBUS_SSPP1, 6, 1},
+	{ DBGBUS_SSPP1, 26, 0},
+	{ DBGBUS_SSPP1, 26, 1},
+
+	/* scale */
+	{ DBGBUS_SSPP0, 16, 0},
+	{ DBGBUS_SSPP0, 16, 1},
+	{ DBGBUS_SSPP0, 36, 0},
+	{ DBGBUS_SSPP0, 36, 1},
+	{ DBGBUS_SSPP1, 16, 0},
+	{ DBGBUS_SSPP1, 16, 1},
+	{ DBGBUS_SSPP1, 36, 0},
+	{ DBGBUS_SSPP1, 36, 1},
+
+	/* fetch sspp0 */
+
+	/* vig 0 */
+	{ DBGBUS_SSPP0, 0, 0 },
+	{ DBGBUS_SSPP0, 0, 1 },
+	{ DBGBUS_SSPP0, 0, 2 },
+	{ DBGBUS_SSPP0, 0, 3 },
+	{ DBGBUS_SSPP0, 0, 4 },
+	{ DBGBUS_SSPP0, 0, 5 },
+	{ DBGBUS_SSPP0, 0, 6 },
+	{ DBGBUS_SSPP0, 0, 7 },
+
+	{ DBGBUS_SSPP0, 1, 0 },
+	{ DBGBUS_SSPP0, 1, 1 },
+	{ DBGBUS_SSPP0, 1, 2 },
+	{ DBGBUS_SSPP0, 1, 3 },
+	{ DBGBUS_SSPP0, 1, 4 },
+	{ DBGBUS_SSPP0, 1, 5 },
+	{ DBGBUS_SSPP0, 1, 6 },
+	{ DBGBUS_SSPP0, 1, 7 },
+
+	{ DBGBUS_SSPP0, 2, 0 },
+	{ DBGBUS_SSPP0, 2, 1 },
+	{ DBGBUS_SSPP0, 2, 2 },
+	{ DBGBUS_SSPP0, 2, 3 },
+	{ DBGBUS_SSPP0, 2, 4 },
+	{ DBGBUS_SSPP0, 2, 5 },
+	{ DBGBUS_SSPP0, 2, 6 },
+	{ DBGBUS_SSPP0, 2, 7 },
+
+	{ DBGBUS_SSPP0, 4, 0 },
+	{ DBGBUS_SSPP0, 4, 1 },
+	{ DBGBUS_SSPP0, 4, 2 },
+	{ DBGBUS_SSPP0, 4, 3 },
+	{ DBGBUS_SSPP0, 4, 4 },
+	{ DBGBUS_SSPP0, 4, 5 },
+	{ DBGBUS_SSPP0, 4, 6 },
+	{ DBGBUS_SSPP0, 4, 7 },
+
+	{ DBGBUS_SSPP0, 5, 0 },
+	{ DBGBUS_SSPP0, 5, 1 },
+	{ DBGBUS_SSPP0, 5, 2 },
+	{ DBGBUS_SSPP0, 5, 3 },
+	{ DBGBUS_SSPP0, 5, 4 },
+	{ DBGBUS_SSPP0, 5, 5 },
+	{ DBGBUS_SSPP0, 5, 6 },
+	{ DBGBUS_SSPP0, 5, 7 },
+
+	/* vig 2 */
+	{ DBGBUS_SSPP0, 20, 0 },
+	{ DBGBUS_SSPP0, 20, 1 },
+	{ DBGBUS_SSPP0, 20, 2 },
+	{ DBGBUS_SSPP0, 20, 3 },
+	{ DBGBUS_SSPP0, 20, 4 },
+	{ DBGBUS_SSPP0, 20, 5 },
+	{ DBGBUS_SSPP0, 20, 6 },
+	{ DBGBUS_SSPP0, 20, 7 },
+
+	{ DBGBUS_SSPP0, 21, 0 },
+	{ DBGBUS_SSPP0, 21, 1 },
+	{ DBGBUS_SSPP0, 21, 2 },
+	{ DBGBUS_SSPP0, 21, 3 },
+	{ DBGBUS_SSPP0, 21, 4 },
+	{ DBGBUS_SSPP0, 21, 5 },
+	{ DBGBUS_SSPP0, 21, 6 },
+	{ DBGBUS_SSPP0, 21, 7 },
+
+	{ DBGBUS_SSPP0, 22, 0 },
+	{ DBGBUS_SSPP0, 22, 1 },
+	{ DBGBUS_SSPP0, 22, 2 },
+	{ DBGBUS_SSPP0, 22, 3 },
+	{ DBGBUS_SSPP0, 22, 4 },
+	{ DBGBUS_SSPP0, 22, 5 },
+	{ DBGBUS_SSPP0, 22, 6 },
+	{ DBGBUS_SSPP0, 22, 7 },
+
+	{ DBGBUS_SSPP0, 24, 0 },
+	{ DBGBUS_SSPP0, 24, 1 },
+	{ DBGBUS_SSPP0, 24, 2 },
+	{ DBGBUS_SSPP0, 24, 3 },
+	{ DBGBUS_SSPP0, 24, 4 },
+	{ DBGBUS_SSPP0, 24, 5 },
+	{ DBGBUS_SSPP0, 24, 6 },
+	{ DBGBUS_SSPP0, 24, 7 },
+
+	{ DBGBUS_SSPP0, 25, 0 },
+	{ DBGBUS_SSPP0, 25, 1 },
+	{ DBGBUS_SSPP0, 25, 2 },
+	{ DBGBUS_SSPP0, 25, 3 },
+	{ DBGBUS_SSPP0, 25, 4 },
+	{ DBGBUS_SSPP0, 25, 5 },
+	{ DBGBUS_SSPP0, 25, 6 },
+	{ DBGBUS_SSPP0, 25, 7 },
+
+	/* dma 2 */
+	{ DBGBUS_SSPP0, 30, 0 },
+	{ DBGBUS_SSPP0, 30, 1 },
+	{ DBGBUS_SSPP0, 30, 2 },
+	{ DBGBUS_SSPP0, 30, 3 },
+	{ DBGBUS_SSPP0, 30, 4 },
+	{ DBGBUS_SSPP0, 30, 5 },
+	{ DBGBUS_SSPP0, 30, 6 },
+	{ DBGBUS_SSPP0, 30, 7 },
+
+	{ DBGBUS_SSPP0, 31, 0 },
+	{ DBGBUS_SSPP0, 31, 1 },
+	{ DBGBUS_SSPP0, 31, 2 },
+	{ DBGBUS_SSPP0, 31, 3 },
+	{ DBGBUS_SSPP0, 31, 4 },
+	{ DBGBUS_SSPP0, 31, 5 },
+	{ DBGBUS_SSPP0, 31, 6 },
+	{ DBGBUS_SSPP0, 31, 7 },
+
+	{ DBGBUS_SSPP0, 32, 0 },
+	{ DBGBUS_SSPP0, 32, 1 },
+	{ DBGBUS_SSPP0, 32, 2 },
+	{ DBGBUS_SSPP0, 32, 3 },
+	{ DBGBUS_SSPP0, 32, 4 },
+	{ DBGBUS_SSPP0, 32, 5 },
+	{ DBGBUS_SSPP0, 32, 6 },
+	{ DBGBUS_SSPP0, 32, 7 },
+
+	{ DBGBUS_SSPP0, 33, 0 },
+	{ DBGBUS_SSPP0, 33, 1 },
+	{ DBGBUS_SSPP0, 33, 2 },
+	{ DBGBUS_SSPP0, 33, 3 },
+	{ DBGBUS_SSPP0, 33, 4 },
+	{ DBGBUS_SSPP0, 33, 5 },
+	{ DBGBUS_SSPP0, 33, 6 },
+	{ DBGBUS_SSPP0, 33, 7 },
+
+	{ DBGBUS_SSPP0, 34, 0 },
+	{ DBGBUS_SSPP0, 34, 1 },
+	{ DBGBUS_SSPP0, 34, 2 },
+	{ DBGBUS_SSPP0, 34, 3 },
+	{ DBGBUS_SSPP0, 34, 4 },
+	{ DBGBUS_SSPP0, 34, 5 },
+	{ DBGBUS_SSPP0, 34, 6 },
+	{ DBGBUS_SSPP0, 34, 7 },
+
+	{ DBGBUS_SSPP0, 35, 0 },
+	{ DBGBUS_SSPP0, 35, 1 },
+	{ DBGBUS_SSPP0, 35, 2 },
+	{ DBGBUS_SSPP0, 35, 3 },
+
+	/* dma 0 */
+	{ DBGBUS_SSPP0, 40, 0 },
+	{ DBGBUS_SSPP0, 40, 1 },
+	{ DBGBUS_SSPP0, 40, 2 },
+	{ DBGBUS_SSPP0, 40, 3 },
+	{ DBGBUS_SSPP0, 40, 4 },
+	{ DBGBUS_SSPP0, 40, 5 },
+	{ DBGBUS_SSPP0, 40, 6 },
+	{ DBGBUS_SSPP0, 40, 7 },
+
+	{ DBGBUS_SSPP0, 41, 0 },
+	{ DBGBUS_SSPP0, 41, 1 },
+	{ DBGBUS_SSPP0, 41, 2 },
+	{ DBGBUS_SSPP0, 41, 3 },
+	{ DBGBUS_SSPP0, 41, 4 },
+	{ DBGBUS_SSPP0, 41, 5 },
+	{ DBGBUS_SSPP0, 41, 6 },
+	{ DBGBUS_SSPP0, 41, 7 },
+
+	{ DBGBUS_SSPP0, 42, 0 },
+	{ DBGBUS_SSPP0, 42, 1 },
+	{ DBGBUS_SSPP0, 42, 2 },
+	{ DBGBUS_SSPP0, 42, 3 },
+	{ DBGBUS_SSPP0, 42, 4 },
+	{ DBGBUS_SSPP0, 42, 5 },
+	{ DBGBUS_SSPP0, 42, 6 },
+	{ DBGBUS_SSPP0, 42, 7 },
+
+	{ DBGBUS_SSPP0, 44, 0 },
+	{ DBGBUS_SSPP0, 44, 1 },
+	{ DBGBUS_SSPP0, 44, 2 },
+	{ DBGBUS_SSPP0, 44, 3 },
+	{ DBGBUS_SSPP0, 44, 4 },
+	{ DBGBUS_SSPP0, 44, 5 },
+	{ DBGBUS_SSPP0, 44, 6 },
+	{ DBGBUS_SSPP0, 44, 7 },
+
+	{ DBGBUS_SSPP0, 45, 0 },
+	{ DBGBUS_SSPP0, 45, 1 },
+	{ DBGBUS_SSPP0, 45, 2 },
+	{ DBGBUS_SSPP0, 45, 3 },
+	{ DBGBUS_SSPP0, 45, 4 },
+	{ DBGBUS_SSPP0, 45, 5 },
+	{ DBGBUS_SSPP0, 45, 6 },
+	{ DBGBUS_SSPP0, 45, 7 },
+
+	/* fetch sspp1 */
+	/* vig 1 */
+	{ DBGBUS_SSPP1, 0, 0 },
+	{ DBGBUS_SSPP1, 0, 1 },
+	{ DBGBUS_SSPP1, 0, 2 },
+	{ DBGBUS_SSPP1, 0, 3 },
+	{ DBGBUS_SSPP1, 0, 4 },
+	{ DBGBUS_SSPP1, 0, 5 },
+	{ DBGBUS_SSPP1, 0, 6 },
+	{ DBGBUS_SSPP1, 0, 7 },
+
+	{ DBGBUS_SSPP1, 1, 0 },
+	{ DBGBUS_SSPP1, 1, 1 },
+	{ DBGBUS_SSPP1, 1, 2 },
+	{ DBGBUS_SSPP1, 1, 3 },
+	{ DBGBUS_SSPP1, 1, 4 },
+	{ DBGBUS_SSPP1, 1, 5 },
+	{ DBGBUS_SSPP1, 1, 6 },
+	{ DBGBUS_SSPP1, 1, 7 },
+
+	{ DBGBUS_SSPP1, 2, 0 },
+	{ DBGBUS_SSPP1, 2, 1 },
+	{ DBGBUS_SSPP1, 2, 2 },
+	{ DBGBUS_SSPP1, 2, 3 },
+	{ DBGBUS_SSPP1, 2, 4 },
+	{ DBGBUS_SSPP1, 2, 5 },
+	{ DBGBUS_SSPP1, 2, 6 },
+	{ DBGBUS_SSPP1, 2, 7 },
+
+	{ DBGBUS_SSPP1, 4, 0 },
+	{ DBGBUS_SSPP1, 4, 1 },
+	{ DBGBUS_SSPP1, 4, 2 },
+	{ DBGBUS_SSPP1, 4, 3 },
+	{ DBGBUS_SSPP1, 4, 4 },
+	{ DBGBUS_SSPP1, 4, 5 },
+	{ DBGBUS_SSPP1, 4, 6 },
+	{ DBGBUS_SSPP1, 4, 7 },
+
+	{ DBGBUS_SSPP1, 5, 0 },
+	{ DBGBUS_SSPP1, 5, 1 },
+	{ DBGBUS_SSPP1, 5, 2 },
+	{ DBGBUS_SSPP1, 5, 3 },
+	{ DBGBUS_SSPP1, 5, 4 },
+	{ DBGBUS_SSPP1, 5, 5 },
+	{ DBGBUS_SSPP1, 5, 6 },
+	{ DBGBUS_SSPP1, 5, 7 },
+
+	/* vig 3 */
+	{ DBGBUS_SSPP1, 20, 0 },
+	{ DBGBUS_SSPP1, 20, 1 },
+	{ DBGBUS_SSPP1, 20, 2 },
+	{ DBGBUS_SSPP1, 20, 3 },
+	{ DBGBUS_SSPP1, 20, 4 },
+	{ DBGBUS_SSPP1, 20, 5 },
+	{ DBGBUS_SSPP1, 20, 6 },
+	{ DBGBUS_SSPP1, 20, 7 },
+
+	{ DBGBUS_SSPP1, 21, 0 },
+	{ DBGBUS_SSPP1, 21, 1 },
+	{ DBGBUS_SSPP1, 21, 2 },
+	{ DBGBUS_SSPP1, 21, 3 },
+	{ DBGBUS_SSPP1, 21, 4 },
+	{ DBGBUS_SSPP1, 21, 5 },
+	{ DBGBUS_SSPP1, 21, 6 },
+	{ DBGBUS_SSPP1, 21, 7 },
+
+	{ DBGBUS_SSPP1, 22, 0 },
+	{ DBGBUS_SSPP1, 22, 1 },
+	{ DBGBUS_SSPP1, 22, 2 },
+	{ DBGBUS_SSPP1, 22, 3 },
+	{ DBGBUS_SSPP1, 22, 4 },
+	{ DBGBUS_SSPP1, 22, 5 },
+	{ DBGBUS_SSPP1, 22, 6 },
+	{ DBGBUS_SSPP1, 22, 7 },
+
+	{ DBGBUS_SSPP1, 24, 0 },
+	{ DBGBUS_SSPP1, 24, 1 },
+	{ DBGBUS_SSPP1, 24, 2 },
+	{ DBGBUS_SSPP1, 24, 3 },
+	{ DBGBUS_SSPP1, 24, 4 },
+	{ DBGBUS_SSPP1, 24, 5 },
+	{ DBGBUS_SSPP1, 24, 6 },
+	{ DBGBUS_SSPP1, 24, 7 },
+
+	{ DBGBUS_SSPP1, 25, 0 },
+	{ DBGBUS_SSPP1, 25, 1 },
+	{ DBGBUS_SSPP1, 25, 2 },
+	{ DBGBUS_SSPP1, 25, 3 },
+	{ DBGBUS_SSPP1, 25, 4 },
+	{ DBGBUS_SSPP1, 25, 5 },
+	{ DBGBUS_SSPP1, 25, 6 },
+	{ DBGBUS_SSPP1, 25, 7 },
+
+	/* dma 3 */
+	{ DBGBUS_SSPP1, 30, 0 },
+	{ DBGBUS_SSPP1, 30, 1 },
+	{ DBGBUS_SSPP1, 30, 2 },
+	{ DBGBUS_SSPP1, 30, 3 },
+	{ DBGBUS_SSPP1, 30, 4 },
+	{ DBGBUS_SSPP1, 30, 5 },
+	{ DBGBUS_SSPP1, 30, 6 },
+	{ DBGBUS_SSPP1, 30, 7 },
+
+	{ DBGBUS_SSPP1, 31, 0 },
+	{ DBGBUS_SSPP1, 31, 1 },
+	{ DBGBUS_SSPP1, 31, 2 },
+	{ DBGBUS_SSPP1, 31, 3 },
+	{ DBGBUS_SSPP1, 31, 4 },
+	{ DBGBUS_SSPP1, 31, 5 },
+	{ DBGBUS_SSPP1, 31, 6 },
+	{ DBGBUS_SSPP1, 31, 7 },
+
+	{ DBGBUS_SSPP1, 32, 0 },
+	{ DBGBUS_SSPP1, 32, 1 },
+	{ DBGBUS_SSPP1, 32, 2 },
+	{ DBGBUS_SSPP1, 32, 3 },
+	{ DBGBUS_SSPP1, 32, 4 },
+	{ DBGBUS_SSPP1, 32, 5 },
+	{ DBGBUS_SSPP1, 32, 6 },
+	{ DBGBUS_SSPP1, 32, 7 },
+
+	{ DBGBUS_SSPP1, 33, 0 },
+	{ DBGBUS_SSPP1, 33, 1 },
+	{ DBGBUS_SSPP1, 33, 2 },
+	{ DBGBUS_SSPP1, 33, 3 },
+	{ DBGBUS_SSPP1, 33, 4 },
+	{ DBGBUS_SSPP1, 33, 5 },
+	{ DBGBUS_SSPP1, 33, 6 },
+	{ DBGBUS_SSPP1, 33, 7 },
+
+	{ DBGBUS_SSPP1, 34, 0 },
+	{ DBGBUS_SSPP1, 34, 1 },
+	{ DBGBUS_SSPP1, 34, 2 },
+	{ DBGBUS_SSPP1, 34, 3 },
+	{ DBGBUS_SSPP1, 34, 4 },
+	{ DBGBUS_SSPP1, 34, 5 },
+	{ DBGBUS_SSPP1, 34, 6 },
+	{ DBGBUS_SSPP1, 34, 7 },
+
+	{ DBGBUS_SSPP1, 35, 0 },
+	{ DBGBUS_SSPP1, 35, 1 },
+	{ DBGBUS_SSPP1, 35, 2 },
+
+	/* dma 1 */
+	{ DBGBUS_SSPP1, 40, 0 },
+	{ DBGBUS_SSPP1, 40, 1 },
+	{ DBGBUS_SSPP1, 40, 2 },
+	{ DBGBUS_SSPP1, 40, 3 },
+	{ DBGBUS_SSPP1, 40, 4 },
+	{ DBGBUS_SSPP1, 40, 5 },
+	{ DBGBUS_SSPP1, 40, 6 },
+	{ DBGBUS_SSPP1, 40, 7 },
+
+	{ DBGBUS_SSPP1, 41, 0 },
+	{ DBGBUS_SSPP1, 41, 1 },
+	{ DBGBUS_SSPP1, 41, 2 },
+	{ DBGBUS_SSPP1, 41, 3 },
+	{ DBGBUS_SSPP1, 41, 4 },
+	{ DBGBUS_SSPP1, 41, 5 },
+	{ DBGBUS_SSPP1, 41, 6 },
+	{ DBGBUS_SSPP1, 41, 7 },
+
+	{ DBGBUS_SSPP1, 42, 0 },
+	{ DBGBUS_SSPP1, 42, 1 },
+	{ DBGBUS_SSPP1, 42, 2 },
+	{ DBGBUS_SSPP1, 42, 3 },
+	{ DBGBUS_SSPP1, 42, 4 },
+	{ DBGBUS_SSPP1, 42, 5 },
+	{ DBGBUS_SSPP1, 42, 6 },
+	{ DBGBUS_SSPP1, 42, 7 },
+
+	{ DBGBUS_SSPP1, 44, 0 },
+	{ DBGBUS_SSPP1, 44, 1 },
+	{ DBGBUS_SSPP1, 44, 2 },
+	{ DBGBUS_SSPP1, 44, 3 },
+	{ DBGBUS_SSPP1, 44, 4 },
+	{ DBGBUS_SSPP1, 44, 5 },
+	{ DBGBUS_SSPP1, 44, 6 },
+	{ DBGBUS_SSPP1, 44, 7 },
+
+	{ DBGBUS_SSPP1, 45, 0 },
+	{ DBGBUS_SSPP1, 45, 1 },
+	{ DBGBUS_SSPP1, 45, 2 },
+	{ DBGBUS_SSPP1, 45, 3 },
+	{ DBGBUS_SSPP1, 45, 4 },
+	{ DBGBUS_SSPP1, 45, 5 },
+	{ DBGBUS_SSPP1, 45, 6 },
+	{ DBGBUS_SSPP1, 45, 7 },
+
+	/* cursor 1 */
+	{ DBGBUS_SSPP1, 80, 0 },
+	{ DBGBUS_SSPP1, 80, 1 },
+	{ DBGBUS_SSPP1, 80, 2 },
+	{ DBGBUS_SSPP1, 80, 3 },
+	{ DBGBUS_SSPP1, 80, 4 },
+	{ DBGBUS_SSPP1, 80, 5 },
+	{ DBGBUS_SSPP1, 80, 6 },
+	{ DBGBUS_SSPP1, 80, 7 },
+
+	{ DBGBUS_SSPP1, 81, 0 },
+	{ DBGBUS_SSPP1, 81, 1 },
+	{ DBGBUS_SSPP1, 81, 2 },
+	{ DBGBUS_SSPP1, 81, 3 },
+	{ DBGBUS_SSPP1, 81, 4 },
+	{ DBGBUS_SSPP1, 81, 5 },
+	{ DBGBUS_SSPP1, 81, 6 },
+	{ DBGBUS_SSPP1, 81, 7 },
+
+	{ DBGBUS_SSPP1, 82, 0 },
+	{ DBGBUS_SSPP1, 82, 1 },
+	{ DBGBUS_SSPP1, 82, 2 },
+	{ DBGBUS_SSPP1, 82, 3 },
+	{ DBGBUS_SSPP1, 82, 4 },
+	{ DBGBUS_SSPP1, 82, 5 },
+	{ DBGBUS_SSPP1, 82, 6 },
+	{ DBGBUS_SSPP1, 82, 7 },
+
+	{ DBGBUS_SSPP1, 83, 0 },
+	{ DBGBUS_SSPP1, 83, 1 },
+	{ DBGBUS_SSPP1, 83, 2 },
+	{ DBGBUS_SSPP1, 83, 3 },
+	{ DBGBUS_SSPP1, 83, 4 },
+	{ DBGBUS_SSPP1, 83, 5 },
+	{ DBGBUS_SSPP1, 83, 6 },
+	{ DBGBUS_SSPP1, 83, 7 },
+
+	{ DBGBUS_SSPP1, 84, 0 },
+	{ DBGBUS_SSPP1, 84, 1 },
+	{ DBGBUS_SSPP1, 84, 2 },
+	{ DBGBUS_SSPP1, 84, 3 },
+	{ DBGBUS_SSPP1, 84, 4 },
+	{ DBGBUS_SSPP1, 84, 5 },
+	{ DBGBUS_SSPP1, 84, 6 },
+	{ DBGBUS_SSPP1, 84, 7 },
+
+	/* dspp */
+	{ DBGBUS_DSPP, 13, 0 },
+	{ DBGBUS_DSPP, 19, 0 },
+	{ DBGBUS_DSPP, 14, 0 },
+	{ DBGBUS_DSPP, 14, 1 },
+	{ DBGBUS_DSPP, 14, 3 },
+	{ DBGBUS_DSPP, 20, 0 },
+	{ DBGBUS_DSPP, 20, 1 },
+	{ DBGBUS_DSPP, 20, 3 },
+
+	/* ppb_0 */
+	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
+
+	/* ppb_1 */
+	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
+
+	/* lm_lut */
+	{ DBGBUS_DSPP, 109, 0 },
+	{ DBGBUS_DSPP, 105, 0 },
+	{ DBGBUS_DSPP, 103, 0 },
+
+	/* tear-check */
+	{ DBGBUS_PERIPH, 63, 0 },
+	{ DBGBUS_PERIPH, 64, 0 },
+	{ DBGBUS_PERIPH, 65, 0 },
+	{ DBGBUS_PERIPH, 73, 0 },
+	{ DBGBUS_PERIPH, 74, 0 },
+
+	/* crossbar */
+	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
+
+	/* rotator */
+	{ DBGBUS_DSPP, 9, 0},
+
+	/* blend */
+	/* LM0 */
+	{ DBGBUS_DSPP, 63, 0},
+	{ DBGBUS_DSPP, 63, 1},
+	{ DBGBUS_DSPP, 63, 2},
+	{ DBGBUS_DSPP, 63, 3},
+	{ DBGBUS_DSPP, 63, 4},
+	{ DBGBUS_DSPP, 63, 5},
+	{ DBGBUS_DSPP, 63, 6},
+	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 64, 0},
+	{ DBGBUS_DSPP, 64, 1},
+	{ DBGBUS_DSPP, 64, 2},
+	{ DBGBUS_DSPP, 64, 3},
+	{ DBGBUS_DSPP, 64, 4},
+	{ DBGBUS_DSPP, 64, 5},
+	{ DBGBUS_DSPP, 64, 6},
+	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 65, 0},
+	{ DBGBUS_DSPP, 65, 1},
+	{ DBGBUS_DSPP, 65, 2},
+	{ DBGBUS_DSPP, 65, 3},
+	{ DBGBUS_DSPP, 65, 4},
+	{ DBGBUS_DSPP, 65, 5},
+	{ DBGBUS_DSPP, 65, 6},
+	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 66, 0},
+	{ DBGBUS_DSPP, 66, 1},
+	{ DBGBUS_DSPP, 66, 2},
+	{ DBGBUS_DSPP, 66, 3},
+	{ DBGBUS_DSPP, 66, 4},
+	{ DBGBUS_DSPP, 66, 5},
+	{ DBGBUS_DSPP, 66, 6},
+	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 67, 0},
+	{ DBGBUS_DSPP, 67, 1},
+	{ DBGBUS_DSPP, 67, 2},
+	{ DBGBUS_DSPP, 67, 3},
+	{ DBGBUS_DSPP, 67, 4},
+	{ DBGBUS_DSPP, 67, 5},
+	{ DBGBUS_DSPP, 67, 6},
+	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 68, 0},
+	{ DBGBUS_DSPP, 68, 1},
+	{ DBGBUS_DSPP, 68, 2},
+	{ DBGBUS_DSPP, 68, 3},
+	{ DBGBUS_DSPP, 68, 4},
+	{ DBGBUS_DSPP, 68, 5},
+	{ DBGBUS_DSPP, 68, 6},
+	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 69, 0},
+	{ DBGBUS_DSPP, 69, 1},
+	{ DBGBUS_DSPP, 69, 2},
+	{ DBGBUS_DSPP, 69, 3},
+	{ DBGBUS_DSPP, 69, 4},
+	{ DBGBUS_DSPP, 69, 5},
+	{ DBGBUS_DSPP, 69, 6},
+	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM1 */
+	{ DBGBUS_DSPP, 70, 0},
+	{ DBGBUS_DSPP, 70, 1},
+	{ DBGBUS_DSPP, 70, 2},
+	{ DBGBUS_DSPP, 70, 3},
+	{ DBGBUS_DSPP, 70, 4},
+	{ DBGBUS_DSPP, 70, 5},
+	{ DBGBUS_DSPP, 70, 6},
+	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 71, 0},
+	{ DBGBUS_DSPP, 71, 1},
+	{ DBGBUS_DSPP, 71, 2},
+	{ DBGBUS_DSPP, 71, 3},
+	{ DBGBUS_DSPP, 71, 4},
+	{ DBGBUS_DSPP, 71, 5},
+	{ DBGBUS_DSPP, 71, 6},
+	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 72, 0},
+	{ DBGBUS_DSPP, 72, 1},
+	{ DBGBUS_DSPP, 72, 2},
+	{ DBGBUS_DSPP, 72, 3},
+	{ DBGBUS_DSPP, 72, 4},
+	{ DBGBUS_DSPP, 72, 5},
+	{ DBGBUS_DSPP, 72, 6},
+	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 73, 0},
+	{ DBGBUS_DSPP, 73, 1},
+	{ DBGBUS_DSPP, 73, 2},
+	{ DBGBUS_DSPP, 73, 3},
+	{ DBGBUS_DSPP, 73, 4},
+	{ DBGBUS_DSPP, 73, 5},
+	{ DBGBUS_DSPP, 73, 6},
+	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 74, 0},
+	{ DBGBUS_DSPP, 74, 1},
+	{ DBGBUS_DSPP, 74, 2},
+	{ DBGBUS_DSPP, 74, 3},
+	{ DBGBUS_DSPP, 74, 4},
+	{ DBGBUS_DSPP, 74, 5},
+	{ DBGBUS_DSPP, 74, 6},
+	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 75, 0},
+	{ DBGBUS_DSPP, 75, 1},
+	{ DBGBUS_DSPP, 75, 2},
+	{ DBGBUS_DSPP, 75, 3},
+	{ DBGBUS_DSPP, 75, 4},
+	{ DBGBUS_DSPP, 75, 5},
+	{ DBGBUS_DSPP, 75, 6},
+	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 76, 0},
+	{ DBGBUS_DSPP, 76, 1},
+	{ DBGBUS_DSPP, 76, 2},
+	{ DBGBUS_DSPP, 76, 3},
+	{ DBGBUS_DSPP, 76, 4},
+	{ DBGBUS_DSPP, 76, 5},
+	{ DBGBUS_DSPP, 76, 6},
+	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM2 */
+	{ DBGBUS_DSPP, 77, 0},
+	{ DBGBUS_DSPP, 77, 1},
+	{ DBGBUS_DSPP, 77, 2},
+	{ DBGBUS_DSPP, 77, 3},
+	{ DBGBUS_DSPP, 77, 4},
+	{ DBGBUS_DSPP, 77, 5},
+	{ DBGBUS_DSPP, 77, 6},
+	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 78, 0},
+	{ DBGBUS_DSPP, 78, 1},
+	{ DBGBUS_DSPP, 78, 2},
+	{ DBGBUS_DSPP, 78, 3},
+	{ DBGBUS_DSPP, 78, 4},
+	{ DBGBUS_DSPP, 78, 5},
+	{ DBGBUS_DSPP, 78, 6},
+	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 79, 0},
+	{ DBGBUS_DSPP, 79, 1},
+	{ DBGBUS_DSPP, 79, 2},
+	{ DBGBUS_DSPP, 79, 3},
+	{ DBGBUS_DSPP, 79, 4},
+	{ DBGBUS_DSPP, 79, 5},
+	{ DBGBUS_DSPP, 79, 6},
+	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 80, 0},
+	{ DBGBUS_DSPP, 80, 1},
+	{ DBGBUS_DSPP, 80, 2},
+	{ DBGBUS_DSPP, 80, 3},
+	{ DBGBUS_DSPP, 80, 4},
+	{ DBGBUS_DSPP, 80, 5},
+	{ DBGBUS_DSPP, 80, 6},
+	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 81, 0},
+	{ DBGBUS_DSPP, 81, 1},
+	{ DBGBUS_DSPP, 81, 2},
+	{ DBGBUS_DSPP, 81, 3},
+	{ DBGBUS_DSPP, 81, 4},
+	{ DBGBUS_DSPP, 81, 5},
+	{ DBGBUS_DSPP, 81, 6},
+	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 82, 0},
+	{ DBGBUS_DSPP, 82, 1},
+	{ DBGBUS_DSPP, 82, 2},
+	{ DBGBUS_DSPP, 82, 3},
+	{ DBGBUS_DSPP, 82, 4},
+	{ DBGBUS_DSPP, 82, 5},
+	{ DBGBUS_DSPP, 82, 6},
+	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 83, 0},
+	{ DBGBUS_DSPP, 83, 1},
+	{ DBGBUS_DSPP, 83, 2},
+	{ DBGBUS_DSPP, 83, 3},
+	{ DBGBUS_DSPP, 83, 4},
+	{ DBGBUS_DSPP, 83, 5},
+	{ DBGBUS_DSPP, 83, 6},
+	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
+
+	/* csc */
+	{ DBGBUS_SSPP0, 7, 0},
+	{ DBGBUS_SSPP0, 7, 1},
+	{ DBGBUS_SSPP0, 27, 0},
+	{ DBGBUS_SSPP0, 27, 1},
+	{ DBGBUS_SSPP1, 7, 0},
+	{ DBGBUS_SSPP1, 7, 1},
+	{ DBGBUS_SSPP1, 27, 0},
+	{ DBGBUS_SSPP1, 27, 1},
+
+	/* pcc */
+	{ DBGBUS_SSPP0, 3,  3},
+	{ DBGBUS_SSPP0, 23, 3},
+	{ DBGBUS_SSPP0, 33, 3},
+	{ DBGBUS_SSPP0, 43, 3},
+	{ DBGBUS_SSPP1, 3,  3},
+	{ DBGBUS_SSPP1, 23, 3},
+	{ DBGBUS_SSPP1, 33, 3},
+	{ DBGBUS_SSPP1, 43, 3},
+
+	/* spa */
+	{ DBGBUS_SSPP0, 8,  0},
+	{ DBGBUS_SSPP0, 28, 0},
+	{ DBGBUS_SSPP1, 8,  0},
+	{ DBGBUS_SSPP1, 28, 0},
+	{ DBGBUS_DSPP, 13, 0},
+	{ DBGBUS_DSPP, 19, 0},
+
+	/* igc */
+	{ DBGBUS_SSPP0, 9,  0},
+	{ DBGBUS_SSPP0, 9,  1},
+	{ DBGBUS_SSPP0, 9,  3},
+	{ DBGBUS_SSPP0, 29, 0},
+	{ DBGBUS_SSPP0, 29, 1},
+	{ DBGBUS_SSPP0, 29, 3},
+	{ DBGBUS_SSPP0, 17, 0},
+	{ DBGBUS_SSPP0, 17, 1},
+	{ DBGBUS_SSPP0, 17, 3},
+	{ DBGBUS_SSPP0, 37, 0},
+	{ DBGBUS_SSPP0, 37, 1},
+	{ DBGBUS_SSPP0, 37, 3},
+	{ DBGBUS_SSPP0, 46, 0},
+	{ DBGBUS_SSPP0, 46, 1},
+	{ DBGBUS_SSPP0, 46, 3},
+
+	{ DBGBUS_SSPP1, 9,  0},
+	{ DBGBUS_SSPP1, 9,  1},
+	{ DBGBUS_SSPP1, 9,  3},
+	{ DBGBUS_SSPP1, 29, 0},
+	{ DBGBUS_SSPP1, 29, 1},
+	{ DBGBUS_SSPP1, 29, 3},
+	{ DBGBUS_SSPP1, 17, 0},
+	{ DBGBUS_SSPP1, 17, 1},
+	{ DBGBUS_SSPP1, 17, 3},
+	{ DBGBUS_SSPP1, 37, 0},
+	{ DBGBUS_SSPP1, 37, 1},
+	{ DBGBUS_SSPP1, 37, 3},
+	{ DBGBUS_SSPP1, 46, 0},
+	{ DBGBUS_SSPP1, 46, 1},
+	{ DBGBUS_SSPP1, 46, 3},
+
+	{ DBGBUS_DSPP, 14, 0},
+	{ DBGBUS_DSPP, 14, 1},
+	{ DBGBUS_DSPP, 14, 3},
+	{ DBGBUS_DSPP, 20, 0},
+	{ DBGBUS_DSPP, 20, 1},
+	{ DBGBUS_DSPP, 20, 3},
+
+	{ DBGBUS_PERIPH, 60, 0},
+};
+
+static struct dpu_debug_bus_entry dbg_bus_dpu_sdm845[] = {
+
+	/* Unpack 0 sspp 0*/
+	{ DBGBUS_SSPP0, 50, 2 },
+	{ DBGBUS_SSPP0, 60, 2 },
+	{ DBGBUS_SSPP0, 70, 2 },
+
+	/* Upack 0 sspp 1*/
+	{ DBGBUS_SSPP1, 50, 2 },
+	{ DBGBUS_SSPP1, 60, 2 },
+	{ DBGBUS_SSPP1, 70, 2 },
+
+	/* scheduler */
+	{ DBGBUS_DSPP, 130, 0 },
+	{ DBGBUS_DSPP, 130, 1 },
+	{ DBGBUS_DSPP, 130, 2 },
+	{ DBGBUS_DSPP, 130, 3 },
+	{ DBGBUS_DSPP, 130, 4 },
+	{ DBGBUS_DSPP, 130, 5 },
+
+	/* qseed */
+	{ DBGBUS_SSPP0, 6, 0},
+	{ DBGBUS_SSPP0, 6, 1},
+	{ DBGBUS_SSPP0, 26, 0},
+	{ DBGBUS_SSPP0, 26, 1},
+	{ DBGBUS_SSPP1, 6, 0},
+	{ DBGBUS_SSPP1, 6, 1},
+	{ DBGBUS_SSPP1, 26, 0},
+	{ DBGBUS_SSPP1, 26, 1},
+
+	/* scale */
+	{ DBGBUS_SSPP0, 16, 0},
+	{ DBGBUS_SSPP0, 16, 1},
+	{ DBGBUS_SSPP0, 36, 0},
+	{ DBGBUS_SSPP0, 36, 1},
+	{ DBGBUS_SSPP1, 16, 0},
+	{ DBGBUS_SSPP1, 16, 1},
+	{ DBGBUS_SSPP1, 36, 0},
+	{ DBGBUS_SSPP1, 36, 1},
+
+	/* fetch sspp0 */
+
+	/* vig 0 */
+	{ DBGBUS_SSPP0, 0, 0 },
+	{ DBGBUS_SSPP0, 0, 1 },
+	{ DBGBUS_SSPP0, 0, 2 },
+	{ DBGBUS_SSPP0, 0, 3 },
+	{ DBGBUS_SSPP0, 0, 4 },
+	{ DBGBUS_SSPP0, 0, 5 },
+	{ DBGBUS_SSPP0, 0, 6 },
+	{ DBGBUS_SSPP0, 0, 7 },
+
+	{ DBGBUS_SSPP0, 1, 0 },
+	{ DBGBUS_SSPP0, 1, 1 },
+	{ DBGBUS_SSPP0, 1, 2 },
+	{ DBGBUS_SSPP0, 1, 3 },
+	{ DBGBUS_SSPP0, 1, 4 },
+	{ DBGBUS_SSPP0, 1, 5 },
+	{ DBGBUS_SSPP0, 1, 6 },
+	{ DBGBUS_SSPP0, 1, 7 },
+
+	{ DBGBUS_SSPP0, 2, 0 },
+	{ DBGBUS_SSPP0, 2, 1 },
+	{ DBGBUS_SSPP0, 2, 2 },
+	{ DBGBUS_SSPP0, 2, 3 },
+	{ DBGBUS_SSPP0, 2, 4 },
+	{ DBGBUS_SSPP0, 2, 5 },
+	{ DBGBUS_SSPP0, 2, 6 },
+	{ DBGBUS_SSPP0, 2, 7 },
+
+	{ DBGBUS_SSPP0, 4, 0 },
+	{ DBGBUS_SSPP0, 4, 1 },
+	{ DBGBUS_SSPP0, 4, 2 },
+	{ DBGBUS_SSPP0, 4, 3 },
+	{ DBGBUS_SSPP0, 4, 4 },
+	{ DBGBUS_SSPP0, 4, 5 },
+	{ DBGBUS_SSPP0, 4, 6 },
+	{ DBGBUS_SSPP0, 4, 7 },
+
+	{ DBGBUS_SSPP0, 5, 0 },
+	{ DBGBUS_SSPP0, 5, 1 },
+	{ DBGBUS_SSPP0, 5, 2 },
+	{ DBGBUS_SSPP0, 5, 3 },
+	{ DBGBUS_SSPP0, 5, 4 },
+	{ DBGBUS_SSPP0, 5, 5 },
+	{ DBGBUS_SSPP0, 5, 6 },
+	{ DBGBUS_SSPP0, 5, 7 },
+
+	/* vig 2 */
+	{ DBGBUS_SSPP0, 20, 0 },
+	{ DBGBUS_SSPP0, 20, 1 },
+	{ DBGBUS_SSPP0, 20, 2 },
+	{ DBGBUS_SSPP0, 20, 3 },
+	{ DBGBUS_SSPP0, 20, 4 },
+	{ DBGBUS_SSPP0, 20, 5 },
+	{ DBGBUS_SSPP0, 20, 6 },
+	{ DBGBUS_SSPP0, 20, 7 },
+
+	{ DBGBUS_SSPP0, 21, 0 },
+	{ DBGBUS_SSPP0, 21, 1 },
+	{ DBGBUS_SSPP0, 21, 2 },
+	{ DBGBUS_SSPP0, 21, 3 },
+	{ DBGBUS_SSPP0, 21, 4 },
+	{ DBGBUS_SSPP0, 21, 5 },
+	{ DBGBUS_SSPP0, 21, 6 },
+	{ DBGBUS_SSPP0, 21, 7 },
+
+	{ DBGBUS_SSPP0, 22, 0 },
+	{ DBGBUS_SSPP0, 22, 1 },
+	{ DBGBUS_SSPP0, 22, 2 },
+	{ DBGBUS_SSPP0, 22, 3 },
+	{ DBGBUS_SSPP0, 22, 4 },
+	{ DBGBUS_SSPP0, 22, 5 },
+	{ DBGBUS_SSPP0, 22, 6 },
+	{ DBGBUS_SSPP0, 22, 7 },
+
+	{ DBGBUS_SSPP0, 24, 0 },
+	{ DBGBUS_SSPP0, 24, 1 },
+	{ DBGBUS_SSPP0, 24, 2 },
+	{ DBGBUS_SSPP0, 24, 3 },
+	{ DBGBUS_SSPP0, 24, 4 },
+	{ DBGBUS_SSPP0, 24, 5 },
+	{ DBGBUS_SSPP0, 24, 6 },
+	{ DBGBUS_SSPP0, 24, 7 },
+
+	{ DBGBUS_SSPP0, 25, 0 },
+	{ DBGBUS_SSPP0, 25, 1 },
+	{ DBGBUS_SSPP0, 25, 2 },
+	{ DBGBUS_SSPP0, 25, 3 },
+	{ DBGBUS_SSPP0, 25, 4 },
+	{ DBGBUS_SSPP0, 25, 5 },
+	{ DBGBUS_SSPP0, 25, 6 },
+	{ DBGBUS_SSPP0, 25, 7 },
+
+	/* dma 2 */
+	{ DBGBUS_SSPP0, 30, 0 },
+	{ DBGBUS_SSPP0, 30, 1 },
+	{ DBGBUS_SSPP0, 30, 2 },
+	{ DBGBUS_SSPP0, 30, 3 },
+	{ DBGBUS_SSPP0, 30, 4 },
+	{ DBGBUS_SSPP0, 30, 5 },
+	{ DBGBUS_SSPP0, 30, 6 },
+	{ DBGBUS_SSPP0, 30, 7 },
+
+	{ DBGBUS_SSPP0, 31, 0 },
+	{ DBGBUS_SSPP0, 31, 1 },
+	{ DBGBUS_SSPP0, 31, 2 },
+	{ DBGBUS_SSPP0, 31, 3 },
+	{ DBGBUS_SSPP0, 31, 4 },
+	{ DBGBUS_SSPP0, 31, 5 },
+	{ DBGBUS_SSPP0, 31, 6 },
+	{ DBGBUS_SSPP0, 31, 7 },
+
+	{ DBGBUS_SSPP0, 32, 0 },
+	{ DBGBUS_SSPP0, 32, 1 },
+	{ DBGBUS_SSPP0, 32, 2 },
+	{ DBGBUS_SSPP0, 32, 3 },
+	{ DBGBUS_SSPP0, 32, 4 },
+	{ DBGBUS_SSPP0, 32, 5 },
+	{ DBGBUS_SSPP0, 32, 6 },
+	{ DBGBUS_SSPP0, 32, 7 },
+
+	{ DBGBUS_SSPP0, 33, 0 },
+	{ DBGBUS_SSPP0, 33, 1 },
+	{ DBGBUS_SSPP0, 33, 2 },
+	{ DBGBUS_SSPP0, 33, 3 },
+	{ DBGBUS_SSPP0, 33, 4 },
+	{ DBGBUS_SSPP0, 33, 5 },
+	{ DBGBUS_SSPP0, 33, 6 },
+	{ DBGBUS_SSPP0, 33, 7 },
+
+	{ DBGBUS_SSPP0, 34, 0 },
+	{ DBGBUS_SSPP0, 34, 1 },
+	{ DBGBUS_SSPP0, 34, 2 },
+	{ DBGBUS_SSPP0, 34, 3 },
+	{ DBGBUS_SSPP0, 34, 4 },
+	{ DBGBUS_SSPP0, 34, 5 },
+	{ DBGBUS_SSPP0, 34, 6 },
+	{ DBGBUS_SSPP0, 34, 7 },
+
+	{ DBGBUS_SSPP0, 35, 0 },
+	{ DBGBUS_SSPP0, 35, 1 },
+	{ DBGBUS_SSPP0, 35, 2 },
+	{ DBGBUS_SSPP0, 35, 3 },
+
+	/* dma 0 */
+	{ DBGBUS_SSPP0, 40, 0 },
+	{ DBGBUS_SSPP0, 40, 1 },
+	{ DBGBUS_SSPP0, 40, 2 },
+	{ DBGBUS_SSPP0, 40, 3 },
+	{ DBGBUS_SSPP0, 40, 4 },
+	{ DBGBUS_SSPP0, 40, 5 },
+	{ DBGBUS_SSPP0, 40, 6 },
+	{ DBGBUS_SSPP0, 40, 7 },
+
+	{ DBGBUS_SSPP0, 41, 0 },
+	{ DBGBUS_SSPP0, 41, 1 },
+	{ DBGBUS_SSPP0, 41, 2 },
+	{ DBGBUS_SSPP0, 41, 3 },
+	{ DBGBUS_SSPP0, 41, 4 },
+	{ DBGBUS_SSPP0, 41, 5 },
+	{ DBGBUS_SSPP0, 41, 6 },
+	{ DBGBUS_SSPP0, 41, 7 },
+
+	{ DBGBUS_SSPP0, 42, 0 },
+	{ DBGBUS_SSPP0, 42, 1 },
+	{ DBGBUS_SSPP0, 42, 2 },
+	{ DBGBUS_SSPP0, 42, 3 },
+	{ DBGBUS_SSPP0, 42, 4 },
+	{ DBGBUS_SSPP0, 42, 5 },
+	{ DBGBUS_SSPP0, 42, 6 },
+	{ DBGBUS_SSPP0, 42, 7 },
+
+	{ DBGBUS_SSPP0, 44, 0 },
+	{ DBGBUS_SSPP0, 44, 1 },
+	{ DBGBUS_SSPP0, 44, 2 },
+	{ DBGBUS_SSPP0, 44, 3 },
+	{ DBGBUS_SSPP0, 44, 4 },
+	{ DBGBUS_SSPP0, 44, 5 },
+	{ DBGBUS_SSPP0, 44, 6 },
+	{ DBGBUS_SSPP0, 44, 7 },
+
+	{ DBGBUS_SSPP0, 45, 0 },
+	{ DBGBUS_SSPP0, 45, 1 },
+	{ DBGBUS_SSPP0, 45, 2 },
+	{ DBGBUS_SSPP0, 45, 3 },
+	{ DBGBUS_SSPP0, 45, 4 },
+	{ DBGBUS_SSPP0, 45, 5 },
+	{ DBGBUS_SSPP0, 45, 6 },
+	{ DBGBUS_SSPP0, 45, 7 },
+
+	/* fetch sspp1 */
+	/* vig 1 */
+	{ DBGBUS_SSPP1, 0, 0 },
+	{ DBGBUS_SSPP1, 0, 1 },
+	{ DBGBUS_SSPP1, 0, 2 },
+	{ DBGBUS_SSPP1, 0, 3 },
+	{ DBGBUS_SSPP1, 0, 4 },
+	{ DBGBUS_SSPP1, 0, 5 },
+	{ DBGBUS_SSPP1, 0, 6 },
+	{ DBGBUS_SSPP1, 0, 7 },
+
+	{ DBGBUS_SSPP1, 1, 0 },
+	{ DBGBUS_SSPP1, 1, 1 },
+	{ DBGBUS_SSPP1, 1, 2 },
+	{ DBGBUS_SSPP1, 1, 3 },
+	{ DBGBUS_SSPP1, 1, 4 },
+	{ DBGBUS_SSPP1, 1, 5 },
+	{ DBGBUS_SSPP1, 1, 6 },
+	{ DBGBUS_SSPP1, 1, 7 },
+
+	{ DBGBUS_SSPP1, 2, 0 },
+	{ DBGBUS_SSPP1, 2, 1 },
+	{ DBGBUS_SSPP1, 2, 2 },
+	{ DBGBUS_SSPP1, 2, 3 },
+	{ DBGBUS_SSPP1, 2, 4 },
+	{ DBGBUS_SSPP1, 2, 5 },
+	{ DBGBUS_SSPP1, 2, 6 },
+	{ DBGBUS_SSPP1, 2, 7 },
+
+	{ DBGBUS_SSPP1, 4, 0 },
+	{ DBGBUS_SSPP1, 4, 1 },
+	{ DBGBUS_SSPP1, 4, 2 },
+	{ DBGBUS_SSPP1, 4, 3 },
+	{ DBGBUS_SSPP1, 4, 4 },
+	{ DBGBUS_SSPP1, 4, 5 },
+	{ DBGBUS_SSPP1, 4, 6 },
+	{ DBGBUS_SSPP1, 4, 7 },
+
+	{ DBGBUS_SSPP1, 5, 0 },
+	{ DBGBUS_SSPP1, 5, 1 },
+	{ DBGBUS_SSPP1, 5, 2 },
+	{ DBGBUS_SSPP1, 5, 3 },
+	{ DBGBUS_SSPP1, 5, 4 },
+	{ DBGBUS_SSPP1, 5, 5 },
+	{ DBGBUS_SSPP1, 5, 6 },
+	{ DBGBUS_SSPP1, 5, 7 },
+
+	/* vig 3 */
+	{ DBGBUS_SSPP1, 20, 0 },
+	{ DBGBUS_SSPP1, 20, 1 },
+	{ DBGBUS_SSPP1, 20, 2 },
+	{ DBGBUS_SSPP1, 20, 3 },
+	{ DBGBUS_SSPP1, 20, 4 },
+	{ DBGBUS_SSPP1, 20, 5 },
+	{ DBGBUS_SSPP1, 20, 6 },
+	{ DBGBUS_SSPP1, 20, 7 },
+
+	{ DBGBUS_SSPP1, 21, 0 },
+	{ DBGBUS_SSPP1, 21, 1 },
+	{ DBGBUS_SSPP1, 21, 2 },
+	{ DBGBUS_SSPP1, 21, 3 },
+	{ DBGBUS_SSPP1, 21, 4 },
+	{ DBGBUS_SSPP1, 21, 5 },
+	{ DBGBUS_SSPP1, 21, 6 },
+	{ DBGBUS_SSPP1, 21, 7 },
+
+	{ DBGBUS_SSPP1, 22, 0 },
+	{ DBGBUS_SSPP1, 22, 1 },
+	{ DBGBUS_SSPP1, 22, 2 },
+	{ DBGBUS_SSPP1, 22, 3 },
+	{ DBGBUS_SSPP1, 22, 4 },
+	{ DBGBUS_SSPP1, 22, 5 },
+	{ DBGBUS_SSPP1, 22, 6 },
+	{ DBGBUS_SSPP1, 22, 7 },
+
+	{ DBGBUS_SSPP1, 24, 0 },
+	{ DBGBUS_SSPP1, 24, 1 },
+	{ DBGBUS_SSPP1, 24, 2 },
+	{ DBGBUS_SSPP1, 24, 3 },
+	{ DBGBUS_SSPP1, 24, 4 },
+	{ DBGBUS_SSPP1, 24, 5 },
+	{ DBGBUS_SSPP1, 24, 6 },
+	{ DBGBUS_SSPP1, 24, 7 },
+
+	{ DBGBUS_SSPP1, 25, 0 },
+	{ DBGBUS_SSPP1, 25, 1 },
+	{ DBGBUS_SSPP1, 25, 2 },
+	{ DBGBUS_SSPP1, 25, 3 },
+	{ DBGBUS_SSPP1, 25, 4 },
+	{ DBGBUS_SSPP1, 25, 5 },
+	{ DBGBUS_SSPP1, 25, 6 },
+	{ DBGBUS_SSPP1, 25, 7 },
+
+	/* dma 3 */
+	{ DBGBUS_SSPP1, 30, 0 },
+	{ DBGBUS_SSPP1, 30, 1 },
+	{ DBGBUS_SSPP1, 30, 2 },
+	{ DBGBUS_SSPP1, 30, 3 },
+	{ DBGBUS_SSPP1, 30, 4 },
+	{ DBGBUS_SSPP1, 30, 5 },
+	{ DBGBUS_SSPP1, 30, 6 },
+	{ DBGBUS_SSPP1, 30, 7 },
+
+	{ DBGBUS_SSPP1, 31, 0 },
+	{ DBGBUS_SSPP1, 31, 1 },
+	{ DBGBUS_SSPP1, 31, 2 },
+	{ DBGBUS_SSPP1, 31, 3 },
+	{ DBGBUS_SSPP1, 31, 4 },
+	{ DBGBUS_SSPP1, 31, 5 },
+	{ DBGBUS_SSPP1, 31, 6 },
+	{ DBGBUS_SSPP1, 31, 7 },
+
+	{ DBGBUS_SSPP1, 32, 0 },
+	{ DBGBUS_SSPP1, 32, 1 },
+	{ DBGBUS_SSPP1, 32, 2 },
+	{ DBGBUS_SSPP1, 32, 3 },
+	{ DBGBUS_SSPP1, 32, 4 },
+	{ DBGBUS_SSPP1, 32, 5 },
+	{ DBGBUS_SSPP1, 32, 6 },
+	{ DBGBUS_SSPP1, 32, 7 },
+
+	{ DBGBUS_SSPP1, 33, 0 },
+	{ DBGBUS_SSPP1, 33, 1 },
+	{ DBGBUS_SSPP1, 33, 2 },
+	{ DBGBUS_SSPP1, 33, 3 },
+	{ DBGBUS_SSPP1, 33, 4 },
+	{ DBGBUS_SSPP1, 33, 5 },
+	{ DBGBUS_SSPP1, 33, 6 },
+	{ DBGBUS_SSPP1, 33, 7 },
+
+	{ DBGBUS_SSPP1, 34, 0 },
+	{ DBGBUS_SSPP1, 34, 1 },
+	{ DBGBUS_SSPP1, 34, 2 },
+	{ DBGBUS_SSPP1, 34, 3 },
+	{ DBGBUS_SSPP1, 34, 4 },
+	{ DBGBUS_SSPP1, 34, 5 },
+	{ DBGBUS_SSPP1, 34, 6 },
+	{ DBGBUS_SSPP1, 34, 7 },
+
+	{ DBGBUS_SSPP1, 35, 0 },
+	{ DBGBUS_SSPP1, 35, 1 },
+	{ DBGBUS_SSPP1, 35, 2 },
+
+	/* dma 1 */
+	{ DBGBUS_SSPP1, 40, 0 },
+	{ DBGBUS_SSPP1, 40, 1 },
+	{ DBGBUS_SSPP1, 40, 2 },
+	{ DBGBUS_SSPP1, 40, 3 },
+	{ DBGBUS_SSPP1, 40, 4 },
+	{ DBGBUS_SSPP1, 40, 5 },
+	{ DBGBUS_SSPP1, 40, 6 },
+	{ DBGBUS_SSPP1, 40, 7 },
+
+	{ DBGBUS_SSPP1, 41, 0 },
+	{ DBGBUS_SSPP1, 41, 1 },
+	{ DBGBUS_SSPP1, 41, 2 },
+	{ DBGBUS_SSPP1, 41, 3 },
+	{ DBGBUS_SSPP1, 41, 4 },
+	{ DBGBUS_SSPP1, 41, 5 },
+	{ DBGBUS_SSPP1, 41, 6 },
+	{ DBGBUS_SSPP1, 41, 7 },
+
+	{ DBGBUS_SSPP1, 42, 0 },
+	{ DBGBUS_SSPP1, 42, 1 },
+	{ DBGBUS_SSPP1, 42, 2 },
+	{ DBGBUS_SSPP1, 42, 3 },
+	{ DBGBUS_SSPP1, 42, 4 },
+	{ DBGBUS_SSPP1, 42, 5 },
+	{ DBGBUS_SSPP1, 42, 6 },
+	{ DBGBUS_SSPP1, 42, 7 },
+
+	{ DBGBUS_SSPP1, 44, 0 },
+	{ DBGBUS_SSPP1, 44, 1 },
+	{ DBGBUS_SSPP1, 44, 2 },
+	{ DBGBUS_SSPP1, 44, 3 },
+	{ DBGBUS_SSPP1, 44, 4 },
+	{ DBGBUS_SSPP1, 44, 5 },
+	{ DBGBUS_SSPP1, 44, 6 },
+	{ DBGBUS_SSPP1, 44, 7 },
+
+	{ DBGBUS_SSPP1, 45, 0 },
+	{ DBGBUS_SSPP1, 45, 1 },
+	{ DBGBUS_SSPP1, 45, 2 },
+	{ DBGBUS_SSPP1, 45, 3 },
+	{ DBGBUS_SSPP1, 45, 4 },
+	{ DBGBUS_SSPP1, 45, 5 },
+	{ DBGBUS_SSPP1, 45, 6 },
+	{ DBGBUS_SSPP1, 45, 7 },
+
+	/* dspp */
+	{ DBGBUS_DSPP, 13, 0 },
+	{ DBGBUS_DSPP, 19, 0 },
+	{ DBGBUS_DSPP, 14, 0 },
+	{ DBGBUS_DSPP, 14, 1 },
+	{ DBGBUS_DSPP, 14, 3 },
+	{ DBGBUS_DSPP, 20, 0 },
+	{ DBGBUS_DSPP, 20, 1 },
+	{ DBGBUS_DSPP, 20, 3 },
+
+	/* ppb_0 */
+	{ DBGBUS_DSPP, 31, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 33, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 35, 0, _dpu_debug_bus_ppb0_dump },
+	{ DBGBUS_DSPP, 42, 0, _dpu_debug_bus_ppb0_dump },
+
+	/* ppb_1 */
+	{ DBGBUS_DSPP, 32, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 34, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 36, 0, _dpu_debug_bus_ppb1_dump },
+	{ DBGBUS_DSPP, 43, 0, _dpu_debug_bus_ppb1_dump },
+
+	/* lm_lut */
+	{ DBGBUS_DSPP, 109, 0 },
+	{ DBGBUS_DSPP, 105, 0 },
+	{ DBGBUS_DSPP, 103, 0 },
+
+	/* crossbar */
+	{ DBGBUS_DSPP, 0, 0, _dpu_debug_bus_xbar_dump },
+
+	/* rotator */
+	{ DBGBUS_DSPP, 9, 0},
+
+	/* blend */
+	/* LM0 */
+	{ DBGBUS_DSPP, 63, 1},
+	{ DBGBUS_DSPP, 63, 2},
+	{ DBGBUS_DSPP, 63, 3},
+	{ DBGBUS_DSPP, 63, 4},
+	{ DBGBUS_DSPP, 63, 5},
+	{ DBGBUS_DSPP, 63, 6},
+	{ DBGBUS_DSPP, 63, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 64, 1},
+	{ DBGBUS_DSPP, 64, 2},
+	{ DBGBUS_DSPP, 64, 3},
+	{ DBGBUS_DSPP, 64, 4},
+	{ DBGBUS_DSPP, 64, 5},
+	{ DBGBUS_DSPP, 64, 6},
+	{ DBGBUS_DSPP, 64, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 65, 1},
+	{ DBGBUS_DSPP, 65, 2},
+	{ DBGBUS_DSPP, 65, 3},
+	{ DBGBUS_DSPP, 65, 4},
+	{ DBGBUS_DSPP, 65, 5},
+	{ DBGBUS_DSPP, 65, 6},
+	{ DBGBUS_DSPP, 65, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 66, 1},
+	{ DBGBUS_DSPP, 66, 2},
+	{ DBGBUS_DSPP, 66, 3},
+	{ DBGBUS_DSPP, 66, 4},
+	{ DBGBUS_DSPP, 66, 5},
+	{ DBGBUS_DSPP, 66, 6},
+	{ DBGBUS_DSPP, 66, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 67, 1},
+	{ DBGBUS_DSPP, 67, 2},
+	{ DBGBUS_DSPP, 67, 3},
+	{ DBGBUS_DSPP, 67, 4},
+	{ DBGBUS_DSPP, 67, 5},
+	{ DBGBUS_DSPP, 67, 6},
+	{ DBGBUS_DSPP, 67, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 68, 1},
+	{ DBGBUS_DSPP, 68, 2},
+	{ DBGBUS_DSPP, 68, 3},
+	{ DBGBUS_DSPP, 68, 4},
+	{ DBGBUS_DSPP, 68, 5},
+	{ DBGBUS_DSPP, 68, 6},
+	{ DBGBUS_DSPP, 68, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 69, 1},
+	{ DBGBUS_DSPP, 69, 2},
+	{ DBGBUS_DSPP, 69, 3},
+	{ DBGBUS_DSPP, 69, 4},
+	{ DBGBUS_DSPP, 69, 5},
+	{ DBGBUS_DSPP, 69, 6},
+	{ DBGBUS_DSPP, 69, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 84, 1},
+	{ DBGBUS_DSPP, 84, 2},
+	{ DBGBUS_DSPP, 84, 3},
+	{ DBGBUS_DSPP, 84, 4},
+	{ DBGBUS_DSPP, 84, 5},
+	{ DBGBUS_DSPP, 84, 6},
+	{ DBGBUS_DSPP, 84, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 85, 1},
+	{ DBGBUS_DSPP, 85, 2},
+	{ DBGBUS_DSPP, 85, 3},
+	{ DBGBUS_DSPP, 85, 4},
+	{ DBGBUS_DSPP, 85, 5},
+	{ DBGBUS_DSPP, 85, 6},
+	{ DBGBUS_DSPP, 85, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 86, 1},
+	{ DBGBUS_DSPP, 86, 2},
+	{ DBGBUS_DSPP, 86, 3},
+	{ DBGBUS_DSPP, 86, 4},
+	{ DBGBUS_DSPP, 86, 5},
+	{ DBGBUS_DSPP, 86, 6},
+	{ DBGBUS_DSPP, 86, 7, _dpu_debug_bus_lm_dump },
+
+
+	{ DBGBUS_DSPP, 87, 1},
+	{ DBGBUS_DSPP, 87, 2},
+	{ DBGBUS_DSPP, 87, 3},
+	{ DBGBUS_DSPP, 87, 4},
+	{ DBGBUS_DSPP, 87, 5},
+	{ DBGBUS_DSPP, 87, 6},
+	{ DBGBUS_DSPP, 87, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM1 */
+	{ DBGBUS_DSPP, 70, 1},
+	{ DBGBUS_DSPP, 70, 2},
+	{ DBGBUS_DSPP, 70, 3},
+	{ DBGBUS_DSPP, 70, 4},
+	{ DBGBUS_DSPP, 70, 5},
+	{ DBGBUS_DSPP, 70, 6},
+	{ DBGBUS_DSPP, 70, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 71, 1},
+	{ DBGBUS_DSPP, 71, 2},
+	{ DBGBUS_DSPP, 71, 3},
+	{ DBGBUS_DSPP, 71, 4},
+	{ DBGBUS_DSPP, 71, 5},
+	{ DBGBUS_DSPP, 71, 6},
+	{ DBGBUS_DSPP, 71, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 72, 1},
+	{ DBGBUS_DSPP, 72, 2},
+	{ DBGBUS_DSPP, 72, 3},
+	{ DBGBUS_DSPP, 72, 4},
+	{ DBGBUS_DSPP, 72, 5},
+	{ DBGBUS_DSPP, 72, 6},
+	{ DBGBUS_DSPP, 72, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 73, 1},
+	{ DBGBUS_DSPP, 73, 2},
+	{ DBGBUS_DSPP, 73, 3},
+	{ DBGBUS_DSPP, 73, 4},
+	{ DBGBUS_DSPP, 73, 5},
+	{ DBGBUS_DSPP, 73, 6},
+	{ DBGBUS_DSPP, 73, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 74, 1},
+	{ DBGBUS_DSPP, 74, 2},
+	{ DBGBUS_DSPP, 74, 3},
+	{ DBGBUS_DSPP, 74, 4},
+	{ DBGBUS_DSPP, 74, 5},
+	{ DBGBUS_DSPP, 74, 6},
+	{ DBGBUS_DSPP, 74, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 75, 1},
+	{ DBGBUS_DSPP, 75, 2},
+	{ DBGBUS_DSPP, 75, 3},
+	{ DBGBUS_DSPP, 75, 4},
+	{ DBGBUS_DSPP, 75, 5},
+	{ DBGBUS_DSPP, 75, 6},
+	{ DBGBUS_DSPP, 75, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 76, 1},
+	{ DBGBUS_DSPP, 76, 2},
+	{ DBGBUS_DSPP, 76, 3},
+	{ DBGBUS_DSPP, 76, 4},
+	{ DBGBUS_DSPP, 76, 5},
+	{ DBGBUS_DSPP, 76, 6},
+	{ DBGBUS_DSPP, 76, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 88, 1},
+	{ DBGBUS_DSPP, 88, 2},
+	{ DBGBUS_DSPP, 88, 3},
+	{ DBGBUS_DSPP, 88, 4},
+	{ DBGBUS_DSPP, 88, 5},
+	{ DBGBUS_DSPP, 88, 6},
+	{ DBGBUS_DSPP, 88, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 89, 1},
+	{ DBGBUS_DSPP, 89, 2},
+	{ DBGBUS_DSPP, 89, 3},
+	{ DBGBUS_DSPP, 89, 4},
+	{ DBGBUS_DSPP, 89, 5},
+	{ DBGBUS_DSPP, 89, 6},
+	{ DBGBUS_DSPP, 89, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 90, 1},
+	{ DBGBUS_DSPP, 90, 2},
+	{ DBGBUS_DSPP, 90, 3},
+	{ DBGBUS_DSPP, 90, 4},
+	{ DBGBUS_DSPP, 90, 5},
+	{ DBGBUS_DSPP, 90, 6},
+	{ DBGBUS_DSPP, 90, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 91, 1},
+	{ DBGBUS_DSPP, 91, 2},
+	{ DBGBUS_DSPP, 91, 3},
+	{ DBGBUS_DSPP, 91, 4},
+	{ DBGBUS_DSPP, 91, 5},
+	{ DBGBUS_DSPP, 91, 6},
+	{ DBGBUS_DSPP, 91, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM2 */
+	{ DBGBUS_DSPP, 77, 0},
+	{ DBGBUS_DSPP, 77, 1},
+	{ DBGBUS_DSPP, 77, 2},
+	{ DBGBUS_DSPP, 77, 3},
+	{ DBGBUS_DSPP, 77, 4},
+	{ DBGBUS_DSPP, 77, 5},
+	{ DBGBUS_DSPP, 77, 6},
+	{ DBGBUS_DSPP, 77, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 78, 0},
+	{ DBGBUS_DSPP, 78, 1},
+	{ DBGBUS_DSPP, 78, 2},
+	{ DBGBUS_DSPP, 78, 3},
+	{ DBGBUS_DSPP, 78, 4},
+	{ DBGBUS_DSPP, 78, 5},
+	{ DBGBUS_DSPP, 78, 6},
+	{ DBGBUS_DSPP, 78, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 79, 0},
+	{ DBGBUS_DSPP, 79, 1},
+	{ DBGBUS_DSPP, 79, 2},
+	{ DBGBUS_DSPP, 79, 3},
+	{ DBGBUS_DSPP, 79, 4},
+	{ DBGBUS_DSPP, 79, 5},
+	{ DBGBUS_DSPP, 79, 6},
+	{ DBGBUS_DSPP, 79, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 80, 0},
+	{ DBGBUS_DSPP, 80, 1},
+	{ DBGBUS_DSPP, 80, 2},
+	{ DBGBUS_DSPP, 80, 3},
+	{ DBGBUS_DSPP, 80, 4},
+	{ DBGBUS_DSPP, 80, 5},
+	{ DBGBUS_DSPP, 80, 6},
+	{ DBGBUS_DSPP, 80, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 81, 0},
+	{ DBGBUS_DSPP, 81, 1},
+	{ DBGBUS_DSPP, 81, 2},
+	{ DBGBUS_DSPP, 81, 3},
+	{ DBGBUS_DSPP, 81, 4},
+	{ DBGBUS_DSPP, 81, 5},
+	{ DBGBUS_DSPP, 81, 6},
+	{ DBGBUS_DSPP, 81, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 82, 0},
+	{ DBGBUS_DSPP, 82, 1},
+	{ DBGBUS_DSPP, 82, 2},
+	{ DBGBUS_DSPP, 82, 3},
+	{ DBGBUS_DSPP, 82, 4},
+	{ DBGBUS_DSPP, 82, 5},
+	{ DBGBUS_DSPP, 82, 6},
+	{ DBGBUS_DSPP, 82, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 83, 0},
+	{ DBGBUS_DSPP, 83, 1},
+	{ DBGBUS_DSPP, 83, 2},
+	{ DBGBUS_DSPP, 83, 3},
+	{ DBGBUS_DSPP, 83, 4},
+	{ DBGBUS_DSPP, 83, 5},
+	{ DBGBUS_DSPP, 83, 6},
+	{ DBGBUS_DSPP, 83, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 92, 1},
+	{ DBGBUS_DSPP, 92, 2},
+	{ DBGBUS_DSPP, 92, 3},
+	{ DBGBUS_DSPP, 92, 4},
+	{ DBGBUS_DSPP, 92, 5},
+	{ DBGBUS_DSPP, 92, 6},
+	{ DBGBUS_DSPP, 92, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 93, 1},
+	{ DBGBUS_DSPP, 93, 2},
+	{ DBGBUS_DSPP, 93, 3},
+	{ DBGBUS_DSPP, 93, 4},
+	{ DBGBUS_DSPP, 93, 5},
+	{ DBGBUS_DSPP, 93, 6},
+	{ DBGBUS_DSPP, 93, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 94, 1},
+	{ DBGBUS_DSPP, 94, 2},
+	{ DBGBUS_DSPP, 94, 3},
+	{ DBGBUS_DSPP, 94, 4},
+	{ DBGBUS_DSPP, 94, 5},
+	{ DBGBUS_DSPP, 94, 6},
+	{ DBGBUS_DSPP, 94, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 95, 1},
+	{ DBGBUS_DSPP, 95, 2},
+	{ DBGBUS_DSPP, 95, 3},
+	{ DBGBUS_DSPP, 95, 4},
+	{ DBGBUS_DSPP, 95, 5},
+	{ DBGBUS_DSPP, 95, 6},
+	{ DBGBUS_DSPP, 95, 7, _dpu_debug_bus_lm_dump },
+
+	/* LM5 */
+	{ DBGBUS_DSPP, 110, 1},
+	{ DBGBUS_DSPP, 110, 2},
+	{ DBGBUS_DSPP, 110, 3},
+	{ DBGBUS_DSPP, 110, 4},
+	{ DBGBUS_DSPP, 110, 5},
+	{ DBGBUS_DSPP, 110, 6},
+	{ DBGBUS_DSPP, 110, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 111, 1},
+	{ DBGBUS_DSPP, 111, 2},
+	{ DBGBUS_DSPP, 111, 3},
+	{ DBGBUS_DSPP, 111, 4},
+	{ DBGBUS_DSPP, 111, 5},
+	{ DBGBUS_DSPP, 111, 6},
+	{ DBGBUS_DSPP, 111, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 112, 1},
+	{ DBGBUS_DSPP, 112, 2},
+	{ DBGBUS_DSPP, 112, 3},
+	{ DBGBUS_DSPP, 112, 4},
+	{ DBGBUS_DSPP, 112, 5},
+	{ DBGBUS_DSPP, 112, 6},
+	{ DBGBUS_DSPP, 112, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 113, 1},
+	{ DBGBUS_DSPP, 113, 2},
+	{ DBGBUS_DSPP, 113, 3},
+	{ DBGBUS_DSPP, 113, 4},
+	{ DBGBUS_DSPP, 113, 5},
+	{ DBGBUS_DSPP, 113, 6},
+	{ DBGBUS_DSPP, 113, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 114, 1},
+	{ DBGBUS_DSPP, 114, 2},
+	{ DBGBUS_DSPP, 114, 3},
+	{ DBGBUS_DSPP, 114, 4},
+	{ DBGBUS_DSPP, 114, 5},
+	{ DBGBUS_DSPP, 114, 6},
+	{ DBGBUS_DSPP, 114, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 115, 1},
+	{ DBGBUS_DSPP, 115, 2},
+	{ DBGBUS_DSPP, 115, 3},
+	{ DBGBUS_DSPP, 115, 4},
+	{ DBGBUS_DSPP, 115, 5},
+	{ DBGBUS_DSPP, 115, 6},
+	{ DBGBUS_DSPP, 115, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 116, 1},
+	{ DBGBUS_DSPP, 116, 2},
+	{ DBGBUS_DSPP, 116, 3},
+	{ DBGBUS_DSPP, 116, 4},
+	{ DBGBUS_DSPP, 116, 5},
+	{ DBGBUS_DSPP, 116, 6},
+	{ DBGBUS_DSPP, 116, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 117, 1},
+	{ DBGBUS_DSPP, 117, 2},
+	{ DBGBUS_DSPP, 117, 3},
+	{ DBGBUS_DSPP, 117, 4},
+	{ DBGBUS_DSPP, 117, 5},
+	{ DBGBUS_DSPP, 117, 6},
+	{ DBGBUS_DSPP, 117, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 118, 1},
+	{ DBGBUS_DSPP, 118, 2},
+	{ DBGBUS_DSPP, 118, 3},
+	{ DBGBUS_DSPP, 118, 4},
+	{ DBGBUS_DSPP, 118, 5},
+	{ DBGBUS_DSPP, 118, 6},
+	{ DBGBUS_DSPP, 118, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 119, 1},
+	{ DBGBUS_DSPP, 119, 2},
+	{ DBGBUS_DSPP, 119, 3},
+	{ DBGBUS_DSPP, 119, 4},
+	{ DBGBUS_DSPP, 119, 5},
+	{ DBGBUS_DSPP, 119, 6},
+	{ DBGBUS_DSPP, 119, 7, _dpu_debug_bus_lm_dump },
+
+	{ DBGBUS_DSPP, 120, 1},
+	{ DBGBUS_DSPP, 120, 2},
+	{ DBGBUS_DSPP, 120, 3},
+	{ DBGBUS_DSPP, 120, 4},
+	{ DBGBUS_DSPP, 120, 5},
+	{ DBGBUS_DSPP, 120, 6},
+	{ DBGBUS_DSPP, 120, 7, _dpu_debug_bus_lm_dump },
+
+	/* csc */
+	{ DBGBUS_SSPP0, 7, 0},
+	{ DBGBUS_SSPP0, 7, 1},
+	{ DBGBUS_SSPP0, 27, 0},
+	{ DBGBUS_SSPP0, 27, 1},
+	{ DBGBUS_SSPP1, 7, 0},
+	{ DBGBUS_SSPP1, 7, 1},
+	{ DBGBUS_SSPP1, 27, 0},
+	{ DBGBUS_SSPP1, 27, 1},
+
+	/* pcc */
+	{ DBGBUS_SSPP0, 3,  3},
+	{ DBGBUS_SSPP0, 23, 3},
+	{ DBGBUS_SSPP0, 33, 3},
+	{ DBGBUS_SSPP0, 43, 3},
+	{ DBGBUS_SSPP1, 3,  3},
+	{ DBGBUS_SSPP1, 23, 3},
+	{ DBGBUS_SSPP1, 33, 3},
+	{ DBGBUS_SSPP1, 43, 3},
+
+	/* spa */
+	{ DBGBUS_SSPP0, 8,  0},
+	{ DBGBUS_SSPP0, 28, 0},
+	{ DBGBUS_SSPP1, 8,  0},
+	{ DBGBUS_SSPP1, 28, 0},
+	{ DBGBUS_DSPP, 13, 0},
+	{ DBGBUS_DSPP, 19, 0},
+
+	/* igc */
+	{ DBGBUS_SSPP0, 17, 0},
+	{ DBGBUS_SSPP0, 17, 1},
+	{ DBGBUS_SSPP0, 17, 3},
+	{ DBGBUS_SSPP0, 37, 0},
+	{ DBGBUS_SSPP0, 37, 1},
+	{ DBGBUS_SSPP0, 37, 3},
+	{ DBGBUS_SSPP0, 46, 0},
+	{ DBGBUS_SSPP0, 46, 1},
+	{ DBGBUS_SSPP0, 46, 3},
+
+	{ DBGBUS_SSPP1, 17, 0},
+	{ DBGBUS_SSPP1, 17, 1},
+	{ DBGBUS_SSPP1, 17, 3},
+	{ DBGBUS_SSPP1, 37, 0},
+	{ DBGBUS_SSPP1, 37, 1},
+	{ DBGBUS_SSPP1, 37, 3},
+	{ DBGBUS_SSPP1, 46, 0},
+	{ DBGBUS_SSPP1, 46, 1},
+	{ DBGBUS_SSPP1, 46, 3},
+
+	{ DBGBUS_DSPP, 14, 0},
+	{ DBGBUS_DSPP, 14, 1},
+	{ DBGBUS_DSPP, 14, 3},
+	{ DBGBUS_DSPP, 20, 0},
+	{ DBGBUS_DSPP, 20, 1},
+	{ DBGBUS_DSPP, 20, 3},
+
+	/* intf0-3 */
+	{ DBGBUS_PERIPH, 0, 0},
+	{ DBGBUS_PERIPH, 1, 0},
+	{ DBGBUS_PERIPH, 2, 0},
+	{ DBGBUS_PERIPH, 3, 0},
+
+	/* te counter wrapper */
+	{ DBGBUS_PERIPH, 60, 0},
+
+	/* dsc0 */
+	{ DBGBUS_PERIPH, 47, 0},
+	{ DBGBUS_PERIPH, 47, 1},
+	{ DBGBUS_PERIPH, 47, 2},
+	{ DBGBUS_PERIPH, 47, 3},
+	{ DBGBUS_PERIPH, 47, 4},
+	{ DBGBUS_PERIPH, 47, 5},
+	{ DBGBUS_PERIPH, 47, 6},
+	{ DBGBUS_PERIPH, 47, 7},
+
+	/* dsc1 */
+	{ DBGBUS_PERIPH, 48, 0},
+	{ DBGBUS_PERIPH, 48, 1},
+	{ DBGBUS_PERIPH, 48, 2},
+	{ DBGBUS_PERIPH, 48, 3},
+	{ DBGBUS_PERIPH, 48, 4},
+	{ DBGBUS_PERIPH, 48, 5},
+	{ DBGBUS_PERIPH, 48, 6},
+	{ DBGBUS_PERIPH, 48, 7},
+
+	/* dsc2 */
+	{ DBGBUS_PERIPH, 51, 0},
+	{ DBGBUS_PERIPH, 51, 1},
+	{ DBGBUS_PERIPH, 51, 2},
+	{ DBGBUS_PERIPH, 51, 3},
+	{ DBGBUS_PERIPH, 51, 4},
+	{ DBGBUS_PERIPH, 51, 5},
+	{ DBGBUS_PERIPH, 51, 6},
+	{ DBGBUS_PERIPH, 51, 7},
+
+	/* dsc3 */
+	{ DBGBUS_PERIPH, 52, 0},
+	{ DBGBUS_PERIPH, 52, 1},
+	{ DBGBUS_PERIPH, 52, 2},
+	{ DBGBUS_PERIPH, 52, 3},
+	{ DBGBUS_PERIPH, 52, 4},
+	{ DBGBUS_PERIPH, 52, 5},
+	{ DBGBUS_PERIPH, 52, 6},
+	{ DBGBUS_PERIPH, 52, 7},
+
+	/* tear-check */
+	{ DBGBUS_PERIPH, 63, 0 },
+	{ DBGBUS_PERIPH, 64, 0 },
+	{ DBGBUS_PERIPH, 65, 0 },
+	{ DBGBUS_PERIPH, 73, 0 },
+	{ DBGBUS_PERIPH, 74, 0 },
+
+	/* cdwn */
+	{ DBGBUS_PERIPH, 80, 0},
+	{ DBGBUS_PERIPH, 80, 1},
+	{ DBGBUS_PERIPH, 80, 2},
+
+	{ DBGBUS_PERIPH, 81, 0},
+	{ DBGBUS_PERIPH, 81, 1},
+	{ DBGBUS_PERIPH, 81, 2},
+
+	{ DBGBUS_PERIPH, 82, 0},
+	{ DBGBUS_PERIPH, 82, 1},
+	{ DBGBUS_PERIPH, 82, 2},
+	{ DBGBUS_PERIPH, 82, 3},
+	{ DBGBUS_PERIPH, 82, 4},
+	{ DBGBUS_PERIPH, 82, 5},
+	{ DBGBUS_PERIPH, 82, 6},
+	{ DBGBUS_PERIPH, 82, 7},
+
+	/* hdmi */
+	{ DBGBUS_PERIPH, 68, 0},
+	{ DBGBUS_PERIPH, 68, 1},
+	{ DBGBUS_PERIPH, 68, 2},
+	{ DBGBUS_PERIPH, 68, 3},
+	{ DBGBUS_PERIPH, 68, 4},
+	{ DBGBUS_PERIPH, 68, 5},
+
+	/* edp */
+	{ DBGBUS_PERIPH, 69, 0},
+	{ DBGBUS_PERIPH, 69, 1},
+	{ DBGBUS_PERIPH, 69, 2},
+	{ DBGBUS_PERIPH, 69, 3},
+	{ DBGBUS_PERIPH, 69, 4},
+	{ DBGBUS_PERIPH, 69, 5},
+
+	/* dsi0 */
+	{ DBGBUS_PERIPH, 70, 0},
+	{ DBGBUS_PERIPH, 70, 1},
+	{ DBGBUS_PERIPH, 70, 2},
+	{ DBGBUS_PERIPH, 70, 3},
+	{ DBGBUS_PERIPH, 70, 4},
+	{ DBGBUS_PERIPH, 70, 5},
+
+	/* dsi1 */
+	{ DBGBUS_PERIPH, 71, 0},
+	{ DBGBUS_PERIPH, 71, 1},
+	{ DBGBUS_PERIPH, 71, 2},
+	{ DBGBUS_PERIPH, 71, 3},
+	{ DBGBUS_PERIPH, 71, 4},
+	{ DBGBUS_PERIPH, 71, 5},
+};
+
+static struct vbif_debug_bus_entry vbif_dbg_bus_msm8998[] = {
+	{0x214, 0x21c, 16, 2, 0x0, 0xd},     /* arb clients */
+	{0x214, 0x21c, 16, 2, 0x80, 0xc0},   /* arb clients */
+	{0x214, 0x21c, 16, 2, 0x100, 0x140}, /* arb clients */
+	{0x214, 0x21c, 0, 16, 0x0, 0xf},     /* xin blocks - axi side */
+	{0x214, 0x21c, 0, 16, 0x80, 0xa4},   /* xin blocks - axi side */
+	{0x214, 0x21c, 0, 15, 0x100, 0x124}, /* xin blocks - axi side */
+	{0x21c, 0x214, 0, 14, 0, 0xc}, /* xin blocks - clock side */
+};
+
+/**
+ * _dpu_dbg_enable_power - use callback to turn power on for hw register access
+ * @enable: whether to turn power on or off
+ */
+static inline void _dpu_dbg_enable_power(int enable)
+{
+	if (enable)
+		pm_runtime_get_sync(dpu_dbg_base.dev);
+	else
+		pm_runtime_put_sync(dpu_dbg_base.dev);
+}
+
+static void _dpu_dbg_dump_dpu_dbg_bus(struct dpu_dbg_dpu_debug_bus *bus)
+{
+	bool in_log, in_mem;
+	u32 **dump_mem = NULL;
+	u32 *dump_addr = NULL;
+	u32 status = 0;
+	struct dpu_debug_bus_entry *head;
+	phys_addr_t phys = 0;
+	int list_size;
+	int i;
+	u32 offset;
+	void __iomem *mem_base = NULL;
+	struct dpu_dbg_reg_base *reg_base;
+
+	if (!bus || !bus->cmn.entries_size)
+		return;
+
+	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
+			reg_base_head)
+		if (strlen(reg_base->name) &&
+			!strcmp(reg_base->name, bus->cmn.name))
+			mem_base = reg_base->base + bus->top_blk_off;
+
+	if (!mem_base) {
+		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
+		return;
+	}
+
+	dump_mem = &bus->cmn.dumped_content;
+
+	/* will keep in memory 4 entries of 4 bytes each */
+	list_size = (bus->cmn.entries_size * 4 * 4);
+
+	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
+	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
+
+	if (!in_log && !in_mem)
+		return;
+
+	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
+			bus->cmn.name);
+
+	if (in_mem) {
+		if (!(*dump_mem))
+			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
+				list_size, &phys, GFP_KERNEL);
+
+		if (*dump_mem) {
+			dump_addr = *dump_mem;
+			dev_info(dpu_dbg_base.dev,
+				"%s: start_addr:0x%pK len:0x%x\n",
+				__func__, dump_addr, list_size);
+		} else {
+			in_mem = false;
+			pr_err("dump_mem: allocation fails\n");
+		}
+	}
+
+	_dpu_dbg_enable_power(true);
+	for (i = 0; i < bus->cmn.entries_size; i++) {
+		head = bus->entries + i;
+		writel_relaxed(TEST_MASK(head->block_id, head->test_id),
+				mem_base + head->wr_addr);
+		wmb(); /* make sure test bits were written */
+
+		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP) {
+			offset = DBGBUS_DSPP_STATUS;
+			/* keep DSPP test point enabled */
+			if (head->wr_addr != DBGBUS_DSPP)
+				writel_relaxed(0xF, mem_base + DBGBUS_DSPP);
+		} else {
+			offset = head->wr_addr + 0x4;
+		}
+
+		status = readl_relaxed(mem_base + offset);
+
+		if (in_log)
+			dev_info(dpu_dbg_base.dev,
+					"waddr=0x%x blk=%d tst=%d val=0x%x\n",
+					head->wr_addr, head->block_id,
+					head->test_id, status);
+
+		if (dump_addr && in_mem) {
+			dump_addr[i*4]     = head->wr_addr;
+			dump_addr[i*4 + 1] = head->block_id;
+			dump_addr[i*4 + 2] = head->test_id;
+			dump_addr[i*4 + 3] = status;
+		}
+
+		if (head->analyzer)
+			head->analyzer(mem_base, head, status);
+
+		/* Disable debug bus once we are done */
+		writel_relaxed(0, mem_base + head->wr_addr);
+		if (bus->cmn.flags & DBGBUS_FLAGS_DSPP &&
+						head->wr_addr != DBGBUS_DSPP)
+			writel_relaxed(0x0, mem_base + DBGBUS_DSPP);
+	}
+	_dpu_dbg_enable_power(false);
+
+	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
+			bus->cmn.name);
+}
+
+static void _dpu_dbg_dump_vbif_debug_bus_entry(
+		struct vbif_debug_bus_entry *head, void __iomem *mem_base,
+		u32 *dump_addr, bool in_log)
+{
+	int i, j;
+	u32 val;
+
+	if (!dump_addr && !in_log)
+		return;
+
+	for (i = 0; i < head->block_cnt; i++) {
+		writel_relaxed(1 << (i + head->bit_offset),
+				mem_base + head->block_bus_addr);
+		/* make sure that current bus blcok enable */
+		wmb();
+		for (j = head->test_pnt_start; j < head->test_pnt_cnt; j++) {
+			writel_relaxed(j, mem_base + head->block_bus_addr + 4);
+			/* make sure that test point is enabled */
+			wmb();
+			val = readl_relaxed(mem_base + MMSS_VBIF_TEST_BUS_OUT);
+			if (dump_addr) {
+				*dump_addr++ = head->block_bus_addr;
+				*dump_addr++ = i;
+				*dump_addr++ = j;
+				*dump_addr++ = val;
+			}
+			if (in_log)
+				dev_info(dpu_dbg_base.dev,
+					"testpoint:%x arb/xin id=%d index=%d val=0x%x\n",
+					head->block_bus_addr, i, j, val);
+		}
+	}
+}
+
+static void _dpu_dbg_dump_vbif_dbg_bus(struct dpu_dbg_vbif_debug_bus *bus)
+{
+	bool in_log, in_mem;
+	u32 **dump_mem = NULL;
+	u32 *dump_addr = NULL;
+	u32 value, d0, d1;
+	unsigned long reg, reg1, reg2;
+	struct vbif_debug_bus_entry *head;
+	phys_addr_t phys = 0;
+	int i, list_size = 0;
+	void __iomem *mem_base = NULL;
+	struct vbif_debug_bus_entry *dbg_bus;
+	u32 bus_size;
+	struct dpu_dbg_reg_base *reg_base;
+
+	if (!bus || !bus->cmn.entries_size)
+		return;
+
+	list_for_each_entry(reg_base, &dpu_dbg_base.reg_base_list,
+			reg_base_head)
+		if (strlen(reg_base->name) &&
+			!strcmp(reg_base->name, bus->cmn.name))
+			mem_base = reg_base->base;
+
+	if (!mem_base) {
+		pr_err("unable to find mem_base for %s\n", bus->cmn.name);
+		return;
+	}
+
+	dbg_bus = bus->entries;
+	bus_size = bus->cmn.entries_size;
+	list_size = bus->cmn.entries_size;
+	dump_mem = &bus->cmn.dumped_content;
+
+	dev_info(dpu_dbg_base.dev, "======== start %s dump =========\n",
+			bus->cmn.name);
+
+	if (!dump_mem || !dbg_bus || !bus_size || !list_size)
+		return;
+
+	/* allocate memory for each test point */
+	for (i = 0; i < bus_size; i++) {
+		head = dbg_bus + i;
+		list_size += (head->block_cnt * head->test_pnt_cnt);
+	}
+
+	/* 4 bytes * 4 entries for each test point*/
+	list_size *= 16;
+
+	in_log = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_LOG);
+	in_mem = (bus->cmn.enable_mask & DPU_DBG_DUMP_IN_MEM);
+
+	if (!in_log && !in_mem)
+		return;
+
+	if (in_mem) {
+		if (!(*dump_mem))
+			*dump_mem = dma_alloc_coherent(dpu_dbg_base.dev,
+				list_size, &phys, GFP_KERNEL);
+
+		if (*dump_mem) {
+			dump_addr = *dump_mem;
+			dev_info(dpu_dbg_base.dev,
+				"%s: start_addr:0x%pK len:0x%x\n",
+				__func__, dump_addr, list_size);
+		} else {
+			in_mem = false;
+			pr_err("dump_mem: allocation fails\n");
+		}
+	}
+
+	_dpu_dbg_enable_power(true);
+
+	value = readl_relaxed(mem_base + MMSS_VBIF_CLKON);
+	writel_relaxed(value | BIT(1), mem_base + MMSS_VBIF_CLKON);
+
+	/* make sure that vbif core is on */
+	wmb();
+
+	/**
+	 * Extract VBIF error info based on XIN halt and error status.
+	 * If the XIN client is not in HALT state, or an error is detected,
+	 * then retrieve the VBIF error info for it.
+	 */
+	reg = readl_relaxed(mem_base + MMSS_VBIF_XIN_HALT_CTRL1);
+	reg1 = readl_relaxed(mem_base + MMSS_VBIF_PND_ERR);
+	reg2 = readl_relaxed(mem_base + MMSS_VBIF_SRC_ERR);
+	dev_err(dpu_dbg_base.dev,
+			"XIN HALT:0x%lX, PND ERR:0x%lX, SRC ERR:0x%lX\n",
+			reg, reg1, reg2);
+	reg >>= 16;
+	reg &= ~(reg1 | reg2);
+	for (i = 0; i < MMSS_VBIF_CLIENT_NUM; i++) {
+		if (!test_bit(0, &reg)) {
+			writel_relaxed(i, mem_base + MMSS_VBIF_ERR_INFO);
+			/* make sure reg write goes through */
+			wmb();
+
+			d0 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO);
+			d1 = readl_relaxed(mem_base + MMSS_VBIF_ERR_INFO_1);
+
+			dev_err(dpu_dbg_base.dev,
+					"Client:%d, errinfo=0x%X, errinfo1=0x%X\n",
+					i, d0, d1);
+		}
+		reg >>= 1;
+	}
+
+	for (i = 0; i < bus_size; i++) {
+		head = dbg_bus + i;
+
+		writel_relaxed(0, mem_base + head->disable_bus_addr);
+		writel_relaxed(BIT(0), mem_base + MMSS_VBIF_TEST_BUS_OUT_CTRL);
+		/* make sure that other bus is off */
+		wmb();
+
+		_dpu_dbg_dump_vbif_debug_bus_entry(head, mem_base, dump_addr,
+				in_log);
+		if (dump_addr)
+			dump_addr += (head->block_cnt * head->test_pnt_cnt * 4);
+	}
+
+	_dpu_dbg_enable_power(false);
+
+	dev_info(dpu_dbg_base.dev, "======== end %s dump =========\n",
+			bus->cmn.name);
+}
+
+/**
+ * _dpu_dump_array - dump array of register bases
+ * @name: string indicating origin of dump
+ * @dump_dbgbus_dpu: whether to dump the dpu debug bus
+ * @dump_dbgbus_vbif_rt: whether to dump the vbif rt debug bus
+ */
+static void _dpu_dump_array(const char *name, bool dump_dbgbus_dpu,
+			    bool dump_dbgbus_vbif_rt)
+{
+	if (dump_dbgbus_dpu)
+		_dpu_dbg_dump_dpu_dbg_bus(&dpu_dbg_base.dbgbus_dpu);
+
+	if (dump_dbgbus_vbif_rt)
+		_dpu_dbg_dump_vbif_dbg_bus(&dpu_dbg_base.dbgbus_vbif_rt);
+}
+
+/**
+ * _dpu_dump_work - deferred dump work function
+ * @work: work structure
+ */
+static void _dpu_dump_work(struct work_struct *work)
+{
+	_dpu_dump_array("dpudump_workitem",
+		dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work,
+		dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work);
+}
+
+void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
+		  bool dump_dbgbus_vbif_rt)
+{
+	if (queue_work && work_pending(&dpu_dbg_base.dump_work))
+		return;
+
+	if (!queue_work) {
+		_dpu_dump_array(name, dump_dbgbus_dpu, dump_dbgbus_vbif_rt);
+		return;
+	}
+
+	/* schedule work to dump later */
+	dpu_dbg_base.dbgbus_dpu.cmn.include_in_deferred_work = dump_dbgbus_dpu;
+	dpu_dbg_base.dbgbus_vbif_rt.cmn.include_in_deferred_work =
+			dump_dbgbus_vbif_rt;
+	schedule_work(&dpu_dbg_base.dump_work);
+}
+
+/*
+ * dpu_dbg_debugfs_open - debugfs open handler for debug dump
+ * @inode: debugfs inode
+ * @file: file handle
+ */
+static int dpu_dbg_debugfs_open(struct inode *inode, struct file *file)
+{
+	/* non-seekable */
+	file->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+	file->private_data = inode->i_private;
+	return 0;
+}
+
+/**
+ * dpu_dbg_dump_write - debugfs write handler for debug dump
+ * @file: file handler
+ * @user_buf: user buffer content from debugfs
+ * @count: size of user buffer
+ * @ppos: position offset of user buffer
+ */
+static ssize_t dpu_dbg_dump_write(struct file *file,
+	const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	_dpu_dump_array("dump_debugfs", true, true);
+	return count;
+}
+
+static const struct file_operations dpu_dbg_dump_fops = {
+	.open = dpu_dbg_debugfs_open,
+	.write = dpu_dbg_dump_write,
+};
+
+int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
+{
+	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
+	char debug_name[80] = "";
+
+	if (!debugfs_root)
+		return -EINVAL;
+
+	debugfs_create_file("dump", 0600, debugfs_root, NULL,
+			&dpu_dbg_dump_fops);
+
+	if (dbg->dbgbus_dpu.entries) {
+		dbg->dbgbus_dpu.cmn.name = DBGBUS_NAME_DPU;
+		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
+				dbg->dbgbus_dpu.cmn.name);
+		dbg->dbgbus_dpu.cmn.enable_mask = DEFAULT_DBGBUS_DPU;
+		debugfs_create_u32(debug_name, 0600, debugfs_root,
+				&dbg->dbgbus_dpu.cmn.enable_mask);
+	}
+
+	if (dbg->dbgbus_vbif_rt.entries) {
+		dbg->dbgbus_vbif_rt.cmn.name = DBGBUS_NAME_VBIF_RT;
+		snprintf(debug_name, sizeof(debug_name), "%s_dbgbus",
+				dbg->dbgbus_vbif_rt.cmn.name);
+		dbg->dbgbus_vbif_rt.cmn.enable_mask = DEFAULT_DBGBUS_VBIFRT;
+		debugfs_create_u32(debug_name, 0600, debugfs_root,
+				&dbg->dbgbus_vbif_rt.cmn.enable_mask);
+	}
+
+	return 0;
+}
+
+static void _dpu_dbg_debugfs_destroy(void)
+{
+}
+
+void dpu_dbg_init_dbg_buses(u32 hwversion)
+{
+	static struct dpu_dbg_base *dbg = &dpu_dbg_base;
+
+	memset(&dbg->dbgbus_dpu, 0, sizeof(dbg->dbgbus_dpu));
+	memset(&dbg->dbgbus_vbif_rt, 0, sizeof(dbg->dbgbus_vbif_rt));
+
+	if (IS_MSM8998_TARGET(hwversion)) {
+		dbg->dbgbus_dpu.entries = dbg_bus_dpu_8998;
+		dbg->dbgbus_dpu.cmn.entries_size = ARRAY_SIZE(dbg_bus_dpu_8998);
+		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
+
+		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
+		dbg->dbgbus_vbif_rt.cmn.entries_size =
+				ARRAY_SIZE(vbif_dbg_bus_msm8998);
+	} else if (IS_SDM845_TARGET(hwversion) || IS_SDM670_TARGET(hwversion)) {
+		dbg->dbgbus_dpu.entries = dbg_bus_dpu_sdm845;
+		dbg->dbgbus_dpu.cmn.entries_size =
+				ARRAY_SIZE(dbg_bus_dpu_sdm845);
+		dbg->dbgbus_dpu.cmn.flags = DBGBUS_FLAGS_DSPP;
+
+		/* vbif is unchanged vs 8998 */
+		dbg->dbgbus_vbif_rt.entries = vbif_dbg_bus_msm8998;
+		dbg->dbgbus_vbif_rt.cmn.entries_size =
+				ARRAY_SIZE(vbif_dbg_bus_msm8998);
+	} else {
+		pr_err("unsupported chipset id %X\n", hwversion);
+	}
+}
+
+int dpu_dbg_init(struct device *dev)
+{
+	if (!dev) {
+		pr_err("invalid params\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&dpu_dbg_base.reg_base_list);
+	dpu_dbg_base.dev = dev;
+
+	INIT_WORK(&dpu_dbg_base.dump_work, _dpu_dump_work);
+
+	return 0;
+}
+
+/**
+ * dpu_dbg_destroy - destroy dpu debug facilities
+ */
+void dpu_dbg_destroy(void)
+{
+	_dpu_dbg_debugfs_destroy();
+}
+
+void dpu_dbg_set_dpu_top_offset(u32 blk_off)
+{
+	dpu_dbg_base.dbgbus_dpu.top_blk_off = blk_off;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
new file mode 100644
index 000000000000..1e6fa945f98b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_dbg.h
@@ -0,0 +1,103 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef DPU_DBG_H_
+#define DPU_DBG_H_
+
+#include <stdarg.h>
+#include <linux/debugfs.h>
+#include <linux/list.h>
+
+enum dpu_dbg_dump_flag {
+	DPU_DBG_DUMP_IN_LOG = BIT(0),
+	DPU_DBG_DUMP_IN_MEM = BIT(1),
+};
+
+#if defined(CONFIG_DEBUG_FS)
+
+/**
+ * dpu_dbg_init_dbg_buses - initialize debug bus dumping support for the chipset
+ * @hwversion:		Chipset revision
+ */
+void dpu_dbg_init_dbg_buses(u32 hwversion);
+
+/**
+ * dpu_dbg_init - initialize global dpu debug facilities: regdump
+ * @dev:		device handle
+ * Returns:		0 or -ERROR
+ */
+int dpu_dbg_init(struct device *dev);
+
+/**
+ * dpu_dbg_debugfs_register - register entries at the given debugfs dir
+ * @debugfs_root:	debugfs root in which to create dpu debug entries
+ * Returns:	0 or -ERROR
+ */
+int dpu_dbg_debugfs_register(struct dentry *debugfs_root);
+
+/**
+ * dpu_dbg_destroy - destroy the global dpu debug facilities
+ * Returns:	none
+ */
+void dpu_dbg_destroy(void);
+
+/**
+ * dpu_dbg_dump - trigger dumping of all dpu_dbg facilities
+ * @queue_work:	  whether to queue the dumping work to the work_struct
+ * @name:	  string indicating origin of dump
+ * @dump_dbgbus:  dump the dpu debug bus
+ * @dump_vbif_rt: dump the vbif rt bus
+ * Returns:	none
+ */
+void dpu_dbg_dump(bool queue_work, const char *name, bool dump_dbgbus_dpu,
+		  bool dump_dbgbus_vbif_rt);
+
+/**
+ * dpu_dbg_set_dpu_top_offset - set the target specific offset from mdss base
+ *	address of the top registers. Used for accessing debug bus controls.
+ * @blk_off: offset from mdss base of the top block
+ */
+void dpu_dbg_set_dpu_top_offset(u32 blk_off);
+
+#else
+
+static inline void dpu_dbg_init_dbg_buses(u32 hwversion)
+{
+}
+
+static inline int dpu_dbg_init(struct device *dev)
+{
+	return 0;
+}
+
+static inline int dpu_dbg_debugfs_register(struct dentry *debugfs_root)
+{
+	return 0;
+}
+
+static inline void dpu_dbg_destroy(void)
+{
+}
+
+static inline void dpu_dbg_dump(bool queue_work, const char *name,
+				bool dump_dbgbus_dpu, bool dump_dbgbus_vbif_rt)
+{
+}
+
+static inline void dpu_dbg_set_dpu_top_offset(u32 blk_off)
+{
+}
+
+#endif /* defined(CONFIG_DEBUG_FS) */
+
+
+#endif /* DPU_DBG_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
new file mode 100644
index 000000000000..27775feed32b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -0,0 +1,2575 @@
+/*
+ * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/kthread.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include <drm/drm_crtc.h>
+#include <drm/drm_crtc_helper.h>
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_formats.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_crtc.h"
+#include "dpu_trace.h"
+#include "dpu_core_irq.h"
+
+#define DPU_DEBUG_ENC(e, fmt, ...) DPU_DEBUG("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_ENC(e, fmt, ...) DPU_ERROR("enc%d " fmt,\
+		(e) ? (e)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_DEBUG_PHYS(p, fmt, ...) DPU_DEBUG("enc%d intf%d pp%d " fmt,\
+		(p) ? (p)->parent->base.id : -1, \
+		(p) ? (p)->intf_idx - INTF_0 : -1, \
+		(p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \
+		##__VA_ARGS__)
+
+#define DPU_ERROR_PHYS(p, fmt, ...) DPU_ERROR("enc%d intf%d pp%d " fmt,\
+		(p) ? (p)->parent->base.id : -1, \
+		(p) ? (p)->intf_idx - INTF_0 : -1, \
+		(p) ? ((p)->hw_pp ? (p)->hw_pp->idx - PINGPONG_0 : -1) : -1, \
+		##__VA_ARGS__)
+
+/*
+ * Two to anticipate panels that can do cmd/vid dynamic switching
+ * plan is to create all possible physical encoder types, and switch between
+ * them at runtime
+ */
+#define NUM_PHYS_ENCODER_TYPES 2
+
+#define MAX_PHYS_ENCODERS_PER_VIRTUAL \
+	(MAX_H_TILES_PER_DISPLAY * NUM_PHYS_ENCODER_TYPES)
+
+#define MAX_CHANNELS_PER_ENC 2
+
+#define MISR_BUFF_SIZE			256
+
+#define IDLE_SHORT_TIMEOUT	1
+
+#define MAX_VDISPLAY_SPLIT 1080
+
+/**
+ * enum dpu_enc_rc_events - events for resource control state machine
+ * @DPU_ENC_RC_EVENT_KICKOFF:
+ *	This event happens at NORMAL priority.
+ *	Event that signals the start of the transfer. When this event is
+ *	received, enable MDP/DSI core clocks. Regardless of the previous
+ *	state, the resource should be in ON state at the end of this event.
+ * @DPU_ENC_RC_EVENT_FRAME_DONE:
+ *	This event happens at INTERRUPT level.
+ *	Event signals the end of the data transfer after the PP FRAME_DONE
+ *	event. At the end of this event, a delayed work is scheduled to go to
+ *	IDLE_PC state after IDLE_TIMEOUT time.
+ * @DPU_ENC_RC_EVENT_PRE_STOP:
+ *	This event happens at NORMAL priority.
+ *	This event, when received during the ON state, leave the RC STATE
+ *	in the PRE_OFF state. It should be followed by the STOP event as
+ *	part of encoder disable.
+ *	If received during IDLE or OFF states, it will do nothing.
+ * @DPU_ENC_RC_EVENT_STOP:
+ *	This event happens at NORMAL priority.
+ *	When this event is received, disable all the MDP/DSI core clocks, and
+ *	disable IRQs. It should be called from the PRE_OFF or IDLE states.
+ *	IDLE is expected when IDLE_PC has run, and PRE_OFF did nothing.
+ *	PRE_OFF is expected when PRE_STOP was executed during the ON state.
+ *	Resource state should be in OFF at the end of the event.
+ * @DPU_ENC_RC_EVENT_ENTER_IDLE:
+ *	This event happens at NORMAL priority from a work item.
+ *	Event signals that there were no frame updates for IDLE_TIMEOUT time.
+ *	This would disable MDP/DSI core clocks and change the resource state
+ *	to IDLE.
+ */
+enum dpu_enc_rc_events {
+	DPU_ENC_RC_EVENT_KICKOFF = 1,
+	DPU_ENC_RC_EVENT_FRAME_DONE,
+	DPU_ENC_RC_EVENT_PRE_STOP,
+	DPU_ENC_RC_EVENT_STOP,
+	DPU_ENC_RC_EVENT_ENTER_IDLE
+};
+
+/*
+ * enum dpu_enc_rc_states - states that the resource control maintains
+ * @DPU_ENC_RC_STATE_OFF: Resource is in OFF state
+ * @DPU_ENC_RC_STATE_PRE_OFF: Resource is transitioning to OFF state
+ * @DPU_ENC_RC_STATE_ON: Resource is in ON state
+ * @DPU_ENC_RC_STATE_MODESET: Resource is in modeset state
+ * @DPU_ENC_RC_STATE_IDLE: Resource is in IDLE state
+ */
+enum dpu_enc_rc_states {
+	DPU_ENC_RC_STATE_OFF,
+	DPU_ENC_RC_STATE_PRE_OFF,
+	DPU_ENC_RC_STATE_ON,
+	DPU_ENC_RC_STATE_IDLE
+};
+
+/**
+ * struct dpu_encoder_virt - virtual encoder. Container of one or more physical
+ *	encoders. Virtual encoder manages one "logical" display. Physical
+ *	encoders manage one intf block, tied to a specific panel/sub-panel.
+ *	Virtual encoder defers as much as possible to the physical encoders.
+ *	Virtual encoder registers itself with the DRM Framework as the encoder.
+ * @base:		drm_encoder base class for registration with DRM
+ * @enc_spin_lock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @bus_scaling_client:	Client handle to the bus scaling interface
+ * @num_phys_encs:	Actual number of physical encoders contained.
+ * @phys_encs:		Container of physical encoders managed.
+ * @cur_master:		Pointer to the current master in this mode. Optimization
+ *			Only valid after enable. Cleared as disable.
+ * @hw_pp		Handle to the pingpong blocks used for the display. No.
+ *			pingpong blocks can be different than num_phys_encs.
+ * @intfs_swapped	Whether or not the phys_enc interfaces have been swapped
+ *			for partial update right-only cases, such as pingpong
+ *			split where virtual pingpong does not generate IRQs
+ * @crtc_vblank_cb:	Callback into the upper layer / CRTC for
+ *			notification of the VBLANK
+ * @crtc_vblank_cb_data:	Data from upper layer for VBLANK notification
+ * @crtc_kickoff_cb:		Callback into CRTC that will flush & start
+ *				all CTL paths
+ * @crtc_kickoff_cb_data:	Opaque user data given to crtc_kickoff_cb
+ * @debugfs_root:		Debug file system root file node
+ * @enc_lock:			Lock around physical encoder create/destroy and
+				access.
+ * @frame_busy_mask:		Bitmask tracking which phys_enc we are still
+ *				busy processing current command.
+ *				Bit0 = phys_encs[0] etc.
+ * @crtc_frame_event_cb:	callback handler for frame event
+ * @crtc_frame_event_cb_data:	callback handler private data
+ * @frame_done_timeout:		frame done timeout in Hz
+ * @frame_done_timer:		watchdog timer for frame done event
+ * @vsync_event_timer:		vsync timer
+ * @disp_info:			local copy of msm_display_info struct
+ * @misr_enable:		misr enable/disable status
+ * @misr_frame_count:		misr frame count before start capturing the data
+ * @idle_pc_supported:		indicate if idle power collaps is supported
+ * @rc_lock:			resource control mutex lock to protect
+ *				virt encoder over various state changes
+ * @rc_state:			resource controller state
+ * @delayed_off_work:		delayed worker to schedule disabling of
+ *				clks and resources after IDLE_TIMEOUT time.
+ * @vsync_event_work:		worker to handle vsync event for autorefresh
+ * @topology:                   topology of the display
+ * @mode_set_complete:          flag to indicate modeset completion
+ * @idle_timeout:		idle timeout duration in milliseconds
+ */
+struct dpu_encoder_virt {
+	struct drm_encoder base;
+	spinlock_t enc_spinlock;
+	uint32_t bus_scaling_client;
+
+	uint32_t display_num_of_h_tiles;
+
+	unsigned int num_phys_encs;
+	struct dpu_encoder_phys *phys_encs[MAX_PHYS_ENCODERS_PER_VIRTUAL];
+	struct dpu_encoder_phys *cur_master;
+	struct dpu_hw_pingpong *hw_pp[MAX_CHANNELS_PER_ENC];
+
+	bool intfs_swapped;
+
+	void (*crtc_vblank_cb)(void *);
+	void *crtc_vblank_cb_data;
+
+	struct dentry *debugfs_root;
+	struct mutex enc_lock;
+	DECLARE_BITMAP(frame_busy_mask, MAX_PHYS_ENCODERS_PER_VIRTUAL);
+	void (*crtc_frame_event_cb)(void *, u32 event);
+	void *crtc_frame_event_cb_data;
+
+	atomic_t frame_done_timeout;
+	struct timer_list frame_done_timer;
+	struct timer_list vsync_event_timer;
+
+	struct msm_display_info disp_info;
+	bool misr_enable;
+	u32 misr_frame_count;
+
+	bool idle_pc_supported;
+	struct mutex rc_lock;
+	enum dpu_enc_rc_states rc_state;
+	struct kthread_delayed_work delayed_off_work;
+	struct kthread_work vsync_event_work;
+	struct msm_display_topology topology;
+	bool mode_set_complete;
+
+	u32 idle_timeout;
+};
+
+#define to_dpu_encoder_virt(x) container_of(x, struct dpu_encoder_virt, base)
+static inline int _dpu_encoder_power_enable(struct dpu_encoder_virt *dpu_enc,
+								bool enable)
+{
+	struct drm_encoder *drm_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu enc\n");
+		return -EINVAL;
+	}
+
+	drm_enc = &dpu_enc->base;
+	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("drm device invalid\n");
+		return -EINVAL;
+	}
+
+	priv = drm_enc->dev->dev_private;
+	if (!priv->kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	if (enable)
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	else
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	DRM_ERROR("irq timeout id=%u, intf=%d, pp=%d, intr=%d\n",
+		  DRMID(phys_enc->parent), phys_enc->intf_idx - INTF_0,
+		  phys_enc->hw_pp->idx - PINGPONG_0, intr_idx);
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc,
+				DPU_ENCODER_FRAME_EVENT_ERROR);
+}
+
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx,
+		struct dpu_encoder_wait_info *wait_info)
+{
+	struct dpu_encoder_irq *irq;
+	u32 irq_status;
+	int ret;
+
+	if (!phys_enc || !wait_info || intr_idx >= INTR_IDX_MAX) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	/* note: do master / slave checking outside */
+
+	/* return EWOULDBLOCK since we know the wait isn't necessary */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DRM_ERROR("encoder is disabled id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		return -EWOULDBLOCK;
+	}
+
+	if (irq->irq_idx < 0) {
+		DRM_DEBUG_KMS("skip irq wait id=%u, intr=%d, hw=%d, irq=%s",
+			      DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			      irq->name);
+		return 0;
+	}
+
+	DRM_DEBUG_KMS("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, pending_cnt=%d",
+		      DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+		      irq->irq_idx, phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(wait_info->atomic_cnt));
+
+	ret = dpu_encoder_helper_wait_event_timeout(
+			DRMID(phys_enc->parent),
+			irq->hw_idx,
+			wait_info);
+
+	if (ret <= 0) {
+		irq_status = dpu_core_irq_read(phys_enc->dpu_kms,
+				irq->irq_idx, true);
+		if (irq_status) {
+			unsigned long flags;
+
+			DRM_DEBUG_KMS("irq not triggered id=%u, intr=%d, "
+				      "hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+				      DRMID(phys_enc->parent), intr_idx,
+				      irq->hw_idx, irq->irq_idx,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+			local_irq_save(flags);
+			irq->cb.func(phys_enc, irq->irq_idx);
+			local_irq_restore(flags);
+			ret = 0;
+		} else {
+			ret = -ETIMEDOUT;
+			DRM_DEBUG_KMS("irq timeout id=%u, intr=%d, "
+				      "hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+				      DRMID(phys_enc->parent), intr_idx,
+				      irq->hw_idx, irq->irq_idx,
+				      phys_enc->hw_pp->idx - PINGPONG_0,
+				      atomic_read(wait_info->atomic_cnt));
+		}
+	} else {
+		ret = 0;
+		trace_dpu_enc_irq_wait_success(DRMID(phys_enc->parent),
+			intr_idx, irq->hw_idx, irq->irq_idx,
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(wait_info->atomic_cnt));
+	}
+
+	return ret;
+}
+
+int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	struct dpu_encoder_irq *irq;
+	int ret = 0;
+
+	if (!phys_enc || intr_idx >= INTR_IDX_MAX) {
+		DPU_ERROR("invalid params\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	if (irq->irq_idx >= 0) {
+		DPU_DEBUG_PHYS(phys_enc,
+				"skipping already registered irq %s type %d\n",
+				irq->name, irq->intr_type);
+		return 0;
+	}
+
+	irq->irq_idx = dpu_core_irq_idx_lookup(phys_enc->dpu_kms,
+			irq->intr_type, irq->hw_idx);
+	if (irq->irq_idx < 0) {
+		DPU_ERROR_PHYS(phys_enc,
+			"failed to lookup IRQ index for %s type:%d\n",
+			irq->name, irq->intr_type);
+		return -EINVAL;
+	}
+
+	ret = dpu_core_irq_register_callback(phys_enc->dpu_kms, irq->irq_idx,
+			&irq->cb);
+	if (ret) {
+		DPU_ERROR_PHYS(phys_enc,
+			"failed to register IRQ callback for %s\n",
+			irq->name);
+		irq->irq_idx = -EINVAL;
+		return ret;
+	}
+
+	ret = dpu_core_irq_enable(phys_enc->dpu_kms, &irq->irq_idx, 1);
+	if (ret) {
+		DRM_ERROR("enable failed id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		dpu_core_irq_unregister_callback(phys_enc->dpu_kms,
+				irq->irq_idx, &irq->cb);
+		irq->irq_idx = -EINVAL;
+		return ret;
+	}
+
+	trace_dpu_enc_irq_register_success(DRMID(phys_enc->parent), intr_idx,
+				irq->hw_idx, irq->irq_idx);
+
+	return ret;
+}
+
+int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx)
+{
+	struct dpu_encoder_irq *irq;
+	int ret;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+	irq = &phys_enc->irq[intr_idx];
+
+	/* silently skip irqs that weren't registered */
+	if (irq->irq_idx < 0) {
+		DRM_ERROR("duplicate unregister id=%u, intr=%d, hw=%d, irq=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx);
+		return 0;
+	}
+
+	ret = dpu_core_irq_disable(phys_enc->dpu_kms, &irq->irq_idx, 1);
+	if (ret) {
+		DRM_ERROR("diable failed id=%u, intr=%d, hw=%d, irq=%d ret=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx, ret);
+	}
+
+	ret = dpu_core_irq_unregister_callback(phys_enc->dpu_kms, irq->irq_idx,
+			&irq->cb);
+	if (ret) {
+		DRM_ERROR("unreg cb fail id=%u, intr=%d, hw=%d, irq=%d ret=%d",
+			  DRMID(phys_enc->parent), intr_idx, irq->hw_idx,
+			  irq->irq_idx, ret);
+	}
+
+	trace_dpu_enc_irq_unregister_success(DRMID(phys_enc->parent), intr_idx,
+					     irq->hw_idx, irq->irq_idx);
+
+	irq->irq_idx = -EINVAL;
+
+	return 0;
+}
+
+void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	if (!hw_res || !drm_enc || !conn_state) {
+		DPU_ERROR("invalid argument(s), drm_enc %d, res %d, state %d\n",
+				drm_enc != 0, hw_res != 0, conn_state != 0);
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	/* Query resources used by phys encs, expected to be without overlap */
+	memset(hw_res, 0, sizeof(*hw_res));
+	hw_res->display_num_of_h_tiles = dpu_enc->display_num_of_h_tiles;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.get_hw_resources)
+			phys->ops.get_hw_resources(phys, hw_res, conn_state);
+	}
+}
+
+void dpu_encoder_destroy(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	mutex_lock(&dpu_enc->enc_lock);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.destroy) {
+			phys->ops.destroy(phys);
+			--dpu_enc->num_phys_encs;
+			dpu_enc->phys_encs[i] = NULL;
+		}
+	}
+
+	if (dpu_enc->num_phys_encs)
+		DPU_ERROR_ENC(dpu_enc, "expected 0 num_phys_encs not %d\n",
+				dpu_enc->num_phys_encs);
+	dpu_enc->num_phys_encs = 0;
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	drm_encoder_cleanup(drm_enc);
+	mutex_destroy(&dpu_enc->enc_lock);
+
+	kfree(dpu_enc);
+}
+
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct split_pipe_cfg cfg = { 0 };
+	struct dpu_hw_mdp *hw_mdptop;
+	struct msm_display_info *disp_info;
+
+	if (!phys_enc || !phys_enc->hw_mdptop || !phys_enc->parent) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	hw_mdptop = phys_enc->hw_mdptop;
+	disp_info = &dpu_enc->disp_info;
+
+	if (disp_info->intf_type != DRM_MODE_CONNECTOR_DSI)
+		return;
+
+	/**
+	 * disable split modes since encoder will be operating in as the only
+	 * encoder, either for the entire use case in the case of, for example,
+	 * single DSI, or for this frame in the case of left/right only partial
+	 * update.
+	 */
+	if (phys_enc->split_role == ENC_ROLE_SOLO) {
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+		return;
+	}
+
+	cfg.en = true;
+	cfg.mode = phys_enc->intf_mode;
+	cfg.intf = interface;
+
+	if (cfg.en && phys_enc->ops.needs_single_flush &&
+			phys_enc->ops.needs_single_flush(phys_enc))
+		cfg.split_flush_en = true;
+
+	if (phys_enc->split_role == ENC_ROLE_MASTER) {
+		DPU_DEBUG_ENC(dpu_enc, "enable %d\n", cfg.en);
+
+		if (hw_mdptop->ops.setup_split_pipe)
+			hw_mdptop->ops.setup_split_pipe(hw_mdptop, &cfg);
+	}
+}
+
+static void _dpu_encoder_adjust_mode(struct drm_connector *connector,
+		struct drm_display_mode *adj_mode)
+{
+	struct drm_display_mode *cur_mode;
+
+	if (!connector || !adj_mode)
+		return;
+
+	list_for_each_entry(cur_mode, &connector->modes, head) {
+		if (cur_mode->vdisplay == adj_mode->vdisplay &&
+			cur_mode->hdisplay == adj_mode->hdisplay &&
+			cur_mode->vrefresh == adj_mode->vrefresh) {
+			adj_mode->private = cur_mode->private;
+			adj_mode->private_flags |= cur_mode->private_flags;
+		}
+	}
+}
+
+static struct msm_display_topology dpu_encoder_get_topology(
+			struct dpu_encoder_virt *dpu_enc,
+			struct dpu_kms *dpu_kms,
+			struct drm_display_mode *mode)
+{
+	struct msm_display_topology topology;
+	int i, intf_count = 0;
+
+	for (i = 0; i < MAX_PHYS_ENCODERS_PER_VIRTUAL; i++)
+		if (dpu_enc->phys_encs[i])
+			intf_count++;
+
+	/* User split topology for width > 1080 */
+	topology.num_lm = (mode->vdisplay > MAX_VDISPLAY_SPLIT) ? 2 : 1;
+	topology.num_enc = 0;
+	topology.num_intf = intf_count;
+
+	return topology;
+}
+static int dpu_encoder_virt_atomic_check(
+		struct drm_encoder *drm_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	const struct drm_display_mode *mode;
+	struct drm_display_mode *adj_mode;
+	struct msm_display_topology topology;
+	int i = 0;
+	int ret = 0;
+
+	if (!drm_enc || !crtc_state || !conn_state) {
+		DPU_ERROR("invalid arg(s), drm_enc %d, crtc/conn state %d/%d\n",
+				drm_enc != 0, crtc_state != 0, conn_state != 0);
+		return -EINVAL;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	mode = &crtc_state->mode;
+	adj_mode = &crtc_state->adjusted_mode;
+	trace_dpu_enc_atomic_check(DRMID(drm_enc));
+
+	/*
+	 * display drivers may populate private fields of the drm display mode
+	 * structure while registering possible modes of a connector with DRM.
+	 * These private fields are not populated back while DRM invokes
+	 * the mode_set callbacks. This module retrieves and populates the
+	 * private fields of the given mode.
+	 */
+	_dpu_encoder_adjust_mode(conn_state->connector, adj_mode);
+
+	/* perform atomic check on the first physical encoder (master) */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.atomic_check)
+			ret = phys->ops.atomic_check(phys, crtc_state,
+					conn_state);
+		else if (phys && phys->ops.mode_fixup)
+			if (!phys->ops.mode_fixup(phys, mode, adj_mode))
+				ret = -EINVAL;
+
+		if (ret) {
+			DPU_ERROR_ENC(dpu_enc,
+					"mode unsupported, phys idx %d\n", i);
+			break;
+		}
+	}
+
+	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
+
+	/* Reserve dynamic resources now. Indicating AtomicTest phase */
+	if (!ret) {
+		/*
+		 * Avoid reserving resources when mode set is pending. Topology
+		 * info may not be available to complete reservation.
+		 */
+		if (drm_atomic_crtc_needs_modeset(crtc_state)
+				&& dpu_enc->mode_set_complete) {
+			ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, crtc_state,
+				conn_state, topology, true);
+			dpu_enc->mode_set_complete = false;
+		}
+	}
+
+	if (!ret)
+		drm_mode_set_crtcinfo(adj_mode, 0);
+
+	trace_dpu_enc_atomic_check_flags(DRMID(drm_enc), adj_mode->flags,
+			adj_mode->private_flags);
+
+	return ret;
+}
+
+static void _dpu_encoder_update_vsync_source(struct dpu_encoder_virt *dpu_enc,
+			struct msm_display_info *disp_info)
+{
+	struct dpu_vsync_source_cfg vsync_cfg = { 0 };
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct drm_encoder *drm_enc;
+	int i;
+
+	if (!dpu_enc || !disp_info) {
+		DPU_ERROR("invalid param dpu_enc:%d or disp_info:%d\n",
+					dpu_enc != NULL, disp_info != NULL);
+		return;
+	} else if (dpu_enc->num_phys_encs > ARRAY_SIZE(dpu_enc->hw_pp)) {
+		DPU_ERROR("invalid num phys enc %d/%d\n",
+				dpu_enc->num_phys_encs,
+				(int) ARRAY_SIZE(dpu_enc->hw_pp));
+		return;
+	}
+
+	drm_enc = &dpu_enc->base;
+	/* this pointers are checked in virt_enable_helper */
+	priv = drm_enc->dev->dev_private;
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	}
+
+	hw_mdptop = dpu_kms->hw_mdp;
+	if (!hw_mdptop) {
+		DPU_ERROR("invalid mdptop\n");
+		return;
+	}
+
+	if (hw_mdptop->ops.setup_vsync_source &&
+			disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) {
+		for (i = 0; i < dpu_enc->num_phys_encs; i++)
+			vsync_cfg.ppnumber[i] = dpu_enc->hw_pp[i]->idx;
+
+		vsync_cfg.pp_count = dpu_enc->num_phys_encs;
+		if (disp_info->is_te_using_watchdog_timer)
+			vsync_cfg.vsync_source = DPU_VSYNC_SOURCE_WD_TIMER_0;
+		else
+			vsync_cfg.vsync_source = DPU_VSYNC0_SOURCE_GPIO;
+
+		hw_mdptop->ops.setup_vsync_source(hw_mdptop, &vsync_cfg);
+	}
+}
+
+static void _dpu_encoder_irq_control(struct drm_encoder *drm_enc, bool enable)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	DPU_DEBUG_ENC(dpu_enc, "enable:%d\n", enable);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.irq_control)
+			phys->ops.irq_control(phys, enable);
+	}
+
+}
+
+static void _dpu_encoder_resource_control_helper(struct drm_encoder *drm_enc,
+		bool enable)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct dpu_encoder_virt *dpu_enc;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	trace_dpu_enc_rc_helper(DRMID(drm_enc), enable);
+
+	if (!dpu_enc->cur_master) {
+		DPU_ERROR("encoder master not set\n");
+		return;
+	}
+
+	if (enable) {
+		/* enable DPU core clks */
+		pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+		/* enable all the irq */
+		_dpu_encoder_irq_control(drm_enc, true);
+
+	} else {
+		/* disable all the irq */
+		_dpu_encoder_irq_control(drm_enc, false);
+
+		/* disable DPU core clks */
+		pm_runtime_put_sync(&dpu_kms->pdev->dev);
+	}
+
+}
+
+static int dpu_encoder_resource_control(struct drm_encoder *drm_enc,
+		u32 sw_event)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *disp_thread;
+	bool is_vid_mode = false;
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private ||
+			!drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	is_vid_mode = dpu_enc->disp_info.capabilities &
+						MSM_DISPLAY_CAP_VID_MODE;
+
+	if (drm_enc->crtc->index >= ARRAY_SIZE(priv->disp_thread)) {
+		DPU_ERROR("invalid crtc index\n");
+		return -EINVAL;
+	}
+	disp_thread = &priv->disp_thread[drm_enc->crtc->index];
+
+	/*
+	 * when idle_pc is not supported, process only KICKOFF, STOP and MODESET
+	 * events and return early for other events (ie wb display).
+	 */
+	if (!dpu_enc->idle_pc_supported &&
+			(sw_event != DPU_ENC_RC_EVENT_KICKOFF &&
+			sw_event != DPU_ENC_RC_EVENT_STOP &&
+			sw_event != DPU_ENC_RC_EVENT_PRE_STOP))
+		return 0;
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event, dpu_enc->idle_pc_supported,
+			 dpu_enc->rc_state, "begin");
+
+	switch (sw_event) {
+	case DPU_ENC_RC_EVENT_KICKOFF:
+		/* cancel delayed off work, if any */
+		if (kthread_cancel_delayed_work_sync(
+				&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in ON state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in ON state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state != DPU_ENC_RC_STATE_OFF &&
+				dpu_enc->rc_state != DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_KMS("id;%u, sw_event:%d, rc in state %d\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		if (is_vid_mode && dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE)
+			_dpu_encoder_irq_control(drm_enc, true);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, true);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_ON;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "kickoff");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_FRAME_DONE:
+		/*
+		 * mutex lock is not used as this event happens at interrupt
+		 * context. And locking is not required as, the other events
+		 * like KICKOFF and STOP does a wait-for-idle before executing
+		 * the resource_control
+		 */
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_DEBUG_KMS("id:%d, sw_event:%d,rc:%d-unexpected\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			return -EINVAL;
+		}
+
+		/*
+		 * schedule off work item only when there are no
+		 * frames pending
+		 */
+		if (dpu_crtc_frame_pending(drm_enc->crtc) > 1) {
+			DRM_DEBUG_KMS("id:%d skip schedule work\n",
+				      DRMID(drm_enc));
+			return 0;
+		}
+
+		kthread_queue_delayed_work(
+			&disp_thread->worker,
+			&dpu_enc->delayed_off_work,
+			msecs_to_jiffies(dpu_enc->idle_timeout));
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "frame done");
+		break;
+
+	case DPU_ENC_RC_EVENT_PRE_STOP:
+		/* cancel delayed off work, if any */
+		if (kthread_cancel_delayed_work_sync(
+				&dpu_enc->delayed_off_work))
+			DPU_DEBUG_ENC(dpu_enc, "sw_event:%d, work cancelled\n",
+					sw_event);
+
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (is_vid_mode &&
+			  dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			_dpu_encoder_irq_control(drm_enc, true);
+		}
+		/* skip if is already OFF or IDLE, resources are off already */
+		else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF ||
+				dpu_enc->rc_state == DPU_ENC_RC_STATE_IDLE) {
+			DRM_DEBUG_KMS("id:%u, sw_event:%d, rc in %d state\n",
+				      DRMID(drm_enc), sw_event,
+				      dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_PRE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "pre stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_STOP:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		/* return if the resource control is already in OFF state */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_OFF) {
+			DRM_DEBUG_KMS("id: %u, sw_event:%d, rc in OFF state\n",
+				      DRMID(drm_enc), sw_event);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		} else if (dpu_enc->rc_state == DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc in state %d\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return -EINVAL;
+		}
+
+		/**
+		 * expect to arrive here only if in either idle state or pre-off
+		 * and in IDLE state the resources are already disabled
+		 */
+		if (dpu_enc->rc_state == DPU_ENC_RC_STATE_PRE_OFF)
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_OFF;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "stop");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	case DPU_ENC_RC_EVENT_ENTER_IDLE:
+		mutex_lock(&dpu_enc->rc_lock);
+
+		if (dpu_enc->rc_state != DPU_ENC_RC_STATE_ON) {
+			DRM_ERROR("id: %u, sw_event:%d, rc:%d !ON state\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		/*
+		 * if we are in ON but a frame was just kicked off,
+		 * ignore the IDLE event, it's probably a stale timer event
+		 */
+		if (dpu_enc->frame_busy_mask[0]) {
+			DRM_ERROR("id:%u, sw_event:%d, rc:%d frame pending\n",
+				  DRMID(drm_enc), sw_event, dpu_enc->rc_state);
+			mutex_unlock(&dpu_enc->rc_lock);
+			return 0;
+		}
+
+		if (is_vid_mode)
+			_dpu_encoder_irq_control(drm_enc, false);
+		else
+			_dpu_encoder_resource_control_helper(drm_enc, false);
+
+		dpu_enc->rc_state = DPU_ENC_RC_STATE_IDLE;
+
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "idle");
+
+		mutex_unlock(&dpu_enc->rc_lock);
+		break;
+
+	default:
+		DRM_ERROR("id:%u, unexpected sw_event: %d\n", DRMID(drm_enc),
+			  sw_event);
+		trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+				 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+				 "error");
+		break;
+	}
+
+	trace_dpu_enc_rc(DRMID(drm_enc), sw_event,
+			 dpu_enc->idle_pc_supported, dpu_enc->rc_state,
+			 "end");
+	return 0;
+}
+
+static void dpu_encoder_virt_mode_set(struct drm_encoder *drm_enc,
+				      struct drm_display_mode *mode,
+				      struct drm_display_mode *adj_mode)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct list_head *connector_list;
+	struct drm_connector *conn = NULL, *conn_iter;
+	struct dpu_rm_hw_iter pp_iter;
+	struct msm_display_topology topology;
+	enum dpu_rm_topology_name topology_name;
+	int i = 0, ret;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	connector_list = &dpu_kms->dev->mode_config.connector_list;
+
+	trace_dpu_enc_mode_set(DRMID(drm_enc));
+
+	list_for_each_entry(conn_iter, connector_list, head)
+		if (conn_iter->encoder == drm_enc)
+			conn = conn_iter;
+
+	if (!conn) {
+		DPU_ERROR_ENC(dpu_enc, "failed to find attached connector\n");
+		return;
+	} else if (!conn->state) {
+		DPU_ERROR_ENC(dpu_enc, "invalid connector state\n");
+		return;
+	}
+
+	topology = dpu_encoder_get_topology(dpu_enc, dpu_kms, adj_mode);
+
+	/* Reserve dynamic resources now. Indicating non-AtomicTest phase */
+	ret = dpu_rm_reserve(&dpu_kms->rm, drm_enc, drm_enc->crtc->state,
+			conn->state, topology, false);
+	if (ret) {
+		DPU_ERROR_ENC(dpu_enc,
+				"failed to reserve hw resources, %d\n", ret);
+		return;
+	}
+
+	dpu_rm_init_hw_iter(&pp_iter, drm_enc->base.id, DPU_HW_BLK_PINGPONG);
+	for (i = 0; i < MAX_CHANNELS_PER_ENC; i++) {
+		dpu_enc->hw_pp[i] = NULL;
+		if (!dpu_rm_get_hw(&dpu_kms->rm, &pp_iter))
+			break;
+		dpu_enc->hw_pp[i] = (struct dpu_hw_pingpong *) pp_iter.hw;
+	}
+
+	topology_name = dpu_rm_get_topology_name(topology);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys) {
+			if (!dpu_enc->hw_pp[i]) {
+				DPU_ERROR_ENC(dpu_enc,
+				    "invalid pingpong block for the encoder\n");
+				return;
+			}
+			phys->hw_pp = dpu_enc->hw_pp[i];
+			phys->connector = conn->state->connector;
+			phys->topology_name = topology_name;
+			if (phys->ops.mode_set)
+				phys->ops.mode_set(phys, mode, adj_mode);
+		}
+	}
+
+	dpu_enc->mode_set_complete = true;
+}
+
+static void _dpu_encoder_virt_enable_helper(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	if (!dpu_enc || !dpu_enc->cur_master) {
+		DPU_ERROR("invalid dpu encoder/master\n");
+		return;
+	}
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DisplayPort &&
+	    dpu_enc->cur_master->hw_mdptop &&
+	    dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select)
+		dpu_enc->cur_master->hw_mdptop->ops.intf_audio_select(
+					dpu_enc->cur_master->hw_mdptop);
+
+	if (dpu_enc->cur_master->hw_mdptop &&
+			dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc)
+		dpu_enc->cur_master->hw_mdptop->ops.reset_ubwc(
+				dpu_enc->cur_master->hw_mdptop,
+				dpu_kms->catalog);
+
+	_dpu_encoder_update_vsync_source(dpu_enc, &dpu_enc->disp_info);
+}
+
+void dpu_encoder_virt_restore(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && (phys != dpu_enc->cur_master) && phys->ops.restore)
+			phys->ops.restore(phys);
+	}
+
+	if (dpu_enc->cur_master && dpu_enc->cur_master->ops.restore)
+		dpu_enc->cur_master->ops.restore(dpu_enc->cur_master);
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+}
+
+static void dpu_encoder_virt_enable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i, ret = 0;
+	struct drm_display_mode *cur_mode = NULL;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
+
+	trace_dpu_enc_enable(DRMID(drm_enc), cur_mode->hdisplay,
+			     cur_mode->vdisplay);
+
+	dpu_enc->cur_master = NULL;
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.is_master && phys->ops.is_master(phys)) {
+			DPU_DEBUG_ENC(dpu_enc, "master is now idx %d\n", i);
+			dpu_enc->cur_master = phys;
+			break;
+		}
+	}
+
+	if (!dpu_enc->cur_master) {
+		DPU_ERROR("virt encoder has no master! num_phys %d\n", i);
+		return;
+	}
+
+	ret = dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+	if (ret) {
+		DPU_ERROR_ENC(dpu_enc, "dpu resource control failed: %d\n",
+				ret);
+		return;
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys)
+			continue;
+
+		if (phys != dpu_enc->cur_master) {
+			if (phys->ops.enable)
+				phys->ops.enable(phys);
+		}
+
+		if (dpu_enc->misr_enable && (dpu_enc->disp_info.capabilities &
+		     MSM_DISPLAY_CAP_VID_MODE) && phys->ops.setup_misr)
+			phys->ops.setup_misr(phys, true,
+						dpu_enc->misr_frame_count);
+	}
+
+	if (dpu_enc->cur_master->ops.enable)
+		dpu_enc->cur_master->ops.enable(dpu_enc->cur_master);
+
+	_dpu_encoder_virt_enable_helper(drm_enc);
+}
+
+static void dpu_encoder_virt_disable(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	struct drm_display_mode *mode;
+	int i = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	} else if (!drm_enc->dev) {
+		DPU_ERROR("invalid dev\n");
+		return;
+	} else if (!drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid dev_private\n");
+		return;
+	}
+
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	trace_dpu_enc_disable(DRMID(drm_enc));
+
+	/* wait for idle */
+	dpu_encoder_wait_for_event(drm_enc, MSM_ENC_TX_COMPLETE);
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_PRE_STOP);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.disable)
+			phys->ops.disable(phys);
+	}
+
+	/* after phys waits for frame-done, should be no more frames pending */
+	if (atomic_xchg(&dpu_enc->frame_done_timeout, 0)) {
+		DPU_ERROR("enc%d timeout pending\n", drm_enc->base.id);
+		del_timer_sync(&dpu_enc->frame_done_timer);
+	}
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_STOP);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		if (dpu_enc->phys_encs[i])
+			dpu_enc->phys_encs[i]->connector = NULL;
+	}
+
+	dpu_enc->cur_master = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "encoder disabled\n");
+
+	dpu_rm_release(&dpu_kms->rm, drm_enc);
+}
+
+static enum dpu_intf dpu_encoder_get_intf(struct dpu_mdss_cfg *catalog,
+		enum dpu_intf_type type, u32 controller_id)
+{
+	int i = 0;
+
+	for (i = 0; i < catalog->intf_count; i++) {
+		if (catalog->intf[i].type == type
+		    && catalog->intf[i].controller_id == controller_id) {
+			return catalog->intf[i].id;
+		}
+	}
+
+	return INTF_MAX;
+}
+
+static void dpu_encoder_vblank_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	unsigned long lock_flags;
+
+	if (!drm_enc || !phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_vblank_callback");
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	if (dpu_enc->crtc_vblank_cb)
+		dpu_enc->crtc_vblank_cb(dpu_enc->crtc_vblank_cb_data);
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	atomic_inc(&phy_enc->vsync_cnt);
+	DPU_ATRACE_END("encoder_vblank_callback");
+}
+
+static void dpu_encoder_underrun_callback(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phy_enc)
+{
+	if (!phy_enc)
+		return;
+
+	DPU_ATRACE_BEGIN("encoder_underrun_callback");
+	atomic_inc(&phy_enc->underrun_cnt);
+	trace_dpu_enc_underrun_cb(DRMID(drm_enc),
+				  atomic_read(&phy_enc->underrun_cnt));
+	DPU_ATRACE_END("encoder_underrun_callback");
+}
+
+void dpu_encoder_register_vblank_callback(struct drm_encoder *drm_enc,
+		void (*vbl_cb)(void *), void *vbl_data)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	bool enable;
+	int i;
+
+	enable = vbl_cb ? true : false;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	trace_dpu_enc_vblank_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	dpu_enc->crtc_vblank_cb = vbl_cb;
+	dpu_enc->crtc_vblank_cb_data = vbl_data;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->ops.control_vblank_irq)
+			phys->ops.control_vblank_irq(phys, enable);
+	}
+}
+
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *drm_enc,
+		void (*frame_event_cb)(void *, u32 event),
+		void *frame_event_cb_data)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned long lock_flags;
+	bool enable;
+
+	enable = frame_event_cb ? true : false;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	trace_dpu_enc_frame_event_cb(DRMID(drm_enc), enable);
+
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+	dpu_enc->crtc_frame_event_cb = frame_event_cb;
+	dpu_enc->crtc_frame_event_cb_data = frame_event_cb_data;
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+static void dpu_encoder_frame_done_callback(
+		struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *ready_phys, u32 event)
+{
+	struct dpu_encoder_virt *dpu_enc = to_dpu_encoder_virt(drm_enc);
+	unsigned int i;
+
+	if (event & (DPU_ENCODER_FRAME_EVENT_DONE
+			| DPU_ENCODER_FRAME_EVENT_ERROR
+			| DPU_ENCODER_FRAME_EVENT_PANEL_DEAD)) {
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			/**
+			 * suppress frame_done without waiter,
+			 * likely autorefresh
+			 */
+			trace_dpu_enc_frame_done_cb_not_busy(DRMID(drm_enc),
+					event, ready_phys->intf_idx);
+			return;
+		}
+
+		/* One of the physical encoders has become idle */
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			if (dpu_enc->phys_encs[i] == ready_phys) {
+				clear_bit(i, dpu_enc->frame_busy_mask);
+				trace_dpu_enc_frame_done_cb(DRMID(drm_enc), i,
+						dpu_enc->frame_busy_mask[0]);
+			}
+		}
+
+		if (!dpu_enc->frame_busy_mask[0]) {
+			atomic_set(&dpu_enc->frame_done_timeout, 0);
+			del_timer(&dpu_enc->frame_done_timer);
+
+			dpu_encoder_resource_control(drm_enc,
+					DPU_ENC_RC_EVENT_FRAME_DONE);
+
+			if (dpu_enc->crtc_frame_event_cb)
+				dpu_enc->crtc_frame_event_cb(
+					dpu_enc->crtc_frame_event_cb_data,
+					event);
+		}
+	} else {
+		if (dpu_enc->crtc_frame_event_cb)
+			dpu_enc->crtc_frame_event_cb(
+				dpu_enc->crtc_frame_event_cb_data, event);
+	}
+}
+
+static void dpu_encoder_off_work(struct kthread_work *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, delayed_off_work.work);
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu encoder\n");
+		return;
+	}
+
+	dpu_encoder_resource_control(&dpu_enc->base,
+						DPU_ENC_RC_EVENT_ENTER_IDLE);
+
+	dpu_encoder_frame_done_callback(&dpu_enc->base, NULL,
+				DPU_ENCODER_FRAME_EVENT_IDLE);
+}
+
+/**
+ * _dpu_encoder_trigger_flush - trigger flush for a physical encoder
+ * drm_enc: Pointer to drm encoder structure
+ * phys: Pointer to physical encoder structure
+ * extra_flush_bits: Additional bit mask to include in flush trigger
+ */
+static inline void _dpu_encoder_trigger_flush(struct drm_encoder *drm_enc,
+		struct dpu_encoder_phys *phys, uint32_t extra_flush_bits)
+{
+	struct dpu_hw_ctl *ctl;
+	int pending_kickoff_cnt;
+	u32 ret = UINT_MAX;
+
+	if (!drm_enc || !phys) {
+		DPU_ERROR("invalid argument(s), drm_enc %d, phys_enc %d\n",
+				drm_enc != 0, phys != 0);
+		return;
+	}
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	ctl = phys->hw_ctl;
+	if (!ctl || !ctl->ops.trigger_flush) {
+		DPU_ERROR("missing trigger cb\n");
+		return;
+	}
+
+	pending_kickoff_cnt = dpu_encoder_phys_inc_pending(phys);
+
+	if (extra_flush_bits && ctl->ops.update_pending_flush)
+		ctl->ops.update_pending_flush(ctl, extra_flush_bits);
+
+	ctl->ops.trigger_flush(ctl);
+
+	if (ctl->ops.get_pending_flush)
+		ret = ctl->ops.get_pending_flush(ctl);
+
+	trace_dpu_enc_trigger_flush(DRMID(drm_enc), phys->intf_idx,
+				    pending_kickoff_cnt, ctl->idx, ret);
+}
+
+/**
+ * _dpu_encoder_trigger_start - trigger start for a physical encoder
+ * phys: Pointer to physical encoder structure
+ */
+static inline void _dpu_encoder_trigger_start(struct dpu_encoder_phys *phys)
+{
+	if (!phys) {
+		DPU_ERROR("invalid argument(s)\n");
+		return;
+	}
+
+	if (!phys->hw_pp) {
+		DPU_ERROR("invalid pingpong hw\n");
+		return;
+	}
+
+	if (phys->ops.trigger_start && phys->enable_state != DPU_ENC_DISABLED)
+		phys->ops.trigger_start(phys);
+}
+
+void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	ctl = phys_enc->hw_ctl;
+	if (ctl && ctl->ops.trigger_start) {
+		ctl->ops.trigger_start(ctl);
+		trace_dpu_enc_trigger_start(DRMID(phys_enc->parent), ctl->idx);
+	}
+}
+
+int dpu_encoder_helper_wait_event_timeout(
+		int32_t drm_id,
+		int32_t hw_id,
+		struct dpu_encoder_wait_info *info)
+{
+	int rc = 0;
+	s64 expected_time = ktime_to_ms(ktime_get()) + info->timeout_ms;
+	s64 jiffies = msecs_to_jiffies(info->timeout_ms);
+	s64 time;
+
+	do {
+		rc = wait_event_timeout(*(info->wq),
+				atomic_read(info->atomic_cnt) == 0, jiffies);
+		time = ktime_to_ms(ktime_get());
+
+		trace_dpu_enc_wait_event_timeout(drm_id, hw_id, rc, time,
+						 expected_time,
+						 atomic_read(info->atomic_cnt));
+	/* If we timed out, counter is valid and time is less, wait again */
+	} while (atomic_read(info->atomic_cnt) && (rc == 0) &&
+			(time < expected_time));
+
+	return rc;
+}
+
+void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_hw_ctl *ctl;
+	int rc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(phys_enc->parent);
+	ctl = phys_enc->hw_ctl;
+
+	if (!ctl || !ctl->ops.reset)
+		return;
+
+	DRM_DEBUG_KMS("id:%u ctl %d reset\n", DRMID(phys_enc->parent),
+		      ctl->idx);
+
+	rc = ctl->ops.reset(ctl);
+	if (rc) {
+		DPU_ERROR_ENC(dpu_enc, "ctl %d reset failure\n",  ctl->idx);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+/**
+ * _dpu_encoder_kickoff_phys - handle physical encoder kickoff
+ *	Iterate through the physical encoders and perform consolidated flush
+ *	and/or control start triggering as needed. This is done in the virtual
+ *	encoder rather than the individual physical ones in order to handle
+ *	use cases that require visibility into multiple physical encoders at
+ *	a time.
+ * dpu_enc: Pointer to virtual encoder structure
+ */
+static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	uint32_t i, pending_flush;
+	unsigned long lock_flags;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	pending_flush = 0x0;
+
+	/* update pending counts and trigger kickoff ctl flush atomically */
+	spin_lock_irqsave(&dpu_enc->enc_spinlock, lock_flags);
+
+	/* don't perform flush/start operations for slave encoders */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys || phys->enable_state == DPU_ENC_DISABLED)
+			continue;
+
+		ctl = phys->hw_ctl;
+		if (!ctl)
+			continue;
+
+		if (phys->split_role != ENC_ROLE_SLAVE)
+			set_bit(i, dpu_enc->frame_busy_mask);
+		if (!phys->ops.needs_single_flush ||
+				!phys->ops.needs_single_flush(phys))
+			_dpu_encoder_trigger_flush(&dpu_enc->base, phys, 0x0);
+		else if (ctl->ops.get_pending_flush)
+			pending_flush |= ctl->ops.get_pending_flush(ctl);
+	}
+
+	/* for split flush, combine pending flush masks and send to master */
+	if (pending_flush && dpu_enc->cur_master) {
+		_dpu_encoder_trigger_flush(
+				&dpu_enc->base,
+				dpu_enc->cur_master,
+				pending_flush);
+	}
+
+	_dpu_encoder_trigger_start(dpu_enc->cur_master);
+
+	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
+}
+
+bool dpu_encoder_check_mode(struct drm_encoder *drm_enc, u32 mode)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_display_info *disp_info;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return false;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	disp_info = &dpu_enc->disp_info;
+
+	return (disp_info->capabilities & mode);
+}
+
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	unsigned int i;
+	struct dpu_hw_ctl *ctl;
+	struct msm_display_info *disp_info;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	disp_info = &dpu_enc->disp_info;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+
+		if (phys && phys->hw_ctl) {
+			ctl = phys->hw_ctl;
+			if (ctl->ops.clear_pending_flush)
+				ctl->ops.clear_pending_flush(ctl);
+
+			/* update only for command mode primary ctl */
+			if ((phys == dpu_enc->cur_master) &&
+			   (disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE)
+			    && ctl->ops.trigger_pending)
+				ctl->ops.trigger_pending(ctl);
+		}
+	}
+}
+
+static u32 _dpu_encoder_calculate_linetime(struct dpu_encoder_virt *dpu_enc,
+		struct drm_display_mode *mode)
+{
+	u64 pclk_rate;
+	u32 pclk_period;
+	u32 line_time;
+
+	/*
+	 * For linetime calculation, only operate on master encoder.
+	 */
+	if (!dpu_enc->cur_master)
+		return 0;
+
+	if (!dpu_enc->cur_master->ops.get_line_count) {
+		DPU_ERROR("get_line_count function not defined\n");
+		return 0;
+	}
+
+	pclk_rate = mode->clock; /* pixel clock in kHz */
+	if (pclk_rate == 0) {
+		DPU_ERROR("pclk is 0, cannot calculate line time\n");
+		return 0;
+	}
+
+	pclk_period = DIV_ROUND_UP_ULL(1000000000ull, pclk_rate);
+	if (pclk_period == 0) {
+		DPU_ERROR("pclk period is 0\n");
+		return 0;
+	}
+
+	/*
+	 * Line time calculation based on Pixel clock and HTOTAL.
+	 * Final unit is in ns.
+	 */
+	line_time = (pclk_period * mode->htotal) / 1000;
+	if (line_time == 0) {
+		DPU_ERROR("line time calculation is 0\n");
+		return 0;
+	}
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"clk_rate=%lldkHz, clk_period=%d, linetime=%dns\n",
+			pclk_rate, pclk_period, line_time);
+
+	return line_time;
+}
+
+static int _dpu_encoder_wakeup_time(struct drm_encoder *drm_enc,
+		ktime_t *wakeup_time)
+{
+	struct drm_display_mode *mode;
+	struct dpu_encoder_virt *dpu_enc;
+	u32 cur_line;
+	u32 line_time;
+	u32 vtotal, time_to_vsync;
+	ktime_t cur_time;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	if (!drm_enc->crtc || !drm_enc->crtc->state) {
+		DPU_ERROR("crtc/crtc state object is NULL\n");
+		return -EINVAL;
+	}
+	mode = &drm_enc->crtc->state->adjusted_mode;
+
+	line_time = _dpu_encoder_calculate_linetime(dpu_enc, mode);
+	if (!line_time)
+		return -EINVAL;
+
+	cur_line = dpu_enc->cur_master->ops.get_line_count(dpu_enc->cur_master);
+
+	vtotal = mode->vtotal;
+	if (cur_line >= vtotal)
+		time_to_vsync = line_time * vtotal;
+	else
+		time_to_vsync = line_time * (vtotal - cur_line);
+
+	if (time_to_vsync == 0) {
+		DPU_ERROR("time to vsync should not be zero, vtotal=%d\n",
+				vtotal);
+		return -EINVAL;
+	}
+
+	cur_time = ktime_get();
+	*wakeup_time = ktime_add_ns(cur_time, time_to_vsync);
+
+	DPU_DEBUG_ENC(dpu_enc,
+			"cur_line=%u vtotal=%u time_to_vsync=%u, cur_time=%lld, wakeup_time=%lld\n",
+			cur_line, vtotal, time_to_vsync,
+			ktime_to_ms(cur_time),
+			ktime_to_ms(*wakeup_time));
+	return 0;
+}
+
+static void dpu_encoder_vsync_event_handler(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			vsync_event_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	struct msm_drm_private *priv;
+	struct msm_drm_thread *event_thread;
+
+	if (!drm_enc->dev || !drm_enc->dev->dev_private ||
+			!drm_enc->crtc) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	priv = drm_enc->dev->dev_private;
+
+	if (drm_enc->crtc->index >= ARRAY_SIZE(priv->event_thread)) {
+		DPU_ERROR("invalid crtc index\n");
+		return;
+	}
+	event_thread = &priv->event_thread[drm_enc->crtc->index];
+	if (!event_thread) {
+		DPU_ERROR("event_thread not found for crtc:%d\n",
+				drm_enc->crtc->index);
+		return;
+	}
+
+	del_timer(&dpu_enc->vsync_event_timer);
+}
+
+static void dpu_encoder_vsync_event_work_handler(struct kthread_work *work)
+{
+	struct dpu_encoder_virt *dpu_enc = container_of(work,
+			struct dpu_encoder_virt, vsync_event_work);
+	ktime_t wakeup_time;
+
+	if (!dpu_enc) {
+		DPU_ERROR("invalid dpu encoder\n");
+		return;
+	}
+
+	if (_dpu_encoder_wakeup_time(&dpu_enc->base, &wakeup_time))
+		return;
+
+	trace_dpu_enc_vsync_event_work(DRMID(&dpu_enc->base), wakeup_time);
+	mod_timer(&dpu_enc->vsync_event_timer,
+			nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+}
+
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *drm_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	bool needs_hw_reset = false;
+	unsigned int i;
+
+	if (!drm_enc || !params) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	trace_dpu_enc_prepare_kickoff(DRMID(drm_enc));
+
+	/* prepare for next kickoff, may include waiting on previous kickoff */
+	DPU_ATRACE_BEGIN("enc_prepare_for_kickoff");
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys) {
+			if (phys->ops.prepare_for_kickoff)
+				phys->ops.prepare_for_kickoff(phys, params);
+			if (phys->enable_state == DPU_ENC_ERR_NEEDS_HW_RESET)
+				needs_hw_reset = true;
+		}
+	}
+	DPU_ATRACE_END("enc_prepare_for_kickoff");
+
+	dpu_encoder_resource_control(drm_enc, DPU_ENC_RC_EVENT_KICKOFF);
+
+	/* if any phys needs reset, reset all phys, in-order */
+	if (needs_hw_reset) {
+		trace_dpu_enc_prepare_kickoff_reset(DRMID(drm_enc));
+		for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+			phys = dpu_enc->phys_encs[i];
+			if (phys && phys->ops.hw_reset)
+				phys->ops.hw_reset(phys);
+		}
+	}
+}
+
+void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	ktime_t wakeup_time;
+	unsigned int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DPU_ATRACE_BEGIN("encoder_kickoff");
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	trace_dpu_enc_kickoff(DRMID(drm_enc));
+
+	atomic_set(&dpu_enc->frame_done_timeout,
+			DPU_FRAME_DONE_TIMEOUT * 1000 /
+			drm_enc->crtc->state->adjusted_mode.vrefresh);
+	mod_timer(&dpu_enc->frame_done_timer, jiffies +
+		((atomic_read(&dpu_enc->frame_done_timeout) * HZ) / 1000));
+
+	/* All phys encs are ready to go, trigger the kickoff */
+	_dpu_encoder_kickoff_phys(dpu_enc);
+
+	/* allow phys encs to handle any post-kickoff business */
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys && phys->ops.handle_post_kickoff)
+			phys->ops.handle_post_kickoff(phys);
+	}
+
+	if (dpu_enc->disp_info.intf_type == DRM_MODE_CONNECTOR_DSI &&
+			!_dpu_encoder_wakeup_time(drm_enc, &wakeup_time)) {
+		trace_dpu_enc_early_kickoff(DRMID(drm_enc),
+					    ktime_to_ms(wakeup_time));
+		mod_timer(&dpu_enc->vsync_event_timer,
+				nsecs_to_jiffies(ktime_to_ns(wakeup_time)));
+	}
+
+	DPU_ATRACE_END("encoder_kickoff");
+}
+
+int dpu_encoder_helper_hw_release(struct dpu_encoder_phys *phys_enc,
+		struct drm_framebuffer *fb)
+{
+	struct drm_encoder *drm_enc;
+	struct dpu_hw_mixer_cfg mixer;
+	struct dpu_rm_hw_iter lm_iter;
+	bool lm_valid = false;
+
+	if (!phys_enc || !phys_enc->parent) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	drm_enc = phys_enc->parent;
+	memset(&mixer, 0, sizeof(mixer));
+
+	/* reset associated CTL/LMs */
+	if (phys_enc->hw_ctl->ops.clear_pending_flush)
+		phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl);
+	if (phys_enc->hw_ctl->ops.clear_all_blendstages)
+		phys_enc->hw_ctl->ops.clear_all_blendstages(phys_enc->hw_ctl);
+
+	dpu_rm_init_hw_iter(&lm_iter, drm_enc->base.id, DPU_HW_BLK_LM);
+	while (dpu_rm_get_hw(&phys_enc->dpu_kms->rm, &lm_iter)) {
+		struct dpu_hw_mixer *hw_lm = (struct dpu_hw_mixer *)lm_iter.hw;
+
+		if (!hw_lm)
+			continue;
+
+		/* need to flush LM to remove it */
+		if (phys_enc->hw_ctl->ops.get_bitmask_mixer &&
+				phys_enc->hw_ctl->ops.update_pending_flush)
+			phys_enc->hw_ctl->ops.update_pending_flush(
+					phys_enc->hw_ctl,
+					phys_enc->hw_ctl->ops.get_bitmask_mixer(
+					phys_enc->hw_ctl, hw_lm->idx));
+
+		if (fb) {
+			/* assume a single LM if targeting a frame buffer */
+			if (lm_valid)
+				continue;
+
+			mixer.out_height = fb->height;
+			mixer.out_width = fb->width;
+
+			if (hw_lm->ops.setup_mixer_out)
+				hw_lm->ops.setup_mixer_out(hw_lm, &mixer);
+		}
+
+		lm_valid = true;
+
+		/* only enable border color on LM */
+		if (phys_enc->hw_ctl->ops.setup_blendstage)
+			phys_enc->hw_ctl->ops.setup_blendstage(
+					phys_enc->hw_ctl, hw_lm->idx, NULL);
+	}
+
+	if (!lm_valid) {
+		DPU_DEBUG_ENC(to_dpu_encoder_virt(drm_enc), "lm not found\n");
+		return -EFAULT;
+	}
+	return 0;
+}
+
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct dpu_encoder_phys *phys;
+	int i;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		phys = dpu_enc->phys_encs[i];
+		if (phys && phys->ops.prepare_commit)
+			phys->ops.prepare_commit(phys);
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_encoder_status_show(struct seq_file *s, void *data)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i;
+
+	if (!s || !s->private)
+		return -EINVAL;
+
+	dpu_enc = s->private;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys)
+			continue;
+
+		seq_printf(s, "intf:%d    vsync:%8d     underrun:%8d    ",
+				phys->intf_idx - INTF_0,
+				atomic_read(&phys->vsync_cnt),
+				atomic_read(&phys->underrun_cnt));
+
+		switch (phys->intf_mode) {
+		case INTF_MODE_VIDEO:
+			seq_puts(s, "mode: video\n");
+			break;
+		case INTF_MODE_CMD:
+			seq_puts(s, "mode: command\n");
+			break;
+		default:
+			seq_puts(s, "mode: ???\n");
+			break;
+		}
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return 0;
+}
+
+static int _dpu_encoder_debugfs_status_open(struct inode *inode,
+		struct file *file)
+{
+	return single_open(file, _dpu_encoder_status_show, inode->i_private);
+}
+
+static ssize_t _dpu_encoder_misr_setup(struct file *file,
+		const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i = 0, rc;
+	char buf[MISR_BUFF_SIZE + 1];
+	size_t buff_copy;
+	u32 frame_count, enable;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_enc = file->private_data;
+
+	buff_copy = min_t(size_t, count, MISR_BUFF_SIZE);
+	if (copy_from_user(buf, user_buf, buff_copy))
+		return -EINVAL;
+
+	buf[buff_copy] = 0; /* end of string */
+
+	if (sscanf(buf, "%u %u", &enable, &frame_count) != 2)
+		return -EINVAL;
+
+	rc = _dpu_encoder_power_enable(dpu_enc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	dpu_enc->misr_enable = enable;
+	dpu_enc->misr_frame_count = frame_count;
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys || !phys->ops.setup_misr)
+			continue;
+
+		phys->ops.setup_misr(phys, enable, frame_count);
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+	_dpu_encoder_power_enable(dpu_enc, false);
+
+	return count;
+}
+
+static ssize_t _dpu_encoder_misr_read(struct file *file,
+		char __user *user_buff, size_t count, loff_t *ppos)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	int i = 0, len = 0;
+	char buf[MISR_BUFF_SIZE + 1] = {'\0'};
+	int rc;
+
+	if (*ppos)
+		return 0;
+
+	if (!file || !file->private_data)
+		return -EINVAL;
+
+	dpu_enc = file->private_data;
+
+	rc = _dpu_encoder_power_enable(dpu_enc, true);
+	if (rc)
+		return rc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	if (!dpu_enc->misr_enable) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"disabled\n");
+		goto buff_check;
+	} else if (dpu_enc->disp_info.capabilities &
+						~MSM_DISPLAY_CAP_VID_MODE) {
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"unsupported\n");
+		goto buff_check;
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (!phys || !phys->ops.collect_misr)
+			continue;
+
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len,
+			"Intf idx:%d\n", phys->intf_idx - INTF_0);
+		len += snprintf(buf + len, MISR_BUFF_SIZE - len, "0x%x\n",
+					phys->ops.collect_misr(phys));
+	}
+
+buff_check:
+	if (count <= len) {
+		len = 0;
+		goto end;
+	}
+
+	if (copy_to_user(user_buff, buf, len)) {
+		len = -EFAULT;
+		goto end;
+	}
+
+	*ppos += len;   /* increase offset */
+
+end:
+	mutex_unlock(&dpu_enc->enc_lock);
+	_dpu_encoder_power_enable(dpu_enc, false);
+	return len;
+}
+
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int i;
+
+	static const struct file_operations debugfs_status_fops = {
+		.open =		_dpu_encoder_debugfs_status_open,
+		.read =		seq_read,
+		.llseek =	seq_lseek,
+		.release =	single_release,
+	};
+
+	static const struct file_operations debugfs_misr_fops = {
+		.open = simple_open,
+		.read = _dpu_encoder_misr_read,
+		.write = _dpu_encoder_misr_setup,
+	};
+
+	char name[DPU_NAME_SIZE];
+
+	if (!drm_enc || !drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid encoder or kms\n");
+		return -EINVAL;
+	}
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	priv = drm_enc->dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	snprintf(name, DPU_NAME_SIZE, "encoder%u", drm_enc->base.id);
+
+	/* create overall sub-directory for the encoder */
+	dpu_enc->debugfs_root = debugfs_create_dir(name,
+			drm_enc->dev->primary->debugfs_root);
+	if (!dpu_enc->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_file("status", 0600,
+		dpu_enc->debugfs_root, dpu_enc, &debugfs_status_fops);
+
+	debugfs_create_file("misr_data", 0600,
+		dpu_enc->debugfs_root, dpu_enc, &debugfs_misr_fops);
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++)
+		if (dpu_enc->phys_encs[i] &&
+				dpu_enc->phys_encs[i]->ops.late_register)
+			dpu_enc->phys_encs[i]->ops.late_register(
+					dpu_enc->phys_encs[i],
+					dpu_enc->debugfs_root);
+
+	return 0;
+}
+
+static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
+{
+	struct dpu_encoder_virt *dpu_enc;
+
+	if (!drm_enc)
+		return;
+
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	debugfs_remove_recursive(dpu_enc->debugfs_root);
+}
+#else
+static int _dpu_encoder_init_debugfs(struct drm_encoder *drm_enc)
+{
+	return 0;
+}
+
+static void _dpu_encoder_destroy_debugfs(struct drm_encoder *drm_enc)
+{
+}
+#endif
+
+static int dpu_encoder_late_register(struct drm_encoder *encoder)
+{
+	return _dpu_encoder_init_debugfs(encoder);
+}
+
+static void dpu_encoder_early_unregister(struct drm_encoder *encoder)
+{
+	_dpu_encoder_destroy_debugfs(encoder);
+}
+
+static int dpu_encoder_virt_add_phys_encs(
+		u32 display_caps,
+		struct dpu_encoder_virt *dpu_enc,
+		struct dpu_enc_phys_init_params *params)
+{
+	struct dpu_encoder_phys *enc = NULL;
+
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	/*
+	 * We may create up to NUM_PHYS_ENCODER_TYPES physical encoder types
+	 * in this function, check up-front.
+	 */
+	if (dpu_enc->num_phys_encs + NUM_PHYS_ENCODER_TYPES >=
+			ARRAY_SIZE(dpu_enc->phys_encs)) {
+		DPU_ERROR_ENC(dpu_enc, "too many physical encoders %d\n",
+			  dpu_enc->num_phys_encs);
+		return -EINVAL;
+	}
+
+	if (display_caps & MSM_DISPLAY_CAP_VID_MODE) {
+		enc = dpu_encoder_phys_vid_init(params);
+
+		if (IS_ERR_OR_NULL(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init vid enc: %ld\n",
+				PTR_ERR(enc));
+			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	}
+
+	if (display_caps & MSM_DISPLAY_CAP_CMD_MODE) {
+		enc = dpu_encoder_phys_cmd_init(params);
+
+		if (IS_ERR_OR_NULL(enc)) {
+			DPU_ERROR_ENC(dpu_enc, "failed to init cmd enc: %ld\n",
+				PTR_ERR(enc));
+			return enc == 0 ? -EINVAL : PTR_ERR(enc);
+		}
+
+		dpu_enc->phys_encs[dpu_enc->num_phys_encs] = enc;
+		++dpu_enc->num_phys_encs;
+	}
+
+	return 0;
+}
+
+static const struct dpu_encoder_virt_ops dpu_encoder_parent_ops = {
+	.handle_vblank_virt = dpu_encoder_vblank_callback,
+	.handle_underrun_virt = dpu_encoder_underrun_callback,
+	.handle_frame_done = dpu_encoder_frame_done_callback,
+};
+
+static int dpu_encoder_setup_display(struct dpu_encoder_virt *dpu_enc,
+				 struct dpu_kms *dpu_kms,
+				 struct msm_display_info *disp_info,
+				 int *drm_enc_mode)
+{
+	int ret = 0;
+	int i = 0;
+	enum dpu_intf_type intf_type;
+	struct dpu_enc_phys_init_params phys_params;
+
+	if (!dpu_enc || !dpu_kms) {
+		DPU_ERROR("invalid arg(s), enc %d kms %d\n",
+				dpu_enc != 0, dpu_kms != 0);
+		return -EINVAL;
+	}
+
+	memset(&phys_params, 0, sizeof(phys_params));
+	phys_params.dpu_kms = dpu_kms;
+	phys_params.parent = &dpu_enc->base;
+	phys_params.parent_ops = &dpu_encoder_parent_ops;
+	phys_params.enc_spinlock = &dpu_enc->enc_spinlock;
+
+	DPU_DEBUG("\n");
+
+	if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI) {
+		*drm_enc_mode = DRM_MODE_ENCODER_DSI;
+		intf_type = INTF_DSI;
+	} else if (disp_info->intf_type == DRM_MODE_CONNECTOR_HDMIA) {
+		*drm_enc_mode = DRM_MODE_ENCODER_TMDS;
+		intf_type = INTF_HDMI;
+	} else if (disp_info->intf_type == DRM_MODE_CONNECTOR_DisplayPort) {
+		*drm_enc_mode = DRM_MODE_ENCODER_TMDS;
+		intf_type = INTF_DP;
+	} else {
+		DPU_ERROR_ENC(dpu_enc, "unsupported display interface type\n");
+		return -EINVAL;
+	}
+
+	WARN_ON(disp_info->num_of_h_tiles < 1);
+
+	dpu_enc->display_num_of_h_tiles = disp_info->num_of_h_tiles;
+
+	DPU_DEBUG("dsi_info->num_of_h_tiles %d\n", disp_info->num_of_h_tiles);
+
+	if ((disp_info->capabilities & MSM_DISPLAY_CAP_CMD_MODE) ||
+	    (disp_info->capabilities & MSM_DISPLAY_CAP_VID_MODE))
+		dpu_enc->idle_pc_supported =
+				dpu_kms->catalog->caps->has_idle_pc;
+
+	mutex_lock(&dpu_enc->enc_lock);
+	for (i = 0; i < disp_info->num_of_h_tiles && !ret; i++) {
+		/*
+		 * Left-most tile is at index 0, content is controller id
+		 * h_tile_instance_ids[2] = {0, 1}; DSI0 = left, DSI1 = right
+		 * h_tile_instance_ids[2] = {1, 0}; DSI1 = left, DSI0 = right
+		 */
+		u32 controller_id = disp_info->h_tile_instance[i];
+
+		if (disp_info->num_of_h_tiles > 1) {
+			if (i == 0)
+				phys_params.split_role = ENC_ROLE_MASTER;
+			else
+				phys_params.split_role = ENC_ROLE_SLAVE;
+		} else {
+			phys_params.split_role = ENC_ROLE_SOLO;
+		}
+
+		DPU_DEBUG("h_tile_instance %d = %d, split_role %d\n",
+				i, controller_id, phys_params.split_role);
+
+		phys_params.intf_idx = dpu_encoder_get_intf(dpu_kms->catalog,
+													intf_type,
+													controller_id);
+		if (phys_params.intf_idx == INTF_MAX) {
+			DPU_ERROR_ENC(dpu_enc, "could not get intf: type %d, id %d\n",
+						  intf_type, controller_id);
+			ret = -EINVAL;
+		}
+
+		if (!ret) {
+			ret = dpu_encoder_virt_add_phys_encs(disp_info->capabilities,
+												 dpu_enc,
+												 &phys_params);
+			if (ret)
+				DPU_ERROR_ENC(dpu_enc, "failed to add phys encs\n");
+		}
+	}
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys) {
+			atomic_set(&phys->vsync_cnt, 0);
+			atomic_set(&phys->underrun_cnt, 0);
+		}
+	}
+	mutex_unlock(&dpu_enc->enc_lock);
+
+	return ret;
+}
+
+static void dpu_encoder_frame_done_timeout(struct timer_list *t)
+{
+	struct dpu_encoder_virt *dpu_enc = from_timer(dpu_enc, t,
+			frame_done_timer);
+	struct drm_encoder *drm_enc = &dpu_enc->base;
+	struct msm_drm_private *priv;
+	u32 event;
+
+	if (!drm_enc->dev || !drm_enc->dev->dev_private) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+	priv = drm_enc->dev->dev_private;
+
+	if (!dpu_enc->frame_busy_mask[0] || !dpu_enc->crtc_frame_event_cb) {
+		DRM_DEBUG_KMS("id:%u invalid timeout frame_busy_mask=%lu\n",
+			      DRMID(drm_enc), dpu_enc->frame_busy_mask[0]);
+		return;
+	} else if (!atomic_xchg(&dpu_enc->frame_done_timeout, 0)) {
+		DRM_DEBUG_KMS("id:%u invalid timeout\n", DRMID(drm_enc));
+		return;
+	}
+
+	DPU_ERROR_ENC(dpu_enc, "frame done timeout\n");
+
+	event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	trace_dpu_enc_frame_done_timeout(DRMID(drm_enc), event);
+	dpu_enc->crtc_frame_event_cb(dpu_enc->crtc_frame_event_cb_data, event);
+}
+
+static const struct drm_encoder_helper_funcs dpu_encoder_helper_funcs = {
+	.mode_set = dpu_encoder_virt_mode_set,
+	.disable = dpu_encoder_virt_disable,
+	.enable = dpu_kms_encoder_enable,
+	.atomic_check = dpu_encoder_virt_atomic_check,
+
+	/* This is called by dpu_kms_encoder_enable */
+	.commit = dpu_encoder_virt_enable,
+};
+
+static const struct drm_encoder_funcs dpu_encoder_funcs = {
+		.destroy = dpu_encoder_destroy,
+		.late_register = dpu_encoder_late_register,
+		.early_unregister = dpu_encoder_early_unregister,
+};
+
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info)
+{
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_kms *dpu_kms = to_dpu_kms(priv->kms);
+	struct drm_encoder *drm_enc = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int drm_enc_mode = DRM_MODE_ENCODER_NONE;
+	int ret = 0;
+
+	dpu_enc = to_dpu_encoder_virt(enc);
+
+	mutex_init(&dpu_enc->enc_lock);
+	ret = dpu_encoder_setup_display(dpu_enc, dpu_kms, disp_info,
+			&drm_enc_mode);
+	if (ret)
+		goto fail;
+
+	dpu_enc->cur_master = NULL;
+	spin_lock_init(&dpu_enc->enc_spinlock);
+
+	atomic_set(&dpu_enc->frame_done_timeout, 0);
+	timer_setup(&dpu_enc->frame_done_timer,
+			dpu_encoder_frame_done_timeout, 0);
+
+	if (disp_info->intf_type == DRM_MODE_CONNECTOR_DSI)
+		timer_setup(&dpu_enc->vsync_event_timer,
+				dpu_encoder_vsync_event_handler,
+				0);
+
+
+	mutex_init(&dpu_enc->rc_lock);
+	kthread_init_delayed_work(&dpu_enc->delayed_off_work,
+			dpu_encoder_off_work);
+	dpu_enc->idle_timeout = IDLE_TIMEOUT;
+
+	kthread_init_work(&dpu_enc->vsync_event_work,
+			dpu_encoder_vsync_event_work_handler);
+
+	memcpy(&dpu_enc->disp_info, disp_info, sizeof(*disp_info));
+
+	DPU_DEBUG_ENC(dpu_enc, "created\n");
+
+	return ret;
+
+fail:
+	DPU_ERROR("failed to create encoder\n");
+	if (drm_enc)
+		dpu_encoder_destroy(drm_enc);
+
+	return ret;
+
+
+}
+
+struct drm_encoder *dpu_encoder_init(struct drm_device *dev,
+		int drm_enc_mode)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int rc = 0;
+
+	dpu_enc = devm_kzalloc(dev->dev, sizeof(*dpu_enc), GFP_KERNEL);
+	if (!dpu_enc)
+		return ERR_PTR(ENOMEM);
+
+	rc = drm_encoder_init(dev, &dpu_enc->base, &dpu_encoder_funcs,
+			drm_enc_mode, NULL);
+	if (rc) {
+		devm_kfree(dev->dev, dpu_enc);
+		return ERR_PTR(rc);
+	}
+
+	drm_encoder_helper_add(&dpu_enc->base, &dpu_encoder_helper_funcs);
+
+	return &dpu_enc->base;
+}
+
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_enc,
+	enum msm_event_wait event)
+{
+	int (*fn_wait)(struct dpu_encoder_phys *phys_enc) = NULL;
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i, ret = 0;
+
+	if (!drm_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+	dpu_enc = to_dpu_encoder_virt(drm_enc);
+	DPU_DEBUG_ENC(dpu_enc, "\n");
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		switch (event) {
+		case MSM_ENC_COMMIT_DONE:
+			fn_wait = phys->ops.wait_for_commit_done;
+			break;
+		case MSM_ENC_TX_COMPLETE:
+			fn_wait = phys->ops.wait_for_tx_complete;
+			break;
+		case MSM_ENC_VBLANK:
+			fn_wait = phys->ops.wait_for_vblank;
+			break;
+		default:
+			DPU_ERROR_ENC(dpu_enc, "unknown wait event %d\n",
+					event);
+			return -EINVAL;
+		};
+
+		if (phys && fn_wait) {
+			DPU_ATRACE_BEGIN("wait_for_completion_event");
+			ret = fn_wait(phys);
+			DPU_ATRACE_END("wait_for_completion_event");
+			if (ret)
+				return ret;
+		}
+	}
+
+	return ret;
+}
+
+enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder)
+{
+	struct dpu_encoder_virt *dpu_enc = NULL;
+	int i;
+
+	if (!encoder) {
+		DPU_ERROR("invalid encoder\n");
+		return INTF_MODE_NONE;
+	}
+	dpu_enc = to_dpu_encoder_virt(encoder);
+
+	if (dpu_enc->cur_master)
+		return dpu_enc->cur_master->intf_mode;
+
+	for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+		struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+		if (phys)
+			return phys->intf_mode;
+	}
+
+	return INTF_MODE_NONE;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
new file mode 100644
index 000000000000..ce92901ed227
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
@@ -0,0 +1,191 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __DPU_ENCODER_H__
+#define __DPU_ENCODER_H__
+
+#include <drm/drm_crtc.h>
+#include "dpu_hw_mdss.h"
+
+#define DPU_ENCODER_FRAME_EVENT_DONE			BIT(0)
+#define DPU_ENCODER_FRAME_EVENT_ERROR			BIT(1)
+#define DPU_ENCODER_FRAME_EVENT_PANEL_DEAD		BIT(2)
+#define DPU_ENCODER_FRAME_EVENT_IDLE			BIT(3)
+
+#define IDLE_TIMEOUT	(66 - 16/2)
+
+/**
+ * Encoder functions and data types
+ * @intfs:	Interfaces this encoder is using, INTF_MODE_NONE if unused
+ * @needs_cdm:	Encoder requests a CDM based on pixel format conversion needs
+ * @display_num_of_h_tiles: Number of horizontal tiles in case of split
+ *                          interface
+ * @topology:   Topology of the display
+ */
+struct dpu_encoder_hw_resources {
+	enum dpu_intf_mode intfs[INTF_MAX];
+	bool needs_cdm;
+	u32 display_num_of_h_tiles;
+};
+
+/**
+ * dpu_encoder_kickoff_params - info encoder requires at kickoff
+ * @affected_displays:  bitmask, bit set means the ROI of the commit lies within
+ *                      the bounds of the physical display at the bit index
+ */
+struct dpu_encoder_kickoff_params {
+	unsigned long affected_displays;
+};
+
+/**
+ * dpu_encoder_get_hw_resources - Populate table of required hardware resources
+ * @encoder:	encoder pointer
+ * @hw_res:	resource table to populate with encoder required resources
+ * @conn_state:	report hw reqs based on this proposed connector state
+ */
+void dpu_encoder_get_hw_resources(struct drm_encoder *encoder,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state);
+
+/**
+ * dpu_encoder_register_vblank_callback - provide callback to encoder that
+ *	will be called on the next vblank.
+ * @encoder:	encoder pointer
+ * @cb:		callback pointer, provide NULL to deregister and disable IRQs
+ * @data:	user data provided to callback
+ */
+void dpu_encoder_register_vblank_callback(struct drm_encoder *encoder,
+		void (*cb)(void *), void *data);
+
+/**
+ * dpu_encoder_register_frame_event_callback - provide callback to encoder that
+ *	will be called after the request is complete, or other events.
+ * @encoder:	encoder pointer
+ * @cb:		callback pointer, provide NULL to deregister
+ * @data:	user data provided to callback
+ */
+void dpu_encoder_register_frame_event_callback(struct drm_encoder *encoder,
+		void (*cb)(void *, u32), void *data);
+
+/**
+ * dpu_encoder_prepare_for_kickoff - schedule double buffer flip of the ctl
+ *	path (i.e. ctl flush and start) at next appropriate time.
+ *	Immediately: if no previous commit is outstanding.
+ *	Delayed: Block until next trigger can be issued.
+ * @encoder:	encoder pointer
+ * @params:	kickoff time parameters
+ */
+void dpu_encoder_prepare_for_kickoff(struct drm_encoder *encoder,
+		struct dpu_encoder_kickoff_params *params);
+
+/**
+ * dpu_encoder_trigger_kickoff_pending - Clear the flush bits from previous
+ *        kickoff and trigger the ctl prepare progress for command mode display.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_kickoff - trigger a double buffer flip of the ctl path
+ *	(i.e. ctl flush and start) immediately.
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_kickoff(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_wait_for_event - Waits for encoder events
+ * @encoder:	encoder pointer
+ * @event:      event to wait for
+ * MSM_ENC_COMMIT_DONE -  Wait for hardware to have flushed the current pending
+ *                        frames to hardware at a vblank or ctl_start
+ *                        Encoders will map this differently depending on the
+ *                        panel type.
+ *	                  vid mode -> vsync_irq
+ *                        cmd mode -> ctl_start
+ * MSM_ENC_TX_COMPLETE -  Wait for the hardware to transfer all the pixels to
+ *                        the panel. Encoders will map this differently
+ *                        depending on the panel type.
+ *                        vid mode -> vsync_irq
+ *                        cmd mode -> pp_done
+ * Returns: 0 on success, -EWOULDBLOCK if already signaled, error otherwise
+ */
+int dpu_encoder_wait_for_event(struct drm_encoder *drm_encoder,
+						enum msm_event_wait event);
+
+/*
+ * dpu_encoder_get_intf_mode - get interface mode of the given encoder
+ * @encoder: Pointer to drm encoder object
+ */
+enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_virt_restore - restore the encoder configs
+ * @encoder:	encoder pointer
+ */
+void dpu_encoder_virt_restore(struct drm_encoder *encoder);
+
+/**
+ * dpu_encoder_check_mode - check if given mode is supported or not
+ * @drm_enc: Pointer to drm encoder object
+ * @mode: Mode to be checked
+ * @Return: true if it is cmd mode
+ */
+bool dpu_encoder_check_mode(struct drm_encoder *drm_enc, u32 mode);
+
+/**
+ * dpu_encoder_init - initialize virtual encoder object
+ * @dev:        Pointer to drm device structure
+ * @disp_info:  Pointer to display information structure
+ * Returns:     Pointer to newly created drm encoder
+ */
+struct drm_encoder *dpu_encoder_init(
+		struct drm_device *dev,
+		int drm_enc_mode);
+
+/**
+ * dpu_encoder_setup - setup dpu_encoder for the display probed
+ * @dev:		Pointer to drm device structure
+ * @enc:		Pointer to the drm_encoder
+ * @disp_info:	Pointer to the display info
+ */
+int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
+		struct msm_display_info *disp_info);
+
+/**
+ * dpu_encoder_destroy - destroy previously initialized virtual encoder
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+void dpu_encoder_destroy(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_prepare_commit - prepare encoder at the very beginning of an
+ *	atomic commit, before any registers are written
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ */
+void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc);
+
+/**
+ * dpu_encoder_set_idle_timeout - set the idle timeout for video
+ *                    and command mode encoders.
+ * @drm_enc:    Pointer to previously created drm encoder structure
+ * @idle_timeout:    idle timeout duration in milliseconds
+ */
+void dpu_encoder_set_idle_timeout(struct drm_encoder *drm_enc,
+							u32 idle_timeout);
+
+#endif /* __DPU_ENCODER_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
new file mode 100644
index 000000000000..8505edddcc81
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -0,0 +1,453 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DPU_ENCODER_PHYS_H__
+#define __DPU_ENCODER_PHYS_H__
+
+#include <linux/jiffies.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_intf.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_encoder.h"
+
+#define DPU_ENCODER_NAME_MAX	16
+
+/* wait for at most 2 vsync for lowest refresh rate (24hz) */
+#define KICKOFF_TIMEOUT_MS		84
+#define KICKOFF_TIMEOUT_JIFFIES		msecs_to_jiffies(KICKOFF_TIMEOUT_MS)
+
+/**
+ * enum dpu_enc_split_role - Role this physical encoder will play in a
+ *	split-panel configuration, where one panel is master, and others slaves.
+ *	Masters have extra responsibilities, like managing the VBLANK IRQ.
+ * @ENC_ROLE_SOLO:	This is the one and only panel. This encoder is master.
+ * @ENC_ROLE_MASTER:	This encoder is the master of a split panel config.
+ * @ENC_ROLE_SLAVE:	This encoder is not the master of a split panel config.
+ */
+enum dpu_enc_split_role {
+	ENC_ROLE_SOLO,
+	ENC_ROLE_MASTER,
+	ENC_ROLE_SLAVE,
+};
+
+/**
+ * enum dpu_enc_enable_state - current enabled state of the physical encoder
+ * @DPU_ENC_DISABLING:	Encoder transitioning to disable state
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_DISABLED:	Encoder is disabled
+ * @DPU_ENC_ENABLING:	Encoder transitioning to enabled
+ *			Events bounding transition are encoder type specific
+ * @DPU_ENC_ENABLED:	Encoder is enabled
+ * @DPU_ENC_ERR_NEEDS_HW_RESET:	Encoder is enabled, but requires a hw_reset
+ *				to recover from a previous error
+ */
+enum dpu_enc_enable_state {
+	DPU_ENC_DISABLING,
+	DPU_ENC_DISABLED,
+	DPU_ENC_ENABLING,
+	DPU_ENC_ENABLED,
+	DPU_ENC_ERR_NEEDS_HW_RESET
+};
+
+struct dpu_encoder_phys;
+
+/**
+ * struct dpu_encoder_virt_ops - Interface the containing virtual encoder
+ *	provides for the physical encoders to use to callback.
+ * @handle_vblank_virt:	Notify virtual encoder of vblank IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_underrun_virt: Notify virtual encoder of underrun IRQ reception
+ *			Note: This is called from IRQ handler context.
+ * @handle_frame_done:	Notify virtual encoder that this phys encoder
+ *			completes last request frame.
+ */
+struct dpu_encoder_virt_ops {
+	void (*handle_vblank_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_underrun_virt)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys);
+	void (*handle_frame_done)(struct drm_encoder *,
+			struct dpu_encoder_phys *phys, u32 event);
+};
+
+/**
+ * struct dpu_encoder_phys_ops - Interface the physical encoders provide to
+ *	the containing virtual encoder.
+ * @late_register:		DRM Call. Add Userspace interfaces, debugfs.
+ * @prepare_commit:		MSM Atomic Call, start of atomic commit sequence
+ * @is_master:			Whether this phys_enc is the current master
+ *				encoder. Can be switched at enable time. Based
+ *				on split_role and current mode (CMD/VID).
+ * @mode_fixup:			DRM Call. Fixup a DRM mode.
+ * @mode_set:			DRM Call. Set a DRM mode.
+ *				This likely caches the mode, for use at enable.
+ * @enable:			DRM Call. Enable a DRM mode.
+ * @disable:			DRM Call. Disable mode.
+ * @atomic_check:		DRM Call. Atomic check new DRM state.
+ * @destroy:			DRM Call. Destroy and release resources.
+ * @get_hw_resources:		Populate the structure with the hardware
+ *				resources that this phys_enc is using.
+ *				Expect no overlap between phys_encs.
+ * @control_vblank_irq		Register/Deregister for VBLANK IRQ
+ * @wait_for_commit_done:	Wait for hardware to have flushed the
+ *				current pending frames to hardware
+ * @wait_for_tx_complete:	Wait for hardware to transfer the pixels
+ *				to the panel
+ * @wait_for_vblank:		Wait for VBLANK, for sub-driver internal use
+ * @prepare_for_kickoff:	Do any work necessary prior to a kickoff
+ *				For CMD encoder, may wait for previous tx done
+ * @handle_post_kickoff:	Do any work necessary post-kickoff work
+ * @trigger_start:		Process start event on physical encoder
+ * @needs_single_flush:		Whether encoder slaves need to be flushed
+ * @setup_misr:		Sets up MISR, enable and disables based on sysfs
+ * @collect_misr:		Collects MISR data on frame update
+ * @hw_reset:			Issue HW recovery such as CTL reset and clear
+ *				DPU_ENC_ERR_NEEDS_HW_RESET state
+ * @irq_control:		Handler to enable/disable all the encoder IRQs
+ * @prepare_idle_pc:		phys encoder can update the vsync_enable status
+ *                              on idle power collapse prepare
+ * @restore:			Restore all the encoder configs.
+ * @get_line_count:		Obtain current vertical line count
+ */
+
+struct dpu_encoder_phys_ops {
+	int (*late_register)(struct dpu_encoder_phys *encoder,
+			struct dentry *debugfs_root);
+	void (*prepare_commit)(struct dpu_encoder_phys *encoder);
+	bool (*is_master)(struct dpu_encoder_phys *encoder);
+	bool (*mode_fixup)(struct dpu_encoder_phys *encoder,
+			const struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+	void (*mode_set)(struct dpu_encoder_phys *encoder,
+			struct drm_display_mode *mode,
+			struct drm_display_mode *adjusted_mode);
+	void (*enable)(struct dpu_encoder_phys *encoder);
+	void (*disable)(struct dpu_encoder_phys *encoder);
+	int (*atomic_check)(struct dpu_encoder_phys *encoder,
+			    struct drm_crtc_state *crtc_state,
+			    struct drm_connector_state *conn_state);
+	void (*destroy)(struct dpu_encoder_phys *encoder);
+	void (*get_hw_resources)(struct dpu_encoder_phys *encoder,
+			struct dpu_encoder_hw_resources *hw_res,
+			struct drm_connector_state *conn_state);
+	int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable);
+	int (*wait_for_commit_done)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_tx_complete)(struct dpu_encoder_phys *phys_enc);
+	int (*wait_for_vblank)(struct dpu_encoder_phys *phys_enc);
+	void (*prepare_for_kickoff)(struct dpu_encoder_phys *phys_enc,
+			struct dpu_encoder_kickoff_params *params);
+	void (*handle_post_kickoff)(struct dpu_encoder_phys *phys_enc);
+	void (*trigger_start)(struct dpu_encoder_phys *phys_enc);
+	bool (*needs_single_flush)(struct dpu_encoder_phys *phys_enc);
+
+	void (*setup_misr)(struct dpu_encoder_phys *phys_encs,
+				bool enable, u32 frame_count);
+	u32 (*collect_misr)(struct dpu_encoder_phys *phys_enc);
+	void (*hw_reset)(struct dpu_encoder_phys *phys_enc);
+	void (*irq_control)(struct dpu_encoder_phys *phys, bool enable);
+	void (*prepare_idle_pc)(struct dpu_encoder_phys *phys_enc);
+	void (*restore)(struct dpu_encoder_phys *phys);
+	int (*get_line_count)(struct dpu_encoder_phys *phys);
+};
+
+/**
+ * enum dpu_intr_idx - dpu encoder interrupt index
+ * @INTR_IDX_VSYNC:    Vsync interrupt for video mode panel
+ * @INTR_IDX_PINGPONG: Pingpong done unterrupt for cmd mode panel
+ * @INTR_IDX_UNDERRUN: Underrun unterrupt for video and cmd mode panel
+ * @INTR_IDX_RDPTR:    Readpointer done unterrupt for cmd mode panel
+ */
+enum dpu_intr_idx {
+	INTR_IDX_VSYNC,
+	INTR_IDX_PINGPONG,
+	INTR_IDX_UNDERRUN,
+	INTR_IDX_CTL_START,
+	INTR_IDX_RDPTR,
+	INTR_IDX_MAX,
+};
+
+/**
+ * dpu_encoder_irq - tracking structure for interrupts
+ * @name:		string name of interrupt
+ * @intr_type:		Encoder interrupt type
+ * @intr_idx:		Encoder interrupt enumeration
+ * @hw_idx:		HW Block ID
+ * @irq_idx:		IRQ interface lookup index from DPU IRQ framework
+ *			will be -EINVAL if IRQ is not registered
+ * @irq_cb:		interrupt callback
+ */
+struct dpu_encoder_irq {
+	const char *name;
+	enum dpu_intr_type intr_type;
+	enum dpu_intr_idx intr_idx;
+	int hw_idx;
+	int irq_idx;
+	struct dpu_irq_callback cb;
+};
+
+/**
+ * struct dpu_encoder_phys - physical encoder that drives a single INTF block
+ *	tied to a specific panel / sub-panel. Abstract type, sub-classed by
+ *	phys_vid or phys_cmd for video mode or command mode encs respectively.
+ * @parent:		Pointer to the containing virtual encoder
+ * @connector:		If a mode is set, cached pointer to the active connector
+ * @ops:		Operations exposed to the virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @hw_mdptop:		Hardware interface to the top registers
+ * @hw_ctl:		Hardware interface to the ctl registers
+ * @hw_cdm:		Hardware interface to the cdm registers
+ * @cdm_cfg:		Chroma-down hardware configuration
+ * @hw_pp:		Hardware interface to the ping pong registers
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @cached_mode:	DRM mode cached at mode_set time, acted on in enable
+ * @enabled:		Whether the encoder has enabled and running a mode
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_mode:		Interface mode
+ * @intf_idx:		Interface index on dpu hardware
+ * @topology_name:	topology selected for the display
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ * @enable_state:	Enable state tracking
+ * @vblank_refcount:	Reference count of vblank request
+ * @vsync_cnt:		Vsync count for the physical encoder
+ * @underrun_cnt:	Underrun count for the physical encoder
+ * @pending_kickoff_cnt:	Atomic counter tracking the number of kickoffs
+ *				vs. the number of done/vblank irqs. Should hover
+ *				between 0-2 Incremented when a new kickoff is
+ *				scheduled. Decremented in irq handler
+ * @pending_ctlstart_cnt:	Atomic counter tracking the number of ctl start
+ *                              pending.
+ * @pending_kickoff_wq:		Wait queue for blocking until kickoff completes
+ * @irq:			IRQ tracking structures
+ */
+struct dpu_encoder_phys {
+	struct drm_encoder *parent;
+	struct drm_connector *connector;
+	struct dpu_encoder_phys_ops ops;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	struct dpu_hw_mdp *hw_mdptop;
+	struct dpu_hw_ctl *hw_ctl;
+	struct dpu_hw_cdm *hw_cdm;
+	struct dpu_hw_cdm_cfg cdm_cfg;
+	struct dpu_hw_pingpong *hw_pp;
+	struct dpu_kms *dpu_kms;
+	struct drm_display_mode cached_mode;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf_mode intf_mode;
+	enum dpu_intf intf_idx;
+	enum dpu_rm_topology_name topology_name;
+	spinlock_t *enc_spinlock;
+	enum dpu_enc_enable_state enable_state;
+	atomic_t vblank_refcount;
+	atomic_t vsync_cnt;
+	atomic_t underrun_cnt;
+	atomic_t pending_ctlstart_cnt;
+	atomic_t pending_kickoff_cnt;
+	wait_queue_head_t pending_kickoff_wq;
+	struct dpu_encoder_irq irq[INTR_IDX_MAX];
+};
+
+static inline int dpu_encoder_phys_inc_pending(struct dpu_encoder_phys *phys)
+{
+	atomic_inc_return(&phys->pending_ctlstart_cnt);
+	return atomic_inc_return(&phys->pending_kickoff_cnt);
+}
+
+/**
+ * struct dpu_encoder_phys_vid - sub-class of dpu_encoder_phys to handle video
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @hw_intf:	Hardware interface to the intf registers
+ * @timing_params: Current timing parameter
+ */
+struct dpu_encoder_phys_vid {
+	struct dpu_encoder_phys base;
+	struct dpu_hw_intf *hw_intf;
+	struct intf_timing_params timing_params;
+};
+
+/**
+ * struct dpu_encoder_phys_cmd - sub-class of dpu_encoder_phys to handle command
+ *	mode specific operations
+ * @base:	Baseclass physical encoder structure
+ * @intf_idx:	Intf Block index used by this phys encoder
+ * @stream_sel:	Stream selection for multi-stream interfaces
+ * @serialize_wait4pp:	serialize wait4pp feature waits for pp_done interrupt
+ *			after ctl_start instead of before next frame kickoff
+ * @pp_timeout_report_cnt: number of pingpong done irq timeout errors
+ * @pending_vblank_cnt: Atomic counter tracking pending wait for VBLANK
+ * @pending_vblank_wq: Wait queue for blocking until VBLANK received
+ */
+struct dpu_encoder_phys_cmd {
+	struct dpu_encoder_phys base;
+	int stream_sel;
+	bool serialize_wait4pp;
+	int pp_timeout_report_cnt;
+	atomic_t pending_vblank_cnt;
+	wait_queue_head_t pending_vblank_wq;
+};
+
+/**
+ * struct dpu_enc_phys_init_params - initialization parameters for phys encs
+ * @dpu_kms:		Pointer to the dpu_kms top level
+ * @parent:		Pointer to the containing virtual encoder
+ * @parent_ops:		Callbacks exposed by the parent to the phys_enc
+ * @split_role:		Role to play in a split-panel configuration
+ * @intf_idx:		Interface index this phys_enc will control
+ * @enc_spinlock:	Virtual-Encoder-Wide Spin Lock for IRQ purposes
+ */
+struct dpu_enc_phys_init_params {
+	struct dpu_kms *dpu_kms;
+	struct drm_encoder *parent;
+	const struct dpu_encoder_virt_ops *parent_ops;
+	enum dpu_enc_split_role split_role;
+	enum dpu_intf intf_idx;
+	spinlock_t *enc_spinlock;
+};
+
+/**
+ * dpu_encoder_wait_info - container for passing arguments to irq wait functions
+ * @wq: wait queue structure
+ * @atomic_cnt: wait until atomic_cnt equals zero
+ * @timeout_ms: timeout value in milliseconds
+ */
+struct dpu_encoder_wait_info {
+	wait_queue_head_t *wq;
+	atomic_t *atomic_cnt;
+	s64 timeout_ms;
+};
+
+/**
+ * dpu_encoder_phys_vid_init - Construct a new video mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_phys_cmd_init - Construct a new command mode physical encoder
+ * @p:	Pointer to init params structure
+ * Return: Error code or newly allocated encoder
+ */
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p);
+
+/**
+ * dpu_encoder_helper_trigger_start - control start helper function
+ *	This helper function may be optionally specified by physical
+ *	encoders if they require ctl_start triggering.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc);
+
+/**
+ * dpu_encoder_helper_wait_event_timeout - wait for event with timeout
+ *	taking into account that jiffies may jump between reads leading to
+ *	incorrectly detected timeouts. Prevent failure in this scenario by
+ *	making sure that elapsed time during wait is valid.
+ * @drm_id: drm object id for logging
+ * @hw_id: hw instance id for logging
+ * @info: wait info structure
+ */
+int dpu_encoder_helper_wait_event_timeout(
+		int32_t drm_id,
+		int32_t hw_id,
+		struct dpu_encoder_wait_info *info);
+
+/**
+ * dpu_encoder_helper_hw_reset - issue ctl hw reset
+ *	This helper function may be optionally specified by physical
+ *	encoders if they require ctl hw reset. If state is currently
+ *	DPU_ENC_ERR_NEEDS_HW_RESET, it is set back to DPU_ENC_ENABLED.
+ * @phys_enc: Pointer to physical encoder structure
+ */
+void dpu_encoder_helper_hw_reset(struct dpu_encoder_phys *phys_enc);
+
+static inline enum dpu_3d_blend_mode dpu_encoder_helper_get_3d_blend_mode(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc || phys_enc->enable_state == DPU_ENC_DISABLING)
+		return BLEND_3D_NONE;
+
+	if (phys_enc->split_role == ENC_ROLE_SOLO &&
+	    phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE)
+		return BLEND_3D_H_ROW_INT;
+
+	return BLEND_3D_NONE;
+}
+
+/**
+ * dpu_encoder_helper_split_config - split display configuration helper function
+ *	This helper function may be used by physical encoders to configure
+ *	the split display related registers.
+ * @phys_enc: Pointer to physical encoder structure
+ * @interface: enum dpu_intf setting
+ */
+void dpu_encoder_helper_split_config(
+		struct dpu_encoder_phys *phys_enc,
+		enum dpu_intf interface);
+
+/**
+ * dpu_encoder_helper_hw_release - prepare for h/w reset during disable
+ * @phys_enc: Pointer to physical encoder structure
+ * @fb: Optional fb for specifying new mixer output resolution, may be NULL
+ * Return: Zero on success
+ */
+int dpu_encoder_helper_hw_release(struct dpu_encoder_phys *phys_enc,
+		struct drm_framebuffer *fb);
+
+/**
+ * dpu_encoder_helper_report_irq_timeout - utility to report error that irq has
+ *	timed out, including reporting frame error event to crtc and debug dump
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: Failing interrupt index
+ */
+void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+/**
+ * dpu_encoder_helper_wait_for_irq - utility to wait on an irq.
+ *	note: will call dpu_encoder_helper_wait_for_irq on timeout
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @wait_info: wait info struct
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx,
+		struct dpu_encoder_wait_info *wait_info);
+
+/**
+ * dpu_encoder_helper_register_irq - register and enable an irq
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_register_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+/**
+ * dpu_encoder_helper_unregister_irq - unregister and disable an irq
+ * @phys_enc: Pointer to physical encoder structure
+ * @intr_idx: encoder interrupt index
+ * @Return: 0 or -ERROR
+ */
+int dpu_encoder_helper_unregister_irq(struct dpu_encoder_phys *phys_enc,
+		enum dpu_intr_idx intr_idx);
+
+#endif /* __dpu_encoder_phys_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
new file mode 100644
index 000000000000..035a5fbe1435
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -0,0 +1,905 @@
+/*
+ * Copyright (c) 2015-2018 The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+
+#define DPU_DEBUG_CMDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_CMDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) ? (e)->base.intf_idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_cmd(x) \
+	container_of(x, struct dpu_encoder_phys_cmd, base)
+
+#define PP_TIMEOUT_MAX_TRIALS	10
+
+/*
+ * Tearcheck sync start and continue thresholds are empirically found
+ * based on common panels In the future, may want to allow panels to override
+ * these default values
+ */
+#define DEFAULT_TEARCHECK_SYNC_THRESH_START	4
+#define DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE	4
+
+#define DPU_ENC_WR_PTR_START_TIMEOUT_US 20000
+
+static inline int _dpu_encoder_phys_cmd_get_idle_timeout(
+		struct dpu_encoder_phys_cmd *cmd_enc)
+{
+	return KICKOFF_TIMEOUT_MS;
+}
+
+static inline bool dpu_encoder_phys_cmd_is_master(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return (phys_enc->split_role != ENC_ROLE_SLAVE) ? true : false;
+}
+
+static bool dpu_encoder_phys_cmd_mode_fixup(
+		struct dpu_encoder_phys *phys_enc,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	if (phys_enc)
+		DPU_DEBUG_CMDENC(to_dpu_encoder_phys_cmd(phys_enc), "\n");
+	return true;
+}
+
+static void _dpu_encoder_phys_cmd_update_intf_cfg(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_ctl *ctl;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+
+	if (!phys_enc)
+		return;
+
+	ctl = phys_enc->hw_ctl;
+	if (!ctl || !ctl->ops.setup_intf_cfg)
+		return;
+
+	intf_cfg.intf = phys_enc->intf_idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_CMD;
+	intf_cfg.stream_sel = cmd_enc->stream_sel;
+	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+	ctl->ops.setup_intf_cfg(ctl, &intf_cfg);
+}
+
+static void dpu_encoder_phys_cmd_pp_tx_done_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	unsigned long lock_flags;
+	int new_cnt;
+	u32 event = DPU_ENCODER_FRAME_EVENT_DONE;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return;
+
+	DPU_ATRACE_BEGIN("pp_done_irq");
+	/* notify all synchronous clients first, then asynchronous clients */
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(phys_enc->parent,
+				phys_enc, event);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	trace_dpu_enc_phys_cmd_pp_tx_done(DRMID(phys_enc->parent),
+					  phys_enc->hw_pp->idx - PINGPONG_0,
+					  new_cnt, event);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("pp_done_irq");
+}
+
+static void dpu_encoder_phys_cmd_pp_rd_ptr_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return;
+
+	DPU_ATRACE_BEGIN("rd_ptr_irq");
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+			phys_enc);
+
+	atomic_add_unless(&cmd_enc->pending_vblank_cnt, -1, 0);
+	wake_up_all(&cmd_enc->pending_vblank_wq);
+	DPU_ATRACE_END("rd_ptr_irq");
+}
+
+static void dpu_encoder_phys_cmd_ctl_start_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc || !phys_enc->hw_ctl)
+		return;
+
+	DPU_ATRACE_BEGIN("ctl_start_irq");
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	atomic_add_unless(&phys_enc->pending_ctlstart_cnt, -1, 0);
+
+	/* Signal any waiting ctl start interrupt */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("ctl_start_irq");
+}
+
+static void dpu_encoder_phys_cmd_underrun_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+
+	if (!phys_enc)
+		return;
+
+	if (phys_enc->parent_ops->handle_underrun_virt)
+		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
+			phys_enc);
+}
+
+static void _dpu_encoder_phys_cmd_setup_irq_hw_idx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_irq *irq;
+
+	irq = &phys_enc->irq[INTR_IDX_CTL_START];
+	irq->hw_idx = phys_enc->hw_ctl->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_PINGPONG];
+	irq->hw_idx = phys_enc->hw_pp->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_RDPTR];
+	irq->hw_idx = phys_enc->hw_pp->idx;
+	irq->irq_idx = -EINVAL;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->hw_idx = phys_enc->intf_idx;
+	irq->irq_idx = -EINVAL;
+}
+
+static void dpu_encoder_phys_cmd_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_rm *rm = &phys_enc->dpu_kms->rm;
+	struct dpu_rm_hw_iter iter;
+	int i, instance;
+
+	if (!phys_enc || !mode || !adj_mode) {
+		DPU_ERROR("invalid args\n");
+		return;
+	}
+	phys_enc->cached_mode = *adj_mode;
+	DPU_DEBUG_CMDENC(cmd_enc, "caching mode:\n");
+	drm_mode_debug_printmodeline(adj_mode);
+
+	instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0;
+
+	/* Retrieve previously allocated HW Resources. Shouldn't fail */
+	dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL);
+	for (i = 0; i <= instance; i++) {
+		if (dpu_rm_get_hw(rm, &iter))
+			phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw;
+	}
+
+	if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) {
+		DPU_ERROR_CMDENC(cmd_enc, "failed to init ctl: %ld\n",
+				PTR_ERR(phys_enc->hw_ctl));
+		phys_enc->hw_ctl = NULL;
+		return;
+	}
+
+	_dpu_encoder_phys_cmd_setup_irq_hw_idx(phys_enc);
+}
+
+static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	u32 frame_event = DPU_ENCODER_FRAME_EVENT_ERROR;
+	bool do_log = false;
+
+	if (!phys_enc || !phys_enc->hw_pp || !phys_enc->hw_ctl)
+		return -EINVAL;
+
+	cmd_enc->pp_timeout_report_cnt++;
+	if (cmd_enc->pp_timeout_report_cnt == PP_TIMEOUT_MAX_TRIALS) {
+		frame_event |= DPU_ENCODER_FRAME_EVENT_PANEL_DEAD;
+		do_log = true;
+	} else if (cmd_enc->pp_timeout_report_cnt == 1) {
+		do_log = true;
+	}
+
+	trace_dpu_enc_phys_cmd_pdone_timeout(DRMID(phys_enc->parent),
+		     phys_enc->hw_pp->idx - PINGPONG_0,
+		     cmd_enc->pp_timeout_report_cnt,
+		     atomic_read(&phys_enc->pending_kickoff_cnt),
+		     frame_event);
+
+	/* to avoid flooding, only log first time, and "dead" time */
+	if (do_log) {
+		DRM_ERROR("id:%d pp:%d kickoff timeout %d cnt %d koff_cnt %d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_pp->idx - PINGPONG_0,
+			  phys_enc->hw_ctl->idx - CTL_0,
+			  cmd_enc->pp_timeout_report_cnt,
+			  atomic_read(&phys_enc->pending_kickoff_cnt));
+
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_RDPTR);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+
+	atomic_add_unless(&phys_enc->pending_kickoff_cnt, -1, 0);
+
+	/* request a ctl reset before the next kickoff */
+	phys_enc->enable_state = DPU_ENC_ERR_NEEDS_HW_RESET;
+
+	if (phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc, frame_event);
+
+	return -ETIMEDOUT;
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_idle(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_PINGPONG,
+			&wait_info);
+	if (ret == -ETIMEDOUT)
+		_dpu_encoder_phys_cmd_handle_ppdone_timeout(phys_enc);
+	else if (!ret)
+		cmd_enc->pp_timeout_report_cnt = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	int refcount;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_KMS("id:%u pp:%d enable=%s/%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      enable ? "true" : "false", refcount);
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_RDPTR);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_encoder_helper_unregister_irq(phys_enc,
+				INTR_IDX_RDPTR);
+
+end:
+	if (ret) {
+		DRM_ERROR("vblank irq err id:%u pp:%d ret:%d, enable %s/%d\n",
+			  DRMID(phys_enc->parent),
+			  phys_enc->hw_pp->idx - PINGPONG_0, ret,
+			  enable ? "true" : "false", refcount);
+	}
+
+	return ret;
+}
+
+void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	trace_dpu_enc_phys_cmd_irq_ctrl(DRMID(phys_enc->parent),
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			enable, atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable) {
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_PINGPONG);
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, true);
+
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_encoder_helper_register_irq(phys_enc,
+					INTR_IDX_CTL_START);
+	} else {
+		if (dpu_encoder_phys_cmd_is_master(phys_enc))
+			dpu_encoder_helper_unregister_irq(phys_enc,
+					INTR_IDX_CTL_START);
+
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN);
+		dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, false);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_PINGPONG);
+	}
+}
+
+static void dpu_encoder_phys_cmd_tearcheck_config(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_hw_tear_check tc_cfg = { 0 };
+	struct drm_display_mode *mode;
+	bool tc_enable = true;
+	u32 vsync_hz;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	mode = &phys_enc->cached_mode;
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (!phys_enc->hw_pp->ops.setup_tearcheck ||
+		!phys_enc->hw_pp->ops.enable_tearcheck) {
+		DPU_DEBUG_CMDENC(cmd_enc, "tearcheck not supported\n");
+		return;
+	}
+
+	dpu_kms = phys_enc->dpu_kms;
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid device\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	/*
+	 * TE default: dsi byte clock calculated base on 70 fps;
+	 * around 14 ms to complete a kickoff cycle if te disabled;
+	 * vclk_line base on 60 fps; write is faster than read;
+	 * init == start == rdptr;
+	 *
+	 * vsync_count is ratio of MDP VSYNC clock frequency to LCD panel
+	 * frequency divided by the no. of rows (lines) in the LCDpanel.
+	 */
+	vsync_hz = dpu_kms_get_clk_rate(dpu_kms, "vsync_clk");
+	if (vsync_hz <= 0) {
+		DPU_DEBUG_CMDENC(cmd_enc, "invalid - vsync_hz %u\n",
+				 vsync_hz);
+		return;
+	}
+
+	tc_cfg.vsync_count = vsync_hz / (mode->vtotal * mode->vrefresh);
+
+	/* enable external TE after kickoff to avoid premature autorefresh */
+	tc_cfg.hw_vsync_mode = 0;
+
+	/*
+	 * By setting sync_cfg_height to near max register value, we essentially
+	 * disable dpu hw generated TE signal, since hw TE will arrive first.
+	 * Only caveat is if due to error, we hit wrap-around.
+	 */
+	tc_cfg.sync_cfg_height = 0xFFF0;
+	tc_cfg.vsync_init_val = mode->vdisplay;
+	tc_cfg.sync_threshold_start = DEFAULT_TEARCHECK_SYNC_THRESH_START;
+	tc_cfg.sync_threshold_continue = DEFAULT_TEARCHECK_SYNC_THRESH_CONTINUE;
+	tc_cfg.start_pos = mode->vdisplay;
+	tc_cfg.rd_ptr_irq = mode->vdisplay + 1;
+
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d vsync_clk_speed_hz %u vtotal %u vrefresh %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, vsync_hz,
+		mode->vtotal, mode->vrefresh);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d enable %u start_pos %u rd_ptr_irq %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_enable, tc_cfg.start_pos,
+		tc_cfg.rd_ptr_irq);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d hw_vsync_mode %u vsync_count %u vsync_init_val %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.hw_vsync_mode,
+		tc_cfg.vsync_count, tc_cfg.vsync_init_val);
+	DPU_DEBUG_CMDENC(cmd_enc,
+		"tc %d cfgheight %u thresh_start %u thresh_cont %u\n",
+		phys_enc->hw_pp->idx - PINGPONG_0, tc_cfg.sync_cfg_height,
+		tc_cfg.sync_threshold_start, tc_cfg.sync_threshold_continue);
+
+	phys_enc->hw_pp->ops.setup_tearcheck(phys_enc->hw_pp, &tc_cfg);
+	phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, tc_enable);
+}
+
+static void _dpu_encoder_phys_cmd_pingpong_config(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp
+			|| !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid arg(s), enc %d\n", phys_enc != 0);
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d, enabling mode:\n",
+			phys_enc->hw_pp->idx - PINGPONG_0);
+	drm_mode_debug_printmodeline(&phys_enc->cached_mode);
+
+	_dpu_encoder_phys_cmd_update_intf_cfg(phys_enc);
+	dpu_encoder_phys_cmd_tearcheck_config(phys_enc);
+}
+
+static bool dpu_encoder_phys_cmd_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	/**
+	 * we do separate flush for each CTL and let
+	 * CTL_START synchronize them
+	 */
+	return false;
+}
+
+static void dpu_encoder_phys_cmd_enable_helper(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_ctl *ctl;
+	u32 flush_mask = 0;
+
+	if (!phys_enc || !phys_enc->hw_ctl || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid arg(s), encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	dpu_encoder_helper_split_config(phys_enc, phys_enc->intf_idx);
+
+	_dpu_encoder_phys_cmd_pingpong_config(phys_enc);
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		goto skip_flush;
+
+	ctl = phys_enc->hw_ctl;
+	ctl->ops.get_bitmask_intf(ctl, &flush_mask, phys_enc->intf_idx);
+	ctl->ops.update_pending_flush(ctl, flush_mask);
+
+skip_flush:
+	return;
+}
+
+static void dpu_encoder_phys_cmd_enable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid phys encoder\n");
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp %d\n", phys_enc->hw_pp->idx - PINGPONG_0);
+
+	if (phys_enc->enable_state == DPU_ENC_ENABLED) {
+		DPU_ERROR("already enabled\n");
+		return;
+	}
+
+	dpu_encoder_phys_cmd_enable_helper(phys_enc);
+	phys_enc->enable_state = DPU_ENC_ENABLED;
+}
+
+static void _dpu_encoder_phys_cmd_connect_te(
+		struct dpu_encoder_phys *phys_enc, bool enable)
+{
+	if (!phys_enc || !phys_enc->hw_pp ||
+			!phys_enc->hw_pp->ops.connect_external_te)
+		return;
+
+	trace_dpu_enc_phys_cmd_connect_te(DRMID(phys_enc->parent), enable);
+	phys_enc->hw_pp->ops.connect_external_te(phys_enc->hw_pp, enable);
+}
+
+static void dpu_encoder_phys_cmd_prepare_idle_pc(
+		struct dpu_encoder_phys *phys_enc)
+{
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, false);
+}
+
+static int dpu_encoder_phys_cmd_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_hw_pingpong *hw_pp;
+
+	if (!phys_enc || !phys_enc->hw_pp)
+		return -EINVAL;
+
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return -EINVAL;
+
+	hw_pp = phys_enc->hw_pp;
+	if (!hw_pp->ops.get_line_count)
+		return -EINVAL;
+
+	return hw_pp->ops.get_line_count(hw_pp);
+}
+
+static void dpu_encoder_phys_cmd_disable(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d state:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      phys_enc->enable_state);
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR_CMDENC(cmd_enc, "already disabled\n");
+		return;
+	}
+
+	if (phys_enc->hw_pp->ops.enable_tearcheck)
+		phys_enc->hw_pp->ops.enable_tearcheck(phys_enc->hw_pp, false);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+static void dpu_encoder_phys_cmd_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	kfree(cmd_enc);
+}
+
+static void dpu_encoder_phys_cmd_get_hw_resources(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+		to_dpu_encoder_phys_cmd(phys_enc);
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	if ((phys_enc->intf_idx - INTF_0) >= INTF_MAX) {
+		DPU_ERROR("invalid intf idx:%d\n", phys_enc->intf_idx);
+		return;
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "\n");
+	hw_res->intfs[phys_enc->intf_idx - INTF_0] = INTF_MODE_CMD;
+}
+
+static void dpu_encoder_phys_cmd_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	int ret;
+
+	if (!phys_enc || !phys_enc->hw_pp) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+	DRM_DEBUG_KMS("id:%u pp:%d pending_cnt:%d\n", DRMID(phys_enc->parent),
+		      phys_enc->hw_pp->idx - PINGPONG_0,
+		      atomic_read(&phys_enc->pending_kickoff_cnt));
+
+	/*
+	 * Mark kickoff request as outstanding. If there are more than one,
+	 * outstanding, then we have to wait for the previous one to complete
+	 */
+	ret = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
+	if (ret) {
+		/* force pending_kickoff_cnt 0 to discard failed kickoff */
+		atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+		DRM_ERROR("failed wait_for_idle: id:%u ret:%d pp:%d\n",
+			  DRMID(phys_enc->parent), ret,
+			  phys_enc->hw_pp->idx - PINGPONG_0);
+	}
+
+	DPU_DEBUG_CMDENC(cmd_enc, "pp:%d pending_cnt %d\n",
+			phys_enc->hw_pp->idx - PINGPONG_0,
+			atomic_read(&phys_enc->pending_kickoff_cnt));
+}
+
+static int _dpu_encoder_phys_cmd_wait_for_ctl_start(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_cmd *cmd_enc =
+			to_dpu_encoder_phys_cmd(phys_enc);
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	if (!phys_enc || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid argument(s)\n");
+		return -EINVAL;
+	}
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_ctlstart_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_CTL_START,
+			&wait_info);
+	if (ret == -ETIMEDOUT) {
+		DPU_ERROR_CMDENC(cmd_enc, "ctl start interrupt wait failed\n");
+		ret = -EINVAL;
+	} else if (!ret)
+		ret = 0;
+
+	return ret;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_tx_complete(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	rc = _dpu_encoder_phys_cmd_wait_for_idle(phys_enc);
+	if (rc) {
+		DRM_ERROR("failed wait_for_idle: id:%u ret:%d intf:%d\n",
+			  DRMID(phys_enc->parent), rc,
+			  phys_enc->intf_idx - INTF_0);
+	}
+
+	return rc;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_commit_done(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc = 0;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	/* only required for master controller */
+	if (dpu_encoder_phys_cmd_is_master(phys_enc))
+		rc = _dpu_encoder_phys_cmd_wait_for_ctl_start(phys_enc);
+
+	/* required for both controllers */
+	if (!rc && cmd_enc->serialize_wait4pp)
+		dpu_encoder_phys_cmd_prepare_for_kickoff(phys_enc, NULL);
+
+	return rc;
+}
+
+static int dpu_encoder_phys_cmd_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	int rc = 0;
+	struct dpu_encoder_phys_cmd *cmd_enc;
+	struct dpu_encoder_wait_info wait_info;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	cmd_enc = to_dpu_encoder_phys_cmd(phys_enc);
+
+	/* only required for master controller */
+	if (!dpu_encoder_phys_cmd_is_master(phys_enc))
+		return rc;
+
+	wait_info.wq = &cmd_enc->pending_vblank_wq;
+	wait_info.atomic_cnt = &cmd_enc->pending_vblank_cnt;
+	wait_info.timeout_ms = _dpu_encoder_phys_cmd_get_idle_timeout(cmd_enc);
+
+	atomic_inc(&cmd_enc->pending_vblank_cnt);
+
+	rc = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_RDPTR,
+			&wait_info);
+
+	return rc;
+}
+
+static void dpu_encoder_phys_cmd_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return;
+
+	/**
+	 * re-enable external TE, either for the first time after enabling
+	 * or if disabled for Autorefresh
+	 */
+	_dpu_encoder_phys_cmd_connect_te(phys_enc, true);
+}
+
+static void dpu_encoder_phys_cmd_trigger_start(
+		struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return;
+
+	dpu_encoder_helper_trigger_start(phys_enc);
+}
+
+static void dpu_encoder_phys_cmd_init_ops(
+		struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_cmd_is_master;
+	ops->mode_set = dpu_encoder_phys_cmd_mode_set;
+	ops->mode_fixup = dpu_encoder_phys_cmd_mode_fixup;
+	ops->enable = dpu_encoder_phys_cmd_enable;
+	ops->disable = dpu_encoder_phys_cmd_disable;
+	ops->destroy = dpu_encoder_phys_cmd_destroy;
+	ops->get_hw_resources = dpu_encoder_phys_cmd_get_hw_resources;
+	ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_cmd_wait_for_commit_done;
+	ops->prepare_for_kickoff = dpu_encoder_phys_cmd_prepare_for_kickoff;
+	ops->wait_for_tx_complete = dpu_encoder_phys_cmd_wait_for_tx_complete;
+	ops->wait_for_vblank = dpu_encoder_phys_cmd_wait_for_vblank;
+	ops->trigger_start = dpu_encoder_phys_cmd_trigger_start;
+	ops->needs_single_flush = dpu_encoder_phys_cmd_needs_single_flush;
+	ops->hw_reset = dpu_encoder_helper_hw_reset;
+	ops->irq_control = dpu_encoder_phys_cmd_irq_control;
+	ops->restore = dpu_encoder_phys_cmd_enable_helper;
+	ops->prepare_idle_pc = dpu_encoder_phys_cmd_prepare_idle_pc;
+	ops->handle_post_kickoff = dpu_encoder_phys_cmd_handle_post_kickoff;
+	ops->get_line_count = dpu_encoder_phys_cmd_get_line_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_cmd *cmd_enc = NULL;
+	struct dpu_hw_mdp *hw_mdp;
+	struct dpu_encoder_irq *irq;
+	int i, ret = 0;
+
+	DPU_DEBUG("intf %d\n", p->intf_idx - INTF_0);
+
+	cmd_enc = kzalloc(sizeof(*cmd_enc), GFP_KERNEL);
+	if (!cmd_enc) {
+		ret = -ENOMEM;
+		DPU_ERROR("failed to allocate\n");
+		goto fail;
+	}
+	phys_enc = &cmd_enc->base;
+
+	hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm);
+	if (IS_ERR_OR_NULL(hw_mdp)) {
+		ret = PTR_ERR(hw_mdp);
+		DPU_ERROR("failed to get mdptop\n");
+		goto fail_mdp_init;
+	}
+	phys_enc->hw_mdptop = hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	dpu_encoder_phys_cmd_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_CMD;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	cmd_enc->stream_sel = 0;
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+	for (i = 0; i < INTR_IDX_MAX; i++) {
+		irq = &phys_enc->irq[i];
+		INIT_LIST_HEAD(&irq->cb.list);
+		irq->irq_idx = -EINVAL;
+		irq->hw_idx = -EINVAL;
+		irq->cb.arg = phys_enc;
+	}
+
+	irq = &phys_enc->irq[INTR_IDX_CTL_START];
+	irq->name = "ctl_start";
+	irq->intr_type = DPU_IRQ_TYPE_CTL_START;
+	irq->intr_idx = INTR_IDX_CTL_START;
+	irq->cb.func = dpu_encoder_phys_cmd_ctl_start_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_PINGPONG];
+	irq->name = "pp_done";
+	irq->intr_type = DPU_IRQ_TYPE_PING_PONG_COMP;
+	irq->intr_idx = INTR_IDX_PINGPONG;
+	irq->cb.func = dpu_encoder_phys_cmd_pp_tx_done_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_RDPTR];
+	irq->name = "pp_rd_ptr";
+	irq->intr_type = DPU_IRQ_TYPE_PING_PONG_RD_PTR;
+	irq->intr_idx = INTR_IDX_RDPTR;
+	irq->cb.func = dpu_encoder_phys_cmd_pp_rd_ptr_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->name = "underrun";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN;
+	irq->intr_idx = INTR_IDX_UNDERRUN;
+	irq->cb.func = dpu_encoder_phys_cmd_underrun_irq;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	atomic_set(&phys_enc->pending_ctlstart_cnt, 0);
+	atomic_set(&cmd_enc->pending_vblank_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	init_waitqueue_head(&cmd_enc->pending_vblank_wq);
+
+	DPU_DEBUG_CMDENC(cmd_enc, "created\n");
+
+	return phys_enc;
+
+fail_mdp_init:
+	kfree(cmd_enc);
+fail:
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
new file mode 100644
index 000000000000..14fc7c2a6bb7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
@@ -0,0 +1,922 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_trace.h"
+
+#define DPU_DEBUG_VIDENC(e, fmt, ...) DPU_DEBUG("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_VIDENC(e, fmt, ...) DPU_ERROR("enc%d intf%d " fmt, \
+		(e) && (e)->base.parent ? \
+		(e)->base.parent->base.id : -1, \
+		(e) && (e)->hw_intf ? \
+		(e)->hw_intf->idx - INTF_0 : -1, ##__VA_ARGS__)
+
+#define to_dpu_encoder_phys_vid(x) \
+	container_of(x, struct dpu_encoder_phys_vid, base)
+
+static bool dpu_encoder_phys_vid_is_master(
+		struct dpu_encoder_phys *phys_enc)
+{
+	bool ret = false;
+
+	if (phys_enc->split_role != ENC_ROLE_SLAVE)
+		ret = true;
+
+	return ret;
+}
+
+static void drm_mode_to_intf_timing_params(
+		const struct dpu_encoder_phys_vid *vid_enc,
+		const struct drm_display_mode *mode,
+		struct intf_timing_params *timing)
+{
+	memset(timing, 0, sizeof(*timing));
+
+	if ((mode->htotal < mode->hsync_end)
+			|| (mode->hsync_start < mode->hdisplay)
+			|| (mode->vtotal < mode->vsync_end)
+			|| (mode->vsync_start < mode->vdisplay)
+			|| (mode->hsync_end < mode->hsync_start)
+			|| (mode->vsync_end < mode->vsync_start)) {
+		DPU_ERROR(
+		    "invalid params - hstart:%d,hend:%d,htot:%d,hdisplay:%d\n",
+				mode->hsync_start, mode->hsync_end,
+				mode->htotal, mode->hdisplay);
+		DPU_ERROR("vstart:%d,vend:%d,vtot:%d,vdisplay:%d\n",
+				mode->vsync_start, mode->vsync_end,
+				mode->vtotal, mode->vdisplay);
+		return;
+	}
+
+	/*
+	 * https://www.kernel.org/doc/htmldocs/drm/ch02s05.html
+	 *  Active Region      Front Porch   Sync   Back Porch
+	 * <-----------------><------------><-----><----------->
+	 * <- [hv]display --->
+	 * <--------- [hv]sync_start ------>
+	 * <----------------- [hv]sync_end ------->
+	 * <---------------------------- [hv]total ------------->
+	 */
+	timing->width = mode->hdisplay;	/* active width */
+	timing->height = mode->vdisplay;	/* active height */
+	timing->xres = timing->width;
+	timing->yres = timing->height;
+	timing->h_back_porch = mode->htotal - mode->hsync_end;
+	timing->h_front_porch = mode->hsync_start - mode->hdisplay;
+	timing->v_back_porch = mode->vtotal - mode->vsync_end;
+	timing->v_front_porch = mode->vsync_start - mode->vdisplay;
+	timing->hsync_pulse_width = mode->hsync_end - mode->hsync_start;
+	timing->vsync_pulse_width = mode->vsync_end - mode->vsync_start;
+	timing->hsync_polarity = (mode->flags & DRM_MODE_FLAG_NHSYNC) ? 1 : 0;
+	timing->vsync_polarity = (mode->flags & DRM_MODE_FLAG_NVSYNC) ? 1 : 0;
+	timing->border_clr = 0;
+	timing->underflow_clr = 0xff;
+	timing->hsync_skew = mode->hskew;
+
+	/* DSI controller cannot handle active-low sync signals. */
+	if (vid_enc->hw_intf->cap->type == INTF_DSI) {
+		timing->hsync_polarity = 0;
+		timing->vsync_polarity = 0;
+	}
+
+	/*
+	 * For edp only:
+	 * DISPLAY_V_START = (VBP * HCYCLE) + HBP
+	 * DISPLAY_V_END = (VBP + VACTIVE) * HCYCLE - 1 - HFP
+	 */
+	/*
+	 * if (vid_enc->hw->cap->type == INTF_EDP) {
+	 * display_v_start += mode->htotal - mode->hsync_start;
+	 * display_v_end -= mode->hsync_start - mode->hdisplay;
+	 * }
+	 */
+}
+
+static inline u32 get_horizontal_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->xres;
+	u32 inactive =
+	    timing->h_back_porch + timing->h_front_porch +
+	    timing->hsync_pulse_width;
+	return active + inactive;
+}
+
+static inline u32 get_vertical_total(const struct intf_timing_params *timing)
+{
+	u32 active = timing->yres;
+	u32 inactive =
+	    timing->v_back_porch + timing->v_front_porch +
+	    timing->vsync_pulse_width;
+	return active + inactive;
+}
+
+/*
+ * programmable_fetch_get_num_lines:
+ *	Number of fetch lines in vertical front porch
+ * @timing: Pointer to the intf timing information for the requested mode
+ *
+ * Returns the number of fetch lines in vertical front porch at which mdp
+ * can start fetching the next frame.
+ *
+ * Number of needed prefetch lines is anything that cannot be absorbed in the
+ * start of frame time (back porch + vsync pulse width).
+ *
+ * Some panels have very large VFP, however we only need a total number of
+ * lines based on the chip worst case latencies.
+ */
+static u32 programmable_fetch_get_num_lines(
+		struct dpu_encoder_phys_vid *vid_enc,
+		const struct intf_timing_params *timing)
+{
+	u32 worst_case_needed_lines =
+	    vid_enc->hw_intf->cap->prog_fetch_lines_worst_case;
+	u32 start_of_frame_lines =
+	    timing->v_back_porch + timing->vsync_pulse_width;
+	u32 needed_vfp_lines = worst_case_needed_lines - start_of_frame_lines;
+	u32 actual_vfp_lines = 0;
+
+	/* Fetch must be outside active lines, otherwise undefined. */
+	if (start_of_frame_lines >= worst_case_needed_lines) {
+		DPU_DEBUG_VIDENC(vid_enc,
+				"prog fetch is not needed, large vbp+vsw\n");
+		actual_vfp_lines = 0;
+	} else if (timing->v_front_porch < needed_vfp_lines) {
+		/* Warn fetch needed, but not enough porch in panel config */
+		pr_warn_once
+			("low vbp+vfp may lead to perf issues in some cases\n");
+		DPU_DEBUG_VIDENC(vid_enc,
+				"less vfp than fetch req, using entire vfp\n");
+		actual_vfp_lines = timing->v_front_porch;
+	} else {
+		DPU_DEBUG_VIDENC(vid_enc, "room in vfp for needed prefetch\n");
+		actual_vfp_lines = needed_vfp_lines;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc,
+		"v_front_porch %u v_back_porch %u vsync_pulse_width %u\n",
+		timing->v_front_porch, timing->v_back_porch,
+		timing->vsync_pulse_width);
+	DPU_DEBUG_VIDENC(vid_enc,
+		"wc_lines %u needed_vfp_lines %u actual_vfp_lines %u\n",
+		worst_case_needed_lines, needed_vfp_lines, actual_vfp_lines);
+
+	return actual_vfp_lines;
+}
+
+/*
+ * programmable_fetch_config: Programs HW to prefetch lines by offsetting
+ *	the start of fetch into the vertical front porch for cases where the
+ *	vsync pulse width and vertical back porch time is insufficient
+ *
+ *	Gets # of lines to pre-fetch, then calculate VSYNC counter value.
+ *	HW layer requires VSYNC counter of first pixel of tgt VFP line.
+ *
+ * @timing: Pointer to the intf timing information for the requested mode
+ */
+static void programmable_fetch_config(struct dpu_encoder_phys *phys_enc,
+				      const struct intf_timing_params *timing)
+{
+	struct dpu_encoder_phys_vid *vid_enc =
+		to_dpu_encoder_phys_vid(phys_enc);
+	struct intf_prog_fetch f = { 0 };
+	u32 vfp_fetch_lines = 0;
+	u32 horiz_total = 0;
+	u32 vert_total = 0;
+	u32 vfp_fetch_start_vsync_counter = 0;
+	unsigned long lock_flags;
+
+	if (WARN_ON_ONCE(!vid_enc->hw_intf->ops.setup_prg_fetch))
+		return;
+
+	vfp_fetch_lines = programmable_fetch_get_num_lines(vid_enc, timing);
+	if (vfp_fetch_lines) {
+		vert_total = get_vertical_total(timing);
+		horiz_total = get_horizontal_total(timing);
+		vfp_fetch_start_vsync_counter =
+		    (vert_total - vfp_fetch_lines) * horiz_total + 1;
+		f.enable = 1;
+		f.fetch_start = vfp_fetch_start_vsync_counter;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc,
+		"vfp_fetch_lines %u vfp_fetch_start_vsync_counter %u\n",
+		vfp_fetch_lines, vfp_fetch_start_vsync_counter);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.setup_prg_fetch(vid_enc->hw_intf, &f);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+}
+
+static bool dpu_encoder_phys_vid_mode_fixup(
+		struct dpu_encoder_phys *phys_enc,
+		const struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	if (phys_enc)
+		DPU_DEBUG_VIDENC(to_dpu_encoder_phys_vid(phys_enc), "\n");
+
+	/*
+	 * Modifying mode has consequences when the mode comes back to us
+	 */
+	return true;
+}
+
+static void dpu_encoder_phys_vid_setup_timing_engine(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct drm_display_mode mode;
+	struct intf_timing_params timing_params = { 0 };
+	const struct dpu_format *fmt = NULL;
+	u32 fmt_fourcc = DRM_FORMAT_RGB888;
+	unsigned long lock_flags;
+	struct dpu_hw_intf_cfg intf_cfg = { 0 };
+
+	if (!phys_enc || !phys_enc->hw_ctl->ops.setup_intf_cfg) {
+		DPU_ERROR("invalid encoder %d\n", phys_enc != 0);
+		return;
+	}
+
+	mode = phys_enc->cached_mode;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf->ops.setup_timing_gen) {
+		DPU_ERROR("timing engine setup is not supported\n");
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "enabling mode:\n");
+	drm_mode_debug_printmodeline(&mode);
+
+	if (phys_enc->split_role != ENC_ROLE_SOLO) {
+		mode.hdisplay >>= 1;
+		mode.htotal >>= 1;
+		mode.hsync_start >>= 1;
+		mode.hsync_end >>= 1;
+
+		DPU_DEBUG_VIDENC(vid_enc,
+			"split_role %d, halve horizontal %d %d %d %d\n",
+			phys_enc->split_role,
+			mode.hdisplay, mode.htotal,
+			mode.hsync_start, mode.hsync_end);
+	}
+
+	drm_mode_to_intf_timing_params(vid_enc, &mode, &timing_params);
+
+	fmt = dpu_get_dpu_format(fmt_fourcc);
+	DPU_DEBUG_VIDENC(vid_enc, "fmt_fourcc 0x%X\n", fmt_fourcc);
+
+	intf_cfg.intf = vid_enc->hw_intf->idx;
+	intf_cfg.intf_mode_sel = DPU_CTL_MODE_SEL_VID;
+	intf_cfg.stream_sel = 0; /* Don't care value for video mode */
+	intf_cfg.mode_3d = dpu_encoder_helper_get_3d_blend_mode(phys_enc);
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.setup_timing_gen(vid_enc->hw_intf,
+			&timing_params, fmt);
+	phys_enc->hw_ctl->ops.setup_intf_cfg(phys_enc->hw_ctl, &intf_cfg);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	programmable_fetch_config(phys_enc, &timing_params);
+
+	vid_enc->timing_params = timing_params;
+}
+
+static void dpu_encoder_phys_vid_vblank_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+	struct dpu_hw_ctl *hw_ctl;
+	unsigned long lock_flags;
+	u32 flush_register = 0;
+	int new_cnt = -1, old_cnt = -1;
+
+	if (!phys_enc)
+		return;
+
+	hw_ctl = phys_enc->hw_ctl;
+	if (!hw_ctl)
+		return;
+
+	DPU_ATRACE_BEGIN("vblank_irq");
+
+	if (phys_enc->parent_ops->handle_vblank_virt)
+		phys_enc->parent_ops->handle_vblank_virt(phys_enc->parent,
+				phys_enc);
+
+	old_cnt  = atomic_read(&phys_enc->pending_kickoff_cnt);
+
+	/*
+	 * only decrement the pending flush count if we've actually flushed
+	 * hardware. due to sw irq latency, vblank may have already happened
+	 * so we need to double-check with hw that it accepted the flush bits
+	 */
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	if (hw_ctl && hw_ctl->ops.get_flush_register)
+		flush_register = hw_ctl->ops.get_flush_register(hw_ctl);
+
+	if (flush_register == 0)
+		new_cnt = atomic_add_unless(&phys_enc->pending_kickoff_cnt,
+				-1, 0);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/* Signal any waiting atomic commit thread */
+	wake_up_all(&phys_enc->pending_kickoff_wq);
+	DPU_ATRACE_END("vblank_irq");
+}
+
+static void dpu_encoder_phys_vid_underrun_irq(void *arg, int irq_idx)
+{
+	struct dpu_encoder_phys *phys_enc = arg;
+
+	if (!phys_enc)
+		return;
+
+	if (phys_enc->parent_ops->handle_underrun_virt)
+		phys_enc->parent_ops->handle_underrun_virt(phys_enc->parent,
+			phys_enc);
+}
+
+static bool _dpu_encoder_phys_is_dual_ctl(struct dpu_encoder_phys *phys_enc)
+{
+	if (!phys_enc)
+		return false;
+
+	if (phys_enc->topology_name == DPU_RM_TOPOLOGY_DUALPIPE)
+		return true;
+
+	return false;
+}
+
+static bool dpu_encoder_phys_vid_needs_single_flush(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return (phys_enc && _dpu_encoder_phys_is_dual_ctl(phys_enc));
+}
+
+static void _dpu_encoder_phys_vid_setup_irq_hw_idx(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_irq *irq;
+
+	/*
+	 * Initialize irq->hw_idx only when irq is not registered.
+	 * Prevent invalidating irq->irq_idx as modeset may be
+	 * called many times during dfps.
+	 */
+
+	irq = &phys_enc->irq[INTR_IDX_VSYNC];
+	if (irq->irq_idx < 0)
+		irq->hw_idx = phys_enc->intf_idx;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	if (irq->irq_idx < 0)
+		irq->hw_idx = phys_enc->intf_idx;
+}
+
+static void dpu_encoder_phys_vid_mode_set(
+		struct dpu_encoder_phys *phys_enc,
+		struct drm_display_mode *mode,
+		struct drm_display_mode *adj_mode)
+{
+	struct dpu_rm *rm;
+	struct dpu_rm_hw_iter iter;
+	int i, instance;
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc || !phys_enc->dpu_kms) {
+		DPU_ERROR("invalid encoder/kms\n");
+		return;
+	}
+
+	rm = &phys_enc->dpu_kms->rm;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	if (adj_mode) {
+		phys_enc->cached_mode = *adj_mode;
+		drm_mode_debug_printmodeline(adj_mode);
+		DPU_DEBUG_VIDENC(vid_enc, "caching mode:\n");
+	}
+
+	instance = phys_enc->split_role == ENC_ROLE_SLAVE ? 1 : 0;
+
+	/* Retrieve previously allocated HW Resources. Shouldn't fail */
+	dpu_rm_init_hw_iter(&iter, phys_enc->parent->base.id, DPU_HW_BLK_CTL);
+	for (i = 0; i <= instance; i++) {
+		if (dpu_rm_get_hw(rm, &iter))
+			phys_enc->hw_ctl = (struct dpu_hw_ctl *)iter.hw;
+	}
+	if (IS_ERR_OR_NULL(phys_enc->hw_ctl)) {
+		DPU_ERROR_VIDENC(vid_enc, "failed to init ctl, %ld\n",
+				PTR_ERR(phys_enc->hw_ctl));
+		phys_enc->hw_ctl = NULL;
+		return;
+	}
+
+	_dpu_encoder_phys_vid_setup_irq_hw_idx(phys_enc);
+}
+
+static int dpu_encoder_phys_vid_control_vblank_irq(
+		struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	int ret = 0;
+	struct dpu_encoder_phys_vid *vid_enc;
+	int refcount;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	refcount = atomic_read(&phys_enc->vblank_refcount);
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	/* Slave encoders don't report vblank */
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto end;
+
+	/* protect against negative */
+	if (!enable && refcount == 0) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	DRM_DEBUG_KMS("id:%u enable=%d/%d\n", DRMID(phys_enc->parent), enable,
+		      atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable && atomic_inc_return(&phys_enc->vblank_refcount) == 1)
+		ret = dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_VSYNC);
+	else if (!enable && atomic_dec_return(&phys_enc->vblank_refcount) == 0)
+		ret = dpu_encoder_helper_unregister_irq(phys_enc,
+				INTR_IDX_VSYNC);
+
+end:
+	if (ret) {
+		DRM_ERROR("failed: id:%u intf:%d ret:%d enable:%d refcnt:%d\n",
+			  DRMID(phys_enc->parent),
+			  vid_enc->hw_intf->idx - INTF_0, ret, enable,
+			  refcount);
+	}
+	return ret;
+}
+
+static void dpu_encoder_phys_vid_enable(struct dpu_encoder_phys *phys_enc)
+{
+	struct msm_drm_private *priv;
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct dpu_hw_intf *intf;
+	struct dpu_hw_ctl *ctl;
+	u32 flush_mask = 0;
+
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
+			!phys_enc->parent->dev->dev_private) {
+		DPU_ERROR("invalid encoder/device\n");
+		return;
+	}
+	priv = phys_enc->parent->dev->dev_private;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	intf = vid_enc->hw_intf;
+	ctl = phys_enc->hw_ctl;
+	if (!vid_enc->hw_intf || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
+				vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing))
+		return;
+
+	dpu_encoder_helper_split_config(phys_enc, vid_enc->hw_intf->idx);
+
+	dpu_encoder_phys_vid_setup_timing_engine(phys_enc);
+
+	/*
+	 * For single flush cases (dual-ctl or pp-split), skip setting the
+	 * flush bit for the slave intf, since both intfs use same ctl
+	 * and HW will only flush the master.
+	 */
+	if (dpu_encoder_phys_vid_needs_single_flush(phys_enc) &&
+		!dpu_encoder_phys_vid_is_master(phys_enc))
+		goto skip_flush;
+
+	ctl->ops.get_bitmask_intf(ctl, &flush_mask, intf->idx);
+	ctl->ops.update_pending_flush(ctl, flush_mask);
+
+skip_flush:
+	DPU_DEBUG_VIDENC(vid_enc, "update pending flush ctl %d flush_mask %x\n",
+		ctl->idx - CTL_0, flush_mask);
+
+	/* ctl_flush & timing engine enable will be triggered by framework */
+	if (phys_enc->enable_state == DPU_ENC_DISABLED)
+		phys_enc->enable_state = DPU_ENC_ENABLING;
+}
+
+static void dpu_encoder_phys_vid_destroy(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+	kfree(vid_enc);
+}
+
+static void dpu_encoder_phys_vid_get_hw_resources(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_hw_resources *hw_res,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc || !hw_res) {
+		DPU_ERROR("invalid arg(s), enc %d hw_res %d conn_state %d\n",
+				phys_enc != 0, hw_res != 0, conn_state != 0);
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf) {
+		DPU_ERROR("invalid arg(s), hw_intf\n");
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+	hw_res->intfs[vid_enc->hw_intf->idx - INTF_0] = INTF_MODE_VIDEO;
+}
+
+static int _dpu_encoder_phys_vid_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc, bool notify)
+{
+	struct dpu_encoder_wait_info wait_info;
+	int ret;
+
+	if (!phys_enc) {
+		pr_err("invalid encoder\n");
+		return -EINVAL;
+	}
+
+	wait_info.wq = &phys_enc->pending_kickoff_wq;
+	wait_info.atomic_cnt = &phys_enc->pending_kickoff_cnt;
+	wait_info.timeout_ms = KICKOFF_TIMEOUT_MS;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc)) {
+		if (notify && phys_enc->parent_ops->handle_frame_done)
+			phys_enc->parent_ops->handle_frame_done(
+					phys_enc->parent, phys_enc,
+					DPU_ENCODER_FRAME_EVENT_DONE);
+		return 0;
+	}
+
+	/* Wait for kickoff to complete */
+	ret = dpu_encoder_helper_wait_for_irq(phys_enc, INTR_IDX_VSYNC,
+			&wait_info);
+
+	if (ret == -ETIMEDOUT) {
+		dpu_encoder_helper_report_irq_timeout(phys_enc, INTR_IDX_VSYNC);
+	} else if (!ret && notify && phys_enc->parent_ops->handle_frame_done)
+		phys_enc->parent_ops->handle_frame_done(
+				phys_enc->parent, phys_enc,
+				DPU_ENCODER_FRAME_EVENT_DONE);
+
+	return ret;
+}
+
+static int dpu_encoder_phys_vid_wait_for_vblank(
+		struct dpu_encoder_phys *phys_enc)
+{
+	return _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, true);
+}
+
+static void dpu_encoder_phys_vid_prepare_for_kickoff(
+		struct dpu_encoder_phys *phys_enc,
+		struct dpu_encoder_kickoff_params *params)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	struct dpu_hw_ctl *ctl;
+	int rc;
+
+	if (!phys_enc || !params) {
+		DPU_ERROR("invalid encoder/parameters\n");
+		return;
+	}
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	ctl = phys_enc->hw_ctl;
+	if (!ctl || !ctl->ops.wait_reset_status)
+		return;
+
+	/*
+	 * hw supports hardware initiated ctl reset, so before we kickoff a new
+	 * frame, need to check and wait for hw initiated ctl reset completion
+	 */
+	rc = ctl->ops.wait_reset_status(ctl);
+	if (rc) {
+		DPU_ERROR_VIDENC(vid_enc, "ctl %d reset failure: %d\n",
+				ctl->idx, rc);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_VSYNC);
+		dpu_dbg_dump(false, __func__, true, true);
+	}
+}
+
+static void dpu_encoder_phys_vid_disable(struct dpu_encoder_phys *phys_enc)
+{
+	struct msm_drm_private *priv;
+	struct dpu_encoder_phys_vid *vid_enc;
+	unsigned long lock_flags;
+	int ret;
+
+	if (!phys_enc || !phys_enc->parent || !phys_enc->parent->dev ||
+			!phys_enc->parent->dev->dev_private) {
+		DPU_ERROR("invalid encoder/device\n");
+		return;
+	}
+	priv = phys_enc->parent->dev->dev_private;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf || !phys_enc->hw_ctl) {
+		DPU_ERROR("invalid hw_intf %d hw_ctl %d\n",
+				vid_enc->hw_intf != 0, phys_enc->hw_ctl != 0);
+		return;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	if (WARN_ON(!vid_enc->hw_intf->ops.enable_timing))
+		return;
+
+	if (phys_enc->enable_state == DPU_ENC_DISABLED) {
+		DPU_ERROR("already disabled\n");
+		return;
+	}
+
+	spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+	vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 0);
+	if (dpu_encoder_phys_vid_is_master(phys_enc))
+		dpu_encoder_phys_inc_pending(phys_enc);
+	spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+
+	/*
+	 * Wait for a vsync so we know the ENABLE=0 latched before
+	 * the (connector) source of the vsync's gets disabled,
+	 * otherwise we end up in a funny state if we re-enable
+	 * before the disable latches, which results that some of
+	 * the settings changes for the new modeset (like new
+	 * scanout buffer) don't latch properly..
+	 */
+	if (dpu_encoder_phys_vid_is_master(phys_enc)) {
+		ret = _dpu_encoder_phys_vid_wait_for_vblank(phys_enc, false);
+		if (ret) {
+			atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+			DRM_ERROR("wait disable failed: id:%u intf:%d ret:%d\n",
+				  DRMID(phys_enc->parent),
+				  vid_enc->hw_intf->idx - INTF_0, ret);
+		}
+	}
+
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+}
+
+static void dpu_encoder_phys_vid_handle_post_kickoff(
+		struct dpu_encoder_phys *phys_enc)
+{
+	unsigned long lock_flags;
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc) {
+		DPU_ERROR("invalid encoder\n");
+		return;
+	}
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	DPU_DEBUG_VIDENC(vid_enc, "enable_state %d\n", phys_enc->enable_state);
+
+	/*
+	 * Video mode must flush CTL before enabling timing engine
+	 * Video encoders need to turn on their interfaces now
+	 */
+	if (phys_enc->enable_state == DPU_ENC_ENABLING) {
+		trace_dpu_enc_phys_vid_post_kickoff(DRMID(phys_enc->parent),
+				    vid_enc->hw_intf->idx - INTF_0);
+		spin_lock_irqsave(phys_enc->enc_spinlock, lock_flags);
+		vid_enc->hw_intf->ops.enable_timing(vid_enc->hw_intf, 1);
+		spin_unlock_irqrestore(phys_enc->enc_spinlock, lock_flags);
+		phys_enc->enable_state = DPU_ENC_ENABLED;
+	}
+}
+
+static void dpu_encoder_phys_vid_irq_control(struct dpu_encoder_phys *phys_enc,
+		bool enable)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+	int ret;
+
+	if (!phys_enc)
+		return;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	trace_dpu_enc_phys_vid_irq_ctrl(DRMID(phys_enc->parent),
+			    vid_enc->hw_intf->idx - INTF_0,
+			    enable,
+			    atomic_read(&phys_enc->vblank_refcount));
+
+	if (enable) {
+		ret = dpu_encoder_phys_vid_control_vblank_irq(phys_enc, true);
+		if (ret)
+			return;
+
+		dpu_encoder_helper_register_irq(phys_enc, INTR_IDX_UNDERRUN);
+	} else {
+		dpu_encoder_phys_vid_control_vblank_irq(phys_enc, false);
+		dpu_encoder_helper_unregister_irq(phys_enc, INTR_IDX_UNDERRUN);
+	}
+}
+
+static void dpu_encoder_phys_vid_setup_misr(struct dpu_encoder_phys *phys_enc,
+						bool enable, u32 frame_count)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	if (vid_enc->hw_intf && vid_enc->hw_intf->ops.setup_misr)
+		vid_enc->hw_intf->ops.setup_misr(vid_enc->hw_intf,
+							enable, frame_count);
+}
+
+static u32 dpu_encoder_phys_vid_collect_misr(struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return 0;
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+
+	return vid_enc->hw_intf && vid_enc->hw_intf->ops.collect_misr ?
+		vid_enc->hw_intf->ops.collect_misr(vid_enc->hw_intf) : 0;
+}
+
+static int dpu_encoder_phys_vid_get_line_count(
+		struct dpu_encoder_phys *phys_enc)
+{
+	struct dpu_encoder_phys_vid *vid_enc;
+
+	if (!phys_enc)
+		return -EINVAL;
+
+	if (!dpu_encoder_phys_vid_is_master(phys_enc))
+		return -EINVAL;
+
+	vid_enc = to_dpu_encoder_phys_vid(phys_enc);
+	if (!vid_enc->hw_intf || !vid_enc->hw_intf->ops.get_line_count)
+		return -EINVAL;
+
+	return vid_enc->hw_intf->ops.get_line_count(vid_enc->hw_intf);
+}
+
+static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops)
+{
+	ops->is_master = dpu_encoder_phys_vid_is_master;
+	ops->mode_set = dpu_encoder_phys_vid_mode_set;
+	ops->mode_fixup = dpu_encoder_phys_vid_mode_fixup;
+	ops->enable = dpu_encoder_phys_vid_enable;
+	ops->disable = dpu_encoder_phys_vid_disable;
+	ops->destroy = dpu_encoder_phys_vid_destroy;
+	ops->get_hw_resources = dpu_encoder_phys_vid_get_hw_resources;
+	ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq;
+	ops->wait_for_commit_done = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->wait_for_vblank = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->wait_for_tx_complete = dpu_encoder_phys_vid_wait_for_vblank;
+	ops->irq_control = dpu_encoder_phys_vid_irq_control;
+	ops->prepare_for_kickoff = dpu_encoder_phys_vid_prepare_for_kickoff;
+	ops->handle_post_kickoff = dpu_encoder_phys_vid_handle_post_kickoff;
+	ops->needs_single_flush = dpu_encoder_phys_vid_needs_single_flush;
+	ops->setup_misr = dpu_encoder_phys_vid_setup_misr;
+	ops->collect_misr = dpu_encoder_phys_vid_collect_misr;
+	ops->hw_reset = dpu_encoder_helper_hw_reset;
+	ops->get_line_count = dpu_encoder_phys_vid_get_line_count;
+}
+
+struct dpu_encoder_phys *dpu_encoder_phys_vid_init(
+		struct dpu_enc_phys_init_params *p)
+{
+	struct dpu_encoder_phys *phys_enc = NULL;
+	struct dpu_encoder_phys_vid *vid_enc = NULL;
+	struct dpu_rm_hw_iter iter;
+	struct dpu_hw_mdp *hw_mdp;
+	struct dpu_encoder_irq *irq;
+	int i, ret = 0;
+
+	if (!p) {
+		ret = -EINVAL;
+		goto fail;
+	}
+
+	vid_enc = kzalloc(sizeof(*vid_enc), GFP_KERNEL);
+	if (!vid_enc) {
+		ret = -ENOMEM;
+		goto fail;
+	}
+
+	phys_enc = &vid_enc->base;
+
+	hw_mdp = dpu_rm_get_mdp(&p->dpu_kms->rm);
+	if (IS_ERR_OR_NULL(hw_mdp)) {
+		ret = PTR_ERR(hw_mdp);
+		DPU_ERROR("failed to get mdptop\n");
+		goto fail;
+	}
+	phys_enc->hw_mdptop = hw_mdp;
+	phys_enc->intf_idx = p->intf_idx;
+
+	/**
+	 * hw_intf resource permanently assigned to this encoder
+	 * Other resources allocated at atomic commit time by use case
+	 */
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_INTF);
+	while (dpu_rm_get_hw(&p->dpu_kms->rm, &iter)) {
+		struct dpu_hw_intf *hw_intf = (struct dpu_hw_intf *)iter.hw;
+
+		if (hw_intf->idx == p->intf_idx) {
+			vid_enc->hw_intf = hw_intf;
+			break;
+		}
+	}
+
+	if (!vid_enc->hw_intf) {
+		ret = -EINVAL;
+		DPU_ERROR("failed to get hw_intf\n");
+		goto fail;
+	}
+
+	DPU_DEBUG_VIDENC(vid_enc, "\n");
+
+	dpu_encoder_phys_vid_init_ops(&phys_enc->ops);
+	phys_enc->parent = p->parent;
+	phys_enc->parent_ops = p->parent_ops;
+	phys_enc->dpu_kms = p->dpu_kms;
+	phys_enc->split_role = p->split_role;
+	phys_enc->intf_mode = INTF_MODE_VIDEO;
+	phys_enc->enc_spinlock = p->enc_spinlock;
+	for (i = 0; i < INTR_IDX_MAX; i++) {
+		irq = &phys_enc->irq[i];
+		INIT_LIST_HEAD(&irq->cb.list);
+		irq->irq_idx = -EINVAL;
+		irq->hw_idx = -EINVAL;
+		irq->cb.arg = phys_enc;
+	}
+
+	irq = &phys_enc->irq[INTR_IDX_VSYNC];
+	irq->name = "vsync_irq";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_VSYNC;
+	irq->intr_idx = INTR_IDX_VSYNC;
+	irq->cb.func = dpu_encoder_phys_vid_vblank_irq;
+
+	irq = &phys_enc->irq[INTR_IDX_UNDERRUN];
+	irq->name = "underrun";
+	irq->intr_type = DPU_IRQ_TYPE_INTF_UNDER_RUN;
+	irq->intr_idx = INTR_IDX_UNDERRUN;
+	irq->cb.func = dpu_encoder_phys_vid_underrun_irq;
+
+	atomic_set(&phys_enc->vblank_refcount, 0);
+	atomic_set(&phys_enc->pending_kickoff_cnt, 0);
+	init_waitqueue_head(&phys_enc->pending_kickoff_wq);
+	phys_enc->enable_state = DPU_ENC_DISABLED;
+
+	DPU_DEBUG_VIDENC(vid_enc, "created intf idx:%d\n", p->intf_idx);
+
+	return phys_enc;
+
+fail:
+	DPU_ERROR("failed to create encoder\n");
+	if (vid_enc)
+		dpu_encoder_phys_vid_destroy(phys_enc);
+
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
new file mode 100644
index 000000000000..8189539b0620
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -0,0 +1,1214 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <uapi/drm/drm_fourcc.h>
+
+#include "msm_media_info.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+
+#define DPU_UBWC_META_MACRO_W_H		16
+#define DPU_UBWC_META_BLOCK_SIZE	256
+#define DPU_UBWC_PLANE_SIZE_ALIGNMENT	4096
+
+#define DPU_TILE_HEIGHT_DEFAULT	1
+#define DPU_TILE_HEIGHT_TILED	4
+#define DPU_TILE_HEIGHT_UBWC	4
+#define DPU_TILE_HEIGHT_NV12	8
+
+#define DPU_MAX_IMG_WIDTH		0x3FFF
+#define DPU_MAX_IMG_HEIGHT		0x3FFF
+
+/**
+ * DPU supported format packing, bpp, and other format
+ * information.
+ * DPU currently only supports interleaved RGB formats
+ * UBWC support for a pixel format is indicated by the flag,
+ * there is additional meta data plane for such formats
+ */
+
+#define INTERLEAVED_RGB_FMT(fmt, a, r, g, b, e0, e1, e2, e3, uc, alpha,   \
+bp, flg, fm, np)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define INTERLEAVED_RGB_FMT_TILED(fmt, a, r, g, b, e0, e1, e2, e3, uc,    \
+alpha, bp, flg, fm, np, th)                                               \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3) },                            \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = DPU_CHROMA_RGB,                                  \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = uc,                                               \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define INTERLEAVED_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, e3,              \
+alpha, chroma, count, bp, flg, fm, np)                                    \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_INTERLEAVED,                            \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), (e3)},                             \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = count,                                            \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_TILED(fmt, a, r, g, b, e0, e1, chroma,             \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE(fmt, a, r, g, b, e0, e1, chroma, flg, fm, np)\
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+#define PSEUDO_YUV_FMT_LOOSE_TILED(fmt, a, r, g, b, e0, e1, chroma,       \
+flg, fm, np, th)                                                          \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PSEUDO_PLANAR,                          \
+	.alpha_enable = false,                                            \
+	.element = { (e0), (e1), 0, 0 },                                  \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 1,                                            \
+	.unpack_tight = 0,                                                \
+	.unpack_count = 2,                                                \
+	.bpp = 2,                                                         \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = th                                                 \
+}
+
+
+#define PLANAR_YUV_FMT(fmt, a, r, g, b, e0, e1, e2, alpha, chroma, bp,    \
+flg, fm, np)                                                      \
+{                                                                         \
+	.base.pixel_format = DRM_FORMAT_ ## fmt,                          \
+	.fetch_planes = DPU_PLANE_PLANAR,                                 \
+	.alpha_enable = alpha,                                            \
+	.element = { (e0), (e1), (e2), 0 },                               \
+	.bits = { g, b, r, a },                                           \
+	.chroma_sample = chroma,                                          \
+	.unpack_align_msb = 0,                                            \
+	.unpack_tight = 1,                                                \
+	.unpack_count = 1,                                                \
+	.bpp = bp,                                                        \
+	.fetch_mode = fm,                                                 \
+	.flag = {(flg)},                                                  \
+	.num_planes = np,                                                 \
+	.tile_height = DPU_TILE_HEIGHT_DEFAULT                            \
+}
+
+/*
+ * struct dpu_media_color_map - maps drm format to media format
+ * @format: DRM base pixel format
+ * @color: Media API color related to DRM format
+ */
+struct dpu_media_color_map {
+	uint32_t format;
+	uint32_t color;
+};
+
+static const struct dpu_format dpu_format_map[] = {
+	INTERLEAVED_RGB_FMT(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR888,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 3, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGB565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR1555,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX5551,
+		COLOR_ALPHA_1BIT, COLOR_5BIT, COLOR_5BIT, COLOR_5BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX4444,
+		COLOR_ALPHA_4BIT, COLOR_4BIT, COLOR_4BIT, COLOR_4BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 2, 0,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBA1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(ARGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XRGB2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(BGRX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	INTERLEAVED_RGB_FMT(RGBX1010102,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		false, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_LINEAR, 1),
+
+	PSEUDO_YUV_FMT(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV21,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV16,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PSEUDO_YUV_FMT(NV61,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_H2V1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(VYUY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(UYVY,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YUYV,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C1_B_Cb, C0_G_Y, C2_R_Cr,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	INTERLEAVED_YUV_FMT(YVYU,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C0_G_Y, C2_R_Cr, C0_G_Y, C1_B_Cb,
+		false, DPU_CHROMA_H2V1, 4, 2, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 2),
+
+	PLANAR_YUV_FMT(YUV420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+
+	PLANAR_YUV_FMT(YVU420,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr, C0_G_Y,
+		false, DPU_CHROMA_420, 1, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_LINEAR, 3),
+};
+
+/*
+ * A5x tile formats tables:
+ * These tables hold the A5x tile formats supported.
+ */
+static const struct dpu_format dpu_format_map_tile[] = {
+	INTERLEAVED_RGB_FMT_TILED(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ARGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C1_B_Cb, C0_G_Y, C2_R_Cr, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(RGBA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(BGRA8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		true, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(BGRX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C0_G_Y, C2_R_Cr, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XRGB8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C3_ALPHA, C2_R_Cr, C0_G_Y, C1_B_Cb, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(RGBX8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, 0,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX,
+		DPU_FETCH_UBWC, 1, DPU_TILE_HEIGHT_TILED),
+
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12),
+
+	PSEUDO_YUV_FMT_TILED(NV21,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C1_B_Cb,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_NV12),
+};
+
+/*
+ * UBWC formats table:
+ * This table holds the UBWC formats supported.
+ * If a compression ratio needs to be used for this or any other format,
+ * the data will be passed by user-space.
+ */
+static const struct dpu_format dpu_format_map_ubwc[] = {
+	INTERLEAVED_RGB_FMT_TILED(BGR565,
+		0, COLOR_5BIT, COLOR_6BIT, COLOR_5BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, 0, 3,
+		false, 2, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR8888,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		false, 4, DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(ABGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	INTERLEAVED_RGB_FMT_TILED(XBGR2101010,
+		COLOR_8BIT, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C2_R_Cr, C0_G_Y, C1_B_Cb, C3_ALPHA, 4,
+		true, 4, DPU_FORMAT_FLAG_DX | DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 2, DPU_TILE_HEIGHT_UBWC),
+
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, DPU_FORMAT_FLAG_YUV |
+				DPU_FORMAT_FLAG_COMPRESSED,
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+static const struct dpu_format dpu_format_map_p010[] = {
+	PSEUDO_YUV_FMT_LOOSE(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX),
+		DPU_FETCH_LINEAR, 2),
+};
+
+static const struct dpu_format dpu_format_map_p010_ubwc[] = {
+	PSEUDO_YUV_FMT_LOOSE_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX |
+				DPU_FORMAT_FLAG_COMPRESSED),
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+static const struct dpu_format dpu_format_map_tp10_ubwc[] = {
+	PSEUDO_YUV_FMT_TILED(NV12,
+		0, COLOR_8BIT, COLOR_8BIT, COLOR_8BIT,
+		C1_B_Cb, C2_R_Cr,
+		DPU_CHROMA_420, (DPU_FORMAT_FLAG_YUV | DPU_FORMAT_FLAG_DX |
+				DPU_FORMAT_FLAG_COMPRESSED),
+		DPU_FETCH_UBWC, 4, DPU_TILE_HEIGHT_NV12),
+};
+
+/* _dpu_get_v_h_subsample_rate - Get subsample rates for all formats we support
+ *   Note: Not using the drm_format_*_subsampling since we have formats
+ */
+static void _dpu_get_v_h_subsample_rate(
+	enum dpu_chroma_samp_type chroma_sample,
+	uint32_t *v_sample,
+	uint32_t *h_sample)
+{
+	if (!v_sample || !h_sample)
+		return;
+
+	switch (chroma_sample) {
+	case DPU_CHROMA_H2V1:
+		*v_sample = 1;
+		*h_sample = 2;
+		break;
+	case DPU_CHROMA_H1V2:
+		*v_sample = 2;
+		*h_sample = 1;
+		break;
+	case DPU_CHROMA_420:
+		*v_sample = 2;
+		*h_sample = 2;
+		break;
+	default:
+		*v_sample = 1;
+		*h_sample = 1;
+		break;
+	}
+}
+
+static int _dpu_format_get_media_color_ubwc(const struct dpu_format *fmt)
+{
+	static const struct dpu_media_color_map dpu_media_ubwc_map[] = {
+		{DRM_FORMAT_ABGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_XBGR8888, COLOR_FMT_RGBA8888_UBWC},
+		{DRM_FORMAT_ABGR2101010, COLOR_FMT_RGBA1010102_UBWC},
+		{DRM_FORMAT_XBGR2101010, COLOR_FMT_RGBA1010102_UBWC},
+		{DRM_FORMAT_BGR565, COLOR_FMT_RGB565_UBWC},
+	};
+	int color_fmt = -1;
+	int i;
+
+	if (fmt->base.pixel_format == DRM_FORMAT_NV12) {
+		if (DPU_FORMAT_IS_DX(fmt)) {
+			if (fmt->unpack_tight)
+				color_fmt = COLOR_FMT_NV12_BPP10_UBWC;
+			else
+				color_fmt = COLOR_FMT_P010_UBWC;
+		} else
+			color_fmt = COLOR_FMT_NV12_UBWC;
+		return color_fmt;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_media_ubwc_map); ++i)
+		if (fmt->base.pixel_format == dpu_media_ubwc_map[i].format) {
+			color_fmt = dpu_media_ubwc_map[i].color;
+			break;
+		}
+	return color_fmt;
+}
+
+static int _dpu_format_get_plane_sizes_ubwc(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout)
+{
+	int i;
+	int color;
+	bool meta = DPU_FORMAT_IS_UBWC(fmt);
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	color = _dpu_format_get_media_color_ubwc(fmt);
+	if (color < 0) {
+		DRM_ERROR("UBWC format not supported for fmt: %4.4s\n",
+			(char *)&fmt->base.pixel_format);
+		return -EINVAL;
+	}
+
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		uint32_t y_sclines, uv_sclines;
+		uint32_t y_meta_scanlines = 0;
+		uint32_t uv_meta_scanlines = 0;
+
+		layout->num_planes = 2;
+		layout->plane_pitch[0] = VENUS_Y_STRIDE(color, width);
+		y_sclines = VENUS_Y_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			y_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[1] = VENUS_UV_STRIDE(color, width);
+		uv_sclines = VENUS_UV_SCANLINES(color, height);
+		layout->plane_size[1] = MSM_MEDIA_ALIGN(layout->plane_pitch[1] *
+			uv_sclines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_Y_META_STRIDE(color, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			y_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		layout->plane_pitch[3] = VENUS_UV_META_STRIDE(color, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color, height);
+		layout->plane_size[3] = MSM_MEDIA_ALIGN(layout->plane_pitch[3] *
+			uv_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+	} else {
+		uint32_t rgb_scanlines, rgb_meta_scanlines;
+
+		layout->num_planes = 1;
+
+		layout->plane_pitch[0] = VENUS_RGB_STRIDE(color, width);
+		rgb_scanlines = VENUS_RGB_SCANLINES(color, height);
+		layout->plane_size[0] = MSM_MEDIA_ALIGN(layout->plane_pitch[0] *
+			rgb_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+
+		if (!meta)
+			goto done;
+		layout->num_planes += 2;
+		layout->plane_pitch[2] = VENUS_RGB_META_STRIDE(color, width);
+		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color, height);
+		layout->plane_size[2] = MSM_MEDIA_ALIGN(layout->plane_pitch[2] *
+			rgb_meta_scanlines, DPU_UBWC_PLANE_SIZE_ALIGNMENT);
+	}
+
+done:
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+static int _dpu_format_get_plane_sizes_linear(
+		const struct dpu_format *fmt,
+		const uint32_t width,
+		const uint32_t height,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	int i;
+
+	memset(layout, 0, sizeof(struct dpu_hw_fmt_layout));
+	layout->format = fmt;
+	layout->width = width;
+	layout->height = height;
+	layout->num_planes = fmt->num_planes;
+
+	/* Due to memset above, only need to set planes of interest */
+	if (fmt->fetch_planes == DPU_PLANE_INTERLEAVED) {
+		layout->num_planes = 1;
+		layout->plane_size[0] = width * height * layout->format->bpp;
+		layout->plane_pitch[0] = width * layout->format->bpp;
+	} else {
+		uint32_t v_subsample, h_subsample;
+		uint32_t chroma_samp;
+		uint32_t bpp = 1;
+
+		chroma_samp = fmt->chroma_sample;
+		_dpu_get_v_h_subsample_rate(chroma_samp, &v_subsample,
+				&h_subsample);
+
+		if (width % h_subsample || height % v_subsample) {
+			DRM_ERROR("mismatch in subsample vs dimensions\n");
+			return -EINVAL;
+		}
+
+		if ((fmt->base.pixel_format == DRM_FORMAT_NV12) &&
+			(DPU_FORMAT_IS_DX(fmt)))
+			bpp = 2;
+		layout->plane_pitch[0] = width * bpp;
+		layout->plane_pitch[1] = layout->plane_pitch[0] / h_subsample;
+		layout->plane_size[0] = layout->plane_pitch[0] * height;
+		layout->plane_size[1] = layout->plane_pitch[1] *
+				(height / v_subsample);
+
+		if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+			layout->num_planes = 2;
+			layout->plane_size[1] *= 2;
+			layout->plane_pitch[1] *= 2;
+		} else {
+			/* planar */
+			layout->num_planes = 3;
+			layout->plane_size[2] = layout->plane_size[1];
+			layout->plane_pitch[2] = layout->plane_pitch[1];
+		}
+	}
+
+	/*
+	 * linear format: allow user allocated pitches if they are greater than
+	 * the requirement.
+	 * ubwc format: pitch values are computed uniformly across
+	 * all the components based on ubwc specifications.
+	 */
+	for (i = 0; i < layout->num_planes && i < DPU_MAX_PLANES; ++i) {
+		if (pitches && layout->plane_pitch[i] < pitches[i])
+			layout->plane_pitch[i] = pitches[i];
+	}
+
+	for (i = 0; i < DPU_MAX_PLANES; i++)
+		layout->total_size += layout->plane_size[i];
+
+	return 0;
+}
+
+int dpu_format_get_plane_sizes(
+		const struct dpu_format *fmt,
+		const uint32_t w,
+		const uint32_t h,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches)
+{
+	if (!layout || !fmt) {
+		DRM_ERROR("invalid pointer\n");
+		return -EINVAL;
+	}
+
+	if ((w > DPU_MAX_IMG_WIDTH) || (h > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	if (DPU_FORMAT_IS_UBWC(fmt) || DPU_FORMAT_IS_TILE(fmt))
+		return _dpu_format_get_plane_sizes_ubwc(fmt, w, h, layout);
+
+	return _dpu_format_get_plane_sizes_linear(fmt, w, h, layout, pitches);
+}
+
+int dpu_format_get_block_size(const struct dpu_format *fmt,
+		uint32_t *w, uint32_t *h)
+{
+	if (!fmt || !w || !h) {
+		DRM_ERROR("invalid pointer\n");
+		return -EINVAL;
+	}
+
+	/* TP10 is 96x96 and all others are 128x128 */
+	if (DPU_FORMAT_IS_YUV(fmt) && DPU_FORMAT_IS_DX(fmt) &&
+			(fmt->num_planes == 2) && fmt->unpack_tight)
+		*w = *h = 96;
+	else
+		*w = *h = 128;
+
+	return 0;
+}
+
+uint32_t dpu_format_get_framebuffer_size(
+		const uint32_t format,
+		const uint32_t width,
+		const uint32_t height,
+		const uint32_t *pitches,
+		const uint64_t modifiers)
+{
+	const struct dpu_format *fmt;
+	struct dpu_hw_fmt_layout layout;
+
+	fmt = dpu_get_dpu_format_ext(format, modifiers);
+	if (!fmt)
+		return 0;
+
+	if (!pitches)
+		return -EINVAL;
+
+	if (dpu_format_get_plane_sizes(fmt, width, height, &layout, pitches))
+		layout.total_size = 0;
+
+	return layout.total_size;
+}
+
+static int _dpu_format_populate_addrs_ubwc(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t base_addr = 0;
+	bool meta;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid pointers\n");
+		return -EINVAL;
+	}
+
+	if (aspace)
+		base_addr = msm_framebuffer_iova(fb, aspace, 0);
+	if (!base_addr) {
+		DRM_ERROR("failed to retrieve base addr\n");
+		return -EFAULT;
+	}
+
+	meta = DPU_FORMAT_IS_UBWC(layout->format);
+
+	/* Per-format logic for verifying active planes */
+	if (DPU_FORMAT_IS_YUV(layout->format)) {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      Y meta     |  ** |    Y bitstream   | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |    Y bitstream  |  ** |  CbCr bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |   Cbcr metadata |  ** |       Y meta     | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  CbCr bitstream |  ** |     CbCr meta    | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/************************************************/
+
+		/* configure Y bitstream plane */
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+
+		/* configure CbCr bitstream plane */
+		layout->plane_addr[1] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2] + layout->plane_size[3];
+
+		if (!meta)
+			goto done;
+
+		/* configure Y metadata plane */
+		layout->plane_addr[2] = base_addr;
+
+		/* configure CbCr metadata plane */
+		layout->plane_addr[3] = base_addr + layout->plane_size[0]
+			+ layout->plane_size[2];
+
+	} else {
+		/************************************************/
+		/*      UBWC            **                      */
+		/*      buffer          **      DPU PLANE       */
+		/*      format          **                      */
+		/************************************************/
+		/* -------------------  ** -------------------- */
+		/* |      RGB meta   |  ** |   RGB bitstream  | */
+		/* |       data      |  ** |       plane      | */
+		/* -------------------  ** -------------------- */
+		/* |  RGB bitstream  |  ** |       NONE       | */
+		/* |       data      |  ** |                  | */
+		/* -------------------  ** -------------------- */
+		/*                      ** |     RGB meta     | */
+		/*                      ** |       plane      | */
+		/*                      ** -------------------- */
+		/************************************************/
+
+		layout->plane_addr[0] = base_addr + layout->plane_size[2];
+		layout->plane_addr[1] = 0;
+
+		if (!meta)
+			goto done;
+
+		layout->plane_addr[2] = base_addr;
+		layout->plane_addr[3] = 0;
+	}
+done:
+	return 0;
+}
+
+static int _dpu_format_populate_addrs_linear(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	unsigned int i;
+
+	/* Can now check the pitches given vs pitches expected */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (layout->plane_pitch[i] > fb->pitches[i]) {
+			DRM_ERROR("plane %u expected pitch %u, fb %u\n",
+				i, layout->plane_pitch[i], fb->pitches[i]);
+			return -EINVAL;
+		}
+	}
+
+	/* Populate addresses for simple formats here */
+	for (i = 0; i < layout->num_planes; ++i) {
+		if (aspace)
+			layout->plane_addr[i] =
+				msm_framebuffer_iova(fb, aspace, i);
+		if (!layout->plane_addr[i]) {
+			DRM_ERROR("failed to retrieve base addr\n");
+			return -EFAULT;
+		}
+	}
+
+	return 0;
+}
+
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *layout)
+{
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	int i, ret;
+
+	if (!fb || !layout) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	if ((fb->width > DPU_MAX_IMG_WIDTH) ||
+			(fb->height > DPU_MAX_IMG_HEIGHT)) {
+		DRM_ERROR("image dimensions outside max range\n");
+		return -ERANGE;
+	}
+
+	layout->format = to_dpu_format(msm_framebuffer_format(fb));
+
+	/* Populate the plane sizes etc via get_format */
+	ret = dpu_format_get_plane_sizes(layout->format, fb->width, fb->height,
+			layout, fb->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < DPU_MAX_PLANES; ++i)
+		plane_addr[i] = layout->plane_addr[i];
+
+	/* Populate the addresses given the fb */
+	if (DPU_FORMAT_IS_UBWC(layout->format) ||
+			DPU_FORMAT_IS_TILE(layout->format))
+		ret = _dpu_format_populate_addrs_ubwc(aspace, fb, layout);
+	else
+		ret = _dpu_format_populate_addrs_linear(aspace, fb, layout);
+
+	/* check if anything changed */
+	if (!ret && !memcmp(plane_addr, layout->plane_addr, sizeof(plane_addr)))
+		ret = -EAGAIN;
+
+	return ret;
+}
+
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos)
+{
+	int ret, i, num_base_fmt_planes;
+	const struct dpu_format *fmt;
+	struct dpu_hw_fmt_layout layout;
+	uint32_t bos_total_size = 0;
+
+	if (!msm_fmt || !cmd || !bos) {
+		DRM_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	fmt = to_dpu_format(msm_fmt);
+	num_base_fmt_planes = drm_format_num_planes(fmt->base.pixel_format);
+
+	ret = dpu_format_get_plane_sizes(fmt, cmd->width, cmd->height,
+			&layout, cmd->pitches);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < num_base_fmt_planes; i++) {
+		if (!bos[i]) {
+			DRM_ERROR("invalid handle for plane %d\n", i);
+			return -EINVAL;
+		}
+		if ((i == 0) || (bos[i] != bos[0]))
+			bos_total_size += bos[i]->size;
+	}
+
+	if (bos_total_size < layout.total_size) {
+		DRM_ERROR("buffers total size too small %u expected %u\n",
+				bos_total_size, layout.total_size);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier)
+{
+	uint32_t i = 0;
+	const struct dpu_format *fmt = NULL;
+	const struct dpu_format *map = NULL;
+	ssize_t map_size = 0;
+
+	/*
+	 * Currently only support exactly zero or one modifier.
+	 * All planes use the same modifier.
+	 */
+	DPU_DEBUG("plane format modifier 0x%llX\n", modifier);
+
+	switch (modifier) {
+	case 0:
+		map = dpu_format_map;
+		map_size = ARRAY_SIZE(dpu_format_map);
+		break;
+	case DRM_FORMAT_MOD_QCOM_COMPRESSED:
+		map = dpu_format_map_ubwc;
+		map_size = ARRAY_SIZE(dpu_format_map_ubwc);
+		DPU_DEBUG("found fmt: %4.4s  DRM_FORMAT_MOD_QCOM_COMPRESSED\n",
+				(char *)&format);
+		break;
+	default:
+		DPU_ERROR("unsupported format modifier %llX\n", modifier);
+		return NULL;
+	}
+
+	for (i = 0; i < map_size; i++) {
+		if (format == map[i].base.pixel_format) {
+			fmt = &map[i];
+			break;
+		}
+	}
+
+	if (fmt == NULL)
+		DPU_ERROR("unsupported fmt: %4.4s modifier 0x%llX\n",
+			(char *)&format, modifier);
+	else
+		DPU_DEBUG("fmt %4.4s mod 0x%llX ubwc %d yuv %d\n",
+				(char *)&format, modifier,
+				DPU_FORMAT_IS_UBWC(fmt),
+				DPU_FORMAT_IS_YUV(fmt));
+
+	return fmt;
+}
+
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers)
+{
+	const struct dpu_format *fmt = dpu_get_dpu_format_ext(format,
+			modifiers);
+	if (fmt)
+		return &fmt->base;
+	return NULL;
+}
+
+uint32_t dpu_populate_formats(
+		const struct dpu_format_extended *format_list,
+		uint32_t *pixel_formats,
+		uint64_t *pixel_modifiers,
+		uint32_t pixel_formats_max)
+{
+	uint32_t i, fourcc_format;
+
+	if (!format_list || !pixel_formats)
+		return 0;
+
+	for (i = 0, fourcc_format = 0;
+			format_list->fourcc_format && i < pixel_formats_max;
+			++format_list) {
+		/* verify if listed format is in dpu_format_map? */
+
+		/* optionally return modified formats */
+		if (pixel_modifiers) {
+			/* assume same modifier for all fb planes */
+			pixel_formats[i] = format_list->fourcc_format;
+			pixel_modifiers[i++] = format_list->modifier;
+		} else {
+			/* assume base formats grouped together */
+			if (fourcc_format != format_list->fourcc_format) {
+				fourcc_format = format_list->fourcc_format;
+				pixel_formats[i++] = fourcc_format;
+			}
+		}
+	}
+
+	return i;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
new file mode 100644
index 000000000000..b55bfd13e296
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
@@ -0,0 +1,136 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_FORMATS_H
+#define _DPU_FORMATS_H
+
+#include <drm/drm_fourcc.h>
+#include "msm_gem.h"
+#include "dpu_hw_mdss.h"
+
+/**
+ * dpu_get_dpu_format_ext() - Returns dpu format structure pointer.
+ * @format:          DRM FourCC Code
+ * @modifiers:       format modifier array from client, one per plane
+ */
+const struct dpu_format *dpu_get_dpu_format_ext(
+		const uint32_t format,
+		const uint64_t modifier);
+
+#define dpu_get_dpu_format(f) dpu_get_dpu_format_ext(f, 0)
+
+/**
+ * dpu_get_msm_format - get an dpu_format by its msm_format base
+ *                     callback function registers with the msm_kms layer
+ * @kms:             kms driver
+ * @format:          DRM FourCC Code
+ * @modifiers:       data layout modifier
+ */
+const struct msm_format *dpu_get_msm_format(
+		struct msm_kms *kms,
+		const uint32_t format,
+		const uint64_t modifiers);
+
+/**
+ * dpu_populate_formats - populate the given array with fourcc codes supported
+ * @format_list:       pointer to list of possible formats
+ * @pixel_formats:     array to populate with fourcc codes
+ * @pixel_modifiers:   array to populate with drm modifiers, can be NULL
+ * @pixel_formats_max: length of pixel formats array
+ * Return: number of elements populated
+ */
+uint32_t dpu_populate_formats(
+		const struct dpu_format_extended *format_list,
+		uint32_t *pixel_formats,
+		uint64_t *pixel_modifiers,
+		uint32_t pixel_formats_max);
+
+/**
+ * dpu_format_get_plane_sizes - calculate size and layout of given buffer format
+ * @fmt:             pointer to dpu_format
+ * @w:               width of the buffer
+ * @h:               height of the buffer
+ * @layout:          layout of the buffer
+ * @pitches:         array of size [DPU_MAX_PLANES] to populate
+ *		     pitch for each plane
+ *
+ * Return: size of the buffer
+ */
+int dpu_format_get_plane_sizes(
+		const struct dpu_format *fmt,
+		const uint32_t w,
+		const uint32_t h,
+		struct dpu_hw_fmt_layout *layout,
+		const uint32_t *pitches);
+
+/**
+ * dpu_format_get_block_size - get block size of given format when
+ *	operating in block mode
+ * @fmt:             pointer to dpu_format
+ * @w:               pointer to width of the block
+ * @h:               pointer to height of the block
+ *
+ * Return: 0 if success; error oode otherwise
+ */
+int dpu_format_get_block_size(const struct dpu_format *fmt,
+		uint32_t *w, uint32_t *h);
+
+/**
+ * dpu_format_check_modified_format - validate format and buffers for
+ *                   dpu non-standard, i.e. modified format
+ * @kms:             kms driver
+ * @msm_fmt:         pointer to the msm_fmt base pointer of an dpu_format
+ * @cmd:             fb_cmd2 structure user request
+ * @bos:             gem buffer object list
+ *
+ * Return: error code on failure, 0 on success
+ */
+int dpu_format_check_modified_format(
+		const struct msm_kms *kms,
+		const struct msm_format *msm_fmt,
+		const struct drm_mode_fb_cmd2 *cmd,
+		struct drm_gem_object **bos);
+
+/**
+ * dpu_format_populate_layout - populate the given format layout based on
+ *                     mmu, fb, and format found in the fb
+ * @aspace:            address space pointer
+ * @fb:                framebuffer pointer
+ * @fmtl:              format layout structure to populate
+ *
+ * Return: error code on failure, -EAGAIN if success but the addresses
+ *         are the same as before or 0 if new addresses were populated
+ */
+int dpu_format_populate_layout(
+		struct msm_gem_address_space *aspace,
+		struct drm_framebuffer *fb,
+		struct dpu_hw_fmt_layout *fmtl);
+
+/**
+ * dpu_format_get_framebuffer_size - get framebuffer memory size
+ * @format:            DRM pixel format
+ * @width:             pixel width
+ * @height:            pixel height
+ * @pitches:           array of size [DPU_MAX_PLANES] to populate
+ *		       pitch for each plane
+ * @modifiers:         drm modifier
+ *
+ * Return: memory size required for frame buffer
+ */
+uint32_t dpu_format_get_framebuffer_size(
+		const uint32_t format,
+		const uint32_t width,
+		const uint32_t height,
+		const uint32_t *pitches,
+		const uint64_t modifiers);
+
+#endif /*_DPU_FORMATS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
new file mode 100644
index 000000000000..58d29e43faef
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.c
@@ -0,0 +1,155 @@
+/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/mutex.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_blk.h"
+
+/* Serialization lock for dpu_hw_blk_list */
+static DEFINE_MUTEX(dpu_hw_blk_lock);
+
+/* List of all hw block objects */
+static LIST_HEAD(dpu_hw_blk_list);
+
+/**
+ * dpu_hw_blk_init - initialize hw block object
+ * @type: hw block type - enum dpu_hw_blk_type
+ * @id: instance id of the hw block
+ * @ops: Pointer to block operations
+ * return: 0 if success; error code otherwise
+ */
+int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+		struct dpu_hw_blk_ops *ops)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	INIT_LIST_HEAD(&hw_blk->list);
+	hw_blk->type = type;
+	hw_blk->id = id;
+	atomic_set(&hw_blk->refcount, 0);
+
+	if (ops)
+		hw_blk->ops = *ops;
+
+	mutex_lock(&dpu_hw_blk_lock);
+	list_add(&hw_blk->list, &dpu_hw_blk_list);
+	mutex_unlock(&dpu_hw_blk_lock);
+
+	return 0;
+}
+
+/**
+ * dpu_hw_blk_destroy - destroy hw block object.
+ * @hw_blk:  pointer to hw block object
+ * return: none
+ */
+void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return;
+	}
+
+	if (atomic_read(&hw_blk->refcount))
+		pr_err("hw_blk:%d.%d invalid refcount\n", hw_blk->type,
+				hw_blk->id);
+
+	mutex_lock(&dpu_hw_blk_lock);
+	list_del(&hw_blk->list);
+	mutex_unlock(&dpu_hw_blk_lock);
+}
+
+/**
+ * dpu_hw_blk_get - get hw_blk from free pool
+ * @hw_blk: if specified, increment reference count only
+ * @type: if hw_blk is not specified, allocate the next available of this type
+ * @id: if specified (>= 0), allocate the given instance of the above type
+ * return: pointer to hw block object
+ */
+struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id)
+{
+	struct dpu_hw_blk *curr;
+	int rc, refcount;
+
+	if (!hw_blk) {
+		mutex_lock(&dpu_hw_blk_lock);
+		list_for_each_entry(curr, &dpu_hw_blk_list, list) {
+			if ((curr->type != type) ||
+					(id >= 0 && curr->id != id) ||
+					(id < 0 &&
+						atomic_read(&curr->refcount)))
+				continue;
+
+			hw_blk = curr;
+			break;
+		}
+		mutex_unlock(&dpu_hw_blk_lock);
+	}
+
+	if (!hw_blk) {
+		pr_debug("no hw_blk:%d\n", type);
+		return NULL;
+	}
+
+	refcount = atomic_inc_return(&hw_blk->refcount);
+
+	if (refcount == 1 && hw_blk->ops.start) {
+		rc = hw_blk->ops.start(hw_blk);
+		if (rc) {
+			pr_err("failed to start  hw_blk:%d rc:%d\n", type, rc);
+			goto error_start;
+		}
+	}
+
+	pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type,
+			hw_blk->id, refcount);
+	return hw_blk;
+
+error_start:
+	dpu_hw_blk_put(hw_blk);
+	return ERR_PTR(rc);
+}
+
+/**
+ * dpu_hw_blk_put - put hw_blk to free pool if decremented refcount is zero
+ * @hw_blk: hw block to be freed
+ * @free_blk: function to be called when reference count goes to zero
+ */
+void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk)
+{
+	if (!hw_blk) {
+		pr_err("invalid parameters\n");
+		return;
+	}
+
+	pr_debug("hw_blk:%d.%d refcount:%d\n", hw_blk->type, hw_blk->id,
+			atomic_read(&hw_blk->refcount));
+
+	if (!atomic_read(&hw_blk->refcount)) {
+		pr_err("hw_blk:%d.%d invalid put\n", hw_blk->type, hw_blk->id);
+		return;
+	}
+
+	if (atomic_dec_return(&hw_blk->refcount))
+		return;
+
+	if (hw_blk->ops.stop)
+		hw_blk->ops.stop(hw_blk);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
new file mode 100644
index 000000000000..0f4ca8af1ec5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_blk.h
@@ -0,0 +1,53 @@
+/* Copyright (c) 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_BLK_H
+#define _DPU_HW_BLK_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+#include <linux/atomic.h>
+
+struct dpu_hw_blk;
+
+/**
+ * struct dpu_hw_blk_ops - common hardware block operations
+ * @start: start operation on first get
+ * @stop: stop operation on last put
+ */
+struct dpu_hw_blk_ops {
+	int (*start)(struct dpu_hw_blk *);
+	void (*stop)(struct dpu_hw_blk *);
+};
+
+/**
+ * struct dpu_hw_blk - definition of hardware block object
+ * @list: list of hardware blocks
+ * @type: hardware block type
+ * @id: instance id
+ * @refcount: reference/usage count
+ */
+struct dpu_hw_blk {
+	struct list_head list;
+	u32 type;
+	int id;
+	atomic_t refcount;
+	struct dpu_hw_blk_ops ops;
+};
+
+int dpu_hw_blk_init(struct dpu_hw_blk *hw_blk, u32 type, int id,
+		struct dpu_hw_blk_ops *ops);
+void dpu_hw_blk_destroy(struct dpu_hw_blk *hw_blk);
+
+struct dpu_hw_blk *dpu_hw_blk_get(struct dpu_hw_blk *hw_blk, u32 type, int id);
+void dpu_hw_blk_put(struct dpu_hw_blk *hw_blk);
+#endif /*_DPU_HW_BLK_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
new file mode 100644
index 000000000000..1793cfd29a07
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -0,0 +1,511 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+#include <linux/slab.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_catalog_format.h"
+#include "dpu_kms.h"
+
+#define VIG_SDM845_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_SCALER_QSEED3) | BIT(DPU_SSPP_QOS) |\
+	BIT(DPU_SSPP_CSC_10BIT) | BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_QOS_8LVL) |\
+	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define DMA_SDM845_MASK \
+	(BIT(DPU_SSPP_SRC) | BIT(DPU_SSPP_QOS) | BIT(DPU_SSPP_QOS_8LVL) |\
+	BIT(DPU_SSPP_TS_PREFILL) | BIT(DPU_SSPP_TS_PREFILL_REC1) |\
+	BIT(DPU_SSPP_CDP) | BIT(DPU_SSPP_EXCL_RECT))
+
+#define MIXER_SDM845_MASK \
+	(BIT(DPU_MIXER_SOURCESPLIT) | BIT(DPU_DIM_LAYER))
+
+#define PINGPONG_SDM845_MASK BIT(DPU_PINGPONG_DITHER)
+
+#define PINGPONG_SDM845_SPLIT_MASK \
+	(PINGPONG_SDM845_MASK | BIT(DPU_PINGPONG_TE2))
+
+#define DEFAULT_PIXEL_RAM_SIZE		(50 * 1024)
+#define DEFAULT_DPU_LINE_WIDTH		2048
+#define DEFAULT_DPU_OUTPUT_LINE_WIDTH	2560
+
+#define MAX_HORZ_DECIMATION	4
+#define MAX_VERT_DECIMATION	4
+
+#define MAX_UPSCALE_RATIO	20
+#define MAX_DOWNSCALE_RATIO	4
+#define SSPP_UNITY_SCALE	1
+
+#define STRCAT(X, Y) (X Y)
+
+/*************************************************************
+ * DPU sub blocks config
+ *************************************************************/
+/* DPU top level caps */
+static const struct dpu_caps sdm845_dpu_caps = {
+	.max_mixer_width = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.max_mixer_blendstages = 0xb,
+	.qseed_type = DPU_SSPP_SCALER_QSEED3,
+	.smart_dma_rev = DPU_SSPP_SMART_DMA_V2,
+	.ubwc_version = DPU_HW_UBWC_VER_20,
+	.has_src_split = true,
+	.has_dim_layer = true,
+	.has_idle_pc = true,
+};
+
+static struct dpu_mdp_cfg sdm845_mdp[] = {
+	{
+	.name = "top_0", .id = MDP_TOP,
+	.base = 0x0, .len = 0x45C,
+	.features = 0,
+	.highest_bank_bit = 0x2,
+	.has_dest_scaler = true,
+	.clk_ctrls[DPU_CLK_CTRL_VIG0] = {
+			.reg_off = 0x2AC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG1] = {
+			.reg_off = 0x2B4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG2] = {
+			.reg_off = 0x2BC, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_VIG3] = {
+			.reg_off = 0x2C4, .bit_off = 0},
+	.clk_ctrls[DPU_CLK_CTRL_DMA0] = {
+			.reg_off = 0x2AC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_DMA1] = {
+			.reg_off = 0x2B4, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR0] = {
+			.reg_off = 0x2BC, .bit_off = 8},
+	.clk_ctrls[DPU_CLK_CTRL_CURSOR1] = {
+			.reg_off = 0x2C4, .bit_off = 8},
+	},
+};
+
+/*************************************************************
+ * CTL sub blocks config
+ *************************************************************/
+static struct dpu_ctl_cfg sdm845_ctl[] = {
+	{
+	.name = "ctl_0", .id = CTL_0,
+	.base = 0x1000, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY)
+	},
+	{
+	.name = "ctl_1", .id = CTL_1,
+	.base = 0x1200, .len = 0xE4,
+	.features = BIT(DPU_CTL_SPLIT_DISPLAY)
+	},
+	{
+	.name = "ctl_2", .id = CTL_2,
+	.base = 0x1400, .len = 0xE4,
+	.features = 0
+	},
+	{
+	.name = "ctl_3", .id = CTL_3,
+	.base = 0x1600, .len = 0xE4,
+	.features = 0
+	},
+	{
+	.name = "ctl_4", .id = CTL_4,
+	.base = 0x1800, .len = 0xE4,
+	.features = 0
+	},
+};
+
+/*************************************************************
+ * SSPP sub blocks config
+ *************************************************************/
+
+/* SSPP common configuration */
+static const struct dpu_sspp_blks_common sdm845_sspp_common = {
+	.maxlinewidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.pixel_ram_size = DEFAULT_PIXEL_RAM_SIZE,
+	.maxhdeciexp = MAX_HORZ_DECIMATION,
+	.maxvdeciexp = MAX_VERT_DECIMATION,
+};
+
+#define _VIG_SBLK(num, sdma_pri) \
+	{ \
+	.common = &sdm845_sspp_common, \
+	.maxdwnscale = MAX_DOWNSCALE_RATIO, \
+	.maxupscale = MAX_UPSCALE_RATIO, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.scaler_blk = {.name = STRCAT("sspp_scaler", num), \
+		.id = DPU_SSPP_SCALER_QSEED3, \
+		.base = 0xa00, .len = 0xa0,}, \
+	.csc_blk = {.name = STRCAT("sspp_csc", num), \
+		.id = DPU_SSPP_CSC_10BIT, \
+		.base = 0x1a00, .len = 0x100,}, \
+	.format_list = plane_formats_yuv, \
+	.virt_format_list = plane_formats, \
+	}
+
+#define _DMA_SBLK(num, sdma_pri) \
+	{ \
+	.common = &sdm845_sspp_common, \
+	.maxdwnscale = SSPP_UNITY_SCALE, \
+	.maxupscale = SSPP_UNITY_SCALE, \
+	.smart_dma_priority = sdma_pri, \
+	.src_blk = {.name = STRCAT("sspp_src_", num), \
+		.id = DPU_SSPP_SRC, .base = 0x00, .len = 0x150,}, \
+	.format_list = plane_formats, \
+	.virt_format_list = plane_formats, \
+	}
+
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_0 = _VIG_SBLK("0", 5);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_1 = _VIG_SBLK("1", 6);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_2 = _VIG_SBLK("2", 7);
+static const struct dpu_sspp_sub_blks sdm845_vig_sblk_3 = _VIG_SBLK("3", 8);
+
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_0 = _DMA_SBLK("8", 1);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_1 = _DMA_SBLK("9", 2);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_2 = _DMA_SBLK("10", 3);
+static const struct dpu_sspp_sub_blks sdm845_dma_sblk_3 = _DMA_SBLK("11", 4);
+
+#define SSPP_VIG_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x1c8, \
+	.features = VIG_SDM845_MASK, \
+	.sblk = &_sblk, \
+	.xin_id = _xinid, \
+	.type = SSPP_TYPE_VIG, \
+	.clk_ctrl = _clkctrl \
+	}
+
+#define SSPP_DMA_BLK(_name, _id, _base, _sblk, _xinid, _clkctrl) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x1c8, \
+	.features = DMA_SDM845_MASK, \
+	.sblk = &_sblk, \
+	.xin_id = _xinid, \
+	.type = SSPP_TYPE_DMA, \
+	.clk_ctrl = _clkctrl \
+	}
+
+static struct dpu_sspp_cfg sdm845_sspp[] = {
+	SSPP_VIG_BLK("sspp_0", SSPP_VIG0, 0x4000,
+		sdm845_vig_sblk_0, 0, DPU_CLK_CTRL_VIG0),
+	SSPP_VIG_BLK("sspp_1", SSPP_VIG1, 0x6000,
+		sdm845_vig_sblk_1, 4, DPU_CLK_CTRL_VIG1),
+	SSPP_VIG_BLK("sspp_2", SSPP_VIG2, 0x8000,
+		sdm845_vig_sblk_2, 8, DPU_CLK_CTRL_VIG2),
+	SSPP_VIG_BLK("sspp_3", SSPP_VIG3, 0xa000,
+		sdm845_vig_sblk_3, 12, DPU_CLK_CTRL_VIG3),
+	SSPP_DMA_BLK("sspp_8", SSPP_DMA0, 0x24000,
+		sdm845_dma_sblk_0, 1, DPU_CLK_CTRL_DMA0),
+	SSPP_DMA_BLK("sspp_9", SSPP_DMA1, 0x26000,
+		sdm845_dma_sblk_1, 5, DPU_CLK_CTRL_DMA1),
+	SSPP_DMA_BLK("sspp_10", SSPP_DMA2, 0x28000,
+		sdm845_dma_sblk_2, 9, DPU_CLK_CTRL_CURSOR0),
+	SSPP_DMA_BLK("sspp_11", SSPP_DMA3, 0x2a000,
+		sdm845_dma_sblk_3, 13, DPU_CLK_CTRL_CURSOR1),
+};
+
+/*************************************************************
+ * MIXER sub blocks config
+ *************************************************************/
+static const struct dpu_lm_sub_blks sdm845_lm_sblk = {
+	.maxwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxblendstages = 11, /* excluding base layer */
+	.blendstage_base = { /* offsets relative to mixer base */
+		0x20, 0x38, 0x50, 0x68, 0x80, 0x98,
+		0xb0, 0xc8, 0xe0, 0xf8, 0x110
+	},
+};
+
+#define LM_BLK(_name, _id, _base, _ds, _pp, _lmpair) \
+	{ \
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x320, \
+	.features = MIXER_SDM845_MASK, \
+	.sblk = &sdm845_lm_sblk, \
+	.ds = _ds, \
+	.pingpong = _pp, \
+	.lm_pair_mask = (1 << _lmpair) \
+	}
+
+static struct dpu_lm_cfg sdm845_lm[] = {
+	LM_BLK("lm_0", LM_0, 0x44000, DS_0, PINGPONG_0, LM_1),
+	LM_BLK("lm_1", LM_1, 0x45000, DS_1, PINGPONG_1, LM_0),
+	LM_BLK("lm_2", LM_2, 0x46000, DS_MAX, PINGPONG_2, LM_5),
+	LM_BLK("lm_3", LM_3, 0x0, DS_MAX, PINGPONG_MAX, 0),
+	LM_BLK("lm_4", LM_4, 0x0, DS_MAX, PINGPONG_MAX, 0),
+	LM_BLK("lm_5", LM_5, 0x49000, DS_MAX, PINGPONG_3, LM_2),
+};
+
+/*************************************************************
+ * DS sub blocks config
+ *************************************************************/
+static const struct dpu_ds_top_cfg sdm845_ds_top = {
+	.name = "ds_top_0", .id = DS_TOP,
+	.base = 0x60000, .len = 0xc,
+	.maxinputwidth = DEFAULT_DPU_LINE_WIDTH,
+	.maxoutputwidth = DEFAULT_DPU_OUTPUT_LINE_WIDTH,
+	.maxupscale = MAX_UPSCALE_RATIO,
+};
+
+#define DS_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x800, \
+	.features = DPU_SSPP_SCALER_QSEED3, \
+	.top = &sdm845_ds_top \
+	}
+
+static struct dpu_ds_cfg sdm845_ds[] = {
+	DS_BLK("ds_0", DS_0, 0x800),
+	DS_BLK("ds_1", DS_1, 0x1000),
+};
+
+/*************************************************************
+ * PINGPONG sub blocks config
+ *************************************************************/
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk_te = {
+	.te2 = {.id = DPU_PINGPONG_TE2, .base = 0x2000, .len = 0x0,
+		.version = 0x1},
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+static const struct dpu_pingpong_sub_blks sdm845_pp_sblk = {
+	.dither = {.id = DPU_PINGPONG_DITHER, .base = 0x30e0,
+		.len = 0x20, .version = 0x10000},
+};
+
+#define PP_BLK_TE(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_SPLIT_MASK, \
+	.sblk = &sdm845_pp_sblk_te \
+	}
+#define PP_BLK(_name, _id, _base) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0xd4, \
+	.features = PINGPONG_SDM845_MASK, \
+	.sblk = &sdm845_pp_sblk \
+	}
+
+static struct dpu_pingpong_cfg sdm845_pp[] = {
+	PP_BLK_TE("pingpong_0", PINGPONG_0, 0x70000),
+	PP_BLK_TE("pingpong_1", PINGPONG_1, 0x70800),
+	PP_BLK("pingpong_2", PINGPONG_2, 0x71000),
+	PP_BLK("pingpong_3", PINGPONG_3, 0x71800),
+};
+
+/*************************************************************
+ * INTF sub blocks config
+ *************************************************************/
+#define INTF_BLK(_name, _id, _base, _type, _ctrl_id) \
+	{\
+	.name = _name, .id = _id, \
+	.base = _base, .len = 0x280, \
+	.type = _type, \
+	.controller_id = _ctrl_id, \
+	.prog_fetch_lines_worst_case = 24 \
+	}
+
+static struct dpu_intf_cfg sdm845_intf[] = {
+	INTF_BLK("intf_0", INTF_0, 0x6A000, INTF_DP, 0),
+	INTF_BLK("intf_1", INTF_1, 0x6A800, INTF_DSI, 0),
+	INTF_BLK("intf_2", INTF_2, 0x6B000, INTF_DSI, 1),
+	INTF_BLK("intf_3", INTF_3, 0x6B800, INTF_DP, 1),
+};
+
+/*************************************************************
+ * CDM sub blocks config
+ *************************************************************/
+static struct dpu_cdm_cfg sdm845_cdm[] = {
+	{
+	.name = "cdm_0", .id = CDM_0,
+	.base = 0x79200, .len = 0x224,
+	.features = 0,
+	.intf_connect = BIT(INTF_3),
+	},
+};
+
+/*************************************************************
+ * VBIF sub blocks config
+ *************************************************************/
+/* VBIF QOS remap */
+static u32 sdm845_rt_pri_lvl[] = {3, 3, 4, 4, 5, 5, 6, 6};
+static u32 sdm845_nrt_pri_lvl[] = {3, 3, 3, 3, 3, 3, 3, 3};
+
+static struct dpu_vbif_cfg sdm845_vbif[] = {
+	{
+	.name = "vbif_0", .id = VBIF_0,
+	.base = 0, .len = 0x1040,
+	.features = BIT(DPU_VBIF_QOS_REMAP),
+	.xin_halt_timeout = 0x4000,
+	.qos_rt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_rt_pri_lvl),
+		.priority_lvl = sdm845_rt_pri_lvl,
+		},
+	.qos_nrt_tbl = {
+		.npriority_lvl = ARRAY_SIZE(sdm845_nrt_pri_lvl),
+		.priority_lvl = sdm845_nrt_pri_lvl,
+		},
+	.memtype_count = 14,
+	.memtype = {3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3},
+	},
+};
+
+static struct dpu_reg_dma_cfg sdm845_regdma = {
+	.base = 0x0, .version = 0x1, .trigger_sel_off = 0x119c
+};
+
+/*************************************************************
+ * PERF data config
+ *************************************************************/
+
+/* SSPP QOS LUTs */
+static struct dpu_qos_lut_entry sdm845_qos_linear[] = {
+	{.fl = 4, .lut = 0x357},
+	{.fl = 5, .lut = 0x3357},
+	{.fl = 6, .lut = 0x23357},
+	{.fl = 7, .lut = 0x223357},
+	{.fl = 8, .lut = 0x2223357},
+	{.fl = 9, .lut = 0x22223357},
+	{.fl = 10, .lut = 0x222223357},
+	{.fl = 11, .lut = 0x2222223357},
+	{.fl = 12, .lut = 0x22222223357},
+	{.fl = 13, .lut = 0x222222223357},
+	{.fl = 14, .lut = 0x1222222223357},
+	{.fl = 0, .lut = 0x11222222223357}
+};
+
+static struct dpu_qos_lut_entry sdm845_qos_macrotile[] = {
+	{.fl = 10, .lut = 0x344556677},
+	{.fl = 11, .lut = 0x3344556677},
+	{.fl = 12, .lut = 0x23344556677},
+	{.fl = 13, .lut = 0x223344556677},
+	{.fl = 14, .lut = 0x1223344556677},
+	{.fl = 0, .lut = 0x112233344556677},
+};
+
+static struct dpu_qos_lut_entry sdm845_qos_nrt[] = {
+	{.fl = 0, .lut = 0x0},
+};
+
+static struct dpu_perf_cfg sdm845_perf_data = {
+	.max_bw_low = 6800000,
+	.max_bw_high = 6800000,
+	.min_core_ib = 2400000,
+	.min_llcc_ib = 800000,
+	.min_dram_ib = 800000,
+	.core_ib_ff = "6.0",
+	.core_clk_ff = "1.0",
+	.comp_ratio_rt =
+	"NV12/5/1/1.23 AB24/5/1/1.23 XB24/5/1/1.23",
+	.comp_ratio_nrt =
+	"NV12/5/1/1.25 AB24/5/1/1.25 XB24/5/1/1.25",
+	.undersized_prefill_lines = 2,
+	.xtra_prefill_lines = 2,
+	.dest_scale_prefill_lines = 3,
+	.macrotile_prefill_lines = 4,
+	.yuv_nv12_prefill_lines = 8,
+	.linear_prefill_lines = 1,
+	.downscaling_prefill_lines = 1,
+	.amortizable_threshold = 25,
+	.min_prefill_lines = 24,
+	.danger_lut_tbl = {0xf, 0xffff, 0x0},
+	.qos_lut_tbl = {
+		{.nentry = ARRAY_SIZE(sdm845_qos_linear),
+		.entries = sdm845_qos_linear
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_macrotile),
+		.entries = sdm845_qos_macrotile
+		},
+		{.nentry = ARRAY_SIZE(sdm845_qos_nrt),
+		.entries = sdm845_qos_nrt
+		},
+	},
+	.cdp_cfg = {
+		{.rd_enable = 1, .wr_enable = 1},
+		{.rd_enable = 1, .wr_enable = 0}
+	},
+};
+
+/*************************************************************
+ * Hardware catalog init
+ *************************************************************/
+
+/*
+ * sdm845_cfg_init(): populate sdm845 dpu sub-blocks reg offsets
+ * and instance counts.
+ */
+void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
+{
+	*dpu_cfg = (struct dpu_mdss_cfg){
+		.caps = &sdm845_dpu_caps,
+		.mdp_count = ARRAY_SIZE(sdm845_mdp),
+		.mdp = sdm845_mdp,
+		.ctl_count = ARRAY_SIZE(sdm845_ctl),
+		.ctl = sdm845_ctl,
+		.sspp_count = ARRAY_SIZE(sdm845_sspp),
+		.sspp = sdm845_sspp,
+		.mixer_count = ARRAY_SIZE(sdm845_lm),
+		.mixer = sdm845_lm,
+		.ds_count = ARRAY_SIZE(sdm845_ds),
+		.ds = sdm845_ds,
+		.pingpong_count = ARRAY_SIZE(sdm845_pp),
+		.pingpong = sdm845_pp,
+		.cdm_count = ARRAY_SIZE(sdm845_cdm),
+		.cdm = sdm845_cdm,
+		.intf_count = ARRAY_SIZE(sdm845_intf),
+		.intf = sdm845_intf,
+		.vbif_count = ARRAY_SIZE(sdm845_vbif),
+		.vbif = sdm845_vbif,
+		.reg_dma_count = 1,
+		.dma_cfg = sdm845_regdma,
+		.perf = sdm845_perf_data,
+	};
+}
+
+static struct dpu_mdss_hw_cfg_handler cfg_handler[] = {
+	{ .hw_rev = DPU_HW_VER_400, .cfg_init = sdm845_cfg_init},
+	{ .hw_rev = DPU_HW_VER_401, .cfg_init = sdm845_cfg_init},
+};
+
+void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg)
+{
+	kfree(dpu_cfg);
+}
+
+struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev)
+{
+	int i;
+	struct dpu_mdss_cfg *dpu_cfg;
+
+	dpu_cfg = kzalloc(sizeof(*dpu_cfg), GFP_KERNEL);
+	if (!dpu_cfg)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; i < ARRAY_SIZE(cfg_handler); i++) {
+		if (cfg_handler[i].hw_rev == hw_rev) {
+			cfg_handler[i].cfg_init(dpu_cfg);
+			dpu_cfg->hwversion = hw_rev;
+			return dpu_cfg;
+		}
+	}
+
+	DPU_ERROR("unsupported chipset id:%X\n", hw_rev);
+	dpu_hw_catalog_deinit(dpu_cfg);
+	return ERR_PTR(-ENODEV);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
new file mode 100644
index 000000000000..f0cb0d4fc80e
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.h
@@ -0,0 +1,804 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CATALOG_H
+#define _DPU_HW_CATALOG_H
+
+#include <linux/kernel.h>
+#include <linux/bug.h>
+#include <linux/bitmap.h>
+#include <linux/err.h>
+#include <drm/drmP.h>
+
+/**
+ * Max hardware block count: For ex: max 12 SSPP pipes or
+ * 5 ctl paths. In all cases, it can have max 12 hardware blocks
+ * based on current design
+ */
+#define MAX_BLOCKS    12
+
+#define DPU_HW_VER(MAJOR, MINOR, STEP) (((MAJOR & 0xF) << 28)    |\
+		((MINOR & 0xFFF) << 16)  |\
+		(STEP & 0xFFFF))
+
+#define DPU_HW_MAJOR(rev)		((rev) >> 28)
+#define DPU_HW_MINOR(rev)		(((rev) >> 16) & 0xFFF)
+#define DPU_HW_STEP(rev)		((rev) & 0xFFFF)
+#define DPU_HW_MAJOR_MINOR(rev)		((rev) >> 16)
+
+#define IS_DPU_MAJOR_MINOR_SAME(rev1, rev2)   \
+	(DPU_HW_MAJOR_MINOR((rev1)) == DPU_HW_MAJOR_MINOR((rev2)))
+
+#define DPU_HW_VER_170	DPU_HW_VER(1, 7, 0) /* 8996 v1.0 */
+#define DPU_HW_VER_171	DPU_HW_VER(1, 7, 1) /* 8996 v2.0 */
+#define DPU_HW_VER_172	DPU_HW_VER(1, 7, 2) /* 8996 v3.0 */
+#define DPU_HW_VER_300	DPU_HW_VER(3, 0, 0) /* 8998 v1.0 */
+#define DPU_HW_VER_301	DPU_HW_VER(3, 0, 1) /* 8998 v1.1 */
+#define DPU_HW_VER_400	DPU_HW_VER(4, 0, 0) /* sdm845 v1.0 */
+#define DPU_HW_VER_401	DPU_HW_VER(4, 0, 1) /* sdm845 v2.0 */
+#define DPU_HW_VER_410	DPU_HW_VER(4, 1, 0) /* sdm670 v1.0 */
+#define DPU_HW_VER_500	DPU_HW_VER(5, 0, 0) /* sdm855 v1.0 */
+
+
+#define IS_MSM8996_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_170)
+#define IS_MSM8998_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_300)
+#define IS_SDM845_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_400)
+#define IS_SDM670_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_410)
+#define IS_SDM855_TARGET(rev) IS_DPU_MAJOR_MINOR_SAME((rev), DPU_HW_VER_500)
+
+
+#define DPU_HW_BLK_NAME_LEN	16
+
+#define MAX_IMG_WIDTH 0x3fff
+#define MAX_IMG_HEIGHT 0x3fff
+
+#define CRTC_DUAL_MIXERS	2
+
+#define MAX_XIN_COUNT 16
+
+/**
+ * Supported UBWC feature versions
+ */
+enum {
+	DPU_HW_UBWC_VER_10 = 0x100,
+	DPU_HW_UBWC_VER_20 = 0x200,
+	DPU_HW_UBWC_VER_30 = 0x300,
+};
+
+#define IS_UBWC_20_SUPPORTED(rev)       ((rev) >= DPU_HW_UBWC_VER_20)
+
+/**
+ * MDP TOP BLOCK features
+ * @DPU_MDP_PANIC_PER_PIPE Panic configuration needs to be be done per pipe
+ * @DPU_MDP_10BIT_SUPPORT, Chipset supports 10 bit pixel formats
+ * @DPU_MDP_BWC,           MDSS HW supports Bandwidth compression.
+ * @DPU_MDP_UBWC_1_0,      This chipsets supports Universal Bandwidth
+ *                         compression initial revision
+ * @DPU_MDP_UBWC_1_5,      Universal Bandwidth compression version 1.5
+ * @DPU_MDP_MAX            Maximum value
+
+ */
+enum {
+	DPU_MDP_PANIC_PER_PIPE = 0x1,
+	DPU_MDP_10BIT_SUPPORT,
+	DPU_MDP_BWC,
+	DPU_MDP_UBWC_1_0,
+	DPU_MDP_UBWC_1_5,
+	DPU_MDP_MAX
+};
+
+/**
+ * SSPP sub-blocks/features
+ * @DPU_SSPP_SRC             Src and fetch part of the pipes,
+ * @DPU_SSPP_SCALER_QSEED2,  QSEED2 algorithm support
+ * @DPU_SSPP_SCALER_QSEED3,  QSEED3 alogorithm support
+ * @DPU_SSPP_SCALER_RGB,     RGB Scaler, supported by RGB pipes
+ * @DPU_SSPP_CSC,            Support of Color space converion
+ * @DPU_SSPP_CSC_10BIT,      Support of 10-bit Color space conversion
+ * @DPU_SSPP_CURSOR,         SSPP can be used as a cursor layer
+ * @DPU_SSPP_QOS,            SSPP support QoS control, danger/safe/creq
+ * @DPU_SSPP_QOS_8LVL,       SSPP support 8-level QoS control
+ * @DPU_SSPP_EXCL_RECT,      SSPP supports exclusion rect
+ * @DPU_SSPP_SMART_DMA_V1,   SmartDMA 1.0 support
+ * @DPU_SSPP_SMART_DMA_V2,   SmartDMA 2.0 support
+ * @DPU_SSPP_TS_PREFILL      Supports prefill with traffic shaper
+ * @DPU_SSPP_TS_PREFILL_REC1 Supports prefill with traffic shaper multirec
+ * @DPU_SSPP_CDP             Supports client driven prefetch
+ * @DPU_SSPP_MAX             maximum value
+ */
+enum {
+	DPU_SSPP_SRC = 0x1,
+	DPU_SSPP_SCALER_QSEED2,
+	DPU_SSPP_SCALER_QSEED3,
+	DPU_SSPP_SCALER_RGB,
+	DPU_SSPP_CSC,
+	DPU_SSPP_CSC_10BIT,
+	DPU_SSPP_CURSOR,
+	DPU_SSPP_QOS,
+	DPU_SSPP_QOS_8LVL,
+	DPU_SSPP_EXCL_RECT,
+	DPU_SSPP_SMART_DMA_V1,
+	DPU_SSPP_SMART_DMA_V2,
+	DPU_SSPP_TS_PREFILL,
+	DPU_SSPP_TS_PREFILL_REC1,
+	DPU_SSPP_CDP,
+	DPU_SSPP_MAX
+};
+
+/*
+ * MIXER sub-blocks/features
+ * @DPU_MIXER_LAYER           Layer mixer layer blend configuration,
+ * @DPU_MIXER_SOURCESPLIT     Layer mixer supports source-split configuration
+ * @DPU_MIXER_GC              Gamma correction block
+ * @DPU_DIM_LAYER             Layer mixer supports dim layer
+ * @DPU_MIXER_MAX             maximum value
+ */
+enum {
+	DPU_MIXER_LAYER = 0x1,
+	DPU_MIXER_SOURCESPLIT,
+	DPU_MIXER_GC,
+	DPU_DIM_LAYER,
+	DPU_MIXER_MAX
+};
+
+/**
+ * PINGPONG sub-blocks
+ * @DPU_PINGPONG_TE         Tear check block
+ * @DPU_PINGPONG_TE2        Additional tear check block for split pipes
+ * @DPU_PINGPONG_SPLIT      PP block supports split fifo
+ * @DPU_PINGPONG_SLAVE      PP block is a suitable slave for split fifo
+ * @DPU_PINGPONG_DITHER,    Dither blocks
+ * @DPU_PINGPONG_MAX
+ */
+enum {
+	DPU_PINGPONG_TE = 0x1,
+	DPU_PINGPONG_TE2,
+	DPU_PINGPONG_SPLIT,
+	DPU_PINGPONG_SLAVE,
+	DPU_PINGPONG_DITHER,
+	DPU_PINGPONG_MAX
+};
+
+/**
+ * CTL sub-blocks
+ * @DPU_CTL_SPLIT_DISPLAY       CTL supports video mode split display
+ * @DPU_CTL_MAX
+ */
+enum {
+	DPU_CTL_SPLIT_DISPLAY = 0x1,
+	DPU_CTL_MAX
+};
+
+/**
+ * VBIF sub-blocks and features
+ * @DPU_VBIF_QOS_OTLIM        VBIF supports OT Limit
+ * @DPU_VBIF_QOS_REMAP        VBIF supports QoS priority remap
+ * @DPU_VBIF_MAX              maximum value
+ */
+enum {
+	DPU_VBIF_QOS_OTLIM = 0x1,
+	DPU_VBIF_QOS_REMAP,
+	DPU_VBIF_MAX
+};
+
+/**
+ * MACRO DPU_HW_BLK_INFO - information of HW blocks inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this block
+ * @base:              register base offset to mdss
+ * @len:               length of hardware block
+ * @features           bit mask identifying sub-blocks/features
+ */
+#define DPU_HW_BLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len; \
+	unsigned long features
+
+/**
+ * MACRO DPU_HW_SUBBLK_INFO - information of HW sub-block inside DPU
+ * @name:              string name for debug purposes
+ * @id:                enum identifying this sub-block
+ * @base:              offset of this sub-block relative to the block
+ *                     offset
+ * @len                register block length of this sub-block
+ */
+#define DPU_HW_SUBBLK_INFO \
+	char name[DPU_HW_BLK_NAME_LEN]; \
+	u32 id; \
+	u32 base; \
+	u32 len
+
+/**
+ * struct dpu_src_blk: SSPP part of the source pipes
+ * @info:   HW register and features supported by this sub-blk
+ */
+struct dpu_src_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_scaler_blk: Scaler information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: qseed block revision
+ */
+struct dpu_scaler_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+struct dpu_csc_blk {
+	DPU_HW_SUBBLK_INFO;
+};
+
+/**
+ * struct dpu_pp_blk : Pixel processing sub-blk information
+ * @info:   HW register and features supported by this sub-blk
+ * @version: HW Algorithm version
+ */
+struct dpu_pp_blk {
+	DPU_HW_SUBBLK_INFO;
+	u32 version;
+};
+
+/**
+ * struct dpu_format_extended - define dpu specific pixel format+modifier
+ * @fourcc_format: Base FOURCC pixel format code
+ * @modifier: 64-bit drm format modifier, same modifier must be applied to all
+ *            framebuffer planes
+ */
+struct dpu_format_extended {
+	uint32_t fourcc_format;
+	uint64_t modifier;
+};
+
+/**
+ * enum dpu_qos_lut_usage - define QoS LUT use cases
+ */
+enum dpu_qos_lut_usage {
+	DPU_QOS_LUT_USAGE_LINEAR,
+	DPU_QOS_LUT_USAGE_MACROTILE,
+	DPU_QOS_LUT_USAGE_NRT,
+	DPU_QOS_LUT_USAGE_MAX,
+};
+
+/**
+ * struct dpu_qos_lut_entry - define QoS LUT table entry
+ * @fl: fill level, or zero on last entry to indicate default lut
+ * @lut: lut to use if equal to or less than fill level
+ */
+struct dpu_qos_lut_entry {
+	u32 fl;
+	u64 lut;
+};
+
+/**
+ * struct dpu_qos_lut_tbl - define QoS LUT table
+ * @nentry: number of entry in this table
+ * @entries: Pointer to table entries
+ */
+struct dpu_qos_lut_tbl {
+	u32 nentry;
+	struct dpu_qos_lut_entry *entries;
+};
+
+/**
+ * struct dpu_caps - define DPU capabilities
+ * @max_mixer_width    max layer mixer line width support.
+ * @max_mixer_blendstages max layer mixer blend stages or
+ *                       supported z order
+ * @qseed_type         qseed2 or qseed3 support.
+ * @smart_dma_rev      Supported version of SmartDMA feature.
+ * @ubwc_version       UBWC feature version (0x0 for not supported)
+ * @has_src_split      source split feature status
+ * @has_dim_layer      dim layer feature status
+ * @has_idle_pc        indicate if idle power collapse feature is supported
+ */
+struct dpu_caps {
+	u32 max_mixer_width;
+	u32 max_mixer_blendstages;
+	u32 qseed_type;
+	u32 smart_dma_rev;
+	u32 ubwc_version;
+	bool has_src_split;
+	bool has_dim_layer;
+	bool has_idle_pc;
+};
+
+/**
+ * struct dpu_sspp_blks_common : SSPP sub-blocks common configuration
+ * @maxwidth: max pixelwidth supported by this pipe
+ * @pixel_ram_size: size of latency hiding and de-tiling buffer in bytes
+ * @maxhdeciexp: max horizontal decimation supported by this pipe
+ *				(max is 2^value)
+ * @maxvdeciexp: max vertical decimation supported by this pipe
+ *				(max is 2^value)
+ */
+struct dpu_sspp_blks_common {
+	u32 maxlinewidth;
+	u32 pixel_ram_size;
+	u32 maxhdeciexp;
+	u32 maxvdeciexp;
+};
+
+/**
+ * struct dpu_sspp_sub_blks : SSPP sub-blocks
+ * common: Pointer to common configurations shared by sub blocks
+ * @creq_vblank: creq priority during vertical blanking
+ * @danger_vblank: danger priority during vertical blanking
+ * @maxdwnscale: max downscale ratio supported(without DECIMATION)
+ * @maxupscale:  maxupscale ratio supported
+ * @smart_dma_priority: hw priority of rect1 of multirect pipe
+ * @max_per_pipe_bw: maximum allowable bandwidth of this pipe in kBps
+ * @src_blk:
+ * @scaler_blk:
+ * @csc_blk:
+ * @hsic:
+ * @memcolor:
+ * @pcc_blk:
+ * @igc_blk:
+ * @format_list: Pointer to list of supported formats
+ * @virt_format_list: Pointer to list of supported formats for virtual planes
+ */
+struct dpu_sspp_sub_blks {
+	const struct dpu_sspp_blks_common *common;
+	u32 creq_vblank;
+	u32 danger_vblank;
+	u32 maxdwnscale;
+	u32 maxupscale;
+	u32 smart_dma_priority;
+	u32 max_per_pipe_bw;
+	struct dpu_src_blk src_blk;
+	struct dpu_scaler_blk scaler_blk;
+	struct dpu_pp_blk csc_blk;
+	struct dpu_pp_blk hsic_blk;
+	struct dpu_pp_blk memcolor_blk;
+	struct dpu_pp_blk pcc_blk;
+	struct dpu_pp_blk igc_blk;
+
+	const struct dpu_format_extended *format_list;
+	const struct dpu_format_extended *virt_format_list;
+};
+
+/**
+ * struct dpu_lm_sub_blks:      information of mixer block
+ * @maxwidth:               Max pixel width supported by this mixer
+ * @maxblendstages:         Max number of blend-stages supported
+ * @blendstage_base:        Blend-stage register base offset
+ * @gc: gamma correction block
+ */
+struct dpu_lm_sub_blks {
+	u32 maxwidth;
+	u32 maxblendstages;
+	u32 blendstage_base[MAX_BLOCKS];
+	struct dpu_pp_blk gc;
+};
+
+struct dpu_pingpong_sub_blks {
+	struct dpu_pp_blk te;
+	struct dpu_pp_blk te2;
+	struct dpu_pp_blk dither;
+};
+
+/**
+ * dpu_clk_ctrl_type - Defines top level clock control signals
+ */
+enum dpu_clk_ctrl_type {
+	DPU_CLK_CTRL_NONE,
+	DPU_CLK_CTRL_VIG0,
+	DPU_CLK_CTRL_VIG1,
+	DPU_CLK_CTRL_VIG2,
+	DPU_CLK_CTRL_VIG3,
+	DPU_CLK_CTRL_VIG4,
+	DPU_CLK_CTRL_RGB0,
+	DPU_CLK_CTRL_RGB1,
+	DPU_CLK_CTRL_RGB2,
+	DPU_CLK_CTRL_RGB3,
+	DPU_CLK_CTRL_DMA0,
+	DPU_CLK_CTRL_DMA1,
+	DPU_CLK_CTRL_CURSOR0,
+	DPU_CLK_CTRL_CURSOR1,
+	DPU_CLK_CTRL_INLINE_ROT0_SSPP,
+	DPU_CLK_CTRL_MAX,
+};
+
+/* struct dpu_clk_ctrl_reg : Clock control register
+ * @reg_off:           register offset
+ * @bit_off:           bit offset
+ */
+struct dpu_clk_ctrl_reg {
+	u32 reg_off;
+	u32 bit_off;
+};
+
+/* struct dpu_mdp_cfg : MDP TOP-BLK instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ * @highest_bank_bit:  UBWC parameter
+ * @ubwc_static:       ubwc static configuration
+ * @ubwc_swizzle:      ubwc default swizzle setting
+ * @has_dest_scaler:   indicates support of destination scaler
+ * @clk_ctrls          clock control register definition
+ */
+struct dpu_mdp_cfg {
+	DPU_HW_BLK_INFO;
+	u32 highest_bank_bit;
+	u32 ubwc_static;
+	u32 ubwc_swizzle;
+	bool has_dest_scaler;
+	struct dpu_clk_ctrl_reg clk_ctrls[DPU_CLK_CTRL_MAX];
+};
+
+/* struct dpu_mdp_cfg : MDP TOP-BLK instance info
+ * @id:                index identifying this block
+ * @base:              register base offset to mdss
+ * @features           bit mask identifying sub-blocks/features
+ */
+struct dpu_ctl_cfg {
+	DPU_HW_BLK_INFO;
+};
+
+/**
+ * struct dpu_sspp_cfg - information of source pipes
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              SSPP sub-blocks information
+ * @xin_id:            bus client identifier
+ * @clk_ctrl           clock control identifier
+ * @type               sspp type identifier
+ */
+struct dpu_sspp_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_sspp_sub_blks *sblk;
+	u32 xin_id;
+	enum dpu_clk_ctrl_type clk_ctrl;
+	u32 type;
+};
+
+/**
+ * struct dpu_lm_cfg - information of layer mixer blocks
+ * @id:                index identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk:              LM Sub-blocks information
+ * @pingpong:          ID of connected PingPong, PINGPONG_MAX if unsupported
+ * @ds:                ID of connected DS, DS_MAX if unsupported
+ * @lm_pair_mask:      Bitmask of LMs that can be controlled by same CTL
+ */
+struct dpu_lm_cfg {
+	DPU_HW_BLK_INFO;
+	const struct dpu_lm_sub_blks *sblk;
+	u32 pingpong;
+	u32 ds;
+	unsigned long lm_pair_mask;
+};
+
+/**
+ * struct dpu_ds_top_cfg - information of dest scaler top
+ * @id               enum identifying this block
+ * @base             register offset of this block
+ * @features         bit mask identifying features
+ * @version          hw version of dest scaler
+ * @maxinputwidth    maximum input line width
+ * @maxoutputwidth   maximum output line width
+ * @maxupscale       maximum upscale ratio
+ */
+struct dpu_ds_top_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	u32 maxinputwidth;
+	u32 maxoutputwidth;
+	u32 maxupscale;
+};
+
+/**
+ * struct dpu_ds_cfg - information of dest scaler blocks
+ * @id          enum identifying this block
+ * @base        register offset wrt DS top offset
+ * @features    bit mask identifying features
+ * @version     hw version of the qseed block
+ * @top         DS top information
+ */
+struct dpu_ds_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	const struct dpu_ds_top_cfg *top;
+};
+
+/**
+ * struct dpu_pingpong_cfg - information of PING-PONG blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @sblk               sub-blocks information
+ */
+struct dpu_pingpong_cfg  {
+	DPU_HW_BLK_INFO;
+	const struct dpu_pingpong_sub_blks *sblk;
+};
+
+/**
+ * struct dpu_cdm_cfg - information of chroma down blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @intf_connect       Bitmask of INTF IDs this CDM can connect to
+ */
+struct dpu_cdm_cfg   {
+	DPU_HW_BLK_INFO;
+	unsigned long intf_connect;
+};
+
+/**
+ * struct dpu_intf_cfg - information of timing engine blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @type:              Interface type(DSI, DP, HDMI)
+ * @controller_id:     Controller Instance ID in case of multiple of intf type
+ * @prog_fetch_lines_worst_case	Worst case latency num lines needed to prefetch
+ */
+struct dpu_intf_cfg  {
+	DPU_HW_BLK_INFO;
+	u32 type;   /* interface type*/
+	u32 controller_id;
+	u32 prog_fetch_lines_worst_case;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_cfg - dynamic OT setting
+ * @pps                pixel per seconds
+ * @ot_limit           OT limit to use up to specified pixel per second
+ */
+struct dpu_vbif_dynamic_ot_cfg {
+	u64 pps;
+	u32 ot_limit;
+};
+
+/**
+ * struct dpu_vbif_dynamic_ot_tbl - dynamic OT setting table
+ * @count              length of cfg
+ * @cfg                pointer to array of configuration settings with
+ *                     ascending requirements
+ */
+struct dpu_vbif_dynamic_ot_tbl {
+	u32 count;
+	struct dpu_vbif_dynamic_ot_cfg *cfg;
+};
+
+/**
+ * struct dpu_vbif_qos_tbl - QoS priority table
+ * @npriority_lvl      num of priority level
+ * @priority_lvl       pointer to array of priority level in ascending order
+ */
+struct dpu_vbif_qos_tbl {
+	u32 npriority_lvl;
+	u32 *priority_lvl;
+};
+
+/**
+ * struct dpu_vbif_cfg - information of VBIF blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @ot_rd_limit        default OT read limit
+ * @ot_wr_limit        default OT write limit
+ * @xin_halt_timeout   maximum time (in usec) for xin to halt
+ * @dynamic_ot_rd_tbl  dynamic OT read configuration table
+ * @dynamic_ot_wr_tbl  dynamic OT write configuration table
+ * @qos_rt_tbl         real-time QoS priority table
+ * @qos_nrt_tbl        non-real-time QoS priority table
+ * @memtype_count      number of defined memtypes
+ * @memtype            array of xin memtype definitions
+ */
+struct dpu_vbif_cfg {
+	DPU_HW_BLK_INFO;
+	u32 default_ot_rd_limit;
+	u32 default_ot_wr_limit;
+	u32 xin_halt_timeout;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_rd_tbl;
+	struct dpu_vbif_dynamic_ot_tbl dynamic_ot_wr_tbl;
+	struct dpu_vbif_qos_tbl qos_rt_tbl;
+	struct dpu_vbif_qos_tbl qos_nrt_tbl;
+	u32 memtype_count;
+	u32 memtype[MAX_XIN_COUNT];
+};
+/**
+ * struct dpu_reg_dma_cfg - information of lut dma blocks
+ * @id                 enum identifying this block
+ * @base               register offset of this block
+ * @features           bit mask identifying sub-blocks/features
+ * @version            version of lutdma hw block
+ * @trigger_sel_off    offset to trigger select registers of lutdma
+ */
+struct dpu_reg_dma_cfg {
+	DPU_HW_BLK_INFO;
+	u32 version;
+	u32 trigger_sel_off;
+};
+
+/**
+ * Define CDP use cases
+ * @DPU_PERF_CDP_UDAGE_RT: real-time use cases
+ * @DPU_PERF_CDP_USAGE_NRT: non real-time use cases such as WFD
+ */
+enum {
+	DPU_PERF_CDP_USAGE_RT,
+	DPU_PERF_CDP_USAGE_NRT,
+	DPU_PERF_CDP_USAGE_MAX
+};
+
+/**
+ * struct dpu_perf_cdp_cfg - define CDP use case configuration
+ * @rd_enable: true if read pipe CDP is enabled
+ * @wr_enable: true if write pipe CDP is enabled
+ */
+struct dpu_perf_cdp_cfg {
+	bool rd_enable;
+	bool wr_enable;
+};
+
+/**
+ * struct dpu_perf_cfg - performance control settings
+ * @max_bw_low         low threshold of maximum bandwidth (kbps)
+ * @max_bw_high        high threshold of maximum bandwidth (kbps)
+ * @min_core_ib        minimum bandwidth for core (kbps)
+ * @min_core_ib        minimum mnoc ib vote in kbps
+ * @min_llcc_ib        minimum llcc ib vote in kbps
+ * @min_dram_ib        minimum dram ib vote in kbps
+ * @core_ib_ff         core instantaneous bandwidth fudge factor
+ * @core_clk_ff        core clock fudge factor
+ * @comp_ratio_rt      string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio>
+ * @comp_ratio_nrt     string of 0 or more of <fourcc>/<ven>/<mod>/<comp ratio>
+ * @undersized_prefill_lines   undersized prefill in lines
+ * @xtra_prefill_lines         extra prefill latency in lines
+ * @dest_scale_prefill_lines   destination scaler latency in lines
+ * @macrotile_perfill_lines    macrotile latency in lines
+ * @yuv_nv12_prefill_lines     yuv_nv12 latency in lines
+ * @linear_prefill_lines       linear latency in lines
+ * @downscaling_prefill_lines  downscaling latency in lines
+ * @amortizable_theshold minimum y position for traffic shaping prefill
+ * @min_prefill_lines  minimum pipeline latency in lines
+ * @safe_lut_tbl: LUT tables for safe signals
+ * @danger_lut_tbl: LUT tables for danger signals
+ * @qos_lut_tbl: LUT tables for QoS signals
+ * @cdp_cfg            cdp use case configurations
+ */
+struct dpu_perf_cfg {
+	u32 max_bw_low;
+	u32 max_bw_high;
+	u32 min_core_ib;
+	u32 min_llcc_ib;
+	u32 min_dram_ib;
+	const char *core_ib_ff;
+	const char *core_clk_ff;
+	const char *comp_ratio_rt;
+	const char *comp_ratio_nrt;
+	u32 undersized_prefill_lines;
+	u32 xtra_prefill_lines;
+	u32 dest_scale_prefill_lines;
+	u32 macrotile_prefill_lines;
+	u32 yuv_nv12_prefill_lines;
+	u32 linear_prefill_lines;
+	u32 downscaling_prefill_lines;
+	u32 amortizable_threshold;
+	u32 min_prefill_lines;
+	u32 safe_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	u32 danger_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_qos_lut_tbl qos_lut_tbl[DPU_QOS_LUT_USAGE_MAX];
+	struct dpu_perf_cdp_cfg cdp_cfg[DPU_PERF_CDP_USAGE_MAX];
+};
+
+/**
+ * struct dpu_mdss_cfg - information of MDSS HW
+ * This is the main catalog data structure representing
+ * this HW version. Contains number of instances,
+ * register offsets, capabilities of the all MDSS HW sub-blocks.
+ *
+ * @dma_formats        Supported formats for dma pipe
+ * @cursor_formats     Supported formats for cursor pipe
+ * @vig_formats        Supported formats for vig pipe
+ */
+struct dpu_mdss_cfg {
+	u32 hwversion;
+
+	const struct dpu_caps *caps;
+
+	u32 mdp_count;
+	struct dpu_mdp_cfg *mdp;
+
+	u32 ctl_count;
+	struct dpu_ctl_cfg *ctl;
+
+	u32 sspp_count;
+	struct dpu_sspp_cfg *sspp;
+
+	u32 mixer_count;
+	struct dpu_lm_cfg *mixer;
+
+	u32 ds_count;
+	struct dpu_ds_cfg *ds;
+
+	u32 pingpong_count;
+	struct dpu_pingpong_cfg *pingpong;
+
+	u32 cdm_count;
+	struct dpu_cdm_cfg *cdm;
+
+	u32 intf_count;
+	struct dpu_intf_cfg *intf;
+
+	u32 vbif_count;
+	struct dpu_vbif_cfg *vbif;
+
+	u32 reg_dma_count;
+	struct dpu_reg_dma_cfg dma_cfg;
+
+	u32 ad_count;
+
+	/* Add additional block data structures here */
+
+	struct dpu_perf_cfg perf;
+	struct dpu_format_extended *dma_formats;
+	struct dpu_format_extended *cursor_formats;
+	struct dpu_format_extended *vig_formats;
+};
+
+struct dpu_mdss_hw_cfg_handler {
+	u32 hw_rev;
+	void (*cfg_init)(struct dpu_mdss_cfg *dpu_cfg);
+};
+
+/*
+ * Access Macros
+ */
+#define BLK_MDP(s) ((s)->mdp)
+#define BLK_CTL(s) ((s)->ctl)
+#define BLK_VIG(s) ((s)->vig)
+#define BLK_RGB(s) ((s)->rgb)
+#define BLK_DMA(s) ((s)->dma)
+#define BLK_CURSOR(s) ((s)->cursor)
+#define BLK_MIXER(s) ((s)->mixer)
+#define BLK_DS(s) ((s)->ds)
+#define BLK_PINGPONG(s) ((s)->pingpong)
+#define BLK_CDM(s) ((s)->cdm)
+#define BLK_INTF(s) ((s)->intf)
+#define BLK_AD(s) ((s)->ad)
+
+/**
+ * dpu_hw_catalog_init - dpu hardware catalog init API retrieves
+ * hardcoded target specific catalog information in config structure
+ * @hw_rev:       caller needs provide the hardware revision.
+ *
+ * Return: dpu config structure
+ */
+struct dpu_mdss_cfg *dpu_hw_catalog_init(u32 hw_rev);
+
+/**
+ * dpu_hw_catalog_deinit - dpu hardware catalog cleanup
+ * @dpu_cfg:      pointer returned from init function
+ */
+void dpu_hw_catalog_deinit(struct dpu_mdss_cfg *dpu_cfg);
+
+/**
+ * dpu_hw_sspp_multirect_enabled - check multirect enabled for the sspp
+ * @cfg:          pointer to sspp cfg
+ */
+static inline bool dpu_hw_sspp_multirect_enabled(const struct dpu_sspp_cfg *cfg)
+{
+	return test_bit(DPU_SSPP_SMART_DMA_V1, &cfg->features) ||
+			 test_bit(DPU_SSPP_SMART_DMA_V2, &cfg->features);
+}
+#endif /* _DPU_HW_CATALOG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
new file mode 100644
index 000000000000..3c9f028628ef
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog_format.h
@@ -0,0 +1,168 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hw_mdss.h"
+
+static const struct dpu_format_extended plane_formats[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended plane_formats_yuv[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+
+	{DRM_FORMAT_NV12, 0},
+	{DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_NV21, 0},
+	{DRM_FORMAT_NV16, 0},
+	{DRM_FORMAT_NV61, 0},
+	{DRM_FORMAT_VYUY, 0},
+	{DRM_FORMAT_UYVY, 0},
+	{DRM_FORMAT_YUYV, 0},
+	{DRM_FORMAT_YVYU, 0},
+	{DRM_FORMAT_YUV420, 0},
+	{DRM_FORMAT_YVU420, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended cursor_formats[] = {
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{0, 0},
+};
+
+static const struct dpu_format_extended wb2_formats[] = {
+	{DRM_FORMAT_RGB565, 0},
+	{DRM_FORMAT_BGR565, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_RGB888, 0},
+	{DRM_FORMAT_ARGB8888, 0},
+	{DRM_FORMAT_RGBA8888, 0},
+	{DRM_FORMAT_ABGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_XRGB8888, 0},
+	{DRM_FORMAT_RGBX8888, 0},
+	{DRM_FORMAT_XBGR8888, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_ARGB1555, 0},
+	{DRM_FORMAT_RGBA5551, 0},
+	{DRM_FORMAT_XRGB1555, 0},
+	{DRM_FORMAT_RGBX5551, 0},
+	{DRM_FORMAT_ARGB4444, 0},
+	{DRM_FORMAT_RGBA4444, 0},
+	{DRM_FORMAT_RGBX4444, 0},
+	{DRM_FORMAT_XRGB4444, 0},
+
+	{DRM_FORMAT_BGR565, 0},
+	{DRM_FORMAT_BGR888, 0},
+	{DRM_FORMAT_ABGR8888, 0},
+	{DRM_FORMAT_BGRA8888, 0},
+	{DRM_FORMAT_BGRX8888, 0},
+	{DRM_FORMAT_XBGR8888, 0},
+	{DRM_FORMAT_ABGR1555, 0},
+	{DRM_FORMAT_BGRA5551, 0},
+	{DRM_FORMAT_XBGR1555, 0},
+	{DRM_FORMAT_BGRX5551, 0},
+	{DRM_FORMAT_ABGR4444, 0},
+	{DRM_FORMAT_BGRA4444, 0},
+	{DRM_FORMAT_BGRX4444, 0},
+	{DRM_FORMAT_XBGR4444, 0},
+
+	{DRM_FORMAT_YUV420, 0},
+	{DRM_FORMAT_NV12, 0},
+	{DRM_FORMAT_NV12, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_NV16, 0},
+	{DRM_FORMAT_YUYV, 0},
+
+	{0, 0},
+};
+
+static const struct dpu_format_extended rgb_10bit_formats[] = {
+	{DRM_FORMAT_BGRA1010102, 0},
+	{DRM_FORMAT_BGRX1010102, 0},
+	{DRM_FORMAT_RGBA1010102, 0},
+	{DRM_FORMAT_RGBX1010102, 0},
+	{DRM_FORMAT_ABGR2101010, 0},
+	{DRM_FORMAT_ABGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_XBGR2101010, 0},
+	{DRM_FORMAT_XBGR2101010, DRM_FORMAT_MOD_QCOM_COMPRESSED},
+	{DRM_FORMAT_ARGB2101010, 0},
+	{DRM_FORMAT_XRGB2101010, 0},
+};
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
new file mode 100644
index 000000000000..da6f0609be5f
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
@@ -0,0 +1,323 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define CDM_CSC_10_OPMODE                  0x000
+#define CDM_CSC_10_BASE                    0x004
+
+#define CDM_CDWN2_OP_MODE                  0x100
+#define CDM_CDWN2_CLAMP_OUT                0x104
+#define CDM_CDWN2_PARAMS_3D_0              0x108
+#define CDM_CDWN2_PARAMS_3D_1              0x10C
+#define CDM_CDWN2_COEFF_COSITE_H_0         0x110
+#define CDM_CDWN2_COEFF_COSITE_H_1         0x114
+#define CDM_CDWN2_COEFF_COSITE_H_2         0x118
+#define CDM_CDWN2_COEFF_OFFSITE_H_0        0x11C
+#define CDM_CDWN2_COEFF_OFFSITE_H_1        0x120
+#define CDM_CDWN2_COEFF_OFFSITE_H_2        0x124
+#define CDM_CDWN2_COEFF_COSITE_V           0x128
+#define CDM_CDWN2_COEFF_OFFSITE_V          0x12C
+#define CDM_CDWN2_OUT_SIZE                 0x130
+
+#define CDM_HDMI_PACK_OP_MODE              0x200
+#define CDM_CSC_10_MATRIX_COEFF_0          0x004
+
+/**
+ * Horizontal coefficients for cosite chroma downscale
+ * s13 representation of coefficients
+ */
+static u32 cosite_h_coeff[] = {0x00000016, 0x000001cc, 0x0100009e};
+
+/**
+ * Horizontal coefficients for offsite chroma downscale
+ */
+static u32 offsite_h_coeff[] = {0x000b0005, 0x01db01eb, 0x00e40046};
+
+/**
+ * Vertical coefficients for cosite chroma downscale
+ */
+static u32 cosite_v_coeff[] = {0x00080004};
+/**
+ * Vertical coefficients for offsite chroma downscale
+ */
+static u32 offsite_v_coeff[] = {0x00060002};
+
+/* Limited Range rgb2yuv coeff with clamp and bias values for CSC 10 module */
+static struct dpu_csc_cfg rgb2yuv_cfg = {
+	{
+		0x0083, 0x0102, 0x0032,
+		0x1fb5, 0x1f6c, 0x00e1,
+		0x00e1, 0x1f45, 0x1fdc
+	},
+	{ 0x00, 0x00, 0x00 },
+	{ 0x0040, 0x0200, 0x0200 },
+	{ 0x000, 0x3ff, 0x000, 0x3ff, 0x000, 0x3ff },
+	{ 0x040, 0x3ac, 0x040, 0x3c0, 0x040, 0x3c0 },
+};
+
+static struct dpu_cdm_cfg *_cdm_offset(enum dpu_cdm cdm,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->cdm_count; i++) {
+		if (cdm == m->cdm[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->cdm[i].base;
+			b->length = m->cdm[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_CDM;
+			return &m->cdm[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int dpu_hw_cdm_setup_csc_10bit(struct dpu_hw_cdm *ctx,
+		struct dpu_csc_cfg *data)
+{
+	dpu_hw_csc_setup(&ctx->hw, CDM_CSC_10_MATRIX_COEFF_0, data, true);
+
+	return 0;
+}
+
+static int dpu_hw_cdm_setup_cdwn(struct dpu_hw_cdm *ctx,
+		struct dpu_hw_cdm_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 opmode = 0;
+	u32 out_size = 0;
+
+	if (cfg->output_bit_depth == CDM_CDWN_OUTPUT_10BIT)
+		opmode &= ~BIT(7);
+	else
+		opmode |= BIT(7);
+
+	/* ENABLE DWNS_H bit */
+	opmode |= BIT(1);
+
+	switch (cfg->h_cdwn_type) {
+	case CDM_CDWN_DISABLE:
+		/* CLEAR METHOD_H field */
+		opmode &= ~(0x18);
+		/* CLEAR DWNS_H bit */
+		opmode &= ~BIT(1);
+		break;
+	case CDM_CDWN_PIXEL_DROP:
+		/* Clear METHOD_H field (pixel drop is 0) */
+		opmode &= ~(0x18);
+		break;
+	case CDM_CDWN_AVG:
+		/* Clear METHOD_H field (Average is 0x1) */
+		opmode &= ~(0x18);
+		opmode |= (0x1 << 0x3);
+		break;
+	case CDM_CDWN_COSITE:
+		/* Clear METHOD_H field (Average is 0x2) */
+		opmode &= ~(0x18);
+		opmode |= (0x2 << 0x3);
+		/* Co-site horizontal coefficients */
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_0,
+				cosite_h_coeff[0]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_1,
+				cosite_h_coeff[1]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_COSITE_H_2,
+				cosite_h_coeff[2]);
+		break;
+	case CDM_CDWN_OFFSITE:
+		/* Clear METHOD_H field (Average is 0x3) */
+		opmode &= ~(0x18);
+		opmode |= (0x3 << 0x3);
+
+		/* Off-site horizontal coefficients */
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_0,
+				offsite_h_coeff[0]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_1,
+				offsite_h_coeff[1]);
+		DPU_REG_WRITE(c, CDM_CDWN2_COEFF_OFFSITE_H_2,
+				offsite_h_coeff[2]);
+		break;
+	default:
+		pr_err("%s invalid horz down sampling type\n", __func__);
+		return -EINVAL;
+	}
+
+	/* ENABLE DWNS_V bit */
+	opmode |= BIT(2);
+
+	switch (cfg->v_cdwn_type) {
+	case CDM_CDWN_DISABLE:
+		/* CLEAR METHOD_V field */
+		opmode &= ~(0x60);
+		/* CLEAR DWNS_V bit */
+		opmode &= ~BIT(2);
+		break;
+	case CDM_CDWN_PIXEL_DROP:
+		/* Clear METHOD_V field (pixel drop is 0) */
+		opmode &= ~(0x60);
+		break;
+	case CDM_CDWN_AVG:
+		/* Clear METHOD_V field (Average is 0x1) */
+		opmode &= ~(0x60);
+		opmode |= (0x1 << 0x5);
+		break;
+	case CDM_CDWN_COSITE:
+		/* Clear METHOD_V field (Average is 0x2) */
+		opmode &= ~(0x60);
+		opmode |= (0x2 << 0x5);
+		/* Co-site vertical coefficients */
+		DPU_REG_WRITE(c,
+				CDM_CDWN2_COEFF_COSITE_V,
+				cosite_v_coeff[0]);
+		break;
+	case CDM_CDWN_OFFSITE:
+		/* Clear METHOD_V field (Average is 0x3) */
+		opmode &= ~(0x60);
+		opmode |= (0x3 << 0x5);
+
+		/* Off-site vertical coefficients */
+		DPU_REG_WRITE(c,
+				CDM_CDWN2_COEFF_OFFSITE_V,
+				offsite_v_coeff[0]);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (cfg->v_cdwn_type || cfg->h_cdwn_type)
+		opmode |= BIT(0); /* EN CDWN module */
+	else
+		opmode &= ~BIT(0);
+
+	out_size = (cfg->output_width & 0xFFFF) |
+		((cfg->output_height & 0xFFFF) << 16);
+	DPU_REG_WRITE(c, CDM_CDWN2_OUT_SIZE, out_size);
+	DPU_REG_WRITE(c, CDM_CDWN2_OP_MODE, opmode);
+	DPU_REG_WRITE(c, CDM_CDWN2_CLAMP_OUT,
+			((0x3FF << 16) | 0x0));
+
+	return 0;
+}
+
+int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx,
+		struct dpu_hw_cdm_cfg *cdm)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	const struct dpu_format *fmt = cdm->output_fmt;
+	struct cdm_output_cfg cdm_cfg = { 0 };
+	u32 opmode = 0;
+	u32 csc = 0;
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		return -EINVAL;
+
+	if (cdm->output_type == CDM_CDWN_OUTPUT_HDMI) {
+		if (fmt->chroma_sample != DPU_CHROMA_H1V2)
+			return -EINVAL; /*unsupported format */
+		opmode = BIT(0);
+		opmode |= (fmt->chroma_sample << 1);
+		cdm_cfg.intf_en = true;
+	}
+
+	csc |= BIT(2);
+	csc &= ~BIT(1);
+	csc |= BIT(0);
+
+	if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output)
+		ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg);
+
+	DPU_REG_WRITE(c, CDM_CSC_10_OPMODE, csc);
+	DPU_REG_WRITE(c, CDM_HDMI_PACK_OP_MODE, opmode);
+	return 0;
+}
+
+void dpu_hw_cdm_disable(struct dpu_hw_cdm *ctx)
+{
+	struct cdm_output_cfg cdm_cfg = { 0 };
+
+	if (ctx->hw_mdp && ctx->hw_mdp->ops.setup_cdm_output)
+		ctx->hw_mdp->ops.setup_cdm_output(ctx->hw_mdp, &cdm_cfg);
+}
+
+static void _setup_cdm_ops(struct dpu_hw_cdm_ops *ops,
+	unsigned long features)
+{
+	ops->setup_csc_data = dpu_hw_cdm_setup_csc_10bit;
+	ops->setup_cdwn = dpu_hw_cdm_setup_cdwn;
+	ops->enable = dpu_hw_cdm_enable;
+	ops->disable = dpu_hw_cdm_disable;
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m,
+		struct dpu_hw_mdp *hw_mdp)
+{
+	struct dpu_hw_cdm *c;
+	struct dpu_cdm_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _cdm_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_cdm_ops(&c->ops, c->caps->features);
+	c->hw_mdp = hw_mdp;
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CDM, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	/*
+	 * Perform any default initialization for the chroma down module
+	 * @setup default csc coefficients
+	 */
+	dpu_hw_cdm_setup_csc_10bit(c, &rgb2yuv_cfg);
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm)
+{
+	if (cdm)
+		dpu_hw_blk_destroy(&cdm->base);
+	kfree(cdm);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h
new file mode 100644
index 000000000000..5cceb1ecb8e0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.h
@@ -0,0 +1,139 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CDM_H
+#define _DPU_HW_CDM_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_top.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_cdm;
+
+struct dpu_hw_cdm_cfg {
+	u32 output_width;
+	u32 output_height;
+	u32 output_bit_depth;
+	u32 h_cdwn_type;
+	u32 v_cdwn_type;
+	const struct dpu_format *output_fmt;
+	u32 output_type;
+	int flags;
+};
+
+enum dpu_hw_cdwn_type {
+	CDM_CDWN_DISABLE,
+	CDM_CDWN_PIXEL_DROP,
+	CDM_CDWN_AVG,
+	CDM_CDWN_COSITE,
+	CDM_CDWN_OFFSITE,
+};
+
+enum dpu_hw_cdwn_output_type {
+	CDM_CDWN_OUTPUT_HDMI,
+	CDM_CDWN_OUTPUT_WB,
+};
+
+enum dpu_hw_cdwn_output_bit_depth {
+	CDM_CDWN_OUTPUT_8BIT,
+	CDM_CDWN_OUTPUT_10BIT,
+};
+
+/**
+ * struct dpu_hw_cdm_ops : Interface to the chroma down Hw driver functions
+ *                         Assumption is these functions will be called after
+ *                         clocks are enabled
+ *  @setup_csc:            Programs the csc matrix
+ *  @setup_cdwn:           Sets up the chroma down sub module
+ *  @enable:               Enables the output to interface and programs the
+ *                         output packer
+ *  @disable:              Puts the cdm in bypass mode
+ */
+struct dpu_hw_cdm_ops {
+	/**
+	 * Programs the CSC matrix for conversion from RGB space to YUV space,
+	 * it is optional to call this function as this matrix is automatically
+	 * set during initialization, user should call this if it wants
+	 * to program a different matrix than default matrix.
+	 * @cdm:          Pointer to the chroma down context structure
+	 * @data          Pointer to CSC configuration data
+	 * return:        0 if success; error code otherwise
+	 */
+	int (*setup_csc_data)(struct dpu_hw_cdm *cdm,
+			struct dpu_csc_cfg *data);
+
+	/**
+	 * Programs the Chroma downsample part.
+	 * @cdm         Pointer to chroma down context
+	 */
+	int (*setup_cdwn)(struct dpu_hw_cdm *cdm,
+	struct dpu_hw_cdm_cfg *cfg);
+
+	/**
+	 * Enable the CDM module
+	 * @cdm         Pointer to chroma down context
+	 */
+	int (*enable)(struct dpu_hw_cdm *cdm,
+	struct dpu_hw_cdm_cfg *cfg);
+
+	/**
+	 * Disable the CDM module
+	 * @cdm         Pointer to chroma down context
+	 */
+	void (*disable)(struct dpu_hw_cdm *cdm);
+};
+
+struct dpu_hw_cdm {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* chroma down */
+	const struct dpu_cdm_cfg *caps;
+	enum  dpu_cdm  idx;
+
+	/* mdp top hw driver */
+	struct dpu_hw_mdp *hw_mdp;
+
+	/* ops */
+	struct dpu_hw_cdm_ops ops;
+};
+
+/**
+ * dpu_hw_cdm - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_cdm *to_dpu_hw_cdm(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_cdm, base);
+}
+
+/**
+ * dpu_hw_cdm_init - initializes the cdm hw driver object.
+ * should be called once before accessing every cdm.
+ * @idx:  cdm index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ * @hw_mdp:  pointer to mdp top hw driver object
+ */
+struct dpu_hw_cdm *dpu_hw_cdm_init(enum dpu_cdm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m,
+		struct dpu_hw_mdp *hw_mdp);
+
+/**
+ * dpu_hw_cdm_destroy - destroys CDM driver context
+ * @cdm:   pointer to CDM driver context
+ */
+void dpu_hw_cdm_destroy(struct dpu_hw_cdm *cdm);
+
+#endif /*_DPU_HW_CDM_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
new file mode 100644
index 000000000000..06be7cf7ce50
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c
@@ -0,0 +1,540 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/delay.h>
+#include "dpu_hwio.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define   CTL_LAYER(lm)                 \
+	(((lm) == LM_5) ? (0x024) : (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT(lm)             \
+	(0x40 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT2(lm)             \
+	(0x70 + (((lm) - LM_0) * 0x004))
+#define   CTL_LAYER_EXT3(lm)             \
+	(0xA0 + (((lm) - LM_0) * 0x004))
+#define   CTL_TOP                       0x014
+#define   CTL_FLUSH                     0x018
+#define   CTL_START                     0x01C
+#define   CTL_PREPARE                   0x0d0
+#define   CTL_SW_RESET                  0x030
+#define   CTL_LAYER_EXTN_OFFSET         0x40
+
+#define CTL_MIXER_BORDER_OUT            BIT(24)
+#define CTL_FLUSH_MASK_CTL              BIT(17)
+
+#define DPU_REG_RESET_TIMEOUT_US        2000
+
+static struct dpu_ctl_cfg *_ctl_offset(enum dpu_ctl ctl,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->ctl_count; i++) {
+		if (ctl == m->ctl[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->ctl[i].base;
+			b->length = m->ctl[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_CTL;
+			return &m->ctl[i];
+		}
+	}
+	return ERR_PTR(-ENOMEM);
+}
+
+static int _mixer_stages(const struct dpu_lm_cfg *mixer, int count,
+		enum dpu_lm lm)
+{
+	int i;
+	int stages = -EINVAL;
+
+	for (i = 0; i < count; i++) {
+		if (lm == mixer[i].id) {
+			stages = mixer[i].sblk->maxblendstages;
+			break;
+		}
+	}
+
+	return stages;
+}
+
+static inline void dpu_hw_ctl_trigger_start(struct dpu_hw_ctl *ctx)
+{
+	DPU_REG_WRITE(&ctx->hw, CTL_START, 0x1);
+}
+
+static inline void dpu_hw_ctl_trigger_pending(struct dpu_hw_ctl *ctx)
+{
+	DPU_REG_WRITE(&ctx->hw, CTL_PREPARE, 0x1);
+}
+
+static inline void dpu_hw_ctl_clear_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	ctx->pending_flush_mask = 0x0;
+}
+
+static inline void dpu_hw_ctl_update_pending_flush(struct dpu_hw_ctl *ctx,
+		u32 flushbits)
+{
+	ctx->pending_flush_mask |= flushbits;
+}
+
+static u32 dpu_hw_ctl_get_pending_flush(struct dpu_hw_ctl *ctx)
+{
+	if (!ctx)
+		return 0x0;
+
+	return ctx->pending_flush_mask;
+}
+
+static inline void dpu_hw_ctl_trigger_flush(struct dpu_hw_ctl *ctx)
+{
+
+	DPU_REG_WRITE(&ctx->hw, CTL_FLUSH, ctx->pending_flush_mask);
+}
+
+static inline u32 dpu_hw_ctl_get_flush_register(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, CTL_FLUSH);
+}
+
+static inline uint32_t dpu_hw_ctl_get_bitmask_sspp(struct dpu_hw_ctl *ctx,
+	enum dpu_sspp sspp)
+{
+	uint32_t flushbits = 0;
+
+	switch (sspp) {
+	case SSPP_VIG0:
+		flushbits =  BIT(0);
+		break;
+	case SSPP_VIG1:
+		flushbits = BIT(1);
+		break;
+	case SSPP_VIG2:
+		flushbits = BIT(2);
+		break;
+	case SSPP_VIG3:
+		flushbits = BIT(18);
+		break;
+	case SSPP_RGB0:
+		flushbits = BIT(3);
+		break;
+	case SSPP_RGB1:
+		flushbits = BIT(4);
+		break;
+	case SSPP_RGB2:
+		flushbits = BIT(5);
+		break;
+	case SSPP_RGB3:
+		flushbits = BIT(19);
+		break;
+	case SSPP_DMA0:
+		flushbits = BIT(11);
+		break;
+	case SSPP_DMA1:
+		flushbits = BIT(12);
+		break;
+	case SSPP_DMA2:
+		flushbits = BIT(24);
+		break;
+	case SSPP_DMA3:
+		flushbits = BIT(25);
+		break;
+	case SSPP_CURSOR0:
+		flushbits = BIT(22);
+		break;
+	case SSPP_CURSOR1:
+		flushbits = BIT(23);
+		break;
+	default:
+		break;
+	}
+
+	return flushbits;
+}
+
+static inline uint32_t dpu_hw_ctl_get_bitmask_mixer(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm)
+{
+	uint32_t flushbits = 0;
+
+	switch (lm) {
+	case LM_0:
+		flushbits = BIT(6);
+		break;
+	case LM_1:
+		flushbits = BIT(7);
+		break;
+	case LM_2:
+		flushbits = BIT(8);
+		break;
+	case LM_3:
+		flushbits = BIT(9);
+		break;
+	case LM_4:
+		flushbits = BIT(10);
+		break;
+	case LM_5:
+		flushbits = BIT(20);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	flushbits |= CTL_FLUSH_MASK_CTL;
+
+	return flushbits;
+}
+
+static inline int dpu_hw_ctl_get_bitmask_intf(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_intf intf)
+{
+	switch (intf) {
+	case INTF_0:
+		*flushbits |= BIT(31);
+		break;
+	case INTF_1:
+		*flushbits |= BIT(30);
+		break;
+	case INTF_2:
+		*flushbits |= BIT(29);
+		break;
+	case INTF_3:
+		*flushbits |= BIT(28);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static inline int dpu_hw_ctl_get_bitmask_cdm(struct dpu_hw_ctl *ctx,
+		u32 *flushbits, enum dpu_cdm cdm)
+{
+	switch (cdm) {
+	case CDM_0:
+		*flushbits |= BIT(26);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static u32 dpu_hw_ctl_poll_reset_status(struct dpu_hw_ctl *ctx, u32 timeout_us)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	ktime_t timeout;
+	u32 status;
+
+	timeout = ktime_add_us(ktime_get(), timeout_us);
+
+	/*
+	 * it takes around 30us to have mdp finish resetting its ctl path
+	 * poll every 50us so that reset should be completed at 1st poll
+	 */
+	do {
+		status = DPU_REG_READ(c, CTL_SW_RESET);
+		status &= 0x1;
+		if (status)
+			usleep_range(20, 50);
+	} while (status && ktime_compare_safe(ktime_get(), timeout) < 0);
+
+	return status;
+}
+
+static int dpu_hw_ctl_reset_control(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	pr_debug("issuing hw ctl reset for ctl:%d\n", ctx->idx);
+	DPU_REG_WRITE(c, CTL_SW_RESET, 0x1);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int dpu_hw_ctl_wait_reset_status(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 status;
+
+	status = DPU_REG_READ(c, CTL_SW_RESET);
+	status &= 0x01;
+	if (!status)
+		return 0;
+
+	pr_debug("hw ctl reset is set for ctl:%d\n", ctx->idx);
+	if (dpu_hw_ctl_poll_reset_status(ctx, DPU_REG_RESET_TIMEOUT_US)) {
+		pr_err("hw recovery is not complete for ctl:%d\n", ctx->idx);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void dpu_hw_ctl_clear_all_blendstages(struct dpu_hw_ctl *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int i;
+
+	for (i = 0; i < ctx->mixer_count; i++) {
+		DPU_REG_WRITE(c, CTL_LAYER(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT2(LM_0 + i), 0);
+		DPU_REG_WRITE(c, CTL_LAYER_EXT3(LM_0 + i), 0);
+	}
+}
+
+static void dpu_hw_ctl_setup_blendstage(struct dpu_hw_ctl *ctx,
+	enum dpu_lm lm, struct dpu_hw_stage_cfg *stage_cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 mixercfg = 0, mixercfg_ext = 0, mix, ext;
+	u32 mixercfg_ext2 = 0, mixercfg_ext3 = 0;
+	int i, j;
+	u8 stages;
+	int pipes_per_stage;
+
+	stages = _mixer_stages(ctx->mixer_hw_caps, ctx->mixer_count, lm);
+	if (stages < 0)
+		return;
+
+	if (test_bit(DPU_MIXER_SOURCESPLIT,
+		&ctx->mixer_hw_caps->features))
+		pipes_per_stage = PIPES_PER_STAGE;
+	else
+		pipes_per_stage = 1;
+
+	mixercfg = CTL_MIXER_BORDER_OUT; /* always set BORDER_OUT */
+
+	if (!stage_cfg)
+		goto exit;
+
+	for (i = 0; i <= stages; i++) {
+		/* overflow to ext register if 'i + 1 > 7' */
+		mix = (i + 1) & 0x7;
+		ext = i >= 7;
+
+		for (j = 0 ; j < pipes_per_stage; j++) {
+			enum dpu_sspp_multirect_index rect_index =
+				stage_cfg->multirect_index[i][j];
+
+			switch (stage_cfg->stage[i][j]) {
+			case SSPP_VIG0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 0;
+				} else {
+					mixercfg |= mix << 0;
+					mixercfg_ext |= ext << 0;
+				}
+				break;
+			case SSPP_VIG1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 4;
+				} else {
+					mixercfg |= mix << 3;
+					mixercfg_ext |= ext << 2;
+				}
+				break;
+			case SSPP_VIG2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 6;
+					mixercfg_ext |= ext << 4;
+				}
+				break;
+			case SSPP_VIG3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext3 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 26;
+					mixercfg_ext |= ext << 6;
+				}
+				break;
+			case SSPP_RGB0:
+				mixercfg |= mix << 9;
+				mixercfg_ext |= ext << 8;
+				break;
+			case SSPP_RGB1:
+				mixercfg |= mix << 12;
+				mixercfg_ext |= ext << 10;
+				break;
+			case SSPP_RGB2:
+				mixercfg |= mix << 15;
+				mixercfg_ext |= ext << 12;
+				break;
+			case SSPP_RGB3:
+				mixercfg |= mix << 29;
+				mixercfg_ext |= ext << 14;
+				break;
+			case SSPP_DMA0:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 8;
+				} else {
+					mixercfg |= mix << 18;
+					mixercfg_ext |= ext << 16;
+				}
+				break;
+			case SSPP_DMA1:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 12;
+				} else {
+					mixercfg |= mix << 21;
+					mixercfg_ext |= ext << 18;
+				}
+				break;
+			case SSPP_DMA2:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 16;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 0;
+				}
+				break;
+			case SSPP_DMA3:
+				if (rect_index == DPU_SSPP_RECT_1) {
+					mixercfg_ext2 |= ((i + 1) & 0xF) << 20;
+				} else {
+					mix |= (i + 1) & 0xF;
+					mixercfg_ext2 |= mix << 4;
+				}
+				break;
+			case SSPP_CURSOR0:
+				mixercfg_ext |= ((i + 1) & 0xF) << 20;
+				break;
+			case SSPP_CURSOR1:
+				mixercfg_ext |= ((i + 1) & 0xF) << 26;
+				break;
+			default:
+				break;
+			}
+		}
+	}
+
+exit:
+	DPU_REG_WRITE(c, CTL_LAYER(lm), mixercfg);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT(lm), mixercfg_ext);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT2(lm), mixercfg_ext2);
+	DPU_REG_WRITE(c, CTL_LAYER_EXT3(lm), mixercfg_ext3);
+}
+
+static void dpu_hw_ctl_intf_cfg(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 intf_cfg = 0;
+
+	intf_cfg |= (cfg->intf & 0xF) << 4;
+
+	if (cfg->mode_3d) {
+		intf_cfg |= BIT(19);
+		intf_cfg |= (cfg->mode_3d - 0x1) << 20;
+	}
+
+	switch (cfg->intf_mode_sel) {
+	case DPU_CTL_MODE_SEL_VID:
+		intf_cfg &= ~BIT(17);
+		intf_cfg &= ~(0x3 << 15);
+		break;
+	case DPU_CTL_MODE_SEL_CMD:
+		intf_cfg |= BIT(17);
+		intf_cfg |= ((cfg->stream_sel & 0x3) << 15);
+		break;
+	default:
+		pr_err("unknown interface type %d\n", cfg->intf_mode_sel);
+		return;
+	}
+
+	DPU_REG_WRITE(c, CTL_TOP, intf_cfg);
+}
+
+static void _setup_ctl_ops(struct dpu_hw_ctl_ops *ops,
+		unsigned long cap)
+{
+	ops->clear_pending_flush = dpu_hw_ctl_clear_pending_flush;
+	ops->update_pending_flush = dpu_hw_ctl_update_pending_flush;
+	ops->get_pending_flush = dpu_hw_ctl_get_pending_flush;
+	ops->trigger_flush = dpu_hw_ctl_trigger_flush;
+	ops->get_flush_register = dpu_hw_ctl_get_flush_register;
+	ops->trigger_start = dpu_hw_ctl_trigger_start;
+	ops->trigger_pending = dpu_hw_ctl_trigger_pending;
+	ops->setup_intf_cfg = dpu_hw_ctl_intf_cfg;
+	ops->reset = dpu_hw_ctl_reset_control;
+	ops->wait_reset_status = dpu_hw_ctl_wait_reset_status;
+	ops->clear_all_blendstages = dpu_hw_ctl_clear_all_blendstages;
+	ops->setup_blendstage = dpu_hw_ctl_setup_blendstage;
+	ops->get_bitmask_sspp = dpu_hw_ctl_get_bitmask_sspp;
+	ops->get_bitmask_mixer = dpu_hw_ctl_get_bitmask_mixer;
+	ops->get_bitmask_intf = dpu_hw_ctl_get_bitmask_intf;
+	ops->get_bitmask_cdm = dpu_hw_ctl_get_bitmask_cdm;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_ctl *c;
+	struct dpu_ctl_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _ctl_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_ctl %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->caps = cfg;
+	_setup_ctl_ops(&c->ops, c->caps->features);
+	c->idx = idx;
+	c->mixer_count = m->mixer_count;
+	c->mixer_hw_caps = m->mixer;
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_CTL, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx)
+{
+	if (ctx)
+		dpu_hw_blk_destroy(&ctx->base);
+	kfree(ctx);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
new file mode 100644
index 000000000000..c66a71f8b839
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
@@ -0,0 +1,218 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_CTL_H
+#define _DPU_HW_CTL_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_hw_blk.h"
+
+/**
+ * dpu_ctl_mode_sel: Interface mode selection
+ * DPU_CTL_MODE_SEL_VID:    Video mode interface
+ * DPU_CTL_MODE_SEL_CMD:    Command mode interface
+ */
+enum dpu_ctl_mode_sel {
+	DPU_CTL_MODE_SEL_VID = 0,
+	DPU_CTL_MODE_SEL_CMD
+};
+
+struct dpu_hw_ctl;
+/**
+ * struct dpu_hw_stage_cfg - blending stage cfg
+ * @stage : SSPP_ID at each stage
+ * @multirect_index: index of the rectangle of SSPP.
+ */
+struct dpu_hw_stage_cfg {
+	enum dpu_sspp stage[DPU_STAGE_MAX][PIPES_PER_STAGE];
+	enum dpu_sspp_multirect_index multirect_index
+					[DPU_STAGE_MAX][PIPES_PER_STAGE];
+};
+
+/**
+ * struct dpu_hw_intf_cfg :Describes how the DPU writes data to output interface
+ * @intf :                 Interface id
+ * @mode_3d:               3d mux configuration
+ * @intf_mode_sel:         Interface mode, cmd / vid
+ * @stream_sel:            Stream selection for multi-stream interfaces
+ */
+struct dpu_hw_intf_cfg {
+	enum dpu_intf intf;
+	enum dpu_3d_blend_mode mode_3d;
+	enum dpu_ctl_mode_sel intf_mode_sel;
+	int stream_sel;
+};
+
+/**
+ * struct dpu_hw_ctl_ops - Interface to the wb Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_ctl_ops {
+	/**
+	 * kickoff hw operation for Sw controlled interfaces
+	 * DSI cmd mode and WB interface are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_start)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * kickoff prepare is in progress hw operation for sw
+	 * controlled interfaces: DSI cmd mode and WB interface
+	 * are SW controlled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_pending)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Clear the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Query the value of the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	u32 (*get_pending_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * OR in the given flushbits to the cached pending_flush_mask
+	 * No effect on hardware
+	 * @ctx       : ctl path ctx pointer
+	 * @flushbits : module flushmask
+	 */
+	void (*update_pending_flush)(struct dpu_hw_ctl *ctx,
+		u32 flushbits);
+
+	/**
+	 * Write the value of the pending_flush_mask to hardware
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*trigger_flush)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Read the value of the flush register
+	 * @ctx       : ctl path ctx pointer
+	 * @Return: value of the ctl flush register.
+	 */
+	u32 (*get_flush_register)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Setup ctl_path interface config
+	 * @ctx
+	 * @cfg    : interface config structure pointer
+	 */
+	void (*setup_intf_cfg)(struct dpu_hw_ctl *ctx,
+		struct dpu_hw_intf_cfg *cfg);
+
+	int (*reset)(struct dpu_hw_ctl *c);
+
+	/*
+	 * wait_reset_status - checks ctl reset status
+	 * @ctx       : ctl path ctx pointer
+	 *
+	 * This function checks the ctl reset status bit.
+	 * If the reset bit is set, it keeps polling the status till the hw
+	 * reset is complete.
+	 * Returns: 0 on success or -error if reset incomplete within interval
+	 */
+	int (*wait_reset_status)(struct dpu_hw_ctl *ctx);
+
+	uint32_t (*get_bitmask_sspp)(struct dpu_hw_ctl *ctx,
+		enum dpu_sspp blk);
+
+	uint32_t (*get_bitmask_mixer)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm blk);
+
+	int (*get_bitmask_intf)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits,
+		enum dpu_intf blk);
+
+	int (*get_bitmask_cdm)(struct dpu_hw_ctl *ctx,
+		u32 *flushbits,
+		enum dpu_cdm blk);
+
+	/**
+	 * Set all blend stages to disabled
+	 * @ctx       : ctl path ctx pointer
+	 */
+	void (*clear_all_blendstages)(struct dpu_hw_ctl *ctx);
+
+	/**
+	 * Configure layer mixer to pipe configuration
+	 * @ctx       : ctl path ctx pointer
+	 * @lm        : layer mixer enumeration
+	 * @cfg       : blend stage configuration
+	 */
+	void (*setup_blendstage)(struct dpu_hw_ctl *ctx,
+		enum dpu_lm lm, struct dpu_hw_stage_cfg *cfg);
+};
+
+/**
+ * struct dpu_hw_ctl : CTL PATH driver object
+ * @base: hardware block base structure
+ * @hw: block register map object
+ * @idx: control path index
+ * @caps: control path capabilities
+ * @mixer_count: number of mixers
+ * @mixer_hw_caps: mixer hardware capabilities
+ * @pending_flush_mask: storage for pending ctl_flush managed via ops
+ * @ops: operation list
+ */
+struct dpu_hw_ctl {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* ctl path */
+	int idx;
+	const struct dpu_ctl_cfg *caps;
+	int mixer_count;
+	const struct dpu_lm_cfg *mixer_hw_caps;
+	u32 pending_flush_mask;
+
+	/* ops */
+	struct dpu_hw_ctl_ops ops;
+};
+
+/**
+ * dpu_hw_ctl - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_ctl *to_dpu_hw_ctl(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_ctl, base);
+}
+
+/**
+ * dpu_hw_ctl_init(): Initializes the ctl_path hw driver object.
+ * should be called before accessing every ctl path registers.
+ * @idx:  ctl_path index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_ctl *dpu_hw_ctl_init(enum dpu_ctl idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_ctl_destroy(): Destroys ctl driver context
+ * should be called to free the context
+ */
+void dpu_hw_ctl_destroy(struct dpu_hw_ctl *ctx);
+
+#endif /*_DPU_HW_CTL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
new file mode 100644
index 000000000000..c0b7f0049365
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.c
@@ -0,0 +1,1183 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/bitops.h>
+#include <linux/slab.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+
+/**
+ * Register offsets in MDSS register file for the interrupt registers
+ * w.r.t. to the MDP base
+ */
+#define MDP_SSPP_TOP0_OFF		0x0
+#define MDP_INTF_0_OFF			0x6A000
+#define MDP_INTF_1_OFF			0x6A800
+#define MDP_INTF_2_OFF			0x6B000
+#define MDP_INTF_3_OFF			0x6B800
+#define MDP_INTF_4_OFF			0x6C000
+#define MDP_AD4_0_OFF			0x7C000
+#define MDP_AD4_1_OFF			0x7D000
+#define MDP_AD4_INTR_EN_OFF		0x41c
+#define MDP_AD4_INTR_CLEAR_OFF		0x424
+#define MDP_AD4_INTR_STATUS_OFF		0x420
+
+/**
+ * WB interrupt status bit definitions
+ */
+#define DPU_INTR_WB_0_DONE BIT(0)
+#define DPU_INTR_WB_1_DONE BIT(1)
+#define DPU_INTR_WB_2_DONE BIT(4)
+
+/**
+ * WDOG timer interrupt status bit definitions
+ */
+#define DPU_INTR_WD_TIMER_0_DONE BIT(2)
+#define DPU_INTR_WD_TIMER_1_DONE BIT(3)
+#define DPU_INTR_WD_TIMER_2_DONE BIT(5)
+#define DPU_INTR_WD_TIMER_3_DONE BIT(6)
+#define DPU_INTR_WD_TIMER_4_DONE BIT(7)
+
+/**
+ * Pingpong interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_DONE BIT(8)
+#define DPU_INTR_PING_PONG_1_DONE BIT(9)
+#define DPU_INTR_PING_PONG_2_DONE BIT(10)
+#define DPU_INTR_PING_PONG_3_DONE BIT(11)
+#define DPU_INTR_PING_PONG_0_RD_PTR BIT(12)
+#define DPU_INTR_PING_PONG_1_RD_PTR BIT(13)
+#define DPU_INTR_PING_PONG_2_RD_PTR BIT(14)
+#define DPU_INTR_PING_PONG_3_RD_PTR BIT(15)
+#define DPU_INTR_PING_PONG_0_WR_PTR BIT(16)
+#define DPU_INTR_PING_PONG_1_WR_PTR BIT(17)
+#define DPU_INTR_PING_PONG_2_WR_PTR BIT(18)
+#define DPU_INTR_PING_PONG_3_WR_PTR BIT(19)
+#define DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE BIT(20)
+#define DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE BIT(21)
+#define DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE BIT(22)
+#define DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE BIT(23)
+
+/**
+ * Interface interrupt status bit definitions
+ */
+#define DPU_INTR_INTF_0_UNDERRUN BIT(24)
+#define DPU_INTR_INTF_1_UNDERRUN BIT(26)
+#define DPU_INTR_INTF_2_UNDERRUN BIT(28)
+#define DPU_INTR_INTF_3_UNDERRUN BIT(30)
+#define DPU_INTR_INTF_0_VSYNC BIT(25)
+#define DPU_INTR_INTF_1_VSYNC BIT(27)
+#define DPU_INTR_INTF_2_VSYNC BIT(29)
+#define DPU_INTR_INTF_3_VSYNC BIT(31)
+
+/**
+ * Pingpong Secondary interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE BIT(0)
+#define DPU_INTR_PING_PONG_S0_WR_PTR BIT(4)
+#define DPU_INTR_PING_PONG_S0_RD_PTR BIT(8)
+#define DPU_INTR_PING_PONG_S0_TEAR_DETECTED BIT(22)
+#define DPU_INTR_PING_PONG_S0_TE_DETECTED BIT(28)
+
+/**
+ * Pingpong TEAR detection interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_TEAR_DETECTED BIT(16)
+#define DPU_INTR_PING_PONG_1_TEAR_DETECTED BIT(17)
+#define DPU_INTR_PING_PONG_2_TEAR_DETECTED BIT(18)
+#define DPU_INTR_PING_PONG_3_TEAR_DETECTED BIT(19)
+
+/**
+ * Pingpong TE detection interrupt status bit definitions
+ */
+#define DPU_INTR_PING_PONG_0_TE_DETECTED BIT(24)
+#define DPU_INTR_PING_PONG_1_TE_DETECTED BIT(25)
+#define DPU_INTR_PING_PONG_2_TE_DETECTED BIT(26)
+#define DPU_INTR_PING_PONG_3_TE_DETECTED BIT(27)
+
+/**
+ * Ctl start interrupt status bit definitions
+ */
+#define DPU_INTR_CTL_0_START BIT(9)
+#define DPU_INTR_CTL_1_START BIT(10)
+#define DPU_INTR_CTL_2_START BIT(11)
+#define DPU_INTR_CTL_3_START BIT(12)
+#define DPU_INTR_CTL_4_START BIT(13)
+
+/**
+ * Concurrent WB overflow interrupt status bit definitions
+ */
+#define DPU_INTR_CWB_2_OVERFLOW BIT(14)
+#define DPU_INTR_CWB_3_OVERFLOW BIT(15)
+
+/**
+ * Histogram VIG done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_VIG_0_DONE BIT(0)
+#define DPU_INTR_HIST_VIG_1_DONE BIT(4)
+#define DPU_INTR_HIST_VIG_2_DONE BIT(8)
+#define DPU_INTR_HIST_VIG_3_DONE BIT(10)
+
+/**
+ * Histogram VIG reset Sequence done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_VIG_0_RSTSEQ_DONE BIT(1)
+#define DPU_INTR_HIST_VIG_1_RSTSEQ_DONE BIT(5)
+#define DPU_INTR_HIST_VIG_2_RSTSEQ_DONE BIT(9)
+#define DPU_INTR_HIST_VIG_3_RSTSEQ_DONE BIT(11)
+
+/**
+ * Histogram DSPP done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_DSPP_0_DONE BIT(12)
+#define DPU_INTR_HIST_DSPP_1_DONE BIT(16)
+#define DPU_INTR_HIST_DSPP_2_DONE BIT(20)
+#define DPU_INTR_HIST_DSPP_3_DONE BIT(22)
+
+/**
+ * Histogram DSPP reset Sequence done interrupt status bit definitions
+ */
+#define DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE BIT(13)
+#define DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE BIT(17)
+#define DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE BIT(21)
+#define DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE BIT(23)
+
+/**
+ * INTF interrupt status bit definitions
+ */
+#define DPU_INTR_VIDEO_INTO_STATIC BIT(0)
+#define DPU_INTR_VIDEO_OUTOF_STATIC BIT(1)
+#define DPU_INTR_DSICMD_0_INTO_STATIC BIT(2)
+#define DPU_INTR_DSICMD_0_OUTOF_STATIC BIT(3)
+#define DPU_INTR_DSICMD_1_INTO_STATIC BIT(4)
+#define DPU_INTR_DSICMD_1_OUTOF_STATIC BIT(5)
+#define DPU_INTR_DSICMD_2_INTO_STATIC BIT(6)
+#define DPU_INTR_DSICMD_2_OUTOF_STATIC BIT(7)
+#define DPU_INTR_PROG_LINE BIT(8)
+
+/**
+ * AD4 interrupt status bit definitions
+ */
+#define DPU_INTR_BRIGHTPR_UPDATED BIT(4)
+#define DPU_INTR_DARKENH_UPDATED BIT(3)
+#define DPU_INTR_STREN_OUTROI_UPDATED BIT(2)
+#define DPU_INTR_STREN_INROI_UPDATED BIT(1)
+#define DPU_INTR_BACKLIGHT_UPDATED BIT(0)
+/**
+ * struct dpu_intr_reg - array of DPU register sets
+ * @clr_off:	offset to CLEAR reg
+ * @en_off:	offset to ENABLE reg
+ * @status_off:	offset to STATUS reg
+ */
+struct dpu_intr_reg {
+	u32 clr_off;
+	u32 en_off;
+	u32 status_off;
+};
+
+/**
+ * struct dpu_irq_type - maps each irq with i/f
+ * @intr_type:		type of interrupt listed in dpu_intr_type
+ * @instance_idx:	instance index of the associated HW block in DPU
+ * @irq_mask:		corresponding bit in the interrupt status reg
+ * @reg_idx:		which reg set to use
+ */
+struct dpu_irq_type {
+	u32 intr_type;
+	u32 instance_idx;
+	u32 irq_mask;
+	u32 reg_idx;
+};
+
+/**
+ * List of DPU interrupt registers
+ */
+static const struct dpu_intr_reg dpu_intr_set[] = {
+	{
+		MDP_SSPP_TOP0_OFF+INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR_EN,
+		MDP_SSPP_TOP0_OFF+INTR_STATUS
+	},
+	{
+		MDP_SSPP_TOP0_OFF+INTR2_CLEAR,
+		MDP_SSPP_TOP0_OFF+INTR2_EN,
+		MDP_SSPP_TOP0_OFF+INTR2_STATUS
+	},
+	{
+		MDP_SSPP_TOP0_OFF+HIST_INTR_CLEAR,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_EN,
+		MDP_SSPP_TOP0_OFF+HIST_INTR_STATUS
+	},
+	{
+		MDP_INTF_0_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_0_OFF+INTF_INTR_EN,
+		MDP_INTF_0_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_1_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_1_OFF+INTF_INTR_EN,
+		MDP_INTF_1_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_2_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_2_OFF+INTF_INTR_EN,
+		MDP_INTF_2_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_3_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_3_OFF+INTF_INTR_EN,
+		MDP_INTF_3_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_INTF_4_OFF+INTF_INTR_CLEAR,
+		MDP_INTF_4_OFF+INTF_INTR_EN,
+		MDP_INTF_4_OFF+INTF_INTR_STATUS
+	},
+	{
+		MDP_AD4_0_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_0_OFF + MDP_AD4_INTR_STATUS_OFF,
+	},
+	{
+		MDP_AD4_1_OFF + MDP_AD4_INTR_CLEAR_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_EN_OFF,
+		MDP_AD4_1_OFF + MDP_AD4_INTR_STATUS_OFF,
+	}
+};
+
+/**
+ * IRQ mapping table - use for lookup an irq_idx in this table that have
+ *                     a matching interface type and instance index.
+ */
+static const struct dpu_irq_type dpu_irq_map[] = {
+	/* BEGIN MAP_RANGE: 0-31, INTR */
+	/* irq_idx: 0-3 */
+	{ DPU_IRQ_TYPE_WB_ROT_COMP, WB_0, DPU_INTR_WB_0_DONE, 0},
+	{ DPU_IRQ_TYPE_WB_ROT_COMP, WB_1, DPU_INTR_WB_1_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_0, DPU_INTR_WD_TIMER_0_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_1, DPU_INTR_WD_TIMER_1_DONE, 0},
+	/* irq_idx: 4-7 */
+	{ DPU_IRQ_TYPE_WB_WFD_COMP, WB_2, DPU_INTR_WB_2_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_2, DPU_INTR_WD_TIMER_2_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_3, DPU_INTR_WD_TIMER_3_DONE, 0},
+	{ DPU_IRQ_TYPE_WD_TIMER, WD_TIMER_4, DPU_INTR_WD_TIMER_4_DONE, 0},
+	/* irq_idx: 8-11 */
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_COMP, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_DONE, 0},
+	/* irq_idx: 12-15 */
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_RD_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_RD_PTR, 0},
+	/* irq_idx: 16-19 */
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_WR_PTR, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_WR_PTR, 0},
+	/* irq_idx: 20-23 */
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_AUTOREFRESH_DONE, 0},
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_AUTOREFRESH_DONE, 0},
+	/* irq_idx: 24-27 */
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_0, DPU_INTR_INTF_0_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_0, DPU_INTR_INTF_0_VSYNC, 0},
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_1, DPU_INTR_INTF_1_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_1, DPU_INTR_INTF_1_VSYNC, 0},
+	/* irq_idx: 28-31 */
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_2, DPU_INTR_INTF_2_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_2, DPU_INTR_INTF_2_VSYNC, 0},
+	{ DPU_IRQ_TYPE_INTF_UNDER_RUN, INTF_3, DPU_INTR_INTF_3_UNDERRUN, 0},
+	{ DPU_IRQ_TYPE_INTF_VSYNC, INTF_3, DPU_INTR_INTF_3_VSYNC, 0},
+
+	/* BEGIN MAP_RANGE: 32-64, INTR2 */
+	/* irq_idx: 32-35 */
+	{ DPU_IRQ_TYPE_PING_PONG_AUTO_REF, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_AUTOREFRESH_DONE, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 36-39 */
+	{ DPU_IRQ_TYPE_PING_PONG_WR_PTR, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_WR_PTR, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 40 */
+	{ DPU_IRQ_TYPE_PING_PONG_RD_PTR, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_RD_PTR, 1},
+	/* irq_idx: 41-45 */
+	{ DPU_IRQ_TYPE_CTL_START, CTL_0,
+		DPU_INTR_CTL_0_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_1,
+		DPU_INTR_CTL_1_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_2,
+		DPU_INTR_CTL_2_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_3,
+		DPU_INTR_CTL_3_START, 1},
+	{ DPU_IRQ_TYPE_CTL_START, CTL_4,
+		DPU_INTR_CTL_4_START, 1},
+	/* irq_idx: 46-47 */
+	{ DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_2, DPU_INTR_CWB_2_OVERFLOW, 1},
+	{ DPU_IRQ_TYPE_CWB_OVERFLOW, CWB_3, DPU_INTR_CWB_3_OVERFLOW, 1},
+	/* irq_idx: 48-51 */
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_TEAR_DETECTED, 1},
+	/* irq_idx: 52-55 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_TEAR_DETECTED, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	/* irq_idx: 56-59 */
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_0,
+		DPU_INTR_PING_PONG_0_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_1,
+		DPU_INTR_PING_PONG_1_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_2,
+		DPU_INTR_PING_PONG_2_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_3,
+		DPU_INTR_PING_PONG_3_TE_DETECTED, 1},
+	/* irq_idx: 60-63 */
+	{ DPU_IRQ_TYPE_PING_PONG_TE_CHECK, PINGPONG_S0,
+		DPU_INTR_PING_PONG_S0_TE_DETECTED, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 1},
+
+	/* BEGIN MAP_RANGE: 64-95 HIST */
+	/* irq_idx: 64-67 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG0, DPU_INTR_HIST_VIG_0_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG0,
+		DPU_INTR_HIST_VIG_0_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 68-71 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG1, DPU_INTR_HIST_VIG_1_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG1,
+		DPU_INTR_HIST_VIG_1_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 72-75 */
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG2, DPU_INTR_HIST_VIG_2_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG2,
+		DPU_INTR_HIST_VIG_2_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_DONE, SSPP_VIG3, DPU_INTR_HIST_VIG_3_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_VIG_RSTSEQ, SSPP_VIG3,
+		DPU_INTR_HIST_VIG_3_RSTSEQ_DONE, 2},
+	/* irq_idx: 76-79 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_0, DPU_INTR_HIST_DSPP_0_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_0,
+		DPU_INTR_HIST_DSPP_0_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 80-83 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_1, DPU_INTR_HIST_DSPP_1_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_1,
+		DPU_INTR_HIST_DSPP_1_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 84-87 */
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_2, DPU_INTR_HIST_DSPP_2_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_2,
+		DPU_INTR_HIST_DSPP_2_RSTSEQ_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_DONE, DSPP_3, DPU_INTR_HIST_DSPP_3_DONE, 2},
+	{ DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ, DSPP_3,
+		DPU_INTR_HIST_DSPP_3_RSTSEQ_DONE, 2},
+	/* irq_idx: 88-91 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	/* irq_idx: 92-95 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 2},
+
+	/* BEGIN MAP_RANGE: 96-127 INTF_0_INTR */
+	/* irq_idx: 96-99 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_0,
+		DPU_INTR_VIDEO_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_0,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_0,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_0,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 3},
+	/* irq_idx: 100-103 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_0,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_0,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_0,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 3},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_0,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 3},
+	/* irq_idx: 104-107 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_0, DPU_INTR_PROG_LINE, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 108-111 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 112-115 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 116-119 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 120-123 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	/* irq_idx: 124-127 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 3},
+
+	/* BEGIN MAP_RANGE: 128-159 INTF_1_INTR */
+	/* irq_idx: 128-131 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_1,
+		DPU_INTR_VIDEO_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_1,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_1,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_1,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 4},
+	/* irq_idx: 132-135 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_1,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_1,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_1,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 4},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_1,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 4},
+	/* irq_idx: 136-139 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_1, DPU_INTR_PROG_LINE, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 140-143 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 144-147 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 148-151 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 152-155 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	/* irq_idx: 156-159 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 4},
+
+	/* BEGIN MAP_RANGE: 160-191 INTF_2_INTR */
+	/* irq_idx: 160-163 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_2,
+		DPU_INTR_VIDEO_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_2,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_2,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_2,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 5},
+	/* irq_idx: 164-167 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_2,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_2,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_2,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 5},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_2,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 5},
+	/* irq_idx: 168-171 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_2, DPU_INTR_PROG_LINE, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 172-175 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 176-179 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 180-183 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 184-187 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	/* irq_idx: 188-191 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 5},
+
+	/* BEGIN MAP_RANGE: 192-223 INTF_3_INTR */
+	/* irq_idx: 192-195 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_3,
+		DPU_INTR_VIDEO_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_3,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_3,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_3,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 6},
+	/* irq_idx: 196-199 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_3,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_3,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_3,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 6},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_3,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 6},
+	/* irq_idx: 200-203 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_3, DPU_INTR_PROG_LINE, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 204-207 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 208-211 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 212-215 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 216-219 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	/* irq_idx: 220-223 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 6},
+
+	/* BEGIN MAP_RANGE: 224-255 INTF_4_INTR */
+	/* irq_idx: 224-227 */
+	{ DPU_IRQ_TYPE_SFI_VIDEO_IN, INTF_4,
+		DPU_INTR_VIDEO_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_VIDEO_OUT, INTF_4,
+		DPU_INTR_VIDEO_OUTOF_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_IN, INTF_4,
+		DPU_INTR_DSICMD_0_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_0_OUT, INTF_4,
+		DPU_INTR_DSICMD_0_OUTOF_STATIC, 7},
+	/* irq_idx: 228-231 */
+	{ DPU_IRQ_TYPE_SFI_CMD_1_IN, INTF_4,
+		DPU_INTR_DSICMD_1_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_1_OUT, INTF_4,
+		DPU_INTR_DSICMD_1_OUTOF_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_IN, INTF_4,
+		DPU_INTR_DSICMD_2_INTO_STATIC, 7},
+	{ DPU_IRQ_TYPE_SFI_CMD_2_OUT, INTF_4,
+		DPU_INTR_DSICMD_2_OUTOF_STATIC, 7},
+	/* irq_idx: 232-235 */
+	{ DPU_IRQ_TYPE_PROG_LINE, INTF_4, DPU_INTR_PROG_LINE, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 236-239 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 240-243 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 244-247 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 248-251 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	/* irq_idx: 252-255 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 7},
+
+	/* BEGIN MAP_RANGE: 256-287 AD4_0_INTR */
+	/* irq_idx: 256-259 */
+	{ DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_0, DPU_INTR_BACKLIGHT_UPDATED, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 260-263 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 264-267 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 268-271 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 272-275 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 276-279 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 280-283 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	/* irq_idx: 284-287 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 8},
+
+	/* BEGIN MAP_RANGE: 288-319 AD4_1_INTR */
+	/* irq_idx: 288-291 */
+	{ DPU_IRQ_TYPE_AD4_BL_DONE, DSPP_1, DPU_INTR_BACKLIGHT_UPDATED, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 292-295 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 296-299 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 300-303 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 304-307 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 308-311 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 312-315 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	/* irq_idx: 315-319 */
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+	{ DPU_IRQ_TYPE_RESERVED, 0, 0, 9},
+};
+
+static int dpu_hw_intr_irqidx_lookup(enum dpu_intr_type intr_type,
+		u32 instance_idx)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_irq_map); i++) {
+		if (intr_type == dpu_irq_map[i].intr_type &&
+			instance_idx == dpu_irq_map[i].instance_idx)
+			return i;
+	}
+
+	pr_debug("IRQ lookup fail!! intr_type=%d, instance_idx=%d\n",
+			intr_type, instance_idx);
+	return -EINVAL;
+}
+
+static void dpu_hw_intr_set_mask(struct dpu_hw_intr *intr, uint32_t reg_off,
+		uint32_t mask)
+{
+	if (!intr)
+		return;
+
+	DPU_REG_WRITE(&intr->hw, reg_off, mask);
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+static void dpu_hw_intr_dispatch_irq(struct dpu_hw_intr *intr,
+		void (*cbfunc)(void *, int),
+		void *arg)
+{
+	int reg_idx;
+	int irq_idx;
+	int start_idx;
+	int end_idx;
+	u32 irq_status;
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	/*
+	 * The dispatcher will save the IRQ status before calling here.
+	 * Now need to go through each IRQ status and find matching
+	 * irq lookup index.
+	 */
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	for (reg_idx = 0; reg_idx < ARRAY_SIZE(dpu_intr_set); reg_idx++) {
+		irq_status = intr->save_irq_status[reg_idx];
+
+		/*
+		 * Each Interrupt register has a range of 32 indexes, and
+		 * that is static for dpu_irq_map.
+		 */
+		start_idx = reg_idx * 32;
+		end_idx = start_idx + 32;
+
+		if (start_idx >= ARRAY_SIZE(dpu_irq_map) ||
+				end_idx > ARRAY_SIZE(dpu_irq_map))
+			continue;
+
+		/*
+		 * Search through matching intr status from irq map.
+		 * start_idx and end_idx defined the search range in
+		 * the dpu_irq_map.
+		 */
+		for (irq_idx = start_idx;
+				(irq_idx < end_idx) && irq_status;
+				irq_idx++)
+			if ((irq_status & dpu_irq_map[irq_idx].irq_mask) &&
+				(dpu_irq_map[irq_idx].reg_idx == reg_idx)) {
+				/*
+				 * Once a match on irq mask, perform a callback
+				 * to the given cbfunc. cbfunc will take care
+				 * the interrupt status clearing. If cbfunc is
+				 * not provided, then the interrupt clearing
+				 * is here.
+				 */
+				if (cbfunc)
+					cbfunc(arg, irq_idx);
+				else
+					intr->ops.clear_intr_status_nolock(
+							intr, irq_idx);
+
+				/*
+				 * When callback finish, clear the irq_status
+				 * with the matching mask. Once irq_status
+				 * is all cleared, the search can be stopped.
+				 */
+				irq_status &= ~dpu_irq_map[irq_idx].irq_mask;
+			}
+	}
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static int dpu_hw_intr_enable_irq(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	unsigned long irq_flags;
+	const struct dpu_intr_reg *reg;
+	const struct dpu_irq_type *irq;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	irq = &dpu_irq_map[irq_idx];
+	reg_idx = irq->reg_idx;
+	reg = &dpu_intr_set[reg_idx];
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if (cache_irq_mask & irq->irq_mask) {
+		dbgstr = "DPU IRQ already set:";
+	} else {
+		dbgstr = "DPU IRQ enabled:";
+
+		cache_irq_mask |= irq->irq_mask;
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask);
+		/* Enabling interrupts with the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr,
+			irq->irq_mask, cache_irq_mask);
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irq_nolock(struct dpu_hw_intr *intr, int irq_idx)
+{
+	int reg_idx;
+	const struct dpu_intr_reg *reg;
+	const struct dpu_irq_type *irq;
+	const char *dbgstr = NULL;
+	uint32_t cache_irq_mask;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	irq = &dpu_irq_map[irq_idx];
+	reg_idx = irq->reg_idx;
+	reg = &dpu_intr_set[reg_idx];
+
+	cache_irq_mask = intr->cache_irq_mask[reg_idx];
+	if ((cache_irq_mask & irq->irq_mask) == 0) {
+		dbgstr = "DPU IRQ is already cleared:";
+	} else {
+		dbgstr = "DPU IRQ mask disable:";
+
+		cache_irq_mask &= ~irq->irq_mask;
+		/* Disable interrupts based on the new mask */
+		DPU_REG_WRITE(&intr->hw, reg->en_off, cache_irq_mask);
+		/* Cleaning any pending interrupt */
+		DPU_REG_WRITE(&intr->hw, reg->clr_off, irq->irq_mask);
+
+		/* ensure register write goes through */
+		wmb();
+
+		intr->cache_irq_mask[reg_idx] = cache_irq_mask;
+	}
+
+	pr_debug("%s MASK:0x%.8x, CACHE-MASK:0x%.8x\n", dbgstr,
+			irq->irq_mask, cache_irq_mask);
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irq(struct dpu_hw_intr *intr, int irq_idx)
+{
+	unsigned long irq_flags;
+
+	if (!intr)
+		return -EINVAL;
+
+	if (irq_idx < 0 || irq_idx >= ARRAY_SIZE(dpu_irq_map)) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	dpu_hw_intr_disable_irq_nolock(intr, irq_idx);
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return 0;
+}
+
+static int dpu_hw_intr_clear_irqs(struct dpu_hw_intr *intr)
+{
+	int i;
+
+	if (!intr)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off, 0xffffffff);
+
+	/* ensure register writes go through */
+	wmb();
+
+	return 0;
+}
+
+static int dpu_hw_intr_disable_irqs(struct dpu_hw_intr *intr)
+{
+	int i;
+
+	if (!intr)
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].en_off, 0x00000000);
+
+	/* ensure register writes go through */
+	wmb();
+
+	return 0;
+}
+
+static int dpu_hw_intr_get_valid_interrupts(struct dpu_hw_intr *intr,
+		uint32_t *mask)
+{
+	if (!intr || !mask)
+		return -EINVAL;
+
+	*mask = IRQ_SOURCE_MDP | IRQ_SOURCE_DSI0 | IRQ_SOURCE_DSI1
+		| IRQ_SOURCE_HDMI | IRQ_SOURCE_EDP;
+
+	return 0;
+}
+
+static void dpu_hw_intr_get_interrupt_statuses(struct dpu_hw_intr *intr)
+{
+	int i;
+	u32 enable_mask;
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	for (i = 0; i < ARRAY_SIZE(dpu_intr_set); i++) {
+		/* Read interrupt status */
+		intr->save_irq_status[i] = DPU_REG_READ(&intr->hw,
+				dpu_intr_set[i].status_off);
+
+		/* Read enable mask */
+		enable_mask = DPU_REG_READ(&intr->hw, dpu_intr_set[i].en_off);
+
+		/* and clear the interrupt */
+		if (intr->save_irq_status[i])
+			DPU_REG_WRITE(&intr->hw, dpu_intr_set[i].clr_off,
+					intr->save_irq_status[i]);
+
+		/* Finally update IRQ status based on enable mask */
+		intr->save_irq_status[i] &= enable_mask;
+	}
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static void dpu_hw_intr_clear_intr_status_nolock(struct dpu_hw_intr *intr,
+		int irq_idx)
+{
+	int reg_idx;
+
+	if (!intr)
+		return;
+
+	reg_idx = dpu_irq_map[irq_idx].reg_idx;
+	DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+			dpu_irq_map[irq_idx].irq_mask);
+
+	/* ensure register writes go through */
+	wmb();
+}
+
+static void dpu_hw_intr_clear_interrupt_status(struct dpu_hw_intr *intr,
+		int irq_idx)
+{
+	unsigned long irq_flags;
+
+	if (!intr)
+		return;
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+	dpu_hw_intr_clear_intr_status_nolock(intr, irq_idx);
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+}
+
+static u32 dpu_hw_intr_get_interrupt_status(struct dpu_hw_intr *intr,
+		int irq_idx, bool clear)
+{
+	int reg_idx;
+	unsigned long irq_flags;
+	u32 intr_status;
+
+	if (!intr)
+		return 0;
+
+	if (irq_idx >= ARRAY_SIZE(dpu_irq_map) || irq_idx < 0) {
+		pr_err("invalid IRQ index: [%d]\n", irq_idx);
+		return 0;
+	}
+
+	spin_lock_irqsave(&intr->irq_lock, irq_flags);
+
+	reg_idx = dpu_irq_map[irq_idx].reg_idx;
+	intr_status = DPU_REG_READ(&intr->hw,
+			dpu_intr_set[reg_idx].status_off) &
+					dpu_irq_map[irq_idx].irq_mask;
+	if (intr_status && clear)
+		DPU_REG_WRITE(&intr->hw, dpu_intr_set[reg_idx].clr_off,
+				intr_status);
+
+	/* ensure register writes go through */
+	wmb();
+
+	spin_unlock_irqrestore(&intr->irq_lock, irq_flags);
+
+	return intr_status;
+}
+
+static void __setup_intr_ops(struct dpu_hw_intr_ops *ops)
+{
+	ops->set_mask = dpu_hw_intr_set_mask;
+	ops->irq_idx_lookup = dpu_hw_intr_irqidx_lookup;
+	ops->enable_irq = dpu_hw_intr_enable_irq;
+	ops->disable_irq = dpu_hw_intr_disable_irq;
+	ops->dispatch_irqs = dpu_hw_intr_dispatch_irq;
+	ops->clear_all_irqs = dpu_hw_intr_clear_irqs;
+	ops->disable_all_irqs = dpu_hw_intr_disable_irqs;
+	ops->get_valid_interrupts = dpu_hw_intr_get_valid_interrupts;
+	ops->get_interrupt_statuses = dpu_hw_intr_get_interrupt_statuses;
+	ops->clear_interrupt_status = dpu_hw_intr_clear_interrupt_status;
+	ops->clear_intr_status_nolock = dpu_hw_intr_clear_intr_status_nolock;
+	ops->get_interrupt_status = dpu_hw_intr_get_interrupt_status;
+}
+
+static void __intr_offset(struct dpu_mdss_cfg *m,
+		void __iomem *addr, struct dpu_hw_blk_reg_map *hw)
+{
+	hw->base_off = addr;
+	hw->blk_off = m->mdp[0].base;
+	hw->hwversion = m->hwversion;
+}
+
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intr *intr;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	intr = kzalloc(sizeof(*intr), GFP_KERNEL);
+	if (!intr)
+		return ERR_PTR(-ENOMEM);
+
+	__intr_offset(m, addr, &intr->hw);
+	__setup_intr_ops(&intr->ops);
+
+	intr->irq_idx_tbl_size = ARRAY_SIZE(dpu_irq_map);
+
+	intr->cache_irq_mask = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32),
+			GFP_KERNEL);
+	if (intr->cache_irq_mask == NULL) {
+		kfree(intr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	intr->save_irq_status = kcalloc(ARRAY_SIZE(dpu_intr_set), sizeof(u32),
+			GFP_KERNEL);
+	if (intr->save_irq_status == NULL) {
+		kfree(intr->cache_irq_mask);
+		kfree(intr);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	spin_lock_init(&intr->irq_lock);
+
+	return intr;
+}
+
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr)
+{
+	if (intr) {
+		kfree(intr->cache_irq_mask);
+		kfree(intr->save_irq_status);
+		kfree(intr);
+	}
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
new file mode 100644
index 000000000000..61e4cba36562
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_interrupts.h
@@ -0,0 +1,257 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_INTERRUPTS_H
+#define _DPU_HW_INTERRUPTS_H
+
+#include <linux/types.h>
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_mdss.h"
+
+#define IRQ_SOURCE_MDP		BIT(0)
+#define IRQ_SOURCE_DSI0		BIT(4)
+#define IRQ_SOURCE_DSI1		BIT(5)
+#define IRQ_SOURCE_HDMI		BIT(8)
+#define IRQ_SOURCE_EDP		BIT(12)
+#define IRQ_SOURCE_MHL		BIT(16)
+
+/**
+ * dpu_intr_type - HW Interrupt Type
+ * @DPU_IRQ_TYPE_WB_ROT_COMP:		WB rotator done
+ * @DPU_IRQ_TYPE_WB_WFD_COMP:		WB WFD done
+ * @DPU_IRQ_TYPE_PING_PONG_COMP:	PingPong done
+ * @DPU_IRQ_TYPE_PING_PONG_RD_PTR:	PingPong read pointer
+ * @DPU_IRQ_TYPE_PING_PONG_WR_PTR:	PingPong write pointer
+ * @DPU_IRQ_TYPE_PING_PONG_AUTO_REF:	PingPong auto refresh
+ * @DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK:	PingPong Tear check
+ * @DPU_IRQ_TYPE_PING_PONG_TE_CHECK:	PingPong TE detection
+ * @DPU_IRQ_TYPE_INTF_UNDER_RUN:	INTF underrun
+ * @DPU_IRQ_TYPE_INTF_VSYNC:		INTF VSYNC
+ * @DPU_IRQ_TYPE_CWB_OVERFLOW:		Concurrent WB overflow
+ * @DPU_IRQ_TYPE_HIST_VIG_DONE:		VIG Histogram done
+ * @DPU_IRQ_TYPE_HIST_VIG_RSTSEQ:	VIG Histogram reset
+ * @DPU_IRQ_TYPE_HIST_DSPP_DONE:	DSPP Histogram done
+ * @DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ:	DSPP Histogram reset
+ * @DPU_IRQ_TYPE_WD_TIMER:		Watchdog timer
+ * @DPU_IRQ_TYPE_SFI_VIDEO_IN:		Video static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_VIDEO_OUT:		Video static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_0_IN:		DSI CMD0 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_0_OUT:		DSI CMD0 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_1_IN:		DSI CMD1 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_1_OUT:		DSI CMD1 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_SFI_CMD_2_IN:		DSI CMD2 static frame INTR into static
+ * @DPU_IRQ_TYPE_SFI_CMD_2_OUT:		DSI CMD2 static frame INTR out-of static
+ * @DPU_IRQ_TYPE_PROG_LINE:		Programmable Line interrupt
+ * @DPU_IRQ_TYPE_AD4_BL_DONE:		AD4 backlight
+ * @DPU_IRQ_TYPE_CTL_START:		Control start
+ * @DPU_IRQ_TYPE_RESERVED:		Reserved for expansion
+ */
+enum dpu_intr_type {
+	DPU_IRQ_TYPE_WB_ROT_COMP,
+	DPU_IRQ_TYPE_WB_WFD_COMP,
+	DPU_IRQ_TYPE_PING_PONG_COMP,
+	DPU_IRQ_TYPE_PING_PONG_RD_PTR,
+	DPU_IRQ_TYPE_PING_PONG_WR_PTR,
+	DPU_IRQ_TYPE_PING_PONG_AUTO_REF,
+	DPU_IRQ_TYPE_PING_PONG_TEAR_CHECK,
+	DPU_IRQ_TYPE_PING_PONG_TE_CHECK,
+	DPU_IRQ_TYPE_INTF_UNDER_RUN,
+	DPU_IRQ_TYPE_INTF_VSYNC,
+	DPU_IRQ_TYPE_CWB_OVERFLOW,
+	DPU_IRQ_TYPE_HIST_VIG_DONE,
+	DPU_IRQ_TYPE_HIST_VIG_RSTSEQ,
+	DPU_IRQ_TYPE_HIST_DSPP_DONE,
+	DPU_IRQ_TYPE_HIST_DSPP_RSTSEQ,
+	DPU_IRQ_TYPE_WD_TIMER,
+	DPU_IRQ_TYPE_SFI_VIDEO_IN,
+	DPU_IRQ_TYPE_SFI_VIDEO_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_0_IN,
+	DPU_IRQ_TYPE_SFI_CMD_0_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_1_IN,
+	DPU_IRQ_TYPE_SFI_CMD_1_OUT,
+	DPU_IRQ_TYPE_SFI_CMD_2_IN,
+	DPU_IRQ_TYPE_SFI_CMD_2_OUT,
+	DPU_IRQ_TYPE_PROG_LINE,
+	DPU_IRQ_TYPE_AD4_BL_DONE,
+	DPU_IRQ_TYPE_CTL_START,
+	DPU_IRQ_TYPE_RESERVED,
+};
+
+struct dpu_hw_intr;
+
+/**
+ * Interrupt operations.
+ */
+struct dpu_hw_intr_ops {
+	/**
+	 * set_mask - Programs the given interrupt register with the
+	 *            given interrupt mask. Register value will get overwritten.
+	 * @intr:	HW interrupt handle
+	 * @reg_off:	MDSS HW register offset
+	 * @irqmask:	IRQ mask value
+	 */
+	void (*set_mask)(
+			struct dpu_hw_intr *intr,
+			uint32_t reg,
+			uint32_t irqmask);
+
+	/**
+	 * irq_idx_lookup - Lookup IRQ index on the HW interrupt type
+	 *                 Used for all irq related ops
+	 * @intr_type:		Interrupt type defined in dpu_intr_type
+	 * @instance_idx:	HW interrupt block instance
+	 * @return:		irq_idx or -EINVAL for lookup fail
+	 */
+	int (*irq_idx_lookup)(
+			enum dpu_intr_type intr_type,
+			u32 instance_idx);
+
+	/**
+	 * enable_irq - Enable IRQ based on lookup IRQ index
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*enable_irq)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * disable_irq - Disable IRQ based on lookup IRQ index
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*disable_irq)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * clear_all_irqs - Clears all the interrupts (i.e. acknowledges
+	 *                  any asserted IRQs). Useful during reset.
+	 * @intr:	HW interrupt handle
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*clear_all_irqs)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * disable_all_irqs - Disables all the interrupts. Useful during reset.
+	 * @intr:	HW interrupt handle
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*disable_all_irqs)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * dispatch_irqs - IRQ dispatcher will call the given callback
+	 *                 function when a matching interrupt status bit is
+	 *                 found in the irq mapping table.
+	 * @intr:	HW interrupt handle
+	 * @cbfunc:	Callback function pointer
+	 * @arg:	Argument to pass back during callback
+	 */
+	void (*dispatch_irqs)(
+			struct dpu_hw_intr *intr,
+			void (*cbfunc)(void *arg, int irq_idx),
+			void *arg);
+
+	/**
+	 * get_interrupt_statuses - Gets and store value from all interrupt
+	 *                          status registers that are currently fired.
+	 * @intr:	HW interrupt handle
+	 */
+	void (*get_interrupt_statuses)(
+			struct dpu_hw_intr *intr);
+
+	/**
+	 * clear_interrupt_status - Clears HW interrupt status based on given
+	 *                          lookup IRQ index.
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 */
+	void (*clear_interrupt_status)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * clear_intr_status_nolock() - clears the HW interrupts without lock
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 */
+	void (*clear_intr_status_nolock)(
+			struct dpu_hw_intr *intr,
+			int irq_idx);
+
+	/**
+	 * get_interrupt_status - Gets HW interrupt status, and clear if set,
+	 *                        based on given lookup IRQ index.
+	 * @intr:	HW interrupt handle
+	 * @irq_idx:	Lookup irq index return from irq_idx_lookup
+	 * @clear:	True to clear irq after read
+	 */
+	u32 (*get_interrupt_status)(
+			struct dpu_hw_intr *intr,
+			int irq_idx,
+			bool clear);
+
+	/**
+	 * get_valid_interrupts - Gets a mask of all valid interrupt sources
+	 *                        within DPU. These are actually status bits
+	 *                        within interrupt registers that specify the
+	 *                        source of the interrupt in IRQs. For example,
+	 *                        valid interrupt sources can be MDP, DSI,
+	 *                        HDMI etc.
+	 * @intr:	HW interrupt handle
+	 * @mask:	Returning the interrupt source MASK
+	 * @return:	0 for success, otherwise failure
+	 */
+	int (*get_valid_interrupts)(
+			struct dpu_hw_intr *intr,
+			uint32_t *mask);
+};
+
+/**
+ * struct dpu_hw_intr: hw interrupts handling data structure
+ * @hw:               virtual address mapping
+ * @ops:              function pointer mapping for IRQ handling
+ * @cache_irq_mask:   array of IRQ enable masks reg storage created during init
+ * @save_irq_status:  array of IRQ status reg storage created during init
+ * @irq_idx_tbl_size: total number of irq_idx mapped in the hw_interrupts
+ * @irq_lock:         spinlock for accessing IRQ resources
+ */
+struct dpu_hw_intr {
+	struct dpu_hw_blk_reg_map hw;
+	struct dpu_hw_intr_ops ops;
+	u32 *cache_irq_mask;
+	u32 *save_irq_status;
+	u32 irq_idx_tbl_size;
+	spinlock_t irq_lock;
+};
+
+/**
+ * dpu_hw_intr_init(): Initializes the interrupts hw object
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intr *dpu_hw_intr_init(void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intr_destroy(): Cleanup interrutps hw object
+ * @intr: pointer to interrupts hw object
+ */
+void dpu_hw_intr_destroy(struct dpu_hw_intr *intr);
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
new file mode 100644
index 000000000000..d280df5613c9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.c
@@ -0,0 +1,349 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_intf.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define INTF_TIMING_ENGINE_EN           0x000
+#define INTF_CONFIG                     0x004
+#define INTF_HSYNC_CTL                  0x008
+#define INTF_VSYNC_PERIOD_F0            0x00C
+#define INTF_VSYNC_PERIOD_F1            0x010
+#define INTF_VSYNC_PULSE_WIDTH_F0       0x014
+#define INTF_VSYNC_PULSE_WIDTH_F1       0x018
+#define INTF_DISPLAY_V_START_F0         0x01C
+#define INTF_DISPLAY_V_START_F1         0x020
+#define INTF_DISPLAY_V_END_F0           0x024
+#define INTF_DISPLAY_V_END_F1           0x028
+#define INTF_ACTIVE_V_START_F0          0x02C
+#define INTF_ACTIVE_V_START_F1          0x030
+#define INTF_ACTIVE_V_END_F0            0x034
+#define INTF_ACTIVE_V_END_F1            0x038
+#define INTF_DISPLAY_HCTL               0x03C
+#define INTF_ACTIVE_HCTL                0x040
+#define INTF_BORDER_COLOR               0x044
+#define INTF_UNDERFLOW_COLOR            0x048
+#define INTF_HSYNC_SKEW                 0x04C
+#define INTF_POLARITY_CTL               0x050
+#define INTF_TEST_CTL                   0x054
+#define INTF_TP_COLOR0                  0x058
+#define INTF_TP_COLOR1                  0x05C
+#define INTF_FRAME_LINE_COUNT_EN        0x0A8
+#define INTF_FRAME_COUNT                0x0AC
+#define   INTF_LINE_COUNT               0x0B0
+
+#define   INTF_DEFLICKER_CONFIG         0x0F0
+#define   INTF_DEFLICKER_STRNG_COEFF    0x0F4
+#define   INTF_DEFLICKER_WEAK_COEFF     0x0F8
+
+#define   INTF_DSI_CMD_MODE_TRIGGER_EN  0x084
+#define   INTF_PANEL_FORMAT             0x090
+#define   INTF_TPG_ENABLE               0x100
+#define   INTF_TPG_MAIN_CONTROL         0x104
+#define   INTF_TPG_VIDEO_CONFIG         0x108
+#define   INTF_TPG_COMPONENT_LIMITS     0x10C
+#define   INTF_TPG_RECTANGLE            0x110
+#define   INTF_TPG_INITIAL_VALUE        0x114
+#define   INTF_TPG_BLK_WHITE_PATTERN_FRAMES   0x118
+#define   INTF_TPG_RGB_MAPPING          0x11C
+#define   INTF_PROG_FETCH_START         0x170
+#define   INTF_PROG_ROT_START           0x174
+
+#define   INTF_FRAME_LINE_COUNT_EN      0x0A8
+#define   INTF_FRAME_COUNT              0x0AC
+#define   INTF_LINE_COUNT               0x0B0
+
+#define INTF_MISR_CTRL			0x180
+#define INTF_MISR_SIGNATURE		0x184
+
+static struct dpu_intf_cfg *_intf_offset(enum dpu_intf intf,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->intf_count; i++) {
+		if ((intf == m->intf[i].id) &&
+		(m->intf[i].type != INTF_NONE)) {
+			b->base_off = addr;
+			b->blk_off = m->intf[i].base;
+			b->length = m->intf[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_INTF;
+			return &m->intf[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void dpu_hw_intf_setup_timing_engine(struct dpu_hw_intf *ctx,
+		const struct intf_timing_params *p,
+		const struct dpu_format *fmt)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 hsync_period, vsync_period;
+	u32 display_v_start, display_v_end;
+	u32 hsync_start_x, hsync_end_x;
+	u32 active_h_start, active_h_end;
+	u32 active_v_start, active_v_end;
+	u32 active_hctl, display_hctl, hsync_ctl;
+	u32 polarity_ctl, den_polarity, hsync_polarity, vsync_polarity;
+	u32 panel_format;
+	u32 intf_cfg;
+
+	/* read interface_cfg */
+	intf_cfg = DPU_REG_READ(c, INTF_CONFIG);
+	hsync_period = p->hsync_pulse_width + p->h_back_porch + p->width +
+	p->h_front_porch;
+	vsync_period = p->vsync_pulse_width + p->v_back_porch + p->height +
+	p->v_front_porch;
+
+	display_v_start = ((p->vsync_pulse_width + p->v_back_porch) *
+	hsync_period) + p->hsync_skew;
+	display_v_end = ((vsync_period - p->v_front_porch) * hsync_period) +
+	p->hsync_skew - 1;
+
+	if (ctx->cap->type == INTF_EDP || ctx->cap->type == INTF_DP) {
+		display_v_start += p->hsync_pulse_width + p->h_back_porch;
+		display_v_end -= p->h_front_porch;
+	}
+
+	hsync_start_x = p->h_back_porch + p->hsync_pulse_width;
+	hsync_end_x = hsync_period - p->h_front_porch - 1;
+
+	if (p->width != p->xres) {
+		active_h_start = hsync_start_x;
+		active_h_end = active_h_start + p->xres - 1;
+	} else {
+		active_h_start = 0;
+		active_h_end = 0;
+	}
+
+	if (p->height != p->yres) {
+		active_v_start = display_v_start;
+		active_v_end = active_v_start + (p->yres * hsync_period) - 1;
+	} else {
+		active_v_start = 0;
+		active_v_end = 0;
+	}
+
+	if (active_h_end) {
+		active_hctl = (active_h_end << 16) | active_h_start;
+		intf_cfg |= BIT(29);	/* ACTIVE_H_ENABLE */
+	} else {
+		active_hctl = 0;
+	}
+
+	if (active_v_end)
+		intf_cfg |= BIT(30); /* ACTIVE_V_ENABLE */
+
+	hsync_ctl = (hsync_period << 16) | p->hsync_pulse_width;
+	display_hctl = (hsync_end_x << 16) | hsync_start_x;
+
+	den_polarity = 0;
+	if (ctx->cap->type == INTF_HDMI) {
+		hsync_polarity = p->yres >= 720 ? 0 : 1;
+		vsync_polarity = p->yres >= 720 ? 0 : 1;
+	} else {
+		hsync_polarity = 0;
+		vsync_polarity = 0;
+	}
+	polarity_ctl = (den_polarity << 2) | /*  DEN Polarity  */
+		(vsync_polarity << 1) | /* VSYNC Polarity */
+		(hsync_polarity << 0);  /* HSYNC Polarity */
+
+	if (!DPU_FORMAT_IS_YUV(fmt))
+		panel_format = (fmt->bits[C0_G_Y] |
+				(fmt->bits[C1_B_Cb] << 2) |
+				(fmt->bits[C2_R_Cr] << 4) |
+				(0x21 << 8));
+	else
+		/* Interface treats all the pixel data in RGB888 format */
+		panel_format = (COLOR_8BIT |
+				(COLOR_8BIT << 2) |
+				(COLOR_8BIT << 4) |
+				(0x21 << 8));
+
+	DPU_REG_WRITE(c, INTF_HSYNC_CTL, hsync_ctl);
+	DPU_REG_WRITE(c, INTF_VSYNC_PERIOD_F0, vsync_period * hsync_period);
+	DPU_REG_WRITE(c, INTF_VSYNC_PULSE_WIDTH_F0,
+			p->vsync_pulse_width * hsync_period);
+	DPU_REG_WRITE(c, INTF_DISPLAY_HCTL, display_hctl);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_START_F0, display_v_start);
+	DPU_REG_WRITE(c, INTF_DISPLAY_V_END_F0, display_v_end);
+	DPU_REG_WRITE(c, INTF_ACTIVE_HCTL,  active_hctl);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_START_F0, active_v_start);
+	DPU_REG_WRITE(c, INTF_ACTIVE_V_END_F0, active_v_end);
+	DPU_REG_WRITE(c, INTF_BORDER_COLOR, p->border_clr);
+	DPU_REG_WRITE(c, INTF_UNDERFLOW_COLOR, p->underflow_clr);
+	DPU_REG_WRITE(c, INTF_HSYNC_SKEW, p->hsync_skew);
+	DPU_REG_WRITE(c, INTF_POLARITY_CTL, polarity_ctl);
+	DPU_REG_WRITE(c, INTF_FRAME_LINE_COUNT_EN, 0x3);
+	DPU_REG_WRITE(c, INTF_CONFIG, intf_cfg);
+	DPU_REG_WRITE(c, INTF_PANEL_FORMAT, panel_format);
+}
+
+static void dpu_hw_intf_enable_timing_engine(
+		struct dpu_hw_intf *intf,
+		u8 enable)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	/* Note: Display interface select is handled in top block hw layer */
+	DPU_REG_WRITE(c, INTF_TIMING_ENGINE_EN, enable != 0);
+}
+
+static void dpu_hw_intf_setup_prg_fetch(
+		struct dpu_hw_intf *intf,
+		const struct intf_prog_fetch *fetch)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	int fetch_enable;
+
+	/*
+	 * Fetch should always be outside the active lines. If the fetching
+	 * is programmed within active region, hardware behavior is unknown.
+	 */
+
+	fetch_enable = DPU_REG_READ(c, INTF_CONFIG);
+	if (fetch->enable) {
+		fetch_enable |= BIT(31);
+		DPU_REG_WRITE(c, INTF_PROG_FETCH_START,
+				fetch->fetch_start);
+	} else {
+		fetch_enable &= ~BIT(31);
+	}
+
+	DPU_REG_WRITE(c, INTF_CONFIG, fetch_enable);
+}
+
+static void dpu_hw_intf_get_status(
+		struct dpu_hw_intf *intf,
+		struct intf_status *s)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+
+	s->is_en = DPU_REG_READ(c, INTF_TIMING_ENGINE_EN);
+	if (s->is_en) {
+		s->frame_count = DPU_REG_READ(c, INTF_FRAME_COUNT);
+		s->line_count = DPU_REG_READ(c, INTF_LINE_COUNT);
+	} else {
+		s->line_count = 0;
+		s->frame_count = 0;
+	}
+}
+
+static void dpu_hw_intf_setup_misr(struct dpu_hw_intf *intf,
+						bool enable, u32 frame_count)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+	u32 config = 0;
+
+	DPU_REG_WRITE(c, INTF_MISR_CTRL, MISR_CTRL_STATUS_CLEAR);
+	/* clear misr data */
+	wmb();
+
+	if (enable)
+		config = (frame_count & MISR_FRAME_COUNT_MASK) |
+			MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK;
+
+	DPU_REG_WRITE(c, INTF_MISR_CTRL, config);
+}
+
+static u32 dpu_hw_intf_collect_misr(struct dpu_hw_intf *intf)
+{
+	struct dpu_hw_blk_reg_map *c = &intf->hw;
+
+	return DPU_REG_READ(c, INTF_MISR_SIGNATURE);
+}
+
+static u32 dpu_hw_intf_get_line_count(struct dpu_hw_intf *intf)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!intf)
+		return 0;
+
+	c = &intf->hw;
+
+	return DPU_REG_READ(c, INTF_LINE_COUNT);
+}
+
+static void _setup_intf_ops(struct dpu_hw_intf_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_timing_gen = dpu_hw_intf_setup_timing_engine;
+	ops->setup_prg_fetch  = dpu_hw_intf_setup_prg_fetch;
+	ops->get_status = dpu_hw_intf_get_status;
+	ops->enable_timing = dpu_hw_intf_enable_timing_engine;
+	ops->setup_misr = dpu_hw_intf_setup_misr;
+	ops->collect_misr = dpu_hw_intf_collect_misr;
+	ops->get_line_count = dpu_hw_intf_get_line_count;
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_intf *c;
+	struct dpu_intf_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _intf_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		pr_err("failed to create dpu_hw_intf %d\n", idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	c->mdss = m;
+	_setup_intf_ops(&c->ops, c->cap->features);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_INTF, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf)
+{
+	if (intf)
+		dpu_hw_blk_destroy(&intf->base);
+	kfree(intf);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
new file mode 100644
index 000000000000..a79d735da68d
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_intf.h
@@ -0,0 +1,128 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_INTF_H
+#define _DPU_HW_INTF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_intf;
+
+/* intf timing settings */
+struct intf_timing_params {
+	u32 width;		/* active width */
+	u32 height;		/* active height */
+	u32 xres;		/* Display panel width */
+	u32 yres;		/* Display panel height */
+
+	u32 h_back_porch;
+	u32 h_front_porch;
+	u32 v_back_porch;
+	u32 v_front_porch;
+	u32 hsync_pulse_width;
+	u32 vsync_pulse_width;
+	u32 hsync_polarity;
+	u32 vsync_polarity;
+	u32 border_clr;
+	u32 underflow_clr;
+	u32 hsync_skew;
+};
+
+struct intf_prog_fetch {
+	u8 enable;
+	/* vsync counter for the front porch pixel line */
+	u32 fetch_start;
+};
+
+struct intf_status {
+	u8 is_en;		/* interface timing engine is enabled or not */
+	u32 frame_count;	/* frame count since timing engine enabled */
+	u32 line_count;		/* current line count including blanking */
+};
+
+/**
+ * struct dpu_hw_intf_ops : Interface to the interface Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ * @ setup_timing_gen : programs the timing engine
+ * @ setup_prog_fetch : enables/disables the programmable fetch logic
+ * @ enable_timing: enable/disable timing engine
+ * @ get_status: returns if timing engine is enabled or not
+ * @ setup_misr: enables/disables MISR in HW register
+ * @ collect_misr: reads and stores MISR data from HW register
+ * @ get_line_count: reads current vertical line counter
+ */
+struct dpu_hw_intf_ops {
+	void (*setup_timing_gen)(struct dpu_hw_intf *intf,
+			const struct intf_timing_params *p,
+			const struct dpu_format *fmt);
+
+	void (*setup_prg_fetch)(struct dpu_hw_intf *intf,
+			const struct intf_prog_fetch *fetch);
+
+	void (*enable_timing)(struct dpu_hw_intf *intf,
+			u8 enable);
+
+	void (*get_status)(struct dpu_hw_intf *intf,
+			struct intf_status *status);
+
+	void (*setup_misr)(struct dpu_hw_intf *intf,
+			bool enable, u32 frame_count);
+
+	u32 (*collect_misr)(struct dpu_hw_intf *intf);
+
+	u32 (*get_line_count)(struct dpu_hw_intf *intf);
+};
+
+struct dpu_hw_intf {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* intf */
+	enum dpu_intf idx;
+	const struct dpu_intf_cfg *cap;
+	const struct dpu_mdss_cfg *mdss;
+
+	/* ops */
+	struct dpu_hw_intf_ops ops;
+};
+
+/**
+ * to_dpu_hw_intf - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_intf *to_dpu_hw_intf(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_intf, base);
+}
+
+/**
+ * dpu_hw_intf_init(): Initializes the intf driver for the passed
+ * interface idx.
+ * @idx:  interface index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_intf *dpu_hw_intf_init(enum dpu_intf idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_intf_destroy(): Destroys INTF driver context
+ * @intf:   Pointer to INTF driver context
+ */
+void dpu_hw_intf_destroy(struct dpu_hw_intf *intf);
+
+#endif /*_DPU_HW_INTF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
new file mode 100644
index 000000000000..4ab72b0f07a5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.c
@@ -0,0 +1,261 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_kms.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define LM_OP_MODE                        0x00
+#define LM_OUT_SIZE                       0x04
+#define LM_BORDER_COLOR_0                 0x08
+#define LM_BORDER_COLOR_1                 0x010
+
+/* These register are offset to mixer base + stage base */
+#define LM_BLEND0_OP                     0x00
+#define LM_BLEND0_CONST_ALPHA            0x04
+#define LM_FG_COLOR_FILL_COLOR_0         0x08
+#define LM_FG_COLOR_FILL_COLOR_1         0x0C
+#define LM_FG_COLOR_FILL_SIZE            0x10
+#define LM_FG_COLOR_FILL_XY              0x14
+
+#define LM_BLEND0_FG_ALPHA               0x04
+#define LM_BLEND0_BG_ALPHA               0x08
+
+#define LM_MISR_CTRL			0x310
+#define LM_MISR_SIGNATURE		0x314
+
+static struct dpu_lm_cfg *_lm_offset(enum dpu_lm mixer,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->mixer_count; i++) {
+		if (mixer == m->mixer[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->mixer[i].base;
+			b->length = m->mixer[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_LM;
+			return &m->mixer[i];
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+/**
+ * _stage_offset(): returns the relative offset of the blend registers
+ * for the stage to be setup
+ * @c:     mixer ctx contains the mixer to be programmed
+ * @stage: stage index to setup
+ */
+static inline int _stage_offset(struct dpu_hw_mixer *ctx, enum dpu_stage stage)
+{
+	const struct dpu_lm_sub_blks *sblk = ctx->cap->sblk;
+	int rc;
+
+	if (stage == DPU_STAGE_BASE)
+		rc = -EINVAL;
+	else if (stage <= sblk->maxblendstages)
+		rc = sblk->blendstage_base[stage - DPU_STAGE_0];
+	else
+		rc = -EINVAL;
+
+	return rc;
+}
+
+static void dpu_hw_lm_setup_out(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *mixer)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 outsize;
+	u32 op_mode;
+
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	outsize = mixer->out_height << 16 | mixer->out_width;
+	DPU_REG_WRITE(c, LM_OUT_SIZE, outsize);
+
+	/* SPLIT_LEFT_RIGHT */
+	if (mixer->right_mixer)
+		op_mode |= BIT(31);
+	else
+		op_mode &= ~BIT(31);
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void dpu_hw_lm_setup_border_color(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	if (border_en) {
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_0,
+			(color->color_0 & 0xFFF) |
+			((color->color_1 & 0xFFF) << 0x10));
+		DPU_REG_WRITE(c, LM_BORDER_COLOR_1,
+			(color->color_2 & 0xFFF) |
+			((color->color_3 & 0xFFF) << 0x10));
+	}
+}
+
+static void dpu_hw_lm_setup_blend_config_sdm845(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+	u32 const_alpha;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	const_alpha = (bg_alpha & 0xFF) | ((fg_alpha & 0xFF) << 16);
+	DPU_REG_WRITE(c, LM_BLEND0_CONST_ALPHA + stage_off, const_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_blend_config(struct dpu_hw_mixer *ctx,
+	u32 stage, u32 fg_alpha, u32 bg_alpha, u32 blend_op)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int stage_off;
+
+	if (stage == DPU_STAGE_BASE)
+		return;
+
+	stage_off = _stage_offset(ctx, stage);
+	if (WARN_ON(stage_off < 0))
+		return;
+
+	DPU_REG_WRITE(c, LM_BLEND0_FG_ALPHA + stage_off, fg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_BG_ALPHA + stage_off, bg_alpha);
+	DPU_REG_WRITE(c, LM_BLEND0_OP + stage_off, blend_op);
+}
+
+static void dpu_hw_lm_setup_color3(struct dpu_hw_mixer *ctx,
+	uint32_t mixer_op_mode)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	int op_mode;
+
+	/* read the existing op_mode configuration */
+	op_mode = DPU_REG_READ(c, LM_OP_MODE);
+
+	op_mode = (op_mode & (BIT(31) | BIT(30))) | mixer_op_mode;
+
+	DPU_REG_WRITE(c, LM_OP_MODE, op_mode);
+}
+
+static void dpu_hw_lm_gc(struct dpu_hw_mixer *mixer,
+			void *cfg)
+{
+}
+
+static void dpu_hw_lm_setup_misr(struct dpu_hw_mixer *ctx,
+				bool enable, u32 frame_count)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+	u32 config = 0;
+
+	DPU_REG_WRITE(c, LM_MISR_CTRL, MISR_CTRL_STATUS_CLEAR);
+	/* clear misr data */
+	wmb();
+
+	if (enable)
+		config = (frame_count & MISR_FRAME_COUNT_MASK) |
+			MISR_CTRL_ENABLE | INTF_MISR_CTRL_FREE_RUN_MASK;
+
+	DPU_REG_WRITE(c, LM_MISR_CTRL, config);
+}
+
+static u32 dpu_hw_lm_collect_misr(struct dpu_hw_mixer *ctx)
+{
+	struct dpu_hw_blk_reg_map *c = &ctx->hw;
+
+	return DPU_REG_READ(c, LM_MISR_SIGNATURE);
+}
+
+static void _setup_mixer_ops(struct dpu_mdss_cfg *m,
+		struct dpu_hw_lm_ops *ops,
+		unsigned long features)
+{
+	ops->setup_mixer_out = dpu_hw_lm_setup_out;
+	if (IS_SDM845_TARGET(m->hwversion) || IS_SDM670_TARGET(m->hwversion))
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config_sdm845;
+	else
+		ops->setup_blend_config = dpu_hw_lm_setup_blend_config;
+	ops->setup_alpha_out = dpu_hw_lm_setup_color3;
+	ops->setup_border_color = dpu_hw_lm_setup_border_color;
+	ops->setup_gc = dpu_hw_lm_gc;
+	ops->setup_misr = dpu_hw_lm_setup_misr;
+	ops->collect_misr = dpu_hw_lm_collect_misr;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mixer *c;
+	struct dpu_lm_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _lm_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_mixer_ops(m, &c->ops, c->cap->features);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_LM, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm)
+{
+	if (lm)
+		dpu_hw_blk_destroy(&lm->base);
+	kfree(lm);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
new file mode 100644
index 000000000000..e29e5dab31bf
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_lm.h
@@ -0,0 +1,122 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_LM_H
+#define _DPU_HW_LM_H
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_mixer;
+
+struct dpu_hw_mixer_cfg {
+	u32 out_width;
+	u32 out_height;
+	bool right_mixer;
+	int flags;
+};
+
+struct dpu_hw_color3_cfg {
+	u8 keep_fg[DPU_STAGE_MAX];
+};
+
+/**
+ *
+ * struct dpu_hw_lm_ops : Interface to the mixer Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_lm_ops {
+	/*
+	 * Sets up mixer output width and height
+	 * and border color if enabled
+	 */
+	void (*setup_mixer_out)(struct dpu_hw_mixer *ctx,
+		struct dpu_hw_mixer_cfg *cfg);
+
+	/*
+	 * Alpha blending configuration
+	 * for the specified stage
+	 */
+	void (*setup_blend_config)(struct dpu_hw_mixer *ctx, uint32_t stage,
+		uint32_t fg_alpha, uint32_t bg_alpha, uint32_t blend_op);
+
+	/*
+	 * Alpha color component selection from either fg or bg
+	 */
+	void (*setup_alpha_out)(struct dpu_hw_mixer *ctx, uint32_t mixer_op);
+
+	/**
+	 * setup_border_color : enable/disable border color
+	 */
+	void (*setup_border_color)(struct dpu_hw_mixer *ctx,
+		struct dpu_mdss_color *color,
+		u8 border_en);
+	/**
+	 * setup_gc : enable/disable gamma correction feature
+	 */
+	void (*setup_gc)(struct dpu_hw_mixer *mixer,
+			void *cfg);
+
+	/* setup_misr: enables/disables MISR in HW register */
+	void (*setup_misr)(struct dpu_hw_mixer *ctx,
+			bool enable, u32 frame_count);
+
+	/* collect_misr: reads and stores MISR data from HW register */
+	u32 (*collect_misr)(struct dpu_hw_mixer *ctx);
+};
+
+struct dpu_hw_mixer {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* lm */
+	enum dpu_lm  idx;
+	const struct dpu_lm_cfg   *cap;
+	const struct dpu_mdp_cfg  *mdp;
+	const struct dpu_ctl_cfg  *ctl;
+
+	/* ops */
+	struct dpu_hw_lm_ops ops;
+
+	/* store mixer info specific to display */
+	struct dpu_hw_mixer_cfg cfg;
+};
+
+/**
+ * to_dpu_hw_mixer - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_mixer *to_dpu_hw_mixer(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_mixer, base);
+}
+
+/**
+ * dpu_hw_lm_init(): Initializes the mixer hw driver object.
+ * should be called once before accessing every mixer.
+ * @idx:  mixer index for which driver object is required
+ * @addr: mapped register io address of MDP
+ * @m :   pointer to mdss catalog data
+ */
+struct dpu_hw_mixer *dpu_hw_lm_init(enum dpu_lm idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_lm_destroy(): Destroys layer mixer driver context
+ * @lm:   Pointer to LM driver context
+ */
+void dpu_hw_lm_destroy(struct dpu_hw_mixer *lm);
+
+#endif /*_DPU_HW_LM_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
new file mode 100644
index 000000000000..35e6bf930924
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_mdss.h
@@ -0,0 +1,465 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_MDSS_H
+#define _DPU_HW_MDSS_H
+
+#include <linux/kernel.h>
+#include <linux/err.h>
+
+#include "msm_drv.h"
+
+#define DPU_DBG_NAME			"dpu"
+
+#define DPU_NONE                        0
+
+#ifndef DPU_CSC_MATRIX_COEFF_SIZE
+#define DPU_CSC_MATRIX_COEFF_SIZE	9
+#endif
+
+#ifndef DPU_CSC_CLAMP_SIZE
+#define DPU_CSC_CLAMP_SIZE		6
+#endif
+
+#ifndef DPU_CSC_BIAS_SIZE
+#define DPU_CSC_BIAS_SIZE		3
+#endif
+
+#ifndef DPU_MAX_PLANES
+#define DPU_MAX_PLANES			4
+#endif
+
+#define PIPES_PER_STAGE			2
+#ifndef DPU_MAX_DE_CURVES
+#define DPU_MAX_DE_CURVES		3
+#endif
+
+enum dpu_format_flags {
+	DPU_FORMAT_FLAG_YUV_BIT,
+	DPU_FORMAT_FLAG_DX_BIT,
+	DPU_FORMAT_FLAG_COMPRESSED_BIT,
+	DPU_FORMAT_FLAG_BIT_MAX,
+};
+
+#define DPU_FORMAT_FLAG_YUV		BIT(DPU_FORMAT_FLAG_YUV_BIT)
+#define DPU_FORMAT_FLAG_DX		BIT(DPU_FORMAT_FLAG_DX_BIT)
+#define DPU_FORMAT_FLAG_COMPRESSED	BIT(DPU_FORMAT_FLAG_COMPRESSED_BIT)
+#define DPU_FORMAT_IS_YUV(X)		\
+	(test_bit(DPU_FORMAT_FLAG_YUV_BIT, (X)->flag))
+#define DPU_FORMAT_IS_DX(X)		\
+	(test_bit(DPU_FORMAT_FLAG_DX_BIT, (X)->flag))
+#define DPU_FORMAT_IS_LINEAR(X)		((X)->fetch_mode == DPU_FETCH_LINEAR)
+#define DPU_FORMAT_IS_TILE(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			!test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+#define DPU_FORMAT_IS_UBWC(X) \
+	(((X)->fetch_mode == DPU_FETCH_UBWC) && \
+			test_bit(DPU_FORMAT_FLAG_COMPRESSED_BIT, (X)->flag))
+
+#define DPU_BLEND_FG_ALPHA_FG_CONST	(0 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_CONST	(1 << 0)
+#define DPU_BLEND_FG_ALPHA_FG_PIXEL	(2 << 0)
+#define DPU_BLEND_FG_ALPHA_BG_PIXEL	(3 << 0)
+#define DPU_BLEND_FG_INV_ALPHA		(1 << 2)
+#define DPU_BLEND_FG_MOD_ALPHA		(1 << 3)
+#define DPU_BLEND_FG_INV_MOD_ALPHA	(1 << 4)
+#define DPU_BLEND_FG_TRANSP_EN		(1 << 5)
+#define DPU_BLEND_BG_ALPHA_FG_CONST	(0 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_CONST	(1 << 8)
+#define DPU_BLEND_BG_ALPHA_FG_PIXEL	(2 << 8)
+#define DPU_BLEND_BG_ALPHA_BG_PIXEL	(3 << 8)
+#define DPU_BLEND_BG_INV_ALPHA		(1 << 10)
+#define DPU_BLEND_BG_MOD_ALPHA		(1 << 11)
+#define DPU_BLEND_BG_INV_MOD_ALPHA	(1 << 12)
+#define DPU_BLEND_BG_TRANSP_EN		(1 << 13)
+
+#define DPU_VSYNC0_SOURCE_GPIO		0
+#define DPU_VSYNC1_SOURCE_GPIO		1
+#define DPU_VSYNC2_SOURCE_GPIO		2
+#define DPU_VSYNC_SOURCE_INTF_0		3
+#define DPU_VSYNC_SOURCE_INTF_1		4
+#define DPU_VSYNC_SOURCE_INTF_2		5
+#define DPU_VSYNC_SOURCE_INTF_3		6
+#define DPU_VSYNC_SOURCE_WD_TIMER_4	11
+#define DPU_VSYNC_SOURCE_WD_TIMER_3	12
+#define DPU_VSYNC_SOURCE_WD_TIMER_2	13
+#define DPU_VSYNC_SOURCE_WD_TIMER_1	14
+#define DPU_VSYNC_SOURCE_WD_TIMER_0	15
+
+enum dpu_hw_blk_type {
+	DPU_HW_BLK_TOP = 0,
+	DPU_HW_BLK_SSPP,
+	DPU_HW_BLK_LM,
+	DPU_HW_BLK_CTL,
+	DPU_HW_BLK_CDM,
+	DPU_HW_BLK_PINGPONG,
+	DPU_HW_BLK_INTF,
+	DPU_HW_BLK_WB,
+	DPU_HW_BLK_MAX,
+};
+
+enum dpu_mdp {
+	MDP_TOP = 0x1,
+	MDP_MAX,
+};
+
+enum dpu_sspp {
+	SSPP_NONE,
+	SSPP_VIG0,
+	SSPP_VIG1,
+	SSPP_VIG2,
+	SSPP_VIG3,
+	SSPP_RGB0,
+	SSPP_RGB1,
+	SSPP_RGB2,
+	SSPP_RGB3,
+	SSPP_DMA0,
+	SSPP_DMA1,
+	SSPP_DMA2,
+	SSPP_DMA3,
+	SSPP_CURSOR0,
+	SSPP_CURSOR1,
+	SSPP_MAX
+};
+
+enum dpu_sspp_type {
+	SSPP_TYPE_VIG,
+	SSPP_TYPE_RGB,
+	SSPP_TYPE_DMA,
+	SSPP_TYPE_CURSOR,
+	SSPP_TYPE_MAX
+};
+
+enum dpu_lm {
+	LM_0 = 1,
+	LM_1,
+	LM_2,
+	LM_3,
+	LM_4,
+	LM_5,
+	LM_6,
+	LM_MAX
+};
+
+enum dpu_stage {
+	DPU_STAGE_BASE = 0,
+	DPU_STAGE_0,
+	DPU_STAGE_1,
+	DPU_STAGE_2,
+	DPU_STAGE_3,
+	DPU_STAGE_4,
+	DPU_STAGE_5,
+	DPU_STAGE_6,
+	DPU_STAGE_7,
+	DPU_STAGE_8,
+	DPU_STAGE_9,
+	DPU_STAGE_10,
+	DPU_STAGE_MAX
+};
+enum dpu_dspp {
+	DSPP_0 = 1,
+	DSPP_1,
+	DSPP_2,
+	DSPP_3,
+	DSPP_MAX
+};
+
+enum dpu_ds {
+	DS_TOP,
+	DS_0,
+	DS_1,
+	DS_MAX
+};
+
+enum dpu_ctl {
+	CTL_0 = 1,
+	CTL_1,
+	CTL_2,
+	CTL_3,
+	CTL_4,
+	CTL_MAX
+};
+
+enum dpu_cdm {
+	CDM_0 = 1,
+	CDM_1,
+	CDM_MAX
+};
+
+enum dpu_pingpong {
+	PINGPONG_0 = 1,
+	PINGPONG_1,
+	PINGPONG_2,
+	PINGPONG_3,
+	PINGPONG_4,
+	PINGPONG_S0,
+	PINGPONG_MAX
+};
+
+enum dpu_intf {
+	INTF_0 = 1,
+	INTF_1,
+	INTF_2,
+	INTF_3,
+	INTF_4,
+	INTF_5,
+	INTF_6,
+	INTF_MAX
+};
+
+enum dpu_intf_type {
+	INTF_NONE = 0x0,
+	INTF_DSI = 0x1,
+	INTF_HDMI = 0x3,
+	INTF_LCDC = 0x5,
+	INTF_EDP = 0x9,
+	INTF_DP = 0xa,
+	INTF_TYPE_MAX,
+
+	/* virtual interfaces */
+	INTF_WB = 0x100,
+};
+
+enum dpu_intf_mode {
+	INTF_MODE_NONE = 0,
+	INTF_MODE_CMD,
+	INTF_MODE_VIDEO,
+	INTF_MODE_WB_BLOCK,
+	INTF_MODE_WB_LINE,
+	INTF_MODE_MAX
+};
+
+enum dpu_wb {
+	WB_0 = 1,
+	WB_1,
+	WB_2,
+	WB_3,
+	WB_MAX
+};
+
+enum dpu_ad {
+	AD_0 = 0x1,
+	AD_1,
+	AD_MAX
+};
+
+enum dpu_cwb {
+	CWB_0 = 0x1,
+	CWB_1,
+	CWB_2,
+	CWB_3,
+	CWB_MAX
+};
+
+enum dpu_wd_timer {
+	WD_TIMER_0 = 0x1,
+	WD_TIMER_1,
+	WD_TIMER_2,
+	WD_TIMER_3,
+	WD_TIMER_4,
+	WD_TIMER_5,
+	WD_TIMER_MAX
+};
+
+enum dpu_vbif {
+	VBIF_0,
+	VBIF_1,
+	VBIF_MAX,
+	VBIF_RT = VBIF_0,
+	VBIF_NRT = VBIF_1
+};
+
+enum dpu_iommu_domain {
+	DPU_IOMMU_DOMAIN_UNSECURE,
+	DPU_IOMMU_DOMAIN_SECURE,
+	DPU_IOMMU_DOMAIN_MAX
+};
+
+/**
+ * DPU HW,Component order color map
+ */
+enum {
+	C0_G_Y = 0,
+	C1_B_Cb = 1,
+	C2_R_Cr = 2,
+	C3_ALPHA = 3
+};
+
+/**
+ * enum dpu_plane_type - defines how the color component pixel packing
+ * @DPU_PLANE_INTERLEAVED   : Color components in single plane
+ * @DPU_PLANE_PLANAR        : Color component in separate planes
+ * @DPU_PLANE_PSEUDO_PLANAR : Chroma components interleaved in separate plane
+ */
+enum dpu_plane_type {
+	DPU_PLANE_INTERLEAVED,
+	DPU_PLANE_PLANAR,
+	DPU_PLANE_PSEUDO_PLANAR,
+};
+
+/**
+ * enum dpu_chroma_samp_type - chroma sub-samplng type
+ * @DPU_CHROMA_RGB   : No chroma subsampling
+ * @DPU_CHROMA_H2V1  : Chroma pixels are horizontally subsampled
+ * @DPU_CHROMA_H1V2  : Chroma pixels are vertically subsampled
+ * @DPU_CHROMA_420   : 420 subsampling
+ */
+enum dpu_chroma_samp_type {
+	DPU_CHROMA_RGB,
+	DPU_CHROMA_H2V1,
+	DPU_CHROMA_H1V2,
+	DPU_CHROMA_420
+};
+
+/**
+ * dpu_fetch_type - Defines How DPU HW fetches data
+ * @DPU_FETCH_LINEAR   : fetch is line by line
+ * @DPU_FETCH_TILE     : fetches data in Z order from a tile
+ * @DPU_FETCH_UBWC     : fetch and decompress data
+ */
+enum dpu_fetch_type {
+	DPU_FETCH_LINEAR,
+	DPU_FETCH_TILE,
+	DPU_FETCH_UBWC
+};
+
+/**
+ * Value of enum chosen to fit the number of bits
+ * expected by the HW programming.
+ */
+enum {
+	COLOR_ALPHA_1BIT = 0,
+	COLOR_ALPHA_4BIT = 1,
+	COLOR_4BIT = 0,
+	COLOR_5BIT = 1, /* No 5-bit Alpha */
+	COLOR_6BIT = 2, /* 6-Bit Alpha also = 2 */
+	COLOR_8BIT = 3, /* 8-Bit Alpha also = 3 */
+};
+
+/**
+ * enum dpu_3d_blend_mode
+ * Desribes how the 3d data is blended
+ * @BLEND_3D_NONE      : 3d blending not enabled
+ * @BLEND_3D_FRAME_INT : Frame interleaving
+ * @BLEND_3D_H_ROW_INT : Horizontal row interleaving
+ * @BLEND_3D_V_ROW_INT : vertical row interleaving
+ * @BLEND_3D_COL_INT   : column interleaving
+ * @BLEND_3D_MAX       :
+ */
+enum dpu_3d_blend_mode {
+	BLEND_3D_NONE = 0,
+	BLEND_3D_FRAME_INT,
+	BLEND_3D_H_ROW_INT,
+	BLEND_3D_V_ROW_INT,
+	BLEND_3D_COL_INT,
+	BLEND_3D_MAX
+};
+
+/** struct dpu_format - defines the format configuration which
+ * allows DPU HW to correctly fetch and decode the format
+ * @base: base msm_format struture containing fourcc code
+ * @fetch_planes: how the color components are packed in pixel format
+ * @element: element color ordering
+ * @bits: element bit widths
+ * @chroma_sample: chroma sub-samplng type
+ * @unpack_align_msb: unpack aligned, 0 to LSB, 1 to MSB
+ * @unpack_tight: 0 for loose, 1 for tight
+ * @unpack_count: 0 = 1 component, 1 = 2 component
+ * @bpp: bytes per pixel
+ * @alpha_enable: whether the format has an alpha channel
+ * @num_planes: number of planes (including meta data planes)
+ * @fetch_mode: linear, tiled, or ubwc hw fetch behavior
+ * @is_yuv: is format a yuv variant
+ * @flag: usage bit flags
+ * @tile_width: format tile width
+ * @tile_height: format tile height
+ */
+struct dpu_format {
+	struct msm_format base;
+	enum dpu_plane_type fetch_planes;
+	u8 element[DPU_MAX_PLANES];
+	u8 bits[DPU_MAX_PLANES];
+	enum dpu_chroma_samp_type chroma_sample;
+	u8 unpack_align_msb;
+	u8 unpack_tight;
+	u8 unpack_count;
+	u8 bpp;
+	u8 alpha_enable;
+	u8 num_planes;
+	enum dpu_fetch_type fetch_mode;
+	DECLARE_BITMAP(flag, DPU_FORMAT_FLAG_BIT_MAX);
+	u16 tile_width;
+	u16 tile_height;
+};
+#define to_dpu_format(x) container_of(x, struct dpu_format, base)
+
+/**
+ * struct dpu_hw_fmt_layout - format information of the source pixel data
+ * @format: pixel format parameters
+ * @num_planes: number of planes (including meta data planes)
+ * @width: image width
+ * @height: image height
+ * @total_size: total size in bytes
+ * @plane_addr: address of each plane
+ * @plane_size: length of each plane
+ * @plane_pitch: pitch of each plane
+ */
+struct dpu_hw_fmt_layout {
+	const struct dpu_format *format;
+	uint32_t num_planes;
+	uint32_t width;
+	uint32_t height;
+	uint32_t total_size;
+	uint32_t plane_addr[DPU_MAX_PLANES];
+	uint32_t plane_size[DPU_MAX_PLANES];
+	uint32_t plane_pitch[DPU_MAX_PLANES];
+};
+
+struct dpu_csc_cfg {
+	/* matrix coefficients in S15.16 format */
+	uint32_t csc_mv[DPU_CSC_MATRIX_COEFF_SIZE];
+	uint32_t csc_pre_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_post_bv[DPU_CSC_BIAS_SIZE];
+	uint32_t csc_pre_lv[DPU_CSC_CLAMP_SIZE];
+	uint32_t csc_post_lv[DPU_CSC_CLAMP_SIZE];
+};
+
+/**
+ * struct dpu_mdss_color - mdss color description
+ * color 0 : green
+ * color 1 : blue
+ * color 2 : red
+ * color 3 : alpha
+ */
+struct dpu_mdss_color {
+	u32 color_0;
+	u32 color_1;
+	u32 color_2;
+	u32 color_3;
+};
+
+/*
+ * Define bit masks for h/w logging.
+ */
+#define DPU_DBG_MASK_NONE     (1 << 0)
+#define DPU_DBG_MASK_CDM      (1 << 1)
+#define DPU_DBG_MASK_INTF     (1 << 2)
+#define DPU_DBG_MASK_LM       (1 << 3)
+#define DPU_DBG_MASK_CTL      (1 << 4)
+#define DPU_DBG_MASK_PINGPONG (1 << 5)
+#define DPU_DBG_MASK_SSPP     (1 << 6)
+#define DPU_DBG_MASK_WB       (1 << 7)
+#define DPU_DBG_MASK_TOP      (1 << 8)
+#define DPU_DBG_MASK_VBIF     (1 << 9)
+#define DPU_DBG_MASK_ROT      (1 << 10)
+
+#endif  /* _DPU_HW_MDSS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
new file mode 100644
index 000000000000..cc3a623903f4
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.c
@@ -0,0 +1,250 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/iopoll.h>
+
+#include "dpu_hw_mdss.h"
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+#include "dpu_trace.h"
+
+#define PP_TEAR_CHECK_EN                0x000
+#define PP_SYNC_CONFIG_VSYNC            0x004
+#define PP_SYNC_CONFIG_HEIGHT           0x008
+#define PP_SYNC_WRCOUNT                 0x00C
+#define PP_VSYNC_INIT_VAL               0x010
+#define PP_INT_COUNT_VAL                0x014
+#define PP_SYNC_THRESH                  0x018
+#define PP_START_POS                    0x01C
+#define PP_RD_PTR_IRQ                   0x020
+#define PP_WR_PTR_IRQ                   0x024
+#define PP_OUT_LINE_COUNT               0x028
+#define PP_LINE_COUNT                   0x02C
+
+#define PP_FBC_MODE                     0x034
+#define PP_FBC_BUDGET_CTL               0x038
+#define PP_FBC_LOSSY_MODE               0x03C
+
+static struct dpu_pingpong_cfg *_pingpong_offset(enum dpu_pingpong pp,
+		struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->pingpong_count; i++) {
+		if (pp == m->pingpong[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->pingpong[i].base;
+			b->length = m->pingpong[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_PINGPONG;
+			return &m->pingpong[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static int dpu_hw_pp_setup_te_config(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_tear_check *te)
+{
+	struct dpu_hw_blk_reg_map *c;
+	int cfg;
+
+	if (!pp || !te)
+		return -EINVAL;
+	c = &pp->hw;
+
+	cfg = BIT(19); /*VSYNC_COUNTER_EN */
+	if (te->hw_vsync_mode)
+		cfg |= BIT(20);
+
+	cfg |= te->vsync_count;
+
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_HEIGHT, te->sync_cfg_height);
+	DPU_REG_WRITE(c, PP_VSYNC_INIT_VAL, te->vsync_init_val);
+	DPU_REG_WRITE(c, PP_RD_PTR_IRQ, te->rd_ptr_irq);
+	DPU_REG_WRITE(c, PP_START_POS, te->start_pos);
+	DPU_REG_WRITE(c, PP_SYNC_THRESH,
+			((te->sync_threshold_continue << 16) |
+			 te->sync_threshold_start));
+	DPU_REG_WRITE(c, PP_SYNC_WRCOUNT,
+			(te->start_pos + te->sync_threshold_start + 1));
+
+	return 0;
+}
+
+static int dpu_hw_pp_poll_timeout_wr_ptr(struct dpu_hw_pingpong *pp,
+		u32 timeout_us)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+	int rc;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	rc = readl_poll_timeout(c->base_off + c->blk_off + PP_LINE_COUNT,
+			val, (val & 0xffff) >= 1, 10, timeout_us);
+
+	return rc;
+}
+
+static int dpu_hw_pp_enable_te(struct dpu_hw_pingpong *pp, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!pp)
+		return -EINVAL;
+	c = &pp->hw;
+
+	DPU_REG_WRITE(c, PP_TEAR_CHECK_EN, enable);
+	return 0;
+}
+
+static int dpu_hw_pp_connect_external_te(struct dpu_hw_pingpong *pp,
+		bool enable_external_te)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 cfg;
+	int orig;
+
+	if (!pp)
+		return -EINVAL;
+
+	c = &pp->hw;
+	cfg = DPU_REG_READ(c, PP_SYNC_CONFIG_VSYNC);
+	orig = (bool)(cfg & BIT(20));
+	if (enable_external_te)
+		cfg |= BIT(20);
+	else
+		cfg &= ~BIT(20);
+	DPU_REG_WRITE(c, PP_SYNC_CONFIG_VSYNC, cfg);
+	trace_dpu_pp_connect_ext_te(pp->idx - PINGPONG_0, cfg);
+
+	return orig;
+}
+
+static int dpu_hw_pp_get_vsync_info(struct dpu_hw_pingpong *pp,
+		struct dpu_hw_pp_vsync_info *info)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 val;
+
+	if (!pp || !info)
+		return -EINVAL;
+	c = &pp->hw;
+
+	val = DPU_REG_READ(c, PP_VSYNC_INIT_VAL);
+	info->rd_ptr_init_val = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_INT_COUNT_VAL);
+	info->rd_ptr_frame_count = (val & 0xffff0000) >> 16;
+	info->rd_ptr_line_count = val & 0xffff;
+
+	val = DPU_REG_READ(c, PP_LINE_COUNT);
+	info->wr_ptr_line_count = val & 0xffff;
+
+	return 0;
+}
+
+static u32 dpu_hw_pp_get_line_count(struct dpu_hw_pingpong *pp)
+{
+	struct dpu_hw_blk_reg_map *c = &pp->hw;
+	u32 height, init;
+	u32 line = 0xFFFF;
+
+	if (!pp)
+		return 0;
+	c = &pp->hw;
+
+	init = DPU_REG_READ(c, PP_VSYNC_INIT_VAL) & 0xFFFF;
+	height = DPU_REG_READ(c, PP_SYNC_CONFIG_HEIGHT) & 0xFFFF;
+
+	if (height < init)
+		goto line_count_exit;
+
+	line = DPU_REG_READ(c, PP_INT_COUNT_VAL) & 0xFFFF;
+
+	if (line < init)
+		line += (0xFFFF - init);
+	else
+		line -= init;
+
+line_count_exit:
+	return line;
+}
+
+static void _setup_pingpong_ops(struct dpu_hw_pingpong_ops *ops,
+	const struct dpu_pingpong_cfg *hw_cap)
+{
+	ops->setup_tearcheck = dpu_hw_pp_setup_te_config;
+	ops->enable_tearcheck = dpu_hw_pp_enable_te;
+	ops->connect_external_te = dpu_hw_pp_connect_external_te;
+	ops->get_vsync_info = dpu_hw_pp_get_vsync_info;
+	ops->poll_timeout_wr_ptr = dpu_hw_pp_poll_timeout_wr_ptr;
+	ops->get_line_count = dpu_hw_pp_get_line_count;
+};
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_pingpong *c;
+	struct dpu_pingpong_cfg *cfg;
+	int rc;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _pingpong_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	c->idx = idx;
+	c->caps = cfg;
+	_setup_pingpong_ops(&c->ops, c->caps);
+
+	rc = dpu_hw_blk_init(&c->base, DPU_HW_BLK_PINGPONG, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return c;
+
+blk_init_error:
+	kzfree(c);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp)
+{
+	if (pp)
+		dpu_hw_blk_destroy(&pp->base);
+	kfree(pp);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
new file mode 100644
index 000000000000..3caccd7d6a3e
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_pingpong.h
@@ -0,0 +1,136 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_PINGPONG_H
+#define _DPU_HW_PINGPONG_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_pingpong;
+
+struct dpu_hw_tear_check {
+	/*
+	 * This is ratio of MDP VSYNC clk freq(Hz) to
+	 * refresh rate divided by no of lines
+	 */
+	u32 vsync_count;
+	u32 sync_cfg_height;
+	u32 vsync_init_val;
+	u32 sync_threshold_start;
+	u32 sync_threshold_continue;
+	u32 start_pos;
+	u32 rd_ptr_irq;
+	u8 hw_vsync_mode;
+};
+
+struct dpu_hw_pp_vsync_info {
+	u32 rd_ptr_init_val;	/* value of rd pointer at vsync edge */
+	u32 rd_ptr_frame_count;	/* num frames sent since enabling interface */
+	u32 rd_ptr_line_count;	/* current line on panel (rd ptr) */
+	u32 wr_ptr_line_count;	/* current line within pp fifo (wr ptr) */
+};
+
+/**
+ *
+ * struct dpu_hw_pingpong_ops : Interface to the pingpong Hw driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ *  @setup_tearcheck : program tear check values
+ *  @enable_tearcheck : enables tear check
+ *  @get_vsync_info : retries timing info of the panel
+ *  @setup_dither : function to program the dither hw block
+ *  @get_line_count: obtain current vertical line counter
+ */
+struct dpu_hw_pingpong_ops {
+	/**
+	 * enables vysnc generation and sets up init value of
+	 * read pointer and programs the tear check cofiguration
+	 */
+	int (*setup_tearcheck)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_tear_check *cfg);
+
+	/**
+	 * enables tear check block
+	 */
+	int (*enable_tearcheck)(struct dpu_hw_pingpong *pp,
+			bool enable);
+
+	/**
+	 * read, modify, write to either set or clear listening to external TE
+	 * @Return: 1 if TE was originally connected, 0 if not, or -ERROR
+	 */
+	int (*connect_external_te)(struct dpu_hw_pingpong *pp,
+			bool enable_external_te);
+
+	/**
+	 * provides the programmed and current
+	 * line_count
+	 */
+	int (*get_vsync_info)(struct dpu_hw_pingpong *pp,
+			struct dpu_hw_pp_vsync_info  *info);
+
+	/**
+	 * poll until write pointer transmission starts
+	 * @Return: 0 on success, -ETIMEDOUT on timeout
+	 */
+	int (*poll_timeout_wr_ptr)(struct dpu_hw_pingpong *pp, u32 timeout_us);
+
+	/**
+	 * Obtain current vertical line counter
+	 */
+	u32 (*get_line_count)(struct dpu_hw_pingpong *pp);
+};
+
+struct dpu_hw_pingpong {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* pingpong */
+	enum dpu_pingpong idx;
+	const struct dpu_pingpong_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_pingpong_ops ops;
+};
+
+/**
+ * dpu_hw_pingpong - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pingpong *to_dpu_hw_pingpong(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pingpong, base);
+}
+
+/**
+ * dpu_hw_pingpong_init - initializes the pingpong driver for the passed
+ *	pingpong idx.
+ * @idx:  Pingpong index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ * Returns: Error code or allocated dpu_hw_pingpong context
+ */
+struct dpu_hw_pingpong *dpu_hw_pingpong_init(enum dpu_pingpong idx,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *m);
+
+/**
+ * dpu_hw_pingpong_destroy - destroys pingpong driver context
+ *	should be called to free the context
+ * @pp:   Pointer to PP driver context returned by dpu_hw_pingpong_init
+ */
+void dpu_hw_pingpong_destroy(struct dpu_hw_pingpong *pp);
+
+#endif /*_DPU_HW_PINGPONG_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
new file mode 100644
index 000000000000..c25b52a6b219
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -0,0 +1,753 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define DPU_FETCH_CONFIG_RESET_VALUE   0x00000087
+
+/* DPU_SSPP_SRC */
+#define SSPP_SRC_SIZE                      0x00
+#define SSPP_SRC_XY                        0x08
+#define SSPP_OUT_SIZE                      0x0c
+#define SSPP_OUT_XY                        0x10
+#define SSPP_SRC0_ADDR                     0x14
+#define SSPP_SRC1_ADDR                     0x18
+#define SSPP_SRC2_ADDR                     0x1C
+#define SSPP_SRC3_ADDR                     0x20
+#define SSPP_SRC_YSTRIDE0                  0x24
+#define SSPP_SRC_YSTRIDE1                  0x28
+#define SSPP_SRC_FORMAT                    0x30
+#define SSPP_SRC_UNPACK_PATTERN            0x34
+#define SSPP_SRC_OP_MODE                   0x38
+
+/* SSPP_MULTIRECT*/
+#define SSPP_SRC_SIZE_REC1                 0x16C
+#define SSPP_SRC_XY_REC1                   0x168
+#define SSPP_OUT_SIZE_REC1                 0x160
+#define SSPP_OUT_XY_REC1                   0x164
+#define SSPP_SRC_FORMAT_REC1               0x174
+#define SSPP_SRC_UNPACK_PATTERN_REC1       0x178
+#define SSPP_SRC_OP_MODE_REC1              0x17C
+#define SSPP_MULTIRECT_OPMODE              0x170
+#define SSPP_SRC_CONSTANT_COLOR_REC1       0x180
+#define SSPP_EXCL_REC_SIZE_REC1            0x184
+#define SSPP_EXCL_REC_XY_REC1              0x188
+
+#define MDSS_MDP_OP_DEINTERLACE            BIT(22)
+#define MDSS_MDP_OP_DEINTERLACE_ODD        BIT(23)
+#define MDSS_MDP_OP_IGC_ROM_1              BIT(18)
+#define MDSS_MDP_OP_IGC_ROM_0              BIT(17)
+#define MDSS_MDP_OP_IGC_EN                 BIT(16)
+#define MDSS_MDP_OP_FLIP_UD                BIT(14)
+#define MDSS_MDP_OP_FLIP_LR                BIT(13)
+#define MDSS_MDP_OP_BWC_EN                 BIT(0)
+#define MDSS_MDP_OP_PE_OVERRIDE            BIT(31)
+#define MDSS_MDP_OP_BWC_LOSSLESS           (0 << 1)
+#define MDSS_MDP_OP_BWC_Q_HIGH             (1 << 1)
+#define MDSS_MDP_OP_BWC_Q_MED              (2 << 1)
+
+#define SSPP_SRC_CONSTANT_COLOR            0x3c
+#define SSPP_EXCL_REC_CTL                  0x40
+#define SSPP_UBWC_STATIC_CTRL              0x44
+#define SSPP_FETCH_CONFIG                  0x048
+#define SSPP_DANGER_LUT                    0x60
+#define SSPP_SAFE_LUT                      0x64
+#define SSPP_CREQ_LUT                      0x68
+#define SSPP_QOS_CTRL                      0x6C
+#define SSPP_DECIMATION_CONFIG             0xB4
+#define SSPP_SRC_ADDR_SW_STATUS            0x70
+#define SSPP_CREQ_LUT_0                    0x74
+#define SSPP_CREQ_LUT_1                    0x78
+#define SSPP_SW_PIX_EXT_C0_LR              0x100
+#define SSPP_SW_PIX_EXT_C0_TB              0x104
+#define SSPP_SW_PIX_EXT_C0_REQ_PIXELS      0x108
+#define SSPP_SW_PIX_EXT_C1C2_LR            0x110
+#define SSPP_SW_PIX_EXT_C1C2_TB            0x114
+#define SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS    0x118
+#define SSPP_SW_PIX_EXT_C3_LR              0x120
+#define SSPP_SW_PIX_EXT_C3_TB              0x124
+#define SSPP_SW_PIX_EXT_C3_REQ_PIXELS      0x128
+#define SSPP_TRAFFIC_SHAPER                0x130
+#define SSPP_CDP_CNTL                      0x134
+#define SSPP_UBWC_ERROR_STATUS             0x138
+#define SSPP_TRAFFIC_SHAPER_PREFILL        0x150
+#define SSPP_TRAFFIC_SHAPER_REC1_PREFILL   0x154
+#define SSPP_TRAFFIC_SHAPER_REC1           0x158
+#define SSPP_EXCL_REC_SIZE                 0x1B4
+#define SSPP_EXCL_REC_XY                   0x1B8
+#define SSPP_VIG_OP_MODE                   0x0
+#define SSPP_VIG_CSC_10_OP_MODE            0x0
+#define SSPP_TRAFFIC_SHAPER_BPC_MAX        0xFF
+
+/* SSPP_QOS_CTRL */
+#define SSPP_QOS_CTRL_VBLANK_EN            BIT(16)
+#define SSPP_QOS_CTRL_DANGER_SAFE_EN       BIT(0)
+#define SSPP_QOS_CTRL_DANGER_VBLANK_MASK   0x3
+#define SSPP_QOS_CTRL_DANGER_VBLANK_OFF    4
+#define SSPP_QOS_CTRL_CREQ_VBLANK_MASK     0x3
+#define SSPP_QOS_CTRL_CREQ_VBLANK_OFF      20
+
+/* DPU_SSPP_SCALER_QSEED2 */
+#define SCALE_CONFIG                       0x04
+#define COMP0_3_PHASE_STEP_X               0x10
+#define COMP0_3_PHASE_STEP_Y               0x14
+#define COMP1_2_PHASE_STEP_X               0x18
+#define COMP1_2_PHASE_STEP_Y               0x1c
+#define COMP0_3_INIT_PHASE_X               0x20
+#define COMP0_3_INIT_PHASE_Y               0x24
+#define COMP1_2_INIT_PHASE_X               0x28
+#define COMP1_2_INIT_PHASE_Y               0x2C
+#define VIG_0_QSEED2_SHARP                 0x30
+
+/*
+ * Definitions for ViG op modes
+ */
+#define VIG_OP_CSC_DST_DATAFMT BIT(19)
+#define VIG_OP_CSC_SRC_DATAFMT BIT(18)
+#define VIG_OP_CSC_EN          BIT(17)
+#define VIG_OP_MEM_PROT_CONT   BIT(15)
+#define VIG_OP_MEM_PROT_VAL    BIT(14)
+#define VIG_OP_MEM_PROT_SAT    BIT(13)
+#define VIG_OP_MEM_PROT_HUE    BIT(12)
+#define VIG_OP_HIST            BIT(8)
+#define VIG_OP_SKY_COL         BIT(7)
+#define VIG_OP_FOIL            BIT(6)
+#define VIG_OP_SKIN_COL        BIT(5)
+#define VIG_OP_PA_EN           BIT(4)
+#define VIG_OP_PA_SAT_ZERO_EXP BIT(2)
+#define VIG_OP_MEM_PROT_BLEND  BIT(1)
+
+/*
+ * Definitions for CSC 10 op modes
+ */
+#define VIG_CSC_10_SRC_DATAFMT BIT(1)
+#define VIG_CSC_10_EN          BIT(0)
+#define CSC_10BIT_OFFSET       4
+
+/* traffic shaper clock in Hz */
+#define TS_CLK			19200000
+
+static inline int _sspp_subblk_offset(struct dpu_hw_pipe *ctx,
+		int s_id,
+		u32 *idx)
+{
+	int rc = 0;
+	const struct dpu_sspp_sub_blks *sblk = ctx->cap->sblk;
+
+	if (!ctx)
+		return -EINVAL;
+
+	switch (s_id) {
+	case DPU_SSPP_SRC:
+		*idx = sblk->src_blk.base;
+		break;
+	case DPU_SSPP_SCALER_QSEED2:
+	case DPU_SSPP_SCALER_QSEED3:
+	case DPU_SSPP_SCALER_RGB:
+		*idx = sblk->scaler_blk.base;
+		break;
+	case DPU_SSPP_CSC:
+	case DPU_SSPP_CSC_10BIT:
+		*idx = sblk->csc_blk.base;
+		break;
+	default:
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static void dpu_hw_sspp_setup_multirect(struct dpu_hw_pipe *ctx,
+		enum dpu_sspp_multirect_index index,
+		enum dpu_sspp_multirect_mode mode)
+{
+	u32 mode_mask;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (index == DPU_SSPP_RECT_SOLO) {
+		/**
+		 * if rect index is RECT_SOLO, we cannot expect a
+		 * virtual plane sharing the same SSPP id. So we go
+		 * and disable multirect
+		 */
+		mode_mask = 0;
+	} else {
+		mode_mask = DPU_REG_READ(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx);
+		mode_mask |= index;
+		if (mode == DPU_SSPP_MULTIRECT_TIME_MX)
+			mode_mask |= BIT(2);
+		else
+			mode_mask &= ~BIT(2);
+	}
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_MULTIRECT_OPMODE + idx, mode_mask);
+}
+
+static void _sspp_setup_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (!test_bit(DPU_SSPP_SCALER_QSEED2, &ctx->cap->features) ||
+		_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED2, &idx) ||
+		!test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_OP_MODE + idx);
+
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_OP_MODE + idx, opmode);
+}
+
+static void _sspp_setup_csc10_opmode(struct dpu_hw_pipe *ctx,
+		u32 mask, u8 en)
+{
+	u32 idx;
+	u32 opmode;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC_10BIT, &idx))
+		return;
+
+	opmode = DPU_REG_READ(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx);
+	if (en)
+		opmode |= mask;
+	else
+		opmode &= ~mask;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_VIG_CSC_10_OP_MODE + idx, opmode);
+}
+
+/**
+ * Setup source pixel format, flip,
+ */
+static void dpu_hw_sspp_setup_format(struct dpu_hw_pipe *ctx,
+		const struct dpu_format *fmt, u32 flags,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 chroma_samp, unpack, src_format;
+	u32 opmode = 0;
+	u32 fast_clear = 0;
+	u32 op_mode_off, unpack_pat_off, format_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !fmt)
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO || rect_mode == DPU_SSPP_RECT_0) {
+		op_mode_off = SSPP_SRC_OP_MODE;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN;
+		format_off = SSPP_SRC_FORMAT;
+	} else {
+		op_mode_off = SSPP_SRC_OP_MODE_REC1;
+		unpack_pat_off = SSPP_SRC_UNPACK_PATTERN_REC1;
+		format_off = SSPP_SRC_FORMAT_REC1;
+	}
+
+	c = &ctx->hw;
+	opmode = DPU_REG_READ(c, op_mode_off + idx);
+	opmode &= ~(MDSS_MDP_OP_FLIP_LR | MDSS_MDP_OP_FLIP_UD |
+			MDSS_MDP_OP_BWC_EN | MDSS_MDP_OP_PE_OVERRIDE);
+
+	if (flags & DPU_SSPP_FLIP_LR)
+		opmode |= MDSS_MDP_OP_FLIP_LR;
+	if (flags & DPU_SSPP_FLIP_UD)
+		opmode |= MDSS_MDP_OP_FLIP_UD;
+
+	chroma_samp = fmt->chroma_sample;
+	if (flags & DPU_SSPP_SOURCE_ROTATED_90) {
+		if (chroma_samp == DPU_CHROMA_H2V1)
+			chroma_samp = DPU_CHROMA_H1V2;
+		else if (chroma_samp == DPU_CHROMA_H1V2)
+			chroma_samp = DPU_CHROMA_H2V1;
+	}
+
+	src_format = (chroma_samp << 23) | (fmt->fetch_planes << 19) |
+		(fmt->bits[C3_ALPHA] << 6) | (fmt->bits[C2_R_Cr] << 4) |
+		(fmt->bits[C1_B_Cb] << 2) | (fmt->bits[C0_G_Y] << 0);
+
+	if (flags & DPU_SSPP_ROT_90)
+		src_format |= BIT(11); /* ROT90 */
+
+	if (fmt->alpha_enable && fmt->fetch_planes == DPU_PLANE_INTERLEAVED)
+		src_format |= BIT(8); /* SRCC3_EN */
+
+	if (flags & DPU_SSPP_SOLID_FILL)
+		src_format |= BIT(22);
+
+	unpack = (fmt->element[3] << 24) | (fmt->element[2] << 16) |
+		(fmt->element[1] << 8) | (fmt->element[0] << 0);
+	src_format |= ((fmt->unpack_count - 1) << 12) |
+		(fmt->unpack_tight << 17) |
+		(fmt->unpack_align_msb << 18) |
+		((fmt->bpp - 1) << 9);
+
+	if (fmt->fetch_mode != DPU_FETCH_LINEAR) {
+		if (DPU_FORMAT_IS_UBWC(fmt))
+			opmode |= MDSS_MDP_OP_BWC_EN;
+		src_format |= (fmt->fetch_mode & 3) << 30; /*FRAME_FORMAT */
+		DPU_REG_WRITE(c, SSPP_FETCH_CONFIG,
+			DPU_FETCH_CONFIG_RESET_VALUE |
+			ctx->mdp->highest_bank_bit << 18);
+		if (IS_UBWC_20_SUPPORTED(ctx->catalog->caps->ubwc_version)) {
+			fast_clear = fmt->alpha_enable ? BIT(31) : 0;
+			DPU_REG_WRITE(c, SSPP_UBWC_STATIC_CTRL,
+					fast_clear | (ctx->mdp->ubwc_swizzle) |
+					(ctx->mdp->highest_bank_bit << 4));
+		}
+	}
+
+	opmode |= MDSS_MDP_OP_PE_OVERRIDE;
+
+	/* if this is YUV pixel format, enable CSC */
+	if (DPU_FORMAT_IS_YUV(fmt))
+		src_format |= BIT(15);
+
+	if (DPU_FORMAT_IS_DX(fmt))
+		src_format |= BIT(14);
+
+	/* update scaler opmode, if appropriate */
+	if (test_bit(DPU_SSPP_CSC, &ctx->cap->features))
+		_sspp_setup_opmode(ctx, VIG_OP_CSC_EN | VIG_OP_CSC_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+	else if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features))
+		_sspp_setup_csc10_opmode(ctx,
+			VIG_CSC_10_EN | VIG_CSC_10_SRC_DATAFMT,
+			DPU_FORMAT_IS_YUV(fmt));
+
+	DPU_REG_WRITE(c, format_off + idx, src_format);
+	DPU_REG_WRITE(c, unpack_pat_off + idx, unpack);
+	DPU_REG_WRITE(c, op_mode_off + idx, opmode);
+
+	/* clear previous UBWC error */
+	DPU_REG_WRITE(c, SSPP_UBWC_ERROR_STATUS + idx, BIT(31));
+}
+
+static void dpu_hw_sspp_setup_pe_config(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pixel_ext *pe_ext)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u8 color;
+	u32 lr_pe[4], tb_pe[4], tot_req_pixels[4];
+	const u32 bytemask = 0xff;
+	const u32 shortmask = 0xffff;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !pe_ext)
+		return;
+
+	c = &ctx->hw;
+
+	/* program SW pixel extension override for all pipes*/
+	for (color = 0; color < DPU_MAX_PLANES; color++) {
+		/* color 2 has the same set of registers as color 1 */
+		if (color == 2)
+			continue;
+
+		lr_pe[color] = ((pe_ext->right_ftch[color] & bytemask) << 24)|
+			((pe_ext->right_rpt[color] & bytemask) << 16)|
+			((pe_ext->left_ftch[color] & bytemask) << 8)|
+			(pe_ext->left_rpt[color] & bytemask);
+
+		tb_pe[color] = ((pe_ext->btm_ftch[color] & bytemask) << 24)|
+			((pe_ext->btm_rpt[color] & bytemask) << 16)|
+			((pe_ext->top_ftch[color] & bytemask) << 8)|
+			(pe_ext->top_rpt[color] & bytemask);
+
+		tot_req_pixels[color] = (((pe_ext->roi_h[color] +
+			pe_ext->num_ext_pxls_top[color] +
+			pe_ext->num_ext_pxls_btm[color]) & shortmask) << 16) |
+			((pe_ext->roi_w[color] +
+			pe_ext->num_ext_pxls_left[color] +
+			pe_ext->num_ext_pxls_right[color]) & shortmask);
+	}
+
+	/* color 0 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_LR + idx, lr_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_TB + idx, tb_pe[0]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C0_REQ_PIXELS + idx,
+			tot_req_pixels[0]);
+
+	/* color 1 and color 2 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_LR + idx, lr_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_TB + idx, tb_pe[1]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C1C2_REQ_PIXELS + idx,
+			tot_req_pixels[1]);
+
+	/* color 3 */
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_LR + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_TB + idx, lr_pe[3]);
+	DPU_REG_WRITE(c, SSPP_SW_PIX_EXT_C3_REQ_PIXELS + idx,
+			tot_req_pixels[3]);
+}
+
+static void _dpu_hw_sspp_setup_scaler3(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *sspp,
+		struct dpu_hw_pixel_ext *pe,
+		void *scaler_cfg)
+{
+	u32 idx;
+	struct dpu_hw_scaler3_cfg *scaler3_cfg = scaler_cfg;
+
+	(void)pe;
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx) || !sspp
+		|| !scaler3_cfg || !ctx || !ctx->cap || !ctx->cap->sblk)
+		return;
+
+	dpu_hw_setup_scaler3(&ctx->hw, scaler3_cfg, idx,
+			ctx->cap->sblk->scaler_blk.version,
+			sspp->layout.format);
+}
+
+static u32 _dpu_hw_sspp_get_scaler3_ver(struct dpu_hw_pipe *ctx)
+{
+	u32 idx;
+
+	if (!ctx || _sspp_subblk_offset(ctx, DPU_SSPP_SCALER_QSEED3, &idx))
+		return 0;
+
+	return dpu_hw_get_scaler3_ver(&ctx->hw, idx);
+}
+
+/**
+ * dpu_hw_sspp_setup_rects()
+ */
+static void dpu_hw_sspp_setup_rects(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_index)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 src_size, src_xy, dst_size, dst_xy, ystride0, ystride1;
+	u32 src_size_off, src_xy_off, out_size_off, out_xy_off;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx) || !cfg)
+		return;
+
+	c = &ctx->hw;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0) {
+		src_size_off = SSPP_SRC_SIZE;
+		src_xy_off = SSPP_SRC_XY;
+		out_size_off = SSPP_OUT_SIZE;
+		out_xy_off = SSPP_OUT_XY;
+	} else {
+		src_size_off = SSPP_SRC_SIZE_REC1;
+		src_xy_off = SSPP_SRC_XY_REC1;
+		out_size_off = SSPP_OUT_SIZE_REC1;
+		out_xy_off = SSPP_OUT_XY_REC1;
+	}
+
+
+	/* src and dest rect programming */
+	src_xy = (cfg->src_rect.y1 << 16) | cfg->src_rect.x1;
+	src_size = (drm_rect_height(&cfg->src_rect) << 16) |
+		   drm_rect_width(&cfg->src_rect);
+	dst_xy = (cfg->dst_rect.y1 << 16) | cfg->dst_rect.x1;
+	dst_size = (drm_rect_height(&cfg->dst_rect) << 16) |
+		drm_rect_width(&cfg->dst_rect);
+
+	if (rect_index == DPU_SSPP_RECT_SOLO) {
+		ystride0 = (cfg->layout.plane_pitch[0]) |
+			(cfg->layout.plane_pitch[1] << 16);
+		ystride1 = (cfg->layout.plane_pitch[2]) |
+			(cfg->layout.plane_pitch[3] << 16);
+	} else {
+		ystride0 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE0 + idx);
+		ystride1 = DPU_REG_READ(c, SSPP_SRC_YSTRIDE1 + idx);
+
+		if (rect_index == DPU_SSPP_RECT_0) {
+			ystride0 = (ystride0 & 0xFFFF0000) |
+				(cfg->layout.plane_pitch[0] & 0x0000FFFF);
+			ystride1 = (ystride1 & 0xFFFF0000)|
+				(cfg->layout.plane_pitch[2] & 0x0000FFFF);
+		} else {
+			ystride0 = (ystride0 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[0] << 16) &
+				 0xFFFF0000);
+			ystride1 = (ystride1 & 0x0000FFFF) |
+				((cfg->layout.plane_pitch[2] << 16) &
+				 0xFFFF0000);
+		}
+	}
+
+	/* rectangle register programming */
+	DPU_REG_WRITE(c, src_size_off + idx, src_size);
+	DPU_REG_WRITE(c, src_xy_off + idx, src_xy);
+	DPU_REG_WRITE(c, out_size_off + idx, dst_size);
+	DPU_REG_WRITE(c, out_xy_off + idx, dst_xy);
+
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE0 + idx, ystride0);
+	DPU_REG_WRITE(c, SSPP_SRC_YSTRIDE1 + idx, ystride1);
+}
+
+static void dpu_hw_sspp_setup_sourceaddress(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *cfg,
+		enum dpu_sspp_multirect_index rect_mode)
+{
+	int i;
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_mode == DPU_SSPP_RECT_SOLO) {
+		for (i = 0; i < ARRAY_SIZE(cfg->layout.plane_addr); i++)
+			DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx + i * 0x4,
+					cfg->layout.plane_addr[i]);
+	} else if (rect_mode == DPU_SSPP_RECT_0) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC0_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC2_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC1_ADDR + idx,
+				cfg->layout.plane_addr[0]);
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC3_ADDR + idx,
+				cfg->layout.plane_addr[2]);
+	}
+}
+
+static void dpu_hw_sspp_setup_csc(struct dpu_hw_pipe *ctx,
+		struct dpu_csc_cfg *data)
+{
+	u32 idx;
+	bool csc10 = false;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_CSC, &idx) || !data)
+		return;
+
+	if (test_bit(DPU_SSPP_CSC_10BIT, &ctx->cap->features)) {
+		idx += CSC_10BIT_OFFSET;
+		csc10 = true;
+	}
+
+	dpu_hw_csc_setup(&ctx->hw, idx, data, csc10);
+}
+
+static void dpu_hw_sspp_setup_solidfill(struct dpu_hw_pipe *ctx, u32 color, enum
+		dpu_sspp_multirect_index rect_index)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (rect_index == DPU_SSPP_RECT_SOLO || rect_index == DPU_SSPP_RECT_0)
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR + idx, color);
+	else
+		DPU_REG_WRITE(&ctx->hw, SSPP_SRC_CONSTANT_COLOR_REC1 + idx,
+				color);
+}
+
+static void dpu_hw_sspp_setup_danger_safe_lut(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_DANGER_LUT + idx, cfg->danger_lut);
+	DPU_REG_WRITE(&ctx->hw, SSPP_SAFE_LUT + idx, cfg->safe_lut);
+}
+
+static void dpu_hw_sspp_setup_creq_lut(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (ctx->cap && test_bit(DPU_SSPP_QOS_8LVL, &ctx->cap->features)) {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_0 + idx, cfg->creq_lut);
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT_1 + idx,
+				cfg->creq_lut >> 32);
+	} else {
+		DPU_REG_WRITE(&ctx->hw, SSPP_CREQ_LUT + idx, cfg->creq_lut);
+	}
+}
+
+static void dpu_hw_sspp_setup_qos_ctrl(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_qos_cfg *cfg)
+{
+	u32 idx;
+	u32 qos_ctrl = 0;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (cfg->vblank_en) {
+		qos_ctrl |= ((cfg->creq_vblank &
+				SSPP_QOS_CTRL_CREQ_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_CREQ_VBLANK_OFF);
+		qos_ctrl |= ((cfg->danger_vblank &
+				SSPP_QOS_CTRL_DANGER_VBLANK_MASK) <<
+				SSPP_QOS_CTRL_DANGER_VBLANK_OFF);
+		qos_ctrl |= SSPP_QOS_CTRL_VBLANK_EN;
+	}
+
+	if (cfg->danger_safe_en)
+		qos_ctrl |= SSPP_QOS_CTRL_DANGER_SAFE_EN;
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_QOS_CTRL + idx, qos_ctrl);
+}
+
+static void dpu_hw_sspp_setup_cdp(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cdp_cfg *cfg)
+{
+	u32 idx;
+	u32 cdp_cntl = 0;
+
+	if (!ctx || !cfg)
+		return;
+
+	if (_sspp_subblk_offset(ctx, DPU_SSPP_SRC, &idx))
+		return;
+
+	if (cfg->enable)
+		cdp_cntl |= BIT(0);
+	if (cfg->ubwc_meta_enable)
+		cdp_cntl |= BIT(1);
+	if (cfg->tile_amortize_enable)
+		cdp_cntl |= BIT(2);
+	if (cfg->preload_ahead == DPU_SSPP_CDP_PRELOAD_AHEAD_64)
+		cdp_cntl |= BIT(3);
+
+	DPU_REG_WRITE(&ctx->hw, SSPP_CDP_CNTL, cdp_cntl);
+}
+
+static void _setup_layer_ops(struct dpu_hw_pipe *c,
+		unsigned long features)
+{
+	if (test_bit(DPU_SSPP_SRC, &features)) {
+		c->ops.setup_format = dpu_hw_sspp_setup_format;
+		c->ops.setup_rects = dpu_hw_sspp_setup_rects;
+		c->ops.setup_sourceaddress = dpu_hw_sspp_setup_sourceaddress;
+		c->ops.setup_solidfill = dpu_hw_sspp_setup_solidfill;
+		c->ops.setup_pe = dpu_hw_sspp_setup_pe_config;
+	}
+
+	if (test_bit(DPU_SSPP_QOS, &features)) {
+		c->ops.setup_danger_safe_lut =
+			dpu_hw_sspp_setup_danger_safe_lut;
+		c->ops.setup_creq_lut = dpu_hw_sspp_setup_creq_lut;
+		c->ops.setup_qos_ctrl = dpu_hw_sspp_setup_qos_ctrl;
+	}
+
+	if (test_bit(DPU_SSPP_CSC, &features) ||
+		test_bit(DPU_SSPP_CSC_10BIT, &features))
+		c->ops.setup_csc = dpu_hw_sspp_setup_csc;
+
+	if (dpu_hw_sspp_multirect_enabled(c->cap))
+		c->ops.setup_multirect = dpu_hw_sspp_setup_multirect;
+
+	if (test_bit(DPU_SSPP_SCALER_QSEED3, &features)) {
+		c->ops.setup_scaler = _dpu_hw_sspp_setup_scaler3;
+		c->ops.get_scaler_ver = _dpu_hw_sspp_get_scaler3_ver;
+	}
+
+	if (test_bit(DPU_SSPP_CDP, &features))
+		c->ops.setup_cdp = dpu_hw_sspp_setup_cdp;
+}
+
+static struct dpu_sspp_cfg *_sspp_offset(enum dpu_sspp sspp,
+		void __iomem *addr,
+		struct dpu_mdss_cfg *catalog,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if ((sspp < SSPP_MAX) && catalog && addr && b) {
+		for (i = 0; i < catalog->sspp_count; i++) {
+			if (sspp == catalog->sspp[i].id) {
+				b->base_off = addr;
+				b->blk_off = catalog->sspp[i].base;
+				b->length = catalog->sspp[i].len;
+				b->hwversion = catalog->hwversion;
+				b->log_mask = DPU_DBG_MASK_SSPP;
+				return &catalog->sspp[i];
+			}
+		}
+	}
+
+	return ERR_PTR(-ENOMEM);
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, struct dpu_mdss_cfg *catalog,
+		bool is_virtual_pipe)
+{
+	struct dpu_hw_pipe *hw_pipe;
+	struct dpu_sspp_cfg *cfg;
+	int rc;
+
+	if (!addr || !catalog)
+		return ERR_PTR(-EINVAL);
+
+	hw_pipe = kzalloc(sizeof(*hw_pipe), GFP_KERNEL);
+	if (!hw_pipe)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _sspp_offset(idx, addr, catalog, &hw_pipe->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(hw_pipe);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* Assign ops */
+	hw_pipe->catalog = catalog;
+	hw_pipe->mdp = &catalog->mdp[0];
+	hw_pipe->idx = idx;
+	hw_pipe->cap = cfg;
+	_setup_layer_ops(hw_pipe, hw_pipe->cap->features);
+
+	rc = dpu_hw_blk_init(&hw_pipe->base, DPU_HW_BLK_SSPP, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	return hw_pipe;
+
+blk_init_error:
+	kzfree(hw_pipe);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx)
+{
+	if (ctx)
+		dpu_hw_blk_destroy(&ctx->base);
+	kfree(ctx);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
new file mode 100644
index 000000000000..4d81e5f5ce1b
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -0,0 +1,424 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_SSPP_H
+#define _DPU_HW_SSPP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+#include "dpu_formats.h"
+
+struct dpu_hw_pipe;
+
+/**
+ * Flags
+ */
+#define DPU_SSPP_FLIP_LR		BIT(0)
+#define DPU_SSPP_FLIP_UD		BIT(1)
+#define DPU_SSPP_SOURCE_ROTATED_90	BIT(2)
+#define DPU_SSPP_ROT_90			BIT(3)
+#define DPU_SSPP_SOLID_FILL		BIT(4)
+
+/**
+ * Define all scaler feature bits in catalog
+ */
+#define DPU_SSPP_SCALER ((1UL << DPU_SSPP_SCALER_RGB) | \
+	(1UL << DPU_SSPP_SCALER_QSEED2) | \
+	(1UL << DPU_SSPP_SCALER_QSEED3))
+
+/**
+ * Component indices
+ */
+enum {
+	DPU_SSPP_COMP_0,
+	DPU_SSPP_COMP_1_2,
+	DPU_SSPP_COMP_2,
+	DPU_SSPP_COMP_3,
+
+	DPU_SSPP_COMP_MAX
+};
+
+/**
+ * DPU_SSPP_RECT_SOLO - multirect disabled
+ * DPU_SSPP_RECT_0 - rect0 of a multirect pipe
+ * DPU_SSPP_RECT_1 - rect1 of a multirect pipe
+ *
+ * Note: HW supports multirect with either RECT0 or
+ * RECT1. Considering no benefit of such configs over
+ * SOLO mode and to keep the plane management simple,
+ * we dont support single rect multirect configs.
+ */
+enum dpu_sspp_multirect_index {
+	DPU_SSPP_RECT_SOLO = 0,
+	DPU_SSPP_RECT_0,
+	DPU_SSPP_RECT_1,
+};
+
+enum dpu_sspp_multirect_mode {
+	DPU_SSPP_MULTIRECT_NONE = 0,
+	DPU_SSPP_MULTIRECT_PARALLEL,
+	DPU_SSPP_MULTIRECT_TIME_MX,
+};
+
+enum {
+	DPU_FRAME_LINEAR,
+	DPU_FRAME_TILE_A4X,
+	DPU_FRAME_TILE_A5X,
+};
+
+enum dpu_hw_filter {
+	DPU_SCALE_FILTER_NEAREST = 0,
+	DPU_SCALE_FILTER_BIL,
+	DPU_SCALE_FILTER_PCMN,
+	DPU_SCALE_FILTER_CA,
+	DPU_SCALE_FILTER_MAX
+};
+
+enum dpu_hw_filter_alpa {
+	DPU_SCALE_ALPHA_PIXEL_REP,
+	DPU_SCALE_ALPHA_BIL
+};
+
+enum dpu_hw_filter_yuv {
+	DPU_SCALE_2D_4X4,
+	DPU_SCALE_2D_CIR,
+	DPU_SCALE_1D_SEP,
+	DPU_SCALE_BIL
+};
+
+struct dpu_hw_sharp_cfg {
+	u32 strength;
+	u32 edge_thr;
+	u32 smooth_thr;
+	u32 noise_thr;
+};
+
+struct dpu_hw_pixel_ext {
+	/* scaling factors are enabled for this input layer */
+	uint8_t enable_pxl_ext;
+
+	int init_phase_x[DPU_MAX_PLANES];
+	int phase_step_x[DPU_MAX_PLANES];
+	int init_phase_y[DPU_MAX_PLANES];
+	int phase_step_y[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels extension in left, right, top and bottom direction
+	 * for all color components. This pixel value for each color component
+	 * should be sum of fetch + repeat pixels.
+	 */
+	int num_ext_pxls_left[DPU_MAX_PLANES];
+	int num_ext_pxls_right[DPU_MAX_PLANES];
+	int num_ext_pxls_top[DPU_MAX_PLANES];
+	int num_ext_pxls_btm[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top and
+	 * bottom directions from source image for scaling.
+	 */
+	int left_ftch[DPU_MAX_PLANES];
+	int right_ftch[DPU_MAX_PLANES];
+	int top_ftch[DPU_MAX_PLANES];
+	int btm_ftch[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int left_rpt[DPU_MAX_PLANES];
+	int right_rpt[DPU_MAX_PLANES];
+	int top_rpt[DPU_MAX_PLANES];
+	int btm_rpt[DPU_MAX_PLANES];
+
+	uint32_t roi_w[DPU_MAX_PLANES];
+	uint32_t roi_h[DPU_MAX_PLANES];
+
+	/*
+	 * Filter type to be used for scaling in horizontal and vertical
+	 * directions
+	 */
+	enum dpu_hw_filter horz_filter[DPU_MAX_PLANES];
+	enum dpu_hw_filter vert_filter[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_hw_pipe_cfg : Pipe description
+ * @layout:    format layout information for programming buffer to hardware
+ * @src_rect:  src ROI, caller takes into account the different operations
+ *             such as decimation, flip etc to program this field
+ * @dest_rect: destination ROI.
+ * @index:     index of the rectangle of SSPP
+ * @mode:      parallel or time multiplex multirect mode
+ */
+struct dpu_hw_pipe_cfg {
+	struct dpu_hw_fmt_layout layout;
+	struct drm_rect src_rect;
+	struct drm_rect dst_rect;
+	enum dpu_sspp_multirect_index index;
+	enum dpu_sspp_multirect_mode mode;
+};
+
+/**
+ * struct dpu_hw_pipe_qos_cfg : Source pipe QoS configuration
+ * @danger_lut: LUT for generate danger level based on fill level
+ * @safe_lut: LUT for generate safe level based on fill level
+ * @creq_lut: LUT for generate creq level based on fill level
+ * @creq_vblank: creq value generated to vbif during vertical blanking
+ * @danger_vblank: danger value generated during vertical blanking
+ * @vblank_en: enable creq_vblank and danger_vblank during vblank
+ * @danger_safe_en: enable danger safe generation
+ */
+struct dpu_hw_pipe_qos_cfg {
+	u32 danger_lut;
+	u32 safe_lut;
+	u64 creq_lut;
+	u32 creq_vblank;
+	u32 danger_vblank;
+	bool vblank_en;
+	bool danger_safe_en;
+};
+
+/**
+ * enum CDP preload ahead address size
+ */
+enum {
+	DPU_SSPP_CDP_PRELOAD_AHEAD_32,
+	DPU_SSPP_CDP_PRELOAD_AHEAD_64
+};
+
+/**
+ * struct dpu_hw_pipe_cdp_cfg : CDP configuration
+ * @enable: true to enable CDP
+ * @ubwc_meta_enable: true to enable ubwc metadata preload
+ * @tile_amortize_enable: true to enable amortization control for tile format
+ * @preload_ahead: number of request to preload ahead
+ *	DPU_SSPP_CDP_PRELOAD_AHEAD_32,
+ *	DPU_SSPP_CDP_PRELOAD_AHEAD_64
+ */
+struct dpu_hw_pipe_cdp_cfg {
+	bool enable;
+	bool ubwc_meta_enable;
+	bool tile_amortize_enable;
+	u32 preload_ahead;
+};
+
+/**
+ * struct dpu_hw_pipe_ts_cfg - traffic shaper configuration
+ * @size: size to prefill in bytes, or zero to disable
+ * @time: time to prefill in usec, or zero to disable
+ */
+struct dpu_hw_pipe_ts_cfg {
+	u64 size;
+	u64 time;
+};
+
+/**
+ * struct dpu_hw_sspp_ops - interface to the SSPP Hw driver functions
+ * Caller must call the init function to get the pipe context for each pipe
+ * Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_sspp_ops {
+	/**
+	 * setup_format - setup pixel format cropping rectangle, flip
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @flags: Extra flags for format config
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_format)(struct dpu_hw_pipe *ctx,
+			const struct dpu_format *fmt, u32 flags,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_rects - setup pipe ROI rectangles
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_rects)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_pe - setup pipe pixel extension
+	 * @ctx: Pointer to pipe context
+	 * @pe_ext: Pointer to pixel ext settings
+	 */
+	void (*setup_pe)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pixel_ext *pe_ext);
+
+	/**
+	 * setup_sourceaddress - setup pipe source addresses
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe config structure
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_sourceaddress)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cfg *cfg,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_csc - setup color space coversion
+	 * @ctx: Pointer to pipe context
+	 * @data: Pointer to config structure
+	 */
+	void (*setup_csc)(struct dpu_hw_pipe *ctx, struct dpu_csc_cfg *data);
+
+	/**
+	 * setup_solidfill - enable/disable colorfill
+	 * @ctx: Pointer to pipe context
+	 * @const_color: Fill color value
+	 * @flags: Pipe flags
+	 * @index: rectangle index in multirect
+	 */
+	void (*setup_solidfill)(struct dpu_hw_pipe *ctx, u32 color,
+			enum dpu_sspp_multirect_index index);
+
+	/**
+	 * setup_multirect - setup multirect configuration
+	 * @ctx: Pointer to pipe context
+	 * @index: rectangle index in multirect
+	 * @mode: parallel fetch / time multiplex multirect mode
+	 */
+
+	void (*setup_multirect)(struct dpu_hw_pipe *ctx,
+			enum dpu_sspp_multirect_index index,
+			enum dpu_sspp_multirect_mode mode);
+
+	/**
+	 * setup_sharpening - setup sharpening
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to config structure
+	 */
+	void (*setup_sharpening)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_sharp_cfg *cfg);
+
+	/**
+	 * setup_danger_safe_lut - setup danger safe LUTs
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_danger_safe_lut)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_creq_lut - setup CREQ LUT
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_creq_lut)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_qos_ctrl - setup QoS control
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to pipe QoS configuration
+	 *
+	 */
+	void (*setup_qos_ctrl)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_qos_cfg *cfg);
+
+	/**
+	 * setup_histogram - setup histograms
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to histogram configuration
+	 */
+	void (*setup_histogram)(struct dpu_hw_pipe *ctx,
+			void *cfg);
+
+	/**
+	 * setup_scaler - setup scaler
+	 * @ctx: Pointer to pipe context
+	 * @pipe_cfg: Pointer to pipe configuration
+	 * @pe_cfg: Pointer to pixel extension configuration
+	 * @scaler_cfg: Pointer to scaler configuration
+	 */
+	void (*setup_scaler)(struct dpu_hw_pipe *ctx,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		struct dpu_hw_pixel_ext *pe_cfg,
+		void *scaler_cfg);
+
+	/**
+	 * get_scaler_ver - get scaler h/w version
+	 * @ctx: Pointer to pipe context
+	 */
+	u32 (*get_scaler_ver)(struct dpu_hw_pipe *ctx);
+
+	/**
+	 * setup_cdp - setup client driven prefetch
+	 * @ctx: Pointer to pipe context
+	 * @cfg: Pointer to cdp configuration
+	 */
+	void (*setup_cdp)(struct dpu_hw_pipe *ctx,
+			struct dpu_hw_pipe_cdp_cfg *cfg);
+};
+
+/**
+ * struct dpu_hw_pipe - pipe description
+ * @base: hardware block base structure
+ * @hw: block hardware details
+ * @catalog: back pointer to catalog
+ * @mdp: pointer to associated mdp portion of the catalog
+ * @idx: pipe index
+ * @cap: pointer to layer_cfg
+ * @ops: pointer to operations possible for this pipe
+ */
+struct dpu_hw_pipe {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+	struct dpu_mdss_cfg *catalog;
+	struct dpu_mdp_cfg *mdp;
+
+	/* Pipe */
+	enum dpu_sspp idx;
+	const struct dpu_sspp_cfg *cap;
+
+	/* Ops */
+	struct dpu_hw_sspp_ops ops;
+};
+
+/**
+ * dpu_hw_pipe - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_pipe *to_dpu_hw_pipe(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_pipe, base);
+}
+
+/**
+ * dpu_hw_sspp_init - initializes the sspp hw driver object.
+ * Should be called once before accessing every pipe.
+ * @idx:  Pipe index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @catalog : Pointer to mdss catalog data
+ * @is_virtual_pipe: is this pipe virtual pipe
+ */
+struct dpu_hw_pipe *dpu_hw_sspp_init(enum dpu_sspp idx,
+		void __iomem *addr, struct dpu_mdss_cfg *catalog,
+		bool is_virtual_pipe);
+
+/**
+ * dpu_hw_sspp_destroy(): Destroys SSPP driver context
+ * should be called during Hw pipe cleanup.
+ * @ctx:  Pointer to SSPP driver context returned by dpu_hw_sspp_init
+ */
+void dpu_hw_sspp_destroy(struct dpu_hw_pipe *ctx);
+
+#endif /*_DPU_HW_SSPP_H */
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
new file mode 100644
index 000000000000..42fc72cf48dd
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -0,0 +1,398 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_top.h"
+#include "dpu_dbg.h"
+#include "dpu_kms.h"
+
+#define SSPP_SPARE                        0x28
+#define UBWC_STATIC                       0x144
+
+#define FLD_SPLIT_DISPLAY_CMD             BIT(1)
+#define FLD_SMART_PANEL_FREE_RUN          BIT(2)
+#define FLD_INTF_1_SW_TRG_MUX             BIT(4)
+#define FLD_INTF_2_SW_TRG_MUX             BIT(8)
+#define FLD_TE_LINE_INTER_WATERLEVEL_MASK 0xFFFF
+
+#define DANGER_STATUS                     0x360
+#define SAFE_STATUS                       0x364
+
+#define TE_LINE_INTERVAL                  0x3F4
+
+#define TRAFFIC_SHAPER_EN                 BIT(31)
+#define TRAFFIC_SHAPER_RD_CLIENT(num)     (0x030 + (num * 4))
+#define TRAFFIC_SHAPER_WR_CLIENT(num)     (0x060 + (num * 4))
+#define TRAFFIC_SHAPER_FIXPOINT_FACTOR    4
+
+#define MDP_WD_TIMER_0_CTL                0x380
+#define MDP_WD_TIMER_0_CTL2               0x384
+#define MDP_WD_TIMER_0_LOAD_VALUE         0x388
+#define MDP_WD_TIMER_1_CTL                0x390
+#define MDP_WD_TIMER_1_CTL2               0x394
+#define MDP_WD_TIMER_1_LOAD_VALUE         0x398
+#define MDP_WD_TIMER_2_CTL                0x420
+#define MDP_WD_TIMER_2_CTL2               0x424
+#define MDP_WD_TIMER_2_LOAD_VALUE         0x428
+#define MDP_WD_TIMER_3_CTL                0x430
+#define MDP_WD_TIMER_3_CTL2               0x434
+#define MDP_WD_TIMER_3_LOAD_VALUE         0x438
+#define MDP_WD_TIMER_4_CTL                0x440
+#define MDP_WD_TIMER_4_CTL2               0x444
+#define MDP_WD_TIMER_4_LOAD_VALUE         0x448
+
+#define MDP_TICK_COUNT                    16
+#define XO_CLK_RATE                       19200
+#define MS_TICKS_IN_SEC                   1000
+
+#define CALCULATE_WD_LOAD_VALUE(fps) \
+	((uint32_t)((MS_TICKS_IN_SEC * XO_CLK_RATE)/(MDP_TICK_COUNT * fps)))
+
+#define DCE_SEL                           0x450
+
+static void dpu_hw_setup_split_pipe(struct dpu_hw_mdp *mdp,
+		struct split_pipe_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 upper_pipe = 0;
+	u32 lower_pipe = 0;
+
+	if (!mdp || !cfg)
+		return;
+
+	c = &mdp->hw;
+
+	if (cfg->en) {
+		if (cfg->mode == INTF_MODE_CMD) {
+			lower_pipe = FLD_SPLIT_DISPLAY_CMD;
+			/* interface controlling sw trigger */
+			if (cfg->intf == INTF_2)
+				lower_pipe |= FLD_INTF_1_SW_TRG_MUX;
+			else
+				lower_pipe |= FLD_INTF_2_SW_TRG_MUX;
+			upper_pipe = lower_pipe;
+		} else {
+			if (cfg->intf == INTF_2) {
+				lower_pipe = FLD_INTF_1_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_2_SW_TRG_MUX;
+			} else {
+				lower_pipe = FLD_INTF_2_SW_TRG_MUX;
+				upper_pipe = FLD_INTF_1_SW_TRG_MUX;
+			}
+		}
+	}
+
+	DPU_REG_WRITE(c, SSPP_SPARE, cfg->split_flush_en ? 0x1 : 0x0);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_LOWER_PIPE_CTRL, lower_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_UPPER_PIPE_CTRL, upper_pipe);
+	DPU_REG_WRITE(c, SPLIT_DISPLAY_EN, cfg->en & 0x1);
+}
+
+static void dpu_hw_setup_cdm_output(struct dpu_hw_mdp *mdp,
+		struct cdm_output_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 out_ctl = 0;
+
+	if (!mdp || !cfg)
+		return;
+
+	c = &mdp->hw;
+
+	if (cfg->intf_en)
+		out_ctl |= BIT(19);
+
+	DPU_REG_WRITE(c, MDP_OUT_CTL_0, out_ctl);
+}
+
+static bool dpu_hw_setup_clk_force_ctrl(struct dpu_hw_mdp *mdp,
+		enum dpu_clk_ctrl_type clk_ctrl, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off, bit_off;
+	u32 reg_val, new_val;
+	bool clk_forced_on;
+
+	if (!mdp)
+		return false;
+
+	c = &mdp->hw;
+
+	if (clk_ctrl <= DPU_CLK_CTRL_NONE || clk_ctrl >= DPU_CLK_CTRL_MAX)
+		return false;
+
+	reg_off = mdp->caps->clk_ctrls[clk_ctrl].reg_off;
+	bit_off = mdp->caps->clk_ctrls[clk_ctrl].bit_off;
+
+	reg_val = DPU_REG_READ(c, reg_off);
+
+	if (enable)
+		new_val = reg_val | BIT(bit_off);
+	else
+		new_val = reg_val & ~BIT(bit_off);
+
+	DPU_REG_WRITE(c, reg_off, new_val);
+
+	clk_forced_on = !(reg_val & BIT(bit_off));
+
+	return clk_forced_on;
+}
+
+
+static void dpu_hw_get_danger_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, DANGER_STATUS);
+	status->mdp = (value >> 0) & 0x3;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x3;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x3;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x3;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x3;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x3;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x3;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x3;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x3;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x3;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x3;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x3;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x3;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x3;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x3;
+}
+
+static void dpu_hw_setup_vsync_source(struct dpu_hw_mdp *mdp,
+		struct dpu_vsync_source_cfg *cfg)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg, wd_load_value, wd_ctl, wd_ctl2, i;
+	static const u32 pp_offset[PINGPONG_MAX] = {0xC, 0x8, 0x4, 0x13, 0x18};
+
+	if (!mdp || !cfg || (cfg->pp_count > ARRAY_SIZE(cfg->ppnumber)))
+		return;
+
+	c = &mdp->hw;
+	reg = DPU_REG_READ(c, MDP_VSYNC_SEL);
+	for (i = 0; i < cfg->pp_count; i++) {
+		int pp_idx = cfg->ppnumber[i] - PINGPONG_0;
+
+		if (pp_idx >= ARRAY_SIZE(pp_offset))
+			continue;
+
+		reg &= ~(0xf << pp_offset[pp_idx]);
+		reg |= (cfg->vsync_source & 0xf) << pp_offset[pp_idx];
+	}
+	DPU_REG_WRITE(c, MDP_VSYNC_SEL, reg);
+
+	if (cfg->vsync_source >= DPU_VSYNC_SOURCE_WD_TIMER_4 &&
+			cfg->vsync_source <= DPU_VSYNC_SOURCE_WD_TIMER_0) {
+		switch (cfg->vsync_source) {
+		case DPU_VSYNC_SOURCE_WD_TIMER_4:
+			wd_load_value = MDP_WD_TIMER_4_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_4_CTL;
+			wd_ctl2 = MDP_WD_TIMER_4_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_3:
+			wd_load_value = MDP_WD_TIMER_3_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_3_CTL;
+			wd_ctl2 = MDP_WD_TIMER_3_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_2:
+			wd_load_value = MDP_WD_TIMER_2_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_2_CTL;
+			wd_ctl2 = MDP_WD_TIMER_2_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_1:
+			wd_load_value = MDP_WD_TIMER_1_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_1_CTL;
+			wd_ctl2 = MDP_WD_TIMER_1_CTL2;
+			break;
+		case DPU_VSYNC_SOURCE_WD_TIMER_0:
+		default:
+			wd_load_value = MDP_WD_TIMER_0_LOAD_VALUE;
+			wd_ctl = MDP_WD_TIMER_0_CTL;
+			wd_ctl2 = MDP_WD_TIMER_0_CTL2;
+			break;
+		}
+
+		DPU_REG_WRITE(c, wd_load_value,
+			CALCULATE_WD_LOAD_VALUE(cfg->frame_rate));
+
+		DPU_REG_WRITE(c, wd_ctl, BIT(0)); /* clear timer */
+		reg = DPU_REG_READ(c, wd_ctl2);
+		reg |= BIT(8);		/* enable heartbeat timer */
+		reg |= BIT(0);		/* enable WD timer */
+		DPU_REG_WRITE(c, wd_ctl2, reg);
+
+		/* make sure that timers are enabled/disabled for vsync state */
+		wmb();
+	}
+}
+
+static void dpu_hw_get_safe_status(struct dpu_hw_mdp *mdp,
+		struct dpu_danger_safe_status *status)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 value;
+
+	if (!mdp || !status)
+		return;
+
+	c = &mdp->hw;
+
+	value = DPU_REG_READ(c, SAFE_STATUS);
+	status->mdp = (value >> 0) & 0x1;
+	status->sspp[SSPP_VIG0] = (value >> 4) & 0x1;
+	status->sspp[SSPP_VIG1] = (value >> 6) & 0x1;
+	status->sspp[SSPP_VIG2] = (value >> 8) & 0x1;
+	status->sspp[SSPP_VIG3] = (value >> 10) & 0x1;
+	status->sspp[SSPP_RGB0] = (value >> 12) & 0x1;
+	status->sspp[SSPP_RGB1] = (value >> 14) & 0x1;
+	status->sspp[SSPP_RGB2] = (value >> 16) & 0x1;
+	status->sspp[SSPP_RGB3] = (value >> 18) & 0x1;
+	status->sspp[SSPP_DMA0] = (value >> 20) & 0x1;
+	status->sspp[SSPP_DMA1] = (value >> 22) & 0x1;
+	status->sspp[SSPP_DMA2] = (value >> 28) & 0x1;
+	status->sspp[SSPP_DMA3] = (value >> 30) & 0x1;
+	status->sspp[SSPP_CURSOR0] = (value >> 24) & 0x1;
+	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x1;
+}
+
+void dpu_hw_reset_ubwc(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_blk_reg_map c;
+
+	if (!mdp || !m)
+		return;
+
+	if (!IS_UBWC_20_SUPPORTED(m->caps->ubwc_version))
+		return;
+
+	/* force blk offset to zero to access beginning of register region */
+	c = mdp->hw;
+	c.blk_off = 0x0;
+	DPU_REG_WRITE(&c, UBWC_STATIC, m->mdp[0].ubwc_static);
+}
+
+static void dpu_hw_intf_audio_select(struct dpu_hw_mdp *mdp)
+{
+	struct dpu_hw_blk_reg_map *c;
+
+	if (!mdp)
+		return;
+
+	c = &mdp->hw;
+
+	DPU_REG_WRITE(c, HDMI_DP_CORE_SELECT, 0x1);
+}
+
+static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops,
+		unsigned long cap)
+{
+	ops->setup_split_pipe = dpu_hw_setup_split_pipe;
+	ops->setup_cdm_output = dpu_hw_setup_cdm_output;
+	ops->setup_clk_force_ctrl = dpu_hw_setup_clk_force_ctrl;
+	ops->get_danger_status = dpu_hw_get_danger_status;
+	ops->setup_vsync_source = dpu_hw_setup_vsync_source;
+	ops->get_safe_status = dpu_hw_get_safe_status;
+	ops->reset_ubwc = dpu_hw_reset_ubwc;
+	ops->intf_audio_select = dpu_hw_intf_audio_select;
+}
+
+static const struct dpu_mdp_cfg *_top_offset(enum dpu_mdp mdp,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	if (!m || !addr || !b)
+		return ERR_PTR(-EINVAL);
+
+	for (i = 0; i < m->mdp_count; i++) {
+		if (mdp == m->mdp[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->mdp[i].base;
+			b->length = m->mdp[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_TOP;
+			return &m->mdp[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static struct dpu_hw_blk_ops dpu_hw_ops = {
+	.start = NULL,
+	.stop = NULL,
+};
+
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_mdp *mdp;
+	const struct dpu_mdp_cfg *cfg;
+	int rc;
+
+	if (!addr || !m)
+		return ERR_PTR(-EINVAL);
+
+	mdp = kzalloc(sizeof(*mdp), GFP_KERNEL);
+	if (!mdp)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &mdp->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(mdp);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	mdp->idx = idx;
+	mdp->caps = cfg;
+	_setup_mdp_ops(&mdp->ops, mdp->caps->features);
+
+	rc = dpu_hw_blk_init(&mdp->base, DPU_HW_BLK_TOP, idx, &dpu_hw_ops);
+	if (rc) {
+		DPU_ERROR("failed to init hw blk %d\n", rc);
+		goto blk_init_error;
+	}
+
+	dpu_dbg_set_dpu_top_offset(mdp->hw.blk_off);
+
+	return mdp;
+
+blk_init_error:
+	kzfree(mdp);
+
+	return ERR_PTR(rc);
+}
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp)
+{
+	if (mdp)
+		dpu_hw_blk_destroy(&mdp->base);
+	kfree(mdp);
+}
+
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
new file mode 100644
index 000000000000..899925aaa6d7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.h
@@ -0,0 +1,202 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_TOP_H
+#define _DPU_HW_TOP_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+#include "dpu_hw_blk.h"
+
+struct dpu_hw_mdp;
+
+/**
+ * struct traffic_shaper_cfg: traffic shaper configuration
+ * @en        : enable/disable traffic shaper
+ * @rd_client : true if read client; false if write client
+ * @client_id : client identifier
+ * @bpc_denom : denominator of byte per clk
+ * @bpc_numer : numerator of byte per clk
+ */
+struct traffic_shaper_cfg {
+	bool en;
+	bool rd_client;
+	u32 client_id;
+	u32 bpc_denom;
+	u64 bpc_numer;
+};
+
+/**
+ * struct split_pipe_cfg - pipe configuration for dual display panels
+ * @en        : Enable/disable dual pipe confguration
+ * @mode      : Panel interface mode
+ * @intf      : Interface id for main control path
+ * @split_flush_en: Allows both the paths to be flushed when master path is
+ *              flushed
+ */
+struct split_pipe_cfg {
+	bool en;
+	enum dpu_intf_mode mode;
+	enum dpu_intf intf;
+	bool split_flush_en;
+};
+
+/**
+ * struct cdm_output_cfg: output configuration for cdm
+ * @intf_en   : enable/disable interface output
+ */
+struct cdm_output_cfg {
+	bool intf_en;
+};
+
+/**
+ * struct dpu_danger_safe_status: danger and safe status signals
+ * @mdp: top level status
+ * @sspp: source pipe status
+ */
+struct dpu_danger_safe_status {
+	u8 mdp;
+	u8 sspp[SSPP_MAX];
+};
+
+/**
+ * struct dpu_vsync_source_cfg - configure vsync source and configure the
+ *                                    watchdog timers if required.
+ * @pp_count: number of ping pongs active
+ * @frame_rate: Display frame rate
+ * @ppnumber: ping pong index array
+ * @vsync_source: vsync source selection
+ */
+struct dpu_vsync_source_cfg {
+	u32 pp_count;
+	u32 frame_rate;
+	u32 ppnumber[PINGPONG_MAX];
+	u32 vsync_source;
+};
+
+/**
+ * struct dpu_hw_mdp_ops - interface to the MDP TOP Hw driver functions
+ * Assumption is these functions will be called after clocks are enabled.
+ * @setup_split_pipe : Programs the pipe control registers
+ * @setup_pp_split : Programs the pp split control registers
+ * @setup_cdm_output : programs cdm control
+ * @setup_traffic_shaper : programs traffic shaper control
+ */
+struct dpu_hw_mdp_ops {
+	/** setup_split_pipe() : Regsiters are not double buffered, thisk
+	 * function should be called before timing control enable
+	 * @mdp  : mdp top context driver
+	 * @cfg  : upper and lower part of pipe configuration
+	 */
+	void (*setup_split_pipe)(struct dpu_hw_mdp *mdp,
+			struct split_pipe_cfg *p);
+
+	/**
+	 * setup_cdm_output() : Setup selection control of the cdm data path
+	 * @mdp  : mdp top context driver
+	 * @cfg  : cdm output configuration
+	 */
+	void (*setup_cdm_output)(struct dpu_hw_mdp *mdp,
+			struct cdm_output_cfg *cfg);
+
+	/**
+	 * setup_traffic_shaper() : Setup traffic shaper control
+	 * @mdp  : mdp top context driver
+	 * @cfg  : traffic shaper configuration
+	 */
+	void (*setup_traffic_shaper)(struct dpu_hw_mdp *mdp,
+			struct traffic_shaper_cfg *cfg);
+
+	/**
+	 * setup_clk_force_ctrl - set clock force control
+	 * @mdp: mdp top context driver
+	 * @clk_ctrl: clock to be controlled
+	 * @enable: force on enable
+	 * @return: if the clock is forced-on by this function
+	 */
+	bool (*setup_clk_force_ctrl)(struct dpu_hw_mdp *mdp,
+			enum dpu_clk_ctrl_type clk_ctrl, bool enable);
+
+	/**
+	 * get_danger_status - get danger status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_danger_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * setup_vsync_source - setup vsync source configuration details
+	 * @mdp: mdp top context driver
+	 * @cfg: vsync source selection configuration
+	 */
+	void (*setup_vsync_source)(struct dpu_hw_mdp *mdp,
+				struct dpu_vsync_source_cfg *cfg);
+
+	/**
+	 * get_safe_status - get safe status
+	 * @mdp: mdp top context driver
+	 * @status: Pointer to danger safe status
+	 */
+	void (*get_safe_status)(struct dpu_hw_mdp *mdp,
+			struct dpu_danger_safe_status *status);
+
+	/**
+	 * reset_ubwc - reset top level UBWC configuration
+	 * @mdp: mdp top context driver
+	 * @m: pointer to mdss catalog data
+	 */
+	void (*reset_ubwc)(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m);
+
+	/**
+	 * intf_audio_select - select the external interface for audio
+	 * @mdp: mdp top context driver
+	 */
+	void (*intf_audio_select)(struct dpu_hw_mdp *mdp);
+};
+
+struct dpu_hw_mdp {
+	struct dpu_hw_blk base;
+	struct dpu_hw_blk_reg_map hw;
+
+	/* top */
+	enum dpu_mdp idx;
+	const struct dpu_mdp_cfg *caps;
+
+	/* ops */
+	struct dpu_hw_mdp_ops ops;
+};
+
+/**
+ * to_dpu_hw_mdp - convert base object dpu_hw_base to container
+ * @hw: Pointer to base hardware block
+ * return: Pointer to hardware block container
+ */
+static inline struct dpu_hw_mdp *to_dpu_hw_mdp(struct dpu_hw_blk *hw)
+{
+	return container_of(hw, struct dpu_hw_mdp, base);
+}
+
+/**
+ * dpu_hw_mdptop_init - initializes the top driver for the passed idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDP
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_mdp *dpu_hw_mdptop_init(enum dpu_mdp idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_mdp_destroy(struct dpu_hw_mdp *mdp);
+
+#endif /*_DPU_HW_TOP_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
new file mode 100644
index 000000000000..1ba571e94b32
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
@@ -0,0 +1,452 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+/* using a file static variables for debugfs access */
+static u32 dpu_hw_util_log_mask = DPU_DBG_MASK_NONE;
+
+/* DPU_SCALER_QSEED3 */
+#define QSEED3_HW_VERSION                  0x00
+#define QSEED3_OP_MODE                     0x04
+#define QSEED3_RGB2Y_COEFF                 0x08
+#define QSEED3_PHASE_INIT                  0x0C
+#define QSEED3_PHASE_STEP_Y_H              0x10
+#define QSEED3_PHASE_STEP_Y_V              0x14
+#define QSEED3_PHASE_STEP_UV_H             0x18
+#define QSEED3_PHASE_STEP_UV_V             0x1C
+#define QSEED3_PRELOAD                     0x20
+#define QSEED3_DE_SHARPEN                  0x24
+#define QSEED3_DE_SHARPEN_CTL              0x28
+#define QSEED3_DE_SHAPE_CTL                0x2C
+#define QSEED3_DE_THRESHOLD                0x30
+#define QSEED3_DE_ADJUST_DATA_0            0x34
+#define QSEED3_DE_ADJUST_DATA_1            0x38
+#define QSEED3_DE_ADJUST_DATA_2            0x3C
+#define QSEED3_SRC_SIZE_Y_RGB_A            0x40
+#define QSEED3_SRC_SIZE_UV                 0x44
+#define QSEED3_DST_SIZE                    0x48
+#define QSEED3_COEF_LUT_CTRL               0x4C
+#define QSEED3_COEF_LUT_SWAP_BIT           0
+#define QSEED3_COEF_LUT_DIR_BIT            1
+#define QSEED3_COEF_LUT_Y_CIR_BIT          2
+#define QSEED3_COEF_LUT_UV_CIR_BIT         3
+#define QSEED3_COEF_LUT_Y_SEP_BIT          4
+#define QSEED3_COEF_LUT_UV_SEP_BIT         5
+#define QSEED3_BUFFER_CTRL                 0x50
+#define QSEED3_CLK_CTRL0                   0x54
+#define QSEED3_CLK_CTRL1                   0x58
+#define QSEED3_CLK_STATUS                  0x5C
+#define QSEED3_MISR_CTRL                   0x70
+#define QSEED3_MISR_SIGNATURE_0            0x74
+#define QSEED3_MISR_SIGNATURE_1            0x78
+#define QSEED3_PHASE_INIT_Y_H              0x90
+#define QSEED3_PHASE_INIT_Y_V              0x94
+#define QSEED3_PHASE_INIT_UV_H             0x98
+#define QSEED3_PHASE_INIT_UV_V             0x9C
+#define QSEED3_COEF_LUT                    0x100
+#define QSEED3_FILTERS                     5
+#define QSEED3_LUT_REGIONS                 4
+#define QSEED3_CIRCULAR_LUTS               9
+#define QSEED3_SEPARABLE_LUTS              10
+#define QSEED3_LUT_SIZE                    60
+#define QSEED3_ENABLE                      2
+#define QSEED3_DIR_LUT_SIZE                (200 * sizeof(u32))
+#define QSEED3_CIR_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_CIRCULAR_LUTS * sizeof(u32))
+#define QSEED3_SEP_LUT_SIZE \
+	(QSEED3_LUT_SIZE * QSEED3_SEPARABLE_LUTS * sizeof(u32))
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name)
+{
+	/* don't need to mutex protect this */
+	if (c->log_mask & dpu_hw_util_log_mask)
+		DPU_DEBUG_DRIVER("[%s:0x%X] <= 0x%X\n",
+				name, c->blk_off + reg_off, val);
+	writel_relaxed(val, c->base_off + c->blk_off + reg_off);
+}
+
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off)
+{
+	return readl_relaxed(c->base_off + c->blk_off + reg_off);
+}
+
+u32 *dpu_hw_util_get_log_mask_ptr(void)
+{
+	return &dpu_hw_util_log_mask;
+}
+
+void dpu_set_scaler_v2(struct dpu_hw_scaler3_cfg *cfg,
+		const struct dpu_drm_scaler_v2 *scale_v2)
+{
+	int i;
+
+	cfg->enable = scale_v2->enable;
+	cfg->dir_en = scale_v2->dir_en;
+
+	for (i = 0; i < DPU_MAX_PLANES; i++) {
+		cfg->init_phase_x[i] = scale_v2->init_phase_x[i];
+		cfg->phase_step_x[i] = scale_v2->phase_step_x[i];
+		cfg->init_phase_y[i] = scale_v2->init_phase_y[i];
+		cfg->phase_step_y[i] = scale_v2->phase_step_y[i];
+
+		cfg->preload_x[i] = scale_v2->preload_x[i];
+		cfg->preload_y[i] = scale_v2->preload_y[i];
+		cfg->src_width[i] = scale_v2->src_width[i];
+		cfg->src_height[i] = scale_v2->src_height[i];
+	}
+
+	cfg->dst_width = scale_v2->dst_width;
+	cfg->dst_height = scale_v2->dst_height;
+
+	cfg->y_rgb_filter_cfg = scale_v2->y_rgb_filter_cfg;
+	cfg->uv_filter_cfg = scale_v2->uv_filter_cfg;
+	cfg->alpha_filter_cfg = scale_v2->alpha_filter_cfg;
+	cfg->blend_cfg = scale_v2->blend_cfg;
+
+	cfg->lut_flag = scale_v2->lut_flag;
+	cfg->dir_lut_idx = scale_v2->dir_lut_idx;
+	cfg->y_rgb_cir_lut_idx = scale_v2->y_rgb_cir_lut_idx;
+	cfg->uv_cir_lut_idx = scale_v2->uv_cir_lut_idx;
+	cfg->y_rgb_sep_lut_idx = scale_v2->y_rgb_sep_lut_idx;
+	cfg->uv_sep_lut_idx = scale_v2->uv_sep_lut_idx;
+
+	cfg->de.enable = scale_v2->de.enable;
+	cfg->de.sharpen_level1 = scale_v2->de.sharpen_level1;
+	cfg->de.sharpen_level2 = scale_v2->de.sharpen_level2;
+	cfg->de.clip = scale_v2->de.clip;
+	cfg->de.limit = scale_v2->de.limit;
+	cfg->de.thr_quiet = scale_v2->de.thr_quiet;
+	cfg->de.thr_dieout = scale_v2->de.thr_dieout;
+	cfg->de.thr_low = scale_v2->de.thr_low;
+	cfg->de.thr_high = scale_v2->de.thr_high;
+	cfg->de.prec_shift = scale_v2->de.prec_shift;
+
+	for (i = 0; i < DPU_MAX_DE_CURVES; i++) {
+		cfg->de.adjust_a[i] = scale_v2->de.adjust_a[i];
+		cfg->de.adjust_b[i] = scale_v2->de.adjust_b[i];
+		cfg->de.adjust_c[i] = scale_v2->de.adjust_c[i];
+	}
+}
+
+static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset)
+{
+	int i, j, filter;
+	int config_lut = 0x0;
+	unsigned long lut_flags;
+	u32 lut_addr, lut_offset, lut_len;
+	u32 *lut[QSEED3_FILTERS] = {NULL, NULL, NULL, NULL, NULL};
+	static const uint32_t off_tbl[QSEED3_FILTERS][QSEED3_LUT_REGIONS][2] = {
+		{{18, 0x000}, {12, 0x120}, {12, 0x1E0}, {8, 0x2A0} },
+		{{6, 0x320}, {3, 0x3E0}, {3, 0x440}, {3, 0x4A0} },
+		{{6, 0x500}, {3, 0x5c0}, {3, 0x620}, {3, 0x680} },
+		{{6, 0x380}, {3, 0x410}, {3, 0x470}, {3, 0x4d0} },
+		{{6, 0x560}, {3, 0x5f0}, {3, 0x650}, {3, 0x6b0} },
+	};
+
+	lut_flags = (unsigned long) scaler3_cfg->lut_flag;
+	if (test_bit(QSEED3_COEF_LUT_DIR_BIT, &lut_flags) &&
+		(scaler3_cfg->dir_len == QSEED3_DIR_LUT_SIZE)) {
+		lut[0] = scaler3_cfg->dir_lut;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[1] = scaler3_cfg->cir_lut +
+			scaler3_cfg->y_rgb_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_CIR_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_cir_lut_idx < QSEED3_CIRCULAR_LUTS) &&
+		(scaler3_cfg->cir_len == QSEED3_CIR_LUT_SIZE)) {
+		lut[2] = scaler3_cfg->cir_lut +
+			scaler3_cfg->uv_cir_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_Y_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->y_rgb_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[3] = scaler3_cfg->sep_lut +
+			scaler3_cfg->y_rgb_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+	if (test_bit(QSEED3_COEF_LUT_UV_SEP_BIT, &lut_flags) &&
+		(scaler3_cfg->uv_sep_lut_idx < QSEED3_SEPARABLE_LUTS) &&
+		(scaler3_cfg->sep_len == QSEED3_SEP_LUT_SIZE)) {
+		lut[4] = scaler3_cfg->sep_lut +
+			scaler3_cfg->uv_sep_lut_idx * QSEED3_LUT_SIZE;
+		config_lut = 1;
+	}
+
+	if (config_lut) {
+		for (filter = 0; filter < QSEED3_FILTERS; filter++) {
+			if (!lut[filter])
+				continue;
+			lut_offset = 0;
+			for (i = 0; i < QSEED3_LUT_REGIONS; i++) {
+				lut_addr = QSEED3_COEF_LUT + offset
+					+ off_tbl[filter][i][1];
+				lut_len = off_tbl[filter][i][0] << 2;
+				for (j = 0; j < lut_len; j++) {
+					DPU_REG_WRITE(c,
+						lut_addr,
+						(lut[filter])[lut_offset++]);
+					lut_addr += 4;
+				}
+			}
+		}
+	}
+
+	if (test_bit(QSEED3_COEF_LUT_SWAP_BIT, &lut_flags))
+		DPU_REG_WRITE(c, QSEED3_COEF_LUT_CTRL + offset, BIT(0));
+
+}
+
+static void _dpu_hw_setup_scaler3_de(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_de_cfg *de_cfg, u32 offset)
+{
+	u32 sharp_lvl, sharp_ctl, shape_ctl, de_thr;
+	u32 adjust_a, adjust_b, adjust_c;
+
+	if (!de_cfg->enable)
+		return;
+
+	sharp_lvl = (de_cfg->sharpen_level1 & 0x1FF) |
+		((de_cfg->sharpen_level2 & 0x1FF) << 16);
+
+	sharp_ctl = ((de_cfg->limit & 0xF) << 9) |
+		((de_cfg->prec_shift & 0x7) << 13) |
+		((de_cfg->clip & 0x7) << 16);
+
+	shape_ctl = (de_cfg->thr_quiet & 0xFF) |
+		((de_cfg->thr_dieout & 0x3FF) << 16);
+
+	de_thr = (de_cfg->thr_low & 0x3FF) |
+		((de_cfg->thr_high & 0x3FF) << 16);
+
+	adjust_a = (de_cfg->adjust_a[0] & 0x3FF) |
+		((de_cfg->adjust_a[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_a[2] & 0x3FF) << 20);
+
+	adjust_b = (de_cfg->adjust_b[0] & 0x3FF) |
+		((de_cfg->adjust_b[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_b[2] & 0x3FF) << 20);
+
+	adjust_c = (de_cfg->adjust_c[0] & 0x3FF) |
+		((de_cfg->adjust_c[1] & 0x3FF) << 10) |
+		((de_cfg->adjust_c[2] & 0x3FF) << 20);
+
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN + offset, sharp_lvl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHARPEN_CTL + offset, sharp_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_SHAPE_CTL + offset, shape_ctl);
+	DPU_REG_WRITE(c, QSEED3_DE_THRESHOLD + offset, de_thr);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_0 + offset, adjust_a);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_1 + offset, adjust_b);
+	DPU_REG_WRITE(c, QSEED3_DE_ADJUST_DATA_2 + offset, adjust_c);
+
+}
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format)
+{
+	u32 op_mode = 0;
+	u32 phase_init, preload, src_y_rgb, src_uv, dst;
+
+	if (!scaler3_cfg->enable)
+		goto end;
+
+	op_mode |= BIT(0);
+	op_mode |= (scaler3_cfg->y_rgb_filter_cfg & 0x3) << 16;
+
+	if (format && DPU_FORMAT_IS_YUV(format)) {
+		op_mode |= BIT(12);
+		op_mode |= (scaler3_cfg->uv_filter_cfg & 0x3) << 24;
+	}
+
+	op_mode |= (scaler3_cfg->blend_cfg & 1) << 31;
+	op_mode |= (scaler3_cfg->dir_en) ? BIT(4) : 0;
+
+	preload =
+		((scaler3_cfg->preload_x[0] & 0x7F) << 0) |
+		((scaler3_cfg->preload_y[0] & 0x7F) << 8) |
+		((scaler3_cfg->preload_x[1] & 0x7F) << 16) |
+		((scaler3_cfg->preload_y[1] & 0x7F) << 24);
+
+	src_y_rgb = (scaler3_cfg->src_width[0] & 0x1FFFF) |
+		((scaler3_cfg->src_height[0] & 0x1FFFF) << 16);
+
+	src_uv = (scaler3_cfg->src_width[1] & 0x1FFFF) |
+		((scaler3_cfg->src_height[1] & 0x1FFFF) << 16);
+
+	dst = (scaler3_cfg->dst_width & 0x1FFFF) |
+		((scaler3_cfg->dst_height & 0x1FFFF) << 16);
+
+	if (scaler3_cfg->de.enable) {
+		_dpu_hw_setup_scaler3_de(c, &scaler3_cfg->de, scaler_offset);
+		op_mode |= BIT(8);
+	}
+
+	if (scaler3_cfg->lut_flag)
+		_dpu_hw_setup_scaler3_lut(c, scaler3_cfg,
+								scaler_offset);
+
+	if (scaler_version == 0x1002) {
+		phase_init =
+			((scaler3_cfg->init_phase_x[0] & 0x3F) << 0) |
+			((scaler3_cfg->init_phase_y[0] & 0x3F) << 8) |
+			((scaler3_cfg->init_phase_x[1] & 0x3F) << 16) |
+			((scaler3_cfg->init_phase_y[1] & 0x3F) << 24);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT + scaler_offset, phase_init);
+	} else {
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_H + scaler_offset,
+			scaler3_cfg->init_phase_x[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_Y_V + scaler_offset,
+			scaler3_cfg->init_phase_y[0] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_H + scaler_offset,
+			scaler3_cfg->init_phase_x[1] & 0x1FFFFF);
+		DPU_REG_WRITE(c, QSEED3_PHASE_INIT_UV_V + scaler_offset,
+			scaler3_cfg->init_phase_y[1] & 0x1FFFFF);
+	}
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_H + scaler_offset,
+		scaler3_cfg->phase_step_x[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_Y_V + scaler_offset,
+		scaler3_cfg->phase_step_y[0] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_H + scaler_offset,
+		scaler3_cfg->phase_step_x[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PHASE_STEP_UV_V + scaler_offset,
+		scaler3_cfg->phase_step_y[1] & 0xFFFFFF);
+
+	DPU_REG_WRITE(c, QSEED3_PRELOAD + scaler_offset, preload);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_Y_RGB_A + scaler_offset, src_y_rgb);
+
+	DPU_REG_WRITE(c, QSEED3_SRC_SIZE_UV + scaler_offset, src_uv);
+
+	DPU_REG_WRITE(c, QSEED3_DST_SIZE + scaler_offset, dst);
+
+end:
+	if (format && !DPU_FORMAT_IS_DX(format))
+		op_mode |= BIT(14);
+
+	if (format && format->alpha_enable) {
+		op_mode |= BIT(10);
+		if (scaler_version == 0x1002)
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x1) << 30;
+		else
+			op_mode |= (scaler3_cfg->alpha_filter_cfg & 0x3) << 29;
+	}
+
+	DPU_REG_WRITE(c, QSEED3_OP_MODE + scaler_offset, op_mode);
+}
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+			u32 scaler_offset)
+{
+	return DPU_REG_READ(c, QSEED3_HW_VERSION + scaler_offset);
+}
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map *c,
+		u32 csc_reg_off,
+		struct dpu_csc_cfg *data, bool csc10)
+{
+	static const u32 matrix_shift = 7;
+	u32 clamp_shift = csc10 ? 16 : 8;
+	u32 val;
+
+	/* matrix coeff - convert S15.16 to S4.9 */
+	val = ((data->csc_mv[0] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[1] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off, val);
+	val = ((data->csc_mv[2] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[3] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x4, val);
+	val = ((data->csc_mv[4] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[5] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0x8, val);
+	val = ((data->csc_mv[6] >> matrix_shift) & 0x1FFF) |
+		(((data->csc_mv[7] >> matrix_shift) & 0x1FFF) << 16);
+	DPU_REG_WRITE(c, csc_reg_off + 0xc, val);
+	val = (data->csc_mv[8] >> matrix_shift) & 0x1FFF;
+	DPU_REG_WRITE(c, csc_reg_off + 0x10, val);
+
+	/* Pre clamp */
+	val = (data->csc_pre_lv[0] << clamp_shift) | data->csc_pre_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x14, val);
+	val = (data->csc_pre_lv[2] << clamp_shift) | data->csc_pre_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x18, val);
+	val = (data->csc_pre_lv[4] << clamp_shift) | data->csc_pre_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x1c, val);
+
+	/* Post clamp */
+	val = (data->csc_post_lv[0] << clamp_shift) | data->csc_post_lv[1];
+	DPU_REG_WRITE(c, csc_reg_off + 0x20, val);
+	val = (data->csc_post_lv[2] << clamp_shift) | data->csc_post_lv[3];
+	DPU_REG_WRITE(c, csc_reg_off + 0x24, val);
+	val = (data->csc_post_lv[4] << clamp_shift) | data->csc_post_lv[5];
+	DPU_REG_WRITE(c, csc_reg_off + 0x28, val);
+
+	/* Pre-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x2c, data->csc_pre_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x30, data->csc_pre_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x34, data->csc_pre_bv[2]);
+
+	/* Post-Bias */
+	DPU_REG_WRITE(c, csc_reg_off + 0x38, data->csc_post_bv[0]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x3c, data->csc_post_bv[1]);
+	DPU_REG_WRITE(c, csc_reg_off + 0x40, data->csc_post_bv[2]);
+}
+
+/**
+ * _dpu_copy_formats   - copy formats from src_list to dst_list
+ * @dst_list:          pointer to destination list where to copy formats
+ * @dst_list_size:     size of destination list
+ * @dst_list_pos:      starting position on the list where to copy formats
+ * @src_list:          pointer to source list where to copy formats from
+ * @src_list_size:     size of source list
+ * Return: number of elements populated
+ */
+uint32_t dpu_copy_formats(
+		struct dpu_format_extended *dst_list,
+		uint32_t dst_list_size,
+		uint32_t dst_list_pos,
+		const struct dpu_format_extended *src_list,
+		uint32_t src_list_size)
+{
+	uint32_t cur_pos, i;
+
+	if (!dst_list || !src_list || (dst_list_pos >= (dst_list_size - 1)))
+		return 0;
+
+	for (i = 0, cur_pos = dst_list_pos;
+		(cur_pos < (dst_list_size - 1)) && (i < src_list_size)
+		&& src_list[i].fourcc_format; ++i, ++cur_pos)
+		dst_list[cur_pos] = src_list[i];
+
+	dst_list[cur_pos].fourcc_format = 0;
+
+	return i;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
new file mode 100644
index 000000000000..42f1b228d342
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
@@ -0,0 +1,358 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_UTIL_H
+#define _DPU_HW_UTIL_H
+
+#include <linux/io.h>
+#include <linux/slab.h>
+#include "dpu_hw_mdss.h"
+
+#define REG_MASK(n)                     ((BIT(n)) - 1)
+struct dpu_format_extended;
+
+/*
+ * This is the common struct maintained by each sub block
+ * for mapping the register offsets in this block to the
+ * absoulute IO address
+ * @base_off:     mdp register mapped offset
+ * @blk_off:      pipe offset relative to mdss offset
+ * @length        length of register block offset
+ * @xin_id        xin id
+ * @hwversion     mdss hw version number
+ */
+struct dpu_hw_blk_reg_map {
+	void __iomem *base_off;
+	u32 blk_off;
+	u32 length;
+	u32 xin_id;
+	u32 hwversion;
+	u32 log_mask;
+};
+
+/**
+ * struct dpu_hw_scaler3_de_cfg : QSEEDv3 detail enhancer configuration
+ * @enable:         detail enhancer enable/disable
+ * @sharpen_level1: sharpening strength for noise
+ * @sharpen_level2: sharpening strength for signal
+ * @ clip:          clip shift
+ * @ limit:         limit value
+ * @ thr_quiet:     quiet threshold
+ * @ thr_dieout:    dieout threshold
+ * @ thr_high:      low threshold
+ * @ thr_high:      high threshold
+ * @ prec_shift:    precision shift
+ * @ adjust_a:      A-coefficients for mapping curve
+ * @ adjust_b:      B-coefficients for mapping curve
+ * @ adjust_c:      C-coefficients for mapping curve
+ */
+struct dpu_hw_scaler3_de_cfg {
+	u32 enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+
+/**
+ * struct dpu_hw_scaler3_cfg : QSEEDv3 configuration
+ * @enable:        scaler enable
+ * @dir_en:        direction detection block enable
+ * @ init_phase_x: horizontal initial phase
+ * @ phase_step_x: horizontal phase step
+ * @ init_phase_y: vertical initial phase
+ * @ phase_step_y: vertical phase step
+ * @ preload_x:    horizontal preload value
+ * @ preload_y:    vertical preload value
+ * @ src_width:    source width
+ * @ src_height:   source height
+ * @ dst_width:    destination width
+ * @ dst_height:   destination height
+ * @ y_rgb_filter_cfg: y/rgb plane filter configuration
+ * @ uv_filter_cfg: uv plane filter configuration
+ * @ alpha_filter_cfg: alpha filter configuration
+ * @ blend_cfg:    blend coefficients configuration
+ * @ lut_flag:     scaler LUT update flags
+ *                 0x1 swap LUT bank
+ *                 0x2 update 2D filter LUT
+ *                 0x4 update y circular filter LUT
+ *                 0x8 update uv circular filter LUT
+ *                 0x10 update y separable filter LUT
+ *                 0x20 update uv separable filter LUT
+ * @ dir_lut_idx:  2D filter LUT index
+ * @ y_rgb_cir_lut_idx: y circular filter LUT index
+ * @ uv_cir_lut_idx: uv circular filter LUT index
+ * @ y_rgb_sep_lut_idx: y circular filter LUT index
+ * @ uv_sep_lut_idx: uv separable filter LUT index
+ * @ dir_lut:      pointer to 2D LUT
+ * @ cir_lut:      pointer to circular filter LUT
+ * @ sep_lut:      pointer to separable filter LUT
+ * @ de: detail enhancer configuration
+ */
+struct dpu_hw_scaler3_cfg {
+	u32 enable;
+	u32 dir_en;
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	u32 preload_x[DPU_MAX_PLANES];
+	u32 preload_y[DPU_MAX_PLANES];
+	u32 src_width[DPU_MAX_PLANES];
+	u32 src_height[DPU_MAX_PLANES];
+
+	u32 dst_width;
+	u32 dst_height;
+
+	u32 y_rgb_filter_cfg;
+	u32 uv_filter_cfg;
+	u32 alpha_filter_cfg;
+	u32 blend_cfg;
+
+	u32 lut_flag;
+	u32 dir_lut_idx;
+
+	u32 y_rgb_cir_lut_idx;
+	u32 uv_cir_lut_idx;
+	u32 y_rgb_sep_lut_idx;
+	u32 uv_sep_lut_idx;
+	u32 *dir_lut;
+	size_t dir_len;
+	u32 *cir_lut;
+	size_t cir_len;
+	u32 *sep_lut;
+	size_t sep_len;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_hw_scaler3_de_cfg de;
+};
+
+struct dpu_hw_scaler3_lut_cfg {
+	bool is_configured;
+	u32 *dir_lut;
+	size_t dir_len;
+	u32 *cir_lut;
+	size_t cir_len;
+	u32 *sep_lut;
+	size_t sep_len;
+};
+
+/**
+ * struct dpu_drm_pix_ext_v1 - version 1 of pixel ext structure
+ * @num_ext_pxls_lr: Number of total horizontal pixels
+ * @num_ext_pxls_tb: Number of total vertical lines
+ * @left_ftch:       Number of extra pixels to overfetch from left
+ * @right_ftch:      Number of extra pixels to overfetch from right
+ * @top_ftch:        Number of extra lines to overfetch from top
+ * @btm_ftch:        Number of extra lines to overfetch from bottom
+ * @left_rpt:        Number of extra pixels to repeat from left
+ * @right_rpt:       Number of extra pixels to repeat from right
+ * @top_rpt:         Number of extra lines to repeat from top
+ * @btm_rpt:         Number of extra lines to repeat from bottom
+ */
+struct dpu_drm_pix_ext_v1 {
+	/*
+	 * Number of pixels ext in left, right, top and bottom direction
+	 * for all color components.
+	 */
+	int32_t num_ext_pxls_lr[DPU_MAX_PLANES];
+	int32_t num_ext_pxls_tb[DPU_MAX_PLANES];
+
+	/*
+	 * Number of pixels needs to be overfetched in left, right, top
+	 * and bottom directions from source image for scaling.
+	 */
+	int32_t left_ftch[DPU_MAX_PLANES];
+	int32_t right_ftch[DPU_MAX_PLANES];
+	int32_t top_ftch[DPU_MAX_PLANES];
+	int32_t btm_ftch[DPU_MAX_PLANES];
+	/*
+	 * Number of pixels needs to be repeated in left, right, top and
+	 * bottom directions for scaling.
+	 */
+	int32_t left_rpt[DPU_MAX_PLANES];
+	int32_t right_rpt[DPU_MAX_PLANES];
+	int32_t top_rpt[DPU_MAX_PLANES];
+	int32_t btm_rpt[DPU_MAX_PLANES];
+
+};
+
+/**
+ * struct dpu_drm_de_v1 - version 1 of detail enhancer structure
+ * @enable:         Enables/disables detail enhancer
+ * @sharpen_level1: Sharpening strength for noise
+ * @sharpen_level2: Sharpening strength for context
+ * @clip:           Clip coefficient
+ * @limit:          Detail enhancer limit factor
+ * @thr_quiet:      Quite zone threshold
+ * @thr_dieout:     Die-out zone threshold
+ * @thr_low:        Linear zone left threshold
+ * @thr_high:       Linear zone right threshold
+ * @prec_shift:     Detail enhancer precision
+ * @adjust_a:       Mapping curves A coefficients
+ * @adjust_b:       Mapping curves B coefficients
+ * @adjust_c:       Mapping curves C coefficients
+ */
+struct dpu_drm_de_v1 {
+	uint32_t enable;
+	int16_t sharpen_level1;
+	int16_t sharpen_level2;
+	uint16_t clip;
+	uint16_t limit;
+	uint16_t thr_quiet;
+	uint16_t thr_dieout;
+	uint16_t thr_low;
+	uint16_t thr_high;
+	uint16_t prec_shift;
+	int16_t adjust_a[DPU_MAX_DE_CURVES];
+	int16_t adjust_b[DPU_MAX_DE_CURVES];
+	int16_t adjust_c[DPU_MAX_DE_CURVES];
+};
+
+/**
+ * struct dpu_drm_scaler_v2 - version 2 of struct dpu_drm_scaler
+ * @enable:            Scaler enable
+ * @dir_en:            Detail enhancer enable
+ * @pe:                Pixel extension settings
+ * @horz_decimate:     Horizontal decimation factor
+ * @vert_decimate:     Vertical decimation factor
+ * @init_phase_x:      Initial scaler phase values for x
+ * @phase_step_x:      Phase step values for x
+ * @init_phase_y:      Initial scaler phase values for y
+ * @phase_step_y:      Phase step values for y
+ * @preload_x:         Horizontal preload value
+ * @preload_y:         Vertical preload value
+ * @src_width:         Source width
+ * @src_height:        Source height
+ * @dst_width:         Destination width
+ * @dst_height:        Destination height
+ * @y_rgb_filter_cfg:  Y/RGB plane filter configuration
+ * @uv_filter_cfg:     UV plane filter configuration
+ * @alpha_filter_cfg:  Alpha filter configuration
+ * @blend_cfg:         Selection of blend coefficients
+ * @lut_flag:          LUT configuration flags
+ * @dir_lut_idx:       2d 4x4 LUT index
+ * @y_rgb_cir_lut_idx: Y/RGB circular LUT index
+ * @uv_cir_lut_idx:    UV circular LUT index
+ * @y_rgb_sep_lut_idx: Y/RGB separable LUT index
+ * @uv_sep_lut_idx:    UV separable LUT index
+ * @de:                Detail enhancer settings
+ */
+struct dpu_drm_scaler_v2 {
+	/*
+	 * General definitions
+	 */
+	uint32_t enable;
+	uint32_t dir_en;
+
+	/*
+	 * Pix ext settings
+	 */
+	struct dpu_drm_pix_ext_v1 pe;
+
+	/*
+	 * Decimation settings
+	 */
+	uint32_t horz_decimate;
+	uint32_t vert_decimate;
+
+	/*
+	 * Phase settings
+	 */
+	int32_t init_phase_x[DPU_MAX_PLANES];
+	int32_t phase_step_x[DPU_MAX_PLANES];
+	int32_t init_phase_y[DPU_MAX_PLANES];
+	int32_t phase_step_y[DPU_MAX_PLANES];
+
+	uint32_t preload_x[DPU_MAX_PLANES];
+	uint32_t preload_y[DPU_MAX_PLANES];
+	uint32_t src_width[DPU_MAX_PLANES];
+	uint32_t src_height[DPU_MAX_PLANES];
+
+	uint32_t dst_width;
+	uint32_t dst_height;
+
+	uint32_t y_rgb_filter_cfg;
+	uint32_t uv_filter_cfg;
+	uint32_t alpha_filter_cfg;
+	uint32_t blend_cfg;
+
+	uint32_t lut_flag;
+	uint32_t dir_lut_idx;
+
+	/* for Y(RGB) and UV planes*/
+	uint32_t y_rgb_cir_lut_idx;
+	uint32_t uv_cir_lut_idx;
+	uint32_t y_rgb_sep_lut_idx;
+	uint32_t uv_sep_lut_idx;
+
+	/*
+	 * Detail enhancer settings
+	 */
+	struct dpu_drm_de_v1 de;
+};
+
+
+u32 *dpu_hw_util_get_log_mask_ptr(void);
+
+void dpu_reg_write(struct dpu_hw_blk_reg_map *c,
+		u32 reg_off,
+		u32 val,
+		const char *name);
+int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off);
+
+#define DPU_REG_WRITE(c, off, val) dpu_reg_write(c, off, val, #off)
+#define DPU_REG_READ(c, off) dpu_reg_read(c, off)
+
+#define MISR_FRAME_COUNT_MASK		0xFF
+#define MISR_CTRL_ENABLE		BIT(8)
+#define MISR_CTRL_STATUS		BIT(9)
+#define MISR_CTRL_STATUS_CLEAR		BIT(10)
+#define INTF_MISR_CTRL_FREE_RUN_MASK	BIT(31)
+
+void *dpu_hw_util_get_dir(void);
+
+void dpu_set_scaler_v2(struct dpu_hw_scaler3_cfg *cfg,
+		const struct dpu_drm_scaler_v2 *scale_v2);
+
+void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
+		struct dpu_hw_scaler3_cfg *scaler3_cfg,
+		u32 scaler_offset, u32 scaler_version,
+		const struct dpu_format *format);
+
+u32 dpu_hw_get_scaler3_ver(struct dpu_hw_blk_reg_map *c,
+		u32 scaler_offset);
+
+void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map  *c,
+		u32 csc_reg_off,
+		struct dpu_csc_cfg *data, bool csc10);
+
+uint32_t dpu_copy_formats(
+		struct dpu_format_extended *dst_list,
+		uint32_t dst_list_size,
+		uint32_t dst_list_pos,
+		const struct dpu_format_extended *src_list,
+		uint32_t src_list_size);
+
+#endif /* _DPU_HW_UTIL_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
new file mode 100644
index 000000000000..d43905525f92
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.c
@@ -0,0 +1,275 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "dpu_hwio.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_dbg.h"
+
+#define VBIF_VERSION			0x0000
+#define VBIF_CLK_FORCE_CTRL0		0x0008
+#define VBIF_CLK_FORCE_CTRL1		0x000C
+#define VBIF_QOS_REMAP_00		0x0020
+#define VBIF_QOS_REMAP_01		0x0024
+#define VBIF_QOS_REMAP_10		0x0028
+#define VBIF_QOS_REMAP_11		0x002C
+#define VBIF_WRITE_GATHER_EN		0x00AC
+#define VBIF_IN_RD_LIM_CONF0		0x00B0
+#define VBIF_IN_RD_LIM_CONF1		0x00B4
+#define VBIF_IN_RD_LIM_CONF2		0x00B8
+#define VBIF_IN_WR_LIM_CONF0		0x00C0
+#define VBIF_IN_WR_LIM_CONF1		0x00C4
+#define VBIF_IN_WR_LIM_CONF2		0x00C8
+#define VBIF_OUT_RD_LIM_CONF0		0x00D0
+#define VBIF_OUT_WR_LIM_CONF0		0x00D4
+#define VBIF_OUT_AXI_AMEMTYPE_CONF0	0x0160
+#define VBIF_OUT_AXI_AMEMTYPE_CONF1	0x0164
+#define VBIF_XIN_PND_ERR		0x0190
+#define VBIF_XIN_SRC_ERR		0x0194
+#define VBIF_XIN_CLR_ERR		0x019C
+#define VBIF_XIN_HALT_CTRL0		0x0200
+#define VBIF_XIN_HALT_CTRL1		0x0204
+#define VBIF_XINL_QOS_RP_REMAP_000	0x0550
+#define VBIF_XINL_QOS_LVL_REMAP_000	0x0590
+
+static void dpu_hw_clear_errors(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 pnd, src;
+
+	if (!vbif)
+		return;
+	c = &vbif->hw;
+	pnd = DPU_REG_READ(c, VBIF_XIN_PND_ERR);
+	src = DPU_REG_READ(c, VBIF_XIN_SRC_ERR);
+
+	if (pnd_errors)
+		*pnd_errors = pnd;
+	if (src_errors)
+		*src_errors = src;
+
+	DPU_REG_WRITE(c, VBIF_XIN_CLR_ERR, pnd | src);
+}
+
+static void dpu_hw_set_mem_type(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 value)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_off;
+	u32 bit_off;
+	u32 reg_val;
+
+	/*
+	 * Assume 4 bits per bit field, 8 fields per 32-bit register so
+	 * 16 bit fields maximum across two registers
+	 */
+	if (!vbif || xin_id >= MAX_XIN_COUNT || xin_id >= 16)
+		return;
+
+	c = &vbif->hw;
+
+	if (xin_id >= 8) {
+		xin_id -= 8;
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF1;
+	} else {
+		reg_off = VBIF_OUT_AXI_AMEMTYPE_CONF0;
+	}
+	bit_off = (xin_id & 0x7) * 4;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0x7 << bit_off);
+	reg_val |= (value & 0x7) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static void dpu_hw_set_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd, u32 limit)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	reg_val &= ~(0xFF << bit_off);
+	reg_val |= (limit) << bit_off;
+	DPU_REG_WRITE(c, reg_off, reg_val);
+}
+
+static u32 dpu_hw_get_limit_conf(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool rd)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+	u32 reg_off;
+	u32 bit_off;
+	u32 limit;
+
+	if (rd)
+		reg_off = VBIF_IN_RD_LIM_CONF0;
+	else
+		reg_off = VBIF_IN_WR_LIM_CONF0;
+
+	reg_off += (xin_id / 4) * 4;
+	bit_off = (xin_id % 4) * 8;
+	reg_val = DPU_REG_READ(c, reg_off);
+	limit = (reg_val >> bit_off) & 0xFF;
+
+	return limit;
+}
+
+static void dpu_hw_set_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id, bool enable)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL0);
+
+	if (enable)
+		reg_val |= BIT(xin_id);
+	else
+		reg_val &= ~BIT(xin_id);
+
+	DPU_REG_WRITE(c, VBIF_XIN_HALT_CTRL0, reg_val);
+}
+
+static bool dpu_hw_get_halt_ctrl(struct dpu_hw_vbif *vbif,
+		u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c = &vbif->hw;
+	u32 reg_val;
+
+	reg_val = DPU_REG_READ(c, VBIF_XIN_HALT_CTRL1);
+
+	return (reg_val & BIT(xin_id)) ? true : false;
+}
+
+static void dpu_hw_set_qos_remap(struct dpu_hw_vbif *vbif,
+		u32 xin_id, u32 level, u32 remap_level)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_val, reg_val_lvl, mask, reg_high, reg_shift;
+
+	if (!vbif)
+		return;
+
+	c = &vbif->hw;
+
+	reg_high = ((xin_id & 0x8) >> 3) * 4 + (level * 8);
+	reg_shift = (xin_id & 0x7) * 4;
+
+	reg_val = DPU_REG_READ(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high);
+	reg_val_lvl = DPU_REG_READ(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high);
+
+	mask = 0x7 << reg_shift;
+
+	reg_val &= ~mask;
+	reg_val |= (remap_level << reg_shift) & mask;
+
+	reg_val_lvl &= ~mask;
+	reg_val_lvl |= (remap_level << reg_shift) & mask;
+
+	DPU_REG_WRITE(c, VBIF_XINL_QOS_RP_REMAP_000 + reg_high, reg_val);
+	DPU_REG_WRITE(c, VBIF_XINL_QOS_LVL_REMAP_000 + reg_high, reg_val_lvl);
+}
+
+static void dpu_hw_set_write_gather_en(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	struct dpu_hw_blk_reg_map *c;
+	u32 reg_val;
+
+	if (!vbif || xin_id >= MAX_XIN_COUNT)
+		return;
+
+	c = &vbif->hw;
+
+	reg_val = DPU_REG_READ(c, VBIF_WRITE_GATHER_EN);
+	reg_val |= BIT(xin_id);
+	DPU_REG_WRITE(c, VBIF_WRITE_GATHER_EN, reg_val);
+}
+
+static void _setup_vbif_ops(struct dpu_hw_vbif_ops *ops,
+		unsigned long cap)
+{
+	ops->set_limit_conf = dpu_hw_set_limit_conf;
+	ops->get_limit_conf = dpu_hw_get_limit_conf;
+	ops->set_halt_ctrl = dpu_hw_set_halt_ctrl;
+	ops->get_halt_ctrl = dpu_hw_get_halt_ctrl;
+	if (test_bit(DPU_VBIF_QOS_REMAP, &cap))
+		ops->set_qos_remap = dpu_hw_set_qos_remap;
+	ops->set_mem_type = dpu_hw_set_mem_type;
+	ops->clear_errors = dpu_hw_clear_errors;
+	ops->set_write_gather_en = dpu_hw_set_write_gather_en;
+}
+
+static const struct dpu_vbif_cfg *_top_offset(enum dpu_vbif vbif,
+		const struct dpu_mdss_cfg *m,
+		void __iomem *addr,
+		struct dpu_hw_blk_reg_map *b)
+{
+	int i;
+
+	for (i = 0; i < m->vbif_count; i++) {
+		if (vbif == m->vbif[i].id) {
+			b->base_off = addr;
+			b->blk_off = m->vbif[i].base;
+			b->length = m->vbif[i].len;
+			b->hwversion = m->hwversion;
+			b->log_mask = DPU_DBG_MASK_VBIF;
+			return &m->vbif[i];
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m)
+{
+	struct dpu_hw_vbif *c;
+	const struct dpu_vbif_cfg *cfg;
+
+	c = kzalloc(sizeof(*c), GFP_KERNEL);
+	if (!c)
+		return ERR_PTR(-ENOMEM);
+
+	cfg = _top_offset(idx, m, addr, &c->hw);
+	if (IS_ERR_OR_NULL(cfg)) {
+		kfree(c);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/*
+	 * Assign ops
+	 */
+	c->idx = idx;
+	c->cap = cfg;
+	_setup_vbif_ops(&c->ops, c->cap->features);
+
+	/* no need to register sub-range in dpu dbg, dump entire vbif io base */
+
+	return c;
+}
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif)
+{
+	kfree(vbif);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
new file mode 100644
index 000000000000..471ff673c045
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_vbif.h
@@ -0,0 +1,128 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HW_VBIF_H
+#define _DPU_HW_VBIF_H
+
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_util.h"
+
+struct dpu_hw_vbif;
+
+/**
+ * struct dpu_hw_vbif_ops : Interface to the VBIF hardware driver functions
+ *  Assumption is these functions will be called after clocks are enabled
+ */
+struct dpu_hw_vbif_ops {
+	/**
+	 * set_limit_conf - set transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @limit: outstanding transaction limit
+	 */
+	void (*set_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd, u32 limit);
+
+	/**
+	 * get_limit_conf - get transaction limit config
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @rd: true for read limit; false for write limit
+	 * @return: outstanding transaction limit
+	 */
+	u32 (*get_limit_conf)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool rd);
+
+	/**
+	 * set_halt_ctrl - set halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @enable: halt control enable
+	 */
+	void (*set_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, bool enable);
+
+	/**
+	 * get_halt_ctrl - get halt control
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @return: halt control enable
+	 */
+	bool (*get_halt_ctrl)(struct dpu_hw_vbif *vbif,
+			u32 xin_id);
+
+	/**
+	 * set_qos_remap - set QoS priority remap
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @level: priority level
+	 * @remap_level: remapped level
+	 */
+	void (*set_qos_remap)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 level, u32 remap_level);
+
+	/**
+	 * set_mem_type - set memory type
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 * @value: memory type value
+	 */
+	void (*set_mem_type)(struct dpu_hw_vbif *vbif,
+			u32 xin_id, u32 value);
+
+	/**
+	 * clear_errors - clear any vbif errors
+	 *	This function clears any detected pending/source errors
+	 *	on the VBIF interface, and optionally returns the detected
+	 *	error mask(s).
+	 * @vbif: vbif context driver
+	 * @pnd_errors: pointer to pending error reporting variable
+	 * @src_errors: pointer to source error reporting variable
+	 */
+	void (*clear_errors)(struct dpu_hw_vbif *vbif,
+		u32 *pnd_errors, u32 *src_errors);
+
+	/**
+	 * set_write_gather_en - set write_gather enable
+	 * @vbif: vbif context driver
+	 * @xin_id: client interface identifier
+	 */
+	void (*set_write_gather_en)(struct dpu_hw_vbif *vbif, u32 xin_id);
+};
+
+struct dpu_hw_vbif {
+	/* base */
+	struct dpu_hw_blk_reg_map hw;
+
+	/* vbif */
+	enum dpu_vbif idx;
+	const struct dpu_vbif_cfg *cap;
+
+	/* ops */
+	struct dpu_hw_vbif_ops ops;
+};
+
+/**
+ * dpu_hw_vbif_init - initializes the vbif driver for the passed interface idx
+ * @idx:  Interface index for which driver object is required
+ * @addr: Mapped register io address of MDSS
+ * @m:    Pointer to mdss catalog data
+ */
+struct dpu_hw_vbif *dpu_hw_vbif_init(enum dpu_vbif idx,
+		void __iomem *addr,
+		const struct dpu_mdss_cfg *m);
+
+void dpu_hw_vbif_destroy(struct dpu_hw_vbif *vbif);
+
+#endif /*_DPU_HW_VBIF_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
new file mode 100644
index 000000000000..5b2bc9b65b15
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hwio.h
@@ -0,0 +1,56 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef _DPU_HWIO_H
+#define _DPU_HWIO_H
+
+#include "dpu_hw_util.h"
+
+/**
+ * MDP TOP block Register and bit fields and defines
+ */
+#define DISP_INTF_SEL                   0x004
+#define INTR_EN                         0x010
+#define INTR_STATUS                     0x014
+#define INTR_CLEAR                      0x018
+#define INTR2_EN                        0x008
+#define INTR2_STATUS                    0x00c
+#define INTR2_CLEAR                     0x02c
+#define HIST_INTR_EN                    0x01c
+#define HIST_INTR_STATUS                0x020
+#define HIST_INTR_CLEAR                 0x024
+#define INTF_INTR_EN                    0x1C0
+#define INTF_INTR_STATUS                0x1C4
+#define INTF_INTR_CLEAR                 0x1C8
+#define SPLIT_DISPLAY_EN                0x2F4
+#define SPLIT_DISPLAY_UPPER_PIPE_CTRL   0x2F8
+#define DSPP_IGC_COLOR0_RAM_LUTN        0x300
+#define DSPP_IGC_COLOR1_RAM_LUTN        0x304
+#define DSPP_IGC_COLOR2_RAM_LUTN        0x308
+#define HW_EVENTS_CTL                   0x37C
+#define CLK_CTRL3                       0x3A8
+#define CLK_STATUS3                     0x3AC
+#define CLK_CTRL4                       0x3B0
+#define CLK_STATUS4                     0x3B4
+#define CLK_CTRL5                       0x3B8
+#define CLK_STATUS5                     0x3BC
+#define CLK_CTRL7                       0x3D0
+#define CLK_STATUS7                     0x3D4
+#define SPLIT_DISPLAY_LOWER_PIPE_CTRL   0x3F0
+#define SPLIT_DISPLAY_TE_LINE_INTERVAL  0x3F4
+#define INTF_SW_RESET_MASK              0x3FC
+#define HDMI_DP_CORE_SELECT             0x408
+#define MDP_OUT_CTL_0                   0x410
+#define MDP_VSYNC_SEL                   0x414
+#define DCE_SEL                         0x450
+
+#endif /*_DPU_HWIO_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
new file mode 100644
index 000000000000..8d907faa7496
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -0,0 +1,204 @@
+/* Copyright (c) 2012-2015, 2017-2018, The Linux Foundation.
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/clk/clk-conf.h>
+#include <linux/err.h>
+#include <linux/delay.h>
+
+#include "dpu_io_util.h"
+
+void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk)
+{
+	int i;
+
+	for (i = num_clk - 1; i >= 0; i--) {
+		if (clk_arry[i].clk)
+			clk_put(clk_arry[i].clk);
+		clk_arry[i].clk = NULL;
+	}
+}
+
+int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk)
+{
+	int i, rc = 0;
+
+	for (i = 0; i < num_clk; i++) {
+		clk_arry[i].clk = clk_get(dev, clk_arry[i].clk_name);
+		rc = PTR_RET(clk_arry[i].clk);
+		if (rc) {
+			DEV_ERR("%pS->%s: '%s' get failed. rc=%d\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name, rc);
+			goto error;
+		}
+	}
+
+	return rc;
+
+error:
+	for (i--; i >= 0; i--) {
+		if (clk_arry[i].clk)
+			clk_put(clk_arry[i].clk);
+		clk_arry[i].clk = NULL;
+	}
+
+	return rc;
+}
+
+int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk)
+{
+	int i, rc = 0;
+
+	for (i = 0; i < num_clk; i++) {
+		if (clk_arry[i].clk) {
+			if (clk_arry[i].type != DSS_CLK_AHB) {
+				DEV_DBG("%pS->%s: '%s' rate %ld\n",
+					__builtin_return_address(0), __func__,
+					clk_arry[i].clk_name,
+					clk_arry[i].rate);
+				rc = clk_set_rate(clk_arry[i].clk,
+					clk_arry[i].rate);
+				if (rc) {
+					DEV_ERR("%pS->%s: %s failed. rc=%d\n",
+						__builtin_return_address(0),
+						__func__,
+						clk_arry[i].clk_name, rc);
+					break;
+				}
+			}
+		} else {
+			DEV_ERR("%pS->%s: '%s' is not available\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name);
+			rc = -EPERM;
+			break;
+		}
+	}
+
+	return rc;
+}
+
+int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable)
+{
+	int i, rc = 0;
+
+	if (enable) {
+		for (i = 0; i < num_clk; i++) {
+			DEV_DBG("%pS->%s: enable '%s'\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name);
+			if (clk_arry[i].clk) {
+				rc = clk_prepare_enable(clk_arry[i].clk);
+				if (rc)
+					DEV_ERR("%pS->%s: %s en fail. rc=%d\n",
+						__builtin_return_address(0),
+						__func__,
+						clk_arry[i].clk_name, rc);
+			} else {
+				DEV_ERR("%pS->%s: '%s' is not available\n",
+					__builtin_return_address(0), __func__,
+					clk_arry[i].clk_name);
+				rc = -EPERM;
+			}
+
+			if (rc) {
+				msm_dss_enable_clk(&clk_arry[i],
+					i, false);
+				break;
+			}
+		}
+	} else {
+		for (i = num_clk - 1; i >= 0; i--) {
+			DEV_DBG("%pS->%s: disable '%s'\n",
+				__builtin_return_address(0), __func__,
+				clk_arry[i].clk_name);
+
+			if (clk_arry[i].clk)
+				clk_disable_unprepare(clk_arry[i].clk);
+			else
+				DEV_ERR("%pS->%s: '%s' is not available\n",
+					__builtin_return_address(0), __func__,
+					clk_arry[i].clk_name);
+		}
+	}
+
+	return rc;
+}
+
+int msm_dss_parse_clock(struct platform_device *pdev,
+			struct dss_module_power *mp)
+{
+	u32 i, rc = 0;
+	const char *clock_name;
+	int num_clk = 0;
+
+	if (!pdev || !mp)
+		return -EINVAL;
+
+	mp->num_clk = 0;
+	num_clk = of_property_count_strings(pdev->dev.of_node,
+					    "assigned-clock-names");
+	if (num_clk <= 0) {
+		pr_debug("clocks are not defined\n");
+		return 0;
+	}
+
+	mp->clk_config = devm_kzalloc(&pdev->dev,
+				      sizeof(struct dss_clk) * num_clk,
+				      GFP_KERNEL);
+	if (!mp->clk_config)
+		return -ENOMEM;
+
+	for (i = 0; i < num_clk; i++) {
+		rc = of_property_read_string_index(pdev->dev.of_node,
+						   "assigned-clock-names", i,
+						   &clock_name);
+		if (rc) {
+			dev_err(&pdev->dev, "Failed to get clock name for %d\n",
+				i);
+			break;
+		}
+		strlcpy(mp->clk_config[i].clk_name, clock_name,
+			sizeof(mp->clk_config[i].clk_name));
+
+		mp->clk_config[i].type = DSS_CLK_AHB;
+	}
+
+	rc = msm_dss_get_clk(&pdev->dev, mp->clk_config, num_clk);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to get clock refs %d\n", rc);
+		goto err;
+	}
+
+	rc = of_clk_set_defaults(pdev->dev.of_node, false);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to set clock defaults %d\n", rc);
+		goto err;
+	}
+
+	for (i = 0; i < num_clk; i++) {
+		u32 rate = clk_get_rate(mp->clk_config[i].clk);
+		if (!rate)
+			continue;
+		mp->clk_config[i].rate = rate;
+		mp->clk_config[i].type = DSS_CLK_PCLK;
+	}
+
+	mp->num_clk = num_clk;
+	return 0;
+
+err:
+	msm_dss_put_clk(mp->clk_config, num_clk);
+	return rc;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h
new file mode 100644
index 000000000000..bc07381d7429
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.h
@@ -0,0 +1,57 @@
+/* Copyright (c) 2012, 2017-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_IO_UTIL_H__
+#define __DPU_IO_UTIL_H__
+
+#include <linux/gpio.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#define DEV_DBG(fmt, args...)   pr_debug(fmt, ##args)
+#define DEV_INFO(fmt, args...)  pr_info(fmt, ##args)
+#define DEV_WARN(fmt, args...)  pr_warn(fmt, ##args)
+#define DEV_ERR(fmt, args...)   pr_err(fmt, ##args)
+
+struct dss_gpio {
+	unsigned int gpio;
+	unsigned int value;
+	char gpio_name[32];
+};
+
+enum dss_clk_type {
+	DSS_CLK_AHB, /* no set rate. rate controlled through rpm */
+	DSS_CLK_PCLK,
+};
+
+struct dss_clk {
+	struct clk *clk; /* clk handle */
+	char clk_name[32];
+	enum dss_clk_type type;
+	unsigned long rate;
+	unsigned long max_rate;
+};
+
+struct dss_module_power {
+	unsigned int num_gpio;
+	struct dss_gpio *gpio_config;
+	unsigned int num_clk;
+	struct dss_clk *clk_config;
+};
+
+int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk);
+void msm_dss_put_clk(struct dss_clk *clk_arry, int num_clk);
+int msm_dss_clk_set_rate(struct dss_clk *clk_arry, int num_clk);
+int msm_dss_enable_clk(struct dss_clk *clk_arry, int num_clk, int enable);
+int msm_dss_parse_clock(struct platform_device *pdev,
+		struct dss_module_power *mp);
+#endif /* __DPU_IO_UTIL_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
new file mode 100644
index 000000000000..d5e6ce0140cf
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.c
@@ -0,0 +1,66 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/irqdomain.h>
+#include <linux/irq.h>
+#include <linux/kthread.h>
+
+#include "dpu_irq.h"
+#include "dpu_core_irq.h"
+
+irqreturn_t dpu_irq(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	return dpu_core_irq(dpu_kms);
+}
+
+void dpu_irq_preinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	if (!dpu_kms->dev || !dpu_kms->dev->dev) {
+		pr_err("invalid device handles\n");
+		return;
+	}
+
+	dpu_core_irq_preinstall(dpu_kms);
+}
+
+int dpu_irq_postinstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	int rc;
+
+	if (!kms) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	rc = dpu_core_irq_postinstall(dpu_kms);
+
+	return rc;
+}
+
+void dpu_irq_uninstall(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+
+	if (!kms) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	dpu_core_irq_uninstall(dpu_kms);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
new file mode 100644
index 000000000000..3e147f7176e2
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_irq.h
@@ -0,0 +1,59 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_IRQ_H__
+#define __DPU_IRQ_H__
+
+#include <linux/kernel.h>
+#include <linux/irqdomain.h>
+
+#include "msm_kms.h"
+
+/**
+ * dpu_irq_controller - define MDSS level interrupt controller context
+ * @enabled_mask:	enable status of MDSS level interrupt
+ * @domain:		interrupt domain of this controller
+ */
+struct dpu_irq_controller {
+	unsigned long enabled_mask;
+	struct irq_domain *domain;
+};
+
+/**
+ * dpu_irq_preinstall - perform pre-installation of MDSS IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		none
+ */
+void dpu_irq_preinstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq_postinstall - perform post-installation of MDSS IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		0 if success; error code otherwise
+ */
+int dpu_irq_postinstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq_uninstall - uninstall MDSS IRQ handler
+ * @drm_dev:		pointer to kms context
+ * @return:		none
+ */
+void dpu_irq_uninstall(struct msm_kms *kms);
+
+/**
+ * dpu_irq - MDSS level IRQ handler
+ * @kms:		pointer to kms context
+ * @return:		interrupt handling status
+ */
+irqreturn_t dpu_irq(struct msm_kms *kms);
+
+#endif /* __DPU_IRQ_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
new file mode 100644
index 000000000000..8d4678d29cc7
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -0,0 +1,1345 @@
+/*
+ * Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <drm/drm_crtc.h>
+#include <linux/debugfs.h>
+#include <linux/of_irq.h>
+#include <linux/dma-buf.h>
+
+#include "msm_drv.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+
+#include "dpu_kms.h"
+#include "dpu_core_irq.h"
+#include "dpu_formats.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_vbif.h"
+#include "dpu_encoder.h"
+#include "dpu_plane.h"
+#include "dpu_crtc.h"
+
+#define CREATE_TRACE_POINTS
+#include "dpu_trace.h"
+
+static const char * const iommu_ports[] = {
+		"mdp_0",
+};
+
+/*
+ * To enable overall DRM driver logging
+ * # echo 0x2 > /sys/module/drm/parameters/debug
+ *
+ * To enable DRM driver h/w logging
+ * # echo <mask> > /sys/kernel/debug/dri/0/debug/hw_log_mask
+ *
+ * See dpu_hw_mdss.h for h/w logging mask definitions (search for DPU_DBG_MASK_)
+ */
+#define DPU_DEBUGFS_DIR "msm_dpu"
+#define DPU_DEBUGFS_HWMASKNAME "hw_log_mask"
+
+static int dpu_kms_hw_init(struct msm_kms *kms);
+static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms);
+
+static unsigned long dpu_iomap_size(struct platform_device *pdev,
+				    const char *name)
+{
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
+	if (!res) {
+		DRM_ERROR("failed to get memory resource: %s\n", name);
+		return 0;
+	}
+
+	return resource_size(res);
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int _dpu_danger_signal_status(struct seq_file *s,
+		bool danger_status)
+{
+	struct dpu_kms *kms = (struct dpu_kms *)s->private;
+	struct msm_drm_private *priv;
+	struct dpu_danger_safe_status status;
+	int i;
+
+	if (!kms || !kms->dev || !kms->dev->dev_private || !kms->hw_mdp) {
+		DPU_ERROR("invalid arg(s)\n");
+		return 0;
+	}
+
+	priv = kms->dev->dev_private;
+	memset(&status, 0, sizeof(struct dpu_danger_safe_status));
+
+	pm_runtime_get_sync(&kms->pdev->dev);
+	if (danger_status) {
+		seq_puts(s, "\nDanger signal status:\n");
+		if (kms->hw_mdp->ops.get_danger_status)
+			kms->hw_mdp->ops.get_danger_status(kms->hw_mdp,
+					&status);
+	} else {
+		seq_puts(s, "\nSafe signal status:\n");
+		if (kms->hw_mdp->ops.get_danger_status)
+			kms->hw_mdp->ops.get_danger_status(kms->hw_mdp,
+					&status);
+	}
+	pm_runtime_put_sync(&kms->pdev->dev);
+
+	seq_printf(s, "MDP     :  0x%x\n", status.mdp);
+
+	for (i = SSPP_VIG0; i < SSPP_MAX; i++)
+		seq_printf(s, "SSPP%d   :  0x%x  \t", i - SSPP_VIG0,
+				status.sspp[i]);
+	seq_puts(s, "\n");
+
+	return 0;
+}
+
+#define DEFINE_DPU_DEBUGFS_SEQ_FOPS(__prefix)				\
+static int __prefix ## _open(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, __prefix ## _show, inode->i_private);	\
+}									\
+static const struct file_operations __prefix ## _fops = {		\
+	.owner = THIS_MODULE,						\
+	.open = __prefix ## _open,					\
+	.release = single_release,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+}
+
+static int dpu_debugfs_danger_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, true);
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_danger_stats);
+
+static int dpu_debugfs_safe_stats_show(struct seq_file *s, void *v)
+{
+	return _dpu_danger_signal_status(s, false);
+}
+DEFINE_DPU_DEBUGFS_SEQ_FOPS(dpu_debugfs_safe_stats);
+
+static void dpu_debugfs_danger_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove_recursive(dpu_kms->debugfs_danger);
+	dpu_kms->debugfs_danger = NULL;
+}
+
+static int dpu_debugfs_danger_init(struct dpu_kms *dpu_kms,
+		struct dentry *parent)
+{
+	dpu_kms->debugfs_danger = debugfs_create_dir("danger",
+			parent);
+	if (!dpu_kms->debugfs_danger) {
+		DPU_ERROR("failed to create danger debugfs\n");
+		return -EINVAL;
+	}
+
+	debugfs_create_file("danger_status", 0600, dpu_kms->debugfs_danger,
+			dpu_kms, &dpu_debugfs_danger_stats_fops);
+	debugfs_create_file("safe_status", 0600, dpu_kms->debugfs_danger,
+			dpu_kms, &dpu_debugfs_safe_stats_fops);
+
+	return 0;
+}
+
+static int _dpu_debugfs_show_regset32(struct seq_file *s, void *data)
+{
+	struct dpu_debugfs_regset32 *regset;
+	struct dpu_kms *dpu_kms;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
+	void __iomem *base;
+	uint32_t i, addr;
+
+	if (!s || !s->private)
+		return 0;
+
+	regset = s->private;
+
+	dpu_kms = regset->dpu_kms;
+	if (!dpu_kms || !dpu_kms->mmio)
+		return 0;
+
+	dev = dpu_kms->dev;
+	if (!dev)
+		return 0;
+
+	priv = dev->dev_private;
+	if (!priv)
+		return 0;
+
+	base = dpu_kms->mmio + regset->offset;
+
+	/* insert padding spaces, if needed */
+	if (regset->offset & 0xF) {
+		seq_printf(s, "[%x]", regset->offset & ~0xF);
+		for (i = 0; i < (regset->offset & 0xF); i += 4)
+			seq_puts(s, "         ");
+	}
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	/* main register output */
+	for (i = 0; i < regset->blk_len; i += 4) {
+		addr = regset->offset + i;
+		if ((addr & 0xF) == 0x0)
+			seq_printf(s, i ? "\n[%x]" : "[%x]", addr);
+		seq_printf(s, " %08x", readl_relaxed(base + i));
+	}
+	seq_puts(s, "\n");
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+}
+
+static int dpu_debugfs_open_regset32(struct inode *inode,
+		struct file *file)
+{
+	return single_open(file, _dpu_debugfs_show_regset32, inode->i_private);
+}
+
+static const struct file_operations dpu_fops_regset32 = {
+	.open =		dpu_debugfs_open_regset32,
+	.read =		seq_read,
+	.llseek =	seq_lseek,
+	.release =	single_release,
+};
+
+void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms)
+{
+	if (regset) {
+		regset->offset = offset;
+		regset->blk_len = length;
+		regset->dpu_kms = dpu_kms;
+	}
+}
+
+void *dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent, struct dpu_debugfs_regset32 *regset)
+{
+	if (!name || !regset || !regset->dpu_kms || !regset->blk_len)
+		return NULL;
+
+	/* make sure offset is a multiple of 4 */
+	regset->offset = round_down(regset->offset, 4);
+
+	return debugfs_create_file(name, mode, parent,
+			regset, &dpu_fops_regset32);
+}
+
+static int _dpu_debugfs_init(struct dpu_kms *dpu_kms)
+{
+	void *p;
+	int rc;
+
+	p = dpu_hw_util_get_log_mask_ptr();
+
+	if (!dpu_kms || !p)
+		return -EINVAL;
+
+	dpu_kms->debugfs_root = debugfs_create_dir("debug",
+					   dpu_kms->dev->primary->debugfs_root);
+	if (IS_ERR_OR_NULL(dpu_kms->debugfs_root)) {
+		DRM_ERROR("debugfs create_dir failed %ld\n",
+			  PTR_ERR(dpu_kms->debugfs_root));
+		return PTR_ERR(dpu_kms->debugfs_root);
+	}
+
+	rc = dpu_dbg_debugfs_register(dpu_kms->debugfs_root);
+	if (rc) {
+		DRM_ERROR("failed to reg dpu dbg debugfs: %d\n", rc);
+		return rc;
+	}
+
+	/* allow root to be NULL */
+	debugfs_create_x32(DPU_DEBUGFS_HWMASKNAME, 0600, dpu_kms->debugfs_root, p);
+
+	(void) dpu_debugfs_danger_init(dpu_kms, dpu_kms->debugfs_root);
+	(void) dpu_debugfs_vbif_init(dpu_kms, dpu_kms->debugfs_root);
+	(void) dpu_debugfs_core_irq_init(dpu_kms, dpu_kms->debugfs_root);
+
+	rc = dpu_core_perf_debugfs_init(&dpu_kms->perf, dpu_kms->debugfs_root);
+	if (rc) {
+		DPU_ERROR("failed to init perf %d\n", rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
+{
+	/* don't need to NULL check debugfs_root */
+	if (dpu_kms) {
+		dpu_debugfs_vbif_destroy(dpu_kms);
+		dpu_debugfs_danger_destroy(dpu_kms);
+		dpu_debugfs_core_irq_destroy(dpu_kms);
+		debugfs_remove_recursive(dpu_kms->debugfs_root);
+	}
+}
+#else
+static void _dpu_debugfs_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+
+static int dpu_kms_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	return dpu_crtc_vblank(crtc, true);
+}
+
+static void dpu_kms_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc)
+{
+	dpu_crtc_vblank(crtc, false);
+}
+
+static void dpu_kms_prepare_commit(struct msm_kms *kms,
+		struct drm_atomic_state *state)
+{
+	struct dpu_kms *dpu_kms;
+	struct msm_drm_private *priv;
+	struct drm_device *dev;
+	struct drm_encoder *encoder;
+
+	if (!kms)
+		return;
+	dpu_kms = to_dpu_kms(kms);
+	dev = dpu_kms->dev;
+
+	if (!dev || !dev->dev_private)
+		return;
+	priv = dev->dev_private;
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head)
+		if (encoder->crtc != NULL)
+			dpu_encoder_prepare_commit(encoder);
+}
+
+/*
+ * Override the encoder enable since we need to setup the inline rotator and do
+ * some crtc magic before enabling any bridge that might be present.
+ */
+void dpu_kms_encoder_enable(struct drm_encoder *encoder)
+{
+	const struct drm_encoder_helper_funcs *funcs = encoder->helper_private;
+	struct drm_crtc *crtc = encoder->crtc;
+
+	/* Forward this enable call to the commit hook */
+	if (funcs && funcs->commit)
+		funcs->commit(encoder);
+
+	if (crtc && crtc->state->active) {
+		trace_dpu_kms_enc_enable(DRMID(crtc));
+		dpu_crtc_commit_kickoff(crtc);
+	}
+}
+
+static void dpu_kms_commit(struct msm_kms *kms, struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *crtc_state;
+	int i;
+
+	for_each_new_crtc_in_state(state, crtc, crtc_state, i) {
+		/* If modeset is required, kickoff is run in encoder_enable */
+		if (drm_atomic_crtc_needs_modeset(crtc_state))
+			continue;
+
+		if (crtc->state->active) {
+			trace_dpu_kms_commit(DRMID(crtc));
+			dpu_crtc_commit_kickoff(crtc);
+		}
+	}
+}
+
+static void dpu_kms_complete_commit(struct msm_kms *kms,
+		struct drm_atomic_state *old_state)
+{
+	struct dpu_kms *dpu_kms;
+	struct msm_drm_private *priv;
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *old_crtc_state;
+	int i;
+
+	if (!kms || !old_state)
+		return;
+	dpu_kms = to_dpu_kms(kms);
+
+	if (!dpu_kms->dev || !dpu_kms->dev->dev_private)
+		return;
+	priv = dpu_kms->dev->dev_private;
+
+	DPU_ATRACE_BEGIN("kms_complete_commit");
+
+	for_each_old_crtc_in_state(old_state, crtc, old_crtc_state, i)
+		dpu_crtc_complete_commit(crtc, old_crtc_state);
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	DPU_ATRACE_END("kms_complete_commit");
+}
+
+static void dpu_kms_wait_for_commit_done(struct msm_kms *kms,
+		struct drm_crtc *crtc)
+{
+	struct drm_encoder *encoder;
+	struct drm_device *dev;
+	int ret;
+
+	if (!kms || !crtc || !crtc->state) {
+		DPU_ERROR("invalid params\n");
+		return;
+	}
+
+	dev = crtc->dev;
+
+	if (!crtc->state->enable) {
+		DPU_DEBUG("[crtc:%d] not enable\n", crtc->base.id);
+		return;
+	}
+
+	if (!crtc->state->active) {
+		DPU_DEBUG("[crtc:%d] not active\n", crtc->base.id);
+		return;
+	}
+
+	list_for_each_entry(encoder, &dev->mode_config.encoder_list, head) {
+		if (encoder->crtc != crtc)
+			continue;
+		/*
+		 * Wait for post-flush if necessary to delay before
+		 * plane_cleanup. For example, wait for vsync in case of video
+		 * mode panels. This may be a no-op for command mode panels.
+		 */
+		trace_dpu_kms_wait_for_commit_done(DRMID(crtc));
+		ret = dpu_encoder_wait_for_event(encoder, MSM_ENC_COMMIT_DONE);
+		if (ret && ret != -EWOULDBLOCK) {
+			DPU_ERROR("wait for commit done returned %d\n", ret);
+			break;
+		}
+	}
+}
+
+static void _dpu_kms_initialize_dsi(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	struct drm_encoder *encoder = NULL;
+	int i, rc;
+
+	/*TODO: Support two independent DSI connectors */
+	encoder = dpu_encoder_init(dev, DRM_MODE_CONNECTOR_DSI);
+	if (IS_ERR_OR_NULL(encoder)) {
+		DPU_ERROR("encoder init failed for dsi display\n");
+		return;
+	}
+
+	priv->encoders[priv->num_encoders++] = encoder;
+
+	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		if (!priv->dsi[i]) {
+			DPU_DEBUG("invalid msm_dsi for ctrl %d\n", i);
+			return;
+		}
+
+		rc = msm_dsi_modeset_init(priv->dsi[i], dev, encoder);
+		if (rc) {
+			DPU_ERROR("modeset_init failed for dsi[%d], rc = %d\n",
+				i, rc);
+			continue;
+		}
+	}
+}
+
+/**
+ * _dpu_kms_setup_displays - create encoders, bridges and connectors
+ *                           for underlying displays
+ * @dev:        Pointer to drm device structure
+ * @priv:       Pointer to private drm device data
+ * @dpu_kms:    Pointer to dpu kms structure
+ * Returns:     Zero on success
+ */
+static void _dpu_kms_setup_displays(struct drm_device *dev,
+				    struct msm_drm_private *priv,
+				    struct dpu_kms *dpu_kms)
+{
+	_dpu_kms_initialize_dsi(dev, priv, dpu_kms);
+
+	/**
+	 * Extend this function to initialize other
+	 * types of displays
+	 */
+}
+
+static void _dpu_kms_drm_obj_destroy(struct dpu_kms *dpu_kms)
+{
+	struct msm_drm_private *priv;
+	int i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return;
+	} else if (!dpu_kms->dev) {
+		DPU_ERROR("invalid dev\n");
+		return;
+	} else if (!dpu_kms->dev->dev_private) {
+		DPU_ERROR("invalid dev_private\n");
+		return;
+	}
+	priv = dpu_kms->dev->dev_private;
+
+	for (i = 0; i < priv->num_crtcs; i++)
+		priv->crtcs[i]->funcs->destroy(priv->crtcs[i]);
+	priv->num_crtcs = 0;
+
+	for (i = 0; i < priv->num_planes; i++)
+		priv->planes[i]->funcs->destroy(priv->planes[i]);
+	priv->num_planes = 0;
+
+	for (i = 0; i < priv->num_connectors; i++)
+		priv->connectors[i]->funcs->destroy(priv->connectors[i]);
+	priv->num_connectors = 0;
+
+	for (i = 0; i < priv->num_encoders; i++)
+		priv->encoders[i]->funcs->destroy(priv->encoders[i]);
+	priv->num_encoders = 0;
+}
+
+static int _dpu_kms_drm_obj_init(struct dpu_kms *dpu_kms)
+{
+	struct drm_device *dev;
+	struct drm_plane *primary_planes[MAX_PLANES], *plane;
+	struct drm_crtc *crtc;
+
+	struct msm_drm_private *priv;
+	struct dpu_mdss_cfg *catalog;
+
+	int primary_planes_idx = 0, i, ret;
+	int max_crtc_count;
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return -EINVAL;
+	}
+
+	dev = dpu_kms->dev;
+	priv = dev->dev_private;
+	catalog = dpu_kms->catalog;
+
+	/*
+	 * Create encoder and query display drivers to create
+	 * bridges and connectors
+	 */
+	_dpu_kms_setup_displays(dev, priv, dpu_kms);
+
+	max_crtc_count = min(catalog->mixer_count, priv->num_encoders);
+
+	/* Create the planes */
+	for (i = 0; i < catalog->sspp_count; i++) {
+		bool primary = true;
+
+		if (catalog->sspp[i].features & BIT(DPU_SSPP_CURSOR)
+			|| primary_planes_idx >= max_crtc_count)
+			primary = false;
+
+		plane = dpu_plane_init(dev, catalog->sspp[i].id, primary,
+				(1UL << max_crtc_count) - 1, 0);
+		if (IS_ERR(plane)) {
+			DPU_ERROR("dpu_plane_init failed\n");
+			ret = PTR_ERR(plane);
+			goto fail;
+		}
+		priv->planes[priv->num_planes++] = plane;
+
+		if (primary)
+			primary_planes[primary_planes_idx++] = plane;
+	}
+
+	max_crtc_count = min(max_crtc_count, primary_planes_idx);
+
+	/* Create one CRTC per encoder */
+	for (i = 0; i < max_crtc_count; i++) {
+		crtc = dpu_crtc_init(dev, primary_planes[i]);
+		if (IS_ERR(crtc)) {
+			ret = PTR_ERR(crtc);
+			goto fail;
+		}
+		priv->crtcs[priv->num_crtcs++] = crtc;
+	}
+
+	/* All CRTCs are compatible with all encoders */
+	for (i = 0; i < priv->num_encoders; i++)
+		priv->encoders[i]->possible_crtcs = (1 << priv->num_crtcs) - 1;
+
+	return 0;
+fail:
+	_dpu_kms_drm_obj_destroy(dpu_kms);
+	return ret;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static int dpu_kms_debugfs_init(struct msm_kms *kms, struct drm_minor *minor)
+{
+	struct dpu_kms *dpu_kms = to_dpu_kms(kms);
+	struct drm_device *dev;
+	int rc;
+
+	if (!dpu_kms || !dpu_kms->dev || !dpu_kms->dev->dev) {
+		DPU_ERROR("invalid dpu_kms\n");
+		return -EINVAL;
+	}
+
+	dev = dpu_kms->dev;
+
+	rc = _dpu_debugfs_init(dpu_kms);
+	if (rc)
+		DPU_ERROR("dpu_debugfs init failed: %d\n", rc);
+
+	return rc;
+}
+#endif
+
+static long dpu_kms_round_pixclk(struct msm_kms *kms, unsigned long rate,
+		struct drm_encoder *encoder)
+{
+	return rate;
+}
+
+static void _dpu_kms_hw_destroy(struct dpu_kms *dpu_kms)
+{
+	struct drm_device *dev;
+	int i;
+
+	dev = dpu_kms->dev;
+	if (!dev)
+		return;
+
+	if (dpu_kms->hw_intr)
+		dpu_hw_intr_destroy(dpu_kms->hw_intr);
+	dpu_kms->hw_intr = NULL;
+
+	if (dpu_kms->power_event)
+		dpu_power_handle_unregister_event(
+				&dpu_kms->phandle, dpu_kms->power_event);
+
+	/* safe to call these more than once during shutdown */
+	_dpu_debugfs_destroy(dpu_kms);
+	_dpu_kms_mmu_destroy(dpu_kms);
+
+	if (dpu_kms->catalog) {
+		for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+			u32 vbif_idx = dpu_kms->catalog->vbif[i].id;
+
+			if ((vbif_idx < VBIF_MAX) && dpu_kms->hw_vbif[vbif_idx])
+				dpu_hw_vbif_destroy(dpu_kms->hw_vbif[vbif_idx]);
+		}
+	}
+
+	if (dpu_kms->rm_init)
+		dpu_rm_destroy(&dpu_kms->rm);
+	dpu_kms->rm_init = false;
+
+	if (dpu_kms->catalog)
+		dpu_hw_catalog_deinit(dpu_kms->catalog);
+	dpu_kms->catalog = NULL;
+
+	if (dpu_kms->core_client)
+		dpu_power_client_destroy(&dpu_kms->phandle,
+			dpu_kms->core_client);
+	dpu_kms->core_client = NULL;
+
+	if (dpu_kms->vbif[VBIF_NRT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_NRT]);
+	dpu_kms->vbif[VBIF_NRT] = NULL;
+
+	if (dpu_kms->vbif[VBIF_RT])
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->vbif[VBIF_RT]);
+	dpu_kms->vbif[VBIF_RT] = NULL;
+
+	if (dpu_kms->mmio)
+		devm_iounmap(&dpu_kms->pdev->dev, dpu_kms->mmio);
+	dpu_kms->mmio = NULL;
+}
+
+static void dpu_kms_destroy(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+
+	dpu_dbg_destroy();
+	_dpu_kms_hw_destroy(dpu_kms);
+}
+
+static int dpu_kms_pm_suspend(struct device *dev)
+{
+	struct drm_device *ddev;
+	struct drm_modeset_acquire_ctx ctx;
+	struct drm_atomic_state *state;
+	struct dpu_kms *dpu_kms;
+	int ret = 0, num_crtcs = 0;
+
+	if (!dev)
+		return -EINVAL;
+
+	ddev = dev_get_drvdata(dev);
+	if (!ddev || !ddev_to_msm_kms(ddev))
+		return -EINVAL;
+
+	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
+
+	/* disable hot-plug polling */
+	drm_kms_helper_poll_disable(ddev);
+
+	/* acquire modeset lock(s) */
+	drm_modeset_acquire_init(&ctx, 0);
+
+retry:
+	DPU_ATRACE_BEGIN("kms_pm_suspend");
+
+	ret = drm_modeset_lock_all_ctx(ddev, &ctx);
+	if (ret)
+		goto unlock;
+
+	/* save current state for resume */
+	if (dpu_kms->suspend_state)
+		drm_atomic_state_put(dpu_kms->suspend_state);
+	dpu_kms->suspend_state = drm_atomic_helper_duplicate_state(ddev, &ctx);
+	if (IS_ERR_OR_NULL(dpu_kms->suspend_state)) {
+		DRM_ERROR("failed to back up suspend state\n");
+		dpu_kms->suspend_state = NULL;
+		goto unlock;
+	}
+
+	/* create atomic state to disable all CRTCs */
+	state = drm_atomic_state_alloc(ddev);
+	if (IS_ERR_OR_NULL(state)) {
+		DRM_ERROR("failed to allocate crtc disable state\n");
+		goto unlock;
+	}
+
+	state->acquire_ctx = &ctx;
+
+	/* check for nothing to do */
+	if (num_crtcs == 0) {
+		DRM_DEBUG("all crtcs are already in the off state\n");
+		drm_atomic_state_put(state);
+		goto suspended;
+	}
+
+	/* commit the "disable all" state */
+	ret = drm_atomic_commit(state);
+	if (ret < 0) {
+		DRM_ERROR("failed to disable crtcs, %d\n", ret);
+		drm_atomic_state_put(state);
+		goto unlock;
+	}
+
+suspended:
+	dpu_kms->suspend_block = true;
+
+unlock:
+	if (ret == -EDEADLK) {
+		drm_modeset_backoff(&ctx);
+		goto retry;
+	}
+	drm_modeset_drop_locks(&ctx);
+	drm_modeset_acquire_fini(&ctx);
+
+	DPU_ATRACE_END("kms_pm_suspend");
+	return 0;
+}
+
+static int dpu_kms_pm_resume(struct device *dev)
+{
+	struct drm_device *ddev;
+	struct dpu_kms *dpu_kms;
+	int ret;
+
+	if (!dev)
+		return -EINVAL;
+
+	ddev = dev_get_drvdata(dev);
+	if (!ddev || !ddev_to_msm_kms(ddev))
+		return -EINVAL;
+
+	dpu_kms = to_dpu_kms(ddev_to_msm_kms(ddev));
+
+	DPU_ATRACE_BEGIN("kms_pm_resume");
+
+	drm_mode_config_reset(ddev);
+
+	drm_modeset_lock_all(ddev);
+
+	dpu_kms->suspend_block = false;
+
+	if (dpu_kms->suspend_state) {
+		dpu_kms->suspend_state->acquire_ctx =
+			ddev->mode_config.acquire_ctx;
+		ret = drm_atomic_commit(dpu_kms->suspend_state);
+		if (ret < 0) {
+			DRM_ERROR("failed to restore state, %d\n", ret);
+			drm_atomic_state_put(dpu_kms->suspend_state);
+		}
+		dpu_kms->suspend_state = NULL;
+	}
+	drm_modeset_unlock_all(ddev);
+
+	/* enable hot-plug polling */
+	drm_kms_helper_poll_enable(ddev);
+
+	DPU_ATRACE_END("kms_pm_resume");
+	return 0;
+}
+
+void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
+				 struct drm_encoder *encoder,
+				 bool cmd_mode)
+{
+	struct msm_display_info info;
+	struct msm_drm_private *priv = encoder->dev->dev_private;
+	int i, rc = 0;
+
+	memset(&info, 0, sizeof(info));
+
+	info.intf_type = encoder->encoder_type;
+	info.capabilities = cmd_mode ? MSM_DISPLAY_CAP_CMD_MODE :
+			MSM_DISPLAY_CAP_VID_MODE;
+
+	/* TODO: No support for DSI swap */
+	for (i = 0; i < ARRAY_SIZE(priv->dsi); i++) {
+		if (priv->dsi[i]) {
+			info.h_tile_instance[info.num_of_h_tiles] = i;
+			info.num_of_h_tiles++;
+		}
+	}
+
+	rc = dpu_encoder_setup(encoder->dev, encoder, &info);
+	if (rc)
+		DPU_ERROR("failed to setup DPU encoder %d: rc:%d\n",
+			encoder->base.id, rc);
+}
+
+static const struct msm_kms_funcs kms_funcs = {
+	.hw_init         = dpu_kms_hw_init,
+	.irq_preinstall  = dpu_irq_preinstall,
+	.irq_postinstall = dpu_irq_postinstall,
+	.irq_uninstall   = dpu_irq_uninstall,
+	.irq             = dpu_irq,
+	.prepare_commit  = dpu_kms_prepare_commit,
+	.commit          = dpu_kms_commit,
+	.complete_commit = dpu_kms_complete_commit,
+	.wait_for_crtc_commit_done = dpu_kms_wait_for_commit_done,
+	.enable_vblank   = dpu_kms_enable_vblank,
+	.disable_vblank  = dpu_kms_disable_vblank,
+	.check_modified_format = dpu_format_check_modified_format,
+	.get_format      = dpu_get_msm_format,
+	.round_pixclk    = dpu_kms_round_pixclk,
+	.pm_suspend      = dpu_kms_pm_suspend,
+	.pm_resume       = dpu_kms_pm_resume,
+	.destroy         = dpu_kms_destroy,
+	.set_encoder_mode = _dpu_kms_set_encoder_mode,
+#ifdef CONFIG_DEBUG_FS
+	.debugfs_init    = dpu_kms_debugfs_init,
+#endif
+};
+
+/* the caller api needs to turn on clock before calling it */
+static inline void _dpu_kms_core_hw_rev_init(struct dpu_kms *dpu_kms)
+{
+	dpu_kms->core_rev = readl_relaxed(dpu_kms->mmio + 0x0);
+}
+
+static int _dpu_kms_mmu_destroy(struct dpu_kms *dpu_kms)
+{
+	struct msm_mmu *mmu;
+
+	mmu = dpu_kms->base.aspace->mmu;
+
+	mmu->funcs->detach(mmu, (const char **)iommu_ports,
+			ARRAY_SIZE(iommu_ports));
+	msm_gem_address_space_put(dpu_kms->base.aspace);
+
+	return 0;
+}
+
+static int _dpu_kms_mmu_init(struct dpu_kms *dpu_kms)
+{
+	struct iommu_domain *domain;
+	struct msm_gem_address_space *aspace;
+	int ret;
+
+	domain = iommu_domain_alloc(&platform_bus_type);
+	if (!domain)
+		return 0;
+
+	aspace = msm_gem_address_space_create(dpu_kms->dev->dev,
+			domain, "dpu1");
+	if (IS_ERR(aspace)) {
+		ret = PTR_ERR(aspace);
+		goto fail;
+	}
+
+	dpu_kms->base.aspace = aspace;
+
+	ret = aspace->mmu->funcs->attach(aspace->mmu, iommu_ports,
+			ARRAY_SIZE(iommu_ports));
+	if (ret) {
+		DPU_ERROR("failed to attach iommu %d\n", ret);
+		msm_gem_address_space_put(aspace);
+		goto fail;
+	}
+
+	return 0;
+fail:
+	_dpu_kms_mmu_destroy(dpu_kms);
+
+	return ret;
+}
+
+static struct dss_clk *_dpu_kms_get_clk(struct dpu_kms *dpu_kms,
+		char *clock_name)
+{
+	struct dss_module_power *mp = &dpu_kms->mp;
+	int i;
+
+	for (i = 0; i < mp->num_clk; i++) {
+		if (!strcmp(mp->clk_config[i].clk_name, clock_name))
+			return &mp->clk_config[i];
+	}
+
+	return NULL;
+}
+
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name)
+{
+	struct dss_clk *clk;
+
+	clk = _dpu_kms_get_clk(dpu_kms, clock_name);
+	if (!clk)
+		return -EINVAL;
+
+	return clk_get_rate(clk->clk);
+}
+
+static void dpu_kms_handle_power_event(u32 event_type, void *usr)
+{
+	struct dpu_kms *dpu_kms = usr;
+
+	if (!dpu_kms)
+		return;
+
+	if (event_type == DPU_POWER_EVENT_POST_ENABLE)
+		dpu_vbif_init_memtypes(dpu_kms);
+}
+
+static int dpu_kms_hw_init(struct msm_kms *kms)
+{
+	struct dpu_kms *dpu_kms;
+	struct drm_device *dev;
+	struct msm_drm_private *priv;
+	int i, rc = -EINVAL;
+
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		goto end;
+	}
+
+	dpu_kms = to_dpu_kms(kms);
+	dev = dpu_kms->dev;
+	if (!dev) {
+		DPU_ERROR("invalid device\n");
+		goto end;
+	}
+
+	rc = dpu_dbg_init(&dpu_kms->pdev->dev);
+	if (rc) {
+		DRM_ERROR("failed to init dpu dbg: %d\n", rc);
+		goto end;
+	}
+
+	priv = dev->dev_private;
+	if (!priv) {
+		DPU_ERROR("invalid private data\n");
+		goto dbg_destroy;
+	}
+
+	dpu_kms->mmio = msm_ioremap(dpu_kms->pdev, "mdp", "mdp");
+	if (IS_ERR(dpu_kms->mmio)) {
+		rc = PTR_ERR(dpu_kms->mmio);
+		DPU_ERROR("mdp register memory map failed: %d\n", rc);
+		dpu_kms->mmio = NULL;
+		goto error;
+	}
+	DRM_DEBUG("mapped dpu address space @%pK\n", dpu_kms->mmio);
+	dpu_kms->mmio_len = dpu_iomap_size(dpu_kms->pdev, "mdp");
+
+	dpu_kms->vbif[VBIF_RT] = msm_ioremap(dpu_kms->pdev, "vbif", "vbif");
+	if (IS_ERR(dpu_kms->vbif[VBIF_RT])) {
+		rc = PTR_ERR(dpu_kms->vbif[VBIF_RT]);
+		DPU_ERROR("vbif register memory map failed: %d\n", rc);
+		dpu_kms->vbif[VBIF_RT] = NULL;
+		goto error;
+	}
+	dpu_kms->vbif_len[VBIF_RT] = dpu_iomap_size(dpu_kms->pdev, "vbif");
+	dpu_kms->vbif[VBIF_NRT] = msm_ioremap(dpu_kms->pdev, "vbif_nrt", "vbif_nrt");
+	if (IS_ERR(dpu_kms->vbif[VBIF_NRT])) {
+		dpu_kms->vbif[VBIF_NRT] = NULL;
+		DPU_DEBUG("VBIF NRT is not defined");
+	} else {
+		dpu_kms->vbif_len[VBIF_NRT] = dpu_iomap_size(dpu_kms->pdev,
+							     "vbif_nrt");
+	}
+
+	dpu_kms->reg_dma = msm_ioremap(dpu_kms->pdev, "regdma", "regdma");
+	if (IS_ERR(dpu_kms->reg_dma)) {
+		dpu_kms->reg_dma = NULL;
+		DPU_DEBUG("REG_DMA is not defined");
+	} else {
+		dpu_kms->reg_dma_len = dpu_iomap_size(dpu_kms->pdev, "regdma");
+	}
+
+	dpu_kms->core_client = dpu_power_client_create(&dpu_kms->phandle,
+					"core");
+	if (IS_ERR_OR_NULL(dpu_kms->core_client)) {
+		rc = PTR_ERR(dpu_kms->core_client);
+		if (!dpu_kms->core_client)
+			rc = -EINVAL;
+		DPU_ERROR("dpu power client create failed: %d\n", rc);
+		dpu_kms->core_client = NULL;
+		goto error;
+	}
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+
+	_dpu_kms_core_hw_rev_init(dpu_kms);
+
+	pr_info("dpu hardware revision:0x%x\n", dpu_kms->core_rev);
+
+	dpu_kms->catalog = dpu_hw_catalog_init(dpu_kms->core_rev);
+	if (IS_ERR_OR_NULL(dpu_kms->catalog)) {
+		rc = PTR_ERR(dpu_kms->catalog);
+		if (!dpu_kms->catalog)
+			rc = -EINVAL;
+		DPU_ERROR("catalog init failed: %d\n", rc);
+		dpu_kms->catalog = NULL;
+		goto power_error;
+	}
+
+	dpu_dbg_init_dbg_buses(dpu_kms->core_rev);
+
+	/*
+	 * Now we need to read the HW catalog and initialize resources such as
+	 * clocks, regulators, GDSC/MMAGIC, ioremap the register ranges etc
+	 */
+	rc = _dpu_kms_mmu_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("dpu_kms_mmu_init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	rc = dpu_rm_init(&dpu_kms->rm, dpu_kms->catalog, dpu_kms->mmio,
+			dpu_kms->dev);
+	if (rc) {
+		DPU_ERROR("rm init failed: %d\n", rc);
+		goto power_error;
+	}
+
+	dpu_kms->rm_init = true;
+
+	dpu_kms->hw_mdp = dpu_rm_get_mdp(&dpu_kms->rm);
+	if (IS_ERR_OR_NULL(dpu_kms->hw_mdp)) {
+		rc = PTR_ERR(dpu_kms->hw_mdp);
+		if (!dpu_kms->hw_mdp)
+			rc = -EINVAL;
+		DPU_ERROR("failed to get hw_mdp: %d\n", rc);
+		dpu_kms->hw_mdp = NULL;
+		goto power_error;
+	}
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		u32 vbif_idx = dpu_kms->catalog->vbif[i].id;
+
+		dpu_kms->hw_vbif[i] = dpu_hw_vbif_init(vbif_idx,
+				dpu_kms->vbif[vbif_idx], dpu_kms->catalog);
+		if (IS_ERR_OR_NULL(dpu_kms->hw_vbif[vbif_idx])) {
+			rc = PTR_ERR(dpu_kms->hw_vbif[vbif_idx]);
+			if (!dpu_kms->hw_vbif[vbif_idx])
+				rc = -EINVAL;
+			DPU_ERROR("failed to init vbif %d: %d\n", vbif_idx, rc);
+			dpu_kms->hw_vbif[vbif_idx] = NULL;
+			goto power_error;
+		}
+	}
+
+	rc = dpu_core_perf_init(&dpu_kms->perf, dev, dpu_kms->catalog,
+			&dpu_kms->phandle,
+			_dpu_kms_get_clk(dpu_kms, "core"));
+	if (rc) {
+		DPU_ERROR("failed to init perf %d\n", rc);
+		goto perf_err;
+	}
+
+	dpu_kms->hw_intr = dpu_hw_intr_init(dpu_kms->mmio, dpu_kms->catalog);
+	if (IS_ERR_OR_NULL(dpu_kms->hw_intr)) {
+		rc = PTR_ERR(dpu_kms->hw_intr);
+		DPU_ERROR("hw_intr init failed: %d\n", rc);
+		dpu_kms->hw_intr = NULL;
+		goto hw_intr_init_err;
+	}
+
+	/*
+	 * _dpu_kms_drm_obj_init should create the DRM related objects
+	 * i.e. CRTCs, planes, encoders, connectors and so forth
+	 */
+	rc = _dpu_kms_drm_obj_init(dpu_kms);
+	if (rc) {
+		DPU_ERROR("modeset init failed: %d\n", rc);
+		goto drm_obj_init_err;
+	}
+
+	dev->mode_config.min_width = 0;
+	dev->mode_config.min_height = 0;
+
+	/*
+	 * max crtc width is equal to the max mixer width * 2 and max height is
+	 * is 4K
+	 */
+	dev->mode_config.max_width =
+			dpu_kms->catalog->caps->max_mixer_width * 2;
+	dev->mode_config.max_height = 4096;
+
+	/*
+	 * Support format modifiers for compression etc.
+	 */
+	dev->mode_config.allow_fb_modifiers = true;
+
+	/*
+	 * Handle (re)initializations during power enable
+	 */
+	dpu_kms_handle_power_event(DPU_POWER_EVENT_POST_ENABLE, dpu_kms);
+	dpu_kms->power_event = dpu_power_handle_register_event(
+			&dpu_kms->phandle,
+			DPU_POWER_EVENT_POST_ENABLE,
+			dpu_kms_handle_power_event, dpu_kms, "kms");
+
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+	return 0;
+
+drm_obj_init_err:
+	dpu_core_perf_destroy(&dpu_kms->perf);
+hw_intr_init_err:
+perf_err:
+power_error:
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+error:
+	_dpu_kms_hw_destroy(dpu_kms);
+dbg_destroy:
+	dpu_dbg_destroy();
+end:
+	return rc;
+}
+
+struct msm_kms *dpu_kms_init(struct drm_device *dev)
+{
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+	int irq;
+
+	if (!dev || !dev->dev_private) {
+		DPU_ERROR("drm device node invalid\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	priv = dev->dev_private;
+	dpu_kms = to_dpu_kms(priv->kms);
+
+	irq = irq_of_parse_and_map(dpu_kms->pdev->dev.of_node, 0);
+	if (irq < 0) {
+		DPU_ERROR("failed to get irq: %d\n", irq);
+		return ERR_PTR(irq);
+	}
+	dpu_kms->base.irq = irq;
+
+	return &dpu_kms->base;
+}
+
+static int dpu_bind(struct device *dev, struct device *master, void *data)
+{
+	struct drm_device *ddev = dev_get_drvdata(master);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct msm_drm_private *priv = ddev->dev_private;
+	struct dpu_kms *dpu_kms;
+	struct dss_module_power *mp;
+	int ret = 0;
+
+	dpu_kms = devm_kzalloc(&pdev->dev, sizeof(*dpu_kms), GFP_KERNEL);
+	if (!dpu_kms)
+		return -ENOMEM;
+
+	mp = &dpu_kms->mp;
+	ret = msm_dss_parse_clock(pdev, mp);
+	if (ret) {
+		DPU_ERROR("failed to parse clocks, ret=%d\n", ret);
+		return ret;
+	}
+
+	dpu_power_resource_init(pdev, &dpu_kms->phandle);
+
+	platform_set_drvdata(pdev, dpu_kms);
+
+	msm_kms_init(&dpu_kms->base, &kms_funcs);
+	dpu_kms->dev = ddev;
+	dpu_kms->pdev = pdev;
+
+	pm_runtime_enable(&pdev->dev);
+	dpu_kms->rpm_enabled = true;
+
+	priv->kms = &dpu_kms->base;
+	return ret;
+}
+
+static void dpu_unbind(struct device *dev, struct device *master, void *data)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	dpu_power_resource_deinit(pdev, &dpu_kms->phandle);
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+	devm_kfree(&pdev->dev, mp->clk_config);
+	mp->num_clk = 0;
+
+	if (dpu_kms->rpm_enabled)
+		pm_runtime_disable(&pdev->dev);
+}
+
+static const struct component_ops dpu_ops = {
+	.bind   = dpu_bind,
+	.unbind = dpu_unbind,
+};
+
+static int dpu_dev_probe(struct platform_device *pdev)
+{
+	return component_add(&pdev->dev, &dpu_ops);
+}
+
+static int dpu_dev_remove(struct platform_device *pdev)
+{
+	component_del(&pdev->dev, &dpu_ops);
+	return 0;
+}
+
+static int dpu_runtime_suspend(struct device *dev)
+{
+	int rc = -1;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct drm_device *ddev;
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	ddev = dpu_kms->dev;
+	if (!ddev) {
+		DPU_ERROR("invalid drm_device\n");
+		goto exit;
+	}
+
+	rc = dpu_power_resource_enable(&dpu_kms->phandle,
+			dpu_kms->core_client, false);
+	if (rc)
+		DPU_ERROR("resource disable failed: %d\n", rc);
+
+	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
+	if (rc)
+		DPU_ERROR("clock disable failed rc:%d\n", rc);
+
+exit:
+	return rc;
+}
+
+static int dpu_runtime_resume(struct device *dev)
+{
+	int rc = -1;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct dpu_kms *dpu_kms = platform_get_drvdata(pdev);
+	struct drm_device *ddev;
+	struct dss_module_power *mp = &dpu_kms->mp;
+
+	ddev = dpu_kms->dev;
+	if (!ddev) {
+		DPU_ERROR("invalid drm_device\n");
+		goto exit;
+	}
+
+	rc = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
+	if (rc) {
+		DPU_ERROR("clock enable failed rc:%d\n", rc);
+		goto exit;
+	}
+
+	rc = dpu_power_resource_enable(&dpu_kms->phandle,
+			dpu_kms->core_client, true);
+	if (rc)
+		DPU_ERROR("resource enable failed: %d\n", rc);
+
+exit:
+	return rc;
+}
+
+static const struct dev_pm_ops dpu_pm_ops = {
+	SET_RUNTIME_PM_OPS(dpu_runtime_suspend, dpu_runtime_resume, NULL)
+};
+
+static const struct of_device_id dpu_dt_match[] = {
+	{ .compatible = "qcom,sdm845-dpu", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, dpu_dt_match);
+
+static struct platform_driver dpu_driver = {
+	.probe = dpu_dev_probe,
+	.remove = dpu_dev_remove,
+	.driver = {
+		.name = "msm_dpu",
+		.of_match_table = dpu_dt_match,
+		.pm = &dpu_pm_ops,
+	},
+};
+
+void __init msm_dpu_register(void)
+{
+	platform_driver_register(&dpu_driver);
+}
+
+void __exit msm_dpu_unregister(void)
+{
+	platform_driver_unregister(&dpu_driver);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
new file mode 100644
index 000000000000..407c1ed27fe6
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -0,0 +1,402 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef __DPU_KMS_H__
+#define __DPU_KMS_H__
+
+#include "msm_drv.h"
+#include "msm_kms.h"
+#include "msm_mmu.h"
+#include "msm_gem.h"
+#include "dpu_dbg.h"
+#include "dpu_hw_catalog.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_interrupts.h"
+#include "dpu_hw_top.h"
+#include "dpu_rm.h"
+#include "dpu_power_handle.h"
+#include "dpu_irq.h"
+#include "dpu_core_perf.h"
+
+#define DRMID(x) ((x) ? (x)->base.id : -1)
+
+/**
+ * DPU_DEBUG - macro for kms/plane/crtc/encoder/connector logs
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG(fmt, ...)                                                \
+	do {                                                               \
+		if (unlikely(drm_debug & DRM_UT_KMS))                      \
+			DRM_DEBUG(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+/**
+ * DPU_DEBUG_DRIVER - macro for hardware driver logging
+ * @fmt: Pointer to format string
+ */
+#define DPU_DEBUG_DRIVER(fmt, ...)                                         \
+	do {                                                               \
+		if (unlikely(drm_debug & DRM_UT_DRIVER))                   \
+			DRM_ERROR(fmt, ##__VA_ARGS__); \
+		else                                                       \
+			pr_debug(fmt, ##__VA_ARGS__);                      \
+	} while (0)
+
+#define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
+
+/**
+ * ktime_compare_safe - compare two ktime structures
+ *	This macro is similar to the standard ktime_compare() function, but
+ *	attempts to also handle ktime overflows.
+ * @A: First ktime value
+ * @B: Second ktime value
+ * Returns: -1 if A < B, 0 if A == B, 1 if A > B
+ */
+#define ktime_compare_safe(A, B) \
+	ktime_compare(ktime_sub((A), (B)), ktime_set(0, 0))
+
+#define DPU_NAME_SIZE  12
+
+/* timeout in frames waiting for frame done */
+#define DPU_FRAME_DONE_TIMEOUT	60
+
+/*
+ * struct dpu_irq_callback - IRQ callback handlers
+ * @list: list to callback
+ * @func: intr handler
+ * @arg: argument for the handler
+ */
+struct dpu_irq_callback {
+	struct list_head list;
+	void (*func)(void *arg, int irq_idx);
+	void *arg;
+};
+
+/**
+ * struct dpu_irq: IRQ structure contains callback registration info
+ * @total_irq:    total number of irq_idx obtained from HW interrupts mapping
+ * @irq_cb_tbl:   array of IRQ callbacks setting
+ * @enable_counts array of IRQ enable counts
+ * @cb_lock:      callback lock
+ * @debugfs_file: debugfs file for irq statistics
+ */
+struct dpu_irq {
+	u32 total_irqs;
+	struct list_head *irq_cb_tbl;
+	atomic_t *enable_counts;
+	atomic_t *irq_counts;
+	spinlock_t cb_lock;
+	struct dentry *debugfs_file;
+};
+
+struct dpu_kms {
+	struct msm_kms base;
+	struct drm_device *dev;
+	int core_rev;
+	struct dpu_mdss_cfg *catalog;
+
+	struct dpu_power_handle phandle;
+	struct dpu_power_client *core_client;
+	struct dpu_power_event *power_event;
+
+	/* directory entry for debugfs */
+	struct dentry *debugfs_root;
+	struct dentry *debugfs_danger;
+	struct dentry *debugfs_vbif;
+
+	/* io/register spaces: */
+	void __iomem *mmio, *vbif[VBIF_MAX], *reg_dma;
+	unsigned long mmio_len, vbif_len[VBIF_MAX], reg_dma_len;
+
+	struct regulator *vdd;
+	struct regulator *mmagic;
+	struct regulator *venus;
+
+	struct dpu_hw_intr *hw_intr;
+	struct dpu_irq irq_obj;
+
+	struct dpu_core_perf perf;
+
+	/* saved atomic state during system suspend */
+	struct drm_atomic_state *suspend_state;
+	bool suspend_block;
+
+	struct dpu_rm rm;
+	bool rm_init;
+
+	struct dpu_hw_vbif *hw_vbif[VBIF_MAX];
+	struct dpu_hw_mdp *hw_mdp;
+
+	bool has_danger_ctrl;
+
+	struct platform_device *pdev;
+	bool rpm_enabled;
+	struct dss_module_power mp;
+};
+
+struct vsync_info {
+	u32 frame_count;
+	u32 line_count;
+};
+
+#define to_dpu_kms(x) container_of(x, struct dpu_kms, base)
+
+/* get struct msm_kms * from drm_device * */
+#define ddev_to_msm_kms(D) ((D) && (D)->dev_private ? \
+		((struct msm_drm_private *)((D)->dev_private))->kms : NULL)
+
+/**
+ * dpu_kms_is_suspend_state - whether or not the system is pm suspended
+ * @dev: Pointer to drm device
+ * Return: Suspend status
+ */
+static inline bool dpu_kms_is_suspend_state(struct drm_device *dev)
+{
+	if (!ddev_to_msm_kms(dev))
+		return false;
+
+	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_state != NULL;
+}
+
+/**
+ * dpu_kms_is_suspend_blocked - whether or not commits are blocked due to pm
+ *				suspend status
+ * @dev: Pointer to drm device
+ * Return: True if commits should be rejected due to pm suspend
+ */
+static inline bool dpu_kms_is_suspend_blocked(struct drm_device *dev)
+{
+	if (!dpu_kms_is_suspend_state(dev))
+		return false;
+
+	return to_dpu_kms(ddev_to_msm_kms(dev))->suspend_block;
+}
+
+/**
+ * Debugfs functions - extra helper functions for debugfs support
+ *
+ * Main debugfs documentation is located at,
+ *
+ * Documentation/filesystems/debugfs.txt
+ *
+ * @dpu_debugfs_setup_regset32: Initialize data for dpu_debugfs_create_regset32
+ * @dpu_debugfs_create_regset32: Create 32-bit register dump file
+ * @dpu_debugfs_get_root: Get root dentry for DPU_KMS's debugfs node
+ */
+
+/**
+ * Companion structure for dpu_debugfs_create_regset32. Do not initialize the
+ * members of this structure explicitly; use dpu_debugfs_setup_regset32 instead.
+ */
+struct dpu_debugfs_regset32 {
+	uint32_t offset;
+	uint32_t blk_len;
+	struct dpu_kms *dpu_kms;
+};
+
+/**
+ * dpu_debugfs_setup_regset32 - Initialize register block definition for debugfs
+ * This function is meant to initialize dpu_debugfs_regset32 structures for use
+ * with dpu_debugfs_create_regset32.
+ * @regset: opaque register definition structure
+ * @offset: sub-block offset
+ * @length: sub-block length, in bytes
+ * @dpu_kms: pointer to dpu kms structure
+ */
+void dpu_debugfs_setup_regset32(struct dpu_debugfs_regset32 *regset,
+		uint32_t offset, uint32_t length, struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_debugfs_create_regset32 - Create register read back file for debugfs
+ *
+ * This function is almost identical to the standard debugfs_create_regset32()
+ * function, with the main difference being that a list of register
+ * names/offsets do not need to be provided. The 'read' function simply outputs
+ * sequential register values over a specified range.
+ *
+ * Similar to the related debugfs_create_regset32 API, the structure pointed to
+ * by regset needs to persist for the lifetime of the created file. The calling
+ * code is responsible for initialization/management of this structure.
+ *
+ * The structure pointed to by regset is meant to be opaque. Please use
+ * dpu_debugfs_setup_regset32 to initialize it.
+ *
+ * @name:   File name within debugfs
+ * @mode:   File mode within debugfs
+ * @parent: Parent directory entry within debugfs, can be NULL
+ * @regset: Pointer to persistent register block definition
+ *
+ * Return: dentry pointer for newly created file, use either debugfs_remove()
+ *         or debugfs_remove_recursive() (on a parent directory) to remove the
+ *         file
+ */
+void *dpu_debugfs_create_regset32(const char *name, umode_t mode,
+		void *parent, struct dpu_debugfs_regset32 *regset);
+
+/**
+ * dpu_debugfs_get_root - Return root directory entry for KMS's debugfs
+ *
+ * The return value should be passed as the 'parent' argument to subsequent
+ * debugfs create calls.
+ *
+ * @dpu_kms: Pointer to DPU's KMS structure
+ *
+ * Return: dentry pointer for DPU's debugfs location
+ */
+void *dpu_debugfs_get_root(struct dpu_kms *dpu_kms);
+
+/**
+ * DPU info management functions
+ * These functions/definitions allow for building up a 'dpu_info' structure
+ * containing one or more "key=value\n" entries.
+ */
+#define DPU_KMS_INFO_MAX_SIZE	4096
+
+/**
+ * struct dpu_kms_info - connector information structure container
+ * @data: Array of information character data
+ * @len: Current length of information data
+ * @staged_len: Temporary data buffer length, commit to
+ *              len using dpu_kms_info_stop
+ * @start: Whether or not a partial data entry was just started
+ */
+struct dpu_kms_info {
+	char data[DPU_KMS_INFO_MAX_SIZE];
+	uint32_t len;
+	uint32_t staged_len;
+	bool start;
+};
+
+/**
+ * DPU_KMS_INFO_DATA - Macro for accessing dpu_kms_info data bytes
+ * @S: Pointer to dpu_kms_info structure
+ * Returns: Pointer to byte data
+ */
+#define DPU_KMS_INFO_DATA(S)    ((S) ? ((struct dpu_kms_info *)(S))->data : 0)
+
+/**
+ * DPU_KMS_INFO_DATALEN - Macro for accessing dpu_kms_info data length
+ *			it adds an extra character length to count null.
+ * @S: Pointer to dpu_kms_info structure
+ * Returns: Size of available byte data
+ */
+#define DPU_KMS_INFO_DATALEN(S) ((S) ? ((struct dpu_kms_info *)(S))->len + 1 \
+							: 0)
+
+/**
+ * dpu_kms_info_reset - reset dpu_kms_info structure
+ * @info: Pointer to dpu_kms_info structure
+ */
+void dpu_kms_info_reset(struct dpu_kms_info *info);
+
+/**
+ * dpu_kms_info_add_keyint - add integer value to 'dpu_kms_info'
+ * @info: Pointer to dpu_kms_info structure
+ * @key: Pointer to key string
+ * @value: Signed 64-bit integer value
+ */
+void dpu_kms_info_add_keyint(struct dpu_kms_info *info,
+		const char *key,
+		int64_t value);
+
+/**
+ * dpu_kms_info_add_keystr - add string value to 'dpu_kms_info'
+ * @info: Pointer to dpu_kms_info structure
+ * @key: Pointer to key string
+ * @value: Pointer to string value
+ */
+void dpu_kms_info_add_keystr(struct dpu_kms_info *info,
+		const char *key,
+		const char *value);
+
+/**
+ * dpu_kms_info_start - begin adding key to 'dpu_kms_info'
+ * Usage:
+ *      dpu_kms_info_start(key)
+ *      dpu_kms_info_append(val_1)
+ *      ...
+ *      dpu_kms_info_append(val_n)
+ *      dpu_kms_info_stop
+ * @info: Pointer to dpu_kms_info structure
+ * @key: Pointer to key string
+ */
+void dpu_kms_info_start(struct dpu_kms_info *info,
+		const char *key);
+
+/**
+ * dpu_kms_info_append - append value string to 'dpu_kms_info'
+ * Usage:
+ *      dpu_kms_info_start(key)
+ *      dpu_kms_info_append(val_1)
+ *      ...
+ *      dpu_kms_info_append(val_n)
+ *      dpu_kms_info_stop
+ * @info: Pointer to dpu_kms_info structure
+ * @str: Pointer to partial value string
+ */
+void dpu_kms_info_append(struct dpu_kms_info *info,
+		const char *str);
+
+/**
+ * dpu_kms_info_append_format - append format code string to 'dpu_kms_info'
+ * Usage:
+ *      dpu_kms_info_start(key)
+ *      dpu_kms_info_append_format(fourcc, modifier)
+ *      ...
+ *      dpu_kms_info_stop
+ * @info: Pointer to dpu_kms_info structure
+ * @pixel_format: FOURCC format code
+ * @modifier: 64-bit drm format modifier
+ */
+void dpu_kms_info_append_format(struct dpu_kms_info *info,
+		uint32_t pixel_format,
+		uint64_t modifier);
+
+/**
+ * dpu_kms_info_stop - finish adding key to 'dpu_kms_info'
+ * Usage:
+ *      dpu_kms_info_start(key)
+ *      dpu_kms_info_append(val_1)
+ *      ...
+ *      dpu_kms_info_append(val_n)
+ *      dpu_kms_info_stop
+ * @info: Pointer to dpu_kms_info structure
+ */
+void dpu_kms_info_stop(struct dpu_kms_info *info);
+
+/**
+ * Vblank enable/disable functions
+ */
+int dpu_enable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+void dpu_disable_vblank(struct msm_kms *kms, struct drm_crtc *crtc);
+
+void dpu_kms_encoder_enable(struct drm_encoder *encoder);
+
+/**
+ * dpu_kms_get_clk_rate() - get the clock rate
+ * @dpu_kms:  poiner to dpu_kms structure
+ * @clock_name: clock name to get the rate
+ *
+ * Return: current clock rate
+ */
+u64 dpu_kms_get_clk_rate(struct dpu_kms *dpu_kms, char *clock_name);
+
+#endif /* __dpu_kms_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c
new file mode 100644
index 000000000000..a80b3da5a9fe
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c
@@ -0,0 +1,153 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"dpu-kms_utils:[%s] " fmt, __func__
+
+#include "dpu_kms.h"
+
+void dpu_kms_info_reset(struct dpu_kms_info *info)
+{
+	if (info) {
+		info->len = 0;
+		info->staged_len = 0;
+	}
+}
+
+void dpu_kms_info_add_keyint(struct dpu_kms_info *info,
+		const char *key,
+		int64_t value)
+{
+	uint32_t len;
+
+	if (info && key) {
+		len = snprintf(info->data + info->len,
+				DPU_KMS_INFO_MAX_SIZE - info->len,
+				"%s=%lld\n",
+				key,
+				value);
+
+		/* check if snprintf truncated the string */
+		if ((info->len + len) < DPU_KMS_INFO_MAX_SIZE)
+			info->len += len;
+	}
+}
+
+void dpu_kms_info_add_keystr(struct dpu_kms_info *info,
+		const char *key,
+		const char *value)
+{
+	uint32_t len;
+
+	if (info && key && value) {
+		len = snprintf(info->data + info->len,
+				DPU_KMS_INFO_MAX_SIZE - info->len,
+				"%s=%s\n",
+				key,
+				value);
+
+		/* check if snprintf truncated the string */
+		if ((info->len + len) < DPU_KMS_INFO_MAX_SIZE)
+			info->len += len;
+	}
+}
+
+void dpu_kms_info_start(struct dpu_kms_info *info,
+		const char *key)
+{
+	uint32_t len;
+
+	if (info && key) {
+		len = snprintf(info->data + info->len,
+				DPU_KMS_INFO_MAX_SIZE - info->len,
+				"%s=",
+				key);
+
+		info->start = true;
+
+		/* check if snprintf truncated the string */
+		if ((info->len + len) < DPU_KMS_INFO_MAX_SIZE)
+			info->staged_len = info->len + len;
+	}
+}
+
+void dpu_kms_info_append(struct dpu_kms_info *info,
+		const char *str)
+{
+	uint32_t len;
+
+	if (info) {
+		len = snprintf(info->data + info->staged_len,
+				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
+				"%s",
+				str);
+
+		/* check if snprintf truncated the string */
+		if ((info->staged_len + len) < DPU_KMS_INFO_MAX_SIZE) {
+			info->staged_len += len;
+			info->start = false;
+		}
+	}
+}
+
+void dpu_kms_info_append_format(struct dpu_kms_info *info,
+		uint32_t pixel_format,
+		uint64_t modifier)
+{
+	uint32_t len;
+
+	if (!info)
+		return;
+
+	if (modifier) {
+		len = snprintf(info->data + info->staged_len,
+				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
+				info->start ?
+				"%c%c%c%c/%llX/%llX" : " %c%c%c%c/%llX/%llX",
+				(pixel_format >> 0) & 0xFF,
+				(pixel_format >> 8) & 0xFF,
+				(pixel_format >> 16) & 0xFF,
+				(pixel_format >> 24) & 0xFF,
+				(modifier >> 56) & 0xFF,
+				modifier & ((1ULL << 56) - 1));
+	} else {
+		len = snprintf(info->data + info->staged_len,
+				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
+				info->start ?
+				"%c%c%c%c" : " %c%c%c%c",
+				(pixel_format >> 0) & 0xFF,
+				(pixel_format >> 8) & 0xFF,
+				(pixel_format >> 16) & 0xFF,
+				(pixel_format >> 24) & 0xFF);
+	}
+
+	/* check if snprintf truncated the string */
+	if ((info->staged_len + len) < DPU_KMS_INFO_MAX_SIZE) {
+		info->staged_len += len;
+		info->start = false;
+	}
+}
+
+void dpu_kms_info_stop(struct dpu_kms_info *info)
+{
+	uint32_t len;
+
+	if (info) {
+		/* insert final delimiter */
+		len = snprintf(info->data + info->staged_len,
+				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
+				"\n");
+
+		/* check if snprintf truncated the string */
+		if ((info->staged_len + len) < DPU_KMS_INFO_MAX_SIZE)
+			info->len = info->staged_len + len;
+	}
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
new file mode 100644
index 000000000000..6dfc26698a09
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -0,0 +1,245 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ * Copyright (c) 2018, The Linux Foundation
+ */
+
+#include "dpu_kms.h"
+
+#define to_dpu_mdss(x) container_of(x, struct dpu_mdss, base)
+
+#define HW_INTR_STATUS			0x0010
+
+struct dpu_mdss {
+	struct msm_mdss base;
+	void __iomem *mmio;
+	unsigned long mmio_len;
+	u32 hwversion;
+	struct dss_module_power mp;
+	struct dpu_irq_controller irq_controller;
+};
+
+static irqreturn_t dpu_mdss_irq(int irq, void *arg)
+{
+	struct dpu_mdss *dpu_mdss = arg;
+	u32 interrupts;
+
+	interrupts = readl_relaxed(dpu_mdss->mmio + HW_INTR_STATUS);
+
+	while (interrupts) {
+		irq_hw_number_t hwirq = fls(interrupts) - 1;
+		unsigned int mapping;
+		int rc;
+
+		mapping = irq_find_mapping(dpu_mdss->irq_controller.domain,
+					   hwirq);
+		if (mapping == 0) {
+			DRM_ERROR("couldn't find irq mapping for %lu\n", hwirq);
+			return IRQ_NONE;
+		}
+
+		rc = generic_handle_irq(mapping);
+		if (rc < 0) {
+			DRM_ERROR("handle irq fail: irq=%lu mapping=%u rc=%d\n",
+				  hwirq, mapping, rc);
+			return IRQ_NONE;
+		}
+
+		interrupts &= ~(1 << hwirq);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static void dpu_mdss_irq_mask(struct irq_data *irqd)
+{
+	struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd);
+
+	/* memory barrier */
+	smp_mb__before_atomic();
+	clear_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask);
+	/* memory barrier */
+	smp_mb__after_atomic();
+}
+
+static void dpu_mdss_irq_unmask(struct irq_data *irqd)
+{
+	struct dpu_mdss *dpu_mdss = irq_data_get_irq_chip_data(irqd);
+
+	/* memory barrier */
+	smp_mb__before_atomic();
+	set_bit(irqd->hwirq, &dpu_mdss->irq_controller.enabled_mask);
+	/* memory barrier */
+	smp_mb__after_atomic();
+}
+
+static struct irq_chip dpu_mdss_irq_chip = {
+	.name = "dpu_mdss",
+	.irq_mask = dpu_mdss_irq_mask,
+	.irq_unmask = dpu_mdss_irq_unmask,
+};
+
+static int dpu_mdss_irqdomain_map(struct irq_domain *domain,
+		unsigned int irq, irq_hw_number_t hwirq)
+{
+	struct dpu_mdss *dpu_mdss = domain->host_data;
+	int ret;
+
+	irq_set_chip_and_handler(irq, &dpu_mdss_irq_chip, handle_level_irq);
+	ret = irq_set_chip_data(irq, dpu_mdss);
+
+	return ret;
+}
+
+static const struct irq_domain_ops dpu_mdss_irqdomain_ops = {
+	.map = dpu_mdss_irqdomain_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int _dpu_mdss_irq_domain_add(struct dpu_mdss *dpu_mdss)
+{
+	struct device *dev;
+	struct irq_domain *domain;
+
+	dev = dpu_mdss->base.dev->dev;
+
+	domain = irq_domain_add_linear(dev->of_node, 32,
+			&dpu_mdss_irqdomain_ops, dpu_mdss);
+	if (!domain) {
+		DPU_ERROR("failed to add irq_domain\n");
+		return -EINVAL;
+	}
+
+	dpu_mdss->irq_controller.enabled_mask = 0;
+	dpu_mdss->irq_controller.domain = domain;
+
+	return 0;
+}
+
+int _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss)
+{
+	if (dpu_mdss->irq_controller.domain) {
+		irq_domain_remove(dpu_mdss->irq_controller.domain);
+		dpu_mdss->irq_controller.domain = NULL;
+	}
+	return 0;
+}
+static int dpu_mdss_enable(struct msm_mdss *mdss)
+{
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+	int ret;
+
+	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, true);
+	if (ret)
+		DPU_ERROR("clock enable failed, ret:%d\n", ret);
+
+	return ret;
+}
+
+static int dpu_mdss_disable(struct msm_mdss *mdss)
+{
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+	int ret;
+
+	ret = msm_dss_enable_clk(mp->clk_config, mp->num_clk, false);
+	if (ret)
+		DPU_ERROR("clock disable failed, ret:%d\n", ret);
+
+	return ret;
+}
+
+static void dpu_mdss_destroy(struct drm_device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev->dev);
+	struct msm_drm_private *priv = dev->dev_private;
+	struct dpu_mdss *dpu_mdss = to_dpu_mdss(priv->mdss);
+	struct dss_module_power *mp = &dpu_mdss->mp;
+
+	_dpu_mdss_irq_domain_fini(dpu_mdss);
+
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+	devm_kfree(&pdev->dev, mp->clk_config);
+
+	if (dpu_mdss->mmio)
+		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
+	dpu_mdss->mmio = NULL;
+
+	pm_runtime_disable(dev->dev);
+	priv->mdss = NULL;
+}
+
+static const struct msm_mdss_funcs mdss_funcs = {
+	.enable	= dpu_mdss_enable,
+	.disable = dpu_mdss_disable,
+	.destroy = dpu_mdss_destroy,
+};
+
+int dpu_mdss_init(struct drm_device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev->dev);
+	struct msm_drm_private *priv = dev->dev_private;
+	struct resource *res;
+	struct dpu_mdss *dpu_mdss;
+	struct dss_module_power *mp;
+	int ret = 0;
+
+	dpu_mdss = devm_kzalloc(dev->dev, sizeof(*dpu_mdss), GFP_KERNEL);
+	if (!dpu_mdss)
+		return -ENOMEM;
+
+	dpu_mdss->mmio = msm_ioremap(pdev, "mdss", "mdss");
+	if (IS_ERR(dpu_mdss->mmio))
+		return PTR_ERR(dpu_mdss->mmio);
+
+	DRM_DEBUG("mapped mdss address space @%pK\n", dpu_mdss->mmio);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mdss");
+	if (!res) {
+		DRM_ERROR("failed to get memory resource for mdss\n");
+		return -ENOMEM;
+	}
+	dpu_mdss->mmio_len = resource_size(res);
+
+	mp = &dpu_mdss->mp;
+	ret = msm_dss_parse_clock(pdev, mp);
+	if (ret) {
+		DPU_ERROR("failed to parse clocks, ret=%d\n", ret);
+		goto clk_parse_err;
+	}
+
+	dpu_mdss->base.dev = dev;
+	dpu_mdss->base.funcs = &mdss_funcs;
+
+	ret = _dpu_mdss_irq_domain_add(dpu_mdss);
+	if (ret)
+		goto irq_domain_error;
+
+	ret = devm_request_irq(dev->dev, platform_get_irq(pdev, 0),
+			dpu_mdss_irq, 0, "dpu_mdss_isr", dpu_mdss);
+	if (ret) {
+		DPU_ERROR("failed to init irq: %d\n", ret);
+		goto irq_error;
+	}
+
+	pm_runtime_enable(dev->dev);
+
+	pm_runtime_get_sync(dev->dev);
+	dpu_mdss->hwversion = readl_relaxed(dpu_mdss->mmio);
+	pm_runtime_put_sync(dev->dev);
+
+	priv->mdss = &dpu_mdss->base;
+
+	return ret;
+
+irq_error:
+	_dpu_mdss_irq_domain_fini(dpu_mdss);
+irq_domain_error:
+	msm_dss_put_clk(mp->clk_config, mp->num_clk);
+clk_parse_err:
+	devm_kfree(&pdev->dev, mp->clk_config);
+	if (dpu_mdss->mmio)
+		devm_iounmap(&pdev->dev, dpu_mdss->mmio);
+	dpu_mdss->mmio = NULL;
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
new file mode 100644
index 000000000000..b640e39ebaca
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -0,0 +1,1963 @@
+/*
+ * Copyright (C) 2014-2018 The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+#include <linux/dma-buf.h>
+
+#include "msm_drv.h"
+#include "dpu_kms.h"
+#include "dpu_formats.h"
+#include "dpu_hw_sspp.h"
+#include "dpu_hw_catalog_format.h"
+#include "dpu_trace.h"
+#include "dpu_crtc.h"
+#include "dpu_vbif.h"
+#include "dpu_plane.h"
+
+#define DPU_DEBUG_PLANE(pl, fmt, ...) DPU_DEBUG("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DPU_ERROR_PLANE(pl, fmt, ...) DPU_ERROR("plane%d " fmt,\
+		(pl) ? (pl)->base.base.id : -1, ##__VA_ARGS__)
+
+#define DECIMATED_DIMENSION(dim, deci) (((dim) + ((1 << (deci)) - 1)) >> (deci))
+#define PHASE_STEP_SHIFT	21
+#define PHASE_STEP_UNIT_SCALE   ((int) (1 << PHASE_STEP_SHIFT))
+#define PHASE_RESIDUAL		15
+
+#define SHARP_STRENGTH_DEFAULT	32
+#define SHARP_EDGE_THR_DEFAULT	112
+#define SHARP_SMOOTH_THR_DEFAULT	8
+#define SHARP_NOISE_THR_DEFAULT	2
+
+#define DPU_NAME_SIZE  12
+
+#define DPU_PLANE_COLOR_FILL_FLAG	BIT(31)
+#define DPU_ZPOS_MAX 255
+
+/* multirect rect index */
+enum {
+	R0,
+	R1,
+	R_MAX
+};
+
+#define DPU_QSEED3_DEFAULT_PRELOAD_H 0x4
+#define DPU_QSEED3_DEFAULT_PRELOAD_V 0x3
+
+#define DEFAULT_REFRESH_RATE	60
+
+/**
+ * enum dpu_plane_qos - Different qos configurations for each pipe
+ *
+ * @DPU_PLANE_QOS_VBLANK_CTRL: Setup VBLANK qos for the pipe.
+ * @DPU_PLANE_QOS_VBLANK_AMORTIZE: Enables Amortization within pipe.
+ *	this configuration is mutually exclusive from VBLANK_CTRL.
+ * @DPU_PLANE_QOS_PANIC_CTRL: Setup panic for the pipe.
+ */
+enum dpu_plane_qos {
+	DPU_PLANE_QOS_VBLANK_CTRL = BIT(0),
+	DPU_PLANE_QOS_VBLANK_AMORTIZE = BIT(1),
+	DPU_PLANE_QOS_PANIC_CTRL = BIT(2),
+};
+
+/*
+ * struct dpu_plane - local dpu plane structure
+ * @aspace: address space pointer
+ * @csc_ptr: Points to dpu_csc_cfg structure to use for current
+ * @mplane_list: List of multirect planes of the same pipe
+ * @catalog: Points to dpu catalog structure
+ * @revalidate: force revalidation of all the plane properties
+ */
+struct dpu_plane {
+	struct drm_plane base;
+
+	struct mutex lock;
+
+	enum dpu_sspp pipe;
+	uint32_t features;      /* capabilities from catalog */
+	uint32_t nformats;
+	uint32_t formats[64];
+
+	struct dpu_hw_pipe *pipe_hw;
+	struct dpu_hw_pipe_cfg pipe_cfg;
+	struct dpu_hw_pipe_qos_cfg pipe_qos_cfg;
+	uint32_t color_fill;
+	bool is_error;
+	bool is_rt_pipe;
+	bool is_virtual;
+	struct list_head mplane_list;
+	struct dpu_mdss_cfg *catalog;
+
+	struct dpu_csc_cfg *csc_ptr;
+
+	const struct dpu_sspp_sub_blks *pipe_sblk;
+	char pipe_name[DPU_NAME_SIZE];
+
+	/* debugfs related stuff */
+	struct dentry *debugfs_root;
+	struct dpu_debugfs_regset32 debugfs_src;
+	struct dpu_debugfs_regset32 debugfs_scaler;
+	struct dpu_debugfs_regset32 debugfs_csc;
+	bool debugfs_default_scale;
+};
+
+#define to_dpu_plane(x) container_of(x, struct dpu_plane, base)
+
+static struct dpu_kms *_dpu_plane_get_kms(struct drm_plane *plane)
+{
+	struct msm_drm_private *priv;
+
+	if (!plane || !plane->dev)
+		return NULL;
+	priv = plane->dev->dev_private;
+	if (!priv)
+		return NULL;
+	return to_dpu_kms(priv->kms);
+}
+
+static bool dpu_plane_enabled(struct drm_plane_state *state)
+{
+	return state && state->fb && state->crtc;
+}
+
+static bool dpu_plane_sspp_enabled(struct drm_plane_state *state)
+{
+	return state && state->crtc;
+}
+
+/**
+ * _dpu_plane_calc_fill_level - calculate fill level of the given source format
+ * @plane:		Pointer to drm plane
+ * @fmt:		Pointer to source buffer format
+ * @src_wdith:		width of source buffer
+ * Return: fill level corresponding to the source buffer/format or 0 if error
+ */
+static inline int _dpu_plane_calc_fill_level(struct drm_plane *plane,
+		const struct dpu_format *fmt, u32 src_width)
+{
+	struct dpu_plane *pdpu, *tmp;
+	struct dpu_plane_state *pstate;
+	u32 fixed_buff_size;
+	u32 total_fl;
+
+	if (!plane || !fmt || !plane->state || !src_width || !fmt->bpp) {
+		DPU_ERROR("invalid arguments\n");
+		return 0;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+	fixed_buff_size = pdpu->pipe_sblk->common->pixel_ram_size;
+
+	list_for_each_entry(tmp, &pdpu->mplane_list, mplane_list) {
+		if (!dpu_plane_enabled(tmp->base.state))
+			continue;
+		DPU_DEBUG("plane%d/%d src_width:%d/%d\n",
+				pdpu->base.base.id, tmp->base.base.id,
+				src_width,
+				drm_rect_width(&tmp->pipe_cfg.src_rect));
+		src_width = max_t(u32, src_width,
+				  drm_rect_width(&tmp->pipe_cfg.src_rect));
+	}
+
+	if (fmt->fetch_planes == DPU_PLANE_PSEUDO_PLANAR) {
+		if (fmt->chroma_sample == DPU_CHROMA_420) {
+			/* NV12 */
+			total_fl = (fixed_buff_size / 2) /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			/* non NV12 */
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	} else {
+		if (pstate->multirect_mode == DPU_SSPP_MULTIRECT_PARALLEL) {
+			total_fl = (fixed_buff_size / 2) * 2 /
+				((src_width + 32) * fmt->bpp);
+		} else {
+			total_fl = (fixed_buff_size) * 2 /
+				((src_width + 32) * fmt->bpp);
+		}
+	}
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s w:%u fl:%u\n",
+			plane->base.id, pdpu->pipe - SSPP_VIG0,
+			(char *)&fmt->base.pixel_format,
+			src_width, total_fl);
+
+	return total_fl;
+}
+
+/**
+ * _dpu_plane_get_qos_lut - get LUT mapping based on fill level
+ * @tbl:		Pointer to LUT table
+ * @total_fl:		fill level
+ * Return: LUT setting corresponding to the fill level
+ */
+static u64 _dpu_plane_get_qos_lut(const struct dpu_qos_lut_tbl *tbl,
+		u32 total_fl)
+{
+	int i;
+
+	if (!tbl || !tbl->nentry || !tbl->entries)
+		return 0;
+
+	for (i = 0; i < tbl->nentry; i++)
+		if (total_fl <= tbl->entries[i].fl)
+			return tbl->entries[i].lut;
+
+	/* if last fl is zero, use as default */
+	if (!tbl->entries[i-1].fl)
+		return tbl->entries[i-1].lut;
+
+	return 0;
+}
+
+/**
+ * _dpu_plane_set_qos_lut - set QoS LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ */
+static void _dpu_plane_set_qos_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	const struct dpu_format *fmt = NULL;
+	u64 qos_lut;
+	u32 total_fl = 0, lut_usage;
+
+	if (!plane || !fb) {
+		DPU_ERROR("invalid arguments plane %d fb %d\n",
+				plane != 0, fb != 0);
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_creq_lut) {
+		return;
+	}
+
+	if (!pdpu->is_rt_pipe) {
+		lut_usage = DPU_QOS_LUT_USAGE_NRT;
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+		total_fl = _dpu_plane_calc_fill_level(plane, fmt,
+				drm_rect_width(&pdpu->pipe_cfg.src_rect));
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt))
+			lut_usage = DPU_QOS_LUT_USAGE_LINEAR;
+		else
+			lut_usage = DPU_QOS_LUT_USAGE_MACROTILE;
+	}
+
+	qos_lut = _dpu_plane_get_qos_lut(
+			&pdpu->catalog->perf.qos_lut_tbl[lut_usage], total_fl);
+
+	pdpu->pipe_qos_cfg.creq_lut = qos_lut;
+
+	trace_dpu_perf_set_qos_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			pdpu->is_rt_pipe, total_fl, qos_lut, lut_usage);
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s rt:%d fl:%u lut:0x%llx\n",
+			plane->base.id,
+			pdpu->pipe - SSPP_VIG0,
+			fmt ? (char *)&fmt->base.pixel_format : NULL,
+			pdpu->is_rt_pipe, total_fl, qos_lut);
+
+	pdpu->pipe_hw->ops.setup_creq_lut(pdpu->pipe_hw, &pdpu->pipe_qos_cfg);
+}
+
+/**
+ * _dpu_plane_set_panic_lut - set danger/safe LUT of the given plane
+ * @plane:		Pointer to drm plane
+ * @fb:			Pointer to framebuffer associated with the given plane
+ */
+static void _dpu_plane_set_danger_lut(struct drm_plane *plane,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	const struct dpu_format *fmt = NULL;
+	u32 danger_lut, safe_lut;
+
+	if (!plane || !fb) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk || !pdpu->catalog) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_danger_safe_lut) {
+		return;
+	}
+
+	if (!pdpu->is_rt_pipe) {
+		danger_lut = pdpu->catalog->perf.danger_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+		safe_lut = pdpu->catalog->perf.safe_lut_tbl
+				[DPU_QOS_LUT_USAGE_NRT];
+	} else {
+		fmt = dpu_get_dpu_format_ext(
+				fb->format->format,
+				fb->modifier);
+
+		if (fmt && DPU_FORMAT_IS_LINEAR(fmt)) {
+			danger_lut = pdpu->catalog->perf.danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+			safe_lut = pdpu->catalog->perf.safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_LINEAR];
+		} else {
+			danger_lut = pdpu->catalog->perf.danger_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+			safe_lut = pdpu->catalog->perf.safe_lut_tbl
+					[DPU_QOS_LUT_USAGE_MACROTILE];
+		}
+	}
+
+	pdpu->pipe_qos_cfg.danger_lut = danger_lut;
+	pdpu->pipe_qos_cfg.safe_lut = safe_lut;
+
+	trace_dpu_perf_set_danger_luts(pdpu->pipe - SSPP_VIG0,
+			(fmt) ? fmt->base.pixel_format : 0,
+			(fmt) ? fmt->fetch_mode : 0,
+			pdpu->pipe_qos_cfg.danger_lut,
+			pdpu->pipe_qos_cfg.safe_lut);
+
+	DPU_DEBUG("plane%u: pnum:%d fmt: %4.4s mode:%d luts[0x%x, 0x%x]\n",
+		plane->base.id,
+		pdpu->pipe - SSPP_VIG0,
+		fmt ? (char *)&fmt->base.pixel_format : NULL,
+		fmt ? fmt->fetch_mode : -1,
+		pdpu->pipe_qos_cfg.danger_lut,
+		pdpu->pipe_qos_cfg.safe_lut);
+
+	pdpu->pipe_hw->ops.setup_danger_safe_lut(pdpu->pipe_hw,
+			&pdpu->pipe_qos_cfg);
+}
+
+/**
+ * _dpu_plane_set_qos_ctrl - set QoS control of the given plane
+ * @plane:		Pointer to drm plane
+ * @enable:		true to enable QoS control
+ * @flags:		QoS control mode (enum dpu_plane_qos)
+ */
+static void _dpu_plane_set_qos_ctrl(struct drm_plane *plane,
+	bool enable, u32 flags)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->pipe_hw || !pdpu->pipe_sblk) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	} else if (!pdpu->pipe_hw->ops.setup_qos_ctrl) {
+		return;
+	}
+
+	if (flags & DPU_PLANE_QOS_VBLANK_CTRL) {
+		pdpu->pipe_qos_cfg.creq_vblank = pdpu->pipe_sblk->creq_vblank;
+		pdpu->pipe_qos_cfg.danger_vblank =
+				pdpu->pipe_sblk->danger_vblank;
+		pdpu->pipe_qos_cfg.vblank_en = enable;
+	}
+
+	if (flags & DPU_PLANE_QOS_VBLANK_AMORTIZE) {
+		/* this feature overrules previous VBLANK_CTRL */
+		pdpu->pipe_qos_cfg.vblank_en = false;
+		pdpu->pipe_qos_cfg.creq_vblank = 0; /* clear vblank bits */
+	}
+
+	if (flags & DPU_PLANE_QOS_PANIC_CTRL)
+		pdpu->pipe_qos_cfg.danger_safe_en = enable;
+
+	if (!pdpu->is_rt_pipe) {
+		pdpu->pipe_qos_cfg.vblank_en = false;
+		pdpu->pipe_qos_cfg.danger_safe_en = false;
+	}
+
+	DPU_DEBUG("plane%u: pnum:%d ds:%d vb:%d pri[0x%x, 0x%x] is_rt:%d\n",
+		plane->base.id,
+		pdpu->pipe - SSPP_VIG0,
+		pdpu->pipe_qos_cfg.danger_safe_en,
+		pdpu->pipe_qos_cfg.vblank_en,
+		pdpu->pipe_qos_cfg.creq_vblank,
+		pdpu->pipe_qos_cfg.danger_vblank,
+		pdpu->is_rt_pipe);
+
+	pdpu->pipe_hw->ops.setup_qos_ctrl(pdpu->pipe_hw,
+			&pdpu->pipe_qos_cfg);
+}
+
+int dpu_plane_danger_signal_ctrl(struct drm_plane *plane, bool enable)
+{
+	struct dpu_plane *pdpu;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+
+	if (!pdpu->is_rt_pipe)
+		goto end;
+
+	pm_runtime_get_sync(&dpu_kms->pdev->dev);
+	_dpu_plane_set_qos_ctrl(plane, enable, DPU_PLANE_QOS_PANIC_CTRL);
+	pm_runtime_put_sync(&dpu_kms->pdev->dev);
+
+end:
+	return 0;
+}
+
+/**
+ * _dpu_plane_set_ot_limit - set OT limit for the given plane
+ * @plane:		Pointer to drm plane
+ * @crtc:		Pointer to drm crtc
+ */
+static void _dpu_plane_set_ot_limit(struct drm_plane *plane,
+		struct drm_crtc *crtc)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_vbif_set_ot_params ot_params;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev || !crtc) {
+		DPU_ERROR("invalid arguments plane %d crtc %d\n",
+				plane != 0, crtc != 0);
+		return;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR("invalid pipe reference\n");
+		return;
+	}
+
+	memset(&ot_params, 0, sizeof(ot_params));
+	ot_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	ot_params.num = pdpu->pipe_hw->idx - SSPP_NONE;
+	ot_params.width = drm_rect_width(&pdpu->pipe_cfg.src_rect);
+	ot_params.height = drm_rect_height(&pdpu->pipe_cfg.src_rect);
+	ot_params.is_wfd = !pdpu->is_rt_pipe;
+	ot_params.frame_rate = crtc->mode.vrefresh;
+	ot_params.vbif_idx = VBIF_RT;
+	ot_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	ot_params.rd = true;
+
+	dpu_vbif_set_ot_limit(dpu_kms, &ot_params);
+}
+
+/**
+ * _dpu_plane_set_vbif_qos - set vbif QoS for the given plane
+ * @plane:		Pointer to drm plane
+ */
+static void _dpu_plane_set_qos_remap(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_vbif_set_qos_params qos_params;
+	struct msm_drm_private *priv;
+	struct dpu_kms *dpu_kms;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return;
+	}
+
+	dpu_kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR("invalid pipe reference\n");
+		return;
+	}
+
+	memset(&qos_params, 0, sizeof(qos_params));
+	qos_params.vbif_idx = VBIF_RT;
+	qos_params.clk_ctrl = pdpu->pipe_hw->cap->clk_ctrl;
+	qos_params.xin_id = pdpu->pipe_hw->cap->xin_id;
+	qos_params.num = pdpu->pipe_hw->idx - SSPP_VIG0;
+	qos_params.is_rt = pdpu->is_rt_pipe;
+
+	DPU_DEBUG("plane%d pipe:%d vbif:%d xin:%d rt:%d, clk_ctrl:%d\n",
+			plane->base.id, qos_params.num,
+			qos_params.vbif_idx,
+			qos_params.xin_id, qos_params.is_rt,
+			qos_params.clk_ctrl);
+
+	dpu_vbif_set_qos_remap(dpu_kms, &qos_params);
+}
+
+/**
+ * _dpu_plane_get_aspace: gets the address space
+ */
+static int _dpu_plane_get_aspace(
+		struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		struct msm_gem_address_space **aspace)
+{
+	struct dpu_kms *kms;
+
+	if (!pdpu || !pstate || !aspace) {
+		DPU_ERROR("invalid parameters\n");
+		return -EINVAL;
+	}
+
+	kms = _dpu_plane_get_kms(&pdpu->base);
+	if (!kms) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	*aspace = kms->base.aspace;
+
+	return 0;
+}
+
+static inline void _dpu_plane_set_scanout(struct drm_plane *plane,
+		struct dpu_plane_state *pstate,
+		struct dpu_hw_pipe_cfg *pipe_cfg,
+		struct drm_framebuffer *fb)
+{
+	struct dpu_plane *pdpu;
+	struct msm_gem_address_space *aspace = NULL;
+	int ret;
+
+	if (!plane || !pstate || !pipe_cfg || !fb) {
+		DPU_ERROR(
+			"invalid arg(s), plane %d state %d cfg %d fb %d\n",
+			plane != 0, pstate != 0, pipe_cfg != 0, fb != 0);
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR_PLANE(pdpu, "invalid pipe_hw\n");
+		return;
+	}
+
+	ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "Failed to get aspace %d\n", ret);
+		return;
+	}
+
+	ret = dpu_format_populate_layout(aspace, fb, &pipe_cfg->layout);
+	if (ret == -EAGAIN)
+		DPU_DEBUG_PLANE(pdpu, "not updating same src addrs\n");
+	else if (ret)
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+	else if (pdpu->pipe_hw->ops.setup_sourceaddress) {
+		trace_dpu_plane_set_scanout(pdpu->pipe_hw->idx,
+					    &pipe_cfg->layout,
+					    pstate->multirect_index);
+		pdpu->pipe_hw->ops.setup_sourceaddress(pdpu->pipe_hw, pipe_cfg,
+						pstate->multirect_index);
+	}
+}
+
+static void _dpu_plane_setup_scaler3(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		uint32_t src_w, uint32_t src_h, uint32_t dst_w, uint32_t dst_h,
+		struct dpu_hw_scaler3_cfg *scale_cfg,
+		const struct dpu_format *fmt,
+		uint32_t chroma_subsmpl_h, uint32_t chroma_subsmpl_v)
+{
+	uint32_t i;
+
+	if (!pdpu || !pstate || !scale_cfg || !fmt || !chroma_subsmpl_h ||
+			!chroma_subsmpl_v) {
+		DPU_ERROR(
+			"pdpu %d pstate %d scale_cfg %d fmt %d smp_h %d smp_v %d\n",
+			!!pdpu, !!pstate, !!scale_cfg, !!fmt, chroma_subsmpl_h,
+			chroma_subsmpl_v);
+		return;
+	}
+
+	memset(scale_cfg, 0, sizeof(*scale_cfg));
+	memset(&pstate->pixel_ext, 0, sizeof(struct dpu_hw_pixel_ext));
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_w, dst_w);
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_0] =
+		mult_frac((1 << PHASE_STEP_SHIFT), src_h, dst_h);
+
+
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0] / chroma_subsmpl_v;
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0] / chroma_subsmpl_h;
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_1_2];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_2] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_1_2];
+
+	scale_cfg->phase_step_x[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_x[DPU_SSPP_COMP_0];
+	scale_cfg->phase_step_y[DPU_SSPP_COMP_3] =
+		scale_cfg->phase_step_y[DPU_SSPP_COMP_0];
+
+	for (i = 0; i < DPU_MAX_PLANES; i++) {
+		scale_cfg->src_width[i] = src_w;
+		scale_cfg->src_height[i] = src_h;
+		if (i == DPU_SSPP_COMP_1_2 || i == DPU_SSPP_COMP_2) {
+			scale_cfg->src_width[i] /= chroma_subsmpl_h;
+			scale_cfg->src_height[i] /= chroma_subsmpl_v;
+		}
+		scale_cfg->preload_x[i] = DPU_QSEED3_DEFAULT_PRELOAD_H;
+		scale_cfg->preload_y[i] = DPU_QSEED3_DEFAULT_PRELOAD_V;
+		pstate->pixel_ext.num_ext_pxls_top[i] =
+			scale_cfg->src_height[i];
+		pstate->pixel_ext.num_ext_pxls_left[i] =
+			scale_cfg->src_width[i];
+	}
+	if (!(DPU_FORMAT_IS_YUV(fmt)) && (src_h == dst_h)
+		&& (src_w == dst_w))
+		return;
+
+	scale_cfg->dst_width = dst_w;
+	scale_cfg->dst_height = dst_h;
+	scale_cfg->y_rgb_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->uv_filter_cfg = DPU_SCALE_BIL;
+	scale_cfg->alpha_filter_cfg = DPU_SCALE_ALPHA_BIL;
+	scale_cfg->lut_flag = 0;
+	scale_cfg->blend_cfg = 1;
+	scale_cfg->enable = 1;
+}
+
+static inline void _dpu_plane_setup_csc(struct dpu_plane *pdpu)
+{
+	static const struct dpu_csc_cfg dpu_csc_YUV2RGB_601L = {
+		{
+			/* S15.16 format */
+			0x00012A00, 0x00000000, 0x00019880,
+			0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+			0x00012A00, 0x00020480, 0x00000000,
+		},
+		/* signed bias */
+		{ 0xfff0, 0xff80, 0xff80,},
+		{ 0x0, 0x0, 0x0,},
+		/* unsigned clamp */
+		{ 0x10, 0xeb, 0x10, 0xf0, 0x10, 0xf0,},
+		{ 0x00, 0xff, 0x00, 0xff, 0x00, 0xff,},
+	};
+	static const struct dpu_csc_cfg dpu_csc10_YUV2RGB_601L = {
+		{
+			/* S15.16 format */
+			0x00012A00, 0x00000000, 0x00019880,
+			0x00012A00, 0xFFFF9B80, 0xFFFF3000,
+			0x00012A00, 0x00020480, 0x00000000,
+			},
+		/* signed bias */
+		{ 0xffc0, 0xfe00, 0xfe00,},
+		{ 0x0, 0x0, 0x0,},
+		/* unsigned clamp */
+		{ 0x40, 0x3ac, 0x40, 0x3c0, 0x40, 0x3c0,},
+		{ 0x00, 0x3ff, 0x00, 0x3ff, 0x00, 0x3ff,},
+	};
+
+	if (!pdpu) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	if (BIT(DPU_SSPP_CSC_10BIT) & pdpu->features)
+		pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc10_YUV2RGB_601L;
+	else
+		pdpu->csc_ptr = (struct dpu_csc_cfg *)&dpu_csc_YUV2RGB_601L;
+
+	DPU_DEBUG_PLANE(pdpu, "using 0x%X 0x%X 0x%X...\n",
+			pdpu->csc_ptr->csc_mv[0],
+			pdpu->csc_ptr->csc_mv[1],
+			pdpu->csc_ptr->csc_mv[2]);
+}
+
+static void _dpu_plane_setup_scaler(struct dpu_plane *pdpu,
+		struct dpu_plane_state *pstate,
+		const struct dpu_format *fmt, bool color_fill)
+{
+	struct dpu_hw_pixel_ext *pe;
+	uint32_t chroma_subsmpl_h, chroma_subsmpl_v;
+
+	if (!pdpu || !fmt || !pstate) {
+		DPU_ERROR("invalid arg(s), plane %d fmt %d state %d\n",
+				pdpu != 0, fmt != 0, pstate != 0);
+		return;
+	}
+
+	pe = &pstate->pixel_ext;
+
+	/* don't chroma subsample if decimating */
+	chroma_subsmpl_h =
+		drm_format_horz_chroma_subsampling(fmt->base.pixel_format);
+	chroma_subsmpl_v =
+		drm_format_vert_chroma_subsampling(fmt->base.pixel_format);
+
+	/* update scaler. calculate default config for QSEED3 */
+	_dpu_plane_setup_scaler3(pdpu, pstate,
+			drm_rect_width(&pdpu->pipe_cfg.src_rect),
+			drm_rect_height(&pdpu->pipe_cfg.src_rect),
+			drm_rect_width(&pdpu->pipe_cfg.dst_rect),
+			drm_rect_height(&pdpu->pipe_cfg.dst_rect),
+			&pstate->scaler3_cfg, fmt,
+			chroma_subsmpl_h, chroma_subsmpl_v);
+}
+
+/**
+ * _dpu_plane_color_fill - enables color fill on plane
+ * @pdpu:   Pointer to DPU plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+static int _dpu_plane_color_fill(struct dpu_plane *pdpu,
+		uint32_t color, uint32_t alpha)
+{
+	const struct dpu_format *fmt;
+	const struct drm_plane *plane;
+	struct dpu_plane_state *pstate;
+
+	if (!pdpu || !pdpu->base.state) {
+		DPU_ERROR("invalid plane\n");
+		return -EINVAL;
+	}
+
+	if (!pdpu->pipe_hw) {
+		DPU_ERROR_PLANE(pdpu, "invalid plane h/w pointer\n");
+		return -EINVAL;
+	}
+
+	plane = &pdpu->base;
+	pstate = to_dpu_plane_state(plane->state);
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/*
+	 * select fill format to match user property expectation,
+	 * h/w only supports RGB variants
+	 */
+	fmt = dpu_get_dpu_format(DRM_FORMAT_ABGR8888);
+
+	/* update sspp */
+	if (fmt && pdpu->pipe_hw->ops.setup_solidfill) {
+		pdpu->pipe_hw->ops.setup_solidfill(pdpu->pipe_hw,
+				(color & 0xFFFFFF) | ((alpha & 0xFF) << 24),
+				pstate->multirect_index);
+
+		/* override scaler/decimation if solid fill */
+		pdpu->pipe_cfg.src_rect.x1 = 0;
+		pdpu->pipe_cfg.src_rect.y1 = 0;
+		pdpu->pipe_cfg.src_rect.x2 =
+			drm_rect_width(&pdpu->pipe_cfg.dst_rect);
+		pdpu->pipe_cfg.src_rect.y2 =
+			drm_rect_height(&pdpu->pipe_cfg.dst_rect);
+		_dpu_plane_setup_scaler(pdpu, pstate, fmt, true);
+
+		if (pdpu->pipe_hw->ops.setup_format)
+			pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw,
+					fmt, DPU_SSPP_SOLID_FILL,
+					pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_rects)
+			pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+					&pdpu->pipe_cfg,
+					pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_pe)
+			pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw,
+					&pstate->pixel_ext);
+
+		if (pdpu->pipe_hw->ops.setup_scaler &&
+				pstate->multirect_index != DPU_SSPP_RECT_1)
+			pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw,
+					&pdpu->pipe_cfg, &pstate->pixel_ext,
+					&pstate->scaler3_cfg);
+	}
+
+	return 0;
+}
+
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!drm_state)
+		return;
+
+	pstate = to_dpu_plane_state(drm_state);
+
+	pstate->multirect_index = DPU_SSPP_RECT_SOLO;
+	pstate->multirect_mode = DPU_SSPP_MULTIRECT_NONE;
+}
+
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane)
+{
+	struct dpu_plane_state *pstate[R_MAX];
+	const struct drm_plane_state *drm_state[R_MAX];
+	struct drm_rect src[R_MAX], dst[R_MAX];
+	struct dpu_plane *dpu_plane[R_MAX];
+	const struct dpu_format *fmt[R_MAX];
+	int i, buffer_lines;
+	unsigned int max_tile_height = 1;
+	bool parallel_fetch_qualified = true;
+	bool has_tiled_rect = false;
+
+	for (i = 0; i < R_MAX; i++) {
+		const struct msm_format *msm_fmt;
+
+		drm_state[i] = i ? plane->r1 : plane->r0;
+		msm_fmt = msm_framebuffer_format(drm_state[i]->fb);
+		fmt[i] = to_dpu_format(msm_fmt);
+
+		if (DPU_FORMAT_IS_UBWC(fmt[i])) {
+			has_tiled_rect = true;
+			if (fmt[i]->tile_height > max_tile_height)
+				max_tile_height = fmt[i]->tile_height;
+		}
+	}
+
+	for (i = 0; i < R_MAX; i++) {
+		int width_threshold;
+
+		pstate[i] = to_dpu_plane_state(drm_state[i]);
+		dpu_plane[i] = to_dpu_plane(drm_state[i]->plane);
+
+		if (pstate[i] == NULL) {
+			DPU_ERROR("DPU plane state of plane id %d is NULL\n",
+				drm_state[i]->plane->base.id);
+			return -EINVAL;
+		}
+
+		src[i].x1 = drm_state[i]->src_x >> 16;
+		src[i].y1 = drm_state[i]->src_y >> 16;
+		src[i].x2 = src[i].x1 + (drm_state[i]->src_w >> 16);
+		src[i].y2 = src[i].y1 + (drm_state[i]->src_h >> 16);
+
+		dst[i] = drm_plane_state_dest(drm_state[i]);
+
+		if (drm_rect_calc_hscale(&src[i], &dst[i], 1, 1) != 1 ||
+		    drm_rect_calc_vscale(&src[i], &dst[i], 1, 1) != 1) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"scaling is not supported in multirect mode\n");
+			return -EINVAL;
+		}
+
+		if (DPU_FORMAT_IS_YUV(fmt[i])) {
+			DPU_ERROR_PLANE(dpu_plane[i],
+				"Unsupported format for multirect mode\n");
+			return -EINVAL;
+		}
+
+		/**
+		 * SSPP PD_MEM is split half - one for each RECT.
+		 * Tiled formats need 5 lines of buffering while fetching
+		 * whereas linear formats need only 2 lines.
+		 * So we cannot support more than half of the supported SSPP
+		 * width for tiled formats.
+		 */
+		width_threshold = dpu_plane[i]->pipe_sblk->common->maxlinewidth;
+		if (has_tiled_rect)
+			width_threshold /= 2;
+
+		if (parallel_fetch_qualified &&
+		    drm_rect_width(&src[i]) > width_threshold)
+			parallel_fetch_qualified = false;
+
+	}
+
+	/* Validate RECT's and set the mode */
+
+	/* Prefer PARALLEL FETCH Mode over TIME_MX Mode */
+	if (parallel_fetch_qualified) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
+
+		goto done;
+	}
+
+	/* TIME_MX Mode */
+	buffer_lines = 2 * max_tile_height;
+
+	if (dst[R1].y1 >= dst[R0].y2 + buffer_lines ||
+	    dst[R0].y1 >= dst[R1].y2 + buffer_lines) {
+		pstate[R0]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+		pstate[R1]->multirect_mode = DPU_SSPP_MULTIRECT_TIME_MX;
+	} else {
+		DPU_ERROR(
+			"No multirect mode possible for the planes (%d - %d)\n",
+			drm_state[R0]->plane->base.id,
+			drm_state[R1]->plane->base.id);
+		return -EINVAL;
+	}
+
+done:
+	if (dpu_plane[R0]->is_virtual) {
+		pstate[R0]->multirect_index = DPU_SSPP_RECT_1;
+		pstate[R1]->multirect_index = DPU_SSPP_RECT_0;
+	} else {
+		pstate[R0]->multirect_index = DPU_SSPP_RECT_0;
+		pstate[R1]->multirect_index = DPU_SSPP_RECT_1;
+	};
+
+	DPU_DEBUG_PLANE(dpu_plane[R0], "R0: %d - %d\n",
+		pstate[R0]->multirect_mode, pstate[R0]->multirect_index);
+	DPU_DEBUG_PLANE(dpu_plane[R1], "R1: %d - %d\n",
+		pstate[R1]->multirect_mode, pstate[R1]->multirect_index);
+	return 0;
+}
+
+/**
+ * dpu_plane_get_ctl_flush - get control flush for the given plane
+ * @plane: Pointer to drm plane structure
+ * @ctl: Pointer to hardware control driver
+ * @flush_sspp: Pointer to sspp flush control word
+ */
+void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl,
+		u32 *flush_sspp)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !flush_sspp) {
+		DPU_ERROR("invalid parameters\n");
+		return;
+	}
+
+	pstate = to_dpu_plane_state(plane->state);
+
+	*flush_sspp = ctl->ops.get_bitmask_sspp(ctl, dpu_plane_pipe(plane));
+}
+
+static int dpu_plane_prepare_fb(struct drm_plane *plane,
+		struct drm_plane_state *new_state)
+{
+	struct drm_framebuffer *fb = new_state->fb;
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *pstate = to_dpu_plane_state(new_state);
+	struct dpu_hw_fmt_layout layout;
+	struct drm_gem_object *obj;
+	struct msm_gem_object *msm_obj;
+	struct dma_fence *fence;
+	struct msm_gem_address_space *aspace;
+	int ret;
+
+	if (!new_state->fb)
+		return 0;
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", fb->base.id);
+
+	ret = _dpu_plane_get_aspace(pdpu, pstate, &aspace);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "Failed to get aspace\n");
+		return ret;
+	}
+
+	/* cache aspace */
+	pstate->aspace = aspace;
+
+	/*
+	 * TODO: Need to sort out the msm_framebuffer_prepare() call below so
+	 *       we can use msm_atomic_prepare_fb() instead of doing the
+	 *       implicit fence and fb prepare by hand here.
+	 */
+	obj = msm_framebuffer_bo(new_state->fb, 0);
+	msm_obj = to_msm_bo(obj);
+	fence = reservation_object_get_excl_rcu(msm_obj->resv);
+	if (fence)
+		drm_atomic_set_fence_for_plane(new_state, fence);
+
+	if (pstate->aspace) {
+		ret = msm_framebuffer_prepare(new_state->fb,
+				pstate->aspace);
+		if (ret) {
+			DPU_ERROR("failed to prepare framebuffer\n");
+			return ret;
+		}
+	}
+
+	/* validate framebuffer layout before commit */
+	ret = dpu_format_populate_layout(pstate->aspace,
+			new_state->fb, &layout);
+	if (ret) {
+		DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void dpu_plane_cleanup_fb(struct drm_plane *plane,
+		struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu = to_dpu_plane(plane);
+	struct dpu_plane_state *old_pstate;
+
+	if (!old_state || !old_state->fb)
+		return;
+
+	old_pstate = to_dpu_plane_state(old_state);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u]\n", old_state->fb->base.id);
+
+	msm_framebuffer_cleanup(old_state->fb, old_pstate->aspace);
+}
+
+static bool dpu_plane_validate_src(struct drm_rect *src,
+				   struct drm_rect *fb_rect,
+				   uint32_t min_src_size)
+{
+	/* Ensure fb size is supported */
+	if (drm_rect_width(fb_rect) > MAX_IMG_WIDTH ||
+	    drm_rect_height(fb_rect) > MAX_IMG_HEIGHT)
+		return false;
+
+	/* Ensure src rect is above the minimum size */
+	if (drm_rect_width(src) < min_src_size ||
+	    drm_rect_height(src) < min_src_size)
+		return false;
+
+	/* Ensure src is fully encapsulated in fb */
+	return drm_rect_intersect(fb_rect, src) &&
+		drm_rect_equals(fb_rect, src);
+}
+
+static int dpu_plane_sspp_atomic_check(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	int ret = 0;
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	const struct dpu_format *fmt;
+	struct drm_rect src, dst, fb_rect = { 0 };
+	uint32_t max_upscale = 1, max_downscale = 1;
+	uint32_t min_src_size, max_linewidth;
+	int hscale = 1, vscale = 1;
+
+	if (!plane || !state) {
+		DPU_ERROR("invalid arg(s), plane %d state %d\n",
+				plane != 0, state != 0);
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(state);
+
+	if (!pdpu->pipe_sblk) {
+		DPU_ERROR_PLANE(pdpu, "invalid catalog\n");
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	src.x1 = state->src_x >> 16;
+	src.y1 = state->src_y >> 16;
+	src.x2 = src.x1 + (state->src_w >> 16);
+	src.y2 = src.y1 + (state->src_h >> 16);
+
+	dst = drm_plane_state_dest(state);
+
+	fb_rect.x2 = state->fb->width;
+	fb_rect.y2 = state->fb->height;
+
+	max_linewidth = pdpu->pipe_sblk->common->maxlinewidth;
+
+	if (pdpu->features & DPU_SSPP_SCALER) {
+		max_downscale = pdpu->pipe_sblk->maxdwnscale;
+		max_upscale = pdpu->pipe_sblk->maxupscale;
+	}
+	if (drm_rect_width(&src) < drm_rect_width(&dst))
+		hscale = drm_rect_calc_hscale(&src, &dst, 1, max_upscale);
+	else
+		hscale = drm_rect_calc_hscale(&dst, &src, 1, max_downscale);
+	if (drm_rect_height(&src) < drm_rect_height(&dst))
+		vscale = drm_rect_calc_vscale(&src, &dst, 1, max_upscale);
+	else
+		vscale = drm_rect_calc_vscale(&dst, &src, 1, max_downscale);
+
+	DPU_DEBUG_PLANE(pdpu, "check %d -> %d\n",
+		dpu_plane_enabled(plane->state), dpu_plane_enabled(state));
+
+	if (!dpu_plane_enabled(state))
+		goto exit;
+
+	fmt = to_dpu_format(msm_framebuffer_format(state->fb));
+
+	min_src_size = DPU_FORMAT_IS_YUV(fmt) ? 2 : 1;
+
+	if (DPU_FORMAT_IS_YUV(fmt) &&
+		(!(pdpu->features & DPU_SSPP_SCALER) ||
+		 !(pdpu->features & (BIT(DPU_SSPP_CSC)
+		 | BIT(DPU_SSPP_CSC_10BIT))))) {
+		DPU_ERROR_PLANE(pdpu,
+				"plane doesn't have scaler/csc for yuv\n");
+		ret = -EINVAL;
+
+	/* check src bounds */
+	} else if (!dpu_plane_validate_src(&src, &fb_rect, min_src_size)) {
+		DPU_ERROR_PLANE(pdpu, "invalid source " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src));
+		ret = -E2BIG;
+
+	/* valid yuv image */
+	} else if (DPU_FORMAT_IS_YUV(fmt) &&
+		   (src.x1 & 0x1 || src.y1 & 0x1 ||
+		    drm_rect_width(&src) & 0x1 ||
+		    drm_rect_height(&src) & 0x1)) {
+		DPU_ERROR_PLANE(pdpu, "invalid yuv source " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src));
+		ret = -EINVAL;
+
+	/* min dst support */
+	} else if (drm_rect_width(&dst) < 0x1 || drm_rect_height(&dst) < 0x1) {
+		DPU_ERROR_PLANE(pdpu, "invalid dest rect " DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&dst));
+		ret = -EINVAL;
+
+	/* check decimated source width */
+	} else if (drm_rect_width(&src) > max_linewidth) {
+		DPU_ERROR_PLANE(pdpu, "invalid src " DRM_RECT_FMT " line:%u\n",
+				DRM_RECT_ARG(&src), max_linewidth);
+		ret = -E2BIG;
+
+	/* check scaler capability */
+	} else if (hscale < 0 || vscale < 0) {
+		DPU_ERROR_PLANE(pdpu, "invalid scaling requested src="
+				DRM_RECT_FMT " dst=" DRM_RECT_FMT "\n",
+				DRM_RECT_ARG(&src), DRM_RECT_ARG(&dst));
+		ret = -E2BIG;
+	}
+
+exit:
+	return ret;
+}
+
+static int dpu_plane_atomic_check(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	if (!state->fb)
+		return 0;
+
+	DPU_DEBUG_PLANE(to_dpu_plane(plane), "\n");
+
+	return dpu_plane_sspp_atomic_check(plane, state);
+}
+
+void dpu_plane_flush(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !plane->state) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pstate = to_dpu_plane_state(plane->state);
+
+	/*
+	 * These updates have to be done immediately before the plane flush
+	 * timing, and may not be moved to the atomic_update/mode_set functions.
+	 */
+	if (pdpu->is_error)
+		/* force white frame with 100% alpha pipe output on error */
+		_dpu_plane_color_fill(pdpu, 0xFFFFFF, 0xFF);
+	else if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG)
+		/* force 100% alpha */
+		_dpu_plane_color_fill(pdpu, pdpu->color_fill, 0xFF);
+	else if (pdpu->pipe_hw && pdpu->csc_ptr && pdpu->pipe_hw->ops.setup_csc)
+		pdpu->pipe_hw->ops.setup_csc(pdpu->pipe_hw, pdpu->csc_ptr);
+
+	/* flag h/w flush complete */
+	if (plane->state)
+		pstate->pending = false;
+}
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane)
+		return;
+
+	pdpu = to_dpu_plane(plane);
+	pdpu->is_error = error;
+}
+
+static int dpu_plane_sspp_atomic_update(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	uint32_t nplanes, src_flags;
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+	struct dpu_plane_state *pstate;
+	struct dpu_plane_state *old_pstate;
+	const struct dpu_format *fmt;
+	struct drm_crtc *crtc;
+	struct drm_framebuffer *fb;
+	struct drm_rect src, dst;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return -EINVAL;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return -EINVAL;
+	} else if (!old_state) {
+		DPU_ERROR("invalid old state\n");
+		return -EINVAL;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	state = plane->state;
+
+	pstate = to_dpu_plane_state(state);
+
+	old_pstate = to_dpu_plane_state(old_state);
+
+	crtc = state->crtc;
+	fb = state->fb;
+	if (!crtc || !fb) {
+		DPU_ERROR_PLANE(pdpu, "invalid crtc %d or fb %d\n",
+				crtc != 0, fb != 0);
+		return -EINVAL;
+	}
+	fmt = to_dpu_format(msm_framebuffer_format(fb));
+	nplanes = fmt->num_planes;
+
+	memset(&(pdpu->pipe_cfg), 0, sizeof(struct dpu_hw_pipe_cfg));
+
+	_dpu_plane_set_scanout(plane, pstate, &pdpu->pipe_cfg, fb);
+
+	pstate->pending = true;
+
+	pdpu->is_rt_pipe = (dpu_crtc_get_client_type(crtc) != NRT_CLIENT);
+	_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+	src.x1 = state->src_x >> 16;
+	src.y1 = state->src_y >> 16;
+	src.x2 = src.x1 + (state->src_w >> 16);
+	src.y2 = src.y1 + (state->src_h >> 16);
+
+	dst = drm_plane_state_dest(state);
+
+	DPU_DEBUG_PLANE(pdpu, "FB[%u] " DRM_RECT_FMT "->crtc%u " DRM_RECT_FMT
+			", %4.4s ubwc %d\n", fb->base.id, DRM_RECT_ARG(&src),
+			crtc->base.id, DRM_RECT_ARG(&dst),
+			(char *)&fmt->base.pixel_format,
+			DPU_FORMAT_IS_UBWC(fmt));
+
+	pdpu->pipe_cfg.src_rect = src;
+	pdpu->pipe_cfg.dst_rect = dst;
+
+	_dpu_plane_setup_scaler(pdpu, pstate, fmt, false);
+
+	/* override for color fill */
+	if (pdpu->color_fill & DPU_PLANE_COLOR_FILL_FLAG) {
+		/* skip remaining processing on color fill */
+		return 0;
+	}
+
+	if (pdpu->pipe_hw->ops.setup_rects) {
+		pdpu->pipe_hw->ops.setup_rects(pdpu->pipe_hw,
+				&pdpu->pipe_cfg,
+				pstate->multirect_index);
+	}
+
+	if (pdpu->pipe_hw->ops.setup_pe &&
+			(pstate->multirect_index != DPU_SSPP_RECT_1))
+		pdpu->pipe_hw->ops.setup_pe(pdpu->pipe_hw,
+				&pstate->pixel_ext);
+
+	/**
+	 * when programmed in multirect mode, scalar block will be
+	 * bypassed. Still we need to update alpha and bitwidth
+	 * ONLY for RECT0
+	 */
+	if (pdpu->pipe_hw->ops.setup_scaler &&
+			pstate->multirect_index != DPU_SSPP_RECT_1)
+		pdpu->pipe_hw->ops.setup_scaler(pdpu->pipe_hw,
+				&pdpu->pipe_cfg, &pstate->pixel_ext,
+				&pstate->scaler3_cfg);
+
+	if (pdpu->pipe_hw->ops.setup_multirect)
+		pdpu->pipe_hw->ops.setup_multirect(
+				pdpu->pipe_hw,
+				pstate->multirect_index,
+				pstate->multirect_mode);
+
+	if (pdpu->pipe_hw->ops.setup_format) {
+		src_flags = 0x0;
+
+		/* update format */
+		pdpu->pipe_hw->ops.setup_format(pdpu->pipe_hw, fmt, src_flags,
+				pstate->multirect_index);
+
+		if (pdpu->pipe_hw->ops.setup_cdp) {
+			struct dpu_hw_pipe_cdp_cfg *cdp_cfg = &pstate->cdp_cfg;
+
+			memset(cdp_cfg, 0, sizeof(struct dpu_hw_pipe_cdp_cfg));
+
+			cdp_cfg->enable = pdpu->catalog->perf.cdp_cfg
+					[DPU_PERF_CDP_USAGE_RT].rd_enable;
+			cdp_cfg->ubwc_meta_enable =
+					DPU_FORMAT_IS_UBWC(fmt);
+			cdp_cfg->tile_amortize_enable =
+					DPU_FORMAT_IS_UBWC(fmt) ||
+					DPU_FORMAT_IS_TILE(fmt);
+			cdp_cfg->preload_ahead = DPU_SSPP_CDP_PRELOAD_AHEAD_64;
+
+			pdpu->pipe_hw->ops.setup_cdp(pdpu->pipe_hw, cdp_cfg);
+		}
+
+		/* update csc */
+		if (DPU_FORMAT_IS_YUV(fmt))
+			_dpu_plane_setup_csc(pdpu);
+		else
+			pdpu->csc_ptr = 0;
+	}
+
+	_dpu_plane_set_qos_lut(plane, fb);
+	_dpu_plane_set_danger_lut(plane, fb);
+
+	if (plane->type != DRM_PLANE_TYPE_CURSOR) {
+		_dpu_plane_set_qos_ctrl(plane, true, DPU_PLANE_QOS_PANIC_CTRL);
+		_dpu_plane_set_ot_limit(plane, crtc);
+	}
+
+	_dpu_plane_set_qos_remap(plane);
+	return 0;
+}
+
+static void _dpu_plane_atomic_disable(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+	struct dpu_plane_state *pstate;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return;
+	} else if (!old_state) {
+		DPU_ERROR("invalid old state\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	state = plane->state;
+	pstate = to_dpu_plane_state(state);
+
+	trace_dpu_plane_disable(DRMID(plane), is_dpu_plane_virtual(plane),
+				pstate->multirect_mode);
+
+	pstate->pending = true;
+
+	if (is_dpu_plane_virtual(plane) &&
+			pdpu->pipe_hw && pdpu->pipe_hw->ops.setup_multirect)
+		pdpu->pipe_hw->ops.setup_multirect(pdpu->pipe_hw,
+				DPU_SSPP_RECT_SOLO, DPU_SSPP_MULTIRECT_NONE);
+}
+
+static void dpu_plane_atomic_update(struct drm_plane *plane,
+				struct drm_plane_state *old_state)
+{
+	struct dpu_plane *pdpu;
+	struct drm_plane_state *state;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	pdpu->is_error = false;
+	state = plane->state;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (!dpu_plane_sspp_enabled(state)) {
+		_dpu_plane_atomic_disable(plane, old_state);
+	} else {
+		int ret;
+
+		ret = dpu_plane_sspp_atomic_update(plane, old_state);
+		/* atomic_check should have ensured that this doesn't fail */
+		WARN_ON(ret < 0);
+	}
+}
+
+void dpu_plane_restore(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane || !plane->state) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/* last plane state is same as current state */
+	dpu_plane_atomic_update(plane, plane->state);
+}
+
+static void dpu_plane_destroy(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu = plane ? to_dpu_plane(plane) : NULL;
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	if (pdpu) {
+		_dpu_plane_set_qos_ctrl(plane, false, DPU_PLANE_QOS_PANIC_CTRL);
+
+		mutex_destroy(&pdpu->lock);
+
+		drm_plane_helper_disable(plane, NULL);
+
+		/* this will destroy the states as well */
+		drm_plane_cleanup(plane);
+
+		if (pdpu->pipe_hw)
+			dpu_hw_sspp_destroy(pdpu->pipe_hw);
+
+		kfree(pdpu);
+	}
+}
+
+static void dpu_plane_destroy_state(struct drm_plane *plane,
+		struct drm_plane_state *state)
+{
+	struct dpu_plane_state *pstate;
+
+	if (!plane || !state) {
+		DPU_ERROR("invalid arg(s), plane %d state %d\n",
+				plane != 0, state != 0);
+		return;
+	}
+
+	pstate = to_dpu_plane_state(state);
+
+	/* remove ref count for frame buffers */
+	if (state->fb)
+		drm_framebuffer_put(state->fb);
+
+	kfree(pstate);
+}
+
+static struct drm_plane_state *
+dpu_plane_duplicate_state(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+	struct dpu_plane_state *old_state;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return NULL;
+	} else if (!plane->state) {
+		DPU_ERROR("invalid plane state\n");
+		return NULL;
+	}
+
+	old_state = to_dpu_plane_state(plane->state);
+	pdpu = to_dpu_plane(plane);
+	pstate = kmemdup(old_state, sizeof(*old_state), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return NULL;
+	}
+
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	pstate->pending = false;
+
+	__drm_atomic_helper_plane_duplicate_state(plane, &pstate->base);
+
+	return &pstate->base;
+}
+
+static void dpu_plane_reset(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_plane_state *pstate;
+
+	if (!plane) {
+		DPU_ERROR("invalid plane\n");
+		return;
+	}
+
+	pdpu = to_dpu_plane(plane);
+	DPU_DEBUG_PLANE(pdpu, "\n");
+
+	/* remove previous state, if present */
+	if (plane->state) {
+		dpu_plane_destroy_state(plane, plane->state);
+		plane->state = 0;
+	}
+
+	pstate = kzalloc(sizeof(*pstate), GFP_KERNEL);
+	if (!pstate) {
+		DPU_ERROR_PLANE(pdpu, "failed to allocate state\n");
+		return;
+	}
+
+	pstate->base.plane = plane;
+
+	plane->state = &pstate->base;
+}
+
+#ifdef CONFIG_DEBUG_FS
+static ssize_t _dpu_plane_danger_read(struct file *file,
+			char __user *buff, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	struct dpu_mdss_cfg *cfg = kms->catalog;
+	int len = 0;
+	char buf[40] = {'\0'};
+
+	if (!cfg)
+		return -ENODEV;
+
+	if (*ppos)
+		return 0; /* the end */
+
+	len = snprintf(buf, sizeof(buf), "%d\n", !kms->has_danger_ctrl);
+	if (len < 0 || len >= sizeof(buf))
+		return 0;
+
+	if ((count < sizeof(buf)) || copy_to_user(buff, buf, len))
+		return -EFAULT;
+
+	*ppos += len;   /* increase offset */
+
+	return len;
+}
+
+static void _dpu_plane_set_danger_state(struct dpu_kms *kms, bool enable)
+{
+	struct drm_plane *plane;
+
+	drm_for_each_plane(plane, kms->dev) {
+		if (plane->fb && plane->state) {
+			dpu_plane_danger_signal_ctrl(plane, enable);
+			DPU_DEBUG("plane:%d img:%dx%d ",
+				plane->base.id, plane->fb->width,
+				plane->fb->height);
+			DPU_DEBUG("src[%d,%d,%d,%d] dst[%d,%d,%d,%d]\n",
+				plane->state->src_x >> 16,
+				plane->state->src_y >> 16,
+				plane->state->src_w >> 16,
+				plane->state->src_h >> 16,
+				plane->state->crtc_x, plane->state->crtc_y,
+				plane->state->crtc_w, plane->state->crtc_h);
+		} else {
+			DPU_DEBUG("Inactive plane:%d\n", plane->base.id);
+		}
+	}
+}
+
+static ssize_t _dpu_plane_danger_write(struct file *file,
+		    const char __user *user_buf, size_t count, loff_t *ppos)
+{
+	struct dpu_kms *kms = file->private_data;
+	struct dpu_mdss_cfg *cfg = kms->catalog;
+	int disable_panic;
+	char buf[10];
+
+	if (!cfg)
+		return -EFAULT;
+
+	if (count >= sizeof(buf))
+		return -EFAULT;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	buf[count] = 0;	/* end of string */
+
+	if (kstrtoint(buf, 0, &disable_panic))
+		return -EFAULT;
+
+	if (disable_panic) {
+		/* Disable panic signal for all active pipes */
+		DPU_DEBUG("Disabling danger:\n");
+		_dpu_plane_set_danger_state(kms, false);
+		kms->has_danger_ctrl = false;
+	} else {
+		/* Enable panic signal for all active pipes */
+		DPU_DEBUG("Enabling danger:\n");
+		kms->has_danger_ctrl = true;
+		_dpu_plane_set_danger_state(kms, true);
+	}
+
+	return count;
+}
+
+static const struct file_operations dpu_plane_danger_enable = {
+	.open = simple_open,
+	.read = _dpu_plane_danger_read,
+	.write = _dpu_plane_danger_write,
+};
+
+static int _dpu_plane_init_debugfs(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+	struct dpu_kms *kms;
+	struct msm_drm_private *priv;
+	const struct dpu_sspp_sub_blks *sblk = 0;
+	const struct dpu_sspp_cfg *cfg = 0;
+
+	if (!plane || !plane->dev) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	priv = plane->dev->dev_private;
+	if (!priv || !priv->kms) {
+		DPU_ERROR("invalid KMS reference\n");
+		return -EINVAL;
+	}
+
+	kms = to_dpu_kms(priv->kms);
+	pdpu = to_dpu_plane(plane);
+
+	if (pdpu && pdpu->pipe_hw)
+		cfg = pdpu->pipe_hw->cap;
+	if (cfg)
+		sblk = cfg->sblk;
+
+	if (!sblk)
+		return 0;
+
+	/* create overall sub-directory for the pipe */
+	pdpu->debugfs_root =
+		debugfs_create_dir(pdpu->pipe_name,
+				plane->dev->primary->debugfs_root);
+
+	if (!pdpu->debugfs_root)
+		return -ENOMEM;
+
+	/* don't error check these */
+	debugfs_create_x32("features", 0600,
+			pdpu->debugfs_root, &pdpu->features);
+
+	/* add register dump support */
+	dpu_debugfs_setup_regset32(&pdpu->debugfs_src,
+			sblk->src_blk.base + cfg->base,
+			sblk->src_blk.len,
+			kms);
+	dpu_debugfs_create_regset32("src_blk", 0400,
+			pdpu->debugfs_root, &pdpu->debugfs_src);
+
+	if (cfg->features & BIT(DPU_SSPP_SCALER_QSEED3) ||
+			cfg->features & BIT(DPU_SSPP_SCALER_QSEED2)) {
+		dpu_debugfs_setup_regset32(&pdpu->debugfs_scaler,
+				sblk->scaler_blk.base + cfg->base,
+				sblk->scaler_blk.len,
+				kms);
+		dpu_debugfs_create_regset32("scaler_blk", 0400,
+				pdpu->debugfs_root,
+				&pdpu->debugfs_scaler);
+		debugfs_create_bool("default_scaling",
+				0600,
+				pdpu->debugfs_root,
+				&pdpu->debugfs_default_scale);
+	}
+
+	if (cfg->features & BIT(DPU_SSPP_CSC) ||
+			cfg->features & BIT(DPU_SSPP_CSC_10BIT)) {
+		dpu_debugfs_setup_regset32(&pdpu->debugfs_csc,
+				sblk->csc_blk.base + cfg->base,
+				sblk->csc_blk.len,
+				kms);
+		dpu_debugfs_create_regset32("csc_blk", 0400,
+				pdpu->debugfs_root, &pdpu->debugfs_csc);
+	}
+
+	debugfs_create_u32("xin_id",
+			0400,
+			pdpu->debugfs_root,
+			(u32 *) &cfg->xin_id);
+	debugfs_create_u32("clk_ctrl",
+			0400,
+			pdpu->debugfs_root,
+			(u32 *) &cfg->clk_ctrl);
+	debugfs_create_x32("creq_vblank",
+			0600,
+			pdpu->debugfs_root,
+			(u32 *) &sblk->creq_vblank);
+	debugfs_create_x32("danger_vblank",
+			0600,
+			pdpu->debugfs_root,
+			(u32 *) &sblk->danger_vblank);
+
+	debugfs_create_file("disable_danger",
+			0600,
+			pdpu->debugfs_root,
+			kms, &dpu_plane_danger_enable);
+
+	return 0;
+}
+
+static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
+{
+	struct dpu_plane *pdpu;
+
+	if (!plane)
+		return;
+	pdpu = to_dpu_plane(plane);
+
+	debugfs_remove_recursive(pdpu->debugfs_root);
+}
+#else
+static int _dpu_plane_init_debugfs(struct drm_plane *plane)
+{
+	return 0;
+}
+static void _dpu_plane_destroy_debugfs(struct drm_plane *plane)
+{
+}
+#endif
+
+static int dpu_plane_late_register(struct drm_plane *plane)
+{
+	return _dpu_plane_init_debugfs(plane);
+}
+
+static void dpu_plane_early_unregister(struct drm_plane *plane)
+{
+	_dpu_plane_destroy_debugfs(plane);
+}
+
+static const struct drm_plane_funcs dpu_plane_funcs = {
+		.update_plane = drm_atomic_helper_update_plane,
+		.disable_plane = drm_atomic_helper_disable_plane,
+		.destroy = dpu_plane_destroy,
+		.reset = dpu_plane_reset,
+		.atomic_duplicate_state = dpu_plane_duplicate_state,
+		.atomic_destroy_state = dpu_plane_destroy_state,
+		.late_register = dpu_plane_late_register,
+		.early_unregister = dpu_plane_early_unregister,
+};
+
+static const struct drm_plane_helper_funcs dpu_plane_helper_funcs = {
+		.prepare_fb = dpu_plane_prepare_fb,
+		.cleanup_fb = dpu_plane_cleanup_fb,
+		.atomic_check = dpu_plane_atomic_check,
+		.atomic_update = dpu_plane_atomic_update,
+};
+
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane)
+{
+	return plane ? to_dpu_plane(plane)->pipe : SSPP_NONE;
+}
+
+bool is_dpu_plane_virtual(struct drm_plane *plane)
+{
+	return plane ? to_dpu_plane(plane)->is_virtual : false;
+}
+
+/* initialize plane */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, bool primary_plane,
+		unsigned long possible_crtcs, u32 master_plane_id)
+{
+	struct drm_plane *plane = NULL, *master_plane = NULL;
+	const struct dpu_format_extended *format_list;
+	struct dpu_plane *pdpu;
+	struct msm_drm_private *priv;
+	struct dpu_kms *kms;
+	enum drm_plane_type type;
+	int zpos_max = DPU_ZPOS_MAX;
+	int ret = -EINVAL;
+
+	if (!dev) {
+		DPU_ERROR("[%u]device is NULL\n", pipe);
+		goto exit;
+	}
+
+	priv = dev->dev_private;
+	if (!priv) {
+		DPU_ERROR("[%u]private data is NULL\n", pipe);
+		goto exit;
+	}
+
+	if (!priv->kms) {
+		DPU_ERROR("[%u]invalid KMS reference\n", pipe);
+		goto exit;
+	}
+	kms = to_dpu_kms(priv->kms);
+
+	if (!kms->catalog) {
+		DPU_ERROR("[%u]invalid catalog reference\n", pipe);
+		goto exit;
+	}
+
+	/* create and zero local structure */
+	pdpu = kzalloc(sizeof(*pdpu), GFP_KERNEL);
+	if (!pdpu) {
+		DPU_ERROR("[%u]failed to allocate local plane struct\n", pipe);
+		ret = -ENOMEM;
+		goto exit;
+	}
+
+	/* cache local stuff for later */
+	plane = &pdpu->base;
+	pdpu->pipe = pipe;
+	pdpu->is_virtual = (master_plane_id != 0);
+	INIT_LIST_HEAD(&pdpu->mplane_list);
+	master_plane = drm_plane_find(dev, NULL, master_plane_id);
+	if (master_plane) {
+		struct dpu_plane *mpdpu = to_dpu_plane(master_plane);
+
+		list_add_tail(&pdpu->mplane_list, &mpdpu->mplane_list);
+	}
+
+	/* initialize underlying h/w driver */
+	pdpu->pipe_hw = dpu_hw_sspp_init(pipe, kms->mmio, kms->catalog,
+							master_plane_id != 0);
+	if (IS_ERR(pdpu->pipe_hw)) {
+		DPU_ERROR("[%u]SSPP init failed\n", pipe);
+		ret = PTR_ERR(pdpu->pipe_hw);
+		goto clean_plane;
+	} else if (!pdpu->pipe_hw->cap || !pdpu->pipe_hw->cap->sblk) {
+		DPU_ERROR("[%u]SSPP init returned invalid cfg\n", pipe);
+		goto clean_sspp;
+	}
+
+	/* cache features mask for later */
+	pdpu->features = pdpu->pipe_hw->cap->features;
+	pdpu->pipe_sblk = pdpu->pipe_hw->cap->sblk;
+	if (!pdpu->pipe_sblk) {
+		DPU_ERROR("[%u]invalid sblk\n", pipe);
+		goto clean_sspp;
+	}
+
+	if (!master_plane_id)
+		format_list = pdpu->pipe_sblk->format_list;
+	else
+		format_list = pdpu->pipe_sblk->virt_format_list;
+
+	pdpu->nformats = dpu_populate_formats(format_list,
+				pdpu->formats,
+				0,
+				ARRAY_SIZE(pdpu->formats));
+
+	if (!pdpu->nformats) {
+		DPU_ERROR("[%u]no valid formats for plane\n", pipe);
+		goto clean_sspp;
+	}
+
+	if (pdpu->features & BIT(DPU_SSPP_CURSOR))
+		type = DRM_PLANE_TYPE_CURSOR;
+	else if (primary_plane)
+		type = DRM_PLANE_TYPE_PRIMARY;
+	else
+		type = DRM_PLANE_TYPE_OVERLAY;
+	ret = drm_universal_plane_init(dev, plane, 0xff, &dpu_plane_funcs,
+				pdpu->formats, pdpu->nformats,
+				NULL, type, NULL);
+	if (ret)
+		goto clean_sspp;
+
+	pdpu->catalog = kms->catalog;
+
+	if (kms->catalog->mixer_count &&
+		kms->catalog->mixer[0].sblk->maxblendstages) {
+		zpos_max = kms->catalog->mixer[0].sblk->maxblendstages - 1;
+		if (zpos_max > DPU_STAGE_MAX - DPU_STAGE_0 - 1)
+			zpos_max = DPU_STAGE_MAX - DPU_STAGE_0 - 1;
+	}
+
+	ret = drm_plane_create_zpos_property(plane, 0, 0, zpos_max);
+	if (ret)
+		DPU_ERROR("failed to install zpos property, rc = %d\n", ret);
+
+	/* success! finalize initialization */
+	drm_plane_helper_add(plane, &dpu_plane_helper_funcs);
+
+	/* save user friendly pipe name for later */
+	snprintf(pdpu->pipe_name, DPU_NAME_SIZE, "plane%u", plane->base.id);
+
+	mutex_init(&pdpu->lock);
+
+	DPU_DEBUG("%s created for pipe:%u id:%u virtual:%u\n", pdpu->pipe_name,
+					pipe, plane->base.id, master_plane_id);
+	return plane;
+
+clean_sspp:
+	if (pdpu && pdpu->pipe_hw)
+		dpu_hw_sspp_destroy(pdpu->pipe_hw);
+clean_plane:
+	kfree(pdpu);
+exit:
+	return ERR_PTR(ret);
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
new file mode 100644
index 000000000000..f6fe6ddc7a3a
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.h
@@ -0,0 +1,175 @@
+/*
+ * Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2013 Red Hat
+ * Author: Rob Clark <robdclark@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ * You should have received a copy of the GNU General Public License along with
+ * this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#ifndef _DPU_PLANE_H_
+#define _DPU_PLANE_H_
+
+#include <drm/drm_crtc.h>
+
+#include "dpu_kms.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_sspp.h"
+
+/**
+ * struct dpu_plane_state: Define dpu extension of drm plane state object
+ * @base:	base drm plane state object
+ * @property_state: Local storage for msm_prop properties
+ * @property_values:	cached plane property values
+ * @aspace:	pointer to address space for input/output buffers
+ * @input_fence:	dereferenced input fence pointer
+ * @stage:	assigned by crtc blender
+ * @multirect_index: index of the rectangle of SSPP
+ * @multirect_mode: parallel or time multiplex multirect mode
+ * @pending:	whether the current update is still pending
+ * @scaler3_cfg: configuration data for scaler3
+ * @pixel_ext: configuration data for pixel extensions
+ * @scaler_check_state: indicates status of user provided pixel extension data
+ * @cdp_cfg:	CDP configuration
+ */
+struct dpu_plane_state {
+	struct drm_plane_state base;
+	struct msm_gem_address_space *aspace;
+	void *input_fence;
+	enum dpu_stage stage;
+	uint32_t multirect_index;
+	uint32_t multirect_mode;
+	bool pending;
+
+	/* scaler configuration */
+	struct dpu_hw_scaler3_cfg scaler3_cfg;
+	struct dpu_hw_pixel_ext pixel_ext;
+
+	struct dpu_hw_pipe_cdp_cfg cdp_cfg;
+};
+
+/**
+ * struct dpu_multirect_plane_states: Defines multirect pair of drm plane states
+ * @r0: drm plane configured on rect 0
+ * @r1: drm plane configured on rect 1
+ */
+struct dpu_multirect_plane_states {
+	const struct drm_plane_state *r0;
+	const struct drm_plane_state *r1;
+};
+
+#define to_dpu_plane_state(x) \
+	container_of(x, struct dpu_plane_state, base)
+
+/**
+ * dpu_plane_pipe - return sspp identifier for the given plane
+ * @plane:   Pointer to DRM plane object
+ * Returns: sspp identifier of the given plane
+ */
+enum dpu_sspp dpu_plane_pipe(struct drm_plane *plane);
+
+/**
+ * is_dpu_plane_virtual - check for virtual plane
+ * @plane: Pointer to DRM plane object
+ * returns: true - if the plane is virtual
+ *          false - if the plane is primary
+ */
+bool is_dpu_plane_virtual(struct drm_plane *plane);
+
+/**
+ * dpu_plane_get_ctl_flush - get control flush mask
+ * @plane:   Pointer to DRM plane object
+ * @ctl: Pointer to control hardware
+ * @flush_sspp: Pointer to sspp flush control word
+ */
+void dpu_plane_get_ctl_flush(struct drm_plane *plane, struct dpu_hw_ctl *ctl,
+		u32 *flush_sspp);
+
+/**
+ * dpu_plane_restore - restore hw state if previously power collapsed
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_restore(struct drm_plane *plane);
+
+/**
+ * dpu_plane_flush - final plane operations before commit flush
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_flush(struct drm_plane *plane);
+
+/**
+ * dpu_plane_kickoff - final plane operations before commit kickoff
+ * @plane: Pointer to drm plane structure
+ */
+void dpu_plane_kickoff(struct drm_plane *plane);
+
+/**
+ * dpu_plane_set_error: enable/disable error condition
+ * @plane: pointer to drm_plane structure
+ */
+void dpu_plane_set_error(struct drm_plane *plane, bool error);
+
+/**
+ * dpu_plane_init - create new dpu plane for the given pipe
+ * @dev:   Pointer to DRM device
+ * @pipe:  dpu hardware pipe identifier
+ * @primary_plane: true if this pipe is primary plane for crtc
+ * @possible_crtcs: bitmask of crtc that can be attached to the given pipe
+ * @master_plane_id: primary plane id of a multirect pipe. 0 value passed for
+ *                   a regular plane initialization. A non-zero primary plane
+ *                   id will be passed for a virtual pipe initialization.
+ *
+ */
+struct drm_plane *dpu_plane_init(struct drm_device *dev,
+		uint32_t pipe, bool primary_plane,
+		unsigned long possible_crtcs, u32 master_plane_id);
+
+/**
+ * dpu_plane_validate_multirecti_v2 - validate the multirect planes
+ *				      against hw limitations
+ * @plane: drm plate states of the multirect pair
+ */
+int dpu_plane_validate_multirect_v2(struct dpu_multirect_plane_states *plane);
+
+/**
+ * dpu_plane_clear_multirect - clear multirect bits for the given pipe
+ * @drm_state: Pointer to DRM plane state
+ */
+void dpu_plane_clear_multirect(const struct drm_plane_state *drm_state);
+
+/**
+ * dpu_plane_wait_input_fence - wait for input fence object
+ * @plane:   Pointer to DRM plane object
+ * @wait_ms: Wait timeout value
+ * Returns: Zero on success
+ */
+int dpu_plane_wait_input_fence(struct drm_plane *plane, uint32_t wait_ms);
+
+/**
+ * dpu_plane_color_fill - enables color fill on plane
+ * @plane:  Pointer to DRM plane object
+ * @color:  RGB fill color value, [23..16] Blue, [15..8] Green, [7..0] Red
+ * @alpha:  8-bit fill alpha value, 255 selects 100% alpha
+ * Returns: 0 on success
+ */
+int dpu_plane_color_fill(struct drm_plane *plane,
+		uint32_t color, uint32_t alpha);
+
+/**
+ * dpu_plane_set_revalidate - sets revalidate flag which forces a full
+ *	validation of the plane properties in the next atomic check
+ * @plane: Pointer to DRM plane object
+ * @enable: Boolean to set/unset the flag
+ */
+void dpu_plane_set_revalidate(struct drm_plane *plane, bool enable);
+
+#endif /* _DPU_PLANE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
new file mode 100644
index 000000000000..a68f1249388c
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.c
@@ -0,0 +1,249 @@
+/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d]: " fmt, __func__, __LINE__
+
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/string.h>
+#include <linux/of_address.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <linux/of_platform.h>
+
+#include "dpu_power_handle.h"
+#include "dpu_trace.h"
+
+static const char *data_bus_name[DPU_POWER_HANDLE_DBUS_ID_MAX] = {
+	[DPU_POWER_HANDLE_DBUS_ID_MNOC] = "qcom,dpu-data-bus",
+	[DPU_POWER_HANDLE_DBUS_ID_LLCC] = "qcom,dpu-llcc-bus",
+	[DPU_POWER_HANDLE_DBUS_ID_EBI] = "qcom,dpu-ebi-bus",
+};
+
+const char *dpu_power_handle_get_dbus_name(u32 bus_id)
+{
+	if (bus_id < DPU_POWER_HANDLE_DBUS_ID_MAX)
+		return data_bus_name[bus_id];
+
+	return NULL;
+}
+
+static void dpu_power_event_trigger_locked(struct dpu_power_handle *phandle,
+		u32 event_type)
+{
+	struct dpu_power_event *event;
+
+	list_for_each_entry(event, &phandle->event_list, list) {
+		if (event->event_type & event_type)
+			event->cb_fnc(event_type, event->usr);
+	}
+}
+
+struct dpu_power_client *dpu_power_client_create(
+	struct dpu_power_handle *phandle, char *client_name)
+{
+	struct dpu_power_client *client;
+	static u32 id;
+
+	if (!client_name || !phandle) {
+		pr_err("client name is null or invalid power data\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	client = kzalloc(sizeof(struct dpu_power_client), GFP_KERNEL);
+	if (!client)
+		return ERR_PTR(-ENOMEM);
+
+	mutex_lock(&phandle->phandle_lock);
+	strlcpy(client->name, client_name, MAX_CLIENT_NAME_LEN);
+	client->usecase_ndx = VOTE_INDEX_DISABLE;
+	client->id = id;
+	client->active = true;
+	pr_debug("client %s created:%pK id :%d\n", client_name,
+		client, id);
+	id++;
+	list_add(&client->list, &phandle->power_client_clist);
+	mutex_unlock(&phandle->phandle_lock);
+
+	return client;
+}
+
+void dpu_power_client_destroy(struct dpu_power_handle *phandle,
+	struct dpu_power_client *client)
+{
+	if (!client  || !phandle) {
+		pr_err("reg bus vote: invalid client handle\n");
+	} else if (!client->active) {
+		pr_err("dpu power deinit already done\n");
+		kfree(client);
+	} else {
+		pr_debug("bus vote client %s destroyed:%pK id:%u\n",
+			client->name, client, client->id);
+		mutex_lock(&phandle->phandle_lock);
+		list_del_init(&client->list);
+		mutex_unlock(&phandle->phandle_lock);
+		kfree(client);
+	}
+}
+
+void dpu_power_resource_init(struct platform_device *pdev,
+	struct dpu_power_handle *phandle)
+{
+	phandle->dev = &pdev->dev;
+
+	INIT_LIST_HEAD(&phandle->power_client_clist);
+	INIT_LIST_HEAD(&phandle->event_list);
+
+	mutex_init(&phandle->phandle_lock);
+}
+
+void dpu_power_resource_deinit(struct platform_device *pdev,
+	struct dpu_power_handle *phandle)
+{
+	struct dpu_power_client *curr_client, *next_client;
+	struct dpu_power_event *curr_event, *next_event;
+
+	if (!phandle || !pdev) {
+		pr_err("invalid input param\n");
+		return;
+	}
+
+	mutex_lock(&phandle->phandle_lock);
+	list_for_each_entry_safe(curr_client, next_client,
+			&phandle->power_client_clist, list) {
+		pr_err("cliend:%s-%d still registered with refcount:%d\n",
+				curr_client->name, curr_client->id,
+				curr_client->refcount);
+		curr_client->active = false;
+		list_del(&curr_client->list);
+	}
+
+	list_for_each_entry_safe(curr_event, next_event,
+			&phandle->event_list, list) {
+		pr_err("event:%d, client:%s still registered\n",
+				curr_event->event_type,
+				curr_event->client_name);
+		curr_event->active = false;
+		list_del(&curr_event->list);
+	}
+	mutex_unlock(&phandle->phandle_lock);
+}
+
+int dpu_power_resource_enable(struct dpu_power_handle *phandle,
+	struct dpu_power_client *pclient, bool enable)
+{
+	bool changed = false;
+	u32 max_usecase_ndx = VOTE_INDEX_DISABLE, prev_usecase_ndx;
+	struct dpu_power_client *client;
+
+	if (!phandle || !pclient) {
+		pr_err("invalid input argument\n");
+		return -EINVAL;
+	}
+
+	mutex_lock(&phandle->phandle_lock);
+	if (enable)
+		pclient->refcount++;
+	else if (pclient->refcount)
+		pclient->refcount--;
+
+	if (pclient->refcount)
+		pclient->usecase_ndx = VOTE_INDEX_LOW;
+	else
+		pclient->usecase_ndx = VOTE_INDEX_DISABLE;
+
+	list_for_each_entry(client, &phandle->power_client_clist, list) {
+		if (client->usecase_ndx < VOTE_INDEX_MAX &&
+		    client->usecase_ndx > max_usecase_ndx)
+			max_usecase_ndx = client->usecase_ndx;
+	}
+
+	if (phandle->current_usecase_ndx != max_usecase_ndx) {
+		changed = true;
+		prev_usecase_ndx = phandle->current_usecase_ndx;
+		phandle->current_usecase_ndx = max_usecase_ndx;
+	}
+
+	pr_debug("%pS: changed=%d current idx=%d request client %s id:%u enable:%d refcount:%d\n",
+		__builtin_return_address(0), changed, max_usecase_ndx,
+		pclient->name, pclient->id, enable, pclient->refcount);
+
+	if (!changed)
+		goto end;
+
+	if (enable) {
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_PRE_ENABLE);
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_POST_ENABLE);
+
+	} else {
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_PRE_DISABLE);
+		dpu_power_event_trigger_locked(phandle,
+				DPU_POWER_EVENT_POST_DISABLE);
+	}
+
+end:
+	mutex_unlock(&phandle->phandle_lock);
+	return 0;
+}
+
+struct dpu_power_event *dpu_power_handle_register_event(
+		struct dpu_power_handle *phandle,
+		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
+		void *usr, char *client_name)
+{
+	struct dpu_power_event *event;
+
+	if (!phandle) {
+		pr_err("invalid power handle\n");
+		return ERR_PTR(-EINVAL);
+	} else if (!cb_fnc || !event_type) {
+		pr_err("no callback fnc or event type\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	event = kzalloc(sizeof(struct dpu_power_event), GFP_KERNEL);
+	if (!event)
+		return ERR_PTR(-ENOMEM);
+
+	event->event_type = event_type;
+	event->cb_fnc = cb_fnc;
+	event->usr = usr;
+	strlcpy(event->client_name, client_name, MAX_CLIENT_NAME_LEN);
+	event->active = true;
+
+	mutex_lock(&phandle->phandle_lock);
+	list_add(&event->list, &phandle->event_list);
+	mutex_unlock(&phandle->phandle_lock);
+
+	return event;
+}
+
+void dpu_power_handle_unregister_event(
+		struct dpu_power_handle *phandle,
+		struct dpu_power_event *event)
+{
+	if (!phandle || !event) {
+		pr_err("invalid phandle or event\n");
+	} else if (!event->active) {
+		pr_err("power handle deinit already done\n");
+		kfree(event);
+	} else {
+		mutex_lock(&phandle->phandle_lock);
+		list_del_init(&event->list);
+		mutex_unlock(&phandle->phandle_lock);
+		kfree(event);
+	}
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
new file mode 100644
index 000000000000..344f74464eca
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_power_handle.h
@@ -0,0 +1,225 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef _DPU_POWER_HANDLE_H_
+#define _DPU_POWER_HANDLE_H_
+
+#define MAX_CLIENT_NAME_LEN 128
+
+#define DPU_POWER_HANDLE_ENABLE_BUS_AB_QUOTA	0
+#define DPU_POWER_HANDLE_DISABLE_BUS_AB_QUOTA	0
+#define DPU_POWER_HANDLE_ENABLE_BUS_IB_QUOTA	1600000000
+#define DPU_POWER_HANDLE_DISABLE_BUS_IB_QUOTA	0
+
+#include "dpu_io_util.h"
+
+/* event will be triggered before power handler disable */
+#define DPU_POWER_EVENT_PRE_DISABLE	0x1
+
+/* event will be triggered after power handler disable */
+#define DPU_POWER_EVENT_POST_DISABLE	0x2
+
+/* event will be triggered before power handler enable */
+#define DPU_POWER_EVENT_PRE_ENABLE	0x4
+
+/* event will be triggered after power handler enable */
+#define DPU_POWER_EVENT_POST_ENABLE	0x8
+
+/**
+ * mdss_bus_vote_type: register bus vote type
+ * VOTE_INDEX_DISABLE: removes the client vote
+ * VOTE_INDEX_LOW: keeps the lowest vote for register bus
+ * VOTE_INDEX_MAX: invalid
+ */
+enum mdss_bus_vote_type {
+	VOTE_INDEX_DISABLE,
+	VOTE_INDEX_LOW,
+	VOTE_INDEX_MAX,
+};
+
+/**
+ * enum dpu_power_handle_data_bus_client - type of axi bus clients
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT: core real-time bus client
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT: core non-real-time bus client
+ * @DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX: maximum number of bus client type
+ */
+enum dpu_power_handle_data_bus_client {
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_RT,
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_NRT,
+	DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX
+};
+
+/**
+ * enum DPU_POWER_HANDLE_DBUS_ID - data bus identifier
+ * @DPU_POWER_HANDLE_DBUS_ID_MNOC: DPU/MNOC data bus
+ * @DPU_POWER_HANDLE_DBUS_ID_LLCC: MNOC/LLCC data bus
+ * @DPU_POWER_HANDLE_DBUS_ID_EBI: LLCC/EBI data bus
+ */
+enum DPU_POWER_HANDLE_DBUS_ID {
+	DPU_POWER_HANDLE_DBUS_ID_MNOC,
+	DPU_POWER_HANDLE_DBUS_ID_LLCC,
+	DPU_POWER_HANDLE_DBUS_ID_EBI,
+	DPU_POWER_HANDLE_DBUS_ID_MAX,
+};
+
+/**
+ * struct dpu_power_client: stores the power client for dpu driver
+ * @name:	name of the client
+ * @usecase_ndx: current regs bus vote type
+ * @refcount:	current refcount if multiple modules are using same
+ *              same client for enable/disable. Power module will
+ *              aggregate the refcount and vote accordingly for this
+ *              client.
+ * @id:		assigned during create. helps for debugging.
+ * @list:	list to attach power handle master list
+ * @ab:         arbitrated bandwidth for each bus client
+ * @ib:         instantaneous bandwidth for each bus client
+ * @active:	inidcates the state of dpu power handle
+ */
+struct dpu_power_client {
+	char name[MAX_CLIENT_NAME_LEN];
+	short usecase_ndx;
+	short refcount;
+	u32 id;
+	struct list_head list;
+	u64 ab[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
+	u64 ib[DPU_POWER_HANDLE_DATA_BUS_CLIENT_MAX];
+	bool active;
+};
+
+/*
+ * struct dpu_power_event - local event registration structure
+ * @client_name: name of the client registering
+ * @cb_fnc: pointer to desired callback function
+ * @usr: user pointer to pass to callback event trigger
+ * @event: refer to DPU_POWER_HANDLE_EVENT_*
+ * @list: list to attach event master list
+ * @active: indicates the state of dpu power handle
+ */
+struct dpu_power_event {
+	char client_name[MAX_CLIENT_NAME_LEN];
+	void (*cb_fnc)(u32 event_type, void *usr);
+	void *usr;
+	u32 event_type;
+	struct list_head list;
+	bool active;
+};
+
+/**
+ * struct dpu_power_handle: power handle main struct
+ * @client_clist: master list to store all clients
+ * @phandle_lock: lock to synchronize the enable/disable
+ * @dev: pointer to device structure
+ * @usecase_ndx: current usecase index
+ * @event_list: current power handle event list
+ */
+struct dpu_power_handle {
+	struct list_head power_client_clist;
+	struct mutex phandle_lock;
+	struct device *dev;
+	u32 current_usecase_ndx;
+	struct list_head event_list;
+};
+
+/**
+ * dpu_power_resource_init() - initializes the dpu power handle
+ * @pdev:   platform device to search the power resources
+ * @pdata:  power handle to store the power resources
+ */
+void dpu_power_resource_init(struct platform_device *pdev,
+	struct dpu_power_handle *pdata);
+
+/**
+ * dpu_power_resource_deinit() - release the dpu power handle
+ * @pdev:   platform device for power resources
+ * @pdata:  power handle containing the resources
+ *
+ * Return: error code.
+ */
+void dpu_power_resource_deinit(struct platform_device *pdev,
+	struct dpu_power_handle *pdata);
+
+/**
+ * dpu_power_client_create() - create the client on power handle
+ * @pdata:  power handle containing the resources
+ * @client_name: new client name for registration
+ *
+ * Return: error code.
+ */
+struct dpu_power_client *dpu_power_client_create(struct dpu_power_handle *pdata,
+	char *client_name);
+
+/**
+ * dpu_power_client_destroy() - destroy the client on power handle
+ * @pdata:  power handle containing the resources
+ * @client_name: new client name for registration
+ *
+ * Return: none
+ */
+void dpu_power_client_destroy(struct dpu_power_handle *phandle,
+	struct dpu_power_client *client);
+
+/**
+ * dpu_power_resource_enable() - enable/disable the power resources
+ * @pdata:  power handle containing the resources
+ * @client: client information to enable/disable its vote
+ * @enable: boolean request for enable/disable
+ *
+ * Return: error code.
+ */
+int dpu_power_resource_enable(struct dpu_power_handle *pdata,
+	struct dpu_power_client *pclient, bool enable);
+
+/**
+ * dpu_power_data_bus_bandwidth_ctrl() - control data bus bandwidth enable
+ * @phandle:  power handle containing the resources
+ * @client: client information to bandwidth control
+ * @enable: true to enable bandwidth for data base
+ *
+ * Return: none
+ */
+void dpu_power_data_bus_bandwidth_ctrl(struct dpu_power_handle *phandle,
+		struct dpu_power_client *pclient, int enable);
+
+/**
+ * dpu_power_handle_register_event - register a callback function for an event.
+ *	Clients can register for multiple events with a single register.
+ *	Any block with access to phandle can register for the event
+ *	notification.
+ * @phandle:	power handle containing the resources
+ * @event_type:	event type to register; refer DPU_POWER_HANDLE_EVENT_*
+ * @cb_fnc:	pointer to desired callback function
+ * @usr:	user pointer to pass to callback on event trigger
+ *
+ * Return:	event pointer if success, or error code otherwise
+ */
+struct dpu_power_event *dpu_power_handle_register_event(
+		struct dpu_power_handle *phandle,
+		u32 event_type, void (*cb_fnc)(u32 event_type, void *usr),
+		void *usr, char *client_name);
+/**
+ * dpu_power_handle_unregister_event - unregister callback for event(s)
+ * @phandle:	power handle containing the resources
+ * @event:	event pointer returned after power handle register
+ */
+void dpu_power_handle_unregister_event(struct dpu_power_handle *phandle,
+		struct dpu_power_event *event);
+
+/**
+ * dpu_power_handle_get_dbus_name - get name of given data bus identifier
+ * @bus_id:	data bus identifier
+ * Return:	Pointer to name string if success; NULL otherwise
+ */
+const char *dpu_power_handle_get_dbus_name(u32 bus_id);
+
+#endif /* _DPU_POWER_HANDLE_H_ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
new file mode 100644
index 000000000000..13c0a36d4ef9
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -0,0 +1,1079 @@
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#define pr_fmt(fmt)	"[drm:%s] " fmt, __func__
+#include "dpu_kms.h"
+#include "dpu_hw_lm.h"
+#include "dpu_hw_ctl.h"
+#include "dpu_hw_cdm.h"
+#include "dpu_hw_pingpong.h"
+#include "dpu_hw_intf.h"
+#include "dpu_encoder.h"
+#include "dpu_trace.h"
+
+#define RESERVED_BY_OTHER(h, r) \
+	((h)->rsvp && ((h)->rsvp->enc_id != (r)->enc_id))
+
+#define RM_RQ_LOCK(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_LOCK))
+#define RM_RQ_CLEAR(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_RESERVE_CLEAR))
+#define RM_RQ_DS(r) ((r)->top_ctrl & BIT(DPU_RM_TOPCTL_DS))
+#define RM_IS_TOPOLOGY_MATCH(t, r) ((t).num_lm == (r).num_lm && \
+				(t).num_comp_enc == (r).num_enc && \
+				(t).num_intf == (r).num_intf)
+
+struct dpu_rm_topology_def {
+	enum dpu_rm_topology_name top_name;
+	int num_lm;
+	int num_comp_enc;
+	int num_intf;
+	int num_ctl;
+	int needs_split_display;
+};
+
+static const struct dpu_rm_topology_def g_top_table[] = {
+	{   DPU_RM_TOPOLOGY_NONE,                 0, 0, 0, 0, false },
+	{   DPU_RM_TOPOLOGY_SINGLEPIPE,           1, 0, 1, 1, false },
+	{   DPU_RM_TOPOLOGY_DUALPIPE,             2, 0, 2, 2, true  },
+	{   DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE,     2, 0, 1, 1, false },
+};
+
+/**
+ * struct dpu_rm_requirements - Reservation requirements parameter bundle
+ * @top_ctrl:  topology control preference from kernel client
+ * @top:       selected topology for the display
+ * @hw_res:	   Hardware resources required as reported by the encoders
+ */
+struct dpu_rm_requirements {
+	uint64_t top_ctrl;
+	const struct dpu_rm_topology_def *topology;
+	struct dpu_encoder_hw_resources hw_res;
+};
+
+/**
+ * struct dpu_rm_rsvp - Use Case Reservation tagging structure
+ *	Used to tag HW blocks as reserved by a CRTC->Encoder->Connector chain
+ *	By using as a tag, rather than lists of pointers to HW blocks used
+ *	we can avoid some list management since we don't know how many blocks
+ *	of each type a given use case may require.
+ * @list:	List head for list of all reservations
+ * @seq:	Global RSVP sequence number for debugging, especially for
+ *		differentiating differenct allocations for same encoder.
+ * @enc_id:	Reservations are tracked by Encoder DRM object ID.
+ *		CRTCs may be connected to multiple Encoders.
+ *		An encoder or connector id identifies the display path.
+ * @topology	DRM<->HW topology use case
+ */
+struct dpu_rm_rsvp {
+	struct list_head list;
+	uint32_t seq;
+	uint32_t enc_id;
+	enum dpu_rm_topology_name topology;
+};
+
+/**
+ * struct dpu_rm_hw_blk - hardware block tracking list member
+ * @list:	List head for list of all hardware blocks tracking items
+ * @rsvp:	Pointer to use case reservation if reserved by a client
+ * @rsvp_nxt:	Temporary pointer used during reservation to the incoming
+ *		request. Will be swapped into rsvp if proposal is accepted
+ * @type:	Type of hardware block this structure tracks
+ * @id:		Hardware ID number, within it's own space, ie. LM_X
+ * @catalog:	Pointer to the hardware catalog entry for this block
+ * @hw:		Pointer to the hardware register access object for this block
+ */
+struct dpu_rm_hw_blk {
+	struct list_head list;
+	struct dpu_rm_rsvp *rsvp;
+	struct dpu_rm_rsvp *rsvp_nxt;
+	enum dpu_hw_blk_type type;
+	uint32_t id;
+	struct dpu_hw_blk *hw;
+};
+
+/**
+ * dpu_rm_dbg_rsvp_stage - enum of steps in making reservation for event logging
+ */
+enum dpu_rm_dbg_rsvp_stage {
+	DPU_RM_STAGE_BEGIN,
+	DPU_RM_STAGE_AFTER_CLEAR,
+	DPU_RM_STAGE_AFTER_RSVPNEXT,
+	DPU_RM_STAGE_FINAL
+};
+
+static void _dpu_rm_print_rsvps(
+		struct dpu_rm *rm,
+		enum dpu_rm_dbg_rsvp_stage stage)
+{
+	struct dpu_rm_rsvp *rsvp;
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+
+	DPU_DEBUG("%d\n", stage);
+
+	list_for_each_entry(rsvp, &rm->rsvps, list) {
+		DRM_DEBUG_KMS("%d rsvp[s%ue%u] topology %d\n", stage, rsvp->seq,
+			      rsvp->enc_id, rsvp->topology);
+	}
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (!blk->rsvp && !blk->rsvp_nxt)
+				continue;
+
+			DRM_DEBUG_KMS("%d rsvp[s%ue%u->s%ue%u] %d %d\n", stage,
+				(blk->rsvp) ? blk->rsvp->seq : 0,
+				(blk->rsvp) ? blk->rsvp->enc_id : 0,
+				(blk->rsvp_nxt) ? blk->rsvp_nxt->seq : 0,
+				(blk->rsvp_nxt) ? blk->rsvp_nxt->enc_id : 0,
+				blk->type, blk->id);
+		}
+	}
+}
+
+struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm)
+{
+	return rm->hw_mdp;
+}
+
+enum dpu_rm_topology_name
+dpu_rm_get_topology_name(struct msm_display_topology topology)
+{
+	int i;
+
+	for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++)
+		if (RM_IS_TOPOLOGY_MATCH(g_top_table[i], topology))
+			return g_top_table[i].top_name;
+
+	return DPU_RM_TOPOLOGY_NONE;
+}
+
+void dpu_rm_init_hw_iter(
+		struct dpu_rm_hw_iter *iter,
+		uint32_t enc_id,
+		enum dpu_hw_blk_type type)
+{
+	memset(iter, 0, sizeof(*iter));
+	iter->enc_id = enc_id;
+	iter->type = type;
+}
+
+static bool _dpu_rm_get_hw_locked(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
+{
+	struct list_head *blk_list;
+
+	if (!rm || !i || i->type >= DPU_HW_BLK_MAX) {
+		DPU_ERROR("invalid rm\n");
+		return false;
+	}
+
+	i->hw = NULL;
+	blk_list = &rm->hw_blks[i->type];
+
+	if (i->blk && (&i->blk->list == blk_list)) {
+		DPU_DEBUG("attempt resume iteration past last\n");
+		return false;
+	}
+
+	i->blk = list_prepare_entry(i->blk, blk_list, list);
+
+	list_for_each_entry_continue(i->blk, blk_list, list) {
+		struct dpu_rm_rsvp *rsvp = i->blk->rsvp;
+
+		if (i->blk->type != i->type) {
+			DPU_ERROR("found incorrect block type %d on %d list\n",
+					i->blk->type, i->type);
+			return false;
+		}
+
+		if ((i->enc_id == 0) || (rsvp && rsvp->enc_id == i->enc_id)) {
+			i->hw = i->blk->hw;
+			DPU_DEBUG("found type %d id %d for enc %d\n",
+					i->type, i->blk->id, i->enc_id);
+			return true;
+		}
+	}
+
+	DPU_DEBUG("no match, type %d for enc %d\n", i->type, i->enc_id);
+
+	return false;
+}
+
+bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *i)
+{
+	bool ret;
+
+	mutex_lock(&rm->rm_lock);
+	ret = _dpu_rm_get_hw_locked(rm, i);
+	mutex_unlock(&rm->rm_lock);
+
+	return ret;
+}
+
+static void _dpu_rm_hw_destroy(enum dpu_hw_blk_type type, void *hw)
+{
+	switch (type) {
+	case DPU_HW_BLK_LM:
+		dpu_hw_lm_destroy(hw);
+		break;
+	case DPU_HW_BLK_CTL:
+		dpu_hw_ctl_destroy(hw);
+		break;
+	case DPU_HW_BLK_CDM:
+		dpu_hw_cdm_destroy(hw);
+		break;
+	case DPU_HW_BLK_PINGPONG:
+		dpu_hw_pingpong_destroy(hw);
+		break;
+	case DPU_HW_BLK_INTF:
+		dpu_hw_intf_destroy(hw);
+		break;
+	case DPU_HW_BLK_SSPP:
+		/* SSPPs are not managed by the resource manager */
+	case DPU_HW_BLK_TOP:
+		/* Top is a singleton, not managed in hw_blks list */
+	case DPU_HW_BLK_MAX:
+	default:
+		DPU_ERROR("unsupported block type %d\n", type);
+		break;
+	}
+}
+
+int dpu_rm_destroy(struct dpu_rm *rm)
+{
+
+	struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt;
+	struct dpu_rm_hw_blk *hw_cur, *hw_nxt;
+	enum dpu_hw_blk_type type;
+
+	if (!rm) {
+		DPU_ERROR("invalid rm\n");
+		return -EINVAL;
+	}
+
+	list_for_each_entry_safe(rsvp_cur, rsvp_nxt, &rm->rsvps, list) {
+		list_del(&rsvp_cur->list);
+		kfree(rsvp_cur);
+	}
+
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry_safe(hw_cur, hw_nxt, &rm->hw_blks[type],
+				list) {
+			list_del(&hw_cur->list);
+			_dpu_rm_hw_destroy(hw_cur->type, hw_cur->hw);
+			kfree(hw_cur);
+		}
+	}
+
+	dpu_hw_mdp_destroy(rm->hw_mdp);
+	rm->hw_mdp = NULL;
+
+	mutex_destroy(&rm->rm_lock);
+
+	return 0;
+}
+
+static int _dpu_rm_hw_blk_create(
+		struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		enum dpu_hw_blk_type type,
+		uint32_t id,
+		void *hw_catalog_info)
+{
+	struct dpu_rm_hw_blk *blk;
+	struct dpu_hw_mdp *hw_mdp;
+	void *hw;
+
+	hw_mdp = rm->hw_mdp;
+
+	switch (type) {
+	case DPU_HW_BLK_LM:
+		hw = dpu_hw_lm_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_CTL:
+		hw = dpu_hw_ctl_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_CDM:
+		hw = dpu_hw_cdm_init(id, mmio, cat, hw_mdp);
+		break;
+	case DPU_HW_BLK_PINGPONG:
+		hw = dpu_hw_pingpong_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_INTF:
+		hw = dpu_hw_intf_init(id, mmio, cat);
+		break;
+	case DPU_HW_BLK_SSPP:
+		/* SSPPs are not managed by the resource manager */
+	case DPU_HW_BLK_TOP:
+		/* Top is a singleton, not managed in hw_blks list */
+	case DPU_HW_BLK_MAX:
+	default:
+		DPU_ERROR("unsupported block type %d\n", type);
+		return -EINVAL;
+	}
+
+	if (IS_ERR_OR_NULL(hw)) {
+		DPU_ERROR("failed hw object creation: type %d, err %ld\n",
+				type, PTR_ERR(hw));
+		return -EFAULT;
+	}
+
+	blk = kzalloc(sizeof(*blk), GFP_KERNEL);
+	if (!blk) {
+		_dpu_rm_hw_destroy(type, hw);
+		return -ENOMEM;
+	}
+
+	blk->type = type;
+	blk->id = id;
+	blk->hw = hw;
+	list_add_tail(&blk->list, &rm->hw_blks[type]);
+
+	return 0;
+}
+
+int dpu_rm_init(struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void __iomem *mmio,
+		struct drm_device *dev)
+{
+	int rc, i;
+	enum dpu_hw_blk_type type;
+
+	if (!rm || !cat || !mmio || !dev) {
+		DPU_ERROR("invalid kms\n");
+		return -EINVAL;
+	}
+
+	/* Clear, setup lists */
+	memset(rm, 0, sizeof(*rm));
+
+	mutex_init(&rm->rm_lock);
+
+	INIT_LIST_HEAD(&rm->rsvps);
+	for (type = 0; type < DPU_HW_BLK_MAX; type++)
+		INIT_LIST_HEAD(&rm->hw_blks[type]);
+
+	rm->dev = dev;
+
+	/* Some of the sub-blocks require an mdptop to be created */
+	rm->hw_mdp = dpu_hw_mdptop_init(MDP_TOP, mmio, cat);
+	if (IS_ERR_OR_NULL(rm->hw_mdp)) {
+		rc = PTR_ERR(rm->hw_mdp);
+		rm->hw_mdp = NULL;
+		DPU_ERROR("failed: mdp hw not available\n");
+		goto fail;
+	}
+
+	/* Interrogate HW catalog and create tracking items for hw blocks */
+	for (i = 0; i < cat->mixer_count; i++) {
+		struct dpu_lm_cfg *lm = &cat->mixer[i];
+
+		if (lm->pingpong == PINGPONG_MAX) {
+			DPU_DEBUG("skip mixer %d without pingpong\n", lm->id);
+			continue;
+		}
+
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_LM,
+				cat->mixer[i].id, &cat->mixer[i]);
+		if (rc) {
+			DPU_ERROR("failed: lm hw not available\n");
+			goto fail;
+		}
+
+		if (!rm->lm_max_width) {
+			rm->lm_max_width = lm->sblk->maxwidth;
+		} else if (rm->lm_max_width != lm->sblk->maxwidth) {
+			/*
+			 * Don't expect to have hw where lm max widths differ.
+			 * If found, take the min.
+			 */
+			DPU_ERROR("unsupported: lm maxwidth differs\n");
+			if (rm->lm_max_width > lm->sblk->maxwidth)
+				rm->lm_max_width = lm->sblk->maxwidth;
+		}
+	}
+
+	for (i = 0; i < cat->pingpong_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_PINGPONG,
+				cat->pingpong[i].id, &cat->pingpong[i]);
+		if (rc) {
+			DPU_ERROR("failed: pp hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->intf_count; i++) {
+		if (cat->intf[i].type == INTF_NONE) {
+			DPU_DEBUG("skip intf %d with type none\n", i);
+			continue;
+		}
+
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_INTF,
+				cat->intf[i].id, &cat->intf[i]);
+		if (rc) {
+			DPU_ERROR("failed: intf hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->ctl_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CTL,
+				cat->ctl[i].id, &cat->ctl[i]);
+		if (rc) {
+			DPU_ERROR("failed: ctl hw not available\n");
+			goto fail;
+		}
+	}
+
+	for (i = 0; i < cat->cdm_count; i++) {
+		rc = _dpu_rm_hw_blk_create(rm, cat, mmio, DPU_HW_BLK_CDM,
+				cat->cdm[i].id, &cat->cdm[i]);
+		if (rc) {
+			DPU_ERROR("failed: cdm hw not available\n");
+			goto fail;
+		}
+	}
+
+	return 0;
+
+fail:
+	dpu_rm_destroy(rm);
+
+	return rc;
+}
+
+/**
+ * _dpu_rm_check_lm_and_get_connected_blks - check if proposed layer mixer meets
+ *	proposed use case requirements, incl. hardwired dependent blocks like
+ *	pingpong
+ * @rm: dpu resource manager handle
+ * @rsvp: reservation currently being created
+ * @reqs: proposed use case requirements
+ * @lm: proposed layer mixer, function checks if lm, and all other hardwired
+ *      blocks connected to the lm (pp) is available and appropriate
+ * @pp: output parameter, pingpong block attached to the layer mixer.
+ *      NULL if pp was not available, or not matching requirements.
+ * @primary_lm: if non-null, this function check if lm is compatible primary_lm
+ *              as well as satisfying all other requirements
+ * @Return: true if lm matches all requirements, false otherwise
+ */
+static bool _dpu_rm_check_lm_and_get_connected_blks(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs,
+		struct dpu_rm_hw_blk *lm,
+		struct dpu_rm_hw_blk **pp,
+		struct dpu_rm_hw_blk *primary_lm)
+{
+	const struct dpu_lm_cfg *lm_cfg = to_dpu_hw_mixer(lm->hw)->cap;
+	struct dpu_rm_hw_iter iter;
+
+	*pp = NULL;
+
+	DPU_DEBUG("check lm %d pp %d\n",
+			   lm_cfg->id, lm_cfg->pingpong);
+
+	/* Check if this layer mixer is a peer of the proposed primary LM */
+	if (primary_lm) {
+		const struct dpu_lm_cfg *prim_lm_cfg =
+				to_dpu_hw_mixer(primary_lm->hw)->cap;
+
+		if (!test_bit(lm_cfg->id, &prim_lm_cfg->lm_pair_mask)) {
+			DPU_DEBUG("lm %d not peer of lm %d\n", lm_cfg->id,
+					prim_lm_cfg->id);
+			return false;
+		}
+	}
+
+	/* Already reserved? */
+	if (RESERVED_BY_OTHER(lm, rsvp)) {
+		DPU_DEBUG("lm %d already reserved\n", lm_cfg->id);
+		return false;
+	}
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_PINGPONG);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		if (iter.blk->id == lm_cfg->pingpong) {
+			*pp = iter.blk;
+			break;
+		}
+	}
+
+	if (!*pp) {
+		DPU_ERROR("failed to get pp on lm %d\n", lm_cfg->pingpong);
+		return false;
+	}
+
+	if (RESERVED_BY_OTHER(*pp, rsvp)) {
+		DPU_DEBUG("lm %d pp %d already reserved\n", lm->id,
+				(*pp)->id);
+		return false;
+	}
+
+	return true;
+}
+
+static int _dpu_rm_reserve_lms(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs)
+
+{
+	struct dpu_rm_hw_blk *lm[MAX_BLOCKS];
+	struct dpu_rm_hw_blk *pp[MAX_BLOCKS];
+	struct dpu_rm_hw_iter iter_i, iter_j;
+	int lm_count = 0;
+	int i, rc = 0;
+
+	if (!reqs->topology->num_lm) {
+		DPU_ERROR("invalid number of lm: %d\n", reqs->topology->num_lm);
+		return -EINVAL;
+	}
+
+	/* Find a primary mixer */
+	dpu_rm_init_hw_iter(&iter_i, 0, DPU_HW_BLK_LM);
+	while (lm_count != reqs->topology->num_lm &&
+			_dpu_rm_get_hw_locked(rm, &iter_i)) {
+		memset(&lm, 0, sizeof(lm));
+		memset(&pp, 0, sizeof(pp));
+
+		lm_count = 0;
+		lm[lm_count] = iter_i.blk;
+
+		if (!_dpu_rm_check_lm_and_get_connected_blks(
+				rm, rsvp, reqs, lm[lm_count],
+				&pp[lm_count], NULL))
+			continue;
+
+		++lm_count;
+
+		/* Valid primary mixer found, find matching peers */
+		dpu_rm_init_hw_iter(&iter_j, 0, DPU_HW_BLK_LM);
+
+		while (lm_count != reqs->topology->num_lm &&
+				_dpu_rm_get_hw_locked(rm, &iter_j)) {
+			if (iter_i.blk == iter_j.blk)
+				continue;
+
+			if (!_dpu_rm_check_lm_and_get_connected_blks(
+					rm, rsvp, reqs, iter_j.blk,
+					&pp[lm_count], iter_i.blk))
+				continue;
+
+			lm[lm_count] = iter_j.blk;
+			++lm_count;
+		}
+	}
+
+	if (lm_count != reqs->topology->num_lm) {
+		DPU_DEBUG("unable to find appropriate mixers\n");
+		return -ENAVAIL;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(lm); i++) {
+		if (!lm[i])
+			break;
+
+		lm[i]->rsvp_nxt = rsvp;
+		pp[i]->rsvp_nxt = rsvp;
+
+		trace_dpu_rm_reserve_lms(lm[i]->id, lm[i]->type, rsvp->enc_id,
+					 pp[i]->id);
+	}
+
+	return rc;
+}
+
+static int _dpu_rm_reserve_ctls(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		const struct dpu_rm_topology_def *top)
+{
+	struct dpu_rm_hw_blk *ctls[MAX_BLOCKS];
+	struct dpu_rm_hw_iter iter;
+	int i = 0;
+
+	memset(&ctls, 0, sizeof(ctls));
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CTL);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		const struct dpu_hw_ctl *ctl = to_dpu_hw_ctl(iter.blk->hw);
+		unsigned long features = ctl->caps->features;
+		bool has_split_display;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp))
+			continue;
+
+		has_split_display = BIT(DPU_CTL_SPLIT_DISPLAY) & features;
+
+		DPU_DEBUG("ctl %d caps 0x%lX\n", iter.blk->id, features);
+
+		if (top->needs_split_display != has_split_display)
+			continue;
+
+		ctls[i] = iter.blk;
+		DPU_DEBUG("ctl %d match\n", iter.blk->id);
+
+		if (++i == top->num_ctl)
+			break;
+	}
+
+	if (i != top->num_ctl)
+		return -ENAVAIL;
+
+	for (i = 0; i < ARRAY_SIZE(ctls) && i < top->num_ctl; i++) {
+		ctls[i]->rsvp_nxt = rsvp;
+		trace_dpu_rm_reserve_ctls(ctls[i]->id, ctls[i]->type,
+					  rsvp->enc_id);
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_cdm(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		uint32_t id,
+		enum dpu_hw_blk_type type)
+{
+	struct dpu_rm_hw_iter iter;
+
+	DRM_DEBUG_KMS("type %d id %d\n", type, id);
+
+	dpu_rm_init_hw_iter(&iter, 0, DPU_HW_BLK_CDM);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		const struct dpu_hw_cdm *cdm = to_dpu_hw_cdm(iter.blk->hw);
+		const struct dpu_cdm_cfg *caps = cdm->caps;
+		bool match = false;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp))
+			continue;
+
+		if (type == DPU_HW_BLK_INTF && id != INTF_MAX)
+			match = test_bit(id, &caps->intf_connect);
+
+		DRM_DEBUG_KMS("iter: type:%d id:%d enc:%d cdm:%lu match:%d\n",
+			      iter.blk->type, iter.blk->id, rsvp->enc_id,
+			      caps->intf_connect, match);
+
+		if (!match)
+			continue;
+
+		trace_dpu_rm_reserve_cdm(iter.blk->id, iter.blk->type,
+					 rsvp->enc_id);
+		iter.blk->rsvp_nxt = rsvp;
+		break;
+	}
+
+	if (!iter.hw) {
+		DPU_ERROR("couldn't reserve cdm for type %d id %d\n", type, id);
+		return -ENAVAIL;
+	}
+
+	return 0;
+}
+
+static int _dpu_rm_reserve_intf(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		uint32_t id,
+		enum dpu_hw_blk_type type,
+		bool needs_cdm)
+{
+	struct dpu_rm_hw_iter iter;
+	int ret = 0;
+
+	/* Find the block entry in the rm, and note the reservation */
+	dpu_rm_init_hw_iter(&iter, 0, type);
+	while (_dpu_rm_get_hw_locked(rm, &iter)) {
+		if (iter.blk->id != id)
+			continue;
+
+		if (RESERVED_BY_OTHER(iter.blk, rsvp)) {
+			DPU_ERROR("type %d id %d already reserved\n", type, id);
+			return -ENAVAIL;
+		}
+
+		iter.blk->rsvp_nxt = rsvp;
+		trace_dpu_rm_reserve_intf(iter.blk->id, iter.blk->type,
+					  rsvp->enc_id);
+		break;
+	}
+
+	/* Shouldn't happen since intfs are fixed at probe */
+	if (!iter.hw) {
+		DPU_ERROR("couldn't find type %d id %d\n", type, id);
+		return -EINVAL;
+	}
+
+	if (needs_cdm)
+		ret = _dpu_rm_reserve_cdm(rm, rsvp, id, type);
+
+	return ret;
+}
+
+static int _dpu_rm_reserve_intf_related_hw(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_encoder_hw_resources *hw_res)
+{
+	int i, ret = 0;
+	u32 id;
+
+	for (i = 0; i < ARRAY_SIZE(hw_res->intfs); i++) {
+		if (hw_res->intfs[i] == INTF_MODE_NONE)
+			continue;
+		id = i + INTF_0;
+		ret = _dpu_rm_reserve_intf(rm, rsvp, id,
+				DPU_HW_BLK_INTF, hw_res->needs_cdm);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int _dpu_rm_make_next_rsvp(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct dpu_rm_rsvp *rsvp,
+		struct dpu_rm_requirements *reqs)
+{
+	int ret;
+	struct dpu_rm_topology_def topology;
+
+	/* Create reservation info, tag reserved blocks with it as we go */
+	rsvp->seq = ++rm->rsvp_next_seq;
+	rsvp->enc_id = enc->base.id;
+	rsvp->topology = reqs->topology->top_name;
+	list_add_tail(&rsvp->list, &rm->rsvps);
+
+	ret = _dpu_rm_reserve_lms(rm, rsvp, reqs);
+	if (ret) {
+		DPU_ERROR("unable to find appropriate mixers\n");
+		return ret;
+	}
+
+	/*
+	 * Do assignment preferring to give away low-resource CTLs first:
+	 * - Check mixers without Split Display
+	 * - Only then allow to grab from CTLs with split display capability
+	 */
+	_dpu_rm_reserve_ctls(rm, rsvp, reqs->topology);
+	if (ret && !reqs->topology->needs_split_display) {
+		memcpy(&topology, reqs->topology, sizeof(topology));
+		topology.needs_split_display = true;
+		_dpu_rm_reserve_ctls(rm, rsvp, &topology);
+	}
+	if (ret) {
+		DPU_ERROR("unable to find appropriate CTL\n");
+		return ret;
+	}
+
+	/* Assign INTFs and blks whose usage is tied to them: CTL & CDM */
+	ret = _dpu_rm_reserve_intf_related_hw(rm, rsvp, &reqs->hw_res);
+	if (ret)
+		return ret;
+
+	return ret;
+}
+
+static int _dpu_rm_populate_requirements(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct dpu_rm_requirements *reqs,
+		struct msm_display_topology req_topology)
+{
+	int i;
+
+	memset(reqs, 0, sizeof(*reqs));
+
+	dpu_encoder_get_hw_resources(enc, &reqs->hw_res, conn_state);
+
+	for (i = 0; i < DPU_RM_TOPOLOGY_MAX; i++) {
+		if (RM_IS_TOPOLOGY_MATCH(g_top_table[i],
+					req_topology)) {
+			reqs->topology = &g_top_table[i];
+			break;
+		}
+	}
+
+	if (!reqs->topology) {
+		DPU_ERROR("invalid topology for the display\n");
+		return -EINVAL;
+	}
+
+	/**
+	 * Set the requirement based on caps if not set from user space
+	 * This will ensure to select LM tied with DS blocks
+	 * Currently, DS blocks are tied with LM 0 and LM 1 (primary display)
+	 */
+	if (!RM_RQ_DS(reqs) && rm->hw_mdp->caps->has_dest_scaler &&
+		conn_state->connector->connector_type == DRM_MODE_CONNECTOR_DSI)
+		reqs->top_ctrl |= BIT(DPU_RM_TOPCTL_DS);
+
+	DRM_DEBUG_KMS("top_ctrl: 0x%llX num_h_tiles: %d\n", reqs->top_ctrl,
+		      reqs->hw_res.display_num_of_h_tiles);
+	DRM_DEBUG_KMS("num_lm: %d num_ctl: %d topology: %d split_display: %d\n",
+		      reqs->topology->num_lm, reqs->topology->num_ctl,
+		      reqs->topology->top_name,
+		      reqs->topology->needs_split_display);
+
+	return 0;
+}
+
+static struct dpu_rm_rsvp *_dpu_rm_get_rsvp(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc)
+{
+	struct dpu_rm_rsvp *i;
+
+	if (!rm || !enc) {
+		DPU_ERROR("invalid params\n");
+		return NULL;
+	}
+
+	if (list_empty(&rm->rsvps))
+		return NULL;
+
+	list_for_each_entry(i, &rm->rsvps, list)
+		if (i->enc_id == enc->base.id)
+			return i;
+
+	return NULL;
+}
+
+static struct drm_connector *_dpu_rm_get_connector(
+		struct drm_encoder *enc)
+{
+	struct drm_connector *conn = NULL;
+	struct list_head *connector_list =
+			&enc->dev->mode_config.connector_list;
+
+	list_for_each_entry(conn, connector_list, head)
+		if (conn->encoder == enc)
+			return conn;
+
+	return NULL;
+}
+
+/**
+ * _dpu_rm_release_rsvp - release resources and release a reservation
+ * @rm:	KMS handle
+ * @rsvp:	RSVP pointer to release and release resources for
+ */
+static void _dpu_rm_release_rsvp(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct drm_connector *conn)
+{
+	struct dpu_rm_rsvp *rsvp_c, *rsvp_n;
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+
+	if (!rsvp)
+		return;
+
+	DPU_DEBUG("rel rsvp %d enc %d\n", rsvp->seq, rsvp->enc_id);
+
+	list_for_each_entry_safe(rsvp_c, rsvp_n, &rm->rsvps, list) {
+		if (rsvp == rsvp_c) {
+			list_del(&rsvp_c->list);
+			break;
+		}
+	}
+
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (blk->rsvp == rsvp) {
+				blk->rsvp = NULL;
+				DPU_DEBUG("rel rsvp %d enc %d %d %d\n",
+						rsvp->seq, rsvp->enc_id,
+						blk->type, blk->id);
+			}
+			if (blk->rsvp_nxt == rsvp) {
+				blk->rsvp_nxt = NULL;
+				DPU_DEBUG("rel rsvp_nxt %d enc %d %d %d\n",
+						rsvp->seq, rsvp->enc_id,
+						blk->type, blk->id);
+			}
+		}
+	}
+
+	kfree(rsvp);
+}
+
+void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc)
+{
+	struct dpu_rm_rsvp *rsvp;
+	struct drm_connector *conn;
+
+	if (!rm || !enc) {
+		DPU_ERROR("invalid params\n");
+		return;
+	}
+
+	mutex_lock(&rm->rm_lock);
+
+	rsvp = _dpu_rm_get_rsvp(rm, enc);
+	if (!rsvp) {
+		DPU_ERROR("failed to find rsvp for enc %d\n", enc->base.id);
+		goto end;
+	}
+
+	conn = _dpu_rm_get_connector(enc);
+	if (!conn) {
+		DPU_ERROR("failed to get connector for enc %d\n", enc->base.id);
+		goto end;
+	}
+
+	_dpu_rm_release_rsvp(rm, rsvp, conn);
+end:
+	mutex_unlock(&rm->rm_lock);
+}
+
+static int _dpu_rm_commit_rsvp(
+		struct dpu_rm *rm,
+		struct dpu_rm_rsvp *rsvp,
+		struct drm_connector_state *conn_state)
+{
+	struct dpu_rm_hw_blk *blk;
+	enum dpu_hw_blk_type type;
+	int ret = 0;
+
+	/* Swap next rsvp to be the active */
+	for (type = 0; type < DPU_HW_BLK_MAX; type++) {
+		list_for_each_entry(blk, &rm->hw_blks[type], list) {
+			if (blk->rsvp_nxt) {
+				blk->rsvp = blk->rsvp_nxt;
+				blk->rsvp_nxt = NULL;
+			}
+		}
+	}
+
+	if (!ret)
+		DRM_DEBUG_KMS("rsrv enc %d topology %d\n", rsvp->enc_id,
+			      rsvp->topology);
+
+	return ret;
+}
+
+int dpu_rm_reserve(
+		struct dpu_rm *rm,
+		struct drm_encoder *enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct msm_display_topology topology,
+		bool test_only)
+{
+	struct dpu_rm_rsvp *rsvp_cur, *rsvp_nxt;
+	struct dpu_rm_requirements reqs;
+	int ret;
+
+	if (!rm || !enc || !crtc_state || !conn_state) {
+		DPU_ERROR("invalid arguments\n");
+		return -EINVAL;
+	}
+
+	/* Check if this is just a page-flip */
+	if (!drm_atomic_crtc_needs_modeset(crtc_state))
+		return 0;
+
+	DRM_DEBUG_KMS("reserving hw for conn %d enc %d crtc %d test_only %d\n",
+		      conn_state->connector->base.id, enc->base.id,
+		      crtc_state->crtc->base.id, test_only);
+
+	mutex_lock(&rm->rm_lock);
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_BEGIN);
+
+	ret = _dpu_rm_populate_requirements(rm, enc, crtc_state,
+			conn_state, &reqs, topology);
+	if (ret) {
+		DPU_ERROR("failed to populate hw requirements\n");
+		goto end;
+	}
+
+	/*
+	 * We only support one active reservation per-hw-block. But to implement
+	 * transactional semantics for test-only, and for allowing failure while
+	 * modifying your existing reservation, over the course of this
+	 * function we can have two reservations:
+	 * Current: Existing reservation
+	 * Next: Proposed reservation. The proposed reservation may fail, or may
+	 *       be discarded if in test-only mode.
+	 * If reservation is successful, and we're not in test-only, then we
+	 * replace the current with the next.
+	 */
+	rsvp_nxt = kzalloc(sizeof(*rsvp_nxt), GFP_KERNEL);
+	if (!rsvp_nxt) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	rsvp_cur = _dpu_rm_get_rsvp(rm, enc);
+
+	/*
+	 * User can request that we clear out any reservation during the
+	 * atomic_check phase by using this CLEAR bit
+	 */
+	if (rsvp_cur && test_only && RM_RQ_CLEAR(&reqs)) {
+		DPU_DEBUG("test_only & CLEAR: clear rsvp[s%de%d]\n",
+				rsvp_cur->seq, rsvp_cur->enc_id);
+		_dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector);
+		rsvp_cur = NULL;
+		_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_CLEAR);
+	}
+
+	/* Check the proposed reservation, store it in hw's "next" field */
+	ret = _dpu_rm_make_next_rsvp(rm, enc, crtc_state, conn_state,
+			rsvp_nxt, &reqs);
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_AFTER_RSVPNEXT);
+
+	if (ret) {
+		DPU_ERROR("failed to reserve hw resources: %d\n", ret);
+		_dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector);
+	} else if (test_only && !RM_RQ_LOCK(&reqs)) {
+		/*
+		 * Normally, if test_only, test the reservation and then undo
+		 * However, if the user requests LOCK, then keep the reservation
+		 * made during the atomic_check phase.
+		 */
+		DPU_DEBUG("test_only: discard test rsvp[s%de%d]\n",
+				rsvp_nxt->seq, rsvp_nxt->enc_id);
+		_dpu_rm_release_rsvp(rm, rsvp_nxt, conn_state->connector);
+	} else {
+		if (test_only && RM_RQ_LOCK(&reqs))
+			DPU_DEBUG("test_only & LOCK: lock rsvp[s%de%d]\n",
+					rsvp_nxt->seq, rsvp_nxt->enc_id);
+
+		_dpu_rm_release_rsvp(rm, rsvp_cur, conn_state->connector);
+
+		ret = _dpu_rm_commit_rsvp(rm, rsvp_nxt, conn_state);
+	}
+
+	_dpu_rm_print_rsvps(rm, DPU_RM_STAGE_FINAL);
+
+end:
+	mutex_unlock(&rm->rm_lock);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
new file mode 100644
index 000000000000..ef3f67bedaa0
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
@@ -0,0 +1,199 @@
+/*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#ifndef __DPU_RM_H__
+#define __DPU_RM_H__
+
+#include <linux/list.h>
+
+#include "msm_kms.h"
+#include "dpu_hw_top.h"
+
+/**
+ * enum dpu_rm_topology_name - HW resource use case in use by connector
+ * @DPU_RM_TOPOLOGY_NONE:                 No topology in use currently
+ * @DPU_RM_TOPOLOGY_SINGLEPIPE:           1 LM, 1 PP, 1 INTF/WB
+ * @DPU_RM_TOPOLOGY_DUALPIPE:             2 LM, 2 PP, 2 INTF/WB
+ * @DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE:     2 LM, 2 PP, 3DMux, 1 INTF/WB
+ */
+enum dpu_rm_topology_name {
+	DPU_RM_TOPOLOGY_NONE = 0,
+	DPU_RM_TOPOLOGY_SINGLEPIPE,
+	DPU_RM_TOPOLOGY_DUALPIPE,
+	DPU_RM_TOPOLOGY_DUALPIPE_3DMERGE,
+	DPU_RM_TOPOLOGY_MAX,
+};
+
+/**
+ * enum dpu_rm_topology_control - HW resource use case in use by connector
+ * @DPU_RM_TOPCTL_RESERVE_LOCK: If set, in AtomicTest phase, after a successful
+ *                              test, reserve the resources for this display.
+ *                              Normal behavior would not impact the reservation
+ *                              list during the AtomicTest phase.
+ * @DPU_RM_TOPCTL_RESERVE_CLEAR: If set, in AtomicTest phase, before testing,
+ *                               release any reservation held by this display.
+ *                               Normal behavior would not impact the
+ *                               reservation list during the AtomicTest phase.
+ * @DPU_RM_TOPCTL_DS  : Require layer mixers with DS capabilities
+ */
+enum dpu_rm_topology_control {
+	DPU_RM_TOPCTL_RESERVE_LOCK,
+	DPU_RM_TOPCTL_RESERVE_CLEAR,
+	DPU_RM_TOPCTL_DS,
+};
+
+/**
+ * struct dpu_rm - DPU dynamic hardware resource manager
+ * @dev: device handle for event logging purposes
+ * @rsvps: list of hardware reservations by each crtc->encoder->connector
+ * @hw_blks: array of lists of hardware resources present in the system, one
+ *	list per type of hardware block
+ * @hw_mdp: hardware object for mdp_top
+ * @lm_max_width: cached layer mixer maximum width
+ * @rsvp_next_seq: sequence number for next reservation for debugging purposes
+ * @rm_lock: resource manager mutex
+ */
+struct dpu_rm {
+	struct drm_device *dev;
+	struct list_head rsvps;
+	struct list_head hw_blks[DPU_HW_BLK_MAX];
+	struct dpu_hw_mdp *hw_mdp;
+	uint32_t lm_max_width;
+	uint32_t rsvp_next_seq;
+	struct mutex rm_lock;
+};
+
+/**
+ *  struct dpu_rm_hw_blk - resource manager internal structure
+ *	forward declaration for single iterator definition without void pointer
+ */
+struct dpu_rm_hw_blk;
+
+/**
+ * struct dpu_rm_hw_iter - iterator for use with dpu_rm
+ * @hw: dpu_hw object requested, or NULL on failure
+ * @blk: dpu_rm internal block representation. Clients ignore. Used as iterator.
+ * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
+ * @type: Hardware Block Type client wishes to search for.
+ */
+struct dpu_rm_hw_iter {
+	void *hw;
+	struct dpu_rm_hw_blk *blk;
+	uint32_t enc_id;
+	enum dpu_hw_blk_type type;
+};
+
+/**
+ * dpu_rm_init - Read hardware catalog and create reservation tracking objects
+ *	for all HW blocks.
+ * @rm: DPU Resource Manager handle
+ * @cat: Pointer to hardware catalog
+ * @mmio: mapped register io address of MDP
+ * @dev: device handle for event logging purposes
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_init(struct dpu_rm *rm,
+		struct dpu_mdss_cfg *cat,
+		void *mmio,
+		struct drm_device *dev);
+
+/**
+ * dpu_rm_destroy - Free all memory allocated by dpu_rm_init
+ * @rm: DPU Resource Manager handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_destroy(struct dpu_rm *rm);
+
+/**
+ * dpu_rm_reserve - Given a CRTC->Encoder->Connector display chain, analyze
+ *	the use connections and user requirements, specified through related
+ *	topology control properties, and reserve hardware blocks to that
+ *	display chain.
+ *	HW blocks can then be accessed through dpu_rm_get_* functions.
+ *	HW Reservations should be released via dpu_rm_release_hw.
+ * @rm: DPU Resource Manager handle
+ * @drm_enc: DRM Encoder handle
+ * @crtc_state: Proposed Atomic DRM CRTC State handle
+ * @conn_state: Proposed Atomic DRM Connector State handle
+ * @topology: Pointer to topology info for the display
+ * @test_only: Atomic-Test phase, discard results (unless property overrides)
+ * @Return: 0 on Success otherwise -ERROR
+ */
+int dpu_rm_reserve(struct dpu_rm *rm,
+		struct drm_encoder *drm_enc,
+		struct drm_crtc_state *crtc_state,
+		struct drm_connector_state *conn_state,
+		struct msm_display_topology topology,
+		bool test_only);
+
+/**
+ * dpu_rm_reserve - Given the encoder for the display chain, release any
+ *	HW blocks previously reserved for that use case.
+ * @rm: DPU Resource Manager handle
+ * @enc: DRM Encoder handle
+ * @Return: 0 on Success otherwise -ERROR
+ */
+void dpu_rm_release(struct dpu_rm *rm, struct drm_encoder *enc);
+
+/**
+ * dpu_rm_get_mdp - Retrieve HW block for MDP TOP.
+ *	This is never reserved, and is usable by any display.
+ * @rm: DPU Resource Manager handle
+ * @Return: Pointer to hw block or NULL
+ */
+struct dpu_hw_mdp *dpu_rm_get_mdp(struct dpu_rm *rm);
+
+/**
+ * dpu_rm_init_hw_iter - setup given iterator for new iteration over hw list
+ *	using dpu_rm_get_hw
+ * @iter: iter object to initialize
+ * @enc_id: DRM ID of Encoder client wishes to search for, or 0 for Any Encoder
+ * @type: Hardware Block Type client wishes to search for.
+ */
+void dpu_rm_init_hw_iter(
+		struct dpu_rm_hw_iter *iter,
+		uint32_t enc_id,
+		enum dpu_hw_blk_type type);
+/**
+ * dpu_rm_get_hw - retrieve reserved hw object given encoder and hw type
+ *	Meant to do a single pass through the hardware list to iteratively
+ *	retrieve hardware blocks of a given type for a given encoder.
+ *	Initialize an iterator object.
+ *	Set hw block type of interest. Set encoder id of interest, 0 for any.
+ *	Function returns first hw of type for that encoder.
+ *	Subsequent calls will return the next reserved hw of that type in-order.
+ *	Iterator HW pointer will be null on failure to find hw.
+ * @rm: DPU Resource Manager handle
+ * @iter: iterator object
+ * @Return: true on match found, false on no match found
+ */
+bool dpu_rm_get_hw(struct dpu_rm *rm, struct dpu_rm_hw_iter *iter);
+
+/**
+ * dpu_rm_check_property_topctl - validate property bitmask before it is set
+ * @val: user's proposed topology control bitmask
+ * @Return: 0 on success or error
+ */
+int dpu_rm_check_property_topctl(uint64_t val);
+
+/**
+ * dpu_rm_get_topology_name - returns the name of the the given topology
+ *                            definition
+ * @topology: topology definition
+ * @Return: name of the topology
+ */
+enum dpu_rm_topology_name
+dpu_rm_get_topology_name(struct msm_display_topology topology);
+
+#endif /* __DPU_RM_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
new file mode 100644
index 000000000000..ae0ca5076238
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_trace.h
@@ -0,0 +1,1007 @@
+/* Copyright (c) 2014-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#if !defined(_DPU_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
+#define _DPU_TRACE_H_
+
+#include <linux/stringify.h>
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#include <drm/drm_rect.h>
+#include "dpu_crtc.h"
+#include "dpu_encoder_phys.h"
+#include "dpu_hw_mdss.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_plane.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM dpu
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE dpu_trace
+
+TRACE_EVENT(dpu_perf_set_qos_luts,
+	TP_PROTO(u32 pnum, u32 fmt, bool rt, u32 fl,
+		u32 lut, u32 lut_usage),
+	TP_ARGS(pnum, fmt, rt, fl, lut, lut_usage),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(bool, rt)
+			__field(u32, fl)
+			__field(u64, lut)
+			__field(u32, lut_usage)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->rt = rt;
+			__entry->fl = fl;
+			__entry->lut = lut;
+			__entry->lut_usage = lut_usage;
+	),
+	TP_printk("pnum=%d fmt=%x rt=%d fl=%d lut=0x%llx lut_usage=%d",
+			__entry->pnum, __entry->fmt,
+			__entry->rt, __entry->fl,
+			__entry->lut, __entry->lut_usage)
+);
+
+TRACE_EVENT(dpu_perf_set_danger_luts,
+	TP_PROTO(u32 pnum, u32 fmt, u32 mode, u32 danger_lut,
+		u32 safe_lut),
+	TP_ARGS(pnum, fmt, mode, danger_lut, safe_lut),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, fmt)
+			__field(u32, mode)
+			__field(u32, danger_lut)
+			__field(u32, safe_lut)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->fmt = fmt;
+			__entry->mode = mode;
+			__entry->danger_lut = danger_lut;
+			__entry->safe_lut = safe_lut;
+	),
+	TP_printk("pnum=%d fmt=%x mode=%d luts[0x%x, 0x%x]",
+			__entry->pnum, __entry->fmt,
+			__entry->mode, __entry->danger_lut,
+			__entry->safe_lut)
+);
+
+TRACE_EVENT(dpu_perf_set_ot,
+	TP_PROTO(u32 pnum, u32 xin_id, u32 rd_lim, u32 vbif_idx),
+	TP_ARGS(pnum, xin_id, rd_lim, vbif_idx),
+	TP_STRUCT__entry(
+			__field(u32, pnum)
+			__field(u32, xin_id)
+			__field(u32, rd_lim)
+			__field(u32, vbif_idx)
+	),
+	TP_fast_assign(
+			__entry->pnum = pnum;
+			__entry->xin_id = xin_id;
+			__entry->rd_lim = rd_lim;
+			__entry->vbif_idx = vbif_idx;
+	),
+	TP_printk("pnum:%d xin_id:%d ot:%d vbif:%d",
+			__entry->pnum, __entry->xin_id, __entry->rd_lim,
+			__entry->vbif_idx)
+)
+
+TRACE_EVENT(dpu_perf_update_bus,
+	TP_PROTO(int client, unsigned long long ab_quota,
+	unsigned long long ib_quota),
+	TP_ARGS(client, ab_quota, ib_quota),
+	TP_STRUCT__entry(
+			__field(int, client)
+			__field(u64, ab_quota)
+			__field(u64, ib_quota)
+	),
+	TP_fast_assign(
+			__entry->client = client;
+			__entry->ab_quota = ab_quota;
+			__entry->ib_quota = ib_quota;
+	),
+	TP_printk("Request client:%d ab=%llu ib=%llu",
+			__entry->client,
+			__entry->ab_quota,
+			__entry->ib_quota)
+)
+
+
+TRACE_EVENT(dpu_cmd_release_bw,
+	TP_PROTO(u32 crtc_id),
+	TP_ARGS(crtc_id),
+	TP_STRUCT__entry(
+			__field(u32, crtc_id)
+	),
+	TP_fast_assign(
+			__entry->crtc_id = crtc_id;
+	),
+	TP_printk("crtc:%d", __entry->crtc_id)
+);
+
+TRACE_EVENT(tracing_mark_write,
+	TP_PROTO(int pid, const char *name, bool trace_begin),
+	TP_ARGS(pid, name, trace_begin),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(trace_name, name)
+			__field(bool, trace_begin)
+	),
+	TP_fast_assign(
+			__entry->pid = pid;
+			__assign_str(trace_name, name);
+			__entry->trace_begin = trace_begin;
+	),
+	TP_printk("%s|%d|%s", __entry->trace_begin ? "B" : "E",
+		__entry->pid, __get_str(trace_name))
+)
+
+TRACE_EVENT(dpu_trace_counter,
+	TP_PROTO(int pid, char *name, int value),
+	TP_ARGS(pid, name, value),
+	TP_STRUCT__entry(
+			__field(int, pid)
+			__string(counter_name, name)
+			__field(int, value)
+	),
+	TP_fast_assign(
+			__entry->pid = current->tgid;
+			__assign_str(counter_name, name);
+			__entry->value = value;
+	),
+	TP_printk("%d|%s|%d", __entry->pid,
+			__get_str(counter_name), __entry->value)
+)
+
+TRACE_EVENT(dpu_perf_crtc_update,
+	TP_PROTO(u32 crtc, u64 bw_ctl_mnoc, u64 bw_ctl_llcc,
+			u64 bw_ctl_ebi, u32 core_clk_rate,
+			bool stop_req, u32 update_bus, u32 update_clk),
+	TP_ARGS(crtc, bw_ctl_mnoc, bw_ctl_llcc, bw_ctl_ebi, core_clk_rate,
+		stop_req, update_bus, update_clk),
+	TP_STRUCT__entry(
+			__field(u32, crtc)
+			__field(u64, bw_ctl_mnoc)
+			__field(u64, bw_ctl_llcc)
+			__field(u64, bw_ctl_ebi)
+			__field(u32, core_clk_rate)
+			__field(bool, stop_req)
+			__field(u32, update_bus)
+			__field(u32, update_clk)
+	),
+	TP_fast_assign(
+			__entry->crtc = crtc;
+			__entry->bw_ctl_mnoc = bw_ctl_mnoc;
+			__entry->bw_ctl_llcc = bw_ctl_llcc;
+			__entry->bw_ctl_ebi = bw_ctl_ebi;
+			__entry->core_clk_rate = core_clk_rate;
+			__entry->stop_req = stop_req;
+			__entry->update_bus = update_bus;
+			__entry->update_clk = update_clk;
+	),
+	 TP_printk(
+		"crtc=%d bw_mnoc=%llu bw_llcc=%llu bw_ebi=%llu clk_rate=%u stop_req=%d u_bus=%d u_clk=%d",
+			__entry->crtc,
+			__entry->bw_ctl_mnoc,
+			__entry->bw_ctl_llcc,
+			__entry->bw_ctl_ebi,
+			__entry->core_clk_rate,
+			__entry->stop_req,
+			__entry->update_bus,
+			__entry->update_clk)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_irq_template,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_intr_idx,	intr_idx	)
+		__field(	int,			hw_idx		)
+		__field(	int,			irq_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intr_idx = intr_idx;
+		__entry->hw_idx = hw_idx;
+		__entry->irq_idx = irq_idx;
+	),
+	TP_printk("id=%u, intr=%d, hw=%d, irq=%d",
+		  __entry->drm_id, __entry->intr_idx, __entry->hw_idx,
+		  __entry->irq_idx)
+);
+DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_register_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx)
+);
+DEFINE_EVENT(dpu_enc_irq_template, dpu_enc_irq_unregister_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx)
+);
+
+TRACE_EVENT(dpu_enc_irq_wait_success,
+	TP_PROTO(uint32_t drm_id, enum dpu_intr_idx intr_idx, int hw_idx,
+		 int irq_idx, enum dpu_pingpong pp_idx, int atomic_cnt),
+	TP_ARGS(drm_id, intr_idx, hw_idx, irq_idx, pp_idx, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_intr_idx,	intr_idx	)
+		__field(	int,			hw_idx		)
+		__field(	int,			irq_idx		)
+		__field(	enum dpu_pingpong,	pp_idx		)
+		__field(	int,			atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intr_idx = intr_idx;
+		__entry->hw_idx = hw_idx;
+		__entry->irq_idx = irq_idx;
+		__entry->pp_idx = pp_idx;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, intr=%d, hw=%d, irq=%d, pp=%d, atomic_cnt=%d",
+		  __entry->drm_id, __entry->intr_idx, __entry->hw_idx,
+		  __entry->irq_idx, __entry->pp_idx, __entry->atomic_cnt)
+);
+
+DECLARE_EVENT_CLASS(dpu_drm_obj_template,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+	),
+	TP_printk("id=%u", __entry->drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_atomic_check,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_mode_set,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_disable,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_enc_prepare_kickoff_reset,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_flip,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_vblank_cb,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_crtc_complete_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_enc_enable,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_commit,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+DEFINE_EVENT(dpu_drm_obj_template, dpu_kms_wait_for_commit_done,
+	TP_PROTO(uint32_t drm_id),
+	TP_ARGS(drm_id)
+);
+
+TRACE_EVENT(dpu_enc_enable,
+	TP_PROTO(uint32_t drm_id, int hdisplay, int vdisplay),
+	TP_ARGS(drm_id, hdisplay, vdisplay),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			hdisplay	)
+		__field(	int,			vdisplay	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->hdisplay = hdisplay;
+		__entry->vdisplay = vdisplay;
+	),
+	TP_printk("id=%u, mode=%dx%d",
+		  __entry->drm_id, __entry->hdisplay, __entry->vdisplay)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_keyval_template,
+	TP_PROTO(uint32_t drm_id, int val),
+	TP_ARGS(drm_id, val),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	int,		val	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->val = val;
+	),
+	TP_printk("id=%u, val=%d", __entry->drm_id, __entry->val)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_underrun_cb,
+	TP_PROTO(uint32_t drm_id, int count),
+	TP_ARGS(drm_id, count)
+);
+DEFINE_EVENT(dpu_enc_keyval_template, dpu_enc_trigger_start,
+	TP_PROTO(uint32_t drm_id, int ctl_idx),
+	TP_ARGS(drm_id, ctl_idx)
+);
+
+TRACE_EVENT(dpu_enc_atomic_check_flags,
+	TP_PROTO(uint32_t drm_id, unsigned int flags, int private_flags),
+	TP_ARGS(drm_id, flags, private_flags),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		flags		)
+		__field(	int,			private_flags	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->flags = flags;
+		__entry->private_flags = private_flags;
+	),
+	TP_printk("id=%u, flags=%u, private_flags=%d",
+		  __entry->drm_id, __entry->flags, __entry->private_flags)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_id_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			enable		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+	),
+	TP_printk("id=%u, enable=%s",
+		  __entry->drm_id, __entry->enable ? "true" : "false")
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_rc_helper,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_vblank_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+DEFINE_EVENT(dpu_enc_id_enable_template, dpu_enc_phys_cmd_connect_te,
+	TP_PROTO(uint32_t drm_id, bool enable),
+	TP_ARGS(drm_id, enable)
+);
+
+TRACE_EVENT(dpu_enc_rc,
+	TP_PROTO(uint32_t drm_id, u32 sw_event, bool idle_pc_supported,
+		 int rc_state, const char *stage),
+	TP_ARGS(drm_id, sw_event, idle_pc_supported, rc_state, stage),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	u32,		sw_event		)
+		__field(	bool,		idle_pc_supported	)
+		__field(	int,		rc_state		)
+		__string(	stage_str,	stage			)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->sw_event = sw_event;
+		__entry->idle_pc_supported = idle_pc_supported;
+		__entry->rc_state = rc_state;
+		__assign_str(stage_str, stage);
+	),
+	TP_printk("%s: id:%u, sw_event:%d, idle_pc_supported:%s, rc_state:%d\n",
+		  __get_str(stage_str), __entry->drm_id, __entry->sw_event,
+		  __entry->idle_pc_supported ? "true" : "false",
+		  __entry->rc_state)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb_not_busy,
+	TP_PROTO(uint32_t drm_id, u32 event, enum dpu_intf intf_idx),
+	TP_ARGS(drm_id, event, intf_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	u32,		event		)
+		__field(	enum dpu_intf,	intf_idx	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+		__entry->intf_idx = intf_idx;
+	),
+	TP_printk("id=%u, event=%u, intf=%d", __entry->drm_id, __entry->event,
+		  __entry->intf_idx)
+);
+
+TRACE_EVENT(dpu_enc_frame_done_cb,
+	TP_PROTO(uint32_t drm_id, unsigned int idx,
+		 unsigned long frame_busy_mask),
+	TP_ARGS(drm_id, idx, frame_busy_mask),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	unsigned int,		idx		)
+		__field(	unsigned long,		frame_busy_mask	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->idx = idx;
+		__entry->frame_busy_mask = frame_busy_mask;
+	),
+	TP_printk("id=%u, idx=%u, frame_busy_mask=%lx", __entry->drm_id,
+		  __entry->idx, __entry->frame_busy_mask)
+);
+
+TRACE_EVENT(dpu_enc_trigger_flush,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx,
+		 int pending_kickoff_cnt, int ctl_idx, u32 pending_flush_ret),
+	TP_ARGS(drm_id, intf_idx, pending_kickoff_cnt, ctl_idx,
+		pending_flush_ret),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	enum dpu_intf,	intf_idx		)
+		__field(	int,		pending_kickoff_cnt	)
+		__field(	int,		ctl_idx			)
+		__field(	u32,		pending_flush_ret	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+		__entry->pending_kickoff_cnt = pending_kickoff_cnt;
+		__entry->ctl_idx = ctl_idx;
+		__entry->pending_flush_ret = pending_flush_ret;
+	),
+	TP_printk("id=%u, intf_idx=%d, pending_kickoff_cnt=%d ctl_idx=%d "
+		  "pending_flush_ret=%u", __entry->drm_id,
+		  __entry->intf_idx, __entry->pending_kickoff_cnt,
+		  __entry->ctl_idx, __entry->pending_flush_ret)
+);
+
+DECLARE_EVENT_CLASS(dpu_enc_ktime_template,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	ktime_t,	time	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->time = time;
+	),
+	TP_printk("id=%u, time=%lld", __entry->drm_id,
+		  ktime_to_ms(__entry->time))
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_vsync_event_work,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+DEFINE_EVENT(dpu_enc_ktime_template, dpu_enc_early_kickoff,
+	TP_PROTO(uint32_t drm_id, ktime_t time),
+	TP_ARGS(drm_id, time)
+);
+
+DECLARE_EVENT_CLASS(dpu_id_event_template,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id	)
+		__field(	u32,		event	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, event=%u", __entry->drm_id, __entry->event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_enc_frame_done_timeout,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_cb,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_handle_power_event,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_done,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+DEFINE_EVENT(dpu_id_event_template, dpu_crtc_frame_event_more_pending,
+	TP_PROTO(uint32_t drm_id, u32 event),
+	TP_ARGS(drm_id, event)
+);
+
+TRACE_EVENT(dpu_enc_wait_event_timeout,
+	TP_PROTO(uint32_t drm_id, int32_t hw_id, int rc, s64 time,
+		 s64 expected_time, int atomic_cnt),
+	TP_ARGS(drm_id, hw_id, rc, time, expected_time, atomic_cnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	int32_t,	hw_id		)
+		__field(	int,		rc		)
+		__field(	s64,		time		)
+		__field(	s64,		expected_time	)
+		__field(	int,		atomic_cnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->hw_id = hw_id;
+		__entry->rc = rc;
+		__entry->time = time;
+		__entry->expected_time = expected_time;
+		__entry->atomic_cnt = atomic_cnt;
+	),
+	TP_printk("id=%u, hw_id=%d, rc=%d, time=%lld, expected=%lld cnt=%d",
+		  __entry->drm_id, __entry->hw_id, __entry->rc, __entry->time,
+		  __entry->expected_time, __entry->atomic_cnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, pp, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	bool,			enable	)
+		__field(	int,			refcnt	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, pp=%d, enable=%s, refcnt=%d", __entry->drm_id,
+		  __entry->pp, __entry->enable ? "true" : "false",
+		  __entry->refcnt)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pp_tx_done,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int new_count,
+		 u32 event),
+	TP_ARGS(drm_id, pp, new_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			new_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->new_count = new_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, new_count=%d, event=%u", __entry->drm_id,
+		  __entry->pp, __entry->new_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_cmd_pdone_timeout,
+	TP_PROTO(uint32_t drm_id, enum dpu_pingpong pp, int timeout_count,
+		 int kickoff_count, u32 event),
+	TP_ARGS(drm_id, pp, timeout_count, kickoff_count, event),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	enum dpu_pingpong,	pp		)
+		__field(	int,			timeout_count	)
+		__field(	int,			kickoff_count	)
+		__field(	u32,			event		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->pp = pp;
+		__entry->timeout_count = timeout_count;
+		__entry->kickoff_count = kickoff_count;
+		__entry->event = event;
+	),
+	TP_printk("id=%u, pp=%d, timeout_count=%d, kickoff_count=%d, event=%u",
+		  __entry->drm_id, __entry->pp, __entry->timeout_count,
+		  __entry->kickoff_count, __entry->event)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_post_kickoff,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx),
+	TP_ARGS(drm_id, intf_idx),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id			)
+		__field(	enum dpu_intf,	intf_idx		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+	),
+	TP_printk("id=%u, intf_idx=%d", __entry->drm_id, __entry->intf_idx)
+);
+
+TRACE_EVENT(dpu_enc_phys_vid_irq_ctrl,
+	TP_PROTO(uint32_t drm_id, enum dpu_intf intf_idx, bool enable,
+		 int refcnt),
+	TP_ARGS(drm_id, intf_idx, enable, refcnt),
+	TP_STRUCT__entry(
+		__field(	uint32_t,	drm_id		)
+		__field(	enum dpu_intf,	intf_idx	)
+		__field(	bool,		enable		)
+		__field(	int,		refcnt		)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->intf_idx = intf_idx;
+		__entry->enable = enable;
+		__entry->refcnt = refcnt;
+	),
+	TP_printk("id=%u, intf_idx=%d enable=%s refcnt=%d", __entry->drm_id,
+		  __entry->intf_idx, __entry->enable ? "true" : "false",
+		  __entry->drm_id)
+);
+
+TRACE_EVENT(dpu_crtc_setup_mixer,
+	TP_PROTO(uint32_t crtc_id, uint32_t plane_id,
+		 struct drm_plane_state *state, struct dpu_plane_state *pstate,
+		 uint32_t stage_idx, enum dpu_sspp sspp, uint32_t pixel_format,
+		 uint64_t modifier),
+	TP_ARGS(crtc_id, plane_id, state, pstate, stage_idx, sspp,
+		pixel_format, modifier),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		crtc_id		)
+		__field(	uint32_t,		plane_id	)
+		__field(	struct drm_plane_state*,state		)
+		__field(	struct dpu_plane_state*,pstate		)
+		__field(	uint32_t,		stage_idx	)
+		__field(	enum dpu_sspp,		sspp		)
+		__field(	uint32_t,		pixel_format	)
+		__field(	uint64_t,		modifier	)
+	),
+	TP_fast_assign(
+		__entry->crtc_id = crtc_id;
+		__entry->plane_id = plane_id;
+		__entry->state = state;
+		__entry->pstate = pstate;
+		__entry->stage_idx = stage_idx;
+		__entry->sspp = sspp;
+		__entry->pixel_format = pixel_format;
+		__entry->modifier = modifier;
+	),
+	TP_printk("crtc_id:%u plane_id:%u fb_id:%u src:{%ux%u+%ux%u} "
+		  "dst:{%ux%u+%ux%u} stage_idx:%u stage:%d, sspp:%d "
+		  "multirect_index:%d multirect_mode:%u pix_format:%u "
+		  "modifier:%llu",
+		  __entry->crtc_id, __entry->plane_id,
+		  __entry->state->fb ? __entry->state->fb->base.id : -1,
+		  __entry->state->src_w >> 16,  __entry->state->src_h >> 16,
+		  __entry->state->src_x >> 16,  __entry->state->src_y >> 16,
+		  __entry->state->crtc_w,  __entry->state->crtc_h,
+		  __entry->state->crtc_x,  __entry->state->crtc_y,
+		  __entry->stage_idx, __entry->pstate->stage, __entry->sspp,
+		  __entry->pstate->multirect_index,
+		  __entry->pstate->multirect_mode, __entry->pixel_format,
+		  __entry->modifier)
+);
+
+TRACE_EVENT(dpu_crtc_setup_lm_bounds,
+	TP_PROTO(uint32_t drm_id, int mixer, struct drm_rect *bounds),
+	TP_ARGS(drm_id, mixer, bounds),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	int,			mixer	)
+		__field(	struct drm_rect *,	bounds	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->mixer = mixer;
+		__entry->bounds = bounds;
+	),
+	TP_printk("id:%u mixer:%d bounds:" DRM_RECT_FMT, __entry->drm_id,
+		  __entry->mixer, DRM_RECT_ARG(__entry->bounds))
+);
+
+TRACE_EVENT(dpu_crtc_vblank_enable,
+	TP_PROTO(uint32_t drm_id, uint32_t enc_id, bool enable,
+		 struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enc_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	uint32_t,		enc_id	)
+		__field(	bool,			enable	)
+		__field(	struct dpu_crtc *,	crtc	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enc_id = enc_id;
+		__entry->enable = enable;
+		__entry->crtc = crtc;
+	),
+	TP_printk("id:%u encoder:%u enable:%s state{enabled:%s suspend:%s "
+		  "vblank_req:%s}",
+		  __entry->drm_id, __entry->enc_id,
+		  __entry->enable ? "true" : "false",
+		  __entry->crtc->enabled ? "true" : "false",
+		  __entry->crtc->suspend ? "true" : "false",
+		  __entry->crtc->vblank_requested ? "true" : "false")
+);
+
+DECLARE_EVENT_CLASS(dpu_crtc_enable_template,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id	)
+		__field(	bool,			enable	)
+		__field(	struct dpu_crtc *,	crtc	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->enable = enable;
+		__entry->crtc = crtc;
+	),
+	TP_printk("id:%u enable:%s state{enabled:%s suspend:%s vblank_req:%s}",
+		  __entry->drm_id, __entry->enable ? "true" : "false",
+		  __entry->crtc->enabled ? "true" : "false",
+		  __entry->crtc->suspend ? "true" : "false",
+		  __entry->crtc->vblank_requested ? "true" : "false")
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_set_suspend,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_enable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_disable,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+DEFINE_EVENT(dpu_crtc_enable_template, dpu_crtc_vblank,
+	TP_PROTO(uint32_t drm_id, bool enable, struct dpu_crtc *crtc),
+	TP_ARGS(drm_id, enable, crtc)
+);
+
+TRACE_EVENT(dpu_crtc_disable_frame_pending,
+	TP_PROTO(uint32_t drm_id, int frame_pending),
+	TP_ARGS(drm_id, frame_pending),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	int,			frame_pending	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->frame_pending = frame_pending;
+	),
+	TP_printk("id:%u frame_pending:%d", __entry->drm_id,
+		  __entry->frame_pending)
+);
+
+TRACE_EVENT(dpu_plane_set_scanout,
+	TP_PROTO(enum dpu_sspp index, struct dpu_hw_fmt_layout *layout,
+		 enum dpu_sspp_multirect_index multirect_index),
+	TP_ARGS(index, layout, multirect_index),
+	TP_STRUCT__entry(
+		__field(	enum dpu_sspp,			index	)
+		__field(	struct dpu_hw_fmt_layout*,	layout	)
+		__field(	enum dpu_sspp_multirect_index,	multirect_index)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->layout = layout;
+		__entry->multirect_index = multirect_index;
+	),
+	TP_printk("index:%d layout:{%ux%u @ [%u/%u, %u/%u, %u/%u, %u/%u]} "
+		  "multirect_index:%d", __entry->index, __entry->layout->width,
+		  __entry->layout->height, __entry->layout->plane_addr[0],
+		  __entry->layout->plane_size[0],
+		  __entry->layout->plane_addr[1],
+		  __entry->layout->plane_size[1],
+		  __entry->layout->plane_addr[2],
+		  __entry->layout->plane_size[2],
+		  __entry->layout->plane_addr[3],
+		  __entry->layout->plane_size[3], __entry->multirect_index)
+);
+
+TRACE_EVENT(dpu_plane_disable,
+	TP_PROTO(uint32_t drm_id, bool is_virtual, uint32_t multirect_mode),
+	TP_ARGS(drm_id, is_virtual, multirect_mode),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		drm_id		)
+		__field(	bool,			is_virtual	)
+		__field(	uint32_t,		multirect_mode	)
+	),
+	TP_fast_assign(
+		__entry->drm_id = drm_id;
+		__entry->is_virtual = is_virtual;
+		__entry->multirect_mode = multirect_mode;
+	),
+	TP_printk("id:%u is_virtual:%s multirect_mode:%u", __entry->drm_id,
+		  __entry->is_virtual ? "true" : "false",
+		  __entry->multirect_mode)
+);
+
+DECLARE_EVENT_CLASS(dpu_rm_iter_template,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	enum dpu_hw_blk_type,	type	)
+		__field(	uint32_t,		enc_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->type = type;
+		__entry->enc_id = enc_id;
+	),
+	TP_printk("id:%d type:%d enc_id:%u", __entry->id, __entry->type,
+		  __entry->enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_cdm,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_intf,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+DEFINE_EVENT(dpu_rm_iter_template, dpu_rm_reserve_ctls,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id),
+	TP_ARGS(id, type, enc_id)
+);
+
+TRACE_EVENT(dpu_rm_reserve_lms,
+	TP_PROTO(uint32_t id, enum dpu_hw_blk_type type, uint32_t enc_id,
+		 uint32_t pp_id),
+	TP_ARGS(id, type, enc_id, pp_id),
+	TP_STRUCT__entry(
+		__field(	uint32_t,		id	)
+		__field(	enum dpu_hw_blk_type,	type	)
+		__field(	uint32_t,		enc_id	)
+		__field(	uint32_t,		pp_id	)
+	),
+	TP_fast_assign(
+		__entry->id = id;
+		__entry->type = type;
+		__entry->enc_id = enc_id;
+		__entry->pp_id = pp_id;
+	),
+	TP_printk("id:%d type:%d enc_id:%u pp_id:%u", __entry->id,
+		  __entry->type, __entry->enc_id, __entry->pp_id)
+);
+
+TRACE_EVENT(dpu_vbif_wait_xin_halt_fail,
+	TP_PROTO(enum dpu_vbif index, u32 xin_id),
+	TP_ARGS(index, xin_id),
+	TP_STRUCT__entry(
+		__field(	enum dpu_vbif,	index	)
+		__field(	u32,		xin_id	)
+	),
+	TP_fast_assign(
+		__entry->index = index;
+		__entry->xin_id = xin_id;
+	),
+	TP_printk("index:%d xin_id:%u", __entry->index, __entry->xin_id)
+);
+
+TRACE_EVENT(dpu_pp_connect_ext_te,
+	TP_PROTO(enum dpu_pingpong pp, u32 cfg),
+	TP_ARGS(pp, cfg),
+	TP_STRUCT__entry(
+		__field(	enum dpu_pingpong,	pp	)
+		__field(	u32,			cfg	)
+	),
+	TP_fast_assign(
+		__entry->pp = pp;
+		__entry->cfg = cfg;
+	),
+	TP_printk("pp:%d cfg:%u", __entry->pp, __entry->cfg)
+);
+
+DECLARE_EVENT_CLASS(dpu_core_irq_idx_cnt_template,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count),
+	TP_STRUCT__entry(
+		__field(	int,	irq_idx		)
+		__field(	int,	enable_count	)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+		__entry->enable_count = enable_count;
+	),
+	TP_printk("irq_idx:%d enable_count:%u", __entry->irq_idx,
+		  __entry->enable_count)
+);
+DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_enable_idx,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count)
+);
+DEFINE_EVENT(dpu_core_irq_idx_cnt_template, dpu_core_irq_disable_idx,
+	TP_PROTO(int irq_idx, int enable_count),
+	TP_ARGS(irq_idx, enable_count)
+);
+
+DECLARE_EVENT_CLASS(dpu_core_irq_callback_template,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback),
+	TP_STRUCT__entry(
+		__field(	int,				irq_idx	)
+		__field(	struct dpu_irq_callback *,	callback)
+	),
+	TP_fast_assign(
+		__entry->irq_idx = irq_idx;
+		__entry->callback = callback;
+	),
+	TP_printk("irq_idx:%d callback:%pK", __entry->irq_idx,
+		  __entry->callback)
+);
+DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_register_callback,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback)
+);
+DEFINE_EVENT(dpu_core_irq_callback_template, dpu_core_irq_unregister_callback,
+	TP_PROTO(int irq_idx, struct dpu_irq_callback *callback),
+	TP_ARGS(irq_idx, callback)
+);
+
+TRACE_EVENT(dpu_core_perf_update_clk,
+	TP_PROTO(struct drm_device *dev, bool stop_req, u64 clk_rate),
+	TP_ARGS(dev, stop_req, clk_rate),
+	TP_STRUCT__entry(
+		__field(	struct drm_device *,	dev		)
+		__field(	bool,			stop_req	)
+		__field(	u64,			clk_rate	)
+	),
+	TP_fast_assign(
+		__entry->dev = dev;
+		__entry->stop_req = stop_req;
+		__entry->clk_rate = clk_rate;
+	),
+	TP_printk("dev:%s stop_req:%s clk_rate:%llu", __entry->dev->unique,
+		  __entry->stop_req ? "true" : "false", __entry->clk_rate)
+);
+
+#define DPU_ATRACE_END(name) trace_tracing_mark_write(current->tgid, name, 0)
+#define DPU_ATRACE_BEGIN(name) trace_tracing_mark_write(current->tgid, name, 1)
+#define DPU_ATRACE_FUNC() DPU_ATRACE_BEGIN(__func__)
+
+#define DPU_ATRACE_INT(name, value) \
+	trace_dpu_trace_counter(current->tgid, name, value)
+
+#endif /* _DPU_TRACE_H_ */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#include <trace/define_trace.h>
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
new file mode 100644
index 000000000000..295528292296
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c
@@ -0,0 +1,384 @@
+/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	"[drm:%s:%d] " fmt, __func__, __LINE__
+
+#include <linux/debugfs.h>
+
+#include "dpu_vbif.h"
+#include "dpu_hw_vbif.h"
+#include "dpu_trace.h"
+
+/**
+ * _dpu_vbif_wait_for_xin_halt - wait for the xin to halt
+ * @vbif:	Pointer to hardware vbif driver
+ * @xin_id:	Client interface identifier
+ * @return:	0 if success; error code otherwise
+ */
+static int _dpu_vbif_wait_for_xin_halt(struct dpu_hw_vbif *vbif, u32 xin_id)
+{
+	ktime_t timeout;
+	bool status;
+	int rc;
+
+	if (!vbif || !vbif->cap || !vbif->ops.get_halt_ctrl) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		return -EINVAL;
+	}
+
+	timeout = ktime_add_us(ktime_get(), vbif->cap->xin_halt_timeout);
+	for (;;) {
+		status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+		if (status)
+			break;
+		if (ktime_compare_safe(ktime_get(), timeout) > 0) {
+			status = vbif->ops.get_halt_ctrl(vbif, xin_id);
+			break;
+		}
+		usleep_range(501, 1000);
+	}
+
+	if (!status) {
+		rc = -ETIMEDOUT;
+		DPU_ERROR("VBIF %d client %d not halting. TIMEDOUT.\n",
+				vbif->idx - VBIF_0, xin_id);
+	} else {
+		rc = 0;
+		DPU_DEBUG("VBIF %d client %d is halted\n",
+				vbif->idx - VBIF_0, xin_id);
+	}
+
+	return rc;
+}
+
+/**
+ * _dpu_vbif_apply_dynamic_ot_limit - determine OT based on usecase parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @ot_lim:	Pointer to OT limit to be modified
+ * @params:	Pointer to usecase parameters
+ */
+static void _dpu_vbif_apply_dynamic_ot_limit(struct dpu_hw_vbif *vbif,
+		u32 *ot_lim, struct dpu_vbif_set_ot_params *params)
+{
+	u64 pps;
+	const struct dpu_vbif_dynamic_ot_tbl *tbl;
+	u32 i;
+
+	if (!vbif || !(vbif->cap->features & BIT(DPU_VBIF_QOS_OTLIM)))
+		return;
+
+	/* Dynamic OT setting done only for WFD */
+	if (!params->is_wfd)
+		return;
+
+	pps = params->frame_rate;
+	pps *= params->width;
+	pps *= params->height;
+
+	tbl = params->rd ? &vbif->cap->dynamic_ot_rd_tbl :
+			&vbif->cap->dynamic_ot_wr_tbl;
+
+	for (i = 0; i < tbl->count; i++) {
+		if (pps <= tbl->cfg[i].pps) {
+			*ot_lim = tbl->cfg[i].ot_limit;
+			break;
+		}
+	}
+
+	DPU_DEBUG("vbif:%d xin:%d w:%d h:%d fps:%d pps:%llu ot:%u\n",
+			vbif->idx - VBIF_0, params->xin_id,
+			params->width, params->height, params->frame_rate,
+			pps, *ot_lim);
+}
+
+/**
+ * _dpu_vbif_get_ot_limit - get OT based on usecase & configuration parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @params:	Pointer to usecase parameters
+ * @return:	OT limit
+ */
+static u32 _dpu_vbif_get_ot_limit(struct dpu_hw_vbif *vbif,
+	struct dpu_vbif_set_ot_params *params)
+{
+	u32 ot_lim = 0;
+	u32 val;
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid arguments vbif %d\n", vbif != 0);
+		return -EINVAL;
+	}
+
+	if (vbif->cap->default_ot_wr_limit && !params->rd)
+		ot_lim = vbif->cap->default_ot_wr_limit;
+	else if (vbif->cap->default_ot_rd_limit && params->rd)
+		ot_lim = vbif->cap->default_ot_rd_limit;
+
+	/*
+	 * If default ot is not set from dt/catalog,
+	 * then do not configure it.
+	 */
+	if (ot_lim == 0)
+		goto exit;
+
+	/* Modify the limits if the target and the use case requires it */
+	_dpu_vbif_apply_dynamic_ot_limit(vbif, &ot_lim, params);
+
+	if (vbif && vbif->ops.get_limit_conf) {
+		val = vbif->ops.get_limit_conf(vbif,
+				params->xin_id, params->rd);
+		if (val == ot_lim)
+			ot_lim = 0;
+	}
+
+exit:
+	DPU_DEBUG("vbif:%d xin:%d ot_lim:%d\n",
+			vbif->idx - VBIF_0, params->xin_id, ot_lim);
+	return ot_lim;
+}
+
+/**
+ * dpu_vbif_set_ot_limit - set OT based on usecase & configuration parameters
+ * @vbif:	Pointer to hardware vbif driver
+ * @params:	Pointer to usecase parameters
+ *
+ * Note this function would block waiting for bus halt.
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params)
+{
+	struct dpu_hw_vbif *vbif = NULL;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	u32 ot_lim;
+	int ret, i;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+	mdp = dpu_kms->hw_mdp;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		if (dpu_kms->hw_vbif[i] &&
+				dpu_kms->hw_vbif[i]->idx == params->vbif_idx)
+			vbif = dpu_kms->hw_vbif[i];
+	}
+
+	if (!vbif || !mdp) {
+		DPU_DEBUG("invalid arguments vbif %d mdp %d\n",
+				vbif != 0, mdp != 0);
+		return;
+	}
+
+	if (!mdp->ops.setup_clk_force_ctrl ||
+			!vbif->ops.set_limit_conf ||
+			!vbif->ops.set_halt_ctrl)
+		return;
+
+	/* set write_gather_en for all write clients */
+	if (vbif->ops.set_write_gather_en && !params->rd)
+		vbif->ops.set_write_gather_en(vbif, params->xin_id);
+
+	ot_lim = _dpu_vbif_get_ot_limit(vbif, params) & 0xFF;
+
+	if (ot_lim == 0)
+		goto exit;
+
+	trace_dpu_perf_set_ot(params->num, params->xin_id, ot_lim,
+		params->vbif_idx);
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	vbif->ops.set_limit_conf(vbif, params->xin_id, params->rd, ot_lim);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, true);
+
+	ret = _dpu_vbif_wait_for_xin_halt(vbif, params->xin_id);
+	if (ret)
+		trace_dpu_vbif_wait_xin_halt_fail(vbif->idx, params->xin_id);
+
+	vbif->ops.set_halt_ctrl(vbif, params->xin_id, false);
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+exit:
+	return;
+}
+
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params)
+{
+	struct dpu_hw_vbif *vbif = NULL;
+	struct dpu_hw_mdp *mdp;
+	bool forced_on = false;
+	const struct dpu_vbif_qos_tbl *qos_tbl;
+	int i;
+
+	if (!dpu_kms || !params || !dpu_kms->hw_mdp) {
+		DPU_ERROR("invalid arguments\n");
+		return;
+	}
+	mdp = dpu_kms->hw_mdp;
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		if (dpu_kms->hw_vbif[i] &&
+				dpu_kms->hw_vbif[i]->idx == params->vbif_idx) {
+			vbif = dpu_kms->hw_vbif[i];
+			break;
+		}
+	}
+
+	if (!vbif || !vbif->cap) {
+		DPU_ERROR("invalid vbif %d\n", params->vbif_idx);
+		return;
+	}
+
+	if (!vbif->ops.set_qos_remap || !mdp->ops.setup_clk_force_ctrl) {
+		DPU_DEBUG("qos remap not supported\n");
+		return;
+	}
+
+	qos_tbl = params->is_rt ? &vbif->cap->qos_rt_tbl :
+			&vbif->cap->qos_nrt_tbl;
+
+	if (!qos_tbl->npriority_lvl || !qos_tbl->priority_lvl) {
+		DPU_DEBUG("qos tbl not defined\n");
+		return;
+	}
+
+	forced_on = mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, true);
+
+	for (i = 0; i < qos_tbl->npriority_lvl; i++) {
+		DPU_DEBUG("vbif:%d xin:%d lvl:%d/%d\n",
+				params->vbif_idx, params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+		vbif->ops.set_qos_remap(vbif, params->xin_id, i,
+				qos_tbl->priority_lvl[i]);
+	}
+
+	if (forced_on)
+		mdp->ops.setup_clk_force_ctrl(mdp, params->clk_ctrl, false);
+}
+
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	u32 i, pnd, src;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->ops.clear_errors) {
+			vbif->ops.clear_errors(vbif, &pnd, &src);
+			if (pnd || src) {
+				DRM_DEBUG_KMS("VBIF %d: pnd 0x%X, src 0x%X\n",
+					      vbif->idx - VBIF_0, pnd, src);
+			}
+		}
+	}
+}
+
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms)
+{
+	struct dpu_hw_vbif *vbif;
+	int i, j;
+
+	if (!dpu_kms) {
+		DPU_ERROR("invalid argument\n");
+		return;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(dpu_kms->hw_vbif); i++) {
+		vbif = dpu_kms->hw_vbif[i];
+		if (vbif && vbif->cap && vbif->ops.set_mem_type) {
+			for (j = 0; j < vbif->cap->memtype_count; j++)
+				vbif->ops.set_mem_type(
+						vbif, j, vbif->cap->memtype[j]);
+		}
+	}
+}
+
+#ifdef CONFIG_DEBUG_FS
+void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
+{
+	debugfs_remove_recursive(dpu_kms->debugfs_vbif);
+	dpu_kms->debugfs_vbif = NULL;
+}
+
+int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root)
+{
+	char vbif_name[32];
+	struct dentry *debugfs_vbif;
+	int i, j;
+
+	dpu_kms->debugfs_vbif = debugfs_create_dir("vbif", debugfs_root);
+	if (!dpu_kms->debugfs_vbif) {
+		DPU_ERROR("failed to create vbif debugfs\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < dpu_kms->catalog->vbif_count; i++) {
+		struct dpu_vbif_cfg *vbif = &dpu_kms->catalog->vbif[i];
+
+		snprintf(vbif_name, sizeof(vbif_name), "%d", vbif->id);
+
+		debugfs_vbif = debugfs_create_dir(vbif_name,
+				dpu_kms->debugfs_vbif);
+
+		debugfs_create_u32("features", 0600, debugfs_vbif,
+			(u32 *)&vbif->features);
+
+		debugfs_create_u32("xin_halt_timeout", 0400, debugfs_vbif,
+			(u32 *)&vbif->xin_halt_timeout);
+
+		debugfs_create_u32("default_rd_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_rd_limit);
+
+		debugfs_create_u32("default_wr_ot_limit", 0400, debugfs_vbif,
+			(u32 *)&vbif->default_ot_wr_limit);
+
+		for (j = 0; j < vbif->dynamic_ot_rd_tbl.count; j++) {
+			struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_rd_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_rd_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+
+		for (j = 0; j < vbif->dynamic_ot_wr_tbl.count; j++) {
+			struct dpu_vbif_dynamic_ot_cfg *cfg =
+					&vbif->dynamic_ot_wr_tbl.cfg[j];
+
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_pps", j);
+			debugfs_create_u64(vbif_name, 0400, debugfs_vbif,
+					(u64 *)&cfg->pps);
+			snprintf(vbif_name, sizeof(vbif_name),
+					"dynamic_ot_wr_%d_ot_limit", j);
+			debugfs_create_u32(vbif_name, 0400, debugfs_vbif,
+					(u32 *)&cfg->ot_limit);
+		}
+	}
+
+	return 0;
+}
+#endif
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
new file mode 100644
index 000000000000..f17af52dbbd5
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.h
@@ -0,0 +1,94 @@
+/* Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __DPU_VBIF_H__
+#define __DPU_VBIF_H__
+
+#include "dpu_kms.h"
+
+struct dpu_vbif_set_ot_params {
+	u32 xin_id;
+	u32 num;
+	u32 width;
+	u32 height;
+	u32 frame_rate;
+	bool rd;
+	bool is_wfd;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+};
+
+struct dpu_vbif_set_memtype_params {
+	u32 xin_id;
+	u32 vbif_idx;
+	u32 clk_ctrl;
+	bool is_cacheable;
+};
+
+/**
+ * struct dpu_vbif_set_qos_params - QoS remapper parameter
+ * @vbif_idx: vbif identifier
+ * @xin_id: client interface identifier
+ * @clk_ctrl: clock control identifier of the xin
+ * @num: pipe identifier (debug only)
+ * @is_rt: true if pipe is used in real-time use case
+ */
+struct dpu_vbif_set_qos_params {
+	u32 vbif_idx;
+	u32 xin_id;
+	u32 clk_ctrl;
+	u32 num;
+	bool is_rt;
+};
+
+/**
+ * dpu_vbif_set_ot_limit - set OT limit for vbif client
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to OT configuration parameters
+ */
+void dpu_vbif_set_ot_limit(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_ot_params *params);
+
+/**
+ * dpu_vbif_set_qos_remap - set QoS priority level remap
+ * @dpu_kms:	DPU handler
+ * @params:	Pointer to QoS configuration parameters
+ */
+void dpu_vbif_set_qos_remap(struct dpu_kms *dpu_kms,
+		struct dpu_vbif_set_qos_params *params);
+
+/**
+ * dpu_vbif_clear_errors - clear any vbif errors
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_clear_errors(struct dpu_kms *dpu_kms);
+
+/**
+ * dpu_vbif_init_memtypes - initialize xin memory types for vbif
+ * @dpu_kms:	DPU handler
+ */
+void dpu_vbif_init_memtypes(struct dpu_kms *dpu_kms);
+
+#ifdef CONFIG_DEBUG_FS
+int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms, struct dentry *debugfs_root);
+void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms);
+#else
+static inline int dpu_debugfs_vbif_init(struct dpu_kms *dpu_kms,
+		struct dentry *debugfs_root)
+{
+	return 0;
+}
+static inline void dpu_debugfs_vbif_destroy(struct dpu_kms *dpu_kms)
+{
+}
+#endif
+#endif /* __DPU_VBIF_H__ */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
new file mode 100644
index 000000000000..4f12e5c534c8
--- /dev/null
+++ b/drivers/gpu/drm/msm/disp/dpu1/msm_media_info.h
@@ -0,0 +1,1376 @@
+#ifndef __MEDIA_INFO_H__
+#define __MEDIA_INFO_H__
+
+#ifndef MSM_MEDIA_ALIGN
+#define MSM_MEDIA_ALIGN(__sz, __align) (((__align) & ((__align) - 1)) ?\
+	((((__sz) + (__align) - 1) / (__align)) * (__align)) :\
+	(((__sz) + (__align) - 1) & (~((__align) - 1))))
+#endif
+
+#ifndef MSM_MEDIA_ROUNDUP
+#define MSM_MEDIA_ROUNDUP(__sz, __r) (((__sz) + ((__r) - 1)) / (__r))
+#endif
+
+#ifndef MSM_MEDIA_MAX
+#define MSM_MEDIA_MAX(__a, __b) ((__a) > (__b)?(__a):(__b))
+#endif
+
+enum color_fmts {
+	/* Venus NV12:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV12,
+
+	/* Venus NV21:
+	 * YUV 4:2:0 image with a plane of 8 bit Y samples followed
+	 * by an interleaved V/U plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * V U V U V U V U V U V U . . . .  ^
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  |
+	 * V U V U V U V U V U V U . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Padding & Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_NV21,
+	/* Venus NV12_MVTB:
+	 * Two YUV 4:2:0 images/views one after the other
+	 * in a top-bottom layout, same as NV12
+	 * with a plane of 8 bit Y samples followed
+	 * by an interleaved U/V plane containing 8 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_1
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^               ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |               |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |               |
+	 * . . . . . . . . . . . . . . . .              |             View_2
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              |               |
+	 * . . . . . . . . . . . . . . . .              V               |
+	 * U V U V U V U V U V U V . . . .  ^                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  |                           |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines                |
+	 * . . . . . . . . . . . . . . . .  |                           |
+	 * . . . . . . . . . . . . . . . .  V                           V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width aligned to 128
+	 * UV_Stride : Width aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * View_1 begin at: 0 (zero)
+	 * View_2 begin at: Y_Stride * Y_Scanlines + UV_Stride * UV_Scanlines
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((2*(Y_Stride * Y_Scanlines)
+	 *          + 2*(UV_Stride * UV_Scanlines) + Extradata), 4096)
+	 */
+	COLOR_FMT_NV12_MVTB,
+	/*
+	 * The buffer can be of 2 types:
+	 * (1) Venus NV12 UBWC Progressive
+	 * (2) Venus NV12 UBWC Interlaced
+	 *
+	 * (1) Venus NV12 UBWC Progressive Buffer Format:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 8 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 8 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Y_Stride = align(Width, 128)
+	 * UV_Stride = align(Width, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 *
+	 *
+	 * (2) Venus NV12 UBWC Interlaced Buffer Format:
+	 * Compressed Macro-tile format for NV12 interlaced.
+	 * Contains 8 planes in the following order -
+	 * (A) Y_Meta_Top_Field_Plane
+	 * (B) Y_UBWC_Top_Field_Plane
+	 * (C) UV_Meta_Top_Field_Plane
+	 * (D) UV_UBWC_Top_Field_Plane
+	 * (E) Y_Meta_Bottom_Field_Plane
+	 * (F) Y_UBWC_Bottom_Field_Plane
+	 * (G) UV_Meta_Bottom_Field_Plane
+	 * (H) UV_UBWC_Bottom_Field_Plane
+	 * Y_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Top_Field_Plane.
+	 * Y_UBWC_Top_Field_Plane consists of Y data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Top_Field_Plane data together
+	 * with Y_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit Y samples for top field of an interlaced frame.
+	 *
+	 * UV_Meta_Top_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Top_Field_Plane.
+	 * UV_UBWC_Top_Field_Plane consists of UV data in compressed macro-tile
+	 * format for top field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Top_Field_Plane data together
+	 * with UV_UBWC_Top_Field_Plane data to produce loss-less uncompressed
+	 * 8 bit subsampled color difference samples for top field of an
+	 * interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Top_Field_Plane/UV_UBWC_Top_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * Y_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data for Y_UBWC_Bottom_Field_Plane.
+	 * Y_UBWC_Bottom_Field_Plane consists of Y data in compressed macro-tile
+	 * format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use the Y_Meta_Bottom_Field_Plane data
+	 * together with Y_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit Y samples for bottom field of an interlaced frame.
+	 *
+	 * UV_Meta_Bottom_Field_Plane consists of meta information to decode
+	 * compressed tile data in UV_UBWC_Bottom_Field_Plane.
+	 * UV_UBWC_Bottom_Field_Plane consists of UV data in compressed
+	 * macro-tile format for bottom field of an interlaced frame.
+	 * UBWC decoder block will use UV_Meta_Bottom_Field_Plane data together
+	 * with UV_UBWC_Bottom_Field_Plane data to produce loss-less
+	 * uncompressed 8 bit subsampled color difference samples for bottom
+	 * field of an interlaced frame.
+	 *
+	 * Each tile in Y_UBWC_Bottom_Field_Plane/UV_UBWC_Bottom_Field_Plane is
+	 * independently decodable and randomly accessible. There is no
+	 * dependency between tiles.
+	 *
+	 * <-----Y_TF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_TF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_TF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_TF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_TF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_TF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_TF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_TF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * <-----Y_BF_Meta_Stride---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . . Half_height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_BF_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-Compressed tile Y_BF Stride->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . . Half_height  |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_BF_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----UV_BF_Meta_Stride---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_BF_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <-Compressed tile UV_BF Stride->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_BF_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 * Half_height = (Height+1)>>1
+	 * Y_TF_Stride = align(Width, 128)
+	 * UV_TF_Stride = align(Width, 128)
+	 * Y_TF_Scanlines = align(Half_height, 32)
+	 * UV_TF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_TF_Plane_size = align(Y_TF_Stride * Y_TF_Scanlines, 4096)
+	 * UV_UBWC_TF_Plane_size = align(UV_TF_Stride * UV_TF_Scanlines, 4096)
+	 * Y_TF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_TF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_TF_Meta_Plane_size =
+	 *     align(Y_TF_Meta_Stride * Y_TF_Meta_Scanlines, 4096)
+	 * UV_TF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_TF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_TF_Meta_Plane_size =
+	 *     align(UV_TF_Meta_Stride * UV_TF_Meta_Scanlines, 4096)
+	 * Y_BF_Stride = align(Width, 128)
+	 * UV_BF_Stride = align(Width, 128)
+	 * Y_BF_Scanlines = align(Half_height, 32)
+	 * UV_BF_Scanlines = align((Half_height+1)/2, 32)
+	 * Y_UBWC_BF_Plane_size = align(Y_BF_Stride * Y_BF_Scanlines, 4096)
+	 * UV_UBWC_BF_Plane_size = align(UV_BF_Stride * UV_BF_Scanlines, 4096)
+	 * Y_BF_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_BF_Meta_Scanlines = align(roundup(Half_height, Y_TileHeight), 16)
+	 * Y_BF_Meta_Plane_size =
+	 *     align(Y_BF_Meta_Stride * Y_BF_Meta_Scanlines, 4096)
+	 * UV_BF_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_BF_Meta_Scanlines = align(roundup(Half_height, UV_TileHeight), 16)
+	 * UV_BF_Meta_Plane_size =
+	 *     align(UV_BF_Meta_Stride * UV_BF_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align( Y_UBWC_TF_Plane_size + UV_UBWC_TF_Plane_size +
+	 *           Y_TF_Meta_Plane_size + UV_TF_Meta_Plane_size +
+	 *			 Y_UBWC_BF_Plane_size + UV_UBWC_BF_Plane_size +
+	 *           Y_BF_Meta_Plane_size + UV_BF_Meta_Plane_size +
+	 *           + max(Extradata, Y_TF_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_UBWC,
+	/* Venus NV12 10-bit UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 4/3, 128)
+	 * UV_Stride = align(Width * 4/3, 128)
+	 * Y_Scanlines = align(Height, 32)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_NV12_BPP10_UBWC,
+	/* Venus RGBA8888 format:
+	 * Contains 1 plane in the following order -
+	 * (A) RGBA plane
+	 *
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Plane_size + Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888,
+	/* Venus RGBA8888 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 128)
+	 * RGB_Scanlines = align(Height, 32)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA8888_UBWC,
+	/* Venus RGBA1010102 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGBA plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 4, 256)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGBA1010102_UBWC,
+	/* Venus RGB565 UBWC format:
+	 * Contains 2 planes in the following order -
+	 * (A) Meta plane
+	 * (B) RGB plane
+	 *
+	 * <--- RGB_Meta_Stride ---->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |       Meta_RGB_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <-------- RGB_Stride -------->
+	 * <------- Width ------->
+	 * R R R R R R R R R R R R . . . .  ^           ^
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  Height      |
+	 * R R R R R R R R R R R R . . . .  |       RGB_Scanlines
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  |           |
+	 * R R R R R R R R R R R R . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .    -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 *
+	 * RGB_Stride = align(Width * 2, 128)
+	 * RGB_Scanlines = align(Height, 16)
+	 * RGB_Plane_size = align(RGB_Stride * RGB_Scanlines, 4096)
+	 * RGB_Meta_Stride = align(roundup(Width, RGB_TileWidth), 64)
+	 * RGB_Meta_Scanline = align(roundup(Height, RGB_TileHeight), 16)
+	 * RGB_Meta_Plane_size = align(RGB_Meta_Stride *
+	 *		RGB_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(RGB_Meta_Plane_size + RGB_Plane_size +
+	 *		Extradata, 4096)
+	 */
+	COLOR_FMT_RGB565_UBWC,
+	/* P010 UBWC:
+	 * Compressed Macro-tile format for NV12.
+	 * Contains 4 planes in the following order -
+	 * (A) Y_Meta_Plane
+	 * (B) Y_UBWC_Plane
+	 * (C) UV_Meta_Plane
+	 * (D) UV_UBWC_Plane
+	 *
+	 * Y_Meta_Plane consists of meta information to decode compressed
+	 * tile data in Y_UBWC_Plane.
+	 * Y_UBWC_Plane consists of Y data in compressed macro-tile format.
+	 * UBWC decoder block will use the Y_Meta_Plane data together with
+	 * Y_UBWC_Plane data to produce loss-less uncompressed 10 bit Y samples.
+	 *
+	 * UV_Meta_Plane consists of meta information to decode compressed
+	 * tile data in UV_UBWC_Plane.
+	 * UV_UBWC_Plane consists of UV data in compressed macro-tile format.
+	 * UBWC decoder block will use UV_Meta_Plane data together with
+	 * UV_UBWC_Plane data to produce loss-less uncompressed 10 bit 2x2
+	 * subsampled color difference samples.
+	 *
+	 * Each tile in Y_UBWC_Plane/UV_UBWC_Plane is independently decodable
+	 * and randomly accessible. There is no dependency between tiles.
+	 *
+	 * <----- Y_Meta_Stride ----->
+	 * <-------- Width ------>
+	 * M M M M M M M M M M M M . .      ^           ^
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      Height      |
+	 * M M M M M M M M M M M M . .      |         Meta_Y_Scanlines
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      |           |
+	 * M M M M M M M M M M M M . .      V           |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .                  |
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . .                  V
+	 * <--Compressed tile Y Stride--->
+	 * <------- Width ------->
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  ^           ^
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  Height      |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |        Macro_tile_Y_Scanlines
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  |           |
+	 * Y* Y* Y* Y* Y* Y* Y* Y* . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 * . . . . . . . . . . . . . . . .              V
+	 * <----- UV_Meta_Stride ---->
+	 * M M M M M M M M M M M M . .      ^
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      |
+	 * M M M M M M M M M M M M . .      M_UV_Scanlines
+	 * . . . . . . . . . . . . . .      |
+	 * . . . . . . . . . . . . . .      V
+	 * . . . . . . . . . . . . . .      -------> Buffer size aligned to 4k
+	 * <--Compressed tile UV Stride--->
+	 * U* V* U* V* U* V* U* V* . . . .  ^
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  |
+	 * U* V* U* V* U* V* U* V* . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  -------> Buffer size aligned to 4k
+	 *
+	 *
+	 * Y_Stride = align(Width * 2, 256)
+	 * UV_Stride = align(Width * 2, 256)
+	 * Y_Scanlines = align(Height, 16)
+	 * UV_Scanlines = align(Height/2, 16)
+	 * Y_UBWC_Plane_Size = align(Y_Stride * Y_Scanlines, 4096)
+	 * UV_UBWC_Plane_Size = align(UV_Stride * UV_Scanlines, 4096)
+	 * Y_Meta_Stride = align(roundup(Width, Y_TileWidth), 64)
+	 * Y_Meta_Scanlines = align(roundup(Height, Y_TileHeight), 16)
+	 * Y_Meta_Plane_size = align(Y_Meta_Stride * Y_Meta_Scanlines, 4096)
+	 * UV_Meta_Stride = align(roundup(Width, UV_TileWidth), 64)
+	 * UV_Meta_Scanlines = align(roundup(Height, UV_TileHeight), 16)
+	 * UV_Meta_Plane_size = align(UV_Meta_Stride * UV_Meta_Scanlines, 4096)
+	 * Extradata = 8k
+	 *
+	 * Total size = align(Y_UBWC_Plane_size + UV_UBWC_Plane_size +
+	 *           Y_Meta_Plane_size + UV_Meta_Plane_size
+	 *           + max(Extradata, Y_Stride * 48), 4096)
+	 */
+	COLOR_FMT_P010_UBWC,
+	/* Venus P010:
+	 * YUV 4:2:0 image with a plane of 10 bit Y samples followed
+	 * by an interleaved U/V plane containing 10 bit 2x2 subsampled
+	 * colour difference samples.
+	 *
+	 * <-------- Y/UV_Stride -------->
+	 * <------- Width ------->
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  ^           ^
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  Height      |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |          Y_Scanlines
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  |           |
+	 * Y Y Y Y Y Y Y Y Y Y Y Y . . . .  V           |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              |
+	 * . . . . . . . . . . . . . . . .              V
+	 * U V U V U V U V U V U V . . . .  ^
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  |
+	 * U V U V U V U V U V U V . . . .  UV_Scanlines
+	 * . . . . . . . . . . . . . . . .  |
+	 * . . . . . . . . . . . . . . . .  V
+	 * . . . . . . . . . . . . . . . .  --> Buffer size alignment
+	 *
+	 * Y_Stride : Width * 2 aligned to 128
+	 * UV_Stride : Width * 2 aligned to 128
+	 * Y_Scanlines: Height aligned to 32
+	 * UV_Scanlines: Height/2 aligned to 16
+	 * Extradata: Arbitrary (software-imposed) padding
+	 * Total size = align((Y_Stride * Y_Scanlines
+	 *          + UV_Stride * UV_Scanlines
+	 *          + max(Extradata, Y_Stride * 8), 4096)
+	 */
+	COLOR_FMT_P010,
+};
+
+#define COLOR_FMT_RGBA1010102_UBWC	COLOR_FMT_RGBA1010102_UBWC
+#define COLOR_FMT_RGB565_UBWC		COLOR_FMT_RGB565_UBWC
+#define COLOR_FMT_P010_UBWC		COLOR_FMT_P010_UBWC
+#define COLOR_FMT_P010		COLOR_FMT_P010
+
+static inline unsigned int VENUS_EXTRADATA_SIZE(int width, int height)
+{
+	(void)height;
+	(void)width;
+
+	/*
+	 * In the future, calculate the size based on the w/h but just
+	 * hardcode it for now since 16K satisfies all current usecases.
+	 */
+	return 16 * 1024;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_Y_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment, stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width, alignment);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		break;
+	case COLOR_FMT_P010:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width*2, alignment);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_UV_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment, stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width, alignment);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width, 192);
+		stride = MSM_MEDIA_ALIGN(stride * 4/3, alignment);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		alignment = 256;
+		stride = MSM_MEDIA_ALIGN(width * 2, alignment);
+		break;
+	case COLOR_FMT_P010:
+		alignment = 128;
+		stride = MSM_MEDIA_ALIGN(width*2, alignment);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_Y_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment, sclines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010:
+		alignment = 32;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		alignment = 16;
+		break;
+	default:
+		return 0;
+	}
+	sclines = MSM_MEDIA_ALIGN(height, alignment);
+invalid_input:
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_UV_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment, sclines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_NV12_MVTB:
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+	case COLOR_FMT_P010:
+		alignment = 16;
+		break;
+	case COLOR_FMT_NV12_UBWC:
+		alignment = 32;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	sclines = MSM_MEDIA_ALIGN((height+1)>>1, alignment);
+
+invalid_input:
+	return sclines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_Y_META_STRIDE(int color_fmt, int width)
+{
+	int y_tile_width = 0, y_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_width = 32;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		y_tile_width = 48;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	y_meta_stride = MSM_MEDIA_ROUNDUP(width, y_tile_width);
+	y_meta_stride = MSM_MEDIA_ALIGN(y_meta_stride, 64);
+
+invalid_input:
+	return y_meta_stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_Y_META_SCANLINES(int color_fmt, int height)
+{
+	int y_tile_height = 0, y_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		y_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		y_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	y_meta_scanlines = MSM_MEDIA_ROUNDUP(height, y_tile_height);
+	y_meta_scanlines = MSM_MEDIA_ALIGN(y_meta_scanlines, 16);
+
+invalid_input:
+	return y_meta_scanlines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ */
+static inline unsigned int VENUS_UV_META_STRIDE(int color_fmt, int width)
+{
+	int uv_tile_width = 0, uv_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_width = 16;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		uv_tile_width = 24;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	uv_meta_stride = MSM_MEDIA_ROUNDUP((width+1)>>1, uv_tile_width);
+	uv_meta_stride = MSM_MEDIA_ALIGN(uv_meta_stride, 64);
+
+invalid_input:
+	return uv_meta_stride;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @height
+ * Progressive: height
+ * Interlaced: (height+1)>>1
+ */
+static inline unsigned int VENUS_UV_META_SCANLINES(int color_fmt, int height)
+{
+	int uv_tile_height = 0, uv_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_UBWC:
+		uv_tile_height = 8;
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+	case COLOR_FMT_P010_UBWC:
+		uv_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	uv_meta_scanlines = MSM_MEDIA_ROUNDUP((height+1)>>1, uv_tile_height);
+	uv_meta_scanlines = MSM_MEDIA_ALIGN(uv_meta_scanlines, 16);
+
+invalid_input:
+	return uv_meta_scanlines;
+}
+
+static inline unsigned int VENUS_RGB_STRIDE(int color_fmt, int width)
+{
+	unsigned int alignment = 0, stride = 0, bpp = 4;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 128;
+		break;
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 256;
+		bpp = 2;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+		alignment = 256;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	stride = MSM_MEDIA_ALIGN(width * bpp, alignment);
+
+invalid_input:
+	return stride;
+}
+
+static inline unsigned int VENUS_RGB_SCANLINES(int color_fmt, int height)
+{
+	unsigned int alignment = 0, scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888:
+		alignment = 32;
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		alignment = 16;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	scanlines = MSM_MEDIA_ALIGN(height, alignment);
+
+invalid_input:
+	return scanlines;
+}
+
+static inline unsigned int VENUS_RGB_META_STRIDE(int color_fmt, int width)
+{
+	int rgb_tile_width = 0, rgb_meta_stride = 0;
+
+	if (!width)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_tile_width = 16;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	rgb_meta_stride = MSM_MEDIA_ROUNDUP(width, rgb_tile_width);
+	rgb_meta_stride = MSM_MEDIA_ALIGN(rgb_meta_stride, 64);
+
+invalid_input:
+	return rgb_meta_stride;
+}
+
+static inline unsigned int VENUS_RGB_META_SCANLINES(int color_fmt, int height)
+{
+	int rgb_tile_height = 0, rgb_meta_scanlines = 0;
+
+	if (!height)
+		goto invalid_input;
+
+	switch (color_fmt) {
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_tile_height = 4;
+		break;
+	default:
+		goto invalid_input;
+	}
+
+	rgb_meta_scanlines = MSM_MEDIA_ROUNDUP(height, rgb_tile_height);
+	rgb_meta_scanlines = MSM_MEDIA_ALIGN(rgb_meta_scanlines, 16);
+
+invalid_input:
+	return rgb_meta_scanlines;
+}
+
+/*
+ * Function arguments:
+ * @color_fmt
+ * @width
+ * Progressive: width
+ * Interlaced: width
+ * @height
+ * Progressive: height
+ * Interlaced: height
+ */
+static inline unsigned int VENUS_BUFFER_SIZE(
+	int color_fmt, int width, int height)
+{
+	const unsigned int extra_size = VENUS_EXTRADATA_SIZE(width, height);
+	unsigned int uv_alignment = 0, size = 0;
+	unsigned int y_plane, uv_plane, y_stride,
+		uv_stride, y_sclines, uv_sclines;
+	unsigned int y_ubwc_plane = 0, uv_ubwc_plane = 0;
+	unsigned int y_meta_stride = 0, y_meta_scanlines = 0;
+	unsigned int uv_meta_stride = 0, uv_meta_scanlines = 0;
+	unsigned int y_meta_plane = 0, uv_meta_plane = 0;
+	unsigned int rgb_stride = 0, rgb_scanlines = 0;
+	unsigned int rgb_plane = 0, rgb_ubwc_plane = 0, rgb_meta_plane = 0;
+	unsigned int rgb_meta_stride = 0, rgb_meta_scanlines = 0;
+
+	if (!width || !height)
+		goto invalid_input;
+
+	y_stride = VENUS_Y_STRIDE(color_fmt, width);
+	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
+	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
+	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
+	rgb_stride = VENUS_RGB_STRIDE(color_fmt, width);
+	rgb_scanlines = VENUS_RGB_SCANLINES(color_fmt, height);
+
+	switch (color_fmt) {
+	case COLOR_FMT_NV21:
+	case COLOR_FMT_NV12:
+	case COLOR_FMT_P010:
+		uv_alignment = 4096;
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines + uv_alignment;
+		size = y_plane + uv_plane +
+				MSM_MEDIA_MAX(extra_size, 8 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_MVTB:
+		uv_alignment = 4096;
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines + uv_alignment;
+		size = y_plane + uv_plane;
+		size = 2 * size + extra_size;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_UBWC:
+		y_sclines = VENUS_Y_SCANLINES(color_fmt, (height+1)>>1);
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_sclines = VENUS_UV_SCANLINES(color_fmt, (height+1)>>1);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines =
+			VENUS_Y_META_SCANLINES(color_fmt, (height+1)>>1);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+			y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines =
+			VENUS_UV_META_SCANLINES(color_fmt, (height+1)>>1);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+			uv_meta_scanlines, 4096);
+
+		size = (y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane)*2 +
+			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_NV12_BPP10_UBWC:
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+				y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+					uv_meta_scanlines, 4096);
+
+		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane +
+			MSM_MEDIA_MAX(extra_size + 8192, 48 * y_stride);
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_P010_UBWC:
+		y_ubwc_plane = MSM_MEDIA_ALIGN(y_stride * y_sclines, 4096);
+		uv_ubwc_plane = MSM_MEDIA_ALIGN(uv_stride * uv_sclines, 4096);
+		y_meta_stride = VENUS_Y_META_STRIDE(color_fmt, width);
+		y_meta_scanlines = VENUS_Y_META_SCANLINES(color_fmt, height);
+		y_meta_plane = MSM_MEDIA_ALIGN(
+				y_meta_stride * y_meta_scanlines, 4096);
+		uv_meta_stride = VENUS_UV_META_STRIDE(color_fmt, width);
+		uv_meta_scanlines = VENUS_UV_META_SCANLINES(color_fmt, height);
+		uv_meta_plane = MSM_MEDIA_ALIGN(uv_meta_stride *
+					uv_meta_scanlines, 4096);
+
+		size = y_ubwc_plane + uv_ubwc_plane + y_meta_plane +
+			uv_meta_plane;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_RGBA8888:
+		rgb_plane = MSM_MEDIA_ALIGN(rgb_stride  * rgb_scanlines, 4096);
+		size = rgb_plane;
+		size =  MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	case COLOR_FMT_RGBA8888_UBWC:
+	case COLOR_FMT_RGBA1010102_UBWC:
+	case COLOR_FMT_RGB565_UBWC:
+		rgb_ubwc_plane = MSM_MEDIA_ALIGN(rgb_stride * rgb_scanlines,
+							4096);
+		rgb_meta_stride = VENUS_RGB_META_STRIDE(color_fmt, width);
+		rgb_meta_scanlines = VENUS_RGB_META_SCANLINES(color_fmt,
+					height);
+		rgb_meta_plane = MSM_MEDIA_ALIGN(rgb_meta_stride *
+					rgb_meta_scanlines, 4096);
+		size = rgb_ubwc_plane + rgb_meta_plane;
+		size = MSM_MEDIA_ALIGN(size, 4096);
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return size;
+}
+
+static inline unsigned int VENUS_VIEW2_OFFSET(
+	int color_fmt, int width, int height)
+{
+	unsigned int offset = 0;
+	unsigned int y_plane, uv_plane, y_stride,
+		uv_stride, y_sclines, uv_sclines;
+	if (!width || !height)
+		goto invalid_input;
+
+	y_stride = VENUS_Y_STRIDE(color_fmt, width);
+	uv_stride = VENUS_UV_STRIDE(color_fmt, width);
+	y_sclines = VENUS_Y_SCANLINES(color_fmt, height);
+	uv_sclines = VENUS_UV_SCANLINES(color_fmt, height);
+	switch (color_fmt) {
+	case COLOR_FMT_NV12_MVTB:
+		y_plane = y_stride * y_sclines;
+		uv_plane = uv_stride * uv_sclines;
+		offset = y_plane + uv_plane;
+		break;
+	default:
+		break;
+	}
+invalid_input:
+	return offset;
+}
+
+#endif
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index e79ad74ca98c..46876bc8b707 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -15,6 +16,8 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/kthread.h>
+#include <uapi/linux/sched/types.h>
 #include <drm/drm_of.h>
 
 #include "msm_drv.h"
@@ -149,7 +152,7 @@ struct vblank_event {
 	bool enable;
 };
 
-static void vblank_ctrl_worker(struct work_struct *work)
+static void vblank_ctrl_worker(struct kthread_work *work)
 {
 	struct msm_vblank_ctrl *vbl_ctrl = container_of(work,
 						struct msm_vblank_ctrl, work);
@@ -197,7 +200,8 @@ static int vblank_ctrl_queue_work(struct msm_drm_private *priv,
 	list_add_tail(&vbl_ev->node, &vbl_ctrl->event_list);
 	spin_unlock_irqrestore(&vbl_ctrl->lock, flags);
 
-	queue_work(priv->wq, &vbl_ctrl->work);
+	kthread_queue_work(&priv->disp_thread[crtc_id].worker,
+			&vbl_ctrl->work);
 
 	return 0;
 }
@@ -211,17 +215,33 @@ static int msm_drm_uninit(struct device *dev)
 	struct msm_mdss *mdss = priv->mdss;
 	struct msm_vblank_ctrl *vbl_ctrl = &priv->vblank_ctrl;
 	struct vblank_event *vbl_ev, *tmp;
+	int i;
 
 	/* We must cancel and cleanup any pending vblank enable/disable
 	 * work before drm_irq_uninstall() to avoid work re-enabling an
 	 * irq after uninstall has disabled it.
 	 */
-	cancel_work_sync(&vbl_ctrl->work);
+	kthread_flush_work(&vbl_ctrl->work);
 	list_for_each_entry_safe(vbl_ev, tmp, &vbl_ctrl->event_list, node) {
 		list_del(&vbl_ev->node);
 		kfree(vbl_ev);
 	}
 
+	/* clean up display commit/event worker threads */
+	for (i = 0; i < priv->num_crtcs; i++) {
+		if (priv->disp_thread[i].thread) {
+			kthread_flush_worker(&priv->disp_thread[i].worker);
+			kthread_stop(priv->disp_thread[i].thread);
+			priv->disp_thread[i].thread = NULL;
+		}
+
+		if (priv->event_thread[i].thread) {
+			kthread_flush_worker(&priv->event_thread[i].worker);
+			kthread_stop(priv->event_thread[i].thread);
+			priv->event_thread[i].thread = NULL;
+		}
+	}
+
 	msm_gem_shrinker_cleanup(ddev);
 
 	drm_kms_helper_poll_fini(ddev);
@@ -269,6 +289,7 @@ static int msm_drm_uninit(struct device *dev)
 
 #define KMS_MDP4 4
 #define KMS_MDP5 5
+#define KMS_DPU  3
 
 static int get_mdp_ver(struct platform_device *pdev)
 {
@@ -360,7 +381,8 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	struct msm_drm_private *priv;
 	struct msm_kms *kms;
 	struct msm_mdss *mdss;
-	int ret;
+	int ret, i;
+	struct sched_param param;
 
 	ddev = drm_dev_alloc(drv, dev);
 	if (IS_ERR(ddev)) {
@@ -379,7 +401,17 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	ddev->dev_private = priv;
 	priv->dev = ddev;
 
-	ret = mdp5_mdss_init(ddev);
+	switch (get_mdp_ver(pdev)) {
+	case KMS_MDP5:
+		ret = mdp5_mdss_init(ddev);
+		break;
+	case KMS_DPU:
+		ret = dpu_mdss_init(ddev);
+		break;
+	default:
+		ret = 0;
+		break;
+	}
 	if (ret)
 		goto err_free_priv;
 
@@ -389,7 +421,7 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 
 	INIT_LIST_HEAD(&priv->inactive_list);
 	INIT_LIST_HEAD(&priv->vblank_ctrl.event_list);
-	INIT_WORK(&priv->vblank_ctrl.work, vblank_ctrl_worker);
+	kthread_init_work(&priv->vblank_ctrl.work, vblank_ctrl_worker);
 	spin_lock_init(&priv->vblank_ctrl.lock);
 
 	drm_mode_config_init(ddev);
@@ -413,6 +445,10 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	case KMS_MDP5:
 		kms = mdp5_kms_init(ddev);
 		break;
+	case KMS_DPU:
+		kms = dpu_kms_init(ddev);
+		priv->kms = kms;
+		break;
 	default:
 		kms = ERR_PTR(-ENODEV);
 		break;
@@ -444,6 +480,79 @@ static int msm_drm_init(struct device *dev, struct drm_driver *drv)
 	ddev->mode_config.funcs = &mode_config_funcs;
 	ddev->mode_config.helper_private = &mode_config_helper_funcs;
 
+	/**
+	 * this priority was found during empiric testing to have appropriate
+	 * realtime scheduling to process display updates and interact with
+	 * other real time and normal priority task
+	 */
+	param.sched_priority = 16;
+	for (i = 0; i < priv->num_crtcs; i++) {
+
+		/* initialize display thread */
+		priv->disp_thread[i].crtc_id = priv->crtcs[i]->base.id;
+		kthread_init_worker(&priv->disp_thread[i].worker);
+		priv->disp_thread[i].dev = ddev;
+		priv->disp_thread[i].thread =
+			kthread_run(kthread_worker_fn,
+				&priv->disp_thread[i].worker,
+				"crtc_commit:%d", priv->disp_thread[i].crtc_id);
+		ret = sched_setscheduler(priv->disp_thread[i].thread,
+							SCHED_FIFO, &param);
+		if (ret)
+			pr_warn("display thread priority update failed: %d\n",
+									ret);
+
+		if (IS_ERR(priv->disp_thread[i].thread)) {
+			dev_err(dev, "failed to create crtc_commit kthread\n");
+			priv->disp_thread[i].thread = NULL;
+		}
+
+		/* initialize event thread */
+		priv->event_thread[i].crtc_id = priv->crtcs[i]->base.id;
+		kthread_init_worker(&priv->event_thread[i].worker);
+		priv->event_thread[i].dev = ddev;
+		priv->event_thread[i].thread =
+			kthread_run(kthread_worker_fn,
+				&priv->event_thread[i].worker,
+				"crtc_event:%d", priv->event_thread[i].crtc_id);
+		/**
+		 * event thread should also run at same priority as disp_thread
+		 * because it is handling frame_done events. A lower priority
+		 * event thread and higher priority disp_thread can causes
+		 * frame_pending counters beyond 2. This can lead to commit
+		 * failure at crtc commit level.
+		 */
+		ret = sched_setscheduler(priv->event_thread[i].thread,
+							SCHED_FIFO, &param);
+		if (ret)
+			pr_warn("display event thread priority update failed: %d\n",
+									ret);
+
+		if (IS_ERR(priv->event_thread[i].thread)) {
+			dev_err(dev, "failed to create crtc_event kthread\n");
+			priv->event_thread[i].thread = NULL;
+		}
+
+		if ((!priv->disp_thread[i].thread) ||
+				!priv->event_thread[i].thread) {
+			/* clean up previously created threads if any */
+			for ( ; i >= 0; i--) {
+				if (priv->disp_thread[i].thread) {
+					kthread_stop(
+						priv->disp_thread[i].thread);
+					priv->disp_thread[i].thread = NULL;
+				}
+
+				if (priv->event_thread[i].thread) {
+					kthread_stop(
+						priv->event_thread[i].thread);
+					priv->event_thread[i].thread = NULL;
+				}
+			}
+			goto err_msm_uninit;
+		}
+	}
+
 	ret = drm_vblank_init(ddev, priv->num_crtcs);
 	if (ret < 0) {
 		dev_err(dev, "failed to initialize vblank\n");
@@ -1060,12 +1169,13 @@ static int add_display_components(struct device *dev,
 	int ret;
 
 	/*
-	 * MDP5 based devices don't have a flat hierarchy. There is a top level
-	 * parent: MDSS, and children: MDP5, DSI, HDMI, eDP etc. Populate the
-	 * children devices, find the MDP5 node, and then add the interfaces
-	 * to our components list.
+	 * MDP5/DPU based devices don't have a flat hierarchy. There is a top
+	 * level parent: MDSS, and children: MDP5/DPU, DSI, HDMI, eDP etc.
+	 * Populate the children devices, find the MDP5/DPU node, and then add
+	 * the interfaces to our components list.
 	 */
-	if (of_device_is_compatible(dev->of_node, "qcom,mdss")) {
+	if (of_device_is_compatible(dev->of_node, "qcom,mdss") ||
+	    of_device_is_compatible(dev->of_node, "qcom,sdm845-mdss")) {
 		ret = of_platform_populate(dev->of_node, NULL, NULL, dev);
 		if (ret) {
 			dev_err(dev, "failed to populate children devices\n");
@@ -1177,6 +1287,7 @@ static int msm_pdev_remove(struct platform_device *pdev)
 static const struct of_device_id dt_match[] = {
 	{ .compatible = "qcom,mdp4", .data = (void *)KMS_MDP4 },
 	{ .compatible = "qcom,mdss", .data = (void *)KMS_MDP5 },
+	{ .compatible = "qcom,sdm845-mdss", .data = (void *)KMS_DPU },
 	{}
 };
 MODULE_DEVICE_TABLE(of, dt_match);
@@ -1198,6 +1309,7 @@ static int __init msm_drm_register(void)
 
 	DBG("init");
 	msm_mdp_register();
+	msm_dpu_register();
 	msm_dsi_register();
 	msm_edp_register();
 	msm_hdmi_register();
@@ -1214,6 +1326,7 @@ static void __exit msm_drm_unregister(void)
 	msm_edp_unregister();
 	msm_dsi_unregister();
 	msm_mdp_unregister();
+	msm_dpu_unregister();
 }
 
 module_init(msm_drm_register);
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index 3b206ae6423f..0cba86ed3f54 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -33,6 +34,7 @@
 #include <linux/of_graph.h>
 #include <linux/of_device.h>
 #include <asm/sizes.h>
+#include <linux/kthread.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_atomic.h>
@@ -55,7 +57,7 @@ struct msm_gem_address_space;
 struct msm_gem_vma;
 
 #define MAX_CRTCS      8
-#define MAX_PLANES     16
+#define MAX_PLANES     20
 #define MAX_ENCODERS   8
 #define MAX_BRIDGES    8
 #define MAX_CONNECTORS 8
@@ -74,12 +76,77 @@ enum msm_mdp_plane_property {
 };
 
 struct msm_vblank_ctrl {
-	struct work_struct work;
+	struct kthread_work work;
 	struct list_head event_list;
 	spinlock_t lock;
 };
 
 #define MSM_GPU_MAX_RINGS 4
+#define MAX_H_TILES_PER_DISPLAY 2
+
+/**
+ * enum msm_display_caps - features/capabilities supported by displays
+ * @MSM_DISPLAY_CAP_VID_MODE:           Video or "active" mode supported
+ * @MSM_DISPLAY_CAP_CMD_MODE:           Command mode supported
+ * @MSM_DISPLAY_CAP_HOT_PLUG:           Hot plug detection supported
+ * @MSM_DISPLAY_CAP_EDID:               EDID supported
+ */
+enum msm_display_caps {
+	MSM_DISPLAY_CAP_VID_MODE	= BIT(0),
+	MSM_DISPLAY_CAP_CMD_MODE	= BIT(1),
+	MSM_DISPLAY_CAP_HOT_PLUG	= BIT(2),
+	MSM_DISPLAY_CAP_EDID		= BIT(3),
+};
+
+/**
+ * enum msm_event_wait - type of HW events to wait for
+ * @MSM_ENC_COMMIT_DONE - wait for the driver to flush the registers to HW
+ * @MSM_ENC_TX_COMPLETE - wait for the HW to transfer the frame to panel
+ * @MSM_ENC_VBLANK - wait for the HW VBLANK event (for driver-internal waiters)
+ */
+enum msm_event_wait {
+	MSM_ENC_COMMIT_DONE = 0,
+	MSM_ENC_TX_COMPLETE,
+	MSM_ENC_VBLANK,
+};
+
+/**
+ * struct msm_display_topology - defines a display topology pipeline
+ * @num_lm:       number of layer mixers used
+ * @num_enc:      number of compression encoder blocks used
+ * @num_intf:     number of interfaces the panel is mounted on
+ */
+struct msm_display_topology {
+	u32 num_lm;
+	u32 num_enc;
+	u32 num_intf;
+};
+
+/**
+ * struct msm_display_info - defines display properties
+ * @intf_type:          DRM_MODE_CONNECTOR_ display type
+ * @capabilities:       Bitmask of display flags
+ * @num_of_h_tiles:     Number of horizontal tiles in case of split interface
+ * @h_tile_instance:    Controller instance used per tile. Number of elements is
+ *                      based on num_of_h_tiles
+ * @is_te_using_watchdog_timer:  Boolean to indicate watchdog TE is
+ *				 used instead of panel TE in cmd mode panels
+ */
+struct msm_display_info {
+	int intf_type;
+	uint32_t capabilities;
+	uint32_t num_of_h_tiles;
+	uint32_t h_tile_instance[MAX_H_TILES_PER_DISPLAY];
+	bool is_te_using_watchdog_timer;
+};
+
+/* Commit/Event thread specific structure */
+struct msm_drm_thread {
+	struct drm_device *dev;
+	struct task_struct *thread;
+	unsigned int crtc_id;
+	struct kthread_worker worker;
+};
 
 struct msm_drm_private {
 
@@ -90,7 +157,7 @@ struct msm_drm_private {
 	/* subordinate devices, if present: */
 	struct platform_device *gpu_pdev;
 
-	/* top level MDSS wrapper device (for MDP5 only) */
+	/* top level MDSS wrapper device (for MDP5/DPU only) */
 	struct msm_mdss *mdss;
 
 	/* possibly this should be in the kms component, but it is
@@ -128,6 +195,9 @@ struct msm_drm_private {
 	unsigned int num_crtcs;
 	struct drm_crtc *crtcs[MAX_CRTCS];
 
+	struct msm_drm_thread disp_thread[MAX_CRTCS];
+	struct msm_drm_thread event_thread[MAX_CRTCS];
+
 	unsigned int num_encoders;
 	struct drm_encoder *encoders[MAX_ENCODERS];
 
@@ -180,6 +250,9 @@ struct msm_gem_address_space *
 msm_gem_address_space_create(struct device *dev, struct iommu_domain *domain,
 		const char *name);
 
+int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
+void msm_unregister_mmu(struct drm_device *dev, struct msm_mmu *mmu);
+
 void msm_gem_submit_free(struct msm_gem_submit *submit);
 int msm_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
@@ -291,6 +364,8 @@ static inline int msm_dsi_modeset_init(struct msm_dsi *msm_dsi,
 
 void __init msm_mdp_register(void);
 void __exit msm_mdp_unregister(void);
+void __init msm_dpu_register(void);
+void __exit msm_dpu_unregister(void);
 
 #ifdef CONFIG_DEBUG_FS
 void msm_gem_describe(struct drm_gem_object *obj, struct seq_file *m);
diff --git a/drivers/gpu/drm/msm/msm_kms.h b/drivers/gpu/drm/msm/msm_kms.h
index c15de28ae2dd..fd88cebb6adb 100644
--- a/drivers/gpu/drm/msm/msm_kms.h
+++ b/drivers/gpu/drm/msm/msm_kms.h
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2016-2018, The Linux Foundation. All rights reserved.
  * Copyright (C) 2013 Red Hat
  * Author: Rob Clark <robdclark@gmail.com>
  *
@@ -51,6 +52,11 @@ struct msm_kms_funcs {
 	const struct msm_format *(*get_format)(struct msm_kms *kms,
 					const uint32_t format,
 					const uint64_t modifiers);
+	/* do format checking on format modified through fb_cmd2 modifiers */
+	int (*check_modified_format)(const struct msm_kms *kms,
+			const struct msm_format *msm_fmt,
+			const struct drm_mode_fb_cmd2 *cmd,
+			struct drm_gem_object **bos);
 	/* misc: */
 	long (*round_pixclk)(struct msm_kms *kms, unsigned long rate,
 			struct drm_encoder *encoder);
@@ -90,6 +96,7 @@ static inline void msm_kms_init(struct msm_kms *kms,
 
 struct msm_kms *mdp4_kms_init(struct drm_device *dev);
 struct msm_kms *mdp5_kms_init(struct drm_device *dev);
+struct msm_kms *dpu_kms_init(struct drm_device *dev);
 
 struct msm_mdss_funcs {
 	int (*enable)(struct msm_mdss *mdss);
@@ -103,5 +110,6 @@ struct msm_mdss {
 };
 
 int mdp5_mdss_init(struct drm_device *dev);
+int dpu_mdss_init(struct drm_device *dev);
 
 #endif /* __MSM_KMS_H__ */
-- 
cgit v1.2.3


From 2f2eb723b50b4da887a34570ff15a3c23d966b85 Mon Sep 17 00:00:00 2001
From: Rajesh Yadav <ryadav@codeaurora.org>
Date: Fri, 13 Jul 2018 18:27:23 +0530
Subject: drm/msm: rework vblank event handling in dpu_crtc

The vblank on/off calls were missing in dpu_crtc
leading to "driver forgot to call drm_crtc_vblank_off()"
warning while entering suspend state.
Also handle the state update completion event for
a crtc being disabled in current atomic commit.

This patch depends on https://www.spinics.net/lists/dri-devel/msg182402.html

Signed-off-by: Rajesh Yadav <ryadav@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index bcc4796cb5da..7ac0e0dda866 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -1606,6 +1606,7 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 	struct drm_encoder *encoder;
 	struct msm_drm_private *priv;
 	int ret;
+	unsigned long flags;
 
 	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !crtc->state) {
 		DPU_ERROR("invalid crtc\n");
@@ -1621,6 +1622,9 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 	if (dpu_kms_is_suspend_state(crtc->dev))
 		_dpu_crtc_set_suspend(crtc, true);
 
+	/* Disable/save vblank irq handling */
+	drm_crtc_vblank_off(crtc);
+
 	mutex_lock(&dpu_crtc->crtc_lock);
 
 	/* wait for frame_event_done completion */
@@ -1658,7 +1662,6 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 		dpu_power_handle_unregister_event(dpu_crtc->phandle,
 				dpu_crtc->power_event);
 
-
 	memset(dpu_crtc->mixers, 0, sizeof(dpu_crtc->mixers));
 	dpu_crtc->num_mixers = 0;
 	dpu_crtc->mixers_swapped = false;
@@ -1668,6 +1671,13 @@ static void dpu_crtc_disable(struct drm_crtc *crtc)
 	cstate->bw_split_vote = false;
 
 	mutex_unlock(&dpu_crtc->crtc_lock);
+
+	if (crtc->state->event && !crtc->state->active) {
+		spin_lock_irqsave(&crtc->dev->event_lock, flags);
+		drm_crtc_send_vblank_event(crtc, crtc->state->event);
+		crtc->state->event = NULL;
+		spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+	}
 }
 
 static void dpu_crtc_enable(struct drm_crtc *crtc,
@@ -1707,6 +1717,9 @@ static void dpu_crtc_enable(struct drm_crtc *crtc,
 
 	mutex_unlock(&dpu_crtc->crtc_lock);
 
+	/* Enable/restore vblank irq handling */
+	drm_crtc_vblank_on(crtc);
+
 	dpu_crtc->power_event = dpu_power_handle_register_event(
 		dpu_crtc->phandle,
 		DPU_POWER_EVENT_POST_ENABLE | DPU_POWER_EVENT_POST_DISABLE |
-- 
cgit v1.2.3


From 036e4963bfb2d4513c30efd80e4bd50ff6c79e3e Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 26 Jul 2018 14:45:42 +0200
Subject: ASoC: meson: use IRQ_RETVAL in the fifo irq handler

Use IRQ_RETVAL instead of the open coded ternary operation.

Suggested-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/axg-fifo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c
index db367d85290f..30262550e37b 100644
--- a/sound/soc/meson/axg-fifo.c
+++ b/sound/soc/meson/axg-fifo.c
@@ -174,7 +174,7 @@ static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id)
 	/* Ack irqs */
 	axg_fifo_ack_irq(fifo, status);
 
-	return !status ? IRQ_NONE : IRQ_HANDLED;
+	return IRQ_RETVAL(status);
 }
 
 static int axg_fifo_pcm_open(struct snd_pcm_substream *ss)
-- 
cgit v1.2.3


From d9e81048127604fe6373fb76181fefcf218965f4 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 26 Jul 2018 14:45:43 +0200
Subject: ASoC: meson: update axg sound card bindings

Remove the amlogic prefix in front of the generic properties and change
the card 'name' property to 'model'

Suggested-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/sound/amlogic,axg-sound-card.txt      | 68 +++++++++++-----------
 1 file changed, 34 insertions(+), 34 deletions(-)

diff --git a/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt b/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt
index 39e005da0407..80b411296480 100644
--- a/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt
+++ b/Documentation/devicetree/bindings/sound/amlogic,axg-sound-card.txt
@@ -3,19 +3,19 @@ Amlogic AXG sound card:
 Required properties:
 
 - compatible: "amlogic,axg-sound-card"
-- amlogic,name : User specified audio sound card name, one string
+- model : User specified audio sound card name, one string
 
 Optional properties:
 
-- amlogic,aux-devs : List of phandles pointing to auxiliary devices
-- amlogic,widgets : Please refer to widgets.txt.
-- amlogic,routing : A list of the connections between audio components.
+- audio-aux-devs : List of phandles pointing to auxiliary devices
+- audio-widgets : Please refer to widgets.txt.
+- audio-routing : A list of the connections between audio components.
 
 Subnodes:
 
-- amlogic,dai-link: Container for dai-link level properties and the
-		    CODEC sub-nodes. There should be at least one (and
-		    probably) subnode of this type.
+- dai-link: Container for dai-link level properties and the CODEC
+	    sub-nodes. There should be at least one (and probably more)
+	    subnode of this type.
 
 Required dai-link properties:
 
@@ -57,38 +57,38 @@ Example:
 
 sound {
 	compatible = "amlogic,axg-sound-card";
-	amlogic,name = "AXG-S420";
-	amlogic,aux-devs = <&tdmin_a>, <&tdmout_c>;
-	amlogic,widgets = "Line", "Lineout",
-			  "Line", "Linein",
-			  "Speaker", "Speaker1 Left",
-			  "Speaker", "Speaker1 Right";
-			  "Speaker", "Speaker2 Left",
-			  "Speaker", "Speaker2 Right";
-	amlogic,routing = "TDMOUT_C IN 0", "FRDDR_A OUT 2",
-			  "SPDIFOUT IN 0", "FRDDR_A OUT 3",
-			  "TDM_C Playback", "TDMOUT_C OUT",
-			  "TDMIN_A IN 2", "TDM_C Capture",
-			  "TDMIN_A IN 5", "TDM_C Loopback",
-			  "TODDR_A IN 0", "TDMIN_A OUT",
-			  "Lineout", "Lineout AOUTL",
-			  "Lineout", "Lineout AOUTR",
-			  "Speaker1 Left", "SPK1 OUT_A",
-			  "Speaker2 Left", "SPK2 OUT_A",
-			  "Speaker1 Right", "SPK1 OUT_B",
-			  "Speaker2 Right", "SPK2 OUT_B",
-			  "Linein AINL", "Linein",
-			  "Linein AINR", "Linein";
-
-	amlogic,dai-link@0 {
+	model = "AXG-S420";
+	audio-aux-devs = <&tdmin_a>, <&tdmout_c>;
+	audio-widgets = "Line", "Lineout",
+			"Line", "Linein",
+			"Speaker", "Speaker1 Left",
+			"Speaker", "Speaker1 Right";
+			"Speaker", "Speaker2 Left",
+			"Speaker", "Speaker2 Right";
+	audio-routing = "TDMOUT_C IN 0", "FRDDR_A OUT 2",
+			"SPDIFOUT IN 0", "FRDDR_A OUT 3",
+			"TDM_C Playback", "TDMOUT_C OUT",
+			"TDMIN_A IN 2", "TDM_C Capture",
+			"TDMIN_A IN 5", "TDM_C Loopback",
+			"TODDR_A IN 0", "TDMIN_A OUT",
+			"Lineout", "Lineout AOUTL",
+			"Lineout", "Lineout AOUTR",
+			"Speaker1 Left", "SPK1 OUT_A",
+			"Speaker2 Left", "SPK2 OUT_A",
+			"Speaker1 Right", "SPK1 OUT_B",
+			"Speaker2 Right", "SPK2 OUT_B",
+			"Linein AINL", "Linein",
+			"Linein AINR", "Linein";
+
+	dai-link@0 {
 		sound-dai = <&frddr_a>;
 	};
 
-	amlogic,dai-link@1 {
+	dai-link@1 {
 		sound-dai = <&toddr_a>;
 	};
 
-	amlogic,dai-link@2 {
+	dai-link@2 {
 		sound-dai = <&tdmif_c>;
 		dai-format = "i2s";
 		dai-tdm-slot-tx-mask-2 = <1 1>;
@@ -114,7 +114,7 @@ sound {
 
 	};
 
-	amlogic,dai-link@4 {
+	dai-link@3 {
 		sound-dai = <&spdifout>;
 
 		codec {
-- 
cgit v1.2.3


From 435857e015dc7b337c5f21d195ac2e4ffd694283 Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 26 Jul 2018 14:45:44 +0200
Subject: ASoC: meson: align axg card driver with DT bindings documentation

Drop amlogic prefix in front of the generic DT properties and change
property "name" to "model".

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/meson/axg-card.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c
index d6d1081d94ad..2914ba0d965b 100644
--- a/sound/soc/meson/axg-card.c
+++ b/sound/soc/meson/axg-card.c
@@ -123,7 +123,7 @@ static int axg_card_add_aux_devices(struct snd_soc_card *card)
 	struct snd_soc_aux_dev *aux;
 	int num, i;
 
-	num = of_count_phandle_with_args(node, PREFIX "aux-devs", NULL);
+	num = of_count_phandle_with_args(node, "audio-aux-devs", NULL);
 	if (num == -ENOENT) {
 		/*
 		 * It is ok to have no auxiliary devices but for this card it
@@ -144,8 +144,8 @@ static int axg_card_add_aux_devices(struct snd_soc_card *card)
 	card->num_aux_devs = num;
 
 	for (i = 0; i < card->num_aux_devs; i++, aux++) {
-		aux->codec_of_node = of_parse_phandle(node,
-						      PREFIX "aux-devs", i);
+		aux->codec_of_node =
+			of_parse_phandle(node, "audio-aux-devs", i);
 		if (!aux->codec_of_node)
 			return -EINVAL;
 	}
@@ -610,18 +610,18 @@ static int axg_card_probe(struct platform_device *pdev)
 	priv->card.owner = THIS_MODULE;
 	priv->card.dev = dev;
 
-	ret = snd_soc_of_parse_card_name(&priv->card, PREFIX "name");
+	ret = snd_soc_of_parse_card_name(&priv->card, "model");
 	if (ret < 0)
 		return ret;
 
-	ret = axg_card_parse_of_optional(&priv->card, PREFIX "routing",
+	ret = axg_card_parse_of_optional(&priv->card, "audio-routing",
 					 snd_soc_of_parse_audio_routing);
 	if (ret) {
 		dev_err(dev, "error while parsing routing\n");
 		return ret;
 	}
 
-	ret = axg_card_parse_of_optional(&priv->card, PREFIX "widgets",
+	ret = axg_card_parse_of_optional(&priv->card, "audio-widgets",
 					 snd_soc_of_parse_audio_simple_widgets);
 	if (ret) {
 		dev_err(dev, "error while parsing widgets\n");
-- 
cgit v1.2.3


From 150a6dc8fc764c1912fa2a46e18d1505dfd3536f Mon Sep 17 00:00:00 2001
From: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx@renesas.com>
Date: Thu, 26 Jul 2018 05:40:15 +0900
Subject: ASoC: rsnd: Document R-Car M3-N support

Document support for the sound modules in the Renesas M3-N (r8a77965)
SoC.

No driver update is needed.

Signed-off-by: Hiroyuki Yokoyama <hiroyuki.yokoyama.vx@renesas.com>
Signed-off-by: Yoshihiro Kaneko <ykaneko0929@gmail.com>
Acked-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/renesas,rsnd.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
index b86d790f630f..9e764270c36b 100644
--- a/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
+++ b/Documentation/devicetree/bindings/sound/renesas,rsnd.txt
@@ -352,6 +352,7 @@ Required properties:
 				    - "renesas,rcar_sound-r8a7794" (R-Car E2)
 				    - "renesas,rcar_sound-r8a7795" (R-Car H3)
 				    - "renesas,rcar_sound-r8a7796" (R-Car M3-W)
+				    - "renesas,rcar_sound-r8a77965" (R-Car M3-N)
 - reg				: Should contain the register physical address.
 				  required register is
 				   SRU/ADG/SSI      if generation1
-- 
cgit v1.2.3


From c889a45d229938a94b50aadb819def8bb11a6a54 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 22:40:49 +0200
Subject: ASoC: zte: Fix incorrect PCM format bit usages

zx-tdm driver sets the DAI driver definitions with the format bits
wrongly set with SNDRV_PCM_FORMAT_*, instead of SNDRV_PCM_FMTBIT_*.

This patch corrects the definitions.

Spotted by a sparse warning:
  sound/soc/zte/zx-tdm.c:363:35: warning: restricted snd_pcm_format_t degrades to integer

Fixes: 870e0ddc4345 ("ASoC: zx-tdm: add zte's tdm controller driver")
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/zte/zx-tdm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/zte/zx-tdm.c b/sound/soc/zte/zx-tdm.c
index dc955272f58b..389272eeba9a 100644
--- a/sound/soc/zte/zx-tdm.c
+++ b/sound/soc/zte/zx-tdm.c
@@ -144,8 +144,8 @@ static void zx_tdm_rx_dma_en(struct zx_tdm_info *tdm, bool on)
 #define ZX_TDM_RATES	(SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000)
 
 #define ZX_TDM_FMTBIT \
-	(SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FORMAT_MU_LAW | \
-	SNDRV_PCM_FORMAT_A_LAW)
+	(SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_MU_LAW | \
+	SNDRV_PCM_FMTBIT_A_LAW)
 
 static int zx_tdm_dai_probe(struct snd_soc_dai *dai)
 {
-- 
cgit v1.2.3


From 40d1299f87bf915931970c8e6ea3852acacd1889 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 22:42:08 +0200
Subject: ASoC: dmaengine: Fix missing __user prefix in copy_user callback

It seems that __user prefix was forgotten to be added to
dmaengine_copy_user callback while we refactored the user-copy PCM
core.

This patch adds the missing prefix, remove the superfluous cast, and
add the needed cast (__force is needed for downgrading from user
pointer to kernel pointer), too.

Spotted by a sparse warning like:
  sound/soc/soc-generic-dmaengine-pcm.c:397:27: warning: incorrect type in initializer (incompatible argument 4 (different address spaces))

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-generic-dmaengine-pcm.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 13bdca6e41c5..120f7b39e256 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -334,7 +334,7 @@ static snd_pcm_uframes_t dmaengine_pcm_pointer(
 
 static int dmaengine_copy_user(struct snd_pcm_substream *substream,
 			       int channel, unsigned long hwoff,
-			       void *buf, unsigned long bytes)
+			       void __user *buf, unsigned long bytes)
 {
 	struct snd_soc_pcm_runtime *rtd = substream->private_data;
 	struct snd_soc_component *component =
@@ -350,18 +350,17 @@ static int dmaengine_copy_user(struct snd_pcm_substream *substream,
 	int ret;
 
 	if (is_playback)
-		if (copy_from_user(dma_ptr, (void __user *)buf, bytes))
+		if (copy_from_user(dma_ptr, buf, bytes))
 			return -EFAULT;
 
 	if (process) {
-		ret = process(substream, channel, hwoff,
-			      (void __user *)buf, bytes);
+		ret = process(substream, channel, hwoff, (__force void *)buf, bytes);
 		if (ret < 0)
 			return ret;
 	}
 
 	if (!is_playback)
-		if (copy_to_user((void __user *)buf, dma_ptr, bytes))
+		if (copy_to_user(buf, dma_ptr, bytes))
 			return -EFAULT;
 
 	return 0;
-- 
cgit v1.2.3


From 3ba66feb59810e2ce616da0c4f1a5230c74768a8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 22:43:26 +0200
Subject: ASoC: dapm: Use int for format bit position

fmt in snd_soc_dai_link_event() contains the format bit position, not
the format bit itself.  Hence it can be a simple integer instead of
the explicit u64.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-dapm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 0602b2888d52..7e96793050c9 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3656,7 +3656,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w,
 	struct snd_pcm_substream substream;
 	struct snd_pcm_hw_params *params = NULL;
 	struct snd_pcm_runtime *runtime = NULL;
-	u64 fmt;
+	unsigned int fmt;
 	int ret;
 
 	if (WARN_ON(!config) ||
-- 
cgit v1.2.3


From c32cd419d6650e42b9cdebb83c672ec945e6bd7e Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 9 Jul 2018 10:05:22 +0100
Subject: ARM: signal: copy registers using __copy_from_user()

__get_user_error() is used as a fast accessor to make copying structure
members in the signal handling path as efficient as possible.  However,
with software PAN and the recent Spectre variant 1, the efficiency is
reduced as these are no longer fast accessors.

In the case of software PAN, it has to switch the domain register around
each access, and with Spectre variant 1, it would have to repeat the
access_ok() check for each access.

It becomes much more efficient to use __copy_from_user() instead, so
let's use this for the ARM integer registers.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/kernel/signal.c | 38 +++++++++++++++++++++-----------------
 1 file changed, 21 insertions(+), 17 deletions(-)

diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index bd8810d4acb3..0ae74207e43e 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -176,6 +176,7 @@ static int restore_vfp_context(char __user **auxp)
 
 static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 {
+	struct sigcontext context;
 	char __user *aux;
 	sigset_t set;
 	int err;
@@ -184,23 +185,26 @@ static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf)
 	if (err == 0)
 		set_current_blocked(&set);
 
-	__get_user_error(regs->ARM_r0, &sf->uc.uc_mcontext.arm_r0, err);
-	__get_user_error(regs->ARM_r1, &sf->uc.uc_mcontext.arm_r1, err);
-	__get_user_error(regs->ARM_r2, &sf->uc.uc_mcontext.arm_r2, err);
-	__get_user_error(regs->ARM_r3, &sf->uc.uc_mcontext.arm_r3, err);
-	__get_user_error(regs->ARM_r4, &sf->uc.uc_mcontext.arm_r4, err);
-	__get_user_error(regs->ARM_r5, &sf->uc.uc_mcontext.arm_r5, err);
-	__get_user_error(regs->ARM_r6, &sf->uc.uc_mcontext.arm_r6, err);
-	__get_user_error(regs->ARM_r7, &sf->uc.uc_mcontext.arm_r7, err);
-	__get_user_error(regs->ARM_r8, &sf->uc.uc_mcontext.arm_r8, err);
-	__get_user_error(regs->ARM_r9, &sf->uc.uc_mcontext.arm_r9, err);
-	__get_user_error(regs->ARM_r10, &sf->uc.uc_mcontext.arm_r10, err);
-	__get_user_error(regs->ARM_fp, &sf->uc.uc_mcontext.arm_fp, err);
-	__get_user_error(regs->ARM_ip, &sf->uc.uc_mcontext.arm_ip, err);
-	__get_user_error(regs->ARM_sp, &sf->uc.uc_mcontext.arm_sp, err);
-	__get_user_error(regs->ARM_lr, &sf->uc.uc_mcontext.arm_lr, err);
-	__get_user_error(regs->ARM_pc, &sf->uc.uc_mcontext.arm_pc, err);
-	__get_user_error(regs->ARM_cpsr, &sf->uc.uc_mcontext.arm_cpsr, err);
+	err |= __copy_from_user(&context, &sf->uc.uc_mcontext, sizeof(context));
+	if (err == 0) {
+		regs->ARM_r0 = context.arm_r0;
+		regs->ARM_r1 = context.arm_r1;
+		regs->ARM_r2 = context.arm_r2;
+		regs->ARM_r3 = context.arm_r3;
+		regs->ARM_r4 = context.arm_r4;
+		regs->ARM_r5 = context.arm_r5;
+		regs->ARM_r6 = context.arm_r6;
+		regs->ARM_r7 = context.arm_r7;
+		regs->ARM_r8 = context.arm_r8;
+		regs->ARM_r9 = context.arm_r9;
+		regs->ARM_r10 = context.arm_r10;
+		regs->ARM_fp = context.arm_fp;
+		regs->ARM_ip = context.arm_ip;
+		regs->ARM_sp = context.arm_sp;
+		regs->ARM_lr = context.arm_lr;
+		regs->ARM_pc = context.arm_pc;
+		regs->ARM_cpsr = context.arm_cpsr;
+	}
 
 	err |= !valid_user_regs(regs);
 
-- 
cgit v1.2.3


From 38b7e7f8ae821bbed28a13b3ac7a7a58aa7cdb95 Mon Sep 17 00:00:00 2001
From: Tony Nguyen <anthony.l.nguyen@intel.com>
Date: Wed, 30 May 2018 16:14:23 -0700
Subject: ixgbe: Do not allow LRO or MTU change with XDP

XDP does not support jumbo frames or LRO.  These checks are being made
outside the driver when an XDP program is loaded, however, there is
nothing preventing these from changing after an XDP program is loaded.
Add the checks so that while an XDP program is loaded, do not allow MTU
to be changed or LRO to be enabled.

Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 5a6600f7b382..c42256e91997 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -6469,6 +6469,11 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 
+	if (adapter->xdp_prog) {
+		e_warn(probe, "MTU cannot be changed while XDP program is loaded\n");
+		return -EPERM;
+	}
+
 	/*
 	 * For 82599EB we cannot allow legacy VFs to enable their receive
 	 * paths when MTU greater than 1500 is configured.  So display a
@@ -9407,6 +9412,11 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev,
 	if (!(adapter->flags2 & IXGBE_FLAG2_RSC_CAPABLE))
 		features &= ~NETIF_F_LRO;
 
+	if (adapter->xdp_prog && (features & NETIF_F_LRO)) {
+		e_dev_err("LRO is not supported with XDP\n");
+		features &= ~NETIF_F_LRO;
+	}
+
 	return features;
 }
 
-- 
cgit v1.2.3


From 7f6cdbdafbd19191ef88ca148747a213f422be43 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@oracle.com>
Date: Mon, 2 Jul 2018 17:09:30 -0700
Subject: ixgbe: add ipsec security registers into ethtool register dump

Add the ixgbe's security configuration registers into
the register dump.

Signed-off-by: Shannon Nelson <shannon.nelson@oracle.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index bd1ba88ec1d5..1d688840cd6c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -511,7 +511,7 @@ static void ixgbe_set_msglevel(struct net_device *netdev, u32 data)
 
 static int ixgbe_get_regs_len(struct net_device *netdev)
 {
-#define IXGBE_REGS_LEN  1139
+#define IXGBE_REGS_LEN  1145
 	return IXGBE_REGS_LEN * sizeof(u32);
 }
 
@@ -874,6 +874,14 @@ static void ixgbe_get_regs(struct net_device *netdev,
 	/* X540 specific DCB registers  */
 	regs_buff[1137] = IXGBE_READ_REG(hw, IXGBE_RTTQCNCR);
 	regs_buff[1138] = IXGBE_READ_REG(hw, IXGBE_RTTQCNTG);
+
+	/* Security config registers */
+	regs_buff[1139] = IXGBE_READ_REG(hw, IXGBE_SECTXCTRL);
+	regs_buff[1140] = IXGBE_READ_REG(hw, IXGBE_SECTXSTAT);
+	regs_buff[1141] = IXGBE_READ_REG(hw, IXGBE_SECTXBUFFAF);
+	regs_buff[1142] = IXGBE_READ_REG(hw, IXGBE_SECTXMINIFG);
+	regs_buff[1143] = IXGBE_READ_REG(hw, IXGBE_SECRXCTRL);
+	regs_buff[1144] = IXGBE_READ_REG(hw, IXGBE_SECRXSTAT);
 }
 
 static int ixgbe_get_eeprom_len(struct net_device *netdev)
-- 
cgit v1.2.3


From 2a83fba6cae89dd9c0625e68ff8ffff791c67ac0 Mon Sep 17 00:00:00 2001
From: Christian Grönke <c.groenke@infodas.de>
Date: Tue, 26 Jun 2018 10:12:18 +0000
Subject: igb: Remove superfluous reset to PHY and page 0 selection
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch reverts two previous applied patches to fix an issue
that appeared when using SGMII based SFP modules. In the current
state the driver will try to reset the PHY before obtaining the
phy_addr of the SGMII attached PHY. That leads to an error in
e1000_write_phy_reg_sgmii_82575. Causing the initialization to
fail:

    igb: Intel(R) Gigabit Ethernet Network Driver - version 5.4.0-k
    igb: Copyright (c) 2007-2014 Intel Corporation.
    igb: probe of ????:??:??.? failed with error -3

The patches being reverted are:

    commit 182785335447957409282ca745aa5bc3968facee
    Author: Aaron Sierra <asierra@xes-inc.com>
    Date:   Tue Nov 29 10:03:56 2016 -0600

        igb: reset the PHY before reading the PHY ID

    commit 440aeca4b9858248d8f16d724d9fa87a4f65fa33
    Author: Matwey V Kornilov <matwey@sai.msu.ru>
    Date:   Thu Nov 24 13:32:48 2016 +0300

         igb: Explicitly select page 0 at initialization

The first reverted patch directly causes the problem mentioned above.
In case of SGMII the phy_addr is not known at this point and will
only be obtained by 'igb_get_phy_id_82575' further down in the code.
The second removed patch selects forces selection of page 0 in the
PHY. Something that the reset tries to address as well.

As pointed out by Alexander Duzck, the patch below fixes the same
issue but in the proper location:

    commit 4e684f59d760a2c7c716bb60190783546e2d08a1
    Author: Chris J Arges <christopherarges@gmail.com>
    Date:   Wed Nov 2 09:13:42 2016 -0500

        igb: Workaround for igb i210 firmware issue

Reverts: 440aeca4b9858248d8f16d724d9fa87a4f65fa33.
Reverts: 182785335447957409282ca745aa5bc3968facee.

Signed-off-by: Christian Grönke <c.groenke@infodas.de>
Reviewed-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/e1000_82575.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index b13b42e5a1d9..a795c07d0df7 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -225,19 +225,7 @@ static s32 igb_init_phy_params_82575(struct e1000_hw *hw)
 	hw->bus.func = (rd32(E1000_STATUS) & E1000_STATUS_FUNC_MASK) >>
 			E1000_STATUS_FUNC_SHIFT;
 
-	/* Make sure the PHY is in a good state. Several people have reported
-	 * firmware leaving the PHY's page select register set to something
-	 * other than the default of zero, which causes the PHY ID read to
-	 * access something other than the intended register.
-	 */
-	ret_val = hw->phy.ops.reset(hw);
-	if (ret_val) {
-		hw_dbg("Error resetting the PHY.\n");
-		goto out;
-	}
-
 	/* Set phy->phy_addr and phy->id. */
-	igb_write_phy_reg_82580(hw, I347AT4_PAGE_SELECT, 0);
 	ret_val = igb_get_phy_id_82575(hw);
 	if (ret_val)
 		return ret_val;
-- 
cgit v1.2.3


From 73017f4e051c86985cf4647eceee34de7c13b1b1 Mon Sep 17 00:00:00 2001
From: Venkatesh Srinivas <venkateshs@google.com>
Date: Fri, 25 May 2018 00:13:21 -0400
Subject: igb: Use dma_wmb() instead of wmb() before doorbell writes

igb writes to doorbells to post transmit and receive descriptors;
after writing descriptors to memory but before writing to doorbells,
use dma_wmb() rather than wmb(). wmb() is more heavyweight than
necessary before doorbell writes.

On x86, this avoids SFENCEs before doorbell writes in both the
tx and rx refill paths.

Signed-off-by: Venkatesh Srinivas <venkateshs@google.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index e3a0c02721c9..25720d95d4ea 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -6031,7 +6031,7 @@ static int igb_tx_map(struct igb_ring *tx_ring,
 	 * We also need this memory barrier to make certain all of the
 	 * status bits have been updated before next_to_watch is written.
 	 */
-	wmb();
+	dma_wmb();
 
 	/* set next_to_watch value indicating a packet is present */
 	first->next_to_watch = tx_desc;
@@ -8531,7 +8531,7 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 		 * applicable for weak-ordered memory model archs,
 		 * such as IA-64).
 		 */
-		wmb();
+		dma_wmb();
 		writel(i, rx_ring->tail);
 	}
 }
-- 
cgit v1.2.3


From 3b5f14b50ee2079190ae6cfe7477e74676651665 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 20 Jul 2018 18:29:29 -0400
Subject: ixgbe: Reorder Tx/Rx shutdown to reduce time needed to stop device

This change is meant to help reduce the time needed to shutdown the
transmit and receive paths for the device. Specifically what we now do
after this patch is disable the transmit path first at the netdev level,
and then work on disabling the Rx. This way while we are waiting on the Rx
queues to be disabled the Tx queues have an opportunity to drain out.

In addition I have dropped the 10ms timeout that was left in the ixgbe_down
function that seems to have been carried through from back in e1000 as far
as I can tell. We shouldn't need it since we don't actually disable the Tx
until much later and we have additional logic in place for verifying the Tx
queues have been disabled.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Don Buchholz <donald.buchholz@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index c42256e91997..aa4f05c36260 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5814,6 +5814,13 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	if (test_and_set_bit(__IXGBE_DOWN, &adapter->state))
 		return; /* do nothing if already down */
 
+	/* Shut off incoming Tx traffic */
+	netif_tx_stop_all_queues(netdev);
+
+	/* call carrier off first to avoid false dev_watchdog timeouts */
+	netif_carrier_off(netdev);
+	netif_tx_disable(netdev);
+
 	/* disable receives */
 	hw->mac.ops.disable_rx(hw);
 
@@ -5822,16 +5829,9 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 		/* this call also flushes the previous write */
 		ixgbe_disable_rx_queue(adapter, adapter->rx_ring[i]);
 
-	usleep_range(10000, 20000);
-
 	/* synchronize_sched() needed for pending XDP buffers to drain */
 	if (adapter->xdp_ring[0])
 		synchronize_sched();
-	netif_tx_stop_all_queues(netdev);
-
-	/* call carrier off first to avoid false dev_watchdog timeouts */
-	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 
 	ixgbe_irq_disable(adapter);
 
-- 
cgit v1.2.3


From 1918e937ca3b4270181e6f05734d5240306bd2cf Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexander.h.duyck@intel.com>
Date: Fri, 20 Jul 2018 18:29:34 -0400
Subject: ixgbe: Refactor queue disable logic to take completion time into
 account

This change is meant to allow us to take completion time into account when
disabling queues. Previously we were just working with hard coded values
for how long we should wait. This worked fine for the standard case where
completion timeout was operating in the 50us to 50ms range, however on
platforms that have higher completion timeout times this was resulting in
Rx queues disable messages being displayed as we weren't waiting long
enough for outstanding Rx DMA completions.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Don Buchholz <donald.buchholz@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe.h         |   3 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c |  32 +--
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c    | 280 +++++++++++++++++------
 3 files changed, 224 insertions(+), 91 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index 144d5fe6b944..4fc906c6166b 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -855,7 +855,8 @@ void ixgbe_free_rx_resources(struct ixgbe_ring *);
 void ixgbe_free_tx_resources(struct ixgbe_ring *);
 void ixgbe_configure_rx_ring(struct ixgbe_adapter *, struct ixgbe_ring *);
 void ixgbe_configure_tx_ring(struct ixgbe_adapter *, struct ixgbe_ring *);
-void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter, struct ixgbe_ring *);
+void ixgbe_disable_rx(struct ixgbe_adapter *adapter);
+void ixgbe_disable_tx(struct ixgbe_adapter *adapter);
 void ixgbe_update_stats(struct ixgbe_adapter *adapter);
 int ixgbe_init_interrupt_scheme(struct ixgbe_adapter *adapter);
 bool ixgbe_wol_supported(struct ixgbe_adapter *adapter, u16 device_id,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index 1d688840cd6c..e5a8461fe6a9 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -1698,35 +1698,17 @@ static int ixgbe_intr_test(struct ixgbe_adapter *adapter, u64 *data)
 
 static void ixgbe_free_desc_rings(struct ixgbe_adapter *adapter)
 {
-	struct ixgbe_ring *tx_ring = &adapter->test_tx_ring;
-	struct ixgbe_ring *rx_ring = &adapter->test_rx_ring;
-	struct ixgbe_hw *hw = &adapter->hw;
-	u32 reg_ctl;
-
-	/* shut down the DMA engines now so they can be reinitialized later */
+	/* Shut down the DMA engines now so they can be reinitialized later,
+	 * since the test rings and normally used rings should overlap on
+	 * queue 0 we can just use the standard disable Rx/Tx calls and they
+	 * will take care of disabling the test rings for us.
+	 */
 
 	/* first Rx */
-	hw->mac.ops.disable_rx(hw);
-	ixgbe_disable_rx_queue(adapter, rx_ring);
+	ixgbe_disable_rx(adapter);
 
 	/* now Tx */
-	reg_ctl = IXGBE_READ_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx));
-	reg_ctl &= ~IXGBE_TXDCTL_ENABLE;
-	IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(tx_ring->reg_idx), reg_ctl);
-
-	switch (hw->mac.type) {
-	case ixgbe_mac_82599EB:
-	case ixgbe_mac_X540:
-	case ixgbe_mac_X550:
-	case ixgbe_mac_X550EM_x:
-	case ixgbe_mac_x550em_a:
-		reg_ctl = IXGBE_READ_REG(hw, IXGBE_DMATXCTL);
-		reg_ctl &= ~IXGBE_DMATXCTL_TE;
-		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL, reg_ctl);
-		break;
-	default:
-		break;
-	}
+	ixgbe_disable_tx(adapter);
 
 	ixgbe_reset(adapter);
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index aa4f05c36260..447098005490 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -4022,38 +4022,6 @@ static void ixgbe_rx_desc_queue_enable(struct ixgbe_adapter *adapter,
 	}
 }
 
-void ixgbe_disable_rx_queue(struct ixgbe_adapter *adapter,
-			    struct ixgbe_ring *ring)
-{
-	struct ixgbe_hw *hw = &adapter->hw;
-	int wait_loop = IXGBE_MAX_RX_DESC_POLL;
-	u32 rxdctl;
-	u8 reg_idx = ring->reg_idx;
-
-	if (ixgbe_removed(hw->hw_addr))
-		return;
-	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
-	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
-
-	/* write value back with RXDCTL.ENABLE bit cleared */
-	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
-
-	if (hw->mac.type == ixgbe_mac_82598EB &&
-	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
-		return;
-
-	/* the hardware may take up to 100us to really disable the rx queue */
-	do {
-		udelay(10);
-		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
-	} while (--wait_loop && (rxdctl & IXGBE_RXDCTL_ENABLE));
-
-	if (!wait_loop) {
-		e_err(drv, "RXDCTL.ENABLE on Rx queue %d not cleared within "
-		      "the polling period\n", reg_idx);
-	}
-}
-
 void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 			     struct ixgbe_ring *ring)
 {
@@ -4063,9 +4031,13 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter,
 	u32 rxdctl;
 	u8 reg_idx = ring->reg_idx;
 
-	/* disable queue to avoid issues while updating state */
+	/* disable queue to avoid use of these values while updating state */
 	rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
-	ixgbe_disable_rx_queue(adapter, ring);
+	rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+
+	/* write value back with RXDCTL.ENABLE bit cleared */
+	IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
+	IXGBE_WRITE_FLUSH(hw);
 
 	IXGBE_WRITE_REG(hw, IXGBE_RDBAL(reg_idx), (rdba & DMA_BIT_MASK(32)));
 	IXGBE_WRITE_REG(hw, IXGBE_RDBAH(reg_idx), (rdba >> 32));
@@ -5633,6 +5605,212 @@ void ixgbe_up(struct ixgbe_adapter *adapter)
 	ixgbe_up_complete(adapter);
 }
 
+static unsigned long ixgbe_get_completion_timeout(struct ixgbe_adapter *adapter)
+{
+	u16 devctl2;
+
+	pcie_capability_read_word(adapter->pdev, PCI_EXP_DEVCTL2, &devctl2);
+
+	switch (devctl2 & IXGBE_PCIDEVCTRL2_TIMEO_MASK) {
+	case IXGBE_PCIDEVCTRL2_17_34s:
+	case IXGBE_PCIDEVCTRL2_4_8s:
+		/* For now we cap the upper limit on delay to 2 seconds
+		 * as we end up going up to 34 seconds of delay in worst
+		 * case timeout value.
+		 */
+	case IXGBE_PCIDEVCTRL2_1_2s:
+		return 2000000ul;	/* 2.0 s */
+	case IXGBE_PCIDEVCTRL2_260_520ms:
+		return 520000ul;	/* 520 ms */
+	case IXGBE_PCIDEVCTRL2_65_130ms:
+		return 130000ul;	/* 130 ms */
+	case IXGBE_PCIDEVCTRL2_16_32ms:
+		return 32000ul;		/* 32 ms */
+	case IXGBE_PCIDEVCTRL2_1_2ms:
+		return 2000ul;		/* 2 ms */
+	case IXGBE_PCIDEVCTRL2_50_100us:
+		return 100ul;		/* 100 us */
+	case IXGBE_PCIDEVCTRL2_16_32ms_def:
+		return 32000ul;		/* 32 ms */
+	default:
+		break;
+	}
+
+	/* We shouldn't need to hit this path, but just in case default as
+	 * though completion timeout is not supported and support 32ms.
+	 */
+	return 32000ul;
+}
+
+void ixgbe_disable_rx(struct ixgbe_adapter *adapter)
+{
+	unsigned long wait_delay, delay_interval;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i, wait_loop;
+	u32 rxdctl;
+
+	/* disable receives */
+	hw->mac.ops.disable_rx(hw);
+
+	if (ixgbe_removed(hw->hw_addr))
+		return;
+
+	/* disable all enabled Rx queues */
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct ixgbe_ring *ring = adapter->rx_ring[i];
+		u8 reg_idx = ring->reg_idx;
+
+		rxdctl = IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+		rxdctl &= ~IXGBE_RXDCTL_ENABLE;
+		rxdctl |= IXGBE_RXDCTL_SWFLSH;
+
+		/* write value back with RXDCTL.ENABLE bit cleared */
+		IXGBE_WRITE_REG(hw, IXGBE_RXDCTL(reg_idx), rxdctl);
+	}
+
+	/* RXDCTL.EN may not change on 82598 if link is down, so skip it */
+	if (hw->mac.type == ixgbe_mac_82598EB &&
+	    !(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
+		return;
+
+	/* Determine our minimum delay interval. We will increase this value
+	 * with each subsequent test. This way if the device returns quickly
+	 * we should spend as little time as possible waiting, however as
+	 * the time increases we will wait for larger periods of time.
+	 *
+	 * The trick here is that we increase the interval using the
+	 * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result
+	 * of that wait is that it totals up to 100x whatever interval we
+	 * choose. Since our minimum wait is 100us we can just divide the
+	 * total timeout by 100 to get our minimum delay interval.
+	 */
+	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+	wait_loop = IXGBE_MAX_RX_DESC_POLL;
+	wait_delay = delay_interval;
+
+	while (wait_loop--) {
+		usleep_range(wait_delay, wait_delay + 10);
+		wait_delay += delay_interval * 2;
+		rxdctl = 0;
+
+		/* OR together the reading of all the active RXDCTL registers,
+		 * and then test the result. We need the disable to complete
+		 * before we start freeing the memory and invalidating the
+		 * DMA mappings.
+		 */
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			struct ixgbe_ring *ring = adapter->rx_ring[i];
+			u8 reg_idx = ring->reg_idx;
+
+			rxdctl |= IXGBE_READ_REG(hw, IXGBE_RXDCTL(reg_idx));
+		}
+
+		if (!(rxdctl & IXGBE_RXDCTL_ENABLE))
+			return;
+	}
+
+	e_err(drv,
+	      "RXDCTL.ENABLE for one or more queues not cleared within the polling period\n");
+}
+
+void ixgbe_disable_tx(struct ixgbe_adapter *adapter)
+{
+	unsigned long wait_delay, delay_interval;
+	struct ixgbe_hw *hw = &adapter->hw;
+	int i, wait_loop;
+	u32 txdctl;
+
+	if (ixgbe_removed(hw->hw_addr))
+		return;
+
+	/* disable all enabled Tx queues */
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		struct ixgbe_ring *ring = adapter->tx_ring[i];
+		u8 reg_idx = ring->reg_idx;
+
+		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+	}
+
+	/* disable all enabled XDP Tx queues */
+	for (i = 0; i < adapter->num_xdp_queues; i++) {
+		struct ixgbe_ring *ring = adapter->xdp_ring[i];
+		u8 reg_idx = ring->reg_idx;
+
+		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
+	}
+
+	/* If the link is not up there shouldn't be much in the way of
+	 * pending transactions. Those that are left will be flushed out
+	 * when the reset logic goes through the flush sequence to clean out
+	 * the pending Tx transactions.
+	 */
+	if (!(IXGBE_READ_REG(hw, IXGBE_LINKS) & IXGBE_LINKS_UP))
+		goto dma_engine_disable;
+
+	/* Determine our minimum delay interval. We will increase this value
+	 * with each subsequent test. This way if the device returns quickly
+	 * we should spend as little time as possible waiting, however as
+	 * the time increases we will wait for larger periods of time.
+	 *
+	 * The trick here is that we increase the interval using the
+	 * following pattern: 1x 3x 5x 7x 9x 11x 13x 15x 17x 19x. The result
+	 * of that wait is that it totals up to 100x whatever interval we
+	 * choose. Since our minimum wait is 100us we can just divide the
+	 * total timeout by 100 to get our minimum delay interval.
+	 */
+	delay_interval = ixgbe_get_completion_timeout(adapter) / 100;
+
+	wait_loop = IXGBE_MAX_RX_DESC_POLL;
+	wait_delay = delay_interval;
+
+	while (wait_loop--) {
+		usleep_range(wait_delay, wait_delay + 10);
+		wait_delay += delay_interval * 2;
+		txdctl = 0;
+
+		/* OR together the reading of all the active TXDCTL registers,
+		 * and then test the result. We need the disable to complete
+		 * before we start freeing the memory and invalidating the
+		 * DMA mappings.
+		 */
+		for (i = 0; i < adapter->num_tx_queues; i++) {
+			struct ixgbe_ring *ring = adapter->tx_ring[i];
+			u8 reg_idx = ring->reg_idx;
+
+			txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
+		}
+		for (i = 0; i < adapter->num_xdp_queues; i++) {
+			struct ixgbe_ring *ring = adapter->xdp_ring[i];
+			u8 reg_idx = ring->reg_idx;
+
+			txdctl |= IXGBE_READ_REG(hw, IXGBE_TXDCTL(reg_idx));
+		}
+
+		if (!(txdctl & IXGBE_TXDCTL_ENABLE))
+			goto dma_engine_disable;
+	}
+
+	e_err(drv,
+	      "TXDCTL.ENABLE for one or more queues not cleared within the polling period\n");
+
+dma_engine_disable:
+	/* Disable the Tx DMA engine on 82599 and later MAC */
+	switch (hw->mac.type) {
+	case ixgbe_mac_82599EB:
+	case ixgbe_mac_X540:
+	case ixgbe_mac_X550:
+	case ixgbe_mac_X550EM_x:
+	case ixgbe_mac_x550em_a:
+		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
+				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
+				 ~IXGBE_DMATXCTL_TE));
+		/* fall through */
+	default:
+		break;
+	}
+}
+
 void ixgbe_reset(struct ixgbe_adapter *adapter)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
@@ -5821,13 +5999,8 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	netif_carrier_off(netdev);
 	netif_tx_disable(netdev);
 
-	/* disable receives */
-	hw->mac.ops.disable_rx(hw);
-
-	/* disable all enabled rx queues */
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		/* this call also flushes the previous write */
-		ixgbe_disable_rx_queue(adapter, adapter->rx_ring[i]);
+	/* Disable Rx */
+	ixgbe_disable_rx(adapter);
 
 	/* synchronize_sched() needed for pending XDP buffers to drain */
 	if (adapter->xdp_ring[0])
@@ -5859,30 +6032,7 @@ void ixgbe_down(struct ixgbe_adapter *adapter)
 	}
 
 	/* disable transmits in the hardware now that interrupts are off */
-	for (i = 0; i < adapter->num_tx_queues; i++) {
-		u8 reg_idx = adapter->tx_ring[i]->reg_idx;
-		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
-	}
-	for (i = 0; i < adapter->num_xdp_queues; i++) {
-		u8 reg_idx = adapter->xdp_ring[i]->reg_idx;
-
-		IXGBE_WRITE_REG(hw, IXGBE_TXDCTL(reg_idx), IXGBE_TXDCTL_SWFLSH);
-	}
-
-	/* Disable the Tx DMA engine on 82599 and later MAC */
-	switch (hw->mac.type) {
-	case ixgbe_mac_82599EB:
-	case ixgbe_mac_X540:
-	case ixgbe_mac_X550:
-	case ixgbe_mac_X550EM_x:
-	case ixgbe_mac_x550em_a:
-		IXGBE_WRITE_REG(hw, IXGBE_DMATXCTL,
-				(IXGBE_READ_REG(hw, IXGBE_DMATXCTL) &
-				 ~IXGBE_DMATXCTL_TE));
-		break;
-	default:
-		break;
-	}
+	ixgbe_disable_tx(adapter);
 
 	if (!pci_channel_offline(adapter->pdev))
 		ixgbe_reset(adapter);
-- 
cgit v1.2.3


From 4cae99d9b5305ab8cccc839fccceb81ec9e5abda Mon Sep 17 00:00:00 2001
From: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Date: Wed, 25 Jul 2018 15:15:56 -0500
Subject: ALSA: memalloc: declare snd_sgbuf_aligned_pages() unconditionally

Make this helper inline function available for all platforms. This
helps solve 0-day compilation issues when CONFIG_SND_DMA_SGBUF is not
defined.

Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/memalloc.h | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index 9c3db3dce32b..c669900e6cbe 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -67,6 +67,14 @@ struct snd_dma_buffer {
 	void *private_data;	/* private for allocator; don't touch */
 };
 
+/*
+ * return the pages matching with the given byte size
+ */
+static inline unsigned int snd_sgbuf_aligned_pages(size_t size)
+{
+	return (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
+}
+
 #ifdef CONFIG_SND_DMA_SGBUF
 /*
  * Scatter-Gather generic device pages
@@ -90,14 +98,6 @@ struct snd_sg_buf {
 	struct device *dev;
 };
 
-/*
- * return the pages matching with the given byte size
- */
-static inline unsigned int snd_sgbuf_aligned_pages(size_t size)
-{
-	return (size + PAGE_SIZE - 1) >> PAGE_SHIFT;
-}
-
 /*
  * return the physical address at the corresponding offset
  */
-- 
cgit v1.2.3


From 0b62834e73e332fea76a340d62aaf50c732b17e0 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:17:17 +0200
Subject: ALSA: pcm: Add snd_mask_set_format() helper for standard usages

Many drivers calling snd_mask_set() need to do ugly cast with __force
for shutting up the sparse warnings.  Actually almost all of them are
about setting the format, so it's far better to provide a common
helper snd_mask_set_format() to pass SNDRV_PCM_FORMAT_* directly
without the cast.

There are a few other calls of snd_mask_set(), but they are in the PCM
core code, so we leave them for now.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/pcm_params.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/sound/pcm_params.h b/include/sound/pcm_params.h
index c704357775fc..2dd37cada7c0 100644
--- a/include/sound/pcm_params.h
+++ b/include/sound/pcm_params.h
@@ -87,6 +87,13 @@ static inline void snd_mask_set(struct snd_mask *mask, unsigned int val)
 	mask->bits[MASK_OFS(val)] |= MASK_BIT(val);
 }
 
+/* Most of drivers need only this one */
+static inline void snd_mask_set_format(struct snd_mask *mask,
+				       snd_pcm_format_t format)
+{
+	snd_mask_set(mask, (__force unsigned int)format);
+}
+
 static inline void snd_mask_reset(struct snd_mask *mask, unsigned int val)
 {
 	mask->bits[MASK_OFS(val)] &= ~MASK_BIT(val);
@@ -369,8 +376,7 @@ static inline int params_physical_width(const struct snd_pcm_hw_params *p)
 static inline void
 params_set_format(struct snd_pcm_hw_params *p, snd_pcm_format_t fmt)
 {
-	snd_mask_set(hw_param_mask(p, SNDRV_PCM_HW_PARAM_FORMAT),
-		(__force int)fmt);
+	snd_mask_set_format(hw_param_mask(p, SNDRV_PCM_HW_PARAM_FORMAT), fmt);
 }
 
 #endif /* __SOUND_PCM_PARAMS_H */
-- 
cgit v1.2.3


From 533a9274850b041b32fbe6d1df58a5c5b0b9e652 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:17:18 +0200
Subject: ASoC: doc: Replace open code with params_set_format()

The example code in dpcm.rst contains an open code calling
snd_mask_set(), and this can be better represented with
params_set_format() instead.  This automatically fixes the sparse
warning about snd_pcm_format_t handling, too.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/sound/soc/dpcm.rst | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/Documentation/sound/soc/dpcm.rst b/Documentation/sound/soc/dpcm.rst
index 395e5a516282..fe61e02277f8 100644
--- a/Documentation/sound/soc/dpcm.rst
+++ b/Documentation/sound/soc/dpcm.rst
@@ -254,9 +254,7 @@ configuration.
 	channels->min = channels->max = 2;
 
 	/* set DAI0 to 16 bit */
-	snd_mask_set(&params->masks[SNDRV_PCM_HW_PARAM_FORMAT -
-				    SNDRV_PCM_HW_PARAM_FIRST_MASK],
-				    SNDRV_PCM_FORMAT_S16_LE);
+	params_set_format(params, SNDRV_PCM_FORMAT_S16_LE);
 	return 0;
   }
 
-- 
cgit v1.2.3


From b5453e8ca311fdb6003c6583ad101d2b9131b994 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:17:19 +0200
Subject: ASoC: intel: Fix snd_pcm_format_t handling

As sparse warns, the PCM format type can't be dealt as integer as
found in Intel SST driver codes.

Fix them in the following two ways:

- The open code with snd_mask_set() and params->masks reference is
  replaced with params_set_format()

- The rest codes with snd_mask_set(fmt, SNDRV_PCM_FORMAT_XXX) are
  replaced with the new helper, snd_mask_set_format().

Reported-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bdw-rt5677.c                 | 4 +---
 sound/soc/intel/boards/bxt_da7219_max98357a.c       | 2 +-
 sound/soc/intel/boards/bxt_rt298.c                  | 2 +-
 sound/soc/intel/boards/kbl_da7219_max98357a.c       | 2 +-
 sound/soc/intel/boards/kbl_rt5663_max98927.c        | 4 ++--
 sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c | 4 ++--
 sound/soc/intel/boards/skl_nau88l25_max98357a.c     | 2 +-
 sound/soc/intel/boards/skl_nau88l25_ssm4567.c       | 2 +-
 sound/soc/intel/boards/skl_rt286.c                  | 2 +-
 9 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/sound/soc/intel/boards/bdw-rt5677.c b/sound/soc/intel/boards/bdw-rt5677.c
index 6ea360f33575..efcfd906c856 100644
--- a/sound/soc/intel/boards/bdw-rt5677.c
+++ b/sound/soc/intel/boards/bdw-rt5677.c
@@ -154,9 +154,7 @@ static int broadwell_ssp0_fixup(struct snd_soc_pcm_runtime *rtd,
 	channels->min = channels->max = 2;
 
 	/* set SSP0 to 16 bit */
-	snd_mask_set(&params->masks[SNDRV_PCM_HW_PARAM_FORMAT -
-				    SNDRV_PCM_HW_PARAM_FIRST_MASK],
-				    SNDRV_PCM_FORMAT_S16_LE);
+	params_set_format(params, SNDRV_PCM_FORMAT_S16_LE);
 	return 0;
 }
 
diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index 3aba5bcf806a..be6e4b40bf03 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -160,7 +160,7 @@ static int broxton_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
index b68c289558a8..27308337ab12 100644
--- a/sound/soc/intel/boards/bxt_rt298.c
+++ b/sound/soc/intel/boards/bxt_rt298.c
@@ -221,7 +221,7 @@ static int broxton_ssp5_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP5 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/kbl_da7219_max98357a.c b/sound/soc/intel/boards/kbl_da7219_max98357a.c
index 7961f1fd18bd..38f6ab74709d 100644
--- a/sound/soc/intel/boards/kbl_da7219_max98357a.c
+++ b/sound/soc/intel/boards/kbl_da7219_max98357a.c
@@ -152,7 +152,7 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/kbl_rt5663_max98927.c b/sound/soc/intel/boards/kbl_rt5663_max98927.c
index 3a61252fe450..21a6490746a6 100644
--- a/sound/soc/intel/boards/kbl_rt5663_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_max98927.c
@@ -434,14 +434,14 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 		rate->min = rate->max = 48000;
 		channels->min = channels->max = 2;
 		snd_mask_none(fmt);
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	}
 	/*
 	 * The speaker on the SSP0 supports S16_LE and not S24_LE.
 	 * thus changing the mask here
 	 */
 	if (!strcmp(be_dai_link->name, "SSP0-Codec"))
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S16_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
index 92f5fb2ae0a3..a892b37eab7c 100644
--- a/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
+++ b/sound/soc/intel/boards/kbl_rt5663_rt5514_max98927.c
@@ -307,7 +307,7 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 		rate->min = rate->max = 48000;
 		channels->min = channels->max = 2;
 		snd_mask_none(fmt);
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	} else if (!strcmp(fe_dai_link->name, "Kbl Audio DMIC cap")) {
 		if (params_channels(params) == 2 ||
 				DMIC_CH(dmic_constraints) == 2)
@@ -320,7 +320,7 @@ static int kabylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 	 * thus changing the mask here
 	 */
 	if (!strcmp(be_dai_link->name, "SSP0-Codec"))
-		snd_mask_set(fmt, SNDRV_PCM_FORMAT_S16_LE);
+		snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/skl_nau88l25_max98357a.c b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
index 3ff6646cfa21..d31482b8c9bb 100644
--- a/sound/soc/intel/boards/skl_nau88l25_max98357a.c
+++ b/sound/soc/intel/boards/skl_nau88l25_max98357a.c
@@ -157,7 +157,7 @@ static int skylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP0 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 
 	return 0;
 }
diff --git a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
index b0610bba3cfa..e877bb60beb1 100644
--- a/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
+++ b/sound/soc/intel/boards/skl_nau88l25_ssm4567.c
@@ -346,7 +346,7 @@ static int skylake_ssp_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP0 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	return 0;
 }
 
diff --git a/sound/soc/intel/boards/skl_rt286.c b/sound/soc/intel/boards/skl_rt286.c
index 38a1495c29cf..0e1818dd4cc6 100644
--- a/sound/soc/intel/boards/skl_rt286.c
+++ b/sound/soc/intel/boards/skl_rt286.c
@@ -229,7 +229,7 @@ static int skylake_ssp0_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	/* set SSP0 to 24 bit */
 	snd_mask_none(fmt);
-	snd_mask_set(fmt, SNDRV_PCM_FORMAT_S24_LE);
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S24_LE);
 	return 0;
 }
 
-- 
cgit v1.2.3


From ebc22af0c9268dc4032326c20b02f2f227203330 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:17:20 +0200
Subject: ASoC: fsl: Use snd_mask_set_format()

Use the new helper function snd_mask_set_format() for avoiding the
ugly cast with __force prefix.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl-asoc-card.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/fsl/fsl-asoc-card.c b/sound/soc/fsl/fsl-asoc-card.c
index 07808c6d5461..44433b20435c 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -195,7 +195,7 @@ static int be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 
 	mask = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
 	snd_mask_none(mask);
-	snd_mask_set(mask, (__force int)priv->asrc_format);
+	snd_mask_set_format(mask, priv->asrc_format);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 79b8a50813a80ac15fdcdc96674098dee15eaaf5 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:17:21 +0200
Subject: ASoC: pcm186x: Declare PCM format with snd_pcm_format_t

The PCM format type is with __bitwise, so we should use the dedicated
snd_pcm_format_t instead of int.

This fixes the sparse warning like:
  sound/soc/codecs/pcm186x.c:268:44: warning: incorrect type in initializer (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/pcm186x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/pcm186x.c b/sound/soc/codecs/pcm186x.c
index 88fde70b1e9e..690c26e7389e 100644
--- a/sound/soc/codecs/pcm186x.c
+++ b/sound/soc/codecs/pcm186x.c
@@ -265,7 +265,7 @@ static int pcm186x_hw_params(struct snd_pcm_substream *substream,
 	struct snd_soc_component *component = dai->component;
 	struct pcm186x_priv *priv = snd_soc_component_get_drvdata(component);
 	unsigned int rate = params_rate(params);
-	unsigned int format = params_format(params);
+	snd_pcm_format_t format = params_format(params);
 	unsigned int width = params_width(params);
 	unsigned int channels = params_channels(params);
 	unsigned int div_lrck;
-- 
cgit v1.2.3


From 8adf3df4156345f1edcdfa8c7f7beeb0de351ce2 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:17:22 +0200
Subject: ASoC: dmaengine: Use standard pcm_format_to_bits() macro

The conversion from PCM format type to bits needs an explicit cast,
and it'll be uglier.  Since we have a standard macro for that, let's
use it instead.

This patch fixes the sparse warning:
  sound/soc/soc-generic-dmaengine-pcm.c:200:63: warning: restricted snd_pcm_format_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-generic-dmaengine-pcm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/soc-generic-dmaengine-pcm.c b/sound/soc/soc-generic-dmaengine-pcm.c
index 120f7b39e256..52fd7af952a5 100644
--- a/sound/soc/soc-generic-dmaengine-pcm.c
+++ b/sound/soc/soc-generic-dmaengine-pcm.c
@@ -188,7 +188,7 @@ static int dmaengine_pcm_set_runtime_hwparams(struct snd_pcm_substream *substrea
 			case 32:
 			case 64:
 				if (addr_widths & (1 << (bits / 8)))
-					hw.formats |= (1LL << i);
+					hw.formats |= pcm_format_to_bits(i);
 				break;
 			default:
 				/* Unsupported types */
-- 
cgit v1.2.3


From 5a967512bb812d7a4b7e9f3930f49d6d88533dc3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 26 Jul 2018 11:38:34 +0200
Subject: selftests: forwarding: add tests for TC chain get and dump operations

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/tc_chains.sh | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh
index 031e322e28b3..2934fb5ed2a2 100755
--- a/tools/testing/selftests/net/forwarding/tc_chains.sh
+++ b/tools/testing/selftests/net/forwarding/tc_chains.sh
@@ -88,9 +88,30 @@ create_destroy_chain()
 	tc chain add dev $h2 ingress
 	check_err $? "Failed to create default chain"
 
+	output="$(tc -j chain get dev $h2 ingress)"
+	check_err $? "Failed to get default chain"
+
+	echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null
+	check_err $? "Unexpected output for default chain"
+
 	tc chain add dev $h2 ingress chain 1
 	check_err $? "Failed to create chain 1"
 
+	output="$(tc -j chain get dev $h2 ingress chain 1)"
+	check_err $? "Failed to get chain 1"
+
+	echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null
+	check_err $? "Unexpected output for chain 1"
+
+	output="$(tc -j chain show dev $h2 ingress)"
+	check_err $? "Failed to dump chains"
+
+	echo $output | jq -e ".[] | select(.chain == 0)" &> /dev/null
+	check_err $? "Can't find default chain in dump"
+
+	echo $output | jq -e ".[] | select(.chain == 1)" &> /dev/null
+	check_err $? "Can't find chain 1 in dump"
+
 	tc chain del dev $h2 ingress
 	check_err $? "Failed to destroy default chain"
 
-- 
cgit v1.2.3


From eb91f42ef074467e0c441a9789dc1fc0519a25ad Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Thu, 26 Jul 2018 11:53:58 +0200
Subject: selftests/net: add tls to .gitignore

Add the tls binary to .gitignore

Fixes: 7f657d5bf507 ("selftests: tls: add selftests for TLS sockets")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 1a0ac3a29ec5..78b24cf76f40 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -13,3 +13,4 @@ udpgso
 udpgso_bench_rx
 udpgso_bench_tx
 tcp_inq
+tls
-- 
cgit v1.2.3


From 336a443bd9ddca319b99b5375e7756724a5545dd Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 26 Jul 2018 21:19:58 +0800
Subject: net: hns: Make many functions static

Fixes the following sparse warning:

drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:73:20: warning: symbol 'hns_ae_get_handle' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:332:6: warning: symbol 'hns_ae_stop' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:360:6: warning: symbol 'hns_ae_toggle_ring_irq' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:580:6: warning: symbol 'hns_ae_update_stats' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:663:6: warning: symbol 'hns_ae_get_stats' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:695:6: warning: symbol 'hns_ae_get_strings' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:728:5: warning: symbol 'hns_ae_get_sset_count' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:774:6: warning: symbol 'hns_ae_update_led_status' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:786:5: warning: symbol 'hns_ae_cpld_set_led_id' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:798:6: warning: symbol 'hns_ae_get_regs' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c:823:5: warning: symbol 'hns_ae_get_regs_len' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c:342:6: warning: symbol 'hns_gmac_update_stats' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c:934:12: warning: symbol 'hns_mac_get_vaddr' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c:953:5: warning: symbol 'hns_mac_get_cfg' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c:343:6: warning: symbol 'hns_dsaf_srst_chns' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c:366:1: warning: symbol 'hns_dsaf_srst_chns_acpi' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c:373:6: warning: symbol 'hns_dsaf_roce_srst' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c:387:6: warning: symbol 'hns_dsaf_roce_srst_acpi' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c:571:5: warning: symbol 'hns_mac_get_sfp_prsnt' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c:589:5: warning: symbol 'hns_mac_get_sfp_prsnt_acpi' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:31:12: warning: symbol 'g_dsaf_mode_match' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:45:5: warning: symbol 'hns_dsaf_get_cfg' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:962:6: warning: symbol 'hns_dsaf_tcam_addr_get' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:2087:6: warning: symbol 'hns_dsaf_port_work_rate_cfg' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:2837:5: warning: symbol 'hns_dsaf_roce_reset' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c:76:5: warning: symbol 'hns_ppe_common_get_cfg' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c:107:6: warning: symbol 'hns_ppe_common_free_cfg' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c:340:6: warning: symbol 'hns_ppe_uninit_ex' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c:708:5: warning: symbol 'hns_rcb_get_ring_num' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c:744:14: warning: symbol 'hns_rcb_common_get_vaddr' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c:314:6: warning: symbol 'hns_xgmac_update_stats' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_enet.c:1303:6: warning: symbol 'hns_nic_update_stats' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_enet.c:1585:6: warning: symbol 'hns_nic_poll_controller' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_enet.c:1938:6: warning: symbol 'hns_set_multicast_list' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_enet.c:1960:6: warning: symbol 'hns_nic_set_rx_mode' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:661:6: warning: symbol 'hns_get_ringparam' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:811:6: warning: symbol 'hns_get_channels' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:828:6: warning: symbol 'hns_get_ethtool_stats' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:886:6: warning: symbol 'hns_get_strings' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:976:5: warning: symbol 'hns_get_sset_count' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:1010:5: warning: symbol 'hns_phy_led_set' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:1032:5: warning: symbol 'hns_set_phys_id' was not declared. Should it be static?
drivers/net/ethernet/hisilicon/hns/hns_ethtool.c:1106:6: warning: symbol 'hns_get_regs' was not declared. Should it be static?

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c  | 30 +++++++++++-----------
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c |  2 +-
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c  |  8 +++---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c | 14 +++++-----
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c | 13 +++++-----
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c  |  7 ++---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c  |  4 +--
 .../net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c    |  2 +-
 drivers/net/ethernet/hisilicon/hns/hns_enet.c      |  8 +++---
 drivers/net/ethernet/hisilicon/hns/hns_ethtool.c   | 24 +++++++++--------
 10 files changed, 60 insertions(+), 52 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
index bd68379d2bea..e6aad30e7e69 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ae_adapt.c
@@ -70,8 +70,8 @@ static struct ring_pair_cb *hns_ae_get_ring_pair(struct hnae_queue *q)
 	return container_of(q, struct ring_pair_cb, q);
 }
 
-struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev,
-				      u32 port_id)
+static struct hnae_handle *hns_ae_get_handle(struct hnae_ae_dev *dev,
+					     u32 port_id)
 {
 	int vfnum_per_port;
 	int qnum_per_vf;
@@ -329,7 +329,7 @@ static int hns_ae_start(struct hnae_handle *handle)
 	return 0;
 }
 
-void hns_ae_stop(struct hnae_handle *handle)
+static void hns_ae_stop(struct hnae_handle *handle)
 {
 	struct hns_mac_cb *mac_cb = hns_get_mac_cb(handle);
 
@@ -357,7 +357,7 @@ static void hns_ae_reset(struct hnae_handle *handle)
 	}
 }
 
-void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask)
+static void hns_ae_toggle_ring_irq(struct hnae_ring *ring, u32 mask)
 {
 	u32 flag;
 
@@ -577,8 +577,8 @@ static void hns_ae_get_coalesce_range(struct hnae_handle *handle,
 	*rx_usecs_high  = HNS_RCB_RX_USECS_HIGH;
 }
 
-void hns_ae_update_stats(struct hnae_handle *handle,
-			 struct net_device_stats *net_stats)
+static void hns_ae_update_stats(struct hnae_handle *handle,
+				struct net_device_stats *net_stats)
 {
 	int port;
 	int idx;
@@ -660,7 +660,7 @@ void hns_ae_update_stats(struct hnae_handle *handle,
 	net_stats->multicast = mac_cb->hw_stats.rx_mc_pkts;
 }
 
-void hns_ae_get_stats(struct hnae_handle *handle, u64 *data)
+static void hns_ae_get_stats(struct hnae_handle *handle, u64 *data)
 {
 	int idx;
 	struct hns_mac_cb *mac_cb;
@@ -692,8 +692,8 @@ void hns_ae_get_stats(struct hnae_handle *handle, u64 *data)
 		hns_dsaf_get_stats(vf_cb->dsaf_dev, p, vf_cb->port_index);
 }
 
-void hns_ae_get_strings(struct hnae_handle *handle,
-			u32 stringset, u8 *data)
+static void hns_ae_get_strings(struct hnae_handle *handle,
+			       u32 stringset, u8 *data)
 {
 	int port;
 	int idx;
@@ -725,7 +725,7 @@ void hns_ae_get_strings(struct hnae_handle *handle,
 		hns_dsaf_get_strings(stringset, p, port, dsaf_dev);
 }
 
-int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset)
+static int hns_ae_get_sset_count(struct hnae_handle *handle, int stringset)
 {
 	u32 sset_count = 0;
 	struct hns_mac_cb *mac_cb;
@@ -771,7 +771,7 @@ static int hns_ae_config_loopback(struct hnae_handle *handle,
 	return ret;
 }
 
-void hns_ae_update_led_status(struct hnae_handle *handle)
+static void hns_ae_update_led_status(struct hnae_handle *handle)
 {
 	struct hns_mac_cb *mac_cb;
 
@@ -783,8 +783,8 @@ void hns_ae_update_led_status(struct hnae_handle *handle)
 	hns_set_led_opt(mac_cb);
 }
 
-int hns_ae_cpld_set_led_id(struct hnae_handle *handle,
-			   enum hnae_led_state status)
+static int hns_ae_cpld_set_led_id(struct hnae_handle *handle,
+				  enum hnae_led_state status)
 {
 	struct hns_mac_cb *mac_cb;
 
@@ -795,7 +795,7 @@ int hns_ae_cpld_set_led_id(struct hnae_handle *handle,
 	return hns_cpld_led_set_id(mac_cb, status);
 }
 
-void hns_ae_get_regs(struct hnae_handle *handle, void *data)
+static void hns_ae_get_regs(struct hnae_handle *handle, void *data)
 {
 	u32 *p = data;
 	int i;
@@ -820,7 +820,7 @@ void hns_ae_get_regs(struct hnae_handle *handle, void *data)
 		hns_dsaf_get_regs(vf_cb->dsaf_dev, vf_cb->port_index, p);
 }
 
-int hns_ae_get_regs_len(struct hnae_handle *handle)
+static int hns_ae_get_regs_len(struct hnae_handle *handle)
 {
 	u32 total_num;
 	struct hnae_vf_cb *vf_cb = hns_ae_get_vf_cb(handle);
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
index 74bd260ca02a..5488c6e89f21 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_gmac.c
@@ -339,7 +339,7 @@ static void hns_gmac_init(void *mac_drv)
 			   GMAC_TX_WATER_LINE_SHIFT, 8);
 }
 
-void hns_gmac_update_stats(void *mac_drv)
+static void hns_gmac_update_stats(void *mac_drv)
 {
 	struct mac_hw_stats *hw_stats = NULL;
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 9dcc5765f11f..6e5107d428c7 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -931,8 +931,9 @@ static int hns_mac_get_mode(phy_interface_t phy_if)
 	}
 }
 
-u8 __iomem *hns_mac_get_vaddr(struct dsaf_device *dsaf_dev,
-			      struct hns_mac_cb *mac_cb, u32 mac_mode_idx)
+static u8 __iomem *
+hns_mac_get_vaddr(struct dsaf_device *dsaf_dev,
+		  struct hns_mac_cb *mac_cb, u32 mac_mode_idx)
 {
 	u8 __iomem *base = dsaf_dev->io_base;
 	int mac_id = mac_cb->mac_id;
@@ -950,7 +951,8 @@ u8 __iomem *hns_mac_get_vaddr(struct dsaf_device *dsaf_dev,
  * @mac_cb: mac control block
  * return 0 - success , negative --fail
  */
-int hns_mac_get_cfg(struct dsaf_device *dsaf_dev, struct hns_mac_cb *mac_cb)
+static int
+hns_mac_get_cfg(struct dsaf_device *dsaf_dev, struct hns_mac_cb *mac_cb)
 {
 	int ret;
 	u32 mac_mode_idx;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 0ce07f6eb1e6..7afc67510569 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -28,7 +28,7 @@
 #include "hns_dsaf_rcb.h"
 #include "hns_dsaf_misc.h"
 
-const char *g_dsaf_mode_match[DSAF_MODE_MAX] = {
+const static char *g_dsaf_mode_match[DSAF_MODE_MAX] = {
 	[DSAF_MODE_DISABLE_2PORT_64VM] = "2port-64vf",
 	[DSAF_MODE_DISABLE_6PORT_0VM] = "6port-16rss",
 	[DSAF_MODE_DISABLE_6PORT_16VM] = "6port-16vf",
@@ -42,7 +42,7 @@ static const struct acpi_device_id hns_dsaf_acpi_match[] = {
 };
 MODULE_DEVICE_TABLE(acpi, hns_dsaf_acpi_match);
 
-int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
+static int hns_dsaf_get_cfg(struct dsaf_device *dsaf_dev)
 {
 	int ret, i;
 	u32 desc_num;
@@ -959,7 +959,8 @@ static void hns_dsaf_tcam_mc_invld(struct dsaf_device *dsaf_dev, u32 address)
 	spin_unlock_bh(&dsaf_dev->tcam_lock);
 }
 
-void hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr)
+static void
+hns_dsaf_tcam_addr_get(struct dsaf_drv_tbl_tcam_key *mac_key, u8 *addr)
 {
 	addr[0] = mac_key->high.bits.mac_0;
 	addr[1] = mac_key->high.bits.mac_1;
@@ -2084,8 +2085,9 @@ static void hns_dsaf_pfc_unit_cnt(struct dsaf_device *dsaf_dev, int  mac_id,
  * @dsaf_id: dsa fabric id
  * @xge_ge_work_mode
  */
-void hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id,
-				 enum dsaf_port_rate_mode rate_mode)
+static void
+hns_dsaf_port_work_rate_cfg(struct dsaf_device *dsaf_dev, int mac_id,
+			    enum dsaf_port_rate_mode rate_mode)
 {
 	u32 port_work_mode;
 
@@ -2834,7 +2836,7 @@ module_platform_driver(g_dsaf_driver);
  * @enable: false - request reset , true - drop reset
  * retuen 0 - success , negative -fail
  */
-int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
+static int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 {
 	struct dsaf_device *dsaf_dev;
 	struct platform_device *pdev;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
index acf29633ec79..16294cd3c954 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_misc.c
@@ -340,7 +340,8 @@ static void hns_dsaf_xge_srst_by_port_acpi(struct dsaf_device *dsaf_dev,
  * bit18-19 for com/dfx
  * @enable: false - request reset , true - drop reset
  */
-void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
+static void
+hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
 {
 	u32 reg_addr;
 
@@ -362,7 +363,7 @@ void hns_dsaf_srst_chns(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
  * bit18-19 for com/dfx
  * @enable: false - request reset , true - drop reset
  */
-void
+static void
 hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
 {
 	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
@@ -370,7 +371,7 @@ hns_dsaf_srst_chns_acpi(struct dsaf_device *dsaf_dev, u32 msk, bool dereset)
 				   msk, dereset);
 }
 
-void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset)
+static void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset)
 {
 	if (!dereset) {
 		dsaf_write_sub(dsaf_dev, DSAF_SUB_SC_ROCEE_RESET_REQ_REG, 1);
@@ -384,7 +385,7 @@ void hns_dsaf_roce_srst(struct dsaf_device *dsaf_dev, bool dereset)
 	}
 }
 
-void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset)
+static void hns_dsaf_roce_srst_acpi(struct dsaf_device *dsaf_dev, bool dereset)
 {
 	hns_dsaf_acpi_srst_by_port(dsaf_dev, HNS_OP_RESET_FUNC,
 				   HNS_ROCE_RESET_FUNC, 0, dereset);
@@ -568,7 +569,7 @@ static phy_interface_t hns_mac_get_phy_if_acpi(struct hns_mac_cb *mac_cb)
 	return phy_if;
 }
 
-int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+static int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 {
 	u32 val = 0;
 	int ret;
@@ -586,7 +587,7 @@ int hns_mac_get_sfp_prsnt(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 	return 0;
 }
 
-int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
+static int hns_mac_get_sfp_prsnt_acpi(struct hns_mac_cb *mac_cb, int *sfp_prsnt)
 {
 	union acpi_object *obj;
 	union acpi_object obj_args, argv4;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 93e71e27401b..1c3db67491a4 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -73,7 +73,7 @@ hns_ppe_common_get_ioaddr(struct ppe_common_cb *ppe_common)
  * comm_index: common index
  * retuen 0 - success , negative --fail
  */
-int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
+static int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
 {
 	struct ppe_common_cb *ppe_common;
 	int ppe_num;
@@ -104,7 +104,8 @@ int hns_ppe_common_get_cfg(struct dsaf_device *dsaf_dev, int comm_index)
 	return 0;
 }
 
-void hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index)
+static void
+hns_ppe_common_free_cfg(struct dsaf_device *dsaf_dev, u32 comm_index)
 {
 	dsaf_dev->ppe_common[comm_index] = NULL;
 }
@@ -337,7 +338,7 @@ static void hns_ppe_uninit_hw(struct hns_ppe_cb *ppe_cb)
 	}
 }
 
-void hns_ppe_uninit_ex(struct ppe_common_cb *ppe_common)
+static void hns_ppe_uninit_ex(struct ppe_common_cb *ppe_common)
 {
 	u32 i;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
index e2e28532e4dc..9d76e2e54f9d 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_rcb.c
@@ -705,7 +705,7 @@ void hns_rcb_get_queue_mode(enum dsaf_mode dsaf_mode, u16 *max_vfn,
 	}
 }
 
-int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
+static int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
 {
 	switch (dsaf_dev->dsaf_mode) {
 	case DSAF_MODE_ENABLE_FIX:
@@ -741,7 +741,7 @@ int hns_rcb_get_ring_num(struct dsaf_device *dsaf_dev)
 	}
 }
 
-void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
+static void __iomem *hns_rcb_common_get_vaddr(struct rcb_common_cb *rcb_common)
 {
 	struct dsaf_device *dsaf_dev = rcb_common->dsaf_dev;
 
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index 51e7e9f5af49..40711af5bd76 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -311,7 +311,7 @@ static void hns_xgmac_config_max_frame_length(void *mac_drv, u16 newval)
 	dsaf_write_dev(drv, XGMAC_MAC_MAX_PKT_SIZE_REG, newval);
 }
 
-void hns_xgmac_update_stats(void *mac_drv)
+static void hns_xgmac_update_stats(void *mac_drv)
 {
 	struct mac_driver *drv = (struct mac_driver *)mac_drv;
 	struct mac_hw_stats *hw_stats = &drv->mac_cb->hw_stats;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
index 948b3e0d18f4..c2ac187ec8fc 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c
@@ -1300,7 +1300,7 @@ static int hns_nic_net_set_mac_address(struct net_device *ndev, void *p)
 	return 0;
 }
 
-void hns_nic_update_stats(struct net_device *netdev)
+static void hns_nic_update_stats(struct net_device *netdev)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1582,7 +1582,7 @@ static int hns_nic_do_ioctl(struct net_device *netdev, struct ifreq *ifr,
 
 /* use only for netconsole to poll with the device without interrupt */
 #ifdef CONFIG_NET_POLL_CONTROLLER
-void hns_nic_poll_controller(struct net_device *ndev)
+static void hns_nic_poll_controller(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	unsigned long flags;
@@ -1935,7 +1935,7 @@ static int hns_nic_uc_unsync(struct net_device *netdev,
  *
  * return void
  */
-void hns_set_multicast_list(struct net_device *ndev)
+static void hns_set_multicast_list(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1957,7 +1957,7 @@ void hns_set_multicast_list(struct net_device *ndev)
 	}
 }
 
-void hns_nic_set_rx_mode(struct net_device *ndev)
+static void hns_nic_set_rx_mode(struct net_device *ndev)
 {
 	struct hns_nic_priv *priv = netdev_priv(ndev);
 	struct hnae_handle *h = priv->ae_handle;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 2e14a3ae1d8b..3957205abb81 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -658,8 +658,8 @@ static void hns_nic_get_drvinfo(struct net_device *net_dev,
  * @dev: net device
  * @param: ethtool parameter
  */
-void hns_get_ringparam(struct net_device *net_dev,
-		       struct ethtool_ringparam *param)
+static void hns_get_ringparam(struct net_device *net_dev,
+			      struct ethtool_ringparam *param)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
@@ -808,7 +808,8 @@ static int hns_set_coalesce(struct net_device *net_dev,
  * @dev: net device
  * @ch: channel info.
  */
-void hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch)
+static void
+hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 
@@ -825,8 +826,8 @@ void hns_get_channels(struct net_device *net_dev, struct ethtool_channels *ch)
  * @stats: statistics info.
  * @data: statistics data.
  */
-void hns_get_ethtool_stats(struct net_device *netdev,
-			   struct ethtool_stats *stats, u64 *data)
+static void hns_get_ethtool_stats(struct net_device *netdev,
+				  struct ethtool_stats *stats, u64 *data)
 {
 	u64 *p = data;
 	struct hns_nic_priv *priv = netdev_priv(netdev);
@@ -883,7 +884,7 @@ void hns_get_ethtool_stats(struct net_device *netdev,
  * @stats: string set ID.
  * @data: objects data.
  */
-void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
+static void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -973,7 +974,7 @@ void hns_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
  *
  * Return string set count.
  */
-int hns_get_sset_count(struct net_device *netdev, int stringset)
+static int hns_get_sset_count(struct net_device *netdev, int stringset)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1007,7 +1008,7 @@ int hns_get_sset_count(struct net_device *netdev, int stringset)
  *
  * Return 0 on success, negative on failure.
  */
-int hns_phy_led_set(struct net_device *netdev, int value)
+static int hns_phy_led_set(struct net_device *netdev, int value)
 {
 	int retval;
 	struct phy_device *phy_dev = netdev->phydev;
@@ -1029,7 +1030,8 @@ int hns_phy_led_set(struct net_device *netdev, int value)
  *
  * Return 0 on success, negative on failure.
  */
-int hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
+static int
+hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
 {
 	struct hns_nic_priv *priv = netdev_priv(netdev);
 	struct hnae_handle *h = priv->ae_handle;
@@ -1103,8 +1105,8 @@ int hns_set_phys_id(struct net_device *netdev, enum ethtool_phys_id_state state)
  * @cmd: ethtool cmd
  * @date: register data
  */
-void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd,
-		  void *data)
+static void hns_get_regs(struct net_device *net_dev, struct ethtool_regs *cmd,
+			 void *data)
 {
 	struct hns_nic_priv *priv = netdev_priv(net_dev);
 	struct hnae_ae_ops *ops;
-- 
cgit v1.2.3


From 02dff7bf81685b6770a082243060e0b5aac348cf Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:07 -0700
Subject: xfs: pull up dfops from xfs_itruncate_extents()

xfs_itruncate_extents[_flags]() uses a local dfops with a
transaction provided by the caller. It uses hacky ->t_dfops
replacement logic to avoid stomping over an already populated
->t_dfops.

The latter never occurs for current callers and the logic itself is
not really appropriate. Clean this up by updating all callers to
initialize a dfops and to use that down in xfs_itruncate_extents().
This more closely resembles the upcoming logic where dfops will be
embedded within the transaction. We can also replace the
xfs_defer_init() in the xfs_itruncate_extents_flags() loop with an
assert. Both dfops and firstblock should be in a valid state
after xfs_defer_finish() and the inode joined to the dfops is fixed
throughout the loop.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_attr_inactive.c | 3 +++
 fs/xfs/xfs_bmap_util.c     | 2 ++
 fs/xfs/xfs_inode.c         | 8 +++-----
 fs/xfs/xfs_iops.c          | 3 +++
 fs/xfs/xfs_qm_syscalls.c   | 3 +++
 5 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index 7ce10055f275..d3055972d3a6 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -26,6 +26,7 @@
 #include "xfs_quota.h"
 #include "xfs_trace.h"
 #include "xfs_dir2.h"
+#include "xfs_defer.h"
 
 /*
  * Look at all the extents for this logical region,
@@ -381,6 +382,7 @@ xfs_attr_inactive(
 {
 	struct xfs_trans	*trans;
 	struct xfs_mount	*mp;
+	struct xfs_defer_ops	dfops;
 	int			lock_mode = XFS_ILOCK_SHARED;
 	int			error = 0;
 
@@ -397,6 +399,7 @@ xfs_attr_inactive(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrinval, 0, 0, 0, &trans);
 	if (error)
 		goto out_destroy_fork;
+	xfs_defer_init(trans, &dfops);
 
 	lock_mode = XFS_ILOCK_EXCL;
 	xfs_ilock(dp, lock_mode);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 1b78c20de7bd..1a4617c74c6a 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -792,6 +792,7 @@ xfs_free_eofblocks(
 	int			nimaps;
 	struct xfs_bmbt_irec	imap;
 	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_defer_ops	dfops;
 
 	/*
 	 * Figure out if there are any blocks beyond the end
@@ -831,6 +832,7 @@ xfs_free_eofblocks(
 			ASSERT(XFS_FORCED_SHUTDOWN(mp));
 			return error;
 		}
+		xfs_defer_init(tp, &dfops);
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, 0);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7b2694d3901a..7d7d7e95fa17 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1541,8 +1541,6 @@ xfs_itruncate_extents_flags(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
-	struct xfs_defer_ops	*odfops = tp->t_dfops;
-	struct xfs_defer_ops	dfops;
 	xfs_fileoff_t		first_unmap_block;
 	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
@@ -1579,7 +1577,7 @@ xfs_itruncate_extents_flags(
 	ASSERT(first_unmap_block < last_block);
 	unmap_len = last_block - first_unmap_block + 1;
 	while (!done) {
-		xfs_defer_init(tp, &dfops);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
 				    XFS_ITRUNC_MAX_EXTENTS, &done);
 		if (error)
@@ -1618,8 +1616,6 @@ xfs_itruncate_extents_flags(
 	trace_xfs_itruncate_extents_end(ip, new_size);
 
 out:
-	/* ->t_dfops points to local stack, don't leak it! */
-	tp->t_dfops = odfops;
 	*tpp = tp;
 	return error;
 out_bmap_cancel:
@@ -1723,6 +1719,7 @@ xfs_inactive_truncate(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
+	struct xfs_defer_ops	dfops;
 	int			error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
@@ -1730,6 +1727,7 @@ xfs_inactive_truncate(
 		ASSERT(XFS_FORCED_SHUTDOWN(mp));
 		return error;
 	}
+	xfs_defer_init(tp, &dfops);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 0fa29f39d658..704b57a8b99e 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -26,6 +26,7 @@
 #include "xfs_dir2.h"
 #include "xfs_trans_space.h"
 #include "xfs_iomap.h"
+#include "xfs_defer.h"
 
 #include <linux/capability.h>
 #include <linux/xattr.h>
@@ -812,6 +813,7 @@ xfs_setattr_size(
 	struct inode		*inode = VFS_I(ip);
 	xfs_off_t		oldsize, newsize;
 	struct xfs_trans	*tp;
+	struct xfs_defer_ops	dfops;
 	int			error;
 	uint			lock_flags = 0;
 	bool			did_zeroing = false;
@@ -915,6 +917,7 @@ xfs_setattr_size(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
 	if (error)
 		return error;
+	xfs_defer_init(tp, &dfops);
 
 	lock_flags |= XFS_ILOCK_EXCL;
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index abc8a21e3a82..df0783303887 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -22,6 +22,7 @@
 #include "xfs_qm.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
+#include "xfs_defer.h"
 
 STATIC int	xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
@@ -213,6 +214,7 @@ xfs_qm_scall_trunc_qfile(
 {
 	struct xfs_inode	*ip;
 	struct xfs_trans	*tp;
+	struct xfs_defer_ops	dfops;
 	int			error;
 
 	if (ino == NULLFSINO)
@@ -229,6 +231,7 @@ xfs_qm_scall_trunc_qfile(
 		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 		goto out_put;
 	}
+	xfs_defer_init(tp, &dfops);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
-- 
cgit v1.2.3


From a61acc3c78df14bb9b7bfefb2cc771fcda15b8fe Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:08 -0700
Subject: xfs: use ->t_dfops in log recovery intent processing

xlog_finish_defer_ops() processes the deferred operations collected
over the entire intent recovery sequence. We can't xfs_defer_init()
here because the dfops is already populated. Attach it manually and
eliminate the last caller of xfs_defer_finish() that doesn't pass
->t_dfops.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log_recover.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index cbac943896f4..3289811eb076 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4854,6 +4854,8 @@ xlog_finish_defer_ops(
 			0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
+	/* dfops is already populated so assign it manually */
+	tp->t_dfops = dfops;
 
 	error = xfs_defer_finish(&tp, dfops);
 	if (error)
-- 
cgit v1.2.3


From dcbd44f79986e55691600b969c14db004d741883 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:08 -0700
Subject: xfs: fix transaction leak on remote attr set/remove failure

The xattr remote value set/remove handlers both clear args.trans in
the error path without having cancelled the transaction. This leaks
the transaction, causes warnings around returning to userspace with
locks held and leads to system lockups or other general problems.

The higher level xfs_attr_[set|remove]() functions already detect
and cancel args.trans when set in the error path. Drop the NULL
assignments from the rmtval handlers and allow the callers to clean
up the transaction correctly.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_remote.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 7841e6255129..829ab20f0cd7 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -558,7 +558,6 @@ xfs_attr_rmtval_set(
 	return 0;
 out_defer_cancel:
 	xfs_defer_cancel(args->trans->t_dfops);
-	args->trans = NULL;
 	return error;
 }
 
@@ -646,6 +645,5 @@ xfs_attr_rmtval_remove(
 	return 0;
 out_defer_cancel:
 	xfs_defer_cancel(args->trans->t_dfops);
-	args->trans = NULL;
 	return error;
 }
-- 
cgit v1.2.3


From 03f4e4b26cd5f6eed728f82d90039a19d1b51ce3 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:09 -0700
Subject: xfs: make deferred processing safe for embedded dfops

xfs_defer_finish() has a couple quirks that are not safe with
respect to the upcoming internal dfops functionality. First,
xfs_defer_finish() attaches the passed in dfops structure to
->t_dfops and caches and restores the original value. Second, it
continues to use the initial dfops reference before and after the
transaction roll.

These behaviors assume that dop is an independent memory allocation
from the transaction itself, which may not always be true once
transactions begin to use an embedded dfops structure. In the latter
model, dfops processing creates a new xfs_defer_ops structure with
each transaction and the associated state is migrated across to the
new transaction.

Fix up xfs_defer_finish() to handle the possibility of the current
dfops changing after a transaction roll. Since ->t_dfops is used
unconditionally in this path, it is no longer necessary to
attach/restore ->t_dfops and pass it explicitly down to
xfs_defer_trans_roll(). Update dop in the latter function and the
caller to ensure that it always refers to the current dfops
structure.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 32 ++++++++++++++------------------
 1 file changed, 14 insertions(+), 18 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index c4b0eaeb5190..ee734a8b3fa9 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -225,9 +225,9 @@ xfs_defer_trans_abort(
 /* Roll a transaction so we can do some deferred op processing. */
 STATIC int
 xfs_defer_trans_roll(
-	struct xfs_trans		**tp,
-	struct xfs_defer_ops		*dop)
+	struct xfs_trans		**tp)
 {
+	struct xfs_defer_ops		*dop = (*tp)->t_dfops;
 	int				i;
 	int				error;
 
@@ -243,6 +243,7 @@ xfs_defer_trans_roll(
 
 	/* Roll the transaction. */
 	error = xfs_trans_roll(tp);
+	dop = (*tp)->t_dfops;
 	if (error) {
 		trace_xfs_defer_trans_roll_error((*tp)->t_mountp, dop, error);
 		xfs_defer_trans_abort(*tp, dop, error);
@@ -338,31 +339,25 @@ xfs_defer_finish(
 	void				*state;
 	int				error = 0;
 	void				(*cleanup_fn)(struct xfs_trans *, void *, int);
-	struct xfs_defer_ops		*orig_dop;
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
+	ASSERT((*tp)->t_dfops == dop);
 
 	trace_xfs_defer_finish((*tp)->t_mountp, dop, _RET_IP_);
 
-	/*
-	 * Attach dfops to the transaction during deferred ops processing. This
-	 * explicitly causes calls into the allocator to defer AGFL block frees.
-	 * Note that this code can go away once all dfops users attach to the
-	 * associated tp.
-	 */
-	ASSERT(!(*tp)->t_dfops || ((*tp)->t_dfops == dop));
-	orig_dop = (*tp)->t_dfops;
-	(*tp)->t_dfops = dop;
-
 	/* Until we run out of pending work to finish... */
 	while (xfs_defer_has_unfinished_work(dop)) {
 		/* Log intents for work items sitting in the intake. */
 		xfs_defer_intake_work(*tp, dop);
 
-		/* Roll the transaction. */
-		error = xfs_defer_trans_roll(tp, dop);
+		/*
+		 * Roll the transaction and update dop in case dfops was
+		 * embedded in the transaction.
+		 */
+		error = xfs_defer_trans_roll(tp);
 		if (error)
 			goto out;
+		dop = (*tp)->t_dfops;
 
 		/* Log an intent-done item for the first pending item. */
 		dfp = list_first_entry(&dop->dop_pending,
@@ -428,10 +423,11 @@ xfs_defer_finish(
 	 * Roll the transaction once more to avoid returning to the caller
 	 * with a dirty transaction.
 	 */
-	if ((*tp)->t_flags & XFS_TRANS_DIRTY)
-		error = xfs_defer_trans_roll(tp, dop);
+	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+		error = xfs_defer_trans_roll(tp);
+		dop = (*tp)->t_dfops;
+	}
 out:
-	(*tp)->t_dfops = orig_dop;
 	if (error)
 		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
 	else
-- 
cgit v1.2.3


From 83200bfac6082a46cc962366478d050052e50450 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:09 -0700
Subject: xfs: remove unused deferred ops committed field

dop_committed is set when deferred item processing rolls the
transaction at least once, but is only ever accessed in tracepoints.
The transaction roll/commit events are already available via
independent tracepoints, so remove the otherwise unused field.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 1 -
 fs/xfs/libxfs/xfs_defer.h | 1 -
 fs/xfs/xfs_trace.h        | 8 ++------
 3 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index ee734a8b3fa9..0df09c094e42 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -249,7 +249,6 @@ xfs_defer_trans_roll(
 		xfs_defer_trans_abort(*tp, dop, error);
 		return error;
 	}
-	dop->dop_committed = true;
 
 	/* Rejoin the joined inodes. */
 	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index c17c9deda995..58c979c9f3fa 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -49,7 +49,6 @@ enum xfs_defer_ops_type {
 #define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
 
 struct xfs_defer_ops {
-	bool			dop_committed;	/* did any trans commit? */
 	bool			dop_low;	/* alloc in low mode */
 	struct list_head	dop_intake;	/* unlogged pending work */
 	struct list_head	dop_pending;	/* logged pending work */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b668fc127aa7..cc6995cfce66 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2229,14 +2229,12 @@ DECLARE_EVENT_CLASS(xfs_defer_class,
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
 		__entry->dop = dop;
-		__entry->committed = dop->dop_committed;
 		__entry->low = dop->dop_low;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d, caller %pS",
+	TP_printk("dev %d:%d ops %p low %d, caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dop,
-		  __entry->committed,
 		  __entry->low,
 		  (char *)__entry->caller_ip)
 )
@@ -2259,14 +2257,12 @@ DECLARE_EVENT_CLASS(xfs_defer_error_class,
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
 		__entry->dop = dop;
-		__entry->committed = dop->dop_committed;
 		__entry->low = dop->dop_low;
 		__entry->error = error;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d err %d",
+	TP_printk("dev %d:%d ops %p low %d err %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dop,
-		  __entry->committed,
 		  __entry->low,
 		  __entry->error)
 )
-- 
cgit v1.2.3


From 509308b413c9e4e3140b4bc524522255d126787e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:10 -0700
Subject: xfs: reset dfops to initial state after finish

xfs_defer_init() is currently used in two particular situations. The
first and most obvious case is raw initialization of an
xfs_defer_ops struct. The other case is partial reinit of
xfs_defer_ops on reuse due to iteration.

Most instances of the first case will be replaced by a single init
of a dfops embedded in the transaction. Init calls are still
technically required for the second case because the dfops may have
low space mode enabled or have joined items that need to be reset
before the dfops should be reused.

Since the current dfops usage expects either a final transaction
commit after xfs_defer_finish() or xfs_defer_init() if dfops is to
be reused, we can shift some of the init logic into
xfs_defer_finish() such that the latter returns with a reinitialized
dfops. This eliminates the second dependency noted above such that a
dfops is immediately ready for reuse after an xfs_defer_finish()
without the need to change any calling code.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 0df09c094e42..23f2a52b088e 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -319,6 +319,19 @@ xfs_defer_bjoin(
 	return -EFSCORRUPTED;
 }
 
+/*
+ * Reset an already used dfops after finish.
+ */
+static void
+xfs_defer_reset(
+	struct xfs_defer_ops	*dop)
+{
+	ASSERT(!xfs_defer_has_unfinished_work(dop));
+	dop->dop_low = false;
+	memset(dop->dop_inodes, 0, sizeof(dop->dop_inodes));
+	memset(dop->dop_bufs, 0, sizeof(dop->dop_bufs));
+}
+
 /*
  * Finish all the pending work.  This involves logging intent items for
  * any work items that wandered in since the last transaction roll (if
@@ -427,10 +440,13 @@ xfs_defer_finish(
 		dop = (*tp)->t_dfops;
 	}
 out:
-	if (error)
+	if (error) {
 		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
-	else
+	} else {
 		trace_xfs_defer_finish_done((*tp)->t_mountp, dop, _RET_IP_);
+		xfs_defer_reset(dop);
+	}
+
 	return error;
 }
 
-- 
cgit v1.2.3


From 44fd294681de73990da656294e3dacaa7878f577 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:11 -0700
Subject: xfs: pack holes in xfs_defer_ops and xfs_trans

Both structures have holes due to member alignment. Move dop_low to
the end of xfs_defer ops to sanitize the cache line alignment and
move t_flags to save 8 bytes in xfs_trans.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.h | 3 ++-
 fs/xfs/xfs_trans.h        | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 58c979c9f3fa..8f58f217fdff 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -49,13 +49,14 @@ enum xfs_defer_ops_type {
 #define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
 
 struct xfs_defer_ops {
-	bool			dop_low;	/* alloc in low mode */
 	struct list_head	dop_intake;	/* unlogged pending work */
 	struct list_head	dop_pending;	/* logged pending work */
 
 	/* relog these with each roll */
 	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
 	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
+
+	bool			dop_low;	/* alloc in low mode */
 };
 
 void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 37fdacc690c7..6f857af61455 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -102,12 +102,12 @@ typedef struct xfs_trans {
 	unsigned int		t_blk_res_used;	/* # of resvd blocks used */
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
+	unsigned int		t_flags;	/* misc flags */
 	xfs_fsblock_t		t_firstblock;	/* first block allocated */
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
 	struct xfs_defer_ops	*t_dfops;	/* dfops reference */
-	unsigned int		t_flags;	/* misc flags */
 	int64_t			t_icount_delta;	/* superblock icount change */
 	int64_t			t_ifree_delta;	/* superblock ifree change */
 	int64_t			t_fdblocks_delta; /* superblock fdblocks chg */
-- 
cgit v1.2.3


From e021a2e5fc520d930f949f303e7307038e258645 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:11 -0700
Subject: xfs: support embedded dfops in transaction

The dfops structure used by multi-transaction operations is
typically stored on the stack and carried around by the associated
transaction. The lifecycle of dfops does not quite match that of the
transaction, but they are tightly related in that the former depends
on the latter.

The relationship of these objects is tight enough that we can avoid
the cumbersome boilerplate code required in most cases to manage
them separately by just embedding an xfs_defer_ops in the
transaction itself. This means that a transaction allocation returns
with an initialized dfops, a transaction commit finishes pending
deferred items before the tx commit, a transaction cancel cancels
the dfops before the transaction and a transaction dup operation
transfers the current dfops state to the new transaction.

The dup operation is slightly complicated by the fact that we can no
longer just copy a dfops pointer from the old transaction to the new
transaction. This is solved through a dfops move helper that
transfers the pending items and other dfops state across the
transactions. This also requires that transaction rolling code
always refer to the transaction for the current dfops reference.

Finally, to facilitate incremental conversion to the internal dfops
and continue to support the current external dfops mode of
operation, create the new ->t_dfops_internal field with a layer of
indirection. On allocation, ->t_dfops points to the internal dfops.
This state is overridden by callers who re-init a local dfops on the
transaction. Once ->t_dfops is overridden, the external dfops
reference is maintained as the transaction rolls.

This patch adds the fundamental ability to support an internal
dfops. All codepaths that perform deferred processing continue to
override the internal dfops until they are converted over in
subsequent patches.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 22 ++++++++++++++++++++++
 fs/xfs/libxfs/xfs_defer.h | 16 ++--------------
 fs/xfs/xfs_trans.c        | 30 ++++++++++++++++++++++++++----
 fs/xfs/xfs_trans.h        | 17 ++++++++++++++++-
 4 files changed, 66 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 23f2a52b088e..b63cc9e730da 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -555,3 +555,25 @@ xfs_defer_init(
 	}
 	trace_xfs_defer_init(mp, dop, _RET_IP_);
 }
+
+/*
+ * Move state from one xfs_defer_ops to another and reset the source to initial
+ * state. This is primarily used to carry state forward across transaction rolls
+ * with internal dfops.
+ */
+void
+xfs_defer_move(
+	struct xfs_defer_ops	*dst,
+	struct xfs_defer_ops	*src)
+{
+	ASSERT(dst != src);
+
+	list_splice_init(&src->dop_intake, &dst->dop_intake);
+	list_splice_init(&src->dop_pending, &dst->dop_pending);
+
+	memcpy(dst->dop_inodes, src->dop_inodes, sizeof(dst->dop_inodes));
+	memcpy(dst->dop_bufs, src->dop_bufs, sizeof(dst->dop_bufs));
+	dst->dop_low = src->dop_low;
+
+	xfs_defer_reset(src);
+}
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 8f58f217fdff..35507ca9a148 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -7,6 +7,7 @@
 #define	__XFS_DEFER_H__
 
 struct xfs_defer_op_type;
+struct xfs_defer_ops;
 
 /*
  * Save a log intent item and a list of extents, so that we can replay
@@ -45,20 +46,6 @@ enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_MAX,
 };
 
-#define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
-#define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
-
-struct xfs_defer_ops {
-	struct list_head	dop_intake;	/* unlogged pending work */
-	struct list_head	dop_pending;	/* logged pending work */
-
-	/* relog these with each roll */
-	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
-	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
-
-	bool			dop_low;	/* alloc in low mode */
-};
-
 void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
 		struct list_head *h);
 int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop);
@@ -67,6 +54,7 @@ void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
 int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
+void xfs_defer_move(struct xfs_defer_ops *dst, struct xfs_defer_ops *src);
 
 /* Description of a deferred type. */
 struct xfs_defer_op_type {
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index de00f79ff698..412c8d236c71 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -119,7 +119,13 @@ xfs_trans_dup(
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
 	ntp->t_pflags = tp->t_pflags;
-	ntp->t_dfops = tp->t_dfops;
+
+	/* copy the dfops pointer if it's external, otherwise move it */
+	xfs_defer_init(ntp, &ntp->t_dfops_internal);
+	if (tp->t_dfops != &tp->t_dfops_internal)
+		ntp->t_dfops = tp->t_dfops;
+	else
+		xfs_defer_move(ntp->t_dfops, tp->t_dfops);
 
 	xfs_trans_dup_dqinfo(tp, ntp);
 
@@ -275,6 +281,13 @@ xfs_trans_alloc(
 	INIT_LIST_HEAD(&tp->t_items);
 	INIT_LIST_HEAD(&tp->t_busy);
 	tp->t_firstblock = NULLFSBLOCK;
+	/*
+	 * We only roll transactions with permanent log reservation. Don't init
+	 * ->t_dfops to skip attempts to finish or cancel an empty dfops with a
+	 * non-permanent res.
+	 */
+	if (resp->tr_logflags & XFS_TRANS_PERM_LOG_RES)
+		xfs_defer_init(tp, &tp->t_dfops_internal);
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error) {
@@ -916,11 +929,17 @@ __xfs_trans_commit(
 	int			error = 0;
 	int			sync = tp->t_flags & XFS_TRANS_SYNC;
 
-	ASSERT(!tp->t_dfops ||
-	       !xfs_defer_has_unfinished_work(tp->t_dfops) || regrant);
-
 	trace_xfs_trans_commit(tp, _RET_IP_);
 
+	/* finish deferred items on final commit */
+	if (!regrant && tp->t_dfops) {
+		error = xfs_defer_finish(&tp, tp->t_dfops);
+		if (error) {
+			xfs_defer_cancel(tp->t_dfops);
+			goto out_unreserve;
+		}
+	}
+
 	/*
 	 * If there is nothing to be logged by the transaction,
 	 * then unlock all of the items associated with the
@@ -1010,6 +1029,9 @@ xfs_trans_cancel(
 
 	trace_xfs_trans_cancel(tp, _RET_IP_);
 
+	if (tp->t_dfops)
+		xfs_defer_cancel(tp->t_dfops);
+
 	/*
 	 * See if the caller is relying on us to shut down the
 	 * filesystem.  This happens in paths where we detect
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 6f857af61455..dc79e3c1d3e8 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -24,7 +24,6 @@ struct xfs_rui_log_item;
 struct xfs_btree_cur;
 struct xfs_cui_log_item;
 struct xfs_cud_log_item;
-struct xfs_defer_ops;
 struct xfs_bui_log_item;
 struct xfs_bud_log_item;
 
@@ -90,6 +89,21 @@ void	xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
 #define XFS_ITEM_LOCKED		2
 #define XFS_ITEM_FLUSHING	3
 
+/*
+ * Deferred operations tracking structure.
+ */
+#define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
+#define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
+struct xfs_defer_ops {
+	struct list_head	dop_intake;	/* unlogged pending work */
+	struct list_head	dop_pending;	/* logged pending work */
+
+	/* relog these with each roll */
+	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
+	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
+
+	bool			dop_low;	/* alloc in low mode */
+};
 
 /*
  * This is the structure maintained for every active transaction.
@@ -130,6 +144,7 @@ typedef struct xfs_trans {
 	struct list_head	t_items;	/* log item descriptors */
 	struct list_head	t_busy;		/* list of busy extents */
 	unsigned long		t_pflags;	/* saved process flags state */
+	struct xfs_defer_ops	t_dfops_internal;
 } xfs_trans_t;
 
 /*
-- 
cgit v1.2.3


From 1e5ae1995a44f2b7a03f08a10504568a96040a8c Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:12 -0700
Subject: xfs: use internal dfops in cow blocks cancel

All callers either explicitly initialize a dfops or pass a
transaction with an internal dfops. Drop the hacky old dfops
replacement logic and use the one associated with the transaction.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_reflink.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 406f79d44153..04c25ee6b6f8 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -483,8 +483,6 @@ xfs_reflink_cancel_cow_blocks(
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
 	struct xfs_iext_cursor		icur;
-	struct xfs_defer_ops		dfops;
-	struct xfs_defer_ops		*odfops = (*tpp)->t_dfops;
 	int				error = 0;
 
 	if (!xfs_is_reflink_inode(ip))
@@ -511,7 +509,8 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			xfs_defer_init(*tpp, &dfops);
+			ASSERT((*tpp)->t_dfops);
+			ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
@@ -553,7 +552,6 @@ next_extent:
 	/* clear tag if cow fork is emptied */
 	if (!ifp->if_bytes)
 		xfs_inode_clear_cowblocks_tag(ip);
-	(*tpp)->t_dfops = odfops;
 	return error;
 }
 
-- 
cgit v1.2.3


From 9c6bb0cf7ba318767107328f39aac880344ddd2e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:12 -0700
Subject: xfs: use internal dfops in attr code

Remove the unnecessary on-stack dfops structure and use the internal
transaction dfops instead. The lower level xattr code already
appropriately accesses ->t_dfops throughout.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 927d4c968f9a..66a22c80a0db 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -202,7 +202,6 @@ xfs_attr_set(
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_buf		*leaf_bp = NULL;
 	struct xfs_da_args	args;
-	struct xfs_defer_ops	dfops;
 	struct xfs_trans_res	tres;
 	int			rsvd = (flags & ATTR_ROOT) != 0;
 	int			error, err2, local;
@@ -251,7 +250,6 @@ xfs_attr_set(
 			rsvd ? XFS_TRANS_RESERVE : 0, &args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(args.trans, &dfops);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(args.trans, dp, args.total, 0,
@@ -315,18 +313,18 @@ xfs_attr_set(
 		 */
 		error = xfs_attr_shortform_to_leaf(&args, &leaf_bp);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		/*
 		 * Prevent the leaf buffer from being unlocked so that a
 		 * concurrent AIL push cannot grab the half-baked leaf
 		 * buffer and run into problems with the write verifier.
 		 */
 		xfs_trans_bhold(args.trans, leaf_bp);
-		xfs_defer_bjoin(&dfops, leaf_bp);
-		xfs_defer_ijoin(&dfops, dp);
-		error = xfs_defer_finish(&args.trans, &dfops);
+		xfs_defer_bjoin(args.trans->t_dfops, leaf_bp);
+		xfs_defer_ijoin(args.trans->t_dfops, dp);
+		error = xfs_defer_finish(&args.trans, args.trans->t_dfops);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 
 		/*
 		 * Commit the leaf transformation.  We'll need another (linked)
@@ -366,8 +364,6 @@ xfs_attr_set(
 
 	return error;
 
-out_defer_cancel:
-	xfs_defer_cancel(&dfops);
 out:
 	if (leaf_bp)
 		xfs_trans_brelse(args.trans, leaf_bp);
@@ -389,7 +385,6 @@ xfs_attr_remove(
 {
 	struct xfs_mount	*mp = dp->i_mount;
 	struct xfs_da_args	args;
-	struct xfs_defer_ops	dfops;
 	int			error;
 
 	XFS_STATS_INC(mp, xs_attr_remove);
@@ -422,7 +417,6 @@ xfs_attr_remove(
 			&args.trans);
 	if (error)
 		return error;
-	xfs_defer_init(args.trans, &dfops);
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL);
 	/*
-- 
cgit v1.2.3


From 91ef75b6572498face47746c253926e733a4da3b Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:13 -0700
Subject: xfs: use internal dfops during [b|c]ui recovery

bmap and refcount intent processing associates a dfops from the
caller with a local transaction to collect all deferred items for
post-processing. Use the internal dfops in both of these functions
and move the deferred items to the parent dfops before the
transaction commits.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_item.c     | 21 +++++++++++----------
 fs/xfs/xfs_log_recover.c   |  6 +++---
 fs/xfs/xfs_refcount_item.c | 30 ++++++++++++++++--------------
 3 files changed, 30 insertions(+), 27 deletions(-)

diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 478bfc798861..bc5eb2e0ab0c 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -441,7 +441,12 @@ xfs_bui_recover(
 			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
 	if (error)
 		return error;
-	tp->t_dfops = dfops;
+	/*
+	 * Recovery stashes all deferred ops during intent processing and
+	 * finishes them on completion. Transfer current dfops state to this
+	 * transaction and transfer the result back before we return.
+	 */
+	xfs_defer_move(tp->t_dfops, dfops);
 	budp = xfs_trans_get_bud(tp, buip);
 
 	/* Grab the inode. */
@@ -470,7 +475,7 @@ xfs_bui_recover(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	count = bmap->me_len;
-	error = xfs_trans_log_finish_bmap_update(tp, budp, dfops, type,
+	error = xfs_trans_log_finish_bmap_update(tp, budp, tp->t_dfops, type,
 			ip, whichfork, bmap->me_startoff,
 			bmap->me_startblock, &count, state);
 	if (error)
@@ -482,18 +487,14 @@ xfs_bui_recover(
 		irec.br_blockcount = count;
 		irec.br_startoff = bmap->me_startoff;
 		irec.br_state = state;
-		error = xfs_bmap_unmap_extent(tp->t_mountp, dfops, ip, &irec);
+		error = xfs_bmap_unmap_extent(tp->t_mountp, tp->t_dfops, ip,
+					      &irec);
 		if (error)
 			goto err_inode;
 	}
 
 	set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
-	/*
-	 * Recovery finishes all deferred ops once intent processing is
-	 * complete. Reset the trans reference because commit expects a finished
-	 * dfops or none at all.
-	 */
-	tp->t_dfops = NULL;
+	xfs_defer_move(dfops, tp->t_dfops);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	IRELE(ip);
@@ -501,7 +502,7 @@ xfs_bui_recover(
 	return error;
 
 err_inode:
-	tp->t_dfops = NULL;
+	xfs_defer_move(dfops, tp->t_dfops);
 	xfs_trans_cancel(tp);
 	if (ip) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 3289811eb076..958e9b96dc6a 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4854,10 +4854,10 @@ xlog_finish_defer_ops(
 			0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
-	/* dfops is already populated so assign it manually */
-	tp->t_dfops = dfops;
+	/* transfer all collected dfops to this transaction */
+	xfs_defer_move(tp->t_dfops, dfops);
 
-	error = xfs_defer_finish(&tp, dfops);
+	error = xfs_defer_finish(&tp, tp->t_dfops);
 	if (error)
 		goto out_cancel;
 
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 2064c689bc72..d3582a06626f 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -452,7 +452,12 @@ xfs_cui_recover(
 			mp->m_refc_maxlevels * 2, 0, XFS_TRANS_RESERVE, &tp);
 	if (error)
 		return error;
-	tp->t_dfops = dfops;
+	/*
+	 * Recovery stashes all deferred ops during intent processing and
+	 * finishes them on completion. Transfer current dfops state to this
+	 * transaction and transfer the result back before we return.
+	 */
+	xfs_defer_move(tp->t_dfops, dfops);
 	cudp = xfs_trans_get_cud(tp, cuip);
 
 	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
@@ -474,8 +479,8 @@ xfs_cui_recover(
 			new_len = refc->pe_len;
 		} else
 			error = xfs_trans_log_finish_refcount_update(tp, cudp,
-				dfops, type, refc->pe_startblock, refc->pe_len,
-				&new_fsb, &new_len, &rcur);
+				tp->t_dfops, type, refc->pe_startblock,
+				refc->pe_len, &new_fsb, &new_len, &rcur);
 		if (error)
 			goto abort_error;
 
@@ -486,21 +491,23 @@ xfs_cui_recover(
 			switch (type) {
 			case XFS_REFCOUNT_INCREASE:
 				error = xfs_refcount_increase_extent(
-						tp->t_mountp, dfops, &irec);
+						tp->t_mountp, tp->t_dfops,
+						&irec);
 				break;
 			case XFS_REFCOUNT_DECREASE:
 				error = xfs_refcount_decrease_extent(
-						tp->t_mountp, dfops, &irec);
+						tp->t_mountp, tp->t_dfops,
+						&irec);
 				break;
 			case XFS_REFCOUNT_ALLOC_COW:
 				error = xfs_refcount_alloc_cow_extent(
-						tp->t_mountp, dfops,
+						tp->t_mountp, tp->t_dfops,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
 			case XFS_REFCOUNT_FREE_COW:
 				error = xfs_refcount_free_cow_extent(
-						tp->t_mountp, dfops,
+						tp->t_mountp, tp->t_dfops,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
@@ -515,18 +522,13 @@ xfs_cui_recover(
 
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
-	/*
-	 * Recovery finishes all deferred ops once intent processing is
-	 * complete. Reset the trans reference because commit expects a finished
-	 * dfops or none at all.
-	 */
-	tp->t_dfops = NULL;
+	xfs_defer_move(dfops, tp->t_dfops);
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
-	tp->t_dfops = NULL;
+	xfs_defer_move(dfops, tp->t_dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
-- 
cgit v1.2.3


From c8eac49ef798a7d00240847f63902caa1388241a Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:13 -0700
Subject: xfs: remove all boilerplate defer init/finish code

At this point, the transaction subsystem completely manages deferred
items internally such that the common and boilerplate
xfs_trans_alloc() -> xfs_defer_init() -> xfs_defer_finish() ->
xfs_trans_commit() sequence can be replaced with a simple
transaction allocation and commit.

Remove all such boilerplate deferred ops code. In doing so, we
change each case over to use the dfops in the transaction and
specifically eliminate:

- The on-stack dfops and associated xfs_defer_init() call, as the
  internal dfops is initialized on transaction allocation.
- xfs_bmap_finish() calls that precede a final xfs_trans_commit() of
  a transaction.
- xfs_defer_cancel() calls in error handlers that precede a
  transaction cancel.

The only deferred ops calls that remain are those that are
non-deterministic with respect to the final commit of the associated
transaction or are open-coded due to special handling.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c     | 16 +--------
 fs/xfs/libxfs/xfs_refcount.c | 10 +-----
 fs/xfs/xfs_attr_inactive.c   |  2 --
 fs/xfs/xfs_bmap_util.c       | 43 ++++--------------------
 fs/xfs/xfs_dquot.c           |  4 ---
 fs/xfs/xfs_inode.c           | 79 ++++++++------------------------------------
 fs/xfs/xfs_iomap.c           | 26 ++-------------
 fs/xfs/xfs_iops.c            |  2 --
 fs/xfs/xfs_log_recover.c     |  8 -----
 fs/xfs/xfs_qm_syscalls.c     |  2 --
 fs/xfs/xfs_reflink.c         | 37 +++++++--------------
 fs/xfs/xfs_rtalloc.c         |  9 +----
 fs/xfs/xfs_symlink.c         | 38 +++++----------------
 13 files changed, 44 insertions(+), 232 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 6bc0cdff488e..92cd064a2589 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1018,7 +1018,6 @@ xfs_bmap_add_attrfork(
 	int			size,		/* space new attribute needs */
 	int			rsvd)		/* xact may use reserved blks */
 {
-	struct xfs_defer_ops	dfops;		/* freed extent records */
 	xfs_mount_t		*mp;		/* mount structure */
 	xfs_trans_t		*tp;		/* transaction pointer */
 	int			blks;		/* space reservation */
@@ -1037,7 +1036,6 @@ xfs_bmap_add_attrfork(
 			rsvd ? XFS_TRANS_RESERVE : 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(tp, &dfops);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	error = xfs_trans_reserve_quota_nblks(tp, ip, blks, 0, rsvd ?
@@ -1102,7 +1100,7 @@ xfs_bmap_add_attrfork(
 	if (logflags)
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (error)
-		goto bmap_cancel;
+		goto trans_cancel;
 	if (!xfs_sb_version_hasattr(&mp->m_sb) ||
 	   (!xfs_sb_version_hasattr2(&mp->m_sb) && version == 2)) {
 		bool log_sb = false;
@@ -1121,15 +1119,10 @@ xfs_bmap_add_attrfork(
 			xfs_log_sb(tp);
 	}
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto bmap_cancel;
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 
-bmap_cancel:
-	xfs_defer_cancel(&dfops);
 trans_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -5953,14 +5946,12 @@ xfs_bmap_split_extent(
 {
 	struct xfs_mount        *mp = ip->i_mount;
 	struct xfs_trans        *tp;
-	struct xfs_defer_ops    dfops;
 	int                     error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
 			XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(tp, &dfops);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
@@ -5969,14 +5960,9 @@ xfs_bmap_split_extent(
 	if (error)
 		goto out;
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out;
-
 	return xfs_trans_commit(tp);
 
 out:
-	xfs_defer_cancel(&dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 9ef1f440a6f2..4cbc2efb099e 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1635,7 +1635,6 @@ xfs_refcount_recover_cow_leftovers(
 	struct list_head		debris;
 	union xfs_btree_irec		low;
 	union xfs_btree_irec		high;
-	struct xfs_defer_ops		dfops;
 	xfs_fsblock_t			fsb;
 	xfs_agblock_t			agbno;
 	int				error;
@@ -1691,22 +1690,17 @@ xfs_refcount_recover_cow_leftovers(
 		trace_xfs_refcount_recover_extent(mp, agno, &rr->rr_rrec);
 
 		/* Free the orphan record */
-		xfs_defer_init(tp, &dfops);
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
 		error = xfs_refcount_free_cow_extent(mp, tp->t_dfops, fsb,
 				rr->rr_rrec.rc_blockcount);
 		if (error)
-			goto out_defer;
+			goto out_trans;
 
 		/* Free the block. */
 		xfs_bmap_add_free(mp, tp->t_dfops, fsb,
 				rr->rr_rrec.rc_blockcount, NULL);
 
-		error = xfs_defer_finish(&tp, tp->t_dfops);
-		if (error)
-			goto out_defer;
-
 		error = xfs_trans_commit(tp);
 		if (error)
 			goto out_free;
@@ -1716,8 +1710,6 @@ xfs_refcount_recover_cow_leftovers(
 	}
 
 	return error;
-out_defer:
-	xfs_defer_cancel(tp->t_dfops);
 out_trans:
 	xfs_trans_cancel(tp);
 out_free:
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index d3055972d3a6..228821b2ebe0 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -382,7 +382,6 @@ xfs_attr_inactive(
 {
 	struct xfs_trans	*trans;
 	struct xfs_mount	*mp;
-	struct xfs_defer_ops	dfops;
 	int			lock_mode = XFS_ILOCK_SHARED;
 	int			error = 0;
 
@@ -399,7 +398,6 @@ xfs_attr_inactive(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_attrinval, 0, 0, 0, &trans);
 	if (error)
 		goto out_destroy_fork;
-	xfs_defer_init(trans, &dfops);
 
 	lock_mode = XFS_ILOCK_EXCL;
 	xfs_ilock(dp, lock_mode);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 1a4617c74c6a..ddb5f1200d3d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -792,7 +792,6 @@ xfs_free_eofblocks(
 	int			nimaps;
 	struct xfs_bmbt_irec	imap;
 	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_defer_ops	dfops;
 
 	/*
 	 * Figure out if there are any blocks beyond the end
@@ -832,7 +831,6 @@ xfs_free_eofblocks(
 			ASSERT(XFS_FORCED_SHUTDOWN(mp));
 			return error;
 		}
-		xfs_defer_init(tp, &dfops);
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, 0);
@@ -880,7 +878,6 @@ xfs_alloc_file_space(
 	int			rt;
 	xfs_trans_t		*tp;
 	xfs_bmbt_irec_t		imaps[1], *imapp;
-	struct xfs_defer_ops	dfops;
 	uint			qblocks, resblks, resrtextents;
 	int			error;
 
@@ -973,7 +970,6 @@ xfs_alloc_file_space(
 
 		xfs_trans_ijoin(tp, ip, 0);
 
-		xfs_defer_init(tp, &dfops);
 		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
 					allocatesize_fsb, alloc_type, resblks,
 					imapp, &nimaps);
@@ -983,10 +979,6 @@ xfs_alloc_file_space(
 		/*
 		 * Complete the transaction
 		 */
-		error = xfs_defer_finish(&tp, tp->t_dfops);
-		if (error)
-			goto error0;
-
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
@@ -1005,8 +997,7 @@ xfs_alloc_file_space(
 
 	return error;
 
-error0:	/* Cancel bmap, unlock inode, unreserve quota blocks, cancel trans */
-	xfs_defer_cancel(&dfops);
+error0:	/* unlock inode, unreserve quota blocks, cancel trans */
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 
 error1:	/* Just cancel transaction */
@@ -1024,7 +1015,6 @@ xfs_unmap_extent(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
 	int			error;
 
@@ -1042,23 +1032,17 @@ xfs_unmap_extent(
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops);
 	error = xfs_bunmapi(tp, ip, startoffset_fsb, len_fsb, 0, 2, done);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	xfs_defer_ijoin(tp->t_dfops, ip);
-	error = xfs_defer_finish(&tp, tp->t_dfops);
-	if (error)
-		goto out_bmap_cancel;
 
 	error = xfs_trans_commit(tp);
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	goto out_unlock;
@@ -1310,7 +1294,6 @@ xfs_collapse_file_space(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
 	xfs_fileoff_t		next_fsb = XFS_B_TO_FSB(mp, offset + len);
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
 	uint			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
@@ -1343,22 +1326,16 @@ xfs_collapse_file_space(
 			goto out_trans_cancel;
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(tp, &dfops);
 		error = xfs_bmap_collapse_extents(tp, ip, &next_fsb, shift_fsb,
 				&done);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
-		error = xfs_defer_finish(&tp, tp->t_dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 	}
 
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
@@ -1385,7 +1362,6 @@ xfs_insert_file_space(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
 	xfs_fileoff_t		stop_fsb = XFS_B_TO_FSB(mp, offset);
 	xfs_fileoff_t		next_fsb = NULLFSBLOCK;
 	xfs_fileoff_t		shift_fsb = XFS_B_TO_FSB(mp, len);
@@ -1421,22 +1397,17 @@ xfs_insert_file_space(
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-		xfs_defer_init(tp, &dfops);
 		error = xfs_bmap_insert_extents(tp, ip, &next_fsb, shift_fsb,
 				&done, stop_fsb);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
-		error = xfs_defer_finish(&tp, tp->t_dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 	}
 
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
+out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -1607,7 +1578,7 @@ xfs_swap_extent_rmap(
 
 		/* Unmap the old blocks in the source file. */
 		while (tirec.br_blockcount) {
-			xfs_defer_init(tp, tp->t_dfops);
+			ASSERT(tp->t_firstblock == NULLFSBLOCK);
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &tirec);
 
 			/* Read extent from the source file */
@@ -1831,7 +1802,6 @@ xfs_swap_extents(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
 	struct xfs_bstat	*sbp = &sxp->sx_stat;
 	int			src_log_flags, target_log_flags;
 	int			error = 0;
@@ -1900,7 +1870,6 @@ xfs_swap_extents(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
-	xfs_defer_init(tp, &dfops);
 
 	/*
 	 * Lock and join the inodes to the tansaction so that transaction commit
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index c53de34c9ae5..a57d5e8c3118 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -295,8 +295,6 @@ xfs_dquot_disk_alloc(
 
 	trace_xfs_dqalloc(dqp);
 
-	xfs_defer_init(tp, tp->t_dfops);
-
 	xfs_ilock(quotip, XFS_ILOCK_EXCL);
 	if (!xfs_this_quota_on(dqp->q_mount, dqp->dq_flags)) {
 		/*
@@ -538,7 +536,6 @@ xfs_qm_dqread_alloc(
 	struct xfs_buf		**bpp)
 {
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
 	struct xfs_buf		*bp;
 	int			error;
 
@@ -546,7 +543,6 @@ xfs_qm_dqread_alloc(
 			XFS_QM_DQALLOC_SPACE_RES(mp), 0, 0, &tp);
 	if (error)
 		goto err;
-	xfs_defer_init(tp, &dfops);
 
 	error = xfs_dquot_disk_alloc(&tp, dqp, &bp);
 	if (error)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7d7d7e95fa17..c47183a2f167 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1142,7 +1142,6 @@ xfs_create(
 	struct xfs_inode	*ip = NULL;
 	struct xfs_trans	*tp = NULL;
 	int			error;
-	struct xfs_defer_ops	dfops;
 	bool                    unlock_dp_on_error = false;
 	prid_t			prid;
 	struct xfs_dquot	*udqp = NULL;
@@ -1194,8 +1193,6 @@ xfs_create(
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = true;
 
-	xfs_defer_init(tp, &dfops);
-
 	/*
 	 * Reserve disk quota and the inode.
 	 */
@@ -1236,11 +1233,11 @@ xfs_create(
 	if (is_dir) {
 		error = xfs_dir_init(tp, ip, dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		error = xfs_bumplink(tp, dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -1258,10 +1255,6 @@ xfs_create(
 	 */
 	xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_release_inode;
@@ -1273,8 +1266,6 @@ xfs_create(
 	*ipp = ip;
 	return 0;
 
- out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
  out_trans_cancel:
 	xfs_trans_cancel(tp);
  out_release_inode:
@@ -1399,7 +1390,6 @@ xfs_link(
 	xfs_mount_t		*mp = tdp->i_mount;
 	xfs_trans_t		*tp;
 	int			error;
-	struct xfs_defer_ops	dfops;
 	int			resblks;
 
 	trace_xfs_link(tdp, target_name);
@@ -1448,8 +1438,6 @@ xfs_link(
 			goto error_return;
 	}
 
-	xfs_defer_init(tp, &dfops);
-
 	/*
 	 * Handle initial link state of O_TMPFILE inode
 	 */
@@ -1478,12 +1466,6 @@ xfs_link(
 	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error) {
-		xfs_defer_cancel(&dfops);
-		goto error_return;
-	}
-
 	return xfs_trans_commit(tp);
 
  error_return:
@@ -1719,7 +1701,6 @@ xfs_inactive_truncate(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
 	int			error;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
@@ -1727,8 +1708,6 @@ xfs_inactive_truncate(
 		ASSERT(XFS_FORCED_SHUTDOWN(mp));
 		return error;
 	}
-	xfs_defer_init(tp, &dfops);
-
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
@@ -1769,7 +1748,6 @@ STATIC int
 xfs_inactive_ifree(
 	struct xfs_inode *ip)
 {
-	struct xfs_defer_ops	dfops;
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
@@ -1806,7 +1784,6 @@ xfs_inactive_ifree(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops);
 	error = xfs_ifree(tp, ip);
 	if (error) {
 		/*
@@ -1833,12 +1810,6 @@ xfs_inactive_ifree(
 	 * Just ignore errors at this point.  There is nothing we can do except
 	 * to try to keep going. Make sure it's not a silent error.
 	 */
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error) {
-		xfs_notice(mp, "%s: xfs_defer_finish returned error %d",
-			__func__, error);
-		xfs_defer_cancel(&dfops);
-	}
 	error = xfs_trans_commit(tp);
 	if (error)
 		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
@@ -2569,7 +2540,6 @@ xfs_remove(
 	xfs_trans_t             *tp = NULL;
 	int			is_dir = S_ISDIR(VFS_I(ip)->i_mode);
 	int                     error = 0;
-	struct xfs_defer_ops	dfops;
 	uint			resblks;
 
 	trace_xfs_remove(dp, name);
@@ -2649,11 +2619,10 @@ xfs_remove(
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_defer_init(tp, &dfops);
 	error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
 	if (error) {
 		ASSERT(error != -ENOENT);
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 	}
 
 	/*
@@ -2664,10 +2633,6 @@ xfs_remove(
 	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, &dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto std_return;
@@ -2677,8 +2642,6 @@ xfs_remove(
 
 	return 0;
 
- out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
  out_trans_cancel:
 	xfs_trans_cancel(tp);
  std_return:
@@ -2740,9 +2703,6 @@ static int
 xfs_finish_rename(
 	struct xfs_trans	*tp)
 {
-	struct xfs_defer_ops	*dfops = tp->t_dfops;
-	int			error;
-
 	/*
 	 * If this is a synchronous mount, make sure that the rename transaction
 	 * goes to disk before returning to the user.
@@ -2750,13 +2710,6 @@ xfs_finish_rename(
 	if (tp->t_mountp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
 
-	error = xfs_defer_finish(&tp, dfops);
-	if (error) {
-		xfs_defer_cancel(dfops);
-		xfs_trans_cancel(tp);
-		return error;
-	}
-
 	return xfs_trans_commit(tp);
 }
 
@@ -2869,7 +2822,6 @@ xfs_cross_rename(
 	return xfs_finish_rename(tp);
 
 out_trans_abort:
-	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
@@ -2924,7 +2876,6 @@ xfs_rename(
 {
 	struct xfs_mount	*mp = src_dp->i_mount;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
 	struct xfs_inode	*wip = NULL;		/* whiteout inode */
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
 	int			num_inodes = __XFS_SORT_INODES;
@@ -3006,8 +2957,6 @@ xfs_rename(
 		goto out_trans_cancel;
 	}
 
-	xfs_defer_init(tp, &dfops);
-
 	/* RENAME_EXCHANGE is unique from here on. */
 	if (flags & RENAME_EXCHANGE)
 		return xfs_cross_rename(tp, src_dp, src_name, src_ip,
@@ -3035,7 +2984,7 @@ xfs_rename(
 		error = xfs_dir_createname(tp, target_dp, target_name,
 					   src_ip->i_ino, spaceres);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		xfs_trans_ichgtime(tp, target_dp,
 					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -3043,7 +2992,7 @@ xfs_rename(
 		if (new_parent && src_is_directory) {
 			error = xfs_bumplink(tp, target_dp);
 			if (error)
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 		}
 	} else { /* target_ip != NULL */
 		/*
@@ -3074,7 +3023,7 @@ xfs_rename(
 		error = xfs_dir_replace(tp, target_dp, target_name,
 					src_ip->i_ino, spaceres);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		xfs_trans_ichgtime(tp, target_dp,
 					XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
@@ -3085,7 +3034,7 @@ xfs_rename(
 		 */
 		error = xfs_droplink(tp, target_ip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		if (src_is_directory) {
 			/*
@@ -3093,7 +3042,7 @@ xfs_rename(
 			 */
 			error = xfs_droplink(tp, target_ip);
 			if (error)
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 		}
 	} /* target_ip != NULL */
 
@@ -3109,7 +3058,7 @@ xfs_rename(
 					target_dp->i_ino, spaceres);
 		ASSERT(error != -EEXIST);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -3135,7 +3084,7 @@ xfs_rename(
 		 */
 		error = xfs_droplink(tp, src_dp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -3150,7 +3099,7 @@ xfs_rename(
 		error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
 					   spaceres);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	/*
 	 * For whiteouts, we need to bump the link count on the whiteout inode.
@@ -3164,10 +3113,10 @@ xfs_rename(
 		ASSERT(VFS_I(wip)->i_nlink == 0);
 		error = xfs_bumplink(tp, wip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		error = xfs_iunlink_remove(tp, wip);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
 
 		/*
@@ -3188,8 +3137,6 @@ xfs_rename(
 		IRELE(wip);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(&dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_wip:
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 756694219f77..8e8ca9f03f0e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -157,7 +157,6 @@ xfs_iomap_write_direct(
 	int		quota_flag;
 	int		rt;
 	xfs_trans_t	*tp;
-	struct xfs_defer_ops dfops;
 	uint		qblocks, resblks, resrtextents;
 	int		error;
 	int		lockmode;
@@ -253,20 +252,15 @@ xfs_iomap_write_direct(
 	 * From this point onwards we overwrite the imap pointer that the
 	 * caller gave to us.
 	 */
-	xfs_defer_init(tp, &dfops);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 				bmapi_flags, resblks, imap, &nimaps);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_res_cancel;
 
 	/*
 	 * Complete the transaction
 	 */
-	error = xfs_defer_finish(&tp, tp->t_dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;
@@ -286,8 +280,7 @@ out_unlock:
 	xfs_iunlock(ip, lockmode);
 	return error;
 
-out_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
+out_res_cancel:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)qblocks, 0, quota_flag);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
@@ -663,7 +656,6 @@ xfs_iomap_write_allocate(
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb, last_block;
 	xfs_fileoff_t	end_fsb, map_start_fsb;
-	struct xfs_defer_ops	dfops;
 	xfs_filblks_t	count_fsb;
 	xfs_trans_t	*tp;
 	int		nimaps;
@@ -713,8 +705,6 @@ xfs_iomap_write_allocate(
 			xfs_ilock(ip, XFS_ILOCK_EXCL);
 			xfs_trans_ijoin(tp, ip, 0);
 
-			xfs_defer_init(tp, &dfops);
-
 			/*
 			 * it is possible that the extents have changed since
 			 * we did the read call as we dropped the ilock for a
@@ -772,10 +762,6 @@ xfs_iomap_write_allocate(
 			if (error)
 				goto trans_cancel;
 
-			error = xfs_defer_finish(&tp, tp->t_dfops);
-			if (error)
-				goto trans_cancel;
-
 			error = xfs_trans_commit(tp);
 			if (error)
 				goto error0;
@@ -806,7 +792,6 @@ xfs_iomap_write_allocate(
 	}
 
 trans_cancel:
-	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_cancel(tp);
 error0:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -827,7 +812,6 @@ xfs_iomap_write_unwritten(
 	int		nimaps;
 	xfs_trans_t	*tp;
 	xfs_bmbt_irec_t imap;
-	struct xfs_defer_ops dfops;
 	struct inode	*inode = VFS_I(ip);
 	xfs_fsize_t	i_size;
 	uint		resblks;
@@ -872,7 +856,6 @@ xfs_iomap_write_unwritten(
 		/*
 		 * Modify the unwritten extent state of the buffer.
 		 */
-		xfs_defer_init(tp, &dfops);
 		nimaps = 1;
 		error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
 					XFS_BMAPI_CONVERT, resblks, &imap,
@@ -896,10 +879,6 @@ xfs_iomap_write_unwritten(
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
-		error = xfs_defer_finish(&tp, tp->t_dfops);
-		if (error)
-			goto error_on_bmapi_transaction;
-
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
@@ -923,7 +902,6 @@ xfs_iomap_write_unwritten(
 	return 0;
 
 error_on_bmapi_transaction:
-	xfs_defer_cancel(tp->t_dfops);
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 704b57a8b99e..2eac22bfad6a 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -813,7 +813,6 @@ xfs_setattr_size(
 	struct inode		*inode = VFS_I(ip);
 	xfs_off_t		oldsize, newsize;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
 	int			error;
 	uint			lock_flags = 0;
 	bool			did_zeroing = false;
@@ -917,7 +916,6 @@ xfs_setattr_size(
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
 	if (error)
 		return error;
-	xfs_defer_init(tp, &dfops);
 
 	lock_flags |= XFS_ILOCK_EXCL;
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 958e9b96dc6a..265e1f561157 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4857,15 +4857,7 @@ xlog_finish_defer_ops(
 	/* transfer all collected dfops to this transaction */
 	xfs_defer_move(tp->t_dfops, dfops);
 
-	error = xfs_defer_finish(&tp, tp->t_dfops);
-	if (error)
-		goto out_cancel;
-
 	return xfs_trans_commit(tp);
-
-out_cancel:
-	xfs_trans_cancel(tp);
-	return error;
 }
 
 /*
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index df0783303887..c07c5a39d516 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -214,7 +214,6 @@ xfs_qm_scall_trunc_qfile(
 {
 	struct xfs_inode	*ip;
 	struct xfs_trans	*tp;
-	struct xfs_defer_ops	dfops;
 	int			error;
 
 	if (ino == NULLFSINO)
@@ -231,7 +230,6 @@ xfs_qm_scall_trunc_qfile(
 		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 		goto out_put;
 	}
-	xfs_defer_init(tp, &dfops);
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 04c25ee6b6f8..a653739c9fb2 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -364,7 +364,6 @@ xfs_reflink_allocate_cow(
 	xfs_fileoff_t		offset_fsb = imap->br_startoff;
 	xfs_filblks_t		count_fsb = imap->br_blockcount;
 	struct xfs_bmbt_irec	got;
-	struct xfs_defer_ops	dfops;
 	struct xfs_trans	*tp = NULL;
 	int			nimaps, error = 0;
 	bool			trimmed;
@@ -424,7 +423,6 @@ retry:
 
 	xfs_trans_ijoin(tp, ip, 0);
 
-	xfs_defer_init(tp, &dfops);
 	nimaps = 1;
 
 	/* Allocate the entire reservation as unwritten blocks. */
@@ -432,15 +430,11 @@ retry:
 			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC,
 			resblks, imap, &nimaps);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 
 	xfs_inode_set_cowblocks_tag(ip);
 
 	/* Finish up. */
-	error = xfs_defer_finish(&tp, tp->t_dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		return error;
@@ -453,8 +447,7 @@ retry:
 		return -ENOSPC;
 convert:
 	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb);
-out_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
+out_trans_cancel:
 	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
 			XFS_QMOPT_RES_REGBLKS);
 out:
@@ -624,7 +617,6 @@ xfs_reflink_end_cow(
 	struct xfs_trans		*tp;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
-	struct xfs_defer_ops		dfops;
 	int				error;
 	unsigned int			resblks;
 	xfs_filblks_t			rlen;
@@ -691,11 +683,11 @@ xfs_reflink_end_cow(
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */
-		xfs_defer_init(tp, &dfops);
+		ASSERT(tp->t_dfops && tp->t_firstblock == NULLFSBLOCK);
 		rlen = del.br_blockcount;
 		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Trim the extent to whatever got unmapped. */
 		if (rlen) {
@@ -708,13 +700,13 @@ xfs_reflink_end_cow(
 		error = xfs_refcount_free_cow_extent(tp->t_mountp, tp->t_dfops,
 				del.br_startblock, del.br_blockcount);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
 		error = xfs_bmap_map_extent(tp->t_mountp, tp->t_dfops, ip,
 					    &del);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Charge this new data fork mapping to the on-disk quota. */
 		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_DELBCOUNT,
@@ -726,7 +718,7 @@ xfs_reflink_end_cow(
 		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 		if (!xfs_iext_get_extent(ifp, &icur, &got))
 			break;
 		continue;
@@ -741,8 +733,6 @@ prev_extent:
 		goto out;
 	return 0;
 
-out_defer:
-	xfs_defer_cancel(tp->t_dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -998,7 +988,6 @@ xfs_reflink_remap_extent(
 	bool			real_extent = xfs_bmap_is_real_extent(irec);
 	struct xfs_trans	*tp;
 	unsigned int		resblks;
-	struct xfs_defer_ops	dfops;
 	struct xfs_bmbt_irec	uirec;
 	xfs_filblks_t		rlen;
 	xfs_filblks_t		unmap_len;
@@ -1039,10 +1028,10 @@ xfs_reflink_remap_extent(
 	/* Unmap the old blocks in the data fork. */
 	rlen = unmap_len;
 	while (rlen) {
-		xfs_defer_init(tp, &dfops);
+		ASSERT(tp->t_dfops && tp->t_firstblock == NULLFSBLOCK);
 		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/*
 		 * Trim the extent to whatever got unmapped.
@@ -1063,12 +1052,12 @@ xfs_reflink_remap_extent(
 		/* Update the refcount tree */
 		error = xfs_refcount_increase_extent(mp, tp->t_dfops, &uirec);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
 		error = xfs_bmap_map_extent(mp, tp->t_dfops, ip, &uirec);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 
 		/* Update quota accounting. */
 		xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT,
@@ -1090,7 +1079,7 @@ next_extent:
 		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_defer_finish(&tp, tp->t_dfops);
 		if (error)
-			goto out_defer;
+			goto out_cancel;
 	}
 
 	error = xfs_trans_commit(tp);
@@ -1099,8 +1088,6 @@ next_extent:
 		goto out;
 	return 0;
 
-out_defer:
-	xfs_defer_cancel(tp->t_dfops);
 out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index bc471d42a968..86d7d2f76226 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -761,7 +761,6 @@ xfs_growfs_rt_alloc(
 	struct xfs_buf		*bp;	/* temporary buffer for zeroing */
 	xfs_daddr_t		d;		/* disk block address */
 	int			error;		/* error return value */
-	struct xfs_defer_ops	dfops;		/* list of freed blocks */
 	xfs_fsblock_t		fsbno;		/* filesystem block for bno */
 	struct xfs_bmbt_irec	map;		/* block map output */
 	int			nmap;		/* number of block maps */
@@ -786,7 +785,6 @@ xfs_growfs_rt_alloc(
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
-		xfs_defer_init(tp, &dfops);
 		/*
 		 * Allocate blocks to the bitmap file.
 		 */
@@ -797,13 +795,10 @@ xfs_growfs_rt_alloc(
 		if (!error && nmap < 1)
 			error = -ENOSPC;
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 		/*
 		 * Free any blocks freed up in the transaction, then commit.
 		 */
-		error = xfs_defer_finish(&tp, tp->t_dfops);
-		if (error)
-			goto out_bmap_cancel;
 		error = xfs_trans_commit(tp);
 		if (error)
 			return error;
@@ -853,8 +848,6 @@ xfs_growfs_rt_alloc(
 
 	return 0;
 
-out_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 	return error;
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index d1ab0afa2723..ce801aedbcdc 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -163,7 +163,6 @@ xfs_symlink(
 	struct xfs_inode	*ip = NULL;
 	int			error = 0;
 	int			pathlen;
-	struct xfs_defer_ops	dfops;
 	bool                    unlock_dp_on_error = false;
 	xfs_fileoff_t		first_fsb;
 	xfs_filblks_t		fs_blocks;
@@ -241,12 +240,6 @@ xfs_symlink(
 	if (error)
 		goto out_trans_cancel;
 
-	/*
-	 * Initialize the bmap freelist prior to calling either
-	 * bmapi or the directory create code.
-	 */
-	xfs_defer_init(tp, &dfops);
-
 	/*
 	 * Allocate an inode for the symlink.
 	 */
@@ -290,7 +283,7 @@ xfs_symlink(
 		error = xfs_bmapi_write(tp, ip, first_fsb, fs_blocks,
 				  XFS_BMAPI_METADATA, resblks, mval, &nmaps);
 		if (error)
-			goto out_bmap_cancel;
+			goto out_trans_cancel;
 
 		if (resblks)
 			resblks -= fs_blocks;
@@ -308,7 +301,7 @@ xfs_symlink(
 					       BTOBB(byte_cnt), 0);
 			if (!bp) {
 				error = -ENOMEM;
-				goto out_bmap_cancel;
+				goto out_trans_cancel;
 			}
 			bp->b_ops = &xfs_symlink_buf_ops;
 
@@ -337,7 +330,7 @@ xfs_symlink(
 	 */
 	error = xfs_dir_createname(tp, dp, link_name, ip->i_ino, resblks);
 	if (error)
-		goto out_bmap_cancel;
+		goto out_trans_cancel;
 	xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
@@ -350,10 +343,6 @@ xfs_symlink(
 		xfs_trans_set_sync(tp);
 	}
 
-	error = xfs_defer_finish(&tp, tp->t_dfops);
-	if (error)
-		goto out_bmap_cancel;
-
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_release_inode;
@@ -365,8 +354,6 @@ xfs_symlink(
 	*ipp = ip;
 	return 0;
 
-out_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_inode:
@@ -399,7 +386,6 @@ xfs_inactive_symlink_rmt(
 	xfs_buf_t	*bp;
 	int		done;
 	int		error;
-	struct xfs_defer_ops	dfops;
 	int		i;
 	xfs_mount_t	*mp;
 	xfs_bmbt_irec_t	mval[XFS_SYMLINK_MAPS];
@@ -438,7 +424,6 @@ xfs_inactive_symlink_rmt(
 	 * Find the block(s) so we can inval and unmap them.
 	 */
 	done = 0;
-	xfs_defer_init(tp, &dfops);
 	nmaps = ARRAY_SIZE(mval);
 	error = xfs_bmapi_read(ip, 0, xfs_symlink_blocks(mp, size),
 				mval, &nmaps, 0);
@@ -453,7 +438,7 @@ xfs_inactive_symlink_rmt(
 			XFS_FSB_TO_BB(mp, mval[i].br_blockcount), 0);
 		if (!bp) {
 			error = -ENOMEM;
-			goto error_bmap_cancel;
+			goto error_trans_cancel;
 		}
 		xfs_trans_binval(tp, bp);
 	}
@@ -462,19 +447,14 @@ xfs_inactive_symlink_rmt(
 	 */
 	error = xfs_bunmapi(tp, ip, 0, size, 0, nmaps, &done);
 	if (error)
-		goto error_bmap_cancel;
+		goto error_trans_cancel;
 	ASSERT(done);
-	/*
-	 * Commit the first transaction.  This logs the EFI and the inode.
-	 */
-	xfs_defer_ijoin(tp->t_dfops, ip);
-	error = xfs_defer_finish(&tp, tp->t_dfops);
-	if (error)
-		goto error_bmap_cancel;
 
 	/*
-	 * Commit the transaction containing extent freeing and EFDs.
+	 * Commit the transaction. This first logs the EFI and the inode, then
+	 * rolls and commits the transaction that frees the extents.
 	 */
+	xfs_defer_ijoin(tp->t_dfops, ip);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	error = xfs_trans_commit(tp);
 	if (error) {
@@ -492,8 +472,6 @@ xfs_inactive_symlink_rmt(
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return 0;
 
-error_bmap_cancel:
-	xfs_defer_cancel(tp->t_dfops);
 error_trans_cancel:
 	xfs_trans_cancel(tp);
 error_unlock:
-- 
cgit v1.2.3


From d5cca7eb244d276177a57e42494d479742bbba37 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:14 -0700
Subject: xfs: remove unnecessary dfops init calls in xattr code

Each xfs_defer_init() call in the xattr code uses the internal dfops
reference. In addition, a successful xfs_defer_finish() always
returns with a reset xfs_defer_ops structure.

Given that along with the fact that every xfs_defer_init() call in
the xattr code is followed up by an xfs_defer_finish(), the former
calls are no longer necessary and can be removed.

Note that the xfs_defer_init() call in the remote value copy loop of
xfs_attr_rmtval_set() is not followed by a finish, but the dfops is
unused in this instance.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 8 --------
 fs/xfs/libxfs/xfs_attr_remote.c | 3 ---
 2 files changed, 11 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 66a22c80a0db..3e98f0af389c 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -587,7 +587,6 @@ xfs_attr_leaf_addname(
 		 * Commit that transaction so that the node_addname() call
 		 * can manage its own transactions.
 		 */
-		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
@@ -676,7 +675,6 @@ xfs_attr_leaf_addname(
 		 * If the result is small enough, shrink it all into the inode.
 		 */
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
@@ -741,7 +739,6 @@ xfs_attr_leaf_removename(
 	 * If the result is small enough, shrink it all into the inode.
 	 */
 	if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
@@ -870,7 +867,6 @@ restart:
 			 */
 			xfs_da_state_free(state);
 			state = NULL;
-			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
@@ -897,7 +893,6 @@ restart:
 		 * in the index/blkno/rmtblkno/rmtblkcnt fields and
 		 * in the index2/blkno2/rmtblkno2/rmtblkcnt2 fields.
 		 */
-		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
@@ -995,7 +990,6 @@ restart:
 		 * Check to see if the tree needs to be collapsed.
 		 */
 		if (retval && (state->path.active > 1)) {
-			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
@@ -1120,7 +1114,6 @@ xfs_attr_node_removename(
 	 * Check to see if the tree needs to be collapsed.
 	 */
 	if (retval && (state->path.active > 1)) {
-		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
@@ -1152,7 +1145,6 @@ xfs_attr_node_removename(
 			goto out;
 
 		if ((forkoff = xfs_attr_shortform_allfit(bp, dp))) {
-			xfs_defer_init(args->trans, args->trans->t_dfops);
 			error = xfs_attr3_leaf_to_shortform(bp, args, forkoff);
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 829ab20f0cd7..0fbfb740949e 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -480,7 +480,6 @@ xfs_attr_rmtval_set(
 		 * extent and then crash then the block may not contain the
 		 * correct metadata after log recovery occurs.
 		 */
-		xfs_defer_init(args->trans, args->trans->t_dfops);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
 				  blkcnt, XFS_BMAPI_ATTRFORK, args->total, &map,
@@ -522,7 +521,6 @@ xfs_attr_rmtval_set(
 
 		ASSERT(blkcnt > 0);
 
-		xfs_defer_init(args->trans, args->trans->t_dfops);
 		nmap = 1;
 		error = xfs_bmapi_read(dp, (xfs_fileoff_t)lblkno,
 				       blkcnt, &map, &nmap,
@@ -625,7 +623,6 @@ xfs_attr_rmtval_remove(
 	blkcnt = args->rmtblkcnt;
 	done = 0;
 	while (!done) {
-		xfs_defer_init(args->trans, args->trans->t_dfops);
 		error = xfs_bunmapi(args->trans, args->dp, lblkno, blkcnt,
 				    XFS_BMAPI_ATTRFORK, 1, &done);
 		if (error)
-- 
cgit v1.2.3


From 9e28a242be65b8274742425ca5d146f366205a90 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:15 -0700
Subject: xfs: drop unnecessary xfs_defer_finish() dfops parameter

Every caller of xfs_defer_finish() now passes the transaction and
its associated ->t_dfops. The xfs_defer_ops parameter is therefore
no longer necessary and can be removed.

Since most xfs_defer_finish() callers also have to consider
xfs_defer_cancel() on error, update the latter to also receive the
transaction for consistency. The log recovery code contains an
outlier case that cancels a dfops directly without an available
transaction. Retain an internal wrapper to support this outlier case
for the time being.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 27 +++++++++++++--------------
 fs/xfs/libxfs/xfs_attr_remote.c |  8 ++++----
 fs/xfs/libxfs/xfs_defer.c       |  7 +++----
 fs/xfs/libxfs/xfs_defer.h       |  4 ++--
 fs/xfs/xfs_bmap_util.c          |  4 ++--
 fs/xfs/xfs_dquot.c              |  4 ++--
 fs/xfs/xfs_inode.c              |  4 ++--
 fs/xfs/xfs_log_recover.c        |  2 +-
 fs/xfs/xfs_reflink.c            |  8 ++++----
 fs/xfs/xfs_trans.c              | 13 ++++++++++---
 fs/xfs/xfs_trans.h              |  3 +++
 11 files changed, 46 insertions(+), 38 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 3e98f0af389c..3deb5cdadf08 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -322,7 +322,7 @@ xfs_attr_set(
 		xfs_trans_bhold(args.trans, leaf_bp);
 		xfs_defer_bjoin(args.trans->t_dfops, leaf_bp);
 		xfs_defer_ijoin(args.trans->t_dfops, dp);
-		error = xfs_defer_finish(&args.trans, args.trans->t_dfops);
+		error = xfs_defer_finish(&args.trans);
 		if (error)
 			goto out;
 
@@ -591,7 +591,7 @@ xfs_attr_leaf_addname(
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
 
@@ -680,7 +680,7 @@ xfs_attr_leaf_addname(
 			if (error)
 				goto out_defer_cancel;
 			xfs_defer_ijoin(args->trans->t_dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
 		}
@@ -698,7 +698,7 @@ xfs_attr_leaf_addname(
 	}
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->trans->t_dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -744,13 +744,13 @@ xfs_attr_leaf_removename(
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->trans->t_dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -871,8 +871,7 @@ restart:
 			if (error)
 				goto out_defer_cancel;
 			xfs_defer_ijoin(args->trans->t_dfops, dp);
-			error = xfs_defer_finish(&args->trans,
-						 args->trans->t_dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
 
@@ -897,7 +896,7 @@ restart:
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
 	} else {
@@ -994,7 +993,7 @@ restart:
 			if (error)
 				goto out_defer_cancel;
 			xfs_defer_ijoin(args->trans->t_dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
 		}
@@ -1023,7 +1022,7 @@ out:
 		return error;
 	return retval;
 out_defer_cancel:
-	xfs_defer_cancel(args->trans->t_dfops);
+	xfs_defer_cancel(args->trans);
 	goto out;
 }
 
@@ -1118,7 +1117,7 @@ xfs_attr_node_removename(
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
 		/*
@@ -1150,7 +1149,7 @@ xfs_attr_node_removename(
 			if (error)
 				goto out_defer_cancel;
 			xfs_defer_ijoin(args->trans->t_dfops, dp);
-			error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
 		} else
@@ -1162,7 +1161,7 @@ out:
 	xfs_da_state_free(state);
 	return error;
 out_defer_cancel:
-	xfs_defer_cancel(args->trans->t_dfops);
+	xfs_defer_cancel(args->trans);
 	goto out;
 }
 
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 0fbfb740949e..77ca38586913 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -487,7 +487,7 @@ xfs_attr_rmtval_set(
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, dp);
-		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
 
@@ -555,7 +555,7 @@ xfs_attr_rmtval_set(
 	ASSERT(valuelen == 0);
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->trans->t_dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
 
@@ -628,7 +628,7 @@ xfs_attr_rmtval_remove(
 		if (error)
 			goto out_defer_cancel;
 		xfs_defer_ijoin(args->trans->t_dfops, args->dp);
-		error = xfs_defer_finish(&args->trans, args->trans->t_dfops);
+		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
 
@@ -641,6 +641,6 @@ xfs_attr_rmtval_remove(
 	}
 	return 0;
 out_defer_cancel:
-	xfs_defer_cancel(args->trans->t_dfops);
+	xfs_defer_cancel(args->trans);
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index b63cc9e730da..cbee0a86c978 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -342,9 +342,9 @@ xfs_defer_reset(
  */
 int
 xfs_defer_finish(
-	struct xfs_trans		**tp,
-	struct xfs_defer_ops		*dop)
+	struct xfs_trans		**tp)
 {
+	struct xfs_defer_ops		*dop = (*tp)->t_dfops;
 	struct xfs_defer_pending	*dfp;
 	struct list_head		*li;
 	struct list_head		*n;
@@ -353,7 +353,6 @@ xfs_defer_finish(
 	void				(*cleanup_fn)(struct xfs_trans *, void *, int);
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
-	ASSERT((*tp)->t_dfops == dop);
 
 	trace_xfs_defer_finish((*tp)->t_mountp, dop, _RET_IP_);
 
@@ -454,7 +453,7 @@ out:
  * Free up any items left in the list.
  */
 void
-xfs_defer_cancel(
+__xfs_defer_cancel(
 	struct xfs_defer_ops		*dop)
 {
 	struct xfs_defer_pending	*dfp;
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 35507ca9a148..56f927803940 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -48,8 +48,8 @@ enum xfs_defer_ops_type {
 
 void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
 		struct list_head *h);
-int xfs_defer_finish(struct xfs_trans **tp, struct xfs_defer_ops *dop);
-void xfs_defer_cancel(struct xfs_defer_ops *dop);
+int xfs_defer_finish(struct xfs_trans **tp);
+void __xfs_defer_cancel(struct xfs_defer_ops *dop);
 void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index ddb5f1200d3d..c32ec17048f5 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1624,7 +1624,7 @@ xfs_swap_extent_rmap(
 				goto out_defer;
 
 			xfs_defer_ijoin(tp->t_dfops, ip);
-			error = xfs_defer_finish(tpp, tp->t_dfops);
+			error = xfs_defer_finish(tpp);
 			tp = *tpp;
 			if (error)
 				goto out_defer;
@@ -1645,7 +1645,7 @@ xfs_swap_extent_rmap(
 	return 0;
 
 out_defer:
-	xfs_defer_cancel(tp->t_dfops);
+	xfs_defer_cancel(tp);
 out:
 	trace_xfs_swap_extent_rmap_error(ip, error, _RET_IP_);
 	tip->i_d.di_flags2 = tip_flags2;
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index a57d5e8c3118..da5c55cec966 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -368,7 +368,7 @@ xfs_dquot_disk_alloc(
 		xfs_trans_brelse(tp, bp);
 		goto error1;
 	}
-	error = xfs_defer_finish(tpp, tp->t_dfops);
+	error = xfs_defer_finish(tpp);
 	tp = *tpp;
 	if (error) {
 		xfs_buf_relse(bp);
@@ -378,7 +378,7 @@ xfs_dquot_disk_alloc(
 	return 0;
 
 error1:
-	xfs_defer_cancel(tp->t_dfops);
+	xfs_defer_cancel(tp);
 error0:
 	return error;
 }
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c47183a2f167..0e4bd559a6a7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1570,7 +1570,7 @@ xfs_itruncate_extents_flags(
 		 * reservation and commit the old transaction.
 		 */
 		xfs_defer_ijoin(tp->t_dfops, ip);
-		error = xfs_defer_finish(&tp, tp->t_dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_bmap_cancel;
 
@@ -1606,7 +1606,7 @@ out_bmap_cancel:
 	 * the transaction can be properly aborted.  We just need to make sure
 	 * we're not holding any resources that we were not when we came in.
 	 */
-	xfs_defer_cancel(tp->t_dfops);
+	xfs_defer_cancel(tp);
 	goto out;
 }
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 265e1f561157..94908a4019e1 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4946,7 +4946,7 @@ out:
 	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->ail_lock);
 	if (error)
-		xfs_defer_cancel(&dfops);
+		__xfs_defer_cancel(&dfops);
 	else
 		error = xlog_finish_defer_ops(log->l_mp, &dfops);
 
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index a653739c9fb2..68b6921dc3f6 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -518,9 +518,9 @@ xfs_reflink_cancel_cow_blocks(
 
 			/* Roll the transaction */
 			xfs_defer_ijoin((*tpp)->t_dfops, ip);
-			error = xfs_defer_finish(tpp, (*tpp)->t_dfops);
+			error = xfs_defer_finish(tpp);
 			if (error) {
-				xfs_defer_cancel((*tpp)->t_dfops);
+				xfs_defer_cancel(*tpp);
 				break;
 			}
 
@@ -716,7 +716,7 @@ xfs_reflink_end_cow(
 		xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
 
 		xfs_defer_ijoin(tp->t_dfops, ip);
-		error = xfs_defer_finish(&tp, tp->t_dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_cancel;
 		if (!xfs_iext_get_extent(ifp, &icur, &got))
@@ -1077,7 +1077,7 @@ xfs_reflink_remap_extent(
 next_extent:
 		/* Process all the deferred stuff. */
 		xfs_defer_ijoin(tp->t_dfops, ip);
-		error = xfs_defer_finish(&tp, tp->t_dfops);
+		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_cancel;
 	}
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 412c8d236c71..cd553aa9ecb0 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -933,9 +933,9 @@ __xfs_trans_commit(
 
 	/* finish deferred items on final commit */
 	if (!regrant && tp->t_dfops) {
-		error = xfs_defer_finish(&tp, tp->t_dfops);
+		error = xfs_defer_finish(&tp);
 		if (error) {
-			xfs_defer_cancel(tp->t_dfops);
+			xfs_defer_cancel(tp);
 			goto out_unreserve;
 		}
 	}
@@ -1030,7 +1030,7 @@ xfs_trans_cancel(
 	trace_xfs_trans_cancel(tp, _RET_IP_);
 
 	if (tp->t_dfops)
-		xfs_defer_cancel(tp->t_dfops);
+		xfs_defer_cancel(tp);
 
 	/*
 	 * See if the caller is relying on us to shut down the
@@ -1111,3 +1111,10 @@ xfs_trans_roll(
 	tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
 	return xfs_trans_reserve(*tpp, &tres, 0, 0);
 }
+
+void
+xfs_defer_cancel(
+	struct xfs_trans	*tp)
+{
+	__xfs_defer_cancel(tp->t_dfops);
+}
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index dc79e3c1d3e8..5170e89bec02 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -214,6 +214,9 @@ xfs_trans_read_buf(
 				      flags, bpp, ops);
 }
 
+/* cancel dfops associated with a transaction */
+void xfs_defer_cancel(struct xfs_trans *);
+
 struct xfs_buf	*xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
-- 
cgit v1.2.3


From b277c37f43dd387f7430a2186deda0e58c943087 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 24 Jul 2018 13:43:15 -0700
Subject: xfs: bypass final dfops roll in trans commit path

Once xfs_defer_finish() has completed all deferred operations, it
checks the dirty state of the transaction and rolls it once more to
return a clean transaction for the caller. This primarily to cover
the case where repeated xfs_defer_finish() calls are made in a loop
and we need to make sure that the caller starts the next iteration
with a clean transaction. Otherwise we risk transaction reservation
overrun.

This final transaction roll is not required in the transaction
commit path, however, because the transaction is immediately
committed and freed after dfops completion. Refactor the final roll
into a separate helper such that we can avoid it in the transaction
commit path.  Lift the dfops reset as well so dfops remains valid
until after the last call to xfs_defer_trans_roll(). The reset is
also unnecessary in the transaction commit path because the
transaction is about to complete.

This eliminates unnecessary regrants of transactions where the
associated transaction roll can be replaced by a transaction commit.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 38 +++++++++++++++++++++++++-------------
 fs/xfs/libxfs/xfs_defer.h |  1 +
 fs/xfs/xfs_trans.c        |  2 +-
 3 files changed, 27 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index cbee0a86c978..a5f7dc18a62f 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -341,7 +341,7 @@ xfs_defer_reset(
  * If an inode is provided, relog it to the new transaction.
  */
 int
-xfs_defer_finish(
+xfs_defer_finish_noroll(
 	struct xfs_trans		**tp)
 {
 	struct xfs_defer_ops		*dop = (*tp)->t_dfops;
@@ -430,25 +430,37 @@ xfs_defer_finish(
 			cleanup_fn(*tp, state, error);
 	}
 
-	/*
-	 * Roll the transaction once more to avoid returning to the caller
-	 * with a dirty transaction.
-	 */
-	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
-		error = xfs_defer_trans_roll(tp);
-		dop = (*tp)->t_dfops;
-	}
 out:
-	if (error) {
+	if (error)
 		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
-	} else {
+	 else
 		trace_xfs_defer_finish_done((*tp)->t_mountp, dop, _RET_IP_);
-		xfs_defer_reset(dop);
-	}
 
 	return error;
 }
 
+int
+xfs_defer_finish(
+	struct xfs_trans	**tp)
+{
+	int			error;
+
+	/*
+	 * Finish and roll the transaction once more to avoid returning to the
+	 * caller with a dirty transaction.
+	 */
+	error = xfs_defer_finish_noroll(tp);
+	if (error)
+		return error;
+	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
+		error = xfs_defer_trans_roll(tp);
+		if (error)
+			return error;
+	}
+	xfs_defer_reset((*tp)->t_dfops);
+	return 0;
+}
+
 /*
  * Free up any items left in the list.
  */
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 56f927803940..85c41fe4dbae 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -48,6 +48,7 @@ enum xfs_defer_ops_type {
 
 void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
 		struct list_head *h);
+int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
 void __xfs_defer_cancel(struct xfs_defer_ops *dop);
 void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index cd553aa9ecb0..7bf5c1202719 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -933,7 +933,7 @@ __xfs_trans_commit(
 
 	/* finish deferred items on final commit */
 	if (!regrant && tp->t_dfops) {
-		error = xfs_defer_finish(&tp);
+		error = xfs_defer_finish_noroll(&tp);
 		if (error) {
 			xfs_defer_cancel(tp);
 			goto out_unreserve;
-- 
cgit v1.2.3


From 89c3e8cf3c266d61347abcc412b9330d81da794b Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 25 Jul 2018 12:51:48 -0700
Subject: xfs: kill IHOLD

Nobody uses this macro, get rid of it.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/xfs_inode.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index b1f0e8394f3b..c43abf4ea3fc 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -483,13 +483,6 @@ static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
 	xfs_finish_inode_setup(ip);
 }
 
-#define IHOLD(ip) \
-do { \
-	ASSERT(atomic_read(&VFS_I(ip)->i_count) > 0) ; \
-	ihold(VFS_I(ip)); \
-	trace_xfs_ihold(ip, _THIS_IP_); \
-} while (0)
-
 #define IRELE(ip) \
 do { \
 	trace_xfs_irele(ip, _THIS_IP_); \
-- 
cgit v1.2.3


From 44a8736bd20a08e1adbf479d11f8198a1243958d Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 25 Jul 2018 12:52:32 -0700
Subject: xfs: clean up IRELE/iput callsites

Replace the IRELE macro with a proper function so that we can do proper
typechecking and so that we can stop open-coding iput in scrub, which
means that we'll be able to ftrace inode lifetimes going through scrub
correctly.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/common.c    |  2 +-
 fs/xfs/scrub/dir.c       |  2 +-
 fs/xfs/scrub/parent.c    |  6 +++---
 fs/xfs/scrub/scrub.c     |  2 +-
 fs/xfs/xfs_bmap_item.c   |  4 ++--
 fs/xfs/xfs_export.c      |  2 +-
 fs/xfs/xfs_filestream.c  |  4 ++--
 fs/xfs/xfs_icache.c      |  4 ++--
 fs/xfs/xfs_inode.c       | 17 +++++++++++++----
 fs/xfs/xfs_inode.h       |  6 +-----
 fs/xfs/xfs_iops.c        |  4 ++--
 fs/xfs/xfs_itable.c      |  2 +-
 fs/xfs/xfs_log_recover.c |  4 ++--
 fs/xfs/xfs_mount.c       |  4 ++--
 fs/xfs/xfs_qm.c          | 22 +++++++++++-----------
 fs/xfs/xfs_qm_syscalls.c |  8 ++++----
 fs/xfs/xfs_quotaops.c    |  2 +-
 fs/xfs/xfs_rtalloc.c     |  6 +++---
 fs/xfs/xfs_symlink.c     |  2 +-
 19 files changed, 54 insertions(+), 49 deletions(-)

diff --git a/fs/xfs/scrub/common.c b/fs/xfs/scrub/common.c
index baac08304a5a..346b02abccf7 100644
--- a/fs/xfs/scrub/common.c
+++ b/fs/xfs/scrub/common.c
@@ -711,7 +711,7 @@ xchk_get_inode(
 		return error;
 	}
 	if (VFS_I(ip)->i_generation != sc->sm->sm_gen) {
-		iput(VFS_I(ip));
+		xfs_irele(ip);
 		return -ENOENT;
 	}
 
diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c
index f58709052b03..cd3e4d768a18 100644
--- a/fs/xfs/scrub/dir.c
+++ b/fs/xfs/scrub/dir.c
@@ -87,7 +87,7 @@ xchk_dir_check_ftype(
 			xfs_mode_to_ftype(VFS_I(ip)->i_mode));
 	if (ino_dtype != dtype)
 		xchk_fblock_set_corrupt(sdc->sc, XFS_DATA_FORK, offset);
-	iput(VFS_I(ip));
+	xfs_irele(ip);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/parent.c b/fs/xfs/scrub/parent.c
index aacb0284c48a..1c9d7c7f64f5 100644
--- a/fs/xfs/scrub/parent.c
+++ b/fs/xfs/scrub/parent.c
@@ -230,11 +230,11 @@ xchk_parent_validate(
 
 	/* Drat, parent changed.  Try again! */
 	if (dnum != dp->i_ino) {
-		iput(VFS_I(dp));
+		xfs_irele(dp);
 		*try_again = true;
 		return 0;
 	}
-	iput(VFS_I(dp));
+	xfs_irele(dp);
 
 	/*
 	 * '..' didn't change, so check that there was only one entry
@@ -247,7 +247,7 @@ xchk_parent_validate(
 out_unlock:
 	xfs_iunlock(dp, XFS_IOLOCK_SHARED);
 out_rele:
-	iput(VFS_I(dp));
+	xfs_irele(dp);
 out:
 	return error;
 }
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 5956b8073e2f..6efb926f3cf8 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -183,7 +183,7 @@ xchk_teardown(
 			xfs_iunlock(sc->ip, sc->ilock_flags);
 		if (sc->ip != ip_in &&
 		    !xfs_internal_inum(sc->mp, sc->ip->i_ino))
-			iput(VFS_I(sc->ip));
+			xfs_irele(sc->ip);
 		sc->ip = NULL;
 	}
 	if (sc->has_quotaofflock)
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index bc5eb2e0ab0c..e1d6c127b07d 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -497,7 +497,7 @@ xfs_bui_recover(
 	xfs_defer_move(dfops, tp->t_dfops);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	IRELE(ip);
+	xfs_irele(ip);
 
 	return error;
 
@@ -506,7 +506,7 @@ err_inode:
 	xfs_trans_cancel(tp);
 	if (ip) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 	return error;
 }
diff --git a/fs/xfs/xfs_export.c b/fs/xfs/xfs_export.c
index 3cf4682e2510..f2284ceb129f 100644
--- a/fs/xfs/xfs_export.c
+++ b/fs/xfs/xfs_export.c
@@ -150,7 +150,7 @@ xfs_nfs_get_inode(
 	}
 
 	if (VFS_I(ip)->i_generation != generation) {
-		IRELE(ip);
+		xfs_irele(ip);
 		return ERR_PTR(-ESTALE);
 	}
 
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 56a3999cefae..212173c62588 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -340,7 +340,7 @@ xfs_filestream_lookup_ag(
 	if (xfs_filestream_pick_ag(pip, startag, &ag, 0, 0))
 		ag = NULLAGNUMBER;
 out:
-	IRELE(pip);
+	xfs_irele(pip);
 	return ag;
 }
 
@@ -389,7 +389,7 @@ xfs_filestream_new_ag(
 	if (mru)
 		xfs_fstrm_free_func(mp, mru);
 
-	IRELE(pip);
+	xfs_irele(pip);
 exit:
 	if (*agp == NULLAGNUMBER)
 		*agp = 0;
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 47f417d20a30..8de94ecd73ae 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -716,7 +716,7 @@ xfs_icache_inode_is_allocated(
 		return error;
 
 	*inuse = !!(VFS_I(ip)->i_mode);
-	IRELE(ip);
+	xfs_irele(ip);
 	return 0;
 }
 
@@ -856,7 +856,7 @@ restart:
 			    xfs_iflags_test(batch[i], XFS_INEW))
 				xfs_inew_wait(batch[i]);
 			error = execute(batch[i], flags, args);
-			IRELE(batch[i]);
+			xfs_irele(batch[i]);
 			if (error == -EAGAIN) {
 				skipped++;
 				continue;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 0e4bd559a6a7..64c694d2b2a5 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1276,7 +1276,7 @@ xfs_create(
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -1371,7 +1371,7 @@ xfs_create_tmpfile(
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
@@ -3134,14 +3134,14 @@ xfs_rename(
 
 	error = xfs_finish_rename(tp);
 	if (wip)
-		IRELE(wip);
+		xfs_irele(wip);
 	return error;
 
 out_trans_cancel:
 	xfs_trans_cancel(tp);
 out_release_wip:
 	if (wip)
-		IRELE(wip);
+		xfs_irele(wip);
 	return error;
 }
 
@@ -3597,3 +3597,12 @@ xfs_iflush_int(
 corrupt_out:
 	return -EFSCORRUPTED;
 }
+
+/* Release an inode. */
+void
+xfs_irele(
+	struct xfs_inode	*ip)
+{
+	trace_xfs_irele(ip, _RET_IP_);
+	iput(VFS_I(ip));
+}
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index c43abf4ea3fc..8db34d6f2835 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -483,11 +483,7 @@ static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
 	xfs_finish_inode_setup(ip);
 }
 
-#define IRELE(ip) \
-do { \
-	trace_xfs_irele(ip, _THIS_IP_); \
-	iput(VFS_I(ip)); \
-} while (0)
+void xfs_irele(struct xfs_inode *ip);
 
 extern struct kmem_zone	*xfs_inode_zone;
 
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 2eac22bfad6a..0ef5ad7fb851 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -209,7 +209,7 @@ xfs_generic_create(
 	xfs_finish_inode_setup(ip);
 	if (!tmpfile)
 		xfs_cleanup_inode(dir, inode, dentry);
-	iput(inode);
+	xfs_irele(ip);
 	goto out_free_acl;
 }
 
@@ -391,7 +391,7 @@ xfs_vn_symlink(
  out_cleanup_inode:
 	xfs_finish_inode_setup(cip);
 	xfs_cleanup_inode(dir, inode, dentry);
-	iput(inode);
+	xfs_irele(cip);
  out:
 	return error;
 }
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 65810827a8d0..e9508ba01ed1 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -114,7 +114,7 @@ xfs_bulkstat_one_int(
 		break;
 	}
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	IRELE(ip);
+	xfs_irele(ip);
 
 	error = formatter(buffer, ubsize, ubused, buf);
 	if (!error)
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 94908a4019e1..7776fde9430c 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -5087,11 +5087,11 @@ xlog_recover_process_one_iunlink(
 	 */
 	ip->i_d.di_dmevmask = 0;
 
-	IRELE(ip);
+	xfs_irele(ip);
 	return agino;
 
  fail_iput:
-	IRELE(ip);
+	xfs_irele(ip);
  fail:
 	/*
 	 * We can't read in the inode this bucket points to, or this inode
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 4fb361cde32a..8f739e4d0d1c 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -1039,7 +1039,7 @@ xfs_mountfs(
  out_rtunmount:
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
-	IRELE(rip);
+	xfs_irele(rip);
 	/* Clean out dquots that might be in memory after quotacheck. */
 	xfs_qm_unmount(mp);
 	/*
@@ -1095,7 +1095,7 @@ xfs_unmountfs(
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
 	xfs_rtunmount_inodes(mp);
-	IRELE(mp->m_rootip);
+	xfs_irele(mp->m_rootip);
 
 	/*
 	 * We can potentially deadlock here if we have an inode cluster
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index 9ceb85cce33a..52ed7904df10 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -231,15 +231,15 @@ xfs_qm_unmount_quotas(
 	 */
 	if (mp->m_quotainfo) {
 		if (mp->m_quotainfo->qi_uquotaip) {
-			IRELE(mp->m_quotainfo->qi_uquotaip);
+			xfs_irele(mp->m_quotainfo->qi_uquotaip);
 			mp->m_quotainfo->qi_uquotaip = NULL;
 		}
 		if (mp->m_quotainfo->qi_gquotaip) {
-			IRELE(mp->m_quotainfo->qi_gquotaip);
+			xfs_irele(mp->m_quotainfo->qi_gquotaip);
 			mp->m_quotainfo->qi_gquotaip = NULL;
 		}
 		if (mp->m_quotainfo->qi_pquotaip) {
-			IRELE(mp->m_quotainfo->qi_pquotaip);
+			xfs_irele(mp->m_quotainfo->qi_pquotaip);
 			mp->m_quotainfo->qi_pquotaip = NULL;
 		}
 	}
@@ -1200,12 +1200,12 @@ xfs_qm_dqusage_adjust(
 			goto error0;
 	}
 
-	IRELE(ip);
+	xfs_irele(ip);
 	*res = BULKSTAT_RV_DIDONE;
 	return 0;
 
 error0:
-	IRELE(ip);
+	xfs_irele(ip);
 	*res = BULKSTAT_RV_GIVEUP;
 	return error;
 }
@@ -1575,11 +1575,11 @@ xfs_qm_init_quotainos(
 
 error_rele:
 	if (uip)
-		IRELE(uip);
+		xfs_irele(uip);
 	if (gip)
-		IRELE(gip);
+		xfs_irele(gip);
 	if (pip)
-		IRELE(pip);
+		xfs_irele(pip);
 	return error;
 }
 
@@ -1588,15 +1588,15 @@ xfs_qm_destroy_quotainos(
 	xfs_quotainfo_t	*qi)
 {
 	if (qi->qi_uquotaip) {
-		IRELE(qi->qi_uquotaip);
+		xfs_irele(qi->qi_uquotaip);
 		qi->qi_uquotaip = NULL; /* paranoia */
 	}
 	if (qi->qi_gquotaip) {
-		IRELE(qi->qi_gquotaip);
+		xfs_irele(qi->qi_gquotaip);
 		qi->qi_gquotaip = NULL;
 	}
 	if (qi->qi_pquotaip) {
-		IRELE(qi->qi_pquotaip);
+		xfs_irele(qi->qi_pquotaip);
 		qi->qi_pquotaip = NULL;
 	}
 }
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index c07c5a39d516..b3190890f096 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -190,15 +190,15 @@ xfs_qm_scall_quotaoff(
 	 * Release our quotainode references if we don't need them anymore.
 	 */
 	if ((dqtype & XFS_QMOPT_UQUOTA) && q->qi_uquotaip) {
-		IRELE(q->qi_uquotaip);
+		xfs_irele(q->qi_uquotaip);
 		q->qi_uquotaip = NULL;
 	}
 	if ((dqtype & XFS_QMOPT_GQUOTA) && q->qi_gquotaip) {
-		IRELE(q->qi_gquotaip);
+		xfs_irele(q->qi_gquotaip);
 		q->qi_gquotaip = NULL;
 	}
 	if ((dqtype & XFS_QMOPT_PQUOTA) && q->qi_pquotaip) {
-		IRELE(q->qi_pquotaip);
+		xfs_irele(q->qi_pquotaip);
 		q->qi_pquotaip = NULL;
 	}
 
@@ -251,7 +251,7 @@ xfs_qm_scall_trunc_qfile(
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 out_put:
-	IRELE(ip);
+	xfs_irele(ip);
 	return error;
 }
 
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index 205fbb2a77e4..a7c0c657dfaf 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -45,7 +45,7 @@ xfs_qm_fill_state(
 	tstate->ino_warnlimit = q->qi_iwarnlimit;
 	tstate->rt_spc_warnlimit = q->qi_rtbwarnlimit;
 	if (tempqip)
-		IRELE(ip);
+		xfs_irele(ip);
 }
 
 /*
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 86d7d2f76226..926ed314ffba 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1207,7 +1207,7 @@ xfs_rtmount_inodes(
 	ASSERT(sbp->sb_rsumino != NULLFSINO);
 	error = xfs_iget(mp, NULL, sbp->sb_rsumino, 0, 0, &mp->m_rsumip);
 	if (error) {
-		IRELE(mp->m_rbmip);
+		xfs_irele(mp->m_rbmip);
 		return error;
 	}
 	ASSERT(mp->m_rsumip != NULL);
@@ -1219,9 +1219,9 @@ xfs_rtunmount_inodes(
 	struct xfs_mount	*mp)
 {
 	if (mp->m_rbmip)
-		IRELE(mp->m_rbmip);
+		xfs_irele(mp->m_rbmip);
 	if (mp->m_rsumip)
-		IRELE(mp->m_rsumip);
+		xfs_irele(mp->m_rsumip);
 }
 
 /*
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index ce801aedbcdc..2bfe7fbbedb2 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -364,7 +364,7 @@ out_release_inode:
 	 */
 	if (ip) {
 		xfs_finish_inode_setup(ip);
-		IRELE(ip);
+		xfs_irele(ip);
 	}
 
 	xfs_qm_dqrele(udqp);
-- 
cgit v1.2.3


From 1c02d502c20809a2a5f71ec16a930a61ed779b81 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@sandeen.net>
Date: Thu, 26 Jul 2018 09:11:27 -0700
Subject: xfs: remove deprecated barrier/nobarrier mount

The barrier mount options have been no-ops and deprecated since

4cf4573 xfs: deprecate barrier/nobarrier mount option

i.e. kernel 4.10 / December 2016, with a stated deprecation schedule
after v4.15.  Should be fair game to remove them now.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 Documentation/filesystems/xfs.txt |  4 ++--
 fs/xfs/xfs_mount.h                |  1 -
 fs/xfs/xfs_super.c                | 34 ++++------------------------------
 3 files changed, 6 insertions(+), 33 deletions(-)

diff --git a/Documentation/filesystems/xfs.txt b/Documentation/filesystems/xfs.txt
index 4d9ff0a7f8e1..a9ae82fb9d13 100644
--- a/Documentation/filesystems/xfs.txt
+++ b/Documentation/filesystems/xfs.txt
@@ -223,8 +223,6 @@ Deprecated Mount Options
 
   Name				Removal Schedule
   ----				----------------
-  barrier			no earlier than v4.15
-  nobarrier			no earlier than v4.15
 
 
 Removed Mount Options
@@ -236,6 +234,8 @@ Removed Mount Options
   ihashsize			v4.0
   irixsgid			v4.0
   osyncisdsync/osyncisosync	v4.0
+  barrier			v4.19
+  nobarrier			v4.19
 
 
 sysctls
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 540353a51478..7964513c3128 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -217,7 +217,6 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_SMALL_INUMS	(1ULL << 14)	/* user wants 32bit inodes */
 #define XFS_MOUNT_32BITINODES	(1ULL << 15)	/* inode32 allocator active */
 #define XFS_MOUNT_NOUUID	(1ULL << 16)	/* ignore uuid during mount */
-#define XFS_MOUNT_BARRIER	(1ULL << 17)
 #define XFS_MOUNT_IKEEP		(1ULL << 18)	/* keep empty inode clusters*/
 #define XFS_MOUNT_SWALLOC	(1ULL << 19)	/* turn on stripe width
 						 * allocation */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index f9f8dc490d3d..d2ebacd5975c 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -65,11 +65,10 @@ enum {
 	Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
 	Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
 	Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
-	Opt_allocsize, Opt_norecovery, Opt_barrier, Opt_nobarrier,
-	Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep,
-	Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams,
-	Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
-	Opt_uquota, Opt_gquota, Opt_pquota,
+	Opt_allocsize, Opt_norecovery, Opt_inode64, Opt_inode32, Opt_ikeep,
+	Opt_noikeep, Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2,
+	Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
+	Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
 	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
 	Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
 };
@@ -118,14 +117,7 @@ static const match_table_t tokens = {
 	{Opt_qnoenforce, "qnoenforce"},	/* same as uqnoenforce */
 	{Opt_discard,	"discard"},	/* Discard unused blocks */
 	{Opt_nodiscard,	"nodiscard"},	/* Do not discard unused blocks */
-
 	{Opt_dax,	"dax"},		/* Enable direct access to bdev pages */
-
-	/* Deprecated mount options scheduled for removal */
-	{Opt_barrier,	"barrier"},	/* use writer barriers for log write and
-					 * unwritten extent conversion */
-	{Opt_nobarrier,	"nobarrier"},	/* .. disable */
-
 	{Opt_err,	NULL},
 };
 
@@ -209,7 +201,6 @@ xfs_parseargs(
 	 * Set some default flags that could be cleared by the mount option
 	 * parsing.
 	 */
-	mp->m_flags |= XFS_MOUNT_BARRIER;
 	mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
 
 	/*
@@ -362,14 +353,6 @@ xfs_parseargs(
 			mp->m_flags |= XFS_MOUNT_DAX;
 			break;
 #endif
-		case Opt_barrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags |= XFS_MOUNT_BARRIER;
-			break;
-		case Opt_nobarrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-			break;
 		default:
 			xfs_warn(mp, "unknown mount option [%s].", p);
 			return -EINVAL;
@@ -487,7 +470,6 @@ xfs_showargs(
 	static struct proc_xfs_info xfs_info_unset[] = {
 		/* the few simple ones we can get from the mount struct */
 		{ XFS_MOUNT_COMPAT_IOSIZE,	",largeio" },
-		{ XFS_MOUNT_BARRIER,		",nobarrier" },
 		{ XFS_MOUNT_SMALL_INUMS,	",inode64" },
 		{ 0, NULL }
 	};
@@ -1278,14 +1260,6 @@ xfs_fs_remount(
 
 		token = match_token(p, tokens, args);
 		switch (token) {
-		case Opt_barrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags |= XFS_MOUNT_BARRIER;
-			break;
-		case Opt_nobarrier:
-			xfs_warn(mp, "%s option is deprecated, ignoring.", p);
-			mp->m_flags &= ~XFS_MOUNT_BARRIER;
-			break;
 		case Opt_inode64:
 			mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
 			mp->m_maxagi = xfs_set_inode_alloc(mp, sbp->sb_agcount);
-- 
cgit v1.2.3


From 74a2c0c466284dd537fe467e4c5e3cb8db52a4b2 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Thu, 26 Jul 2018 18:40:54 +0200
Subject: MIPS: TXx9: remove useless RTC definitions

The RTC definitions were moved to the driver, remove them from the platform
header.

[paul.burton@mips.com:
  - Also remove the unused tx4939_rtcptr which would use struct
    tx4939_rtc_reg if it were ever expanded.]

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20024/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/txx9/tx4939.h | 29 -----------------------------
 1 file changed, 29 deletions(-)

diff --git a/arch/mips/include/asm/txx9/tx4939.h b/arch/mips/include/asm/txx9/tx4939.h
index 6d667087f2aa..00805ac6e9fc 100644
--- a/arch/mips/include/asm/txx9/tx4939.h
+++ b/arch/mips/include/asm/txx9/tx4939.h
@@ -101,13 +101,6 @@ struct tx4939_irc_reg {
 	struct tx4939_le_reg maskext;
 };
 
-struct tx4939_rtc_reg {
-	__u32 ctl;
-	__u32 adr;
-	__u32 dat;
-	__u32 tbc;
-};
-
 struct tx4939_crypto_reg {
 	struct tx4939_le_reg csr;
 	struct tx4939_le_reg idesptr;
@@ -369,26 +362,6 @@ struct tx4939_vpc_desc {
 #define TX4939_CLKCTR_SIO0RST	0x00000002
 #define TX4939_CLKCTR_CYPRST	0x00000001
 
-/*
- * RTC
- */
-#define TX4939_RTCCTL_ALME	0x00000080
-#define TX4939_RTCCTL_ALMD	0x00000040
-#define TX4939_RTCCTL_BUSY	0x00000020
-
-#define TX4939_RTCCTL_COMMAND	0x00000007
-#define TX4939_RTCCTL_COMMAND_NOP	0x00000000
-#define TX4939_RTCCTL_COMMAND_GETTIME	0x00000001
-#define TX4939_RTCCTL_COMMAND_SETTIME	0x00000002
-#define TX4939_RTCCTL_COMMAND_GETALARM	0x00000003
-#define TX4939_RTCCTL_COMMAND_SETALARM	0x00000004
-
-#define TX4939_RTCTBC_PM	0x00000080
-#define TX4939_RTCTBC_COMP	0x0000007f
-
-#define TX4939_RTC_REG_RAMSIZE	0x00000100
-#define TX4939_RTC_REG_RWBSIZE	0x00000006
-
 /*
  * CRYPTO
  */
@@ -498,8 +471,6 @@ struct tx4939_vpc_desc {
 #define tx4939_ccfgptr \
 		((struct tx4939_ccfg_reg __iomem *)TX4939_CCFG_REG)
 #define tx4939_sramcptr		tx4938_sramcptr
-#define tx4939_rtcptr \
-		((struct tx4939_rtc_reg __iomem *)TX4939_RTC_REG)
 #define tx4939_cryptoptr \
 		((struct tx4939_crypto_reg __iomem *)TX4939_CRYPTO_REG)
 #define tx4939_vpcptr	((struct tx4939_vpc_reg __iomem *)TX4939_VPC_REG)
-- 
cgit v1.2.3


From 49e5bb13adc11fe6e2e40f65c04f3a461aea1fec Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@bootlin.com>
Date: Wed, 25 Jul 2018 14:21:32 +0200
Subject: MIPS: mscc: ocelot: fix length of memory address space for MIIM

The length of memory address space for MIIM0 is from 0x7107009c to
0x710700bf included which is 36 bytes long in decimal, or 0x24 bytes in
hexadecimal and not 0x36.

Fixes: 49b031690abe ("MIPS: mscc: Add switch to ocelot")

Signed-off-by: Quentin Schulz <quentin.schulz@bootlin.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20013/
Cc: robh+dt@kernel.org
Cc: mark.rutland@arm.com
Cc: ralf@linux-mips.org
Cc: jhogan@kernel.org
Cc: linux-mips@linux-mips.org
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: thomas.petazzoni@bootlin.com
---
 arch/mips/boot/dts/mscc/ocelot.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index 4f33dbc67348..7096915f26e0 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -184,7 +184,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			compatible = "mscc,ocelot-miim";
-			reg = <0x107009c 0x36>, <0x10700f0 0x8>;
+			reg = <0x107009c 0x24>, <0x10700f0 0x8>;
 			interrupts = <14>;
 			status = "disabled";
 
-- 
cgit v1.2.3


From a0553e01f85bb27fb7bbd32f6168f9592e9dc575 Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@bootlin.com>
Date: Wed, 25 Jul 2018 14:22:41 +0200
Subject: MIPS: mscc: ocelot: add MIIM1 bus

There is an additional MIIM (MDIO) bus in this SoC so let's declare it
in the dtsi.

This bus requires GPIO 14 and 15 pins that need to be muxed. There is no
support for internal PHY reset on this bus on the contrary of MIIM0 so
there is only one register address space and not two.

Signed-off-by: Quentin Schulz <quentin.schulz@bootlin.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20014/
Cc: robh+dt@kernel.org
Cc: mark.rutland@arm.com
Cc: ralf@linux-mips.org
Cc: jhogan@kernel.org
Cc: linux-mips@linux-mips.org
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: thomas.petazzoni@bootlin.com
---
 arch/mips/boot/dts/mscc/ocelot.dtsi | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index 7096915f26e0..d7f0e3551500 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -178,6 +178,11 @@
 				pins = "GPIO_12", "GPIO_13";
 				function = "uart2";
 			};
+
+			miim1: miim1 {
+				pins = "GPIO_14", "GPIO_15";
+				function = "miim1";
+			};
 		};
 
 		mdio0: mdio@107009c {
@@ -201,5 +206,16 @@
 				reg = <3>;
 			};
 		};
+
+		mdio1: mdio@10700c0 {
+			#address-cells = <1>;
+			#size-cells = <0>;
+			compatible = "mscc,ocelot-miim";
+			reg = <0x10700c0 0x24>;
+			interrupts = <15>;
+			pinctrl-names = "default";
+			pinctrl-0 = <&miim1>;
+			status = "disabled";
+		};
 	};
 };
-- 
cgit v1.2.3


From 5bdd5fbb35ab0fe21bf2263106f51c5bee466a07 Mon Sep 17 00:00:00 2001
From: Alban Bedel <albeu@free.fr>
Date: Mon, 13 Feb 2017 23:25:46 +0100
Subject: MIPS: ath79: Fix the USB PHY reset names

The binding for the USB PHY went thru before the driver. However the
new version of the driver now use the PHY core support for reset, and
this expect the reset to be named "phy". So remove the "usb-" prefix
from the the reset names.

Signed-off-by: Alban Bedel <albeu@free.fr>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/15282/
Cc: linux-kernel@vger.kernel.org
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Antony Pavlov <antonynpavlov@gmail.com>
Cc: devicetree@vger.kernel.org
Cc: linux-mips@linux-mips.org
---
 Documentation/devicetree/bindings/phy/phy-ath79-usb.txt | 4 ++--
 arch/mips/boot/dts/qca/ar9132.dtsi                      | 2 +-
 arch/mips/boot/dts/qca/ar9331.dtsi                      | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
index cafe2197dad9..c3a29c5feea3 100644
--- a/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
+++ b/Documentation/devicetree/bindings/phy/phy-ath79-usb.txt
@@ -3,7 +3,7 @@
 Required properties:
 - compatible: "qca,ar7100-usb-phy"
 - #phys-cells: should be 0
-- reset-names: "usb-phy"[, "usb-suspend-override"]
+- reset-names: "phy"[, "suspend-override"]
 - resets: references to the reset controllers
 
 Example:
@@ -11,7 +11,7 @@ Example:
 	usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/arch/mips/boot/dts/qca/ar9132.dtsi b/arch/mips/boot/dts/qca/ar9132.dtsi
index 1fe561c5f90e..61dcfa5b6ca7 100644
--- a/arch/mips/boot/dts/qca/ar9132.dtsi
+++ b/arch/mips/boot/dts/qca/ar9132.dtsi
@@ -161,7 +161,7 @@
 	usb_phy: usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
diff --git a/arch/mips/boot/dts/qca/ar9331.dtsi b/arch/mips/boot/dts/qca/ar9331.dtsi
index efd5f0722206..2bae201aa365 100644
--- a/arch/mips/boot/dts/qca/ar9331.dtsi
+++ b/arch/mips/boot/dts/qca/ar9331.dtsi
@@ -146,7 +146,7 @@
 	usb_phy: usb-phy {
 		compatible = "qca,ar7100-usb-phy";
 
-		reset-names = "usb-phy", "usb-suspend-override";
+		reset-names = "phy", "suspend-override";
 		resets = <&rst 4>, <&rst 3>;
 
 		#phy-cells = <0>;
-- 
cgit v1.2.3


From d4da0e97baea8768b3d66ccef3967bebd50dfc3b Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@imgtec.com>
Date: Fri, 25 Nov 2016 18:46:09 +0000
Subject: MIPS: WARN_ON invalid DMA cache maintenance, not BUG_ON

If a driver causes DMA cache maintenance with a zero length then we
currently BUG and kill the kernel. As this is a scenario that we may
well be able to recover from, WARN & return in the condition instead.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Patchwork: https://patchwork.linux-mips.org/patch/14623/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/mm/c-r4k.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/mips/mm/c-r4k.c b/arch/mips/mm/c-r4k.c
index 1b4b583fab08..a9ef057c79fe 100644
--- a/arch/mips/mm/c-r4k.c
+++ b/arch/mips/mm/c-r4k.c
@@ -835,7 +835,8 @@ static void r4k_flush_icache_user_range(unsigned long start, unsigned long end)
 static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
@@ -871,7 +872,8 @@ static void r4k_dma_cache_wback_inv(unsigned long addr, unsigned long size)
 static void r4k_dma_cache_inv(unsigned long addr, unsigned long size)
 {
 	/* Catch bad driver code */
-	BUG_ON(size == 0);
+	if (WARN_ON(size == 0))
+		return;
 
 	preempt_disable();
 	if (cpu_has_inclusive_pcaches) {
-- 
cgit v1.2.3


From 3f30f929bb17877ebc1653c6f3ff41863f1ba524 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Thu, 26 Jul 2018 12:59:13 -0500
Subject: gfs2: cleanup: call gfs2_rgrp_ondisk2lvb from gfs2_rgrp_out

Before this patch gfs2_rgrp_ondisk2lvb was called after every call
to gfs2_rgrp_out. This patch just calls it directly from within
gfs2_rgrp_out, and moves the function to be before it so we don't
need a function prototype.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/rgrp.c | 30 +++++++++++++-----------------
 1 file changed, 13 insertions(+), 17 deletions(-)

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 68a81afd3b4a..7c5afeba8888 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1053,6 +1053,18 @@ static void gfs2_rgrp_in(struct gfs2_rgrpd *rgd, const void *buf)
 	/* rd_data0, rd_data and rd_bitbytes already set from rindex */
 }
 
+static void gfs2_rgrp_ondisk2lvb(struct gfs2_rgrp_lvb *rgl, const void *buf)
+{
+	const struct gfs2_rgrp *str = buf;
+
+	rgl->rl_magic = cpu_to_be32(GFS2_MAGIC);
+	rgl->rl_flags = str->rg_flags;
+	rgl->rl_free = str->rg_free;
+	rgl->rl_dinodes = str->rg_dinodes;
+	rgl->rl_igeneration = str->rg_igeneration;
+	rgl->__pad = 0UL;
+}
+
 static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
 {
 	struct gfs2_rgrpd *next = gfs2_rgrpd_get_next(rgd);
@@ -1075,6 +1087,7 @@ static void gfs2_rgrp_out(struct gfs2_rgrpd *rgd, void *buf)
 	str->rg_crc = cpu_to_be32(crc);
 
 	memset(&str->rg_reserved, 0, sizeof(str->rg_reserved));
+	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, buf);
 }
 
 static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd)
@@ -1089,18 +1102,6 @@ static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd)
 	return 1;
 }
 
-static void gfs2_rgrp_ondisk2lvb(struct gfs2_rgrp_lvb *rgl, const void *buf)
-{
-	const struct gfs2_rgrp *str = buf;
-
-	rgl->rl_magic = cpu_to_be32(GFS2_MAGIC);
-	rgl->rl_flags = str->rg_flags;
-	rgl->rl_free = str->rg_free;
-	rgl->rl_dinodes = str->rg_dinodes;
-	rgl->rl_igeneration = str->rg_igeneration;
-	rgl->__pad = 0UL;
-}
-
 static void update_rgrp_lvb_unlinked(struct gfs2_rgrpd *rgd, u32 change)
 {
 	struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
@@ -1426,7 +1427,6 @@ int gfs2_fitrim(struct file *filp, void __user *argp)
 				rgd->rd_flags |= GFS2_RGF_TRIMMED;
 				gfs2_trans_add_meta(rgd->rd_gl, bh);
 				gfs2_rgrp_out(rgd, bh->b_data);
-				gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, bh->b_data);
 				gfs2_trans_end(sdp);
 			}
 		}
@@ -2424,7 +2424,6 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 
 	gfs2_trans_add_meta(rbm.rgd->rd_gl, rbm.rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rbm.rgd, rbm.rgd->rd_bits[0].bi_bh->b_data);
-	gfs2_rgrp_ondisk2lvb(rbm.rgd->rd_rgl, rbm.rgd->rd_bits[0].bi_bh->b_data);
 
 	gfs2_statfs_change(sdp, 0, -(s64)*nblocks, dinode ? 1 : 0);
 	if (dinode)
@@ -2465,7 +2464,6 @@ void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta)
 	rgd->rd_flags &= ~GFS2_RGF_TRIMMED;
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
-	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
 
 	/* Directories keep their data in the metadata address space */
 	if (meta || ip->i_depth)
@@ -2502,7 +2500,6 @@ void gfs2_unlink_di(struct inode *inode)
 	trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
-	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
 	update_rgrp_lvb_unlinked(rgd, 1);
 }
 
@@ -2523,7 +2520,6 @@ void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
 
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
-	gfs2_rgrp_ondisk2lvb(rgd->rd_rgl, rgd->rd_bits[0].bi_bh->b_data);
 	update_rgrp_lvb_unlinked(rgd, -1);
 
 	gfs2_statfs_change(sdp, 0, +1, -1);
-- 
cgit v1.2.3


From 990e35ecba1cb8ebee4ad4a028735e24f4615417 Mon Sep 17 00:00:00 2001
From: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Date: Mon, 23 Jul 2018 17:08:00 -0700
Subject: cbs: Add support for the graft function

This will allow to install a child qdisc under cbs. The main use case
is to install ETF (Earliest TxTime First) qdisc under cbs, so there's
another level of control for time-sensitive traffic.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cbs.c | 134 ++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 125 insertions(+), 9 deletions(-)

diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c
index cdd96b9a27bc..e26a24017faa 100644
--- a/net/sched/sch_cbs.c
+++ b/net/sched/sch_cbs.c
@@ -78,18 +78,42 @@ struct cbs_sched_data {
 	s64 sendslope; /* in bytes/s */
 	s64 idleslope; /* in bytes/s */
 	struct qdisc_watchdog watchdog;
-	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch);
+	int (*enqueue)(struct sk_buff *skb, struct Qdisc *sch,
+		       struct sk_buff **to_free);
 	struct sk_buff *(*dequeue)(struct Qdisc *sch);
+	struct Qdisc *qdisc;
 };
 
-static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch)
+static int cbs_child_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+			     struct Qdisc *child,
+			     struct sk_buff **to_free)
 {
-	return qdisc_enqueue_tail(skb, sch);
+	int err;
+
+	err = child->ops->enqueue(skb, child, to_free);
+	if (err != NET_XMIT_SUCCESS)
+		return err;
+
+	qdisc_qstats_backlog_inc(sch, skb);
+	sch->q.qlen++;
+
+	return NET_XMIT_SUCCESS;
 }
 
-static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
+static int cbs_enqueue_offload(struct sk_buff *skb, struct Qdisc *sch,
+			       struct sk_buff **to_free)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
+
+	return cbs_child_enqueue(skb, sch, qdisc, to_free);
+}
+
+static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch,
+			    struct sk_buff **to_free)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
 
 	if (sch->q.qlen == 0 && q->credits > 0) {
 		/* We need to stop accumulating credits when there's
@@ -99,7 +123,7 @@ static int cbs_enqueue_soft(struct sk_buff *skb, struct Qdisc *sch)
 		q->last = ktime_get_ns();
 	}
 
-	return qdisc_enqueue_tail(skb, sch);
+	return cbs_child_enqueue(skb, sch, qdisc, to_free);
 }
 
 static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
@@ -107,7 +131,7 @@ static int cbs_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
 
-	return q->enqueue(skb, sch);
+	return q->enqueue(skb, sch, to_free);
 }
 
 /* timediff is in ns, slope is in bytes/s */
@@ -132,9 +156,25 @@ static s64 credits_from_len(unsigned int len, s64 slope, s64 port_rate)
 	return div64_s64(len * slope, port_rate);
 }
 
+static struct sk_buff *cbs_child_dequeue(struct Qdisc *sch, struct Qdisc *child)
+{
+	struct sk_buff *skb;
+
+	skb = child->ops->dequeue(child);
+	if (!skb)
+		return NULL;
+
+	qdisc_qstats_backlog_dec(sch, skb);
+	qdisc_bstats_update(sch, skb);
+	sch->q.qlen--;
+
+	return skb;
+}
+
 static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 {
 	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
 	s64 now = ktime_get_ns();
 	struct sk_buff *skb;
 	s64 credits;
@@ -157,8 +197,7 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 			return NULL;
 		}
 	}
-
-	skb = qdisc_dequeue_head(sch);
+	skb = cbs_child_dequeue(sch, qdisc);
 	if (!skb)
 		return NULL;
 
@@ -178,7 +217,10 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch)
 
 static struct sk_buff *cbs_dequeue_offload(struct Qdisc *sch)
 {
-	return qdisc_dequeue_head(sch);
+	struct cbs_sched_data *q = qdisc_priv(sch);
+	struct Qdisc *qdisc = q->qdisc;
+
+	return cbs_child_dequeue(sch, qdisc);
 }
 
 static struct sk_buff *cbs_dequeue(struct Qdisc *sch)
@@ -310,6 +352,13 @@ static int cbs_init(struct Qdisc *sch, struct nlattr *opt,
 		return -EINVAL;
 	}
 
+	q->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+				     sch->handle, extack);
+	if (!q->qdisc)
+		return -ENOMEM;
+
+	qdisc_hash_add(q->qdisc, false);
+
 	q->queue = sch->dev_queue - netdev_get_tx_queue(dev, 0);
 
 	q->enqueue = cbs_enqueue_soft;
@@ -328,6 +377,9 @@ static void cbs_destroy(struct Qdisc *sch)
 	qdisc_watchdog_cancel(&q->watchdog);
 
 	cbs_disable_offload(dev, q);
+
+	if (q->qdisc)
+		qdisc_destroy(q->qdisc);
 }
 
 static int cbs_dump(struct Qdisc *sch, struct sk_buff *skb)
@@ -356,8 +408,72 @@ nla_put_failure:
 	return -1;
 }
 
+static int cbs_dump_class(struct Qdisc *sch, unsigned long cl,
+			  struct sk_buff *skb, struct tcmsg *tcm)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	if (cl != 1 || !q->qdisc)	/* only one class */
+		return -ENOENT;
+
+	tcm->tcm_handle |= TC_H_MIN(1);
+	tcm->tcm_info = q->qdisc->handle;
+
+	return 0;
+}
+
+static int cbs_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
+		     struct Qdisc **old, struct netlink_ext_ack *extack)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	if (!new) {
+		new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+					sch->handle, NULL);
+		if (!new)
+			new = &noop_qdisc;
+	}
+
+	*old = qdisc_replace(sch, new, &q->qdisc);
+	return 0;
+}
+
+static struct Qdisc *cbs_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	struct cbs_sched_data *q = qdisc_priv(sch);
+
+	return q->qdisc;
+}
+
+static unsigned long cbs_find(struct Qdisc *sch, u32 classid)
+{
+	return 1;
+}
+
+static void cbs_walk(struct Qdisc *sch, struct qdisc_walker *walker)
+{
+	if (!walker->stop) {
+		if (walker->count >= walker->skip) {
+			if (walker->fn(sch, 1, walker) < 0) {
+				walker->stop = 1;
+				return;
+			}
+		}
+		walker->count++;
+	}
+}
+
+static const struct Qdisc_class_ops cbs_class_ops = {
+	.graft		=	cbs_graft,
+	.leaf		=	cbs_leaf,
+	.find		=	cbs_find,
+	.walk		=	cbs_walk,
+	.dump		=	cbs_dump_class,
+};
+
 static struct Qdisc_ops cbs_qdisc_ops __read_mostly = {
 	.id		=	"cbs",
+	.cl_ops		=	&cbs_class_ops,
 	.priv_size	=	sizeof(struct cbs_sched_data),
 	.enqueue	=	cbs_enqueue,
 	.dequeue	=	cbs_dequeue,
-- 
cgit v1.2.3


From 201876b33c09edcb6c2914f0ced798437a102648 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Tue, 24 Jul 2018 16:54:27 +0530
Subject: net/tls: Removed redundant checks for non-NULL

Removed checks against non-NULL before calling kfree_skb() and
crypto_free_aead(). These functions are safe to be called with NULL
as an argument.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 03f1370f5db1..0687a7a4689f 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1047,8 +1047,7 @@ void tls_sw_free_resources_tx(struct sock *sk)
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx);
 
-	if (ctx->aead_send)
-		crypto_free_aead(ctx->aead_send);
+	crypto_free_aead(ctx->aead_send);
 	tls_free_both_sg(sk);
 
 	kfree(ctx);
@@ -1060,10 +1059,8 @@ void tls_sw_release_resources_rx(struct sock *sk)
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
 
 	if (ctx->aead_recv) {
-		if (ctx->recv_pkt) {
-			kfree_skb(ctx->recv_pkt);
-			ctx->recv_pkt = NULL;
-		}
+		kfree_skb(ctx->recv_pkt);
+		ctx->recv_pkt = NULL;
 		crypto_free_aead(ctx->aead_recv);
 		strp_stop(&ctx->strp);
 		write_lock_bh(&sk->sk_callback_lock);
-- 
cgit v1.2.3


From 63135ee0a6e5f5a5ad1345e48099e62d3d617a81 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 25 Jul 2018 18:00:49 +0800
Subject: tipc: add missing dev_put() on error in tipc_enable_l2_media

when tipc_own_id failed to obtain node identity,dev_put should
be call before return -EINVAL.

Fixes: 682cd3cf946b ("tipc: confgiure and apply UDP bearer MTU on running links")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bearer.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c
index fd6d8f18955c..418f03d0be90 100644
--- a/net/tipc/bearer.c
+++ b/net/tipc/bearer.c
@@ -395,6 +395,7 @@ int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b,
 		tipc_net_init(net, node_id, 0);
 	}
 	if (!tipc_own_id(net)) {
+		dev_put(dev);
 		pr_warn("Failed to obtain node identity\n");
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 2b139e6b1ec86e1d3646039965dd79ad05d8dca4 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Wed, 25 Jul 2018 14:53:33 +0200
Subject: l2tp: remove ->recv_payload_hook

The tunnel reception hook is only used by l2tp_ppp for skipping PPP
framing bytes. This is a session specific operation, but once a PPP
session sets ->recv_payload_hook on its tunnel, all frames received by
the tunnel will enter pppol2tp_recv_payload_hook(), including those
targeted at Ethernet sessions (an L2TPv3 tunnel can multiplex PPP and
Ethernet sessions).

So this mechanism is wrong, and uselessly complex. Let's just move this
functionality to the pppol2tp rx handler and drop ->recv_payload_hook.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 16 ++++------------
 net/l2tp/l2tp_core.h |  3 +--
 net/l2tp/l2tp_ip.c   |  2 +-
 net/l2tp/l2tp_ip6.c  |  3 +--
 net/l2tp/l2tp_ppp.c  | 33 +++++++++++----------------------
 5 files changed, 18 insertions(+), 39 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c8fc0f7f0b4b..d10f4ed52d92 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -619,7 +619,7 @@ discard:
  */
 void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      unsigned char *ptr, unsigned char *optr, u16 hdrflags,
-		      int length, int (*payload_hook)(struct sk_buff *skb))
+		      int length)
 {
 	struct l2tp_tunnel *tunnel = session->tunnel;
 	int offset;
@@ -740,13 +740,6 @@ void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 
 	__skb_pull(skb, offset);
 
-	/* If caller wants to process the payload before we queue the
-	 * packet, do so now.
-	 */
-	if (payload_hook)
-		if ((*payload_hook)(skb))
-			goto discard;
-
 	/* Prepare skb for adding to the session's reorder_q.  Hold
 	 * packets for max reorder_timeout or 1 second if not
 	 * reordering.
@@ -800,8 +793,7 @@ static int l2tp_session_queue_purge(struct l2tp_session *session)
  * Returns 1 if the packet was not a good data packet and could not be
  * forwarded.  All such packets are passed up to userspace to deal with.
  */
-static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
-			      int (*payload_hook)(struct sk_buff *skb))
+static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 {
 	struct l2tp_session *session = NULL;
 	unsigned char *ptr, *optr;
@@ -892,7 +884,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb,
 		goto error;
 	}
 
-	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length, payload_hook);
+	l2tp_recv_common(session, skb, ptr, optr, hdrflags, length);
 	l2tp_session_dec_refcount(session);
 
 	return 0;
@@ -921,7 +913,7 @@ int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
 	l2tp_dbg(tunnel, L2TP_MSG_DATA, "%s: received %d bytes\n",
 		 tunnel->name, skb->len);
 
-	if (l2tp_udp_recv_core(tunnel, skb, tunnel->recv_payload_hook))
+	if (l2tp_udp_recv_core(tunnel, skb))
 		goto pass_up;
 
 	return 0;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index a5c09d3a5698..d85fde793a8c 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -180,7 +180,6 @@ struct l2tp_tunnel {
 	struct net		*l2tp_net;	/* the net we belong to */
 
 	refcount_t		ref_count;
-	int (*recv_payload_hook)(struct sk_buff *skb);
 	void (*old_sk_destruct)(struct sock *);
 	struct sock		*sock;		/* Parent socket */
 	int			fd;		/* Parent fd, if tunnel socket
@@ -232,7 +231,7 @@ int l2tp_session_delete(struct l2tp_session *session);
 void l2tp_session_free(struct l2tp_session *session);
 void l2tp_recv_common(struct l2tp_session *session, struct sk_buff *skb,
 		      unsigned char *ptr, unsigned char *optr, u16 hdrflags,
-		      int length, int (*payload_hook)(struct sk_buff *skb));
+		      int length);
 int l2tp_udp_encap_recv(struct sock *sk, struct sk_buff *skb);
 void l2tp_session_set_header_len(struct l2tp_session *session, int version);
 
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index a9c05b2bc1b0..0bc39cc20a3f 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -165,7 +165,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
 
-	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len, tunnel->recv_payload_hook);
+	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
 	l2tp_session_dec_refcount(session);
 
 	return 0;
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 672e5b753738..42f828cf62fb 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -178,8 +178,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
 	}
 
-	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
-			 tunnel->recv_payload_hook);
+	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len);
 	l2tp_session_dec_refcount(session);
 
 	return 0;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 9ac02c93df98..000c9829304c 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -183,25 +183,6 @@ out:
  * Receive data handling
  *****************************************************************************/
 
-static int pppol2tp_recv_payload_hook(struct sk_buff *skb)
-{
-	/* Skip PPP header, if present.	 In testing, Microsoft L2TP clients
-	 * don't send the PPP header (PPP header compression enabled), but
-	 * other clients can include the header. So we cope with both cases
-	 * here. The PPP header is always FF03 when using L2TP.
-	 *
-	 * Note that skb->data[] isn't dereferenced from a u16 ptr here since
-	 * the field may be unaligned.
-	 */
-	if (!pskb_may_pull(skb, 2))
-		return 1;
-
-	if ((skb->data[0] == PPP_ALLSTATIONS) && (skb->data[1] == PPP_UI))
-		skb_pull(skb, 2);
-
-	return 0;
-}
-
 /* Receive message. This is the recvmsg for the PPPoL2TP socket.
  */
 static int pppol2tp_recvmsg(struct socket *sock, struct msghdr *msg,
@@ -248,6 +229,17 @@ static void pppol2tp_recv(struct l2tp_session *session, struct sk_buff *skb, int
 	if (sk == NULL)
 		goto no_sock;
 
+	/* If the first two bytes are 0xFF03, consider that it is the PPP's
+	 * Address and Control fields and skip them. The L2TP module has always
+	 * worked this way, although, in theory, the use of these fields should
+	 * be negociated and handled at the PPP layer. These fields are
+	 * constant: 0xFF is the All-Stations Address and 0x03 the Unnumbered
+	 * Information command with Poll/Final bit set to zero (RFC 1662).
+	 */
+	if (pskb_may_pull(skb, 2) && skb->data[0] == PPP_ALLSTATIONS &&
+	    skb->data[1] == PPP_UI)
+		skb_pull(skb, 2);
+
 	if (sk->sk_state & PPPOX_BOUND) {
 		struct pppox_sock *po;
 
@@ -763,9 +755,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 			goto end;
 	}
 
-	if (tunnel->recv_payload_hook == NULL)
-		tunnel->recv_payload_hook = pppol2tp_recv_payload_hook;
-
 	if (tunnel->peer_tunnel_id == 0)
 		tunnel->peer_tunnel_id = info.peer_tunnel_id;
 
-- 
cgit v1.2.3


From 2ed9db3074fcd8d12709fe40ff0e691d74229818 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 25 Jul 2018 09:07:24 -0500
Subject: net: sched: cls_api: fix dead code in switch

Code at line 1850 is unreachable. Fix this by removing the break
statement above it, so the code for case RTM_GETCHAIN can be
properly executed.

Addresses-Coverity-ID: 1472050 ("Structurally dead code")
Fixes: 32a4f5ecd738 ("net: sched: introduce chain object to uapi")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 5f7098b5405e..f3d78c23338e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1846,7 +1846,6 @@ replay:
 		tcf_chain_put_explicitly_created(chain);
 		break;
 	case RTM_GETCHAIN:
-		break;
 		err = tc_chain_notify(chain, skb, n->nlmsg_seq,
 				      n->nlmsg_seq, n->nlmsg_type, true);
 		if (err < 0)
-- 
cgit v1.2.3


From 0a26cf3ff47d9e70fbed2fa79b0678ee70e25113 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Wed, 25 Jul 2018 14:48:21 -0700
Subject: tls: Skip zerocopy path for ITER_KVEC

The zerocopy path ultimately calls iov_iter_get_pages, which defines the
step function for ITER_KVECs as simply, return -EFAULT. Taking the
non-zerocopy path for ITER_KVECs avoids the unnecessary fallback.

See https://lore.kernel.org/lkml/20150401023311.GL29656@ZenIV.linux.org.uk/T/#u
for a discussion of why zerocopy for vmalloc data is not a good idea.

Discovered while testing NBD traffic encrypted with ktls.

Fixes: c46234ebb4d1 ("tls: RX path for ktls")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 0687a7a4689f..f9971717f7e0 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -362,6 +362,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	int record_room;
 	bool full_record;
 	int orig_size;
+	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
 
 	if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL))
 		return -ENOTSUPP;
@@ -410,8 +411,7 @@ alloc_encrypted:
 			try_to_copy -= required_size - ctx->sg_encrypted_size;
 			full_record = true;
 		}
-
-		if (full_record || eor) {
+		if (!is_kvec && (full_record || eor)) {
 			ret = zerocopy_from_iter(sk, &msg->msg_iter,
 				try_to_copy, &ctx->sg_plaintext_num_elem,
 				&ctx->sg_plaintext_size,
@@ -779,6 +779,7 @@ int tls_sw_recvmsg(struct sock *sk,
 	bool cmsg = false;
 	int target, err = 0;
 	long timeo;
+	bool is_kvec = msg->msg_iter.type & ITER_KVEC;
 
 	flags |= nonblock;
 
@@ -822,7 +823,7 @@ int tls_sw_recvmsg(struct sock *sk,
 			page_count = iov_iter_npages(&msg->msg_iter,
 						     MAX_SKB_FRAGS);
 			to_copy = rxm->full_len - tls_ctx->rx.overhead_size;
-			if (to_copy <= len && page_count < MAX_SKB_FRAGS &&
+			if (!is_kvec && to_copy <= len && page_count < MAX_SKB_FRAGS &&
 			    likely(!(flags & MSG_PEEK)))  {
 				struct scatterlist sgin[MAX_SKB_FRAGS + 1];
 				int pages = 0;
-- 
cgit v1.2.3


From c921d7db3d1248c9091af070a7fdce2e55baa86a Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 26 Jul 2018 18:27:58 +0200
Subject: net: sched: unmark chain as explicitly created on delete

Once user manually deletes the chain using "chain del", the chain cannot
be marked as explicitly created anymore.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Fixes: 32a4f5ecd738 ("net: sched: introduce chain object to uapi")
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f3d78c23338e..75cce2819de9 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1844,6 +1844,7 @@ replay:
 		 * to the chain previously taken during addition.
 		 */
 		tcf_chain_put_explicitly_created(chain);
+		chain->explicitly_created = false;
 		break;
 	case RTM_GETCHAIN:
 		err = tc_chain_notify(chain, skb, n->nlmsg_seq,
-- 
cgit v1.2.3


From 1fee4f77523a3e5a44fa33c9aa76de8c6c42a632 Mon Sep 17 00:00:00 2001
From: Masami Hiramatsu <mhiramat@kernel.org>
Date: Thu, 26 Jul 2018 21:43:36 +0900
Subject: doc: tracing: Fix a typo of trace_stat

The name of the directory for per-cpu function statistics
is trace_stat, not trace_stats.

Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/trace/ftrace.rst | 4 ++--
 kernel/trace/Kconfig           | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index a20d34955333..7ea16a0ceffc 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -329,9 +329,9 @@ of ftrace. Here is a list of some of the key files:
 	track of the time spent in those functions. The histogram
 	content can be displayed in the files:
 
-	trace_stats/function<cpu> ( function0, function1, etc).
+	trace_stat/function<cpu> ( function0, function1, etc).
 
-  trace_stats:
+  trace_stat:
 
 	A directory that holds different tracing stats.
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 2bd4a9181a0f..9a27f146fa1c 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -521,7 +521,7 @@ config FUNCTION_PROFILER
 	  in debugfs called function_profile_enabled which defaults to zero.
 	  When a 1 is echoed into this file profiling begins, and when a
 	  zero is entered, profiling stops. A "functions" file is created in
-	  the trace_stats directory; this file shows the list of functions that
+	  the trace_stat directory; this file shows the list of functions that
 	  have been hit and their counters.
 
 	  If in doubt, say N.
-- 
cgit v1.2.3


From 359f642700f2ff05d9c94cd9216c97af7b8e9553 Mon Sep 17 00:00:00 2001
From: Greg Edwards <gedwards@ddn.com>
Date: Wed, 25 Jul 2018 10:22:58 -0400
Subject: block: move bio_integrity_{intervals,bytes} into blkdev.h

This allows bio_integrity_bytes() to be called from drivers instead of
open coding it.

Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Greg Edwards <gedwards@ddn.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio-integrity.c  | 22 ----------------------
 include/linux/blkdev.h | 34 ++++++++++++++++++++++++++++++++++
 2 files changed, 34 insertions(+), 22 deletions(-)

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index add7c7c85335..67b5fb861a51 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -159,28 +159,6 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 }
 EXPORT_SYMBOL(bio_integrity_add_page);
 
-/**
- * bio_integrity_intervals - Return number of integrity intervals for a bio
- * @bi:		blk_integrity profile for device
- * @sectors:	Size of the bio in 512-byte sectors
- *
- * Description: The block layer calculates everything in 512 byte
- * sectors but integrity metadata is done in terms of the data integrity
- * interval size of the storage device.  Convert the block layer sectors
- * to the appropriate number of integrity intervals.
- */
-static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
-						   unsigned int sectors)
-{
-	return sectors >> (bi->interval_exp - 9);
-}
-
-static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
-					       unsigned int sectors)
-{
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
-}
-
 /**
  * bio_integrity_process - Process integrity metadata for a bio
  * @bio:	bio to generate/verify integrity metadata for
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 331a6cb8805f..050d599f5ea9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1865,6 +1865,28 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 				bip_next->bip_vec[0].bv_offset);
 }
 
+/**
+ * bio_integrity_intervals - Return number of integrity intervals for a bio
+ * @bi:		blk_integrity profile for device
+ * @sectors:	Size of the bio in 512-byte sectors
+ *
+ * Description: The block layer calculates everything in 512 byte
+ * sectors but integrity metadata is done in terms of the data integrity
+ * interval size of the storage device.  Convert the block layer sectors
+ * to the appropriate number of integrity intervals.
+ */
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return sectors >> (bi->interval_exp - 9);
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1938,6 +1960,18 @@ static inline bool integrity_req_gap_front_merge(struct request *req,
 	return false;
 }
 
+static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
+						   unsigned int sectors)
+{
+	return 0;
+}
+
+static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
+					       unsigned int sectors)
+{
+	return 0;
+}
+
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct block_device_operations {
-- 
cgit v1.2.3


From cdcdcaae8450a975e7d07e1bfec21f9b8c016d0c Mon Sep 17 00:00:00 2001
From: Greg Edwards <gedwards@ddn.com>
Date: Thu, 26 Jul 2018 15:52:54 -0400
Subject: scsi: virtio_scsi: fix pi_bytes{out,in} on 4 KiB block size devices

When the underlying device is a 4 KiB logical block size device with a
protection interval exponent of 0, i.e. 4096 bytes data + 8 bytes PI, the
driver miscalculates the pi_bytes{out,in} by a factor of 8x (64 bytes).

This leads to errors on all reads and writes on 4 KiB logical block size
devices when CONFIG_BLK_DEV_INTEGRITY is enabled and the
VIRTIO_SCSI_F_T10_PI feature bit has been negotiated.

Fixes: e6dc783a38ec0 ("virtio-scsi: Enable DIF/DIX modes in SCSI host LLD")
Acked-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Greg Edwards <gedwards@ddn.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/scsi/virtio_scsi.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/virtio_scsi.c b/drivers/scsi/virtio_scsi.c
index 6dc8891ccb74..1c72db94270e 100644
--- a/drivers/scsi/virtio_scsi.c
+++ b/drivers/scsi/virtio_scsi.c
@@ -513,12 +513,12 @@ static void virtio_scsi_init_hdr_pi(struct virtio_device *vdev,
 
 	if (sc->sc_data_direction == DMA_TO_DEVICE)
 		cmd_pi->pi_bytesout = cpu_to_virtio32(vdev,
-							blk_rq_sectors(rq) *
-							bi->tuple_size);
+						      bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 	else if (sc->sc_data_direction == DMA_FROM_DEVICE)
 		cmd_pi->pi_bytesin = cpu_to_virtio32(vdev,
-						       blk_rq_sectors(rq) *
-						       bi->tuple_size);
+						     bio_integrity_bytes(bi,
+							blk_rq_sectors(rq)));
 }
 #endif
 
-- 
cgit v1.2.3


From c8cce10a62aaaca33bbdbe7356bde20a47790290 Mon Sep 17 00:00:00 2001
From: Jonathan Corbet <corbet@lwn.net>
Date: Thu, 26 Jul 2018 16:17:55 -0600
Subject: docs: Fix the reference labels in Locking.rst

Two jump tags were misspelled, leading to non-working cross-reference
links.

Reported-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/kernel-hacking/locking.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst
index f937c0fd11aa..9cc036ff57b9 100644
--- a/Documentation/kernel-hacking/locking.rst
+++ b/Documentation/kernel-hacking/locking.rst
@@ -177,7 +177,7 @@ perfect world).
 
 Note that you can also use :c:func:`spin_lock_irq()` or
 :c:func:`spin_lock_irqsave()` here, which stop hardware interrupts
-as well: see `Hard IRQ Context <#hardirq-context>`__.
+as well: see `Hard IRQ Context <#hard-irq-context>`__.
 
 This works perfectly for UP as well: the spin lock vanishes, and this
 macro simply becomes :c:func:`local_bh_disable()`
@@ -228,7 +228,7 @@ The Same Softirq
 ~~~~~~~~~~~~~~~~
 
 The same softirq can run on the other CPUs: you can use a per-CPU array
-(see `Per-CPU Data <#per-cpu>`__) for better performance. If you're
+(see `Per-CPU Data <#per-cpu-data>`__) for better performance. If you're
 going so far as to use a softirq, you probably care about scalable
 performance enough to justify the extra complexity.
 
-- 
cgit v1.2.3


From 1497624fffab130608a8f2825f47fb8231a90355 Mon Sep 17 00:00:00 2001
From: Federico Vaga <federico.vaga@vaga.pv.it>
Date: Sat, 7 Jul 2018 00:05:17 +0200
Subject: doc:it_IT: translation for kernel-hacking

This patch includes the kernel-hacking translation in Italian (both
hacking.rst and locking.rst).

It adds also the anchors for the english kernel-hacking documents.

Signed-off-by: Federico Vaga <federico.vaga@vaga.pv.it>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/kernel-hacking/hacking.rst           |    2 +
 Documentation/kernel-hacking/locking.rst           |    2 +
 Documentation/translations/it_IT/index.rst         |    1 +
 .../translations/it_IT/kernel-hacking/hacking.rst  |  855 +++++++++++
 .../translations/it_IT/kernel-hacking/index.rst    |   16 +
 .../translations/it_IT/kernel-hacking/locking.rst  | 1493 ++++++++++++++++++++
 6 files changed, 2369 insertions(+)
 create mode 100644 Documentation/translations/it_IT/kernel-hacking/hacking.rst
 create mode 100644 Documentation/translations/it_IT/kernel-hacking/index.rst
 create mode 100644 Documentation/translations/it_IT/kernel-hacking/locking.rst

diff --git a/Documentation/kernel-hacking/hacking.rst b/Documentation/kernel-hacking/hacking.rst
index 9999c8468293..d824e4feaff3 100644
--- a/Documentation/kernel-hacking/hacking.rst
+++ b/Documentation/kernel-hacking/hacking.rst
@@ -1,3 +1,5 @@
+.. _kernel_hacking_hack:
+
 ============================================
 Unreliable Guide To Hacking The Linux Kernel
 ============================================
diff --git a/Documentation/kernel-hacking/locking.rst b/Documentation/kernel-hacking/locking.rst
index 9cc036ff57b9..519673df0e82 100644
--- a/Documentation/kernel-hacking/locking.rst
+++ b/Documentation/kernel-hacking/locking.rst
@@ -1,3 +1,5 @@
+.. _kernel_hacking_lock:
+
 ===========================
 Unreliable Guide To Locking
 ===========================
diff --git a/Documentation/translations/it_IT/index.rst b/Documentation/translations/it_IT/index.rst
index dae01886b073..898a7823a6f4 100644
--- a/Documentation/translations/it_IT/index.rst
+++ b/Documentation/translations/it_IT/index.rst
@@ -87,6 +87,7 @@ vostre modifiche molto più semplice
    :maxdepth: 2
 
    doc-guide/index
+   kernel-hacking/index
 
 .. warning::
 
diff --git a/Documentation/translations/it_IT/kernel-hacking/hacking.rst b/Documentation/translations/it_IT/kernel-hacking/hacking.rst
new file mode 100644
index 000000000000..7178e517af0a
--- /dev/null
+++ b/Documentation/translations/it_IT/kernel-hacking/hacking.rst
@@ -0,0 +1,855 @@
+.. include:: ../disclaimer-ita.rst
+
+.. note:: Per leggere la documentazione originale in inglese:
+	  :ref:`Documentation/kernel-hacking/hacking.rst <kernel_hacking_hack>`
+
+:Original: :ref:`Documentation/kernel-hacking/hacking.rst <kernel_hacking_hack>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
+
+.. _it_kernel_hacking_hack:
+
+=================================================
+L'inaffidabile guida all'hacking del kernel Linux
+=================================================
+
+:Author: Rusty Russell
+
+Introduzione
+============
+
+Benvenuto, gentile lettore, alla notevole ed inaffidabile guida all'hacking
+del kernel Linux ad opera di Rusty. Questo documento descrive le procedure
+più usate ed i concetti necessari per scrivere codice per il kernel: lo scopo
+è di fornire ai programmatori C più esperti un manuale di base per sviluppo.
+Eviterò dettagli implementativi: per questo abbiamo il codice,
+ed ignorerò intere parti di alcune procedure.
+
+Prima di leggere questa guida, sappiate che non ho mai voluto scriverla,
+essendo esageratamente sotto qualificato, ma ho sempre voluto leggere
+qualcosa di simile, e quindi questa era l'unica via. Spero che possa
+crescere e diventare un compendio di buone pratiche, punti di partenza
+e generiche informazioni.
+
+Gli attori
+==========
+
+In qualsiasi momento ognuna delle CPU di un sistema può essere:
+
+-  non associata ad alcun processo, servendo un'interruzione hardware;
+
+-  non associata ad alcun processo, servendo un softirq o tasklet;
+
+-  in esecuzione nello spazio kernel, associata ad un processo
+   (contesto utente);
+
+-  in esecuzione di un processo nello spazio utente;
+
+Esiste un ordine fra questi casi. Gli ultimi due possono avvicendarsi (preempt)
+l'un l'altro, ma a parte questo esiste una gerarchia rigida: ognuno di questi
+può avvicendarsi solo ad uno di quelli sottostanti. Per esempio, mentre un
+softirq è in esecuzione su d'una CPU, nessun altro softirq può avvicendarsi
+nell'esecuzione, ma un'interruzione hardware può. Ciò nonostante, le altre CPU
+del sistema operano indipendentemente.
+
+Più avanti vedremo alcuni modi in cui dal contesto utente è possibile bloccare
+le interruzioni, così da impedirne davvero il diritto di prelazione.
+
+Contesto utente
+---------------
+
+Ci si trova nel contesto utente quando si arriva da una chiamata di sistema
+od altre eccezioni: come nello spazio utente, altre procedure più importanti,
+o le interruzioni, possono far valere il proprio diritto di prelazione sul
+vostro processo. Potete sospendere l'esecuzione chiamando :c:func:`schedule()`.
+
+.. note::
+
+    Si è sempre in contesto utente quando un modulo viene caricato o rimosso,
+    e durante le operazioni nello strato dei dispositivi a blocchi
+    (*block layer*).
+
+Nel contesto utente, il puntatore ``current`` (il quale indica il processo al
+momento in esecuzione) è valido, e :c:func:`in_interrupt()`
+(``include/linux/preempt.h``) è falsa.
+
+.. warning::
+
+    Attenzione che se avete la prelazione o i softirq disabilitati (vedere
+    di seguito), :c:func:`in_interrupt()` ritornerà un falso positivo.
+
+Interruzioni hardware (Hard IRQs)
+---------------------------------
+
+Temporizzatori, schede di rete e tastiere sono esempi di vero hardware
+che possono produrre interruzioni in un qualsiasi momento. Il kernel esegue
+i gestori d'interruzione che prestano un servizio all'hardware. Il kernel
+garantisce che questi gestori non vengano mai interrotti: se una stessa
+interruzione arriva, questa verrà accodata (o scartata).
+Dato che durante la loro esecuzione le interruzioni vengono disabilitate,
+i gestori d'interruzioni devono essere veloci: spesso si limitano
+esclusivamente a notificare la presa in carico dell'interruzione,
+programmare una 'interruzione software' per l'esecuzione e quindi terminare.
+
+Potete dire d'essere in una interruzione hardware perché :c:func:`in_irq()`
+ritorna vero.
+
+.. warning::
+
+    Attenzione, questa ritornerà un falso positivo se le interruzioni
+    sono disabilitate (vedere di seguito).
+
+Contesto d'interruzione software: softirq e tasklet
+---------------------------------------------------
+
+Quando una chiamata di sistema sta per tornare allo spazio utente,
+oppure un gestore d'interruzioni termina, qualsiasi 'interruzione software'
+marcata come pendente (solitamente da un'interruzione hardware) viene
+eseguita (``kernel/softirq.c``).
+
+La maggior parte del lavoro utile alla gestione di un'interruzione avviene qui.
+All'inizio della transizione ai sistemi multiprocessore, c'erano solo i
+cosiddetti 'bottom half' (BH), i quali non traevano alcun vantaggio da questi
+sistemi. Non appena abbandonammo i computer raffazzonati con fiammiferi e
+cicche, abbandonammo anche questa limitazione e migrammo alle interruzioni
+software 'softirqs'.
+
+Il file ``include/linux/interrupt.h`` elenca i differenti tipi di 'softirq'.
+Un tipo di softirq molto importante è il timer (``include/linux/timer.h``):
+potete programmarlo per far si che esegua funzioni dopo un determinato
+periodo di tempo.
+
+Dato che i softirq possono essere eseguiti simultaneamente su più di un
+processore, spesso diventa estenuante l'averci a che fare. Per questa ragione,
+i tasklet (``include/linux/interrupt.h``) vengo usati più di frequente:
+possono essere registrati dinamicamente (il che significa che potete averne
+quanti ne volete), e garantiscono che un qualsiasi tasklet verrà eseguito
+solo su un processore alla volta, sebbene diversi tasklet possono essere
+eseguiti simultaneamente.
+
+.. warning::
+
+    Il nome 'tasklet' è ingannevole: non hanno niente a che fare
+    con i 'processi' ('tasks'), e probabilmente hanno più a che vedere
+    con qualche pessima vodka che Alexey Kuznetsov si fece a quel tempo.
+
+Potete determinate se siete in un softirq (o tasklet) utilizzando la
+macro :c:func:`in_softirq()` (``include/linux/preempt.h``).
+
+.. warning::
+
+    State attenti che questa macro ritornerà un falso positivo
+    se :ref:`botton half lock <it_local_bh_disable>` è bloccato.
+
+Alcune regole basilari
+======================
+
+Nessuna protezione della memoria
+    Se corrompete la memoria, che sia in contesto utente o d'interruzione,
+    la macchina si pianterà. Siete sicuri che quello che volete fare
+    non possa essere fatto nello spazio utente?
+
+Nessun numero in virgola mobile o MMX
+    Il contesto della FPU non è salvato; anche se siete in contesto utente
+    lo stato dell'FPU probabilmente non corrisponde a quello del processo
+    corrente: vi incasinerete con lo stato di qualche altro processo. Se
+    volete davvero usare la virgola mobile, allora dovrete salvare e recuperare
+    lo stato dell'FPU (ed evitare cambi di contesto). Generalmente è una
+    cattiva idea; usate l'aritmetica a virgola fissa.
+
+Un limite rigido dello stack
+    A seconda della configurazione del kernel lo stack è fra 3K e 6K per la
+    maggior parte delle architetture a 32-bit; è di 14K per la maggior
+    parte di quelle a 64-bit; e spesso è condiviso con le interruzioni,
+    per cui non si può usare.
+    Evitare profonde ricorsioni ad enormi array locali nello stack
+    (allocateli dinamicamente).
+
+Il kernel Linux è portabile
+    Quindi mantenetelo tale. Il vostro codice dovrebbe essere a 64-bit ed
+    indipendente dall'ordine dei byte (endianess) di un processore. Inoltre,
+    dovreste minimizzare il codice specifico per un processore; per esempio
+    il codice assembly dovrebbe essere incapsulato in modo pulito e minimizzato
+    per facilitarne la migrazione. Generalmente questo codice dovrebbe essere
+    limitato alla parte di kernel specifica per un'architettura.
+
+ioctl: non scrivere nuove chiamate di sistema
+=============================================
+
+Una chiamata di sistema, generalmente, è scritta così::
+
+    asmlinkage long sys_mycall(int arg)
+    {
+            return 0;
+    }
+
+Primo, nella maggior parte dei casi non volete creare nuove chiamate di
+sistema.
+Create un dispositivo a caratteri ed implementate l'appropriata chiamata ioctl.
+Questo meccanismo è molto più flessibile delle chiamate di sistema: esso non
+dev'essere dichiarato in tutte le architetture nei file
+``include/asm/unistd.h`` e ``arch/kernel/entry.S``; inoltre, è improbabile
+che questo venga accettato da Linus.
+
+Se tutto quello che il vostro codice fa è leggere o scrivere alcuni parametri,
+considerate l'implementazione di un'interfaccia :c:func:`sysfs()`.
+
+All'interno di una ioctl vi trovate nel contesto utente di un processo. Quando
+avviene un errore dovete ritornare un valore negativo di errno (consultate
+``include/uapi/asm-generic/errno-base.h``,
+``include/uapi/asm-generic/errno.h`` e ``include/linux/errno.h``), altrimenti
+ritornate 0.
+
+Dopo aver dormito dovreste verificare se ci sono stati dei segnali: il modo
+Unix/Linux di gestire un segnale è di uscire temporaneamente dalla chiamata
+di sistema con l'errore ``-ERESTARTSYS``. La chiamata di sistema ritornerà
+al contesto utente, eseguirà il gestore del segnale e poi la vostra chiamata
+di sistema riprenderà (a meno che l'utente non l'abbia disabilitata). Quindi,
+dovreste essere pronti per continuare l'esecuzione, per esempio nel mezzo
+della manipolazione di una struttura dati.
+
+::
+
+    if (signal_pending(current))
+            return -ERESTARTSYS;
+
+Se dovete eseguire dei calcoli molto lunghi: pensate allo spazio utente.
+Se **davvero** volete farlo nel kernel ricordatevi di verificare periodicamente
+se dovete *lasciare* il processore (ricordatevi che, per ogni processore, c'è
+un sistema multi-processo senza diritto di prelazione).
+Esempio::
+
+    cond_resched(); /* Will sleep */
+
+Una breve nota sulla progettazione delle interfacce: il motto dei sistemi
+UNIX è "fornite meccanismi e non politiche"
+
+La ricetta per uno stallo
+=========================
+
+Non è permesso invocare una procedura che potrebbe dormire, fanno eccezione
+i seguenti casi:
+
+-  Siete in un contesto utente.
+
+-  Non trattenete alcun spinlock.
+
+-  Avete abilitato le interruzioni (in realtà, Andy Kleen dice che
+   lo schedulatore le abiliterà per voi, ma probabilmente questo non è quello
+   che volete).
+
+Da tener presente che alcune funzioni potrebbero dormire implicitamente:
+le più comuni sono quelle per l'accesso allo spazio utente (\*_user) e
+quelle per l'allocazione della memoria senza l'opzione ``GFP_ATOMIC``
+
+Dovreste sempre compilare il kernel con l'opzione ``CONFIG_DEBUG_ATOMIC_SLEEP``
+attiva, questa vi avviserà se infrangete una di queste regole.
+Se **infrangete** le regole, allora potreste bloccare il vostro scatolotto.
+
+Veramente.
+
+Alcune delle procedure più comuni
+=================================
+
+:c:func:`printk()`
+------------------
+
+Definita in ``include/linux/printk.h``
+
+:c:func:`printk()` fornisce messaggi alla console, dmesg, e al demone syslog.
+Essa è utile per il debugging o per la notifica di errori; può essere
+utilizzata anche all'interno del contesto d'interruzione, ma usatela con
+cautela: una macchina che ha la propria console inondata da messaggi diventa
+inutilizzabile. La funzione utilizza un formato stringa quasi compatibile con
+la printf ANSI C, e la concatenazione di una stringa C come primo argomento
+per indicare la "priorità"::
+
+    printk(KERN_INFO "i = %u\n", i);
+
+Consultate ``include/linux/kern_levels.h`` per gli altri valori ``KERN_``;
+questi sono interpretati da syslog come livelli. Un caso speciale:
+per stampare un indirizzo IP usate::
+
+    __be32 ipaddress;
+    printk(KERN_INFO "my ip: %pI4\n", &ipaddress);
+
+
+:c:func:`printk()` utilizza un buffer interno di 1K e non s'accorge di
+eventuali sforamenti. Accertatevi che vi basti.
+
+.. note::
+
+    Saprete di essere un vero hacker del kernel quando inizierete a digitare
+    nei vostri programmi utenti le printf come se fossero printk :)
+
+.. note::
+
+    Un'altra nota a parte: la versione originale di Unix 6 aveva un commento
+    sopra alla funzione printf: "Printf non dovrebbe essere usata per il
+    chiacchiericcio". Dovreste seguire questo consiglio.
+
+:c:func:`copy_to_user()` / :c:func:`copy_from_user()` / :c:func:`get_user()` / :c:func:`put_user()`
+---------------------------------------------------------------------------------------------------
+
+Definite in ``include/linux/uaccess.h`` / ``asm/uaccess.h``
+
+**[DORMONO]**
+
+:c:func:`put_user()` e :c:func:`get_user()` sono usate per ricevere ed
+impostare singoli valori (come int, char, o long) da e verso lo spazio utente.
+Un puntatore nello spazio utente non dovrebbe mai essere dereferenziato: i dati
+dovrebbero essere copiati usando suddette procedure. Entrambe ritornano
+``-EFAULT`` oppure 0.
+
+:c:func:`copy_to_user()` e :c:func:`copy_from_user()` sono più generiche:
+esse copiano una quantità arbitraria di dati da e verso lo spazio utente.
+
+.. warning::
+
+    Al contrario di:c:func:`put_user()` e :c:func:`get_user()`, queste
+    funzioni ritornano la quantità di dati copiati (0 è comunque un successo).
+
+[Sì, questa stupida interfaccia mi imbarazza. La battaglia torna in auge anno
+dopo anno. --RR]
+
+Le funzioni potrebbero dormire implicitamente. Queste non dovrebbero mai essere
+invocate fuori dal contesto utente (non ha senso), con le interruzioni
+disabilitate, o con uno spinlock trattenuto.
+
+:c:func:`kmalloc()`/:c:func:`kfree()`
+-------------------------------------
+
+Definite in ``include/linux/slab.h``
+
+**[POTREBBERO DORMIRE: LEGGI SOTTO]**
+
+Queste procedure sono utilizzate per la richiesta dinamica di un puntatore ad
+un pezzo di memoria allineato, esattamente come malloc e free nello spazio
+utente, ma :c:func:`kmalloc()` ha un argomento aggiuntivo per indicare alcune
+opzioni. Le opzioni più importanti sono:
+
+``GFP_KERNEL``
+    Potrebbe dormire per librarare della memoria. L'opzione fornisce il modo
+    più affidabile per allocare memoria, ma il suo uso è strettamente limitato
+    allo spazio utente.
+
+``GFP_ATOMIC``
+    Non dorme. Meno affidabile di ``GFP_KERNEL``, ma può essere usata in un
+    contesto d'interruzione. Dovreste avere **davvero** una buona strategia
+    per la gestione degli errori in caso di mancanza di memoria.
+
+``GFP_DMA``
+    Alloca memoria per il DMA sul bus ISA nello spazio d'indirizzamento
+    inferiore ai 16MB. Se non sapete cos'è allora non vi serve.
+    Molto inaffidabile.
+
+Se vedete un messaggio d'avviso per una funzione dormiente che viene chiamata
+da un contesto errato, allora probabilmente avete usato una funzione
+d'allocazione dormiente da un contesto d'interruzione senza ``GFP_ATOMIC``.
+Dovreste correggerlo. Sbrigatevi, non cincischiate.
+
+Se allocate almeno ``PAGE_SIZE``(``asm/page.h`` o ``asm/page_types.h``) byte,
+considerate l'uso di :c:func:`__get_free_pages()` (``include/linux/gfp.h``).
+Accetta un argomento che definisce l'ordine (0 per per la dimensione di una
+pagine, 1 per una doppia pagina, 2 per quattro pagine, eccetra) e le stesse
+opzioni d'allocazione viste precedentemente.
+
+Se state allocando un numero di byte notevolemnte superiore ad una pagina
+potete usare :c:func:`vmalloc()`. Essa allocherà memoria virtuale all'interno
+dello spazio kernel. Questo è un blocco di memoria fisica non contiguo, ma
+la MMU vi darà l'impressione che lo sia (quindi, sarà contiguo solo dal punto
+di vista dei processori, non dal punto di vista dei driver dei dispositivi
+esterni).
+Se per qualche strana ragione avete davvero bisogno di una grossa quantità di
+memoria fisica contigua, avete un problema: Linux non ha un buon supporto per
+questo caso d'uso perché, dopo un po' di tempo, la frammentazione della memoria
+rende l'operazione difficile. Il modo migliore per allocare un simile blocco
+all'inizio dell'avvio del sistema è attraverso la procedura
+:c:func:`alloc_bootmem()`.
+
+Prima di inventare la vostra cache per gli oggetti più usati, considerate
+l'uso di una cache slab disponibile in ``include/linux/slab.h``.
+
+:c:func:`current()`
+-------------------
+
+Definita in ``include/asm/current.h``
+
+Questa variabile globale (in realtà una macro) contiene un puntatore alla
+struttura del processo corrente, quindi è valido solo dal contesto utente.
+Per esempio, quando un processo esegue una chiamata di sistema, questo
+punterà alla struttura dati del processo chiamate.
+Nel contesto d'interruzione in suo valore **non è NULL**.
+
+:c:func:`mdelay()`/:c:func:`udelay()`
+-------------------------------------
+
+Definite in ``include/asm/delay.h`` / ``include/linux/delay.h``
+
+Le funzioni :c:func:`udelay()` e :c:func:`ndelay()` possono essere utilizzate
+per brevi pause. Non usate grandi valori perché rischiate d'avere un
+overflow - in questo contesto la funzione :c:func:`mdelay()` è utile,
+oppure considerate :c:func:`msleep()`.
+
+:c:func:`cpu_to_be32()`/:c:func:`be32_to_cpu()`/:c:func:`cpu_to_le32()`/:c:func:`le32_to_cpu()`
+-----------------------------------------------------------------------------------------------
+
+Definite in ``include/asm/byteorder.h``
+
+La famiglia di funzioni :c:func:`cpu_to_be32()` (dove "32" può essere
+sostituito da 64 o 16, e "be" con "le") forniscono un modo generico
+per fare conversioni sull'ordine dei byte (endianess): esse ritornano
+il valore convertito. Tutte le varianti supportano anche il processo inverso:
+:c:func:`be32_to_cpu()`, eccetera.
+
+Queste funzioni hanno principalmente due varianti: la variante per
+puntatori, come :c:func:`cpu_to_be32p(), che prende un puntatore
+ad un tipo, e ritorna il valore convertito. L'altra variante per
+la famiglia di conversioni "in-situ", come :c:func:`cpu_to_be32s()`,
+che convertono il valore puntato da un puntatore, e ritornano void.
+
+:c:func:`local_irq_save()`/:c:func:`local_irq_restore()`
+--------------------------------------------------------
+
+Definite in ``include/linux/irqflags.h``
+
+Queste funzioni abilitano e disabilitano le interruzioni hardware
+sul processore locale. Entrambe sono rientranti; esse salvano lo stato
+precedente nel proprio argomento ``unsigned long flags``. Se sapete
+che le interruzioni sono abilite, potete semplicemente utilizzare
+:c:func:`local_irq_disable()` e :c:func:`local_irq_enable()`.
+
+.. _it_local_bh_disable:
+
+:c:func:`local_bh_disable()`/:c:func:`local_bh_enable()`
+--------------------------------------------------------
+
+Definite in ``include/linux/bottom_half.h``
+
+
+Queste funzioni abilitano e disabilitano le interruzioni software
+sul processore locale. Entrambe sono rientranti; se le interruzioni
+software erano già state disabilitate in precedenza, rimarranno
+disabilitate anche dopo aver invocato questa coppia di funzioni.
+Lo scopo è di prevenire l'esecuzione di softirq e tasklet sul processore
+attuale.
+
+:c:func:`smp_processor_id()`
+----------------------------
+
+Definita in ``include/linux/smp.h``
+
+:c:func:`get_cpu()` nega il diritto di prelazione (quindi non potete essere
+spostati su un altro processore all'improvviso) e ritorna il numero
+del processore attuale, fra 0 e ``NR_CPUS``. Da notare che non è detto
+che la numerazione dei processori sia continua. Quando avete terminato,
+ritornate allo stato precedente con :c:func:`put_cpu()`.
+
+Se sapete che non dovete essere interrotti da altri processi (per esempio,
+se siete in un contesto d'interruzione, o il diritto di prelazione
+è disabilitato) potete utilizzare smp_processor_id().
+
+
+``__init``/``__exit``/``__initdata``
+------------------------------------
+
+Definite in  ``include/linux/init.h``
+
+Dopo l'avvio, il kernel libera una sezione speciale; le funzioni marcate
+con ``__init`` e le strutture dati marcate con ``__initdata`` vengono
+eliminate dopo il completamento dell'avvio: in modo simile i moduli eliminano
+questa memoria dopo l'inizializzazione. ``__exit`` viene utilizzato per
+dichiarare che una funzione verrà utilizzata solo in fase di rimozione:
+la detta funzione verrà eliminata quando il file che la contiene non è
+compilato come modulo. Guardate l'header file per informazioni. Da notare che
+non ha senso avere una funzione marcata come ``__init`` e al tempo stesso
+esportata ai moduli utilizzando :c:func:`EXPORT_SYMBOL()` o
+:c:func:`EXPORT_SYMBOL_GPL()` - non funzionerà.
+
+
+:c:func:`__initcall()`/:c:func:`module_init()`
+----------------------------------------------
+
+Definite in  ``include/linux/init.h`` / ``include/linux/module.h``
+
+Molte parti del kernel funzionano bene come moduli (componenti del kernel
+caricabili dinamicamente). L'utilizzo delle macro :c:func:`module_init()`
+e :c:func:`module_exit()` semplifica la scrittura di codice che può funzionare
+sia come modulo, sia come parte del kernel, senza l'ausilio di #ifdef.
+
+La macro :c:func:`module_init()` definisce quale funzione dev'essere
+chiamata quando il modulo viene inserito (se il file è stato compilato come
+tale), o in fase di avvio : se il file non è stato compilato come modulo la
+macro :c:func:`module_init()` diventa equivalente a :c:func:`__initcall()`,
+la quale, tramite qualche magia del linker, s'assicura che la funzione venga
+chiamata durante l'avvio.
+
+La funzione può ritornare un numero d'errore negativo per scatenare un
+fallimento del caricamento (sfortunatamente, questo non ha effetto se il
+modulo è compilato come parte integrante del kernel). Questa funzione è chiamata
+in contesto utente con le interruzioni abilitate, quindi potrebbe dormire.
+
+
+:c:func:`module_exit()`
+-----------------------
+
+
+Definita in  ``include/linux/module.h``
+
+Questa macro definisce la funzione che dev'essere chiamata al momento della
+rimozione (o mai, nel caso in cui il file sia parte integrante del kernel).
+Essa verrà chiamata solo quando il contatore d'uso del modulo raggiunge lo
+zero. Questa funzione può anche dormire, ma non può fallire: tutto dev'essere
+ripulito prima che la funzione ritorni.
+
+Da notare che questa macro è opzionale: se non presente, il modulo non sarà
+removibile (a meno che non usiate 'rmmod -f' ).
+
+
+:c:func:`try_module_get()`/:c:func:`module_put()`
+-------------------------------------------------
+
+Definite in ``include/linux/module.h``
+
+Queste funzioni maneggiano il contatore d'uso del modulo per proteggerlo dalla
+rimozione (in aggiunta, un modulo non può essere rimosso se un altro modulo
+utilizzo uno dei sui simboli esportati: vedere di seguito). Prima di eseguire
+codice del modulo, dovreste chiamare :c:func:`try_module_get()` su quel modulo:
+se fallisce significa che il modulo è stato rimosso e dovete agire come se
+non fosse presente. Altrimenti, potete accedere al modulo in sicurezza, e
+chiamare :c:func:`module_put()` quando avete finito.
+
+La maggior parte delle strutture registrabili hanno un campo owner
+(proprietario), come nella struttura
+:c:type:`struct file_operations <file_operations>`.
+Impostate questo campo al valore della macro ``THIS_MODULE``.
+
+
+Code d'attesa ``include/linux/wait.h``
+======================================
+
+**[DORMONO]**
+
+Una coda d'attesa è usata per aspettare che qualcuno vi attivi quando una
+certa condizione s'avvera. Per evitare corse critiche, devono essere usate
+con cautela. Dichiarate una :c:type:`wait_queue_head_t`, e poi i processi
+che vogliono attendere il verificarsi di quella condizione dichiareranno
+una :c:type:`wait_queue_entry_t` facendo riferimento a loro stessi, poi
+metteranno questa in coda.
+
+Dichiarazione
+-------------
+
+Potere dichiarare una ``wait_queue_head_t`` utilizzando la macro
+:c:func:`DECLARE_WAIT_QUEUE_HEAD()` oppure utilizzando la procedura
+:c:func:`init_waitqueue_head()` nel vostro codice d'inizializzazione.
+
+Accodamento
+-----------
+
+Mettersi in una coda d'attesa è piuttosto complesso, perché dovete
+mettervi in coda prima di verificare la condizione. Esiste una macro
+a questo scopo: :c:func:`wait_event_interruptible()` (``include/linux/wait.h``).
+Il primo argomento è la testa della coda d'attesa, e il secondo è
+un'espressione che dev'essere valutata; la macro ritorna 0 quando questa
+espressione è vera, altrimenti ``-ERESTARTSYS`` se è stato ricevuto un segnale.
+La versione :c:func:`wait_event()` ignora i segnali.
+
+Svegliare una procedura in coda
+-------------------------------
+
+Chiamate :c:func:`wake_up()` (``include/linux/wait.h``); questa attiverà tutti
+i processi in coda. Ad eccezione se uno di questi è impostato come
+``TASK_EXCLUSIVE``, in questo caso i rimanenti non verranno svegliati.
+Nello stesso header file esistono altre varianti di questa funzione.
+
+Operazioni atomiche
+===================
+
+Certe operazioni sono garantite come atomiche su tutte le piattaforme.
+Il primo gruppo di operazioni utilizza :c:type:`atomic_t`
+(``include/asm/atomic.h``); questo contiene un intero con segno (minimo 32bit),
+e dovete utilizzare queste funzione per modificare o leggere variabili di tipo
+:c:type:`atomic_t`. :c:func:`atomic_read()` e :c:func:`atomic_set()` leggono ed
+impostano il contatore, :c:func:`atomic_add()`, :c:func:`atomic_sub()`,
+:c:func:`atomic_inc()`, :c:func:`atomic_dec()`, e
+:c:func:`atomic_dec_and_test()` (ritorna vero se raggiunge zero dopo essere
+stata decrementata).
+
+Sì. Ritorna vero (ovvero != 0) se la variabile atomica è zero.
+
+Da notare che queste funzioni sono più lente rispetto alla normale aritmetica,
+e quindi non dovrebbero essere usate a sproposito.
+
+Il secondo gruppo di operazioni atomiche sono definite in
+``include/linux/bitops.h`` ed agiscono sui bit d'una variabile di tipo
+``unsigned long``. Queste operazioni prendono come argomento un puntatore
+alla variabile, e un numero di bit dove 0 è quello meno significativo.
+:c:func:`set_bit()`, :c:func:`clear_bit()` e :c:func:`change_bit()`
+impostano, cancellano, ed invertono il bit indicato.
+:c:func:`test_and_set_bit()`, :c:func:`test_and_clear_bit()` e
+:c:func:`test_and_change_bit()` fanno la stessa cosa, ad eccezione che
+ritornano vero se il bit era impostato; queste sono particolarmente
+utili quando si vuole impostare atomicamente dei flag.
+
+Con queste operazioni è possibile utilizzare indici di bit che eccedono
+il valore ``BITS_PER_LONG``. Il comportamento è strano sulle piattaforme
+big-endian quindi è meglio evitarlo.
+
+Simboli
+=======
+
+All'interno del kernel, si seguono le normali regole del linker (ovvero,
+a meno che un simbolo non venga dichiarato con visibilita limitata ad un
+file con la parola chiave ``static``, esso può essere utilizzato in qualsiasi
+parte del kernel). Nonostante ciò, per i moduli, esiste una tabella dei
+simboli esportati che limita i punti di accesso al kernel. Anche i moduli
+possono esportare simboli.
+
+:c:func:`EXPORT_SYMBOL()`
+-------------------------
+
+Definita in ``include/linux/export.h``
+
+Questo è il classico metodo per esportare un simbolo: i moduli caricati
+dinamicamente potranno utilizzare normalmente il simbolo.
+
+:c:func:`EXPORT_SYMBOL_GPL()`
+-----------------------------
+
+Definita in ``include/linux/export.h``
+
+Essa è simile a :c:func:`EXPORT_SYMBOL()` ad eccezione del fatto che i
+simboli esportati con :c:func:`EXPORT_SYMBOL_GPL()` possono essere
+utilizzati solo dai moduli che hanno dichiarato una licenza compatibile
+con la GPL attraverso :c:func:`MODULE_LICENSE()`. Questo implica che la
+funzione esportata è considerata interna, e non una vera e propria interfaccia.
+Alcuni manutentori e sviluppatori potrebbero comunque richiedere
+:c:func:`EXPORT_SYMBOL_GPL()` quando si aggiungono nuove funzionalità o
+interfacce.
+
+Procedure e convenzioni
+=======================
+
+Liste doppiamente concatenate ``include/linux/list.h``
+------------------------------------------------------
+
+Un tempo negli header del kernel c'erano tre gruppi di funzioni per
+le liste concatenate, ma questa è stata la vincente. Se non avete particolari
+necessità per una semplice lista concatenata, allora questa è una buona scelta.
+
+In particolare, :c:func:`list_for_each_entry()` è utile.
+
+Convenzione dei valori di ritorno
+---------------------------------
+
+Per codice chiamato in contesto utente, è molto comune sfidare le convenzioni
+C e ritornare 0 in caso di successo, ed un codice di errore negativo
+(eg. ``-EFAULT``) nei casi fallimentari. Questo potrebbe essere controintuitivo
+a prima vista, ma è abbastanza diffuso nel kernel.
+
+Utilizzate :c:func:`ERR_PTR()` (``include/linux/err.h``) per codificare
+un numero d'errore negativo in un puntatore, e :c:func:`IS_ERR()` e
+:c:func:`PTR_ERR()` per recuperarlo di nuovo: così si evita d'avere un
+puntatore dedicato per il numero d'errore. Da brividi, ma in senso positivo.
+
+Rompere la compilazione
+-----------------------
+
+Linus e gli altri sviluppatori a volte cambiano i nomi delle funzioni e
+delle strutture nei kernel in sviluppo; questo non è solo per tenere
+tutti sulle spine: questo riflette cambiamenti fondamentati (eg. la funzione
+non può più essere chiamata con le funzioni attive, o fa controlli aggiuntivi,
+o non fa più controlli che venivano fatti in precedenza). Solitamente a questo
+s'accompagna un'adeguata e completa nota sulla lista di discussone
+linux-kernel; cercate negli archivi.
+Solitamente eseguire una semplice sostituzione su tutto un file rendere
+le cose **peggiori**.
+
+Inizializzazione dei campi d'una struttura
+------------------------------------------
+
+Il metodo preferito per l'inizializzazione delle strutture è quello
+di utilizzare gli inizializzatori designati, come definiti nello
+standard ISO C99, eg::
+
+    static struct block_device_operations opt_fops = {
+            .open               = opt_open,
+            .release            = opt_release,
+            .ioctl              = opt_ioctl,
+            .check_media_change = opt_media_change,
+    };
+
+Questo rende più facile la ricerca con grep, e rende più chiaro quale campo
+viene impostato. Dovreste fare così perché si mostra meglio.
+
+Estensioni GNU
+--------------
+
+Le estensioni GNU sono esplicitamente permesse nel kernel Linux. Da notare
+che alcune delle più complesse non sono ben supportate, per via dello scarso
+sviluppo, ma le seguenti sono da considerarsi la norma (per maggiori dettagli,
+leggete la sezione "C Extensions" nella pagina info di GCC - Sì, davvero
+la pagina info, la pagina man è solo un breve riassunto delle cose nella
+pagina info).
+
+-  Funzioni inline
+
+-  Istruzioni in espressioni (ie. il costrutto ({ and }) ).
+
+-  Dichiarate attributi di una funzione / variabile / tipo
+   (__attribute__)
+
+-  typeof
+
+-  Array con lunghezza zero
+
+-  Macro varargs
+
+-  Aritmentica sui puntatori void
+
+-  Inizializzatori non costanti
+
+-  Istruzioni assembler (non al di fuori di 'arch/' e 'include/asm/')
+
+-  Nomi delle funzioni come stringhe (__func__).
+
+-  __builtin_constant_p()
+
+Siate sospettosi quando utilizzate long long nel kernel, il codice generato
+da gcc è orribile ed anche peggio: le divisioni e le moltiplicazioni non
+funzionano sulle piattaforme i386 perché le rispettive funzioni di runtime
+di GCC non sono incluse nell'ambiente del kernel.
+
+C++
+---
+
+Solitamente utilizzare il C++ nel kernel è una cattiva idea perché
+il kernel non fornisce il necessario ambiente di runtime e gli header file
+non sono stati verificati. Rimane comunque possibile, ma non consigliato.
+Se davvero volete usarlo, almeno evitate le eccezioni.
+
+NUMif
+-----
+
+Viene generalmente considerato più pulito l'uso delle macro negli header file
+(o all'inizio dei file .c) per astrarre funzioni piuttosto che utlizzare
+l'istruzione di pre-processore \`#if' all'interno del codice sorgente.
+
+Mettere le vostre cose nel kernel
+=================================
+
+Al fine d'avere le vostre cose in ordine per l'inclusione ufficiale, o
+anche per avere patch pulite, c'è del lavoro amministrativo da fare:
+
+-  Trovare di chi è lo stagno in cui state pisciando. Guardare in cima
+   ai file sorgenti, all'interno del file ``MAINTAINERS``, ed alla fine
+   di tutti nel file ``CREDITS``. Dovreste coordinarvi con queste persone
+   per evitare di duplicare gli sforzi, o provare qualcosa che è già stato
+   rigettato.
+
+   Assicuratevi di mettere il vostro nome ed indirizzo email in cima a
+   tutti i file che create o che mangeggiate significativamente. Questo è
+   il primo posto dove le persone guarderanno quando troveranno un baco,
+   o quando **loro** vorranno fare una modifica.
+
+-  Solitamente vorrete un'opzione di configurazione per la vostra modifica
+   al kernel. Modificate ``Kconfig`` nella cartella giusta. Il linguaggio
+   Config è facile con copia ed incolla, e c'è una completa documentazione
+   nel file ``Documentation/kbuild/kconfig-language.txt``.
+
+   Nella descrizione della vostra opzione, assicuratevi di parlare sia agli
+   utenti esperti sia agli utente che non sanno nulla del vostro lavoro.
+   Menzionate qui le incompatibilità ed i problemi. Chiaramente la
+   descrizione deve terminare con “if in doubt, say N” (se siete in dubbio,
+   dite N) (oppure, occasionalmente, \`Y'); questo è per le persone che non
+   hanno idea di che cosa voi stiate parlando.
+
+-  Modificate il file ``Makefile``: le variabili CONFIG sono esportate qui,
+   quindi potete solitamente aggiungere una riga come la seguete
+   "obj-$(CONFIG_xxx) += xxx.o". La sintassi è documentata nel file
+   ``Documentation/kbuild/makefiles.txt``.
+
+-  Aggiungete voi stessi in ``CREDITS`` se avete fatto qualcosa di notevole,
+   solitamente qualcosa che supera il singolo file (comunque il vostro nome
+   dovrebbe essere all'inizio dei file sorgenti). ``MAINTAINERS`` significa
+   che volete essere consultati quando vengono fatte delle modifiche ad un
+   sottosistema, e quando ci sono dei bachi; questo implica molto di più
+   di un semplice impegno su una parte del codice.
+
+-  Infine, non dimenticatevi di leggere
+   ``Documentation/process/submitting-patches.rst`` e possibilmente anche
+   ``Documentation/process/submitting-drivers.rst``.
+
+Trucchetti del kernel
+=====================
+
+Dopo una rapida occhiata al codice, questi sono i preferiti. Sentitevi liberi
+di aggiungerne altri.
+
+``arch/x86/include/asm/delay.h``::
+
+    #define ndelay(n) (__builtin_constant_p(n) ? \
+            ((n) > 20000 ? __bad_ndelay() : __const_udelay((n) * 5ul)) : \
+            __ndelay(n))
+
+
+``include/linux/fs.h``::
+
+    /*
+     * Kernel pointers have redundant information, so we can use a
+     * scheme where we can return either an error code or a dentry
+     * pointer with the same return value.
+     *
+     * This should be a per-architecture thing, to allow different
+     * error and pointer decisions.
+     */
+     #define ERR_PTR(err)    ((void *)((long)(err)))
+     #define PTR_ERR(ptr)    ((long)(ptr))
+     #define IS_ERR(ptr)     ((unsigned long)(ptr) > (unsigned long)(-1000))
+
+``arch/x86/include/asm/uaccess_32.h:``::
+
+    #define copy_to_user(to,from,n)                         \
+            (__builtin_constant_p(n) ?                      \
+             __constant_copy_to_user((to),(from),(n)) :     \
+             __generic_copy_to_user((to),(from),(n)))
+
+
+``arch/sparc/kernel/head.S:``::
+
+    /*
+     * Sun people can't spell worth damn. "compatability" indeed.
+     * At least we *know* we can't spell, and use a spell-checker.
+     */
+
+    /* Uh, actually Linus it is I who cannot spell. Too much murky
+     * Sparc assembly will do this to ya.
+     */
+    C_LABEL(cputypvar):
+            .asciz "compatibility"
+
+    /* Tested on SS-5, SS-10. Probably someone at Sun applied a spell-checker. */
+            .align 4
+    C_LABEL(cputypvar_sun4m):
+            .asciz "compatible"
+
+
+``arch/sparc/lib/checksum.S:``::
+
+            /* Sun, you just can't beat me, you just can't.  Stop trying,
+             * give up.  I'm serious, I am going to kick the living shit
+             * out of you, game over, lights out.
+             */
+
+
+Ringraziamenti
+==============
+
+Ringrazio Andi Kleen per le sue idee, le risposte alle mie domande,
+le correzioni dei miei errori, l'aggiunta di contenuti, eccetera.
+Philipp Rumpf per l'ortografia e per aver reso più chiaro il testo, e
+per alcuni eccellenti punti tutt'altro che ovvi. Werner Almesberger
+per avermi fornito un ottimo riassunto di :c:func:`disable_irq()`,
+e Jes Sorensen e Andrea Arcangeli per le precisazioni. Michael Elizabeth
+Chastain per aver verificato ed aggiunto la sezione configurazione.
+Telsa Gwynne per avermi insegnato DocBook.
diff --git a/Documentation/translations/it_IT/kernel-hacking/index.rst b/Documentation/translations/it_IT/kernel-hacking/index.rst
new file mode 100644
index 000000000000..50228380bd50
--- /dev/null
+++ b/Documentation/translations/it_IT/kernel-hacking/index.rst
@@ -0,0 +1,16 @@
+.. include:: ../disclaimer-ita.rst
+
+:Original: :ref:`Documentation/kernel-hacking/index.rst <kernel_hacking>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
+
+.. _it_kernel_hacking:
+
+============================
+Guida all'hacking del kernel
+============================
+
+.. toctree::
+   :maxdepth: 2
+
+   hacking
+   locking
diff --git a/Documentation/translations/it_IT/kernel-hacking/locking.rst b/Documentation/translations/it_IT/kernel-hacking/locking.rst
new file mode 100644
index 000000000000..753643622c23
--- /dev/null
+++ b/Documentation/translations/it_IT/kernel-hacking/locking.rst
@@ -0,0 +1,1493 @@
+.. include:: ../disclaimer-ita.rst
+
+:Original: :ref:`Documentation/kernel-hacking/locking.rst <kernel_hacking_lock>`
+:Translator: Federico Vaga <federico.vaga@vaga.pv.it>
+
+.. _it_kernel_hacking_lock:
+
+==========================================
+L'inaffidabile guida alla sincronizzazione
+==========================================
+
+:Author: Rusty Russell
+
+Introduzione
+============
+
+Benvenuto, alla notevole ed inaffidabile guida ai problemi di sincronizzazione
+(locking) nel kernel. Questo documento descrive il sistema di sincronizzazione
+nel kernel Linux 2.6.
+
+Dato il largo utilizzo del multi-threading e della prelazione nel kernel
+Linux, chiunque voglia dilettarsi col kernel deve conoscere i concetti
+fondamentali della concorrenza e della sincronizzazione nei sistemi
+multi-processore.
+
+Il problema con la concorrenza
+==============================
+
+(Saltatelo se sapete già cos'è una corsa critica).
+
+In un normale programma, potete incrementare un contatore nel seguente modo:
+
+::
+
+          contatore++;
+
+Questo è quello che vi aspettereste che accada sempre:
+
+
+.. table:: Risultati attesi
+
+  +------------------------------------+------------------------------------+
+  | Istanza 1                          | Istanza 2                          |
+  +====================================+====================================+
+  | leggi contatore (5)                |                                    |
+  +------------------------------------+------------------------------------+
+  | aggiungi 1 (6)                     |                                    |
+  +------------------------------------+------------------------------------+
+  | scrivi contatore (6)               |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | leggi contatore (6)                |
+  +------------------------------------+------------------------------------+
+  |                                    | aggiungi 1 (7)                     |
+  +------------------------------------+------------------------------------+
+  |                                    | scrivi contatore (7)               |
+  +------------------------------------+------------------------------------+
+
+Questo è quello che potrebbe succedere in realtà:
+
+.. table:: Possibile risultato
+
+  +------------------------------------+------------------------------------+
+  | Istanza 1                          | Istanza 2                          |
+  +====================================+====================================+
+  | leggi contatore (5)                |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | leggi contatore (5)                |
+  +------------------------------------+------------------------------------+
+  | aggiungi 1 (6)                     |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | aggiungi 1 (6)                     |
+  +------------------------------------+------------------------------------+
+  | scrivi contatore (6)               |                                    |
+  +------------------------------------+------------------------------------+
+  |                                    | scrivi contatore (6)               |
+  +------------------------------------+------------------------------------+
+
+
+Corse critiche e sezioni critiche
+---------------------------------
+
+Questa sovrapposizione, ovvero quando un risultato dipende dal tempo che
+intercorre fra processi diversi, è chiamata corsa critica. La porzione
+di codice che contiene questo problema è chiamata sezione critica.
+In particolar modo da quando Linux ha incominciato a girare su
+macchine multi-processore, le sezioni critiche sono diventate uno dei
+maggiori problemi di progettazione ed implementazione del kernel.
+
+La prelazione può sortire gli stessi effetti, anche se c'è una sola CPU:
+interrompendo un processo nella sua sezione critica otterremo comunque
+la stessa corsa critica. In questo caso, il thread che si avvicenda
+nell'esecuzione potrebbe eseguire anch'esso la sezione critica.
+
+La soluzione è quella di riconoscere quando avvengono questi accessi
+simultanei, ed utilizzare i *lock* per accertarsi che solo un'istanza
+per volta possa entrare nella sezione critica. Il kernel offre delle buone
+funzioni a questo scopo. E poi ci sono quelle meno buone, ma farò finta
+che non esistano.
+
+Sincronizzazione nel kernel Linux
+=================================
+
+Se posso darvi un suggerimento: non dormite mai con qualcuno più pazzo di
+voi. Ma se dovessi darvi un suggerimento sulla sincronizzazione:
+**mantenetela semplice**.
+
+Siate riluttanti nell'introduzione di nuovi *lock*.
+
+Abbastanza strano, quest'ultimo è l'esatto opposto del mio suggerimento
+su quando **avete** dormito con qualcuno più pazzo di voi. E dovreste
+pensare a prendervi un cane bello grande.
+
+I due principali tipi di *lock* nel kernel: spinlock e mutex
+------------------------------------------------------------
+
+Ci sono due tipi principali di *lock* nel kernel. Il tipo fondamentale è lo
+spinlock (``include/asm/spinlock.h``), un semplice *lock* che può essere
+trattenuto solo da un processo: se non si può trattenere lo spinlock, allora
+rimane in attesa attiva (in inglese *spinning*) finché non ci riesce.
+Gli spinlock sono molto piccoli e rapidi, possono essere utilizzati ovunque.
+
+Il secondo tipo è il mutex (``include/linux/mutex.h``): è come uno spinlock,
+ma potreste bloccarvi trattenendolo. Se non potete trattenere un mutex
+il vostro processo si auto-sospenderà; verrà riattivato quando il mutex
+verrà rilasciato. Questo significa che il processore potrà occuparsi d'altro
+mentre il vostro processo è in attesa. Esistono molti casi in cui non potete
+permettervi di sospendere un processo (vedere
+:ref:`Quali funzioni possono essere chiamate in modo sicuro dalle interruzioni? <it_sleeping-things>`)
+e quindi dovrete utilizzare gli spinlock.
+
+Nessuno di questi *lock* è ricorsivo: vedere
+:ref:`Stallo: semplice ed avanzato <it_deadlock>`
+
+I *lock* e i kernel per sistemi monoprocessore
+----------------------------------------------
+
+Per i kernel compilati senza ``CONFIG_SMP`` e senza ``CONFIG_PREEMPT``
+gli spinlock non esistono. Questa è un'ottima scelta di progettazione:
+quando nessun altro processo può essere eseguito in simultanea, allora
+non c'è la necessità di avere un *lock*.
+
+Se il kernel è compilato senza ``CONFIG_SMP`` ma con ``CONFIG_PREEMPT``,
+allora gli spinlock disabilitano la prelazione; questo è sufficiente a
+prevenire le corse critiche. Nella maggior parte dei casi, possiamo considerare
+la prelazione equivalente ad un sistema multi-processore senza preoccuparci
+di trattarla indipendentemente.
+
+Dovreste verificare sempre la sincronizzazione con le opzioni ``CONFIG_SMP`` e
+``CONFIG_PREEMPT`` abilitate, anche quando non avete un sistema
+multi-processore, questo vi permetterà di identificare alcuni problemi
+di sincronizzazione.
+
+Come vedremo di seguito, i mutex continuano ad esistere perché sono necessari
+per la sincronizzazione fra processi in contesto utente.
+
+Sincronizzazione in contesto utente
+-----------------------------------
+
+Se avete una struttura dati che verrà utilizzata solo dal contesto utente,
+allora, per proteggerla, potete utilizzare un semplice mutex
+(``include/linux/mutex.h``). Questo è il caso più semplice: inizializzate il
+mutex; invocate :c:func:`mutex_lock_interruptible()` per trattenerlo e
+:c:func:`mutex_unlock()` per rilasciarlo. C'è anche :c:func:`mutex_lock()`
+ma questa dovrebbe essere evitata perché non ritorna in caso di segnali.
+
+Per esempio: ``net/netfilter/nf_sockopt.c`` permette la registrazione
+di nuove chiamate per :c:func:`setsockopt()` e :c:func:`getsockopt()`
+usando la funzione :c:func:`nf_register_sockopt()`. La registrazione e
+la rimozione vengono eseguite solamente quando il modulo viene caricato
+o scaricato (e durante l'avvio del sistema, qui non abbiamo concorrenza),
+e la lista delle funzioni registrate viene consultata solamente quando
+:c:func:`setsockopt()` o :c:func:`getsockopt()` sono sconosciute al sistema.
+In questo caso ``nf_sockopt_mutex`` è perfetto allo scopo, in particolar modo
+visto che setsockopt e getsockopt potrebbero dormire.
+
+Sincronizzazione fra il contesto utente e i softirq
+---------------------------------------------------
+
+Se un softirq condivide dati col contesto utente, avete due problemi.
+Primo, il contesto utente corrente potrebbe essere interroto da un softirq,
+e secondo, la sezione critica potrebbe essere eseguita da un altro
+processore. Questo è quando :c:func:`spin_lock_bh()`
+(``include/linux/spinlock.h``) viene utilizzato. Questo disabilita i softirq
+sul processore e trattiene il *lock*. Invece, :c:func:`spin_unlock_bh()` fa
+l'opposto. (Il suffisso '_bh' è un residuo storico che fa riferimento al
+"Bottom Halves", il vecchio nome delle interruzioni software. In un mondo
+perfetto questa funzione si chiamerebbe 'spin_lock_softirq()').
+
+Da notare che in questo caso potete utilizzare anche :c:func:`spin_lock_irq()`
+o :c:func:`spin_lock_irqsave()`, queste fermano anche le interruzioni hardware:
+vedere :ref:`Contesto di interruzione hardware <it_hardirq-context>`.
+
+Questo funziona alla perfezione anche sui sistemi monoprocessore: gli spinlock
+svaniscono e questa macro diventa semplicemente :c:func:`local_bh_disable()`
+(``include/linux/interrupt.h``), la quale impedisce ai softirq d'essere
+eseguiti.
+
+Sincronizzazione fra contesto utente e i tasklet
+------------------------------------------------
+
+Questo caso è uguale al precedente, un tasklet viene eseguito da un softirq.
+
+Sincronizzazione fra contesto utente e i timer
+----------------------------------------------
+
+Anche questo caso è uguale al precedente, un timer viene eseguito da un
+softirq.
+Dal punto di vista della sincronizzazione, tasklet e timer sono identici.
+
+Sincronizzazione fra tasklet e timer
+------------------------------------
+
+Qualche volta un tasklet od un timer potrebbero condividere i dati con
+un altro tasklet o timer
+
+Lo stesso tasklet/timer
+~~~~~~~~~~~~~~~~~~~~~~~
+
+Dato che un tasklet non viene mai eseguito contemporaneamente su due
+processori, non dovete preoccuparvi che sia rientrante (ovvero eseguito
+più volte in contemporanea), perfino su sistemi multi-processore.
+
+Differenti tasklet/timer
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+Se un altro tasklet/timer vuole condividere dati col vostro tasklet o timer,
+allora avrete bisogno entrambe di :c:func:`spin_lock()` e
+:c:func:`spin_unlock()`. Qui :c:func:`spin_lock_bh()` è inutile, siete già
+in un tasklet ed avete la garanzia che nessun altro verrà eseguito sullo
+stesso processore.
+
+Sincronizzazione fra softirq
+----------------------------
+
+Spesso un softirq potrebbe condividere dati con se stesso o un tasklet/timer.
+
+Lo stesso softirq
+~~~~~~~~~~~~~~~~~
+
+Lo stesso softirq può essere eseguito su un diverso processore: allo scopo
+di migliorare le prestazioni potete utilizzare dati riservati ad ogni
+processore (vedere :ref:`Dati per processore <it_per-cpu>`). Se siete arrivati
+fino a questo punto nell'uso dei softirq, probabilmente tenete alla scalabilità
+delle prestazioni abbastanza da giustificarne la complessità aggiuntiva.
+
+Dovete utilizzare :c:func:`spin_lock()` e :c:func:`spin_unlock()` per
+proteggere i dati condivisi.
+
+Diversi Softirqs
+~~~~~~~~~~~~~~~~
+
+Dovete utilizzare :c:func:`spin_lock()` e :c:func:`spin_unlock()` per
+proteggere i dati condivisi, che siano timer, tasklet, diversi softirq o
+lo stesso o altri softirq: uno qualsiasi di essi potrebbe essere in esecuzione
+su un diverso processore.
+
+.. _`it_hardirq-context`:
+
+Contesto di interruzione hardware
+=================================
+
+Solitamente le interruzioni hardware comunicano con un tasklet o un softirq.
+Spesso questo si traduce nel mettere in coda qualcosa da fare che verrà
+preso in carico da un softirq.
+
+Sincronizzazione fra interruzioni hardware e softirq/tasklet
+------------------------------------------------------------
+
+Se un gestore di interruzioni hardware condivide dati con un softirq, allora
+avrete due preoccupazioni. Primo, il softirq può essere interrotto da
+un'interruzione hardware, e secondo, la sezione critica potrebbe essere
+eseguita da un'interruzione hardware su un processore diverso. Questo è il caso
+dove :c:func:`spin_lock_irq()` viene utilizzato. Disabilita le interruzioni
+sul processore che l'esegue, poi trattiene il lock. :c:func:`spin_unlock_irq()`
+fa l'opposto.
+
+Il gestore d'interruzione hardware non usa :c:func:`spin_lock_irq()` perché
+i softirq non possono essere eseguiti quando il gestore d'interruzione hardware
+è in esecuzione: per questo si può usare :c:func:`spin_lock()`, che è un po'
+più veloce. L'unica eccezione è quando un altro gestore d'interruzioni
+hardware utilizza lo stesso *lock*: :c:func:`spin_lock_irq()` impedirà a questo
+secondo gestore di interrompere quello in esecuzione.
+
+Questo funziona alla perfezione anche sui sistemi monoprocessore: gli spinlock
+svaniscono e questa macro diventa semplicemente :c:func:`local_irq_disable()`
+(``include/asm/smp.h``), la quale impedisce a softirq/tasklet/BH d'essere
+eseguiti.
+
+:c:func:`spin_lock_irqsave()` (``include/linux/spinlock.h``) è una variante che
+salva lo stato delle interruzioni in una variabile, questa verrà poi passata
+a :c:func:`spin_unlock_irqrestore()`. Questo significa che lo stesso codice
+potrà essere utilizzato in un'interruzione hardware (dove le interruzioni sono
+già disabilitate) e in un softirq (dove la disabilitazione delle interruzioni
+è richiesta).
+
+Da notare che i softirq (e quindi tasklet e timer) sono eseguiti al ritorno
+da un'interruzione hardware, quindi :c:func:`spin_lock_irq()` interrompe
+anche questi. Tenuto conto di questo si può dire che
+:c:func:`spin_lock_irqsave()` è la funzione di sincronizzazione più generica
+e potente.
+
+Sincronizzazione fra due gestori d'interruzioni hardware
+--------------------------------------------------------
+
+Condividere dati fra due gestori di interruzione hardware è molto raro, ma se
+succede, dovreste usare :c:func:`spin_lock_irqsave()`: è una specificità
+dell'architettura il fatto che tutte le interruzioni vengano interrotte
+quando si eseguono di gestori di interruzioni.
+
+Bigino della sincronizzazione
+=============================
+
+Pete Zaitcev ci offre il seguente riassunto:
+
+-  Se siete in un contesto utente (una qualsiasi chiamata di sistema)
+   e volete sincronizzarvi con altri processi, usate i mutex. Potete trattenere
+   il mutex e dormire (``copy_from_user*(`` o ``kmalloc(x,GFP_KERNEL)``).
+
+-  Altrimenti (== i dati possono essere manipolati da un'interruzione) usate
+   :c:func:`spin_lock_irqsave()` e :c:func:`spin_unlock_irqrestore()`.
+
+-  Evitate di trattenere uno spinlock per più di 5 righe di codice incluse
+   le chiamate a funzione (ad eccezione di quell per l'accesso come
+   :c:func:`readb()`).
+
+Tabella dei requisiti minimi
+----------------------------
+
+La tabella seguente illustra i requisiti **minimi** per la sincronizzazione fra
+diversi contesti. In alcuni casi, lo stesso contesto può essere eseguito solo
+da un processore per volta, quindi non ci sono requisiti per la
+sincronizzazione (per esempio, un thread può essere eseguito solo su un
+processore alla volta, ma se deve condividere dati con un altro thread, allora
+la sincronizzazione è necessaria).
+
+Ricordatevi il suggerimento qui sopra: potete sempre usare
+:c:func:`spin_lock_irqsave()`, che è un sovrainsieme di tutte le altre funzioni
+per spinlock.
+
+============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ==============
+.              IRQ Handler A IRQ Handler B Softirq A Softirq B Tasklet A Tasklet B Timer A Timer B User Context A User Context B
+============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ==============
+IRQ Handler A  None
+IRQ Handler B  SLIS          None
+Softirq A      SLI           SLI           SL
+Softirq B      SLI           SLI           SL        SL
+Tasklet A      SLI           SLI           SL        SL        None
+Tasklet B      SLI           SLI           SL        SL        SL        None
+Timer A        SLI           SLI           SL        SL        SL        SL        None
+Timer B        SLI           SLI           SL        SL        SL        SL        SL      None
+User Context A SLI           SLI           SLBH      SLBH      SLBH      SLBH      SLBH    SLBH    None
+User Context B SLI           SLI           SLBH      SLBH      SLBH      SLBH      SLBH    SLBH    MLI            None
+============== ============= ============= ========= ========= ========= ========= ======= ======= ============== ==============
+
+Table: Tabella dei requisiti per la sincronizzazione
+
++--------+----------------------------+
+| SLIS   | spin_lock_irqsave          |
++--------+----------------------------+
+| SLI    | spin_lock_irq              |
++--------+----------------------------+
+| SL     | spin_lock                  |
++--------+----------------------------+
+| SLBH   | spin_lock_bh               |
++--------+----------------------------+
+| MLI    | mutex_lock_interruptible   |
++--------+----------------------------+
+
+Table: Legenda per la tabella dei requisiti per la sincronizzazione
+
+Le funzioni *trylock*
+=====================
+
+Ci sono funzioni che provano a trattenere un *lock* solo una volta e
+ritornano immediatamente comunicato il successo od il fallimento
+dell'operazione. Posso essere usate quando non serve accedere ai dati
+protetti dal *lock* quando qualche altro thread lo sta già facendo
+trattenendo il *lock*. Potrete acquisire il *lock* più tardi se vi
+serve accedere ai dati protetti da questo *lock*.
+
+La funzione :c:func:`spin_trylock()` non ritenta di acquisire il *lock*,
+se ci riesce al primo colpo ritorna un valore diverso da zero, altrimenti
+se fallisce ritorna 0. Questa funzione può essere utilizzata in un qualunque
+contesto, ma come :c:func:`spin_lock()`: dovete disabilitare i contesti che
+potrebbero interrompervi e quindi trattenere lo spinlock.
+
+La funzione :c:func:`mutex_trylock()` invece di sospendere il vostro processo
+ritorna un valore diverso da zero se è possibile trattenere il lock al primo
+colpo, altrimenti se fallisce ritorna 0. Nonostante non dorma, questa funzione
+non può essere usata in modo sicuro in contesti di interruzione hardware o
+software.
+
+Esempi più comuni
+=================
+
+Guardiamo un semplice esempio: una memoria che associa nomi a numeri.
+La memoria tiene traccia di quanto spesso viene utilizzato ogni oggetto;
+quando è piena, l'oggetto meno usato viene eliminato.
+
+Tutto in contesto utente
+------------------------
+
+Nel primo esempio, supponiamo che tutte le operazioni avvengano in contesto
+utente (in soldoni, da una chiamata di sistema), quindi possiamo dormire.
+Questo significa che possiamo usare i mutex per proteggere la nostra memoria
+e tutti gli oggetti che contiene. Ecco il codice::
+
+    #include <linux/list.h>
+    #include <linux/slab.h>
+    #include <linux/string.h>
+    #include <linux/mutex.h>
+    #include <asm/errno.h>
+
+    struct object
+    {
+            struct list_head list;
+            int id;
+            char name[32];
+            int popularity;
+    };
+
+    /* Protects the cache, cache_num, and the objects within it */
+    static DEFINE_MUTEX(cache_lock);
+    static LIST_HEAD(cache);
+    static unsigned int cache_num = 0;
+    #define MAX_CACHE_SIZE 10
+
+    /* Must be holding cache_lock */
+    static struct object *__cache_find(int id)
+    {
+            struct object *i;
+
+            list_for_each_entry(i, &cache, list)
+                    if (i->id == id) {
+                            i->popularity++;
+                            return i;
+                    }
+            return NULL;
+    }
+
+    /* Must be holding cache_lock */
+    static void __cache_delete(struct object *obj)
+    {
+            BUG_ON(!obj);
+            list_del(&obj->list);
+            kfree(obj);
+            cache_num--;
+    }
+
+    /* Must be holding cache_lock */
+    static void __cache_add(struct object *obj)
+    {
+            list_add(&obj->list, &cache);
+            if (++cache_num > MAX_CACHE_SIZE) {
+                    struct object *i, *outcast = NULL;
+                    list_for_each_entry(i, &cache, list) {
+                            if (!outcast || i->popularity < outcast->popularity)
+                                    outcast = i;
+                    }
+                    __cache_delete(outcast);
+            }
+    }
+
+    int cache_add(int id, const char *name)
+    {
+            struct object *obj;
+
+            if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL)
+                    return -ENOMEM;
+
+            strlcpy(obj->name, name, sizeof(obj->name));
+            obj->id = id;
+            obj->popularity = 0;
+
+            mutex_lock(&cache_lock);
+            __cache_add(obj);
+            mutex_unlock(&cache_lock);
+            return 0;
+    }
+
+    void cache_delete(int id)
+    {
+            mutex_lock(&cache_lock);
+            __cache_delete(__cache_find(id));
+            mutex_unlock(&cache_lock);
+    }
+
+    int cache_find(int id, char *name)
+    {
+            struct object *obj;
+            int ret = -ENOENT;
+
+            mutex_lock(&cache_lock);
+            obj = __cache_find(id);
+            if (obj) {
+                    ret = 0;
+                    strcpy(name, obj->name);
+            }
+            mutex_unlock(&cache_lock);
+            return ret;
+    }
+
+Da notare che ci assicuriamo sempre di trattenere cache_lock quando
+aggiungiamo, rimuoviamo od ispezioniamo la memoria: sia la struttura
+della memoria che il suo contenuto sono protetti dal *lock*. Questo
+caso è semplice dato che copiamo i dati dall'utente e non permettiamo
+mai loro di accedere direttamente agli oggetti.
+
+C'è una piccola ottimizzazione qui: nella funzione :c:func:`cache_add()`
+impostiamo i campi dell'oggetto prima di acquisire il *lock*. Questo è
+sicuro perché nessun altro potrà accedervi finché non lo inseriremo
+nella memoria.
+
+Accesso dal contesto utente
+---------------------------
+
+Ora consideriamo il caso in cui :c:func:`cache_find()` può essere invocata
+dal contesto d'interruzione: sia hardware che software. Un esempio potrebbe
+essere un timer che elimina oggetti dalla memoria.
+
+Qui di seguito troverete la modifica nel formato *patch*: le righe ``-``
+sono quelle rimosse, mentre quelle ``+`` sono quelle aggiunte.
+
+::
+
+    --- cache.c.usercontext 2003-12-09 13:58:54.000000000 +1100
+    +++ cache.c.interrupt   2003-12-09 14:07:49.000000000 +1100
+    @@ -12,7 +12,7 @@
+             int popularity;
+     };
+
+    -static DEFINE_MUTEX(cache_lock);
+    +static DEFINE_SPINLOCK(cache_lock);
+     static LIST_HEAD(cache);
+     static unsigned int cache_num = 0;
+     #define MAX_CACHE_SIZE 10
+    @@ -55,6 +55,7 @@
+     int cache_add(int id, const char *name)
+     {
+             struct object *obj;
+    +        unsigned long flags;
+
+             if ((obj = kmalloc(sizeof(*obj), GFP_KERNEL)) == NULL)
+                     return -ENOMEM;
+    @@ -63,30 +64,33 @@
+             obj->id = id;
+             obj->popularity = 0;
+
+    -        mutex_lock(&cache_lock);
+    +        spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+    -        mutex_unlock(&cache_lock);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+             return 0;
+     }
+
+     void cache_delete(int id)
+     {
+    -        mutex_lock(&cache_lock);
+    +        unsigned long flags;
+    +
+    +        spin_lock_irqsave(&cache_lock, flags);
+             __cache_delete(__cache_find(id));
+    -        mutex_unlock(&cache_lock);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+     }
+
+     int cache_find(int id, char *name)
+     {
+             struct object *obj;
+             int ret = -ENOENT;
+    +        unsigned long flags;
+
+    -        mutex_lock(&cache_lock);
+    +        spin_lock_irqsave(&cache_lock, flags);
+             obj = __cache_find(id);
+             if (obj) {
+                     ret = 0;
+                     strcpy(name, obj->name);
+             }
+    -        mutex_unlock(&cache_lock);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+             return ret;
+     }
+
+Da notare che :c:func:`spin_lock_irqsave()` disabiliterà le interruzioni
+se erano attive, altrimenti non farà niente (quando siamo già in un contesto
+d'interruzione); dunque queste funzioni possono essere chiamante in
+sicurezza da qualsiasi contesto.
+
+Sfortunatamente, :c:func:`cache_add()` invoca :c:func:`kmalloc()` con
+l'opzione ``GFP_KERNEL`` che è permessa solo in contesto utente. Ho supposto
+che :c:func:`cache_add()` venga chiamata dal contesto utente, altrimenti
+questa opzione deve diventare un parametro di :c:func:`cache_add()`.
+
+Exposing Objects Outside This File
+----------------------------------
+
+Se i vostri oggetti contengono più informazioni, potrebbe non essere
+sufficiente copiare i dati avanti e indietro: per esempio, altre parti del
+codice potrebbero avere un puntatore a questi oggetti piuttosto che cercarli
+ogni volta. Questo introduce due problemi.
+
+Il primo problema è che utilizziamo ``cache_lock`` per proteggere gli oggetti:
+dobbiamo renderlo dinamico così che il resto del codice possa usarlo. Questo
+rende la sincronizzazione più complicata dato che non avviene più in un unico
+posto.
+
+Il secondo problema è il problema del ciclo di vita: se un'altra struttura
+mantiene un puntatore ad un oggetto, presumibilmente si aspetta che questo
+puntatore rimanga valido. Sfortunatamente, questo è garantito solo mentre
+si trattiene il *lock*, altrimenti qualcuno potrebbe chiamare
+:c:func:`cache_delete()` o peggio, aggiungere un oggetto che riutilizza lo
+stesso indirizzo.
+
+Dato che c'è un solo *lock*, non potete trattenerlo a vita: altrimenti
+nessun altro potrà eseguire il proprio lavoro.
+
+La soluzione a questo problema è l'uso di un contatore di riferimenti:
+chiunque punti ad un oggetto deve incrementare il contatore, e decrementarlo
+quando il puntatore non viene più usato. Quando il contatore raggiunge lo zero
+significa che non è più usato e l'oggetto può essere rimosso.
+
+Ecco il codice::
+
+    --- cache.c.interrupt   2003-12-09 14:25:43.000000000 +1100
+    +++ cache.c.refcnt  2003-12-09 14:33:05.000000000 +1100
+    @@ -7,6 +7,7 @@
+     struct object
+     {
+             struct list_head list;
+    +        unsigned int refcnt;
+             int id;
+             char name[32];
+             int popularity;
+    @@ -17,6 +18,35 @@
+     static unsigned int cache_num = 0;
+     #define MAX_CACHE_SIZE 10
+
+    +static void __object_put(struct object *obj)
+    +{
+    +        if (--obj->refcnt == 0)
+    +                kfree(obj);
+    +}
+    +
+    +static void __object_get(struct object *obj)
+    +{
+    +        obj->refcnt++;
+    +}
+    +
+    +void object_put(struct object *obj)
+    +{
+    +        unsigned long flags;
+    +
+    +        spin_lock_irqsave(&cache_lock, flags);
+    +        __object_put(obj);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+    +}
+    +
+    +void object_get(struct object *obj)
+    +{
+    +        unsigned long flags;
+    +
+    +        spin_lock_irqsave(&cache_lock, flags);
+    +        __object_get(obj);
+    +        spin_unlock_irqrestore(&cache_lock, flags);
+    +}
+    +
+     /* Must be holding cache_lock */
+     static struct object *__cache_find(int id)
+     {
+    @@ -35,6 +65,7 @@
+     {
+             BUG_ON(!obj);
+             list_del(&obj->list);
+    +        __object_put(obj);
+             cache_num--;
+     }
+
+    @@ -63,6 +94,7 @@
+             strlcpy(obj->name, name, sizeof(obj->name));
+             obj->id = id;
+             obj->popularity = 0;
+    +        obj->refcnt = 1; /* The cache holds a reference */
+
+             spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+    @@ -79,18 +111,15 @@
+             spin_unlock_irqrestore(&cache_lock, flags);
+     }
+
+    -int cache_find(int id, char *name)
+    +struct object *cache_find(int id)
+     {
+             struct object *obj;
+    -        int ret = -ENOENT;
+             unsigned long flags;
+
+             spin_lock_irqsave(&cache_lock, flags);
+             obj = __cache_find(id);
+    -        if (obj) {
+    -                ret = 0;
+    -                strcpy(name, obj->name);
+    -        }
+    +        if (obj)
+    +                __object_get(obj);
+             spin_unlock_irqrestore(&cache_lock, flags);
+    -        return ret;
+    +        return obj;
+     }
+
+Abbiamo incapsulato il contatore di riferimenti nelle tipiche funzioni
+di 'get' e 'put'. Ora possiamo ritornare l'oggetto da :c:func:`cache_find()`
+col vantaggio che l'utente può dormire trattenendo l'oggetto (per esempio,
+:c:func:`copy_to_user()` per copiare il nome verso lo spazio utente).
+
+Un altro punto da notare è che ho detto che il contatore dovrebbe incrementarsi
+per ogni puntatore ad un oggetto: quindi il contatore di riferimenti è 1
+quando l'oggetto viene inserito nella memoria. In altre versione il framework
+non trattiene un riferimento per se, ma diventa più complicato.
+
+Usare operazioni atomiche per il contatore di riferimenti
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In sostanza, :c:type:`atomic_t` viene usato come contatore di riferimenti.
+Ci sono un certo numbero di operazioni atomiche definite
+in ``include/asm/atomic.h``: queste sono garantite come atomiche su qualsiasi
+processore del sistema, quindi non sono necessari i *lock*. In questo caso è
+più semplice rispetto all'uso degli spinlock, benché l'uso degli spinlock
+sia più elegante per casi non banali. Le funzioni :c:func:`atomic_inc()` e
+:c:func:`atomic_dec_and_test()` vengono usate al posto dei tipici operatori di
+incremento e decremento, e i *lock* non sono più necessari per proteggere il
+contatore stesso.
+
+::
+
+    --- cache.c.refcnt  2003-12-09 15:00:35.000000000 +1100
+    +++ cache.c.refcnt-atomic   2003-12-11 15:49:42.000000000 +1100
+    @@ -7,7 +7,7 @@
+     struct object
+     {
+             struct list_head list;
+    -        unsigned int refcnt;
+    +        atomic_t refcnt;
+             int id;
+             char name[32];
+             int popularity;
+    @@ -18,33 +18,15 @@
+     static unsigned int cache_num = 0;
+     #define MAX_CACHE_SIZE 10
+
+    -static void __object_put(struct object *obj)
+    -{
+    -        if (--obj->refcnt == 0)
+    -                kfree(obj);
+    -}
+    -
+    -static void __object_get(struct object *obj)
+    -{
+    -        obj->refcnt++;
+    -}
+    -
+     void object_put(struct object *obj)
+     {
+    -        unsigned long flags;
+    -
+    -        spin_lock_irqsave(&cache_lock, flags);
+    -        __object_put(obj);
+    -        spin_unlock_irqrestore(&cache_lock, flags);
+    +        if (atomic_dec_and_test(&obj->refcnt))
+    +                kfree(obj);
+     }
+
+     void object_get(struct object *obj)
+     {
+    -        unsigned long flags;
+    -
+    -        spin_lock_irqsave(&cache_lock, flags);
+    -        __object_get(obj);
+    -        spin_unlock_irqrestore(&cache_lock, flags);
+    +        atomic_inc(&obj->refcnt);
+     }
+
+     /* Must be holding cache_lock */
+    @@ -65,7 +47,7 @@
+     {
+             BUG_ON(!obj);
+             list_del(&obj->list);
+    -        __object_put(obj);
+    +        object_put(obj);
+             cache_num--;
+     }
+
+    @@ -94,7 +76,7 @@
+             strlcpy(obj->name, name, sizeof(obj->name));
+             obj->id = id;
+             obj->popularity = 0;
+    -        obj->refcnt = 1; /* The cache holds a reference */
+    +        atomic_set(&obj->refcnt, 1); /* The cache holds a reference */
+
+             spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+    @@ -119,7 +101,7 @@
+             spin_lock_irqsave(&cache_lock, flags);
+             obj = __cache_find(id);
+             if (obj)
+    -                __object_get(obj);
+    +                object_get(obj);
+             spin_unlock_irqrestore(&cache_lock, flags);
+             return obj;
+     }
+
+Proteggere l'oggetto stesso
+---------------------------
+
+In questo esempio, assumiamo che gli oggetti (ad eccezione del contatore
+di riferimenti) non cambino mai dopo la loro creazione. Se vogliamo permettere
+al nome di cambiare abbiamo tre possibilità:
+
+-  Si può togliere static da ``cache_lock`` e dire agli utenti che devono
+   trattenere il *lock* prima di modificare il nome di un oggetto.
+
+-  Si può fornire una funzione :c:func:`cache_obj_rename()` che prende il
+   *lock* e cambia il nome per conto del chiamante; si dirà poi agli utenti
+   di usare questa funzione.
+
+-  Si può decidere che ``cache_lock`` protegge solo la memoria stessa, ed
+   un altro *lock* è necessario per la protezione del nome.
+
+Teoricamente, possiamo avere un *lock* per ogni campo e per ogni oggetto.
+In pratica, le varianti più comuni sono:
+
+-  un *lock* che protegge l'infrastruttura (la lista ``cache`` di questo
+   esempio) e gli oggetti. Questo è quello che abbiamo fatto finora.
+
+-  un *lock* che protegge l'infrastruttura (inclusi i puntatori alla lista
+   negli oggetti), e un *lock* nell'oggetto per proteggere il resto
+   dell'oggetto stesso.
+
+-  *lock* multipli per proteggere l'infrastruttura (per esempio un *lock*
+   per ogni lista), possibilmente con un *lock* per oggetto.
+
+Qui di seguito un'implementazione con "un lock per oggetto":
+
+::
+
+    --- cache.c.refcnt-atomic   2003-12-11 15:50:54.000000000 +1100
+    +++ cache.c.perobjectlock   2003-12-11 17:15:03.000000000 +1100
+    @@ -6,11 +6,17 @@
+
+     struct object
+     {
+    +        /* These two protected by cache_lock. */
+             struct list_head list;
+    +        int popularity;
+    +
+             atomic_t refcnt;
+    +
+    +        /* Doesn't change once created. */
+             int id;
+    +
+    +        spinlock_t lock; /* Protects the name */
+             char name[32];
+    -        int popularity;
+     };
+
+     static DEFINE_SPINLOCK(cache_lock);
+    @@ -77,6 +84,7 @@
+             obj->id = id;
+             obj->popularity = 0;
+             atomic_set(&obj->refcnt, 1); /* The cache holds a reference */
+    +        spin_lock_init(&obj->lock);
+
+             spin_lock_irqsave(&cache_lock, flags);
+             __cache_add(obj);
+
+Da notare che ho deciso che il contatore di popolarità dovesse essere
+protetto da ``cache_lock`` piuttosto che dal *lock* dell'oggetto; questo
+perché è logicamente parte dell'infrastruttura (come
+:c:type:`struct list_head <list_head>` nell'oggetto). In questo modo,
+in :c:func:`__cache_add()`, non ho bisogno di trattenere il *lock* di ogni
+oggetto mentre si cerca il meno popolare.
+
+Ho anche deciso che il campo id è immutabile, quindi non ho bisogno di
+trattenere il lock dell'oggetto quando si usa :c:func:`__cache_find()`
+per leggere questo campo; il *lock* dell'oggetto è usato solo dal chiamante
+che vuole leggere o scrivere il campo name.
+
+Inoltre, da notare che ho aggiunto un commento che descrive i dati che sono
+protetti dal *lock*. Questo è estremamente importante in quanto descrive il
+comportamento del codice, che altrimenti sarebbe di difficile comprensione
+leggendo solamente il codice. E come dice Alan Cox: “Lock data, not code”.
+
+Problemi comuni
+===============
+
+.. _`it_deadlock`:
+
+Stallo: semplice ed avanzato
+----------------------------
+
+Esiste un tipo di  baco dove un pezzo di codice tenta di trattenere uno
+spinlock due volte: questo rimarrà in attesa attiva per sempre aspettando che
+il *lock* venga rilasciato (in Linux spinlocks, rwlocks e mutex non sono
+ricorsivi).
+Questo è facile da diagnosticare: non è uno di quei problemi che ti tengono
+sveglio 5 notti a parlare da solo.
+
+Un caso un pochino più complesso; immaginate d'avere una spazio condiviso
+fra un softirq ed il contesto utente. Se usate :c:func:`spin_lock()` per
+proteggerlo, il contesto utente potrebbe essere interrotto da un softirq
+mentre trattiene il lock, da qui il softirq rimarrà in attesa attiva provando
+ad acquisire il *lock* già trattenuto nel contesto utente.
+
+Questi casi sono chiamati stalli (*deadlock*), e come mostrato qui sopra,
+può succedere anche con un solo processore (Ma non sui sistemi
+monoprocessore perché gli spinlock spariscano quando il kernel è compilato
+con ``CONFIG_SMP``\ =n. Nonostante ciò, nel secondo caso avrete comunque
+una corruzione dei dati).
+
+Questi casi sono facili da diagnosticare; sui sistemi multi-processore
+il supervisione (*watchdog*) o l'opzione di compilazione ``DEBUG_SPINLOCK``
+(``include/linux/spinlock.h``) permettono di scovare immediatamente quando
+succedono.
+
+Esiste un caso più complesso che è conosciuto come l'abbraccio della morte;
+questo coinvolge due o più *lock*. Diciamo che avete un vettore di hash in cui
+ogni elemento è uno spinlock a cui è associata una lista di elementi con lo
+stesso hash. In un gestore di interruzioni software, dovete modificare un
+oggetto e spostarlo su un altro hash; quindi dovrete trattenete lo spinlock
+del vecchio hash e di quello nuovo, quindi rimuovere l'oggetto dal vecchio ed
+inserirlo nel nuovo.
+
+Qui abbiamo due problemi. Primo, se il vostro codice prova a spostare un
+oggetto all'interno della stessa lista, otterrete uno stallo visto che
+tenterà di trattenere lo stesso *lock* due volte. Secondo, se la stessa
+interruzione software su un altro processore sta tentando di spostare
+un altro oggetto nella direzione opposta, potrebbe accadere quanto segue:
+
++---------------------------------+---------------------------------+
+| CPU 1                           | CPU 2                           |
++=================================+=================================+
+| Trattiene *lock* A -> OK        | Trattiene *lock* B -> OK        |
++---------------------------------+---------------------------------+
+| Trattiene *lock* B -> attesa    | Trattiene *lock* A -> attesa    |
++---------------------------------+---------------------------------+
+
+Table: Conseguenze
+
+Entrambe i processori rimarranno in attesa attiva sul *lock* per sempre,
+aspettando che l'altro lo rilasci. Sembra e puzza come un blocco totale.
+
+Prevenire gli stalli
+--------------------
+
+I libri di testo vi diranno che se trattenete i *lock* sempre nello stesso
+ordine non avrete mai un simile stallo. La pratica vi dirà che questo
+approccio non funziona all'ingrandirsi del sistema: quando creo un nuovo
+*lock* non ne capisco abbastanza del kernel per dire in quale dei 5000 *lock*
+si incastrerà.
+
+I *lock* migliori sono quelli incapsulati: non vengono esposti nei file di
+intestazione, e non vengono mai trattenuti fuori dallo stesso file. Potete
+rileggere questo codice e vedere che non ci sarà mai uno stallo perché
+non tenterà mai di trattenere un altro *lock* quando lo ha già.
+Le persone che usano il vostro codice non devono nemmeno sapere che voi
+state usando dei *lock*.
+
+Un classico problema deriva dall'uso di *callback* e di *hook*: se li
+chiamate mentre trattenete un *lock*, rischiate uno stallo o un abbraccio
+della morte (chi lo sa cosa farà una *callback*?).
+
+Ossessiva prevenzione degli stalli
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+Gli stalli sono un problema, ma non così terribile come la corruzione dei dati.
+Un pezzo di codice trattiene un *lock* di lettura, cerca in una lista,
+fallisce nel trovare quello che vuole, quindi rilascia il *lock* di lettura,
+trattiene un *lock* di scrittura ed inserisce un oggetto; questo genere di
+codice presenta una corsa critica.
+
+Se non riuscite a capire il perché, per favore state alla larga dal mio
+codice.
+
+corsa fra temporizzatori: un passatempo del kernel
+--------------------------------------------------
+
+I temporizzatori potrebbero avere dei problemi con le corse critiche.
+Considerate una collezione di oggetti (liste, hash, eccetera) dove ogni oggetto
+ha un temporizzatore che sta per distruggerlo.
+
+Se volete eliminare l'intera collezione (diciamo quando rimuovete un modulo),
+potreste fare come segue::
+
+            /* THIS CODE BAD BAD BAD BAD: IF IT WAS ANY WORSE IT WOULD USE
+               HUNGARIAN NOTATION */
+            spin_lock_bh(&list_lock);
+
+            while (list) {
+                    struct foo *next = list->next;
+                    del_timer(&list->timer);
+                    kfree(list);
+                    list = next;
+            }
+
+            spin_unlock_bh(&list_lock);
+
+Primo o poi, questo esploderà su un sistema multiprocessore perché un
+temporizzatore potrebbe essere già partiro prima di :c:func:`spin_lock_bh()`,
+e prenderà il *lock* solo dopo :c:func:`spin_unlock_bh()`, e cercherà
+di eliminare il suo oggetto (che però è già stato eliminato).
+
+Questo può essere evitato controllando il valore di ritorno di
+:c:func:`del_timer()`: se ritorna 1, il temporizzatore è stato già
+rimosso. Se 0, significa (in questo caso) che il temporizzatore è in
+esecuzione, quindi possiamo fare come segue::
+
+            retry:
+                    spin_lock_bh(&list_lock);
+
+                    while (list) {
+                            struct foo *next = list->next;
+                            if (!del_timer(&list->timer)) {
+                                    /* Give timer a chance to delete this */
+                                    spin_unlock_bh(&list_lock);
+                                    goto retry;
+                            }
+                            kfree(list);
+                            list = next;
+                    }
+
+                    spin_unlock_bh(&list_lock);
+
+Un altro problema è l'eliminazione dei temporizzatori che si riavviano
+da soli (chiamando :c:func:`add_timer()` alla fine della loro esecuzione).
+Dato che questo è un problema abbastanza comune con una propensione
+alle corse critiche, dovreste usare :c:func:`del_timer_sync()`
+(``include/linux/timer.h``) per gestire questo caso. Questa ritorna il
+numero di volte che il temporizzatore è stato interrotto prima che
+fosse in grado di fermarlo senza che si riavviasse.
+
+Velocità della sincronizzazione
+===============================
+
+Ci sono tre cose importanti da tenere in considerazione quando si valuta
+la velocità d'esecuzione di un pezzo di codice che necessita di
+sincronizzazione. La prima è la concorrenza: quante cose rimangono in attesa
+mentre qualcuno trattiene un *lock*. La seconda è il tempo necessario per
+acquisire (senza contese) e rilasciare un *lock*. La terza è di usare meno
+*lock* o di più furbi. Immagino che i *lock* vengano usati regolarmente,
+altrimenti, non sareste interessati all'efficienza.
+
+La concorrenza dipende da quanto a lungo un *lock* è trattenuto: dovreste
+trattenere un *lock* solo il tempo minimo necessario ma non un istante in più.
+Nella memoria dell'esempio precedente, creiamo gli oggetti senza trattenere
+il *lock*, poi acquisiamo il *lock* quando siamo pronti per inserirlo nella
+lista.
+
+Il tempo di acquisizione di un *lock* dipende da quanto danno fa
+l'operazione sulla *pipeline* (ovvero stalli della *pipeline*) e quant'è
+probabile che il processore corrente sia stato anche l'ultimo ad acquisire
+il *lock* (in pratica, il *lock* è nella memoria cache del processore
+corrente?): su sistemi multi-processore questa probabilità precipita
+rapidamente. Consideriamo un processore Intel Pentium III a 700Mhz: questo
+esegue un'istruzione in 0.7ns, un incremento atomico richiede 58ns, acquisire
+un *lock* che è nella memoria cache del processore richiede 160ns, e un
+trasferimento dalla memoria cache di un altro processore richiede altri
+170/360ns (Leggetevi l'articolo di Paul McKenney's `Linux Journal RCU
+article <http://www.linuxjournal.com/article.php?sid=6993>`__).
+
+Questi due obiettivi sono in conflitto: trattenere un *lock* per il minor
+tempo possibile potrebbe richiedere la divisione in più *lock* per diverse
+parti (come nel nostro ultimo esempio con un *lock* per ogni oggetto),
+ma questo aumenta il numero di acquisizioni di *lock*, ed il risultato
+spesso è che tutto è più lento che con un singolo *lock*. Questo è un altro
+argomento in favore della semplicità quando si parla di sincronizzazione.
+
+Il terzo punto è discusso di seguito: ci sono alcune tecniche per ridurre
+il numero di sincronizzazioni che devono essere fatte.
+
+Read/Write Lock Variants
+------------------------
+
+Sia gli spinlock che i mutex hanno una variante per la lettura/scrittura
+(read/write): ``rwlock_t`` e :c:type:`struct rw_semaphore <rw_semaphore>`.
+Queste dividono gli utenti in due categorie: i lettori e gli scrittori.
+Se state solo leggendo i dati, potete acquisire il *lock* di lettura, ma
+per scrivere avrete bisogno del *lock* di scrittura. Molti possono trattenere
+il *lock* di lettura, ma solo uno scrittore alla volta può trattenere
+quello di scrittura.
+
+Se il vostro codice si divide chiaramente in codice per lettori e codice
+per scrittori (come nel nostro esempio), e il *lock* dei lettori viene
+trattenuto per molto tempo, allora l'uso di questo tipo di *lock* può aiutare.
+Questi sono leggermente più lenti rispetto alla loro versione normale, quindi
+nella pratica l'uso di ``rwlock_t`` non ne vale la pena.
+
+Evitare i *lock*: Read Copy Update
+--------------------------------------------
+
+Esiste un metodo di sincronizzazione per letture e scritture detto
+Read Copy Update. Con l'uso della tecnica RCU, i lettori possono scordarsi
+completamente di trattenere i *lock*; dato che nel nostro esempio ci
+aspettiamo d'avere più lettore che scrittori (altrimenti questa memoria
+sarebbe uno spreco) possiamo dire che questo meccanismo permette
+un'ottimizzazione.
+
+Come facciamo a sbarazzarci dei *lock* di lettura? Sbarazzarsi dei *lock* di
+lettura significa che uno scrittore potrebbe cambiare la lista sotto al naso
+dei lettori. Questo è abbastanza semplice: possiamo leggere una lista
+concatenata se lo scrittore aggiunge elementi alla fine e con certe
+precauzioni. Per esempio, aggiungendo ``new`` ad una lista concatenata
+chiamata ``list``::
+
+            new->next = list->next;
+            wmb();
+            list->next = new;
+
+La funzione :c:func:`wmb()` è una barriera di sincronizzazione delle
+scritture. Questa garantisce che la prima operazione (impostare l'elemento
+``next`` del nuovo elemento) venga completata e vista da tutti i processori
+prima che venga eseguita la seconda operazione (che sarebbe quella di mettere
+il nuovo elemento nella lista). Questo è importante perché i moderni
+compilatori ed i moderni processori possono, entrambe, riordinare le istruzioni
+se non vengono istruiti altrimenti: vogliamo che i lettori non vedano
+completamente il nuovo elemento; oppure che lo vedano correttamente e quindi
+il puntatore ``next`` deve puntare al resto della lista.
+
+Fortunatamente, c'è una funzione che fa questa operazione sulle liste
+:c:type:`struct list_head <list_head>`: :c:func:`list_add_rcu()`
+(``include/linux/list.h``).
+
+Rimuovere un elemento dalla lista è anche più facile: sostituiamo il puntatore
+al vecchio elemento con quello del suo successore, e i lettori vedranno
+l'elemento o lo salteranno.
+
+::
+
+            list->next = old->next;
+
+La funzione :c:func:`list_del_rcu()` (``include/linux/list.h``) fa esattamente
+questo (la versione normale corrompe il vecchio oggetto, e non vogliamo che
+accada).
+
+Anche i lettori devono stare attenti: alcuni processori potrebbero leggere
+attraverso il puntatore ``next`` il contenuto dell'elemento successivo
+troppo presto, ma non accorgersi che il contenuto caricato è sbagliato quando
+il puntatore ``next`` viene modificato alla loro spalle. Ancora una volta
+c'è una funzione che viene in vostro aiuto :c:func:`list_for_each_entry_rcu()`
+(``include/linux/list.h``). Ovviamente, gli scrittori possono usare
+:c:func:`list_for_each_entry()` dato che non ci possono essere due scrittori
+in contemporanea.
+
+Il nostro ultimo dilemma è il seguente: quando possiamo realmente distruggere
+l'elemento rimosso? Ricordate, un lettore potrebbe aver avuto accesso a questo
+elemento proprio ora: se eliminiamo questo elemento ed il puntatore ``next``
+cambia, il lettore salterà direttamente nella spazzatura e scoppierà. Dobbiamo
+aspettare finché tutti i lettori che stanno attraversando la lista abbiano
+finito. Utilizziamo :c:func:`call_rcu()` per registrare una funzione di
+richiamo che distrugga l'oggetto quando tutti i lettori correnti hanno
+terminato. In alternative, potrebbe essere usata la funzione
+:c:func:`synchronize_rcu()` che blocca l'esecuzione finché tutti i lettori
+non terminano di ispezionare la lista.
+
+Ma come fa l'RCU a sapere quando i lettori sono finiti? Il meccanismo è
+il seguente: innanzi tutto i lettori accedono alla lista solo fra la coppia
+:c:func:`rcu_read_lock()`/:c:func:`rcu_read_unlock()` che disabilita la
+prelazione così che i lettori non vengano sospesi mentre stanno leggendo
+la lista.
+
+Poi, l'RCU aspetta finché tutti i processori non abbiano dormito almeno
+una volta; a questo punto, dato che i lettori non possono dormire, possiamo
+dedurre che un qualsiasi lettore che abbia consultato la lista durante la
+rimozione abbia già terminato, quindi la *callback* viene eseguita. Il vero
+codice RCU è un po' più ottimizzato di così, ma questa è l'idea di fondo.
+
+::
+
+    --- cache.c.perobjectlock   2003-12-11 17:15:03.000000000 +1100
+    +++ cache.c.rcupdate    2003-12-11 17:55:14.000000000 +1100
+    @@ -1,15 +1,18 @@
+     #include <linux/list.h>
+     #include <linux/slab.h>
+     #include <linux/string.h>
+    +#include <linux/rcupdate.h>
+     #include <linux/mutex.h>
+     #include <asm/errno.h>
+
+     struct object
+     {
+    -        /* These two protected by cache_lock. */
+    +        /* This is protected by RCU */
+             struct list_head list;
+             int popularity;
+
+    +        struct rcu_head rcu;
+    +
+             atomic_t refcnt;
+
+             /* Doesn't change once created. */
+    @@ -40,7 +43,7 @@
+     {
+             struct object *i;
+
+    -        list_for_each_entry(i, &cache, list) {
+    +        list_for_each_entry_rcu(i, &cache, list) {
+                     if (i->id == id) {
+                             i->popularity++;
+                             return i;
+    @@ -49,19 +52,25 @@
+             return NULL;
+     }
+
+    +/* Final discard done once we know no readers are looking. */
+    +static void cache_delete_rcu(void *arg)
+    +{
+    +        object_put(arg);
+    +}
+    +
+     /* Must be holding cache_lock */
+     static void __cache_delete(struct object *obj)
+     {
+             BUG_ON(!obj);
+    -        list_del(&obj->list);
+    -        object_put(obj);
+    +        list_del_rcu(&obj->list);
+             cache_num--;
+    +        call_rcu(&obj->rcu, cache_delete_rcu);
+     }
+
+     /* Must be holding cache_lock */
+     static void __cache_add(struct object *obj)
+     {
+    -        list_add(&obj->list, &cache);
+    +        list_add_rcu(&obj->list, &cache);
+             if (++cache_num > MAX_CACHE_SIZE) {
+                     struct object *i, *outcast = NULL;
+                     list_for_each_entry(i, &cache, list) {
+    @@ -104,12 +114,11 @@
+     struct object *cache_find(int id)
+     {
+             struct object *obj;
+    -        unsigned long flags;
+
+    -        spin_lock_irqsave(&cache_lock, flags);
+    +        rcu_read_lock();
+             obj = __cache_find(id);
+             if (obj)
+                     object_get(obj);
+    -        spin_unlock_irqrestore(&cache_lock, flags);
+    +        rcu_read_unlock();
+             return obj;
+     }
+
+Da notare che i lettori modificano il campo popularity nella funzione
+:c:func:`__cache_find()`, e ora non trattiene alcun *lock*. Una soluzione
+potrebbe essere quella di rendere la variabile ``atomic_t``, ma per l'uso
+che ne abbiamo fatto qui, non ci interessano queste corse critiche perché un
+risultato approssimativo è comunque accettabile, quindi non l'ho cambiato.
+
+Il risultato è che la funzione :c:func:`cache_find()` non ha bisogno di alcuna
+sincronizzazione con le altre funzioni, quindi è veloce su un sistema
+multi-processore tanto quanto lo sarebbe su un sistema mono-processore.
+
+Esiste un'ulteriore ottimizzazione possibile: vi ricordate il codice originale
+della nostra memoria dove non c'erano contatori di riferimenti e il chiamante
+semplicemente tratteneva il *lock* prima di accedere ad un oggetto? Questo è
+ancora possibile: se trattenete un *lock* nessuno potrà cancellare l'oggetto,
+quindi non avete bisogno di incrementare e decrementare il contatore di
+riferimenti.
+
+Ora, dato che il '*lock* di lettura' di un RCU non fa altro che disabilitare
+la prelazione, un chiamante che ha sempre la prelazione disabilitata fra le
+chiamate :c:func:`cache_find()` e :c:func:`object_put()` non necessita
+di incrementare e decrementare il contatore di riferimenti. Potremmo
+esporre la funzione :c:func:`__cache_find()` dichiarandola non-static,
+e quel chiamante potrebbe usare direttamente questa funzione.
+
+Il beneficio qui sta nel fatto che il contatore di riferimenti no
+viene scritto: l'oggetto non viene alterato in alcun modo e quindi diventa
+molto più veloce su sistemi molti-processore grazie alla loro memoria cache.
+
+.. _`it_per-cpu`:
+
+Dati per processore
+-------------------
+
+Un'altra tecnica comunemente usata per evitare la sincronizzazione è quella
+di duplicare le informazioni per ogni processore. Per esempio, se volete
+avere un contatore di qualcosa, potreste utilizzare uno spinlock ed un
+singolo contatore. Facile e pulito.
+
+Se questo dovesse essere troppo lento (solitamente non lo è, ma se avete
+dimostrato che lo è devvero), potreste usare un contatore per ogni processore
+e quindi non sarebbe più necessaria la mutua esclusione. Vedere
+:c:func:`DEFINE_PER_CPU()`, :c:func:`get_cpu_var()` e :c:func:`put_cpu_var()`
+(``include/linux/percpu.h``).
+
+Il tipo di dato ``local_t``, la funzione :c:func:`cpu_local_inc()` e tutte
+le altre funzioni associate, sono di particolare utilità per semplici contatori
+per-processore; su alcune architetture sono anche più efficienti
+(``include/asm/local.h``).
+
+Da notare che non esiste un modo facile ed affidabile per ottenere il valore
+di un simile contatore senza introdurre altri *lock*. In alcuni casi questo
+non è un problema.
+
+Dati che sono usati prevalentemente dai gestori d'interruzioni
+--------------------------------------------------------------
+
+Se i dati vengono utilizzati sempre dallo stesso gestore d'interruzioni,
+allora i *lock* non vi servono per niente: il kernel già vi garantisce che
+il gestore d'interruzione non verrà eseguito in contemporanea su diversi
+processori.
+
+Manfred Spraul fa notare che potreste comunque comportarvi così anche
+se i dati vengono occasionalmente utilizzati da un contesto utente o
+da un'interruzione software. Il gestore d'interruzione non utilizza alcun
+*lock*, e tutti gli altri accessi verranno fatti così::
+
+        spin_lock(&lock);
+        disable_irq(irq);
+        ...
+        enable_irq(irq);
+        spin_unlock(&lock);
+
+La funzione :c:func:`disable_irq()` impedisce al gestore d'interruzioni
+d'essere eseguito (e aspetta che finisca nel caso fosse in esecuzione su
+un altro processore). Lo spinlock, invece, previene accessi simultanei.
+Naturalmente, questo è più lento della semplice chiamata
+:c:func:`spin_lock_irq()`, quindi ha senso solo se questo genere di accesso
+è estremamente raro.
+
+.. _`it_sleeping-things`:
+
+Quali funzioni possono essere chiamate in modo sicuro dalle interruzioni?
+=========================================================================
+
+Molte funzioni del kernel dormono (in sostanza, chiamano ``schedule()``)
+direttamente od indirettamente: non potete chiamarle se trattenere uno
+spinlock o avete la prelazione disabilitata, mai. Questo significa che
+dovete necessariamente essere nel contesto utente: chiamarle da un
+contesto d'interruzione è illegale.
+
+Alcune funzioni che dormono
+---------------------------
+
+Le più comuni sono elencate qui di seguito, ma solitamente dovete leggere
+il codice per scoprire se altre chiamate sono sicure. Se chiunque altro
+le chiami dorme, allora dovreste poter dormire anche voi. In particolar
+modo, le funzioni di registrazione e deregistrazione solitamente si
+aspettano d'essere chiamante da un contesto utente e quindi che possono
+dormire.
+
+-  Accessi allo spazio utente:
+
+   -  :c:func:`copy_from_user()`
+
+   -  :c:func:`copy_to_user()`
+
+   -  :c:func:`get_user()`
+
+   -  :c:func:`put_user()`
+
+-  :c:func:`kmalloc(GFP_KERNEL) <kmalloc>`
+
+-  :c:func:`mutex_lock_interruptible()` and
+   :c:func:`mutex_lock()`
+
+   C'è anche :c:func:`mutex_trylock()` che però non dorme.
+   Comunque, non deve essere usata in un contesto d'interruzione dato
+   che la sua implementazione non è sicura in quel contesto.
+   Anche :c:func:`mutex_unlock()` non dorme mai. Non può comunque essere
+   usata in un contesto d'interruzione perché un mutex deve essere rilasciato
+   dallo stesso processo che l'ha acquisito.
+
+Alcune funzioni che non dormono
+-------------------------------
+
+Alcune funzioni possono essere chiamate tranquillamente da qualsiasi
+contesto, o trattenendo un qualsiasi *lock*.
+
+-  :c:func:`printk()`
+
+-  :c:func:`kfree()`
+
+-  :c:func:`add_timer()` e :c:func:`del_timer()`
+
+Riferimento per l'API dei Mutex
+===============================
+
+.. kernel-doc:: include/linux/mutex.h
+   :internal:
+
+.. kernel-doc:: kernel/locking/mutex.c
+   :export:
+
+Riferimento per l'API dei Futex
+===============================
+
+.. kernel-doc:: kernel/futex.c
+   :internal:
+
+Approfondimenti
+===============
+
+-  ``Documentation/locking/spinlocks.txt``: la guida di Linus Torvalds agli
+   spinlock del kernel.
+
+-  Unix Systems for Modern Architectures: Symmetric Multiprocessing and
+   Caching for Kernel Programmers.
+
+   L'introduzione alla sincronizzazione a livello di kernel di Curt Schimmel
+   è davvero ottima (non è scritta per Linux, ma approssimativamente si adatta
+   a tutte le situazioni). Il libro è costoso, ma vale ogni singolo spicciolo
+   per capire la sincronizzazione nei sistemi multi-processore.
+   [ISBN: 0201633388]
+
+Ringraziamenti
+==============
+
+Grazie a Telsa Gwynne per aver formattato questa guida in DocBook, averla
+pulita e aggiunto un po' di stile.
+
+Grazie a Martin Pool, Philipp Rumpf, Stephen Rothwell, Paul Mackerras,
+Ruedi Aschwanden, Alan Cox, Manfred Spraul, Tim Waugh, Pete Zaitcev,
+James Morris, Robert Love, Paul McKenney, John Ashby per aver revisionato,
+corretto, maledetto e commentato.
+
+Grazie alla congrega per non aver avuto alcuna influenza su questo documento.
+
+Glossario
+=========
+
+prelazione
+  Prima del kernel 2.5, o quando ``CONFIG_PREEMPT`` non è impostato, i processi
+  in contesto utente non si avvicendano nell'esecuzione (in pratica, il
+  processo userà il processore fino al proprio termine, a meno che non ci siano
+  delle interruzioni). Con l'aggiunta di ``CONFIG_PREEMPT`` nella versione
+  2.5.4 questo è cambiato: quando si è in contesto utente, processi con una
+  priorità maggiore possono subentrare nell'esecuzione: gli spinlock furono
+  cambiati per disabilitare la prelazioni, anche su sistemi monoprocessore.
+
+bh
+  Bottom Half: per ragioni storiche, le funzioni che contengono '_bh' nel
+  loro nome ora si riferiscono a qualsiasi interruzione software; per esempio,
+  :c:func:`spin_lock_bh()` blocca qualsiasi interuzione software sul processore
+  corrente. I *Bottom Halves* sono deprecati, e probabilmente verranno
+  sostituiti dai tasklet. In un dato momento potrà esserci solo un
+  *bottom half* in esecuzione.
+
+contesto d'interruzione
+  Non è il contesto utente: qui si processano le interruzioni hardware e
+  software. La macro :c:func:`in_interrupt()` ritorna vero.
+
+contesto utente
+  Il kernel che esegue qualcosa per conto di un particolare processo (per
+  esempio una chiamata di sistema) o di un thread del kernel. Potete
+  identificare il processo con la macro ``current``. Da non confondere
+  con lo spazio utente. Può essere interrotto sia da interruzioni software
+  che hardware.
+
+interruzione hardware
+  Richiesta di interruzione hardware. :c:func:`in_irq()` ritorna vero in un
+  gestore d'interruzioni hardware.
+
+interruzione software / softirq
+  Gestore di interruzioni software: :c:func:`in_irq()` ritorna falso;
+  :c:func:`in_softirq()` ritorna vero. I tasklet e le softirq sono entrambi
+  considerati 'interruzioni software'.
+
+  In soldoni, un softirq è uno delle 32 interruzioni software che possono
+  essere eseguite su più processori in contemporanea. A volte si usa per
+  riferirsi anche ai tasklet (in pratica tutte le interruzioni software).
+
+monoprocessore / UP
+  (Uni-Processor) un solo processore, ovvero non è SMP. (``CONFIG_SMP=n``).
+
+multi-processore / SMP
+  (Symmetric Multi-Processor) kernel compilati per sistemi multi-processore
+  (``CONFIG_SMP=y``).
+
+spazio utente
+  Un processo che esegue il proprio codice fuori dal kernel.
+
+tasklet
+  Un'interruzione software registrabile dinamicamente che ha la garanzia
+  d'essere eseguita solo su un processore alla volta.
+
+timer
+  Un'interruzione software registrabile dinamicamente che viene eseguita
+  (circa) in un determinato momento. Quando è in esecuzione è come un tasklet
+  (infatti, sono chiamati da ``TIMER_SOFTIRQ``).
-- 
cgit v1.2.3


From afab995e06ee1fb76de195a4fba9d03267f8dbe3 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 12 Jun 2018 10:08:43 +0300
Subject: net/mlx5e: Replace call to MPWQE free with dealloc in interface down
 flow

No need to expose the MPWQE free function to control path.
The dealloc function already exposed, use it.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 1 -
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 2 +-
 3 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index e1b237ccdf56..dc9aa070eafa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -892,7 +892,6 @@ bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq);
 bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq);
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix);
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
 struct sk_buff *
 mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 				u16 cqe_bcnt, u32 head_offset, u32 page_idx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index dccde18f6170..c214b23e14ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -877,7 +877,7 @@ static void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
 
 		/* UMR WQE (if in progress) is always at wq->head */
 		if (rq->mpwqe.umr_in_progress)
-			mlx5e_free_rx_mpwqe(rq, &rq->mpwqe.info[wq->head]);
+			rq->dealloc_wqe(rq, wq->head);
 
 		while (!mlx5_wq_ll_is_empty(wq)) {
 			struct mlx5e_rx_wqe_ll *wqe;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1d5295ee863c..e6b3d178c45f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -396,7 +396,7 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 	}
 }
 
-void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
+static void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 {
 	const bool no_xdp_xmit =
 		bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
-- 
cgit v1.2.3


From cb5189d173097af805ff74c88191aba25fc60a55 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 12 Jun 2018 10:09:24 +0300
Subject: net/mlx5e: Do not recycle RX pages in interface down flow

Keep all page-pool recycle calls within NAPI context.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 37 +++++++++++++------------
 1 file changed, 20 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e6b3d178c45f..97db5eeca9f3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -277,10 +277,11 @@ static inline int mlx5e_get_rx_frag(struct mlx5e_rq *rq,
 }
 
 static inline void mlx5e_put_rx_frag(struct mlx5e_rq *rq,
-				     struct mlx5e_wqe_frag_info *frag)
+				     struct mlx5e_wqe_frag_info *frag,
+				     bool recycle)
 {
 	if (frag->last_in_page)
-		mlx5e_page_release(rq, frag->di, true);
+		mlx5e_page_release(rq, frag->di, recycle);
 }
 
 static inline struct mlx5e_wqe_frag_info *get_frag(struct mlx5e_rq *rq, u16 ix)
@@ -308,25 +309,26 @@ static int mlx5e_alloc_rx_wqe(struct mlx5e_rq *rq, struct mlx5e_rx_wqe_cyc *wqe,
 
 free_frags:
 	while (--i >= 0)
-		mlx5e_put_rx_frag(rq, --frag);
+		mlx5e_put_rx_frag(rq, --frag, true);
 
 	return err;
 }
 
 static inline void mlx5e_free_rx_wqe(struct mlx5e_rq *rq,
-				     struct mlx5e_wqe_frag_info *wi)
+				     struct mlx5e_wqe_frag_info *wi,
+				     bool recycle)
 {
 	int i;
 
 	for (i = 0; i < rq->wqe.info.num_frags; i++, wi++)
-		mlx5e_put_rx_frag(rq, wi);
+		mlx5e_put_rx_frag(rq, wi, recycle);
 }
 
 void mlx5e_dealloc_rx_wqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_wqe_frag_info *wi = get_frag(rq, ix);
 
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, false);
 }
 
 static int mlx5e_alloc_rx_wqes(struct mlx5e_rq *rq, u16 ix, u8 wqe_bulk)
@@ -396,7 +398,8 @@ mlx5e_copy_skb_header_mpwqe(struct device *pdev,
 	}
 }
 
-static void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
+static void
+mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi, bool recycle)
 {
 	const bool no_xdp_xmit =
 		bitmap_empty(wi->xdp_xmit_bitmap, MLX5_MPWRQ_PAGES_PER_WQE);
@@ -405,7 +408,7 @@ static void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi)
 
 	for (i = 0; i < MLX5_MPWRQ_PAGES_PER_WQE; i++)
 		if (no_xdp_xmit || !test_bit(i, wi->xdp_xmit_bitmap))
-			mlx5e_page_release(rq, &dma_info[i], true);
+			mlx5e_page_release(rq, &dma_info[i], recycle);
 }
 
 static void mlx5e_post_rx_mpwqe(struct mlx5e_rq *rq)
@@ -505,8 +508,8 @@ err_unmap:
 void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 {
 	struct mlx5e_mpw_info *wi = &rq->mpwqe.info[ix];
-
-	mlx5e_free_rx_mpwqe(rq, wi);
+	/* Don't recycle, this function is called on rq/netdev close */
+	mlx5e_free_rx_mpwqe(rq, wi, false);
 }
 
 bool mlx5e_post_rx_wqes(struct mlx5e_rq *rq)
@@ -1113,7 +1116,7 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
@@ -1155,7 +1158,7 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
@@ -1292,7 +1295,7 @@ mpwrq_cqe_out:
 
 	wq  = &rq->mpwqe.wq;
 	wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
-	mlx5e_free_rx_mpwqe(rq, wi);
+	mlx5e_free_rx_mpwqe(rq, wi, true);
 	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
 }
 
@@ -1521,7 +1524,7 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	napi_gro_receive(rq->cq.napi, skb);
 
 wq_free_wqe:
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 	mlx5_wq_cyc_pop(wq);
 }
 
@@ -1544,19 +1547,19 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
 	skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt);
 	if (unlikely(!skb)) {
 		/* a DROP, save the page-reuse checks */
-		mlx5e_free_rx_wqe(rq, wi);
+		mlx5e_free_rx_wqe(rq, wi, true);
 		goto wq_cyc_pop;
 	}
 	skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt);
 	if (unlikely(!skb)) {
-		mlx5e_free_rx_wqe(rq, wi);
+		mlx5e_free_rx_wqe(rq, wi, true);
 		goto wq_cyc_pop;
 	}
 
 	mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb);
 	napi_gro_receive(rq->cq.napi, skb);
 
-	mlx5e_free_rx_wqe(rq, wi);
+	mlx5e_free_rx_wqe(rq, wi, true);
 wq_cyc_pop:
 	mlx5_wq_cyc_pop(wq);
 }
-- 
cgit v1.2.3


From 0ec13877ce95c00737ff4f71a96cd90533b12b48 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 12 Mar 2018 18:26:51 +0200
Subject: net/mlx5e: Gather all XDP pre-requisite checks in a single function

Dedicate a function to all checks done when setting an XDP program.
Take indications from priv instead of netdev features.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 33 +++++++++++++++--------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c214b23e14ba..a1a54ea3aeb4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4094,26 +4094,37 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 	queue_work(priv->wq, &priv->tx_timeout_work);
 }
 
+static int mlx5e_xdp_allowed(struct mlx5e_priv *priv)
+{
+	struct net_device *netdev = priv->netdev;
+
+	if (priv->channels.params.lro_en) {
+		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
+		return -EINVAL;
+	}
+
+	if (MLX5_IPSEC_DEV(priv->mdev)) {
+		netdev_warn(netdev, "can't set XDP with IPSec offload\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct bpf_prog *old_prog;
-	int err = 0;
 	bool reset, was_opened;
+	int err;
 	int i;
 
 	mutex_lock(&priv->state_lock);
 
-	if ((netdev->features & NETIF_F_LRO) && prog) {
-		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
-		err = -EINVAL;
-		goto unlock;
-	}
-
-	if ((netdev->features & NETIF_F_HW_ESP) && prog) {
-		netdev_warn(netdev, "can't set XDP with IPSec offload\n");
-		err = -EINVAL;
-		goto unlock;
+	if (prog) {
+		err = mlx5e_xdp_allowed(priv);
+		if (err)
+			goto unlock;
 	}
 
 	was_opened = test_bit(MLX5E_STATE_OPENED, &priv->state);
-- 
cgit v1.2.3


From a26a5bdf3ee2da419ba2c2baa54f467103dc8cc5 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 31 Dec 2017 15:50:13 +0200
Subject: net/mlx5e: Restrict the combination of large MTU and XDP

Add checks in control path upon an MTU change or an XDP program set,
to prevent reaching cases where large MTU and XDP are set simultaneously.

This is to make sure we allow XDP only with the linear RX memory scheme,
i.e. a received packet is not scattered to different pages.
Change mlx5e_rx_get_linear_frag_sz() accordingly, so that we make sure
the XDP configuration can really be set, instead of assuming that it is.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  2 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 39 ++++++++++++++++++-----
 2 files changed, 33 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index dc9aa070eafa..7840f6f44379 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -72,6 +72,8 @@ struct page_pool;
 #define MLX5_RX_HEADROOM NET_SKB_PAD
 #define MLX5_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
 				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
+				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 
 #define MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev) \
 	(6 + MLX5_CAP_GEN(mdev, cache_line_128byte)) /* HW restriction */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a1a54ea3aeb4..56ae6e428fdf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -96,14 +96,19 @@ bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 
 static u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params)
 {
-	if (!params->xdp_prog) {
-		u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-		u16 rq_headroom = MLX5_RX_HEADROOM + NET_IP_ALIGN;
+	u16 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	u16 linear_rq_headroom = params->xdp_prog ?
+		XDP_PACKET_HEADROOM : MLX5_RX_HEADROOM;
+	u32 frag_sz;
 
-		return MLX5_SKB_FRAG_SZ(rq_headroom + hw_mtu);
-	}
+	linear_rq_headroom += NET_IP_ALIGN;
 
-	return PAGE_SIZE;
+	frag_sz = MLX5_SKB_FRAG_SZ(linear_rq_headroom + hw_mtu);
+
+	if (params->xdp_prog && frag_sz < PAGE_SIZE)
+		frag_sz = PAGE_SIZE;
+
+	return frag_sz;
 }
 
 static u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params)
@@ -3707,6 +3712,14 @@ int mlx5e_change_mtu(struct net_device *netdev, int new_mtu,
 	new_channels.params = *params;
 	new_channels.params.sw_mtu = new_mtu;
 
+	if (params->xdp_prog &&
+	    !mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+		netdev_err(netdev, "MTU(%d) > %d is not allowed while XDP enabled\n",
+			   new_mtu, MLX5E_XDP_MAX_MTU);
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) {
 		u8 ppw_old = mlx5e_mpwqe_log_pkts_per_wqe(params);
 		u8 ppw_new = mlx5e_mpwqe_log_pkts_per_wqe(&new_channels.params);
@@ -4094,9 +4107,10 @@ static void mlx5e_tx_timeout(struct net_device *dev)
 	queue_work(priv->wq, &priv->tx_timeout_work);
 }
 
-static int mlx5e_xdp_allowed(struct mlx5e_priv *priv)
+static int mlx5e_xdp_allowed(struct mlx5e_priv *priv, struct bpf_prog *prog)
 {
 	struct net_device *netdev = priv->netdev;
+	struct mlx5e_channels new_channels = {};
 
 	if (priv->channels.params.lro_en) {
 		netdev_warn(netdev, "can't set XDP while LRO is on, disable LRO first\n");
@@ -4108,6 +4122,15 @@ static int mlx5e_xdp_allowed(struct mlx5e_priv *priv)
 		return -EINVAL;
 	}
 
+	new_channels.params = priv->channels.params;
+	new_channels.params.xdp_prog = prog;
+
+	if (!mlx5e_rx_is_linear_skb(priv->mdev, &new_channels.params)) {
+		netdev_warn(netdev, "XDP is not allowed with MTU(%d) > %d\n",
+			    new_channels.params.sw_mtu, MLX5E_XDP_MAX_MTU);
+		return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -4122,7 +4145,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	mutex_lock(&priv->state_lock);
 
 	if (prog) {
-		err = mlx5e_xdp_allowed(priv);
+		err = mlx5e_xdp_allowed(priv, prog);
 		if (err)
 			goto unlock;
 	}
-- 
cgit v1.2.3


From 159d21313423b5ffe301834273cba79e915c65ee Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 15 Jul 2018 10:28:44 +0300
Subject: net/mlx5e: Move XDP related code into new XDP files

Take XDP code out of the general EN header and RX file into
new XDP files.

Currently, XDP-SQ resides only within an RQ and used from a
single flow (XDP_TX) triggered upon RX completions.
In a downstream patch, additional type of XDP-SQ instances will be
presented and used for the XDP_REDIRECT flow, totally unrelated to
the RX context.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile  |   2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |   9 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 225 ++++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h  |  62 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |   1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c   | 208 +-------------------
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c |   1 +
 7 files changed, 293 insertions(+), 215 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index fa7fcca5dc78..ae2bdcb1647c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,7 +14,7 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o          \
+		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o vxlan.o \
 		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 7840f6f44379..2f1058da0907 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -72,8 +72,6 @@ struct page_pool;
 #define MLX5_RX_HEADROOM NET_SKB_PAD
 #define MLX5_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
 				 SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
-#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
-				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
 
 #define MLX5_MPWRQ_MIN_LOG_STRIDE_SZ(mdev) \
 	(6 + MLX5_CAP_GEN(mdev, cache_line_128byte)) /* HW restriction */
@@ -149,10 +147,6 @@ struct page_pool;
 	(DIV_ROUND_UP(MLX5E_UMR_WQE_INLINE_SZ, MLX5_SEND_WQE_BB))
 #define MLX5E_ICOSQ_MAX_WQEBBS MLX5E_UMR_WQEBBS
 
-#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
-#define MLX5E_XDP_TX_DS_COUNT \
-	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
-
 #define MLX5E_NUM_MAIN_GROUPS 9
 
 #define MLX5E_MSG_LEVEL			NETIF_MSG_LINK
@@ -878,14 +872,13 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
 
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev);
 bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev,
 				struct mlx5e_params *params);
 
+void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info);
 void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info,
 			bool recycle);
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
new file mode 100644
index 000000000000..649675c1af61
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -0,0 +1,225 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/bpf_trace.h>
+#include "en/xdp.h"
+
+/* returns true if packet was consumed by xdp */
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+		      void *va, u16 *rx_headroom, u32 *len)
+{
+	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
+	struct xdp_buff xdp;
+	u32 act;
+	int err;
+
+	if (!prog)
+		return false;
+
+	xdp.data = va + *rx_headroom;
+	xdp_set_data_meta_invalid(&xdp);
+	xdp.data_end = xdp.data + *len;
+	xdp.data_hard_start = va;
+	xdp.rxq = &rq->xdp_rxq;
+
+	act = bpf_prog_run_xdp(prog, &xdp);
+	switch (act) {
+	case XDP_PASS:
+		*rx_headroom = xdp.data - xdp.data_hard_start;
+		*len = xdp.data_end - xdp.data;
+		return false;
+	case XDP_TX:
+		if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp)))
+			trace_xdp_exception(rq->netdev, prog, act);
+		return true;
+	case XDP_REDIRECT:
+		/* When XDP enabled then page-refcnt==1 here */
+		err = xdp_do_redirect(rq->netdev, &xdp, prog);
+		if (!err) {
+			__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
+			rq->xdpsq.db.redirect_flush = true;
+			mlx5e_page_dma_unmap(rq, di);
+		}
+		return true;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+	case XDP_ABORTED:
+		trace_xdp_exception(rq->netdev, prog, act);
+	case XDP_DROP:
+		rq->stats->xdp_drop++;
+		return true;
+	}
+}
+
+bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+			  const struct xdp_buff *xdp)
+{
+	struct mlx5e_xdpsq       *sq   = &rq->xdpsq;
+	struct mlx5_wq_cyc       *wq   = &sq->wq;
+	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
+	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
+	struct mlx5_wqe_data_seg *dseg;
+
+	ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
+	dma_addr_t dma_addr  = di->addr + data_offset;
+	unsigned int dma_len = xdp->data_end - xdp->data;
+
+	struct mlx5e_rq_stats *stats = rq->stats;
+
+	prefetchw(wqe);
+
+	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) {
+		stats->xdp_drop++;
+		return false;
+	}
+
+	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
+		if (sq->db.doorbell) {
+			/* SQ is full, ring doorbell */
+			mlx5e_xmit_xdp_doorbell(sq);
+			sq->db.doorbell = false;
+		}
+		stats->xdp_tx_full++;
+		return false;
+	}
+
+	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
+
+	cseg->fm_ce_se = 0;
+
+	dseg = (struct mlx5_wqe_data_seg *)eseg + 1;
+
+	/* copy the inline part if required */
+	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
+		memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE);
+		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
+		dma_len  -= MLX5E_XDP_MIN_INLINE;
+		dma_addr += MLX5E_XDP_MIN_INLINE;
+		dseg++;
+	}
+
+	/* write the dma part */
+	dseg->addr       = cpu_to_be64(dma_addr);
+	dseg->byte_count = cpu_to_be32(dma_len);
+
+	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
+
+	/* move page to reference to sq responsibility,
+	 * and mark so it's not put back in page-cache.
+	 */
+	__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
+	sq->db.di[pi] = *di;
+	sq->pc++;
+
+	sq->db.doorbell = true;
+
+	stats->xdp_tx++;
+	return true;
+}
+
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
+{
+	struct mlx5e_xdpsq *sq;
+	struct mlx5_cqe64 *cqe;
+	struct mlx5e_rq *rq;
+	u16 sqcc;
+	int i;
+
+	sq = container_of(cq, struct mlx5e_xdpsq, cq);
+
+	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+		return false;
+
+	cqe = mlx5_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
+		return false;
+
+	rq = container_of(sq, struct mlx5e_rq, xdpsq);
+
+	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
+	 * otherwise a cq overrun may occur
+	 */
+	sqcc = sq->cc;
+
+	i = 0;
+	do {
+		u16 wqe_counter;
+		bool last_wqe;
+
+		mlx5_cqwq_pop(&cq->wq);
+
+		wqe_counter = be16_to_cpu(cqe->wqe_counter);
+
+		do {
+			struct mlx5e_dma_info *di;
+			u16 ci;
+
+			last_wqe = (sqcc == wqe_counter);
+
+			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			di = &sq->db.di[ci];
+
+			sqcc++;
+			/* Recycle RX page */
+			mlx5e_page_release(rq, di, true);
+		} while (!last_wqe);
+	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
+
+	rq->stats->xdp_tx_cqe += i;
+
+	mlx5_cqwq_update_db_record(&cq->wq);
+
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+	sq->cc = sqcc;
+	return (i == MLX5E_TX_CQ_POLL_BUDGET);
+}
+
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
+	struct mlx5e_dma_info *di;
+	u16 ci;
+
+	while (sq->cc != sq->pc) {
+		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+		di = &sq->db.di[ci];
+		sq->cc++;
+
+		mlx5e_page_release(rq, di, false);
+	}
+}
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
new file mode 100644
index 000000000000..a8a856a82c63
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -0,0 +1,62 @@
+/*
+ * Copyright (c) 2018, Mellanox Technologies. All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __MLX5_EN_XDP_H__
+#define __MLX5_EN_XDP_H__
+
+#include "en.h"
+
+#define MLX5E_XDP_MAX_MTU ((int)(PAGE_SIZE - \
+				 MLX5_SKB_FRAG_SZ(XDP_PACKET_HEADROOM)))
+#define MLX5E_XDP_MIN_INLINE (ETH_HLEN + VLAN_HLEN)
+#define MLX5E_XDP_TX_DS_COUNT \
+	((sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) + 1 /* SG DS */)
+
+bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+		      void *va, u16 *rx_headroom, u32 *len);
+bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
+void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
+
+bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
+			  const struct xdp_buff *xdp);
+
+static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	struct mlx5e_tx_wqe *wqe;
+	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
+
+	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
+
+	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
+}
+
+#endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 56ae6e428fdf..dd5eec923766 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -47,6 +47,7 @@
 #include "accel/tls.h"
 #include "vxlan.h"
 #include "en/port.h"
+#include "en/xdp.h"
 
 struct mlx5e_rq_param {
 	u32			rqc[MLX5_ST_SZ_DW(rqc)];
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 97db5eeca9f3..70b984c4e8a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -34,7 +34,6 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
-#include <linux/bpf_trace.h>
 #include <net/busy_poll.h>
 #include <net/ip6_checksum.h>
 #include <net/page_pool.h>
@@ -46,6 +45,7 @@
 #include "en_accel/ipsec_rxtx.h"
 #include "en_accel/tls_rxtx.h"
 #include "lib/clock.h"
+#include "en/xdp.h"
 
 static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config)
 {
@@ -239,8 +239,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq,
 	return 0;
 }
 
-static void mlx5e_page_dma_unmap(struct mlx5e_rq *rq,
-					struct mlx5e_dma_info *dma_info)
+void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info)
 {
 	dma_unmap_page(rq->pdev, dma_info->addr, PAGE_SIZE, rq->buff.map_dir);
 }
@@ -850,135 +849,6 @@ static inline void mlx5e_complete_rx_cqe(struct mlx5e_rq *rq,
 	mlx5e_build_rx_skb(cqe, cqe_bcnt, rq, skb);
 }
 
-static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
-{
-	struct mlx5_wq_cyc *wq = &sq->wq;
-	struct mlx5e_tx_wqe *wqe;
-	u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc - 1); /* last pi */
-
-	wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &wqe->ctrl);
-}
-
-static inline bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq,
-					struct mlx5e_dma_info *di,
-					const struct xdp_buff *xdp)
-{
-	struct mlx5e_xdpsq       *sq   = &rq->xdpsq;
-	struct mlx5_wq_cyc       *wq   = &sq->wq;
-	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
-	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
-
-	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-	struct mlx5_wqe_data_seg *dseg;
-
-	ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
-	dma_addr_t dma_addr  = di->addr + data_offset;
-	unsigned int dma_len = xdp->data_end - xdp->data;
-
-	struct mlx5e_rq_stats *stats = rq->stats;
-
-	prefetchw(wqe);
-
-	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) {
-		stats->xdp_drop++;
-		return false;
-	}
-
-	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
-		if (sq->db.doorbell) {
-			/* SQ is full, ring doorbell */
-			mlx5e_xmit_xdp_doorbell(sq);
-			sq->db.doorbell = false;
-		}
-		stats->xdp_tx_full++;
-		return false;
-	}
-
-	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
-
-	cseg->fm_ce_se = 0;
-
-	dseg = (struct mlx5_wqe_data_seg *)eseg + 1;
-
-	/* copy the inline part if required */
-	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE);
-		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
-		dma_len  -= MLX5E_XDP_MIN_INLINE;
-		dma_addr += MLX5E_XDP_MIN_INLINE;
-		dseg++;
-	}
-
-	/* write the dma part */
-	dseg->addr       = cpu_to_be64(dma_addr);
-	dseg->byte_count = cpu_to_be32(dma_len);
-
-	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
-
-	/* move page to reference to sq responsibility,
-	 * and mark so it's not put back in page-cache.
-	 */
-	__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
-	sq->db.di[pi] = *di;
-	sq->pc++;
-
-	sq->db.doorbell = true;
-
-	stats->xdp_tx++;
-	return true;
-}
-
-/* returns true if packet was consumed by xdp */
-static inline bool mlx5e_xdp_handle(struct mlx5e_rq *rq,
-				    struct mlx5e_dma_info *di,
-				    void *va, u16 *rx_headroom, u32 *len)
-{
-	struct bpf_prog *prog = READ_ONCE(rq->xdp_prog);
-	struct xdp_buff xdp;
-	u32 act;
-	int err;
-
-	if (!prog)
-		return false;
-
-	xdp.data = va + *rx_headroom;
-	xdp_set_data_meta_invalid(&xdp);
-	xdp.data_end = xdp.data + *len;
-	xdp.data_hard_start = va;
-	xdp.rxq = &rq->xdp_rxq;
-
-	act = bpf_prog_run_xdp(prog, &xdp);
-	switch (act) {
-	case XDP_PASS:
-		*rx_headroom = xdp.data - xdp.data_hard_start;
-		*len = xdp.data_end - xdp.data;
-		return false;
-	case XDP_TX:
-		if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp)))
-			trace_xdp_exception(rq->netdev, prog, act);
-		return true;
-	case XDP_REDIRECT:
-		/* When XDP enabled then page-refcnt==1 here */
-		err = xdp_do_redirect(rq->netdev, &xdp, prog);
-		if (!err) {
-			__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
-			rq->xdpsq.db.redirect_flush = true;
-			mlx5e_page_dma_unmap(rq, di);
-		}
-		return true;
-	default:
-		bpf_warn_invalid_xdp_action(act);
-	case XDP_ABORTED:
-		trace_xdp_exception(rq->netdev, prog, act);
-	case XDP_DROP:
-		rq->stats->xdp_drop++;
-		return true;
-	}
-}
-
 static inline
 struct sk_buff *mlx5e_build_linear_skb(struct mlx5e_rq *rq, void *va,
 				       u32 frag_size, u16 headroom,
@@ -1349,80 +1219,6 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	return work_done;
 }
 
-bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
-{
-	struct mlx5e_xdpsq *sq;
-	struct mlx5_cqe64 *cqe;
-	struct mlx5e_rq *rq;
-	u16 sqcc;
-	int i;
-
-	sq = container_of(cq, struct mlx5e_xdpsq, cq);
-
-	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
-		return false;
-
-	cqe = mlx5_cqwq_get_cqe(&cq->wq);
-	if (!cqe)
-		return false;
-
-	rq = container_of(sq, struct mlx5e_rq, xdpsq);
-
-	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
-	 * otherwise a cq overrun may occur
-	 */
-	sqcc = sq->cc;
-
-	i = 0;
-	do {
-		u16 wqe_counter;
-		bool last_wqe;
-
-		mlx5_cqwq_pop(&cq->wq);
-
-		wqe_counter = be16_to_cpu(cqe->wqe_counter);
-
-		do {
-			struct mlx5e_dma_info *di;
-			u16 ci;
-
-			last_wqe = (sqcc == wqe_counter);
-
-			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			di = &sq->db.di[ci];
-
-			sqcc++;
-			/* Recycle RX page */
-			mlx5e_page_release(rq, di, true);
-		} while (!last_wqe);
-	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
-
-	rq->stats->xdp_tx_cqe += i;
-
-	mlx5_cqwq_update_db_record(&cq->wq);
-
-	/* ensure cq space is freed before enabling more cqes */
-	wmb();
-
-	sq->cc = sqcc;
-	return (i == MLX5E_TX_CQ_POLL_BUDGET);
-}
-
-void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
-{
-	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
-	struct mlx5e_dma_info *di;
-	u16 ci;
-
-	while (sq->cc != sq->pc) {
-		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
-		di = &sq->db.di[ci];
-		sq->cc++;
-
-		mlx5e_page_release(rq, di, false);
-	}
-}
-
 #ifdef CONFIG_MLX5_CORE_IPOIB
 
 #define MLX5_IB_GRH_DGID_OFFSET 24
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index 4e1f99a98d5d..f31bbbe1bdb1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -32,6 +32,7 @@
 
 #include <linux/irq.h>
 #include "en.h"
+#include "en/xdp.h"
 
 static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c)
 {
-- 
cgit v1.2.3


From 86690b4b4a5127b912348201f4f5880bb75a6621 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 16 May 2018 10:16:30 +0300
Subject: net/mlx5e: Add counter for XDP redirect in RX

Add per-ring and total stats for received packets that
goes into XDP redirection.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 3 +++
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 2 ++
 3 files changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 649675c1af61..34accf3f4cee 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -69,6 +69,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 			rq->xdpsq.db.redirect_flush = true;
 			mlx5e_page_dma_unmap(rq, di);
 		}
+		rq->stats->xdp_redirect++;
 		return true;
 	default:
 		bpf_warn_invalid_xdp_action(act);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index c0507fada0be..b88db9d923ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -59,6 +59,7 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_complete) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
@@ -142,6 +143,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
 		s->rx_xdp_drop += rq_stats->xdp_drop;
+		s->rx_xdp_redirect += rq_stats->xdp_redirect;
 		s->rx_xdp_tx += rq_stats->xdp_tx;
 		s->rx_xdp_tx_cqe  += rq_stats->xdp_tx_cqe;
 		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
@@ -1126,6 +1128,7 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
+	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_cqe) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index fc3f66003edd..07529cc58471 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -70,6 +70,7 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_complete;
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
+	u64 rx_xdp_redirect;
 	u64 rx_xdp_tx;
 	u64 rx_xdp_tx_cqe;
 	u64 rx_xdp_tx_full;
@@ -178,6 +179,7 @@ struct mlx5e_rq_stats {
 	u64 lro_bytes;
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
+	u64 xdp_redirect;
 	u64 xdp_tx;
 	u64 xdp_tx_cqe;
 	u64 xdp_tx_full;
-- 
cgit v1.2.3


From c94e4f117e473dec11c7b9395b4d88cae2ba27c9 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Sun, 15 Jul 2018 10:34:39 +0300
Subject: net/mlx5e: Make XDP xmit functions more generic

Convert the XDP xmit functions to use the generic xdp_frame API
in XDP_TX flow.
Same functions will be used later in this series to transmit
the XDP redirect-out packets as well.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 20 ++++---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c  | 70 ++++++++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h  |  3 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 10 ++--
 4 files changed, 61 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 2f1058da0907..118d66207079 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -395,6 +395,17 @@ struct mlx5e_txqsq {
 	} recover;
 } ____cacheline_aligned_in_smp;
 
+struct mlx5e_dma_info {
+	struct page     *page;
+	dma_addr_t      addr;
+};
+
+struct mlx5e_xdp_info {
+	struct xdp_frame      *xdpf;
+	dma_addr_t            dma_addr;
+	struct mlx5e_dma_info di;
+};
+
 struct mlx5e_xdpsq {
 	/* data path */
 
@@ -406,7 +417,7 @@ struct mlx5e_xdpsq {
 
 	/* write@xmit, read@completion */
 	struct {
-		struct mlx5e_dma_info     *di;
+		struct mlx5e_xdp_info     *xdpi;
 		bool                       doorbell;
 		bool                       redirect_flush;
 	} db;
@@ -419,6 +430,7 @@ struct mlx5e_xdpsq {
 	__be32                     mkey_be;
 	u8                         min_inline_mode;
 	unsigned long              state;
+	unsigned int               hw_mtu;
 
 	/* control path */
 	struct mlx5_wq_ctrl        wq_ctrl;
@@ -455,11 +467,6 @@ mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 	return (mlx5_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
 }
 
-struct mlx5e_dma_info {
-	struct page	*page;
-	dma_addr_t	addr;
-};
-
 struct mlx5e_wqe_frag_info {
 	struct mlx5e_dma_info *di;
 	u32 offset;
@@ -562,7 +569,6 @@ struct mlx5e_rq {
 
 	/* XDP */
 	struct bpf_prog       *xdp_prog;
-	unsigned int           hw_mtu;
 	struct mlx5e_xdpsq     xdpsq;
 	DECLARE_BITMAP(flags, 8);
 	struct page_pool      *page_pool;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 34accf3f4cee..53d011eb71ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -33,6 +33,23 @@
 #include <linux/bpf_trace.h>
 #include "en/xdp.h"
 
+static inline bool
+mlx5e_xmit_xdp_buff(struct mlx5e_xdpsq *sq, struct mlx5e_dma_info *di,
+		    struct xdp_buff *xdp)
+{
+	struct mlx5e_xdp_info xdpi;
+
+	xdpi.xdpf = convert_to_xdp_frame(xdp);
+	if (unlikely(!xdpi.xdpf))
+		return false;
+	xdpi.dma_addr = di->addr + (xdpi.xdpf->data - (void *)xdpi.xdpf);
+	dma_sync_single_for_device(sq->pdev, xdpi.dma_addr,
+				   xdpi.xdpf->len, PCI_DMA_TODEVICE);
+	xdpi.di = *di;
+
+	return mlx5e_xmit_xdp_frame(sq, &xdpi);
+}
+
 /* returns true if packet was consumed by xdp */
 bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		      void *va, u16 *rx_headroom, u32 *len)
@@ -58,22 +75,24 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		*len = xdp.data_end - xdp.data;
 		return false;
 	case XDP_TX:
-		if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp)))
-			trace_xdp_exception(rq->netdev, prog, act);
+		if (unlikely(!mlx5e_xmit_xdp_buff(&rq->xdpsq, di, &xdp)))
+			goto xdp_abort;
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
 		return true;
 	case XDP_REDIRECT:
 		/* When XDP enabled then page-refcnt==1 here */
 		err = xdp_do_redirect(rq->netdev, &xdp, prog);
-		if (!err) {
-			__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
-			rq->xdpsq.db.redirect_flush = true;
-			mlx5e_page_dma_unmap(rq, di);
-		}
+		if (unlikely(err))
+			goto xdp_abort;
+		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
+		rq->xdpsq.db.redirect_flush = true;
+		mlx5e_page_dma_unmap(rq, di);
 		rq->stats->xdp_redirect++;
 		return true;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 	case XDP_ABORTED:
+xdp_abort:
 		trace_xdp_exception(rq->netdev, prog, act);
 	case XDP_DROP:
 		rq->stats->xdp_drop++;
@@ -81,27 +100,27 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 	}
 }
 
-bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
-			  const struct xdp_buff *xdp)
+bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 {
-	struct mlx5e_xdpsq       *sq   = &rq->xdpsq;
 	struct mlx5_wq_cyc       *wq   = &sq->wq;
 	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
 
+	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
+
 	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
 	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-	struct mlx5_wqe_data_seg *dseg;
+	struct mlx5_wqe_data_seg *dseg = wqe->data;
 
-	ptrdiff_t data_offset = xdp->data - xdp->data_hard_start;
-	dma_addr_t dma_addr  = di->addr + data_offset;
-	unsigned int dma_len = xdp->data_end - xdp->data;
+	struct xdp_frame *xdpf = xdpi->xdpf;
+	dma_addr_t dma_addr  = xdpi->dma_addr;
+	unsigned int dma_len = xdpf->len;
 
 	struct mlx5e_rq_stats *stats = rq->stats;
 
 	prefetchw(wqe);
 
-	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || rq->hw_mtu < dma_len)) {
+	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || sq->hw_mtu < dma_len)) {
 		stats->xdp_drop++;
 		return false;
 	}
@@ -116,15 +135,11 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		return false;
 	}
 
-	dma_sync_single_for_device(sq->pdev, dma_addr, dma_len, PCI_DMA_TODEVICE);
-
 	cseg->fm_ce_se = 0;
 
-	dseg = (struct mlx5_wqe_data_seg *)eseg + 1;
-
 	/* copy the inline part if required */
 	if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-		memcpy(eseg->inline_hdr.start, xdp->data, MLX5E_XDP_MIN_INLINE);
+		memcpy(eseg->inline_hdr.start, xdpf->data, MLX5E_XDP_MIN_INLINE);
 		eseg->inline_hdr.sz = cpu_to_be16(MLX5E_XDP_MIN_INLINE);
 		dma_len  -= MLX5E_XDP_MIN_INLINE;
 		dma_addr += MLX5E_XDP_MIN_INLINE;
@@ -140,8 +155,7 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 	/* move page to reference to sq responsibility,
 	 * and mark so it's not put back in page-cache.
 	 */
-	__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); /* non-atomic */
-	sq->db.di[pi] = *di;
+	sq->db.xdpi[pi] = *xdpi;
 	sq->pc++;
 
 	sq->db.doorbell = true;
@@ -184,17 +198,17 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
 		do {
-			struct mlx5e_dma_info *di;
+			struct mlx5e_xdp_info *xdpi;
 			u16 ci;
 
 			last_wqe = (sqcc == wqe_counter);
 
 			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			di = &sq->db.di[ci];
+			xdpi = &sq->db.xdpi[ci];
 
 			sqcc++;
 			/* Recycle RX page */
-			mlx5e_page_release(rq, di, true);
+			mlx5e_page_release(rq, &xdpi->di, true);
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
@@ -212,15 +226,15 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 {
 	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
-	struct mlx5e_dma_info *di;
+	struct mlx5e_xdp_info *xdpi;
 	u16 ci;
 
 	while (sq->cc != sq->pc) {
 		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
-		di = &sq->db.di[ci];
+		xdpi = &sq->db.xdpi[ci];
 		sq->cc++;
 
-		mlx5e_page_release(rq, di, false);
+		mlx5e_page_release(rq, &xdpi->di, false);
 	}
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index a8a856a82c63..81739aad0188 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -45,8 +45,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
 
-bool mlx5e_xmit_xdp_frame(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
-			  const struct xdp_buff *xdp);
+bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
 
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index dd5eec923766..7ed71db9b32f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -491,7 +491,6 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	rq->channel = c;
 	rq->ix      = c->ix;
 	rq->mdev    = mdev;
-	rq->hw_mtu  = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 	rq->stats   = &c->priv->channel_stats[c->ix].rq;
 
 	rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL;
@@ -969,16 +968,16 @@ static void mlx5e_close_rq(struct mlx5e_rq *rq)
 
 static void mlx5e_free_xdpsq_db(struct mlx5e_xdpsq *sq)
 {
-	kvfree(sq->db.di);
+	kvfree(sq->db.xdpi);
 }
 
 static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 {
 	int wq_sz = mlx5_wq_cyc_get_size(&sq->wq);
 
-	sq->db.di = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.di)),
-				  GFP_KERNEL, numa);
-	if (!sq->db.di) {
+	sq->db.xdpi = kvzalloc_node(array_size(wq_sz, sizeof(*sq->db.xdpi)),
+				    GFP_KERNEL, numa);
+	if (!sq->db.xdpi) {
 		mlx5e_free_xdpsq_db(sq);
 		return -ENOMEM;
 	}
@@ -1001,6 +1000,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
+	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
-- 
cgit v1.2.3


From 890388ad6f6b3740265173fa5296ece5d945e977 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 22 May 2018 16:29:31 +0300
Subject: net/mlx5e: Refactor XDP counters

Separate the XDP counters into two sets:
(1) One set reside in the RQ stats, and they monitor XDP stats
in the RQ side.
(2) Another set is per XDP-SQ, and they monitor XDP stats that
are related to XDP transmit flow.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  2 +
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   | 12 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 47 +++++++++++++++-------
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h | 16 +++++---
 5 files changed, 52 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 118d66207079..d9e24fbe6a28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -424,6 +424,7 @@ struct mlx5e_xdpsq {
 
 	/* read only */
 	struct mlx5_wq_cyc         wq;
+	struct mlx5e_xdpsq_stats  *stats;
 	void __iomem              *uar_map;
 	u32                        sqn;
 	struct device             *pdev;
@@ -619,6 +620,7 @@ struct mlx5e_channel_stats {
 	struct mlx5e_ch_stats ch;
 	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
+	struct mlx5e_xdpsq_stats rq_xdpsq;
 } ____cacheline_aligned_in_smp;
 
 enum mlx5e_traffic_types {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 53d011eb71ab..26e24823504b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -106,8 +106,6 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	u16                       pi   = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
 	struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(wq, pi);
 
-	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
-
 	struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
 	struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
 	struct mlx5_wqe_data_seg *dseg = wqe->data;
@@ -116,12 +114,12 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	dma_addr_t dma_addr  = xdpi->dma_addr;
 	unsigned int dma_len = xdpf->len;
 
-	struct mlx5e_rq_stats *stats = rq->stats;
+	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
 	prefetchw(wqe);
 
 	if (unlikely(dma_len < MLX5E_XDP_MIN_INLINE || sq->hw_mtu < dma_len)) {
-		stats->xdp_drop++;
+		stats->err++;
 		return false;
 	}
 
@@ -131,7 +129,7 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 			mlx5e_xmit_xdp_doorbell(sq);
 			sq->db.doorbell = false;
 		}
-		stats->xdp_tx_full++;
+		stats->full++;
 		return false;
 	}
 
@@ -160,7 +158,7 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 
 	sq->db.doorbell = true;
 
-	stats->xdp_tx++;
+	stats->xmit++;
 	return true;
 }
 
@@ -212,7 +210,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
-	rq->stats->xdp_tx_cqe += i;
+	sq->stats->cqes += i;
 
 	mlx5_cqwq_update_db_record(&cq->wq);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7ed71db9b32f..5a6c4403a3e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1001,6 +1001,7 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
+	sq->stats     = &c->priv->channel_stats[c->ix].rq_xdpsq;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index b88db9d923ad..85b1827b76c6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -60,9 +60,10 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_csum_unnecessary_inner) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_drop) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_redirect) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx) },
-	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_none) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_csum_partial_inner) },
@@ -129,6 +130,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) {
 		struct mlx5e_channel_stats *channel_stats =
 			&priv->channel_stats[i];
+		struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
 		struct mlx5e_ch_stats *ch_stats = &channel_stats->ch;
 		int j;
@@ -142,11 +144,12 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->rx_csum_complete += rq_stats->csum_complete;
 		s->rx_csum_unnecessary += rq_stats->csum_unnecessary;
 		s->rx_csum_unnecessary_inner += rq_stats->csum_unnecessary_inner;
-		s->rx_xdp_drop += rq_stats->xdp_drop;
+		s->rx_xdp_drop     += rq_stats->xdp_drop;
 		s->rx_xdp_redirect += rq_stats->xdp_redirect;
-		s->rx_xdp_tx += rq_stats->xdp_tx;
-		s->rx_xdp_tx_cqe  += rq_stats->xdp_tx_cqe;
-		s->rx_xdp_tx_full += rq_stats->xdp_tx_full;
+		s->rx_xdp_tx_xmit  += xdpsq_stats->xmit;
+		s->rx_xdp_tx_full  += xdpsq_stats->full;
+		s->rx_xdp_tx_err   += xdpsq_stats->err;
+		s->rx_xdp_tx_cqe   += xdpsq_stats->cqes;
 		s->rx_wqe_err   += rq_stats->wqe_err;
 		s->rx_mpwqe_filler_cqes    += rq_stats->mpwqe_filler_cqes;
 		s->rx_mpwqe_filler_strides += rq_stats->mpwqe_filler_strides;
@@ -164,7 +167,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->ch_poll        += ch_stats->poll;
 		s->ch_arm         += ch_stats->arm;
 		s->ch_aff_change  += ch_stats->aff_change;
-		s->ch_eq_rearm += ch_stats->eq_rearm;
+		s->ch_eq_rearm    += ch_stats->eq_rearm;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -1129,9 +1132,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, csum_none) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_drop) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_redirect) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_cqe) },
-	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, xdp_tx_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, lro_bytes) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, removed_vlan_packets) },
@@ -1171,6 +1171,13 @@ static const struct counter_desc sq_stats_desc[] = {
 	{ MLX5E_DECLARE_TX_STAT(struct mlx5e_sq_stats, cqe_err) },
 };
 
+static const struct counter_desc rq_xdpsq_stats_desc[] = {
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
+	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
+};
+
 static const struct counter_desc ch_stats_desc[] = {
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
@@ -1181,6 +1188,7 @@ static const struct counter_desc ch_stats_desc[] = {
 
 #define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
+#define NUM_RQ_XDPSQ_STATS		ARRAY_SIZE(rq_xdpsq_stats_desc)
 #define NUM_CH_STATS			ARRAY_SIZE(ch_stats_desc)
 
 static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
@@ -1189,7 +1197,8 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
 
 	return (NUM_RQ_STATS * max_nch) +
 	       (NUM_CH_STATS * max_nch) +
-	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc);
+	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc) +
+	       (NUM_RQ_XDPSQ_STATS * max_nch);
 }
 
 static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
@@ -1203,9 +1212,14 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 			sprintf(data + (idx++) * ETH_GSTRING_LEN,
 				ch_stats_desc[j].format, i);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
-			sprintf(data + (idx++) * ETH_GSTRING_LEN, rq_stats_desc[j].format, i);
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_stats_desc[j].format, i);
+		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				rq_xdpsq_stats_desc[j].format, i);
+	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
@@ -1229,11 +1243,16 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].ch,
 						     ch_stats_desc, j);
 
-	for (i = 0; i < max_nch; i++)
+	for (i = 0; i < max_nch; i++) {
 		for (j = 0; j < NUM_RQ_STATS; j++)
 			data[idx++] =
 				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq,
 						     rq_stats_desc, j);
+		for (j = 0; j < NUM_RQ_XDPSQ_STATS; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].rq_xdpsq,
+						     rq_xdpsq_stats_desc, j);
+	}
 
 	for (tc = 0; tc < priv->max_opened_tc; tc++)
 		for (i = 0; i < max_nch; i++)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 07529cc58471..95e1f32c67d9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -44,6 +44,7 @@
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld)
 
 struct counter_desc {
@@ -71,9 +72,10 @@ struct mlx5e_sw_stats {
 	u64 rx_csum_unnecessary_inner;
 	u64 rx_xdp_drop;
 	u64 rx_xdp_redirect;
-	u64 rx_xdp_tx;
-	u64 rx_xdp_tx_cqe;
+	u64 rx_xdp_tx_xmit;
 	u64 rx_xdp_tx_full;
+	u64 rx_xdp_tx_err;
+	u64 rx_xdp_tx_cqe;
 	u64 tx_csum_none;
 	u64 tx_csum_partial;
 	u64 tx_csum_partial_inner;
@@ -180,9 +182,6 @@ struct mlx5e_rq_stats {
 	u64 removed_vlan_packets;
 	u64 xdp_drop;
 	u64 xdp_redirect;
-	u64 xdp_tx;
-	u64 xdp_tx_cqe;
-	u64 xdp_tx_full;
 	u64 wqe_err;
 	u64 mpwqe_filler_cqes;
 	u64 mpwqe_filler_strides;
@@ -227,6 +226,13 @@ struct mlx5e_sq_stats {
 	u64 cqe_err;
 };
 
+struct mlx5e_xdpsq_stats {
+	u64 xmit;
+	u64 full;
+	u64 err;
+	u64 cqes;
+};
+
 struct mlx5e_ch_stats {
 	u64 events;
 	u64 poll;
-- 
cgit v1.2.3


From dac0d15fff6f825e93aafa6ba8bf24fd77ecb2ae Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 22 May 2018 16:43:54 +0300
Subject: net/mlx5e: Re-order fields of struct mlx5e_xdpsq

In the downstream patch that adds support to XDP_REDIRECT-out,
the XDP xmit frame function doesn't share the same run context as
the NAPI that polls the XDP-SQ completion queue.

Hence, need to re-order the XDP-SQ fields to avoid cacheline
false-sharing.

Take redirect_flush and doorbell out of DB, into separated
cachelines.

Add a cacheline breaker within the stats struct.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 18 +++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   |  8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c    |  8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |  3 ++-
 4 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index d9e24fbe6a28..16e219a8f240 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -409,22 +409,22 @@ struct mlx5e_xdp_info {
 struct mlx5e_xdpsq {
 	/* data path */
 
-	/* dirtied @rx completion */
+	/* dirtied @completion */
 	u16                        cc;
-	u16                        pc;
+	bool                       redirect_flush;
 
-	struct mlx5e_cq            cq;
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	bool                       doorbell;
 
-	/* write@xmit, read@completion */
-	struct {
-		struct mlx5e_xdp_info     *xdpi;
-		bool                       doorbell;
-		bool                       redirect_flush;
-	} db;
+	struct mlx5e_cq            cq;
 
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	struct mlx5e_xdpsq_stats  *stats;
+	struct {
+		struct mlx5e_xdp_info     *xdpi;
+	} db;
 	void __iomem              *uar_map;
 	u32                        sqn;
 	struct device             *pdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 26e24823504b..eabd5537927d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -85,7 +85,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		if (unlikely(err))
 			goto xdp_abort;
 		__set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags);
-		rq->xdpsq.db.redirect_flush = true;
+		rq->xdpsq.redirect_flush = true;
 		mlx5e_page_dma_unmap(rq, di);
 		rq->stats->xdp_redirect++;
 		return true;
@@ -124,10 +124,10 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	}
 
 	if (unlikely(!mlx5e_wqc_has_room_for(wq, sq->cc, sq->pc, 1))) {
-		if (sq->db.doorbell) {
+		if (sq->doorbell) {
 			/* SQ is full, ring doorbell */
 			mlx5e_xmit_xdp_doorbell(sq);
-			sq->db.doorbell = false;
+			sq->doorbell = false;
 		}
 		stats->full++;
 		return false;
@@ -156,7 +156,7 @@ bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi)
 	sq->db.xdpi[pi] = *xdpi;
 	sq->pc++;
 
-	sq->db.doorbell = true;
+	sq->doorbell = true;
 
 	stats->xmit++;
 	return true;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 70b984c4e8a4..e33ca03b2100 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1201,14 +1201,14 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 		rq->handle_rx_cqe(rq, cqe);
 	} while ((++work_done < budget) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
-	if (xdpsq->db.doorbell) {
+	if (xdpsq->doorbell) {
 		mlx5e_xmit_xdp_doorbell(xdpsq);
-		xdpsq->db.doorbell = false;
+		xdpsq->doorbell = false;
 	}
 
-	if (xdpsq->db.redirect_flush) {
+	if (xdpsq->redirect_flush) {
 		xdp_do_flush_map();
-		xdpsq->db.redirect_flush = false;
+		xdpsq->redirect_flush = false;
 	}
 
 	mlx5_cqwq_update_db_record(&cq->wq);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 95e1f32c67d9..7aa8ff389cdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -230,7 +230,8 @@ struct mlx5e_xdpsq_stats {
 	u64 xmit;
 	u64 full;
 	u64 err;
-	u64 cqes;
+	/* dirtied @completion */
+	u64 cqes ____cacheline_aligned_in_smp;
 };
 
 struct mlx5e_ch_stats {
-- 
cgit v1.2.3


From 58b99ee3e3ebecfaccc5641a4014d92a818494a5 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 22 May 2018 16:48:48 +0300
Subject: net/mlx5e: Add support for XDP_REDIRECT in device-out side

Add implementation for the ndo_xdp_xmit callback.

Dedicate a new set of XDP-SQ instances to satisfy the XDP_REDIRECT
requests.  These instances are totally separated from the existing
XDP-SQ objects that satisfy local XDP_TX actions.

Performance tests:

xdp_redirect_map from ConnectX-5 to ConnectX-5.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz
Packet-rate of 64B packets.

Single queue: 7 Mpps.
Multi queue: 55 Mpps.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Eugenia Emantayev <eugenia@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |  5 ++
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c   | 92 ++++++++++++++++++----
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h   |  2 +
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  | 36 +++++++--
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 32 +++++++-
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |  5 ++
 drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c  |  3 +
 7 files changed, 154 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 16e219a8f240..3f21cafe6be3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -344,6 +344,7 @@ enum {
 	MLX5E_SQ_STATE_IPSEC,
 	MLX5E_SQ_STATE_AM,
 	MLX5E_SQ_STATE_TLS,
+	MLX5E_SQ_STATE_REDIRECT,
 };
 
 struct mlx5e_sq_wqe_info {
@@ -598,6 +599,9 @@ struct mlx5e_channel {
 	__be32                     mkey_be;
 	u8                         num_tc;
 
+	/* XDP_REDIRECT */
+	struct mlx5e_xdpsq         xdpsq;
+
 	/* data path - accessed per napi poll */
 	struct irq_desc *irq_desc;
 	struct mlx5e_ch_stats     *stats;
@@ -621,6 +625,7 @@ struct mlx5e_channel_stats {
 	struct mlx5e_sq_stats sq[MLX5E_MAX_NUM_TC];
 	struct mlx5e_rq_stats rq;
 	struct mlx5e_xdpsq_stats rq_xdpsq;
+	struct mlx5e_xdpsq_stats xdpsq;
 } ____cacheline_aligned_in_smp;
 
 enum mlx5e_traffic_types {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index eabd5537927d..bab8cd44d1c5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -167,6 +167,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	struct mlx5e_xdpsq *sq;
 	struct mlx5_cqe64 *cqe;
 	struct mlx5e_rq *rq;
+	bool is_redirect;
 	u16 sqcc;
 	int i;
 
@@ -179,6 +180,7 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 	if (!cqe)
 		return false;
 
+	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
 	rq = container_of(sq, struct mlx5e_rq, xdpsq);
 
 	/* sq->cc must be updated only after mlx5_cqwq_update_db_record(),
@@ -196,17 +198,20 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 		wqe_counter = be16_to_cpu(cqe->wqe_counter);
 
 		do {
-			struct mlx5e_xdp_info *xdpi;
-			u16 ci;
+			u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
+			struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
 
 			last_wqe = (sqcc == wqe_counter);
-
-			ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sqcc);
-			xdpi = &sq->db.xdpi[ci];
-
 			sqcc++;
-			/* Recycle RX page */
-			mlx5e_page_release(rq, &xdpi->di, true);
+
+			if (is_redirect) {
+				xdp_return_frame(xdpi->xdpf);
+				dma_unmap_single(sq->pdev, xdpi->dma_addr,
+						 xdpi->xdpf->len, DMA_TO_DEVICE);
+			} else {
+				/* Recycle RX page */
+				mlx5e_page_release(rq, &xdpi->di, true);
+			}
 		} while (!last_wqe);
 	} while ((++i < MLX5E_TX_CQ_POLL_BUDGET) && (cqe = mlx5_cqwq_get_cqe(&cq->wq)));
 
@@ -223,16 +228,75 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq)
 
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq)
 {
-	struct mlx5e_rq *rq = container_of(sq, struct mlx5e_rq, xdpsq);
-	struct mlx5e_xdp_info *xdpi;
-	u16 ci;
+	struct mlx5e_rq *rq;
+	bool is_redirect;
+
+	is_redirect = test_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
+	rq = is_redirect ? NULL : container_of(sq, struct mlx5e_rq, xdpsq);
 
 	while (sq->cc != sq->pc) {
-		ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
-		xdpi = &sq->db.xdpi[ci];
+		u16 ci = mlx5_wq_cyc_ctr2ix(&sq->wq, sq->cc);
+		struct mlx5e_xdp_info *xdpi = &sq->db.xdpi[ci];
+
 		sq->cc++;
 
-		mlx5e_page_release(rq, &xdpi->di, false);
+		if (is_redirect) {
+			xdp_return_frame(xdpi->xdpf);
+			dma_unmap_single(sq->pdev, xdpi->dma_addr,
+					 xdpi->xdpf->len, DMA_TO_DEVICE);
+		} else {
+			/* Recycle RX page */
+			mlx5e_page_release(rq, &xdpi->di, false);
+		}
 	}
 }
 
+int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		   u32 flags)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	struct mlx5e_xdpsq *sq;
+	int drops = 0;
+	int sq_num;
+	int i;
+
+	if (unlikely(!test_bit(MLX5E_STATE_OPENED, &priv->state)))
+		return -ENETDOWN;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	sq_num = smp_processor_id();
+
+	if (unlikely(sq_num >= priv->channels.num))
+		return -ENXIO;
+
+	sq = &priv->channels.c[sq_num]->xdpsq;
+
+	if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &sq->state)))
+		return -ENETDOWN;
+
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *xdpf = frames[i];
+		struct mlx5e_xdp_info xdpi;
+
+		xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len,
+					       DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) {
+			drops++;
+			continue;
+		}
+
+		xdpi.xdpf = xdpf;
+
+		if (unlikely(!mlx5e_xmit_xdp_frame(sq, &xdpi))) {
+			xdp_return_frame_rx_napi(xdpf);
+			drops++;
+		}
+	}
+
+	if (flags & XDP_XMIT_FLUSH)
+		mlx5e_xmit_xdp_doorbell(sq);
+
+	return n - drops;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index 81739aad0188..6dfab045925f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -46,6 +46,8 @@ bool mlx5e_poll_xdpsq_cq(struct mlx5e_cq *cq);
 void mlx5e_free_xdpsq_descs(struct mlx5e_xdpsq *sq);
 
 bool mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_info *xdpi);
+int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+		   u32 flags);
 
 static inline void mlx5e_xmit_xdp_doorbell(struct mlx5e_xdpsq *sq)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5a6c4403a3e2..fad947079a43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -988,7 +988,8 @@ static int mlx5e_alloc_xdpsq_db(struct mlx5e_xdpsq *sq, int numa)
 static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_sq_param *param,
-			     struct mlx5e_xdpsq *sq)
+			     struct mlx5e_xdpsq *sq,
+			     bool is_redirect)
 {
 	void *sqc_wq               = MLX5_ADDR_OF(sqc, param->sqc, wq);
 	struct mlx5_core_dev *mdev = c->mdev;
@@ -1001,7 +1002,9 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 	sq->hw_mtu    = MLX5E_SW2HW_MTU(params, params->sw_mtu);
-	sq->stats     = &c->priv->channel_stats[c->ix].rq_xdpsq;
+	sq->stats     = is_redirect ?
+		&c->priv->channel_stats[c->ix].xdpsq :
+		&c->priv->channel_stats[c->ix].rq_xdpsq;
 
 	param->wq.db_numa_node = cpu_to_node(c->cpu);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, wq, &sq->wq_ctrl);
@@ -1531,7 +1534,8 @@ static void mlx5e_close_icosq(struct mlx5e_icosq *sq)
 static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 			    struct mlx5e_params *params,
 			    struct mlx5e_sq_param *param,
-			    struct mlx5e_xdpsq *sq)
+			    struct mlx5e_xdpsq *sq,
+			    bool is_redirect)
 {
 	unsigned int ds_cnt = MLX5E_XDP_TX_DS_COUNT;
 	struct mlx5e_create_sq_param csp = {};
@@ -1539,7 +1543,7 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	err = mlx5e_alloc_xdpsq(c, params, param, sq);
+	err = mlx5e_alloc_xdpsq(c, params, param, sq, is_redirect);
 	if (err)
 		return err;
 
@@ -1548,6 +1552,8 @@ static int mlx5e_open_xdpsq(struct mlx5e_channel *c,
 	csp.cqn             = sq->cq.mcq.cqn;
 	csp.wq_ctrl         = &sq->wq_ctrl;
 	csp.min_inline_mode = sq->min_inline_mode;
+	if (is_redirect)
+		set_bit(MLX5E_SQ_STATE_REDIRECT, &sq->state);
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn);
 	if (err)
@@ -1930,10 +1936,14 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq_cq;
 
-	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
+	err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->xdpsq.cq);
 	if (err)
 		goto err_close_tx_cqs;
 
+	err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->rq.cq);
+	if (err)
+		goto err_close_xdp_tx_cqs;
+
 	/* XDP SQ CQ params are same as normal TXQ sq CQ params */
 	err = c->xdp ? mlx5e_open_cq(c, params->tx_cq_moderation,
 				     &cparam->tx_cq, &c->rq.xdpsq.cq) : 0;
@@ -1950,7 +1960,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_icosq;
 
-	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq) : 0;
+	err = c->xdp ? mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->rq.xdpsq, false) : 0;
 	if (err)
 		goto err_close_sqs;
 
@@ -1958,9 +1968,17 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	if (err)
 		goto err_close_xdp_sq;
 
+	err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, &c->xdpsq, true);
+	if (err)
+		goto err_close_rq;
+
 	*cp = c;
 
 	return 0;
+
+err_close_rq:
+	mlx5e_close_rq(&c->rq);
+
 err_close_xdp_sq:
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq.xdpsq);
@@ -1979,6 +1997,9 @@ err_disable_napi:
 err_close_rx_cq:
 	mlx5e_close_cq(&c->rq.cq);
 
+err_close_xdp_tx_cqs:
+	mlx5e_close_cq(&c->xdpsq.cq);
+
 err_close_tx_cqs:
 	mlx5e_close_tx_cqs(c);
 
@@ -2013,6 +2034,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
 
 static void mlx5e_close_channel(struct mlx5e_channel *c)
 {
+	mlx5e_close_xdpsq(&c->xdpsq);
 	mlx5e_close_rq(&c->rq);
 	if (c->xdp)
 		mlx5e_close_xdpsq(&c->rq.xdpsq);
@@ -2022,6 +2044,7 @@ static void mlx5e_close_channel(struct mlx5e_channel *c)
 	if (c->xdp)
 		mlx5e_close_cq(&c->rq.xdpsq.cq);
 	mlx5e_close_cq(&c->rq.cq);
+	mlx5e_close_cq(&c->xdpsq.cq);
 	mlx5e_close_tx_cqs(c);
 	mlx5e_close_cq(&c->icosq.cq);
 	netif_napi_del(&c->napi);
@@ -4278,6 +4301,7 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 #endif
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
 	.ndo_bpf		 = mlx5e_xdp,
+	.ndo_xdp_xmit            = mlx5e_xdp_xmit,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller     = mlx5e_netpoll,
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 85b1827b76c6..12fdf5c92b67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -75,6 +75,10 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_queue_wake) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_udp_seg_rem) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_cqe_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_wqe_err) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_cqes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_mpwqe_filler_strides) },
@@ -130,6 +134,7 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 	for (i = 0; i < priv->profile->max_nch(priv->mdev); i++) {
 		struct mlx5e_channel_stats *channel_stats =
 			&priv->channel_stats[i];
+		struct mlx5e_xdpsq_stats *xdpsq_red_stats = &channel_stats->xdpsq;
 		struct mlx5e_xdpsq_stats *xdpsq_stats = &channel_stats->rq_xdpsq;
 		struct mlx5e_rq_stats *rq_stats = &channel_stats->rq;
 		struct mlx5e_ch_stats *ch_stats = &channel_stats->ch;
@@ -168,6 +173,11 @@ void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv)
 		s->ch_arm         += ch_stats->arm;
 		s->ch_aff_change  += ch_stats->aff_change;
 		s->ch_eq_rearm    += ch_stats->eq_rearm;
+		/* xdp redirect */
+		s->tx_xdp_xmit    += xdpsq_red_stats->xmit;
+		s->tx_xdp_full    += xdpsq_red_stats->full;
+		s->tx_xdp_err     += xdpsq_red_stats->err;
+		s->tx_xdp_cqes    += xdpsq_red_stats->cqes;
 
 		for (j = 0; j < priv->max_opened_tc; j++) {
 			struct mlx5e_sq_stats *sq_stats = &channel_stats->sq[j];
@@ -1178,6 +1188,13 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = {
 	{ MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
 };
 
+static const struct counter_desc xdpsq_stats_desc[] = {
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) },
+	{ MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) },
+};
+
 static const struct counter_desc ch_stats_desc[] = {
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, events) },
 	{ MLX5E_DECLARE_CH_STAT(struct mlx5e_ch_stats, poll) },
@@ -1188,6 +1205,7 @@ static const struct counter_desc ch_stats_desc[] = {
 
 #define NUM_RQ_STATS			ARRAY_SIZE(rq_stats_desc)
 #define NUM_SQ_STATS			ARRAY_SIZE(sq_stats_desc)
+#define NUM_XDPSQ_STATS			ARRAY_SIZE(xdpsq_stats_desc)
 #define NUM_RQ_XDPSQ_STATS		ARRAY_SIZE(rq_xdpsq_stats_desc)
 #define NUM_CH_STATS			ARRAY_SIZE(ch_stats_desc)
 
@@ -1198,7 +1216,8 @@ static int mlx5e_grp_channels_get_num_stats(struct mlx5e_priv *priv)
 	return (NUM_RQ_STATS * max_nch) +
 	       (NUM_CH_STATS * max_nch) +
 	       (NUM_SQ_STATS * max_nch * priv->max_opened_tc) +
-	       (NUM_RQ_XDPSQ_STATS * max_nch);
+	       (NUM_RQ_XDPSQ_STATS * max_nch) +
+	       (NUM_XDPSQ_STATS * max_nch);
 }
 
 static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
@@ -1228,6 +1247,11 @@ static int mlx5e_grp_channels_fill_strings(struct mlx5e_priv *priv, u8 *data,
 					sq_stats_desc[j].format,
 					priv->channel_tc2txq[i][tc]);
 
+	for (i = 0; i < max_nch; i++)
+		for (j = 0; j < NUM_XDPSQ_STATS; j++)
+			sprintf(data + (idx++) * ETH_GSTRING_LEN,
+				xdpsq_stats_desc[j].format, i);
+
 	return idx;
 }
 
@@ -1261,6 +1285,12 @@ static int mlx5e_grp_channels_fill_stats(struct mlx5e_priv *priv, u64 *data,
 					MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].sq[tc],
 							     sq_stats_desc, j);
 
+	for (i = 0; i < max_nch; i++)
+		for (j = 0; j < NUM_XDPSQ_STATS; j++)
+			data[idx++] =
+				MLX5E_READ_CTR64_CPU(&priv->channel_stats[i].xdpsq,
+						     xdpsq_stats_desc, j);
+
 	return idx;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 7aa8ff389cdd..a4c035aedd46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -44,6 +44,7 @@
 #define MLX5E_DECLARE_STAT(type, fld) #fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RX_STAT(type, fld) "rx%d_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_TX_STAT(type, fld) "tx%d_"#fld, offsetof(type, fld)
+#define MLX5E_DECLARE_XDPSQ_STAT(type, fld) "tx%d_xdp_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_RQ_XDPSQ_STAT(type, fld) "rx%d_xdp_tx_"#fld, offsetof(type, fld)
 #define MLX5E_DECLARE_CH_STAT(type, fld) "ch%d_"#fld, offsetof(type, fld)
 
@@ -87,6 +88,10 @@ struct mlx5e_sw_stats {
 	u64 tx_queue_wake;
 	u64 tx_udp_seg_rem;
 	u64 tx_cqe_err;
+	u64 tx_xdp_xmit;
+	u64 tx_xdp_full;
+	u64 tx_xdp_err;
+	u64 tx_xdp_cqes;
 	u64 rx_wqe_err;
 	u64 rx_mpwqe_filler_cqes;
 	u64 rx_mpwqe_filler_strides;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
index f31bbbe1bdb1..85d517360157 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c
@@ -85,6 +85,8 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 	for (i = 0; i < c->num_tc; i++)
 		busy |= mlx5e_poll_tx_cq(&c->sq[i].cq, budget);
 
+	busy |= mlx5e_poll_xdpsq_cq(&c->xdpsq.cq);
+
 	if (c->xdp)
 		busy |= mlx5e_poll_xdpsq_cq(&c->rq.xdpsq.cq);
 
@@ -117,6 +119,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget)
 
 	mlx5e_cq_arm(&c->rq.cq);
 	mlx5e_cq_arm(&c->icosq.cq);
+	mlx5e_cq_arm(&c->xdpsq.cq);
 
 	return work_done;
 }
-- 
cgit v1.2.3


From d3398a4f1887eee46c22b37f6245faa6c51b130b Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Wed, 16 May 2018 10:46:57 +0300
Subject: net/mlx5e: RX, Prefetch the xdp_frame data area

A loaded XDP program might write to the xdp_frame data area,
prefetchw() it to avoid a potential cache miss.

Performance tests:
ConnectX-5, XDP_TX packet rate, single ring.
CPU: Intel(R) Xeon(R) CPU E5-2680 v3 @ 2.50GHz

Before: 13,172,976 pps
After:  13,456,248 pps
2% gain.

Fixes: 22f453988194 ("net/mlx5e: Support XDP over Striding RQ")
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index e33ca03b2100..15d8ae28c040 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -1099,6 +1099,7 @@ mlx5e_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi,
 
 	dma_sync_single_range_for_cpu(rq->pdev, di->addr, head_offset,
 				      frag_size, DMA_FROM_DEVICE);
+	prefetchw(va); /* xdp_frame data area */
 	prefetch(data);
 
 	rcu_read_lock();
-- 
cgit v1.2.3


From 9a3956da1c0a59b5853594d9a498289d9773df63 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Tue, 22 May 2018 17:06:38 +0300
Subject: net/mlx5e: TX, Move DB fields in TXQ-SQ struct

Pointers in DB are static, move them to read-only area so they
do not share a cacheline with fields modified in datapath.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 3f21cafe6be3..c41cfc2a4b70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -365,16 +365,14 @@ struct mlx5e_txqsq {
 
 	struct mlx5e_cq            cq;
 
-	/* write@xmit, read@completion */
-	struct {
-		struct mlx5e_sq_dma       *dma_fifo;
-		struct mlx5e_tx_wqe_info  *wqe_info;
-	} db;
-
 	/* read only */
 	struct mlx5_wq_cyc         wq;
 	u32                        dma_fifo_mask;
 	struct mlx5e_sq_stats     *stats;
+	struct {
+		struct mlx5e_sq_dma       *dma_fifo;
+		struct mlx5e_tx_wqe_info  *wqe_info;
+	} db;
 	void __iomem              *uar_map;
 	struct netdev_queue       *txq;
 	u32                        sqn;
-- 
cgit v1.2.3


From 8ee48233566624826d185bf63735cc01d7113fce Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@mellanox.com>
Date: Mon, 20 Nov 2017 13:34:15 +0200
Subject: net/mlx5e: TX, Use function to access sq_dma object in fifo

Use designated function mlx5e_dma_get() to get
the mlx5e_sq_dma object to be pushed into fifo.

Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index 9106ea45e3cb..ae73ea992845 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -66,22 +66,21 @@ static inline void mlx5e_tx_dma_unmap(struct device *pdev,
 	}
 }
 
+static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
+{
+	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+}
+
 static inline void mlx5e_dma_push(struct mlx5e_txqsq *sq,
 				  dma_addr_t addr,
 				  u32 size,
 				  enum mlx5e_dma_map_type map_type)
 {
-	u32 i = sq->dma_fifo_pc & sq->dma_fifo_mask;
+	struct mlx5e_sq_dma *dma = mlx5e_dma_get(sq, sq->dma_fifo_pc++);
 
-	sq->db.dma_fifo[i].addr = addr;
-	sq->db.dma_fifo[i].size = size;
-	sq->db.dma_fifo[i].type = map_type;
-	sq->dma_fifo_pc++;
-}
-
-static inline struct mlx5e_sq_dma *mlx5e_dma_get(struct mlx5e_txqsq *sq, u32 i)
-{
-	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+	dma->addr = addr;
+	dma->size = size;
+	dma->type = map_type;
 }
 
 static void mlx5e_dma_unmap_wqe_err(struct mlx5e_txqsq *sq, u8 num_dma)
-- 
cgit v1.2.3


From d1634e1aedbc7c30fbba819f8f4fb37df076f49c Mon Sep 17 00:00:00 2001
From: Prashant Dhamdhere <pdhamdhe@redhat.com>
Date: Fri, 20 Jul 2018 19:05:00 +0530
Subject: Documentation: vm.txt: Adding 'nr_hugepages_mempolicy' parameter
 description.

This patch adds 'nr_hugepages_mempolicy' parameter which is currently missing
in 'vm.txt' file. It also contains a short description of 'nr_hugepages_mempolicy'
parameter.

Signed-off-by: Prashant Dhamdhere <pdhamdhe@redhat.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/sysctl/vm.txt | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/sysctl/vm.txt b/Documentation/sysctl/vm.txt
index 960e82759ffb..e72853b6d725 100644
--- a/Documentation/sysctl/vm.txt
+++ b/Documentation/sysctl/vm.txt
@@ -45,6 +45,7 @@ Currently, these files are in /proc/sys/vm:
 - mmap_rnd_bits
 - mmap_rnd_compat_bits
 - nr_hugepages
+- nr_hugepages_mempolicy
 - nr_overcommit_hugepages
 - nr_trim_pages         (only if CONFIG_MMU=n)
 - numa_zonelist_order
@@ -532,6 +533,15 @@ See Documentation/admin-guide/mm/hugetlbpage.rst
 
 ==============================================================
 
+nr_hugepages_mempolicy
+
+Change the size of the hugepage pool at run-time on a specific
+set of NUMA nodes.
+
+See Documentation/admin-guide/mm/hugetlbpage.rst
+
+==============================================================
+
 nr_overcommit_hugepages
 
 Change the maximum size of the hugepage pool. The maximum is
-- 
cgit v1.2.3


From 598135e7444c121f11c8c16495ba1e6ab122678f Mon Sep 17 00:00:00 2001
From: Brian Brooks <brian.brooks@linaro.org>
Date: Wed, 25 Jul 2018 16:08:19 -0500
Subject: samples/bpf: xdpsock: order memory on AArch64
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Define u_smp_rmb() and u_smp_wmb() to respective barrier instructions.
This ensures the processor will order accesses to queue indices against
accesses to queue ring entries.

Signed-off-by: Brian Brooks <brian.brooks@linaro.org>
Acked-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/xdpsock_user.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 5904b1543831..1e82f7c617c3 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -145,8 +145,13 @@ static void dump_stats(void);
 	} while (0)
 
 #define barrier() __asm__ __volatile__("": : :"memory")
+#ifdef __aarch64__
+#define u_smp_rmb() __asm__ __volatile__("dmb ishld": : :"memory")
+#define u_smp_wmb() __asm__ __volatile__("dmb ishst": : :"memory")
+#else
 #define u_smp_rmb() barrier()
 #define u_smp_wmb() barrier()
+#endif
 #define likely(x) __builtin_expect(!!(x), 1)
 #define unlikely(x) __builtin_expect(!!(x), 0)
 
-- 
cgit v1.2.3


From 9778cfdfc9d94396d1464630073d696cdea84037 Mon Sep 17 00:00:00 2001
From: Taeung Song <treeze.taeung@gmail.com>
Date: Thu, 26 Jul 2018 19:13:44 +0900
Subject: samples/bpf: Add BTF build flags to Makefile

To smoothly test BTF supported binary on samples/bpf,
let samples/bpf/Makefile probe llc, pahole and
llvm-objcopy for BPF support and use them
like tools/testing/selftests/bpf/Makefile
changed from the commit c0fa1b6c3efc ("bpf: btf:
Add BTF tests").

Signed-off-by: Taeung Song <treeze.taeung@gmail.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/Makefile | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 9ea2f7b64869..77f512625b8c 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -195,6 +195,8 @@ HOSTLOADLIBES_xdpsock		+= -pthread
 #  make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang
 LLC ?= llc
 CLANG ?= clang
+LLVM_OBJCOPY ?= llvm-objcopy
+BTF_PAHOLE ?= pahole
 
 # Detect that we're cross compiling and use the cross compiler
 ifdef CROSS_COMPILE
@@ -202,6 +204,16 @@ HOSTCC = $(CROSS_COMPILE)gcc
 CLANG_ARCH_ARGS = -target $(ARCH)
 endif
 
+BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help 2>&1 | grep dwarfris)
+BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help 2>&1 | grep BTF)
+BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --help 2>&1 | grep -i 'usage.*llvm')
+
+ifneq ($(and $(BTF_LLC_PROBE),$(BTF_PAHOLE_PROBE),$(BTF_OBJCOPY_PROBE)),)
+	EXTRA_CFLAGS += -g
+	LLC_FLAGS += -mattr=dwarfris
+	DWARF2BTF = y
+endif
+
 # Trick to allow make to be run from this directory
 all:
 	$(MAKE) -C ../../ $(CURDIR)/ BPF_SAMPLES_PATH=$(CURDIR)
@@ -260,4 +272,7 @@ $(obj)/%.o: $(src)/%.c
 		-Wno-gnu-variable-sized-type-not-at-end \
 		-Wno-address-of-packed-member -Wno-tautological-compare \
 		-Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
-		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@
+		-O2 -emit-llvm -c $< -o -| $(LLC) -march=bpf $(LLC_FLAGS) -filetype=obj -o $@
+ifeq ($(DWARF2BTF),y)
+	$(BTF_PAHOLE) -J $@
+endif
-- 
cgit v1.2.3


From 8c3799ee25e1fda159099af09f5f2e86091e41d4 Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:43 +0300
Subject: xen/grant-table: Make set/clear page private code shared

Make set/clear page private code shared and accessible to
other kernel modules which can re-use these instead of open-coding.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/grant-table.c | 54 ++++++++++++++++++++++++++++++-----------------
 include/xen/grant_table.h |  3 +++
 2 files changed, 38 insertions(+), 19 deletions(-)

diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index ba9f3eec2bd0..bb4840653bf2 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -769,29 +769,18 @@ void gnttab_free_auto_xlat_frames(void)
 }
 EXPORT_SYMBOL_GPL(gnttab_free_auto_xlat_frames);
 
-/**
- * gnttab_alloc_pages - alloc pages suitable for grant mapping into
- * @nr_pages: number of pages to alloc
- * @pages: returns the pages
- */
-int gnttab_alloc_pages(int nr_pages, struct page **pages)
+int gnttab_pages_set_private(int nr_pages, struct page **pages)
 {
 	int i;
-	int ret;
-
-	ret = alloc_xenballooned_pages(nr_pages, pages);
-	if (ret < 0)
-		return ret;
 
 	for (i = 0; i < nr_pages; i++) {
 #if BITS_PER_LONG < 64
 		struct xen_page_foreign *foreign;
 
 		foreign = kzalloc(sizeof(*foreign), GFP_KERNEL);
-		if (!foreign) {
-			gnttab_free_pages(nr_pages, pages);
+		if (!foreign)
 			return -ENOMEM;
-		}
+
 		set_page_private(pages[i], (unsigned long)foreign);
 #endif
 		SetPagePrivate(pages[i]);
@@ -799,14 +788,30 @@ int gnttab_alloc_pages(int nr_pages, struct page **pages)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+EXPORT_SYMBOL_GPL(gnttab_pages_set_private);
 
 /**
- * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
- * @nr_pages; number of pages to free
- * @pages: the pages
+ * gnttab_alloc_pages - alloc pages suitable for grant mapping into
+ * @nr_pages: number of pages to alloc
+ * @pages: returns the pages
  */
-void gnttab_free_pages(int nr_pages, struct page **pages)
+int gnttab_alloc_pages(int nr_pages, struct page **pages)
+{
+	int ret;
+
+	ret = alloc_xenballooned_pages(nr_pages, pages);
+	if (ret < 0)
+		return ret;
+
+	ret = gnttab_pages_set_private(nr_pages, pages);
+	if (ret < 0)
+		gnttab_free_pages(nr_pages, pages);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_alloc_pages);
+
+void gnttab_pages_clear_private(int nr_pages, struct page **pages)
 {
 	int i;
 
@@ -818,6 +823,17 @@ void gnttab_free_pages(int nr_pages, struct page **pages)
 			ClearPagePrivate(pages[i]);
 		}
 	}
+}
+EXPORT_SYMBOL_GPL(gnttab_pages_clear_private);
+
+/**
+ * gnttab_free_pages - free pages allocated by gnttab_alloc_pages()
+ * @nr_pages; number of pages to free
+ * @pages: the pages
+ */
+void gnttab_free_pages(int nr_pages, struct page **pages)
+{
+	gnttab_pages_clear_private(nr_pages, pages);
 	free_xenballooned_pages(nr_pages, pages);
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index 2e37741f6b8d..de03f2542bb7 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -198,6 +198,9 @@ void gnttab_free_auto_xlat_frames(void);
 int gnttab_alloc_pages(int nr_pages, struct page **pages);
 void gnttab_free_pages(int nr_pages, struct page **pages);
 
+int gnttab_pages_set_private(int nr_pages, struct page **pages);
+void gnttab_pages_clear_private(int nr_pages, struct page **pages);
+
 int gnttab_map_refs(struct gnttab_map_grant_ref *map_ops,
 		    struct gnttab_map_grant_ref *kmap_ops,
 		    struct page **pages, unsigned int count);
-- 
cgit v1.2.3


From ae4c51a50c990d6feba7058c181dc8f22ca5f1d8 Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:44 +0300
Subject: xen/balloon: Share common memory reservation routines

Memory {increase|decrease}_reservation and VA mappings update/reset
code used in balloon driver can be made common, so other drivers can
also re-use the same functionality without open-coding.
Create a dedicated file for the shared code and export corresponding
symbols for other kernel modules.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/Makefile          |   1 +
 drivers/xen/balloon.c         |  75 +++------------------------
 drivers/xen/mem-reservation.c | 118 ++++++++++++++++++++++++++++++++++++++++++
 include/xen/mem-reservation.h |  59 +++++++++++++++++++++
 4 files changed, 184 insertions(+), 69 deletions(-)
 create mode 100644 drivers/xen/mem-reservation.c
 create mode 100644 include/xen/mem-reservation.h

diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 48b154276179..129dd1cc1b83 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -2,6 +2,7 @@
 obj-$(CONFIG_HOTPLUG_CPU)		+= cpu_hotplug.o
 obj-$(CONFIG_X86)			+= fallback.o
 obj-y	+= grant-table.o features.o balloon.o manage.o preempt.o time.o
+obj-y	+= mem-reservation.o
 obj-y	+= events/
 obj-y	+= xenbus/
 
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index 065f0b607373..e12bb256036f 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -71,6 +71,7 @@
 #include <xen/balloon.h>
 #include <xen/features.h>
 #include <xen/page.h>
+#include <xen/mem-reservation.h>
 
 static int xen_hotplug_unpopulated;
 
@@ -157,13 +158,6 @@ static DECLARE_DELAYED_WORK(balloon_worker, balloon_process);
 #define GFP_BALLOON \
 	(GFP_HIGHUSER | __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC)
 
-static void scrub_page(struct page *page)
-{
-#ifdef CONFIG_XEN_SCRUB_PAGES
-	clear_highpage(page);
-#endif
-}
-
 /* balloon_append: add the given page to the balloon. */
 static void __balloon_append(struct page *page)
 {
@@ -463,11 +457,6 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 	int rc;
 	unsigned long i;
 	struct page   *page;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
 		nr_pages = ARRAY_SIZE(frame_list);
@@ -479,16 +468,11 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 			break;
 		}
 
-		/* XENMEM_populate_physmap requires a PFN based on Xen
-		 * granularity.
-		 */
 		frame_list[i] = page_to_xen_pfn(page);
 		page = balloon_next_page(page);
 	}
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents = nr_pages;
-	rc = HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+	rc = xenmem_reservation_increase(nr_pages, frame_list);
 	if (rc <= 0)
 		return BP_EAGAIN;
 
@@ -496,29 +480,7 @@ static enum bp_state increase_reservation(unsigned long nr_pages)
 		page = balloon_retrieve(false);
 		BUG_ON(page == NULL);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
-
-			set_phys_to_machine(pfn, frame_list[i]);
-
-			/* Link back into the page tables if not highmem. */
-			if (!PageHighMem(page)) {
-				int ret;
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						mfn_pte(frame_list[i], PAGE_KERNEL),
-						0);
-				BUG_ON(ret);
-			}
-		}
-#endif
+		xenmem_reservation_va_mapping_update(1, &page, &frame_list[i]);
 
 		/* Relinquish the page back to the allocator. */
 		free_reserved_page(page);
@@ -535,11 +497,6 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	unsigned long i;
 	struct page *page, *tmp;
 	int ret;
-	struct xen_memory_reservation reservation = {
-		.address_bits = 0,
-		.extent_order = EXTENT_ORDER,
-		.domid        = DOMID_SELF
-	};
 	LIST_HEAD(pages);
 
 	if (nr_pages > ARRAY_SIZE(frame_list))
@@ -553,7 +510,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 			break;
 		}
 		adjust_managed_page_count(page, -1);
-		scrub_page(page);
+		xenmem_reservation_scrub_page(page);
 		list_add(&page->lru, &pages);
 	}
 
@@ -572,28 +529,10 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 	 */
 	i = 0;
 	list_for_each_entry_safe(page, tmp, &pages, lru) {
-		/* XENMEM_decrease_reservation requires a GFN */
 		frame_list[i++] = xen_page_to_gfn(page);
 
-#ifdef CONFIG_XEN_HAVE_PVMMU
-		/*
-		 * We don't support PV MMU when Linux and Xen is using
-		 * different page granularity.
-		 */
-		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
-
-		if (!xen_feature(XENFEAT_auto_translated_physmap)) {
-			unsigned long pfn = page_to_pfn(page);
+		xenmem_reservation_va_mapping_reset(1, &page);
 
-			if (!PageHighMem(page)) {
-				ret = HYPERVISOR_update_va_mapping(
-						(unsigned long)__va(pfn << PAGE_SHIFT),
-						__pte_ma(0), 0);
-				BUG_ON(ret);
-			}
-			__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
-		}
-#endif
 		list_del(&page->lru);
 
 		balloon_append(page);
@@ -601,9 +540,7 @@ static enum bp_state decrease_reservation(unsigned long nr_pages, gfp_t gfp)
 
 	flush_tlb_all();
 
-	set_xen_guest_handle(reservation.extent_start, frame_list);
-	reservation.nr_extents   = nr_pages;
-	ret = HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+	ret = xenmem_reservation_decrease(nr_pages, frame_list);
 	BUG_ON(ret != nr_pages);
 
 	balloon_stats.current_pages -= nr_pages;
diff --git a/drivers/xen/mem-reservation.c b/drivers/xen/mem-reservation.c
new file mode 100644
index 000000000000..084799c6180e
--- /dev/null
+++ b/drivers/xen/mem-reservation.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/******************************************************************************
+ * Xen memory reservation utilities.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <asm/xen/hypercall.h>
+
+#include <xen/interface/memory.h>
+#include <xen/mem-reservation.h>
+
+/*
+ * Use one extent per PAGE_SIZE to avoid to break down the page into
+ * multiple frame.
+ */
+#define EXTENT_ORDER (fls(XEN_PFN_PER_PAGE) - 1)
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+void __xenmem_reservation_va_mapping_update(unsigned long count,
+					    struct page **pages,
+					    xen_pfn_t *frames)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		BUG_ON(!page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen is using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		set_phys_to_machine(pfn, frames[i]);
+
+		/* Link back into the page tables if not highmem. */
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					mfn_pte(frames[i], PAGE_KERNEL),
+					0);
+			BUG_ON(ret);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_update);
+
+void __xenmem_reservation_va_mapping_reset(unsigned long count,
+					   struct page **pages)
+{
+	int i;
+
+	for (i = 0; i < count; i++) {
+		struct page *page = pages[i];
+		unsigned long pfn = page_to_pfn(page);
+
+		/*
+		 * We don't support PV MMU when Linux and Xen are using
+		 * different page granularity.
+		 */
+		BUILD_BUG_ON(XEN_PAGE_SIZE != PAGE_SIZE);
+
+		if (!PageHighMem(page)) {
+			int ret;
+
+			ret = HYPERVISOR_update_va_mapping(
+					(unsigned long)__va(pfn << PAGE_SHIFT),
+					__pte_ma(0), 0);
+			BUG_ON(ret);
+		}
+		__set_phys_to_machine(pfn, INVALID_P2M_ENTRY);
+	}
+}
+EXPORT_SYMBOL_GPL(__xenmem_reservation_va_mapping_reset);
+#endif /* CONFIG_XEN_HAVE_PVMMU */
+
+/* @frames is an array of PFNs */
+int xenmem_reservation_increase(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_populate_physmap requires a PFN based on Xen granularity. */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_populate_physmap, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_increase);
+
+/* @frames is an array of GFNs */
+int xenmem_reservation_decrease(int count, xen_pfn_t *frames)
+{
+	struct xen_memory_reservation reservation = {
+		.address_bits = 0,
+		.extent_order = EXTENT_ORDER,
+		.domid        = DOMID_SELF
+	};
+
+	/* XENMEM_decrease_reservation requires a GFN */
+	set_xen_guest_handle(reservation.extent_start, frames);
+	reservation.nr_extents = count;
+	return HYPERVISOR_memory_op(XENMEM_decrease_reservation, &reservation);
+}
+EXPORT_SYMBOL_GPL(xenmem_reservation_decrease);
diff --git a/include/xen/mem-reservation.h b/include/xen/mem-reservation.h
new file mode 100644
index 000000000000..80b52b4945e9
--- /dev/null
+++ b/include/xen/mem-reservation.h
@@ -0,0 +1,59 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Xen memory reservation utilities.
+ *
+ * Copyright (c) 2003, B Dragovic
+ * Copyright (c) 2003-2004, M Williamson, K Fraser
+ * Copyright (c) 2005 Dan M. Smith, IBM Corporation
+ * Copyright (c) 2010 Daniel Kiper
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _XENMEM_RESERVATION_H
+#define _XENMEM_RESERVATION_H
+
+#include <linux/highmem.h>
+
+#include <xen/page.h>
+
+static inline void xenmem_reservation_scrub_page(struct page *page)
+{
+#ifdef CONFIG_XEN_SCRUB_PAGES
+	clear_highpage(page);
+#endif
+}
+
+#ifdef CONFIG_XEN_HAVE_PVMMU
+void __xenmem_reservation_va_mapping_update(unsigned long count,
+					    struct page **pages,
+					    xen_pfn_t *frames);
+
+void __xenmem_reservation_va_mapping_reset(unsigned long count,
+					   struct page **pages);
+#endif
+
+static inline void xenmem_reservation_va_mapping_update(unsigned long count,
+							struct page **pages,
+							xen_pfn_t *frames)
+{
+#ifdef CONFIG_XEN_HAVE_PVMMU
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		__xenmem_reservation_va_mapping_update(count, pages, frames);
+#endif
+}
+
+static inline void xenmem_reservation_va_mapping_reset(unsigned long count,
+						       struct page **pages)
+{
+#ifdef CONFIG_XEN_HAVE_PVMMU
+	if (!xen_feature(XENFEAT_auto_translated_physmap))
+		__xenmem_reservation_va_mapping_reset(count, pages);
+#endif
+}
+
+int xenmem_reservation_increase(int count, xen_pfn_t *frames);
+
+int xenmem_reservation_decrease(int count, xen_pfn_t *frames);
+
+#endif
-- 
cgit v1.2.3


From 9bdc7304f536f3f77f0a69e7c3a8f5afda561a68 Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:45 +0300
Subject: xen/grant-table: Allow allocating buffers suitable for DMA

Extend grant table module API to allow allocating buffers that can
be used for DMA operations and mapping foreign grant references
on top of those.
The resulting buffer is similar to the one allocated by the balloon
driver in that proper memory reservation is made by
({increase|decrease}_reservation and VA mappings are updated if
needed).
This is useful for sharing foreign buffers with HW drivers which
cannot work with scattered buffers provided by the balloon driver,
but require DMAable memory instead.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/Kconfig       | 14 +++++++
 drivers/xen/grant-table.c | 97 +++++++++++++++++++++++++++++++++++++++++++++++
 include/xen/grant_table.h | 18 +++++++++
 3 files changed, 129 insertions(+)

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index e5d0c28372ea..75e5c40f80a5 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -161,6 +161,20 @@ config XEN_GRANT_DEV_ALLOC
 	  to other domains. This can be used to implement frontend drivers
 	  or as part of an inter-domain shared memory channel.
 
+config XEN_GRANT_DMA_ALLOC
+	bool "Allow allocating DMA capable buffers with grant reference module"
+	depends on XEN && HAS_DMA
+	help
+	  Extends grant table module API to allow allocating DMA capable
+	  buffers and mapping foreign grant references on top of it.
+	  The resulting buffer is similar to one allocated by the balloon
+	  driver in that proper memory reservation is made by
+	  ({increase|decrease}_reservation and VA mappings are updated if
+	  needed).
+	  This is useful for sharing foreign buffers with HW drivers which
+	  cannot work with scattered buffers provided by the balloon driver,
+	  but require DMAable memory instead.
+
 config SWIOTLB_XEN
 	def_bool y
 	select SWIOTLB
diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c
index bb4840653bf2..7bafa703a992 100644
--- a/drivers/xen/grant-table.c
+++ b/drivers/xen/grant-table.c
@@ -45,6 +45,9 @@
 #include <linux/workqueue.h>
 #include <linux/ratelimit.h>
 #include <linux/moduleparam.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/dma-mapping.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/interface/xen.h>
@@ -57,6 +60,7 @@
 #ifdef CONFIG_X86
 #include <asm/xen/cpuid.h>
 #endif
+#include <xen/mem-reservation.h>
 #include <asm/xen/hypercall.h>
 #include <asm/xen/interface.h>
 
@@ -838,6 +842,99 @@ void gnttab_free_pages(int nr_pages, struct page **pages)
 }
 EXPORT_SYMBOL_GPL(gnttab_free_pages);
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+/**
+ * gnttab_dma_alloc_pages - alloc DMAable pages suitable for grant mapping into
+ * @args: arguments to the function
+ */
+int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args)
+{
+	unsigned long pfn, start_pfn;
+	size_t size;
+	int i, ret;
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		args->vaddr = dma_alloc_coherent(args->dev, size,
+						 &args->dev_bus_addr,
+						 GFP_KERNEL | __GFP_NOWARN);
+	else
+		args->vaddr = dma_alloc_wc(args->dev, size,
+					   &args->dev_bus_addr,
+					   GFP_KERNEL | __GFP_NOWARN);
+	if (!args->vaddr) {
+		pr_debug("Failed to allocate DMA buffer of size %zu\n", size);
+		return -ENOMEM;
+	}
+
+	start_pfn = __phys_to_pfn(args->dev_bus_addr);
+	for (pfn = start_pfn, i = 0; pfn < start_pfn + args->nr_pages;
+			pfn++, i++) {
+		struct page *page = pfn_to_page(pfn);
+
+		args->pages[i] = page;
+		args->frames[i] = xen_page_to_gfn(page);
+		xenmem_reservation_scrub_page(page);
+	}
+
+	xenmem_reservation_va_mapping_reset(args->nr_pages, args->pages);
+
+	ret = xenmem_reservation_decrease(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+		goto fail;
+	}
+
+	ret = gnttab_pages_set_private(args->nr_pages, args->pages);
+	if (ret < 0)
+		goto fail;
+
+	return 0;
+
+fail:
+	gnttab_dma_free_pages(args);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_alloc_pages);
+
+/**
+ * gnttab_dma_free_pages - free DMAable pages
+ * @args: arguments to the function
+ */
+int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args)
+{
+	size_t size;
+	int i, ret;
+
+	gnttab_pages_clear_private(args->nr_pages, args->pages);
+
+	for (i = 0; i < args->nr_pages; i++)
+		args->frames[i] = page_to_xen_pfn(args->pages[i]);
+
+	ret = xenmem_reservation_increase(args->nr_pages, args->frames);
+	if (ret != args->nr_pages) {
+		pr_debug("Failed to decrease reservation for DMA buffer\n");
+		ret = -EFAULT;
+	} else {
+		ret = 0;
+	}
+
+	xenmem_reservation_va_mapping_update(args->nr_pages, args->pages,
+					     args->frames);
+
+	size = args->nr_pages << PAGE_SHIFT;
+	if (args->coherent)
+		dma_free_coherent(args->dev, size,
+				  args->vaddr, args->dev_bus_addr);
+	else
+		dma_free_wc(args->dev, size,
+			    args->vaddr, args->dev_bus_addr);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(gnttab_dma_free_pages);
+#endif
+
 /* Handling of paged out grant targets (GNTST_eagain) */
 #define MAX_DELAY 256
 static inline void
diff --git a/include/xen/grant_table.h b/include/xen/grant_table.h
index de03f2542bb7..9bc5bc07d4d3 100644
--- a/include/xen/grant_table.h
+++ b/include/xen/grant_table.h
@@ -198,6 +198,24 @@ void gnttab_free_auto_xlat_frames(void);
 int gnttab_alloc_pages(int nr_pages, struct page **pages);
 void gnttab_free_pages(int nr_pages, struct page **pages);
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+struct gnttab_dma_alloc_args {
+	/* Device for which DMA memory will be/was allocated. */
+	struct device *dev;
+	/* If set then DMA buffer is coherent and write-combine otherwise. */
+	bool coherent;
+
+	int nr_pages;
+	struct page **pages;
+	xen_pfn_t *frames;
+	void *vaddr;
+	dma_addr_t dev_bus_addr;
+};
+
+int gnttab_dma_alloc_pages(struct gnttab_dma_alloc_args *args);
+int gnttab_dma_free_pages(struct gnttab_dma_alloc_args *args);
+#endif
+
 int gnttab_pages_set_private(int nr_pages, struct page **pages);
 void gnttab_pages_clear_private(int nr_pages, struct page **pages);
 
-- 
cgit v1.2.3


From 975ef7ff81bb000af6e6c8e63e81f89f3468dcf7 Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:46 +0300
Subject: xen/gntdev: Allow mappings for DMA buffers

Allow mappings for DMA backed  buffers if grant table module
supports such: this extends grant device to not only map buffers
made of balloon pages, but also from buffers allocated with
dma_alloc_xxx.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/gntdev.c      | 99 ++++++++++++++++++++++++++++++++++++++++++++++-
 include/uapi/xen/gntdev.h | 15 +++++++
 2 files changed, 112 insertions(+), 2 deletions(-)

diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index bd56653b9bbc..173332f439d8 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -37,6 +37,9 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/refcount.h>
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+#include <linux/of_device.h>
+#endif
 
 #include <xen/xen.h>
 #include <xen/grant_table.h>
@@ -72,6 +75,11 @@ struct gntdev_priv {
 	struct mutex lock;
 	struct mm_struct *mm;
 	struct mmu_notifier mn;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/* Device for which DMA memory is allocated. */
+	struct device *dma_dev;
+#endif
 };
 
 struct unmap_notify {
@@ -96,10 +104,27 @@ struct grant_map {
 	struct gnttab_unmap_grant_ref *kunmap_ops;
 	struct page **pages;
 	unsigned long pages_vm_start;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/*
+	 * If dmabuf_vaddr is not NULL then this mapping is backed by DMA
+	 * capable memory.
+	 */
+
+	struct device *dma_dev;
+	/* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */
+	int dma_flags;
+	void *dma_vaddr;
+	dma_addr_t dma_bus_addr;
+	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
+	xen_pfn_t *frames;
+#endif
 };
 
 static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
 
+static struct miscdevice gntdev_miscdev;
+
 /* ------------------------------------------------------------------ */
 
 static void gntdev_print_maps(struct gntdev_priv *priv,
@@ -121,8 +146,27 @@ static void gntdev_free_map(struct grant_map *map)
 	if (map == NULL)
 		return;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	if (map->dma_vaddr) {
+		struct gnttab_dma_alloc_args args;
+
+		args.dev = map->dma_dev;
+		args.coherent = !!(map->dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = map->count;
+		args.pages = map->pages;
+		args.frames = map->frames;
+		args.vaddr = map->dma_vaddr;
+		args.dev_bus_addr = map->dma_bus_addr;
+
+		gnttab_dma_free_pages(&args);
+	} else
+#endif
 	if (map->pages)
 		gnttab_free_pages(map->count, map->pages);
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	kfree(map->frames);
+#endif
 	kfree(map->pages);
 	kfree(map->grants);
 	kfree(map->map_ops);
@@ -132,7 +176,8 @@ static void gntdev_free_map(struct grant_map *map)
 	kfree(map);
 }
 
-static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
+static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags)
 {
 	struct grant_map *add;
 	int i;
@@ -155,6 +200,37 @@ static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count)
 	    NULL == add->pages)
 		goto err;
 
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	add->dma_flags = dma_flags;
+
+	/*
+	 * Check if this mapping is requested to be backed
+	 * by a DMA buffer.
+	 */
+	if (dma_flags & (GNTDEV_DMA_FLAG_WC | GNTDEV_DMA_FLAG_COHERENT)) {
+		struct gnttab_dma_alloc_args args;
+
+		add->frames = kcalloc(count, sizeof(add->frames[0]),
+				      GFP_KERNEL);
+		if (!add->frames)
+			goto err;
+
+		/* Remember the device, so we can free DMA memory. */
+		add->dma_dev = priv->dma_dev;
+
+		args.dev = priv->dma_dev;
+		args.coherent = !!(dma_flags & GNTDEV_DMA_FLAG_COHERENT);
+		args.nr_pages = count;
+		args.pages = add->pages;
+		args.frames = add->frames;
+
+		if (gnttab_dma_alloc_pages(&args))
+			goto err;
+
+		add->dma_vaddr = args.vaddr;
+		add->dma_bus_addr = args.dev_bus_addr;
+	} else
+#endif
 	if (gnttab_alloc_pages(count, add->pages))
 		goto err;
 
@@ -325,6 +401,14 @@ static int map_grant_pages(struct grant_map *map)
 		map->unmap_ops[i].handle = map->map_ops[i].handle;
 		if (use_ptemod)
 			map->kunmap_ops[i].handle = map->kmap_ops[i].handle;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+		else if (map->dma_vaddr) {
+			unsigned long bfn;
+
+			bfn = pfn_to_bfn(page_to_pfn(map->pages[i]));
+			map->unmap_ops[i].dev_bus_addr = __pfn_to_phys(bfn);
+		}
+#endif
 	}
 	return err;
 }
@@ -548,6 +632,17 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	}
 
 	flip->private_data = priv;
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	priv->dma_dev = gntdev_miscdev.this_device;
+
+	/*
+	 * The device is not spawn from a device tree, so arch_setup_dma_ops
+	 * is not called, thus leaving the device with dummy DMA ops.
+	 * Fix this by calling of_dma_configure() with a NULL node to set
+	 * default DMA ops.
+	 */
+	of_dma_configure(priv->dma_dev, NULL, true);
+#endif
 	pr_debug("priv %p\n", priv);
 
 	return 0;
@@ -589,7 +684,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 		return -EINVAL;
 
 	err = -ENOMEM;
-	map = gntdev_alloc_map(priv, op.count);
+	map = gntdev_alloc_map(priv, op.count, 0 /* This is not a dma-buf. */);
 	if (!map)
 		return err;
 
diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h
index 6d1163456c03..4b9d498a31d4 100644
--- a/include/uapi/xen/gntdev.h
+++ b/include/uapi/xen/gntdev.h
@@ -200,4 +200,19 @@ struct ioctl_gntdev_grant_copy {
 /* Send an interrupt on the indicated event channel */
 #define UNMAP_NOTIFY_SEND_EVENT 0x2
 
+/*
+ * Flags to be used while requesting memory mapping's backing storage
+ * to be allocated with DMA API.
+ */
+
+/*
+ * The buffer is backed with memory allocated with dma_alloc_wc.
+ */
+#define GNTDEV_DMA_FLAG_WC		(1 << 0)
+
+/*
+ * The buffer is backed with memory allocated with dma_alloc_coherent.
+ */
+#define GNTDEV_DMA_FLAG_COHERENT	(1 << 1)
+
 #endif /* __LINUX_PUBLIC_GNTDEV_H__ */
-- 
cgit v1.2.3


From 1d314567553883d9f606cc59e8e66f465a4b6ccd Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:47 +0300
Subject: xen/gntdev: Make private routines/structures accessible

This is in preparation for adding support of DMA buffer
functionality: make map/unmap related code and structures, used
privately by gntdev, ready for dma-buf extension, which will re-use
these. Rename corresponding structures as those become non-private
to gntdev now.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/gntdev-common.h |  88 +++++++++++++++++++++++++++++
 drivers/xen/gntdev.c        | 134 ++++++++++++++------------------------------
 2 files changed, 131 insertions(+), 91 deletions(-)
 create mode 100644 drivers/xen/gntdev-common.h

diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h
new file mode 100644
index 000000000000..2346c198f72e
--- /dev/null
+++ b/drivers/xen/gntdev-common.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Common functionality of grant device.
+ *
+ * Copyright (c) 2006-2007, D G Murray.
+ *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_COMMON_H
+#define _GNTDEV_COMMON_H
+
+#include <linux/mm.h>
+#include <linux/mman.h>
+#include <linux/mmu_notifier.h>
+#include <linux/types.h>
+
+struct gntdev_priv {
+	/* Maps with visible offsets in the file descriptor. */
+	struct list_head maps;
+	/*
+	 * Maps that are not visible; will be freed on munmap.
+	 * Only populated if populate_freeable_maps == 1
+	 */
+	struct list_head freeable_maps;
+	/* lock protects maps and freeable_maps. */
+	struct mutex lock;
+	struct mm_struct *mm;
+	struct mmu_notifier mn;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/* Device for which DMA memory is allocated. */
+	struct device *dma_dev;
+#endif
+};
+
+struct gntdev_unmap_notify {
+	int flags;
+	/* Address relative to the start of the gntdev_grant_map. */
+	int addr;
+	int event;
+};
+
+struct gntdev_grant_map {
+	struct list_head next;
+	struct vm_area_struct *vma;
+	int index;
+	int count;
+	int flags;
+	refcount_t users;
+	struct gntdev_unmap_notify notify;
+	struct ioctl_gntdev_grant_ref *grants;
+	struct gnttab_map_grant_ref   *map_ops;
+	struct gnttab_unmap_grant_ref *unmap_ops;
+	struct gnttab_map_grant_ref   *kmap_ops;
+	struct gnttab_unmap_grant_ref *kunmap_ops;
+	struct page **pages;
+	unsigned long pages_vm_start;
+
+#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
+	/*
+	 * If dmabuf_vaddr is not NULL then this mapping is backed by DMA
+	 * capable memory.
+	 */
+
+	struct device *dma_dev;
+	/* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */
+	int dma_flags;
+	void *dma_vaddr;
+	dma_addr_t dma_bus_addr;
+	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
+	xen_pfn_t *frames;
+#endif
+};
+
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+					  int dma_flags);
+
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add);
+
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map);
+
+bool gntdev_account_mapped_pages(int count);
+
+int gntdev_map_grant_pages(struct gntdev_grant_map *map);
+
+#endif
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 173332f439d8..e03f50052f3e 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -6,6 +6,7 @@
  *
  * Copyright (c) 2006-2007, D G Murray.
  *           (c) 2009 Gerd Hoffmann <kraxel@redhat.com>
+ *           (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
  *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
@@ -26,10 +27,6 @@
 #include <linux/init.h>
 #include <linux/miscdevice.h>
 #include <linux/fs.h>
-#include <linux/mm.h>
-#include <linux/mman.h>
-#include <linux/mmu_notifier.h>
-#include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/sched.h>
 #include <linux/sched/mm.h>
@@ -50,6 +47,8 @@
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
+#include "gntdev-common.h"
+
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
 	      "Gerd Hoffmann <kraxel@redhat.com>");
@@ -65,73 +64,23 @@ static atomic_t pages_mapped = ATOMIC_INIT(0);
 static int use_ptemod;
 #define populate_freeable_maps use_ptemod
 
-struct gntdev_priv {
-	/* maps with visible offsets in the file descriptor */
-	struct list_head maps;
-	/* maps that are not visible; will be freed on munmap.
-	 * Only populated if populate_freeable_maps == 1 */
-	struct list_head freeable_maps;
-	/* lock protects maps and freeable_maps */
-	struct mutex lock;
-	struct mm_struct *mm;
-	struct mmu_notifier mn;
-
-#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
-	/* Device for which DMA memory is allocated. */
-	struct device *dma_dev;
-#endif
-};
-
-struct unmap_notify {
-	int flags;
-	/* Address relative to the start of the grant_map */
-	int addr;
-	int event;
-};
-
-struct grant_map {
-	struct list_head next;
-	struct vm_area_struct *vma;
-	int index;
-	int count;
-	int flags;
-	refcount_t users;
-	struct unmap_notify notify;
-	struct ioctl_gntdev_grant_ref *grants;
-	struct gnttab_map_grant_ref   *map_ops;
-	struct gnttab_unmap_grant_ref *unmap_ops;
-	struct gnttab_map_grant_ref   *kmap_ops;
-	struct gnttab_unmap_grant_ref *kunmap_ops;
-	struct page **pages;
-	unsigned long pages_vm_start;
-
-#ifdef CONFIG_XEN_GRANT_DMA_ALLOC
-	/*
-	 * If dmabuf_vaddr is not NULL then this mapping is backed by DMA
-	 * capable memory.
-	 */
-
-	struct device *dma_dev;
-	/* Flags used to create this DMA buffer: GNTDEV_DMA_FLAG_XXX. */
-	int dma_flags;
-	void *dma_vaddr;
-	dma_addr_t dma_bus_addr;
-	/* Needed to avoid allocation in gnttab_dma_free_pages(). */
-	xen_pfn_t *frames;
-#endif
-};
-
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages);
+static int unmap_grant_pages(struct gntdev_grant_map *map,
+			     int offset, int pages);
 
 static struct miscdevice gntdev_miscdev;
 
 /* ------------------------------------------------------------------ */
 
+bool gntdev_account_mapped_pages(int count)
+{
+	return atomic_add_return(count, &pages_mapped) > limit;
+}
+
 static void gntdev_print_maps(struct gntdev_priv *priv,
 			      char *text, int text_index)
 {
 #ifdef DEBUG
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("%s: maps list (priv %p)\n", __func__, priv);
 	list_for_each_entry(map, &priv->maps, next)
@@ -141,7 +90,7 @@ static void gntdev_print_maps(struct gntdev_priv *priv,
 #endif
 }
 
-static void gntdev_free_map(struct grant_map *map)
+static void gntdev_free_map(struct gntdev_grant_map *map)
 {
 	if (map == NULL)
 		return;
@@ -176,13 +125,13 @@ static void gntdev_free_map(struct grant_map *map)
 	kfree(map);
 }
 
-static struct grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
+struct gntdev_grant_map *gntdev_alloc_map(struct gntdev_priv *priv, int count,
 					  int dma_flags)
 {
-	struct grant_map *add;
+	struct gntdev_grant_map *add;
 	int i;
 
-	add = kzalloc(sizeof(struct grant_map), GFP_KERNEL);
+	add = kzalloc(sizeof(*add), GFP_KERNEL);
 	if (NULL == add)
 		return NULL;
 
@@ -252,9 +201,9 @@ err:
 	return NULL;
 }
 
-static void gntdev_add_map(struct gntdev_priv *priv, struct grant_map *add)
+void gntdev_add_map(struct gntdev_priv *priv, struct gntdev_grant_map *add)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (add->index + add->count < map->index) {
@@ -269,10 +218,10 @@ done:
 	gntdev_print_maps(priv, "[new]", add->index);
 }
 
-static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
-		int index, int count)
+static struct gntdev_grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
+						      int index, int count)
 {
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	list_for_each_entry(map, &priv->maps, next) {
 		if (map->index != index)
@@ -284,7 +233,7 @@ static struct grant_map *gntdev_find_map_index(struct gntdev_priv *priv,
 	return NULL;
 }
 
-static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
+void gntdev_put_map(struct gntdev_priv *priv, struct gntdev_grant_map *map)
 {
 	if (!map)
 		return;
@@ -315,7 +264,7 @@ static void gntdev_put_map(struct gntdev_priv *priv, struct grant_map *map)
 static int find_grant_ptes(pte_t *pte, pgtable_t token,
 		unsigned long addr, void *data)
 {
-	struct grant_map *map = data;
+	struct gntdev_grant_map *map = data;
 	unsigned int pgnr = (addr - map->vma->vm_start) >> PAGE_SHIFT;
 	int flags = map->flags | GNTMAP_application_map | GNTMAP_contains_pte;
 	u64 pte_maddr;
@@ -348,7 +297,7 @@ static int set_grant_ptes_as_special(pte_t *pte, pgtable_t token,
 }
 #endif
 
-static int map_grant_pages(struct grant_map *map)
+int gntdev_map_grant_pages(struct gntdev_grant_map *map)
 {
 	int i, err = 0;
 
@@ -413,7 +362,8 @@ static int map_grant_pages(struct grant_map *map)
 	return err;
 }
 
-static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int __unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			       int pages)
 {
 	int i, err = 0;
 	struct gntab_unmap_queue_data unmap_data;
@@ -448,7 +398,8 @@ static int __unmap_grant_pages(struct grant_map *map, int offset, int pages)
 	return err;
 }
 
-static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
+static int unmap_grant_pages(struct gntdev_grant_map *map, int offset,
+			     int pages)
 {
 	int range, err = 0;
 
@@ -480,7 +431,7 @@ static int unmap_grant_pages(struct grant_map *map, int offset, int pages)
 
 static void gntdev_vma_open(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	pr_debug("gntdev_vma_open %p\n", vma);
 	refcount_inc(&map->users);
@@ -488,7 +439,7 @@ static void gntdev_vma_open(struct vm_area_struct *vma)
 
 static void gntdev_vma_close(struct vm_area_struct *vma)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 	struct file *file = vma->vm_file;
 	struct gntdev_priv *priv = file->private_data;
 
@@ -512,7 +463,7 @@ static void gntdev_vma_close(struct vm_area_struct *vma)
 static struct page *gntdev_vma_find_special_page(struct vm_area_struct *vma,
 						 unsigned long addr)
 {
-	struct grant_map *map = vma->vm_private_data;
+	struct gntdev_grant_map *map = vma->vm_private_data;
 
 	return map->pages[(addr - map->pages_vm_start) >> PAGE_SHIFT];
 }
@@ -525,7 +476,7 @@ static const struct vm_operations_struct gntdev_vmops = {
 
 /* ------------------------------------------------------------------ */
 
-static void unmap_if_in_range(struct grant_map *map,
+static void unmap_if_in_range(struct gntdev_grant_map *map,
 			      unsigned long start, unsigned long end)
 {
 	unsigned long mstart, mend;
@@ -554,7 +505,7 @@ static void mn_invl_range_start(struct mmu_notifier *mn,
 				unsigned long start, unsigned long end)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	mutex_lock(&priv->lock);
 	list_for_each_entry(map, &priv->maps, next) {
@@ -570,7 +521,7 @@ static void mn_release(struct mmu_notifier *mn,
 		       struct mm_struct *mm)
 {
 	struct gntdev_priv *priv = container_of(mn, struct gntdev_priv, mn);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	mutex_lock(&priv->lock);
@@ -651,13 +602,14 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 static int gntdev_release(struct inode *inode, struct file *flip)
 {
 	struct gntdev_priv *priv = flip->private_data;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 
 	pr_debug("priv %p\n", priv);
 
 	mutex_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
-		map = list_entry(priv->maps.next, struct grant_map, next);
+		map = list_entry(priv->maps.next,
+				 struct gntdev_grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
@@ -674,7 +626,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 				       struct ioctl_gntdev_map_grant_ref __user *u)
 {
 	struct ioctl_gntdev_map_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -688,7 +640,7 @@ static long gntdev_ioctl_map_grant_ref(struct gntdev_priv *priv,
 	if (!map)
 		return err;
 
-	if (unlikely(atomic_add_return(op.count, &pages_mapped) > limit)) {
+	if (unlikely(gntdev_account_mapped_pages(op.count))) {
 		pr_debug("can't map: over limit\n");
 		gntdev_put_map(NULL, map);
 		return err;
@@ -715,7 +667,7 @@ static long gntdev_ioctl_unmap_grant_ref(struct gntdev_priv *priv,
 					 struct ioctl_gntdev_unmap_grant_ref __user *u)
 {
 	struct ioctl_gntdev_unmap_grant_ref op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int err = -ENOENT;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -741,7 +693,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 {
 	struct ioctl_gntdev_get_offset_for_vaddr op;
 	struct vm_area_struct *vma;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rv = -EINVAL;
 
 	if (copy_from_user(&op, u, sizeof(op)) != 0)
@@ -772,7 +724,7 @@ static long gntdev_ioctl_get_offset_for_vaddr(struct gntdev_priv *priv,
 static long gntdev_ioctl_notify(struct gntdev_priv *priv, void __user *u)
 {
 	struct ioctl_gntdev_unmap_notify op;
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int rc;
 	int out_flags;
 	unsigned int out_event;
@@ -1070,7 +1022,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 	struct gntdev_priv *priv = flip->private_data;
 	int index = vma->vm_pgoff;
 	int count = vma_pages(vma);
-	struct grant_map *map;
+	struct gntdev_grant_map *map;
 	int i, err = -EINVAL;
 
 	if ((vma->vm_flags & VM_WRITE) && !(vma->vm_flags & VM_SHARED))
@@ -1127,7 +1079,7 @@ static int gntdev_mmap(struct file *flip, struct vm_area_struct *vma)
 		}
 	}
 
-	err = map_grant_pages(map);
+	err = gntdev_map_grant_pages(map);
 	if (err)
 		goto out_put_map;
 
-- 
cgit v1.2.3


From 932d6562179efe8e2460a0343dbe0fcacf288a9e Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:48 +0300
Subject: xen/gntdev: Add initial support for dma-buf UAPI

Add UAPI and IOCTLs for dma-buf grant device driver extension:
the extension allows userspace processes and kernel modules to
use Xen backed dma-buf implementation. With this extension grant
references to the pages of an imported dma-buf can be exported
for other domain use and grant references coming from a foreign
domain can be converted into a local dma-buf for local export.
Implement basic initialization and stubs for Xen DMA buffers'
support.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/Kconfig         |  10 +++
 drivers/xen/Makefile        |   1 +
 drivers/xen/gntdev-common.h |   6 ++
 drivers/xen/gntdev-dmabuf.c | 177 ++++++++++++++++++++++++++++++++++++++++++++
 drivers/xen/gntdev-dmabuf.h |  33 +++++++++
 drivers/xen/gntdev.c        |  31 ++++++++
 include/uapi/xen/gntdev.h   |  91 +++++++++++++++++++++++
 7 files changed, 349 insertions(+)
 create mode 100644 drivers/xen/gntdev-dmabuf.c
 create mode 100644 drivers/xen/gntdev-dmabuf.h

diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 75e5c40f80a5..b459edfacff3 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -152,6 +152,16 @@ config XEN_GNTDEV
 	help
 	  Allows userspace processes to use grants.
 
+config XEN_GNTDEV_DMABUF
+	bool "Add support for dma-buf grant access device driver extension"
+	depends on XEN_GNTDEV && XEN_GRANT_DMA_ALLOC && DMA_SHARED_BUFFER
+	help
+	  Allows userspace processes and kernel modules to use Xen backed
+	  dma-buf implementation. With this extension grant references to
+	  the pages of an imported dma-buf can be exported for other domain
+	  use and grant references coming from a foreign domain can be
+	  converted into a local dma-buf for local export.
+
 config XEN_GRANT_DEV_ALLOC
 	tristate "User-space grant reference allocator driver"
 	depends on XEN
diff --git a/drivers/xen/Makefile b/drivers/xen/Makefile
index 129dd1cc1b83..3e542f60f29f 100644
--- a/drivers/xen/Makefile
+++ b/drivers/xen/Makefile
@@ -41,5 +41,6 @@ obj-$(CONFIG_XEN_PVCALLS_BACKEND)	+= pvcalls-back.o
 obj-$(CONFIG_XEN_PVCALLS_FRONTEND)	+= pvcalls-front.o
 xen-evtchn-y				:= evtchn.o
 xen-gntdev-y				:= gntdev.o
+xen-gntdev-$(CONFIG_XEN_GNTDEV_DMABUF)	+= gntdev-dmabuf.o
 xen-gntalloc-y				:= gntalloc.o
 xen-privcmd-y				:= privcmd.o privcmd-buf.o
diff --git a/drivers/xen/gntdev-common.h b/drivers/xen/gntdev-common.h
index 2346c198f72e..2f8b949c3eeb 100644
--- a/drivers/xen/gntdev-common.h
+++ b/drivers/xen/gntdev-common.h
@@ -16,6 +16,8 @@
 #include <linux/mmu_notifier.h>
 #include <linux/types.h>
 
+struct gntdev_dmabuf_priv;
+
 struct gntdev_priv {
 	/* Maps with visible offsets in the file descriptor. */
 	struct list_head maps;
@@ -33,6 +35,10 @@ struct gntdev_priv {
 	/* Device for which DMA memory is allocated. */
 	struct device *dma_dev;
 #endif
+
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+#endif
 };
 
 struct gntdev_unmap_notify {
diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
new file mode 100644
index 000000000000..af782c0a8a19
--- /dev/null
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+
+#include <xen/xen.h>
+#include <xen/grant_table.h>
+
+#include "gntdev-common.h"
+#include "gntdev-dmabuf.h"
+
+struct gntdev_dmabuf_priv {
+	/* List of exported DMA buffers. */
+	struct list_head exp_list;
+	/* List of wait objects. */
+	struct list_head exp_wait_list;
+	/* This is the lock which protects dma_buf_xxx lists. */
+	struct mutex lock;
+};
+
+/* DMA buffer export support. */
+
+/* Implementation of wait for exported DMA buffer to be released. */
+
+static int dmabuf_exp_wait_released(struct gntdev_dmabuf_priv *priv, int fd,
+				    int wait_to_ms)
+{
+	return -EINVAL;
+}
+
+static int dmabuf_exp_from_refs(struct gntdev_priv *priv, int flags,
+				int count, u32 domid, u32 *refs, u32 *fd)
+{
+	*fd = -1;
+	return -EINVAL;
+}
+
+/* DMA buffer import support. */
+
+static struct gntdev_dmabuf *
+dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
+		   int fd, int count, int domid)
+{
+	return ERR_PTR(-ENOMEM);
+}
+
+static u32 *dmabuf_imp_get_refs(struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	return NULL;
+}
+
+static int dmabuf_imp_release(struct gntdev_dmabuf_priv *priv, u32 fd)
+{
+	return -EINVAL;
+}
+
+/* DMA buffer IOCTL support. */
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_from_refs op;
+	u32 *refs;
+	long ret;
+
+	if (use_ptemod) {
+		pr_debug("Cannot provide dma-buf: use_ptemode %d\n",
+			 use_ptemod);
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(op.count <= 0))
+		return -EINVAL;
+
+	refs = kcalloc(op.count, sizeof(*refs), GFP_KERNEL);
+	if (!refs)
+		return -ENOMEM;
+
+	if (copy_from_user(refs, u->refs, sizeof(*refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out;
+	}
+
+	ret = dmabuf_exp_from_refs(priv, op.flags, op.count,
+				   op.domid, refs, &op.fd);
+	if (ret)
+		goto out;
+
+	if (copy_to_user(u, &op, sizeof(op)) != 0)
+		ret = -EFAULT;
+
+out:
+	kfree(refs);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u)
+{
+	struct ioctl_gntdev_dmabuf_exp_wait_released op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_exp_wait_released(priv->dmabuf_priv, op.fd,
+					op.wait_to_ms);
+}
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_to_refs op;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	long ret;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	if (unlikely(op.count <= 0))
+		return -EINVAL;
+
+	gntdev_dmabuf = dmabuf_imp_to_refs(priv->dmabuf_priv,
+					   priv->dma_dev, op.fd,
+					   op.count, op.domid);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	if (copy_to_user(u->refs, dmabuf_imp_get_refs(gntdev_dmabuf),
+			 sizeof(*u->refs) * op.count) != 0) {
+		ret = -EFAULT;
+		goto out_release;
+	}
+	return 0;
+
+out_release:
+	dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+	return ret;
+}
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u)
+{
+	struct ioctl_gntdev_dmabuf_imp_release op;
+
+	if (copy_from_user(&op, u, sizeof(op)) != 0)
+		return -EFAULT;
+
+	return dmabuf_imp_release(priv->dmabuf_priv, op.fd);
+}
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void)
+{
+	struct gntdev_dmabuf_priv *priv;
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return ERR_PTR(-ENOMEM);
+
+	return priv;
+}
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv)
+{
+	kfree(priv);
+}
diff --git a/drivers/xen/gntdev-dmabuf.h b/drivers/xen/gntdev-dmabuf.h
new file mode 100644
index 000000000000..7220a53d0fc5
--- /dev/null
+++ b/drivers/xen/gntdev-dmabuf.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Xen dma-buf functionality for gntdev.
+ *
+ * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
+ */
+
+#ifndef _GNTDEV_DMABUF_H
+#define _GNTDEV_DMABUF_H
+
+#include <xen/gntdev.h>
+
+struct gntdev_dmabuf_priv;
+struct gntdev_priv;
+
+struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void);
+
+void gntdev_dmabuf_fini(struct gntdev_dmabuf_priv *priv);
+
+long gntdev_ioctl_dmabuf_exp_from_refs(struct gntdev_priv *priv, int use_ptemod,
+				       struct ioctl_gntdev_dmabuf_exp_from_refs __user *u);
+
+long gntdev_ioctl_dmabuf_exp_wait_released(struct gntdev_priv *priv,
+					   struct ioctl_gntdev_dmabuf_exp_wait_released __user *u);
+
+long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_to_refs __user *u);
+
+long gntdev_ioctl_dmabuf_imp_release(struct gntdev_priv *priv,
+				     struct ioctl_gntdev_dmabuf_imp_release __user *u);
+
+#endif
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index e03f50052f3e..c866a62f766d 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -48,6 +48,9 @@
 #include <asm/xen/hypercall.h>
 
 #include "gntdev-common.h"
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+#include "gntdev-dmabuf.h"
+#endif
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Derek G. Murray <Derek.Murray@cl.cam.ac.uk>, "
@@ -566,6 +569,15 @@ static int gntdev_open(struct inode *inode, struct file *flip)
 	INIT_LIST_HEAD(&priv->freeable_maps);
 	mutex_init(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	priv->dmabuf_priv = gntdev_dmabuf_init();
+	if (IS_ERR(priv->dmabuf_priv)) {
+		ret = PTR_ERR(priv->dmabuf_priv);
+		kfree(priv);
+		return ret;
+	}
+#endif
+
 	if (use_ptemod) {
 		priv->mm = get_task_mm(current);
 		if (!priv->mm) {
@@ -616,8 +628,13 @@ static int gntdev_release(struct inode *inode, struct file *flip)
 	WARN_ON(!list_empty(&priv->freeable_maps));
 	mutex_unlock(&priv->lock);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	gntdev_dmabuf_fini(priv->dmabuf_priv);
+#endif
+
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
+
 	kfree(priv);
 	return 0;
 }
@@ -1009,6 +1026,20 @@ static long gntdev_ioctl(struct file *flip,
 	case IOCTL_GNTDEV_GRANT_COPY:
 		return gntdev_ioctl_grant_copy(priv, ptr);
 
+#ifdef CONFIG_XEN_GNTDEV_DMABUF
+	case IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS:
+		return gntdev_ioctl_dmabuf_exp_from_refs(priv, use_ptemod, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED:
+		return gntdev_ioctl_dmabuf_exp_wait_released(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_TO_REFS:
+		return gntdev_ioctl_dmabuf_imp_to_refs(priv, ptr);
+
+	case IOCTL_GNTDEV_DMABUF_IMP_RELEASE:
+		return gntdev_ioctl_dmabuf_imp_release(priv, ptr);
+#endif
+
 	default:
 		pr_debug("priv %p, unknown cmd %x\n", priv, cmd);
 		return -ENOIOCTLCMD;
diff --git a/include/uapi/xen/gntdev.h b/include/uapi/xen/gntdev.h
index 4b9d498a31d4..fe4423e518c6 100644
--- a/include/uapi/xen/gntdev.h
+++ b/include/uapi/xen/gntdev.h
@@ -5,6 +5,7 @@
  * Interface to /dev/xen/gntdev.
  * 
  * Copyright (c) 2007, D G Murray
+ * Copyright (c) 2018, Oleksandr Andrushchenko, EPAM Systems Inc.
  * 
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License version 2
@@ -215,4 +216,94 @@ struct ioctl_gntdev_grant_copy {
  */
 #define GNTDEV_DMA_FLAG_COHERENT	(1 << 1)
 
+/*
+ * Create a dma-buf [1] from grant references @refs of count @count provided
+ * by the foreign domain @domid with flags @flags.
+ *
+ * By default dma-buf is backed by system memory pages, but by providing
+ * one of the GNTDEV_DMA_FLAG_XXX flags it can also be created as
+ * a DMA write-combine or coherent buffer, e.g. allocated with dma_alloc_wc/
+ * dma_alloc_coherent.
+ *
+ * Returns 0 if dma-buf was successfully created and the corresponding
+ * dma-buf's file descriptor is returned in @fd.
+ *
+ * [1] Documentation/driver-api/dma-buf.rst
+ */
+
+#define IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS \
+	_IOC(_IOC_NONE, 'G', 9, \
+	     sizeof(struct ioctl_gntdev_dmabuf_exp_from_refs))
+struct ioctl_gntdev_dmabuf_exp_from_refs {
+	/* IN parameters. */
+	/* Specific options for this dma-buf: see GNTDEV_DMA_FLAG_XXX. */
+	__u32 flags;
+	/* Number of grant references in @refs array. */
+	__u32 count;
+	/* OUT parameters. */
+	/* File descriptor of the dma-buf. */
+	__u32 fd;
+	/* The domain ID of the grant references to be mapped. */
+	__u32 domid;
+	/* Variable IN parameter. */
+	/* Array of grant references of size @count. */
+	__u32 refs[1];
+};
+
+/*
+ * This will block until the dma-buf with the file descriptor @fd is
+ * released. This is only valid for buffers created with
+ * IOCTL_GNTDEV_DMABUF_EXP_FROM_REFS.
+ *
+ * If within @wait_to_ms milliseconds the buffer is not released
+ * then -ETIMEDOUT error is returned.
+ * If the buffer with the file descriptor @fd does not exist or has already
+ * been released, then -ENOENT is returned. For valid file descriptors
+ * this must not be treated as error.
+ */
+#define IOCTL_GNTDEV_DMABUF_EXP_WAIT_RELEASED \
+	_IOC(_IOC_NONE, 'G', 10, \
+	     sizeof(struct ioctl_gntdev_dmabuf_exp_wait_released))
+struct ioctl_gntdev_dmabuf_exp_wait_released {
+	/* IN parameters */
+	__u32 fd;
+	__u32 wait_to_ms;
+};
+
+/*
+ * Import a dma-buf with file descriptor @fd and export granted references
+ * to the pages of that dma-buf into array @refs of size @count.
+ */
+#define IOCTL_GNTDEV_DMABUF_IMP_TO_REFS \
+	_IOC(_IOC_NONE, 'G', 11, \
+	     sizeof(struct ioctl_gntdev_dmabuf_imp_to_refs))
+struct ioctl_gntdev_dmabuf_imp_to_refs {
+	/* IN parameters. */
+	/* File descriptor of the dma-buf. */
+	__u32 fd;
+	/* Number of grant references in @refs array. */
+	__u32 count;
+	/* The domain ID for which references to be granted. */
+	__u32 domid;
+	/* Reserved - must be zero. */
+	__u32 reserved;
+	/* OUT parameters. */
+	/* Array of grant references of size @count. */
+	__u32 refs[1];
+};
+
+/*
+ * This will close all references to the imported buffer with file descriptor
+ * @fd, so it can be released by the owner. This is only valid for buffers
+ * created with IOCTL_GNTDEV_DMABUF_IMP_TO_REFS.
+ */
+#define IOCTL_GNTDEV_DMABUF_IMP_RELEASE \
+	_IOC(_IOC_NONE, 'G', 12, \
+	     sizeof(struct ioctl_gntdev_dmabuf_imp_release))
+struct ioctl_gntdev_dmabuf_imp_release {
+	/* IN parameters */
+	__u32 fd;
+	__u32 reserved;
+};
+
 #endif /* __LINUX_PUBLIC_GNTDEV_H__ */
-- 
cgit v1.2.3


From a240d6e42e28c34fdc34b3a98ca838a31c939901 Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:49 +0300
Subject: xen/gntdev: Implement dma-buf export functionality

1. Create a dma-buf from grant references provided by the foreign
   domain. By default dma-buf is backed by system memory pages, but
   by providing GNTDEV_DMA_FLAG_XXX flags it can also be created
   as a DMA write-combine/coherent buffer, e.g. allocated with
   corresponding dma_alloc_xxx API.
   Export the resulting buffer as a new dma-buf.

2. Implement waiting for the dma-buf to be released: block until the
   dma-buf with the file descriptor provided is released.
   If within the time-out provided the buffer is not released then
   -ETIMEDOUT error is returned. If the buffer with the file descriptor
   does not exist or has already been released, then -ENOENT is
   returned. For valid file descriptors this must not be treated as
   error.

3. Make gntdev's common code and structures available to dma-buf.

[boris: added 'args.fd = -1' to dmabuf_exp_from_refs() to avoid an
 unnecessary warning about it not being initialized on i386 with gcc 8.1.1]

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/gntdev-dmabuf.c | 456 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 453 insertions(+), 3 deletions(-)

diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index af782c0a8a19..4ca361fdf355 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -3,11 +3,14 @@
 /*
  * Xen dma-buf functionality for gntdev.
  *
+ * DMA buffer implementation is based on drivers/gpu/drm/drm_prime.c.
+ *
  * Copyright (c) 2018 Oleksandr Andrushchenko, EPAM Systems Inc.
  */
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/dma-buf.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
@@ -18,6 +21,39 @@
 #include "gntdev-common.h"
 #include "gntdev-dmabuf.h"
 
+struct gntdev_dmabuf {
+	struct gntdev_dmabuf_priv *priv;
+	struct dma_buf *dmabuf;
+	struct list_head next;
+	int fd;
+
+	union {
+		struct {
+			/* Exported buffers are reference counted. */
+			struct kref refcount;
+
+			struct gntdev_priv *priv;
+			struct gntdev_grant_map *map;
+		} exp;
+	} u;
+
+	/* Number of pages this buffer has. */
+	int nr_pages;
+	/* Pages of this buffer. */
+	struct page **pages;
+};
+
+struct gntdev_dmabuf_wait_obj {
+	struct list_head next;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct completion completion;
+};
+
+struct gntdev_dmabuf_attachment {
+	struct sg_table *sgt;
+	enum dma_data_direction dir;
+};
+
 struct gntdev_dmabuf_priv {
 	/* List of exported DMA buffers. */
 	struct list_head exp_list;
@@ -31,17 +67,427 @@ struct gntdev_dmabuf_priv {
 
 /* Implementation of wait for exported DMA buffer to be released. */
 
+static void dmabuf_exp_release(struct kref *kref);
+
+static struct gntdev_dmabuf_wait_obj *
+dmabuf_exp_wait_obj_new(struct gntdev_dmabuf_priv *priv,
+			struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+
+	init_completion(&obj->completion);
+	obj->gntdev_dmabuf = gntdev_dmabuf;
+
+	mutex_lock(&priv->lock);
+	list_add(&obj->next, &priv->exp_wait_list);
+	/* Put our reference and wait for gntdev_dmabuf's release to fire. */
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+	return obj;
+}
+
+static void dmabuf_exp_wait_obj_free(struct gntdev_dmabuf_priv *priv,
+				     struct gntdev_dmabuf_wait_obj *obj)
+{
+	mutex_lock(&priv->lock);
+	list_del(&obj->next);
+	mutex_unlock(&priv->lock);
+	kfree(obj);
+}
+
+static int dmabuf_exp_wait_obj_wait(struct gntdev_dmabuf_wait_obj *obj,
+				    u32 wait_to_ms)
+{
+	if (wait_for_completion_timeout(&obj->completion,
+			msecs_to_jiffies(wait_to_ms)) <= 0)
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void dmabuf_exp_wait_obj_signal(struct gntdev_dmabuf_priv *priv,
+				       struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	struct gntdev_dmabuf_wait_obj *obj;
+
+	list_for_each_entry(obj, &priv->exp_wait_list, next)
+		if (obj->gntdev_dmabuf == gntdev_dmabuf) {
+			pr_debug("Found gntdev_dmabuf in the wait list, wake\n");
+			complete_all(&obj->completion);
+			break;
+		}
+}
+
+static struct gntdev_dmabuf *
+dmabuf_exp_wait_obj_get_dmabuf(struct gntdev_dmabuf_priv *priv, int fd)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry(gntdev_dmabuf, &priv->exp_list, next)
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the wait list\n");
+			kref_get(&gntdev_dmabuf->u.exp.refcount);
+			ret = gntdev_dmabuf;
+			break;
+		}
+	mutex_unlock(&priv->lock);
+	return ret;
+}
+
 static int dmabuf_exp_wait_released(struct gntdev_dmabuf_priv *priv, int fd,
 				    int wait_to_ms)
 {
-	return -EINVAL;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct gntdev_dmabuf_wait_obj *obj;
+	int ret;
+
+	pr_debug("Will wait for dma-buf with fd %d\n", fd);
+	/*
+	 * Try to find the DMA buffer: if not found means that
+	 * either the buffer has already been released or file descriptor
+	 * provided is wrong.
+	 */
+	gntdev_dmabuf = dmabuf_exp_wait_obj_get_dmabuf(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	/*
+	 * gntdev_dmabuf still exists and is reference count locked by us now,
+	 * so prepare to wait: allocate wait object and add it to the wait list,
+	 * so we can find it on release.
+	 */
+	obj = dmabuf_exp_wait_obj_new(priv, gntdev_dmabuf);
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	ret = dmabuf_exp_wait_obj_wait(obj, wait_to_ms);
+	dmabuf_exp_wait_obj_free(priv, obj);
+	return ret;
+}
+
+/* DMA buffer export support. */
+
+static struct sg_table *
+dmabuf_pages_to_sgt(struct page **pages, unsigned int nr_pages)
+{
+	struct sg_table *sgt;
+	int ret;
+
+	sgt = kmalloc(sizeof(*sgt), GFP_KERNEL);
+	if (!sgt) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	ret = sg_alloc_table_from_pages(sgt, pages, nr_pages, 0,
+					nr_pages << PAGE_SHIFT,
+					GFP_KERNEL);
+	if (ret)
+		goto out;
+
+	return sgt;
+
+out:
+	kfree(sgt);
+	return ERR_PTR(ret);
+}
+
+static int dmabuf_exp_ops_attach(struct dma_buf *dma_buf,
+				 struct device *target_dev,
+				 struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach;
+
+	gntdev_dmabuf_attach = kzalloc(sizeof(*gntdev_dmabuf_attach),
+				       GFP_KERNEL);
+	if (!gntdev_dmabuf_attach)
+		return -ENOMEM;
+
+	gntdev_dmabuf_attach->dir = DMA_NONE;
+	attach->priv = gntdev_dmabuf_attach;
+	return 0;
+}
+
+static void dmabuf_exp_ops_detach(struct dma_buf *dma_buf,
+				  struct dma_buf_attachment *attach)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+
+	if (gntdev_dmabuf_attach) {
+		struct sg_table *sgt = gntdev_dmabuf_attach->sgt;
+
+		if (sgt) {
+			if (gntdev_dmabuf_attach->dir != DMA_NONE)
+				dma_unmap_sg_attrs(attach->dev, sgt->sgl,
+						   sgt->nents,
+						   gntdev_dmabuf_attach->dir,
+						   DMA_ATTR_SKIP_CPU_SYNC);
+			sg_free_table(sgt);
+		}
+
+		kfree(sgt);
+		kfree(gntdev_dmabuf_attach);
+		attach->priv = NULL;
+	}
+}
+
+static struct sg_table *
+dmabuf_exp_ops_map_dma_buf(struct dma_buf_attachment *attach,
+			   enum dma_data_direction dir)
+{
+	struct gntdev_dmabuf_attachment *gntdev_dmabuf_attach = attach->priv;
+	struct gntdev_dmabuf *gntdev_dmabuf = attach->dmabuf->priv;
+	struct sg_table *sgt;
+
+	pr_debug("Mapping %d pages for dev %p\n", gntdev_dmabuf->nr_pages,
+		 attach->dev);
+
+	if (dir == DMA_NONE || !gntdev_dmabuf_attach)
+		return ERR_PTR(-EINVAL);
+
+	/* Return the cached mapping when possible. */
+	if (gntdev_dmabuf_attach->dir == dir)
+		return gntdev_dmabuf_attach->sgt;
+
+	/*
+	 * Two mappings with different directions for the same attachment are
+	 * not allowed.
+	 */
+	if (gntdev_dmabuf_attach->dir != DMA_NONE)
+		return ERR_PTR(-EBUSY);
+
+	sgt = dmabuf_pages_to_sgt(gntdev_dmabuf->pages,
+				  gntdev_dmabuf->nr_pages);
+	if (!IS_ERR(sgt)) {
+		if (!dma_map_sg_attrs(attach->dev, sgt->sgl, sgt->nents, dir,
+				      DMA_ATTR_SKIP_CPU_SYNC)) {
+			sg_free_table(sgt);
+			kfree(sgt);
+			sgt = ERR_PTR(-ENOMEM);
+		} else {
+			gntdev_dmabuf_attach->sgt = sgt;
+			gntdev_dmabuf_attach->dir = dir;
+		}
+	}
+	if (IS_ERR(sgt))
+		pr_debug("Failed to map sg table for dev %p\n", attach->dev);
+	return sgt;
+}
+
+static void dmabuf_exp_ops_unmap_dma_buf(struct dma_buf_attachment *attach,
+					 struct sg_table *sgt,
+					 enum dma_data_direction dir)
+{
+	/* Not implemented. The unmap is done at dmabuf_exp_ops_detach(). */
+}
+
+static void dmabuf_exp_release(struct kref *kref)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf =
+		container_of(kref, struct gntdev_dmabuf, u.exp.refcount);
+
+	dmabuf_exp_wait_obj_signal(gntdev_dmabuf->priv, gntdev_dmabuf);
+	list_del(&gntdev_dmabuf->next);
+	kfree(gntdev_dmabuf);
+}
+
+static void dmabuf_exp_remove_map(struct gntdev_priv *priv,
+				  struct gntdev_grant_map *map)
+{
+	mutex_lock(&priv->lock);
+	list_del(&map->next);
+	gntdev_put_map(NULL /* already removed */, map);
+	mutex_unlock(&priv->lock);
+}
+
+static void dmabuf_exp_ops_release(struct dma_buf *dma_buf)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf = dma_buf->priv;
+	struct gntdev_dmabuf_priv *priv = gntdev_dmabuf->priv;
+
+	dmabuf_exp_remove_map(gntdev_dmabuf->u.exp.priv,
+			      gntdev_dmabuf->u.exp.map);
+	mutex_lock(&priv->lock);
+	kref_put(&gntdev_dmabuf->u.exp.refcount, dmabuf_exp_release);
+	mutex_unlock(&priv->lock);
+}
+
+static void *dmabuf_exp_ops_kmap(struct dma_buf *dma_buf,
+				 unsigned long page_num)
+{
+	/* Not implemented. */
+	return NULL;
+}
+
+static void dmabuf_exp_ops_kunmap(struct dma_buf *dma_buf,
+				  unsigned long page_num, void *addr)
+{
+	/* Not implemented. */
+}
+
+static int dmabuf_exp_ops_mmap(struct dma_buf *dma_buf,
+			       struct vm_area_struct *vma)
+{
+	/* Not implemented. */
+	return 0;
+}
+
+static const struct dma_buf_ops dmabuf_exp_ops =  {
+	.attach = dmabuf_exp_ops_attach,
+	.detach = dmabuf_exp_ops_detach,
+	.map_dma_buf = dmabuf_exp_ops_map_dma_buf,
+	.unmap_dma_buf = dmabuf_exp_ops_unmap_dma_buf,
+	.release = dmabuf_exp_ops_release,
+	.map = dmabuf_exp_ops_kmap,
+	.unmap = dmabuf_exp_ops_kunmap,
+	.mmap = dmabuf_exp_ops_mmap,
+};
+
+struct gntdev_dmabuf_export_args {
+	struct gntdev_priv *priv;
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_priv *dmabuf_priv;
+	struct device *dev;
+	int count;
+	struct page **pages;
+	u32 fd;
+};
+
+static int dmabuf_exp_from_pages(struct gntdev_dmabuf_export_args *args)
+{
+	DEFINE_DMA_BUF_EXPORT_INFO(exp_info);
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	int ret;
+
+	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
+	if (!gntdev_dmabuf)
+		return -ENOMEM;
+
+	kref_init(&gntdev_dmabuf->u.exp.refcount);
+
+	gntdev_dmabuf->priv = args->dmabuf_priv;
+	gntdev_dmabuf->nr_pages = args->count;
+	gntdev_dmabuf->pages = args->pages;
+	gntdev_dmabuf->u.exp.priv = args->priv;
+	gntdev_dmabuf->u.exp.map = args->map;
+
+	exp_info.exp_name = KBUILD_MODNAME;
+	if (args->dev->driver && args->dev->driver->owner)
+		exp_info.owner = args->dev->driver->owner;
+	else
+		exp_info.owner = THIS_MODULE;
+	exp_info.ops = &dmabuf_exp_ops;
+	exp_info.size = args->count << PAGE_SHIFT;
+	exp_info.flags = O_RDWR;
+	exp_info.priv = gntdev_dmabuf;
+
+	gntdev_dmabuf->dmabuf = dma_buf_export(&exp_info);
+	if (IS_ERR(gntdev_dmabuf->dmabuf)) {
+		ret = PTR_ERR(gntdev_dmabuf->dmabuf);
+		gntdev_dmabuf->dmabuf = NULL;
+		goto fail;
+	}
+
+	ret = dma_buf_fd(gntdev_dmabuf->dmabuf, O_CLOEXEC);
+	if (ret < 0)
+		goto fail;
+
+	gntdev_dmabuf->fd = ret;
+	args->fd = ret;
+
+	pr_debug("Exporting DMA buffer with fd %d\n", ret);
+
+	mutex_lock(&args->dmabuf_priv->lock);
+	list_add(&gntdev_dmabuf->next, &args->dmabuf_priv->exp_list);
+	mutex_unlock(&args->dmabuf_priv->lock);
+	return 0;
+
+fail:
+	if (gntdev_dmabuf->dmabuf)
+		dma_buf_put(gntdev_dmabuf->dmabuf);
+	kfree(gntdev_dmabuf);
+	return ret;
+}
+
+static struct gntdev_grant_map *
+dmabuf_exp_alloc_backing_storage(struct gntdev_priv *priv, int dmabuf_flags,
+				 int count)
+{
+	struct gntdev_grant_map *map;
+
+	if (unlikely(count <= 0))
+		return ERR_PTR(-EINVAL);
+
+	if ((dmabuf_flags & GNTDEV_DMA_FLAG_WC) &&
+	    (dmabuf_flags & GNTDEV_DMA_FLAG_COHERENT)) {
+		pr_debug("Wrong dma-buf flags: 0x%x\n", dmabuf_flags);
+		return ERR_PTR(-EINVAL);
+	}
+
+	map = gntdev_alloc_map(priv, count, dmabuf_flags);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	if (unlikely(gntdev_account_mapped_pages(count))) {
+		pr_debug("can't map %d pages: over limit\n", count);
+		gntdev_put_map(NULL, map);
+		return ERR_PTR(-ENOMEM);
+	}
+	return map;
 }
 
 static int dmabuf_exp_from_refs(struct gntdev_priv *priv, int flags,
 				int count, u32 domid, u32 *refs, u32 *fd)
 {
-	*fd = -1;
-	return -EINVAL;
+	struct gntdev_grant_map *map;
+	struct gntdev_dmabuf_export_args args;
+	int i, ret;
+
+	map = dmabuf_exp_alloc_backing_storage(priv, flags, count);
+	if (IS_ERR(map))
+		return PTR_ERR(map);
+
+	for (i = 0; i < count; i++) {
+		map->grants[i].domid = domid;
+		map->grants[i].ref = refs[i];
+	}
+
+	mutex_lock(&priv->lock);
+	gntdev_add_map(priv, map);
+	mutex_unlock(&priv->lock);
+
+	map->flags |= GNTMAP_host_map;
+#if defined(CONFIG_X86)
+	map->flags |= GNTMAP_device_map;
+#endif
+
+	ret = gntdev_map_grant_pages(map);
+	if (ret < 0)
+		goto out;
+
+	args.priv = priv;
+	args.map = map;
+	args.dev = priv->dma_dev;
+	args.dmabuf_priv = priv->dmabuf_priv;
+	args.count = map->count;
+	args.pages = map->pages;
+	args.fd = -1; /* Shut up unnecessary gcc warning for i386 */
+
+	ret = dmabuf_exp_from_pages(&args);
+	if (ret < 0)
+		goto out;
+
+	*fd = args.fd;
+	return 0;
+
+out:
+	dmabuf_exp_remove_map(priv, map);
+	return ret;
 }
 
 /* DMA buffer import support. */
@@ -168,6 +614,10 @@ struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void)
 	if (!priv)
 		return ERR_PTR(-ENOMEM);
 
+	mutex_init(&priv->lock);
+	INIT_LIST_HEAD(&priv->exp_list);
+	INIT_LIST_HEAD(&priv->exp_wait_list);
+
 	return priv;
 }
 
-- 
cgit v1.2.3


From bf8dc55b135873d8bc58bb8fbc91c52f3a902eea Mon Sep 17 00:00:00 2001
From: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Date: Fri, 20 Jul 2018 12:01:50 +0300
Subject: xen/gntdev: Implement dma-buf import functionality

1. Import a dma-buf with the file descriptor provided and export
   granted references to the pages of that dma-buf into the array
   of grant references.

2. Add API to close all references to an imported buffer, so it can be
   released by the owner. This is only valid for buffers created with
   IOCTL_GNTDEV_DMABUF_IMP_TO_REFS.

Signed-off-by: Oleksandr Andrushchenko <oleksandr_andrushchenko@epam.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/gntdev-dmabuf.c | 239 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 234 insertions(+), 5 deletions(-)

diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index 4ca361fdf355..faaa4d3970ea 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -21,6 +21,15 @@
 #include "gntdev-common.h"
 #include "gntdev-dmabuf.h"
 
+#ifndef GRANT_INVALID_REF
+/*
+ * Note on usage of grant reference 0 as invalid grant reference:
+ * grant reference 0 is valid, but never exposed to a driver,
+ * because of the fact it is already in use/reserved by the PV console.
+ */
+#define GRANT_INVALID_REF	0
+#endif
+
 struct gntdev_dmabuf {
 	struct gntdev_dmabuf_priv *priv;
 	struct dma_buf *dmabuf;
@@ -35,6 +44,14 @@ struct gntdev_dmabuf {
 			struct gntdev_priv *priv;
 			struct gntdev_grant_map *map;
 		} exp;
+		struct {
+			/* Granted references of the imported buffer. */
+			grant_ref_t *refs;
+			/* Scatter-gather table of the imported buffer. */
+			struct sg_table *sgt;
+			/* dma-buf attachment of the imported buffer. */
+			struct dma_buf_attachment *attach;
+		} imp;
 	} u;
 
 	/* Number of pages this buffer has. */
@@ -59,6 +76,8 @@ struct gntdev_dmabuf_priv {
 	struct list_head exp_list;
 	/* List of wait objects. */
 	struct list_head exp_wait_list;
+	/* List of imported DMA buffers. */
+	struct list_head imp_list;
 	/* This is the lock which protects dma_buf_xxx lists. */
 	struct mutex lock;
 };
@@ -492,21 +511,230 @@ out:
 
 /* DMA buffer import support. */
 
+static int
+dmabuf_imp_grant_foreign_access(struct page **pages, u32 *refs,
+				int count, int domid)
+{
+	grant_ref_t priv_gref_head;
+	int i, ret;
+
+	ret = gnttab_alloc_grant_references(count, &priv_gref_head);
+	if (ret < 0) {
+		pr_debug("Cannot allocate grant references, ret %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < count; i++) {
+		int cur_ref;
+
+		cur_ref = gnttab_claim_grant_reference(&priv_gref_head);
+		if (cur_ref < 0) {
+			ret = cur_ref;
+			pr_debug("Cannot claim grant reference, ret %d\n", ret);
+			goto out;
+		}
+
+		gnttab_grant_foreign_access_ref(cur_ref, domid,
+						xen_page_to_gfn(pages[i]), 0);
+		refs[i] = cur_ref;
+	}
+
+	return 0;
+
+out:
+	gnttab_free_grant_references(priv_gref_head);
+	return ret;
+}
+
+static void dmabuf_imp_end_foreign_access(u32 *refs, int count)
+{
+	int i;
+
+	for (i = 0; i < count; i++)
+		if (refs[i] != GRANT_INVALID_REF)
+			gnttab_end_foreign_access(refs[i], 0, 0UL);
+}
+
+static void dmabuf_imp_free_storage(struct gntdev_dmabuf *gntdev_dmabuf)
+{
+	kfree(gntdev_dmabuf->pages);
+	kfree(gntdev_dmabuf->u.imp.refs);
+	kfree(gntdev_dmabuf);
+}
+
+static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
+{
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	int i;
+
+	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
+	if (!gntdev_dmabuf)
+		goto fail;
+
+	gntdev_dmabuf->u.imp.refs = kcalloc(count,
+					    sizeof(gntdev_dmabuf->u.imp.refs[0]),
+					    GFP_KERNEL);
+	if (!gntdev_dmabuf->u.imp.refs)
+		goto fail;
+
+	gntdev_dmabuf->pages = kcalloc(count,
+				       sizeof(gntdev_dmabuf->pages[0]),
+				       GFP_KERNEL);
+	if (!gntdev_dmabuf->pages)
+		goto fail;
+
+	gntdev_dmabuf->nr_pages = count;
+
+	for (i = 0; i < count; i++)
+		gntdev_dmabuf->u.imp.refs[i] = GRANT_INVALID_REF;
+
+	return gntdev_dmabuf;
+
+fail:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+	return ERR_PTR(-ENOMEM);
+}
+
 static struct gntdev_dmabuf *
 dmabuf_imp_to_refs(struct gntdev_dmabuf_priv *priv, struct device *dev,
 		   int fd, int count, int domid)
 {
-	return ERR_PTR(-ENOMEM);
+	struct gntdev_dmabuf *gntdev_dmabuf, *ret;
+	struct dma_buf *dma_buf;
+	struct dma_buf_attachment *attach;
+	struct sg_table *sgt;
+	struct sg_page_iter sg_iter;
+	int i;
+
+	dma_buf = dma_buf_get(fd);
+	if (IS_ERR(dma_buf))
+		return ERR_CAST(dma_buf);
+
+	gntdev_dmabuf = dmabuf_imp_alloc_storage(count);
+	if (IS_ERR(gntdev_dmabuf)) {
+		ret = gntdev_dmabuf;
+		goto fail_put;
+	}
+
+	gntdev_dmabuf->priv = priv;
+	gntdev_dmabuf->fd = fd;
+
+	attach = dma_buf_attach(dma_buf, dev);
+	if (IS_ERR(attach)) {
+		ret = ERR_CAST(attach);
+		goto fail_free_obj;
+	}
+
+	gntdev_dmabuf->u.imp.attach = attach;
+
+	sgt = dma_buf_map_attachment(attach, DMA_BIDIRECTIONAL);
+	if (IS_ERR(sgt)) {
+		ret = ERR_CAST(sgt);
+		goto fail_detach;
+	}
+
+	/* Check number of pages that imported buffer has. */
+	if (attach->dmabuf->size != gntdev_dmabuf->nr_pages << PAGE_SHIFT) {
+		ret = ERR_PTR(-EINVAL);
+		pr_debug("DMA buffer has %zu pages, user-space expects %d\n",
+			 attach->dmabuf->size, gntdev_dmabuf->nr_pages);
+		goto fail_unmap;
+	}
+
+	gntdev_dmabuf->u.imp.sgt = sgt;
+
+	/* Now convert sgt to array of pages and check for page validity. */
+	i = 0;
+	for_each_sg_page(sgt->sgl, &sg_iter, sgt->nents, 0) {
+		struct page *page = sg_page_iter_page(&sg_iter);
+		/*
+		 * Check if page is valid: this can happen if we are given
+		 * a page from VRAM or other resources which are not backed
+		 * by a struct page.
+		 */
+		if (!pfn_valid(page_to_pfn(page))) {
+			ret = ERR_PTR(-EINVAL);
+			goto fail_unmap;
+		}
+
+		gntdev_dmabuf->pages[i++] = page;
+	}
+
+	ret = ERR_PTR(dmabuf_imp_grant_foreign_access(gntdev_dmabuf->pages,
+						      gntdev_dmabuf->u.imp.refs,
+						      count, domid));
+	if (IS_ERR(ret))
+		goto fail_end_access;
+
+	pr_debug("Imported DMA buffer with fd %d\n", fd);
+
+	mutex_lock(&priv->lock);
+	list_add(&gntdev_dmabuf->next, &priv->imp_list);
+	mutex_unlock(&priv->lock);
+
+	return gntdev_dmabuf;
+
+fail_end_access:
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs, count);
+fail_unmap:
+	dma_buf_unmap_attachment(attach, sgt, DMA_BIDIRECTIONAL);
+fail_detach:
+	dma_buf_detach(dma_buf, attach);
+fail_free_obj:
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_put:
+	dma_buf_put(dma_buf);
+	return ret;
 }
 
-static u32 *dmabuf_imp_get_refs(struct gntdev_dmabuf *gntdev_dmabuf)
+/*
+ * Find the hyper dma-buf by its file descriptor and remove
+ * it from the buffer's list.
+ */
+static struct gntdev_dmabuf *
+dmabuf_imp_find_unlink(struct gntdev_dmabuf_priv *priv, int fd)
 {
-	return NULL;
+	struct gntdev_dmabuf *q, *gntdev_dmabuf, *ret = ERR_PTR(-ENOENT);
+
+	mutex_lock(&priv->lock);
+	list_for_each_entry_safe(gntdev_dmabuf, q, &priv->imp_list, next) {
+		if (gntdev_dmabuf->fd == fd) {
+			pr_debug("Found gntdev_dmabuf in the import list\n");
+			ret = gntdev_dmabuf;
+			list_del(&gntdev_dmabuf->next);
+			break;
+		}
+	}
+	mutex_unlock(&priv->lock);
+	return ret;
 }
 
 static int dmabuf_imp_release(struct gntdev_dmabuf_priv *priv, u32 fd)
 {
-	return -EINVAL;
+	struct gntdev_dmabuf *gntdev_dmabuf;
+	struct dma_buf_attachment *attach;
+	struct dma_buf *dma_buf;
+
+	gntdev_dmabuf = dmabuf_imp_find_unlink(priv, fd);
+	if (IS_ERR(gntdev_dmabuf))
+		return PTR_ERR(gntdev_dmabuf);
+
+	pr_debug("Releasing DMA buffer with fd %d\n", fd);
+
+	dmabuf_imp_end_foreign_access(gntdev_dmabuf->u.imp.refs,
+				      gntdev_dmabuf->nr_pages);
+
+	attach = gntdev_dmabuf->u.imp.attach;
+
+	if (gntdev_dmabuf->u.imp.sgt)
+		dma_buf_unmap_attachment(attach, gntdev_dmabuf->u.imp.sgt,
+					 DMA_BIDIRECTIONAL);
+	dma_buf = attach->dmabuf;
+	dma_buf_detach(attach->dmabuf, attach);
+	dma_buf_put(dma_buf);
+
+	dmabuf_imp_free_storage(gntdev_dmabuf);
+	return 0;
 }
 
 /* DMA buffer IOCTL support. */
@@ -583,7 +811,7 @@ long gntdev_ioctl_dmabuf_imp_to_refs(struct gntdev_priv *priv,
 	if (IS_ERR(gntdev_dmabuf))
 		return PTR_ERR(gntdev_dmabuf);
 
-	if (copy_to_user(u->refs, dmabuf_imp_get_refs(gntdev_dmabuf),
+	if (copy_to_user(u->refs, gntdev_dmabuf->u.imp.refs,
 			 sizeof(*u->refs) * op.count) != 0) {
 		ret = -EFAULT;
 		goto out_release;
@@ -617,6 +845,7 @@ struct gntdev_dmabuf_priv *gntdev_dmabuf_init(void)
 	mutex_init(&priv->lock);
 	INIT_LIST_HEAD(&priv->exp_list);
 	INIT_LIST_HEAD(&priv->exp_wait_list);
+	INIT_LIST_HEAD(&priv->imp_list);
 
 	return priv;
 }
-- 
cgit v1.2.3


From 47b428d14f06dbeab23dd5c7e424e15283841765 Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Thu, 19 Jul 2018 17:39:57 -0400
Subject: xen/spinlock: Don't use pvqspinlock if only 1 vCPU

On a VM with only 1 vCPU, the locking fast paths will always be
successful. In this case, there is no need to use the the PV qspinlock
code which has higher overhead on the unlock side than the native
qspinlock code.

The xen_pvspin veriable is also turned off in this 1 vCPU case to
eliminate unneeded pvqspinlock initialization in xen_init_lock_cpu()
which is run after xen_init_spinlocks().

Signed-off-by: Waiman Long <longman@redhat.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/xen/spinlock.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index cd97a62394e7..973f10e05211 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -130,6 +130,10 @@ PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
 void __init xen_init_spinlocks(void)
 {
 
+	/*  Don't need to use pvqspinlock code if there is only 1 vCPU. */
+	if (num_possible_cpus() == 1)
+		xen_pvspin = false;
+
 	if (!xen_pvspin) {
 		printk(KERN_DEBUG "xen: PV spinlocks disabled\n");
 		return;
-- 
cgit v1.2.3


From ff7b91262b3ad31dfe1461dace0314a773b0fa55 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 27 Jul 2018 09:53:12 +0800
Subject: net: hns: make hns_dsaf_roce_reset non static

hns_dsaf_roce_reset is exported and used in hns_roce_hw_v1.c
In commit 336a443bd9dd ("net: hns: Make many functions static") I make
it static wrongly.

drivers/infiniband/hw/hns/hns_roce_hw_v1.o: In function `hns_roce_v1_reset':
hns_roce_hw_v1.c:(.text+0x37ac): undefined reference to `hns_dsaf_roce_reset'
hns_roce_hw_v1.c:(.text+0x37cc): undefined reference to `hns_dsaf_roce_reset'

Fixes: 336a443bd9dd ("net: hns: Make many functions static")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 7afc67510569..619e6ce465c2 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -2836,7 +2836,7 @@ module_platform_driver(g_dsaf_driver);
  * @enable: false - request reset , true - drop reset
  * retuen 0 - success , negative -fail
  */
-static int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
+int hns_dsaf_roce_reset(struct fwnode_handle *dsaf_fwnode, bool dereset)
 {
 	struct dsaf_device *dsaf_dev;
 	struct platform_device *pdev;
-- 
cgit v1.2.3


From 8c957d66d2edb3293ff6a45d660bdaec45f7a5d0 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 10:39:06 +0800
Subject: isdn: mISDN: hfcpci: Replace GFP_ATOMIC with GFP_KERNEL in
 hfc_probe()

hfc_probe() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/mISDN/hfcpci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/isdn/hardware/mISDN/hfcpci.c b/drivers/isdn/hardware/mISDN/hfcpci.c
index 72a271b98873..ebb3fa2e1d00 100644
--- a/drivers/isdn/hardware/mISDN/hfcpci.c
+++ b/drivers/isdn/hardware/mISDN/hfcpci.c
@@ -2220,7 +2220,7 @@ hfc_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	struct hfc_pci	*card;
 	struct _hfc_map	*m = (struct _hfc_map *)ent->driver_data;
 
-	card = kzalloc(sizeof(struct hfc_pci), GFP_ATOMIC);
+	card = kzalloc(sizeof(struct hfc_pci), GFP_KERNEL);
 	if (!card) {
 		printk(KERN_ERR "No kmem for HFC card\n");
 		return err;
-- 
cgit v1.2.3


From 9d8009dee92cc97f866403da1b306e6e29fc12cc Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 10:41:09 +0800
Subject: isdn: mISDN: netjet: Replace GFP_ATOMIC with GFP_KERNEL in nj_probe()

nj_probe() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hardware/mISDN/netjet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/isdn/hardware/mISDN/netjet.c b/drivers/isdn/hardware/mISDN/netjet.c
index 89d9ba8ed535..2b317cb63d06 100644
--- a/drivers/isdn/hardware/mISDN/netjet.c
+++ b/drivers/isdn/hardware/mISDN/netjet.c
@@ -1084,7 +1084,7 @@ nj_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		return -ENODEV;
 	}
 
-	card = kzalloc(sizeof(struct tiger_hw), GFP_ATOMIC);
+	card = kzalloc(sizeof(struct tiger_hw), GFP_KERNEL);
 	if (!card) {
 		pr_info("No kmem for Netjet\n");
 		return err;
-- 
cgit v1.2.3


From 87935aa776caae9c8346797271d19fa710b65a6a Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 10:45:30 +0800
Subject: isdn: hisax: callc: Replace GFP_ATOMIC with GFP_KERNEL in
 init_PStack()

init_PStack() is never called in atomic context.
It calls kmalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hisax/callc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/isdn/hisax/callc.c b/drivers/isdn/hisax/callc.c
index 5f43783039d4..9ee06328784c 100644
--- a/drivers/isdn/hisax/callc.c
+++ b/drivers/isdn/hisax/callc.c
@@ -1012,7 +1012,7 @@ dummy_pstack(struct PStack *st, int pr, void *arg) {
 
 static int
 init_PStack(struct PStack **stp) {
-	*stp = kmalloc(sizeof(struct PStack), GFP_ATOMIC);
+	*stp = kmalloc(sizeof(struct PStack), GFP_KERNEL);
 	if (!*stp)
 		return -ENOMEM;
 	(*stp)->next = NULL;
-- 
cgit v1.2.3


From 055d624facda577d3168951a1d6e2519e4fc30f7 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 10:48:28 +0800
Subject: isdn: hisax: config: Replace GFP_ATOMIC with GFP_KERNEL

hisax_cs_new() and hisax_cs_setup() are never called in atomic context.
They call kmalloc() and kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/isdn/hisax/config.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/isdn/hisax/config.c b/drivers/isdn/hisax/config.c
index fcc9c46127b4..b12e6cae26c2 100644
--- a/drivers/isdn/hisax/config.c
+++ b/drivers/isdn/hisax/config.c
@@ -1029,7 +1029,7 @@ static int hisax_cs_new(int cardnr, char *id, struct IsdnCard *card,
 
 	*cs_out = NULL;
 
-	cs = kzalloc(sizeof(struct IsdnCardState), GFP_ATOMIC);
+	cs = kzalloc(sizeof(struct IsdnCardState), GFP_KERNEL);
 	if (!cs) {
 		printk(KERN_WARNING
 		       "HiSax: No memory for IsdnCardState(card %d)\n",
@@ -1059,12 +1059,12 @@ static int hisax_cs_new(int cardnr, char *id, struct IsdnCard *card,
 		       "HiSax: Card Type %d out of range\n", card->typ);
 		goto outf_cs;
 	}
-	if (!(cs->dlog = kmalloc(MAX_DLOG_SPACE, GFP_ATOMIC))) {
+	if (!(cs->dlog = kmalloc(MAX_DLOG_SPACE, GFP_KERNEL))) {
 		printk(KERN_WARNING
 		       "HiSax: No memory for dlog(card %d)\n", cardnr + 1);
 		goto outf_cs;
 	}
-	if (!(cs->status_buf = kmalloc(HISAX_STATUS_BUFSIZE, GFP_ATOMIC))) {
+	if (!(cs->status_buf = kmalloc(HISAX_STATUS_BUFSIZE, GFP_KERNEL))) {
 		printk(KERN_WARNING
 		       "HiSax: No memory for status_buf(card %d)\n",
 		       cardnr + 1);
@@ -1123,7 +1123,7 @@ static int hisax_cs_setup(int cardnr, struct IsdnCard *card,
 {
 	int ret;
 
-	if (!(cs->rcvbuf = kmalloc(MAX_DFRAME_LEN_L1, GFP_ATOMIC))) {
+	if (!(cs->rcvbuf = kmalloc(MAX_DFRAME_LEN_L1, GFP_KERNEL))) {
 		printk(KERN_WARNING "HiSax: No memory for isac rcvbuf\n");
 		ll_unload(cs);
 		goto outf_cs;
-- 
cgit v1.2.3


From d8ad2f31f88d609e0f8e4a34f6aeeb482ee5423b Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 11:51:06 +0800
Subject: net: adaptec: Replace mdelay() with msleep() in starfire_init_one()

starfire_init_one() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/adaptec/starfire.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/adaptec/starfire.c b/drivers/net/ethernet/adaptec/starfire.c
index 3872ab96b80a..097467f44b0d 100644
--- a/drivers/net/ethernet/adaptec/starfire.c
+++ b/drivers/net/ethernet/adaptec/starfire.c
@@ -802,7 +802,7 @@ static int starfire_init_one(struct pci_dev *pdev,
 		int mii_status;
 		for (phy = 0; phy < 32 && phy_idx < PHY_CNT; phy++) {
 			mdio_write(dev, phy, MII_BMCR, BMCR_RESET);
-			mdelay(100);
+			msleep(100);
 			boguscnt = 1000;
 			while (--boguscnt > 0)
 				if ((mdio_read(dev, phy, MII_BMCR) & BMCR_RESET) == 0)
-- 
cgit v1.2.3


From f58252cdc04cc4b2d512b2a3a41e4d9d1dc04e2e Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 26 Jul 2018 15:02:24 +1000
Subject: docs: Add rest label the_canonical_patch_format

In preparation to convert Documentation/network/netdev-FAQ.rst to
restructured text format.  We would like to be able to reference 'the
canonical patch format' section.

Add rest label: 'the_canonical_patch_format'.

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/process/submitting-patches.rst | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/process/submitting-patches.rst b/Documentation/process/submitting-patches.rst
index 908bb55be407..c0917107b90a 100644
--- a/Documentation/process/submitting-patches.rst
+++ b/Documentation/process/submitting-patches.rst
@@ -611,6 +611,7 @@ which stable kernel versions should receive your fix. This is the preferred
 method for indicating a bug fixed by the patch. See :ref:`describe_changes`
 for more details.
 
+.. _the_canonical_patch_format:
 
 14) The canonical patch format
 ------------------------------
-- 
cgit v1.2.3


From 96398ddf63ff47833bc5f847a6e83778899058b6 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 26 Jul 2018 15:02:25 +1000
Subject: docs: net: Convert netdev-FAQ to restructured text

Preferred kernel docs format is now restructured text.  Convert
netdev-FAQ.txt to restructured text.

 - Add SPDX license identifier.

 - Change file heading 'Information you need to know about netdev' to
  'netdev FAQ' to better suit displayed index (in HTML).

 - Change question/answer layout to suit rst.  Copy format in
   Documentation/bpf/bpf_devel_QA.rst

 - Fix indentation of code snippets

 - If multiple consecutive URLs appear put them in a list (to maintain
  whitespace).

 - Use uniform spelling of 'bug fix' throughout document (not bugfix or
   bug-fix).

 - Add double back ticks to 'net' and 'net-next' when referring to the
   trees.

 - Use rst references for Documentation/ links.

 - Add rst label 'netdev-FAQ' for referencing by other docs files.

 - Remove stale entry from Documentation/networking/00-INDEX

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/00-INDEX       |   2 -
 Documentation/networking/index.rst      |   1 +
 Documentation/networking/netdev-FAQ.rst | 259 ++++++++++++++++++++++++++++++++
 Documentation/networking/netdev-FAQ.txt | 244 ------------------------------
 4 files changed, 260 insertions(+), 246 deletions(-)
 create mode 100644 Documentation/networking/netdev-FAQ.rst
 delete mode 100644 Documentation/networking/netdev-FAQ.txt

diff --git a/Documentation/networking/00-INDEX b/Documentation/networking/00-INDEX
index 1e5153ed8990..02a323c43261 100644
--- a/Documentation/networking/00-INDEX
+++ b/Documentation/networking/00-INDEX
@@ -138,8 +138,6 @@ multiqueue.txt
 	- HOWTO for multiqueue network device support.
 netconsole.txt
 	- The network console module netconsole.ko: configuration and notes.
-netdev-FAQ.txt
-	- FAQ describing how to submit net changes to netdev mailing list.
 netdev-features.txt
 	- Network interface features API description.
 netdevices.txt
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index f0ae9b65dfba..884a26145f20 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -6,6 +6,7 @@ Contents:
 .. toctree::
    :maxdepth: 2
 
+   netdev-FAQ
    af_xdp
    batman-adv
    can
diff --git a/Documentation/networking/netdev-FAQ.rst b/Documentation/networking/netdev-FAQ.rst
new file mode 100644
index 000000000000..0ac5fa77f501
--- /dev/null
+++ b/Documentation/networking/netdev-FAQ.rst
@@ -0,0 +1,259 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+.. _netdev-FAQ:
+
+==========
+netdev FAQ
+==========
+
+Q: What is netdev?
+------------------
+A: It is a mailing list for all network-related Linux stuff.  This
+includes anything found under net/ (i.e. core code like IPv6) and
+drivers/net (i.e. hardware specific drivers) in the Linux source tree.
+
+Note that some subsystems (e.g. wireless drivers) which have a high
+volume of traffic have their own specific mailing lists.
+
+The netdev list is managed (like many other Linux mailing lists) through
+VGER (http://vger.kernel.org/) and archives can be found below:
+
+-  http://marc.info/?l=linux-netdev
+-  http://www.spinics.net/lists/netdev/
+
+Aside from subsystems like that mentioned above, all network-related
+Linux development (i.e. RFC, review, comments, etc.) takes place on
+netdev.
+
+Q: How do the changes posted to netdev make their way into Linux?
+-----------------------------------------------------------------
+A: There are always two trees (git repositories) in play.  Both are
+driven by David Miller, the main network maintainer.  There is the
+``net`` tree, and the ``net-next`` tree.  As you can probably guess from
+the names, the ``net`` tree is for fixes to existing code already in the
+mainline tree from Linus, and ``net-next`` is where the new code goes
+for the future release.  You can find the trees here:
+
+- https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
+- https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
+
+Q: How often do changes from these trees make it to the mainline Linus tree?
+----------------------------------------------------------------------------
+A: To understand this, you need to know a bit of background information on
+the cadence of Linux development.  Each new release starts off with a
+two week "merge window" where the main maintainers feed their new stuff
+to Linus for merging into the mainline tree.  After the two weeks, the
+merge window is closed, and it is called/tagged ``-rc1``.  No new
+features get mainlined after this -- only fixes to the rc1 content are
+expected.  After roughly a week of collecting fixes to the rc1 content,
+rc2 is released.  This repeats on a roughly weekly basis until rc7
+(typically; sometimes rc6 if things are quiet, or rc8 if things are in a
+state of churn), and a week after the last vX.Y-rcN was done, the
+official vX.Y is released.
+
+Relating that to netdev: At the beginning of the 2-week merge window,
+the ``net-next`` tree will be closed - no new changes/features.  The
+accumulated new content of the past ~10 weeks will be passed onto
+mainline/Linus via a pull request for vX.Y -- at the same time, the
+``net`` tree will start accumulating fixes for this pulled content
+relating to vX.Y
+
+An announcement indicating when ``net-next`` has been closed is usually
+sent to netdev, but knowing the above, you can predict that in advance.
+
+IMPORTANT: Do not send new ``net-next`` content to netdev during the
+period during which ``net-next`` tree is closed.
+
+Shortly after the two weeks have passed (and vX.Y-rc1 is released), the
+tree for ``net-next`` reopens to collect content for the next (vX.Y+1)
+release.
+
+If you aren't subscribed to netdev and/or are simply unsure if
+``net-next`` has re-opened yet, simply check the ``net-next`` git
+repository link above for any new networking-related commits.  You may
+also check the following website for the current status:
+
+  http://vger.kernel.org/~davem/net-next.html
+
+The ``net`` tree continues to collect fixes for the vX.Y content, and is
+fed back to Linus at regular (~weekly) intervals.  Meaning that the
+focus for ``net`` is on stabilization and bug fixes.
+
+Finally, the vX.Y gets released, and the whole cycle starts over.
+
+Q: So where are we now in this cycle?
+
+Load the mainline (Linus) page here:
+
+  https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+
+and note the top of the "tags" section.  If it is rc1, it is early in
+the dev cycle.  If it was tagged rc7 a week ago, then a release is
+probably imminent.
+
+Q: How do I indicate which tree (net vs. net-next) my patch should be in?
+-------------------------------------------------------------------------
+A: Firstly, think whether you have a bug fix or new "next-like" content.
+Then once decided, assuming that you use git, use the prefix flag, i.e.
+::
+
+  git format-patch --subject-prefix='PATCH net-next' start..finish
+
+Use ``net`` instead of ``net-next`` (always lower case) in the above for
+bug-fix ``net`` content.  If you don't use git, then note the only magic
+in the above is just the subject text of the outgoing e-mail, and you
+can manually change it yourself with whatever MUA you are comfortable
+with.
+
+Q: I sent a patch and I'm wondering what happened to it?
+--------------------------------------------------------
+Q: How can I tell whether it got merged?
+A: Start by looking at the main patchworks queue for netdev:
+
+  http://patchwork.ozlabs.org/project/netdev/list/
+
+The "State" field will tell you exactly where things are at with your
+patch.
+
+Q: The above only says "Under Review".  How can I find out more?
+----------------------------------------------------------------
+A: Generally speaking, the patches get triaged quickly (in less than
+48h).  So be patient.  Asking the maintainer for status updates on your
+patch is a good way to ensure your patch is ignored or pushed to the
+bottom of the priority list.
+
+Q: I submitted multiple versions of the patch series
+----------------------------------------------------
+Q: should I directly update patchwork for the previous versions of these
+patch series?
+A: No, please don't interfere with the patch status on patchwork, leave
+it to the maintainer to figure out what is the most recent and current
+version that should be applied. If there is any doubt, the maintainer
+will reply and ask what should be done.
+
+Q: How can I tell what patches are queued up for backporting to the various stable releases?
+--------------------------------------------------------------------------------------------
+A: Normally Greg Kroah-Hartman collects stable commits himself, but for
+networking, Dave collects up patches he deems critical for the
+networking subsystem, and then hands them off to Greg.
+
+There is a patchworks queue that you can see here:
+
+  http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
+
+It contains the patches which Dave has selected, but not yet handed off
+to Greg.  If Greg already has the patch, then it will be here:
+
+  https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
+
+A quick way to find whether the patch is in this stable-queue is to
+simply clone the repo, and then git grep the mainline commit ID, e.g.
+::
+
+  stable-queue$ git grep -l 284041ef21fdf2e
+  releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+  releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+  releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
+  stable/stable-queue$
+
+Q: I see a network patch and I think it should be backported to stable.
+-----------------------------------------------------------------------
+Q: Should I request it via stable@vger.kernel.org like the references in
+the kernel's Documentation/process/stable-kernel-rules.rst file say?
+A: No, not for networking.  Check the stable queues as per above first
+to see if it is already queued.  If not, then send a mail to netdev,
+listing the upstream commit ID and why you think it should be a stable
+candidate.
+
+Before you jump to go do the above, do note that the normal stable rules
+in :ref:`Documentation/process/stable-kernel-rules.rst <stable_kernel_rules>`
+still apply.  So you need to explicitly indicate why it is a critical
+fix and exactly what users are impacted.  In addition, you need to
+convince yourself that you *really* think it has been overlooked,
+vs. having been considered and rejected.
+
+Generally speaking, the longer it has had a chance to "soak" in
+mainline, the better the odds that it is an OK candidate for stable.  So
+scrambling to request a commit be added the day after it appears should
+be avoided.
+
+Q: I have created a network patch and I think it should be backported to stable.
+--------------------------------------------------------------------------------
+Q: Should I add a Cc: stable@vger.kernel.org like the references in the
+kernel's Documentation/ directory say?
+A: No.  See above answer.  In short, if you think it really belongs in
+stable, then ensure you write a decent commit log that describes who
+gets impacted by the bug fix and how it manifests itself, and when the
+bug was introduced.  If you do that properly, then the commit will get
+handled appropriately and most likely get put in the patchworks stable
+queue if it really warrants it.
+
+If you think there is some valid information relating to it being in
+stable that does *not* belong in the commit log, then use the three dash
+marker line as described in
+:ref:`Documentation/process/submitting-patches.rst <the_canonical_patch_format>`
+to temporarily embed that information into the patch that you send.
+
+Q: Are all networking bug fixes backported to all stable releases?
+------------------------------------------------------------------
+A: Due to capacity, Dave could only take care of the backports for the
+last two stable releases. For earlier stable releases, each stable
+branch maintainer is supposed to take care of them. If you find any
+patch is missing from an earlier stable branch, please notify
+stable@vger.kernel.org with either a commit ID or a formal patch
+backported, and CC Dave and other relevant networking developers.
+
+Q: Is the comment style convention different for the networking content?
+------------------------------------------------------------------------
+A: Yes, in a largely trivial way.  Instead of this::
+
+  /*
+   * foobar blah blah blah
+   * another line of text
+   */
+
+it is requested that you make it look like this::
+
+  /* foobar blah blah blah
+   * another line of text
+   */
+
+Q: I am working in existing code that has the former comment style and not the latter.
+--------------------------------------------------------------------------------------
+Q: Should I submit new code in the former style or the latter?
+A: Make it the latter style, so that eventually all code in the domain
+of netdev is of this format.
+
+Q: I found a bug that might have possible security implications or similar.
+---------------------------------------------------------------------------
+Q: Should I mail the main netdev maintainer off-list?**
+A: No. The current netdev maintainer has consistently requested that
+people use the mailing lists and not reach out directly.  If you aren't
+OK with that, then perhaps consider mailing security@kernel.org or
+reading about http://oss-security.openwall.org/wiki/mailing-lists/distros
+as possible alternative mechanisms.
+
+Q: What level of testing is expected before I submit my change?
+---------------------------------------------------------------
+A: If your changes are against ``net-next``, the expectation is that you
+have tested by layering your changes on top of ``net-next``.  Ideally
+you will have done run-time testing specific to your change, but at a
+minimum, your changes should survive an ``allyesconfig`` and an
+``allmodconfig`` build without new warnings or failures.
+
+Q: Any other tips to help ensure my net/net-next patch gets OK'd?
+-----------------------------------------------------------------
+A: Attention to detail.  Re-read your own work as if you were the
+reviewer.  You can start with using ``checkpatch.pl``, perhaps even with
+the ``--strict`` flag.  But do not be mindlessly robotic in doing so.
+If your change is a bug fix, make sure your commit log indicates the
+end-user visible symptom, the underlying reason as to why it happens,
+and then if necessary, explain why the fix proposed is the best way to
+get things done.  Don't mangle whitespace, and as is common, don't
+mis-indent function arguments that span multiple lines.  If it is your
+first patch, mail it to yourself so you can test apply it to an
+unpatched tree to confirm infrastructure didn't mangle it.
+
+Finally, go back and read
+:ref:`Documentation/process/submitting-patches.rst <submittingpatches>`
+to be sure you are not repeating some common mistake documented there.
diff --git a/Documentation/networking/netdev-FAQ.txt b/Documentation/networking/netdev-FAQ.txt
deleted file mode 100644
index fa951b820b25..000000000000
--- a/Documentation/networking/netdev-FAQ.txt
+++ /dev/null
@@ -1,244 +0,0 @@
-
-Information you need to know about netdev
------------------------------------------
-
-Q: What is netdev?
-
-A: It is a mailing list for all network-related Linux stuff.  This includes
-   anything found under net/  (i.e. core code like IPv6) and drivers/net
-   (i.e. hardware specific drivers) in the Linux source tree.
-
-   Note that some subsystems (e.g. wireless drivers) which have a high volume
-   of traffic have their own specific mailing lists.
-
-   The netdev list is managed (like many other Linux mailing lists) through
-   VGER ( http://vger.kernel.org/ ) and archives can be found below:
-
-	http://marc.info/?l=linux-netdev
-	http://www.spinics.net/lists/netdev/
-
-   Aside from subsystems like that mentioned above, all network-related Linux
-   development (i.e. RFC, review, comments, etc.) takes place on netdev.
-
-Q: How do the changes posted to netdev make their way into Linux?
-
-A: There are always two trees (git repositories) in play.  Both are driven
-   by David Miller, the main network maintainer.  There is the "net" tree,
-   and the "net-next" tree.  As you can probably guess from the names, the
-   net tree is for fixes to existing code already in the mainline tree from
-   Linus, and net-next is where the new code goes for the future release.
-   You can find the trees here:
-
-        https://git.kernel.org/pub/scm/linux/kernel/git/davem/net.git
-        https://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next.git
-
-Q: How often do changes from these trees make it to the mainline Linus tree?
-
-A: To understand this, you need to know a bit of background information
-   on the cadence of Linux development.  Each new release starts off with
-   a two week "merge window" where the main maintainers feed their new
-   stuff to Linus for merging into the mainline tree.  After the two weeks,
-   the merge window is closed, and it is called/tagged "-rc1".  No new
-   features get mainlined after this -- only fixes to the rc1 content
-   are expected.  After roughly a week of collecting fixes to the rc1
-   content, rc2 is released.  This repeats on a roughly weekly basis
-   until rc7 (typically; sometimes rc6 if things are quiet, or rc8 if
-   things are in a state of churn), and a week after the last vX.Y-rcN
-   was done, the official "vX.Y" is released.
-
-   Relating that to netdev:  At the beginning of the 2-week merge window,
-   the net-next tree will be closed - no new changes/features.  The
-   accumulated new content of the past ~10 weeks will be passed onto
-   mainline/Linus via a pull request for vX.Y -- at the same time,
-   the "net" tree will start accumulating fixes for this pulled content
-   relating to vX.Y
-
-   An announcement indicating when net-next has been closed is usually
-   sent to netdev, but knowing the above, you can predict that in advance.
-
-   IMPORTANT:  Do not send new net-next content to netdev during the
-   period during which net-next tree is closed.
-
-   Shortly after the two weeks have passed (and vX.Y-rc1 is released), the
-   tree for net-next reopens to collect content for the next (vX.Y+1) release.
-
-   If you aren't subscribed to netdev and/or are simply unsure if net-next
-   has re-opened yet, simply check the net-next git repository link above for
-   any new networking-related commits.  You may also check the following
-   website for the current status:
-
-        http://vger.kernel.org/~davem/net-next.html
-
-   The "net" tree continues to collect fixes for the vX.Y content, and
-   is fed back to Linus at regular (~weekly) intervals.  Meaning that the
-   focus for "net" is on stabilization and bugfixes.
-
-   Finally, the vX.Y gets released, and the whole cycle starts over.
-
-Q: So where are we now in this cycle?
-
-A: Load the mainline (Linus) page here:
-
-	https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-
-   and note the top of the "tags" section.  If it is rc1, it is early
-   in the dev cycle.  If it was tagged rc7 a week ago, then a release
-   is probably imminent.
-
-Q: How do I indicate which tree (net vs. net-next) my patch should be in?
-
-A: Firstly, think whether you have a bug fix or new "next-like" content.
-   Then once decided, assuming that you use git, use the prefix flag, i.e.
-
-	git format-patch --subject-prefix='PATCH net-next' start..finish
-
-   Use "net" instead of "net-next" (always lower case) in the above for
-   bug-fix net content.  If you don't use git, then note the only magic in
-   the above is just the subject text of the outgoing e-mail, and you can
-   manually change it yourself with whatever MUA you are comfortable with.
-
-Q: I sent a patch and I'm wondering what happened to it.  How can I tell
-   whether it got merged?
-
-A: Start by looking at the main patchworks queue for netdev:
-
-	http://patchwork.ozlabs.org/project/netdev/list/
-
-   The "State" field will tell you exactly where things are at with
-   your patch.
-
-Q: The above only says "Under Review".  How can I find out more?
-
-A: Generally speaking, the patches get triaged quickly (in less than 48h).
-   So be patient.  Asking the maintainer for status updates on your
-   patch is a good way to ensure your patch is ignored or pushed to
-   the bottom of the priority list.
-
-Q: I submitted multiple versions of the patch series, should I directly update
-   patchwork for the previous versions of these patch series?
-
-A: No, please don't interfere with the patch status on patchwork, leave it to
-   the maintainer to figure out what is the most recent and current version that
-   should be applied. If there is any doubt, the maintainer will reply and ask
-   what should be done.
-
-Q: How can I tell what patches are queued up for backporting to the
-   various stable releases?
-
-A: Normally Greg Kroah-Hartman collects stable commits himself, but
-   for networking, Dave collects up patches he deems critical for the
-   networking subsystem, and then hands them off to Greg.
-
-   There is a patchworks queue that you can see here:
-	http://patchwork.ozlabs.org/bundle/davem/stable/?state=*
-
-   It contains the patches which Dave has selected, but not yet handed
-   off to Greg.  If Greg already has the patch, then it will be here:
-	https://git.kernel.org/pub/scm/linux/kernel/git/stable/stable-queue.git
-
-   A quick way to find whether the patch is in this stable-queue is
-   to simply clone the repo, and then git grep the mainline commit ID, e.g.
-
-	stable-queue$ git grep -l 284041ef21fdf2e
-	releases/3.0.84/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-	releases/3.4.51/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-	releases/3.9.8/ipv6-fix-possible-crashes-in-ip6_cork_release.patch
-	stable/stable-queue$
-
-Q: I see a network patch and I think it should be backported to stable.
-   Should I request it via "stable@vger.kernel.org" like the references in
-   the kernel's Documentation/process/stable-kernel-rules.rst file say?
-
-A: No, not for networking.  Check the stable queues as per above 1st to see
-   if it is already queued.  If not, then send a mail to netdev, listing
-   the upstream commit ID and why you think it should be a stable candidate.
-
-   Before you jump to go do the above, do note that the normal stable rules
-   in Documentation/process/stable-kernel-rules.rst still apply.  So you need to
-   explicitly indicate why it is a critical fix and exactly what users are
-   impacted.  In addition, you need to convince yourself that you _really_
-   think it has been overlooked, vs. having been considered and rejected.
-
-   Generally speaking, the longer it has had a chance to "soak" in mainline,
-   the better the odds that it is an OK candidate for stable.  So scrambling
-   to request a commit be added the day after it appears should be avoided.
-
-Q: I have created a network patch and I think it should be backported to
-   stable.  Should I add a "Cc: stable@vger.kernel.org" like the references
-   in the kernel's Documentation/ directory say?
-
-A: No.  See above answer.  In short, if you think it really belongs in
-   stable, then ensure you write a decent commit log that describes who
-   gets impacted by the bugfix and how it manifests itself, and when the
-   bug was introduced.  If you do that properly, then the commit will
-   get handled appropriately and most likely get put in the patchworks
-   stable queue if it really warrants it.
-
-   If you think there is some valid information relating to it being in
-   stable that does _not_ belong in the commit log, then use the three
-   dash marker line as described in Documentation/process/submitting-patches.rst to
-   temporarily embed that information into the patch that you send.
-
-Q: Are all networking bug fixes backported to all stable releases?
-
-A: Due to capacity, Dave could only take care of the backports for the last
-   2 stable releases. For earlier stable releases, each stable branch maintainer
-   is supposed to take care of them. If you find any patch is missing from an
-   earlier stable branch, please notify stable@vger.kernel.org with either a
-   commit ID or a formal patch backported, and CC Dave and other relevant
-   networking developers.
-
-Q: Someone said that the comment style and coding convention is different
-   for the networking content.  Is this true?
-
-A: Yes, in a largely trivial way.  Instead of this:
-
-	/*
-	 * foobar blah blah blah
-	 * another line of text
-	 */
-
-   it is requested that you make it look like this:
-
-	/* foobar blah blah blah
-	 * another line of text
-	 */
-
-Q: I am working in existing code that has the former comment style and not the
-   latter.  Should I submit new code in the former style or the latter?
-
-A: Make it the latter style, so that eventually all code in the domain of
-   netdev is of this format.
-
-Q: I found a bug that might have possible security implications or similar.
-   Should I mail the main netdev maintainer off-list?
-
-A: No. The current netdev maintainer has consistently requested that people
-   use the mailing lists and not reach out directly.  If you aren't OK with
-   that, then perhaps consider mailing "security@kernel.org" or reading about
-   http://oss-security.openwall.org/wiki/mailing-lists/distros
-   as possible alternative mechanisms.
-
-Q: What level of testing is expected before I submit my change?
-
-A: If your changes are against net-next, the expectation is that you
-   have tested by layering your changes on top of net-next.  Ideally you
-   will have done run-time testing specific to your change, but at a
-   minimum, your changes should survive an "allyesconfig" and an
-   "allmodconfig" build without new warnings or failures.
-
-Q: Any other tips to help ensure my net/net-next patch gets OK'd?
-
-A: Attention to detail.  Re-read your own work as if you were the
-   reviewer.  You can start with using checkpatch.pl, perhaps even
-   with the "--strict" flag.  But do not be mindlessly robotic in
-   doing so.  If your change is a bug-fix, make sure your commit log
-   indicates the end-user visible symptom, the underlying reason as
-   to why it happens, and then if necessary, explain why the fix proposed
-   is the best way to get things done.   Don't mangle whitespace, and as
-   is common, don't mis-indent function arguments that span multiple lines.
-   If it is your first patch, mail it to yourself so you can test apply
-   it to an unpatched tree to confirm infrastructure didn't mangle it.
-
-   Finally, go back and read Documentation/process/submitting-patches.rst to be
-   sure you are not repeating some common mistake documented there.
-- 
cgit v1.2.3


From 287f4fa99a5281d9dc3b431eaa7403e948eb1e22 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 26 Jul 2018 15:02:26 +1000
Subject: docs: Update references to netdev-FAQ

File 'Documentation/networking/netdev-FAQ.txt' has been converted to RST
format.  We should update all links/references to point to the new file.

Update references to netdev-FAQ

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/bpf/bpf_devel_QA.rst            | 21 +++++++++------------
 Documentation/process/stable-kernel-rules.rst |  2 +-
 2 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/Documentation/bpf/bpf_devel_QA.rst b/Documentation/bpf/bpf_devel_QA.rst
index 0e7c1d946e83..c9856b927055 100644
--- a/Documentation/bpf/bpf_devel_QA.rst
+++ b/Documentation/bpf/bpf_devel_QA.rst
@@ -106,9 +106,9 @@ into the bpf-next tree will make their way into net-next tree. net and
 net-next are both run by David S. Miller. From there, they will go
 into the kernel mainline tree run by Linus Torvalds. To read up on the
 process of net and net-next being merged into the mainline tree, see
-the `netdev FAQ`_ under:
+the :ref:`netdev-FAQ`
+
 
- `Documentation/networking/netdev-FAQ.txt`_
 
 Occasionally, to prevent merge conflicts, we might send pull requests
 to other trees (e.g. tracing) with a small subset of the patches, but
@@ -125,8 +125,8 @@ request)::
 Q: How do I indicate which tree (bpf vs. bpf-next) my patch should be applied to?
 ---------------------------------------------------------------------------------
 
-A: The process is the very same as described in the `netdev FAQ`_, so
-please read up on it. The subject line must indicate whether the
+A: The process is the very same as described in the :ref:`netdev-FAQ`,
+so please read up on it. The subject line must indicate whether the
 patch is a fix or rather "next-like" content in order to let the
 maintainers know whether it is targeted at bpf or bpf-next.
 
@@ -184,7 +184,7 @@ ii) run extensive BPF test suite and
 Once the BPF pull request was accepted by David S. Miller, then
 the patches end up in net or net-next tree, respectively, and
 make their way from there further into mainline. Again, see the
-`netdev FAQ`_ for additional information e.g. on how often they are
+:ref:`netdev-FAQ` for additional information e.g. on how often they are
 merged to mainline.
 
 Q: How long do I need to wait for feedback on my BPF patches?
@@ -208,7 +208,7 @@ Q: Are patches applied to bpf-next when the merge window is open?
 -----------------------------------------------------------------
 A: For the time when the merge window is open, bpf-next will not be
 processed. This is roughly analogous to net-next patch processing,
-so feel free to read up on the `netdev FAQ`_ about further details.
+so feel free to read up on the :ref:`netdev-FAQ` about further details.
 
 During those two weeks of merge window, we might ask you to resend
 your patch series once bpf-next is open again. Once Linus released
@@ -372,7 +372,7 @@ netdev kernel mailing list in Cc and ask for the fix to be queued up:
   netdev@vger.kernel.org
 
 The process in general is the same as on netdev itself, see also the
-`netdev FAQ`_ document.
+:ref:`netdev-FAQ`.
 
 Q: Do you also backport to kernels not currently maintained as stable?
 ----------------------------------------------------------------------
@@ -388,9 +388,7 @@ Q: The BPF patch I am about to submit needs to go to stable as well
 What should I do?
 
 A: The same rules apply as with netdev patch submissions in general, see
-`netdev FAQ`_ under:
-
-  `Documentation/networking/netdev-FAQ.txt`_
+the :ref:`netdev-FAQ`.
 
 Never add "``Cc: stable@vger.kernel.org``" to the patch description, but
 ask the BPF maintainers to queue the patches instead. This can be done
@@ -630,8 +628,7 @@ when:
 .. Links
 .. _Documentation/process/: https://www.kernel.org/doc/html/latest/process/
 .. _MAINTAINERS: ../../MAINTAINERS
-.. _Documentation/networking/netdev-FAQ.txt: ../networking/netdev-FAQ.txt
-.. _netdev FAQ: ../networking/netdev-FAQ.txt
+.. _netdev-FAQ: ../networking/netdev-FAQ.rst
 .. _samples/bpf/: ../../samples/bpf/
 .. _selftests: ../../tools/testing/selftests/bpf/
 .. _Documentation/dev-tools/kselftest.rst:
diff --git a/Documentation/process/stable-kernel-rules.rst b/Documentation/process/stable-kernel-rules.rst
index 36a2dded525b..0de6f6145cc6 100644
--- a/Documentation/process/stable-kernel-rules.rst
+++ b/Documentation/process/stable-kernel-rules.rst
@@ -37,7 +37,7 @@ Procedure for submitting patches to the -stable tree
 
  - If the patch covers files in net/ or drivers/net please follow netdev stable
    submission guidelines as described in
-   Documentation/networking/netdev-FAQ.txt
+   :ref:`Documentation/networking/netdev-FAQ.rst <netdev-FAQ>`
  - Security patches should not be handled (solely) by the -stable review
    process but should follow the procedures in
    :ref:`Documentation/admin-guide/security-bugs.rst <securitybugs>`.
-- 
cgit v1.2.3


From f61b6db378539e69d8525a1b5001637df1e13040 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 26 Jul 2018 14:25:26 -0700
Subject: netdevsim: make debug dirs' dentries static

The root directories of netdevsim should only be used by the core
to create per-device subdirectories, so limit their visibility to
the core file.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netdevsim/netdev.c    | 6 +++---
 drivers/net/netdevsim/netdevsim.h | 3 ---
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 2d244551298b..8d8e2b3f263e 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -41,6 +41,9 @@ struct nsim_vf_config {
 
 static u32 nsim_dev_id;
 
+static struct dentry *nsim_ddir;
+static struct dentry *nsim_sdev_ddir;
+
 static int nsim_num_vf(struct device *dev)
 {
 	struct netdevsim *ns = to_nsim(dev);
@@ -566,9 +569,6 @@ static struct rtnl_link_ops nsim_link_ops __read_mostly = {
 	.dellink	= nsim_dellink,
 };
 
-struct dentry *nsim_ddir;
-struct dentry *nsim_sdev_ddir;
-
 static int __init nsim_module_init(void)
 {
 	int err;
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 02be199eb005..384c254fafc5 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -103,9 +103,6 @@ struct netdevsim {
 	struct nsim_ipsec ipsec;
 };
 
-extern struct dentry *nsim_ddir;
-extern struct dentry *nsim_sdev_ddir;
-
 #ifdef CONFIG_BPF_SYSCALL
 int nsim_bpf_init(struct netdevsim *ns);
 void nsim_bpf_uninit(struct netdevsim *ns);
-- 
cgit v1.2.3


From c6f5e017df9dfa9f6cbe70da008e7d716d726f1b Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Thu, 26 Jul 2018 15:09:52 +0800
Subject: xfrm: fix ptr_ret.cocci warnings

net/xfrm/xfrm_interface.c:692:1-3: WARNING: PTR_ERR_OR_ZERO can be used

 Use PTR_ERR_OR_ZERO rather than if(IS_ERR(...)) + PTR_ERR

Generated by: scripts/coccinelle/api/ptr_ret.cocci

Fixes: 44e2b838c24d ("xfrm: Return detailed errors from xfrmi_newlink")
CC: Benedict Wong <benedictwong@google.com>
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_interface.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c
index 481d7307ab51..31acc6f33d98 100644
--- a/net/xfrm/xfrm_interface.c
+++ b/net/xfrm/xfrm_interface.c
@@ -689,10 +689,7 @@ static int xfrmi_newlink(struct net *src_net, struct net_device *dev,
 	nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ);
 
 	xi = xfrmi_locate(net, p, 1);
-	if (IS_ERR(xi))
-		return PTR_ERR(xi);
-
-	return 0;
+	return PTR_ERR_OR_ZERO(xi);
 }
 
 static void xfrmi_dellink(struct net_device *dev, struct list_head *head)
-- 
cgit v1.2.3


From 78a8b760e40881c883c5552db991664727a91868 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:53:30 -0700
Subject: nfp: move repr handling on RX path

Representor packets are received on PF queues with special metadata tag
for demux.  There is no reason to resolve the representor ID -> netdev
after the skb has been allocated.  Move the code, this will allow us to
handle special FW messages without SKB allocation overhead.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 .../net/ethernet/netronome/nfp/nfp_net_common.c    | 29 +++++++++++-----------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index cf1704e972b7..cdfbd1e8bf4b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1757,6 +1757,21 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 			}
 		}
 
+		if (likely(!meta.portid)) {
+			netdev = dp->netdev;
+		} else {
+			struct nfp_net *nn;
+
+			nn = netdev_priv(dp->netdev);
+			netdev = nfp_app_repr_get(nn->app, meta.portid);
+			if (unlikely(!netdev)) {
+				nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf,
+						NULL);
+				continue;
+			}
+			nfp_repr_inc_rx_stats(netdev, pkt_len);
+		}
+
 		skb = build_skb(rxbuf->frag, true_bufsz);
 		if (unlikely(!skb)) {
 			nfp_net_rx_drop(dp, r_vec, rx_ring, rxbuf, NULL);
@@ -1772,20 +1787,6 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		nfp_net_rx_give_one(dp, rx_ring, new_frag, new_dma_addr);
 
-		if (likely(!meta.portid)) {
-			netdev = dp->netdev;
-		} else {
-			struct nfp_net *nn;
-
-			nn = netdev_priv(dp->netdev);
-			netdev = nfp_app_repr_get(nn->app, meta.portid);
-			if (unlikely(!netdev)) {
-				nfp_net_rx_drop(dp, r_vec, rx_ring, NULL, skb);
-				continue;
-			}
-			nfp_repr_inc_rx_stats(netdev, pkt_len);
-		}
-
 		skb_reserve(skb, pkt_off);
 		skb_put(skb, pkt_len);
 
-- 
cgit v1.2.3


From 79ca38e80c4588adeb11a0abd116d72ab6fe0ecc Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:53:31 -0700
Subject: nfp: allow control message reception on data queues

Port id 0xffffffff is reserved for control messages.  Allow reception
of messages with this id on data queues.  Hand off a raw buffer to
the higher layer code, without allocating SKB for max efficiency.
The RX handle can't modify or keep the buffer, after it returns
buffer is handed back over to the NIC RX free buffer list.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_app.c        |  2 ++
 drivers/net/ethernet/netronome/nfp/nfp_app.h        | 17 +++++++++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c | 11 +++++++++++
 drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h   |  1 +
 4 files changed, 31 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c
index 69d4ae7a61f3..8607d09ab732 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c
@@ -172,6 +172,8 @@ struct nfp_app *nfp_app_alloc(struct nfp_pf *pf, enum nfp_app_id id)
 
 	if (WARN_ON(!apps[id]->name || !apps[id]->vnic_alloc))
 		return ERR_PTR(-EINVAL);
+	if (WARN_ON(!apps[id]->ctrl_msg_rx && apps[id]->ctrl_msg_rx_raw))
+		return ERR_PTR(-EINVAL);
 
 	app = kzalloc(sizeof(*app), GFP_KERNEL);
 	if (!app)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index afbc19aa66a8..ccb244cf6c30 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -98,6 +98,7 @@ extern const struct nfp_app_type app_abm;
  * @start:	start application logic
  * @stop:	stop application logic
  * @ctrl_msg_rx:    control message handler
+ * @ctrl_msg_rx_raw:	handler for control messages from data queues
  * @setup_tc:	setup TC ndo
  * @bpf:	BPF ndo offload-related calls
  * @xdp_offload:    offload an XDP program
@@ -150,6 +151,8 @@ struct nfp_app_type {
 	void (*stop)(struct nfp_app *app);
 
 	void (*ctrl_msg_rx)(struct nfp_app *app, struct sk_buff *skb);
+	void (*ctrl_msg_rx_raw)(struct nfp_app *app, const void *data,
+				unsigned int len);
 
 	int (*setup_tc)(struct nfp_app *app, struct net_device *netdev,
 			enum tc_setup_type type, void *type_data);
@@ -318,6 +321,11 @@ static inline bool nfp_app_ctrl_has_meta(struct nfp_app *app)
 	return app->type->ctrl_has_meta;
 }
 
+static inline bool nfp_app_ctrl_uses_data_vnics(struct nfp_app *app)
+{
+	return app && app->type->ctrl_msg_rx_raw;
+}
+
 static inline const char *nfp_app_extra_cap(struct nfp_app *app,
 					    struct nfp_net *nn)
 {
@@ -381,6 +389,15 @@ static inline void nfp_app_ctrl_rx(struct nfp_app *app, struct sk_buff *skb)
 	app->type->ctrl_msg_rx(app, skb);
 }
 
+static inline void
+nfp_app_ctrl_rx_raw(struct nfp_app *app, const void *data, unsigned int len)
+{
+	trace_devlink_hwmsg(priv_to_devlink(app->pf), true, 0, data, len);
+
+	if (app && app->type->ctrl_msg_rx_raw)
+		app->type->ctrl_msg_rx_raw(app, data, len);
+}
+
 static inline int nfp_app_eswitch_mode_get(struct nfp_app *app, u16 *mode)
 {
 	if (!app->type->eswitch_mode_get)
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index cdfbd1e8bf4b..ca42f7da4f50 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -1759,6 +1759,14 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget)
 
 		if (likely(!meta.portid)) {
 			netdev = dp->netdev;
+		} else if (meta.portid == NFP_META_PORT_ID_CTRL) {
+			struct nfp_net *nn = netdev_priv(dp->netdev);
+
+			nfp_app_ctrl_rx_raw(nn->app, rxbuf->frag + pkt_off,
+					    pkt_len);
+			nfp_net_rx_give_one(dp, rx_ring, rxbuf->frag,
+					    rxbuf->dma_addr);
+			continue;
 		} else {
 			struct nfp_net *nn;
 
@@ -3857,6 +3865,9 @@ int nfp_net_init(struct nfp_net *nn)
 		nn->dp.mtu = NFP_NET_DEFAULT_MTU;
 	nn->dp.fl_bufsz = nfp_net_calc_fl_bufsz(&nn->dp);
 
+	if (nfp_app_ctrl_uses_data_vnics(nn->app))
+		nn->dp.ctrl |= nn->cap & NFP_NET_CFG_CTRL_CMSG_DATA;
+
 	if (nn->cap & NFP_NET_CFG_CTRL_RSS_ANY) {
 		nfp_net_rss_init(nn);
 		nn->dp.ctrl |= nn->cap & NFP_NET_CFG_CTRL_RSS2 ?:
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
index bb63c115537d..44d3ea75d043 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ctrl.h
@@ -127,6 +127,7 @@
 #define   NFP_NET_CFG_CTRL_GATHER	  (0x1 <<  9) /* Gather DMA */
 #define   NFP_NET_CFG_CTRL_LSO		  (0x1 << 10) /* LSO/TSO (version 1) */
 #define   NFP_NET_CFG_CTRL_CTAG_FILTER	  (0x1 << 11) /* VLAN CTAG filtering */
+#define   NFP_NET_CFG_CTRL_CMSG_DATA	  (0x1 << 12) /* RX cmsgs on data Qs */
 #define   NFP_NET_CFG_CTRL_RINGCFG	  (0x1 << 16) /* Ring runtime changes */
 #define   NFP_NET_CFG_CTRL_RSS		  (0x1 << 17) /* RSS (version 1) */
 #define   NFP_NET_CFG_CTRL_IRQMOD	  (0x1 << 18) /* Interrupt moderation */
-- 
cgit v1.2.3


From 20c54204219987d620ca9da567dd54e569863dad Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:53:32 -0700
Subject: nfp: bpf: pass raw data buffer to nfp_bpf_event_output()

In preparation for SKB-less perf event handling make
nfp_bpf_event_output() take buffer address and length,
not SKB as parameters.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/cmsg.c    |  5 ++++-
 drivers/net/ethernet/netronome/nfp/bpf/main.h    |  3 ++-
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 21 +++++++++------------
 3 files changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index cb87fccb9f6a..0a89b53962aa 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -441,7 +441,10 @@ void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb)
 	}
 
 	if (nfp_bpf_cmsg_get_type(skb) == CMSG_TYPE_BPF_EVENT) {
-		nfp_bpf_event_output(bpf, skb);
+		if (!nfp_bpf_event_output(bpf, skb->data, skb->len))
+			dev_consume_skb_any(skb);
+		else
+			dev_kfree_skb_any(skb);
 		return;
 	}
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index bec935468f90..e25d3c0c7e43 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -501,7 +501,8 @@ int nfp_bpf_ctrl_lookup_entry(struct bpf_offloaded_map *offmap,
 int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap,
 			       void *key, void *next_key);
 
-int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb);
+int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
+			 unsigned int len);
 
 void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb);
 #endif
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 49b03f7dbf46..293dda84818f 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -453,23 +453,24 @@ nfp_bpf_perf_event_copy(void *dst, const void *src,
 	return 0;
 }
 
-int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb)
+int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
+			 unsigned int len)
 {
-	struct cmsg_bpf_event *cbe = (void *)skb->data;
+	struct cmsg_bpf_event *cbe = (void *)data;
 	u32 pkt_size, data_size;
 	struct bpf_map *map;
 
-	if (skb->len < sizeof(struct cmsg_bpf_event))
-		goto err_drop;
+	if (len < sizeof(struct cmsg_bpf_event))
+		return -EINVAL;
 
 	pkt_size = be32_to_cpu(cbe->pkt_size);
 	data_size = be32_to_cpu(cbe->data_size);
 	map = (void *)(unsigned long)be64_to_cpu(cbe->map_ptr);
 
-	if (skb->len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
-		goto err_drop;
+	if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
+		return -EINVAL;
 	if (cbe->hdr.ver != CMSG_MAP_ABI_VERSION)
-		goto err_drop;
+		return -EINVAL;
 
 	rcu_read_lock();
 	if (!rhashtable_lookup_fast(&bpf->maps_neutral, &map,
@@ -477,7 +478,7 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb)
 		rcu_read_unlock();
 		pr_warn("perf event: dest map pointer %px not recognized, dropping event\n",
 			map);
-		goto err_drop;
+		return -EINVAL;
 	}
 
 	bpf_event_output(map, be32_to_cpu(cbe->cpu_id),
@@ -485,11 +486,7 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb)
 			 cbe->data, pkt_size, nfp_bpf_perf_event_copy);
 	rcu_read_unlock();
 
-	dev_consume_skb_any(skb);
 	return 0;
-err_drop:
-	dev_kfree_skb_any(skb);
-	return -EINVAL;
 }
 
 static int
-- 
cgit v1.2.3


From 0958762748e4cfeb19d881aa8d3fe5ba8b5bc50b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:53:33 -0700
Subject: nfp: bpf: allow receiving perf events on data queues

Control queue is fairly low latency, and requires SKB allocations,
which means we can't even reach 0.5Msps with perf events.  Allow
perf events to be delivered to data queues.  This allows us to not
only use multiple queues, but also receive and deliver to user space
more than 5Msps per queue (Xeon E5-2630 v4 2.20GHz, no retpolines).

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/cmsg.c | 18 ++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/bpf/main.c |  1 +
 drivers/net/ethernet/netronome/nfp/bpf/main.h |  3 +++
 3 files changed, 22 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 0a89b53962aa..1946291bf4fd 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -468,3 +468,21 @@ err_unlock:
 err_free:
 	dev_kfree_skb_any(skb);
 }
+
+void
+nfp_bpf_ctrl_msg_rx_raw(struct nfp_app *app, const void *data, unsigned int len)
+{
+	struct nfp_app_bpf *bpf = app->priv;
+	const struct cmsg_hdr *hdr = data;
+
+	if (unlikely(len < sizeof(struct cmsg_reply_map_simple))) {
+		cmsg_warn(bpf, "cmsg drop - too short %d!\n", len);
+		return;
+	}
+
+	if (hdr->type == CMSG_TYPE_BPF_EVENT)
+		nfp_bpf_event_output(bpf, data, len);
+	else
+		cmsg_warn(bpf, "cmsg drop - msg type %d with raw buffer!\n",
+			  hdr->type);
+}
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 994d2b756fe1..192e88981fb2 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -490,6 +490,7 @@ const struct nfp_app_type app_bpf = {
 	.vnic_free	= nfp_bpf_vnic_free,
 
 	.ctrl_msg_rx	= nfp_bpf_ctrl_msg_rx,
+	.ctrl_msg_rx_raw	= nfp_bpf_ctrl_msg_rx_raw,
 
 	.setup_tc	= nfp_bpf_setup_tc,
 	.bpf		= nfp_ndo_bpf,
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index e25d3c0c7e43..017e0ae5e736 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -505,4 +505,7 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
 			 unsigned int len);
 
 void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb);
+void
+nfp_bpf_ctrl_msg_rx_raw(struct nfp_app *app, const void *data,
+			unsigned int len);
 #endif
-- 
cgit v1.2.3


From ab01f4ac5faf6a0ea532fa65cf6b1c9b2019e49b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:53:34 -0700
Subject: nfp: bpf: remember maps by ID

Record perf maps by map ID, not raw kernel pointer.  This helps
with debug messages, because printing pointers to logs is frowned
upon, and makes debug easier for the users, as map ID is something
they should be more familiar with.  Note that perf maps are offload
neutral, therefore IDs won't be orphaned.

While at it use a rate limited print helper for the error message.

Reported-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/cmsg.c    |  2 --
 drivers/net/ethernet/netronome/nfp/bpf/jit.c     | 12 ++++++++----
 drivers/net/ethernet/netronome/nfp/bpf/main.c    |  4 ++--
 drivers/net/ethernet/netronome/nfp/bpf/main.h    |  3 +++
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 22 +++++++++++++---------
 5 files changed, 26 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
index 1946291bf4fd..2572a4b91c7c 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c
@@ -43,8 +43,6 @@
 #include "fw.h"
 #include "main.h"
 
-#define cmsg_warn(bpf, msg...)	nn_dp_warn(&(bpf)->app->ctrl->dp, msg)
-
 #define NFP_BPF_TAG_ALLOC_SPAN	(U16_MAX / 4)
 
 static bool nfp_bpf_all_tags_busy(struct nfp_app_bpf *bpf)
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 1d9e36835404..3c22d27de9da 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -3883,6 +3883,7 @@ static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
 	struct nfp_insn_meta *meta1, *meta2;
 	struct nfp_bpf_map *nfp_map;
 	struct bpf_map *map;
+	u32 id;
 
 	nfp_for_each_insn_walk2(nfp_prog, meta1, meta2) {
 		if (meta1->skip || meta2->skip)
@@ -3894,11 +3895,14 @@ static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog)
 
 		map = (void *)(unsigned long)((u32)meta1->insn.imm |
 					      (u64)meta2->insn.imm << 32);
-		if (bpf_map_offload_neutral(map))
-			continue;
-		nfp_map = map_to_offmap(map)->dev_priv;
+		if (bpf_map_offload_neutral(map)) {
+			id = map->id;
+		} else {
+			nfp_map = map_to_offmap(map)->dev_priv;
+			id = nfp_map->tid;
+		}
 
-		meta1->insn.imm = nfp_map->tid;
+		meta1->insn.imm = id;
 		meta2->insn.imm = 0;
 	}
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index 192e88981fb2..cce1d2945a32 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -45,8 +45,8 @@
 
 const struct rhashtable_params nfp_bpf_maps_neutral_params = {
 	.nelem_hint		= 4,
-	.key_len		= FIELD_SIZEOF(struct nfp_bpf_neutral_map, ptr),
-	.key_offset		= offsetof(struct nfp_bpf_neutral_map, ptr),
+	.key_len		= FIELD_SIZEOF(struct bpf_map, id),
+	.key_offset		= offsetof(struct nfp_bpf_neutral_map, map_id),
 	.head_offset		= offsetof(struct nfp_bpf_neutral_map, l),
 	.automatic_shrinking	= true,
 };
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 017e0ae5e736..57573bfa8c03 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -47,6 +47,8 @@
 #include "../nfp_asm.h"
 #include "fw.h"
 
+#define cmsg_warn(bpf, msg...)	nn_dp_warn(&(bpf)->app->ctrl->dp, msg)
+
 /* For relocation logic use up-most byte of branch instruction as scratch
  * area.  Remember to clear this before sending instructions to HW!
  */
@@ -221,6 +223,7 @@ struct nfp_bpf_map {
 struct nfp_bpf_neutral_map {
 	struct rhash_head l;
 	struct bpf_map *ptr;
+	u32 map_id;
 	u32 count;
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index 293dda84818f..b1fbb3babc7f 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -67,7 +67,7 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	ASSERT_RTNL();
 
 	/* Reuse path - other offloaded program is already tracking this map. */
-	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map,
+	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map->id,
 					nfp_bpf_maps_neutral_params);
 	if (record) {
 		nfp_prog->map_records[nfp_prog->map_records_cnt++] = record;
@@ -89,6 +89,7 @@ nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog,
 	}
 
 	record->ptr = map;
+	record->map_id = map->id;
 	record->count = 1;
 
 	err = rhashtable_insert_fast(&bpf->maps_neutral, &record->l,
@@ -457,15 +458,17 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
 			 unsigned int len)
 {
 	struct cmsg_bpf_event *cbe = (void *)data;
-	u32 pkt_size, data_size;
-	struct bpf_map *map;
+	struct nfp_bpf_neutral_map *record;
+	u32 pkt_size, data_size, map_id;
+	u64 map_id_full;
 
 	if (len < sizeof(struct cmsg_bpf_event))
 		return -EINVAL;
 
 	pkt_size = be32_to_cpu(cbe->pkt_size);
 	data_size = be32_to_cpu(cbe->data_size);
-	map = (void *)(unsigned long)be64_to_cpu(cbe->map_ptr);
+	map_id_full = be64_to_cpu(cbe->map_ptr);
+	map_id = map_id_full;
 
 	if (len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size)
 		return -EINVAL;
@@ -473,15 +476,16 @@ int nfp_bpf_event_output(struct nfp_app_bpf *bpf, const void *data,
 		return -EINVAL;
 
 	rcu_read_lock();
-	if (!rhashtable_lookup_fast(&bpf->maps_neutral, &map,
-				    nfp_bpf_maps_neutral_params)) {
+	record = rhashtable_lookup_fast(&bpf->maps_neutral, &map_id,
+					nfp_bpf_maps_neutral_params);
+	if (!record || map_id_full > U32_MAX) {
 		rcu_read_unlock();
-		pr_warn("perf event: dest map pointer %px not recognized, dropping event\n",
-			map);
+		cmsg_warn(bpf, "perf event: map id %lld (0x%llx) not recognized, dropping event\n",
+			  map_id_full, map_id_full);
 		return -EINVAL;
 	}
 
-	bpf_event_output(map, be32_to_cpu(cbe->cpu_id),
+	bpf_event_output(record->ptr, be32_to_cpu(cbe->cpu_id),
 			 &cbe->data[round_up(pkt_size, 4)], data_size,
 			 cbe->data, pkt_size, nfp_bpf_perf_event_copy);
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 17082566a9d2d05eefa3a5d6d968aa1d4b87c73d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Wed, 25 Jul 2018 19:53:35 -0700
Subject: nfp: bpf: improve map offload info messages

FW can put constraints on map element size to maximize resource
use and efficiency.  When user attempts offload of a map which
does not fit into those constraints an informational message is
printed to kernel logs to inform user about the reason offload
failed.  Map offload does not have access to any advanced error
reporting like verifier log or extack.  There is also currently
no way for us to nicely expose the FW capabilities to user
space.  Given all those constraints we should make sure log
messages are as informative as possible.  Improve them.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/offload.c | 20 ++++++++++++++++----
 1 file changed, 16 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
index b1fbb3babc7f..1ccd6371a15b 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c
@@ -380,11 +380,23 @@ nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap)
 			bpf->maps.max_elems - bpf->map_elems_in_use);
 		return -ENOMEM;
 	}
-	if (offmap->map.key_size > bpf->maps.max_key_sz ||
-	    offmap->map.value_size > bpf->maps.max_val_sz ||
-	    round_up(offmap->map.key_size, 8) +
+
+	if (round_up(offmap->map.key_size, 8) +
 	    round_up(offmap->map.value_size, 8) > bpf->maps.max_elem_sz) {
-		pr_info("elements don't fit in device constraints\n");
+		pr_info("map elements too large: %u, FW max element size (key+value): %u\n",
+			round_up(offmap->map.key_size, 8) +
+			round_up(offmap->map.value_size, 8),
+			bpf->maps.max_elem_sz);
+		return -ENOMEM;
+	}
+	if (offmap->map.key_size > bpf->maps.max_key_sz) {
+		pr_info("map key size %u, FW max is %u\n",
+			offmap->map.key_size, bpf->maps.max_key_sz);
+		return -ENOMEM;
+	}
+	if (offmap->map.value_size > bpf->maps.max_val_sz) {
+		pr_info("map value size %u, FW max is %u\n",
+			offmap->map.value_size, bpf->maps.max_val_sz);
 		return -ENOMEM;
 	}
 
-- 
cgit v1.2.3


From 1e960043e8ae65d6f53b3414586a3fb634461908 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 26 Jul 2018 14:32:18 -0700
Subject: tools: libbpf: handle NULL program gracefully in
 bpf_program__nth_fd()

bpf_map__fd() handles NULL map gracefully and returns -EINVAL.
bpf_program__fd() and bpf_program__nth_fd() crash in this case.
Make the behaviour more consistent by validating prog pointer
as well.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 955f8eafbf41..afa9860db755 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1991,6 +1991,9 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n)
 {
 	int fd;
 
+	if (!prog)
+		return -EINVAL;
+
 	if (n >= prog->instances.nr || n < 0) {
 		pr_warning("Can't get the %dth fd from program %s: only %d instances\n",
 			   n, prog->section_name, prog->instances.nr);
-- 
cgit v1.2.3


From 6d4b198b0b23ca2a75785173a9b27afd1eee7040 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 26 Jul 2018 14:32:19 -0700
Subject: tools: libbpf: add bpf_object__find_program_by_title()

Allow users to find programs by section names.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 12 ++++++++++++
 tools/lib/bpf/libbpf.h |  3 +++
 2 files changed, 15 insertions(+)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index afa9860db755..857d3d16968e 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -873,6 +873,18 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
 	return NULL;
 }
 
+struct bpf_program *
+bpf_object__find_program_by_title(struct bpf_object *obj, const char *title)
+{
+	struct bpf_program *pos;
+
+	bpf_object__for_each_program(pos, obj) {
+		if (pos->section_name && !strcmp(pos->section_name, title))
+			return pos;
+	}
+	return NULL;
+}
+
 static int
 bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr,
 			   Elf_Data *data, struct bpf_object *obj)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 1f8fc2060460..a295fe2f822b 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -86,6 +86,9 @@ const char *bpf_object__name(struct bpf_object *obj);
 unsigned int bpf_object__kversion(struct bpf_object *obj);
 int bpf_object__btf_fd(const struct bpf_object *obj);
 
+struct bpf_program *
+bpf_object__find_program_by_title(struct bpf_object *obj, const char *title);
+
 struct bpf_object *bpf_object__next(struct bpf_object *prev);
 #define bpf_object__for_each_safe(pos, tmp)			\
 	for ((pos) = bpf_object__next(NULL),		\
-- 
cgit v1.2.3


From e1a40ef418ca2d0ffb6d22f84a13cb0df66cf83c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 26 Jul 2018 14:32:20 -0700
Subject: samples: bpf: convert xdp_fwd_user.c to libbpf

Convert xdp_fwd_user.c to use libbpf instead of bpf_load.o.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/Makefile       |  2 +-
 samples/bpf/xdp_fwd_user.c | 34 +++++++++++++++++++++++-----------
 2 files changed, 24 insertions(+), 12 deletions(-)

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 77f512625b8c..815dec22729d 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -106,7 +106,7 @@ syscall_tp-objs := bpf_load.o syscall_tp_user.o
 cpustat-objs := bpf_load.o cpustat_user.o
 xdp_adjust_tail-objs := xdp_adjust_tail_user.o
 xdpsock-objs := bpf_load.o xdpsock_user.o
-xdp_fwd-objs := bpf_load.o xdp_fwd_user.o
+xdp_fwd-objs := xdp_fwd_user.o
 task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
 xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
 
diff --git a/samples/bpf/xdp_fwd_user.c b/samples/bpf/xdp_fwd_user.c
index a87a2048ed32..f88e1d7093d6 100644
--- a/samples/bpf/xdp_fwd_user.c
+++ b/samples/bpf/xdp_fwd_user.c
@@ -24,8 +24,7 @@
 #include <fcntl.h>
 #include <libgen.h>
 
-#include "bpf_load.h"
-#include "bpf_util.h"
+#include "bpf/libbpf.h"
 #include <bpf/bpf.h>
 
 
@@ -63,9 +62,15 @@ static void usage(const char *prog)
 
 int main(int argc, char **argv)
 {
+	struct bpf_prog_load_attr prog_load_attr = {
+		.prog_type	= BPF_PROG_TYPE_XDP,
+	};
+	const char *prog_name = "xdp_fwd";
+	struct bpf_program *prog;
 	char filename[PATH_MAX];
+	struct bpf_object *obj;
 	int opt, i, idx, err;
-	int prog_id = 0;
+	int prog_fd, map_fd;
 	int attach = 1;
 	int ret = 0;
 
@@ -75,7 +80,7 @@ int main(int argc, char **argv)
 			attach = 0;
 			break;
 		case 'D':
-			prog_id = 1;
+			prog_name = "xdp_fwd_direct";
 			break;
 		default:
 			usage(basename(argv[0]));
@@ -90,6 +95,7 @@ int main(int argc, char **argv)
 
 	if (attach) {
 		snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+		prog_load_attr.file = filename;
 
 		if (access(filename, O_RDONLY) < 0) {
 			printf("error accessing file %s: %s\n",
@@ -97,19 +103,25 @@ int main(int argc, char **argv)
 			return 1;
 		}
 
-		if (load_bpf_file(filename)) {
-			printf("%s", bpf_log_buf);
+		if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
 			return 1;
-		}
 
-		if (!prog_fd[prog_id]) {
-			printf("load_bpf_file: %s\n", strerror(errno));
+		prog = bpf_object__find_program_by_title(obj, prog_name);
+		prog_fd = bpf_program__fd(prog);
+		if (prog_fd < 0) {
+			printf("program not found: %s\n", strerror(prog_fd));
+			return 1;
+		}
+		map_fd = bpf_map__fd(bpf_object__find_map_by_name(obj,
+								  "tx_port"));
+		if (map_fd < 0) {
+			printf("map not found: %s\n", strerror(map_fd));
 			return 1;
 		}
 	}
 	if (attach) {
 		for (i = 1; i < 64; ++i)
-			bpf_map_update_elem(map_fd[0], &i, &i, 0);
+			bpf_map_update_elem(map_fd, &i, &i, 0);
 	}
 
 	for (i = optind; i < argc; ++i) {
@@ -126,7 +138,7 @@ int main(int argc, char **argv)
 			if (err)
 				ret = err;
 		} else {
-			err = do_attach(idx, prog_fd[prog_id], argv[i]);
+			err = do_attach(idx, prog_fd, argv[i]);
 			if (err)
 				ret = err;
 		}
-- 
cgit v1.2.3


From 6748182c2d1850811a577fe060387f83d5fa0fe4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 26 Jul 2018 14:32:21 -0700
Subject: samples: bpf: convert xdpsock_user.c to libbpf

Convert xdpsock_user.c to use libbpf instead of bpf_load.o.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/Makefile       |  2 +-
 samples/bpf/xdpsock_user.c | 38 +++++++++++++++++++++++++++++---------
 2 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 815dec22729d..f88d5683d6ee 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -105,7 +105,7 @@ xdp_rxq_info-objs := xdp_rxq_info_user.o
 syscall_tp-objs := bpf_load.o syscall_tp_user.o
 cpustat-objs := bpf_load.o cpustat_user.o
 xdp_adjust_tail-objs := xdp_adjust_tail_user.o
-xdpsock-objs := bpf_load.o xdpsock_user.o
+xdpsock-objs := xdpsock_user.o
 xdp_fwd-objs := xdp_fwd_user.o
 task_fd_query-objs := bpf_load.o task_fd_query_user.o $(TRACE_HELPERS)
 xdp_sample_pkts-objs := xdp_sample_pkts_user.o $(TRACE_HELPERS)
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 1e82f7c617c3..4914788b6727 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -26,7 +26,7 @@
 #include <sys/types.h>
 #include <poll.h>
 
-#include "bpf_load.h"
+#include "bpf/libbpf.h"
 #include "bpf_util.h"
 #include <bpf/bpf.h>
 
@@ -891,7 +891,13 @@ static void l2fwd(struct xdpsock *xsk)
 int main(int argc, char **argv)
 {
 	struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY};
+	struct bpf_prog_load_attr prog_load_attr = {
+		.prog_type	= BPF_PROG_TYPE_XDP,
+	};
+	int prog_fd, qidconf_map, xsks_map;
+	struct bpf_object *obj;
 	char xdp_filename[256];
+	struct bpf_map *map;
 	int i, ret, key = 0;
 	pthread_t pt;
 
@@ -904,24 +910,38 @@ int main(int argc, char **argv)
 	}
 
 	snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]);
+	prog_load_attr.file = xdp_filename;
 
-	if (load_bpf_file(xdp_filename)) {
-		fprintf(stderr, "ERROR: load_bpf_file %s\n", bpf_log_buf);
+	if (bpf_prog_load_xattr(&prog_load_attr, &obj, &prog_fd))
+		exit(EXIT_FAILURE);
+	if (prog_fd < 0) {
+		fprintf(stderr, "ERROR: no program found: %s\n",
+			strerror(prog_fd));
 		exit(EXIT_FAILURE);
 	}
 
-	if (!prog_fd[0]) {
-		fprintf(stderr, "ERROR: load_bpf_file: \"%s\"\n",
-			strerror(errno));
+	map = bpf_object__find_map_by_name(obj, "qidconf_map");
+	qidconf_map = bpf_map__fd(map);
+	if (qidconf_map < 0) {
+		fprintf(stderr, "ERROR: no qidconf map found: %s\n",
+			strerror(qidconf_map));
+		exit(EXIT_FAILURE);
+	}
+
+	map = bpf_object__find_map_by_name(obj, "xsks_map");
+	xsks_map = bpf_map__fd(map);
+	if (xsks_map < 0) {
+		fprintf(stderr, "ERROR: no xsks map found: %s\n",
+			strerror(xsks_map));
 		exit(EXIT_FAILURE);
 	}
 
-	if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd[0], opt_xdp_flags) < 0) {
+	if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd, opt_xdp_flags) < 0) {
 		fprintf(stderr, "ERROR: link set xdp fd failed\n");
 		exit(EXIT_FAILURE);
 	}
 
-	ret = bpf_map_update_elem(map_fd[0], &key, &opt_queue, 0);
+	ret = bpf_map_update_elem(qidconf_map, &key, &opt_queue, 0);
 	if (ret) {
 		fprintf(stderr, "ERROR: bpf_map_update_elem qidconf\n");
 		exit(EXIT_FAILURE);
@@ -938,7 +958,7 @@ int main(int argc, char **argv)
 	/* ...and insert them into the map. */
 	for (i = 0; i < num_socks; i++) {
 		key = i;
-		ret = bpf_map_update_elem(map_fd[1], &key, &xsks[i]->sfd, 0);
+		ret = bpf_map_update_elem(xsks_map, &key, &xsks[i]->sfd, 0);
 		if (ret) {
 			fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i);
 			exit(EXIT_FAILURE);
-- 
cgit v1.2.3


From d9b9170a26536e9bfe2994d60925e10d16d411dc Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 26 Jul 2018 15:03:02 +1000
Subject: docs: bpf: Rename README.rst to index.rst

Recently bpf/ docs were converted to use RST format.  'README.rst' was
created but in order to fit in with the Sphinx build system this file
should be named 'index.rst'.  Rename file, fixes to integrate into
Sphinx build system in following patches.

docs: Rename Documentation/bpf/README.rst to Documentation/bpf/index.rst

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 Documentation/bpf/README.rst | 36 ------------------------------------
 Documentation/bpf/index.rst  | 36 ++++++++++++++++++++++++++++++++++++
 2 files changed, 36 insertions(+), 36 deletions(-)
 delete mode 100644 Documentation/bpf/README.rst
 create mode 100644 Documentation/bpf/index.rst

diff --git a/Documentation/bpf/README.rst b/Documentation/bpf/README.rst
deleted file mode 100644
index b9a80c9e9392..000000000000
--- a/Documentation/bpf/README.rst
+++ /dev/null
@@ -1,36 +0,0 @@
-=================
-BPF documentation
-=================
-
-This directory contains documentation for the BPF (Berkeley Packet
-Filter) facility, with a focus on the extended BPF version (eBPF).
-
-This kernel side documentation is still work in progress.  The main
-textual documentation is (for historical reasons) described in
-`Documentation/networking/filter.txt`_, which describe both classical
-and extended BPF instruction-set.
-The Cilium project also maintains a `BPF and XDP Reference Guide`_
-that goes into great technical depth about the BPF Architecture.
-
-The primary info for the bpf syscall is available in the `man-pages`_
-for `bpf(2)`_.
-
-
-
-Frequently asked questions (FAQ)
-================================
-
-Two sets of Questions and Answers (Q&A) are maintained.
-
-* QA for common questions about BPF see: bpf_design_QA_
-
-* QA for developers interacting with BPF subsystem: bpf_devel_QA_
-
-
-.. Links:
-.. _bpf_design_QA: bpf_design_QA.rst
-.. _bpf_devel_QA:  bpf_devel_QA.rst
-.. _Documentation/networking/filter.txt: ../networking/filter.txt
-.. _man-pages: https://www.kernel.org/doc/man-pages/
-.. _bpf(2): http://man7.org/linux/man-pages/man2/bpf.2.html
-.. _BPF and XDP Reference Guide: http://cilium.readthedocs.io/en/latest/bpf/
diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
new file mode 100644
index 000000000000..b9a80c9e9392
--- /dev/null
+++ b/Documentation/bpf/index.rst
@@ -0,0 +1,36 @@
+=================
+BPF documentation
+=================
+
+This directory contains documentation for the BPF (Berkeley Packet
+Filter) facility, with a focus on the extended BPF version (eBPF).
+
+This kernel side documentation is still work in progress.  The main
+textual documentation is (for historical reasons) described in
+`Documentation/networking/filter.txt`_, which describe both classical
+and extended BPF instruction-set.
+The Cilium project also maintains a `BPF and XDP Reference Guide`_
+that goes into great technical depth about the BPF Architecture.
+
+The primary info for the bpf syscall is available in the `man-pages`_
+for `bpf(2)`_.
+
+
+
+Frequently asked questions (FAQ)
+================================
+
+Two sets of Questions and Answers (Q&A) are maintained.
+
+* QA for common questions about BPF see: bpf_design_QA_
+
+* QA for developers interacting with BPF subsystem: bpf_devel_QA_
+
+
+.. Links:
+.. _bpf_design_QA: bpf_design_QA.rst
+.. _bpf_devel_QA:  bpf_devel_QA.rst
+.. _Documentation/networking/filter.txt: ../networking/filter.txt
+.. _man-pages: https://www.kernel.org/doc/man-pages/
+.. _bpf(2): http://man7.org/linux/man-pages/man2/bpf.2.html
+.. _BPF and XDP Reference Guide: http://cilium.readthedocs.io/en/latest/bpf/
-- 
cgit v1.2.3


From b3d40f63d20bbaf78c6b6e9112cde604135e30e0 Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 26 Jul 2018 15:03:03 +1000
Subject: docs: bpf: Add toctree to index

Recently bpf/ docs were converted to us RST format.  bp/index.rst was
created out of README but toctree was not added to include files within
Documentation/bpf/

Add toctree to Documentation/bpf/index.rst

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 Documentation/bpf/index.rst | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index b9a80c9e9392..ab2ff13a809b 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -22,14 +22,14 @@ Frequently asked questions (FAQ)
 
 Two sets of Questions and Answers (Q&A) are maintained.
 
-* QA for common questions about BPF see: bpf_design_QA_
+.. toctree::
+   :maxdepth: 1
 
-* QA for developers interacting with BPF subsystem: bpf_devel_QA_
+   bpf_design_QA
+   bpf_devel_QA
 
 
 .. Links:
-.. _bpf_design_QA: bpf_design_QA.rst
-.. _bpf_devel_QA:  bpf_devel_QA.rst
 .. _Documentation/networking/filter.txt: ../networking/filter.txt
 .. _man-pages: https://www.kernel.org/doc/man-pages/
 .. _bpf(2): http://man7.org/linux/man-pages/man2/bpf.2.html
-- 
cgit v1.2.3


From 3209570da7a2dc80e3123dd837ced461f786e6dc Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 26 Jul 2018 15:03:04 +1000
Subject: docs: Add bpf/index to top level index

Recently bpf docs were converted to RST format.  The new files were not
added to the top level toctree.  This causes build system to emit a
warning of type

	WARNING: document isn't included in any toctree

Add bpf/index.rst to Documentation/index.rst

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 Documentation/index.rst | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/index.rst b/Documentation/index.rst
index fdc585703498..086710b054db 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -90,6 +90,7 @@ needed).
    crypto/index
    filesystems/index
    vm/index
+   bpf/index
 
 Architecture-specific documentation
 -----------------------------------
-- 
cgit v1.2.3


From 6919bcc8aa2755be934d38bb7d8d7aee14b27e1d Mon Sep 17 00:00:00 2001
From: "Tobin C. Harding" <me@tobin.cc>
Date: Thu, 26 Jul 2018 15:03:05 +1000
Subject: docs: bpf: Capitalise document heading

The majority of files in the kernel documentation index use
capitalisation for all words, especially the shorter ones.  BPF docs
better fit in with the rest of the documentation if the heading is all
capitalised.

Capitalise document heading.

Signed-off-by: Tobin C. Harding <me@tobin.cc>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 Documentation/bpf/index.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/bpf/index.rst b/Documentation/bpf/index.rst
index ab2ff13a809b..00a8450a602f 100644
--- a/Documentation/bpf/index.rst
+++ b/Documentation/bpf/index.rst
@@ -1,5 +1,5 @@
 =================
-BPF documentation
+BPF Documentation
 =================
 
 This directory contains documentation for the BPF (Berkeley Packet
-- 
cgit v1.2.3


From 50e9ffb1996a5d11ff5040a266585bad4ceeca0a Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 26 Jul 2018 14:27:59 +0200
Subject: ALSA: virmidi: Fix too long output trigger loop

The virmidi output trigger tries to parse the all available bytes and
process sequencer events as much as possible.  In a normal situation,
this is supposed to be relatively short, but a program may give a huge
buffer and it'll take a long time in a single spin lock, which may
eventually lead to a soft lockup.

This patch simply adds a workaround, a cond_resched() call in the loop
if applicable.  A better solution would be to move the event processor
into a work, but let's put a duct-tape quickly at first.

Reported-and-tested-by: Dae R. Jeong <threeearcat@gmail.com>
Reported-by: syzbot+619d9f40141d826b097e@syzkaller.appspotmail.com
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_virmidi.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 289ae6bb81d9..8ebbca554e99 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -163,6 +163,7 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream,
 	int count, res;
 	unsigned char buf[32], *pbuf;
 	unsigned long flags;
+	bool check_resched = !in_atomic();
 
 	if (up) {
 		vmidi->trigger = 1;
@@ -200,6 +201,15 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream,
 					vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
 				}
 			}
+			if (!check_resched)
+				continue;
+			/* do temporary unlock & cond_resched() for avoiding
+			 * CPU soft lockup, which may happen via a write from
+			 * a huge rawmidi buffer
+			 */
+			spin_unlock_irqrestore(&substream->runtime->lock, flags);
+			cond_resched();
+			spin_lock_irqsave(&substream->runtime->lock, flags);
 		}
 	out:
 		spin_unlock_irqrestore(&substream->runtime->lock, flags);
-- 
cgit v1.2.3


From a6ea5fe95ab4a1a7af6d57429fe3ecde9acf5b5a Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:36 +0200
Subject: ALSA: hda: Fix implicit PCM format type conversion

The PCM format type is defined with __bitwise, hence it can't be
passed as integer but needs an explicit cast.  In this patch, instead
of the messy cast flood, define the format argument of
snd_hdac_calc_stream_format() to be the proper snd_pcm_format_t type.

This fixes sparse warnings like:
  sound/hda/hdac_device.c:760:38: warning: incorrect type in argument 1 (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/hdaudio.h | 3 ++-
 sound/hda/hdac_device.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/sound/hdaudio.h b/include/sound/hdaudio.h
index 8305e7971035..6f1e1f3b3063 100644
--- a/include/sound/hdaudio.h
+++ b/include/sound/hdaudio.h
@@ -11,6 +11,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/timecounter.h>
 #include <sound/core.h>
+#include <sound/pcm.h>
 #include <sound/memalloc.h>
 #include <sound/hda_verbs.h>
 #include <drm/i915_component.h>
@@ -133,7 +134,7 @@ int snd_hdac_get_sub_nodes(struct hdac_device *codec, hda_nid_t nid,
 			   hda_nid_t *start_id);
 unsigned int snd_hdac_calc_stream_format(unsigned int rate,
 					 unsigned int channels,
-					 unsigned int format,
+					 snd_pcm_format_t format,
 					 unsigned int maxbps,
 					 unsigned short spdif_ctls);
 int snd_hdac_query_supported_pcm(struct hdac_device *codec, hda_nid_t nid,
diff --git a/sound/hda/hdac_device.c b/sound/hda/hdac_device.c
index 7ba100bb1c3f..dbf02a3a8d2f 100644
--- a/sound/hda/hdac_device.c
+++ b/sound/hda/hdac_device.c
@@ -738,7 +738,7 @@ static struct hda_rate_tbl rate_bits[] = {
  */
 unsigned int snd_hdac_calc_stream_format(unsigned int rate,
 					 unsigned int channels,
-					 unsigned int format,
+					 snd_pcm_format_t format,
 					 unsigned int maxbps,
 					 unsigned short spdif_ctls)
 {
-- 
cgit v1.2.3


From 94dfee0c1a33baa974cba0bd8b83021b1d801297 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:37 +0200
Subject: ALSA: riptide: Fix PCM format type conversion

The PCM format type is with __bitwise, hence it needs to be explicitly
declared as snd_pcm_format_t, as warned by sparse:
  sound/pci/riptide/riptide.c:1028:34: warning: incorrect type in argument 1 (different base types)
  sound/pci/riptide/riptide.c:1028:34:    expected restricted snd_pcm_format_t [usertype] format
  sound/pci/riptide/riptide.c:1028:34:    got unsigned char [unsigned] format

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/riptide/riptide.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index 44f3b48d47b1..9d2b2ef15c6b 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -1017,7 +1017,7 @@ getsamplerate(struct cmdif *cif, unsigned char *intdec, unsigned int *rate)
 static int
 setsampleformat(struct cmdif *cif,
 		unsigned char mixer, unsigned char id,
-		unsigned char channels, unsigned char format)
+		unsigned char channels, snd_pcm_format_t format)
 {
 	unsigned char w, ch, sig, order;
 
-- 
cgit v1.2.3


From f8b6c0cfbdd7359db9bb4da38dd54217296f9264 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:38 +0200
Subject: ALSA: pcm: Fix sparse warning wrt PCM format type

The PCM format type is with __bitwise, hence it needs the explicit
cast with __force.  It's ugly, but there is a reason for that cost...

This fixes the sparse warning:
  sound/core/oss/pcm_oss.c:1854:55: warning: incorrect type in argument 1 (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/oss/pcm_oss.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/core/oss/pcm_oss.c b/sound/core/oss/pcm_oss.c
index 905a53c1cde5..f8d4a419f3af 100644
--- a/sound/core/oss/pcm_oss.c
+++ b/sound/core/oss/pcm_oss.c
@@ -1851,7 +1851,7 @@ static int snd_pcm_oss_get_formats(struct snd_pcm_oss_file *pcm_oss_file)
 	format_mask = hw_param_mask_c(params, SNDRV_PCM_HW_PARAM_FORMAT);
 	for (fmt = 0; fmt < 32; ++fmt) {
 		if (snd_mask_test(format_mask, fmt)) {
-			int f = snd_pcm_oss_format_to(fmt);
+			int f = snd_pcm_oss_format_to((__force snd_pcm_format_t)fmt);
 			if (f >= 0)
 				formats |= f;
 		}
-- 
cgit v1.2.3


From d63f33d3f083bdb3a7c2dfd623f4d811b2a8d772 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:39 +0200
Subject: ALSA: ad1816a: Fix sparse warning wrt PCM format type

The PCM format type is with __bitwise, and it can't be converted from
integer implicitly.  Instead of an ugly cast, declare the function
argument of snd_ad1816a_get_format() with the proper snd_pcm_format_t
type.

This fixes the sparse warning like:
  sound/isa/ad1816a/ad1816a_lib.c:93:14: warning: restricted snd_pcm_format_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/ad1816a/ad1816a_lib.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/isa/ad1816a/ad1816a_lib.c b/sound/isa/ad1816a/ad1816a_lib.c
index 923201414469..fba6d22f7f4b 100644
--- a/sound/isa/ad1816a/ad1816a_lib.c
+++ b/sound/isa/ad1816a/ad1816a_lib.c
@@ -85,7 +85,8 @@ static void snd_ad1816a_write_mask(struct snd_ad1816a *chip, unsigned char reg,
 
 
 static unsigned char snd_ad1816a_get_format(struct snd_ad1816a *chip,
-					    unsigned int format, int channels)
+					    snd_pcm_format_t format,
+					    int channels)
 {
 	unsigned char retval = AD1816A_FMT_LINEAR_8;
 
-- 
cgit v1.2.3


From 10d3d91e3bc4e152a580bf523e4fd6bf279ae532 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:40 +0200
Subject: ALSA: au88x0: Fix sparse warning wrt PCM format type

The PCM format type is with __bitwise, and it can't be converted from
integer implicitly.  Instead of an ugly cast, declare the function
argument of vortex_alsafmt_aspfmt() with the proper snd_pcm_format_t
type.

This fixes the sparse warning like:
  sound/pci/au88x0/au88x0_core.c:2778:14: warning: restricted snd_pcm_format_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/au88x0/au88x0.h      | 2 +-
 sound/pci/au88x0/au88x0_core.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/au88x0/au88x0.h b/sound/pci/au88x0/au88x0.h
index bcc648bf6478..e3e31f07d766 100644
--- a/sound/pci/au88x0/au88x0.h
+++ b/sound/pci/au88x0/au88x0.h
@@ -241,7 +241,7 @@ static int vortex_core_init(vortex_t * card);
 static int vortex_core_shutdown(vortex_t * card);
 static void vortex_enable_int(vortex_t * card);
 static irqreturn_t vortex_interrupt(int irq, void *dev_id);
-static int vortex_alsafmt_aspfmt(int alsafmt, vortex_t *v);
+static int vortex_alsafmt_aspfmt(snd_pcm_format_t alsafmt, vortex_t *v);
 
 /* Connection  stuff. */
 static void vortex_connect_default(vortex_t * vortex, int en);
diff --git a/sound/pci/au88x0/au88x0_core.c b/sound/pci/au88x0/au88x0_core.c
index 4083c8b01619..2e5b460a847c 100644
--- a/sound/pci/au88x0/au88x0_core.c
+++ b/sound/pci/au88x0/au88x0_core.c
@@ -2770,7 +2770,7 @@ static int vortex_core_shutdown(vortex_t * vortex)
 
 /* Alsa support. */
 
-static int vortex_alsafmt_aspfmt(int alsafmt, vortex_t *v)
+static int vortex_alsafmt_aspfmt(snd_pcm_format_t alsafmt, vortex_t *v)
 {
 	int fmt;
 
-- 
cgit v1.2.3


From a91a0e774984aa57090c39dc3269a812417737ed Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:41 +0200
Subject: ALSA: asihpi: Fix PCM format notations

asihpi driver treats -1 as an own invalid PCM format, but this needs
a proper cast with __force prefix since PCM format type is __bitwise.
Define a constant with the proper type and use it allover.

This fixes sparse warnings like:
  sound/pci/asihpi/asihpi.c:315:9: warning: incorrect type in initializer (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/asihpi/asihpi.c | 24 +++++++++++++-----------
 1 file changed, 13 insertions(+), 11 deletions(-)

diff --git a/sound/pci/asihpi/asihpi.c b/sound/pci/asihpi/asihpi.c
index 64e0961f93ba..a31fe1550903 100644
--- a/sound/pci/asihpi/asihpi.c
+++ b/sound/pci/asihpi/asihpi.c
@@ -311,27 +311,29 @@ static void print_hwparams(struct snd_pcm_substream *substream,
 		snd_pcm_format_width(params_format(p)) / 8);
 }
 
+#define INVALID_FORMAT	(__force snd_pcm_format_t)(-1)
+
 static snd_pcm_format_t hpi_to_alsa_formats[] = {
-	-1,			/* INVALID */
+	INVALID_FORMAT,		/* INVALID */
 	SNDRV_PCM_FORMAT_U8,	/* HPI_FORMAT_PCM8_UNSIGNED        1 */
 	SNDRV_PCM_FORMAT_S16,	/* HPI_FORMAT_PCM16_SIGNED         2 */
-	-1,			/* HPI_FORMAT_MPEG_L1              3 */
+	INVALID_FORMAT,		/* HPI_FORMAT_MPEG_L1              3 */
 	SNDRV_PCM_FORMAT_MPEG,	/* HPI_FORMAT_MPEG_L2              4 */
 	SNDRV_PCM_FORMAT_MPEG,	/* HPI_FORMAT_MPEG_L3              5 */
-	-1,			/* HPI_FORMAT_DOLBY_AC2            6 */
-	-1,			/* HPI_FORMAT_DOLBY_AC3            7 */
+	INVALID_FORMAT,		/* HPI_FORMAT_DOLBY_AC2            6 */
+	INVALID_FORMAT,		/* HPI_FORMAT_DOLBY_AC3            7 */
 	SNDRV_PCM_FORMAT_S16_BE,/* HPI_FORMAT_PCM16_BIGENDIAN      8 */
-	-1,			/* HPI_FORMAT_AA_TAGIT1_HITS       9 */
-	-1,			/* HPI_FORMAT_AA_TAGIT1_INSERTS   10 */
+	INVALID_FORMAT,		/* HPI_FORMAT_AA_TAGIT1_HITS       9 */
+	INVALID_FORMAT,		/* HPI_FORMAT_AA_TAGIT1_INSERTS   10 */
 	SNDRV_PCM_FORMAT_S32,	/* HPI_FORMAT_PCM32_SIGNED        11 */
-	-1,			/* HPI_FORMAT_RAW_BITSTREAM       12 */
-	-1,			/* HPI_FORMAT_AA_TAGIT1_HITS_EX1  13 */
+	INVALID_FORMAT,		/* HPI_FORMAT_RAW_BITSTREAM       12 */
+	INVALID_FORMAT,		/* HPI_FORMAT_AA_TAGIT1_HITS_EX1  13 */
 	SNDRV_PCM_FORMAT_FLOAT,	/* HPI_FORMAT_PCM32_FLOAT         14 */
 #if 1
 	/* ALSA can't handle 3 byte sample size together with power-of-2
 	 *  constraint on buffer_bytes, so disable this format
 	 */
-	-1
+	INVALID_FORMAT
 #else
 	/* SNDRV_PCM_FORMAT_S24_3LE */ /* HPI_FORMAT_PCM24_SIGNED 15 */
 #endif
@@ -1023,7 +1025,7 @@ static u64 snd_card_asihpi_playback_formats(struct snd_card_asihpi *asihpi,
 					format, sample_rate, 128000, 0);
 		if (!err)
 			err = hpi_outstream_query_format(h_stream, &hpi_format);
-		if (!err && (hpi_to_alsa_formats[format] != -1))
+		if (!err && (hpi_to_alsa_formats[format] != INVALID_FORMAT))
 			formats |= pcm_format_to_bits(hpi_to_alsa_formats[format]);
 	}
 	return formats;
@@ -1205,7 +1207,7 @@ static u64 snd_card_asihpi_capture_formats(struct snd_card_asihpi *asihpi,
 					format, sample_rate, 128000, 0);
 		if (!err)
 			err = hpi_instream_query_format(h_stream, &hpi_format);
-		if (!err && (hpi_to_alsa_formats[format] != -1))
+		if (!err && (hpi_to_alsa_formats[format] != INVALID_FORMAT))
 			formats |= pcm_format_to_bits(hpi_to_alsa_formats[format]);
 	}
 	return formats;
-- 
cgit v1.2.3


From 6be9a60efb401487a4d658ef23d652a9e6860b34 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:42 +0200
Subject: ALSA: wss: Fix sparse warning wrt PCM format type

The PCM format type is with __bitwise, and it can't be converted from
integer implicitly.  Instead of an ugly cast, declare the function
argument of snd_wss_get_format() with the proper snd_pcm_format_t
type.

This fixes the sparse warnings like:
  sound/isa/wss/wss_lib.c:551:14: warning: restricted snd_pcm_format_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/wss/wss_lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c
index 8a852042a066..d23cc8abe1ef 100644
--- a/sound/isa/wss/wss_lib.c
+++ b/sound/isa/wss/wss_lib.c
@@ -541,7 +541,7 @@ static unsigned char snd_wss_get_rate(unsigned int rate)
 }
 
 static unsigned char snd_wss_get_format(struct snd_wss *chip,
-					int format,
+					snd_pcm_format_t format,
 					int channels)
 {
 	unsigned char rformat;
-- 
cgit v1.2.3


From 55ff2d1ea5487fe131cce399baf4503dcf5cc8e1 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:43 +0200
Subject: ALSA: sb: Fix PCM format bit calculation

The PCM format type in snd_pcm_format_t can't be treated as integer
implicitly since it's with __bitwise.  We have already a helper
function to get the bit index of the given type, and use it in each
place instead.

This fixes sparse warnings like:
  sound/isa/sb/sb16_main.c:61:44: warning: restricted snd_pcm_format_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/sb16_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index 3e39ba220c39..11ed4a6e5bf1 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -49,6 +49,9 @@ MODULE_AUTHOR("Jaroslav Kysela <perex@perex.cz>");
 MODULE_DESCRIPTION("Routines for control of 16-bit SoundBlaster cards and clones");
 MODULE_LICENSE("GPL");
 
+#define runtime_format_bits(runtime) \
+	((unsigned int)pcm_format_to_bits((runtime)->format))
+
 #ifdef CONFIG_SND_SB16_CSP
 static void snd_sb16_csp_playback_prepare(struct snd_sb *chip, struct snd_pcm_runtime *runtime)
 {
@@ -58,7 +61,7 @@ static void snd_sb16_csp_playback_prepare(struct snd_sb *chip, struct snd_pcm_ru
 		if (csp->running & SNDRV_SB_CSP_ST_LOADED) {
 			/* manually loaded codec */
 			if ((csp->mode & SNDRV_SB_CSP_MODE_DSP_WRITE) &&
-			    ((1U << runtime->format) == csp->acc_format)) {
+			    (runtime_format_bits(runtime) == csp->acc_format)) {
 				/* Supported runtime PCM format for playback */
 				if (csp->ops.csp_use(csp) == 0) {
 					/* If CSP was successfully acquired */
@@ -66,7 +69,7 @@ static void snd_sb16_csp_playback_prepare(struct snd_sb *chip, struct snd_pcm_ru
 				}
 			} else if ((csp->mode & SNDRV_SB_CSP_MODE_QSOUND) && (csp->q_enabled)) {
 				/* QSound decoder is loaded and enabled */
-				if ((1 << runtime->format) & (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_U8 |
+				if (runtime_format_bits(runtime) & (SNDRV_PCM_FMTBIT_S8 | SNDRV_PCM_FMTBIT_U8 |
 							      SNDRV_PCM_FMTBIT_S16_LE | SNDRV_PCM_FMTBIT_U16_LE)) {
 					/* Only for simple PCM formats */
 					if (csp->ops.csp_use(csp) == 0) {
@@ -106,7 +109,7 @@ static void snd_sb16_csp_capture_prepare(struct snd_sb *chip, struct snd_pcm_run
 		if (csp->running & SNDRV_SB_CSP_ST_LOADED) {
 			/* manually loaded codec */
 			if ((csp->mode & SNDRV_SB_CSP_MODE_DSP_READ) &&
-			    ((1U << runtime->format) == csp->acc_format)) {
+			    (runtime_format_bits(runtime) == csp->acc_format)) {
 				/* Supported runtime PCM format for capture */
 				if (csp->ops.csp_use(csp) == 0) {
 					/* If CSP was successfully acquired */
-- 
cgit v1.2.3


From e5d3765b6c4cb3ba64295a4205a2f68a4e8fe083 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:44 +0200
Subject: ALSA: sb: Fix sparse warning wrt PCM format type

The PCM format type is with __bitwise, and it can't be converted from
integer implicitly.  Instead of an ugly cast, declare the function
argument of snd_sb_csp_autoload() with the proper snd_pcm_format_t
type.

This fixes the sparse warnings like:
  sound/isa/sb/sb16_csp.c:743:22: warning: restricted snd_pcm_format_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/sb16_csp.h | 2 +-
 sound/isa/sb/sb16_csp.c  | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/sound/sb16_csp.h b/include/sound/sb16_csp.h
index c7c7788005e4..7817e88bd08d 100644
--- a/include/sound/sb16_csp.h
+++ b/include/sound/sb16_csp.h
@@ -46,7 +46,7 @@ enum {
 struct snd_sb_csp_ops {
 	int (*csp_use) (struct snd_sb_csp * p);
 	int (*csp_unuse) (struct snd_sb_csp * p);
-	int (*csp_autoload) (struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode);
+	int (*csp_autoload) (struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode);
 	int (*csp_start) (struct snd_sb_csp * p, int sample_width, int channels);
 	int (*csp_stop) (struct snd_sb_csp * p);
 	int (*csp_qsound_transfer) (struct snd_sb_csp * p);
diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c
index fa5780bb0c68..2210e7c72787 100644
--- a/sound/isa/sb/sb16_csp.c
+++ b/sound/isa/sb/sb16_csp.c
@@ -93,7 +93,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 				struct snd_sb_csp_microcode __user * code);
 static int snd_sb_csp_unload(struct snd_sb_csp * p);
 static int snd_sb_csp_load_user(struct snd_sb_csp * p, const unsigned char __user *buf, int size, int load_flags);
-static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode);
+static int snd_sb_csp_autoload(struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode);
 static int snd_sb_csp_check_version(struct snd_sb_csp * p);
 
 static int snd_sb_csp_use(struct snd_sb_csp * p);
@@ -726,7 +726,7 @@ static int snd_sb_csp_firmware_load(struct snd_sb_csp *p, int index, int flags)
  * autoload hardware codec if necessary
  * return 0 if CSP is loaded and ready to run (p->running != 0)
  */
-static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec_mode)
+static int snd_sb_csp_autoload(struct snd_sb_csp * p, snd_pcm_format_t pcm_sfmt, int play_rec_mode)
 {
 	unsigned long flags;
 	int err = 0;
@@ -736,7 +736,7 @@ static int snd_sb_csp_autoload(struct snd_sb_csp * p, int pcm_sfmt, int play_rec
 		return -EBUSY;
 
 	/* autoload microcode only if requested hardware codec is not already loaded */
-	if (((1 << pcm_sfmt) & p->acc_format) && (play_rec_mode & p->mode)) {
+	if (((1U << (__force int)pcm_sfmt) & p->acc_format) && (play_rec_mode & p->mode)) {
 		p->running = SNDRV_SB_CSP_ST_AUTO;
 	} else {
 		switch (pcm_sfmt) {
-- 
cgit v1.2.3


From 3ac14b3960185d4c8a2f14b84042aa1aa8531d88 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:19:45 +0200
Subject: ALSA: xen: Use standard pcm_format_to_bits() for ALSA format bits

The open codes with the bit shift in xen_snd_front_alsa.c give sparse
warnings as the PCM format type is with __bitwise.
There is already a standard macro to get the format bits, so let's use
it instead.

This fixes sparse warnings like:
  sound/xen/xen_snd_front_alsa.c:191:47: warning: restricted snd_pcm_format_t degrades to integer

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/xen/xen_snd_front_alsa.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/xen/xen_snd_front_alsa.c b/sound/xen/xen_snd_front_alsa.c
index 5a2bd70a2fa1..129180e17db1 100644
--- a/sound/xen/xen_snd_front_alsa.c
+++ b/sound/xen/xen_snd_front_alsa.c
@@ -188,7 +188,7 @@ static u64 to_sndif_formats_mask(u64 alsa_formats)
 
 	mask = 0;
 	for (i = 0; i < ARRAY_SIZE(ALSA_SNDIF_FORMATS); i++)
-		if (1 << ALSA_SNDIF_FORMATS[i].alsa & alsa_formats)
+		if (pcm_format_to_bits(ALSA_SNDIF_FORMATS[i].alsa) & alsa_formats)
 			mask |= 1 << ALSA_SNDIF_FORMATS[i].sndif;
 
 	return mask;
@@ -202,7 +202,7 @@ static u64 to_alsa_formats_mask(u64 sndif_formats)
 	mask = 0;
 	for (i = 0; i < ARRAY_SIZE(ALSA_SNDIF_FORMATS); i++)
 		if (1 << ALSA_SNDIF_FORMATS[i].sndif & sndif_formats)
-			mask |= 1 << ALSA_SNDIF_FORMATS[i].alsa;
+			mask |= pcm_format_to_bits(ALSA_SNDIF_FORMATS[i].alsa);
 
 	return mask;
 }
-- 
cgit v1.2.3


From d3c637632da95d7646053c64b855641cd917960e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:01 +0200
Subject: ALSA: ymfpci: Proper endian notations

The bank values are all little-endians, so they should be defined with
__le32.  This fixes lots of sparse warnings like:
  sound/pci/ymfpci/ymfpci_main.c:315:23: warning: cast to restricted __le32
  sound/pci/ymfpci/ymfpci_main.c:342:32: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ymfpci/ymfpci.h      | 78 +++++++++++++++++++++---------------------
 sound/pci/ymfpci/ymfpci_main.c |  6 ++--
 2 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/sound/pci/ymfpci/ymfpci.h b/sound/pci/ymfpci/ymfpci.h
index aa9bb065f385..e2fa7e360d79 100644
--- a/sound/pci/ymfpci/ymfpci.h
+++ b/sound/pci/ymfpci/ymfpci.h
@@ -185,50 +185,50 @@
  */
 
 struct snd_ymfpci_playback_bank {
-	u32 format;
-	u32 loop_default;
-	u32 base;			/* 32-bit address */
-	u32 loop_start;			/* 32-bit offset */
-	u32 loop_end;			/* 32-bit offset */
-	u32 loop_frac;			/* 8-bit fraction - loop_start */
-	u32 delta_end;			/* pitch delta end */
-	u32 lpfK_end;
-	u32 eg_gain_end;
-	u32 left_gain_end;
-	u32 right_gain_end;
-	u32 eff1_gain_end;
-	u32 eff2_gain_end;
-	u32 eff3_gain_end;
-	u32 lpfQ;
-	u32 status;
-	u32 num_of_frames;
-	u32 loop_count;
-	u32 start;
-	u32 start_frac;
-	u32 delta;
-	u32 lpfK;
-	u32 eg_gain;
-	u32 left_gain;
-	u32 right_gain;
-	u32 eff1_gain;
-	u32 eff2_gain;
-	u32 eff3_gain;
-	u32 lpfD1;
-	u32 lpfD2;
+	__le32 format;
+	__le32 loop_default;
+	__le32 base;			/* 32-bit address */
+	__le32 loop_start;		/* 32-bit offset */
+	__le32 loop_end;		/* 32-bit offset */
+	__le32 loop_frac;		/* 8-bit fraction - loop_start */
+	__le32 delta_end;		/* pitch delta end */
+	__le32 lpfK_end;
+	__le32 eg_gain_end;
+	__le32 left_gain_end;
+	__le32 right_gain_end;
+	__le32 eff1_gain_end;
+	__le32 eff2_gain_end;
+	__le32 eff3_gain_end;
+	__le32 lpfQ;
+	__le32 status;
+	__le32 num_of_frames;
+	__le32 loop_count;
+	__le32 start;
+	__le32 start_frac;
+	__le32 delta;
+	__le32 lpfK;
+	__le32 eg_gain;
+	__le32 left_gain;
+	__le32 right_gain;
+	__le32 eff1_gain;
+	__le32 eff2_gain;
+	__le32 eff3_gain;
+	__le32 lpfD1;
+	__le32 lpfD2;
  };
 
 struct snd_ymfpci_capture_bank {
-	u32 base;			/* 32-bit address */
-	u32 loop_end;			/* 32-bit offset */
-	u32 start;			/* 32-bit offset */
-	u32 num_of_loops;		/* counter */
+	__le32 base;			/* 32-bit address */
+	__le32 loop_end;		/* 32-bit offset */
+	__le32 start;			/* 32-bit offset */
+	__le32 num_of_loops;		/* counter */
 };
 
 struct snd_ymfpci_effect_bank {
-	u32 base;			/* 32-bit address */
-	u32 loop_end;			/* 32-bit offset */
-	u32 start;			/* 32-bit offset */
-	u32 temp;
+	__le32 base;			/* 32-bit address */
+	__le32 loop_end;		/* 32-bit offset */
+	__le32 start;			/* 32-bit offset */
+	__le32 temp;
 };
 
 struct snd_ymfpci_pcm;
@@ -316,7 +316,7 @@ struct snd_ymfpci {
 	dma_addr_t work_base_addr;
 	struct snd_dma_buffer ac3_tmp_base;
 
-	u32 *ctrl_playback;
+	__le32 *ctrl_playback;
 	struct snd_ymfpci_playback_bank *bank_playback[YDSXG_PLAYBACK_VOICES][2];
 	struct snd_ymfpci_capture_bank *bank_capture[YDSXG_CAPTURE_VOICES][2];
 	struct snd_ymfpci_effect_bank *bank_effect[YDSXG_EFFECT_VOICES][2];
diff --git a/sound/pci/ymfpci/ymfpci_main.c b/sound/pci/ymfpci/ymfpci_main.c
index 6f81396aadc9..a4926fb03991 100644
--- a/sound/pci/ymfpci/ymfpci_main.c
+++ b/sound/pci/ymfpci/ymfpci_main.c
@@ -336,7 +336,7 @@ static void snd_ymfpci_pcm_interrupt(struct snd_ymfpci *chip, struct snd_ymfpci_
 			unsigned int subs = ypcm->substream->number;
 			unsigned int next_bank = 1 - chip->active_bank;
 			struct snd_ymfpci_playback_bank *bank;
-			u32 volume;
+			__le32 volume;
 			
 			bank = &voice->bank[next_bank];
 			volume = cpu_to_le32(chip->pcm_mixer[subs].left << 15);
@@ -505,7 +505,7 @@ static void snd_ymfpci_pcm_init_voice(struct snd_ymfpci_pcm *ypcm, unsigned int
 	u32 lpfK = snd_ymfpci_calc_lpfK(runtime->rate);
 	struct snd_ymfpci_playback_bank *bank;
 	unsigned int nbank;
-	u32 vol_left, vol_right;
+	__le32 vol_left, vol_right;
 	u8 use_left, use_right;
 	unsigned long flags;
 
@@ -2135,7 +2135,7 @@ static int snd_ymfpci_memalloc(struct snd_ymfpci *chip)
 
 	chip->bank_base_playback = ptr;
 	chip->bank_base_playback_addr = ptr_addr;
-	chip->ctrl_playback = (u32 *)ptr;
+	chip->ctrl_playback = (__le32 *)ptr;
 	chip->ctrl_playback[0] = cpu_to_le32(YDSXG_PLAYBACK_VOICES);
 	ptr += ALIGN(playback_ctrl_size, 0x100);
 	ptr_addr += ALIGN(playback_ctrl_size, 0x100);
-- 
cgit v1.2.3


From 752089fea357b36ba9dd477db594bdc677110579 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:02 +0200
Subject: ALSA: trident: Proper endian notations

The TLB entries in Trident driver are represented in little-endian,
hence they should be declared as __le32.

This patch fixes the sparse warnings like:
  sound/pci/trident/trident_memory.c:226:17: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/trident/trident.h      | 2 +-
 sound/pci/trident/trident_main.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/trident/trident.h b/sound/pci/trident/trident.h
index 9624e5937719..2d62c1921255 100644
--- a/sound/pci/trident/trident.h
+++ b/sound/pci/trident/trident.h
@@ -264,7 +264,7 @@ struct snd_trident_memblk_arg {
 };
 
 struct snd_trident_tlb {
-	unsigned int * entries;		/* 16k-aligned TLB table */
+	__le32 *entries;		/* 16k-aligned TLB table */
 	dma_addr_t entries_dmaaddr;	/* 16k-aligned PCI address to TLB table */
 	unsigned long * shadow_entries;	/* shadow entries with virtual addresses */
 	struct snd_dma_buffer buffer;
diff --git a/sound/pci/trident/trident_main.c b/sound/pci/trident/trident_main.c
index 49c64fae3466..5523e193d556 100644
--- a/sound/pci/trident/trident_main.c
+++ b/sound/pci/trident/trident_main.c
@@ -3359,7 +3359,7 @@ static int snd_trident_tlb_alloc(struct snd_trident *trident)
 		dev_err(trident->card->dev, "unable to allocate TLB buffer\n");
 		return -ENOMEM;
 	}
-	trident->tlb.entries = (unsigned int*)ALIGN((unsigned long)trident->tlb.buffer.area, SNDRV_TRIDENT_MAX_PAGES * 4);
+	trident->tlb.entries = (__le32 *)ALIGN((unsigned long)trident->tlb.buffer.area, SNDRV_TRIDENT_MAX_PAGES * 4);
 	trident->tlb.entries_dmaaddr = ALIGN(trident->tlb.buffer.addr, SNDRV_TRIDENT_MAX_PAGES * 4);
 	/* allocate shadow TLB page table (virtual addresses) */
 	trident->tlb.shadow_entries =
-- 
cgit v1.2.3


From 7362b0fca5de9570b5ba7bce5034105028daa599 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:03 +0200
Subject: ALSA: hda: Proper endian notations for BDL pointers

The BDL pointer used in snd_hdac_dsp_prepare() should be declared as
__le32, as warned by sparse:
  sound/hda/hdac_stream.c:655:47: warning: incorrect type in argument 4 (different base types)
  sound/hda/hdac_stream.c:655:47:    expected restricted __le32 [usertype] **bdlp
  sound/hda/hdac_stream.c:655:47:    got unsigned int [usertype] **<noident>

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/hda/hdac_stream.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c
index e1472c7ab6c1..eee422390d8e 100644
--- a/sound/hda/hdac_stream.c
+++ b/sound/hda/hdac_stream.c
@@ -621,7 +621,7 @@ int snd_hdac_dsp_prepare(struct hdac_stream *azx_dev, unsigned int format,
 			 unsigned int byte_size, struct snd_dma_buffer *bufp)
 {
 	struct hdac_bus *bus = azx_dev->bus;
-	u32 *bdl;
+	__le32 *bdl;
 	int err;
 
 	snd_hdac_dsp_lock(azx_dev);
@@ -651,7 +651,7 @@ int snd_hdac_dsp_prepare(struct hdac_stream *azx_dev, unsigned int format,
 	snd_hdac_stream_writel(azx_dev, SD_BDLPU, 0);
 
 	azx_dev->frags = 0;
-	bdl = (u32 *)azx_dev->bdl.area;
+	bdl = (__le32 *)azx_dev->bdl.area;
 	err = setup_bdle(bus, bufp, azx_dev, &bdl, 0, byte_size, 0);
 	if (err < 0)
 		goto error;
-- 
cgit v1.2.3


From be05e3de3a933156d472127f659d4473c461dcc5 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:04 +0200
Subject: ALSA: riptide: Properly endian notations

The SG descriptor of Riptide contains the little-endian values, hence
we need to define with __le32 properly.  This fixes sparse warnings
like:
  sound/pci/riptide/riptide.c:1112:40: warning: cast to restricted __le32

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/riptide/riptide.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/pci/riptide/riptide.c b/sound/pci/riptide/riptide.c
index 9d2b2ef15c6b..23017e3bc76c 100644
--- a/sound/pci/riptide/riptide.c
+++ b/sound/pci/riptide/riptide.c
@@ -470,10 +470,10 @@ struct snd_riptide {
 };
 
 struct sgd {			/* scatter gather desriptor */
-	u32 dwNextLink;
-	u32 dwSegPtrPhys;
-	u32 dwSegLen;
-	u32 dwStat_Ctl;
+	__le32 dwNextLink;
+	__le32 dwSegPtrPhys;
+	__le32 dwSegLen;
+	__le32 dwStat_Ctl;
 };
 
 struct pcmhw {			/* pcm descriptor */
-- 
cgit v1.2.3


From 0e7ca66a97c3bbf0b7665010d1b1d6a8c8e3811e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:05 +0200
Subject: ALSA: mixart: Proper endian notations

The miXart driver deals with big-endian values as raw data, while it
declares most of variables as u32.  This leads to sparse warnings like
  sound/pci/mixart/mixart.c:1203:23: warning: cast to restricted __be32

Fix them by properly defining the structs and add the explicit cast to
macros.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/mixart/mixart_core.c  |  4 ++--
 sound/pci/mixart/mixart_hwdep.c | 42 ++++++++++++++++++++---------------------
 sound/pci/mixart/mixart_hwdep.h |  8 ++++----
 3 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c
index 8bf2ce32d4a8..46c292b52fd6 100644
--- a/sound/pci/mixart/mixart_core.c
+++ b/sound/pci/mixart/mixart_core.c
@@ -107,7 +107,7 @@ static int get_msg(struct mixart_mgr *mgr, struct mixart_msg *resp,
 #ifndef __BIG_ENDIAN
 	size /= 4; /* u32 size */
 	for(i=0; i < size; i++) {
-		((u32*)resp->data)[i] = be32_to_cpu(((u32*)resp->data)[i]);
+		((u32*)resp->data)[i] = be32_to_cpu(((__be32*)resp->data)[i]);
 	}
 #endif
 
@@ -519,7 +519,7 @@ irqreturn_t snd_mixart_threaded_irq(int irq, void *dev_id)
 					/* Traces are text: the swapped msg_data has to be swapped back ! */
 					int i;
 					for(i=0; i<(resp.size/4); i++) {
-						(mixart_msg_data)[i] = cpu_to_be32((mixart_msg_data)[i]);
+						((__be32*)mixart_msg_data)[i] = cpu_to_be32((mixart_msg_data)[i]);
 					}
 #endif
 					((char*)mixart_msg_data)[resp.size - 1] = 0;
diff --git a/sound/pci/mixart/mixart_hwdep.c b/sound/pci/mixart/mixart_hwdep.c
index 5bfd3ac80db5..bc92758de82c 100644
--- a/sound/pci/mixart/mixart_hwdep.c
+++ b/sound/pci/mixart/mixart_hwdep.c
@@ -73,30 +73,30 @@ static int mixart_wait_nice_for_register_value(struct mixart_mgr *mgr,
  */
 struct snd_mixart_elf32_ehdr {
 	u8      e_ident[16];
-	u16     e_type;
-	u16     e_machine;
-	u32     e_version;
-	u32     e_entry;
-	u32     e_phoff;
-	u32     e_shoff;
-	u32     e_flags;
-	u16     e_ehsize;
-	u16     e_phentsize;
-	u16     e_phnum;
-	u16     e_shentsize;
-	u16     e_shnum;
-	u16     e_shstrndx;
+	__be16  e_type;
+	__be16  e_machine;
+	__be32  e_version;
+	__be32  e_entry;
+	__be32  e_phoff;
+	__be32  e_shoff;
+	__be32  e_flags;
+	__be16  e_ehsize;
+	__be16  e_phentsize;
+	__be16  e_phnum;
+	__be16  e_shentsize;
+	__be16  e_shnum;
+	__be16  e_shstrndx;
 };
 
 struct snd_mixart_elf32_phdr {
-	u32     p_type;
-	u32     p_offset;
-	u32     p_vaddr;
-	u32     p_paddr;
-	u32     p_filesz;
-	u32     p_memsz;
-	u32     p_flags;
-	u32     p_align;
+	__be32  p_type;
+	__be32  p_offset;
+	__be32  p_vaddr;
+	__be32  p_paddr;
+	__be32  p_filesz;
+	__be32  p_memsz;
+	__be32  p_flags;
+	__be32  p_align;
 };
 
 static int mixart_load_elf(struct mixart_mgr *mgr, const struct firmware *dsp )
diff --git a/sound/pci/mixart/mixart_hwdep.h b/sound/pci/mixart/mixart_hwdep.h
index 812e288ef2e7..2794cd385b8e 100644
--- a/sound/pci/mixart/mixart_hwdep.h
+++ b/sound/pci/mixart/mixart_hwdep.h
@@ -26,19 +26,19 @@
 #include <sound/hwdep.h>
 
 #ifndef readl_be
-#define readl_be(x) be32_to_cpu(__raw_readl(x))
+#define readl_be(x) be32_to_cpu((__force __be32)__raw_readl(x))
 #endif
 
 #ifndef writel_be
-#define writel_be(data,addr) __raw_writel(cpu_to_be32(data),addr)
+#define writel_be(data,addr) __raw_writel((__force u32)cpu_to_be32(data),addr)
 #endif
 
 #ifndef readl_le
-#define readl_le(x) le32_to_cpu(__raw_readl(x))
+#define readl_le(x) le32_to_cpu((__force __le32)__raw_readl(x))
 #endif
 
 #ifndef writel_le
-#define writel_le(data,addr) __raw_writel(cpu_to_le32(data),addr)
+#define writel_le(data,addr) __raw_writel((__force u32)cpu_to_le32(data),addr)
 #endif
 
 #define MIXART_MEM(mgr,x)	((mgr)->mem[0].virt + (x))
-- 
cgit v1.2.3


From 0d9a26fc74578289e0edeac36c6d562596f8a72e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:06 +0200
Subject: ALSA: lola: Proper endian notations

The BDL entries in lola driver are little-endian while we code them as
u32.  This leads to sparse warnings like:
  sound/pci/lola/lola.c:105:40: warning: incorrect type in assignment (different base types)
  sound/pci/lola/lola.c:105:40:    expected unsigned int [unsigned] [usertype] <noident>
  sound/pci/lola/lola.c:105:40:    got restricted __le32 [usertype] <noident>

This patch fixes the declarations to the proper __le32 type.

Also, there was a typo in the original code, where __user was used
that was intended as __iomem.  This was caused also by sparse:
  sound/pci/lola/lola_mixer.c:132:27: warning: incorrect type in assignment (different address spaces)
Fixed in this patch as well.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/lola/lola.c     | 4 ++--
 sound/pci/lola/lola.h     | 4 ++--
 sound/pci/lola/lola_pcm.c | 8 ++++----
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/sound/pci/lola/lola.c b/sound/pci/lola/lola.c
index 9ff600084973..254f24366892 100644
--- a/sound/pci/lola/lola.c
+++ b/sound/pci/lola/lola.c
@@ -369,9 +369,9 @@ static int setup_corb_rirb(struct lola *chip)
 		return err;
 
 	chip->corb.addr = chip->rb.addr;
-	chip->corb.buf = (u32 *)chip->rb.area;
+	chip->corb.buf = (__le32 *)chip->rb.area;
 	chip->rirb.addr = chip->rb.addr + 2048;
-	chip->rirb.buf = (u32 *)(chip->rb.area + 2048);
+	chip->rirb.buf = (__le32 *)(chip->rb.area + 2048);
 
 	/* disable ringbuffer DMAs */
 	lola_writeb(chip, BAR0, RIRBCTL, 0);
diff --git a/sound/pci/lola/lola.h b/sound/pci/lola/lola.h
index f0b100059efd..bd852fed8bb6 100644
--- a/sound/pci/lola/lola.h
+++ b/sound/pci/lola/lola.h
@@ -220,7 +220,7 @@ struct lola_bar {
 
 /* CORB/RIRB */
 struct lola_rb {
-	u32 *buf;		/* CORB/RIRB buffer, 8 byte per each entry */
+	__le32 *buf;		/* CORB/RIRB buffer, 8 byte per each entry */
 	dma_addr_t addr;	/* physical address of CORB/RIRB buffer */
 	unsigned short rp, wp;	/* read/write pointers */
 	int cmds;		/* number of pending requests */
@@ -275,7 +275,7 @@ struct lola_mixer_array {
 struct lola_mixer_widget {
 	unsigned int nid;
 	unsigned int caps;
-	struct lola_mixer_array __user *array;
+	struct lola_mixer_array __iomem *array;
 	struct lola_mixer_array *array_saved;
 	unsigned int src_stream_outs;
 	unsigned int src_phys_ins;
diff --git a/sound/pci/lola/lola_pcm.c b/sound/pci/lola/lola_pcm.c
index 310b26a756c9..e70276c3ea20 100644
--- a/sound/pci/lola/lola_pcm.c
+++ b/sound/pci/lola/lola_pcm.c
@@ -316,10 +316,10 @@ static int lola_pcm_hw_free(struct snd_pcm_substream *substream)
  * set up a BDL entry
  */
 static int setup_bdle(struct snd_pcm_substream *substream,
-		      struct lola_stream *str, u32 **bdlp,
+		      struct lola_stream *str, __le32 **bdlp,
 		      int ofs, int size)
 {
-	u32 *bdl = *bdlp;
+	__le32 *bdl = *bdlp;
 
 	while (size > 0) {
 		dma_addr_t addr;
@@ -355,14 +355,14 @@ static int lola_setup_periods(struct lola *chip, struct lola_pcm *pcm,
 			      struct snd_pcm_substream *substream,
 			      struct lola_stream *str)
 {
-	u32 *bdl;
+	__le32 *bdl;
 	int i, ofs, periods, period_bytes;
 
 	period_bytes = str->period_bytes;
 	periods = str->bufsize / period_bytes;
 
 	/* program the initial BDL entries */
-	bdl = (u32 *)(pcm->bdl.area + LOLA_BDL_ENTRY_SIZE * str->index);
+	bdl = (__le32 *)(pcm->bdl.area + LOLA_BDL_ENTRY_SIZE * str->index);
 	ofs = 0;
 	str->frags = 0;
 	for (i = 0; i < periods; i++) {
-- 
cgit v1.2.3


From 3c164e2ce601bd7abf76d9f37b7f4afa6fa988a1 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:07 +0200
Subject: ALSA: intel8x0: Proper endian notations

The BD address tables in intel8x0 driver are in little-endian, hence
they should be represented as __le32 instead u32.

Spotted by sparse, warnings like:
  sound/pci/intel8x0.c:688:40: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/intel8x0.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/pci/intel8x0.c b/sound/pci/intel8x0.c
index 4c24346340f4..5ee468d1aefe 100644
--- a/sound/pci/intel8x0.c
+++ b/sound/pci/intel8x0.c
@@ -351,7 +351,7 @@ enum {
 struct ichdev {
 	unsigned int ichd;			/* ich device number */
 	unsigned long reg_offset;		/* offset to bmaddr */
-	u32 *bdbar;				/* CPU address (32bit) */
+	__le32 *bdbar;				/* CPU address (32bit) */
 	unsigned int bdbar_addr;		/* PCI bus address (32bit) */
 	struct snd_pcm_substream *substream;
 	unsigned int physbuf;			/* physical address (32bit) */
@@ -677,7 +677,7 @@ static void snd_intel8x0_ali_codec_write(struct snd_ac97 *ac97, unsigned short r
 static void snd_intel8x0_setup_periods(struct intel8x0 *chip, struct ichdev *ichdev) 
 {
 	int idx;
-	u32 *bdbar = ichdev->bdbar;
+	__le32 *bdbar = ichdev->bdbar;
 	unsigned long port = ichdev->reg_offset;
 
 	iputdword(chip, port + ICH_REG_OFF_BDBAR, ichdev->bdbar_addr);
@@ -3143,7 +3143,7 @@ static int snd_intel8x0_create(struct snd_card *card,
 	int_sta_masks = 0;
 	for (i = 0; i < chip->bdbars_count; i++) {
 		ichdev = &chip->ichd[i];
-		ichdev->bdbar = ((u32 *)chip->bdbars.area) +
+		ichdev->bdbar = ((__le32 *)chip->bdbars.area) +
 			(i * ICH_MAX_FRAGS * 2);
 		ichdev->bdbar_addr = chip->bdbars.addr +
 			(i * sizeof(u32) * ICH_MAX_FRAGS * 2);
-- 
cgit v1.2.3


From 7752a7de2596097c8f702fd652cba05118f83bcc Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:08 +0200
Subject: ALSA: intel8x0m: Proper endian notations

The BD address tables in intel8x0m driver are in little-endian, hence
they should be represented as __le32 instead u32.

Spotted by sparse, warnings like:
  sound/pci/intel8x0m.c:406:40: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/intel8x0m.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/pci/intel8x0m.c b/sound/pci/intel8x0m.c
index 3a4769a97d29..943a726b1c1b 100644
--- a/sound/pci/intel8x0m.c
+++ b/sound/pci/intel8x0m.c
@@ -168,7 +168,7 @@ enum { ALID_MDMIN, ALID_MDMOUT, ALID_MDMLAST = ALID_MDMOUT };
 struct ichdev {
 	unsigned int ichd;			/* ich device number */
 	unsigned long reg_offset;		/* offset to bmaddr */
-	u32 *bdbar;				/* CPU address (32bit) */
+	__le32 *bdbar;				/* CPU address (32bit) */
 	unsigned int bdbar_addr;		/* PCI bus address (32bit) */
 	struct snd_pcm_substream *substream;
 	unsigned int physbuf;			/* physical address (32bit) */
@@ -395,7 +395,7 @@ static unsigned short snd_intel8x0m_codec_read(struct snd_ac97 *ac97,
 static void snd_intel8x0m_setup_periods(struct intel8x0m *chip, struct ichdev *ichdev)
 {
 	int idx;
-	u32 *bdbar = ichdev->bdbar;
+	__le32 *bdbar = ichdev->bdbar;
 	unsigned long port = ichdev->reg_offset;
 
 	iputdword(chip, port + ICH_REG_OFF_BDBAR, ichdev->bdbar_addr);
@@ -1217,7 +1217,7 @@ static int snd_intel8x0m_create(struct snd_card *card,
 	int_sta_masks = 0;
 	for (i = 0; i < chip->bdbars_count; i++) {
 		ichdev = &chip->ichd[i];
-		ichdev->bdbar = ((u32 *)chip->bdbars.area) + (i * ICH_MAX_FRAGS * 2);
+		ichdev->bdbar = ((__le32 *)chip->bdbars.area) + (i * ICH_MAX_FRAGS * 2);
 		ichdev->bdbar_addr = chip->bdbars.addr + (i * sizeof(u32) * ICH_MAX_FRAGS * 2);
 		int_sta_masks |= ichdev->int_sta_mask;
 	}
-- 
cgit v1.2.3


From 8c0ab942e05941ade5f1fca59d29b7034fdf164c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:09 +0200
Subject: ALSA: maestro3: Proper endian notations

The ASSP data passed to maestro3 driver is in little-endian format,
hence the data pointer should be with __le16.

Spotted by sparse, warnings like:
  sound/pci/maestro3.c:2128:35: warning: cast to restricted __le16

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/maestro3.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/pci/maestro3.c b/sound/pci/maestro3.c
index 224e942f556d..62962178a9d7 100644
--- a/sound/pci/maestro3.c
+++ b/sound/pci/maestro3.c
@@ -2103,7 +2103,7 @@ static const u16 minisrc_lpf[MINISRC_LPF_LEN] = {
 static void snd_m3_assp_init(struct snd_m3 *chip)
 {
 	unsigned int i;
-	const u16 *data;
+	const __le16 *data;
 
 	/* zero kernel data */
 	for (i = 0; i < (REV_B_DATA_MEMORY_UNIT_LENGTH * NUM_UNITS_KERNEL_DATA) / 2; i++)
@@ -2121,7 +2121,7 @@ static void snd_m3_assp_init(struct snd_m3 *chip)
 			  KDATA_DMA_XFER0);
 
 	/* write kernel into code memory.. */
-	data = (const u16 *)chip->assp_kernel_image->data;
+	data = (const __le16 *)chip->assp_kernel_image->data;
 	for (i = 0 ; i * 2 < chip->assp_kernel_image->size; i++) {
 		snd_m3_assp_write(chip, MEMTYPE_INTERNAL_CODE, 
 				  REV_B_CODE_MEMORY_BEGIN + i,
@@ -2134,7 +2134,7 @@ static void snd_m3_assp_init(struct snd_m3 *chip)
 	 * drop it there.  It seems that the minisrc doesn't
 	 * need vectors, so we won't bother with them..
 	 */
-	data = (const u16 *)chip->assp_minisrc_image->data;
+	data = (const __le16 *)chip->assp_minisrc_image->data;
 	for (i = 0; i * 2 < chip->assp_minisrc_image->size; i++) {
 		snd_m3_assp_write(chip, MEMTYPE_INTERNAL_CODE, 
 				  0x400 + i, le16_to_cpu(data[i]));
-- 
cgit v1.2.3


From 2a833a02a12b1dbb605739d589d11b4400c2078c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:10 +0200
Subject: ALSA: echoaudio: Proper endian notations

Many data fields defined in echoaudio drivers are in little-endian,
hence they should be defined with __le16 or __le32.  This makes it
easier to catch the forgotten conversions.

Spotted by sparse, a warning like:
  sound/pci/echoaudio/echoaudio_dsp.c:990:36: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/echoaudio/echoaudio.h     |  2 +-
 sound/pci/echoaudio/echoaudio_3g.c  | 14 ++++++-----
 sound/pci/echoaudio/echoaudio_dsp.c |  6 ++---
 sound/pci/echoaudio/echoaudio_dsp.h | 50 ++++++++++++++++++-------------------
 sound/pci/echoaudio/echoaudio_gml.c |  8 +++---
 5 files changed, 42 insertions(+), 38 deletions(-)

diff --git a/sound/pci/echoaudio/echoaudio.h b/sound/pci/echoaudio/echoaudio.h
index 44b390a667d5..be4d0489394a 100644
--- a/sound/pci/echoaudio/echoaudio.h
+++ b/sound/pci/echoaudio/echoaudio.h
@@ -294,7 +294,7 @@
 
 
 struct audiopipe {
-	volatile u32 *dma_counter;	/* Commpage register that contains
+	volatile __le32 *dma_counter;	/* Commpage register that contains
 					 * the current dma position
 					 * (lower 32 bits only)
 					 */
diff --git a/sound/pci/echoaudio/echoaudio_3g.c b/sound/pci/echoaudio/echoaudio_3g.c
index 22c786b8a889..cc3c79387194 100644
--- a/sound/pci/echoaudio/echoaudio_3g.c
+++ b/sound/pci/echoaudio/echoaudio_3g.c
@@ -73,19 +73,21 @@ register. write_control_reg sends the new control register value to the DSP. */
 static int write_control_reg(struct echoaudio *chip, u32 ctl, u32 frq,
 			     char force)
 {
+	__le32 ctl_reg, frq_reg;
+
 	if (wait_handshake(chip))
 		return -EIO;
 
 	dev_dbg(chip->card->dev,
 		"WriteControlReg: Setting 0x%x, 0x%x\n", ctl, frq);
 
-	ctl = cpu_to_le32(ctl);
-	frq = cpu_to_le32(frq);
+	ctl_reg = cpu_to_le32(ctl);
+	frq_reg = cpu_to_le32(frq);
 
-	if (ctl != chip->comm_page->control_register ||
-	    frq != chip->comm_page->e3g_frq_register || force) {
-		chip->comm_page->e3g_frq_register = frq;
-		chip->comm_page->control_register = ctl;
+	if (ctl_reg != chip->comm_page->control_register ||
+	    frq_reg != chip->comm_page->e3g_frq_register || force) {
+		chip->comm_page->e3g_frq_register = frq_reg;
+		chip->comm_page->control_register = ctl_reg;
 		clear_handshake(chip);
 		return send_vector(chip, DSP_VC_WRITE_CONTROL_REG);
 	}
diff --git a/sound/pci/echoaudio/echoaudio_dsp.c b/sound/pci/echoaudio/echoaudio_dsp.c
index 15aae2fad8e4..b181752b8481 100644
--- a/sound/pci/echoaudio/echoaudio_dsp.c
+++ b/sound/pci/echoaudio/echoaudio_dsp.c
@@ -679,7 +679,7 @@ static int restore_dsp_rettings(struct echoaudio *chip)
 	/* Gina20/Darla20 only. Should be harmless for other cards. */
 	chip->comm_page->gd_clock_state = GD_CLOCK_UNDEF;
 	chip->comm_page->gd_spdif_status = GD_SPDIF_STATUS_UNDEF;
-	chip->comm_page->handshake = 0xffffffff;
+	chip->comm_page->handshake = cpu_to_le32(0xffffffff);
 
 	/* Restore output busses */
 	for (i = 0; i < num_busses_out(chip); i++) {
@@ -989,7 +989,7 @@ static int init_dsp_comm_page(struct echoaudio *chip)
 	/* Init the comm page */
 	chip->comm_page->comm_size =
 		cpu_to_le32(sizeof(struct comm_page));
-	chip->comm_page->handshake = 0xffffffff;
+	chip->comm_page->handshake = cpu_to_le32(0xffffffff);
 	chip->comm_page->midi_out_free_count =
 		cpu_to_le32(DSP_MIDI_OUT_FIFO_SIZE);
 	chip->comm_page->sample_rate = cpu_to_le32(44100);
@@ -1087,7 +1087,7 @@ static int allocate_pipes(struct echoaudio *chip, struct audiopipe *pipe,
 	/* The counter register is where the DSP writes the 32 bit DMA
 	position for a pipe.  The DSP is constantly updating this value as
 	it moves data. The DMA counter is in units of bytes, not samples. */
-	pipe->dma_counter = &chip->comm_page->position[pipe_index];
+	pipe->dma_counter = (__le32 *)&chip->comm_page->position[pipe_index];
 	*pipe->dma_counter = 0;
 	return pipe_index;
 }
diff --git a/sound/pci/echoaudio/echoaudio_dsp.h b/sound/pci/echoaudio/echoaudio_dsp.h
index cb7d75a0a503..aa9129519795 100644
--- a/sound/pci/echoaudio/echoaudio_dsp.h
+++ b/sound/pci/echoaudio/echoaudio_dsp.h
@@ -627,8 +627,8 @@ sg_entry struct is read by the DSP, so all values must be little-endian. */
 #define MAX_SGLIST_ENTRIES 512
 
 struct sg_entry {
-	u32 addr;
-	u32 size;
+	__le32 addr;
+	__le32 size;
 };
 
 
@@ -643,18 +643,18 @@ struct sg_entry {
  ****************************************************************************/
 
 struct comm_page {		/*				Base	Length*/
-	u32 comm_size;		/* size of this object		0x000	4 */
-	u32 flags;		/* See Appendix A below		0x004	4 */
-	u32 unused;		/* Unused entry			0x008	4 */
-	u32 sample_rate;	/* Card sample rate in Hz	0x00c	4 */
-	u32 handshake;		/* DSP command handshake	0x010	4 */
-	u32 cmd_start;		/* Chs. to start mask		0x014	4 */
-	u32 cmd_stop;		/* Chs. to stop mask		0x018	4 */
-	u32 cmd_reset;		/* Chs. to reset mask		0x01c	4 */
-	u16 audio_format[DSP_MAXPIPES];	/* Chs. audio format	0x020	32*2 */
+	__le32 comm_size;	/* size of this object		0x000	4 */
+	__le32 flags;		/* See Appendix A below		0x004	4 */
+	__le32 unused;		/* Unused entry			0x008	4 */
+	__le32 sample_rate;	/* Card sample rate in Hz	0x00c	4 */
+	__le32 handshake;	/* DSP command handshake	0x010	4 */
+	__le32 cmd_start;	/* Chs. to start mask		0x014	4 */
+	__le32 cmd_stop;	/* Chs. to stop mask		0x018	4 */
+	__le32 cmd_reset;	/* Chs. to reset mask		0x01c	4 */
+	__le16 audio_format[DSP_MAXPIPES];	/* Chs. audio format	0x020	32*2 */
 	struct sg_entry sglist_addr[DSP_MAXPIPES];
 				/* Chs. Physical sglist addrs	0x060	32*8 */
-	u32 position[DSP_MAXPIPES];
+	__le32 position[DSP_MAXPIPES];
 				/* Positions for ea. ch.	0x160	32*4 */
 	s8 vu_meter[DSP_MAXPIPES];
 				/* VU meters			0x1e0	32*1 */
@@ -666,28 +666,28 @@ struct comm_page {		/*				Base	Length*/
 				/* Input gain			0x230	16*1 */
 	s8 monitors[MONITOR_ARRAY_SIZE];
 				/* Monitor map			0x240	0x180 */
-	u32 play_coeff[MAX_PLAY_TAPS];
+	__le32 play_coeff[MAX_PLAY_TAPS];
 			/* Gina/Darla play filters - obsolete	0x3c0	168*4 */
-	u32 rec_coeff[MAX_REC_TAPS];
+	__le32 rec_coeff[MAX_REC_TAPS];
 			/* Gina/Darla record filters - obsolete	0x660	192*4 */
-	u16 midi_input[MIDI_IN_BUFFER_SIZE];
+	__le16 midi_input[MIDI_IN_BUFFER_SIZE];
 			/* MIDI input data transfer buffer	0x960	256*2 */
 	u8 gd_clock_state;	/* Chg Gina/Darla clock state	0xb60	1 */
 	u8 gd_spdif_status;	/* Chg. Gina/Darla S/PDIF state	0xb61	1 */
 	u8 gd_resampler_state;	/* Should always be 3		0xb62	1 */
 	u8 filler2;		/*				0xb63	1 */
-	u32 nominal_level_mask;	/* -10 level enable mask	0xb64	4 */
-	u16 input_clock;	/* Chg. Input clock state	0xb68	2 */
-	u16 output_clock;	/* Chg. Output clock state	0xb6a	2 */
-	u32 status_clocks;	/* Current Input clock state	0xb6c	4 */
-	u32 ext_box_status;	/* External box status		0xb70	4 */
-	u32 cmd_add_buffer;	/* Pipes to add (obsolete)	0xb74	4 */
-	u32 midi_out_free_count;
+	__le32 nominal_level_mask;	/* -10 level enable mask	0xb64	4 */
+	__le16 input_clock;	/* Chg. Input clock state	0xb68	2 */
+	__le16 output_clock;	/* Chg. Output clock state	0xb6a	2 */
+	__le32 status_clocks;	/* Current Input clock state	0xb6c	4 */
+	__le32 ext_box_status;	/* External box status		0xb70	4 */
+	__le32 cmd_add_buffer;	/* Pipes to add (obsolete)	0xb74	4 */
+	__le32 midi_out_free_count;
 			/* # of bytes free in MIDI output FIFO	0xb78	4 */
-	u32 unused2;		/* Cyclic pipes			0xb7c	4 */
-	u32 control_register;
+	__le32 unused2;		/* Cyclic pipes			0xb7c	4 */
+	__le32 control_register;
 			/* Mona, Gina24, Layla24, 3G ctrl reg	0xb80	4 */
-	u32 e3g_frq_register;	/* 3G frequency register	0xb84	4 */
+	__le32 e3g_frq_register;	/* 3G frequency register	0xb84	4 */
 	u8 filler[24];		/* filler			0xb88	24*1 */
 	s8 vmixer[VMIXER_ARRAY_SIZE];
 				/* Vmixer levels		0xba0	64*1 */
diff --git a/sound/pci/echoaudio/echoaudio_gml.c b/sound/pci/echoaudio/echoaudio_gml.c
index 834b39e97db7..eea6fe530ab4 100644
--- a/sound/pci/echoaudio/echoaudio_gml.c
+++ b/sound/pci/echoaudio/echoaudio_gml.c
@@ -63,6 +63,8 @@ the control register.  write_control_reg sends the new control register
 value to the DSP. */
 static int write_control_reg(struct echoaudio *chip, u32 value, char force)
 {
+	__le32 reg_value;
+
 	/* Handle the digital input auto-mute */
 	if (chip->digital_in_automute)
 		value |= GML_DIGITAL_IN_AUTO_MUTE;
@@ -72,11 +74,11 @@ static int write_control_reg(struct echoaudio *chip, u32 value, char force)
 	dev_dbg(chip->card->dev, "write_control_reg: 0x%x\n", value);
 
 	/* Write the control register */
-	value = cpu_to_le32(value);
-	if (value != chip->comm_page->control_register || force) {
+	reg_value = cpu_to_le32(value);
+	if (reg_value != chip->comm_page->control_register || force) {
 		if (wait_handshake(chip))
 			return -EIO;
-		chip->comm_page->control_register = value;
+		chip->comm_page->control_register = reg_value;
 		clear_handshake(chip);
 		return send_vector(chip, DSP_VC_WRITE_CONTROL_REG);
 	}
-- 
cgit v1.2.3


From 58578d1894490c62bf64c3293cb06e0fcdc86a31 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:11 +0200
Subject: ALSA: bt87x: Proper endian notations

The RISC data in bt87x is in little-endian, hence we should define it
with __le32 properly.

Spotted by sparse, a warning like:
  sound/pci/bt87x.c:240:17: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/bt87x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/bt87x.c b/sound/pci/bt87x.c
index d8ade8771a32..ba971042f871 100644
--- a/sound/pci/bt87x.c
+++ b/sound/pci/bt87x.c
@@ -228,14 +228,14 @@ static int snd_bt87x_create_risc(struct snd_bt87x *chip, struct snd_pcm_substrea
 			       	 unsigned int periods, unsigned int period_bytes)
 {
 	unsigned int i, offset;
-	u32 *risc;
+	__le32 *risc;
 
 	if (chip->dma_risc.area == NULL) {
 		if (snd_dma_alloc_pages(SNDRV_DMA_TYPE_DEV, snd_dma_pci_data(chip->pci),
 					PAGE_ALIGN(MAX_RISC_SIZE), &chip->dma_risc) < 0)
 			return -ENOMEM;
 	}
-	risc = (u32 *)chip->dma_risc.area;
+	risc = (__le32 *)chip->dma_risc.area;
 	offset = 0;
 	*risc++ = cpu_to_le32(RISC_SYNC | RISC_SYNC_FM1);
 	*risc++ = cpu_to_le32(0);
-- 
cgit v1.2.3


From c44a81a40af0e1aa52b88d1c60682e30c411fb23 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:12 +0200
Subject: ALSA: atiixp: Proper endian notations

The DMA address table in atiixp driver is in little-endian, hence we should define it with __le32 properly.

Spotted by sparse, a warning like:
  sound/pci/atiixp.c:393:28: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/atiixp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/atiixp.c b/sound/pci/atiixp.c
index 7ae63d452bba..a1e4944dcfe8 100644
--- a/sound/pci/atiixp.c
+++ b/sound/pci/atiixp.c
@@ -207,10 +207,10 @@ struct atiixp;
  */
 
 struct atiixp_dma_desc {
-	u32 addr;	/* DMA buffer address */
+	__le32 addr;	/* DMA buffer address */
 	u16 status;	/* status bits */
 	u16 size;	/* size of the packet in dwords */
-	u32 next;	/* address of the next packet descriptor */
+	__le32 next;	/* address of the next packet descriptor */
 };
 
 /*
-- 
cgit v1.2.3


From 7e49aadf64992c138b354a2e9ae35a3ae0399415 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:13 +0200
Subject: ALSA: atiixp_modem: Proper endian notations

The DMA address table in atiixp modem driver is in little-endian,
hence we should define it with __le32 properly.

Spotted by sparse, a warning like:
  sound/pci/atiixp_modem.c:360:28: warning: incorrect type in assignment (different base types)

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/atiixp_modem.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/atiixp_modem.c b/sound/pci/atiixp_modem.c
index a586635664e0..dc1de860cedf 100644
--- a/sound/pci/atiixp_modem.c
+++ b/sound/pci/atiixp_modem.c
@@ -183,10 +183,10 @@ struct atiixp_modem;
  */
 
 struct atiixp_dma_desc {
-	u32 addr;	/* DMA buffer address */
+	__le32 addr;	/* DMA buffer address */
 	u16 status;	/* status bits */
 	u16 size;	/* size of the packet in dwords */
-	u32 next;	/* address of the next packet descriptor */
+	__le32 next;	/* address of the next packet descriptor */
 };
 
 /*
-- 
cgit v1.2.3


From 13e9a3edb4b702b701b5a9553b830aa3d2a3e3e9 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 25 Jul 2018 23:24:14 +0200
Subject: ALSA: sb: Proper endian notations

The data types defined in SB CSP driver code are all in little-endian,
hence the proper type like __le32 should be used.

Spotted by sparse, a warning like:
  sound/isa/sb/sb16_csp.c:330:14: warning: cast to restricted __le32

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/sb16_csp.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c
index 2210e7c72787..b9d67a7065cd 100644
--- a/sound/isa/sb/sb16_csp.c
+++ b/sound/isa/sb/sb16_csp.c
@@ -60,18 +60,18 @@ MODULE_FIRMWARE("sb16/ima_adpcm_capture.csp");
  * RIFF data format
  */
 struct riff_header {
-	__u32 name;
-	__u32 len;
+	__le32 name;
+	__le32 len;
 };
 
 struct desc_header {
 	struct riff_header info;
-	__u16 func_nr;
-	__u16 VOC_type;
-	__u16 flags_play_rec;
-	__u16 flags_16bit_8bit;
-	__u16 flags_stereo_mono;
-	__u16 flags_rates;
+	__le16 func_nr;
+	__le16 VOC_type;
+	__le16 flags_play_rec;
+	__le16 flags_16bit_8bit;
+	__le16 flags_stereo_mono;
+	__le16 flags_rates;
 };
 
 /*
@@ -314,7 +314,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 	unsigned short func_nr = 0;
 
 	struct riff_header file_h, item_h, code_h;
-	__u32 item_type;
+	__le32 item_type;
 	struct desc_header funcdesc_h;
 
 	unsigned long flags;
@@ -326,7 +326,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 
 	if (copy_from_user(&file_h, data_ptr, sizeof(file_h)))
 		return -EFAULT;
-	if ((file_h.name != RIFF_HEADER) ||
+	if ((le32_to_cpu(file_h.name) != RIFF_HEADER) ||
 	    (le32_to_cpu(file_h.len) >= SNDRV_SB_CSP_MAX_MICROCODE_FILE_SIZE - sizeof(file_h))) {
 		snd_printd("%s: Invalid RIFF header\n", __func__);
 		return -EINVAL;
@@ -336,7 +336,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 
 	if (copy_from_user(&item_type, data_ptr, sizeof(item_type)))
 		return -EFAULT;
-	if (item_type != CSP__HEADER) {
+	if (le32_to_cpu(item_type) != CSP__HEADER) {
 		snd_printd("%s: Invalid RIFF file type\n", __func__);
 		return -EINVAL;
 	}
@@ -346,12 +346,12 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 		if (copy_from_user(&item_h, data_ptr, sizeof(item_h)))
 			return -EFAULT;
 		data_ptr += sizeof(item_h);
-		if (item_h.name != LIST_HEADER)
+		if (le32_to_cpu(item_h.name) != LIST_HEADER)
 			continue;
 
 		if (copy_from_user(&item_type, data_ptr, sizeof(item_type)))
 			 return -EFAULT;
-		switch (item_type) {
+		switch (le32_to_cpu(item_type)) {
 		case FUNC_HEADER:
 			if (copy_from_user(&funcdesc_h, data_ptr + sizeof(item_type), sizeof(funcdesc_h)))
 				return -EFAULT;
@@ -378,7 +378,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 					return -EFAULT;
 
 				/* init microcode blocks */
-				if (code_h.name != INIT_HEADER)
+				if (le32_to_cpu(code_h.name) != INIT_HEADER)
 					break;
 				data_ptr += sizeof(code_h);
 				err = snd_sb_csp_load_user(p, data_ptr, le32_to_cpu(code_h.len),
@@ -391,7 +391,7 @@ static int snd_sb_csp_riff_load(struct snd_sb_csp * p,
 			if (copy_from_user(&code_h, data_ptr, sizeof(code_h)))
 				return -EFAULT;
 
-			if (code_h.name != MAIN_HEADER) {
+			if (le32_to_cpu(code_h.name) != MAIN_HEADER) {
 				snd_printd("%s: Missing 'main' microcode\n", __func__);
 				return -EINVAL;
 			}
-- 
cgit v1.2.3


From 3570a00841fb8a5d2f56ac7c59ccc6c91ea35944 Mon Sep 17 00:00:00 2001
From: Dan Murphy <dmurphy@ti.com>
Date: Tue, 29 May 2018 15:26:12 -0500
Subject: can: uapi: can.h: Fix can error class mask dir path

The CAN error masks header file is in the
include/uapi directory.

Fix the path in the header to the correct location.

Signed-off-by: Dan Murphy <dmurphy@ti.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/uapi/linux/can.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index d7f97ac197a9..0afb7d8e867f 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -77,7 +77,7 @@ typedef __u32 canid_t;
 /*
  * Controller Area Network Error Message Frame Mask structure
  *
- * bit 0-28	: error class mask (see include/linux/can/error.h)
+ * bit 0-28	: error class mask (see include/uapi/linux/can/error.h)
  * bit 29-31	: set to zero
  */
 typedef __u32 can_err_mask_t;
-- 
cgit v1.2.3


From b7cc4f3e127d1134677ce2e829ddae78ca50ebec Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Sat, 28 Apr 2018 23:16:00 +0100
Subject: can: cc770: fix spelling mistake: "comptibility" -> "compatibility"

Trivial fix to spelling mistake in module parameter description text

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/cc770/cc770.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/cc770/cc770.c b/drivers/net/can/cc770/cc770.c
index d4dd4da23997..da636a22c542 100644
--- a/drivers/net/can/cc770/cc770.c
+++ b/drivers/net/can/cc770/cc770.c
@@ -73,7 +73,7 @@ MODULE_PARM_DESC(msgobj15_eff, "Extended 29-bit frames for message object 15 "
 
 static int i82527_compat;
 module_param(i82527_compat, int, 0444);
-MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 comptibility mode "
+MODULE_PARM_DESC(i82527_compat, "Strict Intel 82527 compatibility mode "
 		 "without using additional functions");
 
 /*
-- 
cgit v1.2.3


From ffbdd9172ee2f53020f763574b4cdad8d9760a4f Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Wed, 25 Apr 2018 17:42:00 +0200
Subject: can: usb: Kconfig/Makefile: sort alphabetically

This patch sorts the entries in the Kconfig and Makefile alphabetically,
so that further contributors can generate patches more easily.

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/Kconfig  | 18 ++++++++++++------
 drivers/net/can/usb/Makefile |  4 ++--
 2 files changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index c36f4bdcbf4f..843380ad3e77 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -1,6 +1,12 @@
 menu "CAN USB interfaces"
 	depends on USB
 
+config CAN_8DEV_USB
+	tristate "8 devices USB2CAN interface"
+	---help---
+	  This driver supports the USB2CAN interface
+	  from 8 devices (http://www.8devices.com).
+
 config CAN_EMS_USB
 	tristate "EMS CPC-USB/ARM7 CAN/USB interface"
 	---help---
@@ -61,6 +67,12 @@ config CAN_KVASER_USB
 	  To compile this driver as a module, choose M here: the
 	  module will be called kvaser_usb.
 
+config CAN_MCBA_USB
+	tristate "Microchip CAN BUS Analyzer interface"
+	---help---
+	  This driver supports the CAN BUS Analyzer interface
+	  from Microchip (http://www.microchip.com/development-tools/).
+
 config CAN_PEAK_USB
 	tristate "PEAK PCAN-USB/USB Pro interfaces for CAN 2.0b/CAN-FD"
 	---help---
@@ -77,12 +89,6 @@ config CAN_PEAK_USB
 
 	  (see also http://www.peak-system.com).
 
-config CAN_8DEV_USB
-	tristate "8 devices USB2CAN interface"
-	---help---
-	  This driver supports the USB2CAN interface
-	  from 8 devices (http://www.8devices.com).
-
 config CAN_MCBA_USB
 	tristate "Microchip CAN BUS Analyzer interface"
 	---help---
diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile
index 49ac7b99ba32..c3d6fd95bbd7 100644
--- a/drivers/net/can/usb/Makefile
+++ b/drivers/net/can/usb/Makefile
@@ -3,10 +3,10 @@
 #  Makefile for the Linux Controller Area Network USB drivers.
 #
 
+obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o
 obj-$(CONFIG_CAN_EMS_USB) += ems_usb.o
 obj-$(CONFIG_CAN_ESD_USB2) += esd_usb2.o
 obj-$(CONFIG_CAN_GS_USB) += gs_usb.o
 obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
-obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
-obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o
 obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o
+obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
-- 
cgit v1.2.3


From 9f2d3eae88d26c29d96e42983b755940d9169cd9 Mon Sep 17 00:00:00 2001
From: Jakob Unterwurzacher <jakob.unterwurzacher@theobroma-systems.com>
Date: Wed, 11 Apr 2018 18:06:42 +0200
Subject: can: ucan: add driver for Theobroma Systems UCAN devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The UCAN driver supports the microcontroller-based USB/CAN
adapters from Theobroma Systems. There are two form-factors
that run essentially the same firmware:

* Seal: standalone USB stick ( https://www.theobroma-systems.com/seal )

* Mule: integrated on the PCB of various System-on-Modules from
  Theobroma Systems like the A31-µQ7 and the RK3399-Q7
  ( https://www.theobroma-systems.com/rk3399-q7 )

The USB wire protocol has been designed to be as generic and
hardware-indendent as possible in the hope of being useful for
implementation on other microcontrollers.

Signed-off-by: Martin Elshuber <martin.elshuber@theobroma-systems.com>
Signed-off-by: Jakob Unterwurzacher <jakob.unterwurzacher@theobroma-systems.com>
Signed-off-by: Philipp Tomsich <philipp.tomsich@theobroma-systems.com>
Acked-by: Wolfgang Grandegger <wg@grandegger.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/networking/can_ucan_protocol.rst |  332 +++++
 Documentation/networking/index.rst             |    1 +
 drivers/net/can/usb/Kconfig                    |   16 +
 drivers/net/can/usb/Makefile                   |    1 +
 drivers/net/can/usb/ucan.c                     | 1613 ++++++++++++++++++++++++
 5 files changed, 1963 insertions(+)
 create mode 100644 Documentation/networking/can_ucan_protocol.rst
 create mode 100644 drivers/net/can/usb/ucan.c

diff --git a/Documentation/networking/can_ucan_protocol.rst b/Documentation/networking/can_ucan_protocol.rst
new file mode 100644
index 000000000000..4cef88d24fc7
--- /dev/null
+++ b/Documentation/networking/can_ucan_protocol.rst
@@ -0,0 +1,332 @@
+=================
+The UCAN Protocol
+=================
+
+UCAN is the protocol used by the microcontroller-based USB-CAN
+adapter that is integrated on System-on-Modules from Theobroma Systems
+and that is also available as a standalone USB stick.
+
+The UCAN protocol has been designed to be hardware-independent.
+It is modeled closely after how Linux represents CAN devices
+internally. All multi-byte integers are encoded as Little Endian.
+
+All structures mentioned in this document are defined in
+``drivers/net/can/usb/ucan.c``.
+
+USB Endpoints
+=============
+
+UCAN devices use three USB endpoints:
+
+CONTROL endpoint
+  The driver sends device management commands on this endpoint
+
+IN endpoint
+  The device sends CAN data frames and CAN error frames
+
+OUT endpoint
+  The driver sends CAN data frames on the out endpoint
+
+
+CONTROL Messages
+================
+
+UCAN devices are configured using vendor requests on the control pipe.
+
+To support multiple CAN interfaces in a single USB device all
+configuration commands target the corresponding interface in the USB
+descriptor.
+
+The driver uses ``ucan_ctrl_command_in/out`` and
+``ucan_device_request_in`` to deliver commands to the device.
+
+Setup Packet
+------------
+
+=================  =====================================================
+``bmRequestType``  Direction | Vendor | (Interface or Device)
+``bRequest``       Command Number
+``wValue``         Subcommand Number (16 Bit) or 0 if not used
+``wIndex``         USB Interface Index (0 for device commands)
+``wLength``        * Host to Device - Number of bytes to transmit
+                   * Device to Host - Maximum Number of bytes to
+                     receive. If the device send less. Commom ZLP
+                     semantics are used.
+=================  =====================================================
+
+Error Handling
+--------------
+
+The device indicates failed control commands by stalling the
+pipe.
+
+Device Commands
+---------------
+
+UCAN_DEVICE_GET_FW_STRING
+~~~~~~~~~~~~~~~~~~~~~~~~~
+
+*Dev2Host; optional*
+
+Request the device firmware string.
+
+
+Interface Commands
+------------------
+
+UCAN_COMMAND_START
+~~~~~~~~~~~~~~~~~~
+
+*Host2Dev; mandatory*
+
+Bring the CAN interface up.
+
+Payload Format
+  ``ucan_ctl_payload_t.cmd_start``
+
+====  ============================
+mode  or mask of ``UCAN_MODE_*``
+====  ============================
+
+UCAN_COMMAND_STOP
+~~~~~~~~~~~~~~~~~~
+
+*Host2Dev; mandatory*
+
+Stop the CAN interface
+
+Payload Format
+  *empty*
+
+UCAN_COMMAND_RESET
+~~~~~~~~~~~~~~~~~~
+
+*Host2Dev; mandatory*
+
+Reset the CAN controller (including error counters)
+
+Payload Format
+  *empty*
+
+UCAN_COMMAND_GET
+~~~~~~~~~~~~~~~~
+
+*Host2Dev; mandatory*
+
+Get Information from the Device
+
+Subcommands
+^^^^^^^^^^^
+
+UCAN_COMMAND_GET_INFO
+  Request the device information structure ``ucan_ctl_payload_t.device_info``.
+
+  See the ``device_info`` field for details, and
+  ``uapi/linux/can/netlink.h`` for an explanation of the
+  ``can_bittiming fields``.
+
+  Payload Format
+    ``ucan_ctl_payload_t.device_info``
+
+UCAN_COMMAND_GET_PROTOCOL_VERSION
+
+  Request the device protocol version
+  ``ucan_ctl_payload_t.protocol_version``. The current protocol version is 3.
+
+  Payload Format
+    ``ucan_ctl_payload_t.protocol_version``
+
+.. note:: Devices that do not implement this command use the old
+          protocol version 1
+
+UCAN_COMMAND_SET_BITTIMING
+~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+*Host2Dev; mandatory*
+
+Setup bittiming by sending the the structure
+``ucan_ctl_payload_t.cmd_set_bittiming`` (see ``struct bittiming`` for
+details)
+
+Payload Format
+  ``ucan_ctl_payload_t.cmd_set_bittiming``.
+
+UCAN_SLEEP/WAKE
+~~~~~~~~~~~~~~~
+
+*Host2Dev; optional*
+
+Configure sleep and wake modes. Not yet supported by the driver.
+
+UCAN_FILTER
+~~~~~~~~~~~
+
+*Host2Dev; optional*
+
+Setup hardware CAN filters. Not yet supported by the driver.
+
+Allowed interface commands
+--------------------------
+
+==================  ===================  ==================
+Legal Device State  Command              New Device State
+==================  ===================  ==================
+stopped             SET_BITTIMING        stopped
+stopped             START                started
+started             STOP or RESET        stopped
+stopped             STOP or RESET        stopped
+started             RESTART              started
+any                 GET                  *no change*
+==================  ===================  ==================
+
+IN Message Format
+=================
+
+A data packet on the USB IN endpoint contains one or more
+``ucan_message_in`` values. If multiple messages are batched in a USB
+data packet, the ``len`` field can be used to jump to the next
+``ucan_message_in`` value (take care to sanity-check the ``len`` value
+against the actual data size).
+
+.. _can_ucan_in_message_len:
+
+``len`` field
+-------------
+
+Each ``ucan_message_in`` must be aligned to a 4-byte boundary (relative
+to the start of the start of the data buffer). That means that there
+may be padding bytes between multiple ``ucan_message_in`` values:
+
+.. code::
+
+    +----------------------------+ < 0
+    |                            |
+    |   struct ucan_message_in   |
+    |                            |
+    +----------------------------+ < len
+              [padding]
+    +----------------------------+ < round_up(len, 4)
+    |                            |
+    |   struct ucan_message_in   |
+    |                            |
+    +----------------------------+
+                [...]
+
+``type`` field
+--------------
+
+The ``type`` field specifies the type of the message.
+
+UCAN_IN_RX
+~~~~~~~~~~
+
+``subtype``
+  zero
+
+Data received from the CAN bus (ID + payload).
+
+UCAN_IN_TX_COMPLETE
+~~~~~~~~~~~~~~~~~~~
+
+``subtype``
+  zero
+
+The CAN device has sent a message to the CAN bus. It answers with a
+list of of tuples <echo-ids, flags>.
+
+The echo-id identifies the frame from (echos the id from a previous
+UCAN_OUT_TX message). The flag indicates the result of the
+transmission. Whereas a set Bit 0 indicates success. All other bits
+are reserved and set to zero.
+
+Flow Control
+------------
+
+When receiving CAN messages there is no flow control on the USB
+buffer. The driver has to handle inbound message quickly enough to
+avoid drops. I case the device buffer overflow the condition is
+reported by sending corresponding error frames (see
+:ref:`can_ucan_error_handling`)
+
+
+OUT Message Format
+==================
+
+A data packet on the USB OUT endpoint contains one or more ``struct
+ucan_message_out`` values. If multiple messages are batched into one
+data packet, the device uses the ``len`` field to jump to the next
+ucan_message_out value. Each ucan_message_out must be aligned to 4
+bytes (relative to the start of the data buffer). The mechanism is
+same as described in :ref:`can_ucan_in_message_len`.
+
+.. code::
+
+    +----------------------------+ < 0
+    |                            |
+    |   struct ucan_message_out  |
+    |                            |
+    +----------------------------+ < len
+              [padding]
+    +----------------------------+ < round_up(len, 4)
+    |                            |
+    |   struct ucan_message_out  |
+    |                            |
+    +----------------------------+
+                [...]
+
+``type`` field
+--------------
+
+In protocol version 3 only ``UCAN_OUT_TX`` is defined, others are used
+only by legacy devices (protocol version 1).
+
+UCAN_OUT_TX
+~~~~~~~~~~~
+``subtype``
+  echo id to be replied within a CAN_IN_TX_COMPLETE message
+
+Transmit a CAN frame. (parameters: ``id``, ``data``)
+
+Flow Control
+------------
+
+When the device outbound buffers are full it starts sending *NAKs* on
+the *OUT* pipe until more buffers are available. The driver stops the
+queue when a certain threshold of out packets are incomplete.
+
+.. _can_ucan_error_handling:
+
+CAN Error Handling
+==================
+
+If error reporting is turned on the device encodes errors into CAN
+error frames (see ``uapi/linux/can/error.h``) and sends it using the
+IN endpoint. The driver updates its error statistics and forwards
+it.
+
+Although UCAN devices can suppress error frames completely, in Linux
+the driver is always interested. Hence, the device is always started with
+the ``UCAN_MODE_BERR_REPORT`` set. Filtering those messages for the
+user space is done by the driver.
+
+Bus OFF
+-------
+
+- The device does not recover from bus of automatically.
+- Bus OFF is indicated by an error frame (see ``uapi/linux/can/error.h``)
+- Bus OFF recovery is started by ``UCAN_COMMAND_RESTART``
+- Once Bus OFF recover is completed the device sends an error frame
+  indicating that it is on ERROR-ACTIVE state.
+- During Bus OFF no frames are sent by the device.
+- During Bus OFF transmission requests from the host are completed
+  immediately with the success bit left unset.
+
+Example Conversation
+====================
+
+#) Device is connected to USB
+#) Host sends command ``UCAN_COMMAND_RESET``, subcmd 0
+#) Host sends command ``UCAN_COMMAND_GET``, subcmd ``UCAN_COMMAND_GET_INFO``
+#) Device sends ``UCAN_IN_DEVICE_INFO``
+#) Host sends command ``UCAN_OUT_SET_BITTIMING``
+#) Host sends command ``UCAN_COMMAND_START``, subcmd 0, mode ``UCAN_MODE_BERR_REPORT``
diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst
index 884a26145f20..fcd710f2cc7a 100644
--- a/Documentation/networking/index.rst
+++ b/Documentation/networking/index.rst
@@ -10,6 +10,7 @@ Contents:
    af_xdp
    batman-adv
    can
+   can_ucan_protocol
    dpaa2/index
    e100
    e1000
diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index 843380ad3e77..87b7aa15d175 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -95,4 +95,20 @@ config CAN_MCBA_USB
 	  This driver supports the CAN BUS Analyzer interface
 	  from Microchip (http://www.microchip.com/development-tools/).
 
+config CAN_UCAN
+	tristate "Theobroma Systems UCAN interface"
+	---help---
+	  This driver supports the Theobroma Systems
+	  UCAN USB-CAN interface.
+
+	  The UCAN driver supports the microcontroller-based USB/CAN
+	  adapters from Theobroma Systems. There are two form-factors
+	  that run essentially the same firmware:
+
+	  * Seal: standalone USB stick
+	          https://www.theobroma-systems.com/seal)
+	  * Mule: integrated on the PCB of various System-on-Modules
+	          from Theobroma Systems like the A31-µQ7 and the RK3399-Q7
+	          (https://www.theobroma-systems.com/rk3399-q7)
+
 endmenu
diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile
index c3d6fd95bbd7..613b1999d4d7 100644
--- a/drivers/net/can/usb/Makefile
+++ b/drivers/net/can/usb/Makefile
@@ -10,3 +10,4 @@ obj-$(CONFIG_CAN_GS_USB) += gs_usb.o
 obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
 obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o
 obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
+obj-$(CONFIG_CAN_UCAN) += ucan.o
diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
new file mode 100644
index 000000000000..0678a38b1af4
--- /dev/null
+++ b/drivers/net/can/usb/ucan.c
@@ -0,0 +1,1613 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/* Driver for Theobroma Systems UCAN devices, Protocol Version 3
+ *
+ * Copyright (C) 2018 Theobroma Systems Design und Consulting GmbH
+ *
+ *
+ * General Description:
+ *
+ * The USB Device uses three Endpoints:
+ *
+ *   CONTROL Endpoint: Is used the setup the device (start, stop,
+ *   info, configure).
+ *
+ *   IN Endpoint: The device sends CAN Frame Messages and Device
+ *   Information using the IN endpoint.
+ *
+ *   OUT Endpoint: The driver sends configuration requests, and CAN
+ *   Frames on the out endpoint.
+ *
+ * Error Handling:
+ *
+ *   If error reporting is turned on the device encodes error into CAN
+ *   error frames (see uapi/linux/can/error.h) and sends it using the
+ *   IN Endpoint. The driver updates statistics and forward it.
+ */
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/signal.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+
+#define UCAN_DRIVER_NAME "ucan"
+#define UCAN_MAX_RX_URBS 8
+/* the CAN controller needs a while to enable/disable the bus */
+#define UCAN_USB_CTL_PIPE_TIMEOUT 1000
+/* this driver currently supports protocol version 3 only */
+#define UCAN_PROTOCOL_VERSION_MIN 3
+#define UCAN_PROTOCOL_VERSION_MAX 3
+
+/* UCAN Message Definitions
+ * ------------------------
+ *
+ *  ucan_message_out_t and ucan_message_in_t define the messages
+ *  transmitted on the OUT and IN endpoint.
+ *
+ *  Multibyte fields are transmitted with little endianness
+ *
+ *  INTR Endpoint: a single uint32_t storing the current space in the fifo
+ *
+ *  OUT Endpoint: single message of type ucan_message_out_t is
+ *    transmitted on the out endpoint
+ *
+ *  IN Endpoint: multiple messages ucan_message_in_t concateted in
+ *    the following way:
+ *
+ *	m[n].len <=> the length if message n(including the header in bytes)
+ *	m[n] is is aligned to a 4 byte boundary, hence
+ *	  offset(m[0])	 := 0;
+ *	  offset(m[n+1]) := offset(m[n]) + (m[n].len + 3) & 3
+ *
+ *	this implies that
+ *	  offset(m[n]) % 4 <=> 0
+ */
+
+/* Device Global Commands */
+enum {
+	UCAN_DEVICE_GET_FW_STRING = 0,
+};
+
+/* UCAN Commands */
+enum {
+	/* start the can transceiver - val defines the operation mode */
+	UCAN_COMMAND_START = 0,
+	/* cancel pending transmissions and stop the can transceiver */
+	UCAN_COMMAND_STOP = 1,
+	/* send can transceiver into low-power sleep mode */
+	UCAN_COMMAND_SLEEP = 2,
+	/* wake up can transceiver from low-power sleep mode */
+	UCAN_COMMAND_WAKEUP = 3,
+	/* reset the can transceiver */
+	UCAN_COMMAND_RESET = 4,
+	/* get piece of info from the can transceiver - subcmd defines what
+	 * piece
+	 */
+	UCAN_COMMAND_GET = 5,
+	/* clear or disable hardware filter - subcmd defines which of the two */
+	UCAN_COMMAND_FILTER = 6,
+	/* Setup bittiming */
+	UCAN_COMMAND_SET_BITTIMING = 7,
+	/* recover from bus-off state */
+	UCAN_COMMAND_RESTART = 8,
+};
+
+/* UCAN_COMMAND_START and UCAN_COMMAND_GET_INFO operation modes (bitmap).
+ * Undefined bits must be set to 0.
+ */
+enum {
+	UCAN_MODE_LOOPBACK = BIT(0),
+	UCAN_MODE_SILENT = BIT(1),
+	UCAN_MODE_3_SAMPLES = BIT(2),
+	UCAN_MODE_ONE_SHOT = BIT(3),
+	UCAN_MODE_BERR_REPORT = BIT(4),
+};
+
+/* UCAN_COMMAND_GET subcommands */
+enum {
+	UCAN_COMMAND_GET_INFO = 0,
+	UCAN_COMMAND_GET_PROTOCOL_VERSION = 1,
+};
+
+/* UCAN_COMMAND_FILTER subcommands */
+enum {
+	UCAN_FILTER_CLEAR = 0,
+	UCAN_FILTER_DISABLE = 1,
+	UCAN_FILTER_ENABLE = 2,
+};
+
+/* OUT endpoint message types */
+enum {
+	UCAN_OUT_TX = 2,     /* transmit a CAN frame */
+};
+
+/* IN endpoint message types */
+enum {
+	UCAN_IN_TX_COMPLETE = 1,  /* CAN frame transmission completed */
+	UCAN_IN_RX = 2,           /* CAN frame received */
+};
+
+struct ucan_ctl_cmd_start {
+	__le16 mode;         /* OR-ing any of UCAN_MODE_* */
+} __packed;
+
+struct ucan_ctl_cmd_set_bittiming {
+	__le32 tq;           /* Time quanta (TQ) in nanoseconds */
+	__le16 brp;          /* TQ Prescaler */
+	__le16 sample_point; /* Samplepoint on tenth percent */
+	u8 prop_seg;         /* Propagation segment in TQs */
+	u8 phase_seg1;       /* Phase buffer segment 1 in TQs */
+	u8 phase_seg2;       /* Phase buffer segment 2 in TQs */
+	u8 sjw;              /* Synchronisation jump width in TQs */
+} __packed;
+
+struct ucan_ctl_cmd_device_info {
+	__le32 freq;         /* Clock Frequency for tq generation */
+	u8 tx_fifo;          /* Size of the transmission fifo */
+	u8 sjw_max;          /* can_bittiming fields... */
+	u8 tseg1_min;
+	u8 tseg1_max;
+	u8 tseg2_min;
+	u8 tseg2_max;
+	__le16 brp_inc;
+	__le32 brp_min;
+	__le32 brp_max;      /* ...can_bittiming fields */
+	__le16 ctrlmodes;    /* supported control modes */
+	__le16 hwfilter;     /* Number of HW filter banks */
+	__le16 rxmboxes;     /* Number of receive Mailboxes */
+} __packed;
+
+struct ucan_ctl_cmd_get_protocol_version {
+	__le32 version;
+} __packed;
+
+union ucan_ctl_payload {
+	/* Setup Bittiming
+	 * bmRequest == UCAN_COMMAND_START
+	 */
+	struct ucan_ctl_cmd_start cmd_start;
+	/* Setup Bittiming
+	 * bmRequest == UCAN_COMMAND_SET_BITTIMING
+	 */
+	struct ucan_ctl_cmd_set_bittiming cmd_set_bittiming;
+	/* Get Device Information
+	 * bmRequest == UCAN_COMMAND_GET; wValue = UCAN_COMMAND_GET_INFO
+	 */
+	struct ucan_ctl_cmd_device_info cmd_get_device_info;
+	/* Get Protocol Version
+	 * bmRequest == UCAN_COMMAND_GET;
+	 * wValue = UCAN_COMMAND_GET_PROTOCOL_VERSION
+	 */
+	struct ucan_ctl_cmd_get_protocol_version cmd_get_protocol_version;
+
+	u8 raw[128];
+} __packed;
+
+enum {
+	UCAN_TX_COMPLETE_SUCCESS = BIT(0),
+};
+
+/* Transmission Complete within ucan_message_in */
+struct ucan_tx_complete_entry_t {
+	u8 echo_index;
+	u8 flags;
+} __packed __aligned(0x2);
+
+/* CAN Data message format within ucan_message_in/out */
+struct ucan_can_msg {
+	/* note DLC is computed by
+	 *    msg.len - sizeof (msg.len)
+	 *            - sizeof (msg.type)
+	 *            - sizeof (msg.can_msg.id)
+	 */
+	__le32 id;
+
+	union {
+		u8 data[CAN_MAX_DLEN];  /* Data of CAN frames */
+		u8 dlc;                 /* RTR dlc */
+	};
+} __packed;
+
+/* OUT Endpoint, outbound messages */
+struct ucan_message_out {
+	__le16 len; /* Length of the content include header */
+	u8 type;    /* UCAN_OUT_TX and friends */
+	u8 subtype; /* command sub type */
+
+	union {
+		/* Transmit CAN frame
+		 * (type == UCAN_TX) && ((msg.can_msg.id & CAN_RTR_FLAG) == 0)
+		 * subtype stores the echo id
+		 */
+		struct ucan_can_msg can_msg;
+	} msg;
+} __packed __aligned(0x4);
+
+/* IN Endpoint, inbound messages */
+struct ucan_message_in {
+	__le16 len; /* Length of the content include header */
+	u8 type;    /* UCAN_IN_RX and friends */
+	u8 subtype; /* command sub type */
+
+	union {
+		/* CAN Frame received
+		 * (type == UCAN_IN_RX)
+		 * && ((msg.can_msg.id & CAN_RTR_FLAG) == 0)
+		 */
+		struct ucan_can_msg can_msg;
+
+		/* CAN transmission complete
+		 * (type == UCAN_IN_TX_COMPLETE)
+		 */
+		struct ucan_tx_complete_entry_t can_tx_complete_msg[0];
+	} __aligned(0x4) msg;
+} __packed;
+
+/* Macros to calculate message lengths */
+#define UCAN_OUT_HDR_SIZE offsetof(struct ucan_message_out, msg)
+
+#define UCAN_IN_HDR_SIZE offsetof(struct ucan_message_in, msg)
+#define UCAN_IN_LEN(member) (UCAN_OUT_HDR_SIZE + sizeof(member))
+
+struct ucan_priv;
+
+/* Context Information for transmission URBs */
+struct ucan_urb_context {
+	struct ucan_priv *up;
+	u8 dlc;
+	bool allocated;
+};
+
+/* Information reported by the USB device */
+struct ucan_device_info {
+	struct can_bittiming_const bittiming_const;
+	u8 tx_fifo;
+};
+
+/* Driver private data */
+struct ucan_priv {
+	/* must be the first member */
+	struct can_priv can;
+
+	/* linux USB device structures */
+	struct usb_device *udev;
+	struct usb_interface *intf;
+	struct net_device *netdev;
+
+	/* lock for can->echo_skb (used around
+	 * can_put/get/free_echo_skb
+	 */
+	spinlock_t echo_skb_lock;
+
+	/* usb device information information */
+	u8 intf_index;
+	u8 in_ep_addr;
+	u8 out_ep_addr;
+	u16 in_ep_size;
+
+	/* transmission and reception buffers */
+	struct usb_anchor rx_urbs;
+	struct usb_anchor tx_urbs;
+
+	union ucan_ctl_payload *ctl_msg_buffer;
+	struct ucan_device_info device_info;
+
+	/* transmission control information and locks */
+	spinlock_t context_lock;
+	unsigned int available_tx_urbs;
+	struct ucan_urb_context *context_array;
+};
+
+static u8 ucan_get_can_dlc(struct ucan_can_msg *msg, u16 len)
+{
+	if (le32_to_cpu(msg->id) & CAN_RTR_FLAG)
+		return get_can_dlc(msg->dlc);
+	else
+		return get_can_dlc(len - (UCAN_IN_HDR_SIZE + sizeof(msg->id)));
+}
+
+static void ucan_release_context_array(struct ucan_priv *up)
+{
+	if (!up->context_array)
+		return;
+
+	/* lock is not needed because, driver is currently opening or closing */
+	up->available_tx_urbs = 0;
+
+	kfree(up->context_array);
+	up->context_array = NULL;
+}
+
+static int ucan_alloc_context_array(struct ucan_priv *up)
+{
+	int i;
+
+	/* release contexts if any */
+	ucan_release_context_array(up);
+
+	up->context_array = kcalloc(up->device_info.tx_fifo,
+				    sizeof(*up->context_array),
+				    GFP_KERNEL);
+	if (!up->context_array) {
+		netdev_err(up->netdev,
+			   "Not enough memory to allocate tx contexts\n");
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < up->device_info.tx_fifo; i++) {
+		up->context_array[i].allocated = false;
+		up->context_array[i].up = up;
+	}
+
+	/* lock is not needed because, driver is currently opening */
+	up->available_tx_urbs = up->device_info.tx_fifo;
+
+	return 0;
+}
+
+static struct ucan_urb_context *ucan_alloc_context(struct ucan_priv *up)
+{
+	int i;
+	unsigned long flags;
+	struct ucan_urb_context *ret = NULL;
+
+	if (WARN_ON_ONCE(!up->context_array))
+		return NULL;
+
+	/* execute context operation atomically */
+	spin_lock_irqsave(&up->context_lock, flags);
+
+	for (i = 0; i < up->device_info.tx_fifo; i++) {
+		if (!up->context_array[i].allocated) {
+			/* update context */
+			ret = &up->context_array[i];
+			up->context_array[i].allocated = true;
+
+			/* stop queue if necessary */
+			up->available_tx_urbs--;
+			if (!up->available_tx_urbs)
+				netif_stop_queue(up->netdev);
+
+			break;
+		}
+	}
+
+	spin_unlock_irqrestore(&up->context_lock, flags);
+	return ret;
+}
+
+static bool ucan_release_context(struct ucan_priv *up,
+				 struct ucan_urb_context *ctx)
+{
+	unsigned long flags;
+	bool ret = false;
+
+	if (WARN_ON_ONCE(!up->context_array))
+		return false;
+
+	/* execute context operation atomically */
+	spin_lock_irqsave(&up->context_lock, flags);
+
+	/* context was not allocated, maybe the device sent garbage */
+	if (ctx->allocated) {
+		ctx->allocated = false;
+
+		/* check if the queue needs to be woken */
+		if (!up->available_tx_urbs)
+			netif_wake_queue(up->netdev);
+		up->available_tx_urbs++;
+
+		ret = true;
+	}
+
+	spin_unlock_irqrestore(&up->context_lock, flags);
+	return ret;
+}
+
+static int ucan_ctrl_command_out(struct ucan_priv *up,
+				 u8 cmd, u16 subcmd, u16 datalen)
+{
+	return usb_control_msg(up->udev,
+			       usb_sndctrlpipe(up->udev, 0),
+			       cmd,
+			       USB_DIR_OUT | USB_TYPE_VENDOR |
+						USB_RECIP_INTERFACE,
+			       subcmd,
+			       up->intf_index,
+			       up->ctl_msg_buffer,
+			       datalen,
+			       UCAN_USB_CTL_PIPE_TIMEOUT);
+}
+
+static int ucan_device_request_in(struct ucan_priv *up,
+				  u8 cmd, u16 subcmd, u16 datalen)
+{
+	return usb_control_msg(up->udev,
+			       usb_rcvctrlpipe(up->udev, 0),
+			       cmd,
+			       USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
+			       subcmd,
+			       0,
+			       up->ctl_msg_buffer,
+			       datalen,
+			       UCAN_USB_CTL_PIPE_TIMEOUT);
+}
+
+/* Parse the device information structure reported by the device and
+ * setup private variables accordingly
+ */
+static void ucan_parse_device_info(struct ucan_priv *up,
+				   struct ucan_ctl_cmd_device_info *device_info)
+{
+	struct can_bittiming_const *bittiming =
+		&up->device_info.bittiming_const;
+	u16 ctrlmodes;
+
+	/* store the data */
+	up->can.clock.freq = le32_to_cpu(device_info->freq);
+	up->device_info.tx_fifo = device_info->tx_fifo;
+	strcpy(bittiming->name, "ucan");
+	bittiming->tseg1_min = device_info->tseg1_min;
+	bittiming->tseg1_max = device_info->tseg1_max;
+	bittiming->tseg2_min = device_info->tseg2_min;
+	bittiming->tseg2_max = device_info->tseg2_max;
+	bittiming->sjw_max = device_info->sjw_max;
+	bittiming->brp_min = le32_to_cpu(device_info->brp_min);
+	bittiming->brp_max = le32_to_cpu(device_info->brp_max);
+	bittiming->brp_inc = le16_to_cpu(device_info->brp_inc);
+
+	ctrlmodes = le16_to_cpu(device_info->ctrlmodes);
+
+	up->can.ctrlmode_supported = 0;
+
+	if (ctrlmodes & UCAN_MODE_LOOPBACK)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_LOOPBACK;
+	if (ctrlmodes & UCAN_MODE_SILENT)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
+	if (ctrlmodes & UCAN_MODE_3_SAMPLES)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+	if (ctrlmodes & UCAN_MODE_ONE_SHOT)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_ONE_SHOT;
+	if (ctrlmodes & UCAN_MODE_BERR_REPORT)
+		up->can.ctrlmode_supported |= CAN_CTRLMODE_BERR_REPORTING;
+}
+
+/* Handle a CAN error frame that we have received from the device.
+ * Returns true if the can state has changed.
+ */
+static bool ucan_handle_error_frame(struct ucan_priv *up,
+				    struct ucan_message_in *m,
+				    canid_t canid)
+{
+	enum can_state new_state = up->can.state;
+	struct net_device_stats *net_stats = &up->netdev->stats;
+	struct can_device_stats *can_stats = &up->can.can_stats;
+
+	if (canid & CAN_ERR_LOSTARB)
+		can_stats->arbitration_lost++;
+
+	if (canid & CAN_ERR_BUSERROR)
+		can_stats->bus_error++;
+
+	if (canid & CAN_ERR_ACK)
+		net_stats->tx_errors++;
+
+	if (canid & CAN_ERR_BUSOFF)
+		new_state = CAN_STATE_BUS_OFF;
+
+	/* controller problems, details in data[1] */
+	if (canid & CAN_ERR_CRTL) {
+		u8 d1 = m->msg.can_msg.data[1];
+
+		if (d1 & CAN_ERR_CRTL_RX_OVERFLOW)
+			net_stats->rx_over_errors++;
+
+		/* controller state bits: if multiple are set the worst wins */
+		if (d1 & CAN_ERR_CRTL_ACTIVE)
+			new_state = CAN_STATE_ERROR_ACTIVE;
+
+		if (d1 & (CAN_ERR_CRTL_RX_WARNING | CAN_ERR_CRTL_TX_WARNING))
+			new_state = CAN_STATE_ERROR_WARNING;
+
+		if (d1 & (CAN_ERR_CRTL_RX_PASSIVE | CAN_ERR_CRTL_TX_PASSIVE))
+			new_state = CAN_STATE_ERROR_PASSIVE;
+	}
+
+	/* protocol error, details in data[2] */
+	if (canid & CAN_ERR_PROT) {
+		u8 d2 = m->msg.can_msg.data[2];
+
+		if (d2 & CAN_ERR_PROT_TX)
+			net_stats->tx_errors++;
+		else
+			net_stats->rx_errors++;
+	}
+
+	/* no state change - we are done */
+	if (up->can.state == new_state)
+		return false;
+
+	/* we switched into a better state */
+	if (up->can.state > new_state) {
+		up->can.state = new_state;
+		return true;
+	}
+
+	/* we switched into a worse state */
+	up->can.state = new_state;
+	switch (new_state) {
+	case CAN_STATE_BUS_OFF:
+		can_stats->bus_off++;
+		can_bus_off(up->netdev);
+		break;
+	case CAN_STATE_ERROR_PASSIVE:
+		can_stats->error_passive++;
+		break;
+	case CAN_STATE_ERROR_WARNING:
+		can_stats->error_warning++;
+		break;
+	default:
+		break;
+	}
+	return true;
+}
+
+/* Callback on reception of a can frame via the IN endpoint
+ *
+ * This function allocates an skb and transferres it to the Linux
+ * network stack
+ */
+static void ucan_rx_can_msg(struct ucan_priv *up, struct ucan_message_in *m)
+{
+	int len;
+	canid_t canid;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct net_device_stats *stats = &up->netdev->stats;
+
+	/* get the contents of the length field */
+	len = le16_to_cpu(m->len);
+
+	/* check sanity */
+	if (len < UCAN_IN_HDR_SIZE + sizeof(m->msg.can_msg.id)) {
+		netdev_warn(up->netdev, "invalid input message len: %d\n", len);
+		return;
+	}
+
+	/* handle error frames */
+	canid = le32_to_cpu(m->msg.can_msg.id);
+	if (canid & CAN_ERR_FLAG) {
+		bool busstate_changed = ucan_handle_error_frame(up, m, canid);
+
+		/* if berr-reporting is off only state changes get through */
+		if (!(up->can.ctrlmode & CAN_CTRLMODE_BERR_REPORTING) &&
+		    !busstate_changed)
+			return;
+	} else {
+		canid_t canid_mask;
+		/* compute the mask for canid */
+		canid_mask = CAN_RTR_FLAG;
+		if (canid & CAN_EFF_FLAG)
+			canid_mask |= CAN_EFF_MASK | CAN_EFF_FLAG;
+		else
+			canid_mask |= CAN_SFF_MASK;
+
+		if (canid & ~canid_mask)
+			netdev_warn(up->netdev,
+				    "unexpected bits set (canid %x, mask %x)",
+				    canid, canid_mask);
+
+		canid &= canid_mask;
+	}
+
+	/* allocate skb */
+	skb = alloc_can_skb(up->netdev, &cf);
+	if (!skb)
+		return;
+
+	/* fill the can frame */
+	cf->can_id = canid;
+
+	/* compute DLC taking RTR_FLAG into account */
+	cf->can_dlc = ucan_get_can_dlc(&m->msg.can_msg, len);
+
+	/* copy the payload of non RTR frames */
+	if (!(cf->can_id & CAN_RTR_FLAG) || (cf->can_id & CAN_ERR_FLAG))
+		memcpy(cf->data, m->msg.can_msg.data, cf->can_dlc);
+
+	/* don't count error frames as real packets */
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+
+	/* pass it to Linux */
+	netif_rx(skb);
+}
+
+/* callback indicating completed transmission */
+static void ucan_tx_complete_msg(struct ucan_priv *up,
+				 struct ucan_message_in *m)
+{
+	unsigned long flags;
+	u16 count, i;
+	u8 echo_index, dlc;
+	u16 len = le16_to_cpu(m->len);
+
+	struct ucan_urb_context *context;
+
+	if (len < UCAN_IN_HDR_SIZE || (len % 2 != 0)) {
+		netdev_err(up->netdev, "invalid tx complete length\n");
+		return;
+	}
+
+	count = (len - UCAN_IN_HDR_SIZE) / 2;
+	for (i = 0; i < count; i++) {
+		/* we did not submit such echo ids */
+		echo_index = m->msg.can_tx_complete_msg[i].echo_index;
+		if (echo_index >= up->device_info.tx_fifo) {
+			up->netdev->stats.tx_errors++;
+			netdev_err(up->netdev,
+				   "invalid echo_index %d received\n",
+				   echo_index);
+			continue;
+		}
+
+		/* gather information from the context */
+		context = &up->context_array[echo_index];
+		dlc = READ_ONCE(context->dlc);
+
+		/* Release context and restart queue if necessary.
+		 * Also check if the context was allocated
+		 */
+		if (!ucan_release_context(up, context))
+			continue;
+
+		spin_lock_irqsave(&up->echo_skb_lock, flags);
+		if (m->msg.can_tx_complete_msg[i].flags &
+		    UCAN_TX_COMPLETE_SUCCESS) {
+			/* update statistics */
+			up->netdev->stats.tx_packets++;
+			up->netdev->stats.tx_bytes += dlc;
+			can_get_echo_skb(up->netdev, echo_index);
+		} else {
+			up->netdev->stats.tx_dropped++;
+			can_free_echo_skb(up->netdev, echo_index);
+		}
+		spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+	}
+}
+
+/* callback on reception of a USB message */
+static void ucan_read_bulk_callback(struct urb *urb)
+{
+	int ret;
+	int pos;
+	struct ucan_priv *up = urb->context;
+	struct net_device *netdev = up->netdev;
+	struct ucan_message_in *m;
+
+	/* the device is not up and the driver should not receive any
+	 * data on the bulk in pipe
+	 */
+	if (WARN_ON(!up->context_array)) {
+		usb_free_coherent(up->udev,
+				  up->in_ep_size,
+				  urb->transfer_buffer,
+				  urb->transfer_dma);
+		return;
+	}
+
+	/* check URB status */
+	switch (urb->status) {
+	case 0:
+		break;
+	case -ENOENT:
+	case -EPIPE:
+	case -EPROTO:
+	case -ESHUTDOWN:
+	case -ETIME:
+		/* urb is not resubmitted -> free dma data */
+		usb_free_coherent(up->udev,
+				  up->in_ep_size,
+				  urb->transfer_buffer,
+				  urb->transfer_dma);
+		netdev_dbg(up->netdev, "not resumbmitting urb; status: %d\n",
+			   urb->status);
+		return;
+	default:
+		goto resubmit;
+	}
+
+	/* sanity check */
+	if (!netif_device_present(netdev))
+		return;
+
+	/* iterate over input */
+	pos = 0;
+	while (pos < urb->actual_length) {
+		int len;
+
+		/* check sanity (length of header) */
+		if ((urb->actual_length - pos) < UCAN_IN_HDR_SIZE) {
+			netdev_warn(up->netdev,
+				    "invalid message (short; no hdr; l:%d)\n",
+				    urb->actual_length);
+			goto resubmit;
+		}
+
+		/* setup the message address */
+		m = (struct ucan_message_in *)
+			((u8 *)urb->transfer_buffer + pos);
+		len = le16_to_cpu(m->len);
+
+		/* check sanity (length of content) */
+		if (urb->actual_length - pos < len) {
+			netdev_warn(up->netdev,
+				    "invalid message (short; no data; l:%d)\n",
+				    urb->actual_length);
+			print_hex_dump(KERN_WARNING,
+				       "raw data: ",
+				       DUMP_PREFIX_ADDRESS,
+				       16,
+				       1,
+				       urb->transfer_buffer,
+				       urb->actual_length,
+				       true);
+
+			goto resubmit;
+		}
+
+		switch (m->type) {
+		case UCAN_IN_RX:
+			ucan_rx_can_msg(up, m);
+			break;
+		case UCAN_IN_TX_COMPLETE:
+			ucan_tx_complete_msg(up, m);
+			break;
+		default:
+			netdev_warn(up->netdev,
+				    "invalid message (type; t:%d)\n",
+				    m->type);
+			break;
+		}
+
+		/* proceed to next message */
+		pos += len;
+		/* align to 4 byte boundary */
+		pos = round_up(pos, 4);
+	}
+
+resubmit:
+	/* resubmit urb when done */
+	usb_fill_bulk_urb(urb, up->udev,
+			  usb_rcvbulkpipe(up->udev,
+					  up->in_ep_addr),
+			  urb->transfer_buffer,
+			  up->in_ep_size,
+			  ucan_read_bulk_callback,
+			  up);
+
+	usb_anchor_urb(urb, &up->rx_urbs);
+	ret = usb_submit_urb(urb, GFP_KERNEL);
+
+	if (ret < 0) {
+		netdev_err(up->netdev,
+			   "failed resubmitting read bulk urb: %d\n",
+			   ret);
+
+		usb_unanchor_urb(urb);
+		usb_free_coherent(up->udev,
+				  up->in_ep_size,
+				  urb->transfer_buffer,
+				  urb->transfer_dma);
+
+		if (ret == -ENODEV)
+			netif_device_detach(netdev);
+	}
+}
+
+/* callback after transmission of a USB message */
+static void ucan_write_bulk_callback(struct urb *urb)
+{
+	unsigned long flags;
+	struct ucan_priv *up;
+	struct ucan_urb_context *context = urb->context;
+
+	/* get the urb context */
+	if (WARN_ON_ONCE(!context))
+		return;
+
+	/* free up our allocated buffer */
+	usb_free_coherent(urb->dev,
+			  sizeof(struct ucan_message_out),
+			  urb->transfer_buffer,
+			  urb->transfer_dma);
+
+	up = context->up;
+	if (WARN_ON_ONCE(!up))
+		return;
+
+	/* sanity check */
+	if (!netif_device_present(up->netdev))
+		return;
+
+	/* transmission failed (USB - the device will not send a TX complete) */
+	if (urb->status) {
+		netdev_warn(up->netdev,
+			    "failed to transmit USB message to device: %d\n",
+			     urb->status);
+
+		/* update counters an cleanup */
+		spin_lock_irqsave(&up->echo_skb_lock, flags);
+		can_free_echo_skb(up->netdev, context - up->context_array);
+		spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+
+		up->netdev->stats.tx_dropped++;
+
+		/* release context and restart the queue if necessary */
+		if (!ucan_release_context(up, context))
+			netdev_err(up->netdev,
+				   "urb failed, failed to release context\n");
+	}
+}
+
+static void ucan_cleanup_rx_urbs(struct ucan_priv *up, struct urb **urbs)
+{
+	int i;
+
+	for (i = 0; i < UCAN_MAX_RX_URBS; i++) {
+		if (urbs[i]) {
+			usb_unanchor_urb(urbs[i]);
+			usb_free_coherent(up->udev,
+					  up->in_ep_size,
+					  urbs[i]->transfer_buffer,
+					  urbs[i]->transfer_dma);
+			usb_free_urb(urbs[i]);
+		}
+	}
+
+	memset(urbs, 0, sizeof(*urbs) * UCAN_MAX_RX_URBS);
+}
+
+static int ucan_prepare_and_anchor_rx_urbs(struct ucan_priv *up,
+					   struct urb **urbs)
+{
+	int i;
+
+	memset(urbs, 0, sizeof(*urbs) * UCAN_MAX_RX_URBS);
+
+	for (i = 0; i < UCAN_MAX_RX_URBS; i++) {
+		void *buf;
+
+		urbs[i] = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urbs[i])
+			goto err;
+
+		buf = usb_alloc_coherent(up->udev,
+					 up->in_ep_size,
+					 GFP_KERNEL, &urbs[i]->transfer_dma);
+		if (!buf) {
+			/* cleanup this urb */
+			usb_free_urb(urbs[i]);
+			urbs[i] = NULL;
+			goto err;
+		}
+
+		usb_fill_bulk_urb(urbs[i], up->udev,
+				  usb_rcvbulkpipe(up->udev,
+						  up->in_ep_addr),
+				  buf,
+				  up->in_ep_size,
+				  ucan_read_bulk_callback,
+				  up);
+
+		urbs[i]->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+
+		usb_anchor_urb(urbs[i], &up->rx_urbs);
+	}
+	return 0;
+
+err:
+	/* cleanup other unsubmitted urbs */
+	ucan_cleanup_rx_urbs(up, urbs);
+	return -ENOMEM;
+}
+
+/* Submits rx urbs with the semantic: Either submit all, or cleanup
+ * everything. I case of errors submitted urbs are killed and all urbs in
+ * the array are freed. I case of no errors every entry in the urb
+ * array is set to NULL.
+ */
+static int ucan_submit_rx_urbs(struct ucan_priv *up, struct urb **urbs)
+{
+	int i, ret;
+
+	/* Iterate over all urbs to submit. On success remove the urb
+	 * from the list.
+	 */
+	for (i = 0; i < UCAN_MAX_RX_URBS; i++) {
+		ret = usb_submit_urb(urbs[i], GFP_KERNEL);
+		if (ret) {
+			netdev_err(up->netdev,
+				   "could not submit urb; code: %d\n",
+				   ret);
+			goto err;
+		}
+
+		/* Anchor URB and drop reference, USB core will take
+		 * care of freeing it
+		 */
+		usb_free_urb(urbs[i]);
+		urbs[i] = NULL;
+	}
+	return 0;
+
+err:
+	/* Cleanup unsubmitted urbs */
+	ucan_cleanup_rx_urbs(up, urbs);
+
+	/* Kill urbs that are already submitted */
+	usb_kill_anchored_urbs(&up->rx_urbs);
+
+	return ret;
+}
+
+/* Open the network device */
+static int ucan_open(struct net_device *netdev)
+{
+	int ret, ret_cleanup;
+	u16 ctrlmode;
+	struct urb *urbs[UCAN_MAX_RX_URBS];
+	struct ucan_priv *up = netdev_priv(netdev);
+
+	ret = ucan_alloc_context_array(up);
+	if (ret)
+		return ret;
+
+	/* Allocate and prepare IN URBS - allocated and anchored
+	 * urbs are stored in urbs[] for clean
+	 */
+	ret = ucan_prepare_and_anchor_rx_urbs(up, urbs);
+	if (ret)
+		goto err_contexts;
+
+	/* Check the control mode */
+	ctrlmode = 0;
+	if (up->can.ctrlmode & CAN_CTRLMODE_LOOPBACK)
+		ctrlmode |= UCAN_MODE_LOOPBACK;
+	if (up->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		ctrlmode |= UCAN_MODE_SILENT;
+	if (up->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		ctrlmode |= UCAN_MODE_3_SAMPLES;
+	if (up->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT)
+		ctrlmode |= UCAN_MODE_ONE_SHOT;
+
+	/* Enable this in any case - filtering is down within the
+	 * receive path
+	 */
+	ctrlmode |= UCAN_MODE_BERR_REPORT;
+	up->ctl_msg_buffer->cmd_start.mode = cpu_to_le16(ctrlmode);
+
+	/* Driver is ready to receive data - start the USB device */
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_START, 0, 2);
+	if (ret < 0) {
+		netdev_err(up->netdev,
+			   "could not start device, code: %d\n",
+			   ret);
+		goto err_reset;
+	}
+
+	/* Call CAN layer open */
+	ret = open_candev(netdev);
+	if (ret)
+		goto err_stop;
+
+	/* Driver is ready to receive data. Submit RX URBS */
+	ret = ucan_submit_rx_urbs(up, urbs);
+	if (ret)
+		goto err_stop;
+
+	up->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	/* Start the network queue */
+	netif_start_queue(netdev);
+
+	return 0;
+
+err_stop:
+	/* The device have started already stop it */
+	ret_cleanup = ucan_ctrl_command_out(up, UCAN_COMMAND_STOP, 0, 0);
+	if (ret_cleanup < 0)
+		netdev_err(up->netdev,
+			   "could not stop device, code: %d\n",
+			   ret_cleanup);
+
+err_reset:
+	/* The device might have received data, reset it for
+	 * consistent state
+	 */
+	ret_cleanup = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
+	if (ret_cleanup < 0)
+		netdev_err(up->netdev,
+			   "could not reset device, code: %d\n",
+			   ret_cleanup);
+
+	/* clean up unsubmitted urbs */
+	ucan_cleanup_rx_urbs(up, urbs);
+
+err_contexts:
+	ucan_release_context_array(up);
+	return ret;
+}
+
+static struct urb *ucan_prepare_tx_urb(struct ucan_priv *up,
+				       struct ucan_urb_context *context,
+				       struct can_frame *cf,
+				       u8 echo_index)
+{
+	int mlen;
+	struct urb *urb;
+	struct ucan_message_out *m;
+
+	/* create a URB, and a buffer for it, and copy the data to the URB */
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb) {
+		netdev_err(up->netdev, "no memory left for URBs\n");
+		return NULL;
+	}
+
+	m = usb_alloc_coherent(up->udev,
+			       sizeof(struct ucan_message_out),
+			       GFP_ATOMIC,
+			       &urb->transfer_dma);
+	if (!m) {
+		netdev_err(up->netdev, "no memory left for USB buffer\n");
+		usb_free_urb(urb);
+		return NULL;
+	}
+
+	/* build the USB message */
+	m->type = UCAN_OUT_TX;
+	m->msg.can_msg.id = cpu_to_le32(cf->can_id);
+
+	if (cf->can_id & CAN_RTR_FLAG) {
+		mlen = UCAN_OUT_HDR_SIZE +
+			offsetof(struct ucan_can_msg, dlc) +
+			sizeof(m->msg.can_msg.dlc);
+		m->msg.can_msg.dlc = cf->can_dlc;
+	} else {
+		mlen = UCAN_OUT_HDR_SIZE +
+			sizeof(m->msg.can_msg.id) + cf->can_dlc;
+		memcpy(m->msg.can_msg.data, cf->data, cf->can_dlc);
+	}
+	m->len = cpu_to_le16(mlen);
+
+	context->dlc = cf->can_dlc;
+
+	m->subtype = echo_index;
+
+	/* build the urb */
+	usb_fill_bulk_urb(urb, up->udev,
+			  usb_sndbulkpipe(up->udev,
+					  up->out_ep_addr),
+			  m, mlen, ucan_write_bulk_callback, context);
+	urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+
+	return urb;
+}
+
+static void ucan_clean_up_tx_urb(struct ucan_priv *up, struct urb *urb)
+{
+	usb_free_coherent(up->udev, sizeof(struct ucan_message_out),
+			  urb->transfer_buffer, urb->transfer_dma);
+	usb_free_urb(urb);
+}
+
+/* callback when Linux needs to send a can frame */
+static netdev_tx_t ucan_start_xmit(struct sk_buff *skb,
+				   struct net_device *netdev)
+{
+	unsigned long flags;
+	int ret;
+	u8 echo_index;
+	struct urb *urb;
+	struct ucan_urb_context *context;
+	struct ucan_priv *up = netdev_priv(netdev);
+	struct can_frame *cf = (struct can_frame *)skb->data;
+
+	/* check skb */
+	if (can_dropped_invalid_skb(netdev, skb))
+		return NETDEV_TX_OK;
+
+	/* allocate a context and slow down tx path, if fifo state is low */
+	context = ucan_alloc_context(up);
+	echo_index = context - up->context_array;
+
+	if (WARN_ON_ONCE(!context))
+		return NETDEV_TX_BUSY;
+
+	/* prepare urb for transmission */
+	urb = ucan_prepare_tx_urb(up, context, cf, echo_index);
+	if (!urb)
+		goto drop;
+
+	/* put the skb on can loopback stack */
+	spin_lock_irqsave(&up->echo_skb_lock, flags);
+	can_put_echo_skb(skb, up->netdev, echo_index);
+	spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+
+	/* transmit it */
+	usb_anchor_urb(urb, &up->tx_urbs);
+	ret = usb_submit_urb(urb, GFP_ATOMIC);
+
+	/* cleanup urb */
+	if (ret) {
+		/* on error, clean up */
+		usb_unanchor_urb(urb);
+		ucan_clean_up_tx_urb(up, urb);
+		if (!ucan_release_context(up, context))
+			netdev_err(up->netdev,
+				   "xmit err: failed to release context\n");
+
+		/* remove the skb from the echo stack - this also
+		 * frees the skb
+		 */
+		spin_lock_irqsave(&up->echo_skb_lock, flags);
+		can_free_echo_skb(up->netdev, echo_index);
+		spin_unlock_irqrestore(&up->echo_skb_lock, flags);
+
+		if (ret == -ENODEV) {
+			netif_device_detach(up->netdev);
+		} else {
+			netdev_warn(up->netdev,
+				    "xmit err: failed to submit urb %d\n",
+				    ret);
+			up->netdev->stats.tx_dropped++;
+		}
+		return NETDEV_TX_OK;
+	}
+
+	netif_trans_update(netdev);
+
+	/* release ref, as we do not need the urb anymore */
+	usb_free_urb(urb);
+
+	return NETDEV_TX_OK;
+
+drop:
+	if (!ucan_release_context(up, context))
+		netdev_err(up->netdev,
+			   "xmit drop: failed to release context\n");
+	dev_kfree_skb(skb);
+	up->netdev->stats.tx_dropped++;
+
+	return NETDEV_TX_OK;
+}
+
+/* Device goes down
+ *
+ * Clean up used resources
+ */
+static int ucan_close(struct net_device *netdev)
+{
+	int ret;
+	struct ucan_priv *up = netdev_priv(netdev);
+
+	up->can.state = CAN_STATE_STOPPED;
+
+	/* stop sending data */
+	usb_kill_anchored_urbs(&up->tx_urbs);
+
+	/* stop receiving data */
+	usb_kill_anchored_urbs(&up->rx_urbs);
+
+	/* stop and reset can device */
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_STOP, 0, 0);
+	if (ret < 0)
+		netdev_err(up->netdev,
+			   "could not stop device, code: %d\n",
+			   ret);
+
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
+	if (ret < 0)
+		netdev_err(up->netdev,
+			   "could not reset device, code: %d\n",
+			   ret);
+
+	netif_stop_queue(netdev);
+
+	ucan_release_context_array(up);
+
+	close_candev(up->netdev);
+	return 0;
+}
+
+/* CAN driver callbacks */
+static const struct net_device_ops ucan_netdev_ops = {
+	.ndo_open = ucan_open,
+	.ndo_stop = ucan_close,
+	.ndo_start_xmit = ucan_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+/* Request to set bittiming
+ *
+ * This function generates an USB set bittiming message and transmits
+ * it to the device
+ */
+static int ucan_set_bittiming(struct net_device *netdev)
+{
+	int ret;
+	struct ucan_priv *up = netdev_priv(netdev);
+	struct ucan_ctl_cmd_set_bittiming *cmd_set_bittiming;
+
+	cmd_set_bittiming = &up->ctl_msg_buffer->cmd_set_bittiming;
+	cmd_set_bittiming->tq = cpu_to_le32(up->can.bittiming.tq);
+	cmd_set_bittiming->brp = cpu_to_le16(up->can.bittiming.brp);
+	cmd_set_bittiming->sample_point =
+	    cpu_to_le16(up->can.bittiming.sample_point);
+	cmd_set_bittiming->prop_seg = up->can.bittiming.prop_seg;
+	cmd_set_bittiming->phase_seg1 = up->can.bittiming.phase_seg1;
+	cmd_set_bittiming->phase_seg2 = up->can.bittiming.phase_seg2;
+	cmd_set_bittiming->sjw = up->can.bittiming.sjw;
+
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_SET_BITTIMING, 0,
+				    sizeof(*cmd_set_bittiming));
+	return (ret < 0) ? ret : 0;
+}
+
+/* Restart the device to get it out of BUS-OFF state.
+ * Called when the user runs "ip link set can1 type can restart".
+ */
+static int ucan_set_mode(struct net_device *netdev, enum can_mode mode)
+{
+	int ret;
+	unsigned long flags;
+	struct ucan_priv *up = netdev_priv(netdev);
+
+	switch (mode) {
+	case CAN_MODE_START:
+		netdev_dbg(up->netdev, "restarting device\n");
+
+		ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESTART, 0, 0);
+		up->can.state = CAN_STATE_ERROR_ACTIVE;
+
+		/* check if queue can be restarted,
+		 * up->available_tx_urbs must be protected by the
+		 * lock
+		 */
+		spin_lock_irqsave(&up->context_lock, flags);
+
+		if (up->available_tx_urbs > 0)
+			netif_wake_queue(up->netdev);
+
+		spin_unlock_irqrestore(&up->context_lock, flags);
+
+		return ret;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/* Probe the device, reset it and gather general device information */
+static int ucan_probe(struct usb_interface *intf,
+		      const struct usb_device_id *id)
+{
+	int ret;
+	int i;
+	u32 protocol_version;
+	struct usb_device *udev;
+	struct net_device *netdev;
+	struct usb_host_interface *iface_desc;
+	struct ucan_priv *up;
+	struct usb_endpoint_descriptor *ep;
+	u16 in_ep_size;
+	u16 out_ep_size;
+	u8 in_ep_addr;
+	u8 out_ep_addr;
+	union ucan_ctl_payload *ctl_msg_buffer;
+	char firmware_str[sizeof(union ucan_ctl_payload) + 1];
+
+	udev = interface_to_usbdev(intf);
+
+	/* Stage 1 - Interface Parsing
+	 * ---------------------------
+	 *
+	 * Identifie the device USB interface descriptor and its
+	 * endpoints. Probing is aborted on errors.
+	 */
+
+	/* check if the interface is sane */
+	iface_desc = intf->cur_altsetting;
+	if (!iface_desc)
+		return -ENODEV;
+
+	dev_info(&udev->dev,
+		 "%s: probing device on interface #%d\n",
+		 UCAN_DRIVER_NAME,
+		 iface_desc->desc.bInterfaceNumber);
+
+	/* interface sanity check */
+	if (iface_desc->desc.bNumEndpoints != 2) {
+		dev_err(&udev->dev,
+			"%s: invalid EP count (%d)",
+			UCAN_DRIVER_NAME, iface_desc->desc.bNumEndpoints);
+		goto err_firmware_needs_update;
+	}
+
+	/* check interface endpoints */
+	in_ep_addr = 0;
+	out_ep_addr = 0;
+	in_ep_size = 0;
+	out_ep_size = 0;
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) {
+		ep = &iface_desc->endpoint[i].desc;
+
+		if (((ep->bEndpointAddress & USB_ENDPOINT_DIR_MASK) != 0) &&
+		    ((ep->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) ==
+		     USB_ENDPOINT_XFER_BULK)) {
+			/* In Endpoint */
+			in_ep_addr = ep->bEndpointAddress;
+			in_ep_addr &= USB_ENDPOINT_NUMBER_MASK;
+			in_ep_size = le16_to_cpu(ep->wMaxPacketSize);
+		} else if (((ep->bEndpointAddress & USB_ENDPOINT_DIR_MASK) ==
+			    0) &&
+			   ((ep->bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) ==
+			    USB_ENDPOINT_XFER_BULK)) {
+			/* Out Endpoint */
+			out_ep_addr = ep->bEndpointAddress;
+			out_ep_addr &= USB_ENDPOINT_NUMBER_MASK;
+			out_ep_size = le16_to_cpu(ep->wMaxPacketSize);
+		}
+	}
+
+	/* check if interface is sane */
+	if (!in_ep_addr || !out_ep_addr) {
+		dev_err(&udev->dev, "%s: invalid endpoint configuration\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (in_ep_size < sizeof(struct ucan_message_in)) {
+		dev_err(&udev->dev, "%s: invalid in_ep MaxPacketSize\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (out_ep_size < sizeof(struct ucan_message_out)) {
+		dev_err(&udev->dev, "%s: invalid out_ep MaxPacketSize\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+
+	/* Stage 2 - Device Identification
+	 * -------------------------------
+	 *
+	 * The device interface seems to be a ucan device. Do further
+	 * compatibility checks. On error probing is aborted, on
+	 * success this stage leaves the ctl_msg_buffer with the
+	 * reported contents of a GET_INFO command (supported
+	 * bittimings, tx_fifo depth). This information is used in
+	 * Stage 3 for the final driver initialisation.
+	 */
+
+	/* Prepare Memory for control transferes */
+	ctl_msg_buffer = devm_kzalloc(&udev->dev,
+				      sizeof(union ucan_ctl_payload),
+				      GFP_KERNEL);
+	if (!ctl_msg_buffer) {
+		dev_err(&udev->dev,
+			"%s: failed to allocate control pipe memory\n",
+			UCAN_DRIVER_NAME);
+		return -ENOMEM;
+	}
+
+	/* get protocol version
+	 *
+	 * note: ucan_ctrl_command_* wrappers cannot be used yet
+	 * because `up` is initialised in Stage 3
+	 */
+	ret = usb_control_msg(udev,
+			      usb_rcvctrlpipe(udev, 0),
+			      UCAN_COMMAND_GET,
+			      USB_DIR_IN | USB_TYPE_VENDOR |
+					USB_RECIP_INTERFACE,
+			      UCAN_COMMAND_GET_PROTOCOL_VERSION,
+			      iface_desc->desc.bInterfaceNumber,
+			      ctl_msg_buffer,
+			      sizeof(union ucan_ctl_payload),
+			      UCAN_USB_CTL_PIPE_TIMEOUT);
+
+	/* older firmware version do not support this command - those
+	 * are not supported by this drive
+	 */
+	if (ret != 4) {
+		dev_err(&udev->dev,
+			"%s: could not read protocol version, ret=%d\n",
+			UCAN_DRIVER_NAME, ret);
+		if (ret >= 0)
+			ret = -EINVAL;
+		goto err_firmware_needs_update;
+	}
+
+	/* this driver currently supports protocol version 3 only */
+	protocol_version =
+		le32_to_cpu(ctl_msg_buffer->cmd_get_protocol_version.version);
+	if (protocol_version < UCAN_PROTOCOL_VERSION_MIN ||
+	    protocol_version > UCAN_PROTOCOL_VERSION_MAX) {
+		dev_err(&udev->dev,
+			"%s: device protocol version %d is not supported\n",
+			UCAN_DRIVER_NAME, protocol_version);
+		goto err_firmware_needs_update;
+	}
+
+	/* request the device information and store it in ctl_msg_buffer
+	 *
+	 * note: ucan_ctrl_command_* wrappers connot be used yet
+	 * because `up` is initialised in Stage 3
+	 */
+	ret = usb_control_msg(udev,
+			      usb_rcvctrlpipe(udev, 0),
+			      UCAN_COMMAND_GET,
+			      USB_DIR_IN | USB_TYPE_VENDOR |
+					USB_RECIP_INTERFACE,
+			      UCAN_COMMAND_GET_INFO,
+			      iface_desc->desc.bInterfaceNumber,
+			      ctl_msg_buffer,
+			      sizeof(ctl_msg_buffer->cmd_get_device_info),
+			      UCAN_USB_CTL_PIPE_TIMEOUT);
+
+	if (ret < 0) {
+		dev_err(&udev->dev, "%s: failed to retrieve device info\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (ret < sizeof(ctl_msg_buffer->cmd_get_device_info)) {
+		dev_err(&udev->dev, "%s: device reported invalid device info\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+	if (ctl_msg_buffer->cmd_get_device_info.tx_fifo == 0) {
+		dev_err(&udev->dev,
+			"%s: device reported invalid tx-fifo size\n",
+			UCAN_DRIVER_NAME);
+		goto err_firmware_needs_update;
+	}
+
+	/* Stage 3 - Driver Initialisation
+	 * -------------------------------
+	 *
+	 * Register device to Linux, prepare private structures and
+	 * reset the device.
+	 */
+
+	/* allocate driver resources */
+	netdev = alloc_candev(sizeof(struct ucan_priv),
+			      ctl_msg_buffer->cmd_get_device_info.tx_fifo);
+	if (!netdev) {
+		dev_err(&udev->dev,
+			"%s: cannot allocate candev\n", UCAN_DRIVER_NAME);
+		return -ENOMEM;
+	}
+
+	up = netdev_priv(netdev);
+
+	/* initialze data */
+	up->udev = udev;
+	up->intf = intf;
+	up->netdev = netdev;
+	up->intf_index = iface_desc->desc.bInterfaceNumber;
+	up->in_ep_addr = in_ep_addr;
+	up->out_ep_addr = out_ep_addr;
+	up->in_ep_size = in_ep_size;
+	up->ctl_msg_buffer = ctl_msg_buffer;
+	up->context_array = NULL;
+	up->available_tx_urbs = 0;
+
+	up->can.state = CAN_STATE_STOPPED;
+	up->can.bittiming_const = &up->device_info.bittiming_const;
+	up->can.do_set_bittiming = ucan_set_bittiming;
+	up->can.do_set_mode = &ucan_set_mode;
+	spin_lock_init(&up->context_lock);
+	spin_lock_init(&up->echo_skb_lock);
+	netdev->netdev_ops = &ucan_netdev_ops;
+
+	usb_set_intfdata(intf, up);
+	SET_NETDEV_DEV(netdev, &intf->dev);
+
+	/* parse device information
+	 * the data retrieved in Stage 2 is still available in
+	 * up->ctl_msg_buffer
+	 */
+	ucan_parse_device_info(up, &ctl_msg_buffer->cmd_get_device_info);
+
+	/* just print some device information - if available */
+	ret = ucan_device_request_in(up, UCAN_DEVICE_GET_FW_STRING, 0,
+				     sizeof(union ucan_ctl_payload));
+	if (ret > 0) {
+		/* copy string while ensuring zero terminiation */
+		strncpy(firmware_str, up->ctl_msg_buffer->raw,
+			sizeof(union ucan_ctl_payload));
+		firmware_str[sizeof(union ucan_ctl_payload)] = '\0';
+	} else {
+		strcpy(firmware_str, "unknown");
+	}
+
+	/* device is compatible, reset it */
+	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
+	if (ret < 0)
+		goto err_free_candev;
+
+	init_usb_anchor(&up->rx_urbs);
+	init_usb_anchor(&up->tx_urbs);
+
+	up->can.state = CAN_STATE_STOPPED;
+
+	/* register the device */
+	ret = register_candev(netdev);
+	if (ret)
+		goto err_free_candev;
+
+	/* initialisation complete, log device info */
+	netdev_info(up->netdev, "registered device\n");
+	netdev_info(up->netdev, "firmware string: %s\n", firmware_str);
+
+	/* success */
+	return 0;
+
+err_free_candev:
+	free_candev(netdev);
+	return ret;
+
+err_firmware_needs_update:
+	dev_err(&udev->dev,
+		"%s: probe failed; try to update the device firmware\n",
+		UCAN_DRIVER_NAME);
+	return -ENODEV;
+}
+
+/* disconnect the device */
+static void ucan_disconnect(struct usb_interface *intf)
+{
+	struct usb_device *udev;
+	struct ucan_priv *up = usb_get_intfdata(intf);
+
+	udev = interface_to_usbdev(intf);
+
+	usb_set_intfdata(intf, NULL);
+
+	if (up) {
+		unregister_netdev(up->netdev);
+		free_candev(up->netdev);
+	}
+}
+
+static struct usb_device_id ucan_table[] = {
+	/* Mule (soldered onto compute modules) */
+	{USB_DEVICE_INTERFACE_NUMBER(0x2294, 0x425a, 0)},
+	/* Seal (standalone USB stick) */
+	{USB_DEVICE_INTERFACE_NUMBER(0x2294, 0x425b, 0)},
+	{} /* Terminating entry */
+};
+
+MODULE_DEVICE_TABLE(usb, ucan_table);
+/* driver callbacks */
+static struct usb_driver ucan_driver = {
+	.name = UCAN_DRIVER_NAME,
+	.probe = ucan_probe,
+	.disconnect = ucan_disconnect,
+	.id_table = ucan_table,
+};
+
+module_usb_driver(ucan_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Martin Elshuber <martin.elshuber@theobroma-systems.com>");
+MODULE_AUTHOR("Jakob Unterwurzacher <jakob.unterwurzacher@theobroma-systems.com>");
+MODULE_DESCRIPTION("Driver for Theobroma Systems UCAN devices");
-- 
cgit v1.2.3


From 8551e71d1063edfaab03585e5f78077ec1c85da3 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 28 Apr 2018 15:49:57 +0800
Subject: can: dev: use skb_put_zero to simplfy code

use helper skb_put_zero to replace the pattern of skb_put() && memset()

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 3c71f1cb205f..5bb6e8896601 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -649,8 +649,7 @@ struct sk_buff *alloc_can_skb(struct net_device *dev, struct can_frame **cf)
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	can_skb_prv(skb)->skbcnt = 0;
 
-	*cf = skb_put(skb, sizeof(struct can_frame));
-	memset(*cf, 0, sizeof(struct can_frame));
+	*cf = skb_put_zero(skb, sizeof(struct can_frame));
 
 	return skb;
 }
@@ -678,8 +677,7 @@ struct sk_buff *alloc_canfd_skb(struct net_device *dev,
 	can_skb_prv(skb)->ifindex = dev->ifindex;
 	can_skb_prv(skb)->skbcnt = 0;
 
-	*cfd = skb_put(skb, sizeof(struct canfd_frame));
-	memset(*cfd, 0, sizeof(struct canfd_frame));
+	*cfd = skb_put_zero(skb, sizeof(struct canfd_frame));
 
 	return skb;
 }
-- 
cgit v1.2.3


From 038709071328ff68a936c6b8c33a24a805eea3c5 Mon Sep 17 00:00:00 2001
From: Zhu Yi <yi.zhu5@cn.bosch.com>
Date: Wed, 13 Jun 2018 16:37:17 +0200
Subject: can: dev: enable multi-queue for SocketCAN devices

The existing SocketCAN implementation provides alloc_candev() to
allocate a CAN device using a single Tx and Rx queue. This can lead to
priority inversion in case the single Tx queue is already full with low
priority messages and a high priority message needs to be sent while the
bus is fully loaded with medium priority messages.

This problem can be solved by using the existing multi-queue support of
the network subsytem. The commit makes it possible to use multi-queue in
the CAN subsystem in the same way it is used in the Ethernet subsystem
by adding an alloc_candev_mqs() call and accompanying macros. With this
support a CAN device can use multi-queue qdisc (e.g. mqprio) to avoid
the aforementioned priority inversion.

The exisiting functionality of alloc_candev() is the same as before.

CAN devices need to have prioritized multiple hardware queues or are
able to abort waiting for arbitration to make sensible use of
multi-queues.

Signed-off-by: Zhu Yi <yi.zhu5@cn.bosch.com>
Signed-off-by: Mark Jonas <mark.jonas@de.bosch.com>
Reviewed-by: Heiko Schocher <hs@denx.de>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev.c   | 8 +++++---
 include/linux/can/dev.h | 7 ++++++-
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/dev.c b/drivers/net/can/dev.c
index 5bb6e8896601..49163570a63a 100644
--- a/drivers/net/can/dev.c
+++ b/drivers/net/can/dev.c
@@ -701,7 +701,8 @@ EXPORT_SYMBOL_GPL(alloc_can_err_skb);
 /*
  * Allocate and setup space for the CAN network device
  */
-struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
+struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
+				    unsigned int txqs, unsigned int rxqs)
 {
 	struct net_device *dev;
 	struct can_priv *priv;
@@ -713,7 +714,8 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
 	else
 		size = sizeof_priv;
 
-	dev = alloc_netdev(size, "can%d", NET_NAME_UNKNOWN, can_setup);
+	dev = alloc_netdev_mqs(size, "can%d", NET_NAME_UNKNOWN, can_setup,
+			       txqs, rxqs);
 	if (!dev)
 		return NULL;
 
@@ -732,7 +734,7 @@ struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max)
 
 	return dev;
 }
-EXPORT_SYMBOL_GPL(alloc_candev);
+EXPORT_SYMBOL_GPL(alloc_candev_mqs);
 
 /*
  * Free space of the CAN network device
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 055aaf5ed9af..a83e1f632eb7 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -143,7 +143,12 @@ u8 can_dlc2len(u8 can_dlc);
 /* map the sanitized data length to an appropriate data length code */
 u8 can_len2dlc(u8 len);
 
-struct net_device *alloc_candev(int sizeof_priv, unsigned int echo_skb_max);
+struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
+				    unsigned int txqs, unsigned int rxqs);
+#define alloc_candev(sizeof_priv, echo_skb_max) \
+	alloc_candev_mqs(sizeof_priv, echo_skb_max, 1, 1)
+#define alloc_candev_mq(sizeof_priv, echo_skb_max, count) \
+	alloc_candev_mqs(sizeof_priv, echo_skb_max, count, count)
 void free_candev(struct net_device *dev);
 
 /* a candev safe wrapper around netdev_priv */
-- 
cgit v1.2.3


From 67c2eef22e2b5cdc45dad51bb36277362c04bccc Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Thu, 26 Apr 2018 23:13:36 +0200
Subject: can: janz-ican3: fix ican3_xmit()'s return type

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.

Fix this by returning 'netdev_tx_t' in this driver too.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/janz-ican3.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/janz-ican3.c b/drivers/net/can/janz-ican3.c
index adfdb66a486e..02042cb09bd2 100644
--- a/drivers/net/can/janz-ican3.c
+++ b/drivers/net/can/janz-ican3.c
@@ -1684,7 +1684,7 @@ static int ican3_stop(struct net_device *ndev)
 	return 0;
 }
 
-static int ican3_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t ican3_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct ican3_dev *mod = netdev_priv(ndev);
 	struct can_frame *cf = (struct can_frame *)skb->data;
-- 
cgit v1.2.3


From 79b110bb0b608a4f7d03d6d6a0d8eb03453d65cc Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Thu, 26 Apr 2018 23:13:37 +0200
Subject: can: sun4i: fix sun4ican_start_xmit()'s return type

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.

Fix this by returning 'netdev_tx_t' in this driver too.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/sun4i_can.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/sun4i_can.c b/drivers/net/can/sun4i_can.c
index 1ac2090a1721..093fc9a529f0 100644
--- a/drivers/net/can/sun4i_can.c
+++ b/drivers/net/can/sun4i_can.c
@@ -409,7 +409,7 @@ static int sun4ican_set_mode(struct net_device *dev, enum can_mode mode)
  * xx xx xx xx         ff         ll 00 11 22 33 44 55 66 77
  * [ can_id ] [flags] [len] [can data (up to 8 bytes]
  */
-static int sun4ican_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t sun4ican_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct sun4ican_priv *priv = netdev_priv(dev);
 	struct can_frame *cf = (struct can_frame *)skb->data;
-- 
cgit v1.2.3


From 97f2a5893ca539bfc308c8abf0a36d678305c854 Mon Sep 17 00:00:00 2001
From: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Date: Thu, 26 Apr 2018 23:13:38 +0200
Subject: can: xilinx: fix xcan_start_xmit()'s return type

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.

Fix this by returning 'netdev_tx_t' in this driver too.

Signed-off-by: Luc Van Oostenryck <luc.vanoostenryck@gmail.com>
Acked-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 5a24039733ef..545f69476866 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -398,9 +398,9 @@ static int xcan_do_set_mode(struct net_device *ndev, enum can_mode mode)
  * function uses the next available free txbuff and populates their fields to
  * start the transmission.
  *
- * Return: 0 on success and failure value on error
+ * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY when the tx queue is full
  */
-static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &ndev->stats;
-- 
cgit v1.2.3


From fb1e13e6daf443b5b0bd37f5390961c49e0bb280 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Thu, 26 Apr 2018 23:13:38 +0200
Subject: can: flexcan: fix flexcan_start_xmit()'s return type

The method ndo_start_xmit() is defined as returning an 'netdev_tx_t',
which is a typedef for an enum type, but the implementation in this
driver returns an 'int'.

Fix this by returning 'netdev_tx_t' in this driver too.

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index d53a45bf2a72..c1b8c472a82e 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -523,7 +523,7 @@ static int flexcan_get_berr_counter(const struct net_device *dev,
 	return err;
 }
 
-static int flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t flexcan_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	const struct flexcan_priv *priv = netdev_priv(dev);
 	struct can_frame *cf = (struct can_frame *)skb->data;
-- 
cgit v1.2.3


From 5b749be31d4ce674c013fb0620fddbce89a0d85f Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Fri, 6 Jul 2018 14:35:12 -0300
Subject: can: flexcan: Switch to SPDX identifier

Adopt the SPDX license identifier headers to ease license compliance
management.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan.c | 31 ++++++++++---------------------
 1 file changed, 10 insertions(+), 21 deletions(-)

diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index c1b8c472a82e..8e972ef08637 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -1,24 +1,13 @@
-/*
- * flexcan.c - FLEXCAN CAN controller driver
- *
- * Copyright (c) 2005-2006 Varma Electronics Oy
- * Copyright (c) 2009 Sascha Hauer, Pengutronix
- * Copyright (c) 2010-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
- * Copyright (c) 2014 David Jander, Protonic Holland
- *
- * Based on code originally by Andrey Volkov <avolkov@varma-el.com>
- *
- * LICENCE:
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// flexcan.c - FLEXCAN CAN controller driver
+//
+// Copyright (c) 2005-2006 Varma Electronics Oy
+// Copyright (c) 2009 Sascha Hauer, Pengutronix
+// Copyright (c) 2010-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
+// Copyright (c) 2014 David Jander, Protonic Holland
+//
+// Based on code originally by Andrey Volkov <avolkov@varma-el.com>
 
 #include <linux/netdevice.h>
 #include <linux/can.h>
-- 
cgit v1.2.3


From 276b7361bb1be3dccbc10b5be93cfee4bef2249c Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Wed, 11 Apr 2018 09:42:58 +0800
Subject: can: sja1000: Replace mdelay with usleep_range in peak_pci_probe

peak_pci_probe() is never called in atomic context.

peak_pci_probe() is set as ".probe" in struct pci_driver.

Despite never getting called from atomic context, peak_pci_probe()
calls mdelay() to busily wait.
This is not necessary and can be replaced with usleep_range() to
avoid busy waiting.

This is found by a static analysis tool named DCNS written by myself.
And I also manually check it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/sja1000/peak_pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/sja1000/peak_pci.c b/drivers/net/can/sja1000/peak_pci.c
index 5adc95c922ee..a97b81d1d0da 100644
--- a/drivers/net/can/sja1000/peak_pci.c
+++ b/drivers/net/can/sja1000/peak_pci.c
@@ -608,7 +608,7 @@ static int peak_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	writeb(0x00, cfg_base + PITA_GPIOICR);
 	/* Toggle reset */
 	writeb(0x05, cfg_base + PITA_MISC + 3);
-	mdelay(5);
+	usleep_range(5000, 6000);
 	/* Leave parport mux mode */
 	writeb(0x04, cfg_base + PITA_MISC + 3);
 
-- 
cgit v1.2.3


From c8d4dea2a82b0e1c695646aaabdada130ab71f79 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Wed, 11 Apr 2018 09:43:26 +0800
Subject: can: sja1000: Replace mdelay with usleep_range in pcan_add_channels

pcan_add_channels() is never called in atomic context.

pcan_add_channels() is only called by pcan_probe(), which is only set as
".probe" in struct pcmcia_driver.

Despite never getting called from atomic context, pcan_add_channels()
calls mdelay() to busily wait.
This is not necessary and can be replaced with usleep_range() to
avoid busy waiting.

This is found by a static analysis tool named DCNS written by myself.
And I also manually check it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/sja1000/peak_pcmcia.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/sja1000/peak_pcmcia.c b/drivers/net/can/sja1000/peak_pcmcia.c
index 485b19c9ae47..b8c39ede7cd5 100644
--- a/drivers/net/can/sja1000/peak_pcmcia.c
+++ b/drivers/net/can/sja1000/peak_pcmcia.c
@@ -530,7 +530,7 @@ static int pcan_add_channels(struct pcan_pccard *card)
 	pcan_write_reg(card, PCC_CCR, ccr);
 
 	/* wait 2ms before unresetting channels */
-	mdelay(2);
+	usleep_range(2000, 3000);
 
 	ccr &= ~PCC_CCR_RST_ALL;
 	pcan_write_reg(card, PCC_CCR, ccr);
-- 
cgit v1.2.3


From 7e2804aae1288643f3d3d5c018feefc98c098509 Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Wed, 8 Feb 2017 13:32:43 +0200
Subject: can: xilinx_can: only report warning and passive states on state
 changes

The xilinx_can driver currently increments error-warning and
error-passive statistics on every error interrupt regardless of whether
the interface was already in the same state. Similarly, the error frame
sent on error interrupts is always sent with
CAN_ERR_CRTL_(RX|TX)_(PASSIVE|WARNING) bit set.

To make the error-warning and error-passive statistics more useful, add
a check to only set the error state when the state has actually been
changed.

Tested with the integrated CAN on Zynq-7000 SoC.

Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 545f69476866..32e49acd4ebd 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -703,7 +703,8 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 	} else {
 		enum can_state new_state = xcan_current_error_state(ndev);
 
-		xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
+		if (new_state != priv->can.state)
+			xcan_set_error_state(ndev, new_state, skb ? cf : NULL);
 	}
 
 	/* Check for Arbitration lost interrupt */
-- 
cgit v1.2.3


From 6181dbc02b6c73fd2e07d06bb8766867bb96ebbe Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Mon, 29 Jan 2018 17:28:24 +0200
Subject: can: xilinx_can: use can_change_state()

Replace some custom code with a call to can_change_state().

This subtly changes the error reporting behavior when both RX and TX
error counters indicate the same state.

Previously, if both RX and TX counters indicated the same state:
- if overall state is PASSIVE, report CAN_ERR_CRTL_RX_PASSIVE
- if overall state is WARNING, report CAN_ERR_CRTL_TX_WARNING or
  CAN_ERR_CRTL_RX_WARNING depending on which counter is higher,
  or CAN_ERR_CRTL_RX_WARNING if the counters have the same value.

After this commit:
- report RX_* or TX_* depending on which counter is higher, or both if
  the counters have exactly the same value.

This behavior is consistent with many other CAN drivers that use this
same code pattern.

Tested with the integrated CAN on Zynq-7000 SoC.

v2: Simplify resolving states as suggested by Andri Yngvason.

Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 34 +++++++---------------------------
 1 file changed, 7 insertions(+), 27 deletions(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 32e49acd4ebd..c7e5373a8f3c 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -594,39 +594,19 @@ static void xcan_set_error_state(struct net_device *ndev,
 	u32 ecr = priv->read_reg(priv, XCAN_ECR_OFFSET);
 	u32 txerr = ecr & XCAN_ECR_TEC_MASK;
 	u32 rxerr = (ecr & XCAN_ECR_REC_MASK) >> XCAN_ESR_REC_SHIFT;
+	enum can_state tx_state = txerr >= rxerr ? new_state : 0;
+	enum can_state rx_state = txerr <= rxerr ? new_state : 0;
 
-	priv->can.state = new_state;
+	/* non-ERROR states are handled elsewhere */
+	if (WARN_ON(new_state > CAN_STATE_ERROR_PASSIVE))
+		return;
+
+	can_change_state(ndev, cf, tx_state, rx_state);
 
 	if (cf) {
-		cf->can_id |= CAN_ERR_CRTL;
 		cf->data[6] = txerr;
 		cf->data[7] = rxerr;
 	}
-
-	switch (new_state) {
-	case CAN_STATE_ERROR_PASSIVE:
-		priv->can.can_stats.error_passive++;
-		if (cf)
-			cf->data[1] = (rxerr > 127) ?
-					CAN_ERR_CRTL_RX_PASSIVE :
-					CAN_ERR_CRTL_TX_PASSIVE;
-		break;
-	case CAN_STATE_ERROR_WARNING:
-		priv->can.can_stats.error_warning++;
-		if (cf)
-			cf->data[1] |= (txerr > rxerr) ?
-					CAN_ERR_CRTL_TX_WARNING :
-					CAN_ERR_CRTL_RX_WARNING;
-		break;
-	case CAN_STATE_ERROR_ACTIVE:
-		if (cf)
-			cf->data[1] |= CAN_ERR_CRTL_ACTIVE;
-		break;
-	default:
-		/* non-ERROR states are handled elsewhere */
-		WARN_ON(1);
-		break;
-	}
 }
 
 /**
-- 
cgit v1.2.3


From 11ee5fcd6af37b1107aa0e8980a40f8e17703c0b Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Mon, 26 Feb 2018 14:50:35 +0200
Subject: can: xilinx_can: update stats.tx_bytes after transmission

The driver updates stats.tx_bytes in start_xmit() even though it could
do so in TX interrupt handler.

Change the code to update tx_bytes in the interrupt handler, using the
return value of can_get_echo_skb().

Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Cc: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index c7e5373a8f3c..9bce846acfcc 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -403,7 +403,6 @@ static int xcan_do_set_mode(struct net_device *ndev, enum can_mode mode)
 static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
-	struct net_device_stats *stats = &ndev->stats;
 	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 id, dlc, data[2] = {0, 0};
 	unsigned long flags;
@@ -469,7 +468,6 @@ static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 		 * write triggers tranmission
 		 */
 		priv->write_reg(priv, XCAN_TXFIFO_DW2_OFFSET, data[1]);
-		stats->tx_bytes += cf->can_dlc;
 	}
 
 	/* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
@@ -889,8 +887,8 @@ static void xcan_tx_interrupt(struct net_device *ndev, u32 isr)
 	}
 
 	while (frames_sent--) {
-		can_get_echo_skb(ndev, priv->tx_tail %
-					priv->tx_max);
+		stats->tx_bytes += can_get_echo_skb(ndev, priv->tx_tail %
+						    priv->tx_max);
 		priv->tx_tail++;
 		stats->tx_packets++;
 	}
-- 
cgit v1.2.3


From 7cb0f17f5252874ba0ecbda964e7e01587bf828e Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Fri, 18 May 2018 15:31:48 +0300
Subject: dt-bindings: can: xilinx_can: add Xilinx CAN FD bindings

Add compatible string and new attributes to support the Xilinx CAN FD
core.

Unlike the previously documented Xilinx CAN cores, the CAN FD core has
TX mailboxes instead of TX FIFO, and optionally RX mailboxes instead of
RX FIFO (selected at core generation time, not switchable at runtime).
Add "tx-mailbox-count" and "rx-mailbox-count" to specify the mailbox
counts instead of reusing "tx-fifo-depth" and "rx-fifo-depth".

The RX FIFO depth is constant 32, but allow it to be specified via
"rx-fifo-depth" to match DT usage with Zynq CAN (which has constant RX
FIFO of depth of 64).

v2: Remove unnecessary "rx-mode" DT property.

Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Cc: Michal Simek <michal.simek@xilinx.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../devicetree/bindings/net/can/xilinx_can.txt     | 35 ++++++++++++++++------
 1 file changed, 26 insertions(+), 9 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/can/xilinx_can.txt b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
index fe38847d8e26..ae5c07e96ad5 100644
--- a/Documentation/devicetree/bindings/net/can/xilinx_can.txt
+++ b/Documentation/devicetree/bindings/net/can/xilinx_can.txt
@@ -2,20 +2,26 @@ Xilinx Axi CAN/Zynq CANPS controller Device Tree Bindings
 ---------------------------------------------------------
 
 Required properties:
-- compatible		: Should be "xlnx,zynq-can-1.0" for Zynq CAN
-			  controllers and "xlnx,axi-can-1.00.a" for Axi CAN
-			  controllers.
-- reg			: Physical base address and size of the Axi CAN/Zynq
-			  CANPS registers map.
+- compatible		: Should be:
+			  - "xlnx,zynq-can-1.0" for Zynq CAN controllers
+			  - "xlnx,axi-can-1.00.a" for Axi CAN controllers
+			  - "xlnx,canfd-1.0" for CAN FD controllers
+- reg			: Physical base address and size of the controller
+			  registers map.
 - interrupts		: Property with a value describing the interrupt
 			  number.
 - interrupt-parent	: Must be core interrupt controller
-- clock-names		: List of input clock names - "can_clk", "pclk"
-			  (For CANPS), "can_clk" , "s_axi_aclk"(For AXI CAN)
+- clock-names		: List of input clock names
+			  - "can_clk", "pclk" (For CANPS),
+			  - "can_clk", "s_axi_aclk" (For AXI CAN and CAN FD).
 			  (See clock bindings for details).
 - clocks		: Clock phandles (see clock bindings for details).
-- tx-fifo-depth		: Can Tx fifo depth.
-- rx-fifo-depth		: Can Rx fifo depth.
+- tx-fifo-depth		: Can Tx fifo depth (Zynq, Axi CAN).
+- rx-fifo-depth		: Can Rx fifo depth (Zynq, Axi CAN, CAN FD in
+                          sequential Rx mode).
+- tx-mailbox-count	: Can Tx mailbox buffer count (CAN FD).
+- rx-mailbox-count	: Can Rx mailbox buffer count (CAN FD in mailbox Rx
+			  mode).
 
 
 Example:
@@ -42,3 +48,14 @@ For Axi CAN Dts file:
 			tx-fifo-depth = <0x40>;
 			rx-fifo-depth = <0x40>;
 		};
+For CAN FD Dts file:
+	canfd_0: canfd@40000000 {
+			compatible = "xlnx,canfd-1.0";
+			clocks = <&clkc 0>, <&clkc 1>;
+			clock-names = "can_clk", "s_axi_aclk";
+			reg = <0x40000000 0x2000>;
+			interrupt-parent = <&intc>;
+			interrupts = <0 59 1>;
+			tx-mailbox-count = <0x20>;
+			rx-fifo-depth = <0x20>;
+		};
-- 
cgit v1.2.3


From 1598efe57b3e768056e4ca56cb9cf33111e68d1c Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Mon, 26 Feb 2018 15:56:51 +0200
Subject: can: xilinx_can: refactor code in preparation for CAN FD support

Xilinx CAN FD cores are different enough from the previous Zynq and AXI
CAN cores that some refactoring of the driver is needed.

This commit contains most of the required refactoring to existing code
and should not alter behavior on existing supported HW.

The changes are:

- Reading and writing to frame registers is parametrized to allow
  reading/writing a different frame in the future.

- Slightly misleading (as it did not specify *all* the interrupts
  supported by the HW) XCAN_INTR_ALL is replaced with specifying the
  interrupts inline in interrupt enabling code.

- xcan_devtype_data.caps is renamed to xcan_devtype_data.flags to allow
  for flags that define alternative functionality (e.g. mailboxes vs.
  FIFO) instead of purely additive capabilities.

- can_bittiming_const is added to xcan_devtype_data as CAN FD cores will
  have wider setting ranges.

- bus_clk clock name is now determined through xcan_devtype_data instead
  of comparing compatible string in probe().

- xcan_devtype_data is added to xcan_priv to allow flag checks after
  probe().

- XCAN_CAP_WATERMARK is now XCAN_FLAG_TXFEMP. CAN FD cores have
  watermark support but no TXFEMP interrupt, which is what we are
  actually interested in.

- xcan_start_xmit() is split to in two parts to prepare for TX mailboxes
  instead of FIFO in CAN FD cores.

v2: Wrapped some long lines in xcan_write_frame().

Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Cc: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 206 +++++++++++++++++++++++++------------------
 1 file changed, 118 insertions(+), 88 deletions(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 9bce846acfcc..204a7890dc9c 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -51,16 +51,15 @@ enum xcan_reg {
 	XCAN_ISR_OFFSET		= 0x1C, /* Interrupt status */
 	XCAN_IER_OFFSET		= 0x20, /* Interrupt enable */
 	XCAN_ICR_OFFSET		= 0x24, /* Interrupt clear */
-	XCAN_TXFIFO_ID_OFFSET	= 0x30,/* TX FIFO ID */
-	XCAN_TXFIFO_DLC_OFFSET	= 0x34, /* TX FIFO DLC */
-	XCAN_TXFIFO_DW1_OFFSET	= 0x38, /* TX FIFO Data Word 1 */
-	XCAN_TXFIFO_DW2_OFFSET	= 0x3C, /* TX FIFO Data Word 2 */
-	XCAN_RXFIFO_ID_OFFSET	= 0x50, /* RX FIFO ID */
-	XCAN_RXFIFO_DLC_OFFSET	= 0x54, /* RX FIFO DLC */
-	XCAN_RXFIFO_DW1_OFFSET	= 0x58, /* RX FIFO Data Word 1 */
-	XCAN_RXFIFO_DW2_OFFSET	= 0x5C, /* RX FIFO Data Word 2 */
+	XCAN_TXFIFO_OFFSET	= 0x30, /* TX FIFO base */
+	XCAN_RXFIFO_OFFSET	= 0x50, /* RX FIFO base */
 };
 
+#define XCAN_FRAME_ID_OFFSET(frame_base)	((frame_base) + 0x00)
+#define XCAN_FRAME_DLC_OFFSET(frame_base)	((frame_base) + 0x04)
+#define XCAN_FRAME_DW1_OFFSET(frame_base)	((frame_base) + 0x08)
+#define XCAN_FRAME_DW2_OFFSET(frame_base)	((frame_base) + 0x0C)
+
 /* CAN register bit masks - XCAN_<REG>_<BIT>_MASK */
 #define XCAN_SRR_CEN_MASK		0x00000002 /* CAN enable */
 #define XCAN_SRR_RESET_MASK		0x00000001 /* Soft Reset the CAN core */
@@ -101,11 +100,6 @@ enum xcan_reg {
 #define XCAN_IDR_RTR_MASK		0x00000001 /* Remote TX request */
 #define XCAN_DLCR_DLC_MASK		0xF0000000 /* Data length code */
 
-#define XCAN_INTR_ALL		(XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |\
-				 XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK | \
-				 XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK | \
-				 XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK)
-
 /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
 #define XCAN_BTR_SJW_SHIFT		7  /* Synchronous jump width */
 #define XCAN_BTR_TS2_SHIFT		4  /* Time segment 2 */
@@ -118,6 +112,15 @@ enum xcan_reg {
 #define XCAN_FRAME_MAX_DATA_LEN		8
 #define XCAN_TIMEOUT			(1 * HZ)
 
+/* TX-FIFO-empty interrupt available */
+#define XCAN_FLAG_TXFEMP	0x0001
+
+struct xcan_devtype_data {
+	unsigned int flags;
+	const struct can_bittiming_const *bittiming_const;
+	const char *bus_clk_name;
+};
+
 /**
  * struct xcan_priv - This definition define CAN driver instance
  * @can:			CAN private data structure.
@@ -133,6 +136,7 @@ enum xcan_reg {
  * @irq_flags:			For request_irq()
  * @bus_clk:			Pointer to struct clk
  * @can_clk:			Pointer to struct clk
+ * @devtype:			Device type specific constants
  */
 struct xcan_priv {
 	struct can_priv can;
@@ -149,6 +153,7 @@ struct xcan_priv {
 	unsigned long irq_flags;
 	struct clk *bus_clk;
 	struct clk *can_clk;
+	struct xcan_devtype_data devtype;
 };
 
 /* CAN Bittiming constants as per Xilinx CAN specs */
@@ -164,11 +169,6 @@ static const struct can_bittiming_const xcan_bittiming_const = {
 	.brp_inc = 1,
 };
 
-#define XCAN_CAP_WATERMARK	0x0001
-struct xcan_devtype_data {
-	unsigned int caps;
-};
-
 /**
  * xcan_write_reg_le - Write a value to the device register little endian
  * @priv:	Driver private data structure
@@ -329,7 +329,11 @@ static int xcan_chip_start(struct net_device *ndev)
 		return err;
 
 	/* Enable interrupts */
-	priv->write_reg(priv, XCAN_IER_OFFSET, XCAN_INTR_ALL);
+	priv->write_reg(priv, XCAN_IER_OFFSET,
+			XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |
+			XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK |
+			XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK |
+			XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK);
 
 	/* Check whether it is loopback mode or normal mode  */
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) {
@@ -390,33 +394,15 @@ static int xcan_do_set_mode(struct net_device *ndev, enum can_mode mode)
 }
 
 /**
- * xcan_start_xmit - Starts the transmission
- * @skb:	sk_buff pointer that contains data to be Txed
- * @ndev:	Pointer to net_device structure
- *
- * This function is invoked from upper layers to initiate transmission. This
- * function uses the next available free txbuff and populates their fields to
- * start the transmission.
- *
- * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY when the tx queue is full
+ * xcan_write_frame - Write a frame to HW
+ * @skb:		sk_buff pointer that contains data to be Txed
+ * @frame_offset:	Register offset to write the frame to
  */
-static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+static void xcan_write_frame(struct xcan_priv *priv, struct sk_buff *skb,
+			     int frame_offset)
 {
-	struct xcan_priv *priv = netdev_priv(ndev);
-	struct can_frame *cf = (struct can_frame *)skb->data;
 	u32 id, dlc, data[2] = {0, 0};
-	unsigned long flags;
-
-	if (can_dropped_invalid_skb(ndev, skb))
-		return NETDEV_TX_OK;
-
-	/* Check if the TX buffer is full */
-	if (unlikely(priv->read_reg(priv, XCAN_SR_OFFSET) &
-			XCAN_SR_TXFLL_MASK)) {
-		netif_stop_queue(ndev);
-		netdev_err(ndev, "BUG!, TX FIFO full when queue awake!\n");
-		return NETDEV_TX_BUSY;
-	}
+	struct can_frame *cf = (struct can_frame *)skb->data;
 
 	/* Watch carefully on the bit sequence */
 	if (cf->can_id & CAN_EFF_FLAG) {
@@ -452,23 +438,42 @@ static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	if (cf->can_dlc > 4)
 		data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
 
+	priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id);
+	/* If the CAN frame is RTR frame this write triggers transmission */
+	priv->write_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_offset), dlc);
+	if (!(cf->can_id & CAN_RTR_FLAG)) {
+		priv->write_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_offset),
+				data[0]);
+		/* If the CAN frame is Standard/Extended frame this
+		 * write triggers transmission
+		 */
+		priv->write_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_offset),
+				data[1]);
+	}
+}
+
+/**
+ * xcan_start_xmit_fifo - Starts the transmission (FIFO mode)
+ *
+ * Return: 0 on success, -ENOSPC if FIFO is full.
+ */
+static int xcan_start_xmit_fifo(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	unsigned long flags;
+
+	/* Check if the TX buffer is full */
+	if (unlikely(priv->read_reg(priv, XCAN_SR_OFFSET) &
+			XCAN_SR_TXFLL_MASK))
+		return -ENOSPC;
+
 	can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max);
 
 	spin_lock_irqsave(&priv->tx_lock, flags);
 
 	priv->tx_head++;
 
-	/* Write the Frame to Xilinx CAN TX FIFO */
-	priv->write_reg(priv, XCAN_TXFIFO_ID_OFFSET, id);
-	/* If the CAN frame is RTR frame this write triggers tranmission */
-	priv->write_reg(priv, XCAN_TXFIFO_DLC_OFFSET, dlc);
-	if (!(cf->can_id & CAN_RTR_FLAG)) {
-		priv->write_reg(priv, XCAN_TXFIFO_DW1_OFFSET, data[0]);
-		/* If the CAN frame is Standard/Extended frame this
-		 * write triggers tranmission
-		 */
-		priv->write_reg(priv, XCAN_TXFIFO_DW2_OFFSET, data[1]);
-	}
+	xcan_write_frame(priv, skb, XCAN_TXFIFO_OFFSET);
 
 	/* Clear TX-FIFO-empty interrupt for xcan_tx_interrupt() */
 	if (priv->tx_max > 1)
@@ -480,6 +485,35 @@ static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	spin_unlock_irqrestore(&priv->tx_lock, flags);
 
+	return 0;
+}
+
+/**
+ * xcan_start_xmit - Starts the transmission
+ * @skb:	sk_buff pointer that contains data to be Txed
+ * @ndev:	Pointer to net_device structure
+ *
+ * This function is invoked from upper layers to initiate transmission. This
+ * function uses the next available free txbuff and populates their fields to
+ * start the transmission.
+ *
+ * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY when the tx queue is full
+ */
+static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
+{
+	int ret;
+
+	if (can_dropped_invalid_skb(ndev, skb))
+		return NETDEV_TX_OK;
+
+	ret = xcan_start_xmit_fifo(skb, ndev);
+
+	if (ret < 0) {
+		netdev_err(ndev, "BUG!, TX full when queue awake!\n");
+		netif_stop_queue(ndev);
+		return NETDEV_TX_BUSY;
+	}
+
 	return NETDEV_TX_OK;
 }
 
@@ -487,13 +521,14 @@ static netdev_tx_t xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
  * xcan_rx -  Is called from CAN isr to complete the received
  *		frame  processing
  * @ndev:	Pointer to net_device structure
+ * @frame_base:	Register offset to the frame to be read
  *
  * This function is invoked from the CAN isr(poll) to process the Rx frames. It
  * does minimal processing and invokes "netif_receive_skb" to complete further
  * processing.
  * Return: 1 on success and 0 on failure.
  */
-static int xcan_rx(struct net_device *ndev)
+static int xcan_rx(struct net_device *ndev, int frame_base)
 {
 	struct xcan_priv *priv = netdev_priv(ndev);
 	struct net_device_stats *stats = &ndev->stats;
@@ -508,9 +543,9 @@ static int xcan_rx(struct net_device *ndev)
 	}
 
 	/* Read a frame from Xilinx zynq CANPS */
-	id_xcan = priv->read_reg(priv, XCAN_RXFIFO_ID_OFFSET);
-	dlc = priv->read_reg(priv, XCAN_RXFIFO_DLC_OFFSET) >>
-				XCAN_DLCR_DLC_SHIFT;
+	id_xcan = priv->read_reg(priv, XCAN_FRAME_ID_OFFSET(frame_base));
+	dlc = priv->read_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_base)) >>
+				   XCAN_DLCR_DLC_SHIFT;
 
 	/* Change Xilinx CAN data length format to socketCAN data format */
 	cf->can_dlc = get_can_dlc(dlc);
@@ -533,8 +568,8 @@ static int xcan_rx(struct net_device *ndev)
 	}
 
 	/* DW1/DW2 must always be read to remove message from RXFIFO */
-	data[0] = priv->read_reg(priv, XCAN_RXFIFO_DW1_OFFSET);
-	data[1] = priv->read_reg(priv, XCAN_RXFIFO_DW2_OFFSET);
+	data[0] = priv->read_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_base));
+	data[1] = priv->read_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_base));
 
 	if (!(cf->can_id & CAN_RTR_FLAG)) {
 		/* Change Xilinx CAN data format to socketCAN data format */
@@ -806,7 +841,7 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
-		work_done += xcan_rx(ndev);
+		work_done += xcan_rx(ndev, XCAN_RXFIFO_OFFSET);
 		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
 		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
 	}
@@ -1193,13 +1228,21 @@ static const struct dev_pm_ops xcan_dev_pm_ops = {
 };
 
 static const struct xcan_devtype_data xcan_zynq_data = {
-	.caps = XCAN_CAP_WATERMARK,
+	.flags = XCAN_FLAG_TXFEMP,
+	.bittiming_const = &xcan_bittiming_const,
+	.bus_clk_name = "pclk",
+};
+
+static const struct xcan_devtype_data xcan_axi_data = {
+	.flags = 0,
+	.bittiming_const = &xcan_bittiming_const,
+	.bus_clk_name = "s_axi_aclk",
 };
 
 /* Match table for OF platform binding */
 static const struct of_device_id xcan_of_match[] = {
 	{ .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
-	{ .compatible = "xlnx,axi-can-1.00.a", },
+	{ .compatible = "xlnx,axi-can-1.00.a", .data = &xcan_axi_data },
 	{ /* end of list */ },
 };
 MODULE_DEVICE_TABLE(of, xcan_of_match);
@@ -1219,7 +1262,7 @@ static int xcan_probe(struct platform_device *pdev)
 	struct net_device *ndev;
 	struct xcan_priv *priv;
 	const struct of_device_id *of_id;
-	int caps = 0;
+	const struct xcan_devtype_data *devtype = &xcan_axi_data;
 	void __iomem *addr;
 	int ret, rx_max, tx_max, tx_fifo_depth;
 
@@ -1241,12 +1284,8 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 
 	of_id = of_match_device(xcan_of_match, &pdev->dev);
-	if (of_id) {
-		const struct xcan_devtype_data *devtype_data = of_id->data;
-
-		if (devtype_data)
-			caps = devtype_data->caps;
-	}
+	if (of_id && of_id->data)
+		devtype = of_id->data;
 
 	/* There is no way to directly figure out how many frames have been
 	 * sent when the TXOK interrupt is processed. If watermark programming
@@ -1259,7 +1298,7 @@ static int xcan_probe(struct platform_device *pdev)
 	 * sent), which is not a sensible state - possibly TXFWMEMP is not
 	 * completely synchronized with the rest of the bits?
 	 */
-	if (caps & XCAN_CAP_WATERMARK)
+	if (devtype->flags & XCAN_FLAG_TXFEMP)
 		tx_max = min(tx_fifo_depth, 2);
 	else
 		tx_max = 1;
@@ -1271,13 +1310,14 @@ static int xcan_probe(struct platform_device *pdev)
 
 	priv = netdev_priv(ndev);
 	priv->dev = &pdev->dev;
-	priv->can.bittiming_const = &xcan_bittiming_const;
+	priv->can.bittiming_const = devtype->bittiming_const;
 	priv->can.do_set_mode = xcan_do_set_mode;
 	priv->can.do_get_berr_counter = xcan_get_berr_counter;
 	priv->can.ctrlmode_supported = CAN_CTRLMODE_LOOPBACK |
 					CAN_CTRLMODE_BERR_REPORTING;
 	priv->reg_base = addr;
 	priv->tx_max = tx_max;
+	priv->devtype = *devtype;
 	spin_lock_init(&priv->tx_lock);
 
 	/* Get IRQ for the device */
@@ -1295,22 +1335,12 @@ static int xcan_probe(struct platform_device *pdev)
 		ret = PTR_ERR(priv->can_clk);
 		goto err_free;
 	}
-	/* Check for type of CAN device */
-	if (of_device_is_compatible(pdev->dev.of_node,
-				    "xlnx,zynq-can-1.0")) {
-		priv->bus_clk = devm_clk_get(&pdev->dev, "pclk");
-		if (IS_ERR(priv->bus_clk)) {
-			dev_err(&pdev->dev, "bus clock not found\n");
-			ret = PTR_ERR(priv->bus_clk);
-			goto err_free;
-		}
-	} else {
-		priv->bus_clk = devm_clk_get(&pdev->dev, "s_axi_aclk");
-		if (IS_ERR(priv->bus_clk)) {
-			dev_err(&pdev->dev, "bus clock not found\n");
-			ret = PTR_ERR(priv->bus_clk);
-			goto err_free;
-		}
+
+	priv->bus_clk = devm_clk_get(&pdev->dev, devtype->bus_clk_name);
+	if (IS_ERR(priv->bus_clk)) {
+		dev_err(&pdev->dev, "bus clock not found\n");
+		ret = PTR_ERR(priv->bus_clk);
+		goto err_free;
 	}
 
 	priv->write_reg = xcan_write_reg_le;
-- 
cgit v1.2.3


From 9e5f1b273e6abdd7f17b15a65ff5414c6c94384b Mon Sep 17 00:00:00 2001
From: Anssi Hannula <anssi.hannula@bitwise.fi>
Date: Tue, 27 Feb 2018 10:06:51 +0200
Subject: can: xilinx_can: add support for Xilinx CAN FD core

Add support for Xilinx CAN FD core.

The major difference from the previously supported cores is that there
are TX mailboxes instead of a TX FIFO and the RX FIFO access method is
different.

We only transmit one frame at a time to prevent the HW from reordering
frames (it uses CAN ID priority order).

Support for CAN FD protocol is not added yet.

v2: Removed unnecessary "rx-mode" DT property and wrapped some long
    lines.

Signed-off-by: Anssi Hannula <anssi.hannula@bitwise.fi>
Cc: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/xilinx_can.c | 303 ++++++++++++++++++++++++++++++++++++-------
 1 file changed, 259 insertions(+), 44 deletions(-)

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 204a7890dc9c..045f0845e665 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -2,7 +2,7 @@
  *
  * Copyright (C) 2012 - 2014 Xilinx, Inc.
  * Copyright (C) 2009 PetaLogix. All rights reserved.
- * Copyright (C) 2017 Sandvik Mining and Construction Oy
+ * Copyright (C) 2017 - 2018 Sandvik Mining and Construction Oy
  *
  * Description:
  * This driver is developed for Axi CAN IP and for Zynq CANPS Controller.
@@ -51,8 +51,18 @@ enum xcan_reg {
 	XCAN_ISR_OFFSET		= 0x1C, /* Interrupt status */
 	XCAN_IER_OFFSET		= 0x20, /* Interrupt enable */
 	XCAN_ICR_OFFSET		= 0x24, /* Interrupt clear */
+
+	/* not on CAN FD cores */
 	XCAN_TXFIFO_OFFSET	= 0x30, /* TX FIFO base */
 	XCAN_RXFIFO_OFFSET	= 0x50, /* RX FIFO base */
+	XCAN_AFR_OFFSET		= 0x60, /* Acceptance Filter */
+
+	/* only on CAN FD cores */
+	XCAN_TRR_OFFSET		= 0x0090, /* TX Buffer Ready Request */
+	XCAN_AFR_EXT_OFFSET	= 0x00E0, /* Acceptance Filter */
+	XCAN_FSR_OFFSET		= 0x00E8, /* RX FIFO Status */
+	XCAN_TXMSG_BASE_OFFSET	= 0x0100, /* TX Message Space */
+	XCAN_RXMSG_BASE_OFFSET	= 0x1100, /* RX Message Space */
 };
 
 #define XCAN_FRAME_ID_OFFSET(frame_base)	((frame_base) + 0x00)
@@ -60,6 +70,15 @@ enum xcan_reg {
 #define XCAN_FRAME_DW1_OFFSET(frame_base)	((frame_base) + 0x08)
 #define XCAN_FRAME_DW2_OFFSET(frame_base)	((frame_base) + 0x0C)
 
+#define XCAN_CANFD_FRAME_SIZE		0x48
+#define XCAN_TXMSG_FRAME_OFFSET(n)	(XCAN_TXMSG_BASE_OFFSET + \
+					 XCAN_CANFD_FRAME_SIZE * (n))
+#define XCAN_RXMSG_FRAME_OFFSET(n)	(XCAN_RXMSG_BASE_OFFSET + \
+					 XCAN_CANFD_FRAME_SIZE * (n))
+
+/* the single TX mailbox used by this driver on CAN FD HW */
+#define XCAN_TX_MAILBOX_IDX		0
+
 /* CAN register bit masks - XCAN_<REG>_<BIT>_MASK */
 #define XCAN_SRR_CEN_MASK		0x00000002 /* CAN enable */
 #define XCAN_SRR_RESET_MASK		0x00000001 /* Soft Reset the CAN core */
@@ -69,6 +88,9 @@ enum xcan_reg {
 #define XCAN_BTR_SJW_MASK		0x00000180 /* Synchronous jump width */
 #define XCAN_BTR_TS2_MASK		0x00000070 /* Time segment 2 */
 #define XCAN_BTR_TS1_MASK		0x0000000F /* Time segment 1 */
+#define XCAN_BTR_SJW_MASK_CANFD		0x000F0000 /* Synchronous jump width */
+#define XCAN_BTR_TS2_MASK_CANFD		0x00000F00 /* Time segment 2 */
+#define XCAN_BTR_TS1_MASK_CANFD		0x0000003F /* Time segment 1 */
 #define XCAN_ECR_REC_MASK		0x0000FF00 /* Receive error counter */
 #define XCAN_ECR_TEC_MASK		0x000000FF /* Transmit error counter */
 #define XCAN_ESR_ACKER_MASK		0x00000010 /* ACK error */
@@ -82,6 +104,7 @@ enum xcan_reg {
 #define XCAN_SR_NORMAL_MASK		0x00000008 /* Normal mode */
 #define XCAN_SR_LBACK_MASK		0x00000002 /* Loop back mode */
 #define XCAN_SR_CONFIG_MASK		0x00000001 /* Configuration mode */
+#define XCAN_IXR_RXMNF_MASK		0x00020000 /* RX match not finished */
 #define XCAN_IXR_TXFEMP_MASK		0x00004000 /* TX FIFO Empty */
 #define XCAN_IXR_WKUP_MASK		0x00000800 /* Wake up interrupt */
 #define XCAN_IXR_SLP_MASK		0x00000400 /* Sleep interrupt */
@@ -99,10 +122,15 @@ enum xcan_reg {
 #define XCAN_IDR_ID2_MASK		0x0007FFFE /* Extended message ident */
 #define XCAN_IDR_RTR_MASK		0x00000001 /* Remote TX request */
 #define XCAN_DLCR_DLC_MASK		0xF0000000 /* Data length code */
+#define XCAN_FSR_FL_MASK		0x00003F00 /* RX Fill Level */
+#define XCAN_FSR_IRI_MASK		0x00000080 /* RX Increment Read Index */
+#define XCAN_FSR_RI_MASK		0x0000001F /* RX Read Index */
 
 /* CAN register bit shift - XCAN_<REG>_<BIT>_SHIFT */
 #define XCAN_BTR_SJW_SHIFT		7  /* Synchronous jump width */
 #define XCAN_BTR_TS2_SHIFT		4  /* Time segment 2 */
+#define XCAN_BTR_SJW_SHIFT_CANFD	16 /* Synchronous jump width */
+#define XCAN_BTR_TS2_SHIFT_CANFD	8  /* Time segment 2 */
 #define XCAN_IDR_ID1_SHIFT		21 /* Standard Messg Identifier */
 #define XCAN_IDR_ID2_SHIFT		1  /* Extended Message Identifier */
 #define XCAN_DLCR_DLC_SHIFT		28 /* Data length code */
@@ -114,11 +142,23 @@ enum xcan_reg {
 
 /* TX-FIFO-empty interrupt available */
 #define XCAN_FLAG_TXFEMP	0x0001
+/* RX Match Not Finished interrupt available */
+#define XCAN_FLAG_RXMNF		0x0002
+/* Extended acceptance filters with control at 0xE0 */
+#define XCAN_FLAG_EXT_FILTERS	0x0004
+/* TX mailboxes instead of TX FIFO */
+#define XCAN_FLAG_TX_MAILBOXES	0x0008
+/* RX FIFO with each buffer in separate registers at 0x1100
+ * instead of the regular FIFO at 0x50
+ */
+#define XCAN_FLAG_RX_FIFO_MULTI	0x0010
 
 struct xcan_devtype_data {
 	unsigned int flags;
 	const struct can_bittiming_const *bittiming_const;
 	const char *bus_clk_name;
+	unsigned int btr_ts2_shift;
+	unsigned int btr_sjw_shift;
 };
 
 /**
@@ -169,6 +209,18 @@ static const struct can_bittiming_const xcan_bittiming_const = {
 	.brp_inc = 1,
 };
 
+static const struct can_bittiming_const xcan_bittiming_const_canfd = {
+	.name = DRIVER_NAME,
+	.tseg1_min = 1,
+	.tseg1_max = 64,
+	.tseg2_min = 1,
+	.tseg2_max = 16,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
 /**
  * xcan_write_reg_le - Write a value to the device register little endian
  * @priv:	Driver private data structure
@@ -223,6 +275,23 @@ static u32 xcan_read_reg_be(const struct xcan_priv *priv, enum xcan_reg reg)
 	return ioread32be(priv->reg_base + reg);
 }
 
+/**
+ * xcan_rx_int_mask - Get the mask for the receive interrupt
+ * @priv:	Driver private data structure
+ *
+ * Return: The receive interrupt mask used by the driver on this HW
+ */
+static u32 xcan_rx_int_mask(const struct xcan_priv *priv)
+{
+	/* RXNEMP is better suited for our use case as it cannot be cleared
+	 * while the FIFO is non-empty, but CAN FD HW does not have it
+	 */
+	if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI)
+		return XCAN_IXR_RXOK_MASK;
+	else
+		return XCAN_IXR_RXNEMP_MASK;
+}
+
 /**
  * set_reset_mode - Resets the CAN device mode
  * @ndev:	Pointer to net_device structure
@@ -287,10 +356,10 @@ static int xcan_set_bittiming(struct net_device *ndev)
 	btr1 = (bt->prop_seg + bt->phase_seg1 - 1);
 
 	/* Setting Time Segment 2 in BTR Register */
-	btr1 |= (bt->phase_seg2 - 1) << XCAN_BTR_TS2_SHIFT;
+	btr1 |= (bt->phase_seg2 - 1) << priv->devtype.btr_ts2_shift;
 
 	/* Setting Synchronous jump width in BTR Register */
-	btr1 |= (bt->sjw - 1) << XCAN_BTR_SJW_SHIFT;
+	btr1 |= (bt->sjw - 1) << priv->devtype.btr_sjw_shift;
 
 	priv->write_reg(priv, XCAN_BRPR_OFFSET, btr0);
 	priv->write_reg(priv, XCAN_BTR_OFFSET, btr1);
@@ -318,6 +387,7 @@ static int xcan_chip_start(struct net_device *ndev)
 	u32 reg_msr, reg_sr_mask;
 	int err;
 	unsigned long timeout;
+	u32 ier;
 
 	/* Check if it is in reset mode */
 	err = set_reset_mode(ndev);
@@ -329,11 +399,15 @@ static int xcan_chip_start(struct net_device *ndev)
 		return err;
 
 	/* Enable interrupts */
-	priv->write_reg(priv, XCAN_IER_OFFSET,
-			XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |
-			XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK |
-			XCAN_IXR_RXNEMP_MASK | XCAN_IXR_ERROR_MASK |
-			XCAN_IXR_RXOFLW_MASK | XCAN_IXR_ARBLST_MASK);
+	ier = XCAN_IXR_TXOK_MASK | XCAN_IXR_BSOFF_MASK |
+		XCAN_IXR_WKUP_MASK | XCAN_IXR_SLP_MASK |
+		XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
+		XCAN_IXR_ARBLST_MASK | xcan_rx_int_mask(priv);
+
+	if (priv->devtype.flags & XCAN_FLAG_RXMNF)
+		ier |= XCAN_IXR_RXMNF_MASK;
+
+	priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 
 	/* Check whether it is loopback mode or normal mode  */
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LOOPBACK) {
@@ -344,6 +418,12 @@ static int xcan_chip_start(struct net_device *ndev)
 		reg_sr_mask = XCAN_SR_NORMAL_MASK;
 	}
 
+	/* enable the first extended filter, if any, as cores with extended
+	 * filtering default to non-receipt if all filters are disabled
+	 */
+	if (priv->devtype.flags & XCAN_FLAG_EXT_FILTERS)
+		priv->write_reg(priv, XCAN_AFR_EXT_OFFSET, 0x00000001);
+
 	priv->write_reg(priv, XCAN_MSR_OFFSET, reg_msr);
 	priv->write_reg(priv, XCAN_SRR_OFFSET, XCAN_SRR_CEN_MASK);
 
@@ -439,13 +519,15 @@ static void xcan_write_frame(struct xcan_priv *priv, struct sk_buff *skb,
 		data[1] = be32_to_cpup((__be32 *)(cf->data + 4));
 
 	priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id);
-	/* If the CAN frame is RTR frame this write triggers transmission */
+	/* If the CAN frame is RTR frame this write triggers transmission
+	 * (not on CAN FD)
+	 */
 	priv->write_reg(priv, XCAN_FRAME_DLC_OFFSET(frame_offset), dlc);
 	if (!(cf->can_id & CAN_RTR_FLAG)) {
 		priv->write_reg(priv, XCAN_FRAME_DW1_OFFSET(frame_offset),
 				data[0]);
 		/* If the CAN frame is Standard/Extended frame this
-		 * write triggers transmission
+		 * write triggers transmission (not on CAN FD)
 		 */
 		priv->write_reg(priv, XCAN_FRAME_DW2_OFFSET(frame_offset),
 				data[1]);
@@ -488,25 +570,60 @@ static int xcan_start_xmit_fifo(struct sk_buff *skb, struct net_device *ndev)
 	return 0;
 }
 
+/**
+ * xcan_start_xmit_mailbox - Starts the transmission (mailbox mode)
+ *
+ * Return: 0 on success, -ENOSPC if there is no space
+ */
+static int xcan_start_xmit_mailbox(struct sk_buff *skb, struct net_device *ndev)
+{
+	struct xcan_priv *priv = netdev_priv(ndev);
+	unsigned long flags;
+
+	if (unlikely(priv->read_reg(priv, XCAN_TRR_OFFSET) &
+		     BIT(XCAN_TX_MAILBOX_IDX)))
+		return -ENOSPC;
+
+	can_put_echo_skb(skb, ndev, 0);
+
+	spin_lock_irqsave(&priv->tx_lock, flags);
+
+	priv->tx_head++;
+
+	xcan_write_frame(priv, skb,
+			 XCAN_TXMSG_FRAME_OFFSET(XCAN_TX_MAILBOX_IDX));
+
+	/* Mark buffer as ready for transmit */
+	priv->write_reg(priv, XCAN_TRR_OFFSET, BIT(XCAN_TX_MAILBOX_IDX));
+
+	netif_stop_queue(ndev);
+
+	spin_unlock_irqrestore(&priv->tx_lock, flags);
+
+	return 0;
+}
+
 /**
  * xcan_start_xmit - Starts the transmission
  * @skb:	sk_buff pointer that contains data to be Txed
  * @ndev:	Pointer to net_device structure
  *
- * This function is invoked from upper layers to initiate transmission. This
- * function uses the next available free txbuff and populates their fields to
- * start the transmission.
+ * This function is invoked from upper layers to initiate transmission.
  *
  * Return: NETDEV_TX_OK on success and NETDEV_TX_BUSY when the tx queue is full
  */
 static int xcan_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 {
+	struct xcan_priv *priv = netdev_priv(ndev);
 	int ret;
 
 	if (can_dropped_invalid_skb(ndev, skb))
 		return NETDEV_TX_OK;
 
-	ret = xcan_start_xmit_fifo(skb, ndev);
+	if (priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES)
+		ret = xcan_start_xmit_mailbox(skb, ndev);
+	else
+		ret = xcan_start_xmit_fifo(skb, ndev);
 
 	if (ret < 0) {
 		netdev_err(ndev, "BUG!, TX full when queue awake!\n");
@@ -739,6 +856,17 @@ static void xcan_err_interrupt(struct net_device *ndev, u32 isr)
 		}
 	}
 
+	/* Check for RX Match Not Finished interrupt */
+	if (isr & XCAN_IXR_RXMNF_MASK) {
+		stats->rx_dropped++;
+		stats->rx_errors++;
+		netdev_err(ndev, "RX match not finished, frame discarded\n");
+		if (skb) {
+			cf->can_id |= CAN_ERR_CRTL;
+			cf->data[1] |= CAN_ERR_CRTL_UNSPEC;
+		}
+	}
+
 	/* Check for error interrupt */
 	if (isr & XCAN_IXR_ERROR_MASK) {
 		if (skb)
@@ -822,6 +950,44 @@ static void xcan_state_interrupt(struct net_device *ndev, u32 isr)
 		priv->can.state = CAN_STATE_ERROR_ACTIVE;
 }
 
+/**
+ * xcan_rx_fifo_get_next_frame - Get register offset of next RX frame
+ *
+ * Return: Register offset of the next frame in RX FIFO.
+ */
+static int xcan_rx_fifo_get_next_frame(struct xcan_priv *priv)
+{
+	int offset;
+
+	if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI) {
+		u32 fsr;
+
+		/* clear RXOK before the is-empty check so that any newly
+		 * received frame will reassert it without a race
+		 */
+		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXOK_MASK);
+
+		fsr = priv->read_reg(priv, XCAN_FSR_OFFSET);
+
+		/* check if RX FIFO is empty */
+		if (!(fsr & XCAN_FSR_FL_MASK))
+			return -ENOENT;
+
+		offset = XCAN_RXMSG_FRAME_OFFSET(fsr & XCAN_FSR_RI_MASK);
+
+	} else {
+		/* check if RX FIFO is empty */
+		if (!(priv->read_reg(priv, XCAN_ISR_OFFSET) &
+		      XCAN_IXR_RXNEMP_MASK))
+			return -ENOENT;
+
+		/* frames are read from a static offset */
+		offset = XCAN_RXFIFO_OFFSET;
+	}
+
+	return offset;
+}
+
 /**
  * xcan_rx_poll - Poll routine for rx packets (NAPI)
  * @napi:	napi structure pointer
@@ -836,14 +1002,24 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 {
 	struct net_device *ndev = napi->dev;
 	struct xcan_priv *priv = netdev_priv(ndev);
-	u32 isr, ier;
+	u32 ier;
 	int work_done = 0;
-
-	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
-	while ((isr & XCAN_IXR_RXNEMP_MASK) && (work_done < quota)) {
-		work_done += xcan_rx(ndev, XCAN_RXFIFO_OFFSET);
-		priv->write_reg(priv, XCAN_ICR_OFFSET, XCAN_IXR_RXNEMP_MASK);
-		isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
+	int frame_offset;
+
+	while ((frame_offset = xcan_rx_fifo_get_next_frame(priv)) >= 0 &&
+	       (work_done < quota)) {
+		work_done += xcan_rx(ndev, frame_offset);
+
+		if (priv->devtype.flags & XCAN_FLAG_RX_FIFO_MULTI)
+			/* increment read index */
+			priv->write_reg(priv, XCAN_FSR_OFFSET,
+					XCAN_FSR_IRI_MASK);
+		else
+			/* clear rx-not-empty (will actually clear only if
+			 * empty)
+			 */
+			priv->write_reg(priv, XCAN_ICR_OFFSET,
+					XCAN_IXR_RXNEMP_MASK);
 	}
 
 	if (work_done) {
@@ -854,7 +1030,7 @@ static int xcan_rx_poll(struct napi_struct *napi, int quota)
 	if (work_done < quota) {
 		napi_complete_done(napi, work_done);
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier |= XCAN_IXR_RXNEMP_MASK;
+		ier |= xcan_rx_int_mask(priv);
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 	}
 	return work_done;
@@ -953,6 +1129,7 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 	struct xcan_priv *priv = netdev_priv(ndev);
 	u32 isr, ier;
 	u32 isr_errors;
+	u32 rx_int_mask = xcan_rx_int_mask(priv);
 
 	/* Get the interrupt status from Xilinx CAN */
 	isr = priv->read_reg(priv, XCAN_ISR_OFFSET);
@@ -972,16 +1149,17 @@ static irqreturn_t xcan_interrupt(int irq, void *dev_id)
 
 	/* Check for the type of error interrupt and Processing it */
 	isr_errors = isr & (XCAN_IXR_ERROR_MASK | XCAN_IXR_RXOFLW_MASK |
-			    XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK);
+			    XCAN_IXR_BSOFF_MASK | XCAN_IXR_ARBLST_MASK |
+			    XCAN_IXR_RXMNF_MASK);
 	if (isr_errors) {
 		priv->write_reg(priv, XCAN_ICR_OFFSET, isr_errors);
 		xcan_err_interrupt(ndev, isr);
 	}
 
 	/* Check for the type of receive interrupt and Processing it */
-	if (isr & XCAN_IXR_RXNEMP_MASK) {
+	if (isr & rx_int_mask) {
 		ier = priv->read_reg(priv, XCAN_IER_OFFSET);
-		ier &= ~XCAN_IXR_RXNEMP_MASK;
+		ier &= ~rx_int_mask;
 		priv->write_reg(priv, XCAN_IER_OFFSET, ier);
 		napi_schedule(&priv->napi);
 	}
@@ -1228,14 +1406,27 @@ static const struct dev_pm_ops xcan_dev_pm_ops = {
 };
 
 static const struct xcan_devtype_data xcan_zynq_data = {
-	.flags = XCAN_FLAG_TXFEMP,
 	.bittiming_const = &xcan_bittiming_const,
+	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT,
+	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT,
 	.bus_clk_name = "pclk",
 };
 
 static const struct xcan_devtype_data xcan_axi_data = {
-	.flags = 0,
 	.bittiming_const = &xcan_bittiming_const,
+	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT,
+	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT,
+	.bus_clk_name = "s_axi_aclk",
+};
+
+static const struct xcan_devtype_data xcan_canfd_data = {
+	.flags = XCAN_FLAG_EXT_FILTERS |
+		 XCAN_FLAG_RXMNF |
+		 XCAN_FLAG_TX_MAILBOXES |
+		 XCAN_FLAG_RX_FIFO_MULTI,
+	.bittiming_const = &xcan_bittiming_const,
+	.btr_ts2_shift = XCAN_BTR_TS2_SHIFT_CANFD,
+	.btr_sjw_shift = XCAN_BTR_SJW_SHIFT_CANFD,
 	.bus_clk_name = "s_axi_aclk",
 };
 
@@ -1243,6 +1434,7 @@ static const struct xcan_devtype_data xcan_axi_data = {
 static const struct of_device_id xcan_of_match[] = {
 	{ .compatible = "xlnx,zynq-can-1.0", .data = &xcan_zynq_data },
 	{ .compatible = "xlnx,axi-can-1.00.a", .data = &xcan_axi_data },
+	{ .compatible = "xlnx,canfd-1.0", .data = &xcan_canfd_data },
 	{ /* end of list */ },
 };
 MODULE_DEVICE_TABLE(of, xcan_of_match);
@@ -1264,7 +1456,10 @@ static int xcan_probe(struct platform_device *pdev)
 	const struct of_device_id *of_id;
 	const struct xcan_devtype_data *devtype = &xcan_axi_data;
 	void __iomem *addr;
-	int ret, rx_max, tx_max, tx_fifo_depth;
+	int ret;
+	int rx_max, tx_max;
+	int hw_tx_max, hw_rx_max;
+	const char *hw_tx_max_property;
 
 	/* Get the virtual base address for the device */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -1274,21 +1469,33 @@ static int xcan_probe(struct platform_device *pdev)
 		goto err;
 	}
 
-	ret = of_property_read_u32(pdev->dev.of_node, "tx-fifo-depth",
-				   &tx_fifo_depth);
-	if (ret < 0)
-		goto err;
-
-	ret = of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth", &rx_max);
-	if (ret < 0)
-		goto err;
-
 	of_id = of_match_device(xcan_of_match, &pdev->dev);
 	if (of_id && of_id->data)
 		devtype = of_id->data;
 
-	/* There is no way to directly figure out how many frames have been
-	 * sent when the TXOK interrupt is processed. If watermark programming
+	hw_tx_max_property = devtype->flags & XCAN_FLAG_TX_MAILBOXES ?
+			     "tx-mailbox-count" : "tx-fifo-depth";
+
+	ret = of_property_read_u32(pdev->dev.of_node, hw_tx_max_property,
+				   &hw_tx_max);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "missing %s property\n",
+			hw_tx_max_property);
+		goto err;
+	}
+
+	ret = of_property_read_u32(pdev->dev.of_node, "rx-fifo-depth",
+				   &hw_rx_max);
+	if (ret < 0) {
+		dev_err(&pdev->dev,
+			"missing rx-fifo-depth property (mailbox mode is not supported)\n");
+		goto err;
+	}
+
+	/* With TX FIFO:
+	 *
+	 * There is no way to directly figure out how many frames have been
+	 * sent when the TXOK interrupt is processed. If TXFEMP
 	 * is supported, we can have 2 frames in the FIFO and use TXFEMP
 	 * to determine if 1 or 2 frames have been sent.
 	 * Theoretically we should be able to use TXFWMEMP to determine up
@@ -1297,12 +1504,20 @@ static int xcan_probe(struct platform_device *pdev)
 	 * than 2 frames in FIFO) is set anyway with no TXOK (a frame was
 	 * sent), which is not a sensible state - possibly TXFWMEMP is not
 	 * completely synchronized with the rest of the bits?
+	 *
+	 * With TX mailboxes:
+	 *
+	 * HW sends frames in CAN ID priority order. To preserve FIFO ordering
+	 * we submit frames one at a time.
 	 */
-	if (devtype->flags & XCAN_FLAG_TXFEMP)
-		tx_max = min(tx_fifo_depth, 2);
+	if (!(devtype->flags & XCAN_FLAG_TX_MAILBOXES) &&
+	    (devtype->flags & XCAN_FLAG_TXFEMP))
+		tx_max = min(hw_tx_max, 2);
 	else
 		tx_max = 1;
 
+	rx_max = hw_rx_max;
+
 	/* Create a CAN device instance */
 	ndev = alloc_candev(sizeof(struct xcan_priv), tx_max);
 	if (!ndev)
@@ -1373,9 +1588,9 @@ static int xcan_probe(struct platform_device *pdev)
 
 	pm_runtime_put(&pdev->dev);
 
-	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx fifo depth: actual %d, using %d\n",
-			priv->reg_base, ndev->irq, priv->can.clock.freq,
-			tx_fifo_depth, priv->tx_max);
+	netdev_dbg(ndev, "reg_base=0x%p irq=%d clock=%d, tx buffers: actual %d, using %d\n",
+		   priv->reg_base, ndev->irq, priv->can.clock.freq,
+		   hw_tx_max, priv->tx_max);
 
 	return 0;
 
-- 
cgit v1.2.3


From f805ed84895abc56e20328ccfe340d4ff74a3983 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 28 Jun 2018 12:41:42 -0500
Subject: can: peak_usb: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/peak_usb/pcan_usb.c      | 1 +
 drivers/net/can/usb/peak_usb/pcan_usb_core.c | 1 +
 drivers/net/can/usb/peak_usb/pcan_usb_pro.c  | 2 ++
 3 files changed, 4 insertions(+)

diff --git a/drivers/net/can/usb/peak_usb/pcan_usb.c b/drivers/net/can/usb/peak_usb/pcan_usb.c
index f530a80f5051..13238a72a338 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb.c
@@ -423,6 +423,7 @@ static int pcan_usb_decode_error(struct pcan_usb_msg_context *mc, u8 n,
 			new_state = CAN_STATE_ERROR_WARNING;
 			break;
 		}
+		/* else: fall through */
 
 	case CAN_STATE_ERROR_WARNING:
 		if (n & PCAN_USB_ERROR_BUS_HEAVY) {
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_core.c b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
index 50e911428638..611f9d31be5d 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_core.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_core.c
@@ -353,6 +353,7 @@ static netdev_tx_t peak_usb_ndo_start_xmit(struct sk_buff *skb,
 		default:
 			netdev_warn(netdev, "tx urb submitting failed err=%d\n",
 				    err);
+			/* fall through */
 		case -ENOENT:
 			/* cable unplugged */
 			stats->tx_dropped++;
diff --git a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
index 0105fbfea273..d516def846ab 100644
--- a/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
+++ b/drivers/net/can/usb/peak_usb/pcan_usb_pro.c
@@ -141,8 +141,10 @@ static int pcan_msg_add_rec(struct pcan_usb_pro_msg *pm, u8 id, ...)
 	switch (id) {
 	case PCAN_USBPRO_TXMSG8:
 		i += 4;
+		/* fall through */
 	case PCAN_USBPRO_TXMSG4:
 		i += 4;
+		/* fall through */
 	case PCAN_USBPRO_TXMSG0:
 		*pc++ = va_arg(ap, int);
 		*pc++ = va_arg(ap, int);
-- 
cgit v1.2.3


From 0cccf0abf2daeff3c97c3912049ed175d17df559 Mon Sep 17 00:00:00 2001
From: Stephane Grosjean <s.grosjean@peak-system.com>
Date: Thu, 21 Jun 2018 15:23:26 +0200
Subject: can: peak_canfd: improves 32-bit alignment

The embedded firmware aligns its messages on 32-bit boundaries.
This patch makes sure to browse through the list of received messages
while respecting 32-bit alignment.

Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/peak_canfd/peak_canfd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/peak_canfd/peak_canfd.c b/drivers/net/can/peak_canfd/peak_canfd.c
index ed8561d4a90f..5696d7e80751 100644
--- a/drivers/net/can/peak_canfd/peak_canfd.c
+++ b/drivers/net/can/peak_canfd/peak_canfd.c
@@ -486,7 +486,7 @@ int peak_canfd_handle_msgs_list(struct peak_canfd_priv *priv,
 		if (msg_size <= 0)
 			break;
 
-		msg_ptr += msg_size;
+		msg_ptr += ALIGN(msg_size, 4);
 	}
 
 	if (msg_size < 0)
-- 
cgit v1.2.3


From f6c740f592ac878cb7c19e650c88c29f6b25e761 Mon Sep 17 00:00:00 2001
From: Stephane Grosjean <s.grosjean@peak-system.com>
Date: Thu, 21 Jun 2018 15:23:27 +0200
Subject: can: peak_canfd: remove useless defined symbols

CANFD_IRQ_SET as well as CANFD_TX_PATH_SET are not used.

Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/peak_canfd/peak_pciefd_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index 455a3797a200..d9d569a16c36 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -174,9 +174,6 @@ struct pciefd_page {
 	u32 size;
 };
 
-#define CANFD_IRQ_SET		0x00000001
-#define CANFD_TX_PATH_SET	0x00000002
-
 /* CAN-FD channel object */
 struct pciefd_board;
 struct pciefd_can {
-- 
cgit v1.2.3


From cc5f9bb02ea5891980b532fec7519c90e909c3e0 Mon Sep 17 00:00:00 2001
From: Stephane Grosjean <s.grosjean@peak-system.com>
Date: Thu, 21 Jun 2018 15:23:28 +0200
Subject: can: peak_canfd: use ndev irq instead of pci_dev one

This cosmetic change should facilitate in the future the use of MSI
rather than legacy INTx interrupts.

Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/peak_canfd/peak_pciefd_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index d9d569a16c36..3c7c0d82568f 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -415,7 +415,7 @@ static int pciefd_pre_cmd(struct peak_canfd_priv *ucan)
 			break;
 
 		/* going into operational mode: setup IRQ handler */
-		err = request_irq(priv->board->pci_dev->irq,
+		err = request_irq(priv->ucan.ndev->irq,
 				  pciefd_irq_handler,
 				  IRQF_SHARED,
 				  PCIEFD_DRV_NAME,
@@ -496,7 +496,7 @@ static int pciefd_post_cmd(struct peak_canfd_priv *ucan)
 		pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT,
 				    PCIEFD_REG_CAN_RX_CTL_CLR);
 
-		free_irq(priv->board->pci_dev->irq, priv);
+		free_irq(priv->ucan.ndev->irq, priv);
 
 		ucan->can.state = CAN_STATE_STOPPED;
 
@@ -688,7 +688,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd)
 	pciefd->can[pciefd->can_count] = priv;
 
 	dev_info(&pciefd->pci_dev->dev, "%s at reg_base=0x%p irq=%d\n",
-		 ndev->name, priv->reg_base, pciefd->pci_dev->irq);
+		 ndev->name, priv->reg_base, ndev->irq);
 
 	return 0;
 
-- 
cgit v1.2.3


From d31f8513f252e25be3d4e64fe99d1efd5da3c83a Mon Sep 17 00:00:00 2001
From: Stephane Grosjean <s.grosjean@peak-system.com>
Date: Thu, 21 Jun 2018 15:23:29 +0200
Subject: can: peak_canfd: fix typo in error message

This patch fixes a typo in the error message in pciefd_can_probe().

Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/peak_canfd/peak_pciefd_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index 3c7c0d82568f..b09961b1eeef 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -635,7 +635,7 @@ static int pciefd_can_probe(struct pciefd_board *pciefd)
 						 GFP_KERNEL);
 	if (!priv->tx_dma_vaddr) {
 		dev_err(&pciefd->pci_dev->dev,
-			"Tx dmaim_alloc_coherent(%u) failure\n",
+			"Tx dmam_alloc_coherent(%u) failure\n",
 			PCIEFD_TX_DMA_SIZE);
 		goto err_free_candev;
 	}
-- 
cgit v1.2.3


From 5592cd0390741e6fecfc7908baaeadb4682f3c48 Mon Sep 17 00:00:00 2001
From: Stephane Grosjean <s.grosjean@peak-system.com>
Date: Thu, 21 Jun 2018 15:23:30 +0200
Subject: can: peak_canfd: rearrange the way resources are released

This patch improves the sequence the resources are released by, first,

- disabling the IRQ in the controller, then by
- resetting the DMA logic, and finally, by
- adding a read cycle to ensure that the above commands have been received

before freeing the system interrupt.

Signed-off-by: Stephane Grosjean <s.grosjean@peak-system.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/peak_canfd/peak_pciefd_main.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/can/peak_canfd/peak_pciefd_main.c b/drivers/net/can/peak_canfd/peak_pciefd_main.c
index b09961b1eeef..c458d5fdc8d3 100644
--- a/drivers/net/can/peak_canfd/peak_pciefd_main.c
+++ b/drivers/net/can/peak_canfd/peak_pciefd_main.c
@@ -488,13 +488,16 @@ static int pciefd_post_cmd(struct peak_canfd_priv *ucan)
 
 		/* controller now in reset mode: */
 
+		/* disable IRQ for this CAN */
+		pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT,
+				    PCIEFD_REG_CAN_RX_CTL_CLR);
+
 		/* stop and reset DMA addresses in Tx/Rx engines */
 		pciefd_can_clear_tx_dma(priv);
 		pciefd_can_clear_rx_dma(priv);
 
-		/* disable IRQ for this CAN */
-		pciefd_can_writereg(priv, CANFD_CTL_IEN_BIT,
-				    PCIEFD_REG_CAN_RX_CTL_CLR);
+		/* wait for above commands to complete (read cycle) */
+		(void)pciefd_sys_readreg(priv->board, PCIEFD_REG_SYS_VER1);
 
 		free_irq(priv->ucan.ndev->irq, priv);
 
-- 
cgit v1.2.3


From deaa1c984be7c2aa6ae96c6b23a103a25692c543 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:18 +0200
Subject: can: kvaser_usb: Remove unnecessary return

Remove unnecessary return at end of void function.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index daed57d3d209..604f09b18308 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -1383,8 +1383,6 @@ resubmit_urb:
 		dev_err(dev->udev->dev.parent,
 			"Failed resubmitting read bulk urb: %d\n", err);
 	}
-
-	return;
 }
 
 static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
-- 
cgit v1.2.3


From 23757222012170a8b18caba7cf4dfeeee1e2917b Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:19 +0200
Subject: can: kvaser_usb: Remove unused commands and defines

Remove unused commands:
  struct kvaser_msg_cardinfo2
  struct leaf_msg_tx_acknowledge
  struct usbcan_msg_tx_acknowledge

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 38 --------------------------------------
 1 file changed, 38 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 604f09b18308..53ea4d6bf9a8 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -110,36 +110,25 @@ static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
 #define CMD_RX_EXT_MESSAGE		14
 #define CMD_TX_EXT_MESSAGE		15
 #define CMD_SET_BUS_PARAMS		16
-#define CMD_GET_BUS_PARAMS		17
-#define CMD_GET_BUS_PARAMS_REPLY	18
-#define CMD_GET_CHIP_STATE		19
 #define CMD_CHIP_STATE_EVENT		20
 #define CMD_SET_CTRL_MODE		21
-#define CMD_GET_CTRL_MODE		22
-#define CMD_GET_CTRL_MODE_REPLY		23
 #define CMD_RESET_CHIP			24
-#define CMD_RESET_CARD			25
 #define CMD_START_CHIP			26
 #define CMD_START_CHIP_REPLY		27
 #define CMD_STOP_CHIP			28
 #define CMD_STOP_CHIP_REPLY		29
 
-#define CMD_LEAF_GET_CARD_INFO2		32
-#define CMD_USBCAN_RESET_CLOCK		32
 #define CMD_USBCAN_CLOCK_OVERFLOW_EVENT	33
 
 #define CMD_GET_CARD_INFO		34
 #define CMD_GET_CARD_INFO_REPLY		35
 #define CMD_GET_SOFTWARE_INFO		38
 #define CMD_GET_SOFTWARE_INFO_REPLY	39
-#define CMD_ERROR_EVENT			45
 #define CMD_FLUSH_QUEUE			48
-#define CMD_RESET_ERROR_COUNTER		49
 #define CMD_TX_ACKNOWLEDGE		50
 #define CMD_CAN_ERROR_EVENT		51
 #define CMD_FLUSH_QUEUE_REPLY		68
 
-#define CMD_LEAF_USB_THROTTLE		77
 #define CMD_LEAF_LOG_MESSAGE		106
 
 /* error factors */
@@ -221,13 +210,6 @@ struct kvaser_msg_cardinfo {
 	__le16 padding;
 } __packed;
 
-struct kvaser_msg_cardinfo2 {
-	u8 tid;
-	u8 reserved;
-	u8 pcb_id[24];
-	__le32 oem_unlock_code;
-} __packed;
-
 struct leaf_msg_softinfo {
 	u8 tid;
 	u8 padding0;
@@ -323,23 +305,6 @@ struct kvaser_msg_tx_acknowledge_header {
 	u8 tid;
 } __packed;
 
-struct leaf_msg_tx_acknowledge {
-	u8 channel;
-	u8 tid;
-
-	__le16 time[3];
-	u8 flags;
-	u8 time_offset;
-} __packed;
-
-struct usbcan_msg_tx_acknowledge {
-	u8 channel;
-	u8 tid;
-
-	__le16 time;
-	__le16 padding;
-} __packed;
-
 struct leaf_msg_error_event {
 	u8 tid;
 	u8 flags;
@@ -394,7 +359,6 @@ struct kvaser_msg {
 	union	{
 		struct kvaser_msg_simple simple;
 		struct kvaser_msg_cardinfo cardinfo;
-		struct kvaser_msg_cardinfo2 cardinfo2;
 		struct kvaser_msg_busparams busparams;
 
 		struct kvaser_msg_rx_can_header rx_can_header;
@@ -404,7 +368,6 @@ struct kvaser_msg {
 			struct leaf_msg_softinfo softinfo;
 			struct leaf_msg_rx_can rx_can;
 			struct leaf_msg_chip_state_event chip_state_event;
-			struct leaf_msg_tx_acknowledge tx_acknowledge;
 			struct leaf_msg_error_event error_event;
 			struct leaf_msg_log_message log_message;
 		} __packed leaf;
@@ -413,7 +376,6 @@ struct kvaser_msg {
 			struct usbcan_msg_softinfo softinfo;
 			struct usbcan_msg_rx_can rx_can;
 			struct usbcan_msg_chip_state_event chip_state_event;
-			struct usbcan_msg_tx_acknowledge tx_acknowledge;
 			struct usbcan_msg_error_event error_event;
 		} __packed usbcan;
 
-- 
cgit v1.2.3


From f741f938556da50fda3b74905d65ddd71ee9abc5 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:20 +0200
Subject: can: kvaser_usb: Rename message/msg to command/cmd

Rename message to command and msg to cmd, where appropriate. To make the
code more readable and to better match Kvaser's Linux drivers.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 475 +++++++++++++++++++--------------------
 1 file changed, 237 insertions(+), 238 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 53ea4d6bf9a8..5168b63fcd51 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -85,8 +85,8 @@ static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
 #define KVASER_HAS_SILENT_MODE		BIT(0)
 #define KVASER_HAS_TXRX_ERRORS		BIT(1)
 
-/* Message header size */
-#define MSG_HEADER_LEN			2
+/* Command header size */
+#define CMD_HEADER_LEN			2
 
 /* Can message flags */
 #define MSG_FLAG_ERROR_FRAME		BIT(0)
@@ -104,7 +104,7 @@ static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
 #define M16C_STATE_BUS_PASSIVE		BIT(5)
 #define M16C_STATE_BUS_OFF		BIT(6)
 
-/* Can msg ids */
+/* Leaf/usbcan command ids */
 #define CMD_RX_STD_MESSAGE		12
 #define CMD_TX_STD_MESSAGE		13
 #define CMD_RX_EXT_MESSAGE		14
@@ -177,12 +177,12 @@ enum kvaser_usb_family {
 	KVASER_USBCAN,
 };
 
-struct kvaser_msg_simple {
+struct kvaser_cmd_simple {
 	u8 tid;
 	u8 channel;
 } __packed;
 
-struct kvaser_msg_cardinfo {
+struct kvaser_cmd_cardinfo {
 	u8 tid;
 	u8 nchannels;
 	union {
@@ -210,7 +210,7 @@ struct kvaser_msg_cardinfo {
 	__le16 padding;
 } __packed;
 
-struct leaf_msg_softinfo {
+struct leaf_cmd_softinfo {
 	u8 tid;
 	u8 padding0;
 	__le32 sw_options;
@@ -219,7 +219,7 @@ struct leaf_msg_softinfo {
 	__le16 padding1[9];
 } __packed;
 
-struct usbcan_msg_softinfo {
+struct usbcan_cmd_softinfo {
 	u8 tid;
 	u8 fw_name[5];
 	__le16 max_outstanding_tx;
@@ -229,7 +229,7 @@ struct usbcan_msg_softinfo {
 	__le16 sw_options;
 } __packed;
 
-struct kvaser_msg_busparams {
+struct kvaser_cmd_busparams {
 	u8 tid;
 	u8 channel;
 	__le32 bitrate;
@@ -239,10 +239,10 @@ struct kvaser_msg_busparams {
 	u8 no_samp;
 } __packed;
 
-struct kvaser_msg_tx_can {
+struct kvaser_cmd_tx_can {
 	u8 channel;
 	u8 tid;
-	u8 msg[14];
+	u8 data[14];
 	union {
 		struct {
 			u8 padding;
@@ -255,28 +255,28 @@ struct kvaser_msg_tx_can {
 	} __packed;
 } __packed;
 
-struct kvaser_msg_rx_can_header {
+struct kvaser_cmd_rx_can_header {
 	u8 channel;
 	u8 flag;
 } __packed;
 
-struct leaf_msg_rx_can {
+struct leaf_cmd_rx_can {
 	u8 channel;
 	u8 flag;
 
 	__le16 time[3];
-	u8 msg[14];
+	u8 data[14];
 } __packed;
 
-struct usbcan_msg_rx_can {
+struct usbcan_cmd_rx_can {
 	u8 channel;
 	u8 flag;
 
-	u8 msg[14];
+	u8 data[14];
 	__le16 time;
 } __packed;
 
-struct leaf_msg_chip_state_event {
+struct leaf_cmd_chip_state_event {
 	u8 tid;
 	u8 channel;
 
@@ -288,7 +288,7 @@ struct leaf_msg_chip_state_event {
 	u8 padding[3];
 } __packed;
 
-struct usbcan_msg_chip_state_event {
+struct usbcan_cmd_chip_state_event {
 	u8 tid;
 	u8 channel;
 
@@ -300,12 +300,12 @@ struct usbcan_msg_chip_state_event {
 	u8 padding[3];
 } __packed;
 
-struct kvaser_msg_tx_acknowledge_header {
+struct kvaser_cmd_tx_acknowledge_header {
 	u8 channel;
 	u8 tid;
 } __packed;
 
-struct leaf_msg_error_event {
+struct leaf_cmd_error_event {
 	u8 tid;
 	u8 flags;
 	__le16 time[3];
@@ -317,7 +317,7 @@ struct leaf_msg_error_event {
 	u8 error_factor;
 } __packed;
 
-struct usbcan_msg_error_event {
+struct usbcan_cmd_error_event {
 	u8 tid;
 	u8 padding;
 	u8 tx_errors_count_ch0;
@@ -329,21 +329,21 @@ struct usbcan_msg_error_event {
 	__le16 time;
 } __packed;
 
-struct kvaser_msg_ctrl_mode {
+struct kvaser_cmd_ctrl_mode {
 	u8 tid;
 	u8 channel;
 	u8 ctrl_mode;
 	u8 padding[3];
 } __packed;
 
-struct kvaser_msg_flush_queue {
+struct kvaser_cmd_flush_queue {
 	u8 tid;
 	u8 channel;
 	u8 flags;
 	u8 padding[3];
 } __packed;
 
-struct leaf_msg_log_message {
+struct leaf_cmd_log_message {
 	u8 channel;
 	u8 flags;
 	__le16 time[3];
@@ -353,35 +353,35 @@ struct leaf_msg_log_message {
 	u8 data[8];
 } __packed;
 
-struct kvaser_msg {
+struct kvaser_cmd {
 	u8 len;
 	u8 id;
 	union	{
-		struct kvaser_msg_simple simple;
-		struct kvaser_msg_cardinfo cardinfo;
-		struct kvaser_msg_busparams busparams;
+		struct kvaser_cmd_simple simple;
+		struct kvaser_cmd_cardinfo cardinfo;
+		struct kvaser_cmd_busparams busparams;
 
-		struct kvaser_msg_rx_can_header rx_can_header;
-		struct kvaser_msg_tx_acknowledge_header tx_acknowledge_header;
+		struct kvaser_cmd_rx_can_header rx_can_header;
+		struct kvaser_cmd_tx_acknowledge_header tx_acknowledge_header;
 
 		union {
-			struct leaf_msg_softinfo softinfo;
-			struct leaf_msg_rx_can rx_can;
-			struct leaf_msg_chip_state_event chip_state_event;
-			struct leaf_msg_error_event error_event;
-			struct leaf_msg_log_message log_message;
+			struct leaf_cmd_softinfo softinfo;
+			struct leaf_cmd_rx_can rx_can;
+			struct leaf_cmd_chip_state_event chip_state_event;
+			struct leaf_cmd_error_event error_event;
+			struct leaf_cmd_log_message log_message;
 		} __packed leaf;
 
 		union {
-			struct usbcan_msg_softinfo softinfo;
-			struct usbcan_msg_rx_can rx_can;
-			struct usbcan_msg_chip_state_event chip_state_event;
-			struct usbcan_msg_error_event error_event;
+			struct usbcan_cmd_softinfo softinfo;
+			struct usbcan_cmd_rx_can rx_can;
+			struct usbcan_cmd_chip_state_event chip_state_event;
+			struct usbcan_cmd_error_event error_event;
 		} __packed usbcan;
 
-		struct kvaser_msg_tx_can tx_can;
-		struct kvaser_msg_ctrl_mode ctrl_mode;
-		struct kvaser_msg_flush_queue flush_queue;
+		struct kvaser_cmd_tx_can tx_can;
+		struct kvaser_cmd_ctrl_mode ctrl_mode;
+		struct kvaser_cmd_flush_queue flush_queue;
 	} u;
 } __packed;
 
@@ -521,22 +521,22 @@ static const struct usb_device_id kvaser_usb_table[] = {
 };
 MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
 
-static inline int kvaser_usb_send_msg(const struct kvaser_usb *dev,
-				      struct kvaser_msg *msg)
+static inline int kvaser_usb_send_cmd(const struct kvaser_usb *dev,
+				      struct kvaser_cmd *cmd)
 {
 	int actual_len;
 
 	return usb_bulk_msg(dev->udev,
 			    usb_sndbulkpipe(dev->udev,
 					dev->bulk_out->bEndpointAddress),
-			    msg, msg->len, &actual_len,
+			    cmd, cmd->len, &actual_len,
 			    USB_SEND_TIMEOUT);
 }
 
-static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id,
-			       struct kvaser_msg *msg)
+static int kvaser_usb_wait_cmd(const struct kvaser_usb *dev, u8 id,
+			       struct kvaser_cmd *cmd)
 {
-	struct kvaser_msg *tmp;
+	struct kvaser_cmd *tmp;
 	void *buf;
 	int actual_len;
 	int err;
@@ -557,10 +557,10 @@ static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id,
 			goto end;
 
 		pos = 0;
-		while (pos <= actual_len - MSG_HEADER_LEN) {
+		while (pos <= actual_len - CMD_HEADER_LEN) {
 			tmp = buf + pos;
 
-			/* Handle messages crossing the USB endpoint max packet
+			/* Handle commands crossing the USB endpoint max packet
 			 * size boundary. Check kvaser_usb_read_bulk_callback()
 			 * for further details.
 			 */
@@ -577,7 +577,7 @@ static int kvaser_usb_wait_msg(const struct kvaser_usb *dev, u8 id,
 			}
 
 			if (tmp->id == id) {
-				memcpy(msg, tmp, tmp->len);
+				memcpy(cmd, tmp, tmp->len);
 				goto end;
 			}
 
@@ -593,50 +593,50 @@ end:
 	return err;
 }
 
-static int kvaser_usb_send_simple_msg(const struct kvaser_usb *dev,
-				      u8 msg_id, int channel)
+static int kvaser_usb_send_simple_cmd(const struct kvaser_usb *dev,
+				      u8 cmd_id, int channel)
 {
-	struct kvaser_msg *msg;
+	struct kvaser_cmd *cmd;
 	int rc;
 
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
 		return -ENOMEM;
 
-	msg->id = msg_id;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_simple);
-	msg->u.simple.channel = channel;
-	msg->u.simple.tid = 0xff;
+	cmd->id = cmd_id;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
+	cmd->u.simple.channel = channel;
+	cmd->u.simple.tid = 0xff;
 
-	rc = kvaser_usb_send_msg(dev, msg);
+	rc = kvaser_usb_send_cmd(dev, cmd);
 
-	kfree(msg);
+	kfree(cmd);
 	return rc;
 }
 
 static int kvaser_usb_get_software_info(struct kvaser_usb *dev)
 {
-	struct kvaser_msg msg;
+	struct kvaser_cmd cmd;
 	int err;
 
-	err = kvaser_usb_send_simple_msg(dev, CMD_GET_SOFTWARE_INFO, 0);
+	err = kvaser_usb_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO, 0);
 	if (err)
 		return err;
 
-	err = kvaser_usb_wait_msg(dev, CMD_GET_SOFTWARE_INFO_REPLY, &msg);
+	err = kvaser_usb_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_REPLY, &cmd);
 	if (err)
 		return err;
 
 	switch (dev->family) {
 	case KVASER_LEAF:
-		dev->fw_version = le32_to_cpu(msg.u.leaf.softinfo.fw_version);
+		dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version);
 		dev->max_tx_urbs =
-			le16_to_cpu(msg.u.leaf.softinfo.max_outstanding_tx);
+			le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx);
 		break;
 	case KVASER_USBCAN:
-		dev->fw_version = le32_to_cpu(msg.u.usbcan.softinfo.fw_version);
+		dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
 		dev->max_tx_urbs =
-			le16_to_cpu(msg.u.usbcan.softinfo.max_outstanding_tx);
+			le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
 		break;
 	}
 
@@ -645,18 +645,18 @@ static int kvaser_usb_get_software_info(struct kvaser_usb *dev)
 
 static int kvaser_usb_get_card_info(struct kvaser_usb *dev)
 {
-	struct kvaser_msg msg;
+	struct kvaser_cmd cmd;
 	int err;
 
-	err = kvaser_usb_send_simple_msg(dev, CMD_GET_CARD_INFO, 0);
+	err = kvaser_usb_send_simple_cmd(dev, CMD_GET_CARD_INFO, 0);
 	if (err)
 		return err;
 
-	err = kvaser_usb_wait_msg(dev, CMD_GET_CARD_INFO_REPLY, &msg);
+	err = kvaser_usb_wait_cmd(dev, CMD_GET_CARD_INFO_REPLY, &cmd);
 	if (err)
 		return err;
 
-	dev->nchannels = msg.u.cardinfo.nchannels;
+	dev->nchannels = cmd.u.cardinfo.nchannels;
 	if ((dev->nchannels > MAX_NET_DEVICES) ||
 	    (dev->family == KVASER_USBCAN &&
 	     dev->nchannels > MAX_USBCAN_NET_DEVICES))
@@ -666,7 +666,7 @@ static int kvaser_usb_get_card_info(struct kvaser_usb *dev)
 }
 
 static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev,
-				      const struct kvaser_msg *msg)
+				      const struct kvaser_cmd *cmd)
 {
 	struct net_device_stats *stats;
 	struct kvaser_usb_tx_urb_context *context;
@@ -676,8 +676,8 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev,
 	unsigned long flags;
 	u8 channel, tid;
 
-	channel = msg->u.tx_acknowledge_header.channel;
-	tid = msg->u.tx_acknowledge_header.tid;
+	channel = cmd->u.tx_acknowledge_header.channel;
+	tid = cmd->u.tx_acknowledge_header.tid;
 
 	if (channel >= dev->nchannels) {
 		dev_err(dev->udev->dev.parent,
@@ -728,7 +728,7 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev,
 	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
 }
 
-static void kvaser_usb_simple_msg_callback(struct urb *urb)
+static void kvaser_usb_simple_cmd_callback(struct urb *urb)
 {
 	struct net_device *netdev = urb->context;
 
@@ -739,12 +739,12 @@ static void kvaser_usb_simple_msg_callback(struct urb *urb)
 			    urb->status);
 }
 
-static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv,
-				       u8 msg_id)
+static int kvaser_usb_simple_cmd_async(struct kvaser_usb_net_priv *priv,
+				       u8 cmd_id)
 {
 	struct kvaser_usb *dev = priv->dev;
 	struct net_device *netdev = priv->netdev;
-	struct kvaser_msg *msg;
+	struct kvaser_cmd *cmd;
 	struct urb *urb;
 	void *buf;
 	int err;
@@ -753,22 +753,22 @@ static int kvaser_usb_simple_msg_async(struct kvaser_usb_net_priv *priv,
 	if (!urb)
 		return -ENOMEM;
 
-	buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
+	buf = kmalloc(sizeof(struct kvaser_cmd), GFP_ATOMIC);
 	if (!buf) {
 		usb_free_urb(urb);
 		return -ENOMEM;
 	}
 
-	msg = (struct kvaser_msg *)buf;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_simple);
-	msg->id = msg_id;
-	msg->u.simple.channel = priv->channel;
+	cmd = (struct kvaser_cmd *)buf;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
+	cmd->id = cmd_id;
+	cmd->u.simple.channel = priv->channel;
 
 	usb_fill_bulk_urb(urb, dev->udev,
 			  usb_sndbulkpipe(dev->udev,
 					  dev->bulk_out->bEndpointAddress),
-			  buf, msg->len,
-			  kvaser_usb_simple_msg_callback, netdev);
+			  buf, cmd->len,
+			  kvaser_usb_simple_cmd_callback, netdev);
 	usb_anchor_urb(urb, &priv->tx_submitted);
 
 	err = usb_submit_urb(urb, GFP_ATOMIC);
@@ -894,7 +894,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 		if (es->status &
 		    (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
 			if (!priv->can.restart_ms)
-				kvaser_usb_simple_msg_async(priv, CMD_STOP_CHIP);
+				kvaser_usb_simple_cmd_async(priv, CMD_STOP_CHIP);
 			netif_carrier_off(priv->netdev);
 		}
 
@@ -981,27 +981,27 @@ static void kvaser_usbcan_conditionally_rx_error(const struct kvaser_usb *dev,
 }
 
 static void kvaser_usbcan_rx_error(const struct kvaser_usb *dev,
-				   const struct kvaser_msg *msg)
+				   const struct kvaser_cmd *cmd)
 {
 	struct kvaser_usb_error_summary es = { };
 
-	switch (msg->id) {
+	switch (cmd->id) {
 	/* Sometimes errors are sent as unsolicited chip state events */
 	case CMD_CHIP_STATE_EVENT:
-		es.channel = msg->u.usbcan.chip_state_event.channel;
-		es.status =  msg->u.usbcan.chip_state_event.status;
-		es.txerr = msg->u.usbcan.chip_state_event.tx_errors_count;
-		es.rxerr = msg->u.usbcan.chip_state_event.rx_errors_count;
+		es.channel = cmd->u.usbcan.chip_state_event.channel;
+		es.status =  cmd->u.usbcan.chip_state_event.status;
+		es.txerr = cmd->u.usbcan.chip_state_event.tx_errors_count;
+		es.rxerr = cmd->u.usbcan.chip_state_event.rx_errors_count;
 		kvaser_usbcan_conditionally_rx_error(dev, &es);
 		break;
 
 	case CMD_CAN_ERROR_EVENT:
 		es.channel = 0;
-		es.status = msg->u.usbcan.error_event.status_ch0;
-		es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch0;
-		es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch0;
+		es.status = cmd->u.usbcan.error_event.status_ch0;
+		es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch0;
+		es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch0;
 		es.usbcan.other_ch_status =
-			msg->u.usbcan.error_event.status_ch1;
+			cmd->u.usbcan.error_event.status_ch1;
 		kvaser_usbcan_conditionally_rx_error(dev, &es);
 
 		/* The USBCAN firmware supports up to 2 channels.
@@ -1009,51 +1009,51 @@ static void kvaser_usbcan_rx_error(const struct kvaser_usb *dev,
 		 */
 		if (dev->nchannels == MAX_USBCAN_NET_DEVICES) {
 			es.channel = 1;
-			es.status = msg->u.usbcan.error_event.status_ch1;
-			es.txerr = msg->u.usbcan.error_event.tx_errors_count_ch1;
-			es.rxerr = msg->u.usbcan.error_event.rx_errors_count_ch1;
+			es.status = cmd->u.usbcan.error_event.status_ch1;
+			es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch1;
+			es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch1;
 			es.usbcan.other_ch_status =
-				msg->u.usbcan.error_event.status_ch0;
+				cmd->u.usbcan.error_event.status_ch0;
 			kvaser_usbcan_conditionally_rx_error(dev, &es);
 		}
 		break;
 
 	default:
-		dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n",
-			msg->id);
+		dev_err(dev->udev->dev.parent, "Invalid cmd id (%d)\n",
+			cmd->id);
 	}
 }
 
 static void kvaser_leaf_rx_error(const struct kvaser_usb *dev,
-				 const struct kvaser_msg *msg)
+				 const struct kvaser_cmd *cmd)
 {
 	struct kvaser_usb_error_summary es = { };
 
-	switch (msg->id) {
+	switch (cmd->id) {
 	case CMD_CAN_ERROR_EVENT:
-		es.channel = msg->u.leaf.error_event.channel;
-		es.status =  msg->u.leaf.error_event.status;
-		es.txerr = msg->u.leaf.error_event.tx_errors_count;
-		es.rxerr = msg->u.leaf.error_event.rx_errors_count;
-		es.leaf.error_factor = msg->u.leaf.error_event.error_factor;
+		es.channel = cmd->u.leaf.error_event.channel;
+		es.status =  cmd->u.leaf.error_event.status;
+		es.txerr = cmd->u.leaf.error_event.tx_errors_count;
+		es.rxerr = cmd->u.leaf.error_event.rx_errors_count;
+		es.leaf.error_factor = cmd->u.leaf.error_event.error_factor;
 		break;
 	case CMD_LEAF_LOG_MESSAGE:
-		es.channel = msg->u.leaf.log_message.channel;
-		es.status = msg->u.leaf.log_message.data[0];
-		es.txerr = msg->u.leaf.log_message.data[2];
-		es.rxerr = msg->u.leaf.log_message.data[3];
-		es.leaf.error_factor = msg->u.leaf.log_message.data[1];
+		es.channel = cmd->u.leaf.log_message.channel;
+		es.status = cmd->u.leaf.log_message.data[0];
+		es.txerr = cmd->u.leaf.log_message.data[2];
+		es.rxerr = cmd->u.leaf.log_message.data[3];
+		es.leaf.error_factor = cmd->u.leaf.log_message.data[1];
 		break;
 	case CMD_CHIP_STATE_EVENT:
-		es.channel = msg->u.leaf.chip_state_event.channel;
-		es.status =  msg->u.leaf.chip_state_event.status;
-		es.txerr = msg->u.leaf.chip_state_event.tx_errors_count;
-		es.rxerr = msg->u.leaf.chip_state_event.rx_errors_count;
+		es.channel = cmd->u.leaf.chip_state_event.channel;
+		es.status =  cmd->u.leaf.chip_state_event.status;
+		es.txerr = cmd->u.leaf.chip_state_event.tx_errors_count;
+		es.rxerr = cmd->u.leaf.chip_state_event.rx_errors_count;
 		es.leaf.error_factor = 0;
 		break;
 	default:
-		dev_err(dev->udev->dev.parent, "Invalid msg id (%d)\n",
-			msg->id);
+		dev_err(dev->udev->dev.parent, "Invalid cmd id (%d)\n",
+			cmd->id);
 		return;
 	}
 
@@ -1061,22 +1061,22 @@ static void kvaser_leaf_rx_error(const struct kvaser_usb *dev,
 }
 
 static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv,
-				  const struct kvaser_msg *msg)
+				  const struct kvaser_cmd *cmd)
 {
 	struct can_frame *cf;
 	struct sk_buff *skb;
 	struct net_device_stats *stats = &priv->netdev->stats;
 
-	if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
+	if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
 					 MSG_FLAG_NERR)) {
 		netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n",
-			   msg->u.rx_can_header.flag);
+			   cmd->u.rx_can_header.flag);
 
 		stats->rx_errors++;
 		return;
 	}
 
-	if (msg->u.rx_can_header.flag & MSG_FLAG_OVERRUN) {
+	if (cmd->u.rx_can_header.flag & MSG_FLAG_OVERRUN) {
 		stats->rx_over_errors++;
 		stats->rx_errors++;
 
@@ -1096,14 +1096,14 @@ static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv,
 }
 
 static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
-				  const struct kvaser_msg *msg)
+				  const struct kvaser_cmd *cmd)
 {
 	struct kvaser_usb_net_priv *priv;
 	struct can_frame *cf;
 	struct sk_buff *skb;
 	struct net_device_stats *stats;
-	u8 channel = msg->u.rx_can_header.channel;
-	const u8 *rx_msg = NULL;	/* GCC */
+	u8 channel = cmd->u.rx_can_header.channel;
+	const u8 *rx_data = NULL;	/* GCC */
 
 	if (channel >= dev->nchannels) {
 		dev_err(dev->udev->dev.parent,
@@ -1114,28 +1114,28 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
 	priv = dev->nets[channel];
 	stats = &priv->netdev->stats;
 
-	if ((msg->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) &&
-	    (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE)) {
-		kvaser_leaf_rx_error(dev, msg);
+	if ((cmd->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) &&
+	    (dev->family == KVASER_LEAF && cmd->id == CMD_LEAF_LOG_MESSAGE)) {
+		kvaser_leaf_rx_error(dev, cmd);
 		return;
-	} else if (msg->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
+	} else if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
 						MSG_FLAG_NERR |
 						MSG_FLAG_OVERRUN)) {
-		kvaser_usb_rx_can_err(priv, msg);
+		kvaser_usb_rx_can_err(priv, cmd);
 		return;
-	} else if (msg->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) {
+	} else if (cmd->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) {
 		netdev_warn(priv->netdev,
 			    "Unhandled frame (flags: 0x%02x)",
-			    msg->u.rx_can_header.flag);
+			    cmd->u.rx_can_header.flag);
 		return;
 	}
 
 	switch (dev->family) {
 	case KVASER_LEAF:
-		rx_msg = msg->u.leaf.rx_can.msg;
+		rx_data = cmd->u.leaf.rx_can.data;
 		break;
 	case KVASER_USBCAN:
-		rx_msg = msg->u.usbcan.rx_can.msg;
+		rx_data = cmd->u.usbcan.rx_can.data;
 		break;
 	}
 
@@ -1145,38 +1145,37 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
 		return;
 	}
 
-	if (dev->family == KVASER_LEAF && msg->id == CMD_LEAF_LOG_MESSAGE) {
-		cf->can_id = le32_to_cpu(msg->u.leaf.log_message.id);
+	if (dev->family == KVASER_LEAF && cmd->id == CMD_LEAF_LOG_MESSAGE) {
+		cf->can_id = le32_to_cpu(cmd->u.leaf.log_message.id);
 		if (cf->can_id & KVASER_EXTENDED_FRAME)
 			cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG;
 		else
 			cf->can_id &= CAN_SFF_MASK;
 
-		cf->can_dlc = get_can_dlc(msg->u.leaf.log_message.dlc);
+		cf->can_dlc = get_can_dlc(cmd->u.leaf.log_message.dlc);
 
-		if (msg->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
+		if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
 			cf->can_id |= CAN_RTR_FLAG;
 		else
-			memcpy(cf->data, &msg->u.leaf.log_message.data,
+			memcpy(cf->data, &cmd->u.leaf.log_message.data,
 			       cf->can_dlc);
 	} else {
-		cf->can_id = ((rx_msg[0] & 0x1f) << 6) | (rx_msg[1] & 0x3f);
+		cf->can_id = ((rx_data[0] & 0x1f) << 6) | (rx_data[1] & 0x3f);
 
-		if (msg->id == CMD_RX_EXT_MESSAGE) {
+		if (cmd->id == CMD_RX_EXT_MESSAGE) {
 			cf->can_id <<= 18;
-			cf->can_id |= ((rx_msg[2] & 0x0f) << 14) |
-				      ((rx_msg[3] & 0xff) << 6) |
-				      (rx_msg[4] & 0x3f);
+			cf->can_id |= ((rx_data[2] & 0x0f) << 14) |
+				      ((rx_data[3] & 0xff) << 6) |
+				      (rx_data[4] & 0x3f);
 			cf->can_id |= CAN_EFF_FLAG;
 		}
 
-		cf->can_dlc = get_can_dlc(rx_msg[5]);
+		cf->can_dlc = get_can_dlc(rx_data[5]);
 
-		if (msg->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
+		if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
 			cf->can_id |= CAN_RTR_FLAG;
 		else
-			memcpy(cf->data, &rx_msg[6],
-			       cf->can_dlc);
+			memcpy(cf->data, &rx_data[6], cf->can_dlc);
 	}
 
 	stats->rx_packets++;
@@ -1185,10 +1184,10 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
 }
 
 static void kvaser_usb_start_chip_reply(const struct kvaser_usb *dev,
-					const struct kvaser_msg *msg)
+					const struct kvaser_cmd *cmd)
 {
 	struct kvaser_usb_net_priv *priv;
-	u8 channel = msg->u.simple.channel;
+	u8 channel = cmd->u.simple.channel;
 
 	if (channel >= dev->nchannels) {
 		dev_err(dev->udev->dev.parent,
@@ -1208,10 +1207,10 @@ static void kvaser_usb_start_chip_reply(const struct kvaser_usb *dev,
 }
 
 static void kvaser_usb_stop_chip_reply(const struct kvaser_usb *dev,
-				       const struct kvaser_msg *msg)
+				       const struct kvaser_cmd *cmd)
 {
 	struct kvaser_usb_net_priv *priv;
-	u8 channel = msg->u.simple.channel;
+	u8 channel = cmd->u.simple.channel;
 
 	if (channel >= dev->nchannels) {
 		dev_err(dev->udev->dev.parent,
@@ -1224,42 +1223,42 @@ static void kvaser_usb_stop_chip_reply(const struct kvaser_usb *dev,
 	complete(&priv->stop_comp);
 }
 
-static void kvaser_usb_handle_message(const struct kvaser_usb *dev,
-				      const struct kvaser_msg *msg)
+static void kvaser_usb_handle_cmd(const struct kvaser_usb *dev,
+				  const struct kvaser_cmd *cmd)
 {
-	switch (msg->id) {
+	switch (cmd->id) {
 	case CMD_START_CHIP_REPLY:
-		kvaser_usb_start_chip_reply(dev, msg);
+		kvaser_usb_start_chip_reply(dev, cmd);
 		break;
 
 	case CMD_STOP_CHIP_REPLY:
-		kvaser_usb_stop_chip_reply(dev, msg);
+		kvaser_usb_stop_chip_reply(dev, cmd);
 		break;
 
 	case CMD_RX_STD_MESSAGE:
 	case CMD_RX_EXT_MESSAGE:
-		kvaser_usb_rx_can_msg(dev, msg);
+		kvaser_usb_rx_can_msg(dev, cmd);
 		break;
 
 	case CMD_LEAF_LOG_MESSAGE:
 		if (dev->family != KVASER_LEAF)
 			goto warn;
-		kvaser_usb_rx_can_msg(dev, msg);
+		kvaser_usb_rx_can_msg(dev, cmd);
 		break;
 
 	case CMD_CHIP_STATE_EVENT:
 	case CMD_CAN_ERROR_EVENT:
 		if (dev->family == KVASER_LEAF)
-			kvaser_leaf_rx_error(dev, msg);
+			kvaser_leaf_rx_error(dev, cmd);
 		else
-			kvaser_usbcan_rx_error(dev, msg);
+			kvaser_usbcan_rx_error(dev, cmd);
 		break;
 
 	case CMD_TX_ACKNOWLEDGE:
-		kvaser_usb_tx_acknowledge(dev, msg);
+		kvaser_usb_tx_acknowledge(dev, cmd);
 		break;
 
-	/* Ignored messages */
+	/* Ignored commands */
 	case CMD_USBCAN_CLOCK_OVERFLOW_EVENT:
 		if (dev->family != KVASER_USBCAN)
 			goto warn;
@@ -1272,7 +1271,7 @@ static void kvaser_usb_handle_message(const struct kvaser_usb *dev,
 
 	default:
 warn:		dev_warn(dev->udev->dev.parent,
-			 "Unhandled message (%d)\n", msg->id);
+			 "Unhandled command (%d)\n", cmd->id);
 		break;
 	}
 }
@@ -1280,7 +1279,7 @@ warn:		dev_warn(dev->udev->dev.parent,
 static void kvaser_usb_read_bulk_callback(struct urb *urb)
 {
 	struct kvaser_usb *dev = urb->context;
-	struct kvaser_msg *msg;
+	struct kvaser_cmd *cmd;
 	int pos = 0;
 	int err, i;
 
@@ -1298,10 +1297,10 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 		goto resubmit_urb;
 	}
 
-	while (pos <= (int)(urb->actual_length - MSG_HEADER_LEN)) {
-		msg = urb->transfer_buffer + pos;
+	while (pos <= (int)(urb->actual_length - CMD_HEADER_LEN)) {
+		cmd = urb->transfer_buffer + pos;
 
-		/* The Kvaser firmware can only read and write messages that
+		/* The Kvaser firmware can only read and write commands that
 		 * does not cross the USB's endpoint wMaxPacketSize boundary.
 		 * If a follow-up command crosses such boundary, firmware puts
 		 * a placeholder zero-length command in its place then aligns
@@ -1310,20 +1309,20 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 		 * Handle such cases or we're going to miss a significant
 		 * number of events in case of a heavy rx load on the bus.
 		 */
-		if (msg->len == 0) {
+		if (cmd->len == 0) {
 			pos = round_up(pos, le16_to_cpu(dev->bulk_in->
 							wMaxPacketSize));
 			continue;
 		}
 
-		if (pos + msg->len > urb->actual_length) {
+		if (pos + cmd->len > urb->actual_length) {
 			dev_err_ratelimited(dev->udev->dev.parent,
 					    "Format error\n");
 			break;
 		}
 
-		kvaser_usb_handle_message(dev, msg);
-		pos += msg->len;
+		kvaser_usb_handle_cmd(dev, cmd);
+		pos += cmd->len;
 	}
 
 resubmit_urb:
@@ -1416,26 +1415,26 @@ static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
 
 static int kvaser_usb_set_opt_mode(const struct kvaser_usb_net_priv *priv)
 {
-	struct kvaser_msg *msg;
+	struct kvaser_cmd *cmd;
 	int rc;
 
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
 		return -ENOMEM;
 
-	msg->id = CMD_SET_CTRL_MODE;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_ctrl_mode);
-	msg->u.ctrl_mode.tid = 0xff;
-	msg->u.ctrl_mode.channel = priv->channel;
+	cmd->id = CMD_SET_CTRL_MODE;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_ctrl_mode);
+	cmd->u.ctrl_mode.tid = 0xff;
+	cmd->u.ctrl_mode.channel = priv->channel;
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
-		msg->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT;
+		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT;
 	else
-		msg->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL;
+		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL;
 
-	rc = kvaser_usb_send_msg(priv->dev, msg);
+	rc = kvaser_usb_send_cmd(priv->dev, cmd);
 
-	kfree(msg);
+	kfree(cmd);
 	return rc;
 }
 
@@ -1445,7 +1444,7 @@ static int kvaser_usb_start_chip(struct kvaser_usb_net_priv *priv)
 
 	init_completion(&priv->start_comp);
 
-	err = kvaser_usb_send_simple_msg(priv->dev, CMD_START_CHIP,
+	err = kvaser_usb_send_simple_cmd(priv->dev, CMD_START_CHIP,
 					 priv->channel);
 	if (err)
 		return err;
@@ -1535,7 +1534,7 @@ static int kvaser_usb_stop_chip(struct kvaser_usb_net_priv *priv)
 
 	init_completion(&priv->stop_comp);
 
-	err = kvaser_usb_send_simple_msg(priv->dev, CMD_STOP_CHIP,
+	err = kvaser_usb_send_simple_cmd(priv->dev, CMD_STOP_CHIP,
 					 priv->channel);
 	if (err)
 		return err;
@@ -1549,21 +1548,21 @@ static int kvaser_usb_stop_chip(struct kvaser_usb_net_priv *priv)
 
 static int kvaser_usb_flush_queue(struct kvaser_usb_net_priv *priv)
 {
-	struct kvaser_msg *msg;
+	struct kvaser_cmd *cmd;
 	int rc;
 
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
 		return -ENOMEM;
 
-	msg->id = CMD_FLUSH_QUEUE;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_flush_queue);
-	msg->u.flush_queue.channel = priv->channel;
-	msg->u.flush_queue.flags = 0x00;
+	cmd->id = CMD_FLUSH_QUEUE;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_flush_queue);
+	cmd->u.flush_queue.channel = priv->channel;
+	cmd->u.flush_queue.flags = 0x00;
 
-	rc = kvaser_usb_send_msg(priv->dev, msg);
+	rc = kvaser_usb_send_cmd(priv->dev, cmd);
 
-	kfree(msg);
+	kfree(cmd);
 	return rc;
 }
 
@@ -1579,7 +1578,7 @@ static int kvaser_usb_close(struct net_device *netdev)
 	if (err)
 		netdev_warn(netdev, "Cannot flush queue, error %d\n", err);
 
-	err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, priv->channel);
+	err = kvaser_usb_send_simple_cmd(dev, CMD_RESET_CHIP, priv->channel);
 	if (err)
 		netdev_warn(netdev, "Cannot reset card, error %d\n", err);
 
@@ -1627,9 +1626,9 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 	struct kvaser_usb_tx_urb_context *context = NULL;
 	struct urb *urb;
 	void *buf;
-	struct kvaser_msg *msg;
+	struct kvaser_cmd *cmd;
 	int i, err, ret = NETDEV_TX_OK;
-	u8 *msg_tx_can_flags = NULL;		/* GCC */
+	u8 *cmd_tx_can_flags = NULL;		/* GCC */
 	unsigned long flags;
 
 	if (can_dropped_invalid_skb(netdev, skb))
@@ -1642,46 +1641,46 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 		return NETDEV_TX_OK;
 	}
 
-	buf = kmalloc(sizeof(struct kvaser_msg), GFP_ATOMIC);
+	buf = kmalloc(sizeof(struct kvaser_cmd), GFP_ATOMIC);
 	if (!buf) {
 		stats->tx_dropped++;
 		dev_kfree_skb(skb);
 		goto freeurb;
 	}
 
-	msg = buf;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_tx_can);
-	msg->u.tx_can.channel = priv->channel;
+	cmd = buf;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_tx_can);
+	cmd->u.tx_can.channel = priv->channel;
 
 	switch (dev->family) {
 	case KVASER_LEAF:
-		msg_tx_can_flags = &msg->u.tx_can.leaf.flags;
+		cmd_tx_can_flags = &cmd->u.tx_can.leaf.flags;
 		break;
 	case KVASER_USBCAN:
-		msg_tx_can_flags = &msg->u.tx_can.usbcan.flags;
+		cmd_tx_can_flags = &cmd->u.tx_can.usbcan.flags;
 		break;
 	}
 
-	*msg_tx_can_flags = 0;
+	*cmd_tx_can_flags = 0;
 
 	if (cf->can_id & CAN_EFF_FLAG) {
-		msg->id = CMD_TX_EXT_MESSAGE;
-		msg->u.tx_can.msg[0] = (cf->can_id >> 24) & 0x1f;
-		msg->u.tx_can.msg[1] = (cf->can_id >> 18) & 0x3f;
-		msg->u.tx_can.msg[2] = (cf->can_id >> 14) & 0x0f;
-		msg->u.tx_can.msg[3] = (cf->can_id >> 6) & 0xff;
-		msg->u.tx_can.msg[4] = cf->can_id & 0x3f;
+		cmd->id = CMD_TX_EXT_MESSAGE;
+		cmd->u.tx_can.data[0] = (cf->can_id >> 24) & 0x1f;
+		cmd->u.tx_can.data[1] = (cf->can_id >> 18) & 0x3f;
+		cmd->u.tx_can.data[2] = (cf->can_id >> 14) & 0x0f;
+		cmd->u.tx_can.data[3] = (cf->can_id >> 6) & 0xff;
+		cmd->u.tx_can.data[4] = cf->can_id & 0x3f;
 	} else {
-		msg->id = CMD_TX_STD_MESSAGE;
-		msg->u.tx_can.msg[0] = (cf->can_id >> 6) & 0x1f;
-		msg->u.tx_can.msg[1] = cf->can_id & 0x3f;
+		cmd->id = CMD_TX_STD_MESSAGE;
+		cmd->u.tx_can.data[0] = (cf->can_id >> 6) & 0x1f;
+		cmd->u.tx_can.data[1] = cf->can_id & 0x3f;
 	}
 
-	msg->u.tx_can.msg[5] = cf->can_dlc;
-	memcpy(&msg->u.tx_can.msg[6], cf->data, cf->can_dlc);
+	cmd->u.tx_can.data[5] = cf->can_dlc;
+	memcpy(&cmd->u.tx_can.data[6], cf->data, cf->can_dlc);
 
 	if (cf->can_id & CAN_RTR_FLAG)
-		*msg_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
+		*cmd_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
 
 	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
 	for (i = 0; i < dev->max_tx_urbs; i++) {
@@ -1711,12 +1710,12 @@ static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
 	context->priv = priv;
 	context->dlc = cf->can_dlc;
 
-	msg->u.tx_can.tid = context->echo_index;
+	cmd->u.tx_can.tid = context->echo_index;
 
 	usb_fill_bulk_urb(urb, dev->udev,
 			  usb_sndbulkpipe(dev->udev,
 					  dev->bulk_out->bEndpointAddress),
-			  buf, msg->len,
+			  buf, cmd->len,
 			  kvaser_usb_write_bulk_callback, context);
 	usb_anchor_urb(urb, &priv->tx_submitted);
 
@@ -1775,30 +1774,30 @@ static int kvaser_usb_set_bittiming(struct net_device *netdev)
 	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
 	struct can_bittiming *bt = &priv->can.bittiming;
 	struct kvaser_usb *dev = priv->dev;
-	struct kvaser_msg *msg;
+	struct kvaser_cmd *cmd;
 	int rc;
 
-	msg = kmalloc(sizeof(*msg), GFP_KERNEL);
-	if (!msg)
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
 		return -ENOMEM;
 
-	msg->id = CMD_SET_BUS_PARAMS;
-	msg->len = MSG_HEADER_LEN + sizeof(struct kvaser_msg_busparams);
-	msg->u.busparams.channel = priv->channel;
-	msg->u.busparams.tid = 0xff;
-	msg->u.busparams.bitrate = cpu_to_le32(bt->bitrate);
-	msg->u.busparams.sjw = bt->sjw;
-	msg->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1;
-	msg->u.busparams.tseg2 = bt->phase_seg2;
+	cmd->id = CMD_SET_BUS_PARAMS;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_busparams);
+	cmd->u.busparams.channel = priv->channel;
+	cmd->u.busparams.tid = 0xff;
+	cmd->u.busparams.bitrate = cpu_to_le32(bt->bitrate);
+	cmd->u.busparams.sjw = bt->sjw;
+	cmd->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1;
+	cmd->u.busparams.tseg2 = bt->phase_seg2;
 
 	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
-		msg->u.busparams.no_samp = 3;
+		cmd->u.busparams.no_samp = 3;
 	else
-		msg->u.busparams.no_samp = 1;
+		cmd->u.busparams.no_samp = 1;
 
-	rc = kvaser_usb_send_msg(dev, msg);
+	rc = kvaser_usb_send_cmd(dev, cmd);
 
-	kfree(msg);
+	kfree(cmd);
 	return rc;
 }
 
@@ -1810,7 +1809,7 @@ static int kvaser_usb_set_mode(struct net_device *netdev,
 
 	switch (mode) {
 	case CAN_MODE_START:
-		err = kvaser_usb_simple_msg_async(priv, CMD_START_CHIP);
+		err = kvaser_usb_simple_cmd_async(priv, CMD_START_CHIP);
 		if (err)
 			return err;
 		break;
@@ -1860,7 +1859,7 @@ static int kvaser_usb_init_one(struct usb_interface *intf,
 	struct kvaser_usb_net_priv *priv;
 	int err;
 
-	err = kvaser_usb_send_simple_msg(dev, CMD_RESET_CHIP, channel);
+	err = kvaser_usb_send_simple_cmd(dev, CMD_RESET_CHIP, channel);
 	if (err)
 		return err;
 
-- 
cgit v1.2.3


From 75d2b4c3e399ff8a59dc6e22dc6d281345d51374 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:21 +0200
Subject: can: kvaser_usb: Replace USB timeout constants with one define

Replace USB timeout constants used when sending and receiving, with a
single constant.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 16 ++++++----------
 1 file changed, 6 insertions(+), 10 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 5168b63fcd51..9c33f725d9dc 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -26,10 +26,7 @@
 #include <linux/can/error.h>
 
 #define MAX_RX_URBS			4
-#define START_TIMEOUT			1000 /* msecs */
-#define STOP_TIMEOUT			1000 /* msecs */
-#define USB_SEND_TIMEOUT		1000 /* msecs */
-#define USB_RECV_TIMEOUT		1000 /* msecs */
+#define KVASER_USB_TIMEOUT		1000 /* msecs */
 #define RX_BUFFER_SIZE			3072
 #define CAN_USB_CLOCK			8000000
 #define MAX_NET_DEVICES			3
@@ -529,8 +526,7 @@ static inline int kvaser_usb_send_cmd(const struct kvaser_usb *dev,
 	return usb_bulk_msg(dev->udev,
 			    usb_sndbulkpipe(dev->udev,
 					dev->bulk_out->bEndpointAddress),
-			    cmd, cmd->len, &actual_len,
-			    USB_SEND_TIMEOUT);
+			    cmd, cmd->len, &actual_len, KVASER_USB_TIMEOUT);
 }
 
 static int kvaser_usb_wait_cmd(const struct kvaser_usb *dev, u8 id,
@@ -541,7 +537,7 @@ static int kvaser_usb_wait_cmd(const struct kvaser_usb *dev, u8 id,
 	int actual_len;
 	int err;
 	int pos;
-	unsigned long to = jiffies + msecs_to_jiffies(USB_RECV_TIMEOUT);
+	unsigned long to = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT);
 
 	buf = kzalloc(RX_BUFFER_SIZE, GFP_KERNEL);
 	if (!buf)
@@ -552,7 +548,7 @@ static int kvaser_usb_wait_cmd(const struct kvaser_usb *dev, u8 id,
 				   usb_rcvbulkpipe(dev->udev,
 					dev->bulk_in->bEndpointAddress),
 				   buf, RX_BUFFER_SIZE, &actual_len,
-				   USB_RECV_TIMEOUT);
+				   KVASER_USB_TIMEOUT);
 		if (err < 0)
 			goto end;
 
@@ -1450,7 +1446,7 @@ static int kvaser_usb_start_chip(struct kvaser_usb_net_priv *priv)
 		return err;
 
 	if (!wait_for_completion_timeout(&priv->start_comp,
-					 msecs_to_jiffies(START_TIMEOUT)))
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
 		return -ETIMEDOUT;
 
 	return 0;
@@ -1540,7 +1536,7 @@ static int kvaser_usb_stop_chip(struct kvaser_usb_net_priv *priv)
 		return err;
 
 	if (!wait_for_completion_timeout(&priv->stop_comp,
-					 msecs_to_jiffies(STOP_TIMEOUT)))
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
 		return -ETIMEDOUT;
 
 	return 0;
-- 
cgit v1.2.3


From 0e30619fd6fae62c58d76e739b8ba7a14c52c4bd Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:22 +0200
Subject: can: kvaser_usb: Add pointer to struct usb_interface into struct
 kvaser_usb

Add pointer to struct usb_interface into struct kvaser_usb.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 9c33f725d9dc..9e0e2c852943 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -414,6 +414,7 @@ struct kvaser_usb_tx_urb_context {
 
 struct kvaser_usb {
 	struct usb_device *udev;
+	struct usb_interface *intf;
 	struct kvaser_usb_net_priv *nets[MAX_NET_DEVICES];
 
 	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
@@ -1962,6 +1963,8 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 		return -ENODEV;
 	}
 
+	dev->intf = intf;
+
 	err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out);
 	if (err) {
 		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
-- 
cgit v1.2.3


From 99ce1bc1746266a20e91417b600533e82d57734d Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:23 +0200
Subject: can: kvaser_usb: Refactor kvaser_usb_get_endpoints()

Replace parameters with struct kvaser_usb pointer. Rename the function
from kvaser_usb_get_endpoints() to kvaser_usb_setup_endpoints().

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 9e0e2c852943..cb3a2d6d3ba4 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -1914,27 +1914,25 @@ static int kvaser_usb_init_one(struct usb_interface *intf,
 	return 0;
 }
 
-static int kvaser_usb_get_endpoints(const struct usb_interface *intf,
-				    struct usb_endpoint_descriptor **in,
-				    struct usb_endpoint_descriptor **out)
+static int kvaser_usb_setup_endpoints(struct kvaser_usb *dev)
 {
 	const struct usb_host_interface *iface_desc;
 	struct usb_endpoint_descriptor *endpoint;
 	int i;
 
-	iface_desc = &intf->altsetting[0];
+	iface_desc = &dev->intf->altsetting[0];
 
 	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
 		endpoint = &iface_desc->endpoint[i].desc;
 
-		if (!*in && usb_endpoint_is_bulk_in(endpoint))
-			*in = endpoint;
+		if (!dev->bulk_in && usb_endpoint_is_bulk_in(endpoint))
+			dev->bulk_in = endpoint;
 
-		if (!*out && usb_endpoint_is_bulk_out(endpoint))
-			*out = endpoint;
+		if (!dev->bulk_out && usb_endpoint_is_bulk_out(endpoint))
+			dev->bulk_out = endpoint;
 
 		/* use first bulk endpoint for in and out */
-		if (*in && *out)
+		if (dev->bulk_in && dev->bulk_out)
 			return 0;
 	}
 
@@ -1965,7 +1963,7 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 
 	dev->intf = intf;
 
-	err = kvaser_usb_get_endpoints(intf, &dev->bulk_in, &dev->bulk_out);
+	err = kvaser_usb_setup_endpoints(dev);
 	if (err) {
 		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
 		return err;
-- 
cgit v1.2.3


From 7c47801461777c8cb473cca65202a60b99657313 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:24 +0200
Subject: can: kvaser_usb: Refactor kvaser_usb_init_one()

Replace first parameter in kvaser_usb_init_one() with a pointer to
struct kvaser_usb.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index cb3a2d6d3ba4..7f7ebaffb3f0 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -1848,10 +1848,9 @@ static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev)
 	}
 }
 
-static int kvaser_usb_init_one(struct usb_interface *intf,
+static int kvaser_usb_init_one(struct kvaser_usb *dev,
 			       const struct usb_device_id *id, int channel)
 {
-	struct kvaser_usb *dev = usb_get_intfdata(intf);
 	struct net_device *netdev;
 	struct kvaser_usb_net_priv *priv;
 	int err;
@@ -1864,7 +1863,7 @@ static int kvaser_usb_init_one(struct usb_interface *intf,
 			      dev->max_tx_urbs * sizeof(*priv->tx_contexts),
 			      dev->max_tx_urbs);
 	if (!netdev) {
-		dev_err(&intf->dev, "Cannot alloc candev\n");
+		dev_err(&dev->intf->dev, "Cannot alloc candev\n");
 		return -ENOMEM;
 	}
 
@@ -1896,14 +1895,14 @@ static int kvaser_usb_init_one(struct usb_interface *intf,
 
 	netdev->netdev_ops = &kvaser_usb_netdev_ops;
 
-	SET_NETDEV_DEV(netdev, &intf->dev);
+	SET_NETDEV_DEV(netdev, &dev->intf->dev);
 	netdev->dev_id = channel;
 
 	dev->nets[channel] = priv;
 
 	err = register_candev(netdev);
 	if (err) {
-		dev_err(&intf->dev, "Failed to register can device\n");
+		dev_err(&dev->intf->dev, "Failed to register can device\n");
 		free_candev(netdev);
 		dev->nets[channel] = NULL;
 		return err;
@@ -2005,7 +2004,7 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	}
 
 	for (i = 0; i < dev->nchannels; i++) {
-		err = kvaser_usb_init_one(intf, id, i);
+		err = kvaser_usb_init_one(dev, id, i);
 		if (err) {
 			kvaser_usb_remove_interfaces(dev);
 			return err;
-- 
cgit v1.2.3


From 6ba0b9294bca0fca727198a9660771d06823cf1a Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:25 +0200
Subject: can: kvaser_usb: Improve logging messages

Replace dev->udev->dev.parent with &dev->intf->dev, when it is the
first argument passed to dev_* logging function call.

This will result in:
kvaser_usb 1-2:1.0: Format error
compared to
usb 1-2: Format error

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 40 +++++++++++++++++-----------------------
 1 file changed, 17 insertions(+), 23 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 7f7ebaffb3f0..0559d139f988 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -568,7 +568,7 @@ static int kvaser_usb_wait_cmd(const struct kvaser_usb *dev, u8 id,
 			}
 
 			if (pos + tmp->len > actual_len) {
-				dev_err_ratelimited(dev->udev->dev.parent,
+				dev_err_ratelimited(&dev->intf->dev,
 						    "Format error\n");
 				break;
 			}
@@ -677,7 +677,7 @@ static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev,
 	tid = cmd->u.tx_acknowledge_header.tid;
 
 	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
+		dev_err(&dev->intf->dev,
 			"Invalid channel number (%d)\n", channel);
 		return;
 	}
@@ -858,7 +858,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 	enum can_state old_state, new_state;
 
 	if (es->channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
+		dev_err(&dev->intf->dev,
 			"Invalid channel number (%d)\n", es->channel);
 		return;
 	}
@@ -951,7 +951,7 @@ static void kvaser_usbcan_conditionally_rx_error(const struct kvaser_usb *dev,
 
 	channel = es->channel;
 	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
+		dev_err(&dev->intf->dev,
 			"Invalid channel number (%d)\n", channel);
 		return;
 	}
@@ -1016,8 +1016,7 @@ static void kvaser_usbcan_rx_error(const struct kvaser_usb *dev,
 		break;
 
 	default:
-		dev_err(dev->udev->dev.parent, "Invalid cmd id (%d)\n",
-			cmd->id);
+		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
 	}
 }
 
@@ -1049,8 +1048,7 @@ static void kvaser_leaf_rx_error(const struct kvaser_usb *dev,
 		es.leaf.error_factor = 0;
 		break;
 	default:
-		dev_err(dev->udev->dev.parent, "Invalid cmd id (%d)\n",
-			cmd->id);
+		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
 		return;
 	}
 
@@ -1103,7 +1101,7 @@ static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
 	const u8 *rx_data = NULL;	/* GCC */
 
 	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
+		dev_err(&dev->intf->dev,
 			"Invalid channel number (%d)\n", channel);
 		return;
 	}
@@ -1187,7 +1185,7 @@ static void kvaser_usb_start_chip_reply(const struct kvaser_usb *dev,
 	u8 channel = cmd->u.simple.channel;
 
 	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
+		dev_err(&dev->intf->dev,
 			"Invalid channel number (%d)\n", channel);
 		return;
 	}
@@ -1210,7 +1208,7 @@ static void kvaser_usb_stop_chip_reply(const struct kvaser_usb *dev,
 	u8 channel = cmd->u.simple.channel;
 
 	if (channel >= dev->nchannels) {
-		dev_err(dev->udev->dev.parent,
+		dev_err(&dev->intf->dev,
 			"Invalid channel number (%d)\n", channel);
 		return;
 	}
@@ -1267,8 +1265,7 @@ static void kvaser_usb_handle_cmd(const struct kvaser_usb *dev,
 		break;
 
 	default:
-warn:		dev_warn(dev->udev->dev.parent,
-			 "Unhandled command (%d)\n", cmd->id);
+warn:		dev_warn(&dev->intf->dev, "Unhandled command (%d)\n", cmd->id);
 		break;
 	}
 }
@@ -1289,8 +1286,7 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 	case -ESHUTDOWN:
 		return;
 	default:
-		dev_info(dev->udev->dev.parent, "Rx URB aborted (%d)\n",
-			 urb->status);
+		dev_info(&dev->intf->dev, "Rx URB aborted (%d)\n", urb->status);
 		goto resubmit_urb;
 	}
 
@@ -1313,8 +1309,7 @@ static void kvaser_usb_read_bulk_callback(struct urb *urb)
 		}
 
 		if (pos + cmd->len > urb->actual_length) {
-			dev_err_ratelimited(dev->udev->dev.parent,
-					    "Format error\n");
+			dev_err_ratelimited(&dev->intf->dev, "Format error\n");
 			break;
 		}
 
@@ -1338,7 +1333,7 @@ resubmit_urb:
 			netif_device_detach(dev->nets[i]->netdev);
 		}
 	} else if (err) {
-		dev_err(dev->udev->dev.parent,
+		dev_err(&dev->intf->dev,
 			"Failed resubmitting read bulk urb: %d\n", err);
 	}
 }
@@ -1364,7 +1359,7 @@ static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
 		buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE,
 					 GFP_KERNEL, &buf_dma);
 		if (!buf) {
-			dev_warn(dev->udev->dev.parent,
+			dev_warn(&dev->intf->dev,
 				 "No memory left for USB buffer\n");
 			usb_free_urb(urb);
 			err = -ENOMEM;
@@ -1397,12 +1392,11 @@ static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
 	}
 
 	if (i == 0) {
-		dev_warn(dev->udev->dev.parent,
-			 "Cannot setup read URBs, error %d\n", err);
+		dev_warn(&dev->intf->dev, "Cannot setup read URBs, error %d\n",
+			 err);
 		return err;
 	} else if (i < MAX_RX_URBS) {
-		dev_warn(dev->udev->dev.parent,
-			 "RX performances may be slow\n");
+		dev_warn(&dev->intf->dev, "RX performances may be slow\n");
 	}
 
 	dev->rxinitdone = true;
-- 
cgit v1.2.3


From 2b049c1500803081e26be46cf5a02d63a3eb13a4 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:26 +0200
Subject: can: kvaser_usb: Fix typos

Fix some typos. Change can to CAN, when referring to
Controller Area Network.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 0559d139f988..07b91841140a 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -85,7 +85,7 @@ static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
 /* Command header size */
 #define CMD_HEADER_LEN			2
 
-/* Can message flags */
+/* CAN message flags */
 #define MSG_FLAG_ERROR_FRAME		BIT(0)
 #define MSG_FLAG_OVERRUN		BIT(1)
 #define MSG_FLAG_NERR			BIT(2)
@@ -95,7 +95,7 @@ static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
 #define MSG_FLAG_TX_ACK			BIT(6)
 #define MSG_FLAG_TX_REQUEST		BIT(7)
 
-/* Can states (M16C CxSTRH register) */
+/* CAN states (M16C CxSTRH register) */
 #define M16C_STATE_BUS_RESET		BIT(0)
 #define M16C_STATE_BUS_ERROR		BIT(4)
 #define M16C_STATE_BUS_PASSIVE		BIT(5)
@@ -866,14 +866,14 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 	priv = dev->nets[es->channel];
 	stats = &priv->netdev->stats;
 
-	/* Update all of the can interface's state and error counters before
+	/* Update all of the CAN interface's state and error counters before
 	 * trying any memory allocation that can actually fail with -ENOMEM.
 	 *
-	 * We send a temporary stack-allocated error can frame to
+	 * We send a temporary stack-allocated error CAN frame to
 	 * can_change_state() for the very same reason.
 	 *
 	 * TODO: Split can_change_state() responsibility between updating the
-	 * can interface's state and counters, and the setting up of can error
+	 * CAN interface's state and counters, and the setting up of CAN error
 	 * frame ID and data to userspace. Remove stack allocation afterwards.
 	 */
 	old_state = priv->can.state;
@@ -939,7 +939,7 @@ static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
 	netif_rx(skb);
 }
 
-/* For USBCAN, report error to userspace iff the channels's errors counter
+/* For USBCAN, report error to userspace if the channels's errors counter
  * has changed, or we're the only channel seeing a bus error state.
  */
 static void kvaser_usbcan_conditionally_rx_error(const struct kvaser_usb *dev,
@@ -1896,7 +1896,7 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev,
 
 	err = register_candev(netdev);
 	if (err) {
-		dev_err(&dev->intf->dev, "Failed to register can device\n");
+		dev_err(&dev->intf->dev, "Failed to register CAN device\n");
 		free_candev(netdev);
 		dev->nets[channel] = NULL;
 		return err;
-- 
cgit v1.2.3


From e0543f2479f811e431005906462c04a9b582caee Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:27 +0200
Subject: can: kvaser_usb: Add SPDX GPL-2.0 license identifier

Add SPDX GPL-2.0 license identifier to kvaser_usb.c.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
index 07b91841140a..fd5890f7917f 100644
--- a/drivers/net/can/usb/kvaser_usb.c
+++ b/drivers/net/can/usb/kvaser_usb.c
@@ -1,9 +1,5 @@
-/*
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation version 2.
- *
- * Parts of this driver are based on the following:
+// SPDX-License-Identifier: GPL-2.0
+/* Parts of this driver are based on the following:
  *  - Kvaser linux leaf driver (version 4.78)
  *  - CAN driver for esd CAN-USB/2
  *  - Kvaser linux usbcanII driver (version 5.3)
-- 
cgit v1.2.3


From 7259124eac7d1b76b41c7a9cb2511a30556deebe Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:28 +0200
Subject: can: kvaser_usb: Split driver into kvaser_usb_core.c and
 kvaser_usb_leaf.c

First part of adding support for Kvaser USB device family "hydra".

Split kvaser_usb.c into kvaser_usb/kvaser_usb{.h,_core.c,_leaf.c}.

kvaser_usb_core.c contains common functionality, such as USB
writing/reading and allocation of netdev.
kvaser_usb_leaf.c contains device specific code, used in
kvaser_usb_core.c.

struct kvaser_usb_dev_ops contains device specific functions that are
common for all devices in the family. While, struct kvaser_usb_dev_cfg
describes the device configurations in terms of CAN clock frequency,
timestamp frequency and CAN controller bittiming constants.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/Makefile                     |    2 +-
 drivers/net/can/usb/kvaser_usb.c                 | 2030 ----------------------
 drivers/net/can/usb/kvaser_usb/Makefile          |    2 +
 drivers/net/can/usb/kvaser_usb/kvaser_usb.h      |  158 ++
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c |  769 ++++++++
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 1363 +++++++++++++++
 6 files changed, 2293 insertions(+), 2031 deletions(-)
 delete mode 100644 drivers/net/can/usb/kvaser_usb.c
 create mode 100644 drivers/net/can/usb/kvaser_usb/Makefile
 create mode 100644 drivers/net/can/usb/kvaser_usb/kvaser_usb.h
 create mode 100644 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
 create mode 100644 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c

diff --git a/drivers/net/can/usb/Makefile b/drivers/net/can/usb/Makefile
index 613b1999d4d7..aa0f17c0b2ed 100644
--- a/drivers/net/can/usb/Makefile
+++ b/drivers/net/can/usb/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_CAN_8DEV_USB) += usb_8dev.o
 obj-$(CONFIG_CAN_EMS_USB) += ems_usb.o
 obj-$(CONFIG_CAN_ESD_USB2) += esd_usb2.o
 obj-$(CONFIG_CAN_GS_USB) += gs_usb.o
-obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
+obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb/
 obj-$(CONFIG_CAN_MCBA_USB) += mcba_usb.o
 obj-$(CONFIG_CAN_PEAK_USB) += peak_usb/
 obj-$(CONFIG_CAN_UCAN) += ucan.o
diff --git a/drivers/net/can/usb/kvaser_usb.c b/drivers/net/can/usb/kvaser_usb.c
deleted file mode 100644
index fd5890f7917f..000000000000
--- a/drivers/net/can/usb/kvaser_usb.c
+++ /dev/null
@@ -1,2030 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Parts of this driver are based on the following:
- *  - Kvaser linux leaf driver (version 4.78)
- *  - CAN driver for esd CAN-USB/2
- *  - Kvaser linux usbcanII driver (version 5.3)
- *
- * Copyright (C) 2002-2006 KVASER AB, Sweden. All rights reserved.
- * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
- * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
- * Copyright (C) 2015 Valeo S.A.
- */
-
-#include <linux/spinlock.h>
-#include <linux/kernel.h>
-#include <linux/completion.h>
-#include <linux/module.h>
-#include <linux/netdevice.h>
-#include <linux/usb.h>
-
-#include <linux/can.h>
-#include <linux/can/dev.h>
-#include <linux/can/error.h>
-
-#define MAX_RX_URBS			4
-#define KVASER_USB_TIMEOUT		1000 /* msecs */
-#define RX_BUFFER_SIZE			3072
-#define CAN_USB_CLOCK			8000000
-#define MAX_NET_DEVICES			3
-#define MAX_USBCAN_NET_DEVICES		2
-
-/* Kvaser Leaf USB devices */
-#define KVASER_VENDOR_ID		0x0bfd
-#define USB_LEAF_DEVEL_PRODUCT_ID	10
-#define USB_LEAF_LITE_PRODUCT_ID	11
-#define USB_LEAF_PRO_PRODUCT_ID		12
-#define USB_LEAF_SPRO_PRODUCT_ID	14
-#define USB_LEAF_PRO_LS_PRODUCT_ID	15
-#define USB_LEAF_PRO_SWC_PRODUCT_ID	16
-#define USB_LEAF_PRO_LIN_PRODUCT_ID	17
-#define USB_LEAF_SPRO_LS_PRODUCT_ID	18
-#define USB_LEAF_SPRO_SWC_PRODUCT_ID	19
-#define USB_MEMO2_DEVEL_PRODUCT_ID	22
-#define USB_MEMO2_HSHS_PRODUCT_ID	23
-#define USB_UPRO_HSHS_PRODUCT_ID	24
-#define USB_LEAF_LITE_GI_PRODUCT_ID	25
-#define USB_LEAF_PRO_OBDII_PRODUCT_ID	26
-#define USB_MEMO2_HSLS_PRODUCT_ID	27
-#define USB_LEAF_LITE_CH_PRODUCT_ID	28
-#define USB_BLACKBIRD_SPRO_PRODUCT_ID	29
-#define USB_OEM_MERCURY_PRODUCT_ID	34
-#define USB_OEM_LEAF_PRODUCT_ID		35
-#define USB_CAN_R_PRODUCT_ID		39
-#define USB_LEAF_LITE_V2_PRODUCT_ID	288
-#define USB_MINI_PCIE_HS_PRODUCT_ID	289
-#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID 290
-#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID	291
-#define USB_MINI_PCIE_2HS_PRODUCT_ID	292
-
-static inline bool kvaser_is_leaf(const struct usb_device_id *id)
-{
-	return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
-	       id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID;
-}
-
-/* Kvaser USBCan-II devices */
-#define USB_USBCAN_REVB_PRODUCT_ID	2
-#define USB_VCI2_PRODUCT_ID		3
-#define USB_USBCAN2_PRODUCT_ID		4
-#define USB_MEMORATOR_PRODUCT_ID	5
-
-static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
-{
-	return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID &&
-	       id->idProduct <= USB_MEMORATOR_PRODUCT_ID;
-}
-
-/* USB devices features */
-#define KVASER_HAS_SILENT_MODE		BIT(0)
-#define KVASER_HAS_TXRX_ERRORS		BIT(1)
-
-/* Command header size */
-#define CMD_HEADER_LEN			2
-
-/* CAN message flags */
-#define MSG_FLAG_ERROR_FRAME		BIT(0)
-#define MSG_FLAG_OVERRUN		BIT(1)
-#define MSG_FLAG_NERR			BIT(2)
-#define MSG_FLAG_WAKEUP			BIT(3)
-#define MSG_FLAG_REMOTE_FRAME		BIT(4)
-#define MSG_FLAG_RESERVED		BIT(5)
-#define MSG_FLAG_TX_ACK			BIT(6)
-#define MSG_FLAG_TX_REQUEST		BIT(7)
-
-/* CAN states (M16C CxSTRH register) */
-#define M16C_STATE_BUS_RESET		BIT(0)
-#define M16C_STATE_BUS_ERROR		BIT(4)
-#define M16C_STATE_BUS_PASSIVE		BIT(5)
-#define M16C_STATE_BUS_OFF		BIT(6)
-
-/* Leaf/usbcan command ids */
-#define CMD_RX_STD_MESSAGE		12
-#define CMD_TX_STD_MESSAGE		13
-#define CMD_RX_EXT_MESSAGE		14
-#define CMD_TX_EXT_MESSAGE		15
-#define CMD_SET_BUS_PARAMS		16
-#define CMD_CHIP_STATE_EVENT		20
-#define CMD_SET_CTRL_MODE		21
-#define CMD_RESET_CHIP			24
-#define CMD_START_CHIP			26
-#define CMD_START_CHIP_REPLY		27
-#define CMD_STOP_CHIP			28
-#define CMD_STOP_CHIP_REPLY		29
-
-#define CMD_USBCAN_CLOCK_OVERFLOW_EVENT	33
-
-#define CMD_GET_CARD_INFO		34
-#define CMD_GET_CARD_INFO_REPLY		35
-#define CMD_GET_SOFTWARE_INFO		38
-#define CMD_GET_SOFTWARE_INFO_REPLY	39
-#define CMD_FLUSH_QUEUE			48
-#define CMD_TX_ACKNOWLEDGE		50
-#define CMD_CAN_ERROR_EVENT		51
-#define CMD_FLUSH_QUEUE_REPLY		68
-
-#define CMD_LEAF_LOG_MESSAGE		106
-
-/* error factors */
-#define M16C_EF_ACKE			BIT(0)
-#define M16C_EF_CRCE			BIT(1)
-#define M16C_EF_FORME			BIT(2)
-#define M16C_EF_STFE			BIT(3)
-#define M16C_EF_BITE0			BIT(4)
-#define M16C_EF_BITE1			BIT(5)
-#define M16C_EF_RCVE			BIT(6)
-#define M16C_EF_TRE			BIT(7)
-
-/* Only Leaf-based devices can report M16C error factors,
- * thus define our own error status flags for USBCANII
- */
-#define USBCAN_ERROR_STATE_NONE		0
-#define USBCAN_ERROR_STATE_TX_ERROR	BIT(0)
-#define USBCAN_ERROR_STATE_RX_ERROR	BIT(1)
-#define USBCAN_ERROR_STATE_BUSERROR	BIT(2)
-
-/* bittiming parameters */
-#define KVASER_USB_TSEG1_MIN		1
-#define KVASER_USB_TSEG1_MAX		16
-#define KVASER_USB_TSEG2_MIN		1
-#define KVASER_USB_TSEG2_MAX		8
-#define KVASER_USB_SJW_MAX		4
-#define KVASER_USB_BRP_MIN		1
-#define KVASER_USB_BRP_MAX		64
-#define KVASER_USB_BRP_INC		1
-
-/* ctrl modes */
-#define KVASER_CTRL_MODE_NORMAL		1
-#define KVASER_CTRL_MODE_SILENT		2
-#define KVASER_CTRL_MODE_SELFRECEPTION	3
-#define KVASER_CTRL_MODE_OFF		4
-
-/* Extended CAN identifier flag */
-#define KVASER_EXTENDED_FRAME		BIT(31)
-
-/* Kvaser USB CAN dongles are divided into two major families:
- * - Leaf: Based on Renesas M32C, running firmware labeled as 'filo'
- * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios'
- */
-enum kvaser_usb_family {
-	KVASER_LEAF,
-	KVASER_USBCAN,
-};
-
-struct kvaser_cmd_simple {
-	u8 tid;
-	u8 channel;
-} __packed;
-
-struct kvaser_cmd_cardinfo {
-	u8 tid;
-	u8 nchannels;
-	union {
-		struct {
-			__le32 serial_number;
-			__le32 padding;
-		} __packed leaf0;
-		struct {
-			__le32 serial_number_low;
-			__le32 serial_number_high;
-		} __packed usbcan0;
-	} __packed;
-	__le32 clock_resolution;
-	__le32 mfgdate;
-	u8 ean[8];
-	u8 hw_revision;
-	union {
-		struct {
-			u8 usb_hs_mode;
-		} __packed leaf1;
-		struct {
-			u8 padding;
-		} __packed usbcan1;
-	} __packed;
-	__le16 padding;
-} __packed;
-
-struct leaf_cmd_softinfo {
-	u8 tid;
-	u8 padding0;
-	__le32 sw_options;
-	__le32 fw_version;
-	__le16 max_outstanding_tx;
-	__le16 padding1[9];
-} __packed;
-
-struct usbcan_cmd_softinfo {
-	u8 tid;
-	u8 fw_name[5];
-	__le16 max_outstanding_tx;
-	u8 padding[6];
-	__le32 fw_version;
-	__le16 checksum;
-	__le16 sw_options;
-} __packed;
-
-struct kvaser_cmd_busparams {
-	u8 tid;
-	u8 channel;
-	__le32 bitrate;
-	u8 tseg1;
-	u8 tseg2;
-	u8 sjw;
-	u8 no_samp;
-} __packed;
-
-struct kvaser_cmd_tx_can {
-	u8 channel;
-	u8 tid;
-	u8 data[14];
-	union {
-		struct {
-			u8 padding;
-			u8 flags;
-		} __packed leaf;
-		struct {
-			u8 flags;
-			u8 padding;
-		} __packed usbcan;
-	} __packed;
-} __packed;
-
-struct kvaser_cmd_rx_can_header {
-	u8 channel;
-	u8 flag;
-} __packed;
-
-struct leaf_cmd_rx_can {
-	u8 channel;
-	u8 flag;
-
-	__le16 time[3];
-	u8 data[14];
-} __packed;
-
-struct usbcan_cmd_rx_can {
-	u8 channel;
-	u8 flag;
-
-	u8 data[14];
-	__le16 time;
-} __packed;
-
-struct leaf_cmd_chip_state_event {
-	u8 tid;
-	u8 channel;
-
-	__le16 time[3];
-	u8 tx_errors_count;
-	u8 rx_errors_count;
-
-	u8 status;
-	u8 padding[3];
-} __packed;
-
-struct usbcan_cmd_chip_state_event {
-	u8 tid;
-	u8 channel;
-
-	u8 tx_errors_count;
-	u8 rx_errors_count;
-	__le16 time;
-
-	u8 status;
-	u8 padding[3];
-} __packed;
-
-struct kvaser_cmd_tx_acknowledge_header {
-	u8 channel;
-	u8 tid;
-} __packed;
-
-struct leaf_cmd_error_event {
-	u8 tid;
-	u8 flags;
-	__le16 time[3];
-	u8 channel;
-	u8 padding;
-	u8 tx_errors_count;
-	u8 rx_errors_count;
-	u8 status;
-	u8 error_factor;
-} __packed;
-
-struct usbcan_cmd_error_event {
-	u8 tid;
-	u8 padding;
-	u8 tx_errors_count_ch0;
-	u8 rx_errors_count_ch0;
-	u8 tx_errors_count_ch1;
-	u8 rx_errors_count_ch1;
-	u8 status_ch0;
-	u8 status_ch1;
-	__le16 time;
-} __packed;
-
-struct kvaser_cmd_ctrl_mode {
-	u8 tid;
-	u8 channel;
-	u8 ctrl_mode;
-	u8 padding[3];
-} __packed;
-
-struct kvaser_cmd_flush_queue {
-	u8 tid;
-	u8 channel;
-	u8 flags;
-	u8 padding[3];
-} __packed;
-
-struct leaf_cmd_log_message {
-	u8 channel;
-	u8 flags;
-	__le16 time[3];
-	u8 dlc;
-	u8 time_offset;
-	__le32 id;
-	u8 data[8];
-} __packed;
-
-struct kvaser_cmd {
-	u8 len;
-	u8 id;
-	union	{
-		struct kvaser_cmd_simple simple;
-		struct kvaser_cmd_cardinfo cardinfo;
-		struct kvaser_cmd_busparams busparams;
-
-		struct kvaser_cmd_rx_can_header rx_can_header;
-		struct kvaser_cmd_tx_acknowledge_header tx_acknowledge_header;
-
-		union {
-			struct leaf_cmd_softinfo softinfo;
-			struct leaf_cmd_rx_can rx_can;
-			struct leaf_cmd_chip_state_event chip_state_event;
-			struct leaf_cmd_error_event error_event;
-			struct leaf_cmd_log_message log_message;
-		} __packed leaf;
-
-		union {
-			struct usbcan_cmd_softinfo softinfo;
-			struct usbcan_cmd_rx_can rx_can;
-			struct usbcan_cmd_chip_state_event chip_state_event;
-			struct usbcan_cmd_error_event error_event;
-		} __packed usbcan;
-
-		struct kvaser_cmd_tx_can tx_can;
-		struct kvaser_cmd_ctrl_mode ctrl_mode;
-		struct kvaser_cmd_flush_queue flush_queue;
-	} u;
-} __packed;
-
-/* Summary of a kvaser error event, for a unified Leaf/Usbcan error
- * handling. Some discrepancies between the two families exist:
- *
- * - USBCAN firmware does not report M16C "error factors"
- * - USBCAN controllers has difficulties reporting if the raised error
- *   event is for ch0 or ch1. They leave such arbitration to the OS
- *   driver by letting it compare error counters with previous values
- *   and decide the error event's channel. Thus for USBCAN, the channel
- *   field is only advisory.
- */
-struct kvaser_usb_error_summary {
-	u8 channel, status, txerr, rxerr;
-	union {
-		struct {
-			u8 error_factor;
-		} leaf;
-		struct {
-			u8 other_ch_status;
-			u8 error_state;
-		} usbcan;
-	};
-};
-
-/* Context for an outstanding, not yet ACKed, transmission */
-struct kvaser_usb_tx_urb_context {
-	struct kvaser_usb_net_priv *priv;
-	u32 echo_index;
-	int dlc;
-};
-
-struct kvaser_usb {
-	struct usb_device *udev;
-	struct usb_interface *intf;
-	struct kvaser_usb_net_priv *nets[MAX_NET_DEVICES];
-
-	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
-	struct usb_anchor rx_submitted;
-
-	/* @max_tx_urbs: Firmware-reported maximum number of outstanding,
-	 * not yet ACKed, transmissions on this device. This value is
-	 * also used as a sentinel for marking free tx contexts.
-	 */
-	u32 fw_version;
-	unsigned int nchannels;
-	unsigned int max_tx_urbs;
-	enum kvaser_usb_family family;
-
-	bool rxinitdone;
-	void *rxbuf[MAX_RX_URBS];
-	dma_addr_t rxbuf_dma[MAX_RX_URBS];
-};
-
-struct kvaser_usb_net_priv {
-	struct can_priv can;
-	struct can_berr_counter bec;
-
-	struct kvaser_usb *dev;
-	struct net_device *netdev;
-	int channel;
-
-	struct completion start_comp, stop_comp;
-	struct usb_anchor tx_submitted;
-
-	spinlock_t tx_contexts_lock;
-	int active_tx_contexts;
-	struct kvaser_usb_tx_urb_context tx_contexts[];
-};
-
-static const struct usb_device_id kvaser_usb_table[] = {
-	/* Leaf family IDs */
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_SWC_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LIN_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_LS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_SWC_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_DEVEL_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSHS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_UPRO_HSHS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_OBDII_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS |
-			       KVASER_HAS_SILENT_MODE },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSLS_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_CH_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_SPRO_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_MERCURY_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_LEAF_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
-
-	/* USBCANII family IDs */
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-	{ USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID),
-		.driver_info = KVASER_HAS_TXRX_ERRORS },
-
-	{ }
-};
-MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
-
-static inline int kvaser_usb_send_cmd(const struct kvaser_usb *dev,
-				      struct kvaser_cmd *cmd)
-{
-	int actual_len;
-
-	return usb_bulk_msg(dev->udev,
-			    usb_sndbulkpipe(dev->udev,
-					dev->bulk_out->bEndpointAddress),
-			    cmd, cmd->len, &actual_len, KVASER_USB_TIMEOUT);
-}
-
-static int kvaser_usb_wait_cmd(const struct kvaser_usb *dev, u8 id,
-			       struct kvaser_cmd *cmd)
-{
-	struct kvaser_cmd *tmp;
-	void *buf;
-	int actual_len;
-	int err;
-	int pos;
-	unsigned long to = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT);
-
-	buf = kzalloc(RX_BUFFER_SIZE, GFP_KERNEL);
-	if (!buf)
-		return -ENOMEM;
-
-	do {
-		err = usb_bulk_msg(dev->udev,
-				   usb_rcvbulkpipe(dev->udev,
-					dev->bulk_in->bEndpointAddress),
-				   buf, RX_BUFFER_SIZE, &actual_len,
-				   KVASER_USB_TIMEOUT);
-		if (err < 0)
-			goto end;
-
-		pos = 0;
-		while (pos <= actual_len - CMD_HEADER_LEN) {
-			tmp = buf + pos;
-
-			/* Handle commands crossing the USB endpoint max packet
-			 * size boundary. Check kvaser_usb_read_bulk_callback()
-			 * for further details.
-			 */
-			if (tmp->len == 0) {
-				pos = round_up(pos, le16_to_cpu(dev->bulk_in->
-								wMaxPacketSize));
-				continue;
-			}
-
-			if (pos + tmp->len > actual_len) {
-				dev_err_ratelimited(&dev->intf->dev,
-						    "Format error\n");
-				break;
-			}
-
-			if (tmp->id == id) {
-				memcpy(cmd, tmp, tmp->len);
-				goto end;
-			}
-
-			pos += tmp->len;
-		}
-	} while (time_before(jiffies, to));
-
-	err = -EINVAL;
-
-end:
-	kfree(buf);
-
-	return err;
-}
-
-static int kvaser_usb_send_simple_cmd(const struct kvaser_usb *dev,
-				      u8 cmd_id, int channel)
-{
-	struct kvaser_cmd *cmd;
-	int rc;
-
-	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	cmd->id = cmd_id;
-	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
-	cmd->u.simple.channel = channel;
-	cmd->u.simple.tid = 0xff;
-
-	rc = kvaser_usb_send_cmd(dev, cmd);
-
-	kfree(cmd);
-	return rc;
-}
-
-static int kvaser_usb_get_software_info(struct kvaser_usb *dev)
-{
-	struct kvaser_cmd cmd;
-	int err;
-
-	err = kvaser_usb_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO, 0);
-	if (err)
-		return err;
-
-	err = kvaser_usb_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_REPLY, &cmd);
-	if (err)
-		return err;
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version);
-		dev->max_tx_urbs =
-			le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx);
-		break;
-	case KVASER_USBCAN:
-		dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
-		dev->max_tx_urbs =
-			le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
-		break;
-	}
-
-	return 0;
-}
-
-static int kvaser_usb_get_card_info(struct kvaser_usb *dev)
-{
-	struct kvaser_cmd cmd;
-	int err;
-
-	err = kvaser_usb_send_simple_cmd(dev, CMD_GET_CARD_INFO, 0);
-	if (err)
-		return err;
-
-	err = kvaser_usb_wait_cmd(dev, CMD_GET_CARD_INFO_REPLY, &cmd);
-	if (err)
-		return err;
-
-	dev->nchannels = cmd.u.cardinfo.nchannels;
-	if ((dev->nchannels > MAX_NET_DEVICES) ||
-	    (dev->family == KVASER_USBCAN &&
-	     dev->nchannels > MAX_USBCAN_NET_DEVICES))
-		return -EINVAL;
-
-	return 0;
-}
-
-static void kvaser_usb_tx_acknowledge(const struct kvaser_usb *dev,
-				      const struct kvaser_cmd *cmd)
-{
-	struct net_device_stats *stats;
-	struct kvaser_usb_tx_urb_context *context;
-	struct kvaser_usb_net_priv *priv;
-	struct sk_buff *skb;
-	struct can_frame *cf;
-	unsigned long flags;
-	u8 channel, tid;
-
-	channel = cmd->u.tx_acknowledge_header.channel;
-	tid = cmd->u.tx_acknowledge_header.tid;
-
-	if (channel >= dev->nchannels) {
-		dev_err(&dev->intf->dev,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-
-	if (!netif_device_present(priv->netdev))
-		return;
-
-	stats = &priv->netdev->stats;
-
-	context = &priv->tx_contexts[tid % dev->max_tx_urbs];
-
-	/* Sometimes the state change doesn't come after a bus-off event */
-	if (priv->can.restart_ms &&
-	    (priv->can.state >= CAN_STATE_BUS_OFF)) {
-		skb = alloc_can_err_skb(priv->netdev, &cf);
-		if (skb) {
-			cf->can_id |= CAN_ERR_RESTARTED;
-
-			stats->rx_packets++;
-			stats->rx_bytes += cf->can_dlc;
-			netif_rx(skb);
-		} else {
-			netdev_err(priv->netdev,
-				   "No memory left for err_skb\n");
-		}
-
-		priv->can.can_stats.restarts++;
-		netif_carrier_on(priv->netdev);
-
-		priv->can.state = CAN_STATE_ERROR_ACTIVE;
-	}
-
-	stats->tx_packets++;
-	stats->tx_bytes += context->dlc;
-
-	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
-
-	can_get_echo_skb(priv->netdev, context->echo_index);
-	context->echo_index = dev->max_tx_urbs;
-	--priv->active_tx_contexts;
-	netif_wake_queue(priv->netdev);
-
-	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
-}
-
-static void kvaser_usb_simple_cmd_callback(struct urb *urb)
-{
-	struct net_device *netdev = urb->context;
-
-	kfree(urb->transfer_buffer);
-
-	if (urb->status)
-		netdev_warn(netdev, "urb status received: %d\n",
-			    urb->status);
-}
-
-static int kvaser_usb_simple_cmd_async(struct kvaser_usb_net_priv *priv,
-				       u8 cmd_id)
-{
-	struct kvaser_usb *dev = priv->dev;
-	struct net_device *netdev = priv->netdev;
-	struct kvaser_cmd *cmd;
-	struct urb *urb;
-	void *buf;
-	int err;
-
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!urb)
-		return -ENOMEM;
-
-	buf = kmalloc(sizeof(struct kvaser_cmd), GFP_ATOMIC);
-	if (!buf) {
-		usb_free_urb(urb);
-		return -ENOMEM;
-	}
-
-	cmd = (struct kvaser_cmd *)buf;
-	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
-	cmd->id = cmd_id;
-	cmd->u.simple.channel = priv->channel;
-
-	usb_fill_bulk_urb(urb, dev->udev,
-			  usb_sndbulkpipe(dev->udev,
-					  dev->bulk_out->bEndpointAddress),
-			  buf, cmd->len,
-			  kvaser_usb_simple_cmd_callback, netdev);
-	usb_anchor_urb(urb, &priv->tx_submitted);
-
-	err = usb_submit_urb(urb, GFP_ATOMIC);
-	if (err) {
-		netdev_err(netdev, "Error transmitting URB\n");
-		usb_unanchor_urb(urb);
-		kfree(buf);
-		usb_free_urb(urb);
-		return err;
-	}
-
-	usb_free_urb(urb);
-
-	return 0;
-}
-
-static void kvaser_usb_rx_error_update_can_state(struct kvaser_usb_net_priv *priv,
-						 const struct kvaser_usb_error_summary *es,
-						 struct can_frame *cf)
-{
-	struct kvaser_usb *dev = priv->dev;
-	struct net_device_stats *stats = &priv->netdev->stats;
-	enum can_state cur_state, new_state, tx_state, rx_state;
-
-	netdev_dbg(priv->netdev, "Error status: 0x%02x\n", es->status);
-
-	new_state = cur_state = priv->can.state;
-
-	if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET))
-		new_state = CAN_STATE_BUS_OFF;
-	else if (es->status & M16C_STATE_BUS_PASSIVE)
-		new_state = CAN_STATE_ERROR_PASSIVE;
-	else if (es->status & M16C_STATE_BUS_ERROR) {
-		/* Guard against spurious error events after a busoff */
-		if (cur_state < CAN_STATE_BUS_OFF) {
-			if ((es->txerr >= 128) || (es->rxerr >= 128))
-				new_state = CAN_STATE_ERROR_PASSIVE;
-			else if ((es->txerr >= 96) || (es->rxerr >= 96))
-				new_state = CAN_STATE_ERROR_WARNING;
-			else if (cur_state > CAN_STATE_ERROR_ACTIVE)
-				new_state = CAN_STATE_ERROR_ACTIVE;
-		}
-	}
-
-	if (!es->status)
-		new_state = CAN_STATE_ERROR_ACTIVE;
-
-	if (new_state != cur_state) {
-		tx_state = (es->txerr >= es->rxerr) ? new_state : 0;
-		rx_state = (es->txerr <= es->rxerr) ? new_state : 0;
-
-		can_change_state(priv->netdev, cf, tx_state, rx_state);
-	}
-
-	if (priv->can.restart_ms &&
-	    (cur_state >= CAN_STATE_BUS_OFF) &&
-	    (new_state < CAN_STATE_BUS_OFF)) {
-		priv->can.can_stats.restarts++;
-	}
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		if (es->leaf.error_factor) {
-			priv->can.can_stats.bus_error++;
-			stats->rx_errors++;
-		}
-		break;
-	case KVASER_USBCAN:
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_TX_ERROR)
-			stats->tx_errors++;
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_RX_ERROR)
-			stats->rx_errors++;
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) {
-			priv->can.can_stats.bus_error++;
-		}
-		break;
-	}
-
-	priv->bec.txerr = es->txerr;
-	priv->bec.rxerr = es->rxerr;
-}
-
-static void kvaser_usb_rx_error(const struct kvaser_usb *dev,
-				const struct kvaser_usb_error_summary *es)
-{
-	struct can_frame *cf, tmp_cf = { .can_id = CAN_ERR_FLAG, .can_dlc = CAN_ERR_DLC };
-	struct sk_buff *skb;
-	struct net_device_stats *stats;
-	struct kvaser_usb_net_priv *priv;
-	enum can_state old_state, new_state;
-
-	if (es->channel >= dev->nchannels) {
-		dev_err(&dev->intf->dev,
-			"Invalid channel number (%d)\n", es->channel);
-		return;
-	}
-
-	priv = dev->nets[es->channel];
-	stats = &priv->netdev->stats;
-
-	/* Update all of the CAN interface's state and error counters before
-	 * trying any memory allocation that can actually fail with -ENOMEM.
-	 *
-	 * We send a temporary stack-allocated error CAN frame to
-	 * can_change_state() for the very same reason.
-	 *
-	 * TODO: Split can_change_state() responsibility between updating the
-	 * CAN interface's state and counters, and the setting up of CAN error
-	 * frame ID and data to userspace. Remove stack allocation afterwards.
-	 */
-	old_state = priv->can.state;
-	kvaser_usb_rx_error_update_can_state(priv, es, &tmp_cf);
-	new_state = priv->can.state;
-
-	skb = alloc_can_err_skb(priv->netdev, &cf);
-	if (!skb) {
-		stats->rx_dropped++;
-		return;
-	}
-	memcpy(cf, &tmp_cf, sizeof(*cf));
-
-	if (new_state != old_state) {
-		if (es->status &
-		    (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
-			if (!priv->can.restart_ms)
-				kvaser_usb_simple_cmd_async(priv, CMD_STOP_CHIP);
-			netif_carrier_off(priv->netdev);
-		}
-
-		if (priv->can.restart_ms &&
-		    (old_state >= CAN_STATE_BUS_OFF) &&
-		    (new_state < CAN_STATE_BUS_OFF)) {
-			cf->can_id |= CAN_ERR_RESTARTED;
-			netif_carrier_on(priv->netdev);
-		}
-	}
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		if (es->leaf.error_factor) {
-			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
-
-			if (es->leaf.error_factor & M16C_EF_ACKE)
-				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
-			if (es->leaf.error_factor & M16C_EF_CRCE)
-				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
-			if (es->leaf.error_factor & M16C_EF_FORME)
-				cf->data[2] |= CAN_ERR_PROT_FORM;
-			if (es->leaf.error_factor & M16C_EF_STFE)
-				cf->data[2] |= CAN_ERR_PROT_STUFF;
-			if (es->leaf.error_factor & M16C_EF_BITE0)
-				cf->data[2] |= CAN_ERR_PROT_BIT0;
-			if (es->leaf.error_factor & M16C_EF_BITE1)
-				cf->data[2] |= CAN_ERR_PROT_BIT1;
-			if (es->leaf.error_factor & M16C_EF_TRE)
-				cf->data[2] |= CAN_ERR_PROT_TX;
-		}
-		break;
-	case KVASER_USBCAN:
-		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR) {
-			cf->can_id |= CAN_ERR_BUSERROR;
-		}
-		break;
-	}
-
-	cf->data[6] = es->txerr;
-	cf->data[7] = es->rxerr;
-
-	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
-	netif_rx(skb);
-}
-
-/* For USBCAN, report error to userspace if the channels's errors counter
- * has changed, or we're the only channel seeing a bus error state.
- */
-static void kvaser_usbcan_conditionally_rx_error(const struct kvaser_usb *dev,
-						 struct kvaser_usb_error_summary *es)
-{
-	struct kvaser_usb_net_priv *priv;
-	int channel;
-	bool report_error;
-
-	channel = es->channel;
-	if (channel >= dev->nchannels) {
-		dev_err(&dev->intf->dev,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-	report_error = false;
-
-	if (es->txerr != priv->bec.txerr) {
-		es->usbcan.error_state |= USBCAN_ERROR_STATE_TX_ERROR;
-		report_error = true;
-	}
-	if (es->rxerr != priv->bec.rxerr) {
-		es->usbcan.error_state |= USBCAN_ERROR_STATE_RX_ERROR;
-		report_error = true;
-	}
-	if ((es->status & M16C_STATE_BUS_ERROR) &&
-	    !(es->usbcan.other_ch_status & M16C_STATE_BUS_ERROR)) {
-		es->usbcan.error_state |= USBCAN_ERROR_STATE_BUSERROR;
-		report_error = true;
-	}
-
-	if (report_error)
-		kvaser_usb_rx_error(dev, es);
-}
-
-static void kvaser_usbcan_rx_error(const struct kvaser_usb *dev,
-				   const struct kvaser_cmd *cmd)
-{
-	struct kvaser_usb_error_summary es = { };
-
-	switch (cmd->id) {
-	/* Sometimes errors are sent as unsolicited chip state events */
-	case CMD_CHIP_STATE_EVENT:
-		es.channel = cmd->u.usbcan.chip_state_event.channel;
-		es.status =  cmd->u.usbcan.chip_state_event.status;
-		es.txerr = cmd->u.usbcan.chip_state_event.tx_errors_count;
-		es.rxerr = cmd->u.usbcan.chip_state_event.rx_errors_count;
-		kvaser_usbcan_conditionally_rx_error(dev, &es);
-		break;
-
-	case CMD_CAN_ERROR_EVENT:
-		es.channel = 0;
-		es.status = cmd->u.usbcan.error_event.status_ch0;
-		es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch0;
-		es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch0;
-		es.usbcan.other_ch_status =
-			cmd->u.usbcan.error_event.status_ch1;
-		kvaser_usbcan_conditionally_rx_error(dev, &es);
-
-		/* The USBCAN firmware supports up to 2 channels.
-		 * Now that ch0 was checked, check if ch1 has any errors.
-		 */
-		if (dev->nchannels == MAX_USBCAN_NET_DEVICES) {
-			es.channel = 1;
-			es.status = cmd->u.usbcan.error_event.status_ch1;
-			es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch1;
-			es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch1;
-			es.usbcan.other_ch_status =
-				cmd->u.usbcan.error_event.status_ch0;
-			kvaser_usbcan_conditionally_rx_error(dev, &es);
-		}
-		break;
-
-	default:
-		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
-	}
-}
-
-static void kvaser_leaf_rx_error(const struct kvaser_usb *dev,
-				 const struct kvaser_cmd *cmd)
-{
-	struct kvaser_usb_error_summary es = { };
-
-	switch (cmd->id) {
-	case CMD_CAN_ERROR_EVENT:
-		es.channel = cmd->u.leaf.error_event.channel;
-		es.status =  cmd->u.leaf.error_event.status;
-		es.txerr = cmd->u.leaf.error_event.tx_errors_count;
-		es.rxerr = cmd->u.leaf.error_event.rx_errors_count;
-		es.leaf.error_factor = cmd->u.leaf.error_event.error_factor;
-		break;
-	case CMD_LEAF_LOG_MESSAGE:
-		es.channel = cmd->u.leaf.log_message.channel;
-		es.status = cmd->u.leaf.log_message.data[0];
-		es.txerr = cmd->u.leaf.log_message.data[2];
-		es.rxerr = cmd->u.leaf.log_message.data[3];
-		es.leaf.error_factor = cmd->u.leaf.log_message.data[1];
-		break;
-	case CMD_CHIP_STATE_EVENT:
-		es.channel = cmd->u.leaf.chip_state_event.channel;
-		es.status =  cmd->u.leaf.chip_state_event.status;
-		es.txerr = cmd->u.leaf.chip_state_event.tx_errors_count;
-		es.rxerr = cmd->u.leaf.chip_state_event.rx_errors_count;
-		es.leaf.error_factor = 0;
-		break;
-	default:
-		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
-		return;
-	}
-
-	kvaser_usb_rx_error(dev, &es);
-}
-
-static void kvaser_usb_rx_can_err(const struct kvaser_usb_net_priv *priv,
-				  const struct kvaser_cmd *cmd)
-{
-	struct can_frame *cf;
-	struct sk_buff *skb;
-	struct net_device_stats *stats = &priv->netdev->stats;
-
-	if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
-					 MSG_FLAG_NERR)) {
-		netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n",
-			   cmd->u.rx_can_header.flag);
-
-		stats->rx_errors++;
-		return;
-	}
-
-	if (cmd->u.rx_can_header.flag & MSG_FLAG_OVERRUN) {
-		stats->rx_over_errors++;
-		stats->rx_errors++;
-
-		skb = alloc_can_err_skb(priv->netdev, &cf);
-		if (!skb) {
-			stats->rx_dropped++;
-			return;
-		}
-
-		cf->can_id |= CAN_ERR_CRTL;
-		cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
-
-		stats->rx_packets++;
-		stats->rx_bytes += cf->can_dlc;
-		netif_rx(skb);
-	}
-}
-
-static void kvaser_usb_rx_can_msg(const struct kvaser_usb *dev,
-				  const struct kvaser_cmd *cmd)
-{
-	struct kvaser_usb_net_priv *priv;
-	struct can_frame *cf;
-	struct sk_buff *skb;
-	struct net_device_stats *stats;
-	u8 channel = cmd->u.rx_can_header.channel;
-	const u8 *rx_data = NULL;	/* GCC */
-
-	if (channel >= dev->nchannels) {
-		dev_err(&dev->intf->dev,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-	stats = &priv->netdev->stats;
-
-	if ((cmd->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) &&
-	    (dev->family == KVASER_LEAF && cmd->id == CMD_LEAF_LOG_MESSAGE)) {
-		kvaser_leaf_rx_error(dev, cmd);
-		return;
-	} else if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
-						MSG_FLAG_NERR |
-						MSG_FLAG_OVERRUN)) {
-		kvaser_usb_rx_can_err(priv, cmd);
-		return;
-	} else if (cmd->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) {
-		netdev_warn(priv->netdev,
-			    "Unhandled frame (flags: 0x%02x)",
-			    cmd->u.rx_can_header.flag);
-		return;
-	}
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		rx_data = cmd->u.leaf.rx_can.data;
-		break;
-	case KVASER_USBCAN:
-		rx_data = cmd->u.usbcan.rx_can.data;
-		break;
-	}
-
-	skb = alloc_can_skb(priv->netdev, &cf);
-	if (!skb) {
-		stats->rx_dropped++;
-		return;
-	}
-
-	if (dev->family == KVASER_LEAF && cmd->id == CMD_LEAF_LOG_MESSAGE) {
-		cf->can_id = le32_to_cpu(cmd->u.leaf.log_message.id);
-		if (cf->can_id & KVASER_EXTENDED_FRAME)
-			cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG;
-		else
-			cf->can_id &= CAN_SFF_MASK;
-
-		cf->can_dlc = get_can_dlc(cmd->u.leaf.log_message.dlc);
-
-		if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
-			cf->can_id |= CAN_RTR_FLAG;
-		else
-			memcpy(cf->data, &cmd->u.leaf.log_message.data,
-			       cf->can_dlc);
-	} else {
-		cf->can_id = ((rx_data[0] & 0x1f) << 6) | (rx_data[1] & 0x3f);
-
-		if (cmd->id == CMD_RX_EXT_MESSAGE) {
-			cf->can_id <<= 18;
-			cf->can_id |= ((rx_data[2] & 0x0f) << 14) |
-				      ((rx_data[3] & 0xff) << 6) |
-				      (rx_data[4] & 0x3f);
-			cf->can_id |= CAN_EFF_FLAG;
-		}
-
-		cf->can_dlc = get_can_dlc(rx_data[5]);
-
-		if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
-			cf->can_id |= CAN_RTR_FLAG;
-		else
-			memcpy(cf->data, &rx_data[6], cf->can_dlc);
-	}
-
-	stats->rx_packets++;
-	stats->rx_bytes += cf->can_dlc;
-	netif_rx(skb);
-}
-
-static void kvaser_usb_start_chip_reply(const struct kvaser_usb *dev,
-					const struct kvaser_cmd *cmd)
-{
-	struct kvaser_usb_net_priv *priv;
-	u8 channel = cmd->u.simple.channel;
-
-	if (channel >= dev->nchannels) {
-		dev_err(&dev->intf->dev,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-
-	if (completion_done(&priv->start_comp) &&
-	    netif_queue_stopped(priv->netdev)) {
-		netif_wake_queue(priv->netdev);
-	} else {
-		netif_start_queue(priv->netdev);
-		complete(&priv->start_comp);
-	}
-}
-
-static void kvaser_usb_stop_chip_reply(const struct kvaser_usb *dev,
-				       const struct kvaser_cmd *cmd)
-{
-	struct kvaser_usb_net_priv *priv;
-	u8 channel = cmd->u.simple.channel;
-
-	if (channel >= dev->nchannels) {
-		dev_err(&dev->intf->dev,
-			"Invalid channel number (%d)\n", channel);
-		return;
-	}
-
-	priv = dev->nets[channel];
-
-	complete(&priv->stop_comp);
-}
-
-static void kvaser_usb_handle_cmd(const struct kvaser_usb *dev,
-				  const struct kvaser_cmd *cmd)
-{
-	switch (cmd->id) {
-	case CMD_START_CHIP_REPLY:
-		kvaser_usb_start_chip_reply(dev, cmd);
-		break;
-
-	case CMD_STOP_CHIP_REPLY:
-		kvaser_usb_stop_chip_reply(dev, cmd);
-		break;
-
-	case CMD_RX_STD_MESSAGE:
-	case CMD_RX_EXT_MESSAGE:
-		kvaser_usb_rx_can_msg(dev, cmd);
-		break;
-
-	case CMD_LEAF_LOG_MESSAGE:
-		if (dev->family != KVASER_LEAF)
-			goto warn;
-		kvaser_usb_rx_can_msg(dev, cmd);
-		break;
-
-	case CMD_CHIP_STATE_EVENT:
-	case CMD_CAN_ERROR_EVENT:
-		if (dev->family == KVASER_LEAF)
-			kvaser_leaf_rx_error(dev, cmd);
-		else
-			kvaser_usbcan_rx_error(dev, cmd);
-		break;
-
-	case CMD_TX_ACKNOWLEDGE:
-		kvaser_usb_tx_acknowledge(dev, cmd);
-		break;
-
-	/* Ignored commands */
-	case CMD_USBCAN_CLOCK_OVERFLOW_EVENT:
-		if (dev->family != KVASER_USBCAN)
-			goto warn;
-		break;
-
-	case CMD_FLUSH_QUEUE_REPLY:
-		if (dev->family != KVASER_LEAF)
-			goto warn;
-		break;
-
-	default:
-warn:		dev_warn(&dev->intf->dev, "Unhandled command (%d)\n", cmd->id);
-		break;
-	}
-}
-
-static void kvaser_usb_read_bulk_callback(struct urb *urb)
-{
-	struct kvaser_usb *dev = urb->context;
-	struct kvaser_cmd *cmd;
-	int pos = 0;
-	int err, i;
-
-	switch (urb->status) {
-	case 0:
-		break;
-	case -ENOENT:
-	case -EPIPE:
-	case -EPROTO:
-	case -ESHUTDOWN:
-		return;
-	default:
-		dev_info(&dev->intf->dev, "Rx URB aborted (%d)\n", urb->status);
-		goto resubmit_urb;
-	}
-
-	while (pos <= (int)(urb->actual_length - CMD_HEADER_LEN)) {
-		cmd = urb->transfer_buffer + pos;
-
-		/* The Kvaser firmware can only read and write commands that
-		 * does not cross the USB's endpoint wMaxPacketSize boundary.
-		 * If a follow-up command crosses such boundary, firmware puts
-		 * a placeholder zero-length command in its place then aligns
-		 * the real command to the next max packet size.
-		 *
-		 * Handle such cases or we're going to miss a significant
-		 * number of events in case of a heavy rx load on the bus.
-		 */
-		if (cmd->len == 0) {
-			pos = round_up(pos, le16_to_cpu(dev->bulk_in->
-							wMaxPacketSize));
-			continue;
-		}
-
-		if (pos + cmd->len > urb->actual_length) {
-			dev_err_ratelimited(&dev->intf->dev, "Format error\n");
-			break;
-		}
-
-		kvaser_usb_handle_cmd(dev, cmd);
-		pos += cmd->len;
-	}
-
-resubmit_urb:
-	usb_fill_bulk_urb(urb, dev->udev,
-			  usb_rcvbulkpipe(dev->udev,
-					  dev->bulk_in->bEndpointAddress),
-			  urb->transfer_buffer, RX_BUFFER_SIZE,
-			  kvaser_usb_read_bulk_callback, dev);
-
-	err = usb_submit_urb(urb, GFP_ATOMIC);
-	if (err == -ENODEV) {
-		for (i = 0; i < dev->nchannels; i++) {
-			if (!dev->nets[i])
-				continue;
-
-			netif_device_detach(dev->nets[i]->netdev);
-		}
-	} else if (err) {
-		dev_err(&dev->intf->dev,
-			"Failed resubmitting read bulk urb: %d\n", err);
-	}
-}
-
-static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
-{
-	int i, err = 0;
-
-	if (dev->rxinitdone)
-		return 0;
-
-	for (i = 0; i < MAX_RX_URBS; i++) {
-		struct urb *urb = NULL;
-		u8 *buf = NULL;
-		dma_addr_t buf_dma;
-
-		urb = usb_alloc_urb(0, GFP_KERNEL);
-		if (!urb) {
-			err = -ENOMEM;
-			break;
-		}
-
-		buf = usb_alloc_coherent(dev->udev, RX_BUFFER_SIZE,
-					 GFP_KERNEL, &buf_dma);
-		if (!buf) {
-			dev_warn(&dev->intf->dev,
-				 "No memory left for USB buffer\n");
-			usb_free_urb(urb);
-			err = -ENOMEM;
-			break;
-		}
-
-		usb_fill_bulk_urb(urb, dev->udev,
-				  usb_rcvbulkpipe(dev->udev,
-					  dev->bulk_in->bEndpointAddress),
-				  buf, RX_BUFFER_SIZE,
-				  kvaser_usb_read_bulk_callback,
-				  dev);
-		urb->transfer_dma = buf_dma;
-		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
-		usb_anchor_urb(urb, &dev->rx_submitted);
-
-		err = usb_submit_urb(urb, GFP_KERNEL);
-		if (err) {
-			usb_unanchor_urb(urb);
-			usb_free_coherent(dev->udev, RX_BUFFER_SIZE, buf,
-					  buf_dma);
-			usb_free_urb(urb);
-			break;
-		}
-
-		dev->rxbuf[i] = buf;
-		dev->rxbuf_dma[i] = buf_dma;
-
-		usb_free_urb(urb);
-	}
-
-	if (i == 0) {
-		dev_warn(&dev->intf->dev, "Cannot setup read URBs, error %d\n",
-			 err);
-		return err;
-	} else if (i < MAX_RX_URBS) {
-		dev_warn(&dev->intf->dev, "RX performances may be slow\n");
-	}
-
-	dev->rxinitdone = true;
-
-	return 0;
-}
-
-static int kvaser_usb_set_opt_mode(const struct kvaser_usb_net_priv *priv)
-{
-	struct kvaser_cmd *cmd;
-	int rc;
-
-	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	cmd->id = CMD_SET_CTRL_MODE;
-	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_ctrl_mode);
-	cmd->u.ctrl_mode.tid = 0xff;
-	cmd->u.ctrl_mode.channel = priv->channel;
-
-	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
-		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT;
-	else
-		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL;
-
-	rc = kvaser_usb_send_cmd(priv->dev, cmd);
-
-	kfree(cmd);
-	return rc;
-}
-
-static int kvaser_usb_start_chip(struct kvaser_usb_net_priv *priv)
-{
-	int err;
-
-	init_completion(&priv->start_comp);
-
-	err = kvaser_usb_send_simple_cmd(priv->dev, CMD_START_CHIP,
-					 priv->channel);
-	if (err)
-		return err;
-
-	if (!wait_for_completion_timeout(&priv->start_comp,
-					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int kvaser_usb_open(struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct kvaser_usb *dev = priv->dev;
-	int err;
-
-	err = open_candev(netdev);
-	if (err)
-		return err;
-
-	err = kvaser_usb_setup_rx_urbs(dev);
-	if (err)
-		goto error;
-
-	err = kvaser_usb_set_opt_mode(priv);
-	if (err)
-		goto error;
-
-	err = kvaser_usb_start_chip(priv);
-	if (err) {
-		netdev_warn(netdev, "Cannot start device, error %d\n", err);
-		goto error;
-	}
-
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
-
-	return 0;
-
-error:
-	close_candev(netdev);
-	return err;
-}
-
-static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv)
-{
-	int i, max_tx_urbs;
-
-	max_tx_urbs = priv->dev->max_tx_urbs;
-
-	priv->active_tx_contexts = 0;
-	for (i = 0; i < max_tx_urbs; i++)
-		priv->tx_contexts[i].echo_index = max_tx_urbs;
-}
-
-/* This method might sleep. Do not call it in the atomic context
- * of URB completions.
- */
-static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv)
-{
-	usb_kill_anchored_urbs(&priv->tx_submitted);
-	kvaser_usb_reset_tx_urb_contexts(priv);
-}
-
-static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev)
-{
-	int i;
-
-	usb_kill_anchored_urbs(&dev->rx_submitted);
-
-	for (i = 0; i < MAX_RX_URBS; i++)
-		usb_free_coherent(dev->udev, RX_BUFFER_SIZE,
-				  dev->rxbuf[i],
-				  dev->rxbuf_dma[i]);
-
-	for (i = 0; i < dev->nchannels; i++) {
-		struct kvaser_usb_net_priv *priv = dev->nets[i];
-
-		if (priv)
-			kvaser_usb_unlink_tx_urbs(priv);
-	}
-}
-
-static int kvaser_usb_stop_chip(struct kvaser_usb_net_priv *priv)
-{
-	int err;
-
-	init_completion(&priv->stop_comp);
-
-	err = kvaser_usb_send_simple_cmd(priv->dev, CMD_STOP_CHIP,
-					 priv->channel);
-	if (err)
-		return err;
-
-	if (!wait_for_completion_timeout(&priv->stop_comp,
-					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
-		return -ETIMEDOUT;
-
-	return 0;
-}
-
-static int kvaser_usb_flush_queue(struct kvaser_usb_net_priv *priv)
-{
-	struct kvaser_cmd *cmd;
-	int rc;
-
-	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	cmd->id = CMD_FLUSH_QUEUE;
-	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_flush_queue);
-	cmd->u.flush_queue.channel = priv->channel;
-	cmd->u.flush_queue.flags = 0x00;
-
-	rc = kvaser_usb_send_cmd(priv->dev, cmd);
-
-	kfree(cmd);
-	return rc;
-}
-
-static int kvaser_usb_close(struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct kvaser_usb *dev = priv->dev;
-	int err;
-
-	netif_stop_queue(netdev);
-
-	err = kvaser_usb_flush_queue(priv);
-	if (err)
-		netdev_warn(netdev, "Cannot flush queue, error %d\n", err);
-
-	err = kvaser_usb_send_simple_cmd(dev, CMD_RESET_CHIP, priv->channel);
-	if (err)
-		netdev_warn(netdev, "Cannot reset card, error %d\n", err);
-
-	err = kvaser_usb_stop_chip(priv);
-	if (err)
-		netdev_warn(netdev, "Cannot stop device, error %d\n", err);
-
-	/* reset tx contexts */
-	kvaser_usb_unlink_tx_urbs(priv);
-
-	priv->can.state = CAN_STATE_STOPPED;
-	close_candev(priv->netdev);
-
-	return 0;
-}
-
-static void kvaser_usb_write_bulk_callback(struct urb *urb)
-{
-	struct kvaser_usb_tx_urb_context *context = urb->context;
-	struct kvaser_usb_net_priv *priv;
-	struct net_device *netdev;
-
-	if (WARN_ON(!context))
-		return;
-
-	priv = context->priv;
-	netdev = priv->netdev;
-
-	kfree(urb->transfer_buffer);
-
-	if (!netif_device_present(netdev))
-		return;
-
-	if (urb->status)
-		netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status);
-}
-
-static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
-					 struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct kvaser_usb *dev = priv->dev;
-	struct net_device_stats *stats = &netdev->stats;
-	struct can_frame *cf = (struct can_frame *)skb->data;
-	struct kvaser_usb_tx_urb_context *context = NULL;
-	struct urb *urb;
-	void *buf;
-	struct kvaser_cmd *cmd;
-	int i, err, ret = NETDEV_TX_OK;
-	u8 *cmd_tx_can_flags = NULL;		/* GCC */
-	unsigned long flags;
-
-	if (can_dropped_invalid_skb(netdev, skb))
-		return NETDEV_TX_OK;
-
-	urb = usb_alloc_urb(0, GFP_ATOMIC);
-	if (!urb) {
-		stats->tx_dropped++;
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-
-	buf = kmalloc(sizeof(struct kvaser_cmd), GFP_ATOMIC);
-	if (!buf) {
-		stats->tx_dropped++;
-		dev_kfree_skb(skb);
-		goto freeurb;
-	}
-
-	cmd = buf;
-	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_tx_can);
-	cmd->u.tx_can.channel = priv->channel;
-
-	switch (dev->family) {
-	case KVASER_LEAF:
-		cmd_tx_can_flags = &cmd->u.tx_can.leaf.flags;
-		break;
-	case KVASER_USBCAN:
-		cmd_tx_can_flags = &cmd->u.tx_can.usbcan.flags;
-		break;
-	}
-
-	*cmd_tx_can_flags = 0;
-
-	if (cf->can_id & CAN_EFF_FLAG) {
-		cmd->id = CMD_TX_EXT_MESSAGE;
-		cmd->u.tx_can.data[0] = (cf->can_id >> 24) & 0x1f;
-		cmd->u.tx_can.data[1] = (cf->can_id >> 18) & 0x3f;
-		cmd->u.tx_can.data[2] = (cf->can_id >> 14) & 0x0f;
-		cmd->u.tx_can.data[3] = (cf->can_id >> 6) & 0xff;
-		cmd->u.tx_can.data[4] = cf->can_id & 0x3f;
-	} else {
-		cmd->id = CMD_TX_STD_MESSAGE;
-		cmd->u.tx_can.data[0] = (cf->can_id >> 6) & 0x1f;
-		cmd->u.tx_can.data[1] = cf->can_id & 0x3f;
-	}
-
-	cmd->u.tx_can.data[5] = cf->can_dlc;
-	memcpy(&cmd->u.tx_can.data[6], cf->data, cf->can_dlc);
-
-	if (cf->can_id & CAN_RTR_FLAG)
-		*cmd_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
-
-	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
-	for (i = 0; i < dev->max_tx_urbs; i++) {
-		if (priv->tx_contexts[i].echo_index == dev->max_tx_urbs) {
-			context = &priv->tx_contexts[i];
-
-			context->echo_index = i;
-			can_put_echo_skb(skb, netdev, context->echo_index);
-			++priv->active_tx_contexts;
-			if (priv->active_tx_contexts >= dev->max_tx_urbs)
-				netif_stop_queue(netdev);
-
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
-
-	/* This should never happen; it implies a flow control bug */
-	if (!context) {
-		netdev_warn(netdev, "cannot find free context\n");
-
-		kfree(buf);
-		ret =  NETDEV_TX_BUSY;
-		goto freeurb;
-	}
-
-	context->priv = priv;
-	context->dlc = cf->can_dlc;
-
-	cmd->u.tx_can.tid = context->echo_index;
-
-	usb_fill_bulk_urb(urb, dev->udev,
-			  usb_sndbulkpipe(dev->udev,
-					  dev->bulk_out->bEndpointAddress),
-			  buf, cmd->len,
-			  kvaser_usb_write_bulk_callback, context);
-	usb_anchor_urb(urb, &priv->tx_submitted);
-
-	err = usb_submit_urb(urb, GFP_ATOMIC);
-	if (unlikely(err)) {
-		spin_lock_irqsave(&priv->tx_contexts_lock, flags);
-
-		can_free_echo_skb(netdev, context->echo_index);
-		context->echo_index = dev->max_tx_urbs;
-		--priv->active_tx_contexts;
-		netif_wake_queue(netdev);
-
-		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
-
-		usb_unanchor_urb(urb);
-		kfree(buf);
-
-		stats->tx_dropped++;
-
-		if (err == -ENODEV)
-			netif_device_detach(netdev);
-		else
-			netdev_warn(netdev, "Failed tx_urb %d\n", err);
-
-		goto freeurb;
-	}
-
-	ret = NETDEV_TX_OK;
-
-freeurb:
-	usb_free_urb(urb);
-	return ret;
-}
-
-static const struct net_device_ops kvaser_usb_netdev_ops = {
-	.ndo_open = kvaser_usb_open,
-	.ndo_stop = kvaser_usb_close,
-	.ndo_start_xmit = kvaser_usb_start_xmit,
-	.ndo_change_mtu = can_change_mtu,
-};
-
-static const struct can_bittiming_const kvaser_usb_bittiming_const = {
-	.name = "kvaser_usb",
-	.tseg1_min = KVASER_USB_TSEG1_MIN,
-	.tseg1_max = KVASER_USB_TSEG1_MAX,
-	.tseg2_min = KVASER_USB_TSEG2_MIN,
-	.tseg2_max = KVASER_USB_TSEG2_MAX,
-	.sjw_max = KVASER_USB_SJW_MAX,
-	.brp_min = KVASER_USB_BRP_MIN,
-	.brp_max = KVASER_USB_BRP_MAX,
-	.brp_inc = KVASER_USB_BRP_INC,
-};
-
-static int kvaser_usb_set_bittiming(struct net_device *netdev)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	struct can_bittiming *bt = &priv->can.bittiming;
-	struct kvaser_usb *dev = priv->dev;
-	struct kvaser_cmd *cmd;
-	int rc;
-
-	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
-	if (!cmd)
-		return -ENOMEM;
-
-	cmd->id = CMD_SET_BUS_PARAMS;
-	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_busparams);
-	cmd->u.busparams.channel = priv->channel;
-	cmd->u.busparams.tid = 0xff;
-	cmd->u.busparams.bitrate = cpu_to_le32(bt->bitrate);
-	cmd->u.busparams.sjw = bt->sjw;
-	cmd->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1;
-	cmd->u.busparams.tseg2 = bt->phase_seg2;
-
-	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
-		cmd->u.busparams.no_samp = 3;
-	else
-		cmd->u.busparams.no_samp = 1;
-
-	rc = kvaser_usb_send_cmd(dev, cmd);
-
-	kfree(cmd);
-	return rc;
-}
-
-static int kvaser_usb_set_mode(struct net_device *netdev,
-			       enum can_mode mode)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-	int err;
-
-	switch (mode) {
-	case CAN_MODE_START:
-		err = kvaser_usb_simple_cmd_async(priv, CMD_START_CHIP);
-		if (err)
-			return err;
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	return 0;
-}
-
-static int kvaser_usb_get_berr_counter(const struct net_device *netdev,
-				       struct can_berr_counter *bec)
-{
-	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
-
-	*bec = priv->bec;
-
-	return 0;
-}
-
-static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev)
-{
-	int i;
-
-	for (i = 0; i < dev->nchannels; i++) {
-		if (!dev->nets[i])
-			continue;
-
-		unregister_candev(dev->nets[i]->netdev);
-	}
-
-	kvaser_usb_unlink_all_urbs(dev);
-
-	for (i = 0; i < dev->nchannels; i++) {
-		if (!dev->nets[i])
-			continue;
-
-		free_candev(dev->nets[i]->netdev);
-	}
-}
-
-static int kvaser_usb_init_one(struct kvaser_usb *dev,
-			       const struct usb_device_id *id, int channel)
-{
-	struct net_device *netdev;
-	struct kvaser_usb_net_priv *priv;
-	int err;
-
-	err = kvaser_usb_send_simple_cmd(dev, CMD_RESET_CHIP, channel);
-	if (err)
-		return err;
-
-	netdev = alloc_candev(sizeof(*priv) +
-			      dev->max_tx_urbs * sizeof(*priv->tx_contexts),
-			      dev->max_tx_urbs);
-	if (!netdev) {
-		dev_err(&dev->intf->dev, "Cannot alloc candev\n");
-		return -ENOMEM;
-	}
-
-	priv = netdev_priv(netdev);
-
-	init_usb_anchor(&priv->tx_submitted);
-	init_completion(&priv->start_comp);
-	init_completion(&priv->stop_comp);
-
-	priv->dev = dev;
-	priv->netdev = netdev;
-	priv->channel = channel;
-
-	spin_lock_init(&priv->tx_contexts_lock);
-	kvaser_usb_reset_tx_urb_contexts(priv);
-
-	priv->can.state = CAN_STATE_STOPPED;
-	priv->can.clock.freq = CAN_USB_CLOCK;
-	priv->can.bittiming_const = &kvaser_usb_bittiming_const;
-	priv->can.do_set_bittiming = kvaser_usb_set_bittiming;
-	priv->can.do_set_mode = kvaser_usb_set_mode;
-	if (id->driver_info & KVASER_HAS_TXRX_ERRORS)
-		priv->can.do_get_berr_counter = kvaser_usb_get_berr_counter;
-	priv->can.ctrlmode_supported = CAN_CTRLMODE_3_SAMPLES;
-	if (id->driver_info & KVASER_HAS_SILENT_MODE)
-		priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
-
-	netdev->flags |= IFF_ECHO;
-
-	netdev->netdev_ops = &kvaser_usb_netdev_ops;
-
-	SET_NETDEV_DEV(netdev, &dev->intf->dev);
-	netdev->dev_id = channel;
-
-	dev->nets[channel] = priv;
-
-	err = register_candev(netdev);
-	if (err) {
-		dev_err(&dev->intf->dev, "Failed to register CAN device\n");
-		free_candev(netdev);
-		dev->nets[channel] = NULL;
-		return err;
-	}
-
-	netdev_dbg(netdev, "device registered\n");
-
-	return 0;
-}
-
-static int kvaser_usb_setup_endpoints(struct kvaser_usb *dev)
-{
-	const struct usb_host_interface *iface_desc;
-	struct usb_endpoint_descriptor *endpoint;
-	int i;
-
-	iface_desc = &dev->intf->altsetting[0];
-
-	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
-		endpoint = &iface_desc->endpoint[i].desc;
-
-		if (!dev->bulk_in && usb_endpoint_is_bulk_in(endpoint))
-			dev->bulk_in = endpoint;
-
-		if (!dev->bulk_out && usb_endpoint_is_bulk_out(endpoint))
-			dev->bulk_out = endpoint;
-
-		/* use first bulk endpoint for in and out */
-		if (dev->bulk_in && dev->bulk_out)
-			return 0;
-	}
-
-	return -ENODEV;
-}
-
-static int kvaser_usb_probe(struct usb_interface *intf,
-			    const struct usb_device_id *id)
-{
-	struct kvaser_usb *dev;
-	int err = -ENOMEM;
-	int i, retry = 3;
-
-	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
-	if (!dev)
-		return -ENOMEM;
-
-	if (kvaser_is_leaf(id)) {
-		dev->family = KVASER_LEAF;
-	} else if (kvaser_is_usbcan(id)) {
-		dev->family = KVASER_USBCAN;
-	} else {
-		dev_err(&intf->dev,
-			"Product ID (%d) does not belong to any known Kvaser USB family",
-			id->idProduct);
-		return -ENODEV;
-	}
-
-	dev->intf = intf;
-
-	err = kvaser_usb_setup_endpoints(dev);
-	if (err) {
-		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
-		return err;
-	}
-
-	dev->udev = interface_to_usbdev(intf);
-
-	init_usb_anchor(&dev->rx_submitted);
-
-	usb_set_intfdata(intf, dev);
-
-	/* On some x86 laptops, plugging a Kvaser device again after
-	 * an unplug makes the firmware always ignore the very first
-	 * command. For such a case, provide some room for retries
-	 * instead of completely exiting the driver.
-	 */
-	do {
-		err = kvaser_usb_get_software_info(dev);
-	} while (--retry && err == -ETIMEDOUT);
-
-	if (err) {
-		dev_err(&intf->dev,
-			"Cannot get software infos, error %d\n", err);
-		return err;
-	}
-
-	dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n",
-		((dev->fw_version >> 24) & 0xff),
-		((dev->fw_version >> 16) & 0xff),
-		(dev->fw_version & 0xffff));
-
-	dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs);
-
-	err = kvaser_usb_get_card_info(dev);
-	if (err) {
-		dev_err(&intf->dev,
-			"Cannot get card infos, error %d\n", err);
-		return err;
-	}
-
-	for (i = 0; i < dev->nchannels; i++) {
-		err = kvaser_usb_init_one(dev, id, i);
-		if (err) {
-			kvaser_usb_remove_interfaces(dev);
-			return err;
-		}
-	}
-
-	return 0;
-}
-
-static void kvaser_usb_disconnect(struct usb_interface *intf)
-{
-	struct kvaser_usb *dev = usb_get_intfdata(intf);
-
-	usb_set_intfdata(intf, NULL);
-
-	if (!dev)
-		return;
-
-	kvaser_usb_remove_interfaces(dev);
-}
-
-static struct usb_driver kvaser_usb_driver = {
-	.name = "kvaser_usb",
-	.probe = kvaser_usb_probe,
-	.disconnect = kvaser_usb_disconnect,
-	.id_table = kvaser_usb_table,
-};
-
-module_usb_driver(kvaser_usb_driver);
-
-MODULE_AUTHOR("Olivier Sobrie <olivier@sobrie.be>");
-MODULE_DESCRIPTION("CAN driver for Kvaser CAN/USB devices");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb/Makefile b/drivers/net/can/usb/kvaser_usb/Makefile
new file mode 100644
index 000000000000..37b69dbc71b0
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
+kvaser_usb-y = kvaser_usb_core.o kvaser_usb_leaf.o
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
new file mode 100644
index 000000000000..82e6ecad034d
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -0,0 +1,158 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux leaf driver (version 4.78)
+ *  - CAN driver for esd CAN-USB/2
+ *  - Kvaser linux usbcanII driver (version 5.3)
+ *
+ * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
+ * Copyright (C) 2015 Valeo S.A.
+ */
+
+#ifndef KVASER_USB_H
+#define KVASER_USB_H
+
+/* Kvaser USB CAN dongles are divided into two major families:
+ * - Leaf: Based on Renesas M32C, running firmware labeled as 'filo'
+ * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios'
+ */
+
+#include <linux/completion.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+
+#define KVASER_USB_MAX_RX_URBS			4
+#define KVASER_USB_MAX_TX_URBS			128
+#define KVASER_USB_TIMEOUT			1000 /* msecs */
+#define KVASER_USB_RX_BUFFER_SIZE		3072
+#define KVASER_USB_MAX_NET_DEVICES		3
+
+/* USB devices features */
+#define KVASER_USB_HAS_SILENT_MODE		BIT(0)
+#define KVASER_USB_HAS_TXRX_ERRORS		BIT(1)
+
+struct kvaser_usb_dev_cfg;
+
+enum kvaser_usb_leaf_family {
+	KVASER_LEAF,
+	KVASER_USBCAN,
+};
+
+struct kvaser_usb_dev_card_data {
+	u32 ctrlmode_supported;
+	struct {
+		enum kvaser_usb_leaf_family family;
+	} leaf;
+};
+
+/* Context for an outstanding, not yet ACKed, transmission */
+struct kvaser_usb_tx_urb_context {
+	struct kvaser_usb_net_priv *priv;
+	u32 echo_index;
+	int dlc;
+};
+
+struct kvaser_usb {
+	struct usb_device *udev;
+	struct usb_interface *intf;
+	struct kvaser_usb_net_priv *nets[KVASER_USB_MAX_NET_DEVICES];
+	const struct kvaser_usb_dev_ops *ops;
+	const struct kvaser_usb_dev_cfg *cfg;
+
+	struct usb_endpoint_descriptor *bulk_in, *bulk_out;
+	struct usb_anchor rx_submitted;
+
+	/* @max_tx_urbs: Firmware-reported maximum number of outstanding,
+	 * not yet ACKed, transmissions on this device. This value is
+	 * also used as a sentinel for marking free tx contexts.
+	 */
+	u32 fw_version;
+	unsigned int nchannels;
+	unsigned int max_tx_urbs;
+	struct kvaser_usb_dev_card_data card_data;
+
+	bool rxinitdone;
+	void *rxbuf[KVASER_USB_MAX_RX_URBS];
+	dma_addr_t rxbuf_dma[KVASER_USB_MAX_RX_URBS];
+};
+
+struct kvaser_usb_net_priv {
+	struct can_priv can;
+	struct can_berr_counter bec;
+
+	struct kvaser_usb *dev;
+	struct net_device *netdev;
+	int channel;
+
+	struct completion start_comp, stop_comp;
+	struct usb_anchor tx_submitted;
+
+	spinlock_t tx_contexts_lock; /* lock for active_tx_contexts */
+	int active_tx_contexts;
+	struct kvaser_usb_tx_urb_context tx_contexts[];
+};
+
+/**
+ * struct kvaser_usb_dev_ops - Device specific functions
+ * @dev_set_mode:		used for can.do_set_mode
+ * @dev_set_bittiming:		used for can.do_set_bittiming
+ * @dev_get_berr_counter:	used for can.do_get_berr_counter
+ *
+ * @dev_setup_endpoints:	setup USB in and out endpoints
+ * @dev_init_card:		initialize card
+ * @dev_get_software_info:	get software info
+ * @dev_get_card_info:		get card info
+ *
+ * @dev_set_opt_mode:		set ctrlmod
+ * @dev_start_chip:		start the CAN controller
+ * @dev_stop_chip:		stop the CAN controller
+ * @dev_reset_chip:		reset the CAN controller
+ * @dev_flush_queue:		flush outstanding CAN messages
+ * @dev_read_bulk_callback:	handle incoming commands
+ * @dev_frame_to_cmd:		translate struct can_frame into device command
+ */
+struct kvaser_usb_dev_ops {
+	int (*dev_set_mode)(struct net_device *netdev, enum can_mode mode);
+	int (*dev_set_bittiming)(struct net_device *netdev);
+	int (*dev_get_berr_counter)(const struct net_device *netdev,
+				    struct can_berr_counter *bec);
+	int (*dev_setup_endpoints)(struct kvaser_usb *dev);
+	int (*dev_init_card)(struct kvaser_usb *dev);
+	int (*dev_get_software_info)(struct kvaser_usb *dev);
+	int (*dev_get_card_info)(struct kvaser_usb *dev);
+	int (*dev_set_opt_mode)(const struct kvaser_usb_net_priv *priv);
+	int (*dev_start_chip)(struct kvaser_usb_net_priv *priv);
+	int (*dev_stop_chip)(struct kvaser_usb_net_priv *priv);
+	int (*dev_reset_chip)(struct kvaser_usb *dev, int channel);
+	int (*dev_flush_queue)(struct kvaser_usb_net_priv *priv);
+	void (*dev_read_bulk_callback)(struct kvaser_usb *dev, void *buf,
+				       int len);
+	void *(*dev_frame_to_cmd)(const struct kvaser_usb_net_priv *priv,
+				  const struct sk_buff *skb, int *frame_len,
+				  int *cmd_len, u16 transid);
+};
+
+struct kvaser_usb_dev_cfg {
+	const struct can_clock clock;
+	const unsigned int timestamp_freq;
+	const struct can_bittiming_const * const bittiming_const;
+	const struct can_bittiming_const * const data_bittiming_const;
+};
+
+extern const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops;
+
+int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len,
+			int *actual_len);
+
+int kvaser_usb_send_cmd(const struct kvaser_usb *dev, void *cmd, int len);
+
+int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd,
+			      int len);
+
+int kvaser_usb_can_rx_over_error(struct net_device *netdev);
+#endif /* KVASER_USB_H */
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
new file mode 100644
index 000000000000..55ac489037fc
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -0,0 +1,769 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux leaf driver (version 4.78)
+ *  - CAN driver for esd CAN-USB/2
+ *  - Kvaser linux usbcanII driver (version 5.3)
+ *
+ * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
+ * Copyright (C) 2015 Valeo S.A.
+ */
+
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <linux/if.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/netlink.h>
+
+#include "kvaser_usb.h"
+
+/* Kvaser USB vendor id. */
+#define KVASER_VENDOR_ID			0x0bfd
+
+/* Kvaser Leaf USB devices product ids */
+#define USB_LEAF_DEVEL_PRODUCT_ID		10
+#define USB_LEAF_LITE_PRODUCT_ID		11
+#define USB_LEAF_PRO_PRODUCT_ID			12
+#define USB_LEAF_SPRO_PRODUCT_ID		14
+#define USB_LEAF_PRO_LS_PRODUCT_ID		15
+#define USB_LEAF_PRO_SWC_PRODUCT_ID		16
+#define USB_LEAF_PRO_LIN_PRODUCT_ID		17
+#define USB_LEAF_SPRO_LS_PRODUCT_ID		18
+#define USB_LEAF_SPRO_SWC_PRODUCT_ID		19
+#define USB_MEMO2_DEVEL_PRODUCT_ID		22
+#define USB_MEMO2_HSHS_PRODUCT_ID		23
+#define USB_UPRO_HSHS_PRODUCT_ID		24
+#define USB_LEAF_LITE_GI_PRODUCT_ID		25
+#define USB_LEAF_PRO_OBDII_PRODUCT_ID		26
+#define USB_MEMO2_HSLS_PRODUCT_ID		27
+#define USB_LEAF_LITE_CH_PRODUCT_ID		28
+#define USB_BLACKBIRD_SPRO_PRODUCT_ID		29
+#define USB_OEM_MERCURY_PRODUCT_ID		34
+#define USB_OEM_LEAF_PRODUCT_ID			35
+#define USB_CAN_R_PRODUCT_ID			39
+#define USB_LEAF_LITE_V2_PRODUCT_ID		288
+#define USB_MINI_PCIE_HS_PRODUCT_ID		289
+#define USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID	290
+#define USB_USBCAN_LIGHT_2HS_PRODUCT_ID		291
+#define USB_MINI_PCIE_2HS_PRODUCT_ID		292
+
+/* Kvaser USBCan-II devices product ids */
+#define USB_USBCAN_REVB_PRODUCT_ID		2
+#define USB_VCI2_PRODUCT_ID			3
+#define USB_USBCAN2_PRODUCT_ID			4
+#define USB_MEMORATOR_PRODUCT_ID		5
+
+static inline bool kvaser_is_leaf(const struct usb_device_id *id)
+{
+	return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
+	       id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID;
+}
+
+static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
+{
+	return id->idProduct >= USB_USBCAN_REVB_PRODUCT_ID &&
+	       id->idProduct <= USB_MEMORATOR_PRODUCT_ID;
+}
+
+static const struct usb_device_id kvaser_usb_table[] = {
+	/* Leaf USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_SWC_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_LIN_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_LS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_SPRO_SWC_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_DEVEL_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSHS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_UPRO_HSHS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_GI_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_OBDII_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS |
+			       KVASER_USB_HAS_SILENT_MODE },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO2_HSLS_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_CH_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_SPRO_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_MERCURY_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_OEM_LEAF_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_CAN_R_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LITE_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_LIGHT_HS_V2_OEM_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_2HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MINI_PCIE_2HS_PRODUCT_ID) },
+
+	/* USBCANII USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN2_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_REVB_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMORATOR_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID),
+		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+	{ }
+};
+MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
+
+int kvaser_usb_send_cmd(const struct kvaser_usb *dev, void *cmd, int len)
+{
+	int actual_len; /* Not used */
+
+	return usb_bulk_msg(dev->udev,
+			    usb_sndbulkpipe(dev->udev,
+					    dev->bulk_out->bEndpointAddress),
+			    cmd, len, &actual_len, KVASER_USB_TIMEOUT);
+}
+
+int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len,
+			int *actual_len)
+{
+	return usb_bulk_msg(dev->udev,
+			    usb_rcvbulkpipe(dev->udev,
+					    dev->bulk_in->bEndpointAddress),
+			    cmd, len, actual_len, KVASER_USB_TIMEOUT);
+}
+
+static void kvaser_usb_send_cmd_callback(struct urb *urb)
+{
+	struct net_device *netdev = urb->context;
+
+	kfree(urb->transfer_buffer);
+
+	if (urb->status)
+		netdev_warn(netdev, "urb status received: %d\n", urb->status);
+}
+
+int kvaser_usb_send_cmd_async(struct kvaser_usb_net_priv *priv, void *cmd,
+			      int len)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct net_device *netdev = priv->netdev;
+	struct urb *urb;
+	int err;
+
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb)
+		return -ENOMEM;
+
+	usb_fill_bulk_urb(urb, dev->udev,
+			  usb_sndbulkpipe(dev->udev,
+					  dev->bulk_out->bEndpointAddress),
+			  cmd, len, kvaser_usb_send_cmd_callback, netdev);
+	usb_anchor_urb(urb, &priv->tx_submitted);
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (err) {
+		netdev_err(netdev, "Error transmitting URB\n");
+		usb_unanchor_urb(urb);
+	}
+	usb_free_urb(urb);
+
+	return 0;
+}
+
+int kvaser_usb_can_rx_over_error(struct net_device *netdev)
+{
+	struct net_device_stats *stats = &netdev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+
+	stats->rx_over_errors++;
+	stats->rx_errors++;
+
+	skb = alloc_can_err_skb(netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return -ENOMEM;
+	}
+
+	cf->can_id |= CAN_ERR_CRTL;
+	cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+
+	return 0;
+}
+
+static void kvaser_usb_read_bulk_callback(struct urb *urb)
+{
+	struct kvaser_usb *dev = urb->context;
+	int err;
+	unsigned int i;
+
+	switch (urb->status) {
+	case 0:
+		break;
+	case -ENOENT:
+	case -EPIPE:
+	case -EPROTO:
+	case -ESHUTDOWN:
+		return;
+	default:
+		dev_info(&dev->intf->dev, "Rx URB aborted (%d)\n", urb->status);
+		goto resubmit_urb;
+	}
+
+	dev->ops->dev_read_bulk_callback(dev, urb->transfer_buffer,
+					 urb->actual_length);
+
+resubmit_urb:
+	usb_fill_bulk_urb(urb, dev->udev,
+			  usb_rcvbulkpipe(dev->udev,
+					  dev->bulk_in->bEndpointAddress),
+			  urb->transfer_buffer, KVASER_USB_RX_BUFFER_SIZE,
+			  kvaser_usb_read_bulk_callback, dev);
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (err == -ENODEV) {
+		for (i = 0; i < dev->nchannels; i++) {
+			if (!dev->nets[i])
+				continue;
+
+			netif_device_detach(dev->nets[i]->netdev);
+		}
+	} else if (err) {
+		dev_err(&dev->intf->dev,
+			"Failed resubmitting read bulk urb: %d\n", err);
+	}
+}
+
+static int kvaser_usb_setup_rx_urbs(struct kvaser_usb *dev)
+{
+	int i, err = 0;
+
+	if (dev->rxinitdone)
+		return 0;
+
+	for (i = 0; i < KVASER_USB_MAX_RX_URBS; i++) {
+		struct urb *urb = NULL;
+		u8 *buf = NULL;
+		dma_addr_t buf_dma;
+
+		urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!urb) {
+			err = -ENOMEM;
+			break;
+		}
+
+		buf = usb_alloc_coherent(dev->udev, KVASER_USB_RX_BUFFER_SIZE,
+					 GFP_KERNEL, &buf_dma);
+		if (!buf) {
+			dev_warn(&dev->intf->dev,
+				 "No memory left for USB buffer\n");
+			usb_free_urb(urb);
+			err = -ENOMEM;
+			break;
+		}
+
+		usb_fill_bulk_urb(urb, dev->udev,
+				  usb_rcvbulkpipe
+					(dev->udev,
+					 dev->bulk_in->bEndpointAddress),
+				  buf, KVASER_USB_RX_BUFFER_SIZE,
+				  kvaser_usb_read_bulk_callback, dev);
+		urb->transfer_dma = buf_dma;
+		urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+		usb_anchor_urb(urb, &dev->rx_submitted);
+
+		err = usb_submit_urb(urb, GFP_KERNEL);
+		if (err) {
+			usb_unanchor_urb(urb);
+			usb_free_coherent(dev->udev,
+					  KVASER_USB_RX_BUFFER_SIZE, buf,
+					  buf_dma);
+			usb_free_urb(urb);
+			break;
+		}
+
+		dev->rxbuf[i] = buf;
+		dev->rxbuf_dma[i] = buf_dma;
+
+		usb_free_urb(urb);
+	}
+
+	if (i == 0) {
+		dev_warn(&dev->intf->dev, "Cannot setup read URBs, error %d\n",
+			 err);
+		return err;
+	} else if (i < KVASER_USB_MAX_RX_URBS) {
+		dev_warn(&dev->intf->dev, "RX performances may be slow\n");
+	}
+
+	dev->rxinitdone = true;
+
+	return 0;
+}
+
+static int kvaser_usb_open(struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct kvaser_usb *dev = priv->dev;
+	int err;
+
+	err = open_candev(netdev);
+	if (err)
+		return err;
+
+	err = kvaser_usb_setup_rx_urbs(dev);
+	if (err)
+		goto error;
+
+	err = dev->ops->dev_set_opt_mode(priv);
+	if (err)
+		goto error;
+
+	err = dev->ops->dev_start_chip(priv);
+	if (err) {
+		netdev_warn(netdev, "Cannot start device, error %d\n", err);
+		goto error;
+	}
+
+	priv->can.state = CAN_STATE_ERROR_ACTIVE;
+
+	return 0;
+
+error:
+	close_candev(netdev);
+	return err;
+}
+
+static void kvaser_usb_reset_tx_urb_contexts(struct kvaser_usb_net_priv *priv)
+{
+	int i, max_tx_urbs;
+
+	max_tx_urbs = priv->dev->max_tx_urbs;
+
+	priv->active_tx_contexts = 0;
+	for (i = 0; i < max_tx_urbs; i++)
+		priv->tx_contexts[i].echo_index = max_tx_urbs;
+}
+
+/* This method might sleep. Do not call it in the atomic context
+ * of URB completions.
+ */
+static void kvaser_usb_unlink_tx_urbs(struct kvaser_usb_net_priv *priv)
+{
+	usb_kill_anchored_urbs(&priv->tx_submitted);
+	kvaser_usb_reset_tx_urb_contexts(priv);
+}
+
+static void kvaser_usb_unlink_all_urbs(struct kvaser_usb *dev)
+{
+	int i;
+
+	usb_kill_anchored_urbs(&dev->rx_submitted);
+
+	for (i = 0; i < KVASER_USB_MAX_RX_URBS; i++)
+		usb_free_coherent(dev->udev, KVASER_USB_RX_BUFFER_SIZE,
+				  dev->rxbuf[i], dev->rxbuf_dma[i]);
+
+	for (i = 0; i < dev->nchannels; i++) {
+		struct kvaser_usb_net_priv *priv = dev->nets[i];
+
+		if (priv)
+			kvaser_usb_unlink_tx_urbs(priv);
+	}
+}
+
+static int kvaser_usb_close(struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct kvaser_usb *dev = priv->dev;
+	int err;
+
+	netif_stop_queue(netdev);
+
+	err = dev->ops->dev_flush_queue(priv);
+	if (err)
+		netdev_warn(netdev, "Cannot flush queue, error %d\n", err);
+
+	if (dev->ops->dev_reset_chip) {
+		err = dev->ops->dev_reset_chip(dev, priv->channel);
+		if (err)
+			netdev_warn(netdev, "Cannot reset card, error %d\n",
+				    err);
+	}
+
+	err = dev->ops->dev_stop_chip(priv);
+	if (err)
+		netdev_warn(netdev, "Cannot stop device, error %d\n", err);
+
+	/* reset tx contexts */
+	kvaser_usb_unlink_tx_urbs(priv);
+
+	priv->can.state = CAN_STATE_STOPPED;
+	close_candev(priv->netdev);
+
+	return 0;
+}
+
+static void kvaser_usb_write_bulk_callback(struct urb *urb)
+{
+	struct kvaser_usb_tx_urb_context *context = urb->context;
+	struct kvaser_usb_net_priv *priv;
+	struct net_device *netdev;
+
+	if (WARN_ON(!context))
+		return;
+
+	priv = context->priv;
+	netdev = priv->netdev;
+
+	kfree(urb->transfer_buffer);
+
+	if (!netif_device_present(netdev))
+		return;
+
+	if (urb->status)
+		netdev_info(netdev, "Tx URB aborted (%d)\n", urb->status);
+}
+
+static netdev_tx_t kvaser_usb_start_xmit(struct sk_buff *skb,
+					 struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct kvaser_usb *dev = priv->dev;
+	struct net_device_stats *stats = &netdev->stats;
+	struct kvaser_usb_tx_urb_context *context = NULL;
+	struct urb *urb;
+	void *buf;
+	int cmd_len = 0;
+	int err, ret = NETDEV_TX_OK;
+	unsigned int i;
+	unsigned long flags;
+
+	if (can_dropped_invalid_skb(netdev, skb))
+		return NETDEV_TX_OK;
+
+	urb = usb_alloc_urb(0, GFP_ATOMIC);
+	if (!urb) {
+		stats->tx_dropped++;
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+	for (i = 0; i < dev->max_tx_urbs; i++) {
+		if (priv->tx_contexts[i].echo_index == dev->max_tx_urbs) {
+			context = &priv->tx_contexts[i];
+
+			context->echo_index = i;
+			can_put_echo_skb(skb, netdev, context->echo_index);
+			++priv->active_tx_contexts;
+			if (priv->active_tx_contexts >= (int)dev->max_tx_urbs)
+				netif_stop_queue(netdev);
+
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+
+	/* This should never happen; it implies a flow control bug */
+	if (!context) {
+		netdev_warn(netdev, "cannot find free context\n");
+
+		ret = NETDEV_TX_BUSY;
+		goto freeurb;
+	}
+
+	buf = dev->ops->dev_frame_to_cmd(priv, skb, &context->dlc, &cmd_len,
+					 context->echo_index);
+	if (!buf) {
+		stats->tx_dropped++;
+		dev_kfree_skb(skb);
+		spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+
+		can_free_echo_skb(netdev, context->echo_index);
+		context->echo_index = dev->max_tx_urbs;
+		--priv->active_tx_contexts;
+		netif_wake_queue(netdev);
+
+		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+		goto freeurb;
+	}
+
+	context->priv = priv;
+
+	usb_fill_bulk_urb(urb, dev->udev,
+			  usb_sndbulkpipe(dev->udev,
+					  dev->bulk_out->bEndpointAddress),
+			  buf, cmd_len, kvaser_usb_write_bulk_callback,
+			  context);
+	usb_anchor_urb(urb, &priv->tx_submitted);
+
+	err = usb_submit_urb(urb, GFP_ATOMIC);
+	if (unlikely(err)) {
+		spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+
+		can_free_echo_skb(netdev, context->echo_index);
+		context->echo_index = dev->max_tx_urbs;
+		--priv->active_tx_contexts;
+		netif_wake_queue(netdev);
+
+		spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+
+		usb_unanchor_urb(urb);
+		kfree(buf);
+
+		stats->tx_dropped++;
+
+		if (err == -ENODEV)
+			netif_device_detach(netdev);
+		else
+			netdev_warn(netdev, "Failed tx_urb %d\n", err);
+
+		goto freeurb;
+	}
+
+	ret = NETDEV_TX_OK;
+
+freeurb:
+	usb_free_urb(urb);
+	return ret;
+}
+
+static const struct net_device_ops kvaser_usb_netdev_ops = {
+	.ndo_open = kvaser_usb_open,
+	.ndo_stop = kvaser_usb_close,
+	.ndo_start_xmit = kvaser_usb_start_xmit,
+	.ndo_change_mtu = can_change_mtu,
+};
+
+static void kvaser_usb_remove_interfaces(struct kvaser_usb *dev)
+{
+	int i;
+
+	for (i = 0; i < dev->nchannels; i++) {
+		if (!dev->nets[i])
+			continue;
+
+		unregister_candev(dev->nets[i]->netdev);
+	}
+
+	kvaser_usb_unlink_all_urbs(dev);
+
+	for (i = 0; i < dev->nchannels; i++) {
+		if (!dev->nets[i])
+			continue;
+
+		free_candev(dev->nets[i]->netdev);
+	}
+}
+
+static int kvaser_usb_init_one(struct kvaser_usb *dev,
+			       const struct usb_device_id *id, int channel)
+{
+	struct net_device *netdev;
+	struct kvaser_usb_net_priv *priv;
+	int err;
+
+	if (dev->ops->dev_reset_chip) {
+		err = dev->ops->dev_reset_chip(dev, channel);
+		if (err)
+			return err;
+	}
+
+	netdev = alloc_candev(sizeof(*priv) +
+			      dev->max_tx_urbs * sizeof(*priv->tx_contexts),
+			      dev->max_tx_urbs);
+	if (!netdev) {
+		dev_err(&dev->intf->dev, "Cannot alloc candev\n");
+		return -ENOMEM;
+	}
+
+	priv = netdev_priv(netdev);
+
+	init_usb_anchor(&priv->tx_submitted);
+	init_completion(&priv->start_comp);
+	init_completion(&priv->stop_comp);
+	priv->can.ctrlmode_supported = 0;
+
+	priv->dev = dev;
+	priv->netdev = netdev;
+	priv->channel = channel;
+
+	spin_lock_init(&priv->tx_contexts_lock);
+	kvaser_usb_reset_tx_urb_contexts(priv);
+
+	priv->can.state = CAN_STATE_STOPPED;
+	priv->can.clock.freq = dev->cfg->clock.freq;
+	priv->can.bittiming_const = dev->cfg->bittiming_const;
+	priv->can.do_set_bittiming = dev->ops->dev_set_bittiming;
+	priv->can.do_set_mode = dev->ops->dev_set_mode;
+	if (id->driver_info & KVASER_USB_HAS_TXRX_ERRORS)
+		priv->can.do_get_berr_counter = dev->ops->dev_get_berr_counter;
+	if (id->driver_info & KVASER_USB_HAS_SILENT_MODE)
+		priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
+
+	priv->can.ctrlmode_supported |= dev->card_data.ctrlmode_supported;
+
+	netdev->flags |= IFF_ECHO;
+
+	netdev->netdev_ops = &kvaser_usb_netdev_ops;
+
+	SET_NETDEV_DEV(netdev, &dev->intf->dev);
+	netdev->dev_id = channel;
+
+	dev->nets[channel] = priv;
+
+	err = register_candev(netdev);
+	if (err) {
+		dev_err(&dev->intf->dev, "Failed to register CAN device\n");
+		free_candev(netdev);
+		dev->nets[channel] = NULL;
+		return err;
+	}
+
+	netdev_dbg(netdev, "device registered\n");
+
+	return 0;
+}
+
+static int kvaser_usb_probe(struct usb_interface *intf,
+			    const struct usb_device_id *id)
+{
+	struct kvaser_usb *dev;
+	int err;
+	int i;
+
+	dev = devm_kzalloc(&intf->dev, sizeof(*dev), GFP_KERNEL);
+	if (!dev)
+		return -ENOMEM;
+
+	if (kvaser_is_leaf(id)) {
+		dev->card_data.leaf.family = KVASER_LEAF;
+		dev->ops = &kvaser_usb_leaf_dev_ops;
+	} else if (kvaser_is_usbcan(id)) {
+		dev->card_data.leaf.family = KVASER_USBCAN;
+		dev->ops = &kvaser_usb_leaf_dev_ops;
+	} else {
+		dev_err(&intf->dev,
+			"Product ID (%d) is not a supported Kvaser USB device\n",
+			id->idProduct);
+		return -ENODEV;
+	}
+
+	dev->intf = intf;
+
+	err = dev->ops->dev_setup_endpoints(dev);
+	if (err) {
+		dev_err(&intf->dev, "Cannot get usb endpoint(s)");
+		return err;
+	}
+
+	dev->udev = interface_to_usbdev(intf);
+
+	init_usb_anchor(&dev->rx_submitted);
+
+	usb_set_intfdata(intf, dev);
+
+	dev->card_data.ctrlmode_supported = 0;
+	err = dev->ops->dev_init_card(dev);
+	if (err) {
+		dev_err(&intf->dev,
+			"Failed to initialize card, error %d\n", err);
+		return err;
+	}
+
+	err = dev->ops->dev_get_software_info(dev);
+	if (err) {
+		dev_err(&intf->dev,
+			"Cannot get software info, error %d\n", err);
+		return err;
+	}
+
+	if (WARN_ON(!dev->cfg))
+		return -ENODEV;
+
+	dev_dbg(&intf->dev, "Firmware version: %d.%d.%d\n",
+		((dev->fw_version >> 24) & 0xff),
+		((dev->fw_version >> 16) & 0xff),
+		(dev->fw_version & 0xffff));
+
+	dev_dbg(&intf->dev, "Max outstanding tx = %d URBs\n", dev->max_tx_urbs);
+
+	err = dev->ops->dev_get_card_info(dev);
+	if (err) {
+		dev_err(&intf->dev, "Cannot get card info, error %d\n", err);
+		return err;
+	}
+
+	for (i = 0; i < dev->nchannels; i++) {
+		err = kvaser_usb_init_one(dev, id, i);
+		if (err) {
+			kvaser_usb_remove_interfaces(dev);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void kvaser_usb_disconnect(struct usb_interface *intf)
+{
+	struct kvaser_usb *dev = usb_get_intfdata(intf);
+
+	usb_set_intfdata(intf, NULL);
+
+	if (!dev)
+		return;
+
+	kvaser_usb_remove_interfaces(dev);
+}
+
+static struct usb_driver kvaser_usb_driver = {
+	.name = "kvaser_usb",
+	.probe = kvaser_usb_probe,
+	.disconnect = kvaser_usb_disconnect,
+	.id_table = kvaser_usb_table,
+};
+
+module_usb_driver(kvaser_usb_driver);
+
+MODULE_AUTHOR("Olivier Sobrie <olivier@sobrie.be>");
+MODULE_AUTHOR("Kvaser AB <support@kvaser.com>");
+MODULE_DESCRIPTION("CAN driver for Kvaser CAN/USB devices");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
new file mode 100644
index 000000000000..82806732dcdf
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -0,0 +1,1363 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux leaf driver (version 4.78)
+ *  - CAN driver for esd CAN-USB/2
+ *  - Kvaser linux usbcanII driver (version 5.3)
+ *
+ * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ * Copyright (C) 2012 Olivier Sobrie <olivier@sobrie.be>
+ * Copyright (C) 2015 Valeo S.A.
+ */
+
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/netlink.h>
+
+#include "kvaser_usb.h"
+
+/* Forward declaration */
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg;
+
+#define CAN_USB_CLOCK			8000000
+#define MAX_USBCAN_NET_DEVICES		2
+
+/* Command header size */
+#define CMD_HEADER_LEN			2
+
+/* Kvaser CAN message flags */
+#define MSG_FLAG_ERROR_FRAME		BIT(0)
+#define MSG_FLAG_OVERRUN		BIT(1)
+#define MSG_FLAG_NERR			BIT(2)
+#define MSG_FLAG_WAKEUP			BIT(3)
+#define MSG_FLAG_REMOTE_FRAME		BIT(4)
+#define MSG_FLAG_RESERVED		BIT(5)
+#define MSG_FLAG_TX_ACK			BIT(6)
+#define MSG_FLAG_TX_REQUEST		BIT(7)
+
+/* CAN states (M16C CxSTRH register) */
+#define M16C_STATE_BUS_RESET		BIT(0)
+#define M16C_STATE_BUS_ERROR		BIT(4)
+#define M16C_STATE_BUS_PASSIVE		BIT(5)
+#define M16C_STATE_BUS_OFF		BIT(6)
+
+/* Leaf/usbcan command ids */
+#define CMD_RX_STD_MESSAGE		12
+#define CMD_TX_STD_MESSAGE		13
+#define CMD_RX_EXT_MESSAGE		14
+#define CMD_TX_EXT_MESSAGE		15
+#define CMD_SET_BUS_PARAMS		16
+#define CMD_CHIP_STATE_EVENT		20
+#define CMD_SET_CTRL_MODE		21
+#define CMD_RESET_CHIP			24
+#define CMD_START_CHIP			26
+#define CMD_START_CHIP_REPLY		27
+#define CMD_STOP_CHIP			28
+#define CMD_STOP_CHIP_REPLY		29
+
+#define CMD_USBCAN_CLOCK_OVERFLOW_EVENT	33
+
+#define CMD_GET_CARD_INFO		34
+#define CMD_GET_CARD_INFO_REPLY		35
+#define CMD_GET_SOFTWARE_INFO		38
+#define CMD_GET_SOFTWARE_INFO_REPLY	39
+#define CMD_FLUSH_QUEUE			48
+#define CMD_TX_ACKNOWLEDGE		50
+#define CMD_CAN_ERROR_EVENT		51
+#define CMD_FLUSH_QUEUE_REPLY		68
+
+#define CMD_LEAF_LOG_MESSAGE		106
+
+/* error factors */
+#define M16C_EF_ACKE			BIT(0)
+#define M16C_EF_CRCE			BIT(1)
+#define M16C_EF_FORME			BIT(2)
+#define M16C_EF_STFE			BIT(3)
+#define M16C_EF_BITE0			BIT(4)
+#define M16C_EF_BITE1			BIT(5)
+#define M16C_EF_RCVE			BIT(6)
+#define M16C_EF_TRE			BIT(7)
+
+/* Only Leaf-based devices can report M16C error factors,
+ * thus define our own error status flags for USBCANII
+ */
+#define USBCAN_ERROR_STATE_NONE		0
+#define USBCAN_ERROR_STATE_TX_ERROR	BIT(0)
+#define USBCAN_ERROR_STATE_RX_ERROR	BIT(1)
+#define USBCAN_ERROR_STATE_BUSERROR	BIT(2)
+
+/* bittiming parameters */
+#define KVASER_USB_TSEG1_MIN		1
+#define KVASER_USB_TSEG1_MAX		16
+#define KVASER_USB_TSEG2_MIN		1
+#define KVASER_USB_TSEG2_MAX		8
+#define KVASER_USB_SJW_MAX		4
+#define KVASER_USB_BRP_MIN		1
+#define KVASER_USB_BRP_MAX		64
+#define KVASER_USB_BRP_INC		1
+
+/* ctrl modes */
+#define KVASER_CTRL_MODE_NORMAL		1
+#define KVASER_CTRL_MODE_SILENT		2
+#define KVASER_CTRL_MODE_SELFRECEPTION	3
+#define KVASER_CTRL_MODE_OFF		4
+
+/* Extended CAN identifier flag */
+#define KVASER_EXTENDED_FRAME		BIT(31)
+
+struct kvaser_cmd_simple {
+	u8 tid;
+	u8 channel;
+} __packed;
+
+struct kvaser_cmd_cardinfo {
+	u8 tid;
+	u8 nchannels;
+	union {
+		struct {
+			__le32 serial_number;
+			__le32 padding;
+		} __packed leaf0;
+		struct {
+			__le32 serial_number_low;
+			__le32 serial_number_high;
+		} __packed usbcan0;
+	} __packed;
+	__le32 clock_resolution;
+	__le32 mfgdate;
+	u8 ean[8];
+	u8 hw_revision;
+	union {
+		struct {
+			u8 usb_hs_mode;
+		} __packed leaf1;
+		struct {
+			u8 padding;
+		} __packed usbcan1;
+	} __packed;
+	__le16 padding;
+} __packed;
+
+struct leaf_cmd_softinfo {
+	u8 tid;
+	u8 padding0;
+	__le32 sw_options;
+	__le32 fw_version;
+	__le16 max_outstanding_tx;
+	__le16 padding1[9];
+} __packed;
+
+struct usbcan_cmd_softinfo {
+	u8 tid;
+	u8 fw_name[5];
+	__le16 max_outstanding_tx;
+	u8 padding[6];
+	__le32 fw_version;
+	__le16 checksum;
+	__le16 sw_options;
+} __packed;
+
+struct kvaser_cmd_busparams {
+	u8 tid;
+	u8 channel;
+	__le32 bitrate;
+	u8 tseg1;
+	u8 tseg2;
+	u8 sjw;
+	u8 no_samp;
+} __packed;
+
+struct kvaser_cmd_tx_can {
+	u8 channel;
+	u8 tid;
+	u8 data[14];
+	union {
+		struct {
+			u8 padding;
+			u8 flags;
+		} __packed leaf;
+		struct {
+			u8 flags;
+			u8 padding;
+		} __packed usbcan;
+	} __packed;
+} __packed;
+
+struct kvaser_cmd_rx_can_header {
+	u8 channel;
+	u8 flag;
+} __packed;
+
+struct leaf_cmd_rx_can {
+	u8 channel;
+	u8 flag;
+
+	__le16 time[3];
+	u8 data[14];
+} __packed;
+
+struct usbcan_cmd_rx_can {
+	u8 channel;
+	u8 flag;
+
+	u8 data[14];
+	__le16 time;
+} __packed;
+
+struct leaf_cmd_chip_state_event {
+	u8 tid;
+	u8 channel;
+
+	__le16 time[3];
+	u8 tx_errors_count;
+	u8 rx_errors_count;
+
+	u8 status;
+	u8 padding[3];
+} __packed;
+
+struct usbcan_cmd_chip_state_event {
+	u8 tid;
+	u8 channel;
+
+	u8 tx_errors_count;
+	u8 rx_errors_count;
+	__le16 time;
+
+	u8 status;
+	u8 padding[3];
+} __packed;
+
+struct kvaser_cmd_tx_acknowledge_header {
+	u8 channel;
+	u8 tid;
+} __packed;
+
+struct leaf_cmd_error_event {
+	u8 tid;
+	u8 flags;
+	__le16 time[3];
+	u8 channel;
+	u8 padding;
+	u8 tx_errors_count;
+	u8 rx_errors_count;
+	u8 status;
+	u8 error_factor;
+} __packed;
+
+struct usbcan_cmd_error_event {
+	u8 tid;
+	u8 padding;
+	u8 tx_errors_count_ch0;
+	u8 rx_errors_count_ch0;
+	u8 tx_errors_count_ch1;
+	u8 rx_errors_count_ch1;
+	u8 status_ch0;
+	u8 status_ch1;
+	__le16 time;
+} __packed;
+
+struct kvaser_cmd_ctrl_mode {
+	u8 tid;
+	u8 channel;
+	u8 ctrl_mode;
+	u8 padding[3];
+} __packed;
+
+struct kvaser_cmd_flush_queue {
+	u8 tid;
+	u8 channel;
+	u8 flags;
+	u8 padding[3];
+} __packed;
+
+struct leaf_cmd_log_message {
+	u8 channel;
+	u8 flags;
+	__le16 time[3];
+	u8 dlc;
+	u8 time_offset;
+	__le32 id;
+	u8 data[8];
+} __packed;
+
+struct kvaser_cmd {
+	u8 len;
+	u8 id;
+	union	{
+		struct kvaser_cmd_simple simple;
+		struct kvaser_cmd_cardinfo cardinfo;
+		struct kvaser_cmd_busparams busparams;
+
+		struct kvaser_cmd_rx_can_header rx_can_header;
+		struct kvaser_cmd_tx_acknowledge_header tx_acknowledge_header;
+
+		union {
+			struct leaf_cmd_softinfo softinfo;
+			struct leaf_cmd_rx_can rx_can;
+			struct leaf_cmd_chip_state_event chip_state_event;
+			struct leaf_cmd_error_event error_event;
+			struct leaf_cmd_log_message log_message;
+		} __packed leaf;
+
+		union {
+			struct usbcan_cmd_softinfo softinfo;
+			struct usbcan_cmd_rx_can rx_can;
+			struct usbcan_cmd_chip_state_event chip_state_event;
+			struct usbcan_cmd_error_event error_event;
+		} __packed usbcan;
+
+		struct kvaser_cmd_tx_can tx_can;
+		struct kvaser_cmd_ctrl_mode ctrl_mode;
+		struct kvaser_cmd_flush_queue flush_queue;
+	} u;
+} __packed;
+
+/* Summary of a kvaser error event, for a unified Leaf/Usbcan error
+ * handling. Some discrepancies between the two families exist:
+ *
+ * - USBCAN firmware does not report M16C "error factors"
+ * - USBCAN controllers has difficulties reporting if the raised error
+ *   event is for ch0 or ch1. They leave such arbitration to the OS
+ *   driver by letting it compare error counters with previous values
+ *   and decide the error event's channel. Thus for USBCAN, the channel
+ *   field is only advisory.
+ */
+struct kvaser_usb_err_summary {
+	u8 channel, status, txerr, rxerr;
+	union {
+		struct {
+			u8 error_factor;
+		} leaf;
+		struct {
+			u8 other_ch_status;
+			u8 error_state;
+		} usbcan;
+	};
+};
+
+static void *
+kvaser_usb_leaf_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
+			     const struct sk_buff *skb, int *frame_len,
+			     int *cmd_len, u16 transid)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	u8 *cmd_tx_can_flags = NULL;		/* GCC */
+	struct can_frame *cf = (struct can_frame *)skb->data;
+
+	*frame_len = cf->can_dlc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC);
+	if (cmd) {
+		cmd->u.tx_can.tid = transid & 0xff;
+		cmd->len = *cmd_len = CMD_HEADER_LEN +
+				      sizeof(struct kvaser_cmd_tx_can);
+		cmd->u.tx_can.channel = priv->channel;
+
+		switch (dev->card_data.leaf.family) {
+		case KVASER_LEAF:
+			cmd_tx_can_flags = &cmd->u.tx_can.leaf.flags;
+			break;
+		case KVASER_USBCAN:
+			cmd_tx_can_flags = &cmd->u.tx_can.usbcan.flags;
+			break;
+		}
+
+		*cmd_tx_can_flags = 0;
+
+		if (cf->can_id & CAN_EFF_FLAG) {
+			cmd->id = CMD_TX_EXT_MESSAGE;
+			cmd->u.tx_can.data[0] = (cf->can_id >> 24) & 0x1f;
+			cmd->u.tx_can.data[1] = (cf->can_id >> 18) & 0x3f;
+			cmd->u.tx_can.data[2] = (cf->can_id >> 14) & 0x0f;
+			cmd->u.tx_can.data[3] = (cf->can_id >> 6) & 0xff;
+			cmd->u.tx_can.data[4] = cf->can_id & 0x3f;
+		} else {
+			cmd->id = CMD_TX_STD_MESSAGE;
+			cmd->u.tx_can.data[0] = (cf->can_id >> 6) & 0x1f;
+			cmd->u.tx_can.data[1] = cf->can_id & 0x3f;
+		}
+
+		cmd->u.tx_can.data[5] = cf->can_dlc;
+		memcpy(&cmd->u.tx_can.data[6], cf->data, cf->can_dlc);
+
+		if (cf->can_id & CAN_RTR_FLAG)
+			*cmd_tx_can_flags |= MSG_FLAG_REMOTE_FRAME;
+	}
+	return cmd;
+}
+
+static int kvaser_usb_leaf_wait_cmd(const struct kvaser_usb *dev, u8 id,
+				    struct kvaser_cmd *cmd)
+{
+	struct kvaser_cmd *tmp;
+	void *buf;
+	int actual_len;
+	int err;
+	int pos;
+	unsigned long to = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT);
+
+	buf = kzalloc(KVASER_USB_RX_BUFFER_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	do {
+		err = kvaser_usb_recv_cmd(dev, buf, KVASER_USB_RX_BUFFER_SIZE,
+					  &actual_len);
+		if (err < 0)
+			goto end;
+
+		pos = 0;
+		while (pos <= actual_len - CMD_HEADER_LEN) {
+			tmp = buf + pos;
+
+			/* Handle commands crossing the USB endpoint max packet
+			 * size boundary. Check kvaser_usb_read_bulk_callback()
+			 * for further details.
+			 */
+			if (tmp->len == 0) {
+				pos = round_up(pos,
+					       le16_to_cpu
+						(dev->bulk_in->wMaxPacketSize));
+				continue;
+			}
+
+			if (pos + tmp->len > actual_len) {
+				dev_err_ratelimited(&dev->intf->dev,
+						    "Format error\n");
+				break;
+			}
+
+			if (tmp->id == id) {
+				memcpy(cmd, tmp, tmp->len);
+				goto end;
+			}
+
+			pos += tmp->len;
+		}
+	} while (time_before(jiffies, to));
+
+	err = -EINVAL;
+
+end:
+	kfree(buf);
+
+	return err;
+}
+
+static int kvaser_usb_leaf_send_simple_cmd(const struct kvaser_usb *dev,
+					   u8 cmd_id, int channel)
+{
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = cmd_id;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
+	cmd->u.simple.channel = channel;
+	cmd->u.simple.tid = 0xff;
+
+	rc = kvaser_usb_send_cmd(dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_get_software_info_inner(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_leaf_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO, 0);
+	if (err)
+		return err;
+
+	err = kvaser_usb_leaf_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_REPLY, &cmd);
+	if (err)
+		return err;
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		dev->fw_version = le32_to_cpu(cmd.u.leaf.softinfo.fw_version);
+		dev->max_tx_urbs =
+			le16_to_cpu(cmd.u.leaf.softinfo.max_outstanding_tx);
+		break;
+	case KVASER_USBCAN:
+		dev->fw_version = le32_to_cpu(cmd.u.usbcan.softinfo.fw_version);
+		dev->max_tx_urbs =
+			le16_to_cpu(cmd.u.usbcan.softinfo.max_outstanding_tx);
+		break;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_get_software_info(struct kvaser_usb *dev)
+{
+	int err;
+	int retry = 3;
+
+	/* On some x86 laptops, plugging a Kvaser device again after
+	 * an unplug makes the firmware always ignore the very first
+	 * command. For such a case, provide some room for retries
+	 * instead of completely exiting the driver.
+	 */
+	do {
+		err = kvaser_usb_leaf_get_software_info_inner(dev);
+	} while (--retry && err == -ETIMEDOUT);
+
+	return err;
+}
+
+static int kvaser_usb_leaf_get_card_info(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_leaf_send_simple_cmd(dev, CMD_GET_CARD_INFO, 0);
+	if (err)
+		return err;
+
+	err = kvaser_usb_leaf_wait_cmd(dev, CMD_GET_CARD_INFO_REPLY, &cmd);
+	if (err)
+		return err;
+
+	dev->nchannels = cmd.u.cardinfo.nchannels;
+	if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES ||
+	    (dev->card_data.leaf.family == KVASER_USBCAN &&
+	     dev->nchannels > MAX_USBCAN_NET_DEVICES))
+		return -EINVAL;
+
+	return 0;
+}
+
+static void kvaser_usb_leaf_tx_acknowledge(const struct kvaser_usb *dev,
+					   const struct kvaser_cmd *cmd)
+{
+	struct net_device_stats *stats;
+	struct kvaser_usb_tx_urb_context *context;
+	struct kvaser_usb_net_priv *priv;
+	unsigned long flags;
+	u8 channel, tid;
+
+	channel = cmd->u.tx_acknowledge_header.channel;
+	tid = cmd->u.tx_acknowledge_header.tid;
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+
+	if (!netif_device_present(priv->netdev))
+		return;
+
+	stats = &priv->netdev->stats;
+
+	context = &priv->tx_contexts[tid % dev->max_tx_urbs];
+
+	/* Sometimes the state change doesn't come after a bus-off event */
+	if (priv->can.restart_ms && priv->can.state >= CAN_STATE_BUS_OFF) {
+		struct sk_buff *skb;
+		struct can_frame *cf;
+
+		skb = alloc_can_err_skb(priv->netdev, &cf);
+		if (skb) {
+			cf->can_id |= CAN_ERR_RESTARTED;
+
+			stats->rx_packets++;
+			stats->rx_bytes += cf->can_dlc;
+			netif_rx(skb);
+		} else {
+			netdev_err(priv->netdev,
+				   "No memory left for err_skb\n");
+		}
+
+		priv->can.can_stats.restarts++;
+		netif_carrier_on(priv->netdev);
+
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
+	}
+
+	stats->tx_packets++;
+	stats->tx_bytes += context->dlc;
+
+	spin_lock_irqsave(&priv->tx_contexts_lock, flags);
+
+	can_get_echo_skb(priv->netdev, context->echo_index);
+	context->echo_index = dev->max_tx_urbs;
+	--priv->active_tx_contexts;
+	netif_wake_queue(priv->netdev);
+
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, flags);
+}
+
+static int kvaser_usb_leaf_simple_cmd_async(struct kvaser_usb_net_priv *priv,
+					    u8 cmd_id)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_ATOMIC);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_simple);
+	cmd->id = cmd_id;
+	cmd->u.simple.channel = priv->channel;
+
+	err = kvaser_usb_send_cmd_async(priv, cmd, cmd->len);
+	if (err)
+		kfree(cmd);
+
+	return err;
+}
+
+static void
+kvaser_usb_leaf_rx_error_update_can_state(struct kvaser_usb_net_priv *priv,
+					const struct kvaser_usb_err_summary *es,
+					struct can_frame *cf)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct net_device_stats *stats = &priv->netdev->stats;
+	enum can_state cur_state, new_state, tx_state, rx_state;
+
+	netdev_dbg(priv->netdev, "Error status: 0x%02x\n", es->status);
+
+	new_state = priv->can.state;
+	cur_state = priv->can.state;
+
+	if (es->status & (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
+		new_state = CAN_STATE_BUS_OFF;
+	} else if (es->status & M16C_STATE_BUS_PASSIVE) {
+		new_state = CAN_STATE_ERROR_PASSIVE;
+	} else if (es->status & M16C_STATE_BUS_ERROR) {
+		/* Guard against spurious error events after a busoff */
+		if (cur_state < CAN_STATE_BUS_OFF) {
+			if (es->txerr >= 128 || es->rxerr >= 128)
+				new_state = CAN_STATE_ERROR_PASSIVE;
+			else if (es->txerr >= 96 || es->rxerr >= 96)
+				new_state = CAN_STATE_ERROR_WARNING;
+			else if (cur_state > CAN_STATE_ERROR_ACTIVE)
+				new_state = CAN_STATE_ERROR_ACTIVE;
+		}
+	}
+
+	if (!es->status)
+		new_state = CAN_STATE_ERROR_ACTIVE;
+
+	if (new_state != cur_state) {
+		tx_state = (es->txerr >= es->rxerr) ? new_state : 0;
+		rx_state = (es->txerr <= es->rxerr) ? new_state : 0;
+
+		can_change_state(priv->netdev, cf, tx_state, rx_state);
+	}
+
+	if (priv->can.restart_ms &&
+	    cur_state >= CAN_STATE_BUS_OFF &&
+	    new_state < CAN_STATE_BUS_OFF)
+		priv->can.can_stats.restarts++;
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		if (es->leaf.error_factor) {
+			priv->can.can_stats.bus_error++;
+			stats->rx_errors++;
+		}
+		break;
+	case KVASER_USBCAN:
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_TX_ERROR)
+			stats->tx_errors++;
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_RX_ERROR)
+			stats->rx_errors++;
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR)
+			priv->can.can_stats.bus_error++;
+		break;
+	}
+
+	priv->bec.txerr = es->txerr;
+	priv->bec.rxerr = es->rxerr;
+}
+
+static void kvaser_usb_leaf_rx_error(const struct kvaser_usb *dev,
+				     const struct kvaser_usb_err_summary *es)
+{
+	struct can_frame *cf;
+	struct can_frame tmp_cf = { .can_id = CAN_ERR_FLAG,
+				    .can_dlc = CAN_ERR_DLC };
+	struct sk_buff *skb;
+	struct net_device_stats *stats;
+	struct kvaser_usb_net_priv *priv;
+	enum can_state old_state, new_state;
+
+	if (es->channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", es->channel);
+		return;
+	}
+
+	priv = dev->nets[es->channel];
+	stats = &priv->netdev->stats;
+
+	/* Update all of the CAN interface's state and error counters before
+	 * trying any memory allocation that can actually fail with -ENOMEM.
+	 *
+	 * We send a temporary stack-allocated error CAN frame to
+	 * can_change_state() for the very same reason.
+	 *
+	 * TODO: Split can_change_state() responsibility between updating the
+	 * CAN interface's state and counters, and the setting up of CAN error
+	 * frame ID and data to userspace. Remove stack allocation afterwards.
+	 */
+	old_state = priv->can.state;
+	kvaser_usb_leaf_rx_error_update_can_state(priv, es, &tmp_cf);
+	new_state = priv->can.state;
+
+	skb = alloc_can_err_skb(priv->netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+	memcpy(cf, &tmp_cf, sizeof(*cf));
+
+	if (new_state != old_state) {
+		if (es->status &
+		    (M16C_STATE_BUS_OFF | M16C_STATE_BUS_RESET)) {
+			if (!priv->can.restart_ms)
+				kvaser_usb_leaf_simple_cmd_async(priv,
+								 CMD_STOP_CHIP);
+			netif_carrier_off(priv->netdev);
+		}
+
+		if (priv->can.restart_ms &&
+		    old_state >= CAN_STATE_BUS_OFF &&
+		    new_state < CAN_STATE_BUS_OFF) {
+			cf->can_id |= CAN_ERR_RESTARTED;
+			netif_carrier_on(priv->netdev);
+		}
+	}
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		if (es->leaf.error_factor) {
+			cf->can_id |= CAN_ERR_BUSERROR | CAN_ERR_PROT;
+
+			if (es->leaf.error_factor & M16C_EF_ACKE)
+				cf->data[3] = CAN_ERR_PROT_LOC_ACK;
+			if (es->leaf.error_factor & M16C_EF_CRCE)
+				cf->data[3] = CAN_ERR_PROT_LOC_CRC_SEQ;
+			if (es->leaf.error_factor & M16C_EF_FORME)
+				cf->data[2] |= CAN_ERR_PROT_FORM;
+			if (es->leaf.error_factor & M16C_EF_STFE)
+				cf->data[2] |= CAN_ERR_PROT_STUFF;
+			if (es->leaf.error_factor & M16C_EF_BITE0)
+				cf->data[2] |= CAN_ERR_PROT_BIT0;
+			if (es->leaf.error_factor & M16C_EF_BITE1)
+				cf->data[2] |= CAN_ERR_PROT_BIT1;
+			if (es->leaf.error_factor & M16C_EF_TRE)
+				cf->data[2] |= CAN_ERR_PROT_TX;
+		}
+		break;
+	case KVASER_USBCAN:
+		if (es->usbcan.error_state & USBCAN_ERROR_STATE_BUSERROR)
+			cf->can_id |= CAN_ERR_BUSERROR;
+		break;
+	}
+
+	cf->data[6] = es->txerr;
+	cf->data[7] = es->rxerr;
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+/* For USBCAN, report error to userspace if the channels's errors counter
+ * has changed, or we're the only channel seeing a bus error state.
+ */
+static void
+kvaser_usb_leaf_usbcan_conditionally_rx_error(const struct kvaser_usb *dev,
+					      struct kvaser_usb_err_summary *es)
+{
+	struct kvaser_usb_net_priv *priv;
+	unsigned int channel;
+	bool report_error;
+
+	channel = es->channel;
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+	report_error = false;
+
+	if (es->txerr != priv->bec.txerr) {
+		es->usbcan.error_state |= USBCAN_ERROR_STATE_TX_ERROR;
+		report_error = true;
+	}
+	if (es->rxerr != priv->bec.rxerr) {
+		es->usbcan.error_state |= USBCAN_ERROR_STATE_RX_ERROR;
+		report_error = true;
+	}
+	if ((es->status & M16C_STATE_BUS_ERROR) &&
+	    !(es->usbcan.other_ch_status & M16C_STATE_BUS_ERROR)) {
+		es->usbcan.error_state |= USBCAN_ERROR_STATE_BUSERROR;
+		report_error = true;
+	}
+
+	if (report_error)
+		kvaser_usb_leaf_rx_error(dev, es);
+}
+
+static void kvaser_usb_leaf_usbcan_rx_error(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_err_summary es = { };
+
+	switch (cmd->id) {
+	/* Sometimes errors are sent as unsolicited chip state events */
+	case CMD_CHIP_STATE_EVENT:
+		es.channel = cmd->u.usbcan.chip_state_event.channel;
+		es.status = cmd->u.usbcan.chip_state_event.status;
+		es.txerr = cmd->u.usbcan.chip_state_event.tx_errors_count;
+		es.rxerr = cmd->u.usbcan.chip_state_event.rx_errors_count;
+		kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es);
+		break;
+
+	case CMD_CAN_ERROR_EVENT:
+		es.channel = 0;
+		es.status = cmd->u.usbcan.error_event.status_ch0;
+		es.txerr = cmd->u.usbcan.error_event.tx_errors_count_ch0;
+		es.rxerr = cmd->u.usbcan.error_event.rx_errors_count_ch0;
+		es.usbcan.other_ch_status =
+			cmd->u.usbcan.error_event.status_ch1;
+		kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es);
+
+		/* The USBCAN firmware supports up to 2 channels.
+		 * Now that ch0 was checked, check if ch1 has any errors.
+		 */
+		if (dev->nchannels == MAX_USBCAN_NET_DEVICES) {
+			es.channel = 1;
+			es.status = cmd->u.usbcan.error_event.status_ch1;
+			es.txerr =
+				cmd->u.usbcan.error_event.tx_errors_count_ch1;
+			es.rxerr =
+				cmd->u.usbcan.error_event.rx_errors_count_ch1;
+			es.usbcan.other_ch_status =
+				cmd->u.usbcan.error_event.status_ch0;
+			kvaser_usb_leaf_usbcan_conditionally_rx_error(dev, &es);
+		}
+		break;
+
+	default:
+		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
+	}
+}
+
+static void kvaser_usb_leaf_leaf_rx_error(const struct kvaser_usb *dev,
+					  const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_err_summary es = { };
+
+	switch (cmd->id) {
+	case CMD_CAN_ERROR_EVENT:
+		es.channel = cmd->u.leaf.error_event.channel;
+		es.status = cmd->u.leaf.error_event.status;
+		es.txerr = cmd->u.leaf.error_event.tx_errors_count;
+		es.rxerr = cmd->u.leaf.error_event.rx_errors_count;
+		es.leaf.error_factor = cmd->u.leaf.error_event.error_factor;
+		break;
+	case CMD_LEAF_LOG_MESSAGE:
+		es.channel = cmd->u.leaf.log_message.channel;
+		es.status = cmd->u.leaf.log_message.data[0];
+		es.txerr = cmd->u.leaf.log_message.data[2];
+		es.rxerr = cmd->u.leaf.log_message.data[3];
+		es.leaf.error_factor = cmd->u.leaf.log_message.data[1];
+		break;
+	case CMD_CHIP_STATE_EVENT:
+		es.channel = cmd->u.leaf.chip_state_event.channel;
+		es.status = cmd->u.leaf.chip_state_event.status;
+		es.txerr = cmd->u.leaf.chip_state_event.tx_errors_count;
+		es.rxerr = cmd->u.leaf.chip_state_event.rx_errors_count;
+		es.leaf.error_factor = 0;
+		break;
+	default:
+		dev_err(&dev->intf->dev, "Invalid cmd id (%d)\n", cmd->id);
+		return;
+	}
+
+	kvaser_usb_leaf_rx_error(dev, &es);
+}
+
+static void kvaser_usb_leaf_rx_can_err(const struct kvaser_usb_net_priv *priv,
+				       const struct kvaser_cmd *cmd)
+{
+	if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
+					 MSG_FLAG_NERR)) {
+		struct net_device_stats *stats = &priv->netdev->stats;
+
+		netdev_err(priv->netdev, "Unknown error (flags: 0x%02x)\n",
+			   cmd->u.rx_can_header.flag);
+
+		stats->rx_errors++;
+		return;
+	}
+
+	if (cmd->u.rx_can_header.flag & MSG_FLAG_OVERRUN)
+		kvaser_usb_can_rx_over_error(priv->netdev);
+}
+
+static void kvaser_usb_leaf_rx_can_msg(const struct kvaser_usb *dev,
+				       const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct net_device_stats *stats;
+	u8 channel = cmd->u.rx_can_header.channel;
+	const u8 *rx_data = NULL;	/* GCC */
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+	stats = &priv->netdev->stats;
+
+	if ((cmd->u.rx_can_header.flag & MSG_FLAG_ERROR_FRAME) &&
+	    (dev->card_data.leaf.family == KVASER_LEAF &&
+	     cmd->id == CMD_LEAF_LOG_MESSAGE)) {
+		kvaser_usb_leaf_leaf_rx_error(dev, cmd);
+		return;
+	} else if (cmd->u.rx_can_header.flag & (MSG_FLAG_ERROR_FRAME |
+						MSG_FLAG_NERR |
+						MSG_FLAG_OVERRUN)) {
+		kvaser_usb_leaf_rx_can_err(priv, cmd);
+		return;
+	} else if (cmd->u.rx_can_header.flag & ~MSG_FLAG_REMOTE_FRAME) {
+		netdev_warn(priv->netdev,
+			    "Unhandled frame (flags: 0x%02x)\n",
+			    cmd->u.rx_can_header.flag);
+		return;
+	}
+
+	switch (dev->card_data.leaf.family) {
+	case KVASER_LEAF:
+		rx_data = cmd->u.leaf.rx_can.data;
+		break;
+	case KVASER_USBCAN:
+		rx_data = cmd->u.usbcan.rx_can.data;
+		break;
+	}
+
+	skb = alloc_can_skb(priv->netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	if (dev->card_data.leaf.family == KVASER_LEAF && cmd->id ==
+	    CMD_LEAF_LOG_MESSAGE) {
+		cf->can_id = le32_to_cpu(cmd->u.leaf.log_message.id);
+		if (cf->can_id & KVASER_EXTENDED_FRAME)
+			cf->can_id &= CAN_EFF_MASK | CAN_EFF_FLAG;
+		else
+			cf->can_id &= CAN_SFF_MASK;
+
+		cf->can_dlc = get_can_dlc(cmd->u.leaf.log_message.dlc);
+
+		if (cmd->u.leaf.log_message.flags & MSG_FLAG_REMOTE_FRAME)
+			cf->can_id |= CAN_RTR_FLAG;
+		else
+			memcpy(cf->data, &cmd->u.leaf.log_message.data,
+			       cf->can_dlc);
+	} else {
+		cf->can_id = ((rx_data[0] & 0x1f) << 6) | (rx_data[1] & 0x3f);
+
+		if (cmd->id == CMD_RX_EXT_MESSAGE) {
+			cf->can_id <<= 18;
+			cf->can_id |= ((rx_data[2] & 0x0f) << 14) |
+				      ((rx_data[3] & 0xff) << 6) |
+				      (rx_data[4] & 0x3f);
+			cf->can_id |= CAN_EFF_FLAG;
+		}
+
+		cf->can_dlc = get_can_dlc(rx_data[5]);
+
+		if (cmd->u.rx_can_header.flag & MSG_FLAG_REMOTE_FRAME)
+			cf->can_id |= CAN_RTR_FLAG;
+		else
+			memcpy(cf->data, &rx_data[6], cf->can_dlc);
+	}
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_leaf_start_chip_reply(const struct kvaser_usb *dev,
+					     const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	u8 channel = cmd->u.simple.channel;
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+
+	if (completion_done(&priv->start_comp) &&
+	    netif_queue_stopped(priv->netdev)) {
+		netif_wake_queue(priv->netdev);
+	} else {
+		netif_start_queue(priv->netdev);
+		complete(&priv->start_comp);
+	}
+}
+
+static void kvaser_usb_leaf_stop_chip_reply(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	u8 channel = cmd->u.simple.channel;
+
+	if (channel >= dev->nchannels) {
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+		return;
+	}
+
+	priv = dev->nets[channel];
+
+	complete(&priv->stop_comp);
+}
+
+static void kvaser_usb_leaf_handle_command(const struct kvaser_usb *dev,
+					   const struct kvaser_cmd *cmd)
+{
+	switch (cmd->id) {
+	case CMD_START_CHIP_REPLY:
+		kvaser_usb_leaf_start_chip_reply(dev, cmd);
+		break;
+
+	case CMD_STOP_CHIP_REPLY:
+		kvaser_usb_leaf_stop_chip_reply(dev, cmd);
+		break;
+
+	case CMD_RX_STD_MESSAGE:
+	case CMD_RX_EXT_MESSAGE:
+		kvaser_usb_leaf_rx_can_msg(dev, cmd);
+		break;
+
+	case CMD_LEAF_LOG_MESSAGE:
+		if (dev->card_data.leaf.family != KVASER_LEAF)
+			goto warn;
+		kvaser_usb_leaf_rx_can_msg(dev, cmd);
+		break;
+
+	case CMD_CHIP_STATE_EVENT:
+	case CMD_CAN_ERROR_EVENT:
+		if (dev->card_data.leaf.family == KVASER_LEAF)
+			kvaser_usb_leaf_leaf_rx_error(dev, cmd);
+		else
+			kvaser_usb_leaf_usbcan_rx_error(dev, cmd);
+		break;
+
+	case CMD_TX_ACKNOWLEDGE:
+		kvaser_usb_leaf_tx_acknowledge(dev, cmd);
+		break;
+
+	/* Ignored commands */
+	case CMD_USBCAN_CLOCK_OVERFLOW_EVENT:
+		if (dev->card_data.leaf.family != KVASER_USBCAN)
+			goto warn;
+		break;
+
+	case CMD_FLUSH_QUEUE_REPLY:
+		if (dev->card_data.leaf.family != KVASER_LEAF)
+			goto warn;
+		break;
+
+	default:
+warn:		dev_warn(&dev->intf->dev, "Unhandled command (%d)\n", cmd->id);
+		break;
+	}
+}
+
+static void kvaser_usb_leaf_read_bulk_callback(struct kvaser_usb *dev,
+					       void *buf, int len)
+{
+	struct kvaser_cmd *cmd;
+	int pos = 0;
+
+	while (pos <= len - CMD_HEADER_LEN) {
+		cmd = buf + pos;
+
+		/* The Kvaser firmware can only read and write commands that
+		 * does not cross the USB's endpoint wMaxPacketSize boundary.
+		 * If a follow-up command crosses such boundary, firmware puts
+		 * a placeholder zero-length command in its place then aligns
+		 * the real command to the next max packet size.
+		 *
+		 * Handle such cases or we're going to miss a significant
+		 * number of events in case of a heavy rx load on the bus.
+		 */
+		if (cmd->len == 0) {
+			pos = round_up(pos, le16_to_cpu
+						(dev->bulk_in->wMaxPacketSize));
+			continue;
+		}
+
+		if (pos + cmd->len > len) {
+			dev_err_ratelimited(&dev->intf->dev, "Format error\n");
+			break;
+		}
+
+		kvaser_usb_leaf_handle_command(dev, cmd);
+		pos += cmd->len;
+	}
+}
+
+static int kvaser_usb_leaf_set_opt_mode(const struct kvaser_usb_net_priv *priv)
+{
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = CMD_SET_CTRL_MODE;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_ctrl_mode);
+	cmd->u.ctrl_mode.tid = 0xff;
+	cmd->u.ctrl_mode.channel = priv->channel;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_SILENT;
+	else
+		cmd->u.ctrl_mode.ctrl_mode = KVASER_CTRL_MODE_NORMAL;
+
+	rc = kvaser_usb_send_cmd(priv->dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_start_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->start_comp);
+
+	err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_START_CHIP,
+					      priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->start_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_stop_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->stop_comp);
+
+	err = kvaser_usb_leaf_send_simple_cmd(priv->dev, CMD_STOP_CHIP,
+					      priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->stop_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_reset_chip(struct kvaser_usb *dev, int channel)
+{
+	return kvaser_usb_leaf_send_simple_cmd(dev, CMD_RESET_CHIP, channel);
+}
+
+static int kvaser_usb_leaf_flush_queue(struct kvaser_usb_net_priv *priv)
+{
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = CMD_FLUSH_QUEUE;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_flush_queue);
+	cmd->u.flush_queue.channel = priv->channel;
+	cmd->u.flush_queue.flags = 0x00;
+
+	rc = kvaser_usb_send_cmd(priv->dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_init_card(struct kvaser_usb *dev)
+{
+	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
+
+	dev->cfg = &kvaser_usb_leaf_dev_cfg;
+	card_data->ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+
+	return 0;
+}
+
+static const struct can_bittiming_const kvaser_usb_leaf_bittiming_const = {
+	.name = "kvaser_usb",
+	.tseg1_min = KVASER_USB_TSEG1_MIN,
+	.tseg1_max = KVASER_USB_TSEG1_MAX,
+	.tseg2_min = KVASER_USB_TSEG2_MIN,
+	.tseg2_max = KVASER_USB_TSEG2_MAX,
+	.sjw_max = KVASER_USB_SJW_MAX,
+	.brp_min = KVASER_USB_BRP_MIN,
+	.brp_max = KVASER_USB_BRP_MAX,
+	.brp_inc = KVASER_USB_BRP_INC,
+};
+
+static int kvaser_usb_leaf_set_bittiming(struct net_device *netdev)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	int rc;
+
+	cmd = kmalloc(sizeof(*cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->id = CMD_SET_BUS_PARAMS;
+	cmd->len = CMD_HEADER_LEN + sizeof(struct kvaser_cmd_busparams);
+	cmd->u.busparams.channel = priv->channel;
+	cmd->u.busparams.tid = 0xff;
+	cmd->u.busparams.bitrate = cpu_to_le32(bt->bitrate);
+	cmd->u.busparams.sjw = bt->sjw;
+	cmd->u.busparams.tseg1 = bt->prop_seg + bt->phase_seg1;
+	cmd->u.busparams.tseg2 = bt->phase_seg2;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+		cmd->u.busparams.no_samp = 3;
+	else
+		cmd->u.busparams.no_samp = 1;
+
+	rc = kvaser_usb_send_cmd(dev, cmd, cmd->len);
+
+	kfree(cmd);
+	return rc;
+}
+
+static int kvaser_usb_leaf_set_mode(struct net_device *netdev,
+				    enum can_mode mode)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	int err;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		err = kvaser_usb_leaf_simple_cmd_async(priv, CMD_START_CHIP);
+		if (err)
+			return err;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_get_berr_counter(const struct net_device *netdev,
+					    struct can_berr_counter *bec)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+
+	*bec = priv->bec;
+
+	return 0;
+}
+
+static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev)
+{
+	const struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *endpoint;
+	int i;
+
+	iface_desc = &dev->intf->altsetting[0];
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
+		endpoint = &iface_desc->endpoint[i].desc;
+
+		if (!dev->bulk_in && usb_endpoint_is_bulk_in(endpoint))
+			dev->bulk_in = endpoint;
+
+		if (!dev->bulk_out && usb_endpoint_is_bulk_out(endpoint))
+			dev->bulk_out = endpoint;
+
+		/* use first bulk endpoint for in and out */
+		if (dev->bulk_in && dev->bulk_out)
+			return 0;
+	}
+
+	return -ENODEV;
+}
+
+const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = {
+	.dev_set_mode = kvaser_usb_leaf_set_mode,
+	.dev_set_bittiming = kvaser_usb_leaf_set_bittiming,
+	.dev_get_berr_counter = kvaser_usb_leaf_get_berr_counter,
+	.dev_setup_endpoints = kvaser_usb_leaf_setup_endpoints,
+	.dev_init_card = kvaser_usb_leaf_init_card,
+	.dev_get_software_info = kvaser_usb_leaf_get_software_info,
+	.dev_get_card_info = kvaser_usb_leaf_get_card_info,
+	.dev_set_opt_mode = kvaser_usb_leaf_set_opt_mode,
+	.dev_start_chip = kvaser_usb_leaf_start_chip,
+	.dev_stop_chip = kvaser_usb_leaf_stop_chip,
+	.dev_reset_chip = kvaser_usb_leaf_reset_chip,
+	.dev_flush_queue = kvaser_usb_leaf_flush_queue,
+	.dev_read_bulk_callback = kvaser_usb_leaf_read_bulk_callback,
+	.dev_frame_to_cmd = kvaser_usb_leaf_frame_to_cmd,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_leaf_dev_cfg = {
+	.clock = {
+		.freq = CAN_USB_CLOCK,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_leaf_bittiming_const,
+};
-- 
cgit v1.2.3


From aec5fb2268b700f3c4e8481ab431eefcd33893f6 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <extja@kvaser.com>
Date: Wed, 18 Jul 2018 23:29:29 +0200
Subject: can: kvaser_usb: Add support for Kvaser USB hydra family

This patch adds support for a new Kvaser USB family, denoted hydra.
The hydra family currently contains USB devices with one CAN channel
up to five. There are devices with and without CAN FD support.

Signed-off-by: Jimmy Assarsson <extja@kvaser.com>
Signed-off-by: Christer Beskow <chbe@kvaser.com>
Signed-off-by: Nicklas Johansson <extnj@kvaser.com>
Signed-off-by: Martin Henriksson <mh@kvaser.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/Kconfig                       |   14 +-
 drivers/net/can/usb/kvaser_usb/Makefile           |    2 +-
 drivers/net/can/usb/kvaser_usb/kvaser_usb.h       |   44 +-
 drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c  |   72 +-
 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 2028 +++++++++++++++++++++
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c  |    3 +
 6 files changed, 2151 insertions(+), 12 deletions(-)
 create mode 100644 drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c

diff --git a/drivers/net/can/usb/Kconfig b/drivers/net/can/usb/Kconfig
index 87b7aa15d175..750d04d9e2ae 100644
--- a/drivers/net/can/usb/Kconfig
+++ b/drivers/net/can/usb/Kconfig
@@ -32,7 +32,7 @@ config CAN_KVASER_USB
 	tristate "Kvaser CAN/USB interface"
 	---help---
 	  This driver adds support for Kvaser CAN/USB devices like Kvaser
-	  Leaf Light and Kvaser USBcan II.
+	  Leaf Light, Kvaser USBcan II and Kvaser Memorator Pro 5xHS.
 
 	  The driver provides support for the following devices:
 	    - Kvaser Leaf Light
@@ -61,6 +61,18 @@ config CAN_KVASER_USB
 	    - Kvaser Memorator HS/HS
 	    - Kvaser Memorator HS/LS
 	    - Scania VCI2 (if you have the Kvaser logo on top)
+	    - Kvaser BlackBird v2
+	    - Kvaser Leaf Pro HS v2
+	    - Kvaser Hybrid 2xCAN/LIN
+	    - Kvaser Hybrid Pro 2xCAN/LIN
+	    - Kvaser Memorator 2xHS v2
+	    - Kvaser Memorator Pro 2xHS v2
+	    - Kvaser Memorator Pro 5xHS
+	    - Kvaser USBcan Light 4xHS
+	    - Kvaser USBcan Pro 2xHS v2
+	    - Kvaser USBcan Pro 5xHS
+	    - ATI Memorator Pro 2xHS v2
+	    - ATI USBcan Pro 2xHS v2
 
 	  If unsure, say N.
 
diff --git a/drivers/net/can/usb/kvaser_usb/Makefile b/drivers/net/can/usb/kvaser_usb/Makefile
index 37b69dbc71b0..9f41ddab6a5a 100644
--- a/drivers/net/can/usb/kvaser_usb/Makefile
+++ b/drivers/net/can/usb/kvaser_usb/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_CAN_KVASER_USB) += kvaser_usb.o
-kvaser_usb-y = kvaser_usb_core.o kvaser_usb_leaf.o
+kvaser_usb-y = kvaser_usb_core.o kvaser_usb_leaf.o kvaser_usb_hydra.o
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
index 82e6ecad034d..390b6bde883c 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb.h
@@ -3,6 +3,7 @@
  *  - Kvaser linux leaf driver (version 4.78)
  *  - CAN driver for esd CAN-USB/2
  *  - Kvaser linux usbcanII driver (version 5.3)
+ *  - Kvaser linux mhydra driver (version 5.24)
  *
  * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
  * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
@@ -13,8 +14,10 @@
 #ifndef KVASER_USB_H
 #define KVASER_USB_H
 
-/* Kvaser USB CAN dongles are divided into two major families:
- * - Leaf: Based on Renesas M32C, running firmware labeled as 'filo'
+/* Kvaser USB CAN dongles are divided into three major platforms:
+ * - Hydra: Running firmware labeled as 'mhydra'
+ * - Leaf: Based on Renesas M32C or Freescale i.MX28, running firmware labeled
+ *         as 'filo'
  * - UsbcanII: Based on Renesas M16C, running firmware labeled as 'helios'
  */
 
@@ -30,12 +33,17 @@
 #define KVASER_USB_MAX_TX_URBS			128
 #define KVASER_USB_TIMEOUT			1000 /* msecs */
 #define KVASER_USB_RX_BUFFER_SIZE		3072
-#define KVASER_USB_MAX_NET_DEVICES		3
+#define KVASER_USB_MAX_NET_DEVICES		5
 
 /* USB devices features */
 #define KVASER_USB_HAS_SILENT_MODE		BIT(0)
 #define KVASER_USB_HAS_TXRX_ERRORS		BIT(1)
 
+/* Device capabilities */
+#define KVASER_USB_CAP_BERR_CAP			0x01
+#define KVASER_USB_CAP_EXT_CAP			0x02
+#define KVASER_USB_HYDRA_CAP_EXT_CMD		0x04
+
 struct kvaser_usb_dev_cfg;
 
 enum kvaser_usb_leaf_family {
@@ -43,11 +51,26 @@ enum kvaser_usb_leaf_family {
 	KVASER_USBCAN,
 };
 
+#define KVASER_USB_HYDRA_MAX_CMD_LEN		128
+struct kvaser_usb_dev_card_data_hydra {
+	u8 channel_to_he[KVASER_USB_MAX_NET_DEVICES];
+	u8 sysdbg_he;
+	spinlock_t transid_lock; /* lock for transid */
+	u16 transid;
+	/* lock for usb_rx_leftover and usb_rx_leftover_len */
+	spinlock_t usb_rx_leftover_lock;
+	u8 usb_rx_leftover[KVASER_USB_HYDRA_MAX_CMD_LEN];
+	u8 usb_rx_leftover_len;
+};
 struct kvaser_usb_dev_card_data {
 	u32 ctrlmode_supported;
-	struct {
-		enum kvaser_usb_leaf_family family;
-	} leaf;
+	u32 capabilities;
+	union {
+		struct {
+			enum kvaser_usb_leaf_family family;
+		} leaf;
+		struct kvaser_usb_dev_card_data_hydra hydra;
+	};
 };
 
 /* Context for an outstanding, not yet ACKed, transmission */
@@ -89,7 +112,7 @@ struct kvaser_usb_net_priv {
 	struct net_device *netdev;
 	int channel;
 
-	struct completion start_comp, stop_comp;
+	struct completion start_comp, stop_comp, flush_comp;
 	struct usb_anchor tx_submitted;
 
 	spinlock_t tx_contexts_lock; /* lock for active_tx_contexts */
@@ -101,12 +124,15 @@ struct kvaser_usb_net_priv {
  * struct kvaser_usb_dev_ops - Device specific functions
  * @dev_set_mode:		used for can.do_set_mode
  * @dev_set_bittiming:		used for can.do_set_bittiming
+ * @dev_set_data_bittiming:	used for can.do_set_data_bittiming
  * @dev_get_berr_counter:	used for can.do_get_berr_counter
  *
  * @dev_setup_endpoints:	setup USB in and out endpoints
  * @dev_init_card:		initialize card
  * @dev_get_software_info:	get software info
+ * @dev_get_software_details:	get software details
  * @dev_get_card_info:		get card info
+ * @dev_get_capabilities:	discover device capabilities
  *
  * @dev_set_opt_mode:		set ctrlmod
  * @dev_start_chip:		start the CAN controller
@@ -119,12 +145,15 @@ struct kvaser_usb_net_priv {
 struct kvaser_usb_dev_ops {
 	int (*dev_set_mode)(struct net_device *netdev, enum can_mode mode);
 	int (*dev_set_bittiming)(struct net_device *netdev);
+	int (*dev_set_data_bittiming)(struct net_device *netdev);
 	int (*dev_get_berr_counter)(const struct net_device *netdev,
 				    struct can_berr_counter *bec);
 	int (*dev_setup_endpoints)(struct kvaser_usb *dev);
 	int (*dev_init_card)(struct kvaser_usb *dev);
 	int (*dev_get_software_info)(struct kvaser_usb *dev);
+	int (*dev_get_software_details)(struct kvaser_usb *dev);
 	int (*dev_get_card_info)(struct kvaser_usb *dev);
+	int (*dev_get_capabilities)(struct kvaser_usb *dev);
 	int (*dev_set_opt_mode)(const struct kvaser_usb_net_priv *priv);
 	int (*dev_start_chip)(struct kvaser_usb_net_priv *priv);
 	int (*dev_stop_chip)(struct kvaser_usb_net_priv *priv);
@@ -144,6 +173,7 @@ struct kvaser_usb_dev_cfg {
 	const struct can_bittiming_const * const data_bittiming_const;
 };
 
+extern const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops;
 extern const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops;
 
 int kvaser_usb_recv_cmd(const struct kvaser_usb *dev, void *cmd, int len,
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
index 55ac489037fc..b939a4c10b84 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_core.c
@@ -3,6 +3,7 @@
  *  - Kvaser linux leaf driver (version 4.78)
  *  - CAN driver for esd CAN-USB/2
  *  - Kvaser linux usbcanII driver (version 5.3)
+ *  - Kvaser linux mhydra driver (version 5.24)
  *
  * Copyright (C) 2002-2018 KVASER AB, Sweden. All rights reserved.
  * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
@@ -64,10 +65,26 @@
 #define USB_USBCAN2_PRODUCT_ID			4
 #define USB_MEMORATOR_PRODUCT_ID		5
 
+/* Kvaser Minihydra USB devices product ids */
+#define USB_BLACKBIRD_V2_PRODUCT_ID		258
+#define USB_MEMO_PRO_5HS_PRODUCT_ID		260
+#define USB_USBCAN_PRO_5HS_PRODUCT_ID		261
+#define USB_USBCAN_LIGHT_4HS_PRODUCT_ID		262
+#define USB_LEAF_PRO_HS_V2_PRODUCT_ID		263
+#define USB_USBCAN_PRO_2HS_V2_PRODUCT_ID	264
+#define USB_MEMO_2HS_PRODUCT_ID			265
+#define USB_MEMO_PRO_2HS_V2_PRODUCT_ID		266
+#define USB_HYBRID_CANLIN_PRODUCT_ID		267
+#define USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID	268
+#define USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID	269
+#define USB_HYBRID_PRO_CANLIN_PRODUCT_ID	270
+
 static inline bool kvaser_is_leaf(const struct usb_device_id *id)
 {
-	return id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
-	       id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID;
+	return (id->idProduct >= USB_LEAF_DEVEL_PRODUCT_ID &&
+		id->idProduct <= USB_CAN_R_PRODUCT_ID) ||
+		(id->idProduct >= USB_LEAF_LITE_V2_PRODUCT_ID &&
+		 id->idProduct <= USB_MINI_PCIE_2HS_PRODUCT_ID);
 }
 
 static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
@@ -76,6 +93,12 @@ static inline bool kvaser_is_usbcan(const struct usb_device_id *id)
 	       id->idProduct <= USB_MEMORATOR_PRODUCT_ID;
 }
 
+static inline bool kvaser_is_hydra(const struct usb_device_id *id)
+{
+	return id->idProduct >= USB_BLACKBIRD_V2_PRODUCT_ID &&
+	       id->idProduct <= USB_HYBRID_PRO_CANLIN_PRODUCT_ID;
+}
+
 static const struct usb_device_id kvaser_usb_table[] = {
 	/* Leaf USB product IDs */
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_DEVEL_PRODUCT_ID) },
@@ -140,6 +163,20 @@ static const struct usb_device_id kvaser_usb_table[] = {
 		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
 	{ USB_DEVICE(KVASER_VENDOR_ID, USB_VCI2_PRODUCT_ID),
 		.driver_info = KVASER_USB_HAS_TXRX_ERRORS },
+
+	/* Minihydra USB product IDs */
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_BLACKBIRD_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_5HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_5HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_LIGHT_4HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_LEAF_PRO_HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_2HS_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_MEMO_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_CANLIN_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_USBCAN_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_ATI_MEMO_PRO_2HS_V2_PRODUCT_ID) },
+	{ USB_DEVICE(KVASER_VENDOR_ID, USB_HYBRID_PRO_CANLIN_PRODUCT_ID) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, kvaser_usb_table);
@@ -633,13 +670,20 @@ static int kvaser_usb_init_one(struct kvaser_usb *dev,
 	priv->can.bittiming_const = dev->cfg->bittiming_const;
 	priv->can.do_set_bittiming = dev->ops->dev_set_bittiming;
 	priv->can.do_set_mode = dev->ops->dev_set_mode;
-	if (id->driver_info & KVASER_USB_HAS_TXRX_ERRORS)
+	if ((id->driver_info & KVASER_USB_HAS_TXRX_ERRORS) ||
+	    (priv->dev->card_data.capabilities & KVASER_USB_CAP_BERR_CAP))
 		priv->can.do_get_berr_counter = dev->ops->dev_get_berr_counter;
 	if (id->driver_info & KVASER_USB_HAS_SILENT_MODE)
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_LISTENONLY;
 
 	priv->can.ctrlmode_supported |= dev->card_data.ctrlmode_supported;
 
+	if (priv->can.ctrlmode_supported & CAN_CTRLMODE_FD) {
+		priv->can.data_bittiming_const = dev->cfg->data_bittiming_const;
+		priv->can.do_set_data_bittiming =
+					dev->ops->dev_set_data_bittiming;
+	}
+
 	netdev->flags |= IFF_ECHO;
 
 	netdev->netdev_ops = &kvaser_usb_netdev_ops;
@@ -679,6 +723,8 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	} else if (kvaser_is_usbcan(id)) {
 		dev->card_data.leaf.family = KVASER_USBCAN;
 		dev->ops = &kvaser_usb_leaf_dev_ops;
+	} else if (kvaser_is_hydra(id)) {
+		dev->ops = &kvaser_usb_hydra_dev_ops;
 	} else {
 		dev_err(&intf->dev,
 			"Product ID (%d) is not a supported Kvaser USB device\n",
@@ -701,6 +747,7 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 	usb_set_intfdata(intf, dev);
 
 	dev->card_data.ctrlmode_supported = 0;
+	dev->card_data.capabilities = 0;
 	err = dev->ops->dev_init_card(dev);
 	if (err) {
 		dev_err(&intf->dev,
@@ -715,6 +762,15 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 		return err;
 	}
 
+	if (dev->ops->dev_get_software_details) {
+		err = dev->ops->dev_get_software_details(dev);
+		if (err) {
+			dev_err(&intf->dev,
+				"Cannot get software details, error %d\n", err);
+			return err;
+		}
+	}
+
 	if (WARN_ON(!dev->cfg))
 		return -ENODEV;
 
@@ -731,6 +787,16 @@ static int kvaser_usb_probe(struct usb_interface *intf,
 		return err;
 	}
 
+	if (dev->ops->dev_get_capabilities) {
+		err = dev->ops->dev_get_capabilities(dev);
+		if (err) {
+			dev_err(&intf->dev,
+				"Cannot get capabilities, error %d\n", err);
+			kvaser_usb_remove_interfaces(dev);
+			return err;
+		}
+	}
+
 	for (i = 0; i < dev->nchannels; i++) {
 		err = kvaser_usb_init_one(dev, id, i);
 		if (err) {
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
new file mode 100644
index 000000000000..c084bae5ec0a
--- /dev/null
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_hydra.c
@@ -0,0 +1,2028 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Parts of this driver are based on the following:
+ *  - Kvaser linux mhydra driver (version 5.24)
+ *  - CAN driver for esd CAN-USB/2
+ *
+ * Copyright (C) 2018 KVASER AB, Sweden. All rights reserved.
+ * Copyright (C) 2010 Matthias Fuchs <matthias.fuchs@esd.eu>, esd gmbh
+ *
+ * Known issues:
+ *  - Transition from CAN_STATE_ERROR_WARNING to CAN_STATE_ERROR_ACTIVE is only
+ *    reported after a call to do_get_berr_counter(), since firmware does not
+ *    distinguish between ERROR_WARNING and ERROR_ACTIVE.
+ *  - Hardware timestamps are not set for CAN Tx frames.
+ */
+
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/gfp.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/usb.h>
+
+#include <linux/can.h>
+#include <linux/can/dev.h>
+#include <linux/can/error.h>
+#include <linux/can/netlink.h>
+
+#include "kvaser_usb.h"
+
+/* Forward declarations */
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_kcan;
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc;
+
+#define KVASER_USB_HYDRA_BULK_EP_IN_ADDR	0x82
+#define KVASER_USB_HYDRA_BULK_EP_OUT_ADDR	0x02
+
+#define KVASER_USB_HYDRA_MAX_TRANSID		0xff
+#define KVASER_USB_HYDRA_MIN_TRANSID		0x01
+
+/* Minihydra command IDs */
+#define CMD_SET_BUSPARAMS_REQ			16
+#define CMD_GET_CHIP_STATE_REQ			19
+#define CMD_CHIP_STATE_EVENT			20
+#define CMD_SET_DRIVERMODE_REQ			21
+#define CMD_START_CHIP_REQ			26
+#define CMD_START_CHIP_RESP			27
+#define CMD_STOP_CHIP_REQ			28
+#define CMD_STOP_CHIP_RESP			29
+#define CMD_TX_CAN_MESSAGE			33
+#define CMD_GET_CARD_INFO_REQ			34
+#define CMD_GET_CARD_INFO_RESP			35
+#define CMD_GET_SOFTWARE_INFO_REQ		38
+#define CMD_GET_SOFTWARE_INFO_RESP		39
+#define CMD_ERROR_EVENT				45
+#define CMD_FLUSH_QUEUE				48
+#define CMD_TX_ACKNOWLEDGE			50
+#define CMD_FLUSH_QUEUE_RESP			66
+#define CMD_SET_BUSPARAMS_FD_REQ		69
+#define CMD_SET_BUSPARAMS_FD_RESP		70
+#define CMD_SET_BUSPARAMS_RESP			85
+#define CMD_GET_CAPABILITIES_REQ		95
+#define CMD_GET_CAPABILITIES_RESP		96
+#define CMD_RX_MESSAGE				106
+#define CMD_MAP_CHANNEL_REQ			200
+#define CMD_MAP_CHANNEL_RESP			201
+#define CMD_GET_SOFTWARE_DETAILS_REQ		202
+#define CMD_GET_SOFTWARE_DETAILS_RESP		203
+#define CMD_EXTENDED				255
+
+/* Minihydra extended command IDs */
+#define CMD_TX_CAN_MESSAGE_FD			224
+#define CMD_TX_ACKNOWLEDGE_FD			225
+#define CMD_RX_MESSAGE_FD			226
+
+/* Hydra commands are handled by different threads in firmware.
+ * The threads are denoted hydra entity (HE). Each HE got a unique 6-bit
+ * address. The address is used in hydra commands to get/set source and
+ * destination HE. There are two predefined HE addresses, the remaining
+ * addresses are different between devices and firmware versions. Hence, we need
+ * to enumerate the addresses (see kvaser_usb_hydra_map_channel()).
+ */
+
+/* Well-known HE addresses */
+#define KVASER_USB_HYDRA_HE_ADDRESS_ROUTER	0x00
+#define KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL	0x3e
+
+#define KVASER_USB_HYDRA_TRANSID_CANHE		0x40
+#define KVASER_USB_HYDRA_TRANSID_SYSDBG		0x61
+
+struct kvaser_cmd_map_ch_req {
+	char name[16];
+	u8 channel;
+	u8 reserved[11];
+} __packed;
+
+struct kvaser_cmd_map_ch_res {
+	u8 he_addr;
+	u8 channel;
+	u8 reserved[26];
+} __packed;
+
+struct kvaser_cmd_card_info {
+	__le32 serial_number;
+	__le32 clock_res;
+	__le32 mfg_date;
+	__le32 ean[2];
+	u8 hw_version;
+	u8 usb_mode;
+	u8 hw_type;
+	u8 reserved0;
+	u8 nchannels;
+	u8 reserved1[3];
+} __packed;
+
+struct kvaser_cmd_sw_info {
+	u8 reserved0[8];
+	__le16 max_outstanding_tx;
+	u8 reserved1[18];
+} __packed;
+
+struct kvaser_cmd_sw_detail_req {
+	u8 use_ext_cmd;
+	u8 reserved[27];
+} __packed;
+
+/* Software detail flags */
+#define KVASER_USB_HYDRA_SW_FLAG_FW_BETA	BIT(2)
+#define KVASER_USB_HYDRA_SW_FLAG_FW_BAD		BIT(4)
+#define KVASER_USB_HYDRA_SW_FLAG_FREQ_80M	BIT(5)
+#define KVASER_USB_HYDRA_SW_FLAG_EXT_CMD	BIT(9)
+#define KVASER_USB_HYDRA_SW_FLAG_CANFD		BIT(10)
+#define KVASER_USB_HYDRA_SW_FLAG_NONISO		BIT(11)
+#define KVASER_USB_HYDRA_SW_FLAG_EXT_CAP	BIT(12)
+struct kvaser_cmd_sw_detail_res {
+	__le32 sw_flags;
+	__le32 sw_version;
+	__le32 sw_name;
+	__le32 ean[2];
+	__le32 max_bitrate;
+	u8 reserved[4];
+} __packed;
+
+/* Sub commands for cap_req and cap_res */
+#define KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE	0x02
+#define KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT	0x05
+#define KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT	0x06
+struct kvaser_cmd_cap_req {
+	__le16 cap_cmd;
+	u8 reserved[26];
+} __packed;
+
+/* Status codes for cap_res */
+#define KVASER_USB_HYDRA_CAP_STAT_OK		0x00
+#define KVASER_USB_HYDRA_CAP_STAT_NOT_IMPL	0x01
+#define KVASER_USB_HYDRA_CAP_STAT_UNAVAIL	0x02
+struct kvaser_cmd_cap_res {
+	__le16 cap_cmd;
+	__le16 status;
+	__le32 mask;
+	__le32 value;
+	u8 reserved[16];
+} __packed;
+
+/* CMD_ERROR_EVENT error codes */
+#define KVASER_USB_HYDRA_ERROR_EVENT_CAN	0x01
+#define KVASER_USB_HYDRA_ERROR_EVENT_PARAM	0x09
+struct kvaser_cmd_error_event {
+	__le16 timestamp[3];
+	u8 reserved;
+	u8 error_code;
+	__le16 info1;
+	__le16 info2;
+} __packed;
+
+/* Chip state status flags. Used for chip_state_event and err_frame_data. */
+#define KVASER_USB_HYDRA_BUS_ERR_ACT		0x00
+#define KVASER_USB_HYDRA_BUS_ERR_PASS		BIT(5)
+#define KVASER_USB_HYDRA_BUS_BUS_OFF		BIT(6)
+struct kvaser_cmd_chip_state_event {
+	__le16 timestamp[3];
+	u8 tx_err_counter;
+	u8 rx_err_counter;
+	u8 bus_status;
+	u8 reserved[19];
+} __packed;
+
+/* Busparam modes */
+#define KVASER_USB_HYDRA_BUS_MODE_CAN		0x00
+#define KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO	0x01
+#define KVASER_USB_HYDRA_BUS_MODE_NONISO	0x02
+struct kvaser_cmd_set_busparams {
+	__le32 bitrate;
+	u8 tseg1;
+	u8 tseg2;
+	u8 sjw;
+	u8 nsamples;
+	u8 reserved0[4];
+	__le32 bitrate_d;
+	u8 tseg1_d;
+	u8 tseg2_d;
+	u8 sjw_d;
+	u8 nsamples_d;
+	u8 canfd_mode;
+	u8 reserved1[7];
+} __packed;
+
+/* Ctrl modes */
+#define KVASER_USB_HYDRA_CTRLMODE_NORMAL	0x01
+#define KVASER_USB_HYDRA_CTRLMODE_LISTEN	0x02
+struct kvaser_cmd_set_ctrlmode {
+	u8 mode;
+	u8 reserved[27];
+} __packed;
+
+struct kvaser_err_frame_data {
+	u8 bus_status;
+	u8 reserved0;
+	u8 tx_err_counter;
+	u8 rx_err_counter;
+	u8 reserved1[4];
+} __packed;
+
+struct kvaser_cmd_rx_can {
+	u8 cmd_len;
+	u8 cmd_no;
+	u8 channel;
+	u8 flags;
+	__le16 timestamp[3];
+	u8 dlc;
+	u8 padding;
+	__le32 id;
+	union {
+		u8 data[8];
+		struct kvaser_err_frame_data err_frame_data;
+	};
+} __packed;
+
+/* Extended CAN ID flag. Used in rx_can and tx_can */
+#define KVASER_USB_HYDRA_EXTENDED_FRAME_ID	BIT(31)
+struct kvaser_cmd_tx_can {
+	__le32 id;
+	u8 data[8];
+	u8 dlc;
+	u8 flags;
+	__le16 transid;
+	u8 channel;
+	u8 reserved[11];
+} __packed;
+
+struct kvaser_cmd_header {
+	u8 cmd_no;
+	/* The destination HE address is stored in 0..5 of he_addr.
+	 * The upper part of source HE address is stored in 6..7 of he_addr, and
+	 * the lower part is stored in 12..15 of transid.
+	 */
+	u8 he_addr;
+	__le16 transid;
+} __packed;
+
+struct kvaser_cmd {
+	struct kvaser_cmd_header header;
+	union {
+		struct kvaser_cmd_map_ch_req map_ch_req;
+		struct kvaser_cmd_map_ch_res map_ch_res;
+
+		struct kvaser_cmd_card_info card_info;
+		struct kvaser_cmd_sw_info sw_info;
+		struct kvaser_cmd_sw_detail_req sw_detail_req;
+		struct kvaser_cmd_sw_detail_res sw_detail_res;
+
+		struct kvaser_cmd_cap_req cap_req;
+		struct kvaser_cmd_cap_res cap_res;
+
+		struct kvaser_cmd_error_event error_event;
+
+		struct kvaser_cmd_set_busparams set_busparams_req;
+
+		struct kvaser_cmd_chip_state_event chip_state_event;
+
+		struct kvaser_cmd_set_ctrlmode set_ctrlmode;
+
+		struct kvaser_cmd_rx_can rx_can;
+		struct kvaser_cmd_tx_can tx_can;
+	} __packed;
+} __packed;
+
+/* CAN frame flags. Used in rx_can, ext_rx_can, tx_can and ext_tx_can */
+#define KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME	BIT(0)
+#define KVASER_USB_HYDRA_CF_FLAG_OVERRUN	BIT(1)
+#define KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME	BIT(4)
+#define KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID	BIT(5)
+/* CAN frame flags. Used in ext_rx_can and ext_tx_can */
+#define KVASER_USB_HYDRA_CF_FLAG_OSM_NACK	BIT(12)
+#define KVASER_USB_HYDRA_CF_FLAG_ABL		BIT(13)
+#define KVASER_USB_HYDRA_CF_FLAG_FDF		BIT(16)
+#define KVASER_USB_HYDRA_CF_FLAG_BRS		BIT(17)
+#define KVASER_USB_HYDRA_CF_FLAG_ESI		BIT(18)
+
+/* KCAN packet header macros. Used in ext_rx_can and ext_tx_can */
+#define KVASER_USB_KCAN_DATA_DLC_BITS		4
+#define KVASER_USB_KCAN_DATA_DLC_SHIFT		8
+#define KVASER_USB_KCAN_DATA_DLC_MASK \
+				GENMASK(KVASER_USB_KCAN_DATA_DLC_BITS - 1 + \
+				KVASER_USB_KCAN_DATA_DLC_SHIFT, \
+				KVASER_USB_KCAN_DATA_DLC_SHIFT)
+
+#define KVASER_USB_KCAN_DATA_BRS		BIT(14)
+#define KVASER_USB_KCAN_DATA_FDF		BIT(15)
+#define KVASER_USB_KCAN_DATA_OSM		BIT(16)
+#define KVASER_USB_KCAN_DATA_AREQ		BIT(31)
+#define KVASER_USB_KCAN_DATA_SRR		BIT(31)
+#define KVASER_USB_KCAN_DATA_RTR		BIT(29)
+#define KVASER_USB_KCAN_DATA_IDE		BIT(30)
+struct kvaser_cmd_ext_rx_can {
+	__le32 flags;
+	__le32 id;
+	__le32 kcan_id;
+	__le32 kcan_header;
+	__le64 timestamp;
+	union {
+		u8 kcan_payload[64];
+		struct kvaser_err_frame_data err_frame_data;
+	};
+} __packed;
+
+struct kvaser_cmd_ext_tx_can {
+	__le32 flags;
+	__le32 id;
+	__le32 kcan_id;
+	__le32 kcan_header;
+	u8 databytes;
+	u8 dlc;
+	u8 reserved[6];
+	u8 kcan_payload[64];
+} __packed;
+
+struct kvaser_cmd_ext_tx_ack {
+	__le32 flags;
+	u8 reserved0[4];
+	__le64 timestamp;
+	u8 reserved1[8];
+} __packed;
+
+/* struct for extended commands (CMD_EXTENDED) */
+struct kvaser_cmd_ext {
+	struct kvaser_cmd_header header;
+	__le16 len;
+	u8 cmd_no_ext;
+	u8 reserved;
+
+	union {
+		struct kvaser_cmd_ext_rx_can rx_can;
+		struct kvaser_cmd_ext_tx_can tx_can;
+		struct kvaser_cmd_ext_tx_ack tx_ack;
+	} __packed;
+} __packed;
+
+static const struct can_bittiming_const kvaser_usb_hydra_kcan_bittiming_c = {
+	.name = "kvaser_usb_kcan",
+	.tseg1_min = 1,
+	.tseg1_max = 255,
+	.tseg2_min = 1,
+	.tseg2_max = 32,
+	.sjw_max = 16,
+	.brp_min = 1,
+	.brp_max = 4096,
+	.brp_inc = 1,
+};
+
+static const struct can_bittiming_const kvaser_usb_hydra_flexc_bittiming_c = {
+	.name = "kvaser_usb_flex",
+	.tseg1_min = 4,
+	.tseg1_max = 16,
+	.tseg2_min = 2,
+	.tseg2_max = 8,
+	.sjw_max = 4,
+	.brp_min = 1,
+	.brp_max = 256,
+	.brp_inc = 1,
+};
+
+#define KVASER_USB_HYDRA_TRANSID_BITS		12
+#define KVASER_USB_HYDRA_TRANSID_MASK \
+				GENMASK(KVASER_USB_HYDRA_TRANSID_BITS - 1, 0)
+#define KVASER_USB_HYDRA_HE_ADDR_SRC_MASK	GENMASK(7, 6)
+#define KVASER_USB_HYDRA_HE_ADDR_DEST_MASK	GENMASK(5, 0)
+#define KVASER_USB_HYDRA_HE_ADDR_SRC_BITS	2
+static inline u16 kvaser_usb_hydra_get_cmd_transid(const struct kvaser_cmd *cmd)
+{
+	return le16_to_cpu(cmd->header.transid) & KVASER_USB_HYDRA_TRANSID_MASK;
+}
+
+static inline void kvaser_usb_hydra_set_cmd_transid(struct kvaser_cmd *cmd,
+						    u16 transid)
+{
+	cmd->header.transid =
+			cpu_to_le16(transid & KVASER_USB_HYDRA_TRANSID_MASK);
+}
+
+static inline u8 kvaser_usb_hydra_get_cmd_src_he(const struct kvaser_cmd *cmd)
+{
+	return (cmd->header.he_addr & KVASER_USB_HYDRA_HE_ADDR_SRC_MASK) >>
+		KVASER_USB_HYDRA_HE_ADDR_SRC_BITS |
+		le16_to_cpu(cmd->header.transid) >>
+		KVASER_USB_HYDRA_TRANSID_BITS;
+}
+
+static inline void kvaser_usb_hydra_set_cmd_dest_he(struct kvaser_cmd *cmd,
+						    u8 dest_he)
+{
+	cmd->header.he_addr =
+		(cmd->header.he_addr & KVASER_USB_HYDRA_HE_ADDR_SRC_MASK) |
+		(dest_he & KVASER_USB_HYDRA_HE_ADDR_DEST_MASK);
+}
+
+static u8 kvaser_usb_hydra_channel_from_cmd(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	int i;
+	u8 channel = 0xff;
+	u8 src_he = kvaser_usb_hydra_get_cmd_src_he(cmd);
+
+	for (i = 0; i < KVASER_USB_MAX_NET_DEVICES; i++) {
+		if (dev->card_data.hydra.channel_to_he[i] == src_he) {
+			channel = i;
+			break;
+		}
+	}
+
+	return channel;
+}
+
+static u16 kvaser_usb_hydra_get_next_transid(struct kvaser_usb *dev)
+{
+	unsigned long flags;
+	u16 transid;
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+
+	spin_lock_irqsave(&card_data->transid_lock, flags);
+	transid = card_data->transid;
+	if (transid >= KVASER_USB_HYDRA_MAX_TRANSID)
+		transid = KVASER_USB_HYDRA_MIN_TRANSID;
+	else
+		transid++;
+	card_data->transid = transid;
+	spin_unlock_irqrestore(&card_data->transid_lock, flags);
+
+	return transid;
+}
+
+static size_t kvaser_usb_hydra_cmd_size(struct kvaser_cmd *cmd)
+{
+	size_t ret;
+
+	if (cmd->header.cmd_no == CMD_EXTENDED)
+		ret = le16_to_cpu(((struct kvaser_cmd_ext *)cmd)->len);
+	else
+		ret = sizeof(struct kvaser_cmd);
+
+	return ret;
+}
+
+static struct kvaser_usb_net_priv *
+kvaser_usb_hydra_net_priv_from_cmd(const struct kvaser_usb *dev,
+				   const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv = NULL;
+	u8 channel = kvaser_usb_hydra_channel_from_cmd(dev, cmd);
+
+	if (channel >= dev->nchannels)
+		dev_err(&dev->intf->dev,
+			"Invalid channel number (%d)\n", channel);
+	else
+		priv = dev->nets[channel];
+
+	return priv;
+}
+
+static ktime_t
+kvaser_usb_hydra_ktime_from_rx_cmd(const struct kvaser_usb_dev_cfg *cfg,
+				   const struct kvaser_cmd *cmd)
+{
+	u64 ticks;
+
+	if (cmd->header.cmd_no == CMD_EXTENDED) {
+		struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd;
+
+		ticks = le64_to_cpu(cmd_ext->rx_can.timestamp);
+	} else {
+		ticks = le16_to_cpu(cmd->rx_can.timestamp[0]);
+		ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[1])) << 16;
+		ticks += (u64)(le16_to_cpu(cmd->rx_can.timestamp[2])) << 32;
+	}
+
+	return ns_to_ktime(div_u64(ticks * 1000, cfg->timestamp_freq));
+}
+
+static int kvaser_usb_hydra_send_simple_cmd(struct kvaser_usb *dev,
+					    u8 cmd_no, int channel)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = cmd_no;
+	if (channel < 0) {
+		kvaser_usb_hydra_set_cmd_dest_he
+				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL);
+	} else {
+		if (channel >= KVASER_USB_MAX_NET_DEVICES) {
+			dev_err(&dev->intf->dev, "channel (%d) out of range.\n",
+				channel);
+			err = -EINVAL;
+			goto end;
+		}
+		kvaser_usb_hydra_set_cmd_dest_he
+			(cmd, dev->card_data.hydra.channel_to_he[channel]);
+	}
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static int
+kvaser_usb_hydra_send_simple_cmd_async(struct kvaser_usb_net_priv *priv,
+				       u8 cmd_no)
+{
+	struct kvaser_cmd *cmd;
+	struct kvaser_usb *dev = priv->dev;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = cmd_no;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd_async(priv, cmd,
+					kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		kfree(cmd);
+
+	return err;
+}
+
+/* This function is used for synchronously waiting on hydra control commands.
+ * Note: Compared to kvaser_usb_hydra_read_bulk_callback(), we never need to
+ *       handle partial hydra commands. Since hydra control commands are always
+ *       non-extended commands.
+ */
+static int kvaser_usb_hydra_wait_cmd(const struct kvaser_usb *dev, u8 cmd_no,
+				     struct kvaser_cmd *cmd)
+{
+	void *buf;
+	int err;
+	unsigned long timeout = jiffies + msecs_to_jiffies(KVASER_USB_TIMEOUT);
+
+	if (cmd->header.cmd_no == CMD_EXTENDED) {
+		dev_err(&dev->intf->dev, "Wait for CMD_EXTENDED not allowed\n");
+		return -EINVAL;
+	}
+
+	buf = kzalloc(KVASER_USB_RX_BUFFER_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	do {
+		int actual_len = 0;
+		int pos = 0;
+
+		err = kvaser_usb_recv_cmd(dev, buf, KVASER_USB_RX_BUFFER_SIZE,
+					  &actual_len);
+		if (err < 0)
+			goto end;
+
+		while (pos < actual_len) {
+			struct kvaser_cmd *tmp_cmd;
+			size_t cmd_len;
+
+			tmp_cmd = buf + pos;
+			cmd_len = kvaser_usb_hydra_cmd_size(tmp_cmd);
+			if (pos + cmd_len > actual_len) {
+				dev_err_ratelimited(&dev->intf->dev,
+						    "Format error\n");
+				break;
+			}
+
+			if (tmp_cmd->header.cmd_no == cmd_no) {
+				memcpy(cmd, tmp_cmd, cmd_len);
+				goto end;
+			}
+			pos += cmd_len;
+		}
+	} while (time_before(jiffies, timeout));
+
+	err = -EINVAL;
+
+end:
+	kfree(buf);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_map_channel_resp(struct kvaser_usb *dev,
+					     const struct kvaser_cmd *cmd)
+{
+	u8 he, channel;
+	u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd);
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+
+	if (transid > 0x007f || transid < 0x0040) {
+		dev_err(&dev->intf->dev,
+			"CMD_MAP_CHANNEL_RESP, invalid transid: 0x%x\n",
+			transid);
+		return -EINVAL;
+	}
+
+	switch (transid) {
+	case KVASER_USB_HYDRA_TRANSID_CANHE:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 1:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 2:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 3:
+	case KVASER_USB_HYDRA_TRANSID_CANHE + 4:
+		channel = transid & 0x000f;
+		he = cmd->map_ch_res.he_addr;
+		card_data->channel_to_he[channel] = he;
+		break;
+	case KVASER_USB_HYDRA_TRANSID_SYSDBG:
+		card_data->sysdbg_he = cmd->map_ch_res.he_addr;
+		break;
+	default:
+		dev_warn(&dev->intf->dev,
+			 "Unknown CMD_MAP_CHANNEL_RESP transid=0x%x\n",
+			 transid);
+		break;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_map_channel(struct kvaser_usb *dev, u16 transid,
+					u8 channel, const char *name)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	strcpy(cmd->map_ch_req.name, name);
+	cmd->header.cmd_no = CMD_MAP_CHANNEL_REQ;
+	kvaser_usb_hydra_set_cmd_dest_he
+				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ROUTER);
+	cmd->map_ch_req.channel = channel;
+
+	kvaser_usb_hydra_set_cmd_transid(cmd, transid);
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_MAP_CHANNEL_RESP, cmd);
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_map_channel_resp(dev, cmd);
+	if (err)
+		goto end;
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_get_single_capability(struct kvaser_usb *dev,
+						  u16 cap_cmd_req, u16 *status)
+{
+	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
+	struct kvaser_cmd *cmd;
+	u32 value = 0;
+	u32 mask = 0;
+	u16 cap_cmd_res;
+	int err;
+	int i;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_GET_CAPABILITIES_REQ;
+	cmd->cap_req.cap_cmd = cpu_to_le16(cap_cmd_req);
+
+	kvaser_usb_hydra_set_cmd_dest_he(cmd, card_data->hydra.sysdbg_he);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_CAPABILITIES_RESP, cmd);
+	if (err)
+		goto end;
+
+	*status = le16_to_cpu(cmd->cap_res.status);
+
+	if (*status != KVASER_USB_HYDRA_CAP_STAT_OK)
+		goto end;
+
+	cap_cmd_res = le16_to_cpu(cmd->cap_res.cap_cmd);
+	switch (cap_cmd_res) {
+	case KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE:
+	case KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT:
+	case KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT:
+		value = le32_to_cpu(cmd->cap_res.value);
+		mask = le32_to_cpu(cmd->cap_res.mask);
+		break;
+	default:
+		dev_warn(&dev->intf->dev, "Unknown capability command %u\n",
+			 cap_cmd_res);
+		break;
+	}
+
+	for (i = 0; i < dev->nchannels; i++) {
+		if (BIT(i) & (value & mask)) {
+			switch (cap_cmd_res) {
+			case KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE:
+				card_data->ctrlmode_supported |=
+						CAN_CTRLMODE_LISTENONLY;
+				break;
+			case KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT:
+				card_data->capabilities |=
+						KVASER_USB_CAP_BERR_CAP;
+				break;
+			case KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT:
+				card_data->ctrlmode_supported |=
+						CAN_CTRLMODE_ONE_SHOT;
+				break;
+			}
+		}
+	}
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static void kvaser_usb_hydra_start_chip_reply(const struct kvaser_usb *dev,
+					      const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	if (completion_done(&priv->start_comp) &&
+	    netif_queue_stopped(priv->netdev)) {
+		netif_wake_queue(priv->netdev);
+	} else {
+		netif_start_queue(priv->netdev);
+		complete(&priv->start_comp);
+	}
+}
+
+static void kvaser_usb_hydra_stop_chip_reply(const struct kvaser_usb *dev,
+					     const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	complete(&priv->stop_comp);
+}
+
+static void kvaser_usb_hydra_flush_queue_reply(const struct kvaser_usb *dev,
+					       const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	complete(&priv->flush_comp);
+}
+
+static void
+kvaser_usb_hydra_bus_status_to_can_state(const struct kvaser_usb_net_priv *priv,
+					 u8 bus_status,
+					 const struct can_berr_counter *bec,
+					 enum can_state *new_state)
+{
+	if (bus_status & KVASER_USB_HYDRA_BUS_BUS_OFF) {
+		*new_state = CAN_STATE_BUS_OFF;
+	} else if (bus_status & KVASER_USB_HYDRA_BUS_ERR_PASS) {
+		*new_state = CAN_STATE_ERROR_PASSIVE;
+	} else if (bus_status == KVASER_USB_HYDRA_BUS_ERR_ACT) {
+		if (bec->txerr >= 128 || bec->rxerr >= 128) {
+			netdev_warn(priv->netdev,
+				    "ERR_ACTIVE but err tx=%u or rx=%u >=128\n",
+				    bec->txerr, bec->rxerr);
+			*new_state = CAN_STATE_ERROR_PASSIVE;
+		} else if (bec->txerr >= 96 || bec->rxerr >= 96) {
+			*new_state = CAN_STATE_ERROR_WARNING;
+		} else {
+			*new_state = CAN_STATE_ERROR_ACTIVE;
+		}
+	}
+}
+
+static void kvaser_usb_hydra_update_state(struct kvaser_usb_net_priv *priv,
+					  u8 bus_status,
+					  const struct can_berr_counter *bec)
+{
+	struct net_device *netdev = priv->netdev;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct net_device_stats *stats;
+	enum can_state new_state, old_state;
+
+	old_state = priv->can.state;
+
+	kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, bec,
+						 &new_state);
+
+	if (new_state == old_state)
+		return;
+
+	/* Ignore state change if previous state was STOPPED and the new state
+	 * is BUS_OFF. Firmware always report this as BUS_OFF, since firmware
+	 * does not distinguish between BUS_OFF and STOPPED.
+	 */
+	if (old_state == CAN_STATE_STOPPED && new_state == CAN_STATE_BUS_OFF)
+		return;
+
+	skb = alloc_can_err_skb(netdev, &cf);
+	if (skb) {
+		enum can_state tx_state, rx_state;
+
+		tx_state = (bec->txerr >= bec->rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+		rx_state = (bec->txerr <= bec->rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+		can_change_state(netdev, cf, tx_state, rx_state);
+	}
+
+	if (new_state == CAN_STATE_BUS_OFF && old_state < CAN_STATE_BUS_OFF) {
+		if (!priv->can.restart_ms)
+			kvaser_usb_hydra_send_simple_cmd_async
+						(priv, CMD_STOP_CHIP_REQ);
+
+		can_bus_off(netdev);
+	}
+
+	if (!skb) {
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return;
+	}
+
+	if (priv->can.restart_ms &&
+	    old_state >= CAN_STATE_BUS_OFF &&
+	    new_state < CAN_STATE_BUS_OFF)
+		priv->can.can_stats.restarts++;
+
+	cf->data[6] = bec->txerr;
+	cf->data[7] = bec->rxerr;
+
+	stats = &netdev->stats;
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_state_event(const struct kvaser_usb *dev,
+					 const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv;
+	struct can_berr_counter bec;
+	u8 bus_status;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	bus_status = cmd->chip_state_event.bus_status;
+	bec.txerr = cmd->chip_state_event.tx_err_counter;
+	bec.rxerr = cmd->chip_state_event.rx_err_counter;
+
+	kvaser_usb_hydra_update_state(priv, bus_status, &bec);
+	priv->bec.txerr = bec.txerr;
+	priv->bec.rxerr = bec.rxerr;
+}
+
+static void kvaser_usb_hydra_error_event_parameter(const struct kvaser_usb *dev,
+						   const struct kvaser_cmd *cmd)
+{
+	/* info1 will contain the offending cmd_no */
+	switch (le16_to_cpu(cmd->error_event.info1)) {
+	case CMD_START_CHIP_REQ:
+		dev_warn(&dev->intf->dev,
+			 "CMD_START_CHIP_REQ error in parameter\n");
+		break;
+
+	case CMD_STOP_CHIP_REQ:
+		dev_warn(&dev->intf->dev,
+			 "CMD_STOP_CHIP_REQ error in parameter\n");
+		break;
+
+	case CMD_FLUSH_QUEUE:
+		dev_warn(&dev->intf->dev,
+			 "CMD_FLUSH_QUEUE error in parameter\n");
+		break;
+
+	case CMD_SET_BUSPARAMS_REQ:
+		dev_warn(&dev->intf->dev,
+			 "Set bittiming failed. Error in parameter\n");
+		break;
+
+	case CMD_SET_BUSPARAMS_FD_REQ:
+		dev_warn(&dev->intf->dev,
+			 "Set data bittiming failed. Error in parameter\n");
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev,
+			 "Unhandled parameter error event cmd_no (%u)\n",
+			 le16_to_cpu(cmd->error_event.info1));
+		break;
+	}
+}
+
+static void kvaser_usb_hydra_error_event(const struct kvaser_usb *dev,
+					 const struct kvaser_cmd *cmd)
+{
+	switch (cmd->error_event.error_code) {
+	case KVASER_USB_HYDRA_ERROR_EVENT_PARAM:
+		kvaser_usb_hydra_error_event_parameter(dev, cmd);
+		break;
+
+	case KVASER_USB_HYDRA_ERROR_EVENT_CAN:
+		/* Wrong channel mapping?! This should never happen!
+		 * info1 will contain the offending cmd_no
+		 */
+		dev_err(&dev->intf->dev,
+			"Received CAN error event for cmd_no (%u)\n",
+			le16_to_cpu(cmd->error_event.info1));
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev,
+			 "Unhandled error event (%d)\n",
+			 cmd->error_event.error_code);
+		break;
+	}
+}
+
+static void
+kvaser_usb_hydra_error_frame(struct kvaser_usb_net_priv *priv,
+			     const struct kvaser_err_frame_data *err_frame_data,
+			     ktime_t hwtstamp)
+{
+	struct net_device *netdev = priv->netdev;
+	struct net_device_stats *stats = &netdev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	struct can_berr_counter bec;
+	enum can_state new_state, old_state;
+	u8 bus_status;
+
+	priv->can.can_stats.bus_error++;
+	stats->rx_errors++;
+
+	bus_status = err_frame_data->bus_status;
+	bec.txerr = err_frame_data->tx_err_counter;
+	bec.rxerr = err_frame_data->rx_err_counter;
+
+	old_state = priv->can.state;
+	kvaser_usb_hydra_bus_status_to_can_state(priv, bus_status, &bec,
+						 &new_state);
+
+	skb = alloc_can_err_skb(netdev, &cf);
+
+	if (new_state != old_state) {
+		if (skb) {
+			enum can_state tx_state, rx_state;
+
+			tx_state = (bec.txerr >= bec.rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+			rx_state = (bec.txerr <= bec.rxerr) ?
+					new_state : CAN_STATE_ERROR_ACTIVE;
+
+			can_change_state(netdev, cf, tx_state, rx_state);
+		}
+
+		if (new_state == CAN_STATE_BUS_OFF) {
+			if (!priv->can.restart_ms)
+				kvaser_usb_hydra_send_simple_cmd_async
+						(priv, CMD_STOP_CHIP_REQ);
+
+			can_bus_off(netdev);
+		}
+
+		if (priv->can.restart_ms &&
+		    old_state >= CAN_STATE_BUS_OFF &&
+		    new_state < CAN_STATE_BUS_OFF)
+			cf->can_id |= CAN_ERR_RESTARTED;
+	}
+
+	if (!skb) {
+		stats->rx_dropped++;
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return;
+	}
+
+	shhwtstamps = skb_hwtstamps(skb);
+	shhwtstamps->hwtstamp = hwtstamp;
+
+	cf->can_id |= CAN_ERR_BUSERROR;
+	cf->data[6] = bec.txerr;
+	cf->data[7] = bec.rxerr;
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+
+	priv->bec.txerr = bec.txerr;
+	priv->bec.rxerr = bec.rxerr;
+}
+
+static void kvaser_usb_hydra_one_shot_fail(struct kvaser_usb_net_priv *priv,
+					   const struct kvaser_cmd_ext *cmd)
+{
+	struct net_device *netdev = priv->netdev;
+	struct net_device_stats *stats = &netdev->stats;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	u32 flags;
+
+	skb = alloc_can_err_skb(netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		netdev_warn(netdev, "No memory left for err_skb\n");
+		return;
+	}
+
+	cf->can_id |= CAN_ERR_BUSERROR;
+	flags = le32_to_cpu(cmd->tx_ack.flags);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_OSM_NACK)
+		cf->can_id |= CAN_ERR_ACK;
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_ABL) {
+		cf->can_id |= CAN_ERR_LOSTARB;
+		priv->can.can_stats.arbitration_lost++;
+	}
+
+	stats->tx_errors++;
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_tx_acknowledge(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_tx_urb_context *context;
+	struct kvaser_usb_net_priv *priv;
+	unsigned long irq_flags;
+	bool one_shot_fail = false;
+	u16 transid = kvaser_usb_hydra_get_cmd_transid(cmd);
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	if (!netif_device_present(priv->netdev))
+		return;
+
+	if (cmd->header.cmd_no == CMD_EXTENDED) {
+		struct kvaser_cmd_ext *cmd_ext = (struct kvaser_cmd_ext *)cmd;
+		u32 flags = le32_to_cpu(cmd_ext->tx_ack.flags);
+
+		if (flags & (KVASER_USB_HYDRA_CF_FLAG_OSM_NACK |
+			     KVASER_USB_HYDRA_CF_FLAG_ABL)) {
+			kvaser_usb_hydra_one_shot_fail(priv, cmd_ext);
+			one_shot_fail = true;
+		}
+	}
+
+	context = &priv->tx_contexts[transid % dev->max_tx_urbs];
+	if (!one_shot_fail) {
+		struct net_device_stats *stats = &priv->netdev->stats;
+
+		stats->tx_packets++;
+		stats->tx_bytes += can_dlc2len(context->dlc);
+	}
+
+	spin_lock_irqsave(&priv->tx_contexts_lock, irq_flags);
+
+	can_get_echo_skb(priv->netdev, context->echo_index);
+	context->echo_index = dev->max_tx_urbs;
+	--priv->active_tx_contexts;
+	netif_wake_queue(priv->netdev);
+
+	spin_unlock_irqrestore(&priv->tx_contexts_lock, irq_flags);
+}
+
+static void kvaser_usb_hydra_rx_msg_std(const struct kvaser_usb *dev,
+					const struct kvaser_cmd *cmd)
+{
+	struct kvaser_usb_net_priv *priv = NULL;
+	struct can_frame *cf;
+	struct sk_buff *skb;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	struct net_device_stats *stats;
+	u8 flags;
+	ktime_t hwtstamp;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, cmd);
+	if (!priv)
+		return;
+
+	stats = &priv->netdev->stats;
+
+	flags = cmd->rx_can.flags;
+	hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, cmd);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) {
+		kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data,
+					     hwtstamp);
+		return;
+	}
+
+	skb = alloc_can_skb(priv->netdev, &cf);
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	shhwtstamps = skb_hwtstamps(skb);
+	shhwtstamps->hwtstamp = hwtstamp;
+
+	cf->can_id = le32_to_cpu(cmd->rx_can.id);
+
+	if (cf->can_id &  KVASER_USB_HYDRA_EXTENDED_FRAME_ID) {
+		cf->can_id &= CAN_EFF_MASK;
+		cf->can_id |= CAN_EFF_FLAG;
+	} else {
+		cf->can_id &= CAN_SFF_MASK;
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN)
+		kvaser_usb_can_rx_over_error(priv->netdev);
+
+	cf->can_dlc = get_can_dlc(cmd->rx_can.dlc);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
+		cf->can_id |= CAN_RTR_FLAG;
+	else
+		memcpy(cf->data, cmd->rx_can.data, cf->can_dlc);
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->can_dlc;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_rx_msg_ext(const struct kvaser_usb *dev,
+					const struct kvaser_cmd_ext *cmd)
+{
+	struct kvaser_cmd *std_cmd = (struct kvaser_cmd *)cmd;
+	struct kvaser_usb_net_priv *priv;
+	struct canfd_frame *cf;
+	struct sk_buff *skb;
+	struct skb_shared_hwtstamps *shhwtstamps;
+	struct net_device_stats *stats;
+	u32 flags;
+	u8 dlc;
+	u32 kcan_header;
+	ktime_t hwtstamp;
+
+	priv = kvaser_usb_hydra_net_priv_from_cmd(dev, std_cmd);
+	if (!priv)
+		return;
+
+	stats = &priv->netdev->stats;
+
+	kcan_header = le32_to_cpu(cmd->rx_can.kcan_header);
+	dlc = (kcan_header & KVASER_USB_KCAN_DATA_DLC_MASK) >>
+		KVASER_USB_KCAN_DATA_DLC_SHIFT;
+
+	flags = le32_to_cpu(cmd->rx_can.flags);
+	hwtstamp = kvaser_usb_hydra_ktime_from_rx_cmd(dev->cfg, std_cmd);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME) {
+		kvaser_usb_hydra_error_frame(priv, &cmd->rx_can.err_frame_data,
+					     hwtstamp);
+		return;
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF)
+		skb = alloc_canfd_skb(priv->netdev, &cf);
+	else
+		skb = alloc_can_skb(priv->netdev, (struct can_frame **)&cf);
+
+	if (!skb) {
+		stats->rx_dropped++;
+		return;
+	}
+
+	shhwtstamps = skb_hwtstamps(skb);
+	shhwtstamps->hwtstamp = hwtstamp;
+
+	cf->can_id = le32_to_cpu(cmd->rx_can.id);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID) {
+		cf->can_id &= CAN_EFF_MASK;
+		cf->can_id |= CAN_EFF_FLAG;
+	} else {
+		cf->can_id &= CAN_SFF_MASK;
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_OVERRUN)
+		kvaser_usb_can_rx_over_error(priv->netdev);
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_FDF) {
+		cf->len = can_dlc2len(get_canfd_dlc(dlc));
+		if (flags & KVASER_USB_HYDRA_CF_FLAG_BRS)
+			cf->flags |= CANFD_BRS;
+		if (flags & KVASER_USB_HYDRA_CF_FLAG_ESI)
+			cf->flags |= CANFD_ESI;
+	} else {
+		cf->len = get_can_dlc(dlc);
+	}
+
+	if (flags & KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME)
+		cf->can_id |= CAN_RTR_FLAG;
+	else
+		memcpy(cf->data, cmd->rx_can.kcan_payload, cf->len);
+
+	stats->rx_packets++;
+	stats->rx_bytes += cf->len;
+	netif_rx(skb);
+}
+
+static void kvaser_usb_hydra_handle_cmd_std(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd *cmd)
+{
+	switch (cmd->header.cmd_no) {
+	case CMD_START_CHIP_RESP:
+		kvaser_usb_hydra_start_chip_reply(dev, cmd);
+		break;
+
+	case CMD_STOP_CHIP_RESP:
+		kvaser_usb_hydra_stop_chip_reply(dev, cmd);
+		break;
+
+	case CMD_FLUSH_QUEUE_RESP:
+		kvaser_usb_hydra_flush_queue_reply(dev, cmd);
+		break;
+
+	case CMD_CHIP_STATE_EVENT:
+		kvaser_usb_hydra_state_event(dev, cmd);
+		break;
+
+	case CMD_ERROR_EVENT:
+		kvaser_usb_hydra_error_event(dev, cmd);
+		break;
+
+	case CMD_TX_ACKNOWLEDGE:
+		kvaser_usb_hydra_tx_acknowledge(dev, cmd);
+		break;
+
+	case CMD_RX_MESSAGE:
+		kvaser_usb_hydra_rx_msg_std(dev, cmd);
+		break;
+
+	/* Ignored commands */
+	case CMD_SET_BUSPARAMS_RESP:
+	case CMD_SET_BUSPARAMS_FD_RESP:
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev, "Unhandled command (%d)\n",
+			 cmd->header.cmd_no);
+		break;
+	}
+}
+
+static void kvaser_usb_hydra_handle_cmd_ext(const struct kvaser_usb *dev,
+					    const struct kvaser_cmd_ext *cmd)
+{
+	switch (cmd->cmd_no_ext) {
+	case CMD_TX_ACKNOWLEDGE_FD:
+		kvaser_usb_hydra_tx_acknowledge(dev, (struct kvaser_cmd *)cmd);
+		break;
+
+	case CMD_RX_MESSAGE_FD:
+		kvaser_usb_hydra_rx_msg_ext(dev, cmd);
+		break;
+
+	default:
+		dev_warn(&dev->intf->dev, "Unhandled extended command (%d)\n",
+			 cmd->header.cmd_no);
+		break;
+	}
+}
+
+static void kvaser_usb_hydra_handle_cmd(const struct kvaser_usb *dev,
+					const struct kvaser_cmd *cmd)
+{
+		if (cmd->header.cmd_no == CMD_EXTENDED)
+			kvaser_usb_hydra_handle_cmd_ext
+					(dev, (struct kvaser_cmd_ext *)cmd);
+		else
+			kvaser_usb_hydra_handle_cmd_std(dev, cmd);
+}
+
+static void *
+kvaser_usb_hydra_frame_to_cmd_ext(const struct kvaser_usb_net_priv *priv,
+				  const struct sk_buff *skb, int *frame_len,
+				  int *cmd_len, u16 transid)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd_ext *cmd;
+	struct canfd_frame *cf = (struct canfd_frame *)skb->data;
+	u8 dlc = can_len2dlc(cf->len);
+	u8 nbr_of_bytes = cf->len;
+	u32 flags;
+	u32 id;
+	u32 kcan_id;
+	u32 kcan_header;
+
+	*frame_len = nbr_of_bytes;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd_ext), GFP_ATOMIC);
+	if (!cmd)
+		return NULL;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+			((struct kvaser_cmd *)cmd,
+			 dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid((struct kvaser_cmd *)cmd, transid);
+
+	cmd->header.cmd_no = CMD_EXTENDED;
+	cmd->cmd_no_ext = CMD_TX_CAN_MESSAGE_FD;
+
+	*cmd_len = ALIGN(sizeof(struct kvaser_cmd_ext) -
+			 sizeof(cmd->tx_can.kcan_payload) + nbr_of_bytes,
+			 8);
+
+	cmd->len = cpu_to_le16(*cmd_len);
+
+	cmd->tx_can.databytes = nbr_of_bytes;
+	cmd->tx_can.dlc = dlc;
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		id = cf->can_id & CAN_EFF_MASK;
+		flags = KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID;
+		kcan_id = (cf->can_id & CAN_EFF_MASK) |
+			  KVASER_USB_KCAN_DATA_IDE | KVASER_USB_KCAN_DATA_SRR;
+	} else {
+		id = cf->can_id & CAN_SFF_MASK;
+		flags = 0;
+		kcan_id = cf->can_id & CAN_SFF_MASK;
+	}
+
+	if (cf->can_id & CAN_ERR_FLAG)
+		flags |= KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME;
+
+	kcan_header = ((dlc << KVASER_USB_KCAN_DATA_DLC_SHIFT) &
+				KVASER_USB_KCAN_DATA_DLC_MASK) |
+			KVASER_USB_KCAN_DATA_AREQ |
+			(priv->can.ctrlmode & CAN_CTRLMODE_ONE_SHOT ?
+				KVASER_USB_KCAN_DATA_OSM : 0);
+
+	if (can_is_canfd_skb(skb)) {
+		kcan_header |= KVASER_USB_KCAN_DATA_FDF |
+			       (cf->flags & CANFD_BRS ?
+					KVASER_USB_KCAN_DATA_BRS : 0);
+	} else {
+		if (cf->can_id & CAN_RTR_FLAG) {
+			kcan_id |= KVASER_USB_KCAN_DATA_RTR;
+			cmd->tx_can.databytes = 0;
+			flags |= KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME;
+		}
+	}
+
+	cmd->tx_can.kcan_id = cpu_to_le32(kcan_id);
+	cmd->tx_can.id = cpu_to_le32(id);
+	cmd->tx_can.flags = cpu_to_le32(flags);
+	cmd->tx_can.kcan_header = cpu_to_le32(kcan_header);
+
+	memcpy(cmd->tx_can.kcan_payload, cf->data, nbr_of_bytes);
+
+	return cmd;
+}
+
+static void *
+kvaser_usb_hydra_frame_to_cmd_std(const struct kvaser_usb_net_priv *priv,
+				  const struct sk_buff *skb, int *frame_len,
+				  int *cmd_len, u16 transid)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	struct can_frame *cf = (struct can_frame *)skb->data;
+	u32 flags;
+	u32 id;
+
+	*frame_len = cf->can_dlc;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_ATOMIC);
+	if (!cmd)
+		return NULL;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid(cmd, transid);
+
+	cmd->header.cmd_no = CMD_TX_CAN_MESSAGE;
+
+	*cmd_len = ALIGN(sizeof(struct kvaser_cmd), 8);
+
+	if (cf->can_id & CAN_EFF_FLAG) {
+		id = (cf->can_id & CAN_EFF_MASK);
+		id |= KVASER_USB_HYDRA_EXTENDED_FRAME_ID;
+	} else {
+		id = cf->can_id & CAN_SFF_MASK;
+	}
+
+	cmd->tx_can.dlc = cf->can_dlc;
+
+	flags = (cf->can_id & CAN_EFF_FLAG ?
+		 KVASER_USB_HYDRA_CF_FLAG_EXTENDED_ID : 0);
+
+	if (cf->can_id & CAN_RTR_FLAG)
+		flags |= KVASER_USB_HYDRA_CF_FLAG_REMOTE_FRAME;
+
+	flags |= (cf->can_id & CAN_ERR_FLAG ?
+		  KVASER_USB_HYDRA_CF_FLAG_ERROR_FRAME : 0);
+
+	cmd->tx_can.id = cpu_to_le32(id);
+	cmd->tx_can.flags = flags;
+
+	memcpy(cmd->tx_can.data, cf->data, *frame_len);
+
+	return cmd;
+}
+
+static int kvaser_usb_hydra_set_mode(struct net_device *netdev,
+				     enum can_mode mode)
+{
+	int err = 0;
+
+	switch (mode) {
+	case CAN_MODE_START:
+		/* CAN controller automatically recovers from BUS_OFF */
+		break;
+	default:
+		err = -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static int kvaser_usb_hydra_set_bittiming(struct net_device *netdev)
+{
+	struct kvaser_cmd *cmd;
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct can_bittiming *bt = &priv->can.bittiming;
+	struct kvaser_usb *dev = priv->dev;
+	int tseg1 = bt->prop_seg + bt->phase_seg1;
+	int tseg2 = bt->phase_seg2;
+	int sjw = bt->sjw;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_SET_BUSPARAMS_REQ;
+	cmd->set_busparams_req.bitrate = cpu_to_le32(bt->bitrate);
+	cmd->set_busparams_req.sjw = (u8)sjw;
+	cmd->set_busparams_req.tseg1 = (u8)tseg1;
+	cmd->set_busparams_req.tseg2 = (u8)tseg2;
+	cmd->set_busparams_req.nsamples = 1;
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_set_data_bittiming(struct net_device *netdev)
+{
+	struct kvaser_cmd *cmd;
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	struct can_bittiming *dbt = &priv->can.data_bittiming;
+	struct kvaser_usb *dev = priv->dev;
+	int tseg1 = dbt->prop_seg + dbt->phase_seg1;
+	int tseg2 = dbt->phase_seg2;
+	int sjw = dbt->sjw;
+	int err;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_SET_BUSPARAMS_FD_REQ;
+	cmd->set_busparams_req.bitrate_d = cpu_to_le32(dbt->bitrate);
+	cmd->set_busparams_req.sjw_d = (u8)sjw;
+	cmd->set_busparams_req.tseg1_d = (u8)tseg1;
+	cmd->set_busparams_req.tseg2_d = (u8)tseg2;
+	cmd->set_busparams_req.nsamples_d = 1;
+
+	if (priv->can.ctrlmode & CAN_CTRLMODE_FD) {
+		if (priv->can.ctrlmode & CAN_CTRLMODE_FD_NON_ISO)
+			cmd->set_busparams_req.canfd_mode =
+					KVASER_USB_HYDRA_BUS_MODE_NONISO;
+		else
+			cmd->set_busparams_req.canfd_mode =
+					KVASER_USB_HYDRA_BUS_MODE_CANFD_ISO;
+	}
+
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_get_berr_counter(const struct net_device *netdev,
+					     struct can_berr_counter *bec)
+{
+	struct kvaser_usb_net_priv *priv = netdev_priv(netdev);
+	int err;
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev,
+					       CMD_GET_CHIP_STATE_REQ,
+					       priv->channel);
+	if (err)
+		return err;
+
+	*bec = priv->bec;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_setup_endpoints(struct kvaser_usb *dev)
+{
+	const struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *ep;
+	int i;
+
+	iface_desc = &dev->intf->altsetting[0];
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) {
+		ep = &iface_desc->endpoint[i].desc;
+
+		if (!dev->bulk_in && usb_endpoint_is_bulk_in(ep) &&
+		    ep->bEndpointAddress == KVASER_USB_HYDRA_BULK_EP_IN_ADDR)
+			dev->bulk_in = ep;
+
+		if (!dev->bulk_out && usb_endpoint_is_bulk_out(ep) &&
+		    ep->bEndpointAddress == KVASER_USB_HYDRA_BULK_EP_OUT_ADDR)
+			dev->bulk_out = ep;
+
+		if (dev->bulk_in && dev->bulk_out)
+			return 0;
+	}
+
+	return -ENODEV;
+}
+
+static int kvaser_usb_hydra_init_card(struct kvaser_usb *dev)
+{
+	int err;
+	unsigned int i;
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+
+	card_data->transid = KVASER_USB_HYDRA_MIN_TRANSID;
+	spin_lock_init(&card_data->transid_lock);
+
+	memset(card_data->usb_rx_leftover, 0, KVASER_USB_HYDRA_MAX_CMD_LEN);
+	card_data->usb_rx_leftover_len = 0;
+	spin_lock_init(&card_data->usb_rx_leftover_lock);
+
+	memset(card_data->channel_to_he, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL,
+	       sizeof(card_data->channel_to_he));
+	card_data->sysdbg_he = 0;
+
+	for (i = 0; i < KVASER_USB_MAX_NET_DEVICES; i++) {
+		err = kvaser_usb_hydra_map_channel
+					(dev,
+					 (KVASER_USB_HYDRA_TRANSID_CANHE | i),
+					 i, "CAN");
+		if (err) {
+			dev_err(&dev->intf->dev,
+				"CMD_MAP_CHANNEL_REQ failed for CAN%u\n", i);
+			return err;
+		}
+	}
+
+	err = kvaser_usb_hydra_map_channel(dev, KVASER_USB_HYDRA_TRANSID_SYSDBG,
+					   0, "SYSDBG");
+	if (err) {
+		dev_err(&dev->intf->dev,
+			"CMD_MAP_CHANNEL_REQ failed for SYSDBG\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_get_software_info(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_hydra_send_simple_cmd(dev, CMD_GET_SOFTWARE_INFO_REQ,
+					       -1);
+	if (err)
+		return err;
+
+	memset(&cmd, 0, sizeof(struct kvaser_cmd));
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_SOFTWARE_INFO_RESP, &cmd);
+	if (err)
+		return err;
+
+	dev->max_tx_urbs = min_t(unsigned int, KVASER_USB_MAX_TX_URBS,
+				 le16_to_cpu(cmd.sw_info.max_outstanding_tx));
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_get_software_details(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd *cmd;
+	int err;
+	u32 flags;
+	struct kvaser_usb_dev_card_data *card_data = &dev->card_data;
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_GET_SOFTWARE_DETAILS_REQ;
+	cmd->sw_detail_req.use_ext_cmd = 1;
+	kvaser_usb_hydra_set_cmd_dest_he
+				(cmd, KVASER_USB_HYDRA_HE_ADDRESS_ILLEGAL);
+
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	if (err)
+		goto end;
+
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_SOFTWARE_DETAILS_RESP,
+					cmd);
+	if (err)
+		goto end;
+
+	dev->fw_version = le32_to_cpu(cmd->sw_detail_res.sw_version);
+	flags = le32_to_cpu(cmd->sw_detail_res.sw_flags);
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_FW_BAD) {
+		dev_err(&dev->intf->dev,
+			"Bad firmware, device refuse to run!\n");
+		err = -EINVAL;
+		goto end;
+	}
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_FW_BETA)
+		dev_info(&dev->intf->dev, "Beta firmware in use\n");
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_EXT_CAP)
+		card_data->capabilities |= KVASER_USB_CAP_EXT_CAP;
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_EXT_CMD)
+		card_data->capabilities |= KVASER_USB_HYDRA_CAP_EXT_CMD;
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_CANFD)
+		card_data->ctrlmode_supported |= CAN_CTRLMODE_FD;
+
+	if (flags & KVASER_USB_HYDRA_SW_FLAG_NONISO)
+		card_data->ctrlmode_supported |= CAN_CTRLMODE_FD_NON_ISO;
+
+	if (flags &  KVASER_USB_HYDRA_SW_FLAG_FREQ_80M)
+		dev->cfg = &kvaser_usb_hydra_dev_cfg_kcan;
+	else
+		dev->cfg = &kvaser_usb_hydra_dev_cfg_flexc;
+
+end:
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_get_card_info(struct kvaser_usb *dev)
+{
+	struct kvaser_cmd cmd;
+	int err;
+
+	err = kvaser_usb_hydra_send_simple_cmd(dev, CMD_GET_CARD_INFO_REQ, -1);
+	if (err)
+		return err;
+
+	memset(&cmd, 0, sizeof(struct kvaser_cmd));
+	err = kvaser_usb_hydra_wait_cmd(dev, CMD_GET_CARD_INFO_RESP, &cmd);
+	if (err)
+		return err;
+
+	dev->nchannels = cmd.card_info.nchannels;
+	if (dev->nchannels > KVASER_USB_MAX_NET_DEVICES)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_get_capabilities(struct kvaser_usb *dev)
+{
+	int err;
+	u16 status;
+
+	if (!(dev->card_data.capabilities & KVASER_USB_CAP_EXT_CAP)) {
+		dev_info(&dev->intf->dev,
+			 "No extended capability support. Upgrade your device.\n");
+		return 0;
+	}
+
+	err = kvaser_usb_hydra_get_single_capability
+					(dev,
+					 KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE,
+					 &status);
+	if (err)
+		return err;
+	if (status)
+		dev_info(&dev->intf->dev,
+			 "KVASER_USB_HYDRA_CAP_CMD_LISTEN_MODE failed %u\n",
+			 status);
+
+	err = kvaser_usb_hydra_get_single_capability
+					(dev,
+					 KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT,
+					 &status);
+	if (err)
+		return err;
+	if (status)
+		dev_info(&dev->intf->dev,
+			 "KVASER_USB_HYDRA_CAP_CMD_ERR_REPORT failed %u\n",
+			 status);
+
+	err = kvaser_usb_hydra_get_single_capability
+					(dev, KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT,
+					 &status);
+	if (err)
+		return err;
+	if (status)
+		dev_info(&dev->intf->dev,
+			 "KVASER_USB_HYDRA_CAP_CMD_ONE_SHOT failed %u\n",
+			 status);
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_set_opt_mode(const struct kvaser_usb_net_priv *priv)
+{
+	struct kvaser_usb *dev = priv->dev;
+	struct kvaser_cmd *cmd;
+	int err;
+
+	if ((priv->can.ctrlmode &
+	    (CAN_CTRLMODE_FD | CAN_CTRLMODE_FD_NON_ISO)) ==
+	    CAN_CTRLMODE_FD_NON_ISO) {
+		netdev_warn(priv->netdev,
+			    "CTRLMODE_FD shall be on if CTRLMODE_FD_NON_ISO is on\n");
+		return -EINVAL;
+	}
+
+	cmd = kcalloc(1, sizeof(struct kvaser_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->header.cmd_no = CMD_SET_DRIVERMODE_REQ;
+	kvaser_usb_hydra_set_cmd_dest_he
+		(cmd, dev->card_data.hydra.channel_to_he[priv->channel]);
+	kvaser_usb_hydra_set_cmd_transid
+				(cmd, kvaser_usb_hydra_get_next_transid(dev));
+	if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+		cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_LISTEN;
+	else
+		cmd->set_ctrlmode.mode = KVASER_USB_HYDRA_CTRLMODE_NORMAL;
+
+	err = kvaser_usb_send_cmd(dev, cmd, kvaser_usb_hydra_cmd_size(cmd));
+	kfree(cmd);
+
+	return err;
+}
+
+static int kvaser_usb_hydra_start_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->start_comp);
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_START_CHIP_REQ,
+					       priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->start_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_stop_chip(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->stop_comp);
+
+	/* Make sure we do not report invalid BUS_OFF from CMD_CHIP_STATE_EVENT
+	 * see comment in kvaser_usb_hydra_update_state()
+	 */
+	priv->can.state = CAN_STATE_STOPPED;
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_STOP_CHIP_REQ,
+					       priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->stop_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static int kvaser_usb_hydra_flush_queue(struct kvaser_usb_net_priv *priv)
+{
+	int err;
+
+	init_completion(&priv->flush_comp);
+
+	err = kvaser_usb_hydra_send_simple_cmd(priv->dev, CMD_FLUSH_QUEUE,
+					       priv->channel);
+	if (err)
+		return err;
+
+	if (!wait_for_completion_timeout(&priv->flush_comp,
+					 msecs_to_jiffies(KVASER_USB_TIMEOUT)))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+/* A single extended hydra command can be transmitted in multiple transfers
+ * We have to buffer partial hydra commands, and handle them on next callback.
+ */
+static void kvaser_usb_hydra_read_bulk_callback(struct kvaser_usb *dev,
+						void *buf, int len)
+{
+	unsigned long irq_flags;
+	struct kvaser_cmd *cmd;
+	int pos = 0;
+	size_t cmd_len;
+	struct kvaser_usb_dev_card_data_hydra *card_data =
+							&dev->card_data.hydra;
+	int usb_rx_leftover_len;
+	spinlock_t *usb_rx_leftover_lock = &card_data->usb_rx_leftover_lock;
+
+	spin_lock_irqsave(usb_rx_leftover_lock, irq_flags);
+	usb_rx_leftover_len = card_data->usb_rx_leftover_len;
+	if (usb_rx_leftover_len) {
+		int remaining_bytes;
+
+		cmd = (struct kvaser_cmd *)card_data->usb_rx_leftover;
+
+		cmd_len = kvaser_usb_hydra_cmd_size(cmd);
+
+		remaining_bytes = min_t(unsigned int, len,
+					cmd_len - usb_rx_leftover_len);
+		/* Make sure we do not overflow usb_rx_leftover */
+		if (remaining_bytes + usb_rx_leftover_len >
+						KVASER_USB_HYDRA_MAX_CMD_LEN) {
+			dev_err(&dev->intf->dev, "Format error\n");
+			spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags);
+			return;
+		}
+
+		memcpy(card_data->usb_rx_leftover + usb_rx_leftover_len, buf,
+		       remaining_bytes);
+		pos += remaining_bytes;
+
+		if (remaining_bytes + usb_rx_leftover_len == cmd_len) {
+			kvaser_usb_hydra_handle_cmd(dev, cmd);
+			usb_rx_leftover_len = 0;
+		} else {
+			/* Command still not complete */
+			usb_rx_leftover_len += remaining_bytes;
+		}
+		card_data->usb_rx_leftover_len = usb_rx_leftover_len;
+	}
+	spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags);
+
+	while (pos < len) {
+		cmd = buf + pos;
+
+		cmd_len = kvaser_usb_hydra_cmd_size(cmd);
+
+		if (pos + cmd_len > len) {
+			/* We got first part of a command */
+			int leftover_bytes;
+
+			leftover_bytes = len - pos;
+			/* Make sure we do not overflow usb_rx_leftover */
+			if (leftover_bytes > KVASER_USB_HYDRA_MAX_CMD_LEN) {
+				dev_err(&dev->intf->dev, "Format error\n");
+				return;
+			}
+			spin_lock_irqsave(usb_rx_leftover_lock, irq_flags);
+			memcpy(card_data->usb_rx_leftover, buf + pos,
+			       leftover_bytes);
+			card_data->usb_rx_leftover_len = leftover_bytes;
+			spin_unlock_irqrestore(usb_rx_leftover_lock, irq_flags);
+			break;
+		}
+
+		kvaser_usb_hydra_handle_cmd(dev, cmd);
+		pos += cmd_len;
+	}
+}
+
+static void *
+kvaser_usb_hydra_frame_to_cmd(const struct kvaser_usb_net_priv *priv,
+			      const struct sk_buff *skb, int *frame_len,
+			      int *cmd_len, u16 transid)
+{
+	void *buf;
+
+	if (priv->dev->card_data.capabilities & KVASER_USB_HYDRA_CAP_EXT_CMD)
+		buf = kvaser_usb_hydra_frame_to_cmd_ext(priv, skb, frame_len,
+							cmd_len, transid);
+	else
+		buf = kvaser_usb_hydra_frame_to_cmd_std(priv, skb, frame_len,
+							cmd_len, transid);
+
+	return buf;
+}
+
+const struct kvaser_usb_dev_ops kvaser_usb_hydra_dev_ops = {
+	.dev_set_mode = kvaser_usb_hydra_set_mode,
+	.dev_set_bittiming = kvaser_usb_hydra_set_bittiming,
+	.dev_set_data_bittiming = kvaser_usb_hydra_set_data_bittiming,
+	.dev_get_berr_counter = kvaser_usb_hydra_get_berr_counter,
+	.dev_setup_endpoints = kvaser_usb_hydra_setup_endpoints,
+	.dev_init_card = kvaser_usb_hydra_init_card,
+	.dev_get_software_info = kvaser_usb_hydra_get_software_info,
+	.dev_get_software_details = kvaser_usb_hydra_get_software_details,
+	.dev_get_card_info = kvaser_usb_hydra_get_card_info,
+	.dev_get_capabilities = kvaser_usb_hydra_get_capabilities,
+	.dev_set_opt_mode = kvaser_usb_hydra_set_opt_mode,
+	.dev_start_chip = kvaser_usb_hydra_start_chip,
+	.dev_stop_chip = kvaser_usb_hydra_stop_chip,
+	.dev_reset_chip = NULL,
+	.dev_flush_queue = kvaser_usb_hydra_flush_queue,
+	.dev_read_bulk_callback = kvaser_usb_hydra_read_bulk_callback,
+	.dev_frame_to_cmd = kvaser_usb_hydra_frame_to_cmd,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_kcan = {
+	.clock = {
+		.freq = 80000000,
+	},
+	.timestamp_freq = 80,
+	.bittiming_const = &kvaser_usb_hydra_kcan_bittiming_c,
+	.data_bittiming_const = &kvaser_usb_hydra_kcan_bittiming_c,
+};
+
+static const struct kvaser_usb_dev_cfg kvaser_usb_hydra_dev_cfg_flexc = {
+	.clock = {
+		.freq = 24000000,
+	},
+	.timestamp_freq = 1,
+	.bittiming_const = &kvaser_usb_hydra_flexc_bittiming_c,
+};
diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 82806732dcdf..70ffff724a26 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -1340,11 +1340,14 @@ static int kvaser_usb_leaf_setup_endpoints(struct kvaser_usb *dev)
 const struct kvaser_usb_dev_ops kvaser_usb_leaf_dev_ops = {
 	.dev_set_mode = kvaser_usb_leaf_set_mode,
 	.dev_set_bittiming = kvaser_usb_leaf_set_bittiming,
+	.dev_set_data_bittiming = NULL,
 	.dev_get_berr_counter = kvaser_usb_leaf_get_berr_counter,
 	.dev_setup_endpoints = kvaser_usb_leaf_setup_endpoints,
 	.dev_init_card = kvaser_usb_leaf_init_card,
 	.dev_get_software_info = kvaser_usb_leaf_get_software_info,
+	.dev_get_software_details = NULL,
 	.dev_get_card_info = kvaser_usb_leaf_get_card_info,
+	.dev_get_capabilities = NULL,
 	.dev_set_opt_mode = kvaser_usb_leaf_set_opt_mode,
 	.dev_start_chip = kvaser_usb_leaf_start_chip,
 	.dev_stop_chip = kvaser_usb_leaf_stop_chip,
-- 
cgit v1.2.3


From 1f6ed42c742e8d1cfd3811ef7a134eaa75a511d6 Mon Sep 17 00:00:00 2001
From: Jimmy Assarsson <jimmyassarsson@gmail.com>
Date: Fri, 16 Feb 2018 14:41:06 +0100
Subject: can: kvaser_usb: Simplify struct kvaser_cmd_cardinfo

serial_number_high can be removed from the struct since it is never used in
the USBcan II firmware.

Signed-off-by: Jimmy Assarsson <jimmyassarsson@gmail.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
index 70ffff724a26..07d2f3aa2c02 100644
--- a/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
+++ b/drivers/net/can/usb/kvaser_usb/kvaser_usb_leaf.c
@@ -125,16 +125,8 @@ struct kvaser_cmd_simple {
 struct kvaser_cmd_cardinfo {
 	u8 tid;
 	u8 nchannels;
-	union {
-		struct {
-			__le32 serial_number;
-			__le32 padding;
-		} __packed leaf0;
-		struct {
-			__le32 serial_number_low;
-			__le32 serial_number_high;
-		} __packed usbcan0;
-	} __packed;
+	__le32 serial_number;
+	__le32 padding0;
 	__le32 clock_resolution;
 	__le32 mfgdate;
 	u8 ean[8];
@@ -147,7 +139,7 @@ struct kvaser_cmd_cardinfo {
 			u8 padding;
 		} __packed usbcan1;
 	} __packed;
-	__le16 padding;
+	__le16 padding1;
 } __packed;
 
 struct leaf_cmd_softinfo {
-- 
cgit v1.2.3


From 30800b3a1fb14c6f143db5616a4aaea9fef94af3 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Thu, 31 May 2018 16:21:43 +0100
Subject: irqchip/gic-v3-its: Reduce minimum LPI allocation to 1 for PCI
 devices

Allocating a minimum of 32 LPIs per PCI device, let's reduce it to
be just 1, as most devices do not need that many interrupts.

We still have to special-case DevID 0, as there is plenty of broken
HW around where the PCI RID is not presented as a DevID to the ITS,
and all the devices are presented as DevID 0. In this case, we keep
the 32 minimal allocation.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its-pci-msi.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its-pci-msi.c b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
index 75c3cafabc6a..8d6d009d1d58 100644
--- a/drivers/irqchip/irq-gic-v3-its-pci-msi.c
+++ b/drivers/irqchip/irq-gic-v3-its-pci-msi.c
@@ -66,7 +66,7 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 {
 	struct pci_dev *pdev, *alias_dev;
 	struct msi_domain_info *msi_info;
-	int alias_count = 0;
+	int alias_count = 0, minnvec = 1;
 
 	if (!dev_is_pci(dev))
 		return -EINVAL;
@@ -86,9 +86,17 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain, pdev);
 
-	/* Allocate at least 32 MSIs, and always as a power of 2 */
+	/*
+	 * Always allocate a power of 2, and special case device 0 for
+	 * broken systems where the DevID is not wired (and all devices
+	 * appear as DevID 0). For that reason, we generously allocate a
+	 * minimum of 32 MSIs for DevID 0. If you want more because all
+	 * your devices are aliasing to DevID 0, consider fixing your HW.
+	 */
 	nvec = max(nvec, alias_count);
-	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
+	if (!info->scratchpad[0].ul)
+		minnvec = 32;
+	nvec = max_t(int, minnvec, roundup_pow_of_two(nvec));
 	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
 }
 
-- 
cgit v1.2.3


From df3f0347fd856272ca9fdbb6e691b7b512b7acb4 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:55:28 +0800
Subject: ALSA: usb-audio: quirks: Replace mdelay() with msleep() and
 usleep_range()

snd_usb_select_mode_quirk(), snd_usb_set_interface_quirk() and
snd_usb_ctl_msg_quirk() are never called in atomic context.
They call mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep() and usleep_range().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index dde87d64bc32..8a945ece9869 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1213,7 +1213,7 @@ int snd_usb_select_mode_quirk(struct snd_usb_substream *subs,
 		if (err < 0)
 			return err;
 
-		mdelay(20); /* Delay needed after setting the interface */
+		msleep(20); /* Delay needed after setting the interface */
 
 		/* Vendor mode switch cmd is required. */
 		if (fmt->formats & SNDRV_PCM_FMTBIT_DSD_U32_BE) {
@@ -1234,7 +1234,7 @@ int snd_usb_select_mode_quirk(struct snd_usb_substream *subs,
 				return err;
 
 		}
-		mdelay(20);
+		msleep(20);
 	}
 	return 0;
 }
@@ -1281,7 +1281,7 @@ void snd_usb_set_interface_quirk(struct usb_device *dev)
 	switch (USB_ID_VENDOR(chip->usb_id)) {
 	case 0x23ba: /* Playback Design */
 	case 0x0644: /* TEAC Corp. */
-		mdelay(50);
+		msleep(50);
 		break;
 	}
 }
@@ -1301,7 +1301,7 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	 */
 	if (USB_ID_VENDOR(chip->usb_id) == 0x23ba &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(20);
+		msleep(20);
 
 	/*
 	 * "TEAC Corp." products need a 20ms delay after each
@@ -1309,14 +1309,14 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	 */
 	if (USB_ID_VENDOR(chip->usb_id) == 0x0644 &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(20);
+		msleep(20);
 
 	/* ITF-USB DSD based DACs functionality need a delay
 	 * after each class compliant request
 	 */
 	if (is_itf_usb_dsd_dac(chip->usb_id)
 	    && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(20);
+		msleep(20);
 
 	/* Zoom R16/24, Logitech H650e, Jabra 550a needs a tiny delay here,
 	 * otherwise requests like get/set frequency return as failed despite
@@ -1326,7 +1326,7 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe,
 	     chip->usb_id == USB_ID(0x046d, 0x0a46) ||
 	     chip->usb_id == USB_ID(0x0b0e, 0x0349)) &&
 	    (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)
-		mdelay(1);
+		usleep_range(1000, 2000);
 }
 
 /*
-- 
cgit v1.2.3


From 08fd8325d94eeddfe49ef8191337e5f54553f6b0 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:57:56 +0800
Subject: ALSA:: ctxfi: cthw20k1: Replace mdelay() with msleep()

hw_pll_init(), hw_reset_dac() and hw_card_init() are never
called in atomic context.
They calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ctxfi/cthw20k1.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/sound/pci/ctxfi/cthw20k1.c b/sound/pci/ctxfi/cthw20k1.c
index 8e6eb9d7984b..6a051a1c3724 100644
--- a/sound/pci/ctxfi/cthw20k1.c
+++ b/sound/pci/ctxfi/cthw20k1.c
@@ -1319,7 +1319,7 @@ static int hw_pll_init(struct hw *hw, unsigned int rsr)
 			break;
 
 		hw_write_20kx(hw, PLLCTL, pllctl);
-		mdelay(40);
+		msleep(40);
 	}
 	if (i >= 3) {
 		dev_alert(hw->card->dev, "PLL initialization failed!!!\n");
@@ -1407,7 +1407,7 @@ static int hw_reset_dac(struct hw *hw)
 	/* To be effective, need to reset the DAC twice. */
 	for (i = 0; i < 2;  i++) {
 		/* set gpio */
-		mdelay(100);
+		msleep(100);
 		gpioorg = (u16)hw_read_20kx(hw, GPIO);
 		gpioorg &= 0xfffd;
 		hw_write_20kx(hw, GPIO, gpioorg);
@@ -2030,7 +2030,7 @@ static int hw_card_init(struct hw *hw, struct card_conf *info)
 	hw_write_20kx(hw, GIE, 0);
 	/* Reset all SRC pending interrupts */
 	hw_write_20kx(hw, SRCIP, 0);
-	mdelay(30);
+	msleep(30);
 
 	/* Detect the card ID and configure GPIO accordingly. */
 	switch (hw->model) {
-- 
cgit v1.2.3


From fad56c895f1f33f9063da558067307b00d44d40d Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 17:01:43 +0800
Subject: ALSA: ctxfi: cthw20k2: Replace mdelay() with msleep() and
 usleep_range()

hw_pll_init(), hw_dac_stop(), hw_dac_start() and hw_adc_init()
are never called in atomic context.
They call mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ctxfi/cthw20k2.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/sound/pci/ctxfi/cthw20k2.c b/sound/pci/ctxfi/cthw20k2.c
index b866d6b2c923..3c966fafc754 100644
--- a/sound/pci/ctxfi/cthw20k2.c
+++ b/sound/pci/ctxfi/cthw20k2.c
@@ -1316,12 +1316,12 @@ static int hw_pll_init(struct hw *hw, unsigned int rsr)
 	set_field(&pllctl, PLLCTL_FD, 48000 == rsr ? 16 - 4 : 147 - 4);
 	set_field(&pllctl, PLLCTL_RD, 48000 == rsr ? 1 - 1 : 10 - 1);
 	hw_write_20kx(hw, PLL_CTL, pllctl);
-	mdelay(40);
+	msleep(40);
 
 	pllctl = hw_read_20kx(hw, PLL_CTL);
 	set_field(&pllctl, PLLCTL_FD, 48000 == rsr ? 16 - 2 : 147 - 2);
 	hw_write_20kx(hw, PLL_CTL, pllctl);
-	mdelay(40);
+	msleep(40);
 
 	for (i = 0; i < 1000; i++) {
 		pllstat = hw_read_20kx(hw, PLL_STAT);
@@ -1584,7 +1584,7 @@ static void hw_dac_stop(struct hw *hw)
 	data = hw_read_20kx(hw, GPIO_DATA);
 	data &= 0xFFFFFFFD;
 	hw_write_20kx(hw, GPIO_DATA, data);
-	mdelay(10);
+	usleep_range(10000, 11000);
 }
 
 static void hw_dac_start(struct hw *hw)
@@ -1593,7 +1593,7 @@ static void hw_dac_start(struct hw *hw)
 	data = hw_read_20kx(hw, GPIO_DATA);
 	data |= 0x2;
 	hw_write_20kx(hw, GPIO_DATA, data);
-	mdelay(50);
+	msleep(50);
 }
 
 static void hw_dac_reset(struct hw *hw)
@@ -1864,11 +1864,11 @@ static int hw_adc_init(struct hw *hw, const struct adc_conf *info)
 		hw_write_20kx(hw, GPIO_DATA, data);
 	}
 
-	mdelay(10);
+	usleep_range(10000, 11000);
 	/* Return the ADC to normal operation. */
 	data |= (0x1 << 15);
 	hw_write_20kx(hw, GPIO_DATA, data);
-	mdelay(50);
+	msleep(50);
 
 	/* I2C write to register offset 0x0B to set ADC LRCLK polarity */
 	/* invert bit, interface format to I2S, word length to 24-bit, */
-- 
cgit v1.2.3


From 443eaa359be191f407bcfd52242cf3ce126d906a Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Wed, 25 Jul 2018 09:26:04 -0400
Subject: media: media-types.rst: codec entities can have more than one source
 pad

Some decoders and encoders can potentially have more than one source pad,
so update the description to say 'at least one source pad'.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-types.rst | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst
index 7b17acc049cf..0e9adc7869b8 100644
--- a/Documentation/media/uapi/mediactl/media-types.rst
+++ b/Documentation/media/uapi/mediactl/media-types.rst
@@ -192,12 +192,13 @@ Types and flags used to represent the media graph elements
 
     *  -  ``MEDIA_ENT_F_PROC_VIDEO_ENCODER``
        -  Video (MPEG, HEVC, VPx, etc.) encoder. An entity capable of
-          compressing video frames. Must have one sink pad and one source pad.
+          compressing video frames. Must have one sink pad and at least
+	  one source pad.
 
     *  -  ``MEDIA_ENT_F_PROC_VIDEO_DECODER``
        -  Video (MPEG, HEVC, VPx, etc.) decoder. An entity capable of
           decompressing a compressed video stream into uncompressed video
-	  frames. Must have one sink pad and one source pad.
+	  frames. Must have one sink pad and at least one source pad.
 
     *  -  ``MEDIA_ENT_F_VID_MUX``
        - Video multiplexer. An entity capable of multiplexing must have at
-- 
cgit v1.2.3


From 48db0089bff6f9154f6bd98ce7a6ae3786fa8ebe Mon Sep 17 00:00:00 2001
From: Mika Båtsman <mika.batsman@gmail.com>
Date: Wed, 16 May 2018 16:32:19 -0400
Subject: media: gl861: fix probe of dvb_usb_gl861
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Probe of dvb_usb_gl861 was working at least with v4.4. Noticed the issue
with v4.13 but according to similar issues the problem started with v4.9.

[   15.288065] transfer buffer not dma capable
[   15.288090] WARNING: CPU: 2 PID: 493 at drivers/usb/core/hcd.c:1595 usb_hcd_map_urb_for_dma+0x4e2/0x640
...CUT...
[   15.288791] dvb_usb_gl861: probe of 3-7:1.0 failed with error -5

Tested with MSI Mega Sky 580 DVB-T Tuner [GL861]

[mchehab+samsung@kernel.org: rebased on the top of upstream]
Cc: stable@vger.kernel.org
Signed-off-by: Mika Båtsman <mika.batsman@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb-v2/gl861.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/media/usb/dvb-usb-v2/gl861.c b/drivers/media/usb/dvb-usb-v2/gl861.c
index 9d154fdae45b..fee4b30df778 100644
--- a/drivers/media/usb/dvb-usb-v2/gl861.c
+++ b/drivers/media/usb/dvb-usb-v2/gl861.c
@@ -26,10 +26,14 @@ static int gl861_i2c_msg(struct dvb_usb_device *d, u8 addr,
 	if (wo) {
 		req = GL861_REQ_I2C_WRITE;
 		type = GL861_WRITE;
+		buf = kmemdup(wbuf, wlen, GFP_KERNEL);
 	} else { /* rw */
 		req = GL861_REQ_I2C_READ;
 		type = GL861_READ;
+		buf = kmalloc(rlen, GFP_KERNEL);
 	}
+	if (!buf)
+		return -ENOMEM;
 
 	switch (wlen) {
 	case 1:
@@ -42,24 +46,19 @@ static int gl861_i2c_msg(struct dvb_usb_device *d, u8 addr,
 	default:
 		dev_err(&d->udev->dev, "%s: wlen=%d, aborting\n",
 				KBUILD_MODNAME, wlen);
+		kfree(buf);
 		return -EINVAL;
 	}
-	buf = NULL;
-	if (rlen > 0) {
-		buf = kmalloc(rlen, GFP_KERNEL);
-		if (!buf)
-			return -ENOMEM;
-	}
+
 	usleep_range(1000, 2000); /* avoid I2C errors */
 
 	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0), req, type,
 			      value, index, buf, rlen, 2000);
-	if (rlen > 0) {
-		if (ret > 0)
-			memcpy(rbuf, buf, rlen);
-		kfree(buf);
-	}
 
+	if (!wo && ret > 0)
+		memcpy(rbuf, buf, rlen);
+
+	kfree(buf);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 8f2240cc4e4f2ae564f9235560fca3e2115d77e0 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Sun, 20 May 2018 02:50:32 -0400
Subject: media: netup_unidvb: don't check number of messages in the driver

Since commit 1eace8344c02 ("i2c: add param sanity check to
i2c_transfer()"), the I2C core does this check now. We can remove it
from drivers.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
index b13e319d24b7..5f1613aec93c 100644
--- a/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
+++ b/drivers/media/pci/netup_unidvb/netup_unidvb_i2c.c
@@ -214,11 +214,6 @@ static int netup_i2c_xfer(struct i2c_adapter *adap,
 	struct netup_i2c *i2c = i2c_get_adapdata(adap);
 	u16 reg;
 
-	if (num <= 0) {
-		dev_dbg(i2c->adap.dev.parent,
-			"%s(): num == %d\n", __func__, num);
-		return -EINVAL;
-	}
 	spin_lock_irqsave(&i2c->lock, flags);
 	if (i2c->state != STATE_DONE) {
 		dev_dbg(i2c->adap.dev.parent,
-- 
cgit v1.2.3


From a27c0cad9e658dbc548e6731d9416b793fa68f03 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Sun, 20 May 2018 02:50:37 -0400
Subject: media: tm6000: don't check number of messages in the driver

Since commit 1eace8344c02 ("i2c: add param sanity check to
i2c_transfer()"), the I2C core does this check now. We can remove it
from drivers.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/tm6000/tm6000-i2c.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/usb/tm6000/tm6000-i2c.c b/drivers/media/usb/tm6000/tm6000-i2c.c
index 659b63febf85..ccd1adf862b1 100644
--- a/drivers/media/usb/tm6000/tm6000-i2c.c
+++ b/drivers/media/usb/tm6000/tm6000-i2c.c
@@ -145,8 +145,6 @@ static int tm6000_i2c_xfer(struct i2c_adapter *i2c_adap,
 	struct tm6000_core *dev = i2c_adap->algo_data;
 	int addr, rc, i, byte;
 
-	if (num <= 0)
-		return 0;
 	for (i = 0; i < num; i++) {
 		addr = (msgs[i].addr << 1) & 0xff;
 		i2c_dprintk(2, "%s %s addr=0x%x len=%d:",
-- 
cgit v1.2.3


From decb9f225efda830f2193edcce6b750b7be18150 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Sun, 20 May 2018 02:50:38 -0400
Subject: media: dvb-usb: don't check number of messages in the driver

Since commit 1eace8344c02 ("i2c: add param sanity check to
i2c_transfer()"), the I2C core does this check now. We can remove it
from drivers.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb/m920x.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/media/usb/dvb-usb/m920x.c b/drivers/media/usb/dvb-usb/m920x.c
index 51b026fa6bfb..22554d9abd43 100644
--- a/drivers/media/usb/dvb-usb/m920x.c
+++ b/drivers/media/usb/dvb-usb/m920x.c
@@ -255,9 +255,6 @@ static int m920x_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int nu
 	int i, j;
 	int ret = 0;
 
-	if (!num)
-		return -EINVAL;
-
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
 
-- 
cgit v1.2.3


From 0eaddd7cc0ad8a6165345c08cfa62a6833c05830 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Sun, 20 May 2018 02:50:36 -0400
Subject: media: hdpvr: don't check number of messages in the driver

Since commit 1eace8344c02 ("i2c: add param sanity check to
i2c_transfer()"), the I2C core does this check now. We can remove it
from drivers.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/hdpvr/hdpvr-i2c.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/media/usb/hdpvr/hdpvr-i2c.c b/drivers/media/usb/hdpvr/hdpvr-i2c.c
index c71ddefd2e58..5a3cb614a211 100644
--- a/drivers/media/usb/hdpvr/hdpvr-i2c.c
+++ b/drivers/media/usb/hdpvr/hdpvr-i2c.c
@@ -117,9 +117,6 @@ static int hdpvr_transfer(struct i2c_adapter *i2c_adapter, struct i2c_msg *msgs,
 	struct hdpvr_device *dev = i2c_get_adapdata(i2c_adapter);
 	int retval = 0, addr;
 
-	if (num <= 0)
-		return 0;
-
 	mutex_lock(&dev->i2c_mutex);
 
 	addr = msgs[0].addr << 1;
-- 
cgit v1.2.3


From 4e4ddfd8e3123cdac71c6f97c35427cc5daeb1bf Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Sun, 20 May 2018 02:50:35 -0400
Subject: media: em28xx: don't check number of messages in the driver

Since commit 1eace8344c02 ("i2c: add param sanity check to
i2c_transfer()"), the I2C core does this check now. We can remove it
from drivers.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-i2c.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/media/usb/em28xx/em28xx-i2c.c b/drivers/media/usb/em28xx/em28xx-i2c.c
index 6458682bc6e2..e19d6342e0d0 100644
--- a/drivers/media/usb/em28xx/em28xx-i2c.c
+++ b/drivers/media/usb/em28xx/em28xx-i2c.c
@@ -559,10 +559,6 @@ static int em28xx_i2c_xfer(struct i2c_adapter *i2c_adap,
 		dev->cur_i2c_bus = bus;
 	}
 
-	if (num <= 0) {
-		rt_mutex_unlock(&dev->i2c_bus_lock);
-		return 0;
-	}
 	for (i = 0; i < num; i++) {
 		addr = msgs[i].addr << 1;
 		if (!msgs[i].len) {
-- 
cgit v1.2.3


From a6e65c2ce8970db5a8d0536774ccb9346e69b064 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Sun, 20 May 2018 02:50:33 -0400
Subject: media: si4713: don't check number of messages in the driver

Since commit 1eace8344c02 ("i2c: add param sanity check to
i2c_transfer()"), the I2C core does this check now. We can remove it
from drivers.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/radio/si4713/radio-usb-si4713.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/media/radio/si4713/radio-usb-si4713.c b/drivers/media/radio/si4713/radio-usb-si4713.c
index 05c66701a899..1ebbf0217142 100644
--- a/drivers/media/radio/si4713/radio-usb-si4713.c
+++ b/drivers/media/radio/si4713/radio-usb-si4713.c
@@ -370,9 +370,6 @@ static int si4713_transfer(struct i2c_adapter *i2c_adapter,
 	int retval = -EINVAL;
 	int i;
 
-	if (num <= 0)
-		return 0;
-
 	for (i = 0; i < num; i++) {
 		if (msgs[i].flags & I2C_M_RD)
 			retval = si4713_i2c_read(radio, msgs[i].buf, msgs[i].len);
-- 
cgit v1.2.3


From ada19043e5c6fd66d2b8e11c49e27c55c48f3b7c Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa@the-dreams.de>
Date: Sun, 20 May 2018 02:50:34 -0400
Subject: media: cx231xx: don't check number of messages in the driver

Since commit 1eace8344c02 ("i2c: add param sanity check to
i2c_transfer()"), the I2C core does this check now. We can remove it
from drivers.

Signed-off-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/cx231xx/cx231xx-i2c.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/usb/cx231xx/cx231xx-i2c.c b/drivers/media/usb/cx231xx/cx231xx-i2c.c
index 6e1bef2a45bb..15a91169e749 100644
--- a/drivers/media/usb/cx231xx/cx231xx-i2c.c
+++ b/drivers/media/usb/cx231xx/cx231xx-i2c.c
@@ -376,8 +376,6 @@ static int cx231xx_i2c_xfer(struct i2c_adapter *i2c_adap,
 	struct cx231xx *dev = bus->dev;
 	int addr, rc, i, byte;
 
-	if (num <= 0)
-		return 0;
 	mutex_lock(&dev->i2c_lock);
 	for (i = 0; i < num; i++) {
 
-- 
cgit v1.2.3


From f2047d6044e530c05a618a33d1be09b1498f9e0b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 22 May 2018 12:04:59 -0400
Subject: media: dvb-bt8xx: remove duplicate code

The same code is executed regardless of whether c->frequency < 600000000
or c->frequency < 730000000 is true.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/bt8xx/dvb-bt8xx.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/media/pci/bt8xx/dvb-bt8xx.c b/drivers/media/pci/bt8xx/dvb-bt8xx.c
index 5ef6e2051d45..6b2a9e6eb6a8 100644
--- a/drivers/media/pci/bt8xx/dvb-bt8xx.c
+++ b/drivers/media/pci/bt8xx/dvb-bt8xx.c
@@ -386,10 +386,6 @@ static int advbt771_samsung_tdtc9251dh0_tuner_calc_regs(struct dvb_frontend *fe,
 		bs = 0x02;
 	else if (c->frequency < 470000000)
 		bs = 0x02;
-	else if (c->frequency < 600000000)
-		bs = 0x08;
-	else if (c->frequency < 730000000)
-		bs = 0x08;
 	else
 		bs = 0x08;
 
-- 
cgit v1.2.3


From b094e64fbd88dfcde137c2235b58c904ccac00ea Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 22 May 2018 12:20:01 -0400
Subject: media: dib0700: add code comment

Add FIXME code comment:
/* FIXME: check if it is fe_adap[1] */

It is likely that it should be adap->fe_adap[1].fe in the second clause,
but this has never been verified.

Suggested-by: Mauro Carvalho Chehab <mchehab@kernel.org>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb/dib0700_devices.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/usb/dvb-usb/dib0700_devices.c b/drivers/media/usb/dvb-usb/dib0700_devices.c
index c53a969bc6be..091389fdf89e 100644
--- a/drivers/media/usb/dvb-usb/dib0700_devices.c
+++ b/drivers/media/usb/dvb-usb/dib0700_devices.c
@@ -1745,6 +1745,7 @@ static int dib809x_tuner_attach(struct dvb_usb_adapter *adap)
 		if (dvb_attach(dib0090_register, adap->fe_adap[0].fe, tun_i2c, &dib809x_dib0090_config) == NULL)
 			return -ENODEV;
 	} else {
+		/* FIXME: check if it is fe_adap[1] */
 		if (dvb_attach(dib0090_register, adap->fe_adap[0].fe, tun_i2c, &dib809x_dib0090_config) == NULL)
 			return -ENODEV;
 	}
-- 
cgit v1.2.3


From 64004337d0d8842b8993107c8427b80d6e36646c Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Thu, 26 Jul 2018 03:11:01 -0400
Subject: media: vicodec: current -> cur

'current' is also defined in asm-generic/current.h.

When compiling this driver for older kernels with the media_build system,
this header is included via compat.h and it no longer compiles. Rename
current to cur.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vicodec/vicodec-codec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/vicodec/vicodec-codec.c b/drivers/media/platform/vicodec/vicodec-codec.c
index e880a6c5747f..2d047646f614 100644
--- a/drivers/media/platform/vicodec/vicodec-codec.c
+++ b/drivers/media/platform/vicodec/vicodec-codec.c
@@ -555,7 +555,7 @@ static int var_inter(const s16 *old, const s16 *new)
 	return ret;
 }
 
-static int decide_blocktype(const u8 *current, const u8 *reference,
+static int decide_blocktype(const u8 *cur, const u8 *reference,
 			    s16 *deltablock, unsigned int stride,
 			    unsigned int input_step)
 {
@@ -566,7 +566,7 @@ static int decide_blocktype(const u8 *current, const u8 *reference,
 	int vari;
 	int vard;
 
-	fill_encoder_block(current, tmp, stride, input_step);
+	fill_encoder_block(cur, tmp, stride, input_step);
 	fill_encoder_block(reference, old, 8, 1);
 	vari = var_intra(tmp);
 
-- 
cgit v1.2.3


From a7853c257a3ea0907467a1750ff45de4d9ba1915 Mon Sep 17 00:00:00 2001
From: Brad Love <brad@nextdimension.cc>
Date: Thu, 28 Jun 2018 13:29:09 -0400
Subject: media: em28xx: Fix dual transport stream operation

Addresses the following, which introduced a regression itself:

Commit 509f89652f83 ("media: em28xx: fix a regression with HVR-950")

The regression fix breaks dual transport stream support. Currently,
when a tuner starts streaming it sets alt mode on the USB interface.
The problem is, in a dual tuner model, both tuners share the same
USB interface, so when the second tuner becomes active and sets alt
mode on the interface it kills streaming on the other port.

This patch addresses the regression by only setting alt mode
on the USB interface during em28xx_start_streaming, if the
device is not a dual tuner model. This allows all older and
single tuner devices to explicitly set alt mode during stream
startup. Testers report both isoc and bulk DualHD models work
correctly with the alt mode set only once, in em28xx_dvb_init.

Fixes: 509f89652f83 ("media: em28xx: fix a regression with HVR-950")
Signed-off-by: Brad Love <brad@nextdimension.cc>
Signed-off-by: Michael Ira Krufky <mkrufky@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-dvb.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/usb/em28xx/em28xx-dvb.c b/drivers/media/usb/em28xx/em28xx-dvb.c
index b778d8a1983e..a73faf12f7e4 100644
--- a/drivers/media/usb/em28xx/em28xx-dvb.c
+++ b/drivers/media/usb/em28xx/em28xx-dvb.c
@@ -218,7 +218,9 @@ static int em28xx_start_streaming(struct em28xx_dvb *dvb)
 		dvb_alt = dev->dvb_alt_isoc;
 	}
 
-	usb_set_interface(udev, dev->ifnum, dvb_alt);
+	if (!dev->board.has_dual_ts)
+		usb_set_interface(udev, dev->ifnum, dvb_alt);
+
 	rc = em28xx_set_mode(dev, EM28XX_DIGITAL_MODE);
 	if (rc < 0)
 		return rc;
-- 
cgit v1.2.3


From 20cdcaf903298d54b834daedf65a2ddef70cae0a Mon Sep 17 00:00:00 2001
From: Brad Love <brad@nextdimension.cc>
Date: Wed, 27 Jun 2018 11:32:01 -0400
Subject: media: em28xx: Fix DualHD disconnect oops

During the duplication of em28xx state for the second tuner pair
a pointer to alt_max_pkt_size_isoc is copied. During tear down
the second tuner is destroyed first and kfrees alt_max_pkt_size_isoc,
then the first tuner is destroyed and kfrees it again. The property
should only be kfree'd if the tuner is PRIMARY_TS.

[  354.888560] ------------[ cut here ]------------
[  354.888562] kernel BUG at mm/slub.c:296!
[  354.888574] invalid opcode: 0000 [#1] SMP NOPTI
[  354.888869] CPU: 1 PID: 19 Comm: kworker/1:0 Not tainted 4.18.0-rc1+ #20
[  354.889140] Hardware name: MSI MS-7A39/B350M GAMING PRO (MS-7A39), BIOS 2.G0 04/27/2018
[  354.889408] Workqueue: usb_hub_wq hub_event
[  354.889679] RIP: 0010:__slab_free+0x217/0x370
[  354.889942] Code: bb c0 e8 07 41 38 c7 72 39 48 83 c4 70 5b 41 5a 41 5c 41 5d 41 5e 41 5f 5d 49 8d 62 f8 c3 f3 90 49 8b 04 24 a8 01 75 f6 eb 82 <0f> 0b 44 89 45 80 48 89 4d 88 e8 aa fa ff ff 85 c0 74 cc e9 b7 fe
[  354.890598] RSP: 0018:ffffb84c41a4fad0 EFLAGS: 00010246
[  354.890934] RAX: ffff948646e85150 RBX: ffff948646e85150 RCX: ffff948646e85150
[  354.891280] RDX: 00000000820001d9 RSI: fffffa8fd01ba140 RDI: ffff94865e807c00
[  354.891649] RBP: ffffb84c41a4fb70 R08: 0000000000000001 R09: ffffffffc059ce21
[  354.892025] R10: ffff948646e85150 R11: 0000000000000001 R12: fffffa8fd01ba140
[  354.892403] R13: ffff948646e85150 R14: ffff94865e807c00 R15: ffff94864c92e0a0
[  354.892780] FS:  0000000000000000(0000) GS:ffff94865ec40000(0000) knlGS:0000000000000000
[  354.893150] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  354.893530] CR2: 00007f4e476da950 CR3: 000000040112c000 CR4: 00000000003406e0
[  354.893917] Call Trace:
[  354.894315]  ? __dev_printk+0x3c/0x80
[  354.894695]  ? _dev_info+0x64/0x80
[  354.895082]  ? em28xx_free_device+0x41/0x50 [em28xx]
[  354.895464]  kfree+0x17a/0x190
[  354.895852]  ? kfree+0x17a/0x190
[  354.896310]  em28xx_free_device+0x41/0x50 [em28xx]
[  354.896698]  em28xx_usb_disconnect+0xfa/0x110 [em28xx]
[  354.897083]  usb_unbind_interface+0x7a/0x270
[  354.897475]  device_release_driver_internal+0x17c/0x250
[  354.897864]  device_release_driver+0x12/0x20
[  354.898252]  bus_remove_device+0xec/0x160
[  354.898639]  device_del+0x13d/0x320
[  354.899018]  ? usb_remove_ep_devs+0x1f/0x30
[  354.899392]  usb_disable_device+0x9e/0x270
[  354.899772]  usb_disconnect+0x92/0x2a0
[  354.900149]  hub_event+0x98e/0x1650
[  354.900519]  ? sched_clock_cpu+0x11/0xa0
[  354.900890]  process_one_work+0x167/0x3f0
[  354.901251]  worker_thread+0x4d/0x460
[  354.901610]  kthread+0x105/0x140
[  354.901964]  ? rescuer_thread+0x360/0x360
[  354.902318]  ? kthread_associate_blkcg+0xa0/0xa0
[  354.902672]  ret_from_fork+0x22/0x40
[  354.903024] Modules linked in: rc_hauppauge em28xx_rc rc_core si2157 lgdt3306a i2c_mux em28xx_dvb dvb_core videobuf2_vmalloc videobuf2_memops videobuf2_common snd_hda_codec_hdmi nls_iso8859_1 edac_mce_amd kvm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel pcbc snd_hda_intel snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_seq_midi aesni_intel snd_seq_midi_event aes_x86_64 snd_rawmidi crypto_simd em28xx cryptd glue_helper asix tveeprom usbnet snd_seq v4l2_common mii videodev snd_seq_device media input_leds snd_timer joydev ccp k10temp wmi_bmof snd soundcore mac_hid sch_fq_codel parport_pc ppdev lp parport ip_tables x_tables vfio_pci vfio_virqfd irqbypass vfio_iommu_type1 vfio nouveau mxm_wmi video i2c_algo_bit ttm drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops i2c_piix4 drm ahci libahci
[  354.905129]  wmi gpio_amdpt gpio_generic hid_generic usbhid hid
[  354.908140] ---[ end trace c230d02716298c34 ]---
[  354.908145] RIP: 0010:__slab_free+0x217/0x370
[  354.908147] Code: bb c0 e8 07 41 38 c7 72 39 48 83 c4 70 5b 41 5a 41 5c 41 5d 41 5e 41 5f 5d 49 8d 62 f8 c3 f3 90 49 8b 04 24 a8 01 75 f6 eb 82 <0f> 0b 44 89 45 80 48 89 4d 88 e8 aa fa ff ff 85 c0 74 cc e9 b7 fe
[  354.908183] RSP: 0018:ffffb84c41a4fad0 EFLAGS: 00010246
[  354.908186] RAX: ffff948646e85150 RBX: ffff948646e85150 RCX: ffff948646e85150
[  354.908189] RDX: 00000000820001d9 RSI: fffffa8fd01ba140 RDI: ffff94865e807c00
[  354.908191] RBP: ffffb84c41a4fb70 R08: 0000000000000001 R09: ffffffffc059ce21
[  354.908193] R10: ffff948646e85150 R11: 0000000000000001 R12: fffffa8fd01ba140
[  354.908195] R13: ffff948646e85150 R14: ffff94865e807c00 R15: ffff94864c92e0a0
[  354.908198] FS:  0000000000000000(0000) GS:ffff94865ec40000(0000) knlGS:0000000000000000
[  354.908201] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  354.908203] CR2: 00007f4e476da950 CR3: 000000016b20a000 CR4: 00000000003406e0

Signed-off-by: Brad Love <brad@nextdimension.cc>
Signed-off-by: Michael Ira Krufky <mkrufky@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-cards.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 6c8438311d3b..ff5e41ac4723 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -3376,7 +3376,9 @@ void em28xx_free_device(struct kref *ref)
 	if (!dev->disconnected)
 		em28xx_release_resources(dev);
 
-	kfree(dev->alt_max_pkt_size_isoc);
+	if (dev->ts == PRIMARY_TS)
+		kfree(dev->alt_max_pkt_size_isoc);
+
 	kfree(dev);
 }
 EXPORT_SYMBOL_GPL(em28xx_free_device);
-- 
cgit v1.2.3


From 5871f8bc08bc68f7d69820d40f5a0cd50c573cf6 Mon Sep 17 00:00:00 2001
From: Brad Love <brad@nextdimension.cc>
Date: Wed, 27 Jun 2018 11:32:00 -0400
Subject: media: em28xx: Remove duplicate PID

Half-revert: commit 5b1a270d224b ("media: dvb: add alternative USB PID for Hauppauge WinTV-soloHD")'

The PID already exists on the line above.

Signed-off-by: Brad Love <brad@nextdimension.cc>
Signed-off-by: Michael Ira Krufky <mkrufky@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-cards.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index ff5e41ac4723..48bc505a872a 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -2688,8 +2688,6 @@ struct usb_device_id em28xx_id_table[] = {
 			.driver_info = EM28178_BOARD_PCTV_292E },
 	{ USB_DEVICE(0x2040, 0x8268), /* Hauppauge Retail WinTV-soloHD Bulk */
 			.driver_info = EM28178_BOARD_PCTV_292E },
-	{ USB_DEVICE(0x2040, 0x8268), /* Hauppauge WinTV-soloHD alt. PID */
-			.driver_info = EM28178_BOARD_PCTV_292E },
 	{ USB_DEVICE(0x0413, 0x6f07),
 			.driver_info = EM2861_BOARD_LEADTEK_VC100 },
 	{ USB_DEVICE(0xeb1a, 0x8179),
-- 
cgit v1.2.3


From 0900dc319245774ce5f0abcf0484df53457c36b7 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab@infradead.org>
Date: Thu, 28 Jun 2018 14:43:21 -0400
Subject: media: em28xx-cards: disable V4L2 mode for dual tuners

Right now, the code that calculates alternate modes is not ready
for devices with dual tuners. That's ok, as we currently don't
have any such devices, but better to add a warning for such
case, as, if anyone adds such device, the logic will need to
be reviewed.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Acked-by: Brad Love <brad@nextdimension.cc>
Reviewed-by: Michael Ira Krufky <mkrufky@linuxtv.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-cards.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 48bc505a872a..afdc92998fff 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -3861,6 +3861,17 @@ static int em28xx_usb_probe(struct usb_interface *intf,
 		dev->has_video = false;
 	}
 
+	if (dev->board.has_dual_ts &&
+	    (dev->tuner_type != TUNER_ABSENT || INPUT(0)->type)) {
+		/*
+		 * The logic with sets alternate is not ready for dual-tuners
+		 * which analog modes.
+		 */
+		dev_err(&intf->dev,
+			"We currently don't support analog TV or stream capture on dual tuners.\n");
+		has_video = false;
+	}
+
 	/* Select USB transfer types to use */
 	if (has_video) {
 		if (!dev->analog_ep_isoc || (try_bulk && dev->analog_ep_bulk))
-- 
cgit v1.2.3


From ec55cdba4168d665670335e13697fc01a69f2785 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham@ideasonboard.com>
Date: Tue, 20 Mar 2018 11:43:08 -0400
Subject: media: uvcvideo: Fix minor spelling

Provide the missing 't' from straightforward.

Signed-off-by: Kieran Bingham <kieran.bingham@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/uvc/uvc_ctrl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index a36b4fb949fa..4042cbdb721b 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -1125,7 +1125,7 @@ done:
 }
 
 /*
- * Mapping V4L2 controls to UVC controls can be straighforward if done well.
+ * Mapping V4L2 controls to UVC controls can be straightforward if done well.
  * Most of the UVC controls exist in V4L2, and can be mapped directly. Some
  * must be grouped (for instance the Red Balance, Blue Balance and Do White
  * Balance V4L2 controls use the White Balance Component UVC control) or
-- 
cgit v1.2.3


From 557a5c7fe6503230f6a3a41441981aed6e897d17 Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Date: Wed, 21 Mar 2018 05:16:40 -0400
Subject: media: uvcvideo: Add KSMedia 8-bit IR format support

Add support for the 8-bit IR format GUID defined in the Microsoft Kernel
Streaming Media API.

Reported-by: Paul Menzel <pmenzel+linux-media@molgen.mpg.de>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Tested-by: Paul Menzel <pmenzel+linux-media@molgen.mpg.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/uvc/uvc_driver.c | 5 +++++
 drivers/media/usb/uvc/uvcvideo.h   | 3 +++
 2 files changed, 8 insertions(+)

diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index 8e138201330f..d46dc432456c 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -99,6 +99,11 @@ static struct uvc_format_desc uvc_fmts[] = {
 		.guid		= UVC_GUID_FORMAT_D3DFMT_L8,
 		.fcc		= V4L2_PIX_FMT_GREY,
 	},
+	{
+		.name		= "IR 8-bit (L8_IR)",
+		.guid		= UVC_GUID_FORMAT_KSMEDIA_L8_IR,
+		.fcc		= V4L2_PIX_FMT_GREY,
+	},
 	{
 		.name		= "Greyscale 10-bit (Y10 )",
 		.guid		= UVC_GUID_FORMAT_Y10,
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index be5cf179228b..6b955e0dd956 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -157,6 +157,9 @@
 #define UVC_GUID_FORMAT_D3DFMT_L8 \
 	{0x32, 0x00, 0x00, 0x00, 0x00, 0x00, 0x10, 0x00, \
 	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
+#define UVC_GUID_FORMAT_KSMEDIA_L8_IR \
+	{0x32, 0x00, 0x00, 0x00, 0x02, 0x00, 0x10, 0x00, \
+	 0x80, 0x00, 0x00, 0xaa, 0x00, 0x38, 0x9b, 0x71}
 
 
 /* ------------------------------------------------------------------------
-- 
cgit v1.2.3


From 95f5cbff90b9e4324839a5c28ee3153a3c9921a5 Mon Sep 17 00:00:00 2001
From: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Date: Mon, 4 Jun 2018 20:24:15 -0400
Subject: media: uvcvideo: Also validate buffers in BULK mode

Just like for ISOC, validate the decoded BULK buffer size when possible.
This avoids sending corrupted or partial buffers to userspace, which may
lead to application crash or run-time failure.

Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
[laurent.pinchart@ideasonboard.com: Move uvc_video_validate_buffer() call to uvc_video_next_buffers()]
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/uvc/uvc_video.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index a88b2e51a666..3ed5f27e786b 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -1232,6 +1232,8 @@ static void uvc_video_validate_buffer(const struct uvc_streaming *stream,
 static void uvc_video_next_buffers(struct uvc_streaming *stream,
 		struct uvc_buffer **video_buf, struct uvc_buffer **meta_buf)
 {
+	uvc_video_validate_buffer(stream, *video_buf);
+
 	if (*meta_buf) {
 		struct vb2_v4l2_buffer *vb2_meta = &(*meta_buf)->buf;
 		const struct vb2_v4l2_buffer *vb2_video = &(*video_buf)->buf;
@@ -1270,10 +1272,8 @@ static void uvc_video_decode_isoc(struct urb *urb, struct uvc_streaming *stream,
 		do {
 			ret = uvc_video_decode_start(stream, buf, mem,
 				urb->iso_frame_desc[i].actual_length);
-			if (ret == -EAGAIN) {
-				uvc_video_validate_buffer(stream, buf);
+			if (ret == -EAGAIN)
 				uvc_video_next_buffers(stream, &buf, &meta_buf);
-			}
 		} while (ret == -EAGAIN);
 
 		if (ret < 0)
@@ -1289,10 +1289,8 @@ static void uvc_video_decode_isoc(struct urb *urb, struct uvc_streaming *stream,
 		uvc_video_decode_end(stream, buf, mem,
 			urb->iso_frame_desc[i].actual_length);
 
-		if (buf->state == UVC_BUF_STATE_READY) {
-			uvc_video_validate_buffer(stream, buf);
+		if (buf->state == UVC_BUF_STATE_READY)
 			uvc_video_next_buffers(stream, &buf, &meta_buf);
-		}
 	}
 }
 
-- 
cgit v1.2.3


From 222964eaf2472053221341c331eb81e87c8b04f2 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <guennadi.liakhovetski@intel.com>
Date: Tue, 8 May 2018 11:07:42 -0400
Subject: media: uvcvideo: Remove a redundant check

Event subscribers cannot have a NULL file handle. They are only added
at a single location in the code, and the .fh pointer is used without
checking there.

Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@intel.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/uvc/uvc_ctrl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index 4042cbdb721b..12b5be66fd2f 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -1229,9 +1229,9 @@ static void uvc_ctrl_send_event(struct uvc_fh *handle,
 	uvc_ctrl_fill_event(handle->chain, &ev, ctrl, mapping, value, changes);
 
 	list_for_each_entry(sev, &mapping->ev_subs, node) {
-		if (sev->fh && (sev->fh != &handle->vfh ||
+		if (sev->fh != &handle->vfh ||
 		    (sev->flags & V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK) ||
-		    (changes & V4L2_EVENT_CTRL_CH_FLAGS)))
+		    (changes & V4L2_EVENT_CTRL_CH_FLAGS))
 			v4l2_event_queue_fh(sev->fh, &ev);
 	}
 }
-- 
cgit v1.2.3


From 8e7a1dbc7b0ae048bf3f4b9707fe1a845e69aab7 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <guennadi.liakhovetski@intel.com>
Date: Tue, 8 May 2018 11:07:44 -0400
Subject: media: uvcvideo: Handle control pipe protocol STALLs

When a command ends up in a STALL on the control pipe, use the Request
Error Code control to provide a more precise error information to the
user. For example, if a camera is still busy processing a control,
when the same or an interrelated control set request arrives, the
camera can react with a STALL and then return the "Not ready" status
in response to a UVC_VC_REQUEST_ERROR_CODE_CONTROL command. With this
patch the user would then get an EBUSY error code instead of a
generic EPIPE.

Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@intel.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/uvc/uvc_video.c | 52 ++++++++++++++++++++++++++++++++++-----
 1 file changed, 46 insertions(+), 6 deletions(-)

diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
index 3ed5f27e786b..86a99f461fd8 100644
--- a/drivers/media/usb/uvc/uvc_video.c
+++ b/drivers/media/usb/uvc/uvc_video.c
@@ -73,17 +73,57 @@ int uvc_query_ctrl(struct uvc_device *dev, u8 query, u8 unit,
 			u8 intfnum, u8 cs, void *data, u16 size)
 {
 	int ret;
+	u8 error;
+	u8 tmp;
 
 	ret = __uvc_query_ctrl(dev, query, unit, intfnum, cs, data, size,
 				UVC_CTRL_CONTROL_TIMEOUT);
-	if (ret != size) {
-		uvc_printk(KERN_ERR, "Failed to query (%s) UVC control %u on "
-			"unit %u: %d (exp. %u).\n", uvc_query_name(query), cs,
-			unit, ret, size);
-		return -EIO;
+	if (likely(ret == size))
+		return 0;
+
+	uvc_printk(KERN_ERR,
+		   "Failed to query (%s) UVC control %u on unit %u: %d (exp. %u).\n",
+		   uvc_query_name(query), cs, unit, ret, size);
+
+	if (ret != -EPIPE)
+		return ret;
+
+	tmp = *(u8 *)data;
+
+	ret = __uvc_query_ctrl(dev, UVC_GET_CUR, 0, intfnum,
+			       UVC_VC_REQUEST_ERROR_CODE_CONTROL, data, 1,
+			       UVC_CTRL_CONTROL_TIMEOUT);
+
+	error = *(u8 *)data;
+	*(u8 *)data = tmp;
+
+	if (ret != 1)
+		return ret < 0 ? ret : -EPIPE;
+
+	uvc_trace(UVC_TRACE_CONTROL, "Control error %u\n", error);
+
+	switch (error) {
+	case 0:
+		/* Cannot happen - we received a STALL */
+		return -EPIPE;
+	case 1: /* Not ready */
+		return -EBUSY;
+	case 2: /* Wrong state */
+		return -EILSEQ;
+	case 3: /* Power */
+		return -EREMOTE;
+	case 4: /* Out of range */
+		return -ERANGE;
+	case 5: /* Invalid unit */
+	case 6: /* Invalid control */
+	case 7: /* Invalid Request */
+	case 8: /* Invalid value within range */
+		return -EINVAL;
+	default: /* reserved or unknown */
+		break;
 	}
 
-	return 0;
+	return -EPIPE;
 }
 
 static void uvc_fixup_video_ctrl(struct uvc_streaming *stream,
-- 
cgit v1.2.3


From e5225c820c057537dc780244760e2e24c7d27366 Mon Sep 17 00:00:00 2001
From: Guennadi Liakhovetski <guennadi.liakhovetski@intel.com>
Date: Thu, 26 Jul 2018 04:17:53 -0400
Subject: media: uvcvideo: Send a control event when a Control Change interrupt
 arrives

UVC defines a method of handling asynchronous controls, which sends a
USB packet over the interrupt pipe. This patch implements support for
such packets by sending a control event to the user. Since this can
involve USB traffic and, therefore, scheduling, this has to be done
in a work queue.

Signed-off-by: Guennadi Liakhovetski <guennadi.liakhovetski@intel.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/uvc/uvc_ctrl.c   | 211 ++++++++++++++++++++++++++++---------
 drivers/media/usb/uvc/uvc_status.c | 121 ++++++++++++++++++---
 drivers/media/usb/uvc/uvc_v4l2.c   |   4 +-
 drivers/media/usb/uvc/uvcvideo.h   |  15 ++-
 include/uapi/linux/uvcvideo.h      |   2 +
 5 files changed, 286 insertions(+), 67 deletions(-)

diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
index 12b5be66fd2f..c2ad102bd693 100644
--- a/drivers/media/usb/uvc/uvc_ctrl.c
+++ b/drivers/media/usb/uvc/uvc_ctrl.c
@@ -20,6 +20,7 @@
 #include <linux/videodev2.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
+#include <linux/workqueue.h>
 #include <linux/atomic.h>
 #include <media/v4l2-ctrls.h>
 
@@ -971,12 +972,30 @@ static int uvc_ctrl_populate_cache(struct uvc_video_chain *chain,
 	return 0;
 }
 
+static s32 __uvc_ctrl_get_value(struct uvc_control_mapping *mapping,
+				const u8 *data)
+{
+	s32 value = mapping->get(mapping, UVC_GET_CUR, data);
+
+	if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) {
+		struct uvc_menu_info *menu = mapping->menu_info;
+		unsigned int i;
+
+		for (i = 0; i < mapping->menu_count; ++i, ++menu) {
+			if (menu->value == value) {
+				value = i;
+				break;
+			}
+		}
+	}
+
+	return value;
+}
+
 static int __uvc_ctrl_get(struct uvc_video_chain *chain,
 	struct uvc_control *ctrl, struct uvc_control_mapping *mapping,
 	s32 *value)
 {
-	struct uvc_menu_info *menu;
-	unsigned int i;
 	int ret;
 
 	if ((ctrl->info.flags & UVC_CTRL_FLAG_GET_CUR) == 0)
@@ -993,18 +1012,8 @@ static int __uvc_ctrl_get(struct uvc_video_chain *chain,
 		ctrl->loaded = 1;
 	}
 
-	*value = mapping->get(mapping, UVC_GET_CUR,
-		uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
-
-	if (mapping->v4l2_type == V4L2_CTRL_TYPE_MENU) {
-		menu = mapping->menu_info;
-		for (i = 0; i < mapping->menu_count; ++i, ++menu) {
-			if (menu->value == *value) {
-				*value = i;
-				break;
-			}
-		}
-	}
+	*value = __uvc_ctrl_get_value(mapping,
+				uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
 
 	return 0;
 }
@@ -1216,53 +1225,135 @@ static void uvc_ctrl_fill_event(struct uvc_video_chain *chain,
 	ev->u.ctrl.default_value = v4l2_ctrl.default_value;
 }
 
-static void uvc_ctrl_send_event(struct uvc_fh *handle,
-	struct uvc_control *ctrl, struct uvc_control_mapping *mapping,
-	s32 value, u32 changes)
+/*
+ * Send control change events to all subscribers for the @ctrl control. By
+ * default the subscriber that generated the event, as identified by @handle,
+ * is not notified unless it has set the V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK flag.
+ * @handle can be NULL for asynchronous events related to auto-update controls,
+ * in which case all subscribers are notified.
+ */
+static void uvc_ctrl_send_event(struct uvc_video_chain *chain,
+	struct uvc_fh *handle, struct uvc_control *ctrl,
+	struct uvc_control_mapping *mapping, s32 value, u32 changes)
 {
+	struct v4l2_fh *originator = handle ? &handle->vfh : NULL;
 	struct v4l2_subscribed_event *sev;
 	struct v4l2_event ev;
 
 	if (list_empty(&mapping->ev_subs))
 		return;
 
-	uvc_ctrl_fill_event(handle->chain, &ev, ctrl, mapping, value, changes);
+	uvc_ctrl_fill_event(chain, &ev, ctrl, mapping, value, changes);
 
 	list_for_each_entry(sev, &mapping->ev_subs, node) {
-		if (sev->fh != &handle->vfh ||
+		if (sev->fh != originator ||
 		    (sev->flags & V4L2_EVENT_SUB_FL_ALLOW_FEEDBACK) ||
 		    (changes & V4L2_EVENT_CTRL_CH_FLAGS))
 			v4l2_event_queue_fh(sev->fh, &ev);
 	}
 }
 
-static void uvc_ctrl_send_slave_event(struct uvc_fh *handle,
-	struct uvc_control *master, u32 slave_id,
-	const struct v4l2_ext_control *xctrls, unsigned int xctrls_count)
+/*
+ * Send control change events for the slave of the @master control identified
+ * by the V4L2 ID @slave_id. The @handle identifies the event subscriber that
+ * generated the event and may be NULL for auto-update events.
+ */
+static void uvc_ctrl_send_slave_event(struct uvc_video_chain *chain,
+	struct uvc_fh *handle, struct uvc_control *master, u32 slave_id)
 {
 	struct uvc_control_mapping *mapping = NULL;
 	struct uvc_control *ctrl = NULL;
 	u32 changes = V4L2_EVENT_CTRL_CH_FLAGS;
-	unsigned int i;
 	s32 val = 0;
 
-	/*
-	 * We can skip sending an event for the slave if the slave
-	 * is being modified in the same transaction.
-	 */
-	for (i = 0; i < xctrls_count; i++) {
-		if (xctrls[i].id == slave_id)
-			return;
-	}
-
 	__uvc_find_control(master->entity, slave_id, &mapping, &ctrl, 0);
 	if (ctrl == NULL)
 		return;
 
-	if (__uvc_ctrl_get(handle->chain, ctrl, mapping, &val) == 0)
+	if (__uvc_ctrl_get(chain, ctrl, mapping, &val) == 0)
 		changes |= V4L2_EVENT_CTRL_CH_VALUE;
 
-	uvc_ctrl_send_event(handle, ctrl, mapping, val, changes);
+	uvc_ctrl_send_event(chain, handle, ctrl, mapping, val, changes);
+}
+
+static void uvc_ctrl_status_event_work(struct work_struct *work)
+{
+	struct uvc_device *dev = container_of(work, struct uvc_device,
+					      async_ctrl.work);
+	struct uvc_ctrl_work *w = &dev->async_ctrl;
+	struct uvc_video_chain *chain = w->chain;
+	struct uvc_control_mapping *mapping;
+	struct uvc_control *ctrl = w->ctrl;
+	struct uvc_fh *handle;
+	unsigned int i;
+	int ret;
+
+	mutex_lock(&chain->ctrl_mutex);
+
+	handle = ctrl->handle;
+	ctrl->handle = NULL;
+
+	list_for_each_entry(mapping, &ctrl->info.mappings, list) {
+		s32 value = __uvc_ctrl_get_value(mapping, w->data);
+
+		/*
+		 * handle may be NULL here if the device sends auto-update
+		 * events without a prior related control set from userspace.
+		 */
+		for (i = 0; i < ARRAY_SIZE(mapping->slave_ids); ++i) {
+			if (!mapping->slave_ids[i])
+				break;
+
+			uvc_ctrl_send_slave_event(chain, handle, ctrl,
+						  mapping->slave_ids[i]);
+		}
+
+		uvc_ctrl_send_event(chain, handle, ctrl, mapping, value,
+				    V4L2_EVENT_CTRL_CH_VALUE);
+	}
+
+	mutex_unlock(&chain->ctrl_mutex);
+
+	/* Resubmit the URB. */
+	w->urb->interval = dev->int_ep->desc.bInterval;
+	ret = usb_submit_urb(w->urb, GFP_KERNEL);
+	if (ret < 0)
+		uvc_printk(KERN_ERR, "Failed to resubmit status URB (%d).\n",
+			   ret);
+}
+
+bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain,
+			   struct uvc_control *ctrl, const u8 *data)
+{
+	struct uvc_device *dev = chain->dev;
+	struct uvc_ctrl_work *w = &dev->async_ctrl;
+
+	if (list_empty(&ctrl->info.mappings)) {
+		ctrl->handle = NULL;
+		return false;
+	}
+
+	w->data = data;
+	w->urb = urb;
+	w->chain = chain;
+	w->ctrl = ctrl;
+
+	schedule_work(&w->work);
+
+	return true;
+}
+
+static bool uvc_ctrl_xctrls_has_control(const struct v4l2_ext_control *xctrls,
+					unsigned int xctrls_count, u32 id)
+{
+	unsigned int i;
+
+	for (i = 0; i < xctrls_count; ++i) {
+		if (xctrls[i].id == id)
+			return true;
+	}
+
+	return false;
 }
 
 static void uvc_ctrl_send_events(struct uvc_fh *handle,
@@ -1277,29 +1368,39 @@ static void uvc_ctrl_send_events(struct uvc_fh *handle,
 	for (i = 0; i < xctrls_count; ++i) {
 		ctrl = uvc_find_control(handle->chain, xctrls[i].id, &mapping);
 
+		if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS)
+			/* Notification will be sent from an Interrupt event. */
+			continue;
+
 		for (j = 0; j < ARRAY_SIZE(mapping->slave_ids); ++j) {
-			if (!mapping->slave_ids[j])
+			u32 slave_id = mapping->slave_ids[j];
+
+			if (!slave_id)
 				break;
-			uvc_ctrl_send_slave_event(handle, ctrl,
-						  mapping->slave_ids[j],
-						  xctrls, xctrls_count);
+
+			/*
+			 * We can skip sending an event for the slave if the
+			 * slave is being modified in the same transaction.
+			 */
+			if (uvc_ctrl_xctrls_has_control(xctrls, xctrls_count,
+							slave_id))
+				continue;
+
+			uvc_ctrl_send_slave_event(handle->chain, handle, ctrl,
+						  slave_id);
 		}
 
 		/*
 		 * If the master is being modified in the same transaction
 		 * flags may change too.
 		 */
-		if (mapping->master_id) {
-			for (j = 0; j < xctrls_count; j++) {
-				if (xctrls[j].id == mapping->master_id) {
-					changes |= V4L2_EVENT_CTRL_CH_FLAGS;
-					break;
-				}
-			}
-		}
+		if (mapping->master_id &&
+		    uvc_ctrl_xctrls_has_control(xctrls, xctrls_count,
+						mapping->master_id))
+			changes |= V4L2_EVENT_CTRL_CH_FLAGS;
 
-		uvc_ctrl_send_event(handle, ctrl, mapping, xctrls[i].value,
-				    changes);
+		uvc_ctrl_send_event(handle->chain, handle, ctrl, mapping,
+				    xctrls[i].value, changes);
 	}
 }
 
@@ -1472,9 +1573,10 @@ int uvc_ctrl_get(struct uvc_video_chain *chain,
 	return __uvc_ctrl_get(chain, ctrl, mapping, &xctrl->value);
 }
 
-int uvc_ctrl_set(struct uvc_video_chain *chain,
+int uvc_ctrl_set(struct uvc_fh *handle,
 	struct v4l2_ext_control *xctrl)
 {
+	struct uvc_video_chain *chain = handle->chain;
 	struct uvc_control *ctrl;
 	struct uvc_control_mapping *mapping;
 	s32 value;
@@ -1581,6 +1683,9 @@ int uvc_ctrl_set(struct uvc_video_chain *chain,
 	mapping->set(mapping, value,
 		uvc_ctrl_data(ctrl, UVC_CTRL_DATA_CURRENT));
 
+	if (ctrl->info.flags & UVC_CTRL_FLAG_ASYNCHRONOUS)
+		ctrl->handle = handle;
+
 	ctrl->dirty = 1;
 	ctrl->modified = 1;
 	return 0;
@@ -1612,7 +1717,9 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev,
 			    |  (data[0] & UVC_CONTROL_CAP_SET ?
 				UVC_CTRL_FLAG_SET_CUR : 0)
 			    |  (data[0] & UVC_CONTROL_CAP_AUTOUPDATE ?
-				UVC_CTRL_FLAG_AUTO_UPDATE : 0);
+				UVC_CTRL_FLAG_AUTO_UPDATE : 0)
+			    |  (data[0] & UVC_CONTROL_CAP_ASYNCHRONOUS ?
+				UVC_CTRL_FLAG_ASYNCHRONOUS : 0);
 
 	kfree(data);
 	return ret;
@@ -2173,6 +2280,8 @@ int uvc_ctrl_init_device(struct uvc_device *dev)
 	struct uvc_entity *entity;
 	unsigned int i;
 
+	INIT_WORK(&dev->async_ctrl.work, uvc_ctrl_status_event_work);
+
 	/* Walk the entities list and instantiate controls */
 	list_for_each_entry(entity, &dev->entities, list) {
 		struct uvc_control *ctrl;
@@ -2241,6 +2350,8 @@ void uvc_ctrl_cleanup_device(struct uvc_device *dev)
 	struct uvc_entity *entity;
 	unsigned int i;
 
+	cancel_work_sync(&dev->async_ctrl.work);
+
 	/* Free controls and control mappings for all entities. */
 	list_for_each_entry(entity, &dev->entities, list) {
 		for (i = 0; i < entity->ncontrols; ++i) {
diff --git a/drivers/media/usb/uvc/uvc_status.c b/drivers/media/usb/uvc/uvc_status.c
index 7b710410584a..0722dc684378 100644
--- a/drivers/media/usb/uvc/uvc_status.c
+++ b/drivers/media/usb/uvc/uvc_status.c
@@ -78,7 +78,24 @@ static void uvc_input_report_key(struct uvc_device *dev, unsigned int code,
 /* --------------------------------------------------------------------------
  * Status interrupt endpoint
  */
-static void uvc_event_streaming(struct uvc_device *dev, u8 *data, int len)
+struct uvc_streaming_status {
+	u8	bStatusType;
+	u8	bOriginator;
+	u8	bEvent;
+	u8	bValue[];
+} __packed;
+
+struct uvc_control_status {
+	u8	bStatusType;
+	u8	bOriginator;
+	u8	bEvent;
+	u8	bSelector;
+	u8	bAttribute;
+	u8	bValue[];
+} __packed;
+
+static void uvc_event_streaming(struct uvc_device *dev,
+				struct uvc_streaming_status *status, int len)
 {
 	if (len < 3) {
 		uvc_trace(UVC_TRACE_STATUS, "Invalid streaming status event "
@@ -86,31 +103,97 @@ static void uvc_event_streaming(struct uvc_device *dev, u8 *data, int len)
 		return;
 	}
 
-	if (data[2] == 0) {
+	if (status->bEvent == 0) {
 		if (len < 4)
 			return;
 		uvc_trace(UVC_TRACE_STATUS, "Button (intf %u) %s len %d\n",
-			data[1], data[3] ? "pressed" : "released", len);
-		uvc_input_report_key(dev, KEY_CAMERA, data[3]);
+			  status->bOriginator,
+			  status->bValue[0] ? "pressed" : "released", len);
+		uvc_input_report_key(dev, KEY_CAMERA, status->bValue[0]);
 	} else {
 		uvc_trace(UVC_TRACE_STATUS,
 			  "Stream %u error event %02x len %d.\n",
-			  data[1], data[2], len);
+			  status->bOriginator, status->bEvent, len);
 	}
 }
 
-static void uvc_event_control(struct uvc_device *dev, u8 *data, int len)
+#define UVC_CTRL_VALUE_CHANGE	0
+#define UVC_CTRL_INFO_CHANGE	1
+#define UVC_CTRL_FAILURE_CHANGE	2
+#define UVC_CTRL_MIN_CHANGE	3
+#define UVC_CTRL_MAX_CHANGE	4
+
+static struct uvc_control *uvc_event_entity_find_ctrl(struct uvc_entity *entity,
+						      u8 selector)
 {
-	char *attrs[3] = { "value", "info", "failure" };
+	struct uvc_control *ctrl;
+	unsigned int i;
+
+	for (i = 0, ctrl = entity->controls; i < entity->ncontrols; i++, ctrl++)
+		if (ctrl->info.selector == selector)
+			return ctrl;
+
+	return NULL;
+}
 
-	if (len < 6 || data[2] != 0 || data[4] > 2) {
+static struct uvc_control *uvc_event_find_ctrl(struct uvc_device *dev,
+					const struct uvc_control_status *status,
+					struct uvc_video_chain **chain)
+{
+	list_for_each_entry((*chain), &dev->chains, list) {
+		struct uvc_entity *entity;
+		struct uvc_control *ctrl;
+
+		list_for_each_entry(entity, &(*chain)->entities, chain) {
+			if (entity->id != status->bOriginator)
+				continue;
+
+			ctrl = uvc_event_entity_find_ctrl(entity,
+							  status->bSelector);
+			if (ctrl)
+				return ctrl;
+		}
+	}
+
+	return NULL;
+}
+
+static bool uvc_event_control(struct urb *urb,
+			      const struct uvc_control_status *status, int len)
+{
+	static const char *attrs[] = { "value", "info", "failure", "min", "max" };
+	struct uvc_device *dev = urb->context;
+	struct uvc_video_chain *chain;
+	struct uvc_control *ctrl;
+
+	if (len < 6 || status->bEvent != 0 ||
+	    status->bAttribute >= ARRAY_SIZE(attrs)) {
 		uvc_trace(UVC_TRACE_STATUS, "Invalid control status event "
 				"received.\n");
-		return;
+		return false;
 	}
 
 	uvc_trace(UVC_TRACE_STATUS, "Control %u/%u %s change len %d.\n",
-		data[1], data[3], attrs[data[4]], len);
+		  status->bOriginator, status->bSelector,
+		  attrs[status->bAttribute], len);
+
+	/* Find the control. */
+	ctrl = uvc_event_find_ctrl(dev, status, &chain);
+	if (!ctrl)
+		return false;
+
+	switch (status->bAttribute) {
+	case UVC_CTRL_VALUE_CHANGE:
+		return uvc_ctrl_status_event(urb, chain, ctrl, status->bValue);
+
+	case UVC_CTRL_INFO_CHANGE:
+	case UVC_CTRL_FAILURE_CHANGE:
+	case UVC_CTRL_MIN_CHANGE:
+	case UVC_CTRL_MAX_CHANGE:
+		break;
+	}
+
+	return false;
 }
 
 static void uvc_status_complete(struct urb *urb)
@@ -138,13 +221,23 @@ static void uvc_status_complete(struct urb *urb)
 	len = urb->actual_length;
 	if (len > 0) {
 		switch (dev->status[0] & 0x0f) {
-		case UVC_STATUS_TYPE_CONTROL:
-			uvc_event_control(dev, dev->status, len);
+		case UVC_STATUS_TYPE_CONTROL: {
+			struct uvc_control_status *status =
+				(struct uvc_control_status *)dev->status;
+
+			if (uvc_event_control(urb, status, len))
+				/* The URB will be resubmitted in work context. */
+				return;
 			break;
+		}
 
-		case UVC_STATUS_TYPE_STREAMING:
-			uvc_event_streaming(dev, dev->status, len);
+		case UVC_STATUS_TYPE_STREAMING: {
+			struct uvc_streaming_status *status =
+				(struct uvc_streaming_status *)dev->status;
+
+			uvc_event_streaming(dev, status, len);
 			break;
+		}
 
 		default:
 			uvc_trace(UVC_TRACE_STATUS, "Unknown status event "
diff --git a/drivers/media/usb/uvc/uvc_v4l2.c b/drivers/media/usb/uvc/uvc_v4l2.c
index bd32914259ae..18a7384b50ee 100644
--- a/drivers/media/usb/uvc/uvc_v4l2.c
+++ b/drivers/media/usb/uvc/uvc_v4l2.c
@@ -994,7 +994,7 @@ static int uvc_ioctl_s_ctrl(struct file *file, void *fh,
 	if (ret < 0)
 		return ret;
 
-	ret = uvc_ctrl_set(chain, &xctrl);
+	ret = uvc_ctrl_set(handle, &xctrl);
 	if (ret < 0) {
 		uvc_ctrl_rollback(handle);
 		return ret;
@@ -1069,7 +1069,7 @@ static int uvc_ioctl_s_try_ext_ctrls(struct uvc_fh *handle,
 		return ret;
 
 	for (i = 0; i < ctrls->count; ++ctrl, ++i) {
-		ret = uvc_ctrl_set(chain, ctrl);
+		ret = uvc_ctrl_set(handle, ctrl);
 		if (ret < 0) {
 			uvc_ctrl_rollback(handle);
 			ctrls->error_idx = commit ? ctrls->count : i;
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index 6b955e0dd956..e5f5d84f1d1d 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -12,6 +12,7 @@
 #include <linux/usb/video.h>
 #include <linux/uvcvideo.h>
 #include <linux/videodev2.h>
+#include <linux/workqueue.h>
 #include <media/media-device.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-event.h>
@@ -259,6 +260,8 @@ struct uvc_control {
 	   initialized:1;
 
 	u8 *uvc_data;
+
+	struct uvc_fh *handle;	/* File handle that last changed the control. */
 };
 
 struct uvc_format_desc {
@@ -603,6 +606,14 @@ struct uvc_device {
 	u8 *status;
 	struct input_dev *input;
 	char input_phys[64];
+
+	struct uvc_ctrl_work {
+		struct work_struct work;
+		struct urb *urb;
+		struct uvc_video_chain *chain;
+		struct uvc_control *ctrl;
+		const void *data;
+	} async_ctrl;
 };
 
 enum uvc_handle_state {
@@ -756,6 +767,8 @@ int uvc_ctrl_add_mapping(struct uvc_video_chain *chain,
 int uvc_ctrl_init_device(struct uvc_device *dev);
 void uvc_ctrl_cleanup_device(struct uvc_device *dev);
 int uvc_ctrl_restore_values(struct uvc_device *dev);
+bool uvc_ctrl_status_event(struct urb *urb, struct uvc_video_chain *chain,
+			   struct uvc_control *ctrl, const u8 *data);
 
 int uvc_ctrl_begin(struct uvc_video_chain *chain);
 int __uvc_ctrl_commit(struct uvc_fh *handle, int rollback,
@@ -773,7 +786,7 @@ static inline int uvc_ctrl_rollback(struct uvc_fh *handle)
 }
 
 int uvc_ctrl_get(struct uvc_video_chain *chain, struct v4l2_ext_control *xctrl);
-int uvc_ctrl_set(struct uvc_video_chain *chain, struct v4l2_ext_control *xctrl);
+int uvc_ctrl_set(struct uvc_fh *handle, struct v4l2_ext_control *xctrl);
 
 int uvc_xu_ctrl_query(struct uvc_video_chain *chain,
 		      struct uvc_xu_control_query *xqry);
diff --git a/include/uapi/linux/uvcvideo.h b/include/uapi/linux/uvcvideo.h
index 020714d2c5bd..f80f05b3c423 100644
--- a/include/uapi/linux/uvcvideo.h
+++ b/include/uapi/linux/uvcvideo.h
@@ -28,6 +28,8 @@
 #define UVC_CTRL_FLAG_RESTORE		(1 << 6)
 /* Control can be updated by the camera. */
 #define UVC_CTRL_FLAG_AUTO_UPDATE	(1 << 7)
+/* Control supports asynchronous reporting */
+#define UVC_CTRL_FLAG_ASYNCHRONOUS	(1 << 8)
 
 #define UVC_CTRL_FLAG_GET_RANGE \
 	(UVC_CTRL_FLAG_GET_CUR | UVC_CTRL_FLAG_GET_MIN | \
-- 
cgit v1.2.3


From d0dd962d8a4ef4df9b710c4e3a975e6bfd9f0225 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Mon, 28 May 2018 10:32:41 -0400
Subject: media: dvb: get rid of VIDEO_SET_SPU_PALETTE

No upstream drivers use it. It doesn't make any sense to have
a compat32 code for something that nobody uses upstream.

Reported-by: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../media/uapi/dvb/video-set-spu-palette.rst       | 82 ----------------------
 .../media/uapi/dvb/video_function_calls.rst        |  1 -
 Documentation/media/uapi/dvb/video_types.rst       | 18 -----
 Documentation/media/video.h.rst.exceptions         |  1 -
 fs/compat_ioctl.c                                  | 30 --------
 include/uapi/linux/dvb/video.h                     |  7 --
 6 files changed, 139 deletions(-)
 delete mode 100644 Documentation/media/uapi/dvb/video-set-spu-palette.rst

diff --git a/Documentation/media/uapi/dvb/video-set-spu-palette.rst b/Documentation/media/uapi/dvb/video-set-spu-palette.rst
deleted file mode 100644
index 51a1913d21d2..000000000000
--- a/Documentation/media/uapi/dvb/video-set-spu-palette.rst
+++ /dev/null
@@ -1,82 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_SET_SPU_PALETTE:
-
-=====================
-VIDEO_SET_SPU_PALETTE
-=====================
-
-Name
-----
-
-VIDEO_SET_SPU_PALETTE
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, VIDEO_SET_SPU_PALETTE, struct video_spu_palette *palette )
-    :name: VIDEO_SET_SPU_PALETTE
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_SET_SPU_PALETTE for this command.
-
-    -  .. row 3
-
-       -  video_spu_palette_t \*palette
-
-       -  SPU palette according to section ??.
-
-
-Description
------------
-
-This ioctl sets the SPU color palette.
-
-.. c:type:: video_spu_palette
-
-.. code-block::c
-
-	typedef struct video_spu_palette {      /* SPU Palette information */
-		int length;
-		__u8 __user *palette;
-	} video_spu_palette_t;
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  input is not a valid palette or driver doesn’t handle SPU.
diff --git a/Documentation/media/uapi/dvb/video_function_calls.rst b/Documentation/media/uapi/dvb/video_function_calls.rst
index 68588ac7fecb..8d8383ffaeba 100644
--- a/Documentation/media/uapi/dvb/video_function_calls.rst
+++ b/Documentation/media/uapi/dvb/video_function_calls.rst
@@ -38,6 +38,5 @@ Video Function Calls
     video-set-system
     video-set-highlight
     video-set-spu
-    video-set-spu-palette
     video-get-navi
     video-set-attributes
diff --git a/Documentation/media/uapi/dvb/video_types.rst b/Documentation/media/uapi/dvb/video_types.rst
index 640a21de6b8a..4cfa00e5c934 100644
--- a/Documentation/media/uapi/dvb/video_types.rst
+++ b/Documentation/media/uapi/dvb/video_types.rst
@@ -320,24 +320,6 @@ to the following format:
      } video_spu_t;
 
 
-.. c:type:: video_spu_palette
-
-struct video_spu_palette
-========================
-
-The following structure is used to set the SPU palette by calling
-VIDEO_SPU_PALETTE:
-
-
-.. code-block:: c
-
-     typedef
-     struct video_spu_palette {
-	 int length;
-	 uint8_t *palette;
-     } video_spu_palette_t;
-
-
 .. c:type:: video_navi_pack
 
 struct video_navi_pack
diff --git a/Documentation/media/video.h.rst.exceptions b/Documentation/media/video.h.rst.exceptions
index a91aa884ce0e..89d7c3ef2da7 100644
--- a/Documentation/media/video.h.rst.exceptions
+++ b/Documentation/media/video.h.rst.exceptions
@@ -36,5 +36,4 @@ replace typedef video_stream_source_t :c:type:`video_stream_source`
 replace typedef video_play_state_t :c:type:`video_play_state`
 replace typedef video_highlight_t :c:type:`video_highlight`
 replace typedef video_spu_t :c:type:`video_spu`
-replace typedef video_spu_palette_t :c:type:`video_spu_palette`
 replace typedef video_navi_pack_t :c:type:`video_navi_pack`
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 9907475b4226..fdb5ef9b5d06 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -198,34 +198,6 @@ static int do_video_stillpicture(struct file *file,
 	return err;
 }
 
-struct compat_video_spu_palette {
-	int length;
-	compat_uptr_t palette;
-};
-
-static int do_video_set_spu_palette(struct file *file,
-		unsigned int cmd, struct compat_video_spu_palette __user *up)
-{
-	struct video_spu_palette __user *up_native;
-	compat_uptr_t palp;
-	int length, err;
-
-	err  = get_user(palp, &up->palette);
-	err |= get_user(length, &up->length);
-	if (err)
-		return -EFAULT;
-
-	up_native = compat_alloc_user_space(sizeof(struct video_spu_palette));
-	err  = put_user(compat_ptr(palp), &up_native->palette);
-	err |= put_user(length, &up_native->length);
-	if (err)
-		return -EFAULT;
-
-	err = do_ioctl(file, cmd, (unsigned long) up_native);
-
-	return err;
-}
-
 #ifdef CONFIG_BLOCK
 typedef struct sg_io_hdr32 {
 	compat_int_t interface_id;	/* [i] 'S' for SCSI generic (required) */
@@ -1347,8 +1319,6 @@ static long do_ioctl_trans(unsigned int cmd,
 		return do_video_get_event(file, cmd, argp);
 	case VIDEO_STILLPICTURE:
 		return do_video_stillpicture(file, cmd, argp);
-	case VIDEO_SET_SPU_PALETTE:
-		return do_video_set_spu_palette(file, cmd, argp);
 	}
 
 	/*
diff --git a/include/uapi/linux/dvb/video.h b/include/uapi/linux/dvb/video.h
index df3d7028c807..6a0c9757b7ba 100644
--- a/include/uapi/linux/dvb/video.h
+++ b/include/uapi/linux/dvb/video.h
@@ -186,12 +186,6 @@ typedef struct video_spu {
 } video_spu_t;
 
 
-typedef struct video_spu_palette {      /* SPU Palette information */
-	int length;
-	__u8 __user *palette;
-} video_spu_palette_t;
-
-
 typedef struct video_navi_pack {
 	int length;          /* 0 ... 1024 */
 	__u8 data[1024];
@@ -248,7 +242,6 @@ typedef __u16 video_attributes_t;
 #define VIDEO_SET_SYSTEM           _IO('o', 38)
 #define VIDEO_SET_HIGHLIGHT        _IOW('o', 39, video_highlight_t)
 #define VIDEO_SET_SPU              _IOW('o', 50, video_spu_t)
-#define VIDEO_SET_SPU_PALETTE      _IOW('o', 51, video_spu_palette_t)
 #define VIDEO_GET_NAVI             _IOR('o', 52, video_navi_pack_t)
 #define VIDEO_SET_ATTRIBUTES       _IO('o', 53)
 #define VIDEO_GET_SIZE             _IOR('o', 55, video_size_t)
-- 
cgit v1.2.3


From 3976d8d8f9b1f67ee21c5e583ec768b50605f547 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham@ideasonboard.com>
Date: Mon, 28 May 2018 06:24:20 -0400
Subject: media: vsp1: Document vsp1_dl_body refcnt

In commit 2d9445db0ee9 ("media: vsp1: Use reference counting for
bodies"), a new field was introduced to the vsp1_dl_body structure to
account for usage tracking of the body.

Document the newly added field in the kerneldoc.

Signed-off-by: Kieran Bingham <kieran.bingham@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index d9b9cdd8fbe2..10a24bde2299 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -43,6 +43,7 @@ struct vsp1_dl_entry {
  * struct vsp1_dl_body - Display list body
  * @list: entry in the display list list of bodies
  * @free: entry in the pool free body list
+ * @refcnt: reference tracking for the body
  * @pool: pool to which this body belongs
  * @vsp1: the VSP1 device
  * @entries: array of entries
-- 
cgit v1.2.3


From a00e5f074b3f3cd39d1ccdc53d4d805b014df3f3 Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Mon, 28 May 2018 21:09:20 -0400
Subject: media: helene: fix xtal frequency setting at power on

This patch fixes crystal frequency setting when power on this device.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Acked-by: Abylay Ospan <aospan@netup.ru>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/helene.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c
index a0d0b53c91d7..a5de65dcf784 100644
--- a/drivers/media/dvb-frontends/helene.c
+++ b/drivers/media/dvb-frontends/helene.c
@@ -897,7 +897,10 @@ static int helene_x_pon(struct helene_priv *priv)
 	helene_write_regs(priv, 0x99, cdata, sizeof(cdata));
 
 	/* 0x81 - 0x94 */
-	data[0] = 0x18; /* xtal 24 MHz */
+	if (priv->xtal == SONY_HELENE_XTAL_16000)
+		data[0] = 0x10; /* xtal 16 MHz */
+	else
+		data[0] = 0x18; /* xtal 24 MHz */
 	data[1] = (uint8_t)(0x80 | (0x04 & 0x1F)); /* 4 x 25 = 100uA */
 	data[2] = (uint8_t)(0x80 | (0x26 & 0x7F)); /* 38 x 0.25 = 9.5pF */
 	data[3] = 0x80; /* REFOUT signal output 500mVpp */
-- 
cgit v1.2.3


From 06b168aeb5096530c1dde1804a076d85f01bd122 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Fri, 27 Jul 2018 06:40:45 -0400
Subject: media: media-types.rst: fix doc warnings

Fix these warnings when building the documentation:

media.h.rst:6: WARNING: undefined label: media-ent-f-dv-decoder (if the link has no caption the label must precede a section header)
media.h.rst:6: WARNING: undefined label: media-ent-f-dv-encoder (if the link has no caption the label must precede a section header)
media.h.rst:6: WARNING: undefined label: media-ent-f-dv-decoder (if the link has no caption the label must precede a section header)

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/mediactl/media-types.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/media/uapi/mediactl/media-types.rst b/Documentation/media/uapi/mediactl/media-types.rst
index 0e9adc7869b8..e4c57c8f4553 100644
--- a/Documentation/media/uapi/mediactl/media-types.rst
+++ b/Documentation/media/uapi/mediactl/media-types.rst
@@ -41,7 +41,8 @@ Types and flags used to represent the media graph elements
 .. _MEDIA-ENT-F-PROC-VIDEO-DECODER:
 .. _MEDIA-ENT-F-VID-MUX:
 .. _MEDIA-ENT-F-VID-IF-BRIDGE:
-.. _MEDIA-ENT-F-DTV-DECODER:
+.. _MEDIA-ENT-F-DV-DECODER:
+.. _MEDIA-ENT-F-DV-ENCODER:
 
 .. cssclass:: longtable
 
-- 
cgit v1.2.3


From 7988b2532aca7463149eea701530d9bafc64619e Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 19 Jul 2018 06:42:28 -0400
Subject: media: coda: let CODA960 firmware set frame cropping in SPS header

When encoding h.264, if visible resolution is not aligned to macroblock
size, frame cropping has to be set in the SPS header to produce correct
streams. The CODA960 firmware can do this on its own if asked to.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index 529fc187ccfd..c255c8e9db52 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -536,6 +536,8 @@ static int coda_encode_header(struct coda_ctx *ctx, struct vb2_v4l2_buffer *buf,
 {
 	struct vb2_buffer *vb = &buf->vb2_buf;
 	struct coda_dev *dev = ctx->dev;
+	struct coda_q_data *q_data_src;
+	struct v4l2_rect *r;
 	size_t bufsize;
 	int ret;
 	int i;
@@ -549,6 +551,23 @@ static int coda_encode_header(struct coda_ctx *ctx, struct vb2_v4l2_buffer *buf,
 	if (dev->devtype->product == CODA_960)
 		bufsize /= 1024;
 	coda_write(dev, bufsize, CODA_CMD_ENC_HEADER_BB_SIZE);
+	if (dev->devtype->product == CODA_960 &&
+	    ctx->codec->dst_fourcc == V4L2_PIX_FMT_H264 &&
+	    header_code == CODA_HEADER_H264_SPS) {
+		q_data_src = get_q_data(ctx, V4L2_BUF_TYPE_VIDEO_OUTPUT);
+		r = &q_data_src->rect;
+
+		if (r->width % 16 || r->height % 16) {
+			u32 crop_right = round_up(r->width, 16) -  r->width;
+			u32 crop_bottom = round_up(r->height, 16) - r->height;
+
+			coda_write(dev, crop_right,
+				   CODA9_CMD_ENC_HEADER_FRAME_CROP_H);
+			coda_write(dev, crop_bottom,
+				   CODA9_CMD_ENC_HEADER_FRAME_CROP_V);
+			header_code |= CODA9_HEADER_FRAME_CROP;
+		}
+	}
 	coda_write(dev, header_code, CODA_CMD_ENC_HEADER_CODE);
 	ret = coda_command_sync(ctx, CODA_COMMAND_ENCODE_HEADER);
 	if (ret < 0) {
-- 
cgit v1.2.3


From 0dff710d1f939c3ca42960769431cf20c095dbce Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 19 Jul 2018 06:45:10 -0400
Subject: media: coda: add SPS fixup code for frame sizes that are not
 multiples of 16

The CODA7541 firmware does not set the SPS frame cropping fields to
properly describe coded h.264 streams with frame sizes that are not a
multiple of the macroblock size.
This adds RBSP parsing code and a SPS fixup routine to manually replace
the cropping information in the headers produced by the firmware with
the correct values.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
[hans.verkuil@cisco.com: added explanation of SPS RBSP to comment]
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/coda/coda-bit.c  |  21 +++
 drivers/media/platform/coda/coda-h264.c | 316 ++++++++++++++++++++++++++++++++
 drivers/media/platform/coda/coda.h      |   2 +
 3 files changed, 339 insertions(+)

diff --git a/drivers/media/platform/coda/coda-bit.c b/drivers/media/platform/coda/coda-bit.c
index c255c8e9db52..d26c2d85a009 100644
--- a/drivers/media/platform/coda/coda-bit.c
+++ b/drivers/media/platform/coda/coda-bit.c
@@ -1215,6 +1215,27 @@ static int coda_start_encoding(struct coda_ctx *ctx)
 		if (ret < 0)
 			goto out;
 
+		/*
+		 * If visible width or height are not aligned to macroblock
+		 * size, the crop_right and crop_bottom SPS fields must be set
+		 * to the difference between visible and coded size.  This is
+		 * only supported by CODA960 firmware. All others do not allow
+		 * writing frame cropping parameters, so we have to manually
+		 * fix up the SPS RBSP (Sequence Parameter Set Raw Byte
+		 * Sequence Payload) ourselves.
+		 */
+		if (ctx->dev->devtype->product != CODA_960 &&
+		    ((q_data_src->rect.width % 16) ||
+		     (q_data_src->rect.height % 16))) {
+			ret = coda_h264_sps_fixup(ctx, q_data_src->rect.width,
+						  q_data_src->rect.height,
+						  &ctx->vpu_header[0][0],
+						  &ctx->vpu_header_size[0],
+						  sizeof(ctx->vpu_header[0]));
+			if (ret < 0)
+				goto out;
+		}
+
 		/*
 		 * Get PPS in the first frame and copy it to an
 		 * intermediate buffer.
diff --git a/drivers/media/platform/coda/coda-h264.c b/drivers/media/platform/coda/coda-h264.c
index 07b4c706504f..635356a839cf 100644
--- a/drivers/media/platform/coda/coda-h264.c
+++ b/drivers/media/platform/coda/coda-h264.c
@@ -114,3 +114,319 @@ int coda_h264_level(int level_idc)
 	default: return -EINVAL;
 	}
 }
+
+struct rbsp {
+	char *buf;
+	int size;
+	int pos;
+};
+
+static inline int rbsp_read_bit(struct rbsp *rbsp)
+{
+	int shift = 7 - (rbsp->pos % 8);
+	int ofs = rbsp->pos++ / 8;
+
+	if (ofs >= rbsp->size)
+		return -EINVAL;
+
+	return (rbsp->buf[ofs] >> shift) & 1;
+}
+
+static inline int rbsp_write_bit(struct rbsp *rbsp, int bit)
+{
+	int shift = 7 - (rbsp->pos % 8);
+	int ofs = rbsp->pos++ / 8;
+
+	if (ofs >= rbsp->size)
+		return -EINVAL;
+
+	rbsp->buf[ofs] &= ~(1 << shift);
+	rbsp->buf[ofs] |= bit << shift;
+
+	return 0;
+}
+
+static inline int rbsp_read_bits(struct rbsp *rbsp, int num, int *val)
+{
+	int i, ret;
+	int tmp = 0;
+
+	if (num > 32)
+		return -EINVAL;
+
+	for (i = 0; i < num; i++) {
+		ret = rbsp_read_bit(rbsp);
+		if (ret < 0)
+			return ret;
+		tmp |= ret << (num - i - 1);
+	}
+
+	if (val)
+		*val = tmp;
+
+	return 0;
+}
+
+static int rbsp_write_bits(struct rbsp *rbsp, int num, int value)
+{
+	int ret;
+
+	while (num--) {
+		ret = rbsp_write_bit(rbsp, (value >> num) & 1);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int rbsp_read_uev(struct rbsp *rbsp, unsigned int *val)
+{
+	int leading_zero_bits = 0;
+	unsigned int tmp = 0;
+	int ret;
+
+	while ((ret = rbsp_read_bit(rbsp)) == 0)
+		leading_zero_bits++;
+	if (ret < 0)
+		return ret;
+
+	if (leading_zero_bits > 0) {
+		ret = rbsp_read_bits(rbsp, leading_zero_bits, &tmp);
+		if (ret)
+			return ret;
+	}
+
+	if (val)
+		*val = (1 << leading_zero_bits) - 1 + tmp;
+
+	return 0;
+}
+
+static int rbsp_write_uev(struct rbsp *rbsp, unsigned int value)
+{
+	int i;
+	int ret;
+	int tmp = value + 1;
+	int leading_zero_bits = fls(tmp) - 1;
+
+	for (i = 0; i < leading_zero_bits; i++) {
+		ret = rbsp_write_bit(rbsp, 0);
+		if (ret)
+			return ret;
+	}
+
+	return rbsp_write_bits(rbsp, leading_zero_bits + 1, tmp);
+}
+
+static int rbsp_read_sev(struct rbsp *rbsp, int *val)
+{
+	unsigned int tmp;
+	int ret;
+
+	ret = rbsp_read_uev(rbsp, &tmp);
+	if (ret)
+		return ret;
+
+	if (val) {
+		if (tmp & 1)
+			*val = (tmp + 1) / 2;
+		else
+			*val = -(tmp / 2);
+	}
+
+	return 0;
+}
+
+/**
+ * coda_h264_sps_fixup - fixes frame cropping values in h.264 SPS
+ * @ctx: encoder context
+ * @width: visible width
+ * @height: visible height
+ * @buf: buffer containing h.264 SPS RBSP, starting with NAL header
+ * @size: modified RBSP size return value
+ * @max_size: available size in buf
+ *
+ * Rewrites the frame cropping values in an h.264 SPS RBSP correctly for the
+ * given visible width and height.
+ */
+int coda_h264_sps_fixup(struct coda_ctx *ctx, int width, int height, char *buf,
+			int *size, int max_size)
+{
+	int profile_idc;
+	unsigned int pic_order_cnt_type;
+	int pic_width_in_mbs_minus1, pic_height_in_map_units_minus1;
+	int frame_mbs_only_flag, frame_cropping_flag;
+	int vui_parameters_present_flag;
+	unsigned int crop_right, crop_bottom;
+	struct rbsp sps;
+	int pos;
+	int ret;
+
+	if (*size < 8 || *size >= max_size)
+		return -EINVAL;
+
+	sps.buf = buf + 5; /* Skip NAL header */
+	sps.size = *size - 5;
+
+	profile_idc = sps.buf[0];
+	/* Skip constraint_set[0-5]_flag, reserved_zero_2bits */
+	/* Skip level_idc */
+	sps.pos = 24;
+
+	/* seq_parameter_set_id */
+	ret = rbsp_read_uev(&sps, NULL);
+	if (ret)
+		return ret;
+
+	if (profile_idc == 100 || profile_idc == 110 || profile_idc == 122 ||
+	    profile_idc == 244 || profile_idc == 44 || profile_idc == 83 ||
+	    profile_idc == 86 || profile_idc == 118 || profile_idc == 128 ||
+	    profile_idc == 138 || profile_idc == 139 || profile_idc == 134 ||
+	    profile_idc == 135) {
+		dev_err(ctx->fh.vdev->dev_parent,
+			"%s: Handling profile_idc %d not implemented\n",
+			__func__, profile_idc);
+		return -EINVAL;
+	}
+
+	/* log2_max_frame_num_minus4 */
+	ret = rbsp_read_uev(&sps, NULL);
+	if (ret)
+		return ret;
+
+	ret = rbsp_read_uev(&sps, &pic_order_cnt_type);
+	if (ret)
+		return ret;
+
+	if (pic_order_cnt_type == 0) {
+		/* log2_max_pic_order_cnt_lsb_minus4 */
+		ret = rbsp_read_uev(&sps, NULL);
+		if (ret)
+			return ret;
+	} else if (pic_order_cnt_type == 1) {
+		unsigned int i, num_ref_frames_in_pic_order_cnt_cycle;
+
+		/* delta_pic_order_always_zero_flag */
+		ret = rbsp_read_bit(&sps);
+		if (ret < 0)
+			return ret;
+		/* offset_for_non_ref_pic */
+		ret = rbsp_read_sev(&sps, NULL);
+		if (ret)
+			return ret;
+		/* offset_for_top_to_bottom_field */
+		ret = rbsp_read_sev(&sps, NULL);
+		if (ret)
+			return ret;
+
+		ret = rbsp_read_uev(&sps,
+				    &num_ref_frames_in_pic_order_cnt_cycle);
+		if (ret)
+			return ret;
+		for (i = 0; i < num_ref_frames_in_pic_order_cnt_cycle; i++) {
+			/* offset_for_ref_frame */
+			ret = rbsp_read_sev(&sps, NULL);
+			if (ret)
+				return ret;
+		}
+	}
+
+	/* max_num_ref_frames */
+	ret = rbsp_read_uev(&sps, NULL);
+	if (ret)
+		return ret;
+
+	/* gaps_in_frame_num_value_allowed_flag */
+	ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	ret = rbsp_read_uev(&sps, &pic_width_in_mbs_minus1);
+	if (ret)
+		return ret;
+	ret = rbsp_read_uev(&sps, &pic_height_in_map_units_minus1);
+	if (ret)
+		return ret;
+	frame_mbs_only_flag = ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	if (!frame_mbs_only_flag) {
+		/* mb_adaptive_frame_field_flag */
+		ret = rbsp_read_bit(&sps);
+		if (ret < 0)
+			return ret;
+	}
+	/* direct_8x8_inference_flag */
+	ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+
+	/* Mark position of the frame cropping flag */
+	pos = sps.pos;
+	frame_cropping_flag = ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	if (frame_cropping_flag) {
+		unsigned int crop_left, crop_top;
+
+		ret = rbsp_read_uev(&sps, &crop_left);
+		if (ret)
+			return ret;
+		ret = rbsp_read_uev(&sps, &crop_right);
+		if (ret)
+			return ret;
+		ret = rbsp_read_uev(&sps, &crop_top);
+		if (ret)
+			return ret;
+		ret = rbsp_read_uev(&sps, &crop_bottom);
+		if (ret)
+			return ret;
+	}
+	vui_parameters_present_flag = ret = rbsp_read_bit(&sps);
+	if (ret < 0)
+		return ret;
+	if (vui_parameters_present_flag) {
+		dev_err(ctx->fh.vdev->dev_parent,
+			"%s: Handling vui_parameters not implemented\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	crop_right = round_up(width, 16) - width;
+	crop_bottom = round_up(height, 16) - height;
+	crop_right /= 2;
+	if (frame_mbs_only_flag)
+		crop_bottom /= 2;
+	else
+		crop_bottom /= 4;
+
+
+	sps.size = max_size - 5;
+	sps.pos = pos;
+	frame_cropping_flag = 1;
+	ret = rbsp_write_bit(&sps, frame_cropping_flag);
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, 0); /* crop_left */
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, crop_right);
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, 0); /* crop_top */
+	if (ret)
+		return ret;
+	ret = rbsp_write_uev(&sps, crop_bottom);
+	if (ret)
+		return ret;
+	ret = rbsp_write_bit(&sps, 0); /* vui_parameters_present_flag */
+	if (ret)
+		return ret;
+	ret = rbsp_write_bit(&sps, 1);
+	if (ret)
+		return ret;
+
+	*size = 5 + DIV_ROUND_UP(sps.pos, 8);
+
+	return 0;
+}
diff --git a/drivers/media/platform/coda/coda.h b/drivers/media/platform/coda/coda.h
index 9f57f73161d6..19ac0b9dc6eb 100644
--- a/drivers/media/platform/coda/coda.h
+++ b/drivers/media/platform/coda/coda.h
@@ -305,6 +305,8 @@ int coda_h264_padding(int size, char *p);
 int coda_h264_profile(int profile_idc);
 int coda_h264_level(int level_idc);
 int coda_sps_parse_profile(struct coda_ctx *ctx, struct vb2_buffer *vb);
+int coda_h264_sps_fixup(struct coda_ctx *ctx, int width, int height, char *buf,
+			int *size, int max_size);
 
 bool coda_jpeg_check_buffer(struct coda_ctx *ctx, struct vb2_buffer *vb);
 int coda_jpeg_write_tables(struct coda_ctx *ctx);
-- 
cgit v1.2.3


From 915ffab02193371e99453ac94160d69ef58273bc Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Fri, 27 Jul 2018 07:01:03 -0400
Subject: media: media.h.rst.exceptions: ignore MEDIA-ENT-F-DTV-DECODER

This was kept just for backward compatibility. Solves this warning:
	media.h.rst:6: WARNING: undefined label: media-ent-f-dtv-decoder (if the link has no caption the label must precede a section header)

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/media.h.rst.exceptions | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/media/media.h.rst.exceptions b/Documentation/media/media.h.rst.exceptions
index 83d7f7c722fb..684fe9c86dee 100644
--- a/Documentation/media/media.h.rst.exceptions
+++ b/Documentation/media/media.h.rst.exceptions
@@ -6,10 +6,10 @@ ignore define MEDIA_API_VERSION
 ignore define MEDIA_ENT_F_BASE
 ignore define MEDIA_ENT_F_OLD_BASE
 ignore define MEDIA_ENT_F_OLD_SUBDEV_BASE
+ignore define MEDIA_ENT_F_DTV_DECODER
 ignore define MEDIA_INTF_T_DVB_BASE
 ignore define MEDIA_INTF_T_V4L_BASE
 ignore define MEDIA_INTF_T_ALSA_BASE
-
 #ignore legacy entity type macros
 ignore define MEDIA_ENT_TYPE_SHIFT
 ignore define MEDIA_ENT_TYPE_MASK
-- 
cgit v1.2.3


From 5a2c3a395ab3c3f4f9e3c7864603478bc22dc344 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 16 Jul 2018 11:20:22 +0530
Subject: hwrng: msm - remove msm hw_random driver

This driver is for a psedo-rng so should not be added in hwrng.
Remove it so that it's replacement can be added.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/char/hw_random/Kconfig   |  13 ---
 drivers/char/hw_random/Makefile  |   1 -
 drivers/char/hw_random/msm-rng.c | 183 ---------------------------------------
 3 files changed, 197 deletions(-)
 delete mode 100644 drivers/char/hw_random/msm-rng.c

diff --git a/drivers/char/hw_random/Kconfig b/drivers/char/hw_random/Kconfig
index c34b257d852d..dac895dc01b9 100644
--- a/drivers/char/hw_random/Kconfig
+++ b/drivers/char/hw_random/Kconfig
@@ -307,19 +307,6 @@ config HW_RANDOM_HISI
 
 	  If unsure, say Y.
 
-config HW_RANDOM_MSM
-	tristate "Qualcomm SoCs Random Number Generator support"
-	depends on HW_RANDOM && ARCH_QCOM
-	default HW_RANDOM
-	---help---
-	  This driver provides kernel-side support for the Random Number
-	  Generator hardware found on Qualcomm SoCs.
-
-	  To compile this driver as a module, choose M here. the
-	  module will be called msm-rng.
-
-	  If unsure, say Y.
-
 config HW_RANDOM_ST
 	tristate "ST Microelectronics HW Random Number Generator support"
 	depends on HW_RANDOM && ARCH_STI
diff --git a/drivers/char/hw_random/Makefile b/drivers/char/hw_random/Makefile
index 533e913c93d1..e35ec3ce3a20 100644
--- a/drivers/char/hw_random/Makefile
+++ b/drivers/char/hw_random/Makefile
@@ -29,7 +29,6 @@ obj-$(CONFIG_HW_RANDOM_POWERNV) += powernv-rng.o
 obj-$(CONFIG_HW_RANDOM_HISI)	+= hisi-rng.o
 obj-$(CONFIG_HW_RANDOM_BCM2835) += bcm2835-rng.o
 obj-$(CONFIG_HW_RANDOM_IPROC_RNG200) += iproc-rng200.o
-obj-$(CONFIG_HW_RANDOM_MSM) += msm-rng.o
 obj-$(CONFIG_HW_RANDOM_ST) += st-rng.o
 obj-$(CONFIG_HW_RANDOM_XGENE) += xgene-rng.o
 obj-$(CONFIG_HW_RANDOM_STM32) += stm32-rng.o
diff --git a/drivers/char/hw_random/msm-rng.c b/drivers/char/hw_random/msm-rng.c
deleted file mode 100644
index 841fee845ec9..000000000000
--- a/drivers/char/hw_random/msm-rng.c
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- * Copyright (c) 2011-2013, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-#include <linux/clk.h>
-#include <linux/err.h>
-#include <linux/hw_random.h>
-#include <linux/io.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-
-/* Device specific register offsets */
-#define PRNG_DATA_OUT		0x0000
-#define PRNG_STATUS		0x0004
-#define PRNG_LFSR_CFG		0x0100
-#define PRNG_CONFIG		0x0104
-
-/* Device specific register masks and config values */
-#define PRNG_LFSR_CFG_MASK	0x0000ffff
-#define PRNG_LFSR_CFG_CLOCKS	0x0000dddd
-#define PRNG_CONFIG_HW_ENABLE	BIT(1)
-#define PRNG_STATUS_DATA_AVAIL	BIT(0)
-
-#define MAX_HW_FIFO_DEPTH	16
-#define MAX_HW_FIFO_SIZE	(MAX_HW_FIFO_DEPTH * 4)
-#define WORD_SZ			4
-
-struct msm_rng {
-	void __iomem *base;
-	struct clk *clk;
-	struct hwrng hwrng;
-};
-
-#define to_msm_rng(p)	container_of(p, struct msm_rng, hwrng)
-
-static int msm_rng_enable(struct hwrng *hwrng, int enable)
-{
-	struct msm_rng *rng = to_msm_rng(hwrng);
-	u32 val;
-	int ret;
-
-	ret = clk_prepare_enable(rng->clk);
-	if (ret)
-		return ret;
-
-	if (enable) {
-		/* Enable PRNG only if it is not already enabled */
-		val = readl_relaxed(rng->base + PRNG_CONFIG);
-		if (val & PRNG_CONFIG_HW_ENABLE)
-			goto already_enabled;
-
-		val = readl_relaxed(rng->base + PRNG_LFSR_CFG);
-		val &= ~PRNG_LFSR_CFG_MASK;
-		val |= PRNG_LFSR_CFG_CLOCKS;
-		writel(val, rng->base + PRNG_LFSR_CFG);
-
-		val = readl_relaxed(rng->base + PRNG_CONFIG);
-		val |= PRNG_CONFIG_HW_ENABLE;
-		writel(val, rng->base + PRNG_CONFIG);
-	} else {
-		val = readl_relaxed(rng->base + PRNG_CONFIG);
-		val &= ~PRNG_CONFIG_HW_ENABLE;
-		writel(val, rng->base + PRNG_CONFIG);
-	}
-
-already_enabled:
-	clk_disable_unprepare(rng->clk);
-	return 0;
-}
-
-static int msm_rng_read(struct hwrng *hwrng, void *data, size_t max, bool wait)
-{
-	struct msm_rng *rng = to_msm_rng(hwrng);
-	size_t currsize = 0;
-	u32 *retdata = data;
-	size_t maxsize;
-	int ret;
-	u32 val;
-
-	/* calculate max size bytes to transfer back to caller */
-	maxsize = min_t(size_t, MAX_HW_FIFO_SIZE, max);
-
-	ret = clk_prepare_enable(rng->clk);
-	if (ret)
-		return ret;
-
-	/* read random data from hardware */
-	do {
-		val = readl_relaxed(rng->base + PRNG_STATUS);
-		if (!(val & PRNG_STATUS_DATA_AVAIL))
-			break;
-
-		val = readl_relaxed(rng->base + PRNG_DATA_OUT);
-		if (!val)
-			break;
-
-		*retdata++ = val;
-		currsize += WORD_SZ;
-
-		/* make sure we stay on 32bit boundary */
-		if ((maxsize - currsize) < WORD_SZ)
-			break;
-	} while (currsize < maxsize);
-
-	clk_disable_unprepare(rng->clk);
-
-	return currsize;
-}
-
-static int msm_rng_init(struct hwrng *hwrng)
-{
-	return msm_rng_enable(hwrng, 1);
-}
-
-static void msm_rng_cleanup(struct hwrng *hwrng)
-{
-	msm_rng_enable(hwrng, 0);
-}
-
-static int msm_rng_probe(struct platform_device *pdev)
-{
-	struct resource *res;
-	struct msm_rng *rng;
-	int ret;
-
-	rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL);
-	if (!rng)
-		return -ENOMEM;
-
-	platform_set_drvdata(pdev, rng);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	rng->base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(rng->base))
-		return PTR_ERR(rng->base);
-
-	rng->clk = devm_clk_get(&pdev->dev, "core");
-	if (IS_ERR(rng->clk))
-		return PTR_ERR(rng->clk);
-
-	rng->hwrng.name = KBUILD_MODNAME,
-	rng->hwrng.init = msm_rng_init,
-	rng->hwrng.cleanup = msm_rng_cleanup,
-	rng->hwrng.read = msm_rng_read,
-
-	ret = devm_hwrng_register(&pdev->dev, &rng->hwrng);
-	if (ret) {
-		dev_err(&pdev->dev, "failed to register hwrng\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-static const struct of_device_id msm_rng_of_match[] = {
-	{ .compatible = "qcom,prng", },
-	{}
-};
-MODULE_DEVICE_TABLE(of, msm_rng_of_match);
-
-static struct platform_driver msm_rng_driver = {
-	.probe = msm_rng_probe,
-	.driver = {
-		.name = KBUILD_MODNAME,
-		.of_match_table = of_match_ptr(msm_rng_of_match),
-	}
-};
-module_platform_driver(msm_rng_driver);
-
-MODULE_ALIAS("platform:" KBUILD_MODNAME);
-MODULE_AUTHOR("The Linux Foundation");
-MODULE_DESCRIPTION("Qualcomm MSM random number generator driver");
-MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From d978b031c5886f18341cb4b609b150d81ad0faf4 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 16 Jul 2018 11:20:23 +0530
Subject: dt-bindings: crypto: Move prng binding to crypto

Now that we are adding new driver for prng in crypto, move the
binding as well.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/devicetree/bindings/crypto/qcom,prng.txt | 17 +++++++++++++++++
 Documentation/devicetree/bindings/rng/qcom,prng.txt    | 17 -----------------
 2 files changed, 17 insertions(+), 17 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/crypto/qcom,prng.txt
 delete mode 100644 Documentation/devicetree/bindings/rng/qcom,prng.txt

diff --git a/Documentation/devicetree/bindings/crypto/qcom,prng.txt b/Documentation/devicetree/bindings/crypto/qcom,prng.txt
new file mode 100644
index 000000000000..8e5853c2879b
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/qcom,prng.txt
@@ -0,0 +1,17 @@
+Qualcomm MSM pseudo random number generator.
+
+Required properties:
+
+- compatible  : should be "qcom,prng"
+- reg         : specifies base physical address and size of the registers map
+- clocks      : phandle to clock-controller plus clock-specifier pair
+- clock-names : "core" clocks all registers, FIFO and circuits in PRNG IP block
+
+Example:
+
+	rng@f9bff000 {
+		compatible = "qcom,prng";
+		reg = <0xf9bff000 0x200>;
+		clocks = <&clock GCC_PRNG_AHB_CLK>;
+		clock-names = "core";
+	};
diff --git a/Documentation/devicetree/bindings/rng/qcom,prng.txt b/Documentation/devicetree/bindings/rng/qcom,prng.txt
deleted file mode 100644
index 8e5853c2879b..000000000000
--- a/Documentation/devicetree/bindings/rng/qcom,prng.txt
+++ /dev/null
@@ -1,17 +0,0 @@
-Qualcomm MSM pseudo random number generator.
-
-Required properties:
-
-- compatible  : should be "qcom,prng"
-- reg         : specifies base physical address and size of the registers map
-- clocks      : phandle to clock-controller plus clock-specifier pair
-- clock-names : "core" clocks all registers, FIFO and circuits in PRNG IP block
-
-Example:
-
-	rng@f9bff000 {
-		compatible = "qcom,prng";
-		reg = <0xf9bff000 0x200>;
-		clocks = <&clock GCC_PRNG_AHB_CLK>;
-		clock-names = "core";
-	};
-- 
cgit v1.2.3


From ceec5f5b59882b871a722ca4d49b767a09a4bde9 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 16 Jul 2018 11:20:24 +0530
Subject: crypto: qcom-rng - Add Qcom prng driver

This ports the Qcom prng from older hw_random driver.

No change of functionality and move from hw_random to crypto
APIs is done.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/Kconfig    |  11 +++
 drivers/crypto/Makefile   |   1 +
 drivers/crypto/qcom-rng.c | 208 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 220 insertions(+)
 create mode 100644 drivers/crypto/qcom-rng.c

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 7c6ba111671d..2bf799ba7674 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -585,6 +585,17 @@ config CRYPTO_DEV_QCE
 	  hardware. To compile this driver as a module, choose M here. The
 	  module will be called qcrypto.
 
+config CRYPTO_DEV_QCOM_RNG
+	tristate "Qualcomm Random Number Generator Driver"
+	depends on ARCH_QCOM || COMPILE_TEST
+	select CRYPTO_RNG
+	help
+	  This driver provides support for the Random Number
+	  Generator hardware found on Qualcomm SoCs.
+
+	  To compile this driver as a module, choose M here. The
+          module will be called qcom-rng. If unsure, say N.
+
 config CRYPTO_DEV_VMX
 	bool "Support for VMX cryptographic acceleration instructions"
 	depends on PPC64 && VSX
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 7ae87b4f6c8d..3602875c4f80 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -33,6 +33,7 @@ obj-$(CONFIG_CRYPTO_DEV_PICOXCELL) += picoxcell_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_PPC4XX) += amcc/
 obj-$(CONFIG_CRYPTO_DEV_QAT) += qat/
 obj-$(CONFIG_CRYPTO_DEV_QCE) += qce/
+obj-$(CONFIG_CRYPTO_DEV_QCOM_RNG) += qcom-rng.o
 obj-$(CONFIG_CRYPTO_DEV_ROCKCHIP) += rockchip/
 obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o
 obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o
diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c
new file mode 100644
index 000000000000..e921382099d7
--- /dev/null
+++ b/drivers/crypto/qcom-rng.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2017-18 Linaro Limited
+//
+// Based on msm-rng.c and downstream driver
+
+#include <crypto/internal/rng.h>
+#include <linux/clk.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+
+/* Device specific register offsets */
+#define PRNG_DATA_OUT		0x0000
+#define PRNG_STATUS		0x0004
+#define PRNG_LFSR_CFG		0x0100
+#define PRNG_CONFIG		0x0104
+
+/* Device specific register masks and config values */
+#define PRNG_LFSR_CFG_MASK	0x0000ffff
+#define PRNG_LFSR_CFG_CLOCKS	0x0000dddd
+#define PRNG_CONFIG_HW_ENABLE	BIT(1)
+#define PRNG_STATUS_DATA_AVAIL	BIT(0)
+
+#define WORD_SZ			4
+
+struct qcom_rng {
+	struct mutex lock;
+	void __iomem *base;
+	struct clk *clk;
+};
+
+struct qcom_rng_ctx {
+	struct qcom_rng *rng;
+};
+
+static struct qcom_rng *qcom_rng_dev;
+
+static int qcom_rng_read(struct qcom_rng *rng, u8 *data, unsigned int max)
+{
+	unsigned int currsize = 0;
+	u32 val;
+
+	/* read random data from hardware */
+	do {
+		val = readl_relaxed(rng->base + PRNG_STATUS);
+		if (!(val & PRNG_STATUS_DATA_AVAIL))
+			break;
+
+		val = readl_relaxed(rng->base + PRNG_DATA_OUT);
+		if (!val)
+			break;
+
+		if ((max - currsize) >= WORD_SZ) {
+			memcpy(data, &val, WORD_SZ);
+			data += WORD_SZ;
+			currsize += WORD_SZ;
+		} else {
+			/* copy only remaining bytes */
+			memcpy(data, &val, max - currsize);
+			break;
+		}
+	} while (currsize < max);
+
+	return currsize;
+}
+
+static int qcom_rng_generate(struct crypto_rng *tfm,
+			     const u8 *src, unsigned int slen,
+			     u8 *dstn, unsigned int dlen)
+{
+	struct qcom_rng_ctx *ctx = crypto_rng_ctx(tfm);
+	struct qcom_rng *rng = ctx->rng;
+	int ret;
+
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	mutex_lock(&rng->lock);
+
+	ret = qcom_rng_read(rng, dstn, dlen);
+
+	mutex_unlock(&rng->lock);
+	clk_disable_unprepare(rng->clk);
+
+	return 0;
+}
+
+static int qcom_rng_seed(struct crypto_rng *tfm, const u8 *seed,
+			 unsigned int slen)
+{
+	return 0;
+}
+
+static int qcom_rng_enable(struct qcom_rng *rng)
+{
+	u32 val;
+	int ret;
+
+	ret = clk_prepare_enable(rng->clk);
+	if (ret)
+		return ret;
+
+	/* Enable PRNG only if it is not already enabled */
+	val = readl_relaxed(rng->base + PRNG_CONFIG);
+	if (val & PRNG_CONFIG_HW_ENABLE)
+		goto already_enabled;
+
+	val = readl_relaxed(rng->base + PRNG_LFSR_CFG);
+	val &= ~PRNG_LFSR_CFG_MASK;
+	val |= PRNG_LFSR_CFG_CLOCKS;
+	writel(val, rng->base + PRNG_LFSR_CFG);
+
+	val = readl_relaxed(rng->base + PRNG_CONFIG);
+	val |= PRNG_CONFIG_HW_ENABLE;
+	writel(val, rng->base + PRNG_CONFIG);
+
+already_enabled:
+	clk_disable_unprepare(rng->clk);
+
+	return 0;
+}
+
+static int qcom_rng_init(struct crypto_tfm *tfm)
+{
+	struct qcom_rng_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->rng = qcom_rng_dev;
+
+	return qcom_rng_enable(ctx->rng);
+}
+
+static struct rng_alg qcom_rng_alg = {
+	.generate	= qcom_rng_generate,
+	.seed		= qcom_rng_seed,
+	.seedsize	= 0,
+	.base		= {
+		.cra_name		= "stdrng",
+		.cra_driver_name	= "qcom-rng",
+		.cra_flags		= CRYPTO_ALG_TYPE_RNG,
+		.cra_priority		= 300,
+		.cra_ctxsize		= sizeof(struct qcom_rng_ctx),
+		.cra_module		= THIS_MODULE,
+		.cra_init		= qcom_rng_init,
+	}
+};
+
+static int qcom_rng_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	struct qcom_rng *rng;
+	int ret;
+
+	rng = devm_kzalloc(&pdev->dev, sizeof(*rng), GFP_KERNEL);
+	if (!rng)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, rng);
+	mutex_init(&rng->lock);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	rng->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(rng->base))
+		return PTR_ERR(rng->base);
+
+	rng->clk = devm_clk_get(&pdev->dev, "core");
+	if (IS_ERR(rng->clk))
+		return PTR_ERR(rng->clk);
+
+	qcom_rng_dev = rng;
+	ret = crypto_register_rng(&qcom_rng_alg);
+	if (ret) {
+		dev_err(&pdev->dev, "Register crypto rng failed: %d\n", ret);
+		qcom_rng_dev = NULL;
+	}
+
+	return ret;
+}
+
+static int qcom_rng_remove(struct platform_device *pdev)
+{
+	crypto_unregister_rng(&qcom_rng_alg);
+
+	qcom_rng_dev = NULL;
+
+	return 0;
+}
+
+static const struct of_device_id qcom_rng_of_match[] = {
+	{ .compatible = "qcom,prng" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, qcom_rng_of_match);
+
+static struct platform_driver qcom_rng_driver = {
+	.probe = qcom_rng_probe,
+	.remove =  qcom_rng_remove,
+	.driver = {
+		.name = KBUILD_MODNAME,
+		.of_match_table = of_match_ptr(qcom_rng_of_match),
+	}
+};
+module_platform_driver(qcom_rng_driver);
+
+MODULE_ALIAS("platform:" KBUILD_MODNAME);
+MODULE_DESCRIPTION("Qualcomm random number generator driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 3be36ce13c9276eb045a55184ff5c08511adb30b Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 16 Jul 2018 11:20:25 +0530
Subject: dt-bindings: crypto: Add new compatible qcom, prng-ee

Later qcom chips support v2 of the prng, which exposes an EE
(Execution Environment) for OS to use so add new compatible
qcom,prng-ee for this.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 Documentation/devicetree/bindings/crypto/qcom,prng.txt | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/crypto/qcom,prng.txt b/Documentation/devicetree/bindings/crypto/qcom,prng.txt
index 8e5853c2879b..7ee0e9eac973 100644
--- a/Documentation/devicetree/bindings/crypto/qcom,prng.txt
+++ b/Documentation/devicetree/bindings/crypto/qcom,prng.txt
@@ -2,7 +2,9 @@ Qualcomm MSM pseudo random number generator.
 
 Required properties:
 
-- compatible  : should be "qcom,prng"
+- compatible  : should be "qcom,prng" for 8916 etc
+              : should be "qcom,prng-ee" for 8996 and later using EE
+		(Execution Environment) slice of prng
 - reg         : specifies base physical address and size of the registers map
 - clocks      : phandle to clock-controller plus clock-specifier pair
 - clock-names : "core" clocks all registers, FIFO and circuits in PRNG IP block
-- 
cgit v1.2.3


From ba3ab6371cdda214bf3d416edae62809a68d0b73 Mon Sep 17 00:00:00 2001
From: Vinod Koul <vkoul@kernel.org>
Date: Mon, 16 Jul 2018 11:20:26 +0530
Subject: crypto: qcom-rng - Add support for prng-ee

Qcom 8996 and later chips features multiple Execution Environments
(EE) and secure world is typically responsible for configuring the
prng.

Add driver data for qcom,prng as 0 and qcom,prng-ee as 1 and use
that to skip initialization routine.

Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/qcom-rng.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c
index e921382099d7..80544326e310 100644
--- a/drivers/crypto/qcom-rng.c
+++ b/drivers/crypto/qcom-rng.c
@@ -28,6 +28,7 @@ struct qcom_rng {
 	struct mutex lock;
 	void __iomem *base;
 	struct clk *clk;
+	unsigned int skip_init;
 };
 
 struct qcom_rng_ctx {
@@ -128,7 +129,10 @@ static int qcom_rng_init(struct crypto_tfm *tfm)
 
 	ctx->rng = qcom_rng_dev;
 
-	return qcom_rng_enable(ctx->rng);
+	if (!ctx->rng->skip_init)
+		return qcom_rng_enable(ctx->rng);
+
+	return 0;
 }
 
 static struct rng_alg qcom_rng_alg = {
@@ -168,6 +172,8 @@ static int qcom_rng_probe(struct platform_device *pdev)
 	if (IS_ERR(rng->clk))
 		return PTR_ERR(rng->clk);
 
+	rng->skip_init = (unsigned long)device_get_match_data(&pdev->dev);
+
 	qcom_rng_dev = rng;
 	ret = crypto_register_rng(&qcom_rng_alg);
 	if (ret) {
@@ -188,7 +194,8 @@ static int qcom_rng_remove(struct platform_device *pdev)
 }
 
 static const struct of_device_id qcom_rng_of_match[] = {
-	{ .compatible = "qcom,prng" },
+	{ .compatible = "qcom,prng", .data = (void *)0},
+	{ .compatible = "qcom,prng-ee", .data = (void *)1},
 	{}
 };
 MODULE_DEVICE_TABLE(of, qcom_rng_of_match);
-- 
cgit v1.2.3


From d96542ac1020ecd47d2a1668384694789b65cb91 Mon Sep 17 00:00:00 2001
From: Timur Tabi <timur@codeaurora.org>
Date: Mon, 16 Jul 2018 11:20:27 +0530
Subject: crypto: qcom-rng - Add ACPI support

Add support for probing on ACPI systems, with ACPI HID QCOM8160.

On ACPI systems, clocks are always enabled, the PRNG should
already be enabled, and the register region is read-only.
The driver only verifies that the hardware is already
enabled never tries to disable or configure it.

Signed-off-by: Timur Tabi <timur@codeaurora.org>
Tested-by: Jeffrey Hugo <jhugo@codeaurora.org>
[port to crypto API]
Signed-off-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/qcom-rng.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c
index 80544326e310..e54249ccc009 100644
--- a/drivers/crypto/qcom-rng.c
+++ b/drivers/crypto/qcom-rng.c
@@ -4,6 +4,7 @@
 // Based on msm-rng.c and downstream driver
 
 #include <crypto/internal/rng.h>
+#include <linux/acpi.h>
 #include <linux/clk.h>
 #include <linux/crypto.h>
 #include <linux/module.h>
@@ -168,9 +169,13 @@ static int qcom_rng_probe(struct platform_device *pdev)
 	if (IS_ERR(rng->base))
 		return PTR_ERR(rng->base);
 
-	rng->clk = devm_clk_get(&pdev->dev, "core");
-	if (IS_ERR(rng->clk))
-		return PTR_ERR(rng->clk);
+	/* ACPI systems have clk already on, so skip clk_get */
+	if (!has_acpi_companion(&pdev->dev)) {
+		rng->clk = devm_clk_get(&pdev->dev, "core");
+		if (IS_ERR(rng->clk))
+			return PTR_ERR(rng->clk);
+	}
+
 
 	rng->skip_init = (unsigned long)device_get_match_data(&pdev->dev);
 
@@ -193,6 +198,14 @@ static int qcom_rng_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_ACPI)
+static const struct acpi_device_id qcom_rng_acpi_match[] = {
+	{ .id = "QCOM8160", .driver_data = 1 },
+	{}
+};
+MODULE_DEVICE_TABLE(acpi, qcom_rng_acpi_match);
+#endif
+
 static const struct of_device_id qcom_rng_of_match[] = {
 	{ .compatible = "qcom,prng", .data = (void *)0},
 	{ .compatible = "qcom,prng-ee", .data = (void *)1},
@@ -206,6 +219,7 @@ static struct platform_driver qcom_rng_driver = {
 	.driver = {
 		.name = KBUILD_MODNAME,
 		.of_match_table = of_match_ptr(qcom_rng_of_match),
+		.acpi_match_table = ACPI_PTR(qcom_rng_acpi_match),
 	}
 };
 module_platform_driver(qcom_rng_driver);
-- 
cgit v1.2.3


From 1fb2e3f276ddafee81073d884f599cd2574c31e2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 17 Jul 2018 18:05:36 +0200
Subject: lib/crc: Move polynomial definition to separate header

Allow other drivers and parts of kernel to use the same define for
CRC32 polynomial, instead of duplicating it in many places.  This code
does not bring any functional changes, except moving existing code.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crc32poly.h | 20 ++++++++++++++++++++
 lib/crc32.c               |  1 +
 lib/crc32defs.h           | 14 --------------
 lib/gen_crc32table.c      |  1 +
 4 files changed, 22 insertions(+), 14 deletions(-)
 create mode 100644 include/linux/crc32poly.h

diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h
new file mode 100644
index 000000000000..7ad5aa92d3c7
--- /dev/null
+++ b/include/linux/crc32poly.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CRC32_POLY_H
+#define _LINUX_CRC32_POLY_H
+
+/*
+ * There are multiple 16-bit CRC polynomials in common use, but this is
+ * *the* standard CRC-32 polynomial, first popularized by Ethernet.
+ * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0
+ */
+#define CRCPOLY_LE 0xedb88320
+#define CRCPOLY_BE 0x04c11db7
+
+/*
+ * This is the CRC32c polynomial, as outlined by Castagnoli.
+ * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+
+ * x^8+x^6+x^0
+ */
+#define CRC32C_POLY_LE 0x82F63B78
+
+#endif /* _LINUX_CRC32_POLY_H */
diff --git a/lib/crc32.c b/lib/crc32.c
index 2ef20fe84b69..341c54cb4edf 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -27,6 +27,7 @@
 /* see: Documentation/crc32.txt for a description of algorithms */
 
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 #include <linux/module.h>
 #include <linux/types.h>
 #include <linux/sched.h>
diff --git a/lib/crc32defs.h b/lib/crc32defs.h
index cb275a28a750..0c8fb5923e7e 100644
--- a/lib/crc32defs.h
+++ b/lib/crc32defs.h
@@ -1,18 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * There are multiple 16-bit CRC polynomials in common use, but this is
- * *the* standard CRC-32 polynomial, first popularized by Ethernet.
- * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0
- */
-#define CRCPOLY_LE 0xedb88320
-#define CRCPOLY_BE 0x04c11db7
-
-/*
- * This is the CRC32c polynomial, as outlined by Castagnoli.
- * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+
- * x^8+x^6+x^0
- */
-#define CRC32C_POLY_LE 0x82F63B78
 
 /* Try to choose an implementation variant via Kconfig */
 #ifdef CONFIG_CRC32_SLICEBY8
diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
index 8f26660ea10a..34c3bc826f45 100644
--- a/lib/gen_crc32table.c
+++ b/lib/gen_crc32table.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <stdio.h>
+#include "../include/linux/crc32poly.h"
 #include "../include/generated/autoconf.h"
 #include "crc32defs.h"
 #include <inttypes.h>
-- 
cgit v1.2.3


From e37f2f93afe594682702439ca34eb8130598cdf2 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 17 Jul 2018 18:05:37 +0200
Subject: lib/crc: Use consistent naming for CRC-32 polynomials

Header was defining CRCPOLY_LE/BE and CRC32C_POLY_LE but in fact all of
them are CRC-32 polynomials so use consistent naming.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/crc32poly.h |  4 ++--
 lib/crc32.c               | 10 +++++-----
 lib/gen_crc32table.c      |  4 ++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h
index 7ad5aa92d3c7..62c4b7790a28 100644
--- a/include/linux/crc32poly.h
+++ b/include/linux/crc32poly.h
@@ -7,8 +7,8 @@
  * *the* standard CRC-32 polynomial, first popularized by Ethernet.
  * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0
  */
-#define CRCPOLY_LE 0xedb88320
-#define CRCPOLY_BE 0x04c11db7
+#define CRC32_POLY_LE 0xedb88320
+#define CRC32_POLY_BE 0x04c11db7
 
 /*
  * This is the CRC32c polynomial, as outlined by Castagnoli.
diff --git a/lib/crc32.c b/lib/crc32.c
index 341c54cb4edf..a6c9afafc8c8 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -185,7 +185,7 @@ static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
 #if CRC_LE_BITS == 1
 u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_le_generic(crc, p, len, NULL, CRCPOLY_LE);
+	return crc32_le_generic(crc, p, len, NULL, CRC32_POLY_LE);
 }
 u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 {
@@ -195,7 +195,7 @@ u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
 {
 	return crc32_le_generic(crc, p, len,
-			(const u32 (*)[256])crc32table_le, CRCPOLY_LE);
+			(const u32 (*)[256])crc32table_le, CRC32_POLY_LE);
 }
 u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
 {
@@ -269,7 +269,7 @@ static u32 __attribute_const__ crc32_generic_shift(u32 crc, size_t len,
 
 u32 __attribute_const__ crc32_le_shift(u32 crc, size_t len)
 {
-	return crc32_generic_shift(crc, len, CRCPOLY_LE);
+	return crc32_generic_shift(crc, len, CRC32_POLY_LE);
 }
 
 u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len)
@@ -331,13 +331,13 @@ static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
 #if CRC_LE_BITS == 1
 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
-	return crc32_be_generic(crc, p, len, NULL, CRCPOLY_BE);
+	return crc32_be_generic(crc, p, len, NULL, CRC32_POLY_BE);
 }
 #else
 u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
 {
 	return crc32_be_generic(crc, p, len,
-			(const u32 (*)[256])crc32table_be, CRCPOLY_BE);
+			(const u32 (*)[256])crc32table_be, CRC32_POLY_BE);
 }
 #endif
 EXPORT_SYMBOL(crc32_be);
diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
index 34c3bc826f45..f755b997b967 100644
--- a/lib/gen_crc32table.c
+++ b/lib/gen_crc32table.c
@@ -58,7 +58,7 @@ static void crc32init_le_generic(const uint32_t polynomial,
 
 static void crc32init_le(void)
 {
-	crc32init_le_generic(CRCPOLY_LE, crc32table_le);
+	crc32init_le_generic(CRC32_POLY_LE, crc32table_le);
 }
 
 static void crc32cinit_le(void)
@@ -77,7 +77,7 @@ static void crc32init_be(void)
 	crc32table_be[0][0] = 0;
 
 	for (i = 1; i < BE_TABLE_SIZE; i <<= 1) {
-		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0);
+		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0);
 		for (j = 0; j < i; j++)
 			crc32table_be[0][i + j] = crc ^ crc32table_be[0][j];
 	}
-- 
cgit v1.2.3


From f7aee87822fdb7c43b9510e196cb74cc1bb9bb1e Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 17 Jul 2018 18:05:38 +0200
Subject: crypto: stm32_crc32 - Use existing define with polynomial

Do not define again the polynomial but use header with existing define.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/stm32/stm32_crc32.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/crypto/stm32/stm32_crc32.c b/drivers/crypto/stm32/stm32_crc32.c
index 04ba5e1399e5..5f3242a246fc 100644
--- a/drivers/crypto/stm32/stm32_crc32.c
+++ b/drivers/crypto/stm32/stm32_crc32.c
@@ -6,6 +6,7 @@
 
 #include <linux/bitrev.h>
 #include <linux/clk.h>
+#include <linux/crc32poly.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
@@ -29,10 +30,6 @@
 #define CRC_CR_REVERSE          (BIT(7) | BIT(6) | BIT(5))
 #define CRC_INIT_DEFAULT        0xFFFFFFFF
 
-/* Polynomial reversed */
-#define POLY_CRC32              0xEDB88320
-#define POLY_CRC32C             0x82F63B78
-
 #define CRC_AUTOSUSPEND_DELAY	50
 
 struct stm32_crc {
@@ -69,7 +66,7 @@ static int stm32_crc32_cra_init(struct crypto_tfm *tfm)
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
 	mctx->key = CRC_INIT_DEFAULT;
-	mctx->poly = POLY_CRC32;
+	mctx->poly = CRC32_POLY_LE;
 	return 0;
 }
 
@@ -78,7 +75,7 @@ static int stm32_crc32c_cra_init(struct crypto_tfm *tfm)
 	struct stm32_crc_ctx *mctx = crypto_tfm_ctx(tfm);
 
 	mctx->key = CRC_INIT_DEFAULT;
-	mctx->poly = POLY_CRC32C;
+	mctx->poly = CRC32C_POLY_LE;
 	return 0;
 }
 
@@ -187,7 +184,7 @@ static int stm32_crc_final(struct shash_desc *desc, u8 *out)
 	struct stm32_crc_ctx *mctx = crypto_shash_ctx(desc->tfm);
 
 	/* Send computed CRC */
-	put_unaligned_le32(mctx->poly == POLY_CRC32C ?
+	put_unaligned_le32(mctx->poly == CRC32C_POLY_LE ?
 			   ~ctx->partial : ctx->partial, out);
 
 	return 0;
-- 
cgit v1.2.3


From 5d258b48efbd0e28d9d0b5dc31de21050608e351 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 17 Jul 2018 18:05:39 +0200
Subject: net: ethernet: Use existing define with polynomial

Do not define again the polynomial but use header with existing define.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/net/ethernet/amd/xgbe/xgbe-dev.c         | 4 ++--
 drivers/net/ethernet/apple/bmac.c                | 8 ++------
 drivers/net/ethernet/broadcom/tg3.c              | 3 ++-
 drivers/net/ethernet/freescale/fec_main.c        | 4 ++--
 drivers/net/ethernet/freescale/fs_enet/fec.h     | 3 ---
 drivers/net/ethernet/freescale/fs_enet/mac-fec.c | 3 ++-
 drivers/net/ethernet/micrel/ks8851_mll.c         | 3 ++-
 drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c    | 4 ++--
 8 files changed, 14 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
index e107e180e2c8..1e929a1e4ca7 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-dev.c
@@ -119,6 +119,7 @@
 #include <linux/clk.h>
 #include <linux/bitrev.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 
 #include "xgbe.h"
 #include "xgbe-common.h"
@@ -887,7 +888,6 @@ static int xgbe_disable_rx_vlan_filtering(struct xgbe_prv_data *pdata)
 
 static u32 xgbe_vid_crc32_le(__le16 vid_le)
 {
-	u32 poly = 0xedb88320;	/* CRCPOLY_LE */
 	u32 crc = ~0;
 	u32 temp = 0;
 	unsigned char *data = (unsigned char *)&vid_le;
@@ -904,7 +904,7 @@ static u32 xgbe_vid_crc32_le(__le16 vid_le)
 		data_byte >>= 1;
 
 		if (temp)
-			crc ^= poly;
+			crc ^= CRC32_POLY_LE;
 	}
 
 	return crc;
diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c
index 5a655d289dd5..024998d6d8c6 100644
--- a/drivers/net/ethernet/apple/bmac.c
+++ b/drivers/net/ethernet/apple/bmac.c
@@ -19,6 +19,7 @@
 #include <linux/init.h>
 #include <linux/spinlock.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 #include <linux/bitrev.h>
 #include <linux/ethtool.h>
 #include <linux/slab.h>
@@ -37,11 +38,6 @@
 #define trunc_page(x)	((void *)(((unsigned long)(x)) & ~((unsigned long)(PAGE_SIZE - 1))))
 #define round_page(x)	trunc_page(((unsigned long)(x)) + ((unsigned long)(PAGE_SIZE - 1)))
 
-/*
- * CRC polynomial - used in working out multicast filter bits.
- */
-#define ENET_CRCPOLY 0x04c11db7
-
 /* switch to use multicast code lifted from sunhme driver */
 #define SUNHME_MULTICAST
 
@@ -838,7 +834,7 @@ crc416(unsigned int curval, unsigned short nxtval)
 		next = next >> 1;
 
 		/* do the XOR */
-		if (high_crc_set ^ low_data_set) cur = cur ^ ENET_CRCPOLY;
+		if (high_crc_set ^ low_data_set) cur = cur ^ CRC32_POLY_BE;
 	}
 	return cur;
 }
diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c
index 3be87efdc93d..af8134d202ae 100644
--- a/drivers/net/ethernet/broadcom/tg3.c
+++ b/drivers/net/ethernet/broadcom/tg3.c
@@ -50,6 +50,7 @@
 #include <linux/ssb/ssb_driver_gige.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
+#include <linux/crc32poly.h>
 
 #include <net/checksum.h>
 #include <net/ip.h>
@@ -9707,7 +9708,7 @@ static inline u32 calc_crc(unsigned char *buf, int len)
 			reg >>= 1;
 
 			if (tmp)
-				reg ^= 0xedb88320;
+				reg ^= CRC32_POLY_LE;
 		}
 	}
 
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index c729665107f5..a7cb378ef881 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -48,6 +48,7 @@
 #include <linux/io.h>
 #include <linux/irq.h>
 #include <linux/clk.h>
+#include <linux/crc32poly.h>
 #include <linux/platform_device.h>
 #include <linux/mdio.h>
 #include <linux/phy.h>
@@ -2949,7 +2950,6 @@ fec_enet_close(struct net_device *ndev)
  */
 
 #define FEC_HASH_BITS	6		/* #bits in hash */
-#define CRC32_POLY	0xEDB88320
 
 static void set_multicast_list(struct net_device *ndev)
 {
@@ -2989,7 +2989,7 @@ static void set_multicast_list(struct net_device *ndev)
 			data = ha->addr[i];
 			for (bit = 0; bit < 8; bit++, data >>= 1) {
 				crc = (crc >> 1) ^
-				(((crc ^ data) & 1) ? CRC32_POLY : 0);
+				(((crc ^ data) & 1) ? CRC32_POLY_LE : 0);
 			}
 		}
 
diff --git a/drivers/net/ethernet/freescale/fs_enet/fec.h b/drivers/net/ethernet/freescale/fs_enet/fec.h
index 7832db71dcb9..1dbee5d898b3 100644
--- a/drivers/net/ethernet/freescale/fs_enet/fec.h
+++ b/drivers/net/ethernet/freescale/fs_enet/fec.h
@@ -2,9 +2,6 @@
 #ifndef FS_ENET_FEC_H
 #define FS_ENET_FEC_H
 
-/* CRC polynomium used by the FEC for the multicast group filtering */
-#define FEC_CRC_POLY   0x04C11DB7
-
 #define FEC_MAX_MULTICAST_ADDRS	64
 
 /* Interrupt events/masks.
diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
index 1fc27c97e3b2..05093e5fc9dd 100644
--- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
+++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c
@@ -18,6 +18,7 @@
 #include <linux/string.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
+#include <linux/crc32poly.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
 #include <linux/delay.h>
@@ -187,7 +188,7 @@ static void set_multicast_one(struct net_device *dev, const u8 *mac)
 			msb = crc >> 31;
 			crc <<= 1;
 			if (msb ^ (byte & 0x1))
-				crc ^= FEC_CRC_POLY;
+				crc ^= CRC32_POLY_BE;
 			byte >>= 1;
 		}
 	}
diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c
index f3e9dd47b56f..0e9719fbc624 100644
--- a/drivers/net/ethernet/micrel/ks8851_mll.c
+++ b/drivers/net/ethernet/micrel/ks8851_mll.c
@@ -30,6 +30,7 @@
 #include <linux/ethtool.h>
 #include <linux/cache.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 #include <linux/mii.h>
 #include <linux/platform_device.h>
 #include <linux/delay.h>
@@ -1078,7 +1079,7 @@ static void ks_stop_rx(struct ks_net *ks)
 
 }  /* ks_stop_rx */
 
-static unsigned long const ethernet_polynomial = 0x04c11db7U;
+static unsigned long const ethernet_polynomial = CRC32_POLY_BE;
 
 static unsigned long ether_gen_crc(int length, u8 *data)
 {
diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
index 458a7844260a..99d86e39ff54 100644
--- a/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
+++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-hw.c
@@ -20,6 +20,7 @@
 #include <linux/clk.h>
 #include <linux/bitrev.h>
 #include <linux/crc32.h>
+#include <linux/crc32poly.h>
 #include <linux/dcbnl.h>
 
 #include "dwc-xlgmac.h"
@@ -193,7 +194,6 @@ static u32 xlgmac_vid_crc32_le(__le16 vid_le)
 {
 	unsigned char *data = (unsigned char *)&vid_le;
 	unsigned char data_byte = 0;
-	u32 poly = 0xedb88320;
 	u32 crc = ~0;
 	u32 temp = 0;
 	int i, bits;
@@ -208,7 +208,7 @@ static u32 xlgmac_vid_crc32_le(__le16 vid_le)
 		data_byte >>= 1;
 
 		if (temp)
-			crc ^= poly;
+			crc ^= CRC32_POLY_LE;
 	}
 
 	return crc;
-- 
cgit v1.2.3


From 9ecdb984195378be87e185c2dee80129c5cbf140 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 17 Jul 2018 18:05:40 +0200
Subject: staging: rtl: Use existing define with polynomial

Do not define again the polynomial but use header with existing define.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/staging/rtl8712/rtl871x_security.c    | 5 ++---
 drivers/staging/rtl8723bs/core/rtw_security.c | 5 ++---
 2 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/staging/rtl8712/rtl871x_security.c b/drivers/staging/rtl8712/rtl871x_security.c
index 7bc74d7d8a3a..1075eacdb441 100644
--- a/drivers/staging/rtl8712/rtl871x_security.c
+++ b/drivers/staging/rtl8712/rtl871x_security.c
@@ -40,6 +40,7 @@
 #include <linux/uaccess.h>
 #include <asm/byteorder.h>
 #include <linux/atomic.h>
+#include <linux/crc32poly.h>
 #include <linux/semaphore.h>
 
 #include "osdep_service.h"
@@ -49,8 +50,6 @@
 
 /* =====WEP related===== */
 
-#define CRC32_POLY 0x04c11db7
-
 struct arc4context {
 	u32 x;
 	u32 y;
@@ -135,7 +134,7 @@ static void crc32_init(void)
 	for (i = 0; i < 256; ++i) {
 		k = crc32_reverseBit((u8)i);
 		for (c = ((u32)k) << 24, j = 8; j > 0; --j)
-			c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY : (c << 1);
+			c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY_BE : (c << 1);
 		p1 = (u8 *)&crc32_table[i];
 		p1[0] = crc32_reverseBit(p[3]);
 		p1[1] = crc32_reverseBit(p[2]);
diff --git a/drivers/staging/rtl8723bs/core/rtw_security.c b/drivers/staging/rtl8723bs/core/rtw_security.c
index 612277a555d2..6c8ac9e86c9f 100644
--- a/drivers/staging/rtl8723bs/core/rtw_security.c
+++ b/drivers/staging/rtl8723bs/core/rtw_security.c
@@ -6,6 +6,7 @@
  ******************************************************************************/
 #define  _RTW_SECURITY_C_
 
+#include <linux/crc32poly.h>
 #include <drv_types.h>
 #include <rtw_debug.h>
 
@@ -87,8 +88,6 @@ const char *security_type_str(u8 value)
 
 /* WEP related ===== */
 
-#define CRC32_POLY 0x04c11db7
-
 struct arc4context {
 	u32 x;
 	u32 y;
@@ -178,7 +177,7 @@ static void crc32_init(void)
 		for (i = 0; i < 256; ++i) {
 			k = crc32_reverseBit((u8)i);
 			for (c = ((u32)k) << 24, j = 8; j > 0; --j) {
-				c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY : (c << 1);
+				c = c & 0x80000000 ? (c << 1) ^ CRC32_POLY_BE : (c << 1);
 			}
 			p1 = (u8 *)&crc32_table[i];
 
-- 
cgit v1.2.3


From faa16bc404d72a5afb857c924c83a5f691f83386 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 17 Jul 2018 18:05:41 +0200
Subject: lib: Use existing define with polynomial

Do not define again the polynomial but use header with existing define.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 lib/decompress_bunzip2.c | 3 ++-
 lib/xz/xz_crc32.c        | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 0234361b24b8..7c4932eed748 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -51,6 +51,7 @@
 #endif /* STATIC */
 
 #include <linux/decompress/mm.h>
+#include <linux/crc32poly.h>
 
 #ifndef INT_MAX
 #define INT_MAX 0x7fffffff
@@ -654,7 +655,7 @@ static int INIT start_bunzip(struct bunzip_data **bdp, void *inbuf, long len,
 	for (i = 0; i < 256; i++) {
 		c = i << 24;
 		for (j = 8; j; j--)
-			c = c&0x80000000 ? (c << 1)^0x04c11db7 : (c << 1);
+			c = c&0x80000000 ? (c << 1)^(CRC32_POLY_BE) : (c << 1);
 		bd->crc32Table[i] = c;
 	}
 
diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c
index 34532d14fd4c..25a5d87e2e4c 100644
--- a/lib/xz/xz_crc32.c
+++ b/lib/xz/xz_crc32.c
@@ -15,6 +15,7 @@
  * but they are bigger and use more memory for the lookup table.
  */
 
+#include <linux/crc32poly.h>
 #include "xz_private.h"
 
 /*
@@ -29,7 +30,7 @@ STATIC_RW_DATA uint32_t xz_crc32_table[256];
 
 XZ_EXTERN void xz_crc32_init(void)
 {
-	const uint32_t poly = 0xEDB88320;
+	const uint32_t poly = CRC32_POLY_LE;
 
 	uint32_t i;
 	uint32_t j;
-- 
cgit v1.2.3


From 6b0daa78207b622d768cce2a8251c830256bade9 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 17 Jul 2018 10:09:26 -0700
Subject: crypto: arm64/sha256 - increase cra_priority of scalar
 implementations

Commit b73b7ac0a774 ("crypto: sha256_generic - add cra_priority") gave
sha256-generic and sha224-generic a cra_priority of 100, to match the
convention for generic implementations.  But sha256-arm64 and
sha224-arm64 also have priority 100, so their order relative to the
generic implementations became ambiguous.

Therefore, increase their priority to 125 so that they have higher
priority than the generic implementations but lower priority than the
NEON implementations which have priority 150.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm64/crypto/sha256-glue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c
index f1b4f4420ca1..4aedeaefd61f 100644
--- a/arch/arm64/crypto/sha256-glue.c
+++ b/arch/arm64/crypto/sha256-glue.c
@@ -67,7 +67,7 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha256_state),
 	.base.cra_name		= "sha256",
 	.base.cra_driver_name	= "sha256-arm64",
-	.base.cra_priority	= 100,
+	.base.cra_priority	= 125,
 	.base.cra_blocksize	= SHA256_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 }, {
@@ -79,7 +79,7 @@ static struct shash_alg algs[] = { {
 	.descsize		= sizeof(struct sha256_state),
 	.base.cra_name		= "sha224",
 	.base.cra_driver_name	= "sha224-arm64",
-	.base.cra_priority	= 100,
+	.base.cra_priority	= 125,
 	.base.cra_blocksize	= SHA224_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
 } };
-- 
cgit v1.2.3


From d75f482eaface11dd30e73977c245fab5e07c3aa Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 12:12:00 -0500
Subject: crypto: rmd256 - use swap macro in rmd256_transform

Make use of the swap macro and remove unnecessary variable *tmp*.
This makes the code easier to read and maintain.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/rmd256.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/crypto/rmd256.c b/crypto/rmd256.c
index 0afbb5af4499..0e9d30676a01 100644
--- a/crypto/rmd256.c
+++ b/crypto/rmd256.c
@@ -49,7 +49,7 @@ struct rmd256_ctx {
 
 static void rmd256_transform(u32 *state, const __le32 *in)
 {
-	u32 aa, bb, cc, dd, aaa, bbb, ccc, ddd, tmp;
+	u32 aa, bb, cc, dd, aaa, bbb, ccc, ddd;
 
 	/* Initialize left lane */
 	aa = state[0];
@@ -100,7 +100,7 @@ static void rmd256_transform(u32 *state, const __le32 *in)
 	ROUND(bbb, ccc, ddd, aaa, F4, KK1, in[12],  6);
 
 	/* Swap contents of "a" registers */
-	tmp = aa; aa = aaa; aaa = tmp;
+	swap(aa, aaa);
 
 	/* round 2: left lane */
 	ROUND(aa, bb, cc, dd, F2, K2, in[7],   7);
@@ -139,7 +139,7 @@ static void rmd256_transform(u32 *state, const __le32 *in)
 	ROUND(bbb, ccc, ddd, aaa, F3, KK2, in[2],  11);
 
 	/* Swap contents of "b" registers */
-	tmp = bb; bb = bbb; bbb = tmp;
+	swap(bb, bbb);
 
 	/* round 3: left lane */
 	ROUND(aa, bb, cc, dd, F3, K3, in[3],  11);
@@ -178,7 +178,7 @@ static void rmd256_transform(u32 *state, const __le32 *in)
 	ROUND(bbb, ccc, ddd, aaa, F2, KK3, in[13],  5);
 
 	/* Swap contents of "c" registers */
-	tmp = cc; cc = ccc; ccc = tmp;
+	swap(cc, ccc);
 
 	/* round 4: left lane */
 	ROUND(aa, bb, cc, dd, F4, K4, in[1],  11);
@@ -217,7 +217,7 @@ static void rmd256_transform(u32 *state, const __le32 *in)
 	ROUND(bbb, ccc, ddd, aaa, F1, KK4, in[14],  8);
 
 	/* Swap contents of "d" registers */
-	tmp = dd; dd = ddd; ddd = tmp;
+	swap(dd, ddd);
 
 	/* combine results */
 	state[0] += aa;
-- 
cgit v1.2.3


From a4789089937941959be6c18fa53e1fc0189257fd Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 18 Jul 2018 12:19:08 -0500
Subject: crypto: rmd320 - use swap macro in rmd320_transform

Make use of the swap macro and remove unnecessary variable *tmp*.
This makes the code easier to read and maintain.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/rmd320.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/crypto/rmd320.c b/crypto/rmd320.c
index ab3cf93624d2..3ae1df5bb48c 100644
--- a/crypto/rmd320.c
+++ b/crypto/rmd320.c
@@ -53,7 +53,7 @@ struct rmd320_ctx {
 
 static void rmd320_transform(u32 *state, const __le32 *in)
 {
-	u32 aa, bb, cc, dd, ee, aaa, bbb, ccc, ddd, eee, tmp;
+	u32 aa, bb, cc, dd, ee, aaa, bbb, ccc, ddd, eee;
 
 	/* Initialize left lane */
 	aa = state[0];
@@ -106,7 +106,7 @@ static void rmd320_transform(u32 *state, const __le32 *in)
 	ROUND(aaa, bbb, ccc, ddd, eee, F5, KK1, in[12],  6);
 
 	/* Swap contents of "a" registers */
-	tmp = aa; aa = aaa; aaa = tmp;
+	swap(aa, aaa);
 
 	/* round 2: left lane" */
 	ROUND(ee, aa, bb, cc, dd, F2, K2, in[7],   7);
@@ -145,7 +145,7 @@ static void rmd320_transform(u32 *state, const __le32 *in)
 	ROUND(eee, aaa, bbb, ccc, ddd, F4, KK2, in[2],  11);
 
 	/* Swap contents of "b" registers */
-	tmp = bb; bb = bbb; bbb = tmp;
+	swap(bb, bbb);
 
 	/* round 3: left lane" */
 	ROUND(dd, ee, aa, bb, cc, F3, K3, in[3],  11);
@@ -184,7 +184,7 @@ static void rmd320_transform(u32 *state, const __le32 *in)
 	ROUND(ddd, eee, aaa, bbb, ccc, F3, KK3, in[13],  5);
 
 	/* Swap contents of "c" registers */
-	tmp = cc; cc = ccc; ccc = tmp;
+	swap(cc, ccc);
 
 	/* round 4: left lane" */
 	ROUND(cc, dd, ee, aa, bb, F4, K4, in[1],  11);
@@ -223,7 +223,7 @@ static void rmd320_transform(u32 *state, const __le32 *in)
 	ROUND(ccc, ddd, eee, aaa, bbb, F2, KK4, in[14],  8);
 
 	/* Swap contents of "d" registers */
-	tmp = dd; dd = ddd; ddd = tmp;
+	swap(dd, ddd);
 
 	/* round 5: left lane" */
 	ROUND(bb, cc, dd, ee, aa, F5, K5, in[4],   9);
@@ -262,7 +262,7 @@ static void rmd320_transform(u32 *state, const __le32 *in)
 	ROUND(bbb, ccc, ddd, eee, aaa, F1, KK5, in[11], 11);
 
 	/* Swap contents of "e" registers */
-	tmp = ee; ee = eee; eee = tmp;
+	swap(ee, eee);
 
 	/* combine results */
 	state[0] += aa;
-- 
cgit v1.2.3


From 43bd1dce39cea87a75e8691aad4ce11a9b457d8e Mon Sep 17 00:00:00 2001
From: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Date: Fri, 20 Jul 2018 10:09:16 -0400
Subject: media: vivid: Fix V4L2_FIELD_ALTERNATE new frame check

The vivid driver will overlay stream time on generated frames. Though,
in interlacing mode V4L2_FIELD_ALTERNATE, each field is separate and
must have the same time to ensure proper render. Though, this time was
only updated every 2 frames as the code was checking against the wrong
counter (frame counter rather then field counter).

Signed-off-by: Nicolas Dufresne <nicolas.dufresne@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vivid/vivid-kthread-cap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/vivid/vivid-kthread-cap.c b/drivers/media/platform/vivid/vivid-kthread-cap.c
index 3fdb280c36ca..f06003bb8e42 100644
--- a/drivers/media/platform/vivid/vivid-kthread-cap.c
+++ b/drivers/media/platform/vivid/vivid-kthread-cap.c
@@ -477,7 +477,7 @@ static void vivid_fillbuff(struct vivid_dev *dev, struct vivid_buffer *buf)
 
 	/* Updates stream time, only update at the start of a new frame. */
 	if (dev->field_cap != V4L2_FIELD_ALTERNATE ||
-			(buf->vb.sequence & 1) == 0)
+			(dev->vid_cap_seq_count & 1) == 0)
 		dev->ms_vid_cap =
 			jiffies_to_msecs(jiffies - dev->jiffies_vid_cap);
 
-- 
cgit v1.2.3


From 87e1a881e1fe3bfd89903c54ae0d6d6adedb76f1 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Wed, 25 Jul 2018 08:51:39 -0400
Subject: media: media.h: remove linux/version.h include

The media.h public header is one of only three public headers that include
linux/version.h. Drop it from media.h. It was only used for an obsolete
define.

It has to be added to media-device.c, since that source relied on media.h
to include it.

Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/media-device.c | 1 +
 include/uapi/linux/media.h   | 3 +--
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c
index 14959b19a342..fcdf3d5dc4b6 100644
--- a/drivers/media/media-device.c
+++ b/drivers/media/media-device.c
@@ -25,6 +25,7 @@
 #include <linux/types.h>
 #include <linux/pci.h>
 #include <linux/usb.h>
+#include <linux/version.h>
 
 #include <media/media-device.h>
 #include <media/media-devnode.h>
diff --git a/include/uapi/linux/media.h b/include/uapi/linux/media.h
index 82ec9f132a53..36f76e777ef9 100644
--- a/include/uapi/linux/media.h
+++ b/include/uapi/linux/media.h
@@ -25,7 +25,6 @@
 #endif
 #include <linux/ioctl.h>
 #include <linux/types.h>
-#include <linux/version.h>
 
 struct media_device_info {
 	char driver[16];
@@ -421,7 +420,7 @@ struct media_v2_topology {
 #define MEDIA_INTF_T_ALSA_TIMER			(MEDIA_INTF_T_ALSA_BASE + 7)
 
 /* Obsolete symbol for media_version, no longer used in the kernel */
-#define MEDIA_API_VERSION			KERNEL_VERSION(0, 1, 0)
+#define MEDIA_API_VERSION			((0 << 16) | (1 << 8) | 0)
 
 #endif
 
-- 
cgit v1.2.3


From ddc5c1f799123224a8e02c49d992f962bed225f3 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Wed, 25 Jul 2018 17:01:23 -0400
Subject: media: rockchip/rga: Fix bad dma_free_attrs() parameter

In rga_remove(), dma_free_attrs is being passed the wrong
cpu address, which triggers an exception if the driver is
removed. Fix it.

Tested on a RK3399 platform, with a bind/unbind cycle.

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rockchip/rga/rga.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/rockchip/rga/rga.c b/drivers/media/platform/rockchip/rga/rga.c
index 69a2797d7bbe..ab5a6f95044a 100644
--- a/drivers/media/platform/rockchip/rga/rga.c
+++ b/drivers/media/platform/rockchip/rga/rga.c
@@ -925,7 +925,7 @@ static int rga_remove(struct platform_device *pdev)
 {
 	struct rockchip_rga *rga = platform_get_drvdata(pdev);
 
-	dma_free_attrs(rga->dev, RGA_CMDBUF_SIZE, &rga->cmdbuf_virt,
+	dma_free_attrs(rga->dev, RGA_CMDBUF_SIZE, rga->cmdbuf_virt,
 		       rga->cmdbuf_phy, DMA_ATTR_WRITE_COMBINE);
 
 	free_pages((unsigned long)rga->src_mmu_pages, 3);
-- 
cgit v1.2.3


From 6457b6263f0f11a9bff4e03a0141820ae9c81460 Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Thu, 26 Jul 2018 06:27:15 -0400
Subject: media: adv7180: fix field type to V4L2_FIELD_ALTERNATE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ADV7180 and ADV7182 transmit whole fields, bottom field followed
by top (or vice-versa, depending on detected video standard). So
for chips that do not have support for explicitly setting the field
mode via I2P, set the field mode to V4L2_FIELD_ALTERNATE.

I2P converts fields into frames using an edge adaptive algorithm. The
frame rate is the same as the 'field rate': e.g. X fields per second
are now X frames per second.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/adv7180.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index a727d7f806a1..5a2751a688b8 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -644,6 +644,9 @@ static int adv7180_mbus_fmt(struct v4l2_subdev *sd,
 	fmt->width = 720;
 	fmt->height = state->curr_norm & V4L2_STD_525_60 ? 480 : 576;
 
+	if (state->field == V4L2_FIELD_ALTERNATE)
+		fmt->height /= 2;
+
 	return 0;
 }
 
@@ -711,11 +714,11 @@ static int adv7180_set_pad_format(struct v4l2_subdev *sd,
 
 	switch (format->format.field) {
 	case V4L2_FIELD_NONE:
-		if (!(state->chip_info->flags & ADV7180_FLAG_I2P))
-			format->format.field = V4L2_FIELD_INTERLACED;
-		break;
+		if (state->chip_info->flags & ADV7180_FLAG_I2P)
+			break;
+		/* fall through */
 	default:
-		format->format.field = V4L2_FIELD_INTERLACED;
+		format->format.field = V4L2_FIELD_ALTERNATE;
 		break;
 	}
 
@@ -1291,7 +1294,7 @@ static int adv7180_probe(struct i2c_client *client,
 		return -ENOMEM;
 
 	state->client = client;
-	state->field = V4L2_FIELD_INTERLACED;
+	state->field = V4L2_FIELD_ALTERNATE;
 	state->chip_info = (struct adv7180_chip_info *)id->driver_data;
 
 	state->pwdn_gpio = devm_gpiod_get_optional(&client->dev, "powerdown",
-- 
cgit v1.2.3


From 38566d28ea9114f9019e7f9804d6db5cd98bf6dd Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Thu, 26 Jul 2018 06:27:16 -0400
Subject: media: adv7180: add g_frame_interval support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement g_frame_interval to return the current standard's frame
interval.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/adv7180.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/media/i2c/adv7180.c b/drivers/media/i2c/adv7180.c
index 5a2751a688b8..de10367d550b 100644
--- a/drivers/media/i2c/adv7180.c
+++ b/drivers/media/i2c/adv7180.c
@@ -461,6 +461,22 @@ static int adv7180_g_std(struct v4l2_subdev *sd, v4l2_std_id *norm)
 	return 0;
 }
 
+static int adv7180_g_frame_interval(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_frame_interval *fi)
+{
+	struct adv7180_state *state = to_state(sd);
+
+	if (state->curr_norm & V4L2_STD_525_60) {
+		fi->interval.numerator = 1001;
+		fi->interval.denominator = 30000;
+	} else {
+		fi->interval.numerator = 1;
+		fi->interval.denominator = 25;
+	}
+
+	return 0;
+}
+
 static void adv7180_set_power_pin(struct adv7180_state *state, bool on)
 {
 	if (!state->pwdn_gpio)
@@ -820,6 +836,7 @@ static int adv7180_subscribe_event(struct v4l2_subdev *sd,
 static const struct v4l2_subdev_video_ops adv7180_video_ops = {
 	.s_std = adv7180_s_std,
 	.g_std = adv7180_g_std,
+	.g_frame_interval = adv7180_g_frame_interval,
 	.querystd = adv7180_querystd,
 	.g_input_status = adv7180_g_input_status,
 	.s_routing = adv7180_s_routing,
-- 
cgit v1.2.3


From 17f330ce9e434333a98b0fbc7b6d5ddbe0cc6770 Mon Sep 17 00:00:00 2001
From: Matt Ranostay <matt.ranostay@konsulko.com>
Date: Thu, 26 Jul 2018 21:47:24 -0400
Subject: media: video-i2c: hwmon: fix return value from amg88xx_hwmon_init()

PTR_ERR was making any pointer passed an error pointer, and should be
replaced with PTR_ERR_OR_ZERO which checks if is an actual error condition.

Signed-off-by: Matt Ranostay <matt.ranostay@konsulko.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/video-i2c.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/video-i2c.c b/drivers/media/i2c/video-i2c.c
index 7dc9338502e5..06d29d8f6be8 100644
--- a/drivers/media/i2c/video-i2c.c
+++ b/drivers/media/i2c/video-i2c.c
@@ -167,7 +167,7 @@ static int amg88xx_hwmon_init(struct video_i2c_data *data)
 	void *hwmon = devm_hwmon_device_register_with_info(&data->client->dev,
 				"amg88xx", data, &amg88xx_chip_info, NULL);
 
-	return PTR_ERR(hwmon);
+	return PTR_ERR_OR_ZERO(hwmon);
 }
 #else
 #define	amg88xx_hwmon_init	NULL
-- 
cgit v1.2.3


From 2b5c5798750180a34cb1f39cf648d8a8bceec287 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 22:58:43 -0400
Subject: media: i2c: adv7842: Replace mdelay() with msleep() and
 usleep_range() in adv7842_ddr_ram_test()

adv7842_ddr_ram_test() is never called in atomic context.
It only calls from:
adv7842_ddr_ram_test() <- adv7842_command_ram_test() <- adv7842_ioctl()

adv7842_ddr_ram_test() calls mdelay() to busily wait,
which is not necessary.
mdelay() can be replaced with msleep() and usleep_range().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/adv7842.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/media/i2c/adv7842.c b/drivers/media/i2c/adv7842.c
index 99d781343fb1..4f8fbdd00e35 100644
--- a/drivers/media/i2c/adv7842.c
+++ b/drivers/media/i2c/adv7842.c
@@ -3102,7 +3102,7 @@ static int adv7842_ddr_ram_test(struct v4l2_subdev *sd)
 	sdp_write(sd, 0x12, 0x00); /* Disable 3D comb, Frame TBC & 3DNR */
 	io_write(sd, 0xFF, 0x04);  /* Reset memory controller */
 
-	mdelay(5);
+	usleep_range(5000, 6000);
 
 	sdp_write(sd, 0x12, 0x00);    /* Disable 3D Comb, Frame TBC & 3DNR */
 	sdp_io_write(sd, 0x2A, 0x01); /* Memory BIST Initialisation */
@@ -3116,12 +3116,12 @@ static int adv7842_ddr_ram_test(struct v4l2_subdev *sd)
 	sdp_io_write(sd, 0x7d, 0x00); /* Memory BIST Initialisation */
 	sdp_io_write(sd, 0x7e, 0x1a); /* Memory BIST Initialisation */
 
-	mdelay(5);
+	usleep_range(5000, 6000);
 
 	sdp_io_write(sd, 0xd9, 0xd5); /* Enable BIST Test */
 	sdp_write(sd, 0x12, 0x05); /* Enable FRAME TBC & 3D COMB */
 
-	mdelay(20);
+	msleep(20);
 
 	for (i = 0; i < 10; i++) {
 		u8 result = sdp_io_read(sd, 0xdb);
@@ -3132,7 +3132,7 @@ static int adv7842_ddr_ram_test(struct v4l2_subdev *sd)
 			else
 				pass++;
 		}
-		mdelay(20);
+		msleep(20);
 	}
 
 	v4l2_dbg(1, debug, sd,
-- 
cgit v1.2.3


From a8a4d304b1a41105568c1408e4276cd6f32be787 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:02:40 -0400
Subject: media: i2c: vs6624: Replace mdelay() with msleep() and usleep_range()
 in vs6624_probe()

vs6624_probe() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep() and usleep_range().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/vs6624.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/i2c/vs6624.c b/drivers/media/i2c/vs6624.c
index 1658816a9844..bc9825f4a73d 100644
--- a/drivers/media/i2c/vs6624.c
+++ b/drivers/media/i2c/vs6624.c
@@ -770,7 +770,7 @@ static int vs6624_probe(struct i2c_client *client,
 		return ret;
 	}
 	/* wait 100ms before any further i2c writes are performed */
-	mdelay(100);
+	msleep(100);
 
 	sensor = devm_kzalloc(&client->dev, sizeof(*sensor), GFP_KERNEL);
 	if (sensor == NULL)
@@ -782,7 +782,7 @@ static int vs6624_probe(struct i2c_client *client,
 	vs6624_writeregs(sd, vs6624_p1);
 	vs6624_write(sd, VS6624_MICRO_EN, 0x2);
 	vs6624_write(sd, VS6624_DIO_EN, 0x1);
-	mdelay(10);
+	usleep_range(10000, 11000);
 	vs6624_writeregs(sd, vs6624_p2);
 
 	vs6624_writeregs(sd, vs6624_default);
-- 
cgit v1.2.3


From da27ef68751f804dbe6c2b84a49848f90ae48fd0 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:07:04 -0400
Subject: media: pci: cobalt: Replace GFP_ATOMIC with GFP_KERNEL in
 cobalt_probe()

cobalt_probe() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cobalt/cobalt-driver.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/cobalt/cobalt-driver.c b/drivers/media/pci/cobalt/cobalt-driver.c
index c8b1a6206c65..4885e833c052 100644
--- a/drivers/media/pci/cobalt/cobalt-driver.c
+++ b/drivers/media/pci/cobalt/cobalt-driver.c
@@ -670,7 +670,7 @@ static int cobalt_probe(struct pci_dev *pci_dev,
 	/* FIXME - module parameter arrays constrain max instances */
 	i = atomic_inc_return(&cobalt_instance) - 1;
 
-	cobalt = kzalloc(sizeof(struct cobalt), GFP_ATOMIC);
+	cobalt = kzalloc(sizeof(struct cobalt), GFP_KERNEL);
 	if (cobalt == NULL)
 		return -ENOMEM;
 	cobalt->pci_dev = pci_dev;
-- 
cgit v1.2.3


From c5157101e7793b42a56e07368c7f4cb73fb58008 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 12 Jul 2018 00:18:22 +0100
Subject: arm64: mm: Export __sync_icache_dcache() for xen-privcmd

The xen-privcmd driver, which can be modular, calls set_pte_at()
which in turn may call __sync_icache_dcache().

The call to __sync_icache_dcache() may be optimised out because it is
conditional on !pte_special(), and xen-privcmd calls pte_mkspecial().
But it seems unwise to rely on this optimisation.

Fixes: 3ad0876554ca ("xen/privcmd: add IOCTL_PRIVCMD_MMAP_RESOURCE")
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/mm/flush.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 9786f9d5d3dc..30695a868107 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -66,6 +66,7 @@ void __sync_icache_dcache(pte_t pte)
 		sync_icache_aliases(page_address(page),
 				    PAGE_SIZE << compound_order(page));
 }
+EXPORT_SYMBOL_GPL(__sync_icache_dcache);
 
 /*
  * This function is called when a page has been modified by the kernel. Mark
-- 
cgit v1.2.3


From ccb2ca78a7278ec0024f281fdc2155b32f995cef Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:09:46 -0400
Subject: media: pci: cx23885: Replace mdelay() with msleep() and
 usleep_range() in altera_ci_slot_reset()

altera_ci_slot_reset() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx23885/altera-ci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/cx23885/altera-ci.c b/drivers/media/pci/cx23885/altera-ci.c
index 70aec9bb7e95..62bc8049b320 100644
--- a/drivers/media/pci/cx23885/altera-ci.c
+++ b/drivers/media/pci/cx23885/altera-ci.c
@@ -346,7 +346,7 @@ static int altera_ci_slot_reset(struct dvb_ca_en50221 *en50221, int slot)
 	mutex_unlock(&inter->fpga_mutex);
 
 	for (;;) {
-		mdelay(50);
+		msleep(50);
 
 		mutex_lock(&inter->fpga_mutex);
 
-- 
cgit v1.2.3


From 9095b23fc2a1f64b774368a12cc91b941e200512 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:15:34 -0400
Subject: media: pci: cx23885: Replace mdelay() with msleep() and
 usleep_range() in cx23885_gpio_setup()

cx23885_gpio_setup() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep() and usleep_range().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx23885/cx23885-cards.c | 82 +++++++++++++++----------------
 1 file changed, 41 insertions(+), 41 deletions(-)

diff --git a/drivers/media/pci/cx23885/cx23885-cards.c b/drivers/media/pci/cx23885/cx23885-cards.c
index 9f50748fdf56..ed3210dc50bc 100644
--- a/drivers/media/pci/cx23885/cx23885-cards.c
+++ b/drivers/media/pci/cx23885/cx23885-cards.c
@@ -1497,20 +1497,20 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the demod into reset and protect the eeprom */
 		mc417_gpio_clear(dev, GPIO_15 | GPIO_14);
-		mdelay(100);
+		msleep(100);
 
 		/* Bring the demod and blaster out of reset */
 		mc417_gpio_set(dev, GPIO_15 | GPIO_14);
-		mdelay(100);
+		msleep(100);
 
 		/* Force the TDA8295A into reset and back */
 		cx23885_gpio_enable(dev, GPIO_2, 1);
 		cx23885_gpio_set(dev, GPIO_2);
-		mdelay(20);
+		msleep(20);
 		cx23885_gpio_clear(dev, GPIO_2);
-		mdelay(20);
+		msleep(20);
 		cx23885_gpio_set(dev, GPIO_2);
-		mdelay(20);
+		msleep(20);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1200:
 		/* GPIO-0 tda10048 demodulator reset */
@@ -1518,9 +1518,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00050000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000005);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00050005);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1700:
@@ -1539,9 +1539,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00050000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000005);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00050005);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1400:
@@ -1551,9 +1551,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00050000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000005);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00050005);
 		break;
 	case CX23885_BOARD_DVICO_FUSIONHDTV_7_DUAL_EXP:
@@ -1564,9 +1564,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x000f0000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x0000000f);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x000f000f);
 		break;
 	case CX23885_BOARD_DVICO_FUSIONHDTV_DVB_T_DUAL_EXP:
@@ -1578,9 +1578,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x000f0000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x0000000f);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x000f000f);
 		break;
 	case CX23885_BOARD_LEADTEK_WINFAST_PXDVR3200_H:
@@ -1596,9 +1596,9 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the parts into reset and back */
 		cx_set(GP0_IO, 0x00040000);
-		mdelay(20);
+		msleep(20);
 		cx_clear(GP0_IO, 0x00000004);
-		mdelay(20);
+		msleep(20);
 		cx_set(GP0_IO, 0x00040004);
 		break;
 	case CX23885_BOARD_TBS_6920:
@@ -1608,11 +1608,11 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_write(MC417_CTL, 0x00000036);
 		cx_write(MC417_OEN, 0x00001000);
 		cx_set(MC417_RWD, 0x00000002);
-		mdelay(200);
+		msleep(200);
 		cx_clear(MC417_RWD, 0x00000800);
-		mdelay(200);
+		msleep(200);
 		cx_set(MC417_RWD, 0x00000800);
-		mdelay(200);
+		msleep(200);
 		break;
 	case CX23885_BOARD_NETUP_DUAL_DVBS2_CI:
 		/* GPIO-0 INTA from CiMax1
@@ -1630,7 +1630,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_set(GP0_IO, 0x00040000); /* GPIO as out */
 		/* GPIO1 and GPIO2 as INTA and INTB from CiMaxes, reset low */
 		cx_clear(GP0_IO, 0x00030004);
-		mdelay(100);/* reset delay */
+		msleep(100);/* reset delay */
 		cx_set(GP0_IO, 0x00040004); /* GPIO as out, reset high */
 		cx_write(MC417_CTL, 0x00000037);/* enable GPIO3-18 pins */
 		/* GPIO-15 IN as ~ACK, rest as OUT */
@@ -1653,7 +1653,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx23885_gpio_enable(dev, GPIO_9 | GPIO_6 | GPIO_5, 1);
 		cx23885_gpio_set(dev, GPIO_9 | GPIO_6 | GPIO_5);
 		cx23885_gpio_clear(dev, GPIO_9);
-		mdelay(20);
+		msleep(20);
 		cx23885_gpio_set(dev, GPIO_9);
 		break;
 	case CX23885_BOARD_MYGICA_X8506:
@@ -1664,18 +1664,18 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		/* GPIO-2 demod reset */
 		cx23885_gpio_enable(dev, GPIO_0 | GPIO_1 | GPIO_2, 1);
 		cx23885_gpio_clear(dev, GPIO_1 | GPIO_2);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_0 | GPIO_1 | GPIO_2);
-		mdelay(100);
+		msleep(100);
 		break;
 	case CX23885_BOARD_MYGICA_X8558PRO:
 		/* GPIO-0 reset first ATBM8830 */
 		/* GPIO-1 reset second ATBM8830 */
 		cx23885_gpio_enable(dev, GPIO_0 | GPIO_1, 1);
 		cx23885_gpio_clear(dev, GPIO_0 | GPIO_1);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_0 | GPIO_1);
-		mdelay(100);
+		msleep(100);
 		break;
 	case CX23885_BOARD_HAUPPAUGE_HVR1850:
 	case CX23885_BOARD_HAUPPAUGE_HVR1290:
@@ -1699,11 +1699,11 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		/* Put the demod into reset and protect the eeprom */
 		mc417_gpio_clear(dev, GPIO_14 | GPIO_13);
-		mdelay(100);
+		msleep(100);
 
 		/* Bring the demod out of reset */
 		mc417_gpio_set(dev, GPIO_14);
-		mdelay(100);
+		msleep(100);
 
 		/* CX24228 GPIO */
 		/* Connected to IF / Mux */
@@ -1728,7 +1728,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_set(GP0_IO, 0x00060000); /* GPIO-1,2 as out */
 		/* GPIO-0 as INT, reset & TMS low */
 		cx_clear(GP0_IO, 0x00010006);
-		mdelay(100);/* reset delay */
+		msleep(100);/* reset delay */
 		cx_set(GP0_IO, 0x00000004); /* reset high */
 		cx_write(MC417_CTL, 0x00000037);/* enable GPIO-3..18 pins */
 		/* GPIO-17 is TDO in, GPIO-15 is ~RDY in, rest is out */
@@ -1747,36 +1747,36 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx23885_gpio_enable(dev, GPIO_8 | GPIO_9, 1);
 
 		cx23885_gpio_clear(dev, GPIO_8 | GPIO_9);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_8 | GPIO_9);
-		mdelay(100);
+		msleep(100);
 
 		break;
 	case CX23885_BOARD_AVERMEDIA_HC81R:
 		cx_clear(MC417_CTL, 1);
 		/* GPIO-0,1,2 setup direction as output */
 		cx_set(GP0_IO, 0x00070000);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		/* AF9013 demod reset */
 		cx_set(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_clear(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_set(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		/* demod tune? */
 		cx_clear(GP0_IO, 0x00030003);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_set(GP0_IO, 0x00020002);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_set(GP0_IO, 0x00010001);
-		mdelay(10);
+		usleep_range(10000, 11000);
 		cx_clear(GP0_IO, 0x00020002);
 		/* XC3028L tuner reset */
 		cx_set(GP0_IO, 0x00040004);
 		cx_clear(GP0_IO, 0x00040004);
 		cx_set(GP0_IO, 0x00040004);
-		mdelay(60);
+		msleep(60);
 		break;
 	case CX23885_BOARD_DVBSKY_T9580:
 	case CX23885_BOARD_DVBSKY_S952:
@@ -1785,7 +1785,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 		cx_write(MC417_CTL, 0x00000037);
 		cx23885_gpio_enable(dev, GPIO_2 | GPIO_11, 1);
 		cx23885_gpio_clear(dev, GPIO_2 | GPIO_11);
-		mdelay(100);
+		msleep(100);
 		cx23885_gpio_set(dev, GPIO_2 | GPIO_11);
 		break;
 	case CX23885_BOARD_DVBSKY_T980C:
@@ -1807,7 +1807,7 @@ void cx23885_gpio_setup(struct cx23885_dev *dev)
 
 		cx_set(GP0_IO, 0x00060002); /* GPIO 1/2 as output */
 		cx_clear(GP0_IO, 0x00010004); /* GPIO 0 as input */
-		mdelay(100); /* reset delay */
+		msleep(100); /* reset delay */
 		cx_set(GP0_IO, 0x00060004); /* GPIO as out, reset high */
 		cx_clear(GP0_IO, 0x00010002);
 		cx_write(MC417_CTL, 0x00000037); /* enable GPIO3-18 pins */
-- 
cgit v1.2.3


From 71be8dee6bf13a00bab0f568ce403b3c28c5295f Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:18:46 -0400
Subject: media: pci: cx23885: Replace mdelay() with msleep() in
 cx23885_reset()

cx23885_reset() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx23885/cx23885-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/cx23885/cx23885-core.c b/drivers/media/pci/cx23885/cx23885-core.c
index 94b996ff12a9..39804d830305 100644
--- a/drivers/media/pci/cx23885/cx23885-core.c
+++ b/drivers/media/pci/cx23885/cx23885-core.c
@@ -667,7 +667,7 @@ static void cx23885_reset(struct cx23885_dev *dev)
 
 	/* clear dma in progress */
 	cx23885_clear_bridge_error(dev);
-	mdelay(100);
+	msleep(100);
 
 	cx23885_sram_channel_setup(dev, &dev->sram_channels[SRAM_CH01],
 		720*4, 0);
-- 
cgit v1.2.3


From 65155a9bbc18e4312a989a13c137c7410e1568dd Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:22:09 -0400
Subject: media: pci: cx25821: Replace mdelay() with msleep()

cx25821_gpio_init(), cx25821_initialize() and cx25821_registers_init()
are never called in atomic context.
They call mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx25821/cx25821-core.c | 4 ++--
 drivers/media/pci/cx25821/cx25821-gpio.c | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/pci/cx25821/cx25821-core.c b/drivers/media/pci/cx25821/cx25821-core.c
index 040c6c251d3a..2f0171134f7e 100644
--- a/drivers/media/pci/cx25821/cx25821-core.c
+++ b/drivers/media/pci/cx25821/cx25821-core.c
@@ -428,7 +428,7 @@ static void cx25821_registers_init(struct cx25821_dev *dev)
 	tmp |= FLD_USE_ALT_PLL_REF;
 	cx_write(CLK_RST, tmp & ~(FLD_VID_I_CLK_NOE | FLD_VID_J_CLK_NOE));
 
-	mdelay(100);
+	msleep(100);
 }
 
 int cx25821_sram_channel_setup(struct cx25821_dev *dev,
@@ -803,7 +803,7 @@ static void cx25821_initialize(struct cx25821_dev *dev)
 	cx_write(CLK_DELAY, cx_read(CLK_DELAY) & 0x80000000);
 	cx_write(PAD_CTRL, 0x12);	/* for I2C */
 	cx25821_registers_init(dev);	/* init Pecos registers */
-	mdelay(100);
+	msleep(100);
 
 	for (i = 0; i < VID_CHANNEL_NUM; i++) {
 		cx25821_set_vip_mode(dev, dev->channels[i].sram_channels);
diff --git a/drivers/media/pci/cx25821/cx25821-gpio.c b/drivers/media/pci/cx25821/cx25821-gpio.c
index 76b8f619e55a..f5ffaf880e5f 100644
--- a/drivers/media/pci/cx25821/cx25821-gpio.c
+++ b/drivers/media/pci/cx25821/cx25821-gpio.c
@@ -88,7 +88,7 @@ void cx25821_gpio_init(struct cx25821_dev *dev)
 	default:
 		/* set GPIO 5 to select the path for Medusa/Athena */
 		cx25821_set_gpiopin_logicvalue(dev, 5, 1);
-		mdelay(20);
+		msleep(20);
 		break;
 	}
 
-- 
cgit v1.2.3


From dddaf754cb3af9fe779be1f6e117dc76e36cfdc2 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:38:23 -0400
Subject: media: pci: cx88: Replace mdelay() with msleep() in
 cx88_card_setup_pre_i2c()

cx88_card_setup_pre_i2c() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx88/cx88-cards.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/pci/cx88/cx88-cards.c b/drivers/media/pci/cx88/cx88-cards.c
index 4c92d2388c26..07e1483e987d 100644
--- a/drivers/media/pci/cx88/cx88-cards.c
+++ b/drivers/media/pci/cx88/cx88-cards.c
@@ -3307,9 +3307,9 @@ static void cx88_card_setup_pre_i2c(struct cx88_core *core)
 	case CX88_BOARD_PROLINK_PV_GLOBAL_XTREME:
 	case CX88_BOARD_PROLINK_PV_8000GT:
 		cx_write(MO_GP2_IO, 0xcf7);
-		mdelay(50);
+		msleep(50);
 		cx_write(MO_GP2_IO, 0xef5);
-		mdelay(50);
+		msleep(50);
 		cx_write(MO_GP2_IO, 0xcf7);
 		usleep_range(10000, 20000);
 		break;
-- 
cgit v1.2.3


From 9d08ba6de0c52d87b1f9619df3f6faacde2134b7 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:41:50 -0400
Subject: media: pci: cx88: Replace mdelay() with msleep() in dvb_register()

dvb_register() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/cx88/cx88-dvb.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/media/pci/cx88/cx88-dvb.c b/drivers/media/pci/cx88/cx88-dvb.c
index ccfde28d4af2..90b208747e0f 100644
--- a/drivers/media/pci/cx88/cx88-dvb.c
+++ b/drivers/media/pci/cx88/cx88-dvb.c
@@ -1226,9 +1226,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 1);
-		mdelay(200);
+		msleep(200);
 
 		/* Select RF connector callback */
 		fusionhdtv_3_gold.pll_rf_set = lgdt330x_pll_rf_set;
@@ -1248,9 +1248,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 9);
-		mdelay(200);
+		msleep(200);
 		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &fusionhdtv_3_gold,
 					       0x0e,
@@ -1267,9 +1267,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 1);
-		mdelay(200);
+		msleep(200);
 		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &fusionhdtv_5_gold,
 					       0x0e,
@@ -1289,9 +1289,9 @@ static int dvb_register(struct cx8802_dev *dev)
 
 		/* Do a hardware reset of chip before using it. */
 		cx_clear(MO_GP0_IO, 1);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 1);
-		mdelay(200);
+		msleep(200);
 		fe0->dvb.frontend = dvb_attach(lgdt330x_attach,
 					       &pchdtv_hd5500,
 					       0x59,
@@ -1583,9 +1583,9 @@ static int dvb_register(struct cx8802_dev *dev)
 		cx_set(MO_GP0_IO, 0x0101);
 
 		cx_clear(MO_GP0_IO, 0x01);
-		mdelay(100);
+		msleep(100);
 		cx_set(MO_GP0_IO, 0x01);
-		mdelay(200);
+		msleep(200);
 
 		fe0->dvb.frontend = dvb_attach(stv0299_attach,
 					       &samsung_stv0299_config,
-- 
cgit v1.2.3


From 5bfffa0c86915e5afbfe56d9790457b2a9887f2d Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 23:44:24 -0400
Subject: media: pci: ivtv: Replace GFP_ATOMIC with GFP_KERNEL

ivtv_probe() and ivtvfb_init_card() are never called in atomic context.
They call kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ivtv/ivtv-driver.c | 2 +-
 drivers/media/pci/ivtv/ivtvfb.c      | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/pci/ivtv/ivtv-driver.c b/drivers/media/pci/ivtv/ivtv-driver.c
index 6b2ffdc96961..dd727098daf4 100644
--- a/drivers/media/pci/ivtv/ivtv-driver.c
+++ b/drivers/media/pci/ivtv/ivtv-driver.c
@@ -999,7 +999,7 @@ static int ivtv_probe(struct pci_dev *pdev, const struct pci_device_id *pci_id)
 	int vbi_buf_size;
 	struct ivtv *itv;
 
-	itv = kzalloc(sizeof(struct ivtv), GFP_ATOMIC);
+	itv = kzalloc(sizeof(struct ivtv), GFP_KERNEL);
 	if (itv == NULL)
 		return -ENOMEM;
 	itv->pdev = pdev;
diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
index b19058e36853..5ddaa8ed11a5 100644
--- a/drivers/media/pci/ivtv/ivtvfb.c
+++ b/drivers/media/pci/ivtv/ivtvfb.c
@@ -1178,7 +1178,7 @@ static int ivtvfb_init_card(struct ivtv *itv)
 	}
 
 	itv->osd_info = kzalloc(sizeof(struct osd_info),
-					GFP_ATOMIC|__GFP_NOWARN);
+					GFP_KERNEL|__GFP_NOWARN);
 	if (itv->osd_info == NULL) {
 		IVTVFB_ERR("Failed to allocate memory for osd_info\n");
 		return -ENOMEM;
-- 
cgit v1.2.3


From 4070fc9ade52f7d0ad1397fe74f564ae95e68a4f Mon Sep 17 00:00:00 2001
From: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Date: Thu, 26 Jul 2018 18:36:57 -0400
Subject: media: rcar-csi2: update stream start for V3M
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Latest errata document updates the start procedure for V3M. This change
in addition to adhering to the datasheet update fixes capture on early
revisions of V3M.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/rcar-csi2.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/rcar-csi2.c b/drivers/media/platform/rcar-vin/rcar-csi2.c
index daef72d410a3..dc5ae8025832 100644
--- a/drivers/media/platform/rcar-vin/rcar-csi2.c
+++ b/drivers/media/platform/rcar-vin/rcar-csi2.c
@@ -339,6 +339,7 @@ enum rcar_csi2_pads {
 
 struct rcar_csi2_info {
 	int (*init_phtw)(struct rcar_csi2 *priv, unsigned int mbps);
+	int (*confirm_start)(struct rcar_csi2 *priv);
 	const struct rcsi2_mbps_reg *hsfreqrange;
 	unsigned int csi0clkfreqrange;
 	bool clear_ulps;
@@ -545,6 +546,13 @@ static int rcsi2_start(struct rcar_csi2 *priv)
 	if (ret)
 		return ret;
 
+	/* Confirm start */
+	if (priv->info->confirm_start) {
+		ret = priv->info->confirm_start(priv);
+		if (ret)
+			return ret;
+	}
+
 	/* Clear Ultra Low Power interrupt. */
 	if (priv->info->clear_ulps)
 		rcsi2_write(priv, INTSTATE_REG,
@@ -880,6 +888,11 @@ static int rcsi2_init_phtw_h3_v3h_m3n(struct rcar_csi2 *priv, unsigned int mbps)
 }
 
 static int rcsi2_init_phtw_v3m_e3(struct rcar_csi2 *priv, unsigned int mbps)
+{
+	return rcsi2_phtw_write_mbps(priv, mbps, phtw_mbps_v3m_e3, 0x44);
+}
+
+static int rcsi2_confirm_start_v3m_e3(struct rcar_csi2 *priv)
 {
 	static const struct phtw_value step1[] = {
 		{ .data = 0xed, .code = 0x34 },
@@ -890,12 +903,6 @@ static int rcsi2_init_phtw_v3m_e3(struct rcar_csi2 *priv, unsigned int mbps)
 		{ /* sentinel */ },
 	};
 
-	int ret;
-
-	ret = rcsi2_phtw_write_mbps(priv, mbps, phtw_mbps_v3m_e3, 0x44);
-	if (ret)
-		return ret;
-
 	return rcsi2_phtw_write_array(priv, step1);
 }
 
@@ -949,6 +956,7 @@ static const struct rcar_csi2_info rcar_csi2_info_r8a77965 = {
 
 static const struct rcar_csi2_info rcar_csi2_info_r8a77970 = {
 	.init_phtw = rcsi2_init_phtw_v3m_e3,
+	.confirm_start = rcsi2_confirm_start_v3m_e3,
 };
 
 static const struct of_device_id rcar_csi2_of_table[] = {
-- 
cgit v1.2.3


From 9d248517d4bd807c7690d55d0b6f54618fc60942 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 23 Jul 2018 16:01:39 +0200
Subject: drm/amdgpu: add support for inplace IB patching for MM engines v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We are going to need that for the second UVD instance on Vega20.

v2: rename to patch_cs_in_place

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-and-tested-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h      |  1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c   | 22 +++++++++++++++-------
 drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h |  1 +
 3 files changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 0283e2b3c851..1f6345dda6ea 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1748,6 +1748,7 @@ amdgpu_get_sdma_instance(struct amdgpu_ring *ring)
 #define amdgpu_vm_write_pte(adev, ib, pe, value, count, incr) ((adev)->vm_manager.vm_pte_funcs->write_pte((ib), (pe), (value), (count), (incr)))
 #define amdgpu_vm_set_pte_pde(adev, ib, pe, addr, count, incr, flags) ((adev)->vm_manager.vm_pte_funcs->set_pte_pde((ib), (pe), (addr), (count), (incr), (flags)))
 #define amdgpu_ring_parse_cs(r, p, ib) ((r)->funcs->parse_cs((p), (ib)))
+#define amdgpu_ring_patch_cs_in_place(r, p, ib) ((r)->funcs->patch_cs_in_place((p), (ib)))
 #define amdgpu_ring_test_ring(r) (r)->funcs->test_ring((r))
 #define amdgpu_ring_test_ib(r, t) (r)->funcs->test_ib((r), (t))
 #define amdgpu_ring_get_rptr(r) (r)->funcs->get_rptr((r))
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 178d9ce4eba1..533b2e7656c0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -916,7 +916,7 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 	int r;
 
 	/* Only for UVD/VCE VM emulation */
-	if (p->ring->funcs->parse_cs) {
+	if (p->ring->funcs->parse_cs || p->ring->funcs->patch_cs_in_place) {
 		unsigned i, j;
 
 		for (i = 0, j = 0; i < p->nchunks && j < p->job->num_ibs; i++) {
@@ -957,12 +957,20 @@ static int amdgpu_cs_ib_vm_chunk(struct amdgpu_device *adev,
 			offset = m->start * AMDGPU_GPU_PAGE_SIZE;
 			kptr += va_start - offset;
 
-			memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
-			amdgpu_bo_kunmap(aobj);
-
-			r = amdgpu_ring_parse_cs(ring, p, j);
-			if (r)
-				return r;
+			if (p->ring->funcs->parse_cs) {
+				memcpy(ib->ptr, kptr, chunk_ib->ib_bytes);
+				amdgpu_bo_kunmap(aobj);
+
+				r = amdgpu_ring_parse_cs(ring, p, j);
+				if (r)
+					return r;
+			} else {
+				ib->ptr = (uint32_t *)kptr;
+				r = amdgpu_ring_patch_cs_in_place(ring, p, j);
+				amdgpu_bo_kunmap(aobj);
+				if (r)
+					return r;
+			}
 
 			j++;
 		}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 5018c0b6bf1a..d242b9a51e90 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -123,6 +123,7 @@ struct amdgpu_ring_funcs {
 	void (*set_wptr)(struct amdgpu_ring *ring);
 	/* validating and patching of IBs */
 	int (*parse_cs)(struct amdgpu_cs_parser *p, uint32_t ib_idx);
+	int (*patch_cs_in_place)(struct amdgpu_cs_parser *p, uint32_t ib_idx);
 	/* constants to calculate how many DW are needed for an emit */
 	unsigned emit_frame_size;
 	unsigned emit_ib_size;
-- 
cgit v1.2.3


From 66c28d6df2d8292098839d365b82a1e30b567211 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Wed, 18 Jul 2018 14:52:42 +0200
Subject: drm/amdgpu: patch the IBs for the second UVD instance v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patch the IBs for the second UVD instance so that userspace don't need
to care about the instance they submit to.

v2: use direct IB patching

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-and-tested-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c | 29 +++++++++++++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index db5f3d78ab12..d74c1b242667 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -1205,6 +1205,34 @@ static int uvd_v7_0_ring_test_ring(struct amdgpu_ring *ring)
 	return r;
 }
 
+/**
+ * uvd_v7_0_ring_patch_cs_in_place - Patch the IB for command submission.
+ *
+ * @p: the CS parser with the IBs
+ * @ib_idx: which IB to patch
+ *
+ */
+static int uvd_v7_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
+					   uint32_t ib_idx)
+{
+	struct amdgpu_ib *ib = &p->job->ibs[ib_idx];
+	unsigned i;
+
+	/* No patching necessary for the first instance */
+	if (!p->ring->me)
+		return 0;
+
+	for (i = 0; i < ib->length_dw; i += 2) {
+		uint32_t reg = amdgpu_get_ib_value(p, ib_idx, i);
+
+		reg -= p->adev->reg_offset[UVD_HWIP][0][1];
+		reg += p->adev->reg_offset[UVD_HWIP][1][1];
+
+		amdgpu_set_ib_value(p, ib_idx, i, reg);
+	}
+	return 0;
+}
+
 /**
  * uvd_v7_0_ring_emit_ib - execute indirect buffer
  *
@@ -1697,6 +1725,7 @@ static const struct amdgpu_ring_funcs uvd_v7_0_ring_vm_funcs = {
 	.get_rptr = uvd_v7_0_ring_get_rptr,
 	.get_wptr = uvd_v7_0_ring_get_wptr,
 	.set_wptr = uvd_v7_0_ring_set_wptr,
+	.patch_cs_in_place = uvd_v7_0_ring_patch_cs_in_place,
 	.emit_frame_size =
 		6 + /* hdp invalidate */
 		SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
-- 
cgit v1.2.3


From 824474ba38e27ccacc9d2dd066f780e9b3c2ad78 Mon Sep 17 00:00:00 2001
From: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Date: Fri, 13 Jul 2018 18:00:06 -0400
Subject: drm/amd/display: Retry link training again

[Why]
Some receivers seem to fail the first link training but are good on
subsequent tries. We want to retry link training again. This fixes
HTC vive pro not lighting up after being disabled.

[How]
Check if the link training passed without fall back if this is not
the case then we retry link training.

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c    | 20 ++++++++++++++++++--
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c |  5 ++++-
 drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h  |  3 ++-
 3 files changed, 24 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 388a0635c38d..966d2f9c8c99 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -60,7 +60,14 @@
 
 enum {
 	LINK_RATE_REF_FREQ_IN_MHZ = 27,
-	PEAK_FACTOR_X1000 = 1006
+	PEAK_FACTOR_X1000 = 1006,
+	/*
+	* Some receivers fail to train on first try and are good
+	* on subsequent tries. 2 retries should be plenty. If we
+	* don't have a successful training then we don't expect to
+	* ever get one.
+	*/
+	LINK_TRAINING_MAX_VERIFY_RETRY = 2
 };
 
 /*******************************************************************************
@@ -760,7 +767,16 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 				 */
 
 				/* deal with non-mst cases */
-				dp_verify_link_cap(link, &link->reported_link_cap);
+				for (i = 0; i < LINK_TRAINING_MAX_VERIFY_RETRY; i++) {
+					int fail_count = 0;
+
+					dp_verify_link_cap(link,
+							  &link->reported_link_cap,
+							  &fail_count);
+
+					if (fail_count == 0)
+						break;
+				}
 			}
 
 			/* HDMI-DVI Dongle */
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 9d901ca70588..58ee9aad13fb 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1088,7 +1088,8 @@ static struct dc_link_settings get_max_link_cap(struct dc_link *link)
 
 bool dp_verify_link_cap(
 	struct dc_link *link,
-	struct dc_link_settings *known_limit_link_setting)
+	struct dc_link_settings *known_limit_link_setting,
+	int *fail_count)
 {
 	struct dc_link_settings max_link_cap = {0};
 	struct dc_link_settings cur_link_setting = {0};
@@ -1160,6 +1161,8 @@ bool dp_verify_link_cap(
 							skip_video_pattern);
 			if (status == LINK_TRAINING_SUCCESS)
 				success = true;
+			else
+				(*fail_count)++;
 		}
 
 		if (success)
diff --git a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
index 697b5ee73845..a37255c757e0 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/dc_link_dp.h
@@ -35,7 +35,8 @@ struct dc_link_settings;
 
 bool dp_verify_link_cap(
 	struct dc_link *link,
-	struct dc_link_settings *known_limit_link_setting);
+	struct dc_link_settings *known_limit_link_setting,
+	int *fail_count);
 
 bool dp_validate_mode_timing(
 	struct dc_link *link,
-- 
cgit v1.2.3


From 65c78961b30005447a0d9b285de93354d8308f34 Mon Sep 17 00:00:00 2001
From: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Date: Thu, 28 Jun 2018 17:50:05 -0400
Subject: drm/amd/display: flatten aux_engine and engine

[Why]
engine and aux_engine are unnecessary layers we want to remove this
layer.

[How]
flatten engine and aux engine structs into one struct called
aux_engine and remove all references to the engine struct.

Signed-off-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c  |   8 +-
 drivers/gpu/drm/amd/display/dc/dce/dce_aux.c       |  55 ++++-----
 drivers/gpu/drm/amd/display/dc/dce/dce_aux.h       |   4 +-
 .../drm/amd/display/dc/dce100/dce100_resource.c    |   4 +-
 .../drm/amd/display/dc/dce110/dce110_resource.c    |   4 +-
 .../drm/amd/display/dc/dce112/dce112_resource.c    |   4 +-
 .../drm/amd/display/dc/dce120/dce120_resource.c    |   4 +-
 .../gpu/drm/amd/display/dc/dce80/dce80_resource.c  |   4 +-
 .../gpu/drm/amd/display/dc/dcn10/dcn10_resource.c  |   4 +-
 drivers/gpu/drm/amd/display/dc/inc/core_types.h    |   2 +-
 drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h | 127 ++++++++++++++++-----
 drivers/gpu/drm/amd/display/dc/inc/hw/engine.h     | 106 -----------------
 12 files changed, 140 insertions(+), 186 deletions(-)
 delete mode 100644 drivers/gpu/drm/amd/display/dc/inc/hw/engine.h

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
index 4019fe07d291..8def0d9fa0ff 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c
@@ -33,7 +33,6 @@
 #include "include/vector.h"
 #include "core_types.h"
 #include "dc_link_ddc.h"
-#include "engine.h"
 #include "aux_engine.h"
 
 #define AUX_POWER_UP_WA_DELAY 500
@@ -640,7 +639,6 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 			     enum i2caux_transaction_action action)
 {
 	struct ddc *ddc_pin = ddc->ddc_pin;
-	struct engine *engine;
 	struct aux_engine *aux_engine;
 	enum aux_channel_operation_result operation_result;
 	struct aux_request_transaction_data aux_req;
@@ -652,8 +650,8 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 	memset(&aux_req, 0, sizeof(aux_req));
 	memset(&aux_rep, 0, sizeof(aux_rep));
 
-	engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
-	aux_engine = engine->funcs->acquire(engine, ddc_pin);
+	aux_engine = ddc->ctx->dc->res_pool->engines[ddc_pin->pin_data->en];
+	aux_engine->funcs->acquire(aux_engine, ddc_pin);
 
 	aux_req.type = type;
 	aux_req.action = action;
@@ -685,7 +683,7 @@ int dc_link_aux_transfer(struct ddc_service *ddc,
 		res = -1;
 		break;
 	}
-	aux_engine->base.funcs->release_engine(&aux_engine->base);
+	aux_engine->funcs->release_engine(aux_engine);
 	return res;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
index b28e2120767e..3f5b2e6f7553 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.c
@@ -28,12 +28,12 @@
 #include "dce/dce_11_0_sh_mask.h"
 
 #define CTX \
-	aux110->base.base.ctx
+	aux110->base.ctx
 #define REG(reg_name)\
 	(aux110->regs->reg_name)
 
 #define DC_LOGGER \
-	engine->base.ctx->logger
+	engine->ctx->logger
 
 #include "reg_helper.h"
 
@@ -51,9 +51,9 @@ enum {
 	AUX_DEFER_RETRY_COUNTER = 6
 };
 static void release_engine(
-	struct engine *engine)
+	struct aux_engine *engine)
 {
-	struct aux_engine_dce110 *aux110 = FROM_ENGINE(engine);
+	struct aux_engine_dce110 *aux110 = FROM_AUX_ENGINE(engine);
 
 	dal_ddc_close(engine->ddc);
 
@@ -827,22 +827,21 @@ static bool end_of_transaction_command(
 
 	/* according Syed, it does not need now DoDummyMOT */
 }
-bool submit_request(
-	struct engine *engine,
+static bool submit_request(
+	struct aux_engine *engine,
 	struct i2caux_transaction_request *request,
 	bool middle_of_transaction)
 {
-	struct aux_engine *aux_engine = FROM_AUX_ENGINE_ENGINE(engine);
 
 	bool result;
 	bool mot_used = true;
 
 	switch (request->operation) {
 	case I2CAUX_TRANSACTION_READ:
-		result = read_command(aux_engine, request, mot_used);
+		result = read_command(engine, request, mot_used);
 	break;
 	case I2CAUX_TRANSACTION_WRITE:
-		result = write_command(aux_engine, request, mot_used);
+		result = write_command(engine, request, mot_used);
 	break;
 	default:
 		result = false;
@@ -854,45 +853,45 @@ bool submit_request(
 	 */
 
 	if (!middle_of_transaction || !result)
-		end_of_transaction_command(aux_engine, request);
+		end_of_transaction_command(engine, request);
 
 	/* mask AUX interrupt */
 
 	return result;
 }
 enum i2caux_engine_type get_engine_type(
-		const struct engine *engine)
+		const struct aux_engine *engine)
 {
 	return I2CAUX_ENGINE_TYPE_AUX;
 }
 
-static struct aux_engine *acquire(
-	struct engine *engine,
+static bool acquire(
+	struct aux_engine *engine,
 	struct ddc *ddc)
 {
-	struct aux_engine *aux_engine = FROM_AUX_ENGINE_ENGINE(engine);
+
 	enum gpio_result result;
 
-	if (aux_engine->funcs->is_engine_available) {
+	if (engine->funcs->is_engine_available) {
 		/*check whether SW could use the engine*/
-		if (!aux_engine->funcs->is_engine_available(aux_engine))
-			return NULL;
+		if (!engine->funcs->is_engine_available(engine))
+			return false;
 	}
 
 	result = dal_ddc_open(ddc, GPIO_MODE_HARDWARE,
 		GPIO_DDC_CONFIG_TYPE_MODE_AUX);
 
 	if (result != GPIO_RESULT_OK)
-		return NULL;
+		return false;
 
-	if (!aux_engine->funcs->acquire_engine(aux_engine)) {
+	if (!engine->funcs->acquire_engine(engine)) {
 		dal_ddc_close(ddc);
-		return NULL;
+		return false;
 	}
 
 	engine->ddc = ddc;
 
-	return aux_engine;
+	return true;
 }
 
 static const struct aux_engine_funcs aux_engine_funcs = {
@@ -902,9 +901,6 @@ static const struct aux_engine_funcs aux_engine_funcs = {
 	.read_channel_reply = read_channel_reply,
 	.get_channel_status = get_channel_status,
 	.is_engine_available = is_engine_available,
-};
-
-static const struct engine_funcs engine_funcs = {
 	.release_engine = release_engine,
 	.destroy_engine = dce110_engine_destroy,
 	.submit_request = submit_request,
@@ -912,10 +908,10 @@ static const struct engine_funcs engine_funcs = {
 	.acquire = acquire,
 };
 
-void dce110_engine_destroy(struct engine **engine)
+void dce110_engine_destroy(struct aux_engine **engine)
 {
 
-	struct aux_engine_dce110 *engine110 = FROM_ENGINE(*engine);
+	struct aux_engine_dce110 *engine110 = FROM_AUX_ENGINE(*engine);
 
 	kfree(engine110);
 	*engine = NULL;
@@ -927,13 +923,12 @@ struct aux_engine *dce110_aux_engine_construct(struct aux_engine_dce110 *aux_eng
 		uint32_t timeout_period,
 		const struct dce110_aux_registers *regs)
 {
-	aux_engine110->base.base.ddc = NULL;
-	aux_engine110->base.base.ctx = ctx;
+	aux_engine110->base.ddc = NULL;
+	aux_engine110->base.ctx = ctx;
 	aux_engine110->base.delay = 0;
 	aux_engine110->base.max_defer_write_retry = 0;
-	aux_engine110->base.base.funcs = &engine_funcs;
 	aux_engine110->base.funcs = &aux_engine_funcs;
-	aux_engine110->base.base.inst = inst;
+	aux_engine110->base.inst = inst;
 	aux_engine110->timeout_period = timeout_period;
 	aux_engine110->regs = regs;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
index c6b2aec2e367..f7caab85dc80 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_aux.h
@@ -103,9 +103,9 @@ struct aux_engine *dce110_aux_engine_construct(
 		uint32_t timeout_period,
 		const struct dce110_aux_registers *regs);
 
-void dce110_engine_destroy(struct engine **engine);
+void dce110_engine_destroy(struct aux_engine **engine);
 
 bool dce110_aux_engine_acquire(
-	struct engine *aux_engine,
+	struct aux_engine *aux_engine,
 	struct ddc *ddc);
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index c34c9531915e..fd2bdae4dcec 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -586,7 +586,7 @@ struct output_pixel_processor *dce100_opp_create(
 	return &opp->base;
 }
 
-struct engine *dce100_aux_engine_create(
+struct aux_engine *dce100_aux_engine_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -600,7 +600,7 @@ struct engine *dce100_aux_engine_create(
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
 				    &aux_engine_regs[inst]);
 
-	return &aux_engine->base.base;
+	return &aux_engine->base;
 }
 
 struct clock_source *dce100_clock_source_create(
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
index 4a665a29191b..e5e9e92521e9 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_resource.c
@@ -604,7 +604,7 @@ static struct output_pixel_processor *dce110_opp_create(
 	return &opp->base;
 }
 
-struct engine *dce110_aux_engine_create(
+struct aux_engine *dce110_aux_engine_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -618,7 +618,7 @@ struct engine *dce110_aux_engine_create(
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
 				    &aux_engine_regs[inst]);
 
-	return &aux_engine->base.base;
+	return &aux_engine->base;
 }
 
 struct clock_source *dce110_clock_source_create(
diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index caf90ae2cbb0..84a05ff2d674 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -604,7 +604,7 @@ struct output_pixel_processor *dce112_opp_create(
 	return &opp->base;
 }
 
-struct engine *dce112_aux_engine_create(
+struct aux_engine *dce112_aux_engine_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -618,7 +618,7 @@ struct engine *dce112_aux_engine_create(
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
 				    &aux_engine_regs[inst]);
 
-	return &aux_engine->base.base;
+	return &aux_engine->base;
 }
 
 struct clock_source *dce112_clock_source_create(
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index f7d02f2190d3..61d8e22d23c9 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -376,7 +376,7 @@ struct output_pixel_processor *dce120_opp_create(
 			     ctx, inst, &opp_regs[inst], &opp_shift, &opp_mask);
 	return &opp->base;
 }
-struct engine *dce120_aux_engine_create(
+struct aux_engine *dce120_aux_engine_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -390,7 +390,7 @@ struct engine *dce120_aux_engine_create(
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
 				    &aux_engine_regs[inst]);
 
-	return &aux_engine->base.base;
+	return &aux_engine->base;
 }
 
 static const struct bios_registers bios_regs = {
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index 6fb33ad2d3c8..dc9f3e9afc33 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -464,7 +464,7 @@ static struct output_pixel_processor *dce80_opp_create(
 	return &opp->base;
 }
 
-struct engine *dce80_aux_engine_create(
+struct aux_engine *dce80_aux_engine_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -478,7 +478,7 @@ struct engine *dce80_aux_engine_create(
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
 				    &aux_engine_regs[inst]);
 
-	return &aux_engine->base.base;
+	return &aux_engine->base;
 }
 
 static struct stream_encoder *dce80_stream_encoder_create(
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index cd8c22839227..5d169f07d745 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -594,7 +594,7 @@ static struct output_pixel_processor *dcn10_opp_create(
 	return &opp->base;
 }
 
-struct engine *dcn10_aux_engine_create(
+struct aux_engine *dcn10_aux_engine_create(
 	struct dc_context *ctx,
 	uint32_t inst)
 {
@@ -608,7 +608,7 @@ struct engine *dcn10_aux_engine_create(
 				    SW_AUX_TIMEOUT_PERIOD_MULTIPLIER * AUX_TIMEOUT_PERIOD,
 				    &aux_engine_regs[inst]);
 
-	return &aux_engine->base.base;
+	return &aux_engine->base;
 }
 
 static struct mpc *dcn10_mpc_create(struct dc_context *ctx)
diff --git a/drivers/gpu/drm/amd/display/dc/inc/core_types.h b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
index 0fa385872ed3..9f33306f9014 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/core_types.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/core_types.h
@@ -138,7 +138,7 @@ struct resource_pool {
 	struct output_pixel_processor *opps[MAX_PIPES];
 	struct timing_generator *timing_generators[MAX_PIPES];
 	struct stream_encoder *stream_enc[MAX_PIPES * 2];
-	struct engine *engines[MAX_PIPES];
+	struct aux_engine *engines[MAX_PIPES];
 	struct hubbub *hubbub;
 	struct mpc *mpc;
 	struct pp_smu_funcs_rv *pp_smu;
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
index 06d7e5d4cf21..e79cd4e92919 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/aux_engine.h
@@ -26,46 +26,72 @@
 #ifndef __DAL_AUX_ENGINE_H__
 #define __DAL_AUX_ENGINE_H__
 
-#include "engine.h"
+#include "dc_ddc_types.h"
 #include "include/i2caux_interface.h"
 
-struct aux_engine;
-union aux_config;
-struct aux_engine_funcs {
-	void (*destroy)(
-		struct aux_engine **ptr);
-	bool (*acquire_engine)(
-		struct aux_engine *engine);
-	void (*configure)(
-		struct aux_engine *engine,
-		union aux_config cfg);
-	void (*submit_channel_request)(
-		struct aux_engine *engine,
-		struct aux_request_transaction_data *request);
-	void (*process_channel_reply)(
-		struct aux_engine *engine,
-		struct aux_reply_transaction_data *reply);
-	int (*read_channel_reply)(
-		struct aux_engine *engine,
-		uint32_t size,
-		uint8_t *buffer,
-		uint8_t *reply_result,
-		uint32_t *sw_status);
-	enum aux_channel_operation_result (*get_channel_status)(
-		struct aux_engine *engine,
-		uint8_t *returned_bytes);
-	bool (*is_engine_available)(struct aux_engine *engine);
+enum i2caux_transaction_operation {
+	I2CAUX_TRANSACTION_READ,
+	I2CAUX_TRANSACTION_WRITE
+};
+
+enum i2caux_transaction_address_space {
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C = 1,
+	I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD
+};
+
+struct i2caux_transaction_payload {
+	enum i2caux_transaction_address_space address_space;
+	uint32_t address;
+	uint32_t length;
+	uint8_t *data;
+};
+
+enum i2caux_transaction_status {
+	I2CAUX_TRANSACTION_STATUS_UNKNOWN = (-1L),
+	I2CAUX_TRANSACTION_STATUS_SUCCEEDED,
+	I2CAUX_TRANSACTION_STATUS_FAILED_CHANNEL_BUSY,
+	I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT,
+	I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR,
+	I2CAUX_TRANSACTION_STATUS_FAILED_NACK,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INCOMPLETE,
+	I2CAUX_TRANSACTION_STATUS_FAILED_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_INVALID_OPERATION,
+	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW,
+	I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON
+};
+
+struct i2caux_transaction_request {
+	enum i2caux_transaction_operation operation;
+	struct i2caux_transaction_payload payload;
+	enum i2caux_transaction_status status;
+};
+
+enum i2caux_engine_type {
+	I2CAUX_ENGINE_TYPE_UNKNOWN = (-1L),
+	I2CAUX_ENGINE_TYPE_AUX,
+	I2CAUX_ENGINE_TYPE_I2C_DDC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_GENERIC_HW,
+	I2CAUX_ENGINE_TYPE_I2C_SW
+};
+
+enum i2c_default_speed {
+	I2CAUX_DEFAULT_I2C_HW_SPEED = 50,
+	I2CAUX_DEFAULT_I2C_SW_SPEED = 50
 };
-struct engine;
+
+union aux_config;
+
 struct aux_engine {
-	struct engine base;
+	uint32_t inst;
+	struct ddc *ddc;
+	struct dc_context *ctx;
 	const struct aux_engine_funcs *funcs;
 	/* following values are expressed in milliseconds */
 	uint32_t delay;
 	uint32_t max_defer_write_retry;
-
 	bool acquire_reset;
 };
+
 struct read_command_context {
 	uint8_t *buffer;
 	uint32_t current_read_length;
@@ -86,6 +112,7 @@ struct read_command_context {
 	bool transaction_complete;
 	bool operation_succeeded;
 };
+
 struct write_command_context {
 	bool mot;
 
@@ -110,4 +137,44 @@ struct write_command_context {
 	bool transaction_complete;
 	bool operation_succeeded;
 };
+
+
+struct aux_engine_funcs {
+	void (*destroy)(
+		struct aux_engine **ptr);
+	bool (*acquire_engine)(
+		struct aux_engine *engine);
+	void (*configure)(
+		struct aux_engine *engine,
+		union aux_config cfg);
+	void (*submit_channel_request)(
+		struct aux_engine *engine,
+		struct aux_request_transaction_data *request);
+	void (*process_channel_reply)(
+		struct aux_engine *engine,
+		struct aux_reply_transaction_data *reply);
+	int (*read_channel_reply)(
+		struct aux_engine *engine,
+		uint32_t size,
+		uint8_t *buffer,
+		uint8_t *reply_result,
+		uint32_t *sw_status);
+	enum aux_channel_operation_result (*get_channel_status)(
+		struct aux_engine *engine,
+		uint8_t *returned_bytes);
+	bool (*is_engine_available)(struct aux_engine *engine);
+	enum i2caux_engine_type (*get_engine_type)(
+		const struct aux_engine *engine);
+	bool (*acquire)(
+		struct aux_engine *engine,
+		struct ddc *ddc);
+	bool (*submit_request)(
+		struct aux_engine *engine,
+		struct i2caux_transaction_request *request,
+		bool middle_of_transaction);
+	void (*release_engine)(
+		struct aux_engine *engine);
+	void (*destroy_engine)(
+		struct aux_engine **engine);
+};
 #endif
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h b/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h
deleted file mode 100644
index 1f5476f41236..000000000000
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/engine.h
+++ /dev/null
@@ -1,106 +0,0 @@
-/*
- * Copyright 2012-15 Advanced Micro Devices, Inc.
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
- * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
- * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
- * OTHER DEALINGS IN THE SOFTWARE.
- *
- * Authors: AMD
- *
- */
-
-#ifndef __DAL_ENGINE_H__
-#define __DAL_ENGINE_H__
-
-#include "dc_ddc_types.h"
-
-enum i2caux_transaction_operation {
-	I2CAUX_TRANSACTION_READ,
-	I2CAUX_TRANSACTION_WRITE
-};
-
-enum i2caux_transaction_address_space {
-	I2CAUX_TRANSACTION_ADDRESS_SPACE_I2C = 1,
-	I2CAUX_TRANSACTION_ADDRESS_SPACE_DPCD
-};
-
-struct i2caux_transaction_payload {
-	enum i2caux_transaction_address_space address_space;
-	uint32_t address;
-	uint32_t length;
-	uint8_t *data;
-};
-
-enum i2caux_transaction_status {
-	I2CAUX_TRANSACTION_STATUS_UNKNOWN = (-1L),
-	I2CAUX_TRANSACTION_STATUS_SUCCEEDED,
-	I2CAUX_TRANSACTION_STATUS_FAILED_CHANNEL_BUSY,
-	I2CAUX_TRANSACTION_STATUS_FAILED_TIMEOUT,
-	I2CAUX_TRANSACTION_STATUS_FAILED_PROTOCOL_ERROR,
-	I2CAUX_TRANSACTION_STATUS_FAILED_NACK,
-	I2CAUX_TRANSACTION_STATUS_FAILED_INCOMPLETE,
-	I2CAUX_TRANSACTION_STATUS_FAILED_OPERATION,
-	I2CAUX_TRANSACTION_STATUS_FAILED_INVALID_OPERATION,
-	I2CAUX_TRANSACTION_STATUS_FAILED_BUFFER_OVERFLOW,
-	I2CAUX_TRANSACTION_STATUS_FAILED_HPD_DISCON
-};
-
-struct i2caux_transaction_request {
-	enum i2caux_transaction_operation operation;
-	struct i2caux_transaction_payload payload;
-	enum i2caux_transaction_status status;
-};
-
-enum i2caux_engine_type {
-	I2CAUX_ENGINE_TYPE_UNKNOWN = (-1L),
-	I2CAUX_ENGINE_TYPE_AUX,
-	I2CAUX_ENGINE_TYPE_I2C_DDC_HW,
-	I2CAUX_ENGINE_TYPE_I2C_GENERIC_HW,
-	I2CAUX_ENGINE_TYPE_I2C_SW
-};
-
-enum i2c_default_speed {
-	I2CAUX_DEFAULT_I2C_HW_SPEED = 50,
-	I2CAUX_DEFAULT_I2C_SW_SPEED = 50
-};
-
-struct engine;
-
-struct engine_funcs {
-	enum i2caux_engine_type (*get_engine_type)(
-		const struct engine *engine);
-	struct aux_engine* (*acquire)(
-		struct engine *engine,
-		struct ddc *ddc);
-	bool (*submit_request)(
-		struct engine *engine,
-		struct i2caux_transaction_request *request,
-		bool middle_of_transaction);
-	void (*release_engine)(
-		struct engine *engine);
-	void (*destroy_engine)(
-		struct engine **engine);
-};
-
-struct engine {
-	const struct engine_funcs *funcs;
-	uint32_t inst;
-	struct ddc *ddc;
-	struct dc_context *ctx;
-};
-
-#endif
-- 
cgit v1.2.3


From f358b39d187500717b4bc8633cef45d87eff0a3e Mon Sep 17 00:00:00 2001
From: "Jerry (Fangzhi) Zuo" <Jerry.Zuo@amd.com>
Date: Tue, 17 Jul 2018 11:53:54 -0400
Subject: drm/amd/display: Fix Vega10 black screen after mode change

[Why]
The sequence is slightly changed when bring .set_bandwidth out
from the end of programming backend to the end of programming
surface. Vega10 doesn't like to get clocks updated if
stream_count is zero in the current context (Atomic Reset).

[How]
Do not update clocks if no stream is showing up in the context.

Fixes 1b2b130192 "dc: Remove 300Mhz minimum disp clk limit."

Signed-off-by: Jerry (Fangzhi) Zuo <Jerry.Zuo@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c |  2 +-
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h |  5 +++++
 drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c | 10 ++++++++++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 33a14e163f88..1149c413f6d2 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2552,7 +2552,7 @@ static void pplib_apply_display_requirements(
 	dc->prev_display_config = *pp_display_cfg;
 }
 
-static void dce110_set_bandwidth(
+void dce110_set_bandwidth(
 		struct dc *dc,
 		struct dc_state *context,
 		bool decrease_allowed)
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
index d6db3dbd9015..e4c5db75c4c6 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.h
@@ -68,6 +68,11 @@ void dce110_fill_display_configs(
 	const struct dc_state *context,
 	struct dm_pp_display_configuration *pp_display_cfg);
 
+void dce110_set_bandwidth(
+		struct dc *dc,
+		struct dc_state *context,
+		bool decrease_allowed);
+
 uint32_t dce110_get_min_vblank_time_us(const struct dc_state *context);
 
 void dp_receiver_power_ctrl(struct dc_link *link, bool on);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
index e96ff86d2fc3..5853522a6182 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_hw_sequencer.c
@@ -244,7 +244,16 @@ static void dce120_update_dchub(
 	dh_data->dchub_info_valid = false;
 }
 
+static void dce120_set_bandwidth(
+		struct dc *dc,
+		struct dc_state *context,
+		bool decrease_allowed)
+{
+	if (context->stream_count <= 0)
+		return;
 
+	dce110_set_bandwidth(dc, context, decrease_allowed);
+}
 
 void dce120_hw_sequencer_construct(struct dc *dc)
 {
@@ -254,5 +263,6 @@ void dce120_hw_sequencer_construct(struct dc *dc)
 	dce110_hw_sequencer_construct(dc);
 	dc->hwss.enable_display_power_gating = dce120_enable_display_power_gating;
 	dc->hwss.update_dchub = dce120_update_dchub;
+	dc->hwss.set_bandwidth = dce120_set_bandwidth;
 }
 
-- 
cgit v1.2.3


From 9907704174e0ad4ed02766fac4049971e583323d Mon Sep 17 00:00:00 2001
From: Anthony Koo <Anthony.Koo@amd.com>
Date: Tue, 17 Jul 2018 09:43:44 -0400
Subject: drm/amd/display: Prevent PSR from being enabled if initialization
 fails

[Why]
PSR_SET command is sent to the microcontroller in order to initialize
parameters needed for PSR feature, such as telling the microcontroller
which pipe is driving the PSR supported panel. When this command is
skipped or fails, the microcontroller may program the wrong thing if
driver tries to enable PSR.

[How]
If PSR_SET fails, do not set psr_enable flag to indicate the feature is
not yet initialized.

Signed-off-by: Anthony Koo <Anthony.Koo@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c | 38 ++++++++++++++++-----------
 drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h  |  2 +-
 2 files changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
index 062a46543887..ca7989e4932b 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_dmcu.c
@@ -150,7 +150,7 @@ static void dce_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait)
 	}
 }
 
-static void dce_dmcu_setup_psr(struct dmcu *dmcu,
+static bool dce_dmcu_setup_psr(struct dmcu *dmcu,
 		struct dc_link *link,
 		struct psr_context *psr_context)
 {
@@ -261,6 +261,8 @@ static void dce_dmcu_setup_psr(struct dmcu *dmcu,
 
 	/* notifyDMCUMsg */
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
+
+	return true;
 }
 
 static bool dce_is_dmcu_initialized(struct dmcu *dmcu)
@@ -545,24 +547,25 @@ static void dcn10_dmcu_set_psr_enable(struct dmcu *dmcu, bool enable, bool wait)
 	 *  least a few frames. Should never hit the max retry assert below.
 	 */
 	if (wait == true) {
-	for (retryCount = 0; retryCount <= 1000; retryCount++) {
-		dcn10_get_dmcu_psr_state(dmcu, &psr_state);
-		if (enable) {
-			if (psr_state != 0)
-				break;
-		} else {
-			if (psr_state == 0)
-				break;
+		for (retryCount = 0; retryCount <= 1000; retryCount++) {
+			dcn10_get_dmcu_psr_state(dmcu, &psr_state);
+			if (enable) {
+				if (psr_state != 0)
+					break;
+			} else {
+				if (psr_state == 0)
+					break;
+			}
+			udelay(500);
 		}
-		udelay(500);
-	}
 
-	/* assert if max retry hit */
-	ASSERT(retryCount <= 1000);
+		/* assert if max retry hit */
+		if (retryCount >= 1000)
+			ASSERT(0);
 	}
 }
 
-static void dcn10_dmcu_setup_psr(struct dmcu *dmcu,
+static bool dcn10_dmcu_setup_psr(struct dmcu *dmcu,
 		struct dc_link *link,
 		struct psr_context *psr_context)
 {
@@ -577,7 +580,7 @@ static void dcn10_dmcu_setup_psr(struct dmcu *dmcu,
 
 	/* If microcontroller is not running, do nothing */
 	if (dmcu->dmcu_state != DMCU_RUNNING)
-		return;
+		return false;
 
 	link->link_enc->funcs->psr_program_dp_dphy_fast_training(link->link_enc,
 			psr_context->psrExitLinkTrainingRequired);
@@ -677,6 +680,11 @@ static void dcn10_dmcu_setup_psr(struct dmcu *dmcu,
 
 	/* notifyDMCUMsg */
 	REG_UPDATE(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 1);
+
+	/* waitDMCUReadyForCmd */
+	REG_WAIT(MASTER_COMM_CNTL_REG, MASTER_COMM_INTERRUPT, 0, 1, 10000);
+
+	return true;
 }
 
 static void dcn10_psr_wait_loop(
diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
index de60f940030d..4550747fb61c 100644
--- a/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
+++ b/drivers/gpu/drm/amd/display/dc/inc/hw/dmcu.h
@@ -48,7 +48,7 @@ struct dmcu_funcs {
 			const char *src,
 			unsigned int bytes);
 	void (*set_psr_enable)(struct dmcu *dmcu, bool enable, bool wait);
-	void (*setup_psr)(struct dmcu *dmcu,
+	bool (*setup_psr)(struct dmcu *dmcu,
 			struct dc_link *link,
 			struct psr_context *psr_context);
 	void (*get_psr_state)(struct dmcu *dmcu, uint32_t *psr_state);
-- 
cgit v1.2.3


From 116f451c90a94de6203757c117278b99a837d3b5 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Mon, 9 Jul 2018 17:26:34 -0400
Subject: drm/amd/display: DC 3.1.59

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Aric Cyr <Aric.Cyr@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 7515c0dcbdd2..c2d390fba0bf 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -38,7 +38,7 @@
 #include "inc/compressor.h"
 #include "dml/display_mode_lib.h"
 
-#define DC_VER "3.1.58"
+#define DC_VER "3.1.59"
 
 #define MAX_SURFACES 3
 #define MAX_STREAMS 6
-- 
cgit v1.2.3


From d04cc604a66b07eff8fce824fb6c0fdc0875d2e3 Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Wed, 25 Jul 2018 09:45:47 -0400
Subject: drm/amd: Add missing fields in atom_integrated_system_info_v1_11

This structure needs to align with structure in atomfirmware table.
Update it.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Dmytro Laktyushkin <dmytro.laktyushkin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/include/atomfirmware.h | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
index 33b4de4ad66e..4bc118df3bc4 100644
--- a/drivers/gpu/drm/amd/include/atomfirmware.h
+++ b/drivers/gpu/drm/amd/include/atomfirmware.h
@@ -1074,7 +1074,7 @@ struct atom_integrated_system_info_v1_11
   uint16_t  dpphy_override;                   // bit vector, enum of atom_sysinfo_dpphy_override_def
   uint16_t  lvds_misc;                        // enum of atom_sys_info_lvds_misc_def
   uint16_t  backlight_pwm_hz;                 // pwm frequency in hz
-  uint8_t   memorytype;                       // enum of atom_sys_mem_type
+  uint8_t   memorytype;                       // enum of atom_dmi_t17_mem_type_def, APU memory type indication.
   uint8_t   umachannelnumber;                 // number of memory channels
   uint8_t   pwr_on_digon_to_de;               /* all pwr sequence numbers below are in uint of 4ms */
   uint8_t   pwr_on_de_to_vary_bl;
@@ -1084,18 +1084,25 @@ struct atom_integrated_system_info_v1_11
   uint8_t   pwr_on_vary_bl_to_blon;
   uint8_t   pwr_down_bloff_to_vary_bloff;
   uint8_t   min_allowed_bl_level;
+  uint8_t   htc_hyst_limit;
+  uint8_t   htc_tmp_limit;
+  uint8_t   reserved1;
+  uint8_t   reserved2;
   struct atom_external_display_connection_info extdispconninfo;
   struct atom_14nm_dpphy_dvihdmi_tuningset dvi_tuningset;
   struct atom_14nm_dpphy_dvihdmi_tuningset hdmi_tuningset;
   struct atom_14nm_dpphy_dvihdmi_tuningset hdmi6g_tuningset;
-  struct atom_14nm_dpphy_dp_tuningset dp_tuningset;
-  struct atom_14nm_dpphy_dp_tuningset dp_hbr3_tuningset;
+  struct atom_14nm_dpphy_dp_tuningset dp_tuningset;        // rbr 1.62G dp tuning set
+  struct atom_14nm_dpphy_dp_tuningset dp_hbr3_tuningset;   // HBR3 dp tuning set
   struct atom_camera_data  camera_info;
   struct atom_hdmi_retimer_redriver_set dp0_retimer_set;   //for DP0
   struct atom_hdmi_retimer_redriver_set dp1_retimer_set;   //for DP1
   struct atom_hdmi_retimer_redriver_set dp2_retimer_set;   //for DP2
   struct atom_hdmi_retimer_redriver_set dp3_retimer_set;   //for DP3
-  uint32_t  reserved[108];
+  struct atom_14nm_dpphy_dp_tuningset dp_hbr_tuningset;    //hbr 2.7G dp tuning set
+  struct atom_14nm_dpphy_dp_tuningset dp_hbr2_tuningset;   //hbr2 5.4G dp turnig set
+  struct atom_14nm_dpphy_dp_tuningset edp_tuningset;       //edp tuning set
+  uint32_t  reserved[66];
 };
 
 
-- 
cgit v1.2.3


From f1e582ebfd703ea01dc4caf4d339b7c84ec3ff29 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Wed, 25 Jul 2018 15:11:34 -0500
Subject: drm/amdgpu: implement harvesting support for UVD 7.2 (v3)

Properly handle cases where one or more instance of the IP
block may be harvested.

v2: make sure ip_num_rings is initialized amdgpu_queue_mgr.c
v3: rebase on Christian's UVD changes, drop unused var

Reviewed-by: James Zhu <James.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c       | 17 +++++---
 drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c | 13 +++++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c       | 11 +++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h       |  4 ++
 drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c         | 56 +++++++++++++++++++++++++--
 5 files changed, 89 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index c7dce14fd47d..dd2132fa2b89 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -286,7 +286,7 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 	struct drm_crtc *crtc;
 	uint32_t ui32 = 0;
 	uint64_t ui64 = 0;
-	int i, found;
+	int i, j, found;
 	int ui32_size = sizeof(ui32);
 
 	if (!info->return_size || !info->return_pointer)
@@ -348,7 +348,11 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_UVD:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			ring_mask |= adev->uvd.inst[0].ring.ready;
+			for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+				if (adev->uvd.harvest_config & (1 << i))
+					continue;
+				ring_mask |= adev->uvd.inst[i].ring.ready;
+			}
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
@@ -361,9 +365,12 @@ static int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file
 			break;
 		case AMDGPU_HW_IP_UVD_ENC:
 			type = AMD_IP_BLOCK_TYPE_UVD;
-			for (i = 0; i < adev->uvd.num_enc_rings; i++)
-				ring_mask |=
-					adev->uvd.inst[0].ring_enc[i].ready << i;
+			for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+				if (adev->uvd.harvest_config & (1 << i))
+					continue;
+				for (j = 0; j < adev->uvd.num_enc_rings; j++)
+					ring_mask |= adev->uvd.inst[i].ring_enc[j].ready << j;
+			}
 			ib_start_alignment = 64;
 			ib_size_alignment = 64;
 			break;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
index d8357290ad09..a172bba32b45 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_queue_mgr.c
@@ -214,7 +214,7 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 			 u32 hw_ip, u32 instance, u32 ring,
 			 struct amdgpu_ring **out_ring)
 {
-	int r, ip_num_rings;
+	int i, r, ip_num_rings = 0;
 	struct amdgpu_queue_mapper *mapper = &mgr->mapper[hw_ip];
 
 	if (!adev || !mgr || !out_ring)
@@ -243,14 +243,21 @@ int amdgpu_queue_mgr_map(struct amdgpu_device *adev,
 		ip_num_rings = adev->sdma.num_instances;
 		break;
 	case AMDGPU_HW_IP_UVD:
-		ip_num_rings = adev->uvd.num_uvd_inst;
+		for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+			if (!(adev->uvd.harvest_config & (1 << i)))
+				ip_num_rings++;
+		}
 		break;
 	case AMDGPU_HW_IP_VCE:
 		ip_num_rings = adev->vce.num_rings;
 		break;
 	case AMDGPU_HW_IP_UVD_ENC:
+		for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+			if (!(adev->uvd.harvest_config & (1 << i)))
+				ip_num_rings++;
+		}
 		ip_num_rings =
-			adev->uvd.num_enc_rings * adev->uvd.num_uvd_inst;
+			adev->uvd.num_enc_rings * ip_num_rings;
 		break;
 	case AMDGPU_HW_IP_VCN_DEC:
 		ip_num_rings = 1;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
index fca86d71fafc..632fa5980ff4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -255,7 +255,8 @@ int amdgpu_uvd_sw_init(struct amdgpu_device *adev)
 		bo_size += AMDGPU_GPU_PAGE_ALIGN(le32_to_cpu(hdr->ucode_size_bytes) + 8);
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
-
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		r = amdgpu_bo_create_kernel(adev, bo_size, PAGE_SIZE,
 					    AMDGPU_GEM_DOMAIN_VRAM, &adev->uvd.inst[j].vcpu_bo,
 					    &adev->uvd.inst[j].gpu_addr, &adev->uvd.inst[j].cpu_addr);
@@ -308,6 +309,8 @@ int amdgpu_uvd_sw_fini(struct amdgpu_device *adev)
 	drm_sched_entity_destroy(&adev->uvd.entity);
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		kfree(adev->uvd.inst[j].saved_bo);
 
 		amdgpu_bo_free_kernel(&adev->uvd.inst[j].vcpu_bo,
@@ -343,6 +346,8 @@ int amdgpu_uvd_suspend(struct amdgpu_device *adev)
 	}
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		if (adev->uvd.inst[j].vcpu_bo == NULL)
 			continue;
 
@@ -365,6 +370,8 @@ int amdgpu_uvd_resume(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		if (adev->uvd.inst[i].vcpu_bo == NULL)
 			return -EINVAL;
 
@@ -1159,6 +1166,8 @@ static void amdgpu_uvd_idle_work_handler(struct work_struct *work)
 	unsigned fences = 0, i, j;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		fences += amdgpu_fence_count_emitted(&adev->uvd.inst[i].ring);
 		for (j = 0; j < adev->uvd.num_enc_rings; ++j) {
 			fences += amdgpu_fence_count_emitted(&adev->uvd.inst[i].ring_enc[j]);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
index 66872286ab12..33c5f806f925 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.h
@@ -48,6 +48,9 @@ struct amdgpu_uvd_inst {
 	uint32_t                srbm_soft_reset;
 };
 
+#define AMDGPU_UVD_HARVEST_UVD0 (1 << 0)
+#define AMDGPU_UVD_HARVEST_UVD1 (1 << 1)
+
 struct amdgpu_uvd {
 	const struct firmware	*fw;	/* UVD firmware */
 	unsigned		fw_version;
@@ -61,6 +64,7 @@ struct amdgpu_uvd {
 	atomic_t		handles[AMDGPU_MAX_UVD_HANDLES];
 	struct drm_sched_entity entity;
 	struct delayed_work	idle_work;
+	unsigned		harvest_config;
 };
 
 int amdgpu_uvd_sw_init(struct amdgpu_device *adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
index d74c1b242667..5fab3560a71d 100644
--- a/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/uvd_v7_0.c
@@ -41,6 +41,12 @@
 #include "mmhub/mmhub_1_0_sh_mask.h"
 #include "ivsrcid/uvd/irqsrcs_uvd_7_0.h"
 
+#define mmUVD_PG0_CC_UVD_HARVESTING                                                                    0x00c7
+#define mmUVD_PG0_CC_UVD_HARVESTING_BASE_IDX                                                           1
+//UVD_PG0_CC_UVD_HARVESTING
+#define UVD_PG0_CC_UVD_HARVESTING__UVD_DISABLE__SHIFT                                                         0x1
+#define UVD_PG0_CC_UVD_HARVESTING__UVD_DISABLE_MASK                                                           0x00000002L
+
 #define UVD7_MAX_HW_INSTANCES_VEGA20			2
 
 static void uvd_v7_0_set_ring_funcs(struct amdgpu_device *adev);
@@ -370,10 +376,25 @@ error:
 static int uvd_v7_0_early_init(void *handle)
 {
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
-	if (adev->asic_type == CHIP_VEGA20)
+
+	if (adev->asic_type == CHIP_VEGA20) {
+		u32 harvest;
+		int i;
+
 		adev->uvd.num_uvd_inst = UVD7_MAX_HW_INSTANCES_VEGA20;
-	else
+		for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+			harvest = RREG32_SOC15(UVD, i, mmUVD_PG0_CC_UVD_HARVESTING);
+			if (harvest & UVD_PG0_CC_UVD_HARVESTING__UVD_DISABLE_MASK) {
+				adev->uvd.harvest_config |= 1 << i;
+			}
+		}
+		if (adev->uvd.harvest_config == (AMDGPU_UVD_HARVEST_UVD0 |
+						 AMDGPU_UVD_HARVEST_UVD1))
+			/* both instances are harvested, disable the block */
+			return -ENOENT;
+	} else {
 		adev->uvd.num_uvd_inst = 1;
+	}
 
 	if (amdgpu_sriov_vf(adev))
 		adev->uvd.num_enc_rings = 1;
@@ -393,6 +414,8 @@ static int uvd_v7_0_sw_init(void *handle)
 	struct amdgpu_device *adev = (struct amdgpu_device *)handle;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		/* UVD TRAP */
 		r = amdgpu_irq_add_id(adev, amdgpu_ih_clientid_uvds[j], UVD_7_0__SRCID__UVD_SYSTEM_MESSAGE_INTERRUPT, &adev->uvd.inst[j].irq);
 		if (r)
@@ -425,6 +448,8 @@ static int uvd_v7_0_sw_init(void *handle)
 		return r;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		if (!amdgpu_sriov_vf(adev)) {
 			ring = &adev->uvd.inst[j].ring;
 			sprintf(ring->name, "uvd<%d>", j);
@@ -472,6 +497,8 @@ static int uvd_v7_0_sw_fini(void *handle)
 		return r;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i)
 			amdgpu_ring_fini(&adev->uvd.inst[j].ring_enc[i]);
 	}
@@ -500,6 +527,8 @@ static int uvd_v7_0_hw_init(void *handle)
 		goto done;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; ++j) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		ring = &adev->uvd.inst[j].ring;
 
 		if (!amdgpu_sriov_vf(adev)) {
@@ -579,8 +608,11 @@ static int uvd_v7_0_hw_fini(void *handle)
 		DRM_DEBUG("For SRIOV client, shouldn't do anything.\n");
 	}
 
-	for (i = 0; i < adev->uvd.num_uvd_inst; ++i)
+	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		adev->uvd.inst[i].ring.ready = false;
+	}
 
 	return 0;
 }
@@ -623,6 +655,8 @@ static void uvd_v7_0_mc_resume(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		if (adev->firmware.load_type == AMDGPU_FW_LOAD_PSP) {
 			WREG32_SOC15(UVD, i, mmUVD_LMI_VCPU_CACHE_64BIT_BAR_LOW,
 				lower_32_bits(adev->firmware.ucode[AMDGPU_UCODE_ID_UVD].mc_addr));
@@ -695,6 +729,8 @@ static int uvd_v7_0_mmsch_start(struct amdgpu_device *adev,
 	WREG32_SOC15(VCE, 0, mmVCE_MMSCH_VF_MAILBOX_RESP, 0);
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		WDOORBELL32(adev->uvd.inst[i].ring_enc[0].doorbell_index, 0);
 		adev->wb.wb[adev->uvd.inst[i].ring_enc[0].wptr_offs] = 0;
 		adev->uvd.inst[i].ring_enc[0].wptr = 0;
@@ -751,6 +787,8 @@ static int uvd_v7_0_sriov_start(struct amdgpu_device *adev)
 		init_table += header->uvd_table_offset;
 
 		for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+			if (adev->uvd.harvest_config & (1 << i))
+				continue;
 			ring = &adev->uvd.inst[i].ring;
 			ring->wptr = 0;
 			size = AMDGPU_GPU_PAGE_ALIGN(adev->uvd.fw->size + 4);
@@ -890,6 +928,8 @@ static int uvd_v7_0_start(struct amdgpu_device *adev)
 	int i, j, k, r;
 
 	for (k = 0; k < adev->uvd.num_uvd_inst; ++k) {
+		if (adev->uvd.harvest_config & (1 << k))
+			continue;
 		/* disable DPG */
 		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_POWER_STATUS), 0,
 				~UVD_POWER_STATUS__UVD_PG_MODE_MASK);
@@ -902,6 +942,8 @@ static int uvd_v7_0_start(struct amdgpu_device *adev)
 	uvd_v7_0_mc_resume(adev);
 
 	for (k = 0; k < adev->uvd.num_uvd_inst; ++k) {
+		if (adev->uvd.harvest_config & (1 << k))
+			continue;
 		ring = &adev->uvd.inst[k].ring;
 		/* disable clock gating */
 		WREG32_P(SOC15_REG_OFFSET(UVD, k, mmUVD_CGC_CTRL), 0,
@@ -1069,6 +1111,8 @@ static void uvd_v7_0_stop(struct amdgpu_device *adev)
 	uint8_t i = 0;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; ++i) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		/* force RBC into idle state */
 		WREG32_SOC15(UVD, i, mmUVD_RBC_RB_CNTL, 0x11010101);
 
@@ -1785,6 +1829,8 @@ static void uvd_v7_0_set_ring_funcs(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		adev->uvd.inst[i].ring.funcs = &uvd_v7_0_ring_vm_funcs;
 		adev->uvd.inst[i].ring.me = i;
 		DRM_INFO("UVD(%d) is enabled in VM mode\n", i);
@@ -1796,6 +1842,8 @@ static void uvd_v7_0_set_enc_ring_funcs(struct amdgpu_device *adev)
 	int i, j;
 
 	for (j = 0; j < adev->uvd.num_uvd_inst; j++) {
+		if (adev->uvd.harvest_config & (1 << j))
+			continue;
 		for (i = 0; i < adev->uvd.num_enc_rings; ++i) {
 			adev->uvd.inst[j].ring_enc[i].funcs = &uvd_v7_0_enc_ring_vm_funcs;
 			adev->uvd.inst[j].ring_enc[i].me = j;
@@ -1815,6 +1863,8 @@ static void uvd_v7_0_set_irq_funcs(struct amdgpu_device *adev)
 	int i;
 
 	for (i = 0; i < adev->uvd.num_uvd_inst; i++) {
+		if (adev->uvd.harvest_config & (1 << i))
+			continue;
 		adev->uvd.inst[i].irq.num_types = adev->uvd.num_enc_rings + 1;
 		adev->uvd.inst[i].irq.funcs = &uvd_v7_0_irq_funcs;
 	}
-- 
cgit v1.2.3


From dc30b96ab6d569060741572cf30517d3179429a8 Mon Sep 17 00:00:00 2001
From: Markus Stockhausen <stockhausen@collogia.de>
Date: Fri, 27 Jul 2018 09:09:53 -0600
Subject: readahead: stricter check for bdi io_pages

ondemand_readahead() checks bdi->io_pages to cap the maximum pages
that need to be processed. This works until the readit section. If
we would do an async only readahead (async size = sync size) and
target is at beginning of window we expand the pages by another
get_next_ra_size() pages. Btrace for large reads shows that kernel
always issues a doubled size read at the beginning of processing.
Add an additional check for io_pages in the lower part of the func.
The fix helps devices that hard limit bio pages and rely on proper
handling of max_hw_read_sectors (e.g. older FusionIO cards). For
that reason it could qualify for stable.

Fixes: 9491ae4a ("mm: don't cap request size based on read-ahead setting")
Cc: stable@vger.kernel.org
Signed-off-by: Markus Stockhausen stockhausen@collogia.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 mm/readahead.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/mm/readahead.c b/mm/readahead.c
index 9f62b7151100..a59ea70527b9 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -386,6 +386,7 @@ ondemand_readahead(struct address_space *mapping,
 {
 	struct backing_dev_info *bdi = inode_to_bdi(mapping->host);
 	unsigned long max_pages = ra->ra_pages;
+	unsigned long add_pages;
 	pgoff_t prev_offset;
 
 	/*
@@ -475,10 +476,17 @@ readit:
 	 * Will this read hit the readahead marker made by itself?
 	 * If so, trigger the readahead marker hit now, and merge
 	 * the resulted next readahead window into the current one.
+	 * Take care of maximum IO pages as above.
 	 */
 	if (offset == ra->start && ra->size == ra->async_size) {
-		ra->async_size = get_next_ra_size(ra, max_pages);
-		ra->size += ra->async_size;
+		add_pages = get_next_ra_size(ra, max_pages);
+		if (ra->size + add_pages <= max_pages) {
+			ra->async_size = add_pages;
+			ra->size += add_pages;
+		} else {
+			ra->size = max_pages;
+			ra->async_size = max_pages >> 1;
+		}
 	}
 
 	return ra_submit(ra, mapping, filp);
-- 
cgit v1.2.3


From 99a27d59bd7b2ce1a82a4e826e8e7881f4d4954d Mon Sep 17 00:00:00 2001
From: Tang Junhui <tang.junhui@zte.com.cn>
Date: Thu, 26 Jul 2018 12:17:33 +0800
Subject: bcache: simplify the calculation of the total amount of flash dirty
 data

Currently we calculate the total amount of flash only devices dirty data
by adding the dirty data of each flash only device under registering
locker. It is very inefficient.

In this patch, we add a member flash_dev_dirty_sectors in struct cache_set
to record the total amount of flash only devices dirty data in real time,
so we didn't need to calculate the total amount of dirty data any more.

Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bcache.h    |  1 +
 drivers/md/bcache/super.c     |  2 ++
 drivers/md/bcache/writeback.c |  5 ++++-
 drivers/md/bcache/writeback.h | 19 -------------------
 4 files changed, 7 insertions(+), 20 deletions(-)

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index d6bf294f3907..3226d38bf859 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -525,6 +525,7 @@ struct cache_set {
 	unsigned		devices_max_used;
 	struct list_head	cached_devs;
 	uint64_t		cached_dev_sectors;
+	atomic_long_t		flash_dev_dirty_sectors;
 	struct closure		caching;
 
 	struct closure		sb_write;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index fa4058e43202..cea2a42ea276 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1311,6 +1311,8 @@ static void flash_dev_free(struct closure *cl)
 {
 	struct bcache_device *d = container_of(cl, struct bcache_device, cl);
 	mutex_lock(&bch_register_lock);
+	atomic_long_sub(bcache_dev_sectors_dirty(d),
+			&d->c->flash_dev_dirty_sectors);
 	bcache_device_free(d);
 	mutex_unlock(&bch_register_lock);
 	kobject_put(&d->kobj);
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index ad45ebe1a74b..0d2a05074a81 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -27,7 +27,7 @@ static uint64_t __calc_target_rate(struct cached_dev *dc)
 	 * flash-only devices
 	 */
 	uint64_t cache_sectors = c->nbuckets * c->sb.bucket_size -
-				bcache_flash_devs_sectors_dirty(c);
+				atomic_long_read(&c->flash_dev_dirty_sectors);
 
 	/*
 	 * Unfortunately there is no control of global dirty data.  If the
@@ -476,6 +476,9 @@ void bcache_dev_sectors_dirty_add(struct cache_set *c, unsigned inode,
 	if (!d)
 		return;
 
+	if (UUID_FLASH_ONLY(&c->uuids[inode]))
+		atomic_long_add(nr_sectors, &c->flash_dev_dirty_sectors);
+
 	stripe = offset_to_stripe(d, offset);
 	stripe_offset = offset & (d->stripe_size - 1);
 
diff --git a/drivers/md/bcache/writeback.h b/drivers/md/bcache/writeback.h
index 610fb01de629..3745d7004c47 100644
--- a/drivers/md/bcache/writeback.h
+++ b/drivers/md/bcache/writeback.h
@@ -28,25 +28,6 @@ static inline uint64_t bcache_dev_sectors_dirty(struct bcache_device *d)
 	return ret;
 }
 
-static inline uint64_t  bcache_flash_devs_sectors_dirty(struct cache_set *c)
-{
-	uint64_t i, ret = 0;
-
-	mutex_lock(&bch_register_lock);
-
-	for (i = 0; i < c->devices_max_used; i++) {
-		struct bcache_device *d = c->devices[i];
-
-		if (!d || !UUID_FLASH_ONLY(&c->uuids[i]))
-			continue;
-		ret += bcache_dev_sectors_dirty(d);
-	}
-
-	mutex_unlock(&bch_register_lock);
-
-	return ret;
-}
-
 static inline unsigned offset_to_stripe(struct bcache_device *d,
 					uint64_t offset)
 {
-- 
cgit v1.2.3


From 5c25c4fc74af40657606dd01df27cc5eb9efb26c Mon Sep 17 00:00:00 2001
From: Tang Junhui <tang.junhui@zte.com.cn>
Date: Thu, 26 Jul 2018 12:17:34 +0800
Subject: bcache: finish incremental GC

In GC thread, we record the latest GC key in gc_done, which is expected
to be used for incremental GC, but in currently code, we didn't realize
it. When GC runs, front side IO would be blocked until the GC over, it
would be a long time if there is a lot of btree nodes.

This patch realizes incremental GC, the main ideal is that, when there
are front side I/Os, after GC some nodes (100), we stop GC, release locker
of the btree node, and go to process the front side I/Os for some times
(100 ms), then go back to GC again.

By this patch, when we doing GC, I/Os are not blocked all the time, and
there is no obvious I/Os zero jump problem any more.

Patch v2: Rename some variables and macros name as Coly suggested.

Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bcache.h  |  5 +++++
 drivers/md/bcache/btree.c   | 14 +++++++++++++-
 drivers/md/bcache/request.c |  3 +++
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 3226d38bf859..872ef4d67711 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -474,6 +474,7 @@ struct cache {
 
 struct gc_stat {
 	size_t			nodes;
+	size_t			nodes_pre;
 	size_t			key_bytes;
 
 	size_t			nkeys;
@@ -603,6 +604,10 @@ struct cache_set {
 	 * rescale; when it hits 0 we rescale all the bucket priorities.
 	 */
 	atomic_t		rescale;
+	/*
+	 * used for GC, identify if any front side I/Os is inflight
+	 */
+	atomic_t		search_inflight;
 	/*
 	 * When we invalidate buckets, we use both the priority and the amount
 	 * of good data to determine which buckets to reuse first - to weight
diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 547c9eedc2f4..b4407ba12667 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -90,6 +90,8 @@
 
 #define MAX_NEED_GC		64
 #define MAX_SAVE_PRIO		72
+#define MIN_GC_NODES		100
+#define GC_SLEEP_MS		100
 
 #define PTR_DIRTY_BIT		(((uint64_t) 1 << 36))
 
@@ -1585,6 +1587,13 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		memmove(r + 1, r, sizeof(r[0]) * (GC_MERGE_NODES - 1));
 		r->b = NULL;
 
+		if (atomic_read(&b->c->search_inflight) &&
+		    gc->nodes >= gc->nodes_pre + MIN_GC_NODES) {
+			gc->nodes_pre =  gc->nodes;
+			ret = -EAGAIN;
+			break;
+		}
+
 		if (need_resched()) {
 			ret = -EAGAIN;
 			break;
@@ -1753,7 +1762,10 @@ static void bch_btree_gc(struct cache_set *c)
 		closure_sync(&writes);
 		cond_resched();
 
-		if (ret && ret != -EAGAIN)
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(msecs_to_jiffies
+						       (GC_SLEEP_MS));
+		else if (ret)
 			pr_warn("gc failed!");
 	} while (ret && !test_bit(CACHE_SET_IO_DISABLE, &c->flags));
 
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 97707b0c54ce..43af905920f5 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -701,6 +701,8 @@ static void search_free(struct closure *cl)
 {
 	struct search *s = container_of(cl, struct search, cl);
 
+	atomic_dec(&s->d->c->search_inflight);
+
 	if (s->iop.bio)
 		bio_put(s->iop.bio);
 
@@ -718,6 +720,7 @@ static inline struct search *search_alloc(struct bio *bio,
 
 	closure_init(&s->cl, NULL);
 	do_bio_hook(s, bio, request_endio);
+	atomic_inc(&d->c->search_inflight);
 
 	s->orig_bio		= bio;
 	s->cache_miss		= NULL;
-- 
cgit v1.2.3


From 7f4a59de28137aae4316a58f501b599ac3b87395 Mon Sep 17 00:00:00 2001
From: Tang Junhui <tang.junhui@zte.com.cn>
Date: Thu, 26 Jul 2018 12:17:35 +0800
Subject: bcache: calculate the number of incremental GC nodes according to the
 total of btree nodes

This patch base on "[PATCH] bcache: finish incremental GC".

Since incremental GC would stop 100ms when front side I/O comes, so when
there are many btree nodes, if GC only processes constant (100) nodes each
time, GC would last a long time, and the front I/Os would run out of the
buckets (since no new bucket can be allocated during GC), and I/Os be
blocked again.

So GC should not process constant nodes, but varied nodes according to the
number of btree nodes. In this patch, GC is divided into constant (100)
times, so when there are many btree nodes, GC can process more nodes each
time, otherwise GC will process less nodes each time (but no less than
MIN_GC_NODES).

Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/btree.c | 37 +++++++++++++++++++++++++++++++++++--
 1 file changed, 35 insertions(+), 2 deletions(-)

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index b4407ba12667..475008fbbaab 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -90,6 +90,7 @@
 
 #define MAX_NEED_GC		64
 #define MAX_SAVE_PRIO		72
+#define MAX_GC_TIMES		100
 #define MIN_GC_NODES		100
 #define GC_SLEEP_MS		100
 
@@ -1522,6 +1523,32 @@ static unsigned btree_gc_count_keys(struct btree *b)
 	return ret;
 }
 
+static size_t btree_gc_min_nodes(struct cache_set *c)
+{
+	size_t min_nodes;
+
+	/*
+	 * Since incremental GC would stop 100ms when front
+	 * side I/O comes, so when there are many btree nodes,
+	 * if GC only processes constant (100) nodes each time,
+	 * GC would last a long time, and the front side I/Os
+	 * would run out of the buckets (since no new bucket
+	 * can be allocated during GC), and be blocked again.
+	 * So GC should not process constant nodes, but varied
+	 * nodes according to the number of btree nodes, which
+	 * realized by dividing GC into constant(100) times,
+	 * so when there are many btree nodes, GC can process
+	 * more nodes each time, otherwise, GC will process less
+	 * nodes each time (but no less than MIN_GC_NODES)
+	 */
+	min_nodes = c->gc_stats.nodes / MAX_GC_TIMES;
+	if (min_nodes < MIN_GC_NODES)
+		min_nodes = MIN_GC_NODES;
+
+	return min_nodes;
+}
+
+
 static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 			    struct closure *writes, struct gc_stat *gc)
 {
@@ -1588,7 +1615,7 @@ static int btree_gc_recurse(struct btree *b, struct btree_op *op,
 		r->b = NULL;
 
 		if (atomic_read(&b->c->search_inflight) &&
-		    gc->nodes >= gc->nodes_pre + MIN_GC_NODES) {
+		    gc->nodes >= gc->nodes_pre + btree_gc_min_nodes(b->c)) {
 			gc->nodes_pre =  gc->nodes;
 			ret = -EAGAIN;
 			break;
@@ -1846,8 +1873,14 @@ static int bch_btree_check_recurse(struct btree *b, struct btree_op *op)
 		do {
 			k = bch_btree_iter_next_filter(&iter, &b->keys,
 						       bch_ptr_bad);
-			if (k)
+			if (k) {
 				btree_node_prefetch(b, k);
+				/*
+				 * initiallize c->gc_stats.nodes
+				 * for incremental GC
+				 */
+				b->c->gc_stats.nodes++;
+			}
 
 			if (p)
 				ret = btree(check_recurse, p, b, op);
-- 
cgit v1.2.3


From 94f71c16062e86069fb87dfa9b6683e2f1c21232 Mon Sep 17 00:00:00 2001
From: Tang Junhui <tang.junhui@zte.com.cn>
Date: Thu, 26 Jul 2018 12:17:36 +0800
Subject: bcache: fix I/O significant decline while backend devices registering

I attached several backend devices in the same cache set, and produced lots
of dirty data by running small rand I/O writes in a long time, then I
continue run I/O in the others cached devices, and stopped a cached device,
after a mean while, I register the stopped device again, I see the running
I/O in the others cached devices dropped significantly, sometimes even
jumps to zero.

In currently code, bcache would traverse each keys and btree node to count
the dirty data under read locker, and the writes threads can not get the
btree write locker, and when there is a lot of keys and btree node in the
registering device, it would last several seconds, so the write I/Os in
others cached device are blocked and declined significantly.

In this patch, when a device registering to a ache set, which exist others
cached devices with running I/Os, we get the amount of dirty data of the
device in an incremental way, and do not block other cached devices all the
time.

Patch v2: Rename some variables and macros name as Coly suggested.

Signed-off-by: Tang Junhui <tang.junhui@zte.com.cn>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/writeback.c | 29 ++++++++++++++++++++++++++---
 1 file changed, 26 insertions(+), 3 deletions(-)

diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 0d2a05074a81..912e969fedba 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -676,10 +676,14 @@ static int bch_writeback_thread(void *arg)
 }
 
 /* Init */
+#define INIT_KEYS_EACH_TIME	500000
+#define INIT_KEYS_SLEEP_MS	100
 
 struct sectors_dirty_init {
 	struct btree_op	op;
 	unsigned	inode;
+	size_t		count;
+	struct bkey	start;
 };
 
 static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
@@ -694,18 +698,37 @@ static int sectors_dirty_init_fn(struct btree_op *_op, struct btree *b,
 		bcache_dev_sectors_dirty_add(b->c, KEY_INODE(k),
 					     KEY_START(k), KEY_SIZE(k));
 
+	op->count++;
+	if (atomic_read(&b->c->search_inflight) &&
+	    !(op->count % INIT_KEYS_EACH_TIME)) {
+		bkey_copy_key(&op->start, k);
+		return -EAGAIN;
+	}
+
 	return MAP_CONTINUE;
 }
 
 void bch_sectors_dirty_init(struct bcache_device *d)
 {
 	struct sectors_dirty_init op;
+	int ret;
 
 	bch_btree_op_init(&op.op, -1);
 	op.inode = d->id;
-
-	bch_btree_map_keys(&op.op, d->c, &KEY(op.inode, 0, 0),
-			   sectors_dirty_init_fn, 0);
+	op.count = 0;
+	op.start = KEY(op.inode, 0, 0);
+
+	do {
+		ret = bch_btree_map_keys(&op.op, d->c, &op.start,
+					 sectors_dirty_init_fn, 0);
+		if (ret == -EAGAIN)
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(INIT_KEYS_SLEEP_MS));
+		else if (ret < 0) {
+			pr_warn("sectors dirty init failed, ret=%d!", ret);
+			break;
+		}
+	} while (ret == -EAGAIN);
 }
 
 void bch_cached_dev_writeback_init(struct cached_dev *dc)
-- 
cgit v1.2.3


From a56489d4b3c914eb30b724ff25debc2e59c7950e Mon Sep 17 00:00:00 2001
From: Florian Schmaus <flo@geekplace.eu>
Date: Thu, 26 Jul 2018 12:17:37 +0800
Subject: bcache: do not assign in if condition register_bcache()

Fixes an error condition reported by checkpatch.pl which is caused by
assigning a variable in an if condition.

Signed-off-by: Florian Schmaus <flo@geekplace.eu>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/super.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index cea2a42ea276..093b3789ce05 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -2165,8 +2165,12 @@ static ssize_t register_bcache(struct kobject *k, struct kobj_attribute *attr,
 	if (!try_module_get(THIS_MODULE))
 		return -EBUSY;
 
-	if (!(path = kstrndup(buffer, size, GFP_KERNEL)) ||
-	    !(sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL)))
+	path = kstrndup(buffer, size, GFP_KERNEL);
+	if (!path)
+		goto err;
+
+	sb = kmalloc(sizeof(struct cache_sb), GFP_KERNEL);
+	if (!sb)
 		goto err;
 
 	err = "failed to open device";
-- 
cgit v1.2.3


From 6268dc2c4703aabfb0b35681be709acf4c2826c6 Mon Sep 17 00:00:00 2001
From: Shenghui Wang <shhuiw@foxmail.com>
Date: Thu, 26 Jul 2018 12:17:38 +0800
Subject: bcache: free heap cache_set->flush_btree in bch_journal_free

Free the cache_set->flush_bree heap memory on journal free.

Signed-off-by: Wang Sheng-Hui <shhuiw@foxmail.com>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/journal.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/bcache/journal.c b/drivers/md/bcache/journal.c
index 18f1b5239620..10748c626a1d 100644
--- a/drivers/md/bcache/journal.c
+++ b/drivers/md/bcache/journal.c
@@ -828,6 +828,7 @@ void bch_journal_free(struct cache_set *c)
 	free_pages((unsigned long) c->journal.w[1].data, JSET_BITS);
 	free_pages((unsigned long) c->journal.w[0].data, JSET_BITS);
 	free_fifo(&c->journal.pin);
+	free_heap(&c->flush_btree);
 }
 
 int bch_journal_alloc(struct cache_set *c)
-- 
cgit v1.2.3


From 16c1fdf4cfd6c0091e59b93ec2cb7e99973f8244 Mon Sep 17 00:00:00 2001
From: Florian Schmaus <flo@geekplace.eu>
Date: Thu, 26 Jul 2018 12:17:39 +0800
Subject: bcache: do not assign in if condition in bcache_init()

Fixes an error condition reported by checkpatch.pl which is caused by
assigning a variable in an if condition.

Signed-off-by: Florian Schmaus <flo@geekplace.eu>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/super.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 093b3789ce05..a852018964ad 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -2330,9 +2330,15 @@ static int __init bcache_init(void)
 		return bcache_major;
 	}
 
-	if (!(bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0)) ||
-	    !(bcache_kobj = kobject_create_and_add("bcache", fs_kobj)) ||
-	    bch_request_init() ||
+	bcache_wq = alloc_workqueue("bcache", WQ_MEM_RECLAIM, 0);
+	if (!bcache_wq)
+		goto err;
+
+	bcache_kobj = kobject_create_and_add("bcache", fs_kobj);
+	if (!bcache_kobj)
+		goto err;
+
+	if (bch_request_init() ||
 	    bch_debug_init(bcache_kobj) || closure_debug_init() ||
 	    sysfs_create_files(bcache_kobj, files))
 		goto err;
-- 
cgit v1.2.3


From 9b4e9f5abb94b671f998ffc0efebd1582852fee3 Mon Sep 17 00:00:00 2001
From: Florian Schmaus <flo@geekplace.eu>
Date: Thu, 26 Jul 2018 12:17:40 +0800
Subject: bcache: do not assign in if condition in bcache_device_init()

Fixes an error condition reported by checkpatch.pl which is caused by
assigning a variable in an if condition.

Signed-off-by: Florian Schmaus <flo@geekplace.eu>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/super.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index a852018964ad..40fe26fef00f 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -796,11 +796,12 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 		return idx;
 
 	if (bioset_init(&d->bio_split, 4, offsetof(struct bbio, bio),
-			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER) ||
-	    !(d->disk = alloc_disk(BCACHE_MINORS))) {
-		ida_simple_remove(&bcache_device_idx, idx);
-		return -ENOMEM;
-	}
+			BIOSET_NEED_BVECS|BIOSET_NEED_RESCUER))
+		goto err;
+
+	d->disk = alloc_disk(BCACHE_MINORS);
+	if (!d->disk)
+		goto err;
 
 	set_capacity(d->disk, sectors);
 	snprintf(d->disk->disk_name, DISK_NAME_LEN, "bcache%i", idx);
@@ -834,6 +835,11 @@ static int bcache_device_init(struct bcache_device *d, unsigned block_size,
 	blk_queue_write_cache(q, true, true);
 
 	return 0;
+
+err:
+	ida_simple_remove(&bcache_device_idx, idx);
+	return -ENOMEM;
+
 }
 
 /* Cached device */
-- 
cgit v1.2.3


From 75cbb3f1d840429e6aa67b351332f38b29e6292c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 26 Jul 2018 12:17:41 +0800
Subject: bcache: stop using the deprecated get_seconds()

The get_seconds function is deprecated now since it returns a 32-bit
value that will eventually overflow, and we are replacing it throughout
the kernel with ktime_get_seconds() or ktime_get_real_seconds() that
return a time64_t.

bcache uses get_seconds() to read the current system time and store it in
the superblock as well as in uuid_entry structures that are user visible.

Unfortunately, the two structures in are still limited to 32 bits, so this
won't fix any real problems but will still overflow in year 2106. Let's
at least document that properly, in case we get an updated format in the
future it can be fixed. We still have a long time before the overflow
and checking the tools at https://github.com/koverstreet/bcache-tools
reveals no access to any of them.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/super.c   | 12 ++++++------
 include/uapi/linux/bcache.h |  4 ++--
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 40fe26fef00f..e0a92104ca23 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -181,7 +181,7 @@ static const char *read_super(struct cache_sb *sb, struct block_device *bdev,
 		goto err;
 	}
 
-	sb->last_mount = get_seconds();
+	sb->last_mount = (u32)ktime_get_real_seconds();
 	err = NULL;
 
 	get_page(bh->b_page);
@@ -701,7 +701,7 @@ static void bcache_device_detach(struct bcache_device *d)
 
 		SET_UUID_FLASH_ONLY(u, 0);
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		bch_uuid_write(d->c);
 	}
 
@@ -1033,7 +1033,7 @@ void bch_cached_dev_detach(struct cached_dev *dc)
 int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 			  uint8_t *set_uuid)
 {
-	uint32_t rtime = cpu_to_le32(get_seconds());
+	uint32_t rtime = cpu_to_le32((u32)ktime_get_real_seconds());
 	struct uuid_entry *u;
 	struct cached_dev *exist_dc, *t;
 
@@ -1076,7 +1076,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 	    (BDEV_STATE(&dc->sb) == BDEV_STATE_STALE ||
 	     BDEV_STATE(&dc->sb) == BDEV_STATE_NONE)) {
 		memcpy(u->uuid, invalid_uuid, 16);
-		u->invalidated = cpu_to_le32(get_seconds());
+		u->invalidated = cpu_to_le32((u32)ktime_get_real_seconds());
 		u = NULL;
 	}
 
@@ -1398,7 +1398,7 @@ int bch_flash_dev_create(struct cache_set *c, uint64_t size)
 
 	get_random_bytes(u->uuid, 16);
 	memset(u->label, 0, 32);
-	u->first_reg = u->last_reg = cpu_to_le32(get_seconds());
+	u->first_reg = u->last_reg = cpu_to_le32((u32)ktime_get_real_seconds());
 
 	SET_UUID_FLASH_ONLY(u, 1);
 	u->sectors = size >> 9;
@@ -1902,7 +1902,7 @@ static void run_cache_set(struct cache_set *c)
 		goto err;
 
 	closure_sync(&cl);
-	c->sb.last_mount = get_seconds();
+	c->sb.last_mount = (u32)ktime_get_real_seconds();
 	bcache_write_super(c);
 
 	list_for_each_entry_safe(dc, t, &uncached_devices, list)
diff --git a/include/uapi/linux/bcache.h b/include/uapi/linux/bcache.h
index 821f71a2e48f..8d19e02d752a 100644
--- a/include/uapi/linux/bcache.h
+++ b/include/uapi/linux/bcache.h
@@ -195,7 +195,7 @@ struct cache_sb {
 	};
 	};
 
-	__u32			last_mount;	/* time_t */
+	__u32			last_mount;	/* time overflow in y2106 */
 
 	__u16			first_bucket;
 	union {
@@ -318,7 +318,7 @@ struct uuid_entry {
 		struct {
 			__u8	uuid[16];
 			__u8	label[32];
-			__u32	first_reg;
+			__u32	first_reg; /* time overflow in y2106 */
 			__u32	last_reg;
 			__u32	invalidated;
 
-- 
cgit v1.2.3


From 14cb2c8a6c5dae57ee3e2da10fa3db2b9087e39e Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Wed, 25 Jul 2018 22:46:28 -0300
Subject: partitions/aix: fix usage of uninitialized lv_info and lvname
 structures

The if-block that sets a successful return value in aix_partition()
uses 'lvip[].pps_per_lv' and 'n[].name' potentially uninitialized.

For example, if 'numlvs' is zero or alloc_lvn() fails, neither is
initialized, but are used anyway if alloc_pvd() succeeds after it.

So, make the alloc_pvd() call conditional on their initialization.

This has been hit when attaching an apparently corrupted/stressed
AIX LUN, misleading the kernel to pr_warn() invalid data and hang.

    [...] partition (null) (11 pp's found) is not contiguous
    [...] partition (null) (2 pp's found) is not contiguous
    [...] partition (null) (3 pp's found) is not contiguous
    [...] partition (null) (64 pp's found) is not contiguous

Fixes: 6ceea22bbbc8 ("partitions: add aix lvm partition support files")
Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/aix.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/block/partitions/aix.c b/block/partitions/aix.c
index 007f95eea0e1..850cbd1860d4 100644
--- a/block/partitions/aix.c
+++ b/block/partitions/aix.c
@@ -178,7 +178,7 @@ int aix_partition(struct parsed_partitions *state)
 	u32 vgda_sector = 0;
 	u32 vgda_len = 0;
 	int numlvs = 0;
-	struct pvd *pvd;
+	struct pvd *pvd = NULL;
 	struct lv_info {
 		unsigned short pps_per_lv;
 		unsigned short pps_found;
@@ -232,10 +232,11 @@ int aix_partition(struct parsed_partitions *state)
 				if (lvip[i].pps_per_lv)
 					foundlvs += 1;
 			}
+			/* pvd loops depend on n[].name and lvip[].pps_per_lv */
+			pvd = alloc_pvd(state, vgda_sector + 17);
 		}
 		put_dev_sector(sect);
 	}
-	pvd = alloc_pvd(state, vgda_sector + 17);
 	if (pvd) {
 		int numpps = be16_to_cpu(pvd->pp_count);
 		int psn_part1 = be32_to_cpu(pvd->psn_part1);
-- 
cgit v1.2.3


From d43fdae7bac2def8c4314b5a49822cb7f08a45f1 Mon Sep 17 00:00:00 2001
From: Mauricio Faria de Oliveira <mfo@canonical.com>
Date: Wed, 25 Jul 2018 22:46:29 -0300
Subject: partitions/aix: append null character to print data from disk

Even if properly initialized, the lvname array (i.e., strings)
is read from disk, and might contain corrupt data (e.g., lack
the null terminating character for strings).

So, make sure the partition name string used in pr_warn() has
the null terminating character.

Fixes: 6ceea22bbbc8 ("partitions: add aix lvm partition support files")
Suggested-by: Daniel J. Axtens <daniel.axtens@canonical.com>
Signed-off-by: Mauricio Faria de Oliveira <mfo@canonical.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/aix.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/block/partitions/aix.c b/block/partitions/aix.c
index 850cbd1860d4..903f3ed175d0 100644
--- a/block/partitions/aix.c
+++ b/block/partitions/aix.c
@@ -283,10 +283,14 @@ int aix_partition(struct parsed_partitions *state)
 				next_lp_ix += 1;
 		}
 		for (i = 0; i < state->limit; i += 1)
-			if (lvip[i].pps_found && !lvip[i].lv_is_contiguous)
+			if (lvip[i].pps_found && !lvip[i].lv_is_contiguous) {
+				char tmp[sizeof(n[i].name) + 1]; // null char
+
+				snprintf(tmp, sizeof(tmp), "%s", n[i].name);
 				pr_warn("partition %s (%u pp's found) is "
 					"not contiguous\n",
-					n[i].name, lvip[i].pps_found);
+					tmp, lvip[i].pps_found);
+			}
 		kfree(pvd);
 	}
 	kfree(n);
-- 
cgit v1.2.3


From e6c17ada3188e0deb43652b0eed249f37e0d44b0 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Fri, 20 Jul 2018 17:07:15 -0400
Subject: media: dw9807-vcm: Recognise this is just the VCM bit of the device

The dw9807 contains a voice coil lens driver as well as an EEPROM. This
driver is just for the VCM. Reflect this in the driver's name --- this is
already the case for the compatible string, for instance.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/Kconfig      |   2 +-
 drivers/media/i2c/Makefile     |   2 +-
 drivers/media/i2c/dw9807-vcm.c | 329 +++++++++++++++++++++++++++++++++++++++++
 drivers/media/i2c/dw9807.c     | 329 -----------------------------------------
 4 files changed, 331 insertions(+), 331 deletions(-)
 create mode 100644 drivers/media/i2c/dw9807-vcm.c
 delete mode 100644 drivers/media/i2c/dw9807.c

diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 439f6be08b95..3a6434cdc2c0 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -346,7 +346,7 @@ config VIDEO_DW9714
 	  capability. This is designed for linear control of
 	  voice coil motors, controlled via I2C serial interface.
 
-config VIDEO_DW9807
+config VIDEO_DW9807_VCM
 	tristate "DW9807 lens voice coil support"
 	depends on I2C && VIDEO_V4L2 && MEDIA_CONTROLLER
 	depends on VIDEO_V4L2_SUBDEV_API
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index 837c428339df..a6314160a3f5 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -25,7 +25,7 @@ obj-$(CONFIG_VIDEO_SAA6752HS) += saa6752hs.o
 obj-$(CONFIG_VIDEO_AD5820)  += ad5820.o
 obj-$(CONFIG_VIDEO_AK7375)  += ak7375.o
 obj-$(CONFIG_VIDEO_DW9714)  += dw9714.o
-obj-$(CONFIG_VIDEO_DW9807)  += dw9807.o
+obj-$(CONFIG_VIDEO_DW9807_VCM)  += dw9807-vcm.o
 obj-$(CONFIG_VIDEO_ADV7170) += adv7170.o
 obj-$(CONFIG_VIDEO_ADV7175) += adv7175.o
 obj-$(CONFIG_VIDEO_ADV7180) += adv7180.o
diff --git a/drivers/media/i2c/dw9807-vcm.c b/drivers/media/i2c/dw9807-vcm.c
new file mode 100644
index 000000000000..8ba3920b6e2f
--- /dev/null
+++ b/drivers/media/i2c/dw9807-vcm.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2018 Intel Corporation
+
+#include <linux/acpi.h>
+#include <linux/delay.h>
+#include <linux/i2c.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/pm_runtime.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+
+#define DW9807_MAX_FOCUS_POS	1023
+/*
+ * This sets the minimum granularity for the focus positions.
+ * A value of 1 gives maximum accuracy for a desired focus position.
+ */
+#define DW9807_FOCUS_STEPS	1
+/*
+ * This acts as the minimum granularity of lens movement.
+ * Keep this value power of 2, so the control steps can be
+ * uniformly adjusted for gradual lens movement, with desired
+ * number of control steps.
+ */
+#define DW9807_CTRL_STEPS	16
+#define DW9807_CTRL_DELAY_US	1000
+
+#define DW9807_CTL_ADDR		0x02
+/*
+ * DW9807 separates two registers to control the VCM position.
+ * One for MSB value, another is LSB value.
+ */
+#define DW9807_MSB_ADDR		0x03
+#define DW9807_LSB_ADDR		0x04
+#define DW9807_STATUS_ADDR	0x05
+#define DW9807_MODE_ADDR	0x06
+#define DW9807_RESONANCE_ADDR	0x07
+
+#define MAX_RETRY		10
+
+struct dw9807_device {
+	struct v4l2_ctrl_handler ctrls_vcm;
+	struct v4l2_subdev sd;
+	u16 current_val;
+};
+
+static inline struct dw9807_device *sd_to_dw9807_vcm(
+					struct v4l2_subdev *subdev)
+{
+	return container_of(subdev, struct dw9807_device, sd);
+}
+
+static int dw9807_i2c_check(struct i2c_client *client)
+{
+	const char status_addr = DW9807_STATUS_ADDR;
+	char status_result;
+	int ret;
+
+	ret = i2c_master_send(client, &status_addr, sizeof(status_addr));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write STATUS address fail ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = i2c_master_recv(client, &status_result, sizeof(status_result));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C read STATUS value fail ret = %d\n",
+			ret);
+		return ret;
+	}
+
+	return status_result;
+}
+
+static int dw9807_set_dac(struct i2c_client *client, u16 data)
+{
+	const char tx_data[3] = {
+		DW9807_MSB_ADDR, ((data >> 8) & 0x03), (data & 0xff)
+	};
+	int val, ret;
+
+	/*
+	 * According to the datasheet, need to check the bus status before we
+	 * write VCM position. This ensure that we really write the value
+	 * into the register
+	 */
+	ret = readx_poll_timeout(dw9807_i2c_check, client, val, val <= 0,
+			DW9807_CTRL_DELAY_US, MAX_RETRY * DW9807_CTRL_DELAY_US);
+
+	if (ret || val < 0) {
+		if (ret) {
+			dev_warn(&client->dev,
+				"Cannot do the write operation because VCM is busy\n");
+		}
+
+		return ret ? -EBUSY : val;
+	}
+
+	/* Write VCM position to registers */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev,
+			"I2C write MSB fail ret=%d\n", ret);
+
+		return ret;
+	}
+
+	return 0;
+}
+
+static int dw9807_set_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct dw9807_device *dev_vcm = container_of(ctrl->handler,
+		struct dw9807_device, ctrls_vcm);
+
+	if (ctrl->id == V4L2_CID_FOCUS_ABSOLUTE) {
+		struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
+
+		dev_vcm->current_val = ctrl->val;
+		return dw9807_set_dac(client, ctrl->val);
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops dw9807_vcm_ctrl_ops = {
+	.s_ctrl = dw9807_set_ctrl,
+};
+
+static int dw9807_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	int rval;
+
+	rval = pm_runtime_get_sync(sd->dev);
+	if (rval < 0) {
+		pm_runtime_put_noidle(sd->dev);
+		return rval;
+	}
+
+	return 0;
+}
+
+static int dw9807_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	pm_runtime_put(sd->dev);
+
+	return 0;
+}
+
+static const struct v4l2_subdev_internal_ops dw9807_int_ops = {
+	.open = dw9807_open,
+	.close = dw9807_close,
+};
+
+static const struct v4l2_subdev_ops dw9807_ops = { };
+
+static void dw9807_subdev_cleanup(struct dw9807_device *dw9807_dev)
+{
+	v4l2_async_unregister_subdev(&dw9807_dev->sd);
+	v4l2_ctrl_handler_free(&dw9807_dev->ctrls_vcm);
+	media_entity_cleanup(&dw9807_dev->sd.entity);
+}
+
+static int dw9807_init_controls(struct dw9807_device *dev_vcm)
+{
+	struct v4l2_ctrl_handler *hdl = &dev_vcm->ctrls_vcm;
+	const struct v4l2_ctrl_ops *ops = &dw9807_vcm_ctrl_ops;
+	struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
+
+	v4l2_ctrl_handler_init(hdl, 1);
+
+	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FOCUS_ABSOLUTE,
+			  0, DW9807_MAX_FOCUS_POS, DW9807_FOCUS_STEPS, 0);
+
+	dev_vcm->sd.ctrl_handler = hdl;
+	if (hdl->error) {
+		dev_err(&client->dev, "%s fail error: 0x%x\n",
+			__func__, hdl->error);
+		return hdl->error;
+	}
+
+	return 0;
+}
+
+static int dw9807_probe(struct i2c_client *client)
+{
+	struct dw9807_device *dw9807_dev;
+	int rval;
+
+	dw9807_dev = devm_kzalloc(&client->dev, sizeof(*dw9807_dev),
+				  GFP_KERNEL);
+	if (dw9807_dev == NULL)
+		return -ENOMEM;
+
+	v4l2_i2c_subdev_init(&dw9807_dev->sd, client, &dw9807_ops);
+	dw9807_dev->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	dw9807_dev->sd.internal_ops = &dw9807_int_ops;
+
+	rval = dw9807_init_controls(dw9807_dev);
+	if (rval)
+		goto err_cleanup;
+
+	rval = media_entity_pads_init(&dw9807_dev->sd.entity, 0, NULL);
+	if (rval < 0)
+		goto err_cleanup;
+
+	dw9807_dev->sd.entity.function = MEDIA_ENT_F_LENS;
+
+	rval = v4l2_async_register_subdev(&dw9807_dev->sd);
+	if (rval < 0)
+		goto err_cleanup;
+
+	pm_runtime_set_active(&client->dev);
+	pm_runtime_enable(&client->dev);
+	pm_runtime_idle(&client->dev);
+
+	return 0;
+
+err_cleanup:
+	dw9807_subdev_cleanup(dw9807_dev);
+
+	return rval;
+}
+
+static int dw9807_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+
+	pm_runtime_disable(&client->dev);
+	pm_runtime_set_suspended(&client->dev);
+
+	dw9807_subdev_cleanup(dw9807_dev);
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position, so it consumes least current
+ * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int __maybe_unused dw9807_vcm_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+	const char tx_data[2] = { DW9807_CTL_ADDR, 0x01 };
+	int ret, val;
+
+	for (val = dw9807_dev->current_val & ~(DW9807_CTRL_STEPS - 1);
+	     val >= 0; val -= DW9807_CTRL_STEPS) {
+		ret = dw9807_set_dac(client, val);
+		if (ret)
+			dev_err_once(dev, "%s I2C failure: %d", __func__, ret);
+		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
+	}
+
+	/* Power down */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * This function sets the vcm position to the value set by the user
+ * through v4l2_ctrl_ops s_ctrl handler
+ * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
+ * to make the movements smoothly.
+ */
+static int  __maybe_unused dw9807_vcm_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
+	const char tx_data[2] = { DW9807_CTL_ADDR, 0x00 };
+	int ret, val;
+
+	/* Power on */
+	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
+	if (ret < 0) {
+		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
+		return ret;
+	}
+
+	for (val = dw9807_dev->current_val % DW9807_CTRL_STEPS;
+	     val < dw9807_dev->current_val + DW9807_CTRL_STEPS - 1;
+	     val += DW9807_CTRL_STEPS) {
+		ret = dw9807_set_dac(client, val);
+		if (ret)
+			dev_err_ratelimited(dev, "%s I2C failure: %d",
+						__func__, ret);
+		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
+	}
+
+	return 0;
+}
+
+static const struct of_device_id dw9807_of_table[] = {
+	{ .compatible = "dongwoon,dw9807-vcm" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, dw9807_of_table);
+
+static const struct dev_pm_ops dw9807_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume)
+	SET_RUNTIME_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume, NULL)
+};
+
+static struct i2c_driver dw9807_i2c_driver = {
+	.driver = {
+		.name = "dw9807",
+		.pm = &dw9807_pm_ops,
+		.of_match_table = dw9807_of_table,
+	},
+	.probe_new = dw9807_probe,
+	.remove = dw9807_remove,
+};
+
+module_i2c_driver(dw9807_i2c_driver);
+
+MODULE_AUTHOR("Chiang, Alan <alanx.chiang@intel.com>");
+MODULE_DESCRIPTION("DW9807 VCM driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/i2c/dw9807.c b/drivers/media/i2c/dw9807.c
deleted file mode 100644
index 8ba3920b6e2f..000000000000
--- a/drivers/media/i2c/dw9807.c
+++ /dev/null
@@ -1,329 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (C) 2018 Intel Corporation
-
-#include <linux/acpi.h>
-#include <linux/delay.h>
-#include <linux/i2c.h>
-#include <linux/iopoll.h>
-#include <linux/module.h>
-#include <linux/pm_runtime.h>
-#include <media/v4l2-ctrls.h>
-#include <media/v4l2-device.h>
-
-#define DW9807_MAX_FOCUS_POS	1023
-/*
- * This sets the minimum granularity for the focus positions.
- * A value of 1 gives maximum accuracy for a desired focus position.
- */
-#define DW9807_FOCUS_STEPS	1
-/*
- * This acts as the minimum granularity of lens movement.
- * Keep this value power of 2, so the control steps can be
- * uniformly adjusted for gradual lens movement, with desired
- * number of control steps.
- */
-#define DW9807_CTRL_STEPS	16
-#define DW9807_CTRL_DELAY_US	1000
-
-#define DW9807_CTL_ADDR		0x02
-/*
- * DW9807 separates two registers to control the VCM position.
- * One for MSB value, another is LSB value.
- */
-#define DW9807_MSB_ADDR		0x03
-#define DW9807_LSB_ADDR		0x04
-#define DW9807_STATUS_ADDR	0x05
-#define DW9807_MODE_ADDR	0x06
-#define DW9807_RESONANCE_ADDR	0x07
-
-#define MAX_RETRY		10
-
-struct dw9807_device {
-	struct v4l2_ctrl_handler ctrls_vcm;
-	struct v4l2_subdev sd;
-	u16 current_val;
-};
-
-static inline struct dw9807_device *sd_to_dw9807_vcm(
-					struct v4l2_subdev *subdev)
-{
-	return container_of(subdev, struct dw9807_device, sd);
-}
-
-static int dw9807_i2c_check(struct i2c_client *client)
-{
-	const char status_addr = DW9807_STATUS_ADDR;
-	char status_result;
-	int ret;
-
-	ret = i2c_master_send(client, &status_addr, sizeof(status_addr));
-	if (ret < 0) {
-		dev_err(&client->dev, "I2C write STATUS address fail ret = %d\n",
-			ret);
-		return ret;
-	}
-
-	ret = i2c_master_recv(client, &status_result, sizeof(status_result));
-	if (ret < 0) {
-		dev_err(&client->dev, "I2C read STATUS value fail ret = %d\n",
-			ret);
-		return ret;
-	}
-
-	return status_result;
-}
-
-static int dw9807_set_dac(struct i2c_client *client, u16 data)
-{
-	const char tx_data[3] = {
-		DW9807_MSB_ADDR, ((data >> 8) & 0x03), (data & 0xff)
-	};
-	int val, ret;
-
-	/*
-	 * According to the datasheet, need to check the bus status before we
-	 * write VCM position. This ensure that we really write the value
-	 * into the register
-	 */
-	ret = readx_poll_timeout(dw9807_i2c_check, client, val, val <= 0,
-			DW9807_CTRL_DELAY_US, MAX_RETRY * DW9807_CTRL_DELAY_US);
-
-	if (ret || val < 0) {
-		if (ret) {
-			dev_warn(&client->dev,
-				"Cannot do the write operation because VCM is busy\n");
-		}
-
-		return ret ? -EBUSY : val;
-	}
-
-	/* Write VCM position to registers */
-	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
-	if (ret < 0) {
-		dev_err(&client->dev,
-			"I2C write MSB fail ret=%d\n", ret);
-
-		return ret;
-	}
-
-	return 0;
-}
-
-static int dw9807_set_ctrl(struct v4l2_ctrl *ctrl)
-{
-	struct dw9807_device *dev_vcm = container_of(ctrl->handler,
-		struct dw9807_device, ctrls_vcm);
-
-	if (ctrl->id == V4L2_CID_FOCUS_ABSOLUTE) {
-		struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
-
-		dev_vcm->current_val = ctrl->val;
-		return dw9807_set_dac(client, ctrl->val);
-	}
-
-	return -EINVAL;
-}
-
-static const struct v4l2_ctrl_ops dw9807_vcm_ctrl_ops = {
-	.s_ctrl = dw9807_set_ctrl,
-};
-
-static int dw9807_open(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
-{
-	int rval;
-
-	rval = pm_runtime_get_sync(sd->dev);
-	if (rval < 0) {
-		pm_runtime_put_noidle(sd->dev);
-		return rval;
-	}
-
-	return 0;
-}
-
-static int dw9807_close(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
-{
-	pm_runtime_put(sd->dev);
-
-	return 0;
-}
-
-static const struct v4l2_subdev_internal_ops dw9807_int_ops = {
-	.open = dw9807_open,
-	.close = dw9807_close,
-};
-
-static const struct v4l2_subdev_ops dw9807_ops = { };
-
-static void dw9807_subdev_cleanup(struct dw9807_device *dw9807_dev)
-{
-	v4l2_async_unregister_subdev(&dw9807_dev->sd);
-	v4l2_ctrl_handler_free(&dw9807_dev->ctrls_vcm);
-	media_entity_cleanup(&dw9807_dev->sd.entity);
-}
-
-static int dw9807_init_controls(struct dw9807_device *dev_vcm)
-{
-	struct v4l2_ctrl_handler *hdl = &dev_vcm->ctrls_vcm;
-	const struct v4l2_ctrl_ops *ops = &dw9807_vcm_ctrl_ops;
-	struct i2c_client *client = v4l2_get_subdevdata(&dev_vcm->sd);
-
-	v4l2_ctrl_handler_init(hdl, 1);
-
-	v4l2_ctrl_new_std(hdl, ops, V4L2_CID_FOCUS_ABSOLUTE,
-			  0, DW9807_MAX_FOCUS_POS, DW9807_FOCUS_STEPS, 0);
-
-	dev_vcm->sd.ctrl_handler = hdl;
-	if (hdl->error) {
-		dev_err(&client->dev, "%s fail error: 0x%x\n",
-			__func__, hdl->error);
-		return hdl->error;
-	}
-
-	return 0;
-}
-
-static int dw9807_probe(struct i2c_client *client)
-{
-	struct dw9807_device *dw9807_dev;
-	int rval;
-
-	dw9807_dev = devm_kzalloc(&client->dev, sizeof(*dw9807_dev),
-				  GFP_KERNEL);
-	if (dw9807_dev == NULL)
-		return -ENOMEM;
-
-	v4l2_i2c_subdev_init(&dw9807_dev->sd, client, &dw9807_ops);
-	dw9807_dev->sd.flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-	dw9807_dev->sd.internal_ops = &dw9807_int_ops;
-
-	rval = dw9807_init_controls(dw9807_dev);
-	if (rval)
-		goto err_cleanup;
-
-	rval = media_entity_pads_init(&dw9807_dev->sd.entity, 0, NULL);
-	if (rval < 0)
-		goto err_cleanup;
-
-	dw9807_dev->sd.entity.function = MEDIA_ENT_F_LENS;
-
-	rval = v4l2_async_register_subdev(&dw9807_dev->sd);
-	if (rval < 0)
-		goto err_cleanup;
-
-	pm_runtime_set_active(&client->dev);
-	pm_runtime_enable(&client->dev);
-	pm_runtime_idle(&client->dev);
-
-	return 0;
-
-err_cleanup:
-	dw9807_subdev_cleanup(dw9807_dev);
-
-	return rval;
-}
-
-static int dw9807_remove(struct i2c_client *client)
-{
-	struct v4l2_subdev *sd = i2c_get_clientdata(client);
-	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
-
-	pm_runtime_disable(&client->dev);
-	pm_runtime_set_suspended(&client->dev);
-
-	dw9807_subdev_cleanup(dw9807_dev);
-
-	return 0;
-}
-
-/*
- * This function sets the vcm position, so it consumes least current
- * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
- * to make the movements smoothly.
- */
-static int __maybe_unused dw9807_vcm_suspend(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct v4l2_subdev *sd = i2c_get_clientdata(client);
-	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
-	const char tx_data[2] = { DW9807_CTL_ADDR, 0x01 };
-	int ret, val;
-
-	for (val = dw9807_dev->current_val & ~(DW9807_CTRL_STEPS - 1);
-	     val >= 0; val -= DW9807_CTRL_STEPS) {
-		ret = dw9807_set_dac(client, val);
-		if (ret)
-			dev_err_once(dev, "%s I2C failure: %d", __func__, ret);
-		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
-	}
-
-	/* Power down */
-	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
-	if (ret < 0) {
-		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-/*
- * This function sets the vcm position to the value set by the user
- * through v4l2_ctrl_ops s_ctrl handler
- * The lens position is gradually moved in units of DW9807_CTRL_STEPS,
- * to make the movements smoothly.
- */
-static int  __maybe_unused dw9807_vcm_resume(struct device *dev)
-{
-	struct i2c_client *client = to_i2c_client(dev);
-	struct v4l2_subdev *sd = i2c_get_clientdata(client);
-	struct dw9807_device *dw9807_dev = sd_to_dw9807_vcm(sd);
-	const char tx_data[2] = { DW9807_CTL_ADDR, 0x00 };
-	int ret, val;
-
-	/* Power on */
-	ret = i2c_master_send(client, tx_data, sizeof(tx_data));
-	if (ret < 0) {
-		dev_err(&client->dev, "I2C write CTL fail ret = %d\n", ret);
-		return ret;
-	}
-
-	for (val = dw9807_dev->current_val % DW9807_CTRL_STEPS;
-	     val < dw9807_dev->current_val + DW9807_CTRL_STEPS - 1;
-	     val += DW9807_CTRL_STEPS) {
-		ret = dw9807_set_dac(client, val);
-		if (ret)
-			dev_err_ratelimited(dev, "%s I2C failure: %d",
-						__func__, ret);
-		usleep_range(DW9807_CTRL_DELAY_US, DW9807_CTRL_DELAY_US + 10);
-	}
-
-	return 0;
-}
-
-static const struct of_device_id dw9807_of_table[] = {
-	{ .compatible = "dongwoon,dw9807-vcm" },
-	{ /* sentinel */ }
-};
-MODULE_DEVICE_TABLE(of, dw9807_of_table);
-
-static const struct dev_pm_ops dw9807_pm_ops = {
-	SET_SYSTEM_SLEEP_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume)
-	SET_RUNTIME_PM_OPS(dw9807_vcm_suspend, dw9807_vcm_resume, NULL)
-};
-
-static struct i2c_driver dw9807_i2c_driver = {
-	.driver = {
-		.name = "dw9807",
-		.pm = &dw9807_pm_ops,
-		.of_match_table = dw9807_of_table,
-	},
-	.probe_new = dw9807_probe,
-	.remove = dw9807_remove,
-};
-
-module_i2c_driver(dw9807_i2c_driver);
-
-MODULE_AUTHOR("Chiang, Alan <alanx.chiang@intel.com>");
-MODULE_DESCRIPTION("DW9807 VCM driver");
-MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 7c98c5ad80021cc0bc0d072da120441ce9190261 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Wed, 25 Jul 2018 09:44:30 -0400
Subject: media: dt-bindings: media: i2c: Document MT9V111 bindings

Add documentation for Aptina MT9V111 image sensor.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../bindings/media/i2c/aptina,mt9v111.txt          | 46 ++++++++++++++++++++++
 MAINTAINERS                                        |  8 ++++
 2 files changed, 54 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/media/i2c/aptina,mt9v111.txt

diff --git a/Documentation/devicetree/bindings/media/i2c/aptina,mt9v111.txt b/Documentation/devicetree/bindings/media/i2c/aptina,mt9v111.txt
new file mode 100644
index 000000000000..bd896e9f67d1
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/aptina,mt9v111.txt
@@ -0,0 +1,46 @@
+* Aptina MT9V111 CMOS sensor
+----------------------------
+
+The Aptina MT9V111 is a 1/4-Inch VGA-format digital image sensor with a core
+based on Aptina MT9V011 sensor and an integrated Image Flow Processor (IFP).
+
+The sensor has an active pixel array of 640x480 pixels and can output a number
+of image resolution and formats controllable through a simple two-wires
+interface.
+
+Required properties:
+--------------------
+
+- compatible: shall be "aptina,mt9v111".
+- clocks: reference to the system clock input provider.
+
+Optional properties:
+--------------------
+
+- enable-gpios: output enable signal, pin name "OE#". Active low.
+- standby-gpios: low power state control signal, pin name "STANDBY".
+  Active high.
+- reset-gpios: chip reset signal, pin name "RESET#". Active low.
+
+The device node must contain one 'port' child node with one 'endpoint' child
+sub-node for its digital output video port, in accordance with the video
+interface bindings defined in:
+Documentation/devicetree/bindings/media/video-interfaces.txt
+
+Example:
+--------
+
+        &i2c1 {
+                camera@48 {
+                        compatible = "aptina,mt9v111";
+                        reg = <0x48>;
+
+                        clocks = <&camera_clk>;
+
+                        port {
+                                mt9v111_out: endpoint {
+                                        remote-endpoint = <&ceu_in>;
+                                };
+                        };
+                };
+        };
diff --git a/MAINTAINERS b/MAINTAINERS
index 59a9e92caed9..a13344d6149a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9659,6 +9659,14 @@ F:	Documentation/devicetree/bindings/media/i2c/mt9v032.txt
 F:	drivers/media/i2c/mt9v032.c
 F:	include/media/i2c/mt9v032.h
 
+MT9V111 APTINA CAMERA SENSOR
+M:	Jacopo Mondi <jacopo@jmondi.org>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	Documentation/devicetree/bindings/media/i2c/aptina,mt9v111.txt
+F:	drivers/media/i2c/mt9v111.c
+
 MULTIFUNCTION DEVICES (MFD)
 M:	Lee Jones <lee.jones@linaro.org>
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd.git
-- 
cgit v1.2.3


From aab7ed1c392703604fbdc5bd5005dfb61a0b32f9 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Wed, 25 Jul 2018 09:44:31 -0400
Subject: media: i2c: Add driver for Aptina MT9V111

Add V4L2 sensor driver for Aptina MT9V111 CMOS image sensor.

The MT9V111 is a 1/4-Inch CMOS image sensor based on MT9V011 with an
integrated Image Flow Processor.

Reviewed-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/Kconfig   |   11 +
 drivers/media/i2c/Makefile  |    1 +
 drivers/media/i2c/mt9v111.c | 1298 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 1310 insertions(+)
 create mode 100644 drivers/media/i2c/mt9v111.c

diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index 3a6434cdc2c0..f4892f2b9788 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -861,6 +861,17 @@ config VIDEO_MT9V032
 	  This is a Video4Linux2 sensor driver for the Micron
 	  MT9V032 752x480 CMOS sensor.
 
+config VIDEO_MT9V111
+	tristate "Aptina MT9V111 sensor support"
+	depends on I2C && VIDEO_V4L2
+	depends on MEDIA_CAMERA_SUPPORT
+	help
+	  This is a Video4Linux2 sensor driver for the Aptina/Micron
+	  MT9V111 sensor.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called mt9v111.
+
 config VIDEO_SR030PC30
 	tristate "Siliconfile SR030PC30 sensor support"
 	depends on I2C && VIDEO_V4L2
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index a6314160a3f5..804d0818da18 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -86,6 +86,7 @@ obj-$(CONFIG_VIDEO_MT9T001) += mt9t001.o
 obj-$(CONFIG_VIDEO_MT9T112) += mt9t112.o
 obj-$(CONFIG_VIDEO_MT9V011) += mt9v011.o
 obj-$(CONFIG_VIDEO_MT9V032) += mt9v032.o
+obj-$(CONFIG_VIDEO_MT9V111) += mt9v111.o
 obj-$(CONFIG_VIDEO_SR030PC30)	+= sr030pc30.o
 obj-$(CONFIG_VIDEO_NOON010PC30)	+= noon010pc30.o
 obj-$(CONFIG_VIDEO_RJ54N1)	+= rj54n1cb0c.o
diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
new file mode 100644
index 000000000000..da8f6ab91307
--- /dev/null
+++ b/drivers/media/i2c/mt9v111.c
@@ -0,0 +1,1298 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * V4L2 sensor driver for Aptina MT9V111 image sensor
+ * Copyright (C) 2018 Jacopo Mondi <jacopo@jmondi.org>
+ *
+ * Based on mt9v032 driver
+ * Copyright (C) 2010, Laurent Pinchart <laurent.pinchart@ideasonboard.com>
+ * Copyright (C) 2008, Guennadi Liakhovetski <kernel@pengutronix.de>
+ *
+ * Based on mt9v011 driver
+ * Copyright (c) 2009 Mauro Carvalho Chehab <mchehab@kernel.org>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/i2c.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+#include <linux/v4l2-mediabus.h>
+#include <linux/module.h>
+
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-fwnode.h>
+#include <media/v4l2-image-sizes.h>
+#include <media/v4l2-subdev.h>
+
+/*
+ * MT9V111 is a 1/4-Inch CMOS digital image sensor with an integrated
+ * Image Flow Processing (IFP) engine and a sensor core loosely based on
+ * MT9V011.
+ *
+ * The IFP can produce several output image formats from the sensor core
+ * output. This driver currently supports only YUYV format permutations.
+ *
+ * The driver allows manual frame rate control through s_frame_interval subdev
+ * operation or V4L2_CID_V/HBLANK controls, but it is known that the
+ * auto-exposure algorithm might modify the programmed frame rate. While the
+ * driver initially programs the sensor with auto-exposure and
+ * auto-white-balancing enabled, it is possible to disable them and more
+ * precisely control the frame rate.
+ *
+ * While it seems possible to instruct the auto-exposure control algorithm to
+ * respect a programmed frame rate when adjusting the pixel integration time,
+ * registers controlling this feature are not documented in the public
+ * available sensor manual used to develop this driver (09005aef80e90084,
+ * MT9V111_1.fm - Rev. G 1/05 EN).
+ */
+
+#define MT9V111_CHIP_ID_HIGH				0x82
+#define MT9V111_CHIP_ID_LOW				0x3a
+
+#define MT9V111_R01_ADDR_SPACE				0x01
+#define MT9V111_R01_IFP					0x01
+#define MT9V111_R01_CORE				0x04
+
+#define MT9V111_IFP_R06_OPMODE_CTRL			0x06
+#define		MT9V111_IFP_R06_OPMODE_CTRL_AWB_EN	BIT(1)
+#define		MT9V111_IFP_R06_OPMODE_CTRL_AE_EN	BIT(14)
+#define MT9V111_IFP_R07_IFP_RESET			0x07
+#define		MT9V111_IFP_R07_IFP_RESET_MASK		BIT(0)
+#define MT9V111_IFP_R08_OUTFMT_CTRL			0x08
+#define		MT9V111_IFP_R08_OUTFMT_CTRL_FLICKER	BIT(11)
+#define		MT9V111_IFP_R08_OUTFMT_CTRL_PCLK	BIT(5)
+#define MT9V111_IFP_R3A_OUTFMT_CTRL2			0x3a
+#define		MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_CBCR	BIT(0)
+#define		MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_YC	BIT(1)
+#define		MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_MASK	GENMASK(2, 0)
+#define MT9V111_IFP_RA5_HPAN				0xa5
+#define MT9V111_IFP_RA6_HZOOM				0xa6
+#define MT9V111_IFP_RA7_HOUT				0xa7
+#define MT9V111_IFP_RA8_VPAN				0xa8
+#define MT9V111_IFP_RA9_VZOOM				0xa9
+#define MT9V111_IFP_RAA_VOUT				0xaa
+#define MT9V111_IFP_DECIMATION_MASK			GENMASK(9, 0)
+#define MT9V111_IFP_DECIMATION_FREEZE			BIT(15)
+
+#define MT9V111_CORE_R03_WIN_HEIGHT			0x03
+#define		MT9V111_CORE_R03_WIN_V_OFFS		2
+#define MT9V111_CORE_R04_WIN_WIDTH			0x04
+#define		MT9V111_CORE_R04_WIN_H_OFFS		114
+#define MT9V111_CORE_R05_HBLANK				0x05
+#define		MT9V111_CORE_R05_MIN_HBLANK		0x09
+#define		MT9V111_CORE_R05_MAX_HBLANK		GENMASK(9, 0)
+#define		MT9V111_CORE_R05_DEF_HBLANK		0x26
+#define MT9V111_CORE_R06_VBLANK				0x06
+#define		MT9V111_CORE_R06_MIN_VBLANK		0x03
+#define		MT9V111_CORE_R06_MAX_VBLANK		GENMASK(11, 0)
+#define		MT9V111_CORE_R06_DEF_VBLANK		0x04
+#define MT9V111_CORE_R07_OUT_CTRL			0x07
+#define		MT9V111_CORE_R07_OUT_CTRL_SAMPLE	BIT(4)
+#define MT9V111_CORE_R09_PIXEL_INT			0x09
+#define		MT9V111_CORE_R09_PIXEL_INT_MASK		GENMASK(11, 0)
+#define MT9V111_CORE_R0D_CORE_RESET			0x0d
+#define		MT9V111_CORE_R0D_CORE_RESET_MASK	BIT(0)
+#define MT9V111_CORE_RFF_CHIP_VER			0xff
+
+#define MT9V111_PIXEL_ARRAY_WIDTH			640
+#define MT9V111_PIXEL_ARRAY_HEIGHT			480
+
+#define MT9V111_MAX_CLKIN				27000000
+
+/* The default sensor configuration at startup time. */
+static struct v4l2_mbus_framefmt mt9v111_def_fmt = {
+	.width		= 640,
+	.height		= 480,
+	.code		= MEDIA_BUS_FMT_UYVY8_2X8,
+	.field		= V4L2_FIELD_NONE,
+	.colorspace	= V4L2_COLORSPACE_SRGB,
+	.ycbcr_enc	= V4L2_YCBCR_ENC_601,
+	.quantization	= V4L2_QUANTIZATION_LIM_RANGE,
+	.xfer_func	= V4L2_XFER_FUNC_SRGB,
+};
+
+struct mt9v111_dev {
+	struct device *dev;
+	struct i2c_client *client;
+
+	u8 addr_space;
+
+	struct v4l2_subdev sd;
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	struct media_pad pad;
+#endif
+
+	struct v4l2_ctrl *auto_awb;
+	struct v4l2_ctrl *auto_exp;
+	struct v4l2_ctrl *hblank;
+	struct v4l2_ctrl *vblank;
+	struct v4l2_ctrl_handler ctrls;
+
+	/* Output image format and sizes. */
+	struct v4l2_mbus_framefmt fmt;
+	unsigned int fps;
+
+	/* Protects power up/down sequences. */
+	struct mutex pwr_mutex;
+	int pwr_count;
+
+	/* Protects stream on/off sequences. */
+	struct mutex stream_mutex;
+	bool streaming;
+
+	/* Flags to mark HW settings as not yet applied. */
+	bool pending;
+
+	/* Clock provider and system clock frequency. */
+	struct clk *clk;
+	u32 sysclk;
+
+	struct gpio_desc *oe;
+	struct gpio_desc *standby;
+	struct gpio_desc *reset;
+};
+
+#define sd_to_mt9v111(__sd) container_of((__sd), struct mt9v111_dev, sd)
+
+/*
+ * mt9v111_mbus_fmt - List all media bus formats supported by the driver.
+ *
+ * Only list the media bus code here. The image sizes are freely configurable
+ * in the pixel array sizes range.
+ *
+ * The desired frame interval, in the supported frame interval range, is
+ * obtained by configuring blanking as the sensor does not have a PLL but
+ * only a fixed clock divider that generates the output pixel clock.
+ */
+static struct mt9v111_mbus_fmt {
+	u32	code;
+} mt9v111_formats[] = {
+	{
+		.code	= MEDIA_BUS_FMT_UYVY8_2X8,
+	},
+	{
+		.code	= MEDIA_BUS_FMT_YUYV8_2X8,
+	},
+	{
+		.code	= MEDIA_BUS_FMT_VYUY8_2X8,
+	},
+	{
+		.code	= MEDIA_BUS_FMT_YVYU8_2X8,
+	},
+};
+
+static u32 mt9v111_frame_intervals[] = {5, 10, 15, 20, 30};
+
+/*
+ * mt9v111_frame_sizes - List sensor's supported resolutions.
+ *
+ * Resolution generated through decimation in the IFP block from the
+ * full VGA pixel array.
+ */
+static struct v4l2_rect mt9v111_frame_sizes[] = {
+	{
+		.width	= 640,
+		.height	= 480,
+	},
+	{
+		.width	= 352,
+		.height	= 288
+	},
+	{
+		.width	= 320,
+		.height	= 240,
+	},
+	{
+		.width	= 176,
+		.height	= 144,
+	},
+	{
+		.width	= 160,
+		.height	= 120,
+	},
+};
+
+/* --- Device I/O access --- */
+
+static int __mt9v111_read(struct i2c_client *c, u8 reg, u16 *val)
+{
+	struct i2c_msg msg[2];
+	__be16 buf;
+	int ret;
+
+	msg[0].addr = c->addr;
+	msg[0].flags = 0;
+	msg[0].len = 1;
+	msg[0].buf = &reg;
+
+	msg[1].addr = c->addr;
+	msg[1].flags = I2C_M_RD;
+	msg[1].len = 2;
+	msg[1].buf = (char *)&buf;
+
+	ret = i2c_transfer(c->adapter, msg, 2);
+	if (ret < 0) {
+		dev_err(&c->dev, "i2c read transfer error: %d\n", ret);
+		return ret;
+	}
+
+	*val = be16_to_cpu(buf);
+
+	dev_dbg(&c->dev, "%s: %x=%x\n", __func__, reg, *val);
+
+	return 0;
+}
+
+static int __mt9v111_write(struct i2c_client *c, u8 reg, u16 val)
+{
+	struct i2c_msg msg;
+	u8 buf[3] = { 0 };
+	int ret;
+
+	buf[0] = reg;
+	buf[1] = val >> 8;
+	buf[2] = val & 0xff;
+
+	msg.addr = c->addr;
+	msg.flags = 0;
+	msg.len = 3;
+	msg.buf = (char *)buf;
+
+	dev_dbg(&c->dev, "%s: %x = %x%x\n", __func__, reg, buf[1], buf[2]);
+
+	ret = i2c_transfer(c->adapter, &msg, 1);
+	if (ret < 0) {
+		dev_err(&c->dev, "i2c write transfer error: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __mt9v111_addr_space_select(struct i2c_client *c, u16 addr_space)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(c);
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	u16 val;
+	int ret;
+
+	if (mt9v111->addr_space == addr_space)
+		return 0;
+
+	ret = __mt9v111_write(c, MT9V111_R01_ADDR_SPACE, addr_space);
+	if (ret)
+		return ret;
+
+	/* Verify address space has been updated */
+	ret = __mt9v111_read(c, MT9V111_R01_ADDR_SPACE, &val);
+	if (ret)
+		return ret;
+
+	if (val != addr_space)
+		return -EINVAL;
+
+	mt9v111->addr_space = addr_space;
+
+	return 0;
+}
+
+static int mt9v111_read(struct i2c_client *c, u8 addr_space, u8 reg, u16 *val)
+{
+	int ret;
+
+	/* Select register address space first. */
+	ret = __mt9v111_addr_space_select(c, addr_space);
+	if (ret)
+		return ret;
+
+	ret = __mt9v111_read(c, reg, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mt9v111_write(struct i2c_client *c, u8 addr_space, u8 reg, u16 val)
+{
+	int ret;
+
+	/* Select register address space first. */
+	ret = __mt9v111_addr_space_select(c, addr_space);
+	if (ret)
+		return ret;
+
+	ret = __mt9v111_write(c, reg, val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int mt9v111_update(struct i2c_client *c, u8 addr_space, u8 reg,
+			  u16 mask, u16 val)
+{
+	u16 current_val;
+	int ret;
+
+	/* Select register address space first. */
+	ret = __mt9v111_addr_space_select(c, addr_space);
+	if (ret)
+		return ret;
+
+	/* Read the current register value, then update it. */
+	ret = __mt9v111_read(c, reg, &current_val);
+	if (ret)
+		return ret;
+
+	current_val &= ~mask;
+	current_val |= (val & mask);
+	ret = __mt9v111_write(c, reg, current_val);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+/* --- Sensor HW operations --- */
+
+static int __mt9v111_power_on(struct v4l2_subdev *sd)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	int ret;
+
+	ret = clk_prepare_enable(mt9v111->clk);
+	if (ret)
+		return ret;
+
+	clk_set_rate(mt9v111->clk, mt9v111->sysclk);
+
+	gpiod_set_value(mt9v111->standby, 0);
+	usleep_range(500, 1000);
+
+	gpiod_set_value(mt9v111->oe, 1);
+	usleep_range(500, 1000);
+
+	return 0;
+}
+
+static int __mt9v111_power_off(struct v4l2_subdev *sd)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+
+	gpiod_set_value(mt9v111->oe, 0);
+	usleep_range(500, 1000);
+
+	gpiod_set_value(mt9v111->standby, 1);
+	usleep_range(500, 1000);
+
+	clk_disable_unprepare(mt9v111->clk);
+
+	return 0;
+}
+
+static int __mt9v111_hw_reset(struct mt9v111_dev *mt9v111)
+{
+	if (!mt9v111->reset)
+		return -EINVAL;
+
+	gpiod_set_value(mt9v111->reset, 1);
+	usleep_range(500, 1000);
+
+	gpiod_set_value(mt9v111->reset, 0);
+	usleep_range(500, 1000);
+
+	return 0;
+}
+
+static int __mt9v111_sw_reset(struct mt9v111_dev *mt9v111)
+{
+	struct i2c_client *c = mt9v111->client;
+	int ret;
+
+	/* Software reset core and IFP blocks. */
+
+	ret = mt9v111_update(c, MT9V111_R01_CORE,
+			     MT9V111_CORE_R0D_CORE_RESET,
+			     MT9V111_CORE_R0D_CORE_RESET_MASK, 1);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	ret = mt9v111_update(c, MT9V111_R01_CORE,
+			     MT9V111_CORE_R0D_CORE_RESET,
+			     MT9V111_CORE_R0D_CORE_RESET_MASK, 0);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	ret = mt9v111_update(c, MT9V111_R01_IFP,
+			     MT9V111_IFP_R07_IFP_RESET,
+			     MT9V111_IFP_R07_IFP_RESET_MASK, 1);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	ret = mt9v111_update(c, MT9V111_R01_IFP,
+			     MT9V111_IFP_R07_IFP_RESET,
+			     MT9V111_IFP_R07_IFP_RESET_MASK, 0);
+	if (ret)
+		return ret;
+	usleep_range(500, 1000);
+
+	return 0;
+}
+
+static int mt9v111_calc_frame_rate(struct mt9v111_dev *mt9v111,
+				   struct v4l2_fract *tpf)
+{
+	unsigned int fps = tpf->numerator ?
+			   tpf->denominator / tpf->numerator :
+			   tpf->denominator;
+	unsigned int best_diff;
+	unsigned int frm_cols;
+	unsigned int row_pclk;
+	unsigned int best_fps;
+	unsigned int pclk;
+	unsigned int diff;
+	unsigned int idx;
+	unsigned int hb;
+	unsigned int vb;
+	unsigned int i;
+	int ret;
+
+	/* Approximate to the closest supported frame interval. */
+	best_diff = ~0L;
+	for (i = 0, idx = 0; i < ARRAY_SIZE(mt9v111_frame_intervals); i++) {
+		diff = abs(fps - mt9v111_frame_intervals[i]);
+		if (diff < best_diff) {
+			idx = i;
+			best_diff = diff;
+		}
+	}
+	fps = mt9v111_frame_intervals[idx];
+
+	/*
+	 * The sensor does not provide a PLL circuitry and pixel clock is
+	 * generated dividing the master clock source by two.
+	 *
+	 * Trow = (W + Hblank + 114) * 2 * (1 / SYSCLK)
+	 * TFrame = Trow * (H + Vblank + 2)
+	 *
+	 * FPS = (SYSCLK / 2) / (Trow * (H + Vblank + 2))
+	 *
+	 * This boils down to tune H and V blanks to best approximate the
+	 * above equation.
+	 *
+	 * Test all available H/V blank values, until we reach the
+	 * desired frame rate.
+	 */
+	best_fps = vb = hb = 0;
+	pclk = DIV_ROUND_CLOSEST(mt9v111->sysclk, 2);
+	row_pclk = MT9V111_PIXEL_ARRAY_WIDTH + 7 + MT9V111_CORE_R04_WIN_H_OFFS;
+	frm_cols = MT9V111_PIXEL_ARRAY_HEIGHT + 7 + MT9V111_CORE_R03_WIN_V_OFFS;
+
+	best_diff = ~0L;
+	for (vb = MT9V111_CORE_R06_MIN_VBLANK;
+	     vb < MT9V111_CORE_R06_MAX_VBLANK; vb++) {
+		for (hb = MT9V111_CORE_R05_MIN_HBLANK;
+		     hb < MT9V111_CORE_R05_MAX_HBLANK; hb += 10) {
+			unsigned int t_frame = (row_pclk + hb) *
+					       (frm_cols + vb);
+			unsigned int t_fps = DIV_ROUND_CLOSEST(pclk, t_frame);
+
+			diff = abs(fps - t_fps);
+			if (diff < best_diff) {
+				best_diff = diff;
+				best_fps = t_fps;
+
+				if (diff == 0)
+					break;
+			}
+		}
+
+		if (diff == 0)
+			break;
+	}
+
+	ret = v4l2_ctrl_s_ctrl_int64(mt9v111->hblank, hb);
+	if (ret)
+		return ret;
+
+	ret = v4l2_ctrl_s_ctrl_int64(mt9v111->vblank, vb);
+	if (ret)
+		return ret;
+
+	tpf->numerator = 1;
+	tpf->denominator = best_fps;
+
+	return 0;
+}
+
+static int mt9v111_hw_config(struct mt9v111_dev *mt9v111)
+{
+	struct i2c_client *c = mt9v111->client;
+	unsigned int ret;
+	u16 outfmtctrl2;
+
+	/* Force device reset. */
+	ret = __mt9v111_hw_reset(mt9v111);
+	if (ret == -EINVAL)
+		ret = __mt9v111_sw_reset(mt9v111);
+	if (ret)
+		return ret;
+
+	/* Configure internal clock sample rate. */
+	ret = mt9v111->sysclk < DIV_ROUND_CLOSEST(MT9V111_MAX_CLKIN, 2) ?
+				mt9v111_update(c, MT9V111_R01_CORE,
+					MT9V111_CORE_R07_OUT_CTRL,
+					MT9V111_CORE_R07_OUT_CTRL_SAMPLE, 1) :
+				mt9v111_update(c, MT9V111_R01_CORE,
+					MT9V111_CORE_R07_OUT_CTRL,
+					MT9V111_CORE_R07_OUT_CTRL_SAMPLE, 0);
+	if (ret)
+		return ret;
+
+	/*
+	 * Configure output image format components ordering.
+	 *
+	 * TODO: IFP block can also output several RGB permutations, we only
+	 *	 support YUYV permutations at the moment.
+	 */
+	switch (mt9v111->fmt.code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+			outfmtctrl2 = MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_YC;
+			break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+			outfmtctrl2 = MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_CBCR;
+			break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+			outfmtctrl2 = MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_YC |
+				      MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_CBCR;
+			break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+			outfmtctrl2 = 0;
+			break;
+	}
+
+	ret = mt9v111_update(c, MT9V111_R01_IFP, MT9V111_IFP_R3A_OUTFMT_CTRL2,
+			     MT9V111_IFP_R3A_OUTFMT_CTRL2_SWAP_MASK,
+			     outfmtctrl2);
+	if (ret)
+		return ret;
+
+	/*
+	 * Do not change default sensor's core configuration:
+	 * output the whole 640x480 pixel array, skip 18 columns and 6 rows.
+	 *
+	 * Instead, control the output image size through IFP block.
+	 *
+	 * TODO: No zoom&pan support. Currently we control the output image
+	 *	 size only through decimation, with no zoom support.
+	 */
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA5_HPAN,
+			    MT9V111_IFP_DECIMATION_FREEZE);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA8_VPAN,
+			    MT9V111_IFP_DECIMATION_FREEZE);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA6_HZOOM,
+			    MT9V111_IFP_DECIMATION_FREEZE |
+			    MT9V111_PIXEL_ARRAY_WIDTH);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA9_VZOOM,
+			    MT9V111_IFP_DECIMATION_FREEZE |
+			    MT9V111_PIXEL_ARRAY_HEIGHT);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RA7_HOUT,
+			    MT9V111_IFP_DECIMATION_FREEZE |
+			    mt9v111->fmt.width);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_write(c, MT9V111_R01_IFP, MT9V111_IFP_RAA_VOUT,
+			    mt9v111->fmt.height);
+	if (ret)
+		return ret;
+
+	/* Apply controls to set auto exp, auto awb and timings */
+	ret = v4l2_ctrl_handler_setup(&mt9v111->ctrls);
+	if (ret)
+		return ret;
+
+	/*
+	 * Set pixel integration time to the whole frame time.
+	 * This value controls the the shutter delay when running with AE
+	 * disabled. If longer than frame time, it affects the output
+	 * frame rate.
+	 */
+	return mt9v111_write(c, MT9V111_R01_CORE, MT9V111_CORE_R09_PIXEL_INT,
+			     MT9V111_PIXEL_ARRAY_HEIGHT);
+}
+
+/* ---  V4L2 subdev operations --- */
+
+static int mt9v111_s_power(struct v4l2_subdev *sd, int on)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	int pwr_count;
+	int ret = 0;
+
+	mutex_lock(&mt9v111->pwr_mutex);
+
+	/*
+	 * Make sure we're transitioning from 0 to 1, or viceversa,
+	 * before actually changing the power state.
+	 */
+	pwr_count = mt9v111->pwr_count;
+	pwr_count += on ? 1 : -1;
+	if (pwr_count == !!on) {
+		ret = on ? __mt9v111_power_on(sd) :
+			   __mt9v111_power_off(sd);
+		if (!ret)
+			/* All went well, updated power counter. */
+			mt9v111->pwr_count = pwr_count;
+
+		mutex_unlock(&mt9v111->pwr_mutex);
+
+		return ret;
+	}
+
+	/*
+	 * Update power counter to keep track of how many nested calls we
+	 * received.
+	 */
+	WARN_ON(pwr_count < 0 || pwr_count > 1);
+	mt9v111->pwr_count = pwr_count;
+
+	mutex_unlock(&mt9v111->pwr_mutex);
+
+	return ret;
+}
+
+static int mt9v111_s_stream(struct v4l2_subdev *subdev, int enable)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(subdev);
+	int ret;
+
+	mutex_lock(&mt9v111->stream_mutex);
+
+	if (mt9v111->streaming == enable) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return 0;
+	}
+
+	ret = mt9v111_s_power(subdev, enable);
+	if (ret)
+		goto error_unlock;
+
+	if (enable && mt9v111->pending) {
+		ret = mt9v111_hw_config(mt9v111);
+		if (ret)
+			goto error_unlock;
+
+		/*
+		 * No need to update control here as far as only H/VBLANK are
+		 * supported and immediately programmed to registers in .s_ctrl
+		 */
+
+		mt9v111->pending = false;
+	}
+
+	mt9v111->streaming = enable ? true : false;
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+
+error_unlock:
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return ret;
+}
+
+static int mt9v111_s_frame_interval(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_frame_interval *ival)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	struct v4l2_fract *tpf = &ival->interval;
+	unsigned int fps = tpf->numerator ?
+			   tpf->denominator / tpf->numerator :
+			   tpf->denominator;
+	unsigned int max_fps;
+
+	if (!tpf->numerator)
+		tpf->numerator = 1;
+
+	mutex_lock(&mt9v111->stream_mutex);
+
+	if (mt9v111->streaming) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EBUSY;
+	}
+
+	if (mt9v111->fps == fps) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return 0;
+	}
+
+	/* Make sure frame rate/image sizes constraints are respected. */
+	if (mt9v111->fmt.width < QVGA_WIDTH &&
+	    mt9v111->fmt.height < QVGA_HEIGHT)
+		max_fps = 90;
+	else if (mt9v111->fmt.width < CIF_WIDTH &&
+		 mt9v111->fmt.height < CIF_HEIGHT)
+		max_fps = 60;
+	else
+		max_fps = mt9v111->sysclk <
+				DIV_ROUND_CLOSEST(MT9V111_MAX_CLKIN, 2) ? 15 :
+									  30;
+
+	if (fps > max_fps) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EINVAL;
+	}
+
+	mt9v111_calc_frame_rate(mt9v111, tpf);
+
+	mt9v111->fps = fps;
+	mt9v111->pending = true;
+
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static int mt9v111_g_frame_interval(struct v4l2_subdev *sd,
+				    struct v4l2_subdev_frame_interval *ival)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+	struct v4l2_fract *tpf = &ival->interval;
+
+	mutex_lock(&mt9v111->stream_mutex);
+
+	tpf->numerator = 1;
+	tpf->denominator = mt9v111->fps;
+
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static struct v4l2_mbus_framefmt *__mt9v111_get_pad_format(
+					struct mt9v111_dev *mt9v111,
+					struct v4l2_subdev_pad_config *cfg,
+					unsigned int pad,
+					enum v4l2_subdev_format_whence which)
+{
+	switch (which) {
+	case V4L2_SUBDEV_FORMAT_TRY:
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+		return v4l2_subdev_get_try_format(&mt9v111->sd, cfg, pad);
+#else
+		return &cfg->try_fmt;
+#endif
+	case V4L2_SUBDEV_FORMAT_ACTIVE:
+		return &mt9v111->fmt;
+	default:
+		return NULL;
+	}
+}
+
+static int mt9v111_enum_mbus_code(struct v4l2_subdev *subdev,
+				  struct v4l2_subdev_pad_config *cfg,
+				  struct v4l2_subdev_mbus_code_enum *code)
+{
+	if (code->pad || code->index > ARRAY_SIZE(mt9v111_formats) - 1)
+		return -EINVAL;
+
+	code->code = mt9v111_formats[code->index].code;
+
+	return 0;
+}
+
+static int mt9v111_enum_frame_interval(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_frame_interval_enum *fie)
+{
+	unsigned int i;
+
+	if (fie->pad || fie->index >= ARRAY_SIZE(mt9v111_frame_intervals))
+		return -EINVAL;
+
+	for (i = 0; i < ARRAY_SIZE(mt9v111_frame_sizes); i++)
+		if (fie->width == mt9v111_frame_sizes[i].width &&
+		    fie->height == mt9v111_frame_sizes[i].height)
+			break;
+
+	if (i == ARRAY_SIZE(mt9v111_frame_sizes))
+		return -EINVAL;
+
+	fie->interval.numerator = 1;
+	fie->interval.denominator = mt9v111_frame_intervals[fie->index];
+
+	return 0;
+}
+
+static int mt9v111_enum_frame_size(struct v4l2_subdev *subdev,
+				   struct v4l2_subdev_pad_config *cfg,
+				   struct v4l2_subdev_frame_size_enum *fse)
+{
+	if (fse->pad || fse->index > ARRAY_SIZE(mt9v111_frame_sizes))
+		return -EINVAL;
+
+	fse->min_width = mt9v111_frame_sizes[fse->index].width;
+	fse->max_width = mt9v111_frame_sizes[fse->index].width;
+	fse->min_height = mt9v111_frame_sizes[fse->index].height;
+	fse->max_height = mt9v111_frame_sizes[fse->index].height;
+
+	return 0;
+}
+
+static int mt9v111_get_format(struct v4l2_subdev *subdev,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *format)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(subdev);
+
+	if (format->pad)
+		return -EINVAL;
+
+	mutex_lock(&mt9v111->stream_mutex);
+	format->format = *__mt9v111_get_pad_format(mt9v111, cfg, format->pad,
+						   format->which);
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static int mt9v111_set_format(struct v4l2_subdev *subdev,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_format *format)
+{
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(subdev);
+	struct v4l2_mbus_framefmt new_fmt;
+	struct v4l2_mbus_framefmt *__fmt;
+	unsigned int best_fit = ~0L;
+	unsigned int idx;
+	unsigned int i;
+
+	mutex_lock(&mt9v111->stream_mutex);
+	if (mt9v111->streaming) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EBUSY;
+	}
+
+	if (format->pad) {
+		mutex_unlock(&mt9v111->stream_mutex);
+		return -EINVAL;
+	}
+
+	/* Update mbus format code and sizes. */
+	for (i = 0; i < ARRAY_SIZE(mt9v111_formats); i++) {
+		if (format->format.code == mt9v111_formats[i].code) {
+			new_fmt.code = mt9v111_formats[i].code;
+			break;
+		}
+	}
+	if (i == ARRAY_SIZE(mt9v111_formats))
+		new_fmt.code = mt9v111_formats[0].code;
+
+	for (i = 0; i < ARRAY_SIZE(mt9v111_frame_sizes); i++) {
+		unsigned int fit = abs(mt9v111_frame_sizes[i].width -
+				       format->format.width) +
+				   abs(mt9v111_frame_sizes[i].height -
+				       format->format.height);
+		if (fit < best_fit) {
+			best_fit = fit;
+			idx = i;
+
+			if (fit == 0)
+				break;
+		}
+	}
+	new_fmt.width = mt9v111_frame_sizes[idx].width;
+	new_fmt.height = mt9v111_frame_sizes[idx].height;
+
+	/* Update the device (or pad) format if it has changed. */
+	__fmt = __mt9v111_get_pad_format(mt9v111, cfg, format->pad,
+					 format->which);
+
+	/* Format hasn't changed, stop here. */
+	if (__fmt->code == new_fmt.code &&
+	    __fmt->width == new_fmt.width &&
+	    __fmt->height == new_fmt.height)
+		goto done;
+
+	/* Update the format and sizes, then  mark changes as pending. */
+	__fmt->code = new_fmt.code;
+	__fmt->width = new_fmt.width;
+	__fmt->height = new_fmt.height;
+
+	if (format->which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		mt9v111->pending = true;
+
+	dev_dbg(mt9v111->dev, "%s: mbus_code: %x - (%ux%u)\n",
+		__func__, __fmt->code, __fmt->width, __fmt->height);
+
+done:
+	format->format = *__fmt;
+
+	mutex_unlock(&mt9v111->stream_mutex);
+
+	return 0;
+}
+
+static int mt9v111_init_cfg(struct v4l2_subdev *subdev,
+			    struct v4l2_subdev_pad_config *cfg)
+{
+	cfg->try_fmt = mt9v111_def_fmt;
+
+	return 0;
+}
+
+static const struct v4l2_subdev_core_ops mt9v111_core_ops = {
+	.s_power		= mt9v111_s_power,
+};
+
+static const struct v4l2_subdev_video_ops mt9v111_video_ops = {
+	.s_stream		= mt9v111_s_stream,
+	.s_frame_interval	= mt9v111_s_frame_interval,
+	.g_frame_interval	= mt9v111_g_frame_interval,
+};
+
+static const struct v4l2_subdev_pad_ops mt9v111_pad_ops = {
+	.init_cfg		= mt9v111_init_cfg,
+	.enum_mbus_code		= mt9v111_enum_mbus_code,
+	.enum_frame_size	= mt9v111_enum_frame_size,
+	.enum_frame_interval	= mt9v111_enum_frame_interval,
+	.get_fmt		= mt9v111_get_format,
+	.set_fmt		= mt9v111_set_format,
+};
+
+static const struct v4l2_subdev_ops mt9v111_ops = {
+	.core	= &mt9v111_core_ops,
+	.video	= &mt9v111_video_ops,
+	.pad	= &mt9v111_pad_ops,
+};
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+static const struct media_entity_operations mt9v111_subdev_entity_ops = {
+	.link_validate = v4l2_subdev_link_validate,
+};
+#endif
+
+/* --- V4L2 ctrl --- */
+static int mt9v111_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct mt9v111_dev *mt9v111 = container_of(ctrl->handler,
+						   struct mt9v111_dev,
+						   ctrls);
+	int ret;
+
+	mutex_lock(&mt9v111->pwr_mutex);
+	/*
+	 * If sensor is powered down, just cache new control values,
+	 * no actual register access.
+	 */
+	if (!mt9v111->pwr_count) {
+		mt9v111->pending = true;
+		mutex_unlock(&mt9v111->pwr_mutex);
+		return 0;
+	}
+	mutex_unlock(&mt9v111->pwr_mutex);
+
+	/*
+	 * Flickering control gets disabled if both auto exp and auto awb
+	 * are disabled too. If any of the two is enabled, enable it.
+	 *
+	 * Disabling flickering when ae and awb are off allows a more precise
+	 * control of the programmed frame rate.
+	 */
+	if (mt9v111->auto_exp->is_new || mt9v111->auto_awb->is_new) {
+		if (mt9v111->auto_exp->val == V4L2_EXPOSURE_MANUAL &&
+		    mt9v111->auto_awb->val == V4L2_WHITE_BALANCE_MANUAL)
+			ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+					     MT9V111_IFP_R08_OUTFMT_CTRL,
+					     MT9V111_IFP_R08_OUTFMT_CTRL_FLICKER,
+					     0);
+		else
+			ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+					     MT9V111_IFP_R08_OUTFMT_CTRL,
+					     MT9V111_IFP_R08_OUTFMT_CTRL_FLICKER,
+					     1);
+		if (ret)
+			return ret;
+	}
+
+	ret = -EINVAL;
+	switch (ctrl->id) {
+	case V4L2_CID_AUTO_WHITE_BALANCE:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+				     MT9V111_IFP_R06_OPMODE_CTRL,
+				     MT9V111_IFP_R06_OPMODE_CTRL_AWB_EN,
+				     ctrl->val == V4L2_WHITE_BALANCE_AUTO ?
+				     MT9V111_IFP_R06_OPMODE_CTRL_AWB_EN : 0);
+		break;
+	case V4L2_CID_EXPOSURE_AUTO:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_IFP,
+				     MT9V111_IFP_R06_OPMODE_CTRL,
+				     MT9V111_IFP_R06_OPMODE_CTRL_AE_EN,
+				     ctrl->val == V4L2_EXPOSURE_AUTO ?
+				     MT9V111_IFP_R06_OPMODE_CTRL_AE_EN : 0);
+		break;
+	case V4L2_CID_HBLANK:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_CORE,
+				     MT9V111_CORE_R05_HBLANK,
+				     MT9V111_CORE_R05_MAX_HBLANK,
+				     mt9v111->hblank->val);
+		break;
+	case V4L2_CID_VBLANK:
+		ret = mt9v111_update(mt9v111->client, MT9V111_R01_CORE,
+				     MT9V111_CORE_R06_VBLANK,
+				     MT9V111_CORE_R06_MAX_VBLANK,
+				     mt9v111->vblank->val);
+		break;
+	}
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops mt9v111_ctrl_ops = {
+	.s_ctrl = mt9v111_s_ctrl,
+};
+
+static int mt9v111_chip_probe(struct mt9v111_dev *mt9v111)
+{
+	int ret;
+	u16 val;
+
+	ret = __mt9v111_power_on(&mt9v111->sd);
+	if (ret)
+		return ret;
+
+	ret = mt9v111_read(mt9v111->client, MT9V111_R01_CORE,
+			   MT9V111_CORE_RFF_CHIP_VER, &val);
+	if (ret)
+		goto power_off;
+
+	if ((val >> 8) != MT9V111_CHIP_ID_HIGH &&
+	    (val & 0xff) != MT9V111_CHIP_ID_LOW) {
+		dev_err(mt9v111->dev,
+			"Unable to identify MT9V111 chip: 0x%2x%2x\n",
+			val >> 8, val & 0xff);
+		ret = -EIO;
+		goto power_off;
+	}
+
+	dev_dbg(mt9v111->dev, "Chip identified: 0x%2x%2x\n",
+		val >> 8, val & 0xff);
+
+power_off:
+	__mt9v111_power_off(&mt9v111->sd);
+
+	return ret;
+}
+
+static int mt9v111_probe(struct i2c_client *client)
+{
+	struct mt9v111_dev *mt9v111;
+	struct v4l2_fract tpf;
+	int ret;
+
+	mt9v111 = devm_kzalloc(&client->dev, sizeof(*mt9v111), GFP_KERNEL);
+	if (!mt9v111)
+		return -ENOMEM;
+
+	mt9v111->dev = &client->dev;
+	mt9v111->client = client;
+
+	mt9v111->clk = devm_clk_get(&client->dev, NULL);
+	if (IS_ERR(mt9v111->clk))
+		return PTR_ERR(mt9v111->clk);
+
+	mt9v111->sysclk = clk_get_rate(mt9v111->clk);
+	if (mt9v111->sysclk > MT9V111_MAX_CLKIN)
+		return -EINVAL;
+
+	mt9v111->oe = devm_gpiod_get_optional(&client->dev, "enable",
+					      GPIOD_OUT_LOW);
+	if (IS_ERR(mt9v111->oe)) {
+		dev_err(&client->dev, "Unable to get GPIO \"enable\": %ld\n",
+			PTR_ERR(mt9v111->oe));
+		return PTR_ERR(mt9v111->oe);
+	}
+
+	mt9v111->standby = devm_gpiod_get_optional(&client->dev, "standby",
+						   GPIOD_OUT_HIGH);
+	if (IS_ERR(mt9v111->standby)) {
+		dev_err(&client->dev, "Unable to get GPIO \"standby\": %ld\n",
+			PTR_ERR(mt9v111->standby));
+		return PTR_ERR(mt9v111->standby);
+	}
+
+	mt9v111->reset = devm_gpiod_get_optional(&client->dev, "reset",
+						 GPIOD_OUT_LOW);
+	if (IS_ERR(mt9v111->reset)) {
+		dev_err(&client->dev, "Unable to get GPIO \"reset\": %ld\n",
+			PTR_ERR(mt9v111->reset));
+		return PTR_ERR(mt9v111->reset);
+	}
+
+	mutex_init(&mt9v111->pwr_mutex);
+	mutex_init(&mt9v111->stream_mutex);
+
+	v4l2_ctrl_handler_init(&mt9v111->ctrls, 5);
+
+	mt9v111->auto_awb = v4l2_ctrl_new_std(&mt9v111->ctrls,
+					      &mt9v111_ctrl_ops,
+					      V4L2_CID_AUTO_WHITE_BALANCE,
+					      0, 1, 1,
+					      V4L2_WHITE_BALANCE_AUTO);
+	if (IS_ERR_OR_NULL(mt9v111->auto_awb)) {
+		ret = PTR_ERR(mt9v111->auto_awb);
+		goto error_free_ctrls;
+	}
+
+	mt9v111->auto_exp = v4l2_ctrl_new_std_menu(&mt9v111->ctrls,
+						   &mt9v111_ctrl_ops,
+						   V4L2_CID_EXPOSURE_AUTO,
+						   V4L2_EXPOSURE_MANUAL,
+						   0, V4L2_EXPOSURE_AUTO);
+	if (IS_ERR_OR_NULL(mt9v111->auto_exp)) {
+		ret = PTR_ERR(mt9v111->auto_exp);
+		goto error_free_ctrls;
+	}
+
+	/* Initialize timings */
+	mt9v111->hblank = v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops,
+					    V4L2_CID_HBLANK,
+					    MT9V111_CORE_R05_MIN_HBLANK,
+					    MT9V111_CORE_R05_MAX_HBLANK, 1,
+					    MT9V111_CORE_R05_DEF_HBLANK);
+	if (IS_ERR_OR_NULL(mt9v111->hblank)) {
+		ret = PTR_ERR(mt9v111->hblank);
+		goto error_free_ctrls;
+	}
+
+	mt9v111->vblank = v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops,
+					    V4L2_CID_VBLANK,
+					    MT9V111_CORE_R06_MIN_VBLANK,
+					    MT9V111_CORE_R06_MAX_VBLANK, 1,
+					    MT9V111_CORE_R06_DEF_VBLANK);
+	if (IS_ERR_OR_NULL(mt9v111->vblank)) {
+		ret = PTR_ERR(mt9v111->vblank);
+		goto error_free_ctrls;
+	}
+
+	/* PIXEL_RATE is fixed: just expose it to user space. */
+	v4l2_ctrl_new_std(&mt9v111->ctrls, &mt9v111_ctrl_ops,
+			  V4L2_CID_PIXEL_RATE, 0,
+			  DIV_ROUND_CLOSEST(mt9v111->sysclk, 2), 1,
+			  DIV_ROUND_CLOSEST(mt9v111->sysclk, 2));
+
+	mt9v111->sd.ctrl_handler = &mt9v111->ctrls;
+
+	/* Start with default configuration: 640x480 UYVY. */
+	mt9v111->fmt	= mt9v111_def_fmt;
+
+	/* Re-calculate blankings for 640x480@15fps. */
+	mt9v111->fps		= 15;
+	tpf.numerator		= 1;
+	tpf.denominator		= mt9v111->fps;
+	mt9v111_calc_frame_rate(mt9v111, &tpf);
+
+	mt9v111->pwr_count	= 0;
+	mt9v111->addr_space	= MT9V111_R01_IFP;
+	mt9v111->pending	= true;
+
+	v4l2_i2c_subdev_init(&mt9v111->sd, client, &mt9v111_ops);
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	mt9v111->sd.flags	|= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	mt9v111->sd.entity.ops	= &mt9v111_subdev_entity_ops;
+	mt9v111->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+
+	mt9v111->pad.flags	= MEDIA_PAD_FL_SOURCE;
+	ret = media_entity_pads_init(&mt9v111->sd.entity, 1, &mt9v111->pad);
+	if (ret)
+		goto error_free_ctrls;
+#endif
+
+	ret = mt9v111_chip_probe(mt9v111);
+	if (ret)
+		goto error_free_ctrls;
+
+	ret = v4l2_async_register_subdev(&mt9v111->sd);
+	if (ret)
+		goto error_free_ctrls;
+
+	return 0;
+
+error_free_ctrls:
+	v4l2_ctrl_handler_free(&mt9v111->ctrls);
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	media_entity_cleanup(&mt9v111->sd.entity);
+#endif
+
+	mutex_destroy(&mt9v111->pwr_mutex);
+	mutex_destroy(&mt9v111->stream_mutex);
+
+	return ret;
+}
+
+static int mt9v111_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct mt9v111_dev *mt9v111 = sd_to_mt9v111(sd);
+
+	v4l2_async_unregister_subdev(sd);
+
+	v4l2_ctrl_handler_free(&mt9v111->ctrls);
+
+#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+	media_entity_cleanup(&sd->entity);
+#endif
+
+	mutex_destroy(&mt9v111->pwr_mutex);
+	mutex_destroy(&mt9v111->stream_mutex);
+
+	devm_gpiod_put(mt9v111->dev, mt9v111->oe);
+	devm_gpiod_put(mt9v111->dev, mt9v111->standby);
+	devm_gpiod_put(mt9v111->dev, mt9v111->reset);
+
+	devm_clk_put(mt9v111->dev, mt9v111->clk);
+
+	return 0;
+}
+
+static const struct of_device_id mt9v111_of_match[] = {
+	{ .compatible = "aptina,mt9v111", },
+	{ /* sentinel */ },
+};
+
+static struct i2c_driver mt9v111_driver = {
+	.driver = {
+		.name = "mt9v111",
+		.of_match_table = mt9v111_of_match,
+	},
+	.probe_new	= mt9v111_probe,
+	.remove		= mt9v111_remove,
+};
+
+module_i2c_driver(mt9v111_driver);
+
+MODULE_DESCRIPTION("V4L2 sensor driver for Aptina MT9V111");
+MODULE_AUTHOR("Jacopo Mondi <jacopo@jmondi.org>");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 1434e3b34816bede31400f9d2bc0c8bc6850459a Mon Sep 17 00:00:00 2001
From: Rui Miguel Silva <rui.silva@linaro.org>
Date: Tue, 3 Jul 2018 10:08:02 -0400
Subject: media: ov2680: dt: Add bindings for OV2680

Add device tree binding documentation for the OV2680 camera sensor.

[Sakari Ailus: Squash MAINTAINERS entry from Rui]

CC: devicetree@vger.kernel.org
Signed-off-by: Rui Miguel Silva <rui.silva@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../devicetree/bindings/media/i2c/ov2680.txt       | 46 ++++++++++++++++++++++
 MAINTAINERS                                        |  8 ++++
 2 files changed, 54 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/media/i2c/ov2680.txt

diff --git a/Documentation/devicetree/bindings/media/i2c/ov2680.txt b/Documentation/devicetree/bindings/media/i2c/ov2680.txt
new file mode 100644
index 000000000000..11e925ed9dad
--- /dev/null
+++ b/Documentation/devicetree/bindings/media/i2c/ov2680.txt
@@ -0,0 +1,46 @@
+* Omnivision OV2680 MIPI CSI-2 sensor
+
+Required Properties:
+- compatible: should be "ovti,ov2680".
+- clocks: reference to the xvclk input clock.
+- clock-names: should be "xvclk".
+- DOVDD-supply: Digital I/O voltage supply.
+- DVDD-supply: Digital core voltage supply.
+- AVDD-supply: Analog voltage supply.
+
+Optional Properties:
+- reset-gpios: reference to the GPIO connected to the powerdown/reset pin,
+               if any. This is an active low signal to the OV2680.
+
+The device node must contain one 'port' child node for its digital output
+video port, and this port must have a single endpoint in accordance with
+ the video interface bindings defined in
+Documentation/devicetree/bindings/media/video-interfaces.txt.
+
+Endpoint node required properties for CSI-2 connection are:
+- remote-endpoint: a phandle to the bus receiver's endpoint node.
+- clock-lanes: should be set to <0> (clock lane on hardware lane 0).
+- data-lanes: should be set to <1> (one CSI-2 lane supported).
+
+Example:
+
+&i2c2 {
+	ov2680: camera-sensor@36 {
+		compatible = "ovti,ov2680";
+		reg = <0x36>;
+		clocks = <&osc>;
+		clock-names = "xvclk";
+		reset-gpios = <&gpio1 3 GPIO_ACTIVE_LOW>;
+		DOVDD-supply = <&sw2_reg>;
+		DVDD-supply = <&sw2_reg>;
+		AVDD-supply = <&reg_peri_3p15v>;
+
+		port {
+			ov2680_to_mipi: endpoint {
+				remote-endpoint = <&mipi_from_sensor>;
+				clock-lanes = <0>;
+				data-lanes = <1>;
+			};
+		};
+	};
+};
diff --git a/MAINTAINERS b/MAINTAINERS
index a13344d6149a..ab739894d257 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10490,6 +10490,14 @@ T:	git git://linuxtv.org/media_tree.git
 S:	Maintained
 F:	drivers/media/i2c/ov13858.c
 
+OMNIVISION OV2680 SENSOR DRIVER
+M:	Rui Miguel Silva <rmfrfs@gmail.com>
+L:	linux-media@vger.kernel.org
+T:	git git://linuxtv.org/media_tree.git
+S:	Maintained
+F:	drivers/media/i2c/ov2680.c
+F:	Documentation/devicetree/bindings/media/i2c/ov2680.txt
+
 OMNIVISION OV2685 SENSOR DRIVER
 M:	Shunqian Zheng <zhengsq@rock-chips.com>
 L:	linux-media@vger.kernel.org
-- 
cgit v1.2.3


From 1f3ed383fb9a073ae2e408cd7a0717b04c7c3a21 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 27 Jul 2018 09:45:05 +0200
Subject: net: sched: don't dump chains only held by actions

In case a chain is empty and not explicitly created by a user,
such chain should not exist. The only exception is if there is
an action "goto chain" pointing to it. In that case, don't show the
chain in the dump. Track the chain references held by actions and
use them to find out if a chain should or should not be shown
in chain dump.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h     |  3 ++
 include/net/sch_generic.h |  1 +
 net/sched/act_api.c       |  4 +--
 net/sched/cls_api.c       | 70 +++++++++++++++++++++++++++++++++++++++--------
 4 files changed, 64 insertions(+), 14 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index a3101582f642..6d02f31abba8 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -39,7 +39,10 @@ bool tcf_queue_work(struct rcu_work *rwork, work_func_t func);
 #ifdef CONFIG_NET_CLS
 struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
 				bool create);
+struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block,
+				       u32 chain_index);
 void tcf_chain_put(struct tcf_chain *chain);
+void tcf_chain_put_by_act(struct tcf_chain *chain);
 void tcf_block_netif_keep_dst(struct tcf_block *block);
 int tcf_block_get(struct tcf_block **p_block,
 		  struct tcf_proto __rcu **p_filter_chain, struct Qdisc *q,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 085c509c8674..c5432362dc26 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -314,6 +314,7 @@ struct tcf_chain {
 	struct tcf_block *block;
 	u32 index; /* chain index */
 	unsigned int refcnt;
+	unsigned int action_refcnt;
 	bool explicitly_created;
 	const struct tcf_proto_ops *tmplt_ops;
 	void *tmplt_priv;
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 148a89ab789b..b43df1e25c6d 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -36,7 +36,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp)
 
 	if (!tp)
 		return -EINVAL;
-	a->goto_chain = tcf_chain_get(tp->chain->block, chain_index, true);
+	a->goto_chain = tcf_chain_get_by_act(tp->chain->block, chain_index);
 	if (!a->goto_chain)
 		return -ENOMEM;
 	return 0;
@@ -44,7 +44,7 @@ static int tcf_action_goto_chain_init(struct tc_action *a, struct tcf_proto *tp)
 
 static void tcf_action_goto_chain_fini(struct tc_action *a)
 {
-	tcf_chain_put(a->goto_chain);
+	tcf_chain_put_by_act(a->goto_chain);
 }
 
 static void tcf_action_goto_chain_exec(const struct tc_action *a,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 75cce2819de9..e20aad1987b8 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -262,6 +262,25 @@ static void tcf_chain_hold(struct tcf_chain *chain)
 	++chain->refcnt;
 }
 
+static void tcf_chain_hold_by_act(struct tcf_chain *chain)
+{
+	++chain->action_refcnt;
+}
+
+static void tcf_chain_release_by_act(struct tcf_chain *chain)
+{
+	--chain->action_refcnt;
+}
+
+static bool tcf_chain_is_zombie(struct tcf_chain *chain)
+{
+	/* In case all the references are action references, this
+	 * chain is a zombie and should not be listed in the chain
+	 * dump list.
+	 */
+	return chain->refcnt == chain->action_refcnt;
+}
+
 static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
 					  u32 chain_index)
 {
@@ -298,6 +317,15 @@ struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
 }
 EXPORT_SYMBOL(tcf_chain_get);
 
+struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index)
+{
+	struct tcf_chain *chain = tcf_chain_get(block, chain_index, true);
+
+	tcf_chain_hold_by_act(chain);
+	return chain;
+}
+EXPORT_SYMBOL(tcf_chain_get_by_act);
+
 static void tc_chain_tmplt_del(struct tcf_chain *chain);
 
 void tcf_chain_put(struct tcf_chain *chain)
@@ -310,6 +338,13 @@ void tcf_chain_put(struct tcf_chain *chain)
 }
 EXPORT_SYMBOL(tcf_chain_put);
 
+void tcf_chain_put_by_act(struct tcf_chain *chain)
+{
+	tcf_chain_release_by_act(chain);
+	tcf_chain_put(chain);
+}
+EXPORT_SYMBOL(tcf_chain_put_by_act);
+
 static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
 {
 	if (chain->explicitly_created)
@@ -1803,20 +1838,29 @@ replay:
 	chain = tcf_chain_lookup(block, chain_index);
 	if (n->nlmsg_type == RTM_NEWCHAIN) {
 		if (chain) {
-			NL_SET_ERR_MSG(extack, "Filter chain already exists");
-			return -EEXIST;
-		}
-		if (!(n->nlmsg_flags & NLM_F_CREATE)) {
-			NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
-			return -ENOENT;
-		}
-		chain = tcf_chain_create(block, chain_index);
-		if (!chain) {
-			NL_SET_ERR_MSG(extack, "Failed to create filter chain");
-			return -ENOMEM;
+			if (tcf_chain_is_zombie(chain)) {
+				/* The chain exists only because there is
+				 * some action referencing it, meaning it
+				 * is a zombie.
+				 */
+				tcf_chain_hold(chain);
+			} else {
+				NL_SET_ERR_MSG(extack, "Filter chain already exists");
+				return -EEXIST;
+			}
+		} else {
+			if (!(n->nlmsg_flags & NLM_F_CREATE)) {
+				NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
+				return -ENOENT;
+			}
+			chain = tcf_chain_create(block, chain_index);
+			if (!chain) {
+				NL_SET_ERR_MSG(extack, "Failed to create filter chain");
+				return -ENOMEM;
+			}
 		}
 	} else {
-		if (!chain) {
+		if (!chain || tcf_chain_is_zombie(chain)) {
 			NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
 			return -EINVAL;
 		}
@@ -1944,6 +1988,8 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 			index++;
 			continue;
 		}
+		if (tcf_chain_is_zombie(chain))
+			continue;
 		err = tc_chain_fill_node(chain, net, skb, block,
 					 NETLINK_CB(cb->skb).portid,
 					 cb->nlh->nlmsg_seq, NLM_F_MULTI,
-- 
cgit v1.2.3


From 3ee47cad3e6955147882f1a24a9465704d8eddd2 Mon Sep 17 00:00:00 2001
From: Rui Miguel Silva <rui.silva@linaro.org>
Date: Tue, 3 Jul 2018 10:08:03 -0400
Subject: media: ov2680: Add Omnivision OV2680 sensor driver

This patch adds V4L2 sub-device driver for OV2680 image sensor.
The OV2680 is a 1/5" CMOS color sensor from Omnivision.
Supports output format: 10-bit Raw RGB.
The OV2680 has a single lane MIPI interface.

The driver exposes following V4L2 controls:
- auto/manual exposure,
- exposure,
- auto/manual gain,
- gain,
- horizontal/vertical flip,
- test pattern menu.
Supported resolution are only: QUXGA, 720P, UXGA.

[Sakari Ailus: Drop "-level" from Kconfig help text]

Signed-off-by: Rui Miguel Silva <rui.silva@linaro.org>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/Kconfig  |   12 +
 drivers/media/i2c/Makefile |    1 +
 drivers/media/i2c/ov2680.c | 1186 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 1199 insertions(+)
 create mode 100644 drivers/media/i2c/ov2680.c

diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
index f4892f2b9788..82af97430e5b 100644
--- a/drivers/media/i2c/Kconfig
+++ b/drivers/media/i2c/Kconfig
@@ -637,6 +637,18 @@ config VIDEO_OV2659
 	  To compile this driver as a module, choose M here: the
 	  module will be called ov2659.
 
+config VIDEO_OV2680
+	tristate "OmniVision OV2680 sensor support"
+	depends on VIDEO_V4L2 && I2C && MEDIA_CONTROLLER
+	depends on MEDIA_CAMERA_SUPPORT
+	select V4L2_FWNODE
+	---help---
+	  This is a Video4Linux2 sensor driver for the OmniVision
+	  OV2680 camera.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called ov2680.
+
 config VIDEO_OV2685
 	tristate "OmniVision OV2685 sensor support"
 	depends on VIDEO_V4L2 && I2C && MEDIA_CONTROLLER
diff --git a/drivers/media/i2c/Makefile b/drivers/media/i2c/Makefile
index 804d0818da18..a94eb03d10d4 100644
--- a/drivers/media/i2c/Makefile
+++ b/drivers/media/i2c/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_VIDEO_SONY_BTF_MPX) += sony-btf-mpx.o
 obj-$(CONFIG_VIDEO_UPD64031A) += upd64031a.o
 obj-$(CONFIG_VIDEO_UPD64083) += upd64083.o
 obj-$(CONFIG_VIDEO_OV2640) += ov2640.o
+obj-$(CONFIG_VIDEO_OV2680) += ov2680.o
 obj-$(CONFIG_VIDEO_OV2685) += ov2685.o
 obj-$(CONFIG_VIDEO_OV5640) += ov5640.o
 obj-$(CONFIG_VIDEO_OV5645) += ov5645.o
diff --git a/drivers/media/i2c/ov2680.c b/drivers/media/i2c/ov2680.c
new file mode 100644
index 000000000000..f753a1c333ef
--- /dev/null
+++ b/drivers/media/i2c/ov2680.c
@@ -0,0 +1,1186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Omnivision OV2680 CMOS Image Sensor driver
+ *
+ * Copyright (C) 2018 Linaro Ltd
+ *
+ * Based on OV5640 Sensor Driver
+ * Copyright (C) 2011-2013 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright (C) 2014-2017 Mentor Graphics Inc.
+ *
+ */
+
+#include <asm/unaligned.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/i2c.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/gpio/consumer.h>
+#include <linux/regulator/consumer.h>
+
+#include <media/v4l2-common.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-subdev.h>
+
+#define OV2680_XVCLK_VALUE	24000000
+
+#define OV2680_CHIP_ID		0x2680
+
+#define OV2680_REG_STREAM_CTRL		0x0100
+#define OV2680_REG_SOFT_RESET		0x0103
+
+#define OV2680_REG_CHIP_ID_HIGH		0x300a
+#define OV2680_REG_CHIP_ID_LOW		0x300b
+
+#define OV2680_REG_R_MANUAL		0x3503
+#define OV2680_REG_GAIN_PK		0x350a
+#define OV2680_REG_EXPOSURE_PK_HIGH	0x3500
+#define OV2680_REG_TIMING_HTS		0x380c
+#define OV2680_REG_TIMING_VTS		0x380e
+#define OV2680_REG_FORMAT1		0x3820
+#define OV2680_REG_FORMAT2		0x3821
+
+#define OV2680_REG_ISP_CTRL00		0x5080
+
+#define OV2680_FRAME_RATE		30
+
+#define OV2680_REG_VALUE_8BIT		1
+#define OV2680_REG_VALUE_16BIT		2
+#define OV2680_REG_VALUE_24BIT		3
+
+#define OV2680_WIDTH_MAX		1600
+#define OV2680_HEIGHT_MAX		1200
+
+enum ov2680_mode_id {
+	OV2680_MODE_QUXGA_800_600,
+	OV2680_MODE_720P_1280_720,
+	OV2680_MODE_UXGA_1600_1200,
+	OV2680_MODE_MAX,
+};
+
+struct reg_value {
+	u16 reg_addr;
+	u8 val;
+};
+
+static const char * const ov2680_supply_name[] = {
+	"DOVDD",
+	"DVDD",
+	"AVDD",
+};
+
+#define OV2680_NUM_SUPPLIES ARRAY_SIZE(ov2680_supply_name)
+
+struct ov2680_mode_info {
+	const char *name;
+	enum ov2680_mode_id id;
+	u32 width;
+	u32 height;
+	const struct reg_value *reg_data;
+	u32 reg_data_size;
+};
+
+struct ov2680_ctrls {
+	struct v4l2_ctrl_handler handler;
+	struct {
+		struct v4l2_ctrl *auto_exp;
+		struct v4l2_ctrl *exposure;
+	};
+	struct {
+		struct v4l2_ctrl *auto_gain;
+		struct v4l2_ctrl *gain;
+	};
+
+	struct v4l2_ctrl *hflip;
+	struct v4l2_ctrl *vflip;
+	struct v4l2_ctrl *test_pattern;
+};
+
+struct ov2680_dev {
+	struct i2c_client		*i2c_client;
+	struct v4l2_subdev		sd;
+
+	struct media_pad		pad;
+	struct clk			*xvclk;
+	u32				xvclk_freq;
+	struct regulator_bulk_data	supplies[OV2680_NUM_SUPPLIES];
+
+	struct gpio_desc		*reset_gpio;
+	struct mutex			lock; /* protect members */
+
+	bool				mode_pending_changes;
+	bool				is_enabled;
+	bool				is_streaming;
+
+	struct ov2680_ctrls		ctrls;
+	struct v4l2_mbus_framefmt	fmt;
+	struct v4l2_fract		frame_interval;
+
+	const struct ov2680_mode_info	*current_mode;
+};
+
+static const char * const test_pattern_menu[] = {
+	"Disabled",
+	"Color Bars",
+	"Random Data",
+	"Square",
+	"Black Image",
+};
+
+static const int ov2680_hv_flip_bayer_order[] = {
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+};
+
+static const struct reg_value ov2680_setting_30fps_QUXGA_800_600[] = {
+	{0x3086, 0x01}, {0x370a, 0x23}, {0x3808, 0x03}, {0x3809, 0x20},
+	{0x380a, 0x02}, {0x380b, 0x58}, {0x380c, 0x06}, {0x380d, 0xac},
+	{0x380e, 0x02}, {0x380f, 0x84}, {0x3811, 0x04}, {0x3813, 0x04},
+	{0x3814, 0x31}, {0x3815, 0x31}, {0x3820, 0xc0}, {0x4008, 0x00},
+	{0x4009, 0x03}, {0x4837, 0x1e}, {0x3501, 0x4e}, {0x3502, 0xe0},
+};
+
+static const struct reg_value ov2680_setting_30fps_720P_1280_720[] = {
+	{0x3086, 0x00}, {0x3808, 0x05}, {0x3809, 0x00}, {0x380a, 0x02},
+	{0x380b, 0xd0}, {0x380c, 0x06}, {0x380d, 0xa8}, {0x380e, 0x05},
+	{0x380f, 0x0e}, {0x3811, 0x08}, {0x3813, 0x06}, {0x3814, 0x11},
+	{0x3815, 0x11}, {0x3820, 0xc0}, {0x4008, 0x00},
+};
+
+static const struct reg_value ov2680_setting_30fps_UXGA_1600_1200[] = {
+	{0x3086, 0x00}, {0x3501, 0x4e}, {0x3502, 0xe0}, {0x3808, 0x06},
+	{0x3809, 0x40}, {0x380a, 0x04}, {0x380b, 0xb0}, {0x380c, 0x06},
+	{0x380d, 0xa8}, {0x380e, 0x05}, {0x380f, 0x0e}, {0x3811, 0x00},
+	{0x3813, 0x00}, {0x3814, 0x11}, {0x3815, 0x11}, {0x3820, 0xc0},
+	{0x4008, 0x00}, {0x4837, 0x18}
+};
+
+static const struct ov2680_mode_info ov2680_mode_init_data = {
+	"mode_quxga_800_600", OV2680_MODE_QUXGA_800_600, 800, 600,
+	ov2680_setting_30fps_QUXGA_800_600,
+	ARRAY_SIZE(ov2680_setting_30fps_QUXGA_800_600),
+};
+
+static const struct ov2680_mode_info ov2680_mode_data[OV2680_MODE_MAX] = {
+	{"mode_quxga_800_600", OV2680_MODE_QUXGA_800_600,
+	 800, 600, ov2680_setting_30fps_QUXGA_800_600,
+	 ARRAY_SIZE(ov2680_setting_30fps_QUXGA_800_600)},
+	{"mode_720p_1280_720", OV2680_MODE_720P_1280_720,
+	 1280, 720, ov2680_setting_30fps_720P_1280_720,
+	 ARRAY_SIZE(ov2680_setting_30fps_720P_1280_720)},
+	{"mode_uxga_1600_1200", OV2680_MODE_UXGA_1600_1200,
+	 1600, 1200, ov2680_setting_30fps_UXGA_1600_1200,
+	 ARRAY_SIZE(ov2680_setting_30fps_UXGA_1600_1200)},
+};
+
+static struct ov2680_dev *to_ov2680_dev(struct v4l2_subdev *sd)
+{
+	return container_of(sd, struct ov2680_dev, sd);
+}
+
+static struct device *ov2680_to_dev(struct ov2680_dev *sensor)
+{
+	return &sensor->i2c_client->dev;
+}
+
+static inline struct v4l2_subdev *ctrl_to_sd(struct v4l2_ctrl *ctrl)
+{
+	return &container_of(ctrl->handler, struct ov2680_dev,
+			     ctrls.handler)->sd;
+}
+
+static int __ov2680_write_reg(struct ov2680_dev *sensor, u16 reg,
+			      unsigned int len, u32 val)
+{
+	struct i2c_client *client = sensor->i2c_client;
+	u8 buf[6];
+	int ret;
+
+	if (len > 4)
+		return -EINVAL;
+
+	put_unaligned_be16(reg, buf);
+	put_unaligned_be32(val << (8 * (4 - len)), buf + 2);
+	ret = i2c_master_send(client, buf, len + 2);
+	if (ret != len + 2) {
+		dev_err(&client->dev, "write error: reg=0x%4x: %d\n", reg, ret);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+#define ov2680_write_reg(s, r, v) \
+	__ov2680_write_reg(s, r, OV2680_REG_VALUE_8BIT, v)
+
+#define ov2680_write_reg16(s, r, v) \
+	__ov2680_write_reg(s, r, OV2680_REG_VALUE_16BIT, v)
+
+#define ov2680_write_reg24(s, r, v) \
+	__ov2680_write_reg(s, r, OV2680_REG_VALUE_24BIT, v)
+
+static int __ov2680_read_reg(struct ov2680_dev *sensor, u16 reg,
+			     unsigned int len, u32 *val)
+{
+	struct i2c_client *client = sensor->i2c_client;
+	struct i2c_msg msgs[2];
+	u8 addr_buf[2] = { reg >> 8, reg & 0xff };
+	u8 data_buf[4] = { 0, };
+	int ret;
+
+	if (len > 4)
+		return -EINVAL;
+
+	msgs[0].addr = client->addr;
+	msgs[0].flags = 0;
+	msgs[0].len = ARRAY_SIZE(addr_buf);
+	msgs[0].buf = addr_buf;
+
+	msgs[1].addr = client->addr;
+	msgs[1].flags = I2C_M_RD;
+	msgs[1].len = len;
+	msgs[1].buf = &data_buf[4 - len];
+
+	ret = i2c_transfer(client->adapter, msgs, ARRAY_SIZE(msgs));
+	if (ret != ARRAY_SIZE(msgs)) {
+		dev_err(&client->dev, "read error: reg=0x%4x: %d\n", reg, ret);
+		return -EIO;
+	}
+
+	*val = get_unaligned_be32(data_buf);
+
+	return 0;
+}
+
+#define ov2680_read_reg(s, r, v) \
+	__ov2680_read_reg(s, r, OV2680_REG_VALUE_8BIT, v)
+
+#define ov2680_read_reg16(s, r, v) \
+	__ov2680_read_reg(s, r, OV2680_REG_VALUE_16BIT, v)
+
+#define ov2680_read_reg24(s, r, v) \
+	__ov2680_read_reg(s, r, OV2680_REG_VALUE_24BIT, v)
+
+static int ov2680_mod_reg(struct ov2680_dev *sensor, u16 reg, u8 mask, u8 val)
+{
+	u32 readval;
+	int ret;
+
+	ret = ov2680_read_reg(sensor, reg, &readval);
+	if (ret < 0)
+		return ret;
+
+	readval &= ~mask;
+	val &= mask;
+	val |= readval;
+
+	return ov2680_write_reg(sensor, reg, val);
+}
+
+static int ov2680_load_regs(struct ov2680_dev *sensor,
+			    const struct ov2680_mode_info *mode)
+{
+	const struct reg_value *regs = mode->reg_data;
+	unsigned int i;
+	int ret = 0;
+	u16 reg_addr;
+	u8 val;
+
+	for (i = 0; i < mode->reg_data_size; ++i, ++regs) {
+		reg_addr = regs->reg_addr;
+		val = regs->val;
+
+		ret = ov2680_write_reg(sensor, reg_addr, val);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
+static void ov2680_power_up(struct ov2680_dev *sensor)
+{
+	if (!sensor->reset_gpio)
+		return;
+
+	gpiod_set_value(sensor->reset_gpio, 0);
+	usleep_range(5000, 10000);
+}
+
+static void ov2680_power_down(struct ov2680_dev *sensor)
+{
+	if (!sensor->reset_gpio)
+		return;
+
+	gpiod_set_value(sensor->reset_gpio, 1);
+	usleep_range(5000, 10000);
+}
+
+static int ov2680_bayer_order(struct ov2680_dev *sensor)
+{
+	u32 format1;
+	u32 format2;
+	u32 hv_flip;
+	int ret;
+
+	ret = ov2680_read_reg(sensor, OV2680_REG_FORMAT1, &format1);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_read_reg(sensor, OV2680_REG_FORMAT2, &format2);
+	if (ret < 0)
+		return ret;
+
+	hv_flip = (format2 & BIT(2)  << 1) | (format1 & BIT(2));
+
+	sensor->fmt.code = ov2680_hv_flip_bayer_order[hv_flip];
+
+	return 0;
+}
+
+static int ov2680_vflip_enable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT1, BIT(2), BIT(2));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_vflip_disable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT1, BIT(2), BIT(0));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_hflip_enable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT2, BIT(2), BIT(2));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_hflip_disable(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_FORMAT2, BIT(2), BIT(0));
+	if (ret < 0)
+		return ret;
+
+	return ov2680_bayer_order(sensor);
+}
+
+static int ov2680_test_pattern_set(struct ov2680_dev *sensor, int value)
+{
+	int ret;
+
+	if (!value)
+		return ov2680_mod_reg(sensor, OV2680_REG_ISP_CTRL00, BIT(7), 0);
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_ISP_CTRL00, 0x03, value - 1);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_ISP_CTRL00, BIT(7), BIT(7));
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int ov2680_gain_set(struct ov2680_dev *sensor, bool auto_gain)
+{
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	u32 gain;
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_R_MANUAL, BIT(1),
+			     auto_gain ? 0 : BIT(1));
+	if (ret < 0)
+		return ret;
+
+	if (auto_gain || !ctrls->gain->is_new)
+		return 0;
+
+	gain = ctrls->gain->val;
+
+	ret = ov2680_write_reg16(sensor, OV2680_REG_GAIN_PK, gain);
+
+	return 0;
+}
+
+static int ov2680_gain_get(struct ov2680_dev *sensor)
+{
+	u32 gain;
+	int ret;
+
+	ret = ov2680_read_reg16(sensor, OV2680_REG_GAIN_PK, &gain);
+	if (ret)
+		return ret;
+
+	return gain;
+}
+
+static int ov2680_exposure_set(struct ov2680_dev *sensor, bool auto_exp)
+{
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	u32 exp;
+	int ret;
+
+	ret = ov2680_mod_reg(sensor, OV2680_REG_R_MANUAL, BIT(0),
+			     auto_exp ? 0 : BIT(0));
+	if (ret < 0)
+		return ret;
+
+	if (auto_exp || !ctrls->exposure->is_new)
+		return 0;
+
+	exp = (u32)ctrls->exposure->val;
+	exp <<= 4;
+
+	return ov2680_write_reg24(sensor, OV2680_REG_EXPOSURE_PK_HIGH, exp);
+}
+
+static int ov2680_exposure_get(struct ov2680_dev *sensor)
+{
+	int ret;
+	u32 exp;
+
+	ret = ov2680_read_reg24(sensor, OV2680_REG_EXPOSURE_PK_HIGH, &exp);
+	if (ret)
+		return ret;
+
+	return exp >> 4;
+}
+
+static int ov2680_stream_enable(struct ov2680_dev *sensor)
+{
+	return ov2680_write_reg(sensor, OV2680_REG_STREAM_CTRL, 1);
+}
+
+static int ov2680_stream_disable(struct ov2680_dev *sensor)
+{
+	return ov2680_write_reg(sensor, OV2680_REG_STREAM_CTRL, 0);
+}
+
+static int ov2680_mode_set(struct ov2680_dev *sensor)
+{
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	int ret;
+
+	ret = ov2680_gain_set(sensor, false);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_exposure_set(sensor, false);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_load_regs(sensor, sensor->current_mode);
+	if (ret < 0)
+		return ret;
+
+	if (ctrls->auto_gain->val) {
+		ret = ov2680_gain_set(sensor, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	if (ctrls->auto_exp->val == V4L2_EXPOSURE_AUTO) {
+		ret = ov2680_exposure_set(sensor, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	sensor->mode_pending_changes = false;
+
+	return 0;
+}
+
+static int ov2680_mode_restore(struct ov2680_dev *sensor)
+{
+	int ret;
+
+	ret = ov2680_load_regs(sensor, &ov2680_mode_init_data);
+	if (ret < 0)
+		return ret;
+
+	return ov2680_mode_set(sensor);
+}
+
+static int ov2680_power_off(struct ov2680_dev *sensor)
+{
+	if (!sensor->is_enabled)
+		return 0;
+
+	clk_disable_unprepare(sensor->xvclk);
+	ov2680_power_down(sensor);
+	regulator_bulk_disable(OV2680_NUM_SUPPLIES, sensor->supplies);
+	sensor->is_enabled = false;
+
+	return 0;
+}
+
+static int ov2680_power_on(struct ov2680_dev *sensor)
+{
+	struct device *dev = ov2680_to_dev(sensor);
+	int ret;
+
+	if (sensor->is_enabled)
+		return 0;
+
+	ret = regulator_bulk_enable(OV2680_NUM_SUPPLIES, sensor->supplies);
+	if (ret < 0) {
+		dev_err(dev, "failed to enable regulators: %d\n", ret);
+		return ret;
+	}
+
+	if (!sensor->reset_gpio) {
+		ret = ov2680_write_reg(sensor, OV2680_REG_SOFT_RESET, 0x01);
+		if (ret != 0) {
+			dev_err(dev, "sensor soft reset failed\n");
+			return ret;
+		}
+		usleep_range(1000, 2000);
+	} else {
+		ov2680_power_down(sensor);
+		ov2680_power_up(sensor);
+	}
+
+	ret = clk_prepare_enable(sensor->xvclk);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_mode_restore(sensor);
+	if (ret < 0)
+		goto disable;
+
+	sensor->is_enabled = true;
+
+	/* Set clock lane into LP-11 state */
+	ov2680_stream_enable(sensor);
+	usleep_range(1000, 2000);
+	ov2680_stream_disable(sensor);
+
+	return 0;
+
+disable:
+	dev_err(dev, "failed to enable sensor: %d\n", ret);
+	ov2680_power_off(sensor);
+
+	return ret;
+}
+
+static int ov2680_s_power(struct v4l2_subdev *sd, int on)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	int ret = 0;
+
+	mutex_lock(&sensor->lock);
+
+	if (on)
+		ret = ov2680_power_on(sensor);
+	else
+		ret = ov2680_power_off(sensor);
+
+	mutex_unlock(&sensor->lock);
+
+	if (on && ret == 0) {
+		ret = v4l2_ctrl_handler_setup(&sensor->ctrls.handler);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int ov2680_s_g_frame_interval(struct v4l2_subdev *sd,
+				     struct v4l2_subdev_frame_interval *fi)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	mutex_lock(&sensor->lock);
+	fi->interval = sensor->frame_interval;
+	mutex_unlock(&sensor->lock);
+
+	return 0;
+}
+
+static int ov2680_s_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	int ret = 0;
+
+	mutex_lock(&sensor->lock);
+
+	if (sensor->is_streaming == !!enable)
+		goto unlock;
+
+	if (enable && sensor->mode_pending_changes) {
+		ret = ov2680_mode_set(sensor);
+		if (ret < 0)
+			goto unlock;
+	}
+
+	if (enable)
+		ret = ov2680_stream_enable(sensor);
+	else
+		ret = ov2680_stream_disable(sensor);
+
+	sensor->is_streaming = !!enable;
+
+unlock:
+	mutex_unlock(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_enum_mbus_code(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_pad_config *cfg,
+				 struct v4l2_subdev_mbus_code_enum *code)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	if (code->pad != 0 || code->index != 0)
+		return -EINVAL;
+
+	code->code = sensor->fmt.code;
+
+	return 0;
+}
+
+static int ov2680_get_fmt(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *format)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct v4l2_mbus_framefmt *fmt = NULL;
+	int ret = 0;
+
+	if (format->pad != 0)
+		return -EINVAL;
+
+	mutex_lock(&sensor->lock);
+
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+		fmt = v4l2_subdev_get_try_format(&sensor->sd, cfg, format->pad);
+#else
+		ret = -ENOTTY;
+#endif
+	} else {
+		fmt = &sensor->fmt;
+	}
+
+	if (fmt)
+		format->format = *fmt;
+
+	mutex_unlock(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_set_fmt(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *format)
+{
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct v4l2_mbus_framefmt *fmt = &format->format;
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+	struct v4l2_mbus_framefmt *try_fmt;
+#endif
+	const struct ov2680_mode_info *mode;
+	int ret = 0;
+
+	if (format->pad != 0)
+		return -EINVAL;
+
+	mutex_lock(&sensor->lock);
+
+	if (sensor->is_streaming) {
+		ret = -EBUSY;
+		goto unlock;
+	}
+
+	mode = v4l2_find_nearest_size(ov2680_mode_data,
+				      ARRAY_SIZE(ov2680_mode_data), width,
+				      height, fmt->width, fmt->height);
+	if (!mode) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	if (format->which == V4L2_SUBDEV_FORMAT_TRY) {
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+		try_fmt = v4l2_subdev_get_try_format(sd, cfg, 0);
+		format->format = *try_fmt;
+#else
+		ret = -ENOTTY;
+#endif
+
+		goto unlock;
+	}
+
+	fmt->width = mode->width;
+	fmt->height = mode->height;
+	fmt->code = sensor->fmt.code;
+	fmt->colorspace = sensor->fmt.colorspace;
+
+	sensor->current_mode = mode;
+	sensor->fmt = format->format;
+	sensor->mode_pending_changes = true;
+
+unlock:
+	mutex_unlock(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_init_cfg(struct v4l2_subdev *sd,
+			   struct v4l2_subdev_pad_config *cfg)
+{
+	struct v4l2_subdev_format fmt = {
+		.which = cfg ? V4L2_SUBDEV_FORMAT_TRY
+				: V4L2_SUBDEV_FORMAT_ACTIVE,
+		.format = {
+			.width = 800,
+			.height = 600,
+		}
+	};
+
+	return ov2680_set_fmt(sd, cfg, &fmt);
+}
+
+static int ov2680_enum_frame_size(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_pad_config *cfg,
+				  struct v4l2_subdev_frame_size_enum *fse)
+{
+	int index = fse->index;
+
+	if (index >= OV2680_MODE_MAX || index < 0)
+		return -EINVAL;
+
+	fse->min_width = ov2680_mode_data[index].width;
+	fse->min_height = ov2680_mode_data[index].height;
+	fse->max_width = ov2680_mode_data[index].width;
+	fse->max_height = ov2680_mode_data[index].height;
+
+	return 0;
+}
+
+static int ov2680_enum_frame_interval(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_frame_interval_enum *fie)
+{
+	struct v4l2_fract tpf;
+
+	if (fie->index >= OV2680_MODE_MAX || fie->width > OV2680_WIDTH_MAX ||
+	    fie->height > OV2680_HEIGHT_MAX ||
+	    fie->which > V4L2_SUBDEV_FORMAT_ACTIVE)
+		return -EINVAL;
+
+	tpf.denominator = OV2680_FRAME_RATE;
+	tpf.numerator = 1;
+
+	fie->interval = tpf;
+
+	return 0;
+}
+
+static int ov2680_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd = ctrl_to_sd(ctrl);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	int val;
+
+	if (!sensor->is_enabled)
+		return 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_GAIN:
+		val = ov2680_gain_get(sensor);
+		if (val < 0)
+			return val;
+		ctrls->gain->val = val;
+		break;
+	case V4L2_CID_EXPOSURE:
+		val = ov2680_exposure_get(sensor);
+		if (val < 0)
+			return val;
+		ctrls->exposure->val = val;
+		break;
+	}
+
+	return 0;
+}
+
+static int ov2680_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct v4l2_subdev *sd = ctrl_to_sd(ctrl);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+
+	if (!sensor->is_enabled)
+		return 0;
+
+	switch (ctrl->id) {
+	case V4L2_CID_AUTOGAIN:
+		return ov2680_gain_set(sensor, !!ctrl->val);
+	case V4L2_CID_GAIN:
+		return ov2680_gain_set(sensor, !!ctrls->auto_gain->val);
+	case V4L2_CID_EXPOSURE_AUTO:
+		return ov2680_exposure_set(sensor, !!ctrl->val);
+	case V4L2_CID_EXPOSURE:
+		return ov2680_exposure_set(sensor, !!ctrls->auto_exp->val);
+	case V4L2_CID_VFLIP:
+		if (sensor->is_streaming)
+			return -EBUSY;
+		if (ctrl->val)
+			return ov2680_vflip_enable(sensor);
+		else
+			return ov2680_vflip_disable(sensor);
+	case V4L2_CID_HFLIP:
+		if (sensor->is_streaming)
+			return -EBUSY;
+		if (ctrl->val)
+			return ov2680_hflip_enable(sensor);
+		else
+			return ov2680_hflip_disable(sensor);
+	case V4L2_CID_TEST_PATTERN:
+		return ov2680_test_pattern_set(sensor, ctrl->val);
+	default:
+		break;
+	}
+
+	return -EINVAL;
+}
+
+static const struct v4l2_ctrl_ops ov2680_ctrl_ops = {
+	.g_volatile_ctrl = ov2680_g_volatile_ctrl,
+	.s_ctrl = ov2680_s_ctrl,
+};
+
+static const struct v4l2_subdev_core_ops ov2680_core_ops = {
+	.s_power = ov2680_s_power,
+};
+
+static const struct v4l2_subdev_video_ops ov2680_video_ops = {
+	.g_frame_interval	= ov2680_s_g_frame_interval,
+	.s_frame_interval	= ov2680_s_g_frame_interval,
+	.s_stream		= ov2680_s_stream,
+};
+
+static const struct v4l2_subdev_pad_ops ov2680_pad_ops = {
+	.init_cfg		= ov2680_init_cfg,
+	.enum_mbus_code		= ov2680_enum_mbus_code,
+	.get_fmt		= ov2680_get_fmt,
+	.set_fmt		= ov2680_set_fmt,
+	.enum_frame_size	= ov2680_enum_frame_size,
+	.enum_frame_interval	= ov2680_enum_frame_interval,
+};
+
+static const struct v4l2_subdev_ops ov2680_subdev_ops = {
+	.core	= &ov2680_core_ops,
+	.video	= &ov2680_video_ops,
+	.pad	= &ov2680_pad_ops,
+};
+
+static int ov2680_mode_init(struct ov2680_dev *sensor)
+{
+	const struct ov2680_mode_info *init_mode;
+
+	/* set initial mode */
+	sensor->fmt.code = MEDIA_BUS_FMT_SBGGR10_1X10;
+	sensor->fmt.width = 800;
+	sensor->fmt.height = 600;
+	sensor->fmt.field = V4L2_FIELD_NONE;
+	sensor->fmt.colorspace = V4L2_COLORSPACE_SRGB;
+
+	sensor->frame_interval.denominator = OV2680_FRAME_RATE;
+	sensor->frame_interval.numerator = 1;
+
+	init_mode = &ov2680_mode_init_data;
+
+	sensor->current_mode = init_mode;
+
+	sensor->mode_pending_changes = true;
+
+	return 0;
+}
+
+static int ov2680_v4l2_init(struct ov2680_dev *sensor)
+{
+	const struct v4l2_ctrl_ops *ops = &ov2680_ctrl_ops;
+	struct ov2680_ctrls *ctrls = &sensor->ctrls;
+	struct v4l2_ctrl_handler *hdl = &ctrls->handler;
+	int ret = 0;
+
+	v4l2_i2c_subdev_init(&sensor->sd, sensor->i2c_client,
+			     &ov2680_subdev_ops);
+
+#ifdef CONFIG_VIDEO_V4L2_SUBDEV_API
+	sensor->sd.flags = V4L2_SUBDEV_FL_HAS_DEVNODE;
+#endif
+	sensor->pad.flags = MEDIA_PAD_FL_SOURCE;
+	sensor->sd.entity.function = MEDIA_ENT_F_CAM_SENSOR;
+
+	ret = media_entity_pads_init(&sensor->sd.entity, 1, &sensor->pad);
+	if (ret < 0)
+		return ret;
+
+	v4l2_ctrl_handler_init(hdl, 7);
+
+	hdl->lock = &sensor->lock;
+
+	ctrls->vflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_VFLIP, 0, 1, 1, 0);
+	ctrls->hflip = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_HFLIP, 0, 1, 1, 0);
+
+	ctrls->test_pattern = v4l2_ctrl_new_std_menu_items(hdl,
+					&ov2680_ctrl_ops, V4L2_CID_TEST_PATTERN,
+					ARRAY_SIZE(test_pattern_menu) - 1,
+					0, 0, test_pattern_menu);
+
+	ctrls->auto_exp = v4l2_ctrl_new_std_menu(hdl, ops,
+						 V4L2_CID_EXPOSURE_AUTO,
+						 V4L2_EXPOSURE_MANUAL, 0,
+						 V4L2_EXPOSURE_AUTO);
+
+	ctrls->exposure = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_EXPOSURE,
+					    0, 32767, 1, 0);
+
+	ctrls->auto_gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_AUTOGAIN,
+					     0, 1, 1, 1);
+	ctrls->gain = v4l2_ctrl_new_std(hdl, ops, V4L2_CID_GAIN, 0, 2047, 1, 0);
+
+	if (hdl->error) {
+		ret = hdl->error;
+		goto cleanup_entity;
+	}
+
+	ctrls->gain->flags |= V4L2_CTRL_FLAG_VOLATILE;
+	ctrls->exposure->flags |= V4L2_CTRL_FLAG_VOLATILE;
+
+	v4l2_ctrl_auto_cluster(2, &ctrls->auto_gain, 0, true);
+	v4l2_ctrl_auto_cluster(2, &ctrls->auto_exp, 1, true);
+
+	sensor->sd.ctrl_handler = hdl;
+
+	ret = v4l2_async_register_subdev(&sensor->sd);
+	if (ret < 0)
+		goto cleanup_entity;
+
+	return 0;
+
+cleanup_entity:
+	media_entity_cleanup(&sensor->sd.entity);
+	v4l2_ctrl_handler_free(hdl);
+
+	return ret;
+}
+
+static int ov2680_get_regulators(struct ov2680_dev *sensor)
+{
+	int i;
+
+	for (i = 0; i < OV2680_NUM_SUPPLIES; i++)
+		sensor->supplies[i].supply = ov2680_supply_name[i];
+
+	return devm_regulator_bulk_get(&sensor->i2c_client->dev,
+				       OV2680_NUM_SUPPLIES,
+				       sensor->supplies);
+}
+
+static int ov2680_check_id(struct ov2680_dev *sensor)
+{
+	struct device *dev = ov2680_to_dev(sensor);
+	u32 chip_id;
+	int ret;
+
+	ov2680_power_on(sensor);
+
+	ret = ov2680_read_reg16(sensor, OV2680_REG_CHIP_ID_HIGH, &chip_id);
+	if (ret < 0) {
+		dev_err(dev, "failed to read chip id high\n");
+		return -ENODEV;
+	}
+
+	if (chip_id != OV2680_CHIP_ID) {
+		dev_err(dev, "chip id: 0x%04x does not match expected 0x%04x\n",
+			chip_id, OV2680_CHIP_ID);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int ov2860_parse_dt(struct ov2680_dev *sensor)
+{
+	struct device *dev = ov2680_to_dev(sensor);
+	int ret;
+
+	sensor->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						     GPIOD_OUT_HIGH);
+	ret = PTR_ERR_OR_ZERO(sensor->reset_gpio);
+	if (ret < 0) {
+		dev_dbg(dev, "error while getting reset gpio: %d\n", ret);
+		return ret;
+	}
+
+	sensor->xvclk = devm_clk_get(dev, "xvclk");
+	if (IS_ERR(sensor->xvclk)) {
+		dev_err(dev, "xvclk clock missing or invalid\n");
+		return PTR_ERR(sensor->xvclk);
+	}
+
+	sensor->xvclk_freq = clk_get_rate(sensor->xvclk);
+	if (sensor->xvclk_freq != OV2680_XVCLK_VALUE) {
+		dev_err(dev, "wrong xvclk frequency %d HZ, expected: %d Hz\n",
+			sensor->xvclk_freq, OV2680_XVCLK_VALUE);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ov2680_probe(struct i2c_client *client)
+{
+	struct device *dev = &client->dev;
+	struct ov2680_dev *sensor;
+	int ret;
+
+	sensor = devm_kzalloc(dev, sizeof(*sensor), GFP_KERNEL);
+	if (!sensor)
+		return -ENOMEM;
+
+	sensor->i2c_client = client;
+
+	ret = ov2860_parse_dt(sensor);
+	if (ret < 0)
+		return -EINVAL;
+
+	ret = ov2680_mode_init(sensor);
+	if (ret < 0)
+		return ret;
+
+	ret = ov2680_get_regulators(sensor);
+	if (ret < 0) {
+		dev_err(dev, "failed to get regulators\n");
+		return ret;
+	}
+
+	mutex_init(&sensor->lock);
+
+	ret = ov2680_v4l2_init(sensor);
+	if (ret < 0)
+		goto lock_destroy;
+
+	ret = ov2680_check_id(sensor);
+	if (ret < 0)
+		goto error_cleanup;
+
+	dev_info(dev, "ov2680 init correctly\n");
+
+	return 0;
+
+error_cleanup:
+	dev_err(dev, "ov2680 init fail: %d\n", ret);
+
+	media_entity_cleanup(&sensor->sd.entity);
+	v4l2_async_unregister_subdev(&sensor->sd);
+	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
+
+lock_destroy:
+	mutex_destroy(&sensor->lock);
+
+	return ret;
+}
+
+static int ov2680_remove(struct i2c_client *client)
+{
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	v4l2_async_unregister_subdev(&sensor->sd);
+	mutex_destroy(&sensor->lock);
+	media_entity_cleanup(&sensor->sd.entity);
+	v4l2_ctrl_handler_free(&sensor->ctrls.handler);
+
+	return 0;
+}
+
+static int __maybe_unused ov2680_suspend(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+
+	if (sensor->is_streaming)
+		ov2680_stream_disable(sensor);
+
+	return 0;
+}
+
+static int __maybe_unused ov2680_resume(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct v4l2_subdev *sd = i2c_get_clientdata(client);
+	struct ov2680_dev *sensor = to_ov2680_dev(sd);
+	int ret;
+
+	if (sensor->is_streaming) {
+		ret = ov2680_stream_enable(sensor);
+		if (ret < 0)
+			goto stream_disable;
+	}
+
+	return 0;
+
+stream_disable:
+	ov2680_stream_disable(sensor);
+	sensor->is_streaming = false;
+
+	return ret;
+}
+
+static const struct dev_pm_ops ov2680_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(ov2680_suspend, ov2680_resume)
+};
+
+static const struct of_device_id ov2680_dt_ids[] = {
+	{ .compatible = "ovti,ov2680" },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, ov2680_dt_ids);
+
+static struct i2c_driver ov2680_i2c_driver = {
+	.driver = {
+		.name  = "ov2680",
+		.pm = &ov2680_pm_ops,
+		.of_match_table	= of_match_ptr(ov2680_dt_ids),
+	},
+	.probe_new	= ov2680_probe,
+	.remove		= ov2680_remove,
+};
+module_i2c_driver(ov2680_i2c_driver);
+
+MODULE_AUTHOR("Rui Miguel Silva <rui.silva@linaro.org>");
+MODULE_DESCRIPTION("OV2680 CMOS Image Sensor driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 279b4b9aaa3d04ea8de960e39e54e38aafe93e62 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Wed, 25 Jul 2018 12:24:54 -0400
Subject: media: imx274: use regmap_bulk_write to write multybyte registers

Currently 2-bytes and 3-bytes registers are set by very similar
functions doing the needed shift & mask manipulation, followed by very
similar for loops setting one byte at a time over I2C.

Replace all of this code by a unique helper function that calls
regmap_bulk_write(), which has two advantages:
 - sets all the bytes in a unique I2C transaction
 - removes lots of now unused code.

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 102 +++++++++++++++++----------------------------
 1 file changed, 39 insertions(+), 63 deletions(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index edca63eaea9b..093c4587832a 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -690,6 +690,35 @@ static inline int imx274_write_reg(struct stimx274 *priv, u16 addr, u8 val)
 	return err;
 }
 
+/**
+ * Write a multibyte register.
+ *
+ * Uses a bulk write where possible.
+ *
+ * @priv: Pointer to device structure
+ * @addr: Address of the LSB register.  Other registers must be
+ *        consecutive, least-to-most significant.
+ * @val: Value to be written to the register (cpu endianness)
+ * @nbytes: Number of bits to write (range: [1..3])
+ */
+static int imx274_write_mbreg(struct stimx274 *priv, u16 addr, u32 val,
+			      size_t nbytes)
+{
+	__le32 val_le = cpu_to_le32(val);
+	int err;
+
+	err = regmap_bulk_write(priv->regmap, addr, &val_le, nbytes);
+	if (err)
+		dev_err(&priv->client->dev,
+			"%s : i2c bulk write failed, %x = %x (%zu bytes)\n",
+			__func__, addr, val, nbytes);
+	else
+		dev_dbg(&priv->client->dev,
+			"%s : addr 0x%x, val=0x%x (%zu bytes)\n",
+			__func__, addr, val, nbytes);
+	return err;
+}
+
 /*
  * Set mode registers to start stream.
  * @priv: Pointer to device structure
@@ -1163,15 +1192,6 @@ static int imx274_set_digital_gain(struct stimx274 *priv, u32 dgain)
 				reg_val & IMX274_MASK_LSB_4_BITS);
 }
 
-static inline void imx274_calculate_gain_regs(struct reg_8 regs[2], u16 gain)
-{
-	regs->addr = IMX274_ANALOG_GAIN_ADDR_MSB;
-	regs->val = (gain >> IMX274_SHIFT_8_BITS) & IMX274_MASK_LSB_3_BITS;
-
-	(regs + 1)->addr = IMX274_ANALOG_GAIN_ADDR_LSB;
-	(regs + 1)->val = (gain) & IMX274_MASK_LSB_8_BITS;
-}
-
 /*
  * imx274_set_gain - Function called when setting gain
  * @priv: Pointer to device structure
@@ -1185,10 +1205,8 @@ static inline void imx274_calculate_gain_regs(struct reg_8 regs[2], u16 gain)
  */
 static int imx274_set_gain(struct stimx274 *priv, struct v4l2_ctrl *ctrl)
 {
-	struct reg_8 reg_list[2];
 	int err;
 	u32 gain, analog_gain, digital_gain, gain_reg;
-	int i;
 
 	gain = (u32)(ctrl->val);
 
@@ -1229,14 +1247,10 @@ static int imx274_set_gain(struct stimx274 *priv, struct v4l2_ctrl *ctrl)
 	if (gain_reg > IMX274_GAIN_REG_MAX)
 		gain_reg = IMX274_GAIN_REG_MAX;
 
-	imx274_calculate_gain_regs(reg_list, (u16)gain_reg);
-
-	for (i = 0; i < ARRAY_SIZE(reg_list); i++) {
-		err = imx274_write_reg(priv, reg_list[i].addr,
-				       reg_list[i].val);
-		if (err)
-			goto fail;
-	}
+	err = imx274_write_mbreg(priv, IMX274_ANALOG_GAIN_ADDR_LSB, gain_reg,
+				 2);
+	if (err)
+		goto fail;
 
 	if (IMX274_GAIN_CONST - gain_reg == 0) {
 		err = -EINVAL;
@@ -1258,16 +1272,6 @@ fail:
 	return err;
 }
 
-static inline void imx274_calculate_coarse_time_regs(struct reg_8 regs[2],
-						     u32 coarse_time)
-{
-	regs->addr = IMX274_SHR_REG_MSB;
-	regs->val = (coarse_time >> IMX274_SHIFT_8_BITS)
-			& IMX274_MASK_LSB_8_BITS;
-	(regs + 1)->addr = IMX274_SHR_REG_LSB;
-	(regs + 1)->val = (coarse_time) & IMX274_MASK_LSB_8_BITS;
-}
-
 /*
  * imx274_set_coarse_time - Function called when setting SHR value
  * @priv: Pointer to device structure
@@ -1279,10 +1283,8 @@ static inline void imx274_calculate_coarse_time_regs(struct reg_8 regs[2],
  */
 static int imx274_set_coarse_time(struct stimx274 *priv, u32 *val)
 {
-	struct reg_8 reg_list[2];
 	int err;
 	u32 coarse_time, frame_length;
-	int i;
 
 	coarse_time = *val;
 
@@ -1291,16 +1293,9 @@ static int imx274_set_coarse_time(struct stimx274 *priv, u32 *val)
 	if (err)
 		goto fail;
 
-	/* prepare SHR registers */
-	imx274_calculate_coarse_time_regs(reg_list, coarse_time);
-
-	/* write to SHR registers */
-	for (i = 0; i < ARRAY_SIZE(reg_list); i++) {
-		err = imx274_write_reg(priv, reg_list[i].addr,
-				       reg_list[i].val);
-		if (err)
-			goto fail;
-	}
+	err = imx274_write_mbreg(priv, IMX274_SHR_REG_LSB, coarse_time, 2);
+	if (err)
+		goto fail;
 
 	*val = frame_length - coarse_time;
 	return 0;
@@ -1429,19 +1424,6 @@ static int imx274_set_test_pattern(struct stimx274 *priv, int val)
 	return err;
 }
 
-static inline void imx274_calculate_frame_length_regs(struct reg_8 regs[3],
-						      u32 frame_length)
-{
-	regs->addr = IMX274_VMAX_REG_1;
-	regs->val = (frame_length >> IMX274_SHIFT_16_BITS)
-			& IMX274_MASK_LSB_4_BITS;
-	(regs + 1)->addr = IMX274_VMAX_REG_2;
-	(regs + 1)->val = (frame_length >> IMX274_SHIFT_8_BITS)
-			& IMX274_MASK_LSB_8_BITS;
-	(regs + 2)->addr = IMX274_VMAX_REG_3;
-	(regs + 2)->val = (frame_length) & IMX274_MASK_LSB_8_BITS;
-}
-
 /*
  * imx274_set_frame_length - Function called when setting frame length
  * @priv: Pointer to device structure
@@ -1453,23 +1435,17 @@ static inline void imx274_calculate_frame_length_regs(struct reg_8 regs[3],
  */
 static int imx274_set_frame_length(struct stimx274 *priv, u32 val)
 {
-	struct reg_8 reg_list[3];
 	int err;
 	u32 frame_length;
-	int i;
 
 	dev_dbg(&priv->client->dev, "%s : input length = %d\n",
 		__func__, val);
 
 	frame_length = (u32)val;
 
-	imx274_calculate_frame_length_regs(reg_list, frame_length);
-	for (i = 0; i < ARRAY_SIZE(reg_list); i++) {
-		err = imx274_write_reg(priv, reg_list[i].addr,
-				       reg_list[i].val);
-		if (err)
-			goto fail;
-	}
+	err = imx274_write_mbreg(priv, IMX274_VMAX_REG_3, frame_length, 3);
+	if (err)
+		goto fail;
 
 	return 0;
 
-- 
cgit v1.2.3


From 8927c27b32703e28041ae19bf25ea53461be83a1 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 27 Jul 2018 00:27:21 +0200
Subject: clk: mvebu: armada-37xx-periph: Remove unused var num_parents
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When building armada-37xx-periph, num_parents isn't used in function
clk_pm_cpu_get_parent:
drivers/clk/mvebu/armada-37xx-periph.c: In function ‘clk_pm_cpu_get_parent’:
drivers/clk/mvebu/armada-37xx-periph.c:419:6: warning: unused variable ‘num_parents’ [-Wunused-variable]
  int num_parents = clk_hw_get_num_parents(hw);
      ^~~~~~~~~~~
Remove the declaration of num_parents to dispose the warning.

Fixes: 616bf80d381d ("clk: mvebu: armada-37xx-periph: Fix wrong return value in get_parent")
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/mvebu/armada-37xx-periph.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/clk/mvebu/armada-37xx-periph.c b/drivers/clk/mvebu/armada-37xx-periph.c
index 5cf0a52b87e8..b841ec3c6d6e 100644
--- a/drivers/clk/mvebu/armada-37xx-periph.c
+++ b/drivers/clk/mvebu/armada-37xx-periph.c
@@ -418,7 +418,6 @@ static unsigned int armada_3700_pm_dvfs_get_cpu_parent(struct regmap *base)
 static u8 clk_pm_cpu_get_parent(struct clk_hw *hw)
 {
 	struct clk_pm_cpu *pm_cpu = to_clk_pm_cpu(hw);
-	int num_parents = clk_hw_get_num_parents(hw);
 	u32 val;
 
 	if (armada_3700_pm_dvfs_is_enabled(pm_cpu->nb_pm_base)) {
-- 
cgit v1.2.3


From 39dd23dc9d4c512954ec511d22d93ea854cf0265 Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca@lucaceresoli.net>
Date: Wed, 25 Jul 2018 12:24:55 -0400
Subject: media: imx274: add cropping support via SELECTION API

Currently this driver does not support cropping. The supported modes
are the following, all capturing the entire area:

 - 3840x2160, 1:1 binning (native sensor resolution)
 - 1920x1080, 2:1 binning
 - 1280x720,  3:1 binning

The VIDIOC_SUBDEV_S_FMT ioctl chooses among these 3 configurations the
one that matches the requested format.

Add cropping support via VIDIOC_SUBDEV_S_SELECTION: with target
V4L2_SEL_TGT_CROP to choose the captured area, with
V4L2_SEL_TGT_COMPOSE to choose the output resolution.

To maintain backward compatibility we also allow setting the compose
format via VIDIOC_SUBDEV_S_FMT. To obtain this, compose rect and
output format are computed in the common helper function
__imx274_change_compose(), which sets both to the same width/height
values.

Cropping also calls __imx274_change_compose() whenever cropping rect
size changes in order to reset the compose rect (and output format
size) for 1:1 binning.

Also rename enum imx274_mode to imx274_binning (and its values from
IMX274_MODE_BINNING_* to IMX274_BINNING_*). Without cropping, the two
naming are equivalent. With cropping, the resolution could be
different, e.g. using 2:1 binning mode to crop 1200x960 and output a
600x480 format. Using binning in the names avoids any
misunderstanding. For the same reason, replace the 'size' field in
struct imx274_frmfmt with 'bin_ratio'.

[Sakari Ailus: Remove leftover condition in imx274_apply_trimming]

Signed-off-by: Luca Ceresoli <luca@lucaceresoli.net>
Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/imx274.c | 466 ++++++++++++++++++++++++++++++++++++---------
 1 file changed, 375 insertions(+), 91 deletions(-)

diff --git a/drivers/media/i2c/imx274.c b/drivers/media/i2c/imx274.c
index 093c4587832a..f8c70f1a34fe 100644
--- a/drivers/media/i2c/imx274.c
+++ b/drivers/media/i2c/imx274.c
@@ -5,6 +5,7 @@
  *
  * Leon Luo <leonl@leopardimaging.com>
  * Edwin Zou <edwinz@leopardimaging.com>
+ * Luca Ceresoli <luca@lucaceresoli.net>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -25,6 +26,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/i2c.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of_gpio.h>
 #include <linux/regmap.h>
@@ -74,7 +76,7 @@
  */
 #define IMX274_MIN_EXPOSURE_TIME		(4 * 260 / 72)
 
-#define IMX274_DEFAULT_MODE			IMX274_MODE_3840X2160
+#define IMX274_DEFAULT_MODE			IMX274_BINNING_OFF
 #define IMX274_MAX_WIDTH			(3840)
 #define IMX274_MAX_HEIGHT			(2160)
 #define IMX274_MAX_FRAME_RATE			(120)
@@ -111,6 +113,20 @@
 #define IMX274_SHR_REG_LSB			0x300C /* SHR */
 #define IMX274_SVR_REG_MSB			0x300F /* SVR */
 #define IMX274_SVR_REG_LSB			0x300E /* SVR */
+#define IMX274_HTRIM_EN_REG			0x3037
+#define IMX274_HTRIM_START_REG_LSB		0x3038
+#define IMX274_HTRIM_START_REG_MSB		0x3039
+#define IMX274_HTRIM_END_REG_LSB		0x303A
+#define IMX274_HTRIM_END_REG_MSB		0x303B
+#define IMX274_VWIDCUTEN_REG			0x30DD
+#define IMX274_VWIDCUT_REG_LSB			0x30DE
+#define IMX274_VWIDCUT_REG_MSB			0x30DF
+#define IMX274_VWINPOS_REG_LSB			0x30E0
+#define IMX274_VWINPOS_REG_MSB			0x30E1
+#define IMX274_WRITE_VSIZE_REG_LSB		0x3130
+#define IMX274_WRITE_VSIZE_REG_MSB		0x3131
+#define IMX274_Y_OUT_SIZE_REG_LSB		0x3132
+#define IMX274_Y_OUT_SIZE_REG_MSB		0x3133
 #define IMX274_VMAX_REG_1			0x30FA /* VMAX, MSB */
 #define IMX274_VMAX_REG_2			0x30F9 /* VMAX */
 #define IMX274_VMAX_REG_3			0x30F8 /* VMAX, LSB */
@@ -140,10 +156,10 @@ static const struct regmap_config imx274_regmap_config = {
 	.cache_type = REGCACHE_RBTREE,
 };
 
-enum imx274_mode {
-	IMX274_MODE_3840X2160,
-	IMX274_MODE_1920X1080,
-	IMX274_MODE_1280X720,
+enum imx274_binning {
+	IMX274_BINNING_OFF,
+	IMX274_BINNING_2_1,
+	IMX274_BINNING_3_1,
 };
 
 /*
@@ -152,8 +168,8 @@ enum imx274_mode {
  * These are the values to configure the sensor in one of the
  * implemented modes.
  *
- * @size: recommended recording pixels
  * @init_regs: registers to initialize the mode
+ * @bin_ratio: downscale factor (e.g. 3 for 3:1 binning)
  * @min_frame_len: Minimum frame length for each mode (see "Frame Rate
  *                 Adjustment (CSI-2)" in the datasheet)
  * @min_SHR: Minimum SHR register value (see "Shutter Setting (CSI-2)" in the
@@ -163,8 +179,8 @@ enum imx274_mode {
  *           in Each Readout Drive Mode (CSI-2)" in the datasheet)
  */
 struct imx274_frmfmt {
-	struct v4l2_frmsize_discrete size;
 	const struct reg_8 *init_regs;
+	unsigned int bin_ratio;
 	int min_frame_len;
 	int min_SHR;
 	int max_fps;
@@ -215,31 +231,14 @@ static const struct reg_8 imx274_mode1_3840x2160_raw10[] = {
 	{0x3004, 0x01},
 	{0x3005, 0x01},
 	{0x3006, 0x00},
-	{0x3007, 0x02},
+	{0x3007, 0xa2},
 
 	{0x3018, 0xA2}, /* output XVS, HVS */
 
 	{0x306B, 0x05},
 	{0x30E2, 0x01},
-	{0x30F6, 0x07}, /* HMAX, 263 */
-	{0x30F7, 0x01}, /* HMAX */
-
-	{0x30dd, 0x01}, /* crop to 2160 */
-	{0x30de, 0x06},
-	{0x30df, 0x00},
-	{0x30e0, 0x12},
-	{0x30e1, 0x00},
-	{0x3037, 0x01}, /* to crop to 3840 */
-	{0x3038, 0x0c},
-	{0x3039, 0x00},
-	{0x303a, 0x0c},
-	{0x303b, 0x0f},
 
 	{0x30EE, 0x01},
-	{0x3130, 0x86},
-	{0x3131, 0x08},
-	{0x3132, 0x7E},
-	{0x3133, 0x08},
 	{0x3342, 0x0A},
 	{0x3343, 0x00},
 	{0x3344, 0x16},
@@ -273,32 +272,14 @@ static const struct reg_8 imx274_mode3_1920x1080_raw10[] = {
 	{0x3004, 0x02},
 	{0x3005, 0x21},
 	{0x3006, 0x00},
-	{0x3007, 0x11},
+	{0x3007, 0xb1},
 
 	{0x3018, 0xA2}, /* output XVS, HVS */
 
 	{0x306B, 0x05},
 	{0x30E2, 0x02},
 
-	{0x30F6, 0x04}, /* HMAX, 260 */
-	{0x30F7, 0x01}, /* HMAX */
-
-	{0x30dd, 0x01}, /* to crop to 1920x1080 */
-	{0x30de, 0x05},
-	{0x30df, 0x00},
-	{0x30e0, 0x04},
-	{0x30e1, 0x00},
-	{0x3037, 0x01},
-	{0x3038, 0x0c},
-	{0x3039, 0x00},
-	{0x303a, 0x0c},
-	{0x303b, 0x0f},
-
 	{0x30EE, 0x01},
-	{0x3130, 0x4E},
-	{0x3131, 0x04},
-	{0x3132, 0x46},
-	{0x3133, 0x04},
 	{0x3342, 0x0A},
 	{0x3343, 0x00},
 	{0x3344, 0x1A},
@@ -331,31 +312,14 @@ static const struct reg_8 imx274_mode5_1280x720_raw10[] = {
 	{0x3004, 0x03},
 	{0x3005, 0x31},
 	{0x3006, 0x00},
-	{0x3007, 0x09},
+	{0x3007, 0xa9},
 
 	{0x3018, 0xA2}, /* output XVS, HVS */
 
 	{0x306B, 0x05},
 	{0x30E2, 0x03},
 
-	{0x30F6, 0x04}, /* HMAX, 260 */
-	{0x30F7, 0x01}, /* HMAX */
-
-	{0x30DD, 0x01},
-	{0x30DE, 0x07},
-	{0x30DF, 0x00},
-	{0x40E0, 0x04},
-	{0x30E1, 0x00},
-	{0x3030, 0xD4},
-	{0x3031, 0x02},
-	{0x3032, 0xD0},
-	{0x3033, 0x02},
-
 	{0x30EE, 0x01},
-	{0x3130, 0xE2},
-	{0x3131, 0x02},
-	{0x3132, 0xDE},
-	{0x3133, 0x02},
 	{0x3342, 0x0A},
 	{0x3343, 0x00},
 	{0x3344, 0x1B},
@@ -498,7 +462,7 @@ static const struct reg_8 imx274_tp_regs[] = {
 static const struct imx274_frmfmt imx274_formats[] = {
 	{
 		/* mode 1, 4K */
-		.size = {3840, 2160},
+		.bin_ratio = 1,
 		.init_regs = imx274_mode1_3840x2160_raw10,
 		.min_frame_len = 4550,
 		.min_SHR = 12,
@@ -507,7 +471,7 @@ static const struct imx274_frmfmt imx274_formats[] = {
 	},
 	{
 		/* mode 3, 1080p */
-		.size = {1920, 1080},
+		.bin_ratio = 2,
 		.init_regs = imx274_mode3_1920x1080_raw10,
 		.min_frame_len = 2310,
 		.min_SHR = 8,
@@ -516,7 +480,7 @@ static const struct imx274_frmfmt imx274_formats[] = {
 	},
 	{
 		/* mode 5, 720p */
-		.size = {1280, 720},
+		.bin_ratio = 3,
 		.init_regs = imx274_mode5_1280x720_raw10,
 		.min_frame_len = 2310,
 		.min_SHR = 8,
@@ -547,7 +511,10 @@ struct imx274_ctrls {
  * @pad: Media pad structure
  * @client: Pointer to I2C client
  * @ctrls: imx274 control structure
+ * @crop: rect to be captured
+ * @compose: compose rect, i.e. output resolution
  * @format: V4L2 media bus frame format structure
+ *          (width and height are in sync with the compose rect)
  * @frame_rate: V4L2 frame rate structure
  * @regmap: Pointer to regmap structure
  * @reset_gpio: Pointer to reset gpio
@@ -559,6 +526,7 @@ struct stimx274 {
 	struct media_pad pad;
 	struct i2c_client *client;
 	struct imx274_ctrls ctrls;
+	struct v4l2_rect crop;
 	struct v4l2_mbus_framefmt format;
 	struct v4l2_fract frame_interval;
 	struct regmap *regmap;
@@ -567,6 +535,13 @@ struct stimx274 {
 	const struct imx274_frmfmt *mode;
 };
 
+#define IMX274_ROUND(dim, step, flags)			\
+	((flags) & V4L2_SEL_FLAG_GE			\
+	 ? roundup((dim), (step))			\
+	 : ((flags) & V4L2_SEL_FLAG_LE			\
+	    ? rounddown((dim), (step))			\
+	    : rounddown((dim) + (step) / 2, (step))))
+
 /*
  * Function declaration
  */
@@ -840,6 +815,114 @@ static int imx274_s_ctrl(struct v4l2_ctrl *ctrl)
 	return ret;
 }
 
+static int imx274_binning_goodness(struct stimx274 *imx274,
+				   int w, int ask_w,
+				   int h, int ask_h, u32 flags)
+{
+	struct device *dev = &imx274->client->dev;
+	const int goodness = 100000;
+	int val = 0;
+
+	if (flags & V4L2_SEL_FLAG_GE) {
+		if (w < ask_w)
+			val -= goodness;
+		if (h < ask_h)
+			val -= goodness;
+	}
+
+	if (flags & V4L2_SEL_FLAG_LE) {
+		if (w > ask_w)
+			val -= goodness;
+		if (h > ask_h)
+			val -= goodness;
+	}
+
+	val -= abs(w - ask_w);
+	val -= abs(h - ask_h);
+
+	dev_dbg(dev, "%s: ask %dx%d, size %dx%d, goodness %d\n",
+		__func__, ask_w, ask_h, w, h, val);
+
+	return val;
+}
+
+/**
+ * Helper function to change binning and set both compose and format.
+ *
+ * We have two entry points to change binning: set_fmt and
+ * set_selection(COMPOSE). Both have to compute the new output size
+ * and set it in both the compose rect and the frame format size. We
+ * also need to do the same things after setting cropping to restore
+ * 1:1 binning.
+ *
+ * This function contains the common code for these three cases, it
+ * has many arguments in order to accommodate the needs of all of
+ * them.
+ *
+ * Must be called with imx274->lock locked.
+ *
+ * @imx274: The device object
+ * @cfg:    The pad config we are editing for TRY requests
+ * @which:  V4L2_SUBDEV_FORMAT_ACTIVE or V4L2_SUBDEV_FORMAT_TRY from the caller
+ * @width:  Input-output parameter: set to the desired width before
+ *          the call, contains the chosen value after returning successfully
+ * @height: Input-output parameter for height (see @width)
+ * @flags:  Selection flags from struct v4l2_subdev_selection, or 0 if not
+ *          available (when called from set_fmt)
+ */
+static int __imx274_change_compose(struct stimx274 *imx274,
+				   struct v4l2_subdev_pad_config *cfg,
+				   u32 which,
+				   u32 *width,
+				   u32 *height,
+				   u32 flags)
+{
+	struct device *dev = &imx274->client->dev;
+	const struct v4l2_rect *cur_crop;
+	struct v4l2_mbus_framefmt *tgt_fmt;
+	unsigned int i;
+	const struct imx274_frmfmt *best_mode = &imx274_formats[0];
+	int best_goodness = INT_MIN;
+
+	if (which == V4L2_SUBDEV_FORMAT_TRY) {
+		cur_crop = &cfg->try_crop;
+		tgt_fmt = &cfg->try_fmt;
+	} else {
+		cur_crop = &imx274->crop;
+		tgt_fmt = &imx274->format;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(imx274_formats); i++) {
+		unsigned int ratio = imx274_formats[i].bin_ratio;
+
+		int goodness = imx274_binning_goodness(
+			imx274,
+			cur_crop->width / ratio, *width,
+			cur_crop->height / ratio, *height,
+			flags);
+
+		if (goodness >= best_goodness) {
+			best_goodness = goodness;
+			best_mode = &imx274_formats[i];
+		}
+	}
+
+	*width = cur_crop->width / best_mode->bin_ratio;
+	*height = cur_crop->height / best_mode->bin_ratio;
+
+	if (which == V4L2_SUBDEV_FORMAT_ACTIVE)
+		imx274->mode = best_mode;
+
+	dev_dbg(dev, "%s: selected %u:1 binning\n",
+		__func__, best_mode->bin_ratio);
+
+	tgt_fmt->width = *width;
+	tgt_fmt->height = *height;
+	tgt_fmt->field = V4L2_FIELD_NONE;
+
+	return 0;
+}
+
 /**
  * imx274_get_fmt - Get the pad format
  * @sd: Pointer to V4L2 Sub device structure
@@ -878,45 +961,238 @@ static int imx274_set_fmt(struct v4l2_subdev *sd,
 {
 	struct v4l2_mbus_framefmt *fmt = &format->format;
 	struct stimx274 *imx274 = to_imx274(sd);
-	struct i2c_client *client = imx274->client;
-	int index;
-
-	dev_dbg(&client->dev,
-		"%s: width = %d height = %d code = %d\n",
-		__func__, fmt->width, fmt->height, fmt->code);
+	int err = 0;
 
 	mutex_lock(&imx274->lock);
 
-	for (index = 0; index < ARRAY_SIZE(imx274_formats); index++) {
-		if (imx274_formats[index].size.width == fmt->width &&
-		    imx274_formats[index].size.height == fmt->height)
-			break;
-	}
-
-	if (index >= ARRAY_SIZE(imx274_formats)) {
-		/* default to first format */
-		index = 0;
-	}
+	err = __imx274_change_compose(imx274, cfg, format->which,
+				      &fmt->width, &fmt->height, 0);
 
-	imx274->mode = &imx274_formats[index];
+	if (err)
+		goto out;
 
-	if (fmt->width > IMX274_MAX_WIDTH)
-		fmt->width = IMX274_MAX_WIDTH;
-	if (fmt->height > IMX274_MAX_HEIGHT)
-		fmt->height = IMX274_MAX_HEIGHT;
-	fmt->width = fmt->width & (~IMX274_MASK_LSB_2_BITS);
-	fmt->height = fmt->height & (~IMX274_MASK_LSB_2_BITS);
+	/*
+	 * __imx274_change_compose already set width and height in the
+	 * applicable format, but we need to keep all other format
+	 * values, so do a full copy here
+	 */
 	fmt->field = V4L2_FIELD_NONE;
-
 	if (format->which == V4L2_SUBDEV_FORMAT_TRY)
 		cfg->try_fmt = *fmt;
 	else
 		imx274->format = *fmt;
 
+out:
+	mutex_unlock(&imx274->lock);
+
+	return err;
+}
+
+static int imx274_get_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct stimx274 *imx274 = to_imx274(sd);
+	const struct v4l2_rect *src_crop;
+	const struct v4l2_mbus_framefmt *src_fmt;
+	int ret = 0;
+
+	if (sel->pad != 0)
+		return -EINVAL;
+
+	if (sel->target == V4L2_SEL_TGT_CROP_BOUNDS) {
+		sel->r.left = 0;
+		sel->r.top = 0;
+		sel->r.width = IMX274_MAX_WIDTH;
+		sel->r.height = IMX274_MAX_HEIGHT;
+		return 0;
+	}
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_TRY) {
+		src_crop = &cfg->try_crop;
+		src_fmt = &cfg->try_fmt;
+	} else {
+		src_crop = &imx274->crop;
+		src_fmt = &imx274->format;
+	}
+
+	mutex_lock(&imx274->lock);
+
+	switch (sel->target) {
+	case V4L2_SEL_TGT_CROP:
+		sel->r = *src_crop;
+		break;
+	case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+		sel->r.top = 0;
+		sel->r.left = 0;
+		sel->r.width = src_crop->width;
+		sel->r.height = src_crop->height;
+		break;
+	case V4L2_SEL_TGT_COMPOSE:
+		sel->r.top = 0;
+		sel->r.left = 0;
+		sel->r.width = src_fmt->width;
+		sel->r.height = src_fmt->height;
+		break;
+	default:
+		ret = -EINVAL;
+	}
+
+	mutex_unlock(&imx274->lock);
+
+	return ret;
+}
+
+static int imx274_set_selection_crop(struct stimx274 *imx274,
+				     struct v4l2_subdev_pad_config *cfg,
+				     struct v4l2_subdev_selection *sel)
+{
+	struct v4l2_rect *tgt_crop;
+	struct v4l2_rect new_crop;
+	bool size_changed;
+
+	/*
+	 * h_step could be 12 or 24 depending on the binning. But we
+	 * won't know the binning until we choose the mode later in
+	 * __imx274_change_compose(). Thus let's be safe and use the
+	 * most conservative value in all cases.
+	 */
+	const u32 h_step = 24;
+
+	new_crop.width = min_t(u32,
+			       IMX274_ROUND(sel->r.width, h_step, sel->flags),
+			       IMX274_MAX_WIDTH);
+
+	/* Constraint: HTRIMMING_END - HTRIMMING_START >= 144 */
+	if (new_crop.width < 144)
+		new_crop.width = 144;
+
+	new_crop.left = min_t(u32,
+			      IMX274_ROUND(sel->r.left, h_step, 0),
+			      IMX274_MAX_WIDTH - new_crop.width);
+
+	new_crop.height = min_t(u32,
+				IMX274_ROUND(sel->r.height, 2, sel->flags),
+				IMX274_MAX_HEIGHT);
+
+	new_crop.top = min_t(u32, IMX274_ROUND(sel->r.top, 2, 0),
+			     IMX274_MAX_HEIGHT - new_crop.height);
+
+	sel->r = new_crop;
+
+	if (sel->which == V4L2_SUBDEV_FORMAT_TRY)
+		tgt_crop = &cfg->try_crop;
+	else
+		tgt_crop = &imx274->crop;
+
+	mutex_lock(&imx274->lock);
+
+	size_changed = (new_crop.width != tgt_crop->width ||
+			new_crop.height != tgt_crop->height);
+
+	/* __imx274_change_compose needs the new size in *tgt_crop */
+	*tgt_crop = new_crop;
+
+	/* if crop size changed then reset the output image size */
+	if (size_changed)
+		__imx274_change_compose(imx274, cfg, sel->which,
+					&new_crop.width, &new_crop.height,
+					sel->flags);
+
 	mutex_unlock(&imx274->lock);
+
 	return 0;
 }
 
+static int imx274_set_selection(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_selection *sel)
+{
+	struct stimx274 *imx274 = to_imx274(sd);
+
+	if (sel->pad != 0)
+		return -EINVAL;
+
+	if (sel->target == V4L2_SEL_TGT_CROP)
+		return imx274_set_selection_crop(imx274, cfg, sel);
+
+	if (sel->target == V4L2_SEL_TGT_COMPOSE) {
+		int err;
+
+		mutex_lock(&imx274->lock);
+		err =  __imx274_change_compose(imx274, cfg, sel->which,
+					       &sel->r.width, &sel->r.height,
+					       sel->flags);
+		mutex_unlock(&imx274->lock);
+
+		/*
+		 * __imx274_change_compose already set width and
+		 * height in set->r, we still need to set top-left
+		 */
+		if (!err) {
+			sel->r.top = 0;
+			sel->r.left = 0;
+		}
+
+		return err;
+	}
+
+	return -EINVAL;
+}
+
+static int imx274_apply_trimming(struct stimx274 *imx274)
+{
+	u32 h_start;
+	u32 h_end;
+	u32 hmax;
+	u32 v_cut;
+	s32 v_pos;
+	u32 write_v_size;
+	u32 y_out_size;
+	int err;
+
+	h_start = imx274->crop.left + 12;
+	h_end = h_start + imx274->crop.width;
+
+	/* Use the minimum allowed value of HMAX */
+	/* Note: except in mode 1, (width / 16 + 23) is always < hmax_min */
+	/* Note: 260 is the minimum HMAX in all implemented modes */
+	hmax = max_t(u32, 260, (imx274->crop.width) / 16 + 23);
+
+	/* invert v_pos if VFLIP */
+	v_pos = imx274->ctrls.vflip->cur.val ?
+		(-imx274->crop.top / 2) : (imx274->crop.top / 2);
+	v_cut = (IMX274_MAX_HEIGHT - imx274->crop.height) / 2;
+	write_v_size = imx274->crop.height + 22;
+	y_out_size   = imx274->crop.height + 14;
+
+	err = imx274_write_mbreg(imx274, IMX274_HMAX_REG_LSB, hmax, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_HTRIM_EN_REG, 1, 1);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_HTRIM_START_REG_LSB,
+					 h_start, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_HTRIM_END_REG_LSB,
+					 h_end, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_VWIDCUTEN_REG, 1, 1);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_VWIDCUT_REG_LSB,
+					 v_cut, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_VWINPOS_REG_LSB,
+					 v_pos, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_WRITE_VSIZE_REG_LSB,
+					 write_v_size, 2);
+	if (!err)
+		err = imx274_write_mbreg(imx274, IMX274_Y_OUT_SIZE_REG_LSB,
+					 y_out_size, 2);
+
+	return err;
+}
+
 /**
  * imx274_g_frame_interval - Get the frame interval
  * @sd: Pointer to V4L2 Sub device structure
@@ -1057,6 +1333,10 @@ static int imx274_s_stream(struct v4l2_subdev *sd, int on)
 		if (ret)
 			goto fail;
 
+		ret = imx274_apply_trimming(imx274);
+		if (ret)
+			goto fail;
+
 		/*
 		 * update frame rate & expsoure. if the last mode is different,
 		 * HMAX could be changed. As the result, frame rate & exposure
@@ -1545,6 +1825,8 @@ fail:
 static const struct v4l2_subdev_pad_ops imx274_pad_ops = {
 	.get_fmt = imx274_get_fmt,
 	.set_fmt = imx274_set_fmt,
+	.get_selection = imx274_get_selection,
+	.set_selection = imx274_set_selection,
 };
 
 static const struct v4l2_subdev_video_ops imx274_video_ops = {
@@ -1590,8 +1872,10 @@ static int imx274_probe(struct i2c_client *client,
 
 	/* initialize format */
 	imx274->mode = &imx274_formats[IMX274_DEFAULT_MODE];
-	imx274->format.width = imx274->mode->size.width;
-	imx274->format.height = imx274->mode->size.height;
+	imx274->crop.width = IMX274_MAX_WIDTH;
+	imx274->crop.height = IMX274_MAX_HEIGHT;
+	imx274->format.width = imx274->crop.width / imx274->mode->bin_ratio;
+	imx274->format.height = imx274->crop.height / imx274->mode->bin_ratio;
 	imx274->format.field = V4L2_FIELD_NONE;
 	imx274->format.code = MEDIA_BUS_FMT_SRGGB10_1X10;
 	imx274->format.colorspace = V4L2_COLORSPACE_SRGB;
-- 
cgit v1.2.3


From 9db3bbf58be59ab496ccd1c7528f4b0e8835c5b1 Mon Sep 17 00:00:00 2001
From: Ezequiel Garcia <ezequiel@collabora.com>
Date: Wed, 25 Jul 2018 13:15:12 -0400
Subject: media: v4l2-mem2mem: Fix missing v4l2_m2m_try_run call

Commit 34dbb848d5e4 ("media: mem2mem: Remove excessive try_run call")
removed a redundant call to v4l2_m2m_try_run but instead introduced
a bug. Consider the following case:

 1) Context A schedules, queues and runs job A.
 2) While the m2m device is running, context B schedules
    and queues job B. Job B cannot run, because it has to
    wait for job A.
 3) Job A completes, calls v4l2_m2m_job_finish, and tries
    to queue a job for context A, but since the context is
    empty it won't do anything.

In this scenario, queued job B will never run. Fix this by calling
v4l2_m2m_try_run from v4l2_m2m_try_schedule.

While here, add more documentation to these functions.

Fixes: 34dbb848d5e4 ("media: mem2mem: Remove excessive try_run call")

Signed-off-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
[hans.verkuil@cisco.com: split >80 cols line]
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-mem2mem.c | 33 ++++++++++++++++++++++++++++++---
 1 file changed, 30 insertions(+), 3 deletions(-)

diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index d9565ee44578..0a93c5b173c2 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -249,15 +249,24 @@ static void v4l2_m2m_try_run(struct v4l2_m2m_dev *m2m_dev)
 	m2m_dev->curr_ctx->job_flags |= TRANS_RUNNING;
 	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags);
 
+	dprintk("Running job on m2m_ctx: %p\n", m2m_dev->curr_ctx);
 	m2m_dev->m2m_ops->device_run(m2m_dev->curr_ctx->priv);
 }
 
-void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx)
+/*
+ * __v4l2_m2m_try_queue() - queue a job
+ * @m2m_dev: m2m device
+ * @m2m_ctx: m2m context
+ *
+ * Check if this context is ready to queue a job.
+ *
+ * This function can run in interrupt context.
+ */
+static void __v4l2_m2m_try_queue(struct v4l2_m2m_dev *m2m_dev,
+				 struct v4l2_m2m_ctx *m2m_ctx)
 {
-	struct v4l2_m2m_dev *m2m_dev;
 	unsigned long flags_job, flags_out, flags_cap;
 
-	m2m_dev = m2m_ctx->m2m_dev;
 	dprintk("Trying to schedule a job for m2m_ctx: %p\n", m2m_ctx);
 
 	if (!m2m_ctx->out_q_ctx.q.streaming
@@ -315,7 +324,25 @@ void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx)
 	m2m_ctx->job_flags |= TRANS_QUEUED;
 
 	spin_unlock_irqrestore(&m2m_dev->job_spinlock, flags_job);
+}
+
+/**
+ * v4l2_m2m_try_schedule() - schedule and possibly run a job for any context
+ * @m2m_ctx: m2m context
+ *
+ * Check if this context is ready to queue a job. If suitable,
+ * run the next queued job on the mem2mem device.
+ *
+ * This function shouldn't run in interrupt context.
+ *
+ * Note that v4l2_m2m_try_schedule() can schedule one job for this context,
+ * and then run another job for another context.
+ */
+void v4l2_m2m_try_schedule(struct v4l2_m2m_ctx *m2m_ctx)
+{
+	struct v4l2_m2m_dev *m2m_dev = m2m_ctx->m2m_dev;
 
+	__v4l2_m2m_try_queue(m2m_dev, m2m_ctx);
 	v4l2_m2m_try_run(m2m_dev);
 }
 EXPORT_SYMBOL_GPL(v4l2_m2m_try_schedule);
-- 
cgit v1.2.3


From a5516219b10218a87abb3352c82248ce3088e94a Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Fri, 27 Jul 2018 15:14:15 +0100
Subject: of/platform: Initialise default DMA masks

When of_dma_configure() was first born in 591c1ee465ce ("of: configure
the platform device dma parameters"), everything DMA-related was
factored out of of_platform_device_create_pdata() as seemed appropriate
at the time. However, now that of_dma_configure() has grown into the
generic handler for processing DMA-related properties from DT for all
kinds of devices, it is no longer an appropriate place to be doing
OF-platform-specific business. Since there are still plenty of platform
drivers not setting their own masks and depending on the bus default,
let's reinstate that inialisation in the OF-platform code itself, and
restore the long-standing status quo from 0589342c2794 ("of: set
dma_mask to point to coherent_dma_mask")

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/of/platform.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/of/platform.c b/drivers/of/platform.c
index 6925d993e1f0..7ba90c290a42 100644
--- a/drivers/of/platform.c
+++ b/drivers/of/platform.c
@@ -185,6 +185,9 @@ static struct platform_device *of_platform_device_create_pdata(
 	if (!dev)
 		goto err_clear_flag;
 
+	dev->dev.coherent_dma_mask = DMA_BIT_MASK(32);
+	if (!dev->dev.dma_mask)
+		dev->dev.dma_mask = &dev->dev.coherent_dma_mask;
 	dev->dev.bus = &platform_bus_type;
 	dev->dev.platform_data = platform_data;
 	of_msi_configure(&dev->dev, dev->dev.of_node);
-- 
cgit v1.2.3


From 5ac65e8c89410892189ef778f567da4adafb2e2f Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 23:16:06 +0100
Subject: ACPI/IORT: Support address size limit for root complexes

IORT revision D allows PCI root complex nodes to specify a memory
address size limit equivalently to named components, to help describe
straightforward integrations which don't really warrant a full-blown
_DMA method. Now that our headers are up-to-date, plumb it in.

If both _DMA and an address size limit are present, we would always
expect the former to be a more specific subset of the latter (since it
makes little sense for a _DMA range to involve bits which IORT says
aren't wired up), thus we can save calculating an explicit intersection
of the two effective masks and simply use short-circuit logic instead.

Reviewed-by: Hanjun Guo <hanjun.guo@linaro.org>
Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Will Deacon <will.deacon@arm.com>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/acpi/arm64/iort.c | 25 +++++++++++++++++++++++--
 1 file changed, 23 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 7a3a541046ed..4a66896e2aa3 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -947,6 +947,24 @@ static int nc_dma_get_range(struct device *dev, u64 *size)
 	return 0;
 }
 
+static int rc_dma_get_range(struct device *dev, u64 *size)
+{
+	struct acpi_iort_node *node;
+	struct acpi_iort_root_complex *rc;
+
+	node = iort_scan_node(ACPI_IORT_NODE_PCI_ROOT_COMPLEX,
+			      iort_match_node_callback, dev);
+	if (!node || node->revision < 1)
+		return -ENODEV;
+
+	rc = (struct acpi_iort_root_complex *)node->node_data;
+
+	*size = rc->memory_address_limit >= 64 ? U64_MAX :
+			1ULL<<rc->memory_address_limit;
+
+	return 0;
+}
+
 /**
  * iort_dma_setup() - Set-up device DMA parameters.
  *
@@ -975,10 +993,13 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 
 	size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
 
-	if (dev_is_pci(dev))
+	if (dev_is_pci(dev)) {
 		ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
-	else
+		if (ret == -ENODEV)
+			ret = rc_dma_get_range(dev, &size);
+	} else {
 		ret = nc_dma_get_range(dev, &size);
+	}
 
 	if (!ret) {
 		msb = fls64(dmaaddr + size - 1);
-- 
cgit v1.2.3


From f07d141fe9430cdf9f8a65a87c4136bd83b8ab2e Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 23:16:07 +0100
Subject: dma-mapping: Generalise dma_32bit_limit flag

Whilst the notion of an upstream DMA restriction is most commonly seen
in PCI host bridges saddled with a 32-bit native interface, a more
general version of the same issue can exist on complex SoCs where a bus
or point-to-point interconnect link from a device's DMA master interface
to another component along the path to memory (often an IOMMU) may carry
fewer address bits than the interfaces at both ends nominally support.
In order to properly deal with this, the first step is to expand the
dma_32bit_limit flag into an arbitrary mask.

To minimise the impact on existing code, we'll make sure to only
consider this new mask valid if set. That makes sense anyway, since a
mask of zero would represent DMA not being wired up at all, and that
would be better handled by not providing valid ops in the first place.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 arch/x86/kernel/pci-dma.c | 2 +-
 include/linux/device.h    | 6 +++---
 kernel/dma/direct.c       | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index ab5d9dd668d2..80f9fe8d27d0 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -175,7 +175,7 @@ rootfs_initcall(pci_iommu_init);
 
 static int via_no_dac_cb(struct pci_dev *pdev, void *data)
 {
-	pdev->dev.dma_32bit_limit = true;
+	pdev->dev.bus_dma_mask = DMA_BIT_MASK(32);
 	return 0;
 }
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 055a69dbcd18..6d3b000be57e 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -886,6 +886,8 @@ struct dev_links_info {
  * @coherent_dma_mask: Like dma_mask, but for alloc_coherent mapping as not all
  * 		hardware supports 64-bit addresses for consistent allocations
  * 		such descriptors.
+ * @bus_dma_mask: Mask of an upstream bridge or bus which imposes a smaller DMA
+ *		limit than the device itself supports.
  * @dma_pfn_offset: offset of DMA memory range relatively of RAM
  * @dma_parms:	A low level driver may set these to teach IOMMU code about
  * 		segment limitations.
@@ -912,8 +914,6 @@ struct dev_links_info {
  * @offline:	Set after successful invocation of bus type's .offline().
  * @of_node_reused: Set if the device-tree node is shared with an ancestor
  *              device.
- * @dma_32bit_limit: bridge limited to 32bit DMA even if the device itself
- *		indicates support for a higher limit in the dma_mask field.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -967,6 +967,7 @@ struct device {
 					     not all hardware supports
 					     64 bit addresses for consistent
 					     allocations such descriptors. */
+	u64		bus_dma_mask;	/* upstream dma_mask constraint */
 	unsigned long	dma_pfn_offset;
 
 	struct device_dma_parameters *dma_parms;
@@ -1002,7 +1003,6 @@ struct device {
 	bool			offline_disabled:1;
 	bool			offline:1;
 	bool			of_node_reused:1;
-	bool			dma_32bit_limit:1;
 };
 
 static inline struct device *kobj_to_dev(struct kobject *kobj)
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 8be8106270c2..c2860c5a9e96 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -180,10 +180,10 @@ int dma_direct_supported(struct device *dev, u64 mask)
 		return 0;
 #endif
 	/*
-	 * Various PCI/PCIe bridges have broken support for > 32bit DMA even
-	 * if the device itself might support it.
+	 * Upstream PCI/PCIe bridges or SoC interconnects may not carry
+	 * as many DMA address bits as the device itself supports.
 	 */
-	if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+	if (dev->bus_dma_mask && mask > dev->bus_dma_mask)
 		return 0;
 	return 1;
 }
-- 
cgit v1.2.3


From d74ea7100b0d065f2008c4e1ddf637483bc3d28c Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 23:16:08 +0100
Subject: ACPI/IORT: Set bus DMA mask as appropriate

When an explicit DMA limit is described by firmware, we need to remember
it regardless of how drivers might subsequently update their devices'
masks. The new bus_dma_mask field does that.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/acpi/arm64/iort.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 4a66896e2aa3..bc51cff5505e 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1014,6 +1014,7 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 		 * Limit coherent and dma mask based on size
 		 * retrieved from firmware.
 		 */
+		dev->bus_dma_mask = mask;
 		dev->coherent_dma_mask = mask;
 		*dev->dma_mask = mask;
 	}
-- 
cgit v1.2.3


From 6c2fb2ea76361da9b420a8e23a2a19e7842cbdda Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 23:16:09 +0100
Subject: of/device: Set bus DMA mask as appropriate

When an explicit DMA limit is described by firmware, we need to remember
it regardless of how drivers might subsequently update their devices'
masks. The new bus_dma_mask field does that.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/of/device.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/of/device.c b/drivers/of/device.c
index 33d85511d790..0d39633e8545 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -149,6 +149,7 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	 * set by the driver.
 	 */
 	mask = DMA_BIT_MASK(ilog2(dma_addr + size - 1) + 1);
+	dev->bus_dma_mask = mask;
 	dev->coherent_dma_mask &= mask;
 	*dev->dma_mask &= mask;
 
-- 
cgit v1.2.3


From 03bfdc31176cbe21e456f889ccbbf67568831149 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 23:16:10 +0100
Subject: iommu/dma: Respect bus DMA limit for IOVAs

Take the new bus limit into account (when present) for IOVA allocations,
to accommodate those SoCs which integrate off-the-shelf IP blocks with
narrower interconnects such that the link between a device output and an
IOMMU input can truncate DMA addresses to even fewer bits than the
native size of either block's interface would imply.

Eventually it might make sense for the DMA core to apply this constraint
up-front in dma_set_mask() and friends, but for now this seems like the
least risky approach.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/iommu/dma-iommu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index ddcbbdb5d658..511ff9a1d6d9 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -367,6 +367,9 @@ static dma_addr_t iommu_dma_alloc_iova(struct iommu_domain *domain,
 	if (iova_len < (1 << (IOVA_RANGE_CACHE_MAX_SIZE - 1)))
 		iova_len = roundup_pow_of_two(iova_len);
 
+	if (dev->bus_dma_mask)
+		dma_limit &= dev->bus_dma_mask;
+
 	if (domain->geometry.force_aperture)
 		dma_limit = min(dma_limit, domain->geometry.aperture_end);
 
-- 
cgit v1.2.3


From 6757cdae44449dec2af68cd4db0a5f9a30e66b38 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 23:16:11 +0100
Subject: ACPI/IORT: Don't set default coherent DMA mask

Now that we can track upstream DMA constraints properly with
bus_dma_mask instead of trying (and failing) to maintain it in
coherent_dma_mask, it doesn't make much sense for the firmware code to
be touching the latter at all. It's merely papering over bugs wherein a
driver has failed to call dma_set_coherent_mask() *and* the bus code has
not initialised any default value.

We don't really want to encourage more drivers coercing dma_mask so
we'll continue to fix that up if necessary, but add a warning to help
flush out any such buggy bus code that remains.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Acked-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/acpi/arm64/iort.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index bc51cff5505e..08f26db2da7e 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -978,20 +978,20 @@ void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *dma_size)
 	int ret, msb;
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	if (dev->coherent_dma_mask)
+		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else
+		size = 1ULL << 32;
 
 	if (dev_is_pci(dev)) {
 		ret = acpi_dma_get_range(dev, &dmaaddr, &offset, &size);
-- 
cgit v1.2.3


From 4d8bde883bfba3e8dd3335f91b640e5a70ec0aa6 Mon Sep 17 00:00:00 2001
From: Robin Murphy <robin.murphy@arm.com>
Date: Mon, 23 Jul 2018 23:16:12 +0100
Subject: OF: Don't set default coherent DMA mask

Now that we can track upstream DMA constraints properly with
bus_dma_mask instead of trying (and failing) to maintain it in
coherent_dma_mask, it doesn't make much sense for the firmware code to
be touching the latter at all. It's merely papering over bugs wherein a
driver has failed to call dma_set_coherent_mask() *and* the bus code has
not initialised any default value.

We don't really want to encourage more drivers coercing dma_mask so
we'll continue to fix that up if necessary, but add a warning to help
flush out any such buggy bus code that remains.

Signed-off-by: Robin Murphy <robin.murphy@arm.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/of/device.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/of/device.c b/drivers/of/device.c
index 0d39633e8545..5957cd4fa262 100644
--- a/drivers/of/device.c
+++ b/drivers/of/device.c
@@ -127,20 +127,20 @@ int of_dma_configure(struct device *dev, struct device_node *np, bool force_dma)
 	}
 
 	/*
-	 * Set default coherent_dma_mask to 32 bit.  Drivers are expected to
-	 * setup the correct supported mask.
+	 * If @dev is expected to be DMA-capable then the bus code that created
+	 * it should have initialised its dma_mask pointer by this point. For
+	 * now, we'll continue the legacy behaviour of coercing it to the
+	 * coherent mask if not, but we'll no longer do so quietly.
 	 */
-	if (!dev->coherent_dma_mask)
-		dev->coherent_dma_mask = DMA_BIT_MASK(32);
-	/*
-	 * Set it to coherent_dma_mask by default if the architecture
-	 * code has not set it.
-	 */
-	if (!dev->dma_mask)
+	if (!dev->dma_mask) {
+		dev_warn(dev, "DMA mask not set\n");
 		dev->dma_mask = &dev->coherent_dma_mask;
+	}
 
-	if (!size)
+	if (!size && dev->coherent_dma_mask)
 		size = max(dev->coherent_dma_mask, dev->coherent_dma_mask + 1);
+	else if (!size)
+		size = 1ULL << 32;
 
 	dev->dma_pfn_offset = offset;
 
-- 
cgit v1.2.3


From 4faeaf9c0f4581667ce5826f9c90c4fd463ef086 Mon Sep 17 00:00:00 2001
From: Sylwester Nawrocki <s.nawrocki@samsung.com>
Date: Tue, 5 Jun 2018 09:33:59 -0400
Subject: media: s5p-mfc: Fix buffer look up in s5p_mfc_handle_frame_{new,
 copy_time} functions

Look up of buffers in s5p_mfc_handle_frame_new, s5p_mfc_handle_frame_copy_time
functions is not working properly for DMA addresses above 2 GiB. As a result
flags and timestamp of returned buffers are not set correctly and it breaks
operation of GStreamer/OMX plugins which rely on the CAPTURE buffer queue
flags.

Due to improper return type of the get_dec_y_adr, get_dspl_y_adr callbacks
and sign bit extension these callbacks return incorrect address values,
e.g. 0xfffffffffefc0000 instead of 0x00000000fefc0000. Then the statement:

"if (vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0) == dec_y_addr)"

is always false, which breaks looking up capture queue buffers.

To ensure proper matching by address u32 type is used for the DMA
addresses. This should work on all related SoCs, since the MFC DMA
address width is not larger than 32-bit.

Changes done in this patch are minimal as there is a larger patch series
pending refactoring the whole driver.

Signed-off-by: Sylwester Nawrocki <s.nawrocki@samsung.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/s5p-mfc/s5p_mfc.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/drivers/media/platform/s5p-mfc/s5p_mfc.c b/drivers/media/platform/s5p-mfc/s5p_mfc.c
index 9ca707cb2a42..927a1235408d 100644
--- a/drivers/media/platform/s5p-mfc/s5p_mfc.c
+++ b/drivers/media/platform/s5p-mfc/s5p_mfc.c
@@ -254,24 +254,24 @@ static void s5p_mfc_handle_frame_all_extracted(struct s5p_mfc_ctx *ctx)
 static void s5p_mfc_handle_frame_copy_time(struct s5p_mfc_ctx *ctx)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
-	struct s5p_mfc_buf  *dst_buf, *src_buf;
-	size_t dec_y_addr;
+	struct s5p_mfc_buf *dst_buf, *src_buf;
+	u32 dec_y_addr;
 	unsigned int frame_type;
 
 	/* Make sure we actually have a new frame before continuing. */
 	frame_type = s5p_mfc_hw_call(dev->mfc_ops, get_dec_frame_type, dev);
 	if (frame_type == S5P_FIMV_DECODE_FRAME_SKIPPED)
 		return;
-	dec_y_addr = s5p_mfc_hw_call(dev->mfc_ops, get_dec_y_adr, dev);
+	dec_y_addr = (u32)s5p_mfc_hw_call(dev->mfc_ops, get_dec_y_adr, dev);
 
 	/* Copy timestamp / timecode from decoded src to dst and set
 	   appropriate flags. */
 	src_buf = list_entry(ctx->src_queue.next, struct s5p_mfc_buf, list);
 	list_for_each_entry(dst_buf, &ctx->dst_queue, list) {
-		if (vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0)
-				== dec_y_addr) {
-			dst_buf->b->timecode =
-						src_buf->b->timecode;
+		u32 addr = (u32)vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0);
+
+		if (addr == dec_y_addr) {
+			dst_buf->b->timecode = src_buf->b->timecode;
 			dst_buf->b->vb2_buf.timestamp =
 						src_buf->b->vb2_buf.timestamp;
 			dst_buf->b->flags &=
@@ -307,10 +307,10 @@ static void s5p_mfc_handle_frame_new(struct s5p_mfc_ctx *ctx, unsigned int err)
 {
 	struct s5p_mfc_dev *dev = ctx->dev;
 	struct s5p_mfc_buf  *dst_buf;
-	size_t dspl_y_addr;
+	u32 dspl_y_addr;
 	unsigned int frame_type;
 
-	dspl_y_addr = s5p_mfc_hw_call(dev->mfc_ops, get_dspl_y_adr, dev);
+	dspl_y_addr = (u32)s5p_mfc_hw_call(dev->mfc_ops, get_dspl_y_adr, dev);
 	if (IS_MFCV6_PLUS(dev))
 		frame_type = s5p_mfc_hw_call(dev->mfc_ops,
 			get_disp_frame_type, ctx);
@@ -329,9 +329,10 @@ static void s5p_mfc_handle_frame_new(struct s5p_mfc_ctx *ctx, unsigned int err)
 	/* The MFC returns address of the buffer, now we have to
 	 * check which videobuf does it correspond to */
 	list_for_each_entry(dst_buf, &ctx->dst_queue, list) {
+		u32 addr = (u32)vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0);
+
 		/* Check if this is the buffer we're looking for */
-		if (vb2_dma_contig_plane_dma_addr(&dst_buf->b->vb2_buf, 0)
-				== dspl_y_addr) {
+		if (addr == dspl_y_addr) {
 			list_del(&dst_buf->list);
 			ctx->dst_queue_cnt--;
 			dst_buf->b->sequence = ctx->sequence;
-- 
cgit v1.2.3


From 9b89bc3857a6c0dfda18ddae2a42c114ecc32753 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 12 May 2018 18:18:12 +0200
Subject: nvme.h: add support for the log specific field

NVMe 1.3 added a new log specific field to the get log page CQ
defintion, add it to our get_log_page SQ structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 include/linux/nvme.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 80dfedcf0bf7..39f05b0b8c7f 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -885,7 +885,7 @@ struct nvme_get_log_page_command {
 	__u64			rsvd2[2];
 	union nvme_data_ptr	dptr;
 	__u8			lid;
-	__u8			rsvd10;
+	__u8			lsp; /* upper 4 bits reserved */
 	__le16			numdl;
 	__le16			numdu;
 	__u16			rsvd11;
-- 
cgit v1.2.3


From 1a37621658fe06b10cf8bac02c32304d2a1c888c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 13 May 2018 18:53:57 +0200
Subject: nvme.h: add ANA definitions

Add various defintions from NVMe 1.3 TP 4004.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 include/linux/nvme.h | 50 +++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 47 insertions(+), 3 deletions(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 39f05b0b8c7f..64c9175723de 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -242,7 +242,12 @@ struct nvme_id_ctrl {
 	__le32			sanicap;
 	__le32			hmminds;
 	__le16			hmmaxd;
-	__u8			rsvd338[174];
+	__u8			rsvd338[4];
+	__u8			anatt;
+	__u8			anacap;
+	__le32			anagrpmax;
+	__le32			nanagrpid;
+	__u8			rsvd352[160];
 	__u8			sqes;
 	__u8			cqes;
 	__le16			maxcmd;
@@ -258,7 +263,8 @@ struct nvme_id_ctrl {
 	__le16			acwu;
 	__u8			rsvd534[2];
 	__le32			sgls;
-	__u8			rsvd540[228];
+	__le32			mnan;
+	__u8			rsvd544[224];
 	char			subnqn[256];
 	__u8			rsvd1024[768];
 	__le32			ioccsz;
@@ -312,7 +318,9 @@ struct nvme_id_ns {
 	__le16			nabspf;
 	__le16			noiob;
 	__u8			nvmcap[16];
-	__u8			rsvd64[40];
+	__u8			rsvd64[28];
+	__le32			anagrpid;
+	__u8			rsvd96[8];
 	__u8			nguid[16];
 	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
@@ -425,6 +433,32 @@ struct nvme_effects_log {
 	__u8   resv[2048];
 };
 
+enum nvme_ana_state {
+	NVME_ANA_OPTIMIZED		= 0x01,
+	NVME_ANA_NONOPTIMIZED		= 0x02,
+	NVME_ANA_INACCESSIBLE		= 0x03,
+	NVME_ANA_PERSISTENT_LOSS	= 0x04,
+	NVME_ANA_CHANGE			= 0x0f,
+};
+
+struct nvme_ana_group_desc {
+	__le32	grpid;
+	__le32	nnsids;
+	__le64	chgcnt;
+	__u8	state;
+	__u8	rsvd17[7];
+	__le32	nsids[];
+};
+
+/* flag for the log specific field of the ANA log */
+#define NVME_ANA_LOG_RGO	(1 << 0)
+
+struct nvme_ana_rsp_hdr {
+	__le64	chgcnt;
+	__le16	ngrps;
+	__le16	rsvd10[3];
+};
+
 enum {
 	NVME_SMART_CRIT_SPARE		= 1 << 0,
 	NVME_SMART_CRIT_TEMPERATURE	= 1 << 1,
@@ -444,11 +478,13 @@ enum {
 enum {
 	NVME_AER_NOTICE_NS_CHANGED	= 0x00,
 	NVME_AER_NOTICE_FW_ACT_STARTING = 0x01,
+	NVME_AER_NOTICE_ANA		= 0x03,
 };
 
 enum {
 	NVME_AEN_CFG_NS_ATTR		= 1 << 8,
 	NVME_AEN_CFG_FW_ACT		= 1 << 9,
+	NVME_AEN_CFG_ANA_CHANGE		= 1 << 11,
 };
 
 struct nvme_lba_range_type {
@@ -763,6 +799,7 @@ enum {
 	NVME_LOG_FW_SLOT	= 0x03,
 	NVME_LOG_CHANGED_NS	= 0x04,
 	NVME_LOG_CMD_EFFECTS	= 0x05,
+	NVME_LOG_ANA		= 0x0c,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -1185,6 +1222,13 @@ enum {
 	NVME_SC_ACCESS_DENIED		= 0x286,
 	NVME_SC_UNWRITTEN_BLOCK		= 0x287,
 
+	/*
+	 * Path-related Errors:
+	 */
+	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
+	NVME_SC_ANA_INACCESSIBLE	= 0x302,
+	NVME_SC_ANA_TRANSITION		= 0x303,
+
 	NVME_SC_DNR			= 0x4000,
 };
 
-- 
cgit v1.2.3


From 0e98719b0e4b48b61965e1d1cba037c2005d01d7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 6 Jun 2018 14:39:00 +0200
Subject: nvme: simplify the API for getting log pages

Merge nvme_get_log and nvme_get_log_ext into a single helper, which takes
a plain nsid instead of the nvme_ns pointer.  Also add support for the
log specific field while we're at it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/nvme/host/core.c     | 32 +++++++++++---------------------
 drivers/nvme/host/lightnvm.c |  5 +++--
 drivers/nvme/host/nvme.h     |  4 ++--
 3 files changed, 16 insertions(+), 25 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e77e6418a21c..4552167f8b2b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2249,21 +2249,16 @@ out_unlock:
 	return ret;
 }
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		     u8 log_page, void *log,
-		     size_t size, u64 offset)
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset)
 {
 	struct nvme_command c = { };
 	unsigned long dwlen = size / 4 - 1;
 
 	c.get_log_page.opcode = nvme_admin_get_log_page;
-
-	if (ns)
-		c.get_log_page.nsid = cpu_to_le32(ns->head->ns_id);
-	else
-		c.get_log_page.nsid = cpu_to_le32(NVME_NSID_ALL);
-
+	c.get_log_page.nsid = cpu_to_le32(nsid);
 	c.get_log_page.lid = log_page;
+	c.get_log_page.lsp = lsp;
 	c.get_log_page.numdl = cpu_to_le16(dwlen & ((1 << 16) - 1));
 	c.get_log_page.numdu = cpu_to_le16(dwlen >> 16);
 	c.get_log_page.lpol = cpu_to_le32(lower_32_bits(offset));
@@ -2272,12 +2267,6 @@ int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return nvme_submit_sync_cmd(ctrl->admin_q, &c, log, size);
 }
 
-static int nvme_get_log(struct nvme_ctrl *ctrl, u8 log_page, void *log,
-			size_t size)
-{
-	return nvme_get_log_ext(ctrl, NULL, log_page, log, size, 0);
-}
-
 static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 {
 	int ret;
@@ -2288,8 +2277,8 @@ static int nvme_get_effects_log(struct nvme_ctrl *ctrl)
 	if (!ctrl->effects)
 		return 0;
 
-	ret = nvme_get_log(ctrl, NVME_LOG_CMD_EFFECTS, ctrl->effects,
-					sizeof(*ctrl->effects));
+	ret = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CMD_EFFECTS, 0,
+			ctrl->effects, sizeof(*ctrl->effects), 0);
 	if (ret) {
 		kfree(ctrl->effects);
 		ctrl->effects = NULL;
@@ -3208,7 +3197,8 @@ static void nvme_clear_changed_ns_log(struct nvme_ctrl *ctrl)
 	 * raced with us in reading the log page, which could cause us to miss
 	 * updates.
 	 */
-	error = nvme_get_log(ctrl, NVME_LOG_CHANGED_NS, log, log_size);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_CHANGED_NS, 0, log,
+			log_size, 0);
 	if (error)
 		dev_warn(ctrl->device,
 			"reading changed ns log failed: %d\n", error);
@@ -3325,9 +3315,9 @@ static void nvme_get_fw_slot_info(struct nvme_ctrl *ctrl)
 	if (!log)
 		return;
 
-	if (nvme_get_log(ctrl, NVME_LOG_FW_SLOT, log, sizeof(*log)))
-		dev_warn(ctrl->device,
-				"Get FW SLOT INFO log error\n");
+	if (nvme_get_log(ctrl, NVME_NSID_ALL, 0, NVME_LOG_FW_SLOT, log,
+			sizeof(*log), 0))
+		dev_warn(ctrl->device, "Get FW SLOT INFO log error\n");
 	kfree(log);
 }
 
diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index d9e4cccd5b66..7e4cf4eb9d66 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -604,8 +604,9 @@ static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
 	while (left) {
 		len = min_t(unsigned int, left, max_len);
 
-		ret = nvme_get_log_ext(ctrl, ns, NVME_NVM_LOG_REPORT_CHUNK,
-				dev_meta, len, offset);
+		ret = nvme_get_log(ctrl, ns->head->ns_id,
+				NVME_NVM_LOG_REPORT_CHUNK, 0, dev_meta, len,
+				offset);
 		if (ret) {
 			dev_err(ctrl->device, "Get REPORT CHUNK log error\n");
 			break;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 4ad0c8ad2a27..f463eaf56db5 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -443,8 +443,8 @@ int nvme_reset_ctrl_sync(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl(struct nvme_ctrl *ctrl);
 int nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl);
 
-int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
-		u8 log_page, void *log, size_t size, u64 offset);
+int nvme_get_log(struct nvme_ctrl *ctrl, u32 nsid, u8 log_page, u8 lsp,
+		void *log, size_t size, u64 offset);
 
 extern const struct attribute_group nvme_ns_id_attr_group;
 extern const struct block_device_operations nvme_ns_head_ops;
-- 
cgit v1.2.3


From 8decf5d5b9f3f72b802a017b0b035f7db0592acf Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 4 Jun 2018 08:43:00 +0200
Subject: nvme: remove nvme_req_needs_failover

Now that we just call out to blk_path_error there isn't really any good
reason to not merge it into the only caller.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/nvme/host/core.c      | 3 ++-
 drivers/nvme/host/multipath.c | 7 -------
 drivers/nvme/host/nvme.h      | 6 ------
 3 files changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 4552167f8b2b..456d37a02ea3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -236,7 +236,8 @@ void nvme_complete_rq(struct request *req)
 	trace_nvme_complete_rq(req);
 
 	if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) {
-		if (nvme_req_needs_failover(req, status)) {
+		if ((req->cmd_flags & REQ_NVME_MPATH) &&
+		    blk_path_error(status)) {
 			nvme_failover_req(req);
 			return;
 		}
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 1ffd3e8b13a1..348aa405b641 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -56,13 +56,6 @@ void nvme_failover_req(struct request *req)
 	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
-bool nvme_req_needs_failover(struct request *req, blk_status_t error)
-{
-	if (!(req->cmd_flags & REQ_NVME_MPATH))
-		return false;
-	return blk_path_error(error);
-}
-
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 	struct nvme_ns *ns;
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index f463eaf56db5..07452adef110 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -453,7 +453,6 @@ extern const struct block_device_operations nvme_ns_head_ops;
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
 void nvme_failover_req(struct request *req);
-bool nvme_req_needs_failover(struct request *req, blk_status_t error);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
 void nvme_mpath_add_disk(struct nvme_ns_head *head);
@@ -490,11 +489,6 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 static inline void nvme_failover_req(struct request *req)
 {
 }
-static inline bool nvme_req_needs_failover(struct request *req,
-					   blk_status_t error)
-{
-	return false;
-}
 static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 {
 }
-- 
cgit v1.2.3


From 0d0b660f214dc4905db7b6bc998bad0c16dfb1ba Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 14 May 2018 08:48:54 +0200
Subject: nvme: add ANA support

Add support for Asynchronous Namespace Access as specified in NVMe 1.3
TP 4004.  With ANA each namespace attached to a controller belongs to an
ANA group that describes the characteristics of accessing the namespaces
through this controller.  In the optimized and non-optimized states
namespaces can be accessed regularly, although in a multi-pathing
environment we should always prefer to access a namespace through a
controller where an optimized relationship exists.  Namespaces in
Inaccessible, Permanent-Loss or Change state for a given controller
should not be accessed.

The states are updated through reading the ANA log page, which is read
once during controller initialization, whenever the ANA change notice
AEN is received, or when one of the ANA specific status codes that
signal a state change is received on a command.

The ANA state is kept in the nvme_ns structure, which makes the checks in
the fast path very simple.  Updating the ANA state when reading the log
page is also very simple, the only downside is that finding the initial
ANA state when scanning for namespaces is a bit cumbersome.

The gendisk for a ns_head is only registered once a live path for it
exists.  Without that the kernel would hang during partition scanning.

Includes fixes and improvements from Hannes Reinecke.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/nvme/host/core.c      |  42 +++++-
 drivers/nvme/host/multipath.c | 342 ++++++++++++++++++++++++++++++++++++++++--
 drivers/nvme/host/nvme.h      |  51 ++++++-
 3 files changed, 408 insertions(+), 27 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 456d37a02ea3..e62592c949ab 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1035,18 +1035,18 @@ int nvme_set_queue_count(struct nvme_ctrl *ctrl, int *count)
 EXPORT_SYMBOL_GPL(nvme_set_queue_count);
 
 #define NVME_AEN_SUPPORTED \
-	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT)
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_FW_ACT | NVME_AEN_CFG_ANA_CHANGE)
 
 static void nvme_enable_aen(struct nvme_ctrl *ctrl)
 {
-	u32 result;
+	u32 supported = ctrl->oaes & NVME_AEN_SUPPORTED, result;
 	int status;
 
-	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT,
-			ctrl->oaes & NVME_AEN_SUPPORTED, NULL, 0, &result);
+	status = nvme_set_features(ctrl, NVME_FEAT_ASYNC_EVENT, supported, NULL,
+			0, &result);
 	if (status)
 		dev_warn(ctrl->device, "Failed to configure AEN (cfg %x)\n",
-			 ctrl->oaes & NVME_AEN_SUPPORTED);
+			 supported);
 }
 
 static int nvme_submit_io(struct nvme_ns *ns, struct nvme_user_io __user *uio)
@@ -2370,6 +2370,7 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 	nvme_set_queue_limits(ctrl, ctrl->admin_q);
 	ctrl->sgls = le32_to_cpu(id->sgls);
 	ctrl->kas = le16_to_cpu(id->kas);
+	ctrl->max_namespaces = le32_to_cpu(id->mnan);
 
 	if (id->rtd3e) {
 		/* us -> s */
@@ -2429,8 +2430,12 @@ int nvme_init_identify(struct nvme_ctrl *ctrl)
 		ctrl->hmmaxd = le16_to_cpu(id->hmmaxd);
 	}
 
+	ret = nvme_mpath_init(ctrl, id);
 	kfree(id);
 
+	if (ret < 0)
+		return ret;
+
 	if (ctrl->apst_enabled && !prev_apst_enabled)
 		dev_pm_qos_expose_latency_tolerance(ctrl->device);
 	else if (!ctrl->apst_enabled && prev_apst_enabled)
@@ -2649,6 +2654,10 @@ static struct attribute *nvme_ns_id_attrs[] = {
 	&dev_attr_nguid.attr,
 	&dev_attr_eui.attr,
 	&dev_attr_nsid.attr,
+#ifdef CONFIG_NVME_MULTIPATH
+	&dev_attr_ana_grpid.attr,
+	&dev_attr_ana_state.attr,
+#endif
 	NULL,
 };
 
@@ -2671,6 +2680,14 @@ static umode_t nvme_ns_id_attrs_are_visible(struct kobject *kobj,
 		if (!memchr_inv(ids->eui64, 0, sizeof(ids->eui64)))
 			return 0;
 	}
+#ifdef CONFIG_NVME_MULTIPATH
+	if (a == &dev_attr_ana_grpid.attr || a == &dev_attr_ana_state.attr) {
+		if (dev_to_disk(dev)->fops != &nvme_fops) /* per-path attr */
+			return 0;
+		if (!nvme_ctrl_use_ana(nvme_get_ns_from_dev(dev)->ctrl))
+			return 0;
+	}
+#endif
 	return a->mode;
 }
 
@@ -3044,8 +3061,6 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 
 	nvme_get_ctrl(ctrl);
 
-	kfree(id);
-
 	device_add_disk(ctrl->device, ns->disk);
 	if (sysfs_create_group(&disk_to_dev(ns->disk)->kobj,
 					&nvme_ns_id_attr_group))
@@ -3055,8 +3070,10 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid)
 		pr_warn("%s: failed to register lightnvm sysfs group for identification\n",
 			ns->disk->disk_name);
 
-	nvme_mpath_add_disk(ns->head);
+	nvme_mpath_add_disk(ns, id);
 	nvme_fault_inject_init(ns);
+	kfree(id);
+
 	return;
  out_unlink_ns:
 	mutex_lock(&ctrl->subsys->lock);
@@ -3364,6 +3381,13 @@ static void nvme_handle_aen_notice(struct nvme_ctrl *ctrl, u32 result)
 	case NVME_AER_NOTICE_FW_ACT_STARTING:
 		queue_work(nvme_wq, &ctrl->fw_act_work);
 		break;
+#ifdef CONFIG_NVME_MULTIPATH
+	case NVME_AER_NOTICE_ANA:
+		if (!ctrl->ana_log_buf)
+			break;
+		queue_work(nvme_wq, &ctrl->ana_work);
+		break;
+#endif
 	default:
 		dev_warn(ctrl->device, "async event result %08x\n", result);
 	}
@@ -3396,6 +3420,7 @@ EXPORT_SYMBOL_GPL(nvme_complete_async_event);
 
 void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
 {
+	nvme_mpath_stop(ctrl);
 	nvme_stop_keep_alive(ctrl);
 	flush_work(&ctrl->async_event_work);
 	flush_work(&ctrl->scan_work);
@@ -3433,6 +3458,7 @@ static void nvme_free_ctrl(struct device *dev)
 
 	ida_simple_remove(&nvme_instance_ida, ctrl->instance);
 	kfree(ctrl->effects);
+	nvme_mpath_uninit(ctrl);
 
 	if (subsys) {
 		mutex_lock(&subsys->lock);
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 348aa405b641..c643872f8dac 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 Christoph Hellwig.
+ * Copyright (c) 2017-2018 Christoph Hellwig.
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms and conditions of the GNU General Public License,
@@ -20,6 +20,11 @@ module_param(multipath, bool, 0444);
 MODULE_PARM_DESC(multipath,
 	"turn on native support for multiple controllers per subsystem");
 
+inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return multipath && (ctrl->subsys->cmic & (1 << 3));
+}
+
 /*
  * If multipathing is enabled we need to always use the subsystem instance
  * number for numbering our devices to avoid conflicts between subsystems that
@@ -45,6 +50,7 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 void nvme_failover_req(struct request *req)
 {
 	struct nvme_ns *ns = req->q->queuedata;
+	u16 status = nvme_req(req)->status;
 	unsigned long flags;
 
 	spin_lock_irqsave(&ns->head->requeue_lock, flags);
@@ -52,7 +58,34 @@ void nvme_failover_req(struct request *req)
 	spin_unlock_irqrestore(&ns->head->requeue_lock, flags);
 	blk_mq_end_request(req, 0);
 
-	nvme_reset_ctrl(ns->ctrl);
+	switch (status & 0x7ff) {
+	case NVME_SC_ANA_TRANSITION:
+	case NVME_SC_ANA_INACCESSIBLE:
+	case NVME_SC_ANA_PERSISTENT_LOSS:
+		/*
+		 * If we got back an ANA error we know the controller is alive,
+		 * but not ready to serve this namespaces.  The spec suggests
+		 * we should update our general state here, but due to the fact
+		 * that the admin and I/O queues are not serialized that is
+		 * fundamentally racy.  So instead just clear the current path,
+		 * mark the the path as pending and kick of a re-read of the ANA
+		 * log page ASAP.
+		 */
+		nvme_mpath_clear_current_path(ns);
+		if (ns->ctrl->ana_log_buf) {
+			set_bit(NVME_NS_ANA_PENDING, &ns->flags);
+			queue_work(nvme_wq, &ns->ctrl->ana_work);
+		}
+		break;
+	default:
+		/*
+		 * Reset the controller for any non-ANA error as we don't know
+		 * what caused the error.
+		 */
+		nvme_reset_ctrl(ns->ctrl);
+		break;
+	}
+
 	kblockd_schedule_work(&ns->head->requeue_work);
 }
 
@@ -68,25 +101,51 @@ void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl)
 	up_read(&ctrl->namespaces_rwsem);
 }
 
+static const char *nvme_ana_state_names[] = {
+	[0]				= "invalid state",
+	[NVME_ANA_OPTIMIZED]		= "optimized",
+	[NVME_ANA_NONOPTIMIZED]		= "non-optimized",
+	[NVME_ANA_INACCESSIBLE]		= "inaccessible",
+	[NVME_ANA_PERSISTENT_LOSS]	= "persistent-loss",
+	[NVME_ANA_CHANGE]		= "change",
+};
+
 static struct nvme_ns *__nvme_find_path(struct nvme_ns_head *head)
 {
-	struct nvme_ns *ns;
+	struct nvme_ns *ns, *fallback = NULL;
 
 	list_for_each_entry_rcu(ns, &head->list, siblings) {
-		if (ns->ctrl->state == NVME_CTRL_LIVE) {
+		if (ns->ctrl->state != NVME_CTRL_LIVE ||
+		    test_bit(NVME_NS_ANA_PENDING, &ns->flags))
+			continue;
+		switch (ns->ana_state) {
+		case NVME_ANA_OPTIMIZED:
 			rcu_assign_pointer(head->current_path, ns);
 			return ns;
+		case NVME_ANA_NONOPTIMIZED:
+			fallback = ns;
+			break;
+		default:
+			break;
 		}
 	}
 
-	return NULL;
+	if (fallback)
+		rcu_assign_pointer(head->current_path, fallback);
+	return fallback;
+}
+
+static inline bool nvme_path_is_optimized(struct nvme_ns *ns)
+{
+	return ns->ctrl->state == NVME_CTRL_LIVE &&
+		ns->ana_state == NVME_ANA_OPTIMIZED;
 }
 
 inline struct nvme_ns *nvme_find_path(struct nvme_ns_head *head)
 {
 	struct nvme_ns *ns = srcu_dereference(head->current_path, &head->srcu);
 
-	if (unlikely(!ns || ns->ctrl->state != NVME_CTRL_LIVE))
+	if (unlikely(!ns || !nvme_path_is_optimized(ns)))
 		ns = __nvme_find_path(head);
 	return ns;
 }
@@ -135,7 +194,7 @@ static bool nvme_ns_head_poll(struct request_queue *q, blk_qc_t qc)
 
 	srcu_idx = srcu_read_lock(&head->srcu);
 	ns = srcu_dereference(head->current_path, &head->srcu);
-	if (likely(ns && ns->ctrl->state == NVME_CTRL_LIVE))
+	if (likely(ns && nvme_path_is_optimized(ns)))
 		found = ns->queue->poll_fn(q, qc);
 	srcu_read_unlock(&head->srcu, srcu_idx);
 	return found;
@@ -169,6 +228,7 @@ int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl, struct nvme_ns_head *head)
 	struct request_queue *q;
 	bool vwc = false;
 
+	mutex_init(&head->lock);
 	bio_list_init(&head->requeue_list);
 	spin_lock_init(&head->requeue_lock);
 	INIT_WORK(&head->requeue_work, nvme_requeue_work);
@@ -213,29 +273,232 @@ out:
 	return -ENOMEM;
 }
 
-void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static void nvme_mpath_set_live(struct nvme_ns *ns)
 {
+	struct nvme_ns_head *head = ns->head;
+
+	lockdep_assert_held(&ns->head->lock);
+
 	if (!head->disk)
 		return;
 
-	mutex_lock(&head->subsys->lock);
 	if (!(head->disk->flags & GENHD_FL_UP)) {
 		device_add_disk(&head->subsys->dev, head->disk);
 		if (sysfs_create_group(&disk_to_dev(head->disk)->kobj,
 				&nvme_ns_id_attr_group))
-			pr_warn("%s: failed to create sysfs group for identification\n",
-				head->disk->disk_name);
+			dev_warn(&head->subsys->dev,
+				 "failed to create id group.\n");
+	}
+
+	kblockd_schedule_work(&ns->head->requeue_work);
+}
+
+static int nvme_parse_ana_log(struct nvme_ctrl *ctrl, void *data,
+		int (*cb)(struct nvme_ctrl *ctrl, struct nvme_ana_group_desc *,
+			void *))
+{
+	void *base = ctrl->ana_log_buf;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr);
+	int error, i;
+
+	lockdep_assert_held(&ctrl->ana_lock);
+
+	for (i = 0; i < le16_to_cpu(ctrl->ana_log_buf->ngrps); i++) {
+		struct nvme_ana_group_desc *desc = base + offset;
+		u32 nr_nsids = le32_to_cpu(desc->nnsids);
+		size_t nsid_buf_size = nr_nsids * sizeof(__le32);
+
+		if (WARN_ON_ONCE(desc->grpid == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(le32_to_cpu(desc->grpid) > ctrl->anagrpmax))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state == 0))
+			return -EINVAL;
+		if (WARN_ON_ONCE(desc->state > NVME_ANA_CHANGE))
+			return -EINVAL;
+
+		offset += sizeof(*desc);
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - nsid_buf_size))
+			return -EINVAL;
+
+		error = cb(ctrl, desc, data);
+		if (error)
+			return error;
+
+		offset += nsid_buf_size;
+		if (WARN_ON_ONCE(offset > ctrl->ana_log_size - sizeof(*desc)))
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline bool nvme_state_is_live(enum nvme_ana_state state)
+{
+	return state == NVME_ANA_OPTIMIZED || state == NVME_ANA_NONOPTIMIZED;
+}
+
+static void nvme_update_ns_ana_state(struct nvme_ana_group_desc *desc,
+		struct nvme_ns *ns)
+{
+	enum nvme_ana_state old;
+
+	mutex_lock(&ns->head->lock);
+	old = ns->ana_state;
+	ns->ana_grpid = le32_to_cpu(desc->grpid);
+	ns->ana_state = desc->state;
+	clear_bit(NVME_NS_ANA_PENDING, &ns->flags);
+
+	if (nvme_state_is_live(ns->ana_state) && !nvme_state_is_live(old))
+		nvme_mpath_set_live(ns);
+	mutex_unlock(&ns->head->lock);
+}
+
+static int nvme_update_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	u32 nr_nsids = le32_to_cpu(desc->nnsids), n = 0;
+	unsigned *nr_change_groups = data;
+	struct nvme_ns *ns;
+
+	dev_info(ctrl->device, "ANA group %d: %s.\n",
+			le32_to_cpu(desc->grpid),
+			nvme_ana_state_names[desc->state]);
+
+	if (desc->state == NVME_ANA_CHANGE)
+		(*nr_change_groups)++;
+
+	if (!nr_nsids)
+		return 0;
+
+	down_write(&ctrl->namespaces_rwsem);
+	list_for_each_entry(ns, &ctrl->namespaces, list) {
+		if (ns->head->ns_id != le32_to_cpu(desc->nsids[n]))
+			continue;
+		nvme_update_ns_ana_state(desc, ns);
+		if (++n == nr_nsids)
+			break;
+	}
+	up_write(&ctrl->namespaces_rwsem);
+	WARN_ON_ONCE(n < nr_nsids);
+	return 0;
+}
+
+static int nvme_read_ana_log(struct nvme_ctrl *ctrl, bool groups_only)
+{
+	u32 nr_change_groups = 0;
+	int error;
+
+	mutex_lock(&ctrl->ana_lock);
+	error = nvme_get_log(ctrl, NVME_NSID_ALL, NVME_LOG_ANA,
+			groups_only ? NVME_ANA_LOG_RGO : 0,
+			ctrl->ana_log_buf, ctrl->ana_log_size, 0);
+	if (error) {
+		dev_warn(ctrl->device, "Failed to get ANA log: %d\n", error);
+		goto out_unlock;
+	}
+
+	error = nvme_parse_ana_log(ctrl, &nr_change_groups,
+			nvme_update_ana_state);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * In theory we should have an ANATT timer per group as they might enter
+	 * the change state at different times.  But that is a lot of overhead
+	 * just to protect against a target that keeps entering new changes
+	 * states while never finishing previous ones.  But we'll still
+	 * eventually time out once all groups are in change state, so this
+	 * isn't a big deal.
+	 *
+	 * We also double the ANATT value to provide some slack for transports
+	 * or AEN processing overhead.
+	 */
+	if (nr_change_groups)
+		mod_timer(&ctrl->anatt_timer, ctrl->anatt * HZ * 2 + jiffies);
+	else
+		del_timer_sync(&ctrl->anatt_timer);
+out_unlock:
+	mutex_unlock(&ctrl->ana_lock);
+	return error;
+}
+
+static void nvme_ana_work(struct work_struct *work)
+{
+	struct nvme_ctrl *ctrl = container_of(work, struct nvme_ctrl, ana_work);
+
+	nvme_read_ana_log(ctrl, false);
+}
+
+static void nvme_anatt_timeout(struct timer_list *t)
+{
+	struct nvme_ctrl *ctrl = from_timer(ctrl, t, anatt_timer);
+
+	dev_info(ctrl->device, "ANATT timeout, resetting controller.\n");
+	nvme_reset_ctrl(ctrl);
+}
+
+void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+	if (!nvme_ctrl_use_ana(ctrl))
+		return;
+	del_timer_sync(&ctrl->anatt_timer);
+	cancel_work_sync(&ctrl->ana_work);
+}
+
+static ssize_t ana_grpid_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	return sprintf(buf, "%d\n", nvme_get_ns_from_dev(dev)->ana_grpid);
+}
+DEVICE_ATTR_RO(ana_grpid);
+
+static ssize_t ana_state_show(struct device *dev, struct device_attribute *attr,
+		char *buf)
+{
+	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
+
+	return sprintf(buf, "%s\n", nvme_ana_state_names[ns->ana_state]);
+}
+DEVICE_ATTR_RO(ana_state);
+
+static int nvme_set_ns_ana_state(struct nvme_ctrl *ctrl,
+		struct nvme_ana_group_desc *desc, void *data)
+{
+	struct nvme_ns *ns = data;
+
+	if (ns->ana_grpid == le32_to_cpu(desc->grpid)) {
+		nvme_update_ns_ana_state(desc, ns);
+		return -ENXIO; /* just break out of the loop */
+	}
+
+	return 0;
+}
+
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id)
+{
+	if (nvme_ctrl_use_ana(ns->ctrl)) {
+		mutex_lock(&ns->ctrl->ana_lock);
+		ns->ana_grpid = le32_to_cpu(id->anagrpid);
+		nvme_parse_ana_log(ns->ctrl, ns, nvme_set_ns_ana_state);
+		mutex_unlock(&ns->ctrl->ana_lock);
+	} else {
+		mutex_lock(&ns->head->lock);
+		ns->ana_state = NVME_ANA_OPTIMIZED; 
+		nvme_mpath_set_live(ns);
+		mutex_unlock(&ns->head->lock);
 	}
-	mutex_unlock(&head->subsys->lock);
 }
 
 void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
-			   &nvme_ns_id_attr_group);
-	del_gendisk(head->disk);
+	if (head->disk->flags & GENHD_FL_UP) {
+		sysfs_remove_group(&disk_to_dev(head->disk)->kobj,
+				   &nvme_ns_id_attr_group);
+		del_gendisk(head->disk);
+	}
 	blk_set_queue_dying(head->disk->queue);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
@@ -243,3 +506,52 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 	blk_cleanup_queue(head->disk->queue);
 	put_disk(head->disk);
 }
+
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
+{
+	int error;
+
+	if (!nvme_ctrl_use_ana(ctrl))
+		return 0;
+
+	ctrl->anacap = id->anacap;
+	ctrl->anatt = id->anatt;
+	ctrl->nanagrpid = le32_to_cpu(id->nanagrpid);
+	ctrl->anagrpmax = le32_to_cpu(id->anagrpmax);
+
+	mutex_init(&ctrl->ana_lock);
+	timer_setup(&ctrl->anatt_timer, nvme_anatt_timeout, 0);
+	ctrl->ana_log_size = sizeof(struct nvme_ana_rsp_hdr) +
+		ctrl->nanagrpid * sizeof(struct nvme_ana_group_desc);
+	if (!(ctrl->anacap & (1 << 6)))
+		ctrl->ana_log_size += ctrl->max_namespaces * sizeof(__le32);
+
+	if (ctrl->ana_log_size > ctrl->max_hw_sectors << SECTOR_SHIFT) {
+		dev_err(ctrl->device,
+			"ANA log page size (%zd) larger than MDTS (%d).\n",
+			ctrl->ana_log_size,
+			ctrl->max_hw_sectors << SECTOR_SHIFT);
+		dev_err(ctrl->device, "disabling ANA support.\n");
+		return 0;
+	}
+
+	INIT_WORK(&ctrl->ana_work, nvme_ana_work);
+	ctrl->ana_log_buf = kmalloc(ctrl->ana_log_size, GFP_KERNEL);
+	if (!ctrl->ana_log_buf)
+		goto out;
+
+	error = nvme_read_ana_log(ctrl, true);
+	if (error)
+		goto out_free_ana_log_buf;
+	return 0;
+out_free_ana_log_buf:
+	kfree(ctrl->ana_log_buf);
+out:
+	return -ENOMEM;
+}
+
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+	kfree(ctrl->ana_log_buf);
+}
+
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 07452adef110..8b356f1d941c 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -183,6 +183,7 @@ struct nvme_ctrl {
 	u16 oacs;
 	u16 nssa;
 	u16 nr_streams;
+	u32 max_namespaces;
 	atomic_t abort_limit;
 	u8 vwc;
 	u32 vs;
@@ -205,6 +206,19 @@ struct nvme_ctrl {
 	struct work_struct fw_act_work;
 	unsigned long events;
 
+#ifdef CONFIG_NVME_MULTIPATH
+	/* asymmetric namespace access: */
+	u8 anacap;
+	u8 anatt;
+	u32 anagrpmax;
+	u32 nanagrpid;
+	struct mutex ana_lock;
+	struct nvme_ana_rsp_hdr *ana_log_buf;
+	size_t ana_log_size;
+	struct timer_list anatt_timer;
+	struct work_struct ana_work;
+#endif
+
 	/* Power saving configuration */
 	u64 ps_max_latency_us;
 	bool apst_enabled;
@@ -269,6 +283,7 @@ struct nvme_ns_head {
 	struct bio_list		requeue_list;
 	spinlock_t		requeue_lock;
 	struct work_struct	requeue_work;
+	struct mutex		lock;
 #endif
 	struct list_head	list;
 	struct srcu_struct      srcu;
@@ -295,6 +310,10 @@ struct nvme_ns {
 	struct nvme_ctrl *ctrl;
 	struct request_queue *queue;
 	struct gendisk *disk;
+#ifdef CONFIG_NVME_MULTIPATH
+	enum nvme_ana_state ana_state;
+	u32 ana_grpid;
+#endif
 	struct list_head siblings;
 	struct nvm_dev *ndev;
 	struct kref kref;
@@ -307,8 +326,9 @@ struct nvme_ns {
 	bool ext;
 	u8 pi_type;
 	unsigned long flags;
-#define NVME_NS_REMOVING 0
-#define NVME_NS_DEAD     1
+#define NVME_NS_REMOVING	0
+#define NVME_NS_DEAD     	1
+#define NVME_NS_ANA_PENDING	2
 	u16 noiob;
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
@@ -450,13 +470,17 @@ extern const struct attribute_group nvme_ns_id_attr_group;
 extern const struct block_device_operations nvme_ns_head_ops;
 
 #ifdef CONFIG_NVME_MULTIPATH
+bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl);
 void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns,
 			struct nvme_ctrl *ctrl, int *flags);
 void nvme_failover_req(struct request *req);
 void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl);
 int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head);
-void nvme_mpath_add_disk(struct nvme_ns_head *head);
+void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id);
 void nvme_mpath_remove_disk(struct nvme_ns_head *head);
+int nvme_mpath_init(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id);
+void nvme_mpath_uninit(struct nvme_ctrl *ctrl);
+void nvme_mpath_stop(struct nvme_ctrl *ctrl);
 
 static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 {
@@ -475,7 +499,14 @@ static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 		kblockd_schedule_work(&head->requeue_work);
 }
 
+extern struct device_attribute dev_attr_ana_grpid;
+extern struct device_attribute dev_attr_ana_state;
+
 #else
+static inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
+{
+	return false;
+}
 /*
  * Without the multipath code enabled, multiple controller per subsystems are
  * visible as devices and thus we cannot use the subsystem instance.
@@ -497,7 +528,8 @@ static inline int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,
 {
 	return 0;
 }
-static inline void nvme_mpath_add_disk(struct nvme_ns_head *head)
+static inline void nvme_mpath_add_disk(struct nvme_ns *ns,
+		struct nvme_id_ns *id)
 {
 }
 static inline void nvme_mpath_remove_disk(struct nvme_ns_head *head)
@@ -509,6 +541,17 @@ static inline void nvme_mpath_clear_current_path(struct nvme_ns *ns)
 static inline void nvme_mpath_check_last_path(struct nvme_ns *ns)
 {
 }
+static inline int nvme_mpath_init(struct nvme_ctrl *ctrl,
+		struct nvme_id_ctrl *id)
+{
+	return 0;
+}
+static inline void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
+{
+}
+static inline void nvme_mpath_stop(struct nvme_ctrl *ctrl)
+{
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 #ifdef CONFIG_NVM
-- 
cgit v1.2.3


From 4ee43280488b0f6cbd74702725a32f47d03d690b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 7 Jun 2018 15:09:50 +0200
Subject: nvmet: keep a port pointer in nvmet_ctrl

This will be needed for the ANA AEN code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/nvme/target/core.c  | 2 ++
 drivers/nvme/target/nvmet.h | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index ddd85715a00a..cbcd19f52121 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -876,6 +876,8 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
 
 	nvmet_init_cap(ctrl);
 
+	ctrl->port = req->port;
+
 	INIT_WORK(&ctrl->async_event_work, nvmet_async_event_work);
 	INIT_LIST_HEAD(&ctrl->async_events);
 
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 688993855402..de12dcbfd3f3 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -140,6 +140,8 @@ struct nvmet_ctrl {
 	u16			cntlid;
 	u32			kato;
 
+	struct nvmet_port	*port;
+
 	u32			aen_enabled;
 	unsigned long		aen_masked;
 	struct nvmet_req	*async_event_cmds[NVMET_ASYNC_EVENTS];
-- 
cgit v1.2.3


From 793c7cfce02ce88b7bd67d43834c052d16c096e3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sun, 13 May 2018 19:00:13 +0200
Subject: nvmet: track and limit the number of namespaces per subsystem

TP 4004 introduces a new 'Maximum Number of Allocated Namespaces' field
in the Identify controller data to help the host size resources.  Put
an upper limit on the supported namespaces to be able to support this
value as supporting 32-bits worth of namespaces would lead to very
large buffers.  The limit is completely arbitrary at this point.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/nvme/target/admin-cmd.c | 1 +
 drivers/nvme/target/core.c      | 8 +++++++-
 drivers/nvme/target/nvmet.h     | 8 ++++++++
 3 files changed, 16 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 16a9b24270f9..55f2bf4b5d07 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -252,6 +252,7 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->maxcmd = cpu_to_le16(NVMET_MAX_CMD);
 
 	id->nn = cpu_to_le32(ctrl->subsys->max_nsid);
+	id->mnan = cpu_to_le32(NVMET_MAX_NAMESPACES);
 	id->oncs = cpu_to_le16(NVME_CTRL_ONCS_DSM |
 			NVME_CTRL_ONCS_WRITE_ZEROES);
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index cbcd19f52121..42e8565015d5 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -337,9 +337,13 @@ static void nvmet_ns_dev_disable(struct nvmet_ns *ns)
 int nvmet_ns_enable(struct nvmet_ns *ns)
 {
 	struct nvmet_subsys *subsys = ns->subsys;
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&subsys->lock);
+	ret = -EMFILE;
+	if (subsys->nr_namespaces == NVMET_MAX_NAMESPACES)
+		goto out_unlock;
+	ret = 0;
 	if (ns->enabled)
 		goto out_unlock;
 
@@ -374,6 +378,7 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 
 		list_add_tail_rcu(&ns->dev_link, &old->dev_link);
 	}
+	subsys->nr_namespaces++;
 
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
@@ -414,6 +419,7 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	percpu_ref_exit(&ns->ref);
 
 	mutex_lock(&subsys->lock);
+	subsys->nr_namespaces--;
 	nvmet_ns_changed(subsys, ns->nsid);
 	nvmet_ns_dev_disable(ns);
 out_unlock:
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index de12dcbfd3f3..701017f7f3df 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -170,6 +170,7 @@ struct nvmet_subsys {
 	struct kref		ref;
 
 	struct list_head	namespaces;
+	unsigned int		nr_namespaces;
 	unsigned int		max_nsid;
 
 	struct list_head	ctrls;
@@ -362,6 +363,13 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
 #define NVMET_QUEUE_SIZE	1024
 #define NVMET_NR_QUEUES		128
 #define NVMET_MAX_CMD		NVMET_QUEUE_SIZE
+
+/*
+ * Nice round number that makes a list of nsids fit into a page.
+ * Should become tunable at some point in the future.
+ */
+#define NVMET_MAX_NAMESPACES	1024
+
 #define NVMET_KAS		10
 #define NVMET_DISC_KATO		120
 
-- 
cgit v1.2.3


From 72efd25dcf4f6310e9e6fa85620aa443b27c23fe Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 19 Jul 2018 07:35:20 -0700
Subject: nvmet: add minimal ANA support

Add support for Asynchronous Namespace Access as specified in NVMe 1.3
TP 4004.

Just add a default ANA group 1 that is optimized on all ports.  This is
(and will remain) the default assignment for any namespace not epxlicitly
assigned to another ANA group.  The ANA state can be manually changed
through the configfs interface, including the change state.

Includes fixes and improvements from Hannes Reinecke.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/nvme/target/admin-cmd.c | 87 +++++++++++++++++++++++++++++++++++++++--
 drivers/nvme/target/configfs.c  | 10 +++++
 drivers/nvme/target/core.c      | 34 ++++++++++++++++
 drivers/nvme/target/nvmet.h     | 15 +++++++
 4 files changed, 142 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index 55f2bf4b5d07..b98d38c4e579 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -182,6 +182,69 @@ out:
 	nvmet_req_complete(req, status);
 }
 
+static u32 nvmet_format_ana_group(struct nvmet_req *req, u32 grpid,
+		struct nvme_ana_group_desc *desc)
+{
+	struct nvmet_ctrl *ctrl = req->sq->ctrl;
+	struct nvmet_ns *ns;
+	u32 count = 0;
+
+	if (!(req->cmd->get_log_page.lsp & NVME_ANA_LOG_RGO)) {
+		rcu_read_lock();
+		list_for_each_entry_rcu(ns, &ctrl->subsys->namespaces, dev_link)
+			if (ns->anagrpid == grpid)
+				desc->nsids[count++] = cpu_to_le32(ns->nsid);
+		rcu_read_unlock();
+	}
+
+	desc->grpid = cpu_to_le32(grpid);
+	desc->nnsids = cpu_to_le32(count);
+	desc->chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	desc->state = req->port->ana_state[grpid];
+	memset(desc->rsvd17, 0, sizeof(desc->rsvd17));
+	return sizeof(struct nvme_ana_group_desc) + count * sizeof(__le32);
+}
+
+static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
+{
+	struct nvme_ana_rsp_hdr hdr = { 0, };
+	struct nvme_ana_group_desc *desc;
+	size_t offset = sizeof(struct nvme_ana_rsp_hdr); /* start beyond hdr */
+	size_t len;
+	u32 grpid;
+	u16 ngrps = 0;
+	u16 status;
+
+	status = NVME_SC_INTERNAL;
+	desc = kmalloc(sizeof(struct nvme_ana_group_desc) +
+			NVMET_MAX_NAMESPACES * sizeof(__le32), GFP_KERNEL);
+	if (!desc)
+		goto out;
+
+	down_read(&nvmet_ana_sem);
+	for (grpid = 1; grpid <= NVMET_MAX_ANAGRPS; grpid++) {
+		if (!nvmet_ana_group_enabled[grpid])
+			continue;
+		len = nvmet_format_ana_group(req, grpid, desc);
+		status = nvmet_copy_to_sgl(req, offset, desc, len);
+		if (status)
+			break;
+		offset += len;
+		ngrps++;
+	}
+
+	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
+	hdr.ngrps = cpu_to_le16(ngrps);
+	up_read(&nvmet_ana_sem);
+
+	kfree(desc);
+
+	/* copy the header last once we know the number of groups */
+	status = nvmet_copy_to_sgl(req, 0, &hdr, sizeof(hdr));
+out:
+	nvmet_req_complete(req, status);
+}
+
 static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 {
 	struct nvmet_ctrl *ctrl = req->sq->ctrl;
@@ -213,8 +276,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	 * the safest is to leave it as zeroes.
 	 */
 
-	/* we support multiple ports and multiples hosts: */
-	id->cmic = (1 << 0) | (1 << 1);
+	/* we support multiple ports, multiples hosts and ANA: */
+	id->cmic = (1 << 0) | (1 << 1) | (1 << 3);
 
 	/* no limit on data transfer sizes for now */
 	id->mdts = 0;
@@ -282,6 +345,11 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 
 	id->msdbd = ctrl->ops->msdbd;
 
+	id->anacap = (1 << 0) | (1 << 1) | (1 << 2) | (1 << 3) | (1 << 4);
+	id->anatt = 10; /* random value */
+	id->anagrpmax = cpu_to_le32(NVMET_MAX_ANAGRPS);
+	id->nanagrpid = cpu_to_le32(NVMET_MAX_ANAGRPS);
+
 	/*
 	 * Meh, we don't really support any power state.  Fake up the same
 	 * values that qemu does.
@@ -323,8 +391,15 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * nuse = ncap = nsze isn't always true, but we have no way to find
 	 * that out from the underlying device.
 	 */
-	id->ncap = id->nuse = id->nsze =
-		cpu_to_le64(ns->size >> ns->blksize_shift);
+	id->ncap = id->nsze = cpu_to_le64(ns->size >> ns->blksize_shift);
+	switch (req->port->ana_state[ns->anagrpid]) {
+	case NVME_ANA_INACCESSIBLE:
+	case NVME_ANA_PERSISTENT_LOSS:
+		break;
+	default:
+		id->nuse = id->nsze;
+		break;
+        }
 
 	/*
 	 * We just provide a single LBA format that matches what the
@@ -338,6 +413,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 	 * controllers, but also with any other user of the block device.
 	 */
 	id->nmic = (1 << 0);
+	id->anagrpid = cpu_to_le32(ns->anagrpid);
 
 	memcpy(&id->nguid, &ns->nguid, sizeof(id->nguid));
 
@@ -620,6 +696,9 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
 		case NVME_LOG_CMD_EFFECTS:
 			req->execute = nvmet_execute_get_log_cmd_effects_ns;
 			return 0;
+		case NVME_LOG_ANA:
+			req->execute = nvmet_execute_get_log_page_ana;
+			return 0;
 		}
 		break;
 	case nvme_admin_identify:
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index 3ba5ea5c4376..b3c62b41b2ae 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -923,6 +923,7 @@ static void nvmet_port_release(struct config_item *item)
 {
 	struct nvmet_port *port = to_nvmet_port(item);
 
+	kfree(port->ana_state);
 	kfree(port);
 }
 
@@ -959,6 +960,15 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 	if (!port)
 		return ERR_PTR(-ENOMEM);
 
+	port->ana_state = kcalloc(NVMET_MAX_ANAGRPS + 1,
+			sizeof(*port->ana_state), GFP_KERNEL);
+	if (!port->ana_state) {
+		kfree(port);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	port->ana_state[NVMET_DEFAULT_ANA_GRPID] = NVME_ANA_OPTIMIZED;
+
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
 	INIT_LIST_HEAD(&port->referrals);
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 42e8565015d5..43a755f7baa5 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -40,6 +40,10 @@ static DEFINE_IDA(cntlid_ida);
  */
 DECLARE_RWSEM(nvmet_config_sem);
 
+u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+u64 nvmet_ana_chgcnt;
+DECLARE_RWSEM(nvmet_ana_sem);
+
 static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
 		const char *subsysnqn);
 
@@ -430,6 +434,10 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 {
 	nvmet_ns_disable(ns);
 
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[ns->anagrpid]--;
+	up_write(&nvmet_ana_sem);
+
 	kfree(ns->device_path);
 	kfree(ns);
 }
@@ -447,6 +455,12 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 
 	ns->nsid = nsid;
 	ns->subsys = subsys;
+
+	down_write(&nvmet_ana_sem);
+	ns->anagrpid = NVMET_DEFAULT_ANA_GRPID;
+	nvmet_ana_group_enabled[ns->anagrpid]++;
+	up_write(&nvmet_ana_sem);
+
 	uuid_gen(&ns->uuid);
 	ns->buffered_io = false;
 
@@ -554,6 +568,20 @@ int nvmet_sq_init(struct nvmet_sq *sq)
 }
 EXPORT_SYMBOL_GPL(nvmet_sq_init);
 
+static inline u16 nvmet_check_ana_state(struct nvmet_port *port,
+		struct nvmet_ns *ns)
+{
+	enum nvme_ana_state state = port->ana_state[ns->anagrpid];
+
+	if (unlikely(state == NVME_ANA_INACCESSIBLE))
+		return NVME_SC_ANA_INACCESSIBLE;
+	if (unlikely(state == NVME_ANA_PERSISTENT_LOSS))
+		return NVME_SC_ANA_PERSISTENT_LOSS;
+	if (unlikely(state == NVME_ANA_CHANGE))
+		return NVME_SC_ANA_TRANSITION;
+	return 0;
+}
+
 static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
@@ -566,6 +594,9 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 	req->ns = nvmet_find_namespace(req->sq->ctrl, cmd->rw.nsid);
 	if (unlikely(!req->ns))
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+	ret = nvmet_check_ana_state(req->port, req->ns);
+	if (unlikely(ret))
+		return ret;
 
 	if (req->ns->file)
 		return nvmet_file_parse_io_cmd(req);
@@ -1123,12 +1154,15 @@ static int __init nvmet_init(void)
 {
 	int error;
 
+	nvmet_ana_group_enabled[NVMET_DEFAULT_ANA_GRPID] = 1;
+
 	buffered_io_wq = alloc_workqueue("nvmet-buffered-io-wq",
 			WQ_MEM_RECLAIM, 0);
 	if (!buffered_io_wq) {
 		error = -ENOMEM;
 		goto out;
 	}
+
 	error = nvmet_init_discovery();
 	if (error)
 		goto out;
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 701017f7f3df..f7d622fc1aa7 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -64,6 +64,7 @@ struct nvmet_ns {
 	loff_t			size;
 	u8			nguid[16];
 	uuid_t			uuid;
+	u32			anagrpid;
 
 	bool			buffered_io;
 	bool			enabled;
@@ -115,6 +116,7 @@ struct nvmet_port {
 	struct list_head		subsystems;
 	struct config_group		referrals_group;
 	struct list_head		referrals;
+	enum nvme_ana_state		*ana_state;
 	void				*priv;
 	bool				enabled;
 	int				inline_data_size;
@@ -370,6 +372,15 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
  */
 #define NVMET_MAX_NAMESPACES	1024
 
+/*
+ * 0 is not a valid ANA group ID, so we start numbering at 1.
+ *
+ * ANA Group 1 exists without manual intervention, has namespaces assigned to it
+ * by default, and is available in an optimized state through all ports.
+ */
+#define NVMET_MAX_ANAGRPS	1
+#define NVMET_DEFAULT_ANA_GRPID	1
+
 #define NVMET_KAS		10
 #define NVMET_DISC_KATO		120
 
@@ -383,6 +394,10 @@ extern struct nvmet_subsys *nvmet_disc_subsys;
 extern u64 nvmet_genctr;
 extern struct rw_semaphore nvmet_config_sem;
 
+extern u32 nvmet_ana_group_enabled[NVMET_MAX_ANAGRPS + 1];
+extern u64 nvmet_ana_chgcnt;
+extern struct rw_semaphore nvmet_ana_sem;
+
 bool nvmet_host_allowed(struct nvmet_req *req, struct nvmet_subsys *subsys,
 		const char *hostnqn);
 
-- 
cgit v1.2.3


From 62ac0d32f74ea511d5813be728dc589d03f866a3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 1 Jun 2018 08:59:25 +0200
Subject: nvmet: support configuring ANA groups

Allow creating non-default ANA groups (group ID > 1).  Groups are created
either by assigning the group ID to a namespace, or by creating a configfs
group object under a specific port.  All namespaces assigned to a group
that doesn't have a configfs object for a given port are marked as
inaccessible.

Allow changing the ANA state on a per-port basis by creating an
ana_groups directory under each port, and another directory with an
ana_state file in it.  The default ANA group 1 directory is created
automatically for each port.

For all changes in ANA configuration the ANA change AEN is sent.  We only
keep a global changecount instead of additional per-group changecounts to
keep the implementation as simple as possible.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <keith.busch@intel.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
---
 drivers/nvme/target/admin-cmd.c |   1 +
 drivers/nvme/target/configfs.c  | 182 +++++++++++++++++++++++++++++++++++++++-
 drivers/nvme/target/core.c      |  27 ++++++
 drivers/nvme/target/nvmet.h     |  30 ++++++-
 4 files changed, 236 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index b98d38c4e579..d1de639786ee 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -235,6 +235,7 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
 
 	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
 	hdr.ngrps = cpu_to_le16(ngrps);
+	clear_bit(NVME_AEN_CFG_ANA_CHANGE, &req->sq->ctrl->aen_masked);
 	up_read(&nvmet_ana_sem);
 
 	kfree(desc);
diff --git a/drivers/nvme/target/configfs.c b/drivers/nvme/target/configfs.c
index b3c62b41b2ae..51f5a8c092b4 100644
--- a/drivers/nvme/target/configfs.c
+++ b/drivers/nvme/target/configfs.c
@@ -411,6 +411,39 @@ out_unlock:
 
 CONFIGFS_ATTR(nvmet_ns_, device_nguid);
 
+static ssize_t nvmet_ns_ana_grpid_show(struct config_item *item, char *page)
+{
+	return sprintf(page, "%u\n", to_nvmet_ns(item)->anagrpid);
+}
+
+static ssize_t nvmet_ns_ana_grpid_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ns *ns = to_nvmet_ns(item);
+	u32 oldgrpid, newgrpid;
+	int ret;
+
+	ret = kstrtou32(page, 0, &newgrpid);
+	if (ret)
+		return ret;
+
+	if (newgrpid < 1 || newgrpid > NVMET_MAX_ANAGRPS)
+		return -EINVAL;
+
+	down_write(&nvmet_ana_sem);
+	oldgrpid = ns->anagrpid;
+	nvmet_ana_group_enabled[newgrpid]++;
+	ns->anagrpid = newgrpid;
+	nvmet_ana_group_enabled[oldgrpid]--;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_send_ana_event(ns->subsys, NULL);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ns_, ana_grpid);
+
 static ssize_t nvmet_ns_enable_show(struct config_item *item, char *page)
 {
 	return sprintf(page, "%d\n", to_nvmet_ns(item)->enabled);
@@ -468,6 +501,7 @@ static struct configfs_attribute *nvmet_ns_attrs[] = {
 	&nvmet_ns_attr_device_path,
 	&nvmet_ns_attr_device_nguid,
 	&nvmet_ns_attr_device_uuid,
+	&nvmet_ns_attr_ana_grpid,
 	&nvmet_ns_attr_enable,
 	&nvmet_ns_attr_buffered_io,
 	NULL,
@@ -916,6 +950,134 @@ static const struct config_item_type nvmet_referrals_type = {
 	.ct_group_ops	= &nvmet_referral_group_ops,
 };
 
+static struct {
+	enum nvme_ana_state	state;
+	const char		*name;
+} nvmet_ana_state_names[] = {
+	{ NVME_ANA_OPTIMIZED,		"optimized" },
+	{ NVME_ANA_NONOPTIMIZED,	"non-optimized" },
+	{ NVME_ANA_INACCESSIBLE,	"inaccessible" },
+	{ NVME_ANA_PERSISTENT_LOSS,	"persistent-loss" },
+	{ NVME_ANA_CHANGE,		"change" },
+};
+
+static ssize_t nvmet_ana_group_ana_state_show(struct config_item *item,
+		char *page)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	enum nvme_ana_state state = grp->port->ana_state[grp->grpid];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (state != nvmet_ana_state_names[i].state)
+			continue;
+		return sprintf(page, "%s\n", nvmet_ana_state_names[i].name);
+	}
+
+	return sprintf(page, "\n");
+}
+
+static ssize_t nvmet_ana_group_ana_state_store(struct config_item *item,
+		const char *page, size_t count)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nvmet_ana_state_names); i++) {
+		if (sysfs_streq(page, nvmet_ana_state_names[i].name))
+			goto found;
+	}
+
+	pr_err("Invalid value '%s' for ana_state\n", page);
+	return -EINVAL;
+
+found:
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = nvmet_ana_state_names[i].state;
+	nvmet_ana_chgcnt++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	return count;
+}
+
+CONFIGFS_ATTR(nvmet_ana_group_, ana_state);
+
+static struct configfs_attribute *nvmet_ana_group_attrs[] = {
+	&nvmet_ana_group_attr_ana_state,
+	NULL,
+};
+
+static void nvmet_ana_group_release(struct config_item *item)
+{
+	struct nvmet_ana_group *grp = to_ana_group(item);
+
+	if (grp == &grp->port->ana_default_group)
+		return;
+
+	down_write(&nvmet_ana_sem);
+	grp->port->ana_state[grp->grpid] = NVME_ANA_INACCESSIBLE;
+	nvmet_ana_group_enabled[grp->grpid]--;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+	kfree(grp);
+}
+
+static struct configfs_item_operations nvmet_ana_group_item_ops = {
+	.release		= nvmet_ana_group_release,
+};
+
+static const struct config_item_type nvmet_ana_group_type = {
+	.ct_item_ops		= &nvmet_ana_group_item_ops,
+	.ct_attrs		= nvmet_ana_group_attrs,
+	.ct_owner		= THIS_MODULE,
+};
+
+static struct config_group *nvmet_ana_groups_make_group(
+		struct config_group *group, const char *name)
+{
+	struct nvmet_port *port = ana_groups_to_port(&group->cg_item);
+	struct nvmet_ana_group *grp;
+	u32 grpid;
+	int ret;
+
+	ret = kstrtou32(name, 0, &grpid);
+	if (ret)
+		goto out;
+
+	ret = -EINVAL;
+	if (grpid <= 1 || grpid > NVMET_MAX_ANAGRPS)
+		goto out;
+
+	ret = -ENOMEM;
+	grp = kzalloc(sizeof(*grp), GFP_KERNEL);
+	if (!grp)
+		goto out;
+	grp->port = port;
+	grp->grpid = grpid;
+
+	down_write(&nvmet_ana_sem);
+	nvmet_ana_group_enabled[grpid]++;
+	up_write(&nvmet_ana_sem);
+
+	nvmet_port_send_ana_event(grp->port);
+
+	config_group_init_type_name(&grp->group, name, &nvmet_ana_group_type);
+	return &grp->group;
+out:
+	return ERR_PTR(ret);
+}
+
+static struct configfs_group_operations nvmet_ana_groups_group_ops = {
+	.make_group		= nvmet_ana_groups_make_group,
+};
+
+static const struct config_item_type nvmet_ana_groups_type = {
+	.ct_group_ops		= &nvmet_ana_groups_group_ops,
+	.ct_owner		= THIS_MODULE,
+};
+
 /*
  * Ports definitions.
  */
@@ -952,6 +1114,7 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 {
 	struct nvmet_port *port;
 	u16 portid;
+	u32 i;
 
 	if (kstrtou16(name, 0, &portid))
 		return ERR_PTR(-EINVAL);
@@ -967,7 +1130,12 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 		return ERR_PTR(-ENOMEM);
 	}
 
-	port->ana_state[NVMET_DEFAULT_ANA_GRPID] = NVME_ANA_OPTIMIZED;
+	for (i = 1; i <= NVMET_MAX_ANAGRPS; i++) {
+		if (i == NVMET_DEFAULT_ANA_GRPID)
+			port->ana_state[1] = NVME_ANA_OPTIMIZED;
+		else
+			port->ana_state[i] = NVME_ANA_INACCESSIBLE;
+	}
 
 	INIT_LIST_HEAD(&port->entry);
 	INIT_LIST_HEAD(&port->subsystems);
@@ -985,6 +1153,18 @@ static struct config_group *nvmet_ports_make(struct config_group *group,
 			"referrals", &nvmet_referrals_type);
 	configfs_add_default_group(&port->referrals_group, &port->group);
 
+	config_group_init_type_name(&port->ana_groups_group,
+			"ana_groups", &nvmet_ana_groups_type);
+	configfs_add_default_group(&port->ana_groups_group, &port->group);
+
+	port->ana_default_group.port = port;
+	port->ana_default_group.grpid = NVMET_DEFAULT_ANA_GRPID;
+	config_group_init_type_name(&port->ana_default_group.group,
+			__stringify(NVMET_DEFAULT_ANA_GRPID),
+			&nvmet_ana_group_type);
+	configfs_add_default_group(&port->ana_default_group.group,
+			&port->ana_groups_group);
+
 	return &port->group;
 }
 
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 43a755f7baa5..3ceb7a03bb2a 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -194,6 +194,33 @@ static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 	}
 }
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port)
+{
+	struct nvmet_ctrl *ctrl;
+
+	mutex_lock(&subsys->lock);
+	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry) {
+		if (port && ctrl->port != port)
+			continue;
+		if (nvmet_aen_disabled(ctrl, NVME_AEN_CFG_ANA_CHANGE))
+			continue;
+		nvmet_add_async_event(ctrl, NVME_AER_TYPE_NOTICE,
+				NVME_AER_NOTICE_ANA, NVME_LOG_ANA);
+	}
+	mutex_unlock(&subsys->lock);
+}
+
+void nvmet_port_send_ana_event(struct nvmet_port *port)
+{
+	struct nvmet_subsys_link *p;
+
+	down_read(&nvmet_config_sem);
+	list_for_each_entry(p, &port->subsystems, entry)
+		nvmet_send_ana_event(p->subsys, port);
+	up_read(&nvmet_config_sem);
+}
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops)
 {
 	int ret = 0;
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index f7d622fc1aa7..22941045f46e 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -30,12 +30,11 @@
 #define NVMET_ASYNC_EVENTS		4
 #define NVMET_ERROR_LOG_SLOTS		128
 
-
 /*
  * Supported optional AENs:
  */
 #define NVMET_AEN_CFG_OPTIONAL \
-	NVME_AEN_CFG_NS_ATTR
+	(NVME_AEN_CFG_NS_ATTR | NVME_AEN_CFG_ANA_CHANGE)
 
 /*
  * Plus mandatory SMART AENs (we'll never send them, but allow enabling them):
@@ -99,6 +98,18 @@ struct nvmet_sq {
 	struct completion	confirm_done;
 };
 
+struct nvmet_ana_group {
+	struct config_group	group;
+	struct nvmet_port	*port;
+	u32			grpid;
+};
+
+static inline struct nvmet_ana_group *to_ana_group(struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_ana_group,
+			group);
+}
+
 /**
  * struct nvmet_port -	Common structure to keep port
  *				information for the target.
@@ -116,6 +127,8 @@ struct nvmet_port {
 	struct list_head		subsystems;
 	struct config_group		referrals_group;
 	struct list_head		referrals;
+	struct config_group		ana_groups_group;
+	struct nvmet_ana_group		ana_default_group;
 	enum nvme_ana_state		*ana_state;
 	void				*priv;
 	bool				enabled;
@@ -128,6 +141,13 @@ static inline struct nvmet_port *to_nvmet_port(struct config_item *item)
 			group);
 }
 
+static inline struct nvmet_port *ana_groups_to_port(
+		struct config_item *item)
+{
+	return container_of(to_config_group(item), struct nvmet_port,
+			ana_groups_group);
+}
+
 struct nvmet_ctrl {
 	struct nvmet_subsys	*subsys;
 	struct nvmet_cq		**cqs;
@@ -345,6 +365,10 @@ void nvmet_ns_disable(struct nvmet_ns *ns);
 struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid);
 void nvmet_ns_free(struct nvmet_ns *ns);
 
+void nvmet_send_ana_event(struct nvmet_subsys *subsys,
+		struct nvmet_port *port);
+void nvmet_port_send_ana_event(struct nvmet_port *port);
+
 int nvmet_register_transport(const struct nvmet_fabrics_ops *ops);
 void nvmet_unregister_transport(const struct nvmet_fabrics_ops *ops);
 
@@ -378,7 +402,7 @@ u32 nvmet_get_log_page_len(struct nvme_command *cmd);
  * ANA Group 1 exists without manual intervention, has namespaces assigned to it
  * by default, and is available in an optimized state through all ports.
  */
-#define NVMET_MAX_ANAGRPS	1
+#define NVMET_MAX_ANAGRPS	128
 #define NVMET_DEFAULT_ANA_GRPID	1
 
 #define NVMET_KAS		10
-- 
cgit v1.2.3


From b369b30cf510fe94d8884837039362e2ec223cec Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Thu, 26 Jul 2018 14:00:41 -0700
Subject: nvmet: use Retain Async Event bit to clear AEN

In the current implementation, we clear the AEN bit when we get the
"get log page" command if given log page is associated with AEN.
This patch allows optionally retaining the AEN for the ctrl
under consideration when Retain Asynchronous Event (RAE) bit is set
as a part of "get log page" command.

This allows the host to read the Log page and optionally retaining the
AEN associated with this log page when using userspace tools like
nvme-cli.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
[hch: also use the new helper in the just merged ANA code]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/admin-cmd.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index d1de639786ee..f517bc562d26 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -19,6 +19,19 @@
 #include <asm/unaligned.h>
 #include "nvmet.h"
 
+/*
+ * This helper allows us to clear the AEN based on the RAE bit,
+ * Please use this helper when processing the log pages which are
+ * associated with the AEN.
+ */
+static inline void nvmet_clear_aen(struct nvmet_req *req, u32 aen_bit)
+{
+	int rae = le32_to_cpu(req->cmd->common.cdw10[0]) & 1 << 15;
+
+	if (!rae)
+		clear_bit(aen_bit, &req->sq->ctrl->aen_masked);
+}
+
 u32 nvmet_get_log_page_len(struct nvme_command *cmd)
 {
 	u32 len = le16_to_cpu(cmd->get_log_page.numdu);
@@ -176,7 +189,7 @@ static void nvmet_execute_get_log_changed_ns(struct nvmet_req *req)
 	if (!status)
 		status = nvmet_zero_sgl(req, len, req->data_len - len);
 	ctrl->nr_changed_ns = 0;
-	clear_bit(NVME_AEN_CFG_NS_ATTR, &ctrl->aen_masked);
+	nvmet_clear_aen(req, NVME_AEN_CFG_NS_ATTR);
 	mutex_unlock(&ctrl->lock);
 out:
 	nvmet_req_complete(req, status);
@@ -235,7 +248,7 @@ static void nvmet_execute_get_log_page_ana(struct nvmet_req *req)
 
 	hdr.chgcnt = cpu_to_le64(nvmet_ana_chgcnt);
 	hdr.ngrps = cpu_to_le16(ngrps);
-	clear_bit(NVME_AEN_CFG_ANA_CHANGE, &req->sq->ctrl->aen_masked);
+	nvmet_clear_aen(req, NVME_AEN_CFG_ANA_CHANGE);
 	up_read(&nvmet_ana_sem);
 
 	kfree(desc);
-- 
cgit v1.2.3


From 2ac305b7c8d7f93a6ef0018391e9865ea4ac0d65 Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Thu, 26 Jul 2018 16:32:08 +0800
Subject: drm/ttm: add ttm_set_memory header (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch moves all non-x86 abstraction to the ttm_set_memory header.
It is to make function calling more clearly.

(v2): add ttm_ prefix.

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Bas Nieuwenhuizen <basni@chromium.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/drm/ttm/ttm_set_memory.h | 128 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 128 insertions(+)
 create mode 100644 include/drm/ttm/ttm_set_memory.h

diff --git a/include/drm/ttm/ttm_set_memory.h b/include/drm/ttm/ttm_set_memory.h
new file mode 100644
index 000000000000..a70723cf208b
--- /dev/null
+++ b/include/drm/ttm/ttm_set_memory.h
@@ -0,0 +1,128 @@
+/**************************************************************************
+ *
+ * Copyright (c) 2018 Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+ * "Software"), to deal in the Software without restriction, including
+ * without limitation the rights to use, copy, modify, merge, publish,
+ * distribute, sub license, and/or sell copies of the Software, and to
+ * permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the
+ * next paragraph) shall be included in all copies or substantial portions
+ * of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT. IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDERS, AUTHORS AND/OR ITS SUPPLIERS BE LIABLE FOR ANY CLAIM,
+ * DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
+ * OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
+ * USE OR OTHER DEALINGS IN THE SOFTWARE.
+ *
+ **************************************************************************/
+/*
+ * Authors: Huang Rui <ray.huang@amd.com>
+ */
+
+#ifndef TTM_SET_MEMORY
+#define TTM_SET_MEMORY
+
+#include <linux/mm.h>
+
+#ifdef CONFIG_X86
+
+#include <asm/set_memory.h>
+
+static inline int ttm_set_pages_array_wb(struct page **pages, int addrinarray)
+{
+	return set_pages_array_wb(pages, addrinarray);
+}
+
+static inline int ttm_set_pages_array_wc(struct page **pages, int addrinarray)
+{
+	return set_pages_array_wc(pages, addrinarray);
+}
+
+static inline int ttm_set_pages_array_uc(struct page **pages, int addrinarray)
+{
+	return set_pages_array_uc(pages, addrinarray);
+}
+
+static inline int ttm_set_pages_wb(struct page *page, int numpages)
+{
+	return set_pages_wb(page, numpages);
+}
+
+#else /* for CONFIG_X86 */
+
+#if IS_ENABLED(CONFIG_AGP)
+
+#include <asm/agp.h>
+
+static inline int ttm_set_pages_array_wb(struct page **pages, int addrinarray)
+{
+	int i;
+
+	for (i = 0; i < addrinarray; i++)
+		unmap_page_from_agp(pages[i]);
+	return 0;
+}
+
+static inline int ttm_set_pages_array_wc(struct page **pages, int addrinarray)
+{
+	int i;
+
+	for (i = 0; i < addrinarray; i++)
+		map_page_into_agp(pages[i]);
+	return 0;
+}
+
+static inline int ttm_set_pages_array_uc(struct page **pages, int addrinarray)
+{
+	int i;
+
+	for (i = 0; i < addrinarray; i++)
+		map_page_into_agp(pages[i]);
+	return 0;
+}
+
+static inline int ttm_set_pages_wb(struct page *page, int numpages)
+{
+	int i;
+
+	for (i = 0; i < numpages; i++)
+		unmap_page_from_agp(page++);
+	return 0;
+}
+
+#else /* for CONFIG_AGP */
+
+static inline int ttm_set_pages_array_wb(struct page **pages, int addrinarray)
+{
+	return 0;
+}
+
+static inline int ttm_set_pages_array_wc(struct page **pages, int addrinarray)
+{
+	return 0;
+}
+
+static inline int ttm_set_pages_array_uc(struct page **pages, int addrinarray)
+{
+	return 0;
+}
+
+static inline int ttm_set_pages_wb(struct page *page, int numpages)
+{
+	return 0;
+}
+
+#endif /* for CONFIG_AGP */
+
+#endif /* for CONFIG_X86 */
+
+#endif
-- 
cgit v1.2.3


From c7bb1e57e20a7f43b52df183d1a5a1aa936acc2d Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Thu, 26 Jul 2018 16:48:54 +0800
Subject: drm/ttm: clean up non-x86 definitions on ttm_page_alloc_dma
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All non-x86 definitions are moved to ttm_set_memory header, so remove it from
ttm_page_alloc_dma.c.

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Bas Nieuwenhuizen <basni@chromium.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 48 +++-----------------------------
 1 file changed, 4 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 3f14c1cc0789..f31148ad981c 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -50,12 +50,7 @@
 #include <linux/kthread.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_page_alloc.h>
-#if IS_ENABLED(CONFIG_AGP)
-#include <asm/agp.h>
-#endif
-#ifdef CONFIG_X86
-#include <asm/set_memory.h>
-#endif
+#include <drm/ttm/ttm_set_memory.h>
 
 #define NUM_PAGES_TO_ALLOC		(PAGE_SIZE/sizeof(struct page *))
 #define SMALL_ALLOCATION		4
@@ -268,41 +263,6 @@ static struct kobj_type ttm_pool_kobj_type = {
 	.default_attrs = ttm_pool_attrs,
 };
 
-#ifndef CONFIG_X86
-static int set_pages_array_wb(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		unmap_page_from_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_wc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_uc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-#endif /* for !CONFIG_X86 */
-
 static int ttm_set_pages_caching(struct dma_pool *pool,
 				 struct page **pages, unsigned cpages)
 {
@@ -315,7 +275,7 @@ static int ttm_set_pages_caching(struct dma_pool *pool,
 			       pool->dev_name, cpages);
 	}
 	if (pool->type & IS_WC) {
-		r = set_pages_array_wc(pages, cpages);
+		r = ttm_set_pages_array_wc(pages, cpages);
 		if (r)
 			pr_err("%s: Failed to set %d pages to wc!\n",
 			       pool->dev_name, cpages);
@@ -395,7 +355,7 @@ static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
 	if (!(pool->type & IS_CACHED)) {
 		num_pages = pool->size / PAGE_SIZE;
 		for (i = 0; i < num_pages; ++i, ++page) {
-			if (set_pages_array_wb(&page, 1)) {
+			if (ttm_set_pages_array_wb(&page, 1)) {
 				pr_err("%s: Failed to set %d pages to wb!\n",
 				       pool->dev_name, 1);
 			}
@@ -420,7 +380,7 @@ static void ttm_dma_pages_put(struct dma_pool *pool, struct list_head *d_pages,
 
 	/* Don't set WB on WB page pool. */
 	if (npages && !(pool->type & IS_CACHED) &&
-	    set_pages_array_wb(pages, npages))
+	    ttm_set_pages_array_wb(pages, npages))
 		pr_err("%s: Failed to set %d pages to wb!\n",
 		       pool->dev_name, npages);
 
-- 
cgit v1.2.3


From d55f9b87428f4732472ec7e9ccb7b4135751996c Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Thu, 26 Jul 2018 16:49:36 +0800
Subject: drm/ttm: clean up non-x86 definitions on ttm_page_alloc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All non-x86 definitions are moved to ttm_set_memory header, so remove it from
ttm_page_alloc.c.

Suggested-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Bas Nieuwenhuizen <basni@chromium.org>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc.c | 62 +++---------------------------------
 1 file changed, 5 insertions(+), 57 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc.c b/drivers/gpu/drm/ttm/ttm_page_alloc.c
index 6e2d1300b457..f841accc2c00 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc.c
@@ -47,13 +47,7 @@
 
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_page_alloc.h>
-
-#if IS_ENABLED(CONFIG_AGP)
-#include <asm/agp.h>
-#endif
-#ifdef CONFIG_X86
-#include <asm/set_memory.h>
-#endif
+#include <drm/ttm/ttm_set_memory.h>
 
 #define NUM_PAGES_TO_ALLOC		(PAGE_SIZE/sizeof(struct page *))
 #define SMALL_ALLOCATION		16
@@ -222,52 +216,6 @@ static struct kobj_type ttm_pool_kobj_type = {
 
 static struct ttm_pool_manager *_manager;
 
-#ifndef CONFIG_X86
-static int set_pages_wb(struct page *page, int numpages)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < numpages; i++)
-		unmap_page_from_agp(page++);
-#endif
-	return 0;
-}
-
-static int set_pages_array_wb(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		unmap_page_from_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_wc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-
-static int set_pages_array_uc(struct page **pages, int addrinarray)
-{
-#if IS_ENABLED(CONFIG_AGP)
-	int i;
-
-	for (i = 0; i < addrinarray; i++)
-		map_page_into_agp(pages[i]);
-#endif
-	return 0;
-}
-#endif
-
 /**
  * Select the right pool or requested caching state and ttm flags. */
 static struct ttm_page_pool *ttm_get_pool(int flags, bool huge,
@@ -302,13 +250,13 @@ static void ttm_pages_put(struct page *pages[], unsigned npages,
 	unsigned int i, pages_nr = (1 << order);
 
 	if (order == 0) {
-		if (set_pages_array_wb(pages, npages))
+		if (ttm_set_pages_array_wb(pages, npages))
 			pr_err("Failed to set %d pages to wb!\n", npages);
 	}
 
 	for (i = 0; i < npages; ++i) {
 		if (order > 0) {
-			if (set_pages_wb(pages[i], pages_nr))
+			if (ttm_set_pages_wb(pages[i], pages_nr))
 				pr_err("Failed to set %d pages to wb!\n", pages_nr);
 		}
 		__free_pages(pages[i], order);
@@ -498,12 +446,12 @@ static int ttm_set_pages_caching(struct page **pages,
 	/* Set page caching */
 	switch (cstate) {
 	case tt_uncached:
-		r = set_pages_array_uc(pages, cpages);
+		r = ttm_set_pages_array_uc(pages, cpages);
 		if (r)
 			pr_err("Failed to set %d pages to uc!\n", cpages);
 		break;
 	case tt_wc:
-		r = set_pages_array_wc(pages, cpages);
+		r = ttm_set_pages_array_wc(pages, cpages);
 		if (r)
 			pr_err("Failed to set %d pages to wc!\n", cpages);
 		break;
-- 
cgit v1.2.3


From 610b399f1ff269e4b9ec85cfdffb06f9befd0c41 Mon Sep 17 00:00:00 2001
From: Bas Nieuwenhuizen <basni@chromium.org>
Date: Wed, 25 Jul 2018 22:29:50 +0200
Subject: drm/ttm: Merge hugepage attr changes in ttm_dma_page_put. (v2)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Every set_pages_array_wb call resulted in cross-core
interrupts and TLB flushes. Merge more of them for
less overhead.

This reduces the time needed to free a 1.6 GiB GTT WC
buffer as part of Vulkan CTS from  ~2 sec to < 0.25 sec.
(Allocation still takes more than 2 sec though)

(v2): use set_pages_wb instead of set_memory_wb.

Signed-off-by: Bas Nieuwenhuizen <basni@chromium.org>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index f31148ad981c..8304917294a2 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -349,17 +349,14 @@ static void ttm_pool_update_free_locked(struct dma_pool *pool,
 static void ttm_dma_page_put(struct dma_pool *pool, struct dma_page *d_page)
 {
 	struct page *page = d_page->p;
-	unsigned i, num_pages;
+	unsigned num_pages;
 
 	/* Don't set WB on WB page pool. */
 	if (!(pool->type & IS_CACHED)) {
 		num_pages = pool->size / PAGE_SIZE;
-		for (i = 0; i < num_pages; ++i, ++page) {
-			if (ttm_set_pages_array_wb(&page, 1)) {
-				pr_err("%s: Failed to set %d pages to wb!\n",
-				       pool->dev_name, 1);
-			}
-		}
+		if (ttm_set_pages_wb(page, num_pages))
+			pr_err("%s: Failed to set %d pages to wb!\n",
+			       pool->dev_name, num_pages);
 	}
 
 	list_del(&d_page->page_list);
-- 
cgit v1.2.3


From 204029e1979959ea6150c2a5c3e961800f52d0d4 Mon Sep 17 00:00:00 2001
From: Junwei Zhang <Jerry.Zhang@amd.com>
Date: Thu, 26 Jul 2018 18:00:13 +0800
Subject: drm/amdgpu: correct evict flag for bo move
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

pass the evict flag instead of hard code

Signed-off-by: Junwei Zhang <Jerry.Zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 8c4358e36c87..c1ae528c7b0e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -580,7 +580,7 @@ static int amdgpu_move_vram_ram(struct ttm_buffer_object *bo, bool evict,
 	}
 
 	/* blit VRAM to GTT */
-	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, &tmp_mem, old_mem);
+	r = amdgpu_move_blit(bo, evict, ctx->no_wait_gpu, &tmp_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
@@ -632,7 +632,7 @@ static int amdgpu_move_ram_vram(struct ttm_buffer_object *bo, bool evict,
 	}
 
 	/* copy to VRAM */
-	r = amdgpu_move_blit(bo, true, ctx->no_wait_gpu, new_mem, old_mem);
+	r = amdgpu_move_blit(bo, evict, ctx->no_wait_gpu, new_mem, old_mem);
 	if (unlikely(r)) {
 		goto out_cleanup;
 	}
-- 
cgit v1.2.3


From 2e603d0429a4e7cba93a4bc4fcdbdf830adaa472 Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Thu, 26 Jul 2018 14:08:03 +0800
Subject: drm/amdgpu: clean up the superfluous space and align the comment text
 for amdgpu_ttm
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch cleans up spaces and align the text to refine the comment for
amdgpu_ttm.

Signed-off-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 107 +++++++++++++++-----------------
 1 file changed, 51 insertions(+), 56 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index c1ae528c7b0e..fcf421263fd9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -92,11 +92,9 @@ static void amdgpu_ttm_mem_global_release(struct drm_global_reference *ref)
 }
 
 /**
- * amdgpu_ttm_global_init - Initialize global TTM memory reference
- * 							structures.
+ * amdgpu_ttm_global_init - Initialize global TTM memory reference structures.
  *
- * @adev:  	AMDGPU device for which the global structures need to be
- *			registered.
+ * @adev: AMDGPU device for which the global structures need to be registered.
  *
  * This is called as part of the AMDGPU ttm init from amdgpu_ttm_init()
  * during bring up.
@@ -162,13 +160,12 @@ static int amdgpu_invalidate_caches(struct ttm_bo_device *bdev, uint32_t flags)
 }
 
 /**
- * amdgpu_init_mem_type - 	Initialize a memory manager for a specific
- * 							type of memory request.
+ * amdgpu_init_mem_type - Initialize a memory manager for a specific type of
+ * memory request.
  *
- * @bdev:	The TTM BO device object (contains a reference to
- * 			amdgpu_device)
- * @type:	The type of memory requested
- * @man:
+ * @bdev: The TTM BO device object (contains a reference to amdgpu_device)
+ * @type: The type of memory requested
+ * @man: The memory type manager for each domain
  *
  * This is called by ttm_bo_init_mm() when a buffer object is being
  * initialized.
@@ -292,8 +289,8 @@ static void amdgpu_evict_flags(struct ttm_buffer_object *bo,
 /**
  * amdgpu_verify_access - Verify access for a mmap call
  *
- * @bo:		The buffer object to map
- * @filp:	The file pointer from the process performing the mmap
+ * @bo:	The buffer object to map
+ * @filp: The file pointer from the process performing the mmap
  *
  * This is called by ttm_bo_mmap() to verify whether a process
  * has the right to mmap a BO to their process space.
@@ -318,11 +315,10 @@ static int amdgpu_verify_access(struct ttm_buffer_object *bo, struct file *filp)
 /**
  * amdgpu_move_null - Register memory for a buffer object
  *
- * @bo:			The bo to assign the memory to
- * @new_mem:	The memory to be assigned.
+ * @bo: The bo to assign the memory to
+ * @new_mem: The memory to be assigned.
  *
- * Assign the memory from new_mem to the memory of the buffer object
- * bo.
+ * Assign the memory from new_mem to the memory of the buffer object bo.
  */
 static void amdgpu_move_null(struct ttm_buffer_object *bo,
 			     struct ttm_mem_reg *new_mem)
@@ -335,8 +331,12 @@ static void amdgpu_move_null(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_mm_node_addr -	Compute the GPU relative offset of a GTT
- * 							buffer.
+ * amdgpu_mm_node_addr - Compute the GPU relative offset of a GTT buffer.
+ *
+ * @bo: The bo to assign the memory to.
+ * @mm_node: Memory manager node for drm allocator.
+ * @mem: The region where the bo resides.
+ *
  */
 static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 				    struct drm_mm_node *mm_node,
@@ -352,10 +352,12 @@ static uint64_t amdgpu_mm_node_addr(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_find_mm_node -	Helper function finds the drm_mm_node
- *  						corresponding to @offset. It also modifies
- * 							the offset to be within the drm_mm_node
- * 							returned
+ * amdgpu_find_mm_node - Helper function finds the drm_mm_node corresponding to
+ * @offset. It also modifies the offset to be within the drm_mm_node returned
+ *
+ * @mem: The region where the bo resides.
+ * @offset: The offset that drm_mm_node is used for finding.
+ *
  */
 static struct drm_mm_node *amdgpu_find_mm_node(struct ttm_mem_reg *mem,
 					       unsigned long *offset)
@@ -497,8 +499,8 @@ error:
 /**
  * amdgpu_move_blit - Copy an entire buffer to another buffer
  *
- * This is a helper called by amdgpu_bo_move() and
- * amdgpu_move_vram_ram() to help move buffers to and from VRAM.
+ * This is a helper called by amdgpu_bo_move() and amdgpu_move_vram_ram() to
+ * help move buffers to and from VRAM.
  */
 static int amdgpu_move_blit(struct ttm_buffer_object *bo,
 			    bool evict, bool no_wait_gpu,
@@ -794,8 +796,8 @@ struct amdgpu_ttm_tt {
 };
 
 /**
- * amdgpu_ttm_tt_get_user_pages - 	Pin pages of memory pointed to
- * 									by a USERPTR pointer to memory
+ * amdgpu_ttm_tt_get_user_pages - Pin pages of memory pointed to by a USERPTR
+ * pointer to memory
  *
  * Called by amdgpu_gem_userptr_ioctl() and amdgpu_cs_parser_bos().
  * This provides a wrapper around the get_user_pages() call to provide
@@ -818,8 +820,10 @@ int amdgpu_ttm_tt_get_user_pages(struct ttm_tt *ttm, struct page **pages)
 	down_read(&mm->mmap_sem);
 
 	if (gtt->userflags & AMDGPU_GEM_USERPTR_ANONONLY) {
-		/* check that we only use anonymous memory
-		   to prevent problems with writeback */
+		/*
+		 * check that we only use anonymous memory to prevent problems
+		 * with writeback
+		 */
 		unsigned long end = gtt->userptr + ttm->num_pages * PAGE_SIZE;
 		struct vm_area_struct *vma;
 
@@ -870,10 +874,9 @@ release_pages:
 }
 
 /**
- * amdgpu_ttm_tt_set_user_pages - 	Copy pages in, putting old pages
- * 									as necessary.
+ * amdgpu_ttm_tt_set_user_pages - Copy pages in, putting old pages as necessary.
  *
- * Called by amdgpu_cs_list_validate().  This creates the page list
+ * Called by amdgpu_cs_list_validate(). This creates the page list
  * that backs user memory and will ultimately be mapped into the device
  * address space.
  */
@@ -915,8 +918,7 @@ void amdgpu_ttm_tt_mark_user_pages(struct ttm_tt *ttm)
 }
 
 /**
- * amdgpu_ttm_tt_pin_userptr - 	prepare the sg table with the
- * 								user pages
+ * amdgpu_ttm_tt_pin_userptr - 	prepare the sg table with the user pages
  *
  * Called by amdgpu_ttm_backend_bind()
  **/
@@ -1295,8 +1297,8 @@ static void amdgpu_ttm_tt_unpopulate(struct ttm_tt *ttm)
 }
 
 /**
- * amdgpu_ttm_tt_set_userptr -	Initialize userptr GTT ttm_tt
- * 								for the current task
+ * amdgpu_ttm_tt_set_userptr - Initialize userptr GTT ttm_tt for the current
+ * task
  *
  * @ttm: The ttm_tt object to bind this userptr object to
  * @addr:  The address in the current tasks VM space to use
@@ -1346,9 +1348,8 @@ struct mm_struct *amdgpu_ttm_tt_get_usermm(struct ttm_tt *ttm)
 }
 
 /**
- * amdgpu_ttm_tt_affect_userptr -	Determine if a ttm_tt object lays
- * 									inside an address range for the
- * 									current task.
+ * amdgpu_ttm_tt_affect_userptr - Determine if a ttm_tt object lays inside an
+ * address range for the current task.
  *
  */
 bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
@@ -1386,8 +1387,7 @@ bool amdgpu_ttm_tt_affect_userptr(struct ttm_tt *ttm, unsigned long start,
 }
 
 /**
- * amdgpu_ttm_tt_userptr_invalidated -	Has the ttm_tt object been
- * 										invalidated?
+ * amdgpu_ttm_tt_userptr_invalidated - Has the ttm_tt object been invalidated?
  */
 bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
 				       int *last_invalidated)
@@ -1400,10 +1400,8 @@ bool amdgpu_ttm_tt_userptr_invalidated(struct ttm_tt *ttm,
 }
 
 /**
- * amdgpu_ttm_tt_userptr_needs_pages -	Have the pages backing this
- * 										ttm_tt object been invalidated
- * 										since the last time they've
- * 										been set?
+ * amdgpu_ttm_tt_userptr_needs_pages - Have the pages backing this ttm_tt object
+ * been invalidated since the last time they've been set?
  */
 bool amdgpu_ttm_tt_userptr_needs_pages(struct ttm_tt *ttm)
 {
@@ -1459,13 +1457,12 @@ uint64_t amdgpu_ttm_tt_pte_flags(struct amdgpu_device *adev, struct ttm_tt *ttm,
 }
 
 /**
- * amdgpu_ttm_bo_eviction_valuable -	Check to see if we can evict
- * 										a buffer object.
+ * amdgpu_ttm_bo_eviction_valuable - Check to see if we can evict a buffer
+ * object.
  *
- * Return true if eviction is sensible.  Called by
- * ttm_mem_evict_first() on behalf of ttm_bo_mem_force_space()
- * which tries to evict buffer objects until it can find space
- * for a new object and by ttm_bo_force_list_clean() which is
+ * Return true if eviction is sensible. Called by ttm_mem_evict_first() on
+ * behalf of ttm_bo_mem_force_space() which tries to evict buffer objects until
+ * it can find space for a new object and by ttm_bo_force_list_clean() which is
  * used to clean out a memory space.
  */
 static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
@@ -1515,8 +1512,7 @@ static bool amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
 }
 
 /**
- * amdgpu_ttm_access_memory -	Read or Write memory that backs a
- * 								buffer object.
+ * amdgpu_ttm_access_memory - Read or Write memory that backs a buffer object.
  *
  * @bo:  The buffer object to read/write
  * @offset:  Offset into buffer object
@@ -1704,8 +1700,8 @@ error_create:
 	return r;
 }
 /**
- * amdgpu_ttm_init -	Init the memory management (ttm) as well as
- * 						various gtt/vram related fields.
+ * amdgpu_ttm_init - Init the memory management (ttm) as well as various
+ * gtt/vram related fields.
  *
  * This initializes all of the memory space pools that the TTM layer
  * will need such as the GTT space (system memory mapped to the device),
@@ -1856,8 +1852,7 @@ int amdgpu_ttm_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_ttm_late_init -	Handle any late initialization for
- * 							amdgpu_ttm
+ * amdgpu_ttm_late_init - Handle any late initialization for amdgpu_ttm
  */
 void amdgpu_ttm_late_init(struct amdgpu_device *adev)
 {
-- 
cgit v1.2.3


From 08193d1a893c802c4b807e4d522865061f4e9f4f Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:26:55 +0300
Subject: net: dcb: For wild-card lookups, use priority -1, not 0

The function dcb_app_lookup walks the list of specified DCB APP entries,
looking for one that matches a given criteria: ifindex, selector,
protocol ID and optionally also priority. The "don't care" value for
priority is set to 0, because that priority has not been allowed under
CEE regime, which predates the IEEE standardization.

Under IEEE, 0 is a valid priority number. But because dcb_app_lookup
considers zero a wild card, attempts to add an APP entry with priority 0
fail when other entries exist for a given ifindex / selector / PID
triplet.

Fix by changing the wild-card value to -1.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/dcb/dcbnl.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 2589a6b78aa1..013fdb6fa07a 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1786,7 +1786,7 @@ static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app,
 		if (itr->app.selector == app->selector &&
 		    itr->app.protocol == app->protocol &&
 		    itr->ifindex == ifindex &&
-		    (!prio || itr->app.priority == prio))
+		    ((prio == -1) || itr->app.priority == prio))
 			return itr;
 	}
 
@@ -1821,7 +1821,8 @@ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app)
 	u8 prio = 0;
 
 	spin_lock_bh(&dcb_lock);
-	if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
+	itr = dcb_app_lookup(app, dev->ifindex, -1);
+	if (itr)
 		prio = itr->app.priority;
 	spin_unlock_bh(&dcb_lock);
 
@@ -1849,7 +1850,8 @@ int dcb_setapp(struct net_device *dev, struct dcb_app *new)
 
 	spin_lock_bh(&dcb_lock);
 	/* Search for existing match and replace */
-	if ((itr = dcb_app_lookup(new, dev->ifindex, 0))) {
+	itr = dcb_app_lookup(new, dev->ifindex, -1);
+	if (itr) {
 		if (new->priority)
 			itr->app.priority = new->priority;
 		else {
@@ -1882,7 +1884,8 @@ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app)
 	u8 prio = 0;
 
 	spin_lock_bh(&dcb_lock);
-	if ((itr = dcb_app_lookup(app, dev->ifindex, 0)))
+	itr = dcb_app_lookup(app, dev->ifindex, -1);
+	if (itr)
 		prio |= 1 << itr->app.priority;
 	spin_unlock_bh(&dcb_lock);
 
-- 
cgit v1.2.3


From b67c540b8a987e365dc548e5b2ddf023946e3d63 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:26:56 +0300
Subject: net: dcb: Add priority-to-DSCP map getters

On ingress, a network device such as a switch assigns to packets
priority based on various criteria. Common options include interpreting
PCP and DSCP fields according to user configuration. When a packet
egresses the switch, a reverse process may rewrite PCP and/or DSCP
values according to packet priority.

The following three functions support a) obtaining a DSCP-to-priority
map or vice versa, and b) finding default-priority entries in APP
database.

The DCB subsystem supports for APP entries a very generous M:N mapping
between priorities and protocol identifiers. Understandably,
several (say) DSCP values can map to the same priority. But this
asymmetry holds the other way around as well--one priority can map to
several DSCP values. For this reason, the following functions operate in
terms of bitmaps, with ones in positions that match some APP entry.

- dcb_ieee_getapp_dscp_prio_mask_map() to compute for a given netdevice
  a map of DSCP-to-priority-mask, which gives for each DSCP value a
  bitmap of priorities related to that DSCP value by APP, along the
  lines of dcb_ieee_getapp_mask().

- dcb_ieee_getapp_prio_dscp_mask_map() similarly to compute for a given
  netdevice a map from priorities to a bitmap of DSCPs.

- dcb_ieee_getapp_default_prio_mask() which finds all default-priority
  rules for a given port in APP database, and returns a mask of
  priorities allowed by these default-priority rules.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dcbnl.h | 13 ++++++++
 net/dcb/dcbnl.c     | 86 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 99 insertions(+)

diff --git a/include/net/dcbnl.h b/include/net/dcbnl.h
index 0e5e91be2d30..e22a8a3c089b 100644
--- a/include/net/dcbnl.h
+++ b/include/net/dcbnl.h
@@ -34,6 +34,19 @@ int dcb_ieee_setapp(struct net_device *, struct dcb_app *);
 int dcb_ieee_delapp(struct net_device *, struct dcb_app *);
 u8 dcb_ieee_getapp_mask(struct net_device *, struct dcb_app *);
 
+struct dcb_ieee_app_prio_map {
+	u64 map[IEEE_8021QAZ_MAX_TCS];
+};
+void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev,
+					struct dcb_ieee_app_prio_map *p_map);
+
+struct dcb_ieee_app_dscp_map {
+	u8 map[64];
+};
+void dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev,
+					struct dcb_ieee_app_dscp_map *p_map);
+u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev);
+
 int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd,
 		      u32 seq, u32 pid);
 int dcbnl_cee_notify(struct net_device *dev, int event, int cmd,
diff --git a/net/dcb/dcbnl.c b/net/dcb/dcbnl.c
index 013fdb6fa07a..a556cd708885 100644
--- a/net/dcb/dcbnl.c
+++ b/net/dcb/dcbnl.c
@@ -1958,6 +1958,92 @@ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del)
 }
 EXPORT_SYMBOL(dcb_ieee_delapp);
 
+/**
+ * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from
+ * priorities to the DSCP values assigned to that priority. Initialize p_map
+ * such that each map element holds a bit mask of DSCP values configured for
+ * that priority by APP entries.
+ */
+void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev,
+					struct dcb_ieee_app_prio_map *p_map)
+{
+	int ifindex = dev->ifindex;
+	struct dcb_app_type *itr;
+	u8 prio;
+
+	memset(p_map->map, 0, sizeof(p_map->map));
+
+	spin_lock_bh(&dcb_lock);
+	list_for_each_entry(itr, &dcb_app_list, list) {
+		if (itr->ifindex == ifindex &&
+		    itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP &&
+		    itr->app.protocol < 64 &&
+		    itr->app.priority < IEEE_8021QAZ_MAX_TCS) {
+			prio = itr->app.priority;
+			p_map->map[prio] |= 1ULL << itr->app.protocol;
+		}
+	}
+	spin_unlock_bh(&dcb_lock);
+}
+EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map);
+
+/**
+ * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from
+ * DSCP values to the priorities assigned to that DSCP value. Initialize p_map
+ * such that each map element holds a bit mask of priorities configured for a
+ * given DSCP value by APP entries.
+ */
+void
+dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev,
+				   struct dcb_ieee_app_dscp_map *p_map)
+{
+	int ifindex = dev->ifindex;
+	struct dcb_app_type *itr;
+
+	memset(p_map->map, 0, sizeof(p_map->map));
+
+	spin_lock_bh(&dcb_lock);
+	list_for_each_entry(itr, &dcb_app_list, list) {
+		if (itr->ifindex == ifindex &&
+		    itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP &&
+		    itr->app.protocol < 64 &&
+		    itr->app.priority < IEEE_8021QAZ_MAX_TCS)
+			p_map->map[itr->app.protocol] |= 1 << itr->app.priority;
+	}
+	spin_unlock_bh(&dcb_lock);
+}
+EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map);
+
+/**
+ * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet
+ * type, with valid PID values >= 1536. A special meaning is then assigned to
+ * protocol value of 0: "default priority. For use when priority is not
+ * otherwise specified".
+ *
+ * dcb_ieee_getapp_default_prio_mask - For a given device, find all APP entries
+ * of the form {$PRIO, ETHERTYPE, 0} and construct a bit mask of all default
+ * priorities set by these entries.
+ */
+u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev)
+{
+	int ifindex = dev->ifindex;
+	struct dcb_app_type *itr;
+	u8 mask = 0;
+
+	spin_lock_bh(&dcb_lock);
+	list_for_each_entry(itr, &dcb_app_list, list) {
+		if (itr->ifindex == ifindex &&
+		    itr->app.selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE &&
+		    itr->app.protocol == 0 &&
+		    itr->app.priority < IEEE_8021QAZ_MAX_TCS)
+			mask |= 1 << itr->app.priority;
+	}
+	spin_unlock_bh(&dcb_lock);
+
+	return mask;
+}
+EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask);
+
 static int __init dcbnl_init(void)
 {
 	INIT_LIST_HEAD(&dcb_app_list);
-- 
cgit v1.2.3


From 02837d726721cbc87629741e6b2570580ce47fae Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:26:57 +0300
Subject: mlxsw: reg: Add QoS Port DSCP to Priority Mapping Register

The QPDPM register controls the mapping from DSCP field to Switch
Priority for IP packets.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 52 +++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index fd2e3dd166d2..411d06b5aaae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3329,6 +3329,57 @@ static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
 	mlxsw_reg_qeec_next_element_index_set(payload, next_index);
 }
 
+/* QPDPM - QoS Port DSCP to Priority Mapping Register
+ * --------------------------------------------------
+ * This register controls the mapping from DSCP field to
+ * Switch Priority for IP packets.
+ */
+#define MLXSW_REG_QPDPM_ID 0x4013
+#define MLXSW_REG_QPDPM_BASE_LEN 0x4 /* base length, without records */
+#define MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN 0x2 /* record length */
+#define MLXSW_REG_QPDPM_DSCP_ENTRY_REC_MAX_COUNT 64
+#define MLXSW_REG_QPDPM_LEN (MLXSW_REG_QPDPM_BASE_LEN +			\
+			     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN *	\
+			     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(qpdpm, MLXSW_REG_QPDPM_ID, MLXSW_REG_QPDPM_LEN);
+
+/* reg_qpdpm_local_port
+ * Local Port. Supported for data packets from CPU port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qpdpm, local_port, 0x00, 16, 8);
+
+/* reg_qpdpm_dscp_e
+ * Enable update of the specific entry. When cleared, the switch_prio and color
+ * fields are ignored and the previous switch_prio and color values are
+ * preserved.
+ * Access: WO
+ */
+MLXSW_ITEM16_INDEXED(reg, qpdpm, dscp_entry_e, MLXSW_REG_QPDPM_BASE_LEN, 15, 1,
+		     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdpm_dscp_prio
+ * The new Switch Priority value for the relevant DSCP value.
+ * Access: RW
+ */
+MLXSW_ITEM16_INDEXED(reg, qpdpm, dscp_entry_prio,
+		     MLXSW_REG_QPDPM_BASE_LEN, 0, 4,
+		     MLXSW_REG_QPDPM_DSCP_ENTRY_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_qpdpm_pack(char *payload, u8 local_port)
+{
+	MLXSW_REG_ZERO(qpdpm, payload);
+	mlxsw_reg_qpdpm_local_port_set(payload, local_port);
+}
+
+static inline void
+mlxsw_reg_qpdpm_dscp_pack(char *payload, unsigned short dscp, u8 prio)
+{
+	mlxsw_reg_qpdpm_dscp_entry_e_set(payload, dscp, 1);
+	mlxsw_reg_qpdpm_dscp_entry_prio_set(payload, dscp, prio);
+}
+
 /* PMLP - Ports Module to Local Port Register
  * ------------------------------------------
  * Configures the assignment of modules to local ports.
@@ -8542,6 +8593,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
 	MLXSW_REG(qeec),
+	MLXSW_REG(qpdpm),
 	MLXSW_REG(pmlp),
 	MLXSW_REG(pmtu),
 	MLXSW_REG(ptys),
-- 
cgit v1.2.3


From 746da42a1f60728fc0f3ba7818ffe8d1aa69cacd Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:26:58 +0300
Subject: mlxsw: reg: Add QoS Priority Trust State Register

The QPTS register controls the port policy to calculate the switch
priority and packet color based on incoming packet fields.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 39 +++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 411d06b5aaae..c50e754dd725 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3017,6 +3017,44 @@ static inline void mlxsw_reg_iedr_rec_pack(char *payload, int rec_index,
 	mlxsw_reg_iedr_rec_index_start_set(payload, rec_index, rec_index_start);
 }
 
+/* QPTS - QoS Priority Trust State Register
+ * ----------------------------------------
+ * This register controls the port policy to calculate the switch priority and
+ * packet color based on incoming packet fields.
+ */
+#define MLXSW_REG_QPTS_ID 0x4002
+#define MLXSW_REG_QPTS_LEN 0x8
+
+MLXSW_REG_DEFINE(qpts, MLXSW_REG_QPTS_ID, MLXSW_REG_QPTS_LEN);
+
+/* reg_qpts_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is supported.
+ */
+MLXSW_ITEM32(reg, qpts, local_port, 0x00, 16, 8);
+
+enum mlxsw_reg_qpts_trust_state {
+	MLXSW_REG_QPTS_TRUST_STATE_PCP = 1,
+	MLXSW_REG_QPTS_TRUST_STATE_DSCP = 2, /* For MPLS, trust EXP. */
+};
+
+/* reg_qpts_trust_state
+ * Trust state for a given port.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qpts, trust_state, 0x04, 0, 3);
+
+static inline void mlxsw_reg_qpts_pack(char *payload, u8 local_port,
+				       enum mlxsw_reg_qpts_trust_state ts)
+{
+	MLXSW_REG_ZERO(qpts, payload);
+
+	mlxsw_reg_qpts_local_port_set(payload, local_port);
+	mlxsw_reg_qpts_trust_state_set(payload, ts);
+}
+
 /* QPCR - QoS Policer Configuration Register
  * -----------------------------------------
  * The QPCR register is used to create policers - that limit
@@ -8590,6 +8628,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(percr),
 	MLXSW_REG(pererp),
 	MLXSW_REG(iedr),
+	MLXSW_REG(qpts),
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
 	MLXSW_REG(qeec),
-- 
cgit v1.2.3


From e67131d9b861eb753b077961e291fc21a59daa28 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:26:59 +0300
Subject: mlxsw: reg: Add QoS ReWrite Enable Register

This register configures the rewrite enable (whether PCP or DSCP value
in packet should be updated according to packet priority) per receive
port.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 39 +++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index c50e754dd725..02c0e1531ed2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3367,6 +3367,44 @@ static inline void mlxsw_reg_qeec_pack(char *payload, u8 local_port,
 	mlxsw_reg_qeec_next_element_index_set(payload, next_index);
 }
 
+/* QRWE - QoS ReWrite Enable
+ * -------------------------
+ * This register configures the rewrite enable per receive port.
+ */
+#define MLXSW_REG_QRWE_ID 0x400F
+#define MLXSW_REG_QRWE_LEN 0x08
+
+MLXSW_REG_DEFINE(qrwe, MLXSW_REG_QRWE_ID, MLXSW_REG_QRWE_LEN);
+
+/* reg_qrwe_local_port
+ * Local port number.
+ * Access: Index
+ *
+ * Note: CPU port is supported. No support for router port.
+ */
+MLXSW_ITEM32(reg, qrwe, local_port, 0x00, 16, 8);
+
+/* reg_qrwe_dscp
+ * Whether to enable DSCP rewrite (default is 0, don't rewrite).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qrwe, dscp, 0x04, 1, 1);
+
+/* reg_qrwe_pcp
+ * Whether to enable PCP and DEI rewrite (default is 0, don't rewrite).
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, qrwe, pcp, 0x04, 0, 1);
+
+static inline void mlxsw_reg_qrwe_pack(char *payload, u8 local_port,
+				       bool rewrite_pcp, bool rewrite_dscp)
+{
+	MLXSW_REG_ZERO(qrwe, payload);
+	mlxsw_reg_qrwe_local_port_set(payload, local_port);
+	mlxsw_reg_qrwe_pcp_set(payload, rewrite_pcp);
+	mlxsw_reg_qrwe_dscp_set(payload, rewrite_dscp);
+}
+
 /* QPDPM - QoS Port DSCP to Priority Mapping Register
  * --------------------------------------------------
  * This register controls the mapping from DSCP field to
@@ -8632,6 +8670,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(qpcr),
 	MLXSW_REG(qtct),
 	MLXSW_REG(qeec),
+	MLXSW_REG(qrwe),
 	MLXSW_REG(qpdpm),
 	MLXSW_REG(pmlp),
 	MLXSW_REG(pmtu),
-- 
cgit v1.2.3


From 55fb71f481aac930ba87dc0f99a3060ced0326d3 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:27:00 +0300
Subject: mlxsw: reg: Add QoS Priority to DSCP Mapping Register

This register controls mapping from Priority to DSCP for purposes of
rewrite. Note that rewrite happens as the packet is transmitted provided
that the DSCP rewrite bit is enabled for the packet.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 89 +++++++++++++++++++++++++++++++
 1 file changed, 89 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 02c0e1531ed2..e52841627966 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3405,6 +3405,94 @@ static inline void mlxsw_reg_qrwe_pack(char *payload, u8 local_port,
 	mlxsw_reg_qrwe_dscp_set(payload, rewrite_dscp);
 }
 
+/* QPDSM - QoS Priority to DSCP Mapping
+ * ------------------------------------
+ * QoS Priority to DSCP Mapping Register
+ */
+#define MLXSW_REG_QPDSM_ID 0x4011
+#define MLXSW_REG_QPDSM_BASE_LEN 0x04 /* base length, without records */
+#define MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN 0x4 /* record length */
+#define MLXSW_REG_QPDSM_PRIO_ENTRY_REC_MAX_COUNT 16
+#define MLXSW_REG_QPDSM_LEN (MLXSW_REG_QPDSM_BASE_LEN +			\
+			     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN *	\
+			     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_MAX_COUNT)
+
+MLXSW_REG_DEFINE(qpdsm, MLXSW_REG_QPDSM_ID, MLXSW_REG_QPDSM_LEN);
+
+/* reg_qpdsm_local_port
+ * Local Port. Supported for data packets from CPU port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qpdsm, local_port, 0x00, 16, 8);
+
+/* reg_qpdsm_prio_entry_color0_e
+ * Enable update of the entry for color 0 and a given port.
+ * Access: WO
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color0_e,
+		     MLXSW_REG_QPDSM_BASE_LEN, 31, 1,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color0_dscp
+ * DSCP field in the outer label of the packet for color 0 and a given port.
+ * Reserved when e=0.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color0_dscp,
+		     MLXSW_REG_QPDSM_BASE_LEN, 24, 6,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color1_e
+ * Enable update of the entry for color 1 and a given port.
+ * Access: WO
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color1_e,
+		     MLXSW_REG_QPDSM_BASE_LEN, 23, 1,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color1_dscp
+ * DSCP field in the outer label of the packet for color 1 and a given port.
+ * Reserved when e=0.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color1_dscp,
+		     MLXSW_REG_QPDSM_BASE_LEN, 16, 6,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color2_e
+ * Enable update of the entry for color 2 and a given port.
+ * Access: WO
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color2_e,
+		     MLXSW_REG_QPDSM_BASE_LEN, 15, 1,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+/* reg_qpdsm_prio_entry_color2_dscp
+ * DSCP field in the outer label of the packet for color 2 and a given port.
+ * Reserved when e=0.
+ * Access: RW
+ */
+MLXSW_ITEM32_INDEXED(reg, qpdsm, prio_entry_color2_dscp,
+		     MLXSW_REG_QPDSM_BASE_LEN, 8, 6,
+		     MLXSW_REG_QPDSM_PRIO_ENTRY_REC_LEN, 0x00, false);
+
+static inline void mlxsw_reg_qpdsm_pack(char *payload, u8 local_port)
+{
+	MLXSW_REG_ZERO(qpdsm, payload);
+	mlxsw_reg_qpdsm_local_port_set(payload, local_port);
+}
+
+static inline void
+mlxsw_reg_qpdsm_prio_pack(char *payload, unsigned short prio, u8 dscp)
+{
+	mlxsw_reg_qpdsm_prio_entry_color0_e_set(payload, prio, 1);
+	mlxsw_reg_qpdsm_prio_entry_color0_dscp_set(payload, prio, dscp);
+	mlxsw_reg_qpdsm_prio_entry_color1_e_set(payload, prio, 1);
+	mlxsw_reg_qpdsm_prio_entry_color1_dscp_set(payload, prio, dscp);
+	mlxsw_reg_qpdsm_prio_entry_color2_e_set(payload, prio, 1);
+	mlxsw_reg_qpdsm_prio_entry_color2_dscp_set(payload, prio, dscp);
+}
+
 /* QPDPM - QoS Port DSCP to Priority Mapping Register
  * --------------------------------------------------
  * This register controls the mapping from DSCP field to
@@ -8671,6 +8759,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(qtct),
 	MLXSW_REG(qeec),
 	MLXSW_REG(qrwe),
+	MLXSW_REG(qpdsm),
 	MLXSW_REG(qpdpm),
 	MLXSW_REG(pmlp),
 	MLXSW_REG(pmtu),
-- 
cgit v1.2.3


From b2b1dab6884e39c9cea2650b0c399e1990cd855a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:27:01 +0300
Subject: mlxsw: spectrum: Support ieee_setapp, ieee_delapp

The APP TLVs are used for communicating priority-to-protocol ID maps for
a given netdevice. Support the following APP TLVs:

- DSCP (selector 5) to configure priority-to-DSCP code point maps. Use
  these maps to configure packet priority on ingress, and DSCP code
  point rewrite on egress.

- Default priority (selector 1, PID 0) to configure priority for the
  DSCP code points that don't have one assigned by the DSCP selector. In
  future this could also be used for assigning default port priority
  when a packet arrives without DSCP tagging.

Besides setting up the maps themselves, also configure port trust level
and rewrite bits.

Port trust level determines whether, for a packet arriving through a
certain port, the priority should be determined based on PCP or DSCP
header fields. So far, mlxsw kept the device default of trust-PCP. Now,
as soon as the first DSCP APP TLV is configured, switch to trust-DSCP.
Only when all DSCP APP TLVs are removed, switch back to trust-PCP again.
Note that the default priority APP TLV doesn't impact the trust level
configuration.

Rewrite bits determine whether DSCP and PCP fields of egressing packets
should be updated according to switch priority. When port trust is
switched to DSCP, enable rewrite of DSCP field.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     |   4 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c | 269 ++++++++++++++++++++-
 2 files changed, 271 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index bc2704193666..13eca1a79d52 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -1,6 +1,6 @@
 /*
  * drivers/net/ethernet/mellanox/mlxsw/spectrum.h
- * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved.
  * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
  * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
  * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
@@ -54,6 +54,7 @@
 #include "core.h"
 #include "core_acl_flex_keys.h"
 #include "core_acl_flex_actions.h"
+#include "reg.h"
 
 #define MLXSW_SP_FID_8021D_MAX 1024
 
@@ -243,6 +244,7 @@ struct mlxsw_sp_port {
 		struct ieee_ets *ets;
 		struct ieee_maxrate *maxrate;
 		struct ieee_pfc *pfc;
+		enum mlxsw_reg_qpts_trust_state trust_state;
 	} dcb;
 	struct {
 		u8 module;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
index b6ed7f7c531e..c31aeb25ab5a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -1,6 +1,6 @@
 /*
  * drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved.
  * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
  *
  * Redistribution and use in source and binary forms, with or without
@@ -255,6 +255,270 @@ static int mlxsw_sp_dcbnl_ieee_setets(struct net_device *dev,
 	return 0;
 }
 
+static int mlxsw_sp_dcbnl_app_validate(struct net_device *dev,
+				       struct dcb_app *app)
+{
+	int prio;
+
+	if (app->priority >= IEEE_8021QAZ_MAX_TCS) {
+		netdev_err(dev, "APP entry with priority value %u is invalid\n",
+			   app->priority);
+		return -EINVAL;
+	}
+
+	switch (app->selector) {
+	case IEEE_8021QAZ_APP_SEL_DSCP:
+		if (app->protocol >= 64) {
+			netdev_err(dev, "DSCP APP entry with protocol value %u is invalid\n",
+				   app->protocol);
+			return -EINVAL;
+		}
+
+		/* Warn about any DSCP APP entries with the same PID. */
+		prio = fls(dcb_ieee_getapp_mask(dev, app));
+		if (prio--) {
+			if (prio < app->priority)
+				netdev_warn(dev, "Choosing priority %d for DSCP %d in favor of previously-active value of %d\n",
+					    app->priority, app->protocol, prio);
+			else if (prio > app->priority)
+				netdev_warn(dev, "Ignoring new priority %d for DSCP %d in favor of current value of %d\n",
+					    app->priority, app->protocol, prio);
+		}
+		break;
+
+	case IEEE_8021QAZ_APP_SEL_ETHERTYPE:
+		if (app->protocol) {
+			netdev_err(dev, "EtherType APP entries with protocol value != 0 not supported\n");
+			return -EINVAL;
+		}
+		break;
+
+	default:
+		netdev_err(dev, "APP entries with selector %u not supported\n",
+			   app->selector);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static u8
+mlxsw_sp_port_dcb_app_default_prio(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	u8 prio_mask;
+
+	prio_mask = dcb_ieee_getapp_default_prio_mask(mlxsw_sp_port->dev);
+	if (prio_mask)
+		/* Take the highest configured priority. */
+		return fls(prio_mask) - 1;
+
+	return 0;
+}
+
+static void
+mlxsw_sp_port_dcb_app_dscp_prio_map(struct mlxsw_sp_port *mlxsw_sp_port,
+				    u8 default_prio,
+				    struct dcb_ieee_app_dscp_map *map)
+{
+	int i;
+
+	dcb_ieee_getapp_dscp_prio_mask_map(mlxsw_sp_port->dev, map);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i) {
+		if (map->map[i])
+			map->map[i] = fls(map->map[i]) - 1;
+		else
+			map->map[i] = default_prio;
+	}
+}
+
+static bool
+mlxsw_sp_port_dcb_app_prio_dscp_map(struct mlxsw_sp_port *mlxsw_sp_port,
+				    struct dcb_ieee_app_prio_map *map)
+{
+	bool have_dscp = false;
+	int i;
+
+	dcb_ieee_getapp_prio_dscp_mask_map(mlxsw_sp_port->dev, map);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i) {
+		if (map->map[i]) {
+			map->map[i] = fls64(map->map[i]) - 1;
+			have_dscp = true;
+		}
+	}
+
+	return have_dscp;
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qpts(struct mlxsw_sp_port *mlxsw_sp_port,
+				  enum mlxsw_reg_qpts_trust_state ts)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qpts_pl[MLXSW_REG_QPTS_LEN];
+
+	mlxsw_reg_qpts_pack(qpts_pl, mlxsw_sp_port->local_port, ts);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpts), qpts_pl);
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qrwe(struct mlxsw_sp_port *mlxsw_sp_port,
+				  bool rewrite_dscp)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qrwe_pl[MLXSW_REG_QRWE_LEN];
+
+	mlxsw_reg_qrwe_pack(qrwe_pl, mlxsw_sp_port->local_port,
+			    false, rewrite_dscp);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qrwe), qrwe_pl);
+}
+
+static int
+mlxsw_sp_port_dcb_toggle_trust(struct mlxsw_sp_port *mlxsw_sp_port,
+			       enum mlxsw_reg_qpts_trust_state ts)
+{
+	bool rewrite_dscp = ts == MLXSW_REG_QPTS_TRUST_STATE_DSCP;
+	int err;
+
+	if (mlxsw_sp_port->dcb.trust_state == ts)
+		return 0;
+
+	err = mlxsw_sp_port_dcb_app_update_qpts(mlxsw_sp_port, ts);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_port_dcb_app_update_qrwe(mlxsw_sp_port, rewrite_dscp);
+	if (err)
+		goto err_update_qrwe;
+
+	mlxsw_sp_port->dcb.trust_state = ts;
+	return 0;
+
+err_update_qrwe:
+	mlxsw_sp_port_dcb_app_update_qpts(mlxsw_sp_port,
+					  mlxsw_sp_port->dcb.trust_state);
+	return err;
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qpdpm(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct dcb_ieee_app_dscp_map *map)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qpdpm_pl[MLXSW_REG_QPDPM_LEN];
+	short int i;
+
+	mlxsw_reg_qpdpm_pack(qpdpm_pl, mlxsw_sp_port->local_port);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i)
+		mlxsw_reg_qpdpm_dscp_pack(qpdpm_pl, i, map->map[i]);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpdpm), qpdpm_pl);
+}
+
+static int
+mlxsw_sp_port_dcb_app_update_qpdsm(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct dcb_ieee_app_prio_map *map)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qpdsm_pl[MLXSW_REG_QPDSM_LEN];
+	short int i;
+
+	mlxsw_reg_qpdsm_pack(qpdsm_pl, mlxsw_sp_port->local_port);
+	for (i = 0; i < ARRAY_SIZE(map->map); ++i)
+		mlxsw_reg_qpdsm_prio_pack(qpdsm_pl, i, map->map[i]);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpdsm), qpdsm_pl);
+}
+
+static int mlxsw_sp_port_dcb_app_update(struct mlxsw_sp_port *mlxsw_sp_port)
+{
+	struct dcb_ieee_app_prio_map prio_map;
+	struct dcb_ieee_app_dscp_map dscp_map;
+	u8 default_prio;
+	bool have_dscp;
+	int err;
+
+	default_prio = mlxsw_sp_port_dcb_app_default_prio(mlxsw_sp_port);
+	have_dscp = mlxsw_sp_port_dcb_app_prio_dscp_map(mlxsw_sp_port,
+							&prio_map);
+
+	if (!have_dscp) {
+		err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port,
+					MLXSW_REG_QPTS_TRUST_STATE_PCP);
+		if (err)
+			netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L2\n");
+		return err;
+	}
+
+	mlxsw_sp_port_dcb_app_dscp_prio_map(mlxsw_sp_port, default_prio,
+					    &dscp_map);
+	err = mlxsw_sp_port_dcb_app_update_qpdpm(mlxsw_sp_port,
+						 &dscp_map);
+	if (err) {
+		netdev_err(mlxsw_sp_port->dev, "Couldn't configure priority map\n");
+		return err;
+	}
+
+	err = mlxsw_sp_port_dcb_app_update_qpdsm(mlxsw_sp_port,
+						 &prio_map);
+	if (err) {
+		netdev_err(mlxsw_sp_port->dev, "Couldn't configure DSCP rewrite map\n");
+		return err;
+	}
+
+	err = mlxsw_sp_port_dcb_toggle_trust(mlxsw_sp_port,
+					     MLXSW_REG_QPTS_TRUST_STATE_DSCP);
+	if (err) {
+		/* A failure to set trust DSCP means that the QPDPM and QPDSM
+		 * maps installed above are not in effect. And since we are here
+		 * attempting to set trust DSCP, we couldn't have attempted to
+		 * switch trust to PCP. Thus no cleanup is necessary.
+		 */
+		netdev_err(mlxsw_sp_port->dev, "Couldn't switch to trust L3\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int mlxsw_sp_dcbnl_ieee_setapp(struct net_device *dev,
+				      struct dcb_app *app)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int err;
+
+	err = mlxsw_sp_dcbnl_app_validate(dev, app);
+	if (err)
+		return err;
+
+	err = dcb_ieee_setapp(dev, app);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_port_dcb_app_update(mlxsw_sp_port);
+	if (err)
+		goto err_update;
+
+	return 0;
+
+err_update:
+	dcb_ieee_delapp(dev, app);
+	return err;
+}
+
+static int mlxsw_sp_dcbnl_ieee_delapp(struct net_device *dev,
+				      struct dcb_app *app)
+{
+	struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev);
+	int err;
+
+	err = dcb_ieee_delapp(dev, app);
+	if (err)
+		return err;
+
+	err = mlxsw_sp_port_dcb_app_update(mlxsw_sp_port);
+	if (err)
+		netdev_err(dev, "Failed to update DCB APP configuration\n");
+	return 0;
+}
+
 static int mlxsw_sp_dcbnl_ieee_getmaxrate(struct net_device *dev,
 					  struct ieee_maxrate *maxrate)
 {
@@ -394,6 +658,8 @@ static const struct dcbnl_rtnl_ops mlxsw_sp_dcbnl_ops = {
 	.ieee_setmaxrate	= mlxsw_sp_dcbnl_ieee_setmaxrate,
 	.ieee_getpfc		= mlxsw_sp_dcbnl_ieee_getpfc,
 	.ieee_setpfc		= mlxsw_sp_dcbnl_ieee_setpfc,
+	.ieee_setapp		= mlxsw_sp_dcbnl_ieee_setapp,
+	.ieee_delapp		= mlxsw_sp_dcbnl_ieee_delapp,
 
 	.getdcbx		= mlxsw_sp_dcbnl_getdcbx,
 	.setdcbx		= mlxsw_sp_dcbnl_setdcbx,
@@ -467,6 +733,7 @@ int mlxsw_sp_port_dcb_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	if (err)
 		goto err_port_pfc_init;
 
+	mlxsw_sp_port->dcb.trust_state = MLXSW_REG_QPTS_TRUST_STATE_PCP;
 	mlxsw_sp_port->dev->dcbnl_ops = &mlxsw_sp_dcbnl_ops;
 
 	return 0;
-- 
cgit v1.2.3


From d159261f3662a89a5cd4fae041107ee511d9552e Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Fri, 27 Jul 2018 15:27:02 +0300
Subject: selftests: mlxsw: Add test for trust-DSCP

Add a test that exercises the new code. Send DSCP-tagged packets, and
observe how they are prioritized in the switch and the DSCP is updated
on egress again.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_dscp_bridge.sh | 248 +++++++++++++++++++++
 1 file changed, 248 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
new file mode 100755
index 000000000000..418319f19108
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
@@ -0,0 +1,248 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for DSCP prioritization and rewrite. Packets ingress $swp1 with a DSCP
+# tag and are prioritized according to the map at $swp1. They egress $swp2 and
+# the DSCP value is updated to match the map at that interface. The updated DSCP
+# tag is verified at $h2.
+#
+# ICMP responses are produced with the same DSCP tag that arrived at $h2. They
+# go through prioritization at $swp2 and DSCP retagging at $swp1. The tag is
+# verified at $h1--it should match the original tag.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |    + $h1             |                             |            $h2 +     |
+# |    | 192.0.2.1/28    |                             |   192.0.2.2/28 |     |
+# +----|-----------------+                             +----------------|-----+
+#      |                                                                |
+# +----|----------------------------------------------------------------|-----+
+# | SW |                                                                |     |
+# |  +-|----------------------------------------------------------------|-+   |
+# |  | + $swp1                       BR                           $swp2 + |   |
+# |  |   APP=0,5,10 .. 7,5,17                      APP=0,5,20 .. 7,5,27   |   |
+# |  +--------------------------------------------------------------------+   |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	test_dscp
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+
+__dscp_capture_add_del()
+{
+	local add_del=$1; shift
+	local dev=$1; shift
+	local base=$1; shift
+	local dscp;
+
+	for prio in {0..7}; do
+		dscp=$((base + prio))
+		__icmp_capture_add_del $add_del $dscp "" $dev \
+				       "ip_tos $((dscp << 2))"
+	done
+}
+
+dscp_capture_install()
+{
+	local dev=$1; shift
+	local base=$1; shift
+
+	__dscp_capture_add_del add $dev $base
+}
+
+dscp_capture_uninstall()
+{
+	local dev=$1; shift
+	local base=$1; shift
+
+	__dscp_capture_add_del del $dev $base
+}
+
+h1_create()
+{
+	local dscp;
+
+	simple_if_init $h1 192.0.2.1/28
+	tc qdisc add dev $h1 clsact
+	dscp_capture_install $h1 10
+}
+
+h1_destroy()
+{
+	dscp_capture_uninstall $h1 10
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/28
+	tc qdisc add dev $h2 clsact
+	dscp_capture_install $h2 20
+}
+
+h2_destroy()
+{
+	dscp_capture_uninstall $h2 20
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2 192.0.2.2/28
+}
+
+dscp_map()
+{
+	local base=$1; shift
+
+	for prio in {0..7}; do
+		echo app=$prio,5,$((base + prio))
+	done
+}
+
+lldpad_wait()
+{
+	local dev=$1; shift
+
+	while lldptool -t -i $dev -V APP -c app | grep -q pending; do
+	    echo "$dev: waiting for lldpad to push pending APP updates"
+	    sleep 5
+	done
+}
+
+switch_create()
+{
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 up
+	ip link set dev $swp1 master br1
+	ip link set dev $swp1 up
+	ip link set dev $swp2 master br1
+	ip link set dev $swp2 up
+
+	lldptool -T -i $swp1 -V APP $(dscp_map 10) >/dev/null
+	lldptool -T -i $swp2 -V APP $(dscp_map 20) >/dev/null
+	lldpad_wait $swp1
+	lldpad_wait $swp2
+}
+
+switch_destroy()
+{
+	lldptool -T -i $swp2 -V APP -d $(dscp_map 20) >/dev/null
+	lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null
+
+	# Give lldpad a chance to push down the changes. If the device is downed
+	# too soon, the updates will be left pending, but will have been struck
+	# off the lldpad's DB already, and we won't be able to tell. Then on
+	# next test iteration this would cause weirdness as newly-added APP
+	# rules conflict with the old ones, sometimes getting stuck in an
+	# "unknown" state.
+	sleep 5
+
+	ip link set dev $swp2 nomaster
+	ip link set dev $swp1 nomaster
+	ip link del dev br1
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+dscp_fetch_stats()
+{
+	local dev=$1; shift
+	local base=$1; shift
+
+	for prio in {0..7}; do
+		local dscp=$((base + prio))
+		local t=$(tc_rule_stats_get $dev $dscp)
+		echo "[$dscp]=$t "
+	done
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.2
+}
+
+dscp_ping_test()
+{
+	local vrf_name=$1; shift
+	local sip=$1; shift
+	local dip=$1; shift
+	local prio=$1; shift
+	local dev_10=$1; shift
+	local dev_20=$1; shift
+
+	local dscp_10=$(((prio + 10) << 2))
+	local dscp_20=$(((prio + 20) << 2))
+
+	RET=0
+
+	local -A t0s
+	eval "t0s=($(dscp_fetch_stats $dev_10 10)
+		   $(dscp_fetch_stats $dev_20 20))"
+
+	ip vrf exec $vrf_name \
+	   ${PING} -Q $dscp_10 ${sip:+-I $sip} $dip \
+		   -c 10 -i 0.1 -w 2 &> /dev/null
+
+	local -A t1s
+	eval "t1s=($(dscp_fetch_stats $dev_10 10)
+		   $(dscp_fetch_stats $dev_20 20))"
+
+	for key in ${!t0s[@]}; do
+		local expect
+		if ((key == dscp_10 || key == dscp_20)); then
+			expect=10
+		else
+			expect=0
+		fi
+
+		local delta=$((t1s[key] - t0s[key]))
+		((expect == delta))
+		check_err $? "DSCP $key: Expected to capture $expect packets, got $delta."
+	done
+
+	log_test "DSCP rewrite: $dscp_10-(prio $prio)-$dscp_20"
+}
+
+test_dscp()
+{
+	for prio in {0..7}; do
+		dscp_ping_test v$h1 192.0.2.1 192.0.2.2 $prio $h1 $h2
+	done
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 3e4e36436047155f67eafffe3062a09db1dff8df Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Fri, 27 Jul 2018 15:18:49 +0200
Subject: net/rds/Kconfig: Correct the RDS depends

Remove prefix 'CONFIG_' from CONFIG_IPV6

Fixes: ba7d7e2677c0 ("net/rds/Kconfig: RDS should depend on IPV6")
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index 607128f10bcd..4c7f2595d919 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -1,7 +1,7 @@
 
 config RDS
 	tristate "The RDS Protocol"
-	depends on INET && CONFIG_IPV6
+	depends on INET && IPV6
 	---help---
 	  The RDS (Reliable Datagram Sockets) protocol provides reliable,
 	  sequenced delivery of datagrams over Infiniband or TCP.
-- 
cgit v1.2.3


From 3ae5536b808dced0af5b2e6768a41862620c779d Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 27 Jul 2018 10:59:57 +0200
Subject: l2tp: ignore L2TP_ATTR_DATA_SEQ netlink attribute

The value of this attribute is never used.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/l2tp.h | 7 ++++---
 net/l2tp/l2tp_core.h      | 8 --------
 net/l2tp/l2tp_debugfs.c   | 4 +---
 net/l2tp/l2tp_netlink.c   | 6 ------
 4 files changed, 5 insertions(+), 20 deletions(-)

diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 7d570c7bd117..ae888606b3ec 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -65,9 +65,9 @@ struct sockaddr_l2tpip6 {
  * TUNNEL_MODIFY	- CONN_ID, udpcsum
  * TUNNEL_GETSTATS	- CONN_ID, (stats)
  * TUNNEL_GET		- CONN_ID, (...)
- * SESSION_CREATE	- SESSION_ID, PW_TYPE, data_seq, cookie, peer_cookie, l2spec
+ * SESSION_CREATE	- SESSION_ID, PW_TYPE, cookie, peer_cookie, l2spec
  * SESSION_DELETE	- SESSION_ID
- * SESSION_MODIFY	- SESSION_ID, data_seq
+ * SESSION_MODIFY	- SESSION_ID
  * SESSION_GET		- SESSION_ID, (...)
  * SESSION_GETSTATS	- SESSION_ID, (stats)
  *
@@ -95,7 +95,7 @@ enum {
 	L2TP_ATTR_PW_TYPE,		/* u16, enum l2tp_pwtype */
 	L2TP_ATTR_ENCAP_TYPE,		/* u16, enum l2tp_encap_type */
 	L2TP_ATTR_OFFSET,		/* u16 (not used) */
-	L2TP_ATTR_DATA_SEQ,		/* u16 */
+	L2TP_ATTR_DATA_SEQ,		/* u16 (not used) */
 	L2TP_ATTR_L2SPEC_TYPE,		/* u8, enum l2tp_l2spec_type */
 	L2TP_ATTR_L2SPEC_LEN,		/* u8 (not used) */
 	L2TP_ATTR_PROTO_VERSION,	/* u8 */
@@ -169,6 +169,7 @@ enum l2tp_encap_type {
 	L2TP_ENCAPTYPE_IP,
 };
 
+/* For L2TP_ATTR_DATA_SEQ. Unused. */
 enum l2tp_seqmode {
 	L2TP_SEQ_NONE = 0,
 	L2TP_SEQ_IP = 1,
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index d85fde793a8c..7dbfb55ab3b5 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -45,10 +45,6 @@ struct l2tp_tunnel;
  */
 struct l2tp_session_cfg {
 	enum l2tp_pwtype	pw_type;
-	unsigned int		data_seq:2;	/* data sequencing level
-						 * 0 => none, 1 => IP only,
-						 * 2 => all
-						 */
 	unsigned int		recv_seq:1;	/* expect receive packets with
 						 * sequence numbers? */
 	unsigned int		send_seq:1;	/* send packets with sequence
@@ -99,10 +95,6 @@ struct l2tp_session {
 
 	char			name[32];	/* for logging */
 	char			ifname[IFNAMSIZ];
-	unsigned int		data_seq:2;	/* data sequencing level
-						 * 0 => none, 1 => IP only,
-						 * 2 => all
-						 */
 	unsigned int		recv_seq:1;	/* expect receive packets with
 						 * sequence numbers? */
 	unsigned int		send_seq:1;	/* send packets with sequence
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index b5d7dde003ef..91b9248610f0 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -191,12 +191,10 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
 	if (session->send_seq || session->recv_seq)
 		seq_printf(m, "   nr %hu, ns %hu\n", session->nr, session->ns);
 	seq_printf(m, "   refcnt %d\n", refcount_read(&session->ref_count));
-	seq_printf(m, "   config %d/%d/%c/%c/%s/%s %08x %u\n",
+	seq_printf(m, "   config %d/%d/%c/%c/-/%s %08x %u\n",
 		   session->mtu, session->mru,
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
-		   session->data_seq == 1 ? "IPSEQ" :
-		   session->data_seq == 2 ? "DATASEQ" : "-",
 		   session->lns_mode ? "LNS" : "LAC",
 		   session->debug,
 		   jiffies_to_msecs(session->reorder_timeout));
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 5b9900889e31..e4785f6966f6 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -560,9 +560,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 	}
 
 	if (tunnel->version > 2) {
-		if (info->attrs[L2TP_ATTR_DATA_SEQ])
-			cfg.data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]);
-
 		if (info->attrs[L2TP_ATTR_L2SPEC_TYPE]) {
 			cfg.l2specific_type = nla_get_u8(info->attrs[L2TP_ATTR_L2SPEC_TYPE]);
 			if (cfg.l2specific_type != L2TP_L2SPECTYPE_DEFAULT &&
@@ -693,9 +690,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_DEBUG])
 		session->debug = nla_get_u32(info->attrs[L2TP_ATTR_DEBUG]);
 
-	if (info->attrs[L2TP_ATTR_DATA_SEQ])
-		session->data_seq = nla_get_u8(info->attrs[L2TP_ATTR_DATA_SEQ]);
-
 	if (info->attrs[L2TP_ATTR_RECV_SEQ])
 		session->recv_seq = nla_get_u8(info->attrs[L2TP_ATTR_RECV_SEQ]);
 
-- 
cgit v1.2.3


From ae51a7c6d54876c47ae53c455434023df2c19801 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 27 Jul 2018 10:59:58 +0200
Subject: l2tp: ignore L2TP_ATTR_VLAN_ID netlink attribute

The value of this attribute is never used.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/l2tp.h | 4 ++--
 net/l2tp/l2tp_core.h      | 1 -
 net/l2tp/l2tp_netlink.c   | 3 ---
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index ae888606b3ec..41bf79a4b165 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -60,7 +60,7 @@ struct sockaddr_l2tpip6 {
 /*
  * Commands.
  * Valid TLVs of each command are:-
- * TUNNEL_CREATE	- CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum, vlanid
+ * TUNNEL_CREATE	- CONN_ID, pw_type, netns, ifname, ipinfo, udpinfo, udpcsum
  * TUNNEL_DELETE	- CONN_ID
  * TUNNEL_MODIFY	- CONN_ID, udpcsum
  * TUNNEL_GETSTATS	- CONN_ID, (stats)
@@ -105,7 +105,7 @@ enum {
 	L2TP_ATTR_SESSION_ID,		/* u32 */
 	L2TP_ATTR_PEER_SESSION_ID,	/* u32 */
 	L2TP_ATTR_UDP_CSUM,		/* u8 */
-	L2TP_ATTR_VLAN_ID,		/* u16 */
+	L2TP_ATTR_VLAN_ID,		/* u16 (not used) */
 	L2TP_ATTR_COOKIE,		/* 0, 4 or 8 bytes */
 	L2TP_ATTR_PEER_COOKIE,		/* 0, 4 or 8 bytes */
 	L2TP_ATTR_DEBUG,		/* u32, enum l2tp_debug_flags */
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 7dbfb55ab3b5..49fd5e05538c 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -54,7 +54,6 @@ struct l2tp_session_cfg {
 						 * control of LNS. */
 	int			debug;		/* bitmask of debug message
 						 * categories */
-	u16			vlan_id;	/* VLAN pseudowire only */
 	u16			l2specific_type; /* Layer 2 specific type */
 	u8			cookie[8];	/* optional cookie */
 	int			cookie_len;	/* 0, 4 or 8 bytes */
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index e4785f6966f6..8ea1deefbc37 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -591,9 +591,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 		}
 		if (info->attrs[L2TP_ATTR_IFNAME])
 			cfg.ifname = nla_data(info->attrs[L2TP_ATTR_IFNAME]);
-
-		if (info->attrs[L2TP_ATTR_VLAN_ID])
-			cfg.vlan_id = nla_get_u16(info->attrs[L2TP_ATTR_VLAN_ID]);
 	}
 
 	if (info->attrs[L2TP_ATTR_DEBUG])
-- 
cgit v1.2.3


From 1998b5ed9c9bba5369e7c3659fc8a2e468e62bea Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 27 Jul 2018 10:59:59 +0200
Subject: l2tp: drop ->flags from struct pppol2tp_session

This field is not used.

Keep validating user input in PPPIOCSFLAGS. Even though we discard the
value, it would look wrong to succeed if an invalid address was passed
from userspace.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 13 ++-----------
 1 file changed, 2 insertions(+), 11 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 000c9829304c..759ce8421269 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -127,8 +127,6 @@ struct pppol2tp_session {
 						 * PPPoX socket */
 	struct sock		*__sk;		/* Copy of .sk, for cleanup */
 	struct rcu_head		rcu;		/* For asynchronous release */
-	int			flags;		/* accessed by PPPIOCGFLAGS.
-						 * Unused. */
 };
 
 static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb);
@@ -1057,7 +1055,6 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 	int err = 0;
 	struct sock *sk;
 	int val = (int) arg;
-	struct pppol2tp_session *ps = l2tp_session_priv(session);
 	struct l2tp_tunnel *tunnel = session->tunnel;
 	struct pppol2tp_ioc_stats stats;
 
@@ -1134,21 +1131,15 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 
 	case PPPIOCGFLAGS:
 		err = -EFAULT;
-		if (put_user(ps->flags, (int __user *) arg))
+		if (put_user(0, (int __user *)arg))
 			break;
-
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: get flags=%d\n",
-			  session->name, ps->flags);
 		err = 0;
 		break;
 
 	case PPPIOCSFLAGS:
 		err = -EFAULT;
-		if (get_user(val, (int __user *) arg))
+		if (get_user(val, (int __user *)arg))
 			break;
-		ps->flags = val;
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: set flags=%d\n",
-			  session->name, ps->flags);
 		err = 0;
 		break;
 
-- 
cgit v1.2.3


From 92ea4a7eec7289468ac8de5386f4b13d9c210cb5 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 27 Jul 2018 11:00:00 +0200
Subject: l2tp: drop ->mru from struct l2tp_session

This field is not used.

Treat PPPIOC*MRU the same way as PPPIOC*FLAGS: "get" requests return 0,
while "set" requests vadidate the user supplied pointer but discard its
value.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/l2tp.h |  2 +-
 net/l2tp/l2tp_core.c      |  1 -
 net/l2tp/l2tp_core.h      |  2 --
 net/l2tp/l2tp_debugfs.c   |  4 ++--
 net/l2tp/l2tp_netlink.c   | 10 +---------
 net/l2tp/l2tp_ppp.c       | 41 +++++------------------------------------
 6 files changed, 9 insertions(+), 51 deletions(-)

diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 41bf79a4b165..8bb8c7cfabe5 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -120,7 +120,7 @@ enum {
 	L2TP_ATTR_UDP_SPORT,		/* u16 */
 	L2TP_ATTR_UDP_DPORT,		/* u16 */
 	L2TP_ATTR_MTU,			/* u16 */
-	L2TP_ATTR_MRU,			/* u16 */
+	L2TP_ATTR_MRU,			/* u16 (not used) */
 	L2TP_ATTR_STATS,		/* nested */
 	L2TP_ATTR_IP6_SADDR,		/* struct in6_addr */
 	L2TP_ATTR_IP6_DADDR,		/* struct in6_addr */
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index d10f4ed52d92..c61a467fd9b8 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1675,7 +1675,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 			session->pwtype = cfg->pw_type;
 			session->debug = cfg->debug;
 			session->mtu = cfg->mtu;
-			session->mru = cfg->mru;
 			session->send_seq = cfg->send_seq;
 			session->recv_seq = cfg->recv_seq;
 			session->lns_mode = cfg->lns_mode;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 49fd5e05538c..fa5ae9432d38 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -62,7 +62,6 @@ struct l2tp_session_cfg {
 	int			reorder_timeout; /* configured reorder timeout
 						  * (in jiffies) */
 	int			mtu;
-	int			mru;
 	char			*ifname;
 };
 
@@ -107,7 +106,6 @@ struct l2tp_session {
 						  * (in jiffies) */
 	int			reorder_skip;	/* set if skip to next nr */
 	int			mtu;
-	int			mru;
 	enum l2tp_pwtype	pwtype;
 	struct l2tp_stats	stats;
 	struct hlist_node	global_hlist;	/* Global hash list node */
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index 91b9248610f0..aee271741f5b 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -191,8 +191,8 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
 	if (session->send_seq || session->recv_seq)
 		seq_printf(m, "   nr %hu, ns %hu\n", session->nr, session->ns);
 	seq_printf(m, "   refcnt %d\n", refcount_read(&session->ref_count));
-	seq_printf(m, "   config %d/%d/%c/%c/-/%s %08x %u\n",
-		   session->mtu, session->mru,
+	seq_printf(m, "   config %d/0/%c/%c/-/%s %08x %u\n",
+		   session->mtu,
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 8ea1deefbc37..a7c409215336 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -611,9 +611,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_MTU])
 		cfg.mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]);
 
-	if (info->attrs[L2TP_ATTR_MRU])
-		cfg.mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]);
-
 #ifdef CONFIG_MODULES
 	if (l2tp_nl_cmd_ops[cfg.pw_type] == NULL) {
 		genl_unlock();
@@ -704,9 +701,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_MTU])
 		session->mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]);
 
-	if (info->attrs[L2TP_ATTR_MRU])
-		session->mru = nla_get_u16(info->attrs[L2TP_ATTR_MRU]);
-
 	ret = l2tp_session_notify(&l2tp_nl_family, info,
 				  session, L2TP_CMD_SESSION_MODIFY);
 
@@ -737,9 +731,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 			session->peer_session_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) ||
 	    nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype) ||
-	    nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu) ||
-	    (session->mru &&
-	     nla_put_u16(skb, L2TP_ATTR_MRU, session->mru)))
+	    nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu))
 		goto nla_put_failure;
 
 	if ((session->ifname[0] &&
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 759ce8421269..44cac66284a5 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -570,10 +570,9 @@ static void pppol2tp_session_init(struct l2tp_session *session)
 	if (dst) {
 		u32 pmtu = dst_mtu(dst);
 
-		if (pmtu) {
+		if (pmtu)
 			session->mtu = pmtu - PPPOL2TP_HEADER_OVERHEAD;
-			session->mru = pmtu - PPPOL2TP_HEADER_OVERHEAD;
-		}
+
 		dst_release(dst);
 	}
 }
@@ -781,7 +780,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	} else {
 		/* Default MTU must allow space for UDP/L2TP/PPP headers */
 		cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
-		cfg.mru = cfg.mtu;
 		cfg.pw_type = L2TP_PWTYPE_PPP;
 
 		session = l2tp_session_create(sizeof(struct pppol2tp_session),
@@ -885,8 +883,6 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
 	/* Default MTU values. */
 	if (cfg->mtu == 0)
 		cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
-	if (cfg->mru == 0)
-		cfg->mru = cfg->mtu;
 
 	/* Allocate and initialize a new session context. */
 	session = l2tp_session_create(sizeof(struct pppol2tp_session),
@@ -1101,34 +1097,6 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 		break;
 
 	case PPPIOCGMRU:
-		err = -ENXIO;
-		if (!(sk->sk_state & PPPOX_CONNECTED))
-			break;
-
-		err = -EFAULT;
-		if (put_user(session->mru, (int __user *) arg))
-			break;
-
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: get mru=%d\n",
-			  session->name, session->mru);
-		err = 0;
-		break;
-
-	case PPPIOCSMRU:
-		err = -ENXIO;
-		if (!(sk->sk_state & PPPOX_CONNECTED))
-			break;
-
-		err = -EFAULT;
-		if (get_user(val, (int __user *) arg))
-			break;
-
-		session->mru = val;
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: set mru=%d\n",
-			  session->name, session->mru);
-		err = 0;
-		break;
-
 	case PPPIOCGFLAGS:
 		err = -EFAULT;
 		if (put_user(0, (int __user *)arg))
@@ -1136,6 +1104,7 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 		err = 0;
 		break;
 
+	case PPPIOCSMRU:
 	case PPPIOCSFLAGS:
 		err = -EFAULT;
 		if (get_user(val, (int __user *)arg))
@@ -1723,8 +1692,8 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		   tunnel->peer_tunnel_id,
 		   session->peer_session_id,
 		   state, user_data_ok);
-	seq_printf(m, "   %d/%d/%c/%c/%s %08x %u\n",
-		   session->mtu, session->mru,
+	seq_printf(m, "   %d/0/%c/%c/%s %08x %u\n",
+		   session->mtu,
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
-- 
cgit v1.2.3


From 27defe9d8f6a548e26cd8d9029e5d002163ba854 Mon Sep 17 00:00:00 2001
From: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Date: Fri, 27 Jul 2018 14:29:22 +0530
Subject: cxgb4: print ULD queue information managed by LLD

Signed-off-by: Rahul Lakkireddy <rahul.lakkireddy@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 296 +++++++++++++++++++--
 1 file changed, 277 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 2320f7829a6b..6f312e03432f 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2474,16 +2474,64 @@ static inline struct port_info *ethqset2pinfo(struct adapter *adap, int qset)
 	return NULL;
 }
 
+static int sge_qinfo_uld_txq_entries(const struct adapter *adap, int uld)
+{
+	const struct sge_uld_txq_info *utxq_info = adap->sge.uld_txq_info[uld];
+
+	if (!utxq_info)
+		return 0;
+
+	return DIV_ROUND_UP(utxq_info->ntxq, 4);
+}
+
+static int sge_qinfo_uld_rspq_entries(const struct adapter *adap, int uld,
+				      bool ciq)
+{
+	const struct sge_uld_rxq_info *urxq_info = adap->sge.uld_rxq_info[uld];
+
+	if (!urxq_info)
+		return 0;
+
+	return ciq ? DIV_ROUND_UP(urxq_info->nciq, 4) :
+		     DIV_ROUND_UP(urxq_info->nrxq, 4);
+}
+
+static int sge_qinfo_uld_rxq_entries(const struct adapter *adap, int uld)
+{
+	return sge_qinfo_uld_rspq_entries(adap, uld, false);
+}
+
+static int sge_qinfo_uld_ciq_entries(const struct adapter *adap, int uld)
+{
+	return sge_qinfo_uld_rspq_entries(adap, uld, true);
+}
+
 static int sge_qinfo_show(struct seq_file *seq, void *v)
 {
+	int uld_rxq_entries[CXGB4_ULD_MAX] = { 0 };
+	int uld_ciq_entries[CXGB4_ULD_MAX] = { 0 };
+	int uld_txq_entries[CXGB4_TX_MAX] = { 0 };
+	const struct sge_uld_txq_info *utxq_info;
+	const struct sge_uld_rxq_info *urxq_info;
 	struct adapter *adap = seq->private;
-	int eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
-	int ofld_entries = DIV_ROUND_UP(adap->sge.ofldqsets, 4);
-	int ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
-	int i, r = (uintptr_t)v - 1;
-	int ofld_idx = r - eth_entries;
-	int ctrl_idx =  ofld_idx - ofld_entries;
-	int fq_idx =  ctrl_idx - ctrl_entries;
+	int i, n, r = (uintptr_t)v - 1;
+	int eth_entries, ctrl_entries;
+	struct sge *s = &adap->sge;
+
+	eth_entries = DIV_ROUND_UP(adap->sge.ethqsets, 4);
+	ctrl_entries = DIV_ROUND_UP(MAX_CTRL_QUEUES, 4);
+
+	mutex_lock(&uld_mutex);
+	if (s->uld_txq_info)
+		for (i = 0; i < ARRAY_SIZE(uld_txq_entries); i++)
+			uld_txq_entries[i] = sge_qinfo_uld_txq_entries(adap, i);
+
+	if (s->uld_rxq_info) {
+		for (i = 0; i < ARRAY_SIZE(uld_rxq_entries); i++) {
+			uld_rxq_entries[i] = sge_qinfo_uld_rxq_entries(adap, i);
+			uld_ciq_entries[i] = sge_qinfo_uld_ciq_entries(adap, i);
+		}
+	}
 
 	if (r)
 		seq_putc(seq, '\n');
@@ -2505,9 +2553,10 @@ do { \
 
 	if (r < eth_entries) {
 		int base_qset = r * 4;
-		const struct sge_eth_rxq *rx = &adap->sge.ethrxq[base_qset];
-		const struct sge_eth_txq *tx = &adap->sge.ethtxq[base_qset];
-		int n = min(4, adap->sge.ethqsets - 4 * r);
+		const struct sge_eth_rxq *rx = &s->ethrxq[base_qset];
+		const struct sge_eth_txq *tx = &s->ethtxq[base_qset];
+
+		n = min(4, s->ethqsets - 4 * r);
 
 		S("QType:", "Ethernet");
 		S("Interface:",
@@ -2532,8 +2581,7 @@ do { \
 		R("RspQ CIDX:", rspq.cidx);
 		R("RspQ Gen:", rspq.gen);
 		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
-		S3("u", "Intr pktcnt:",
-		   adap->sge.counter_val[rx[i].rspq.pktcnt_idx]);
+		S3("u", "Intr pktcnt:", s->counter_val[rx[i].rspq.pktcnt_idx]);
 		R("FL ID:", fl.cntxt_id);
 		R("FL size:", fl.size - 8);
 		R("FL pend:", fl.pend_cred);
@@ -2558,9 +2606,196 @@ do { \
 		RL("FLLow:", fl.low);
 		RL("FLStarving:", fl.starving);
 
-	} else if (ctrl_idx < ctrl_entries) {
-		const struct sge_ctrl_txq *tx = &adap->sge.ctrlq[ctrl_idx * 4];
-		int n = min(4, adap->params.nports - 4 * ctrl_idx);
+		goto unlock;
+	}
+
+	r -= eth_entries;
+	if (r < uld_txq_entries[CXGB4_TX_OFLD]) {
+		const struct sge_uld_txq *tx;
+
+		utxq_info = s->uld_txq_info[CXGB4_TX_OFLD];
+		tx = &utxq_info->uldtxq[r * 4];
+		n = min(4, utxq_info->ntxq - 4 * r);
+
+		S("QType:", "OFLD-TXQ");
+		T("TxQ ID:", q.cntxt_id);
+		T("TxQ size:", q.size);
+		T("TxQ inuse:", q.in_use);
+		T("TxQ CIDX:", q.cidx);
+		T("TxQ PIDX:", q.pidx);
+
+		goto unlock;
+	}
+
+	r -= uld_txq_entries[CXGB4_TX_OFLD];
+	if (r < uld_rxq_entries[CXGB4_ULD_RDMA]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_RDMA];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "RDMA-CPL");
+		S("Interface:",
+		  rx[i].rspq.netdev ? rx[i].rspq.netdev->name : "N/A");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_RDMA];
+	if (r < uld_ciq_entries[CXGB4_ULD_RDMA]) {
+		const struct sge_ofld_rxq *rx;
+		int ciq_idx = 0;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_RDMA];
+		ciq_idx = urxq_info->nrxq + (r * 4);
+		rx = &urxq_info->uldrxq[ciq_idx];
+		n = min(4, urxq_info->nciq - 4 * r);
+
+		S("QType:", "RDMA-CIQ");
+		S("Interface:",
+		  rx[i].rspq.netdev ? rx[i].rspq.netdev->name : "N/A");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+
+		goto unlock;
+	}
+
+	r -= uld_ciq_entries[CXGB4_ULD_RDMA];
+	if (r < uld_rxq_entries[CXGB4_ULD_ISCSI]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_ISCSI];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "iSCSI");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_ISCSI];
+	if (r < uld_rxq_entries[CXGB4_ULD_ISCSIT]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_ISCSIT];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "iSCSIT");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_ISCSIT];
+	if (r < uld_rxq_entries[CXGB4_ULD_TLS]) {
+		const struct sge_ofld_rxq *rx;
+
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_TLS];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, urxq_info->nrxq - 4 * r);
+
+		S("QType:", "TLS");
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_rxq_entries[CXGB4_ULD_TLS];
+	if (r < uld_txq_entries[CXGB4_TX_CRYPTO]) {
+		const struct sge_ofld_rxq *rx;
+		const struct sge_uld_txq *tx;
+
+		utxq_info = s->uld_txq_info[CXGB4_TX_CRYPTO];
+		urxq_info = s->uld_rxq_info[CXGB4_ULD_CRYPTO];
+		tx = &utxq_info->uldtxq[r * 4];
+		rx = &urxq_info->uldrxq[r * 4];
+		n = min(4, utxq_info->ntxq - 4 * r);
+
+		S("QType:", "Crypto");
+		T("TxQ ID:", q.cntxt_id);
+		T("TxQ size:", q.size);
+		T("TxQ inuse:", q.in_use);
+		T("TxQ CIDX:", q.cidx);
+		T("TxQ PIDX:", q.pidx);
+		R("RspQ ID:", rspq.abs_id);
+		R("RspQ size:", rspq.size);
+		R("RspQE size:", rspq.iqe_len);
+		R("RspQ CIDX:", rspq.cidx);
+		R("RspQ Gen:", rspq.gen);
+		S3("u", "Intr delay:", qtimer_val(adap, &rx[i].rspq));
+		S3("u", "Intr pktcnt:",	s->counter_val[rx[i].rspq.pktcnt_idx]);
+		R("FL ID:", fl.cntxt_id);
+		R("FL size:", fl.size - 8);
+		R("FL pend:", fl.pend_cred);
+		R("FL avail:", fl.avail);
+		R("FL PIDX:", fl.pidx);
+		R("FL CIDX:", fl.cidx);
+
+		goto unlock;
+	}
+
+	r -= uld_txq_entries[CXGB4_TX_CRYPTO];
+	if (r < ctrl_entries) {
+		const struct sge_ctrl_txq *tx = &s->ctrlq[r * 4];
+
+		n = min(4, adap->params.nports - 4 * r);
 
 		S("QType:", "Control");
 		T("TxQ ID:", q.cntxt_id);
@@ -2570,8 +2805,13 @@ do { \
 		T("TxQ PIDX:", q.pidx);
 		TL("TxQFull:", q.stops);
 		TL("TxQRestarts:", q.restarts);
-	} else if (fq_idx == 0) {
-		const struct sge_rspq *evtq = &adap->sge.fw_evtq;
+
+		goto unlock;
+	}
+
+	r -= ctrl_entries;
+	if (r < 1) {
+		const struct sge_rspq *evtq = &s->fw_evtq;
 
 		seq_printf(seq, "%-12s %16s\n", "QType:", "FW event queue");
 		seq_printf(seq, "%-12s %16u\n", "RspQ ID:", evtq->abs_id);
@@ -2582,8 +2822,13 @@ do { \
 		seq_printf(seq, "%-12s %16u\n", "Intr delay:",
 			   qtimer_val(adap, evtq));
 		seq_printf(seq, "%-12s %16u\n", "Intr pktcnt:",
-			   adap->sge.counter_val[evtq->pktcnt_idx]);
+			   s->counter_val[evtq->pktcnt_idx]);
+
+		goto unlock;
 	}
+
+unlock:
+	mutex_unlock(&uld_mutex);
 #undef R
 #undef RL
 #undef T
@@ -2597,8 +2842,21 @@ do { \
 
 static int sge_queue_entries(const struct adapter *adap)
 {
+	int tot_uld_entries = 0;
+	int i;
+
+	mutex_lock(&uld_mutex);
+	for (i = 0; i < CXGB4_TX_MAX; i++)
+		tot_uld_entries += sge_qinfo_uld_txq_entries(adap, i);
+
+	for (i = 0; i < CXGB4_ULD_MAX; i++) {
+		tot_uld_entries += sge_qinfo_uld_rxq_entries(adap, i);
+		tot_uld_entries += sge_qinfo_uld_ciq_entries(adap, i);
+	}
+	mutex_unlock(&uld_mutex);
+
 	return DIV_ROUND_UP(adap->sge.ethqsets, 4) +
-	       DIV_ROUND_UP(adap->sge.ofldqsets, 4) +
+	       tot_uld_entries +
 	       DIV_ROUND_UP(MAX_CTRL_QUEUES, 4) + 1;
 }
 
-- 
cgit v1.2.3


From 2db6dc2662bab14e59517ab4b86a164cc4d2db42 Mon Sep 17 00:00:00 2001
From: Dave Taht <dave.taht@gmail.com>
Date: Thu, 26 Jul 2018 19:45:10 -0700
Subject: sch_cake: Make gso-splitting configurable from userspace

This patch restores cake's deployed behavior at line rate to always
split gso, and makes gso splitting configurable from userspace.

running cake unlimited (unshaped) at 1gigE, local traffic:

no-split-gso bql limit: 131966
split-gso bql limit:   ~42392-45420

On this 4 stream test splitting gso apart results in halving the
observed interpacket latency at no loss in throughput.

Summary of tcp_nup test run 'gso-split' (at 2018-07-26 16:03:51.824728):

 Ping (ms) ICMP :         0.83         0.81 ms              341
 TCP upload avg :       235.43       235.39 Mbits/s         301
 TCP upload sum :       941.71       941.56 Mbits/s         301
 TCP upload::1  :       235.45       235.43 Mbits/s         271
 TCP upload::2  :       235.45       235.41 Mbits/s         289
 TCP upload::3  :       235.40       235.40 Mbits/s         288
 TCP upload::4  :       235.41       235.40 Mbits/s         291

verses

Summary of tcp_nup test run 'no-split-gso' (at 2018-07-26 16:37:23.563960):

                           avg       median          # data pts
 Ping (ms) ICMP :         1.67         1.73 ms              348
 TCP upload avg :       234.56       235.37 Mbits/s         301
 TCP upload sum :       938.24       941.49 Mbits/s         301
 TCP upload::1  :       234.55       235.38 Mbits/s         285
 TCP upload::2  :       234.57       235.37 Mbits/s         286
 TCP upload::3  :       234.58       235.37 Mbits/s         274
 TCP upload::4  :       234.54       235.42 Mbits/s         288

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/sch_cake.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 539c9490c308..35fc7252187c 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -80,7 +80,6 @@
 #define CAKE_QUEUES (1024)
 #define CAKE_FLOW_MASK 63
 #define CAKE_FLOW_NAT_FLAG 64
-#define CAKE_SPLIT_GSO_THRESHOLD (125000000) /* 1Gbps */
 
 /* struct cobalt_params - contains codel and blue parameters
  * @interval:	codel initial drop rate
@@ -2569,10 +2568,12 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_CAKE_MEMORY])
 		q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
 
-	if (q->rate_bps && q->rate_bps <= CAKE_SPLIT_GSO_THRESHOLD)
-		q->rate_flags |= CAKE_FLAG_SPLIT_GSO;
-	else
-		q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO;
+	if (tb[TCA_CAKE_SPLIT_GSO]) {
+		if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO]))
+			q->rate_flags |= CAKE_FLAG_SPLIT_GSO;
+		else
+			q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO;
+	}
 
 	if (q->tins) {
 		sch_tree_lock(sch);
@@ -2608,7 +2609,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt,
 	q->target   =   5000; /* 5ms: codel RFC argues
 			       * for 5 to 10% of interval
 			       */
-
+	q->rate_flags |= CAKE_FLAG_SPLIT_GSO;
 	q->cur_tin = 0;
 	q->cur_flow  = 0;
 
-- 
cgit v1.2.3


From 39a212ad15f34cebf6d785114c0776a318024ba3 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 26 Jun 2018 17:45:34 -0500
Subject: PCI: Document ACPI description of PCI host bridges

Add a writeup about how PCI host bridges should be described in ACPI
using PNP0A03/PNP0A08 devices, PNP0C02 devices, and the MCFG table.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/PCI/00-INDEX      |   2 +
 Documentation/PCI/acpi-info.txt | 187 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 189 insertions(+)
 create mode 100644 Documentation/PCI/acpi-info.txt

diff --git a/Documentation/PCI/00-INDEX b/Documentation/PCI/00-INDEX
index 00c9a90b6f38..206b1d5c1e71 100644
--- a/Documentation/PCI/00-INDEX
+++ b/Documentation/PCI/00-INDEX
@@ -1,5 +1,7 @@
 00-INDEX
 	- this file
+acpi-info.txt
+	- info on how PCI host bridges are represented in ACPI
 MSI-HOWTO.txt
 	- the Message Signaled Interrupts (MSI) Driver Guide HOWTO and FAQ.
 PCIEBUS-HOWTO.txt
diff --git a/Documentation/PCI/acpi-info.txt b/Documentation/PCI/acpi-info.txt
new file mode 100644
index 000000000000..3ffa3b03970e
--- /dev/null
+++ b/Documentation/PCI/acpi-info.txt
@@ -0,0 +1,187 @@
+		ACPI considerations for PCI host bridges
+
+The general rule is that the ACPI namespace should describe everything the
+OS might use unless there's another way for the OS to find it [1, 2].
+
+For example, there's no standard hardware mechanism for enumerating PCI
+host bridges, so the ACPI namespace must describe each host bridge, the
+method for accessing PCI config space below it, the address space windows
+the host bridge forwards to PCI (using _CRS), and the routing of legacy
+INTx interrupts (using _PRT).
+
+PCI devices, which are below the host bridge, generally do not need to be
+described via ACPI.  The OS can discover them via the standard PCI
+enumeration mechanism, using config accesses to discover and identify
+devices and read and size their BARs.  However, ACPI may describe PCI
+devices if it provides power management or hotplug functionality for them
+or if the device has INTx interrupts connected by platform interrupt
+controllers and a _PRT is needed to describe those connections.
+
+ACPI resource description is done via _CRS objects of devices in the ACPI
+namespace [2].   The _CRS is like a generalized PCI BAR: the OS can read
+_CRS and figure out what resource is being consumed even if it doesn't have
+a driver for the device [3].  That's important because it means an old OS
+can work correctly even on a system with new devices unknown to the OS.
+The new devices might not do anything, but the OS can at least make sure no
+resources conflict with them.
+
+Static tables like MCFG, HPET, ECDT, etc., are *not* mechanisms for
+reserving address space.  The static tables are for things the OS needs to
+know early in boot, before it can parse the ACPI namespace.  If a new table
+is defined, an old OS needs to operate correctly even though it ignores the
+table.  _CRS allows that because it is generic and understood by the old
+OS; a static table does not.
+
+If the OS is expected to manage a non-discoverable device described via
+ACPI, that device will have a specific _HID/_CID that tells the OS what
+driver to bind to it, and the _CRS tells the OS and the driver where the
+device's registers are.
+
+PCI host bridges are PNP0A03 or PNP0A08 devices.  Their _CRS should
+describe all the address space they consume.  This includes all the windows
+they forward down to the PCI bus, as well as registers of the host bridge
+itself that are not forwarded to PCI.  The host bridge registers include
+things like secondary/subordinate bus registers that determine the bus
+range below the bridge, window registers that describe the apertures, etc.
+These are all device-specific, non-architected things, so the only way a
+PNP0A03/PNP0A08 driver can manage them is via _PRS/_CRS/_SRS, which contain
+the device-specific details.  The host bridge registers also include ECAM
+space, since it is consumed by the host bridge.
+
+ACPI defines a Consumer/Producer bit to distinguish the bridge registers
+("Consumer") from the bridge apertures ("Producer") [4, 5], but early
+BIOSes didn't use that bit correctly.  The result is that the current ACPI
+spec defines Consumer/Producer only for the Extended Address Space
+descriptors; the bit should be ignored in the older QWord/DWord/Word
+Address Space descriptors.  Consequently, OSes have to assume all
+QWord/DWord/Word descriptors are windows.
+
+Prior to the addition of Extended Address Space descriptors, the failure of
+Consumer/Producer meant there was no way to describe bridge registers in
+the PNP0A03/PNP0A08 device itself.  The workaround was to describe the
+bridge registers (including ECAM space) in PNP0C02 catch-all devices [6].
+With the exception of ECAM, the bridge register space is device-specific
+anyway, so the generic PNP0A03/PNP0A08 driver (pci_root.c) has no need to
+know about it.  
+
+New architectures should be able to use "Consumer" Extended Address Space
+descriptors in the PNP0A03 device for bridge registers, including ECAM,
+although a strict interpretation of [6] might prohibit this.  Old x86 and
+ia64 kernels assume all address space descriptors, including "Consumer"
+Extended Address Space ones, are windows, so it would not be safe to
+describe bridge registers this way on those architectures.
+
+PNP0C02 "motherboard" devices are basically a catch-all.  There's no
+programming model for them other than "don't use these resources for
+anything else."  So a PNP0C02 _CRS should claim any address space that is
+(1) not claimed by _CRS under any other device object in the ACPI namespace
+and (2) should not be assigned by the OS to something else.
+
+The PCIe spec requires the Enhanced Configuration Access Method (ECAM)
+unless there's a standard firmware interface for config access, e.g., the
+ia64 SAL interface [7].  A host bridge consumes ECAM memory address space
+and converts memory accesses into PCI configuration accesses.  The spec
+defines the ECAM address space layout and functionality; only the base of
+the address space is device-specific.  An ACPI OS learns the base address
+from either the static MCFG table or a _CBA method in the PNP0A03 device.
+
+The MCFG table must describe the ECAM space of non-hot pluggable host
+bridges [8].  Since MCFG is a static table and can't be updated by hotplug,
+a _CBA method in the PNP0A03 device describes the ECAM space of a
+hot-pluggable host bridge [9].  Note that for both MCFG and _CBA, the base
+address always corresponds to bus 0, even if the bus range below the bridge
+(which is reported via _CRS) doesn't start at 0.
+
+
+[1] ACPI 6.2, sec 6.1:
+    For any device that is on a non-enumerable type of bus (for example, an
+    ISA bus), OSPM enumerates the devices' identifier(s) and the ACPI
+    system firmware must supply an _HID object ... for each device to
+    enable OSPM to do that.
+
+[2] ACPI 6.2, sec 3.7:
+    The OS enumerates motherboard devices simply by reading through the
+    ACPI Namespace looking for devices with hardware IDs.
+
+    Each device enumerated by ACPI includes ACPI-defined objects in the
+    ACPI Namespace that report the hardware resources the device could
+    occupy [_PRS], an object that reports the resources that are currently
+    used by the device [_CRS], and objects for configuring those resources
+    [_SRS].  The information is used by the Plug and Play OS (OSPM) to
+    configure the devices.
+
+[3] ACPI 6.2, sec 6.2:
+    OSPM uses device configuration objects to configure hardware resources
+    for devices enumerated via ACPI.  Device configuration objects provide
+    information about current and possible resource requirements, the
+    relationship between shared resources, and methods for configuring
+    hardware resources.
+
+    When OSPM enumerates a device, it calls _PRS to determine the resource
+    requirements of the device.  It may also call _CRS to find the current
+    resource settings for the device.  Using this information, the Plug and
+    Play system determines what resources the device should consume and
+    sets those resources by calling the device’s _SRS control method.
+
+    In ACPI, devices can consume resources (for example, legacy keyboards),
+    provide resources (for example, a proprietary PCI bridge), or do both.
+    Unless otherwise specified, resources for a device are assumed to be
+    taken from the nearest matching resource above the device in the device
+    hierarchy.
+
+[4] ACPI 6.2, sec 6.4.3.5.1, 2, 3, 4:
+    QWord/DWord/Word Address Space Descriptor (.1, .2, .3)
+    General Flags: Bit [0] Ignored
+
+    Extended Address Space Descriptor (.4)
+    General Flags: Bit [0] Consumer/Producer:
+	1–This device consumes this resource
+	0–This device produces and consumes this resource
+
+[5] ACPI 6.2, sec 19.6.43:
+    ResourceUsage specifies whether the Memory range is consumed by
+    this device (ResourceConsumer) or passed on to child devices
+    (ResourceProducer).  If nothing is specified, then
+    ResourceConsumer is assumed.
+
+[6] PCI Firmware 3.2, sec 4.1.2:
+    If the operating system does not natively comprehend reserving the
+    MMCFG region, the MMCFG region must be reserved by firmware.  The
+    address range reported in the MCFG table or by _CBA method (see Section
+    4.1.3) must be reserved by declaring a motherboard resource.  For most
+    systems, the motherboard resource would appear at the root of the ACPI
+    namespace (under \_SB) in a node with a _HID of EISAID (PNP0C02), and
+    the resources in this case should not be claimed in the root PCI bus’s
+    _CRS.  The resources can optionally be returned in Int15 E820 or
+    EFIGetMemoryMap as reserved memory but must always be reported through
+    ACPI as a motherboard resource.
+
+[7] PCI Express 4.0, sec 7.2.2:
+    For systems that are PC-compatible, or that do not implement a
+    processor-architecture-specific firmware interface standard that allows
+    access to the Configuration Space, the ECAM is required as defined in
+    this section.
+
+[8] PCI Firmware 3.2, sec 4.1.2:
+    The MCFG table is an ACPI table that is used to communicate the base
+    addresses corresponding to the non-hot removable PCI Segment Groups
+    range within a PCI Segment Group available to the operating system at
+    boot. This is required for the PC-compatible systems.
+
+    The MCFG table is only used to communicate the base addresses
+    corresponding to the PCI Segment Groups available to the system at
+    boot.
+
+[9] PCI Firmware 3.2, sec 4.1.3:
+    The _CBA (Memory mapped Configuration Base Address) control method is
+    an optional ACPI object that returns the 64-bit memory mapped
+    configuration base address for the hot plug capable host bridge. The
+    base address returned by _CBA is processor-relative address. The _CBA
+    control method evaluates to an Integer.
+
+    This control method appears under a host bridge object. When the _CBA
+    method appears under an active host bridge object, the operating system
+    evaluates this structure to identify the memory mapped configuration
+    base address corresponding to the PCI Segment Group for the bus number
+    range specified in _CRS method. An ACPI name space object that contains
+    the _CBA method must also contain a corresponding _SEG method.
-- 
cgit v1.2.3


From 2bcd619e6e7b992ddaa1caaeafd3eea6990de75c Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 15:57:58 +0800
Subject: net: amd: pcnet32: Replace GFP_ATOMIC with GFP_KERNEL in
 pcnet32_alloc_ring()

pcnet32_alloc_ring() is never called in atomic context.
It calls kcalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/amd/pcnet32.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/amd/pcnet32.c b/drivers/net/ethernet/amd/pcnet32.c
index be198cc0b10c..f5ad12c10934 100644
--- a/drivers/net/ethernet/amd/pcnet32.c
+++ b/drivers/net/ethernet/amd/pcnet32.c
@@ -2036,22 +2036,22 @@ static int pcnet32_alloc_ring(struct net_device *dev, const char *name)
 	}
 
 	lp->tx_dma_addr = kcalloc(lp->tx_ring_size, sizeof(dma_addr_t),
-				  GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!lp->tx_dma_addr)
 		return -ENOMEM;
 
 	lp->rx_dma_addr = kcalloc(lp->rx_ring_size, sizeof(dma_addr_t),
-				  GFP_ATOMIC);
+				  GFP_KERNEL);
 	if (!lp->rx_dma_addr)
 		return -ENOMEM;
 
 	lp->tx_skbuff = kcalloc(lp->tx_ring_size, sizeof(struct sk_buff *),
-				GFP_ATOMIC);
+				GFP_KERNEL);
 	if (!lp->tx_skbuff)
 		return -ENOMEM;
 
 	lp->rx_skbuff = kcalloc(lp->rx_ring_size, sizeof(struct sk_buff *),
-				GFP_ATOMIC);
+				GFP_KERNEL);
 	if (!lp->rx_skbuff)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 89036f233a45d8d17c2de94850bd5e63f185da3d Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:01:41 +0800
Subject: net: hisilicon: hns: Replace mdelay() with msleep()

hns_ppe_common_init_hw() and hns_xgmac_init() are never
called in atomic context.
They call mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c   | 4 ++--
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
index 1c3db67491a4..d160d8c9e45b 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_ppe.c
@@ -204,9 +204,9 @@ static int hns_ppe_common_init_hw(struct ppe_common_cb *ppe_common)
 	enum dsaf_mode dsaf_mode = dsaf_dev->dsaf_mode;
 
 	dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 0);
-	mdelay(100);
+	msleep(100);
 	dsaf_dev->misc_op->ppe_comm_srst(dsaf_dev, 1);
-	mdelay(100);
+	msleep(100);
 
 	if (ppe_common->ppe_mode == PPE_COMMON_MODE_SERVICE) {
 		switch (dsaf_mode) {
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
index 40711af5bd76..ba4316910dea 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_xgmac.c
@@ -215,10 +215,10 @@ static void hns_xgmac_init(void *mac_drv)
 	u32 port = drv->mac_id;
 
 	dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 0);
-	mdelay(100);
+	msleep(100);
 	dsaf_dev->misc_op->xge_srst(dsaf_dev, port, 1);
 
-	mdelay(100);
+	msleep(100);
 	hns_xgmac_lf_rf_control_init(drv);
 	hns_xgmac_exc_irq_en(drv, 0);
 
-- 
cgit v1.2.3


From d818c59a8f490ed8d07bdb4cc175dec97030df26 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:25:07 +0800
Subject: net: jme: Replace mdelay() with msleep() and usleep_range() in
 jme_wait_link()

jme_wait_link() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep() and usleep_range().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/jme.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
index 06ff185eb188..a5ab6f3403ae 100644
--- a/drivers/net/ethernet/jme.c
+++ b/drivers/net/ethernet/jme.c
@@ -1911,10 +1911,10 @@ jme_wait_link(struct jme_adapter *jme)
 {
 	u32 phylink, to = JME_WAIT_LINK_TIME;
 
-	mdelay(1000);
+	msleep(1000);
 	phylink = jme_linkstat_from_phy(jme);
 	while (!(phylink & PHY_LINK_UP) && (to -= 10) > 0) {
-		mdelay(10);
+		usleep_range(10000, 11000);
 		phylink = jme_linkstat_from_phy(jme);
 	}
 }
-- 
cgit v1.2.3


From 6ae5cbc418459c119d211cc3102602b2ec8bc11f Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:29:31 +0800
Subject: net: nvidia: forcedeth: Replace GFP_ATOMIC with GFP_KERNEL in
 nv_probe()

nv_probe() is never called in atomic context.
It calls dma_alloc_coherent() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/nvidia/forcedeth.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c
index 7cbd0174459c..1d9b0d44ddb6 100644
--- a/drivers/net/ethernet/nvidia/forcedeth.c
+++ b/drivers/net/ethernet/nvidia/forcedeth.c
@@ -5777,7 +5777,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 						      (np->rx_ring_size +
 						      np->tx_ring_size),
 						      &np->ring_addr,
-						      GFP_ATOMIC);
+						      GFP_KERNEL);
 		if (!np->rx_ring.orig)
 			goto out_unmap;
 		np->tx_ring.orig = &np->rx_ring.orig[np->rx_ring_size];
@@ -5786,7 +5786,7 @@ static int nv_probe(struct pci_dev *pci_dev, const struct pci_device_id *id)
 						    sizeof(struct ring_desc_ex) *
 						    (np->rx_ring_size +
 						    np->tx_ring_size),
-						    &np->ring_addr, GFP_ATOMIC);
+						    &np->ring_addr, GFP_KERNEL);
 		if (!np->rx_ring.ex)
 			goto out_unmap;
 		np->tx_ring.ex = &np->rx_ring.ex[np->rx_ring_size];
-- 
cgit v1.2.3


From 0df125d05d19ea71678842289647f35cec6d3314 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:34:25 +0800
Subject: net: phy: marvell: Replace mdelay() with msleep() in
 m88e1116r_config_init()

m88e1116r_config_init() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/marvell.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 1cd439bdf608..f7c69ca34056 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -679,7 +679,7 @@ static int m88e1116r_config_init(struct phy_device *phydev)
 	if (err < 0)
 		return err;
 
-	mdelay(500);
+	msleep(500);
 
 	err = marvell_set_page(phydev, MII_MARVELL_COPPER_PAGE);
 	if (err < 0)
-- 
cgit v1.2.3


From 6dff5add089f2cedd597937a3e39a01ebba8b7c8 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:36:29 +0800
Subject: net: usb: pegasus: Replace mdelay() with msleep() in
 setup_pegasus_II()

setup_pegasus_II() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/pegasus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/pegasus.c b/drivers/net/usb/pegasus.c
index 6514c86f043e..f4247b275e09 100644
--- a/drivers/net/usb/pegasus.c
+++ b/drivers/net/usb/pegasus.c
@@ -1067,7 +1067,7 @@ static inline void setup_pegasus_II(pegasus_t *pegasus)
 
 	set_register(pegasus, Reg1d, 0);
 	set_register(pegasus, Reg7b, 1);
-	mdelay(100);
+	msleep(100);
 	if ((pegasus->features & HAS_HOME_PNA) && mii_mode)
 		set_register(pegasus, Reg7b, 0);
 	else
-- 
cgit v1.2.3


From ba23dc642dffd1a97dc08480acc788fdb8632425 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:41:04 +0800
Subject: net: usb: sr9700: Replace mdelay() with msleep() in sr9700_bind()

sr9700_bind() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/sr9700.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 2d316c1b851b..6ac232e52bf7 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -358,7 +358,7 @@ static int sr9700_bind(struct usbnet *dev, struct usb_interface *intf)
 	/* power up and reset phy */
 	sr_write_reg(dev, SR_PRR, PRR_PHY_RST);
 	/* at least 10ms, here 20ms for safe */
-	mdelay(20);
+	msleep(20);
 	sr_write_reg(dev, SR_PRR, 0);
 	/* at least 1ms, here 2ms for reading right register */
 	udelay(2 * 1000);
-- 
cgit v1.2.3


From 04b9ce48ef19e09d8c65eb506b7982e99db212d7 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 17:28:25 +0800
Subject: net: tipc: name_table: Replace GFP_ATOMIC with GFP_KERNEL in
 tipc_nametbl_init()

tipc_nametbl_init() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/name_table.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c
index bebe88cae07b..88f027b502f6 100644
--- a/net/tipc/name_table.c
+++ b/net/tipc/name_table.c
@@ -735,7 +735,7 @@ int tipc_nametbl_init(struct net *net)
 	struct name_table *nt;
 	int i;
 
-	nt = kzalloc(sizeof(*nt), GFP_ATOMIC);
+	nt = kzalloc(sizeof(*nt), GFP_KERNEL);
 	if (!nt)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From a0732548ba03c27fb42da4cf8e1eecc205760f12 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 17:31:35 +0800
Subject: net: tipc: bcast: Replace GFP_ATOMIC with GFP_KERNEL in
 tipc_bcast_init()

tipc_bcast_init() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/bcast.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
index f3711176be45..9ee6cfea56dd 100644
--- a/net/tipc/bcast.c
+++ b/net/tipc/bcast.c
@@ -512,7 +512,7 @@ int tipc_bcast_init(struct net *net)
 	struct tipc_bc_base *bb = NULL;
 	struct tipc_link *l = NULL;
 
-	bb = kzalloc(sizeof(*bb), GFP_ATOMIC);
+	bb = kzalloc(sizeof(*bb), GFP_KERNEL);
 	if (!bb)
 		goto enomem;
 	tn->bcbase = bb;
-- 
cgit v1.2.3


From a082c4f4f022ac5c05c7f26f2dab2982d11d6adb Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Wed, 17 Jan 2018 11:02:31 +0200
Subject: net/mlx5e: Vxlan, reflect 4789 UDP port default addition to software
 database

The hardware offloads 4789 UDP port (default VXLAN port) automatically.
Add it to the software database as well in order to reflect the hardware
state appropriately.

Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 40 +++++++++++++++++--------
 1 file changed, 27 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 2f74953e4561..2f699998d13e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -36,12 +36,20 @@
 #include "mlx5_core.h"
 #include "vxlan.h"
 
+static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
+
 void mlx5e_vxlan_init(struct mlx5e_priv *priv)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 
 	spin_lock_init(&vxlan_db->lock);
 	INIT_RADIX_TREE(&vxlan_db->tree, GFP_ATOMIC);
+
+	if (mlx5e_vxlan_allowed(priv->mdev))
+		/* Hardware adds 4789 by default.
+		 * Lockless since we are the only hash table consumers, wq and TX are disabled.
+		 */
+		mlx5e_vxlan_add_port(priv, 4789);
 }
 
 static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
@@ -78,25 +86,20 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
 	return vxlan;
 }
 
-static void mlx5e_vxlan_add_port(struct work_struct *work)
+static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 {
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv = vxlan_work->priv;
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	u16 port = vxlan_work->port;
 	struct mlx5e_vxlan *vxlan;
 	int err;
 
-	mutex_lock(&priv->state_lock);
 	vxlan = mlx5e_vxlan_lookup_port(priv, port);
 	if (vxlan) {
 		atomic_inc(&vxlan->refcount);
-		goto free_work;
+		return;
 	}
 
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
-		goto free_work;
+		return;
 
 	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
 	if (!vxlan)
@@ -111,18 +114,29 @@ static void mlx5e_vxlan_add_port(struct work_struct *work)
 	if (err)
 		goto err_free;
 
-	goto free_work;
+	return;
 
 err_free:
 	kfree(vxlan);
 err_delete_port:
 	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-free_work:
+}
+
+static void mlx5e_vxlan_add_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5e_vxlan_add_port(priv, port);
 	mutex_unlock(&priv->state_lock);
+
 	kfree(vxlan_work);
 }
 
-static void mlx5e_vxlan_del_port(struct work_struct *work)
+static void mlx5e_vxlan_del_work(struct work_struct *work)
 {
 	struct mlx5e_vxlan_work *vxlan_work =
 		container_of(work, struct mlx5e_vxlan_work, work);
@@ -164,9 +178,9 @@ void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
 		return;
 
 	if (add)
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_port);
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_work);
 	else
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_port);
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_work);
 
 	vxlan_work->priv = priv;
 	vxlan_work->port = port;
-- 
cgit v1.2.3


From 22a65aa8b1a84ca429c0fc8415dee5681ab36eb3 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Mon, 25 Dec 2017 18:40:52 +0200
Subject: net/mlx5e: Vxlan, check maximum number of UDP ports

The NIC has a limited number of offloaded VXLAN UDP ports (usually 4).
Instead of letting the firmware fail when trying to add more ports than
it can handle, let the driver check it on its own.

Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h    |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 14 ++++++++++++++
 include/linux/mlx5/mlx5_ifc.h                   |  4 +++-
 3 files changed, 18 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c41cfc2a4b70..c4d4db8722f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -657,6 +657,7 @@ enum {
 struct mlx5e_vxlan_db {
 	spinlock_t			lock; /* protect vxlan table */
 	struct radix_tree_root		tree;
+	int				num_ports;
 };
 
 struct mlx5e_l2_rule {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 2f699998d13e..e3af2efe18ce 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -52,6 +52,11 @@ void mlx5e_vxlan_init(struct mlx5e_priv *priv)
 		mlx5e_vxlan_add_port(priv, 4789);
 }
 
+static inline u8 mlx5e_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4;
+}
+
 static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 {
 	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
@@ -98,6 +103,13 @@ static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 		return;
 	}
 
+	if (vxlan_db->num_ports >= mlx5e_vxlan_max_udp_ports(priv->mdev)) {
+		netdev_info(priv->netdev,
+			    "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
+			    port, mlx5e_vxlan_max_udp_ports(priv->mdev));
+		return;
+	}
+
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
 		return;
 
@@ -114,6 +126,7 @@ static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 	if (err)
 		goto err_free;
 
+	vxlan_db->num_ports++;
 	return;
 
 err_free:
@@ -163,6 +176,7 @@ out_unlock:
 	if (remove) {
 		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 		kfree(vxlan);
+		vxlan_db->num_ports--;
 	}
 	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 22f54bedfaae..60c2308fe062 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -668,7 +668,9 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         swp[0x1];
 	u8         swp_csum[0x1];
 	u8         swp_lso[0x1];
-	u8         reserved_at_23[0x1b];
+	u8         reserved_at_23[0xd];
+	u8         max_vxlan_udp_ports[0x8];
+	u8         reserved_at_38[0x6];
 	u8         max_geneve_opt_len[0x1];
 	u8         tunnel_stateless_geneve_rx[0x1];
 
-- 
cgit v1.2.3


From d30d8cde19726f177be7615f2e12700d994f6d7f Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 26 Dec 2017 18:27:08 +0200
Subject: net/mlx5e: Vxlan, replace ports radix-tree with hash table

The VXLAN database is accessed in the data path for each VXLAN TX skb in
order to check whether the UDP port is being offloaded or not.
The number of elements in the database is relatively small, we can
simplify the radix-tree to a hash table and speedup the lookup process.

Measuring mlx5e_vxlan_lookup_port execution time:

                  Radix Tree   Hash Table
 --------------- ------------ ------------
  Single Stream   161 ns       79  ns (51% improvement)
  Multi Stream    259 ns       136 ns (47% improvement)

Measuring UDP stream packet rate, single fully utilized TX core:
Radix Tree: 498,300 PPS
Hash Table: 555,468 PPS (11% improvement)

Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h    |  3 +-
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 41 +++++++++++++++----------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h |  1 +
 3 files changed, 28 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index c4d4db8722f5..6878925c3abf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -656,7 +656,8 @@ enum {
 
 struct mlx5e_vxlan_db {
 	spinlock_t			lock; /* protect vxlan table */
-	struct radix_tree_root		tree;
+	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
+	DECLARE_HASHTABLE(htable, 4);
 	int				num_ports;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index e3af2efe18ce..3c0ea9bc20e3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -43,7 +43,7 @@ void mlx5e_vxlan_init(struct mlx5e_priv *priv)
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 
 	spin_lock_init(&vxlan_db->lock);
-	INIT_RADIX_TREE(&vxlan_db->tree, GFP_ATOMIC);
+	hash_init(vxlan_db->htable);
 
 	if (mlx5e_vxlan_allowed(priv->mdev))
 		/* Hardware adds 4789 by default.
@@ -79,13 +79,27 @@ static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
 
+static struct mlx5e_vxlan *mlx5e_vxlan_lookup_port_locked(struct mlx5e_priv *priv,
+							  u16 port)
+{
+	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
+	struct mlx5e_vxlan    *vxlan;
+
+	hash_for_each_possible(vxlan_db->htable, vxlan, hlist, port) {
+		if (vxlan->udp_port == port)
+			return vxlan;
+	}
+
+	return NULL;
+}
+
 struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
 
 	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
+	vxlan = mlx5e_vxlan_lookup_port_locked(priv, port);
 	spin_unlock_bh(&vxlan_db->lock);
 
 	return vxlan;
@@ -95,7 +109,6 @@ static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
-	int err;
 
 	vxlan = mlx5e_vxlan_lookup_port(priv, port);
 	if (vxlan) {
@@ -121,16 +134,12 @@ static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 	atomic_set(&vxlan->refcount, 1);
 
 	spin_lock_bh(&vxlan_db->lock);
-	err = radix_tree_insert(&vxlan_db->tree, vxlan->udp_port, vxlan);
+	hash_add(vxlan_db->htable, &vxlan->hlist, port);
 	spin_unlock_bh(&vxlan_db->lock);
-	if (err)
-		goto err_free;
 
 	vxlan_db->num_ports++;
 	return;
 
-err_free:
-	kfree(vxlan);
 err_delete_port:
 	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 }
@@ -161,12 +170,12 @@ static void mlx5e_vxlan_del_work(struct work_struct *work)
 
 	mutex_lock(&priv->state_lock);
 	spin_lock_bh(&vxlan_db->lock);
-	vxlan = radix_tree_lookup(&vxlan_db->tree, port);
+	vxlan = mlx5e_vxlan_lookup_port_locked(priv, port);
 	if (!vxlan)
 		goto out_unlock;
 
 	if (atomic_dec_and_test(&vxlan->refcount)) {
-		radix_tree_delete(&vxlan_db->tree, port);
+		hash_del(&vxlan->hlist);
 		remove = true;
 	}
 
@@ -206,13 +215,13 @@ void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
-	unsigned int port = 0;
+	struct hlist_node *tmp;
+	int bkt;
 
-	/* Lockless since we are the only radix-tree consumers, wq is disabled */
-	while (radix_tree_gang_lookup(&vxlan_db->tree, (void **)&vxlan, port, 1)) {
-		port = vxlan->udp_port;
-		radix_tree_delete(&vxlan_db->tree, port);
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+	/* Lockless since we are the only hash table consumers, wq and TX are disabled */
+	hash_for_each_safe(vxlan_db->htable, bkt, tmp, vxlan, hlist) {
+		hash_del(&vxlan->hlist);
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
 		kfree(vxlan);
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 5ef6ae7d568a..52c41c22235d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -36,6 +36,7 @@
 #include "en.h"
 
 struct mlx5e_vxlan {
+	struct hlist_node hlist;
 	atomic_t refcount;
 	u16 udp_port;
 };
-- 
cgit v1.2.3


From 9bebf3485c6a365ef0b7e83443a707eda2abc78b Mon Sep 17 00:00:00 2001
From: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Date: Wed, 2 May 2018 15:20:35 +0200
Subject: thermal: ti-soc-thermal: remove dead code

Majority of this code (i.e. functions from ti-bandgap.c) has been
introduced in May 2013 by commit eb982001dbd8 ("thermal: introduce TI
SoC thermal driver"). Just remove it altogether (in case it is needed
it can be easily resurrected from git repo).

While at it fix incorrect "not used" comments.

Tested-by: Keerthy <j-keerthy@ti.com>
Acked-by: Keerthy <j-keerthy@ti.com>
Signed-off-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/ti-soc-thermal/dra752-bandgap.h    |  68 ----
 .../thermal/ti-soc-thermal/dra752-thermal-data.c   |  65 ----
 .../thermal/ti-soc-thermal/omap3-thermal-data.c    |   6 -
 .../thermal/ti-soc-thermal/omap4-thermal-data.c    |  10 -
 drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h  |  10 -
 .../thermal/ti-soc-thermal/omap5-thermal-data.c    |  46 +--
 drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h  |  41 ---
 drivers/thermal/ti-soc-thermal/ti-bandgap.c        | 370 ---------------------
 drivers/thermal/ti-soc-thermal/ti-bandgap.h        |  43 +--
 9 files changed, 5 insertions(+), 654 deletions(-)

diff --git a/drivers/thermal/ti-soc-thermal/dra752-bandgap.h b/drivers/thermal/ti-soc-thermal/dra752-bandgap.h
index a31e4b5e82cd..9490cd63fa6a 100644
--- a/drivers/thermal/ti-soc-thermal/dra752-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/dra752-bandgap.h
@@ -54,56 +54,36 @@
 #define DRA752_STD_FUSE_OPP_BGAP_CORE_OFFSET		0x8
 #define DRA752_TEMP_SENSOR_CORE_OFFSET			0x154
 #define DRA752_BANDGAP_THRESHOLD_CORE_OFFSET		0x1ac
-#define DRA752_BANDGAP_CUMUL_DTEMP_CORE_OFFSET		0x1c4
-#define DRA752_DTEMP_CORE_0_OFFSET			0x208
 #define DRA752_DTEMP_CORE_1_OFFSET			0x20c
 #define DRA752_DTEMP_CORE_2_OFFSET			0x210
-#define DRA752_DTEMP_CORE_3_OFFSET			0x214
-#define DRA752_DTEMP_CORE_4_OFFSET			0x218
 
 /* DRA752.iva register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_IVA_OFFSET		0x388
 #define DRA752_TEMP_SENSOR_IVA_OFFSET			0x398
 #define DRA752_BANDGAP_THRESHOLD_IVA_OFFSET		0x3a4
-#define DRA752_BANDGAP_CUMUL_DTEMP_IVA_OFFSET		0x3b4
-#define DRA752_DTEMP_IVA_0_OFFSET			0x3d0
 #define DRA752_DTEMP_IVA_1_OFFSET			0x3d4
 #define DRA752_DTEMP_IVA_2_OFFSET			0x3d8
-#define DRA752_DTEMP_IVA_3_OFFSET			0x3dc
-#define DRA752_DTEMP_IVA_4_OFFSET			0x3e0
 
 /* DRA752.mpu register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_MPU_OFFSET		0x4
 #define DRA752_TEMP_SENSOR_MPU_OFFSET			0x14c
 #define DRA752_BANDGAP_THRESHOLD_MPU_OFFSET		0x1a4
-#define DRA752_BANDGAP_CUMUL_DTEMP_MPU_OFFSET		0x1bc
-#define DRA752_DTEMP_MPU_0_OFFSET			0x1e0
 #define DRA752_DTEMP_MPU_1_OFFSET			0x1e4
 #define DRA752_DTEMP_MPU_2_OFFSET			0x1e8
-#define DRA752_DTEMP_MPU_3_OFFSET			0x1ec
-#define DRA752_DTEMP_MPU_4_OFFSET			0x1f0
 
 /* DRA752.dspeve register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_DSPEVE_OFFSET			0x384
 #define DRA752_TEMP_SENSOR_DSPEVE_OFFSET			0x394
 #define DRA752_BANDGAP_THRESHOLD_DSPEVE_OFFSET			0x3a0
-#define DRA752_BANDGAP_CUMUL_DTEMP_DSPEVE_OFFSET		0x3b0
-#define DRA752_DTEMP_DSPEVE_0_OFFSET				0x3bc
 #define DRA752_DTEMP_DSPEVE_1_OFFSET				0x3c0
 #define DRA752_DTEMP_DSPEVE_2_OFFSET				0x3c4
-#define DRA752_DTEMP_DSPEVE_3_OFFSET				0x3c8
-#define DRA752_DTEMP_DSPEVE_4_OFFSET				0x3cc
 
 /* DRA752.gpu register offsets */
 #define DRA752_STD_FUSE_OPP_BGAP_GPU_OFFSET		0x0
 #define DRA752_TEMP_SENSOR_GPU_OFFSET			0x150
 #define DRA752_BANDGAP_THRESHOLD_GPU_OFFSET		0x1a8
-#define DRA752_BANDGAP_CUMUL_DTEMP_GPU_OFFSET		0x1c0
-#define DRA752_DTEMP_GPU_0_OFFSET			0x1f4
 #define DRA752_DTEMP_GPU_1_OFFSET			0x1f8
 #define DRA752_DTEMP_GPU_2_OFFSET			0x1fc
-#define DRA752_DTEMP_GPU_3_OFFSET			0x200
-#define DRA752_DTEMP_GPU_4_OFFSET			0x204
 
 /**
  * Register bitfields for DRA752
@@ -114,7 +94,6 @@
  */
 
 /* DRA752.BANDGAP_STATUS_1 */
-#define DRA752_BANDGAP_STATUS_1_ALERT_MASK		BIT(31)
 #define DRA752_BANDGAP_STATUS_1_HOT_CORE_MASK		BIT(5)
 #define DRA752_BANDGAP_STATUS_1_COLD_CORE_MASK		BIT(4)
 #define DRA752_BANDGAP_STATUS_1_HOT_GPU_MASK		BIT(3)
@@ -125,10 +104,6 @@
 /* DRA752.BANDGAP_CTRL_2 */
 #define DRA752_BANDGAP_CTRL_2_FREEZE_IVA_MASK			BIT(22)
 #define DRA752_BANDGAP_CTRL_2_FREEZE_DSPEVE_MASK		BIT(21)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_IVA_MASK			BIT(19)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_DSPEVE_MASK			BIT(18)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_IVA_MASK		BIT(16)
-#define DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_DSPEVE_MASK		BIT(15)
 #define DRA752_BANDGAP_CTRL_2_MASK_HOT_IVA_MASK			BIT(3)
 #define DRA752_BANDGAP_CTRL_2_MASK_COLD_IVA_MASK		BIT(2)
 #define DRA752_BANDGAP_CTRL_2_MASK_HOT_DSPEVE_MASK		BIT(1)
@@ -141,17 +116,10 @@
 #define DRA752_BANDGAP_STATUS_2_COLD_DSPEVE_MASK		BIT(0)
 
 /* DRA752.BANDGAP_CTRL_1 */
-#define DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK			(0x3 << 30)
 #define DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK		(0x7 << 27)
 #define DRA752_BANDGAP_CTRL_1_FREEZE_CORE_MASK			BIT(23)
 #define DRA752_BANDGAP_CTRL_1_FREEZE_GPU_MASK			BIT(22)
 #define DRA752_BANDGAP_CTRL_1_FREEZE_MPU_MASK			BIT(21)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_CORE_MASK			BIT(20)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_GPU_MASK			BIT(19)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_MPU_MASK			BIT(18)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_CORE_MASK		BIT(17)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_GPU_MASK		BIT(16)
-#define DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_MPU_MASK		BIT(15)
 #define DRA752_BANDGAP_CTRL_1_MASK_HOT_CORE_MASK		BIT(5)
 #define DRA752_BANDGAP_CTRL_1_MASK_COLD_CORE_MASK		BIT(4)
 #define DRA752_BANDGAP_CTRL_1_MASK_HOT_GPU_MASK			BIT(3)
@@ -168,22 +136,6 @@
 #define DRA752_BANDGAP_THRESHOLD_HOT_MASK		(0x3ff << 16)
 #define DRA752_BANDGAP_THRESHOLD_COLD_MASK		(0x3ff << 0)
 
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_CORE */
-#define DRA752_BANDGAP_CUMUL_DTEMP_CORE_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_IVA */
-#define DRA752_BANDGAP_CUMUL_DTEMP_IVA_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_MPU */
-#define DRA752_BANDGAP_CUMUL_DTEMP_MPU_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_DSPEVE */
-#define DRA752_BANDGAP_CUMUL_DTEMP_DSPEVE_MASK		(0xffffffff << 0)
-
-/* DRA752.BANDGAP_CUMUL_DTEMP_GPU */
-#define DRA752_BANDGAP_CUMUL_DTEMP_GPU_MASK		(0xffffffff << 0)
-
 /**
  * Temperature limits and thresholds for DRA752
  *
@@ -202,10 +154,6 @@
 /* bandgap clock limits */
 #define DRA752_GPU_MAX_FREQ				1500000
 #define DRA752_GPU_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_GPU_MIN_TEMP				-40000
-#define DRA752_GPU_MAX_TEMP				125000
-#define DRA752_GPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_GPU_T_HOT				800
 #define DRA752_GPU_T_COLD				795
@@ -214,10 +162,6 @@
 /* bandgap clock limits */
 #define DRA752_MPU_MAX_FREQ				1500000
 #define DRA752_MPU_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_MPU_MIN_TEMP				-40000
-#define DRA752_MPU_MAX_TEMP				125000
-#define DRA752_MPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_MPU_T_HOT				800
 #define DRA752_MPU_T_COLD				795
@@ -226,10 +170,6 @@
 /* bandgap clock limits */
 #define DRA752_CORE_MAX_FREQ				1500000
 #define DRA752_CORE_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_CORE_MIN_TEMP				-40000
-#define DRA752_CORE_MAX_TEMP				125000
-#define DRA752_CORE_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_CORE_T_HOT				800
 #define DRA752_CORE_T_COLD				795
@@ -238,10 +178,6 @@
 /* bandgap clock limits */
 #define DRA752_DSPEVE_MAX_FREQ				1500000
 #define DRA752_DSPEVE_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_DSPEVE_MIN_TEMP				-40000
-#define DRA752_DSPEVE_MAX_TEMP				125000
-#define DRA752_DSPEVE_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_DSPEVE_T_HOT				800
 #define DRA752_DSPEVE_T_COLD				795
@@ -250,10 +186,6 @@
 /* bandgap clock limits */
 #define DRA752_IVA_MAX_FREQ				1500000
 #define DRA752_IVA_MIN_FREQ				1000000
-/* sensor limits */
-#define DRA752_IVA_MIN_TEMP				-40000
-#define DRA752_IVA_MAX_TEMP				125000
-#define DRA752_IVA_HYST_VAL				5000
 /* interrupts thresholds */
 #define DRA752_IVA_T_HOT				800
 #define DRA752_IVA_T_COLD				795
diff --git a/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c b/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
index 4167373327d9..33a3030aa3c0 100644
--- a/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/dra752-thermal-data.c
@@ -41,24 +41,16 @@ dra752_core_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_1_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_CORE_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_CORE_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_CORE_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_CORE_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_CORE_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_CORE_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_1_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_1_HOT_CORE_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_1_COLD_CORE_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_CORE_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_CORE_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_CORE_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_CORE_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_CORE_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_CORE_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_CORE_OFFSET,
 };
 
@@ -74,24 +66,16 @@ dra752_iva_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_2_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_2_MASK_HOT_IVA_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_2_MASK_COLD_IVA_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_2_FREEZE_IVA_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_2_CLEAR_IVA_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_IVA_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_IVA_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_2_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_2_HOT_IVA_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_2_COLD_IVA_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_IVA_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_IVA_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_IVA_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_IVA_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_IVA_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_IVA_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_IVA_OFFSET,
 };
 
@@ -107,24 +91,16 @@ dra752_mpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_1_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_MPU_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_MPU_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_MPU_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_MPU_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_MPU_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_MPU_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_1_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_1_HOT_MPU_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_1_COLD_MPU_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_MPU_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_MPU_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_MPU_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_MPU_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_MPU_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_MPU_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_MPU_OFFSET,
 };
 
@@ -140,24 +116,16 @@ dra752_dspeve_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_2_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_2_MASK_HOT_DSPEVE_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_2_MASK_COLD_DSPEVE_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_2_FREEZE_DSPEVE_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_2_CLEAR_DSPEVE_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_2_CLEAR_ACCUM_DSPEVE_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_DSPEVE_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_2_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_2_HOT_DSPEVE_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_2_COLD_DSPEVE_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_DSPEVE_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_DSPEVE_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_DSPEVE_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_DSPEVE_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_DSPEVE_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_DSPEVE_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_DSPEVE_OFFSET,
 };
 
@@ -173,24 +141,16 @@ dra752_gpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = DRA752_BANDGAP_CTRL_1_OFFSET,
 	.mask_hot_mask = DRA752_BANDGAP_CTRL_1_MASK_HOT_GPU_MASK,
 	.mask_cold_mask = DRA752_BANDGAP_CTRL_1_MASK_COLD_GPU_MASK,
-	.mask_sidlemode_mask = DRA752_BANDGAP_CTRL_1_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = DRA752_BANDGAP_CTRL_1_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = DRA752_BANDGAP_CTRL_1_FREEZE_GPU_MASK,
-	.mask_clear_mask = DRA752_BANDGAP_CTRL_1_CLEAR_GPU_MASK,
-	.mask_clear_accum_mask = DRA752_BANDGAP_CTRL_1_CLEAR_ACCUM_GPU_MASK,
 	.bgap_threshold = DRA752_BANDGAP_THRESHOLD_GPU_OFFSET,
 	.threshold_thot_mask = DRA752_BANDGAP_THRESHOLD_HOT_MASK,
 	.threshold_tcold_mask = DRA752_BANDGAP_THRESHOLD_COLD_MASK,
 	.bgap_status = DRA752_BANDGAP_STATUS_1_OFFSET,
-	.status_bgap_alert_mask = DRA752_BANDGAP_STATUS_1_ALERT_MASK,
 	.status_hot_mask = DRA752_BANDGAP_STATUS_1_HOT_GPU_MASK,
 	.status_cold_mask = DRA752_BANDGAP_STATUS_1_COLD_GPU_MASK,
-	.bgap_cumul_dtemp = DRA752_BANDGAP_CUMUL_DTEMP_GPU_OFFSET,
-	.ctrl_dtemp_0 = DRA752_DTEMP_GPU_0_OFFSET,
 	.ctrl_dtemp_1 = DRA752_DTEMP_GPU_1_OFFSET,
 	.ctrl_dtemp_2 = DRA752_DTEMP_GPU_2_OFFSET,
-	.ctrl_dtemp_3 = DRA752_DTEMP_GPU_3_OFFSET,
-	.ctrl_dtemp_4 = DRA752_DTEMP_GPU_4_OFFSET,
 	.bgap_efuse = DRA752_STD_FUSE_OPP_BGAP_GPU_OFFSET,
 };
 
@@ -200,11 +160,6 @@ static struct temp_sensor_data dra752_mpu_temp_sensor_data = {
 	.t_cold = DRA752_MPU_T_COLD,
 	.min_freq = DRA752_MPU_MIN_FREQ,
 	.max_freq = DRA752_MPU_MAX_FREQ,
-	.max_temp = DRA752_MPU_MAX_TEMP,
-	.min_temp = DRA752_MPU_MIN_TEMP,
-	.hyst_val = DRA752_MPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 GPU temperature sensor */
@@ -213,11 +168,6 @@ static struct temp_sensor_data dra752_gpu_temp_sensor_data = {
 	.t_cold = DRA752_GPU_T_COLD,
 	.min_freq = DRA752_GPU_MIN_FREQ,
 	.max_freq = DRA752_GPU_MAX_FREQ,
-	.max_temp = DRA752_GPU_MAX_TEMP,
-	.min_temp = DRA752_GPU_MIN_TEMP,
-	.hyst_val = DRA752_GPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 CORE temperature sensor */
@@ -226,11 +176,6 @@ static struct temp_sensor_data dra752_core_temp_sensor_data = {
 	.t_cold = DRA752_CORE_T_COLD,
 	.min_freq = DRA752_CORE_MIN_FREQ,
 	.max_freq = DRA752_CORE_MAX_FREQ,
-	.max_temp = DRA752_CORE_MAX_TEMP,
-	.min_temp = DRA752_CORE_MIN_TEMP,
-	.hyst_val = DRA752_CORE_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 DSPEVE temperature sensor */
@@ -239,11 +184,6 @@ static struct temp_sensor_data dra752_dspeve_temp_sensor_data = {
 	.t_cold = DRA752_DSPEVE_T_COLD,
 	.min_freq = DRA752_DSPEVE_MIN_FREQ,
 	.max_freq = DRA752_DSPEVE_MAX_FREQ,
-	.max_temp = DRA752_DSPEVE_MAX_TEMP,
-	.min_temp = DRA752_DSPEVE_MIN_TEMP,
-	.hyst_val = DRA752_DSPEVE_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for DRA752 IVA temperature sensor */
@@ -252,11 +192,6 @@ static struct temp_sensor_data dra752_iva_temp_sensor_data = {
 	.t_cold = DRA752_IVA_T_COLD,
 	.min_freq = DRA752_IVA_MIN_FREQ,
 	.max_freq = DRA752_IVA_MAX_FREQ,
-	.max_temp = DRA752_IVA_MAX_TEMP,
-	.min_temp = DRA752_IVA_MIN_TEMP,
-	.hyst_val = DRA752_IVA_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /*
diff --git a/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c
index c6d217913dd1..f5366807daf0 100644
--- a/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap3-thermal-data.c
@@ -48,9 +48,6 @@ omap34xx_mpu_temp_sensor_registers = {
 static struct temp_sensor_data omap34xx_mpu_temp_sensor_data = {
 	.min_freq = 32768,
 	.max_freq = 32768,
-	.max_temp = 125000,
-	.min_temp = -40000,
-	.hyst_val = 5000,
 };
 
 /*
@@ -119,9 +116,6 @@ omap36xx_mpu_temp_sensor_registers = {
 static struct temp_sensor_data omap36xx_mpu_temp_sensor_data = {
 	.min_freq = 32768,
 	.max_freq = 32768,
-	.max_temp = 125000,
-	.min_temp = -40000,
-	.hyst_val = 5000,
 };
 
 /*
diff --git a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
index fd1113360603..c12211eaaac4 100644
--- a/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap4-thermal-data.c
@@ -42,9 +42,6 @@ omap4430_mpu_temp_sensor_registers = {
 static struct temp_sensor_data omap4430_mpu_temp_sensor_data = {
 	.min_freq = OMAP4430_MIN_FREQ,
 	.max_freq = OMAP4430_MAX_FREQ,
-	.max_temp = OMAP4430_MAX_TEMP,
-	.min_temp = OMAP4430_MIN_TEMP,
-	.hyst_val = OMAP4430_HYST_VAL,
 };
 
 /*
@@ -121,8 +118,6 @@ omap4460_mpu_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP4460_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP4460_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = OMAP4460_CLEAN_STOP_MASK,
-	.status_bgap_alert_mask = OMAP4460_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP4460_HOT_FLAG_MASK,
 	.status_cold_mask = OMAP4460_COLD_FLAG_MASK,
 
@@ -137,11 +132,6 @@ static struct temp_sensor_data omap4460_mpu_temp_sensor_data = {
 	.t_cold = OMAP4460_T_COLD,
 	.min_freq = OMAP4460_MIN_FREQ,
 	.max_freq = OMAP4460_MAX_FREQ,
-	.max_temp = OMAP4460_MAX_TEMP,
-	.min_temp = OMAP4460_MIN_TEMP,
-	.hyst_val = OMAP4460_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /*
diff --git a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
index 6f2de3a3356d..b87c8659ec60 100644
--- a/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/omap4xxx-bandgap.h
@@ -73,10 +73,6 @@
 /* bandgap clock limits (no control on 4430) */
 #define OMAP4430_MAX_FREQ				32768
 #define OMAP4430_MIN_FREQ				32768
-/* sensor limits */
-#define OMAP4430_MIN_TEMP				-40000
-#define OMAP4430_MAX_TEMP				125000
-#define OMAP4430_HYST_VAL				5000
 
 /**
  * *** OMAP4460 *** Applicable for OMAP4470
@@ -143,8 +139,6 @@
 #define OMAP4460_TSHUT_COLD_MASK			(0x3ff << 0)
 
 /* OMAP4460.BANDGAP_STATUS bits */
-#define OMAP4460_CLEAN_STOP_MASK			BIT(3)
-#define OMAP4460_BGAP_ALERT_MASK			BIT(2)
 #define OMAP4460_HOT_FLAG_MASK				BIT(1)
 #define OMAP4460_COLD_FLAG_MASK				BIT(0)
 
@@ -162,10 +156,6 @@
 /* bandgap clock limits */
 #define OMAP4460_MAX_FREQ				1500000
 #define OMAP4460_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP4460_MIN_TEMP				-40000
-#define OMAP4460_MAX_TEMP				123000
-#define OMAP4460_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP4460_TSHUT_HOT				900	/* 122 deg C */
 #define OMAP4460_TSHUT_COLD				895	/* 100 deg C */
diff --git a/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c b/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c
index 6ac037098b52..8191bae834de 100644
--- a/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c
+++ b/drivers/thermal/ti-soc-thermal/omap5-thermal-data.c
@@ -38,12 +38,8 @@ omap5430_mpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = OMAP5430_BGAP_CTRL_OFFSET,
 	.mask_hot_mask = OMAP5430_MASK_HOT_MPU_MASK,
 	.mask_cold_mask = OMAP5430_MASK_COLD_MPU_MASK,
-	.mask_sidlemode_mask = OMAP5430_MASK_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = OMAP5430_MASK_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = OMAP5430_MASK_FREEZE_MPU_MASK,
-	.mask_clear_mask = OMAP5430_MASK_CLEAR_MPU_MASK,
-	.mask_clear_accum_mask = OMAP5430_MASK_CLEAR_ACCUM_MPU_MASK,
-
 
 	.bgap_counter = OMAP5430_BGAP_CTRL_OFFSET,
 	.counter_mask = OMAP5430_COUNTER_MASK,
@@ -57,17 +53,11 @@ omap5430_mpu_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP5430_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP5430_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = 0x0,
-	.status_bgap_alert_mask = OMAP5430_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP5430_HOT_MPU_FLAG_MASK,
 	.status_cold_mask = OMAP5430_COLD_MPU_FLAG_MASK,
 
-	.bgap_cumul_dtemp = OMAP5430_BGAP_CUMUL_DTEMP_MPU_OFFSET,
-	.ctrl_dtemp_0 = OMAP5430_BGAP_DTEMP_MPU_0_OFFSET,
 	.ctrl_dtemp_1 = OMAP5430_BGAP_DTEMP_MPU_1_OFFSET,
 	.ctrl_dtemp_2 = OMAP5430_BGAP_DTEMP_MPU_2_OFFSET,
-	.ctrl_dtemp_3 = OMAP5430_BGAP_DTEMP_MPU_3_OFFSET,
-	.ctrl_dtemp_4 = OMAP5430_BGAP_DTEMP_MPU_4_OFFSET,
 	.bgap_efuse = OMAP5430_FUSE_OPP_BGAP_MPU,
 };
 
@@ -84,11 +74,8 @@ omap5430_gpu_temp_sensor_registers = {
 	.bgap_mask_ctrl = OMAP5430_BGAP_CTRL_OFFSET,
 	.mask_hot_mask = OMAP5430_MASK_HOT_GPU_MASK,
 	.mask_cold_mask = OMAP5430_MASK_COLD_GPU_MASK,
-	.mask_sidlemode_mask = OMAP5430_MASK_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = OMAP5430_MASK_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = OMAP5430_MASK_FREEZE_GPU_MASK,
-	.mask_clear_mask = OMAP5430_MASK_CLEAR_GPU_MASK,
-	.mask_clear_accum_mask = OMAP5430_MASK_CLEAR_ACCUM_GPU_MASK,
 
 	.bgap_counter = OMAP5430_BGAP_CTRL_OFFSET,
 	.counter_mask = OMAP5430_COUNTER_MASK,
@@ -102,17 +89,11 @@ omap5430_gpu_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP5430_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP5430_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = 0x0,
-	.status_bgap_alert_mask = OMAP5430_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP5430_HOT_GPU_FLAG_MASK,
 	.status_cold_mask = OMAP5430_COLD_GPU_FLAG_MASK,
 
-	.bgap_cumul_dtemp = OMAP5430_BGAP_CUMUL_DTEMP_GPU_OFFSET,
-	.ctrl_dtemp_0 = OMAP5430_BGAP_DTEMP_GPU_0_OFFSET,
 	.ctrl_dtemp_1 = OMAP5430_BGAP_DTEMP_GPU_1_OFFSET,
 	.ctrl_dtemp_2 = OMAP5430_BGAP_DTEMP_GPU_2_OFFSET,
-	.ctrl_dtemp_3 = OMAP5430_BGAP_DTEMP_GPU_3_OFFSET,
-	.ctrl_dtemp_4 = OMAP5430_BGAP_DTEMP_GPU_4_OFFSET,
 
 	.bgap_efuse = OMAP5430_FUSE_OPP_BGAP_GPU,
 };
@@ -130,11 +111,8 @@ omap5430_core_temp_sensor_registers = {
 	.bgap_mask_ctrl = OMAP5430_BGAP_CTRL_OFFSET,
 	.mask_hot_mask = OMAP5430_MASK_HOT_CORE_MASK,
 	.mask_cold_mask = OMAP5430_MASK_COLD_CORE_MASK,
-	.mask_sidlemode_mask = OMAP5430_MASK_SIDLEMODE_MASK,
 	.mask_counter_delay_mask = OMAP5430_MASK_COUNTER_DELAY_MASK,
 	.mask_freeze_mask = OMAP5430_MASK_FREEZE_CORE_MASK,
-	.mask_clear_mask = OMAP5430_MASK_CLEAR_CORE_MASK,
-	.mask_clear_accum_mask = OMAP5430_MASK_CLEAR_ACCUM_CORE_MASK,
 
 	.bgap_counter = OMAP5430_BGAP_CTRL_OFFSET,
 	.counter_mask = OMAP5430_COUNTER_MASK,
@@ -148,17 +126,11 @@ omap5430_core_temp_sensor_registers = {
 	.tshut_cold_mask = OMAP5430_TSHUT_COLD_MASK,
 
 	.bgap_status = OMAP5430_BGAP_STATUS_OFFSET,
-	.status_clean_stop_mask = 0x0,
-	.status_bgap_alert_mask = OMAP5430_BGAP_ALERT_MASK,
 	.status_hot_mask = OMAP5430_HOT_CORE_FLAG_MASK,
 	.status_cold_mask = OMAP5430_COLD_CORE_FLAG_MASK,
 
-	.bgap_cumul_dtemp = OMAP5430_BGAP_CUMUL_DTEMP_CORE_OFFSET,
-	.ctrl_dtemp_0 = OMAP5430_BGAP_DTEMP_CORE_0_OFFSET,
 	.ctrl_dtemp_1 = OMAP5430_BGAP_DTEMP_CORE_1_OFFSET,
 	.ctrl_dtemp_2 = OMAP5430_BGAP_DTEMP_CORE_2_OFFSET,
-	.ctrl_dtemp_3 = OMAP5430_BGAP_DTEMP_CORE_3_OFFSET,
-	.ctrl_dtemp_4 = OMAP5430_BGAP_DTEMP_CORE_4_OFFSET,
 
 	.bgap_efuse = OMAP5430_FUSE_OPP_BGAP_CORE,
 };
@@ -171,11 +143,6 @@ static struct temp_sensor_data omap5430_mpu_temp_sensor_data = {
 	.t_cold = OMAP5430_MPU_T_COLD,
 	.min_freq = OMAP5430_MPU_MIN_FREQ,
 	.max_freq = OMAP5430_MPU_MAX_FREQ,
-	.max_temp = OMAP5430_MPU_MAX_TEMP,
-	.min_temp = OMAP5430_MPU_MIN_TEMP,
-	.hyst_val = OMAP5430_MPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for OMAP5430 GPU temperature sensor */
@@ -186,11 +153,6 @@ static struct temp_sensor_data omap5430_gpu_temp_sensor_data = {
 	.t_cold = OMAP5430_GPU_T_COLD,
 	.min_freq = OMAP5430_GPU_MIN_FREQ,
 	.max_freq = OMAP5430_GPU_MAX_FREQ,
-	.max_temp = OMAP5430_GPU_MAX_TEMP,
-	.min_temp = OMAP5430_GPU_MIN_TEMP,
-	.hyst_val = OMAP5430_GPU_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /* Thresholds and limits for OMAP5430 CORE temperature sensor */
@@ -201,11 +163,6 @@ static struct temp_sensor_data omap5430_core_temp_sensor_data = {
 	.t_cold = OMAP5430_CORE_T_COLD,
 	.min_freq = OMAP5430_CORE_MIN_FREQ,
 	.max_freq = OMAP5430_CORE_MAX_FREQ,
-	.max_temp = OMAP5430_CORE_MAX_TEMP,
-	.min_temp = OMAP5430_CORE_MIN_TEMP,
-	.hyst_val = OMAP5430_CORE_HYST_VAL,
-	.update_int1 = 1000,
-	.update_int2 = 2000,
 };
 
 /*
@@ -319,8 +276,7 @@ const struct ti_bandgap_data omap5430_data = {
 			TI_BANDGAP_FEATURE_FREEZE_BIT |
 			TI_BANDGAP_FEATURE_TALERT |
 			TI_BANDGAP_FEATURE_COUNTER_DELAY |
-			TI_BANDGAP_FEATURE_HISTORY_BUFFER |
-			TI_BANDGAP_FEATURE_ERRATA_813,
+			TI_BANDGAP_FEATURE_HISTORY_BUFFER,
 	.fclock_name = "l3instr_ts_gclk_div",
 	.div_ck_name = "l3instr_ts_gclk_div",
 	.conv_table = omap5430_adc_to_temp,
diff --git a/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h b/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h
index 400b55dffadd..9096403b74b0 100644
--- a/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/omap5xxx-bandgap.h
@@ -44,36 +44,24 @@
 #define OMAP5430_TEMP_SENSOR_GPU_OFFSET			0x150
 #define OMAP5430_BGAP_THRESHOLD_GPU_OFFSET		0x1A8
 #define OMAP5430_BGAP_TSHUT_GPU_OFFSET			0x1B4
-#define OMAP5430_BGAP_CUMUL_DTEMP_GPU_OFFSET		0x1C0
-#define OMAP5430_BGAP_DTEMP_GPU_0_OFFSET		0x1F4
 #define OMAP5430_BGAP_DTEMP_GPU_1_OFFSET		0x1F8
 #define OMAP5430_BGAP_DTEMP_GPU_2_OFFSET		0x1FC
-#define OMAP5430_BGAP_DTEMP_GPU_3_OFFSET		0x200
-#define OMAP5430_BGAP_DTEMP_GPU_4_OFFSET		0x204
 
 /* OMAP5430.MPU register offsets */
 #define OMAP5430_FUSE_OPP_BGAP_MPU			0x4
 #define OMAP5430_TEMP_SENSOR_MPU_OFFSET			0x14C
 #define OMAP5430_BGAP_THRESHOLD_MPU_OFFSET		0x1A4
 #define OMAP5430_BGAP_TSHUT_MPU_OFFSET			0x1B0
-#define OMAP5430_BGAP_CUMUL_DTEMP_MPU_OFFSET		0x1BC
-#define OMAP5430_BGAP_DTEMP_MPU_0_OFFSET		0x1E0
 #define OMAP5430_BGAP_DTEMP_MPU_1_OFFSET		0x1E4
 #define OMAP5430_BGAP_DTEMP_MPU_2_OFFSET		0x1E8
-#define OMAP5430_BGAP_DTEMP_MPU_3_OFFSET		0x1EC
-#define OMAP5430_BGAP_DTEMP_MPU_4_OFFSET		0x1F0
 
 /* OMAP5430.MPU register offsets */
 #define OMAP5430_FUSE_OPP_BGAP_CORE			0x8
 #define OMAP5430_TEMP_SENSOR_CORE_OFFSET		0x154
 #define OMAP5430_BGAP_THRESHOLD_CORE_OFFSET		0x1AC
 #define OMAP5430_BGAP_TSHUT_CORE_OFFSET			0x1B8
-#define OMAP5430_BGAP_CUMUL_DTEMP_CORE_OFFSET		0x1C4
-#define OMAP5430_BGAP_DTEMP_CORE_0_OFFSET		0x208
 #define OMAP5430_BGAP_DTEMP_CORE_1_OFFSET		0x20C
 #define OMAP5430_BGAP_DTEMP_CORE_2_OFFSET		0x210
-#define OMAP5430_BGAP_DTEMP_CORE_3_OFFSET		0x214
-#define OMAP5430_BGAP_DTEMP_CORE_4_OFFSET		0x218
 
 /* OMAP5430.common register offsets */
 #define OMAP5430_BGAP_CTRL_OFFSET			0x1A0
@@ -94,17 +82,10 @@
 #define OMAP5430_BGAP_TEMP_SENSOR_DTEMP_MASK		(0x3ff << 0)
 
 /* OMAP5430.BANDGAP_CTRL */
-#define OMAP5430_MASK_SIDLEMODE_MASK			(0x3 << 30)
 #define OMAP5430_MASK_COUNTER_DELAY_MASK		(0x7 << 27)
 #define OMAP5430_MASK_FREEZE_CORE_MASK			BIT(23)
 #define OMAP5430_MASK_FREEZE_GPU_MASK			BIT(22)
 #define OMAP5430_MASK_FREEZE_MPU_MASK			BIT(21)
-#define OMAP5430_MASK_CLEAR_CORE_MASK			BIT(20)
-#define OMAP5430_MASK_CLEAR_GPU_MASK			BIT(19)
-#define OMAP5430_MASK_CLEAR_MPU_MASK			BIT(18)
-#define OMAP5430_MASK_CLEAR_ACCUM_CORE_MASK		BIT(17)
-#define OMAP5430_MASK_CLEAR_ACCUM_GPU_MASK		BIT(16)
-#define OMAP5430_MASK_CLEAR_ACCUM_MPU_MASK		BIT(15)
 #define OMAP5430_MASK_HOT_CORE_MASK			BIT(5)
 #define OMAP5430_MASK_COLD_CORE_MASK			BIT(4)
 #define OMAP5430_MASK_HOT_GPU_MASK			BIT(3)
@@ -123,17 +104,7 @@
 #define OMAP5430_TSHUT_HOT_MASK				(0x3ff << 16)
 #define OMAP5430_TSHUT_COLD_MASK			(0x3ff << 0)
 
-/* OMAP5430.BANDGAP_CUMUL_DTEMP_MPU */
-#define OMAP5430_CUMUL_DTEMP_MPU_MASK			(0xffffffff << 0)
-
-/* OMAP5430.BANDGAP_CUMUL_DTEMP_GPU */
-#define OMAP5430_CUMUL_DTEMP_GPU_MASK			(0xffffffff << 0)
-
-/* OMAP5430.BANDGAP_CUMUL_DTEMP_CORE */
-#define OMAP5430_CUMUL_DTEMP_CORE_MASK			(0xffffffff << 0)
-
 /* OMAP5430.BANDGAP_STATUS */
-#define OMAP5430_BGAP_ALERT_MASK			BIT(31)
 #define OMAP5430_HOT_CORE_FLAG_MASK			BIT(5)
 #define OMAP5430_COLD_CORE_FLAG_MASK			BIT(4)
 #define OMAP5430_HOT_GPU_FLAG_MASK			BIT(3)
@@ -159,10 +130,6 @@
 /* bandgap clock limits */
 #define OMAP5430_GPU_MAX_FREQ				1500000
 #define OMAP5430_GPU_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP5430_GPU_MIN_TEMP				-40000
-#define OMAP5430_GPU_MAX_TEMP				125000
-#define OMAP5430_GPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP5430_GPU_TSHUT_HOT				915
 #define OMAP5430_GPU_TSHUT_COLD				900
@@ -173,10 +140,6 @@
 /* bandgap clock limits */
 #define OMAP5430_MPU_MAX_FREQ				1500000
 #define OMAP5430_MPU_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP5430_MPU_MIN_TEMP				-40000
-#define OMAP5430_MPU_MAX_TEMP				125000
-#define OMAP5430_MPU_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP5430_MPU_TSHUT_HOT				915
 #define OMAP5430_MPU_TSHUT_COLD				900
@@ -187,10 +150,6 @@
 /* bandgap clock limits */
 #define OMAP5430_CORE_MAX_FREQ				1500000
 #define OMAP5430_CORE_MIN_FREQ				1000000
-/* sensor limits */
-#define OMAP5430_CORE_MIN_TEMP				-40000
-#define OMAP5430_CORE_MAX_TEMP				125000
-#define OMAP5430_CORE_HYST_VAL				5000
 /* interrupts thresholds */
 #define OMAP5430_CORE_TSHUT_HOT				915
 #define OMAP5430_CORE_TSHUT_COLD			900
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.c b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
index 696ab3046b87..097328d8e943 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.c
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.c
@@ -305,217 +305,6 @@ int ti_bandgap_adc_to_mcelsius(struct ti_bandgap *bgp, int adc_val, int *t)
 	return 0;
 }
 
-/**
- * ti_bandgap_mcelsius_to_adc() - converts a mCelsius value to ADC scale
- * @bgp: struct ti_bandgap pointer
- * @temp: value in mCelsius
- * @adc: address where to write the resulting temperature in ADC representation
- *
- * Simple conversion from mCelsius to ADC values. In case the temp value
- * is out of the ADC conv table range, it returns -ERANGE, 0 on success.
- * The conversion table is indexed by the ADC values.
- *
- * Return: 0 if conversion was successful, else -ERANGE in case the @temp
- * argument is out of the ADC conv table range.
- */
-static
-int ti_bandgap_mcelsius_to_adc(struct ti_bandgap *bgp, long temp, int *adc)
-{
-	const struct ti_bandgap_data *conf = bgp->conf;
-	const int *conv_table = bgp->conf->conv_table;
-	int high, low, mid;
-
-	low = 0;
-	high = conf->adc_end_val - conf->adc_start_val;
-	mid = (high + low) / 2;
-
-	if (temp < conv_table[low] || temp > conv_table[high])
-		return -ERANGE;
-
-	while (low < high) {
-		if (temp < conv_table[mid])
-			high = mid - 1;
-		else
-			low = mid + 1;
-		mid = (low + high) / 2;
-	}
-
-	*adc = conf->adc_start_val + low;
-	return 0;
-}
-
-/**
- * ti_bandgap_add_hyst() - add hysteresis (in mCelsius) to an ADC value
- * @bgp: struct ti_bandgap pointer
- * @adc_val: temperature value in ADC representation
- * @hyst_val: hysteresis value in mCelsius
- * @sum: address where to write the resulting temperature (in ADC scale)
- *
- * Adds an hysteresis value (in mCelsius) to a ADC temperature value.
- *
- * Return: 0 on success, -ERANGE otherwise.
- */
-static
-int ti_bandgap_add_hyst(struct ti_bandgap *bgp, int adc_val, int hyst_val,
-			u32 *sum)
-{
-	int temp, ret;
-
-	/*
-	 * Need to add in the mcelsius domain, so we have a temperature
-	 * the conv_table range
-	 */
-	ret = ti_bandgap_adc_to_mcelsius(bgp, adc_val, &temp);
-	if (ret < 0)
-		return ret;
-
-	temp += hyst_val;
-
-	ret = ti_bandgap_mcelsius_to_adc(bgp, temp, sum);
-	return ret;
-}
-
-/***   Helper functions handling device Alert/Shutdown signals   ***/
-
-/**
- * ti_bandgap_unmask_interrupts() - unmasks the events of thot & tcold
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @t_hot: hot temperature value to trigger alert signal
- * @t_cold: cold temperature value to trigger alert signal
- *
- * Checks the requested t_hot and t_cold values and configures the IRQ event
- * masks accordingly. Call this function only if bandgap features HAS(TALERT).
- */
-static void ti_bandgap_unmask_interrupts(struct ti_bandgap *bgp, int id,
-					 u32 t_hot, u32 t_cold)
-{
-	struct temp_sensor_registers *tsr;
-	u32 temp, reg_val;
-
-	/* Read the current on die temperature */
-	temp = ti_bandgap_read_temp(bgp, id);
-
-	tsr = bgp->conf->sensors[id].registers;
-	reg_val = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
-
-	if (temp < t_hot)
-		reg_val |= tsr->mask_hot_mask;
-	else
-		reg_val &= ~tsr->mask_hot_mask;
-
-	if (t_cold < temp)
-		reg_val |= tsr->mask_cold_mask;
-	else
-		reg_val &= ~tsr->mask_cold_mask;
-	ti_bandgap_writel(bgp, reg_val, tsr->bgap_mask_ctrl);
-}
-
-/**
- * ti_bandgap_update_alert_threshold() - sequence to update thresholds
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @val: value (ADC) of a new threshold
- * @hot: desired threshold to be updated. true if threshold hot, false if
- *       threshold cold
- *
- * It will program the required thresholds (hot and cold) for TALERT signal.
- * This function can be used to update t_hot or t_cold, depending on @hot value.
- * It checks the resulting t_hot and t_cold values, based on the new passed @val
- * and configures the thresholds so that t_hot is always greater than t_cold.
- * Call this function only if bandgap features HAS(TALERT).
- *
- * Return: 0 if no error, else corresponding error
- */
-static int ti_bandgap_update_alert_threshold(struct ti_bandgap *bgp, int id,
-					     int val, bool hot)
-{
-	struct temp_sensor_data *ts_data = bgp->conf->sensors[id].ts_data;
-	struct temp_sensor_registers *tsr;
-	u32 thresh_val, reg_val, t_hot, t_cold, ctrl;
-	int err = 0;
-
-	tsr = bgp->conf->sensors[id].registers;
-
-	/* obtain the current value */
-	thresh_val = ti_bandgap_readl(bgp, tsr->bgap_threshold);
-	t_cold = (thresh_val & tsr->threshold_tcold_mask) >>
-		__ffs(tsr->threshold_tcold_mask);
-	t_hot = (thresh_val & tsr->threshold_thot_mask) >>
-		__ffs(tsr->threshold_thot_mask);
-	if (hot)
-		t_hot = val;
-	else
-		t_cold = val;
-
-	if (t_cold > t_hot) {
-		if (hot)
-			err = ti_bandgap_add_hyst(bgp, t_hot,
-						  -ts_data->hyst_val,
-						  &t_cold);
-		else
-			err = ti_bandgap_add_hyst(bgp, t_cold,
-						  ts_data->hyst_val,
-						  &t_hot);
-	}
-
-	/* write the new threshold values */
-	reg_val = thresh_val &
-		  ~(tsr->threshold_thot_mask | tsr->threshold_tcold_mask);
-	reg_val |= (t_hot << __ffs(tsr->threshold_thot_mask)) |
-		   (t_cold << __ffs(tsr->threshold_tcold_mask));
-
-	/**
-	 * Errata i813:
-	 * Spurious Thermal Alert: Talert can happen randomly while the device
-	 * remains under the temperature limit defined for this event to trig.
-	 * This spurious event is caused by a incorrect re-synchronization
-	 * between clock domains. The comparison between configured threshold
-	 * and current temperature value can happen while the value is
-	 * transitioning (metastable), thus causing inappropriate event
-	 * generation. No spurious event occurs as long as the threshold value
-	 * stays unchanged. Spurious event can be generated while a thermal
-	 * alert threshold is modified in
-	 * CONTROL_BANDGAP_THRESHOLD_MPU/GPU/CORE/DSPEVE/IVA_n.
-	 */
-
-	if (TI_BANDGAP_HAS(bgp, ERRATA_813)) {
-		/* Mask t_hot and t_cold events at the IP Level */
-		ctrl = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
-
-		if (hot)
-			ctrl &= ~tsr->mask_hot_mask;
-		else
-			ctrl &= ~tsr->mask_cold_mask;
-
-		ti_bandgap_writel(bgp, ctrl, tsr->bgap_mask_ctrl);
-	}
-
-	/* Write the threshold value */
-	ti_bandgap_writel(bgp, reg_val, tsr->bgap_threshold);
-
-	if (TI_BANDGAP_HAS(bgp, ERRATA_813)) {
-		/* Unmask t_hot and t_cold events at the IP Level */
-		ctrl = ti_bandgap_readl(bgp, tsr->bgap_mask_ctrl);
-		if (hot)
-			ctrl |= tsr->mask_hot_mask;
-		else
-			ctrl |= tsr->mask_cold_mask;
-
-		ti_bandgap_writel(bgp, ctrl, tsr->bgap_mask_ctrl);
-	}
-
-	if (err) {
-		dev_err(bgp->dev, "failed to reprogram thot threshold\n");
-		err = -EIO;
-		goto exit;
-	}
-
-	ti_bandgap_unmask_interrupts(bgp, id, t_hot, t_cold);
-exit:
-	return err;
-}
-
 /**
  * ti_bandgap_validate() - helper to check the sanity of a struct ti_bandgap
  * @bgp: struct ti_bandgap pointer
@@ -543,165 +332,6 @@ static inline int ti_bandgap_validate(struct ti_bandgap *bgp, int id)
 	return 0;
 }
 
-/**
- * _ti_bandgap_write_threshold() - helper to update TALERT t_cold or t_hot
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @val: value (mCelsius) of a new threshold
- * @hot: desired threshold to be updated. true if threshold hot, false if
- *       threshold cold
- *
- * It will update the required thresholds (hot and cold) for TALERT signal.
- * This function can be used to update t_hot or t_cold, depending on @hot value.
- * Validates the mCelsius range and update the requested threshold.
- * Call this function only if bandgap features HAS(TALERT).
- *
- * Return: 0 if no error, else corresponding error value.
- */
-static int _ti_bandgap_write_threshold(struct ti_bandgap *bgp, int id, int val,
-				       bool hot)
-{
-	struct temp_sensor_data *ts_data;
-	struct temp_sensor_registers *tsr;
-	u32 adc_val;
-	int ret;
-
-	ret = ti_bandgap_validate(bgp, id);
-	if (ret)
-		return ret;
-
-	if (!TI_BANDGAP_HAS(bgp, TALERT))
-		return -ENOTSUPP;
-
-	ts_data = bgp->conf->sensors[id].ts_data;
-	tsr = bgp->conf->sensors[id].registers;
-	if (hot) {
-		if (val < ts_data->min_temp + ts_data->hyst_val)
-			ret = -EINVAL;
-	} else {
-		if (val > ts_data->max_temp + ts_data->hyst_val)
-			ret = -EINVAL;
-	}
-
-	if (ret)
-		return ret;
-
-	ret = ti_bandgap_mcelsius_to_adc(bgp, val, &adc_val);
-	if (ret < 0)
-		return ret;
-
-	spin_lock(&bgp->lock);
-	ret = ti_bandgap_update_alert_threshold(bgp, id, adc_val, hot);
-	spin_unlock(&bgp->lock);
-	return ret;
-}
-
-/**
- * _ti_bandgap_read_threshold() - helper to read TALERT t_cold or t_hot
- * @bgp: struct ti_bandgap pointer
- * @id: bandgap sensor id
- * @val: value (mCelsius) of a threshold
- * @hot: desired threshold to be read. true if threshold hot, false if
- *       threshold cold
- *
- * It will fetch the required thresholds (hot and cold) for TALERT signal.
- * This function can be used to read t_hot or t_cold, depending on @hot value.
- * Call this function only if bandgap features HAS(TALERT).
- *
- * Return: 0 if no error, -ENOTSUPP if it has no TALERT support, or the
- * corresponding error value if some operation fails.
- */
-static int _ti_bandgap_read_threshold(struct ti_bandgap *bgp, int id,
-				      int *val, bool hot)
-{
-	struct temp_sensor_registers *tsr;
-	u32 temp, mask;
-	int ret = 0;
-
-	ret = ti_bandgap_validate(bgp, id);
-	if (ret)
-		goto exit;
-
-	if (!TI_BANDGAP_HAS(bgp, TALERT)) {
-		ret = -ENOTSUPP;
-		goto exit;
-	}
-
-	tsr = bgp->conf->sensors[id].registers;
-	if (hot)
-		mask = tsr->threshold_thot_mask;
-	else
-		mask = tsr->threshold_tcold_mask;
-
-	temp = ti_bandgap_readl(bgp, tsr->bgap_threshold);
-	temp = (temp & mask) >> __ffs(mask);
-	ret = ti_bandgap_adc_to_mcelsius(bgp, temp, &temp);
-	if (ret) {
-		dev_err(bgp->dev, "failed to read thot\n");
-		ret = -EIO;
-		goto exit;
-	}
-
-	*val = temp;
-
-exit:
-	return ret;
-}
-
-/***   Exposed APIs   ***/
-
-/**
- * ti_bandgap_read_thot() - reads sensor current thot
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @thot: resulting current thot value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_read_thot(struct ti_bandgap *bgp, int id, int *thot)
-{
-	return _ti_bandgap_read_threshold(bgp, id, thot, true);
-}
-
-/**
- * ti_bandgap_write_thot() - sets sensor current thot
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @val: desired thot value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_write_thot(struct ti_bandgap *bgp, int id, int val)
-{
-	return _ti_bandgap_write_threshold(bgp, id, val, true);
-}
-
-/**
- * ti_bandgap_read_tcold() - reads sensor current tcold
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @tcold: resulting current tcold value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_read_tcold(struct ti_bandgap *bgp, int id, int *tcold)
-{
-	return _ti_bandgap_read_threshold(bgp, id, tcold, false);
-}
-
-/**
- * ti_bandgap_write_tcold() - sets the sensor tcold
- * @bgp: pointer to bandgap instance
- * @id: sensor id
- * @val: desired tcold value
- *
- * Return: 0 on success or the proper error code
- */
-int ti_bandgap_write_tcold(struct ti_bandgap *bgp, int id, int val)
-{
-	return _ti_bandgap_write_threshold(bgp, id, val, false);
-}
-
 /**
  * ti_bandgap_read_counter() - read the sensor counter
  * @bgp: pointer to bandgap instance
diff --git a/drivers/thermal/ti-soc-thermal/ti-bandgap.h b/drivers/thermal/ti-soc-thermal/ti-bandgap.h
index 209c664c2823..68d39ad43241 100644
--- a/drivers/thermal/ti-soc-thermal/ti-bandgap.h
+++ b/drivers/thermal/ti-soc-thermal/ti-bandgap.h
@@ -78,11 +78,8 @@
  * @bgap_mask_ctrl: BANDGAP_MASK_CTRL register offset
  * @mask_hot_mask: mask to bandgap_mask_ctrl.mask_hot
  * @mask_cold_mask: mask to bandgap_mask_ctrl.mask_cold
- * @mask_sidlemode_mask: mask to bandgap_mask_ctrl.mask_sidlemode
  * @mask_counter_delay_mask: mask to bandgap_mask_ctrl.mask_counter_delay
  * @mask_freeze_mask: mask to bandgap_mask_ctrl.mask_free
- * @mask_clear_mask: mask to bandgap_mask_ctrl.mask_clear
- * @mask_clear_accum_mask: mask to bandgap_mask_ctrl.mask_clear_accum
  * @bgap_mode_ctrl: BANDGAP_MODE_CTRL register offset
  * @mode_ctrl_mask: mask to bandgap_mode_ctrl.mode_ctrl
  * @bgap_counter: BANDGAP_COUNTER register offset
@@ -91,21 +88,13 @@
  * @threshold_thot_mask: mask to bandgap_threhold.thot
  * @threshold_tcold_mask: mask to bandgap_threhold.tcold
  * @tshut_threshold: TSHUT_THRESHOLD register offset (TSHUT thresholds)
- * @tshut_efuse_mask: mask to tshut_threshold.tshut_efuse
- * @tshut_efuse_shift: shift to tshut_threshold.tshut_efuse
  * @tshut_hot_mask: mask to tshut_threhold.thot
  * @tshut_cold_mask: mask to tshut_threhold.thot
  * @bgap_status: BANDGAP_STATUS register offset
- * @status_clean_stop_mask: mask to bandgap_status.clean_stop
- * @status_bgap_alert_mask: mask to bandgap_status.bandgap_alert
  * @status_hot_mask: mask to bandgap_status.hot
  * @status_cold_mask: mask to bandgap_status.cold
- * @bgap_cumul_dtemp: BANDGAP_CUMUL_DTEMP register offset
- * @ctrl_dtemp_0: CTRL_DTEMP0 register offset
  * @ctrl_dtemp_1: CTRL_DTEMP1 register offset
  * @ctrl_dtemp_2: CTRL_DTEMP2 register offset
- * @ctrl_dtemp_3: CTRL_DTEMP3 register offset
- * @ctrl_dtemp_4: CTRL_DTEMP4 register offset
  * @bgap_efuse: BANDGAP_EFUSE register offset
  *
  * The register offsets and bitfields might change across
@@ -121,17 +110,14 @@ struct temp_sensor_registers {
 	u32	temp_sensor_ctrl;
 	u32	bgap_tempsoff_mask;
 	u32	bgap_soc_mask;
-	u32	bgap_eocz_mask; /* not used: but needs revisit */
+	u32	bgap_eocz_mask;
 	u32	bgap_dtemp_mask;
 
 	u32	bgap_mask_ctrl;
 	u32	mask_hot_mask;
 	u32	mask_cold_mask;
-	u32	mask_sidlemode_mask; /* not used: but may be needed for pm */
 	u32	mask_counter_delay_mask;
 	u32	mask_freeze_mask;
-	u32	mask_clear_mask; /* not used: but needed for trending */
-	u32	mask_clear_accum_mask; /* not used: but needed for trending */
 
 	u32	bgap_mode_ctrl;
 	u32	mode_ctrl_mask;
@@ -144,23 +130,15 @@ struct temp_sensor_registers {
 	u32	threshold_tcold_mask;
 
 	u32	tshut_threshold;
-	u32	tshut_efuse_mask; /* not used */
-	u32	tshut_efuse_shift; /* not used */
 	u32	tshut_hot_mask;
 	u32	tshut_cold_mask;
 
 	u32	bgap_status;
-	u32	status_clean_stop_mask; /* not used: but needed for trending */
-	u32	status_bgap_alert_mask; /* not used */
 	u32	status_hot_mask;
 	u32	status_cold_mask;
 
-	u32	bgap_cumul_dtemp; /* not used: but needed for trending */
-	u32	ctrl_dtemp_0; /* not used: but needed for trending */
-	u32	ctrl_dtemp_1; /* not used: but needed for trending */
-	u32	ctrl_dtemp_2; /* not used: but needed for trending */
-	u32	ctrl_dtemp_3; /* not used: but needed for trending */
-	u32	ctrl_dtemp_4; /* not used: but needed for trending */
+	u32	ctrl_dtemp_1;
+	u32	ctrl_dtemp_2;
 	u32	bgap_efuse;
 };
 
@@ -172,11 +150,6 @@ struct temp_sensor_registers {
  * @t_cold: temperature to trigger a thermal alert (low initial value)
  * @min_freq: sensor minimum clock rate
  * @max_freq: sensor maximum clock rate
- * @max_temp: sensor maximum temperature
- * @min_temp: sensor minimum temperature
- * @hyst_val: temperature hysteresis considered while converting ADC values
- * @update_int1: update interval
- * @update_int2: update interval
  *
  * This data structure will hold the required thresholds and temperature limits
  * for a specific temperature sensor, like shutdown temperature, alert
@@ -189,11 +162,6 @@ struct temp_sensor_data {
 	u32	t_cold;
 	u32	min_freq;
 	u32	max_freq;
-	int     max_temp;
-	int     min_temp;
-	int     hyst_val;
-	u32     update_int1; /* not used */
-	u32     update_int2; /* not used */
 };
 
 struct ti_bandgap_data;
@@ -316,8 +284,6 @@ struct ti_temp_sensor {
  *
  * TI_BANDGAP_FEATURE_ERRATA_814 - used to workaorund when the bandgap device
  *	has Errata 814
- * TI_BANDGAP_FEATURE_ERRATA_813 - used to workaorund when the bandgap device
- *	has Errata 813
  * TI_BANDGAP_FEATURE_UNRELIABLE - used when the sensor readings are too
  *	inaccurate.
  * TI_BANDGAP_HAS(b, f) - macro to check if a bandgap device is capable of a
@@ -334,8 +300,7 @@ struct ti_temp_sensor {
 #define TI_BANDGAP_FEATURE_COUNTER_DELAY	BIT(8)
 #define TI_BANDGAP_FEATURE_HISTORY_BUFFER	BIT(9)
 #define TI_BANDGAP_FEATURE_ERRATA_814		BIT(10)
-#define TI_BANDGAP_FEATURE_ERRATA_813		BIT(11)
-#define TI_BANDGAP_FEATURE_UNRELIABLE		BIT(12)
+#define TI_BANDGAP_FEATURE_UNRELIABLE		BIT(11)
 #define TI_BANDGAP_HAS(b, f)			\
 			((b)->conf->features & TI_BANDGAP_FEATURE_ ## f)
 
-- 
cgit v1.2.3


From 8d98761a6fc1eeee7232471c5285665fc7ecaa23 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:44 +0200
Subject: thermal: armada: add a function that sanitizes the thermal zone name

Thermal zone names must follow certain rules imposed by the framework.
They are limited in length and shall not have any hyphen '-'.

This is done in a separate function for future use in another location.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 37 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 4c275ec10ac5..4c88d70f09e5 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -70,6 +70,7 @@ struct armada_thermal_priv {
 	void __iomem *status;
 	void __iomem *control0;
 	void __iomem *control1;
+	char zone_name[THERMAL_NAME_LENGTH];
 	struct armada_thermal_data *data;
 };
 
@@ -353,6 +354,37 @@ static const struct of_device_id armada_thermal_id_table[] = {
 };
 MODULE_DEVICE_TABLE(of, armada_thermal_id_table);
 
+static void armada_set_sane_name(struct platform_device *pdev,
+				 struct armada_thermal_priv *priv)
+{
+	const char *name = dev_name(&pdev->dev);
+	char *insane_char;
+
+	if (strlen(name) > THERMAL_NAME_LENGTH) {
+		/*
+		 * When inside a system controller, the device name has the
+		 * form: f06f8000.system-controller:ap-thermal so stripping
+		 * after the ':' should give us a shorter but meaningful name.
+		 */
+		name = strrchr(name, ':');
+		if (!name)
+			name = "armada_thermal";
+		else
+			name++;
+	}
+
+	/* Save the name locally */
+	strncpy(priv->zone_name, name, THERMAL_NAME_LENGTH - 1);
+	priv->zone_name[THERMAL_NAME_LENGTH - 1] = '\0';
+
+	/* Then check there are no '-' or hwmon core will complain */
+	do {
+		insane_char = strpbrk(priv->zone_name, "-");
+		if (insane_char)
+			*insane_char = '_';
+	} while (insane_char);
+}
+
 static int armada_thermal_probe(struct platform_device *pdev)
 {
 	void __iomem *control = NULL;
@@ -381,6 +413,9 @@ static int armada_thermal_probe(struct platform_device *pdev)
 
 	priv->data = (struct armada_thermal_data *)match->data;
 
+	/* Ensure device name is correct for the thermal core */
+	armada_set_sane_name(pdev, priv);
+
 	/*
 	 * Legacy DT bindings only described "control1" register (also referred
 	 * as "control MSB" on old documentation). New bindings cover
@@ -402,7 +437,7 @@ static int armada_thermal_probe(struct platform_device *pdev)
 
 	priv->data->init_sensor(pdev, priv);
 
-	thermal = thermal_zone_device_register(dev_name(&pdev->dev), 0, 0, priv,
+	thermal = thermal_zone_device_register(priv->zone_name, 0, 0, priv,
 					       &ops, NULL, 0, 0);
 	if (IS_ERR(thermal)) {
 		dev_err(&pdev->dev,
-- 
cgit v1.2.3


From 931d3c5db42c935c7fcf119e844176ca5dcae326 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:45 +0200
Subject: thermal: armada: remove useless register accesses

Prepare the migration to use regmaps by first simplifying the
initialization functions: avoid unnecessary write/read cycles on
configuration registers.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 4c88d70f09e5..de1d1c6b1975 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -103,16 +103,13 @@ static void armadaxp_init_sensor(struct platform_device *pdev,
 
 	reg = readl_relaxed(priv->control1);
 	reg |= PMU_TDC0_OTF_CAL_MASK;
-	writel(reg, priv->control1);
 
 	/* Reference calibration value */
 	reg &= ~PMU_TDC0_REF_CAL_CNT_MASK;
 	reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS);
-	writel(reg, priv->control1);
 
 	/* Reset the sensor */
-	reg = readl_relaxed(priv->control1);
-	writel((reg | PMU_TDC0_SW_RST_MASK), priv->control1);
+	reg |= PMU_TDC0_SW_RST_MASK;
 
 	writel(reg, priv->control1);
 
@@ -129,14 +126,13 @@ static void armada370_init_sensor(struct platform_device *pdev,
 
 	reg = readl_relaxed(priv->control1);
 	reg |= PMU_TDC0_OTF_CAL_MASK;
-	writel(reg, priv->control1);
 
 	/* Reference calibration value */
 	reg &= ~PMU_TDC0_REF_CAL_CNT_MASK;
 	reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS);
-	writel(reg, priv->control1);
 
 	reg &= ~PMU_TDC0_START_CAL_MASK;
+
 	writel(reg, priv->control1);
 
 	msleep(10);
-- 
cgit v1.2.3


From c5d7d57e6892e1613157c89c22b13441f9d2ddf5 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:46 +0200
Subject: thermal: armada: remove misleading comments

On older versions of this thermal IP, TSEN referred as the internal
sensor in the thermal IP while EXT_TSEN referred as sensors outside of
this IP, ie in the CPUs most of the time. The bit names in the
specifications do not follow this rule anymore, so remove these comments
that are misleading.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index de1d1c6b1975..6cc53eef651d 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -51,12 +51,10 @@
 #define CONTROL0_TSEN_TC_TRIM_MASK	0x7
 #define CONTROL0_TSEN_TC_TRIM_VAL	0x3
 
-/* TSEN refers to the temperature sensors within the AP */
 #define CONTROL0_TSEN_START		BIT(0)
 #define CONTROL0_TSEN_RESET		BIT(1)
 #define CONTROL0_TSEN_ENABLE		BIT(2)
 
-/* EXT_TSEN refers to the external temperature sensors, out of the AP */
 #define CONTROL1_EXT_TSEN_SW_RESET	BIT(7)
 #define CONTROL1_EXT_TSEN_HW_RESETn	BIT(8)
 
-- 
cgit v1.2.3


From 8b4c2712cd7cbf9f83b8032550c7cbdfcdf970eb Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:47 +0200
Subject: thermal: armada: rename the initialization routine

Calling a hook ->init_sensor() while what is initialized is the IP
itself and not the sensors is misleading. Rename the hook ->init() to
avoid any confusion in later work bringing multi-sensors support.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 6cc53eef651d..2f2150f9639f 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -73,9 +73,9 @@ struct armada_thermal_priv {
 };
 
 struct armada_thermal_data {
-	/* Initialize the sensor */
-	void (*init_sensor)(struct platform_device *pdev,
-			    struct armada_thermal_priv *);
+	/* Initialize the thermal IC */
+	void (*init)(struct platform_device *pdev,
+		     struct armada_thermal_priv *priv);
 
 	/* Test for a valid sensor value (optional) */
 	bool (*is_valid)(struct armada_thermal_priv *);
@@ -94,8 +94,8 @@ struct armada_thermal_data {
 	bool needs_control0;
 };
 
-static void armadaxp_init_sensor(struct platform_device *pdev,
-				 struct armada_thermal_priv *priv)
+static void armadaxp_init(struct platform_device *pdev,
+			  struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
@@ -117,8 +117,8 @@ static void armadaxp_init_sensor(struct platform_device *pdev,
 	writel(reg, priv->status);
 }
 
-static void armada370_init_sensor(struct platform_device *pdev,
-				  struct armada_thermal_priv *priv)
+static void armada370_init(struct platform_device *pdev,
+			   struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
@@ -136,8 +136,8 @@ static void armada370_init_sensor(struct platform_device *pdev,
 	msleep(10);
 }
 
-static void armada375_init_sensor(struct platform_device *pdev,
-				  struct armada_thermal_priv *priv)
+static void armada375_init(struct platform_device *pdev,
+			   struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
@@ -164,8 +164,8 @@ static void armada_wait_sensor_validity(struct armada_thermal_priv *priv)
 				   STATUS_POLL_TIMEOUT_US);
 }
 
-static void armada380_init_sensor(struct platform_device *pdev,
-				  struct armada_thermal_priv *priv)
+static void armada380_init(struct platform_device *pdev,
+			   struct armada_thermal_priv *priv)
 {
 	u32 reg = readl_relaxed(priv->control1);
 
@@ -186,8 +186,8 @@ static void armada380_init_sensor(struct platform_device *pdev,
 	armada_wait_sensor_validity(priv);
 }
 
-static void armada_ap806_init_sensor(struct platform_device *pdev,
-				     struct armada_thermal_priv *priv)
+static void armada_ap806_init(struct platform_device *pdev,
+			      struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
@@ -247,7 +247,7 @@ static struct thermal_zone_device_ops ops = {
 };
 
 static const struct armada_thermal_data armadaxp_data = {
-	.init_sensor = armadaxp_init_sensor,
+	.init = armadaxp_init,
 	.temp_shift = 10,
 	.temp_mask = 0x1ff,
 	.coef_b = 3153000000ULL,
@@ -257,7 +257,7 @@ static const struct armada_thermal_data armadaxp_data = {
 
 static const struct armada_thermal_data armada370_data = {
 	.is_valid = armada_is_valid,
-	.init_sensor = armada370_init_sensor,
+	.init = armada370_init,
 	.is_valid_bit = BIT(9),
 	.temp_shift = 10,
 	.temp_mask = 0x1ff,
@@ -268,7 +268,7 @@ static const struct armada_thermal_data armada370_data = {
 
 static const struct armada_thermal_data armada375_data = {
 	.is_valid = armada_is_valid,
-	.init_sensor = armada375_init_sensor,
+	.init = armada375_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
 	.temp_mask = 0x1ff,
@@ -280,7 +280,7 @@ static const struct armada_thermal_data armada375_data = {
 
 static const struct armada_thermal_data armada380_data = {
 	.is_valid = armada_is_valid,
-	.init_sensor = armada380_init_sensor,
+	.init = armada380_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
@@ -292,7 +292,7 @@ static const struct armada_thermal_data armada380_data = {
 
 static const struct armada_thermal_data armada_ap806_data = {
 	.is_valid = armada_is_valid,
-	.init_sensor = armada_ap806_init_sensor,
+	.init = armada_ap806_init,
 	.is_valid_bit = BIT(16),
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
@@ -306,7 +306,7 @@ static const struct armada_thermal_data armada_ap806_data = {
 
 static const struct armada_thermal_data armada_cp110_data = {
 	.is_valid = armada_is_valid,
-	.init_sensor = armada380_init_sensor,
+	.init = armada380_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
@@ -429,7 +429,7 @@ static int armada_thermal_probe(struct platform_device *pdev)
 		priv->control1 = control + CONTROL1_OFFSET;
 	}
 
-	priv->data->init_sensor(pdev, priv);
+	priv->data->init(pdev, priv);
 
 	thermal = thermal_zone_device_register(priv->zone_name, 0, 0, priv,
 					       &ops, NULL, 0, 0);
-- 
cgit v1.2.3


From 5b5e17a182e14316ab4369fd9e8173207cf42130 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:48 +0200
Subject: thermal: armada: dissociate a380 and cp110 ->init() hooks

Until now, Armada 380 and CP110 could share the same ->init() function
because their use was identical.

Prepare the support of multi-sensors support and overheat interrupt
feature by separating the initialization paths before they actually
diverge.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 2f2150f9639f..31ff57a654ba 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -200,6 +200,12 @@ static void armada_ap806_init(struct platform_device *pdev,
 	armada_wait_sensor_validity(priv);
 }
 
+static void armada_cp110_init(struct platform_device *pdev,
+			      struct armada_thermal_priv *priv)
+{
+	armada380_init(pdev, priv);
+}
+
 static bool armada_is_valid(struct armada_thermal_priv *priv)
 {
 	u32 reg = readl_relaxed(priv->status);
@@ -306,7 +312,7 @@ static const struct armada_thermal_data armada_ap806_data = {
 
 static const struct armada_thermal_data armada_cp110_data = {
 	.is_valid = armada_is_valid,
-	.init = armada380_init,
+	.init = armada_cp110_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
 	.temp_mask = 0x3ff,
-- 
cgit v1.2.3


From a9fae794e4c581bbe460106609ce88dec8b00973 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:49 +0200
Subject: thermal: armada: average over samples to avoid glitches

Configure the sample frequency and number of averaged samples.

This is needed for two reasons:
1/ To be bootloader independent.
2/ To prepare the introduction of multi-sensors support by preventing
   inconsistencies when reading temperatures that could be a mean of
   samples took from different sensors.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 31ff57a654ba..05214ebf1093 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -54,7 +54,12 @@
 #define CONTROL0_TSEN_START		BIT(0)
 #define CONTROL0_TSEN_RESET		BIT(1)
 #define CONTROL0_TSEN_ENABLE		BIT(2)
+#define CONTROL0_TSEN_AVG_BYPASS	BIT(6)
+#define CONTROL0_TSEN_OSR_SHIFT		24
+#define CONTROL0_TSEN_OSR_MAX		0x3
 
+#define CONTROL1_TSEN_AVG_SHIFT		0
+#define CONTROL1_TSEN_AVG_MASK		0x7
 #define CONTROL1_EXT_TSEN_SW_RESET	BIT(7)
 #define CONTROL1_EXT_TSEN_HW_RESETn	BIT(8)
 
@@ -194,6 +199,13 @@ static void armada_ap806_init(struct platform_device *pdev,
 	reg = readl_relaxed(priv->control0);
 	reg &= ~CONTROL0_TSEN_RESET;
 	reg |= CONTROL0_TSEN_START | CONTROL0_TSEN_ENABLE;
+
+	/* Sample every ~2ms */
+	reg |= CONTROL0_TSEN_OSR_MAX << CONTROL0_TSEN_OSR_SHIFT;
+
+	/* Enable average (2 samples by default) */
+	reg &= ~CONTROL0_TSEN_AVG_BYPASS;
+
 	writel(reg, priv->control0);
 
 	/* Wait the sensors to be valid or the core will warn the user */
@@ -203,7 +215,20 @@ static void armada_ap806_init(struct platform_device *pdev,
 static void armada_cp110_init(struct platform_device *pdev,
 			      struct armada_thermal_priv *priv)
 {
+	u32 reg;
+
 	armada380_init(pdev, priv);
+
+	/* Sample every ~2ms */
+	reg = readl_relaxed(priv->control0);
+	reg |= CONTROL0_TSEN_OSR_MAX << CONTROL0_TSEN_OSR_SHIFT;
+	writel(reg, priv->control0);
+
+	/* Average the output value over 2^1 = 2 samples */
+	reg = readl_relaxed(priv->control1);
+	reg &= ~CONTROL1_TSEN_AVG_MASK << CONTROL1_TSEN_AVG_SHIFT;
+	reg |= 1 << CONTROL1_TSEN_AVG_SHIFT;
+	writel(reg, priv->control1);
 }
 
 static bool armada_is_valid(struct armada_thermal_priv *priv)
-- 
cgit v1.2.3


From 3d4e51844a4eb3c86e568bdcc9408602b46dc638 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:50 +0200
Subject: thermal: armada: convert driver to syscon register accesses

Until recently, only one register was referenced in MVEBU thermal IP
node. Recent changes added a second entry pointing to another
register right next to it. We cannot know for sure that we will not
have to access other registers. That will be actually the case when
overheat interrupt feature will come, where it will be needed to access
DFX registers in the same area.

This approach is not scalable so instead of adding consinuously memory
areas in the DT (and change the DT bindings, while keeping backward
compatibility), move the thermal node into a wider syscon from which it
will be possible to also configure the thermal interrupt.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 199 +++++++++++++++++++++++++--------------
 1 file changed, 129 insertions(+), 70 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 05214ebf1093..4d1ede40654f 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -24,6 +24,8 @@
 #include <linux/of_device.h>
 #include <linux/thermal.h>
 #include <linux/iopoll.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 /* Thermal Manager Control and Status Register */
 #define PMU_TDC0_SW_RST_MASK		(0x1 << 1)
@@ -39,14 +41,6 @@
 #define A375_READOUT_INVERT		BIT(15)
 #define A375_HW_RESETn			BIT(8)
 
-/* Legacy bindings */
-#define LEGACY_CONTROL_MEM_LEN		0x4
-
-/* Current bindings with the 2 control registers under the same memory area */
-#define LEGACY_CONTROL1_OFFSET		0x0
-#define CONTROL0_OFFSET			0x0
-#define CONTROL1_OFFSET			0x4
-
 /* Errata fields */
 #define CONTROL0_TSEN_TC_TRIM_MASK	0x7
 #define CONTROL0_TSEN_TC_TRIM_VAL	0x3
@@ -70,9 +64,7 @@ struct armada_thermal_data;
 
 /* Marvell EBU Thermal Sensor Dev Structure */
 struct armada_thermal_priv {
-	void __iomem *status;
-	void __iomem *control0;
-	void __iomem *control1;
+	struct regmap *syscon;
 	char zone_name[THERMAL_NAME_LENGTH];
 	struct armada_thermal_data *data;
 };
@@ -96,15 +88,20 @@ struct armada_thermal_data {
 	unsigned int temp_shift;
 	unsigned int temp_mask;
 	u32 is_valid_bit;
-	bool needs_control0;
+
+	/* Syscon access */
+	unsigned int syscon_control0_off;
+	unsigned int syscon_control1_off;
+	unsigned int syscon_status_off;
 };
 
 static void armadaxp_init(struct platform_device *pdev,
 			  struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl_relaxed(priv->control1);
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg |= PMU_TDC0_OTF_CAL_MASK;
 
 	/* Reference calibration value */
@@ -114,29 +111,31 @@ static void armadaxp_init(struct platform_device *pdev,
 	/* Reset the sensor */
 	reg |= PMU_TDC0_SW_RST_MASK;
 
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
 	/* Enable the sensor */
-	reg = readl_relaxed(priv->status);
+	regmap_read(priv->syscon, data->syscon_status_off, &reg);
 	reg &= ~PMU_TM_DISABLE_MASK;
-	writel(reg, priv->status);
+	regmap_write(priv->syscon, data->syscon_status_off, reg);
 }
 
 static void armada370_init(struct platform_device *pdev,
 			   struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl_relaxed(priv->control1);
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg |= PMU_TDC0_OTF_CAL_MASK;
 
 	/* Reference calibration value */
 	reg &= ~PMU_TDC0_REF_CAL_CNT_MASK;
 	reg |= (0xf1 << PMU_TDC0_REF_CAL_CNT_OFFS);
 
+	/* Reset the sensor */
 	reg &= ~PMU_TDC0_START_CAL_MASK;
 
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
 	msleep(10);
 }
@@ -144,18 +143,20 @@ static void armada370_init(struct platform_device *pdev,
 static void armada375_init(struct platform_device *pdev,
 			   struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl(priv->control1);
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg &= ~(A375_UNIT_CONTROL_MASK << A375_UNIT_CONTROL_SHIFT);
 	reg &= ~A375_READOUT_INVERT;
 	reg &= ~A375_HW_RESETn;
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
-	writel(reg, priv->control1);
 	msleep(20);
 
 	reg |= A375_HW_RESETn;
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
+
 	msleep(50);
 }
 
@@ -163,29 +164,29 @@ static void armada_wait_sensor_validity(struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
-	readl_relaxed_poll_timeout(priv->status, reg,
-				   reg & priv->data->is_valid_bit,
-				   STATUS_POLL_PERIOD_US,
-				   STATUS_POLL_TIMEOUT_US);
+	regmap_read_poll_timeout(priv->syscon, priv->data->syscon_status_off,
+				 reg, reg & priv->data->is_valid_bit,
+				 STATUS_POLL_PERIOD_US,
+				 STATUS_POLL_TIMEOUT_US);
 }
 
 static void armada380_init(struct platform_device *pdev,
 			   struct armada_thermal_priv *priv)
 {
-	u32 reg = readl_relaxed(priv->control1);
+	struct armada_thermal_data *data = priv->data;
+	u32 reg;
 
 	/* Disable the HW/SW reset */
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg |= CONTROL1_EXT_TSEN_HW_RESETn;
 	reg &= ~CONTROL1_EXT_TSEN_SW_RESET;
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 
 	/* Set Tsen Tc Trim to correct default value (errata #132698) */
-	if (priv->control0) {
-		reg = readl_relaxed(priv->control0);
-		reg &= ~CONTROL0_TSEN_TC_TRIM_MASK;
-		reg |= CONTROL0_TSEN_TC_TRIM_VAL;
-		writel(reg, priv->control0);
-	}
+	regmap_read(priv->syscon, data->syscon_control0_off, &reg);
+	reg &= ~CONTROL0_TSEN_TC_TRIM_MASK;
+	reg |= CONTROL0_TSEN_TC_TRIM_VAL;
+	regmap_write(priv->syscon, data->syscon_control0_off, reg);
 
 	/* Wait the sensors to be valid or the core will warn the user */
 	armada_wait_sensor_validity(priv);
@@ -194,9 +195,10 @@ static void armada380_init(struct platform_device *pdev,
 static void armada_ap806_init(struct platform_device *pdev,
 			      struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
-	reg = readl_relaxed(priv->control0);
+	regmap_read(priv->syscon, data->syscon_control0_off, &reg);
 	reg &= ~CONTROL0_TSEN_RESET;
 	reg |= CONTROL0_TSEN_START | CONTROL0_TSEN_ENABLE;
 
@@ -206,7 +208,7 @@ static void armada_ap806_init(struct platform_device *pdev,
 	/* Enable average (2 samples by default) */
 	reg &= ~CONTROL0_TSEN_AVG_BYPASS;
 
-	writel(reg, priv->control0);
+	regmap_write(priv->syscon, data->syscon_control0_off, reg);
 
 	/* Wait the sensors to be valid or the core will warn the user */
 	armada_wait_sensor_validity(priv);
@@ -215,25 +217,28 @@ static void armada_ap806_init(struct platform_device *pdev,
 static void armada_cp110_init(struct platform_device *pdev,
 			      struct armada_thermal_priv *priv)
 {
+	struct armada_thermal_data *data = priv->data;
 	u32 reg;
 
 	armada380_init(pdev, priv);
 
 	/* Sample every ~2ms */
-	reg = readl_relaxed(priv->control0);
+	regmap_read(priv->syscon, data->syscon_control0_off, &reg);
 	reg |= CONTROL0_TSEN_OSR_MAX << CONTROL0_TSEN_OSR_SHIFT;
-	writel(reg, priv->control0);
+	regmap_write(priv->syscon, data->syscon_control0_off, reg);
 
 	/* Average the output value over 2^1 = 2 samples */
-	reg = readl_relaxed(priv->control1);
+	regmap_read(priv->syscon, data->syscon_control1_off, &reg);
 	reg &= ~CONTROL1_TSEN_AVG_MASK << CONTROL1_TSEN_AVG_SHIFT;
 	reg |= 1 << CONTROL1_TSEN_AVG_SHIFT;
-	writel(reg, priv->control1);
+	regmap_write(priv->syscon, data->syscon_control1_off, reg);
 }
 
 static bool armada_is_valid(struct armada_thermal_priv *priv)
 {
-	u32 reg = readl_relaxed(priv->status);
+	u32 reg;
+
+	regmap_read(priv->syscon, priv->data->syscon_status_off, &reg);
 
 	return reg & priv->data->is_valid_bit;
 }
@@ -252,7 +257,7 @@ static int armada_get_temp(struct thermal_zone_device *thermal,
 		return -EIO;
 	}
 
-	reg = readl_relaxed(priv->status);
+	regmap_read(priv->syscon, priv->data->syscon_status_off, &reg);
 	reg = (reg >> priv->data->temp_shift) & priv->data->temp_mask;
 	if (priv->data->signed_sample)
 		/* The most significant bit is the sign bit */
@@ -284,6 +289,8 @@ static const struct armada_thermal_data armadaxp_data = {
 	.coef_b = 3153000000ULL,
 	.coef_m = 10000000ULL,
 	.coef_div = 13825,
+	.syscon_status_off = 0xb0,
+	.syscon_control1_off = 0xd0,
 };
 
 static const struct armada_thermal_data armada370_data = {
@@ -295,6 +302,8 @@ static const struct armada_thermal_data armada370_data = {
 	.coef_b = 3153000000ULL,
 	.coef_m = 10000000ULL,
 	.coef_div = 13825,
+	.syscon_status_off = 0x0,
+	.syscon_control1_off = 0x4,
 };
 
 static const struct armada_thermal_data armada375_data = {
@@ -306,7 +315,9 @@ static const struct armada_thermal_data armada375_data = {
 	.coef_b = 3171900000ULL,
 	.coef_m = 10000000ULL,
 	.coef_div = 13616,
-	.needs_control0 = true,
+	.syscon_status_off = 0x78,
+	.syscon_control0_off = 0x7c,
+	.syscon_control1_off = 0x80,
 };
 
 static const struct armada_thermal_data armada380_data = {
@@ -319,6 +330,9 @@ static const struct armada_thermal_data armada380_data = {
 	.coef_m = 2000096ULL,
 	.coef_div = 4201,
 	.inverted = true,
+	.syscon_control0_off = 0x70,
+	.syscon_control1_off = 0x74,
+	.syscon_status_off = 0x78,
 };
 
 static const struct armada_thermal_data armada_ap806_data = {
@@ -332,7 +346,9 @@ static const struct armada_thermal_data armada_ap806_data = {
 	.coef_div = 1,
 	.inverted = true,
 	.signed_sample = true,
-	.needs_control0 = true,
+	.syscon_control0_off = 0x84,
+	.syscon_control1_off = 0x88,
+	.syscon_status_off = 0x8C,
 };
 
 static const struct armada_thermal_data armada_cp110_data = {
@@ -345,7 +361,9 @@ static const struct armada_thermal_data armada_cp110_data = {
 	.coef_m = 2000096ULL,
 	.coef_div = 4201,
 	.inverted = true,
-	.needs_control0 = true,
+	.syscon_control0_off = 0x70,
+	.syscon_control1_off = 0x74,
+	.syscon_status_off = 0x78,
 };
 
 static const struct of_device_id armada_thermal_id_table[] = {
@@ -379,6 +397,57 @@ static const struct of_device_id armada_thermal_id_table[] = {
 };
 MODULE_DEVICE_TABLE(of, armada_thermal_id_table);
 
+static const struct regmap_config armada_thermal_regmap_config = {
+	.reg_bits = 32,
+	.reg_stride = 4,
+	.val_bits = 32,
+	.fast_io = true,
+};
+
+static int armada_thermal_probe_legacy(struct platform_device *pdev,
+				       struct armada_thermal_priv *priv)
+{
+	struct armada_thermal_data *data = priv->data;
+	struct resource *res;
+	void __iomem *base;
+
+	/* First memory region points towards the status register */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (IS_ERR(res))
+		return PTR_ERR(res);
+
+	/*
+	 * Edit the resource start address and length to map over all the
+	 * registers, instead of pointing at them one by one.
+	 */
+	res->start -= data->syscon_status_off;
+	res->end = res->start + max(data->syscon_status_off,
+				    max(data->syscon_control0_off,
+					data->syscon_control1_off)) +
+		   sizeof(unsigned int) - 1;
+
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	priv->syscon = devm_regmap_init_mmio(&pdev->dev, base,
+					     &armada_thermal_regmap_config);
+	if (IS_ERR(priv->syscon))
+		return PTR_ERR(priv->syscon);
+
+	return 0;
+}
+
+static int armada_thermal_probe_syscon(struct platform_device *pdev,
+				       struct armada_thermal_priv *priv)
+{
+	priv->syscon = syscon_node_to_regmap(pdev->dev.parent->of_node);
+	if (IS_ERR(priv->syscon))
+		return PTR_ERR(priv->syscon);
+
+	return 0;
+}
+
 static void armada_set_sane_name(struct platform_device *pdev,
 				 struct armada_thermal_priv *priv)
 {
@@ -412,11 +481,10 @@ static void armada_set_sane_name(struct platform_device *pdev,
 
 static int armada_thermal_probe(struct platform_device *pdev)
 {
-	void __iomem *control = NULL;
 	struct thermal_zone_device *thermal;
 	const struct of_device_id *match;
 	struct armada_thermal_priv *priv;
-	struct resource *res;
+	int ret;
 
 	match = of_match_device(armada_thermal_id_table, &pdev->dev);
 	if (!match)
@@ -426,16 +494,6 @@ static int armada_thermal_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	priv->status = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(priv->status))
-		return PTR_ERR(priv->status);
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	control = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(control))
-		return PTR_ERR(control);
-
 	priv->data = (struct armada_thermal_data *)match->data;
 
 	/* Ensure device name is correct for the thermal core */
@@ -443,22 +501,23 @@ static int armada_thermal_probe(struct platform_device *pdev)
 
 	/*
 	 * Legacy DT bindings only described "control1" register (also referred
-	 * as "control MSB" on old documentation). New bindings cover
+	 * as "control MSB" on old documentation). Then, bindings moved to cover
 	 * "control0/control LSB" and "control1/control MSB" registers within
-	 * the same resource, which is then of size 8 instead of 4.
+	 * the same resource, which was then of size 8 instead of 4.
+	 *
+	 * The logic of defining sporadic registers is broken. For instance, it
+	 * blocked the addition of the overheat interrupt feature that needed
+	 * another resource somewhere else in the same memory area. One solution
+	 * is to define an overall system controller and put the thermal node
+	 * into it, which requires the use of regmaps across all the driver.
 	 */
-	if (resource_size(res) == LEGACY_CONTROL_MEM_LEN) {
-		/* ->control0 unavailable in this configuration */
-		if (priv->data->needs_control0) {
-			dev_err(&pdev->dev, "No access to control0 register\n");
-			return -EINVAL;
-		}
-
-		priv->control1 = control + LEGACY_CONTROL1_OFFSET;
-	} else {
-		priv->control0 = control + CONTROL0_OFFSET;
-		priv->control1 = control + CONTROL1_OFFSET;
-	}
+	if (IS_ERR(syscon_node_to_regmap(pdev->dev.parent->of_node)))
+		ret = armada_thermal_probe_legacy(pdev, priv);
+	else
+		ret = armada_thermal_probe_syscon(pdev, priv);
+
+	if (ret)
+		return ret;
 
 	priv->data->init(pdev, priv);
 
-- 
cgit v1.2.3


From c9899c183921f919e10fe821be7de9fea876ba65 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:51 +0200
Subject: thermal: armada: use the resource managed registration helper
 alternative

Current use of thermal_zone_device_register() triggers a warning at boot
and should be replaced by devm_thermal_zone_of_sensor_register(). This
allows better handling of multiple thermal zones for later multi-sensors
support.

Also change the driver data to embed a new structure to make the
difference between legacy data (which needs to be cleaned) and
syscon-related data.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 122 ++++++++++++++++++++++++++++++++-------
 1 file changed, 100 insertions(+), 22 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 4d1ede40654f..414329e94f8c 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -64,6 +64,7 @@ struct armada_thermal_data;
 
 /* Marvell EBU Thermal Sensor Dev Structure */
 struct armada_thermal_priv {
+	struct device *dev;
 	struct regmap *syscon;
 	char zone_name[THERMAL_NAME_LENGTH];
 	struct armada_thermal_data *data;
@@ -95,6 +96,26 @@ struct armada_thermal_data {
 	unsigned int syscon_status_off;
 };
 
+struct armada_drvdata {
+	enum drvtype {
+		LEGACY,
+		SYSCON
+	} type;
+	union {
+		struct armada_thermal_priv *priv;
+		struct thermal_zone_device *tz;
+	} data;
+};
+
+/*
+ * struct armada_thermal_sensor - hold the information of one thermal sensor
+ * @thermal: pointer to the local private structure
+ * @tzd: pointer to the thermal zone device
+ */
+struct armada_thermal_sensor {
+	struct armada_thermal_priv *priv;
+};
+
 static void armadaxp_init(struct platform_device *pdev,
 			  struct armada_thermal_priv *priv)
 {
@@ -243,16 +264,14 @@ static bool armada_is_valid(struct armada_thermal_priv *priv)
 	return reg & priv->data->is_valid_bit;
 }
 
-static int armada_get_temp(struct thermal_zone_device *thermal,
-			   int *temp)
+static int armada_read_sensor(struct armada_thermal_priv *priv, int *temp)
 {
-	struct armada_thermal_priv *priv = thermal->devdata;
 	u32 reg, div;
 	s64 sample, b, m;
 
 	/* Valid check */
 	if (priv->data->is_valid && !priv->data->is_valid(priv)) {
-		dev_err(&thermal->device,
+		dev_err(priv->dev,
 			"Temperature sensor reading not valid\n");
 		return -EIO;
 	}
@@ -278,7 +297,32 @@ static int armada_get_temp(struct thermal_zone_device *thermal,
 	return 0;
 }
 
-static struct thermal_zone_device_ops ops = {
+static int armada_get_temp_legacy(struct thermal_zone_device *thermal,
+				  int *temp)
+{
+	struct armada_thermal_priv *priv = thermal->devdata;
+	int ret;
+
+	/* Do the actual reading */
+	ret = armada_read_sensor(priv, temp);
+
+	return ret;
+}
+
+static struct thermal_zone_device_ops legacy_ops = {
+	.get_temp = armada_get_temp_legacy,
+};
+
+static int armada_get_temp(void *_sensor, int *temp)
+{
+	struct armada_thermal_sensor *sensor = _sensor;
+	struct armada_thermal_priv *priv = sensor->priv;
+
+	/* Do the actual reading */
+	return armada_read_sensor(priv, temp);
+}
+
+static struct thermal_zone_of_device_ops of_ops = {
 	.get_temp = armada_get_temp,
 };
 
@@ -481,7 +525,9 @@ static void armada_set_sane_name(struct platform_device *pdev,
 
 static int armada_thermal_probe(struct platform_device *pdev)
 {
-	struct thermal_zone_device *thermal;
+	struct thermal_zone_device *tz;
+	struct armada_thermal_sensor *sensors;
+	struct armada_drvdata *drvdata;
 	const struct of_device_id *match;
 	struct armada_thermal_priv *priv;
 	int ret;
@@ -494,10 +540,12 @@ static int armada_thermal_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	priv->data = (struct armada_thermal_data *)match->data;
+	drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
 
-	/* Ensure device name is correct for the thermal core */
-	armada_set_sane_name(pdev, priv);
+	priv->dev = &pdev->dev;
+	priv->data = (struct armada_thermal_data *)match->data;
 
 	/*
 	 * Legacy DT bindings only described "control1" register (also referred
@@ -511,35 +559,65 @@ static int armada_thermal_probe(struct platform_device *pdev)
 	 * is to define an overall system controller and put the thermal node
 	 * into it, which requires the use of regmaps across all the driver.
 	 */
-	if (IS_ERR(syscon_node_to_regmap(pdev->dev.parent->of_node)))
+	if (IS_ERR(syscon_node_to_regmap(pdev->dev.parent->of_node))) {
+		/* Ensure device name is correct for the thermal core */
+		armada_set_sane_name(pdev, priv);
+
 		ret = armada_thermal_probe_legacy(pdev, priv);
-	else
-		ret = armada_thermal_probe_syscon(pdev, priv);
+		if (ret)
+			return ret;
 
+		priv->data->init(pdev, priv);
+
+		tz = thermal_zone_device_register(priv->zone_name, 0, 0, priv,
+						  &legacy_ops, NULL, 0, 0);
+		if (IS_ERR(tz)) {
+			dev_err(&pdev->dev,
+				"Failed to register thermal zone device\n");
+			return PTR_ERR(tz);
+		}
+
+		drvdata->type = LEGACY;
+		drvdata->data.tz = tz;
+		platform_set_drvdata(pdev, drvdata);
+
+		return 0;
+	}
+
+	ret = armada_thermal_probe_syscon(pdev, priv);
 	if (ret)
 		return ret;
 
 	priv->data->init(pdev, priv);
+	drvdata->type = SYSCON;
+	drvdata->data.priv = priv;
+	platform_set_drvdata(pdev, drvdata);
 
-	thermal = thermal_zone_device_register(priv->zone_name, 0, 0, priv,
-					       &ops, NULL, 0, 0);
-	if (IS_ERR(thermal)) {
+	sensors = devm_kzalloc(&pdev->dev, sizeof(struct armada_thermal_sensor),
+			       GFP_KERNEL);
+	if (!sensors)
+		return -ENOMEM;
+
+	sensors->priv = priv;
+
+	tz = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, sensors,
+						  &of_ops);
+	if (IS_ERR(tz)) {
 		dev_err(&pdev->dev,
-			"Failed to register thermal zone device\n");
-		return PTR_ERR(thermal);
+			"Failed to register thermal sensor (err: %ld)\n",
+			PTR_ERR(tz));
+		return PTR_ERR(tz);
 	}
 
-	platform_set_drvdata(pdev, thermal);
-
 	return 0;
 }
 
 static int armada_thermal_exit(struct platform_device *pdev)
 {
-	struct thermal_zone_device *armada_thermal =
-		platform_get_drvdata(pdev);
+	struct armada_drvdata *drvdata = platform_get_drvdata(pdev);
 
-	thermal_zone_device_unregister(armada_thermal);
+	if (drvdata->type == LEGACY)
+		thermal_zone_device_unregister(drvdata->data.tz);
 
 	return 0;
 }
-- 
cgit v1.2.3


From f7c2068a1728c1b2aed9416b071a3e2f8f887786 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:52 +0200
Subject: thermal: armada: add multi-channel sensors support

MVEBU thermal IP supports multiple channels. Each channel may have
several sensors but for now each channel is wired to only one thermal
sensor. The first channel always points to the so called internal
sensor, within the thermal IP. There is usually one more channel (with
one sensor each time) per CPU. The code has been written to support
possible evolutions of the ap806 IP that would embed more CPUs and thus
more channels to select. Each channel should be referenced in the device
tree as an independent thermal zone.

Add the possibility to read each of these sensors through sysfs by
registering all the sensors (translated in "thermal_zone"). Also add a
mutex on these accesses to avoid read conflicts (only one channel/sensor
may be selected and read at a time).

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 135 +++++++++++++++++++++++++++++++++------
 1 file changed, 114 insertions(+), 21 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 414329e94f8c..e20d4f954f21 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -49,8 +49,13 @@
 #define CONTROL0_TSEN_RESET		BIT(1)
 #define CONTROL0_TSEN_ENABLE		BIT(2)
 #define CONTROL0_TSEN_AVG_BYPASS	BIT(6)
+#define CONTROL0_TSEN_CHAN_SHIFT	13
+#define CONTROL0_TSEN_CHAN_MASK		0xF
 #define CONTROL0_TSEN_OSR_SHIFT		24
 #define CONTROL0_TSEN_OSR_MAX		0x3
+#define CONTROL0_TSEN_MODE_SHIFT	30
+#define CONTROL0_TSEN_MODE_EXTERNAL	0x2
+#define CONTROL0_TSEN_MODE_MASK		0x3
 
 #define CONTROL1_TSEN_AVG_SHIFT		0
 #define CONTROL1_TSEN_AVG_MASK		0x7
@@ -67,7 +72,10 @@ struct armada_thermal_priv {
 	struct device *dev;
 	struct regmap *syscon;
 	char zone_name[THERMAL_NAME_LENGTH];
+	/* serialize temperature reads/updates */
+	struct mutex update_lock;
 	struct armada_thermal_data *data;
+	int current_channel;
 };
 
 struct armada_thermal_data {
@@ -94,6 +102,9 @@ struct armada_thermal_data {
 	unsigned int syscon_control0_off;
 	unsigned int syscon_control1_off;
 	unsigned int syscon_status_off;
+
+	/* One sensor is in the thermal IC, the others are in the CPUs if any */
+	unsigned int cpu_nr;
 };
 
 struct armada_drvdata {
@@ -111,9 +122,11 @@ struct armada_drvdata {
  * struct armada_thermal_sensor - hold the information of one thermal sensor
  * @thermal: pointer to the local private structure
  * @tzd: pointer to the thermal zone device
+ * @id: identifier of the thermal sensor
  */
 struct armada_thermal_sensor {
 	struct armada_thermal_priv *priv;
+	int id;
 };
 
 static void armadaxp_init(struct platform_device *pdev,
@@ -181,14 +194,15 @@ static void armada375_init(struct platform_device *pdev,
 	msleep(50);
 }
 
-static void armada_wait_sensor_validity(struct armada_thermal_priv *priv)
+static int armada_wait_sensor_validity(struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
-	regmap_read_poll_timeout(priv->syscon, priv->data->syscon_status_off,
-				 reg, reg & priv->data->is_valid_bit,
-				 STATUS_POLL_PERIOD_US,
-				 STATUS_POLL_TIMEOUT_US);
+	return regmap_read_poll_timeout(priv->syscon,
+					priv->data->syscon_status_off, reg,
+					reg & priv->data->is_valid_bit,
+					STATUS_POLL_PERIOD_US,
+					STATUS_POLL_TIMEOUT_US);
 }
 
 static void armada380_init(struct platform_device *pdev,
@@ -264,6 +278,58 @@ static bool armada_is_valid(struct armada_thermal_priv *priv)
 	return reg & priv->data->is_valid_bit;
 }
 
+/* There is currently no board with more than one sensor per channel */
+static int armada_select_channel(struct armada_thermal_priv *priv, int channel)
+{
+	struct armada_thermal_data *data = priv->data;
+	u32 ctrl0;
+
+	if (channel < 0 || channel > priv->data->cpu_nr)
+		return -EINVAL;
+
+	if (priv->current_channel == channel)
+		return 0;
+
+	/* Stop the measurements */
+	regmap_read(priv->syscon, data->syscon_control0_off, &ctrl0);
+	ctrl0 &= ~CONTROL0_TSEN_START;
+	regmap_write(priv->syscon, data->syscon_control0_off, ctrl0);
+
+	/* Reset the mode, internal sensor will be automatically selected */
+	ctrl0 &= ~(CONTROL0_TSEN_MODE_MASK << CONTROL0_TSEN_MODE_SHIFT);
+
+	/* Other channels are external and should be selected accordingly */
+	if (channel) {
+		/* Change the mode to external */
+		ctrl0 |= CONTROL0_TSEN_MODE_EXTERNAL <<
+			 CONTROL0_TSEN_MODE_SHIFT;
+		/* Select the sensor */
+		ctrl0 &= ~(CONTROL0_TSEN_CHAN_MASK << CONTROL0_TSEN_CHAN_SHIFT);
+		ctrl0 |= (channel - 1) << CONTROL0_TSEN_CHAN_SHIFT;
+	}
+
+	/* Actually set the mode/channel */
+	regmap_write(priv->syscon, data->syscon_control0_off, ctrl0);
+	priv->current_channel = channel;
+
+	/* Re-start the measurements */
+	ctrl0 |= CONTROL0_TSEN_START;
+	regmap_write(priv->syscon, data->syscon_control0_off, ctrl0);
+
+	/*
+	 * The IP has a latency of ~15ms, so after updating the selected source,
+	 * we must absolutely wait for the sensor validity bit to ensure we read
+	 * actual data.
+	 */
+	if (armada_wait_sensor_validity(priv)) {
+		dev_err(priv->dev,
+			"Temperature sensor reading not valid\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int armada_read_sensor(struct armada_thermal_priv *priv, int *temp)
 {
 	u32 reg, div;
@@ -317,9 +383,22 @@ static int armada_get_temp(void *_sensor, int *temp)
 {
 	struct armada_thermal_sensor *sensor = _sensor;
 	struct armada_thermal_priv *priv = sensor->priv;
+	int ret;
+
+	mutex_lock(&priv->update_lock);
+
+	/* Select the desired channel */
+	ret = armada_select_channel(priv, sensor->id);
+	if (ret)
+		goto unlock_mutex;
 
 	/* Do the actual reading */
-	return armada_read_sensor(priv, temp);
+	ret = armada_read_sensor(priv, temp);
+
+unlock_mutex:
+	mutex_unlock(&priv->update_lock);
+
+	return ret;
 }
 
 static struct thermal_zone_of_device_ops of_ops = {
@@ -393,6 +472,7 @@ static const struct armada_thermal_data armada_ap806_data = {
 	.syscon_control0_off = 0x84,
 	.syscon_control1_off = 0x88,
 	.syscon_status_off = 0x8C,
+	.cpu_nr = 4,
 };
 
 static const struct armada_thermal_data armada_cp110_data = {
@@ -526,10 +606,11 @@ static void armada_set_sane_name(struct platform_device *pdev,
 static int armada_thermal_probe(struct platform_device *pdev)
 {
 	struct thermal_zone_device *tz;
-	struct armada_thermal_sensor *sensors;
+	struct armada_thermal_sensor *sensor;
 	struct armada_drvdata *drvdata;
 	const struct of_device_id *match;
 	struct armada_thermal_priv *priv;
+	int sensor_id;
 	int ret;
 
 	match = of_match_device(armada_thermal_id_table, &pdev->dev);
@@ -547,6 +628,8 @@ static int armada_thermal_probe(struct platform_device *pdev)
 	priv->dev = &pdev->dev;
 	priv->data = (struct armada_thermal_data *)match->data;
 
+	mutex_init(&priv->update_lock);
+
 	/*
 	 * Legacy DT bindings only described "control1" register (also referred
 	 * as "control MSB" on old documentation). Then, bindings moved to cover
@@ -588,25 +671,35 @@ static int armada_thermal_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	priv->current_channel = -1;
 	priv->data->init(pdev, priv);
 	drvdata->type = SYSCON;
 	drvdata->data.priv = priv;
 	platform_set_drvdata(pdev, drvdata);
 
-	sensors = devm_kzalloc(&pdev->dev, sizeof(struct armada_thermal_sensor),
-			       GFP_KERNEL);
-	if (!sensors)
-		return -ENOMEM;
-
-	sensors->priv = priv;
-
-	tz = devm_thermal_zone_of_sensor_register(&pdev->dev, 0, sensors,
-						  &of_ops);
-	if (IS_ERR(tz)) {
-		dev_err(&pdev->dev,
-			"Failed to register thermal sensor (err: %ld)\n",
-			PTR_ERR(tz));
-		return PTR_ERR(tz);
+	/*
+	 * There is one channel for the IC and one per CPU (if any), each
+	 * channel has one sensor.
+	 */
+	for (sensor_id = 0; sensor_id <= priv->data->cpu_nr; sensor_id++) {
+		sensor = devm_kzalloc(&pdev->dev,
+				      sizeof(struct armada_thermal_sensor),
+				      GFP_KERNEL);
+		if (!sensor)
+			return -ENOMEM;
+
+		/* Register the sensor */
+		sensor->priv = priv;
+		sensor->id = sensor_id;
+		tz = devm_thermal_zone_of_sensor_register(&pdev->dev,
+							  sensor->id, sensor,
+							  &of_ops);
+		if (IS_ERR(tz)) {
+			dev_info(&pdev->dev, "Thermal sensor %d unavailable\n",
+				 sensor_id);
+			devm_kfree(&pdev->dev, sensor);
+			continue;
+		}
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 00707e4c9618949d492f685c324326f39f08ea9c Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:53 +0200
Subject: thermal: armada: remove sensors validity from the IP initialization

When using new bindings with multiple sensors, sensor validity is
checked twice because sensor selection also checks for the validity.

Remove the redundant call from the IP initialization helper and move it
to the legacy probe section where it is still needed.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index e20d4f954f21..1f6bc317748d 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -222,9 +222,6 @@ static void armada380_init(struct platform_device *pdev,
 	reg &= ~CONTROL0_TSEN_TC_TRIM_MASK;
 	reg |= CONTROL0_TSEN_TC_TRIM_VAL;
 	regmap_write(priv->syscon, data->syscon_control0_off, reg);
-
-	/* Wait the sensors to be valid or the core will warn the user */
-	armada_wait_sensor_validity(priv);
 }
 
 static void armada_ap806_init(struct platform_device *pdev,
@@ -244,9 +241,6 @@ static void armada_ap806_init(struct platform_device *pdev,
 	reg &= ~CONTROL0_TSEN_AVG_BYPASS;
 
 	regmap_write(priv->syscon, data->syscon_control0_off, reg);
-
-	/* Wait the sensors to be valid or the core will warn the user */
-	armada_wait_sensor_validity(priv);
 }
 
 static void armada_cp110_init(struct platform_device *pdev,
@@ -652,6 +646,9 @@ static int armada_thermal_probe(struct platform_device *pdev)
 
 		priv->data->init(pdev, priv);
 
+		/* Wait the sensors to be valid */
+		armada_wait_sensor_validity(priv);
+
 		tz = thermal_zone_device_register(priv->zone_name, 0, 0, priv,
 						  &legacy_ops, NULL, 0, 0);
 		if (IS_ERR(tz)) {
-- 
cgit v1.2.3


From 68b14828ca102630e721d10b2e5dedc9c9b38095 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:54 +0200
Subject: thermal: armada: move validity check out of the read function

Sensor selection when using multiple sensors already checks for the
sensor validity. Move it to the legacy ->get_temp() hook, where it is
still needed.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 1f6bc317748d..53e757a28506 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -329,13 +329,6 @@ static int armada_read_sensor(struct armada_thermal_priv *priv, int *temp)
 	u32 reg, div;
 	s64 sample, b, m;
 
-	/* Valid check */
-	if (priv->data->is_valid && !priv->data->is_valid(priv)) {
-		dev_err(priv->dev,
-			"Temperature sensor reading not valid\n");
-		return -EIO;
-	}
-
 	regmap_read(priv->syscon, priv->data->syscon_status_off, &reg);
 	reg = (reg >> priv->data->temp_shift) & priv->data->temp_mask;
 	if (priv->data->signed_sample)
@@ -363,6 +356,13 @@ static int armada_get_temp_legacy(struct thermal_zone_device *thermal,
 	struct armada_thermal_priv *priv = thermal->devdata;
 	int ret;
 
+	/* Valid check */
+	if (priv->data->is_valid && !priv->data->is_valid(priv)) {
+		dev_err(priv->dev,
+			"Temperature sensor reading not valid\n");
+		return -EIO;
+	}
+
 	/* Do the actual reading */
 	ret = armada_read_sensor(priv, temp);
 
-- 
cgit v1.2.3


From 8c0e64ac4075b7ca870098ed2ad6089868f5fa7b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:55 +0200
Subject: thermal: armada: get rid of the ->is_valid() pointer

The implementation of armada_is_valid() is very simple and is the same
across all the versions of the IP since the ->is_valid_bit has been
introduced. Simplify the structure by getting rid of the function
pointer and calling directly the function.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 53e757a28506..4164a5a4e480 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -83,9 +83,6 @@ struct armada_thermal_data {
 	void (*init)(struct platform_device *pdev,
 		     struct armada_thermal_priv *priv);
 
-	/* Test for a valid sensor value (optional) */
-	bool (*is_valid)(struct armada_thermal_priv *);
-
 	/* Formula coeficients: temp = (b - m * reg) / div */
 	s64 coef_b;
 	s64 coef_m;
@@ -267,6 +264,9 @@ static bool armada_is_valid(struct armada_thermal_priv *priv)
 {
 	u32 reg;
 
+	if (!priv->data->is_valid_bit)
+		return true;
+
 	regmap_read(priv->syscon, priv->data->syscon_status_off, &reg);
 
 	return reg & priv->data->is_valid_bit;
@@ -357,7 +357,7 @@ static int armada_get_temp_legacy(struct thermal_zone_device *thermal,
 	int ret;
 
 	/* Valid check */
-	if (priv->data->is_valid && !priv->data->is_valid(priv)) {
+	if (armada_is_valid(priv)) {
 		dev_err(priv->dev,
 			"Temperature sensor reading not valid\n");
 		return -EIO;
@@ -411,7 +411,6 @@ static const struct armada_thermal_data armadaxp_data = {
 };
 
 static const struct armada_thermal_data armada370_data = {
-	.is_valid = armada_is_valid,
 	.init = armada370_init,
 	.is_valid_bit = BIT(9),
 	.temp_shift = 10,
@@ -424,7 +423,6 @@ static const struct armada_thermal_data armada370_data = {
 };
 
 static const struct armada_thermal_data armada375_data = {
-	.is_valid = armada_is_valid,
 	.init = armada375_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
@@ -438,7 +436,6 @@ static const struct armada_thermal_data armada375_data = {
 };
 
 static const struct armada_thermal_data armada380_data = {
-	.is_valid = armada_is_valid,
 	.init = armada380_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
@@ -453,7 +450,6 @@ static const struct armada_thermal_data armada380_data = {
 };
 
 static const struct armada_thermal_data armada_ap806_data = {
-	.is_valid = armada_is_valid,
 	.init = armada_ap806_init,
 	.is_valid_bit = BIT(16),
 	.temp_shift = 0,
@@ -470,7 +466,6 @@ static const struct armada_thermal_data armada_ap806_data = {
 };
 
 static const struct armada_thermal_data armada_cp110_data = {
-	.is_valid = armada_is_valid,
 	.init = armada_cp110_init,
 	.is_valid_bit = BIT(10),
 	.temp_shift = 0,
-- 
cgit v1.2.3


From 4aa5496980e4c099ede8815d0672809efd8e226a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:56 +0200
Subject: dt-bindings: cp110: rename cp110 syscon file

There is no need to give numbers to system controllers inside the
documentation as the syscons use the same compatibles. Furthermore, this
approach does not scale very well and would force the creation of a new
file each time a new syscon is added in the device tree.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../arm/marvell/cp110-system-controller.txt        | 188 +++++++++++++++++++++
 .../arm/marvell/cp110-system-controller0.txt       | 188 ---------------------
 2 files changed, 188 insertions(+), 188 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
 delete mode 100644 Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt

diff --git a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
new file mode 100644
index 000000000000..29cdbae6c5ac
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
@@ -0,0 +1,188 @@
+Marvell Armada CP110 System Controller 0
+========================================
+
+The CP110 is one of the two core HW blocks of the Marvell Armada 7K/8K
+SoCs. It contains two sets of system control registers, System
+Controller 0 and System Controller 1. This Device Tree binding allows
+to describe the first system controller, which provides registers to
+configure various aspects of the SoC.
+
+For the top level node:
+ - compatible: must be: "syscon", "simple-mfd";
+ - reg: register area of the CP110 system controller 0
+
+Clocks:
+-------
+
+The Device Tree node representing this System Controller 0 provides a
+number of clocks:
+
+ - a set of core clocks
+ - a set of gatable clocks
+
+Those clocks can be referenced by other Device Tree nodes using two
+cells:
+ - The first cell must be 0 or 1. 0 for the core clocks and 1 for the
+   gatable clocks.
+ - The second cell identifies the particular core clock or gatable
+   clocks.
+
+The following clocks are available:
+ - Core clocks
+   - 0 0	APLL
+   - 0 1	PPv2 core
+   - 0 2	EIP
+   - 0 3	Core
+   - 0 4	NAND core
+   - 0 5	SDIO core
+ - Gatable clocks
+   - 1 0	Audio
+   - 1 1	Comm Unit
+   - 1 2	NAND
+   - 1 3	PPv2
+   - 1 4	SDIO
+   - 1 5	MG Domain
+   - 1 6	MG Core
+   - 1 7	XOR1
+   - 1 8	XOR0
+   - 1 9	GOP DP
+   - 1 11	PCIe x1 0
+   - 1 12	PCIe x1 1
+   - 1 13	PCIe x4
+   - 1 14	PCIe / XOR
+   - 1 15	SATA
+   - 1 16	SATA USB
+   - 1 17	Main
+   - 1 18	SD/MMC/GOP
+   - 1 21	Slow IO (SPI, NOR, BootROM, I2C, UART)
+   - 1 22	USB3H0
+   - 1 23	USB3H1
+   - 1 24	USB3 Device
+   - 1 25	EIP150
+   - 1 26	EIP197
+
+Required properties:
+
+ - compatible: must be:
+     "marvell,cp110-clock"
+ - #clock-cells: must be set to 2
+
+Pinctrl:
+--------
+
+For common binding part and usage, refer to the file
+Documentation/devicetree/bindings/pinctrl/marvell,mvebu-pinctrl.txt.
+
+Required properties:
+
+- compatible: "marvell,armada-7k-pinctrl",
+  "marvell,armada-8k-cpm-pinctrl" or "marvell,armada-8k-cps-pinctrl"
+  depending on the specific variant of the SoC being used.
+
+Available mpp pins/groups and functions:
+Note: brackets (x) are not part of the mpp name for marvell,function and given
+only for more detailed description in this document.
+
+name	pins	functions
+================================================================================
+mpp0	0	gpio, dev(ale1), au(i2smclk), ge0(rxd3), tdm(pclk), ptp(pulse), mss_i2c(sda), uart0(rxd), sata0(present_act), ge(mdio)
+mpp1	1	gpio, dev(ale0), au(i2sdo_spdifo), ge0(rxd2), tdm(drx), ptp(clk), mss_i2c(sck), uart0(txd), sata1(present_act), ge(mdc)
+mpp2	2	gpio, dev(ad15), au(i2sextclk), ge0(rxd1), tdm(dtx), mss_uart(rxd), ptp(pclk_out), i2c1(sck), uart1(rxd), sata0(present_act), xg(mdc)
+mpp3	3	gpio, dev(ad14), au(i2slrclk), ge0(rxd0), tdm(fsync), mss_uart(txd), pcie(rstoutn), i2c1(sda), uart1(txd), sata1(present_act), xg(mdio)
+mpp4	4	gpio, dev(ad13), au(i2sbclk), ge0(rxctl), tdm(rstn), mss_uart(rxd), uart1(cts), pcie0(clkreq), uart3(rxd), ge(mdc)
+mpp5	5	gpio, dev(ad12), au(i2sdi), ge0(rxclk), tdm(intn), mss_uart(txd), uart1(rts), pcie1(clkreq), uart3(txd), ge(mdio)
+mpp6	6	gpio, dev(ad11), ge0(txd3), spi0(csn2), au(i2sextclk), sata1(present_act), pcie2(clkreq), uart0(rxd), ptp(pulse)
+mpp7	7	gpio, dev(ad10), ge0(txd2), spi0(csn1), spi1(csn1), sata0(present_act), led(data), uart0(txd), ptp(clk)
+mpp8	8	gpio, dev(ad9), ge0(txd1), spi0(csn0), spi1(csn0), uart0(cts), led(stb), uart2(rxd), ptp(pclk_out), synce1(clk)
+mpp9	9	gpio, dev(ad8), ge0(txd0), spi0(mosi), spi1(mosi), pcie(rstoutn), synce2(clk)
+mpp10	10	gpio, dev(readyn), ge0(txctl), spi0(miso), spi1(miso), uart0(cts), sata1(present_act)
+mpp11	11	gpio, dev(wen1), ge0(txclkout), spi0(clk), spi1(clk), uart0(rts), led(clk), uart2(txd), sata0(present_act)
+mpp12	12	gpio, dev(clk_out), nf(rbn1), spi1(csn1), ge0(rxclk)
+mpp13	13	gpio, dev(burstn), nf(rbn0), spi1(miso), ge0(rxctl), mss_spi(miso)
+mpp14	14	gpio, dev(bootcsn), dev(csn0), spi1(csn0), spi0(csn3), au(i2sextclk), spi0(miso), sata0(present_act), mss_spi(csn)
+mpp15	15	gpio, dev(ad7), spi1(mosi), spi0(mosi), mss_spi(mosi), ptp(pulse_cp2cp)
+mpp16	16	gpio, dev(ad6), spi1(clk), mss_spi(clk)
+mpp17	17	gpio, dev(ad5), ge0(txd3)
+mpp18	18	gpio, dev(ad4), ge0(txd2), ptp(clk_cp2cp)
+mpp19	19	gpio, dev(ad3), ge0(txd1), wakeup(out_cp2cp)
+mpp20	20	gpio, dev(ad2), ge0(txd0)
+mpp21	21	gpio, dev(ad1), ge0(txctl), sei(in_cp2cp)
+mpp22	22	gpio, dev(ad0), ge0(txclkout), wakeup(in_cp2cp)
+mpp23	23	gpio, dev(a1), au(i2smclk), link(rd_in_cp2cp)
+mpp24	24	gpio, dev(a0), au(i2slrclk)
+mpp25	25	gpio, dev(oen), au(i2sdo_spdifo)
+mpp26	26	gpio, dev(wen0), au(i2sbclk)
+mpp27	27	gpio, dev(csn0), spi1(miso), mss_gpio4, ge0(rxd3), spi0(csn4), ge(mdio), sata0(present_act), uart0(rts), rei(in_cp2cp)
+mpp28	28	gpio, dev(csn1), spi1(csn0), mss_gpio5, ge0(rxd2), spi0(csn5), pcie2(clkreq), ptp(pulse), ge(mdc), sata1(present_act), uart0(cts), led(data)
+mpp29	29	gpio, dev(csn2), spi1(mosi), mss_gpio6, ge0(rxd1), spi0(csn6), pcie1(clkreq), ptp(clk), mss_i2c(sda), sata0(present_act), uart0(rxd), led(stb)
+mpp30	30	gpio, dev(csn3), spi1(clk), mss_gpio7, ge0(rxd0), spi0(csn7), pcie0(clkreq), ptp(pclk_out), mss_i2c(sck), sata1(present_act), uart0(txd), led(clk)
+mpp31	31	gpio, dev(a2), mss_gpio4, pcie(rstoutn), ge(mdc)
+mpp32	32	gpio, mii(col), mii(txerr), mss_spi(miso), tdm(drx), au(i2sextclk), au(i2sdi), ge(mdio), sdio(v18_en), pcie1(clkreq), mss_gpio0
+mpp33	33	gpio, mii(txclk), sdio(pwr10), mss_spi(csn), tdm(fsync), au(i2smclk), sdio(bus_pwr), xg(mdio), pcie2(clkreq), mss_gpio1
+mpp34	34	gpio, mii(rxerr), sdio(pwr11), mss_spi(mosi), tdm(dtx), au(i2slrclk), sdio(wr_protect), ge(mdc), pcie0(clkreq), mss_gpio2
+mpp35	35	gpio, sata1(present_act), i2c1(sda), mss_spi(clk), tdm(pclk), au(i2sdo_spdifo), sdio(card_detect), xg(mdio), ge(mdio), pcie(rstoutn), mss_gpio3
+mpp36	36	gpio, synce2(clk), i2c1(sck), ptp(clk), synce1(clk), au(i2sbclk), sata0(present_act), xg(mdc), ge(mdc), pcie2(clkreq), mss_gpio5
+mpp37	37	gpio, uart2(rxd), i2c0(sck), ptp(pclk_out), tdm(intn), mss_i2c(sck), sata1(present_act), ge(mdc), xg(mdc), pcie1(clkreq), mss_gpio6, link(rd_out_cp2cp)
+mpp38	38	gpio, uart2(txd), i2c0(sda), ptp(pulse), tdm(rstn), mss_i2c(sda), sata0(present_act), ge(mdio), xg(mdio), au(i2sextclk), mss_gpio7, ptp(pulse_cp2cp)
+mpp39	39	gpio, sdio(wr_protect), au(i2sbclk), ptp(clk), spi0(csn1), sata1(present_act), mss_gpio0
+mpp40	40	gpio, sdio(pwr11), synce1(clk), mss_i2c(sda), au(i2sdo_spdifo), ptp(pclk_out), spi0(clk), uart1(txd), ge(mdio), sata0(present_act), mss_gpio1
+mpp41	41	gpio, sdio(pwr10), sdio(bus_pwr), mss_i2c(sck), au(i2slrclk), ptp(pulse), spi0(mosi), uart1(rxd), ge(mdc), sata1(present_act), mss_gpio2, rei(out_cp2cp)
+mpp42	42	gpio, sdio(v18_en), sdio(wr_protect), synce2(clk), au(i2smclk), mss_uart(txd), spi0(miso), uart1(cts), xg(mdc), sata0(present_act), mss_gpio4
+mpp43	43	gpio, sdio(card_detect), synce1(clk), au(i2sextclk), mss_uart(rxd), spi0(csn0), uart1(rts), xg(mdio), sata1(present_act), mss_gpio5, wakeup(out_cp2cp)
+mpp44	44	gpio, ge1(txd2), uart0(rts), ptp(clk_cp2cp)
+mpp45	45	gpio, ge1(txd3), uart0(txd), pcie(rstoutn)
+mpp46	46	gpio, ge1(txd1), uart1(rts)
+mpp47	47	gpio, ge1(txd0), spi1(clk), uart1(txd), ge(mdc)
+mpp48	48	gpio, ge1(txctl_txen), spi1(mosi), xg(mdc), wakeup(in_cp2cp)
+mpp49	49	gpio, ge1(txclkout), mii(crs), spi1(miso), uart1(rxd), ge(mdio), pcie0(clkreq), sdio(v18_en), sei(out_cp2cp)
+mpp50	50	gpio, ge1(rxclk), mss_i2c(sda), spi1(csn0), uart2(txd), uart0(rxd), xg(mdio), sdio(pwr11)
+mpp51	51	gpio, ge1(rxd0), mss_i2c(sck), spi1(csn1), uart2(rxd), uart0(cts), sdio(pwr10)
+mpp52	52	gpio, ge1(rxd1), synce1(clk), synce2(clk), spi1(csn2), uart1(cts), led(clk), pcie(rstoutn), pcie0(clkreq)
+mpp53	53	gpio, ge1(rxd2), ptp(clk), spi1(csn3), uart1(rxd), led(stb), sdio(led)
+mpp54	54	gpio, ge1(rxd3), synce2(clk), ptp(pclk_out), synce1(clk), led(data), sdio(hw_rst), sdio(wr_protect)
+mpp55	55	gpio, ge1(rxctl_rxdv), ptp(pulse), sdio(led), sdio(card_detect)
+mpp56	56	gpio, tdm(drx), au(i2sdo_spdifo), spi0(clk), uart1(rxd), sata1(present_act), sdio(clk)
+mpp57	57	gpio, mss_i2c(sda), ptp(pclk_out), tdm(intn), au(i2sbclk), spi0(mosi), uart1(txd), sata0(present_act), sdio(cmd)
+mpp58	58	gpio, mss_i2c(sck), ptp(clk), tdm(rstn), au(i2sdi), spi0(miso), uart1(cts), led(clk), sdio(d0)
+mpp59	59	gpio, mss_gpio7, synce2(clk), tdm(fsync), au(i2slrclk), spi0(csn0), uart0(cts), led(stb), uart1(txd), sdio(d1)
+mpp60	60	gpio, mss_gpio6, ptp(pulse), tdm(dtx), au(i2smclk), spi0(csn1), uart0(rts), led(data), uart1(rxd), sdio(d2)
+mpp61	61	gpio, mss_gpio5, ptp(clk), tdm(pclk), au(i2sextclk), spi0(csn2), uart0(txd), uart2(txd), sata1(present_act), ge(mdio), sdio(d3)
+mpp62	62	gpio, mss_gpio4, synce1(clk), ptp(pclk_out), sata1(present_act), spi0(csn3), uart0(rxd), uart2(rxd), sata0(present_act), ge(mdc)
+
+GPIO:
+-----
+
+For common binding part and usage, refer to
+Documentation/devicetree/bindings/gpio/gpio-mvebu.txt.
+
+Required properties:
+
+- compatible: "marvell,armada-8k-gpio"
+
+- offset: offset address inside the syscon block
+
+Example:
+
+cpm_syscon0: system-controller@440000 {
+	compatible = "syscon", "simple-mfd";
+	reg = <0x440000 0x1000>;
+
+	cpm_clk: clock {
+		compatible = "marvell,cp110-clock";
+		#clock-cells = <2>;
+	};
+
+	cpm_pinctrl: pinctrl {
+		compatible = "marvell,armada-8k-cpm-pinctrl";
+	};
+
+	cpm_gpio1: gpio@100 {
+		compatible = "marvell,armada-8k-gpio";
+		offset = <0x100>;
+		ngpios = <32>;
+		gpio-controller;
+		#gpio-cells = <2>;
+		gpio-ranges = <&cpm_pinctrl 0 0 32>;
+	};
+
+};
diff --git a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
deleted file mode 100644
index 29cdbae6c5ac..000000000000
--- a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller0.txt
+++ /dev/null
@@ -1,188 +0,0 @@
-Marvell Armada CP110 System Controller 0
-========================================
-
-The CP110 is one of the two core HW blocks of the Marvell Armada 7K/8K
-SoCs. It contains two sets of system control registers, System
-Controller 0 and System Controller 1. This Device Tree binding allows
-to describe the first system controller, which provides registers to
-configure various aspects of the SoC.
-
-For the top level node:
- - compatible: must be: "syscon", "simple-mfd";
- - reg: register area of the CP110 system controller 0
-
-Clocks:
--------
-
-The Device Tree node representing this System Controller 0 provides a
-number of clocks:
-
- - a set of core clocks
- - a set of gatable clocks
-
-Those clocks can be referenced by other Device Tree nodes using two
-cells:
- - The first cell must be 0 or 1. 0 for the core clocks and 1 for the
-   gatable clocks.
- - The second cell identifies the particular core clock or gatable
-   clocks.
-
-The following clocks are available:
- - Core clocks
-   - 0 0	APLL
-   - 0 1	PPv2 core
-   - 0 2	EIP
-   - 0 3	Core
-   - 0 4	NAND core
-   - 0 5	SDIO core
- - Gatable clocks
-   - 1 0	Audio
-   - 1 1	Comm Unit
-   - 1 2	NAND
-   - 1 3	PPv2
-   - 1 4	SDIO
-   - 1 5	MG Domain
-   - 1 6	MG Core
-   - 1 7	XOR1
-   - 1 8	XOR0
-   - 1 9	GOP DP
-   - 1 11	PCIe x1 0
-   - 1 12	PCIe x1 1
-   - 1 13	PCIe x4
-   - 1 14	PCIe / XOR
-   - 1 15	SATA
-   - 1 16	SATA USB
-   - 1 17	Main
-   - 1 18	SD/MMC/GOP
-   - 1 21	Slow IO (SPI, NOR, BootROM, I2C, UART)
-   - 1 22	USB3H0
-   - 1 23	USB3H1
-   - 1 24	USB3 Device
-   - 1 25	EIP150
-   - 1 26	EIP197
-
-Required properties:
-
- - compatible: must be:
-     "marvell,cp110-clock"
- - #clock-cells: must be set to 2
-
-Pinctrl:
---------
-
-For common binding part and usage, refer to the file
-Documentation/devicetree/bindings/pinctrl/marvell,mvebu-pinctrl.txt.
-
-Required properties:
-
-- compatible: "marvell,armada-7k-pinctrl",
-  "marvell,armada-8k-cpm-pinctrl" or "marvell,armada-8k-cps-pinctrl"
-  depending on the specific variant of the SoC being used.
-
-Available mpp pins/groups and functions:
-Note: brackets (x) are not part of the mpp name for marvell,function and given
-only for more detailed description in this document.
-
-name	pins	functions
-================================================================================
-mpp0	0	gpio, dev(ale1), au(i2smclk), ge0(rxd3), tdm(pclk), ptp(pulse), mss_i2c(sda), uart0(rxd), sata0(present_act), ge(mdio)
-mpp1	1	gpio, dev(ale0), au(i2sdo_spdifo), ge0(rxd2), tdm(drx), ptp(clk), mss_i2c(sck), uart0(txd), sata1(present_act), ge(mdc)
-mpp2	2	gpio, dev(ad15), au(i2sextclk), ge0(rxd1), tdm(dtx), mss_uart(rxd), ptp(pclk_out), i2c1(sck), uart1(rxd), sata0(present_act), xg(mdc)
-mpp3	3	gpio, dev(ad14), au(i2slrclk), ge0(rxd0), tdm(fsync), mss_uart(txd), pcie(rstoutn), i2c1(sda), uart1(txd), sata1(present_act), xg(mdio)
-mpp4	4	gpio, dev(ad13), au(i2sbclk), ge0(rxctl), tdm(rstn), mss_uart(rxd), uart1(cts), pcie0(clkreq), uart3(rxd), ge(mdc)
-mpp5	5	gpio, dev(ad12), au(i2sdi), ge0(rxclk), tdm(intn), mss_uart(txd), uart1(rts), pcie1(clkreq), uart3(txd), ge(mdio)
-mpp6	6	gpio, dev(ad11), ge0(txd3), spi0(csn2), au(i2sextclk), sata1(present_act), pcie2(clkreq), uart0(rxd), ptp(pulse)
-mpp7	7	gpio, dev(ad10), ge0(txd2), spi0(csn1), spi1(csn1), sata0(present_act), led(data), uart0(txd), ptp(clk)
-mpp8	8	gpio, dev(ad9), ge0(txd1), spi0(csn0), spi1(csn0), uart0(cts), led(stb), uart2(rxd), ptp(pclk_out), synce1(clk)
-mpp9	9	gpio, dev(ad8), ge0(txd0), spi0(mosi), spi1(mosi), pcie(rstoutn), synce2(clk)
-mpp10	10	gpio, dev(readyn), ge0(txctl), spi0(miso), spi1(miso), uart0(cts), sata1(present_act)
-mpp11	11	gpio, dev(wen1), ge0(txclkout), spi0(clk), spi1(clk), uart0(rts), led(clk), uart2(txd), sata0(present_act)
-mpp12	12	gpio, dev(clk_out), nf(rbn1), spi1(csn1), ge0(rxclk)
-mpp13	13	gpio, dev(burstn), nf(rbn0), spi1(miso), ge0(rxctl), mss_spi(miso)
-mpp14	14	gpio, dev(bootcsn), dev(csn0), spi1(csn0), spi0(csn3), au(i2sextclk), spi0(miso), sata0(present_act), mss_spi(csn)
-mpp15	15	gpio, dev(ad7), spi1(mosi), spi0(mosi), mss_spi(mosi), ptp(pulse_cp2cp)
-mpp16	16	gpio, dev(ad6), spi1(clk), mss_spi(clk)
-mpp17	17	gpio, dev(ad5), ge0(txd3)
-mpp18	18	gpio, dev(ad4), ge0(txd2), ptp(clk_cp2cp)
-mpp19	19	gpio, dev(ad3), ge0(txd1), wakeup(out_cp2cp)
-mpp20	20	gpio, dev(ad2), ge0(txd0)
-mpp21	21	gpio, dev(ad1), ge0(txctl), sei(in_cp2cp)
-mpp22	22	gpio, dev(ad0), ge0(txclkout), wakeup(in_cp2cp)
-mpp23	23	gpio, dev(a1), au(i2smclk), link(rd_in_cp2cp)
-mpp24	24	gpio, dev(a0), au(i2slrclk)
-mpp25	25	gpio, dev(oen), au(i2sdo_spdifo)
-mpp26	26	gpio, dev(wen0), au(i2sbclk)
-mpp27	27	gpio, dev(csn0), spi1(miso), mss_gpio4, ge0(rxd3), spi0(csn4), ge(mdio), sata0(present_act), uart0(rts), rei(in_cp2cp)
-mpp28	28	gpio, dev(csn1), spi1(csn0), mss_gpio5, ge0(rxd2), spi0(csn5), pcie2(clkreq), ptp(pulse), ge(mdc), sata1(present_act), uart0(cts), led(data)
-mpp29	29	gpio, dev(csn2), spi1(mosi), mss_gpio6, ge0(rxd1), spi0(csn6), pcie1(clkreq), ptp(clk), mss_i2c(sda), sata0(present_act), uart0(rxd), led(stb)
-mpp30	30	gpio, dev(csn3), spi1(clk), mss_gpio7, ge0(rxd0), spi0(csn7), pcie0(clkreq), ptp(pclk_out), mss_i2c(sck), sata1(present_act), uart0(txd), led(clk)
-mpp31	31	gpio, dev(a2), mss_gpio4, pcie(rstoutn), ge(mdc)
-mpp32	32	gpio, mii(col), mii(txerr), mss_spi(miso), tdm(drx), au(i2sextclk), au(i2sdi), ge(mdio), sdio(v18_en), pcie1(clkreq), mss_gpio0
-mpp33	33	gpio, mii(txclk), sdio(pwr10), mss_spi(csn), tdm(fsync), au(i2smclk), sdio(bus_pwr), xg(mdio), pcie2(clkreq), mss_gpio1
-mpp34	34	gpio, mii(rxerr), sdio(pwr11), mss_spi(mosi), tdm(dtx), au(i2slrclk), sdio(wr_protect), ge(mdc), pcie0(clkreq), mss_gpio2
-mpp35	35	gpio, sata1(present_act), i2c1(sda), mss_spi(clk), tdm(pclk), au(i2sdo_spdifo), sdio(card_detect), xg(mdio), ge(mdio), pcie(rstoutn), mss_gpio3
-mpp36	36	gpio, synce2(clk), i2c1(sck), ptp(clk), synce1(clk), au(i2sbclk), sata0(present_act), xg(mdc), ge(mdc), pcie2(clkreq), mss_gpio5
-mpp37	37	gpio, uart2(rxd), i2c0(sck), ptp(pclk_out), tdm(intn), mss_i2c(sck), sata1(present_act), ge(mdc), xg(mdc), pcie1(clkreq), mss_gpio6, link(rd_out_cp2cp)
-mpp38	38	gpio, uart2(txd), i2c0(sda), ptp(pulse), tdm(rstn), mss_i2c(sda), sata0(present_act), ge(mdio), xg(mdio), au(i2sextclk), mss_gpio7, ptp(pulse_cp2cp)
-mpp39	39	gpio, sdio(wr_protect), au(i2sbclk), ptp(clk), spi0(csn1), sata1(present_act), mss_gpio0
-mpp40	40	gpio, sdio(pwr11), synce1(clk), mss_i2c(sda), au(i2sdo_spdifo), ptp(pclk_out), spi0(clk), uart1(txd), ge(mdio), sata0(present_act), mss_gpio1
-mpp41	41	gpio, sdio(pwr10), sdio(bus_pwr), mss_i2c(sck), au(i2slrclk), ptp(pulse), spi0(mosi), uart1(rxd), ge(mdc), sata1(present_act), mss_gpio2, rei(out_cp2cp)
-mpp42	42	gpio, sdio(v18_en), sdio(wr_protect), synce2(clk), au(i2smclk), mss_uart(txd), spi0(miso), uart1(cts), xg(mdc), sata0(present_act), mss_gpio4
-mpp43	43	gpio, sdio(card_detect), synce1(clk), au(i2sextclk), mss_uart(rxd), spi0(csn0), uart1(rts), xg(mdio), sata1(present_act), mss_gpio5, wakeup(out_cp2cp)
-mpp44	44	gpio, ge1(txd2), uart0(rts), ptp(clk_cp2cp)
-mpp45	45	gpio, ge1(txd3), uart0(txd), pcie(rstoutn)
-mpp46	46	gpio, ge1(txd1), uart1(rts)
-mpp47	47	gpio, ge1(txd0), spi1(clk), uart1(txd), ge(mdc)
-mpp48	48	gpio, ge1(txctl_txen), spi1(mosi), xg(mdc), wakeup(in_cp2cp)
-mpp49	49	gpio, ge1(txclkout), mii(crs), spi1(miso), uart1(rxd), ge(mdio), pcie0(clkreq), sdio(v18_en), sei(out_cp2cp)
-mpp50	50	gpio, ge1(rxclk), mss_i2c(sda), spi1(csn0), uart2(txd), uart0(rxd), xg(mdio), sdio(pwr11)
-mpp51	51	gpio, ge1(rxd0), mss_i2c(sck), spi1(csn1), uart2(rxd), uart0(cts), sdio(pwr10)
-mpp52	52	gpio, ge1(rxd1), synce1(clk), synce2(clk), spi1(csn2), uart1(cts), led(clk), pcie(rstoutn), pcie0(clkreq)
-mpp53	53	gpio, ge1(rxd2), ptp(clk), spi1(csn3), uart1(rxd), led(stb), sdio(led)
-mpp54	54	gpio, ge1(rxd3), synce2(clk), ptp(pclk_out), synce1(clk), led(data), sdio(hw_rst), sdio(wr_protect)
-mpp55	55	gpio, ge1(rxctl_rxdv), ptp(pulse), sdio(led), sdio(card_detect)
-mpp56	56	gpio, tdm(drx), au(i2sdo_spdifo), spi0(clk), uart1(rxd), sata1(present_act), sdio(clk)
-mpp57	57	gpio, mss_i2c(sda), ptp(pclk_out), tdm(intn), au(i2sbclk), spi0(mosi), uart1(txd), sata0(present_act), sdio(cmd)
-mpp58	58	gpio, mss_i2c(sck), ptp(clk), tdm(rstn), au(i2sdi), spi0(miso), uart1(cts), led(clk), sdio(d0)
-mpp59	59	gpio, mss_gpio7, synce2(clk), tdm(fsync), au(i2slrclk), spi0(csn0), uart0(cts), led(stb), uart1(txd), sdio(d1)
-mpp60	60	gpio, mss_gpio6, ptp(pulse), tdm(dtx), au(i2smclk), spi0(csn1), uart0(rts), led(data), uart1(rxd), sdio(d2)
-mpp61	61	gpio, mss_gpio5, ptp(clk), tdm(pclk), au(i2sextclk), spi0(csn2), uart0(txd), uart2(txd), sata1(present_act), ge(mdio), sdio(d3)
-mpp62	62	gpio, mss_gpio4, synce1(clk), ptp(pclk_out), sata1(present_act), spi0(csn3), uart0(rxd), uart2(rxd), sata0(present_act), ge(mdc)
-
-GPIO:
------
-
-For common binding part and usage, refer to
-Documentation/devicetree/bindings/gpio/gpio-mvebu.txt.
-
-Required properties:
-
-- compatible: "marvell,armada-8k-gpio"
-
-- offset: offset address inside the syscon block
-
-Example:
-
-cpm_syscon0: system-controller@440000 {
-	compatible = "syscon", "simple-mfd";
-	reg = <0x440000 0x1000>;
-
-	cpm_clk: clock {
-		compatible = "marvell,cp110-clock";
-		#clock-cells = <2>;
-	};
-
-	cpm_pinctrl: pinctrl {
-		compatible = "marvell,armada-8k-cpm-pinctrl";
-	};
-
-	cpm_gpio1: gpio@100 {
-		compatible = "marvell,armada-8k-gpio";
-		offset = <0x100>;
-		ngpios = <32>;
-		gpio-controller;
-		#gpio-cells = <2>;
-		gpio-ranges = <&cpm_pinctrl 0 0 32>;
-	};
-
-};
-- 
cgit v1.2.3


From 2cefabe03f5ef6ff2c6c3faf949b05db63fda2a5 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:57 +0200
Subject: dt-bindings: ap806: prepare the syscon file to list other syscons
 nodes

There are multiple system controllers in AP806. Because all syscon nodes
use the same compatible, it is pertinent to use this same file to list
IPs inside it. Thus, change the header to be more generic.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../bindings/arm/marvell/ap806-system-controller.txt           | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt b/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
index 0b887440e08a..a856eb9a4e05 100644
--- a/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
@@ -2,14 +2,14 @@ Marvell Armada AP806 System Controller
 ======================================
 
 The AP806 is one of the two core HW blocks of the Marvell Armada 7K/8K
-SoCs. It contains a system controller, which provides a number
-registers giving access to numerous features: clocks, pin-muxing and
-many other SoC configuration items. This DT binding allows to describe
-this system controller.
+SoCs. It contains system controllers, which provide several registers
+giving access to numerous features: clocks, pin-muxing and many other
+SoC configuration items. This DT binding allows to describe these
+system controllers.
 
 For the top level node:
  - compatible: must be: "syscon", "simple-mfd";
-  - reg: register area of the AP806 system controller
+ - reg: register area of the AP806 system controller
 
 Clocks:
 -------
-- 
cgit v1.2.3


From ab0156c50d7986aacbc9b8bd9abc59bb29869d81 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:58 +0200
Subject: dt-bindings: cp110: prepare the syscon file to list other syscons
 nodes

There are multiple system controllers in CP110. Because all syscon nodes
use the same compatible, it is pertinent to use this same file to list
IPs inside it. Thus, change the header to be more generic, and align
with AP806 file.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../bindings/arm/marvell/cp110-system-controller.txt       | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
index 29cdbae6c5ac..56e7fb1153e7 100644
--- a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
@@ -1,15 +1,15 @@
-Marvell Armada CP110 System Controller 0
-========================================
+Marvell Armada CP110 System Controller
+======================================
 
 The CP110 is one of the two core HW blocks of the Marvell Armada 7K/8K
-SoCs. It contains two sets of system control registers, System
-Controller 0 and System Controller 1. This Device Tree binding allows
-to describe the first system controller, which provides registers to
-configure various aspects of the SoC.
+SoCs. It contains system controllers, which provide several registers
+giving access to numerous features: clocks, pin-muxing and many other
+SoC configuration items. This DT binding allows to describe these
+system controllers.
 
 For the top level node:
  - compatible: must be: "syscon", "simple-mfd";
- - reg: register area of the CP110 system controller 0
+ - reg: register area of the CP110 system controller
 
 Clocks:
 -------
-- 
cgit v1.2.3


From afa544a2fb6827b5ea8547a69b28115439e14533 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:41:59 +0200
Subject: dt-bindings: ap806: add the thermal node in the syscon file

Explain the thermal bindings now that the thermal IP is described being
inside of a system controller. Add a reference to the thermal-zone node.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../arm/marvell/ap806-system-controller.txt        | 38 ++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt b/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
index a856eb9a4e05..3fd21bb7cb37 100644
--- a/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
@@ -11,6 +11,9 @@ For the top level node:
  - compatible: must be: "syscon", "simple-mfd";
  - reg: register area of the AP806 system controller
 
+SYSTEM CONTROLLER 0
+===================
+
 Clocks:
 -------
 
@@ -98,3 +101,38 @@ ap_syscon: system-controller@6f4000 {
 		gpio-ranges = <&ap_pinctrl 0 0 19>;
 	};
 };
+
+SYSTEM CONTROLLER 1
+===================
+
+Thermal:
+--------
+
+For common binding part and usage, refer to
+Documentation/devicetree/bindings/thermal/thermal.txt
+
+The thermal IP can probe the temperature all around the processor. It
+may feature several channels, each of them wired to one sensor.
+
+Required properties:
+- compatible: must be one of:
+  * marvell,armada-ap806-thermal
+- reg: register range associated with the thermal functions.
+
+Optional properties:
+- #thermal-sensor-cells: shall be <1> when thermal-zones subnodes refer
+  to this IP and represents the channel ID. There is one sensor per
+  channel. O refers to the thermal IP internal channel, while positive
+  IDs refer to each CPU.
+
+Example:
+ap_syscon1: system-controller@6f8000 {
+	compatible = "syscon", "simple-mfd";
+	reg = <0x6f8000 0x1000>;
+
+	ap_thermal: thermal-sensor@80 {
+		compatible = "marvell,armada-ap806-thermal";
+		reg = <0x80 0x10>;
+		#thermal-sensor-cells = <1>;
+	};
+};
-- 
cgit v1.2.3


From e1ea68beaf539a1872debd749c62025cde0e2430 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:42:00 +0200
Subject: dt-bindings: cp110: update documentation since DT de-duplication

CP110 master/slave DT files have been merged in a DT de-duplication work
merged in v4.16. Update the syscon documentation accordingly to match
the current state of the DT nodes.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../bindings/arm/marvell/cp110-system-controller.txt           | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
index 56e7fb1153e7..54b0d64ce819 100644
--- a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
@@ -163,26 +163,26 @@ Required properties:
 
 Example:
 
-cpm_syscon0: system-controller@440000 {
+CP110_LABEL(syscon0): system-controller@440000 {
 	compatible = "syscon", "simple-mfd";
 	reg = <0x440000 0x1000>;
 
-	cpm_clk: clock {
+	CP110_LABEL(clk): clock {
 		compatible = "marvell,cp110-clock";
 		#clock-cells = <2>;
 	};
 
-	cpm_pinctrl: pinctrl {
+	CP110_LABEL(pinctrl): pinctrl {
 		compatible = "marvell,armada-8k-cpm-pinctrl";
 	};
 
-	cpm_gpio1: gpio@100 {
+	CP110_LABEL(gpio1): gpio@100 {
 		compatible = "marvell,armada-8k-gpio";
 		offset = <0x100>;
 		ngpios = <32>;
 		gpio-controller;
 		#gpio-cells = <2>;
-		gpio-ranges = <&cpm_pinctrl 0 0 32>;
+		gpio-ranges = <&CP110_LABEL(pinctrl) 0 0 32>;
 	};
 
 };
-- 
cgit v1.2.3


From c3ab5dfff1e088e163aa2f866dd66e5a55af463f Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:42:01 +0200
Subject: dt-bindings: cp110: add the thermal node in the syscon file

Explain the thermal bindings now that the thermal IP is described being
inside of a system controller. Add a reference to the thermal-zone node.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../arm/marvell/cp110-system-controller.txt        | 37 ++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
index 54b0d64ce819..81ce742d2760 100644
--- a/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
+++ b/Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
@@ -11,6 +11,9 @@ For the top level node:
  - compatible: must be: "syscon", "simple-mfd";
  - reg: register area of the CP110 system controller
 
+SYSTEM CONTROLLER 0
+===================
+
 Clocks:
 -------
 
@@ -186,3 +189,37 @@ CP110_LABEL(syscon0): system-controller@440000 {
 	};
 
 };
+
+SYSTEM CONTROLLER 1
+===================
+
+Thermal:
+--------
+
+The thermal IP can probe the temperature all around the processor. It
+may feature several channels, each of them wired to one sensor.
+
+For common binding part and usage, refer to
+Documentation/devicetree/bindings/thermal/thermal.txt
+
+Required properties:
+- compatible: must be one of:
+  * marvell,armada-cp110-thermal
+- reg: register range associated with the thermal functions.
+
+Optional properties:
+- #thermal-sensor-cells: shall be <1> when thermal-zones subnodes refer
+  to this IP and represents the channel ID. There is one sensor per
+  channel. O refers to the thermal IP internal channel.
+
+Example:
+CP110_LABEL(syscon1): system-controller@6f8000 {
+	compatible = "syscon", "simple-mfd";
+	reg = <0x6f8000 0x1000>;
+
+	CP110_LABEL(thermal): thermal-sensor@70 {
+		compatible = "marvell,armada-cp110-thermal";
+		reg = <0x70 0x10>;
+		#thermal-sensor-cells = <1>;
+	};
+};
-- 
cgit v1.2.3


From 59d7f4a7fa9821a4ce0ea5870c367f9d8adb2619 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Mon, 16 Jul 2018 16:42:02 +0200
Subject: dt-bindings: thermal: armada: add reference to new bindings

New bindings (using a syscon) are available for AP806 and CP110
compatibles. Add a reference to these files from the original
documentation.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Rob Herring <robh@kernel.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 Documentation/devicetree/bindings/thermal/armada-thermal.txt | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/thermal/armada-thermal.txt b/Documentation/devicetree/bindings/thermal/armada-thermal.txt
index e0d013a2e66d..f3b441100890 100644
--- a/Documentation/devicetree/bindings/thermal/armada-thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/armada-thermal.txt
@@ -10,6 +10,11 @@ Required properties:
     * marvell,armada-ap806-thermal
     * marvell,armada-cp110-thermal
 
+Note: these bindings are deprecated for AP806/CP110 and should instead
+follow the rules described in:
+Documentation/devicetree/bindings/arm/marvell/ap806-system-controller.txt
+Documentation/devicetree/bindings/arm/marvell/cp110-system-controller.txt
+
 - reg: Device's register space.
   Two entries are expected, see the examples below. The first one points
   to the status register (4B). The second one points to the control
-- 
cgit v1.2.3


From 409ef0bacacf72c51cc876349ae3fdf7cf726d47 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 10 Jul 2018 16:40:34 +0100
Subject: thermal_hwmon: Sanitize attribute name passed to hwmon

My Chromebook Plus (kevin) is spitting the following at boot time:

(NULL device *): hwmon: 'sbs-9-000b' is not a valid name attribute, please fix

Clearly, __hwmon_device_register is unhappy about the property name.
Some investigation reveals that thermal_add_hwmon_sysfs doesn't
sanitize the name of the attribute.

In order to keep it quiet, let's replace '-' with '_' in hwmon->type
This is consistent with what iio-hwmon does since b92fe9e3379c8.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/thermal_hwmon.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index 11278836ed12..0bd47007c57f 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -142,6 +142,7 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 
 	INIT_LIST_HEAD(&hwmon->tz_list);
 	strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
+	strreplace(hwmon->type, '-', '_');
 	hwmon->device = hwmon_device_register_with_info(NULL, hwmon->type,
 							hwmon, NULL, NULL);
 	if (IS_ERR(hwmon->device)) {
-- 
cgit v1.2.3


From f6b6b52ef7a54160c0a4d2b56a58f84a2e5b33c5 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <marc.zyngier@arm.com>
Date: Tue, 10 Jul 2018 16:40:35 +0100
Subject: thermal_hwmon: Pass the originating device down to
 hwmon_device_register_with_info

When registering the hwmon device, we pass NULL as the device.
While this doesn't result in any immediate breakage, it leaves
the hwmon device at the root of the virtual devices, rather than
attached to the thermal zone hierarchy.

Instead, let's pass the actual device, which is part of the
thermal_zone_device structure. This also avoids the rather
unpleasant ""NULL device *" which can be generated by dev_{err,info}
in the hwmon subsystem.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
Tested-by: Enric Balletbo i Serra <enric.balletbo@collabora.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/thermal_hwmon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/thermal_hwmon.c b/drivers/thermal/thermal_hwmon.c
index 0bd47007c57f..40c69a533b24 100644
--- a/drivers/thermal/thermal_hwmon.c
+++ b/drivers/thermal/thermal_hwmon.c
@@ -143,7 +143,7 @@ int thermal_add_hwmon_sysfs(struct thermal_zone_device *tz)
 	INIT_LIST_HEAD(&hwmon->tz_list);
 	strlcpy(hwmon->type, tz->type, THERMAL_NAME_LENGTH);
 	strreplace(hwmon->type, '-', '_');
-	hwmon->device = hwmon_device_register_with_info(NULL, hwmon->type,
+	hwmon->device = hwmon_device_register_with_info(&tz->device, hwmon->type,
 							hwmon, NULL, NULL);
 	if (IS_ERR(hwmon->device)) {
 		result = PTR_ERR(hwmon->device);
-- 
cgit v1.2.3


From 5834edde914b042faedb9179386335927315767b Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Wed, 18 Jul 2018 12:13:07 +0530
Subject: thermal: tsens: Get rid of unused fields in structure

status_field and trdy are unused in any of the tsens drivers. Remove them.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Acked-by: Rajendra Nayak <rnayak@codeaurora.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/qcom/tsens.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h
index 911c1978892b..dc56e1e2a19e 100644
--- a/drivers/thermal/qcom/tsens.h
+++ b/drivers/thermal/qcom/tsens.h
@@ -77,9 +77,7 @@ struct tsens_device {
 	struct device			*dev;
 	u32				num_sensors;
 	struct regmap			*map;
-	struct regmap_field		*status_field;
 	struct tsens_context		ctx;
-	bool				trdy;
 	const struct tsens_ops		*ops;
 	struct tsens_sensor		sensor[0];
 };
-- 
cgit v1.2.3


From 4ce6dcfd0d38169d9067c768fcce8e0d49f60fac Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Wed, 18 Jul 2018 12:13:08 +0530
Subject: dt: thermal: tsens: Document the fallback DT property for v2 of TSENS
 IP

We want to create common code for v2 of the TSENS IP block that is used in
a large number of Qualcomm SoCs. "qcom,tsens-v2" should be able to handle
most of the common functionality start with a common get_temp() function.

It is also necessary to split out the memory regions for the TM and SROT
register banks because their offsets are not constant across SoC families.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 .../devicetree/bindings/thermal/qcom-tsens.txt     | 31 +++++++++++++++++-----
 1 file changed, 25 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/thermal/qcom-tsens.txt b/Documentation/devicetree/bindings/thermal/qcom-tsens.txt
index 06195e8f35e2..1d9e8cf61018 100644
--- a/Documentation/devicetree/bindings/thermal/qcom-tsens.txt
+++ b/Documentation/devicetree/bindings/thermal/qcom-tsens.txt
@@ -1,18 +1,28 @@
 * QCOM SoC Temperature Sensor (TSENS)
 
 Required properties:
-- compatible :
- - "qcom,msm8916-tsens" : For 8916 Family of SoCs
- - "qcom,msm8974-tsens" : For 8974 Family of SoCs
- - "qcom,msm8996-tsens" : For 8996 Family of SoCs
+- compatible:
+  Must be one of the following:
+    - "qcom,msm8916-tsens" (MSM8916)
+    - "qcom,msm8974-tsens" (MSM8974)
+    - "qcom,msm8996-tsens" (MSM8996)
+    - "qcom,msm8998-tsens", "qcom,tsens-v2" (MSM8998)
+    - "qcom,sdm845-tsens", "qcom,tsens-v2" (SDM845)
+  The generic "qcom,tsens-v2" property must be used as a fallback for any SoC
+  with version 2 of the TSENS IP. MSM8996 is the only exception because the
+  generic property did not exist when support was added.
+
+- reg: Address range of the thermal registers.
+  New platforms containing v2.x.y of the TSENS IP must specify the SROT and TM
+  register spaces separately, with order being TM before SROT.
+  See Example 2, below.
 
-- reg: Address range of the thermal registers
 - #thermal-sensor-cells : Should be 1. See ./thermal.txt for a description.
 - #qcom,sensors: Number of sensors in tsens block
 - Refer to Documentation/devicetree/bindings/nvmem/nvmem.txt to know how to specify
 nvmem cells
 
-Example:
+Example 1 (legacy support before a fallback tsens-v2 property was introduced):
 tsens: thermal-sensor@900000 {
 		compatible = "qcom,msm8916-tsens";
 		reg = <0x4a8000 0x2000>;
@@ -20,3 +30,12 @@ tsens: thermal-sensor@900000 {
 		nvmem-cell-names = "caldata", "calsel";
 		#thermal-sensor-cells = <1>;
 	};
+
+Example 2 (for any platform containing v2 of the TSENS IP):
+tsens0: thermal-sensor@c263000 {
+		compatible = "qcom,sdm845-tsens", "qcom,tsens-v2";
+		reg = <0xc263000 0x1ff>, /* TM */
+			<0xc222000 0x1ff>; /* SROT */
+		#qcom,sensors = <13>;
+		#thermal-sensor-cells = <1>;
+	};
-- 
cgit v1.2.3


From 5b1283984fa39933e094d237387ad8fd39527fc1 Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Wed, 18 Jul 2018 12:13:09 +0530
Subject: thermal: tsens: Add support to split up register address space into
 two

There are two banks of registers for v2 TSENS IPs: SROT and TM. On older
SoCs these were contiguous, leading to DTs mapping them as one register
address space of size 0x2000. In newer SoCs, these two banks are not
contiguous anymore.

Add logic to init_common() to differentiate between old and new DTs and
adjust associated offsets for the TM register bank so that the old DTs will
continue to function correctly.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/qcom/tsens-8996.c   |  4 ++--
 drivers/thermal/qcom/tsens-common.c | 12 ++++++++++++
 drivers/thermal/qcom/tsens.h        |  1 +
 3 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/thermal/qcom/tsens-8996.c b/drivers/thermal/qcom/tsens-8996.c
index e1f77818d8fa..3e60cecd2c45 100644
--- a/drivers/thermal/qcom/tsens-8996.c
+++ b/drivers/thermal/qcom/tsens-8996.c
@@ -16,7 +16,7 @@
 #include <linux/regmap.h>
 #include "tsens.h"
 
-#define STATUS_OFFSET	0x10a0
+#define STATUS_OFFSET	0xa0
 #define LAST_TEMP_MASK	0xfff
 #define STATUS_VALID_BIT	BIT(21)
 #define CODE_SIGN_BIT		BIT(11)
@@ -28,7 +28,7 @@ static int get_temp_8996(struct tsens_device *tmdev, int id, int *temp)
 	unsigned int sensor_addr;
 	int last_temp = 0, last_temp2 = 0, last_temp3 = 0, ret;
 
-	sensor_addr = STATUS_OFFSET + s->hw_id * 4;
+	sensor_addr = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4;
 	ret = regmap_read(tmdev->map, sensor_addr, &code);
 	if (ret)
 		return ret;
diff --git a/drivers/thermal/qcom/tsens-common.c b/drivers/thermal/qcom/tsens-common.c
index b1449ad67fc0..c22dc18c7c65 100644
--- a/drivers/thermal/qcom/tsens-common.c
+++ b/drivers/thermal/qcom/tsens-common.c
@@ -16,6 +16,7 @@
 #include <linux/io.h>
 #include <linux/nvmem-consumer.h>
 #include <linux/of_address.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include "tsens.h"
@@ -126,11 +127,22 @@ static const struct regmap_config tsens_config = {
 int __init init_common(struct tsens_device *tmdev)
 {
 	void __iomem *base;
+	struct platform_device *op = of_find_device_by_node(tmdev->dev->of_node);
 
+	if (!op)
+		return -EINVAL;
 	base = of_iomap(tmdev->dev->of_node, 0);
 	if (!base)
 		return -EINVAL;
 
+	/* The driver only uses the TM register address space for now */
+	if (op->num_resources > 1) {
+		tmdev->tm_offset = 0;
+	} else {
+		/* old DTs where SROT and TM were in a contiguous 2K block */
+		tmdev->tm_offset = 0x1000;
+	}
+
 	tmdev->map = devm_regmap_init_mmio(tmdev->dev, base, &tsens_config);
 	if (IS_ERR(tmdev->map)) {
 		iounmap(base);
diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h
index dc56e1e2a19e..d785b37b47d2 100644
--- a/drivers/thermal/qcom/tsens.h
+++ b/drivers/thermal/qcom/tsens.h
@@ -77,6 +77,7 @@ struct tsens_device {
 	struct device			*dev;
 	u32				num_sensors;
 	struct regmap			*map;
+	u32				tm_offset;
 	struct tsens_context		ctx;
 	const struct tsens_ops		*ops;
 	struct tsens_sensor		sensor[0];
-- 
cgit v1.2.3


From 770324a4bf2ffbcab5692d473c3f3f0e36b5a289 Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Wed, 18 Jul 2018 12:13:11 +0530
Subject: thermal: tsens: Rename tsens-8996 to tsens-v2 for reuse

The TSENS block inside the 8996 is internally classified as version 2 of
the IP. Several other SoC families use this block and can share this code.

We rename get_temp() to reflect that it can be used across the v2 family.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/qcom/Makefile     |  2 +-
 drivers/thermal/qcom/tsens-8996.c | 84 ---------------------------------------
 drivers/thermal/qcom/tsens-v2.c   | 75 ++++++++++++++++++++++++++++++++++
 3 files changed, 76 insertions(+), 85 deletions(-)
 delete mode 100644 drivers/thermal/qcom/tsens-8996.c
 create mode 100644 drivers/thermal/qcom/tsens-v2.c

diff --git a/drivers/thermal/qcom/Makefile b/drivers/thermal/qcom/Makefile
index 2cc2193637e7..a821929ede0b 100644
--- a/drivers/thermal/qcom/Makefile
+++ b/drivers/thermal/qcom/Makefile
@@ -1,2 +1,2 @@
 obj-$(CONFIG_QCOM_TSENS)	+= qcom_tsens.o
-qcom_tsens-y			+= tsens.o tsens-common.o tsens-8916.o tsens-8974.o tsens-8960.o tsens-8996.o
+qcom_tsens-y			+= tsens.o tsens-common.o tsens-8916.o tsens-8974.o tsens-8960.o tsens-v2.o
diff --git a/drivers/thermal/qcom/tsens-8996.c b/drivers/thermal/qcom/tsens-8996.c
deleted file mode 100644
index 3e60cecd2c45..000000000000
--- a/drivers/thermal/qcom/tsens-8996.c
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * Copyright (c) 2015, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
-
-#include <linux/platform_device.h>
-#include <linux/regmap.h>
-#include "tsens.h"
-
-#define STATUS_OFFSET	0xa0
-#define LAST_TEMP_MASK	0xfff
-#define STATUS_VALID_BIT	BIT(21)
-#define CODE_SIGN_BIT		BIT(11)
-
-static int get_temp_8996(struct tsens_device *tmdev, int id, int *temp)
-{
-	struct tsens_sensor *s = &tmdev->sensor[id];
-	u32 code;
-	unsigned int sensor_addr;
-	int last_temp = 0, last_temp2 = 0, last_temp3 = 0, ret;
-
-	sensor_addr = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4;
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
-	if (ret)
-		return ret;
-	last_temp = code & LAST_TEMP_MASK;
-	if (code & STATUS_VALID_BIT)
-		goto done;
-
-	/* Try a second time */
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
-	if (ret)
-		return ret;
-	if (code & STATUS_VALID_BIT) {
-		last_temp = code & LAST_TEMP_MASK;
-		goto done;
-	} else {
-		last_temp2 = code & LAST_TEMP_MASK;
-	}
-
-	/* Try a third/last time */
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
-	if (ret)
-		return ret;
-	if (code & STATUS_VALID_BIT) {
-		last_temp = code & LAST_TEMP_MASK;
-		goto done;
-	} else {
-		last_temp3 = code & LAST_TEMP_MASK;
-	}
-
-	if (last_temp == last_temp2)
-		last_temp = last_temp2;
-	else if (last_temp2 == last_temp3)
-		last_temp = last_temp3;
-done:
-	/* Code sign bit is the sign extension for a negative value */
-	if (last_temp & CODE_SIGN_BIT)
-		last_temp |= ~CODE_SIGN_BIT;
-
-	/* Temperatures are in deciCelicius */
-	*temp = last_temp * 100;
-
-	return 0;
-}
-
-static const struct tsens_ops ops_8996 = {
-	.init		= init_common,
-	.get_temp	= get_temp_8996,
-};
-
-const struct tsens_data data_8996 = {
-	.num_sensors	= 13,
-	.ops		= &ops_8996,
-};
diff --git a/drivers/thermal/qcom/tsens-v2.c b/drivers/thermal/qcom/tsens-v2.c
new file mode 100644
index 000000000000..44d3736109d6
--- /dev/null
+++ b/drivers/thermal/qcom/tsens-v2.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2018, Linaro Limited
+ */
+
+#include <linux/regmap.h>
+#include "tsens.h"
+
+#define STATUS_OFFSET		0xa0
+#define LAST_TEMP_MASK		0xfff
+#define STATUS_VALID_BIT	BIT(21)
+#define CODE_SIGN_BIT		BIT(11)
+
+static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp)
+{
+	struct tsens_sensor *s = &tmdev->sensor[id];
+	u32 code;
+	unsigned int sensor_addr;
+	int last_temp = 0, last_temp2 = 0, last_temp3 = 0, ret;
+
+	sensor_addr = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4;
+	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	if (ret)
+		return ret;
+	last_temp = code & LAST_TEMP_MASK;
+	if (code & STATUS_VALID_BIT)
+		goto done;
+
+	/* Try a second time */
+	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	if (ret)
+		return ret;
+	if (code & STATUS_VALID_BIT) {
+		last_temp = code & LAST_TEMP_MASK;
+		goto done;
+	} else {
+		last_temp2 = code & LAST_TEMP_MASK;
+	}
+
+	/* Try a third/last time */
+	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	if (ret)
+		return ret;
+	if (code & STATUS_VALID_BIT) {
+		last_temp = code & LAST_TEMP_MASK;
+		goto done;
+	} else {
+		last_temp3 = code & LAST_TEMP_MASK;
+	}
+
+	if (last_temp == last_temp2)
+		last_temp = last_temp2;
+	else if (last_temp2 == last_temp3)
+		last_temp = last_temp3;
+done:
+	/* Code sign bit is the sign extension for a negative value */
+	if (last_temp & CODE_SIGN_BIT)
+		last_temp |= ~CODE_SIGN_BIT;
+
+	/* Temperatures are in deciCelicius */
+	*temp = last_temp * 100;
+
+	return 0;
+}
+
+static const struct tsens_ops ops_generic_v2 = {
+	.init		= init_common,
+	.get_temp	= get_temp_tsens_v2,
+};
+
+const struct tsens_data data_8996 = {
+	.num_sensors	= 13,
+	.ops		= &ops_generic_v2,
+};
-- 
cgit v1.2.3


From 191dc74bad60e1462094b2e25321479e7eb17cdc Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Wed, 18 Jul 2018 12:13:12 +0530
Subject: thermal: tsens: Add generic support for TSENS v2 IP

SDM845 uses v2 of the TSENS IP block but the get_temp() function appears to
be identical across v2.x.y in code seen so far. We use the generic
get_temp() function defined as part of ops_generic_v2.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Tested-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/qcom/tsens-v2.c | 5 +++++
 drivers/thermal/qcom/tsens.c    | 3 +++
 drivers/thermal/qcom/tsens.h    | 5 ++++-
 3 files changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/thermal/qcom/tsens-v2.c b/drivers/thermal/qcom/tsens-v2.c
index 44d3736109d6..f40150fd7eae 100644
--- a/drivers/thermal/qcom/tsens-v2.c
+++ b/drivers/thermal/qcom/tsens-v2.c
@@ -69,6 +69,11 @@ static const struct tsens_ops ops_generic_v2 = {
 	.get_temp	= get_temp_tsens_v2,
 };
 
+const struct tsens_data data_tsens_v2 = {
+	.ops            = &ops_generic_v2,
+};
+
+/* Kept around for backward compatibility with old msm8996.dtsi */
 const struct tsens_data data_8996 = {
 	.num_sensors	= 13,
 	.ops		= &ops_generic_v2,
diff --git a/drivers/thermal/qcom/tsens.c b/drivers/thermal/qcom/tsens.c
index 3440166c2ae9..a2c9bfae3d86 100644
--- a/drivers/thermal/qcom/tsens.c
+++ b/drivers/thermal/qcom/tsens.c
@@ -72,6 +72,9 @@ static const struct of_device_id tsens_table[] = {
 	}, {
 		.compatible = "qcom,msm8996-tsens",
 		.data = &data_8996,
+	}, {
+		.compatible = "qcom,tsens-v2",
+		.data = &data_tsens_v2,
 	},
 	{}
 };
diff --git a/drivers/thermal/qcom/tsens.h b/drivers/thermal/qcom/tsens.h
index d785b37b47d2..14331eb45a86 100644
--- a/drivers/thermal/qcom/tsens.h
+++ b/drivers/thermal/qcom/tsens.h
@@ -88,6 +88,9 @@ void compute_intercept_slope(struct tsens_device *, u32 *, u32 *, u32);
 int init_common(struct tsens_device *);
 int get_temp_common(struct tsens_device *, int, int *);
 
-extern const struct tsens_data data_8916, data_8974, data_8960, data_8996;
+/* TSENS v1 targets */
+extern const struct tsens_data data_8916, data_8974, data_8960;
+/* TSENS v2 targets */
+extern const struct tsens_data data_8996, data_tsens_v2;
 
 #endif /* __QCOM_TSENS_H__ */
-- 
cgit v1.2.3


From e0fe01426c50f54d06b6ff69de2be536ec0a3256 Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Thu, 26 Jul 2018 16:03:08 +0530
Subject: thermal: tsens: Rename variable

We're actually reading the temperature from the status register. Fix the
variable name to reflect that.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/qcom/tsens-common.c |  6 +++---
 drivers/thermal/qcom/tsens-v2.c     | 10 +++++-----
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/thermal/qcom/tsens-common.c b/drivers/thermal/qcom/tsens-common.c
index c22dc18c7c65..25e7f247b027 100644
--- a/drivers/thermal/qcom/tsens-common.c
+++ b/drivers/thermal/qcom/tsens-common.c
@@ -104,11 +104,11 @@ int get_temp_common(struct tsens_device *tmdev, int id, int *temp)
 {
 	struct tsens_sensor *s = &tmdev->sensor[id];
 	u32 code;
-	unsigned int sensor_addr;
+	unsigned int status_reg;
 	int last_temp = 0, ret;
 
-	sensor_addr = S0_ST_ADDR + s->hw_id * SN_ADDR_OFFSET;
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	status_reg = S0_ST_ADDR + s->hw_id * SN_ADDR_OFFSET;
+	ret = regmap_read(tmdev->map, status_reg, &code);
 	if (ret)
 		return ret;
 	last_temp = code & SN_ST_TEMP_MASK;
diff --git a/drivers/thermal/qcom/tsens-v2.c b/drivers/thermal/qcom/tsens-v2.c
index f40150fd7eae..908e3dcb2d5c 100644
--- a/drivers/thermal/qcom/tsens-v2.c
+++ b/drivers/thermal/qcom/tsens-v2.c
@@ -16,11 +16,11 @@ static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp)
 {
 	struct tsens_sensor *s = &tmdev->sensor[id];
 	u32 code;
-	unsigned int sensor_addr;
+	unsigned int status_reg;
 	int last_temp = 0, last_temp2 = 0, last_temp3 = 0, ret;
 
-	sensor_addr = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4;
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	status_reg = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4;
+	ret = regmap_read(tmdev->map, status_reg, &code);
 	if (ret)
 		return ret;
 	last_temp = code & LAST_TEMP_MASK;
@@ -28,7 +28,7 @@ static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp)
 		goto done;
 
 	/* Try a second time */
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	ret = regmap_read(tmdev->map, status_reg, &code);
 	if (ret)
 		return ret;
 	if (code & STATUS_VALID_BIT) {
@@ -39,7 +39,7 @@ static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp)
 	}
 
 	/* Try a third/last time */
-	ret = regmap_read(tmdev->map, sensor_addr, &code);
+	ret = regmap_read(tmdev->map, status_reg, &code);
 	if (ret)
 		return ret;
 	if (code & STATUS_VALID_BIT) {
-- 
cgit v1.2.3


From faa590baf8dfe5ad877e062f18de4419e4d174f7 Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Thu, 26 Jul 2018 16:03:09 +0530
Subject: thermal: tsens: switch from of_iomap() to devm_ioremap_resource()

devm_ioremap_resources() automatically requests resources (so that the I/O
region shows up in /proc/iomem) and devm_ wrappers do better error handling
and unmapping of the I/O region when needed.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/qcom/tsens-common.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/thermal/qcom/tsens-common.c b/drivers/thermal/qcom/tsens-common.c
index 25e7f247b027..6207d8d92351 100644
--- a/drivers/thermal/qcom/tsens-common.c
+++ b/drivers/thermal/qcom/tsens-common.c
@@ -127,13 +127,11 @@ static const struct regmap_config tsens_config = {
 int __init init_common(struct tsens_device *tmdev)
 {
 	void __iomem *base;
+	struct resource *res;
 	struct platform_device *op = of_find_device_by_node(tmdev->dev->of_node);
 
 	if (!op)
 		return -EINVAL;
-	base = of_iomap(tmdev->dev->of_node, 0);
-	if (!base)
-		return -EINVAL;
 
 	/* The driver only uses the TM register address space for now */
 	if (op->num_resources > 1) {
@@ -143,11 +141,14 @@ int __init init_common(struct tsens_device *tmdev)
 		tmdev->tm_offset = 0x1000;
 	}
 
+	res = platform_get_resource(op, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&op->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
 	tmdev->map = devm_regmap_init_mmio(tmdev->dev, base, &tsens_config);
-	if (IS_ERR(tmdev->map)) {
-		iounmap(base);
+	if (IS_ERR(tmdev->map))
 		return PTR_ERR(tmdev->map);
-	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 432121adf5e880240237bd9b15ec0ab995d7ea1f Mon Sep 17 00:00:00 2001
From: Amit Kucheria <amit.kucheria@linaro.org>
Date: Thu, 26 Jul 2018 16:03:10 +0530
Subject: thermal: tsens: Fix negative temperature reporting

The current code will always return 0xffffffff in case of negative
temperatures due to a bug in how the binary sign extension is being done.

Use sign_extend32() instead.

Signed-off-by: Amit Kucheria <amit.kucheria@linaro.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Bjorn Andersson <bjorn.andersson@linaro.org>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/qcom/tsens-v2.c | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/drivers/thermal/qcom/tsens-v2.c b/drivers/thermal/qcom/tsens-v2.c
index 908e3dcb2d5c..44da02f594ac 100644
--- a/drivers/thermal/qcom/tsens-v2.c
+++ b/drivers/thermal/qcom/tsens-v2.c
@@ -5,19 +5,20 @@
  */
 
 #include <linux/regmap.h>
+#include <linux/bitops.h>
 #include "tsens.h"
 
 #define STATUS_OFFSET		0xa0
 #define LAST_TEMP_MASK		0xfff
 #define STATUS_VALID_BIT	BIT(21)
-#define CODE_SIGN_BIT		BIT(11)
 
 static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp)
 {
 	struct tsens_sensor *s = &tmdev->sensor[id];
 	u32 code;
 	unsigned int status_reg;
-	int last_temp = 0, last_temp2 = 0, last_temp3 = 0, ret;
+	u32 last_temp = 0, last_temp2 = 0, last_temp3 = 0;
+	int ret;
 
 	status_reg = tmdev->tm_offset + STATUS_OFFSET + s->hw_id * 4;
 	ret = regmap_read(tmdev->map, status_reg, &code);
@@ -54,12 +55,8 @@ static int get_temp_tsens_v2(struct tsens_device *tmdev, int id, int *temp)
 	else if (last_temp2 == last_temp3)
 		last_temp = last_temp3;
 done:
-	/* Code sign bit is the sign extension for a negative value */
-	if (last_temp & CODE_SIGN_BIT)
-		last_temp |= ~CODE_SIGN_BIT;
-
-	/* Temperatures are in deciCelicius */
-	*temp = last_temp * 100;
+	/* Convert temperature from deciCelsius to milliCelsius */
+	*temp = sign_extend32(last_temp, fls(LAST_TEMP_MASK) - 1) * 100;
 
 	return 0;
 }
-- 
cgit v1.2.3


From a999933db9ed44f8501e0241f7f1fbdf36554396 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 27 Jul 2018 19:26:06 +0200
Subject: MIPS: remove mips_swiotlb_ops

mips_swiotlb_ops differs from the generic swiotlb_dma_ops only in that
it contains a mb() barrier after each operations that maps or syncs
dma memory to the device.

The dma operations are defined to not be memory barriers, but instead
the write* operations to kick the DMA off are supposed to contain them.

For mips this handled by war_io_reorder_wmb(), which evaluates to the
stronger wmb() instead of the pure compiler barrier barrier() for
just those platforms that use swiotlb, so I think we are covered
properly.

[paul.burton@mips.com:
  - Include linux/swiotlb.h to fix build failures for configs with
    CONFIG_SWIOTLB=y.]

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20038/
Cc: David Daney <ddaney@caviumnetworks.com>
Cc: Huacai Chen <chenhc@lemote.com>
Cc: linux-mips@linux-mips.org
Cc: iommu@lists.linux-foundation.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/include/asm/dma-mapping.h |  5 +--
 arch/mips/mm/Makefile               |  1 -
 arch/mips/mm/dma-swiotlb.c          | 61 -------------------------------------
 3 files changed, 3 insertions(+), 64 deletions(-)
 delete mode 100644 arch/mips/mm/dma-swiotlb.c

diff --git a/arch/mips/include/asm/dma-mapping.h b/arch/mips/include/asm/dma-mapping.h
index 1c6e0c8ef483..e81c4e97ff1a 100644
--- a/arch/mips/include/asm/dma-mapping.h
+++ b/arch/mips/include/asm/dma-mapping.h
@@ -2,15 +2,16 @@
 #ifndef _ASM_DMA_MAPPING_H
 #define _ASM_DMA_MAPPING_H
 
+#include <linux/swiotlb.h>
+
 extern const struct dma_map_ops jazz_dma_ops;
-extern const struct dma_map_ops mips_swiotlb_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
 #if defined(CONFIG_MACH_JAZZ)
 	return &jazz_dma_ops;
 #elif defined(CONFIG_SWIOTLB)
-	return &mips_swiotlb_ops;
+	return &swiotlb_dma_ops;
 #elif defined(CONFIG_DMA_NONCOHERENT_OPS)
 	return &dma_noncoherent_ops;
 #else
diff --git a/arch/mips/mm/Makefile b/arch/mips/mm/Makefile
index 6922f393af19..3e5bb203c95a 100644
--- a/arch/mips/mm/Makefile
+++ b/arch/mips/mm/Makefile
@@ -18,7 +18,6 @@ obj-$(CONFIG_64BIT)		+= pgtable-64.o
 obj-$(CONFIG_HIGHMEM)		+= highmem.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
 obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-noncoherent.o
-obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
 obj-$(CONFIG_CPU_R4K_CACHE_TLB) += c-r4k.o cex-gen.o tlb-r4k.o
 obj-$(CONFIG_CPU_R3000)		+= c-r3k.o tlb-r3k.o
diff --git a/arch/mips/mm/dma-swiotlb.c b/arch/mips/mm/dma-swiotlb.c
deleted file mode 100644
index 6014ed3479fd..000000000000
--- a/arch/mips/mm/dma-swiotlb.c
+++ /dev/null
@@ -1,61 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <linux/dma-mapping.h>
-#include <linux/swiotlb.h>
-
-static void *mips_swiotlb_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
-{
-	void *ret = swiotlb_alloc(dev, size, dma_handle, gfp, attrs);
-
-	mb();
-	return ret;
-}
-
-static dma_addr_t mips_swiotlb_map_page(struct device *dev,
-		struct page *page, unsigned long offset, size_t size,
-		enum dma_data_direction dir, unsigned long attrs)
-{
-	dma_addr_t daddr = swiotlb_map_page(dev, page, offset, size,
-					dir, attrs);
-	mb();
-	return daddr;
-}
-
-static int mips_swiotlb_map_sg(struct device *dev, struct scatterlist *sg,
-		int nents, enum dma_data_direction dir, unsigned long attrs)
-{
-	int r = swiotlb_map_sg_attrs(dev, sg, nents, dir, attrs);
-	mb();
-
-	return r;
-}
-
-static void mips_swiotlb_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size, enum dma_data_direction dir)
-{
-	swiotlb_sync_single_for_device(dev, dma_handle, size, dir);
-	mb();
-}
-
-static void mips_swiotlb_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sg, int nents, enum dma_data_direction dir)
-{
-	swiotlb_sync_sg_for_device(dev, sg, nents, dir);
-	mb();
-}
-
-const struct dma_map_ops mips_swiotlb_ops = {
-	.alloc			= mips_swiotlb_alloc,
-	.free			= swiotlb_free,
-	.map_page		= mips_swiotlb_map_page,
-	.unmap_page		= swiotlb_unmap_page,
-	.map_sg			= mips_swiotlb_map_sg,
-	.unmap_sg		= swiotlb_unmap_sg_attrs,
-	.sync_single_for_cpu	= swiotlb_sync_single_for_cpu,
-	.sync_single_for_device	= mips_swiotlb_sync_single_for_device,
-	.sync_sg_for_cpu	= swiotlb_sync_sg_for_cpu,
-	.sync_sg_for_device	= mips_swiotlb_sync_sg_for_device,
-	.mapping_error		= swiotlb_dma_mapping_error,
-	.dma_supported		= swiotlb_dma_supported,
-};
-EXPORT_SYMBOL(mips_swiotlb_ops);
-- 
cgit v1.2.3


From 278d7f3dc0a65bf0135e28164adaf86fb39ac308 Mon Sep 17 00:00:00 2001
From: Gal Pressman <galp@mellanox.com>
Date: Tue, 13 Feb 2018 10:31:26 +0200
Subject: net/mlx5e: Vxlan, cleanup an unused member in vxlan work

Cleanup the sa_family member of the vxlan work, it is unused/needed
anywhere in the code.

Signed-off-by: Gal Pressman <galp@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c   | 4 +---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h   | 4 +---
 3 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index fad947079a43..14a201cbb0a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3980,7 +3980,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
 	if (!mlx5e_vxlan_allowed(priv->mdev))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 1);
+	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
 }
 
 static void mlx5e_del_vxlan_port(struct net_device *netdev,
@@ -3994,7 +3994,7 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev,
 	if (!mlx5e_vxlan_allowed(priv->mdev))
 		return;
 
-	mlx5e_vxlan_queue_work(priv, ti->sa_family, be16_to_cpu(ti->port), 0);
+	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0);
 }
 
 static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 3c0ea9bc20e3..4b9190d677fc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -191,8 +191,7 @@ out_unlock:
 	kfree(vxlan_work);
 }
 
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
-			    u16 port, int add)
+void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
 {
 	struct mlx5e_vxlan_work *vxlan_work;
 
@@ -207,7 +206,6 @@ void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
 
 	vxlan_work->priv = priv;
 	vxlan_work->port = port;
-	vxlan_work->sa_family = sa_family;
 	queue_work(priv->wq, &vxlan_work->work);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 52c41c22235d..51f19e3e5784 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -44,7 +44,6 @@ struct mlx5e_vxlan {
 struct mlx5e_vxlan_work {
 	struct work_struct	work;
 	struct mlx5e_priv	*priv;
-	sa_family_t		sa_family;
 	u16			port;
 };
 
@@ -57,8 +56,7 @@ static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev)
 void mlx5e_vxlan_init(struct mlx5e_priv *priv);
 void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv);
 
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, sa_family_t sa_family,
-			    u16 port, int add);
+void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add);
 struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port);
 
 #endif /* __MLX5_VXLAN_H__ */
-- 
cgit v1.2.3


From 0f647bfcd05cb072f952badd7ea4b6b496b64892 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Mon, 7 May 2018 18:06:26 -0700
Subject: net/mlx5e: Vxlan, add direct delete function

Add direct vxlan delete function to be called from vxlan_delete_work.
Needed in downstream patch.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 4b9190d677fc..baeac5922e8c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -158,18 +158,14 @@ static void mlx5e_vxlan_add_work(struct work_struct *work)
 	kfree(vxlan_work);
 }
 
-static void mlx5e_vxlan_del_work(struct work_struct *work)
+static void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port)
 {
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv         = vxlan_work->priv;
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	u16 port = vxlan_work->port;
 	struct mlx5e_vxlan *vxlan;
 	bool remove = false;
 
-	mutex_lock(&priv->state_lock);
 	spin_lock_bh(&vxlan_db->lock);
+
 	vxlan = mlx5e_vxlan_lookup_port_locked(priv, port);
 	if (!vxlan)
 		goto out_unlock;
@@ -187,6 +183,17 @@ out_unlock:
 		kfree(vxlan);
 		vxlan_db->num_ports--;
 	}
+}
+
+static void mlx5e_vxlan_del_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv         = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5e_vxlan_del_port(priv, port);
 	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
-- 
cgit v1.2.3


From dccea6bf384c853f4a3ca60cb3d729dc41971602 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 8 May 2018 01:49:43 -0700
Subject: net/mlx5e: Vxlan, move netdev only logic to en_main.c

Create a direct vxlan API to add and delete vxlan ports from HW.
+void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
+void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port);

And move vxlan_add/del_work to en_main.c since they are netdev only
logic.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 51 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c   | 55 +++--------------------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h   | 16 ++-----
 3 files changed, 61 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 14a201cbb0a4..7a6b78e3b5f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3969,6 +3969,57 @@ static int mlx5e_get_vf_stats(struct net_device *dev,
 }
 #endif
 
+struct mlx5e_vxlan_work {
+	struct work_struct	work;
+	struct mlx5e_priv	*priv;
+	u16			port;
+};
+
+static void mlx5e_vxlan_add_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5e_vxlan_add_port(priv, port);
+	mutex_unlock(&priv->state_lock);
+
+	kfree(vxlan_work);
+}
+
+static void mlx5e_vxlan_del_work(struct work_struct *work)
+{
+	struct mlx5e_vxlan_work *vxlan_work =
+		container_of(work, struct mlx5e_vxlan_work, work);
+	struct mlx5e_priv *priv         = vxlan_work->priv;
+	u16 port = vxlan_work->port;
+
+	mutex_lock(&priv->state_lock);
+	mlx5e_vxlan_del_port(priv, port);
+	mutex_unlock(&priv->state_lock);
+	kfree(vxlan_work);
+}
+
+static void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
+{
+	struct mlx5e_vxlan_work *vxlan_work;
+
+	vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC);
+	if (!vxlan_work)
+		return;
+
+	if (add)
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_work);
+	else
+		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_work);
+
+	vxlan_work->priv = priv;
+	vxlan_work->port = port;
+	queue_work(priv->wq, &vxlan_work->work);
+}
+
 static void mlx5e_add_vxlan_port(struct net_device *netdev,
 				 struct udp_tunnel_info *ti)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index baeac5922e8c..9a8ca532a443 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -36,7 +36,11 @@
 #include "mlx5_core.h"
 #include "vxlan.h"
 
-static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
+struct mlx5e_vxlan {
+	struct hlist_node hlist;
+	atomic_t refcount;
+	u16 udp_port;
+};
 
 void mlx5e_vxlan_init(struct mlx5e_priv *priv)
 {
@@ -105,7 +109,7 @@ struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
 	return vxlan;
 }
 
-static void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
+void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
@@ -144,21 +148,7 @@ err_delete_port:
 	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
 }
 
-static void mlx5e_vxlan_add_work(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv = vxlan_work->priv;
-	u16 port = vxlan_work->port;
-
-	mutex_lock(&priv->state_lock);
-	mlx5e_vxlan_add_port(priv, port);
-	mutex_unlock(&priv->state_lock);
-
-	kfree(vxlan_work);
-}
-
-static void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port)
+void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5e_vxlan *vxlan;
@@ -185,37 +175,6 @@ out_unlock:
 	}
 }
 
-static void mlx5e_vxlan_del_work(struct work_struct *work)
-{
-	struct mlx5e_vxlan_work *vxlan_work =
-		container_of(work, struct mlx5e_vxlan_work, work);
-	struct mlx5e_priv *priv         = vxlan_work->priv;
-	u16 port = vxlan_work->port;
-
-	mutex_lock(&priv->state_lock);
-	mlx5e_vxlan_del_port(priv, port);
-	mutex_unlock(&priv->state_lock);
-	kfree(vxlan_work);
-}
-
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add)
-{
-	struct mlx5e_vxlan_work *vxlan_work;
-
-	vxlan_work = kmalloc(sizeof(*vxlan_work), GFP_ATOMIC);
-	if (!vxlan_work)
-		return;
-
-	if (add)
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_add_work);
-	else
-		INIT_WORK(&vxlan_work->work, mlx5e_vxlan_del_work);
-
-	vxlan_work->priv = priv;
-	vxlan_work->port = port;
-	queue_work(priv->wq, &vxlan_work->work);
-}
-
 void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 51f19e3e5784..1a02f5b38009 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -35,17 +35,7 @@
 #include <linux/mlx5/driver.h>
 #include "en.h"
 
-struct mlx5e_vxlan {
-	struct hlist_node hlist;
-	atomic_t refcount;
-	u16 udp_port;
-};
-
-struct mlx5e_vxlan_work {
-	struct work_struct	work;
-	struct mlx5e_priv	*priv;
-	u16			port;
-};
+struct mlx5e_vxlan;
 
 static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev)
 {
@@ -55,8 +45,8 @@ static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev)
 
 void mlx5e_vxlan_init(struct mlx5e_priv *priv);
 void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv);
-
-void mlx5e_vxlan_queue_work(struct mlx5e_priv *priv, u16 port, int add);
+void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
+void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port);
 struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port);
 
 #endif /* __MLX5_VXLAN_H__ */
-- 
cgit v1.2.3


From 5006eb221e6c1680067134f5de83d52bc5c2e1b6 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 8 May 2018 02:23:49 -0700
Subject: net/mlx5e: Vxlan, rename struct mlx5e_vxlan to mlx5_vxlan_port

The name mlx5e_vxlan will be used in downstream patch to describe
mlx5 vxlan structure that will replace mlx5e_vxlan_db.

Hence we rename struct mlx5e_vxlan to mlx5_vxlan_port which describes a
mlx5 vxlan port.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 63 ++++++++++++-------------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h |  4 +-
 2 files changed, 33 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 9a8ca532a443..a2b48ad77f26 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -36,7 +36,7 @@
 #include "mlx5_core.h"
 #include "vxlan.h"
 
-struct mlx5e_vxlan {
+struct mlx5_vxlan_port {
 	struct hlist_node hlist;
 	atomic_t refcount;
 	u16 udp_port;
@@ -83,40 +83,40 @@ static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static struct mlx5e_vxlan *mlx5e_vxlan_lookup_port_locked(struct mlx5e_priv *priv,
-							  u16 port)
+static struct mlx5_vxlan_port*
+mlx5e_vxlan_lookup_port_locked(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan    *vxlan;
+	struct mlx5_vxlan_port *vxlanp;
 
-	hash_for_each_possible(vxlan_db->htable, vxlan, hlist, port) {
-		if (vxlan->udp_port == port)
-			return vxlan;
+	hash_for_each_possible(vxlan_db->htable, vxlanp, hlist, port) {
+		if (vxlanp->udp_port == port)
+			return vxlanp;
 	}
 
 	return NULL;
 }
 
-struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
+struct mlx5_vxlan_port *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
+	struct mlx5_vxlan_port *vxlanp;
 
 	spin_lock_bh(&vxlan_db->lock);
-	vxlan = mlx5e_vxlan_lookup_port_locked(priv, port);
+	vxlanp = mlx5e_vxlan_lookup_port_locked(priv, port);
 	spin_unlock_bh(&vxlan_db->lock);
 
-	return vxlan;
+	return vxlanp;
 }
 
 void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
+	struct mlx5_vxlan_port *vxlanp;
 
-	vxlan = mlx5e_vxlan_lookup_port(priv, port);
-	if (vxlan) {
-		atomic_inc(&vxlan->refcount);
+	vxlanp = mlx5e_vxlan_lookup_port(priv, port);
+	if (vxlanp) {
+		atomic_inc(&vxlanp->refcount);
 		return;
 	}
 
@@ -130,15 +130,15 @@ void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
 		return;
 
-	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
-	if (!vxlan)
+	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
+	if (!vxlanp)
 		goto err_delete_port;
 
-	vxlan->udp_port = port;
-	atomic_set(&vxlan->refcount, 1);
+	vxlanp->udp_port = port;
+	atomic_set(&vxlanp->refcount, 1);
 
 	spin_lock_bh(&vxlan_db->lock);
-	hash_add(vxlan_db->htable, &vxlan->hlist, port);
+	hash_add(vxlan_db->htable, &vxlanp->hlist, port);
 	spin_unlock_bh(&vxlan_db->lock);
 
 	vxlan_db->num_ports++;
@@ -151,17 +151,16 @@ err_delete_port:
 void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
+	struct mlx5_vxlan_port *vxlanp;
 	bool remove = false;
 
 	spin_lock_bh(&vxlan_db->lock);
-
-	vxlan = mlx5e_vxlan_lookup_port_locked(priv, port);
-	if (!vxlan)
+	vxlanp = mlx5e_vxlan_lookup_port_locked(priv, port);
+	if (!vxlanp)
 		goto out_unlock;
 
-	if (atomic_dec_and_test(&vxlan->refcount)) {
-		hash_del(&vxlan->hlist);
+	if (atomic_dec_and_test(&vxlanp->refcount)) {
+		hash_del(&vxlanp->hlist);
 		remove = true;
 	}
 
@@ -170,7 +169,7 @@ out_unlock:
 
 	if (remove) {
 		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
-		kfree(vxlan);
+		kfree(vxlanp);
 		vxlan_db->num_ports--;
 	}
 }
@@ -178,14 +177,14 @@ out_unlock:
 void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
 {
 	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-	struct mlx5e_vxlan *vxlan;
+	struct mlx5_vxlan_port *vxlanp;
 	struct hlist_node *tmp;
 	int bkt;
 
 	/* Lockless since we are the only hash table consumers, wq and TX are disabled */
-	hash_for_each_safe(vxlan_db->htable, bkt, tmp, vxlan, hlist) {
-		hash_del(&vxlan->hlist);
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlan->udp_port);
-		kfree(vxlan);
+	hash_for_each_safe(vxlan_db->htable, bkt, tmp, vxlanp, hlist) {
+		hash_del(&vxlanp->hlist);
+		mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlanp->udp_port);
+		kfree(vxlanp);
 	}
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 1a02f5b38009..6b38b6fbd030 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -35,7 +35,7 @@
 #include <linux/mlx5/driver.h>
 #include "en.h"
 
-struct mlx5e_vxlan;
+struct mlx5_vxlan_port;
 
 static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev)
 {
@@ -47,6 +47,6 @@ void mlx5e_vxlan_init(struct mlx5e_priv *priv);
 void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv);
 void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
 void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port);
-struct mlx5e_vxlan *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port);
+struct mlx5_vxlan_port *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port);
 
 #endif /* __MLX5_VXLAN_H__ */
-- 
cgit v1.2.3


From a3c785d73cf280a023684dc6c7bbeff25b8b8163 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 8 May 2018 02:51:23 -0700
Subject: net/mlx5e: Vxlan, rename from mlx5e to mlx5

Rename vxlan functions from mlx5e_vxlan_* to mlx5_vxlan_*.
Rename mlx5e_vxlan_db to mlx5_vxlan and move it from en.h to vxlan.c
since it is not related to mlx5e anymore.

Allocate mlx5_vxlan structure dynamically in order to make it easier to
move later to core driver and to make it private in vxlan.c.

This is in preparation to move vxlan API to mlx5 core.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  10 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c |  21 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c   |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c   | 118 +++++++++++++---------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h   |  30 ++++--
 5 files changed, 104 insertions(+), 79 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 6878925c3abf..1bd4536b9061 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -52,6 +52,7 @@
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
+#include "vxlan.h"
 
 struct page_pool;
 
@@ -654,13 +655,6 @@ enum {
 	MLX5E_STATE_DESTROYING,
 };
 
-struct mlx5e_vxlan_db {
-	spinlock_t			lock; /* protect vxlan table */
-	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
-	DECLARE_HASHTABLE(htable, 4);
-	int				num_ports;
-};
-
 struct mlx5e_l2_rule {
 	u8  addr[ETH_ALEN + 2];
 	struct mlx5_flow_handle *rule;
@@ -818,7 +812,7 @@ struct mlx5e_priv {
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
-	struct mlx5e_vxlan_db      vxlan;
+	struct mlx5_vxlan          *vxlan;
 
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7a6b78e3b5f7..ef4b2f0c427c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2974,7 +2974,7 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
-	if (mlx5e_vxlan_allowed(priv->mdev))
+	if (mlx5_vxlan_allowed(priv->vxlan))
 		udp_tunnel_get_rx_info(netdev);
 
 	return err;
@@ -3983,7 +3983,7 @@ static void mlx5e_vxlan_add_work(struct work_struct *work)
 	u16 port = vxlan_work->port;
 
 	mutex_lock(&priv->state_lock);
-	mlx5e_vxlan_add_port(priv, port);
+	mlx5_vxlan_add_port(priv->vxlan, port);
 	mutex_unlock(&priv->state_lock);
 
 	kfree(vxlan_work);
@@ -3997,7 +3997,7 @@ static void mlx5e_vxlan_del_work(struct work_struct *work)
 	u16 port = vxlan_work->port;
 
 	mutex_lock(&priv->state_lock);
-	mlx5e_vxlan_del_port(priv, port);
+	mlx5_vxlan_del_port(priv->vxlan, port);
 	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
@@ -4028,7 +4028,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5e_vxlan_allowed(priv->mdev))
+	if (!mlx5_vxlan_allowed(priv->vxlan))
 		return;
 
 	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
@@ -4042,7 +4042,7 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5e_vxlan_allowed(priv->mdev))
+	if (!mlx5_vxlan_allowed(priv->vxlan))
 		return;
 
 	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0);
@@ -4076,7 +4076,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		port = be16_to_cpu(udph->dest);
 
 		/* Verify if UDP port is being offloaded by HW */
-		if (mlx5e_vxlan_lookup_port(priv, port))
+		if (mlx5_vxlan_lookup_port(priv->vxlan, port))
 			return features;
 	}
 
@@ -4648,7 +4648,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5e_vxlan_allowed(mdev) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
+	if (mlx5_vxlan_allowed(priv->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
 		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
 		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -4656,7 +4656,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 		netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
 	}
 
-	if (mlx5e_vxlan_allowed(mdev)) {
+	if (mlx5_vxlan_allowed(priv->vxlan)) {
 		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
 					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
 		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
@@ -4758,6 +4758,8 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
 
+	priv->vxlan = mlx5_vxlan_create(mdev);
+
 	mlx5e_build_nic_netdev_priv(mdev, netdev, profile, ppriv);
 	err = mlx5e_ipsec_init(priv);
 	if (err)
@@ -4767,14 +4769,13 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 		mlx5_core_err(mdev, "TLS initialization failed, %d\n", err);
 	mlx5e_build_nic_netdev(netdev);
 	mlx5e_build_tc2txq_maps(priv);
-	mlx5e_vxlan_init(priv);
 }
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
+	mlx5_vxlan_destroy(priv->vxlan);
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
-	mlx5e_vxlan_cleanup(priv);
 }
 
 static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 1010ee983ab7..1b4931b62094 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1133,7 +1133,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
 			goto vxlan_match_offload_err;
 
-		if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->dst)) &&
+		if (mlx5_vxlan_lookup_port(up_priv->vxlan, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
 		else {
@@ -2557,7 +2557,7 @@ vxlan_encap_offload_err:
 		return -EOPNOTSUPP;
 	}
 
-	if (mlx5e_vxlan_lookup_port(up_priv, be16_to_cpu(key->tp_dst)) &&
+	if (mlx5_vxlan_lookup_port(up_priv->vxlan, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		tunnel_type = MLX5_HEADER_TYPE_VXLAN;
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index a2b48ad77f26..759260f52bdd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -36,32 +36,26 @@
 #include "mlx5_core.h"
 #include "vxlan.h"
 
+struct mlx5_vxlan {
+	struct mlx5_core_dev		*mdev;
+	spinlock_t			lock; /* protect vxlan table */
+	int				num_ports;
+	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
+	DECLARE_HASHTABLE(htable, 4);
+};
+
 struct mlx5_vxlan_port {
 	struct hlist_node hlist;
 	atomic_t refcount;
 	u16 udp_port;
 };
 
-void mlx5e_vxlan_init(struct mlx5e_priv *priv)
-{
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
-
-	spin_lock_init(&vxlan_db->lock);
-	hash_init(vxlan_db->htable);
-
-	if (mlx5e_vxlan_allowed(priv->mdev))
-		/* Hardware adds 4789 by default.
-		 * Lockless since we are the only hash table consumers, wq and TX are disabled.
-		 */
-		mlx5e_vxlan_add_port(priv, 4789);
-}
-
-static inline u8 mlx5e_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
+static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
 {
 	return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4;
 }
 
-static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 {
 	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
@@ -72,7 +66,7 @@ static int mlx5e_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
 
-static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 {
 	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
 	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
@@ -84,12 +78,11 @@ static int mlx5e_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
 }
 
 static struct mlx5_vxlan_port*
-mlx5e_vxlan_lookup_port_locked(struct mlx5e_priv *priv, u16 port)
+mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port)
 {
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5_vxlan_port *vxlanp;
 
-	hash_for_each_possible(vxlan_db->htable, vxlanp, hlist, port) {
+	hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) {
 		if (vxlanp->udp_port == port)
 			return vxlanp;
 	}
@@ -97,37 +90,38 @@ mlx5e_vxlan_lookup_port_locked(struct mlx5e_priv *priv, u16 port)
 	return NULL;
 }
 
-struct mlx5_vxlan_port *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port)
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port)
 {
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5_vxlan_port *vxlanp;
 
-	spin_lock_bh(&vxlan_db->lock);
-	vxlanp = mlx5e_vxlan_lookup_port_locked(priv, port);
-	spin_unlock_bh(&vxlan_db->lock);
+	if (!mlx5_vxlan_allowed(vxlan))
+		return NULL;
+
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
+	spin_unlock_bh(&vxlan->lock);
 
 	return vxlanp;
 }
 
-void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
+void mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
 {
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5_vxlan_port *vxlanp;
 
-	vxlanp = mlx5e_vxlan_lookup_port(priv, port);
+	vxlanp = mlx5_vxlan_lookup_port(vxlan, port);
 	if (vxlanp) {
 		atomic_inc(&vxlanp->refcount);
 		return;
 	}
 
-	if (vxlan_db->num_ports >= mlx5e_vxlan_max_udp_ports(priv->mdev)) {
-		netdev_info(priv->netdev,
-			    "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
-			    port, mlx5e_vxlan_max_udp_ports(priv->mdev));
+	if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) {
+		mlx5_core_info(vxlan->mdev,
+			       "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
+			       port, mlx5_vxlan_max_udp_ports(vxlan->mdev));
 		return;
 	}
 
-	if (mlx5e_vxlan_core_add_port_cmd(priv->mdev, port))
+	if (mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port))
 		return;
 
 	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
@@ -137,25 +131,24 @@ void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port)
 	vxlanp->udp_port = port;
 	atomic_set(&vxlanp->refcount, 1);
 
-	spin_lock_bh(&vxlan_db->lock);
-	hash_add(vxlan_db->htable, &vxlanp->hlist, port);
-	spin_unlock_bh(&vxlan_db->lock);
+	spin_lock_bh(&vxlan->lock);
+	hash_add(vxlan->htable, &vxlanp->hlist, port);
+	spin_unlock_bh(&vxlan->lock);
 
-	vxlan_db->num_ports++;
+	vxlan->num_ports++;
 	return;
 
 err_delete_port:
-	mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+	mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
 }
 
-void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port)
+void mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
 {
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5_vxlan_port *vxlanp;
 	bool remove = false;
 
-	spin_lock_bh(&vxlan_db->lock);
-	vxlanp = mlx5e_vxlan_lookup_port_locked(priv, port);
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
 	if (!vxlanp)
 		goto out_unlock;
 
@@ -165,26 +158,51 @@ void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port)
 	}
 
 out_unlock:
-	spin_unlock_bh(&vxlan_db->lock);
+	spin_unlock_bh(&vxlan->lock);
 
 	if (remove) {
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, port);
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
 		kfree(vxlanp);
-		vxlan_db->num_ports--;
+		vxlan->num_ports--;
 	}
 }
 
-void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv)
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_vxlan *vxlan;
+
+	if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev))
+		return ERR_PTR(-ENOTSUPP);
+
+	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
+	if (!vxlan)
+		return ERR_PTR(-ENOMEM);
+
+	vxlan->mdev = mdev;
+	spin_lock_init(&vxlan->lock);
+	hash_init(vxlan->htable);
+
+	/* Hardware adds 4789 by default */
+	mlx5_vxlan_add_port(vxlan, 4789);
+
+	return vxlan;
+}
+
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
 {
-	struct mlx5e_vxlan_db *vxlan_db = &priv->vxlan;
 	struct mlx5_vxlan_port *vxlanp;
 	struct hlist_node *tmp;
 	int bkt;
 
-	/* Lockless since we are the only hash table consumers, wq and TX are disabled */
-	hash_for_each_safe(vxlan_db->htable, bkt, tmp, vxlanp, hlist) {
+	if (!mlx5_vxlan_allowed(vxlan))
+		return;
+
+	/* Lockless since we are the only hash table consumers*/
+	hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
 		hash_del(&vxlanp->hlist);
-		mlx5e_vxlan_core_del_port_cmd(priv->mdev, vxlanp->udp_port);
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
 		kfree(vxlanp);
 	}
+
+	kfree(vxlan);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 6b38b6fbd030..9d6327321814 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -33,20 +33,32 @@
 #define __MLX5_VXLAN_H__
 
 #include <linux/mlx5/driver.h>
-#include "en.h"
 
+struct mlx5_vxlan;
 struct mlx5_vxlan_port;
 
-static inline bool mlx5e_vxlan_allowed(struct mlx5_core_dev *mdev)
+#ifdef CONFIG_MLX5_CORE_EN
+
+static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
 {
-	return (MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) &&
-		mlx5_core_is_pf(mdev));
+	/* not allowed reason is encoded in vxlan pointer as error,
+	 * on mlx5_vxlan_create
+	 */
+	return !IS_ERR_OR_NULL(vxlan);
 }
 
-void mlx5e_vxlan_init(struct mlx5e_priv *priv);
-void mlx5e_vxlan_cleanup(struct mlx5e_priv *priv);
-void mlx5e_vxlan_add_port(struct mlx5e_priv *priv, u16 port);
-void mlx5e_vxlan_del_port(struct mlx5e_priv *priv, u16 port);
-struct mlx5_vxlan_port *mlx5e_vxlan_lookup_port(struct mlx5e_priv *priv, u16 port);
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
+void mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
+void mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+
+#else
+
+static inline struct mlx5_vxlan*
+mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); }
+static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
+
+#endif
 
 #endif /* __MLX5_VXLAN_H__ */
-- 
cgit v1.2.3


From 1b318a92f3ddaed6c91d5027dfd42549f87602f6 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 8 May 2018 14:33:19 -0700
Subject: net/mlx5e: Vxlan, return values for add/del port

For a better API mlx5_vxlan_{add/del}_port can fail, make them return
error values.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 28 +++++++++++++++++--------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h |  4 ++--
 2 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index 759260f52bdd..c9a50753ab23 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -104,29 +104,34 @@ struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 por
 	return vxlanp;
 }
 
-void mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
 {
 	struct mlx5_vxlan_port *vxlanp;
+	int ret = -ENOSPC;
 
 	vxlanp = mlx5_vxlan_lookup_port(vxlan, port);
 	if (vxlanp) {
 		atomic_inc(&vxlanp->refcount);
-		return;
+		return 0;
 	}
 
 	if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) {
 		mlx5_core_info(vxlan->mdev,
 			       "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
 			       port, mlx5_vxlan_max_udp_ports(vxlan->mdev));
-		return;
+		ret = -ENOSPC;
+		return ret;
 	}
 
-	if (mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port))
-		return;
+	ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port);
+	if (ret)
+		return ret;
 
 	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
-	if (!vxlanp)
+	if (!vxlanp) {
+		ret = -ENOMEM;
 		goto err_delete_port;
+	}
 
 	vxlanp->udp_port = port;
 	atomic_set(&vxlanp->refcount, 1);
@@ -136,21 +141,25 @@ void mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
 	spin_unlock_bh(&vxlan->lock);
 
 	vxlan->num_ports++;
-	return;
+	return 0;
 
 err_delete_port:
 	mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+	return ret;
 }
 
-void mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
 {
 	struct mlx5_vxlan_port *vxlanp;
 	bool remove = false;
+	int ret = 0;
 
 	spin_lock_bh(&vxlan->lock);
 	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
-	if (!vxlanp)
+	if (!vxlanp) {
+		ret = -ENOENT;
 		goto out_unlock;
+	}
 
 	if (atomic_dec_and_test(&vxlanp->refcount)) {
 		hash_del(&vxlanp->hlist);
@@ -165,6 +174,7 @@ out_unlock:
 		kfree(vxlanp);
 		vxlan->num_ports--;
 	}
+	return ret;
 }
 
 struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
index 9d6327321814..fd874a30c4d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
@@ -49,8 +49,8 @@ static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
 
 struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
 void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
-void mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
-void mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
 struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
 
 #else
-- 
cgit v1.2.3


From aec4eab9af9606e8a6a1ceab3ec5a15030751876 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 8 May 2018 16:17:06 -0700
Subject: net/mlx5e: Vxlan, add sync lock for add/del vxlan port

Vxlan API can and will be called from different mlx5 modules, we should
not count on mlx5e private state lock only, hence we introduce a vxlan
private mutex to sync between add/del vxlan port operations.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
index c9a50753ab23..9a8fd762167b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
@@ -39,9 +39,10 @@
 struct mlx5_vxlan {
 	struct mlx5_core_dev		*mdev;
 	spinlock_t			lock; /* protect vxlan table */
-	int				num_ports;
 	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
 	DECLARE_HASHTABLE(htable, 4);
+	int				num_ports;
+	struct mutex                    sync_lock; /* sync add/del port HW operations */
 };
 
 struct mlx5_vxlan_port {
@@ -115,17 +116,18 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
 		return 0;
 	}
 
+	mutex_lock(&vxlan->sync_lock);
 	if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) {
 		mlx5_core_info(vxlan->mdev,
 			       "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
 			       port, mlx5_vxlan_max_udp_ports(vxlan->mdev));
 		ret = -ENOSPC;
-		return ret;
+		goto unlock;
 	}
 
 	ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port);
 	if (ret)
-		return ret;
+		goto unlock;
 
 	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
 	if (!vxlanp) {
@@ -141,10 +143,14 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
 	spin_unlock_bh(&vxlan->lock);
 
 	vxlan->num_ports++;
+	mutex_unlock(&vxlan->sync_lock);
 	return 0;
 
 err_delete_port:
 	mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+
+unlock:
+	mutex_unlock(&vxlan->sync_lock);
 	return ret;
 }
 
@@ -154,6 +160,8 @@ int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
 	bool remove = false;
 	int ret = 0;
 
+	mutex_lock(&vxlan->sync_lock);
+
 	spin_lock_bh(&vxlan->lock);
 	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
 	if (!vxlanp) {
@@ -174,6 +182,9 @@ out_unlock:
 		kfree(vxlanp);
 		vxlan->num_ports--;
 	}
+
+	mutex_unlock(&vxlan->sync_lock);
+
 	return ret;
 }
 
@@ -189,6 +200,7 @@ struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
 		return ERR_PTR(-ENOMEM);
 
 	vxlan->mdev = mdev;
+	mutex_init(&vxlan->sync_lock);
 	spin_lock_init(&vxlan->lock);
 	hash_init(vxlan->htable);
 
-- 
cgit v1.2.3


From 358aa5ce288aa1085f0f3ef9f315119563fa6541 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 9 May 2018 13:28:00 -0700
Subject: net/mlx5e: Vxlan, move vxlan logic to core driver

Move vxlan logic and objects to mlx5 core dirver.
Since it going to be used from different mlx5 interfaces.
e.g. mlx5e PF NIC netdev and mlx5e E-Switch representors.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   4 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h       |   2 -
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  21 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c    |   6 +-
 .../net/ethernet/mellanox/mlx5/core/lib/vxlan.c    | 230 +++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/lib/vxlan.h    |  64 ++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   5 +
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c    | 230 ---------------------
 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h    |  64 ------
 include/linux/mlx5/driver.h                        |   2 +
 10 files changed, 315 insertions(+), 313 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
 delete mode 100644 drivers/net/ethernet/mellanox/mlx5/core/vxlan.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index ae2bdcb1647c..f20fda1ced4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -14,8 +14,8 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
-		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o vxlan.o \
-		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o
+		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
+		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o lib/vxlan.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 1bd4536b9061..c7ed3d20fd54 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -52,7 +52,6 @@
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
-#include "vxlan.h"
 
 struct page_pool;
 
@@ -812,7 +811,6 @@ struct mlx5e_priv {
 	u32                        tx_rates[MLX5E_MAX_NUM_SQS];
 
 	struct mlx5e_flow_steering fs;
-	struct mlx5_vxlan          *vxlan;
 
 	struct workqueue_struct    *wq;
 	struct work_struct         update_carrier_work;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index ef4b2f0c427c..fde35021a257 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -45,7 +45,7 @@
 #include "en_accel/tls.h"
 #include "accel/ipsec.h"
 #include "accel/tls.h"
-#include "vxlan.h"
+#include "lib/vxlan.h"
 #include "en/port.h"
 #include "en/xdp.h"
 
@@ -2974,7 +2974,7 @@ int mlx5e_open(struct net_device *netdev)
 		mlx5_set_port_admin_status(priv->mdev, MLX5_PORT_UP);
 	mutex_unlock(&priv->state_lock);
 
-	if (mlx5_vxlan_allowed(priv->vxlan))
+	if (mlx5_vxlan_allowed(priv->mdev->vxlan))
 		udp_tunnel_get_rx_info(netdev);
 
 	return err;
@@ -3983,7 +3983,7 @@ static void mlx5e_vxlan_add_work(struct work_struct *work)
 	u16 port = vxlan_work->port;
 
 	mutex_lock(&priv->state_lock);
-	mlx5_vxlan_add_port(priv->vxlan, port);
+	mlx5_vxlan_add_port(priv->mdev->vxlan, port);
 	mutex_unlock(&priv->state_lock);
 
 	kfree(vxlan_work);
@@ -3997,7 +3997,7 @@ static void mlx5e_vxlan_del_work(struct work_struct *work)
 	u16 port = vxlan_work->port;
 
 	mutex_lock(&priv->state_lock);
-	mlx5_vxlan_del_port(priv->vxlan, port);
+	mlx5_vxlan_del_port(priv->mdev->vxlan, port);
 	mutex_unlock(&priv->state_lock);
 	kfree(vxlan_work);
 }
@@ -4028,7 +4028,7 @@ static void mlx5e_add_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5_vxlan_allowed(priv->vxlan))
+	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
 		return;
 
 	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 1);
@@ -4042,7 +4042,7 @@ static void mlx5e_del_vxlan_port(struct net_device *netdev,
 	if (ti->type != UDP_TUNNEL_TYPE_VXLAN)
 		return;
 
-	if (!mlx5_vxlan_allowed(priv->vxlan))
+	if (!mlx5_vxlan_allowed(priv->mdev->vxlan))
 		return;
 
 	mlx5e_vxlan_queue_work(priv, be16_to_cpu(ti->port), 0);
@@ -4076,7 +4076,7 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv,
 		port = be16_to_cpu(udph->dest);
 
 		/* Verify if UDP port is being offloaded by HW */
-		if (mlx5_vxlan_lookup_port(priv->vxlan, port))
+		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, port))
 			return features;
 	}
 
@@ -4648,7 +4648,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	netdev->hw_features      |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	netdev->hw_features      |= NETIF_F_HW_VLAN_STAG_TX;
 
-	if (mlx5_vxlan_allowed(priv->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
+	if (mlx5_vxlan_allowed(mdev->vxlan) || MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) {
 		netdev->hw_enc_features |= NETIF_F_IP_CSUM;
 		netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
 		netdev->hw_enc_features |= NETIF_F_TSO;
@@ -4656,7 +4656,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 		netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
 	}
 
-	if (mlx5_vxlan_allowed(priv->vxlan)) {
+	if (mlx5_vxlan_allowed(mdev->vxlan)) {
 		netdev->hw_features     |= NETIF_F_GSO_UDP_TUNNEL |
 					   NETIF_F_GSO_UDP_TUNNEL_CSUM;
 		netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL |
@@ -4758,8 +4758,6 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	int err;
 
-	priv->vxlan = mlx5_vxlan_create(mdev);
-
 	mlx5e_build_nic_netdev_priv(mdev, netdev, profile, ppriv);
 	err = mlx5e_ipsec_init(priv);
 	if (err)
@@ -4773,7 +4771,6 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev,
 
 static void mlx5e_nic_cleanup(struct mlx5e_priv *priv)
 {
-	mlx5_vxlan_destroy(priv->vxlan);
 	mlx5e_tls_cleanup(priv);
 	mlx5e_ipsec_cleanup(priv);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 1b4931b62094..288a57f76e84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -50,7 +50,7 @@
 #include "en_rep.h"
 #include "en_tc.h"
 #include "eswitch.h"
-#include "vxlan.h"
+#include "lib/vxlan.h"
 #include "fs_core.h"
 #include "en/port.h"
 
@@ -1133,7 +1133,7 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
 			goto vxlan_match_offload_err;
 
-		if (mlx5_vxlan_lookup_port(up_priv->vxlan, be16_to_cpu(key->dst)) &&
+		if (mlx5_vxlan_lookup_port(up_priv->mdev->vxlan, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
 		else {
@@ -2557,7 +2557,7 @@ vxlan_encap_offload_err:
 		return -EOPNOTSUPP;
 	}
 
-	if (mlx5_vxlan_lookup_port(up_priv->vxlan, be16_to_cpu(key->tp_dst)) &&
+	if (mlx5_vxlan_lookup_port(up_priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		tunnel_type = MLX5_HEADER_TYPE_VXLAN;
 	} else {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
new file mode 100644
index 000000000000..9a8fd762167b
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c
@@ -0,0 +1,230 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mlx5/driver.h>
+#include "mlx5_core.h"
+#include "vxlan.h"
+
+struct mlx5_vxlan {
+	struct mlx5_core_dev		*mdev;
+	spinlock_t			lock; /* protect vxlan table */
+	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
+	DECLARE_HASHTABLE(htable, 4);
+	int				num_ports;
+	struct mutex                    sync_lock; /* sync add/del port HW operations */
+};
+
+struct mlx5_vxlan_port {
+	struct hlist_node hlist;
+	atomic_t refcount;
+	u16 udp_port;
+};
+
+static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4;
+}
+
+static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+{
+	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
+
+	MLX5_SET(add_vxlan_udp_dport_in, in, opcode,
+		 MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT);
+	MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port);
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
+{
+	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
+	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
+
+	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
+		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
+	MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port);
+	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
+}
+
+static struct mlx5_vxlan_port*
+mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+
+	hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) {
+		if (vxlanp->udp_port == port)
+			return vxlanp;
+	}
+
+	return NULL;
+}
+
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+
+	if (!mlx5_vxlan_allowed(vxlan))
+		return NULL;
+
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
+	spin_unlock_bh(&vxlan->lock);
+
+	return vxlanp;
+}
+
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	int ret = -ENOSPC;
+
+	vxlanp = mlx5_vxlan_lookup_port(vxlan, port);
+	if (vxlanp) {
+		atomic_inc(&vxlanp->refcount);
+		return 0;
+	}
+
+	mutex_lock(&vxlan->sync_lock);
+	if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) {
+		mlx5_core_info(vxlan->mdev,
+			       "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
+			       port, mlx5_vxlan_max_udp_ports(vxlan->mdev));
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port);
+	if (ret)
+		goto unlock;
+
+	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
+	if (!vxlanp) {
+		ret = -ENOMEM;
+		goto err_delete_port;
+	}
+
+	vxlanp->udp_port = port;
+	atomic_set(&vxlanp->refcount, 1);
+
+	spin_lock_bh(&vxlan->lock);
+	hash_add(vxlan->htable, &vxlanp->hlist, port);
+	spin_unlock_bh(&vxlan->lock);
+
+	vxlan->num_ports++;
+	mutex_unlock(&vxlan->sync_lock);
+	return 0;
+
+err_delete_port:
+	mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+
+unlock:
+	mutex_unlock(&vxlan->sync_lock);
+	return ret;
+}
+
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	bool remove = false;
+	int ret = 0;
+
+	mutex_lock(&vxlan->sync_lock);
+
+	spin_lock_bh(&vxlan->lock);
+	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
+	if (!vxlanp) {
+		ret = -ENOENT;
+		goto out_unlock;
+	}
+
+	if (atomic_dec_and_test(&vxlanp->refcount)) {
+		hash_del(&vxlanp->hlist);
+		remove = true;
+	}
+
+out_unlock:
+	spin_unlock_bh(&vxlan->lock);
+
+	if (remove) {
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
+		kfree(vxlanp);
+		vxlan->num_ports--;
+	}
+
+	mutex_unlock(&vxlan->sync_lock);
+
+	return ret;
+}
+
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_vxlan *vxlan;
+
+	if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev))
+		return ERR_PTR(-ENOTSUPP);
+
+	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
+	if (!vxlan)
+		return ERR_PTR(-ENOMEM);
+
+	vxlan->mdev = mdev;
+	mutex_init(&vxlan->sync_lock);
+	spin_lock_init(&vxlan->lock);
+	hash_init(vxlan->htable);
+
+	/* Hardware adds 4789 by default */
+	mlx5_vxlan_add_port(vxlan, 4789);
+
+	return vxlan;
+}
+
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
+{
+	struct mlx5_vxlan_port *vxlanp;
+	struct hlist_node *tmp;
+	int bkt;
+
+	if (!mlx5_vxlan_allowed(vxlan))
+		return;
+
+	/* Lockless since we are the only hash table consumers*/
+	hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
+		hash_del(&vxlanp->hlist);
+		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
+		kfree(vxlanp);
+	}
+
+	kfree(vxlan);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
new file mode 100644
index 000000000000..fd874a30c4d0
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
@@ -0,0 +1,64 @@
+/*
+ * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef __MLX5_VXLAN_H__
+#define __MLX5_VXLAN_H__
+
+#include <linux/mlx5/driver.h>
+
+struct mlx5_vxlan;
+struct mlx5_vxlan_port;
+
+#ifdef CONFIG_MLX5_CORE_EN
+
+static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
+{
+	/* not allowed reason is encoded in vxlan pointer as error,
+	 * on mlx5_vxlan_create
+	 */
+	return !IS_ERR_OR_NULL(vxlan);
+}
+
+struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
+void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
+int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
+int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
+struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
+
+#else
+
+static inline struct mlx5_vxlan*
+mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); }
+static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
+
+#endif
+
+#endif /* __MLX5_VXLAN_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 6ddbb70e95de..03b9c6733eed 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -62,6 +62,7 @@
 #include "accel/ipsec.h"
 #include "accel/tls.h"
 #include "lib/clock.h"
+#include "lib/vxlan.h"
 #include "diag/fw_tracer.h"
 
 MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>");
@@ -961,6 +962,8 @@ static int mlx5_init_once(struct mlx5_core_dev *dev, struct mlx5_priv *priv)
 
 	mlx5_init_clock(dev);
 
+	dev->vxlan = mlx5_vxlan_create(dev);
+
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init rate limiting\n");
@@ -1004,6 +1007,7 @@ err_mpfs_cleanup:
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
 err_tables_cleanup:
+	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_mkey_table(dev);
 	mlx5_cleanup_srq_table(dev);
 	mlx5_cleanup_qp_table(dev);
@@ -1024,6 +1028,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_eswitch_cleanup(dev->priv.eswitch);
 	mlx5_mpfs_cleanup(dev);
 	mlx5_cleanup_rl_table(dev);
+	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cleanup_mkey_table(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
deleted file mode 100644
index 9a8fd762167b..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.c
+++ /dev/null
@@ -1,230 +0,0 @@
-/*
- * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mlx5/driver.h>
-#include "mlx5_core.h"
-#include "vxlan.h"
-
-struct mlx5_vxlan {
-	struct mlx5_core_dev		*mdev;
-	spinlock_t			lock; /* protect vxlan table */
-	/* max_num_ports is usuallly 4, 16 buckets is more than enough */
-	DECLARE_HASHTABLE(htable, 4);
-	int				num_ports;
-	struct mutex                    sync_lock; /* sync add/del port HW operations */
-};
-
-struct mlx5_vxlan_port {
-	struct hlist_node hlist;
-	atomic_t refcount;
-	u16 udp_port;
-};
-
-static inline u8 mlx5_vxlan_max_udp_ports(struct mlx5_core_dev *mdev)
-{
-	return MLX5_CAP_ETH(mdev, max_vxlan_udp_ports) ?: 4;
-}
-
-static int mlx5_vxlan_core_add_port_cmd(struct mlx5_core_dev *mdev, u16 port)
-{
-	u32 in[MLX5_ST_SZ_DW(add_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(add_vxlan_udp_dport_out)] = {0};
-
-	MLX5_SET(add_vxlan_udp_dport_in, in, opcode,
-		 MLX5_CMD_OP_ADD_VXLAN_UDP_DPORT);
-	MLX5_SET(add_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-}
-
-static int mlx5_vxlan_core_del_port_cmd(struct mlx5_core_dev *mdev, u16 port)
-{
-	u32 in[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_in)]   = {0};
-	u32 out[MLX5_ST_SZ_DW(delete_vxlan_udp_dport_out)] = {0};
-
-	MLX5_SET(delete_vxlan_udp_dport_in, in, opcode,
-		 MLX5_CMD_OP_DELETE_VXLAN_UDP_DPORT);
-	MLX5_SET(delete_vxlan_udp_dport_in, in, vxlan_udp_port, port);
-	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
-}
-
-static struct mlx5_vxlan_port*
-mlx5_vxlan_lookup_port_locked(struct mlx5_vxlan *vxlan, u16 port)
-{
-	struct mlx5_vxlan_port *vxlanp;
-
-	hash_for_each_possible(vxlan->htable, vxlanp, hlist, port) {
-		if (vxlanp->udp_port == port)
-			return vxlanp;
-	}
-
-	return NULL;
-}
-
-struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port)
-{
-	struct mlx5_vxlan_port *vxlanp;
-
-	if (!mlx5_vxlan_allowed(vxlan))
-		return NULL;
-
-	spin_lock_bh(&vxlan->lock);
-	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
-	spin_unlock_bh(&vxlan->lock);
-
-	return vxlanp;
-}
-
-int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port)
-{
-	struct mlx5_vxlan_port *vxlanp;
-	int ret = -ENOSPC;
-
-	vxlanp = mlx5_vxlan_lookup_port(vxlan, port);
-	if (vxlanp) {
-		atomic_inc(&vxlanp->refcount);
-		return 0;
-	}
-
-	mutex_lock(&vxlan->sync_lock);
-	if (vxlan->num_ports >= mlx5_vxlan_max_udp_ports(vxlan->mdev)) {
-		mlx5_core_info(vxlan->mdev,
-			       "UDP port (%d) not offloaded, max number of UDP ports (%d) are already offloaded\n",
-			       port, mlx5_vxlan_max_udp_ports(vxlan->mdev));
-		ret = -ENOSPC;
-		goto unlock;
-	}
-
-	ret = mlx5_vxlan_core_add_port_cmd(vxlan->mdev, port);
-	if (ret)
-		goto unlock;
-
-	vxlanp = kzalloc(sizeof(*vxlanp), GFP_KERNEL);
-	if (!vxlanp) {
-		ret = -ENOMEM;
-		goto err_delete_port;
-	}
-
-	vxlanp->udp_port = port;
-	atomic_set(&vxlanp->refcount, 1);
-
-	spin_lock_bh(&vxlan->lock);
-	hash_add(vxlan->htable, &vxlanp->hlist, port);
-	spin_unlock_bh(&vxlan->lock);
-
-	vxlan->num_ports++;
-	mutex_unlock(&vxlan->sync_lock);
-	return 0;
-
-err_delete_port:
-	mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
-
-unlock:
-	mutex_unlock(&vxlan->sync_lock);
-	return ret;
-}
-
-int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port)
-{
-	struct mlx5_vxlan_port *vxlanp;
-	bool remove = false;
-	int ret = 0;
-
-	mutex_lock(&vxlan->sync_lock);
-
-	spin_lock_bh(&vxlan->lock);
-	vxlanp = mlx5_vxlan_lookup_port_locked(vxlan, port);
-	if (!vxlanp) {
-		ret = -ENOENT;
-		goto out_unlock;
-	}
-
-	if (atomic_dec_and_test(&vxlanp->refcount)) {
-		hash_del(&vxlanp->hlist);
-		remove = true;
-	}
-
-out_unlock:
-	spin_unlock_bh(&vxlan->lock);
-
-	if (remove) {
-		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, port);
-		kfree(vxlanp);
-		vxlan->num_ports--;
-	}
-
-	mutex_unlock(&vxlan->sync_lock);
-
-	return ret;
-}
-
-struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev)
-{
-	struct mlx5_vxlan *vxlan;
-
-	if (!MLX5_CAP_ETH(mdev, tunnel_stateless_vxlan) || !mlx5_core_is_pf(mdev))
-		return ERR_PTR(-ENOTSUPP);
-
-	vxlan = kzalloc(sizeof(*vxlan), GFP_KERNEL);
-	if (!vxlan)
-		return ERR_PTR(-ENOMEM);
-
-	vxlan->mdev = mdev;
-	mutex_init(&vxlan->sync_lock);
-	spin_lock_init(&vxlan->lock);
-	hash_init(vxlan->htable);
-
-	/* Hardware adds 4789 by default */
-	mlx5_vxlan_add_port(vxlan, 4789);
-
-	return vxlan;
-}
-
-void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan)
-{
-	struct mlx5_vxlan_port *vxlanp;
-	struct hlist_node *tmp;
-	int bkt;
-
-	if (!mlx5_vxlan_allowed(vxlan))
-		return;
-
-	/* Lockless since we are the only hash table consumers*/
-	hash_for_each_safe(vxlan->htable, bkt, tmp, vxlanp, hlist) {
-		hash_del(&vxlanp->hlist);
-		mlx5_vxlan_core_del_port_cmd(vxlan->mdev, vxlanp->udp_port);
-		kfree(vxlanp);
-	}
-
-	kfree(vxlan);
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
deleted file mode 100644
index fd874a30c4d0..000000000000
--- a/drivers/net/ethernet/mellanox/mlx5/core/vxlan.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/*
- * Copyright (c) 2016, Mellanox Technologies, Ltd.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-#ifndef __MLX5_VXLAN_H__
-#define __MLX5_VXLAN_H__
-
-#include <linux/mlx5/driver.h>
-
-struct mlx5_vxlan;
-struct mlx5_vxlan_port;
-
-#ifdef CONFIG_MLX5_CORE_EN
-
-static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
-{
-	/* not allowed reason is encoded in vxlan pointer as error,
-	 * on mlx5_vxlan_create
-	 */
-	return !IS_ERR_OR_NULL(vxlan);
-}
-
-struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
-void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
-int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
-int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
-struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
-
-#else
-
-static inline struct mlx5_vxlan*
-mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); }
-static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
-
-#endif
-
-#endif /* __MLX5_VXLAN_H__ */
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index fd0aaa5568fe..54f385cc8811 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -818,6 +818,7 @@ struct mlx5_clock {
 };
 
 struct mlx5_fw_tracer;
+struct mlx5_vxlan;
 
 struct mlx5_core_dev {
 	struct pci_dev	       *pdev;
@@ -850,6 +851,7 @@ struct mlx5_core_dev {
 	atomic_t		num_qps;
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
+	struct mlx5_vxlan       *vxlan;
 	struct {
 		struct mlx5_rsvd_gids	reserved_gids;
 		u32			roce_en;
-- 
cgit v1.2.3


From a3e673660bc3fca3e9e0cbab871b2fb100e9ed64 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Sat, 19 May 2018 05:34:48 -0700
Subject: net/mlx5e: Issue direct lookup on vxlan ports by vport representors

Remove uplink representor netdevice private structure lookup, and use
mlx5 core handle directly from representor private structure to lookup
vxlan ports.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index 288a57f76e84..c28fe469b04a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -1124,16 +1124,12 @@ static int parse_tunnel_attr(struct mlx5e_priv *priv,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_ENC_PORTS,
 						  f->mask);
-		struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-		struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH);
-		struct net_device *up_dev = uplink_rpriv->netdev;
-		struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 
 		/* Full udp dst port must be given */
 		if (memchr_inv(&mask->dst, 0xff, sizeof(mask->dst)))
 			goto vxlan_match_offload_err;
 
-		if (mlx5_vxlan_lookup_port(up_priv->mdev->vxlan, be16_to_cpu(key->dst)) &&
+		if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->dst)) &&
 		    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap))
 			parse_vxlan_attr(spec, f);
 		else {
@@ -2533,11 +2529,7 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv,
 			      struct mlx5e_tc_flow *flow)
 {
 	struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
-	struct mlx5e_rep_priv *uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw,
-									   REP_ETH);
-	struct net_device *up_dev = uplink_rpriv->netdev;
 	unsigned short family = ip_tunnel_info_af(tun_info);
-	struct mlx5e_priv *up_priv = netdev_priv(up_dev);
 	struct mlx5_esw_flow_attr *attr = flow->esw_attr;
 	struct ip_tunnel_key *key = &tun_info->key;
 	struct mlx5e_encap_entry *e;
@@ -2557,7 +2549,7 @@ vxlan_encap_offload_err:
 		return -EOPNOTSUPP;
 	}
 
-	if (mlx5_vxlan_lookup_port(up_priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) &&
+	if (mlx5_vxlan_lookup_port(priv->mdev->vxlan, be16_to_cpu(key->tp_dst)) &&
 	    MLX5_CAP_ESW(priv->mdev, vxlan_encap_decap)) {
 		tunnel_type = MLX5_HEADER_TYPE_VXLAN;
 	} else {
-- 
cgit v1.2.3


From c0c04707033c71d0490a412b0a941d87011949a3 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 17 Jul 2018 17:46:17 +0200
Subject: thermal: samsung: Remove Exynos5440 clock handling left-overs

Commit 8014220d48e7 ("thermal: samsung: Remove support for Exynos5440")
removed the Exynos5440 specific part of code for accessing TMU interrupt
registers but the surrounding clock handling was left.

Clean it up.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Acked-by: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/samsung/exynos_tmu.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/thermal/samsung/exynos_tmu.c b/drivers/thermal/samsung/exynos_tmu.c
index a992e51ef065..48eef552cba4 100644
--- a/drivers/thermal/samsung/exynos_tmu.c
+++ b/drivers/thermal/samsung/exynos_tmu.c
@@ -789,11 +789,6 @@ static void exynos_tmu_work(struct work_struct *work)
 	struct exynos_tmu_data *data = container_of(work,
 			struct exynos_tmu_data, irq_work);
 
-	if (!IS_ERR(data->clk_sec))
-		clk_enable(data->clk_sec);
-	if (!IS_ERR(data->clk_sec))
-		clk_disable(data->clk_sec);
-
 	thermal_zone_device_update(data->tzd, THERMAL_EVENT_UNSPECIFIED);
 
 	mutex_lock(&data->lock);
-- 
cgit v1.2.3


From 542cdf4068049458e1411b120bd5a4bbe3ddc49a Mon Sep 17 00:00:00 2001
From: Simon Horman <horms+renesas@verge.net.au>
Date: Tue, 24 Jul 2018 13:14:13 +0200
Subject: thermal: rcar_thermal: avoid NULL dereference in absence of IRQ
 resources

Ensure that the base address used by a call to rcar_thermal_common_write()
may be NULL if the SOC supports interrupts for use with the thermal device
but none are defined in DT as is the case for R-Car H1 (r8a7779). Guard
against this condition to prevent a NULL dereference when the device is
probed.

Tested on:
* R-Mobile APE6 (r8a73a4) / APE6EVM
* R-Car H1 (r8a7779) / Marzen
* R-Car H2 (r8a7790) / Lager
* R-Car M2-W (r8a7791) / Koelsch
* R-Car M2-N (r8a7793) / Gose
* R-Car D3 ES1.0 (r8a77995) / Draak

Fixes: 1969d9dc2079 ("thermal: rcar_thermal: add r8a77995 support")
Signed-off-by: Simon Horman <horms+renesas@verge.net.au>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/rcar_thermal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c
index 45fb284d4c11..e77e63070e99 100644
--- a/drivers/thermal/rcar_thermal.c
+++ b/drivers/thermal/rcar_thermal.c
@@ -598,7 +598,7 @@ static int rcar_thermal_probe(struct platform_device *pdev)
 			enr_bits |= 3 << (i * 8);
 	}
 
-	if (enr_bits)
+	if (common->base && enr_bits)
 		rcar_thermal_common_write(common, ENR, enr_bits);
 
 	dev_info(dev, "%d sensor probed\n", i);
-- 
cgit v1.2.3


From 6b0709f5a50a98df5919ade32fd131dde10bdcb0 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 25 Jul 2018 14:16:10 +0900
Subject: ARM: at91: remove unused duplicated filechk_offsets

The filechk_offsets in arch/arm/mach-at91/Makefile is never
used because it is always overridden by the equivalent one in
scripts/Makefile.lib

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 arch/arm/mach-at91/Makefile | 25 -------------------------
 1 file changed, 25 deletions(-)

diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index 4ea93c9df77b..7415f181907b 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -19,31 +19,6 @@ ifeq ($(CONFIG_PM_DEBUG),y)
 CFLAGS_pm.o += -DDEBUG
 endif
 
-# Default sed regexp - multiline due to syntax constraints
-define sed-y
-	"/^->/{s:->#\(.*\):/* \1 */:; \
-	s:^->\([^ ]*\) [\$$#]*\([-0-9]*\) \(.*\):#define \1 \2 /* \3 */:; \
-	s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; \
-	s:->::; p;}"
-endef
-
-# Use filechk to avoid rebuilds when a header changes, but the resulting file
-# does not
-define filechk_offsets
-	(set -e; \
-	 echo "#ifndef $2"; \
-	 echo "#define $2"; \
-	 echo "/*"; \
-	 echo " * DO NOT MODIFY."; \
-	 echo " *"; \
-	 echo " * This file was generated by Kbuild"; \
-	 echo " */"; \
-	 echo ""; \
-	 sed -ne $(sed-y); \
-	 echo ""; \
-	 echo "#endif" )
-endef
-
 arch/arm/mach-at91/pm_data-offsets.s: arch/arm/mach-at91/pm_data-offsets.c
 	$(call if_changed_dep,cc_s_c)
 
-- 
cgit v1.2.3


From 43fee2b238959a7b46e2e8c0cd3305c7c044ded8 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 25 Jul 2018 14:16:11 +0900
Subject: kbuild: do not redirect the first prerequisite for filechk

Currently, filechk unconditionally opens the first prerequisite and
redirects it as the stdin of a filechk_* rule.  Hence, every target
using $(call filechk,...) must list something as the first prerequisite
even if it is unneeded.

'< $<' is actually unneeded in most cases.  Each rule can explicitly
adds it if necessary.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Makefile                           | 2 +-
 arch/s390/kernel/syscalls/Makefile | 6 +++---
 arch/um/Makefile                   | 2 +-
 scripts/Kbuild.include             | 2 +-
 scripts/Makefile.lib               | 2 +-
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/Makefile b/Makefile
index 433f87015c1d..bc3a65be9035 100644
--- a/Makefile
+++ b/Makefile
@@ -1117,7 +1117,7 @@ define filechk_version.h
 	echo '#define KERNEL_VERSION(a,b,c) (((a) << 16) + ((b) << 8) + (c))';)
 endef
 
-$(version_h): $(srctree)/Makefile FORCE
+$(version_h): FORCE
 	$(call filechk,version.h)
 	$(Q)rm -f $(old_version_h)
 
diff --git a/arch/s390/kernel/syscalls/Makefile b/arch/s390/kernel/syscalls/Makefile
index 8ff96c08955f..4d929edc80a6 100644
--- a/arch/s390/kernel/syscalls/Makefile
+++ b/arch/s390/kernel/syscalls/Makefile
@@ -25,15 +25,15 @@ _dummy := $(shell [ -d '$(uapi)' ] || mkdir -p '$(uapi)') \
 	  $(shell [ -d '$(kapi)' ] || mkdir -p '$(kapi)')
 
 define filechk_syshdr
-	$(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2"
+	$(CONFIG_SHELL) '$(systbl)' -H -a $(syshdr_abi_$(basetarget)) -f "$2" < $<
 endef
 
 define filechk_sysnr
-	$(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget))
+	$(CONFIG_SHELL) '$(systbl)' -N -a $(sysnr_abi_$(basetarget)) < $<
 endef
 
 define filechk_syscalls
-	$(CONFIG_SHELL) '$(systbl)' -S
+	$(CONFIG_SHELL) '$(systbl)' -S < $<
 endef
 
 syshdr_abi_unistd_32 := common,32
diff --git a/arch/um/Makefile b/arch/um/Makefile
index e54dda8a0363..8c35261f5706 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -169,7 +169,7 @@ define filechk_gen-asm-offsets
          echo " *"; \
          echo " */"; \
          echo ""; \
-         sed -ne "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}"; \
+         sed -ne "/^->/{s:^->\([^ ]*\) [\$$#]*\([^ ]*\) \(.*\):#define \1 \2 /* \3 */:; s:->::; p;}" < $<; \
          echo ""; )
 endef
 
diff --git a/scripts/Kbuild.include b/scripts/Kbuild.include
index 02bb3163cd8d..7eabe80cb9fb 100644
--- a/scripts/Kbuild.include
+++ b/scripts/Kbuild.include
@@ -56,7 +56,7 @@ kecho := $($(quiet)kecho)
 define filechk
 	$(Q)set -e;				\
 	mkdir -p $(dir $@);			\
-	$(filechk_$(1)) < $< > $@.tmp;		\
+	$(filechk_$(1)) > $@.tmp;		\
 	if [ -r $@ ] && cmp -s $@ $@.tmp; then	\
 		rm -f $@.tmp;			\
 	else					\
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index f56bb4b8bc60..df0fff252619 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -415,7 +415,7 @@ define filechk_offsets
 	 echo " * This file was generated by Kbuild"; \
 	 echo " */"; \
 	 echo ""; \
-	 sed -ne $(sed-offsets); \
+	 sed -ne $(sed-offsets) < $<; \
 	 echo ""; \
 	 echo "#endif" )
 endef
-- 
cgit v1.2.3


From f2abcc13e4a1b3139f1e3a0ca71bf4db8b7dfe72 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:20:28 +0100
Subject: builddeb: Skip architecture detection when KBUILD_DEBARCH is set

If KBUILD_DEBARCH is set then we will not use the result of
architecture detection, and we may also warn unnecessarily.
Move the check for KBUILD_DEBARCH further up to avoid this.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 985d72d1ab34..434f0b4d5231 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -7,6 +7,11 @@
 set -e
 
 set_debarch() {
+	if [ -n "$KBUILD_DEBARCH" ] ; then
+		debarch="$KBUILD_DEBARCH"
+		return
+	fi
+
 	# Attempt to find the correct Debian architecture
 	case "$UTS_MACHINE" in
 	i386|ia64|alpha)
@@ -46,10 +51,8 @@ set_debarch() {
 		echo "Falling back to using your current userspace instead!" >&2
 		echo "Please add support for $UTS_MACHINE to ${0} ..." >&2
 		echo "" >&2
+		;;
 	esac
-	if [ -n "$KBUILD_DEBARCH" ] ; then
-		debarch="$KBUILD_DEBARCH"
-	fi
 }
 
 # Some variables and settings used throughout the script
-- 
cgit v1.2.3


From 091d30aefc8a4d76ffa139a6e51dc237ea1cd599 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:20:45 +0100
Subject: builddeb: Change architecture detection fallback to use
 dpkg-architecture

We currently use dpkg --print-architecture, which reports the
architecture of the build machine.  We can make a better guess
than this by asking dpkg-architecture what the host architecture,
i.e. the default architecture for building packages, is.  This is
sensitive to environment variables such as CC and DEB_HOST_ARCH,
which should already be set in a cross-build environment.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 434f0b4d5231..389bf983879d 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -42,13 +42,13 @@ set_debarch() {
 		fi
 		;;
 	*)
-		debarch=$(dpkg --print-architecture)
+		debarch=$(dpkg-architecture -qDEB_HOST_ARCH)
 		echo "" >&2
 		echo "** ** **  WARNING  ** ** **" >&2
 		echo "" >&2
 		echo "Your architecture doesn't have its equivalent" >&2
 		echo "Debian userspace architecture defined!" >&2
-		echo "Falling back to using your current userspace instead!" >&2
+		echo "Falling back to the current host architecture ($debarch)." >&2
 		echo "Please add support for $UTS_MACHINE to ${0} ..." >&2
 		echo "" >&2
 		;;
-- 
cgit v1.2.3


From 4260ecd0ad8c10cef8ff6551267bb351e10f70c9 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:20:54 +0100
Subject: builddeb: Drop check for 32-bit s390

s390 now only supports 64-bit configurations.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 389bf983879d..f4449b575379 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -21,7 +21,7 @@ set_debarch() {
 	sparc*)
 		debarch=sparc ;;
 	s390*)
-		debarch=s390$(grep -q CONFIG_64BIT=y $KCONFIG_CONFIG && echo x || true) ;;
+		debarch=s390x ;;
 	ppc*)
 		debarch=$(grep -q CPU_LITTLE_ENDIAN=y $KCONFIG_CONFIG && echo ppc64el || echo powerpc) ;;
 	parisc*)
-- 
cgit v1.2.3


From 08d3892cdcea7e918106bd78be5471d05b000b30 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:21:01 +0100
Subject: builddeb: Introduce functions to simplify kconfig tests in
 set_debarch

We now have many repetitive greps over the kernel config.  Refactor
them into functions.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index f4449b575379..ada3c73d1493 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -6,6 +6,18 @@
 
 set -e
 
+is_enabled() {
+	grep -q "^CONFIG_$1=y" $KCONFIG_CONFIG
+}
+
+if_enabled_echo() {
+	if is_enabled "$1"; then
+		echo -n "$2"
+	elif [ $# -ge 3 ]; then
+		echo -n "$3"
+	fi
+}
+
 set_debarch() {
 	if [ -n "$KBUILD_DEBARCH" ] ; then
 		debarch="$KBUILD_DEBARCH"
@@ -23,22 +35,18 @@ set_debarch() {
 	s390*)
 		debarch=s390x ;;
 	ppc*)
-		debarch=$(grep -q CPU_LITTLE_ENDIAN=y $KCONFIG_CONFIG && echo ppc64el || echo powerpc) ;;
+		debarch=$(if_enabled_echo CPU_LITTLE_ENDIAN ppc64el powerpc) ;;
 	parisc*)
 		debarch=hppa ;;
 	mips*)
-		debarch=mips$(grep -q CPU_LITTLE_ENDIAN=y $KCONFIG_CONFIG && echo el || true) ;;
+		debarch=mips$(if_enabled_echo CPU_LITTLE_ENDIAN el) ;;
 	aarch64|arm64)
 		debarch=arm64 ;;
 	arm*)
-		if grep -q CONFIG_AEABI=y $KCONFIG_CONFIG; then
-		    if grep -q CONFIG_VFP=y $KCONFIG_CONFIG; then
-			debarch=armhf
-		    else
-			debarch=armel
-		    fi
+		if is_enabled AEABI; then
+			debarch=arm$(if_enabled_echo VFP hf el)
 		else
-		    debarch=arm
+			debarch=arm
 		fi
 		;;
 	*)
-- 
cgit v1.2.3


From 50d511ba6246c46654857b8ef64aefe76a87e455 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:21:09 +0100
Subject: builddeb: Add automatic support for ppc64 and powerpcspe
 architectures

We currently label 64-bit big-endian kernel packages as
powerpc (32-bit), mostly because it was officially supported while
ppc64 (64-bit big-endian) was not.  Now neither is officially
supported, so label these packages as ppc64.

Debian also has a powerpcspe (32-bit with SPE) architecture.
Label packages with a suitable configuration as powerpcspe.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index ada3c73d1493..0891974f499b 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -35,7 +35,12 @@ set_debarch() {
 	s390*)
 		debarch=s390x ;;
 	ppc*)
-		debarch=$(if_enabled_echo CPU_LITTLE_ENDIAN ppc64el powerpc) ;;
+		if is_enabled 64BIT; then
+			debarch=ppc64$(if_enabled_echo CPU_LITTLE_ENDIAN el)
+		else
+			debarch=powerpc$(if_enabled_echo SPE spe)
+		fi
+		;;
 	parisc*)
 		debarch=hppa ;;
 	mips*)
-- 
cgit v1.2.3


From 159b37942286b32aa1c08620b3a1ed2dace7d047 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:21:16 +0100
Subject: builddeb: Add automatic support for mips64el architecture

We currently label 64-bit little-endian kernel packages as
mipsel (32-bit little-endian), mostly it was officially supported
while mips64el (64-bit little-endian) was not.  Now both are
officially supported, so label these packages as mips64el.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 0891974f499b..350724cdc5af 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -44,7 +44,12 @@ set_debarch() {
 	parisc*)
 		debarch=hppa ;;
 	mips*)
-		debarch=mips$(if_enabled_echo CPU_LITTLE_ENDIAN el) ;;
+		if is_enabled CPU_LITTLE_ENDIAN; then
+			debarch=mips$(if_enabled_echo 64BIT 64)el
+		else
+			debarch=mips
+		fi
+		;;
 	aarch64|arm64)
 		debarch=arm64 ;;
 	arm*)
-- 
cgit v1.2.3


From 679caaf3f79f0adad3b6b6b02539b868a963f46d Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:22:20 +0100
Subject: builddeb: Add automatic support for mips{,64}r6{,el} architectures

MIPS R6 is not fully backward-compatible, so Debian has separate
architecture names for userland built for R6.  Label kernel
packages accordingly.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 350724cdc5af..595482923844 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -45,7 +45,9 @@ set_debarch() {
 		debarch=hppa ;;
 	mips*)
 		if is_enabled CPU_LITTLE_ENDIAN; then
-			debarch=mips$(if_enabled_echo 64BIT 64)el
+			debarch=mips$(if_enabled_echo 64BIT 64)$(if_enabled_echo CPU_MIPSR6 r6)el
+		elif is_enabled CPU_MIPSR6; then
+			debarch=mips$(if_enabled_echo 64BIT 64)r6
 		else
 			debarch=mips
 		fi
-- 
cgit v1.2.3


From a27ae285d5efb6d41f70f504dddadaca560de476 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:22:27 +0100
Subject: builddeb: Add automatic support for sparc64 architecture

We currently label 64-bit kernel packages as sparc (32-bit), mostly
because it was officially supported while sparc64 was not.  Now
neither is officially supported, so label these packages as sparc64.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 595482923844..83179a4c6fda 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -31,7 +31,7 @@ set_debarch() {
 	x86_64)
 		debarch=amd64 ;;
 	sparc*)
-		debarch=sparc ;;
+		debarch=sparc$(if_enabled_echo 64BIT 64) ;;
 	s390*)
 		debarch=s390x ;;
 	ppc*)
-- 
cgit v1.2.3


From 822f44fb5bf456f7032c2b428158d51b5fda1e99 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:22:34 +0100
Subject: builddeb: Add automatic support for or1k architecture

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 83179a4c6fda..fb0d3056f3e2 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -61,6 +61,8 @@ set_debarch() {
 			debarch=arm
 		fi
 		;;
+	openrisc)
+		debarch=or1k ;;
 	*)
 		debarch=$(dpkg-architecture -qDEB_HOST_ARCH)
 		echo "" >&2
-- 
cgit v1.2.3


From 60ca40a0649b462c7b398c6c603433faa0f56e26 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:22:42 +0100
Subject: builddeb: Add automatic support for m68k architecture

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index fb0d3056f3e2..470899fa3a8c 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -26,7 +26,7 @@ set_debarch() {
 
 	# Attempt to find the correct Debian architecture
 	case "$UTS_MACHINE" in
-	i386|ia64|alpha)
+	i386|ia64|alpha|m68k)
 		debarch="$UTS_MACHINE" ;;
 	x86_64)
 		debarch=amd64 ;;
-- 
cgit v1.2.3


From 75ebcee7699739c0f6c63abcb9f5754538107c62 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:22:47 +0100
Subject: builddeb: Add automatic support for riscv* architectures

Debian currently only defines "riscv64", but it seems safe to assume
that any 32-bit port will now be called "riscv32", also matching
$UTS_MACHINE.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 470899fa3a8c..3ef2fd0c5086 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -26,7 +26,7 @@ set_debarch() {
 
 	# Attempt to find the correct Debian architecture
 	case "$UTS_MACHINE" in
-	i386|ia64|alpha|m68k)
+	i386|ia64|alpha|m68k|riscv*)
 		debarch="$UTS_MACHINE" ;;
 	x86_64)
 		debarch=amd64 ;;
-- 
cgit v1.2.3


From 79a85b55e39e65d6f20c753c4ae8bcd6f4cd7007 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Thu, 26 Jul 2018 11:22:54 +0100
Subject: builddeb: Add automatic support for sh{3,4}{,eb} architectures

Different generations of the SH architecture are not very compatible,
so there are/were separate Debian ports for SH3 and SH4.

Move the fallback out of the "case" statement, so that it will also be
used in case we find some SH architecture version without a known
mapping.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/package/mkdebian | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/scripts/package/mkdebian b/scripts/package/mkdebian
index 3ef2fd0c5086..663a7f343b42 100755
--- a/scripts/package/mkdebian
+++ b/scripts/package/mkdebian
@@ -63,7 +63,15 @@ set_debarch() {
 		;;
 	openrisc)
 		debarch=or1k ;;
-	*)
+	sh)
+		if is_enabled CPU_SH3; then
+			debarch=sh3$(if_enabled_echo CPU_BIG_ENDIAN eb)
+		elif is_enabled CPU_SH4; then
+			debarch=sh4$(if_enabled_echo CPU_BIG_ENDIAN eb)
+		fi
+		;;
+	esac
+	if [ -z "$debarch" ]; then
 		debarch=$(dpkg-architecture -qDEB_HOST_ARCH)
 		echo "" >&2
 		echo "** ** **  WARNING  ** ** **" >&2
@@ -73,8 +81,7 @@ set_debarch() {
 		echo "Falling back to the current host architecture ($debarch)." >&2
 		echo "Please add support for $UTS_MACHINE to ${0} ..." >&2
 		echo "" >&2
-		;;
-	esac
+	fi
 }
 
 # Some variables and settings used throughout the script
-- 
cgit v1.2.3


From 24babe69d7ff8d3845fac49b741b7257fb03f906 Mon Sep 17 00:00:00 2001
From: Alban Bedel <albeu@free.fr>
Date: Tue, 14 Feb 2017 00:10:37 +0100
Subject: MIPS: ath79: Use the IRQ based GPIO key driver for the buttons

Now that the GPIO driver support interrupts we don't need to poll the
buttons.

Signed-off-by: Alban Bedel <albeu@free.fr>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/15283/
Cc: linux-mips@linux-mips.org
Cc: Rob Herring <robh+dt@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Antony Pavlov <antonynpavlov@gmail.com>
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts | 3 +--
 arch/mips/boot/dts/qca/ar9331_dpt_module.dts     | 5 ++---
 arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts   | 5 ++---
 arch/mips/boot/dts/qca/ar9331_omega.dts          | 5 ++---
 arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts      | 5 ++---
 5 files changed, 9 insertions(+), 14 deletions(-)

diff --git a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
index 3931033e47c8..7fccf6357225 100644
--- a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
+++ b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
@@ -22,11 +22,10 @@
 	};
 
 	gpio-keys {
-		compatible = "gpio-keys-polled";
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
 
-		poll-interval = <20>;
 		button@0 {
 			label = "reset";
 			linux,code = <KEY_RESTART>;
diff --git a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
index d4e4502daaa8..e7af2cf5f4c1 100644
--- a/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
+++ b/arch/mips/boot/dts/qca/ar9331_dpt_module.dts
@@ -29,11 +29,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "reset";
diff --git a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
index 4f95ccf17c4c..d38aa73f1a2e 100644
--- a/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
+++ b/arch/mips/boot/dts/qca/ar9331_dragino_ms14.dts
@@ -47,11 +47,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "jumpstart";
diff --git a/arch/mips/boot/dts/qca/ar9331_omega.dts b/arch/mips/boot/dts/qca/ar9331_omega.dts
index f70f79c4d0d5..11778abacf66 100644
--- a/arch/mips/boot/dts/qca/ar9331_omega.dts
+++ b/arch/mips/boot/dts/qca/ar9331_omega.dts
@@ -29,11 +29,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "reset";
diff --git a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
index 748131aea22e..c8290d36cfbe 100644
--- a/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
+++ b/arch/mips/boot/dts/qca/ar9331_tl_mr3020.dts
@@ -47,11 +47,10 @@
 		};
 	};
 
-	gpio-keys-polled {
-		compatible = "gpio-keys-polled";
+	gpio-keys {
+		compatible = "gpio-keys";
 		#address-cells = <1>;
 		#size-cells = <0>;
-		poll-interval = <100>;
 
 		button@0 {
 			label = "wps";
-- 
cgit v1.2.3


From 351fdddd366245c0fb4636f32edfb4198c8d6b8c Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Tue, 12 Dec 2017 09:57:47 +0000
Subject: MIPS: VDSO: Prevent use of smp_processor_id()

VDSO code should not be using smp_processor_id(), since it is executed
in user mode.
Introduce a VDSO-specific path which will cause a compile-time
or link-time error (depending upon support for __compiletime_error) if
the VDSO ever incorrectly attempts to use smp_processor_id().

[Matt Redfearn <matt.redfearn@imgtec.com>: Move before change to
smp_processor_id in series]

Signed-off-by: Paul Burton <paul.burton@mips.com>
Signed-off-by: Matt Redfearn <matt.redfearn@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/17932/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/smp.h | 12 +++++++++++-
 arch/mips/vdso/Makefile     |  3 ++-
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/arch/mips/include/asm/smp.h b/arch/mips/include/asm/smp.h
index 88ebd83b3bf9..056a6bf13491 100644
--- a/arch/mips/include/asm/smp.h
+++ b/arch/mips/include/asm/smp.h
@@ -25,7 +25,17 @@ extern cpumask_t cpu_sibling_map[];
 extern cpumask_t cpu_core_map[];
 extern cpumask_t cpu_foreign_map[];
 
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+static inline int raw_smp_processor_id(void)
+{
+#if defined(__VDSO__)
+	extern int vdso_smp_processor_id(void)
+		__compiletime_error("VDSO should not call smp_processor_id()");
+	return vdso_smp_processor_id();
+#else
+	return current_thread_info()->cpu;
+#endif
+}
+#define raw_smp_processor_id raw_smp_processor_id
 
 /* Map from cpu id to sequential logical cpu number.  This will only
    not be idempotent when cpus failed to come on-line.	*/
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index ce196046ac3e..477c463c89ec 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -7,7 +7,8 @@ ccflags-vdso := \
 	$(filter -I%,$(KBUILD_CFLAGS)) \
 	$(filter -E%,$(KBUILD_CFLAGS)) \
 	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
-	$(filter -march=%,$(KBUILD_CFLAGS))
+	$(filter -march=%,$(KBUILD_CFLAGS)) \
+	-D__VDSO__
 cflags-vdso := $(ccflags-vdso) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
 	-O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
-- 
cgit v1.2.3


From b1259519e618d479ede8a0db5474b3aff99f5056 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Sat, 16 Jun 2018 09:06:33 +0200
Subject: MIPS: Octeon: add missing of_node_put()

The call to of_find_node_by_name returns a node pointer with refcount
incremented thus it must be explicitly decremented here after the last
usage.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19558/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/cavium-octeon/octeon-platform.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/mips/cavium-octeon/octeon-platform.c b/arch/mips/cavium-octeon/octeon-platform.c
index 2940e9cc3a04..807cadaf554e 100644
--- a/arch/mips/cavium-octeon/octeon-platform.c
+++ b/arch/mips/cavium-octeon/octeon-platform.c
@@ -322,6 +322,7 @@ static int __init octeon_ehci_device_init(void)
 		return 0;
 
 	pd = of_find_device_by_node(ehci_node);
+	of_node_put(ehci_node);
 	if (!pd)
 		return 0;
 
@@ -384,6 +385,7 @@ static int __init octeon_ohci_device_init(void)
 		return 0;
 
 	pd = of_find_device_by_node(ohci_node);
+	of_node_put(ohci_node);
 	if (!pd)
 		return 0;
 
-- 
cgit v1.2.3


From 28ec2238f37e72a3a40a7eb46893e7651bcc40a6 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Wed, 11 Jul 2018 20:32:45 +0200
Subject: MIPS: generic: fix missing of_node_put()

of_find_compatible_node() returns a device_node pointer with refcount
incremented and must be decremented explicitly.
 As this code is using the result only to check presence of the interrupt
controller (!NULL) but not actually using the result otherwise the
refcount can be decremented here immediately again.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/19820/
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
---
 arch/mips/generic/init.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/generic/init.c b/arch/mips/generic/init.c
index 07ec08462d70..a106f8113842 100644
--- a/arch/mips/generic/init.c
+++ b/arch/mips/generic/init.c
@@ -203,6 +203,7 @@ void __init arch_init_irq(void)
 					    "mti,cpu-interrupt-controller");
 	if (!cpu_has_veic && !intc_node)
 		mips_cpu_irq_init();
+	of_node_put(intc_node);
 
 	irqchip_init();
 }
-- 
cgit v1.2.3


From cc26c6ef58c781473090ce45e17e4b5ff7bd8b2a Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Date: Tue, 5 Jun 2018 22:22:58 +0300
Subject: tpm: migrate tpm2_shutdown() to use struct tpm_buf

In order to make struct tpm_buf the first class object for constructing TPM
commands, migrated tpm2_shutdown() to use it.

Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Reviewed-by: Nayna Jain <nayna@linux.vnet.ibm.com>
Tested-by: Nayna Jain <nayna@linux.vnet.ibm.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
---
 drivers/char/tpm/tpm2-cmd.c | 47 +++++++++++++++------------------------------
 1 file changed, 15 insertions(+), 32 deletions(-)

diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index d31b09099216..026fec4e1800 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -27,10 +27,6 @@ enum tpm2_session_attributes {
 	TPM2_SA_CONTINUE_SESSION	= BIT(0),
 };
 
-struct tpm2_startup_in {
-	__be16	startup_type;
-} __packed;
-
 struct tpm2_get_tpm_pt_in {
 	__be32	cap_id;
 	__be32	property_id;
@@ -55,7 +51,6 @@ struct tpm2_get_random_out {
 } __packed;
 
 union tpm2_cmd_params {
-	struct	tpm2_startup_in		startup_in;
 	struct	tpm2_get_tpm_pt_in	get_tpm_pt_in;
 	struct	tpm2_get_tpm_pt_out	get_tpm_pt_out;
 	struct	tpm2_get_random_in	getrandom_in;
@@ -762,40 +757,28 @@ ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,  u32 *value,
 }
 EXPORT_SYMBOL_GPL(tpm2_get_tpm_pt);
 
-#define TPM2_SHUTDOWN_IN_SIZE \
-	(sizeof(struct tpm_input_header) + \
-	 sizeof(struct tpm2_startup_in))
-
-static const struct tpm_input_header tpm2_shutdown_header = {
-	.tag = cpu_to_be16(TPM2_ST_NO_SESSIONS),
-	.length = cpu_to_be32(TPM2_SHUTDOWN_IN_SIZE),
-	.ordinal = cpu_to_be32(TPM2_CC_SHUTDOWN)
-};
-
 /**
- * tpm2_shutdown() - send shutdown command to the TPM chip
+ * tpm2_shutdown() - send a TPM shutdown command
  *
- * @chip:		TPM chip to use.
- * @shutdown_type:	shutdown type. The value is either
- *			TPM_SU_CLEAR or TPM_SU_STATE.
+ * Sends a TPM shutdown command. The shutdown command is used in call
+ * sites where the system is going down. If it fails, there is not much
+ * that can be done except print an error message.
+ *
+ * @chip:		a &tpm_chip instance
+ * @shutdown_type:	TPM_SU_CLEAR or TPM_SU_STATE.
  */
 void tpm2_shutdown(struct tpm_chip *chip, u16 shutdown_type)
 {
-	struct tpm2_cmd cmd;
+	struct tpm_buf buf;
 	int rc;
 
-	cmd.header.in = tpm2_shutdown_header;
-	cmd.params.startup_in.startup_type = cpu_to_be16(shutdown_type);
-
-	rc = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd), 0, 0,
-			      "stopping the TPM");
-
-	/* In places where shutdown command is sent there's no much we can do
-	 * except print the error code on a system failure.
-	 */
-	if (rc < 0 && rc != -EPIPE)
-		dev_warn(&chip->dev, "transmit returned %d while stopping the TPM",
-			 rc);
+	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_SHUTDOWN);
+	if (rc)
+		return;
+	tpm_buf_append_u16(&buf, shutdown_type);
+	tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0,
+			 "stopping the TPM");
+	tpm_buf_destroy(&buf);
 }
 
 /*
-- 
cgit v1.2.3


From 94e266ba1fa344631dca424b7c83370c8c22983d Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Date: Mon, 26 Mar 2018 15:14:04 +0300
Subject: tpm: migrate tpm2_probe() to use struct tpm_buf

In order to make struct tpm_buf the first class object for constructing TPM
commands, migrate tpm2_probe() to use it.

Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Acked-by: Jay Freyensee <why2jjj.linux@gmail.com>
Reviewed-by: Nayna Jain <nayna@linux.vnet.ibm.com>
Tested-by: Nayna Jain <nayna@linux.vnet.ibm.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
---
 drivers/char/tpm/tpm2-cmd.c | 40 +++++++++++++++++++++++-----------------
 1 file changed, 23 insertions(+), 17 deletions(-)

diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index 026fec4e1800..b82e2b141754 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -846,31 +846,37 @@ static int tpm2_do_selftest(struct tpm_chip *chip)
 }
 
 /**
- * tpm2_probe() - probe TPM 2.0
- * @chip: TPM chip to use
+ * tpm2_probe() - probe for the TPM 2.0 protocol
+ * @chip:	a &tpm_chip instance
  *
- * Return: < 0 error and 0 on success.
+ * Send an idempotent TPM 2.0 command and see whether there is TPM2 chip in the
+ * other end based on the response tag. The flag TPM_CHIP_FLAG_TPM2 is set by
+ * this function if this is the case.
  *
- * Send idempotent TPM 2.0 command and see whether TPM 2.0 chip replied based on
- * the reply tag.
+ * Return:
+ *   0 on success,
+ *   -errno otherwise
  */
 int tpm2_probe(struct tpm_chip *chip)
 {
-	struct tpm2_cmd cmd;
+	struct tpm_output_header *out;
+	struct tpm_buf buf;
 	int rc;
 
-	cmd.header.in = tpm2_get_tpm_pt_header;
-	cmd.params.get_tpm_pt_in.cap_id = cpu_to_be32(TPM2_CAP_TPM_PROPERTIES);
-	cmd.params.get_tpm_pt_in.property_id = cpu_to_be32(0x100);
-	cmd.params.get_tpm_pt_in.property_cnt = cpu_to_be32(1);
-
-	rc = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd), 0, 0, NULL);
-	if (rc <  0)
+	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY);
+	if (rc)
 		return rc;
-
-	if (be16_to_cpu(cmd.header.out.tag) == TPM2_ST_NO_SESSIONS)
-		chip->flags |= TPM_CHIP_FLAG_TPM2;
-
+	tpm_buf_append_u32(&buf, TPM2_CAP_TPM_PROPERTIES);
+	tpm_buf_append_u32(&buf, TPM_PT_TOTAL_COMMANDS);
+	tpm_buf_append_u32(&buf, 1);
+	rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0, NULL);
+	/* We ignore TPM return codes on purpose. */
+	if (rc >=  0) {
+		out = (struct tpm_output_header *)buf.data;
+		if (be16_to_cpu(out->tag) == TPM2_ST_NO_SESSIONS)
+			chip->flags |= TPM_CHIP_FLAG_TPM2;
+	}
+	tpm_buf_destroy(&buf);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(tpm2_probe);
-- 
cgit v1.2.3


From 2ab3241161b3c340617063beea199e9966ee90c9 Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Date: Mon, 26 Mar 2018 15:14:05 +0300
Subject: tpm: migrate tpm2_get_tpm_pt() to use struct tpm_buf

In order to make struct tpm_buf the first class object for constructing TPM
commands, migrate tpm2_get_tpm_pt() to use it.

Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Reviewed-by: Nayna Jain <nayna@linux.vnet.ibm.com>
Tested-by: Nayna Jain <nayna@linux.vnet.ibm.com>
Reviewed-by: Jerry Snitselaar <jsnitsel@redhat.com>
---
 drivers/char/tpm/tpm2-cmd.c | 69 ++++++++++++++++++---------------------------
 1 file changed, 27 insertions(+), 42 deletions(-)

diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index b82e2b141754..90e3b36cf0dc 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -27,20 +27,6 @@ enum tpm2_session_attributes {
 	TPM2_SA_CONTINUE_SESSION	= BIT(0),
 };
 
-struct tpm2_get_tpm_pt_in {
-	__be32	cap_id;
-	__be32	property_id;
-	__be32	property_cnt;
-} __packed;
-
-struct tpm2_get_tpm_pt_out {
-	u8	more_data;
-	__be32	subcap_id;
-	__be32	property_cnt;
-	__be32	property_id;
-	__be32	value;
-} __packed;
-
 struct tpm2_get_random_in {
 	__be16	size;
 } __packed;
@@ -51,8 +37,6 @@ struct tpm2_get_random_out {
 } __packed;
 
 union tpm2_cmd_params {
-	struct	tpm2_get_tpm_pt_in	get_tpm_pt_in;
-	struct	tpm2_get_tpm_pt_out	get_tpm_pt_out;
 	struct	tpm2_get_random_in	getrandom_in;
 	struct	tpm2_get_random_out	getrandom_out;
 };
@@ -379,19 +363,6 @@ int tpm2_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 	return total ? total : -EIO;
 }
 
-#define TPM2_GET_TPM_PT_IN_SIZE \
-	(sizeof(struct tpm_input_header) + \
-	 sizeof(struct tpm2_get_tpm_pt_in))
-
-#define TPM2_GET_TPM_PT_OUT_BODY_SIZE \
-	 sizeof(struct tpm2_get_tpm_pt_out)
-
-static const struct tpm_input_header tpm2_get_tpm_pt_header = {
-	.tag = cpu_to_be16(TPM2_ST_NO_SESSIONS),
-	.length = cpu_to_be32(TPM2_GET_TPM_PT_IN_SIZE),
-	.ordinal = cpu_to_be32(TPM2_CC_GET_CAPABILITY)
-};
-
 /**
  * tpm2_flush_context_cmd() - execute a TPM2_FlushContext command
  * @chip: TPM chip to use
@@ -728,31 +699,45 @@ out:
 	return rc;
 }
 
+struct tpm2_get_cap_out {
+	u8 more_data;
+	__be32 subcap_id;
+	__be32 property_cnt;
+	__be32 property_id;
+	__be32 value;
+} __packed;
+
 /**
  * tpm2_get_tpm_pt() - get value of a TPM_CAP_TPM_PROPERTIES type property
- * @chip:		TPM chip to use.
+ * @chip:		a &tpm_chip instance
  * @property_id:	property ID.
  * @value:		output variable.
  * @desc:		passed to tpm_transmit_cmd()
  *
- * Return: Same as with tpm_transmit_cmd.
+ * Return:
+ *   0 on success,
+ *   -errno or a TPM return code otherwise
  */
 ssize_t tpm2_get_tpm_pt(struct tpm_chip *chip, u32 property_id,  u32 *value,
 			const char *desc)
 {
-	struct tpm2_cmd cmd;
+	struct tpm2_get_cap_out *out;
+	struct tpm_buf buf;
 	int rc;
 
-	cmd.header.in = tpm2_get_tpm_pt_header;
-	cmd.params.get_tpm_pt_in.cap_id = cpu_to_be32(TPM2_CAP_TPM_PROPERTIES);
-	cmd.params.get_tpm_pt_in.property_id = cpu_to_be32(property_id);
-	cmd.params.get_tpm_pt_in.property_cnt = cpu_to_be32(1);
-
-	rc = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd),
-			      TPM2_GET_TPM_PT_OUT_BODY_SIZE, 0, desc);
-	if (!rc)
-		*value = be32_to_cpu(cmd.params.get_tpm_pt_out.value);
-
+	rc = tpm_buf_init(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_CAPABILITY);
+	if (rc)
+		return rc;
+	tpm_buf_append_u32(&buf, TPM2_CAP_TPM_PROPERTIES);
+	tpm_buf_append_u32(&buf, property_id);
+	tpm_buf_append_u32(&buf, 1);
+	rc = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE, 0, 0, NULL);
+	if (!rc) {
+		out = (struct tpm2_get_cap_out *)
+			&buf.data[TPM_HEADER_SIZE];
+		*value = be32_to_cpu(out->value);
+	}
+	tpm_buf_destroy(&buf);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(tpm2_get_tpm_pt);
-- 
cgit v1.2.3


From ce63c05b664e491b4cc79c713c68d8170bd0f581 Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Date: Mon, 26 Mar 2018 15:14:06 +0300
Subject: tpm: migrate tpm2_get_random() to use struct tpm_buf

In order to make struct tpm_buf the first class object for constructing
TPM commands, migrate tpm2_get_random() to use it. In addition, removed
remaining references to struct tpm2_cmd. All of them use it to acquire
the length of the response, which can be achieved by using
tpm_buf_length().

Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Tested-by: Nayna Jain<nayna@linux.vnet.ibm.com>
---
 drivers/char/tpm/tpm.h      |  19 +++++----
 drivers/char/tpm/tpm2-cmd.c | 102 ++++++++++++++++++--------------------------
 2 files changed, 51 insertions(+), 70 deletions(-)

diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 4426649e431c..9824cccb2c76 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -424,23 +424,24 @@ struct tpm_buf {
 	u8 *data;
 };
 
-static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal)
+static inline void tpm_buf_reset(struct tpm_buf *buf, u16 tag, u32 ordinal)
 {
 	struct tpm_input_header *head;
+	head = (struct tpm_input_header *)buf->data;
+	head->tag = cpu_to_be16(tag);
+	head->length = cpu_to_be32(sizeof(*head));
+	head->ordinal = cpu_to_be32(ordinal);
+}
 
+static inline int tpm_buf_init(struct tpm_buf *buf, u16 tag, u32 ordinal)
+{
 	buf->data_page = alloc_page(GFP_HIGHUSER);
 	if (!buf->data_page)
 		return -ENOMEM;
 
 	buf->flags = 0;
 	buf->data = kmap(buf->data_page);
-
-	head = (struct tpm_input_header *) buf->data;
-
-	head->tag = cpu_to_be16(tag);
-	head->length = cpu_to_be32(sizeof(*head));
-	head->ordinal = cpu_to_be32(ordinal);
-
+	tpm_buf_reset(buf, tag, ordinal);
 	return 0;
 }
 
@@ -569,7 +570,7 @@ static inline u32 tpm2_rc_value(u32 rc)
 int tpm2_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf);
 int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, u32 count,
 		    struct tpm2_digest *digests);
-int tpm2_get_random(struct tpm_chip *chip, u8 *out, size_t max);
+int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max);
 void tpm2_flush_context_cmd(struct tpm_chip *chip, u32 handle,
 			    unsigned int flags);
 int tpm2_seal_trusted(struct tpm_chip *chip,
diff --git a/drivers/char/tpm/tpm2-cmd.c b/drivers/char/tpm/tpm2-cmd.c
index 90e3b36cf0dc..c31b490bd41d 100644
--- a/drivers/char/tpm/tpm2-cmd.c
+++ b/drivers/char/tpm/tpm2-cmd.c
@@ -27,25 +27,6 @@ enum tpm2_session_attributes {
 	TPM2_SA_CONTINUE_SESSION	= BIT(0),
 };
 
-struct tpm2_get_random_in {
-	__be16	size;
-} __packed;
-
-struct tpm2_get_random_out {
-	__be16	size;
-	u8	buffer[TPM_MAX_RNG_DATA];
-} __packed;
-
-union tpm2_cmd_params {
-	struct	tpm2_get_random_in	getrandom_in;
-	struct	tpm2_get_random_out	getrandom_out;
-};
-
-struct tpm2_cmd {
-	tpm_cmd_header		header;
-	union tpm2_cmd_params	params;
-} __packed;
-
 struct tpm2_hash {
 	unsigned int crypto_id;
 	unsigned int tpm_id;
@@ -300,67 +281,70 @@ int tpm2_pcr_extend(struct tpm_chip *chip, int pcr_idx, u32 count,
 }
 
 
-#define TPM2_GETRANDOM_IN_SIZE \
-	(sizeof(struct tpm_input_header) + \
-	 sizeof(struct tpm2_get_random_in))
-
-static const struct tpm_input_header tpm2_getrandom_header = {
-	.tag = cpu_to_be16(TPM2_ST_NO_SESSIONS),
-	.length = cpu_to_be32(TPM2_GETRANDOM_IN_SIZE),
-	.ordinal = cpu_to_be32(TPM2_CC_GET_RANDOM)
-};
+struct tpm2_get_random_out {
+	__be16 size;
+	u8 buffer[TPM_MAX_RNG_DATA];
+} __packed;
 
 /**
  * tpm2_get_random() - get random bytes from the TPM RNG
  *
- * @chip: TPM chip to use
- * @out: destination buffer for the random bytes
- * @max: the max number of bytes to write to @out
+ * @chip:	a &tpm_chip instance
+ * @dest:	destination buffer
+ * @max:	the max number of random bytes to pull
  *
  * Return:
- *    Size of the output buffer, or -EIO on error.
+ *   size of the buffer on success,
+ *   -errno otherwise
  */
-int tpm2_get_random(struct tpm_chip *chip, u8 *out, size_t max)
+int tpm2_get_random(struct tpm_chip *chip, u8 *dest, size_t max)
 {
-	struct tpm2_cmd cmd;
-	u32 recd, rlength;
-	u32 num_bytes;
+	struct tpm2_get_random_out *out;
+	struct tpm_buf buf;
+	u32 recd;
+	u32 num_bytes = max;
 	int err;
 	int total = 0;
 	int retries = 5;
-	u8 *dest = out;
-
-	num_bytes = min_t(u32, max, sizeof(cmd.params.getrandom_out.buffer));
+	u8 *dest_ptr = dest;
 
-	if (!out || !num_bytes ||
-	    max > sizeof(cmd.params.getrandom_out.buffer))
+	if (!num_bytes || max > TPM_MAX_RNG_DATA)
 		return -EINVAL;
 
-	do {
-		cmd.header.in = tpm2_getrandom_header;
-		cmd.params.getrandom_in.size = cpu_to_be16(num_bytes);
+	err = tpm_buf_init(&buf, 0, 0);
+	if (err)
+		return err;
 
-		err = tpm_transmit_cmd(chip, NULL, &cmd, sizeof(cmd),
+	do {
+		tpm_buf_reset(&buf, TPM2_ST_NO_SESSIONS, TPM2_CC_GET_RANDOM);
+		tpm_buf_append_u16(&buf, num_bytes);
+		err = tpm_transmit_cmd(chip, NULL, buf.data, PAGE_SIZE,
 				       offsetof(struct tpm2_get_random_out,
 						buffer),
 				       0, "attempting get random");
 		if (err)
-			break;
+			goto out;
 
-		recd = min_t(u32, be16_to_cpu(cmd.params.getrandom_out.size),
-			     num_bytes);
-		rlength = be32_to_cpu(cmd.header.out.length);
-		if (rlength < offsetof(struct tpm2_get_random_out, buffer) +
-			      recd)
-			return -EFAULT;
-		memcpy(dest, cmd.params.getrandom_out.buffer, recd);
+		out = (struct tpm2_get_random_out *)
+			&buf.data[TPM_HEADER_SIZE];
+		recd = min_t(u32, be16_to_cpu(out->size), num_bytes);
+		if (tpm_buf_length(&buf) <
+		    offsetof(struct tpm2_get_random_out, buffer) + recd) {
+			err = -EFAULT;
+			goto out;
+		}
+		memcpy(dest_ptr, out->buffer, recd);
 
-		dest += recd;
+		dest_ptr += recd;
 		total += recd;
 		num_bytes -= recd;
 	} while (retries-- && total < max);
 
+	tpm_buf_destroy(&buf);
 	return total ? total : -EIO;
+out:
+	tpm_buf_destroy(&buf);
+	return err;
 }
 
 /**
@@ -437,7 +421,7 @@ int tpm2_seal_trusted(struct tpm_chip *chip,
 {
 	unsigned int blob_len;
 	struct tpm_buf buf;
-	u32 hash, rlength;
+	u32 hash;
 	int i;
 	int rc;
 
@@ -512,8 +496,7 @@ int tpm2_seal_trusted(struct tpm_chip *chip,
 		rc = -E2BIG;
 		goto out;
 	}
-	rlength = be32_to_cpu(((struct tpm2_cmd *)&buf)->header.out.length);
-	if (rlength < TPM_HEADER_SIZE + 4 + blob_len) {
+	if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 4 + blob_len) {
 		rc = -EFAULT;
 		goto out;
 	}
@@ -623,7 +606,6 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip,
 	u16 data_len;
 	u8 *data;
 	int rc;
-	u32 rlength;
 
 	rc = tpm_buf_init(&buf, TPM2_ST_SESSIONS, TPM2_CC_UNSEAL);
 	if (rc)
@@ -651,9 +633,7 @@ static int tpm2_unseal_cmd(struct tpm_chip *chip,
 			goto out;
 		}
 
-		rlength = be32_to_cpu(((struct tpm2_cmd *)&buf)
-					->header.out.length);
-		if (rlength < TPM_HEADER_SIZE + 6 + data_len) {
+		if (tpm_buf_length(&buf) < TPM_HEADER_SIZE + 6 + data_len) {
 			rc = -EFAULT;
 			goto out;
 		}
-- 
cgit v1.2.3


From 1a339b658d9dbe1471f67b78237cf8fa08bbbeb5 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 8 Jun 2018 09:09:07 +0200
Subject: tpm_tis_spi: Pass the SPI IRQ down to the driver

An SPI TPM device managed directly on an embedded board using
the SPI bus and some GPIO or similar line as IRQ handler will
pass the IRQn from the TPM device associated with the SPI
device. This is already handled by the SPI core, so make sure
to pass this down to the core as well.

(The TPM core habit of using -1 to signal no IRQ is dubious
(as IRQ 0 is NO_IRQ) but I do not want to mess with that
semantic in this patch.)

Cc: Mark Brown <broonie@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Tested-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm_tis_spi.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/char/tpm/tpm_tis_spi.c b/drivers/char/tpm/tpm_tis_spi.c
index 424ff2fde1f2..9914f6973463 100644
--- a/drivers/char/tpm/tpm_tis_spi.c
+++ b/drivers/char/tpm/tpm_tis_spi.c
@@ -199,6 +199,7 @@ static const struct tpm_tis_phy_ops tpm_spi_phy_ops = {
 static int tpm_tis_spi_probe(struct spi_device *dev)
 {
 	struct tpm_tis_spi_phy *phy;
+	int irq;
 
 	phy = devm_kzalloc(&dev->dev, sizeof(struct tpm_tis_spi_phy),
 			   GFP_KERNEL);
@@ -211,7 +212,13 @@ static int tpm_tis_spi_probe(struct spi_device *dev)
 	if (!phy->iobuf)
 		return -ENOMEM;
 
-	return tpm_tis_core_init(&dev->dev, &phy->priv, -1, &tpm_spi_phy_ops,
+	/* If the SPI device has an IRQ then use that */
+	if (dev->irq > 0)
+		irq = dev->irq;
+	else
+		irq = -1;
+
+	return tpm_tis_core_init(&dev->dev, &phy->priv, irq, &tpm_spi_phy_ops,
 				 NULL);
 }
 
-- 
cgit v1.2.3


From 79e2472f99ab457417aaad98bf83ab565fa32bd0 Mon Sep 17 00:00:00 2001
From: Peter Rosin <peda@axentia.se>
Date: Wed, 20 Jun 2018 07:17:54 +0200
Subject: tpm/tpm_i2c_infineon: switch to i2c_lock_bus(..., I2C_LOCK_SEGMENT)

Locking the root adapter for __i2c_transfer will deadlock if the
device sits behind a mux-locked I2C mux. Switch to the finer-grained
i2c_lock_bus with the I2C_LOCK_SEGMENT flag. If the device does not
sit behind a mux-locked mux, the two locking variants are equivalent.

Signed-off-by: Peter Rosin <peda@axentia.se>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Tested-by: Alexander Steffen <Alexander.Steffen@infineon.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm_i2c_infineon.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c
index 6116cd05e228..9086edc9066b 100644
--- a/drivers/char/tpm/tpm_i2c_infineon.c
+++ b/drivers/char/tpm/tpm_i2c_infineon.c
@@ -117,7 +117,7 @@ static int iic_tpm_read(u8 addr, u8 *buffer, size_t len)
 	/* Lock the adapter for the duration of the whole sequence. */
 	if (!tpm_dev.client->adapter->algo->master_xfer)
 		return -EOPNOTSUPP;
-	i2c_lock_adapter(tpm_dev.client->adapter);
+	i2c_lock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 
 	if (tpm_dev.chip_type == SLB9645) {
 		/* use a combined read for newer chips
@@ -192,7 +192,7 @@ static int iic_tpm_read(u8 addr, u8 *buffer, size_t len)
 	}
 
 out:
-	i2c_unlock_adapter(tpm_dev.client->adapter);
+	i2c_unlock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 	/* take care of 'guard time' */
 	usleep_range(SLEEP_DURATION_LOW, SLEEP_DURATION_HI);
 
@@ -224,7 +224,7 @@ static int iic_tpm_write_generic(u8 addr, u8 *buffer, size_t len,
 
 	if (!tpm_dev.client->adapter->algo->master_xfer)
 		return -EOPNOTSUPP;
-	i2c_lock_adapter(tpm_dev.client->adapter);
+	i2c_lock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 
 	/* prepend the 'register address' to the buffer */
 	tpm_dev.buf[0] = addr;
@@ -243,7 +243,7 @@ static int iic_tpm_write_generic(u8 addr, u8 *buffer, size_t len,
 		usleep_range(sleep_low, sleep_hi);
 	}
 
-	i2c_unlock_adapter(tpm_dev.client->adapter);
+	i2c_unlock_bus(tpm_dev.client->adapter, I2C_LOCK_SEGMENT);
 	/* take care of 'guard time' */
 	usleep_range(SLEEP_DURATION_LOW, SLEEP_DURATION_HI);
 
-- 
cgit v1.2.3


From 627448e85c766587f6fdde1ea3886d6615081c77 Mon Sep 17 00:00:00 2001
From: Tomas Winkler <tomas.winkler@intel.com>
Date: Thu, 28 Jun 2018 18:13:33 +0300
Subject: tpm: separate cmd_ready/go_idle from runtime_pm

Fix tpm ptt initialization error:
tpm tpm0: A TPM error (378) occurred get tpm pcr allocation.

We cannot use go_idle cmd_ready commands via runtime_pm handles
as with the introduction of localities this is no longer an optional
feature, while runtime pm can be not enabled.
Though cmd_ready/go_idle provides a power saving, it's also a part of
TPM2 protocol and should be called explicitly.
This patch exposes cmd_read/go_idle via tpm class ops and removes
runtime pm support as it is not used by any driver.

When calling from nested context always use both flags:
TPM_TRANSMIT_UNLOCKED and TPM_TRANSMIT_RAW. Both are needed to resolve
tpm spaces and locality request recursive calls to tpm_transmit().
TPM_TRANSMIT_RAW should never be used standalone as it will fail
on double locking. While TPM_TRANSMIT_UNLOCKED standalone should be
called from non-recursive locked contexts.

New wrappers are added tpm_cmd_ready() and tpm_go_idle() to
streamline tpm_try_transmit code.

tpm_crb no longer needs own power saving functions and can drop using
tpm_pm_suspend/resume.

This patch cannot be really separated from the locality fix.
Fixes: 888d867df441 (tpm: cmd_ready command can be issued only after granting locality)

Cc: stable@vger.kernel.org
Fixes: 888d867df441 (tpm: cmd_ready command can be issued only after granting locality)
Signed-off-by: Tomas Winkler <tomas.winkler@intel.com>
Tested-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm-interface.c |  51 ++++++++++++++++----
 drivers/char/tpm/tpm.h           |  12 ++++-
 drivers/char/tpm/tpm2-space.c    |  16 ++++---
 drivers/char/tpm/tpm_crb.c       | 101 +++++++++++----------------------------
 include/linux/tpm.h              |   2 +
 5 files changed, 90 insertions(+), 92 deletions(-)

diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index e32f6e85dc6d..31b86e027f9d 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -29,7 +29,6 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
-#include <linux/pm_runtime.h>
 #include <linux/tpm_eventlog.h>
 
 #include "tpm.h"
@@ -369,10 +368,13 @@ err_len:
 	return -EINVAL;
 }
 
-static int tpm_request_locality(struct tpm_chip *chip)
+static int tpm_request_locality(struct tpm_chip *chip, unsigned int flags)
 {
 	int rc;
 
+	if (flags & TPM_TRANSMIT_RAW)
+		return 0;
+
 	if (!chip->ops->request_locality)
 		return 0;
 
@@ -385,10 +387,13 @@ static int tpm_request_locality(struct tpm_chip *chip)
 	return 0;
 }
 
-static void tpm_relinquish_locality(struct tpm_chip *chip)
+static void tpm_relinquish_locality(struct tpm_chip *chip, unsigned int flags)
 {
 	int rc;
 
+	if (flags & TPM_TRANSMIT_RAW)
+		return;
+
 	if (!chip->ops->relinquish_locality)
 		return;
 
@@ -399,6 +404,28 @@ static void tpm_relinquish_locality(struct tpm_chip *chip)
 	chip->locality = -1;
 }
 
+static int tpm_cmd_ready(struct tpm_chip *chip, unsigned int flags)
+{
+	if (flags & TPM_TRANSMIT_RAW)
+		return 0;
+
+	if (!chip->ops->cmd_ready)
+		return 0;
+
+	return chip->ops->cmd_ready(chip);
+}
+
+static int tpm_go_idle(struct tpm_chip *chip, unsigned int flags)
+{
+	if (flags & TPM_TRANSMIT_RAW)
+		return 0;
+
+	if (!chip->ops->go_idle)
+		return 0;
+
+	return chip->ops->go_idle(chip);
+}
+
 static ssize_t tpm_try_transmit(struct tpm_chip *chip,
 				struct tpm_space *space,
 				u8 *buf, size_t bufsiz,
@@ -449,14 +476,15 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip,
 	/* Store the decision as chip->locality will be changed. */
 	need_locality = chip->locality == -1;
 
-	if (!(flags & TPM_TRANSMIT_RAW) && need_locality) {
-		rc = tpm_request_locality(chip);
+	if (need_locality) {
+		rc = tpm_request_locality(chip, flags);
 		if (rc < 0)
 			goto out_no_locality;
 	}
 
-	if (chip->dev.parent)
-		pm_runtime_get_sync(chip->dev.parent);
+	rc = tpm_cmd_ready(chip, flags);
+	if (rc)
+		goto out;
 
 	rc = tpm2_prepare_space(chip, space, ordinal, buf);
 	if (rc)
@@ -516,13 +544,16 @@ out_recv:
 	}
 
 	rc = tpm2_commit_space(chip, space, ordinal, buf, &len);
+	if (rc)
+		dev_err(&chip->dev, "tpm2_commit_space: error %d\n", rc);
 
 out:
-	if (chip->dev.parent)
-		pm_runtime_put_sync(chip->dev.parent);
+	rc = tpm_go_idle(chip, flags);
+	if (rc)
+		goto out;
 
 	if (need_locality)
-		tpm_relinquish_locality(chip);
+		tpm_relinquish_locality(chip, flags);
 
 out_no_locality:
 	if (chip->ops->clk_enable != NULL)
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 9824cccb2c76..17833ef63f6c 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -512,9 +512,17 @@ extern const struct file_operations tpm_fops;
 extern const struct file_operations tpmrm_fops;
 extern struct idr dev_nums_idr;
 
+/**
+ * enum tpm_transmit_flags
+ *
+ * @TPM_TRANSMIT_UNLOCKED: used to lock sequence of tpm_transmit calls.
+ * @TPM_TRANSMIT_RAW: prevent recursive calls into setup steps
+ *                    (go idle, locality,..). Always use with UNLOCKED
+ *                    as it will fail on double locking.
+ */
 enum tpm_transmit_flags {
-	TPM_TRANSMIT_UNLOCKED	= BIT(0),
-	TPM_TRANSMIT_RAW	= BIT(1),
+	TPM_TRANSMIT_UNLOCKED = BIT(0),
+	TPM_TRANSMIT_RAW      = BIT(1),
 };
 
 ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space,
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index 6122d3276f72..11c85ed8c113 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -39,7 +39,8 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space)
 	for (i = 0; i < ARRAY_SIZE(space->session_tbl); i++) {
 		if (space->session_tbl[i])
 			tpm2_flush_context_cmd(chip, space->session_tbl[i],
-					       TPM_TRANSMIT_UNLOCKED);
+					       TPM_TRANSMIT_UNLOCKED |
+					       TPM_TRANSMIT_RAW);
 	}
 }
 
@@ -84,7 +85,7 @@ static int tpm2_load_context(struct tpm_chip *chip, u8 *buf,
 	tpm_buf_append(&tbuf, &buf[*offset], body_size);
 
 	rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 4,
-			      TPM_TRANSMIT_UNLOCKED, NULL);
+			      TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW, NULL);
 	if (rc < 0) {
 		dev_warn(&chip->dev, "%s: failed with a system error %d\n",
 			 __func__, rc);
@@ -133,7 +134,7 @@ static int tpm2_save_context(struct tpm_chip *chip, u32 handle, u8 *buf,
 	tpm_buf_append_u32(&tbuf, handle);
 
 	rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 0,
-			      TPM_TRANSMIT_UNLOCKED, NULL);
+			      TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW, NULL);
 	if (rc < 0) {
 		dev_warn(&chip->dev, "%s: failed with a system error %d\n",
 			 __func__, rc);
@@ -170,7 +171,8 @@ static void tpm2_flush_space(struct tpm_chip *chip)
 	for (i = 0; i < ARRAY_SIZE(space->context_tbl); i++)
 		if (space->context_tbl[i] && ~space->context_tbl[i])
 			tpm2_flush_context_cmd(chip, space->context_tbl[i],
-					       TPM_TRANSMIT_UNLOCKED);
+					       TPM_TRANSMIT_UNLOCKED |
+					       TPM_TRANSMIT_RAW);
 
 	tpm2_flush_sessions(chip, space);
 }
@@ -377,7 +379,8 @@ static int tpm2_map_response_header(struct tpm_chip *chip, u32 cc, u8 *rsp,
 
 	return 0;
 out_no_slots:
-	tpm2_flush_context_cmd(chip, phandle, TPM_TRANSMIT_UNLOCKED);
+	tpm2_flush_context_cmd(chip, phandle,
+			       TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW);
 	dev_warn(&chip->dev, "%s: out of slots for 0x%08X\n", __func__,
 		 phandle);
 	return -ENOMEM;
@@ -465,7 +468,8 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			return rc;
 
 		tpm2_flush_context_cmd(chip, space->context_tbl[i],
-				       TPM_TRANSMIT_UNLOCKED);
+				       TPM_TRANSMIT_UNLOCKED |
+				       TPM_TRANSMIT_RAW);
 		space->context_tbl[i] = ~0;
 	}
 
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index 34fbc6cb097b..36952ef98f90 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -132,7 +132,7 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value,
 }
 
 /**
- * crb_go_idle - request tpm crb device to go the idle state
+ * __crb_go_idle - request tpm crb device to go the idle state
  *
  * @dev:  crb device
  * @priv: crb private data
@@ -147,7 +147,7 @@ static bool crb_wait_for_reg_32(u32 __iomem *reg, u32 mask, u32 value,
  *
  * Return: 0 always
  */
-static int crb_go_idle(struct device *dev, struct crb_priv *priv)
+static int __crb_go_idle(struct device *dev, struct crb_priv *priv)
 {
 	if ((priv->sm == ACPI_TPM2_START_METHOD) ||
 	    (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) ||
@@ -163,11 +163,20 @@ static int crb_go_idle(struct device *dev, struct crb_priv *priv)
 		dev_warn(dev, "goIdle timed out\n");
 		return -ETIME;
 	}
+
 	return 0;
 }
 
+static int crb_go_idle(struct tpm_chip *chip)
+{
+	struct device *dev = &chip->dev;
+	struct crb_priv *priv = dev_get_drvdata(dev);
+
+	return __crb_go_idle(dev, priv);
+}
+
 /**
- * crb_cmd_ready - request tpm crb device to enter ready state
+ * __crb_cmd_ready - request tpm crb device to enter ready state
  *
  * @dev:  crb device
  * @priv: crb private data
@@ -181,7 +190,7 @@ static int crb_go_idle(struct device *dev, struct crb_priv *priv)
  *
  * Return: 0 on success -ETIME on timeout;
  */
-static int crb_cmd_ready(struct device *dev, struct crb_priv *priv)
+static int __crb_cmd_ready(struct device *dev, struct crb_priv *priv)
 {
 	if ((priv->sm == ACPI_TPM2_START_METHOD) ||
 	    (priv->sm == ACPI_TPM2_COMMAND_BUFFER_WITH_START_METHOD) ||
@@ -200,6 +209,14 @@ static int crb_cmd_ready(struct device *dev, struct crb_priv *priv)
 	return 0;
 }
 
+static int crb_cmd_ready(struct tpm_chip *chip)
+{
+	struct device *dev = &chip->dev;
+	struct crb_priv *priv = dev_get_drvdata(dev);
+
+	return __crb_cmd_ready(dev, priv);
+}
+
 static int __crb_request_locality(struct device *dev,
 				  struct crb_priv *priv, int loc)
 {
@@ -401,6 +418,8 @@ static const struct tpm_class_ops tpm_crb = {
 	.send = crb_send,
 	.cancel = crb_cancel,
 	.req_canceled = crb_req_canceled,
+	.go_idle  = crb_go_idle,
+	.cmd_ready = crb_cmd_ready,
 	.request_locality = crb_request_locality,
 	.relinquish_locality = crb_relinquish_locality,
 	.req_complete_mask = CRB_DRV_STS_COMPLETE,
@@ -520,7 +539,7 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,
 	 * PTT HW bug w/a: wake up the device to access
 	 * possibly not retained registers.
 	 */
-	ret = crb_cmd_ready(dev, priv);
+	ret = __crb_cmd_ready(dev, priv);
 	if (ret)
 		goto out_relinquish_locality;
 
@@ -565,7 +584,7 @@ out:
 	if (!ret)
 		priv->cmd_size = cmd_size;
 
-	crb_go_idle(dev, priv);
+	__crb_go_idle(dev, priv);
 
 out_relinquish_locality:
 
@@ -628,32 +647,7 @@ static int crb_acpi_add(struct acpi_device *device)
 	chip->acpi_dev_handle = device->handle;
 	chip->flags = TPM_CHIP_FLAG_TPM2;
 
-	rc = __crb_request_locality(dev, priv, 0);
-	if (rc)
-		return rc;
-
-	rc  = crb_cmd_ready(dev, priv);
-	if (rc)
-		goto out;
-
-	pm_runtime_get_noresume(dev);
-	pm_runtime_set_active(dev);
-	pm_runtime_enable(dev);
-
-	rc = tpm_chip_register(chip);
-	if (rc) {
-		crb_go_idle(dev, priv);
-		pm_runtime_put_noidle(dev);
-		pm_runtime_disable(dev);
-		goto out;
-	}
-
-	pm_runtime_put_sync(dev);
-
-out:
-	__crb_relinquish_locality(dev, priv, 0);
-
-	return rc;
+	return tpm_chip_register(chip);
 }
 
 static int crb_acpi_remove(struct acpi_device *device)
@@ -663,52 +657,11 @@ static int crb_acpi_remove(struct acpi_device *device)
 
 	tpm_chip_unregister(chip);
 
-	pm_runtime_disable(dev);
-
 	return 0;
 }
 
-static int __maybe_unused crb_pm_runtime_suspend(struct device *dev)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct crb_priv *priv = dev_get_drvdata(&chip->dev);
-
-	return crb_go_idle(dev, priv);
-}
-
-static int __maybe_unused crb_pm_runtime_resume(struct device *dev)
-{
-	struct tpm_chip *chip = dev_get_drvdata(dev);
-	struct crb_priv *priv = dev_get_drvdata(&chip->dev);
-
-	return crb_cmd_ready(dev, priv);
-}
-
-static int __maybe_unused crb_pm_suspend(struct device *dev)
-{
-	int ret;
-
-	ret = tpm_pm_suspend(dev);
-	if (ret)
-		return ret;
-
-	return crb_pm_runtime_suspend(dev);
-}
-
-static int __maybe_unused crb_pm_resume(struct device *dev)
-{
-	int ret;
-
-	ret = crb_pm_runtime_resume(dev);
-	if (ret)
-		return ret;
-
-	return tpm_pm_resume(dev);
-}
-
 static const struct dev_pm_ops crb_pm = {
-	SET_SYSTEM_SLEEP_PM_OPS(crb_pm_suspend, crb_pm_resume)
-	SET_RUNTIME_PM_OPS(crb_pm_runtime_suspend, crb_pm_runtime_resume, NULL)
+	SET_SYSTEM_SLEEP_PM_OPS(tpm_pm_suspend, tpm_pm_resume)
 };
 
 static const struct acpi_device_id crb_device_ids[] = {
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 06639fb6ab85..8eb5e5ebe136 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -43,6 +43,8 @@ struct tpm_class_ops {
 	u8 (*status) (struct tpm_chip *chip);
 	bool (*update_timeouts)(struct tpm_chip *chip,
 				unsigned long *timeout_cap);
+	int (*go_idle)(struct tpm_chip *chip);
+	int (*cmd_ready)(struct tpm_chip *chip);
 	int (*request_locality)(struct tpm_chip *chip, int loc);
 	int (*relinquish_locality)(struct tpm_chip *chip, int loc);
 	void (*clk_enable)(struct tpm_chip *chip, bool value);
-- 
cgit v1.2.3


From 36a11029b07ee30bdc4553274d0efea645ed9d91 Mon Sep 17 00:00:00 2001
From: Ricardo Schwarzmeier <Ricardo.Schwarzmeier@infineon.com>
Date: Tue, 26 Jun 2018 17:31:45 +0200
Subject: tpm: Return the actual size when receiving an unsupported command

The userpace expects to read the number of bytes stated in the header.
Returning the size of the buffer instead would be unexpected.

Cc: stable@vger.kernel.org
Fixes: 095531f891e6 ("tpm: return a TPM_RC_COMMAND_CODE response if command is not implemented")
Signed-off-by: Ricardo Schwarzmeier <Ricardo.Schwarzmeier@infineon.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm-interface.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 31b86e027f9d..3a3a7a548a85 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -450,7 +450,7 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip,
 		header->tag = cpu_to_be16(TPM2_ST_NO_SESSIONS);
 		header->return_code = cpu_to_be32(TPM2_RC_COMMAND_CODE |
 						  TSS2_RESMGR_TPM_RC_LAYER);
-		return bufsiz;
+		return sizeof(*header);
 	}
 
 	if (bufsiz > TPM_BUFSIZE)
-- 
cgit v1.2.3


From 7a64c5597aa40403e9f8319c0664228a5580c121 Mon Sep 17 00:00:00 2001
From: Louis Collard <louiscollard@chromium.org>
Date: Fri, 29 Jun 2018 16:13:55 +0800
Subject: tpm: Allow tpm_tis drivers to set hwrng quality.

Adds plumbing required for drivers based on tpm_tis to set hwrng quality.

Signed-off-by: Louis Collard <louiscollard@chromium.org>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm_tis_core.c | 2 ++
 drivers/char/tpm/tpm_tis_core.h | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 8b46aaa9e049..d2345d9fd7b5 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -875,6 +875,8 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq,
 	chip->acpi_dev_handle = acpi_dev_handle;
 #endif
 
+	chip->hwrng.quality = priv->rng_quality;
+
 	/* Maximum timeouts */
 	chip->timeout_a = msecs_to_jiffies(TIS_TIMEOUT_A_MAX);
 	chip->timeout_b = msecs_to_jiffies(TIS_TIMEOUT_B_MAX);
diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h
index f6e1dbe212a7..f48125f1e6e0 100644
--- a/drivers/char/tpm/tpm_tis_core.h
+++ b/drivers/char/tpm/tpm_tis_core.h
@@ -99,6 +99,7 @@ struct tpm_tis_data {
 	wait_queue_head_t int_queue;
 	wait_queue_head_t read_queue;
 	const struct tpm_tis_phy_ops *phy_ops;
+	unsigned short rng_quality;
 };
 
 struct tpm_tis_phy_ops {
-- 
cgit v1.2.3


From fc1d52b745bae6108102096d85e743ac33b446f2 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Tue, 26 Jun 2018 07:06:15 -0400
Subject: tpm: rename tpm_chip_find_get() to tpm_find_get_ops()

Rename tpm_chip_find_get() to tpm_find_get_ops() to more closely match
the tpm_put_ops() counter part.

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Tested-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm-chip.c      |  9 ++++++---
 drivers/char/tpm/tpm-interface.c | 14 +++++++-------
 drivers/char/tpm/tpm.h           |  2 +-
 3 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 0a62c19937b6..242b716aed5e 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -81,18 +81,21 @@ void tpm_put_ops(struct tpm_chip *chip)
 EXPORT_SYMBOL_GPL(tpm_put_ops);
 
 /**
- * tpm_chip_find_get() - find and reserve a TPM chip
+ * tpm_find_get_ops() - find and reserve a TPM chip
  * @chip:	a &struct tpm_chip instance, %NULL for the default chip
  *
  * Finds a TPM chip and reserves its class device and operations. The chip must
- * be released with tpm_chip_put_ops() after use.
+ * be released with tpm_put_ops() after use.
+ * This function is for internal use only. It supports existing TPM callers
+ * by accepting NULL, but those callers should be converted to pass in a chip
+ * directly.
  *
  * Return:
  * A reserved &struct tpm_chip instance.
  * %NULL if a chip is not found.
  * %NULL if the chip is not available.
  */
-struct tpm_chip *tpm_chip_find_get(struct tpm_chip *chip)
+struct tpm_chip *tpm_find_get_ops(struct tpm_chip *chip)
 {
 	struct tpm_chip *res = NULL;
 	int chip_num = 0;
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 3a3a7a548a85..ad761e629a0f 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -961,7 +961,7 @@ int tpm_is_tpm2(struct tpm_chip *chip)
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -985,7 +985,7 @@ int tpm_pcr_read(struct tpm_chip *chip, int pcr_idx, u8 *res_buf)
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 	if (chip->flags & TPM_CHIP_FLAG_TPM2)
@@ -1044,7 +1044,7 @@ int tpm_pcr_extend(struct tpm_chip *chip, int pcr_idx, const u8 *hash)
 	u32 count = 0;
 	int i;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -1173,7 +1173,7 @@ int tpm_send(struct tpm_chip *chip, void *cmd, size_t buflen)
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -1293,7 +1293,7 @@ int tpm_get_random(struct tpm_chip *chip, u8 *out, size_t max)
 	if (!out || !num_bytes || max > TPM_MAX_RNG_DATA)
 		return -EINVAL;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip)
 		return -ENODEV;
 
@@ -1355,7 +1355,7 @@ int tpm_seal_trusted(struct tpm_chip *chip, struct trusted_key_payload *payload,
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
 		return -ENODEV;
 
@@ -1383,7 +1383,7 @@ int tpm_unseal_trusted(struct tpm_chip *chip,
 {
 	int rc;
 
-	chip = tpm_chip_find_get(chip);
+	chip = tpm_find_get_ops(chip);
 	if (!chip || !(chip->flags & TPM_CHIP_FLAG_TPM2))
 		return -ENODEV;
 
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index 17833ef63f6c..ba01488cd029 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -547,7 +547,7 @@ static inline void tpm_msleep(unsigned int delay_msec)
 		     delay_msec * 1000);
 };
 
-struct tpm_chip *tpm_chip_find_get(struct tpm_chip *chip);
+struct tpm_chip *tpm_find_get_ops(struct tpm_chip *chip);
 __must_check int tpm_try_get_ops(struct tpm_chip *chip);
 void tpm_put_ops(struct tpm_chip *chip);
 
-- 
cgit v1.2.3


From aaae81536351f831fe6719e5b4e6afbadc5e5f85 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Tue, 26 Jun 2018 15:09:30 -0400
Subject: tpm: Implement tpm_default_chip() to find a TPM chip

Implement tpm_default_chip() to find the first TPM chip and return it to
the caller while increasing the reference count on its device. This
function can be used by other subsystems, such as IMA, to find the system's
default TPM chip and use it for all subsequent TPM operations.

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm-chip.c | 27 +++++++++++++++++++++++++++
 include/linux/tpm.h         |  5 +++++
 2 files changed, 32 insertions(+)

diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index 242b716aed5e..f551061262c9 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -80,6 +80,33 @@ void tpm_put_ops(struct tpm_chip *chip)
 }
 EXPORT_SYMBOL_GPL(tpm_put_ops);
 
+/**
+ * tpm_default_chip() - find a TPM chip and get a reference to it
+ */
+struct tpm_chip *tpm_default_chip(void)
+{
+	struct tpm_chip *chip, *res = NULL;
+	int chip_num = 0;
+	int chip_prev;
+
+	mutex_lock(&idr_lock);
+
+	do {
+		chip_prev = chip_num;
+		chip = idr_get_next(&dev_nums_idr, &chip_num);
+		if (chip) {
+			get_device(&chip->dev);
+			res = chip;
+			break;
+		}
+	} while (chip_prev != chip_num);
+
+	mutex_unlock(&idr_lock);
+
+	return res;
+}
+EXPORT_SYMBOL_GPL(tpm_default_chip);
+
 /**
  * tpm_find_get_ops() - find and reserve a TPM chip
  * @chip:	a &struct tpm_chip instance, %NULL for the default chip
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index 8eb5e5ebe136..4609b94142d4 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -63,6 +63,7 @@ extern int tpm_seal_trusted(struct tpm_chip *chip,
 extern int tpm_unseal_trusted(struct tpm_chip *chip,
 			      struct trusted_key_payload *payload,
 			      struct trusted_key_options *options);
+extern struct tpm_chip *tpm_default_chip(void);
 #else
 static inline int tpm_is_tpm2(struct tpm_chip *chip)
 {
@@ -98,5 +99,9 @@ static inline int tpm_unseal_trusted(struct tpm_chip *chip,
 {
 	return -ENODEV;
 }
+static inline struct tpm_chip *tpm_default_chip(void)
+{
+	return NULL;
+}
 #endif
 #endif
-- 
cgit v1.2.3


From eccc9bb844838b6b7a9691b31747416c4c34a83f Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Tue, 26 Jun 2018 15:09:31 -0400
Subject: tpm: Convert tpm_find_get_ops() to use tpm_default_chip()

Convert tpm_find_get_ops() to use tpm_default_chip() in case no chip
is passed in.

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Tested-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm-chip.c | 32 +++++++++++++-------------------
 1 file changed, 13 insertions(+), 19 deletions(-)

diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c
index f551061262c9..46caadca916a 100644
--- a/drivers/char/tpm/tpm-chip.c
+++ b/drivers/char/tpm/tpm-chip.c
@@ -124,29 +124,23 @@ EXPORT_SYMBOL_GPL(tpm_default_chip);
  */
 struct tpm_chip *tpm_find_get_ops(struct tpm_chip *chip)
 {
-	struct tpm_chip *res = NULL;
-	int chip_num = 0;
-	int chip_prev;
-
-	mutex_lock(&idr_lock);
+	int rc;
 
-	if (!chip) {
-		do {
-			chip_prev = chip_num;
-			chip = idr_get_next(&dev_nums_idr, &chip_num);
-			if (chip && !tpm_try_get_ops(chip)) {
-				res = chip;
-				break;
-			}
-		} while (chip_prev != chip_num);
-	} else {
+	if (chip) {
 		if (!tpm_try_get_ops(chip))
-			res = chip;
+			return chip;
+		return NULL;
 	}
 
-	mutex_unlock(&idr_lock);
-
-	return res;
+	chip = tpm_default_chip();
+	if (!chip)
+		return NULL;
+	rc = tpm_try_get_ops(chip);
+	/* release additional reference we got from tpm_default_chip() */
+	put_device(&chip->dev);
+	if (rc)
+		return NULL;
+	return chip;
 }
 
 /**
-- 
cgit v1.2.3


From 58bac8cc3010ccb845572a3512fc16c9aaa5e50e Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Date: Fri, 29 Jun 2018 15:24:50 +0300
Subject: tpm: replace TPM_TRANSMIT_RAW with TPM_TRANSMIT_NESTED

As TPM_TRANSMIT_RAW always requires also not to take locks for obvious
reasons (deadlock), this commit renames the flag as TPM_TRANSMIT_NESTED
and prevents taking tpm_mutex when the flag is given to tpm_transmit().

Suggested-by: Tomas Winkler <tomas.winkler@intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm-interface.c  | 13 ++++++-------
 drivers/char/tpm/tpm.h            | 14 +++++++-------
 drivers/char/tpm/tpm2-space.c     | 16 ++++++----------
 drivers/char/tpm/tpm_vtpm_proxy.c |  2 +-
 4 files changed, 20 insertions(+), 25 deletions(-)

diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index ad761e629a0f..1a803b0cf980 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -372,7 +372,7 @@ static int tpm_request_locality(struct tpm_chip *chip, unsigned int flags)
 {
 	int rc;
 
-	if (flags & TPM_TRANSMIT_RAW)
+	if (flags & TPM_TRANSMIT_NESTED)
 		return 0;
 
 	if (!chip->ops->request_locality)
@@ -391,7 +391,7 @@ static void tpm_relinquish_locality(struct tpm_chip *chip, unsigned int flags)
 {
 	int rc;
 
-	if (flags & TPM_TRANSMIT_RAW)
+	if (flags & TPM_TRANSMIT_NESTED)
 		return;
 
 	if (!chip->ops->relinquish_locality)
@@ -406,7 +406,7 @@ static void tpm_relinquish_locality(struct tpm_chip *chip, unsigned int flags)
 
 static int tpm_cmd_ready(struct tpm_chip *chip, unsigned int flags)
 {
-	if (flags & TPM_TRANSMIT_RAW)
+	if (flags & TPM_TRANSMIT_NESTED)
 		return 0;
 
 	if (!chip->ops->cmd_ready)
@@ -417,7 +417,7 @@ static int tpm_cmd_ready(struct tpm_chip *chip, unsigned int flags)
 
 static int tpm_go_idle(struct tpm_chip *chip, unsigned int flags)
 {
-	if (flags & TPM_TRANSMIT_RAW)
+	if (flags & TPM_TRANSMIT_NESTED)
 		return 0;
 
 	if (!chip->ops->go_idle)
@@ -466,10 +466,9 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip,
 		return -E2BIG;
 	}
 
-	if (!(flags & TPM_TRANSMIT_UNLOCKED))
+	if (!(flags & TPM_TRANSMIT_UNLOCKED) && !(flags & TPM_TRANSMIT_NESTED))
 		mutex_lock(&chip->tpm_mutex);
 
-
 	if (chip->ops->clk_enable != NULL)
 		chip->ops->clk_enable(chip, true);
 
@@ -559,7 +558,7 @@ out_no_locality:
 	if (chip->ops->clk_enable != NULL)
 		chip->ops->clk_enable(chip, false);
 
-	if (!(flags & TPM_TRANSMIT_UNLOCKED))
+	if (!(flags & TPM_TRANSMIT_UNLOCKED) && !(flags & TPM_TRANSMIT_NESTED))
 		mutex_unlock(&chip->tpm_mutex);
 	return rc ? rc : len;
 }
diff --git a/drivers/char/tpm/tpm.h b/drivers/char/tpm/tpm.h
index ba01488cd029..f3501d05264f 100644
--- a/drivers/char/tpm/tpm.h
+++ b/drivers/char/tpm/tpm.h
@@ -513,16 +513,16 @@ extern const struct file_operations tpmrm_fops;
 extern struct idr dev_nums_idr;
 
 /**
- * enum tpm_transmit_flags
+ * enum tpm_transmit_flags - flags for tpm_transmit()
  *
- * @TPM_TRANSMIT_UNLOCKED: used to lock sequence of tpm_transmit calls.
- * @TPM_TRANSMIT_RAW: prevent recursive calls into setup steps
- *                    (go idle, locality,..). Always use with UNLOCKED
- *                    as it will fail on double locking.
+ * @TPM_TRANSMIT_UNLOCKED:	do not lock the chip
+ * @TPM_TRANSMIT_NESTED:	discard setup steps (power management,
+ *				locality) including locking (i.e. implicit
+ *				UNLOCKED)
  */
 enum tpm_transmit_flags {
-	TPM_TRANSMIT_UNLOCKED = BIT(0),
-	TPM_TRANSMIT_RAW      = BIT(1),
+	TPM_TRANSMIT_UNLOCKED	= BIT(0),
+	TPM_TRANSMIT_NESTED      = BIT(1),
 };
 
 ssize_t tpm_transmit(struct tpm_chip *chip, struct tpm_space *space,
diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
index 11c85ed8c113..d2e101b32482 100644
--- a/drivers/char/tpm/tpm2-space.c
+++ b/drivers/char/tpm/tpm2-space.c
@@ -39,8 +39,7 @@ static void tpm2_flush_sessions(struct tpm_chip *chip, struct tpm_space *space)
 	for (i = 0; i < ARRAY_SIZE(space->session_tbl); i++) {
 		if (space->session_tbl[i])
 			tpm2_flush_context_cmd(chip, space->session_tbl[i],
-					       TPM_TRANSMIT_UNLOCKED |
-					       TPM_TRANSMIT_RAW);
+					       TPM_TRANSMIT_NESTED);
 	}
 }
 
@@ -85,7 +84,7 @@ static int tpm2_load_context(struct tpm_chip *chip, u8 *buf,
 	tpm_buf_append(&tbuf, &buf[*offset], body_size);
 
 	rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 4,
-			      TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW, NULL);
+			      TPM_TRANSMIT_NESTED, NULL);
 	if (rc < 0) {
 		dev_warn(&chip->dev, "%s: failed with a system error %d\n",
 			 __func__, rc);
@@ -134,7 +133,7 @@ static int tpm2_save_context(struct tpm_chip *chip, u32 handle, u8 *buf,
 	tpm_buf_append_u32(&tbuf, handle);
 
 	rc = tpm_transmit_cmd(chip, NULL, tbuf.data, PAGE_SIZE, 0,
-			      TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW, NULL);
+			      TPM_TRANSMIT_NESTED, NULL);
 	if (rc < 0) {
 		dev_warn(&chip->dev, "%s: failed with a system error %d\n",
 			 __func__, rc);
@@ -171,8 +170,7 @@ static void tpm2_flush_space(struct tpm_chip *chip)
 	for (i = 0; i < ARRAY_SIZE(space->context_tbl); i++)
 		if (space->context_tbl[i] && ~space->context_tbl[i])
 			tpm2_flush_context_cmd(chip, space->context_tbl[i],
-					       TPM_TRANSMIT_UNLOCKED |
-					       TPM_TRANSMIT_RAW);
+					       TPM_TRANSMIT_NESTED);
 
 	tpm2_flush_sessions(chip, space);
 }
@@ -379,8 +377,7 @@ static int tpm2_map_response_header(struct tpm_chip *chip, u32 cc, u8 *rsp,
 
 	return 0;
 out_no_slots:
-	tpm2_flush_context_cmd(chip, phandle,
-			       TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW);
+	tpm2_flush_context_cmd(chip, phandle, TPM_TRANSMIT_NESTED);
 	dev_warn(&chip->dev, "%s: out of slots for 0x%08X\n", __func__,
 		 phandle);
 	return -ENOMEM;
@@ -468,8 +465,7 @@ static int tpm2_save_space(struct tpm_chip *chip)
 			return rc;
 
 		tpm2_flush_context_cmd(chip, space->context_tbl[i],
-				       TPM_TRANSMIT_UNLOCKED |
-				       TPM_TRANSMIT_RAW);
+				       TPM_TRANSMIT_NESTED);
 		space->context_tbl[i] = ~0;
 	}
 
diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c
index e4f79f920450..87a0ce47f201 100644
--- a/drivers/char/tpm/tpm_vtpm_proxy.c
+++ b/drivers/char/tpm/tpm_vtpm_proxy.c
@@ -418,7 +418,7 @@ static int vtpm_proxy_request_locality(struct tpm_chip *chip, int locality)
 	proxy_dev->state |= STATE_DRIVER_COMMAND;
 
 	rc = tpm_transmit_cmd(chip, NULL, buf.data, tpm_buf_length(&buf), 0,
-			      TPM_TRANSMIT_UNLOCKED | TPM_TRANSMIT_RAW,
+			      TPM_TRANSMIT_NESTED,
 			      "attempting to set locality");
 
 	proxy_dev->state &= ~STATE_DRIVER_COMMAND;
-- 
cgit v1.2.3


From 5c2a640aff73914e11ac0db310b32d3b7a1b87ad Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Tue, 26 Jun 2018 15:09:32 -0400
Subject: ima: Use tpm_default_chip() and call TPM functions with a tpm_chip

Rather than accessing the TPM functions by passing a NULL pointer for
the tpm_chip, which causes a lookup for a suitable chip every time, get a
hold of a tpm_chip and access the TPM functions using it.

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 security/integrity/ima/ima.h        |  1 +
 security/integrity/ima/ima_crypto.c |  2 +-
 security/integrity/ima/ima_init.c   | 11 ++++-------
 security/integrity/ima/ima_queue.c  |  2 +-
 4 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 78c15264b17b..dc212c59d4d6 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -56,6 +56,7 @@ extern int ima_policy_flag;
 extern int ima_used_chip;
 extern int ima_hash_algo;
 extern int ima_appraise;
+extern struct tpm_chip *ima_tpm_chip;
 
 /* IMA event related data */
 struct ima_event_data {
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 4e085a17124f..88082f35adb2 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -634,7 +634,7 @@ static void __init ima_pcrread(int idx, u8 *pcr)
 	if (!ima_used_chip)
 		return;
 
-	if (tpm_pcr_read(NULL, idx, pcr) != 0)
+	if (tpm_pcr_read(ima_tpm_chip, idx, pcr) != 0)
 		pr_err("Error Communicating to TPM chip\n");
 }
 
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 29b72cd2502e..1437ed3dbccc 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -27,6 +27,7 @@
 /* name for boot aggregate entry */
 static const char *boot_aggregate_name = "boot_aggregate";
 int ima_used_chip;
+struct tpm_chip *ima_tpm_chip;
 
 /* Add the boot aggregate to the IMA measurement list and extend
  * the PCR register.
@@ -106,17 +107,13 @@ void __init ima_load_x509(void)
 
 int __init ima_init(void)
 {
-	u8 pcr_i[TPM_DIGEST_SIZE];
 	int rc;
 
-	ima_used_chip = 0;
-	rc = tpm_pcr_read(NULL, 0, pcr_i);
-	if (rc == 0)
-		ima_used_chip = 1;
+	ima_tpm_chip = tpm_default_chip();
 
+	ima_used_chip = ima_tpm_chip != NULL;
 	if (!ima_used_chip)
-		pr_info("No TPM chip found, activating TPM-bypass! (rc=%d)\n",
-			rc);
+		pr_info("No TPM chip found, activating TPM-bypass!\n");
 
 	rc = integrity_init_keyring(INTEGRITY_KEYRING_IMA);
 	if (rc)
diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c
index 418f35e38015..c6303fa19a49 100644
--- a/security/integrity/ima/ima_queue.c
+++ b/security/integrity/ima/ima_queue.c
@@ -145,7 +145,7 @@ static int ima_pcr_extend(const u8 *hash, int pcr)
 	if (!ima_used_chip)
 		return result;
 
-	result = tpm_pcr_extend(NULL, pcr, hash);
+	result = tpm_pcr_extend(ima_tpm_chip, pcr, hash);
 	if (result != 0)
 		pr_err("Error Communicating to TPM chip, result: %d\n", result);
 	return result;
-- 
cgit v1.2.3


From ec403d8ed08c8272cfeeeea154fdebcd289988c8 Mon Sep 17 00:00:00 2001
From: Stefan Berger <stefanb@linux.vnet.ibm.com>
Date: Tue, 26 Jun 2018 15:09:33 -0400
Subject: ima: Get rid of ima_used_chip and use ima_tpm_chip != NULL instead

Get rid of ima_used_chip and use ima_tpm_chip variable instead for
determining whether to use the TPM chip.

Signed-off-by: Stefan Berger <stefanb@linux.vnet.ibm.com>
Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 security/integrity/ima/ima.h        | 1 -
 security/integrity/ima/ima_crypto.c | 2 +-
 security/integrity/ima/ima_init.c   | 7 ++-----
 security/integrity/ima/ima_queue.c  | 2 +-
 4 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index dc212c59d4d6..588e4813370c 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -53,7 +53,6 @@ enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
 extern int ima_policy_flag;
 
 /* set during initialization */
-extern int ima_used_chip;
 extern int ima_hash_algo;
 extern int ima_appraise;
 extern struct tpm_chip *ima_tpm_chip;
diff --git a/security/integrity/ima/ima_crypto.c b/security/integrity/ima/ima_crypto.c
index 88082f35adb2..7e7e7e7c250a 100644
--- a/security/integrity/ima/ima_crypto.c
+++ b/security/integrity/ima/ima_crypto.c
@@ -631,7 +631,7 @@ int ima_calc_buffer_hash(const void *buf, loff_t len,
 
 static void __init ima_pcrread(int idx, u8 *pcr)
 {
-	if (!ima_used_chip)
+	if (!ima_tpm_chip)
 		return;
 
 	if (tpm_pcr_read(ima_tpm_chip, idx, pcr) != 0)
diff --git a/security/integrity/ima/ima_init.c b/security/integrity/ima/ima_init.c
index 1437ed3dbccc..faac9ecaa0ae 100644
--- a/security/integrity/ima/ima_init.c
+++ b/security/integrity/ima/ima_init.c
@@ -26,7 +26,6 @@
 
 /* name for boot aggregate entry */
 static const char *boot_aggregate_name = "boot_aggregate";
-int ima_used_chip;
 struct tpm_chip *ima_tpm_chip;
 
 /* Add the boot aggregate to the IMA measurement list and extend
@@ -65,7 +64,7 @@ static int __init ima_add_boot_aggregate(void)
 	iint->ima_hash->algo = HASH_ALGO_SHA1;
 	iint->ima_hash->length = SHA1_DIGEST_SIZE;
 
-	if (ima_used_chip) {
+	if (ima_tpm_chip) {
 		result = ima_calc_boot_aggregate(&hash.hdr);
 		if (result < 0) {
 			audit_cause = "hashing_error";
@@ -110,9 +109,7 @@ int __init ima_init(void)
 	int rc;
 
 	ima_tpm_chip = tpm_default_chip();
-
-	ima_used_chip = ima_tpm_chip != NULL;
-	if (!ima_used_chip)
+	if (!ima_tpm_chip)
 		pr_info("No TPM chip found, activating TPM-bypass!\n");
 
 	rc = integrity_init_keyring(INTEGRITY_KEYRING_IMA);
diff --git a/security/integrity/ima/ima_queue.c b/security/integrity/ima/ima_queue.c
index c6303fa19a49..b186819bd5aa 100644
--- a/security/integrity/ima/ima_queue.c
+++ b/security/integrity/ima/ima_queue.c
@@ -142,7 +142,7 @@ static int ima_pcr_extend(const u8 *hash, int pcr)
 {
 	int result = 0;
 
-	if (!ima_used_chip)
+	if (!ima_tpm_chip)
 		return result;
 
 	result = tpm_pcr_extend(ima_tpm_chip, pcr, hash);
-- 
cgit v1.2.3


From 55690c07b44a82cc3359ce0c233f4ba7d80ba145 Mon Sep 17 00:00:00 2001
From: Jinbum Park <jinb.park7@gmail.com>
Date: Sat, 28 Jul 2018 13:20:44 +0900
Subject: pktcdvd: Fix possible Spectre-v1 for pkt_devs

User controls @dev_minor which to be used as index of pkt_devs.
So, It can be exploited via Spectre-like attack. (speculative execution)

This kind of attack leaks address of pkt_devs, [1]
It leads an attacker to bypass security mechanism such as KASLR.

So sanitize @dev_minor before using it to prevent attack.

[1] https://github.com/jinb-park/linux-exploit/
tree/master/exploit-remaining-spectre-gadget/leak_pkt_devs.c

Signed-off-by: Jinbum Park <jinb.park7@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/pktcdvd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index a4b4d524c3af..9bb7721c26fc 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -67,7 +67,7 @@
 #include <scsi/scsi.h>
 #include <linux/debugfs.h>
 #include <linux/device.h>
-
+#include <linux/nospec.h>
 #include <linux/uaccess.h>
 
 #define DRIVER_NAME	"pktcdvd"
@@ -2254,6 +2254,8 @@ static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
 {
 	if (dev_minor >= MAX_WRITERS)
 		return NULL;
+
+	dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
 	return pkt_devs[dev_minor];
 }
 
-- 
cgit v1.2.3


From d77a4b4a5b0b2ebcbc9840995d91311ef28302ab Mon Sep 17 00:00:00 2001
From: Park Ju Hyung <qkrwngud825@gmail.com>
Date: Sat, 28 Jul 2018 03:16:21 +0900
Subject: ALSA: hda - Turn CX8200 into D3 as well upon reboot

As an equivalent codec with CX20724,
CX8200 is also subject to the reboot bug.

Late 2017 and 2018 LG Gram and some HP Spectre laptops are known victims
to this issue, causing extremely loud noises upon reboot.

Now that we know that this bug is subject to multiple codecs,
fix the comment as well.

Signed-off-by: Park Ju Hyung <qkrwngud825@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_conexant.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index f641c20095f7..909a880f5e01 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -211,6 +211,7 @@ static void cx_auto_reboot_notify(struct hda_codec *codec)
 	struct conexant_spec *spec = codec->spec;
 
 	switch (codec->core.vendor_id) {
+	case 0x14f12008: /* CX8200 */
 	case 0x14f150f2: /* CX20722 */
 	case 0x14f150f4: /* CX20724 */
 		break;
@@ -218,7 +219,7 @@ static void cx_auto_reboot_notify(struct hda_codec *codec)
 		return;
 	}
 
-	/* Turn the CX20722 codec into D3 to avoid spurious noises
+	/* Turn the problematic codec into D3 to avoid spurious noises
 	   from the internal speaker during (and after) reboot */
 	cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, false);
 
-- 
cgit v1.2.3


From f59cf9a0551dd954ad8b752461cf19d9789f4b1d Mon Sep 17 00:00:00 2001
From: Park Ju Hyung <qkrwngud825@gmail.com>
Date: Sat, 28 Jul 2018 03:16:42 +0900
Subject: ALSA: hda - Sleep for 10ms after entering D3 on Conexant codecs

On rare occasions, we are still noticing that the internal speaker
spitting out spurious noises even after adding the problematic codec
to the list.

Adding a 10ms artificial delay before rebooting fixes the issue entirely.

Patch for Realtek codecs also adds the same amount of delay after
entering D3.

Signed-off-by: Park Ju Hyung <qkrwngud825@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_conexant.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
index 909a880f5e01..1a8a2d440fbd 100644
--- a/sound/pci/hda/patch_conexant.c
+++ b/sound/pci/hda/patch_conexant.c
@@ -226,6 +226,7 @@ static void cx_auto_reboot_notify(struct hda_codec *codec)
 	snd_hda_codec_set_power_to_all(codec, codec->core.afg, AC_PWRST_D3);
 	snd_hda_codec_write(codec, codec->core.afg, 0,
 			    AC_VERB_SET_POWER_STATE, AC_PWRST_D3);
+	msleep(10);
 }
 
 static void cx_auto_free(struct hda_codec *codec)
-- 
cgit v1.2.3


From ea5569ecd6b81232eb536017b627c417befc1acb Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Tue, 24 Jul 2018 21:20:28 +0200
Subject: drm_dp_cec.c: fix formatting typo: %pdH -> %phD

This caused a kernel oops since %pdH interpreted the pointer
as a struct file.

Signed-off-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/f3720ddf-ec0f-cd22-46b6-720a5e2098f2@xs4all.nl
---
 drivers/gpu/drm/drm_dp_cec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/drm_dp_cec.c b/drivers/gpu/drm/drm_dp_cec.c
index ddb1c5adebb9..988513346e9c 100644
--- a/drivers/gpu/drm/drm_dp_cec.c
+++ b/drivers/gpu/drm/drm_dp_cec.c
@@ -157,7 +157,7 @@ static void drm_dp_cec_adap_status(struct cec_adapter *adap,
 
 	if (drm_dp_read_desc(aux, &desc, true))
 		return;
-	seq_printf(file, "OUI: %*pdH\n",
+	seq_printf(file, "OUI: %*phD\n",
 		   (int)sizeof(id->oui), id->oui);
 	seq_printf(file, "ID: %*pE\n",
 		   (int)strnlen(id->device_id, sizeof(id->device_id)),
-- 
cgit v1.2.3


From 2ead1be54b22ccdc93d3030172993e363128f1b4 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Date: Wed, 18 Jul 2018 21:40:45 -0300
Subject: drm/vkms: Fix connector leak at the module removal

Currently, vkms shows an error message if the following steps occur: (1)
load vkms, (2) perform any specific operation in the vkms (e.g., run an
IGT test), and (3) unload the module. The following error message
emerges:

[drm:drm_mode_config_cleanup [drm]] *ERROR* connector Virtual-1 leaked!

This commit fixes this error by calling drm_atomic_helper_shutdown()
before drm_mode_config_cleanup, which turns off the whole display
pipeline and remove a reference related to any connector.

Signed-off-by: Rodrigo Siqueira <rodrigosiqueiramelo@gmail.com>
Signed-off-by: Gustavo Padovan <gustavo.padovan@collabora.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180719004045.hzepp565x5lfco3c@smtp.gmail.com
---
 drivers/gpu/drm/vkms/vkms_drv.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index 37aa2ef33b21..6e728b825259 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -44,6 +44,7 @@ static void vkms_release(struct drm_device *dev)
 	struct vkms_device *vkms = container_of(dev, struct vkms_device, drm);
 
 	platform_device_unregister(vkms->platform);
+	drm_atomic_helper_shutdown(&vkms->drm);
 	drm_mode_config_cleanup(&vkms->drm);
 	drm_dev_fini(&vkms->drm);
 }
-- 
cgit v1.2.3


From ddc7c5721ae3554727f3e25e5c7510e278caf6be Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jcline@redhat.com>
Date: Sat, 28 Jul 2018 10:48:33 -0400
Subject: scripts: Add Python 3 support to tracing/draw_functrace.py

Use the print function. This maintains Python 2 support and should have
no functional change.

Signed-off-by: Jeremy Cline <jcline@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/tracing/draw_functrace.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/tracing/draw_functrace.py b/scripts/tracing/draw_functrace.py
index db40fa04cd51..9b6dd4f36335 100755
--- a/scripts/tracing/draw_functrace.py
+++ b/scripts/tracing/draw_functrace.py
@@ -123,7 +123,7 @@ def main():
 		tree = tree.getParent(caller)
 		tree = tree.calls(callee, calltime)
 
-	print CallTree.ROOT
+	print(CallTree.ROOT)
 
 if __name__ == "__main__":
 	main()
-- 
cgit v1.2.3


From 7a86f05faf112463cfbbdfd222012e247de461a1 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 18 Jul 2018 18:10:50 +0200
Subject: net: ethernet: mvneta: Fix napi structure mixup on armada 3700

The mvneta Ethernet driver is used on a few different Marvell SoCs.
Some SoCs have per cpu interrupts for Ethernet events. Some SoCs have
a single interrupt, independent of the CPU. The driver handles this by
having a per CPU napi structure when there are per CPU interrupts, and
a global napi structure when there is a single interrupt.

When the napi core calls mvneta_poll(), it passes the napi
instance. This was not being propagated through the call chain, and
instead the per-cpu napi instance was passed to napi_gro_receive()
call. This breaks when there is a single global napi instance.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Fixes: 2636ac3cc2b4 ("net: mvneta: Add network support for Armada 3700 SoC")
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 0ad2f3f7da85..ec84db47d82d 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1901,10 +1901,10 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 }
 
 /* Main rx processing when using software buffer management */
-static int mvneta_rx_swbm(struct mvneta_port *pp, int rx_todo,
+static int mvneta_rx_swbm(struct napi_struct *napi,
+			  struct mvneta_port *pp, int rx_todo,
 			  struct mvneta_rx_queue *rxq)
 {
-	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 	struct net_device *dev = pp->dev;
 	int rx_done;
 	u32 rcvd_pkts = 0;
@@ -1959,7 +1959,7 @@ err_drop_frame:
 
 			skb->protocol = eth_type_trans(skb, dev);
 			mvneta_rx_csum(pp, rx_status, skb);
-			napi_gro_receive(&port->napi, skb);
+			napi_gro_receive(napi, skb);
 
 			rcvd_pkts++;
 			rcvd_bytes += rx_bytes;
@@ -2001,7 +2001,7 @@ err_drop_frame:
 
 		mvneta_rx_csum(pp, rx_status, skb);
 
-		napi_gro_receive(&port->napi, skb);
+		napi_gro_receive(napi, skb);
 	}
 
 	if (rcvd_pkts) {
@@ -2020,10 +2020,10 @@ err_drop_frame:
 }
 
 /* Main rx processing when using hardware buffer management */
-static int mvneta_rx_hwbm(struct mvneta_port *pp, int rx_todo,
+static int mvneta_rx_hwbm(struct napi_struct *napi,
+			  struct mvneta_port *pp, int rx_todo,
 			  struct mvneta_rx_queue *rxq)
 {
-	struct mvneta_pcpu_port *port = this_cpu_ptr(pp->ports);
 	struct net_device *dev = pp->dev;
 	int rx_done;
 	u32 rcvd_pkts = 0;
@@ -2085,7 +2085,7 @@ err_drop_frame:
 
 			skb->protocol = eth_type_trans(skb, dev);
 			mvneta_rx_csum(pp, rx_status, skb);
-			napi_gro_receive(&port->napi, skb);
+			napi_gro_receive(napi, skb);
 
 			rcvd_pkts++;
 			rcvd_bytes += rx_bytes;
@@ -2129,7 +2129,7 @@ err_drop_frame:
 
 		mvneta_rx_csum(pp, rx_status, skb);
 
-		napi_gro_receive(&port->napi, skb);
+		napi_gro_receive(napi, skb);
 	}
 
 	if (rcvd_pkts) {
@@ -2722,9 +2722,11 @@ static int mvneta_poll(struct napi_struct *napi, int budget)
 	if (rx_queue) {
 		rx_queue = rx_queue - 1;
 		if (pp->bm_priv)
-			rx_done = mvneta_rx_hwbm(pp, budget, &pp->rxqs[rx_queue]);
+			rx_done = mvneta_rx_hwbm(napi, pp, budget,
+						 &pp->rxqs[rx_queue]);
 		else
-			rx_done = mvneta_rx_swbm(pp, budget, &pp->rxqs[rx_queue]);
+			rx_done = mvneta_rx_swbm(napi, pp, budget,
+						 &pp->rxqs[rx_queue]);
 	}
 
 	if (rx_done < budget) {
-- 
cgit v1.2.3


From 8466baf788ec3e18836bd9c91ba0b1a07af25878 Mon Sep 17 00:00:00 2001
From: Yelena Krivosheev <yelena@marvell.com>
Date: Wed, 18 Jul 2018 18:10:51 +0200
Subject: net: mvneta: fix mtu change on port without link

It is incorrect to enable TX/RX queues (call by mvneta_port_up()) for
port without link. Indeed MTU change for interface without link causes TX
queues to stuck.

Fixes: c5aff18204da ("net: mvneta: driver for Marvell Armada 370/XP
network unit")
Signed-off-by: Yelena Krivosheev <yelena@marvell.com>
[gregory.clement: adding Fixes tags and rewording commit log]
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index ec84db47d82d..3d1f4335b0d3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -3196,7 +3196,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 
 	on_each_cpu(mvneta_percpu_enable, pp, true);
 	mvneta_start_dev(pp);
-	mvneta_port_up(pp);
 
 	netdev_update_features(dev);
 
-- 
cgit v1.2.3


From 965cbbec7f207fef969d268fdabbcb779ec294ab Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Wed, 18 Jul 2018 18:10:52 +0200
Subject: net: mvneta: remove data pointer usage from device_node structure

On year ago Rob Herring wanted to remove the data pointer from the
device_node structure[1]. The mvneta driver seemed to be the only one
which used (abused ?) it. However, the proposal of Rob to remove this
pointer from the driver introduced a regression, and I tested and fixed an
alternative way, but it was never submitted as a proper patch.

Now here it is: Instead of using the device_node structure ->data
pointer, we store the BM private data as the driver data of the BM
platform_device. The core mvneta code can retrieve it by doing a lookup
on which platform_device corresponds to the BM device tree node using
of_find_device_by_node(), and get its driver data

[1]https://www.spinics.net/lists/netdev/msg445197.html

Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c    | 18 ++++++++++++------
 drivers/net/ethernet/marvell/mvneta_bm.c | 15 +++++++++++++++
 drivers/net/ethernet/marvell/mvneta_bm.h |  5 +++++
 3 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 3d1f4335b0d3..011794148ec8 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4461,12 +4461,16 @@ static int mvneta_probe(struct platform_device *pdev)
 
 	/* Obtain access to BM resources if enabled and already initialized */
 	bm_node = of_parse_phandle(dn, "buffer-manager", 0);
-	if (bm_node && bm_node->data) {
-		pp->bm_priv = bm_node->data;
-		err = mvneta_bm_port_init(pdev, pp);
-		if (err < 0) {
-			dev_info(&pdev->dev, "use SW buffer management\n");
-			pp->bm_priv = NULL;
+	if (bm_node) {
+		pp->bm_priv = mvneta_bm_get(bm_node);
+		if (pp->bm_priv) {
+			err = mvneta_bm_port_init(pdev, pp);
+			if (err < 0) {
+				dev_info(&pdev->dev,
+					 "use SW buffer management\n");
+				mvneta_bm_put(pp->bm_priv);
+				pp->bm_priv = NULL;
+			}
 		}
 	}
 	of_node_put(bm_node);
@@ -4527,6 +4531,7 @@ err_netdev:
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short,
 				       1 << pp->id);
+		mvneta_bm_put(pp->bm_priv);
 	}
 err_free_stats:
 	free_percpu(pp->stats);
@@ -4564,6 +4569,7 @@ static int mvneta_remove(struct platform_device *pdev)
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_long, 1 << pp->id);
 		mvneta_bm_pool_destroy(pp->bm_priv, pp->pool_short,
 				       1 << pp->id);
+		mvneta_bm_put(pp->bm_priv);
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c
index 466939f8f0cf..de468e1bdba9 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.c
+++ b/drivers/net/ethernet/marvell/mvneta_bm.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/skbuff.h>
 #include <net/hwbm.h>
@@ -392,6 +393,20 @@ static void mvneta_bm_put_sram(struct mvneta_bm *priv)
 		      MVNETA_BM_BPPI_SIZE);
 }
 
+struct mvneta_bm *mvneta_bm_get(struct device_node *node)
+{
+	struct platform_device *pdev = of_find_device_by_node(node);
+
+	return pdev ? platform_get_drvdata(pdev) : NULL;
+}
+EXPORT_SYMBOL_GPL(mvneta_bm_get);
+
+void mvneta_bm_put(struct mvneta_bm *priv)
+{
+	platform_device_put(priv->pdev);
+}
+EXPORT_SYMBOL_GPL(mvneta_bm_put);
+
 static int mvneta_bm_probe(struct platform_device *pdev)
 {
 	struct device_node *dn = pdev->dev.of_node;
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h
index a32de432800c..9358626e51ec 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.h
+++ b/drivers/net/ethernet/marvell/mvneta_bm.h
@@ -134,6 +134,9 @@ void *mvneta_frag_alloc(unsigned int frag_size);
 void mvneta_frag_free(unsigned int frag_size, void *data);
 
 #if IS_ENABLED(CONFIG_MVNETA_BM)
+struct mvneta_bm *mvneta_bm_get(struct device_node *node);
+void mvneta_bm_put(struct mvneta_bm *priv);
+
 void mvneta_bm_pool_destroy(struct mvneta_bm *priv,
 			    struct mvneta_bm_pool *bm_pool, u8 port_map);
 void mvneta_bm_bufs_free(struct mvneta_bm *priv, struct mvneta_bm_pool *bm_pool,
@@ -178,5 +181,7 @@ static inline void mvneta_bm_pool_put_bp(struct mvneta_bm *priv,
 static inline u32 mvneta_bm_pool_get_bp(struct mvneta_bm *priv,
 					struct mvneta_bm_pool *bm_pool)
 { return 0; }
+struct mvneta_bm *mvneta_bm_get(struct device_node *node) { return NULL; }
+void mvneta_bm_put(struct mvneta_bm *priv) {}
 #endif /* CONFIG_MVNETA_BM */
 #endif
-- 
cgit v1.2.3


From c307e2a895c9ce4040e68f034008c289209ce482 Mon Sep 17 00:00:00 2001
From: Yelena Krivosheev <yelena@marvell.com>
Date: Wed, 18 Jul 2018 18:10:53 +0200
Subject: net: mvneta: increase number of buffers in RX and TX queue

The initial values were too small leading to poor performance when using
the software buffer management.

Signed-off-by: Yelena Krivosheev <yelena@marvell.com>
[gregory: extract from a larger patch]
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 011794148ec8..e519439bac97 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -295,10 +295,10 @@
 #define MVNETA_RSS_LU_TABLE_SIZE	1
 
 /* Max number of Rx descriptors */
-#define MVNETA_MAX_RXD 128
+#define MVNETA_MAX_RXD 512
 
 /* Max number of Tx descriptors */
-#define MVNETA_MAX_TXD 532
+#define MVNETA_MAX_TXD 1024
 
 /* Max number of allowed TCP segments for software TSO */
 #define MVNETA_MAX_TSO_SEGS 100
-- 
cgit v1.2.3


From 17a96da627163d82776e2dc3198deef68cf077e0 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Wed, 18 Jul 2018 18:10:54 +0200
Subject: net: mvneta: discriminate error cause for missed packet

In order to improve the diagnostic in case of error, make the distinction
between refill error and skb allocation error. Also make the information
available through the ethtool state.

Based on the work of Yelena Krivosheev <yelena@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index e519439bac97..da2d56826295 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -328,6 +328,8 @@
 
 enum {
 	ETHTOOL_STAT_EEE_WAKEUP,
+	ETHTOOL_STAT_SKB_ALLOC_ERR,
+	ETHTOOL_STAT_REFILL_ERR,
 	ETHTOOL_MAX_STATS,
 };
 
@@ -375,6 +377,8 @@ static const struct mvneta_statistic mvneta_statistics[] = {
 	{ 0x3054, T_REG_32, "fc_sent", },
 	{ 0x300c, T_REG_32, "internal_mac_transmit_err", },
 	{ ETHTOOL_STAT_EEE_WAKEUP, T_SW, "eee_wakeup_errors", },
+	{ ETHTOOL_STAT_SKB_ALLOC_ERR, T_SW, "skb_alloc_errors", },
+	{ ETHTOOL_STAT_REFILL_ERR, T_SW, "refill_errors", },
 };
 
 struct mvneta_pcpu_stats {
@@ -589,9 +593,6 @@ struct mvneta_rx_queue {
 	/* num of rx descriptors in the rx descriptor ring */
 	int size;
 
-	/* counter of times when mvneta_refill() failed */
-	int missed;
-
 	u32 pkts_coal;
 	u32 time_coal;
 
@@ -609,6 +610,10 @@ struct mvneta_rx_queue {
 
 	/* Index of the next RX DMA descriptor to process */
 	int next_desc_to_proc;
+
+	/* error counters */
+	u32 skb_alloc_err;
+	u32 refill_err;
 };
 
 static enum cpuhp_state online_hpstate;
@@ -1946,8 +1951,13 @@ err_drop_frame:
 		if (rx_bytes <= rx_copybreak) {
 		/* better copy a small frame and not unmap the DMA region */
 			skb = netdev_alloc_skb_ip_align(dev, rx_bytes);
-			if (unlikely(!skb))
+			if (unlikely(!skb)) {
+				netdev_err(dev,
+					   "Can't allocate skb on queue %d\n",
+					   rxq->id);
+				rxq->skb_alloc_err++;
 				goto err_drop_frame;
+			}
 
 			dma_sync_single_range_for_cpu(dev->dev.parent,
 						      phys_addr,
@@ -1972,7 +1982,7 @@ err_drop_frame:
 		err = mvneta_rx_refill(pp, rx_desc, rxq);
 		if (err) {
 			netdev_err(dev, "Linux processing - Can't refill\n");
-			rxq->missed++;
+			rxq->refill_err++;
 			goto err_drop_frame;
 		}
 
@@ -2102,7 +2112,7 @@ err_drop_frame:
 		err = hwbm_pool_refill(&bm_pool->hwbm_pool, GFP_ATOMIC);
 		if (err) {
 			netdev_err(dev, "Linux processing - Can't refill\n");
-			rxq->missed++;
+			rxq->refill_err++;
 			goto err_drop_frame_ret_pool;
 		}
 
@@ -3963,6 +3973,12 @@ static void mvneta_ethtool_update_stats(struct mvneta_port *pp)
 			case ETHTOOL_STAT_EEE_WAKEUP:
 				val = phylink_get_eee_err(pp->phylink);
 				break;
+			case ETHTOOL_STAT_SKB_ALLOC_ERR:
+				val = pp->rxqs[0].skb_alloc_err;
+				break;
+			case ETHTOOL_STAT_REFILL_ERR:
+				val = pp->rxqs[0].refill_err;
+				break;
 			}
 			break;
 		}
-- 
cgit v1.2.3


From 7e47fd84b56bb37ff1c3d9ab49c2fff5ee4b3077 Mon Sep 17 00:00:00 2001
From: Gregory CLEMENT <gregory.clement@bootlin.com>
Date: Wed, 18 Jul 2018 18:10:55 +0200
Subject: net: mvneta: Allocate page for the descriptor

Instead of trying to allocate the exact amount of memory for each
descriptor use a page for each of them, it allows to simplify the
allocation management and increase the performance of the driver.

Based on the work of Yelena Krivosheev <yelena@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c    | 62 +++++++++++++-------------------
 drivers/net/ethernet/marvell/mvneta_bm.h |  3 --
 2 files changed, 24 insertions(+), 41 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index da2d56826295..6af583ef2af2 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1795,47 +1795,30 @@ static void mvneta_txq_done(struct mvneta_port *pp,
 	}
 }
 
-void *mvneta_frag_alloc(unsigned int frag_size)
-{
-	if (likely(frag_size <= PAGE_SIZE))
-		return netdev_alloc_frag(frag_size);
-	else
-		return kmalloc(frag_size, GFP_ATOMIC);
-}
-EXPORT_SYMBOL_GPL(mvneta_frag_alloc);
-
-void mvneta_frag_free(unsigned int frag_size, void *data)
-{
-	if (likely(frag_size <= PAGE_SIZE))
-		skb_free_frag(data);
-	else
-		kfree(data);
-}
-EXPORT_SYMBOL_GPL(mvneta_frag_free);
-
 /* Refill processing for SW buffer management */
+/* Allocate page per descriptor */
 static int mvneta_rx_refill(struct mvneta_port *pp,
 			    struct mvneta_rx_desc *rx_desc,
-			    struct mvneta_rx_queue *rxq)
-
+			    struct mvneta_rx_queue *rxq,
+			    gfp_t gfp_mask)
 {
 	dma_addr_t phys_addr;
-	void *data;
+	struct page *page;
 
-	data = mvneta_frag_alloc(pp->frag_size);
-	if (!data)
+	page = __dev_alloc_page(gfp_mask);
+	if (!page)
 		return -ENOMEM;
 
-	phys_addr = dma_map_single(pp->dev->dev.parent, data,
-				   MVNETA_RX_BUF_SIZE(pp->pkt_size),
-				   DMA_FROM_DEVICE);
+	/* map page for use */
+	phys_addr = dma_map_page(pp->dev->dev.parent, page, 0, PAGE_SIZE,
+				 DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(pp->dev->dev.parent, phys_addr))) {
-		mvneta_frag_free(pp->frag_size, data);
+		__free_page(page);
 		return -ENOMEM;
 	}
 
 	phys_addr += pp->rx_offset_correction;
-	mvneta_rx_desc_fill(rx_desc, phys_addr, data, rxq);
+	mvneta_rx_desc_fill(rx_desc, phys_addr, page, rxq);
 	return 0;
 }
 
@@ -1901,7 +1884,7 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 
 		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
-		mvneta_frag_free(pp->frag_size, data);
+		__free_page(data);
 	}
 }
 
@@ -1928,6 +1911,7 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
 		struct sk_buff *skb;
 		unsigned char *data;
+		struct page *page;
 		dma_addr_t phys_addr;
 		u32 rx_status, frag_size;
 		int rx_bytes, err, index;
@@ -1936,7 +1920,10 @@ static int mvneta_rx_swbm(struct napi_struct *napi,
 		rx_status = rx_desc->status;
 		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		index = rx_desc - rxq->descs;
-		data = rxq->buf_virt_addr[index];
+		page = (struct page *)rxq->buf_virt_addr[index];
+		data = page_address(page);
+		/* Prefetch header */
+		prefetch(data);
 		phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
 
 		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
@@ -1979,7 +1966,7 @@ err_drop_frame:
 		}
 
 		/* Refill processing */
-		err = mvneta_rx_refill(pp, rx_desc, rxq);
+		err = mvneta_rx_refill(pp, rx_desc, rxq, GFP_KERNEL);
 		if (err) {
 			netdev_err(dev, "Linux processing - Can't refill\n");
 			rxq->refill_err++;
@@ -2773,9 +2760,11 @@ static int mvneta_rxq_fill(struct mvneta_port *pp, struct mvneta_rx_queue *rxq,
 
 	for (i = 0; i < num; i++) {
 		memset(rxq->descs + i, 0, sizeof(struct mvneta_rx_desc));
-		if (mvneta_rx_refill(pp, rxq->descs + i, rxq) != 0) {
-			netdev_err(pp->dev, "%s:rxq %d, %d of %d buffs  filled\n",
-				__func__, rxq->id, i, num);
+		if (mvneta_rx_refill(pp, rxq->descs + i, rxq,
+				     GFP_KERNEL) != 0) {
+			netdev_err(pp->dev,
+				   "%s:rxq %d, %d of %d buffs  filled\n",
+				   __func__, rxq->id, i, num);
 			break;
 		}
 	}
@@ -3189,8 +3178,6 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu)
 		mvneta_bm_update_mtu(pp, mtu);
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(dev->mtu);
-	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
-	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret) {
@@ -3677,8 +3664,7 @@ static int mvneta_open(struct net_device *dev)
 	int ret;
 
 	pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu);
-	pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) +
-	                SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	pp->frag_size = PAGE_SIZE;
 
 	ret = mvneta_setup_rxqs(pp);
 	if (ret)
diff --git a/drivers/net/ethernet/marvell/mvneta_bm.h b/drivers/net/ethernet/marvell/mvneta_bm.h
index 9358626e51ec..c8425d35c049 100644
--- a/drivers/net/ethernet/marvell/mvneta_bm.h
+++ b/drivers/net/ethernet/marvell/mvneta_bm.h
@@ -130,9 +130,6 @@ struct mvneta_bm_pool {
 };
 
 /* Declarations and definitions */
-void *mvneta_frag_alloc(unsigned int frag_size);
-void mvneta_frag_free(unsigned int frag_size, void *data);
-
 #if IS_ENABLED(CONFIG_MVNETA_BM)
 struct mvneta_bm *mvneta_bm_get(struct device_node *node);
 void mvneta_bm_put(struct mvneta_bm *priv);
-- 
cgit v1.2.3


From f945cec88cbd2f66251a9f5b2532ca10c4e87426 Mon Sep 17 00:00:00 2001
From: Yelena Krivosheev <yelena@marvell.com>
Date: Wed, 18 Jul 2018 18:10:56 +0200
Subject: net: mvneta: Verify hardware checksum only when offload checksum
 feature is set

If the checksum offload feature is not set, then there is no point to
check the status of the hardware.

[gregory: extract from a larger patch]
Signed-off-by: Yelena Krivosheev <yelena@marvell.com>
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 6af583ef2af2..079b515c54c1 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1720,7 +1720,8 @@ static void mvneta_rx_error(struct mvneta_port *pp,
 static void mvneta_rx_csum(struct mvneta_port *pp, u32 status,
 			   struct sk_buff *skb)
 {
-	if ((status & MVNETA_RXD_L3_IP4) &&
+	if ((pp->dev->features & NETIF_F_RXCSUM) &&
+	    (status & MVNETA_RXD_L3_IP4) &&
 	    (status & MVNETA_RXD_L4_CSUM_OK)) {
 		skb->csum = 0;
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
-- 
cgit v1.2.3


From 562e2f467e71f45f0400ebee5077eaa426d3e426 Mon Sep 17 00:00:00 2001
From: Yelena Krivosheev <yelena@marvell.com>
Date: Wed, 18 Jul 2018 18:10:57 +0200
Subject: net: mvneta: Improve the buffer allocation method for SWBM

With system having a small memory (around 256MB), the state "cannot
allocate memory to refill with new buffer" is reach pretty quickly.

By this patch we changed buffer allocation method to a better handling of
this use case by avoiding memory allocation issues.

Signed-off-by: Yelena Krivosheev <yelena@marvell.com>
[gregory: extract from a larger patch]
Signed-off-by: Gregory CLEMENT <gregory.clement@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 281 ++++++++++++++++++++++------------
 1 file changed, 183 insertions(+), 98 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 079b515c54c1..55c2a56c5dae 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -483,7 +483,10 @@ struct mvneta_port {
 #define MVNETA_RXD_ERR_RESOURCE		(BIT(17) | BIT(18))
 #define MVNETA_RXD_ERR_CODE_MASK	(BIT(17) | BIT(18))
 #define MVNETA_RXD_L3_IP4		BIT(25)
-#define MVNETA_RXD_FIRST_LAST_DESC	(BIT(26) | BIT(27))
+#define MVNETA_RXD_LAST_DESC		BIT(26)
+#define MVNETA_RXD_FIRST_DESC		BIT(27)
+#define MVNETA_RXD_FIRST_LAST_DESC	(MVNETA_RXD_FIRST_DESC | \
+					 MVNETA_RXD_LAST_DESC)
 #define MVNETA_RXD_L4_CSUM_OK		BIT(30)
 
 #if defined(__LITTLE_ENDIAN)
@@ -611,6 +614,14 @@ struct mvneta_rx_queue {
 	/* Index of the next RX DMA descriptor to process */
 	int next_desc_to_proc;
 
+	/* Index of first RX DMA descriptor to refill */
+	int first_to_refill;
+	u32 refill_num;
+
+	/* pointer to uncomplete skb buffer */
+	struct sk_buff *skb;
+	int left_size;
+
 	/* error counters */
 	u32 skb_alloc_err;
 	u32 refill_err;
@@ -626,6 +637,7 @@ static int txq_number = 8;
 static int rxq_def;
 
 static int rx_copybreak __read_mostly = 256;
+static int rx_header_size __read_mostly = 128;
 
 /* HW BM need that each port be identify by a unique ID */
 static int global_port_id;
@@ -1689,13 +1701,6 @@ static void mvneta_rx_error(struct mvneta_port *pp,
 {
 	u32 status = rx_desc->status;
 
-	if (!mvneta_rxq_desc_is_first_last(status)) {
-		netdev_err(pp->dev,
-			   "bad rx status %08x (buffer oversize), size=%d\n",
-			   status, rx_desc->data_size);
-		return;
-	}
-
 	switch (status & MVNETA_RXD_ERR_CODE_MASK) {
 	case MVNETA_RXD_ERR_CRC:
 		netdev_err(pp->dev, "bad rx status %08x (crc error), size=%d\n",
@@ -1882,6 +1887,8 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 	for (i = 0; i < rxq->size; i++) {
 		struct mvneta_rx_desc *rx_desc = rxq->descs + i;
 		void *data = rxq->buf_virt_addr[i];
+		if (!data || !(rx_desc->buf_phys_addr))
+			continue;
 
 		dma_unmap_single(pp->dev->dev.parent, rx_desc->buf_phys_addr,
 				 MVNETA_RX_BUF_SIZE(pp->pkt_size), DMA_FROM_DEVICE);
@@ -1889,117 +1896,183 @@ static void mvneta_rxq_drop_pkts(struct mvneta_port *pp,
 	}
 }
 
+static inline
+int mvneta_rx_refill_queue(struct mvneta_port *pp, struct mvneta_rx_queue *rxq)
+{
+	struct mvneta_rx_desc *rx_desc;
+	int curr_desc = rxq->first_to_refill;
+	int i;
+
+	for (i = 0; (i < rxq->refill_num) && (i < 64); i++) {
+		rx_desc = rxq->descs + curr_desc;
+		if (!(rx_desc->buf_phys_addr)) {
+			if (mvneta_rx_refill(pp, rx_desc, rxq, GFP_ATOMIC)) {
+				pr_err("Can't refill queue %d. Done %d from %d\n",
+				       rxq->id, i, rxq->refill_num);
+				rxq->refill_err++;
+				break;
+			}
+		}
+		curr_desc = MVNETA_QUEUE_NEXT_DESC(rxq, curr_desc);
+	}
+	rxq->refill_num -= i;
+	rxq->first_to_refill = curr_desc;
+
+	return i;
+}
+
 /* Main rx processing when using software buffer management */
 static int mvneta_rx_swbm(struct napi_struct *napi,
-			  struct mvneta_port *pp, int rx_todo,
+			  struct mvneta_port *pp, int budget,
 			  struct mvneta_rx_queue *rxq)
 {
 	struct net_device *dev = pp->dev;
-	int rx_done;
+	int rx_todo, rx_proc;
+	int refill = 0;
 	u32 rcvd_pkts = 0;
 	u32 rcvd_bytes = 0;
 
 	/* Get number of received packets */
-	rx_done = mvneta_rxq_busy_desc_num_get(pp, rxq);
-
-	if (rx_todo > rx_done)
-		rx_todo = rx_done;
-
-	rx_done = 0;
+	rx_todo = mvneta_rxq_busy_desc_num_get(pp, rxq);
+	rx_proc = 0;
 
 	/* Fairness NAPI loop */
-	while (rx_done < rx_todo) {
+	while ((rcvd_pkts < budget) && (rx_proc < rx_todo)) {
 		struct mvneta_rx_desc *rx_desc = mvneta_rxq_next_desc_get(rxq);
-		struct sk_buff *skb;
 		unsigned char *data;
 		struct page *page;
 		dma_addr_t phys_addr;
-		u32 rx_status, frag_size;
-		int rx_bytes, err, index;
+		u32 rx_status, index;
+		int rx_bytes, skb_size, copy_size;
+		int frag_num, frag_size, frag_offset;
 
-		rx_done++;
-		rx_status = rx_desc->status;
-		rx_bytes = rx_desc->data_size - (ETH_FCS_LEN + MVNETA_MH_SIZE);
 		index = rx_desc - rxq->descs;
 		page = (struct page *)rxq->buf_virt_addr[index];
 		data = page_address(page);
 		/* Prefetch header */
 		prefetch(data);
-		phys_addr = rx_desc->buf_phys_addr - pp->rx_offset_correction;
 
-		if (!mvneta_rxq_desc_is_first_last(rx_status) ||
-		    (rx_status & MVNETA_RXD_ERR_SUMMARY)) {
-			mvneta_rx_error(pp, rx_desc);
-err_drop_frame:
-			dev->stats.rx_errors++;
-			/* leave the descriptor untouched */
-			continue;
-		}
+		phys_addr = rx_desc->buf_phys_addr;
+		rx_status = rx_desc->status;
+		rx_proc++;
+		rxq->refill_num++;
+
+		if (rx_status & MVNETA_RXD_FIRST_DESC) {
+			/* Check errors only for FIRST descriptor */
+			if (rx_status & MVNETA_RXD_ERR_SUMMARY) {
+				mvneta_rx_error(pp, rx_desc);
+				dev->stats.rx_errors++;
+				/* leave the descriptor untouched */
+				continue;
+			}
+			rx_bytes = rx_desc->data_size -
+				   (ETH_FCS_LEN + MVNETA_MH_SIZE);
 
-		if (rx_bytes <= rx_copybreak) {
-		/* better copy a small frame and not unmap the DMA region */
-			skb = netdev_alloc_skb_ip_align(dev, rx_bytes);
-			if (unlikely(!skb)) {
+			/* Allocate small skb for each new packet */
+			skb_size = max(rx_copybreak, rx_header_size);
+			rxq->skb = netdev_alloc_skb_ip_align(dev, skb_size);
+			if (unlikely(!rxq->skb)) {
 				netdev_err(dev,
 					   "Can't allocate skb on queue %d\n",
 					   rxq->id);
+				dev->stats.rx_dropped++;
 				rxq->skb_alloc_err++;
-				goto err_drop_frame;
+				continue;
 			}
+			copy_size = min(skb_size, rx_bytes);
+
+			/* Copy data from buffer to SKB, skip Marvell header */
+			memcpy(rxq->skb->data, data + MVNETA_MH_SIZE,
+			       copy_size);
+			skb_put(rxq->skb, copy_size);
+			rxq->left_size = rx_bytes - copy_size;
+
+			mvneta_rx_csum(pp, rx_status, rxq->skb);
+			if (rxq->left_size == 0) {
+				int size = copy_size + MVNETA_MH_SIZE;
+
+				dma_sync_single_range_for_cpu(dev->dev.parent,
+							      phys_addr, 0,
+							      size,
+							      DMA_FROM_DEVICE);
+
+				/* leave the descriptor and buffer untouched */
+			} else {
+				/* refill descriptor with new buffer later */
+				rx_desc->buf_phys_addr = 0;
+
+				frag_num = 0;
+				frag_offset = copy_size + MVNETA_MH_SIZE;
+				frag_size = min(rxq->left_size,
+						(int)(PAGE_SIZE - frag_offset));
+				skb_add_rx_frag(rxq->skb, frag_num, page,
+						frag_offset, frag_size,
+						PAGE_SIZE);
+				dma_unmap_single(dev->dev.parent, phys_addr,
+						 PAGE_SIZE, DMA_FROM_DEVICE);
+				rxq->left_size -= frag_size;
+			}
+		} else {
+			/* Middle or Last descriptor */
+			if (unlikely(!rxq->skb)) {
+				pr_debug("no skb for rx_status 0x%x\n",
+					 rx_status);
+				continue;
+			}
+			if (!rxq->left_size) {
+				/* last descriptor has only FCS */
+				/* and can be discarded */
+				dma_sync_single_range_for_cpu(dev->dev.parent,
+							      phys_addr, 0,
+							      ETH_FCS_LEN,
+							      DMA_FROM_DEVICE);
+				/* leave the descriptor and buffer untouched */
+			} else {
+				/* refill descriptor with new buffer later */
+				rx_desc->buf_phys_addr = 0;
+
+				frag_num = skb_shinfo(rxq->skb)->nr_frags;
+				frag_offset = 0;
+				frag_size = min(rxq->left_size,
+						(int)(PAGE_SIZE - frag_offset));
+				skb_add_rx_frag(rxq->skb, frag_num, page,
+						frag_offset, frag_size,
+						PAGE_SIZE);
+
+				dma_unmap_single(dev->dev.parent, phys_addr,
+						 PAGE_SIZE,
+						 DMA_FROM_DEVICE);
+
+				rxq->left_size -= frag_size;
+			}
+		} /* Middle or Last descriptor */
 
-			dma_sync_single_range_for_cpu(dev->dev.parent,
-						      phys_addr,
-						      MVNETA_MH_SIZE + NET_SKB_PAD,
-						      rx_bytes,
-						      DMA_FROM_DEVICE);
-			skb_put_data(skb, data + MVNETA_MH_SIZE + NET_SKB_PAD,
-				     rx_bytes);
-
-			skb->protocol = eth_type_trans(skb, dev);
-			mvneta_rx_csum(pp, rx_status, skb);
-			napi_gro_receive(napi, skb);
-
-			rcvd_pkts++;
-			rcvd_bytes += rx_bytes;
-
-			/* leave the descriptor and buffer untouched */
+		if (!(rx_status & MVNETA_RXD_LAST_DESC))
+			/* no last descriptor this time */
 			continue;
-		}
 
-		/* Refill processing */
-		err = mvneta_rx_refill(pp, rx_desc, rxq, GFP_KERNEL);
-		if (err) {
-			netdev_err(dev, "Linux processing - Can't refill\n");
-			rxq->refill_err++;
-			goto err_drop_frame;
+		if (rxq->left_size) {
+			pr_err("get last desc, but left_size (%d) != 0\n",
+			       rxq->left_size);
+			dev_kfree_skb_any(rxq->skb);
+			rxq->left_size = 0;
+			rxq->skb = NULL;
+			continue;
 		}
-
-		frag_size = pp->frag_size;
-
-		skb = build_skb(data, frag_size > PAGE_SIZE ? 0 : frag_size);
-
-		/* After refill old buffer has to be unmapped regardless
-		 * the skb is successfully built or not.
-		 */
-		dma_unmap_single(dev->dev.parent, phys_addr,
-				 MVNETA_RX_BUF_SIZE(pp->pkt_size),
-				 DMA_FROM_DEVICE);
-
-		if (!skb)
-			goto err_drop_frame;
-
 		rcvd_pkts++;
-		rcvd_bytes += rx_bytes;
+		rcvd_bytes += rxq->skb->len;
 
 		/* Linux processing */
-		skb_reserve(skb, MVNETA_MH_SIZE + NET_SKB_PAD);
-		skb_put(skb, rx_bytes);
-
-		skb->protocol = eth_type_trans(skb, dev);
+		rxq->skb->protocol = eth_type_trans(rxq->skb, dev);
 
-		mvneta_rx_csum(pp, rx_status, skb);
+		if (dev->features & NETIF_F_GRO)
+			napi_gro_receive(napi, rxq->skb);
+		else
+			netif_receive_skb(rxq->skb);
 
-		napi_gro_receive(napi, skb);
+		/* clean uncomplete skb pointer in queue */
+		rxq->skb = NULL;
+		rxq->left_size = 0;
 	}
 
 	if (rcvd_pkts) {
@@ -2011,10 +2084,13 @@ err_drop_frame:
 		u64_stats_update_end(&stats->syncp);
 	}
 
+	/* return some buffers to hardware queue, one at a time is too slow */
+	refill = mvneta_rx_refill_queue(pp, rxq);
+
 	/* Update rxq management counters */
-	mvneta_rxq_desc_num_update(pp, rxq, rx_done, rx_done);
+	mvneta_rxq_desc_num_update(pp, rxq, rx_proc, refill);
 
-	return rx_done;
+	return rcvd_pkts;
 }
 
 /* Main rx processing when using hardware buffer management */
@@ -2823,21 +2899,23 @@ static void mvneta_rxq_hw_init(struct mvneta_port *pp,
 	mvreg_write(pp, MVNETA_RXQ_BASE_ADDR_REG(rxq->id), rxq->descs_phys);
 	mvreg_write(pp, MVNETA_RXQ_SIZE_REG(rxq->id), rxq->size);
 
-	/* Set Offset */
-	mvneta_rxq_offset_set(pp, rxq, NET_SKB_PAD - pp->rx_offset_correction);
-
 	/* Set coalescing pkts and time */
 	mvneta_rx_pkts_coal_set(pp, rxq, rxq->pkts_coal);
 	mvneta_rx_time_coal_set(pp, rxq, rxq->time_coal);
 
 	if (!pp->bm_priv) {
-		/* Fill RXQ with buffers from RX pool */
-		mvneta_rxq_buf_size_set(pp, rxq,
-					MVNETA_RX_BUF_SIZE(pp->pkt_size));
+		/* Set Offset */
+		mvneta_rxq_offset_set(pp, rxq, 0);
+		mvneta_rxq_buf_size_set(pp, rxq, pp->frag_size);
 		mvneta_rxq_bm_disable(pp, rxq);
 		mvneta_rxq_fill(pp, rxq, rxq->size);
 	} else {
+		/* Set Offset */
+		mvneta_rxq_offset_set(pp, rxq,
+				      NET_SKB_PAD - pp->rx_offset_correction);
+
 		mvneta_rxq_bm_enable(pp, rxq);
+		/* Fill RXQ with buffers from RX pool */
 		mvneta_rxq_long_pool_set(pp, rxq);
 		mvneta_rxq_short_pool_set(pp, rxq);
 		mvneta_rxq_non_occup_desc_add(pp, rxq, rxq->size);
@@ -2866,6 +2944,9 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp,
 {
 	mvneta_rxq_drop_pkts(pp, rxq);
 
+	if (rxq->skb)
+		dev_kfree_skb_any(rxq->skb);
+
 	if (rxq->descs)
 		dma_free_coherent(pp->dev->dev.parent,
 				  rxq->size * MVNETA_DESC_ALIGNED_SIZE,
@@ -2876,6 +2957,10 @@ static void mvneta_rxq_deinit(struct mvneta_port *pp,
 	rxq->last_desc         = 0;
 	rxq->next_desc_to_proc = 0;
 	rxq->descs_phys        = 0;
+	rxq->first_to_refill   = 0;
+	rxq->refill_num        = 0;
+	rxq->skb               = NULL;
+	rxq->left_size         = 0;
 }
 
 static int mvneta_txq_sw_init(struct mvneta_port *pp,
@@ -4366,14 +4451,6 @@ static int mvneta_probe(struct platform_device *pdev)
 	pp->dn = dn;
 
 	pp->rxq_def = rxq_def;
-
-	/* Set RX packet offset correction for platforms, whose
-	 * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit
-	 * platforms and 0B for 32-bit ones.
-	 */
-	pp->rx_offset_correction =
-		max(0, NET_SKB_PAD - MVNETA_RX_PKT_OFFSET_CORRECTION);
-
 	pp->indir[0] = rxq_def;
 
 	/* Get special SoC configurations */
@@ -4461,6 +4538,7 @@ static int mvneta_probe(struct platform_device *pdev)
 	SET_NETDEV_DEV(dev, &pdev->dev);
 
 	pp->id = global_port_id++;
+	pp->rx_offset_correction = 0; /* not relevant for SW BM */
 
 	/* Obtain access to BM resources if enabled and already initialized */
 	bm_node = of_parse_phandle(dn, "buffer-manager", 0);
@@ -4475,6 +4553,13 @@ static int mvneta_probe(struct platform_device *pdev)
 				pp->bm_priv = NULL;
 			}
 		}
+		/* Set RX packet offset correction for platforms, whose
+		 * NET_SKB_PAD, exceeds 64B. It should be 64B for 64-bit
+		 * platforms and 0B for 32-bit ones.
+		 */
+		pp->rx_offset_correction = max(0,
+					       NET_SKB_PAD -
+					       MVNETA_RX_PKT_OFFSET_CORRECTION);
 	}
 	of_node_put(bm_node);
 
-- 
cgit v1.2.3


From 5a3611efe5b3095f348c892d040202b2ae969f4e Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Thu, 26 Jul 2018 07:59:35 -0700
Subject: tls: Remove dead code in tls_sw_sendmsg

tls_push_record either returns 0 on success or a negative value on failure.
This patch removes code that would only be executed if tls_push_record
were to return a positive value.

Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index f9971717f7e0..e80d70a1e138 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -423,12 +423,10 @@ alloc_encrypted:
 
 			copied += try_to_copy;
 			ret = tls_push_record(sk, msg->msg_flags, record_type);
-			if (!ret)
-				continue;
-			if (ret < 0)
+			if (ret)
 				goto send_end;
+			continue;
 
-			copied -= try_to_copy;
 fallback_to_reg_send:
 			iov_iter_revert(&msg->msg_iter,
 					ctx->sg_plaintext_size - orig_size);
-- 
cgit v1.2.3


From 2da19ed3e4a87db16c0f69039da9f17a9596c350 Mon Sep 17 00:00:00 2001
From: Doron Roberts-Kedes <doronrk@fb.com>
Date: Thu, 26 Jul 2018 07:59:36 -0700
Subject: tls: Fix improper revert in zerocopy_from_iter

The current code is problematic because the iov_iter is reverted and
never advanced in the non-error case. This patch skips the revert in the
non-error case. This patch also fixes the amount by which the iov_iter
is reverted. Currently, iov_iter is reverted by size, which can be
greater than the amount by which the iter was actually advanced.
Instead, only revert by the amount that the iter was advanced.

Fixes: 4718799817c5 ("tls: Fix zerocopy_from_iter iov handling")
Signed-off-by: Doron Roberts-Kedes <doronrk@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index e80d70a1e138..6deceb7c56ba 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -263,7 +263,7 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 			      int length, int *pages_used,
 			      unsigned int *size_used,
 			      struct scatterlist *to, int to_max_pages,
-			      bool charge, bool revert)
+			      bool charge)
 {
 	struct page *pages[MAX_SKB_FRAGS];
 
@@ -312,10 +312,10 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 	}
 
 out:
+	if (rc)
+		iov_iter_revert(from, size - *size_used);
 	*size_used = size;
 	*pages_used = num_elem;
-	if (revert)
-		iov_iter_revert(from, size);
 
 	return rc;
 }
@@ -417,7 +417,7 @@ alloc_encrypted:
 				&ctx->sg_plaintext_size,
 				ctx->sg_plaintext_data,
 				ARRAY_SIZE(ctx->sg_plaintext_data),
-				true, false);
+				true);
 			if (ret)
 				goto fallback_to_reg_send;
 
@@ -428,8 +428,6 @@ alloc_encrypted:
 			continue;
 
 fallback_to_reg_send:
-			iov_iter_revert(&msg->msg_iter,
-					ctx->sg_plaintext_size - orig_size);
 			trim_sg(sk, ctx->sg_plaintext_data,
 				&ctx->sg_plaintext_num_elem,
 				&ctx->sg_plaintext_size,
@@ -834,7 +832,7 @@ int tls_sw_recvmsg(struct sock *sk,
 				err = zerocopy_from_iter(sk, &msg->msg_iter,
 							 to_copy, &pages,
 							 &chunk, &sgin[1],
-							 MAX_SKB_FRAGS,	false, true);
+							 MAX_SKB_FRAGS,	false);
 				if (err < 0)
 					goto fallback_to_reg_recv;
 
-- 
cgit v1.2.3


From f69548ffafcc4942022f16f2f192b24143de1dba Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 12 Jul 2018 23:06:51 +0200
Subject: ALSA: hda/hdmi: Use single mutex unlock in error paths

Instead of calling mutex_unlock() at each error path multiple times,
take the standard goto-and-a-single-unlock approach.  This will
simplify the code and make easier to find the unbalanced mutex locks.

No functional changes, but only the code readability improvement as a
preliminary work for further changes.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_hdmi.c | 67 +++++++++++++++++++++++-----------------------
 1 file changed, 33 insertions(+), 34 deletions(-)

diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
index ee56359be9ee..cb587dce67a9 100644
--- a/sound/pci/hda/patch_hdmi.c
+++ b/sound/pci/hda/patch_hdmi.c
@@ -339,13 +339,13 @@ static int hdmi_eld_ctl_info(struct snd_kcontrol *kcontrol,
 	if (!per_pin) {
 		/* no pin is bound to the pcm */
 		uinfo->count = 0;
-		mutex_unlock(&spec->pcm_lock);
-		return 0;
+		goto unlock;
 	}
 	eld = &per_pin->sink_eld;
 	uinfo->count = eld->eld_valid ? eld->eld_size : 0;
-	mutex_unlock(&spec->pcm_lock);
 
+ unlock:
+	mutex_unlock(&spec->pcm_lock);
 	return 0;
 }
 
@@ -357,6 +357,7 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 	struct hdmi_spec_per_pin *per_pin;
 	struct hdmi_eld *eld;
 	int pcm_idx;
+	int err = 0;
 
 	pcm_idx = kcontrol->private_value;
 	mutex_lock(&spec->pcm_lock);
@@ -365,16 +366,15 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 		/* no pin is bound to the pcm */
 		memset(ucontrol->value.bytes.data, 0,
 		       ARRAY_SIZE(ucontrol->value.bytes.data));
-		mutex_unlock(&spec->pcm_lock);
-		return 0;
+		goto unlock;
 	}
-	eld = &per_pin->sink_eld;
 
+	eld = &per_pin->sink_eld;
 	if (eld->eld_size > ARRAY_SIZE(ucontrol->value.bytes.data) ||
 	    eld->eld_size > ELD_MAX_SIZE) {
-		mutex_unlock(&spec->pcm_lock);
 		snd_BUG();
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock;
 	}
 
 	memset(ucontrol->value.bytes.data, 0,
@@ -382,9 +382,10 @@ static int hdmi_eld_ctl_get(struct snd_kcontrol *kcontrol,
 	if (eld->eld_valid)
 		memcpy(ucontrol->value.bytes.data, eld->eld_buffer,
 		       eld->eld_size);
-	mutex_unlock(&spec->pcm_lock);
 
-	return 0;
+ unlock:
+	mutex_unlock(&spec->pcm_lock);
+	return err;
 }
 
 static const struct snd_kcontrol_new eld_bytes_ctl = {
@@ -1209,8 +1210,8 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 	pin_idx = hinfo_to_pin_index(codec, hinfo);
 	if (!spec->dyn_pcm_assign) {
 		if (snd_BUG_ON(pin_idx < 0)) {
-			mutex_unlock(&spec->pcm_lock);
-			return -EINVAL;
+			err = -EINVAL;
+			goto unlock;
 		}
 	} else {
 		/* no pin is assigned to the PCM
@@ -1218,16 +1219,13 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 		 */
 		if (pin_idx < 0) {
 			err = hdmi_pcm_open_no_pin(hinfo, codec, substream);
-			mutex_unlock(&spec->pcm_lock);
-			return err;
+			goto unlock;
 		}
 	}
 
 	err = hdmi_choose_cvt(codec, pin_idx, &cvt_idx);
-	if (err < 0) {
-		mutex_unlock(&spec->pcm_lock);
-		return err;
-	}
+	if (err < 0)
+		goto unlock;
 
 	per_cvt = get_cvt(spec, cvt_idx);
 	/* Claim converter */
@@ -1264,12 +1262,11 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 			per_cvt->assigned = 0;
 			hinfo->nid = 0;
 			snd_hda_spdif_ctls_unassign(codec, pcm_idx);
-			mutex_unlock(&spec->pcm_lock);
-			return -ENODEV;
+			err = -ENODEV;
+			goto unlock;
 		}
 	}
 
-	mutex_unlock(&spec->pcm_lock);
 	/* Store the updated parameters */
 	runtime->hw.channels_min = hinfo->channels_min;
 	runtime->hw.channels_max = hinfo->channels_max;
@@ -1278,7 +1275,9 @@ static int hdmi_pcm_open(struct hda_pcm_stream *hinfo,
 
 	snd_pcm_hw_constraint_step(substream->runtime, 0,
 				   SNDRV_PCM_HW_PARAM_CHANNELS, 2);
-	return 0;
+ unlock:
+	mutex_unlock(&spec->pcm_lock);
+	return err;
 }
 
 /*
@@ -1867,7 +1866,7 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	bool non_pcm;
 	int pinctl;
-	int err;
+	int err = 0;
 
 	mutex_lock(&spec->pcm_lock);
 	pin_idx = hinfo_to_pin_index(codec, hinfo);
@@ -1879,13 +1878,12 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 		pin_cvt_fixup(codec, NULL, cvt_nid);
 		snd_hda_codec_setup_stream(codec, cvt_nid,
 					stream_tag, 0, format);
-		mutex_unlock(&spec->pcm_lock);
-		return 0;
+		goto unlock;
 	}
 
 	if (snd_BUG_ON(pin_idx < 0)) {
-		mutex_unlock(&spec->pcm_lock);
-		return -EINVAL;
+		err = -EINVAL;
+		goto unlock;
 	}
 	per_pin = get_pin(spec, pin_idx);
 	pin_nid = per_pin->pin_nid;
@@ -1924,6 +1922,7 @@ static int generic_hdmi_playback_pcm_prepare(struct hda_pcm_stream *hinfo,
 	/* snd_hda_set_dev_select() has been called before */
 	err = spec->ops.setup_stream(codec, cvt_nid, pin_nid,
 				 stream_tag, format);
+ unlock:
 	mutex_unlock(&spec->pcm_lock);
 	return err;
 }
@@ -1945,6 +1944,7 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 	struct hdmi_spec_per_cvt *per_cvt;
 	struct hdmi_spec_per_pin *per_pin;
 	int pinctl;
+	int err = 0;
 
 	if (hinfo->nid) {
 		pcm_idx = hinfo_to_pcm_index(codec, hinfo);
@@ -1963,14 +1963,12 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 		snd_hda_spdif_ctls_unassign(codec, pcm_idx);
 		clear_bit(pcm_idx, &spec->pcm_in_use);
 		pin_idx = hinfo_to_pin_index(codec, hinfo);
-		if (spec->dyn_pcm_assign && pin_idx < 0) {
-			mutex_unlock(&spec->pcm_lock);
-			return 0;
-		}
+		if (spec->dyn_pcm_assign && pin_idx < 0)
+			goto unlock;
 
 		if (snd_BUG_ON(pin_idx < 0)) {
-			mutex_unlock(&spec->pcm_lock);
-			return -EINVAL;
+			err = -EINVAL;
+			goto unlock;
 		}
 		per_pin = get_pin(spec, pin_idx);
 
@@ -1989,10 +1987,11 @@ static int hdmi_pcm_close(struct hda_pcm_stream *hinfo,
 		per_pin->setup = false;
 		per_pin->channels = 0;
 		mutex_unlock(&per_pin->lock);
+	unlock:
 		mutex_unlock(&spec->pcm_lock);
 	}
 
-	return 0;
+	return err;
 }
 
 static const struct hda_pcm_ops generic_ops = {
-- 
cgit v1.2.3


From 5b9bfb8ec467b2017f36d7675434822271ce3d29 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 19 Jun 2018 16:02:28 +0200
Subject: m68k: mac: Use time64_t in RTC handling

The real-time clock on m68k (and powerpc) mac systems uses an unsigned
32-bit value starting in 1904, which overflows in 2040, about two years
later than everyone else, but this gets wrapped around in the Linux
code in 2038 already because of the deprecated usage of time_t and/or
long in the conversion.

Getting rid of the deprecated interfaces makes it work until 2040 as
documented, and it could be easily extended by reinterpreting
the resulting time64_t as a positive number. For the moment, I'm
adding a WARN_ON() that triggers if we encounter a time before 1970
or after 2040 (the two are indistinguishable).

This brings it in line with the corresponding code that we have on
powerpc macintosh.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
[fthain: Adopt __u32 for the union in via_read_time(), consistent with
	 changes to via_write_time()]
[fthain: Use lower_32_bits() in via_write_time(), consistent with changes
	 to pmu_write_time() and cuda_write_time()]
[fthain: Have via_read_time() return a time64_t, consistent with changes
	 to pmu_read_time() and cuda_read_time()]
[fthain: Drop the pointless wraparound conditional in via_read_time()]
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
[geert: Drop WARN_ON(), as it is reported to trigger on powermac]
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/mac/misc.c | 64 +++++++++++++++++++++++++++++-----------------------
 1 file changed, 36 insertions(+), 28 deletions(-)

diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index c68054361615..c2ff5059d3cc 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -26,33 +26,38 @@
 
 #include <asm/machdep.h>
 
-/* Offset between Unix time (1970-based) and Mac time (1904-based) */
+/*
+ * Offset between Unix time (1970-based) and Mac time (1904-based). Cuda and PMU
+ * times wrap in 2040. If we need to handle later times, the read_time functions
+ * need to be changed to interpret wrapped times as post-2040.
+ */
 
 #define RTC_OFFSET 2082844800
 
 static void (*rom_reset)(void);
 
 #ifdef CONFIG_ADB_CUDA
-static long cuda_read_time(void)
+static time64_t cuda_read_time(void)
 {
 	struct adb_request req;
-	long time;
+	time64_t time;
 
 	if (cuda_request(&req, NULL, 2, CUDA_PACKET, CUDA_GET_TIME) < 0)
 		return 0;
 	while (!req.complete)
 		cuda_poll();
 
-	time = (req.reply[3] << 24) | (req.reply[4] << 16) |
-	       (req.reply[5] << 8) | req.reply[6];
+	time = (u32)((req.reply[3] << 24) | (req.reply[4] << 16) |
+		     (req.reply[5] << 8) | req.reply[6]);
+
 	return time - RTC_OFFSET;
 }
 
-static void cuda_write_time(long data)
+static void cuda_write_time(time64_t time)
 {
 	struct adb_request req;
+	u32 data = lower_32_bits(time + RTC_OFFSET);
 
-	data += RTC_OFFSET;
 	if (cuda_request(&req, NULL, 6, CUDA_PACKET, CUDA_SET_TIME,
 			 (data >> 24) & 0xFF, (data >> 16) & 0xFF,
 			 (data >> 8) & 0xFF, data & 0xFF) < 0)
@@ -86,26 +91,27 @@ static void cuda_write_pram(int offset, __u8 data)
 #endif /* CONFIG_ADB_CUDA */
 
 #ifdef CONFIG_ADB_PMU68K
-static long pmu_read_time(void)
+static time64_t pmu_read_time(void)
 {
 	struct adb_request req;
-	long time;
+	time64_t time;
 
 	if (pmu_request(&req, NULL, 1, PMU_READ_RTC) < 0)
 		return 0;
 	while (!req.complete)
 		pmu_poll();
 
-	time = (req.reply[1] << 24) | (req.reply[2] << 16) |
-	       (req.reply[3] << 8) | req.reply[4];
+	time = (u32)((req.reply[1] << 24) | (req.reply[2] << 16) |
+		     (req.reply[3] << 8) | req.reply[4]);
+
 	return time - RTC_OFFSET;
 }
 
-static void pmu_write_time(long data)
+static void pmu_write_time(time64_t time)
 {
 	struct adb_request req;
+	u32 data = lower_32_bits(time + RTC_OFFSET);
 
-	data += RTC_OFFSET;
 	if (pmu_request(&req, NULL, 5, PMU_SET_RTC,
 			(data >> 24) & 0xFF, (data >> 16) & 0xFF,
 			(data >> 8) & 0xFF, data & 0xFF) < 0)
@@ -245,11 +251,11 @@ static void via_write_pram(int offset, __u8 data)
  * is basically any machine with Mac II-style ADB.
  */
 
-static long via_read_time(void)
+static time64_t via_read_time(void)
 {
 	union {
 		__u8 cdata[4];
-		long idata;
+		__u32 idata;
 	} result, last_result;
 	int count = 1;
 
@@ -270,7 +276,7 @@ static long via_read_time(void)
 		via_pram_command(0x8D, &result.cdata[0]);
 
 		if (result.idata == last_result.idata)
-			return result.idata - RTC_OFFSET;
+			return (time64_t)result.idata - RTC_OFFSET;
 
 		if (++count > 10)
 			break;
@@ -278,8 +284,8 @@ static long via_read_time(void)
 		last_result.idata = result.idata;
 	}
 
-	pr_err("via_read_time: failed to read a stable value; got 0x%08lx then 0x%08lx\n",
-	       last_result.idata, result.idata);
+	pr_err("%s: failed to read a stable value; got 0x%08x then 0x%08x\n",
+	       __func__, last_result.idata, result.idata);
 
 	return 0;
 }
@@ -291,11 +297,11 @@ static long via_read_time(void)
  * is basically any machine with Mac II-style ADB.
  */
 
-static void via_write_time(long time)
+static void via_write_time(time64_t time)
 {
 	union {
 		__u8 cdata[4];
-		long idata;
+		__u32 idata;
 	} data;
 	__u8 temp;
 
@@ -304,7 +310,7 @@ static void via_write_time(long time)
 	temp = 0x55;
 	via_pram_command(0x35, &temp);
 
-	data.idata = time + RTC_OFFSET;
+	data.idata = lower_32_bits(time + RTC_OFFSET);
 	via_pram_command(0x01, &data.cdata[3]);
 	via_pram_command(0x05, &data.cdata[2]);
 	via_pram_command(0x09, &data.cdata[1]);
@@ -585,12 +591,15 @@ void mac_reset(void)
  * This function translates seconds since 1970 into a proper date.
  *
  * Algorithm cribbed from glibc2.1, __offtime().
+ *
+ * This is roughly same as rtc_time64_to_tm(), which we should probably
+ * use here, but it's only available when CONFIG_RTC_LIB is enabled.
  */
 #define SECS_PER_MINUTE (60)
 #define SECS_PER_HOUR  (SECS_PER_MINUTE * 60)
 #define SECS_PER_DAY   (SECS_PER_HOUR * 24)
 
-static void unmktime(unsigned long time, long offset,
+static void unmktime(time64_t time, long offset,
 		     int *yearp, int *monp, int *dayp,
 		     int *hourp, int *minp, int *secp)
 {
@@ -602,11 +611,10 @@ static void unmktime(unsigned long time, long offset,
 		/* Leap years.  */
 		{ 0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366 }
 	};
-	long int days, rem, y, wday, yday;
+	int days, rem, y, wday, yday;
 	const unsigned short int *ip;
 
-	days = time / SECS_PER_DAY;
-	rem = time % SECS_PER_DAY;
+	days = div_u64_rem(time, SECS_PER_DAY, &rem);
 	rem += offset;
 	while (rem < 0) {
 		rem += SECS_PER_DAY;
@@ -657,7 +665,7 @@ static void unmktime(unsigned long time, long offset,
 
 int mac_hwclk(int op, struct rtc_time *t)
 {
-	unsigned long now;
+	time64_t now;
 
 	if (!op) { /* read */
 		switch (macintosh_config->adb_type) {
@@ -693,8 +701,8 @@ int mac_hwclk(int op, struct rtc_time *t)
 		         __func__, t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
 		         t->tm_hour, t->tm_min, t->tm_sec);
 
-		now = mktime(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
-			     t->tm_hour, t->tm_min, t->tm_sec);
+		now = mktime64(t->tm_year + 1900, t->tm_mon + 1, t->tm_mday,
+			       t->tm_hour, t->tm_min, t->tm_sec);
 
 		switch (macintosh_config->adb_type) {
 		case MAC_ADB_IOP:
-- 
cgit v1.2.3


From d7de1c3af18b1a638fc5211f8078ac427280d455 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 19 Jun 2018 16:02:29 +0200
Subject: m68k: Remove unused set_clock_mmss() helpers

Commit 397ac99c6cef ("m68k: remove dead timer code") removed set_rtc_mmss()
because it was unused in 2012. However, this was itself the only user of the
mach_set_clock_mmss() callback and the many implementations of that callback,
which are equally unused.

This removes all of those as well.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/apollo/config.c       |  8 ------
 arch/m68k/atari/config.c        |  5 ----
 arch/m68k/atari/time.c          | 63 -----------------------------------------
 arch/m68k/bvme6000/config.c     | 45 -----------------------------
 arch/m68k/include/asm/machdep.h |  1 -
 arch/m68k/kernel/setup_mm.c     |  1 -
 arch/m68k/kernel/setup_no.c     |  1 -
 arch/m68k/mac/config.c          |  2 --
 arch/m68k/mac/misc.c            | 16 -----------
 arch/m68k/mvme147/config.c      |  7 -----
 arch/m68k/mvme16x/config.c      |  8 ------
 arch/m68k/q40/config.c          | 30 --------------------
 12 files changed, 187 deletions(-)

diff --git a/arch/m68k/apollo/config.c b/arch/m68k/apollo/config.c
index b2a6bc63f8cd..aef8d42e078d 100644
--- a/arch/m68k/apollo/config.c
+++ b/arch/m68k/apollo/config.c
@@ -31,7 +31,6 @@ extern void dn_sched_init(irq_handler_t handler);
 extern void dn_init_IRQ(void);
 extern u32 dn_gettimeoffset(void);
 extern int dn_dummy_hwclk(int, struct rtc_time *);
-extern int dn_dummy_set_clock_mmss(unsigned long);
 extern void dn_dummy_reset(void);
 #ifdef CONFIG_HEARTBEAT
 static void dn_heartbeat(int on);
@@ -156,7 +155,6 @@ void __init config_apollo(void)
 	arch_gettimeoffset   = dn_gettimeoffset;
 	mach_max_dma_address = 0xffffffff;
 	mach_hwclk           = dn_dummy_hwclk; /* */
-	mach_set_clock_mmss  = dn_dummy_set_clock_mmss; /* */
 	mach_reset	     = dn_dummy_reset;  /* */
 #ifdef CONFIG_HEARTBEAT
 	mach_heartbeat = dn_heartbeat;
@@ -240,12 +238,6 @@ int dn_dummy_hwclk(int op, struct rtc_time *t) {
 
 }
 
-int dn_dummy_set_clock_mmss(unsigned long nowtime)
-{
-	pr_info("set_clock_mmss\n");
-	return 0;
-}
-
 void dn_dummy_reset(void) {
 
   dn_serial_print("The end !\n");
diff --git a/arch/m68k/atari/config.c b/arch/m68k/atari/config.c
index 565c6f06ab0b..bd96702a1ad0 100644
--- a/arch/m68k/atari/config.c
+++ b/arch/m68k/atari/config.c
@@ -81,9 +81,6 @@ extern void atari_sched_init(irq_handler_t);
 extern u32 atari_gettimeoffset(void);
 extern int atari_mste_hwclk (int, struct rtc_time *);
 extern int atari_tt_hwclk (int, struct rtc_time *);
-extern int atari_mste_set_clock_mmss (unsigned long);
-extern int atari_tt_set_clock_mmss (unsigned long);
-
 
 /* ++roman: This is a more elaborate test for an SCC chip, since the plain
  * Medusa board generates DTACK at the SCC's standard addresses, but a SCC
@@ -362,13 +359,11 @@ void __init config_atari(void)
 		ATARIHW_SET(TT_CLK);
 		pr_cont(" TT_CLK");
 		mach_hwclk = atari_tt_hwclk;
-		mach_set_clock_mmss = atari_tt_set_clock_mmss;
 	}
 	if (hwreg_present(&mste_rtc.sec_ones)) {
 		ATARIHW_SET(MSTE_CLK);
 		pr_cont(" MSTE_CLK");
 		mach_hwclk = atari_mste_hwclk;
-		mach_set_clock_mmss = atari_mste_set_clock_mmss;
 	}
 	if (!MACH_IS_MEDUSA && hwreg_present(&dma_wd.fdc_speed) &&
 	    hwreg_write(&dma_wd.fdc_speed, 0)) {
diff --git a/arch/m68k/atari/time.c b/arch/m68k/atari/time.c
index c549b48174ec..9cca64286464 100644
--- a/arch/m68k/atari/time.c
+++ b/arch/m68k/atari/time.c
@@ -285,69 +285,6 @@ int atari_tt_hwclk( int op, struct rtc_time *t )
     return( 0 );
 }
 
-
-int atari_mste_set_clock_mmss (unsigned long nowtime)
-{
-    short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-    struct MSTE_RTC val;
-    unsigned char rtc_minutes;
-
-    mste_read(&val);
-    rtc_minutes= val.min_ones + val.min_tens * 10;
-    if ((rtc_minutes < real_minutes
-         ? real_minutes - rtc_minutes
-         : rtc_minutes - real_minutes) < 30)
-    {
-        val.sec_ones = real_seconds % 10;
-        val.sec_tens = real_seconds / 10;
-        val.min_ones = real_minutes % 10;
-        val.min_tens = real_minutes / 10;
-        mste_write(&val);
-    }
-    else
-        return -1;
-    return 0;
-}
-
-int atari_tt_set_clock_mmss (unsigned long nowtime)
-{
-    int retval = 0;
-    short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-    unsigned char save_control, save_freq_select, rtc_minutes;
-
-    save_control = RTC_READ (RTC_CONTROL); /* tell the clock it's being set */
-    RTC_WRITE (RTC_CONTROL, save_control | RTC_SET);
-
-    save_freq_select = RTC_READ (RTC_FREQ_SELECT); /* stop and reset prescaler */
-    RTC_WRITE (RTC_FREQ_SELECT, save_freq_select | RTC_DIV_RESET2);
-
-    rtc_minutes = RTC_READ (RTC_MINUTES);
-    if (!(save_control & RTC_DM_BINARY))
-	rtc_minutes = bcd2bin(rtc_minutes);
-
-    /* Since we're only adjusting minutes and seconds, don't interfere
-       with hour overflow.  This avoids messing with unknown time zones
-       but requires your RTC not to be off by more than 30 minutes.  */
-    if ((rtc_minutes < real_minutes
-         ? real_minutes - rtc_minutes
-         : rtc_minutes - real_minutes) < 30)
-        {
-            if (!(save_control & RTC_DM_BINARY))
-                {
-		    real_seconds = bin2bcd(real_seconds);
-		    real_minutes = bin2bcd(real_minutes);
-                }
-            RTC_WRITE (RTC_SECONDS, real_seconds);
-            RTC_WRITE (RTC_MINUTES, real_minutes);
-        }
-    else
-        retval = -1;
-
-    RTC_WRITE (RTC_FREQ_SELECT, save_freq_select);
-    RTC_WRITE (RTC_CONTROL, save_control);
-    return retval;
-}
-
 /*
  * Local variables:
  *  c-indent-level: 4
diff --git a/arch/m68k/bvme6000/config.c b/arch/m68k/bvme6000/config.c
index 2cfff4765040..143ee9fa3893 100644
--- a/arch/m68k/bvme6000/config.c
+++ b/arch/m68k/bvme6000/config.c
@@ -41,7 +41,6 @@ static void bvme6000_get_model(char *model);
 extern void bvme6000_sched_init(irq_handler_t handler);
 extern u32 bvme6000_gettimeoffset(void);
 extern int bvme6000_hwclk (int, struct rtc_time *);
-extern int bvme6000_set_clock_mmss (unsigned long);
 extern void bvme6000_reset (void);
 void bvme6000_set_vectors (void);
 
@@ -113,7 +112,6 @@ void __init config_bvme6000(void)
     mach_init_IRQ        = bvme6000_init_IRQ;
     arch_gettimeoffset   = bvme6000_gettimeoffset;
     mach_hwclk           = bvme6000_hwclk;
-    mach_set_clock_mmss	 = bvme6000_set_clock_mmss;
     mach_reset		 = bvme6000_reset;
     mach_get_model       = bvme6000_get_model;
 
@@ -305,46 +303,3 @@ int bvme6000_hwclk(int op, struct rtc_time *t)
 
 	return 0;
 }
-
-/*
- * Set the minutes and seconds from seconds value 'nowtime'.  Fail if
- * clock is out by > 30 minutes.  Logic lifted from atari code.
- * Algorithm is to wait for the 10ms register to change, and then to
- * wait a short while, and then set it.
- */
-
-int bvme6000_set_clock_mmss (unsigned long nowtime)
-{
-	int retval = 0;
-	short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-	unsigned char rtc_minutes, rtc_tenms;
-	volatile RtcPtr_t rtc = (RtcPtr_t)BVME_RTC_BASE;
-	unsigned char msr = rtc->msr & 0xc0;
-	unsigned long flags;
-	volatile int i;
-
-	rtc->msr = 0;		/* Ensure clock accessible */
-	rtc_minutes = bcd2bin (rtc->bcd_min);
-
-	if ((rtc_minutes < real_minutes
-		? real_minutes - rtc_minutes
-			: rtc_minutes - real_minutes) < 30)
-	{
-		local_irq_save(flags);
-		rtc_tenms = rtc->bcd_tenms;
-		while (rtc_tenms == rtc->bcd_tenms)
-			;
-		for (i = 0; i < 1000; i++)
-			;
-		rtc->bcd_min = bin2bcd(real_minutes);
-		rtc->bcd_sec = bin2bcd(real_seconds);
-		local_irq_restore(flags);
-	}
-	else
-		retval = -1;
-
-	rtc->msr = msr;
-
-	return retval;
-}
-
diff --git a/arch/m68k/include/asm/machdep.h b/arch/m68k/include/asm/machdep.h
index 1605da48ebf2..49bd3266b4b1 100644
--- a/arch/m68k/include/asm/machdep.h
+++ b/arch/m68k/include/asm/machdep.h
@@ -22,7 +22,6 @@ extern int (*mach_hwclk)(int, struct rtc_time*);
 extern unsigned int (*mach_get_ss)(void);
 extern int (*mach_get_rtc_pll)(struct rtc_pll_info *);
 extern int (*mach_set_rtc_pll)(struct rtc_pll_info *);
-extern int (*mach_set_clock_mmss)(unsigned long);
 extern void (*mach_reset)( void );
 extern void (*mach_halt)( void );
 extern void (*mach_power_off)( void );
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index f35e3ebd6331..07244732eb41 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -88,7 +88,6 @@ void (*mach_get_hardware_list) (struct seq_file *m);
 /* machine dependent timer functions */
 int (*mach_hwclk) (int, struct rtc_time*);
 EXPORT_SYMBOL(mach_hwclk);
-int (*mach_set_clock_mmss) (unsigned long);
 unsigned int (*mach_get_ss)(void);
 int (*mach_get_rtc_pll)(struct rtc_pll_info *);
 int (*mach_set_rtc_pll)(struct rtc_pll_info *);
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index a98af1018201..3c53e4c366ac 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -51,7 +51,6 @@ char __initdata command_line[COMMAND_LINE_SIZE];
 
 /* machine dependent timer functions */
 void (*mach_sched_init)(irq_handler_t handler) __initdata = NULL;
-int (*mach_set_clock_mmss)(unsigned long);
 int (*mach_hwclk) (int, struct rtc_time*);
 
 /* machine dependent reboot functions */
diff --git a/arch/m68k/mac/config.c b/arch/m68k/mac/config.c
index d468a9d467a0..b02d7254b73a 100644
--- a/arch/m68k/mac/config.c
+++ b/arch/m68k/mac/config.c
@@ -57,7 +57,6 @@ static unsigned long mac_orig_videoaddr;
 /* Mac specific timer functions */
 extern u32 mac_gettimeoffset(void);
 extern int mac_hwclk(int, struct rtc_time *);
-extern int mac_set_clock_mmss(unsigned long);
 extern void iop_preinit(void);
 extern void iop_init(void);
 extern void via_init(void);
@@ -158,7 +157,6 @@ void __init config_mac(void)
 	mach_get_model = mac_get_model;
 	arch_gettimeoffset = mac_gettimeoffset;
 	mach_hwclk = mac_hwclk;
-	mach_set_clock_mmss = mac_set_clock_mmss;
 	mach_reset = mac_reset;
 	mach_halt = mac_poweroff;
 	mach_power_off = mac_poweroff;
diff --git a/arch/m68k/mac/misc.c b/arch/m68k/mac/misc.c
index c2ff5059d3cc..19e9d8eef1f2 100644
--- a/arch/m68k/mac/misc.c
+++ b/arch/m68k/mac/misc.c
@@ -727,19 +727,3 @@ int mac_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-/*
- * Set minutes/seconds in the hardware clock
- */
-
-int mac_set_clock_mmss (unsigned long nowtime)
-{
-	struct rtc_time now;
-
-	mac_hwclk(0, &now);
-	now.tm_sec = nowtime % 60;
-	now.tm_min = (nowtime / 60) % 60;
-	mac_hwclk(1, &now);
-
-	return 0;
-}
diff --git a/arch/m68k/mvme147/config.c b/arch/m68k/mvme147/config.c
index f8a710fd84cd..adea549d240e 100644
--- a/arch/m68k/mvme147/config.c
+++ b/arch/m68k/mvme147/config.c
@@ -40,7 +40,6 @@ static void mvme147_get_model(char *model);
 extern void mvme147_sched_init(irq_handler_t handler);
 extern u32 mvme147_gettimeoffset(void);
 extern int mvme147_hwclk (int, struct rtc_time *);
-extern int mvme147_set_clock_mmss (unsigned long);
 extern void mvme147_reset (void);
 
 
@@ -92,7 +91,6 @@ void __init config_mvme147(void)
 	mach_init_IRQ		= mvme147_init_IRQ;
 	arch_gettimeoffset	= mvme147_gettimeoffset;
 	mach_hwclk		= mvme147_hwclk;
-	mach_set_clock_mmss	= mvme147_set_clock_mmss;
 	mach_reset		= mvme147_reset;
 	mach_get_model		= mvme147_get_model;
 
@@ -164,8 +162,3 @@ int mvme147_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-int mvme147_set_clock_mmss (unsigned long nowtime)
-{
-	return 0;
-}
diff --git a/arch/m68k/mvme16x/config.c b/arch/m68k/mvme16x/config.c
index 4ffd9ef98de4..6ee36a5b528d 100644
--- a/arch/m68k/mvme16x/config.c
+++ b/arch/m68k/mvme16x/config.c
@@ -46,7 +46,6 @@ static void mvme16x_get_model(char *model);
 extern void mvme16x_sched_init(irq_handler_t handler);
 extern u32 mvme16x_gettimeoffset(void);
 extern int mvme16x_hwclk (int, struct rtc_time *);
-extern int mvme16x_set_clock_mmss (unsigned long);
 extern void mvme16x_reset (void);
 
 int bcd2int (unsigned char b);
@@ -280,7 +279,6 @@ void __init config_mvme16x(void)
     mach_init_IRQ        = mvme16x_init_IRQ;
     arch_gettimeoffset   = mvme16x_gettimeoffset;
     mach_hwclk           = mvme16x_hwclk;
-    mach_set_clock_mmss	 = mvme16x_set_clock_mmss;
     mach_reset		 = mvme16x_reset;
     mach_get_model       = mvme16x_get_model;
     mach_get_hardware_list = mvme16x_get_hardware_list;
@@ -411,9 +409,3 @@ int mvme16x_hwclk(int op, struct rtc_time *t)
 	}
 	return 0;
 }
-
-int mvme16x_set_clock_mmss (unsigned long nowtime)
-{
-	return 0;
-}
-
diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c
index 71c0867ecf20..96810d91da2b 100644
--- a/arch/m68k/q40/config.c
+++ b/arch/m68k/q40/config.c
@@ -43,7 +43,6 @@ extern void q40_sched_init(irq_handler_t handler);
 static u32 q40_gettimeoffset(void);
 static int q40_hwclk(int, struct rtc_time *);
 static unsigned int q40_get_ss(void);
-static int q40_set_clock_mmss(unsigned long);
 static int q40_get_rtc_pll(struct rtc_pll_info *pll);
 static int q40_set_rtc_pll(struct rtc_pll_info *pll);
 
@@ -175,7 +174,6 @@ void __init config_q40(void)
 	mach_get_ss = q40_get_ss;
 	mach_get_rtc_pll = q40_get_rtc_pll;
 	mach_set_rtc_pll = q40_set_rtc_pll;
-	mach_set_clock_mmss = q40_set_clock_mmss;
 
 	mach_reset = q40_reset;
 	mach_get_model = q40_get_model;
@@ -267,34 +265,6 @@ static unsigned int q40_get_ss(void)
 	return bcd2bin(Q40_RTC_SECS);
 }
 
-/*
- * Set the minutes and seconds from seconds value 'nowtime'.  Fail if
- * clock is out by > 30 minutes.  Logic lifted from atari code.
- */
-
-static int q40_set_clock_mmss(unsigned long nowtime)
-{
-	int retval = 0;
-	short real_seconds = nowtime % 60, real_minutes = (nowtime / 60) % 60;
-
-	int rtc_minutes;
-
-	rtc_minutes = bcd2bin(Q40_RTC_MINS);
-
-	if ((rtc_minutes < real_minutes ?
-	     real_minutes - rtc_minutes :
-	     rtc_minutes - real_minutes) < 30) {
-		Q40_RTC_CTRL |= Q40_RTC_WRITE;
-		Q40_RTC_MINS = bin2bcd(real_minutes);
-		Q40_RTC_SECS = bin2bcd(real_seconds);
-		Q40_RTC_CTRL &= ~(Q40_RTC_WRITE);
-	} else
-		retval = -1;
-
-	return retval;
-}
-
-
 /* get and set PLL calibration of RTC clock */
 #define Q40_RTC_PLL_MASK ((1<<5)-1)
 #define Q40_RTC_PLL_SIGN (1<<5)
-- 
cgit v1.2.3


From e295066f66a4fa78c39c29de7d7635e6957dd4f7 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 26 Jun 2018 18:41:11 +0200
Subject: m68k/io: Add missing ioremap define guards, fix typo

  - Add missing define guard for ioremap_wt(),
  - Move ARCH_HAS_IOREMAP_WT from <asm/io_mm.h> to <asm/kmap.h>, as it
    is applicable to Coldfire with MMU, too,
  - Fix typo s/ioremap_fillcache/ioremap_fullcache/,
  - Add define guard for iounmap() for consistency with other
    architectures.

Fixes: 9746882f547d2f00 ("m68k: group io mapping definitions and functions")
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
---
 arch/m68k/include/asm/io_mm.h | 2 --
 arch/m68k/include/asm/kmap.h  | 6 +++++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index fe485f4f5fac..7e518303786c 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -21,8 +21,6 @@
 
 #ifdef __KERNEL__
 
-#define ARCH_HAS_IOREMAP_WT
-
 #include <linux/compiler.h>
 #include <asm/raw_io.h>
 #include <asm/virtconvert.h>
diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h
index 84b8333db8ad..608e12f058a7 100644
--- a/arch/m68k/include/asm/kmap.h
+++ b/arch/m68k/include/asm/kmap.h
@@ -4,6 +4,8 @@
 
 #ifdef CONFIG_MMU
 
+#define ARCH_HAS_IOREMAP_WT
+
 /* Values for nocacheflag and cmode */
 #define IOMAP_FULL_CACHING		0
 #define IOMAP_NOCACHE_SER		1
@@ -16,6 +18,7 @@
  */
 extern void __iomem *__ioremap(unsigned long physaddr, unsigned long size,
 			       int cacheflag);
+#define iounmap iounmap
 extern void iounmap(void __iomem *addr);
 extern void __iounmap(void *addr, unsigned long size);
 
@@ -33,13 +36,14 @@ static inline void __iomem *ioremap_nocache(unsigned long physaddr,
 }
 
 #define ioremap_uc ioremap_nocache
+#define ioremap_wt ioremap_wt
 static inline void __iomem *ioremap_wt(unsigned long physaddr,
 				       unsigned long size)
 {
 	return __ioremap(physaddr, size, IOMAP_WRITETHROUGH);
 }
 
-#define ioremap_fillcache ioremap_fullcache
+#define ioremap_fullcache ioremap_fullcache
 static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
 					      unsigned long size)
 {
-- 
cgit v1.2.3


From 4042cd756e193f49469d31a23d5b85c4dca2a3b6 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 26 Jun 2018 20:32:22 +0200
Subject: net: mac8390: Use standard memcpy_{from,to}io()

The mac8390 driver defines its own variants of memcpy_fromio() and
memcpy_toio(), using similar implementations, but different function
signatures.

Remove the custom definitions of memcpy_fromio() and memcpy_toio(), and
adjust all callers to the standard signatures.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: David S. Miller <davem@davemloft.net>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
---
 drivers/net/ethernet/8390/mac8390.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/8390/mac8390.c b/drivers/net/ethernet/8390/mac8390.c
index b6d735bf8011..342ae08ec3c2 100644
--- a/drivers/net/ethernet/8390/mac8390.c
+++ b/drivers/net/ethernet/8390/mac8390.c
@@ -153,9 +153,6 @@ static void dayna_block_input(struct net_device *dev, int count,
 static void dayna_block_output(struct net_device *dev, int count,
 			       const unsigned char *buf, int start_page);
 
-#define memcpy_fromio(a, b, c)	memcpy((a), (void *)(b), (c))
-#define memcpy_toio(a, b, c)	memcpy((void *)(a), (b), (c))
-
 #define memcmp_withio(a, b, c)	memcmp((a), (void *)(b), (c))
 
 /* Slow Sane (16-bit chunk memory read/write) Cabletron uses this */
@@ -239,7 +236,7 @@ static enum mac8390_access mac8390_testio(unsigned long membase)
 	unsigned long outdata = 0xA5A0B5B0;
 	unsigned long indata =  0x00000000;
 	/* Try writing 32 bits */
-	memcpy_toio(membase, &outdata, 4);
+	memcpy_toio((void __iomem *)membase, &outdata, 4);
 	/* Now compare them */
 	if (memcmp_withio(&outdata, membase, 4) == 0)
 		return ACCESS_32;
@@ -711,7 +708,7 @@ static void sane_get_8390_hdr(struct net_device *dev,
 			      struct e8390_pkt_hdr *hdr, int ring_page)
 {
 	unsigned long hdr_start = (ring_page - WD_START_PG)<<8;
-	memcpy_fromio(hdr, dev->mem_start + hdr_start, 4);
+	memcpy_fromio(hdr, (void __iomem *)dev->mem_start + hdr_start, 4);
 	/* Fix endianness */
 	hdr->count = swab16(hdr->count);
 }
@@ -725,13 +722,16 @@ static void sane_block_input(struct net_device *dev, int count,
 	if (xfer_start + count > ei_status.rmem_end) {
 		/* We must wrap the input move. */
 		int semi_count = ei_status.rmem_end - xfer_start;
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base,
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
 			      semi_count);
 		count -= semi_count;
-		memcpy_fromio(skb->data + semi_count, ei_status.rmem_start,
-			      count);
+		memcpy_fromio(skb->data + semi_count,
+			      (void __iomem *)ei_status.rmem_start, count);
 	} else {
-		memcpy_fromio(skb->data, dev->mem_start + xfer_base, count);
+		memcpy_fromio(skb->data,
+			      (void __iomem *)dev->mem_start + xfer_base,
+			      count);
 	}
 }
 
@@ -740,7 +740,7 @@ static void sane_block_output(struct net_device *dev, int count,
 {
 	long shmem = (start_page - WD_START_PG)<<8;
 
-	memcpy_toio(dev->mem_start + shmem, buf, count);
+	memcpy_toio((void __iomem *)dev->mem_start + shmem, buf, count);
 }
 
 /* dayna block input/output */
-- 
cgit v1.2.3


From dae0c332b6b37bdb6eeed9df6fa168b10def8acc Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 2 Jul 2018 13:55:50 +0200
Subject: Input: hilkbd - Add casts to HP9000/300 I/O accessors

Internally, hilkbd uses "unsigned long" I/O addresses everywhere.
This works fine as:
  - On PA-RISC, hilkbd uses the gsc_{read,write}b() I/O accessors, which
    take "unsigned long" addresses,
  - On m68k, hilkbd uses {read,write}b(), which are currently mapped to
    {in,out}_8(), and convert the passed addresses to pointers
    internally.

However, the asm-generic version of {read,write}b() does not perform
such conversions, and requires passing pointers instead.  Hence add
casts to prepare for switching m68k to the asm-generic version.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/keyboard/hilkbd.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/keyboard/hilkbd.c b/drivers/input/keyboard/hilkbd.c
index a4e404aaf64b..5c7afdec192c 100644
--- a/drivers/input/keyboard/hilkbd.c
+++ b/drivers/input/keyboard/hilkbd.c
@@ -57,8 +57,8 @@ MODULE_LICENSE("GPL v2");
  #define HIL_DATA		0x1
  #define HIL_CMD		0x3
  #define HIL_IRQ		2
- #define hil_readb(p)		readb(p)
- #define hil_writeb(v,p)	writeb((v),(p))
+ #define hil_readb(p)		readb((const volatile void __iomem *)(p))
+ #define hil_writeb(v, p)	writeb((v), (volatile void __iomem *)(p))
 
 #else
 #error "HIL is not supported on this platform"
-- 
cgit v1.2.3


From ab4d391d2756086e34568f0ff84bc4fc7596e685 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 28 Jun 2018 10:54:35 +0200
Subject: m68k/io: Move mem*io define guards to <asm/kmap.h>

The mem*io define guards are applicable to all users of <asm/kmap.h>.
Hence move them, and drop the #ifdef.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
---
 arch/m68k/include/asm/io_no.h | 11 -----------
 arch/m68k/include/asm/kmap.h  |  3 +++
 2 files changed, 3 insertions(+), 11 deletions(-)

diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index 83a0a6d449f4..c207428fae59 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -131,17 +131,6 @@ static inline void writel(u32 value, volatile void __iomem *addr)
 #define PCI_SPACE_LIMIT	PCI_IO_MASK
 #endif /* CONFIG_PCI */
 
-/*
- * These are defined in kmap.h as static inline functions. To maintain
- * previous behavior we put these define guards here so io_mm.h doesn't
- * see them.
- */
-#ifdef CONFIG_MMU
-#define memset_io memset_io
-#define memcpy_fromio memcpy_fromio
-#define memcpy_toio memcpy_toio
-#endif
-
 #include <asm/kmap.h>
 #include <asm/virtconvert.h>
 #include <asm-generic/io.h>
diff --git a/arch/m68k/include/asm/kmap.h b/arch/m68k/include/asm/kmap.h
index 608e12f058a7..aac7f045f7f0 100644
--- a/arch/m68k/include/asm/kmap.h
+++ b/arch/m68k/include/asm/kmap.h
@@ -50,18 +50,21 @@ static inline void __iomem *ioremap_fullcache(unsigned long physaddr,
 	return __ioremap(physaddr, size, IOMAP_FULL_CACHING);
 }
 
+#define memset_io memset_io
 static inline void memset_io(volatile void __iomem *addr, unsigned char val,
 			     int count)
 {
 	__builtin_memset((void __force *) addr, val, count);
 }
 
+#define memcpy_fromio memcpy_fromio
 static inline void memcpy_fromio(void *dst, const volatile void __iomem *src,
 				 int count)
 {
 	__builtin_memcpy(dst, (void __force *) src, count);
 }
 
+#define memcpy_toio memcpy_toio
 static inline void memcpy_toio(volatile void __iomem *dst, const void *src,
 			       int count)
 {
-- 
cgit v1.2.3


From 781c4d6f5f278fc23687d6d224ddb452bb5ac368 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Thu, 28 Jun 2018 11:18:53 +0200
Subject: m68k/io: Switch mmu variant to <asm-generic/io.h>

The dummy functions defined in <asm/io_mm.h> can be provided by
<asm-generic/io.h>.

As nommu already uses <asm-generic/io.h>, move its inclusion to
<asm/io.h>, and add/adjust include guards where appropriate.

This gets rid of lots of "statement with no effect" and "unused
variable" warnings when compile-testing.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
---
 arch/m68k/include/asm/io.h    |  7 +++++++
 arch/m68k/include/asm/io_mm.h | 40 +++-------------------------------------
 arch/m68k/include/asm/io_no.h |  1 -
 3 files changed, 10 insertions(+), 38 deletions(-)

diff --git a/arch/m68k/include/asm/io.h b/arch/m68k/include/asm/io.h
index ca2849afb087..aabe6420ead2 100644
--- a/arch/m68k/include/asm/io.h
+++ b/arch/m68k/include/asm/io.h
@@ -1,6 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _M68K_IO_H
+#define _M68K_IO_H
+
 #if defined(__uClinux__) || defined(CONFIG_COLDFIRE)
 #include <asm/io_no.h>
 #else
 #include <asm/io_mm.h>
 #endif
+
+#include <asm-generic/io.h>
+
+#endif /* _M68K_IO_H */
diff --git a/arch/m68k/include/asm/io_mm.h b/arch/m68k/include/asm/io_mm.h
index 7e518303786c..782b78f8a048 100644
--- a/arch/m68k/include/asm/io_mm.h
+++ b/arch/m68k/include/asm/io_mm.h
@@ -16,8 +16,8 @@
  *    isa_readX(),isa_writeX()  are for ISA memory
  */
 
-#ifndef _IO_H
-#define _IO_H
+#ifndef _M68K_IO_MM_H
+#define _M68K_IO_MM_H
 
 #ifdef __KERNEL__
 
@@ -367,40 +367,6 @@ static inline void isa_delay(void)
 #define writew(val, addr)	out_le16((addr), (val))
 #endif /* CONFIG_ATARI_ROM_ISA */
 
-#if !defined(CONFIG_ISA) && !defined(CONFIG_ATARI_ROM_ISA)
-/*
- * We need to define dummy functions for GENERIC_IOMAP support.
- */
-#define inb(port)          0xff
-#define inb_p(port)        0xff
-#define outb(val,port)     ((void)0)
-#define outb_p(val,port)   ((void)0)
-#define inw(port)          0xffff
-#define inw_p(port)        0xffff
-#define outw(val,port)     ((void)0)
-#define outw_p(val,port)   ((void)0)
-#define inl(port)          0xffffffffUL
-#define inl_p(port)        0xffffffffUL
-#define outl(val,port)     ((void)0)
-#define outl_p(val,port)   ((void)0)
-
-#define insb(port,buf,nr)  ((void)0)
-#define outsb(port,buf,nr) ((void)0)
-#define insw(port,buf,nr)  ((void)0)
-#define outsw(port,buf,nr) ((void)0)
-#define insl(port,buf,nr)  ((void)0)
-#define outsl(port,buf,nr) ((void)0)
-
-/*
- * These should be valid on any ioremap()ed region
- */
-#define readb(addr)      in_8(addr)
-#define writeb(val,addr) out_8((addr),(val))
-#define readw(addr)      in_le16(addr)
-#define writew(val,addr) out_le16((addr),(val))
-
-#endif /* !CONFIG_ISA && !CONFIG_ATARI_ROM_ISA */
-
 #define readl(addr)      in_le32(addr)
 #define writel(val,addr) out_le32((addr),(val))
 
@@ -442,4 +408,4 @@ static inline void isa_delay(void)
 #define writew_relaxed(b, addr)	writew(b, addr)
 #define writel_relaxed(b, addr)	writel(b, addr)
 
-#endif /* _IO_H */
+#endif /* _M68K_IO_MM_H */
diff --git a/arch/m68k/include/asm/io_no.h b/arch/m68k/include/asm/io_no.h
index c207428fae59..0498192e1d98 100644
--- a/arch/m68k/include/asm/io_no.h
+++ b/arch/m68k/include/asm/io_no.h
@@ -133,6 +133,5 @@ static inline void writel(u32 value, volatile void __iomem *addr)
 
 #include <asm/kmap.h>
 #include <asm/virtconvert.h>
-#include <asm-generic/io.h>
 
 #endif /* _M68KNOMMU_IO_H */
-- 
cgit v1.2.3


From 384052e4ed274747fb96deb2df46a14d023a2986 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Wed, 4 Jul 2018 09:28:14 +0300
Subject: m68k/bitops: convert __ffs to match generic declaration

The generic bitops declare __ffs as

	static inline unsigned long __ffs(unsigned long word);

Convert the m68k version to match the generic declaration.

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/include/asm/bitops.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h
index 93b47b1f6fb4..54009ea710b3 100644
--- a/arch/m68k/include/asm/bitops.h
+++ b/arch/m68k/include/asm/bitops.h
@@ -454,7 +454,7 @@ static inline unsigned long ffz(unsigned long word)
  */
 #if (defined(__mcfisaaplus__) || defined(__mcfisac__)) && \
 	!defined(CONFIG_M68000) && !defined(CONFIG_MCPU32)
-static inline int __ffs(int x)
+static inline unsigned long __ffs(unsigned long x)
 {
 	__asm__ __volatile__ ("bitrev %0; ff1 %0"
 		: "=d" (x)
@@ -493,7 +493,11 @@ static inline int ffs(int x)
 		: "dm" (x & -x));
 	return 32 - cnt;
 }
-#define __ffs(x) (ffs(x) - 1)
+
+static inline unsigned long __ffs(unsigned long x)
+{
+	return ffs(x) - 1;
+}
 
 /*
  *	fls: find last bit set.
-- 
cgit v1.2.3


From 9e09221957c5cc6b70596c888651af0c7b052bd9 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Wed, 4 Jul 2018 09:28:15 +0300
Subject: m68k/page_no.h: force __va argument to be unsigned long

Add explicit casting to unsigned long to the __va() parameter

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/include/asm/page_no.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/m68k/include/asm/page_no.h b/arch/m68k/include/asm/page_no.h
index e644c4daf540..6bbe52025de3 100644
--- a/arch/m68k/include/asm/page_no.h
+++ b/arch/m68k/include/asm/page_no.h
@@ -18,7 +18,7 @@ extern unsigned long memory_end;
 #define __HAVE_ARCH_ALLOC_ZEROED_USER_HIGHPAGE
 
 #define __pa(vaddr)		((unsigned long)(vaddr))
-#define __va(paddr)		((void *)(paddr))
+#define __va(paddr)		((void *)((unsigned long)(paddr)))
 
 #define virt_to_pfn(kaddr)	(__pa(kaddr) >> PAGE_SHIFT)
 #define pfn_to_virt(pfn)	__va((pfn) << PAGE_SHIFT)
-- 
cgit v1.2.3


From 1008a11590b966b469e60dc3756c9226a685ce12 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Wed, 4 Jul 2018 09:28:16 +0300
Subject: m68k: switch to MEMBLOCK + NO_BOOTMEM

In m68k the physical memory is described by [memory_start, memory_end] for
!MMU variant and by m68k_memory array of memory ranges for the MMU version.
This information is directly use to register the physical memory with
memblock.

The reserve_bootmem() calls are replaced with memblock_reserve() and the
bootmap bitmap allocation is simply dropped.

Since the MMU variant creates early mappings only for the small part of the
memory we force bottom-up allocations in memblock.

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Greg Ungerer <gerg@linux-m68k.org>
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/Kconfig           |  3 +++
 arch/m68k/kernel/setup_mm.c | 14 ++++----------
 arch/m68k/kernel/setup_no.c | 20 ++++----------------
 arch/m68k/mm/init.c         |  1 -
 arch/m68k/mm/mcfmmu.c       | 13 +++++++------
 arch/m68k/mm/motorola.c     | 35 +++++++++++------------------------
 arch/m68k/sun3/config.c     |  4 ----
 7 files changed, 29 insertions(+), 61 deletions(-)

diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 3f61327da2d5..b29f93774d95 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -26,6 +26,9 @@ config M68K
 	select OLD_SIGSUSPEND3
 	select OLD_SIGACTION
 	select DMA_NONCOHERENT_OPS if HAS_DMA
+	select HAVE_MEMBLOCK
+	select ARCH_DISCARD_MEMBLOCK
+	select NO_BOOTMEM
 
 config CPU_BIG_ENDIAN
 	def_bool y
diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c
index 07244732eb41..5d3596c180f9 100644
--- a/arch/m68k/kernel/setup_mm.c
+++ b/arch/m68k/kernel/setup_mm.c
@@ -21,6 +21,7 @@
 #include <linux/string.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/module.h>
@@ -164,6 +165,8 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 					be32_to_cpu(m->addr);
 				m68k_memory[m68k_num_memory].size =
 					be32_to_cpu(m->size);
+				memblock_add(m68k_memory[m68k_num_memory].addr,
+					     m68k_memory[m68k_num_memory].size);
 				m68k_num_memory++;
 			} else
 				pr_warn("%s: too many memory chunks\n",
@@ -223,10 +226,6 @@ static void __init m68k_parse_bootinfo(const struct bi_record *record)
 
 void __init setup_arch(char **cmdline_p)
 {
-#ifndef CONFIG_SUN3
-	int i;
-#endif
-
 	/* The bootinfo is located right after the kernel */
 	if (!CPU_IS_COLDFIRE)
 		m68k_parse_bootinfo((const struct bi_record *)_end);
@@ -355,14 +354,9 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 #ifndef CONFIG_SUN3
-	for (i = 1; i < m68k_num_memory; i++)
-		free_bootmem_node(NODE_DATA(i), m68k_memory[i].addr,
-				  m68k_memory[i].size);
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (m68k_ramdisk.size) {
-		reserve_bootmem_node(__virt_to_node(phys_to_virt(m68k_ramdisk.addr)),
-				     m68k_ramdisk.addr, m68k_ramdisk.size,
-				     BOOTMEM_DEFAULT);
+		memblock_reserve(m68k_ramdisk.addr, m68k_ramdisk.size);
 		initrd_start = (unsigned long)phys_to_virt(m68k_ramdisk.addr);
 		initrd_end = initrd_start + m68k_ramdisk.size;
 		pr_info("initrd: %08lx - %08lx\n", initrd_start, initrd_end);
diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c
index 3c53e4c366ac..cfd5475bfc31 100644
--- a/arch/m68k/kernel/setup_no.c
+++ b/arch/m68k/kernel/setup_no.c
@@ -28,6 +28,7 @@
 #include <linux/errno.h>
 #include <linux/string.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/initrd.h>
@@ -85,8 +86,6 @@ void (*mach_power_off)(void);
 
 void __init setup_arch(char **cmdline_p)
 {
-	int bootmap_size;
-
 	memory_start = PAGE_ALIGN(_ramstart);
 	memory_end = _ramend;
 
@@ -141,6 +140,8 @@ void __init setup_arch(char **cmdline_p)
 	pr_debug("MEMORY -> ROMFS=0x%p-0x%06lx MEM=0x%06lx-0x%06lx\n ",
 		 __bss_stop, memory_start, memory_start, memory_end);
 
+	memblock_add(memory_start, memory_end - memory_start);
+
 	/* Keep a copy of command line */
 	*cmdline_p = &command_line[0];
 	memcpy(boot_command_line, command_line, COMMAND_LINE_SIZE);
@@ -157,23 +158,10 @@ void __init setup_arch(char **cmdline_p)
 	min_low_pfn = PFN_DOWN(memory_start);
 	max_pfn = max_low_pfn = PFN_DOWN(memory_end);
 
-	bootmap_size = init_bootmem_node(
-			NODE_DATA(0),
-			min_low_pfn,		/* map goes here */
-			PFN_DOWN(PAGE_OFFSET),
-			max_pfn);
-	/*
-	 * Free the usable memory, we have to make sure we do not free
-	 * the bootmem bitmap so we then reserve it after freeing it :-)
-	 */
-	free_bootmem(memory_start, memory_end - memory_start);
-	reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT);
-
 #if defined(CONFIG_UBOOT) && defined(CONFIG_BLK_DEV_INITRD)
 	if ((initrd_start > 0) && (initrd_start < initrd_end) &&
 			(initrd_end < memory_end))
-		reserve_bootmem(initrd_start, initrd_end - initrd_start,
-				 BOOTMEM_DEFAULT);
+		memblock_reserve(initrd_start, initrd_end - initrd_start);
 #endif /* if defined(CONFIG_BLK_DEV_INITRD) */
 
 	/*
diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c
index 8827b7f91402..38e2b272c220 100644
--- a/arch/m68k/mm/init.c
+++ b/arch/m68k/mm/init.c
@@ -71,7 +71,6 @@ void __init m68k_setup_node(int node)
 		pg_data_table[i] = pg_data_map + node;
 	}
 #endif
-	pg_data_map[node].bdata = bootmem_node_data + node;
 	node_set_online(node);
 }
 
diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c
index 2925d795d71a..70dde040779b 100644
--- a/arch/m68k/mm/mcfmmu.c
+++ b/arch/m68k/mm/mcfmmu.c
@@ -14,6 +14,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 
 #include <asm/setup.h>
 #include <asm/page.h>
@@ -153,31 +154,31 @@ int cf_tlb_miss(struct pt_regs *regs, int write, int dtlb, int extension_word)
 
 void __init cf_bootmem_alloc(void)
 {
-	unsigned long start_pfn;
 	unsigned long memstart;
 
 	/* _rambase and _ramend will be naturally page aligned */
 	m68k_memory[0].addr = _rambase;
 	m68k_memory[0].size = _ramend - _rambase;
 
+	memblock_add(m68k_memory[0].addr, m68k_memory[0].size);
+
 	/* compute total pages in system */
 	num_pages = PFN_DOWN(_ramend - _rambase);
 
 	/* page numbers */
 	memstart = PAGE_ALIGN(_ramstart);
 	min_low_pfn = PFN_DOWN(_rambase);
-	start_pfn = PFN_DOWN(memstart);
 	max_pfn = max_low_pfn = PFN_DOWN(_ramend);
 	high_memory = (void *)_ramend;
 
+	/* Reserve kernel text/data/bss */
+	memblock_reserve(memstart, memstart - _rambase);
+
 	m68k_virt_to_node_shift = fls(_ramend - 1) - 6;
 	module_fixup(NULL, __start_fixup, __stop_fixup);
 
-	/* setup bootmem data */
+	/* setup node data */
 	m68k_setup_node(0);
-	memstart += init_bootmem_node(NODE_DATA(0), start_pfn,
-		min_low_pfn, max_low_pfn);
-	free_bootmem_node(NODE_DATA(0), memstart, _ramend - memstart);
 }
 
 /*
diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c
index e490ecc7842c..4e17ecb5928a 100644
--- a/arch/m68k/mm/motorola.c
+++ b/arch/m68k/mm/motorola.c
@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/gfp.h>
 
 #include <asm/setup.h>
@@ -208,7 +209,7 @@ void __init paging_init(void)
 {
 	unsigned long zones_size[MAX_NR_ZONES] = { 0, };
 	unsigned long min_addr, max_addr;
-	unsigned long addr, size, end;
+	unsigned long addr;
 	int i;
 
 #ifdef DEBUG
@@ -253,34 +254,20 @@ void __init paging_init(void)
 	min_low_pfn = availmem >> PAGE_SHIFT;
 	max_pfn = max_low_pfn = max_addr >> PAGE_SHIFT;
 
-	for (i = 0; i < m68k_num_memory; i++) {
-		addr = m68k_memory[i].addr;
-		end = addr + m68k_memory[i].size;
-		m68k_setup_node(i);
-		availmem = PAGE_ALIGN(availmem);
-		availmem += init_bootmem_node(NODE_DATA(i),
-					      availmem >> PAGE_SHIFT,
-					      addr >> PAGE_SHIFT,
-					      end >> PAGE_SHIFT);
-	}
+	/* Reserve kernel text/data/bss and the memory allocated in head.S */
+	memblock_reserve(m68k_memory[0].addr, availmem - m68k_memory[0].addr);
 
 	/*
 	 * Map the physical memory available into the kernel virtual
-	 * address space. First initialize the bootmem allocator with
-	 * the memory we already mapped, so map_node() has something
-	 * to allocate.
+	 * address space. Make sure memblock will not try to allocate
+	 * pages beyond the memory we already mapped in head.S
 	 */
-	addr = m68k_memory[0].addr;
-	size = m68k_memory[0].size;
-	free_bootmem_node(NODE_DATA(0), availmem,
-			  min(m68k_init_mapped_size, size) - (availmem - addr));
-	map_node(0);
-	if (size > m68k_init_mapped_size)
-		free_bootmem_node(NODE_DATA(0), addr + m68k_init_mapped_size,
-				  size - m68k_init_mapped_size);
-
-	for (i = 1; i < m68k_num_memory; i++)
+	memblock_set_bottom_up(true);
+
+	for (i = 0; i < m68k_num_memory; i++) {
+		m68k_setup_node(i);
 		map_node(i);
+	}
 
 	flush_tlb_all();
 
diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c
index 1d28d380e8cc..79a2bb857906 100644
--- a/arch/m68k/sun3/config.c
+++ b/arch/m68k/sun3/config.c
@@ -123,10 +123,6 @@ static void __init sun3_bootmem_alloc(unsigned long memory_start,
 	availmem = memory_start;
 
 	m68k_setup_node(0);
-	availmem += init_bootmem(start_page, num_pages);
-	availmem = (availmem + (PAGE_SIZE-1)) & PAGE_MASK;
-
-	free_bootmem(__pa(availmem), memory_end - (availmem));
 }
 
 
-- 
cgit v1.2.3


From 71a896687b851477bfe2e7022cd4b597ab4f900d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Mon, 23 Jul 2018 10:28:38 +0200
Subject: m68k/defconfig: Update defconfigs for v4.18-rc6

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
---
 arch/m68k/configs/amiga_defconfig    | 32 ++++++++++++++++++++------------
 arch/m68k/configs/apollo_defconfig   | 30 ++++++++++++++++++------------
 arch/m68k/configs/atari_defconfig    | 29 +++++++++++++++++------------
 arch/m68k/configs/bvme6000_defconfig | 30 ++++++++++++++++++------------
 arch/m68k/configs/hp300_defconfig    | 30 ++++++++++++++++++------------
 arch/m68k/configs/mac_defconfig      | 30 ++++++++++++++++++------------
 arch/m68k/configs/multi_defconfig    | 32 ++++++++++++++++++++------------
 arch/m68k/configs/mvme147_defconfig  | 30 ++++++++++++++++++------------
 arch/m68k/configs/mvme16x_defconfig  | 30 ++++++++++++++++++------------
 arch/m68k/configs/q40_defconfig      | 30 ++++++++++++++++++------------
 arch/m68k/configs/sun3_defconfig     | 28 +++++++++++++++++-----------
 arch/m68k/configs/sun3x_defconfig    | 30 ++++++++++++++++++------------
 12 files changed, 218 insertions(+), 143 deletions(-)

diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index a874e54404d1..1d5483f6e457 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -52,6 +52,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -98,18 +99,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -122,6 +119,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -200,7 +198,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -231,7 +228,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -260,7 +256,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -356,6 +352,7 @@ CONFIG_A2091_SCSI=y
 CONFIG_GVP11_SCSI=y
 CONFIG_SCSI_A4000T=y
 CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
 CONFIG_MD=y
 CONFIG_MD_LINEAR=m
 CONFIG_BLK_DEV_DM=m
@@ -363,6 +360,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -402,8 +400,8 @@ CONFIG_A2065=y
 CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -412,8 +410,10 @@ CONFIG_ARIADNE=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
 CONFIG_HYDRA=y
 CONFIG_APNE=y
 CONFIG_ZORRO8390=y
@@ -426,9 +426,9 @@ CONFIG_ZORRO8390=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -478,6 +478,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -499,7 +500,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -600,6 +601,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -622,6 +624,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -657,6 +664,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index 8ce39e23aa42..52a0af127951 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -381,14 +378,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -400,9 +398,9 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -440,6 +438,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -458,7 +457,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -559,6 +558,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -581,6 +581,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -616,6 +621,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 346c4e75edf8..b3103e51268a 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -391,14 +388,15 @@ CONFIG_VETH=m
 CONFIG_ATARILANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
@@ -411,9 +409,9 @@ CONFIG_NE2000=y
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -480,7 +478,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -581,6 +579,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -603,6 +602,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -638,6 +642,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index fca9c7aa71a3..fb7d651a4cab 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_BVME6000_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index f9eab174915c..6b37f5537c39 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -50,6 +50,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -96,18 +97,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -120,6 +117,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -198,7 +196,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -229,7 +226,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -258,7 +254,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -299,6 +294,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -345,6 +341,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -382,14 +379,15 @@ CONFIG_VETH=m
 CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -401,9 +399,9 @@ CONFIG_HPLANCE=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -443,6 +441,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -460,7 +459,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -561,6 +560,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -583,6 +583,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -618,6 +623,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index b52e597899eb..930cc2965a11 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -49,6 +49,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -95,18 +96,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -119,6 +116,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -197,7 +195,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -228,7 +225,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -257,7 +253,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -301,6 +296,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -354,6 +350,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -398,8 +395,8 @@ CONFIG_VETH=m
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -407,6 +404,7 @@ CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -420,9 +418,9 @@ CONFIG_MAC8390=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -465,6 +463,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -482,7 +481,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -583,6 +582,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -605,6 +605,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -640,6 +645,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 2a84eeec5b02..e7dd25300127 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -59,6 +59,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -105,18 +106,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -129,6 +126,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -207,7 +205,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -238,7 +235,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -267,7 +263,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -311,6 +306,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -373,6 +369,7 @@ CONFIG_A2091_SCSI=y
 CONFIG_GVP11_SCSI=y
 CONFIG_SCSI_A4000T=y
 CONFIG_SCSI_ZORRO7XX=y
+CONFIG_SCSI_ZORRO_ESP=y
 CONFIG_ATARI_SCSI=y
 CONFIG_MAC_SCSI=y
 CONFIG_SCSI_MAC_ESP=y
@@ -387,6 +384,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -438,8 +436,8 @@ CONFIG_SUN3LANCE=y
 CONFIG_MACMACE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 CONFIG_MAC89x0=y
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -449,9 +447,11 @@ CONFIG_BVME6000_NET=y
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 CONFIG_MACSONIC=y
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
+CONFIG_XSURF100=y
 CONFIG_HYDRA=y
 CONFIG_MAC8390=y
 CONFIG_NE2000=y
@@ -466,9 +466,9 @@ CONFIG_ZORRO8390=y
 CONFIG_SMC91X=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -533,6 +533,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -562,7 +563,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -663,6 +664,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -685,6 +687,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -720,6 +727,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index 476e69994340..b383327fd77a 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -47,6 +47,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -93,18 +94,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -117,6 +114,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -195,7 +193,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -226,7 +223,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -255,7 +251,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -296,6 +291,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -343,6 +339,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_MVME147_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 1477cda9146e..9783d3deb9e9 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -344,6 +340,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -380,14 +377,15 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMAZON is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -399,9 +397,9 @@ CONFIG_MVME16x_NET=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -433,6 +431,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -450,7 +449,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -551,6 +550,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -573,6 +573,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -608,6 +613,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index b3a543dc48a0..a35d10ee10cb 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -48,6 +48,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -94,18 +95,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -118,6 +115,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -196,7 +194,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -227,7 +224,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -256,7 +252,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -297,6 +292,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -350,6 +346,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -388,8 +385,8 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_AMD is not set
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CIRRUS is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
@@ -398,6 +395,7 @@ CONFIG_VETH=m
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
 CONFIG_NE2000=y
@@ -410,9 +408,9 @@ CONFIG_NE2000=y
 # CONFIG_NET_VENDOR_SMSC is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PLIP=m
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
@@ -455,6 +453,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -473,7 +472,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -574,6 +573,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -596,6 +596,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -631,6 +636,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index d543ed5dfa96..573bf922d448 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -385,6 +382,7 @@ CONFIG_SUN3LANCE=y
 CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -397,9 +395,9 @@ CONFIG_SUN3_82586=y
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
 # CONFIG_NET_VENDOR_SUN is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -435,6 +433,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -574,6 +574,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -609,6 +614,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index a67e54246023..efb27a7fcc55 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -45,6 +45,7 @@ CONFIG_UNIX_DIAG=m
 CONFIG_TLS=m
 CONFIG_XFRM_MIGRATE=y
 CONFIG_NET_KEY=y
+CONFIG_XDP_SOCKETS=y
 CONFIG_INET=y
 CONFIG_IP_PNP=y
 CONFIG_IP_PNP_DHCP=y
@@ -91,18 +92,14 @@ CONFIG_NF_CONNTRACK_SANE=m
 CONFIG_NF_CONNTRACK_SIP=m
 CONFIG_NF_CONNTRACK_TFTP=m
 CONFIG_NF_TABLES=m
+CONFIG_NF_TABLES_SET=m
 CONFIG_NF_TABLES_INET=y
 CONFIG_NF_TABLES_NETDEV=y
-CONFIG_NFT_EXTHDR=m
-CONFIG_NFT_META=m
-CONFIG_NFT_RT=m
 CONFIG_NFT_NUMGEN=m
 CONFIG_NFT_CT=m
 CONFIG_NFT_FLOW_OFFLOAD=m
-CONFIG_NFT_SET_RBTREE=m
-CONFIG_NFT_SET_HASH=m
-CONFIG_NFT_SET_BITMAP=m
 CONFIG_NFT_COUNTER=m
+CONFIG_NFT_CONNLIMIT=m
 CONFIG_NFT_LOG=m
 CONFIG_NFT_LIMIT=m
 CONFIG_NFT_MASQ=m
@@ -115,6 +112,7 @@ CONFIG_NFT_REJECT=m
 CONFIG_NFT_COMPAT=m
 CONFIG_NFT_HASH=m
 CONFIG_NFT_FIB_INET=m
+CONFIG_NFT_SOCKET=m
 CONFIG_NFT_DUP_NETDEV=m
 CONFIG_NFT_FWD_NETDEV=m
 CONFIG_NFT_FIB_NETDEV=m
@@ -193,7 +191,6 @@ CONFIG_IP_SET_HASH_NETPORT=m
 CONFIG_IP_SET_HASH_NETIFACE=m
 CONFIG_IP_SET_LIST_SET=m
 CONFIG_NF_CONNTRACK_IPV4=m
-CONFIG_NF_SOCKET_IPV4=m
 CONFIG_NFT_CHAIN_ROUTE_IPV4=m
 CONFIG_NFT_DUP_IPV4=m
 CONFIG_NFT_FIB_IPV4=m
@@ -224,7 +221,6 @@ CONFIG_IP_NF_ARPTABLES=m
 CONFIG_IP_NF_ARPFILTER=m
 CONFIG_IP_NF_ARP_MANGLE=m
 CONFIG_NF_CONNTRACK_IPV6=m
-CONFIG_NF_SOCKET_IPV6=m
 CONFIG_NFT_CHAIN_ROUTE_IPV6=m
 CONFIG_NFT_CHAIN_NAT_IPV6=m
 CONFIG_NFT_MASQ_IPV6=m
@@ -253,7 +249,6 @@ CONFIG_IP6_NF_NAT=m
 CONFIG_IP6_NF_TARGET_MASQUERADE=m
 CONFIG_IP6_NF_TARGET_NPT=m
 CONFIG_NF_TABLES_BRIDGE=y
-CONFIG_NFT_BRIDGE_META=m
 CONFIG_NFT_BRIDGE_REJECT=m
 CONFIG_NF_LOG_BRIDGE=m
 CONFIG_BRIDGE_NF_EBTABLES=m
@@ -294,6 +289,7 @@ CONFIG_6LOWPAN_GHC_EXT_HDR_FRAG=m
 CONFIG_6LOWPAN_GHC_EXT_HDR_ROUTE=m
 CONFIG_DNS_RESOLVER=y
 CONFIG_BATMAN_ADV=m
+# CONFIG_BATMAN_ADV_BATMAN_V is not set
 CONFIG_BATMAN_ADV_DAT=y
 CONFIG_BATMAN_ADV_NC=y
 CONFIG_BATMAN_ADV_MCAST=y
@@ -341,6 +337,7 @@ CONFIG_DM_UNSTRIPED=m
 CONFIG_DM_CRYPT=m
 CONFIG_DM_SNAPSHOT=m
 CONFIG_DM_THIN_PROVISIONING=m
+CONFIG_DM_WRITECACHE=m
 CONFIG_DM_ERA=m
 CONFIG_DM_MIRROR=m
 CONFIG_DM_RAID=m
@@ -378,14 +375,15 @@ CONFIG_VETH=m
 CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_AQUANTIA is not set
 # CONFIG_NET_VENDOR_ARC is not set
-# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_BROADCOM is not set
+# CONFIG_NET_CADENCE is not set
 # CONFIG_NET_VENDOR_CORTINA is not set
 # CONFIG_NET_VENDOR_EZCHIP is not set
 # CONFIG_NET_VENDOR_HUAWEI is not set
 # CONFIG_NET_VENDOR_INTEL is not set
 # CONFIG_NET_VENDOR_MARVELL is not set
 # CONFIG_NET_VENDOR_MICREL is not set
+# CONFIG_NET_VENDOR_MICROSEMI is not set
 # CONFIG_NET_VENDOR_NATSEMI is not set
 # CONFIG_NET_VENDOR_NETRONOME is not set
 # CONFIG_NET_VENDOR_NI is not set
@@ -397,9 +395,9 @@ CONFIG_SUN3LANCE=y
 # CONFIG_NET_VENDOR_SOLARFLARE is not set
 # CONFIG_NET_VENDOR_SOCIONEXT is not set
 # CONFIG_NET_VENDOR_STMICRO is not set
+# CONFIG_NET_VENDOR_SYNOPSYS is not set
 # CONFIG_NET_VENDOR_VIA is not set
 # CONFIG_NET_VENDOR_WIZNET is not set
-# CONFIG_NET_VENDOR_SYNOPSYS is not set
 CONFIG_PPP=m
 CONFIG_PPP_BSDCOMP=m
 CONFIG_PPP_DEFLATE=m
@@ -435,6 +433,7 @@ CONFIG_HIDRAW=y
 CONFIG_UHID=m
 # CONFIG_HID_GENERIC is not set
 # CONFIG_HID_ITE is not set
+# CONFIG_HID_REDRAGON is not set
 # CONFIG_USB_SUPPORT is not set
 CONFIG_RTC_CLASS=y
 # CONFIG_RTC_NVMEM is not set
@@ -452,7 +451,7 @@ CONFIG_FS_ENCRYPTION=m
 CONFIG_FANOTIFY=y
 CONFIG_QUOTA_NETLINK_INTERFACE=y
 # CONFIG_PRINT_QUOTA_WARNING is not set
-CONFIG_AUTOFS4_FS=m
+CONFIG_AUTOFS_FS=m
 CONFIG_FUSE_FS=m
 CONFIG_CUSE=m
 CONFIG_OVERLAY_FS=m
@@ -553,6 +552,7 @@ CONFIG_TEST_KSTRTOX=m
 CONFIG_TEST_PRINTF=m
 CONFIG_TEST_BITMAP=m
 CONFIG_TEST_UUID=m
+CONFIG_TEST_OVERFLOW=m
 CONFIG_TEST_RHASHTABLE=m
 CONFIG_TEST_HASH=m
 CONFIG_TEST_USER_COPY=m
@@ -575,6 +575,11 @@ CONFIG_CRYPTO_CRYPTD=m
 CONFIG_CRYPTO_MCRYPTD=m
 CONFIG_CRYPTO_TEST=m
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_CRYPTO_AEGIS128=m
+CONFIG_CRYPTO_AEGIS128L=m
+CONFIG_CRYPTO_AEGIS256=m
+CONFIG_CRYPTO_MORUS640=m
+CONFIG_CRYPTO_MORUS1280=m
 CONFIG_CRYPTO_CFB=m
 CONFIG_CRYPTO_LRW=m
 CONFIG_CRYPTO_PCBC=m
@@ -610,6 +615,7 @@ CONFIG_CRYPTO_LZO=m
 CONFIG_CRYPTO_842=m
 CONFIG_CRYPTO_LZ4=m
 CONFIG_CRYPTO_LZ4HC=m
+CONFIG_CRYPTO_ZSTD=m
 CONFIG_CRYPTO_ANSI_CPRNG=m
 CONFIG_CRYPTO_DRBG_HASH=y
 CONFIG_CRYPTO_DRBG_CTR=y
-- 
cgit v1.2.3


From 5ae42de56b5328eed5cf58eeb39c662a903d252d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 27 Jul 2018 19:57:24 +0800
Subject: liquidio: remove redundant function cn23xx_dump_vf_iq_regs

There are no in-tree callers.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/cavium/liquidio/cn23xx_vf_device.c    | 30 ----------------------
 1 file changed, 30 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
index 91dce8b8ef7e..962bb62933db 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_vf_device.c
@@ -682,33 +682,3 @@ int cn23xx_setup_octeon_vf_device(struct octeon_device *oct)
 
 	return 0;
 }
-
-void cn23xx_dump_vf_iq_regs(struct octeon_device *oct)
-{
-	u32 regval, q_no;
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_DOORBELL_0 [0x%x]: 0x%016llx\n",
-		CN23XX_VF_SLI_IQ_DOORBELL(0),
-		CVM_CAST64(octeon_read_csr64(
-					oct, CN23XX_VF_SLI_IQ_DOORBELL(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_BASEADDR_0 [0x%x]: 0x%016llx\n",
-		CN23XX_VF_SLI_IQ_BASE_ADDR64(0),
-		CVM_CAST64(octeon_read_csr64(
-			oct, CN23XX_VF_SLI_IQ_BASE_ADDR64(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_FIFO_RSIZE_0 [0x%x]: 0x%016llx\n",
-		CN23XX_VF_SLI_IQ_SIZE(0),
-		CVM_CAST64(octeon_read_csr64(oct, CN23XX_VF_SLI_IQ_SIZE(0))));
-
-	for (q_no = 0; q_no < oct->sriov_info.rings_per_vf; q_no++) {
-		dev_dbg(&oct->pci_dev->dev, "SLI_PKT[%d]_INPUT_CTL [0x%x]: 0x%016llx\n",
-			q_no, CN23XX_VF_SLI_IQ_PKT_CONTROL64(q_no),
-			CVM_CAST64(octeon_read_csr64(
-				oct, CN23XX_VF_SLI_IQ_PKT_CONTROL64(q_no))));
-	}
-
-	pci_read_config_dword(oct->pci_dev, CN23XX_CONFIG_PCIE_DEVCTL, &regval);
-	dev_dbg(&oct->pci_dev->dev, "Config DevCtl [0x%x]: 0x%08x\n",
-		CN23XX_CONFIG_PCIE_DEVCTL, regval);
-}
-- 
cgit v1.2.3


From 4be90c79d6de941216fdaeb0e76647c48877ffd5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 27 Jul 2018 21:24:27 +0800
Subject: qed: remove redundant functions qed_set_gft_event_id_cm_hdr

There are no in-tree callers of qed_set_gft_event_id_cm_hdr.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
index d845badf9b90..d6430dfebd83 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_init_fw_funcs.c
@@ -1225,19 +1225,6 @@ void qed_gft_disable(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, u16 pf_id)
 	       0);
 }
 
-void qed_set_gft_event_id_cm_hdr(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
-{
-	u32 rfs_cm_hdr_event_id;
-
-	/* Set RFS event ID to be awakened i Tstorm By Prs */
-	rfs_cm_hdr_event_id = qed_rd(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT);
-	rfs_cm_hdr_event_id |= T_ETH_PACKET_ACTION_GFT_EVENTID <<
-			       PRS_REG_CM_HDR_GFT_EVENT_ID_SHIFT;
-	rfs_cm_hdr_event_id |= PARSER_ETH_CONN_GFT_ACTION_CM_HDR <<
-			       PRS_REG_CM_HDR_GFT_CM_HDR_SHIFT;
-	qed_wr(p_hwfn, p_ptt, PRS_REG_CM_HDR_GFT, rfs_cm_hdr_event_id);
-}
-
 void qed_gft_config(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt,
 		    u16 pf_id,
-- 
cgit v1.2.3


From d0c1f01138c4b7e532889474e3f2a485546d7270 Mon Sep 17 00:00:00 2001
From: Vincent Bernat <vincent@bernat.im>
Date: Wed, 25 Jul 2018 13:19:13 +0200
Subject: net/ipv6: allow any source address for sendmsg pktinfo with
 ip_nonlocal_bind

When freebind feature is set of an IPv6 socket, any source address can
be used when sending UDP datagrams using IPv6 PKTINFO ancillary
message. Global non-local bind feature was added in commit
35a256fee52c ("ipv6: Nonlocal bind") for IPv6. This commit also allows
IPv6 source address spoofing when non-local bind feature is enabled.

Signed-off-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/datagram.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 5a094f58fe8a..f0264dfd38de 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -803,7 +803,8 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 
 			if (addr_type != IPV6_ADDR_ANY) {
 				int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
-				if (!(inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
+				if (!(net->ipv6.sysctl.ip_nonlocal_bind ||
+				      inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
 				    !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr,
 							     dev, !strict, 0,
 							     IFA_F_TENTATIVE) &&
-- 
cgit v1.2.3


From a801e569970b9bdc2d1182266d559e610bfc0dc6 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:35:00 -0400
Subject: ext4: move ext4.txt into its own directory

Move Documentation/filesystems/ext4.txt into
Documentation/filesystems/ext4/ext4.rst in preparation for adding more
ext4 documentation.

Note that the documentation isn't in rst format yet, but as it's not
linked from anywhere it won't cause build errors.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4.txt      | 627 --------------------------------
 Documentation/filesystems/ext4/ext4.rst | 627 ++++++++++++++++++++++++++++++++
 2 files changed, 627 insertions(+), 627 deletions(-)
 delete mode 100644 Documentation/filesystems/ext4.txt
 create mode 100644 Documentation/filesystems/ext4/ext4.rst

diff --git a/Documentation/filesystems/ext4.txt b/Documentation/filesystems/ext4.txt
deleted file mode 100644
index 7f628b9f7c4b..000000000000
--- a/Documentation/filesystems/ext4.txt
+++ /dev/null
@@ -1,627 +0,0 @@
-
-Ext4 Filesystem
-===============
-
-Ext4 is an advanced level of the ext3 filesystem which incorporates
-scalability and reliability enhancements for supporting large filesystems
-(64 bit) in keeping with increasing disk capacities and state-of-the-art
-feature requirements.
-
-Mailing list:	linux-ext4@vger.kernel.org
-Web site:	http://ext4.wiki.kernel.org
-
-
-1. Quick usage instructions:
-===========================
-
-Note: More extensive information for getting started with ext4 can be
-      found at the ext4 wiki site at the URL:
-      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
-
-  - Compile and install the latest version of e2fsprogs (as of this
-    writing version 1.41.3) from:
-
-    http://sourceforge.net/project/showfiles.php?group_id=2406
-	
-	or
-
-    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
-
-	or grab the latest git repository from:
-
-    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
-
-  - Note that it is highly important to install the mke2fs.conf file
-    that comes with the e2fsprogs 1.41.x sources in /etc/mke2fs.conf. If
-    you have edited the /etc/mke2fs.conf file installed on your system,
-    you will need to merge your changes with the version from e2fsprogs
-    1.41.x.
-
-  - Create a new filesystem using the ext4 filesystem type:
-
-    	# mke2fs -t ext4 /dev/hda1
-
-    Or to configure an existing ext3 filesystem to support extents: 
-
-	# tune2fs -O extents /dev/hda1
-
-    If the filesystem was created with 128 byte inodes, it can be
-    converted to use 256 byte for greater efficiency via:
-
-        # tune2fs -I 256 /dev/hda1
-
-    (Note: we currently do not have tools to convert an ext4
-    filesystem back to ext3; so please do not do try this on production
-    filesystems.)
-
-  - Mounting:
-
-	# mount -t ext4 /dev/hda1 /wherever
-
-  - When comparing performance with other filesystems, it's always
-    important to try multiple workloads; very often a subtle change in a
-    workload parameter can completely change the ranking of which
-    filesystems do well compared to others.  When comparing versus ext3,
-    note that ext4 enables write barriers by default, while ext3 does
-    not enable write barriers by default.  So it is useful to use
-    explicitly specify whether barriers are enabled or not when via the
-    '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems
-    for a fair comparison.  When tuning ext3 for best benchmark numbers,
-    it is often worthwhile to try changing the data journaling mode; '-o
-    data=writeback' can be faster for some workloads.  (Note however that
-    running mounted with data=writeback can potentially leave stale data
-    exposed in recently written files in case of an unclean shutdown,
-    which could be a security exposure in some situations.)  Configuring
-    the filesystem with a large journal can also be helpful for
-    metadata-intensive workloads.
-
-2. Features
-===========
-
-2.1 Currently available
-
-* ability to use filesystems > 16TB (e2fsprogs support not available yet)
-* extent format reduces metadata overhead (RAM, IO for access, transactions)
-* extent format more robust in face of on-disk corruption due to magics,
-* internal redundancy in tree
-* improved file allocation (multi-block alloc)
-* lift 32000 subdirectory limit imposed by i_links_count[1]
-* nsec timestamps for mtime, atime, ctime, create time
-* inode version field on disk (NFSv4, Lustre)
-* reduced e2fsck time via uninit_bg feature
-* journal checksumming for robustness, performance
-* persistent file preallocation (e.g for streaming media, databases)
-* ability to pack bitmaps and inode tables into larger virtual groups via the
-  flex_bg feature
-* large file support
-* inode allocation using large virtual block groups via flex_bg
-* delayed allocation
-* large block (up to pagesize) support
-* efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force
-  the ordering)
-
-[1] Filesystems with a block size of 1k may see a limit imposed by the
-directory hash tree having a maximum depth of two.
-
-2.2 Candidate features for future inclusion
-
-* online defrag (patches available but not well tested)
-* reduced mke2fs time via lazy itable initialization in conjunction with
-  the uninit_bg feature (capability to do this is available in e2fsprogs
-  but a kernel thread to do lazy zeroing of unused inode table blocks
-  after filesystem is first mounted is required for safety)
-
-There are several others under discussion, whether they all make it in is
-partly a function of how much time everyone has to work on them. Features like
-metadata checksumming have been discussed and planned for a bit but no patches
-exist yet so I'm not sure they're in the near-term roadmap.
-
-The big performance win will come with mballoc, delalloc and flex_bg
-grouping of bitmaps and inode tables.  Some test results available here:
-
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
-
-3. Options
-==========
-
-When mounting an ext4 filesystem, the following option are accepted:
-(*) == default
-
-ro                   	Mount filesystem read only. Note that ext4 will
-                     	replay the journal (and thus write to the
-                     	partition) even when mounted "read only". The
-                     	mount options "ro,noload" can be used to prevent
-		     	writes to the filesystem.
-
-journal_checksum	Enable checksumming of the journal transactions.
-			This will allow the recovery code in e2fsck and the
-			kernel to detect corruption in the kernel.  It is a
-			compatible change and will be ignored by older kernels.
-
-journal_async_commit	Commit block can be written to disk without waiting
-			for descriptor blocks. If enabled older kernels cannot
-			mount the device. This will enable 'journal_checksum'
-			internally.
-
-journal_path=path
-journal_dev=devnum	When the external journal device's major/minor numbers
-			have changed, these options allow the user to specify
-			the new journal location.  The journal device is
-			identified through either its new major/minor numbers
-			encoded in devnum, or via a path to the device.
-
-norecovery		Don't load the journal on mounting.  Note that
-noload			if the filesystem was not unmounted cleanly,
-                     	skipping the journal replay will lead to the
-                     	filesystem containing inconsistencies that can
-                     	lead to any number of problems.
-
-data=journal		All data are committed into the journal prior to being
-			written into the main file system.  Enabling
-			this mode will disable delayed allocation and
-			O_DIRECT support.
-
-data=ordered	(*)	All data are forced directly out to the main file
-			system prior to its metadata being committed to the
-			journal.
-
-data=writeback		Data ordering is not preserved, data may be written
-			into the main file system after its metadata has been
-			committed to the journal.
-
-commit=nrsec	(*)	Ext4 can be told to sync all its data and metadata
-			every 'nrsec' seconds. The default value is 5 seconds.
-			This means that if you lose your power, you will lose
-			as much as the latest 5 seconds of work (your
-			filesystem will not be damaged though, thanks to the
-			journaling).  This default value (or any low value)
-			will hurt performance, but it's good for data-safety.
-			Setting it to 0 will have the same effect as leaving
-			it at the default (5 seconds).
-			Setting it to very large values will improve
-			performance.
-
-barrier=<0|1(*)>	This enables/disables the use of write barriers in
-barrier(*)		the jbd code.  barrier=0 disables, barrier=1 enables.
-nobarrier		This also requires an IO stack which can support
-			barriers, and if jbd gets an error on a barrier
-			write, it will disable again with a warning.
-			Write barriers enforce proper on-disk ordering
-			of journal commits, making volatile disk write caches
-			safe to use, at some performance penalty.  If
-			your disks are battery-backed in one way or another,
-			disabling barriers may safely improve performance.
-			The mount options "barrier" and "nobarrier" can
-			also be used to enable or disable barriers, for
-			consistency with other ext4 mount options.
-
-inode_readahead_blks=n	This tuning parameter controls the maximum
-			number of inode table blocks that ext4's inode
-			table readahead algorithm will pre-read into
-			the buffer cache.  The default value is 32 blocks.
-
-nouser_xattr		Disables Extended User Attributes.  See the
-			attr(5) manual page for more information about
-			extended attributes.
-
-noacl			This option disables POSIX Access Control List
-			support. If ACL support is enabled in the kernel
-			configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
-			enabled by default on mount. See the acl(5) manual
-			page for more information about acl.
-
-bsddf		(*)	Make 'df' act like BSD.
-minixdf			Make 'df' act like Minix.
-
-debug			Extra debugging information is sent to syslog.
-
-abort			Simulate the effects of calling ext4_abort() for
-			debugging purposes.  This is normally used while
-			remounting a filesystem which is already mounted.
-
-errors=remount-ro	Remount the filesystem read-only on an error.
-errors=continue		Keep going on a filesystem error.
-errors=panic		Panic and halt the machine if an error occurs.
-                        (These mount options override the errors behavior
-                        specified in the superblock, which can be configured
-                        using tune2fs)
-
-data_err=ignore(*)	Just print an error message if an error occurs
-			in a file data buffer in ordered mode.
-data_err=abort		Abort the journal if an error occurs in a file
-			data buffer in ordered mode.
-
-grpid			New objects have the group ID of their parent.
-bsdgroups
-
-nogrpid		(*)	New objects have the group ID of their creator.
-sysvgroups
-
-resgid=n		The group ID which may use the reserved blocks.
-
-resuid=n		The user ID which may use the reserved blocks.
-
-sb=n			Use alternate superblock at this location.
-
-quota			These options are ignored by the filesystem. They
-noquota			are used only by quota tools to recognize volumes
-grpquota		where quota should be turned on. See documentation
-usrquota		in the quota-tools package for more details
-			(http://sourceforge.net/projects/linuxquota).
-
-jqfmt=<quota type>	These options tell filesystem details about quota
-usrjquota=<file>	so that quota information can be properly updated
-grpjquota=<file>	during journal replay. They replace the above
-			quota options. See documentation in the quota-tools
-			package for more details
-			(http://sourceforge.net/projects/linuxquota).
-
-stripe=n		Number of filesystem blocks that mballoc will try
-			to use for allocation size and alignment. For RAID5/6
-			systems this should be the number of data
-			disks *  RAID chunk size in file system blocks.
-
-delalloc	(*)	Defer block allocation until just before ext4
-			writes out the block(s) in question.  This
-			allows ext4 to better allocation decisions
-			more efficiently.
-nodelalloc		Disable delayed allocation.  Blocks are allocated
-			when the data is copied from userspace to the
-			page cache, either via the write(2) system call
-			or when an mmap'ed page which was previously
-			unallocated is written for the first time.
-
-max_batch_time=usec	Maximum amount of time ext4 should wait for
-			additional filesystem operations to be batch
-			together with a synchronous write operation.
-			Since a synchronous write operation is going to
-			force a commit and then a wait for the I/O
-			complete, it doesn't cost much, and can be a
-			huge throughput win, we wait for a small amount
-			of time to see if any other transactions can
-			piggyback on the synchronous write.   The
-			algorithm used is designed to automatically tune
-			for the speed of the disk, by measuring the
-			amount of time (on average) that it takes to
-			finish committing a transaction.  Call this time
-			the "commit time".  If the time that the
-			transaction has been running is less than the
-			commit time, ext4 will try sleeping for the
-			commit time to see if other operations will join
-			the transaction.   The commit time is capped by
-			the max_batch_time, which defaults to 15000us
-			(15ms).   This optimization can be turned off
-			entirely by setting max_batch_time to 0.
-
-min_batch_time=usec	This parameter sets the commit time (as
-			described above) to be at least min_batch_time.
-			It defaults to zero microseconds.  Increasing
-			this parameter may improve the throughput of
-			multi-threaded, synchronous workloads on very
-			fast disks, at the cost of increasing latency.
-
-journal_ioprio=prio	The I/O priority (from 0 to 7, where 0 is the
-			highest priority) which should be used for I/O
-			operations submitted by kjournald2 during a
-			commit operation.  This defaults to 3, which is
-			a slightly higher priority than the default I/O
-			priority.
-
-auto_da_alloc(*)	Many broken applications don't use fsync() when 
-noauto_da_alloc		replacing existing files via patterns such as
-			fd = open("foo.new")/write(fd,..)/close(fd)/
-			rename("foo.new", "foo"), or worse yet,
-			fd = open("foo", O_TRUNC)/write(fd,..)/close(fd).
-			If auto_da_alloc is enabled, ext4 will detect
-			the replace-via-rename and replace-via-truncate
-			patterns and force that any delayed allocation
-			blocks are allocated such that at the next
-			journal commit, in the default data=ordered
-			mode, the data blocks of the new file are forced
-			to disk before the rename() operation is
-			committed.  This provides roughly the same level
-			of guarantees as ext3, and avoids the
-			"zero-length" problem that can happen when a
-			system crashes before the delayed allocation
-			blocks are forced to disk.
-
-noinit_itable		Do not initialize any uninitialized inode table
-			blocks in the background.  This feature may be
-			used by installation CD's so that the install
-			process can complete as quickly as possible; the
-			inode table initialization process would then be
-			deferred until the next time the  file system
-			is unmounted.
-
-init_itable=n		The lazy itable init code will wait n times the
-			number of milliseconds it took to zero out the
-			previous block group's inode table.  This
-			minimizes the impact on the system performance
-			while file system's inode table is being initialized.
-
-discard			Controls whether ext4 should issue discard/TRIM
-nodiscard(*)		commands to the underlying block device when
-			blocks are freed.  This is useful for SSD devices
-			and sparse/thinly-provisioned LUNs, but it is off
-			by default until sufficient testing has been done.
-
-nouid32			Disables 32-bit UIDs and GIDs.  This is for
-			interoperability  with  older kernels which only
-			store and expect 16-bit values.
-
-block_validity(*)	These options enable or disable the in-kernel
-noblock_validity	facility for tracking filesystem metadata blocks
-			within internal data structures.  This allows multi-
-			block allocator and other routines to notice
-			bugs or corrupted allocation bitmaps which cause
-			blocks to be allocated which overlap with
-			filesystem metadata blocks.
-
-dioread_lock		Controls whether or not ext4 should use the DIO read
-dioread_nolock		locking. If the dioread_nolock option is specified
-			ext4 will allocate uninitialized extent before buffer
-			write and convert the extent to initialized after IO
-			completes. This approach allows ext4 code to avoid
-			using inode mutex, which improves scalability on high
-			speed storages. However this does not work with
-			data journaling and dioread_nolock option will be
-			ignored with kernel warning. Note that dioread_nolock
-			code path is only used for extent-based files.
-			Because of the restrictions this options comprises
-			it is off by default (e.g. dioread_lock).
-
-max_dir_size_kb=n	This limits the size of directories so that any
-			attempt to expand them beyond the specified
-			limit in kilobytes will cause an ENOSPC error.
-			This is useful in memory constrained
-			environments, where a very large directory can
-			cause severe performance problems or even
-			provoke the Out Of Memory killer.  (For example,
-			if there is only 512mb memory available, a 176mb
-			directory may seriously cramp the system's style.)
-
-i_version		Enable 64-bit inode version support. This option is
-			off by default.
-
-dax			Use direct access (no page cache).  See
-			Documentation/filesystems/dax.txt.  Note that
-			this option is incompatible with data=journal.
-
-Data Mode
-=========
-There are 3 different data modes:
-
-* writeback mode
-In data=writeback mode, ext4 does not journal data at all.  This mode provides
-a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
-mode - metadata journaling.  A crash+recovery can cause incorrect data to
-appear in files which were written shortly before the crash.  This mode will
-typically provide the best ext4 performance.
-
-* ordered mode
-In data=ordered mode, ext4 only officially journals metadata, but it logically
-groups metadata information related to data changes with the data blocks into a
-single unit called a transaction.  When it's time to write the new metadata
-out to disk, the associated data blocks are written first.  In general,
-this mode performs slightly slower than writeback but significantly faster than journal mode.
-
-* journal mode
-data=journal mode provides full data and metadata journaling.  All new data is
-written to the journal first, and then to its final location.
-In the event of a crash, the journal can be replayed, bringing both data and
-metadata into a consistent state.  This mode is the slowest except when data
-needs to be read from and written to disk at the same time where it
-outperforms all others modes.  Enabling this mode will disable delayed
-allocation and O_DIRECT support.
-
-/proc entries
-=============
-
-Information about mounted ext4 file systems can be found in
-/proc/fs/ext4.  Each mounted filesystem will have a directory in
-/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
-/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
-in table below.
-
-Files in /proc/fs/ext4/<devname>
-..............................................................................
- File            Content
- mb_groups       details of multiblock allocator buddy cache of free blocks
-..............................................................................
-
-/sys entries
-============
-
-Information about mounted ext4 file systems can be found in
-/sys/fs/ext4.  Each mounted filesystem will have a directory in
-/sys/fs/ext4 based on its device name (i.e., /sys/fs/ext4/hdc or
-/sys/fs/ext4/dm-0).   The files in each per-device directory are shown
-in table below.
-
-Files in /sys/fs/ext4/<devname>
-(see also Documentation/ABI/testing/sysfs-fs-ext4)
-..............................................................................
- File                         Content
-
- delayed_allocation_blocks    This file is read-only and shows the number of
-                              blocks that are dirty in the page cache, but
-                              which do not have their location in the
-                              filesystem allocated yet.
-
- inode_goal                   Tuning parameter which (if non-zero) controls
-                              the goal inode used by the inode allocator in
-                              preference to all other allocation heuristics.
-                              This is intended for debugging use only, and
-                              should be 0 on production systems.
-
- inode_readahead_blks         Tuning parameter which controls the maximum
-                              number of inode table blocks that ext4's inode
-                              table readahead algorithm will pre-read into
-                              the buffer cache
-
- lifetime_write_kbytes        This file is read-only and shows the number of
-                              kilobytes of data that have been written to this
-                              filesystem since it was created.
-
- max_writeback_mb_bump        The maximum number of megabytes the writeback
-                              code will try to write out before move on to
-                              another inode.
-
- mb_group_prealloc            The multiblock allocator will round up allocation
-                              requests to a multiple of this tuning parameter if
-                              the stripe size is not set in the ext4 superblock
-
- mb_max_to_scan               The maximum number of extents the multiblock
-                              allocator will search to find the best extent
-
- mb_min_to_scan               The minimum number of extents the multiblock
-                              allocator will search to find the best extent
-
- mb_order2_req                Tuning parameter which controls the minimum size
-                              for requests (as a power of 2) where the buddy
-                              cache is used
-
- mb_stats                     Controls whether the multiblock allocator should
-                              collect statistics, which are shown during the
-                              unmount. 1 means to collect statistics, 0 means
-                              not to collect statistics
-
- mb_stream_req                Files which have fewer blocks than this tunable
-                              parameter will have their blocks allocated out
-                              of a block group specific preallocation pool, so
-                              that small files are packed closely together.
-                              Each large file will have its blocks allocated
-                              out of its own unique preallocation pool.
-
- session_write_kbytes         This file is read-only and shows the number of
-                              kilobytes of data that have been written to this
-                              filesystem since it was mounted.
-
- reserved_clusters            This is RW file and contains number of reserved
-                              clusters in the file system which will be used
-                              in the specific situations to avoid costly
-                              zeroout, unexpected ENOSPC, or possible data
-                              loss. The default is 2% or 4096 clusters,
-                              whichever is smaller and this can be changed
-                              however it can never exceed number of clusters
-                              in the file system. If there is not enough space
-                              for the reserved space when mounting the file
-                              mount will _not_ fail.
-..............................................................................
-
-Ioctls
-======
-
-There is some Ext4 specific functionality which can be accessed by applications
-through the system call interfaces. The list of all Ext4 specific ioctls are
-shown in the table below.
-
-Table of Ext4 specific ioctls
-..............................................................................
- Ioctl			      Description
- EXT4_IOC_GETFLAGS	      Get additional attributes associated with inode.
-			      The ioctl argument is an integer bitfield, with
-			      bit values described in ext4.h. This ioctl is an
-			      alias for FS_IOC_GETFLAGS.
-
- EXT4_IOC_SETFLAGS	      Set additional attributes associated with inode.
-			      The ioctl argument is an integer bitfield, with
-			      bit values described in ext4.h. This ioctl is an
-			      alias for FS_IOC_SETFLAGS.
-
- EXT4_IOC_GETVERSION
- EXT4_IOC_GETVERSION_OLD
-			      Get the inode i_generation number stored for
-			      each inode. The i_generation number is normally
-			      changed only when new inode is created and it is
-			      particularly useful for network filesystems. The
-			      '_OLD' version of this ioctl is an alias for
-			      FS_IOC_GETVERSION.
-
- EXT4_IOC_SETVERSION
- EXT4_IOC_SETVERSION_OLD
-			      Set the inode i_generation number stored for
-			      each inode. The '_OLD' version of this ioctl
-			      is an alias for FS_IOC_SETVERSION.
-
- EXT4_IOC_GROUP_EXTEND	      This ioctl has the same purpose as the resize
-			      mount option. It allows to resize filesystem
-			      to the end of the last existing block group,
-			      further resize has to be done with resize2fs,
-			      either online, or offline. The argument points
-			      to the unsigned logn number representing the
-			      filesystem new block count.
-
- EXT4_IOC_MOVE_EXT	      Move the block extents from orig_fd (the one
-			      this ioctl is pointing to) to the donor_fd (the
-			      one specified in move_extent structure passed
-			      as an argument to this ioctl). Then, exchange
-			      inode metadata between orig_fd and donor_fd.
-			      This is especially useful for online
-			      defragmentation, because the allocator has the
-			      opportunity to allocate moved blocks better,
-			      ideally into one contiguous extent.
-
- EXT4_IOC_GROUP_ADD	      Add a new group descriptor to an existing or
-			      new group descriptor block. The new group
-			      descriptor is described by ext4_new_group_input
-			      structure, which is passed as an argument to
-			      this ioctl. This is especially useful in
-			      conjunction with EXT4_IOC_GROUP_EXTEND,
-			      which allows online resize of the filesystem
-			      to the end of the last existing block group.
-			      Those two ioctls combined is used in userspace
-			      online resize tool (e.g. resize2fs).
-
- EXT4_IOC_MIGRATE	      This ioctl operates on the filesystem itself.
-			      It converts (migrates) ext3 indirect block mapped
-			      inode to ext4 extent mapped inode by walking
-			      through indirect block mapping of the original
-			      inode and converting contiguous block ranges
-			      into ext4 extents of the temporary inode. Then,
-			      inodes are swapped. This ioctl might help, when
-			      migrating from ext3 to ext4 filesystem, however
-			      suggestion is to create fresh ext4 filesystem
-			      and copy data from the backup. Note, that
-			      filesystem has to support extents for this ioctl
-			      to work.
-
- EXT4_IOC_ALLOC_DA_BLKS	      Force all of the delay allocated blocks to be
-			      allocated to preserve application-expected ext3
-			      behaviour. Note that this will also start
-			      triggering a write of the data blocks, but this
-			      behaviour may change in the future as it is
-			      not necessary and has been done this way only
-			      for sake of simplicity.
-
- EXT4_IOC_RESIZE_FS	      Resize the filesystem to a new size.  The number
-			      of blocks of resized filesystem is passed in via
-			      64 bit integer argument.  The kernel allocates
-			      bitmaps and inode table, the userspace tool thus
-			      just passes the new number of blocks.
-
- EXT4_IOC_SWAP_BOOT	      Swap i_blocks and associated attributes
-			      (like i_blocks, i_size, i_flags, ...) from
-			      the specified inode with inode
-			      EXT4_BOOT_LOADER_INO (#5). This is typically
-			      used to store a boot loader in a secure part of
-			      the filesystem, where it can't be changed by a
-			      normal user by accident.
-			      The data blocks of the previous boot loader
-			      will be associated with the given inode.
-
-..............................................................................
-
-References
-==========
-
-kernel source:	<file:fs/ext4/>
-		<file:fs/jbd2/>
-
-programs:	http://e2fsprogs.sourceforge.net/
-
-useful links:	http://fedoraproject.org/wiki/ext3-devel
-		http://www.bullopensource.org/ext4/
-		http://ext4.wiki.kernel.org/index.php/Main_Page
-		http://fedoraproject.org/wiki/Features/Ext4
diff --git a/Documentation/filesystems/ext4/ext4.rst b/Documentation/filesystems/ext4/ext4.rst
new file mode 100644
index 000000000000..7f628b9f7c4b
--- /dev/null
+++ b/Documentation/filesystems/ext4/ext4.rst
@@ -0,0 +1,627 @@
+
+Ext4 Filesystem
+===============
+
+Ext4 is an advanced level of the ext3 filesystem which incorporates
+scalability and reliability enhancements for supporting large filesystems
+(64 bit) in keeping with increasing disk capacities and state-of-the-art
+feature requirements.
+
+Mailing list:	linux-ext4@vger.kernel.org
+Web site:	http://ext4.wiki.kernel.org
+
+
+1. Quick usage instructions:
+===========================
+
+Note: More extensive information for getting started with ext4 can be
+      found at the ext4 wiki site at the URL:
+      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
+
+  - Compile and install the latest version of e2fsprogs (as of this
+    writing version 1.41.3) from:
+
+    http://sourceforge.net/project/showfiles.php?group_id=2406
+	
+	or
+
+    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
+
+	or grab the latest git repository from:
+
+    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
+
+  - Note that it is highly important to install the mke2fs.conf file
+    that comes with the e2fsprogs 1.41.x sources in /etc/mke2fs.conf. If
+    you have edited the /etc/mke2fs.conf file installed on your system,
+    you will need to merge your changes with the version from e2fsprogs
+    1.41.x.
+
+  - Create a new filesystem using the ext4 filesystem type:
+
+    	# mke2fs -t ext4 /dev/hda1
+
+    Or to configure an existing ext3 filesystem to support extents: 
+
+	# tune2fs -O extents /dev/hda1
+
+    If the filesystem was created with 128 byte inodes, it can be
+    converted to use 256 byte for greater efficiency via:
+
+        # tune2fs -I 256 /dev/hda1
+
+    (Note: we currently do not have tools to convert an ext4
+    filesystem back to ext3; so please do not do try this on production
+    filesystems.)
+
+  - Mounting:
+
+	# mount -t ext4 /dev/hda1 /wherever
+
+  - When comparing performance with other filesystems, it's always
+    important to try multiple workloads; very often a subtle change in a
+    workload parameter can completely change the ranking of which
+    filesystems do well compared to others.  When comparing versus ext3,
+    note that ext4 enables write barriers by default, while ext3 does
+    not enable write barriers by default.  So it is useful to use
+    explicitly specify whether barriers are enabled or not when via the
+    '-o barriers=[0|1]' mount option for both ext3 and ext4 filesystems
+    for a fair comparison.  When tuning ext3 for best benchmark numbers,
+    it is often worthwhile to try changing the data journaling mode; '-o
+    data=writeback' can be faster for some workloads.  (Note however that
+    running mounted with data=writeback can potentially leave stale data
+    exposed in recently written files in case of an unclean shutdown,
+    which could be a security exposure in some situations.)  Configuring
+    the filesystem with a large journal can also be helpful for
+    metadata-intensive workloads.
+
+2. Features
+===========
+
+2.1 Currently available
+
+* ability to use filesystems > 16TB (e2fsprogs support not available yet)
+* extent format reduces metadata overhead (RAM, IO for access, transactions)
+* extent format more robust in face of on-disk corruption due to magics,
+* internal redundancy in tree
+* improved file allocation (multi-block alloc)
+* lift 32000 subdirectory limit imposed by i_links_count[1]
+* nsec timestamps for mtime, atime, ctime, create time
+* inode version field on disk (NFSv4, Lustre)
+* reduced e2fsck time via uninit_bg feature
+* journal checksumming for robustness, performance
+* persistent file preallocation (e.g for streaming media, databases)
+* ability to pack bitmaps and inode tables into larger virtual groups via the
+  flex_bg feature
+* large file support
+* inode allocation using large virtual block groups via flex_bg
+* delayed allocation
+* large block (up to pagesize) support
+* efficient new ordered mode in JBD2 and ext4 (avoid using buffer head to force
+  the ordering)
+
+[1] Filesystems with a block size of 1k may see a limit imposed by the
+directory hash tree having a maximum depth of two.
+
+2.2 Candidate features for future inclusion
+
+* online defrag (patches available but not well tested)
+* reduced mke2fs time via lazy itable initialization in conjunction with
+  the uninit_bg feature (capability to do this is available in e2fsprogs
+  but a kernel thread to do lazy zeroing of unused inode table blocks
+  after filesystem is first mounted is required for safety)
+
+There are several others under discussion, whether they all make it in is
+partly a function of how much time everyone has to work on them. Features like
+metadata checksumming have been discussed and planned for a bit but no patches
+exist yet so I'm not sure they're in the near-term roadmap.
+
+The big performance win will come with mballoc, delalloc and flex_bg
+grouping of bitmaps and inode tables.  Some test results available here:
+
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
+ - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
+
+3. Options
+==========
+
+When mounting an ext4 filesystem, the following option are accepted:
+(*) == default
+
+ro                   	Mount filesystem read only. Note that ext4 will
+                     	replay the journal (and thus write to the
+                     	partition) even when mounted "read only". The
+                     	mount options "ro,noload" can be used to prevent
+		     	writes to the filesystem.
+
+journal_checksum	Enable checksumming of the journal transactions.
+			This will allow the recovery code in e2fsck and the
+			kernel to detect corruption in the kernel.  It is a
+			compatible change and will be ignored by older kernels.
+
+journal_async_commit	Commit block can be written to disk without waiting
+			for descriptor blocks. If enabled older kernels cannot
+			mount the device. This will enable 'journal_checksum'
+			internally.
+
+journal_path=path
+journal_dev=devnum	When the external journal device's major/minor numbers
+			have changed, these options allow the user to specify
+			the new journal location.  The journal device is
+			identified through either its new major/minor numbers
+			encoded in devnum, or via a path to the device.
+
+norecovery		Don't load the journal on mounting.  Note that
+noload			if the filesystem was not unmounted cleanly,
+                     	skipping the journal replay will lead to the
+                     	filesystem containing inconsistencies that can
+                     	lead to any number of problems.
+
+data=journal		All data are committed into the journal prior to being
+			written into the main file system.  Enabling
+			this mode will disable delayed allocation and
+			O_DIRECT support.
+
+data=ordered	(*)	All data are forced directly out to the main file
+			system prior to its metadata being committed to the
+			journal.
+
+data=writeback		Data ordering is not preserved, data may be written
+			into the main file system after its metadata has been
+			committed to the journal.
+
+commit=nrsec	(*)	Ext4 can be told to sync all its data and metadata
+			every 'nrsec' seconds. The default value is 5 seconds.
+			This means that if you lose your power, you will lose
+			as much as the latest 5 seconds of work (your
+			filesystem will not be damaged though, thanks to the
+			journaling).  This default value (or any low value)
+			will hurt performance, but it's good for data-safety.
+			Setting it to 0 will have the same effect as leaving
+			it at the default (5 seconds).
+			Setting it to very large values will improve
+			performance.
+
+barrier=<0|1(*)>	This enables/disables the use of write barriers in
+barrier(*)		the jbd code.  barrier=0 disables, barrier=1 enables.
+nobarrier		This also requires an IO stack which can support
+			barriers, and if jbd gets an error on a barrier
+			write, it will disable again with a warning.
+			Write barriers enforce proper on-disk ordering
+			of journal commits, making volatile disk write caches
+			safe to use, at some performance penalty.  If
+			your disks are battery-backed in one way or another,
+			disabling barriers may safely improve performance.
+			The mount options "barrier" and "nobarrier" can
+			also be used to enable or disable barriers, for
+			consistency with other ext4 mount options.
+
+inode_readahead_blks=n	This tuning parameter controls the maximum
+			number of inode table blocks that ext4's inode
+			table readahead algorithm will pre-read into
+			the buffer cache.  The default value is 32 blocks.
+
+nouser_xattr		Disables Extended User Attributes.  See the
+			attr(5) manual page for more information about
+			extended attributes.
+
+noacl			This option disables POSIX Access Control List
+			support. If ACL support is enabled in the kernel
+			configuration (CONFIG_EXT4_FS_POSIX_ACL), ACL is
+			enabled by default on mount. See the acl(5) manual
+			page for more information about acl.
+
+bsddf		(*)	Make 'df' act like BSD.
+minixdf			Make 'df' act like Minix.
+
+debug			Extra debugging information is sent to syslog.
+
+abort			Simulate the effects of calling ext4_abort() for
+			debugging purposes.  This is normally used while
+			remounting a filesystem which is already mounted.
+
+errors=remount-ro	Remount the filesystem read-only on an error.
+errors=continue		Keep going on a filesystem error.
+errors=panic		Panic and halt the machine if an error occurs.
+                        (These mount options override the errors behavior
+                        specified in the superblock, which can be configured
+                        using tune2fs)
+
+data_err=ignore(*)	Just print an error message if an error occurs
+			in a file data buffer in ordered mode.
+data_err=abort		Abort the journal if an error occurs in a file
+			data buffer in ordered mode.
+
+grpid			New objects have the group ID of their parent.
+bsdgroups
+
+nogrpid		(*)	New objects have the group ID of their creator.
+sysvgroups
+
+resgid=n		The group ID which may use the reserved blocks.
+
+resuid=n		The user ID which may use the reserved blocks.
+
+sb=n			Use alternate superblock at this location.
+
+quota			These options are ignored by the filesystem. They
+noquota			are used only by quota tools to recognize volumes
+grpquota		where quota should be turned on. See documentation
+usrquota		in the quota-tools package for more details
+			(http://sourceforge.net/projects/linuxquota).
+
+jqfmt=<quota type>	These options tell filesystem details about quota
+usrjquota=<file>	so that quota information can be properly updated
+grpjquota=<file>	during journal replay. They replace the above
+			quota options. See documentation in the quota-tools
+			package for more details
+			(http://sourceforge.net/projects/linuxquota).
+
+stripe=n		Number of filesystem blocks that mballoc will try
+			to use for allocation size and alignment. For RAID5/6
+			systems this should be the number of data
+			disks *  RAID chunk size in file system blocks.
+
+delalloc	(*)	Defer block allocation until just before ext4
+			writes out the block(s) in question.  This
+			allows ext4 to better allocation decisions
+			more efficiently.
+nodelalloc		Disable delayed allocation.  Blocks are allocated
+			when the data is copied from userspace to the
+			page cache, either via the write(2) system call
+			or when an mmap'ed page which was previously
+			unallocated is written for the first time.
+
+max_batch_time=usec	Maximum amount of time ext4 should wait for
+			additional filesystem operations to be batch
+			together with a synchronous write operation.
+			Since a synchronous write operation is going to
+			force a commit and then a wait for the I/O
+			complete, it doesn't cost much, and can be a
+			huge throughput win, we wait for a small amount
+			of time to see if any other transactions can
+			piggyback on the synchronous write.   The
+			algorithm used is designed to automatically tune
+			for the speed of the disk, by measuring the
+			amount of time (on average) that it takes to
+			finish committing a transaction.  Call this time
+			the "commit time".  If the time that the
+			transaction has been running is less than the
+			commit time, ext4 will try sleeping for the
+			commit time to see if other operations will join
+			the transaction.   The commit time is capped by
+			the max_batch_time, which defaults to 15000us
+			(15ms).   This optimization can be turned off
+			entirely by setting max_batch_time to 0.
+
+min_batch_time=usec	This parameter sets the commit time (as
+			described above) to be at least min_batch_time.
+			It defaults to zero microseconds.  Increasing
+			this parameter may improve the throughput of
+			multi-threaded, synchronous workloads on very
+			fast disks, at the cost of increasing latency.
+
+journal_ioprio=prio	The I/O priority (from 0 to 7, where 0 is the
+			highest priority) which should be used for I/O
+			operations submitted by kjournald2 during a
+			commit operation.  This defaults to 3, which is
+			a slightly higher priority than the default I/O
+			priority.
+
+auto_da_alloc(*)	Many broken applications don't use fsync() when 
+noauto_da_alloc		replacing existing files via patterns such as
+			fd = open("foo.new")/write(fd,..)/close(fd)/
+			rename("foo.new", "foo"), or worse yet,
+			fd = open("foo", O_TRUNC)/write(fd,..)/close(fd).
+			If auto_da_alloc is enabled, ext4 will detect
+			the replace-via-rename and replace-via-truncate
+			patterns and force that any delayed allocation
+			blocks are allocated such that at the next
+			journal commit, in the default data=ordered
+			mode, the data blocks of the new file are forced
+			to disk before the rename() operation is
+			committed.  This provides roughly the same level
+			of guarantees as ext3, and avoids the
+			"zero-length" problem that can happen when a
+			system crashes before the delayed allocation
+			blocks are forced to disk.
+
+noinit_itable		Do not initialize any uninitialized inode table
+			blocks in the background.  This feature may be
+			used by installation CD's so that the install
+			process can complete as quickly as possible; the
+			inode table initialization process would then be
+			deferred until the next time the  file system
+			is unmounted.
+
+init_itable=n		The lazy itable init code will wait n times the
+			number of milliseconds it took to zero out the
+			previous block group's inode table.  This
+			minimizes the impact on the system performance
+			while file system's inode table is being initialized.
+
+discard			Controls whether ext4 should issue discard/TRIM
+nodiscard(*)		commands to the underlying block device when
+			blocks are freed.  This is useful for SSD devices
+			and sparse/thinly-provisioned LUNs, but it is off
+			by default until sufficient testing has been done.
+
+nouid32			Disables 32-bit UIDs and GIDs.  This is for
+			interoperability  with  older kernels which only
+			store and expect 16-bit values.
+
+block_validity(*)	These options enable or disable the in-kernel
+noblock_validity	facility for tracking filesystem metadata blocks
+			within internal data structures.  This allows multi-
+			block allocator and other routines to notice
+			bugs or corrupted allocation bitmaps which cause
+			blocks to be allocated which overlap with
+			filesystem metadata blocks.
+
+dioread_lock		Controls whether or not ext4 should use the DIO read
+dioread_nolock		locking. If the dioread_nolock option is specified
+			ext4 will allocate uninitialized extent before buffer
+			write and convert the extent to initialized after IO
+			completes. This approach allows ext4 code to avoid
+			using inode mutex, which improves scalability on high
+			speed storages. However this does not work with
+			data journaling and dioread_nolock option will be
+			ignored with kernel warning. Note that dioread_nolock
+			code path is only used for extent-based files.
+			Because of the restrictions this options comprises
+			it is off by default (e.g. dioread_lock).
+
+max_dir_size_kb=n	This limits the size of directories so that any
+			attempt to expand them beyond the specified
+			limit in kilobytes will cause an ENOSPC error.
+			This is useful in memory constrained
+			environments, where a very large directory can
+			cause severe performance problems or even
+			provoke the Out Of Memory killer.  (For example,
+			if there is only 512mb memory available, a 176mb
+			directory may seriously cramp the system's style.)
+
+i_version		Enable 64-bit inode version support. This option is
+			off by default.
+
+dax			Use direct access (no page cache).  See
+			Documentation/filesystems/dax.txt.  Note that
+			this option is incompatible with data=journal.
+
+Data Mode
+=========
+There are 3 different data modes:
+
+* writeback mode
+In data=writeback mode, ext4 does not journal data at all.  This mode provides
+a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
+mode - metadata journaling.  A crash+recovery can cause incorrect data to
+appear in files which were written shortly before the crash.  This mode will
+typically provide the best ext4 performance.
+
+* ordered mode
+In data=ordered mode, ext4 only officially journals metadata, but it logically
+groups metadata information related to data changes with the data blocks into a
+single unit called a transaction.  When it's time to write the new metadata
+out to disk, the associated data blocks are written first.  In general,
+this mode performs slightly slower than writeback but significantly faster than journal mode.
+
+* journal mode
+data=journal mode provides full data and metadata journaling.  All new data is
+written to the journal first, and then to its final location.
+In the event of a crash, the journal can be replayed, bringing both data and
+metadata into a consistent state.  This mode is the slowest except when data
+needs to be read from and written to disk at the same time where it
+outperforms all others modes.  Enabling this mode will disable delayed
+allocation and O_DIRECT support.
+
+/proc entries
+=============
+
+Information about mounted ext4 file systems can be found in
+/proc/fs/ext4.  Each mounted filesystem will have a directory in
+/proc/fs/ext4 based on its device name (i.e., /proc/fs/ext4/hdc or
+/proc/fs/ext4/dm-0).   The files in each per-device directory are shown
+in table below.
+
+Files in /proc/fs/ext4/<devname>
+..............................................................................
+ File            Content
+ mb_groups       details of multiblock allocator buddy cache of free blocks
+..............................................................................
+
+/sys entries
+============
+
+Information about mounted ext4 file systems can be found in
+/sys/fs/ext4.  Each mounted filesystem will have a directory in
+/sys/fs/ext4 based on its device name (i.e., /sys/fs/ext4/hdc or
+/sys/fs/ext4/dm-0).   The files in each per-device directory are shown
+in table below.
+
+Files in /sys/fs/ext4/<devname>
+(see also Documentation/ABI/testing/sysfs-fs-ext4)
+..............................................................................
+ File                         Content
+
+ delayed_allocation_blocks    This file is read-only and shows the number of
+                              blocks that are dirty in the page cache, but
+                              which do not have their location in the
+                              filesystem allocated yet.
+
+ inode_goal                   Tuning parameter which (if non-zero) controls
+                              the goal inode used by the inode allocator in
+                              preference to all other allocation heuristics.
+                              This is intended for debugging use only, and
+                              should be 0 on production systems.
+
+ inode_readahead_blks         Tuning parameter which controls the maximum
+                              number of inode table blocks that ext4's inode
+                              table readahead algorithm will pre-read into
+                              the buffer cache
+
+ lifetime_write_kbytes        This file is read-only and shows the number of
+                              kilobytes of data that have been written to this
+                              filesystem since it was created.
+
+ max_writeback_mb_bump        The maximum number of megabytes the writeback
+                              code will try to write out before move on to
+                              another inode.
+
+ mb_group_prealloc            The multiblock allocator will round up allocation
+                              requests to a multiple of this tuning parameter if
+                              the stripe size is not set in the ext4 superblock
+
+ mb_max_to_scan               The maximum number of extents the multiblock
+                              allocator will search to find the best extent
+
+ mb_min_to_scan               The minimum number of extents the multiblock
+                              allocator will search to find the best extent
+
+ mb_order2_req                Tuning parameter which controls the minimum size
+                              for requests (as a power of 2) where the buddy
+                              cache is used
+
+ mb_stats                     Controls whether the multiblock allocator should
+                              collect statistics, which are shown during the
+                              unmount. 1 means to collect statistics, 0 means
+                              not to collect statistics
+
+ mb_stream_req                Files which have fewer blocks than this tunable
+                              parameter will have their blocks allocated out
+                              of a block group specific preallocation pool, so
+                              that small files are packed closely together.
+                              Each large file will have its blocks allocated
+                              out of its own unique preallocation pool.
+
+ session_write_kbytes         This file is read-only and shows the number of
+                              kilobytes of data that have been written to this
+                              filesystem since it was mounted.
+
+ reserved_clusters            This is RW file and contains number of reserved
+                              clusters in the file system which will be used
+                              in the specific situations to avoid costly
+                              zeroout, unexpected ENOSPC, or possible data
+                              loss. The default is 2% or 4096 clusters,
+                              whichever is smaller and this can be changed
+                              however it can never exceed number of clusters
+                              in the file system. If there is not enough space
+                              for the reserved space when mounting the file
+                              mount will _not_ fail.
+..............................................................................
+
+Ioctls
+======
+
+There is some Ext4 specific functionality which can be accessed by applications
+through the system call interfaces. The list of all Ext4 specific ioctls are
+shown in the table below.
+
+Table of Ext4 specific ioctls
+..............................................................................
+ Ioctl			      Description
+ EXT4_IOC_GETFLAGS	      Get additional attributes associated with inode.
+			      The ioctl argument is an integer bitfield, with
+			      bit values described in ext4.h. This ioctl is an
+			      alias for FS_IOC_GETFLAGS.
+
+ EXT4_IOC_SETFLAGS	      Set additional attributes associated with inode.
+			      The ioctl argument is an integer bitfield, with
+			      bit values described in ext4.h. This ioctl is an
+			      alias for FS_IOC_SETFLAGS.
+
+ EXT4_IOC_GETVERSION
+ EXT4_IOC_GETVERSION_OLD
+			      Get the inode i_generation number stored for
+			      each inode. The i_generation number is normally
+			      changed only when new inode is created and it is
+			      particularly useful for network filesystems. The
+			      '_OLD' version of this ioctl is an alias for
+			      FS_IOC_GETVERSION.
+
+ EXT4_IOC_SETVERSION
+ EXT4_IOC_SETVERSION_OLD
+			      Set the inode i_generation number stored for
+			      each inode. The '_OLD' version of this ioctl
+			      is an alias for FS_IOC_SETVERSION.
+
+ EXT4_IOC_GROUP_EXTEND	      This ioctl has the same purpose as the resize
+			      mount option. It allows to resize filesystem
+			      to the end of the last existing block group,
+			      further resize has to be done with resize2fs,
+			      either online, or offline. The argument points
+			      to the unsigned logn number representing the
+			      filesystem new block count.
+
+ EXT4_IOC_MOVE_EXT	      Move the block extents from orig_fd (the one
+			      this ioctl is pointing to) to the donor_fd (the
+			      one specified in move_extent structure passed
+			      as an argument to this ioctl). Then, exchange
+			      inode metadata between orig_fd and donor_fd.
+			      This is especially useful for online
+			      defragmentation, because the allocator has the
+			      opportunity to allocate moved blocks better,
+			      ideally into one contiguous extent.
+
+ EXT4_IOC_GROUP_ADD	      Add a new group descriptor to an existing or
+			      new group descriptor block. The new group
+			      descriptor is described by ext4_new_group_input
+			      structure, which is passed as an argument to
+			      this ioctl. This is especially useful in
+			      conjunction with EXT4_IOC_GROUP_EXTEND,
+			      which allows online resize of the filesystem
+			      to the end of the last existing block group.
+			      Those two ioctls combined is used in userspace
+			      online resize tool (e.g. resize2fs).
+
+ EXT4_IOC_MIGRATE	      This ioctl operates on the filesystem itself.
+			      It converts (migrates) ext3 indirect block mapped
+			      inode to ext4 extent mapped inode by walking
+			      through indirect block mapping of the original
+			      inode and converting contiguous block ranges
+			      into ext4 extents of the temporary inode. Then,
+			      inodes are swapped. This ioctl might help, when
+			      migrating from ext3 to ext4 filesystem, however
+			      suggestion is to create fresh ext4 filesystem
+			      and copy data from the backup. Note, that
+			      filesystem has to support extents for this ioctl
+			      to work.
+
+ EXT4_IOC_ALLOC_DA_BLKS	      Force all of the delay allocated blocks to be
+			      allocated to preserve application-expected ext3
+			      behaviour. Note that this will also start
+			      triggering a write of the data blocks, but this
+			      behaviour may change in the future as it is
+			      not necessary and has been done this way only
+			      for sake of simplicity.
+
+ EXT4_IOC_RESIZE_FS	      Resize the filesystem to a new size.  The number
+			      of blocks of resized filesystem is passed in via
+			      64 bit integer argument.  The kernel allocates
+			      bitmaps and inode table, the userspace tool thus
+			      just passes the new number of blocks.
+
+ EXT4_IOC_SWAP_BOOT	      Swap i_blocks and associated attributes
+			      (like i_blocks, i_size, i_flags, ...) from
+			      the specified inode with inode
+			      EXT4_BOOT_LOADER_INO (#5). This is typically
+			      used to store a boot loader in a secure part of
+			      the filesystem, where it can't be changed by a
+			      normal user by accident.
+			      The data blocks of the previous boot loader
+			      will be associated with the given inode.
+
+..............................................................................
+
+References
+==========
+
+kernel source:	<file:fs/ext4/>
+		<file:fs/jbd2/>
+
+programs:	http://e2fsprogs.sourceforge.net/
+
+useful links:	http://fedoraproject.org/wiki/ext3-devel
+		http://www.bullopensource.org/ext4/
+		http://ext4.wiki.kernel.org/index.php/Main_Page
+		http://fedoraproject.org/wiki/Features/Ext4
-- 
cgit v1.2.3


From 489fcb912477e4f4ba5fb65b223331fb8d352a07 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:36:00 -0400
Subject: ext4: convert ext4.rst to restructuredtext format

Convert the existing ext4 documentation into rst format and link it in
with the rest of the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ext4.rst  | 113 ++++++++++++++++++-------------
 Documentation/filesystems/ext4/index.rst |  16 +++++
 Documentation/filesystems/index.rst      |   8 +++
 3 files changed, 89 insertions(+), 48 deletions(-)
 create mode 100644 Documentation/filesystems/ext4/index.rst

diff --git a/Documentation/filesystems/ext4/ext4.rst b/Documentation/filesystems/ext4/ext4.rst
index 7f628b9f7c4b..47f614c47f56 100644
--- a/Documentation/filesystems/ext4/ext4.rst
+++ b/Documentation/filesystems/ext4/ext4.rst
@@ -1,6 +1,8 @@
+.. SPDX-License-Identifier: GPL-2.0
 
-Ext4 Filesystem
-===============
+========================
+General Information
+========================
 
 Ext4 is an advanced level of the ext3 filesystem which incorporates
 scalability and reliability enhancements for supporting large filesystems
@@ -11,18 +13,18 @@ Mailing list:	linux-ext4@vger.kernel.org
 Web site:	http://ext4.wiki.kernel.org
 
 
-1. Quick usage instructions:
-===========================
+Quick usage instructions
+========================
 
 Note: More extensive information for getting started with ext4 can be
-      found at the ext4 wiki site at the URL:
-      http://ext4.wiki.kernel.org/index.php/Ext4_Howto
+found at the ext4 wiki site at the URL:
+http://ext4.wiki.kernel.org/index.php/Ext4_Howto
 
   - Compile and install the latest version of e2fsprogs (as of this
     writing version 1.41.3) from:
 
     http://sourceforge.net/project/showfiles.php?group_id=2406
-	
+
 	or
 
     https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
@@ -37,16 +39,16 @@ Note: More extensive information for getting started with ext4 can be
     you will need to merge your changes with the version from e2fsprogs
     1.41.x.
 
-  - Create a new filesystem using the ext4 filesystem type:
+  - Create a new filesystem using the ext4 filesystem type:::
 
-    	# mke2fs -t ext4 /dev/hda1
+        # mke2fs -t ext4 /dev/hda1
 
-    Or to configure an existing ext3 filesystem to support extents: 
+    Or to configure an existing ext3 filesystem to support extents:::
 
 	# tune2fs -O extents /dev/hda1
 
     If the filesystem was created with 128 byte inodes, it can be
-    converted to use 256 byte for greater efficiency via:
+    converted to use 256 byte for greater efficiency via:::
 
         # tune2fs -I 256 /dev/hda1
 
@@ -54,7 +56,7 @@ Note: More extensive information for getting started with ext4 can be
     filesystem back to ext3; so please do not do try this on production
     filesystems.)
 
-  - Mounting:
+  - Mounting:::
 
 	# mount -t ext4 /dev/hda1 /wherever
 
@@ -75,10 +77,11 @@ Note: More extensive information for getting started with ext4 can be
     the filesystem with a large journal can also be helpful for
     metadata-intensive workloads.
 
-2. Features
-===========
+Features
+========
 
-2.1 Currently available
+Currently Available
+-------------------
 
 * ability to use filesystems > 16TB (e2fsprogs support not available yet)
 * extent format reduces metadata overhead (RAM, IO for access, transactions)
@@ -103,7 +106,8 @@ Note: More extensive information for getting started with ext4 can be
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.
 
-2.2 Candidate features for future inclusion
+Candidate Features for Future Inclusion
+---------------------------------------
 
 * online defrag (patches available but not well tested)
 * reduced mke2fs time via lazy itable initialization in conjunction with
@@ -122,12 +126,15 @@ grouping of bitmaps and inode tables.  Some test results available here:
  - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
  - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
 
-3. Options
-==========
+Options
+=======
 
 When mounting an ext4 filesystem, the following option are accepted:
 (*) == default
 
+======================= =======================================================
+Mount Option            Description
+======================= =======================================================
 ro                   	Mount filesystem read only. Note that ext4 will
                      	replay the journal (and thus write to the
                      	partition) even when mounted "read only". The
@@ -387,33 +394,38 @@ i_version		Enable 64-bit inode version support. This option is
 dax			Use direct access (no page cache).  See
 			Documentation/filesystems/dax.txt.  Note that
 			this option is incompatible with data=journal.
+======================= =======================================================
 
 Data Mode
 =========
 There are 3 different data modes:
 
 * writeback mode
-In data=writeback mode, ext4 does not journal data at all.  This mode provides
-a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
-mode - metadata journaling.  A crash+recovery can cause incorrect data to
-appear in files which were written shortly before the crash.  This mode will
-typically provide the best ext4 performance.
+
+  In data=writeback mode, ext4 does not journal data at all.  This mode provides
+  a similar level of journaling as that of XFS, JFS, and ReiserFS in its default
+  mode - metadata journaling.  A crash+recovery can cause incorrect data to
+  appear in files which were written shortly before the crash.  This mode will
+  typically provide the best ext4 performance.
 
 * ordered mode
-In data=ordered mode, ext4 only officially journals metadata, but it logically
-groups metadata information related to data changes with the data blocks into a
-single unit called a transaction.  When it's time to write the new metadata
-out to disk, the associated data blocks are written first.  In general,
-this mode performs slightly slower than writeback but significantly faster than journal mode.
+
+  In data=ordered mode, ext4 only officially journals metadata, but it logically
+  groups metadata information related to data changes with the data blocks into
+  a single unit called a transaction.  When it's time to write the new metadata
+  out to disk, the associated data blocks are written first.  In general, this
+  mode performs slightly slower than writeback but significantly faster than
+  journal mode.
 
 * journal mode
-data=journal mode provides full data and metadata journaling.  All new data is
-written to the journal first, and then to its final location.
-In the event of a crash, the journal can be replayed, bringing both data and
-metadata into a consistent state.  This mode is the slowest except when data
-needs to be read from and written to disk at the same time where it
-outperforms all others modes.  Enabling this mode will disable delayed
-allocation and O_DIRECT support.
+
+  data=journal mode provides full data and metadata journaling.  All new data is
+  written to the journal first, and then to its final location.  In the event of
+  a crash, the journal can be replayed, bringing both data and metadata into a
+  consistent state.  This mode is the slowest except when data needs to be read
+  from and written to disk at the same time where it outperforms all others
+  modes.  Enabling this mode will disable delayed allocation and O_DIRECT
+  support.
 
 /proc entries
 =============
@@ -425,10 +437,12 @@ Information about mounted ext4 file systems can be found in
 in table below.
 
 Files in /proc/fs/ext4/<devname>
-..............................................................................
+
+================ =======
  File            Content
+================ =======
  mb_groups       details of multiblock allocator buddy cache of free blocks
-..............................................................................
+================ =======
 
 /sys entries
 ============
@@ -439,28 +453,30 @@ Information about mounted ext4 file systems can be found in
 /sys/fs/ext4/dm-0).   The files in each per-device directory are shown
 in table below.
 
-Files in /sys/fs/ext4/<devname>
+Files in /sys/fs/ext4/<devname>:
+
 (see also Documentation/ABI/testing/sysfs-fs-ext4)
-..............................................................................
- File                         Content
 
+============================= =================================================
+File                          Content
+============================= =================================================
  delayed_allocation_blocks    This file is read-only and shows the number of
                               blocks that are dirty in the page cache, but
                               which do not have their location in the
                               filesystem allocated yet.
 
- inode_goal                   Tuning parameter which (if non-zero) controls
+inode_goal                    Tuning parameter which (if non-zero) controls
                               the goal inode used by the inode allocator in
                               preference to all other allocation heuristics.
                               This is intended for debugging use only, and
                               should be 0 on production systems.
 
- inode_readahead_blks         Tuning parameter which controls the maximum
+inode_readahead_blks          Tuning parameter which controls the maximum
                               number of inode table blocks that ext4's inode
                               table readahead algorithm will pre-read into
                               the buffer cache
 
- lifetime_write_kbytes        This file is read-only and shows the number of
+lifetime_write_kbytes         This file is read-only and shows the number of
                               kilobytes of data that have been written to this
                               filesystem since it was created.
 
@@ -508,7 +524,7 @@ Files in /sys/fs/ext4/<devname>
                               in the file system. If there is not enough space
                               for the reserved space when mounting the file
                               mount will _not_ fail.
-..............................................................................
+============================= =================================================
 
 Ioctls
 ======
@@ -518,8 +534,10 @@ through the system call interfaces. The list of all Ext4 specific ioctls are
 shown in the table below.
 
 Table of Ext4 specific ioctls
-..............................................................................
- Ioctl			      Description
+
+============================= =================================================
+Ioctl			      Description
+============================= =================================================
  EXT4_IOC_GETFLAGS	      Get additional attributes associated with inode.
 			      The ioctl argument is an integer bitfield, with
 			      bit values described in ext4.h. This ioctl is an
@@ -610,8 +628,7 @@ Table of Ext4 specific ioctls
 			      normal user by accident.
 			      The data blocks of the previous boot loader
 			      will be associated with the given inode.
-
-..............................................................................
+============================= =================================================
 
 References
 ==========
diff --git a/Documentation/filesystems/ext4/index.rst b/Documentation/filesystems/ext4/index.rst
new file mode 100644
index 000000000000..1270b34f643f
--- /dev/null
+++ b/Documentation/filesystems/ext4/index.rst
@@ -0,0 +1,16 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+====
+ext4
+====
+
+General usage and on-disk artifacts writen by ext4.  More documentation may
+be ported from the wiki as time permits.  This should be considered the
+canonical source of information as the details here have been reviewed by
+the ext4 community.
+
+.. toctree::
+   :maxdepth: 5
+   :numbered:
+
+   ext4
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 53b89d0edc15..7c57b3927308 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -2,6 +2,14 @@
 Linux Filesystems API
 =====================
 
+The documentation in this section are provided by specific filesystem
+subprojects.
+
+.. toctree::
+   :maxdepth: 2
+
+   ext4/index
+
 The Linux VFS
 =============
 
-- 
cgit v1.2.3


From b2e60723c1c14c7c9b79c82bb86d8e2a81051b5e Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:37:00 -0400
Subject: ext4: import on-disk layout book from wiki page

Create the basic structure of the "new" data structures & algorithms
book to be ported over from the on-disk format wiki, and then start by
pulling in the introductory information.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/index.rst        |  1 +
 Documentation/filesystems/ext4/ondisk/about.rst | 44 +++++++++++++++++++++++++
 Documentation/filesystems/ext4/ondisk/index.rst |  6 ++++
 3 files changed, 51 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/about.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/index.rst

diff --git a/Documentation/filesystems/ext4/index.rst b/Documentation/filesystems/ext4/index.rst
index 1270b34f643f..8fe4f7693e8c 100644
--- a/Documentation/filesystems/ext4/index.rst
+++ b/Documentation/filesystems/ext4/index.rst
@@ -14,3 +14,4 @@ the ext4 community.
    :numbered:
 
    ext4
+   ondisk/index
diff --git a/Documentation/filesystems/ext4/ondisk/about.rst b/Documentation/filesystems/ext4/ondisk/about.rst
new file mode 100644
index 000000000000..0aadba052264
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/about.rst
@@ -0,0 +1,44 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+About this Book
+===============
+
+This document attempts to describe the on-disk format for ext4
+filesystems. The same general ideas should apply to ext2/3 filesystems
+as well, though they do not support all the features that ext4 supports,
+and the fields will be shorter.
+
+**NOTE**: This is a work in progress, based on notes that the author
+(djwong) made while picking apart a filesystem by hand. The data
+structure definitions should be current as of Linux 4.18 and
+e2fsprogs-1.44. All comments and corrections are welcome, since there is
+undoubtedly plenty of lore that might not be reflected in freshly
+created demonstration filesystems.
+
+License
+-------
+This book is licensed under the terms of the GNU Public License, v2.
+
+Terminology
+-----------
+
+ext4 divides a storage device into an array of logical blocks both to
+reduce bookkeeping overhead and to increase throughput by forcing larger
+transfer sizes. Generally, the block size will be 4KiB (the same size as
+pages on x86 and the block layer's default block size), though the
+actual size is calculated as 2 ^ (10 + ``sb.s_log_block_size``) bytes.
+Throughout this document, disk locations are given in terms of these
+logical blocks, not raw LBAs, and not 1024-byte blocks. For the sake of
+convenience, the logical block size will be referred to as
+``$block_size`` throughout the rest of the document.
+
+When referenced in ``preformatted text`` blocks, ``sb`` refers to fields
+in the super block, and ``inode`` refers to fields in an inode table
+entry.
+
+Other References
+----------------
+
+Also see http://www.nongnu.org/ext2-doc/ for quite a collection of
+information about ext2/3. Here's another old reference:
+http://wiki.osdev.org/Ext2
diff --git a/Documentation/filesystems/ext4/ondisk/index.rst b/Documentation/filesystems/ext4/ondisk/index.rst
new file mode 100644
index 000000000000..98cde12ee8cb
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/index.rst
@@ -0,0 +1,6 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+==============================
+Data Structures and Algorithms
+==============================
+.. include:: about.rst
-- 
cgit v1.2.3


From 5cbf777cfdf6e5a7b7149006e4881a255da78fdd Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 27 Jul 2018 16:37:28 +0800
Subject: route: add support for directed broadcast forwarding

This patch implements the feature described in rfc1812#section-5.3.5.2
and rfc2644. It allows the router to forward directed broadcast when
sysctl bc_forwarding is enabled.

Note that this feature could be done by iptables -j TEE, but it would
cause some problems:
  - target TEE's gateway param has to be set with a specific address,
    and it's not flexible especially when the route wants forward all
    directed broadcasts.
  - this duplicates the directed broadcasts so this may cause side
    effects to applications.

Besides, to keep consistent with other os router like BSD, it's also
necessary to implement it in the route rx path.

Note that route cache needs to be flushed when bc_forwarding is
changed.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/inetdevice.h   |  1 +
 include/uapi/linux/ip.h      |  1 +
 include/uapi/linux/netconf.h |  1 +
 net/ipv4/devinet.c           | 11 +++++++++++
 net/ipv4/route.c             |  6 +++++-
 5 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index 27650f1bff3d..c759d1cbcedd 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -93,6 +93,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 
 #define IN_DEV_FORWARD(in_dev)		IN_DEV_CONF_GET((in_dev), FORWARDING)
 #define IN_DEV_MFORWARD(in_dev)		IN_DEV_ANDCONF((in_dev), MC_FORWARDING)
+#define IN_DEV_BFORWARD(in_dev)		IN_DEV_ANDCONF((in_dev), BC_FORWARDING)
 #define IN_DEV_RPFILTER(in_dev)		IN_DEV_MAXCONF((in_dev), RP_FILTER)
 #define IN_DEV_SRC_VMARK(in_dev)    	IN_DEV_ORCONF((in_dev), SRC_VMARK)
 #define IN_DEV_SOURCE_ROUTE(in_dev)	IN_DEV_ANDCONF((in_dev), \
diff --git a/include/uapi/linux/ip.h b/include/uapi/linux/ip.h
index b24a742beae5..e42d13b55cf3 100644
--- a/include/uapi/linux/ip.h
+++ b/include/uapi/linux/ip.h
@@ -168,6 +168,7 @@ enum
 	IPV4_DEVCONF_IGNORE_ROUTES_WITH_LINKDOWN,
 	IPV4_DEVCONF_DROP_UNICAST_IN_L2_MULTICAST,
 	IPV4_DEVCONF_DROP_GRATUITOUS_ARP,
+	IPV4_DEVCONF_BC_FORWARDING,
 	__IPV4_DEVCONF_MAX
 };
 
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index c84fcdfca862..fac4edd55379 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -18,6 +18,7 @@ enum {
 	NETCONFA_PROXY_NEIGH,
 	NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 	NETCONFA_INPUT,
+	NETCONFA_BC_FORWARDING,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index d7585ab1a77a..ea4bd8a52422 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1827,6 +1827,8 @@ static int inet_netconf_msgsize_devconf(int type)
 		size += nla_total_size(4);
 	if (all || type == NETCONFA_MC_FORWARDING)
 		size += nla_total_size(4);
+	if (all || type == NETCONFA_BC_FORWARDING)
+		size += nla_total_size(4);
 	if (all || type == NETCONFA_PROXY_NEIGH)
 		size += nla_total_size(4);
 	if (all || type == NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN)
@@ -1873,6 +1875,10 @@ static int inet_netconf_fill_devconf(struct sk_buff *skb, int ifindex,
 	    nla_put_s32(skb, NETCONFA_MC_FORWARDING,
 			IPV4_DEVCONF(*devconf, MC_FORWARDING)) < 0)
 		goto nla_put_failure;
+	if ((all || type == NETCONFA_BC_FORWARDING) &&
+	    nla_put_s32(skb, NETCONFA_BC_FORWARDING,
+			IPV4_DEVCONF(*devconf, BC_FORWARDING)) < 0)
+		goto nla_put_failure;
 	if ((all || type == NETCONFA_PROXY_NEIGH) &&
 	    nla_put_s32(skb, NETCONFA_PROXY_NEIGH,
 			IPV4_DEVCONF(*devconf, PROXY_ARP)) < 0)
@@ -2143,6 +2149,10 @@ static int devinet_conf_proc(struct ctl_table *ctl, int write,
 			if ((new_value == 0) && (old_value != 0))
 				rt_cache_flush(net);
 
+		if (i == IPV4_DEVCONF_BC_FORWARDING - 1 &&
+		    new_value != old_value)
+			rt_cache_flush(net);
+
 		if (i == IPV4_DEVCONF_RP_FILTER - 1 &&
 		    new_value != old_value) {
 			ifindex = devinet_conf_ifindex(net, cnf);
@@ -2259,6 +2269,7 @@ static struct devinet_sysctl_table {
 		DEVINET_SYSCTL_COMPLEX_ENTRY(FORWARDING, "forwarding",
 					     devinet_sysctl_forward),
 		DEVINET_SYSCTL_RO_ENTRY(MC_FORWARDING, "mc_forwarding"),
+		DEVINET_SYSCTL_RW_ENTRY(BC_FORWARDING, "bc_forwarding"),
 
 		DEVINET_SYSCTL_RW_ENTRY(ACCEPT_REDIRECTS, "accept_redirects"),
 		DEVINET_SYSCTL_RW_ENTRY(SECURE_REDIRECTS, "secure_redirects"),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1df6e97106d7..b678466da451 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1996,8 +1996,11 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		goto no_route;
 	}
 
-	if (res->type == RTN_BROADCAST)
+	if (res->type == RTN_BROADCAST) {
+		if (IN_DEV_BFORWARD(in_dev))
+			goto make_route;
 		goto brd_input;
+	}
 
 	if (res->type == RTN_LOCAL) {
 		err = fib_validate_source(skb, saddr, daddr, tos,
@@ -2014,6 +2017,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (res->type != RTN_UNICAST)
 		goto martian_destination;
 
+make_route:
 	err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys);
 out:	return err;
 
-- 
cgit v1.2.3


From 40f98b9af943c3858958032ce1fb7bad449fac7b Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Fri, 27 Jul 2018 16:37:29 +0800
Subject: selftests: add a selftest for directed broadcast forwarding

As Ido's suggestion, this patch is to add a selftest for directed
broadcast forwarding with vrf. It does the assertion by checking
the src IP of the echo-reply packet in ping_test_from.

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/net/forwarding/router_broadcast.sh   | 233 +++++++++++++++++++++
 1 file changed, 233 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/router_broadcast.sh

diff --git a/tools/testing/selftests/net/forwarding/router_broadcast.sh b/tools/testing/selftests/net/forwarding/router_broadcast.sh
new file mode 100755
index 000000000000..7bd2ebb6e9de
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/router_broadcast.sh
@@ -0,0 +1,233 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+ALL_TESTS="ping_ipv4"
+NUM_NETIFS=6
+source lib.sh
+
+h1_create()
+{
+	vrf_create "vrf-h1"
+	ip link set dev $h1 master vrf-h1
+
+	ip link set dev vrf-h1 up
+	ip link set dev $h1 up
+
+	ip address add 192.0.2.2/24 dev $h1
+
+	ip route add 198.51.100.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+	ip route add 198.51.200.0/24 vrf vrf-h1 nexthop via 192.0.2.1
+}
+
+h1_destroy()
+{
+	ip route del 198.51.200.0/24 vrf vrf-h1
+	ip route del 198.51.100.0/24 vrf vrf-h1
+
+	ip address del 192.0.2.2/24 dev $h1
+
+	ip link set dev $h1 down
+	vrf_destroy "vrf-h1"
+}
+
+h2_create()
+{
+	vrf_create "vrf-h2"
+	ip link set dev $h2 master vrf-h2
+
+	ip link set dev vrf-h2 up
+	ip link set dev $h2 up
+
+	ip address add 198.51.100.2/24 dev $h2
+
+	ip route add 192.0.2.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+	ip route add 198.51.200.0/24 vrf vrf-h2 nexthop via 198.51.100.1
+}
+
+h2_destroy()
+{
+	ip route del 198.51.200.0/24 vrf vrf-h2
+	ip route del 192.0.2.0/24 vrf vrf-h2
+
+	ip address del 198.51.100.2/24 dev $h2
+
+	ip link set dev $h2 down
+	vrf_destroy "vrf-h2"
+}
+
+h3_create()
+{
+	vrf_create "vrf-h3"
+	ip link set dev $h3 master vrf-h3
+
+	ip link set dev vrf-h3 up
+	ip link set dev $h3 up
+
+	ip address add 198.51.200.2/24 dev $h3
+
+	ip route add 192.0.2.0/24 vrf vrf-h3 nexthop via 198.51.200.1
+	ip route add 198.51.100.0/24 vrf vrf-h3 nexthop via 198.51.200.1
+}
+
+h3_destroy()
+{
+	ip route del 198.51.100.0/24 vrf vrf-h3
+	ip route del 192.0.2.0/24 vrf vrf-h3
+
+	ip address del 198.51.200.2/24 dev $h3
+
+	ip link set dev $h3 down
+	vrf_destroy "vrf-h3"
+}
+
+router_create()
+{
+	ip link set dev $rp1 up
+	ip link set dev $rp2 up
+	ip link set dev $rp3 up
+
+	ip address add 192.0.2.1/24 dev $rp1
+
+	ip address add 198.51.100.1/24 dev $rp2
+	ip address add 198.51.200.1/24 dev $rp3
+}
+
+router_destroy()
+{
+	ip address del 198.51.200.1/24 dev $rp3
+	ip address del 198.51.100.1/24 dev $rp2
+
+	ip address del 192.0.2.1/24 dev $rp1
+
+	ip link set dev $rp3 down
+	ip link set dev $rp2 down
+	ip link set dev $rp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	rp1=${NETIFS[p2]}
+
+	rp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	rp3=${NETIFS[p5]}
+	h3=${NETIFS[p6]}
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+	h3_create
+
+	router_create
+
+	forwarding_enable
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	forwarding_restore
+
+	router_destroy
+
+	h3_destroy
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+bc_forwarding_disable()
+{
+	sysctl_set net.ipv4.conf.all.bc_forwarding 0
+	sysctl_set net.ipv4.conf.$rp1.bc_forwarding 0
+}
+
+bc_forwarding_enable()
+{
+	sysctl_set net.ipv4.conf.all.bc_forwarding 1
+	sysctl_set net.ipv4.conf.$rp1.bc_forwarding 1
+}
+
+bc_forwarding_restore()
+{
+	sysctl_restore net.ipv4.conf.$rp1.bc_forwarding
+	sysctl_restore net.ipv4.conf.all.bc_forwarding
+}
+
+ping_test_from()
+{
+	local oif=$1
+	local dip=$2
+	local from=$3
+	local fail=${4:-0}
+
+	RET=0
+
+	log_info "ping $dip, expected reply from $from"
+	ip vrf exec $(master_name_get $oif) \
+	$PING -I $oif $dip -c 10 -i 0.1 -w 2 -b 2>&1 | grep $from &> /dev/null
+	check_err_fail $fail $?
+}
+
+ping_ipv4()
+{
+	sysctl_set net.ipv4.icmp_echo_ignore_broadcasts 0
+
+	bc_forwarding_disable
+	log_info "bc_forwarding disabled on r1 =>"
+	ping_test_from $h1 198.51.100.255 192.0.2.1
+	log_test "h1 -> net2: reply from r1 (not forwarding)"
+	ping_test_from $h1 198.51.200.255 192.0.2.1
+	log_test "h1 -> net3: reply from r1 (not forwarding)"
+	ping_test_from $h1 192.0.2.255 192.0.2.1
+	log_test "h1 -> net1: reply from r1 (not dropping)"
+	ping_test_from $h1 255.255.255.255 192.0.2.1
+	log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)"
+
+	ping_test_from $h2 192.0.2.255 198.51.100.1
+	log_test "h2 -> net1: reply from r1 (not forwarding)"
+	ping_test_from $h2 198.51.200.255 198.51.100.1
+	log_test "h2 -> net3: reply from r1 (not forwarding)"
+	ping_test_from $h2 198.51.100.255 198.51.100.1
+	log_test "h2 -> net2: reply from r1 (not dropping)"
+	ping_test_from $h2 255.255.255.255 198.51.100.1
+	log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)"
+	bc_forwarding_restore
+
+	bc_forwarding_enable
+	log_info "bc_forwarding enabled on r1 =>"
+	ping_test_from $h1 198.51.100.255 198.51.100.2
+	log_test "h1 -> net2: reply from h2 (forwarding)"
+	ping_test_from $h1 198.51.200.255 198.51.200.2
+	log_test "h1 -> net3: reply from h3 (forwarding)"
+	ping_test_from $h1 192.0.2.255 192.0.2.1 1
+	log_test "h1 -> net1: no reply (dropping)"
+	ping_test_from $h1 255.255.255.255 192.0.2.1
+	log_test "h1 -> 255.255.255.255: reply from r1 (not forwarding)"
+
+	ping_test_from $h2 192.0.2.255 192.0.2.2
+	log_test "h2 -> net1: reply from h1 (forwarding)"
+	ping_test_from $h2 198.51.200.255 198.51.200.2
+	log_test "h2 -> net3: reply from h3 (forwarding)"
+	ping_test_from $h2 198.51.100.255 198.51.100.1 1
+	log_test "h2 -> net2: no reply (dropping)"
+	ping_test_from $h2 255.255.255.255 198.51.100.1
+	log_test "h2 -> 255.255.255.255: reply from r1 (not forwarding)"
+	bc_forwarding_restore
+
+	sysctl_restore net.ipv4.icmp_echo_ignore_broadcasts
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From c09f3bac6d8c820b4b4ff0ffcff47e3a68b04e54 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:38:00 -0400
Subject: ext4: import high level design chapter from wiki page

Import the chapter about high level design from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 .../filesystems/ext4/ondisk/allocators.rst         |  56 ++++++++
 Documentation/filesystems/ext4/ondisk/bigalloc.rst |  22 ++++
 .../filesystems/ext4/ondisk/blockgroup.rst         | 135 ++++++++++++++++++++
 Documentation/filesystems/ext4/ondisk/blocks.rst   | 142 +++++++++++++++++++++
 .../filesystems/ext4/ondisk/checksums.rst          |  73 +++++++++++
 Documentation/filesystems/ext4/ondisk/eainode.rst  |  18 +++
 Documentation/filesystems/ext4/ondisk/index.rst    |   1 +
 .../filesystems/ext4/ondisk/inlinedata.rst         |  37 ++++++
 Documentation/filesystems/ext4/ondisk/overview.rst |  26 ++++
 .../filesystems/ext4/ondisk/special_inodes.rst     |  38 ++++++
 10 files changed, 548 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/allocators.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/bigalloc.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/blockgroup.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/blocks.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/checksums.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/eainode.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/inlinedata.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/overview.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/special_inodes.rst

diff --git a/Documentation/filesystems/ext4/ondisk/allocators.rst b/Documentation/filesystems/ext4/ondisk/allocators.rst
new file mode 100644
index 000000000000..7aa85152ace3
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/allocators.rst
@@ -0,0 +1,56 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block and Inode Allocation Policy
+---------------------------------
+
+ext4 recognizes (better than ext3, anyway) that data locality is
+generally a desirably quality of a filesystem. On a spinning disk,
+keeping related blocks near each other reduces the amount of movement
+that the head actuator and disk must perform to access a data block,
+thus speeding up disk IO. On an SSD there of course are no moving parts,
+but locality can increase the size of each transfer request while
+reducing the total number of requests. This locality may also have the
+effect of concentrating writes on a single erase block, which can speed
+up file rewrites significantly. Therefore, it is useful to reduce
+fragmentation whenever possible.
+
+The first tool that ext4 uses to combat fragmentation is the multi-block
+allocator. When a file is first created, the block allocator
+speculatively allocates 8KiB of disk space to the file on the assumption
+that the space will get written soon. When the file is closed, the
+unused speculative allocations are of course freed, but if the
+speculation is correct (typically the case for full writes of small
+files) then the file data gets written out in a single multi-block
+extent. A second related trick that ext4 uses is delayed allocation.
+Under this scheme, when a file needs more blocks to absorb file writes,
+the filesystem defers deciding the exact placement on the disk until all
+the dirty buffers are being written out to disk. By not committing to a
+particular placement until it's absolutely necessary (the commit timeout
+is hit, or sync() is called, or the kernel runs out of memory), the hope
+is that the filesystem can make better location decisions.
+
+The third trick that ext4 (and ext3) uses is that it tries to keep a
+file's data blocks in the same block group as its inode. This cuts down
+on the seek penalty when the filesystem first has to read a file's inode
+to learn where the file's data blocks live and then seek over to the
+file's data blocks to begin I/O operations.
+
+The fourth trick is that all the inodes in a directory are placed in the
+same block group as the directory, when feasible. The working assumption
+here is that all the files in a directory might be related, therefore it
+is useful to try to keep them all together.
+
+The fifth trick is that the disk volume is cut up into 128MB block
+groups; these mini-containers are used as outlined above to try to
+maintain data locality. However, there is a deliberate quirk -- when a
+directory is created in the root directory, the inode allocator scans
+the block groups and puts that directory into the least heavily loaded
+block group that it can find. This encourages directories to spread out
+over a disk; as the top-level directory/file blobs fill up one block
+group, the allocators simply move on to the next block group. Allegedly
+this scheme evens out the loading on the block groups, though the author
+suspects that the directories which are so unlucky as to land towards
+the end of a spinning drive get a raw deal performance-wise.
+
+Of course if all of these mechanisms fail, one can always use e4defrag
+to defragment files.
diff --git a/Documentation/filesystems/ext4/ondisk/bigalloc.rst b/Documentation/filesystems/ext4/ondisk/bigalloc.rst
new file mode 100644
index 000000000000..c6d88557553c
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/bigalloc.rst
@@ -0,0 +1,22 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Bigalloc
+--------
+
+At the moment, the default size of a block is 4KiB, which is a commonly
+supported page size on most MMU-capable hardware. This is fortunate, as
+ext4 code is not prepared to handle the case where the block size
+exceeds the page size. However, for a filesystem of mostly huge files,
+it is desirable to be able to allocate disk blocks in units of multiple
+blocks to reduce both fragmentation and metadata overhead. The
+`bigalloc <Bigalloc>`__ feature provides exactly this ability. The
+administrator can set a block cluster size at mkfs time (which is stored
+in the s\_log\_cluster\_size field in the superblock); from then on, the
+block bitmaps track clusters, not individual blocks. This means that
+block groups can be several gigabytes in size (instead of just 128MiB);
+however, the minimum allocation unit becomes a cluster, not a block,
+even for directories. TaoBao had a patchset to extend the “use units of
+clusters instead of blocks” to the extent tree, though it is not clear
+where those patches went-- they eventually morphed into “extent tree v2”
+but that code has not landed as of May 2015.
+
diff --git a/Documentation/filesystems/ext4/ondisk/blockgroup.rst b/Documentation/filesystems/ext4/ondisk/blockgroup.rst
new file mode 100644
index 000000000000..baf888e4c06a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blockgroup.rst
@@ -0,0 +1,135 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Layout
+------
+
+The layout of a standard block group is approximately as follows (each
+of these fields is discussed in a separate section below):
+
+.. list-table::
+   :widths: 1 1 1 1 1 1 1 1
+   :header-rows: 1
+
+   * - Group 0 Padding
+     - ext4 Super Block
+     - Group Descriptors
+     - Reserved GDT Blocks
+     - Data Block Bitmap
+     - inode Bitmap
+     - inode Table
+     - Data Blocks
+   * - 1024 bytes
+     - 1 block
+     - many blocks
+     - many blocks
+     - 1 block
+     - 1 block
+     - many blocks
+     - many more blocks
+
+For the special case of block group 0, the first 1024 bytes are unused,
+to allow for the installation of x86 boot sectors and other oddities.
+The superblock will start at offset 1024 bytes, whichever block that
+happens to be (usually 0). However, if for some reason the block size =
+1024, then block 0 is marked in use and the superblock goes in block 1.
+For all other block groups, there is no padding.
+
+The ext4 driver primarily works with the superblock and the group
+descriptors that are found in block group 0. Redundant copies of the
+superblock and group descriptors are written to some of the block groups
+across the disk in case the beginning of the disk gets trashed, though
+not all block groups necessarily host a redundant copy (see following
+paragraph for more details). If the group does not have a redundant
+copy, the block group begins with the data block bitmap. Note also that
+when the filesystem is freshly formatted, mkfs will allocate “reserve
+GDT block” space after the block group descriptors and before the start
+of the block bitmaps to allow for future expansion of the filesystem. By
+default, a filesystem is allowed to increase in size by a factor of
+1024x over the original filesystem size.
+
+The location of the inode table is given by ``grp.bg_inode_table_*``. It
+is continuous range of blocks large enough to contain
+``sb.s_inodes_per_group * sb.s_inode_size`` bytes.
+
+As for the ordering of items in a block group, it is generally
+established that the super block and the group descriptor table, if
+present, will be at the beginning of the block group. The bitmaps and
+the inode table can be anywhere, and it is quite possible for the
+bitmaps to come after the inode table, or for both to be in different
+groups (flex\_bg). Leftover space is used for file data blocks, indirect
+block maps, extent tree blocks, and extended attributes.
+
+Flexible Block Groups
+---------------------
+
+Starting in ext4, there is a new feature called flexible block groups
+(flex\_bg). In a flex\_bg, several block groups are tied together as one
+logical block group; the bitmap spaces and the inode table space in the
+first block group of the flex\_bg are expanded to include the bitmaps
+and inode tables of all other block groups in the flex\_bg. For example,
+if the flex\_bg size is 4, then group 0 will contain (in order) the
+superblock, group descriptors, data block bitmaps for groups 0-3, inode
+bitmaps for groups 0-3, inode tables for groups 0-3, and the remaining
+space in group 0 is for file data. The effect of this is to group the
+block metadata close together for faster loading, and to enable large
+files to be continuous on disk. Backup copies of the superblock and
+group descriptors are always at the beginning of block groups, even if
+flex\_bg is enabled. The number of block groups that make up a flex\_bg
+is given by 2 ^ ``sb.s_log_groups_per_flex``.
+
+Meta Block Groups
+-----------------
+
+Without the option META\_BG, for safety concerns, all block group
+descriptors copies are kept in the first block group. Given the default
+128MiB(2^27 bytes) block group size and 64-byte group descriptors, ext4
+can have at most 2^27/64 = 2^21 block groups. This limits the entire
+filesystem size to 2^21 ∗ 2^27 = 2^48bytes or 256TiB.
+
+The solution to this problem is to use the metablock group feature
+(META\_BG), which is already in ext3 for all 2.6 releases. With the
+META\_BG feature, ext4 filesystems are partitioned into many metablock
+groups. Each metablock group is a cluster of block groups whose group
+descriptor structures can be stored in a single disk block. For ext4
+filesystems with 4 KB block size, a single metablock group partition
+includes 64 block groups, or 8 GiB of disk space. The metablock group
+feature moves the location of the group descriptors from the congested
+first block group of the whole filesystem into the first group of each
+metablock group itself. The backups are in the second and last group of
+each metablock group. This increases the 2^21 maximum block groups limit
+to the hard limit 2^32, allowing support for a 512PiB filesystem.
+
+The change in the filesystem format replaces the current scheme where
+the superblock is followed by a variable-length set of block group
+descriptors. Instead, the superblock and a single block group descriptor
+block is placed at the beginning of the first, second, and last block
+groups in a meta-block group. A meta-block group is a collection of
+block groups which can be described by a single block group descriptor
+block. Since the size of the block group descriptor structure is 32
+bytes, a meta-block group contains 32 block groups for filesystems with
+a 1KB block size, and 128 block groups for filesystems with a 4KB
+blocksize. Filesystems can either be created using this new block group
+descriptor layout, or existing filesystems can be resized on-line, and
+the field s\_first\_meta\_bg in the superblock will indicate the first
+block group using this new layout.
+
+Please see an important note about ``BLOCK_UNINIT`` in the section about
+block and inode bitmaps.
+
+Lazy Block Group Initialization
+-------------------------------
+
+A new feature for ext4 are three block group descriptor flags that
+enable mkfs to skip initializing other parts of the block group
+metadata. Specifically, the INODE\_UNINIT and BLOCK\_UNINIT flags mean
+that the inode and block bitmaps for that group can be calculated and
+therefore the on-disk bitmap blocks are not initialized. This is
+generally the case for an empty block group or a block group containing
+only fixed-location block group metadata. The INODE\_ZEROED flag means
+that the inode table has been initialized; mkfs will unset this flag and
+rely on the kernel to initialize the inode tables in the background.
+
+By not writing zeroes to the bitmaps and inode table, mkfs time is
+reduced considerably. Note the feature flag is RO\_COMPAT\_GDT\_CSUM,
+but the dumpe2fs output prints this as “uninit\_bg”. They are the same
+thing.
diff --git a/Documentation/filesystems/ext4/ondisk/blocks.rst b/Documentation/filesystems/ext4/ondisk/blocks.rst
new file mode 100644
index 000000000000..73d4dc0f7bda
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blocks.rst
@@ -0,0 +1,142 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Blocks
+------
+
+ext4 allocates storage space in units of “blocks”. A block is a group of
+sectors between 1KiB and 64KiB, and the number of sectors must be an
+integral power of 2. Blocks are in turn grouped into larger units called
+block groups. Block size is specified at mkfs time and typically is
+4KiB. You may experience mounting problems if block size is greater than
+page size (i.e. 64KiB blocks on a i386 which only has 4KiB memory
+pages). By default a filesystem can contain 2^32 blocks; if the '64bit'
+feature is enabled, then a filesystem can have 2^64 blocks.
+
+For 32-bit filesystems, limits are as follows:
+
+.. list-table::
+   :widths: 1 1 1 1 1
+   :header-rows: 1
+
+   * - Item
+     - 1KiB
+     - 2KiB
+     - 4KiB
+     - 64KiB
+   * - Blocks
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Inodes
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - File System Size
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256PiB
+   * - Blocks Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Inodes Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Block Group Size
+     - 8MiB
+     - 32MiB
+     - 128MiB
+     - 32GiB
+   * - Blocks Per File, Extents
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Blocks Per File, Block Maps
+     - 16,843,020
+     - 134,480,396
+     - 1,074,791,436
+     - 4,398,314,962,956 (really 2^32 due to field size limitations)
+   * - File Size, Extents
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256TiB
+   * - File Size, Block Maps
+     - 16GiB
+     - 256GiB
+     - 4TiB
+     - 256TiB
+
+For 64-bit filesystems, limits are as follows:
+
+.. list-table::
+   :widths: 1 1 1 1 1
+   :header-rows: 1
+
+   * - Item
+     - 1KiB
+     - 2KiB
+     - 4KiB
+     - 64KiB
+   * - Blocks
+     - 2^64
+     - 2^64
+     - 2^64
+     - 2^64
+   * - Inodes
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - File System Size
+     - 16ZiB
+     - 32ZiB
+     - 64ZiB
+     - 1YiB
+   * - Blocks Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Inodes Per Block Group
+     - 8,192
+     - 16,384
+     - 32,768
+     - 524,288
+   * - Block Group Size
+     - 8MiB
+     - 32MiB
+     - 128MiB
+     - 32GiB
+   * - Blocks Per File, Extents
+     - 2^32
+     - 2^32
+     - 2^32
+     - 2^32
+   * - Blocks Per File, Block Maps
+     - 16,843,020
+     - 134,480,396
+     - 1,074,791,436
+     - 4,398,314,962,956 (really 2^32 due to field size limitations)
+   * - File Size, Extents
+     - 4TiB
+     - 8TiB
+     - 16TiB
+     - 256TiB
+   * - File Size, Block Maps
+     - 16GiB
+     - 256GiB
+     - 4TiB
+     - 256TiB
+
+Note: Files not using extents (i.e. files using block maps) must be
+placed within the first 2^32 blocks of a filesystem. Files with extents
+must be placed within the first 2^48 blocks of a filesystem. It's not
+clear what happens with larger filesystems.
diff --git a/Documentation/filesystems/ext4/ondisk/checksums.rst b/Documentation/filesystems/ext4/ondisk/checksums.rst
new file mode 100644
index 000000000000..9d6a793b2e03
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/checksums.rst
@@ -0,0 +1,73 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Checksums
+---------
+
+Starting in early 2012, metadata checksums were added to all major ext4
+and jbd2 data structures. The associated feature flag is metadata\_csum.
+The desired checksum algorithm is indicated in the superblock, though as
+of October 2012 the only supported algorithm is crc32c. Some data
+structures did not have space to fit a full 32-bit checksum, so only the
+lower 16 bits are stored. Enabling the 64bit feature increases the data
+structure size so that full 32-bit checksums can be stored for many data
+structures. However, existing 32-bit filesystems cannot be extended to
+enable 64bit mode, at least not without the experimental resize2fs
+patches to do so.
+
+Existing filesystems can have checksumming added by running
+``tune2fs -O metadata_csum`` against the underlying device. If tune2fs
+encounters directory blocks that lack sufficient empty space to add a
+checksum, it will request that you run ``e2fsck -D`` to have the
+directories rebuilt with checksums. This has the added benefit of
+removing slack space from the directory files and rebalancing the htree
+indexes. If you \_ignore\_ this step, your directories will not be
+protected by a checksum!
+
+The following table describes the data elements that go into each type
+of checksum. The checksum function is whatever the superblock describes
+(crc32c as of October 2013) unless noted otherwise.
+
+.. list-table::
+   :widths: 1 1 4
+   :header-rows: 1
+
+   * - Metadata
+     - Length
+     - Ingredients
+   * - Superblock
+     - \_\_le32
+     - The entire superblock up to the checksum field. The UUID lives inside
+       the superblock.
+   * - MMP
+     - \_\_le32
+     - UUID + the entire MMP block up to the checksum field.
+   * - Extended Attributes
+     - \_\_le32
+     - UUID + the entire extended attribute block. The checksum field is set to
+       zero.
+   * - Directory Entries
+     - \_\_le32
+     - UUID + inode number + inode generation + the directory block up to the
+       fake entry enclosing the checksum field.
+   * - HTREE Nodes
+     - \_\_le32
+     - UUID + inode number + inode generation + all valid extents + HTREE tail.
+       The checksum field is set to zero.
+   * - Extents
+     - \_\_le32
+     - UUID + inode number + inode generation + the entire extent block up to
+       the checksum field.
+   * - Bitmaps
+     - \_\_le32 or \_\_le16
+     - UUID + the entire bitmap. Checksums are stored in the group descriptor,
+       and truncated if the group descriptor size is 32 bytes (i.e. ^64bit)
+   * - Inodes
+     - \_\_le32
+     - UUID + inode number + inode generation + the entire inode. The checksum
+       field is set to zero. Each inode has its own checksum.
+   * - Group Descriptors
+     - \_\_le16
+     - If metadata\_csum, then UUID + group number + the entire descriptor;
+       else if gdt\_csum, then crc16(UUID + group number + the entire
+       descriptor). In all cases, only the lower 16 bits are stored.
+
diff --git a/Documentation/filesystems/ext4/ondisk/eainode.rst b/Documentation/filesystems/ext4/ondisk/eainode.rst
new file mode 100644
index 000000000000..ecc0d01a0a72
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/eainode.rst
@@ -0,0 +1,18 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Large Extended Attribute Values
+-------------------------------
+
+To enable ext4 to store extended attribute values that do not fit in the
+inode or in the single extended attribute block attached to an inode,
+the EA\_INODE feature allows us to store the value in the data blocks of
+a regular file inode. This “EA inode” is linked only from the extended
+attribute name index and must not appear in a directory entry. The
+inode's i\_atime field is used to store a checksum of the xattr value;
+and i\_ctime/i\_version store a 64-bit reference count, which enables
+sharing of large xattr values between multiple owning inodes. For
+backward compatibility with older versions of this feature, the
+i\_mtime/i\_generation *may* store a back-reference to the inode number
+and i\_generation of the **one** owning inode (in cases where the EA
+inode is not referenced by multiple inodes) to verify that the EA inode
+is the correct one being accessed.
diff --git a/Documentation/filesystems/ext4/ondisk/index.rst b/Documentation/filesystems/ext4/ondisk/index.rst
index 98cde12ee8cb..282ba197b6b2 100644
--- a/Documentation/filesystems/ext4/ondisk/index.rst
+++ b/Documentation/filesystems/ext4/ondisk/index.rst
@@ -4,3 +4,4 @@
 Data Structures and Algorithms
 ==============================
 .. include:: about.rst
+.. include:: overview.rst
diff --git a/Documentation/filesystems/ext4/ondisk/inlinedata.rst b/Documentation/filesystems/ext4/ondisk/inlinedata.rst
new file mode 100644
index 000000000000..d1075178ce0b
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/inlinedata.rst
@@ -0,0 +1,37 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Inline Data
+-----------
+
+The inline data feature was designed to handle the case that a file's
+data is so tiny that it readily fits inside the inode, which
+(theoretically) reduces disk block consumption and reduces seeks. If the
+file is smaller than 60 bytes, then the data are stored inline in
+``inode.i_block``. If the rest of the file would fit inside the extended
+attribute space, then it might be found as an extended attribute
+“system.data” within the inode body (“ibody EA”). This of course
+constrains the amount of extended attributes one can attach to an inode.
+If the data size increases beyond i\_block + ibody EA, a regular block
+is allocated and the contents moved to that block.
+
+Pending a change to compact the extended attribute key used to store
+inline data, one ought to be able to store 160 bytes of data in a
+256-byte inode (as of June 2015, when i\_extra\_isize is 28). Prior to
+that, the limit was 156 bytes due to inefficient use of inode space.
+
+The inline data feature requires the presence of an extended attribute
+for “system.data”, even if the attribute value is zero length.
+
+Inline Directories
+~~~~~~~~~~~~~~~~~~
+
+The first four bytes of i\_block are the inode number of the parent
+directory. Following that is a 56-byte space for an array of directory
+entries; see ``struct ext4_dir_entry``. If there is a “system.data”
+attribute in the inode body, the EA value is an array of
+``struct ext4_dir_entry`` as well. Note that for inline directories, the
+i\_block and EA space are treated as separate dirent blocks; directory
+entries cannot span the two.
+
+Inline directory entries are not checksummed, as the inode checksum
+should protect all inline data contents.
diff --git a/Documentation/filesystems/ext4/ondisk/overview.rst b/Documentation/filesystems/ext4/ondisk/overview.rst
new file mode 100644
index 000000000000..cbab18baba12
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/overview.rst
@@ -0,0 +1,26 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+High Level Design
+=================
+
+An ext4 file system is split into a series of block groups. To reduce
+performance difficulties due to fragmentation, the block allocator tries
+very hard to keep each file's blocks within the same group, thereby
+reducing seek times. The size of a block group is specified in
+``sb.s_blocks_per_group`` blocks, though it can also calculated as 8 \*
+``block_size_in_bytes``. With the default block size of 4KiB, each group
+will contain 32,768 blocks, for a length of 128MiB. The number of block
+groups is the size of the device divided by the size of a block group.
+
+All fields in ext4 are written to disk in little-endian order. HOWEVER,
+all fields in jbd2 (the journal) are written to disk in big-endian
+order.
+
+.. include:: blocks.rst
+.. include:: blockgroup.rst
+.. include:: special_inodes.rst
+.. include:: allocators.rst
+.. include:: checksums.rst
+.. include:: bigalloc.rst
+.. include:: inlinedata.rst
+.. include:: eainode.rst
diff --git a/Documentation/filesystems/ext4/ondisk/special_inodes.rst b/Documentation/filesystems/ext4/ondisk/special_inodes.rst
new file mode 100644
index 000000000000..a82f70c9baeb
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/special_inodes.rst
@@ -0,0 +1,38 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Special inodes
+--------------
+
+ext4 reserves some inode for special features, as follows:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - inode Number
+     - Purpose
+   * - 0
+     - Doesn't exist; there is no inode 0.
+   * - 1
+     - List of defective blocks.
+   * - 2
+     - Root directory.
+   * - 3
+     - User quota.
+   * - 4
+     - Group quota.
+   * - 5
+     - Boot loader.
+   * - 6
+     - Undelete directory.
+   * - 7
+     - Reserved group descriptors inode. (“resize inode”)
+   * - 8
+     - Journal inode.
+   * - 9
+     - The “exclude” inode, for snapshots(?)
+   * - 10
+     - Replica inode, used for some non-upstream feature?
+   * - 11
+     - Traditional first non-reserved inode. Usually this is the lost+found directory. See s\_first\_ino in the superblock.
+
-- 
cgit v1.2.3


From 3db42a2139f0355554087f82916fa88d7a365230 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:39:00 -0400
Subject: ext4: import superblocks chapter from wiki page

Import the chapter about superblocks from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ondisk/globals.rst |   9 +
 Documentation/filesystems/ext4/ondisk/index.rst   |   1 +
 Documentation/filesystems/ext4/ondisk/super.rst   | 773 ++++++++++++++++++++++
 3 files changed, 783 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/globals.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/super.rst

diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/ondisk/globals.rst
new file mode 100644
index 000000000000..4a33d0571bf2
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/globals.rst
@@ -0,0 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Global Structures
+=================
+
+The filesystem is sharded into a number of block groups, each of which
+have static metadata at fixed locations.
+
+.. include:: super.rst
diff --git a/Documentation/filesystems/ext4/ondisk/index.rst b/Documentation/filesystems/ext4/ondisk/index.rst
index 282ba197b6b2..dbb259f83976 100644
--- a/Documentation/filesystems/ext4/ondisk/index.rst
+++ b/Documentation/filesystems/ext4/ondisk/index.rst
@@ -5,3 +5,4 @@ Data Structures and Algorithms
 ==============================
 .. include:: about.rst
 .. include:: overview.rst
+.. include:: globals.rst
diff --git a/Documentation/filesystems/ext4/ondisk/super.rst b/Documentation/filesystems/ext4/ondisk/super.rst
new file mode 100644
index 000000000000..1f5ac9ab6f0c
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/super.rst
@@ -0,0 +1,773 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Super Block
+-----------
+
+The superblock records various information about the enclosing
+filesystem, such as block counts, inode counts, supported features,
+maintenance information, and more.
+
+If the sparse\_super feature flag is set, redundant copies of the
+superblock and group descriptors are kept only in the groups whose group
+number is either 0 or a power of 3, 5, or 7. If the flag is not set,
+redundant copies are kept in all groups.
+
+The superblock checksum is calculated against the superblock structure,
+which includes the FS UUID.
+
+The ext4 superblock is laid out as follows in
+``struct ext4_super_block``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - s\_inodes\_count
+     - Total inode count.
+   * - 0x4
+     - \_\_le32
+     - s\_blocks\_count\_lo
+     - Total block count.
+   * - 0x8
+     - \_\_le32
+     - s\_r\_blocks\_count\_lo
+     - This number of blocks can only be allocated by the super-user.
+   * - 0xC
+     - \_\_le32
+     - s\_free\_blocks\_count\_lo
+     - Free block count.
+   * - 0x10
+     - \_\_le32
+     - s\_free\_inodes\_count
+     - Free inode count.
+   * - 0x14
+     - \_\_le32
+     - s\_first\_data\_block
+     - First data block. This must be at least 1 for 1k-block filesystems and
+       is typically 0 for all other block sizes.
+   * - 0x18
+     - \_\_le32
+     - s\_log\_block\_size
+     - Block size is 2 ^ (10 + s\_log\_block\_size).
+   * - 0x1C
+     - \_\_le32
+     - s\_log\_cluster\_size
+     - Cluster size is (2 ^ s\_log\_cluster\_size) blocks if bigalloc is
+       enabled. Otherwise s\_log\_cluster\_size must equal s\_log\_block\_size.
+   * - 0x20
+     - \_\_le32
+     - s\_blocks\_per\_group
+     - Blocks per group.
+   * - 0x24
+     - \_\_le32
+     - s\_clusters\_per\_group
+     - Clusters per group, if bigalloc is enabled. Otherwise
+       s\_clusters\_per\_group must equal s\_blocks\_per\_group.
+   * - 0x28
+     - \_\_le32
+     - s\_inodes\_per\_group
+     - Inodes per group.
+   * - 0x2C
+     - \_\_le32
+     - s\_mtime
+     - Mount time, in seconds since the epoch.
+   * - 0x30
+     - \_\_le32
+     - s\_wtime
+     - Write time, in seconds since the epoch.
+   * - 0x34
+     - \_\_le16
+     - s\_mnt\_count
+     - Number of mounts since the last fsck.
+   * - 0x36
+     - \_\_le16
+     - s\_max\_mnt\_count
+     - Number of mounts beyond which a fsck is needed.
+   * - 0x38
+     - \_\_le16
+     - s\_magic
+     - Magic signature, 0xEF53
+   * - 0x3A
+     - \_\_le16
+     - s\_state
+     - File system state. See super_state_ for more info.
+   * - 0x3C
+     - \_\_le16
+     - s\_errors
+     - Behaviour when detecting errors. See super_errors_ for more info.
+   * - 0x3E
+     - \_\_le16
+     - s\_minor\_rev\_level
+     - Minor revision level.
+   * - 0x40
+     - \_\_le32
+     - s\_lastcheck
+     - Time of last check, in seconds since the epoch.
+   * - 0x44
+     - \_\_le32
+     - s\_checkinterval
+     - Maximum time between checks, in seconds.
+   * - 0x48
+     - \_\_le32
+     - s\_creator\_os
+     - Creator OS. See the table super_creator_ for more info.
+   * - 0x4C
+     - \_\_le32
+     - s\_rev\_level
+     - Revision level. See the table super_revision_ for more info.
+   * - 0x50
+     - \_\_le16
+     - s\_def\_resuid
+     - Default uid for reserved blocks.
+   * - 0x52
+     - \_\_le16
+     - s\_def\_resgid
+     - Default gid for reserved blocks.
+   * -
+     -
+     -
+     - These fields are for EXT4_DYNAMIC_REV superblocks only.
+       
+       Note: the difference between the compatible feature set and the
+       incompatible feature set is that if there is a bit set in the
+       incompatible feature set that the kernel doesn't know about, it should
+       refuse to mount the filesystem.
+       
+       e2fsck's requirements are more strict; if it doesn't know
+       about a feature in either the compatible or incompatible feature set, it
+       must abort and not try to meddle with things it doesn't understand...
+   * - 0x54
+     - \_\_le32
+     - s\_first\_ino
+     - First non-reserved inode.
+   * - 0x58
+     - \_\_le16
+     - s\_inode\_size
+     - Size of inode structure, in bytes.
+   * - 0x5A
+     - \_\_le16
+     - s\_block\_group\_nr
+     - Block group # of this superblock.
+   * - 0x5C
+     - \_\_le32
+     - s\_feature\_compat
+     - Compatible feature set flags. Kernel can still read/write this fs even
+       if it doesn't understand a flag; fsck should not do that. See the
+       super_compat_ table for more info.
+   * - 0x60
+     - \_\_le32
+     - s\_feature\_incompat
+     - Incompatible feature set. If the kernel or fsck doesn't understand one
+       of these bits, it should stop. See the super_incompat_ table for more
+       info.
+   * - 0x64
+     - \_\_le32
+     - s\_feature\_ro\_compat
+     - Readonly-compatible feature set. If the kernel doesn't understand one of
+       these bits, it can still mount read-only. See the super_rocompat_ table
+       for more info.
+   * - 0x68
+     - \_\_u8
+     - s\_uuid[16]
+     - 128-bit UUID for volume.
+   * - 0x78
+     - char
+     - s\_volume\_name[16]
+     - Volume label.
+   * - 0x88
+     - char
+     - s\_last\_mounted[64]
+     - Directory where filesystem was last mounted.
+   * - 0xC8
+     - \_\_le32
+     - s\_algorithm\_usage\_bitmap
+     - For compression (Not used in e2fsprogs/Linux)
+   * -
+     -
+     -
+     - Performance hints.  Directory preallocation should only happen if the
+       EXT4_FEATURE_COMPAT_DIR_PREALLOC flag is on.
+   * - 0xCC
+     - \_\_u8
+     - s\_prealloc\_blocks
+     - #. of blocks to try to preallocate for ... files? (Not used in
+       e2fsprogs/Linux)
+   * - 0xCD
+     - \_\_u8
+     - s\_prealloc\_dir\_blocks
+     - #. of blocks to preallocate for directories. (Not used in
+       e2fsprogs/Linux)
+   * - 0xCE
+     - \_\_le16
+     - s\_reserved\_gdt\_blocks
+     - Number of reserved GDT entries for future filesystem expansion.
+   * -
+     -
+     -
+     - Journalling support is valid only if EXT4_FEATURE_COMPAT_HAS_JOURNAL is
+       set.
+   * - 0xD0
+     - \_\_u8
+     - s\_journal\_uuid[16]
+     - UUID of journal superblock
+   * - 0xE0
+     - \_\_le32
+     - s\_journal\_inum
+     - inode number of journal file.
+   * - 0xE4
+     - \_\_le32
+     - s\_journal\_dev
+     - Device number of journal file, if the external journal feature flag is
+       set.
+   * - 0xE8
+     - \_\_le32
+     - s\_last\_orphan
+     - Start of list of orphaned inodes to delete.
+   * - 0xEC
+     - \_\_le32
+     - s\_hash\_seed[4]
+     - HTREE hash seed.
+   * - 0xFC
+     - \_\_u8
+     - s\_def\_hash\_version
+     - Default hash algorithm to use for directory hashes. See super_def_hash_
+       for more info.
+   * - 0xFD
+     - \_\_u8
+     - s\_jnl\_backup\_type
+     - If this value is 0 or EXT3\_JNL\_BACKUP\_BLOCKS (1), then the
+       ``s_jnl_blocks`` field contains a duplicate copy of the inode's
+       ``i_block[]`` array and ``i_size``.
+   * - 0xFE
+     - \_\_le16
+     - s\_desc\_size
+     - Size of group descriptors, in bytes, if the 64bit incompat feature flag
+       is set.
+   * - 0x100
+     - \_\_le32
+     - s\_default\_mount\_opts
+     - Default mount options. See the super_mountopts_ table for more info.
+   * - 0x104
+     - \_\_le32
+     - s\_first\_meta\_bg
+     - First metablock block group, if the meta\_bg feature is enabled.
+   * - 0x108
+     - \_\_le32
+     - s\_mkfs\_time
+     - When the filesystem was created, in seconds since the epoch.
+   * - 0x10C
+     - \_\_le32
+     - s\_jnl\_blocks[17]
+     - Backup copy of the journal inode's ``i_block[]`` array in the first 15
+       elements and i\_size\_high and i\_size in the 16th and 17th elements,
+       respectively.
+   * -
+     -
+     -
+     - 64bit support is valid only if EXT4_FEATURE_COMPAT_64BIT is set.
+   * - 0x150
+     - \_\_le32
+     - s\_blocks\_count\_hi
+     - High 32-bits of the block count.
+   * - 0x154
+     - \_\_le32
+     - s\_r\_blocks\_count\_hi
+     - High 32-bits of the reserved block count.
+   * - 0x158
+     - \_\_le32
+     - s\_free\_blocks\_count\_hi
+     - High 32-bits of the free block count.
+   * - 0x15C
+     - \_\_le16
+     - s\_min\_extra\_isize
+     - All inodes have at least # bytes.
+   * - 0x15E
+     - \_\_le16
+     - s\_want\_extra\_isize
+     - New inodes should reserve # bytes.
+   * - 0x160
+     - \_\_le32
+     - s\_flags
+     - Miscellaneous flags. See the super_flags_ table for more info.
+   * - 0x164
+     - \_\_le16
+     - s\_raid\_stride
+     - RAID stride. This is the number of logical blocks read from or written
+       to the disk before moving to the next disk. This affects the placement
+       of filesystem metadata, which will hopefully make RAID storage faster.
+   * - 0x166
+     - \_\_le16
+     - s\_mmp\_interval
+     - #. seconds to wait in multi-mount prevention (MMP) checking. In theory,
+       MMP is a mechanism to record in the superblock which host and device
+       have mounted the filesystem, in order to prevent multiple mounts. This
+       feature does not seem to be implemented...
+   * - 0x168
+     - \_\_le64
+     - s\_mmp\_block
+     - Block # for multi-mount protection data.
+   * - 0x170
+     - \_\_le32
+     - s\_raid\_stripe\_width
+     - RAID stripe width. This is the number of logical blocks read from or
+       written to the disk before coming back to the current disk. This is used
+       by the block allocator to try to reduce the number of read-modify-write
+       operations in a RAID5/6.
+   * - 0x174
+     - \_\_u8
+     - s\_log\_groups\_per\_flex
+     - Size of a flexible block group is 2 ^ ``s_log_groups_per_flex``.
+   * - 0x175
+     - \_\_u8
+     - s\_checksum\_type
+     - Metadata checksum algorithm type. The only valid value is 1 (crc32c).
+   * - 0x176
+     - \_\_le16
+     - s\_reserved\_pad
+     -
+   * - 0x178
+     - \_\_le64
+     - s\_kbytes\_written
+     - Number of KiB written to this filesystem over its lifetime.
+   * - 0x180
+     - \_\_le32
+     - s\_snapshot\_inum
+     - inode number of active snapshot. (Not used in e2fsprogs/Linux.)
+   * - 0x184
+     - \_\_le32
+     - s\_snapshot\_id
+     - Sequential ID of active snapshot. (Not used in e2fsprogs/Linux.)
+   * - 0x188
+     - \_\_le64
+     - s\_snapshot\_r\_blocks\_count
+     - Number of blocks reserved for active snapshot's future use. (Not used in
+       e2fsprogs/Linux.)
+   * - 0x190
+     - \_\_le32
+     - s\_snapshot\_list
+     - inode number of the head of the on-disk snapshot list. (Not used in
+       e2fsprogs/Linux.)
+   * - 0x194
+     - \_\_le32
+     - s\_error\_count
+     - Number of errors seen.
+   * - 0x198
+     - \_\_le32
+     - s\_first\_error\_time
+     - First time an error happened, in seconds since the epoch.
+   * - 0x19C
+     - \_\_le32
+     - s\_first\_error\_ino
+     - inode involved in first error.
+   * - 0x1A0
+     - \_\_le64
+     - s\_first\_error\_block
+     - Number of block involved of first error.
+   * - 0x1A8
+     - \_\_u8
+     - s\_first\_error\_func[32]
+     - Name of function where the error happened.
+   * - 0x1C8
+     - \_\_le32
+     - s\_first\_error\_line
+     - Line number where error happened.
+   * - 0x1CC
+     - \_\_le32
+     - s\_last\_error\_time
+     - Time of most recent error, in seconds since the epoch.
+   * - 0x1D0
+     - \_\_le32
+     - s\_last\_error\_ino
+     - inode involved in most recent error.
+   * - 0x1D4
+     - \_\_le32
+     - s\_last\_error\_line
+     - Line number where most recent error happened.
+   * - 0x1D8
+     - \_\_le64
+     - s\_last\_error\_block
+     - Number of block involved in most recent error.
+   * - 0x1E0
+     - \_\_u8
+     - s\_last\_error\_func[32]
+     - Name of function where the most recent error happened.
+   * - 0x200
+     - \_\_u8
+     - s\_mount\_opts[64]
+     - ASCIIZ string of mount options.
+   * - 0x240
+     - \_\_le32
+     - s\_usr\_quota\_inum
+     - Inode number of user `quota <quota>`__ file.
+   * - 0x244
+     - \_\_le32
+     - s\_grp\_quota\_inum
+     - Inode number of group `quota <quota>`__ file.
+   * - 0x248
+     - \_\_le32
+     - s\_overhead\_blocks
+     - Overhead blocks/clusters in fs. (Huh? This field is always zero, which
+       means that the kernel calculates it dynamically.)
+   * - 0x24C
+     - \_\_le32
+     - s\_backup\_bgs[2]
+     - Block groups containing superblock backups (if sparse\_super2)
+   * - 0x254
+     - \_\_u8
+     - s\_encrypt\_algos[4]
+     - Encryption algorithms in use. There can be up to four algorithms in use
+       at any time; valid algorithm codes are given in the super_encrypt_ table
+       below.
+   * - 0x258
+     - \_\_u8
+     - s\_encrypt\_pw\_salt[16]
+     - Salt for the string2key algorithm for encryption.
+   * - 0x268
+     - \_\_le32
+     - s\_lpf\_ino
+     - Inode number of lost+found
+   * - 0x26C
+     - \_\_le32
+     - s\_prj\_quota\_inum
+     - Inode that tracks project quotas.
+   * - 0x270
+     - \_\_le32
+     - s\_checksum\_seed
+     - Checksum seed used for metadata\_csum calculations. This value is
+       crc32c(~0, $orig\_fs\_uuid).
+   * - 0x274
+     - \_\_le32
+     - s\_reserved[98]
+     - Padding to the end of the block.
+   * - 0x3FC
+     - \_\_le32
+     - s\_checksum
+     - Superblock checksum.
+
+.. _super_state:
+
+The superblock state is some combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Cleanly umounted
+   * - 0x0002
+     - Errors detected
+   * - 0x0004
+     - Orphans being recovered
+
+.. _super_errors:
+
+The superblock error policy is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - Continue
+   * - 2
+     - Remount read-only
+   * - 3
+     - Panic
+
+.. _super_creator:
+
+The filesystem creator is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Linux
+   * - 1
+     - Hurd
+   * - 2
+     - Masix
+   * - 3
+     - FreeBSD
+   * - 4
+     - Lites
+
+.. _super_revision:
+
+The superblock revision is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Original format
+   * - 1
+     - v2 format w/ dynamic inode sizes
+
+Note that ``EXT4_DYNAMIC_REV`` refers to a revision 1 or newer filesystem.
+
+.. _super_compat:
+
+The superblock compatible features field is a combination of any of the
+following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Directory preallocation (COMPAT\_DIR\_PREALLOC).
+   * - 0x2
+     - “imagic inodes”. Not clear from the code what this does
+       (COMPAT\_IMAGIC\_INODES).
+   * - 0x4
+     - Has a journal (COMPAT\_HAS\_JOURNAL).
+   * - 0x8
+     - Supports extended attributes (COMPAT\_EXT\_ATTR).
+   * - 0x10
+     - Has reserved GDT blocks for filesystem expansion
+       (COMPAT\_RESIZE\_INODE). Requires RO\_COMPAT\_SPARSE\_SUPER.
+   * - 0x20
+     - Has directory indices (COMPAT\_DIR\_INDEX).
+   * - 0x40
+     - “Lazy BG”. Not in Linux kernel, seems to have been for uninitialized
+       block groups? (COMPAT\_LAZY\_BG)
+   * - 0x80
+     - “Exclude inode”. Not used. (COMPAT\_EXCLUDE\_INODE).
+   * - 0x100
+     - “Exclude bitmap”. Seems to be used to indicate the presence of
+       snapshot-related exclude bitmaps? Not defined in kernel or used in
+       e2fsprogs (COMPAT\_EXCLUDE\_BITMAP).
+   * - 0x200
+     - Sparse Super Block, v2. If this flag is set, the SB field s\_backup\_bgs
+       points to the two block groups that contain backup superblocks
+       (COMPAT\_SPARSE\_SUPER2).
+
+.. _super_incompat:
+
+The superblock incompatible features field is a combination of any of the
+following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Compression (INCOMPAT\_COMPRESSION).
+   * - 0x2
+     - Directory entries record the file type. See ext4\_dir\_entry\_2 below
+       (INCOMPAT\_FILETYPE).
+   * - 0x4
+     - Filesystem needs recovery (INCOMPAT\_RECOVER).
+   * - 0x8
+     - Filesystem has a separate journal device (INCOMPAT\_JOURNAL\_DEV).
+   * - 0x10
+     - Meta block groups. See the earlier discussion of this feature
+       (INCOMPAT\_META\_BG).
+   * - 0x40
+     - Files in this filesystem use extents (INCOMPAT\_EXTENTS).
+   * - 0x80
+     - Enable a filesystem size of 2^64 blocks (INCOMPAT\_64BIT).
+   * - 0x100
+     - Multiple mount protection. Not implemented (INCOMPAT\_MMP).
+   * - 0x200
+     - Flexible block groups. See the earlier discussion of this feature
+       (INCOMPAT\_FLEX\_BG).
+   * - 0x400
+     - Inodes can be used to store large extended attribute values
+       (INCOMPAT\_EA\_INODE).
+   * - 0x1000
+     - Data in directory entry (INCOMPAT\_DIRDATA). (Not implemented?)
+   * - 0x2000
+     - Metadata checksum seed is stored in the superblock. This feature enables
+       the administrator to change the UUID of a metadata\_csum filesystem
+       while the filesystem is mounted; without it, the checksum definition
+       requires all metadata blocks to be rewritten (INCOMPAT\_CSUM\_SEED).
+   * - 0x4000
+     - Large directory >2GB or 3-level htree (INCOMPAT\_LARGEDIR). Prior to
+       this feature, directories could not be larger than 4GiB and could not
+       have an htree more than 2 levels deep. If this feature is enabled,
+       directories can be larger than 4GiB and have a maximum htree depth of 3.
+   * - 0x8000
+     - Data in inode (INCOMPAT\_INLINE\_DATA).
+   * - 0x10000
+     - Encrypted inodes are present on the filesystem. (INCOMPAT\_ENCRYPT).
+
+.. _super_rocompat:
+
+The superblock read-only compatible features field is a combination of any of
+the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Sparse superblocks. See the earlier discussion of this feature
+       (RO\_COMPAT\_SPARSE\_SUPER).
+   * - 0x2
+     - This filesystem has been used to store a file greater than 2GiB
+       (RO\_COMPAT\_LARGE\_FILE).
+   * - 0x4
+     - Not used in kernel or e2fsprogs (RO\_COMPAT\_BTREE\_DIR).
+   * - 0x8
+     - This filesystem has files whose sizes are represented in units of
+       logical blocks, not 512-byte sectors. This implies a very large file
+       indeed! (RO\_COMPAT\_HUGE\_FILE)
+   * - 0x10
+     - Group descriptors have checksums. In addition to detecting corruption,
+       this is useful for lazy formatting with uninitialized groups
+       (RO\_COMPAT\_GDT\_CSUM).
+   * - 0x20
+     - Indicates that the old ext3 32,000 subdirectory limit no longer applies
+       (RO\_COMPAT\_DIR\_NLINK). A directory's i\_links\_count will be set to 1
+       if it is incremented past 64,999.
+   * - 0x40
+     - Indicates that large inodes exist on this filesystem
+       (RO\_COMPAT\_EXTRA\_ISIZE).
+   * - 0x80
+     - This filesystem has a snapshot (RO\_COMPAT\_HAS\_SNAPSHOT).
+   * - 0x100
+     - `Quota <Quota>`__ (RO\_COMPAT\_QUOTA).
+   * - 0x200
+     - This filesystem supports “bigalloc”, which means that file extents are
+       tracked in units of clusters (of blocks) instead of blocks
+       (RO\_COMPAT\_BIGALLOC).
+   * - 0x400
+     - This filesystem supports metadata checksumming.
+       (RO\_COMPAT\_METADATA\_CSUM; implies RO\_COMPAT\_GDT\_CSUM, though
+       GDT\_CSUM must not be set)
+   * - 0x800
+     - Filesystem supports replicas. This feature is neither in the kernel nor
+       e2fsprogs. (RO\_COMPAT\_REPLICA)
+   * - 0x1000
+     - Read-only filesystem image; the kernel will not mount this image
+       read-write and most tools will refuse to write to the image.
+       (RO\_COMPAT\_READONLY)
+   * - 0x2000
+     - Filesystem tracks project quotas. (RO\_COMPAT\_PROJECT)
+
+.. _super_def_hash:
+
+The ``s_def_hash_version`` field is one of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Legacy.
+   * - 0x1
+     - Half MD4.
+   * - 0x2
+     - Tea.
+   * - 0x3
+     - Legacy, unsigned.
+   * - 0x4
+     - Half MD4, unsigned.
+   * - 0x5
+     - Tea, unsigned.
+
+.. _super_mountopts:
+
+The ``s_default_mount_opts`` field is any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Print debugging info upon (re)mount. (EXT4\_DEFM\_DEBUG)
+   * - 0x0002
+     - New files take the gid of the containing directory (instead of the fsgid
+       of the current process). (EXT4\_DEFM\_BSDGROUPS)
+   * - 0x0004
+     - Support userspace-provided extended attributes. (EXT4\_DEFM\_XATTR\_USER)
+   * - 0x0008
+     - Support POSIX access control lists (ACLs). (EXT4\_DEFM\_ACL)
+   * - 0x0010
+     - Do not support 32-bit UIDs. (EXT4\_DEFM\_UID16)
+   * - 0x0020
+     - All data and metadata are commited to the journal.
+       (EXT4\_DEFM\_JMODE\_DATA)
+   * - 0x0040
+     - All data are flushed to the disk before metadata are committed to the
+       journal. (EXT4\_DEFM\_JMODE\_ORDERED)
+   * - 0x0060
+     - Data ordering is not preserved; data may be written after the metadata
+       has been written. (EXT4\_DEFM\_JMODE\_WBACK)
+   * - 0x0100
+     - Disable write flushes. (EXT4\_DEFM\_NOBARRIER)
+   * - 0x0200
+     - Track which blocks in a filesystem are metadata and therefore should not
+       be used as data blocks. This option will be enabled by default on 3.18,
+       hopefully. (EXT4\_DEFM\_BLOCK\_VALIDITY)
+   * - 0x0400
+     - Enable DISCARD support, where the storage device is told about blocks
+       becoming unused. (EXT4\_DEFM\_DISCARD)
+   * - 0x0800
+     - Disable delayed allocation. (EXT4\_DEFM\_NODELALLOC)
+
+.. _super_flags:
+
+The ``s_flags`` field is any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0001
+     - Signed directory hash in use.
+   * - 0x0002
+     - Unsigned directory hash in use.
+   * - 0x0004
+     - To test development code.
+
+.. _super_encrypt:
+
+The ``s_encrypt_algos`` list can contain any of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0
+     - Invalid algorithm (ENCRYPTION\_MODE\_INVALID).
+   * - 1
+     - 256-bit AES in XTS mode (ENCRYPTION\_MODE\_AES\_256\_XTS).
+   * - 2
+     - 256-bit AES in GCM mode (ENCRYPTION\_MODE\_AES\_256\_GCM).
+   * - 3
+     - 256-bit AES in CBC mode (ENCRYPTION\_MODE\_AES\_256\_CBC).
+
+Total size of the superblock is 1024 bytes.
-- 
cgit v1.2.3


From 3c6ba09dd3f8081c2da2878ee275c0c2213d2d43 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:40:00 -0400
Subject: ext4: import group descriptors chapter from wiki page

Import the chapter about group descriptors from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ondisk/globals.rst  |   1 +
 .../filesystems/ext4/ondisk/group_descr.rst        | 170 +++++++++++++++++++++
 2 files changed, 171 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/group_descr.rst

diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/ondisk/globals.rst
index 4a33d0571bf2..c0dea6297e7f 100644
--- a/Documentation/filesystems/ext4/ondisk/globals.rst
+++ b/Documentation/filesystems/ext4/ondisk/globals.rst
@@ -7,3 +7,4 @@ The filesystem is sharded into a number of block groups, each of which
 have static metadata at fixed locations.
 
 .. include:: super.rst
+.. include:: group_descr.rst
diff --git a/Documentation/filesystems/ext4/ondisk/group_descr.rst b/Documentation/filesystems/ext4/ondisk/group_descr.rst
new file mode 100644
index 000000000000..759827e5d2cf
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/group_descr.rst
@@ -0,0 +1,170 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block Group Descriptors
+-----------------------
+
+Each block group on the filesystem has one of these descriptors
+associated with it. As noted in the Layout section above, the group
+descriptors (if present) are the second item in the block group. The
+standard configuration is for each block group to contain a full copy of
+the block group descriptor table unless the sparse\_super feature flag
+is set.
+
+Notice how the group descriptor records the location of both bitmaps and
+the inode table (i.e. they can float). This means that within a block
+group, the only data structures with fixed locations are the superblock
+and the group descriptor table. The flex\_bg mechanism uses this
+property to group several block groups into a flex group and lay out all
+of the groups' bitmaps and inode tables into one long run in the first
+group of the flex group.
+
+If the meta\_bg feature flag is set, then several block groups are
+grouped together into a meta group. Note that in the meta\_bg case,
+however, the first and last two block groups within the larger meta
+group contain only group descriptors for the groups inside the meta
+group.
+
+flex\_bg and meta\_bg do not appear to be mutually exclusive features.
+
+In ext2, ext3, and ext4 (when the 64bit feature is not enabled), the
+block group descriptor was only 32 bytes long and therefore ends at
+bg\_checksum. On an ext4 filesystem with the 64bit feature enabled, the
+block group descriptor expands to at least the 64 bytes described below;
+the size is stored in the superblock.
+
+If gdt\_csum is set and metadata\_csum is not set, the block group
+checksum is the crc16 of the FS UUID, the group number, and the group
+descriptor structure. If metadata\_csum is set, then the block group
+checksum is the lower 16 bits of the checksum of the FS UUID, the group
+number, and the group descriptor structure. Both block and inode bitmap
+checksums are calculated against the FS UUID, the group number, and the
+entire bitmap.
+
+The block group descriptor is laid out in ``struct ext4_group_desc``.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - bg\_block\_bitmap\_lo
+     - Lower 32-bits of location of block bitmap.
+   * - 0x4
+     - \_\_le32
+     - bg\_inode\_bitmap\_lo
+     - Lower 32-bits of location of inode bitmap.
+   * - 0x8
+     - \_\_le32
+     - bg\_inode\_table\_lo
+     - Lower 32-bits of location of inode table.
+   * - 0xC
+     - \_\_le16
+     - bg\_free\_blocks\_count\_lo
+     - Lower 16-bits of free block count.
+   * - 0xE
+     - \_\_le16
+     - bg\_free\_inodes\_count\_lo
+     - Lower 16-bits of free inode count.
+   * - 0x10
+     - \_\_le16
+     - bg\_used\_dirs\_count\_lo
+     - Lower 16-bits of directory count.
+   * - 0x12
+     - \_\_le16
+     - bg\_flags
+     - Block group flags. See the bgflags_ table below.
+   * - 0x14
+     - \_\_le32
+     - bg\_exclude\_bitmap\_lo
+     - Lower 32-bits of location of snapshot exclusion bitmap.
+   * - 0x18
+     - \_\_le16
+     - bg\_block\_bitmap\_csum\_lo
+     - Lower 16-bits of the block bitmap checksum.
+   * - 0x1A
+     - \_\_le16
+     - bg\_inode\_bitmap\_csum\_lo
+     - Lower 16-bits of the inode bitmap checksum.
+   * - 0x1C
+     - \_\_le16
+     - bg\_itable\_unused\_lo
+     - Lower 16-bits of unused inode count. If set, we needn't scan past the
+       ``(sb.s_inodes_per_group - gdt.bg_itable_unused)``\ th entry in the
+       inode table for this group.
+   * - 0x1E
+     - \_\_le16
+     - bg\_checksum
+     - Group descriptor checksum; crc16(sb\_uuid+group+desc) if the
+       RO\_COMPAT\_GDT\_CSUM feature is set, or crc32c(sb\_uuid+group\_desc) &
+       0xFFFF if the RO\_COMPAT\_METADATA\_CSUM feature is set.
+   * -
+     -
+     -
+     - These fields only exist if the 64bit feature is enabled and s_desc_size
+       > 32.
+   * - 0x20
+     - \_\_le32
+     - bg\_block\_bitmap\_hi
+     - Upper 32-bits of location of block bitmap.
+   * - 0x24
+     - \_\_le32
+     - bg\_inode\_bitmap\_hi
+     - Upper 32-bits of location of inodes bitmap.
+   * - 0x28
+     - \_\_le32
+     - bg\_inode\_table\_hi
+     - Upper 32-bits of location of inodes table.
+   * - 0x2C
+     - \_\_le16
+     - bg\_free\_blocks\_count\_hi
+     - Upper 16-bits of free block count.
+   * - 0x2E
+     - \_\_le16
+     - bg\_free\_inodes\_count\_hi
+     - Upper 16-bits of free inode count.
+   * - 0x30
+     - \_\_le16
+     - bg\_used\_dirs\_count\_hi
+     - Upper 16-bits of directory count.
+   * - 0x32
+     - \_\_le16
+     - bg\_itable\_unused\_hi
+     - Upper 16-bits of unused inode count.
+   * - 0x34
+     - \_\_le32
+     - bg\_exclude\_bitmap\_hi
+     - Upper 32-bits of location of snapshot exclusion bitmap.
+   * - 0x38
+     - \_\_le16
+     - bg\_block\_bitmap\_csum\_hi
+     - Upper 16-bits of the block bitmap checksum.
+   * - 0x3A
+     - \_\_le16
+     - bg\_inode\_bitmap\_csum\_hi
+     - Upper 16-bits of the inode bitmap checksum.
+   * - 0x3C
+     - \_\_u32
+     - bg\_reserved
+     - Padding to 64 bytes.
+
+.. _bgflags:
+
+Block group flags can be any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - inode table and bitmap are not initialized (EXT4\_BG\_INODE\_UNINIT).
+   * - 0x2
+     - block bitmap is not initialized (EXT4\_BG\_BLOCK\_UNINIT).
+   * - 0x4
+     - inode table is zeroed (EXT4\_BG\_INODE\_ZEROED).
-- 
cgit v1.2.3


From 33dfadc747a88243d616d8cb5c59ec3031dc60dd Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:41:00 -0400
Subject: ext4: import bitmaps chapter from wiki page

Import the chapter about bitmaps from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ondisk/bitmaps.rst | 28 +++++++++++++++++++++++
 Documentation/filesystems/ext4/ondisk/globals.rst |  1 +
 2 files changed, 29 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/bitmaps.rst

diff --git a/Documentation/filesystems/ext4/ondisk/bitmaps.rst b/Documentation/filesystems/ext4/ondisk/bitmaps.rst
new file mode 100644
index 000000000000..c7546dbc197a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/bitmaps.rst
@@ -0,0 +1,28 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Block and inode Bitmaps
+-----------------------
+
+The data block bitmap tracks the usage of data blocks within the block
+group.
+
+The inode bitmap records which entries in the inode table are in use.
+
+As with most bitmaps, one bit represents the usage status of one data
+block or inode table entry. This implies a block group size of 8 \*
+number\_of\_bytes\_in\_a\_logical\_block.
+
+NOTE: If ``BLOCK_UNINIT`` is set for a given block group, various parts
+of the kernel and e2fsprogs code pretends that the block bitmap contains
+zeros (i.e. all blocks in the group are free). However, it is not
+necessarily the case that no blocks are in use -- if ``meta_bg`` is set,
+the bitmaps and group descriptor live inside the group. Unfortunately,
+ext2fs\_test\_block\_bitmap2() will return '0' for those locations,
+which produces confusing debugfs output.
+
+Inode Table
+-----------
+Inode tables are statically allocated at mkfs time.  Each block group
+descriptor points to the start of the table, and the superblock records
+the number of inodes per group.  See the section on inodes for more
+information.
diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/ondisk/globals.rst
index c0dea6297e7f..5891ee137749 100644
--- a/Documentation/filesystems/ext4/ondisk/globals.rst
+++ b/Documentation/filesystems/ext4/ondisk/globals.rst
@@ -8,3 +8,4 @@ have static metadata at fixed locations.
 
 .. include:: super.rst
 .. include:: group_descr.rst
+.. include:: bitmaps.rst
-- 
cgit v1.2.3


From 18ba5a45ce1f590b3a2460f8f4ad52daf88290c4 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:42:00 -0400
Subject: ext4: import multi-mount protection chapter from wiki page

Import the chapter about multi-mount protection from the on-disk format
wiki page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ondisk/globals.rst |  1 +
 Documentation/filesystems/ext4/ondisk/mmp.rst     | 77 +++++++++++++++++++++++
 2 files changed, 78 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/mmp.rst

diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/ondisk/globals.rst
index 5891ee137749..fe6e107bf515 100644
--- a/Documentation/filesystems/ext4/ondisk/globals.rst
+++ b/Documentation/filesystems/ext4/ondisk/globals.rst
@@ -9,3 +9,4 @@ have static metadata at fixed locations.
 .. include:: super.rst
 .. include:: group_descr.rst
 .. include:: bitmaps.rst
+.. include:: mmp.rst
diff --git a/Documentation/filesystems/ext4/ondisk/mmp.rst b/Documentation/filesystems/ext4/ondisk/mmp.rst
new file mode 100644
index 000000000000..b7d7a3137f80
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/mmp.rst
@@ -0,0 +1,77 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Multiple Mount Protection
+-------------------------
+
+Multiple mount protection (MMP) is a feature that protects the
+filesystem against multiple hosts trying to use the filesystem
+simultaneously. When a filesystem is opened (for mounting, or fsck,
+etc.), the MMP code running on the node (call it node A) checks a
+sequence number. If the sequence number is EXT4\_MMP\_SEQ\_CLEAN, the
+open continues. If the sequence number is EXT4\_MMP\_SEQ\_FSCK, then
+fsck is (hopefully) running, and open fails immediately. Otherwise, the
+open code will wait for twice the specified MMP check interval and check
+the sequence number again. If the sequence number has changed, then the
+filesystem is active on another machine and the open fails. If the MMP
+code passes all of those checks, a new MMP sequence number is generated
+and written to the MMP block, and the mount proceeds.
+
+While the filesystem is live, the kernel sets up a timer to re-check the
+MMP block at the specified MMP check interval. To perform the re-check,
+the MMP sequence number is re-read; if it does not match the in-memory
+MMP sequence number, then another node (node B) has mounted the
+filesystem, and node A remounts the filesystem read-only. If the
+sequence numbers match, the sequence number is incremented both in
+memory and on disk, and the re-check is complete.
+
+The hostname and device filename are written into the MMP block whenever
+an open operation succeeds. The MMP code does not use these values; they
+are provided purely for informational purposes.
+
+The checksum is calculated against the FS UUID and the MMP structure.
+The MMP structure (``struct mmp_struct``) is as follows:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - mmp\_magic
+     - Magic number for MMP, 0x004D4D50 (“MMP”).
+   * - 0x4
+     - \_\_le32
+     - mmp\_seq
+     - Sequence number, updated periodically.
+   * - 0x8
+     - \_\_le64
+     - mmp\_time
+     - Time that the MMP block was last updated.
+   * - 0x10
+     - char[64]
+     - mmp\_nodename
+     - Hostname of the node that opened the filesystem.
+   * - 0x50
+     - char[32]
+     - mmp\_bdevname
+     - Block device name of the filesystem.
+   * - 0x70
+     - \_\_le16
+     - mmp\_check\_interval
+     - The MMP re-check interval, in seconds.
+   * - 0x72
+     - \_\_le16
+     - mmp\_pad1
+     - Zero.
+   * - 0x74
+     - \_\_le32[226]
+     - mmp\_pad2
+     - Zero.
+   * - 0x3FC
+     - \_\_le32
+     - mmp\_checksum
+     - Checksum of the MMP block.
-- 
cgit v1.2.3


From 423ddc580b13633429ed17c1c3a3059f402a3660 Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Wed, 18 Jul 2018 14:00:30 +0800
Subject: pinctrl: berlin: add the as370 SoC pinctrl driver

Add the pin-controller driver for Synaptics AS370 SoC, with definition
of its groups and functions. This uses the core Berlin pinctrl driver.

Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/berlin/Kconfig         |   5 +
 drivers/pinctrl/berlin/Makefile        |   1 +
 drivers/pinctrl/berlin/pinctrl-as370.c | 368 +++++++++++++++++++++++++++++++++
 3 files changed, 374 insertions(+)
 create mode 100644 drivers/pinctrl/berlin/pinctrl-as370.c

diff --git a/drivers/pinctrl/berlin/Kconfig b/drivers/pinctrl/berlin/Kconfig
index 8fe6ad7795dc..0dd60278e973 100644
--- a/drivers/pinctrl/berlin/Kconfig
+++ b/drivers/pinctrl/berlin/Kconfig
@@ -5,6 +5,11 @@ config PINCTRL_BERLIN
 	select PINMUX
 	select REGMAP_MMIO
 
+config PINCTRL_AS370
+	bool "Synaptics as370 pin controller driver"
+	depends on OF
+	select PINCTRL_BERLIN
+
 config PINCTRL_BERLIN_BG2
 	def_bool MACH_BERLIN_BG2
 	depends on OF
diff --git a/drivers/pinctrl/berlin/Makefile b/drivers/pinctrl/berlin/Makefile
index 6f641ce2c830..00c53ca3676d 100644
--- a/drivers/pinctrl/berlin/Makefile
+++ b/drivers/pinctrl/berlin/Makefile
@@ -3,3 +3,4 @@ obj-$(CONFIG_PINCTRL_BERLIN_BG2)	+= berlin-bg2.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2CD)	+= berlin-bg2cd.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG2Q)	+= berlin-bg2q.o
 obj-$(CONFIG_PINCTRL_BERLIN_BG4CT)	+= berlin-bg4ct.o
+obj-$(CONFIG_PINCTRL_AS370)		+= pinctrl-as370.o
diff --git a/drivers/pinctrl/berlin/pinctrl-as370.c b/drivers/pinctrl/berlin/pinctrl-as370.c
new file mode 100644
index 000000000000..d2bb811fc5fa
--- /dev/null
+++ b/drivers/pinctrl/berlin/pinctrl-as370.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Synaptics AS370 pinctrl driver
+ *
+ * Copyright (C) 2018 Synaptics Incorporated
+ *
+ * Author: Jisheng Zhang <jszhang@kernel.org>
+ */
+
+#include <linux/init.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+#include "berlin.h"
+
+static const struct berlin_desc_group as370_soc_pinctrl_groups[] = {
+	BERLIN_PINCTRL_GROUP("I2S1_BCLKIO", 0x0, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO0 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG0 */
+	BERLIN_PINCTRL_GROUP("I2S1_LRCKIO", 0x0, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO1 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* LRCKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG1 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO0", 0x0, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* 1P8V RSTB*/
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO0 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO2 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG2 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO1", 0x0, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* 3P3V RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO1 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO3 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG3 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO2", 0x0, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* CORE RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm4"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio"), /* GPIO4 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG4 */
+	BERLIN_PINCTRL_GROUP("I2S1_DO3", 0x0, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO5 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* DO3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm5"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spififib"), /* SPDIFIB */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG5 */
+	BERLIN_PINCTRL_GROUP("I2S1_MCLK", 0x0, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO6 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s1"), /* MCLK */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG6 */
+	BERLIN_PINCTRL_GROUP("I2S2_BCLKIO", 0x0, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO7 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG7 */
+	BERLIN_PINCTRL_GROUP("I2S2_LRCKIO", 0x0, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO8 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* LRCKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG8 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI0", 0x0, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO9 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI0 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm2"),
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG9 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI1", 0x4, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO10 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI1 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm3"),
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG10 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI2", 0x4, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO11 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdific"), /* SPDIFIC */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG11 */
+	BERLIN_PINCTRL_GROUP("I2S2_DI3", 0x4, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO12 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s2"), /* DI3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifia"), /* SPDIFIA */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG12 */
+	BERLIN_PINCTRL_GROUP("PDM_CLKO", 0x4, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO13 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* CLKO */
+			BERLIN_PINCTRL_FUNCTION(0x2, "i2s2"), /* MCLK */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG13 */
+	BERLIN_PINCTRL_GROUP("PDM_DI0", 0x4, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO14 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI0 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG14 */
+	BERLIN_PINCTRL_GROUP("PDM_DI1", 0x4, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO15 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI1 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG15 */
+	BERLIN_PINCTRL_GROUP("PDM_DI2", 0x4, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO16 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm4"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifid"), /* SPDIFID */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG16 */
+	BERLIN_PINCTRL_GROUP("PDM_DI3", 0x4, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO17 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pdm"), /* DI3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm5"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "spdifi"), /* SPDIFI */
+			BERLIN_PINCTRL_FUNCTION(0x4, "spdifo"), /* SPDIFO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG17 */
+	BERLIN_PINCTRL_GROUP("NAND_IO0", 0x4, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO0 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA0 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie0")), /* MDIO */
+	BERLIN_PINCTRL_GROUP("NAND_IO1", 0x4, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO1 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA1 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie0")), /* MDC */
+	BERLIN_PINCTRL_GROUP("NAND_IO2", 0x8, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO2 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA2 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie1")), /* MDIO */
+	BERLIN_PINCTRL_GROUP("NAND_IO3", 0x8, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO3 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* DATA3 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pcie1")), /* MDC */
+	BERLIN_PINCTRL_GROUP("NAND_IO4", 0x8, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO4 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA4 */
+	BERLIN_PINCTRL_GROUP("NAND_IO5", 0x8, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO5 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA5 */
+	BERLIN_PINCTRL_GROUP("NAND_IO6", 0x8, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO6 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA6 */
+	BERLIN_PINCTRL_GROUP("NAND_IO7", 0x8, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* IO7 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc")), /* DATA7 */
+	BERLIN_PINCTRL_GROUP("NAND_ALE", 0x8, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* ALE */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO18 */
+	BERLIN_PINCTRL_GROUP("NAND_CLE", 0x8, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* CLE */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO19 */
+	BERLIN_PINCTRL_GROUP("NAND_WEn", 0x8, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* WEn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO20 */
+	BERLIN_PINCTRL_GROUP("NAND_REn", 0x8, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* REn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO21 */
+	BERLIN_PINCTRL_GROUP("NAND_WPn", 0xc, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* WPn */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* CLK */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO22 */
+	BERLIN_PINCTRL_GROUP("NAND_CEn", 0xc, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* CEn */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* RSTn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO23 */
+	BERLIN_PINCTRL_GROUP("NAND_RDY", 0xc, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "nand"), /* RDY */
+			BERLIN_PINCTRL_FUNCTION(0x1, "emmc"), /* CMD */
+			BERLIN_PINCTRL_FUNCTION(0x3, "gpio")), /* GPIO24 */
+	BERLIN_PINCTRL_GROUP("SPI1_SS0n", 0xc, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS0n */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio")), /* GPIO25 */
+	BERLIN_PINCTRL_GROUP("SPI1_SS1n", 0xc, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SS1n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio"), /* GPIO26 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm2")),
+	BERLIN_PINCTRL_GROUP("SPI1_SS2n", 0xc, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "uart0"), /* RXD */
+			BERLIN_PINCTRL_FUNCTION(0x1, "spi1"), /* SS2n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio"), /* GPIO27 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm3")),
+	BERLIN_PINCTRL_GROUP("SPI1_SS3n", 0xc, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "uart0"), /* TXD */
+			BERLIN_PINCTRL_FUNCTION(0x1, "spi1"), /* SS3n */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO28 */
+	BERLIN_PINCTRL_GROUP("SPI1_SCLK", 0xc, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SCLK */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO29 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm4")),
+	BERLIN_PINCTRL_GROUP("SPI1_SDO", 0xc, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SDO */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO30 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm5")),
+	BERLIN_PINCTRL_GROUP("SPI1_SDI", 0xc, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "spi1"), /* SDI */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio")), /* GPIO31 */
+	BERLIN_PINCTRL_GROUP("USB0_DRV_VBUS", 0x10, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "usb0"), /* VBUS */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO32 */
+			BERLIN_PINCTRL_FUNCTION(0x3, "refclko")), /* 25M */
+	BERLIN_PINCTRL_GROUP("TW1_SCL", 0x10, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO33 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw1")), /* SCL */
+	BERLIN_PINCTRL_GROUP("TW1_SDA", 0x10, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO34 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw1")), /* SDA */
+	BERLIN_PINCTRL_GROUP("TW0_SCL", 0x10, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO35 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw0")), /* SCL */
+	BERLIN_PINCTRL_GROUP("TW0_SDA", 0x10, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO36 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "tw0")), /* SDA */
+	BERLIN_PINCTRL_GROUP("TMS", 0x10, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TMS */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO37 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm0")),
+	BERLIN_PINCTRL_GROUP("TDI", 0x10, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TDI */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO38 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm1")),
+	BERLIN_PINCTRL_GROUP("TDO", 0x10, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "jtag"), /* TDO */
+			BERLIN_PINCTRL_FUNCTION(0x1, "gpio"), /* GPIO39 */
+			BERLIN_PINCTRL_FUNCTION(0x4, "pwm0")),
+	BERLIN_PINCTRL_GROUP("PWM6", 0x10, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO40 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm6")),
+	BERLIN_PINCTRL_GROUP("PWM7", 0x10, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO41 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm7")),
+	BERLIN_PINCTRL_GROUP("PWM0", 0x14, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "por"), /* VDDCPUSOC RSTB */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm0"),
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO42 */
+	BERLIN_PINCTRL_GROUP("PWM1", 0x14, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO43 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm1")),
+	BERLIN_PINCTRL_GROUP("PWM2", 0x14, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO44 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm2")),
+	BERLIN_PINCTRL_GROUP("PWM3", 0x14, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO45 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm3")),
+	BERLIN_PINCTRL_GROUP("PWM4", 0x14, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO46 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm4")),
+	BERLIN_PINCTRL_GROUP("PWM5", 0x14, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO47 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "pwm5")),
+	BERLIN_PINCTRL_GROUP("URT1_RTSn", 0x14, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO48 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* RTSn */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm6"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "tw1a"), /* SCL */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG0 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG18 */
+	BERLIN_PINCTRL_GROUP("URT1_CTSn", 0x14, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO49 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* CTSn */
+			BERLIN_PINCTRL_FUNCTION(0x2, "pwm7"),
+			BERLIN_PINCTRL_FUNCTION(0x3, "tw1a"), /* SDA */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG1 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG19 */
+	BERLIN_PINCTRL_GROUP("URT1_RXD", 0x14, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO50 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* RXD */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG2 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG20 */
+	BERLIN_PINCTRL_GROUP("URT1_TXD", 0x14, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO51 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "uart1"), /* TXD */
+			BERLIN_PINCTRL_FUNCTION(0x4, "aio"), /* DBG3 */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG21 */
+	BERLIN_PINCTRL_GROUP("I2S3_DI", 0x18, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO52 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* DI */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG22 */
+	BERLIN_PINCTRL_GROUP("I2S3_DO", 0x18, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO53 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* DO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "phy")), /* DBG23 */
+	BERLIN_PINCTRL_GROUP("I2S3_BCLKIO", 0x18, 0x3, 0x06,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO54 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3"), /* BCLKIO */
+			BERLIN_PINCTRL_FUNCTION(0x5, "clk")), /* DBG */
+	BERLIN_PINCTRL_GROUP("I2S3_LRCKIO", 0x18, 0x3, 0x09,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO55 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "i2s3")), /* LRCKIO */
+	BERLIN_PINCTRL_GROUP("SD0_DAT0", 0x18, 0x3, 0x0c,
+			BERLIN_PINCTRL_FUNCTION(0x0, "cpupll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT0 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO56 */
+	BERLIN_PINCTRL_GROUP("SD0_DAT1", 0x18, 0x3, 0x0f,
+			BERLIN_PINCTRL_FUNCTION(0x0, "syspll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT1 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO57 */
+	BERLIN_PINCTRL_GROUP("SD0_CLK", 0x18, 0x3, 0x12,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO58 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0")), /* CLK */
+	BERLIN_PINCTRL_GROUP("SD0_DAT2", 0x18, 0x3, 0x15,
+			BERLIN_PINCTRL_FUNCTION(0x0, "mempll"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT2 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO59 */
+	BERLIN_PINCTRL_GROUP("SD0_DAT3", 0x18, 0x3, 0x18,
+			BERLIN_PINCTRL_FUNCTION(0x0, "apll0"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* DAT3 */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO60 */
+	BERLIN_PINCTRL_GROUP("SD0_CMD", 0x18, 0x3, 0x1b,
+			BERLIN_PINCTRL_FUNCTION(0x0, "apll1"), /* OUT */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* CMD */
+			BERLIN_PINCTRL_FUNCTION(0x2, "gpio")), /* GPIO61 */
+	BERLIN_PINCTRL_GROUP("SD0_CDn", 0x1c, 0x3, 0x00,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO62 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* CDn */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm2")),
+	BERLIN_PINCTRL_GROUP("SD0_WP", 0x1c, 0x3, 0x03,
+			BERLIN_PINCTRL_FUNCTION(0x0, "gpio"), /* GPIO63 */
+			BERLIN_PINCTRL_FUNCTION(0x1, "sd0"), /* WP */
+			BERLIN_PINCTRL_FUNCTION(0x3, "pwm3")),
+};
+
+static const struct berlin_pinctrl_desc as370_soc_pinctrl_data = {
+	.groups = as370_soc_pinctrl_groups,
+	.ngroups = ARRAY_SIZE(as370_soc_pinctrl_groups),
+};
+
+static const struct of_device_id as370_pinctrl_match[] = {
+	{
+		.compatible = "syna,as370-soc-pinctrl",
+		.data = &as370_soc_pinctrl_data,
+	},
+	{}
+};
+
+static int as370_pinctrl_probe(struct platform_device *pdev)
+{
+	const struct of_device_id *match =
+		of_match_device(as370_pinctrl_match, &pdev->dev);
+	struct regmap_config *rmconfig;
+	struct regmap *regmap;
+	struct resource *res;
+	void __iomem *base;
+
+	rmconfig = devm_kzalloc(&pdev->dev, sizeof(*rmconfig), GFP_KERNEL);
+	if (!rmconfig)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	rmconfig->reg_bits = 32,
+	rmconfig->val_bits = 32,
+	rmconfig->reg_stride = 4,
+	rmconfig->max_register = resource_size(res);
+
+	regmap = devm_regmap_init_mmio(&pdev->dev, base, rmconfig);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	return berlin_pinctrl_probe_regmap(pdev, match->data, regmap);
+}
+
+static struct platform_driver as370_pinctrl_driver = {
+	.probe	= as370_pinctrl_probe,
+	.driver	= {
+		.name = "as370-pinctrl",
+		.of_match_table = as370_pinctrl_match,
+	},
+};
+builtin_platform_driver(as370_pinctrl_driver);
-- 
cgit v1.2.3


From 567d118a9843a20b72ecebec2719337bc2556229 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:43:00 -0400
Subject: ext4: import journal chapter from wiki page

Import the chapter about the journal from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ondisk/globals.rst |   1 +
 Documentation/filesystems/ext4/ondisk/journal.rst | 611 ++++++++++++++++++++++
 2 files changed, 612 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/journal.rst

diff --git a/Documentation/filesystems/ext4/ondisk/globals.rst b/Documentation/filesystems/ext4/ondisk/globals.rst
index fe6e107bf515..368bf7662b96 100644
--- a/Documentation/filesystems/ext4/ondisk/globals.rst
+++ b/Documentation/filesystems/ext4/ondisk/globals.rst
@@ -10,3 +10,4 @@ have static metadata at fixed locations.
 .. include:: group_descr.rst
 .. include:: bitmaps.rst
 .. include:: mmp.rst
+.. include:: journal.rst
diff --git a/Documentation/filesystems/ext4/ondisk/journal.rst b/Documentation/filesystems/ext4/ondisk/journal.rst
new file mode 100644
index 000000000000..e7031af86876
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/journal.rst
@@ -0,0 +1,611 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Journal (jbd2)
+--------------
+
+Introduced in ext3, the ext4 filesystem employs a journal to protect the
+filesystem against corruption in the case of a system crash. A small
+continuous region of disk (default 128MiB) is reserved inside the
+filesystem as a place to land “important” data writes on-disk as quickly
+as possible. Once the important data transaction is fully written to the
+disk and flushed from the disk write cache, a record of the data being
+committed is also written to the journal. At some later point in time,
+the journal code writes the transactions to their final locations on
+disk (this could involve a lot of seeking or a lot of small
+read-write-erases) before erasing the commit record. Should the system
+crash during the second slow write, the journal can be replayed all the
+way to the latest commit record, guaranteeing the atomicity of whatever
+gets written through the journal to the disk. The effect of this is to
+guarantee that the filesystem does not become stuck midway through a
+metadata update.
+
+For performance reasons, ext4 by default only writes filesystem metadata
+through the journal. This means that file data blocks are /not/
+guaranteed to be in any consistent state after a crash. If this default
+guarantee level (``data=ordered``) is not satisfactory, there is a mount
+option to control journal behavior. If ``data=journal``, all data and
+metadata are written to disk through the journal. This is slower but
+safest. If ``data=writeback``, dirty data blocks are not flushed to the
+disk before the metadata are written to disk through the journal.
+
+The journal inode is typically inode 8. The first 68 bytes of the
+journal inode are replicated in the ext4 superblock. The journal itself
+is normal (but hidden) file within the filesystem. The file usually
+consumes an entire block group, though mke2fs tries to put it in the
+middle of the disk.
+
+All fields in jbd2 are written to disk in big-endian order. This is the
+opposite of ext4.
+
+NOTE: Both ext4 and ocfs2 use jbd2.
+
+The maximum size of a journal embedded in an ext4 filesystem is 2^32
+blocks. jbd2 itself does not seem to care.
+
+Layout
+~~~~~~
+
+Generally speaking, the journal has this format:
+
+.. list-table::
+   :widths: 1 1 78
+   :header-rows: 1
+
+   * - Superblock
+     - descriptor\_block (data\_blocks or revocation\_block) [more data or
+       revocations] commmit\_block
+     - [more transactions...]
+   * - 
+     - One transaction
+     -
+
+Notice that a transaction begins with either a descriptor and some data,
+or a block revocation list. A finished transaction always ends with a
+commit. If there is no commit record (or the checksums don't match), the
+transaction will be discarded during replay.
+
+External Journal
+~~~~~~~~~~~~~~~~
+
+Optionally, an ext4 filesystem can be created with an external journal
+device (as opposed to an internal journal, which uses a reserved inode).
+In this case, on the filesystem device, ``s_journal_inum`` should be
+zero and ``s_journal_uuid`` should be set. On the journal device there
+will be an ext4 super block in the usual place, with a matching UUID.
+The journal superblock will be in the next full block after the
+superblock.
+
+.. list-table::
+   :widths: 1 1 1 1 76
+   :header-rows: 1
+
+   * - 1024 bytes of padding
+     - ext4 Superblock
+     - Journal Superblock
+     - descriptor\_block (data\_blocks or revocation\_block) [more data or
+       revocations] commmit\_block
+     - [more transactions...]
+   * - 
+     -
+     -
+     - One transaction
+     -
+
+Block Header
+~~~~~~~~~~~~
+
+Every block in the journal starts with a common 12-byte header
+``struct journal_header_s``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_be32
+     - h\_magic
+     - jbd2 magic number, 0xC03B3998.
+   * - 0x4
+     - \_\_be32
+     - h\_blocktype
+     - Description of what this block contains. See the jbd2_blocktype_ table
+       below.
+   * - 0x8
+     - \_\_be32
+     - h\_sequence
+     - The transaction ID that goes with this block.
+
+.. _jbd2_blocktype:
+
+The journal block type can be any one of:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - Descriptor. This block precedes a series of data blocks that were
+       written through the journal during a transaction.
+   * - 2
+     - Block commit record. This block signifies the completion of a
+       transaction.
+   * - 3
+     - Journal superblock, v1.
+   * - 4
+     - Journal superblock, v2.
+   * - 5
+     - Block revocation records. This speeds up recovery by enabling the
+       journal to skip writing blocks that were subsequently rewritten.
+
+Super Block
+~~~~~~~~~~~
+
+The super block for the journal is much simpler as compared to ext4's.
+The key data kept within are size of the journal, and where to find the
+start of the log of transactions.
+
+The journal superblock is recorded as ``struct journal_superblock_s``,
+which is 1024 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * -
+     -
+     -
+     - Static information describing the journal.
+   * - 0x0
+     - journal\_header\_t (12 bytes)
+     - s\_header
+     - Common header identifying this as a superblock.
+   * - 0xC
+     - \_\_be32
+     - s\_blocksize
+     - Journal device block size.
+   * - 0x10
+     - \_\_be32
+     - s\_maxlen
+     - Total number of blocks in this journal.
+   * - 0x14
+     - \_\_be32
+     - s\_first
+     - First block of log information.
+   * -
+     -
+     -
+     - Dynamic information describing the current state of the log.
+   * - 0x18
+     - \_\_be32
+     - s\_sequence
+     - First commit ID expected in log.
+   * - 0x1C
+     - \_\_be32
+     - s\_start
+     - Block number of the start of log. Contrary to the comments, this field
+       being zero does not imply that the journal is clean!
+   * - 0x20
+     - \_\_be32
+     - s\_errno
+     - Error value, as set by jbd2\_journal\_abort().
+   * -
+     -
+     -
+     - The remaining fields are only valid in a v2 superblock.
+   * - 0x24
+     - \_\_be32
+     - s\_feature\_compat;
+     - Compatible feature set. See the table jbd2_compat_ below.
+   * - 0x28
+     - \_\_be32
+     - s\_feature\_incompat
+     - Incompatible feature set. See the table jbd2_incompat_ below.
+   * - 0x2C
+     - \_\_be32
+     - s\_feature\_ro\_compat
+     - Read-only compatible feature set. There aren't any of these currently.
+   * - 0x30
+     - \_\_u8
+     - s\_uuid[16]
+     - 128-bit uuid for journal. This is compared against the copy in the ext4
+       super block at mount time.
+   * - 0x40
+     - \_\_be32
+     - s\_nr\_users
+     - Number of file systems sharing this journal.
+   * - 0x44
+     - \_\_be32
+     - s\_dynsuper
+     - Location of dynamic super block copy. (Not used?)
+   * - 0x48
+     - \_\_be32
+     - s\_max\_transaction
+     - Limit of journal blocks per transaction. (Not used?)
+   * - 0x4C
+     - \_\_be32
+     - s\_max\_trans\_data
+     - Limit of data blocks per transaction. (Not used?)
+   * - 0x50
+     - \_\_u8
+     - s\_checksum\_type
+     - Checksum algorithm used for the journal.  See jbd2_checksum_type_ for
+       more info.
+   * - 0x51
+     - \_\_u8[3]
+     - s\_padding2
+     -
+   * - 0x54
+     - \_\_u32
+     - s\_padding[42]
+     -
+   * - 0xFC
+     - \_\_be32
+     - s\_checksum
+     - Checksum of the entire superblock, with this field set to zero.
+   * - 0x100
+     - \_\_u8
+     - s\_users[16\*48]
+     - ids of all file systems sharing the log. e2fsprogs/Linux don't allow
+       shared external journals, but I imagine Lustre (or ocfs2?), which use
+       the jbd2 code, might.
+
+.. _jbd2_compat:
+
+The journal compat features are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Journal maintains checksums on the data blocks.
+       (JBD2\_FEATURE\_COMPAT\_CHECKSUM)
+
+.. _jbd2_incompat:
+
+The journal incompat features are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - Journal has block revocation records. (JBD2\_FEATURE\_INCOMPAT\_REVOKE)
+   * - 0x2
+     - Journal can deal with 64-bit block numbers.
+       (JBD2\_FEATURE\_INCOMPAT\_64BIT)
+   * - 0x4
+     - Journal commits asynchronously. (JBD2\_FEATURE\_INCOMPAT\_ASYNC\_COMMIT)
+   * - 0x8
+     - This journal uses v2 of the checksum on-disk format. Each journal
+       metadata block gets its own checksum, and the block tags in the
+       descriptor table contain checksums for each of the data blocks in the
+       journal. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2)
+   * - 0x10
+     - This journal uses v3 of the checksum on-disk format. This is the same as
+       v2, but the journal block tag size is fixed regardless of the size of
+       block numbers. (JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3)
+
+.. _jbd2_checksum_type:
+
+Journal checksum type codes are one of the following.  crc32 or crc32c are the
+most likely choices.
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 1
+     - CRC32
+   * - 2
+     - MD5
+   * - 3
+     - SHA1
+   * - 4
+     - CRC32C
+
+Descriptor Block
+~~~~~~~~~~~~~~~~
+
+The descriptor block contains an array of journal block tags that
+describe the final locations of the data blocks that follow in the
+journal. Descriptor blocks are open-coded instead of being completely
+described by a data structure, but here is the block structure anyway.
+Descriptor blocks consume at least 36 bytes, but use a full block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - journal\_header\_t
+     - (open coded)
+     - Common block header.
+   * - 0xC
+     - struct journal\_block\_tag\_s
+     - open coded array[]
+     - Enough tags either to fill up the block or to describe all the data
+       blocks that follow this descriptor block.
+
+Journal block tags have any of the following formats, depending on which
+journal feature and block tag flags are set.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is set, the journal block tag is
+defined as ``struct journal_block_tag3_s``, which looks like the
+following. The size is 16 or 32 bytes.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_blocknr
+     - Lower 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * - 0x4
+     - \_\_be32
+     - t\_flags
+     - Flags that go with the descriptor. See the table jbd2_tag_flags_ for
+       more info.
+   * - 0x8
+     - \_\_be32
+     - t\_blocknr\_high
+     - Upper 32-bits of the location of where the corresponding data block
+       should end up on disk. This is zero if JBD2\_FEATURE\_INCOMPAT\_64BIT is
+       not enabled.
+   * - 0xC
+     - \_\_be32
+     - t\_checksum
+     - Checksum of the journal UUID, the sequence number, and the data block.
+   * -
+     -
+     -
+     - This field appears to be open coded. It always comes at the end of the
+       tag, after t_checksum. This field is not present if the "same UUID" flag
+       is set.
+   * - 0x8 or 0xC
+     - char
+     - uuid[16]
+     - A UUID to go with this tag. This field appears to be copied from the
+       ``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that
+       field.
+
+.. _jbd2_tag_flags:
+
+The journal tag flags are any combination of the following:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - On-disk block is escaped. The first four bytes of the data block just
+       happened to match the jbd2 magic number.
+   * - 0x2
+     - This block has the same UUID as previous, therefore the UUID field is
+       omitted.
+   * - 0x4
+     - The data block was deleted by the transaction. (Not used?)
+   * - 0x8
+     - This is the last tag in this descriptor block.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 is NOT set, the journal block tag
+is defined as ``struct journal_block_tag_s``, which looks like the
+following. The size is 8, 12, 24, or 28 bytes:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_blocknr
+     - Lower 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * - 0x4
+     - \_\_be16
+     - t\_checksum
+     - Checksum of the journal UUID, the sequence number, and the data block.
+       Note that only the lower 16 bits are stored.
+   * - 0x6
+     - \_\_be16
+     - t\_flags
+     - Flags that go with the descriptor. See the table jbd2_tag_flags_ for
+       more info.
+   * -
+     -
+     -
+     - This next field is only present if the super block indicates support for
+       64-bit block numbers.
+   * - 0x8
+     - \_\_be32
+     - t\_blocknr\_high
+     - Upper 32-bits of the location of where the corresponding data block
+       should end up on disk.
+   * -
+     -
+     -
+     - This field appears to be open coded. It always comes at the end of the
+       tag, after t_flags or t_blocknr_high. This field is not present if the
+       "same UUID" flag is set.
+   * - 0x8 or 0xC
+     - char
+     - uuid[16]
+     - A UUID to go with this tag. This field appears to be copied from the
+       ``j_uuid`` field in ``struct journal_s``, but only tune2fs touches that
+       field.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
+JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the block is a
+``struct jbd2_journal_block_tail``, which looks like this:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - \_\_be32
+     - t\_checksum
+     - Checksum of the journal UUID + the descriptor block, with this field set
+       to zero.
+
+Data Block
+~~~~~~~~~~
+
+In general, the data blocks being written to disk through the journal
+are written verbatim into the journal file after the descriptor block.
+However, if the first four bytes of the block match the jbd2 magic
+number then those four bytes are replaced with zeroes and the “escaped”
+flag is set in the descriptor block tag.
+
+Revocation Block
+~~~~~~~~~~~~~~~~
+
+A revocation block is used to prevent replay of a block in an earlier
+transaction. This is used to mark blocks that were journalled at one
+time but are no longer journalled. Typically this happens if a metadata
+block is freed and re-allocated as a file data block; in this case, a
+journal replay after the file block was written to disk will cause
+corruption.
+
+**NOTE**: This mechanism is NOT used to express “this journal block is
+superseded by this other journal block”, as the author (djwong)
+mistakenly thought. Any block being added to a transaction will cause
+the removal of all existing revocation records for that block.
+
+Revocation blocks are described in
+``struct jbd2_journal_revoke_header_s``, are at least 16 bytes in
+length, but use a full block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - journal\_header\_t
+     - r\_header
+     - Common block header.
+   * - 0xC
+     - \_\_be32
+     - r\_count
+     - Number of bytes used in this block.
+   * - 0x10
+     - \_\_be32 or \_\_be64
+     - blocks[0]
+     - Blocks to revoke.
+
+After r\_count is a linear array of block numbers that are effectively
+revoked by this transaction. The size of each block number is 8 bytes if
+the superblock advertises 64-bit block number support, or 4 bytes
+otherwise.
+
+If JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or
+JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3 are set, the end of the revocation
+block is a ``struct jbd2_journal_revoke_tail``, which has this format:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_be32
+     - r\_checksum
+     - Checksum of the journal UUID + revocation block
+
+Commit Block
+~~~~~~~~~~~~
+
+The commit block is a sentry that indicates that a transaction has been
+completely written to the journal. Once this commit block reaches the
+journal, the data stored with this transaction can be written to their
+final locations on disk.
+
+The commit block is described by ``struct commit_header``, which is 32
+bytes long (but uses a full block):
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Descriptor
+   * - 0x0
+     - journal\_header\_s
+     - (open coded)
+     - Common block header.
+   * - 0xC
+     - unsigned char
+     - h\_chksum\_type
+     - The type of checksum to use to verify the integrity of the data blocks
+       in the transaction. See jbd2_checksum_type_ for more info.
+   * - 0xD
+     - unsigned char
+     - h\_chksum\_size
+     - The number of bytes used by the checksum. Most likely 4.
+   * - 0xE
+     - unsigned char
+     - h\_padding[2]
+     -
+   * - 0x10
+     - \_\_be32
+     - h\_chksum[JBD2\_CHECKSUM\_BYTES]
+     - 32 bytes of space to store checksums. If
+       JBD2\_FEATURE\_INCOMPAT\_CSUM\_V2 or JBD2\_FEATURE\_INCOMPAT\_CSUM\_V3
+       are set, the first ``__be32`` is the checksum of the journal UUID and
+       the entire commit block, with this field zeroed. If
+       JBD2\_FEATURE\_COMPAT\_CHECKSUM is set, the first ``__be32`` is the
+       crc32 of all the blocks already written to the transaction.
+   * - 0x30
+     - \_\_be64
+     - h\_commit\_sec
+     - The time that the transaction was committed, in seconds since the epoch.
+   * - 0x38
+     - \_\_be32
+     - h\_commit\_nsec
+     - Nanoseconds component of the above timestamp.
+
-- 
cgit v1.2.3


From 46180558f17ec76b854b419c9322d6c0b5fec840 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:44:00 -0400
Subject: ext4: import inodes chapter from wiki page

Import the chapter about inodes from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ondisk/dynamic.rst |   9 +
 Documentation/filesystems/ext4/ondisk/index.rst   |   1 +
 Documentation/filesystems/ext4/ondisk/inodes.rst  | 575 ++++++++++++++++++++++
 3 files changed, 585 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/dynamic.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/inodes.rst

diff --git a/Documentation/filesystems/ext4/ondisk/dynamic.rst b/Documentation/filesystems/ext4/ondisk/dynamic.rst
new file mode 100644
index 000000000000..7c5f5019b9d6
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/dynamic.rst
@@ -0,0 +1,9 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Dynamic Structures
+==================
+
+Dynamic metadata are created on the fly when files and blocks are
+allocated to files.
+
+.. include:: inodes.rst
diff --git a/Documentation/filesystems/ext4/ondisk/index.rst b/Documentation/filesystems/ext4/ondisk/index.rst
index dbb259f83976..f7d082c3a435 100644
--- a/Documentation/filesystems/ext4/ondisk/index.rst
+++ b/Documentation/filesystems/ext4/ondisk/index.rst
@@ -6,3 +6,4 @@ Data Structures and Algorithms
 .. include:: about.rst
 .. include:: overview.rst
 .. include:: globals.rst
+.. include:: dynamic.rst
diff --git a/Documentation/filesystems/ext4/ondisk/inodes.rst b/Documentation/filesystems/ext4/ondisk/inodes.rst
new file mode 100644
index 000000000000..655ce898f3f5
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/inodes.rst
@@ -0,0 +1,575 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Index Nodes
+-----------
+
+In a regular UNIX filesystem, the inode stores all the metadata
+pertaining to the file (time stamps, block maps, extended attributes,
+etc), not the directory entry. To find the information associated with a
+file, one must traverse the directory files to find the directory entry
+associated with a file, then load the inode to find the metadata for
+that file. ext4 appears to cheat (for performance reasons) a little bit
+by storing a copy of the file type (normally stored in the inode) in the
+directory entry. (Compare all this to FAT, which stores all the file
+information directly in the directory entry, but does not support hard
+links and is in general more seek-happy than ext4 due to its simpler
+block allocator and extensive use of linked lists.)
+
+The inode table is a linear array of ``struct ext4_inode``. The table is
+sized to have enough blocks to store at least
+``sb.s_inode_size * sb.s_inodes_per_group`` bytes. The number of the
+block group containing an inode can be calculated as
+``(inode_number - 1) / sb.s_inodes_per_group``, and the offset into the
+group's table is ``(inode_number - 1) % sb.s_inodes_per_group``. There
+is no inode 0.
+
+The inode checksum is calculated against the FS UUID, the inode number,
+and the inode structure itself.
+
+The inode table entry is laid out in ``struct ext4_inode``.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - i\_mode
+     - File mode. See the table i_mode_ below.
+   * - 0x2
+     - \_\_le16
+     - i\_uid
+     - Lower 16-bits of Owner UID.
+   * - 0x4
+     - \_\_le32
+     - i\_size\_lo
+     - Lower 32-bits of size in bytes.
+   * - 0x8
+     - \_\_le32
+     - i\_atime
+     - Last access time, in seconds since the epoch. However, if the EA\_INODE
+       inode flag is set, this inode stores an extended attribute value and
+       this field contains the checksum of the value.
+   * - 0xC
+     - \_\_le32
+     - i\_ctime
+     - Last inode change time, in seconds since the epoch. However, if the
+       EA\_INODE inode flag is set, this inode stores an extended attribute
+       value and this field contains the lower 32 bits of the attribute value's
+       reference count.
+   * - 0x10
+     - \_\_le32
+     - i\_mtime
+     - Last data modification time, in seconds since the epoch. However, if the
+       EA\_INODE inode flag is set, this inode stores an extended attribute
+       value and this field contains the number of the inode that owns the
+       extended attribute.
+   * - 0x14
+     - \_\_le32
+     - i\_dtime
+     - Deletion Time, in seconds since the epoch.
+   * - 0x18
+     - \_\_le16
+     - i\_gid
+     - Lower 16-bits of GID.
+   * - 0x1A
+     - \_\_le16
+     - i\_links\_count
+     - Hard link count. Normally, ext4 does not permit an inode to have more
+       than 65,000 hard links. This applies to files as well as directories,
+       which means that there cannot be more than 64,998 subdirectories in a
+       directory (each subdirectory's '..' entry counts as a hard link, as does
+       the '.' entry in the directory itself). With the DIR\_NLINK feature
+       enabled, ext4 supports more than 64,998 subdirectories by setting this
+       field to 1 to indicate that the number of hard links is not known.
+   * - 0x1C
+     - \_\_le32
+     - i\_blocks\_lo
+     - Lower 32-bits of “block” count. If the huge\_file feature flag is not
+       set on the filesystem, the file consumes ``i_blocks_lo`` 512-byte blocks
+       on disk. If huge\_file is set and EXT4\_HUGE\_FILE\_FL is NOT set in
+       ``inode.i_flags``, then the file consumes ``i_blocks_lo + (i_blocks_hi
+       << 32)`` 512-byte blocks on disk. If huge\_file is set and
+       EXT4\_HUGE\_FILE\_FL IS set in ``inode.i_flags``, then this file
+       consumes (``i_blocks_lo + i_blocks_hi`` << 32) filesystem blocks on
+       disk.
+   * - 0x20
+     - \_\_le32
+     - i\_flags
+     - Inode flags. See the table i_flags_ below.
+   * - 0x24
+     - 4 bytes
+     - i\_osd1
+     - See the table i_osd1_ for more details.
+   * - 0x28
+     - 60 bytes
+     - i\_block[EXT4\_N\_BLOCKS=15]
+     - Block map or extent tree. See the section “The Contents of inode.i\_block”.
+   * - 0x64
+     - \_\_le32
+     - i\_generation
+     - File version (for NFS).
+   * - 0x68
+     - \_\_le32
+     - i\_file\_acl\_lo
+     - Lower 32-bits of extended attribute block. ACLs are of course one of
+       many possible extended attributes; I think the name of this field is a
+       result of the first use of extended attributes being for ACLs.
+   * - 0x6C
+     - \_\_le32
+     - i\_size\_high / i\_dir\_acl
+     - Upper 32-bits of file/directory size. In ext2/3 this field was named
+       i\_dir\_acl, though it was usually set to zero and never used.
+   * - 0x70
+     - \_\_le32
+     - i\_obso\_faddr
+     - (Obsolete) fragment address.
+   * - 0x74
+     - 12 bytes
+     - i\_osd2
+     - See the table i_osd2_ for more details.
+   * - 0x80
+     - \_\_le16
+     - i\_extra\_isize
+     - Size of this inode - 128. Alternately, the size of the extended inode
+       fields beyond the original ext2 inode, including this field.
+   * - 0x82
+     - \_\_le16
+     - i\_checksum\_hi
+     - Upper 16-bits of the inode checksum.
+   * - 0x84
+     - \_\_le32
+     - i\_ctime\_extra
+     - Extra change time bits. This provides sub-second precision. See Inode
+       Timestamps section.
+   * - 0x88
+     - \_\_le32
+     - i\_mtime\_extra
+     - Extra modification time bits. This provides sub-second precision.
+   * - 0x8C
+     - \_\_le32
+     - i\_atime\_extra
+     - Extra access time bits. This provides sub-second precision.
+   * - 0x90
+     - \_\_le32
+     - i\_crtime
+     - File creation time, in seconds since the epoch.
+   * - 0x94
+     - \_\_le32
+     - i\_crtime\_extra
+     - Extra file creation time bits. This provides sub-second precision.
+   * - 0x98
+     - \_\_le32
+     - i\_version\_hi
+     - Upper 32-bits for version number.
+   * - 0x9C
+     - \_\_le32
+     - i\_projid
+     - Project ID.
+
+.. _i_mode:
+
+The ``i_mode`` value is a combination of the following flags:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - S\_IXOTH (Others may execute)
+   * - 0x2
+     - S\_IWOTH (Others may write)
+   * - 0x4
+     - S\_IROTH (Others may read)
+   * - 0x8
+     - S\_IXGRP (Group members may execute)
+   * - 0x10
+     - S\_IWGRP (Group members may write)
+   * - 0x20
+     - S\_IRGRP (Group members may read)
+   * - 0x40
+     - S\_IXUSR (Owner may execute)
+   * - 0x80
+     - S\_IWUSR (Owner may write)
+   * - 0x100
+     - S\_IRUSR (Owner may read)
+   * - 0x200
+     - S\_ISVTX (Sticky bit)
+   * - 0x400
+     - S\_ISGID (Set GID)
+   * - 0x800
+     - S\_ISUID (Set UID)
+   * -
+     - These are mutually-exclusive file types:
+   * - 0x1000
+     - S\_IFIFO (FIFO)
+   * - 0x2000
+     - S\_IFCHR (Character device)
+   * - 0x4000
+     - S\_IFDIR (Directory)
+   * - 0x6000
+     - S\_IFBLK (Block device)
+   * - 0x8000
+     - S\_IFREG (Regular file)
+   * - 0xA000
+     - S\_IFLNK (Symbolic link)
+   * - 0xC000
+     - S\_IFSOCK (Socket)
+
+.. _i_flags:
+
+The ``i_flags`` field is a combination of these values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x1
+     - This file requires secure deletion (EXT4\_SECRM\_FL). (not implemented)
+   * - 0x2
+     - This file should be preserved, should undeletion be desired
+       (EXT4\_UNRM\_FL). (not implemented)
+   * - 0x4
+     - File is compressed (EXT4\_COMPR\_FL). (not really implemented)
+   * - 0x8
+     - All writes to the file must be synchronous (EXT4\_SYNC\_FL).
+   * - 0x10
+     - File is immutable (EXT4\_IMMUTABLE\_FL).
+   * - 0x20
+     - File can only be appended (EXT4\_APPEND\_FL).
+   * - 0x40
+     - The dump(1) utility should not dump this file (EXT4\_NODUMP\_FL).
+   * - 0x80
+     - Do not update access time (EXT4\_NOATIME\_FL).
+   * - 0x100
+     - Dirty compressed file (EXT4\_DIRTY\_FL). (not used)
+   * - 0x200
+     - File has one or more compressed clusters (EXT4\_COMPRBLK\_FL). (not used)
+   * - 0x400
+     - Do not compress file (EXT4\_NOCOMPR\_FL). (not used)
+   * - 0x800
+     - Encrypted inode (EXT4\_ENCRYPT\_FL). This bit value previously was
+       EXT4\_ECOMPR\_FL (compression error), which was never used.
+   * - 0x1000
+     - Directory has hashed indexes (EXT4\_INDEX\_FL).
+   * - 0x2000
+     - AFS magic directory (EXT4\_IMAGIC\_FL).
+   * - 0x4000
+     - File data must always be written through the journal
+       (EXT4\_JOURNAL\_DATA\_FL).
+   * - 0x8000
+     - File tail should not be merged (EXT4\_NOTAIL\_FL). (not used by ext4)
+   * - 0x10000
+     - All directory entry data should be written synchronously (see
+       ``dirsync``) (EXT4\_DIRSYNC\_FL).
+   * - 0x20000
+     - Top of directory hierarchy (EXT4\_TOPDIR\_FL).
+   * - 0x40000
+     - This is a huge file (EXT4\_HUGE\_FILE\_FL).
+   * - 0x80000
+     - Inode uses extents (EXT4\_EXTENTS\_FL).
+   * - 0x200000
+     - Inode stores a large extended attribute value in its data blocks
+       (EXT4\_EA\_INODE\_FL).
+   * - 0x400000
+     - This file has blocks allocated past EOF (EXT4\_EOFBLOCKS\_FL).
+       (deprecated)
+   * - 0x01000000
+     - Inode is a snapshot (``EXT4_SNAPFILE_FL``). (not in mainline)
+   * - 0x04000000
+     - Snapshot is being deleted (``EXT4_SNAPFILE_DELETED_FL``). (not in
+       mainline)
+   * - 0x08000000
+     - Snapshot shrink has completed (``EXT4_SNAPFILE_SHRUNK_FL``). (not in
+       mainline)
+   * - 0x10000000
+     - Inode has inline data (EXT4\_INLINE\_DATA\_FL).
+   * - 0x20000000
+     - Create children with the same project ID (EXT4\_PROJINHERIT\_FL).
+   * - 0x80000000
+     - Reserved for ext4 library (EXT4\_RESERVED\_FL).
+   * -
+     - Aggregate flags:
+   * - 0x4BDFFF
+     - User-visible flags.
+   * - 0x4B80FF
+     - User-modifiable flags. Note that while EXT4\_JOURNAL\_DATA\_FL and
+       EXT4\_EXTENTS\_FL can be set with setattr, they are not in the kernel's
+       EXT4\_FL\_USER\_MODIFIABLE mask, since it needs to handle the setting of
+       these flags in a special manner and they are masked out of the set of
+       flags that are saved directly to i\_flags.
+
+.. _i_osd1:
+
+The ``osd1`` field has multiple meanings depending on the creator:
+
+Linux:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - l\_i\_version
+     - Inode version. However, if the EA\_INODE inode flag is set, this inode
+       stores an extended attribute value and this field contains the upper 32
+       bits of the attribute value's reference count.
+
+Hurd:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_i\_translator
+     - ??
+
+Masix:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - m\_i\_reserved
+     - ??
+
+.. _i_osd2:
+
+The ``osd2`` field has multiple meanings depending on the filesystem creator:
+
+Linux:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - l\_i\_blocks\_high
+     - Upper 16-bits of the block count. Please see the note attached to
+       i\_blocks\_lo.
+   * - 0x2
+     - \_\_le16
+     - l\_i\_file\_acl\_high
+     - Upper 16-bits of the extended attribute block (historically, the file
+       ACL location). See the Extended Attributes section below.
+   * - 0x4
+     - \_\_le16
+     - l\_i\_uid\_high
+     - Upper 16-bits of the Owner UID.
+   * - 0x6
+     - \_\_le16
+     - l\_i\_gid\_high
+     - Upper 16-bits of the GID.
+   * - 0x8
+     - \_\_le16
+     - l\_i\_checksum\_lo
+     - Lower 16-bits of the inode checksum.
+   * - 0xA
+     - \_\_le16
+     - l\_i\_reserved
+     - Unused.
+
+Hurd:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - h\_i\_reserved1
+     - ??
+   * - 0x2
+     - \_\_u16
+     - h\_i\_mode\_high
+     - Upper 16-bits of the file mode.
+   * - 0x4
+     - \_\_le16
+     - h\_i\_uid\_high
+     - Upper 16-bits of the Owner UID.
+   * - 0x6
+     - \_\_le16
+     - h\_i\_gid\_high
+     - Upper 16-bits of the GID.
+   * - 0x8
+     - \_\_u32
+     - h\_i\_author
+     - Author code?
+
+Masix:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - h\_i\_reserved1
+     - ??
+   * - 0x2
+     - \_\_u16
+     - m\_i\_file\_acl\_high
+     - Upper 16-bits of the extended attribute block (historically, the file
+       ACL location).
+   * - 0x4
+     - \_\_u32
+     - m\_i\_reserved2[2]
+     - ??
+
+Inode Size
+~~~~~~~~~~
+
+In ext2 and ext3, the inode structure size was fixed at 128 bytes
+(``EXT2_GOOD_OLD_INODE_SIZE``) and each inode had a disk record size of
+128 bytes. Starting with ext4, it is possible to allocate a larger
+on-disk inode at format time for all inodes in the filesystem to provide
+space beyond the end of the original ext2 inode. The on-disk inode
+record size is recorded in the superblock as ``s_inode_size``. The
+number of bytes actually used by struct ext4\_inode beyond the original
+128-byte ext2 inode is recorded in the ``i_extra_isize`` field for each
+inode, which allows struct ext4\_inode to grow for a new kernel without
+having to upgrade all of the on-disk inodes. Access to fields beyond
+EXT2\_GOOD\_OLD\_INODE\_SIZE should be verified to be within
+``i_extra_isize``. By default, ext4 inode records are 256 bytes, and (as
+of October 2013) the inode structure is 156 bytes
+(``i_extra_isize = 28``). The extra space between the end of the inode
+structure and the end of the inode record can be used to store extended
+attributes. Each inode record can be as large as the filesystem block
+size, though this is not terribly efficient.
+
+Finding an Inode
+~~~~~~~~~~~~~~~~
+
+Each block group contains ``sb->s_inodes_per_group`` inodes. Because
+inode 0 is defined not to exist, this formula can be used to find the
+block group that an inode lives in:
+``bg = (inode_num - 1) / sb->s_inodes_per_group``. The particular inode
+can be found within the block group's inode table at
+``index = (inode_num - 1) % sb->s_inodes_per_group``. To get the byte
+address within the inode table, use
+``offset = index * sb->s_inode_size``.
+
+Inode Timestamps
+~~~~~~~~~~~~~~~~
+
+Four timestamps are recorded in the lower 128 bytes of the inode
+structure -- inode change time (ctime), access time (atime), data
+modification time (mtime), and deletion time (dtime). The four fields
+are 32-bit signed integers that represent seconds since the Unix epoch
+(1970-01-01 00:00:00 GMT), which means that the fields will overflow in
+January 2038. For inodes that are not linked from any directory but are
+still open (orphan inodes), the dtime field is overloaded for use with
+the orphan list. The superblock field ``s_last_orphan`` points to the
+first inode in the orphan list; dtime is then the number of the next
+orphaned inode, or zero if there are no more orphans.
+
+If the inode structure size ``sb->s_inode_size`` is larger than 128
+bytes and the ``i_inode_extra`` field is large enough to encompass the
+respective ``i_[cma]time_extra`` field, the ctime, atime, and mtime
+inode fields are widened to 64 bits. Within this “extra” 32-bit field,
+the lower two bits are used to extend the 32-bit seconds field to be 34
+bit wide; the upper 30 bits are used to provide nanosecond timestamp
+accuracy. Therefore, timestamps should not overflow until May 2446.
+dtime was not widened. There is also a fifth timestamp to record inode
+creation time (crtime); this field is 64-bits wide and decoded in the
+same manner as 64-bit [cma]time. Neither crtime nor dtime are accessible
+through the regular stat() interface, though debugfs will report them.
+
+We use the 32-bit signed time value plus (2^32 \* (extra epoch bits)).
+In other words:
+
+.. list-table::
+   :widths: 20 20 20 20 20
+   :header-rows: 1
+
+   * - Extra epoch bits
+     - MSB of 32-bit time
+     - Adjustment for signed 32-bit to 64-bit tv\_sec
+     - Decoded 64-bit tv\_sec
+     - valid time range
+   * - 0 0
+     - 1
+     - 0
+     - ``-0x80000000 - -0x00000001``
+     - 1901-12-13 to 1969-12-31
+   * - 0 0
+     - 0
+     - 0
+     - ``0x000000000 - 0x07fffffff``
+     - 1970-01-01 to 2038-01-19
+   * - 0 1
+     - 1
+     - 0x100000000
+     - ``0x080000000 - 0x0ffffffff``
+     - 2038-01-19 to 2106-02-07
+   * - 0 1
+     - 0
+     - 0x100000000
+     - ``0x100000000 - 0x17fffffff``
+     - 2106-02-07 to 2174-02-25
+   * - 1 0
+     - 1
+     - 0x200000000
+     - ``0x180000000 - 0x1ffffffff``
+     - 2174-02-25 to 2242-03-16
+   * - 1 0
+     - 0
+     - 0x200000000
+     - ``0x200000000 - 0x27fffffff``
+     - 2242-03-16 to 2310-04-04
+   * - 1 1
+     - 1
+     - 0x300000000
+     - ``0x280000000 - 0x2ffffffff``
+     - 2310-04-04 to 2378-04-22
+   * - 1 1
+     - 0
+     - 0x300000000
+     - ``0x300000000 - 0x37fffffff``
+     - 2378-04-22 to 2446-05-10
+
+This is a somewhat odd encoding since there are effectively seven times
+as many positive values as negative values. There have also been
+long-standing bugs decoding and encoding dates beyond 2038, which don't
+seem to be fixed as of kernel 3.12 and e2fsprogs 1.42.8. 64-bit kernels
+incorrectly use the extra epoch bits 1,1 for dates between 1901 and
+1970. At some point the kernel will be fixed and e2fsck will fix this
+situation, assuming that it is run before 2310.
-- 
cgit v1.2.3


From b4becd48b7b548f564533a41e1cdeb8ae3bd1c70 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:45:00 -0400
Subject: ext4: import inode data fork chapter from wiki page

Import the chapter about inode data fork from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/conf.py                              |   2 +-
 Documentation/filesystems/ext4/ondisk/blockmap.rst |  49 ++++++
 Documentation/filesystems/ext4/ondisk/dynamic.rst  |   1 +
 Documentation/filesystems/ext4/ondisk/ifork.rst    | 194 +++++++++++++++++++++
 4 files changed, 245 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/filesystems/ext4/ondisk/blockmap.rst
 create mode 100644 Documentation/filesystems/ext4/ondisk/ifork.rst

diff --git a/Documentation/conf.py b/Documentation/conf.py
index 62ac5a9f3a9f..b691af4831fa 100644
--- a/Documentation/conf.py
+++ b/Documentation/conf.py
@@ -34,7 +34,7 @@ needs_sphinx = '1.3'
 # Add any Sphinx extension module names here, as strings. They can be
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
-extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure']
+extensions = ['kerneldoc', 'rstFlatTable', 'kernel_include', 'cdomain', 'kfigure', 'sphinx.ext.ifconfig']
 
 # The name of the math extension changed on Sphinx 1.4
 if major == 1 and minor > 3:
diff --git a/Documentation/filesystems/ext4/ondisk/blockmap.rst b/Documentation/filesystems/ext4/ondisk/blockmap.rst
new file mode 100644
index 000000000000..30e25750d88a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/blockmap.rst
@@ -0,0 +1,49 @@
+.. SPDX-License-Identifier: GPL-2.0
+
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| i.i\_block Offset   | Where It Points                                                                                                                                                                                                              |
++=====================+==============================================================================================================================================================================================================================+
+| 0 to 11             | Direct map to file blocks 0 to 11.                                                                                                                                                                                           |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 12                  | Indirect block: (file blocks 12 to (``$block_size`` / 4) + 11, or 12 to 1035 if 4KiB blocks)                                                                                                                                 |
+|                     |                                                                                                                                                                                                                              |
+|                     | +------------------------------+--------------------------------------------------------------------+                                                                                                                        |
+|                     | | Indirect Block Offset        | Where It Points                                                    |                                                                                                                        |
+|                     | +==============================+====================================================================+                                                                                                                        |
+|                     | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |                                                                                                                        |
+|                     | +------------------------------+--------------------------------------------------------------------+                                                                                                                        |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 13                  | Double-indirect block: (file blocks ``$block_size``/4 + 12 to (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 11, or 1036 to 1049611 if 4KiB blocks)                                                                     |
+|                     |                                                                                                                                                                                                                              |
+|                     | +--------------------------------+---------------------------------------------------------------------------------------------------------+                                                                                 |
+|                     | | Double Indirect Block Offset   | Where It Points                                                                                         |                                                                                 |
+|                     | +================================+=========================================================================================================+                                                                                 |
+|                     | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) indirect blocks (1024 if 4KiB blocks)                                      |                                                                                 |
+|                     | |                                |                                                                                                         |                                                                                 |
+|                     | |                                | +------------------------------+--------------------------------------------------------------------+   |                                                                                 |
+|                     | |                                | | Indirect Block Offset        | Where It Points                                                    |   |                                                                                 |
+|                     | |                                | +==============================+====================================================================+   |                                                                                 |
+|                     | |                                | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |   |                                                                                 |
+|                     | |                                | +------------------------------+--------------------------------------------------------------------+   |                                                                                 |
+|                     | +--------------------------------+---------------------------------------------------------------------------------------------------------+                                                                                 |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
+| 14                  | Triple-indirect block: (file blocks (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 12 to (``$block_size`` / 4) ^ 3 + (``$block_size`` / 4) ^ 2 + (``$block_size`` / 4) + 12, or 1049612 to 1074791436 if 4KiB blocks)   |
+|                     |                                                                                                                                                                                                                              |
+|                     | +--------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+                                          |
+|                     | | Triple Indirect Block Offset   | Where It Points                                                                                                                                |                                          |
+|                     | +================================+================================================================================================================================================+                                          |
+|                     | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) double indirect blocks (1024 if 4KiB blocks)                                                                      |                                          |
+|                     | |                                |                                                                                                                                                |                                          |
+|                     | |                                | +--------------------------------+---------------------------------------------------------------------------------------------------------+   |                                          |
+|                     | |                                | | Double Indirect Block Offset   | Where It Points                                                                                         |   |                                          |
+|                     | |                                | +================================+=========================================================================================================+   |                                          |
+|                     | |                                | | 0 to (``$block_size`` / 4)     | Map to (``$block_size`` / 4) indirect blocks (1024 if 4KiB blocks)                                      |   |                                          |
+|                     | |                                | |                                |                                                                                                         |   |                                          |
+|                     | |                                | |                                | +------------------------------+--------------------------------------------------------------------+   |   |                                          |
+|                     | |                                | |                                | | Indirect Block Offset        | Where It Points                                                    |   |   |                                          |
+|                     | |                                | |                                | +==============================+====================================================================+   |   |                                          |
+|                     | |                                | |                                | | 0 to (``$block_size`` / 4)   | Direct map to (``$block_size`` / 4) blocks (1024 if 4KiB blocks)   |   |   |                                          |
+|                     | |                                | |                                | +------------------------------+--------------------------------------------------------------------+   |   |                                          |
+|                     | |                                | +--------------------------------+---------------------------------------------------------------------------------------------------------+   |                                          |
+|                     | +--------------------------------+------------------------------------------------------------------------------------------------------------------------------------------------+                                          |
++---------------------+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
diff --git a/Documentation/filesystems/ext4/ondisk/dynamic.rst b/Documentation/filesystems/ext4/ondisk/dynamic.rst
index 7c5f5019b9d6..f090de8dd1c1 100644
--- a/Documentation/filesystems/ext4/ondisk/dynamic.rst
+++ b/Documentation/filesystems/ext4/ondisk/dynamic.rst
@@ -7,3 +7,4 @@ Dynamic metadata are created on the fly when files and blocks are
 allocated to files.
 
 .. include:: inodes.rst
+.. include:: ifork.rst
diff --git a/Documentation/filesystems/ext4/ondisk/ifork.rst b/Documentation/filesystems/ext4/ondisk/ifork.rst
new file mode 100644
index 000000000000..5dbe3b2b121a
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/ifork.rst
@@ -0,0 +1,194 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+The Contents of inode.i\_block
+------------------------------
+
+Depending on the type of file an inode describes, the 60 bytes of
+storage in ``inode.i_block`` can be used in different ways. In general,
+regular files and directories will use it for file block indexing
+information, and special files will use it for special purposes.
+
+Symbolic Links
+~~~~~~~~~~~~~~
+
+The target of a symbolic link will be stored in this field if the target
+string is less than 60 bytes long. Otherwise, either extents or block
+maps will be used to allocate data blocks to store the link target.
+
+Direct/Indirect Block Addressing
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+In ext2/3, file block numbers were mapped to logical block numbers by
+means of an (up to) three level 1-1 block map. To find the logical block
+that stores a particular file block, the code would navigate through
+this increasingly complicated structure. Notice that there is neither a
+magic number nor a checksum to provide any level of confidence that the
+block isn't full of garbage.
+
+.. ifconfig:: builder != 'latex'
+
+   .. include:: blockmap.rst
+
+.. ifconfig:: builder == 'latex'
+
+   [Table omitted because LaTeX doesn't support nested tables.]
+
+Note that with this block mapping scheme, it is necessary to fill out a
+lot of mapping data even for a large contiguous file! This inefficiency
+led to the creation of the extent mapping scheme, discussed below.
+
+Notice also that a file using this mapping scheme cannot be placed
+higher than 2^32 blocks.
+
+Extent Tree
+~~~~~~~~~~~
+
+In ext4, the file to logical block map has been replaced with an extent
+tree. Under the old scheme, allocating a contiguous run of 1,000 blocks
+requires an indirect block to map all 1,000 entries; with extents, the
+mapping is reduced to a single ``struct ext4_extent`` with
+``ee_len = 1000``. If flex\_bg is enabled, it is possible to allocate
+very large files with a single extent, at a considerable reduction in
+metadata block use, and some improvement in disk efficiency. The inode
+must have the extents flag (0x80000) flag set for this feature to be in
+use.
+
+Extents are arranged as a tree. Each node of the tree begins with a
+``struct ext4_extent_header``. If the node is an interior node
+(``eh.eh_depth`` > 0), the header is followed by ``eh.eh_entries``
+instances of ``struct ext4_extent_idx``; each of these index entries
+points to a block containing more nodes in the extent tree. If the node
+is a leaf node (``eh.eh_depth == 0``), then the header is followed by
+``eh.eh_entries`` instances of ``struct ext4_extent``; these instances
+point to the file's data blocks. The root node of the extent tree is
+stored in ``inode.i_block``, which allows for the first four extents to
+be recorded without the use of extra metadata blocks.
+
+The extent tree header is recorded in ``struct ext4_extent_header``,
+which is 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le16
+     - eh\_magic
+     - Magic number, 0xF30A.
+   * - 0x2
+     - \_\_le16
+     - eh\_entries
+     - Number of valid entries following the header.
+   * - 0x4
+     - \_\_le16
+     - eh\_max
+     - Maximum number of entries that could follow the header.
+   * - 0x6
+     - \_\_le16
+     - eh\_depth
+     - Depth of this extent node in the extent tree. 0 = this extent node
+       points to data blocks; otherwise, this extent node points to other
+       extent nodes. The extent tree can be at most 5 levels deep: a logical
+       block number can be at most ``2^32``, and the smallest ``n`` that
+       satisfies ``4*(((blocksize - 12)/12)^n) >= 2^32`` is 5.
+   * - 0x8
+     - \_\_le32
+     - eh\_generation
+     - Generation of the tree. (Used by Lustre, but not standard ext4).
+
+Internal nodes of the extent tree, also known as index nodes, are
+recorded as ``struct ext4_extent_idx``, and are 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - ei\_block
+     - This index node covers file blocks from 'block' onward.
+   * - 0x4
+     - \_\_le32
+     - ei\_leaf\_lo
+     - Lower 32-bits of the block number of the extent node that is the next
+       level lower in the tree. The tree node pointed to can be either another
+       internal node or a leaf node, described below.
+   * - 0x8
+     - \_\_le16
+     - ei\_leaf\_hi
+     - Upper 16-bits of the previous field.
+   * - 0xA
+     - \_\_u16
+     - ei\_unused
+     -
+
+Leaf nodes of the extent tree are recorded as ``struct ext4_extent``,
+and are also 12 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - ee\_block
+     - First file block number that this extent covers.
+   * - 0x4
+     - \_\_le16
+     - ee\_len
+     - Number of blocks covered by extent. If the value of this field is <=
+       32768, the extent is initialized. If the value of the field is > 32768,
+       the extent is uninitialized and the actual extent length is ``ee_len`` -
+       32768. Therefore, the maximum length of a initialized extent is 32768
+       blocks, and the maximum length of an uninitialized extent is 32767.
+   * - 0x6
+     - \_\_le16
+     - ee\_start\_hi
+     - Upper 16-bits of the block number to which this extent points.
+   * - 0x8
+     - \_\_le32
+     - ee\_start\_lo
+     - Lower 32-bits of the block number to which this extent points.
+
+Prior to the introduction of metadata checksums, the extent header +
+extent entries always left at least 4 bytes of unallocated space at the
+end of each extent tree data block (because (2^x % 12) >= 4). Therefore,
+the 32-bit checksum is inserted into this space. The 4 extents in the
+inode do not need checksumming, since the inode is already checksummed.
+The checksum is calculated against the FS UUID, the inode number, the
+inode generation, and the entire extent block leading up to (but not
+including) the checksum itself.
+
+``struct ext4_extent_tail`` is 4 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - eb\_checksum
+     - Checksum of the extent block, crc32c(uuid+inum+igeneration+extentblock)
+
+Inline Data
+~~~~~~~~~~~
+
+If the inline data feature is enabled for the filesystem and the flag is
+set for the inode, it is possible that the first 60 bytes of the file
+data are stored here.
-- 
cgit v1.2.3


From 60edae3a0424f084187eedd5386bfbeadd4ec1c7 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:46:00 -0400
Subject: ext4: import directory layout chapter from wiki page

Import the chapter about directory layout from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 .../filesystems/ext4/ondisk/directory.rst          | 426 +++++++++++++++++++++
 Documentation/filesystems/ext4/ondisk/dynamic.rst  |   1 +
 2 files changed, 427 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/directory.rst

diff --git a/Documentation/filesystems/ext4/ondisk/directory.rst b/Documentation/filesystems/ext4/ondisk/directory.rst
new file mode 100644
index 000000000000..8fcba68c2884
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/directory.rst
@@ -0,0 +1,426 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Directory Entries
+-----------------
+
+In an ext4 filesystem, a directory is more or less a flat file that maps
+an arbitrary byte string (usually ASCII) to an inode number on the
+filesystem. There can be many directory entries across the filesystem
+that reference the same inode number--these are known as hard links, and
+that is why hard links cannot reference files on other filesystems. As
+such, directory entries are found by reading the data block(s)
+associated with a directory file for the particular directory entry that
+is desired.
+
+Linear (Classic) Directories
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+By default, each directory lists its entries in an “almost-linear”
+array. I write “almost” because it's not a linear array in the memory
+sense because directory entries are not split across filesystem blocks.
+Therefore, it is more accurate to say that a directory is a series of
+data blocks and that each block contains a linear array of directory
+entries. The end of each per-block array is signified by reaching the
+end of the block; the last entry in the block has a record length that
+takes it all the way to the end of the block. The end of the entire
+directory is of course signified by reaching the end of the file. Unused
+directory entries are signified by inode = 0. By default the filesystem
+uses ``struct ext4_dir_entry_2`` for directory entries unless the
+“filetype” feature flag is not set, in which case it uses
+``struct ext4_dir_entry``.
+
+The original directory entry format is ``struct ext4_dir_entry``, which
+is at most 263 bytes long, though on disk you'll need to reference
+``dirent.rec_len`` to know for sure.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - inode
+     - Number of the inode that this directory entry points to.
+   * - 0x4
+     - \_\_le16
+     - rec\_len
+     - Length of this directory entry. Must be a multiple of 4.
+   * - 0x6
+     - \_\_le16
+     - name\_len
+     - Length of the file name.
+   * - 0x8
+     - char
+     - name[EXT4\_NAME\_LEN]
+     - File name.
+
+Since file names cannot be longer than 255 bytes, the new directory
+entry format shortens the rec\_len field and uses the space for a file
+type flag, probably to avoid having to load every inode during directory
+tree traversal. This format is ``ext4_dir_entry_2``, which is at most
+263 bytes long, though on disk you'll need to reference
+``dirent.rec_len`` to know for sure.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - inode
+     - Number of the inode that this directory entry points to.
+   * - 0x4
+     - \_\_le16
+     - rec\_len
+     - Length of this directory entry.
+   * - 0x6
+     - \_\_u8
+     - name\_len
+     - Length of the file name.
+   * - 0x7
+     - \_\_u8
+     - file\_type
+     - File type code, see ftype_ table below.
+   * - 0x8
+     - char
+     - name[EXT4\_NAME\_LEN]
+     - File name.
+
+.. _ftype:
+
+The directory file type is one of the following values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Unknown.
+   * - 0x1
+     - Regular file.
+   * - 0x2
+     - Directory.
+   * - 0x3
+     - Character device file.
+   * - 0x4
+     - Block device file.
+   * - 0x5
+     - FIFO.
+   * - 0x6
+     - Socket.
+   * - 0x7
+     - Symbolic link.
+
+In order to add checksums to these classic directory blocks, a phony
+``struct ext4_dir_entry`` is placed at the end of each leaf block to
+hold the checksum. The directory entry is 12 bytes long. The inode
+number and name\_len fields are set to zero to fool old software into
+ignoring an apparently empty directory entry, and the checksum is stored
+in the place where the name normally goes. The structure is
+``struct ext4_dir_entry_tail``:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Size
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - det\_reserved\_zero1
+     - Inode number, which must be zero.
+   * - 0x4
+     - \_\_le16
+     - det\_rec\_len
+     - Length of this directory entry, which must be 12.
+   * - 0x6
+     - \_\_u8
+     - det\_reserved\_zero2
+     - Length of the file name, which must be zero.
+   * - 0x7
+     - \_\_u8
+     - det\_reserved\_ft
+     - File type, which must be 0xDE.
+   * - 0x8
+     - \_\_le32
+     - det\_checksum
+     - Directory leaf block checksum.
+
+The leaf directory block checksum is calculated against the FS UUID, the
+directory's inode number, the directory's inode generation number, and
+the entire directory entry block up to (but not including) the fake
+directory entry.
+
+Hash Tree Directories
+~~~~~~~~~~~~~~~~~~~~~
+
+A linear array of directory entries isn't great for performance, so a
+new feature was added to ext3 to provide a faster (but peculiar)
+balanced tree keyed off a hash of the directory entry name. If the
+EXT4\_INDEX\_FL (0x1000) flag is set in the inode, this directory uses a
+hashed btree (htree) to organize and find directory entries. For
+backwards read-only compatibility with ext2, this tree is actually
+hidden inside the directory file, masquerading as “empty” directory data
+blocks! It was stated previously that the end of the linear directory
+entry table was signified with an entry pointing to inode 0; this is
+(ab)used to fool the old linear-scan algorithm into thinking that the
+rest of the directory block is empty so that it moves on.
+
+The root of the tree always lives in the first data block of the
+directory. By ext2 custom, the '.' and '..' entries must appear at the
+beginning of this first block, so they are put here as two
+``struct ext4_dir_entry_2``\ s and not stored in the tree. The rest of
+the root node contains metadata about the tree and finally a hash->block
+map to find nodes that are lower in the htree. If
+``dx_root.info.indirect_levels`` is non-zero then the htree has two
+levels; the data block pointed to by the root node's map is an interior
+node, which is indexed by a minor hash. Interior nodes in this tree
+contains a zeroed out ``struct ext4_dir_entry_2`` followed by a
+minor\_hash->block map to find leafe nodes. Leaf nodes contain a linear
+array of all ``struct ext4_dir_entry_2``; all of these entries
+(presumably) hash to the same value. If there is an overflow, the
+entries simply overflow into the next leaf node, and the
+least-significant bit of the hash (in the interior node map) that gets
+us to this next leaf node is set.
+
+To traverse the directory as a htree, the code calculates the hash of
+the desired file name and uses it to find the corresponding block
+number. If the tree is flat, the block is a linear array of directory
+entries that can be searched; otherwise, the minor hash of the file name
+is computed and used against this second block to find the corresponding
+third block number. That third block number will be a linear array of
+directory entries.
+
+To traverse the directory as a linear array (such as the old code does),
+the code simply reads every data block in the directory. The blocks used
+for the htree will appear to have no entries (aside from '.' and '..')
+and so only the leaf nodes will appear to have any interesting content.
+
+The root of the htree is in ``struct dx_root``, which is the full length
+of a data block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - dot.inode
+     - inode number of this directory.
+   * - 0x4
+     - \_\_le16
+     - dot.rec\_len
+     - Length of this record, 12.
+   * - 0x6
+     - u8
+     - dot.name\_len
+     - Length of the name, 1.
+   * - 0x7
+     - u8
+     - dot.file\_type
+     - File type of this entry, 0x2 (directory) (if the feature flag is set).
+   * - 0x8
+     - char
+     - dot.name[4]
+     - “.\\0\\0\\0”
+   * - 0xC
+     - \_\_le32
+     - dotdot.inode
+     - inode number of parent directory.
+   * - 0x10
+     - \_\_le16
+     - dotdot.rec\_len
+     - block\_size - 12. The record length is long enough to cover all htree
+       data.
+   * - 0x12
+     - u8
+     - dotdot.name\_len
+     - Length of the name, 2.
+   * - 0x13
+     - u8
+     - dotdot.file\_type
+     - File type of this entry, 0x2 (directory) (if the feature flag is set).
+   * - 0x14
+     - char
+     - dotdot\_name[4]
+     - “..\\0\\0”
+   * - 0x18
+     - \_\_le32
+     - struct dx\_root\_info.reserved\_zero
+     - Zero.
+   * - 0x1C
+     - u8
+     - struct dx\_root\_info.hash\_version
+     - Hash type, see dirhash_ table below.
+   * - 0x1D
+     - u8
+     - struct dx\_root\_info.info\_length
+     - Length of the tree information, 0x8.
+   * - 0x1E
+     - u8
+     - struct dx\_root\_info.indirect\_levels
+     - Depth of the htree. Cannot be larger than 3 if the INCOMPAT\_LARGEDIR
+       feature is set; cannot be larger than 2 otherwise.
+   * - 0x1F
+     - u8
+     - struct dx\_root\_info.unused\_flags
+     -
+   * - 0x20
+     - \_\_le16
+     - limit
+     - Maximum number of dx\_entries that can follow this header, plus 1 for
+       the header itself.
+   * - 0x22
+     - \_\_le16
+     - count
+     - Actual number of dx\_entries that follow this header, plus 1 for the
+       header itself.
+   * - 0x24
+     - \_\_le32
+     - block
+     - The block number (within the directory file) that goes with hash=0.
+   * - 0x28
+     - struct dx\_entry
+     - entries[0]
+     - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
+
+.. _dirhash:
+
+The directory hash is one of the following values:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Value
+     - Description
+   * - 0x0
+     - Legacy.
+   * - 0x1
+     - Half MD4.
+   * - 0x2
+     - Tea.
+   * - 0x3
+     - Legacy, unsigned.
+   * - 0x4
+     - Half MD4, unsigned.
+   * - 0x5
+     - Tea, unsigned.
+
+Interior nodes of an htree are recorded as ``struct dx_node``, which is
+also the full length of a data block:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - fake.inode
+     - Zero, to make it look like this entry is not in use.
+   * - 0x4
+     - \_\_le16
+     - fake.rec\_len
+     - The size of the block, in order to hide all of the dx\_node data.
+   * - 0x6
+     - u8
+     - name\_len
+     - Zero. There is no name for this “unused” directory entry.
+   * - 0x7
+     - u8
+     - file\_type
+     - Zero. There is no file type for this “unused” directory entry.
+   * - 0x8
+     - \_\_le16
+     - limit
+     - Maximum number of dx\_entries that can follow this header, plus 1 for
+       the header itself.
+   * - 0xA
+     - \_\_le16
+     - count
+     - Actual number of dx\_entries that follow this header, plus 1 for the
+       header itself.
+   * - 0xE
+     - \_\_le32
+     - block
+     - The block number (within the directory file) that goes with the lowest
+       hash value of this block. This value is stored in the parent block.
+   * - 0x12
+     - struct dx\_entry
+     - entries[0]
+     - As many 8-byte ``struct dx_entry`` as fits in the rest of the data block.
+
+The hash maps that exist in both ``struct dx_root`` and
+``struct dx_node`` are recorded as ``struct dx_entry``, which is 8 bytes
+long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - hash
+     - Hash code.
+   * - 0x4
+     - \_\_le32
+     - block
+     - Block number (within the directory file, not filesystem blocks) of the
+       next node in the htree.
+
+(If you think this is all quite clever and peculiar, so does the
+author.)
+
+If metadata checksums are enabled, the last 8 bytes of the directory
+block (precisely the length of one dx\_entry) are used to store a
+``struct dx_tail``, which contains the checksum. The ``limit`` and
+``count`` entries in the dx\_root/dx\_node structures are adjusted as
+necessary to fit the dx\_tail into the block. If there is no space for
+the dx\_tail, the user is notified to run e2fsck -D to rebuild the
+directory index (which will ensure that there's space for the checksum.
+The dx\_tail structure is 8 bytes long and looks like this:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - u32
+     - dt\_reserved
+     - Zero.
+   * - 0x4
+     - \_\_le32
+     - dt\_checksum
+     - Checksum of the htree directory block.
+
+The checksum is calculated against the FS UUID, the htree index header
+(dx\_root or dx\_node), all of the htree indices (dx\_entry) that are in
+use, and the tail block (dx\_tail).
diff --git a/Documentation/filesystems/ext4/ondisk/dynamic.rst b/Documentation/filesystems/ext4/ondisk/dynamic.rst
index f090de8dd1c1..f2f14822b0f5 100644
--- a/Documentation/filesystems/ext4/ondisk/dynamic.rst
+++ b/Documentation/filesystems/ext4/ondisk/dynamic.rst
@@ -8,3 +8,4 @@ allocated to files.
 
 .. include:: inodes.rst
 .. include:: ifork.rst
+.. include:: directory.rst
-- 
cgit v1.2.3


From 66d3239a4d8f0af7795f07159133bac75ed024bd Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 15:47:00 -0400
Subject: ext4: import extended attributes chapter from wiki page

Import the chapter about extended attributes from the on-disk format wiki
page into the kernel documentation.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 .../filesystems/ext4/ondisk/attributes.rst         | 191 +++++++++++++++++++++
 Documentation/filesystems/ext4/ondisk/dynamic.rst  |   1 +
 2 files changed, 192 insertions(+)
 create mode 100644 Documentation/filesystems/ext4/ondisk/attributes.rst

diff --git a/Documentation/filesystems/ext4/ondisk/attributes.rst b/Documentation/filesystems/ext4/ondisk/attributes.rst
new file mode 100644
index 000000000000..0b01b67b81fe
--- /dev/null
+++ b/Documentation/filesystems/ext4/ondisk/attributes.rst
@@ -0,0 +1,191 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+Extended Attributes
+-------------------
+
+Extended attributes (xattrs) are typically stored in a separate data
+block on the disk and referenced from inodes via ``inode.i_file_acl*``.
+The first use of extended attributes seems to have been for storing file
+ACLs and other security data (selinux). With the ``user_xattr`` mount
+option it is possible for users to store extended attributes so long as
+all attribute names begin with “user”; this restriction seems to have
+disappeared as of Linux 3.0.
+
+There are two places where extended attributes can be found. The first
+place is between the end of each inode entry and the beginning of the
+next inode entry. For example, if inode.i\_extra\_isize = 28 and
+sb.inode\_size = 256, then there are 256 - (128 + 28) = 100 bytes
+available for in-inode extended attribute storage. The second place
+where extended attributes can be found is in the block pointed to by
+``inode.i_file_acl``. As of Linux 3.11, it is not possible for this
+block to contain a pointer to a second extended attribute block (or even
+the remaining blocks of a cluster). In theory it is possible for each
+attribute's value to be stored in a separate data block, though as of
+Linux 3.11 the code does not permit this.
+
+Keys are generally assumed to be ASCIIZ strings, whereas values can be
+strings or binary data.
+
+Extended attributes, when stored after the inode, have a header
+``ext4_xattr_ibody_header`` that is 4 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_magic
+     - Magic number for identification, 0xEA020000. This value is set by the
+       Linux driver, though e2fsprogs doesn't seem to check it(?)
+
+The beginning of an extended attribute block is in
+``struct ext4_xattr_header``, which is 32 bytes long:
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_le32
+     - h\_magic
+     - Magic number for identification, 0xEA020000.
+   * - 0x4
+     - \_\_le32
+     - h\_refcount
+     - Reference count.
+   * - 0x8
+     - \_\_le32
+     - h\_blocks
+     - Number of disk blocks used.
+   * - 0xC
+     - \_\_le32
+     - h\_hash
+     - Hash value of all attributes.
+   * - 0x10
+     - \_\_le32
+     - h\_checksum
+     - Checksum of the extended attribute block.
+   * - 0x14
+     - \_\_u32
+     - h\_reserved[2]
+     - Zero.
+
+The checksum is calculated against the FS UUID, the 64-bit block number
+of the extended attribute block, and the entire block (header +
+entries).
+
+Following the ``struct ext4_xattr_header`` or
+``struct ext4_xattr_ibody_header`` is an array of
+``struct ext4_xattr_entry``; each of these entries is at least 16 bytes
+long. When stored in an external block, the ``struct ext4_xattr_entry``
+entries must be stored in sorted order. The sort order is
+``e_name_index``, then ``e_name_len``, and finally ``e_name``.
+Attributes stored inside an inode do not need be stored in sorted order.
+
+.. list-table::
+   :widths: 1 1 1 77
+   :header-rows: 1
+
+   * - Offset
+     - Type
+     - Name
+     - Description
+   * - 0x0
+     - \_\_u8
+     - e\_name\_len
+     - Length of name.
+   * - 0x1
+     - \_\_u8
+     - e\_name\_index
+     - Attribute name index. There is a discussion of this below.
+   * - 0x2
+     - \_\_le16
+     - e\_value\_offs
+     - Location of this attribute's value on the disk block where it is stored.
+       Multiple attributes can share the same value. For an inode attribute
+       this value is relative to the start of the first entry; for a block this
+       value is relative to the start of the block (i.e. the header).
+   * - 0x4
+     - \_\_le32
+     - e\_value\_inum
+     - The inode where the value is stored. Zero indicates the value is in the
+       same block as this entry. This field is only used if the
+       INCOMPAT\_EA\_INODE feature is enabled.
+   * - 0x8
+     - \_\_le32
+     - e\_value\_size
+     - Length of attribute value.
+   * - 0xC
+     - \_\_le32
+     - e\_hash
+     - Hash value of attribute name and attribute value. The kernel doesn't
+       update the hash for in-inode attributes, so for that case this value
+       must be zero, because e2fsck validates any non-zero hash regardless of
+       where the xattr lives.
+   * - 0x10
+     - char
+     - e\_name[e\_name\_len]
+     - Attribute name. Does not include trailing NULL.
+
+Attribute values can follow the end of the entry table. There appears to
+be a requirement that they be aligned to 4-byte boundaries. The values
+are stored starting at the end of the block and grow towards the
+xattr\_header/xattr\_entry table. When the two collide, the overflow is
+put into a separate disk block. If the disk block fills up, the
+filesystem returns -ENOSPC.
+
+The first four fields of the ``ext4_xattr_entry`` are set to zero to
+mark the end of the key list.
+
+Attribute Name Indices
+~~~~~~~~~~~~~~~~~~~~~~
+
+Logically speaking, extended attributes are a series of key=value pairs.
+The keys are assumed to be NULL-terminated strings. To reduce the amount
+of on-disk space that the keys consume, the beginning of the key string
+is matched against the attribute name index. If a match is found, the
+attribute name index field is set, and matching string is removed from
+the key name. Here is a map of name index values to key prefixes:
+
+.. list-table::
+   :widths: 1 79
+   :header-rows: 1
+
+   * - Name Index
+     - Key Prefix
+   * - 0
+     - (no prefix)
+   * - 1
+     - “user.”
+   * - 2
+     - “system.posix\_acl\_access”
+   * - 3
+     - “system.posix\_acl\_default”
+   * - 4
+     - “trusted.”
+   * - 6
+     - “security.”
+   * - 7
+     - “system.” (inline\_data only?)
+   * - 8
+     - “system.richacl” (SuSE kernels only?)
+
+For example, if the attribute key is “user.fubar”, the attribute name
+index is set to 1 and the “fubar” name is recorded on disk.
+
+POSIX ACLs
+~~~~~~~~~~
+
+POSIX ACLs are stored in a reduced version of the Linux kernel (and
+libacl's) internal ACL format. The key difference is that the version
+number is different (1) and the ``e_id`` field is only stored for named
+user and group ACLs.
diff --git a/Documentation/filesystems/ext4/ondisk/dynamic.rst b/Documentation/filesystems/ext4/ondisk/dynamic.rst
index f2f14822b0f5..bb0c84333341 100644
--- a/Documentation/filesystems/ext4/ondisk/dynamic.rst
+++ b/Documentation/filesystems/ext4/ondisk/dynamic.rst
@@ -9,3 +9,4 @@ allocated to files.
 .. include:: inodes.rst
 .. include:: ifork.rst
 .. include:: directory.rst
+.. include:: attributes.rst
-- 
cgit v1.2.3


From a4d2aadca184ece182418950d45ba4ffc7b652d2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 29 Jul 2018 15:48:00 -0400
Subject: ext4: sysfs: print ext4_super_block fields as little-endian

While working on extended rand for last_error/first_error timestamps,
I noticed that the endianess is wrong; we access the little-endian
fields in struct ext4_super_block as native-endian when we print them.

This adds a special case in ext4_attr_show() and ext4_attr_store()
to byteswap the superblock fields if needed.

In older kernels, this code was part of super.c, it got moved to
sysfs.c in linux-4.4.

Cc: stable@vger.kernel.org
Fixes: 52c198c6820f ("ext4: add sysfs entry showing whether the fs contains errors")
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/sysfs.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index f34da0bb8f17..b970a200f20c 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -274,8 +274,12 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 	case attr_pointer_ui:
 		if (!ptr)
 			return 0;
-		return snprintf(buf, PAGE_SIZE, "%u\n",
-				*((unsigned int *) ptr));
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			return snprintf(buf, PAGE_SIZE, "%u\n",
+					le32_to_cpup(ptr));
+		else
+			return snprintf(buf, PAGE_SIZE, "%u\n",
+					*((unsigned int *) ptr));
 	case attr_pointer_atomic:
 		if (!ptr)
 			return 0;
@@ -308,7 +312,10 @@ static ssize_t ext4_attr_store(struct kobject *kobj,
 		ret = kstrtoul(skip_spaces(buf), 0, &t);
 		if (ret)
 			return ret;
-		*((unsigned int *) ptr) = t;
+		if (a->attr_ptr == ptr_ext4_super_block_offset)
+			*((__le32 *) ptr) = cpu_to_le32(t);
+		else
+			*((unsigned int *) ptr) = t;
 		return len;
 	case attr_inode_readahead:
 		return inode_readahead_blks_store(sbi, buf, len);
-- 
cgit v1.2.3


From af123b3718592a66a24716ed4724dc214220492b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 29 Jul 2018 15:49:00 -0400
Subject: ext4: use 64-bit timestamps for mmp_time

The mmp_time field is 64 bits wide, which is good, but calling
get_seconds() results in a 32-bit value on 32-bit architectures. Using
ktime_get_real_seconds() instead returns 64 bits everywhere.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mmp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 638ad4743477..39b07c2d3384 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -147,7 +147,7 @@ static int kmmpd(void *data)
 
 	mmp_block = le64_to_cpu(es->s_mmp_block);
 	mmp = (struct mmp_struct *)(bh->b_data);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 	/*
 	 * Start with the higher mmp_check_interval and reduce it if
 	 * the MMP block is being updated on time.
@@ -165,7 +165,7 @@ static int kmmpd(void *data)
 			seq = 1;
 
 		mmp->mmp_seq = cpu_to_le32(seq);
-		mmp->mmp_time = cpu_to_le64(get_seconds());
+		mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 		last_update_time = jiffies;
 
 		retval = write_mmp_block(sb, bh);
@@ -241,7 +241,7 @@ static int kmmpd(void *data)
 	 * Unmount seems to be clean.
 	 */
 	mmp->mmp_seq = cpu_to_le32(EXT4_MMP_SEQ_CLEAN);
-	mmp->mmp_time = cpu_to_le64(get_seconds());
+	mmp->mmp_time = cpu_to_le64(ktime_get_real_seconds());
 
 	retval = write_mmp_block(sb, bh);
 
-- 
cgit v1.2.3


From 5ffff834322281f550b10c958fd9dd85679b8dbb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 29 Jul 2018 15:50:00 -0400
Subject: ext4: use ktime_get_real_seconds for i_dtime

We only care about the low 32-bit for i_dtime as explained in commit
b5f515735bea ("ext4: avoid Y2038 overflow in recently_deleted()"), so
the use of get_seconds() is correct here, but that function is getting
removed in the process of the y2038 fixes, so let's use the modern
ktime_get_real_seconds() here.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/inode.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 4efe77286ecd..ba0de19fb1ad 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -317,7 +317,7 @@ stop_handle:
 	 * (Well, we could do this if we need to, but heck - it works)
 	 */
 	ext4_orphan_del(handle, inode);
-	EXT4_I(inode)->i_dtime	= get_seconds();
+	EXT4_I(inode)->i_dtime	= (__u32)ktime_get_real_seconds();
 
 	/*
 	 * One subtle ordering requirement: if anything has gone wrong
-- 
cgit v1.2.3


From 7b62b293200ffaba5b281668ba7102cb4209774f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 29 Jul 2018 15:51:00 -0400
Subject: ext4: use timespec64 for all inode times

This is the last missing piece for the inode times on 32-bit systems:
now that VFS interfaces use timespec64, we just need to stop truncating
the tv_sec values for y2038 compatibililty.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h   | 22 +++++++++-------------
 fs/ext4/ialloc.c |  2 +-
 2 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 7c7123f265c2..1d7dac2df6e8 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -789,17 +789,16 @@ struct move_extent {
  * affected filesystem before 2242.
  */
 
-static inline __le32 ext4_encode_extra_time(struct timespec *time)
+static inline __le32 ext4_encode_extra_time(struct timespec64 *time)
 {
-	u32 extra = sizeof(time->tv_sec) > 4 ?
-		((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK : 0;
+	u32 extra =((time->tv_sec - (s32)time->tv_sec) >> 32) & EXT4_EPOCH_MASK;
 	return cpu_to_le32(extra | (time->tv_nsec << EXT4_EPOCH_BITS));
 }
 
-static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
+static inline void ext4_decode_extra_time(struct timespec64 *time,
+					  __le32 extra)
 {
-	if (unlikely(sizeof(time->tv_sec) > 4 &&
-			(extra & cpu_to_le32(EXT4_EPOCH_MASK)))) {
+	if (unlikely(extra & cpu_to_le32(EXT4_EPOCH_MASK))) {
 
 #if 1
 		/* Handle legacy encoding of pre-1970 dates with epoch
@@ -821,9 +820,8 @@ static inline void ext4_decode_extra_time(struct timespec *time, __le32 extra)
 do {										\
 	(raw_inode)->xtime = cpu_to_le32((inode)->xtime.tv_sec);		\
 	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra))     {\
-		struct timespec ts = timespec64_to_timespec((inode)->xtime);	\
 		(raw_inode)->xtime ## _extra =					\
-				ext4_encode_extra_time(&ts);			\
+				ext4_encode_extra_time(&(inode)->xtime);	\
 		}								\
 } while (0)
 
@@ -840,10 +838,8 @@ do {									       \
 do {										\
 	(inode)->xtime.tv_sec = (signed)le32_to_cpu((raw_inode)->xtime);	\
 	if (EXT4_FITS_IN_INODE(raw_inode, EXT4_I(inode), xtime ## _extra)) {	\
-		struct timespec ts = timespec64_to_timespec((inode)->xtime);	\
-		ext4_decode_extra_time(&ts,					\
+		ext4_decode_extra_time(&(inode)->xtime,				\
 				       raw_inode->xtime ## _extra);		\
-		(inode)->xtime = timespec_to_timespec64(ts);			\
 		}								\
 	else									\
 		(inode)->xtime.tv_nsec = 0;					\
@@ -993,9 +989,9 @@ struct ext4_inode_info {
 
 	/*
 	 * File creation time. Its function is same as that of
-	 * struct timespec i_{a,c,m}time in the generic inode.
+	 * struct timespec64 i_{a,c,m}time in the generic inode.
 	 */
-	struct timespec i_crtime;
+	struct timespec64 i_crtime;
 
 	/* mballoc */
 	struct list_head i_prealloc_list;
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f336cbc6e932..dffd21de2694 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1086,7 +1086,7 @@ got:
 	/* This is the optimal IO size (for stat), not the fs block size */
 	inode->i_blocks = 0;
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
-	ei->i_crtime = timespec64_to_timespec(inode->i_mtime);
+	ei->i_crtime = inode->i_mtime;
 
 	memset(ei->i_data, 0, sizeof(ei->i_data));
 	ei->i_dir_start_lookup = 0;
-- 
cgit v1.2.3


From 193736c81788556811238690ed0048af18740a8d Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Fri, 27 Jul 2018 19:54:39 +0300
Subject: net: ethernet: ti: cpsw: add missed RX_CTAG feature for second slave

Seems it was missed while adding for first net dev in dual-emac mode.

Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 171abcfb6184..1b54c26c2bec 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -3287,7 +3287,7 @@ static int cpsw_probe_dual_emac(struct cpsw_priv *priv)
 
 	priv_sl2->emac_port = 1;
 	cpsw->slaves[1].ndev = ndev;
-	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
+	ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX;
 
 	ndev->netdev_ops = &cpsw_netdev_ops;
 	ndev->ethtool_ops = &cpsw_ethtool_ops;
-- 
cgit v1.2.3


From b42d1d6b5b789c41dacbe2bc192c7b359d109d7b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 29 Jul 2018 15:51:47 -0400
Subject: jbd2: replace current_kernel_time64 with ktime equivalent

jbd2 is one of the few callers of current_kernel_time64(), which
is a wrapper around ktime_get_coarse_real_ts64(). This calls the
latter directly for consistency with the rest of the kernel that
is moving to the ktime_get_ family of time accessors.

Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/jbd2/commit.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8de0e7723316..150cc030b4d7 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -121,7 +121,7 @@ static int journal_submit_commit_record(journal_t *journal,
 	struct commit_header *tmp;
 	struct buffer_head *bh;
 	int ret;
-	struct timespec64 now = current_kernel_time64();
+	struct timespec64 now;
 
 	*cbh = NULL;
 
@@ -134,6 +134,7 @@ static int journal_submit_commit_record(journal_t *journal,
 		return 1;
 
 	tmp = (struct commit_header *)bh->b_data;
+	ktime_get_coarse_real_ts64(&now);
 	tmp->h_commit_sec = cpu_to_be64(now.tv_sec);
 	tmp->h_commit_nsec = cpu_to_be32(now.tv_nsec);
 
-- 
cgit v1.2.3


From 6a0678a79bb3a4e5fc1b680e7afc78727e21aff3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Sun, 29 Jul 2018 15:51:48 -0400
Subject: ext4: super: extend timestamps to 40 bits

The inode timestamps use 34 bits in ext4, but the various timestamps in
the superblock are limited to 32 bits. If every user accesses these as
'unsigned', then this is good until year 2106, but it seems better to
extend this a bit further in the process of removing the deprecated
get_seconds() function.

This adds another byte for each timestamp in the superblock, making
them long enough to store timestamps beyond what is in the inodes,
which seems good enough here (in ocfs2, they are already 64-bit wide,
which is appropriate for a new layout).

I did not modify e2fsprogs, which obviously needs the same change to
actually interpret future timestamps correctly.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/ext4.h  |  9 ++++++++-
 fs/ext4/super.c | 39 ++++++++++++++++++++++++++++++---------
 fs/ext4/sysfs.c | 19 +++++++++++++++++--
 3 files changed, 55 insertions(+), 12 deletions(-)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 1d7dac2df6e8..6d7dec48372b 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -1295,7 +1295,14 @@ struct ext4_super_block {
 	__le32	s_lpf_ino;		/* Location of the lost+found inode */
 	__le32	s_prj_quota_inum;	/* inode for tracking project quota */
 	__le32	s_checksum_seed;	/* crc32c(uuid) if csum_seed set */
-	__le32	s_reserved[98];		/* Padding to the end of the block */
+	__u8	s_wtime_hi;
+	__u8	s_mtime_hi;
+	__u8	s_mkfs_time_hi;
+	__u8	s_lastcheck_hi;
+	__u8	s_first_error_time_hi;
+	__u8	s_last_error_time_hi;
+	__u8	s_pad[2];
+	__le32	s_reserved[96];		/* Padding to the end of the block */
 	__le32	s_checksum;		/* crc32c(superblock) */
 };
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index b7f7922061be..67f4310edd0a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -312,6 +312,24 @@ void ext4_itable_unused_set(struct super_block *sb,
 		bg->bg_itable_unused_hi = cpu_to_le16(count >> 16);
 }
 
+static void __ext4_update_tstamp(__le32 *lo, __u8 *hi)
+{
+	time64_t now = ktime_get_real_seconds();
+
+	now = clamp_val(now, 0, (1ull << 40) - 1);
+
+	*lo = cpu_to_le32(lower_32_bits(now));
+	*hi = upper_32_bits(now);
+}
+
+static time64_t __ext4_get_tstamp(__le32 *lo, __u8 *hi)
+{
+	return ((time64_t)(*hi) << 32) + le32_to_cpu(*lo);
+}
+#define ext4_update_tstamp(es, tstamp) \
+	__ext4_update_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
+#define ext4_get_tstamp(es, tstamp) \
+	__ext4_get_tstamp(&(es)->tstamp, &(es)->tstamp ## _hi)
 
 static void __save_error_info(struct super_block *sb, const char *func,
 			    unsigned int line)
@@ -322,11 +340,12 @@ static void __save_error_info(struct super_block *sb, const char *func,
 	if (bdev_read_only(sb->s_bdev))
 		return;
 	es->s_state |= cpu_to_le16(EXT4_ERROR_FS);
-	es->s_last_error_time = cpu_to_le32(get_seconds());
+	ext4_update_tstamp(es, s_last_error_time);
 	strncpy(es->s_last_error_func, func, sizeof(es->s_last_error_func));
 	es->s_last_error_line = cpu_to_le32(line);
 	if (!es->s_first_error_time) {
 		es->s_first_error_time = es->s_last_error_time;
+		es->s_first_error_time_hi = es->s_last_error_time_hi;
 		strncpy(es->s_first_error_func, func,
 			sizeof(es->s_first_error_func));
 		es->s_first_error_line = cpu_to_le32(line);
@@ -2174,8 +2193,8 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 			 "warning: maximal mount count reached, "
 			 "running e2fsck is recommended");
 	else if (le32_to_cpu(es->s_checkinterval) &&
-		(le32_to_cpu(es->s_lastcheck) +
-			le32_to_cpu(es->s_checkinterval) <= get_seconds()))
+		 (ext4_get_tstamp(es, s_lastcheck) +
+		  le32_to_cpu(es->s_checkinterval) <= ktime_get_real_seconds()))
 		ext4_msg(sb, KERN_WARNING,
 			 "warning: checktime reached, "
 			 "running e2fsck is recommended");
@@ -2184,7 +2203,7 @@ static int ext4_setup_super(struct super_block *sb, struct ext4_super_block *es,
 	if (!(__s16) le16_to_cpu(es->s_max_mnt_count))
 		es->s_max_mnt_count = cpu_to_le16(EXT4_DFL_MAX_MNT_COUNT);
 	le16_add_cpu(&es->s_mnt_count, 1);
-	es->s_mtime = cpu_to_le32(get_seconds());
+	ext4_update_tstamp(es, s_mtime);
 	ext4_update_dynamic_rev(sb);
 	if (sbi->s_journal)
 		ext4_set_feature_journal_needs_recovery(sb);
@@ -2875,8 +2894,9 @@ static void print_daily_error_info(struct timer_list *t)
 		ext4_msg(sb, KERN_NOTICE, "error count since last fsck: %u",
 			 le32_to_cpu(es->s_error_count));
 	if (es->s_first_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %u: %.*s:%d",
-		       sb->s_id, le32_to_cpu(es->s_first_error_time),
+		printk(KERN_NOTICE "EXT4-fs (%s): initial error at time %llu: %.*s:%d",
+		       sb->s_id,
+		       ext4_get_tstamp(es, s_first_error_time),
 		       (int) sizeof(es->s_first_error_func),
 		       es->s_first_error_func,
 		       le32_to_cpu(es->s_first_error_line));
@@ -2889,8 +2909,9 @@ static void print_daily_error_info(struct timer_list *t)
 		printk(KERN_CONT "\n");
 	}
 	if (es->s_last_error_time) {
-		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %u: %.*s:%d",
-		       sb->s_id, le32_to_cpu(es->s_last_error_time),
+		printk(KERN_NOTICE "EXT4-fs (%s): last error at time %llu: %.*s:%d",
+		       sb->s_id,
+		       ext4_get_tstamp(es, s_last_error_time),
 		       (int) sizeof(es->s_last_error_func),
 		       es->s_last_error_func,
 		       le32_to_cpu(es->s_last_error_line));
@@ -4813,7 +4834,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	 * to complain and force a full file system check.
 	 */
 	if (!(sb->s_flags & SB_RDONLY))
-		es->s_wtime = cpu_to_le32(get_seconds());
+		ext4_update_tstamp(es, s_wtime);
 	if (sb->s_bdev->bd_part)
 		es->s_kbytes_written =
 			cpu_to_le64(EXT4_SB(sb)->s_kbytes_written +
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index b970a200f20c..e60cc5e89023 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -25,6 +25,8 @@ typedef enum {
 	attr_reserved_clusters,
 	attr_inode_readahead,
 	attr_trigger_test_error,
+	attr_first_error_time,
+	attr_last_error_time,
 	attr_feature,
 	attr_pointer_ui,
 	attr_pointer_atomic,
@@ -182,8 +184,8 @@ EXT4_RW_ATTR_SBI_UI(warning_ratelimit_burst, s_warning_ratelimit_state.burst);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_interval_ms, s_msg_ratelimit_state.interval);
 EXT4_RW_ATTR_SBI_UI(msg_ratelimit_burst, s_msg_ratelimit_state.burst);
 EXT4_RO_ATTR_ES_UI(errors_count, s_error_count);
-EXT4_RO_ATTR_ES_UI(first_error_time, s_first_error_time);
-EXT4_RO_ATTR_ES_UI(last_error_time, s_last_error_time);
+EXT4_ATTR(first_error_time, 0444, first_error_time);
+EXT4_ATTR(last_error_time, 0444, last_error_time);
 
 static unsigned int old_bump_val = 128;
 EXT4_ATTR_PTR(max_writeback_mb_bump, 0444, pointer_ui, &old_bump_val);
@@ -249,6 +251,15 @@ static void *calc_ptr(struct ext4_attr *a, struct ext4_sb_info *sbi)
 	return NULL;
 }
 
+static ssize_t __print_tstamp(char *buf, __le32 lo, __u8 hi)
+{
+	return snprintf(buf, PAGE_SIZE, "%lld",
+			((time64_t)hi << 32) + le32_to_cpu(lo));
+}
+
+#define print_tstamp(buf, es, tstamp) \
+	__print_tstamp(buf, (es)->tstamp, (es)->tstamp ## _hi)
+
 static ssize_t ext4_attr_show(struct kobject *kobj,
 			      struct attribute *attr, char *buf)
 {
@@ -287,6 +298,10 @@ static ssize_t ext4_attr_show(struct kobject *kobj,
 				atomic_read((atomic_t *) ptr));
 	case attr_feature:
 		return snprintf(buf, PAGE_SIZE, "supported\n");
+	case attr_first_error_time:
+		return print_tstamp(buf, sbi->s_es, s_first_error_time);
+	case attr_last_error_time:
+		return print_tstamp(buf, sbi->s_es, s_last_error_time);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 7f144fd046d967ff2fbba59203b42b888ad5aae7 Mon Sep 17 00:00:00 2001
From: Junichi Uekawa <uekawa@google.com>
Date: Sun, 29 Jul 2018 15:51:52 -0400
Subject: ext4: fix warning message in ext4_enable_quotas()

Output the warning message before we clobber type and be -1 all the time.
The error message would now be

[    1.519791] EXT4-fs warning (device vdb): ext4_enable_quotas:5402:
Failed to enable quota tracking (type=0, err=-3). Please run e2fsck to fix.

Signed-off-by: Junichi Uekawa <uekawa@google.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
---
 fs/ext4/super.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 67f4310edd0a..3e64d8d51ac4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5686,13 +5686,13 @@ static int ext4_enable_quotas(struct super_block *sb)
 				DQUOT_USAGE_ENABLED |
 				(quota_mopt[type] ? DQUOT_LIMITS_ENABLED : 0));
 			if (err) {
-				for (type--; type >= 0; type--)
-					dquot_quota_off(sb, type);
-
 				ext4_warning(sb,
 					"Failed to enable quota tracking "
 					"(type=%d, err=%d). Please run "
 					"e2fsck to fix.", type, err);
+				for (type--; type >= 0; type--)
+					dquot_quota_off(sb, type);
+
 				return err;
 			}
 		}
-- 
cgit v1.2.3


From 21ac738ede0b49004b53b4a44fe3df7bb4a78280 Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Sun, 29 Jul 2018 15:51:54 -0400
Subject: ext4: check allocation failure when duplicating "data" in
 ext4_remount()

There is no check for allocation failure when duplicating
"data" in ext4_remount(). Check for failure and return
error -ENOMEM in this case.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
---
 fs/ext4/super.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 3e64d8d51ac4..d4a218ba626c 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -5101,6 +5101,9 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 #endif
 	char *orig_data = kstrdup(data, GFP_KERNEL);
 
+	if (data && !orig_data)
+		return -ENOMEM;
+
 	/* Store the original options */
 	old_sb_flags = sb->s_flags;
 	old_opts.s_mount_opt = sbi->s_mount_opt;
-- 
cgit v1.2.3


From 4b09384aaa2a9b2ac09a584d7a9345cf003617f2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 27 Jul 2018 13:11:00 -0700
Subject: net: dcb: add DSCP to comment about priority selector types

Commit ee2059819450 ("net/dcb: Add dscp to priority selector type")
added a define for the new DSCP selector type created by
IEEE 802.1Qcd, but missed the comment enumerating all selector types.
Update the comment.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/dcbnl.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/dcbnl.h b/include/uapi/linux/dcbnl.h
index 60aa2e446698..69df19aa8e72 100644
--- a/include/uapi/linux/dcbnl.h
+++ b/include/uapi/linux/dcbnl.h
@@ -233,7 +233,8 @@ struct cee_pfc {
  *	2	Well known port number over TCP or SCTP
  *	3	Well known port number over UDP or DCCP
  *	4	Well known port number over TCP, SCTP, UDP, or DCCP
- *	5-7	Reserved
+ *	5	Differentiated Services Code Point (DSCP) value
+ *	6-7	Reserved
  *
  *  Selector field values for CEE
  *	0	Ethertype
-- 
cgit v1.2.3


From 40bb5d725e797ea140e5f83822bf2b5328a2d47f Mon Sep 17 00:00:00 2001
From: Morten Hein Tiljeset <morten.tiljeset@prevas.dk>
Date: Mon, 16 Jul 2018 14:43:39 +0200
Subject: gpio-pisosr: add support for get_multiple

Signed-off-by: Morten Hein Tiljeset <morten.tiljeset@prevas.dk>
Reviewed-by: Sean Nyekjaer <sean.nyekjaer@prevas.dk>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-pisosr.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/gpio/gpio-pisosr.c b/drivers/gpio/gpio-pisosr.c
index f5545049c187..f809a5a8e9eb 100644
--- a/drivers/gpio/gpio-pisosr.c
+++ b/drivers/gpio/gpio-pisosr.c
@@ -12,6 +12,8 @@
  * GNU General Public License version 2 for more details.
  */
 
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/gpio/driver.h>
@@ -90,6 +92,25 @@ static int pisosr_gpio_get(struct gpio_chip *chip, unsigned offset)
 	return (gpio->buffer[offset / 8] >> (offset % 8)) & 0x1;
 }
 
+static int pisosr_gpio_get_multiple(struct gpio_chip *chip,
+				    unsigned long *mask, unsigned long *bits)
+{
+	struct pisosr_gpio *gpio = gpiochip_get_data(chip);
+	unsigned int nbytes = DIV_ROUND_UP(chip->ngpio, 8);
+	unsigned int i, j;
+
+	pisosr_gpio_refresh(gpio);
+
+	bitmap_zero(bits, chip->ngpio);
+	for (i = 0; i < nbytes; i++) {
+		j = i / sizeof(unsigned long);
+		bits[j] |= ((unsigned long) gpio->buffer[i])
+			   << (8 * (i % sizeof(unsigned long)));
+	}
+
+	return 0;
+}
+
 static const struct gpio_chip template_chip = {
 	.label			= "pisosr-gpio",
 	.owner			= THIS_MODULE,
@@ -97,6 +118,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= pisosr_gpio_direction_input,
 	.direction_output	= pisosr_gpio_direction_output,
 	.get			= pisosr_gpio_get,
+	.get_multiple		= pisosr_gpio_get_multiple,
 	.base			= -1,
 	.ngpio			= DEFAULT_NGPIO,
 	.can_sleep		= true,
-- 
cgit v1.2.3


From 3260155ac784ae9f4889c6d3e40b85f33e94d098 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 27 Jul 2018 13:43:21 -0700
Subject: failover: change mtu has RTNL

When changing MTU, RTNL is held so use rtnl_dereference
instead of rcu_dereference.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/net_failover.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index d00d42c845b7..7ae1856d1f18 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -220,14 +220,14 @@ static int net_failover_change_mtu(struct net_device *dev, int new_mtu)
 	struct net_device *primary_dev, *standby_dev;
 	int ret = 0;
 
-	primary_dev = rcu_dereference(nfo_info->primary_dev);
+	primary_dev = rtnl_dereference(nfo_info->primary_dev);
 	if (primary_dev) {
 		ret = dev_set_mtu(primary_dev, new_mtu);
 		if (ret)
 			return ret;
 	}
 
-	standby_dev = rcu_dereference(nfo_info->standby_dev);
+	standby_dev = rtnl_dereference(nfo_info->standby_dev);
 	if (standby_dev) {
 		ret = dev_set_mtu(standby_dev, new_mtu);
 		if (ret) {
-- 
cgit v1.2.3


From 3e7a50ceb11ea75c27e944f1a01e478fd62a2d8d Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 27 Jul 2018 13:43:22 -0700
Subject: net: report min and max mtu network device settings

Report the minimum and maximum MTU allowed on a device
via netlink so that it can be displayed by tools like
ip link.

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/if_link.h | 2 ++
 net/core/rtnetlink.c         | 6 ++++++
 2 files changed, 8 insertions(+)

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 553c438cabe3..43391e2d1153 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -164,6 +164,8 @@ enum {
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
 	IFLA_NEW_IFINDEX,
+	IFLA_MIN_MTU,
+	IFLA_MAX_MTU,
 	__IFLA_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 92b6fa5d5f6e..510d4f765a13 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1015,6 +1015,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4)  /* IFLA_IF_NETNSID */
 	       + nla_total_size(4)  /* IFLA_CARRIER_UP_COUNT */
 	       + nla_total_size(4)  /* IFLA_CARRIER_DOWN_COUNT */
+	       + nla_total_size(4)  /* IFLA_MIN_MTU */
+	       + nla_total_size(4)  /* IFLA_MAX_MTU */
 	       + 0;
 }
 
@@ -1601,6 +1603,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 		       netif_running(dev) ? dev->operstate : IF_OPER_DOWN) ||
 	    nla_put_u8(skb, IFLA_LINKMODE, dev->link_mode) ||
 	    nla_put_u32(skb, IFLA_MTU, dev->mtu) ||
+	    nla_put_u32(skb, IFLA_MIN_MTU, dev->min_mtu) ||
+	    nla_put_u32(skb, IFLA_MAX_MTU, dev->max_mtu) ||
 	    nla_put_u32(skb, IFLA_GROUP, dev->group) ||
 	    nla_put_u32(skb, IFLA_PROMISCUITY, dev->promiscuity) ||
 	    nla_put_u32(skb, IFLA_NUM_TX_QUEUES, dev->num_tx_queues) ||
@@ -1732,6 +1736,8 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_IF_NETNSID]	= { .type = NLA_S32 },
 	[IFLA_CARRIER_UP_COUNT]	= { .type = NLA_U32 },
 	[IFLA_CARRIER_DOWN_COUNT] = { .type = NLA_U32 },
+	[IFLA_MIN_MTU]		= { .type = NLA_U32 },
+	[IFLA_MAX_MTU]		= { .type = NLA_U32 },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
-- 
cgit v1.2.3


From 7a4c53bee3324ac00bf964aa2f82d15d279e86e4 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Fri, 27 Jul 2018 13:43:23 -0700
Subject: net: report invalid mtu value via netlink extack

If an invalid MTU value is set through rtnetlink return extra error
information instead of putting message in kernel log. For other cases
where there is no visible API, keep the error report in the log.

Example:
	# ip li set dev enp12s0 mtu 10000
	Error: mtu greater than device maximum.

	# ifconfig enp12s0 mtu 10000
	SIOCSIFMTU: Invalid argument
	# dmesg | tail -1
	[ 2047.795467] enp12s0: mtu greater than device maximum

Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  2 ++
 net/core/dev.c            | 23 +++++++++++++++++------
 net/core/rtnetlink.c      |  2 +-
 3 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c1295c7a452e..9c917467a2c7 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3546,6 +3546,8 @@ int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int dev_change_net_namespace(struct net_device *, struct net *, const char *);
 int __dev_set_mtu(struct net_device *, int);
+int dev_set_mtu_ext(struct net_device *dev, int mtu,
+		    struct netlink_ext_ack *extack);
 int dev_set_mtu(struct net_device *, int);
 int dev_change_tx_queue_len(struct net_device *, unsigned long);
 void dev_set_group(struct net_device *, int);
diff --git a/net/core/dev.c b/net/core/dev.c
index 87c42c8249ae..89031b5fef9f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7523,13 +7523,15 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 EXPORT_SYMBOL(__dev_set_mtu);
 
 /**
- *	dev_set_mtu - Change maximum transfer unit
+ *	dev_set_mtu_ext - Change maximum transfer unit
  *	@dev: device
  *	@new_mtu: new transfer unit
+ *	@extack: netlink extended ack
  *
  *	Change the maximum transfer size of the network device.
  */
-int dev_set_mtu(struct net_device *dev, int new_mtu)
+int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
+		    struct netlink_ext_ack *extack)
 {
 	int err, orig_mtu;
 
@@ -7538,14 +7540,12 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 
 	/* MTU must be positive, and in range */
 	if (new_mtu < 0 || new_mtu < dev->min_mtu) {
-		net_err_ratelimited("%s: Invalid MTU %d requested, hw min %d\n",
-				    dev->name, new_mtu, dev->min_mtu);
+		NL_SET_ERR_MSG(extack, "mtu less than device minimum");
 		return -EINVAL;
 	}
 
 	if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) {
-		net_err_ratelimited("%s: Invalid MTU %d requested, hw max %d\n",
-				    dev->name, new_mtu, dev->max_mtu);
+		NL_SET_ERR_MSG(extack, "mtu greater than device maximum");
 		return -EINVAL;
 	}
 
@@ -7573,6 +7573,17 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 	}
 	return err;
 }
+
+int dev_set_mtu(struct net_device *dev, int new_mtu)
+{
+	struct netlink_ext_ack extack;
+	int err;
+
+	err = dev_set_mtu_ext(dev, new_mtu, &extack);
+	if (err)
+		net_err_ratelimited("%s: %s\n", dev->name, extack._msg);
+	return err;
+}
 EXPORT_SYMBOL(dev_set_mtu);
 
 /**
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 510d4f765a13..24431e578310 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2382,7 +2382,7 @@ static int do_setlink(const struct sk_buff *skb,
 	}
 
 	if (tb[IFLA_MTU]) {
-		err = dev_set_mtu(dev, nla_get_u32(tb[IFLA_MTU]));
+		err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
 		if (err < 0)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
-- 
cgit v1.2.3


From eef6ab8b7d3223e2ecd02a02f17523e93faba709 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sat, 28 Jul 2018 00:48:13 +0200
Subject: selftests: mlxsw: qos_dscp_bridge: Fix

There are two problems in this test case:

- When indexing in bash associative array, the subscript is interpreted as
  string, not as a variable name to be expanded.

- The keys stored to t0s and t1s are not DSCP values, but priority +
  base (i.e. the logical DSCP value, not the full bitfield value).

In combination these two bugs conspire to make the test just work,
except it doesn't really test anything and always passes.

Fix the above two problems in obvious manner.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
index 418319f19108..cc527660a022 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
@@ -217,13 +217,13 @@ dscp_ping_test()
 
 	for key in ${!t0s[@]}; do
 		local expect
-		if ((key == dscp_10 || key == dscp_20)); then
+		if ((key == prio+10 || key == prio+20)); then
 			expect=10
 		else
 			expect=0
 		fi
 
-		local delta=$((t1s[key] - t0s[key]))
+		local delta=$((t1s[$key] - t0s[$key]))
 		((expect == delta))
 		check_err $? "DSCP $key: Expected to capture $expect packets, got $delta."
 	done
-- 
cgit v1.2.3


From 3b8283f007cbf09eee64804606af23af5f734d54 Mon Sep 17 00:00:00 2001
From: Alexandre Torgue <alexandre.torgue@st.com>
Date: Mon, 16 Jul 2018 14:57:36 +0200
Subject: pinctrl: stm32: fix bank io port number

In case the exti line is not in line with the bank number (that is the case
when there is an hole between two banks, for example GPIOK and then GPIOZ),
use "st,bank-ioport" DT property to get the right exti line.

Signed-off-by: Amelie Delaunay <amelie.delaunay@st.com>
Signed-off-by: Alexandre Torgue <alexandre.torgue@st.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt | 2 ++
 drivers/pinctrl/stm32/pinctrl-stm32.c                          | 9 ++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
index 9a06e1fdbc42..60c678a4c994 100644
--- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
@@ -55,6 +55,8 @@ Optional properties:
    NOTE: If "gpio-ranges" is used for a gpio controller, all gpio-controller
    have to use a "gpio-ranges" entry.
    More details in Documentation/devicetree/bindings/gpio/gpio.txt.
+ - st,bank-ioport: should correspond to the EXTI IOport selection (EXTI line
+   used to select GPIOs as interrupts).
 
 Example 1:
 #include <dt-bindings/pinctrl/stm32f429-pinfunc.h>
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index dfed60982a8a..eb6ae1462f4e 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -73,6 +73,7 @@ struct stm32_gpio_bank {
 	struct fwnode_handle *fwnode;
 	struct irq_domain *domain;
 	u32 bank_nr;
+	u32 bank_ioport_nr;
 };
 
 struct stm32_pinctrl {
@@ -298,7 +299,7 @@ static int stm32_gpio_domain_activate(struct irq_domain *d,
 	struct stm32_gpio_bank *bank = d->host_data;
 	struct stm32_pinctrl *pctl = dev_get_drvdata(bank->gpio_chip.parent);
 
-	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_nr);
+	regmap_field_write(pctl->irqmux[irq_data->hwirq], bank->bank_ioport_nr);
 	return 0;
 }
 
@@ -948,6 +949,7 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 	struct device_node *np)
 {
 	struct stm32_gpio_bank *bank = &pctl->banks[pctl->nbanks];
+	int bank_ioport_nr;
 	struct pinctrl_gpio_range *range = &bank->range;
 	struct of_phandle_args args;
 	struct device *dev = pctl->dev;
@@ -998,12 +1000,17 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl,
 		pinctrl_add_gpio_range(pctl->pctl_dev,
 				       &pctl->banks[bank_nr].range);
 	}
+
+	if (of_property_read_u32(np, "st,bank-ioport", &bank_ioport_nr))
+		bank_ioport_nr = bank_nr;
+
 	bank->gpio_chip.base = bank_nr * STM32_GPIO_PINS_PER_BANK;
 
 	bank->gpio_chip.ngpio = npins;
 	bank->gpio_chip.of_node = np;
 	bank->gpio_chip.parent = dev;
 	bank->bank_nr = bank_nr;
+	bank->bank_ioport_nr = bank_ioport_nr;
 	spin_lock_init(&bank->lock);
 
 	/* create irq hierarchical domain */
-- 
cgit v1.2.3


From 17cf082d6d0d1a662f4ff62608c18d3956b85bf6 Mon Sep 17 00:00:00 2001
From: Alexandre Torgue <alexandre.torgue@st.com>
Date: Mon, 16 Jul 2018 14:57:37 +0200
Subject: pinctrl: stm32: check node status before new gpio bank registering

Register a new GPIO bank only if GPIO bank node is enabled. This patch also
adds checks on ranges which are defined only if a bank is registered.

Signed-off-by: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/stm32/pinctrl-stm32.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index eb6ae1462f4e..111225ec075c 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -639,6 +639,11 @@ static int stm32_pmx_set_mux(struct pinctrl_dev *pctldev,
 	}
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, g->pin);
+	if (!range) {
+		dev_err(pctl->dev, "No gpio range defined.\n");
+		return -EINVAL;
+	}
+
 	bank = gpiochip_get_data(range->gc);
 	pin = stm32_gpio_pin(g->pin);
 
@@ -807,11 +812,17 @@ static int stm32_pconf_parse_conf(struct pinctrl_dev *pctldev,
 		unsigned int pin, enum pin_config_param param,
 		enum pin_config_param arg)
 {
+	struct stm32_pinctrl *pctl = pinctrl_dev_get_drvdata(pctldev);
 	struct pinctrl_gpio_range *range;
 	struct stm32_gpio_bank *bank;
 	int offset, ret = 0;
 
 	range = pinctrl_find_gpio_range_from_pin(pctldev, pin);
+	if (!range) {
+		dev_err(pctl->dev, "No gpio range defined.\n");
+		return -EINVAL;
+	}
+
 	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
@@ -893,6 +904,9 @@ static void stm32_pconf_dbg_show(struct pinctrl_dev *pctldev,
 	bool val;
 
 	range = pinctrl_find_gpio_range_from_pin_nolock(pctldev, pin);
+	if (!range)
+		return;
+
 	bank = gpiochip_get_data(range->gc);
 	offset = stm32_gpio_pin(pin);
 
@@ -1173,7 +1187,7 @@ int stm32_pctl_probe(struct platform_device *pdev)
 		return PTR_ERR(pctl->pctl_dev);
 	}
 
-	for_each_child_of_node(np, child)
+	for_each_available_child_of_node(np, child)
 		if (of_property_read_bool(child, "gpio-controller"))
 			banks++;
 
@@ -1186,7 +1200,7 @@ int stm32_pctl_probe(struct platform_device *pdev)
 	if (!pctl->banks)
 		return -ENOMEM;
 
-	for_each_child_of_node(np, child) {
+	for_each_available_child_of_node(np, child) {
 		if (of_property_read_bool(child, "gpio-controller")) {
 			ret = stm32_gpiolib_register_bank(pctl, child);
 			if (ret)
-- 
cgit v1.2.3


From d1753390274f7760e5b593cb657ea34f0617e559 Mon Sep 17 00:00:00 2001
From: Tyler Hicks <tyhicks@canonical.com>
Date: Fri, 27 Jul 2018 21:33:27 +0000
Subject: sysfs: Fix regression when adding a file to an existing group

Commit 5f81880d5204 ("sysfs, kobject: allow creating kobject belonging
to arbitrary users") incorrectly changed the argument passed as the
parent parameter when calling sysfs_add_file_mode_ns(). This caused some
sysfs attribute files to not be added correctly to certain groups.

Fixes: 5f81880d5204 ("sysfs, kobject: allow creating kobject belonging to arbitrary users")
Signed-off-by: Tyler Hicks <tyhicks@canonical.com>
Reported-by: Heiner Kallweit <hkallweit1@gmail.com>
Tested-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/sysfs/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index fa46216523cf..052e5ad9a4d2 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -373,7 +373,7 @@ int sysfs_add_file_to_group(struct kobject *kobj,
 		return -ENOENT;
 
 	kobject_get_ownership(kobj, &uid, &gid);
-	error = sysfs_add_file_mode_ns(kobj->sd, attr, false,
+	error = sysfs_add_file_mode_ns(parent, attr, false,
 				       attr->mode, uid, gid, NULL);
 	kernfs_put(parent);
 
-- 
cgit v1.2.3


From 62bbdd9974678513fee113f09f6b672623521179 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sun, 29 Jul 2018 16:11:59 -0400
Subject: ext4: use swap macro in mext_page_double_lock

Make use of the swap macro and remove unnecessary variable *tmp*.
This makes the code easier to read and maintain.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/move_extent.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 8e17efdcbf11..a409ff70d67b 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -134,9 +134,7 @@ mext_page_double_lock(struct inode *inode1, struct inode *inode2,
 		mapping[0] = inode1->i_mapping;
 		mapping[1] = inode2->i_mapping;
 	} else {
-		pgoff_t tmp = index1;
-		index1 = index2;
-		index2 = tmp;
+		swap(index1, index2);
 		mapping[0] = inode2->i_mapping;
 		mapping[1] = inode1->i_mapping;
 	}
-- 
cgit v1.2.3


From de1d08b229746fc650c56ce7ddff34b1c8e778df Mon Sep 17 00:00:00 2001
From: Ludovic Barre <ludovic.barre@st.com>
Date: Tue, 17 Jul 2018 11:56:26 +0200
Subject: dt-bindings: pinctrl: add syscfg mask parameter

This patch adds mask parameter to define IRQ mux field.
This field could vary depend of IRQ mux selection register.
This parameter is needed if the mask is different of 0xf.

Signed-off-by: Ludovic Barre <ludovic.barre@st.com>
Acked-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
index 60c678a4c994..046a3de026d4 100644
--- a/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
+++ b/Documentation/devicetree/bindings/pinctrl/st,stm32-pinctrl.txt
@@ -39,9 +39,10 @@ Optional properties:
  - reset:	  : Reference to the reset controller
  - interrupt-parent: phandle of the interrupt parent to which the external
    GPIO interrupts are forwarded to.
- - st,syscfg: Should be phandle/offset pair. The phandle to the syscon node
-   which includes IRQ mux selection register, and the offset of the IRQ mux
-   selection register.
+ - st,syscfg: Should be phandle/offset/mask.
+	-The phandle to the syscon node which includes IRQ mux selection register.
+	-The offset of the IRQ mux selection register
+	-The field mask of IRQ mux, needed if different of 0xf.
  - gpio-ranges: Define a dedicated mapping between a pin-controller and
    a gpio controller. Format is <&phandle a b c> with:
 	-(phandle): phandle of pin-controller.
-- 
cgit v1.2.3


From 6684874af0637c63f4c91e8c2120c64e6e8bb79e Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 16:14:02 -0400
Subject: docs: create filesystem internal section

Create a new top-level section for documentation of filesystem usage,
on-disk format information, and anything else.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/index.rst |  6 +++---
 Documentation/filesystems/index.rst      |  8 --------
 Documentation/index.rst                  | 11 +++++++++++
 3 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/Documentation/filesystems/ext4/index.rst b/Documentation/filesystems/ext4/index.rst
index 8fe4f7693e8c..71121605558c 100644
--- a/Documentation/filesystems/ext4/index.rst
+++ b/Documentation/filesystems/ext4/index.rst
@@ -1,8 +1,8 @@
 .. SPDX-License-Identifier: GPL-2.0
 
-====
-ext4
-====
+===============
+ext4 Filesystem
+===============
 
 General usage and on-disk artifacts writen by ext4.  More documentation may
 be ported from the wiki as time permits.  This should be considered the
diff --git a/Documentation/filesystems/index.rst b/Documentation/filesystems/index.rst
index 7c57b3927308..53b89d0edc15 100644
--- a/Documentation/filesystems/index.rst
+++ b/Documentation/filesystems/index.rst
@@ -2,14 +2,6 @@
 Linux Filesystems API
 =====================
 
-The documentation in this section are provided by specific filesystem
-subprojects.
-
-.. toctree::
-   :maxdepth: 2
-
-   ext4/index
-
 The Linux VFS
 =============
 
diff --git a/Documentation/index.rst b/Documentation/index.rst
index fdc585703498..65c22b1ff5f2 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -102,6 +102,17 @@ implementation.
 
    sh/index
 
+Filesystem Documentation
+------------------------
+
+The documentation in this section are provided by specific filesystem
+subprojects.
+
+.. toctree::
+   :maxdepth: 4
+
+   filesystems/ext4/index
+
 Korean translations
 -------------------
 
-- 
cgit v1.2.3


From 2e25a9cbdf8cc300baa8f5eb5130152a6c25dd0a Mon Sep 17 00:00:00 2001
From: Ludovic Barre <ludovic.barre@st.com>
Date: Tue, 17 Jul 2018 11:56:27 +0200
Subject: pinctrl: stm32: add syscfg mask parameter

This patch adds mask parameter to define IRQ mux field.
This field could vary depend of IRQ mux selection register.
To avoid backward compatibility, the drivers set
the legacy value by default.

Signed-off-by: Ludovic Barre <ludovic.barre@st.com>
Acked-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/stm32/pinctrl-stm32.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index 111225ec075c..a9bec6e6fdd1 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -46,6 +46,8 @@
 #define STM32_GPIO_PINS_PER_BANK 16
 #define STM32_GPIO_IRQ_LINE	 16
 
+#define SYSCFG_IRQMUX_MASK GENMASK(3, 0)
+
 #define gpio_range_to_bank(chip) \
 		container_of(chip, struct stm32_gpio_bank, range)
 
@@ -1054,6 +1056,7 @@ static int stm32_pctrl_dt_setup_irq(struct platform_device *pdev,
 	struct device *dev = &pdev->dev;
 	struct regmap *rm;
 	int offset, ret, i;
+	int mask, mask_width;
 
 	parent = of_irq_find_parent(np);
 	if (!parent)
@@ -1073,12 +1076,21 @@ static int stm32_pctrl_dt_setup_irq(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
+	ret = of_property_read_u32_index(np, "st,syscfg", 2, &mask);
+	if (ret)
+		mask = SYSCFG_IRQMUX_MASK;
+
+	mask_width = fls(mask);
+
 	for (i = 0; i < STM32_GPIO_PINS_PER_BANK; i++) {
 		struct reg_field mux;
 
 		mux.reg = offset + (i / 4) * 4;
-		mux.lsb = (i % 4) * 4;
-		mux.msb = mux.lsb + 3;
+		mux.lsb = (i % 4) * mask_width;
+		mux.msb = mux.lsb + mask_width - 1;
+
+		dev_dbg(dev, "irqmux%d: reg:%#x, lsb:%d, msb:%d\n",
+			i, mux.reg, mux.lsb, mux.msb);
 
 		pctl->irqmux[i] = devm_regmap_field_alloc(dev, rm, mux);
 		if (IS_ERR(pctl->irqmux[i]))
-- 
cgit v1.2.3


From 6c21da204a90ceca73096bf1b91c4fdf43308c16 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Sat, 28 Jul 2018 13:35:55 +0800
Subject: net-next: mediatek: improve more with using dma_zalloc_coherent

Improve more in the existing code by reusing dma_zalloc_coherent instead
of dma_alloc_coherent with __GFP_ZERO or superfluous zeroing buffer.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index c30aea2ab767..8c85a4b4d6c5 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -605,10 +605,10 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	dma_addr_t dma_addr;
 	int i;
 
-	eth->scratch_ring = dma_alloc_coherent(eth->dev,
-					       cnt * sizeof(struct mtk_tx_dma),
-					       &eth->phy_scratch_ring,
-					       GFP_ATOMIC | __GFP_ZERO);
+	eth->scratch_ring = dma_zalloc_coherent(eth->dev,
+						cnt * sizeof(struct mtk_tx_dma),
+						&eth->phy_scratch_ring,
+						GFP_ATOMIC);
 	if (unlikely(!eth->scratch_ring))
 		return -ENOMEM;
 
@@ -623,7 +623,6 @@ static int mtk_init_fq_dma(struct mtk_eth *eth)
 	if (unlikely(dma_mapping_error(eth->dev, dma_addr)))
 		return -ENOMEM;
 
-	memset(eth->scratch_ring, 0x0, sizeof(struct mtk_tx_dma) * cnt);
 	phy_ring_tail = eth->phy_scratch_ring +
 			(sizeof(struct mtk_tx_dma) * (cnt - 1));
 
@@ -1318,10 +1317,9 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag)
 			return -ENOMEM;
 	}
 
-	ring->dma = dma_alloc_coherent(eth->dev,
-				       rx_dma_size * sizeof(*ring->dma),
-				       &ring->phys,
-				       GFP_ATOMIC | __GFP_ZERO);
+	ring->dma = dma_zalloc_coherent(eth->dev,
+					rx_dma_size * sizeof(*ring->dma),
+					&ring->phys, GFP_ATOMIC);
 	if (!ring->dma)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From 2d14ba7228b0c2e43e97bd37be8bcf3b71725fff Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Sat, 28 Jul 2018 13:35:56 +0800
Subject: net-next: mediatek: cleanup unnecessary get chip id and its user

Since driver is devicetree-based, all device type and charateristic can be
determined by the compatible string and its data. It's unnecessary to
create another dependent function to check chip ID and then decide whether
the specific funciton is being supported on a certain device. It can be
totally replaced by the existing flag, so a cleanup is made by removing
the function and the only user, HWLRO.

MT2701 also have a missing HWLRO support in old code, so add it the same
patch.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 48 +++--------------------------
 drivers/net/ethernet/mediatek/mtk_eth_soc.h |  2 +-
 2 files changed, 5 insertions(+), 45 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 8c85a4b4d6c5..6e6abdc399de 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2458,42 +2458,6 @@ free_netdev:
 	return err;
 }
 
-static int mtk_get_chip_id(struct mtk_eth *eth, u32 *chip_id)
-{
-	u32 val[2], id[4];
-
-	regmap_read(eth->ethsys, ETHSYS_CHIPID0_3, &val[0]);
-	regmap_read(eth->ethsys, ETHSYS_CHIPID4_7, &val[1]);
-
-	id[3] = ((val[0] >> 16) & 0xff) - '0';
-	id[2] = ((val[0] >> 24) & 0xff) - '0';
-	id[1] = (val[1] & 0xff) - '0';
-	id[0] = ((val[1] >> 8) & 0xff) - '0';
-
-	*chip_id = (id[3] * 1000) + (id[2] * 100) +
-		   (id[1] * 10) + id[0];
-
-	if (!(*chip_id)) {
-		dev_err(eth->dev, "failed to get chip id\n");
-		return -ENODEV;
-	}
-
-	dev_info(eth->dev, "chip id = %d\n", *chip_id);
-
-	return 0;
-}
-
-static bool mtk_is_hwlro_supported(struct mtk_eth *eth)
-{
-	switch (eth->chip_id) {
-	case MT7622_ETH:
-	case MT7623_ETH:
-		return true;
-	}
-
-	return false;
-}
-
 static int mtk_probe(struct platform_device *pdev)
 {
 	struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
@@ -2572,11 +2536,7 @@ static int mtk_probe(struct platform_device *pdev)
 	if (err)
 		return err;
 
-	err = mtk_get_chip_id(eth, &eth->chip_id);
-	if (err)
-		return err;
-
-	eth->hwlro = mtk_is_hwlro_supported(eth);
+	eth->hwlro = MTK_HAS_CAPS(eth->soc->caps, MTK_HWLRO);
 
 	for_each_child_of_node(pdev->dev.of_node, mac_np) {
 		if (!of_device_is_compatible(mac_np,
@@ -2665,19 +2625,19 @@ static int mtk_remove(struct platform_device *pdev)
 }
 
 static const struct mtk_soc_data mt2701_data = {
-	.caps = MTK_GMAC1_TRGMII,
+	.caps = MTK_GMAC1_TRGMII | MTK_HWLRO,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 };
 
 static const struct mtk_soc_data mt7622_data = {
-	.caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW,
+	.caps = MTK_DUAL_GMAC_SHARED_SGMII | MTK_GMAC1_ESW | MTK_HWLRO,
 	.required_clks = MT7622_CLKS_BITMAP,
 	.required_pctl = false,
 };
 
 static const struct mtk_soc_data mt7623_data = {
-	.caps = MTK_GMAC1_TRGMII,
+	.caps = MTK_GMAC1_TRGMII | MTK_HWLRO,
 	.required_clks = MT7623_CLKS_BITMAP,
 	.required_pctl = true,
 };
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 672b8c353c47..46819297fc3e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -566,6 +566,7 @@ struct mtk_rx_ring {
 #define MTK_GMAC2_SGMII			(BIT(10) | MTK_SGMII)
 #define MTK_DUAL_GMAC_SHARED_SGMII	(BIT(11) | MTK_GMAC1_SGMII | \
 					 MTK_GMAC2_SGMII)
+#define MTK_HWLRO			BIT(12)
 #define MTK_HAS_CAPS(caps, _x)		(((caps) & (_x)) == (_x))
 
 /* struct mtk_eth_data -	This is the structure holding all differences
@@ -635,7 +636,6 @@ struct mtk_eth {
 	struct regmap			*ethsys;
 	struct regmap			*sgmiisys;
 	struct regmap			*pctl;
-	u32				chip_id;
 	bool				hwlro;
 	refcount_t			dma_refcnt;
 	struct mtk_tx_ring		tx_ring;
-- 
cgit v1.2.3


From f5cb282d8b08c05ad70ebde9a8fd2decf32a6406 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 16:16:21 -0400
Subject: docs: add new ext4 superblock time extension fields

The superblock timestamp fields were enlarged by u8 to be 40 bits wide.
Update the documentation to reflect this.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ondisk/super.rst | 32 +++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/ext4/ondisk/super.rst b/Documentation/filesystems/ext4/ondisk/super.rst
index 1f5ac9ab6f0c..5f81dd87e0b9 100644
--- a/Documentation/filesystems/ext4/ondisk/super.rst
+++ b/Documentation/filesystems/ext4/ondisk/super.rst
@@ -442,8 +442,36 @@ The ext4 superblock is laid out as follows in
      - Checksum seed used for metadata\_csum calculations. This value is
        crc32c(~0, $orig\_fs\_uuid).
    * - 0x274
-     - \_\_le32
-     - s\_reserved[98]
+     - \_\_u8
+     - s\_wtime_hi
+     - Upper 8 bits of the s_wtime field.
+   * - 0x275
+     - \_\_u8
+     - s\_wtime_hi
+     - Upper 8 bits of the s_mtime field.
+   * - 0x276
+     - \_\_u8
+     - s\_mkfs_time_hi
+     - Upper 8 bits of the s_mkfs_time field.
+   * - 0x277
+     - \_\_u8
+     - s\_lastcheck_hi
+     - Upper 8 bits of the s_lastcheck_hi field.
+   * - 0x278
+     - \_\_u8
+     - s\_first_error_time_hi
+     - Upper 8 bits of the s_first_error_time_hi field.
+   * - 0x279
+     - \_\_u8
+     - s\_last_error_time_hi
+     - Upper 8 bits of the s_last_error_time_hi field.
+   * - 0x27A
+     - \_\_u8[2]
+     - s\_pad
+     - Zero padding.
+   * - 0x27C
+     - \_\_le32
+     - s\_reserved[96]
      - Padding to the end of the block.
    * - 0x3FC
      - \_\_le32
-- 
cgit v1.2.3


From b23641fe731f035a6071a654fd64309fa2f12208 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 28 Jul 2018 18:23:36 +0800
Subject: qed: remove redundant functions qed_get_cm_pq_idx_rl

There are no in-tree callers of qed_get_cm_pq_idx_rl since it be there,
so it can be removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index e5249b4741d0..37817b3e8fa3 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -507,16 +507,6 @@ u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
 	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
 }
 
-u16 qed_get_cm_pq_idx_rl(struct qed_hwfn *p_hwfn, u8 rl)
-{
-	u16 max_rl = qed_init_qm_get_num_pf_rls(p_hwfn);
-
-	if (rl > max_rl)
-		DP_ERR(p_hwfn, "rl %d must be smaller than %d\n", rl, max_rl);
-
-	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_RLS) + rl;
-}
-
 /* Functions for creating specific types of pqs */
 static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn)
 {
-- 
cgit v1.2.3


From 0a80848ec5cc1294984e648b9a71aecf69c4bb73 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 28 Jul 2018 18:29:01 +0800
Subject: act_pedit: remove unnecessary semicolon

net/sched/act_pedit.c:289:2-3: Unneeded semicolon

Remove unneeded semicolon.

Generated by: scripts/coccinelle/misc/semicolon.cocci

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 9ab5d81aff1a..43ba999b2d23 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -286,7 +286,7 @@ static int pedit_skb_hdr_offset(struct sk_buff *skb,
 	default:
 		ret = -EINVAL;
 		break;
-	};
+	}
 
 	return ret;
 }
-- 
cgit v1.2.3


From f9562fa4a5750d097f4468c0a7fc9a4e0d2dfdc3 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 28 Jul 2018 18:35:15 +0800
Subject: cls_bpf: Use kmemdup instead of duplicating it in
 cls_bpf_prog_from_ops

Replace calls to kmalloc followed by a memcpy with a direct call to
kmemdup.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_bpf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c
index 66e0ac9811f9..fa6fe2fe0f32 100644
--- a/net/sched/cls_bpf.c
+++ b/net/sched/cls_bpf.c
@@ -349,12 +349,10 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog)
 	if (bpf_size != nla_len(tb[TCA_BPF_OPS]))
 		return -EINVAL;
 
-	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	bpf_ops = kmemdup(nla_data(tb[TCA_BPF_OPS]), bpf_size, GFP_KERNEL);
 	if (bpf_ops == NULL)
 		return -ENOMEM;
 
-	memcpy(bpf_ops, nla_data(tb[TCA_BPF_OPS]), bpf_size);
-
 	fprog_tmp.len = bpf_num_ops;
 	fprog_tmp.filter = bpf_ops;
 
-- 
cgit v1.2.3


From 1766e4b7047acf44cdd15aaeb1d63ed76ee78492 Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 16 Jul 2018 19:07:41 -0600
Subject: pinctrl/amd: fix gpio irq level in debugfs

According to the AMD BKDG, the GPIO ActiveLevel bits (10:9) map to:
 00 Active High
 01 Active Low
 10 Active on both edges iff LevelTrig (bit 8) == 0
 11 Reserved

The current code has a bug where it interprets 00 => Active Low, and
01 => Active High.

Fix the bug, restrict "Active on both" to just the edge trigger case, and
refactor a bit to make the logic more readable.

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-amd.c | 14 +++++++-------
 drivers/pinctrl/pinctrl-amd.h |  4 ++++
 2 files changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 04ae139671c8..5df5e8d64c57 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -247,16 +247,16 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc)
 			raw_spin_unlock_irqrestore(&gpio_dev->lock, flags);
 
 			if (pin_reg & BIT(INTERRUPT_ENABLE_OFF)) {
+				u8 level = (pin_reg >> ACTIVE_LEVEL_OFF) &
+						ACTIVE_LEVEL_MASK;
 				interrupt_enable = "interrupt is enabled|";
 
-				if (!(pin_reg & BIT(ACTIVE_LEVEL_OFF)) &&
-				    !(pin_reg & BIT(ACTIVE_LEVEL_OFF + 1)))
-					active_level = "Active low|";
-				else if (pin_reg & BIT(ACTIVE_LEVEL_OFF) &&
-					 !(pin_reg & BIT(ACTIVE_LEVEL_OFF + 1)))
+				if (level == ACTIVE_LEVEL_HIGH)
 					active_level = "Active high|";
-				else if (!(pin_reg & BIT(ACTIVE_LEVEL_OFF)) &&
-					 pin_reg & BIT(ACTIVE_LEVEL_OFF + 1))
+				else if (level == ACTIVE_LEVEL_LOW)
+					active_level = "Active low|";
+				else if (!(pin_reg & BIT(LEVEL_TRIG_OFF)) &&
+					 level == ACTIVE_LEVEL_BOTH)
 					active_level = "Active on both|";
 				else
 					active_level = "Unknown Active level|";
diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h
index 8fa453a59da5..22af7edfdb38 100644
--- a/drivers/pinctrl/pinctrl-amd.h
+++ b/drivers/pinctrl/pinctrl-amd.h
@@ -54,6 +54,10 @@
 #define ACTIVE_LEVEL_MASK	0x3UL
 #define DRV_STRENGTH_SEL_MASK	0x3UL
 
+#define ACTIVE_LEVEL_HIGH	0x0UL
+#define ACTIVE_LEVEL_LOW	0x1UL
+#define ACTIVE_LEVEL_BOTH	0x2UL
+
 #define DB_TYPE_NO_DEBOUNCE               0x0UL
 #define DB_TYPE_PRESERVE_LOW_GLITCH       0x1UL
 #define DB_TYPE_PRESERVE_HIGH_GLITCH      0x2UL
-- 
cgit v1.2.3


From 3f6bcc5162a1ba4e99e867364919168c1d821308 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Sat, 28 Jul 2018 18:38:06 +0800
Subject: act_bpf: Use kmemdup instead of duplicating it in
 tcf_bpf_init_from_ops

Replace calls to kmalloc followed by a memcpy with a direct call to
kmemdup.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 06f743d8ed41..6203eb075c9a 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -196,12 +196,10 @@ static int tcf_bpf_init_from_ops(struct nlattr **tb, struct tcf_bpf_cfg *cfg)
 	if (bpf_size != nla_len(tb[TCA_ACT_BPF_OPS]))
 		return -EINVAL;
 
-	bpf_ops = kzalloc(bpf_size, GFP_KERNEL);
+	bpf_ops = kmemdup(nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size, GFP_KERNEL);
 	if (bpf_ops == NULL)
 		return -ENOMEM;
 
-	memcpy(bpf_ops, nla_data(tb[TCA_ACT_BPF_OPS]), bpf_size);
-
 	fprog_tmp.len = bpf_num_ops;
 	fprog_tmp.filter = bpf_ops;
 
-- 
cgit v1.2.3


From c19fdaeea0aa1938cf6a35aa97f9ea6fd8b22476 Mon Sep 17 00:00:00 2001
From: Anson Huang <Anson.Huang@nxp.com>
Date: Wed, 18 Jul 2018 09:25:32 +0800
Subject: gpio: mxc: add power management support

GPIO registers could lose context on i.MX7D, when
enter LPSR mode, the whole SoC will be powered off
except LPSR domain, GPIO banks will lose context
in this case, need to restore the context after
resume from LPSR mode.

This patch adds new compatible string for i.MX7D
which supports GPIO power off feature in suspend,
and adds the GPIO save/restore operations in noirq
suspend/resume phase, since GPIO is fundamental
module which could be used by other peripherals'
resume phase.

Signed-off-by: Anson Huang <Anson.Huang@nxp.com>
Reviewed-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-mxc.c | 73 +++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 73 insertions(+)

diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index 2f2829966d4c..995cf0b9e0b1 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -45,6 +45,15 @@ struct mxc_gpio_hwdata {
 	unsigned fall_edge;
 };
 
+struct mxc_gpio_reg_saved {
+	u32 icr1;
+	u32 icr2;
+	u32 imr;
+	u32 gdir;
+	u32 edge_sel;
+	u32 dr;
+};
+
 struct mxc_gpio_port {
 	struct list_head node;
 	void __iomem *base;
@@ -55,6 +64,8 @@ struct mxc_gpio_port {
 	struct gpio_chip gc;
 	struct device *dev;
 	u32 both_edges;
+	struct mxc_gpio_reg_saved gpio_saved_reg;
+	bool power_off;
 };
 
 static struct mxc_gpio_hwdata imx1_imx21_gpio_hwdata = {
@@ -143,6 +154,7 @@ static const struct of_device_id mxc_gpio_dt_ids[] = {
 	{ .compatible = "fsl,imx21-gpio", .data = &mxc_gpio_devtype[IMX21_GPIO], },
 	{ .compatible = "fsl,imx31-gpio", .data = &mxc_gpio_devtype[IMX31_GPIO], },
 	{ .compatible = "fsl,imx35-gpio", .data = &mxc_gpio_devtype[IMX35_GPIO], },
+	{ .compatible = "fsl,imx7d-gpio", .data = &mxc_gpio_devtype[IMX35_GPIO], },
 	{ /* sentinel */ }
 };
 
@@ -434,6 +446,9 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 		return err;
 	}
 
+	if (of_device_is_compatible(np, "fsl,imx7d-gpio"))
+		port->power_off = true;
+
 	/* disable the interrupt and clear the status */
 	writel(0, port->base + GPIO_IMR);
 	writel(~0, port->base + GPIO_ISR);
@@ -497,6 +512,8 @@ static int mxc_gpio_probe(struct platform_device *pdev)
 
 	list_add_tail(&port->node, &mxc_gpio_ports);
 
+	platform_set_drvdata(pdev, port);
+
 	return 0;
 
 out_irqdomain_remove:
@@ -507,11 +524,67 @@ out_bgio:
 	return err;
 }
 
+static void mxc_gpio_save_regs(struct mxc_gpio_port *port)
+{
+	if (!port->power_off)
+		return;
+
+	port->gpio_saved_reg.icr1 = readl(port->base + GPIO_ICR1);
+	port->gpio_saved_reg.icr2 = readl(port->base + GPIO_ICR2);
+	port->gpio_saved_reg.imr = readl(port->base + GPIO_IMR);
+	port->gpio_saved_reg.gdir = readl(port->base + GPIO_GDIR);
+	port->gpio_saved_reg.edge_sel = readl(port->base + GPIO_EDGE_SEL);
+	port->gpio_saved_reg.dr = readl(port->base + GPIO_DR);
+}
+
+static void mxc_gpio_restore_regs(struct mxc_gpio_port *port)
+{
+	if (!port->power_off)
+		return;
+
+	writel(port->gpio_saved_reg.icr1, port->base + GPIO_ICR1);
+	writel(port->gpio_saved_reg.icr2, port->base + GPIO_ICR2);
+	writel(port->gpio_saved_reg.imr, port->base + GPIO_IMR);
+	writel(port->gpio_saved_reg.gdir, port->base + GPIO_GDIR);
+	writel(port->gpio_saved_reg.edge_sel, port->base + GPIO_EDGE_SEL);
+	writel(port->gpio_saved_reg.dr, port->base + GPIO_DR);
+}
+
+static int __maybe_unused mxc_gpio_noirq_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct mxc_gpio_port *port = platform_get_drvdata(pdev);
+
+	mxc_gpio_save_regs(port);
+	clk_disable_unprepare(port->clk);
+
+	return 0;
+}
+
+static int __maybe_unused mxc_gpio_noirq_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct mxc_gpio_port *port = platform_get_drvdata(pdev);
+	int ret;
+
+	ret = clk_prepare_enable(port->clk);
+	if (ret)
+		return ret;
+	mxc_gpio_restore_regs(port);
+
+	return 0;
+}
+
+static const struct dev_pm_ops mxc_gpio_dev_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mxc_gpio_noirq_suspend, mxc_gpio_noirq_resume)
+};
+
 static struct platform_driver mxc_gpio_driver = {
 	.driver		= {
 		.name	= "gpio-mxc",
 		.of_match_table = mxc_gpio_dt_ids,
 		.suppress_bind_attrs = true,
+		.pm = &mxc_gpio_dev_pm_ops,
 	},
 	.probe		= mxc_gpio_probe,
 	.id_table	= mxc_gpio_devtype,
-- 
cgit v1.2.3


From 0694f8c39f113bcdb759a7f84981a69bf5d7161d Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Sun, 29 Jul 2018 16:35:23 -0400
Subject: docs: fix up the obviously obsolete bits in the new ext4
 documentation

Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 Documentation/filesystems/ext4/ext4.rst | 47 ++++++---------------------------
 Documentation/index.rst                 |  2 +-
 2 files changed, 9 insertions(+), 40 deletions(-)

diff --git a/Documentation/filesystems/ext4/ext4.rst b/Documentation/filesystems/ext4/ext4.rst
index 47f614c47f56..9d4368d591fa 100644
--- a/Documentation/filesystems/ext4/ext4.rst
+++ b/Documentation/filesystems/ext4/ext4.rst
@@ -20,43 +20,32 @@ Note: More extensive information for getting started with ext4 can be
 found at the ext4 wiki site at the URL:
 http://ext4.wiki.kernel.org/index.php/Ext4_Howto
 
-  - Compile and install the latest version of e2fsprogs (as of this
-    writing version 1.41.3) from:
+  - The latest version of e2fsprogs can be found at:
 
-    http://sourceforge.net/project/showfiles.php?group_id=2406
+    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
 
 	or
 
-    https://www.kernel.org/pub/linux/kernel/people/tytso/e2fsprogs/
+    http://sourceforge.net/project/showfiles.php?group_id=2406
 
 	or grab the latest git repository from:
 
-    git://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
-
-  - Note that it is highly important to install the mke2fs.conf file
-    that comes with the e2fsprogs 1.41.x sources in /etc/mke2fs.conf. If
-    you have edited the /etc/mke2fs.conf file installed on your system,
-    you will need to merge your changes with the version from e2fsprogs
-    1.41.x.
+   https://git.kernel.org/pub/scm/fs/ext2/e2fsprogs.git
 
-  - Create a new filesystem using the ext4 filesystem type:::
+  - Create a new filesystem using the ext4 filesystem type:
 
         # mke2fs -t ext4 /dev/hda1
 
-    Or to configure an existing ext3 filesystem to support extents:::
+    Or to configure an existing ext3 filesystem to support extents:
 
 	# tune2fs -O extents /dev/hda1
 
     If the filesystem was created with 128 byte inodes, it can be
-    converted to use 256 byte for greater efficiency via:::
+    converted to use 256 byte for greater efficiency via:
 
         # tune2fs -I 256 /dev/hda1
 
-    (Note: we currently do not have tools to convert an ext4
-    filesystem back to ext3; so please do not do try this on production
-    filesystems.)
-
-  - Mounting:::
+  - Mounting:
 
 	# mount -t ext4 /dev/hda1 /wherever
 
@@ -106,26 +95,6 @@ Currently Available
 [1] Filesystems with a block size of 1k may see a limit imposed by the
 directory hash tree having a maximum depth of two.
 
-Candidate Features for Future Inclusion
----------------------------------------
-
-* online defrag (patches available but not well tested)
-* reduced mke2fs time via lazy itable initialization in conjunction with
-  the uninit_bg feature (capability to do this is available in e2fsprogs
-  but a kernel thread to do lazy zeroing of unused inode table blocks
-  after filesystem is first mounted is required for safety)
-
-There are several others under discussion, whether they all make it in is
-partly a function of how much time everyone has to work on them. Features like
-metadata checksumming have been discussed and planned for a bit but no patches
-exist yet so I'm not sure they're in the near-term roadmap.
-
-The big performance win will come with mballoc, delalloc and flex_bg
-grouping of bitmaps and inode tables.  Some test results available here:
-
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-write-2.6.27-rc1.html
- - http://www.bullopensource.org/ext4/20080818-ffsb/ffsb-readwrite-2.6.27-rc1.html
-
 Options
 =======
 
diff --git a/Documentation/index.rst b/Documentation/index.rst
index 65c22b1ff5f2..f95ba981f8cd 100644
--- a/Documentation/index.rst
+++ b/Documentation/index.rst
@@ -109,7 +109,7 @@ The documentation in this section are provided by specific filesystem
 subprojects.
 
 .. toctree::
-   :maxdepth: 4
+   :maxdepth: 2
 
    filesystems/ext4/index
 
-- 
cgit v1.2.3


From f78709a5d4114edc21a5d86586ed5e56e284f2bd Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Tue, 17 Jul 2018 19:10:38 +0300
Subject: gpio: tegra: Fix tegra_gpio_irq_set_type()

Commit 36b312792b97 ("gpiolib: Respect error code of ->get_direction()")
broke tegra_gpio_irq_set_type() because requesting of GPIO direction must
be done after enabling GPIO function for a pin.

This patch fixes drivers probe failure like this:

 gpio gpiochip0: (tegra-gpio): gpiochip_lock_as_irq: cannot get GPIO direction
 tegra-gpio 6000d000.gpio: unable to lock Tegra GPIO 144 as IRQ

Fixes: 36b312792b97 ("gpiolib: Respect error code of ->get_direction()")
Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Tested-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tegra.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 94396caaca75..22e7c99ed69e 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -323,13 +323,6 @@ static int tegra_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 		return -EINVAL;
 	}
 
-	ret = gpiochip_lock_as_irq(&tgi->gc, gpio);
-	if (ret) {
-		dev_err(tgi->dev,
-			"unable to lock Tegra GPIO %u as IRQ\n", gpio);
-		return ret;
-	}
-
 	spin_lock_irqsave(&bank->lvl_lock[port], flags);
 
 	val = tegra_gpio_readl(tgi, GPIO_INT_LVL(tgi, gpio));
@@ -342,6 +335,14 @@ static int tegra_gpio_irq_set_type(struct irq_data *d, unsigned int type)
 	tegra_gpio_mask_write(tgi, GPIO_MSK_OE(tgi, gpio), gpio, 0);
 	tegra_gpio_enable(tgi, gpio);
 
+	ret = gpiochip_lock_as_irq(&tgi->gc, gpio);
+	if (ret) {
+		dev_err(tgi->dev,
+			"unable to lock Tegra GPIO %u as IRQ\n", gpio);
+		tegra_gpio_disable(tgi, gpio);
+		return ret;
+	}
+
 	if (type & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 		irq_set_handler_locked(d, handle_level_irq);
 	else if (type & (IRQ_TYPE_EDGE_FALLING | IRQ_TYPE_EDGE_RISING))
-- 
cgit v1.2.3


From 8bbed1eef001fdfc0ee9595f64cc4f769d265af4 Mon Sep 17 00:00:00 2001
From: Daniel Kurtz <djkurtz@chromium.org>
Date: Mon, 16 Jul 2018 18:57:18 -0600
Subject: pinctrl/amd: only handle irq if it is pending and unmasked

The AMD pinctrl driver demultiplexes GPIO interrupts and fires off their
individual handlers.

If one of these GPIO irqs is configured as a level interrupt, and its
downstream handler is a threaded ONESHOT interrupt, the GPIO interrupt
source is masked by handle_level_irq() until the eventual return of the
threaded irq handler.  During this time the level GPIO interrupt status
will still report as high until the actual gpio source is cleared - both
in the individual GPIO interrupt status bit (INTERRUPT_STS_OFF) and in
its corresponding "WAKE_INT_STATUS_REG" bit.

Thus, if another GPIO interrupt occurs during this time,
amd_gpio_irq_handler() will see that the (masked-and-not-yet-cleared)
level irq is still pending and incorrectly call its handler again.

To fix this, have amd_gpio_irq_handler() check for both interrupts status
and mask before calling generic_handle_irq().

Note: Is it possible that this bug was the source of the interrupt storm
on Ryzen when using chained interrupts before commit ba714a9c1dea85
("pinctrl/amd: Use regular interrupt instead of chained")?

Signed-off-by: Daniel Kurtz <djkurtz@chromium.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-amd.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 5df5e8d64c57..41ccc759b8b8 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -552,7 +552,8 @@ static irqreturn_t amd_gpio_irq_handler(int irq, void *dev_id)
 		/* Each status bit covers four pins */
 		for (i = 0; i < 4; i++) {
 			regval = readl(regs + i);
-			if (!(regval & PIN_IRQ_PENDING))
+			if (!(regval & PIN_IRQ_PENDING) ||
+			    !(regval & BIT(INTERRUPT_MASK_OFF)))
 				continue;
 			irq = irq_find_mapping(gc->irq.domain, irqnr + i);
 			generic_handle_irq(irq);
-- 
cgit v1.2.3


From 1777fc97302997f016b720fea9c4d0e1ad858f56 Mon Sep 17 00:00:00 2001
From: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Date: Fri, 20 Jul 2018 09:54:49 +0200
Subject: gpiolib: probe deferral error reporting

Actually report the error code from devm_regulator_get() which may as
well just be a probe deferral.

This is e.g. what one gets upon booting a Colibri T20:

gpiochip_add_data_with_key: GPIOs 0..223 (tegra-gpio) failed to register

Signed-off-by: Marcel Ziswiler <marcel.ziswiler@toradex.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 464d5ba79f96..bdbfc95793e7 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1414,9 +1414,9 @@ err_free_descs:
 err_free_gdev:
 	ida_simple_remove(&gpio_ida, gdev->id);
 	/* failures here can mean systems won't boot... */
-	pr_err("%s: GPIOs %d..%d (%s) failed to register\n", __func__,
+	pr_err("%s: GPIOs %d..%d (%s) failed to register, %d\n", __func__,
 	       gdev->base, gdev->base + gdev->ngpio - 1,
-	       chip->label ? : "generic");
+	       chip->label ? : "generic", status);
 	kfree(gdev);
 	return status;
 }
-- 
cgit v1.2.3


From cdbf8897cb09b7baf2b8a7e78051a35a872b01d5 Mon Sep 17 00:00:00 2001
From: Ross Zwisler <ross.zwisler@linux.intel.com>
Date: Sun, 29 Jul 2018 16:59:16 -0400
Subject: dax: dax_layout_busy_page() warn on !exceptional

Inodes using DAX should only ever have exceptional entries in their page
caches.  Make this clear by warning if the iteration in
dax_layout_busy_page() ever sees a non-exceptional entry, and by adding a
comment for the pagevec_release() call which only deals with struct page
pointers.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
---
 fs/dax.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/fs/dax.c b/fs/dax.c
index 641192808bb6..897b51e41d8f 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -566,7 +566,8 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (index >= end)
 				break;
 
-			if (!radix_tree_exceptional_entry(pvec_ent))
+			if (WARN_ON_ONCE(
+			     !radix_tree_exceptional_entry(pvec_ent)))
 				continue;
 
 			xa_lock_irq(&mapping->i_pages);
@@ -578,6 +579,13 @@ struct page *dax_layout_busy_page(struct address_space *mapping)
 			if (page)
 				break;
 		}
+
+		/*
+		 * We don't expect normal struct page entries to exist in our
+		 * tree, but we keep these pagevec calls so that this code is
+		 * consistent with the common pattern for handling pagevecs
+		 * throughout the kernel.
+		 */
 		pagevec_remove_exceptionals(&pvec);
 		pagevec_release(&pvec);
 		index++;
-- 
cgit v1.2.3


From 430657b6be896db57d974375cc499ca212c7f01d Mon Sep 17 00:00:00 2001
From: Ross Zwisler <ross.zwisler@linux.intel.com>
Date: Sun, 29 Jul 2018 17:00:22 -0400
Subject: ext4: handle layout changes to pinned DAX mappings

Follow the lead of xfs_break_dax_layouts() and add synchronization between
operations in ext4 which remove blocks from an inode (hole punch, truncate
down, etc.) and pages which are pinned due to DAX DMA operations.

Signed-off-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Lukas Czerner <lczerner@redhat.com>
---
 fs/ext4/ext4.h     |  1 +
 fs/ext4/extents.c  | 17 +++++++++++++++++
 fs/ext4/inode.c    | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/ext4/truncate.h |  4 ++++
 4 files changed, 68 insertions(+)

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 6d7dec48372b..1fc013f3d944 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -2459,6 +2459,7 @@ extern int ext4_get_inode_loc(struct inode *, struct ext4_iloc *);
 extern int ext4_inode_attach_jinode(struct inode *inode);
 extern int ext4_can_truncate(struct inode *inode);
 extern int ext4_truncate(struct inode *);
+extern int ext4_break_layouts(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
 extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 8ce6fd5b10dd..72a361d5ef74 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -4826,6 +4826,13 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 		 * released from page cache.
 		 */
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		ret = ext4_break_layouts(inode);
+		if (ret) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			goto out_mutex;
+		}
+
 		ret = ext4_update_disksize_before_punch(inode, offset, len);
 		if (ret) {
 			up_write(&EXT4_I(inode)->i_mmap_sem);
@@ -5499,6 +5506,11 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down offset to be aligned with page size boundary
 	 * for page size > block size.
@@ -5647,6 +5659,11 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_mmap;
+
 	/*
 	 * Need to round down to align start offset to page size boundary
 	 * for page size > block size.
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index ba0de19fb1ad..60432498acfb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4191,6 +4191,39 @@ int ext4_update_disksize_before_punch(struct inode *inode, loff_t offset,
 	return 0;
 }
 
+static void ext4_wait_dax_page(struct ext4_inode_info *ei, bool *did_unlock)
+{
+	*did_unlock = true;
+	up_write(&ei->i_mmap_sem);
+	schedule();
+	down_write(&ei->i_mmap_sem);
+}
+
+int ext4_break_layouts(struct inode *inode)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	struct page *page;
+	bool retry;
+	int error;
+
+	if (WARN_ON_ONCE(!rwsem_is_locked(&ei->i_mmap_sem)))
+		return -EINVAL;
+
+	do {
+		retry = false;
+		page = dax_layout_busy_page(inode->i_mapping);
+		if (!page)
+			return 0;
+
+		error = ___wait_var_event(&page->_refcount,
+				atomic_read(&page->_refcount) == 1,
+				TASK_INTERRUPTIBLE, 0, 0,
+				ext4_wait_dax_page(ei, &retry));
+	} while (error == 0 && retry);
+
+	return error;
+}
+
 /*
  * ext4_punch_hole: punches a hole in a file by releasing the blocks
  * associated with the given offset and length
@@ -4264,6 +4297,11 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 	 * page cache.
 	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_break_layouts(inode);
+	if (ret)
+		goto out_dio;
+
 	first_block_offset = round_up(offset, sb->s_blocksize);
 	last_block_offset = round_down((offset + length), sb->s_blocksize) - 1;
 
@@ -5553,6 +5591,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 				ext4_wait_for_tail_page_commit(inode);
 		}
 		down_write(&EXT4_I(inode)->i_mmap_sem);
+
+		rc = ext4_break_layouts(inode);
+		if (rc) {
+			up_write(&EXT4_I(inode)->i_mmap_sem);
+			error = rc;
+			goto err_out;
+		}
+
 		/*
 		 * Truncate pagecache after we've waited for commit
 		 * in data=journal mode to make pages freeable.
diff --git a/fs/ext4/truncate.h b/fs/ext4/truncate.h
index 0cb13badf473..bcbe3668c1d4 100644
--- a/fs/ext4/truncate.h
+++ b/fs/ext4/truncate.h
@@ -11,6 +11,10 @@
  */
 static inline void ext4_truncate_failed_write(struct inode *inode)
 {
+	/*
+	 * We don't need to call ext4_break_layouts() because the blocks we
+	 * are truncating were never visible to userspace.
+	 */
 	down_write(&EXT4_I(inode)->i_mmap_sem);
 	truncate_inode_pages(inode->i_mapping, inode->i_size);
 	ext4_truncate(inode);
-- 
cgit v1.2.3


From 4bf4eed44bfe288f459496eaf38089502ef91a79 Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Mon, 23 Jul 2018 19:53:30 +0300
Subject: gpio: ml-ioh: Fix buffer underwrite on probe error path

If ioh_gpio_probe() fails on devm_irq_alloc_descs() then chip may point
to any element of chip_save array, so reverse iteration from pointer chip
may become chip_save[-1] and gpiochip_remove() will operate with wrong
memory.

The patch fix the error path of ioh_gpio_probe() to correctly bypass
chip_save array.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-ml-ioh.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c
index b23d9a36be1f..51c7d1b84c2e 100644
--- a/drivers/gpio/gpio-ml-ioh.c
+++ b/drivers/gpio/gpio-ml-ioh.c
@@ -496,9 +496,10 @@ static int ioh_gpio_probe(struct pci_dev *pdev,
 	return 0;
 
 err_gpiochip_add:
+	chip = chip_save;
 	while (--i >= 0) {
-		chip--;
 		gpiochip_remove(&chip->gpio);
+		chip++;
 	}
 	kfree(chip_save);
 
-- 
cgit v1.2.3


From f39b3f45dbcb0343822cce31ea7636ad66e60bc2 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Sun, 29 Jul 2018 17:13:42 -0400
Subject: ext4: reset error code in ext4_find_entry in fallback

When ext4_find_entry() falls back to "searching the old fashioned
way" due to a corrupt dx dir, it needs to reset the error code
to NULL so that the nonstandard ERR_BAD_DX_DIR code isn't returned
to userspace.

https://bugzilla.kernel.org/show_bug.cgi?id=199947

Reported-by: Anatoly Trosinenko <anatoly.trosinenko@yandex.com>
Reviewed-by: Andreas Dilger <adilger@dilger.ca>
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/namei.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 2a4c25c4681d..116ff68c5bd4 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1398,6 +1398,7 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 			goto cleanup_and_exit;
 		dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
 			       "falling back\n"));
+		ret = NULL;
 	}
 	nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
 	if (!nblocks) {
-- 
cgit v1.2.3


From a8cfcf15c91455750ecb5213ad1cbe5d9b3ec2ef Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 24 Jul 2018 13:57:10 +0200
Subject: pinctrl: mediatek: include chained_irq.h header

Some randconfig builds fail in the mtk-eint driver:

drivers/pinctrl/mediatek/mtk-eint.c: In function 'mtk_eint_irq_handler':
drivers/pinctrl/mediatek/mtk-eint.c:324:2: error: implicit declaration of function 'chained_irq_enter'; did you mean 'rcu_irq_enter'? [-Werror=implicit-function-declaration]
  chained_irq_enter(chip, desc);
  ^~~~~~~~~~~~~~~~~
  rcu_irq_enter
drivers/pinctrl/mediatek/mtk-eint.c:367:2: error: implicit declaration of function 'chained_irq_exit'; did you mean 'rcu_irq_exit'? [-Werror=implicit-function-declaration]

The functions are declared in linux/irqchip/chained_irq.h, and including
that header makes it build in all configurations.

Fixes: e46df235b4e6 ("pinctrl: mediatek: refactor EINT related code for all MediaTek pinctrl can fit")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/mediatek/mtk-eint.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/pinctrl/mediatek/mtk-eint.c b/drivers/pinctrl/mediatek/mtk-eint.c
index 30f3316747e2..a613e546717a 100644
--- a/drivers/pinctrl/mediatek/mtk-eint.c
+++ b/drivers/pinctrl/mediatek/mtk-eint.c
@@ -13,6 +13,7 @@
 #include <linux/err.h>
 #include <linux/gpio.h>
 #include <linux/io.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
-- 
cgit v1.2.3


From 9dabfdd84bdfa25f0df486dd3de43e53e79a1892 Mon Sep 17 00:00:00 2001
From: Daniel Mack <daniel@zonque.org>
Date: Fri, 13 Jul 2018 18:15:38 +0200
Subject: gpio: pxa: disable pinctrl calls for PXA3xx

The pxa3xx driver uses the pinctrl-single driver since a while which
does not implement a .gpio_set_direction() callback. The pinmux core
will simply return 0 in this case, and the pxa3xx gpio driver hence
believes the pinctrl driver did its job and returns as well.

This effectively makes pxa_gpio_direction_{input,output} no-ops.

To fix this, do not call into the pinctrl subsystem for the PXA3xx
platform for now. We can revert this once the pinctrl-single driver
learned to support setting pin directions.

Signed-off-by: Daniel Mack <daniel@zonque.org>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-pxa.c | 35 +++++++++++++++++++++++++++--------
 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index 0d09a4fcef49..99070e2ac3cd 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -241,6 +241,17 @@ int pxa_irq_to_gpio(int irq)
 	return irq_gpio0;
 }
 
+static bool pxa_gpio_has_pinctrl(void)
+{
+	switch (gpio_type) {
+	case PXA3XX_GPIO:
+		return false;
+
+	default:
+		return true;
+	}
+}
+
 static int pxa_gpio_to_irq(struct gpio_chip *chip, unsigned offset)
 {
 	struct pxa_gpio_chip *pchip = chip_to_pxachip(chip);
@@ -255,9 +266,11 @@ static int pxa_gpio_direction_input(struct gpio_chip *chip, unsigned offset)
 	unsigned long flags;
 	int ret;
 
-	ret = pinctrl_gpio_direction_input(chip->base + offset);
-	if (!ret)
-		return 0;
+	if (pxa_gpio_has_pinctrl()) {
+		ret = pinctrl_gpio_direction_input(chip->base + offset);
+		if (!ret)
+			return 0;
+	}
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
@@ -282,9 +295,11 @@ static int pxa_gpio_direction_output(struct gpio_chip *chip,
 
 	writel_relaxed(mask, base + (value ? GPSR_OFFSET : GPCR_OFFSET));
 
-	ret = pinctrl_gpio_direction_output(chip->base + offset);
-	if (ret)
-		return ret;
+	if (pxa_gpio_has_pinctrl()) {
+		ret = pinctrl_gpio_direction_output(chip->base + offset);
+		if (ret)
+			return ret;
+	}
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
@@ -348,8 +363,12 @@ static int pxa_init_gpio_chip(struct pxa_gpio_chip *pchip, int ngpio,
 	pchip->chip.set = pxa_gpio_set;
 	pchip->chip.to_irq = pxa_gpio_to_irq;
 	pchip->chip.ngpio = ngpio;
-	pchip->chip.request = gpiochip_generic_request;
-	pchip->chip.free = gpiochip_generic_free;
+
+	if (pxa_gpio_has_pinctrl()) {
+		pchip->chip.request = gpiochip_generic_request;
+		pchip->chip.free = gpiochip_generic_free;
+	}
+
 #ifdef CONFIG_OF_GPIO
 	pchip->chip.of_node = np;
 	pchip->chip.of_xlate = pxa_gpio_of_xlate;
-- 
cgit v1.2.3


From 2bee9e067cad4446928cbdcdaf788be463e74240 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <fabio.estevam@nxp.com>
Date: Tue, 24 Jul 2018 13:29:28 -0300
Subject: gpio: mxs: Fit writel() into a single line

There is no need for splitting the writel() call in two lines.

Make it fit into a single line instead.

Signed-off-by: Fabio Estevam <fabio.estevam@nxp.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-mxs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index e2831ee70cdc..df30490da820 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -126,8 +126,7 @@ static int mxs_gpio_set_irq_type(struct irq_data *d, unsigned int type)
 	else
 		writel(pin_mask, pin_addr + MXS_CLR);
 
-	writel(pin_mask,
-	       port->base + PINCTRL_IRQSTAT(port) + MXS_CLR);
+	writel(pin_mask, port->base + PINCTRL_IRQSTAT(port) + MXS_CLR);
 
 	return 0;
 }
-- 
cgit v1.2.3


From b4859f3edb47825f62d1b2efdd75fe7945996f49 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Thu, 19 Jul 2018 11:16:48 +0300
Subject: pinctrl: imx: off by one in imx_pinconf_group_dbg_show()

The > should really be >= here.  It's harmless because
pinctrl_generic_get_group() will return a NULL if group is invalid.

Fixes: ae75ff814538 ("pinctrl: pinctrl-imx: add imx pinctrl core driver")
Reported-by: Dong Aisheng <aisheng.dong@nxp.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/pinctrl-imx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx.c b/drivers/pinctrl/freescale/pinctrl-imx.c
index 1c6bb15579e1..b04edc22dad7 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx.c
@@ -383,7 +383,7 @@ static void imx_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	const char *name;
 	int i, ret;
 
-	if (group > pctldev->num_groups)
+	if (group >= pctldev->num_groups)
 		return;
 
 	seq_puts(s, "\n");
-- 
cgit v1.2.3


From 9af0b3d1257756394ebbd06b14937b557e3a756b Mon Sep 17 00:00:00 2001
From: Wang Shilong <wshilong@ddn.com>
Date: Sun, 29 Jul 2018 17:27:45 -0400
Subject: ext4: fix race when setting the bitmap corrupted flag

Whenever we hit block or inode bitmap corruptions we set
bit and then reduce this block group free inode/clusters
counter to expose right available space.

However some of ext4_mark_group_bitmap_corrupted() is called
inside group spinlock, some are not, this could make it happen
that we double reduce one block group free counters from system.

Always hold group spinlock for it could fix it, but it looks
a little heavy, we could use test_and_set_bit() to fix race
problems here.

Signed-off-by: Wang Shilong <wshilong@ddn.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/super.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index d4a218ba626c..f7750bc5b85a 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -795,26 +795,26 @@ void ext4_mark_group_bitmap_corrupted(struct super_block *sb,
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_group_info *grp = ext4_get_group_info(sb, group);
 	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+	int ret;
 
-	if ((flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) &&
-	    !EXT4_MB_GRP_BBITMAP_CORRUPT(grp)) {
-		percpu_counter_sub(&sbi->s_freeclusters_counter,
-					grp->bb_free);
-		set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
-			&grp->bb_state);
+	if (flags & EXT4_GROUP_INFO_BBITMAP_CORRUPT) {
+		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_BBITMAP_CORRUPT_BIT,
+					    &grp->bb_state);
+		if (!ret)
+			percpu_counter_sub(&sbi->s_freeclusters_counter,
+					   grp->bb_free);
 	}
 
-	if ((flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) &&
-	    !EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) {
-		if (gdp) {
+	if (flags & EXT4_GROUP_INFO_IBITMAP_CORRUPT) {
+		ret = ext4_test_and_set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
+					    &grp->bb_state);
+		if (!ret && gdp) {
 			int count;
 
 			count = ext4_free_inodes_count(sb, gdp);
 			percpu_counter_sub(&sbi->s_freeinodes_counter,
 					   count);
 		}
-		set_bit(EXT4_GROUP_INFO_IBITMAP_CORRUPT_BIT,
-			&grp->bb_state);
 	}
 }
 
-- 
cgit v1.2.3


From 55aedef50d4d810670916d9fce4a40d5da2079e7 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 25 Jul 2018 15:42:08 +0300
Subject: pinctrl: intel: Do pin translation when lock IRQ

Default GPIOLIB callbacks for request and release IRQ do not do a GPIO
to pin translation which is necessary for Intel hardware, such as Intel
Cannonlake. Absence of the translation prevents some pins to be locked
as IRQ due to direction check. Introduce own callbacks to make
translation possible to avoid above issue.

Fixes: a60eac3239f0 ("pinctrl: intel: Allow custom GPIO base for pad groups")
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index 3d0bd7b99725..d023b64825d0 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -872,6 +872,34 @@ static int intel_gpio_to_pin(struct intel_pinctrl *pctrl, unsigned offset,
 	return -EINVAL;
 }
 
+static int intel_gpio_irq_reqres(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct intel_pinctrl *pctrl = gpiochip_get_data(gc);
+	int pin;
+
+	pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL);
+	if (pin >= 0) {
+		if (gpiochip_lock_as_irq(gc, pin)) {
+			dev_err(pctrl->dev, "unable to lock HW IRQ %d for IRQ\n",
+				pin);
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static void intel_gpio_irq_relres(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct intel_pinctrl *pctrl = gpiochip_get_data(gc);
+	int pin;
+
+	pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL);
+	if (pin >= 0)
+		gpiochip_unlock_as_irq(gc, pin);
+}
+
 static void intel_gpio_irq_ack(struct irq_data *d)
 {
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
@@ -1087,6 +1115,8 @@ static irqreturn_t intel_gpio_irq(int irq, void *data)
 
 static struct irq_chip intel_gpio_irqchip = {
 	.name = "intel-gpio",
+	.irq_request_resources = intel_gpio_irq_reqres,
+	.irq_release_resources = intel_gpio_irq_relres,
 	.irq_enable = intel_gpio_irq_enable,
 	.irq_ack = intel_gpio_irq_ack,
 	.irq_mask = intel_gpio_irq_mask,
-- 
cgit v1.2.3


From 23211b08c367bc9b22469c1460f5dbb67142e06d Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Tue, 24 Jul 2018 19:57:43 +0800
Subject: gpio: fix meaningless return expression

Fix the following sparse error:

drivers/gpio/gpio-ath79.c:54:16: error: return expression in void function

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Acked-by: Alban Bedel <albeu@free.fr>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-ath79.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-ath79.c b/drivers/gpio/gpio-ath79.c
index 684e9d6d6623..0a553d676042 100644
--- a/drivers/gpio/gpio-ath79.c
+++ b/drivers/gpio/gpio-ath79.c
@@ -51,7 +51,7 @@ static u32 ath79_gpio_read(struct ath79_gpio_ctrl *ctrl, unsigned reg)
 static void ath79_gpio_write(struct ath79_gpio_ctrl *ctrl,
 			unsigned reg, u32 val)
 {
-	return writel(val, ctrl->base + reg);
+	writel(val, ctrl->base + reg);
 }
 
 static bool ath79_gpio_update_bits(
-- 
cgit v1.2.3


From 3c94d2d08a032d911bbe34f2edb24cb63a63644a Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Thu, 26 Jul 2018 17:40:24 +0200
Subject: pinctrl: tegra: define GPIO compatible node per SoC

Tegra 2 uses a different GPIO controller which uses "tegra20-gpio" as
compatible string.

Make the compatible string the GPIO node is using a SoC specific
property. This prevents the kernel from registering the GPIO range
twice in case the GPIO range is specified in the device tree.

Fixes: 9462510ce31e ("pinctrl: tegra: Only set the gpio range if needed")
Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/tegra/pinctrl-tegra.c    | 6 +++---
 drivers/pinctrl/tegra/pinctrl-tegra.h    | 1 +
 drivers/pinctrl/tegra/pinctrl-tegra114.c | 1 +
 drivers/pinctrl/tegra/pinctrl-tegra124.c | 1 +
 drivers/pinctrl/tegra/pinctrl-tegra20.c  | 1 +
 drivers/pinctrl/tegra/pinctrl-tegra210.c | 1 +
 drivers/pinctrl/tegra/pinctrl-tegra30.c  | 1 +
 7 files changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.c b/drivers/pinctrl/tegra/pinctrl-tegra.c
index f974eee29a19..1aba75897d14 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.c
@@ -629,12 +629,12 @@ static void tegra_pinctrl_clear_parked_bits(struct tegra_pmx *pmx)
 	}
 }
 
-static bool gpio_node_has_range(void)
+static bool gpio_node_has_range(const char *compatible)
 {
 	struct device_node *np;
 	bool has_prop = false;
 
-	np = of_find_compatible_node(NULL, NULL, "nvidia,tegra30-gpio");
+	np = of_find_compatible_node(NULL, NULL, compatible);
 	if (!np)
 		return has_prop;
 
@@ -728,7 +728,7 @@ int tegra_pinctrl_probe(struct platform_device *pdev,
 
 	tegra_pinctrl_clear_parked_bits(pmx);
 
-	if (!gpio_node_has_range())
+	if (!gpio_node_has_range(pmx->soc->gpio_compatible))
 		pinctrl_add_gpio_range(pmx->pctl, &tegra_pinctrl_gpio_range);
 
 	platform_set_drvdata(pdev, pmx);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra.h b/drivers/pinctrl/tegra/pinctrl-tegra.h
index aa33c20766c4..44c71941b5f8 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra.h
+++ b/drivers/pinctrl/tegra/pinctrl-tegra.h
@@ -189,6 +189,7 @@ struct tegra_pingroup {
  */
 struct tegra_pinctrl_soc_data {
 	unsigned ngpios;
+	const char *gpio_compatible;
 	const struct pinctrl_pin_desc *pins;
 	unsigned npins;
 	struct tegra_function *functions;
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra114.c b/drivers/pinctrl/tegra/pinctrl-tegra114.c
index 56b33fca1bfc..511a8774fd8d 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra114.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra114.c
@@ -1839,6 +1839,7 @@ static const struct tegra_pingroup tegra114_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra114_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra114_pins,
 	.npins = ARRAY_SIZE(tegra114_pins),
 	.functions = tegra114_functions,
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra124.c b/drivers/pinctrl/tegra/pinctrl-tegra124.c
index 7bc998ace0d5..57e3cdcf4503 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra124.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra124.c
@@ -2051,6 +2051,7 @@ static const struct tegra_pingroup tegra124_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra124_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra124_pins,
 	.npins = ARRAY_SIZE(tegra124_pins),
 	.functions = tegra124_functions,
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra20.c b/drivers/pinctrl/tegra/pinctrl-tegra20.c
index b6dd939d32cc..624889ed3a9d 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra20.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra20.c
@@ -2221,6 +2221,7 @@ static const struct tegra_pingroup tegra20_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra20_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra20-gpio",
 	.pins = tegra20_pins,
 	.npins = ARRAY_SIZE(tegra20_pins),
 	.functions = tegra20_functions,
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra210.c b/drivers/pinctrl/tegra/pinctrl-tegra210.c
index c244e5b17bd6..0956a1c73391 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra210.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra210.c
@@ -1553,6 +1553,7 @@ static const struct tegra_pingroup tegra210_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra210_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra210_pins,
 	.npins = ARRAY_SIZE(tegra210_pins),
 	.functions = tegra210_functions,
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra30.c b/drivers/pinctrl/tegra/pinctrl-tegra30.c
index 1f180a20f2ab..c923ad58af84 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra30.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra30.c
@@ -2474,6 +2474,7 @@ static const struct tegra_pingroup tegra30_groups[] = {
 
 static const struct tegra_pinctrl_soc_data tegra30_pinctrl = {
 	.ngpios = NUM_GPIOS,
+	.gpio_compatible = "nvidia,tegra30-gpio",
 	.pins = tegra30_pins,
 	.npins = ARRAY_SIZE(tegra30_pins),
 	.functions = tegra30_functions,
-- 
cgit v1.2.3


From 0b07609ccd48a23103881a161e49eb7a282170e7 Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Thu, 26 Jul 2018 17:42:52 +0200
Subject: gpio: tegra: drop tegra specific GPIO lockdep classes

Since commit e45d1c80c0ee ("gpio: put GPIO IRQs into their own lock
class") and commit a0a8bcf4670c ("gpiolib: irqchip: use different
lockdep class for each gpio irqchip") GPIO lib takes care of lockdep
classes. In fact, gpiochip_irq_map() overwrites the class anyway, so
the lockdep class set by the driver is useless. Remove it.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tegra.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 22e7c99ed69e..2d940785bad0 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -551,13 +551,6 @@ static const struct dev_pm_ops tegra_gpio_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(tegra_gpio_suspend, tegra_gpio_resume)
 };
 
-/*
- * This lock class tells lockdep that GPIO irqs are in a different category
- * than their parents, so it won't report false recursion.
- */
-static struct lock_class_key gpio_lock_class;
-static struct lock_class_key gpio_request_class;
-
 static int tegra_gpio_probe(struct platform_device *pdev)
 {
 	struct tegra_gpio_info *tgi;
@@ -662,8 +655,6 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 
 		bank = &tgi->bank_info[GPIO_BANK(gpio)];
 
-		irq_set_lockdep_class(irq, &gpio_lock_class,
-				      &gpio_request_class);
 		irq_set_chip_data(irq, bank);
 		irq_set_chip_and_handler(irq, &tgi->ic, handle_simple_irq);
 	}
-- 
cgit v1.2.3


From 17ac526824a8b5544bc2545c76f489e49c6593a2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jul 2018 19:59:05 +0300
Subject: pinctrl: cannonlake: Fix community ordering for H variant

The driver was written based on an assumption that BIOS provides
unordered communities in ACPI DSDT. Nevertheless, it seems that
BIOS getting fixed before being provisioned to OxM:s.
So does driver.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=199911
Reported-by: Marc Landolt <2009@marclandolt.ch>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Fixes: a663ccf0fea1 ("pinctrl: intel: Add Intel Cannon Lake PCH-H pin controller support")
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/pinctrl-cannonlake.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-cannonlake.c b/drivers/pinctrl/intel/pinctrl-cannonlake.c
index 71ad67b8fc35..fb1afe55bf53 100644
--- a/drivers/pinctrl/intel/pinctrl-cannonlake.c
+++ b/drivers/pinctrl/intel/pinctrl-cannonlake.c
@@ -444,12 +444,8 @@ static const struct intel_function cnlh_functions[] = {
 static const struct intel_community cnlh_communities[] = {
 	CNL_COMMUNITY(0, 0, 50, cnlh_community0_gpps),
 	CNL_COMMUNITY(1, 51, 154, cnlh_community1_gpps),
-	/*
-	 * ACPI MMIO resources are returned in reverse order for
-	 * communities 3 and 4.
-	 */
-	CNL_COMMUNITY(3, 155, 248, cnlh_community3_gpps),
-	CNL_COMMUNITY(2, 249, 298, cnlh_community4_gpps),
+	CNL_COMMUNITY(2, 155, 248, cnlh_community3_gpps),
+	CNL_COMMUNITY(3, 249, 298, cnlh_community4_gpps),
 };
 
 static const struct intel_pinctrl_soc_data cnlh_soc_data = {
-- 
cgit v1.2.3


From 0969a204bfdaf7470d2666736b90a8595ae671e9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 27 Jul 2018 17:47:01 +0300
Subject: gpiolib: Use GPIOD_OUT_{LOW,HIGH} macros in open drain ones

There should not be anything more than stated by the name of newly
introduced constants, i.e.
	GPIOD_OUT_LOW_OPEN_DRAIN == GPIOD_OUT_LOW + open drain
and nothing more.

Make it better to read and slightly more robust by using GPIOD_OUT_LOW
and GPIOD_OUT_HIGH constants with open drain flag.

No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 include/linux/gpio/consumer.h | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index e8aaf34dd65d..21ddbe440030 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -41,11 +41,8 @@ enum gpiod_flags {
 	GPIOD_OUT_LOW	= GPIOD_FLAGS_BIT_DIR_SET | GPIOD_FLAGS_BIT_DIR_OUT,
 	GPIOD_OUT_HIGH	= GPIOD_FLAGS_BIT_DIR_SET | GPIOD_FLAGS_BIT_DIR_OUT |
 			  GPIOD_FLAGS_BIT_DIR_VAL,
-	GPIOD_OUT_LOW_OPEN_DRAIN = GPIOD_FLAGS_BIT_DIR_SET |
-			  GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_OPEN_DRAIN,
-	GPIOD_OUT_HIGH_OPEN_DRAIN = GPIOD_FLAGS_BIT_DIR_SET |
-			  GPIOD_FLAGS_BIT_DIR_OUT | GPIOD_FLAGS_BIT_DIR_VAL |
-			  GPIOD_FLAGS_BIT_OPEN_DRAIN,
+	GPIOD_OUT_LOW_OPEN_DRAIN = GPIOD_OUT_LOW | GPIOD_FLAGS_BIT_OPEN_DRAIN,
+	GPIOD_OUT_HIGH_OPEN_DRAIN = GPIOD_OUT_HIGH | GPIOD_FLAGS_BIT_OPEN_DRAIN,
 };
 
 #ifdef CONFIG_GPIOLIB
-- 
cgit v1.2.3


From ebcbef3a61a6081ffe20b0b684f18ebbf23f1dfb Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 22:37:08 -0700
Subject: xfs: pass transaction lock while setting up agresv on cyclic metadata

Pass a tranaction pointer through to all helpers that calculate the
per-AG block reservation.  Online repair will use this to reinitialize
per-ag reservations while it still holds all the AG headers locked to
the repair transaction.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/libxfs/xfs_ag_resv.c        | 13 +++++++------
 fs/xfs/libxfs/xfs_ag_resv.h        |  2 +-
 fs/xfs/libxfs/xfs_ialloc_btree.c   | 10 ++++++----
 fs/xfs/libxfs/xfs_ialloc_btree.h   |  4 ++--
 fs/xfs/libxfs/xfs_refcount_btree.c |  5 +++--
 fs/xfs/libxfs/xfs_refcount_btree.h |  3 ++-
 fs/xfs/libxfs/xfs_rmap_btree.c     |  5 +++--
 fs/xfs/libxfs/xfs_rmap_btree.h     |  2 +-
 fs/xfs/xfs_fsops.c                 |  2 +-
 9 files changed, 26 insertions(+), 20 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index fecd187fcf2c..e701ebc36c06 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -248,7 +248,8 @@ __xfs_ag_resv_init(
 /* Create a per-AG block reservation. */
 int
 xfs_ag_resv_init(
-	struct xfs_perag		*pag)
+	struct xfs_perag		*pag,
+	struct xfs_trans		*tp)
 {
 	struct xfs_mount		*mp = pag->pag_mount;
 	xfs_agnumber_t			agno = pag->pag_agno;
@@ -260,11 +261,11 @@ xfs_ag_resv_init(
 	if (pag->pag_meta_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_refcountbt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_refcountbt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
-		error = xfs_finobt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_finobt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -282,7 +283,7 @@ xfs_ag_resv_init(
 
 			mp->m_inotbt_nores = true;
 
-			error = xfs_refcountbt_calc_reserves(mp, agno, &ask,
+			error = xfs_refcountbt_calc_reserves(mp, tp, agno, &ask,
 					&used);
 			if (error)
 				goto out;
@@ -298,7 +299,7 @@ xfs_ag_resv_init(
 	if (pag->pag_rmapbt_resv.ar_asked == 0) {
 		ask = used = 0;
 
-		error = xfs_rmapbt_calc_reserves(mp, agno, &ask, &used);
+		error = xfs_rmapbt_calc_reserves(mp, tp, agno, &ask, &used);
 		if (error)
 			goto out;
 
@@ -309,7 +310,7 @@ xfs_ag_resv_init(
 
 #ifdef DEBUG
 	/* need to read in the AGF for the ASSERT below to work */
-	error = xfs_alloc_pagf_init(pag->pag_mount, NULL, pag->pag_agno, 0);
+	error = xfs_alloc_pagf_init(pag->pag_mount, tp, pag->pag_agno, 0);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ag_resv.h b/fs/xfs/libxfs/xfs_ag_resv.h
index dc953fc84b2f..c0352edc8e41 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.h
+++ b/fs/xfs/libxfs/xfs_ag_resv.h
@@ -7,7 +7,7 @@
 #define	__XFS_AG_RESV_H__
 
 int xfs_ag_resv_free(struct xfs_perag *pag);
-int xfs_ag_resv_init(struct xfs_perag *pag);
+int xfs_ag_resv_init(struct xfs_perag *pag, struct xfs_trans *tp);
 
 bool xfs_ag_resv_critical(struct xfs_perag *pag, enum xfs_ag_resv_type type);
 xfs_extlen_t xfs_ag_resv_needed(struct xfs_perag *pag,
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 735a33252eb2..86c50208a143 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -552,6 +552,7 @@ xfs_inobt_max_size(
 static int
 xfs_inobt_count_blocks(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_btnum_t		btnum,
 	xfs_extlen_t		*tree_blocks)
@@ -560,14 +561,14 @@ xfs_inobt_count_blocks(
 	struct xfs_btree_cur	*cur;
 	int			error;
 
-	error = xfs_ialloc_read_agi(mp, NULL, agno, &agbp);
+	error = xfs_ialloc_read_agi(mp, tp, agno, &agbp);
 	if (error)
 		return error;
 
-	cur = xfs_inobt_init_cursor(mp, NULL, agbp, agno, btnum);
+	cur = xfs_inobt_init_cursor(mp, tp, agbp, agno, btnum);
 	error = xfs_btree_count_blocks(cur, tree_blocks);
 	xfs_btree_del_cursor(cur, error);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 
 	return error;
 }
@@ -578,6 +579,7 @@ xfs_inobt_count_blocks(
 int
 xfs_finobt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -588,7 +590,7 @@ xfs_finobt_calc_reserves(
 	if (!xfs_sb_version_hasfinobt(&mp->m_sb))
 		return 0;
 
-	error = xfs_inobt_count_blocks(mp, agno, XFS_BTNUM_FINO, &tree_len);
+	error = xfs_inobt_count_blocks(mp, tp, agno, XFS_BTNUM_FINO, &tree_len);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.h b/fs/xfs/libxfs/xfs_ialloc_btree.h
index bf8f0c405e7d..ebdd0c6b8766 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.h
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.h
@@ -60,8 +60,8 @@ int xfs_inobt_rec_check_count(struct xfs_mount *,
 #define xfs_inobt_rec_check_count(mp, rec)	0
 #endif	/* DEBUG */
 
-int xfs_finobt_calc_reserves(struct xfs_mount *mp, xfs_agnumber_t agno,
-		xfs_extlen_t *ask, xfs_extlen_t *used);
+int xfs_finobt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
+		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
 extern xfs_extlen_t xfs_iallocbt_calc_size(struct xfs_mount *mp,
 		unsigned long long len);
 
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 26d2300ed865..1aaa01c97517 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -404,6 +404,7 @@ xfs_refcountbt_max_size(
 int
 xfs_refcountbt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -418,14 +419,14 @@ xfs_refcountbt_calc_reserves(
 		return 0;
 
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
 	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_refcount_blocks);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 
 	*ask += xfs_refcountbt_max_size(mp, agblocks);
 	*used += tree_len;
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.h b/fs/xfs/libxfs/xfs_refcount_btree.h
index 801c2c7732fd..ba416f71c824 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.h
+++ b/fs/xfs/libxfs/xfs_refcount_btree.h
@@ -55,6 +55,7 @@ extern xfs_extlen_t xfs_refcountbt_max_size(struct xfs_mount *mp,
 		xfs_agblock_t agblocks);
 
 extern int xfs_refcountbt_calc_reserves(struct xfs_mount *mp,
-		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
+		struct xfs_trans *tp, xfs_agnumber_t agno, xfs_extlen_t *ask,
+		xfs_extlen_t *used);
 
 #endif	/* __XFS_REFCOUNT_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 221a88ea60bb..f79cf040d745 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -554,6 +554,7 @@ xfs_rmapbt_max_size(
 int
 xfs_rmapbt_calc_reserves(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_extlen_t		*ask,
 	xfs_extlen_t		*used)
@@ -567,14 +568,14 @@ xfs_rmapbt_calc_reserves(
 	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
 		return 0;
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
 	agf = XFS_BUF_TO_AGF(agbp);
 	agblocks = be32_to_cpu(agf->agf_length);
 	tree_len = be32_to_cpu(agf->agf_rmap_blocks);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 
 	/* Reserve 1% of the AG or enough for 1 block per record. */
 	*ask += max(agblocks / 100, xfs_rmapbt_max_size(mp, agblocks));
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.h b/fs/xfs/libxfs/xfs_rmap_btree.h
index 50198b6c3bb2..820d668b063d 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rmap_btree.h
@@ -51,7 +51,7 @@ extern xfs_extlen_t xfs_rmapbt_calc_size(struct xfs_mount *mp,
 extern xfs_extlen_t xfs_rmapbt_max_size(struct xfs_mount *mp,
 		xfs_agblock_t agblocks);
 
-extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp,
+extern int xfs_rmapbt_calc_reserves(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agnumber_t agno, xfs_extlen_t *ask, xfs_extlen_t *used);
 
 #endif	/* __XFS_RMAP_BTREE_H__ */
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 3f2bd6032cf8..7c00b8bedfe3 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -536,7 +536,7 @@ xfs_fs_reserve_ag_blocks(
 
 	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
 		pag = xfs_perag_get(mp, agno);
-		err2 = xfs_ag_resv_init(pag);
+		err2 = xfs_ag_resv_init(pag, NULL);
 		xfs_perag_put(pag);
 		if (err2 && !error)
 			error = err2;
-- 
cgit v1.2.3


From bc270b53e6aa3b9723e26a548fa1a1688ea61361 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 22:37:09 -0700
Subject: xfs: move the repair extent list into its own file

Move the xrep_extent_list code into a separate file.  Logically, this
data structure is really just a clumsy bitmap, and in the next patch
we'll make this more obvious.  No functional changes.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/Makefile       |   1 +
 fs/xfs/scrub/bitmap.c | 208 ++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/bitmap.h |  37 +++++++++
 fs/xfs/scrub/repair.c | 194 +---------------------------------------------
 fs/xfs/scrub/repair.h |  27 +------
 5 files changed, 248 insertions(+), 219 deletions(-)
 create mode 100644 fs/xfs/scrub/bitmap.c
 create mode 100644 fs/xfs/scrub/bitmap.h

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 2f3f75a7f180..7f96bdadc372 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -158,6 +158,7 @@ xfs-$(CONFIG_XFS_QUOTA)		+= scrub/quota.o
 ifeq ($(CONFIG_XFS_ONLINE_REPAIR),y)
 xfs-y				+= $(addprefix scrub/, \
 				   agheader_repair.o \
+				   bitmap.o \
 				   repair.o \
 				   )
 endif
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
new file mode 100644
index 000000000000..a7c2f4773f98
--- /dev/null
+++ b/fs/xfs/scrub/bitmap.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
+
+/* Collect a dead btree extent for later disposal. */
+int
+xrep_collect_btree_extent(
+	struct xfs_scrub	*sc,
+	struct xrep_extent_list	*exlist,
+	xfs_fsblock_t		fsbno,
+	xfs_extlen_t		len)
+{
+	struct xrep_extent	*rex;
+
+	trace_xrep_collect_btree_extent(sc->mp,
+			XFS_FSB_TO_AGNO(sc->mp, fsbno),
+			XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
+
+	rex = kmem_alloc(sizeof(struct xrep_extent), KM_MAYFAIL);
+	if (!rex)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&rex->list);
+	rex->fsbno = fsbno;
+	rex->len = len;
+	list_add_tail(&rex->list, &exlist->list);
+
+	return 0;
+}
+
+/*
+ * An error happened during the rebuild so the transaction will be cancelled.
+ * The fs will shut down, and the administrator has to unmount and run repair.
+ * Therefore, free all the memory associated with the list so we can die.
+ */
+void
+xrep_cancel_btree_extents(
+	struct xfs_scrub	*sc,
+	struct xrep_extent_list	*exlist)
+{
+	struct xrep_extent	*rex;
+	struct xrep_extent	*n;
+
+	for_each_xrep_extent_safe(rex, n, exlist) {
+		list_del(&rex->list);
+		kmem_free(rex);
+	}
+}
+
+/* Compare two btree extents. */
+static int
+xrep_btree_extent_cmp(
+	void			*priv,
+	struct list_head	*a,
+	struct list_head	*b)
+{
+	struct xrep_extent	*ap;
+	struct xrep_extent	*bp;
+
+	ap = container_of(a, struct xrep_extent, list);
+	bp = container_of(b, struct xrep_extent, list);
+
+	if (ap->fsbno > bp->fsbno)
+		return 1;
+	if (ap->fsbno < bp->fsbno)
+		return -1;
+	return 0;
+}
+
+/*
+ * Remove all the blocks mentioned in @sublist from the extents in @exlist.
+ *
+ * The intent is that callers will iterate the rmapbt for all of its records
+ * for a given owner to generate @exlist; and iterate all the blocks of the
+ * metadata structures that are not being rebuilt and have the same rmapbt
+ * owner to generate @sublist.  This routine subtracts all the extents
+ * mentioned in sublist from all the extents linked in @exlist, which leaves
+ * @exlist as the list of blocks that are not accounted for, which we assume
+ * are the dead blocks of the old metadata structure.  The blocks mentioned in
+ * @exlist can be reaped.
+ */
+#define LEFT_ALIGNED	(1 << 0)
+#define RIGHT_ALIGNED	(1 << 1)
+int
+xrep_subtract_extents(
+	struct xfs_scrub	*sc,
+	struct xrep_extent_list	*exlist,
+	struct xrep_extent_list	*sublist)
+{
+	struct list_head	*lp;
+	struct xrep_extent	*ex;
+	struct xrep_extent	*newex;
+	struct xrep_extent	*subex;
+	xfs_fsblock_t		sub_fsb;
+	xfs_extlen_t		sub_len;
+	int			state;
+	int			error = 0;
+
+	if (list_empty(&exlist->list) || list_empty(&sublist->list))
+		return 0;
+	ASSERT(!list_empty(&sublist->list));
+
+	list_sort(NULL, &exlist->list, xrep_btree_extent_cmp);
+	list_sort(NULL, &sublist->list, xrep_btree_extent_cmp);
+
+	/*
+	 * Now that we've sorted both lists, we iterate exlist once, rolling
+	 * forward through sublist and/or exlist as necessary until we find an
+	 * overlap or reach the end of either list.  We do not reset lp to the
+	 * head of exlist nor do we reset subex to the head of sublist.  The
+	 * list traversal is similar to merge sort, but we're deleting
+	 * instead.  In this manner we avoid O(n^2) operations.
+	 */
+	subex = list_first_entry(&sublist->list, struct xrep_extent,
+			list);
+	lp = exlist->list.next;
+	while (lp != &exlist->list) {
+		ex = list_entry(lp, struct xrep_extent, list);
+
+		/*
+		 * Advance subex and/or ex until we find a pair that
+		 * intersect or we run out of extents.
+		 */
+		while (subex->fsbno + subex->len <= ex->fsbno) {
+			if (list_is_last(&subex->list, &sublist->list))
+				goto out;
+			subex = list_next_entry(subex, list);
+		}
+		if (subex->fsbno >= ex->fsbno + ex->len) {
+			lp = lp->next;
+			continue;
+		}
+
+		/* trim subex to fit the extent we have */
+		sub_fsb = subex->fsbno;
+		sub_len = subex->len;
+		if (subex->fsbno < ex->fsbno) {
+			sub_len -= ex->fsbno - subex->fsbno;
+			sub_fsb = ex->fsbno;
+		}
+		if (sub_len > ex->len)
+			sub_len = ex->len;
+
+		state = 0;
+		if (sub_fsb == ex->fsbno)
+			state |= LEFT_ALIGNED;
+		if (sub_fsb + sub_len == ex->fsbno + ex->len)
+			state |= RIGHT_ALIGNED;
+		switch (state) {
+		case LEFT_ALIGNED:
+			/* Coincides with only the left. */
+			ex->fsbno += sub_len;
+			ex->len -= sub_len;
+			break;
+		case RIGHT_ALIGNED:
+			/* Coincides with only the right. */
+			ex->len -= sub_len;
+			lp = lp->next;
+			break;
+		case LEFT_ALIGNED | RIGHT_ALIGNED:
+			/* Total overlap, just delete ex. */
+			lp = lp->next;
+			list_del(&ex->list);
+			kmem_free(ex);
+			break;
+		case 0:
+			/*
+			 * Deleting from the middle: add the new right extent
+			 * and then shrink the left extent.
+			 */
+			newex = kmem_alloc(sizeof(struct xrep_extent),
+					KM_MAYFAIL);
+			if (!newex) {
+				error = -ENOMEM;
+				goto out;
+			}
+			INIT_LIST_HEAD(&newex->list);
+			newex->fsbno = sub_fsb + sub_len;
+			newex->len = ex->fsbno + ex->len - newex->fsbno;
+			list_add(&newex->list, &ex->list);
+			ex->len = sub_fsb - ex->fsbno;
+			lp = lp->next;
+			break;
+		default:
+			ASSERT(0);
+			break;
+		}
+	}
+
+out:
+	return error;
+}
+#undef LEFT_ALIGNED
+#undef RIGHT_ALIGNED
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
new file mode 100644
index 000000000000..1038157695a8
--- /dev/null
+++ b/fs/xfs/scrub/bitmap.h
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2018 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#ifndef __XFS_SCRUB_BITMAP_H__
+#define __XFS_SCRUB_BITMAP_H__
+
+struct xrep_extent {
+	struct list_head	list;
+	xfs_fsblock_t		fsbno;
+	xfs_extlen_t		len;
+};
+
+struct xrep_extent_list {
+	struct list_head	list;
+};
+
+static inline void
+xrep_init_extent_list(
+	struct xrep_extent_list		*exlist)
+{
+	INIT_LIST_HEAD(&exlist->list);
+}
+
+#define for_each_xrep_extent_safe(rbe, n, exlist) \
+	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
+int xrep_collect_btree_extent(struct xfs_scrub *sc,
+		struct xrep_extent_list *btlist, xfs_fsblock_t fsbno,
+		xfs_extlen_t len);
+void xrep_cancel_btree_extents(struct xfs_scrub *sc,
+		struct xrep_extent_list *btlist);
+int xrep_subtract_extents(struct xfs_scrub *sc,
+		struct xrep_extent_list *exlist,
+		struct xrep_extent_list *sublist);
+
+#endif	/* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 5de1cac424ec..27a904ef6189 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -34,6 +34,7 @@
 #include "scrub/common.h"
 #include "scrub/trace.h"
 #include "scrub/repair.h"
+#include "scrub/bitmap.h"
 
 /*
  * Attempt to repair some metadata, if the metadata is corrupt and userspace
@@ -380,200 +381,7 @@ xrep_init_btblock(
  * sublist.  As with the other btrees we subtract sublist from exlist, and the
  * result (since the rmapbt lives in the free space) are the blocks from the
  * old rmapbt.
- */
-
-/* Collect a dead btree extent for later disposal. */
-int
-xrep_collect_btree_extent(
-	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist,
-	xfs_fsblock_t		fsbno,
-	xfs_extlen_t		len)
-{
-	struct xrep_extent	*rex;
-
-	trace_xrep_collect_btree_extent(sc->mp,
-			XFS_FSB_TO_AGNO(sc->mp, fsbno),
-			XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
-
-	rex = kmem_alloc(sizeof(struct xrep_extent), KM_MAYFAIL);
-	if (!rex)
-		return -ENOMEM;
-
-	INIT_LIST_HEAD(&rex->list);
-	rex->fsbno = fsbno;
-	rex->len = len;
-	list_add_tail(&rex->list, &exlist->list);
-
-	return 0;
-}
-
-/*
- * An error happened during the rebuild so the transaction will be cancelled.
- * The fs will shut down, and the administrator has to unmount and run repair.
- * Therefore, free all the memory associated with the list so we can die.
- */
-void
-xrep_cancel_btree_extents(
-	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist)
-{
-	struct xrep_extent	*rex;
-	struct xrep_extent	*n;
-
-	for_each_xrep_extent_safe(rex, n, exlist) {
-		list_del(&rex->list);
-		kmem_free(rex);
-	}
-}
-
-/* Compare two btree extents. */
-static int
-xrep_btree_extent_cmp(
-	void			*priv,
-	struct list_head	*a,
-	struct list_head	*b)
-{
-	struct xrep_extent	*ap;
-	struct xrep_extent	*bp;
-
-	ap = container_of(a, struct xrep_extent, list);
-	bp = container_of(b, struct xrep_extent, list);
-
-	if (ap->fsbno > bp->fsbno)
-		return 1;
-	if (ap->fsbno < bp->fsbno)
-		return -1;
-	return 0;
-}
-
-/*
- * Remove all the blocks mentioned in @sublist from the extents in @exlist.
  *
- * The intent is that callers will iterate the rmapbt for all of its records
- * for a given owner to generate @exlist; and iterate all the blocks of the
- * metadata structures that are not being rebuilt and have the same rmapbt
- * owner to generate @sublist.  This routine subtracts all the extents
- * mentioned in sublist from all the extents linked in @exlist, which leaves
- * @exlist as the list of blocks that are not accounted for, which we assume
- * are the dead blocks of the old metadata structure.  The blocks mentioned in
- * @exlist can be reaped.
- */
-#define LEFT_ALIGNED	(1 << 0)
-#define RIGHT_ALIGNED	(1 << 1)
-int
-xrep_subtract_extents(
-	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist,
-	struct xrep_extent_list	*sublist)
-{
-	struct list_head	*lp;
-	struct xrep_extent	*ex;
-	struct xrep_extent	*newex;
-	struct xrep_extent	*subex;
-	xfs_fsblock_t		sub_fsb;
-	xfs_extlen_t		sub_len;
-	int			state;
-	int			error = 0;
-
-	if (list_empty(&exlist->list) || list_empty(&sublist->list))
-		return 0;
-	ASSERT(!list_empty(&sublist->list));
-
-	list_sort(NULL, &exlist->list, xrep_btree_extent_cmp);
-	list_sort(NULL, &sublist->list, xrep_btree_extent_cmp);
-
-	/*
-	 * Now that we've sorted both lists, we iterate exlist once, rolling
-	 * forward through sublist and/or exlist as necessary until we find an
-	 * overlap or reach the end of either list.  We do not reset lp to the
-	 * head of exlist nor do we reset subex to the head of sublist.  The
-	 * list traversal is similar to merge sort, but we're deleting
-	 * instead.  In this manner we avoid O(n^2) operations.
-	 */
-	subex = list_first_entry(&sublist->list, struct xrep_extent,
-			list);
-	lp = exlist->list.next;
-	while (lp != &exlist->list) {
-		ex = list_entry(lp, struct xrep_extent, list);
-
-		/*
-		 * Advance subex and/or ex until we find a pair that
-		 * intersect or we run out of extents.
-		 */
-		while (subex->fsbno + subex->len <= ex->fsbno) {
-			if (list_is_last(&subex->list, &sublist->list))
-				goto out;
-			subex = list_next_entry(subex, list);
-		}
-		if (subex->fsbno >= ex->fsbno + ex->len) {
-			lp = lp->next;
-			continue;
-		}
-
-		/* trim subex to fit the extent we have */
-		sub_fsb = subex->fsbno;
-		sub_len = subex->len;
-		if (subex->fsbno < ex->fsbno) {
-			sub_len -= ex->fsbno - subex->fsbno;
-			sub_fsb = ex->fsbno;
-		}
-		if (sub_len > ex->len)
-			sub_len = ex->len;
-
-		state = 0;
-		if (sub_fsb == ex->fsbno)
-			state |= LEFT_ALIGNED;
-		if (sub_fsb + sub_len == ex->fsbno + ex->len)
-			state |= RIGHT_ALIGNED;
-		switch (state) {
-		case LEFT_ALIGNED:
-			/* Coincides with only the left. */
-			ex->fsbno += sub_len;
-			ex->len -= sub_len;
-			break;
-		case RIGHT_ALIGNED:
-			/* Coincides with only the right. */
-			ex->len -= sub_len;
-			lp = lp->next;
-			break;
-		case LEFT_ALIGNED | RIGHT_ALIGNED:
-			/* Total overlap, just delete ex. */
-			lp = lp->next;
-			list_del(&ex->list);
-			kmem_free(ex);
-			break;
-		case 0:
-			/*
-			 * Deleting from the middle: add the new right extent
-			 * and then shrink the left extent.
-			 */
-			newex = kmem_alloc(sizeof(struct xrep_extent),
-					KM_MAYFAIL);
-			if (!newex) {
-				error = -ENOMEM;
-				goto out;
-			}
-			INIT_LIST_HEAD(&newex->list);
-			newex->fsbno = sub_fsb + sub_len;
-			newex->len = ex->fsbno + ex->len - newex->fsbno;
-			list_add(&newex->list, &ex->list);
-			ex->len = sub_fsb - ex->fsbno;
-			lp = lp->next;
-			break;
-		default:
-			ASSERT(0);
-			break;
-		}
-	}
-
-out:
-	return error;
-}
-#undef LEFT_ALIGNED
-#undef RIGHT_ALIGNED
-
-/*
  * Disposal of Blocks from Old per-AG Btrees
  *
  * Now that we've constructed a new btree to replace the damaged one, we want
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 91355f6b0087..a3d491a438f4 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -27,33 +27,8 @@ int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb,
 		struct xfs_buf **bpp, xfs_btnum_t btnum,
 		const struct xfs_buf_ops *ops);
 
-struct xrep_extent {
-	struct list_head	list;
-	xfs_fsblock_t		fsbno;
-	xfs_extlen_t		len;
-};
-
-struct xrep_extent_list {
-	struct list_head	list;
-};
-
-static inline void
-xrep_init_extent_list(
-	struct xrep_extent_list	*exlist)
-{
-	INIT_LIST_HEAD(&exlist->list);
-}
+struct xrep_extent_list;
 
-#define for_each_xrep_extent_safe(rbe, n, exlist) \
-	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
-int xrep_collect_btree_extent(struct xfs_scrub *sc,
-		struct xrep_extent_list *btlist, xfs_fsblock_t fsbno,
-		xfs_extlen_t len);
-void xrep_cancel_btree_extents(struct xfs_scrub *sc,
-		struct xrep_extent_list *btlist);
-int xrep_subtract_extents(struct xfs_scrub *sc,
-		struct xrep_extent_list *exlist,
-		struct xrep_extent_list *sublist);
 int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
 int xrep_invalidate_blocks(struct xfs_scrub *sc,
 		struct xrep_extent_list *btlist);
-- 
cgit v1.2.3


From 4f919ca2bf6da826ba1a4316e1b8e9c94e5dbeb2 Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Fri, 27 Jul 2018 16:59:29 +0300
Subject: regulator: tps65217: Fix NULL pointer dereference on probe

There is no check that tps->strobes is allocated successfully in
tps65217_regulator_probe().
The patch adds corresponding check.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/tps65217-regulator.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/regulator/tps65217-regulator.c b/drivers/regulator/tps65217-regulator.c
index fc12badf3805..d84fab616abf 100644
--- a/drivers/regulator/tps65217-regulator.c
+++ b/drivers/regulator/tps65217-regulator.c
@@ -232,6 +232,8 @@ static int tps65217_regulator_probe(struct platform_device *pdev)
 	tps->strobes = devm_kcalloc(&pdev->dev,
 				    TPS65217_NUM_REGULATOR, sizeof(u8),
 				    GFP_KERNEL);
+	if (!tps->strobes)
+		return -ENOMEM;
 
 	platform_set_drvdata(pdev, tps);
 
-- 
cgit v1.2.3


From 24d1c2171f15bb6fad2ad69cfc2ee81dc4577b76 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Thu, 19 Jul 2018 18:05:36 +0900
Subject: pinctrl: uniphier: add spi pin-mux settings

Add pin-mux settings for spi controller.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Keiji Hayashibara <hayashibara.keiji@socionext.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c | 10 ++++++++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c | 20 ++++++++++++++++++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c  |  5 +++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c | 10 ++++++++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c | 10 ++++++++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c | 15 +++++++++++++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c | 10 ++++++++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c | 10 ++++++++++
 drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c |  5 +++++
 9 files changed, 95 insertions(+)

diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
index 58825f68b58b..bce533f85420 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld11.c
@@ -517,6 +517,10 @@ static const int i2c4_muxvals[] = {1, 1};
 static const unsigned nand_pins[] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
 				     15, 16, 17};
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {56, 57, 58, 59};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {169, 170, 171, 172};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {1, 2, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
@@ -596,6 +600,8 @@ static const struct uniphier_pinctrl_group uniphier_ld11_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c3),
 	UNIPHIER_PINCTRL_GROUP(i2c4),
 	UNIPHIER_PINCTRL_GROUP(nand),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -632,6 +638,8 @@ static const char * const i2c1_groups[] = {"i2c1"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const i2c4_groups[] = {"i2c4"};
 static const char * const nand_groups[] = {"nand"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0"};
@@ -657,6 +665,8 @@ static const struct uniphier_pinmux_function uniphier_ld11_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(i2c4),
 	UNIPHIER_PINMUX_FUNCTION(nand),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
index 9f449b35e300..99f06fe8e1cb 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld20.c
@@ -606,6 +606,14 @@ static const unsigned nand_pins[] = {3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned sd_pins[] = {10, 11, 12, 13, 14, 15, 16, 17};
 static const int sd_muxvals[] = {3, 3, 3, 3, 3, 3, 3, 3};  /* No SDVOLC */
+static const unsigned spi0_pins[] = {56, 57, 58, 59};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {169, 170, 171, 172};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi2_pins[] = {86, 87, 88, 89};
+static const int spi2_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi3_pins[] = {74, 75, 76, 77};
+static const int spi3_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {1, 2, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,
@@ -685,6 +693,10 @@ static const struct uniphier_pinctrl_group uniphier_ld20_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c4),
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
+	UNIPHIER_PINCTRL_GROUP(spi2),
+	UNIPHIER_PINCTRL_GROUP(spi3),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -722,6 +734,10 @@ static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const i2c4_groups[] = {"i2c4"};
 static const char * const nand_groups[] = {"nand"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
+static const char * const spi2_groups[] = {"spi2"};
+static const char * const spi3_groups[] = {"spi3"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0"};
@@ -751,6 +767,10 @@ static const struct uniphier_pinmux_function uniphier_ld20_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c4),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
+	UNIPHIER_PINMUX_FUNCTION(spi2),
+	UNIPHIER_PINMUX_FUNCTION(spi3),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
index 0b10ebc07eb8..b247011524bf 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld4.c
@@ -576,6 +576,8 @@ static const unsigned nand_cs1_pins[] = {22, 23};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {44, 45, 46, 47, 48, 49, 50, 51, 52};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {135, 136, 137, 138};
+static const int spi0_muxvals[] = {12, 12, 12, 12};
 static const unsigned system_bus_pins[] = {16, 17, 18, 19, 20, 165, 166, 167,
 					   168, 169, 170, 171, 172, 173};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, -1, -1, -1, -1, -1, -1,
@@ -640,6 +642,7 @@ static const struct uniphier_pinctrl_group uniphier_ld4_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -667,6 +670,7 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -690,6 +694,7 @@ static const struct uniphier_pinmux_function uniphier_ld4_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
index 8e4d45fea885..cb58797adaee 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-ld6b.c
@@ -769,6 +769,10 @@ static const unsigned nand_cs1_pins[] = {37, 38};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {47, 48, 49, 50, 51, 52, 53, 54, 55};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {8, 8, 8, 8};
+static const unsigned spi1_pins[] = {93, 94, 95, 96};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					   11, 12, 13};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -851,6 +855,8 @@ static const struct uniphier_pinctrl_group uniphier_ld6b_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs2),
@@ -882,6 +888,8 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1",
 						 "system_bus_cs2",
@@ -907,6 +915,8 @@ static const struct uniphier_pinmux_function uniphier_ld6b_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
index 24788a74c254..89148f81d5e0 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro4.c
@@ -1050,6 +1050,10 @@ static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned sd1_pins[] = {319, 320, 321, 322, 323, 324, 325, 326,
 				    327};
 static const int sd1_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {11, 11, 11, 11};
+static const unsigned spi1_pins[] = {195, 196, 197, 198, 235, 238, 239};
+static const int spi1_muxvals[] = {11, 11, 11, 11, 11, 11, 11};
 static const unsigned system_bus_pins[] = {25, 26, 27, 28, 29, 30, 31, 32, 33,
 					   34, 35, 36, 37, 38};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -1138,6 +1142,8 @@ static const struct uniphier_pinctrl_group uniphier_pro4_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
 	UNIPHIER_PINCTRL_GROUP(sd1),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -1171,6 +1177,8 @@ static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
 static const char * const sd1_groups[] = {"sd1"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -1202,6 +1210,8 @@ static const struct uniphier_pinmux_function uniphier_pro4_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
 	UNIPHIER_PINMUX_FUNCTION(sd1),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
index d5d5e579cb08..d77d6b37aabe 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pro5.c
@@ -818,6 +818,12 @@ static const unsigned nand_cs1_pins[] = {26, 27};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {250, 251, 252, 253, 254, 255, 256, 257, 258};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {120, 121, 122, 123};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {134, 139, 85, 86};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
+static const unsigned spi2_pins[] = {55, 56, 57, 58, 82, 83, 84};
+static const int spi2_muxvals[] = {0, 0, 0, 0, 1, 1, 1};
 static const unsigned system_bus_pins[] = {4, 5, 6, 7, 8, 9, 10, 11, 12, 13,
 					   14, 15, 16, 17};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -904,6 +910,9 @@ static const struct uniphier_pinctrl_group uniphier_pro5_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c5c),
 	UNIPHIER_PINCTRL_GROUP(i2c6),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
+	UNIPHIER_PINCTRL_GROUP(spi2),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs0),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
@@ -934,6 +943,9 @@ static const char * const i2c5_groups[] = {"i2c5", "i2c5b", "i2c5c"};
 static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
+static const char * const spi2_groups[] = {"spi2"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs0",
 						 "system_bus_cs1",
@@ -961,6 +973,9 @@ static const struct uniphier_pinmux_function uniphier_pro5_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c6),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
+	UNIPHIER_PINMUX_FUNCTION(spi2),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
index 032619ad0e73..90199da87eb9 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs2.c
@@ -778,6 +778,10 @@ static const unsigned nand_cs1_pins[] = {37, 38};
 static const int nand_cs1_muxvals[] = {8, 8};
 static const unsigned sd_pins[] = {47, 48, 49, 50, 51, 52, 53, 54, 55};
 static const int sd_muxvals[] = {8, 8, 8, 8, 8, 8, 8, 8, 8};
+static const unsigned spi0_pins[] = {199, 200, 201, 202};
+static const int spi0_muxvals[] = {8, 8, 8, 8};
+static const unsigned spi1_pins[] = {93, 94, 95, 96};
+static const int spi1_muxvals[] = {1, 1, 1, 1};
 static const unsigned system_bus_pins[] = {0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					   11, 12, 13};
 static const int system_bus_muxvals[] = {8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
@@ -861,6 +865,8 @@ static const struct uniphier_pinctrl_group uniphier_pxs2_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -897,6 +903,8 @@ static const char * const i2c5_groups[] = {"i2c5"};
 static const char * const i2c6_groups[] = {"i2c6"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0", "uart0b", "uart0b_ctsrts"};
@@ -928,6 +936,8 @@ static const struct uniphier_pinmux_function uniphier_pxs2_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c6),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
index 535bb2e935e4..3b860da47733 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-pxs3.c
@@ -808,6 +808,10 @@ static const unsigned int nand_pins[] = {16, 17, 18, 19, 20, 21, 22, 23, 24, 25,
 static const int nand_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0};
 static const unsigned int sd_pins[] = {43, 44, 45, 46, 47, 48, 49, 50, 51};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {100, 101, 102, 103};
+static const int spi0_muxvals[] = {0, 0, 0, 0};
+static const unsigned spi1_pins[] = {112, 113, 114, 115};
+static const int spi1_muxvals[] = {2, 2, 2, 2};
 static const unsigned int system_bus_pins[] = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10,
 					       11, 12, 13, 14};
 static const int system_bus_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
@@ -886,6 +890,8 @@ static const struct uniphier_pinctrl_group uniphier_pxs3_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(i2c3),
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
+	UNIPHIER_PINCTRL_GROUP(spi1),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(uart0),
@@ -913,6 +919,8 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
+static const char * const spi1_groups[] = {"spi1"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1"};
 static const char * const uart0_groups[] = {"uart0", "uart0_ctsrts"};
@@ -936,6 +944,8 @@ static const struct uniphier_pinmux_function uniphier_pxs3_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
+	UNIPHIER_PINMUX_FUNCTION(spi1),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
diff --git a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
index 0f921a653164..f086083368a7 100644
--- a/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
+++ b/drivers/pinctrl/uniphier/pinctrl-uniphier-sld8.c
@@ -504,6 +504,8 @@ static const unsigned nand_cs1_pins[] = {22, 23};
 static const int nand_cs1_muxvals[] = {0, 0};
 static const unsigned sd_pins[] = {32, 33, 34, 35, 36, 37, 38, 39, 40};
 static const int sd_muxvals[] = {0, 0, 0, 0, 0, 0, 0, 0, 0};
+static const unsigned spi0_pins[] = {118, 119, 120, 121};
+static const int spi0_muxvals[] = {3, 3, 3, 3};
 static const unsigned system_bus_pins[] = {136, 137, 138, 139, 140, 141, 142,
 					   143, 144, 145, 146, 147, 148, 149};
 static const int system_bus_muxvals[] = {-1, -1, -1, -1, -1, -1, -1, -1, -1,
@@ -570,6 +572,7 @@ static const struct uniphier_pinctrl_group uniphier_sld8_groups[] = {
 	UNIPHIER_PINCTRL_GROUP(nand),
 	UNIPHIER_PINCTRL_GROUP(nand_cs1),
 	UNIPHIER_PINCTRL_GROUP(sd),
+	UNIPHIER_PINCTRL_GROUP(spi0),
 	UNIPHIER_PINCTRL_GROUP(system_bus),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs1),
 	UNIPHIER_PINCTRL_GROUP(system_bus_cs2),
@@ -598,6 +601,7 @@ static const char * const i2c2_groups[] = {"i2c2"};
 static const char * const i2c3_groups[] = {"i2c3"};
 static const char * const nand_groups[] = {"nand", "nand_cs1"};
 static const char * const sd_groups[] = {"sd"};
+static const char * const spi0_groups[] = {"spi0"};
 static const char * const system_bus_groups[] = {"system_bus",
 						 "system_bus_cs1",
 						 "system_bus_cs2",
@@ -622,6 +626,7 @@ static const struct uniphier_pinmux_function uniphier_sld8_functions[] = {
 	UNIPHIER_PINMUX_FUNCTION(i2c3),
 	UNIPHIER_PINMUX_FUNCTION(nand),
 	UNIPHIER_PINMUX_FUNCTION(sd),
+	UNIPHIER_PINMUX_FUNCTION(spi0),
 	UNIPHIER_PINMUX_FUNCTION(system_bus),
 	UNIPHIER_PINMUX_FUNCTION(uart0),
 	UNIPHIER_PINMUX_FUNCTION(uart1),
-- 
cgit v1.2.3


From 222440b4e832059c0ddf18d1e409f0552ab53a7d Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Wed, 4 Jul 2018 12:48:04 +0200
Subject: netfilter: nf_tables: handle meta/lookup with direct call

Currently nft uses inlined variants for common operations
such as 'ip saddr 1.2.3.4' instead of an indirect call.

Also handle meta get operations and lookups without indirect call,
both are builtin.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables_core.h |  7 +++++++
 net/netfilter/nf_tables_core.c         | 16 +++++++++++++++-
 net/netfilter/nft_lookup.c             |  6 +++---
 net/netfilter/nft_meta.c               |  6 +++---
 4 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h
index a05134507e7b..8da837d2aaf9 100644
--- a/include/net/netfilter/nf_tables_core.h
+++ b/include/net/netfilter/nf_tables_core.h
@@ -71,4 +71,11 @@ extern struct nft_set_type nft_set_hash_fast_type;
 extern struct nft_set_type nft_set_rbtree_type;
 extern struct nft_set_type nft_set_bitmap_type;
 
+struct nft_expr;
+struct nft_regs;
+struct nft_pktinfo;
+void nft_meta_get_eval(const struct nft_expr *expr,
+		       struct nft_regs *regs, const struct nft_pktinfo *pkt);
+void nft_lookup_eval(const struct nft_expr *expr,
+		     struct nft_regs *regs, const struct nft_pktinfo *pkt);
 #endif /* _NET_NF_TABLES_CORE_H */
diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index 8de912ca53d3..ffd5c0f9412b 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -120,6 +120,20 @@ struct nft_jumpstack {
 	struct nft_rule	*const *rules;
 };
 
+static void expr_call_ops_eval(const struct nft_expr *expr,
+			       struct nft_regs *regs,
+			       struct nft_pktinfo *pkt)
+{
+	unsigned long e = (unsigned long)expr->ops->eval;
+
+	if (e == (unsigned long)nft_meta_get_eval)
+		nft_meta_get_eval(expr, regs, pkt);
+	else if (e == (unsigned long)nft_lookup_eval)
+		nft_lookup_eval(expr, regs, pkt);
+	else
+		expr->ops->eval(expr, regs, pkt);
+}
+
 unsigned int
 nft_do_chain(struct nft_pktinfo *pkt, void *priv)
 {
@@ -153,7 +167,7 @@ next_rule:
 				nft_cmp_fast_eval(expr, &regs);
 			else if (expr->ops != &nft_payload_fast_ops ||
 				 !nft_payload_fast_eval(expr, &regs, pkt))
-				expr->ops->eval(expr, &regs, pkt);
+				expr_call_ops_eval(expr, &regs, pkt);
 
 			if (regs.verdict.code != NFT_CONTINUE)
 				break;
diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
index c2a1d84cdfc4..ad13e8643599 100644
--- a/net/netfilter/nft_lookup.c
+++ b/net/netfilter/nft_lookup.c
@@ -26,9 +26,9 @@ struct nft_lookup {
 	struct nft_set_binding		binding;
 };
 
-static void nft_lookup_eval(const struct nft_expr *expr,
-			    struct nft_regs *regs,
-			    const struct nft_pktinfo *pkt)
+void nft_lookup_eval(const struct nft_expr *expr,
+		     struct nft_regs *regs,
+		     const struct nft_pktinfo *pkt)
 {
 	const struct nft_lookup *priv = nft_expr_priv(expr);
 	const struct nft_set *set = priv->set;
diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
index 2b94dcc43456..297fe7d97c18 100644
--- a/net/netfilter/nft_meta.c
+++ b/net/netfilter/nft_meta.c
@@ -41,9 +41,9 @@ static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state);
 #include "../bridge/br_private.h"
 #endif
 
-static void nft_meta_get_eval(const struct nft_expr *expr,
-			      struct nft_regs *regs,
-			      const struct nft_pktinfo *pkt)
+void nft_meta_get_eval(const struct nft_expr *expr,
+		       struct nft_regs *regs,
+		       const struct nft_pktinfo *pkt)
 {
 	const struct nft_meta *priv = nft_expr_priv(expr);
 	const struct sk_buff *skb = pkt->skb;
-- 
cgit v1.2.3


From 279fef50b607f9cee94f10bae84f6730e97ccd7c Mon Sep 17 00:00:00 2001
From: Edward Cragg <edward.cragg@codethink.co.uk>
Date: Fri, 27 Jul 2018 13:59:28 +0100
Subject: ASoC: tegra: i2s: Fix typo/broken macro

Fix typo in macro TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK.

Signed-off-by: Edward Cragg <edward.cragg@codethink.co.uk>
Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/tegra/tegra30_i2s.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/tegra/tegra30_i2s.h b/sound/soc/tegra/tegra30_i2s.h
index 774fc6ad2026..2e561e946de2 100644
--- a/sound/soc/tegra/tegra30_i2s.h
+++ b/sound/soc/tegra/tegra30_i2s.h
@@ -173,7 +173,7 @@
 /* Number of slots in frame, minus 1 */
 #define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_SHIFT		16
 #define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK_US	7
-#define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK		(TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOT_MASK_US << TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOT_SHIFT)
+#define TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK		(TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_MASK_US << TEGRA30_I2S_SLOT_CTRL_TOTAL_SLOTS_SHIFT)
 
 /* TDM mode slot enable bitmask */
 #define TEGRA30_I2S_SLOT_CTRL_RX_SLOT_ENABLES_SHIFT	8
-- 
cgit v1.2.3


From c9c9780d8fa526a124933134a7e4041fa09662f6 Mon Sep 17 00:00:00 2001
From: Ladislav Michl <ladis@linux-mips.org>
Date: Sat, 28 Jul 2018 14:30:17 +0200
Subject: ASoC: wm8988: fix typo in rate constraints

Remove duplicated entry and add missing zero in rate constraints.

Signed-off-by: Ladislav Michl <ladis@linux-mips.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8988.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/wm8988.c b/sound/soc/codecs/wm8988.c
index 62200117444b..6e52c6a8bab3 100644
--- a/sound/soc/codecs/wm8988.c
+++ b/sound/soc/codecs/wm8988.c
@@ -522,7 +522,7 @@ static inline int get_coeff(int mclk, int rate)
 /* The set of rates we can generate from the above for each SYSCLK */
 
 static const unsigned int rates_12288[] = {
-	8000, 12000, 16000, 24000, 24000, 32000, 48000, 96000,
+	8000, 12000, 16000, 24000, 32000, 48000, 96000,
 };
 
 static const struct snd_pcm_hw_constraint_list constraints_12288 = {
@@ -540,7 +540,7 @@ static const struct snd_pcm_hw_constraint_list constraints_112896 = {
 };
 
 static const unsigned int rates_12[] = {
-	8000, 11025, 12000, 16000, 22050, 2400, 32000, 41100, 48000,
+	8000, 11025, 12000, 16000, 22050, 24000, 32000, 41100, 48000,
 	48000, 88235, 96000,
 };
 
-- 
cgit v1.2.3


From 5a045bb9c44caebcf4e88bf78343166596c0014b Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:16 +0100
Subject: s390/mm: Make gmap_protect_range more modular

This patch reworks the gmap_protect_range logic and extracts the pte
handling into an own function. Also we do now walk to the pmd and make
it accessible in the function for later use. This way we can add huge
page handling logic more easily.

Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/gmap.c | 93 +++++++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 83 insertions(+), 10 deletions(-)

diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index bc56ec8abcf7..71b0e9ca0137 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -864,7 +864,79 @@ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr,
  */
 static void gmap_pte_op_end(spinlock_t *ptl)
 {
-	spin_unlock(ptl);
+	if (ptl)
+		spin_unlock(ptl);
+}
+
+/**
+ * gmap_pmd_op_walk - walk the gmap tables, get the guest table lock
+ *		      and return the pmd pointer
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ *
+ * Returns a pointer to the pmd for a guest address, or NULL
+ */
+static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr)
+{
+	pmd_t *pmdp;
+
+	BUG_ON(gmap_is_shadow(gmap));
+	spin_lock(&gmap->guest_table_lock);
+	pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1);
+
+	if (!pmdp || pmd_none(*pmdp)) {
+		spin_unlock(&gmap->guest_table_lock);
+		return NULL;
+	}
+
+	/* 4k page table entries are locked via the pte (pte_alloc_map_lock). */
+	if (!pmd_large(*pmdp))
+		spin_unlock(&gmap->guest_table_lock);
+	return pmdp;
+}
+
+/**
+ * gmap_pmd_op_end - release the guest_table_lock if needed
+ * @gmap: pointer to the guest mapping meta data structure
+ * @pmdp: pointer to the pmd
+ */
+static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp)
+{
+	if (pmd_large(*pmdp))
+		spin_unlock(&gmap->guest_table_lock);
+}
+
+/*
+ * gmap_protect_pte - remove access rights to memory and set pgste bits
+ * @gmap: pointer to guest mapping meta data structure
+ * @gaddr: virtual address in the guest address space
+ * @pmdp: pointer to the pmd associated with the pte
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: pgste notification bits to set
+ *
+ * Returns 0 if successfully protected, -ENOMEM if out of memory and
+ * -EAGAIN if a fixup is needed.
+ *
+ * Expected to be called with sg->mm->mmap_sem in read
+ */
+static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
+			    pmd_t *pmdp, int prot, unsigned long bits)
+{
+	int rc;
+	pte_t *ptep;
+	spinlock_t *ptl = NULL;
+
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+		return -EAGAIN;
+
+	ptep = pte_alloc_map_lock(gmap->mm, pmdp, gaddr, &ptl);
+	if (!ptep)
+		return -ENOMEM;
+
+	/* Protect and unlock. */
+	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
+	gmap_pte_op_end(ptl);
+	return rc;
 }
 
 /*
@@ -884,17 +956,21 @@ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
 			      unsigned long len, int prot, unsigned long bits)
 {
 	unsigned long vmaddr;
-	spinlock_t *ptl;
-	pte_t *ptep;
+	pmd_t *pmdp;
 	int rc;
 
 	BUG_ON(gmap_is_shadow(gmap));
 	while (len) {
 		rc = -EAGAIN;
-		ptep = gmap_pte_op_walk(gmap, gaddr, &ptl);
-		if (ptep) {
-			rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
-			gmap_pte_op_end(ptl);
+		pmdp = gmap_pmd_op_walk(gmap, gaddr);
+		if (pmdp) {
+			rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
+					      bits);
+			if (!rc) {
+				len -= PAGE_SIZE;
+				gaddr += PAGE_SIZE;
+			}
+			gmap_pmd_op_end(gmap, pmdp);
 		}
 		if (rc) {
 			vmaddr = __gmap_translate(gmap, gaddr);
@@ -903,10 +979,7 @@ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
 			rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot);
 			if (rc)
 				return rc;
-			continue;
 		}
-		gaddr += PAGE_SIZE;
-		len -= PAGE_SIZE;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 2c46e974dd8b5316e65637af0ff6d4bc78554b2e Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:18 +0100
Subject: s390/mm: Abstract gmap notify bit setting

Currently we use the software PGSTE bits PGSTE_IN_BIT and
PGSTE_VSIE_BIT to notify before an invalidation occurs on a prefix
page or a VSIE page respectively. Both bits are pgste specific, but
are used when protecting a memory range.

Let's introduce abstract GMAP_NOTIFY_* bits that will be realized into
the respective bits when gmap DAT table entries are protected.

Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/include/asm/gmap.h |  4 ++++
 arch/s390/mm/gmap.c          | 11 +++++++----
 2 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index e07cce88dfb0..c1bc5633fc6e 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -9,6 +9,10 @@
 #ifndef _ASM_S390_GMAP_H
 #define _ASM_S390_GMAP_H
 
+/* Generic bits for GMAP notification on DAT table entry changes. */
+#define GMAP_NOTIFY_SHADOW	0x2
+#define GMAP_NOTIFY_MPROT	0x1
+
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 71b0e9ca0137..0bada5e097cb 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -912,7 +912,7 @@ static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp)
  * @gaddr: virtual address in the guest address space
  * @pmdp: pointer to the pmd associated with the pte
  * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
- * @bits: pgste notification bits to set
+ * @bits: notification bits to set
  *
  * Returns 0 if successfully protected, -ENOMEM if out of memory and
  * -EAGAIN if a fixup is needed.
@@ -925,6 +925,7 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
 	int rc;
 	pte_t *ptep;
 	spinlock_t *ptl = NULL;
+	unsigned long pbits = 0;
 
 	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
 		return -EAGAIN;
@@ -933,8 +934,10 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
 	if (!ptep)
 		return -ENOMEM;
 
+	pbits |= (bits & GMAP_NOTIFY_MPROT) ? PGSTE_IN_BIT : 0;
+	pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0;
 	/* Protect and unlock. */
-	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, bits);
+	rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits);
 	gmap_pte_op_end(ptl);
 	return rc;
 }
@@ -1008,7 +1011,7 @@ int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr,
 	if (!MACHINE_HAS_ESOP && prot == PROT_READ)
 		return -EINVAL;
 	down_read(&gmap->mm->mmap_sem);
-	rc = gmap_protect_range(gmap, gaddr, len, prot, PGSTE_IN_BIT);
+	rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT);
 	up_read(&gmap->mm->mmap_sem);
 	return rc;
 }
@@ -1599,7 +1602,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 	down_read(&parent->mm->mmap_sem);
 	rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN,
 				((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE,
-				PROT_READ, PGSTE_VSIE_BIT);
+				PROT_READ, GMAP_NOTIFY_SHADOW);
 	up_read(&parent->mm->mmap_sem);
 	spin_lock(&parent->shadow_lock);
 	new->initialized = true;
-- 
cgit v1.2.3


From 58b7e200d2f1f9af9ef69a401a877791837a1c87 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:20 +0100
Subject: s390/mm: Add gmap pmd linking

Let's allow pmds to be linked into gmap for the upcoming s390 KVM huge
page support.

Before this patch we copied the full userspace pmd entry. This is not
correct, as it contains SW defined bits that might be interpreted
differently in the GMAP context. Now we only copy over all hardware
relevant information leaving out the software bits.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/include/asm/pgtable.h |  6 ++++--
 arch/s390/mm/gmap.c             | 13 +++++++++----
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 5ab636089c60..fe36b3bb2afd 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -268,8 +268,10 @@ static inline int is_module_addr(void *addr)
 #define _REGION_ENTRY_BITS_LARGE 0xffffffff8000fe2fUL
 
 /* Bits in the segment table entry */
-#define _SEGMENT_ENTRY_BITS	0xfffffffffffffe33UL
-#define _SEGMENT_ENTRY_BITS_LARGE 0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_BITS			0xfffffffffffffe33UL
+#define _SEGMENT_ENTRY_BITS_LARGE		0xfffffffffff0ff33UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS		0xfffffffffffffe30UL
+#define _SEGMENT_ENTRY_HARDWARE_BITS_LARGE	0xfffffffffff00730UL
 #define _SEGMENT_ENTRY_ORIGIN_LARGE ~0xfffffUL /* large page address	    */
 #define _SEGMENT_ENTRY_ORIGIN	~0x7ffUL/* page table origin		    */
 #define _SEGMENT_ENTRY_PROTECT	0x200	/* segment protection bit	    */
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 0bada5e097cb..870e81fcb0cf 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -596,10 +596,15 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	if (*table == _SEGMENT_ENTRY_EMPTY) {
 		rc = radix_tree_insert(&gmap->host_to_guest,
 				       vmaddr >> PMD_SHIFT, table);
-		if (!rc)
-			*table = pmd_val(*pmd);
-	} else
-		rc = 0;
+		if (!rc) {
+			if (pmd_large(*pmd)) {
+				*table = pmd_val(*pmd) &
+					_SEGMENT_ENTRY_HARDWARE_BITS_LARGE;
+			} else
+				*table = pmd_val(*pmd) &
+					_SEGMENT_ENTRY_HARDWARE_BITS;
+		}
+	}
 	spin_unlock(&gmap->guest_table_lock);
 	spin_unlock(ptl);
 	radix_tree_preload_end();
-- 
cgit v1.2.3


From 7c4b13a7c042fd6b71dc48d291208f8a97fad333 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:21 +0100
Subject: s390/mm: Add gmap pmd notification bit setting

Like for ptes, we also need invalidation notification for pmds, to
make sure the guest lowcore pages are always accessible and later
addition of shadowed pmds.

With PMDs we do not have PGSTEs or some other bits we could use in the
host PMD. Instead we pick one of the free bits in the gmap PMD. Every
time a host pmd will be invalidated, we will check if the respective
gmap PMD has the bit set and in that case fire up the notifier.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/include/asm/gmap.h |  3 +++
 arch/s390/mm/gmap.c          | 60 +++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 57 insertions(+), 6 deletions(-)

diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index c1bc5633fc6e..276268b48aff 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -13,6 +13,9 @@
 #define GMAP_NOTIFY_SHADOW	0x2
 #define GMAP_NOTIFY_MPROT	0x1
 
+/* Status bits only for huge segment entries */
+#define _SEGMENT_ENTRY_GMAP_IN		0x8000	/* invalidation notify bit */
+
 /**
  * struct gmap_struct - guest address space
  * @list: list head for the mm->context gmap list
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 870e81fcb0cf..96dd94d51ad4 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -911,6 +911,40 @@ static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp)
 		spin_unlock(&gmap->guest_table_lock);
 }
 
+/*
+ * gmap_protect_pmd - remove access rights to memory and set pmd notification bits
+ * @pmdp: pointer to the pmd to be protected
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: notification bits to set
+ *
+ * Returns:
+ * 0 if successfully protected
+ * -EAGAIN if a fixup is needed
+ * -EINVAL if unsupported notifier bits have been specified
+ *
+ * Expected to be called with sg->mm->mmap_sem in read and
+ * guest_table_lock held.
+ */
+static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr,
+			    pmd_t *pmdp, int prot, unsigned long bits)
+{
+	int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID;
+	int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT;
+
+	/* Fixup needed */
+	if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE)))
+		return -EAGAIN;
+
+	if (bits & GMAP_NOTIFY_MPROT)
+		pmd_val(*pmdp) |= _SEGMENT_ENTRY_GMAP_IN;
+
+	/* Shadow GMAP protection needs split PMDs */
+	if (bits & GMAP_NOTIFY_SHADOW)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * gmap_protect_pte - remove access rights to memory and set pgste bits
  * @gmap: pointer to guest mapping meta data structure
@@ -963,7 +997,7 @@ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr,
 static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
 			      unsigned long len, int prot, unsigned long bits)
 {
-	unsigned long vmaddr;
+	unsigned long vmaddr, dist;
 	pmd_t *pmdp;
 	int rc;
 
@@ -972,15 +1006,29 @@ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr,
 		rc = -EAGAIN;
 		pmdp = gmap_pmd_op_walk(gmap, gaddr);
 		if (pmdp) {
-			rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
-					      bits);
-			if (!rc) {
-				len -= PAGE_SIZE;
-				gaddr += PAGE_SIZE;
+			if (!pmd_large(*pmdp)) {
+				rc = gmap_protect_pte(gmap, gaddr, pmdp, prot,
+						      bits);
+				if (!rc) {
+					len -= PAGE_SIZE;
+					gaddr += PAGE_SIZE;
+				}
+			} else {
+				rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot,
+						      bits);
+				if (!rc) {
+					dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK);
+					len = len < dist ? 0 : len - dist;
+					gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE;
+				}
 			}
 			gmap_pmd_op_end(gmap, pmdp);
 		}
 		if (rc) {
+			if (rc == -EINVAL)
+				return rc;
+
+			/* -EAGAIN, fixup of userspace mm and gmap */
 			vmaddr = __gmap_translate(gmap, gaddr);
 			if (IS_ERR_VALUE(vmaddr))
 				return vmaddr;
-- 
cgit v1.2.3


From 6a3762778d1ba1a58ab473124790cd612d10eadc Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:22 +0100
Subject: s390/mm: Add gmap pmd invalidation and clearing

If the host invalidates a pmd, we also have to invalidate the
corresponding gmap pmds, as well as flush them from the TLB. This is
necessary, as we don't share the pmd tables between host and guest as
we do with ptes.

The clearing part of these three new functions sets a guest pmd entry
to _SEGMENT_ENTRY_EMPTY, so the guest will fault on it and we will
re-link it.

Flushing the gmap is not necessary in the host's lazy local and csp
cases. Both purge the TLB completely.

Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/include/asm/pgtable.h |   4 ++
 arch/s390/mm/gmap.c             | 125 ++++++++++++++++++++++++++++++++++++++++
 arch/s390/mm/pgtable.c          |  17 +++++-
 3 files changed, 143 insertions(+), 3 deletions(-)

diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index fe36b3bb2afd..087e0282f165 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1118,6 +1118,10 @@ int set_pgste_bits(struct mm_struct *mm, unsigned long addr,
 int get_pgste(struct mm_struct *mm, unsigned long hva, unsigned long *pgstep);
 int pgste_perform_essa(struct mm_struct *mm, unsigned long hva, int orc,
 			unsigned long *oldpte, unsigned long *oldpgste);
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr);
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr);
 
 /*
  * Certain architectures need to do special things when PTEs
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 96dd94d51ad4..87c174ee3a8c 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2221,6 +2221,131 @@ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr,
 }
 EXPORT_SYMBOL_GPL(ptep_notify);
 
+static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp,
+			     unsigned long gaddr)
+{
+	pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_IN;
+	gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1);
+}
+
+static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
+			    int purge)
+{
+	pmd_t *pmdp;
+	struct gmap *gmap;
+	unsigned long gaddr;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest,
+						  vmaddr >> PMD_SHIFT);
+		if (pmdp) {
+			gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(pmd_val(*pmdp) & ~_SEGMENT_ENTRY_HARDWARE_BITS_LARGE);
+			if (purge)
+				__pmdp_csp(pmdp);
+			pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+
+/**
+ * gmap_pmdp_invalidate - invalidate all affected guest pmd entries without
+ *                        flushing
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr)
+{
+	gmap_pmdp_clear(mm, vmaddr, 0);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_invalidate);
+
+/**
+ * gmap_pmdp_csp - csp all affected guest pmd entries
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr)
+{
+	gmap_pmdp_clear(mm, vmaddr, 1);
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_csp);
+
+/**
+ * gmap_pmdp_idte_local - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
+{
+	unsigned long *entry, gaddr;
+	struct gmap *gmap;
+	pmd_t *pmdp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		entry = radix_tree_delete(&gmap->host_to_guest,
+					  vmaddr >> PMD_SHIFT);
+		if (entry) {
+			pmdp = (pmd_t *)entry;
+			gaddr = __gmap_segment_gaddr(entry);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(*entry & ~_SEGMENT_ENTRY_HARDWARE_BITS_LARGE);
+			if (MACHINE_HAS_TLB_GUEST)
+				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+					    gmap->asce, IDTE_LOCAL);
+			else if (MACHINE_HAS_IDTE)
+				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL);
+			*entry = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local);
+
+/**
+ * gmap_pmdp_idte_global - invalidate and clear a guest pmd entry
+ * @mm: pointer to the process mm_struct
+ * @vmaddr: virtual address in the process address space
+ */
+void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
+{
+	unsigned long *entry, gaddr;
+	struct gmap *gmap;
+	pmd_t *pmdp;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) {
+		spin_lock(&gmap->guest_table_lock);
+		entry = radix_tree_delete(&gmap->host_to_guest,
+					  vmaddr >> PMD_SHIFT);
+		if (entry) {
+			pmdp = (pmd_t *)entry;
+			gaddr = __gmap_segment_gaddr(entry);
+			pmdp_notify_gmap(gmap, pmdp, gaddr);
+			WARN_ON(*entry & ~_SEGMENT_ENTRY_HARDWARE_BITS_LARGE);
+			if (MACHINE_HAS_TLB_GUEST)
+				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
+					    gmap->asce, IDTE_GLOBAL);
+			else if (MACHINE_HAS_IDTE)
+				__pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL);
+			else
+				__pmdp_csp(pmdp);
+			*entry = _SEGMENT_ENTRY_EMPTY;
+		}
+		spin_unlock(&gmap->guest_table_lock);
+	}
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global);
+
 static inline void thp_split_mm(struct mm_struct *mm)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 301e466e4263..fe84c0715395 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -347,18 +347,27 @@ static inline void pmdp_idte_local(struct mm_struct *mm,
 			    mm->context.asce, IDTE_LOCAL);
 	else
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL);
+	if (mm_has_pgste(mm))
+		gmap_pmdp_idte_local(mm, addr);
 }
 
 static inline void pmdp_idte_global(struct mm_struct *mm,
 				    unsigned long addr, pmd_t *pmdp)
 {
-	if (MACHINE_HAS_TLB_GUEST)
+	if (MACHINE_HAS_TLB_GUEST) {
 		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_GLOBAL);
-	else if (MACHINE_HAS_IDTE)
+		if (mm_has_pgste(mm))
+			gmap_pmdp_idte_global(mm, addr);
+	} else if (MACHINE_HAS_IDTE) {
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
-	else
+		if (mm_has_pgste(mm))
+			gmap_pmdp_idte_global(mm, addr);
+	} else {
 		__pmdp_csp(pmdp);
+		if (mm_has_pgste(mm))
+			gmap_pmdp_csp(mm, addr);
+	}
 }
 
 static inline pmd_t pmdp_flush_direct(struct mm_struct *mm,
@@ -392,6 +401,8 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 			  cpumask_of(smp_processor_id()))) {
 		pmd_val(*pmdp) |= _SEGMENT_ENTRY_INVALID;
 		mm->context.flush_mm = 1;
+		if (mm_has_pgste(mm))
+			gmap_pmdp_invalidate(mm, addr);
 	} else {
 		pmdp_idte_global(mm, addr, pmdp);
 	}
-- 
cgit v1.2.3


From 0959e168678d2d95648317e1e5e46bcb358272eb Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Tue, 17 Jul 2018 13:21:22 +0100
Subject: s390/mm: Add huge page dirty sync support

To do dirty loging with huge pages, we protect huge pmds in the
gmap. When they are written to, we unprotect them and mark them dirty.

We introduce the function gmap_test_and_clear_dirty_pmd which handles
dirty sync for huge pages.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/include/asm/gmap.h    |   3 +
 arch/s390/include/asm/pgtable.h |   3 +-
 arch/s390/kvm/kvm-s390.c        |  25 +++++---
 arch/s390/mm/gmap.c             | 127 ++++++++++++++++++++++++++++++++++++++--
 arch/s390/mm/pgtable.c          |  34 +----------
 5 files changed, 148 insertions(+), 44 deletions(-)

diff --git a/arch/s390/include/asm/gmap.h b/arch/s390/include/asm/gmap.h
index 276268b48aff..fcbd638fb9f4 100644
--- a/arch/s390/include/asm/gmap.h
+++ b/arch/s390/include/asm/gmap.h
@@ -15,6 +15,7 @@
 
 /* Status bits only for huge segment entries */
 #define _SEGMENT_ENTRY_GMAP_IN		0x8000	/* invalidation notify bit */
+#define _SEGMENT_ENTRY_GMAP_UC		0x4000	/* dirty (migration) */
 
 /**
  * struct gmap_struct - guest address space
@@ -139,4 +140,6 @@ void gmap_pte_notify(struct mm_struct *, unsigned long addr, pte_t *,
 int gmap_mprotect_notify(struct gmap *, unsigned long start,
 			 unsigned long len, int prot);
 
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long dirty_bitmap[4],
+			     unsigned long gaddr, unsigned long vmaddr);
 #endif /* _ASM_S390_GMAP_H */
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 087e0282f165..0e7cb0dc9c33 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1103,7 +1103,8 @@ int ptep_shadow_pte(struct mm_struct *mm, unsigned long saddr,
 		    pte_t *sptep, pte_t *tptep, pte_t pte);
 void ptep_unshadow_pte(struct mm_struct *mm, unsigned long saddr, pte_t *ptep);
 
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long address);
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long address,
+			    pte_t *ptep);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq);
 int cond_set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 3b7a5151b6a5..4cff5e31ca36 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -511,19 +511,30 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 }
 
 static void kvm_s390_sync_dirty_log(struct kvm *kvm,
-					struct kvm_memory_slot *memslot)
+				    struct kvm_memory_slot *memslot)
 {
+	int i;
 	gfn_t cur_gfn, last_gfn;
-	unsigned long address;
+	unsigned long gaddr, vmaddr;
 	struct gmap *gmap = kvm->arch.gmap;
+	DECLARE_BITMAP(bitmap, _PAGE_ENTRIES);
 
-	/* Loop over all guest pages */
+	/* Loop over all guest segments */
+	cur_gfn = memslot->base_gfn;
 	last_gfn = memslot->base_gfn + memslot->npages;
-	for (cur_gfn = memslot->base_gfn; cur_gfn <= last_gfn; cur_gfn++) {
-		address = gfn_to_hva_memslot(memslot, cur_gfn);
+	for (; cur_gfn <= last_gfn; cur_gfn += _PAGE_ENTRIES) {
+		gaddr = gfn_to_gpa(cur_gfn);
+		vmaddr = gfn_to_hva_memslot(memslot, cur_gfn);
+		if (kvm_is_error_hva(vmaddr))
+			continue;
+
+		bitmap_zero(bitmap, _PAGE_ENTRIES);
+		gmap_sync_dirty_log_pmd(gmap, bitmap, gaddr, vmaddr);
+		for (i = 0; i < _PAGE_ENTRIES; i++) {
+			if (test_bit(i, bitmap))
+				mark_page_dirty(kvm, cur_gfn + i);
+		}
 
-		if (test_and_clear_guest_dirty(gmap->mm, address))
-			mark_page_dirty(kvm, cur_gfn);
 		if (fatal_signal_pending(current))
 			return;
 		cond_resched();
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 87c174ee3a8c..3807de25a706 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -521,6 +521,9 @@ void gmap_unlink(struct mm_struct *mm, unsigned long *table,
 	rcu_read_unlock();
 }
 
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *old, pmd_t new,
+			   unsigned long gaddr);
+
 /**
  * gmap_link - set up shadow page tables to connect a host to a guest address
  * @gmap: pointer to guest mapping meta data structure
@@ -541,6 +544,7 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd;
+	u64 unprot;
 	int rc;
 
 	BUG_ON(gmap_is_shadow(gmap));
@@ -598,12 +602,19 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 				       vmaddr >> PMD_SHIFT, table);
 		if (!rc) {
 			if (pmd_large(*pmd)) {
-				*table = pmd_val(*pmd) &
-					_SEGMENT_ENTRY_HARDWARE_BITS_LARGE;
+				*table = (pmd_val(*pmd) &
+					  _SEGMENT_ENTRY_HARDWARE_BITS_LARGE)
+					| _SEGMENT_ENTRY_GMAP_UC;
 			} else
 				*table = pmd_val(*pmd) &
 					_SEGMENT_ENTRY_HARDWARE_BITS;
 		}
+	} else if (*table & _SEGMENT_ENTRY_PROTECT &&
+		   !(pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT)) {
+		unprot = (u64)*table;
+		unprot &= ~_SEGMENT_ENTRY_PROTECT;
+		unprot |= _SEGMENT_ENTRY_GMAP_UC;
+		gmap_pmdp_xchg(gmap, (pmd_t *)table, __pmd(unprot), gaddr);
 	}
 	spin_unlock(&gmap->guest_table_lock);
 	spin_unlock(ptl);
@@ -930,11 +941,23 @@ static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr,
 {
 	int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID;
 	int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT;
+	pmd_t new = *pmdp;
 
 	/* Fixup needed */
 	if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE)))
 		return -EAGAIN;
 
+	if (prot == PROT_NONE && !pmd_i) {
+		pmd_val(new) |= _SEGMENT_ENTRY_INVALID;
+		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+	}
+
+	if (prot == PROT_READ && !pmd_p) {
+		pmd_val(new) &= ~_SEGMENT_ENTRY_INVALID;
+		pmd_val(new) |= _SEGMENT_ENTRY_PROTECT;
+		gmap_pmdp_xchg(gmap, pmdp, new, gaddr);
+	}
+
 	if (bits & GMAP_NOTIFY_MPROT)
 		pmd_val(*pmdp) |= _SEGMENT_ENTRY_GMAP_IN;
 
@@ -2228,6 +2251,32 @@ static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp,
 	gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1);
 }
 
+/**
+ * gmap_pmdp_xchg - exchange a gmap pmd with another
+ * @gmap: pointer to the guest address space structure
+ * @pmdp: pointer to the pmd entry
+ * @new: replacement entry
+ * @gaddr: the affected guest address
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new,
+			   unsigned long gaddr)
+{
+	gaddr &= HPAGE_MASK;
+	pmdp_notify_gmap(gmap, pmdp, gaddr);
+	pmd_val(new) &= ~_SEGMENT_ENTRY_GMAP_IN;
+	if (MACHINE_HAS_TLB_GUEST)
+		__pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce,
+			    IDTE_GLOBAL);
+	else if (MACHINE_HAS_IDTE)
+		__pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL);
+	else
+		__pmdp_csp(pmdp);
+	*pmdp = new;
+}
+
 static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
 			    int purge)
 {
@@ -2243,7 +2292,8 @@ static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr,
 		if (pmdp) {
 			gaddr = __gmap_segment_gaddr((unsigned long *)pmdp);
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
-			WARN_ON(pmd_val(*pmdp) & ~_SEGMENT_ENTRY_HARDWARE_BITS_LARGE);
+			WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+						   _SEGMENT_ENTRY_GMAP_UC));
 			if (purge)
 				__pmdp_csp(pmdp);
 			pmd_val(*pmdp) = _SEGMENT_ENTRY_EMPTY;
@@ -2296,7 +2346,8 @@ void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr)
 			pmdp = (pmd_t *)entry;
 			gaddr = __gmap_segment_gaddr(entry);
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
-			WARN_ON(*entry & ~_SEGMENT_ENTRY_HARDWARE_BITS_LARGE);
+			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+					   _SEGMENT_ENTRY_GMAP_UC));
 			if (MACHINE_HAS_TLB_GUEST)
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_LOCAL);
@@ -2330,7 +2381,8 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
 			pmdp = (pmd_t *)entry;
 			gaddr = __gmap_segment_gaddr(entry);
 			pmdp_notify_gmap(gmap, pmdp, gaddr);
-			WARN_ON(*entry & ~_SEGMENT_ENTRY_HARDWARE_BITS_LARGE);
+			WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE |
+					   _SEGMENT_ENTRY_GMAP_UC));
 			if (MACHINE_HAS_TLB_GUEST)
 				__pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE,
 					    gmap->asce, IDTE_GLOBAL);
@@ -2346,6 +2398,71 @@ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr)
 }
 EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global);
 
+/**
+ * gmap_test_and_clear_dirty_pmd - test and reset segment dirty status
+ * @gmap: pointer to guest address space
+ * @pmdp: pointer to the pmd to be tested
+ * @gaddr: virtual address in the guest address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp,
+				   unsigned long gaddr)
+{
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID)
+		return false;
+
+	/* Already protected memory, which did not change is clean */
+	if (pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT &&
+	    !(pmd_val(*pmdp) & _SEGMENT_ENTRY_GMAP_UC))
+		return false;
+
+	/* Clear UC indication and reset protection */
+	pmd_val(*pmdp) &= ~_SEGMENT_ENTRY_GMAP_UC;
+	gmap_protect_pmd(gmap, gaddr, pmdp, PROT_READ, 0);
+	return true;
+}
+
+/**
+ * gmap_sync_dirty_log_pmd - set bitmap based on dirty status of segment
+ * @gmap: pointer to guest address space
+ * @bitmap: dirty bitmap for this pmd
+ * @gaddr: virtual address in the guest address space
+ * @vmaddr: virtual address in the host address space
+ *
+ * This function is assumed to be called with the guest_table_lock
+ * held.
+ */
+void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4],
+			     unsigned long gaddr, unsigned long vmaddr)
+{
+	int i;
+	pmd_t *pmdp;
+	pte_t *ptep;
+	spinlock_t *ptl;
+
+	pmdp = gmap_pmd_op_walk(gmap, gaddr);
+	if (!pmdp)
+		return;
+
+	if (pmd_large(*pmdp)) {
+		if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr))
+			bitmap_fill(bitmap, _PAGE_ENTRIES);
+	} else {
+		for (i = 0; i < _PAGE_ENTRIES; i++, vmaddr += PAGE_SIZE) {
+			ptep = pte_alloc_map_lock(gmap->mm, pmdp, vmaddr, &ptl);
+			if (!ptep)
+				continue;
+			if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep))
+				set_bit(i, bitmap);
+			spin_unlock(ptl);
+		}
+	}
+	gmap_pmd_op_end(gmap, pmdp);
+}
+EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd);
+
 static inline void thp_split_mm(struct mm_struct *mm)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index fe84c0715395..684df964e345 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -704,40 +704,14 @@ void ptep_zap_key(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 /*
  * Test and reset if a guest page is dirty
  */
-bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
+bool ptep_test_and_clear_uc(struct mm_struct *mm, unsigned long addr,
+		       pte_t *ptep)
 {
-	spinlock_t *ptl;
-	pgd_t *pgd;
-	p4d_t *p4d;
-	pud_t *pud;
-	pmd_t *pmd;
 	pgste_t pgste;
-	pte_t *ptep;
 	pte_t pte;
 	bool dirty;
 	int nodat;
 
-	pgd = pgd_offset(mm, addr);
-	p4d = p4d_alloc(mm, pgd, addr);
-	if (!p4d)
-		return false;
-	pud = pud_alloc(mm, p4d, addr);
-	if (!pud)
-		return false;
-	pmd = pmd_alloc(mm, pud, addr);
-	if (!pmd)
-		return false;
-	/* We can't run guests backed by huge pages, but userspace can
-	 * still set them up and then try to migrate them without any
-	 * migration support.
-	 */
-	if (pmd_large(*pmd))
-		return true;
-
-	ptep = pte_alloc_map_lock(mm, pmd, addr, &ptl);
-	if (unlikely(!ptep))
-		return false;
-
 	pgste = pgste_get_lock(ptep);
 	dirty = !!(pgste_val(pgste) & PGSTE_UC_BIT);
 	pgste_val(pgste) &= ~PGSTE_UC_BIT;
@@ -753,11 +727,9 @@ bool test_and_clear_guest_dirty(struct mm_struct *mm, unsigned long addr)
 		*ptep = pte;
 	}
 	pgste_set_unlock(ptep, pgste);
-
-	spin_unlock(ptl);
 	return dirty;
 }
-EXPORT_SYMBOL_GPL(test_and_clear_guest_dirty);
+EXPORT_SYMBOL_GPL(ptep_test_and_clear_uc);
 
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq)
-- 
cgit v1.2.3


From 964c2c05c9f3095a18387a57b289cf06de637521 Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 11:28:25 +0100
Subject: s390/mm: Clear huge page storage keys on enable_skey

When a guest starts using storage keys, we trap and set a default one
for its whole valid address space. With this patch we are now able to
do that for large pages.

To speed up the storage key insertion, we use
__storage_key_init_range, which in-turn will use sske_frame to set
multiple storage keys with one instruction. As it has been previously
used for debuging we have to get rid of the default key check and make
it quiescing.

Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
[replaced page_set_storage_key loop with __storage_key_init_range]
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/mm/gmap.c     | 32 +++++++++++++++++++++++++++++---
 arch/s390/mm/pageattr.c |  6 ++----
 2 files changed, 31 insertions(+), 7 deletions(-)

diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 3807de25a706..a8e32e60226b 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2539,17 +2539,43 @@ EXPORT_SYMBOL_GPL(s390_enable_sie);
  * Enable storage key handling from now on and initialize the storage
  * keys with the default key.
  */
-static int __s390_enable_skey(pte_t *pte, unsigned long addr,
-			      unsigned long next, struct mm_walk *walk)
+static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr,
+				  unsigned long next, struct mm_walk *walk)
 {
 	/* Clear storage key */
 	ptep_zap_key(walk->mm, addr, pte);
 	return 0;
 }
 
+static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
+				      unsigned long hmask, unsigned long next,
+				      struct mm_walk *walk)
+{
+	pmd_t *pmd = (pmd_t *)pte;
+	unsigned long start, end;
+
+	/*
+	 * The write check makes sure we do not set a key on shared
+	 * memory. This is needed as the walker does not differentiate
+	 * between actual guest memory and the process executable or
+	 * shared libraries.
+	 */
+	if (pmd_val(*pmd) & _SEGMENT_ENTRY_INVALID ||
+	    !(pmd_val(*pmd) & _SEGMENT_ENTRY_WRITE))
+		return 0;
+
+	start = pmd_val(*pmd) & HPAGE_MASK;
+	end = start + HPAGE_SIZE - 1;
+	__storage_key_init_range(start, end);
+	return 0;
+}
+
 int s390_enable_skey(void)
 {
-	struct mm_walk walk = { .pte_entry = __s390_enable_skey };
+	struct mm_walk walk = {
+		.hugetlb_entry = __s390_enable_skey_hugetlb,
+		.pte_entry = __s390_enable_skey_pte,
+	};
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	int rc = 0;
diff --git a/arch/s390/mm/pageattr.c b/arch/s390/mm/pageattr.c
index c44171588d08..f8c6faab41f4 100644
--- a/arch/s390/mm/pageattr.c
+++ b/arch/s390/mm/pageattr.c
@@ -14,7 +14,7 @@
 
 static inline unsigned long sske_frame(unsigned long addr, unsigned char skey)
 {
-	asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],9,0"
+	asm volatile(".insn rrf,0xb22b0000,%[skey],%[addr],1,0"
 		     : [addr] "+a" (addr) : [skey] "d" (skey));
 	return addr;
 }
@@ -23,8 +23,6 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 {
 	unsigned long boundary, size;
 
-	if (!PAGE_DEFAULT_KEY)
-		return;
 	while (start < end) {
 		if (MACHINE_HAS_EDAT1) {
 			/* set storage keys for a 1MB frame */
@@ -37,7 +35,7 @@ void __storage_key_init_range(unsigned long start, unsigned long end)
 				continue;
 			}
 		}
-		page_set_storage_key(start, PAGE_DEFAULT_KEY, 0);
+		page_set_storage_key(start, PAGE_DEFAULT_KEY, 1);
 		start += PAGE_SIZE;
 	}
 }
-- 
cgit v1.2.3


From 3afdfca69870963ae01e280732a5ee493a2fcbb3 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:26 +0100
Subject: s390/mm: Clear skeys for newly mapped huge guest pmds

Similarly to the pte skey handling, where we set the storage key to
the default key for each newly mapped pte, we have to also do that for
huge pmds.

With the PG_arch_1 flag we keep track if the area has already been
cleared of its skeys.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/hugetlb.h |  5 ++++-
 arch/s390/mm/gmap.c             |  2 ++
 arch/s390/mm/hugetlbpage.c      | 24 ++++++++++++++++++++++++
 3 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 9c5fc50204dd..2d1afa58a4b6 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -37,7 +37,10 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-#define arch_clear_hugepage_flags(page)		do { } while (0)
+static inline void arch_clear_hugepage_flags(struct page *page)
+{
+	clear_bit(PG_arch_1, &page->flags);
+}
 
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index a8e32e60226b..a6738c0c4499 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2553,6 +2553,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
 {
 	pmd_t *pmd = (pmd_t *)pte;
 	unsigned long start, end;
+	struct page *page = pmd_page(*pmd);
 
 	/*
 	 * The write check makes sure we do not set a key on shared
@@ -2567,6 +2568,7 @@ static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr,
 	start = pmd_val(*pmd) & HPAGE_MASK;
 	end = start + HPAGE_SIZE - 1;
 	__storage_key_init_range(start, end);
+	set_bit(PG_arch_1, &page->flags);
 	return 0;
 }
 
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index e804090f4470..b0246c705a19 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -123,6 +123,29 @@ static inline pte_t __rste_to_pte(unsigned long rste)
 	return pte;
 }
 
+static void clear_huge_pte_skeys(struct mm_struct *mm, unsigned long rste)
+{
+	struct page *page;
+	unsigned long size, paddr;
+
+	if (!mm_uses_skeys(mm) ||
+	    rste & _SEGMENT_ENTRY_INVALID)
+		return;
+
+	if ((rste & _REGION_ENTRY_TYPE_MASK) == _REGION_ENTRY_TYPE_R3) {
+		page = pud_page(__pud(rste));
+		size = PUD_SIZE;
+		paddr = rste & PUD_MASK;
+	} else {
+		page = pmd_page(__pmd(rste));
+		size = PMD_SIZE;
+		paddr = rste & PMD_MASK;
+	}
+
+	if (!test_and_set_bit(PG_arch_1, &page->flags))
+		__storage_key_init_range(paddr, paddr + size - 1);
+}
+
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte)
 {
@@ -137,6 +160,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		rste |= _REGION_ENTRY_TYPE_R3 | _REGION3_ENTRY_LARGE;
 	else
 		rste |= _SEGMENT_ENTRY_LARGE;
+	clear_huge_pte_skeys(mm, rste);
 	pte_val(*ptep) = rste;
 }
 
-- 
cgit v1.2.3


From 637ff9efe5eab419ea7f2bd6f2cf50f3cb69e322 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:28 +0100
Subject: s390/mm: Add huge pmd storage key handling

Storage keys for guests with huge page mappings have to be managed in
hardware. There are no PGSTEs for PMDs that we could use to retain the
guests's logical view of the key.

Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/mm/pgtable.c | 108 ++++++++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 98 insertions(+), 10 deletions(-)

diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 684df964e345..37d68706f5aa 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -410,6 +410,24 @@ static inline pmd_t pmdp_flush_lazy(struct mm_struct *mm,
 	return old;
 }
 
+static pmd_t *pmd_alloc_map(struct mm_struct *mm, unsigned long addr)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset(mm, addr);
+	p4d = p4d_alloc(mm, pgd, addr);
+	if (!p4d)
+		return NULL;
+	pud = pud_alloc(mm, p4d, addr);
+	if (!pud)
+		return NULL;
+	pmd = pmd_alloc(mm, pud, addr);
+	return pmd;
+}
+
 pmd_t pmdp_xchg_direct(struct mm_struct *mm, unsigned long addr,
 		       pmd_t *pmdp, pmd_t new)
 {
@@ -734,12 +752,36 @@ EXPORT_SYMBOL_GPL(ptep_test_and_clear_uc);
 int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char key, bool nq)
 {
-	unsigned long keyul;
+	unsigned long keyul, paddr;
 	spinlock_t *ptl;
 	pgste_t old, new;
+	pmd_t *pmdp;
 	pte_t *ptep;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		spin_unlock(ptl);
+		return -EFAULT;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		/*
+		 * Huge pmds need quiescing operations, they are
+		 * always mapped.
+		 */
+		page_set_storage_key(paddr, key, 1);
+		spin_unlock(ptl);
+		return 0;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
@@ -750,14 +792,14 @@ int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 	pgste_val(new) |= (keyul & (_PAGE_CHANGED | _PAGE_REFERENCED)) << 48;
 	pgste_val(new) |= (keyul & (_PAGE_ACC_BITS | _PAGE_FP_BIT)) << 56;
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-		unsigned long address, bits, skey;
+		unsigned long bits, skey;
 
-		address = pte_val(*ptep) & PAGE_MASK;
-		skey = (unsigned long) page_get_storage_key(address);
+		paddr = pte_val(*ptep) & PAGE_MASK;
+		skey = (unsigned long) page_get_storage_key(paddr);
 		bits = skey & (_PAGE_CHANGED | _PAGE_REFERENCED);
 		skey = key & (_PAGE_ACC_BITS | _PAGE_FP_BIT);
 		/* Set storage key ACC and FP */
-		page_set_storage_key(address, skey, !nq);
+		page_set_storage_key(paddr, skey, !nq);
 		/* Merge host changed & referenced into pgste  */
 		pgste_val(new) |= bits << 52;
 	}
@@ -813,11 +855,32 @@ EXPORT_SYMBOL(cond_set_guest_storage_key);
 int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 {
 	spinlock_t *ptl;
+	unsigned long paddr;
 	pgste_t old, new;
+	pmd_t *pmdp;
 	pte_t *ptep;
 	int cc = 0;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		spin_unlock(ptl);
+		return -EFAULT;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		cc = page_reset_referenced(paddr);
+		spin_unlock(ptl);
+		return cc;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
@@ -826,7 +889,8 @@ int reset_guest_reference_bit(struct mm_struct *mm, unsigned long addr)
 	pgste_val(new) &= ~PGSTE_GR_BIT;
 
 	if (!(pte_val(*ptep) & _PAGE_INVALID)) {
-		cc = page_reset_referenced(pte_val(*ptep) & PAGE_MASK);
+		paddr = pte_val(*ptep) & PAGE_MASK;
+		cc = page_reset_referenced(paddr);
 		/* Merge real referenced bit into host-set */
 		pgste_val(new) |= ((unsigned long) cc << 53) & PGSTE_HR_BIT;
 	}
@@ -845,18 +909,42 @@ EXPORT_SYMBOL(reset_guest_reference_bit);
 int get_guest_storage_key(struct mm_struct *mm, unsigned long addr,
 			  unsigned char *key)
 {
+	unsigned long paddr;
 	spinlock_t *ptl;
 	pgste_t pgste;
+	pmd_t *pmdp;
 	pte_t *ptep;
 
-	ptep = get_locked_pte(mm, addr, &ptl);
+	pmdp = pmd_alloc_map(mm, addr);
+	if (unlikely(!pmdp))
+		return -EFAULT;
+
+	ptl = pmd_lock(mm, pmdp);
+	if (!pmd_present(*pmdp)) {
+		/* Not yet mapped memory has a zero key */
+		spin_unlock(ptl);
+		*key = 0;
+		return 0;
+	}
+
+	if (pmd_large(*pmdp)) {
+		paddr = pmd_val(*pmdp) & HPAGE_MASK;
+		paddr |= addr & ~HPAGE_MASK;
+		*key = page_get_storage_key(paddr);
+		spin_unlock(ptl);
+		return 0;
+	}
+	spin_unlock(ptl);
+
+	ptep = pte_alloc_map_lock(mm, pmdp, addr, &ptl);
 	if (unlikely(!ptep))
 		return -EFAULT;
 
 	pgste = pgste_get_lock(ptep);
 	*key = (pgste_val(pgste) & (PGSTE_ACC_BITS | PGSTE_FP_BIT)) >> 56;
+	paddr = pte_val(*ptep) & PAGE_MASK;
 	if (!(pte_val(*ptep) & _PAGE_INVALID))
-		*key = page_get_storage_key(pte_val(*ptep) & PAGE_MASK);
+		*key = page_get_storage_key(paddr);
 	/* Reflect guest's logical view, not physical */
 	*key |= (pgste_val(pgste) & (PGSTE_GR_BIT | PGSTE_GC_BIT)) >> 48;
 	pgste_set_unlock(ptep, pgste);
-- 
cgit v1.2.3


From bd096f6443194e57382686a3ac5f2ce4e82b55d7 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Wed, 18 Jul 2018 13:40:22 +0100
Subject: KVM: s390: Add skey emulation fault handling

When doing skey emulation for huge guests, we now need to fault in
pmds, as we don't have PGSTES anymore to store them when we do not
have valid table entries.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/kvm/kvm-s390.c |  15 +++++--
 arch/s390/kvm/priv.c     | 105 ++++++++++++++++++++++++++++++++---------------
 2 files changed, 83 insertions(+), 37 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 4cff5e31ca36..662f4d8046db 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1551,6 +1551,7 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	uint8_t *keys;
 	uint64_t hva;
 	int srcu_idx, i, r = 0;
+	bool unlocked;
 
 	if (args->flags != 0)
 		return -EINVAL;
@@ -1575,9 +1576,11 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 	if (r)
 		goto out;
 
+	i = 0;
 	down_read(&current->mm->mmap_sem);
 	srcu_idx = srcu_read_lock(&kvm->srcu);
-	for (i = 0; i < args->count; i++) {
+        while (i < args->count) {
+		unlocked = false;
 		hva = gfn_to_hva(kvm, args->start_gfn + i);
 		if (kvm_is_error_hva(hva)) {
 			r = -EFAULT;
@@ -1591,8 +1594,14 @@ static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
 		}
 
 		r = set_guest_storage_key(current->mm, hva, keys[i], 0);
-		if (r)
-			break;
+		if (r) {
+			r = fixup_user_fault(current, current->mm, hva,
+					     FAULT_FLAG_WRITE, &unlocked);
+			if (r)
+				break;
+		}
+		if (!r)
+			i++;
 	}
 	srcu_read_unlock(&kvm->srcu, srcu_idx);
 	up_read(&current->mm->mmap_sem);
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index eb0eb60c7be6..cfc5a62329f6 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -246,9 +246,10 @@ static int try_handle_skey(struct kvm_vcpu *vcpu)
 
 static int handle_iske(struct kvm_vcpu *vcpu)
 {
-	unsigned long addr;
+	unsigned long gaddr, vmaddr;
 	unsigned char key;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_iske++;
@@ -262,18 +263,28 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
-	addr = kvm_s390_logical_to_effective(vcpu, addr);
-	addr = kvm_s390_real_to_abs(vcpu, addr);
-	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
-	if (kvm_is_error_hva(addr))
+	gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+	gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+	vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+	if (kvm_is_error_hva(vmaddr))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+	unlocked = false;
 	down_read(&current->mm->mmap_sem);
-	rc = get_guest_storage_key(current->mm, addr, &key);
-	up_read(&current->mm->mmap_sem);
+	rc = get_guest_storage_key(current->mm, vmaddr, &key);
+
+	if (rc) {
+		rc = fixup_user_fault(current, current->mm, vmaddr,
+				      FAULT_FLAG_WRITE, &unlocked);
+		if (!rc) {
+			up_read(&current->mm->mmap_sem);
+			goto retry;
+		}
+	}
 	if (rc)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+	up_read(&current->mm->mmap_sem);
 	vcpu->run->s.regs.gprs[reg1] &= ~0xff;
 	vcpu->run->s.regs.gprs[reg1] |= key;
 	return 0;
@@ -281,8 +292,9 @@ static int handle_iske(struct kvm_vcpu *vcpu)
 
 static int handle_rrbe(struct kvm_vcpu *vcpu)
 {
-	unsigned long addr;
+	unsigned long vmaddr, gaddr;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_rrbe++;
@@ -296,19 +308,27 @@ static int handle_rrbe(struct kvm_vcpu *vcpu)
 
 	kvm_s390_get_regs_rre(vcpu, &reg1, &reg2);
 
-	addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
-	addr = kvm_s390_logical_to_effective(vcpu, addr);
-	addr = kvm_s390_real_to_abs(vcpu, addr);
-	addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
-	if (kvm_is_error_hva(addr))
+	gaddr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
+	gaddr = kvm_s390_logical_to_effective(vcpu, gaddr);
+	gaddr = kvm_s390_real_to_abs(vcpu, gaddr);
+	vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(gaddr));
+	if (kvm_is_error_hva(vmaddr))
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+retry:
+	unlocked = false;
 	down_read(&current->mm->mmap_sem);
-	rc = reset_guest_reference_bit(current->mm, addr);
-	up_read(&current->mm->mmap_sem);
+	rc = reset_guest_reference_bit(current->mm, vmaddr);
+	if (rc < 0) {
+		rc = fixup_user_fault(current, current->mm, vmaddr,
+				      FAULT_FLAG_WRITE, &unlocked);
+		if (!rc) {
+			up_read(&current->mm->mmap_sem);
+			goto retry;
+		}
+	}
 	if (rc < 0)
 		return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-
+	up_read(&current->mm->mmap_sem);
 	kvm_s390_set_psw_cc(vcpu, rc);
 	return 0;
 }
@@ -323,6 +343,7 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	unsigned long start, end;
 	unsigned char key, oldkey;
 	int reg1, reg2;
+	bool unlocked;
 	int rc;
 
 	vcpu->stat.instruction_sske++;
@@ -355,19 +376,28 @@ static int handle_sske(struct kvm_vcpu *vcpu)
 	}
 
 	while (start != end) {
-		unsigned long addr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		unsigned long vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		unlocked = false;
 
-		if (kvm_is_error_hva(addr))
+		if (kvm_is_error_hva(vmaddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		down_read(&current->mm->mmap_sem);
-		rc = cond_set_guest_storage_key(current->mm, addr, key, &oldkey,
+		rc = cond_set_guest_storage_key(current->mm, vmaddr, key, &oldkey,
 						m3 & SSKE_NQ, m3 & SSKE_MR,
 						m3 & SSKE_MC);
-		up_read(&current->mm->mmap_sem);
-		if (rc < 0)
+
+		if (rc < 0) {
+			rc = fixup_user_fault(current, current->mm, vmaddr,
+					      FAULT_FLAG_WRITE, &unlocked);
+			rc = !rc ? -EAGAIN : rc;
+		}
+		if (rc == -EFAULT)
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		start += PAGE_SIZE;
+
+		up_read(&current->mm->mmap_sem);
+		if (rc >= 0)
+			start += PAGE_SIZE;
 	}
 
 	if (m3 & (SSKE_MC | SSKE_MR)) {
@@ -948,15 +978,16 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 	}
 
 	while (start != end) {
-		unsigned long useraddr;
+		unsigned long vmaddr;
+		bool unlocked = false;
 
 		/* Translate guest address to host address */
-		useraddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
-		if (kvm_is_error_hva(useraddr))
+		vmaddr = gfn_to_hva(vcpu->kvm, gpa_to_gfn(start));
+		if (kvm_is_error_hva(vmaddr))
 			return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 
 		if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
-			if (clear_user((void __user *)useraddr, PAGE_SIZE))
+			if (clear_user((void __user *)vmaddr, PAGE_SIZE))
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
 		}
 
@@ -966,14 +997,20 @@ static int handle_pfmf(struct kvm_vcpu *vcpu)
 			if (rc)
 				return rc;
 			down_read(&current->mm->mmap_sem);
-			rc = cond_set_guest_storage_key(current->mm, useraddr,
+			rc = cond_set_guest_storage_key(current->mm, vmaddr,
 							key, NULL, nq, mr, mc);
-			up_read(&current->mm->mmap_sem);
-			if (rc < 0)
+			if (rc < 0) {
+				rc = fixup_user_fault(current, current->mm, vmaddr,
+						      FAULT_FLAG_WRITE, &unlocked);
+				rc = !rc ? -EAGAIN : rc;
+			}
+			if (rc == -EFAULT)
 				return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
-		}
 
-		start += PAGE_SIZE;
+			up_read(&current->mm->mmap_sem);
+			if (rc >= 0)
+				start += PAGE_SIZE;
+		}
 	}
 	if (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
 		if (psw_bits(vcpu->arch.sie_block->gpsw).eaba == PSW_BITS_AMODE_64BIT) {
-- 
cgit v1.2.3


From 35f5a6acfb5be94e0b9df21c2a5ba934237c1ca3 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 18 Jul 2018 02:07:47 +0100
Subject: ARM: 8782/1: vfp: clean up arch/arm/vfp/Makefile

Since commit 799c43415442 ("kbuild: thin archives make default for
all archs"), $(AR) is used instead of $(LD) to combine object files.

The following code in arch/arm/vfp/Makefile:

  LDFLAGS         +=--no-warn-mismatch

... is no longer used.

Also, arch/arm/Makefile already guards arch/arm/vfp/ by a boolean
symbol, CONFIG_VFP, like this:

  core-$(CONFIG_VFP)              += arch/arm/vfp/

So, $(CONFIG_VFP) is always evaluated to y in arch/arm/vfp/Makefile.
There is no point to use pseudo object, vfp.o, which never becomes
a module.  Add all objects to obj-y directly.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/vfp/Makefile | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/arch/arm/vfp/Makefile b/arch/arm/vfp/Makefile
index a81404c09d5d..94516c40ebd3 100644
--- a/arch/arm/vfp/Makefile
+++ b/arch/arm/vfp/Makefile
@@ -8,8 +8,5 @@
 # asflags-y := -DDEBUG
 
 KBUILD_AFLAGS	:=$(KBUILD_AFLAGS:-msoft-float=-Wa,-mfpu=softvfp+vfp -mfloat-abi=soft)
-LDFLAGS		+=--no-warn-mismatch
 
-obj-y			+= vfp.o
-
-vfp-$(CONFIG_VFP)	+= vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
+obj-y		+= vfpmodule.o entry.o vfphw.o vfpsingle.o vfpdouble.o
-- 
cgit v1.2.3


From c803ce3f18bd93b3b4a15d1da0c5b5ebc60e0b85 Mon Sep 17 00:00:00 2001
From: Vladimir Murzin <vladimir.murzin@arm.com>
Date: Mon, 23 Jul 2018 09:36:18 +0100
Subject: ARM: 8783/1: NOMMU: Extend check for VBAR support

ARMv8R adds support for VBAR and updates ID_PFR1 with the new filed
Sec_frac (bits [23:20]):

Security fractional field. When the Security field is 0000, determines
the support for features from the ARMv7 Security Extensions. Permitted
values are:

0000 No features from the ARMv7 Security Extensions are implemented.
     This value is not supported in ARMv8 if ID_PFR1 bits [7:4] are zero.

0001 The implementation includes the VBAR, and the TCR.PD0 and TCR.PD1
     bits.

0010 As for 0001, plus the ability to access Secure or Non-secure
     physical memory is supported.

All other values are reserved.

This field is only valid when ID_PFR1[7:4] == 0, otherwise it holds
the value 0000.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/mm/nommu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/arm/mm/nommu.c b/arch/arm/mm/nommu.c
index 5dd6c58d653b..7d67c70bbded 100644
--- a/arch/arm/mm/nommu.c
+++ b/arch/arm/mm/nommu.c
@@ -53,7 +53,8 @@ static inline bool security_extensions_enabled(void)
 {
 	/* Check CPUID Identification Scheme before ID_PFR1 read */
 	if ((read_cpuid_id() & 0x000f0000) == 0x000f0000)
-		return !!cpuid_feature_extract(CPUID_EXT_PFR1, 4);
+		return cpuid_feature_extract(CPUID_EXT_PFR1, 4) ||
+			cpuid_feature_extract(CPUID_EXT_PFR1, 20);
 	return 0;
 }
 
-- 
cgit v1.2.3


From cbfc5619e0cc8dcdf3020e27426eec362307cc14 Mon Sep 17 00:00:00 2001
From: Vladimir Murzin <vladimir.murzin@arm.com>
Date: Mon, 23 Jul 2018 09:37:09 +0100
Subject: ARM: 8784/1: NOMMU: Allow enter in Hyp mode

ARMv8R adds support for virtualisation extension (with some deviation
from v8A). With this patch hyp-unaware boot code can offload to kernel
setting up HYP stuff in a sane state.

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/kernel/head-nommu.S | 12 ++++++++++--
 arch/arm/mm/Kconfig          |  1 -
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index dd546d65a383..724734039492 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -53,7 +53,11 @@ ENTRY(stext)
  THUMB(1:			)
 #endif
 
-	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install
+#endif
+	@ ensure svc mode and all interrupts masked
+	safe_svcmode_maskall r9
 						@ and irqs disabled
 #if defined(CONFIG_CPU_CP15)
 	mrc	p15, 0, r9, c0, c0		@ get processor id
@@ -89,7 +93,11 @@ ENTRY(secondary_startup)
 	 * the processor type - there is no need to check the machine type
 	 * as it has already been validated by the primary processor.
 	 */
-	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install_secondary
+#endif
+	safe_svcmode_maskall r9
+
 #ifndef CONFIG_CPU_CP15
 	ldr	r9, =CONFIG_PROCESSOR_ID
 #else
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 96a7b6cf459b..b169e580bf82 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -702,7 +702,6 @@ config ARM_THUMBEE
 
 config ARM_VIRT_EXT
 	bool
-	depends on MMU
 	default y if CPU_V7
 	help
 	  Enable the kernel to make use of the ARM Virtualization
-- 
cgit v1.2.3


From 001a30c4d0e871b21d296e1bcafc6756a1b10607 Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Wed, 25 Jul 2018 04:38:54 +0100
Subject: ARM: 8785/1: use compiler built-ins for ffs and fls

On ARMv5 and above, it is beneficial to use compiler built-ins such as
__builtin_ffs() and __builtin_ctzl() to implement ffs(), __ffs(), fls()
and __fls(). The compiler does inline the clz instruction and even the
rbit instruction when available, or provide a constant value when
possible. On ARMv4 the compiler calls out to helper functions for those
built-ins so it is best to keep the open coded versions in that case.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/include/asm/bitops.h | 92 +++++--------------------------------------
 1 file changed, 9 insertions(+), 83 deletions(-)

diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 4cab9bb823fb..c92e42a5c8f7 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -215,7 +215,6 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 
 #if __LINUX_ARM_ARCH__ < 5
 
-#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/fls.h>
@@ -223,93 +222,20 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 
 #else
 
-static inline int constant_fls(int x)
-{
-	int r = 32;
-
-	if (!x)
-		return 0;
-	if (!(x & 0xffff0000u)) {
-		x <<= 16;
-		r -= 16;
-	}
-	if (!(x & 0xff000000u)) {
-		x <<= 8;
-		r -= 8;
-	}
-	if (!(x & 0xf0000000u)) {
-		x <<= 4;
-		r -= 4;
-	}
-	if (!(x & 0xc0000000u)) {
-		x <<= 2;
-		r -= 2;
-	}
-	if (!(x & 0x80000000u)) {
-		x <<= 1;
-		r -= 1;
-	}
-	return r;
-}
-
-/*
- * On ARMv5 and above those functions can be implemented around the
- * clz instruction for much better code efficiency.  __clz returns
- * the number of leading zeros, zero input will return 32, and
- * 0x80000000 will return 0.
- */
-static inline unsigned int __clz(unsigned int x)
-{
-	unsigned int ret;
-
-	asm("clz\t%0, %1" : "=r" (ret) : "r" (x));
-
-	return ret;
-}
-
-/*
- * fls() returns zero if the input is zero, otherwise returns the bit
- * position of the last set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int fls(int x)
-{
-	if (__builtin_constant_p(x))
-	       return constant_fls(x);
-
-	return 32 - __clz(x);
-}
-
-/*
- * __fls() returns the bit position of the last bit set, where the
- * LSB is 0 and MSB is 31.  Zero input is undefined.
- */
-static inline unsigned long __fls(unsigned long x)
-{
-	return fls(x) - 1;
-}
-
-/*
- * ffs() returns zero if the input was zero, otherwise returns the bit
- * position of the first set bit, where the LSB is 1 and MSB is 32.
- */
-static inline int ffs(int x)
-{
-	return fls(x & -x);
-}
-
 /*
- * __ffs() returns the bit position of the first bit set, where the
- * LSB is 0 and MSB is 31.  Zero input is undefined.
+ * On ARMv5 and above, the gcc built-ins may rely on the clz instruction
+ * and produce optimal inlined code in all cases. On ARMv7 it is even
+ * better by also using the rbit instruction.
  */
-static inline unsigned long __ffs(unsigned long x)
-{
-	return ffs(x) - 1;
-}
-
-#define ffz(x) __ffs( ~(x) )
+#include <asm-generic/bitops/builtin-__fls.h>
+#include <asm-generic/bitops/builtin-__ffs.h>
+#include <asm-generic/bitops/builtin-fls.h>
+#include <asm-generic/bitops/builtin-ffs.h>
 
 #endif
 
+#include <asm-generic/bitops/ffz.h>
+
 #include <asm-generic/bitops/fls64.h>
 
 #include <asm-generic/bitops/sched.h>
-- 
cgit v1.2.3


From 830aadceae20c08704562f0b83fdd0f0062d06c6 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tdz@users.sourceforge.net>
Date: Mon, 30 Jul 2018 11:52:31 +0100
Subject: drm/armada: Replace drm_dev_unref with drm_dev_put

This patch unifies the naming of DRM functions for reference counting
of struct drm_device. The resulting code is more aligned with the rest
of the Linux kernel interfaces.

Signed-off-by: Thomas Zimmermann <tdz@users.sourceforge.net>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_drv.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 4b11b6b52f1d..d1705d298a39 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -109,7 +109,7 @@ static int armada_drm_bind(struct device *dev)
 
 	/*
 	 * The drm_device structure must be at the start of
-	 * armada_private for drm_dev_unref() to work correctly.
+	 * armada_private for drm_dev_put() to work correctly.
 	 */
 	BUILD_BUG_ON(offsetof(struct armada_private, drm) != 0);
 
@@ -180,7 +180,7 @@ static int armada_drm_bind(struct device *dev)
 	drm_mode_config_cleanup(&priv->drm);
 	drm_mm_takedown(&priv->linear);
 	flush_work(&priv->fb_unref_work);
-	drm_dev_unref(&priv->drm);
+	drm_dev_put(&priv->drm);
 	return ret;
 }
 
@@ -200,7 +200,7 @@ static void armada_drm_unbind(struct device *dev)
 	drm_mm_takedown(&priv->linear);
 	flush_work(&priv->fb_unref_work);
 
-	drm_dev_unref(&priv->drm);
+	drm_dev_put(&priv->drm);
 }
 
 static int compare_of(struct device *dev, void *data)
-- 
cgit v1.2.3


From 7794ec7774066eb12af67a0a756bddd66f2d50f8 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Mon, 30 Jul 2018 11:52:31 +0100
Subject: drm/armada: Adding new typedef vm_fault_t

Use new return type vm_fault_t for fault handler in struct
vm_operations_struct. For now, this is just documenting that the
function returns a VM_FAULT value rather than an errno. Once all
instances are converted, vm_fault_t will become a distinct type.

commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Previously vm_insert_pfn() returns err which driver mapped into
VM_FAULT_* type. The new function vmf_insert_pfn() will replace this
inefficiency by returning VM_FAULT_* type.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_gem.c | 15 ++-------------
 1 file changed, 2 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_gem.c b/drivers/gpu/drm/armada/armada_gem.c
index 3fb37c75c065..892c1d9304bb 100644
--- a/drivers/gpu/drm/armada/armada_gem.c
+++ b/drivers/gpu/drm/armada/armada_gem.c
@@ -13,25 +13,14 @@
 #include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
 
-static int armada_gem_vm_fault(struct vm_fault *vmf)
+static vm_fault_t armada_gem_vm_fault(struct vm_fault *vmf)
 {
 	struct drm_gem_object *gobj = vmf->vma->vm_private_data;
 	struct armada_gem_object *obj = drm_to_armada_gem(gobj);
 	unsigned long pfn = obj->phys_addr >> PAGE_SHIFT;
-	int ret;
 
 	pfn += (vmf->address - vmf->vma->vm_start) >> PAGE_SHIFT;
-	ret = vm_insert_pfn(vmf->vma, vmf->address, pfn);
-
-	switch (ret) {
-	case 0:
-	case -EBUSY:
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_pfn(vmf->vma, vmf->address, pfn);
 }
 
 const struct vm_operations_struct armada_gem_vm_ops = {
-- 
cgit v1.2.3


From 1729f56010a960f182a36e09ce8d6504fa637d76 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: clean up armada_drm_crtc_page_flip()

drm_mode_page_flip_ioctl() already takes care of checking the
framebuffer format, and also assigns primary->fb after a successful
call to this handler.  These are both redundant, and can be removed.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 42a40daff132..78bb3d51417b 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -1039,10 +1039,6 @@ static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
 	unsigned i;
 	int ret;
 
-	/* We don't support changing the pixel format */
-	if (fb->format != crtc->primary->fb->format)
-		return -EINVAL;
-
 	work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary);
 	if (!work)
 		return -ENOMEM;
@@ -1068,14 +1064,6 @@ static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
 		return ret;
 	}
 
-	/*
-	 * Don't take a reference on the new framebuffer;
-	 * drm_mode_page_flip_ioctl() has already grabbed a reference and
-	 * will _not_ drop that reference on successful return from this
-	 * function.  Simply mark this new framebuffer as the current one.
-	 */
-	dcrtc->crtc.primary->fb = fb;
-
 	/*
 	 * Finally, if the display is blanked, we won't receive an
 	 * interrupt, so complete it now.
-- 
cgit v1.2.3


From 0239520e0290e7d5f186f7fb7f7ce307c478a439 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: add rectangle helpers

Add helpers to convert rectangle width/height and x/y to register
values.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c    |  8 +++-----
 drivers/gpu/drm/armada/armada_hw.h      | 15 +++++++++++++++
 drivers/gpu/drm/armada/armada_overlay.c |  7 +++----
 3 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 78bb3d51417b..205d5dc7ba81 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -1158,11 +1158,9 @@ static void armada_drm_primary_update_state(struct drm_plane_state *state,
 				     0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
 
 	dplane->state.ctrl0 = val;
-	dplane->state.src_hw = (drm_rect_height(&state->src) & 0xffff0000) |
-				drm_rect_width(&state->src) >> 16;
-	dplane->state.dst_hw = drm_rect_height(&state->dst) << 16 |
-			       drm_rect_width(&state->dst);
-	dplane->state.dst_yx = state->dst.y1 << 16 | state->dst.x1;
+	dplane->state.src_hw = armada_rect_hw_fp(&state->src);
+	dplane->state.dst_hw = armada_rect_hw(&state->dst);
+	dplane->state.dst_yx = armada_rect_yx(&state->dst);
 
 	armada_drm_gra_plane_regs(regs + idx, &dfb->fb, &dplane->state,
 				  state->src.x1 >> 16, state->src.y1 >> 16,
diff --git a/drivers/gpu/drm/armada/armada_hw.h b/drivers/gpu/drm/armada/armada_hw.h
index 345dc4d0851e..277580b36758 100644
--- a/drivers/gpu/drm/armada/armada_hw.h
+++ b/drivers/gpu/drm/armada/armada_hw.h
@@ -316,4 +316,19 @@ enum {
 	PWRDN_IRQ_LEVEL		= 1 << 0,
 };
 
+static inline u32 armada_rect_hw_fp(struct drm_rect *r)
+{
+	return (drm_rect_height(r) & 0xffff0000) | drm_rect_width(r) >> 16;
+}
+
+static inline u32 armada_rect_hw(struct drm_rect *r)
+{
+	return drm_rect_height(r) << 16 | (drm_rect_width(r) & 0x0000ffff);
+}
+
+static inline u32 armada_rect_yx(struct drm_rect *r)
+{
+	return (r)->y1 << 16 | ((r)->x1 & 0x0000ffff);
+}
+
 #endif
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index afa7ded3ae31..2347811ccf1b 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -146,22 +146,21 @@ static void armada_ovl_plane_update_state(struct drm_plane_state *state,
 				     LCD_SPU_DMA_PITCH_UV);
 	}
 
-	val = (drm_rect_height(&state->src) & 0xffff0000) |
-	       drm_rect_width(&state->src) >> 16;
+	val = armada_rect_hw_fp(&state->src);
 	if (dplane->base.state.src_hw != val) {
 		dplane->base.state.src_hw = val;
 		armada_reg_queue_set(regs, idx, val,
 				     LCD_SPU_DMA_HPXL_VLN);
 	}
 
-	val = drm_rect_height(&state->dst) << 16 | drm_rect_width(&state->dst);
+	val = armada_rect_hw(&state->dst);
 	if (dplane->base.state.dst_hw != val) {
 		dplane->base.state.dst_hw = val;
 		armada_reg_queue_set(regs, idx, val,
 				     LCD_SPU_DZM_HPXL_VLN);
 	}
 
-	val = state->dst.y1 << 16 | state->dst.x1;
+	val = armada_rect_yx(&state->dst);
 	if (dplane->base.state.dst_yx != val) {
 		dplane->base.state.dst_yx = val;
 		armada_reg_queue_set(regs, idx, val,
-- 
cgit v1.2.3


From f9a13bb3baf6009225e91f2b9748ed27f2db9c2c Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: move mode set vblank handling and disable/enable

Move the mode set vblank handling and controller enable/disable to the
prepare() and commit() callbacks.  This will be needed when we move to
mode_set_nofb() as we should not enable the controller without the
plane coordinates and location having been properly updated.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 41 ++++++++++++++++++------------------
 drivers/gpu/drm/armada/armada_crtc.h |  1 +
 2 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 205d5dc7ba81..683b2cec3d55 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -399,6 +399,7 @@ static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 	struct drm_plane *plane;
+	u32 val;
 
 	/*
 	 * If we have an overlay plane associated with this CRTC, disable
@@ -411,6 +412,18 @@ static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
 		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
 						    HZ));
 	}
+
+	/* Wait for pending flips to complete */
+	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
+				   MAX_SCHEDULE_TIMEOUT);
+
+	drm_crtc_vblank_off(crtc);
+
+	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
+	if (val != dcrtc->dumb_ctrl) {
+		dcrtc->dumb_ctrl = val;
+		writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL);
+	}
 }
 
 /* The mode_config.mutex will be held for this call */
@@ -418,10 +431,12 @@ static void armada_drm_crtc_commit(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 
-	if (dcrtc->dpms != DRM_MODE_DPMS_ON) {
-		dcrtc->dpms = DRM_MODE_DPMS_ON;
-		armada_drm_crtc_update(dcrtc);
-	}
+	dcrtc->dpms = DRM_MODE_DPMS_ON;
+	armada_drm_crtc_update(dcrtc);
+	drm_crtc_vblank_on(crtc);
+
+	if (dcrtc->old_modeset_fb)
+		armada_drm_crtc_finish_fb(dcrtc, dcrtc->old_modeset_fb, false);
 }
 
 /* The mode_config.mutex will be held for this call */
@@ -623,6 +638,7 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	bool interlaced;
 
 	drm_framebuffer_get(crtc->primary->fb);
+	dcrtc->old_modeset_fb = old_fb;
 
 	interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
 
@@ -656,18 +672,6 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 		adj->crtc_vsync_end,
 		adj->crtc_vtotal, tm, bm);
 
-	/* Wait for pending flips to complete */
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
-
-	drm_crtc_vblank_off(crtc);
-
-	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
-	if (val != dcrtc->dumb_ctrl) {
-		dcrtc->dumb_ctrl = val;
-		writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL);
-	}
-
 	/*
 	 * If we are blanked, we would have disabled the clock.  Re-enable
 	 * it so that compute_clock() does the right thing.
@@ -739,11 +743,6 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	armada_drm_primary_set(crtc, crtc->primary, x, y);
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 
-	armada_drm_crtc_update(dcrtc);
-
-	drm_crtc_vblank_on(crtc);
-	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
-
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 445829b8877a..8edcfd1fa75f 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -93,6 +93,7 @@ struct armada_crtc {
 	uint8_t			csc_rgb_mode;
 
 	struct drm_plane	*plane;
+	struct drm_framebuffer	*old_modeset_fb;
 
 	struct armada_gem_object	*cursor_obj;
 	int			cursor_x;
-- 
cgit v1.2.3


From cfd1b63af78bfce8161e5f65a1d799a9c33b52c6 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: use core of primary update_plane for mode set

Use the core of the update_plane method to configure the primary plane
within mode_set() rather than duplicating this code.  This moves us
closer to the same code structure that the atomic modeset transitional
helpers will use.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 137 +++++++++++++++--------------------
 1 file changed, 59 insertions(+), 78 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 683b2cec3d55..6dd54f1d3ac9 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -613,17 +613,8 @@ static void armada_drm_gra_plane_regs(struct armada_regs *regs,
 	armada_reg_queue_end(regs, i);
 }
 
-static void armada_drm_primary_set(struct drm_crtc *crtc,
-	struct drm_plane *plane, int x, int y)
-{
-	struct armada_plane_state *state = &drm_to_armada_plane(plane)->state;
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_regs regs[8];
-	bool interlaced = dcrtc->interlaced;
-
-	armada_drm_gra_plane_regs(regs, plane->fb, state, x, y, interlaced);
-	armada_drm_crtc_update_regs(dcrtc, regs);
-}
+static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
+	struct drm_framebuffer *old_fb);
 
 /* The mode_config.mutex will be held for this call */
 static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
@@ -637,24 +628,13 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	unsigned i;
 	bool interlaced;
 
-	drm_framebuffer_get(crtc->primary->fb);
+	/* Take a reference on the old fb for armada_drm_crtc_commit() */
+	if (old_fb)
+		drm_framebuffer_get(old_fb);
 	dcrtc->old_modeset_fb = old_fb;
 
 	interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
 
-	val = CFG_GRA_ENA;
-	val |= CFG_GRA_FMT(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt);
-	val |= CFG_GRA_MOD(drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->mod);
-
-	if (drm_fb_to_armada_fb(dcrtc->crtc.primary->fb)->fmt > CFG_420)
-		val |= CFG_PALETTE_ENA;
-
-	drm_to_armada_plane(crtc->primary)->state.ctrl0 = val;
-	drm_to_armada_plane(crtc->primary)->state.src_hw =
-	drm_to_armada_plane(crtc->primary)->state.dst_hw =
-		adj->crtc_vdisplay << 16 | adj->crtc_hdisplay;
-	drm_to_armada_plane(crtc->primary)->state.dst_yx = 0;
-
 	i = 0;
 	rm = adj->crtc_hsync_start - adj->crtc_hdisplay;
 	lm = adj->crtc_htotal - adj->crtc_hsync_end;
@@ -694,9 +674,6 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 
 	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 
-	/* Ensure graphic fifo is enabled */
-	armada_reg_queue_mod(regs, i, 0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
-
 	/* Even interlaced/progressive frame */
 	dcrtc->v[1].spu_v_h_total = adj->crtc_vtotal << 16 |
 				    adj->crtc_htotal;
@@ -739,37 +716,34 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 	armada_reg_queue_end(regs, i);
 
 	armada_drm_crtc_update_regs(dcrtc, regs);
-
-	armada_drm_primary_set(crtc, crtc->primary, x, y);
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 
-	return 0;
+	return armada_drm_crtc_mode_set_base(crtc, x, y, old_fb);
 }
 
+static int armada_drm_do_primary_update(struct drm_plane *plane,
+	struct drm_plane_state *state, struct drm_framebuffer *old_fb);
+
 /* The mode_config.mutex will be held for this call */
 static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_framebuffer *old_fb)
 {
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_regs regs[4];
-	unsigned i;
-
-	i = armada_drm_crtc_calc_fb(crtc->primary->fb, crtc->x, crtc->y, regs,
-				    dcrtc->interlaced);
-	armada_reg_queue_end(regs, i);
-
-	/* Wait for pending flips to complete */
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
-
-	/* Take a reference to the new fb as we're using it */
-	drm_framebuffer_get(crtc->primary->fb);
-
-	/* Update the base in the CRTC */
-	armada_drm_crtc_update_regs(dcrtc, regs);
+	struct drm_plane_state state = {
+		.plane = crtc->primary,
+		.crtc = crtc,
+		.fb = crtc->primary->fb,
+		.crtc_x = 0,
+		.crtc_y = 0,
+		.crtc_w = crtc->mode.hdisplay,
+		.crtc_h = crtc->mode.vdisplay,
+		.src_x = x << 16,
+		.src_y = y << 16,
+		.src_w = crtc->mode.hdisplay << 16,
+		.src_h = crtc->mode.vdisplay << 16,
+		.rotation = DRM_MODE_ROTATE_0,
+	};
 
-	/* Drop our previously held reference */
-	armada_drm_crtc_finish_fb(dcrtc, old_fb, dpms_blanked(dcrtc->dpms));
+	armada_drm_do_primary_update(crtc->primary, &state, old_fb);
 
 	return 0;
 }
@@ -1169,37 +1143,20 @@ static void armada_drm_primary_update_state(struct drm_plane_state *state,
 	dplane->state.changed = true;
 }
 
-static int armada_drm_primary_update(struct drm_plane *plane,
-	struct drm_crtc *crtc, struct drm_framebuffer *fb,
-	int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h,
-	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
-	struct drm_modeset_acquire_ctx *ctx)
+static int armada_drm_do_primary_update(struct drm_plane *plane,
+	struct drm_plane_state *state, struct drm_framebuffer *old_fb)
 {
 	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
 	struct armada_plane_work *work;
-	struct drm_plane_state state = {
-		.plane = plane,
-		.crtc = crtc,
-		.fb = fb,
-		.src_x = src_x,
-		.src_y = src_y,
-		.src_w = src_w,
-		.src_h = src_h,
-		.crtc_x = crtc_x,
-		.crtc_y = crtc_y,
-		.crtc_w = crtc_w,
-		.crtc_h = crtc_h,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
 	struct drm_crtc_state crtc_state = {
-		.crtc = crtc,
-		.enable = crtc->enabled,
-		.mode = crtc->mode,
+		.crtc = state->crtc,
+		.enable = state->crtc->enabled,
+		.mode = state->crtc->mode,
 	};
 	int ret;
 
-	ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0,
+	ret = drm_atomic_helper_check_plane_state(state, &crtc_state, 0,
 						  INT_MAX, true, false);
 	if (ret)
 		return ret;
@@ -1207,19 +1164,19 @@ static int armada_drm_primary_update(struct drm_plane *plane,
 	work = &dplane->works[dplane->next_work];
 	work->fn = armada_drm_crtc_complete_frame_work;
 
-	if (plane->fb != fb) {
+	if (old_fb != state->fb) {
 		/*
 		 * Take a reference on the new framebuffer - we want to
 		 * hold on to it while the hardware is displaying it.
 		 */
-		drm_framebuffer_reference(fb);
+		drm_framebuffer_reference(state->fb);
 
-		work->old_fb = plane->fb;
+		work->old_fb = old_fb;
 	} else {
 		work->old_fb = NULL;
 	}
 
-	armada_drm_primary_update_state(&state, work->regs);
+	armada_drm_primary_update_state(state, work->regs);
 
 	if (!dplane->state.changed)
 		return 0;
@@ -1248,6 +1205,30 @@ static int armada_drm_primary_update(struct drm_plane *plane,
 	return 0;
 }
 
+static int armada_drm_primary_update(struct drm_plane *plane,
+	struct drm_crtc *crtc, struct drm_framebuffer *fb,
+	int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h,
+	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
+	struct drm_modeset_acquire_ctx *ctx)
+{
+	struct drm_plane_state state = {
+		.plane = plane,
+		.crtc = crtc,
+		.fb = fb,
+		.src_x = src_x,
+		.src_y = src_y,
+		.src_w = src_w,
+		.src_h = src_h,
+		.crtc_x = crtc_x,
+		.crtc_y = crtc_y,
+		.crtc_w = crtc_w,
+		.crtc_h = crtc_h,
+		.rotation = DRM_MODE_ROTATE_0,
+	};
+
+	return armada_drm_do_primary_update(plane, &state, plane->fb);
+}
+
 int armada_drm_plane_disable(struct drm_plane *plane,
 			     struct drm_modeset_acquire_ctx *ctx)
 {
-- 
cgit v1.2.3


From ecf25d2380313139a2cc5f07e7ac2d910054b478 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: merge armada_drm_gra_plane_regs() into only caller

armada_drm_gra_plane_regs() is now only ever called from within
armada_drm_primary_update_state(), so merge it into this function.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 55 ++++++++++++++++--------------------
 1 file changed, 24 insertions(+), 31 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 6dd54f1d3ac9..735abdab9754 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -588,31 +588,6 @@ static uint32_t armada_drm_crtc_calculate_csc(struct armada_crtc *dcrtc)
 	return val;
 }
 
-static void armada_drm_gra_plane_regs(struct armada_regs *regs,
-	struct drm_framebuffer *fb, struct armada_plane_state *state,
-	int x, int y, bool interlaced)
-{
-	unsigned int i;
-	u32 ctrl0;
-
-	i = armada_drm_crtc_calc_fb(fb, x, y, regs, interlaced);
-	armada_reg_queue_set(regs, i, state->dst_yx, LCD_SPU_GRA_OVSA_HPXL_VLN);
-	armada_reg_queue_set(regs, i, state->src_hw, LCD_SPU_GRA_HPXL_VLN);
-	armada_reg_queue_set(regs, i, state->dst_hw, LCD_SPU_GZM_HPXL_VLN);
-
-	ctrl0 = state->ctrl0;
-	if (interlaced)
-		ctrl0 |= CFG_GRA_FTOGGLE;
-
-	armada_reg_queue_mod(regs, i, ctrl0, CFG_GRAFORMAT |
-			     CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
-					 CFG_SWAPYU | CFG_YUV2RGB) |
-			     CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
-			     CFG_GRA_HSMOOTH | CFG_GRA_ENA,
-			     LCD_SPU_DMA_CTRL0);
-	armada_reg_queue_end(regs, i);
-}
-
 static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
 	struct drm_framebuffer *old_fb);
 
@@ -1107,8 +1082,8 @@ static const struct drm_crtc_funcs armada_crtc_funcs = {
 	.disable_vblank	= armada_drm_crtc_disable_vblank,
 };
 
-static void armada_drm_primary_update_state(struct drm_plane_state *state,
-	struct armada_regs *regs)
+static unsigned int armada_drm_primary_update_state(
+	struct drm_plane_state *state, struct armada_regs *regs)
 {
 	struct armada_plane *dplane = drm_to_armada_plane(state->plane);
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
@@ -1124,6 +1099,8 @@ static void armada_drm_primary_update_state(struct drm_plane_state *state,
 		val |= CFG_GRA_ENA;
 	if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst))
 		val |= CFG_GRA_HSMOOTH;
+	if (dcrtc->interlaced)
+		val |= CFG_GRA_FTOGGLE;
 
 	was_disabled = !(dplane->state.ctrl0 & CFG_GRA_ENA);
 	if (was_disabled)
@@ -1135,12 +1112,26 @@ static void armada_drm_primary_update_state(struct drm_plane_state *state,
 	dplane->state.dst_hw = armada_rect_hw(&state->dst);
 	dplane->state.dst_yx = armada_rect_yx(&state->dst);
 
-	armada_drm_gra_plane_regs(regs + idx, &dfb->fb, &dplane->state,
-				  state->src.x1 >> 16, state->src.y1 >> 16,
-				  dcrtc->interlaced);
+	idx += armada_drm_crtc_calc_fb(&dfb->fb, state->src.x1 >> 16,
+				       state->src.y1 >> 16, regs + idx,
+				       dcrtc->interlaced);
+	armada_reg_queue_set(regs, idx, dplane->state.dst_yx,
+			     LCD_SPU_GRA_OVSA_HPXL_VLN);
+	armada_reg_queue_set(regs, idx, dplane->state.src_hw,
+			     LCD_SPU_GRA_HPXL_VLN);
+	armada_reg_queue_set(regs, idx, dplane->state.dst_hw,
+			     LCD_SPU_GZM_HPXL_VLN);
+	armada_reg_queue_mod(regs, idx, dplane->state.ctrl0, CFG_GRAFORMAT |
+			     CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+					 CFG_SWAPYU | CFG_YUV2RGB) |
+			     CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
+			     CFG_GRA_HSMOOTH | CFG_GRA_ENA,
+			     LCD_SPU_DMA_CTRL0);
 
 	dplane->state.vsync_update = !was_disabled;
 	dplane->state.changed = true;
+
+	return idx;
 }
 
 static int armada_drm_do_primary_update(struct drm_plane *plane,
@@ -1154,6 +1145,7 @@ static int armada_drm_do_primary_update(struct drm_plane *plane,
 		.enable = state->crtc->enabled,
 		.mode = state->crtc->mode,
 	};
+	unsigned int idx;
 	int ret;
 
 	ret = drm_atomic_helper_check_plane_state(state, &crtc_state, 0,
@@ -1176,7 +1168,8 @@ static int armada_drm_do_primary_update(struct drm_plane *plane,
 		work->old_fb = NULL;
 	}
 
-	armada_drm_primary_update_state(state, work->regs);
+	idx = armada_drm_primary_update_state(state, work->regs);
+	armada_reg_queue_end(work->regs, idx);
 
 	if (!dplane->state.changed)
 		return 0;
-- 
cgit v1.2.3


From 80c63aee8143d83743a9df6d09309d3d15b20680 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: reset all atomic state during driver initialisation

Reset the atomic state of any converted components during driver
initialisation to ensure that we have the atomic state initialised for
any component converted to atomic modeset.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_drv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index d1705d298a39..e47b995b4ce6 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -155,6 +155,8 @@ static int armada_drm_bind(struct device *dev)
 
 	priv->drm.irq_enabled = true;
 
+	drm_mode_config_reset(&priv->drm);
+
 	ret = armada_fbdev_init(&priv->drm);
 	if (ret)
 		goto err_comp;
-- 
cgit v1.2.3


From c36045e17a0e9206078a3254385bf9258e32d5b8 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: convert primary plane to atomic state

Convert the primary plane as a whole to use its atomic state and the
transitional helpers.  The CRTC is also switched to use the transitional
helpers for mode_set() and mode_set_base().

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 308 +++++++++++++++++------------------
 drivers/gpu/drm/armada/armada_crtc.h |   8 +-
 2 files changed, 157 insertions(+), 159 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 735abdab9754..523e0e8c6962 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -325,38 +325,6 @@ armada_drm_crtc_alloc_plane_work(struct drm_plane *plane)
 	return work;
 }
 
-static void armada_drm_crtc_finish_fb(struct armada_crtc *dcrtc,
-	struct drm_framebuffer *fb, bool force)
-{
-	struct armada_plane_work *work;
-
-	if (!fb)
-		return;
-
-	if (force) {
-		/* Display is disabled, so just drop the old fb */
-		drm_framebuffer_put(fb);
-		return;
-	}
-
-	work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary);
-	if (work) {
-		work->old_fb = fb;
-
-		if (armada_drm_plane_work_queue(dcrtc, work) == 0)
-			return;
-
-		kfree(work);
-	}
-
-	/*
-	 * Oops - just drop the reference immediately and hope for
-	 * the best.  The worst that will happen is the buffer gets
-	 * reused before it has finished being displayed.
-	 */
-	drm_framebuffer_put(fb);
-}
-
 static void armada_drm_vblank_off(struct armada_crtc *dcrtc)
 {
 	/*
@@ -434,9 +402,6 @@ static void armada_drm_crtc_commit(struct drm_crtc *crtc)
 	dcrtc->dpms = DRM_MODE_DPMS_ON;
 	armada_drm_crtc_update(dcrtc);
 	drm_crtc_vblank_on(crtc);
-
-	if (dcrtc->old_modeset_fb)
-		armada_drm_crtc_finish_fb(dcrtc, dcrtc->old_modeset_fb, false);
 }
 
 /* The mode_config.mutex will be held for this call */
@@ -588,27 +553,16 @@ static uint32_t armada_drm_crtc_calculate_csc(struct armada_crtc *dcrtc)
 	return val;
 }
 
-static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
-	struct drm_framebuffer *old_fb);
-
 /* The mode_config.mutex will be held for this call */
-static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
-	struct drm_display_mode *mode, struct drm_display_mode *adj,
-	int x, int y, struct drm_framebuffer *old_fb)
+static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
+	struct drm_display_mode *adj = &crtc->state->adjusted_mode;
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 	struct armada_regs regs[17];
 	uint32_t lm, rm, tm, bm, val, sclk;
 	unsigned long flags;
 	unsigned i;
-	bool interlaced;
-
-	/* Take a reference on the old fb for armada_drm_crtc_commit() */
-	if (old_fb)
-		drm_framebuffer_get(old_fb);
-	dcrtc->old_modeset_fb = old_fb;
-
-	interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
+	bool interlaced = !!(adj->flags & DRM_MODE_FLAG_INTERLACE);
 
 	i = 0;
 	rm = adj->crtc_hsync_start - adj->crtc_hdisplay;
@@ -692,35 +646,6 @@ static int armada_drm_crtc_mode_set(struct drm_crtc *crtc,
 
 	armada_drm_crtc_update_regs(dcrtc, regs);
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-
-	return armada_drm_crtc_mode_set_base(crtc, x, y, old_fb);
-}
-
-static int armada_drm_do_primary_update(struct drm_plane *plane,
-	struct drm_plane_state *state, struct drm_framebuffer *old_fb);
-
-/* The mode_config.mutex will be held for this call */
-static int armada_drm_crtc_mode_set_base(struct drm_crtc *crtc, int x, int y,
-	struct drm_framebuffer *old_fb)
-{
-	struct drm_plane_state state = {
-		.plane = crtc->primary,
-		.crtc = crtc,
-		.fb = crtc->primary->fb,
-		.crtc_x = 0,
-		.crtc_y = 0,
-		.crtc_w = crtc->mode.hdisplay,
-		.crtc_h = crtc->mode.vdisplay,
-		.src_x = x << 16,
-		.src_y = y << 16,
-		.src_w = crtc->mode.hdisplay << 16,
-		.src_h = crtc->mode.vdisplay << 16,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
-
-	armada_drm_do_primary_update(crtc->primary, &state, old_fb);
-
-	return 0;
 }
 
 /* The mode_config.mutex will be held for this call */
@@ -732,14 +657,49 @@ static void armada_drm_crtc_disable(struct drm_crtc *crtc)
 	crtc->primary->funcs->disable_plane(crtc->primary, NULL);
 }
 
+static void armada_drm_crtc_atomic_begin(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct armada_plane *dplane;
+
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
+
+	/* Wait 100ms for any plane works to complete */
+	dplane = drm_to_armada_plane(crtc->primary);
+	if (WARN_ON(armada_drm_plane_work_wait(dplane, HZ / 10) == 0))
+		armada_drm_plane_work_cancel(dcrtc, dplane);
+
+	dcrtc->regs_idx = 0;
+	dcrtc->regs = dcrtc->atomic_regs;
+}
+
+static void armada_drm_crtc_atomic_flush(struct drm_crtc *crtc,
+					 struct drm_crtc_state *old_crtc_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	unsigned long flags;
+
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
+
+	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
+
+	spin_lock_irqsave(&dcrtc->irq_lock, flags);
+	armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
+	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+}
+
 static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
 	.dpms		= armada_drm_crtc_dpms,
 	.prepare	= armada_drm_crtc_prepare,
 	.commit		= armada_drm_crtc_commit,
 	.mode_fixup	= armada_drm_crtc_mode_fixup,
-	.mode_set	= armada_drm_crtc_mode_set,
-	.mode_set_base	= armada_drm_crtc_mode_set_base,
+	.mode_set	= drm_helper_crtc_mode_set,
+	.mode_set_nofb	= armada_drm_crtc_mode_set_nofb,
+	.mode_set_base	= drm_helper_crtc_mode_set_base,
 	.disable	= armada_drm_crtc_disable,
+	.atomic_begin	= armada_drm_crtc_atomic_begin,
+	.atomic_flush	= armada_drm_crtc_atomic_flush,
 };
 
 static void armada_load_cursor_argb(void __iomem *base, uint32_t *pix,
@@ -1012,6 +972,12 @@ static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
 		return ret;
 	}
 
+	/*
+	 * We are in transition to atomic modeset: update the atomic modeset
+	 * state with the new framebuffer to keep the state consistent.
+	 */
+	drm_framebuffer_assign(&dcrtc->crtc.primary->state->fb, fb);
+
 	/*
 	 * Finally, if the display is blanked, we won't receive an
 	 * interrupt, so complete it now.
@@ -1072,16 +1038,66 @@ static void armada_drm_crtc_disable_vblank(struct drm_crtc *crtc)
 }
 
 static const struct drm_crtc_funcs armada_crtc_funcs = {
+	.reset		= drm_atomic_helper_crtc_reset,
 	.cursor_set	= armada_drm_crtc_cursor_set,
 	.cursor_move	= armada_drm_crtc_cursor_move,
 	.destroy	= armada_drm_crtc_destroy,
 	.set_config	= drm_crtc_helper_set_config,
 	.page_flip	= armada_drm_crtc_page_flip,
 	.set_property	= armada_drm_crtc_set_property,
+	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
 	.enable_vblank	= armada_drm_crtc_enable_vblank,
 	.disable_vblank	= armada_drm_crtc_disable_vblank,
 };
 
+static int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		state->fb ? state->fb->base.id : 0);
+
+	/*
+	 * Take a reference on the new framebuffer - we want to
+	 * hold on to it while the hardware is displaying it.
+	 */
+	if (state->fb)
+		drm_framebuffer_get(state->fb);
+	return 0;
+}
+
+static void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->fb ? old_state->fb->base.id : 0);
+
+	if (old_state->fb)
+		drm_framebuffer_put(old_state->fb);
+}
+
+static int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	if (state->fb && !WARN_ON(!state->crtc)) {
+		struct drm_crtc *crtc = state->crtc;
+		struct drm_crtc_state crtc_state = {
+			.crtc = crtc,
+			.enable = crtc->enabled,
+			.mode = crtc->mode,
+		};
+
+		return drm_atomic_helper_check_plane_state(state, &crtc_state,
+							   0, INT_MAX,
+							   true, false);
+	} else {
+		state->visible = false;
+	}
+	return 0;
+}
+
 static unsigned int armada_drm_primary_update_state(
 	struct drm_plane_state *state, struct armada_regs *regs)
 {
@@ -1134,94 +1150,70 @@ static unsigned int armada_drm_primary_update_state(
 	return idx;
 }
 
-static int armada_drm_do_primary_update(struct drm_plane *plane,
-	struct drm_plane_state *state, struct drm_framebuffer *old_fb)
+static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
 {
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
-	struct armada_plane_work *work;
-	struct drm_crtc_state crtc_state = {
-		.crtc = state->crtc,
-		.enable = state->crtc->enabled,
-		.mode = state->crtc->mode,
-	};
-	unsigned int idx;
-	int ret;
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
 
-	ret = drm_atomic_helper_check_plane_state(state, &crtc_state, 0,
-						  INT_MAX, true, false);
-	if (ret)
-		return ret;
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
 
-	work = &dplane->works[dplane->next_work];
-	work->fn = armada_drm_crtc_complete_frame_work;
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
 
-	if (old_fb != state->fb) {
-		/*
-		 * Take a reference on the new framebuffer - we want to
-		 * hold on to it while the hardware is displaying it.
-		 */
-		drm_framebuffer_reference(state->fb);
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
 
-		work->old_fb = old_fb;
-	} else {
-		work->old_fb = NULL;
-	}
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
 
-	idx = armada_drm_primary_update_state(state, work->regs);
-	armada_reg_queue_end(work->regs, idx);
+	dcrtc->regs_idx += armada_drm_primary_update_state(state, regs);
+}
 
-	if (!dplane->state.changed)
-		return 0;
+static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct armada_plane *dplane = drm_to_armada_plane(plane);
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx = 0;
 
-	/* Wait for pending work to complete */
-	if (armada_drm_plane_work_wait(dplane, HZ / 10) == 0)
-		armada_drm_plane_work_cancel(dcrtc, dplane);
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
 
-	if (!dplane->state.vsync_update) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-		return 0;
-	}
+	if (!old_state->crtc)
+		return;
 
-	/* Queue it for update on the next interrupt if we are enabled */
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-	}
+	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->crtc->base.id, old_state->crtc->name,
+		old_state->fb->base.id);
 
-	dplane->next_work = !dplane->next_work;
+	dplane->state.ctrl0 &= ~CFG_GRA_ENA;
 
-	return 0;
-}
+	dcrtc = drm_to_armada_crtc(old_state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
 
-static int armada_drm_primary_update(struct drm_plane *plane,
-	struct drm_crtc *crtc, struct drm_framebuffer *fb,
-	int crtc_x, int crtc_y, unsigned int crtc_w, unsigned int crtc_h,
-	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
-	struct drm_modeset_acquire_ctx *ctx)
-{
-	struct drm_plane_state state = {
-		.plane = plane,
-		.crtc = crtc,
-		.fb = fb,
-		.src_x = src_x,
-		.src_y = src_y,
-		.src_w = src_w,
-		.src_h = src_h,
-		.crtc_x = crtc_x,
-		.crtc_y = crtc_y,
-		.crtc_w = crtc_w,
-		.crtc_h = crtc_h,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
-
-	return armada_drm_do_primary_update(plane, &state, plane->fb);
+	/* Disable plane and power down most RAMs and FIFOs */
+	armada_reg_queue_mod(regs, idx, 0, CFG_GRA_ENA, LCD_SPU_DMA_CTRL0);
+	armada_reg_queue_mod(regs, idx, CFG_PDWN256x32 | CFG_PDWN256x24 |
+			     CFG_PDWN256x8 | CFG_PDWN32x32 | CFG_PDWN64x66,
+			     0, LCD_SPU_SRAM_PARA1);
+
+	dcrtc->regs_idx += idx;
 }
 
+static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
+	.prepare_fb	= armada_drm_plane_prepare_fb,
+	.cleanup_fb	= armada_drm_plane_cleanup_fb,
+	.atomic_check	= armada_drm_plane_atomic_check,
+	.atomic_update	= armada_drm_primary_plane_atomic_update,
+	.atomic_disable	= armada_drm_primary_plane_atomic_disable,
+};
+
 int armada_drm_plane_disable(struct drm_plane *plane,
 			     struct drm_modeset_acquire_ctx *ctx)
 {
@@ -1283,9 +1275,12 @@ int armada_drm_plane_disable(struct drm_plane *plane,
 }
 
 static const struct drm_plane_funcs armada_primary_plane_funcs = {
-	.update_plane	= armada_drm_primary_update,
-	.disable_plane	= armada_drm_plane_disable,
+	.update_plane	= drm_plane_helper_update,
+	.disable_plane	= drm_plane_helper_disable,
 	.destroy	= drm_primary_helper_destroy,
+	.reset		= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
 };
 
 int armada_drm_plane_init(struct armada_plane *plane)
@@ -1414,6 +1409,9 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 		goto err_crtc;
 	}
 
+	drm_plane_helper_add(&primary->base,
+			     &armada_primary_plane_helper_funcs);
+
 	ret = drm_universal_plane_init(drm, &primary->base, 0,
 				       &armada_primary_plane_funcs,
 				       armada_primary_formats,
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 8edcfd1fa75f..3253947e0d41 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -93,7 +93,6 @@ struct armada_crtc {
 	uint8_t			csc_rgb_mode;
 
 	struct drm_plane	*plane;
-	struct drm_framebuffer	*old_modeset_fb;
 
 	struct armada_gem_object	*cursor_obj;
 	int			cursor_x;
@@ -110,14 +109,15 @@ struct armada_crtc {
 
 	spinlock_t		irq_lock;
 	uint32_t		irq_ena;
+
+	struct armada_regs	atomic_regs[32];
+	struct armada_regs	*regs;
+	unsigned int		regs_idx;
 };
 #define drm_to_armada_crtc(c) container_of(c, struct armada_crtc, crtc)
 
 void armada_drm_crtc_update_regs(struct armada_crtc *, struct armada_regs *);
 
-int armada_drm_plane_disable(struct drm_plane *plane,
-			     struct drm_modeset_acquire_ctx *ctx);
-
 extern struct platform_driver armada_lcd_platform_driver;
 
 #endif
-- 
cgit v1.2.3


From de503ddff86ed31cde5ec5ea74ec7bf60d3fecc5 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: convert page_flip to use primary plane atomic_update()

page_flip requests happen asynchronously, so we can't wait on the
vblank event before returning to userspace, as the transitional plane
update helper would do.  Craft our own implementation that keeps the
asynchronous behaviour of this request, while making use of the atomic
infrastructure for the primary plane update.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 81 ++++++++++++++++++++++++------------
 1 file changed, 55 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 523e0e8c6962..50b34f5fc97b 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -11,6 +11,7 @@
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_plane_helper.h>
 #include <drm/drm_atomic_helper.h>
@@ -939,53 +940,81 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
  * and a mode_set.
  */
 static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
-	struct drm_framebuffer *fb, struct drm_pending_vblank_event *event, uint32_t page_flip_flags,
-	struct drm_modeset_acquire_ctx *ctx)
+	struct drm_framebuffer *fb, struct drm_pending_vblank_event *event,
+	uint32_t page_flip_flags, struct drm_modeset_acquire_ctx *ctx)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_plane *plane = crtc->primary;
+	const struct drm_plane_helper_funcs *plane_funcs;
+	struct drm_plane_state *state;
 	struct armada_plane_work *work;
-	unsigned i;
 	int ret;
 
-	work = armada_drm_crtc_alloc_plane_work(dcrtc->crtc.primary);
-	if (!work)
+	/* Construct new state for the primary plane */
+	state = drm_atomic_helper_plane_duplicate_state(plane);
+	if (!state)
 		return -ENOMEM;
 
-	work->event = event;
-	work->old_fb = dcrtc->crtc.primary->fb;
+	drm_atomic_set_fb_for_plane(state, fb);
 
-	i = armada_drm_crtc_calc_fb(fb, crtc->x, crtc->y, work->regs,
-				    dcrtc->interlaced);
-	armada_reg_queue_end(work->regs, i);
+	work = armada_drm_crtc_alloc_plane_work(plane);
+	if (!work) {
+		ret = -ENOMEM;
+		goto put_state;
+	}
+
+	/* Make sure we can get vblank interrupts */
+	ret = drm_crtc_vblank_get(crtc);
+	if (ret)
+		goto put_work;
 
 	/*
-	 * Ensure that we hold a reference on the new framebuffer.
-	 * This has to match the behaviour in mode_set.
+	 * If we have another work pending, we can't process this flip.
+	 * The modeset locks protect us from another user queuing a work
+	 * while we're setting up.
 	 */
-	drm_framebuffer_get(fb);
-
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret) {
-		/* Undo our reference above */
-		drm_framebuffer_put(fb);
-		kfree(work);
-		return ret;
+	if (drm_to_armada_plane(plane)->work) {
+		ret = -EBUSY;
+		goto put_vblank;
 	}
 
+	work->event = event;
+	work->old_fb = plane->state->fb;
+
 	/*
-	 * We are in transition to atomic modeset: update the atomic modeset
-	 * state with the new framebuffer to keep the state consistent.
+	 * Hold a ref on the new fb while it's being displayed by the
+	 * hardware. The old fb refcount will be released in the worker.
 	 */
-	drm_framebuffer_assign(&dcrtc->crtc.primary->state->fb, fb);
+	drm_framebuffer_get(state->fb);
+
+	/* Point of no return */
+	swap(plane->state, state);
+
+	dcrtc->regs_idx = 0;
+	dcrtc->regs = work->regs;
+
+	plane_funcs = plane->helper_private;
+	plane_funcs->atomic_update(plane, state);
+	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
+
+	/* Queue the work - this should never fail */
+	WARN_ON(armada_drm_plane_work_queue(dcrtc, work));
+	work = NULL;
 
 	/*
 	 * Finally, if the display is blanked, we won't receive an
 	 * interrupt, so complete it now.
 	 */
 	if (dpms_blanked(dcrtc->dpms))
-		armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
-
-	return 0;
+		armada_drm_plane_work_run(dcrtc, plane);
+
+put_vblank:
+	drm_crtc_vblank_put(crtc);
+put_work:
+	kfree(work);
+put_state:
+	drm_atomic_helper_plane_destroy_state(plane, state);
+	return ret;
 }
 
 static int
-- 
cgit v1.2.3


From 47dc413b0025e96eaa43bdd808233763e4080a10 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: convert overlay plane to atomic state

The overlay plane support updates asynchronously to the request, but the
drm_plane_helper_update() transitional helper waits for a vblank event
before releasing the framebuffer.  Using the transitional helper would
make the call block, which would introduce a performance regression.

Convert the overlay plane update to use the atomic state structures and
methods for the plane, but implement our own legacy update method
rather than the transitional helper.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c    |  79 +-------------
 drivers/gpu/drm/armada/armada_crtc.h    |   7 ++
 drivers/gpu/drm/armada/armada_overlay.c | 179 ++++++++++++++++++++++++--------
 3 files changed, 145 insertions(+), 120 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 50b34f5fc97b..5bb097b75b44 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -295,19 +295,6 @@ static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc,
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 }
 
-static void armada_drm_crtc_complete_disable_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	unsigned long flags;
-
-	if (dcrtc->plane == work->plane)
-		dcrtc->plane = NULL;
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
 static struct armada_plane_work *
 armada_drm_crtc_alloc_plane_work(struct drm_plane *plane)
 {
@@ -1080,7 +1067,7 @@ static const struct drm_crtc_funcs armada_crtc_funcs = {
 	.disable_vblank	= armada_drm_crtc_disable_vblank,
 };
 
-static int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_plane_state *state)
 {
 	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
@@ -1096,7 +1083,7 @@ static int armada_drm_plane_prepare_fb(struct drm_plane *plane,
 	return 0;
 }
 
-static void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
 	struct drm_plane_state *old_state)
 {
 	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
@@ -1107,7 +1094,7 @@ static void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
 		drm_framebuffer_put(old_state->fb);
 }
 
-static int armada_drm_plane_atomic_check(struct drm_plane *plane,
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
 	struct drm_plane_state *state)
 {
 	if (state->fb && !WARN_ON(!state->crtc)) {
@@ -1243,66 +1230,6 @@ static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
 	.atomic_disable	= armada_drm_primary_plane_atomic_disable,
 };
 
-int armada_drm_plane_disable(struct drm_plane *plane,
-			     struct drm_modeset_acquire_ctx *ctx)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_crtc *dcrtc;
-	struct armada_plane_work *work;
-	unsigned int idx = 0;
-	u32 sram_para1, enable_mask;
-
-	if (!plane->crtc)
-		return 0;
-
-	/*
-	 * Arrange to power down most RAMs and FIFOs if this is the primary
-	 * plane, otherwise just the YUV FIFOs for the overlay plane.
-	 */
-	if (plane->type == DRM_PLANE_TYPE_PRIMARY) {
-		sram_para1 = CFG_PDWN256x32 | CFG_PDWN256x24 | CFG_PDWN256x8 |
-			     CFG_PDWN32x32 | CFG_PDWN64x66;
-		enable_mask = CFG_GRA_ENA;
-	} else {
-		sram_para1 = CFG_PDWN16x66 | CFG_PDWN32x66;
-		enable_mask = CFG_DMA_ENA;
-	}
-
-	dplane->state.ctrl0 &= ~enable_mask;
-
-	dcrtc = drm_to_armada_crtc(plane->crtc);
-
-	/*
-	 * Try to disable the plane and drop our ref on the framebuffer
-	 * at the next frame update. If we fail for any reason, disable
-	 * the plane immediately.
-	 */
-	work = &dplane->works[dplane->next_work];
-	work->fn = armada_drm_crtc_complete_disable_work;
-	work->cancel = armada_drm_crtc_complete_disable_work;
-	work->old_fb = plane->fb;
-
-	armada_reg_queue_mod(work->regs, idx,
-			     0, enable_mask, LCD_SPU_DMA_CTRL0);
-	armada_reg_queue_mod(work->regs, idx,
-			     sram_para1, 0, LCD_SPU_SRAM_PARA1);
-	armada_reg_queue_end(work->regs, idx);
-
-	/* Wait for any preceding work to complete, but don't wedge */
-	if (WARN_ON(!armada_drm_plane_work_wait(dplane, HZ)))
-		armada_drm_plane_work_cancel(dcrtc, dplane);
-
-	if (armada_drm_plane_work_queue(dcrtc, work)) {
-		work->fn(dcrtc, work);
-		if (work->old_fb)
-			drm_framebuffer_unreference(work->old_fb);
-	}
-
-	dplane->next_work = !dplane->next_work;
-
-	return 0;
-}
-
 static const struct drm_plane_funcs armada_primary_plane_funcs = {
 	.update_plane	= drm_plane_helper_update,
 	.disable_plane	= drm_plane_helper_disable,
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 3253947e0d41..4da56a171b13 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -75,6 +75,13 @@ void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
 void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
 	int x, int y);
 
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state);
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state);
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state);
+
 struct armada_crtc {
 	struct drm_crtc		crtc;
 	const struct armada_variant *variant;
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index 2347811ccf1b..be9de5d85f9f 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -7,7 +7,9 @@
  * published by the Free Software Foundation.
  */
 #include <drm/drmP.h>
+#include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_fb.h"
@@ -78,7 +80,7 @@ static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 }
 
-static void armada_ovl_plane_update_state(struct drm_plane_state *state,
+static unsigned int armada_ovl_plane_update_state(struct drm_plane_state *state,
 	struct armada_regs *regs)
 {
 	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(state->plane);
@@ -180,67 +182,116 @@ static void armada_ovl_plane_update_state(struct drm_plane_state *state,
 
 	dplane->base.state.changed = idx != 0;
 
-	armada_reg_queue_end(regs, idx);
+	return idx;
 }
 
-static int
-armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
-	struct drm_framebuffer *fb,
-	int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h,
-	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
-	struct drm_modeset_acquire_ctx *ctx)
+static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
+
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	dcrtc->regs_idx += armada_ovl_plane_update_state(state, regs);
+}
+
+static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct armada_plane *dplane = drm_to_armada_plane(plane);
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx = 0;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!old_state->crtc)
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->crtc->base.id, old_state->crtc->name,
+		old_state->fb->base.id);
+
+	dplane->state.ctrl0 &= ~CFG_DMA_ENA;
+
+	dcrtc = drm_to_armada_crtc(old_state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	/* Disable plane and power down the YUV FIFOs */
+	armada_reg_queue_mod(regs, idx, 0, CFG_DMA_ENA, LCD_SPU_DMA_CTRL0);
+	armada_reg_queue_mod(regs, idx, CFG_PDWN16x66 | CFG_PDWN32x66, 0,
+			     LCD_SPU_SRAM_PARA1);
+
+	dcrtc->regs_idx += idx;
+
+	if (dcrtc->plane == plane)
+		dcrtc->plane = NULL;
+}
+
+static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = {
+	.prepare_fb	= armada_drm_plane_prepare_fb,
+	.cleanup_fb	= armada_drm_plane_cleanup_fb,
+	.atomic_check	= armada_drm_plane_atomic_check,
+	.atomic_update	= armada_drm_overlay_plane_atomic_update,
+	.atomic_disable	= armada_drm_overlay_plane_atomic_disable,
+};
+
+static int armada_overlay_commit(struct drm_plane *plane,
+	struct drm_plane_state *state)
 {
 	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	const struct drm_plane_helper_funcs *plane_funcs;
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
 	struct armada_plane_work *work;
-	struct drm_plane_state state = {
-		.plane = plane,
-		.crtc = crtc,
-		.fb = fb,
-		.src_x = src_x,
-		.src_y = src_y,
-		.src_w = src_w,
-		.src_h = src_h,
-		.crtc_x = crtc_x,
-		.crtc_y = crtc_y,
-		.crtc_w = crtc_w,
-		.crtc_h = crtc_h,
-		.rotation = DRM_MODE_ROTATE_0,
-	};
-	struct drm_crtc_state crtc_state = {
-		.crtc = crtc,
-		.enable = crtc->enabled,
-		.mode = crtc->mode,
-	};
 	int ret;
 
-	trace_armada_ovl_plane_update(plane, crtc, fb,
-				 crtc_x, crtc_y, crtc_w, crtc_h,
-				 src_x, src_y, src_w, src_h);
-
-	ret = drm_atomic_helper_check_plane_state(&state, &crtc_state, 0,
-						  INT_MAX, true, false);
+	plane_funcs = plane->helper_private;
+	ret = plane_funcs->atomic_check(plane, state);
 	if (ret)
-		return ret;
+		goto put_state;
 
 	work = &dplane->base.works[dplane->base.next_work];
 
-	if (plane->fb != fb) {
+	if (plane->state->fb != state->fb) {
 		/*
 		 * Take a reference on the new framebuffer - we want to
 		 * hold on to it while the hardware is displaying it.
 		 */
-		drm_framebuffer_reference(fb);
+		drm_framebuffer_reference(state->fb);
 
-		work->old_fb = plane->fb;
+		work->old_fb = plane->state->fb;
 	} else {
 		work->old_fb = NULL;
 	}
 
-	armada_ovl_plane_update_state(&state, work->regs);
+	/* Point of no return */
+	swap(plane->state, state);
+
+	dcrtc->regs_idx = 0;
+	dcrtc->regs = work->regs;
 
+	plane_funcs->atomic_update(plane, state);
+
+	/* If nothing was updated, short-circuit */
 	if (!dplane->base.state.changed)
-		return 0;
+		goto put_state;
+
+	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
 
 	/* Wait for pending work to complete */
 	if (armada_drm_plane_work_wait(&dplane->base, HZ / 25) == 0)
@@ -249,7 +300,7 @@ armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	/* Just updating the position/size? */
 	if (!dplane->base.state.vsync_update) {
 		armada_ovl_plane_work(dcrtc, work);
-		return 0;
+		goto put_state;
 	}
 
 	if (!dcrtc->plane) {
@@ -259,12 +310,48 @@ armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 
 	/* Queue it for update on the next interrupt if we are enabled */
 	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret)
+	if (ret) {
 		DRM_ERROR("failed to queue plane work: %d\n", ret);
+		ret = 0;
+	}
 
 	dplane->base.next_work = !dplane->base.next_work;
 
-	return 0;
+put_state:
+	drm_atomic_helper_plane_destroy_state(plane, state);
+	return ret;
+}
+
+static int
+armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
+	struct drm_framebuffer *fb,
+	int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h,
+	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
+	struct drm_modeset_acquire_ctx *ctx)
+{
+	struct drm_plane_state *state;
+
+	trace_armada_ovl_plane_update(plane, crtc, fb,
+				 crtc_x, crtc_y, crtc_w, crtc_h,
+				 src_x, src_y, src_w, src_h);
+
+	/* Construct new state for the overlay plane */
+	state = drm_atomic_helper_plane_duplicate_state(plane);
+	if (!state)
+		return -ENOMEM;
+
+	state->crtc = crtc;
+	drm_atomic_set_fb_for_plane(state, fb);
+	state->crtc_x = crtc_x;
+	state->crtc_y = crtc_y;
+	state->crtc_h = crtc_h;
+	state->crtc_w = crtc_w;
+	state->src_x = src_x;
+	state->src_y = src_y;
+	state->src_h = src_h;
+	state->src_w = src_w;
+
+	return armada_overlay_commit(plane, state);
 }
 
 static void armada_ovl_plane_destroy(struct drm_plane *plane)
@@ -355,9 +442,10 @@ static int armada_ovl_plane_set_property(struct drm_plane *plane,
 
 static const struct drm_plane_funcs armada_ovl_plane_funcs = {
 	.update_plane	= armada_ovl_plane_update,
-	.disable_plane	= armada_drm_plane_disable,
+	.disable_plane	= drm_plane_helper_disable,
 	.destroy	= armada_ovl_plane_destroy,
 	.set_property	= armada_ovl_plane_set_property,
+	.reset		= drm_atomic_helper_plane_reset,
 };
 
 static const uint32_t armada_ovl_formats[] = {
@@ -450,6 +538,9 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 	dplane->base.works[0].fn = armada_ovl_plane_work;
 	dplane->base.works[1].fn = armada_ovl_plane_work;
 
+	drm_plane_helper_add(&dplane->base.base,
+			     &armada_overlay_plane_helper_funcs);
+
 	ret = drm_universal_plane_init(dev, &dplane->base.base, crtcs,
 				       &armada_ovl_plane_funcs,
 				       armada_ovl_formats,
-- 
cgit v1.2.3


From 9c41467c9aa5b3916ff559b8c2b3725d6290e5ec Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: remove temporary crtc state

Now that we have the CRTC using the atomic modeset transitional helper,
there is no need to build a temporary crtc state anymore - we can use
the CRTC atomic state directly.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 5bb097b75b44..056673911818 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -1099,13 +1099,13 @@ int armada_drm_plane_atomic_check(struct drm_plane *plane,
 {
 	if (state->fb && !WARN_ON(!state->crtc)) {
 		struct drm_crtc *crtc = state->crtc;
-		struct drm_crtc_state crtc_state = {
-			.crtc = crtc,
-			.enable = crtc->enabled,
-			.mode = crtc->mode,
-		};
+		struct drm_crtc_state *crtc_state;
 
-		return drm_atomic_helper_check_plane_state(state, &crtc_state,
+		if (state->state)
+			crtc_state = drm_atomic_get_existing_crtc_state(state->state, crtc);
+		else
+			crtc_state = crtc->state;
+		return drm_atomic_helper_check_plane_state(state, crtc_state,
 							   0, INT_MAX,
 							   true, false);
 	} else {
-- 
cgit v1.2.3


From 3acea7b9b62c282ea3d4d0cd156ca8e35dfa8a8c Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: use old_state for update tracking in atomic_update()

Rather than tracking the register state, we can now check the previous
state and decide which registers need updating from that since the old
plane state indicates the previous state which was programmed into the
hardware.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c    | 116 ++++++++++----------
 drivers/gpu/drm/armada/armada_crtc.h    |  12 --
 drivers/gpu/drm/armada/armada_overlay.c | 189 ++++++++++++++------------------
 3 files changed, 144 insertions(+), 173 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 056673911818..14339d5bed14 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -1114,64 +1114,14 @@ int armada_drm_plane_atomic_check(struct drm_plane *plane,
 	return 0;
 }
 
-static unsigned int armada_drm_primary_update_state(
-	struct drm_plane_state *state, struct armada_regs *regs)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(state->plane);
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb);
-	bool was_disabled;
-	unsigned int idx = 0;
-	u32 val;
-
-	val = CFG_GRA_FMT(dfb->fmt) | CFG_GRA_MOD(dfb->mod);
-	if (dfb->fmt > CFG_420)
-		val |= CFG_PALETTE_ENA;
-	if (state->visible)
-		val |= CFG_GRA_ENA;
-	if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst))
-		val |= CFG_GRA_HSMOOTH;
-	if (dcrtc->interlaced)
-		val |= CFG_GRA_FTOGGLE;
-
-	was_disabled = !(dplane->state.ctrl0 & CFG_GRA_ENA);
-	if (was_disabled)
-		armada_reg_queue_mod(regs, idx,
-				     0, CFG_PDWN64x66, LCD_SPU_SRAM_PARA1);
-
-	dplane->state.ctrl0 = val;
-	dplane->state.src_hw = armada_rect_hw_fp(&state->src);
-	dplane->state.dst_hw = armada_rect_hw(&state->dst);
-	dplane->state.dst_yx = armada_rect_yx(&state->dst);
-
-	idx += armada_drm_crtc_calc_fb(&dfb->fb, state->src.x1 >> 16,
-				       state->src.y1 >> 16, regs + idx,
-				       dcrtc->interlaced);
-	armada_reg_queue_set(regs, idx, dplane->state.dst_yx,
-			     LCD_SPU_GRA_OVSA_HPXL_VLN);
-	armada_reg_queue_set(regs, idx, dplane->state.src_hw,
-			     LCD_SPU_GRA_HPXL_VLN);
-	armada_reg_queue_set(regs, idx, dplane->state.dst_hw,
-			     LCD_SPU_GZM_HPXL_VLN);
-	armada_reg_queue_mod(regs, idx, dplane->state.ctrl0, CFG_GRAFORMAT |
-			     CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
-					 CFG_SWAPYU | CFG_YUV2RGB) |
-			     CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
-			     CFG_GRA_HSMOOTH | CFG_GRA_ENA,
-			     LCD_SPU_DMA_CTRL0);
-
-	dplane->state.vsync_update = !was_disabled;
-	dplane->state.changed = true;
-
-	return idx;
-}
-
 static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
 	struct drm_plane_state *old_state)
 {
 	struct drm_plane_state *state = plane->state;
 	struct armada_crtc *dcrtc;
 	struct armada_regs *regs;
+	u32 cfg, cfg_mask, val;
+	unsigned int idx;
 
 	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
 
@@ -1187,13 +1137,69 @@ static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
 	dcrtc = drm_to_armada_crtc(state->crtc);
 	regs = dcrtc->regs + dcrtc->regs_idx;
 
-	dcrtc->regs_idx += armada_drm_primary_update_state(state, regs);
+	idx = 0;
+	if (!old_state->visible && state->visible) {
+		val = CFG_PDWN64x66;
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			val |= CFG_PDWN256x24;
+		armada_reg_queue_mod(regs, idx, 0, val, LCD_SPU_SRAM_PARA1);
+	}
+	val = armada_rect_hw_fp(&state->src);
+	if (armada_rect_hw_fp(&old_state->src) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_HPXL_VLN);
+	val = armada_rect_yx(&state->dst);
+	if (armada_rect_yx(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_OVSA_HPXL_VLN);
+	val = armada_rect_hw(&state->dst);
+	if (armada_rect_hw(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GZM_HPXL_VLN);
+	if (old_state->src.x1 != state->src.x1 ||
+	    old_state->src.y1 != state->src.y1 ||
+	    old_state->fb != state->fb) {
+		idx += armada_drm_crtc_calc_fb(state->fb,
+					       state->src.x1 >> 16,
+					       state->src.y1 >> 16,
+					       regs + idx,
+					       dcrtc->interlaced);
+	}
+	if (old_state->fb != state->fb) {
+		cfg = CFG_GRA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
+		      CFG_GRA_MOD(drm_fb_to_armada_fb(state->fb)->mod);
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			cfg |= CFG_PALETTE_ENA;
+		if (state->visible)
+			cfg |= CFG_GRA_ENA;
+		if (dcrtc->interlaced)
+			cfg |= CFG_GRA_FTOGGLE;
+		cfg_mask = CFG_GRAFORMAT |
+			   CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+				       CFG_SWAPYU | CFG_YUV2RGB) |
+			   CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
+			   CFG_GRA_ENA;
+	} else if (old_state->visible != state->visible) {
+		cfg = state->visible ? CFG_GRA_ENA : 0;
+		cfg_mask = CFG_GRA_ENA;
+	} else {
+		cfg = cfg_mask = 0;
+	}
+	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
+	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
+		cfg_mask |= CFG_GRA_HSMOOTH;
+		if (drm_rect_width(&state->src) >> 16 !=
+		    drm_rect_width(&state->dst))
+			cfg |= CFG_GRA_HSMOOTH;
+	}
+
+	if (cfg_mask)
+		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
+				     LCD_SPU_DMA_CTRL0);
+
+	dcrtc->regs_idx += idx;
 }
 
 static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
 	struct drm_plane_state *old_state)
 {
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
 	struct armada_crtc *dcrtc;
 	struct armada_regs *regs;
 	unsigned int idx = 0;
@@ -1208,8 +1214,6 @@ static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
 		old_state->crtc->base.id, old_state->crtc->name,
 		old_state->fb->base.id);
 
-	dplane->state.ctrl0 &= ~CFG_GRA_ENA;
-
 	dcrtc = drm_to_armada_crtc(old_state->crtc);
 	regs = dcrtc->regs + dcrtc->regs_idx;
 
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 4da56a171b13..79ac0db047c9 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -45,24 +45,12 @@ struct armada_plane_work {
 	struct armada_regs regs[14];
 };
 
-struct armada_plane_state {
-	u16 src_x;
-	u16 src_y;
-	u32 src_hw;
-	u32 dst_hw;
-	u32 dst_yx;
-	u32 ctrl0;
-	bool changed;
-	bool vsync_update;
-};
-
 struct armada_plane {
 	struct drm_plane	base;
 	wait_queue_head_t	frame_wait;
 	bool			next_work;
 	struct armada_plane_work works[2];
 	struct armada_plane_work *work;
-	struct armada_plane_state state;
 };
 #define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
 
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index be9de5d85f9f..aa2a12aec3cc 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -35,6 +35,7 @@ struct armada_ovl_plane_properties {
 
 struct armada_ovl_plane {
 	struct armada_plane base;
+	bool wait_vblank;
 	struct armada_ovl_plane_properties prop;
 };
 #define drm_to_armada_ovl_plane(p) \
@@ -80,52 +81,55 @@ static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 }
 
-static unsigned int armada_ovl_plane_update_state(struct drm_plane_state *state,
-	struct armada_regs *regs)
+static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
 {
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(state->plane);
-	struct armada_framebuffer *dfb = drm_fb_to_armada_fb(state->fb);
-	const struct drm_format_info *format;
-	unsigned int idx = 0;
-	bool fb_changed;
-	u32 val, ctrl0;
-	u16 src_x, src_y;
-
-	ctrl0 = CFG_DMA_FMT(dfb->fmt) | CFG_DMA_MOD(dfb->mod) | CFG_CBSH_ENA;
-	if (state->visible)
-		ctrl0 |= CFG_DMA_ENA;
-	if (drm_rect_width(&state->src) >> 16 != drm_rect_width(&state->dst))
-		ctrl0 |= CFG_DMA_HSMOOTH;
-
-	/*
-	 * Shifting a YUV packed format image by one pixel causes the U/V
-	 * planes to swap.  Compensate for it by also toggling the UV swap.
-	 */
-	format = dfb->fb.format;
-	if (format->num_planes == 1 && state->src.x1 >> 16 & (format->hsub - 1))
-		ctrl0 ^= CFG_DMA_MOD(CFG_SWAPUV);
-
-	if (~dplane->base.state.ctrl0 & ctrl0 & CFG_DMA_ENA) {
-		/* Power up the Y/U/V FIFOs on ENA 0->1 transitions */
-		armada_reg_queue_mod(regs, idx,
-				     0, CFG_PDWN16x66 | CFG_PDWN32x66,
-				     LCD_SPU_SRAM_PARA1);
-	}
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx;
+	u32 cfg, cfg_mask, val;
 
-	fb_changed = dplane->base.base.fb != &dfb->fb ||
-		     dplane->base.state.src_x != state->src.x1 >> 16 ||
-	             dplane->base.state.src_y != state->src.y1 >> 16;
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
 
-	dplane->base.state.vsync_update = fb_changed;
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
 
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
+
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	drm_to_armada_ovl_plane(plane)->wait_vblank = false;
+
+	idx = 0;
+	if (!old_state->visible && state->visible)
+		armada_reg_queue_mod(regs, idx,
+				     0, CFG_PDWN16x66 | CFG_PDWN32x66,
+				     LCD_SPU_SRAM_PARA1);
+	val = armada_rect_hw_fp(&state->src);
+	if (armada_rect_hw_fp(&old_state->src) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_HPXL_VLN);
+	val = armada_rect_yx(&state->dst);
+	if (armada_rect_yx(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_OVSA_HPXL_VLN);
+	val = armada_rect_hw(&state->dst);
+	if (armada_rect_hw(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DZM_HPXL_VLN);
 	/* FIXME: overlay on an interlaced display */
-	if (fb_changed) {
+	if (old_state->src.x1 != state->src.x1 ||
+	    old_state->src.y1 != state->src.y1 ||
+	    old_state->fb != state->fb) {
+		const struct drm_format_info *format;
+		u16 src_x = state->src.x1 >> 16;
+		u16 src_y = state->src.y1 >> 16;
 		u32 addrs[3];
 
-		dplane->base.state.src_y = src_y = state->src.y1 >> 16;
-		dplane->base.state.src_x = src_x = state->src.x1 >> 16;
-
-		armada_drm_plane_calc_addrs(addrs, &dfb->fb, src_x, src_y);
+		armada_drm_plane_calc_addrs(addrs, state->fb, src_x, src_y);
 
 		armada_reg_queue_set(regs, idx, addrs[0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
@@ -140,79 +144,56 @@ static unsigned int armada_ovl_plane_update_state(struct drm_plane_state *state,
 		armada_reg_queue_set(regs, idx, addrs[2],
 				     LCD_SPU_DMA_START_ADDR_V1);
 
-		val = dfb->fb.pitches[0] << 16 | dfb->fb.pitches[0];
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_PITCH_YC);
-		val = dfb->fb.pitches[1] << 16 | dfb->fb.pitches[2];
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_PITCH_UV);
-	}
-
-	val = armada_rect_hw_fp(&state->src);
-	if (dplane->base.state.src_hw != val) {
-		dplane->base.state.src_hw = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_HPXL_VLN);
-	}
+		val = state->fb->pitches[0] << 16 | state->fb->pitches[0];
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_YC);
+		val = state->fb->pitches[1] << 16 | state->fb->pitches[2];
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_UV);
 
-	val = armada_rect_hw(&state->dst);
-	if (dplane->base.state.dst_hw != val) {
-		dplane->base.state.dst_hw = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DZM_HPXL_VLN);
-	}
+		cfg = CFG_DMA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
+		      CFG_DMA_MOD(drm_fb_to_armada_fb(state->fb)->mod) |
+		      CFG_CBSH_ENA;
+		if (state->visible)
+			cfg |= CFG_DMA_ENA;
 
-	val = armada_rect_yx(&state->dst);
-	if (dplane->base.state.dst_yx != val) {
-		dplane->base.state.dst_yx = val;
-		armada_reg_queue_set(regs, idx, val,
-				     LCD_SPU_DMA_OVSA_HPXL_VLN);
+		/*
+		 * Shifting a YUV packed format image by one pixel causes the
+		 * U/V planes to swap.  Compensate for it by also toggling
+		 * the UV swap.
+		 */
+		format = state->fb->format;
+		if (format->num_planes == 1 && src_x & (format->hsub - 1))
+			cfg ^= CFG_DMA_MOD(CFG_SWAPUV);
+		cfg_mask = CFG_CBSH_ENA | CFG_DMAFORMAT |
+			   CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+				       CFG_SWAPYU | CFG_YUV2RGB) |
+			   CFG_DMA_FTOGGLE | CFG_DMA_TSTMODE |
+			   CFG_DMA_ENA;
+
+		drm_to_armada_ovl_plane(plane)->wait_vblank = true;
+	} else if (old_state->visible != state->visible) {
+		cfg = state->visible ? CFG_DMA_ENA : 0;
+		cfg_mask = CFG_DMA_ENA;
+	} else {
+		cfg = cfg_mask = 0;
 	}
-
-	if (dplane->base.state.ctrl0 != ctrl0) {
-		dplane->base.state.ctrl0 = ctrl0;
-		armada_reg_queue_mod(regs, idx, ctrl0,
-			CFG_CBSH_ENA | CFG_DMAFORMAT | CFG_DMA_FTOGGLE |
-			CFG_DMA_HSMOOTH | CFG_DMA_TSTMODE |
-			CFG_DMA_MOD(CFG_SWAPRB | CFG_SWAPUV | CFG_SWAPYU |
-			CFG_YUV2RGB) | CFG_DMA_ENA,
-			LCD_SPU_DMA_CTRL0);
-		dplane->base.state.vsync_update = true;
+	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
+	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
+		cfg_mask |= CFG_DMA_HSMOOTH;
+		if (drm_rect_width(&state->src) >> 16 !=
+		    drm_rect_width(&state->dst))
+			cfg |= CFG_DMA_HSMOOTH;
 	}
 
-	dplane->base.state.changed = idx != 0;
-
-	return idx;
-}
-
-static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
-	struct drm_plane_state *old_state)
-{
-	struct drm_plane_state *state = plane->state;
-	struct armada_crtc *dcrtc;
-	struct armada_regs *regs;
+	if (cfg_mask)
+		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
+				     LCD_SPU_DMA_CTRL0);
 
-	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
-
-	if (!state->fb || WARN_ON(!state->crtc))
-		return;
-
-	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
-		plane->base.id, plane->name,
-		state->crtc->base.id, state->crtc->name,
-		state->fb->base.id,
-		old_state->visible, state->visible);
-
-	dcrtc = drm_to_armada_crtc(state->crtc);
-	regs = dcrtc->regs + dcrtc->regs_idx;
-
-	dcrtc->regs_idx += armada_ovl_plane_update_state(state, regs);
+	dcrtc->regs_idx += idx;
 }
 
 static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane,
 	struct drm_plane_state *old_state)
 {
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
 	struct armada_crtc *dcrtc;
 	struct armada_regs *regs;
 	unsigned int idx = 0;
@@ -227,8 +208,6 @@ static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane,
 		old_state->crtc->base.id, old_state->crtc->name,
 		old_state->fb->base.id);
 
-	dplane->state.ctrl0 &= ~CFG_DMA_ENA;
-
 	dcrtc = drm_to_armada_crtc(old_state->crtc);
 	regs = dcrtc->regs + dcrtc->regs_idx;
 
@@ -288,7 +267,7 @@ static int armada_overlay_commit(struct drm_plane *plane,
 	plane_funcs->atomic_update(plane, state);
 
 	/* If nothing was updated, short-circuit */
-	if (!dplane->base.state.changed)
+	if (dcrtc->regs_idx == 0)
 		goto put_state;
 
 	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
@@ -298,7 +277,7 @@ static int armada_overlay_commit(struct drm_plane *plane,
 		armada_drm_plane_work_cancel(dcrtc, &dplane->base);
 
 	/* Just updating the position/size? */
-	if (!dplane->base.state.vsync_update) {
+	if (!dplane->wait_vblank) {
 		armada_ovl_plane_work(dcrtc, work);
 		goto put_state;
 	}
-- 
cgit v1.2.3


From d40af7b1ae23da718ba916fcd07f5b064efff921 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: move primary plane to separate file

Split out the primary plane support; this is now entirely separate from
the CRTC support.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/Makefile         |   2 +-
 drivers/gpu/drm/armada/armada_crtc.c    | 273 +----------------------------
 drivers/gpu/drm/armada/armada_crtc.h    |  10 --
 drivers/gpu/drm/armada/armada_overlay.c |   3 +-
 drivers/gpu/drm/armada/armada_plane.c   | 297 ++++++++++++++++++++++++++++++++
 drivers/gpu/drm/armada/armada_plane.h   |  16 ++
 6 files changed, 318 insertions(+), 283 deletions(-)
 create mode 100644 drivers/gpu/drm/armada/armada_plane.c
 create mode 100644 drivers/gpu/drm/armada/armada_plane.h

diff --git a/drivers/gpu/drm/armada/Makefile b/drivers/gpu/drm/armada/Makefile
index ecf25cf9f9f5..9bc3c3213724 100644
--- a/drivers/gpu/drm/armada/Makefile
+++ b/drivers/gpu/drm/armada/Makefile
@@ -1,6 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 armada-y	:= armada_crtc.o armada_drv.o armada_fb.o armada_fbdev.o \
-		   armada_gem.o armada_overlay.o armada_trace.o
+		   armada_gem.o armada_overlay.o armada_plane.o armada_trace.o
 armada-y	+= armada_510.o
 armada-$(CONFIG_DEBUG_FS) += armada_debugfs.o
 
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 14339d5bed14..b9b0a508793d 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -20,6 +20,7 @@
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
+#include "armada_plane.h"
 #include "armada_trace.h"
 
 enum csc_mode {
@@ -30,23 +31,6 @@ enum csc_mode {
 	CSC_RGB_STUDIO = 2,
 };
 
-static const uint32_t armada_primary_formats[] = {
-	DRM_FORMAT_UYVY,
-	DRM_FORMAT_YUYV,
-	DRM_FORMAT_VYUY,
-	DRM_FORMAT_YVYU,
-	DRM_FORMAT_ARGB8888,
-	DRM_FORMAT_ABGR8888,
-	DRM_FORMAT_XRGB8888,
-	DRM_FORMAT_XBGR8888,
-	DRM_FORMAT_RGB888,
-	DRM_FORMAT_BGR888,
-	DRM_FORMAT_ARGB1555,
-	DRM_FORMAT_ABGR1555,
-	DRM_FORMAT_RGB565,
-	DRM_FORMAT_BGR565,
-};
-
 /*
  * A note about interlacing.  Let's consider HDMI 1920x1080i.
  * The timing parameters we have from X are:
@@ -160,57 +144,6 @@ static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
 	}
 }
 
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y)
-{
-	const struct drm_format_info *format = fb->format;
-	unsigned int num_planes = format->num_planes;
-	u32 addr = drm_fb_obj(fb)->dev_addr;
-	int i;
-
-	if (num_planes > 3)
-		num_planes = 3;
-
-	addrs[0] = addr + fb->offsets[0] + y * fb->pitches[0] +
-		   x * format->cpp[0];
-
-	y /= format->vsub;
-	x /= format->hsub;
-
-	for (i = 1; i < num_planes; i++)
-		addrs[i] = addr + fb->offsets[i] + y * fb->pitches[i] +
-			     x * format->cpp[i];
-	for (; i < 3; i++)
-		addrs[i] = 0;
-}
-
-static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb,
-	int x, int y, struct armada_regs *regs, bool interlaced)
-{
-	unsigned pitch = fb->pitches[0];
-	u32 addrs[3], addr_odd, addr_even;
-	unsigned i = 0;
-
-	DRM_DEBUG_DRIVER("pitch %u x %d y %d bpp %d\n",
-		pitch, x, y, fb->format->cpp[0] * 8);
-
-	armada_drm_plane_calc_addrs(addrs, fb, x, y);
-
-	addr_odd = addr_even = addrs[0];
-
-	if (interlaced) {
-		addr_even += pitch;
-		pitch *= 2;
-	}
-
-	/* write offset, base, and pitch */
-	armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0);
-	armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1);
-	armada_reg_queue_mod(regs, i, pitch, 0xffff, LCD_CFG_GRA_PITCH);
-
-	return i;
-}
-
 static void armada_drm_plane_work_call(struct armada_crtc *dcrtc,
 	struct armada_plane_work *work,
 	void (*fn)(struct armada_crtc *, struct armada_plane_work *))
@@ -1067,194 +1000,6 @@ static const struct drm_crtc_funcs armada_crtc_funcs = {
 	.disable_vblank	= armada_drm_crtc_disable_vblank,
 };
 
-int armada_drm_plane_prepare_fb(struct drm_plane *plane,
-	struct drm_plane_state *state)
-{
-	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
-		plane->base.id, plane->name,
-		state->fb ? state->fb->base.id : 0);
-
-	/*
-	 * Take a reference on the new framebuffer - we want to
-	 * hold on to it while the hardware is displaying it.
-	 */
-	if (state->fb)
-		drm_framebuffer_get(state->fb);
-	return 0;
-}
-
-void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
-	struct drm_plane_state *old_state)
-{
-	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
-		plane->base.id, plane->name,
-		old_state->fb ? old_state->fb->base.id : 0);
-
-	if (old_state->fb)
-		drm_framebuffer_put(old_state->fb);
-}
-
-int armada_drm_plane_atomic_check(struct drm_plane *plane,
-	struct drm_plane_state *state)
-{
-	if (state->fb && !WARN_ON(!state->crtc)) {
-		struct drm_crtc *crtc = state->crtc;
-		struct drm_crtc_state *crtc_state;
-
-		if (state->state)
-			crtc_state = drm_atomic_get_existing_crtc_state(state->state, crtc);
-		else
-			crtc_state = crtc->state;
-		return drm_atomic_helper_check_plane_state(state, crtc_state,
-							   0, INT_MAX,
-							   true, false);
-	} else {
-		state->visible = false;
-	}
-	return 0;
-}
-
-static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
-	struct drm_plane_state *old_state)
-{
-	struct drm_plane_state *state = plane->state;
-	struct armada_crtc *dcrtc;
-	struct armada_regs *regs;
-	u32 cfg, cfg_mask, val;
-	unsigned int idx;
-
-	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
-
-	if (!state->fb || WARN_ON(!state->crtc))
-		return;
-
-	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
-		plane->base.id, plane->name,
-		state->crtc->base.id, state->crtc->name,
-		state->fb->base.id,
-		old_state->visible, state->visible);
-
-	dcrtc = drm_to_armada_crtc(state->crtc);
-	regs = dcrtc->regs + dcrtc->regs_idx;
-
-	idx = 0;
-	if (!old_state->visible && state->visible) {
-		val = CFG_PDWN64x66;
-		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
-			val |= CFG_PDWN256x24;
-		armada_reg_queue_mod(regs, idx, 0, val, LCD_SPU_SRAM_PARA1);
-	}
-	val = armada_rect_hw_fp(&state->src);
-	if (armada_rect_hw_fp(&old_state->src) != val)
-		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_HPXL_VLN);
-	val = armada_rect_yx(&state->dst);
-	if (armada_rect_yx(&old_state->dst) != val)
-		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_OVSA_HPXL_VLN);
-	val = armada_rect_hw(&state->dst);
-	if (armada_rect_hw(&old_state->dst) != val)
-		armada_reg_queue_set(regs, idx, val, LCD_SPU_GZM_HPXL_VLN);
-	if (old_state->src.x1 != state->src.x1 ||
-	    old_state->src.y1 != state->src.y1 ||
-	    old_state->fb != state->fb) {
-		idx += armada_drm_crtc_calc_fb(state->fb,
-					       state->src.x1 >> 16,
-					       state->src.y1 >> 16,
-					       regs + idx,
-					       dcrtc->interlaced);
-	}
-	if (old_state->fb != state->fb) {
-		cfg = CFG_GRA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
-		      CFG_GRA_MOD(drm_fb_to_armada_fb(state->fb)->mod);
-		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
-			cfg |= CFG_PALETTE_ENA;
-		if (state->visible)
-			cfg |= CFG_GRA_ENA;
-		if (dcrtc->interlaced)
-			cfg |= CFG_GRA_FTOGGLE;
-		cfg_mask = CFG_GRAFORMAT |
-			   CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
-				       CFG_SWAPYU | CFG_YUV2RGB) |
-			   CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
-			   CFG_GRA_ENA;
-	} else if (old_state->visible != state->visible) {
-		cfg = state->visible ? CFG_GRA_ENA : 0;
-		cfg_mask = CFG_GRA_ENA;
-	} else {
-		cfg = cfg_mask = 0;
-	}
-	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
-	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
-		cfg_mask |= CFG_GRA_HSMOOTH;
-		if (drm_rect_width(&state->src) >> 16 !=
-		    drm_rect_width(&state->dst))
-			cfg |= CFG_GRA_HSMOOTH;
-	}
-
-	if (cfg_mask)
-		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
-				     LCD_SPU_DMA_CTRL0);
-
-	dcrtc->regs_idx += idx;
-}
-
-static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
-	struct drm_plane_state *old_state)
-{
-	struct armada_crtc *dcrtc;
-	struct armada_regs *regs;
-	unsigned int idx = 0;
-
-	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
-
-	if (!old_state->crtc)
-		return;
-
-	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
-		plane->base.id, plane->name,
-		old_state->crtc->base.id, old_state->crtc->name,
-		old_state->fb->base.id);
-
-	dcrtc = drm_to_armada_crtc(old_state->crtc);
-	regs = dcrtc->regs + dcrtc->regs_idx;
-
-	/* Disable plane and power down most RAMs and FIFOs */
-	armada_reg_queue_mod(regs, idx, 0, CFG_GRA_ENA, LCD_SPU_DMA_CTRL0);
-	armada_reg_queue_mod(regs, idx, CFG_PDWN256x32 | CFG_PDWN256x24 |
-			     CFG_PDWN256x8 | CFG_PDWN32x32 | CFG_PDWN64x66,
-			     0, LCD_SPU_SRAM_PARA1);
-
-	dcrtc->regs_idx += idx;
-}
-
-static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
-	.prepare_fb	= armada_drm_plane_prepare_fb,
-	.cleanup_fb	= armada_drm_plane_cleanup_fb,
-	.atomic_check	= armada_drm_plane_atomic_check,
-	.atomic_update	= armada_drm_primary_plane_atomic_update,
-	.atomic_disable	= armada_drm_primary_plane_atomic_disable,
-};
-
-static const struct drm_plane_funcs armada_primary_plane_funcs = {
-	.update_plane	= drm_plane_helper_update,
-	.disable_plane	= drm_plane_helper_disable,
-	.destroy	= drm_primary_helper_destroy,
-	.reset		= drm_atomic_helper_plane_reset,
-	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
-	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
-};
-
-int armada_drm_plane_init(struct armada_plane *plane)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(plane->works); i++)
-		plane->works[i].plane = &plane->base;
-
-	init_waitqueue_head(&plane->frame_wait);
-
-	return 0;
-}
-
 static const struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = {
 	{ CSC_AUTO,        "Auto" },
 	{ CSC_YUV_CCIR601, "CCIR601" },
@@ -1363,21 +1108,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 		goto err_crtc;
 	}
 
-	ret = armada_drm_plane_init(primary);
-	if (ret) {
-		kfree(primary);
-		goto err_crtc;
-	}
-
-	drm_plane_helper_add(&primary->base,
-			     &armada_primary_plane_helper_funcs);
-
-	ret = drm_universal_plane_init(drm, &primary->base, 0,
-				       &armada_primary_plane_funcs,
-				       armada_primary_formats,
-				       ARRAY_SIZE(armada_primary_formats),
-				       NULL,
-				       DRM_PLANE_TYPE_PRIMARY, NULL);
+	ret = armada_drm_primary_plane_init(drm, primary);
 	if (ret) {
 		kfree(primary);
 		goto err_crtc;
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 79ac0db047c9..2672c5cc0e45 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -54,21 +54,11 @@ struct armada_plane {
 };
 #define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
 
-int armada_drm_plane_init(struct armada_plane *plane);
 int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
 	struct armada_plane_work *work);
 int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout);
 void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
 	struct armada_plane *plane);
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y);
-
-int armada_drm_plane_prepare_fb(struct drm_plane *plane,
-	struct drm_plane_state *state);
-void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
-	struct drm_plane_state *old_state);
-int armada_drm_plane_atomic_check(struct drm_plane *plane,
-	struct drm_plane_state *state);
 
 struct armada_crtc {
 	struct drm_crtc		crtc;
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index aa2a12aec3cc..214b2171a8f4 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -10,13 +10,14 @@
 #include <drm/drm_atomic.h>
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_plane_helper.h>
+#include <drm/armada_drm.h>
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_fb.h"
 #include "armada_gem.h"
 #include "armada_hw.h"
-#include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
+#include "armada_plane.h"
 #include "armada_trace.h"
 
 struct armada_ovl_plane_properties {
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
new file mode 100644
index 000000000000..9d1eec1dc720
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -0,0 +1,297 @@
+/*
+ * Copyright (C) 2012 Russell King
+ *  Rewritten from the dovefb driver, and Armada510 manuals.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <drm/drmP.h>
+#include <drm/drm_atomic.h>
+#include <drm/drm_atomic_helper.h>
+#include <drm/drm_plane_helper.h>
+#include "armada_crtc.h"
+#include "armada_drm.h"
+#include "armada_fb.h"
+#include "armada_gem.h"
+#include "armada_hw.h"
+#include "armada_plane.h"
+#include "armada_trace.h"
+
+static const uint32_t armada_primary_formats[] = {
+	DRM_FORMAT_UYVY,
+	DRM_FORMAT_YUYV,
+	DRM_FORMAT_VYUY,
+	DRM_FORMAT_YVYU,
+	DRM_FORMAT_ARGB8888,
+	DRM_FORMAT_ABGR8888,
+	DRM_FORMAT_XRGB8888,
+	DRM_FORMAT_XBGR8888,
+	DRM_FORMAT_RGB888,
+	DRM_FORMAT_BGR888,
+	DRM_FORMAT_ARGB1555,
+	DRM_FORMAT_ABGR1555,
+	DRM_FORMAT_RGB565,
+	DRM_FORMAT_BGR565,
+};
+
+void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
+	int x, int y)
+{
+	const struct drm_format_info *format = fb->format;
+	unsigned int num_planes = format->num_planes;
+	u32 addr = drm_fb_obj(fb)->dev_addr;
+	int i;
+
+	if (num_planes > 3)
+		num_planes = 3;
+
+	addrs[0] = addr + fb->offsets[0] + y * fb->pitches[0] +
+		   x * format->cpp[0];
+
+	y /= format->vsub;
+	x /= format->hsub;
+
+	for (i = 1; i < num_planes; i++)
+		addrs[i] = addr + fb->offsets[i] + y * fb->pitches[i] +
+			     x * format->cpp[i];
+	for (; i < 3; i++)
+		addrs[i] = 0;
+}
+
+static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb,
+	int x, int y, struct armada_regs *regs, bool interlaced)
+{
+	unsigned pitch = fb->pitches[0];
+	u32 addrs[3], addr_odd, addr_even;
+	unsigned i = 0;
+
+	DRM_DEBUG_DRIVER("pitch %u x %d y %d bpp %d\n",
+		pitch, x, y, fb->format->cpp[0] * 8);
+
+	armada_drm_plane_calc_addrs(addrs, fb, x, y);
+
+	addr_odd = addr_even = addrs[0];
+
+	if (interlaced) {
+		addr_even += pitch;
+		pitch *= 2;
+	}
+
+	/* write offset, base, and pitch */
+	armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0);
+	armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1);
+	armada_reg_queue_mod(regs, i, pitch, 0xffff, LCD_CFG_GRA_PITCH);
+
+	return i;
+}
+
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		state->fb ? state->fb->base.id : 0);
+
+	/*
+	 * Take a reference on the new framebuffer - we want to
+	 * hold on to it while the hardware is displaying it.
+	 */
+	if (state->fb)
+		drm_framebuffer_get(state->fb);
+	return 0;
+}
+
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	DRM_DEBUG_KMS("[PLANE:%d:%s] [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->fb ? old_state->fb->base.id : 0);
+
+	if (old_state->fb)
+		drm_framebuffer_put(old_state->fb);
+}
+
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	if (state->fb && !WARN_ON(!state->crtc)) {
+		struct drm_crtc *crtc = state->crtc;
+		struct drm_crtc_state *crtc_state;
+
+		if (state->state)
+			crtc_state = drm_atomic_get_existing_crtc_state(state->state, crtc);
+		else
+			crtc_state = crtc->state;
+		return drm_atomic_helper_check_plane_state(state, crtc_state,
+							   0, INT_MAX,
+							   true, false);
+	} else {
+		state->visible = false;
+	}
+	return 0;
+}
+
+static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct drm_plane_state *state = plane->state;
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	u32 cfg, cfg_mask, val;
+	unsigned int idx;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!state->fb || WARN_ON(!state->crtc))
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] is on [CRTC:%d:%s] with [FB:%d] visible %u->%u\n",
+		plane->base.id, plane->name,
+		state->crtc->base.id, state->crtc->name,
+		state->fb->base.id,
+		old_state->visible, state->visible);
+
+	dcrtc = drm_to_armada_crtc(state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	idx = 0;
+	if (!old_state->visible && state->visible) {
+		val = CFG_PDWN64x66;
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			val |= CFG_PDWN256x24;
+		armada_reg_queue_mod(regs, idx, 0, val, LCD_SPU_SRAM_PARA1);
+	}
+	val = armada_rect_hw_fp(&state->src);
+	if (armada_rect_hw_fp(&old_state->src) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_HPXL_VLN);
+	val = armada_rect_yx(&state->dst);
+	if (armada_rect_yx(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GRA_OVSA_HPXL_VLN);
+	val = armada_rect_hw(&state->dst);
+	if (armada_rect_hw(&old_state->dst) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_GZM_HPXL_VLN);
+	if (old_state->src.x1 != state->src.x1 ||
+	    old_state->src.y1 != state->src.y1 ||
+	    old_state->fb != state->fb) {
+		idx += armada_drm_crtc_calc_fb(state->fb,
+					       state->src.x1 >> 16,
+					       state->src.y1 >> 16,
+					       regs + idx,
+					       dcrtc->interlaced);
+	}
+	if (old_state->fb != state->fb) {
+		cfg = CFG_GRA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
+		      CFG_GRA_MOD(drm_fb_to_armada_fb(state->fb)->mod);
+		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
+			cfg |= CFG_PALETTE_ENA;
+		if (state->visible)
+			cfg |= CFG_GRA_ENA;
+		if (dcrtc->interlaced)
+			cfg |= CFG_GRA_FTOGGLE;
+		cfg_mask = CFG_GRAFORMAT |
+			   CFG_GRA_MOD(CFG_SWAPRB | CFG_SWAPUV |
+				       CFG_SWAPYU | CFG_YUV2RGB) |
+			   CFG_PALETTE_ENA | CFG_GRA_FTOGGLE |
+			   CFG_GRA_ENA;
+	} else if (old_state->visible != state->visible) {
+		cfg = state->visible ? CFG_GRA_ENA : 0;
+		cfg_mask = CFG_GRA_ENA;
+	} else {
+		cfg = cfg_mask = 0;
+	}
+	if (drm_rect_width(&old_state->src) != drm_rect_width(&state->src) ||
+	    drm_rect_width(&old_state->dst) != drm_rect_width(&state->dst)) {
+		cfg_mask |= CFG_GRA_HSMOOTH;
+		if (drm_rect_width(&state->src) >> 16 !=
+		    drm_rect_width(&state->dst))
+			cfg |= CFG_GRA_HSMOOTH;
+	}
+
+	if (cfg_mask)
+		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
+				     LCD_SPU_DMA_CTRL0);
+
+	dcrtc->regs_idx += idx;
+}
+
+static void armada_drm_primary_plane_atomic_disable(struct drm_plane *plane,
+	struct drm_plane_state *old_state)
+{
+	struct armada_crtc *dcrtc;
+	struct armada_regs *regs;
+	unsigned int idx = 0;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s]\n", plane->base.id, plane->name);
+
+	if (!old_state->crtc)
+		return;
+
+	DRM_DEBUG_KMS("[PLANE:%d:%s] was on [CRTC:%d:%s] with [FB:%d]\n",
+		plane->base.id, plane->name,
+		old_state->crtc->base.id, old_state->crtc->name,
+		old_state->fb->base.id);
+
+	dcrtc = drm_to_armada_crtc(old_state->crtc);
+	regs = dcrtc->regs + dcrtc->regs_idx;
+
+	/* Disable plane and power down most RAMs and FIFOs */
+	armada_reg_queue_mod(regs, idx, 0, CFG_GRA_ENA, LCD_SPU_DMA_CTRL0);
+	armada_reg_queue_mod(regs, idx, CFG_PDWN256x32 | CFG_PDWN256x24 |
+			     CFG_PDWN256x8 | CFG_PDWN32x32 | CFG_PDWN64x66,
+			     0, LCD_SPU_SRAM_PARA1);
+
+	dcrtc->regs_idx += idx;
+}
+
+static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
+	.prepare_fb	= armada_drm_plane_prepare_fb,
+	.cleanup_fb	= armada_drm_plane_cleanup_fb,
+	.atomic_check	= armada_drm_plane_atomic_check,
+	.atomic_update	= armada_drm_primary_plane_atomic_update,
+	.atomic_disable	= armada_drm_primary_plane_atomic_disable,
+};
+
+static const struct drm_plane_funcs armada_primary_plane_funcs = {
+	.update_plane	= drm_plane_helper_update,
+	.disable_plane	= drm_plane_helper_disable,
+	.destroy	= drm_primary_helper_destroy,
+	.reset		= drm_atomic_helper_plane_reset,
+	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+};
+
+int armada_drm_plane_init(struct armada_plane *plane)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(plane->works); i++)
+		plane->works[i].plane = &plane->base;
+
+	init_waitqueue_head(&plane->frame_wait);
+
+	return 0;
+}
+
+int armada_drm_primary_plane_init(struct drm_device *drm,
+	struct armada_plane *primary)
+{
+	int ret;
+
+	ret = armada_drm_plane_init(primary);
+	if (ret)
+		return ret;
+
+	drm_plane_helper_add(&primary->base,
+			     &armada_primary_plane_helper_funcs);
+
+	ret = drm_universal_plane_init(drm, &primary->base, 0,
+				       &armada_primary_plane_funcs,
+				       armada_primary_formats,
+				       ARRAY_SIZE(armada_primary_formats),
+				       NULL,
+				       DRM_PLANE_TYPE_PRIMARY, NULL);
+
+	return ret;
+}
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
new file mode 100644
index 000000000000..3c8316003907
--- /dev/null
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -0,0 +1,16 @@
+#ifndef ARMADA_PLANE_H
+#define ARMADA_PLANE_H
+
+void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
+	int x, int y);
+int armada_drm_plane_prepare_fb(struct drm_plane *plane,
+	struct drm_plane_state *state);
+void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
+	struct drm_plane_state *old_state);
+int armada_drm_plane_atomic_check(struct drm_plane *plane,
+	struct drm_plane_state *state);
+int armada_drm_plane_init(struct armada_plane *plane);
+int armada_drm_primary_plane_init(struct drm_device *drm,
+	struct armada_plane *primary);
+
+#endif
-- 
cgit v1.2.3


From 63b93c0834a0cb7d537b30f8e815a9f63d0da37f Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: move plane works to overlay

Only overlay makes use of these now, so move these to the overlay code.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.h    |  2 --
 drivers/gpu/drm/armada/armada_overlay.c | 12 ++++++++----
 drivers/gpu/drm/armada/armada_plane.c   |  6 ------
 3 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 2672c5cc0e45..73ddd7d61eb4 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -48,8 +48,6 @@ struct armada_plane_work {
 struct armada_plane {
 	struct drm_plane	base;
 	wait_queue_head_t	frame_wait;
-	bool			next_work;
-	struct armada_plane_work works[2];
 	struct armada_plane_work *work;
 };
 #define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index 214b2171a8f4..40868e485ae8 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -36,6 +36,8 @@ struct armada_ovl_plane_properties {
 
 struct armada_ovl_plane {
 	struct armada_plane base;
+	struct armada_plane_work works[2];
+	bool next_work;
 	bool wait_vblank;
 	struct armada_ovl_plane_properties prop;
 };
@@ -245,7 +247,7 @@ static int armada_overlay_commit(struct drm_plane *plane,
 	if (ret)
 		goto put_state;
 
-	work = &dplane->base.works[dplane->base.next_work];
+	work = &dplane->works[dplane->next_work];
 
 	if (plane->state->fb != state->fb) {
 		/*
@@ -295,7 +297,7 @@ static int armada_overlay_commit(struct drm_plane *plane,
 		ret = 0;
 	}
 
-	dplane->base.next_work = !dplane->base.next_work;
+	dplane->next_work = !dplane->next_work;
 
 put_state:
 	drm_atomic_helper_plane_destroy_state(plane, state);
@@ -515,8 +517,10 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 		return ret;
 	}
 
-	dplane->base.works[0].fn = armada_ovl_plane_work;
-	dplane->base.works[1].fn = armada_ovl_plane_work;
+	dplane->works[0].plane = &dplane->base.base;
+	dplane->works[0].fn = armada_ovl_plane_work;
+	dplane->works[1].plane = &dplane->base.base;
+	dplane->works[1].fn = armada_ovl_plane_work;
 
 	drm_plane_helper_add(&dplane->base.base,
 			     &armada_overlay_plane_helper_funcs);
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index 9d1eec1dc720..1cb6a605bda9 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -264,13 +264,7 @@ static const struct drm_plane_funcs armada_primary_plane_funcs = {
 
 int armada_drm_plane_init(struct armada_plane *plane)
 {
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(plane->works); i++)
-		plane->works[i].plane = &plane->base;
-
 	init_waitqueue_head(&plane->frame_wait);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 61ba252705a6d5b8dd71bd2ccc544d33cb2af623 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: move CBSH properties into overlay plane state

Move the contrast, brightness, and saturation properties to the overlay
plane state structure, and call our overlay commit function to update
the hardware via the planes atomic_update() method.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.h    |   2 +-
 drivers/gpu/drm/armada/armada_overlay.c | 163 ++++++++++++++++++++++++++------
 2 files changed, 136 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 73ddd7d61eb4..c27435a8776a 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -42,7 +42,7 @@ struct armada_plane_work {
 	struct drm_plane *plane;
 	struct drm_framebuffer *old_fb;
 	struct drm_pending_vblank_event *event;
-	struct armada_regs regs[14];
+	struct armada_regs regs[24];
 };
 
 struct armada_plane {
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index 40868e485ae8..ec3ce28f162e 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -20,6 +20,10 @@
 #include "armada_plane.h"
 #include "armada_trace.h"
 
+#define DEFAULT_BRIGHTNESS	0
+#define DEFAULT_CONTRAST	0x4000
+#define DEFAULT_SATURATION	0x4000
+
 struct armada_ovl_plane_properties {
 	uint32_t colorkey_yr;
 	uint32_t colorkey_ug;
@@ -27,9 +31,6 @@ struct armada_ovl_plane_properties {
 #define K2R(val) (((val) >> 0) & 0xff)
 #define K2G(val) (((val) >> 8) & 0xff)
 #define K2B(val) (((val) >> 16) & 0xff)
-	int16_t  brightness;
-	uint16_t contrast;
-	uint16_t saturation;
 	uint32_t colorkey_mode;
 	uint32_t colorkey_enable;
 };
@@ -44,6 +45,26 @@ struct armada_ovl_plane {
 #define drm_to_armada_ovl_plane(p) \
 	container_of(p, struct armada_ovl_plane, base.base)
 
+struct armada_overlay_state {
+	struct drm_plane_state base;
+	s16 brightness;
+	u16 contrast;
+	u16 saturation;
+};
+#define drm_to_overlay_state(s) \
+	container_of(s, struct armada_overlay_state, base)
+
+static inline u32 armada_spu_contrast(struct drm_plane_state *state)
+{
+	return drm_to_overlay_state(state)->brightness << 16 |
+	       drm_to_overlay_state(state)->contrast;
+}
+
+static inline u32 armada_spu_saturation(struct drm_plane_state *state)
+{
+	/* Docs say 15:0, but it seems to actually be 31:16 on Armada 510 */
+	return drm_to_overlay_state(state)->saturation << 16;
+}
 
 static void
 armada_ovl_update_attr(struct armada_ovl_plane_properties *prop,
@@ -53,13 +74,6 @@ armada_ovl_update_attr(struct armada_ovl_plane_properties *prop,
 	writel_relaxed(prop->colorkey_ug, dcrtc->base + LCD_SPU_COLORKEY_U);
 	writel_relaxed(prop->colorkey_vb, dcrtc->base + LCD_SPU_COLORKEY_V);
 
-	writel_relaxed(prop->brightness << 16 | prop->contrast,
-		       dcrtc->base + LCD_SPU_CONTRAST);
-	/* Docs say 15:0, but it seems to actually be 31:16 on Armada 510 */
-	writel_relaxed(prop->saturation << 16,
-		       dcrtc->base + LCD_SPU_SATURATION);
-	writel_relaxed(0x00002000, dcrtc->base + LCD_SPU_CBSH_HUE);
-
 	spin_lock_irq(&dcrtc->irq_lock);
 	armada_updatel(prop->colorkey_mode,
 		       CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
@@ -191,6 +205,17 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 		armada_reg_queue_mod(regs, idx, cfg, cfg_mask,
 				     LCD_SPU_DMA_CTRL0);
 
+	val = armada_spu_contrast(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_spu_contrast(old_state) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_CONTRAST);
+	val = armada_spu_saturation(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_spu_saturation(old_state) != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_SATURATION);
+	if (!old_state->visible && state->visible)
+		armada_reg_queue_set(regs, idx, 0x00002000, LCD_SPU_CBSH_HUE);
+
 	dcrtc->regs_idx += idx;
 }
 
@@ -264,6 +289,10 @@ static int armada_overlay_commit(struct drm_plane *plane,
 	/* Point of no return */
 	swap(plane->state, state);
 
+	/* No CRTC, can't update */
+	if (!plane->state->crtc)
+		goto put_state;
+
 	dcrtc->regs_idx = 0;
 	dcrtc->regs = work->regs;
 
@@ -300,7 +329,7 @@ static int armada_overlay_commit(struct drm_plane *plane,
 	dplane->next_work = !dplane->next_work;
 
 put_state:
-	drm_atomic_helper_plane_destroy_state(plane, state);
+	plane->funcs->atomic_destroy_state(plane, state);
 	return ret;
 }
 
@@ -318,7 +347,7 @@ armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 				 src_x, src_y, src_w, src_h);
 
 	/* Construct new state for the overlay plane */
-	state = drm_atomic_helper_plane_duplicate_state(plane);
+	state = plane->funcs->atomic_duplicate_state(plane);
 	if (!state)
 		return -ENOMEM;
 
@@ -404,15 +433,22 @@ static int armada_ovl_plane_set_property(struct drm_plane *plane,
 			dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
 		}
 		update_attr = true;
-	} else if (property == priv->brightness_prop) {
-		dplane->prop.brightness = val - 256;
-		update_attr = true;
-	} else if (property == priv->contrast_prop) {
-		dplane->prop.contrast = val;
-		update_attr = true;
-	} else if (property == priv->saturation_prop) {
-		dplane->prop.saturation = val;
-		update_attr = true;
+	} else {
+		struct drm_plane_state *state;
+		int ret;
+
+		state = plane->funcs->atomic_duplicate_state(plane);
+		if (!state)
+			return -ENOMEM;
+
+		ret = plane->funcs->atomic_set_property(plane, state, property,
+							val);
+		if (ret) {
+			plane->funcs->atomic_destroy_state(plane, state);
+			return ret;
+		}
+
+		return armada_overlay_commit(plane, state);
 	}
 
 	if (update_attr && dplane->base.base.crtc)
@@ -422,12 +458,85 @@ static int armada_ovl_plane_set_property(struct drm_plane *plane,
 	return 0;
 }
 
+static void armada_overlay_reset(struct drm_plane *plane)
+{
+	struct armada_overlay_state *state;
+
+	if (plane->state)
+		__drm_atomic_helper_plane_destroy_state(plane->state);
+	kfree(plane->state);
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (state) {
+		state->base.plane = plane;
+		state->base.rotation = DRM_MODE_ROTATE_0;
+		state->brightness = DEFAULT_BRIGHTNESS;
+		state->contrast = DEFAULT_CONTRAST;
+		state->saturation = DEFAULT_SATURATION;
+	}
+	plane->state = &state->base;
+}
+
+struct drm_plane_state *
+armada_overlay_duplicate_state(struct drm_plane *plane)
+{
+	struct armada_overlay_state *state;
+
+	if (WARN_ON(!plane->state))
+		return NULL;
+
+	state = kmemdup(plane->state, sizeof(*state), GFP_KERNEL);
+	if (state)
+		__drm_atomic_helper_plane_duplicate_state(plane, &state->base);
+	return &state->base;
+}
+
+static int armada_overlay_set_property(struct drm_plane *plane,
+	struct drm_plane_state *state, struct drm_property *property,
+	uint64_t val)
+{
+	struct armada_private *priv = plane->dev->dev_private;
+
+	if (property == priv->brightness_prop) {
+		drm_to_overlay_state(state)->brightness = val - 256;
+	} else if (property == priv->contrast_prop) {
+		drm_to_overlay_state(state)->contrast = val;
+	} else if (property == priv->saturation_prop) {
+		drm_to_overlay_state(state)->saturation = val;
+	} else {
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int armada_overlay_get_property(struct drm_plane *plane,
+	const struct drm_plane_state *state, struct drm_property *property,
+	uint64_t *val)
+{
+	struct armada_private *priv = plane->dev->dev_private;
+
+	if (property == priv->brightness_prop) {
+		*val = drm_to_overlay_state(state)->brightness + 256;
+	} else if (property == priv->contrast_prop) {
+		*val = drm_to_overlay_state(state)->contrast;
+	} else if (property == priv->saturation_prop) {
+		*val = drm_to_overlay_state(state)->saturation;
+	} else {
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static const struct drm_plane_funcs armada_ovl_plane_funcs = {
 	.update_plane	= armada_ovl_plane_update,
 	.disable_plane	= drm_plane_helper_disable,
 	.destroy	= armada_ovl_plane_destroy,
 	.set_property	= armada_ovl_plane_set_property,
-	.reset		= drm_atomic_helper_plane_reset,
+	.reset		= armada_overlay_reset,
+	.atomic_duplicate_state = armada_overlay_duplicate_state,
+	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
+	.atomic_set_property = armada_overlay_set_property,
+	.atomic_get_property = armada_overlay_get_property,
 };
 
 static const uint32_t armada_ovl_formats[] = {
@@ -542,9 +651,6 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 	dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
 				     CFG_ALPHAM_GRA | CFG_ALPHA(0);
 	dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
-	dplane->prop.brightness = 0;
-	dplane->prop.contrast = 0x4000;
-	dplane->prop.saturation = 0x4000;
 
 	mobj = &dplane->base.base.base;
 	drm_object_attach_property(mobj, priv->colorkey_prop,
@@ -559,11 +665,12 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 				   0x000000);
 	drm_object_attach_property(mobj, priv->colorkey_mode_prop,
 				   CKMODE_RGB);
-	drm_object_attach_property(mobj, priv->brightness_prop, 256);
+	drm_object_attach_property(mobj, priv->brightness_prop,
+				   256 + DEFAULT_BRIGHTNESS);
 	drm_object_attach_property(mobj, priv->contrast_prop,
-				   dplane->prop.contrast);
+				   DEFAULT_CONTRAST);
 	drm_object_attach_property(mobj, priv->saturation_prop,
-				   dplane->prop.saturation);
+				   DEFAULT_SATURATION);
 
 	return 0;
 }
-- 
cgit v1.2.3


From c96103b6c49ff9a8710e580da72c0f116d24a76c Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: move colorkey properties into overlay plane state

Move the overlay plane colorkey properties into the plane state,
keeping the existing driver behaviour to avoid breaking userspace.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_overlay.c | 251 +++++++++++++++++---------------
 1 file changed, 132 insertions(+), 119 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index ec3ce28f162e..7f75df4f8390 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -24,29 +24,22 @@
 #define DEFAULT_CONTRAST	0x4000
 #define DEFAULT_SATURATION	0x4000
 
-struct armada_ovl_plane_properties {
-	uint32_t colorkey_yr;
-	uint32_t colorkey_ug;
-	uint32_t colorkey_vb;
-#define K2R(val) (((val) >> 0) & 0xff)
-#define K2G(val) (((val) >> 8) & 0xff)
-#define K2B(val) (((val) >> 16) & 0xff)
-	uint32_t colorkey_mode;
-	uint32_t colorkey_enable;
-};
-
 struct armada_ovl_plane {
 	struct armada_plane base;
 	struct armada_plane_work works[2];
 	bool next_work;
 	bool wait_vblank;
-	struct armada_ovl_plane_properties prop;
 };
 #define drm_to_armada_ovl_plane(p) \
 	container_of(p, struct armada_ovl_plane, base.base)
 
 struct armada_overlay_state {
 	struct drm_plane_state base;
+	u32 colorkey_yr;
+	u32 colorkey_ug;
+	u32 colorkey_vb;
+	u32 colorkey_mode;
+	u32 colorkey_enable;
 	s16 brightness;
 	u16 contrast;
 	u16 saturation;
@@ -66,25 +59,6 @@ static inline u32 armada_spu_saturation(struct drm_plane_state *state)
 	return drm_to_overlay_state(state)->saturation << 16;
 }
 
-static void
-armada_ovl_update_attr(struct armada_ovl_plane_properties *prop,
-	struct armada_crtc *dcrtc)
-{
-	writel_relaxed(prop->colorkey_yr, dcrtc->base + LCD_SPU_COLORKEY_Y);
-	writel_relaxed(prop->colorkey_ug, dcrtc->base + LCD_SPU_COLORKEY_U);
-	writel_relaxed(prop->colorkey_vb, dcrtc->base + LCD_SPU_COLORKEY_V);
-
-	spin_lock_irq(&dcrtc->irq_lock);
-	armada_updatel(prop->colorkey_mode,
-		       CFG_CKMODE_MASK | CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
-		       dcrtc->base + LCD_SPU_DMA_CTRL1);
-	if (dcrtc->variant->has_spu_adv_reg)
-		armada_updatel(prop->colorkey_enable,
-			       ADV_GRACOLORKEY | ADV_VIDCOLORKEY,
-			       dcrtc->base + LCD_SPU_ADV_REG);
-	spin_unlock_irq(&dcrtc->irq_lock);
-}
-
 /* === Plane support === */
 static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
 	struct armada_plane_work *work)
@@ -215,6 +189,30 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 		armada_reg_queue_set(regs, idx, val, LCD_SPU_SATURATION);
 	if (!old_state->visible && state->visible)
 		armada_reg_queue_set(regs, idx, 0x00002000, LCD_SPU_CBSH_HUE);
+	val = drm_to_overlay_state(state)->colorkey_yr;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_yr != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_Y);
+	val = drm_to_overlay_state(state)->colorkey_ug;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_ug != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_U);
+	val = drm_to_overlay_state(state)->colorkey_vb;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_vb != val)
+		armada_reg_queue_set(regs, idx, val, LCD_SPU_COLORKEY_V);
+	val = drm_to_overlay_state(state)->colorkey_mode;
+	if ((!old_state->visible && state->visible) ||
+	    drm_to_overlay_state(old_state)->colorkey_mode != val)
+		armada_reg_queue_mod(regs, idx, val, CFG_CKMODE_MASK |
+				     CFG_ALPHAM_MASK | CFG_ALPHA_MASK,
+				     LCD_SPU_DMA_CTRL1);
+	val = drm_to_overlay_state(state)->colorkey_enable;
+	if (((!old_state->visible && state->visible) ||
+	     drm_to_overlay_state(old_state)->colorkey_enable != val) &&
+	    dcrtc->variant->has_spu_adv_reg)
+		armada_reg_queue_mod(regs, idx, val, ADV_GRACOLORKEY |
+				     ADV_VIDCOLORKEY, LCD_SPU_ADV_REG);
 
 	dcrtc->regs_idx += idx;
 }
@@ -314,10 +312,7 @@ static int armada_overlay_commit(struct drm_plane *plane,
 		goto put_state;
 	}
 
-	if (!dcrtc->plane) {
-		dcrtc->plane = plane;
-		armada_ovl_update_attr(&dplane->prop, dcrtc);
-	}
+	dcrtc->plane = plane;
 
 	/* Queue it for update on the next interrupt if we are enabled */
 	ret = armada_drm_plane_work_queue(dcrtc, work);
@@ -377,85 +372,20 @@ static void armada_ovl_plane_destroy(struct drm_plane *plane)
 static int armada_ovl_plane_set_property(struct drm_plane *plane,
 	struct drm_property *property, uint64_t val)
 {
-	struct armada_private *priv = plane->dev->dev_private;
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-	bool update_attr = false;
+	struct drm_plane_state *state;
+	int ret;
 
-	if (property == priv->colorkey_prop) {
-#define CCC(v) ((v) << 24 | (v) << 16 | (v) << 8)
-		dplane->prop.colorkey_yr = CCC(K2R(val));
-		dplane->prop.colorkey_ug = CCC(K2G(val));
-		dplane->prop.colorkey_vb = CCC(K2B(val));
-#undef CCC
-		update_attr = true;
-	} else if (property == priv->colorkey_min_prop) {
-		dplane->prop.colorkey_yr &= ~0x00ff0000;
-		dplane->prop.colorkey_yr |= K2R(val) << 16;
-		dplane->prop.colorkey_ug &= ~0x00ff0000;
-		dplane->prop.colorkey_ug |= K2G(val) << 16;
-		dplane->prop.colorkey_vb &= ~0x00ff0000;
-		dplane->prop.colorkey_vb |= K2B(val) << 16;
-		update_attr = true;
-	} else if (property == priv->colorkey_max_prop) {
-		dplane->prop.colorkey_yr &= ~0xff000000;
-		dplane->prop.colorkey_yr |= K2R(val) << 24;
-		dplane->prop.colorkey_ug &= ~0xff000000;
-		dplane->prop.colorkey_ug |= K2G(val) << 24;
-		dplane->prop.colorkey_vb &= ~0xff000000;
-		dplane->prop.colorkey_vb |= K2B(val) << 24;
-		update_attr = true;
-	} else if (property == priv->colorkey_val_prop) {
-		dplane->prop.colorkey_yr &= ~0x0000ff00;
-		dplane->prop.colorkey_yr |= K2R(val) << 8;
-		dplane->prop.colorkey_ug &= ~0x0000ff00;
-		dplane->prop.colorkey_ug |= K2G(val) << 8;
-		dplane->prop.colorkey_vb &= ~0x0000ff00;
-		dplane->prop.colorkey_vb |= K2B(val) << 8;
-		update_attr = true;
-	} else if (property == priv->colorkey_alpha_prop) {
-		dplane->prop.colorkey_yr &= ~0x000000ff;
-		dplane->prop.colorkey_yr |= K2R(val);
-		dplane->prop.colorkey_ug &= ~0x000000ff;
-		dplane->prop.colorkey_ug |= K2G(val);
-		dplane->prop.colorkey_vb &= ~0x000000ff;
-		dplane->prop.colorkey_vb |= K2B(val);
-		update_attr = true;
-	} else if (property == priv->colorkey_mode_prop) {
-		if (val == CKMODE_DISABLE) {
-			dplane->prop.colorkey_mode =
-				CFG_CKMODE(CKMODE_DISABLE) |
-				CFG_ALPHAM_CFG | CFG_ALPHA(255);
-			dplane->prop.colorkey_enable = 0;
-		} else {
-			dplane->prop.colorkey_mode =
-				CFG_CKMODE(val) |
-				CFG_ALPHAM_GRA | CFG_ALPHA(0);
-			dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
-		}
-		update_attr = true;
-	} else {
-		struct drm_plane_state *state;
-		int ret;
-
-		state = plane->funcs->atomic_duplicate_state(plane);
-		if (!state)
-			return -ENOMEM;
-
-		ret = plane->funcs->atomic_set_property(plane, state, property,
-							val);
-		if (ret) {
-			plane->funcs->atomic_destroy_state(plane, state);
-			return ret;
-		}
+	state = plane->funcs->atomic_duplicate_state(plane);
+	if (!state)
+		return -ENOMEM;
 
-		return armada_overlay_commit(plane, state);
+	ret = plane->funcs->atomic_set_property(plane, state, property, val);
+	if (ret) {
+		plane->funcs->atomic_destroy_state(plane, state);
+		return ret;
 	}
 
-	if (update_attr && dplane->base.base.crtc)
-		armada_ovl_update_attr(&dplane->prop,
-				       drm_to_armada_crtc(dplane->base.base.crtc));
-
-	return 0;
+	return armada_overlay_commit(plane, state);
 }
 
 static void armada_overlay_reset(struct drm_plane *plane)
@@ -470,6 +400,12 @@ static void armada_overlay_reset(struct drm_plane *plane)
 	if (state) {
 		state->base.plane = plane;
 		state->base.rotation = DRM_MODE_ROTATE_0;
+		state->colorkey_yr = 0xfefefe00;
+		state->colorkey_ug = 0x01010100;
+		state->colorkey_vb = 0x01010100;
+		state->colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
+				       CFG_ALPHAM_GRA | CFG_ALPHA(0);
+		state->colorkey_enable = ADV_GRACOLORKEY;
 		state->brightness = DEFAULT_BRIGHTNESS;
 		state->contrast = DEFAULT_CONTRAST;
 		state->saturation = DEFAULT_SATURATION;
@@ -497,7 +433,57 @@ static int armada_overlay_set_property(struct drm_plane *plane,
 {
 	struct armada_private *priv = plane->dev->dev_private;
 
-	if (property == priv->brightness_prop) {
+#define K2R(val) (((val) >> 0) & 0xff)
+#define K2G(val) (((val) >> 8) & 0xff)
+#define K2B(val) (((val) >> 16) & 0xff)
+	if (property == priv->colorkey_prop) {
+#define CCC(v) ((v) << 24 | (v) << 16 | (v) << 8)
+		drm_to_overlay_state(state)->colorkey_yr = CCC(K2R(val));
+		drm_to_overlay_state(state)->colorkey_ug = CCC(K2G(val));
+		drm_to_overlay_state(state)->colorkey_vb = CCC(K2B(val));
+#undef CCC
+	} else if (property == priv->colorkey_min_prop) {
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 16;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 16;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x00ff0000;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 16;
+	} else if (property == priv->colorkey_max_prop) {
+		drm_to_overlay_state(state)->colorkey_yr &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 24;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 24;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0xff000000;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 24;
+	} else if (property == priv->colorkey_val_prop) {
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val) << 8;
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val) << 8;
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x0000ff00;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val) << 8;
+	} else if (property == priv->colorkey_alpha_prop) {
+		drm_to_overlay_state(state)->colorkey_yr &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_yr |= K2R(val);
+		drm_to_overlay_state(state)->colorkey_ug &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_ug |= K2G(val);
+		drm_to_overlay_state(state)->colorkey_vb &= ~0x000000ff;
+		drm_to_overlay_state(state)->colorkey_vb |= K2B(val);
+	} else if (property == priv->colorkey_mode_prop) {
+		if (val == CKMODE_DISABLE) {
+			drm_to_overlay_state(state)->colorkey_mode =
+				CFG_CKMODE(CKMODE_DISABLE) |
+				CFG_ALPHAM_CFG | CFG_ALPHA(255);
+			drm_to_overlay_state(state)->colorkey_enable = 0;
+		} else {
+			drm_to_overlay_state(state)->colorkey_mode =
+				CFG_CKMODE(val) |
+				CFG_ALPHAM_GRA | CFG_ALPHA(0);
+			drm_to_overlay_state(state)->colorkey_enable =
+				ADV_GRACOLORKEY;
+		}
+	} else if (property == priv->brightness_prop) {
 		drm_to_overlay_state(state)->brightness = val - 256;
 	} else if (property == priv->contrast_prop) {
 		drm_to_overlay_state(state)->contrast = val;
@@ -515,7 +501,41 @@ static int armada_overlay_get_property(struct drm_plane *plane,
 {
 	struct armada_private *priv = plane->dev->dev_private;
 
-	if (property == priv->brightness_prop) {
+#define C2K(c,s)	(((c) >> (s)) & 0xff)
+#define R2BGR(r,g,b,s)	(C2K(r,s) << 0 | C2K(g,s) << 8 | C2K(b,s) << 16)
+	if (property == priv->colorkey_prop) {
+		/* Do best-efforts here for this property */
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 16);
+		/* If min != max, or min != val, error out */
+		if (*val != R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+				  drm_to_overlay_state(state)->colorkey_ug,
+				  drm_to_overlay_state(state)->colorkey_vb, 24) ||
+		    *val != R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+				  drm_to_overlay_state(state)->colorkey_ug,
+				  drm_to_overlay_state(state)->colorkey_vb, 8))
+			return -EINVAL;
+	} else if (property == priv->colorkey_min_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 16);
+	} else if (property == priv->colorkey_max_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 24);
+	} else if (property == priv->colorkey_val_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 8);
+	} else if (property == priv->colorkey_alpha_prop) {
+		*val = R2BGR(drm_to_overlay_state(state)->colorkey_yr,
+			     drm_to_overlay_state(state)->colorkey_ug,
+			     drm_to_overlay_state(state)->colorkey_vb, 0);
+	} else if (property == priv->colorkey_mode_prop) {
+		*val = (drm_to_overlay_state(state)->colorkey_mode &
+			CFG_CKMODE_MASK) >> ffs(CFG_CKMODE_MASK);
+	} else if (property == priv->brightness_prop) {
 		*val = drm_to_overlay_state(state)->brightness + 256;
 	} else if (property == priv->contrast_prop) {
 		*val = drm_to_overlay_state(state)->contrast;
@@ -645,13 +665,6 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 		return ret;
 	}
 
-	dplane->prop.colorkey_yr = 0xfefefe00;
-	dplane->prop.colorkey_ug = 0x01010100;
-	dplane->prop.colorkey_vb = 0x01010100;
-	dplane->prop.colorkey_mode = CFG_CKMODE(CKMODE_RGB) |
-				     CFG_ALPHAM_GRA | CFG_ALPHA(0);
-	dplane->prop.colorkey_enable = ADV_GRACOLORKEY;
-
 	mobj = &dplane->base.base.base;
 	drm_object_attach_property(mobj, priv->colorkey_prop,
 				   0x0101fe);
-- 
cgit v1.2.3


From 240cf2b58eb0bdd3c59387ca0cfbd5657708b996 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: remove crtc YUV colourspace properties

Remove the unused CRTC colourspace properties - userspace does not make
use of these.  In any case, these are not a property of the CRTC, since
they demonstrably only affect the video (overlay) plane, irrespective
of the format of the graphics (primary) plane.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 118 -----------------------------------
 drivers/gpu/drm/armada/armada_crtc.h |   2 -
 drivers/gpu/drm/armada/armada_drm.h  |   2 -
 3 files changed, 122 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index b9b0a508793d..35b2df0fc21c 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -23,14 +23,6 @@
 #include "armada_plane.h"
 #include "armada_trace.h"
 
-enum csc_mode {
-	CSC_AUTO = 0,
-	CSC_YUV_CCIR601 = 1,
-	CSC_YUV_CCIR709 = 2,
-	CSC_RGB_COMPUTER = 1,
-	CSC_RGB_STUDIO = 2,
-};
-
 /*
  * A note about interlacing.  Let's consider HDMI 1920x1080i.
  * The timing parameters we have from X are:
@@ -438,42 +430,6 @@ static irqreturn_t armada_drm_irq(int irq, void *arg)
 	return IRQ_NONE;
 }
 
-static uint32_t armada_drm_crtc_calculate_csc(struct armada_crtc *dcrtc)
-{
-	struct drm_display_mode *adj = &dcrtc->crtc.mode;
-	uint32_t val = 0;
-
-	if (dcrtc->csc_yuv_mode == CSC_YUV_CCIR709)
-		val |= CFG_CSC_YUV_CCIR709;
-	if (dcrtc->csc_rgb_mode == CSC_RGB_STUDIO)
-		val |= CFG_CSC_RGB_STUDIO;
-
-	/*
-	 * In auto mode, set the colorimetry, based upon the HDMI spec.
-	 * 1280x720p, 1920x1080p and 1920x1080i use ITU709, others use
-	 * ITU601.  It may be more appropriate to set this depending on
-	 * the source - but what if the graphic frame is YUV and the
-	 * video frame is RGB?
-	 */
-	if ((adj->hdisplay == 1280 && adj->vdisplay == 720 &&
-	     !(adj->flags & DRM_MODE_FLAG_INTERLACE)) ||
-	    (adj->hdisplay == 1920 && adj->vdisplay == 1080)) {
-		if (dcrtc->csc_yuv_mode == CSC_AUTO)
-			val |= CFG_CSC_YUV_CCIR709;
-	}
-
-	/*
-	 * We assume we're connected to a TV-like device, so the YUV->RGB
-	 * conversion should produce a limited range.  We should set this
-	 * depending on the connectors attached to this CRTC, and what
-	 * kind of device they report being connected.
-	 */
-	if (dcrtc->csc_rgb_mode == CSC_AUTO)
-		val |= CFG_CSC_RGB_STUDIO;
-
-	return val;
-}
-
 /* The mode_config.mutex will be held for this call */
 static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 {
@@ -560,9 +516,6 @@ static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 
 	val = adj->flags & DRM_MODE_FLAG_NVSYNC ? CFG_VSYNC_INV : 0;
 	armada_reg_queue_mod(regs, i, val, CFG_VSYNC_INV, LCD_SPU_DMA_CTRL1);
-
-	val = dcrtc->spu_iopad_ctrl | armada_drm_crtc_calculate_csc(dcrtc);
-	armada_reg_queue_set(regs, i, val, LCD_SPU_IOPAD_CONTROL);
 	armada_reg_queue_end(regs, i);
 
 	armada_drm_crtc_update_regs(dcrtc, regs);
@@ -937,33 +890,6 @@ put_state:
 	return ret;
 }
 
-static int
-armada_drm_crtc_set_property(struct drm_crtc *crtc,
-	struct drm_property *property, uint64_t val)
-{
-	struct armada_private *priv = crtc->dev->dev_private;
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	bool update_csc = false;
-
-	if (property == priv->csc_yuv_prop) {
-		dcrtc->csc_yuv_mode = val;
-		update_csc = true;
-	} else if (property == priv->csc_rgb_prop) {
-		dcrtc->csc_rgb_mode = val;
-		update_csc = true;
-	}
-
-	if (update_csc) {
-		uint32_t val;
-
-		val = dcrtc->spu_iopad_ctrl |
-		      armada_drm_crtc_calculate_csc(dcrtc);
-		writel_relaxed(val, dcrtc->base + LCD_SPU_IOPAD_CONTROL);
-	}
-
-	return 0;
-}
-
 /* These are called under the vbl_lock. */
 static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc)
 {
@@ -993,45 +919,12 @@ static const struct drm_crtc_funcs armada_crtc_funcs = {
 	.destroy	= armada_drm_crtc_destroy,
 	.set_config	= drm_crtc_helper_set_config,
 	.page_flip	= armada_drm_crtc_page_flip,
-	.set_property	= armada_drm_crtc_set_property,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
 	.enable_vblank	= armada_drm_crtc_enable_vblank,
 	.disable_vblank	= armada_drm_crtc_disable_vblank,
 };
 
-static const struct drm_prop_enum_list armada_drm_csc_yuv_enum_list[] = {
-	{ CSC_AUTO,        "Auto" },
-	{ CSC_YUV_CCIR601, "CCIR601" },
-	{ CSC_YUV_CCIR709, "CCIR709" },
-};
-
-static const struct drm_prop_enum_list armada_drm_csc_rgb_enum_list[] = {
-	{ CSC_AUTO,         "Auto" },
-	{ CSC_RGB_COMPUTER, "Computer system" },
-	{ CSC_RGB_STUDIO,   "Studio" },
-};
-
-static int armada_drm_crtc_create_properties(struct drm_device *dev)
-{
-	struct armada_private *priv = dev->dev_private;
-
-	if (priv->csc_yuv_prop)
-		return 0;
-
-	priv->csc_yuv_prop = drm_property_create_enum(dev, 0,
-				"CSC_YUV", armada_drm_csc_yuv_enum_list,
-				ARRAY_SIZE(armada_drm_csc_yuv_enum_list));
-	priv->csc_rgb_prop = drm_property_create_enum(dev, 0,
-				"CSC_RGB", armada_drm_csc_rgb_enum_list,
-				ARRAY_SIZE(armada_drm_csc_rgb_enum_list));
-
-	if (!priv->csc_yuv_prop || !priv->csc_rgb_prop)
-		return -ENOMEM;
-
-	return 0;
-}
-
 static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	struct resource *res, int irq, const struct armada_variant *variant,
 	struct device_node *port)
@@ -1042,10 +935,6 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	void __iomem *base;
 	int ret;
 
-	ret = armada_drm_crtc_create_properties(drm);
-	if (ret)
-		return ret;
-
 	base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(base))
 		return PTR_ERR(base);
@@ -1063,8 +952,6 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	dcrtc->base = base;
 	dcrtc->num = drm->mode_config.num_crtc;
 	dcrtc->clk = ERR_PTR(-EINVAL);
-	dcrtc->csc_yuv_mode = CSC_AUTO;
-	dcrtc->csc_rgb_mode = CSC_AUTO;
 	dcrtc->cfg_dumb_ctrl = DUMB24_RGB888_0;
 	dcrtc->spu_iopad_ctrl = CFG_VSCALE_LN_EN | CFG_IOPAD_DUMB24;
 	spin_lock_init(&dcrtc->irq_lock);
@@ -1121,11 +1008,6 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 
 	drm_crtc_helper_add(&dcrtc->crtc, &armada_crtc_helper_funcs);
 
-	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_yuv_prop,
-				   dcrtc->csc_yuv_mode);
-	drm_object_attach_property(&dcrtc->crtc.base, priv->csc_rgb_prop,
-				   dcrtc->csc_rgb_mode);
-
 	return armada_overlay_plane_create(drm, 1 << dcrtc->num);
 
 err_crtc_init:
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index c27435a8776a..21338f7c3d7d 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -72,8 +72,6 @@ struct armada_crtc {
 	} v[2];
 	bool			interlaced;
 	bool			cursor_update;
-	uint8_t			csc_yuv_mode;
-	uint8_t			csc_rgb_mode;
 
 	struct drm_plane	*plane;
 
diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index cc4c557c9f66..28087e4b9b81 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -60,8 +60,6 @@ struct armada_private {
 	struct armada_crtc	*dcrtc[2];
 	struct drm_mm		linear; /* protected by linear_lock */
 	struct mutex		linear_lock;
-	struct drm_property	*csc_yuv_prop;
-	struct drm_property	*csc_rgb_prop;
 	struct drm_property	*colorkey_prop;
 	struct drm_property	*colorkey_min_prop;
 	struct drm_property	*colorkey_max_prop;
-- 
cgit v1.2.3


From c29277d4e56388e805acc3ba428c9cff7df99fa7 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: add plane colorspace properties

Use the DRM standard plane properties for specifying the YUV
colour encoding parameter.  Our colour range is fixed at limited
range.

Since we are transitioning to atomic modeset, we need to explicitly
add handling of these properties to our atomic_set_property() method,
but once the transition is complete, these will be removed.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_overlay.c | 33 ++++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index 7f75df4f8390..bc1b5b860141 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -23,6 +23,7 @@
 #define DEFAULT_BRIGHTNESS	0
 #define DEFAULT_CONTRAST	0x4000
 #define DEFAULT_SATURATION	0x4000
+#define DEFAULT_ENCODING	DRM_COLOR_YCBCR_BT601
 
 struct armada_ovl_plane {
 	struct armada_plane base;
@@ -59,6 +60,19 @@ static inline u32 armada_spu_saturation(struct drm_plane_state *state)
 	return drm_to_overlay_state(state)->saturation << 16;
 }
 
+static inline u32 armada_csc(struct drm_plane_state *state)
+{
+	/*
+	 * The CFG_CSC_RGB_* settings control the output of the colour space
+	 * converter, setting the range of output values it produces.  Since
+	 * we will be blending with the full-range graphics, we need to
+	 * produce full-range RGB output from the conversion.
+	 */
+	return CFG_CSC_RGB_COMPUTER |
+	       (state->color_encoding == DRM_COLOR_YCBCR_BT709 ?
+			CFG_CSC_YUV_CCIR709 : CFG_CSC_YUV_CCIR601);
+}
+
 /* === Plane support === */
 static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
 	struct armada_plane_work *work)
@@ -189,6 +203,11 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 		armada_reg_queue_set(regs, idx, val, LCD_SPU_SATURATION);
 	if (!old_state->visible && state->visible)
 		armada_reg_queue_set(regs, idx, 0x00002000, LCD_SPU_CBSH_HUE);
+	val = armada_csc(state);
+	if ((!old_state->visible && state->visible) ||
+	    armada_csc(old_state) != val)
+		armada_reg_queue_mod(regs, idx, val, CFG_CSC_MASK,
+				     LCD_SPU_IOPAD_CONTROL);
 	val = drm_to_overlay_state(state)->colorkey_yr;
 	if ((!old_state->visible && state->visible) ||
 	    drm_to_overlay_state(old_state)->colorkey_yr != val)
@@ -399,6 +418,8 @@ static void armada_overlay_reset(struct drm_plane *plane)
 	state = kzalloc(sizeof(*state), GFP_KERNEL);
 	if (state) {
 		state->base.plane = plane;
+		state->base.color_encoding = DEFAULT_ENCODING;
+		state->base.color_range = DRM_COLOR_YCBCR_LIMITED_RANGE;
 		state->base.rotation = DRM_MODE_ROTATE_0;
 		state->colorkey_yr = 0xfefefe00;
 		state->colorkey_ug = 0x01010100;
@@ -489,6 +510,9 @@ static int armada_overlay_set_property(struct drm_plane *plane,
 		drm_to_overlay_state(state)->contrast = val;
 	} else if (property == priv->saturation_prop) {
 		drm_to_overlay_state(state)->saturation = val;
+	} else if (property == plane->color_encoding_property) {
+		/* transitional only */
+		state->color_encoding = val;
 	} else {
 		return -EINVAL;
 	}
@@ -685,5 +709,12 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 	drm_object_attach_property(mobj, priv->saturation_prop,
 				   DEFAULT_SATURATION);
 
-	return 0;
+	ret = drm_plane_create_color_properties(&dplane->base.base,
+						BIT(DRM_COLOR_YCBCR_BT601) |
+						BIT(DRM_COLOR_YCBCR_BT709),
+						BIT(DRM_COLOR_YCBCR_LIMITED_RANGE),
+						DEFAULT_ENCODING,
+						DRM_COLOR_YCBCR_LIMITED_RANGE);
+
+	return ret;
 }
-- 
cgit v1.2.3


From 3382a6b999415d1f78cee3f483957651d7e1f8a4 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: move armada_drm_mode_config_funcs to armada_drv.c

Move the armada_drm_mode_config_funcs to armada_drv.c, since this now
has less to do with FBs than it does with general mode configuration.
In doing so, we need to make armada_fb_create() visible to armada_drv.c,
which reveals a function name clash with armada_fbdev.c.  Rename the
version in armada_fbdev.c.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_drm.h   | 2 --
 drivers/gpu/drm/armada/armada_drv.c   | 6 ++++++
 drivers/gpu/drm/armada/armada_fb.c    | 7 +------
 drivers/gpu/drm/armada/armada_fb.h    | 3 ++-
 drivers/gpu/drm/armada/armada_fbdev.c | 4 ++--
 5 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index 28087e4b9b81..64f1c8836078 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -79,8 +79,6 @@ void __armada_drm_queue_unref_work(struct drm_device *,
 void armada_drm_queue_unref_work(struct drm_device *,
 	struct drm_framebuffer *);
 
-extern const struct drm_mode_config_funcs armada_drm_mode_config_funcs;
-
 int armada_fbdev_init(struct drm_device *);
 void armada_fbdev_fini(struct drm_device *);
 
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index e47b995b4ce6..7517f23bb9cd 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -15,6 +15,7 @@
 #include "armada_crtc.h"
 #include "armada_drm.h"
 #include "armada_gem.h"
+#include "armada_fb.h"
 #include "armada_hw.h"
 #include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
@@ -77,6 +78,11 @@ static struct drm_driver armada_drm_driver = {
 	.fops			= &armada_drm_fops,
 };
 
+static const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
+	.fb_create		= armada_fb_create,
+	.output_poll_changed	= drm_fb_helper_output_poll_changed,
+};
+
 static int armada_drm_bind(struct device *dev)
 {
 	struct armada_private *priv;
diff --git a/drivers/gpu/drm/armada/armada_fb.c b/drivers/gpu/drm/armada/armada_fb.c
index edd15126bde9..6bd638a54579 100644
--- a/drivers/gpu/drm/armada/armada_fb.c
+++ b/drivers/gpu/drm/armada/armada_fb.c
@@ -84,7 +84,7 @@ struct armada_framebuffer *armada_framebuffer_create(struct drm_device *dev,
 	return dfb;
 }
 
-static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
+struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
 	struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode)
 {
 	struct armada_gem_object *obj;
@@ -138,8 +138,3 @@ static struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
 	DRM_ERROR("failed to initialize framebuffer: %d\n", ret);
 	return ERR_PTR(ret);
 }
-
-const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
-	.fb_create		= armada_fb_create,
-	.output_poll_changed	= drm_fb_helper_output_poll_changed,
-};
diff --git a/drivers/gpu/drm/armada/armada_fb.h b/drivers/gpu/drm/armada/armada_fb.h
index 5c130ff5da77..476daad0a36a 100644
--- a/drivers/gpu/drm/armada/armada_fb.h
+++ b/drivers/gpu/drm/armada/armada_fb.h
@@ -19,5 +19,6 @@ struct armada_framebuffer {
 
 struct armada_framebuffer *armada_framebuffer_create(struct drm_device *,
 	const struct drm_mode_fb_cmd2 *, struct armada_gem_object *);
-
+struct drm_framebuffer *armada_fb_create(struct drm_device *dev,
+	struct drm_file *dfile, const struct drm_mode_fb_cmd2 *mode);
 #endif
diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c
index 2a59db0994b2..8d23700848df 100644
--- a/drivers/gpu/drm/armada/armada_fbdev.c
+++ b/drivers/gpu/drm/armada/armada_fbdev.c
@@ -24,7 +24,7 @@ static /*const*/ struct fb_ops armada_fb_ops = {
 	.fb_imageblit	= drm_fb_helper_cfb_imageblit,
 };
 
-static int armada_fb_create(struct drm_fb_helper *fbh,
+static int armada_fbdev_create(struct drm_fb_helper *fbh,
 	struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_device *dev = fbh->dev;
@@ -108,7 +108,7 @@ static int armada_fb_probe(struct drm_fb_helper *fbh,
 	int ret = 0;
 
 	if (!fbh->fb) {
-		ret = armada_fb_create(fbh, sizes);
+		ret = armada_fbdev_create(fbh, sizes);
 		if (ret == 0)
 			ret = 1;
 	}
-- 
cgit v1.2.3


From b4df3ba0d76823cb5e548505de104837d89aa5a9 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: pass plane state into armada_drm_plane_calc_addrs()

armada_drm_plane_calc_addrs() gets all its information from the plane
state, so it makes sense to pass the plane state pointer down into this
function, rather than extracting the information in identical ways,
sometimes a couple of layers up.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_overlay.c |  6 +++---
 drivers/gpu/drm/armada/armada_plane.c   | 25 ++++++++++++-------------
 drivers/gpu/drm/armada/armada_plane.h   |  3 +--
 3 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index bc1b5b860141..e8c3bcc09d5c 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -130,11 +130,10 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 	    old_state->src.y1 != state->src.y1 ||
 	    old_state->fb != state->fb) {
 		const struct drm_format_info *format;
-		u16 src_x = state->src.x1 >> 16;
-		u16 src_y = state->src.y1 >> 16;
+		u16 src_x;
 		u32 addrs[3];
 
-		armada_drm_plane_calc_addrs(addrs, state->fb, src_x, src_y);
+		armada_drm_plane_calc_addrs(state, addrs);
 
 		armada_reg_queue_set(regs, idx, addrs[0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
@@ -166,6 +165,7 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 		 * the UV swap.
 		 */
 		format = state->fb->format;
+		src_x = state->src.x1 >> 16;
 		if (format->num_planes == 1 && src_x & (format->hsub - 1))
 			cfg ^= CFG_DMA_MOD(CFG_SWAPUV);
 		cfg_mask = CFG_CBSH_ENA | CFG_DMAFORMAT |
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index 1cb6a605bda9..c426c92c79d9 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -35,14 +35,19 @@ static const uint32_t armada_primary_formats[] = {
 	DRM_FORMAT_BGR565,
 };
 
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y)
+void armada_drm_plane_calc_addrs(struct drm_plane_state *state, u32 addrs[3])
 {
+	struct drm_framebuffer *fb = state->fb;
 	const struct drm_format_info *format = fb->format;
 	unsigned int num_planes = format->num_planes;
+	unsigned int x = state->src.x1 >> 16;
+	unsigned int y = state->src.y1 >> 16;
 	u32 addr = drm_fb_obj(fb)->dev_addr;
 	int i;
 
+	DRM_DEBUG_KMS("pitch %u x %d y %d bpp %d\n",
+		      fb->pitches[0], x, y, format->cpp[0] * 8);
+
 	if (num_planes > 3)
 		num_planes = 3;
 
@@ -59,17 +64,14 @@ void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
 		addrs[i] = 0;
 }
 
-static unsigned armada_drm_crtc_calc_fb(struct drm_framebuffer *fb,
-	int x, int y, struct armada_regs *regs, bool interlaced)
+static unsigned armada_drm_crtc_calc_fb(struct drm_plane_state *state,
+	struct armada_regs *regs, bool interlaced)
 {
-	unsigned pitch = fb->pitches[0];
+	unsigned pitch = state->fb->pitches[0];
 	u32 addrs[3], addr_odd, addr_even;
 	unsigned i = 0;
 
-	DRM_DEBUG_DRIVER("pitch %u x %d y %d bpp %d\n",
-		pitch, x, y, fb->format->cpp[0] * 8);
-
-	armada_drm_plane_calc_addrs(addrs, fb, x, y);
+	armada_drm_plane_calc_addrs(state, addrs);
 
 	addr_odd = addr_even = addrs[0];
 
@@ -175,10 +177,7 @@ static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
 	if (old_state->src.x1 != state->src.x1 ||
 	    old_state->src.y1 != state->src.y1 ||
 	    old_state->fb != state->fb) {
-		idx += armada_drm_crtc_calc_fb(state->fb,
-					       state->src.x1 >> 16,
-					       state->src.y1 >> 16,
-					       regs + idx,
+		idx += armada_drm_crtc_calc_fb(state, regs + idx,
 					       dcrtc->interlaced);
 	}
 	if (old_state->fb != state->fb) {
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
index 3c8316003907..999a0bd3e512 100644
--- a/drivers/gpu/drm/armada/armada_plane.h
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -1,8 +1,7 @@
 #ifndef ARMADA_PLANE_H
 #define ARMADA_PLANE_H
 
-void armada_drm_plane_calc_addrs(u32 *addrs, struct drm_framebuffer *fb,
-	int x, int y);
+void armada_drm_plane_calc_addrs(struct drm_plane_state *state, u32 addrs[3]);
 int armada_drm_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_plane_state *state);
 void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
-- 
cgit v1.2.3


From 4aafe00e2f6bb43656d690b6241f80bb8c236168 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: provide pitches from armada_drm_plane_calc_addrs()

Provide the framebuffer pitches from armada_drm_plane_calc_addrs() as
well as the base addresses for each plane.  Since this is now about
more than just addresses, rename to armada_drm_plane_calc().

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_overlay.c |  8 ++++----
 drivers/gpu/drm/armada/armada_plane.c   | 22 ++++++++++++++--------
 drivers/gpu/drm/armada/armada_plane.h   |  3 ++-
 3 files changed, 20 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index e8c3bcc09d5c..f36f6fb919e7 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -130,10 +130,10 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 	    old_state->src.y1 != state->src.y1 ||
 	    old_state->fb != state->fb) {
 		const struct drm_format_info *format;
-		u16 src_x;
+		u16 src_x, pitches[3];
 		u32 addrs[3];
 
-		armada_drm_plane_calc_addrs(state, addrs);
+		armada_drm_plane_calc(state, addrs, pitches);
 
 		armada_reg_queue_set(regs, idx, addrs[0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
@@ -148,9 +148,9 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 		armada_reg_queue_set(regs, idx, addrs[2],
 				     LCD_SPU_DMA_START_ADDR_V1);
 
-		val = state->fb->pitches[0] << 16 | state->fb->pitches[0];
+		val = pitches[0] << 16 | pitches[0];
 		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_YC);
-		val = state->fb->pitches[1] << 16 | state->fb->pitches[2];
+		val = pitches[1] << 16 | pitches[2];
 		armada_reg_queue_set(regs, idx, val, LCD_SPU_DMA_PITCH_UV);
 
 		cfg = CFG_DMA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index c426c92c79d9..3c9414c56aca 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -35,7 +35,8 @@ static const uint32_t armada_primary_formats[] = {
 	DRM_FORMAT_BGR565,
 };
 
-void armada_drm_plane_calc_addrs(struct drm_plane_state *state, u32 addrs[3])
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[3],
+	u16 pitches[3])
 {
 	struct drm_framebuffer *fb = state->fb;
 	const struct drm_format_info *format = fb->format;
@@ -53,37 +54,42 @@ void armada_drm_plane_calc_addrs(struct drm_plane_state *state, u32 addrs[3])
 
 	addrs[0] = addr + fb->offsets[0] + y * fb->pitches[0] +
 		   x * format->cpp[0];
+	pitches[0] = fb->pitches[0];
 
 	y /= format->vsub;
 	x /= format->hsub;
 
-	for (i = 1; i < num_planes; i++)
+	for (i = 1; i < num_planes; i++) {
 		addrs[i] = addr + fb->offsets[i] + y * fb->pitches[i] +
 			     x * format->cpp[i];
-	for (; i < 3; i++)
+		pitches[i] = fb->pitches[i];
+	}
+	for (; i < 3; i++) {
 		addrs[i] = 0;
+		pitches[i] = 0;
+	}
 }
 
 static unsigned armada_drm_crtc_calc_fb(struct drm_plane_state *state,
 	struct armada_regs *regs, bool interlaced)
 {
-	unsigned pitch = state->fb->pitches[0];
+	u16 pitches[3];
 	u32 addrs[3], addr_odd, addr_even;
 	unsigned i = 0;
 
-	armada_drm_plane_calc_addrs(state, addrs);
+	armada_drm_plane_calc(state, addrs, pitches);
 
 	addr_odd = addr_even = addrs[0];
 
 	if (interlaced) {
-		addr_even += pitch;
-		pitch *= 2;
+		addr_even += pitches[0];
+		pitches[0] *= 2;
 	}
 
 	/* write offset, base, and pitch */
 	armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0);
 	armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1);
-	armada_reg_queue_mod(regs, i, pitch, 0xffff, LCD_CFG_GRA_PITCH);
+	armada_reg_queue_mod(regs, i, pitches[0], 0xffff, LCD_CFG_GRA_PITCH);
 
 	return i;
 }
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
index 999a0bd3e512..98280beaaa44 100644
--- a/drivers/gpu/drm/armada/armada_plane.h
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -1,7 +1,8 @@
 #ifndef ARMADA_PLANE_H
 #define ARMADA_PLANE_H
 
-void armada_drm_plane_calc_addrs(struct drm_plane_state *state, u32 addrs[3]);
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[3],
+	u16 pitches[3]);
 int armada_drm_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_plane_state *state);
 void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
-- 
cgit v1.2.3


From b5bae71a79d712681bdf48ee029f1953697924f7 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: push interlace calculation into armada_drm_plane_calc()

Push the interlaced frame calculation down into armada_drm_plane_calc()
which needs to apply the same correction for both the overlay and
primary planes.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_overlay.c | 16 +++++++-------
 drivers/gpu/drm/armada/armada_plane.c   | 38 +++++++++++++++++----------------
 drivers/gpu/drm/armada/armada_plane.h   |  4 ++--
 3 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index f36f6fb919e7..7de8b6bd7847 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -131,21 +131,21 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 	    old_state->fb != state->fb) {
 		const struct drm_format_info *format;
 		u16 src_x, pitches[3];
-		u32 addrs[3];
+		u32 addrs[2][3];
 
-		armada_drm_plane_calc(state, addrs, pitches);
+		armada_drm_plane_calc(state, addrs, pitches, false);
 
-		armada_reg_queue_set(regs, idx, addrs[0],
+		armada_reg_queue_set(regs, idx, addrs[0][0],
 				     LCD_SPU_DMA_START_ADDR_Y0);
-		armada_reg_queue_set(regs, idx, addrs[1],
+		armada_reg_queue_set(regs, idx, addrs[0][1],
 				     LCD_SPU_DMA_START_ADDR_U0);
-		armada_reg_queue_set(regs, idx, addrs[2],
+		armada_reg_queue_set(regs, idx, addrs[0][2],
 				     LCD_SPU_DMA_START_ADDR_V0);
-		armada_reg_queue_set(regs, idx, addrs[0],
+		armada_reg_queue_set(regs, idx, addrs[1][0],
 				     LCD_SPU_DMA_START_ADDR_Y1);
-		armada_reg_queue_set(regs, idx, addrs[1],
+		armada_reg_queue_set(regs, idx, addrs[1][1],
 				     LCD_SPU_DMA_START_ADDR_U1);
-		armada_reg_queue_set(regs, idx, addrs[2],
+		armada_reg_queue_set(regs, idx, addrs[1][2],
 				     LCD_SPU_DMA_START_ADDR_V1);
 
 		val = pitches[0] << 16 | pitches[0];
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index 3c9414c56aca..1320fec4c386 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -35,8 +35,8 @@ static const uint32_t armada_primary_formats[] = {
 	DRM_FORMAT_BGR565,
 };
 
-void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[3],
-	u16 pitches[3])
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
+	u16 pitches[3], bool interlaced)
 {
 	struct drm_framebuffer *fb = state->fb;
 	const struct drm_format_info *format = fb->format;
@@ -52,43 +52,45 @@ void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[3],
 	if (num_planes > 3)
 		num_planes = 3;
 
-	addrs[0] = addr + fb->offsets[0] + y * fb->pitches[0] +
-		   x * format->cpp[0];
+	addrs[0][0] = addr + fb->offsets[0] + y * fb->pitches[0] +
+		      x * format->cpp[0];
 	pitches[0] = fb->pitches[0];
 
 	y /= format->vsub;
 	x /= format->hsub;
 
 	for (i = 1; i < num_planes; i++) {
-		addrs[i] = addr + fb->offsets[i] + y * fb->pitches[i] +
-			     x * format->cpp[i];
+		addrs[0][i] = addr + fb->offsets[i] + y * fb->pitches[i] +
+			      x * format->cpp[i];
 		pitches[i] = fb->pitches[i];
 	}
 	for (; i < 3; i++) {
-		addrs[i] = 0;
+		addrs[0][i] = 0;
 		pitches[i] = 0;
 	}
+	if (interlaced) {
+		for (i = 0; i < 3; i++) {
+			addrs[1][i] = addrs[0][i] + pitches[i];
+			pitches[i] *= 2;
+		}
+	} else {
+		for (i = 0; i < 3; i++)
+			addrs[1][i] = addrs[0][i];
+	}
 }
 
 static unsigned armada_drm_crtc_calc_fb(struct drm_plane_state *state,
 	struct armada_regs *regs, bool interlaced)
 {
 	u16 pitches[3];
-	u32 addrs[3], addr_odd, addr_even;
+	u32 addrs[2][3];
 	unsigned i = 0;
 
-	armada_drm_plane_calc(state, addrs, pitches);
-
-	addr_odd = addr_even = addrs[0];
-
-	if (interlaced) {
-		addr_even += pitches[0];
-		pitches[0] *= 2;
-	}
+	armada_drm_plane_calc(state, addrs, pitches, interlaced);
 
 	/* write offset, base, and pitch */
-	armada_reg_queue_set(regs, i, addr_odd, LCD_CFG_GRA_START_ADDR0);
-	armada_reg_queue_set(regs, i, addr_even, LCD_CFG_GRA_START_ADDR1);
+	armada_reg_queue_set(regs, i, addrs[0][0], LCD_CFG_GRA_START_ADDR0);
+	armada_reg_queue_set(regs, i, addrs[1][0], LCD_CFG_GRA_START_ADDR1);
 	armada_reg_queue_mod(regs, i, pitches[0], 0xffff, LCD_CFG_GRA_PITCH);
 
 	return i;
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
index 98280beaaa44..1bd8430992e0 100644
--- a/drivers/gpu/drm/armada/armada_plane.h
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -1,8 +1,8 @@
 #ifndef ARMADA_PLANE_H
 #define ARMADA_PLANE_H
 
-void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[3],
-	u16 pitches[3]);
+void armada_drm_plane_calc(struct drm_plane_state *state, u32 addrs[2][3],
+	u16 pitches[3], bool interlaced);
 int armada_drm_plane_prepare_fb(struct drm_plane *plane,
 	struct drm_plane_state *state);
 void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
-- 
cgit v1.2.3


From 155b8290f7635b31faa57ca38cb5ddfe78111c2d Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: move sync signal polarity to mode_set_nofb() method

For atomic modeset, we need to set the sync signal polarities from the
CRTC state structure rather than the legacy mode structure stored in
CRTC.  In any case, we should update this from our mode_set_nofb()
method, rather than the commit() method.  Move it there, and ensure
that armada_drm_crtc_update() will not overwrite these bits.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 47 +++++++++++++++++-------------------
 drivers/gpu/drm/armada/armada_crtc.h |  1 -
 2 files changed, 22 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 35b2df0fc21c..3cae6587b079 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -115,25 +115,9 @@ static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
 		dumb_ctrl |= DUMB_BLANK;
 	}
 
-	/*
-	 * The documentation doesn't indicate what the normal state of
-	 * the sync signals are.  Sebastian Hesselbart kindly probed
-	 * these signals on his board to determine their state.
-	 *
-	 * The non-inverted state of the sync signals is active high.
-	 * Setting these bits makes the appropriate signal active low.
-	 */
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NCSYNC)
-		dumb_ctrl |= CFG_INV_CSYNC;
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NHSYNC)
-		dumb_ctrl |= CFG_INV_HSYNC;
-	if (dcrtc->crtc.mode.flags & DRM_MODE_FLAG_NVSYNC)
-		dumb_ctrl |= CFG_INV_VSYNC;
-
-	if (dcrtc->dumb_ctrl != dumb_ctrl) {
-		dcrtc->dumb_ctrl = dumb_ctrl;
-		writel_relaxed(dumb_ctrl, dcrtc->base + LCD_SPU_DUMB_CTRL);
-	}
+	armada_updatel(dumb_ctrl,
+		       ~(CFG_INV_CSYNC | CFG_INV_HSYNC | CFG_INV_VSYNC),
+		       dcrtc->base + LCD_SPU_DUMB_CTRL);
 }
 
 static void armada_drm_plane_work_call(struct armada_crtc *dcrtc,
@@ -280,7 +264,6 @@ static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 	struct drm_plane *plane;
-	u32 val;
 
 	/*
 	 * If we have an overlay plane associated with this CRTC, disable
@@ -300,11 +283,7 @@ static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
 
 	drm_crtc_vblank_off(crtc);
 
-	val = dcrtc->dumb_ctrl & ~CFG_DUMB_ENA;
-	if (val != dcrtc->dumb_ctrl) {
-		dcrtc->dumb_ctrl = val;
-		writel_relaxed(val, dcrtc->base + LCD_SPU_DUMB_CTRL);
-	}
+	armada_updatel(0, CFG_DUMB_ENA, dcrtc->base + LCD_SPU_DUMB_CTRL);
 }
 
 /* The mode_config.mutex will be held for this call */
@@ -516,6 +495,24 @@ static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 
 	val = adj->flags & DRM_MODE_FLAG_NVSYNC ? CFG_VSYNC_INV : 0;
 	armada_reg_queue_mod(regs, i, val, CFG_VSYNC_INV, LCD_SPU_DMA_CTRL1);
+
+	/*
+	 * The documentation doesn't indicate what the normal state of
+	 * the sync signals are.  Sebastian Hesselbart kindly probed
+	 * these signals on his board to determine their state.
+	 *
+	 * The non-inverted state of the sync signals is active high.
+	 * Setting these bits makes the appropriate signal active low.
+	 */
+	val = 0;
+	if (adj->flags & DRM_MODE_FLAG_NCSYNC)
+		val |= CFG_INV_CSYNC;
+	if (adj->flags & DRM_MODE_FLAG_NHSYNC)
+		val |= CFG_INV_HSYNC;
+	if (adj->flags & DRM_MODE_FLAG_NVSYNC)
+		val |= CFG_INV_VSYNC;
+	armada_reg_queue_mod(regs, i, val, CFG_INV_CSYNC | CFG_INV_HSYNC |
+			     CFG_INV_VSYNC, LCD_SPU_DUMB_CTRL);
 	armada_reg_queue_end(regs, i);
 
 	armada_drm_crtc_update_regs(dcrtc, regs);
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 21338f7c3d7d..775c01c52982 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -85,7 +85,6 @@ struct armada_crtc {
 
 	int			dpms;
 	uint32_t		cfg_dumb_ctrl;
-	uint32_t		dumb_ctrl;
 	uint32_t		spu_iopad_ctrl;
 
 	spinlock_t		irq_lock;
-- 
cgit v1.2.3


From a61c3922f6293ab5d58f64e2312981cc646c2fd8 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: update debug in armada_drm_crtc_mode_set_nofb()

Update debug to use KMS level, and print the mode using the standard
format for mode lines, but print the adjusted CRTC parameters as
that's what we will be programming for.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 3cae6587b079..9ad966caf08c 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -426,16 +426,15 @@ static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	bm = adj->crtc_vsync_start - adj->crtc_vdisplay;
 	tm = adj->crtc_vtotal - adj->crtc_vsync_end;
 
-	DRM_DEBUG_DRIVER("H: %d %d %d %d lm %d rm %d\n",
-		adj->crtc_hdisplay,
-		adj->crtc_hsync_start,
-		adj->crtc_hsync_end,
-		adj->crtc_htotal, lm, rm);
-	DRM_DEBUG_DRIVER("V: %d %d %d %d tm %d bm %d\n",
-		adj->crtc_vdisplay,
-		adj->crtc_vsync_start,
-		adj->crtc_vsync_end,
-		adj->crtc_vtotal, tm, bm);
+	DRM_DEBUG_KMS("[CRTC:%d:%s] mode " DRM_MODE_FMT "\n",
+		      crtc->base.id, crtc->name,
+		      adj->base.id, adj->name, adj->vrefresh, adj->clock,
+		      adj->crtc_hdisplay, adj->crtc_hsync_start,
+		      adj->crtc_hsync_end, adj->crtc_htotal,
+		      adj->crtc_vdisplay, adj->crtc_vsync_start,
+		      adj->crtc_vsync_end, adj->crtc_vtotal,
+		      adj->type, adj->flags);
+	DRM_DEBUG_KMS("lm %d rm %d tm %d bm %d\n", lm, rm, tm, bm);
 
 	/*
 	 * If we are blanked, we would have disabled the clock.  Re-enable
-- 
cgit v1.2.3


From 4e4b3563ac006e47761341682de80528e2cf30ab Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: clean up SPU_ADV_REG

Rather than writing all bits of SPU_ADV_REG on modeset, only write
what we need to change, and initialise the register in the variant
initialisation.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_510.c  |  5 ++++-
 drivers/gpu/drm/armada/armada_crtc.c | 11 ++++-------
 drivers/gpu/drm/armada/armada_drm.h  |  1 -
 3 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_510.c b/drivers/gpu/drm/armada/armada_510.c
index 41a784f5a5e6..9a4fbb6a24b8 100644
--- a/drivers/gpu/drm/armada/armada_510.c
+++ b/drivers/gpu/drm/armada/armada_510.c
@@ -27,6 +27,10 @@ static int armada510_crtc_init(struct armada_crtc *dcrtc, struct device *dev)
 	/* Lower the watermark so to eliminate jitter at higher bandwidths */
 	armada_updatel(0x20, (1 << 11) | 0xff, dcrtc->base + LCD_CFG_RDREG4F);
 
+	/* Initialise SPU register */
+	writel_relaxed(ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND,
+		       dcrtc->base + LCD_SPU_ADV_REG);
+
 	return 0;
 }
 
@@ -77,7 +81,6 @@ static int armada510_crtc_compute_clock(struct armada_crtc *dcrtc,
 
 const struct armada_variant armada510_ops = {
 	.has_spu_adv_reg = true,
-	.spu_adv_reg = ADV_HWC32ENABLE | ADV_HWC32ARGB | ADV_HWC32BLEND,
 	.init = armada510_crtc_init,
 	.compute_clock = armada510_crtc_compute_clock,
 };
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 9ad966caf08c..80d34a4b7d41 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -463,17 +463,15 @@ static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 				    adj->crtc_htotal;
 	dcrtc->v[1].spu_v_porch = tm << 16 | bm;
 	val = adj->crtc_hsync_start;
-	dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN |
-		dcrtc->variant->spu_adv_reg;
+	dcrtc->v[1].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
 
 	if (interlaced) {
 		/* Odd interlaced frame */
+		val -= adj->crtc_htotal / 2;
+		dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN;
 		dcrtc->v[0].spu_v_h_total = dcrtc->v[1].spu_v_h_total +
 						(1 << 16);
 		dcrtc->v[0].spu_v_porch = dcrtc->v[1].spu_v_porch + 1;
-		val = adj->crtc_hsync_start - adj->crtc_htotal / 2;
-		dcrtc->v[0].spu_adv_reg = val << 20 | val | ADV_VSYNCOFFEN |
-			dcrtc->variant->spu_adv_reg;
 	} else {
 		dcrtc->v[0] = dcrtc->v[1];
 	}
@@ -486,11 +484,10 @@ static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	armada_reg_queue_set(regs, i, dcrtc->v[0].spu_v_h_total,
 			   LCD_SPUT_V_H_TOTAL);
 
-	if (dcrtc->variant->has_spu_adv_reg) {
+	if (dcrtc->variant->has_spu_adv_reg)
 		armada_reg_queue_mod(regs, i, dcrtc->v[0].spu_adv_reg,
 				     ADV_VSYNC_L_OFF | ADV_VSYNC_H_OFF |
 				     ADV_VSYNCOFFEN, LCD_SPU_ADV_REG);
-	}
 
 	val = adj->flags & DRM_MODE_FLAG_NVSYNC ? CFG_VSYNC_INV : 0;
 	armada_reg_queue_mod(regs, i, val, CFG_VSYNC_INV, LCD_SPU_DMA_CTRL1);
diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index 64f1c8836078..a6f919b0084c 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -42,7 +42,6 @@ struct armada_private;
 
 struct armada_variant {
 	bool has_spu_adv_reg;
-	uint32_t spu_adv_reg;
 	int (*init)(struct armada_crtc *, struct device *);
 	int (*compute_clock)(struct armada_crtc *,
 			     const struct drm_display_mode *,
-- 
cgit v1.2.3


From dbb4ca8acae100b21946a9c6439af51bd606595e Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: handle atomic modeset crtc events

Prepare handling for atomic modeset CRTC events.  Currently, using the
transition helpers, CRTC events do not exist, but once we switch to
proper atomic modeset, they have to be handled.

We queue an event for the next vblank in two places:
- armada_drm_crtc_atomic_flush() provided we aren't doing an
  atomic modeset.
- armada_drm_crtc_commit() if we are committing a modeset.

This ensures that the event is sent at the correct time (after all
updates have been written to the hardware and after the following
vblank.)

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 33 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/armada/armada_crtc.h |  1 +
 2 files changed, 34 insertions(+)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 80d34a4b7d41..a0c67ec892cf 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -232,6 +232,19 @@ static void armada_drm_vblank_off(struct armada_crtc *dcrtc)
 	armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
 }
 
+static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_pending_vblank_event *event;
+
+	/* If we have an event, we need vblank events enabled */
+	event = xchg(&crtc->state->event, NULL);
+	if (event) {
+		WARN_ON(drm_crtc_vblank_get(crtc) != 0);
+		dcrtc->event = event;
+	}
+}
+
 /* The mode_config.mutex will be held for this call */
 static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
 {
@@ -294,6 +307,8 @@ static void armada_drm_crtc_commit(struct drm_crtc *crtc)
 	dcrtc->dpms = DRM_MODE_DPMS_ON;
 	armada_drm_crtc_update(dcrtc);
 	drm_crtc_vblank_on(crtc);
+
+	armada_drm_crtc_queue_state_event(crtc);
 }
 
 /* The mode_config.mutex will be held for this call */
@@ -337,6 +352,7 @@ static void armada_drm_crtc_enable_irq(struct armada_crtc *dcrtc, u32 mask)
 
 static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 {
+	struct drm_pending_vblank_event *event;
 	void __iomem *base = dcrtc->base;
 	struct drm_plane *ovl_plane;
 
@@ -383,6 +399,16 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 
 	if (stat & GRA_FRAME_IRQ)
 		armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
+
+	if (stat & VSYNC_IRQ) {
+		event = xchg(&dcrtc->event, NULL);
+		if (event) {
+			spin_lock(&dcrtc->crtc.dev->event_lock);
+			drm_crtc_send_vblank_event(&dcrtc->crtc, event);
+			spin_unlock(&dcrtc->crtc.dev->event_lock);
+			drm_crtc_vblank_put(&dcrtc->crtc);
+		}
+	}
 }
 
 static irqreturn_t armada_drm_irq(int irq, void *arg)
@@ -554,6 +580,13 @@ static void armada_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 	spin_lock_irqsave(&dcrtc->irq_lock, flags);
 	armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
+
+	/*
+	 * If we aren't doing a full modeset, then we need to queue
+	 * the event here.
+	 */
+	if (!drm_atomic_crtc_needs_modeset(crtc->state))
+		armada_drm_crtc_queue_state_event(crtc);
 }
 
 static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 775c01c52982..8b1de877cb02 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -90,6 +90,7 @@ struct armada_crtc {
 	spinlock_t		irq_lock;
 	uint32_t		irq_ena;
 
+	struct drm_pending_vblank_event *event;
 	struct armada_regs	atomic_regs[32];
 	struct armada_regs	*regs;
 	unsigned int		regs_idx;
-- 
cgit v1.2.3


From a0fbb35ecde52aa5abf5975d117d29e3b30f7b91 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: push responsibility for clock management to backend

Push responsibility for managing the clock during DPMS down into the
variant backend, rather than the CRTC layer having knowledge of its
state.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_510.c  | 19 +++++++++++++++++++
 drivers/gpu/drm/armada/armada_crtc.c | 19 ++++++-------------
 drivers/gpu/drm/armada/armada_drm.h  |  2 ++
 3 files changed, 27 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_510.c b/drivers/gpu/drm/armada/armada_510.c
index 9a4fbb6a24b8..2f7c048c5361 100644
--- a/drivers/gpu/drm/armada/armada_510.c
+++ b/drivers/gpu/drm/armada/armada_510.c
@@ -79,8 +79,27 @@ static int armada510_crtc_compute_clock(struct armada_crtc *dcrtc,
 	return 0;
 }
 
+static void armada510_crtc_disable(struct armada_crtc *dcrtc)
+{
+	if (!IS_ERR(dcrtc->clk)) {
+		clk_disable_unprepare(dcrtc->clk);
+		dcrtc->clk = ERR_PTR(-EINVAL);
+	}
+}
+
+static void armada510_crtc_enable(struct armada_crtc *dcrtc,
+	const struct drm_display_mode *mode)
+{
+	if (IS_ERR(dcrtc->clk)) {
+		dcrtc->clk = dcrtc->extclk[0];
+		WARN_ON(clk_prepare_enable(dcrtc->clk));
+	}
+}
+
 const struct armada_variant armada510_ops = {
 	.has_spu_adv_reg = true,
 	.init = armada510_crtc_init,
 	.compute_clock = armada510_crtc_compute_clock,
+	.disable = armada510_crtc_disable,
+	.enable = armada510_crtc_enable,
 };
diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index a0c67ec892cf..5d8fdcda27ee 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -253,14 +253,14 @@ static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
 	if (dpms_blanked(dcrtc->dpms) != dpms_blanked(dpms)) {
 		if (dpms_blanked(dpms))
 			armada_drm_vblank_off(dcrtc);
-		else if (!IS_ERR(dcrtc->clk))
-			WARN_ON(clk_prepare_enable(dcrtc->clk));
+		else if (dcrtc->variant->enable)
+			dcrtc->variant->enable(dcrtc, &crtc->hwmode);
 		dcrtc->dpms = dpms;
 		armada_drm_crtc_update(dcrtc);
 		if (!dpms_blanked(dpms))
 			drm_crtc_vblank_on(&dcrtc->crtc);
-		else if (!IS_ERR(dcrtc->clk))
-			clk_disable_unprepare(dcrtc->clk);
+		else if (dcrtc->variant->disable)
+			dcrtc->variant->disable(dcrtc);
 	} else if (dcrtc->dpms != dpms) {
 		dcrtc->dpms = dpms;
 	}
@@ -462,13 +462,6 @@ static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 		      adj->type, adj->flags);
 	DRM_DEBUG_KMS("lm %d rm %d tm %d bm %d\n", lm, rm, tm, bm);
 
-	/*
-	 * If we are blanked, we would have disabled the clock.  Re-enable
-	 * it so that compute_clock() does the right thing.
-	 */
-	if (!IS_ERR(dcrtc->clk) && dpms_blanked(dcrtc->dpms))
-		WARN_ON(clk_prepare_enable(dcrtc->clk));
-
 	/* Now compute the divider for real */
 	dcrtc->variant->compute_clock(dcrtc, adj, &sclk);
 
@@ -824,8 +817,8 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
 	priv->dcrtc[dcrtc->num] = NULL;
 	drm_crtc_cleanup(&dcrtc->crtc);
 
-	if (!IS_ERR(dcrtc->clk))
-		clk_disable_unprepare(dcrtc->clk);
+	if (dcrtc->variant->disable)
+		dcrtc->variant->disable(dcrtc);
 
 	writel_relaxed(0, dcrtc->base + LCD_SPU_IRQ_ENA);
 
diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index a6f919b0084c..9658be917ea1 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -46,6 +46,8 @@ struct armada_variant {
 	int (*compute_clock)(struct armada_crtc *,
 			     const struct drm_display_mode *,
 			     uint32_t *);
+	void (*disable)(struct armada_crtc *);
+	void (*enable)(struct armada_crtc *, const struct drm_display_mode *);
 };
 
 /* Variant ops */
-- 
cgit v1.2.3


From a0f75d2468fe4510bb8d0d6c4e1a5fd5e262e7b5 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: unhook dpms state from armada_drm_crtc_update()

Explicitly pass in the desired enable/disable state into
armada_drm_crtc_update() rather than having it use the DPMS state
stored in our crtc structure.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 5d8fdcda27ee..554135062d93 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -94,13 +94,13 @@ armada_drm_crtc_update_regs(struct armada_crtc *dcrtc, struct armada_regs *regs)
 
 #define dpms_blanked(dpms)	((dpms) != DRM_MODE_DPMS_ON)
 
-static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
+static void armada_drm_crtc_update(struct armada_crtc *dcrtc, bool enable)
 {
 	uint32_t dumb_ctrl;
 
 	dumb_ctrl = dcrtc->cfg_dumb_ctrl;
 
-	if (!dpms_blanked(dcrtc->dpms))
+	if (enable)
 		dumb_ctrl |= CFG_DUMB_ENA;
 
 	/*
@@ -109,8 +109,7 @@ static void armada_drm_crtc_update(struct armada_crtc *dcrtc)
 	 * force LCD_D[23:0] to output blank color, overriding the GPIO or
 	 * SPI usage.  So leave it as-is unless in DUMB24_RGB888_0 mode.
 	 */
-	if (dpms_blanked(dcrtc->dpms) &&
-	    (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) {
+	if (!enable && (dumb_ctrl & DUMB_MASK) == DUMB24_RGB888_0) {
 		dumb_ctrl &= ~DUMB_MASK;
 		dumb_ctrl |= DUMB_BLANK;
 	}
@@ -256,7 +255,7 @@ static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
 		else if (dcrtc->variant->enable)
 			dcrtc->variant->enable(dcrtc, &crtc->hwmode);
 		dcrtc->dpms = dpms;
-		armada_drm_crtc_update(dcrtc);
+		armada_drm_crtc_update(dcrtc, !dpms_blanked(dcrtc->dpms));
 		if (!dpms_blanked(dpms))
 			drm_crtc_vblank_on(&dcrtc->crtc);
 		else if (dcrtc->variant->disable)
@@ -305,7 +304,7 @@ static void armada_drm_crtc_commit(struct drm_crtc *crtc)
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 
 	dcrtc->dpms = DRM_MODE_DPMS_ON;
-	armada_drm_crtc_update(dcrtc);
+	armada_drm_crtc_update(dcrtc, true);
 	drm_crtc_vblank_on(crtc);
 
 	armada_drm_crtc_queue_state_event(crtc);
-- 
cgit v1.2.3


From 34e25ed60ae2cdf91b953dd3772ae48a6bffbd4c Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:52:34 +0100
Subject: drm/armada: implement atomic_enable()/atomic_disable() methods

Implement the atomic_enable()/atomic_disable() methods used by the
atomic modeset helpers.  atomic_disable() will need some transitional
code during conversion to ensure proper ordering is maintained.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 71 ++++++++++++++++++++++++++++++++++++
 1 file changed, 71 insertions(+)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 554135062d93..e93097d3aa06 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -581,6 +581,75 @@ static void armada_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 		armada_drm_crtc_queue_state_event(crtc);
 }
 
+static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc,
+					   struct drm_crtc_state *old_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+	struct drm_pending_vblank_event *event;
+	struct drm_plane *plane;
+
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
+
+	/*
+	 * For transition only - we must wait for completion of our
+	 * untransitioned paths before changing anything.
+	 */
+	plane = dcrtc->plane;
+	if (plane)
+		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
+						    HZ));
+	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
+				   MAX_SCHEDULE_TIMEOUT);
+
+	dcrtc->dpms = DRM_MODE_DPMS_OFF;
+	drm_crtc_vblank_off(crtc);
+	armada_drm_crtc_update(dcrtc, false);
+
+	if (!crtc->state->active) {
+		/*
+		 * This modeset will be leaving the CRTC disabled, so
+		 * call the backend to disable upstream clocks etc.
+		 */
+		if (dcrtc->variant->disable)
+			dcrtc->variant->disable(dcrtc);
+
+		/*
+		 * We will not receive any further vblank events.
+		 * Send the flip_done event manually.
+		 */
+		event = crtc->state->event;
+		crtc->state->event = NULL;
+		if (event) {
+			spin_lock_irq(&crtc->dev->event_lock);
+			drm_crtc_send_vblank_event(crtc, event);
+			spin_unlock_irq(&crtc->dev->event_lock);
+		}
+	}
+}
+
+static void armada_drm_crtc_atomic_enable(struct drm_crtc *crtc,
+					  struct drm_crtc_state *old_state)
+{
+	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
+
+	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
+
+	dcrtc->dpms = DRM_MODE_DPMS_ON;
+	if (!old_state->active) {
+		/*
+		 * This modeset is enabling the CRTC after it having
+		 * been disabled.  Reverse the call to ->disable in
+		 * the atomic_disable().
+		 */
+		if (dcrtc->variant->enable)
+			dcrtc->variant->enable(dcrtc, &crtc->state->adjusted_mode);
+	}
+	armada_drm_crtc_update(dcrtc, true);
+	drm_crtc_vblank_on(crtc);
+
+	armada_drm_crtc_queue_state_event(crtc);
+}
+
 static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
 	.dpms		= armada_drm_crtc_dpms,
 	.prepare	= armada_drm_crtc_prepare,
@@ -592,6 +661,8 @@ static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
 	.disable	= armada_drm_crtc_disable,
 	.atomic_begin	= armada_drm_crtc_atomic_begin,
 	.atomic_flush	= armada_drm_crtc_atomic_flush,
+	.atomic_disable	= armada_drm_crtc_atomic_disable,
+	.atomic_enable	= armada_drm_crtc_atomic_enable,
 };
 
 static void armada_load_cursor_argb(void __iomem *base, uint32_t *pix,
-- 
cgit v1.2.3


From 6bd02908836ed00aa7fcdc759d490029137c2b30 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: enable atomic modeset support

Enable atomic modeset helpers, and internal DRM use of atomic modeset
with armada-drm.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 7 +++----
 drivers/gpu/drm/armada/armada_drv.c  | 5 ++++-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index e93097d3aa06..375a20757561 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -278,13 +278,12 @@ static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
 	struct drm_plane *plane;
 
 	/*
-	 * If we have an overlay plane associated with this CRTC, disable
-	 * it before the modeset to avoid its coordinates being outside
-	 * the new mode parameters.
+	 * If we have an overlay plane associated with this CRTC, disable it
+	 * before the modeset to avoid its coordinates being outside the new
+	 * mode parameters.  For transitional atomic modeset, we only wait.
 	 */
 	plane = dcrtc->plane;
 	if (plane) {
-		drm_plane_force_disable(plane);
 		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
 						    HZ));
 	}
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 7517f23bb9cd..20661bd9001e 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -9,6 +9,7 @@
 #include <linux/component.h>
 #include <linux/module.h>
 #include <linux/of_graph.h>
+#include <drm/drm_atomic_helper.h>
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_fb_helper.h>
 #include <drm/drm_of.h>
@@ -73,7 +74,7 @@ static struct drm_driver armada_drm_driver = {
 	.desc			= "Armada SoC DRM",
 	.date			= "20120730",
 	.driver_features	= DRIVER_GEM | DRIVER_MODESET |
-				  DRIVER_PRIME,
+				  DRIVER_PRIME | DRIVER_ATOMIC,
 	.ioctls			= armada_ioctls,
 	.fops			= &armada_drm_fops,
 };
@@ -81,6 +82,8 @@ static struct drm_driver armada_drm_driver = {
 static const struct drm_mode_config_funcs armada_drm_mode_config_funcs = {
 	.fb_create		= armada_fb_create,
 	.output_poll_changed	= drm_fb_helper_output_poll_changed,
+	.atomic_check		= drm_atomic_helper_check,
+	.atomic_commit		= drm_atomic_helper_commit,
 };
 
 static int armada_drm_bind(struct device *dev)
-- 
cgit v1.2.3


From 6d2f864fdff5c73cb37069cd17b0f897d7995b62 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: switch legacy modeset to atomic modeset

Switch the legacy set_config() method to use the atomic modeset
helper, which allows us to get rid of the legacy dpms, prepare,
commit, mode_set, mode_set_base and disable helper methods.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 103 +----------------------------------
 drivers/gpu/drm/armada/armada_crtc.h |   1 -
 2 files changed, 1 insertion(+), 103 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 375a20757561..0cef40ad3a06 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -92,8 +92,6 @@ armada_drm_crtc_update_regs(struct armada_crtc *dcrtc, struct armada_regs *regs)
 	}
 }
 
-#define dpms_blanked(dpms)	((dpms) != DRM_MODE_DPMS_ON)
-
 static void armada_drm_crtc_update(struct armada_crtc *dcrtc, bool enable)
 {
 	uint32_t dumb_ctrl;
@@ -221,16 +219,6 @@ armada_drm_crtc_alloc_plane_work(struct drm_plane *plane)
 	return work;
 }
 
-static void armada_drm_vblank_off(struct armada_crtc *dcrtc)
-{
-	/*
-	 * Tell the DRM core that vblank IRQs aren't going to happen for
-	 * a while.  This cleans up any pending vblank events for us.
-	 */
-	drm_crtc_vblank_off(&dcrtc->crtc);
-	armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
-}
-
 static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
@@ -244,71 +232,6 @@ static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc)
 	}
 }
 
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_dpms(struct drm_crtc *crtc, int dpms)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-
-	if (dpms_blanked(dcrtc->dpms) != dpms_blanked(dpms)) {
-		if (dpms_blanked(dpms))
-			armada_drm_vblank_off(dcrtc);
-		else if (dcrtc->variant->enable)
-			dcrtc->variant->enable(dcrtc, &crtc->hwmode);
-		dcrtc->dpms = dpms;
-		armada_drm_crtc_update(dcrtc, !dpms_blanked(dcrtc->dpms));
-		if (!dpms_blanked(dpms))
-			drm_crtc_vblank_on(&dcrtc->crtc);
-		else if (dcrtc->variant->disable)
-			dcrtc->variant->disable(dcrtc);
-	} else if (dcrtc->dpms != dpms) {
-		dcrtc->dpms = dpms;
-	}
-}
-
-/*
- * Prepare for a mode set.  Turn off overlay to ensure that we don't end
- * up with the overlay size being bigger than the active screen size.
- * We rely upon X refreshing this state after the mode set has completed.
- *
- * The mode_config.mutex will be held for this call
- */
-static void armada_drm_crtc_prepare(struct drm_crtc *crtc)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct drm_plane *plane;
-
-	/*
-	 * If we have an overlay plane associated with this CRTC, disable it
-	 * before the modeset to avoid its coordinates being outside the new
-	 * mode parameters.  For transitional atomic modeset, we only wait.
-	 */
-	plane = dcrtc->plane;
-	if (plane) {
-		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
-						    HZ));
-	}
-
-	/* Wait for pending flips to complete */
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
-
-	drm_crtc_vblank_off(crtc);
-
-	armada_updatel(0, CFG_DUMB_ENA, dcrtc->base + LCD_SPU_DUMB_CTRL);
-}
-
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_commit(struct drm_crtc *crtc)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-
-	dcrtc->dpms = DRM_MODE_DPMS_ON;
-	armada_drm_crtc_update(dcrtc, true);
-	drm_crtc_vblank_on(crtc);
-
-	armada_drm_crtc_queue_state_event(crtc);
-}
-
 /* The mode_config.mutex will be held for this call */
 static bool armada_drm_crtc_mode_fixup(struct drm_crtc *crtc,
 	const struct drm_display_mode *mode, struct drm_display_mode *adj)
@@ -532,15 +455,6 @@ static void armada_drm_crtc_mode_set_nofb(struct drm_crtc *crtc)
 	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
 }
 
-/* The mode_config.mutex will be held for this call */
-static void armada_drm_crtc_disable(struct drm_crtc *crtc)
-{
-	armada_drm_crtc_dpms(crtc, DRM_MODE_DPMS_OFF);
-
-	/* Disable our primary plane when we disable the CRTC. */
-	crtc->primary->funcs->disable_plane(crtc->primary, NULL);
-}
-
 static void armada_drm_crtc_atomic_begin(struct drm_crtc *crtc,
 					 struct drm_crtc_state *old_crtc_state)
 {
@@ -600,7 +514,6 @@ static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
 				   MAX_SCHEDULE_TIMEOUT);
 
-	dcrtc->dpms = DRM_MODE_DPMS_OFF;
 	drm_crtc_vblank_off(crtc);
 	armada_drm_crtc_update(dcrtc, false);
 
@@ -633,7 +546,6 @@ static void armada_drm_crtc_atomic_enable(struct drm_crtc *crtc,
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	dcrtc->dpms = DRM_MODE_DPMS_ON;
 	if (!old_state->active) {
 		/*
 		 * This modeset is enabling the CRTC after it having
@@ -650,14 +562,8 @@ static void armada_drm_crtc_atomic_enable(struct drm_crtc *crtc,
 }
 
 static const struct drm_crtc_helper_funcs armada_crtc_helper_funcs = {
-	.dpms		= armada_drm_crtc_dpms,
-	.prepare	= armada_drm_crtc_prepare,
-	.commit		= armada_drm_crtc_commit,
 	.mode_fixup	= armada_drm_crtc_mode_fixup,
-	.mode_set	= drm_helper_crtc_mode_set,
 	.mode_set_nofb	= armada_drm_crtc_mode_set_nofb,
-	.mode_set_base	= drm_helper_crtc_mode_set_base,
-	.disable	= armada_drm_crtc_disable,
 	.atomic_begin	= armada_drm_crtc_atomic_begin,
 	.atomic_flush	= armada_drm_crtc_atomic_flush,
 	.atomic_disable	= armada_drm_crtc_atomic_disable,
@@ -962,13 +868,6 @@ static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
 	WARN_ON(armada_drm_plane_work_queue(dcrtc, work));
 	work = NULL;
 
-	/*
-	 * Finally, if the display is blanked, we won't receive an
-	 * interrupt, so complete it now.
-	 */
-	if (dpms_blanked(dcrtc->dpms))
-		armada_drm_plane_work_run(dcrtc, plane);
-
 put_vblank:
 	drm_crtc_vblank_put(crtc);
 put_work:
@@ -1005,7 +904,7 @@ static const struct drm_crtc_funcs armada_crtc_funcs = {
 	.cursor_set	= armada_drm_crtc_cursor_set,
 	.cursor_move	= armada_drm_crtc_cursor_move,
 	.destroy	= armada_drm_crtc_destroy,
-	.set_config	= drm_crtc_helper_set_config,
+	.set_config	= drm_atomic_helper_set_config,
 	.page_flip	= armada_drm_crtc_page_flip,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 8b1de877cb02..afc9266bc1e2 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -83,7 +83,6 @@ struct armada_crtc {
 	uint32_t		cursor_w;
 	uint32_t		cursor_h;
 
-	int			dpms;
 	uint32_t		cfg_dumb_ctrl;
 	uint32_t		spu_iopad_ctrl;
 
-- 
cgit v1.2.3


From 13c94d5349c9c0756131e7bf2e703ab36ea55c73 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: switch primary plane to atomic modeset

Switch the primary plane away from the transitional helpers, and
use the atomic helpers instead to implement the legacy set_plane
ioctl call for this plane.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c  | 116 +---------------------------------
 drivers/gpu/drm/armada/armada_plane.c |   4 +-
 2 files changed, 3 insertions(+), 117 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index 0cef40ad3a06..a25094bbeb2c 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -191,34 +191,6 @@ void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
 		armada_drm_plane_work_call(dcrtc, work, work->cancel);
 }
 
-static void armada_drm_crtc_complete_frame_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
-static struct armada_plane_work *
-armada_drm_crtc_alloc_plane_work(struct drm_plane *plane)
-{
-	struct armada_plane_work *work;
-	int i = 0;
-
-	work = kzalloc(sizeof(*work), GFP_KERNEL);
-	if (!work)
-		return NULL;
-
-	work->plane = plane;
-	work->fn = armada_drm_crtc_complete_frame_work;
-	work->need_kfree = true;
-	armada_reg_queue_end(work->regs, i);
-
-	return work;
-}
-
 static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
@@ -318,9 +290,6 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 
 	spin_unlock(&dcrtc->irq_lock);
 
-	if (stat & GRA_FRAME_IRQ)
-		armada_drm_plane_work_run(dcrtc, dcrtc->crtc.primary);
-
 	if (stat & VSYNC_IRQ) {
 		event = xchg(&dcrtc->event, NULL);
 		if (event) {
@@ -459,15 +428,9 @@ static void armada_drm_crtc_atomic_begin(struct drm_crtc *crtc,
 					 struct drm_crtc_state *old_crtc_state)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct armada_plane *dplane;
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	/* Wait 100ms for any plane works to complete */
-	dplane = drm_to_armada_plane(crtc->primary);
-	if (WARN_ON(armada_drm_plane_work_wait(dplane, HZ / 10) == 0))
-		armada_drm_plane_work_cancel(dcrtc, dplane);
-
 	dcrtc->regs_idx = 0;
 	dcrtc->regs = dcrtc->atomic_regs;
 }
@@ -511,8 +474,6 @@ static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 	if (plane)
 		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
 						    HZ));
-	armada_drm_plane_work_wait(drm_to_armada_plane(dcrtc->crtc.primary),
-				   MAX_SCHEDULE_TIMEOUT);
 
 	drm_crtc_vblank_off(crtc);
 	armada_drm_crtc_update(dcrtc, false);
@@ -802,81 +763,6 @@ static void armada_drm_crtc_destroy(struct drm_crtc *crtc)
 	kfree(dcrtc);
 }
 
-/*
- * The mode_config lock is held here, to prevent races between this
- * and a mode_set.
- */
-static int armada_drm_crtc_page_flip(struct drm_crtc *crtc,
-	struct drm_framebuffer *fb, struct drm_pending_vblank_event *event,
-	uint32_t page_flip_flags, struct drm_modeset_acquire_ctx *ctx)
-{
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	struct drm_plane *plane = crtc->primary;
-	const struct drm_plane_helper_funcs *plane_funcs;
-	struct drm_plane_state *state;
-	struct armada_plane_work *work;
-	int ret;
-
-	/* Construct new state for the primary plane */
-	state = drm_atomic_helper_plane_duplicate_state(plane);
-	if (!state)
-		return -ENOMEM;
-
-	drm_atomic_set_fb_for_plane(state, fb);
-
-	work = armada_drm_crtc_alloc_plane_work(plane);
-	if (!work) {
-		ret = -ENOMEM;
-		goto put_state;
-	}
-
-	/* Make sure we can get vblank interrupts */
-	ret = drm_crtc_vblank_get(crtc);
-	if (ret)
-		goto put_work;
-
-	/*
-	 * If we have another work pending, we can't process this flip.
-	 * The modeset locks protect us from another user queuing a work
-	 * while we're setting up.
-	 */
-	if (drm_to_armada_plane(plane)->work) {
-		ret = -EBUSY;
-		goto put_vblank;
-	}
-
-	work->event = event;
-	work->old_fb = plane->state->fb;
-
-	/*
-	 * Hold a ref on the new fb while it's being displayed by the
-	 * hardware. The old fb refcount will be released in the worker.
-	 */
-	drm_framebuffer_get(state->fb);
-
-	/* Point of no return */
-	swap(plane->state, state);
-
-	dcrtc->regs_idx = 0;
-	dcrtc->regs = work->regs;
-
-	plane_funcs = plane->helper_private;
-	plane_funcs->atomic_update(plane, state);
-	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
-
-	/* Queue the work - this should never fail */
-	WARN_ON(armada_drm_plane_work_queue(dcrtc, work));
-	work = NULL;
-
-put_vblank:
-	drm_crtc_vblank_put(crtc);
-put_work:
-	kfree(work);
-put_state:
-	drm_atomic_helper_plane_destroy_state(plane, state);
-	return ret;
-}
-
 /* These are called under the vbl_lock. */
 static int armada_drm_crtc_enable_vblank(struct drm_crtc *crtc)
 {
@@ -905,7 +791,7 @@ static const struct drm_crtc_funcs armada_crtc_funcs = {
 	.cursor_move	= armada_drm_crtc_cursor_move,
 	.destroy	= armada_drm_crtc_destroy,
 	.set_config	= drm_atomic_helper_set_config,
-	.page_flip	= armada_drm_crtc_page_flip,
+	.page_flip	= drm_atomic_helper_page_flip,
 	.atomic_duplicate_state = drm_atomic_helper_crtc_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_crtc_destroy_state,
 	.enable_vblank	= armada_drm_crtc_enable_vblank,
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index 1320fec4c386..39c9ba3ee57e 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -261,8 +261,8 @@ static const struct drm_plane_helper_funcs armada_primary_plane_helper_funcs = {
 };
 
 static const struct drm_plane_funcs armada_primary_plane_funcs = {
-	.update_plane	= drm_plane_helper_update,
-	.disable_plane	= drm_plane_helper_disable,
+	.update_plane	= drm_atomic_helper_update_plane,
+	.disable_plane	= drm_atomic_helper_disable_plane,
 	.destroy	= drm_primary_helper_destroy,
 	.reset		= drm_atomic_helper_plane_reset,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
-- 
cgit v1.2.3


From b1ec9ed6aa985be432f9ba29696029dc6779258e Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: switch overlay plane to atomic modeset

Switch the overlay plane away from the transitional helpers and legacy
methods, and use atomic helpers instead to implement the legacy
set_plane ioctl methods.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c    |  89 -----------------
 drivers/gpu/drm/armada/armada_crtc.h    |  19 ----
 drivers/gpu/drm/armada/armada_overlay.c | 172 ++++++--------------------------
 3 files changed, 32 insertions(+), 248 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index a25094bbeb2c..ebcb99316c94 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -117,80 +117,6 @@ static void armada_drm_crtc_update(struct armada_crtc *dcrtc, bool enable)
 		       dcrtc->base + LCD_SPU_DUMB_CTRL);
 }
 
-static void armada_drm_plane_work_call(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work,
-	void (*fn)(struct armada_crtc *, struct armada_plane_work *))
-{
-	struct armada_plane *dplane = drm_to_armada_plane(work->plane);
-	struct drm_pending_vblank_event *event;
-	struct drm_framebuffer *fb;
-
-	if (fn)
-		fn(dcrtc, work);
-	drm_crtc_vblank_put(&dcrtc->crtc);
-
-	event = work->event;
-	fb = work->old_fb;
-	if (event || fb) {
-		struct drm_device *dev = dcrtc->crtc.dev;
-		unsigned long flags;
-
-		spin_lock_irqsave(&dev->event_lock, flags);
-		if (event)
-			drm_crtc_send_vblank_event(&dcrtc->crtc, event);
-		if (fb)
-			__armada_drm_queue_unref_work(dev, fb);
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-	}
-
-	if (work->need_kfree)
-		kfree(work);
-
-	wake_up(&dplane->frame_wait);
-}
-
-static void armada_drm_plane_work_run(struct armada_crtc *dcrtc,
-	struct drm_plane *plane)
-{
-	struct armada_plane *dplane = drm_to_armada_plane(plane);
-	struct armada_plane_work *work = xchg(&dplane->work, NULL);
-
-	/* Handle any pending frame work. */
-	if (work)
-		armada_drm_plane_work_call(dcrtc, work, work->fn);
-}
-
-int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	struct armada_plane *plane = drm_to_armada_plane(work->plane);
-	int ret;
-
-	ret = drm_crtc_vblank_get(&dcrtc->crtc);
-	if (ret)
-		return ret;
-
-	ret = cmpxchg(&plane->work, NULL, work) ? -EBUSY : 0;
-	if (ret)
-		drm_crtc_vblank_put(&dcrtc->crtc);
-
-	return ret;
-}
-
-int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout)
-{
-	return wait_event_timeout(plane->frame_wait, !plane->work, timeout);
-}
-
-void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
-	struct armada_plane *dplane)
-{
-	struct armada_plane_work *work = xchg(&dplane->work, NULL);
-
-	if (work)
-		armada_drm_plane_work_call(dcrtc, work, work->cancel);
-}
-
 static void armada_drm_crtc_queue_state_event(struct drm_crtc *crtc)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
@@ -247,7 +173,6 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 {
 	struct drm_pending_vblank_event *event;
 	void __iomem *base = dcrtc->base;
-	struct drm_plane *ovl_plane;
 
 	if (stat & DMA_FF_UNDERFLOW)
 		DRM_ERROR("video underflow on crtc %u\n", dcrtc->num);
@@ -257,10 +182,6 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 	if (stat & VSYNC_IRQ)
 		drm_crtc_handle_vblank(&dcrtc->crtc);
 
-	ovl_plane = dcrtc->plane;
-	if (ovl_plane)
-		armada_drm_plane_work_run(dcrtc, ovl_plane);
-
 	spin_lock(&dcrtc->irq_lock);
 	if (stat & GRA_FRAME_IRQ && dcrtc->interlaced) {
 		int i = stat & GRA_FRAME_IRQ0 ? 0 : 1;
@@ -462,19 +383,9 @@ static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc,
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
 	struct drm_pending_vblank_event *event;
-	struct drm_plane *plane;
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
-	/*
-	 * For transition only - we must wait for completion of our
-	 * untransitioned paths before changing anything.
-	 */
-	plane = dcrtc->plane;
-	if (plane)
-		WARN_ON(!armada_drm_plane_work_wait(drm_to_armada_plane(plane),
-						    HZ));
-
 	drm_crtc_vblank_off(crtc);
 	armada_drm_crtc_update(dcrtc, false);
 
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index afc9266bc1e2..5b607d45f469 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -35,29 +35,12 @@ struct armada_crtc;
 struct armada_plane;
 struct armada_variant;
 
-struct armada_plane_work {
-	void (*fn)(struct armada_crtc *, struct armada_plane_work *);
-	void (*cancel)(struct armada_crtc *, struct armada_plane_work *);
-	bool need_kfree;
-	struct drm_plane *plane;
-	struct drm_framebuffer *old_fb;
-	struct drm_pending_vblank_event *event;
-	struct armada_regs regs[24];
-};
-
 struct armada_plane {
 	struct drm_plane	base;
 	wait_queue_head_t	frame_wait;
-	struct armada_plane_work *work;
 };
 #define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
 
-int armada_drm_plane_work_queue(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work);
-int armada_drm_plane_work_wait(struct armada_plane *plane, long timeout);
-void armada_drm_plane_work_cancel(struct armada_crtc *dcrtc,
-	struct armada_plane *plane);
-
 struct armada_crtc {
 	struct drm_crtc		crtc;
 	const struct armada_variant *variant;
@@ -73,8 +56,6 @@ struct armada_crtc {
 	bool			interlaced;
 	bool			cursor_update;
 
-	struct drm_plane	*plane;
-
 	struct armada_gem_object	*cursor_obj;
 	int			cursor_x;
 	int			cursor_y;
diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index 7de8b6bd7847..ec2043b6f61f 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -27,9 +27,6 @@
 
 struct armada_ovl_plane {
 	struct armada_plane base;
-	struct armada_plane_work works[2];
-	bool next_work;
-	bool wait_vblank;
 };
 #define drm_to_armada_ovl_plane(p) \
 	container_of(p, struct armada_ovl_plane, base.base)
@@ -74,18 +71,6 @@ static inline u32 armada_csc(struct drm_plane_state *state)
 }
 
 /* === Plane support === */
-static void armada_ovl_plane_work(struct armada_crtc *dcrtc,
-	struct armada_plane_work *work)
-{
-	unsigned long flags;
-
-	trace_armada_ovl_plane_work(&dcrtc->crtc, work->plane);
-
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, work->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-}
-
 static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 	struct drm_plane_state *old_state)
 {
@@ -109,8 +94,6 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 	dcrtc = drm_to_armada_crtc(state->crtc);
 	regs = dcrtc->regs + dcrtc->regs_idx;
 
-	drm_to_armada_ovl_plane(plane)->wait_vblank = false;
-
 	idx = 0;
 	if (!old_state->visible && state->visible)
 		armada_reg_queue_mod(regs, idx,
@@ -173,8 +156,6 @@ static void armada_drm_overlay_plane_atomic_update(struct drm_plane *plane,
 				       CFG_SWAPYU | CFG_YUV2RGB) |
 			   CFG_DMA_FTOGGLE | CFG_DMA_TSTMODE |
 			   CFG_DMA_ENA;
-
-		drm_to_armada_ovl_plane(plane)->wait_vblank = true;
 	} else if (old_state->visible != state->visible) {
 		cfg = state->visible ? CFG_DMA_ENA : 0;
 		cfg_mask = CFG_DMA_ENA;
@@ -262,9 +243,6 @@ static void armada_drm_overlay_plane_atomic_disable(struct drm_plane *plane,
 			     LCD_SPU_SRAM_PARA1);
 
 	dcrtc->regs_idx += idx;
-
-	if (dcrtc->plane == plane)
-		dcrtc->plane = NULL;
 }
 
 static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = {
@@ -275,108 +253,50 @@ static const struct drm_plane_helper_funcs armada_overlay_plane_helper_funcs = {
 	.atomic_disable	= armada_drm_overlay_plane_atomic_disable,
 };
 
-static int armada_overlay_commit(struct drm_plane *plane,
-	struct drm_plane_state *state)
-{
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-	const struct drm_plane_helper_funcs *plane_funcs;
-	struct armada_crtc *dcrtc = drm_to_armada_crtc(state->crtc);
-	struct armada_plane_work *work;
-	int ret;
-
-	plane_funcs = plane->helper_private;
-	ret = plane_funcs->atomic_check(plane, state);
-	if (ret)
-		goto put_state;
-
-	work = &dplane->works[dplane->next_work];
-
-	if (plane->state->fb != state->fb) {
-		/*
-		 * Take a reference on the new framebuffer - we want to
-		 * hold on to it while the hardware is displaying it.
-		 */
-		drm_framebuffer_reference(state->fb);
-
-		work->old_fb = plane->state->fb;
-	} else {
-		work->old_fb = NULL;
-	}
-
-	/* Point of no return */
-	swap(plane->state, state);
-
-	/* No CRTC, can't update */
-	if (!plane->state->crtc)
-		goto put_state;
-
-	dcrtc->regs_idx = 0;
-	dcrtc->regs = work->regs;
-
-	plane_funcs->atomic_update(plane, state);
-
-	/* If nothing was updated, short-circuit */
-	if (dcrtc->regs_idx == 0)
-		goto put_state;
-
-	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
-
-	/* Wait for pending work to complete */
-	if (armada_drm_plane_work_wait(&dplane->base, HZ / 25) == 0)
-		armada_drm_plane_work_cancel(dcrtc, &dplane->base);
-
-	/* Just updating the position/size? */
-	if (!dplane->wait_vblank) {
-		armada_ovl_plane_work(dcrtc, work);
-		goto put_state;
-	}
-
-	dcrtc->plane = plane;
-
-	/* Queue it for update on the next interrupt if we are enabled */
-	ret = armada_drm_plane_work_queue(dcrtc, work);
-	if (ret) {
-		DRM_ERROR("failed to queue plane work: %d\n", ret);
-		ret = 0;
-	}
-
-	dplane->next_work = !dplane->next_work;
-
-put_state:
-	plane->funcs->atomic_destroy_state(plane, state);
-	return ret;
-}
-
 static int
-armada_ovl_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
+armada_overlay_plane_update(struct drm_plane *plane, struct drm_crtc *crtc,
 	struct drm_framebuffer *fb,
 	int crtc_x, int crtc_y, unsigned crtc_w, unsigned crtc_h,
 	uint32_t src_x, uint32_t src_y, uint32_t src_w, uint32_t src_h,
 	struct drm_modeset_acquire_ctx *ctx)
 {
-	struct drm_plane_state *state;
+	struct drm_atomic_state *state;
+	struct drm_plane_state *plane_state;
+	int ret = 0;
 
 	trace_armada_ovl_plane_update(plane, crtc, fb,
 				 crtc_x, crtc_y, crtc_w, crtc_h,
 				 src_x, src_y, src_w, src_h);
 
-	/* Construct new state for the overlay plane */
-	state = plane->funcs->atomic_duplicate_state(plane);
+	state = drm_atomic_state_alloc(plane->dev);
 	if (!state)
 		return -ENOMEM;
 
-	state->crtc = crtc;
-	drm_atomic_set_fb_for_plane(state, fb);
-	state->crtc_x = crtc_x;
-	state->crtc_y = crtc_y;
-	state->crtc_h = crtc_h;
-	state->crtc_w = crtc_w;
-	state->src_x = src_x;
-	state->src_y = src_y;
-	state->src_h = src_h;
-	state->src_w = src_w;
-
-	return armada_overlay_commit(plane, state);
+	state->acquire_ctx = ctx;
+	plane_state = drm_atomic_get_plane_state(state, plane);
+	if (IS_ERR(plane_state)) {
+		ret = PTR_ERR(plane_state);
+		goto fail;
+	}
+
+	ret = drm_atomic_set_crtc_for_plane(plane_state, crtc);
+	if (ret != 0)
+		goto fail;
+
+	drm_atomic_set_fb_for_plane(plane_state, fb);
+	plane_state->crtc_x = crtc_x;
+	plane_state->crtc_y = crtc_y;
+	plane_state->crtc_h = crtc_h;
+	plane_state->crtc_w = crtc_w;
+	plane_state->src_x = src_x;
+	plane_state->src_y = src_y;
+	plane_state->src_h = src_h;
+	plane_state->src_w = src_w;
+
+	ret = drm_atomic_nonblocking_commit(state);
+fail:
+	drm_atomic_state_put(state);
+	return ret;
 }
 
 static void armada_ovl_plane_destroy(struct drm_plane *plane)
@@ -388,25 +308,6 @@ static void armada_ovl_plane_destroy(struct drm_plane *plane)
 	kfree(dplane);
 }
 
-static int armada_ovl_plane_set_property(struct drm_plane *plane,
-	struct drm_property *property, uint64_t val)
-{
-	struct drm_plane_state *state;
-	int ret;
-
-	state = plane->funcs->atomic_duplicate_state(plane);
-	if (!state)
-		return -ENOMEM;
-
-	ret = plane->funcs->atomic_set_property(plane, state, property, val);
-	if (ret) {
-		plane->funcs->atomic_destroy_state(plane, state);
-		return ret;
-	}
-
-	return armada_overlay_commit(plane, state);
-}
-
 static void armada_overlay_reset(struct drm_plane *plane)
 {
 	struct armada_overlay_state *state;
@@ -510,9 +411,6 @@ static int armada_overlay_set_property(struct drm_plane *plane,
 		drm_to_overlay_state(state)->contrast = val;
 	} else if (property == priv->saturation_prop) {
 		drm_to_overlay_state(state)->saturation = val;
-	} else if (property == plane->color_encoding_property) {
-		/* transitional only */
-		state->color_encoding = val;
 	} else {
 		return -EINVAL;
 	}
@@ -572,10 +470,9 @@ static int armada_overlay_get_property(struct drm_plane *plane,
 }
 
 static const struct drm_plane_funcs armada_ovl_plane_funcs = {
-	.update_plane	= armada_ovl_plane_update,
-	.disable_plane	= drm_plane_helper_disable,
+	.update_plane	= armada_overlay_plane_update,
+	.disable_plane	= drm_atomic_helper_disable_plane,
 	.destroy	= armada_ovl_plane_destroy,
-	.set_property	= armada_ovl_plane_set_property,
 	.reset		= armada_overlay_reset,
 	.atomic_duplicate_state = armada_overlay_duplicate_state,
 	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
@@ -670,11 +567,6 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 		return ret;
 	}
 
-	dplane->works[0].plane = &dplane->base.base;
-	dplane->works[0].fn = armada_ovl_plane_work;
-	dplane->works[1].plane = &dplane->base.base;
-	dplane->works[1].fn = armada_ovl_plane_work;
-
 	drm_plane_helper_add(&dplane->base.base,
 			     &armada_overlay_plane_helper_funcs);
 
-- 
cgit v1.2.3


From 3cb13ac97bdfda5b301609256e3e0b59bc94f10a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: update planes after the dumb frame is complete

Write out the plane updates after the dumb frame has completed, but
just before the blank period.  This allows all the plane updates to
be performed in a flicker-free non-tearing manner.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c | 46 +++++++++++++++++++++---------------
 drivers/gpu/drm/armada/armada_crtc.h |  1 +
 2 files changed, 28 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index ebcb99316c94..bb1e13b4516b 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -197,21 +197,27 @@ static void armada_drm_crtc_irq(struct armada_crtc *dcrtc, u32 stat)
 		writel_relaxed(val, base + LCD_SPU_ADV_REG);
 	}
 
-	if (stat & DUMB_FRAMEDONE && dcrtc->cursor_update) {
-		writel_relaxed(dcrtc->cursor_hw_pos,
-			       base + LCD_SPU_HWC_OVSA_HPXL_VLN);
-		writel_relaxed(dcrtc->cursor_hw_sz,
-			       base + LCD_SPU_HWC_HPXL_VLN);
-		armada_updatel(CFG_HWC_ENA,
-			       CFG_HWC_ENA | CFG_HWC_1BITMOD | CFG_HWC_1BITENA,
-			       base + LCD_SPU_DMA_CTRL0);
-		dcrtc->cursor_update = false;
+	if (stat & dcrtc->irq_ena & DUMB_FRAMEDONE) {
+		if (dcrtc->update_pending) {
+			armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
+			dcrtc->update_pending = false;
+		}
+		if (dcrtc->cursor_update) {
+			writel_relaxed(dcrtc->cursor_hw_pos,
+				       base + LCD_SPU_HWC_OVSA_HPXL_VLN);
+			writel_relaxed(dcrtc->cursor_hw_sz,
+				       base + LCD_SPU_HWC_HPXL_VLN);
+			armada_updatel(CFG_HWC_ENA,
+				       CFG_HWC_ENA | CFG_HWC_1BITMOD |
+				       CFG_HWC_1BITENA,
+				       base + LCD_SPU_DMA_CTRL0);
+			dcrtc->cursor_update = false;
+		}
 		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 	}
-
 	spin_unlock(&dcrtc->irq_lock);
 
-	if (stat & VSYNC_IRQ) {
+	if (stat & VSYNC_IRQ && !dcrtc->update_pending) {
 		event = xchg(&dcrtc->event, NULL);
 		if (event) {
 			spin_lock(&dcrtc->crtc.dev->event_lock);
@@ -360,22 +366,26 @@ static void armada_drm_crtc_atomic_flush(struct drm_crtc *crtc,
 					 struct drm_crtc_state *old_crtc_state)
 {
 	struct armada_crtc *dcrtc = drm_to_armada_crtc(crtc);
-	unsigned long flags;
 
 	DRM_DEBUG_KMS("[CRTC:%d:%s]\n", crtc->base.id, crtc->name);
 
 	armada_reg_queue_end(dcrtc->regs, dcrtc->regs_idx);
 
-	spin_lock_irqsave(&dcrtc->irq_lock, flags);
-	armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
-	spin_unlock_irqrestore(&dcrtc->irq_lock, flags);
-
 	/*
 	 * If we aren't doing a full modeset, then we need to queue
 	 * the event here.
 	 */
-	if (!drm_atomic_crtc_needs_modeset(crtc->state))
+	if (!drm_atomic_crtc_needs_modeset(crtc->state)) {
+		dcrtc->update_pending = true;
 		armada_drm_crtc_queue_state_event(crtc);
+		spin_lock_irq(&dcrtc->irq_lock);
+		armada_drm_crtc_enable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
+		spin_unlock_irq(&dcrtc->irq_lock);
+	} else {
+		spin_lock_irq(&dcrtc->irq_lock);
+		armada_drm_crtc_update_regs(dcrtc, dcrtc->regs);
+		spin_unlock_irq(&dcrtc->irq_lock);
+	}
 }
 
 static void armada_drm_crtc_atomic_disable(struct drm_crtc *crtc,
@@ -532,7 +542,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload)
 
 	if (!dcrtc->cursor_obj || !h || !w) {
 		spin_lock_irq(&dcrtc->irq_lock);
-		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 		dcrtc->cursor_update = false;
 		armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
 		spin_unlock_irq(&dcrtc->irq_lock);
@@ -556,7 +565,6 @@ static int armada_drm_crtc_cursor_update(struct armada_crtc *dcrtc, bool reload)
 
 	if (dcrtc->cursor_hw_sz != (h << 16 | w)) {
 		spin_lock_irq(&dcrtc->irq_lock);
-		armada_drm_crtc_disable_irq(dcrtc, DUMB_FRAMEDONE_ENA);
 		dcrtc->cursor_update = false;
 		armada_updatel(0, CFG_HWC_ENA, dcrtc->base + LCD_SPU_DMA_CTRL0);
 		spin_unlock_irq(&dcrtc->irq_lock);
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index 5b607d45f469..b95ea13d0705 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -70,6 +70,7 @@ struct armada_crtc {
 	spinlock_t		irq_lock;
 	uint32_t		irq_ena;
 
+	bool			update_pending;
 	struct drm_pending_vblank_event *event;
 	struct armada_regs	atomic_regs[32];
 	struct armada_regs	*regs;
-- 
cgit v1.2.3


From dae2155bb07bb2063ce604049e9aa4e862b6db0a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: update primary framebuffer parameters on mode change

The framebuffer base address and toggling mode needs to be updated
when the interlaced flag for mode changes is updated.  Arrange to
reprogram these parameters when only the mode has changed.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_plane.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index 39c9ba3ee57e..bed2dca83a37 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -184,11 +184,13 @@ static void armada_drm_primary_plane_atomic_update(struct drm_plane *plane,
 		armada_reg_queue_set(regs, idx, val, LCD_SPU_GZM_HPXL_VLN);
 	if (old_state->src.x1 != state->src.x1 ||
 	    old_state->src.y1 != state->src.y1 ||
-	    old_state->fb != state->fb) {
+	    old_state->fb != state->fb ||
+	    state->crtc->state->mode_changed) {
 		idx += armada_drm_crtc_calc_fb(state, regs + idx,
 					       dcrtc->interlaced);
 	}
-	if (old_state->fb != state->fb) {
+	if (old_state->fb != state->fb ||
+	    state->crtc->state->mode_changed) {
 		cfg = CFG_GRA_FMT(drm_fb_to_armada_fb(state->fb)->fmt) |
 		      CFG_GRA_MOD(drm_fb_to_armada_fb(state->fb)->mod);
 		if (drm_fb_to_armada_fb(state->fb)->fmt > CFG_420)
-- 
cgit v1.2.3


From d701278ada5115c40cd4d58ce0fb1169479c0bf6 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: remove unnecessary armada_ovl_plane structure

We no longer need a private plane structure, so get rid of it.  Use the
drm_plane structure directly.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_overlay.c | 34 +++++++++------------------------
 1 file changed, 9 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_overlay.c b/drivers/gpu/drm/armada/armada_overlay.c
index ec2043b6f61f..eb7dfb65ef47 100644
--- a/drivers/gpu/drm/armada/armada_overlay.c
+++ b/drivers/gpu/drm/armada/armada_overlay.c
@@ -25,12 +25,6 @@
 #define DEFAULT_SATURATION	0x4000
 #define DEFAULT_ENCODING	DRM_COLOR_YCBCR_BT601
 
-struct armada_ovl_plane {
-	struct armada_plane base;
-};
-#define drm_to_armada_ovl_plane(p) \
-	container_of(p, struct armada_ovl_plane, base.base)
-
 struct armada_overlay_state {
 	struct drm_plane_state base;
 	u32 colorkey_yr;
@@ -301,11 +295,8 @@ fail:
 
 static void armada_ovl_plane_destroy(struct drm_plane *plane)
 {
-	struct armada_ovl_plane *dplane = drm_to_armada_ovl_plane(plane);
-
 	drm_plane_cleanup(plane);
-
-	kfree(dplane);
+	kfree(plane);
 }
 
 static void armada_overlay_reset(struct drm_plane *plane)
@@ -550,38 +541,31 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 {
 	struct armada_private *priv = dev->dev_private;
 	struct drm_mode_object *mobj;
-	struct armada_ovl_plane *dplane;
+	struct drm_plane *overlay;
 	int ret;
 
 	ret = armada_overlay_create_properties(dev);
 	if (ret)
 		return ret;
 
-	dplane = kzalloc(sizeof(*dplane), GFP_KERNEL);
-	if (!dplane)
+	overlay = kzalloc(sizeof(*overlay), GFP_KERNEL);
+	if (!overlay)
 		return -ENOMEM;
 
-	ret = armada_drm_plane_init(&dplane->base);
-	if (ret) {
-		kfree(dplane);
-		return ret;
-	}
-
-	drm_plane_helper_add(&dplane->base.base,
-			     &armada_overlay_plane_helper_funcs);
+	drm_plane_helper_add(overlay, &armada_overlay_plane_helper_funcs);
 
-	ret = drm_universal_plane_init(dev, &dplane->base.base, crtcs,
+	ret = drm_universal_plane_init(dev, overlay, crtcs,
 				       &armada_ovl_plane_funcs,
 				       armada_ovl_formats,
 				       ARRAY_SIZE(armada_ovl_formats),
 				       NULL,
 				       DRM_PLANE_TYPE_OVERLAY, NULL);
 	if (ret) {
-		kfree(dplane);
+		kfree(overlay);
 		return ret;
 	}
 
-	mobj = &dplane->base.base.base;
+	mobj = &overlay->base;
 	drm_object_attach_property(mobj, priv->colorkey_prop,
 				   0x0101fe);
 	drm_object_attach_property(mobj, priv->colorkey_min_prop,
@@ -601,7 +585,7 @@ int armada_overlay_plane_create(struct drm_device *dev, unsigned long crtcs)
 	drm_object_attach_property(mobj, priv->saturation_prop,
 				   DEFAULT_SATURATION);
 
-	ret = drm_plane_create_color_properties(&dplane->base.base,
+	ret = drm_plane_create_color_properties(overlay,
 						BIT(DRM_COLOR_YCBCR_BT601) |
 						BIT(DRM_COLOR_YCBCR_BT709),
 						BIT(DRM_COLOR_YCBCR_LIMITED_RANGE),
-- 
cgit v1.2.3


From 82c702cb0c041a9a1c69f489d1517235a633fc77 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: remove unnecessary armada_plane structure

We no longer require a private armada_plane structure, so eliminate
it, and use the drm_plane structure directly.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_crtc.c  |  6 +++---
 drivers/gpu/drm/armada/armada_crtc.h  |  7 -------
 drivers/gpu/drm/armada/armada_plane.c | 17 +++--------------
 drivers/gpu/drm/armada/armada_plane.h |  3 +--
 4 files changed, 7 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_crtc.c b/drivers/gpu/drm/armada/armada_crtc.c
index bb1e13b4516b..da9360688b55 100644
--- a/drivers/gpu/drm/armada/armada_crtc.c
+++ b/drivers/gpu/drm/armada/armada_crtc.c
@@ -723,7 +723,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 {
 	struct armada_private *priv = drm->dev_private;
 	struct armada_crtc *dcrtc;
-	struct armada_plane *primary;
+	struct drm_plane *primary;
 	void __iomem *base;
 	int ret;
 
@@ -793,7 +793,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 		goto err_crtc;
 	}
 
-	ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, &primary->base, NULL,
+	ret = drm_crtc_init_with_planes(drm, &dcrtc->crtc, primary, NULL,
 					&armada_crtc_funcs, NULL);
 	if (ret)
 		goto err_crtc_init;
@@ -803,7 +803,7 @@ static int armada_drm_crtc_create(struct drm_device *drm, struct device *dev,
 	return armada_overlay_plane_create(drm, 1 << dcrtc->num);
 
 err_crtc_init:
-	primary->base.funcs->destroy(&primary->base);
+	primary->funcs->destroy(primary);
 err_crtc:
 	kfree(dcrtc);
 
diff --git a/drivers/gpu/drm/armada/armada_crtc.h b/drivers/gpu/drm/armada/armada_crtc.h
index b95ea13d0705..7ebd337b60af 100644
--- a/drivers/gpu/drm/armada/armada_crtc.h
+++ b/drivers/gpu/drm/armada/armada_crtc.h
@@ -32,15 +32,8 @@ struct armada_regs {
 	armada_reg_queue_mod(_r, _i, 0, 0, ~0)
 
 struct armada_crtc;
-struct armada_plane;
 struct armada_variant;
 
-struct armada_plane {
-	struct drm_plane	base;
-	wait_queue_head_t	frame_wait;
-};
-#define drm_to_armada_plane(p) container_of(p, struct armada_plane, base)
-
 struct armada_crtc {
 	struct drm_crtc		crtc;
 	const struct armada_variant *variant;
diff --git a/drivers/gpu/drm/armada/armada_plane.c b/drivers/gpu/drm/armada/armada_plane.c
index bed2dca83a37..9f36423dd394 100644
--- a/drivers/gpu/drm/armada/armada_plane.c
+++ b/drivers/gpu/drm/armada/armada_plane.c
@@ -271,25 +271,14 @@ static const struct drm_plane_funcs armada_primary_plane_funcs = {
 	.atomic_destroy_state = drm_atomic_helper_plane_destroy_state,
 };
 
-int armada_drm_plane_init(struct armada_plane *plane)
-{
-	init_waitqueue_head(&plane->frame_wait);
-	return 0;
-}
-
 int armada_drm_primary_plane_init(struct drm_device *drm,
-	struct armada_plane *primary)
+	struct drm_plane *primary)
 {
 	int ret;
 
-	ret = armada_drm_plane_init(primary);
-	if (ret)
-		return ret;
-
-	drm_plane_helper_add(&primary->base,
-			     &armada_primary_plane_helper_funcs);
+	drm_plane_helper_add(primary, &armada_primary_plane_helper_funcs);
 
-	ret = drm_universal_plane_init(drm, &primary->base, 0,
+	ret = drm_universal_plane_init(drm, primary, 0,
 				       &armada_primary_plane_funcs,
 				       armada_primary_formats,
 				       ARRAY_SIZE(armada_primary_formats),
diff --git a/drivers/gpu/drm/armada/armada_plane.h b/drivers/gpu/drm/armada/armada_plane.h
index 1bd8430992e0..ff4281ba7fad 100644
--- a/drivers/gpu/drm/armada/armada_plane.h
+++ b/drivers/gpu/drm/armada/armada_plane.h
@@ -9,8 +9,7 @@ void armada_drm_plane_cleanup_fb(struct drm_plane *plane,
 	struct drm_plane_state *old_state);
 int armada_drm_plane_atomic_check(struct drm_plane *plane,
 	struct drm_plane_state *state);
-int armada_drm_plane_init(struct armada_plane *plane);
 int armada_drm_primary_plane_init(struct drm_device *drm,
-	struct armada_plane *primary);
+	struct drm_plane *primary);
 
 #endif
-- 
cgit v1.2.3


From aa595c00bcf5b6f2f394a98217f82c9402952ea9 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 30 Jul 2018 11:53:06 +0100
Subject: drm/armada: remove obsolete fb unreferencing kfifo and workqueue

Remove the obsolete fb unreferencing system that is no longer used
since we've transitioned to atomic modeset.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/armada/armada_drm.h |  7 -------
 drivers/gpu/drm/armada/armada_drv.c | 35 -----------------------------------
 2 files changed, 42 deletions(-)

diff --git a/drivers/gpu/drm/armada/armada_drm.h b/drivers/gpu/drm/armada/armada_drm.h
index 9658be917ea1..f09083ff15d3 100644
--- a/drivers/gpu/drm/armada/armada_drm.h
+++ b/drivers/gpu/drm/armada/armada_drm.h
@@ -55,8 +55,6 @@ extern const struct armada_variant armada510_ops;
 
 struct armada_private {
 	struct drm_device	drm;
-	struct work_struct	fb_unref_work;
-	DECLARE_KFIFO(fb_unref, struct drm_framebuffer *, 8);
 	struct drm_fb_helper	*fbdev;
 	struct armada_crtc	*dcrtc[2];
 	struct drm_mm		linear; /* protected by linear_lock */
@@ -75,11 +73,6 @@ struct armada_private {
 #endif
 };
 
-void __armada_drm_queue_unref_work(struct drm_device *,
-	struct drm_framebuffer *);
-void armada_drm_queue_unref_work(struct drm_device *,
-	struct drm_framebuffer *);
-
 int armada_fbdev_init(struct drm_device *);
 void armada_fbdev_fini(struct drm_device *);
 
diff --git a/drivers/gpu/drm/armada/armada_drv.c b/drivers/gpu/drm/armada/armada_drv.c
index 20661bd9001e..fa31589b4fc0 100644
--- a/drivers/gpu/drm/armada/armada_drv.c
+++ b/drivers/gpu/drm/armada/armada_drv.c
@@ -21,36 +21,6 @@
 #include <drm/armada_drm.h>
 #include "armada_ioctlP.h"
 
-static void armada_drm_unref_work(struct work_struct *work)
-{
-	struct armada_private *priv =
-		container_of(work, struct armada_private, fb_unref_work);
-	struct drm_framebuffer *fb;
-
-	while (kfifo_get(&priv->fb_unref, &fb))
-		drm_framebuffer_put(fb);
-}
-
-/* Must be called with dev->event_lock held */
-void __armada_drm_queue_unref_work(struct drm_device *dev,
-	struct drm_framebuffer *fb)
-{
-	struct armada_private *priv = dev->dev_private;
-
-	WARN_ON(!kfifo_put(&priv->fb_unref, fb));
-	schedule_work(&priv->fb_unref_work);
-}
-
-void armada_drm_queue_unref_work(struct drm_device *dev,
-	struct drm_framebuffer *fb)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&dev->event_lock, flags);
-	__armada_drm_queue_unref_work(dev, fb);
-	spin_unlock_irqrestore(&dev->event_lock, flags);
-}
-
 static struct drm_ioctl_desc armada_ioctls[] = {
 	DRM_IOCTL_DEF_DRV(ARMADA_GEM_CREATE, armada_gem_create_ioctl,0),
 	DRM_IOCTL_DEF_DRV(ARMADA_GEM_MMAP, armada_gem_mmap_ioctl, 0),
@@ -134,9 +104,6 @@ static int armada_drm_bind(struct device *dev)
 
 	dev_set_drvdata(dev, &priv->drm);
 
-	INIT_WORK(&priv->fb_unref_work, armada_drm_unref_work);
-	INIT_KFIFO(priv->fb_unref);
-
 	/* Mode setting support */
 	drm_mode_config_init(&priv->drm);
 	priv->drm.mode_config.min_width = 320;
@@ -190,7 +157,6 @@ static int armada_drm_bind(struct device *dev)
  err_kms:
 	drm_mode_config_cleanup(&priv->drm);
 	drm_mm_takedown(&priv->linear);
-	flush_work(&priv->fb_unref_work);
 	drm_dev_put(&priv->drm);
 	return ret;
 }
@@ -209,7 +175,6 @@ static void armada_drm_unbind(struct device *dev)
 
 	drm_mode_config_cleanup(&priv->drm);
 	drm_mm_takedown(&priv->linear);
-	flush_work(&priv->fb_unref_work);
 
 	drm_dev_put(&priv->drm);
 }
-- 
cgit v1.2.3


From c79bdbb490a1d05c6169cbffd37c19f5aa96587a Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Fri, 27 Jul 2018 21:53:54 +0200
Subject: spi: dw: export dw_spi_set_cs

Export dw_spi_set_cs so it can be used from the various IP integration
modules.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-dw.c | 3 ++-
 drivers/spi/spi-dw.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-dw.c b/drivers/spi/spi-dw.c
index 0d8ccb8be5ec..683a4f137a25 100644
--- a/drivers/spi/spi-dw.c
+++ b/drivers/spi/spi-dw.c
@@ -133,7 +133,7 @@ static inline void dw_spi_debugfs_remove(struct dw_spi *dws)
 }
 #endif /* CONFIG_DEBUG_FS */
 
-static void dw_spi_set_cs(struct spi_device *spi, bool enable)
+void dw_spi_set_cs(struct spi_device *spi, bool enable)
 {
 	struct dw_spi *dws = spi_controller_get_devdata(spi->controller);
 	struct chip_data *chip = spi_get_ctldata(spi);
@@ -145,6 +145,7 @@ static void dw_spi_set_cs(struct spi_device *spi, bool enable)
 	if (!enable)
 		dw_writel(dws, DW_SPI_SER, BIT(spi->chip_select));
 }
+EXPORT_SYMBOL_GPL(dw_spi_set_cs);
 
 /* Return the max entries we can fill into tx fifo */
 static inline u32 tx_max(struct dw_spi *dws)
diff --git a/drivers/spi/spi-dw.h b/drivers/spi/spi-dw.h
index 446013022849..0168b08364d5 100644
--- a/drivers/spi/spi-dw.h
+++ b/drivers/spi/spi-dw.h
@@ -245,6 +245,7 @@ struct dw_spi_chip {
 	void (*cs_control)(u32 command);
 };
 
+extern void dw_spi_set_cs(struct spi_device *spi, bool enable);
 extern int dw_spi_add_host(struct device *dev, struct dw_spi *dws);
 extern void dw_spi_remove_host(struct dw_spi *dws);
 extern int dw_spi_suspend_host(struct dw_spi *dws);
-- 
cgit v1.2.3


From c2c25cc397026ec705e050248539df400d2563f8 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Fri, 27 Jul 2018 21:53:56 +0200
Subject: spi: dw-mmio: add MSCC Ocelot support

Because the SPI controller deasserts the chip select when the TX fifo is
empty (which may happen in the middle of a transfer), the CS should be
handled by linux. Unfortunately, some or all of the first four chip
selects are not muxable as GPIOs, depending on the SoC.

There is a way to bitbang those pins by using the SPI boot controller so
use it to set the chip selects.

At init time, it is also necessary to give control of the SPI interface to
the Designware IP.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-dw-mmio.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 90 insertions(+)

diff --git a/drivers/spi/spi-dw-mmio.c b/drivers/spi/spi-dw-mmio.c
index d25cc4037e23..e80f60ed6fdf 100644
--- a/drivers/spi/spi-dw-mmio.c
+++ b/drivers/spi/spi-dw-mmio.c
@@ -15,11 +15,13 @@
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
 #include <linux/scatterlist.h>
+#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_gpio.h>
 #include <linux/of_platform.h>
 #include <linux/property.h>
+#include <linux/regmap.h>
 
 #include "spi-dw.h"
 
@@ -28,10 +30,90 @@
 struct dw_spi_mmio {
 	struct dw_spi  dws;
 	struct clk     *clk;
+	void           *priv;
 };
 
+#define MSCC_CPU_SYSTEM_CTRL_GENERAL_CTRL	0x24
+#define OCELOT_IF_SI_OWNER_MASK			GENMASK(5, 4)
+#define OCELOT_IF_SI_OWNER_OFFSET		4
+#define MSCC_IF_SI_OWNER_SISL			0
+#define MSCC_IF_SI_OWNER_SIBM			1
+#define MSCC_IF_SI_OWNER_SIMC			2
+
+#define MSCC_SPI_MST_SW_MODE			0x14
+#define MSCC_SPI_MST_SW_MODE_SW_PIN_CTRL_MODE	BIT(13)
+#define MSCC_SPI_MST_SW_MODE_SW_SPI_CS(x)	(x << 5)
+
+struct dw_spi_mscc {
+	struct regmap       *syscon;
+	void __iomem        *spi_mst;
+};
+
+/*
+ * The Designware SPI controller (referred to as master in the documentation)
+ * automatically deasserts chip select when the tx fifo is empty. The chip
+ * selects then needs to be either driven as GPIOs or, for the first 4 using the
+ * the SPI boot controller registers. the final chip select is an OR gate
+ * between the Designware SPI controller and the SPI boot controller.
+ */
+static void dw_spi_mscc_set_cs(struct spi_device *spi, bool enable)
+{
+	struct dw_spi *dws = spi_master_get_devdata(spi->master);
+	struct dw_spi_mmio *dwsmmio = container_of(dws, struct dw_spi_mmio, dws);
+	struct dw_spi_mscc *dwsmscc = dwsmmio->priv;
+	u32 cs = spi->chip_select;
+
+	if (cs < 4) {
+		u32 sw_mode = MSCC_SPI_MST_SW_MODE_SW_PIN_CTRL_MODE;
+
+		if (!enable)
+			sw_mode |= MSCC_SPI_MST_SW_MODE_SW_SPI_CS(BIT(cs));
+
+		writel(sw_mode, dwsmscc->spi_mst + MSCC_SPI_MST_SW_MODE);
+	}
+
+	dw_spi_set_cs(spi, enable);
+}
+
+static int dw_spi_mscc_init(struct platform_device *pdev,
+			    struct dw_spi_mmio *dwsmmio)
+{
+	struct dw_spi_mscc *dwsmscc;
+	struct resource *res;
+
+	dwsmscc = devm_kzalloc(&pdev->dev, sizeof(*dwsmscc), GFP_KERNEL);
+	if (!dwsmscc)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	dwsmscc->spi_mst = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(dwsmscc->spi_mst)) {
+		dev_err(&pdev->dev, "SPI_MST region map failed\n");
+		return PTR_ERR(dwsmscc->spi_mst);
+	}
+
+	dwsmscc->syscon = syscon_regmap_lookup_by_compatible("mscc,ocelot-cpu-syscon");
+	if (IS_ERR(dwsmscc->syscon))
+		return PTR_ERR(dwsmscc->syscon);
+
+	/* Deassert all CS */
+	writel(0, dwsmscc->spi_mst + MSCC_SPI_MST_SW_MODE);
+
+	/* Select the owner of the SI interface */
+	regmap_update_bits(dwsmscc->syscon, MSCC_CPU_SYSTEM_CTRL_GENERAL_CTRL,
+			   OCELOT_IF_SI_OWNER_MASK,
+			   MSCC_IF_SI_OWNER_SIMC << OCELOT_IF_SI_OWNER_OFFSET);
+
+	dwsmmio->dws.set_cs = dw_spi_mscc_set_cs;
+	dwsmmio->priv = dwsmscc;
+
+	return 0;
+}
+
 static int dw_spi_mmio_probe(struct platform_device *pdev)
 {
+	int (*init_func)(struct platform_device *pdev,
+			 struct dw_spi_mmio *dwsmmio);
 	struct dw_spi_mmio *dwsmmio;
 	struct dw_spi *dws;
 	struct resource *mem;
@@ -99,6 +181,13 @@ static int dw_spi_mmio_probe(struct platform_device *pdev)
 		}
 	}
 
+	init_func = device_get_match_data(&pdev->dev);
+	if (init_func) {
+		ret = init_func(pdev, dwsmmio);
+		if (ret)
+			goto out;
+	}
+
 	ret = dw_spi_add_host(&pdev->dev, dws);
 	if (ret)
 		goto out;
@@ -123,6 +212,7 @@ static int dw_spi_mmio_remove(struct platform_device *pdev)
 
 static const struct of_device_id dw_spi_mmio_of_match[] = {
 	{ .compatible = "snps,dw-apb-ssi", },
+	{ .compatible = "mscc,ocelot-spi", .data = dw_spi_mscc_init},
 	{ /* end of table */}
 };
 MODULE_DEVICE_TABLE(of, dw_spi_mmio_of_match);
-- 
cgit v1.2.3


From 345a9ca37aa69bb3133c1a8390a71f993abcef0c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 30 Jul 2018 08:46:40 +0200
Subject: ALSA: memalloc: Fix missing PAGE_SIZE definition

The recent fix moved the inline snd_sgbuf_aligned_pages() outside the
ifdef, and this triggered a build error on some architectures due to
the undefined PAGE_SIZE, as spotted by 0day bot.
Fix it by adding the missing header inclusion.

Fixes: 4cae99d9b530 ("ALSA: memalloc: declare snd_sgbuf_aligned_pages() unconditionally")
Reported-by: kbuild test robot <lkp@intel.com>
Cc: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/memalloc.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/include/sound/memalloc.h b/include/sound/memalloc.h
index c669900e6cbe..67561b997915 100644
--- a/include/sound/memalloc.h
+++ b/include/sound/memalloc.h
@@ -24,6 +24,8 @@
 #ifndef __SOUND_MEMALLOC_H
 #define __SOUND_MEMALLOC_H
 
+#include <asm/page.h>
+
 struct device;
 
 /*
-- 
cgit v1.2.3


From fe209b97184f577b70ae0799c2b149be36092f84 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 30 Jul 2018 07:51:41 +0000
Subject: ASoC: ak4642: convert to SPDX identifiers

As original license mentioned, it is GPL-2.0 in SPDX.
Then, MODULE_LICENSE() should be "GPL v2" instead of "GPL".
See ${LINUX}/include/linux/module.h

	"GPL"           [GNU Public License v2 or later]
	"GPL v2"        [GNU Public License v2]

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/ak4642.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/sound/soc/codecs/ak4642.c b/sound/soc/codecs/ak4642.c
index 605055964529..353237025514 100644
--- a/sound/soc/codecs/ak4642.c
+++ b/sound/soc/codecs/ak4642.c
@@ -1,17 +1,13 @@
-/*
- * ak4642.c  --  AK4642/AK4643 ALSA Soc Audio driver
- *
- * Copyright (C) 2009 Renesas Solutions Corp.
- * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * Based on wm8731.c by Richard Purdie
- * Based on ak4535.c by Richard Purdie
- * Based on wm8753.c by Liam Girdwood
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ak4642.c  --  AK4642/AK4643 ALSA Soc Audio driver
+//
+// Copyright (C) 2009 Renesas Solutions Corp.
+// Kuninori Morimoto <morimoto.kuninori@renesas.com>
+//
+// Based on wm8731.c by Richard Purdie
+// Based on ak4535.c by Richard Purdie
+// Based on wm8753.c by Liam Girdwood
 
 /* ** CAUTION **
  *
@@ -709,4 +705,4 @@ module_i2c_driver(ak4642_i2c_driver);
 
 MODULE_DESCRIPTION("Soc AK4642 driver");
 MODULE_AUTHOR("Kuninori Morimoto <morimoto.kuninori@renesas.com>");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 7a968dc66aecaaea3424ca2525b758687b39bc0e Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 30 Jul 2018 07:52:15 +0000
Subject: ASoC: ak4554: convert to SPDX identifiers

As original license mentioned, it is GPL-2.0 in SPDX.
Then, MODULE_LICENSE() should be "GPL v2" instead of "GPL".
See ${LINUX}/include/linux/module.h

	"GPL"           [GNU Public License v2 or later]
	"GPL v2"        [GNU Public License v2]

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/ak4554.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/sound/soc/codecs/ak4554.c b/sound/soc/codecs/ak4554.c
index b7ee13406d93..2fa83a1a84cf 100644
--- a/sound/soc/codecs/ak4554.c
+++ b/sound/soc/codecs/ak4554.c
@@ -1,13 +1,8 @@
-/*
- * ak4554.c
- *
- * Copyright (C) 2013 Renesas Solutions Corp.
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+// ak4554.c
+//
+// Copyright (C) 2013 Renesas Solutions Corp.
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 
 #include <linux/module.h>
 #include <sound/soc.h>
@@ -97,6 +92,6 @@ static struct platform_driver ak4554_driver = {
 };
 module_platform_driver(ak4554_driver);
 
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("SoC AK4554 driver");
 MODULE_AUTHOR("Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>");
-- 
cgit v1.2.3


From c0ca5604d43233b0f5cfb793be9638af21f5535d Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 30 Jul 2018 07:52:46 +0000
Subject: ASoC: da7210: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/da7210.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/sound/soc/codecs/da7210.c b/sound/soc/codecs/da7210.c
index a664111b7184..e172913d04a4 100644
--- a/sound/soc/codecs/da7210.c
+++ b/sound/soc/codecs/da7210.c
@@ -1,19 +1,14 @@
-/*
- * DA7210 ALSA Soc codec driver
- *
- * Copyright (c) 2009 Dialog Semiconductor
- * Written by David Chen <Dajun.chen@diasemi.com>
- *
- * Copyright (C) 2009 Renesas Solutions Corp.
- * Cleanups by Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * Tested on SuperH Ecovec24 board with S16/S24 LE in 48KHz using I2S
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// DA7210 ALSA Soc codec driver
+//
+// Copyright (c) 2009 Dialog Semiconductor
+// Written by David Chen <Dajun.chen@diasemi.com>
+//
+// Copyright (C) 2009 Renesas Solutions Corp.
+// Cleanups by Kuninori Morimoto <morimoto.kuninori@renesas.com>
+//
+// Tested on SuperH Ecovec24 board with S16/S24 LE in 48KHz using I2S
 
 #include <linux/delay.h>
 #include <linux/i2c.h>
-- 
cgit v1.2.3


From e028937c77f44bb38cdbc464afce2bf41d96006b Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 30 Jul 2018 07:53:08 +0000
Subject: ASoC: ak4613: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/ak4613.c | 26 +++++++++++---------------
 1 file changed, 11 insertions(+), 15 deletions(-)

diff --git a/sound/soc/codecs/ak4613.c b/sound/soc/codecs/ak4613.c
index 8523ff9351cf..c1181a20714d 100644
--- a/sound/soc/codecs/ak4613.c
+++ b/sound/soc/codecs/ak4613.c
@@ -1,18 +1,14 @@
-/*
- * ak4613.c  --  Asahi Kasei ALSA Soc Audio driver
- *
- * Copyright (C) 2015 Renesas Electronics Corporation
- * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * Based on ak4642.c by Kuninori Morimoto
- * Based on wm8731.c by Richard Purdie
- * Based on ak4535.c by Richard Purdie
- * Based on wm8753.c by Liam Girdwood
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
+// SPDX-License-Identifier: GPL-2.0
+//
+// ak4613.c  --  Asahi Kasei ALSA Soc Audio driver
+//
+// Copyright (C) 2015 Renesas Electronics Corporation
+// Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
+//
+// Based on ak4642.c by Kuninori Morimoto
+// Based on wm8731.c by Richard Purdie
+// Based on ak4535.c by Richard Purdie
+// Based on wm8753.c by Liam Girdwood
 
 #include <linux/clk.h>
 #include <linux/delay.h>
-- 
cgit v1.2.3


From 7464d3faf62a5adcb99f4f8ea9baabda78aed4aa Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 30 Jul 2018 08:00:22 +0000
Subject: ASoC: sh: Kconfig: convert to SPDX identifiers

By default all files without license information are under the default
license of the kernel, which is GPL version 2.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sh/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/sh/Kconfig b/sound/soc/sh/Kconfig
index 0ae0800bf3a8..dc20f0f7080a 100644
--- a/sound/soc/sh/Kconfig
+++ b/sound/soc/sh/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 menu "SoC Audio support for Renesas SoCs"
 	depends on SUPERH || ARCH_RENESAS || COMPILE_TEST
 
-- 
cgit v1.2.3


From 4321723648b0abb456f7a9af51bb09a4ec60799d Mon Sep 17 00:00:00 2001
From: Alexey Khoroshilov <khoroshilov@ispras.ru>
Date: Sat, 28 Jul 2018 00:06:59 +0300
Subject: ASoC: tegra_alc5632: fix device_node refcounting

tegra_alc5632_probe() increments reference count of device nodes
with of_parse_phandle(), but there is no code decrementing them
in the driver.

The patch adds of_node_put() to tegra_alc5632_remove() and
to error handling paths in the probe.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Alexey Khoroshilov <khoroshilov@ispras.ru>
Acked-by: Jon Hunter <jonathanh@nvidia.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/tegra/tegra_alc5632.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/sound/soc/tegra/tegra_alc5632.c b/sound/soc/tegra/tegra_alc5632.c
index 5197d6b18cb6..98d87801d57a 100644
--- a/sound/soc/tegra/tegra_alc5632.c
+++ b/sound/soc/tegra/tegra_alc5632.c
@@ -190,14 +190,14 @@ static int tegra_alc5632_probe(struct platform_device *pdev)
 		dev_err(&pdev->dev,
 			"Property 'nvidia,i2s-controller' missing or invalid\n");
 		ret = -EINVAL;
-		goto err;
+		goto err_put_codec_of_node;
 	}
 
 	tegra_alc5632_dai.platform_of_node = tegra_alc5632_dai.cpu_of_node;
 
 	ret = tegra_asoc_utils_init(&alc5632->util_data, &pdev->dev);
 	if (ret)
-		goto err;
+		goto err_put_cpu_of_node;
 
 	ret = snd_soc_register_card(card);
 	if (ret) {
@@ -210,6 +210,13 @@ static int tegra_alc5632_probe(struct platform_device *pdev)
 
 err_fini_utils:
 	tegra_asoc_utils_fini(&alc5632->util_data);
+err_put_cpu_of_node:
+	of_node_put(tegra_alc5632_dai.cpu_of_node);
+	tegra_alc5632_dai.cpu_of_node = NULL;
+	tegra_alc5632_dai.platform_of_node = NULL;
+err_put_codec_of_node:
+	of_node_put(tegra_alc5632_dai.codec_of_node);
+	tegra_alc5632_dai.codec_of_node = NULL;
 err:
 	return ret;
 }
@@ -223,6 +230,12 @@ static int tegra_alc5632_remove(struct platform_device *pdev)
 
 	tegra_asoc_utils_fini(&machine->util_data);
 
+	of_node_put(tegra_alc5632_dai.cpu_of_node);
+	tegra_alc5632_dai.cpu_of_node = NULL;
+	tegra_alc5632_dai.platform_of_node = NULL;
+	of_node_put(tegra_alc5632_dai.codec_of_node);
+	tegra_alc5632_dai.codec_of_node = NULL;
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From ae1c696a480c67c45fb23b35162183f72c6be0e1 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 26 Jul 2018 15:49:10 -0500
Subject: ASoC: sirf: Fix potential NULL pointer dereference

There is a potential execution path in which function
platform_get_resource() returns NULL. If this happens,
we will end up having a NULL pointer dereference.

Fix this by replacing devm_ioremap with devm_ioremap_resource,
which has the NULL check and the memory region request.

This code was detected with the help of Coccinelle.

Cc: stable@vger.kernel.org
Fixes: 2bd8d1d5cf89 ("ASoC: sirf: Add audio usp interface driver")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sirf/sirf-usp.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/sound/soc/sirf/sirf-usp.c b/sound/soc/sirf/sirf-usp.c
index 77e7dcf969d0..d70fcd4a1adf 100644
--- a/sound/soc/sirf/sirf-usp.c
+++ b/sound/soc/sirf/sirf-usp.c
@@ -370,10 +370,9 @@ static int sirf_usp_pcm_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, usp);
 
 	mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	base = devm_ioremap(&pdev->dev, mem_res->start,
-		resource_size(mem_res));
-	if (base == NULL)
-		return -ENOMEM;
+	base = devm_ioremap_resource(&pdev->dev, mem_res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
 	usp->regmap = devm_regmap_init_mmio(&pdev->dev, base,
 					    &sirf_usp_regmap_config);
 	if (IS_ERR(usp->regmap))
-- 
cgit v1.2.3


From 8fc9983db199bb397d48e32a6400765b70f1995a Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Fri, 27 Jul 2018 11:37:28 +0900
Subject: ASoC: uniphier: add support for multichannel output

This patch adds multichannel PCM output support for LD11/LD20.
Currently driver tested and supported only 2ch, 6ch, and 8ch.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/uniphier/aio-core.c | 78 ++++++++++++++++++++++++++++++++++++++++---
 sound/soc/uniphier/aio-ld11.c |  2 +-
 sound/soc/uniphier/aio-reg.h  |  1 +
 sound/soc/uniphier/aio.h      |  3 ++
 4 files changed, 78 insertions(+), 6 deletions(-)

diff --git a/sound/soc/uniphier/aio-core.c b/sound/soc/uniphier/aio-core.c
index 638cb3fc5f7b..8b09bbb0f8d0 100644
--- a/sound/soc/uniphier/aio-core.c
+++ b/sound/soc/uniphier/aio-core.c
@@ -264,6 +264,57 @@ void aio_port_reset(struct uniphier_aio_sub *sub)
 	}
 }
 
+/**
+ * aio_port_set_ch - set channels of LPCM
+ * @sub: the AIO substream pointer, PCM substream only
+ * @ch : count of channels
+ *
+ * Set suitable slot selecting to input/output port block of AIO.
+ *
+ * This function may return error if non-PCM substream.
+ *
+ * Return: Zero if successful, otherwise a negative value on error.
+ */
+static int aio_port_set_ch(struct uniphier_aio_sub *sub)
+{
+	struct regmap *r = sub->aio->chip->regmap;
+	u32 slotsel_2ch[] = {
+		0, 0, 0, 0, 0,
+	};
+	u32 slotsel_multi[] = {
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT0,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT1,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT2,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT3,
+		OPORTMXTYSLOTCTR_SLOTSEL_SLOT4,
+	};
+	u32 mode, *slotsel;
+	int i;
+
+	switch (params_channels(&sub->params)) {
+	case 8:
+	case 6:
+		mode = OPORTMXTYSLOTCTR_MODE;
+		slotsel = slotsel_multi;
+		break;
+	case 2:
+		mode = 0;
+		slotsel = slotsel_2ch;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	for (i = 0; i < AUD_MAX_SLOTSEL; i++) {
+		regmap_update_bits(r, OPORTMXTYSLOTCTR(sub->swm->oport.map, i),
+				   OPORTMXTYSLOTCTR_MODE, mode);
+		regmap_update_bits(r, OPORTMXTYSLOTCTR(sub->swm->oport.map, i),
+				   OPORTMXTYSLOTCTR_SLOTSEL_MASK, slotsel[i]);
+	}
+
+	return 0;
+}
+
 /**
  * aio_port_set_rate - set sampling rate of LPCM
  * @sub: the AIO substream pointer, PCM substream only
@@ -575,6 +626,10 @@ int aio_port_set_param(struct uniphier_aio_sub *sub, int pass_through,
 			rate = params_rate(params);
 		}
 
+		ret = aio_port_set_ch(sub);
+		if (ret)
+			return ret;
+
 		ret = aio_port_set_rate(sub, rate);
 		if (ret)
 			return ret;
@@ -731,15 +786,28 @@ void aio_port_set_volume(struct uniphier_aio_sub *sub, int vol)
 int aio_if_set_param(struct uniphier_aio_sub *sub, int pass_through)
 {
 	struct regmap *r = sub->aio->chip->regmap;
-	u32 v;
+	u32 memfmt, v;
 
 	if (sub->swm->dir == PORT_DIR_OUTPUT) {
-		if (pass_through)
+		if (pass_through) {
 			v = PBOUTMXCTR0_ENDIAN_0123 |
 				PBOUTMXCTR0_MEMFMT_STREAM;
-		else
-			v = PBOUTMXCTR0_ENDIAN_3210 |
-				PBOUTMXCTR0_MEMFMT_2CH;
+		} else {
+			switch (params_channels(&sub->params)) {
+			case 2:
+				memfmt = PBOUTMXCTR0_MEMFMT_2CH;
+				break;
+			case 6:
+				memfmt = PBOUTMXCTR0_MEMFMT_6CH;
+				break;
+			case 8:
+				memfmt = PBOUTMXCTR0_MEMFMT_8CH;
+				break;
+			default:
+				return -EINVAL;
+			}
+			v = PBOUTMXCTR0_ENDIAN_3210 | memfmt;
+		}
 
 		regmap_write(r, PBOUTMXCTR0(sub->swm->oif.map), v);
 		regmap_write(r, PBOUTMXCTR1(sub->swm->oif.map), 0);
diff --git a/sound/soc/uniphier/aio-ld11.c b/sound/soc/uniphier/aio-ld11.c
index ab04d3331be9..de962df245ba 100644
--- a/sound/soc/uniphier/aio-ld11.c
+++ b/sound/soc/uniphier/aio-ld11.c
@@ -286,7 +286,7 @@ static struct snd_soc_dai_driver uniphier_aio_dai_ld11[] = {
 			.formats     = SNDRV_PCM_FMTBIT_S32_LE,
 			.rates       = SNDRV_PCM_RATE_48000,
 			.channels_min = 2,
-			.channels_max = 2,
+			.channels_max = 8,
 		},
 		.ops = &uniphier_aio_i2s_ops,
 	},
diff --git a/sound/soc/uniphier/aio-reg.h b/sound/soc/uniphier/aio-reg.h
index 45fdc6ae358a..734395dbcffb 100644
--- a/sound/soc/uniphier/aio-reg.h
+++ b/sound/soc/uniphier/aio-reg.h
@@ -374,6 +374,7 @@
 #define OPORTMXTYVOLGAINSTATUS(n, m)     (0x42108 + 0x400 * (n) + 0x20 * (m))
 #define   OPORTMXTYVOLGAINSTATUS_CUR_MASK  GENMASK(15, 0)
 #define OPORTMXTYSLOTCTR(n, m)           (0x42114 + 0x400 * (n) + 0x20 * (m))
+#define   OPORTMXTYSLOTCTR_MODE            BIT(15)
 #define   OPORTMXTYSLOTCTR_SLOTSEL_MASK    GENMASK(11, 8)
 #define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT0   (0x8 << 8)
 #define   OPORTMXTYSLOTCTR_SLOTSEL_SLOT1   (0x9 << 8)
diff --git a/sound/soc/uniphier/aio.h b/sound/soc/uniphier/aio.h
index aa89c2f6fa24..23a5c3c68658 100644
--- a/sound/soc/uniphier/aio.h
+++ b/sound/soc/uniphier/aio.h
@@ -141,6 +141,9 @@ enum IEC61937_PC {
 #define AUD_MIN_FRAGMENT_SIZE    (4 * 1024)
 #define AUD_MAX_FRAGMENT_SIZE    (16 * 1024)
 
+/* max 5 slots, 10 channels, 2 channel in 1 slot */
+#define AUD_MAX_SLOTSEL    5
+
 /*
  * This is a selector for virtual register map of AIO.
  *
-- 
cgit v1.2.3


From d8504acca759ae672c6d34d49a33d54ace094cbb Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Fri, 27 Jul 2018 11:37:44 +0900
Subject: ASoC: uniphier: change functions to static

This patch changes some functions that are not used by other objects
to static.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/uniphier/aio-core.c | 6 +++---
 sound/soc/uniphier/aio.h      | 3 ---
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/sound/soc/uniphier/aio-core.c b/sound/soc/uniphier/aio-core.c
index 8b09bbb0f8d0..9bcba06ba52e 100644
--- a/sound/soc/uniphier/aio-core.c
+++ b/sound/soc/uniphier/aio-core.c
@@ -327,7 +327,7 @@ static int aio_port_set_ch(struct uniphier_aio_sub *sub)
  *
  * Return: Zero if successful, otherwise a negative value on error.
  */
-int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate)
+static int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate)
 {
 	struct regmap *r = sub->aio->chip->regmap;
 	struct device *dev = &sub->aio->chip->pdev->dev;
@@ -446,7 +446,7 @@ int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate)
  *
  * Return: Zero if successful, otherwise a negative value on error.
  */
-int aio_port_set_fmt(struct uniphier_aio_sub *sub)
+static int aio_port_set_fmt(struct uniphier_aio_sub *sub)
 {
 	struct regmap *r = sub->aio->chip->regmap;
 	struct device *dev = &sub->aio->chip->pdev->dev;
@@ -511,7 +511,7 @@ int aio_port_set_fmt(struct uniphier_aio_sub *sub)
  *
  * Return: Zero if successful, otherwise a negative value on error.
  */
-int aio_port_set_clk(struct uniphier_aio_sub *sub)
+static int aio_port_set_clk(struct uniphier_aio_sub *sub)
 {
 	struct uniphier_aio_chip *chip = sub->aio->chip;
 	struct device *dev = &sub->aio->chip->pdev->dev;
diff --git a/sound/soc/uniphier/aio.h b/sound/soc/uniphier/aio.h
index 23a5c3c68658..ca6ccbae0ee8 100644
--- a/sound/soc/uniphier/aio.h
+++ b/sound/soc/uniphier/aio.h
@@ -325,9 +325,6 @@ int aio_chip_set_pll(struct uniphier_aio_chip *chip, int pll_id,
 void aio_chip_init(struct uniphier_aio_chip *chip);
 int aio_init(struct uniphier_aio_sub *sub);
 void aio_port_reset(struct uniphier_aio_sub *sub);
-int aio_port_set_rate(struct uniphier_aio_sub *sub, int rate);
-int aio_port_set_fmt(struct uniphier_aio_sub *sub);
-int aio_port_set_clk(struct uniphier_aio_sub *sub);
 int aio_port_set_param(struct uniphier_aio_sub *sub, int pass_through,
 		       const struct snd_pcm_hw_params *params);
 void aio_port_set_enable(struct uniphier_aio_sub *sub, int enable);
-- 
cgit v1.2.3


From 6decb5b45e70d6ffff6488cc8e8bad6b9ac7f99b Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:32 +0530
Subject: Bluetooth: Define PHY flags in hdev and set 1M as default

1M is mandatory to be supported by LE controllers and the same
would be set in power on. This patch defines hdev flags for
LE PHYs and set 1M to default.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      | 4 ++++
 include/net/bluetooth/hci_core.h | 3 +++
 net/bluetooth/hci_core.c         | 9 +++++----
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 73e48be5bbb3..664fe1ebf2c7 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1514,6 +1514,10 @@ struct hci_cp_le_set_default_phy {
 	__u8    rx_phys;
 } __packed;
 
+#define HCI_LE_SET_PHY_1M		0x01
+#define HCI_LE_SET_PHY_2M		0x02
+#define HCI_LE_SET_PHY_CODED		0x04
+
 #define HCI_OP_LE_SET_EXT_SCAN_PARAMS   0x2041
 struct hci_cp_le_set_ext_scan_params {
 	__u8    own_addr_type;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a74453571264..71f79df9ee05 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -315,6 +315,9 @@ struct hci_dev {
 	unsigned long	sco_last_tx;
 	unsigned long	le_last_tx;
 
+	__u8		le_tx_def_phys;
+	__u8		le_rx_def_phys;
+
 	struct workqueue_struct	*workqueue;
 	struct workqueue_struct	*req_workqueue;
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index f5c21004186c..432f89f390c0 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -830,10 +830,9 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt)
 	if (hdev->commands[35] & 0x20) {
 		struct hci_cp_le_set_default_phy cp;
 
-		/* No transmitter PHY or receiver PHY preferences */
-		cp.all_phys = 0x03;
-		cp.tx_phys = 0;
-		cp.rx_phys = 0;
+		cp.all_phys = 0x00;
+		cp.tx_phys = hdev->le_tx_def_phys;
+		cp.rx_phys = hdev->le_rx_def_phys;
 
 		hci_req_add(req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp), &cp);
 	}
@@ -3027,6 +3026,8 @@ struct hci_dev *hci_alloc_dev(void)
 	hdev->le_max_tx_time = 0x0148;
 	hdev->le_max_rx_len = 0x001b;
 	hdev->le_max_rx_time = 0x0148;
+	hdev->le_tx_def_phys = HCI_LE_SET_PHY_1M;
+	hdev->le_rx_def_phys = HCI_LE_SET_PHY_1M;
 
 	hdev->rpa_timeout = HCI_DEFAULT_RPA_TIMEOUT;
 	hdev->discov_interleaved_timeout = DISCOV_INTERLEAVED_TIMEOUT;
-- 
cgit v1.2.3


From 5075b972f20ddad5bb19542ea4f5794d06673375 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:33 +0530
Subject: Bluetooth: Add defines for BREDR pkt_type and LE PHYs

This also add macros for checking LMP support for different
pkt_types

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      | 14 ++++++++++++++
 include/net/bluetooth/hci_core.h |  4 ++++
 2 files changed, 18 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 664fe1ebf2c7..89bf800f6eb1 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -291,6 +291,14 @@ enum {
 #define HCI_DH3		0x0800
 #define HCI_DH5		0x8000
 
+/* HCI packet types inverted masks */
+#define HCI_2DH1	0x0002
+#define HCI_3DH1	0x0004
+#define HCI_2DH3	0x0100
+#define HCI_3DH3	0x0200
+#define HCI_2DH5	0x1000
+#define HCI_3DH5	0x2000
+
 #define HCI_HV1		0x0020
 #define HCI_HV2		0x0040
 #define HCI_HV3		0x0080
@@ -354,6 +362,8 @@ enum {
 #define LMP_PCONTROL	0x04
 #define LMP_TRANSPARENT	0x08
 
+#define LMP_EDR_2M		0x02
+#define LMP_EDR_3M		0x04
 #define LMP_RSSI_INQ	0x40
 #define LMP_ESCO	0x80
 
@@ -361,7 +371,9 @@ enum {
 #define LMP_EV5		0x02
 #define LMP_NO_BREDR	0x20
 #define LMP_LE		0x40
+#define LMP_EDR_3SLOT	0x80
 
+#define LMP_EDR_5SLOT	0x01
 #define LMP_SNIFF_SUBR	0x02
 #define LMP_PAUSE_ENC	0x04
 #define LMP_EDR_ESCO_2M	0x20
@@ -399,6 +411,8 @@ enum {
 #define HCI_LE_PING			0x10
 #define HCI_LE_DATA_LEN_EXT		0x20
 #define HCI_LE_EXT_SCAN_POLICY		0x80
+#define HCI_LE_PHY_2M			0x01
+#define HCI_LE_PHY_CODED		0x08
 #define HCI_LE_CHAN_SEL_ALG2		0x40
 
 /* Connection modes */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 71f79df9ee05..a64d13f91d09 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1141,6 +1141,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_inq_tx_pwr_capable(dev) ((dev)->features[0][7] & LMP_INQ_TX_PWR)
 #define lmp_ext_feat_capable(dev)  ((dev)->features[0][7] & LMP_EXTFEATURES)
 #define lmp_transp_capable(dev)    ((dev)->features[0][2] & LMP_TRANSPARENT)
+#define lmp_edr_2m_capable(dev)    ((dev)->features[0][3] & LMP_EDR_2M)
+#define lmp_edr_3m_capable(dev)    ((dev)->features[0][3] & LMP_EDR_3M)
+#define lmp_edr_3slot_capable(dev) ((dev)->features[0][4] & LMP_EDR_3SLOT)
+#define lmp_edr_5slot_capable(dev) ((dev)->features[0][5] & LMP_EDR_5SLOT)
 
 /* ----- Extended LMP capabilities ----- */
 #define lmp_csb_master_capable(dev) ((dev)->features[2][0] & LMP_CSB_MASTER)
-- 
cgit v1.2.3


From 6244691fec4dd0adebca255e60e0ed7ac8155b2e Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:34 +0530
Subject: Bluetooth: Implement Get PHY Configuration mgmt command

This commands basically retrieve the supported packet types of
BREDR and supported PHYs of the controller.

BR_1M_1SLOT, LE_1M_TX and LE_1M_RX would be supported by default.
Other PHYs are supported based on the local features.

Also this sets PHY_CONFIGURATION bit in supported settings.

@ MGMT Command: Get PHY Configuration (0x0044) plen 0
@ MGMT Event: Command Complete (0x0001) plen 15
      Get PHY Configuration (0x0044) plen 12
        Status: Success (0x00)
        Supported PHYs: 0x7fff
          BR 1M 1SLOT
          BR 1M 3SLOT
          BR 1M 5SLOT
          EDR 2M 1SLOT
          EDR 2M 3SLOT
          EDR 2M 5SLOT
          EDR 3M 1SLOT
          EDR 3M 3SLOT
          EDR 3M 5SLOT
          LE 1M TX
          LE 1M RX
          LE 2M TX
          LE 2M RX
          LE CODED TX
          LE CODED RX
        Configurable PHYs: 0x79fe
          BR 1M 3SLOT
          BR 1M 5SLOT
          EDR 2M 1SLOT
          EDR 2M 3SLOT
          EDR 2M 5SLOT
          EDR 3M 1SLOT
          EDR 3M 3SLOT
          EDR 3M 5SLOT
          LE 2M TX
          LE 2M RX
          LE CODED TX
          LE CODED RX
        Selected PHYs: 0x07ff
          BR 1M 1SLOT
          BR 1M 3SLOT
          BR 1M 5SLOT
          EDR 2M 1SLOT
          EDR 2M 3SLOT
          EDR 2M 5SLOT
          EDR 3M 1SLOT
          EDR 3M 3SLOT
          EDR 3M 5SLOT
          LE 1M TX
          LE 1M RX

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h |  25 ++++++++
 net/bluetooth/mgmt.c         | 145 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 170 insertions(+)

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index e7303eee65cd..1c93d6e83a6c 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -101,6 +101,7 @@ struct mgmt_rp_read_index_list {
 #define MGMT_SETTING_PRIVACY		0x00002000
 #define MGMT_SETTING_CONFIGURATION	0x00004000
 #define MGMT_SETTING_STATIC_ADDRESS	0x00008000
+#define MGMT_SETTING_PHY_CONFIGURATION  0x00010000
 
 #define MGMT_OP_READ_INFO		0x0004
 #define MGMT_READ_INFO_SIZE		0
@@ -604,6 +605,30 @@ struct mgmt_cp_set_appearance {
 } __packed;
 #define MGMT_SET_APPEARANCE_SIZE	2
 
+#define MGMT_OP_GET_PHY_CONFIGURATION	0x0044
+struct mgmt_rp_get_phy_confguration {
+	__le32	supported_phys;
+	__le32	configurable_phys;
+	__le32	selected_phys;
+} __packed;
+#define MGMT_GET_PHY_CONFIGURATION_SIZE	0
+
+#define MGMT_PHY_BR_1M_1SLOT	0x00000001
+#define MGMT_PHY_BR_1M_3SLOT	0x00000002
+#define MGMT_PHY_BR_1M_5SLOT	0x00000004
+#define MGMT_PHY_EDR_2M_1SLOT	0x00000008
+#define MGMT_PHY_EDR_2M_3SLOT	0x00000010
+#define MGMT_PHY_EDR_2M_5SLOT	0x00000020
+#define MGMT_PHY_EDR_3M_1SLOT	0x00000040
+#define MGMT_PHY_EDR_3M_3SLOT	0x00000080
+#define MGMT_PHY_EDR_3M_5SLOT	0x00000100
+#define MGMT_PHY_LE_1M_TX		0x00000200
+#define MGMT_PHY_LE_1M_RX		0x00000400
+#define MGMT_PHY_LE_2M_TX		0x00000800
+#define MGMT_PHY_LE_2M_RX		0x00001000
+#define MGMT_PHY_LE_CODED_TX	0x00002000
+#define MGMT_PHY_LE_CODED_RX	0x00004000
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 8a80d48d89c4..c8c3b39fa9f2 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -617,6 +617,127 @@ static int read_config_info(struct sock *sk, struct hci_dev *hdev,
 				 &rp, sizeof(rp));
 }
 
+static u32 get_supported_phys(struct hci_dev *hdev)
+{
+	u32 supported_phys = 0;
+
+	if (lmp_bredr_capable(hdev)) {
+		supported_phys |= MGMT_PHY_BR_1M_1SLOT;
+
+		if (hdev->features[0][0] & LMP_3SLOT)
+			supported_phys |= MGMT_PHY_BR_1M_3SLOT;
+
+		if (hdev->features[0][0] & LMP_5SLOT)
+			supported_phys |= MGMT_PHY_BR_1M_5SLOT;
+
+		if (lmp_edr_2m_capable(hdev)) {
+			supported_phys |= MGMT_PHY_EDR_2M_1SLOT;
+
+			if (lmp_edr_3slot_capable(hdev))
+				supported_phys |= MGMT_PHY_EDR_2M_3SLOT;
+
+			if (lmp_edr_5slot_capable(hdev))
+				supported_phys |= MGMT_PHY_EDR_2M_5SLOT;
+
+			if (lmp_edr_3m_capable(hdev)) {
+				supported_phys |= MGMT_PHY_EDR_3M_1SLOT;
+
+				if (lmp_edr_3slot_capable(hdev))
+					supported_phys |= MGMT_PHY_EDR_3M_3SLOT;
+
+				if (lmp_edr_5slot_capable(hdev))
+					supported_phys |= MGMT_PHY_EDR_3M_5SLOT;
+			}
+		}
+	}
+
+	if (lmp_le_capable(hdev)) {
+		supported_phys |= MGMT_PHY_LE_1M_TX;
+		supported_phys |= MGMT_PHY_LE_1M_RX;
+
+		if (hdev->le_features[1] & HCI_LE_PHY_2M) {
+			supported_phys |= MGMT_PHY_LE_2M_TX;
+			supported_phys |= MGMT_PHY_LE_2M_RX;
+		}
+
+		if (hdev->le_features[1] & HCI_LE_PHY_CODED) {
+			supported_phys |= MGMT_PHY_LE_CODED_TX;
+			supported_phys |= MGMT_PHY_LE_CODED_RX;
+		}
+	}
+
+	return supported_phys;
+}
+
+static u32 get_selected_phys(struct hci_dev *hdev)
+{
+	u32 selected_phys = 0;
+
+	if (lmp_bredr_capable(hdev)) {
+		selected_phys |= MGMT_PHY_BR_1M_1SLOT;
+
+		if (hdev->pkt_type & (HCI_DM3 | HCI_DH3))
+			selected_phys |= MGMT_PHY_BR_1M_3SLOT;
+
+		if (hdev->pkt_type & (HCI_DM5 | HCI_DH5))
+			selected_phys |= MGMT_PHY_BR_1M_5SLOT;
+
+		if (lmp_edr_2m_capable(hdev)) {
+			if (!(hdev->pkt_type & HCI_2DH1))
+				selected_phys |= MGMT_PHY_EDR_2M_1SLOT;
+
+			if (lmp_edr_3slot_capable(hdev) &&
+			    !(hdev->pkt_type & HCI_2DH3))
+				selected_phys |= MGMT_PHY_EDR_2M_3SLOT;
+
+			if (lmp_edr_5slot_capable(hdev) &&
+			    !(hdev->pkt_type & HCI_2DH5))
+				selected_phys |= MGMT_PHY_EDR_2M_5SLOT;
+
+			if (lmp_edr_3m_capable(hdev)) {
+				if (!(hdev->pkt_type & HCI_3DH1))
+					selected_phys |= MGMT_PHY_EDR_3M_1SLOT;
+
+				if (lmp_edr_3slot_capable(hdev) &&
+				    !(hdev->pkt_type & HCI_3DH3))
+					selected_phys |= MGMT_PHY_EDR_3M_3SLOT;
+
+				if (lmp_edr_5slot_capable(hdev) &&
+				    !(hdev->pkt_type & HCI_3DH5))
+					selected_phys |= MGMT_PHY_EDR_3M_5SLOT;
+			}
+		}
+	}
+
+	if (lmp_le_capable(hdev)) {
+		if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_1M)
+			selected_phys |= MGMT_PHY_LE_1M_TX;
+
+		if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_1M)
+			selected_phys |= MGMT_PHY_LE_1M_RX;
+
+		if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_2M)
+			selected_phys |= MGMT_PHY_LE_2M_TX;
+
+		if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_2M)
+			selected_phys |= MGMT_PHY_LE_2M_RX;
+
+		if (hdev->le_tx_def_phys & HCI_LE_SET_PHY_CODED)
+			selected_phys |= MGMT_PHY_LE_CODED_TX;
+
+		if (hdev->le_rx_def_phys & HCI_LE_SET_PHY_CODED)
+			selected_phys |= MGMT_PHY_LE_CODED_RX;
+	}
+
+	return selected_phys;
+}
+
+static u32 get_configurable_phys(struct hci_dev *hdev)
+{
+	return (get_supported_phys(hdev) & ~MGMT_PHY_BR_1M_1SLOT &
+		~MGMT_PHY_LE_1M_TX & ~MGMT_PHY_LE_1M_RX);
+}
+
 static u32 get_supported_settings(struct hci_dev *hdev)
 {
 	u32 settings = 0;
@@ -654,6 +775,8 @@ static u32 get_supported_settings(struct hci_dev *hdev)
 	    hdev->set_bdaddr)
 		settings |= MGMT_SETTING_CONFIGURATION;
 
+	settings |= MGMT_SETTING_PHY_CONFIGURATION;
+
 	return settings;
 }
 
@@ -3184,6 +3307,27 @@ static int set_appearance(struct sock *sk, struct hci_dev *hdev, void *data,
 	return err;
 }
 
+static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev,
+				 void *data, u16 len)
+{
+	struct mgmt_rp_get_phy_confguration rp;
+
+	BT_DBG("sock %p %s", sk, hdev->name);
+
+	hci_dev_lock(hdev);
+
+	memset(&rp, 0, sizeof(rp));
+
+	rp.supported_phys = cpu_to_le32(get_supported_phys(hdev));
+	rp.selected_phys = cpu_to_le32(get_selected_phys(hdev));
+	rp.configurable_phys = cpu_to_le32(get_configurable_phys(hdev));
+
+	hci_dev_unlock(hdev);
+
+	return mgmt_cmd_complete(sk, hdev->id, MGMT_OP_GET_PHY_CONFIGURATION, 0,
+				 &rp, sizeof(rp));
+}
+
 static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status,
 				         u16 opcode, struct sk_buff *skb)
 {
@@ -6544,6 +6688,7 @@ static const struct hci_mgmt_handler mgmt_handlers[] = {
 	{ read_ext_controller_info,MGMT_READ_EXT_INFO_SIZE,
 						HCI_MGMT_UNTRUSTED },
 	{ set_appearance,	   MGMT_SET_APPEARANCE_SIZE },
+	{ get_phy_configuration,   MGMT_GET_PHY_CONFIGURATION_SIZE },
 };
 
 void mgmt_index_added(struct hci_dev *hdev)
-- 
cgit v1.2.3


From 0314f2867fa0c46d0fc1c23c80e7fab9435079df Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:35 +0530
Subject: Bluetooth: Implement Set PHY Confguration command

This enables user to set phys which will be used in all subsequent
connections. Also host will use the same in LE scanning as well.

@ MGMT Command: Set PHY Configuration (0x0045) plen 4
        Selected PHYs: 0x7fff
          BR 1M 1SLOT
          BR 1M 3SLOT
          BR 1M 5SLOT
          EDR 2M 1SLOT
          EDR 2M 3SLOT
          EDR 2M 5SLOT
          EDR 3M 1SLOT
          EDR 3M 3SLOT
          EDR 3M 5SLOT
          LE 1M TX
          LE 1M RX
          LE 2M TX
          LE 2M RX
          LE CODED TX
          LE CODED RX
< HCI Command: LE Set Default PHY (0x08|0x0031) plen 3
        All PHYs preference: 0x00
        TX PHYs preference: 0x07
          LE 1M
          LE 2M
          LE Coded
        RX PHYs preference: 0x07
          LE 1M
          LE 2M
          LE Coded
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Default PHY (0x08|0x0031) ncmd 1
        Status: Success (0x00)
@ MGMT Event: Command Complete (0x0001) plen 3
      Set PHY Configuration (0x0045) plen 0
        Status: Success (0x00)
@ MGMT Event: PHY Configuration Changed (0x0026) plen 4
        Selected PHYs: 0x7fff
          BR 1M 1SLOT
          BR 1M 3SLOT
          BR 1M 5SLOT
          EDR 2M 1SLOT
          EDR 2M 3SLOT
          EDR 2M 5SLOT
          EDR 3M 1SLOT
          EDR 3M 3SLOT
          EDR 3M 5SLOT
          LE 1M TX
          LE 1M RX
          LE 2M TX
          LE 2M RX
          LE CODED TX
          LE CODED RX

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/mgmt.h |  19 +++++
 net/bluetooth/hci_event.c    |  26 +++++++
 net/bluetooth/mgmt.c         | 182 +++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 227 insertions(+)

diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 1c93d6e83a6c..0916e203e5d9 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -629,6 +629,25 @@ struct mgmt_rp_get_phy_confguration {
 #define MGMT_PHY_LE_CODED_TX	0x00002000
 #define MGMT_PHY_LE_CODED_RX	0x00004000
 
+#define MGMT_PHY_BREDR_MASK (MGMT_PHY_BR_1M_1SLOT | MGMT_PHY_BR_1M_3SLOT | \
+			     MGMT_PHY_BR_1M_5SLOT | MGMT_PHY_EDR_2M_1SLOT | \
+			     MGMT_PHY_EDR_2M_3SLOT | MGMT_PHY_EDR_2M_5SLOT | \
+			     MGMT_PHY_EDR_3M_1SLOT | MGMT_PHY_EDR_3M_3SLOT | \
+			     MGMT_PHY_EDR_3M_5SLOT)
+#define MGMT_PHY_LE_MASK (MGMT_PHY_LE_1M_TX | MGMT_PHY_LE_1M_RX | \
+			  MGMT_PHY_LE_2M_TX | MGMT_PHY_LE_2M_RX | \
+			  MGMT_PHY_LE_CODED_TX | MGMT_PHY_LE_CODED_RX)
+#define MGMT_PHY_LE_TX_MASK (MGMT_PHY_LE_1M_TX | MGMT_PHY_LE_2M_TX | \
+			     MGMT_PHY_LE_CODED_TX)
+#define MGMT_PHY_LE_RX_MASK (MGMT_PHY_LE_1M_RX | MGMT_PHY_LE_2M_RX | \
+			     MGMT_PHY_LE_CODED_RX)
+
+#define MGMT_OP_SET_PHY_CONFIGURATION	0x0045
+struct mgmt_cp_set_phy_confguration {
+	__le32	selected_phys;
+} __packed;
+#define MGMT_SET_PHY_CONFIGURATION_SIZE	4
+
 #define MGMT_EV_CMD_COMPLETE		0x0001
 struct mgmt_ev_cmd_complete {
 	__le16	opcode;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 68192152c23b..694231541a4c 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1042,6 +1042,28 @@ static void hci_cc_le_set_random_addr(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_set_default_phy(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+	struct hci_cp_le_set_default_phy *cp;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_DEFAULT_PHY);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	hdev->le_tx_def_phys = cp->tx_phys;
+	hdev->le_rx_def_phys = cp->rx_phys;
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 *sent, status = *((__u8 *) skb->data);
@@ -3163,6 +3185,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_set_ext_scan_enable(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_DEFAULT_PHY:
+		hci_cc_le_set_default_phy(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c8c3b39fa9f2..7cd6a37a63ee 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3328,6 +3328,187 @@ static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev,
 				 &rp, sizeof(rp));
 }
 
+static void set_default_phy_complete(struct hci_dev *hdev, u8 status,
+				     u16 opcode, struct sk_buff *skb)
+{
+	struct mgmt_cp_set_phy_confguration *cp;
+	struct mgmt_pending_cmd *cmd;
+
+	BT_DBG("status 0x%02x", status);
+
+	hci_dev_lock(hdev);
+
+	cmd = pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev);
+	if (!cmd)
+		goto unlock;
+
+	cp = cmd->param;
+
+	if (status) {
+		mgmt_cmd_status(cmd->sk, hdev->id,
+				MGMT_OP_SET_PHY_CONFIGURATION,
+				mgmt_status(status));
+	} else {
+		mgmt_cmd_complete(cmd->sk, hdev->id,
+				  MGMT_OP_SET_PHY_CONFIGURATION, 0,
+				  NULL, 0);
+	}
+
+	mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+}
+
+static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev,
+				 void *data, u16 len)
+{
+	struct mgmt_cp_set_phy_confguration *cp = data;
+	struct hci_cp_le_set_default_phy cp_phy;
+	struct mgmt_pending_cmd *cmd;
+	struct hci_request req;
+	u32 selected_phys, configurable_phys, supported_phys, unconfigure_phys;
+	u16 pkt_type = (HCI_DH1 | HCI_DM1);
+	int err;
+
+	BT_DBG("sock %p %s", sk, hdev->name);
+
+	configurable_phys = get_configurable_phys(hdev);
+	supported_phys = get_supported_phys(hdev);
+	selected_phys = __le32_to_cpu(cp->selected_phys);
+
+	if (selected_phys & ~supported_phys)
+		return mgmt_cmd_status(sk, hdev->id,
+				       MGMT_OP_SET_PHY_CONFIGURATION,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	unconfigure_phys = supported_phys & ~configurable_phys;
+
+	if ((selected_phys & unconfigure_phys) != unconfigure_phys)
+		return mgmt_cmd_status(sk, hdev->id,
+				       MGMT_OP_SET_PHY_CONFIGURATION,
+				       MGMT_STATUS_INVALID_PARAMS);
+
+	if (selected_phys == get_selected_phys(hdev))
+		return mgmt_cmd_complete(sk, hdev->id,
+					 MGMT_OP_SET_PHY_CONFIGURATION,
+					 0, NULL, 0);
+
+	hci_dev_lock(hdev);
+
+	if (!hdev_is_powered(hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id,
+				      MGMT_OP_SET_PHY_CONFIGURATION,
+				      MGMT_STATUS_REJECTED);
+		goto unlock;
+	}
+
+	if (pending_find(MGMT_OP_SET_PHY_CONFIGURATION, hdev)) {
+		err = mgmt_cmd_status(sk, hdev->id,
+				      MGMT_OP_SET_PHY_CONFIGURATION,
+				      MGMT_STATUS_BUSY);
+		goto unlock;
+	}
+
+	if (selected_phys & MGMT_PHY_BR_1M_3SLOT)
+		pkt_type |= (HCI_DH3 | HCI_DM3);
+	else
+		pkt_type &= ~(HCI_DH3 | HCI_DM3);
+
+	if (selected_phys & MGMT_PHY_BR_1M_5SLOT)
+		pkt_type |= (HCI_DH5 | HCI_DM5);
+	else
+		pkt_type &= ~(HCI_DH5 | HCI_DM5);
+
+	if (selected_phys & MGMT_PHY_EDR_2M_1SLOT)
+		pkt_type &= ~HCI_2DH1;
+	else
+		pkt_type |= HCI_2DH1;
+
+	if (selected_phys & MGMT_PHY_EDR_2M_3SLOT)
+		pkt_type &= ~HCI_2DH3;
+	else
+		pkt_type |= HCI_2DH3;
+
+	if (selected_phys & MGMT_PHY_EDR_2M_5SLOT)
+		pkt_type &= ~HCI_2DH5;
+	else
+		pkt_type |= HCI_2DH5;
+
+	if (selected_phys & MGMT_PHY_EDR_3M_1SLOT)
+		pkt_type &= ~HCI_3DH1;
+	else
+		pkt_type |= HCI_3DH1;
+
+	if (selected_phys & MGMT_PHY_EDR_3M_3SLOT)
+		pkt_type &= ~HCI_3DH3;
+	else
+		pkt_type |= HCI_3DH3;
+
+	if (selected_phys & MGMT_PHY_EDR_3M_5SLOT)
+		pkt_type &= ~HCI_3DH5;
+	else
+		pkt_type |= HCI_3DH5;
+
+	if (pkt_type != hdev->pkt_type)
+		hdev->pkt_type = pkt_type;
+
+	if ((selected_phys & MGMT_PHY_LE_MASK) ==
+	    (get_selected_phys(hdev) & MGMT_PHY_LE_MASK)) {
+		err = mgmt_cmd_complete(sk, hdev->id,
+					MGMT_OP_SET_PHY_CONFIGURATION,
+					0, NULL, 0);
+
+		goto unlock;
+	}
+
+	cmd = mgmt_pending_add(sk, MGMT_OP_SET_PHY_CONFIGURATION, hdev, data,
+			       len);
+	if (!cmd) {
+		err = -ENOMEM;
+		goto unlock;
+	}
+
+	hci_req_init(&req, hdev);
+
+	memset(&cp_phy, 0, sizeof(cp_phy));
+
+	if (!(selected_phys & MGMT_PHY_LE_TX_MASK))
+		cp_phy.all_phys |= 0x01;
+
+	if (!(selected_phys & MGMT_PHY_LE_RX_MASK))
+		cp_phy.all_phys |= 0x02;
+
+	if (selected_phys & MGMT_PHY_LE_1M_TX)
+		cp_phy.tx_phys |= HCI_LE_SET_PHY_1M;
+
+	if (selected_phys & MGMT_PHY_LE_2M_TX)
+		cp_phy.tx_phys |= HCI_LE_SET_PHY_2M;
+
+	if (selected_phys & MGMT_PHY_LE_CODED_TX)
+		cp_phy.tx_phys |= HCI_LE_SET_PHY_CODED;
+
+	if (selected_phys & MGMT_PHY_LE_1M_RX)
+		cp_phy.rx_phys |= HCI_LE_SET_PHY_1M;
+
+	if (selected_phys & MGMT_PHY_LE_2M_RX)
+		cp_phy.rx_phys |= HCI_LE_SET_PHY_2M;
+
+	if (selected_phys & MGMT_PHY_LE_CODED_RX)
+		cp_phy.rx_phys |= HCI_LE_SET_PHY_CODED;
+
+	hci_req_add(&req, HCI_OP_LE_SET_DEFAULT_PHY, sizeof(cp_phy), &cp_phy);
+
+	err = hci_req_run_skb(&req, set_default_phy_complete);
+	if (err < 0)
+		mgmt_pending_remove(cmd);
+
+unlock:
+	hci_dev_unlock(hdev);
+
+	return err;
+}
+
 static void read_local_oob_data_complete(struct hci_dev *hdev, u8 status,
 				         u16 opcode, struct sk_buff *skb)
 {
@@ -6689,6 +6870,7 @@ static const struct hci_mgmt_handler mgmt_handlers[] = {
 						HCI_MGMT_UNTRUSTED },
 	{ set_appearance,	   MGMT_SET_APPEARANCE_SIZE },
 	{ get_phy_configuration,   MGMT_GET_PHY_CONFIGURATION_SIZE },
+	{ set_phy_configuration,   MGMT_SET_PHY_CONFIGURATION_SIZE },
 };
 
 void mgmt_index_added(struct hci_dev *hdev)
-- 
cgit v1.2.3


From b7c23df85b6a1c3bcfb591cfa938d341fc3a556e Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:36 +0530
Subject: Bluetooth: Implement PHY changed event

This defines and implement phy changed event and send it to user
whenever selected PHYs changes using SET_PHY_CONFIGURATION.

This will be also trigerred when BREDR pkt_type is changed using
the legacy ioctl HCISETPTYPE.

@ MGMT Command: Set PHY Configuration (0x0045) plen 4
		Selected PHYs: 0x7fff
		  BR 1M 1SLOT
		  BR 1M 3SLOT
		  BR 1M 5SLOT
		  EDR 2M 1SLOT
		  EDR 2M 3SLOT
		  EDR 2M 5SLOT
		  EDR 3M 1SLOT
		  EDR 3M 3SLOT
		  EDR 3M 5SLOT
		  LE 1M TX
		  LE 1M RX
		  LE 2M TX
		  LE 2M RX
		  LE CODED TX
		  LE CODED RX
< HCI Command: LE Set Default PHY (0x08|0x0031) plen 3
		All PHYs preference: 0x00
		TX PHYs preference: 0x07
		  LE 1M
		  LE 2M
		  LE Coded
		RX PHYs preference: 0x07
		  LE 1M
		  LE 2M
		  LE Coded
> HCI Event: Command Complete (0x0e) plen 4
	  LE Set Default PHY (0x08|0x0031) ncmd 1
		Status: Success (0x00)
@ MGMT Event: Command Complete (0x0001) plen 3
	  Set PHY Configuration (0x0045) plen 0
		Status: Success (0x00)
@ MGMT Event: PHY Configuration Changed (0x0026) plen 4
		Selected PHYs: 0x7fff
		  BR 1M 1SLOT
		  BR 1M 3SLOT
		  BR 1M 5SLOT
		  EDR 2M 1SLOT
		  EDR 2M 3SLOT
		  EDR 2M 5SLOT
		  EDR 3M 1SLOT
		  EDR 3M 3SLOT
		  EDR 3M 5SLOT
		  LE 1M TX
		  LE 1M RX
		  LE 2M TX
		  LE 2M RX
		  LE CODED TX
		  LE CODED RX

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci_core.h |  1 +
 include/net/bluetooth/mgmt.h     |  5 +++++
 net/bluetooth/hci_core.c         |  4 ++++
 net/bluetooth/mgmt.c             | 22 +++++++++++++++++++++-
 4 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a64d13f91d09..ab5d494a545a 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1544,6 +1544,7 @@ void mgmt_advertising_added(struct sock *sk, struct hci_dev *hdev,
 			    u8 instance);
 void mgmt_advertising_removed(struct sock *sk, struct hci_dev *hdev,
 			      u8 instance);
+int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip);
 
 u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency,
 		      u16 to_multiplier);
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 0916e203e5d9..7f372e9067c9 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -868,3 +868,8 @@ struct mgmt_ev_ext_info_changed {
 	__le16	eir_len;
 	__u8	eir[0];
 } __packed;
+
+#define MGMT_EV_PHY_CONFIGURATION_CHANGED	0x0026
+struct mgmt_ev_phy_configuration_changed {
+	__le32	selected_phys;
+} __packed;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 432f89f390c0..523e91ad64d0 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1924,7 +1924,11 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
 		break;
 
 	case HCISETPTYPE:
+		if (hdev->pkt_type == (__u16) dr.dev_opt)
+			break;
+
 		hdev->pkt_type = (__u16) dr.dev_opt;
+		mgmt_phy_configuration_changed(hdev, NULL);
 		break;
 
 	case HCISETACLMTU:
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 7cd6a37a63ee..1867aadc5061 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3328,6 +3328,18 @@ static int get_phy_configuration(struct sock *sk, struct hci_dev *hdev,
 				 &rp, sizeof(rp));
 }
 
+int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip)
+{
+	struct mgmt_ev_phy_configuration_changed ev;
+
+	memset(&ev, 0, sizeof(ev));
+
+	ev.selected_phys = cpu_to_le32(get_selected_phys(hdev));
+
+	return mgmt_event(MGMT_EV_PHY_CONFIGURATION_CHANGED, hdev, &ev,
+			  sizeof(ev), skip);
+}
+
 static void set_default_phy_complete(struct hci_dev *hdev, u8 status,
 				     u16 opcode, struct sk_buff *skb)
 {
@@ -3352,6 +3364,8 @@ static void set_default_phy_complete(struct hci_dev *hdev, u8 status,
 		mgmt_cmd_complete(cmd->sk, hdev->id,
 				  MGMT_OP_SET_PHY_CONFIGURATION, 0,
 				  NULL, 0);
+
+		mgmt_phy_configuration_changed(hdev, cmd->sk);
 	}
 
 	mgmt_pending_remove(cmd);
@@ -3369,6 +3383,7 @@ static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev,
 	struct hci_request req;
 	u32 selected_phys, configurable_phys, supported_phys, unconfigure_phys;
 	u16 pkt_type = (HCI_DH1 | HCI_DM1);
+	bool changed = false;
 	int err;
 
 	BT_DBG("sock %p %s", sk, hdev->name);
@@ -3450,11 +3465,16 @@ static int set_phy_configuration(struct sock *sk, struct hci_dev *hdev,
 	else
 		pkt_type |= HCI_3DH5;
 
-	if (pkt_type != hdev->pkt_type)
+	if (pkt_type != hdev->pkt_type) {
 		hdev->pkt_type = pkt_type;
+		changed = true;
+	}
 
 	if ((selected_phys & MGMT_PHY_LE_MASK) ==
 	    (get_selected_phys(hdev) & MGMT_PHY_LE_MASK)) {
+		if (changed)
+			mgmt_phy_configuration_changed(hdev, sk);
+
 		err = mgmt_cmd_complete(sk, hdev->id,
 					MGMT_OP_SET_PHY_CONFIGURATION,
 					0, NULL, 0);
-- 
cgit v1.2.3


From 45bdd86eafc7d29e0b4b6681bec9c6ab8eddc6bf Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:37 +0530
Subject: Bluetooth: Set Scan PHYs based on selected PHYs by user

Use the PHYs selected in Set Phy Configuration management command
while scanning.

< HCI Command: LE Set Extended Scan Parameters (0x08|0x0041) plen 13
        Own address type: Random (0x01)
        Filter policy: Accept all advertisement (0x00)
        PHYs: 0x05
        Entry 0: LE 1M
          Type: Active (0x01)
          Interval: 11.250 msec (0x0012)
          Window: 11.250 msec (0x0012)
        Entry 1: LE Coded
          Type: Active (0x01)
          Interval: 11.250 msec (0x0012)
          Window: 11.250 msec (0x0012)
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Scan Parameters (0x08|0x0041) ncmd 1
        Status: Success (0x00)
< HCI Command: LE Set Extended Scan Enable (0x08|0x0042) plen 6
        Extended scan: Enabled (0x01)
        Filter duplicates: Enabled (0x01)
        Duration: 0 msec (0x0000)
        Period: 0.00 sec (0x0000)
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Scan Enable (0x08|0x0042) ncmd 2
        Status: Success (0x00)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      |  4 +++-
 include/net/bluetooth/hci_core.h |  9 +++++++++
 net/bluetooth/hci_request.c      | 37 ++++++++++++++++++++++++++++---------
 3 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 89bf800f6eb1..04211457367a 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1540,7 +1540,9 @@ struct hci_cp_le_set_ext_scan_params {
 	__u8    data[0];
 } __packed;
 
-#define LE_SCAN_PHY_1M 0x01
+#define LE_SCAN_PHY_1M		0x01
+#define LE_SCAN_PHY_2M		0x02
+#define LE_SCAN_PHY_CODED	0x04
 
 struct hci_cp_le_scan_phy_params {
 	__u8    type;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ab5d494a545a..113c9bb609c7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1165,6 +1165,15 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define bredr_sc_enabled(dev)  (lmp_sc_capable(dev) && \
 				hci_dev_test_flag(dev, HCI_SC_ENABLED))
 
+#define scan_1m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_1M) || \
+		      ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_1M))
+
+#define scan_2m(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_2M) || \
+		      ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_2M))
+
+#define scan_coded(dev) (((dev)->le_tx_def_phys & HCI_LE_SET_PHY_CODED) || \
+			 ((dev)->le_rx_def_phys & HCI_LE_SET_PHY_CODED))
+
 /* Use ext scanning if set ext scan param and ext scan enable is supported */
 #define use_ext_scan(dev) (((dev)->commands[37] & 0x20) && \
 			   ((dev)->commands[37] & 0x40))
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index faf7c711234c..215059a7646e 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -790,8 +790,8 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval,
 		struct hci_cp_le_set_ext_scan_params *ext_param_cp;
 		struct hci_cp_le_set_ext_scan_enable ext_enable_cp;
 		struct hci_cp_le_scan_phy_params *phy_params;
-		/* Ony single PHY (1M) is supported as of now */
-		u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 1];
+		u8 data[sizeof(*ext_param_cp) + sizeof(*phy_params) * 2];
+		u32 plen;
 
 		ext_param_cp = (void *)data;
 		phy_params = (void *)ext_param_cp->data;
@@ -799,16 +799,35 @@ static void hci_req_start_scan(struct hci_request *req, u8 type, u16 interval,
 		memset(ext_param_cp, 0, sizeof(*ext_param_cp));
 		ext_param_cp->own_addr_type = own_addr_type;
 		ext_param_cp->filter_policy = filter_policy;
-		ext_param_cp->scanning_phys = LE_SCAN_PHY_1M;
 
-		memset(phy_params, 0, sizeof(*phy_params));
-		phy_params->type = type;
-		phy_params->interval = cpu_to_le16(interval);
-		phy_params->window = cpu_to_le16(window);
+		plen = sizeof(*ext_param_cp);
+
+		if (scan_1m(hdev) || scan_2m(hdev)) {
+			ext_param_cp->scanning_phys |= LE_SCAN_PHY_1M;
+
+			memset(phy_params, 0, sizeof(*phy_params));
+			phy_params->type = type;
+			phy_params->interval = cpu_to_le16(interval);
+			phy_params->window = cpu_to_le16(window);
+
+			plen += sizeof(*phy_params);
+			phy_params++;
+		}
+
+		if (scan_coded(hdev)) {
+			ext_param_cp->scanning_phys |= LE_SCAN_PHY_CODED;
+
+			memset(phy_params, 0, sizeof(*phy_params));
+			phy_params->type = type;
+			phy_params->interval = cpu_to_le16(interval);
+			phy_params->window = cpu_to_le16(window);
+
+			plen += sizeof(*phy_params);
+			phy_params++;
+		}
 
 		hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_PARAMS,
-			    sizeof(*ext_param_cp) + sizeof(*phy_params),
-			    ext_param_cp);
+			    plen, ext_param_cp);
 
 		memset(&ext_enable_cp, 0, sizeof(ext_enable_cp));
 		ext_enable_cp.enable = LE_SCAN_ENABLE;
-- 
cgit v1.2.3


From b2cc9761f144e8ef714be8c590603073b80ddc13 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:38 +0530
Subject: Bluetooth: Handle extended ADV PDU types

This patch defines the extended ADV types and handle it in ADV report.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  8 ++++++++
 net/bluetooth/hci_event.c   | 50 +++++++++++++++++++++++++++++++++------------
 2 files changed, 45 insertions(+), 13 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 04211457367a..83a1593a128e 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1976,6 +1976,14 @@ struct hci_ev_le_conn_complete {
 #define LE_LEGACY_SCAN_RSP_ADV		0x001b
 #define LE_LEGACY_SCAN_RSP_ADV_SCAN	0x001a
 
+/* Extended Advertising event types */
+#define LE_EXT_ADV_NON_CONN_IND		0x0000
+#define LE_EXT_ADV_CONN_IND		0x0001
+#define LE_EXT_ADV_SCAN_IND		0x0002
+#define LE_EXT_ADV_DIRECT_IND		0x0004
+#define LE_EXT_ADV_SCAN_RSP		0x0008
+#define LE_EXT_ADV_LEGACY_PDU		0x0010
+
 #define ADDR_LE_DEV_PUBLIC	0x00
 #define ADDR_LE_DEV_RANDOM	0x01
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 694231541a4c..5fa00f488cfc 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5137,21 +5137,45 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
-static u8 convert_legacy_evt_type(u16 evt_type)
-{
-	switch (evt_type) {
-	case LE_LEGACY_ADV_IND:
+static u8 ext_evt_type_to_legacy(u16 evt_type)
+{
+	if (evt_type & LE_EXT_ADV_LEGACY_PDU) {
+		switch (evt_type) {
+		case LE_LEGACY_ADV_IND:
+			return LE_ADV_IND;
+		case LE_LEGACY_ADV_DIRECT_IND:
+			return LE_ADV_DIRECT_IND;
+		case LE_LEGACY_ADV_SCAN_IND:
+			return LE_ADV_SCAN_IND;
+		case LE_LEGACY_NONCONN_IND:
+			return LE_ADV_NONCONN_IND;
+		case LE_LEGACY_SCAN_RSP_ADV:
+		case LE_LEGACY_SCAN_RSP_ADV_SCAN:
+			return LE_ADV_SCAN_RSP;
+		}
+
+		BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x",
+				   evt_type);
+
+		return LE_ADV_INVALID;
+	}
+
+	if (evt_type & LE_EXT_ADV_CONN_IND) {
+		if (evt_type & LE_EXT_ADV_DIRECT_IND)
+			return LE_ADV_DIRECT_IND;
+
 		return LE_ADV_IND;
-	case LE_LEGACY_ADV_DIRECT_IND:
-		return LE_ADV_DIRECT_IND;
-	case LE_LEGACY_ADV_SCAN_IND:
+	}
+
+	if (evt_type & LE_EXT_ADV_SCAN_RSP)
+		return LE_ADV_SCAN_RSP;
+
+	if (evt_type & LE_EXT_ADV_SCAN_IND)
 		return LE_ADV_SCAN_IND;
-	case LE_LEGACY_NONCONN_IND:
+
+	if (evt_type == LE_EXT_ADV_NON_CONN_IND ||
+	    evt_type & LE_EXT_ADV_DIRECT_IND)
 		return LE_ADV_NONCONN_IND;
-	case LE_LEGACY_SCAN_RSP_ADV:
-	case LE_LEGACY_SCAN_RSP_ADV_SCAN:
-		return LE_ADV_SCAN_RSP;
-	}
 
 	BT_ERR_RATELIMITED("Unknown advertising packet type: 0x%02x",
 				   evt_type);
@@ -5172,7 +5196,7 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		u16 evt_type;
 
 		evt_type = __le16_to_cpu(ev->evt_type);
-		legacy_evt_type = convert_legacy_evt_type(evt_type);
+		legacy_evt_type = ext_evt_type_to_legacy(evt_type);
 		if (legacy_evt_type != LE_ADV_INVALID) {
 			process_adv_report(hdev, legacy_evt_type, &ev->bdaddr,
 					   ev->bdaddr_type, NULL, 0, ev->rssi,
-- 
cgit v1.2.3


From 4e6e99e9336ce863449c2570dc1d1d6c2c886ac0 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:39 +0530
Subject: Bluetooth: Use selected PHYs in extended connect

Use the selected PHYs by Set PHY Configuration management command
in extended create connection.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/hci_conn.c | 61 +++++++++++++++++++++++++++++++++++-------------
 1 file changed, 45 insertions(+), 16 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index cc967ca67962..64e828ad3951 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -748,6 +748,26 @@ static bool conn_use_rpa(struct hci_conn *conn)
 	return hci_dev_test_flag(hdev, HCI_PRIVACY);
 }
 
+static void set_ext_conn_params(struct hci_conn *conn,
+				struct hci_cp_le_ext_conn_param *p)
+{
+	struct hci_dev *hdev = conn->hdev;
+
+	memset(p, 0, sizeof(*p));
+
+	/* Set window to be the same value as the interval to
+	 * enable continuous scanning.
+	 */
+	p->scan_interval = cpu_to_le16(hdev->le_scan_interval);
+	p->scan_window = p->scan_interval;
+	p->conn_interval_min = cpu_to_le16(conn->le_conn_min_interval);
+	p->conn_interval_max = cpu_to_le16(conn->le_conn_max_interval);
+	p->conn_latency = cpu_to_le16(conn->le_conn_latency);
+	p->supervision_timeout = cpu_to_le16(conn->le_supv_timeout);
+	p->min_ce_len = cpu_to_le16(0x0000);
+	p->max_ce_len = cpu_to_le16(0x0000);
+}
+
 static void hci_req_add_le_create_conn(struct hci_request *req,
 				       struct hci_conn *conn,
 				       bdaddr_t *direct_rpa)
@@ -777,8 +797,8 @@ static void hci_req_add_le_create_conn(struct hci_request *req,
 	if (use_ext_conn(hdev)) {
 		struct hci_cp_le_ext_create_conn *cp;
 		struct hci_cp_le_ext_conn_param *p;
-		/* As of now only LE 1M is supported */
-		u8 data[sizeof(*cp) + sizeof(*p) * 1];
+		u8 data[sizeof(*cp) + sizeof(*p) * 3];
+		u32 plen;
 
 		cp = (void *) data;
 		p = (void *) cp->data;
@@ -788,24 +808,33 @@ static void hci_req_add_le_create_conn(struct hci_request *req,
 		bacpy(&cp->peer_addr, &conn->dst);
 		cp->peer_addr_type = conn->dst_type;
 		cp->own_addr_type = own_addr_type;
-		cp->phys = LE_SCAN_PHY_1M;
 
-		memset(p, 0, sizeof(*p));
+		plen = sizeof(*cp);
 
-		/* Set window to be the same value as the interval to enable
-		 * continuous scanning.
-		 */
+		if (scan_1m(hdev)) {
+			cp->phys |= LE_SCAN_PHY_1M;
+			set_ext_conn_params(conn, p);
+
+			p++;
+			plen += sizeof(*p);
+		}
+
+		if (scan_2m(hdev)) {
+			cp->phys |= LE_SCAN_PHY_2M;
+			set_ext_conn_params(conn, p);
 
-		p->scan_interval = cpu_to_le16(hdev->le_scan_interval);
-		p->scan_window = p->scan_interval;
-		p->conn_interval_min = cpu_to_le16(conn->le_conn_min_interval);
-		p->conn_interval_max = cpu_to_le16(conn->le_conn_max_interval);
-		p->conn_latency = cpu_to_le16(conn->le_conn_latency);
-		p->supervision_timeout = cpu_to_le16(conn->le_supv_timeout);
-		p->min_ce_len = cpu_to_le16(0x0000);
-		p->max_ce_len = cpu_to_le16(0x0000);
+			p++;
+			plen += sizeof(*p);
+		}
+
+		if (scan_coded(hdev)) {
+			cp->phys |= LE_SCAN_PHY_CODED;
+			set_ext_conn_params(conn, p);
+
+			plen += sizeof(*p);
+		}
 
-		hci_req_add(req, HCI_OP_LE_EXT_CREATE_CONN, sizeof(data), data);
+		hci_req_add(req, HCI_OP_LE_EXT_CREATE_CONN, plen, data);
 
 	} else {
 		struct hci_cp_le_create_conn cp;
-- 
cgit v1.2.3


From 6b49bcb4bce2ed0f0aefe8e304a8b9cbaeeaa3f0 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:40 +0530
Subject: Bluetooth: Read no of adv sets during init

This patch reads the number of advertising sets in the controller
during init and save it in hdev.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      |  7 +++++++
 include/net/bluetooth/hci_core.h |  4 ++++
 net/bluetooth/hci_core.c         | 16 ++++++++++++++--
 net/bluetooth/hci_event.c        | 18 ++++++++++++++++++
 4 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 83a1593a128e..3f93ae9765a4 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -410,6 +410,7 @@ enum {
 #define HCI_LE_SLAVE_FEATURES		0x08
 #define HCI_LE_PING			0x10
 #define HCI_LE_DATA_LEN_EXT		0x20
+#define HCI_LE_EXT_ADV			0x10
 #define HCI_LE_EXT_SCAN_POLICY		0x80
 #define HCI_LE_PHY_2M			0x01
 #define HCI_LE_PHY_CODED		0x08
@@ -1579,6 +1580,12 @@ struct hci_cp_le_ext_conn_param {
 	__le16 max_ce_len;
 } __packed;
 
+#define HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS	0x203b
+struct hci_rp_le_read_num_supported_adv_sets {
+	__u8  status;
+	__u8  num_of_sets;
+} __packed;
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 113c9bb609c7..2aad4a863176 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -222,6 +222,7 @@ struct hci_dev {
 	__u8		le_features[8];
 	__u8		le_white_list_size;
 	__u8		le_resolv_list_size;
+	__u8		le_num_of_adv_sets;
 	__u8		le_states[8];
 	__u8		commands[64];
 	__u8		hci_ver;
@@ -1180,6 +1181,9 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 /* Use ext create connection if command is supported */
 #define use_ext_conn(dev) ((dev)->commands[37] & 0x80)
 
+/* Extended advertising support */
+#define ext_adv_capable(dev) (((dev)->le_features[1] & HCI_LE_EXT_ADV))
+
 /* ----- HCI protocols ----- */
 #define HCI_PROTO_DEFER             0x01
 
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 523e91ad64d0..7b08b7f57418 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -715,8 +715,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 		hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events),
 			    events);
 
-		if (hdev->commands[25] & 0x40) {
-			/* Read LE Advertising Channel TX Power */
+		/* Read LE Advertising Channel TX Power */
+		if ((hdev->commands[25] & 0x40) && !ext_adv_capable(hdev)) {
+			/* HCI TS spec forbids mixing of legacy and extended
+			 * advertising commands wherein READ_ADV_TX_POWER is
+			 * also included. So do not call it if extended adv
+			 * is supported otherwise controller will return
+			 * COMMAND_DISALLOWED for extended commands.
+			 */
 			hci_req_add(req, HCI_OP_LE_READ_ADV_TX_POWER, 0, NULL);
 		}
 
@@ -750,6 +756,12 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 			hci_req_add(req, HCI_OP_LE_READ_DEF_DATA_LEN, 0, NULL);
 		}
 
+		if (ext_adv_capable(hdev)) {
+			/* Read LE Number of Supported Advertising Sets */
+			hci_req_add(req, HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS,
+				    0, NULL);
+		}
+
 		hci_set_le_support(req);
 	}
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 5fa00f488cfc..0ceb52edc142 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1267,6 +1267,20 @@ static void hci_cc_le_set_ext_scan_enable(struct hci_dev *hdev,
 	le_set_scan_enable_complete(hdev, cp->enable);
 }
 
+static void hci_cc_le_read_num_adv_sets(struct hci_dev *hdev,
+				      struct sk_buff *skb)
+{
+	struct hci_rp_le_read_num_supported_adv_sets *rp = (void *) skb->data;
+
+	BT_DBG("%s status 0x%2.2x No of Adv sets %u", hdev->name, rp->status,
+	       rp->num_of_sets);
+
+	if (rp->status)
+		return;
+
+	hdev->le_num_of_adv_sets = rp->num_of_sets;
+}
+
 static void hci_cc_le_read_white_list_size(struct hci_dev *hdev,
 					   struct sk_buff *skb)
 {
@@ -3189,6 +3203,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_set_default_phy(hdev, skb);
 		break;
 
+	case HCI_OP_LE_READ_NUM_SUPPORTED_ADV_SETS:
+		hci_cc_le_read_num_adv_sets(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
-- 
cgit v1.2.3


From de181e887ac27dadda127c7d4c3e89c6da8fb6d2 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:41 +0530
Subject: Bluetooth: Impmlement extended adv enable

This patch basically replaces legacy adv with extended adv
based on the controller support. Currently there is no
design change. ie only one adv set will be enabled at a time.

This also adds tx_power in instance and store whatever returns
from Set_ext_parameter, use the same in adv data as well.
For instance 0 tx_power is stored in hdev only.

< HCI Command: LE Set Extended Advertising Parameters (0x08|0x0036) plen 25
        Handle: 0x00
        Properties: 0x0010
          Use legacy advertising PDUs: ADV_NONCONN_IND
        Min advertising interval: 1280.000 msec (0x0800)
        Max advertising interval: 1280.000 msec (0x0800)
        Channel map: 37, 38, 39 (0x07)
        Own address type: Random (0x01)
        Peer address type: Public (0x00)
        Peer address: 00:00:00:00:00:00 (OUI 00-00-00)
        Filter policy: Allow Scan Request from Any, Allow Connect Request from Any (0x00)
        TX power: 127 dbm (0x7f)
        Primary PHY: LE 1M (0x01)
        Secondary max skip: 0x00
        Secondary PHY: LE 1M (0x01)
        SID: 0x00
        Scan request notifications: Disabled (0x00)
> HCI Event: Command Complete (0x0e) plen 5
      LE Set Extended Advertising Parameters (0x08|0x0036) ncmd 1
        Status: Success (0x00)
        TX power (selected): 7 dbm (0x07)
< HCI Command: LE Set Extended Advertising Enable (0x08|0x0039) plen 6
        Extended advertising: Enabled (0x01)
        Number of sets: 1 (0x01)
        Entry 0
          Handle: 0x00
          Duration: 0 ms (0x00)
          Max ext adv events: 0
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Advertising Enable (0x08|0x0039) ncmd 2
        Status: Success (0x00)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      |  39 +++++++++
 include/net/bluetooth/hci_core.h |   1 +
 net/bluetooth/hci_core.c         |   2 +
 net/bluetooth/hci_event.c        |  72 +++++++++++++++++
 net/bluetooth/hci_request.c      | 171 ++++++++++++++++++++++++++++++++++-----
 net/bluetooth/hci_request.h      |   3 +
 net/bluetooth/mgmt.c             |  22 +++--
 7 files changed, 285 insertions(+), 25 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 3f93ae9765a4..b447b127879e 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1586,6 +1586,45 @@ struct hci_rp_le_read_num_supported_adv_sets {
 	__u8  num_of_sets;
 } __packed;
 
+#define HCI_OP_LE_SET_EXT_ADV_PARAMS		0x2036
+struct hci_cp_le_set_ext_adv_params {
+	__u8      handle;
+	__le16    evt_properties;
+	__u8      min_interval[3];
+	__u8      max_interval[3];
+	__u8      channel_map;
+	__u8      own_addr_type;
+	__u8      peer_addr_type;
+	bdaddr_t  peer_addr;
+	__u8      filter_policy;
+	__u8      tx_power;
+	__u8      primary_phy;
+	__u8      secondary_max_skip;
+	__u8      secondary_phy;
+	__u8      sid;
+	__u8      notif_enable;
+} __packed;
+
+#define HCI_ADV_PHY_1M		0X01
+
+struct hci_rp_le_set_ext_adv_params {
+	__u8  status;
+	__u8  tx_power;
+} __packed;
+
+#define HCI_OP_LE_SET_EXT_ADV_ENABLE		0x2039
+struct hci_cp_le_set_ext_adv_enable {
+	__u8  enable;
+	__u8  num_of_sets;
+	__u8  data[0];
+} __packed;
+
+struct hci_cp_ext_adv_set {
+	__u8  handle;
+	__le16 duration;
+	__u8  max_events;
+} __packed;
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 2aad4a863176..ad3518303a0c 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -171,6 +171,7 @@ struct adv_info {
 	__u8	adv_data[HCI_MAX_AD_LENGTH];
 	__u16	scan_rsp_len;
 	__u8	scan_rsp_data[HCI_MAX_AD_LENGTH];
+	__s8	tx_power;
 };
 
 #define HCI_MAX_ADV_INSTANCES		5
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 7b08b7f57418..944d4fedc317 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -2779,6 +2779,8 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 	else
 		adv_instance->duration = duration;
 
+	adv_instance->tx_power = HCI_TX_POWER_INVALID;
+
 	BT_DBG("%s for %dMR", hdev->name, instance);
 
 	return 0;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0ceb52edc142..0418a5514819 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1099,6 +1099,41 @@ static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev,
+					 struct sk_buff *skb)
+{
+	struct hci_cp_le_set_ext_adv_enable *cp;
+	struct hci_cp_ext_adv_set *adv_set;
+	__u8 status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_ENABLE);
+	if (!cp)
+		return;
+
+	adv_set = (void *) cp->data;
+
+	hci_dev_lock(hdev);
+
+	if (cp->enable) {
+		struct hci_conn *conn;
+
+		hci_dev_set_flag(hdev, HCI_LE_ADV);
+
+		conn = hci_lookup_le_connect(hdev);
+		if (conn)
+			queue_delayed_work(hdev->workqueue,
+					   &conn->le_conn_timeout,
+					   conn->conn_timeout);
+	}
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cc_le_set_scan_param(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_cp_le_set_scan_param *cp;
@@ -1486,6 +1521,35 @@ static void hci_cc_set_adv_param(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_set_ext_adv_param(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_rp_le_set_ext_adv_params *rp = (void *) skb->data;
+	struct hci_cp_le_set_ext_adv_params *cp;
+	struct adv_info *adv_instance;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, rp->status);
+
+	if (rp->status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_EXT_ADV_PARAMS);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+	hdev->adv_addr_type = cp->own_addr_type;
+	if (!hdev->cur_adv_instance) {
+		/* Store in hdev for instance 0 */
+		hdev->adv_tx_power = rp->tx_power;
+	} else {
+		adv_instance = hci_find_adv_instance(hdev,
+						     hdev->cur_adv_instance);
+		if (adv_instance)
+			adv_instance->tx_power = rp->tx_power;
+	}
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cc_read_rssi(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct hci_rp_read_rssi *rp = (void *) skb->data;
@@ -3207,6 +3271,14 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_read_num_adv_sets(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_EXT_ADV_PARAMS:
+		hci_cc_set_ext_adv_param(hdev, skb);
+		break;
+
+	case HCI_OP_LE_SET_EXT_ADV_ENABLE:
+		hci_cc_le_set_ext_adv_enable(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 215059a7646e..2ac9fd67440a 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -895,6 +895,24 @@ void hci_req_add_le_passive_scan(struct hci_request *req)
 			   hdev->le_scan_window, own_addr_type, filter_policy);
 }
 
+static u8 get_adv_instance_scan_rsp_len(struct hci_dev *hdev, u8 instance)
+{
+	struct adv_info *adv_instance;
+
+	/* Ignore instance 0 */
+	if (instance == 0x00)
+		return 0;
+
+	adv_instance = hci_find_adv_instance(hdev, instance);
+	if (!adv_instance)
+		return 0;
+
+	/* TODO: Take into account the "appearance" and "local-name" flags here.
+	 * These are currently being ignored as they are not supported.
+	 */
+	return adv_instance->scan_rsp_len;
+}
+
 static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev)
 {
 	u8 instance = hdev->cur_adv_instance;
@@ -1235,15 +1253,27 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
 		ptr += adv_instance->adv_data_len;
 	}
 
-	/* Provide Tx Power only if we can provide a valid value for it */
-	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID &&
-	    (instance_flags & MGMT_ADV_FLAG_TX_POWER)) {
-		ptr[0] = 0x02;
-		ptr[1] = EIR_TX_POWER;
-		ptr[2] = (u8)hdev->adv_tx_power;
+	if (instance_flags & MGMT_ADV_FLAG_TX_POWER) {
+		s8 adv_tx_power;
 
-		ad_len += 3;
-		ptr += 3;
+		if (ext_adv_capable(hdev)) {
+			if (adv_instance)
+				adv_tx_power = adv_instance->tx_power;
+			else
+				adv_tx_power = hdev->adv_tx_power;
+		} else {
+			adv_tx_power = hdev->adv_tx_power;
+		}
+
+		/* Provide Tx Power only if we can provide a valid value for it */
+		if (adv_tx_power != HCI_TX_POWER_INVALID) {
+			ptr[0] = 0x02;
+			ptr[1] = EIR_TX_POWER;
+			ptr[2] = (u8)adv_tx_power;
+
+			ad_len += 3;
+			ptr += 3;
+		}
 	}
 
 	return ad_len;
@@ -1304,9 +1334,13 @@ void hci_req_reenable_advertising(struct hci_dev *hdev)
 		__hci_req_schedule_adv_instance(&req, hdev->cur_adv_instance,
 						true);
 	} else {
-		__hci_req_update_adv_data(&req, 0x00);
-		__hci_req_update_scan_rsp_data(&req, 0x00);
-		__hci_req_enable_advertising(&req);
+		if (ext_adv_capable(hdev)) {
+			__hci_req_start_ext_adv(&req, 0x00);
+		} else {
+			__hci_req_update_adv_data(&req, 0x00);
+			__hci_req_update_scan_rsp_data(&req, 0x00);
+			__hci_req_enable_advertising(&req);
+		}
 	}
 
 	hci_req_run(&req, adv_enable_complete);
@@ -1343,6 +1377,87 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+static int __hci_req_setup_ext_adv_instance(struct hci_request *req,
+					    u8 instance)
+{
+	struct hci_cp_le_set_ext_adv_params cp;
+	struct hci_dev *hdev = req->hdev;
+	bool connectable;
+	u32 flags;
+	/* In ext adv set param interval is 3 octets */
+	const u8 adv_interval[3] = { 0x00, 0x08, 0x00 };
+
+	flags = get_adv_instance_flags(hdev, instance);
+
+	/* If the "connectable" instance flag was not set, then choose between
+	 * ADV_IND and ADV_NONCONN_IND based on the global connectable setting.
+	 */
+	connectable = (flags & MGMT_ADV_FLAG_CONNECTABLE) ||
+		      mgmt_get_connectable(hdev);
+
+	 if (!is_advertising_allowed(hdev, connectable))
+		return -EPERM;
+
+	memset(&cp, 0, sizeof(cp));
+
+	memcpy(cp.min_interval, adv_interval, sizeof(cp.min_interval));
+	memcpy(cp.max_interval, adv_interval, sizeof(cp.max_interval));
+
+	if (connectable)
+		cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND);
+	else if (get_adv_instance_scan_rsp_len(hdev, instance))
+		cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_SCAN_IND);
+	else
+		cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND);
+
+	cp.own_addr_type = BDADDR_LE_PUBLIC;
+	cp.channel_map = hdev->le_adv_channel_map;
+	cp.tx_power = 127;
+	cp.primary_phy = HCI_ADV_PHY_1M;
+	cp.secondary_phy = HCI_ADV_PHY_1M;
+	cp.handle = 0;
+
+	hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp);
+
+	return 0;
+}
+
+void __hci_req_enable_ext_advertising(struct hci_request *req)
+{
+	struct hci_cp_le_set_ext_adv_enable *cp;
+	struct hci_cp_ext_adv_set *adv_set;
+	u8 data[sizeof(*cp) + sizeof(*adv_set) * 1];
+
+	cp = (void *) data;
+	adv_set = (void *) cp->data;
+
+	memset(cp, 0, sizeof(*cp));
+
+	cp->enable = 0x01;
+	cp->num_of_sets = 0x01;
+
+	memset(adv_set, 0, sizeof(*adv_set));
+
+	adv_set->handle = 0;
+
+	hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE,
+		    sizeof(*cp) + sizeof(*adv_set) * cp->num_of_sets,
+		    data);
+}
+
+int __hci_req_start_ext_adv(struct hci_request *req, u8 instance)
+{
+	int err;
+
+	err = __hci_req_setup_ext_adv_instance(req, instance);
+	if (err < 0)
+		return err;
+
+	__hci_req_enable_ext_advertising(req);
+
+	return 0;
+}
+
 int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance,
 				    bool force)
 {
@@ -1396,9 +1511,13 @@ int __hci_req_schedule_adv_instance(struct hci_request *req, u8 instance,
 		return 0;
 
 	hdev->cur_adv_instance = instance;
-	__hci_req_update_adv_data(req, instance);
-	__hci_req_update_scan_rsp_data(req, instance);
-	__hci_req_enable_advertising(req);
+	if (ext_adv_capable(hdev)) {
+		__hci_req_start_ext_adv(req, instance);
+	} else {
+		__hci_req_update_adv_data(req, instance);
+		__hci_req_update_scan_rsp_data(req, instance);
+		__hci_req_enable_advertising(req);
+	}
 
 	return 0;
 }
@@ -1669,8 +1788,12 @@ static int connectable_update(struct hci_request *req, unsigned long opt)
 
 	/* Update the advertising parameters if necessary */
 	if (hci_dev_test_flag(hdev, HCI_ADVERTISING) ||
-	    !list_empty(&hdev->adv_instances))
-		__hci_req_enable_advertising(req);
+	    !list_empty(&hdev->adv_instances)) {
+		if (ext_adv_capable(hdev))
+			__hci_req_start_ext_adv(req, hdev->cur_adv_instance);
+		else
+			__hci_req_enable_advertising(req);
+	}
 
 	__hci_update_background_scan(req);
 
@@ -1779,8 +1902,12 @@ static int discoverable_update(struct hci_request *req, unsigned long opt)
 		/* Discoverable mode affects the local advertising
 		 * address in limited privacy mode.
 		 */
-		if (hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY))
-			__hci_req_enable_advertising(req);
+		if (hci_dev_test_flag(hdev, HCI_LIMITED_PRIVACY)) {
+			if (ext_adv_capable(hdev))
+				__hci_req_start_ext_adv(req, 0x00);
+			else
+				__hci_req_enable_advertising(req);
+		}
 	}
 
 	hci_dev_unlock(hdev);
@@ -2376,8 +2503,12 @@ static int powered_update_hci(struct hci_request *req, unsigned long opt)
 			__hci_req_update_adv_data(req, 0x00);
 			__hci_req_update_scan_rsp_data(req, 0x00);
 
-			if (hci_dev_test_flag(hdev, HCI_ADVERTISING))
-				__hci_req_enable_advertising(req);
+			if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) {
+				if (ext_adv_capable(hdev))
+					__hci_req_start_ext_adv(req, 0x00);
+				else
+					__hci_req_enable_advertising(req);
+			}
 		} else if (!list_empty(&hdev->adv_instances)) {
 			struct adv_info *adv_instance;
 
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 702beb140d9f..9b8c74df6b2b 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -80,6 +80,9 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk,
 				struct hci_request *req, u8 instance,
 				bool force);
 
+int __hci_req_start_ext_adv(struct hci_request *req, u8 instance);
+void __hci_req_enable_ext_advertising(struct hci_request *req);
+
 void __hci_req_update_class(struct hci_request *req);
 
 /* Returns true if HCI commands were queued */
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 1867aadc5061..761a9aeaa824 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -940,7 +940,10 @@ static void rpa_expired(struct work_struct *work)
 	 * function.
 	 */
 	hci_req_init(&req, hdev);
-	__hci_req_enable_advertising(&req);
+	if (ext_adv_capable(hdev))
+		__hci_req_start_ext_adv(&req, hdev->cur_adv_instance);
+	else
+		__hci_req_enable_advertising(&req);
 	hci_req_run(&req, NULL);
 }
 
@@ -4382,9 +4385,14 @@ static int set_advertising(struct sock *sk, struct hci_dev *hdev, void *data,
 		 * HCI_ADVERTISING flag is not yet set.
 		 */
 		hdev->cur_adv_instance = 0x00;
-		__hci_req_update_adv_data(&req, 0x00);
-		__hci_req_update_scan_rsp_data(&req, 0x00);
-		__hci_req_enable_advertising(&req);
+
+		if (ext_adv_capable(hdev)) {
+			__hci_req_start_ext_adv(&req, 0x00);
+		} else {
+			__hci_req_update_adv_data(&req, 0x00);
+			__hci_req_update_scan_rsp_data(&req, 0x00);
+			__hci_req_enable_advertising(&req);
+		}
 	} else {
 		__hci_req_disable_advertising(&req);
 	}
@@ -6312,7 +6320,11 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev)
 	flags |= MGMT_ADV_FLAG_APPEARANCE;
 	flags |= MGMT_ADV_FLAG_LOCAL_NAME;
 
-	if (hdev->adv_tx_power != HCI_TX_POWER_INVALID)
+	/* In extended adv TX_POWER returned from Set Adv Param
+	 * will be always valid.
+	 */
+	if ((hdev->adv_tx_power != HCI_TX_POWER_INVALID) ||
+	    ext_adv_capable(hdev))
 		flags |= MGMT_ADV_FLAG_TX_POWER;
 
 	return flags;
-- 
cgit v1.2.3


From a0fb3726ba55138ef6fdd5dc67da6d9a70360696 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:42 +0530
Subject: Bluetooth: Use Set ext adv/scan rsp data if controller supports

This patch implements Set Ext Adv data and Set Ext Scan rsp data
if controller support extended advertising.

Currently the operation is set as Complete data and fragment
preference is set as no fragment

< HCI Command: LE Set Extended Advertising Data (0x08|0x0037) plen 35
        Handle: 0x00
        Operation: Complete extended advertising data (0x03)
        Fragment preference: Minimize fragmentation (0x01)
        Data length: 0x15
        16-bit Service UUIDs (complete): 2 entries
          Heart Rate (0x180d)
          Battery Service (0x180f)
        Name (complete): Test LE
        Company: Google (224)
          Data: 0102
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Advertising Data (0x08|0x0037) ncmd 1
        Status: Success (0x00)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  22 ++++++++
 net/bluetooth/hci_event.c   |   2 +
 net/bluetooth/hci_request.c | 126 +++++++++++++++++++++++++++++++++-----------
 net/bluetooth/hci_request.h |   1 +
 net/bluetooth/mgmt.c        |  13 +++--
 5 files changed, 130 insertions(+), 34 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index b447b127879e..aace97099ead 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1625,6 +1625,28 @@ struct hci_cp_ext_adv_set {
 	__u8  max_events;
 } __packed;
 
+#define HCI_OP_LE_SET_EXT_ADV_DATA		0x2037
+struct hci_cp_le_set_ext_adv_data {
+	__u8  handle;
+	__u8  operation;
+	__u8  frag_pref;
+	__u8  length;
+	__u8  data[HCI_MAX_AD_LENGTH];
+} __packed;
+
+#define HCI_OP_LE_SET_EXT_SCAN_RSP_DATA		0x2038
+struct hci_cp_le_set_ext_scan_rsp_data {
+	__u8  handle;
+	__u8  operation;
+	__u8  frag_pref;
+	__u8  length;
+	__u8  data[HCI_MAX_AD_LENGTH];
+} __packed;
+
+#define LE_SET_ADV_DATA_OP_COMPLETE	0x03
+
+#define LE_SET_ADV_DATA_NO_FRAG		0x01
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0418a5514819..0a92bf7e3d80 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1547,6 +1547,8 @@ static void hci_cc_set_ext_adv_param(struct hci_dev *hdev, struct sk_buff *skb)
 		if (adv_instance)
 			adv_instance->tx_power = rp->tx_power;
 	}
+	/* Update adv data as tx power is known now */
+	hci_req_update_adv_data(hdev, hdev->cur_adv_instance);
 	hci_dev_unlock(hdev);
 }
 
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 2ac9fd67440a..c41e9bb7818b 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -1174,29 +1174,58 @@ static u8 create_instance_scan_rsp_data(struct hci_dev *hdev, u8 instance,
 void __hci_req_update_scan_rsp_data(struct hci_request *req, u8 instance)
 {
 	struct hci_dev *hdev = req->hdev;
-	struct hci_cp_le_set_scan_rsp_data cp;
 	u8 len;
 
 	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 		return;
 
-	memset(&cp, 0, sizeof(cp));
+	if (ext_adv_capable(hdev)) {
+		struct hci_cp_le_set_ext_scan_rsp_data cp;
 
-	if (instance)
-		len = create_instance_scan_rsp_data(hdev, instance, cp.data);
-	else
-		len = create_default_scan_rsp_data(hdev, cp.data);
+		memset(&cp, 0, sizeof(cp));
 
-	if (hdev->scan_rsp_data_len == len &&
-	    !memcmp(cp.data, hdev->scan_rsp_data, len))
-		return;
+		if (instance)
+			len = create_instance_scan_rsp_data(hdev, instance,
+							    cp.data);
+		else
+			len = create_default_scan_rsp_data(hdev, cp.data);
+
+		if (hdev->scan_rsp_data_len == len &&
+		    !memcmp(cp.data, hdev->scan_rsp_data, len))
+			return;
+
+		memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data));
+		hdev->scan_rsp_data_len = len;
+
+		cp.handle = 0;
+		cp.length = len;
+		cp.operation = LE_SET_ADV_DATA_OP_COMPLETE;
+		cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG;
+
+		hci_req_add(req, HCI_OP_LE_SET_EXT_SCAN_RSP_DATA, sizeof(cp),
+			    &cp);
+	} else {
+		struct hci_cp_le_set_scan_rsp_data cp;
+
+		memset(&cp, 0, sizeof(cp));
+
+		if (instance)
+			len = create_instance_scan_rsp_data(hdev, instance,
+							    cp.data);
+		else
+			len = create_default_scan_rsp_data(hdev, cp.data);
+
+		if (hdev->scan_rsp_data_len == len &&
+		    !memcmp(cp.data, hdev->scan_rsp_data, len))
+			return;
 
-	memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data));
-	hdev->scan_rsp_data_len = len;
+		memcpy(hdev->scan_rsp_data, cp.data, sizeof(cp.data));
+		hdev->scan_rsp_data_len = len;
 
-	cp.length = len;
+		cp.length = len;
 
-	hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp);
+		hci_req_add(req, HCI_OP_LE_SET_SCAN_RSP_DATA, sizeof(cp), &cp);
+	}
 }
 
 static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
@@ -1282,27 +1311,51 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr)
 void __hci_req_update_adv_data(struct hci_request *req, u8 instance)
 {
 	struct hci_dev *hdev = req->hdev;
-	struct hci_cp_le_set_adv_data cp;
 	u8 len;
 
 	if (!hci_dev_test_flag(hdev, HCI_LE_ENABLED))
 		return;
 
-	memset(&cp, 0, sizeof(cp));
+	if (ext_adv_capable(hdev)) {
+		struct hci_cp_le_set_ext_adv_data cp;
 
-	len = create_instance_adv_data(hdev, instance, cp.data);
+		memset(&cp, 0, sizeof(cp));
 
-	/* There's nothing to do if the data hasn't changed */
-	if (hdev->adv_data_len == len &&
-	    memcmp(cp.data, hdev->adv_data, len) == 0)
-		return;
+		len = create_instance_adv_data(hdev, instance, cp.data);
+
+		/* There's nothing to do if the data hasn't changed */
+		if (hdev->adv_data_len == len &&
+		    memcmp(cp.data, hdev->adv_data, len) == 0)
+			return;
+
+		memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
+		hdev->adv_data_len = len;
+
+		cp.length = len;
+		cp.handle = 0;
+		cp.operation = LE_SET_ADV_DATA_OP_COMPLETE;
+		cp.frag_pref = LE_SET_ADV_DATA_NO_FRAG;
 
-	memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
-	hdev->adv_data_len = len;
+		hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_DATA, sizeof(cp), &cp);
+	} else {
+		struct hci_cp_le_set_adv_data cp;
+
+		memset(&cp, 0, sizeof(cp));
 
-	cp.length = len;
+		len = create_instance_adv_data(hdev, instance, cp.data);
+
+		/* There's nothing to do if the data hasn't changed */
+		if (hdev->adv_data_len == len &&
+		    memcmp(cp.data, hdev->adv_data, len) == 0)
+			return;
 
-	hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp);
+		memcpy(hdev->adv_data, cp.data, sizeof(cp.data));
+		hdev->adv_data_len = len;
+
+		cp.length = len;
+
+		hci_req_add(req, HCI_OP_LE_SET_ADV_DATA, sizeof(cp), &cp);
+	}
 }
 
 int hci_req_update_adv_data(struct hci_dev *hdev, u8 instance)
@@ -1377,8 +1430,7 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
-static int __hci_req_setup_ext_adv_instance(struct hci_request *req,
-					    u8 instance)
+int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 {
 	struct hci_cp_le_set_ext_adv_params cp;
 	struct hci_dev *hdev = req->hdev;
@@ -1453,6 +1505,7 @@ int __hci_req_start_ext_adv(struct hci_request *req, u8 instance)
 	if (err < 0)
 		return err;
 
+	__hci_req_update_scan_rsp_data(req, instance);
 	__hci_req_enable_ext_advertising(req);
 
 	return 0;
@@ -2500,14 +2553,25 @@ static int powered_update_hci(struct hci_request *req, unsigned long opt)
 		 */
 		if (hci_dev_test_flag(hdev, HCI_ADVERTISING) ||
 		    list_empty(&hdev->adv_instances)) {
-			__hci_req_update_adv_data(req, 0x00);
-			__hci_req_update_scan_rsp_data(req, 0x00);
+			int err;
+
+			if (ext_adv_capable(hdev)) {
+				err = __hci_req_setup_ext_adv_instance(req,
+								       0x00);
+				if (!err)
+					__hci_req_update_scan_rsp_data(req,
+								       0x00);
+			} else {
+				err = 0;
+				__hci_req_update_adv_data(req, 0x00);
+				__hci_req_update_scan_rsp_data(req, 0x00);
+			}
 
 			if (hci_dev_test_flag(hdev, HCI_ADVERTISING)) {
-				if (ext_adv_capable(hdev))
-					__hci_req_start_ext_adv(req, 0x00);
-				else
+				if (!ext_adv_capable(hdev))
 					__hci_req_enable_advertising(req);
+				else if (!err)
+					__hci_req_enable_ext_advertising(req);
 			}
 		} else if (!list_empty(&hdev->adv_instances)) {
 			struct adv_info *adv_instance;
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 9b8c74df6b2b..6afc624605af 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -80,6 +80,7 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk,
 				struct hci_request *req, u8 instance,
 				bool force);
 
+int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance);
 int __hci_req_start_ext_adv(struct hci_request *req, u8 instance);
 void __hci_req_enable_ext_advertising(struct hci_request *req);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 761a9aeaa824..142f7e72a9a2 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1847,10 +1847,17 @@ static void le_enable_complete(struct hci_dev *hdev, u8 status, u16 opcode)
 	 */
 	if (hci_dev_test_flag(hdev, HCI_LE_ENABLED)) {
 		struct hci_request req;
-
 		hci_req_init(&req, hdev);
-		__hci_req_update_adv_data(&req, 0x00);
-		__hci_req_update_scan_rsp_data(&req, 0x00);
+		if (ext_adv_capable(hdev)) {
+			int err;
+
+			err = __hci_req_setup_ext_adv_instance(&req, 0x00);
+			if (!err)
+				__hci_req_update_scan_rsp_data(&req, 0x00);
+		} else {
+			__hci_req_update_adv_data(&req, 0x00);
+			__hci_req_update_scan_rsp_data(&req, 0x00);
+		}
 		hci_req_run(&req, NULL);
 		hci_update_background_scan(hdev);
 	}
-- 
cgit v1.2.3


From 45b7749f16aacd9ffab8e958caa77e2aa2358c0b Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:43 +0530
Subject: Bluetooth: Implement disable and removal of adv instance

If ext adv is enabled then use ext adv to disable as well.
Also remove the adv set during LE disable.

< HCI Command: LE Set Extended Advertising Enable (0x08|0x0039) plen 2
        Extended advertising: Disabled (0x00)
        Number of sets: Disable all sets (0x00)
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Advertising Enable (0x08|0x0039) ncmd 2
        Status: Success (0x00)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  2 ++
 net/bluetooth/hci_event.c   |  2 ++
 net/bluetooth/hci_request.c | 23 +++++++++++++++++++++--
 net/bluetooth/hci_request.h |  1 +
 net/bluetooth/mgmt.c        |  3 +++
 5 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index aace97099ead..faa2922a69fd 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1647,6 +1647,8 @@ struct hci_cp_le_set_ext_scan_rsp_data {
 
 #define LE_SET_ADV_DATA_NO_FRAG		0x01
 
+#define HCI_OP_LE_CLEAR_ADV_SETS	0x203d
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0a92bf7e3d80..a78d1dd2f57b 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1129,6 +1129,8 @@ static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev,
 			queue_delayed_work(hdev->workqueue,
 					   &conn->le_conn_timeout,
 					   conn->conn_timeout);
+	} else {
+		hci_dev_clear_flag(hdev, HCI_LE_ADV);
 	}
 
 	hci_dev_unlock(hdev);
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index c41e9bb7818b..96e1e05a92c3 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -934,9 +934,19 @@ static u8 get_cur_adv_instance_scan_rsp_len(struct hci_dev *hdev)
 
 void __hci_req_disable_advertising(struct hci_request *req)
 {
-	u8 enable = 0x00;
+	if (ext_adv_capable(req->hdev)) {
+		struct hci_cp_le_set_ext_adv_enable cp;
 
-	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+		cp.enable = 0x00;
+		/* Disable all sets since we only support one set at the moment */
+		cp.num_of_sets = 0x00;
+
+		hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_ENABLE, sizeof(cp), &cp);
+	} else {
+		u8 enable = 0x00;
+
+		hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+	}
 }
 
 static u32 get_adv_instance_flags(struct hci_dev *hdev, u8 instance)
@@ -1430,6 +1440,11 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+void __hci_req_clear_ext_adv_sets(struct hci_request *req)
+{
+	hci_req_add(req, HCI_OP_LE_CLEAR_ADV_SETS, 0, NULL);
+}
+
 int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 {
 	struct hci_cp_le_set_ext_adv_params cp;
@@ -1499,8 +1514,12 @@ void __hci_req_enable_ext_advertising(struct hci_request *req)
 
 int __hci_req_start_ext_adv(struct hci_request *req, u8 instance)
 {
+	struct hci_dev *hdev = req->hdev;
 	int err;
 
+	if (hci_dev_test_flag(hdev, HCI_LE_ADV))
+		__hci_req_disable_advertising(req);
+
 	err = __hci_req_setup_ext_adv_instance(req, instance);
 	if (err < 0)
 		return err;
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 6afc624605af..2451861bb4f8 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -83,6 +83,7 @@ void hci_req_clear_adv_instance(struct hci_dev *hdev, struct sock *sk,
 int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance);
 int __hci_req_start_ext_adv(struct hci_request *req, u8 instance);
 void __hci_req_enable_ext_advertising(struct hci_request *req);
+void __hci_req_clear_ext_adv_sets(struct hci_request *req);
 
 void __hci_req_update_class(struct hci_request *req);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 142f7e72a9a2..c283f0364c0f 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1956,6 +1956,9 @@ static int set_le(struct sock *sk, struct hci_dev *hdev, void *data, u16 len)
 	} else {
 		if (hci_dev_test_flag(hdev, HCI_LE_ADV))
 			__hci_req_disable_advertising(&req);
+
+		if (ext_adv_capable(hdev))
+			__hci_req_clear_ext_adv_sets(&req);
 	}
 
 	hci_req_add(&req, HCI_OP_WRITE_LE_HOST_SUPPORTED, sizeof(hci_cp),
-- 
cgit v1.2.3


From 075e40b79f6d0aa1479701d2dd6dea3b78478d60 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:44 +0530
Subject: Bluetooth: Use ext adv for directed adv

This patch does extended advertising for directed advertising
if the controller supportes. Instance 0 is used for directed
advertising.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/hci_conn.c | 67 ++++++++++++++++++++++++++++++++----------------
 1 file changed, 45 insertions(+), 22 deletions(-)

diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 64e828ad3951..5c37d383caa3 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -868,35 +868,58 @@ static void hci_req_directed_advertising(struct hci_request *req,
 					 struct hci_conn *conn)
 {
 	struct hci_dev *hdev = req->hdev;
-	struct hci_cp_le_set_adv_param cp;
 	u8 own_addr_type;
 	u8 enable;
 
-	/* Clear the HCI_LE_ADV bit temporarily so that the
-	 * hci_update_random_address knows that it's safe to go ahead
-	 * and write a new random address. The flag will be set back on
-	 * as soon as the SET_ADV_ENABLE HCI command completes.
-	 */
-	hci_dev_clear_flag(hdev, HCI_LE_ADV);
+	if (ext_adv_capable(hdev)) {
+		struct hci_cp_le_set_ext_adv_params cp;
 
-	/* Set require_privacy to false so that the remote device has a
-	 * chance of identifying us.
-	 */
-	if (hci_update_random_address(req, false, conn_use_rpa(conn),
-				      &own_addr_type) < 0)
-		return;
+		memset(&cp, 0, sizeof(cp));
 
-	memset(&cp, 0, sizeof(cp));
-	cp.type = LE_ADV_DIRECT_IND;
-	cp.own_address_type = own_addr_type;
-	cp.direct_addr_type = conn->dst_type;
-	bacpy(&cp.direct_addr, &conn->dst);
-	cp.channel_map = hdev->le_adv_channel_map;
+		cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_DIRECT_IND);
+		cp.own_addr_type = own_addr_type;
+		cp.channel_map = hdev->le_adv_channel_map;
+		cp.tx_power = HCI_TX_POWER_INVALID;
+		cp.primary_phy = HCI_ADV_PHY_1M;
+		cp.secondary_phy = HCI_ADV_PHY_1M;
+		cp.handle = 0; /* Use instance 0 for directed adv */
+		cp.own_addr_type = own_addr_type;
+		cp.peer_addr_type = conn->dst_type;
+		bacpy(&cp.peer_addr, &conn->dst);
+
+		hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp);
 
-	hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp);
+		__hci_req_enable_ext_advertising(req);
+	} else {
+		struct hci_cp_le_set_adv_param cp;
+
+		/* Clear the HCI_LE_ADV bit temporarily so that the
+		 * hci_update_random_address knows that it's safe to go ahead
+		 * and write a new random address. The flag will be set back on
+		 * as soon as the SET_ADV_ENABLE HCI command completes.
+		 */
+		hci_dev_clear_flag(hdev, HCI_LE_ADV);
 
-	enable = 0x01;
-	hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable), &enable);
+		/* Set require_privacy to false so that the remote device has a
+		 * chance of identifying us.
+		 */
+		if (hci_update_random_address(req, false, conn_use_rpa(conn),
+					      &own_addr_type) < 0)
+			return;
+
+		memset(&cp, 0, sizeof(cp));
+		cp.type = LE_ADV_DIRECT_IND;
+		cp.own_address_type = own_addr_type;
+		cp.direct_addr_type = conn->dst_type;
+		bacpy(&cp.direct_addr, &conn->dst);
+		cp.channel_map = hdev->le_adv_channel_map;
+
+		hci_req_add(req, HCI_OP_LE_SET_ADV_PARAM, sizeof(cp), &cp);
+
+		enable = 0x01;
+		hci_req_add(req, HCI_OP_LE_SET_ADV_ENABLE, sizeof(enable),
+			    &enable);
+	}
 
 	conn->state = BT_CONNECT;
 }
-- 
cgit v1.2.3


From a73c046a2869048430c332a871a5b169f192c6c3 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:45 +0530
Subject: Bluetooth: Implement Set ADV set random address

This basically sets the random address for the adv instance
Random address can be set only if the instance is created which
is done in Set ext adv param.

Random address and rpa expire timer and flags have been added
to adv instance which will be used when the respective
instance is scheduled.

This introduces a hci_get_random_address() which returns the
own address type and random address (rpa or nrpa) based
on the instance flags and hdev flags. New function is required
since own address type should be known before setting adv params
but address can be set only after setting params.

< HCI Command: LE Set Advertising Set Random Address (0x08|0x0035) plen 7
        Advertising handle: 0x00
        Advertising random address: 3C:8E:56:9B:77:84 (OUI 3C-8E-56)
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Advertising Set Random Address (0x08|0x0035) ncmd 1
        Status: Success (0x00)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h      |   6 ++
 include/net/bluetooth/hci_core.h |   4 ++
 net/bluetooth/hci_conn.c         |  23 +++++++
 net/bluetooth/hci_core.c         |  33 +++++++++-
 net/bluetooth/hci_event.c        |  37 ++++++++++-
 net/bluetooth/hci_request.c      | 128 ++++++++++++++++++++++++++++++++++++++-
 net/bluetooth/hci_request.h      |   3 +
 net/bluetooth/mgmt.c             |   2 +
 8 files changed, 233 insertions(+), 3 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index faa2922a69fd..8d348d0d3eea 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -1649,6 +1649,12 @@ struct hci_cp_le_set_ext_scan_rsp_data {
 
 #define HCI_OP_LE_CLEAR_ADV_SETS	0x203d
 
+#define HCI_OP_LE_SET_ADV_SET_RAND_ADDR	0x2035
+struct hci_cp_le_set_adv_set_rand_addr {
+	__u8  handle;
+	bdaddr_t  bdaddr;
+} __packed;
+
 /* ---- HCI Events ---- */
 #define HCI_EV_INQUIRY_COMPLETE		0x01
 
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index ad3518303a0c..0db1b9b428b7 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -172,6 +172,9 @@ struct adv_info {
 	__u16	scan_rsp_len;
 	__u8	scan_rsp_data[HCI_MAX_AD_LENGTH];
 	__s8	tx_power;
+	bdaddr_t	random_addr;
+	bool 		rpa_expired;
+	struct delayed_work	rpa_expired_cb;
 };
 
 #define HCI_MAX_ADV_INSTANCES		5
@@ -1113,6 +1116,7 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 			 u16 scan_rsp_len, u8 *scan_rsp_data,
 			 u16 timeout, u16 duration);
 int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance);
+void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired);
 
 void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb);
 
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index 5c37d383caa3..bd4978ce8c45 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -873,6 +873,14 @@ static void hci_req_directed_advertising(struct hci_request *req,
 
 	if (ext_adv_capable(hdev)) {
 		struct hci_cp_le_set_ext_adv_params cp;
+		bdaddr_t random_addr;
+
+		/* Set require_privacy to false so that the remote device has a
+		 * chance of identifying us.
+		 */
+		if (hci_get_random_address(hdev, false, conn_use_rpa(conn), NULL,
+					   &own_addr_type, &random_addr) < 0)
+			return;
 
 		memset(&cp, 0, sizeof(cp));
 
@@ -889,6 +897,21 @@ static void hci_req_directed_advertising(struct hci_request *req,
 
 		hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp);
 
+		if (own_addr_type == ADDR_LE_DEV_RANDOM &&
+		    bacmp(&random_addr, BDADDR_ANY) &&
+		    bacmp(&random_addr, &hdev->random_addr)) {
+			struct hci_cp_le_set_adv_set_rand_addr cp;
+
+			memset(&cp, 0, sizeof(cp));
+
+			cp.handle = 0;
+			bacpy(&cp.bdaddr, &random_addr);
+
+			hci_req_add(req,
+				    HCI_OP_LE_SET_ADV_SET_RAND_ADDR,
+				    sizeof(cp), &cp);
+		}
+
 		__hci_req_enable_ext_advertising(req);
 	} else {
 		struct hci_cp_le_set_adv_param cp;
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 944d4fedc317..840e8fd89fa5 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1471,6 +1471,7 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 	if (!ret) {
 		hci_dev_hold(hdev);
 		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
+		hci_adv_instances_set_rpa_expired(hdev, true);
 		set_bit(HCI_UP, &hdev->flags);
 		hci_sock_dev_event(hdev, HCI_DEV_UP);
 		hci_leds_update_powered(hdev, true);
@@ -1626,9 +1627,15 @@ int hci_dev_do_close(struct hci_dev *hdev)
 	if (hci_dev_test_and_clear_flag(hdev, HCI_SERVICE_CACHE))
 		cancel_delayed_work(&hdev->service_cache);
 
-	if (hci_dev_test_flag(hdev, HCI_MGMT))
+	if (hci_dev_test_flag(hdev, HCI_MGMT)) {
+		struct adv_info *adv_instance;
+
 		cancel_delayed_work_sync(&hdev->rpa_expired);
 
+		list_for_each_entry(adv_instance, &hdev->adv_instances, list)
+			cancel_delayed_work_sync(&adv_instance->rpa_expired_cb);
+	}
+
 	/* Avoid potential lockdep warnings from the *_flush() calls by
 	 * ensuring the workqueue is empty up front.
 	 */
@@ -2704,6 +2711,8 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance)
 		hdev->cur_adv_instance = 0x00;
 	}
 
+	cancel_delayed_work_sync(&adv_instance->rpa_expired_cb);
+
 	list_del(&adv_instance->list);
 	kfree(adv_instance);
 
@@ -2712,6 +2721,14 @@ int hci_remove_adv_instance(struct hci_dev *hdev, u8 instance)
 	return 0;
 }
 
+void hci_adv_instances_set_rpa_expired(struct hci_dev *hdev, bool rpa_expired)
+{
+	struct adv_info *adv_instance, *n;
+
+	list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list)
+		adv_instance->rpa_expired = rpa_expired;
+}
+
 /* This function requires the caller holds hdev->lock */
 void hci_adv_instances_clear(struct hci_dev *hdev)
 {
@@ -2723,6 +2740,7 @@ void hci_adv_instances_clear(struct hci_dev *hdev)
 	}
 
 	list_for_each_entry_safe(adv_instance, n, &hdev->adv_instances, list) {
+		cancel_delayed_work_sync(&adv_instance->rpa_expired_cb);
 		list_del(&adv_instance->list);
 		kfree(adv_instance);
 	}
@@ -2731,6 +2749,16 @@ void hci_adv_instances_clear(struct hci_dev *hdev)
 	hdev->cur_adv_instance = 0x00;
 }
 
+static void adv_instance_rpa_expired(struct work_struct *work)
+{
+	struct adv_info *adv_instance = container_of(work, struct adv_info,
+						     rpa_expired_cb.work);
+
+	BT_DBG("");
+
+	adv_instance->rpa_expired = true;
+}
+
 /* This function requires the caller holds hdev->lock */
 int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 			 u16 adv_data_len, u8 *adv_data,
@@ -2781,6 +2809,9 @@ int hci_add_adv_instance(struct hci_dev *hdev, u8 instance, u32 flags,
 
 	adv_instance->tx_power = HCI_TX_POWER_INVALID;
 
+	INIT_DELAYED_WORK(&adv_instance->rpa_expired_cb,
+			  adv_instance_rpa_expired);
+
 	BT_DBG("%s for %dMR", hdev->name, instance);
 
 	return 0;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index a78d1dd2f57b..392c9d8febd0 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1064,6 +1064,35 @@ static void hci_cc_le_set_default_phy(struct hci_dev *hdev, struct sk_buff *skb)
 	hci_dev_unlock(hdev);
 }
 
+static void hci_cc_le_set_adv_set_random_addr(struct hci_dev *hdev,
+                                              struct sk_buff *skb)
+{
+	__u8 status = *((__u8 *) skb->data);
+	struct hci_cp_le_set_adv_set_rand_addr *cp;
+	struct adv_info *adv_instance;
+
+	if (status)
+		return;
+
+	cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADV_SET_RAND_ADDR);
+	if (!cp)
+		return;
+
+	hci_dev_lock(hdev);
+
+	if (!hdev->cur_adv_instance) {
+		/* Store in hdev for instance 0 (Set adv and Directed advs) */
+		bacpy(&hdev->random_addr, &cp->bdaddr);
+	} else {
+		adv_instance = hci_find_adv_instance(hdev,
+						     hdev->cur_adv_instance);
+		if (adv_instance)
+			bacpy(&adv_instance->random_addr, &cp->bdaddr);
+	}
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cc_le_set_adv_enable(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	__u8 *sent, status = *((__u8 *) skb->data);
@@ -2830,8 +2859,10 @@ static void hci_encrypt_change_evt(struct hci_dev *hdev, struct sk_buff *skb)
 	/* We should disregard the current RPA and generate a new one
 	 * whenever the encryption procedure fails.
 	 */
-	if (ev->status && conn->type == LE_LINK)
+	if (ev->status && conn->type == LE_LINK) {
 		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
+		hci_adv_instances_set_rpa_expired(hdev, true);
+	}
 
 	clear_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags);
 
@@ -3283,6 +3314,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_set_ext_adv_enable(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_ADV_SET_RAND_ADDR:
+		hci_cc_le_set_adv_set_random_addr(hdev, skb);
+		break;
+
 	default:
 		BT_DBG("%s opcode 0x%4.4x", hdev->name, *opcode);
 		break;
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index 96e1e05a92c3..c72fd9202666 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -1440,6 +1440,87 @@ unlock:
 	hci_dev_unlock(hdev);
 }
 
+int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
+			   bool use_rpa, struct adv_info *adv_instance,
+			   u8 *own_addr_type, bdaddr_t *rand_addr)
+{
+	int err;
+
+	bacpy(rand_addr, BDADDR_ANY);
+
+	/* If privacy is enabled use a resolvable private address. If
+	 * current RPA has expired then generate a new one.
+	 */
+	if (use_rpa) {
+		int to;
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+
+		if (adv_instance) {
+			if (!adv_instance->rpa_expired &&
+			    !bacmp(&adv_instance->random_addr, &hdev->rpa))
+				return 0;
+
+			adv_instance->rpa_expired = false;
+		} else {
+			if (!hci_dev_test_and_clear_flag(hdev, HCI_RPA_EXPIRED) &&
+			    !bacmp(&hdev->random_addr, &hdev->rpa))
+				return 0;
+		}
+
+		err = smp_generate_rpa(hdev, hdev->irk, &hdev->rpa);
+		if (err < 0) {
+			BT_ERR("%s failed to generate new RPA", hdev->name);
+			return err;
+		}
+
+		bacpy(rand_addr, &hdev->rpa);
+
+		to = msecs_to_jiffies(hdev->rpa_timeout * 1000);
+		if (adv_instance)
+			queue_delayed_work(hdev->workqueue,
+					   &adv_instance->rpa_expired_cb, to);
+		else
+			queue_delayed_work(hdev->workqueue,
+					   &hdev->rpa_expired, to);
+
+		return 0;
+	}
+
+	/* In case of required privacy without resolvable private address,
+	 * use an non-resolvable private address. This is useful for
+	 * non-connectable advertising.
+	 */
+	if (require_privacy) {
+		bdaddr_t nrpa;
+
+		while (true) {
+			/* The non-resolvable private address is generated
+			 * from random six bytes with the two most significant
+			 * bits cleared.
+			 */
+			get_random_bytes(&nrpa, 6);
+			nrpa.b[5] &= 0x3f;
+
+			/* The non-resolvable private address shall not be
+			 * equal to the public address.
+			 */
+			if (bacmp(&hdev->bdaddr, &nrpa))
+				break;
+		}
+
+		*own_addr_type = ADDR_LE_DEV_RANDOM;
+		bacpy(rand_addr, &nrpa);
+
+		return 0;
+	}
+
+	/* No privacy so use a public address. */
+	*own_addr_type = ADDR_LE_DEV_PUBLIC;
+
+	return 0;
+}
+
 void __hci_req_clear_ext_adv_sets(struct hci_request *req)
 {
 	hci_req_add(req, HCI_OP_LE_CLEAR_ADV_SETS, 0, NULL);
@@ -1451,9 +1532,21 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 	struct hci_dev *hdev = req->hdev;
 	bool connectable;
 	u32 flags;
+	bdaddr_t random_addr;
+	u8 own_addr_type;
+	int err;
+	struct adv_info *adv_instance;
 	/* In ext adv set param interval is 3 octets */
 	const u8 adv_interval[3] = { 0x00, 0x08, 0x00 };
 
+	if (instance > 0) {
+		adv_instance = hci_find_adv_instance(hdev, instance);
+		if (!adv_instance)
+			return -EINVAL;
+	} else {
+		adv_instance = NULL;
+	}
+
 	flags = get_adv_instance_flags(hdev, instance);
 
 	/* If the "connectable" instance flag was not set, then choose between
@@ -1465,6 +1558,16 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 	 if (!is_advertising_allowed(hdev, connectable))
 		return -EPERM;
 
+	/* Set require_privacy to true only when non-connectable
+	 * advertising is used. In that case it is fine to use a
+	 * non-resolvable private address.
+	 */
+	err = hci_get_random_address(hdev, !connectable,
+				     adv_use_rpa(hdev, flags), adv_instance,
+				     &own_addr_type, &random_addr);
+	if (err < 0)
+		return err;
+
 	memset(&cp, 0, sizeof(cp));
 
 	memcpy(cp.min_interval, adv_interval, sizeof(cp.min_interval));
@@ -1477,7 +1580,7 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 	else
 		cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND);
 
-	cp.own_addr_type = BDADDR_LE_PUBLIC;
+	cp.own_addr_type = own_addr_type;
 	cp.channel_map = hdev->le_adv_channel_map;
 	cp.tx_power = 127;
 	cp.primary_phy = HCI_ADV_PHY_1M;
@@ -1486,6 +1589,29 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 
 	hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp);
 
+	if (own_addr_type == ADDR_LE_DEV_RANDOM &&
+	    bacmp(&random_addr, BDADDR_ANY)) {
+		struct hci_cp_le_set_adv_set_rand_addr cp;
+
+		/* Check if random address need to be updated */
+		if (adv_instance) {
+			if (!bacmp(&random_addr, &adv_instance->random_addr))
+				return 0;
+		} else {
+			if (!bacmp(&random_addr, &hdev->random_addr))
+				return 0;
+		}
+
+		memset(&cp, 0, sizeof(cp));
+
+		cp.handle = 0;
+		bacpy(&cp.bdaddr, &random_addr);
+
+		hci_req_add(req,
+			    HCI_OP_LE_SET_ADV_SET_RAND_ADDR,
+			    sizeof(cp), &cp);
+	}
+
 	return 0;
 }
 
diff --git a/net/bluetooth/hci_request.h b/net/bluetooth/hci_request.h
index 2451861bb4f8..692cc8b13368 100644
--- a/net/bluetooth/hci_request.h
+++ b/net/bluetooth/hci_request.h
@@ -84,6 +84,9 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance);
 int __hci_req_start_ext_adv(struct hci_request *req, u8 instance);
 void __hci_req_enable_ext_advertising(struct hci_request *req);
 void __hci_req_clear_ext_adv_sets(struct hci_request *req);
+int hci_get_random_address(struct hci_dev *hdev, bool require_privacy,
+			   bool use_rpa, struct adv_info *adv_instance,
+			   u8 *own_addr_type, bdaddr_t *rand_addr);
 
 void __hci_req_update_class(struct hci_request *req);
 
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index c283f0364c0f..949986727019 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -4972,6 +4972,7 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 		changed = !hci_dev_test_and_set_flag(hdev, HCI_PRIVACY);
 		memcpy(hdev->irk, cp->irk, sizeof(hdev->irk));
 		hci_dev_set_flag(hdev, HCI_RPA_EXPIRED);
+		hci_adv_instances_set_rpa_expired(hdev, true);
 		if (cp->privacy == 0x02)
 			hci_dev_set_flag(hdev, HCI_LIMITED_PRIVACY);
 		else
@@ -4980,6 +4981,7 @@ static int set_privacy(struct sock *sk, struct hci_dev *hdev, void *cp_data,
 		changed = hci_dev_test_and_clear_flag(hdev, HCI_PRIVACY);
 		memset(hdev->irk, 0, sizeof(hdev->irk));
 		hci_dev_clear_flag(hdev, HCI_RPA_EXPIRED);
+		hci_adv_instances_set_rpa_expired(hdev, false);
 		hci_dev_clear_flag(hdev, HCI_LIMITED_PRIVACY);
 	}
 
-- 
cgit v1.2.3


From acf0aeae431a0f1723385cd1cb50177e4cc10edd Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:46 +0530
Subject: Bluetooth: Handle ADv set terminated event

This event comes after connection complete event for incoming
connections. Since we now have different random address for
each instance, conn resp address is assigned from this event.

As of now only connection part is handled as we are not
enabling duration or max num of events while starting ext adv.

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  8 ++++++++
 net/bluetooth/hci_core.c    |  8 ++++++++
 net/bluetooth/hci_event.c   | 43 ++++++++++++++++++++++++++++++++++++++++---
 3 files changed, 56 insertions(+), 3 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 8d348d0d3eea..57e3e3675d66 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -2155,6 +2155,14 @@ struct hci_ev_le_enh_conn_complete {
 	__u8      clk_accurancy;
 } __packed;
 
+#define HCI_EV_LE_EXT_ADV_SET_TERM	0x12
+struct hci_evt_le_ext_adv_set_term {
+	__u8	status;
+	__u8	handle;
+	__le16	conn_handle;
+	__u8	num_evts;
+} __packed;
+
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL	0xfd
 struct hci_ev_stack_internal {
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 840e8fd89fa5..79e02d24a215 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -712,6 +712,14 @@ static int hci_init3_req(struct hci_request *req, unsigned long opt)
 						 * Complete
 						 */
 
+		/* If the controller supports the LE Extended Advertising
+		 * command, enable the corresponding event.
+		 */
+		if (ext_adv_capable(hdev))
+			events[2] |= 0x02;	/* LE Advertising Set
+						 * Terminated
+						 */
+
 		hci_req_add(req, HCI_OP_LE_SET_EVENT_MASK, sizeof(events),
 			    events);
 
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 392c9d8febd0..754714c8d752 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4798,10 +4798,15 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status,
 		 * the advertising address type.
 		 */
 		conn->resp_addr_type = hdev->adv_addr_type;
-		if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM)
-			bacpy(&conn->resp_addr, &hdev->random_addr);
-		else
+		if (hdev->adv_addr_type == ADDR_LE_DEV_RANDOM) {
+			/* In case of ext adv, resp_addr will be updated in
+			 * Adv Terminated event.
+			 */
+			if (!ext_adv_capable(hdev))
+				bacpy(&conn->resp_addr, &hdev->random_addr);
+		} else {
 			bacpy(&conn->resp_addr, &hdev->bdaddr);
+		}
 
 		conn->init_addr_type = bdaddr_type;
 		bacpy(&conn->init_addr, bdaddr);
@@ -4931,6 +4936,34 @@ static void hci_le_enh_conn_complete_evt(struct hci_dev *hdev,
 			     le16_to_cpu(ev->supervision_timeout));
 }
 
+static void hci_le_ext_adv_term_evt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_evt_le_ext_adv_set_term *ev = (void *) skb->data;
+	struct hci_conn *conn;
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, ev->status);
+
+	if (ev->status)
+		return;
+
+	conn = hci_conn_hash_lookup_handle(hdev, __le16_to_cpu(ev->conn_handle));
+	if (conn) {
+		struct adv_info *adv_instance;
+
+		if (hdev->adv_addr_type != ADDR_LE_DEV_RANDOM)
+			return;
+
+		if (!hdev->cur_adv_instance) {
+			bacpy(&conn->resp_addr, &hdev->random_addr);
+			return;
+		}
+
+		adv_instance = hci_find_adv_instance(hdev, hdev->cur_adv_instance);
+		if (adv_instance)
+			bacpy(&conn->resp_addr, &adv_instance->random_addr);
+	}
+}
+
 static void hci_le_conn_update_complete_evt(struct hci_dev *hdev,
 					    struct sk_buff *skb)
 {
@@ -5578,6 +5611,10 @@ static void hci_le_meta_evt(struct hci_dev *hdev, struct sk_buff *skb)
 		hci_le_enh_conn_complete_evt(hdev, skb);
 		break;
 
+	case HCI_EV_LE_EXT_ADV_SET_TERM:
+		hci_le_ext_adv_term_evt(hdev, skb);
+		break;
+
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From 85a721a8b0b6880d8cf6b9def70404ade8563225 Mon Sep 17 00:00:00 2001
From: Jaganath Kanakkassery <jaganath.k.os@gmail.com>
Date: Thu, 19 Jul 2018 17:09:47 +0530
Subject: Bluetooth: Implement secondary advertising on different PHYs

This patch adds support for advertising in primary and secondary
channel on different PHYs. User can add the phy preference in
the flag based on which phy type will be added in extended
advertising parameter would be set.

@ MGMT Command: Add Advertising (0x003e) plen 11
        Instance: 1
        Flags: 0x00000200
          Advertise in CODED on Secondary channel
        Duration: 0
        Timeout: 0
        Advertising data length: 0
        Scan response length: 0
< HCI Command: LE Set Extended Advertising Enable (0x08|0x0039) plen 2
        Extended advertising: Disabled (0x00)
        Number of sets: Disable all sets (0x00)
> HCI Event: Command Complete (0x0e) plen 4
      LE Set Extended Advertising Enable (0x08|0x0039) ncmd 2
        Status: Success (0x00)
< HCI Command: LE Set Extended Advertising Parameters (0x08|0x0036) plen 25
        Handle: 0x00
        Properties: 0x0000
        Min advertising interval: 1280.000 msec (0x0800)
        Max advertising interval: 1280.000 msec (0x0800)
        Channel map: 37, 38, 39 (0x07)
        Own address type: Random (0x01)
        Peer address type: Public (0x00)
        Peer address: 00:00:00:00:00:00 (OUI 00-00-00)
        Filter policy: Allow Scan Request from Any, Allow Connect Request from Any (0x00)
        TX power: 127 dbm (0x7f)
        Primary PHY: LE Coded (0x03)
        Secondary max skip: 0x00
        Secondary PHY: LE Coded (0x03)
        SID: 0x00
        Scan request notifications: Disabled (0x00)

Signed-off-by: Jaganath Kanakkassery <jaganathx.kanakkassery@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h  |  4 ++++
 include/net/bluetooth/mgmt.h |  6 ++++++
 net/bluetooth/hci_request.c  | 39 +++++++++++++++++++++++++++++++--------
 net/bluetooth/mgmt.c         | 18 +++++++++++++++---
 4 files changed, 56 insertions(+), 11 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 57e3e3675d66..8ff36463719f 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -410,6 +410,8 @@ enum {
 #define HCI_LE_SLAVE_FEATURES		0x08
 #define HCI_LE_PING			0x10
 #define HCI_LE_DATA_LEN_EXT		0x20
+#define HCI_LE_PHY_2M			0x01
+#define HCI_LE_PHY_CODED		0x08
 #define HCI_LE_EXT_ADV			0x10
 #define HCI_LE_EXT_SCAN_POLICY		0x80
 #define HCI_LE_PHY_2M			0x01
@@ -1606,6 +1608,8 @@ struct hci_cp_le_set_ext_adv_params {
 } __packed;
 
 #define HCI_ADV_PHY_1M		0X01
+#define HCI_ADV_PHY_2M		0x02
+#define HCI_ADV_PHY_CODED	0x03
 
 struct hci_rp_le_set_ext_adv_params {
 	__u8  status;
diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h
index 7f372e9067c9..9cee7ddc6741 100644
--- a/include/net/bluetooth/mgmt.h
+++ b/include/net/bluetooth/mgmt.h
@@ -562,6 +562,12 @@ struct mgmt_rp_add_advertising {
 #define MGMT_ADV_FLAG_TX_POWER		BIT(4)
 #define MGMT_ADV_FLAG_APPEARANCE	BIT(5)
 #define MGMT_ADV_FLAG_LOCAL_NAME	BIT(6)
+#define MGMT_ADV_FLAG_SEC_1M 		BIT(7)
+#define MGMT_ADV_FLAG_SEC_2M 		BIT(8)
+#define MGMT_ADV_FLAG_SEC_CODED 	BIT(9)
+
+#define MGMT_ADV_FLAG_SEC_MASK	(MGMT_ADV_FLAG_SEC_1M | MGMT_ADV_FLAG_SEC_2M | \
+				 MGMT_ADV_FLAG_SEC_CODED)
 
 #define MGMT_OP_REMOVE_ADVERTISING	0x003F
 struct mgmt_cp_remove_advertising {
diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c
index c72fd9202666..e8c9ef1e1922 100644
--- a/net/bluetooth/hci_request.c
+++ b/net/bluetooth/hci_request.c
@@ -1536,6 +1536,7 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 	u8 own_addr_type;
 	int err;
 	struct adv_info *adv_instance;
+	bool secondary_adv;
 	/* In ext adv set param interval is 3 octets */
 	const u8 adv_interval[3] = { 0x00, 0x08, 0x00 };
 
@@ -1573,20 +1574,42 @@ int __hci_req_setup_ext_adv_instance(struct hci_request *req, u8 instance)
 	memcpy(cp.min_interval, adv_interval, sizeof(cp.min_interval));
 	memcpy(cp.max_interval, adv_interval, sizeof(cp.max_interval));
 
-	if (connectable)
-		cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND);
-	else if (get_adv_instance_scan_rsp_len(hdev, instance))
-		cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_SCAN_IND);
-	else
-		cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND);
+	secondary_adv = (flags & MGMT_ADV_FLAG_SEC_MASK);
+
+	if (connectable) {
+		if (secondary_adv)
+			cp.evt_properties = cpu_to_le16(LE_EXT_ADV_CONN_IND);
+		else
+			cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_IND);
+	} else if (get_adv_instance_scan_rsp_len(hdev, instance)) {
+		if (secondary_adv)
+			cp.evt_properties = cpu_to_le16(LE_EXT_ADV_SCAN_IND);
+		else
+			cp.evt_properties = cpu_to_le16(LE_LEGACY_ADV_SCAN_IND);
+	} else {
+		if (secondary_adv)
+			cp.evt_properties = cpu_to_le16(LE_EXT_ADV_NON_CONN_IND);
+		else
+			cp.evt_properties = cpu_to_le16(LE_LEGACY_NONCONN_IND);
+	}
 
 	cp.own_addr_type = own_addr_type;
 	cp.channel_map = hdev->le_adv_channel_map;
 	cp.tx_power = 127;
-	cp.primary_phy = HCI_ADV_PHY_1M;
-	cp.secondary_phy = HCI_ADV_PHY_1M;
 	cp.handle = 0;
 
+	if (flags & MGMT_ADV_FLAG_SEC_2M) {
+		cp.primary_phy = HCI_ADV_PHY_1M;
+		cp.secondary_phy = HCI_ADV_PHY_2M;
+	} else if (flags & MGMT_ADV_FLAG_SEC_CODED) {
+		cp.primary_phy = HCI_ADV_PHY_CODED;
+		cp.secondary_phy = HCI_ADV_PHY_CODED;
+	} else {
+		/* In all other cases use 1M */
+		cp.primary_phy = HCI_ADV_PHY_1M;
+		cp.secondary_phy = HCI_ADV_PHY_1M;
+	}
+
 	hci_req_add(req, HCI_OP_LE_SET_EXT_ADV_PARAMS, sizeof(cp), &cp);
 
 	if (own_addr_type == ADDR_LE_DEV_RANDOM &&
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 949986727019..231602f7cb66 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -6339,6 +6339,16 @@ static u32 get_supported_adv_flags(struct hci_dev *hdev)
 	    ext_adv_capable(hdev))
 		flags |= MGMT_ADV_FLAG_TX_POWER;
 
+	if (ext_adv_capable(hdev)) {
+		flags |= MGMT_ADV_FLAG_SEC_1M;
+
+		if (hdev->le_features[1] & HCI_LE_PHY_2M)
+			flags |= MGMT_ADV_FLAG_SEC_2M;
+
+		if (hdev->le_features[1] & HCI_LE_PHY_CODED)
+			flags |= MGMT_ADV_FLAG_SEC_CODED;
+	}
+
 	return flags;
 }
 
@@ -6544,7 +6554,7 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 	struct mgmt_cp_add_advertising *cp = data;
 	struct mgmt_rp_add_advertising rp;
 	u32 flags;
-	u32 supported_flags;
+	u32 supported_flags, phy_flags;
 	u8 status;
 	u16 timeout, duration;
 	unsigned int prev_instance_cnt = hdev->adv_instance_cnt;
@@ -6574,10 +6584,12 @@ static int add_advertising(struct sock *sk, struct hci_dev *hdev,
 	duration = __le16_to_cpu(cp->duration);
 
 	/* The current implementation only supports a subset of the specified
-	 * flags.
+	 * flags. Also need to check mutual exclusiveness of sec flags.
 	 */
 	supported_flags = get_supported_adv_flags(hdev);
-	if (flags & ~supported_flags)
+	phy_flags = flags & MGMT_ADV_FLAG_SEC_MASK;
+	if (flags & ~supported_flags ||
+	    ((phy_flags && (phy_flags ^ (phy_flags & -phy_flags)))))
 		return mgmt_cmd_status(sk, hdev->id, MGMT_OP_ADD_ADVERTISING,
 				       MGMT_STATUS_INVALID_PARAMS);
 
-- 
cgit v1.2.3


From 6863ea0cda8725072522cd78bda332d9a0b73150 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 25 Jul 2018 17:48:01 +0200
Subject: x86/mm: Remove in_nmi() warning from vmalloc_fault()

It is perfectly okay to take page-faults, especially on the
vmalloc area while executing an NMI handler. Remove the
warning.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: David H. Gutteridge <dhgutteridge@sympatico.ca>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1532533683-5988-2-git-send-email-joro@8bytes.org
---
 arch/x86/mm/fault.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2aafa6ab6103..db1c042e9853 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -317,8 +317,6 @@ static noinline int vmalloc_fault(unsigned long address)
 	if (!(address >= VMALLOC_START && address < VMALLOC_END))
 		return -1;
 
-	WARN_ON_ONCE(in_nmi());
-
 	/*
 	 * Synchronize this task's top level page-table
 	 * with the 'reference' page table.
-- 
cgit v1.2.3


From 0e664eee65337082be49fbbd2ee24aa0d111d0f2 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 25 Jul 2018 17:48:02 +0200
Subject: Revert "perf/core: Make sure the ring-buffer is mapped in all
 page-tables"

This reverts commit 77754cfa09a6c528c38cbca9ee4cc4f7cf6ad6f2.

The patch was necessary to silence a WARN_ON_ONCE(in_nmi())
that triggered in the vmalloc_fault() function when PTI was
enabled on x86-32.

Faulting in an NMI handler turned out to be safe and the
warning in vmalloc_fault() is gone now. So the above patch
can be reverted.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: David H. Gutteridge <dhgutteridge@sympatico.ca>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1532533683-5988-3-git-send-email-joro@8bytes.org
---
 kernel/events/ring_buffer.c | 16 ----------------
 1 file changed, 16 deletions(-)

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index df2d8cf0072c..5d3cf407e374 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -814,13 +814,6 @@ static void rb_free_work(struct work_struct *work)
 
 	vfree(base);
 	kfree(rb);
-
-	/*
-	 * FIXME: PAE workaround for vmalloc_fault(): Make sure buffer is
-	 * unmapped in all page-tables.
-	 */
-	if (IS_ENABLED(CONFIG_X86_PAE))
-		vmalloc_sync_all();
 }
 
 void rb_free(struct ring_buffer *rb)
@@ -847,15 +840,6 @@ struct ring_buffer *rb_alloc(int nr_pages, long watermark, int cpu, int flags)
 	if (!all_buf)
 		goto fail_all_buf;
 
-	/*
-	 * FIXME: PAE workaround for vmalloc_fault(): The buffer is
-	 * accessed in NMI handlers, make sure it is mapped in all
-	 * page-tables in the system so that we don't fault on the range in
-	 * an NMI handler.
-	 */
-	if (IS_ENABLED(CONFIG_X86_PAE))
-		vmalloc_sync_all();
-
 	rb->user_page = all_buf;
 	rb->data_pages[0] = all_buf + PAGE_SIZE;
 	if (nr_pages) {
-- 
cgit v1.2.3


From ca38dc8f2724d101038b1205122c93a1c7f38f11 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 25 Jul 2018 17:48:03 +0200
Subject: x86/kexec: Allocate 8k PGDs for PTI

Fuzzing the PTI-x86-32 code with trinity showed unhandled
kernel paging request oops-messages that looked a lot like
silent data corruption.

Lot's of debugging and testing lead to the kexec-32bit code,
which is still allocating 4k PGDs when PTI is enabled. But
since it uses native_set_pud() to build the page-table, it
will unevitably call into __pti_set_user_pgtbl(), which
writes beyond the allocated 4k page.

Use PGD_ALLOCATION_ORDER to allocate PGDs in the kexec code
to fix the issue.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: David H. Gutteridge <dhgutteridge@sympatico.ca>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1532533683-5988-4-git-send-email-joro@8bytes.org
---
 arch/x86/kernel/machine_kexec_32.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index d1ab07ec8c9a..5409c2800ab5 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -56,7 +56,7 @@ static void load_segments(void)
 
 static void machine_kexec_free_page_tables(struct kimage *image)
 {
-	free_page((unsigned long)image->arch.pgd);
+	free_pages((unsigned long)image->arch.pgd, PGD_ALLOCATION_ORDER);
 	image->arch.pgd = NULL;
 #ifdef CONFIG_X86_PAE
 	free_page((unsigned long)image->arch.pmd0);
@@ -72,7 +72,8 @@ static void machine_kexec_free_page_tables(struct kimage *image)
 
 static int machine_kexec_alloc_page_tables(struct kimage *image)
 {
-	image->arch.pgd = (pgd_t *)get_zeroed_page(GFP_KERNEL);
+	image->arch.pgd = (pgd_t *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+						    PGD_ALLOCATION_ORDER);
 #ifdef CONFIG_X86_PAE
 	image->arch.pmd0 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
 	image->arch.pmd1 = (pmd_t *)get_zeroed_page(GFP_KERNEL);
-- 
cgit v1.2.3


From 740011cfe94859df8d05f5400d589a8693b095e7 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Fri, 20 Jul 2018 13:12:28 +0800
Subject: Bluetooth: Add new quirk for non-persistent setup settings

Add a new quirk HCI_QUIRK_NON_PERSISTENT_SETUP allowing that a quirk that
runs setup() after every open() and not just after the first open().

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h | 9 +++++++++
 net/bluetooth/hci_core.c    | 3 ++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 8ff36463719f..7f008097552e 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -183,6 +183,15 @@ enum {
 	 * during the hdev->setup vendor callback.
 	 */
 	HCI_QUIRK_NON_PERSISTENT_DIAG,
+
+	/* When this quirk is set, setup() would be run after every
+	 * open() and not just after the first open().
+	 *
+	 * This quirk can be set before hci_register_dev is called or
+	 * during the hdev->setup vendor callback.
+	 *
+	 */
+	HCI_QUIRK_NON_PERSISTENT_SETUP,
 };
 
 /* HCI device flags */
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 79e02d24a215..74b29c7d841c 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -1415,7 +1415,8 @@ static int hci_dev_do_open(struct hci_dev *hdev)
 	atomic_set(&hdev->cmd_cnt, 1);
 	set_bit(HCI_INIT, &hdev->flags);
 
-	if (hci_dev_test_flag(hdev, HCI_SETUP)) {
+	if (hci_dev_test_flag(hdev, HCI_SETUP) ||
+	    test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) {
 		hci_sock_dev_event(hdev, HCI_DEV_SETUP);
 
 		if (hdev->setup)
-- 
cgit v1.2.3


From 51c23b47e6b8590ea7a6a6776ffb21810ece73bf Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 13 Jul 2018 14:54:45 +0200
Subject: netfilter: nf_osf: add nf_osf_find()

This new function returns the OS genre as a string. Plan is to use to
from the new nft_osf extension.

Note that this doesn't yet support ttl options, but it could be easily
extended to do so.

Tested-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_osf.h |  9 +++++++++
 net/netfilter/nf_osf.c           | 30 ++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+)

diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h
index 0e114c492fb8..aee460fcbd31 100644
--- a/include/linux/netfilter/nf_osf.h
+++ b/include/linux/netfilter/nf_osf.h
@@ -1,3 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NFOSF_H
+#define _NFOSF_H
+
 #include <uapi/linux/netfilter/nf_osf.h>
 
 /* Initial window size option state machine: multiple of mss, mtu or
@@ -31,3 +35,8 @@ bool nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 		  int hooknum, struct net_device *in, struct net_device *out,
 		  const struct nf_osf_info *info, struct net *net,
 		  const struct list_head *nf_osf_fingers);
+
+const char *nf_osf_find(const struct sk_buff *skb,
+                        const struct list_head *nf_osf_fingers);
+
+#endif /* _NFOSF_H */
diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nf_osf.c
index b44d62d5d9a9..f4c75e982902 100644
--- a/net/netfilter/nf_osf.c
+++ b/net/netfilter/nf_osf.c
@@ -249,4 +249,34 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family,
 }
 EXPORT_SYMBOL_GPL(nf_osf_match);
 
+const char *nf_osf_find(const struct sk_buff *skb,
+			const struct list_head *nf_osf_fingers)
+{
+	const struct iphdr *ip = ip_hdr(skb);
+	const struct nf_osf_user_finger *f;
+	unsigned char opts[MAX_IPOPTLEN];
+	const struct nf_osf_finger *kf;
+	struct nf_osf_hdr_ctx ctx;
+	const struct tcphdr *tcp;
+	const char *genre = NULL;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	if (!tcp)
+		return false;
+
+	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
+		f = &kf->finger;
+		if (!nf_osf_match_one(skb, f, -1, &ctx))
+			continue;
+
+		genre = f->genre;
+		break;
+	}
+
+	return genre;
+}
+EXPORT_SYMBOL_GPL(nf_osf_find);
+
 MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 33b78aaa4457ce5d531c6a06f461f8d402774cad Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 19 Jul 2018 21:20:09 +0800
Subject: netfilter: use PTR_ERR_OR_ZERO()

Fix ptr_ret.cocci warnings:

  net/netfilter/xt_connlimit.c:96:1-3: WARNING: PTR_ERR_OR_ZERO can be used
  net/netfilter/nft_numgen.c:240:1-3: WARNING: PTR_ERR_OR_ZERO can be used

Use PTR_ERR_OR_ZERO rather than if(IS_ERR(...)) + PTR_ERR

Generated by: scripts/coccinelle/api/ptr_ret.cocci

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_numgen.c   | 4 +---
 net/netfilter/xt_connlimit.c | 4 +---
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
index 1f4d0854cf70..649d1700ec5b 100644
--- a/net/netfilter/nft_numgen.c
+++ b/net/netfilter/nft_numgen.c
@@ -237,10 +237,8 @@ static int nft_ng_random_map_init(const struct nft_ctx *ctx,
 	priv->map = nft_set_lookup_global(ctx->net, ctx->table,
 					  tb[NFTA_NG_SET_NAME],
 					  tb[NFTA_NG_SET_ID], genmask);
-	if (IS_ERR(priv->map))
-		return PTR_ERR(priv->map);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(priv->map);
 }
 
 static int nft_ng_random_dump(struct sk_buff *skb, const struct nft_expr *expr)
diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c
index 6275106ccf50..bc6c8ab0fa62 100644
--- a/net/netfilter/xt_connlimit.c
+++ b/net/netfilter/xt_connlimit.c
@@ -93,10 +93,8 @@ static int connlimit_mt_check(const struct xt_mtchk_param *par)
 
 	/* init private data */
 	info->data = nf_conncount_init(par->net, par->family, keylen);
-	if (IS_ERR(info->data))
-		return PTR_ERR(info->data);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(info->data);
 }
 
 static void connlimit_mt_destroy(const struct xt_mtdtor_param *par)
-- 
cgit v1.2.3


From f6b7b5f4f3bcd7e1897c16dd65a10cbcc159cbde Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Wed, 25 Jul 2018 01:32:44 +0200
Subject: netfilter: nf_osf: rename nf_osf.c to nfnetlink_osf.c

Rename nf_osf.c to nfnetlink_osf.c as we introduce nfnetlink_osf which is
the OSF infraestructure.

Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/Kconfig         |  15 ++-
 net/netfilter/Makefile        |   2 +-
 net/netfilter/nf_osf.c        | 282 ------------------------------------------
 net/netfilter/nfnetlink_osf.c | 282 ++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 293 insertions(+), 288 deletions(-)
 delete mode 100644 net/netfilter/nf_osf.c
 create mode 100644 net/netfilter/nfnetlink_osf.c

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 6f6c959aeb8f..85333431e524 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -46,6 +46,14 @@ config NETFILTER_NETLINK_LOG
 	  and is also scheduled to replace the old syslog-based ipt_LOG
 	  and ip6t_LOG modules.
 
+config NETFILTER_NETLINK_OSF
+	tristate "Netfilter OSF over NFNETLINK interface"
+	depends on NETFILTER_ADVANCED
+	select NETFILTER_NETLINK
+	help
+	  If this option is enabled, the kernel will include support
+	  for passive OS fingerprint via NFNETLINK.
+
 config NF_CONNTRACK
 	tristate "Netfilter connection tracking support"
 	default m if NETFILTER_ADVANCED=n
@@ -442,9 +450,6 @@ config NETFILTER_SYNPROXY
 
 endif # NF_CONNTRACK
 
-config NF_OSF
-	tristate
-
 config NF_TABLES
 	select NETFILTER_NETLINK
 	tristate "Netfilter nf_tables support"
@@ -1368,8 +1373,8 @@ config NETFILTER_XT_MATCH_NFACCT
 
 config NETFILTER_XT_MATCH_OSF
 	tristate '"osf" Passive OS fingerprint match'
-	depends on NETFILTER_ADVANCED && NETFILTER_NETLINK
-	select NF_OSF
+	depends on NETFILTER_ADVANCED
+	select NETFILTER_NETLINK_OSF
 	help
 	  This option selects the Passive OS Fingerprinting match module
 	  that allows to passively match the remote operating system by
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index dd26e4961f43..e684f9b8a9c3 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o
 obj-$(CONFIG_NETFILTER_NETLINK_ACCT) += nfnetlink_acct.o
 obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
 obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
+obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o
 
 # connection tracking
 obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o
@@ -108,7 +109,6 @@ obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_FIB)		+= nft_fib.o
 obj-$(CONFIG_NFT_FIB_INET)	+= nft_fib_inet.o
 obj-$(CONFIG_NFT_FIB_NETDEV)	+= nft_fib_netdev.o
-obj-$(CONFIG_NF_OSF)		+= nf_osf.o
 obj-$(CONFIG_NFT_SOCKET)	+= nft_socket.o
 
 # nf_tables netdev
diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nf_osf.c
deleted file mode 100644
index f4c75e982902..000000000000
--- a/net/netfilter/nf_osf.c
+++ /dev/null
@@ -1,282 +0,0 @@
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-#include <linux/module.h>
-#include <linux/kernel.h>
-
-#include <linux/capability.h>
-#include <linux/if.h>
-#include <linux/inetdevice.h>
-#include <linux/ip.h>
-#include <linux/list.h>
-#include <linux/rculist.h>
-#include <linux/skbuff.h>
-#include <linux/slab.h>
-#include <linux/tcp.h>
-
-#include <net/ip.h>
-#include <net/tcp.h>
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/x_tables.h>
-#include <net/netfilter/nf_log.h>
-#include <linux/netfilter/nf_osf.h>
-
-static inline int nf_osf_ttl(const struct sk_buff *skb,
-			     int ttl_check, unsigned char f_ttl)
-{
-	const struct iphdr *ip = ip_hdr(skb);
-
-	if (ttl_check != -1) {
-		if (ttl_check == NF_OSF_TTL_TRUE)
-			return ip->ttl == f_ttl;
-		if (ttl_check == NF_OSF_TTL_NOCHECK)
-			return 1;
-		else if (ip->ttl <= f_ttl)
-			return 1;
-		else {
-			struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
-			int ret = 0;
-
-			for_ifa(in_dev) {
-				if (inet_ifa_match(ip->saddr, ifa)) {
-					ret = (ip->ttl == f_ttl);
-					break;
-				}
-			}
-			endfor_ifa(in_dev);
-
-			return ret;
-		}
-	}
-
-	return ip->ttl == f_ttl;
-}
-
-struct nf_osf_hdr_ctx {
-	bool			df;
-	u16			window;
-	u16			totlen;
-	const unsigned char	*optp;
-	unsigned int		optsize;
-};
-
-static bool nf_osf_match_one(const struct sk_buff *skb,
-			     const struct nf_osf_user_finger *f,
-			     int ttl_check,
-			     struct nf_osf_hdr_ctx *ctx)
-{
-	unsigned int check_WSS = 0;
-	int fmatch = FMATCH_WRONG;
-	int foptsize, optnum;
-	u16 mss = 0;
-
-	if (ctx->totlen != f->ss || !nf_osf_ttl(skb, ttl_check, f->ttl))
-		return false;
-
-	/*
-	 * Should not happen if userspace parser was written correctly.
-	 */
-	if (f->wss.wc >= OSF_WSS_MAX)
-		return false;
-
-	/* Check options */
-
-	foptsize = 0;
-	for (optnum = 0; optnum < f->opt_num; ++optnum)
-		foptsize += f->opt[optnum].length;
-
-	if (foptsize > MAX_IPOPTLEN ||
-	    ctx->optsize > MAX_IPOPTLEN ||
-	    ctx->optsize != foptsize)
-		return false;
-
-	check_WSS = f->wss.wc;
-
-	for (optnum = 0; optnum < f->opt_num; ++optnum) {
-		if (f->opt[optnum].kind == *ctx->optp) {
-			__u32 len = f->opt[optnum].length;
-			const __u8 *optend = ctx->optp + len;
-
-			fmatch = FMATCH_OK;
-
-			switch (*ctx->optp) {
-			case OSFOPT_MSS:
-				mss = ctx->optp[3];
-				mss <<= 8;
-				mss |= ctx->optp[2];
-
-				mss = ntohs((__force __be16)mss);
-				break;
-			case OSFOPT_TS:
-				break;
-			}
-
-			ctx->optp = optend;
-		} else
-			fmatch = FMATCH_OPT_WRONG;
-
-		if (fmatch != FMATCH_OK)
-			break;
-	}
-
-	if (fmatch != FMATCH_OPT_WRONG) {
-		fmatch = FMATCH_WRONG;
-
-		switch (check_WSS) {
-		case OSF_WSS_PLAIN:
-			if (f->wss.val == 0 || ctx->window == f->wss.val)
-				fmatch = FMATCH_OK;
-			break;
-		case OSF_WSS_MSS:
-			/*
-			 * Some smart modems decrease mangle MSS to
-			 * SMART_MSS_2, so we check standard, decreased
-			 * and the one provided in the fingerprint MSS
-			 * values.
-			 */
-#define SMART_MSS_1	1460
-#define SMART_MSS_2	1448
-			if (ctx->window == f->wss.val * mss ||
-			    ctx->window == f->wss.val * SMART_MSS_1 ||
-			    ctx->window == f->wss.val * SMART_MSS_2)
-				fmatch = FMATCH_OK;
-			break;
-		case OSF_WSS_MTU:
-			if (ctx->window == f->wss.val * (mss + 40) ||
-			    ctx->window == f->wss.val * (SMART_MSS_1 + 40) ||
-			    ctx->window == f->wss.val * (SMART_MSS_2 + 40))
-				fmatch = FMATCH_OK;
-			break;
-		case OSF_WSS_MODULO:
-			if ((ctx->window % f->wss.val) == 0)
-				fmatch = FMATCH_OK;
-			break;
-		}
-	}
-
-	return fmatch == FMATCH_OK;
-}
-
-static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx,
-						const struct sk_buff *skb,
-						const struct iphdr *ip,
-						unsigned char *opts)
-{
-	const struct tcphdr *tcp;
-	struct tcphdr _tcph;
-
-	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
-	if (!tcp)
-		return NULL;
-
-	if (!tcp->syn)
-		return NULL;
-
-	ctx->totlen = ntohs(ip->tot_len);
-	ctx->df = ntohs(ip->frag_off) & IP_DF;
-	ctx->window = ntohs(tcp->window);
-
-	if (tcp->doff * 4 > sizeof(struct tcphdr)) {
-		ctx->optsize = tcp->doff * 4 - sizeof(struct tcphdr);
-
-		ctx->optp = skb_header_pointer(skb, ip_hdrlen(skb) +
-				sizeof(struct tcphdr), ctx->optsize, opts);
-	}
-
-	return tcp;
-}
-
-bool
-nf_osf_match(const struct sk_buff *skb, u_int8_t family,
-	     int hooknum, struct net_device *in, struct net_device *out,
-	     const struct nf_osf_info *info, struct net *net,
-	     const struct list_head *nf_osf_fingers)
-{
-	const struct iphdr *ip = ip_hdr(skb);
-	const struct nf_osf_user_finger *f;
-	unsigned char opts[MAX_IPOPTLEN];
-	const struct nf_osf_finger *kf;
-	int fcount = 0, ttl_check;
-	int fmatch = FMATCH_WRONG;
-	struct nf_osf_hdr_ctx ctx;
-	const struct tcphdr *tcp;
-
-	memset(&ctx, 0, sizeof(ctx));
-
-	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
-	if (!tcp)
-		return false;
-
-	ttl_check = (info->flags & NF_OSF_TTL) ? info->ttl : -1;
-
-	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
-
-		f = &kf->finger;
-
-		if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre))
-			continue;
-
-		if (!nf_osf_match_one(skb, f, ttl_check, &ctx))
-			continue;
-
-		fmatch = FMATCH_OK;
-
-		fcount++;
-
-		if (info->flags & NF_OSF_LOG)
-			nf_log_packet(net, family, hooknum, skb,
-				      in, out, NULL,
-				      "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
-				      f->genre, f->version, f->subtype,
-				      &ip->saddr, ntohs(tcp->source),
-				      &ip->daddr, ntohs(tcp->dest),
-				      f->ttl - ip->ttl);
-
-		if ((info->flags & NF_OSF_LOG) &&
-		    info->loglevel == NF_OSF_LOGLEVEL_FIRST)
-			break;
-	}
-
-	if (!fcount && (info->flags & NF_OSF_LOG))
-		nf_log_packet(net, family, hooknum, skb, in, out, NULL,
-			      "Remote OS is not known: %pI4:%u -> %pI4:%u\n",
-			      &ip->saddr, ntohs(tcp->source),
-			      &ip->daddr, ntohs(tcp->dest));
-
-	if (fcount)
-		fmatch = FMATCH_OK;
-
-	return fmatch == FMATCH_OK;
-}
-EXPORT_SYMBOL_GPL(nf_osf_match);
-
-const char *nf_osf_find(const struct sk_buff *skb,
-			const struct list_head *nf_osf_fingers)
-{
-	const struct iphdr *ip = ip_hdr(skb);
-	const struct nf_osf_user_finger *f;
-	unsigned char opts[MAX_IPOPTLEN];
-	const struct nf_osf_finger *kf;
-	struct nf_osf_hdr_ctx ctx;
-	const struct tcphdr *tcp;
-	const char *genre = NULL;
-
-	memset(&ctx, 0, sizeof(ctx));
-
-	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
-	if (!tcp)
-		return false;
-
-	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
-		f = &kf->finger;
-		if (!nf_osf_match_one(skb, f, -1, &ctx))
-			continue;
-
-		genre = f->genre;
-		break;
-	}
-
-	return genre;
-}
-EXPORT_SYMBOL_GPL(nf_osf_find);
-
-MODULE_LICENSE("GPL");
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
new file mode 100644
index 000000000000..f4c75e982902
--- /dev/null
+++ b/net/netfilter/nfnetlink_osf.c
@@ -0,0 +1,282 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include <linux/capability.h>
+#include <linux/if.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/tcp.h>
+
+#include <net/ip.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_log.h>
+#include <linux/netfilter/nf_osf.h>
+
+static inline int nf_osf_ttl(const struct sk_buff *skb,
+			     int ttl_check, unsigned char f_ttl)
+{
+	const struct iphdr *ip = ip_hdr(skb);
+
+	if (ttl_check != -1) {
+		if (ttl_check == NF_OSF_TTL_TRUE)
+			return ip->ttl == f_ttl;
+		if (ttl_check == NF_OSF_TTL_NOCHECK)
+			return 1;
+		else if (ip->ttl <= f_ttl)
+			return 1;
+		else {
+			struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+			int ret = 0;
+
+			for_ifa(in_dev) {
+				if (inet_ifa_match(ip->saddr, ifa)) {
+					ret = (ip->ttl == f_ttl);
+					break;
+				}
+			}
+			endfor_ifa(in_dev);
+
+			return ret;
+		}
+	}
+
+	return ip->ttl == f_ttl;
+}
+
+struct nf_osf_hdr_ctx {
+	bool			df;
+	u16			window;
+	u16			totlen;
+	const unsigned char	*optp;
+	unsigned int		optsize;
+};
+
+static bool nf_osf_match_one(const struct sk_buff *skb,
+			     const struct nf_osf_user_finger *f,
+			     int ttl_check,
+			     struct nf_osf_hdr_ctx *ctx)
+{
+	unsigned int check_WSS = 0;
+	int fmatch = FMATCH_WRONG;
+	int foptsize, optnum;
+	u16 mss = 0;
+
+	if (ctx->totlen != f->ss || !nf_osf_ttl(skb, ttl_check, f->ttl))
+		return false;
+
+	/*
+	 * Should not happen if userspace parser was written correctly.
+	 */
+	if (f->wss.wc >= OSF_WSS_MAX)
+		return false;
+
+	/* Check options */
+
+	foptsize = 0;
+	for (optnum = 0; optnum < f->opt_num; ++optnum)
+		foptsize += f->opt[optnum].length;
+
+	if (foptsize > MAX_IPOPTLEN ||
+	    ctx->optsize > MAX_IPOPTLEN ||
+	    ctx->optsize != foptsize)
+		return false;
+
+	check_WSS = f->wss.wc;
+
+	for (optnum = 0; optnum < f->opt_num; ++optnum) {
+		if (f->opt[optnum].kind == *ctx->optp) {
+			__u32 len = f->opt[optnum].length;
+			const __u8 *optend = ctx->optp + len;
+
+			fmatch = FMATCH_OK;
+
+			switch (*ctx->optp) {
+			case OSFOPT_MSS:
+				mss = ctx->optp[3];
+				mss <<= 8;
+				mss |= ctx->optp[2];
+
+				mss = ntohs((__force __be16)mss);
+				break;
+			case OSFOPT_TS:
+				break;
+			}
+
+			ctx->optp = optend;
+		} else
+			fmatch = FMATCH_OPT_WRONG;
+
+		if (fmatch != FMATCH_OK)
+			break;
+	}
+
+	if (fmatch != FMATCH_OPT_WRONG) {
+		fmatch = FMATCH_WRONG;
+
+		switch (check_WSS) {
+		case OSF_WSS_PLAIN:
+			if (f->wss.val == 0 || ctx->window == f->wss.val)
+				fmatch = FMATCH_OK;
+			break;
+		case OSF_WSS_MSS:
+			/*
+			 * Some smart modems decrease mangle MSS to
+			 * SMART_MSS_2, so we check standard, decreased
+			 * and the one provided in the fingerprint MSS
+			 * values.
+			 */
+#define SMART_MSS_1	1460
+#define SMART_MSS_2	1448
+			if (ctx->window == f->wss.val * mss ||
+			    ctx->window == f->wss.val * SMART_MSS_1 ||
+			    ctx->window == f->wss.val * SMART_MSS_2)
+				fmatch = FMATCH_OK;
+			break;
+		case OSF_WSS_MTU:
+			if (ctx->window == f->wss.val * (mss + 40) ||
+			    ctx->window == f->wss.val * (SMART_MSS_1 + 40) ||
+			    ctx->window == f->wss.val * (SMART_MSS_2 + 40))
+				fmatch = FMATCH_OK;
+			break;
+		case OSF_WSS_MODULO:
+			if ((ctx->window % f->wss.val) == 0)
+				fmatch = FMATCH_OK;
+			break;
+		}
+	}
+
+	return fmatch == FMATCH_OK;
+}
+
+static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx,
+						const struct sk_buff *skb,
+						const struct iphdr *ip,
+						unsigned char *opts)
+{
+	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
+
+	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
+	if (!tcp)
+		return NULL;
+
+	if (!tcp->syn)
+		return NULL;
+
+	ctx->totlen = ntohs(ip->tot_len);
+	ctx->df = ntohs(ip->frag_off) & IP_DF;
+	ctx->window = ntohs(tcp->window);
+
+	if (tcp->doff * 4 > sizeof(struct tcphdr)) {
+		ctx->optsize = tcp->doff * 4 - sizeof(struct tcphdr);
+
+		ctx->optp = skb_header_pointer(skb, ip_hdrlen(skb) +
+				sizeof(struct tcphdr), ctx->optsize, opts);
+	}
+
+	return tcp;
+}
+
+bool
+nf_osf_match(const struct sk_buff *skb, u_int8_t family,
+	     int hooknum, struct net_device *in, struct net_device *out,
+	     const struct nf_osf_info *info, struct net *net,
+	     const struct list_head *nf_osf_fingers)
+{
+	const struct iphdr *ip = ip_hdr(skb);
+	const struct nf_osf_user_finger *f;
+	unsigned char opts[MAX_IPOPTLEN];
+	const struct nf_osf_finger *kf;
+	int fcount = 0, ttl_check;
+	int fmatch = FMATCH_WRONG;
+	struct nf_osf_hdr_ctx ctx;
+	const struct tcphdr *tcp;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	if (!tcp)
+		return false;
+
+	ttl_check = (info->flags & NF_OSF_TTL) ? info->ttl : -1;
+
+	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
+
+		f = &kf->finger;
+
+		if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre))
+			continue;
+
+		if (!nf_osf_match_one(skb, f, ttl_check, &ctx))
+			continue;
+
+		fmatch = FMATCH_OK;
+
+		fcount++;
+
+		if (info->flags & NF_OSF_LOG)
+			nf_log_packet(net, family, hooknum, skb,
+				      in, out, NULL,
+				      "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n",
+				      f->genre, f->version, f->subtype,
+				      &ip->saddr, ntohs(tcp->source),
+				      &ip->daddr, ntohs(tcp->dest),
+				      f->ttl - ip->ttl);
+
+		if ((info->flags & NF_OSF_LOG) &&
+		    info->loglevel == NF_OSF_LOGLEVEL_FIRST)
+			break;
+	}
+
+	if (!fcount && (info->flags & NF_OSF_LOG))
+		nf_log_packet(net, family, hooknum, skb, in, out, NULL,
+			      "Remote OS is not known: %pI4:%u -> %pI4:%u\n",
+			      &ip->saddr, ntohs(tcp->source),
+			      &ip->daddr, ntohs(tcp->dest));
+
+	if (fcount)
+		fmatch = FMATCH_OK;
+
+	return fmatch == FMATCH_OK;
+}
+EXPORT_SYMBOL_GPL(nf_osf_match);
+
+const char *nf_osf_find(const struct sk_buff *skb,
+			const struct list_head *nf_osf_fingers)
+{
+	const struct iphdr *ip = ip_hdr(skb);
+	const struct nf_osf_user_finger *f;
+	unsigned char opts[MAX_IPOPTLEN];
+	const struct nf_osf_finger *kf;
+	struct nf_osf_hdr_ctx ctx;
+	const struct tcphdr *tcp;
+	const char *genre = NULL;
+
+	memset(&ctx, 0, sizeof(ctx));
+
+	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
+	if (!tcp)
+		return false;
+
+	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
+		f = &kf->finger;
+		if (!nf_osf_match_one(skb, f, -1, &ctx))
+			continue;
+
+		genre = f->genre;
+		break;
+	}
+
+	return genre;
+}
+EXPORT_SYMBOL_GPL(nf_osf_find);
+
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From f9324952088f1cd62ea4addf9ff532f1e6452a22 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Wed, 25 Jul 2018 01:32:45 +0200
Subject: netfilter: nfnetlink_osf: extract nfnetlink_subsystem code from
 xt_osf.c

Move nfnetlink osf subsystem from xt_osf.c to standalone module so we can
reuse it from the new nft_ost extension.

Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_osf.h |  11 +++
 include/uapi/linux/netfilter/xt_osf.h |   9 +-
 net/netfilter/nfnetlink_osf.c         | 154 ++++++++++++++++++++++++++++++++++
 net/netfilter/xt_osf.c                | 149 +-------------------------------
 4 files changed, 169 insertions(+), 154 deletions(-)

diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h
index 3738116b2bbe..cc2487ff74f6 100644
--- a/include/uapi/linux/netfilter/nf_osf.h
+++ b/include/uapi/linux/netfilter/nf_osf.h
@@ -70,6 +70,8 @@ struct nf_osf_nlmsg {
 	struct tcphdr			tcp;
 };
 
+extern struct list_head nf_osf_fingers[2];
+
 /* Defines for IANA option kinds */
 enum iana_options {
 	OSFOPT_EOL = 0,		/* End of options */
@@ -94,4 +96,13 @@ enum nf_osf_attr_type {
 	OSF_ATTR_MAX,
 };
 
+/*
+ * Add/remove fingerprint from the kernel.
+ */
+enum nf_osf_msg_types {
+	OSF_MSG_ADD,
+	OSF_MSG_REMOVE,
+	OSF_MSG_MAX,
+};
+
 #endif /* _NF_OSF_H */
diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h
index b189007f4f28..a90e90c27cef 100644
--- a/include/uapi/linux/netfilter/xt_osf.h
+++ b/include/uapi/linux/netfilter/xt_osf.h
@@ -47,13 +47,6 @@
 #define xt_osf_nlmsg		nf_osf_nlmsg
 
 #define xt_osf_attr_type	nf_osf_attr_type
-/*
- * Add/remove fingerprint from the kernel.
- */
-enum xt_osf_msg_types {
-	OSF_MSG_ADD,
-	OSF_MSG_REMOVE,
-	OSF_MSG_MAX,
-};
+#define xt_osf_msg_types	nf_osf_msg_types
 
 #endif				/* _XT_OSF_H */
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index f4c75e982902..ba0fa11869ce 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -20,6 +20,13 @@
 #include <net/netfilter/nf_log.h>
 #include <linux/netfilter/nf_osf.h>
 
+/*
+ * Indexed by dont-fragment bit.
+ * It is the only constant value in the fingerprint.
+ */
+struct list_head nf_osf_fingers[2];
+EXPORT_SYMBOL_GPL(nf_osf_fingers);
+
 static inline int nf_osf_ttl(const struct sk_buff *skb,
 			     int ttl_check, unsigned char f_ttl)
 {
@@ -279,4 +286,151 @@ const char *nf_osf_find(const struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_osf_find);
 
+static const struct nla_policy nfnl_osf_policy[OSF_ATTR_MAX + 1] = {
+	[OSF_ATTR_FINGER]	= { .len = sizeof(struct nf_osf_user_finger) },
+};
+
+static int nfnl_osf_add_callback(struct net *net, struct sock *ctnl,
+				 struct sk_buff *skb, const struct nlmsghdr *nlh,
+				 const struct nlattr * const osf_attrs[],
+				 struct netlink_ext_ack *extack)
+{
+	struct nf_osf_user_finger *f;
+	struct nf_osf_finger *kf = NULL, *sf;
+	int err = 0;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (!osf_attrs[OSF_ATTR_FINGER])
+		return -EINVAL;
+
+	if (!(nlh->nlmsg_flags & NLM_F_CREATE))
+		return -EINVAL;
+
+	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
+
+	kf = kmalloc(sizeof(struct nf_osf_finger), GFP_KERNEL);
+	if (!kf)
+		return -ENOMEM;
+
+	memcpy(&kf->finger, f, sizeof(struct nf_osf_user_finger));
+
+	list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) {
+		if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger)))
+			continue;
+
+		kfree(kf);
+		kf = NULL;
+
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			err = -EEXIST;
+		break;
+	}
+
+	/*
+	 * We are protected by nfnl mutex.
+	 */
+	if (kf)
+		list_add_tail_rcu(&kf->finger_entry, &nf_osf_fingers[!!f->df]);
+
+	return err;
+}
+
+static int nfnl_osf_remove_callback(struct net *net, struct sock *ctnl,
+				    struct sk_buff *skb,
+				    const struct nlmsghdr *nlh,
+				    const struct nlattr * const osf_attrs[],
+				    struct netlink_ext_ack *extack)
+{
+	struct nf_osf_user_finger *f;
+	struct nf_osf_finger *sf;
+	int err = -ENOENT;
+
+	if (!capable(CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (!osf_attrs[OSF_ATTR_FINGER])
+		return -EINVAL;
+
+	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
+
+	list_for_each_entry(sf, &nf_osf_fingers[!!f->df], finger_entry) {
+		if (memcmp(&sf->finger, f, sizeof(struct nf_osf_user_finger)))
+			continue;
+
+		/*
+		 * We are protected by nfnl mutex.
+		 */
+		list_del_rcu(&sf->finger_entry);
+		kfree_rcu(sf, rcu_head);
+
+		err = 0;
+		break;
+	}
+
+	return err;
+}
+
+static const struct nfnl_callback nfnl_osf_callbacks[OSF_MSG_MAX] = {
+	[OSF_MSG_ADD]	= {
+		.call		= nfnl_osf_add_callback,
+		.attr_count	= OSF_ATTR_MAX,
+		.policy		= nfnl_osf_policy,
+	},
+	[OSF_MSG_REMOVE]	= {
+		.call		= nfnl_osf_remove_callback,
+		.attr_count	= OSF_ATTR_MAX,
+		.policy		= nfnl_osf_policy,
+	},
+};
+
+static const struct nfnetlink_subsystem nfnl_osf_subsys = {
+	.name			= "osf",
+	.subsys_id		= NFNL_SUBSYS_OSF,
+	.cb_count		= OSF_MSG_MAX,
+	.cb			= nfnl_osf_callbacks,
+};
+
+static int __init nfnl_osf_init(void)
+{
+	int err = -EINVAL;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i)
+		INIT_LIST_HEAD(&nf_osf_fingers[i]);
+
+	err = nfnetlink_subsys_register(&nfnl_osf_subsys);
+	if (err < 0) {
+		pr_err("Failed to register OSF nsfnetlink helper (%d)\n", err);
+		goto err_out_exit;
+	}
+	return 0;
+
+err_out_exit:
+	return err;
+}
+
+static void __exit nfnl_osf_fini(void)
+{
+	struct nf_osf_finger *f;
+	int i;
+
+	nfnetlink_subsys_unregister(&nfnl_osf_subsys);
+
+	rcu_read_lock();
+	for (i = 0; i < ARRAY_SIZE(nf_osf_fingers); ++i) {
+		list_for_each_entry_rcu(f, &nf_osf_fingers[i], finger_entry) {
+			list_del_rcu(&f->finger_entry);
+			kfree_rcu(f, rcu_head);
+		}
+	}
+	rcu_read_unlock();
+
+	rcu_barrier();
+}
+
+module_init(nfnl_osf_init);
+module_exit(nfnl_osf_fini);
+
 MODULE_LICENSE("GPL");
diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c
index 9cfef73b4107..bf7bba80e24c 100644
--- a/net/netfilter/xt_osf.c
+++ b/net/netfilter/xt_osf.c
@@ -37,118 +37,6 @@
 #include <net/netfilter/nf_log.h>
 #include <linux/netfilter/xt_osf.h>
 
-/*
- * Indexed by dont-fragment bit.
- * It is the only constant value in the fingerprint.
- */
-static struct list_head xt_osf_fingers[2];
-
-static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = {
-	[OSF_ATTR_FINGER]	= { .len = sizeof(struct xt_osf_user_finger) },
-};
-
-static int xt_osf_add_callback(struct net *net, struct sock *ctnl,
-			       struct sk_buff *skb, const struct nlmsghdr *nlh,
-			       const struct nlattr * const osf_attrs[],
-			       struct netlink_ext_ack *extack)
-{
-	struct xt_osf_user_finger *f;
-	struct xt_osf_finger *kf = NULL, *sf;
-	int err = 0;
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (!osf_attrs[OSF_ATTR_FINGER])
-		return -EINVAL;
-
-	if (!(nlh->nlmsg_flags & NLM_F_CREATE))
-		return -EINVAL;
-
-	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
-
-	kf = kmalloc(sizeof(struct xt_osf_finger), GFP_KERNEL);
-	if (!kf)
-		return -ENOMEM;
-
-	memcpy(&kf->finger, f, sizeof(struct xt_osf_user_finger));
-
-	list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) {
-		if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger)))
-			continue;
-
-		kfree(kf);
-		kf = NULL;
-
-		if (nlh->nlmsg_flags & NLM_F_EXCL)
-			err = -EEXIST;
-		break;
-	}
-
-	/*
-	 * We are protected by nfnl mutex.
-	 */
-	if (kf)
-		list_add_tail_rcu(&kf->finger_entry, &xt_osf_fingers[!!f->df]);
-
-	return err;
-}
-
-static int xt_osf_remove_callback(struct net *net, struct sock *ctnl,
-				  struct sk_buff *skb,
-				  const struct nlmsghdr *nlh,
-				  const struct nlattr * const osf_attrs[],
-				  struct netlink_ext_ack *extack)
-{
-	struct xt_osf_user_finger *f;
-	struct xt_osf_finger *sf;
-	int err = -ENOENT;
-
-	if (!capable(CAP_NET_ADMIN))
-		return -EPERM;
-
-	if (!osf_attrs[OSF_ATTR_FINGER])
-		return -EINVAL;
-
-	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
-
-	list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) {
-		if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger)))
-			continue;
-
-		/*
-		 * We are protected by nfnl mutex.
-		 */
-		list_del_rcu(&sf->finger_entry);
-		kfree_rcu(sf, rcu_head);
-
-		err = 0;
-		break;
-	}
-
-	return err;
-}
-
-static const struct nfnl_callback xt_osf_nfnetlink_callbacks[OSF_MSG_MAX] = {
-	[OSF_MSG_ADD]	= {
-		.call		= xt_osf_add_callback,
-		.attr_count	= OSF_ATTR_MAX,
-		.policy		= xt_osf_policy,
-	},
-	[OSF_MSG_REMOVE]	= {
-		.call		= xt_osf_remove_callback,
-		.attr_count	= OSF_ATTR_MAX,
-		.policy		= xt_osf_policy,
-	},
-};
-
-static const struct nfnetlink_subsystem xt_osf_nfnetlink = {
-	.name			= "osf",
-	.subsys_id		= NFNL_SUBSYS_OSF,
-	.cb_count		= OSF_MSG_MAX,
-	.cb			= xt_osf_nfnetlink_callbacks,
-};
-
 static bool
 xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
 {
@@ -159,7 +47,7 @@ xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p)
 		return false;
 
 	return nf_osf_match(skb, xt_family(p), xt_hooknum(p), xt_in(p),
-			    xt_out(p), info, net, xt_osf_fingers);
+			    xt_out(p), info, net, nf_osf_fingers);
 }
 
 static struct xt_match xt_osf_match = {
@@ -177,52 +65,21 @@ static struct xt_match xt_osf_match = {
 
 static int __init xt_osf_init(void)
 {
-	int err = -EINVAL;
-	int i;
-
-	for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i)
-		INIT_LIST_HEAD(&xt_osf_fingers[i]);
-
-	err = nfnetlink_subsys_register(&xt_osf_nfnetlink);
-	if (err < 0) {
-		pr_err("Failed to register OSF nsfnetlink helper (%d)\n", err);
-		goto err_out_exit;
-	}
+	int err;
 
 	err = xt_register_match(&xt_osf_match);
 	if (err) {
 		pr_err("Failed to register OS fingerprint "
 		       "matching module (%d)\n", err);
-		goto err_out_remove;
+		return err;
 	}
 
 	return 0;
-
-err_out_remove:
-	nfnetlink_subsys_unregister(&xt_osf_nfnetlink);
-err_out_exit:
-	return err;
 }
 
 static void __exit xt_osf_fini(void)
 {
-	struct xt_osf_finger *f;
-	int i;
-
-	nfnetlink_subsys_unregister(&xt_osf_nfnetlink);
 	xt_unregister_match(&xt_osf_match);
-
-	rcu_read_lock();
-	for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i) {
-
-		list_for_each_entry_rcu(f, &xt_osf_fingers[i], finger_entry) {
-			list_del_rcu(&f->finger_entry);
-			kfree_rcu(f, rcu_head);
-		}
-	}
-	rcu_read_unlock();
-
-	rcu_barrier();
 }
 
 module_init(xt_osf_init);
-- 
cgit v1.2.3


From b96af92d6eaf9fadd77aa798c508a8a9d2e60020 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Wed, 25 Jul 2018 01:32:46 +0200
Subject: netfilter: nf_tables: implement Passive OS fingerprint module in
 nft_osf

Add basic module functions into nft_osf.[ch] in order to implement OSF
module in nf_tables.

Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |   7 ++
 net/netfilter/Kconfig                    |   7 ++
 net/netfilter/Makefile                   |   1 +
 net/netfilter/nft_osf.c                  | 106 +++++++++++++++++++++++++++++++
 4 files changed, 121 insertions(+)
 create mode 100644 net/netfilter/nft_osf.c

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index f466860bcf75..382c32d630e9 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1463,6 +1463,13 @@ enum nft_flowtable_hook_attributes {
 };
 #define NFTA_FLOWTABLE_HOOK_MAX	(__NFTA_FLOWTABLE_HOOK_MAX - 1)
 
+enum nft_osf_attributes {
+	NFTA_OSF_UNSPEC,
+	NFTA_OSF_DREG,
+	__NFTA_OSF_MAX,
+};
+#define NFTA_OSF_MAX (__NFTA_OSF_MAX - 1)
+
 /**
  * enum nft_device_attributes - nf_tables device netlink attributes
  *
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 85333431e524..16fdfb75efb5 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -627,6 +627,13 @@ config NFT_SOCKET
 	  This option allows matching for the presence or absence of a
 	  corresponding socket and its attributes.
 
+config NFT_OSF
+	tristate "Netfilter nf_tables passive OS fingerprint support"
+	depends on NETFILTER_ADVANCED
+	select NETFILTER_NETLINK_OSF
+	help
+	  This option allows matching packets from an specific OS.
+
 if NF_TABLES_NETDEV
 
 config NF_DUP_NETDEV
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index e684f9b8a9c3..5cbbf6978b55 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -110,6 +110,7 @@ obj-$(CONFIG_NFT_FIB)		+= nft_fib.o
 obj-$(CONFIG_NFT_FIB_INET)	+= nft_fib_inet.o
 obj-$(CONFIG_NFT_FIB_NETDEV)	+= nft_fib_netdev.o
 obj-$(CONFIG_NFT_SOCKET)	+= nft_socket.o
+obj-$(CONFIG_NFT_OSF)		+= nft_osf.o
 
 # nf_tables netdev
 obj-$(CONFIG_NFT_DUP_NETDEV)	+= nft_dup_netdev.o
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
new file mode 100644
index 000000000000..bdacc4cffba4
--- /dev/null
+++ b/net/netfilter/nft_osf.c
@@ -0,0 +1,106 @@
+#include <net/ip.h>
+#include <net/tcp.h>
+
+#include <net/netfilter/nf_tables.h>
+#include <linux/netfilter/nf_osf.h>
+
+#define OSF_GENRE_SIZE		32
+
+struct nft_osf {
+	enum nft_registers	dreg:8;
+};
+
+static const struct nla_policy nft_osf_policy[NFTA_OSF_MAX + 1] = {
+	[NFTA_OSF_DREG]		= { .type = NLA_U32 },
+};
+
+static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
+			 const struct nft_pktinfo *pkt)
+{
+	struct nft_osf *priv = nft_expr_priv(expr);
+	u32 *dest = &regs->data[priv->dreg];
+	struct sk_buff *skb = pkt->skb;
+	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
+	const char *os_name;
+
+	tcp = skb_header_pointer(skb, ip_hdrlen(skb),
+				 sizeof(struct tcphdr), &_tcph);
+	if (!tcp) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+	if (!tcp->syn) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+
+	os_name = nf_osf_find(skb, nf_osf_fingers);
+	if (!os_name)
+		strncpy((char *)dest, "unknown", IFNAMSIZ);
+	else
+		strncpy((char *)dest, os_name, IFNAMSIZ);
+}
+
+static int nft_osf_init(const struct nft_ctx *ctx,
+			const struct nft_expr *expr,
+			const struct nlattr * const tb[])
+{
+	struct nft_osf *priv = nft_expr_priv(expr);
+	int err;
+
+	priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]);
+	err = nft_validate_register_store(ctx, priv->dreg, NULL,
+					  NFTA_DATA_VALUE, OSF_GENRE_SIZE);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int nft_osf_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	const struct nft_osf *priv = nft_expr_priv(expr);
+
+	if (nft_dump_register(skb, NFTA_OSF_DREG, priv->dreg))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_osf_type;
+static const struct nft_expr_ops nft_osf_op = {
+	.eval		= nft_osf_eval,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_osf)),
+	.init		= nft_osf_init,
+	.dump		= nft_osf_dump,
+	.type		= &nft_osf_type,
+};
+
+static struct nft_expr_type nft_osf_type __read_mostly = {
+	.ops		= &nft_osf_op,
+	.name		= "osf",
+	.owner		= THIS_MODULE,
+	.policy		= nft_osf_policy,
+	.maxattr	= NFTA_OSF_MAX,
+};
+
+static int __init nft_osf_module_init(void)
+{
+	return nft_register_expr(&nft_osf_type);
+}
+
+static void __exit nft_osf_module_exit(void)
+{
+	return nft_unregister_expr(&nft_osf_type);
+}
+
+module_init(nft_osf_module_init);
+module_exit(nft_osf_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Fernando Fernandez <ffmancera@riseup.net>");
+MODULE_ALIAS_NFT_EXPR("osf");
-- 
cgit v1.2.3


From 4ed8eb6570a49931c705512060acd50058d61616 Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Mon, 30 Jul 2018 11:07:32 +0200
Subject: netfilter: nf_tables: Add native tproxy support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A great portion of the code is taken from xt_TPROXY.c

There are some changes compared to the iptables implementation:
 - tproxy statement is not terminal here
 - Either address or port has to be specified, but at least one of them
   is necessary. If one of them is not specified, the evaluation will be
   performed with the original attribute of the packet (ie. target port
   is not specified => the packet's dport will be used).

To make this work in inet tables, the tproxy structure has a family
member (typically called priv->family) which is not necessarily equal to
ctx->family.

priv->family can have three values legally:
 - NFPROTO_IPV4 if the table family is ip OR if table family is inet,
   but an ipv4 address is specified as a target address. The rule only
   evaluates ipv4 packets in this case.
 - NFPROTO_IPV6 if the table family is ip6 OR if table family is inet,
   but an ipv6 address is specified as a target address. The rule only
   evaluates ipv6 packets in this case.
 - NFPROTO_UNSPEC if the table family is inet AND if only the port is
   specified. The rule will evaluate both ipv4 and ipv6 packets.

Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  16 ++
 net/netfilter/Kconfig                    |  10 +
 net/netfilter/Makefile                   |   1 +
 net/netfilter/nft_tproxy.c               | 314 +++++++++++++++++++++++++++++++
 4 files changed, 341 insertions(+)
 create mode 100644 net/netfilter/nft_tproxy.c

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 382c32d630e9..f112ea52dc1a 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1252,6 +1252,22 @@ enum nft_nat_attributes {
 };
 #define NFTA_NAT_MAX		(__NFTA_NAT_MAX - 1)
 
+/**
+ * enum nft_tproxy_attributes - nf_tables tproxy expression netlink attributes
+ *
+ * NFTA_TPROXY_FAMILY: Target address family (NLA_U32: nft_registers)
+ * NFTA_TPROXY_REG_ADDR: Target address register (NLA_U32: nft_registers)
+ * NFTA_TPROXY_REG_PORT: Target port register (NLA_U32: nft_registers)
+ */
+enum nft_tproxy_attributes {
+	NFTA_TPROXY_UNSPEC,
+	NFTA_TPROXY_FAMILY,
+	NFTA_TPROXY_REG_ADDR,
+	NFTA_TPROXY_REG_PORT,
+	__NFTA_TPROXY_MAX
+};
+#define NFTA_TPROXY_MAX		(__NFTA_TPROXY_MAX - 1)
+
 /**
  * enum nft_masq_attributes - nf_tables masquerade expression attributes
  *
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 16fdfb75efb5..0febf3e21f91 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -634,6 +634,16 @@ config NFT_OSF
 	help
 	  This option allows matching packets from an specific OS.
 
+config NFT_TPROXY
+	tristate "Netfilter nf_tables tproxy support"
+	depends on IPV6 || IPV6=n
+	select NF_DEFRAG_IPV4
+	select NF_DEFRAG_IPV6 if NF_TABLES_IPV6
+	select NF_TPROXY_IPV4
+	select NF_TPROXY_IPV6 if NF_TABLES_IPV6
+	help
+	  This makes transparent proxy support available in nftables.
+
 if NF_TABLES_NETDEV
 
 config NF_DUP_NETDEV
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index 5cbbf6978b55..cf61615cc529 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -111,6 +111,7 @@ obj-$(CONFIG_NFT_FIB_INET)	+= nft_fib_inet.o
 obj-$(CONFIG_NFT_FIB_NETDEV)	+= nft_fib_netdev.o
 obj-$(CONFIG_NFT_SOCKET)	+= nft_socket.o
 obj-$(CONFIG_NFT_OSF)		+= nft_osf.o
+obj-$(CONFIG_NFT_TPROXY)	+= nft_tproxy.o
 
 # nf_tables netdev
 obj-$(CONFIG_NFT_DUP_NETDEV)	+= nft_dup_netdev.o
diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
new file mode 100644
index 000000000000..c6845f7baa08
--- /dev/null
+++ b/net/netfilter/nft_tproxy.c
@@ -0,0 +1,314 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/module.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_core.h>
+#include <net/netfilter/nf_tproxy.h>
+#include <net/inet_sock.h>
+#include <net/tcp.h>
+#include <linux/if_ether.h>
+#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#endif
+
+struct nft_tproxy {
+	enum nft_registers      sreg_addr:8;
+	enum nft_registers      sreg_port:8;
+	u8			family;
+};
+
+static void nft_tproxy_eval_v4(const struct nft_expr *expr,
+			       struct nft_regs *regs,
+			       const struct nft_pktinfo *pkt)
+{
+	const struct nft_tproxy *priv = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	const struct iphdr *iph = ip_hdr(skb);
+	struct udphdr _hdr, *hp;
+	__be32 taddr = 0;
+	__be16 tport = 0;
+	struct sock *sk;
+
+	hp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_hdr), &_hdr);
+	if (!hp) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+
+	/* check if there's an ongoing connection on the packet addresses, this
+	 * happens if the redirect already happened and the current packet
+	 * belongs to an already established connection
+	 */
+	sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol,
+				   iph->saddr, iph->daddr,
+				   hp->source, hp->dest,
+				   skb->dev, NF_TPROXY_LOOKUP_ESTABLISHED);
+
+	if (priv->sreg_addr)
+		taddr = regs->data[priv->sreg_addr];
+	taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr);
+
+	if (priv->sreg_port)
+		tport = regs->data[priv->sreg_port];
+	if (!tport)
+		tport = hp->dest;
+
+	/* UDP has no TCP_TIME_WAIT state, so we never enter here */
+	if (sk && sk->sk_state == TCP_TIME_WAIT) {
+		/* reopening a TIME_WAIT connection needs special handling */
+		sk = nf_tproxy_handle_time_wait4(nft_net(pkt), skb, taddr, tport, sk);
+	} else if (!sk) {
+		/* no, there's no established connection, check if
+		 * there's a listener on the redirected addr/port
+		 */
+		sk = nf_tproxy_get_sock_v4(nft_net(pkt), skb, iph->protocol,
+					   iph->saddr, taddr,
+					   hp->source, tport,
+					   skb->dev, NF_TPROXY_LOOKUP_LISTENER);
+	}
+
+	if (sk && nf_tproxy_sk_is_transparent(sk))
+		nf_tproxy_assign_sock(skb, sk);
+	else
+		regs->verdict.code = NFT_BREAK;
+}
+
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+static void nft_tproxy_eval_v6(const struct nft_expr *expr,
+			       struct nft_regs *regs,
+			       const struct nft_pktinfo *pkt)
+{
+	const struct nft_tproxy *priv = nft_expr_priv(expr);
+	struct sk_buff *skb = pkt->skb;
+	const struct ipv6hdr *iph = ipv6_hdr(skb);
+	struct in6_addr taddr = {0};
+	int thoff = pkt->xt.thoff;
+	struct udphdr _hdr, *hp;
+	__be16 tport = 0;
+	struct sock *sk;
+	int l4proto;
+
+	if (!pkt->tprot_set) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+	l4proto = pkt->tprot;
+
+	hp = skb_header_pointer(skb, thoff, sizeof(_hdr), &_hdr);
+	if (hp == NULL) {
+		regs->verdict.code = NFT_BREAK;
+		return;
+	}
+
+	/* check if there's an ongoing connection on the packet addresses, this
+	 * happens if the redirect already happened and the current packet
+	 * belongs to an already established connection
+	 */
+	sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff, l4proto,
+				   &iph->saddr, &iph->daddr,
+				   hp->source, hp->dest,
+				   nft_in(pkt), NF_TPROXY_LOOKUP_ESTABLISHED);
+
+	if (priv->sreg_addr)
+		memcpy(&taddr, &regs->data[priv->sreg_addr], sizeof(taddr));
+	taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr);
+
+	if (priv->sreg_port)
+		tport = regs->data[priv->sreg_port];
+	if (!tport)
+		tport = hp->dest;
+
+	/* UDP has no TCP_TIME_WAIT state, so we never enter here */
+	if (sk && sk->sk_state == TCP_TIME_WAIT) {
+		/* reopening a TIME_WAIT connection needs special handling */
+		sk = nf_tproxy_handle_time_wait6(skb, l4proto, thoff,
+						 nft_net(pkt),
+						 &taddr,
+						 tport,
+						 sk);
+	} else if (!sk) {
+		/* no there's no established connection, check if
+		 * there's a listener on the redirected addr/port
+		 */
+		sk = nf_tproxy_get_sock_v6(nft_net(pkt), skb, thoff,
+					   l4proto, &iph->saddr, &taddr,
+					   hp->source, tport,
+					   nft_in(pkt), NF_TPROXY_LOOKUP_LISTENER);
+	}
+
+	/* NOTE: assign_sock consumes our sk reference */
+	if (sk && nf_tproxy_sk_is_transparent(sk))
+		nf_tproxy_assign_sock(skb, sk);
+	else
+		regs->verdict.code = NFT_BREAK;
+}
+#endif
+
+static void nft_tproxy_eval(const struct nft_expr *expr,
+			    struct nft_regs *regs,
+			    const struct nft_pktinfo *pkt)
+{
+	const struct nft_tproxy *priv = nft_expr_priv(expr);
+
+	switch (nft_pf(pkt)) {
+	case NFPROTO_IPV4:
+		switch (priv->family) {
+		case NFPROTO_IPV4:
+		case NFPROTO_UNSPEC:
+			nft_tproxy_eval_v4(expr, regs, pkt);
+			return;
+		}
+		break;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+	case NFPROTO_IPV6:
+		switch (priv->family) {
+		case NFPROTO_IPV6:
+		case NFPROTO_UNSPEC:
+			nft_tproxy_eval_v6(expr, regs, pkt);
+			return;
+		}
+#endif
+	}
+	regs->verdict.code = NFT_BREAK;
+}
+
+static const struct nla_policy nft_tproxy_policy[NFTA_TPROXY_MAX + 1] = {
+	[NFTA_TPROXY_FAMILY]   = { .type = NLA_U32 },
+	[NFTA_TPROXY_REG_ADDR] = { .type = NLA_U32 },
+	[NFTA_TPROXY_REG_PORT] = { .type = NLA_U32 },
+};
+
+static int nft_tproxy_init(const struct nft_ctx *ctx,
+			   const struct nft_expr *expr,
+			   const struct nlattr * const tb[])
+{
+	struct nft_tproxy *priv = nft_expr_priv(expr);
+	unsigned int alen = 0;
+	int err;
+
+	if (!tb[NFTA_TPROXY_FAMILY] ||
+	    (!tb[NFTA_TPROXY_REG_ADDR] && !tb[NFTA_TPROXY_REG_PORT]))
+		return -EINVAL;
+
+	priv->family = ntohl(nla_get_be32(tb[NFTA_TPROXY_FAMILY]));
+
+	switch (ctx->family) {
+	case NFPROTO_IPV4:
+		if (priv->family != NFPROTO_IPV4)
+			return -EINVAL;
+		break;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+	case NFPROTO_IPV6:
+		if (priv->family != NFPROTO_IPV6)
+			return -EINVAL;
+		break;
+#endif
+	case NFPROTO_INET:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/* Address is specified but the rule family is not set accordingly */
+	if (priv->family == NFPROTO_UNSPEC && tb[NFTA_TPROXY_REG_ADDR])
+		return -EINVAL;
+
+	switch (priv->family) {
+	case NFPROTO_IPV4:
+		alen = FIELD_SIZEOF(union nf_inet_addr, in);
+		err = nf_defrag_ipv4_enable(ctx->net);
+		if (err)
+			return err;
+		break;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
+	case NFPROTO_IPV6:
+		alen = FIELD_SIZEOF(union nf_inet_addr, in6);
+		err = nf_defrag_ipv6_enable(ctx->net);
+		if (err)
+			return err;
+		break;
+#endif
+	case NFPROTO_UNSPEC:
+		/* No address is specified here */
+		err = nf_defrag_ipv4_enable(ctx->net);
+		if (err)
+			return err;
+		err = nf_defrag_ipv6_enable(ctx->net);
+		if (err)
+			return err;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (tb[NFTA_TPROXY_REG_ADDR]) {
+		priv->sreg_addr = nft_parse_register(tb[NFTA_TPROXY_REG_ADDR]);
+		err = nft_validate_register_load(priv->sreg_addr, alen);
+		if (err < 0)
+			return err;
+	}
+
+	if (tb[NFTA_TPROXY_REG_PORT]) {
+		priv->sreg_port = nft_parse_register(tb[NFTA_TPROXY_REG_PORT]);
+		err = nft_validate_register_load(priv->sreg_port, sizeof(u16));
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
+static int nft_tproxy_dump(struct sk_buff *skb,
+			   const struct nft_expr *expr)
+{
+	const struct nft_tproxy *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_TPROXY_FAMILY, htonl(priv->family)))
+		return -1;
+
+	if (priv->sreg_addr &&
+	    nft_dump_register(skb, NFTA_TPROXY_REG_ADDR, priv->sreg_addr))
+		return -1;
+
+	if (priv->sreg_port &&
+	    nft_dump_register(skb, NFTA_TPROXY_REG_PORT, priv->sreg_port))
+			return -1;
+
+	return 0;
+}
+
+static struct nft_expr_type nft_tproxy_type;
+static const struct nft_expr_ops nft_tproxy_ops = {
+	.type		= &nft_tproxy_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_tproxy)),
+	.eval		= nft_tproxy_eval,
+	.init		= nft_tproxy_init,
+	.dump		= nft_tproxy_dump,
+};
+
+static struct nft_expr_type nft_tproxy_type __read_mostly = {
+	.name		= "tproxy",
+	.ops		= &nft_tproxy_ops,
+	.policy		= nft_tproxy_policy,
+	.maxattr	= NFTA_TPROXY_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_tproxy_module_init(void)
+{
+	return nft_register_expr(&nft_tproxy_type);
+}
+
+static void __exit nft_tproxy_module_exit(void)
+{
+	nft_unregister_expr(&nft_tproxy_type);
+}
+
+module_init(nft_tproxy_module_init);
+module_exit(nft_tproxy_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Máté Eckl");
+MODULE_DESCRIPTION("nf_tables tproxy support module");
+MODULE_ALIAS_NFT_EXPR("tproxy");
-- 
cgit v1.2.3


From b3cadaa485f0c20add1644a5c877b0765b285c0c Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 30 Jul 2018 13:57:41 +0200
Subject: Bluetooth: hidp: Fix handling of strncpy for hid->name information
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes two issues with setting hid->name information.

  CC      net/bluetooth/hidp/core.o
In function ‘hidp_setup_hid’,
    inlined from ‘hidp_session_dev_init’ at net/bluetooth/hidp/core.c:815:9,
    inlined from ‘hidp_session_new’ at net/bluetooth/hidp/core.c:953:8,
    inlined from ‘hidp_connection_add’ at net/bluetooth/hidp/core.c:1366:8:
net/bluetooth/hidp/core.c:778:2: warning: ‘strncpy’ output may be truncated copying 127 bytes from a string of length 127 [-Wstringop-truncation]
  strncpy(hid->name, req->name, sizeof(req->name) - 1);
  ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

  CC      net/bluetooth/hidp/core.o
net/bluetooth/hidp/core.c: In function ‘hidp_setup_hid’:
net/bluetooth/hidp/core.c:778:38: warning: argument to ‘sizeof’ in ‘strncpy’ call is the same expression as the source; did you mean to use the size of the destination? [-Wsizeof-pointer-memaccess]
  strncpy(hid->name, req->name, sizeof(req->name));
                                      ^

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 net/bluetooth/hidp/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 1036e4fa1ea2..6f3eaf2fb94f 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -775,7 +775,7 @@ static int hidp_setup_hid(struct hidp_session *session,
 	hid->version = req->version;
 	hid->country = req->country;
 
-	strncpy(hid->name, req->name, sizeof(req->name) - 1);
+	strncpy(hid->name, req->name, sizeof(hid->name));
 
 	snprintf(hid->phys, sizeof(hid->phys), "%pMR",
 		 &l2cap_pi(session->ctrl_sock->sk)->chan->src);
-- 
cgit v1.2.3


From f609e7a0f3956e3b03af735b83600a4eef2a04ec Mon Sep 17 00:00:00 2001
From: Corentin Labbe <clabbe@baylibre.com>
Date: Thu, 7 Jun 2018 15:55:25 -0400
Subject: media: sii9234: remove unused header

The include/linux/platform_data/media/sii9234.h header file is unused,
let's remove it.

Signed-off-by: Corentin Labbe <clabbe@baylibre.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 include/linux/platform_data/media/sii9234.h | 24 ------------------------
 1 file changed, 24 deletions(-)
 delete mode 100644 include/linux/platform_data/media/sii9234.h

diff --git a/include/linux/platform_data/media/sii9234.h b/include/linux/platform_data/media/sii9234.h
deleted file mode 100644
index 6a4a809fe9a3..000000000000
--- a/include/linux/platform_data/media/sii9234.h
+++ /dev/null
@@ -1,24 +0,0 @@
-/*
- * Driver header for SII9234 MHL converter chip.
- *
- * Copyright (c) 2011 Samsung Electronics, Co. Ltd
- * Contact: Tomasz Stanislawski <t.stanislaws@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-#ifndef SII9234_H
-#define SII9234_H
-
-/**
- * @gpio_n_reset: GPIO driving nRESET pin
- */
-
-struct sii9234_platform_data {
-	int gpio_n_reset;
-};
-
-#endif /* SII9234_H */
-- 
cgit v1.2.3


From 489cae632fc04927e8ef36ac8d8847193a41df3b Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:19 -0600
Subject: include: Move ascii85 functions from i915 to linux/ascii85.h

The i915 DRM driver very cleverly used ascii85 encoding for their
GPU state file. Move the encode functions to a general header file to
support other drivers that might be interested in the same
functionality.

v4: Make the return value const char * as suggested by Chris Wilson
v3: Fix error_puts -> err_puts pointed out by the 01.org bot
v2: Update API to be cleaner for the caller as suggested by Chris Wilson

Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/i915/i915_gpu_error.c | 34 ++++---------------------------
 include/linux/ascii85.h               | 38 +++++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 30 deletions(-)
 create mode 100644 include/linux/ascii85.h

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 8c81cf3aa182..f7f2aa71d8d9 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -31,6 +31,7 @@
 #include <linux/stop_machine.h>
 #include <linux/zlib.h>
 #include <drm/drm_print.h>
+#include <linux/ascii85.h>
 
 #include "i915_gpu_error.h"
 #include "i915_drv.h"
@@ -517,35 +518,12 @@ void i915_error_printf(struct drm_i915_error_state_buf *e, const char *f, ...)
 	va_end(args);
 }
 
-static int
-ascii85_encode_len(int len)
-{
-	return DIV_ROUND_UP(len, 4);
-}
-
-static bool
-ascii85_encode(u32 in, char *out)
-{
-	int i;
-
-	if (in == 0)
-		return false;
-
-	out[5] = '\0';
-	for (i = 5; i--; ) {
-		out[i] = '!' + in % 85;
-		in /= 85;
-	}
-
-	return true;
-}
-
 static void print_error_obj(struct drm_i915_error_state_buf *m,
 			    struct intel_engine_cs *engine,
 			    const char *name,
 			    struct drm_i915_error_object *obj)
 {
-	char out[6];
+	char out[ASCII85_BUFSZ];
 	int page;
 
 	if (!obj)
@@ -567,12 +545,8 @@ static void print_error_obj(struct drm_i915_error_state_buf *m,
 			len -= obj->unused;
 		len = ascii85_encode_len(len);
 
-		for (i = 0; i < len; i++) {
-			if (ascii85_encode(obj->pages[page][i], out))
-				err_puts(m, out);
-			else
-				err_puts(m, "z");
-		}
+		for (i = 0; i < len; i++)
+			err_puts(m, ascii85_encode(obj->pages[page][i], out));
 	}
 	err_puts(m, "\n");
 }
diff --git a/include/linux/ascii85.h b/include/linux/ascii85.h
new file mode 100644
index 000000000000..4cc40201273e
--- /dev/null
+++ b/include/linux/ascii85.h
@@ -0,0 +1,38 @@
+/*
+ * SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright (c) 2008 Intel Corporation
+ * Copyright (c) 2018 The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _ASCII85_H_
+#define _ASCII85_H_
+
+#include <linux/kernel.h>
+
+#define ASCII85_BUFSZ 6
+
+static inline long
+ascii85_encode_len(long len)
+{
+	return DIV_ROUND_UP(len, 4);
+}
+
+static inline const char *
+ascii85_encode(u32 in, char *out)
+{
+	int i;
+
+	if (in == 0)
+		return "z";
+
+	out[5] = '\0';
+	for (i = 5; i--; ) {
+		out[i] = '!' + in % 85;
+		in /= 85;
+	}
+
+	return out;
+}
+
+#endif
-- 
cgit v1.2.3


From cfc57a18a3c5dc95d06db80bddd30015162c57d2 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:20 -0600
Subject: drm: drm_printer: Add printer for devcoredump

Add a drm printer suitable for use with the read callback for
devcoredump or other suitable buffer based output format that
isn't otherwise covered by seq_file.

v2: Add improved documentation per Daniel Vetter

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/drm_print.c | 74 +++++++++++++++++++++++++++++++++++++++++++++
 include/drm/drm_print.h     | 65 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 139 insertions(+)

diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index b25f98f33f6c..03d1f98e5ac7 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -30,6 +30,80 @@
 #include <drm/drmP.h>
 #include <drm/drm_print.h>
 
+void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
+{
+	struct drm_print_iterator *iterator = p->arg;
+	ssize_t len;
+
+	if (!iterator->remain)
+		return;
+
+	/* Figure out how big the string will be */
+	len = snprintf(NULL, 0, "%pV", vaf);
+
+	if (iterator->offset < iterator->start) {
+		char *buf;
+		ssize_t copy;
+
+		if (iterator->offset + len <= iterator->start) {
+			iterator->offset += len;
+			return;
+		}
+
+		/* Print the string into a temporary buffer */
+		buf = kmalloc(len + 1,
+			GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+		if (!buf)
+			return;
+
+		snprintf(buf, len + 1, "%pV", vaf);
+
+		copy = len - (iterator->start - iterator->offset);
+
+		if (copy > iterator->remain)
+			copy = iterator->remain;
+
+		/* Copy out the bit of the string that we need */
+		memcpy(iterator->data,
+			buf + (iterator->start - iterator->offset), copy);
+
+		iterator->offset = iterator->start + copy;
+		iterator->remain -= copy;
+
+		kfree(buf);
+	} else {
+		char *buf;
+		ssize_t pos = iterator->offset - iterator->start;
+
+		if (len < iterator->remain) {
+			snprintf(((char *) iterator->data) + pos,
+				iterator->remain, "%pV", vaf);
+
+			iterator->offset += len;
+			iterator->remain -= len;
+
+			return;
+		}
+
+		/* Print the string into a temporary buffer */
+		buf = kmalloc(len + 1,
+			GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+		if (!buf)
+			return;
+
+		snprintf(buf, len + 1, "%pV", vaf);
+
+		/* Copy out the remaining bits */
+		memcpy(iterator->data + pos, buf, iterator->remain);
+
+		iterator->offset += iterator->remain;
+		iterator->remain = 0;
+
+		kfree(buf);
+	}
+}
+EXPORT_SYMBOL(__drm_printfn_coredump);
+
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf)
 {
 	seq_printf(p->arg, "%pV", vaf);
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index 767c90b654c5..e7570f93a21f 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -73,6 +73,7 @@ struct drm_printer {
 	const char *prefix;
 };
 
+void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf);
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf);
 void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf);
 void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf);
@@ -104,6 +105,70 @@ drm_vprintf(struct drm_printer *p, const char *fmt, va_list *va)
 #define drm_printf_indent(printer, indent, fmt, ...) \
 	drm_printf((printer), "%.*s" fmt, (indent), "\t\t\t\t\tX", ##__VA_ARGS__)
 
+/**
+ * struct drm_print_iterator - local struct used with drm_printer_coredump
+ * @data: Pointer to the devcoredump output buffer
+ * @start: The offset within the buffer to start writing
+ * @remain: The number of bytes to write for this iteration
+ */
+struct drm_print_iterator {
+	void *data;
+	ssize_t start;
+	ssize_t remain;
+	/* private: */
+	ssize_t offset;
+};
+
+/**
+ * drm_coredump_printer - construct a &drm_printer that can output to a buffer
+ * from the read function for devcoredump
+ * @iter: A pointer to a struct drm_print_iterator for the read instance
+ *
+ * This wrapper extends drm_printf() to work with a dev_coredumpm() callback
+ * function. The passed in drm_print_iterator struct contains the buffer
+ * pointer, size and offset as passed in from devcoredump.
+ *
+ * For example::
+ *
+ *	void coredump_read(char *buffer, loff_t offset, size_t count,
+ *		void *data, size_t datalen)
+ *	{
+ *		struct drm_print_iterator iter;
+ *		struct drm_printer p;
+ *
+ *		iter.data = buffer;
+ *		iter.start = offset;
+ *		iter.remain = count;
+ *
+ *		p = drm_coredump_printer(&iter);
+ *
+ *		drm_printf(p, "foo=%d\n", foo);
+ *	}
+ *
+ *	void makecoredump(...)
+ *	{
+ *		...
+ *		dev_coredumpm(dev, THIS_MODULE, data, 0, GFP_KERNEL,
+ *			coredump_read, ...)
+ *	}
+ *
+ * RETURNS:
+ * The &drm_printer object
+ */
+static inline struct drm_printer
+drm_coredump_printer(struct drm_print_iterator *iter)
+{
+	struct drm_printer p = {
+		.printfn = __drm_printfn_coredump,
+		.arg = iter,
+	};
+
+	/* Set the internal offset of the iterator to zero */
+	iter->offset = 0;
+
+	return p;
+}
+
 /**
  * drm_seq_file_printer - construct a &drm_printer that outputs to &seq_file
  * @f:  the &struct seq_file to output to
-- 
cgit v1.2.3


From 63f4cc015b66dd265c2fd6e7c94be1b9a3b72267 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:21 -0600
Subject: drm: Add drm_puts() to complement drm_printf()

Add drm_puts() for a much faster path to print constant strings
into a drm_printer object with memcpy and friends. This can
have seconds off of really large outputs such as GPU dumps.

If the drm_printer object supports a custom puts function then
use that otherwise fall back to the slower legacy printf call.

v2: Add documentation for drm_puts() per Daniel Vetter

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
[robclark fix minor htmldocs warning]
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/drm_print.c | 17 +++++++++++++++++
 include/drm/drm_print.h     |  2 ++
 2 files changed, 19 insertions(+)

diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index 03d1f98e5ac7..01d4e5583b5d 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -122,6 +122,23 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf)
 }
 EXPORT_SYMBOL(__drm_printfn_debug);
 
+/**
+ * drm_puts - print a const string to a &drm_printer stream
+ * @p: the &drm printer
+ * @str: const string
+ *
+ * Allow &drm_printer types that have a constant string
+ * option to use it.
+ */
+void drm_puts(struct drm_printer *p, const char *str)
+{
+	if (p->puts)
+		p->puts(p, str);
+	else
+		drm_printf(p, "%s", str);
+}
+EXPORT_SYMBOL(drm_puts);
+
 /**
  * drm_printf - print to a &drm_printer stream
  * @p: the &drm_printer
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index e7570f93a21f..f2f42bb87ef2 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -69,6 +69,7 @@
 struct drm_printer {
 	/* private: */
 	void (*printfn)(struct drm_printer *p, struct va_format *vaf);
+	void (*puts)(struct drm_printer *p, const char *str);
 	void *arg;
 	const char *prefix;
 };
@@ -80,6 +81,7 @@ void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf);
 
 __printf(2, 3)
 void drm_printf(struct drm_printer *p, const char *f, ...);
+void drm_puts(struct drm_printer *p, const char *str);
 
 __printf(2, 0)
 /**
-- 
cgit v1.2.3


From 4538d7324507fed892a18b79ad72c8501b6e7027 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:22 -0600
Subject: drm: Add a -puts() function for the seq_file printer

Add a puts() function to use seq_puts() to help speed up
up print time for constant strings.

Reviewed-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/drm_print.c | 6 ++++++
 include/drm/drm_print.h     | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index 01d4e5583b5d..45d787611723 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -104,6 +104,12 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
 }
 EXPORT_SYMBOL(__drm_printfn_coredump);
 
+void __drm_puts_seq_file(struct drm_printer *p, const char *str)
+{
+	seq_puts(p->arg, str);
+}
+EXPORT_SYMBOL(__drm_puts_seq_file);
+
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf)
 {
 	seq_printf(p->arg, "%pV", vaf);
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index f2f42bb87ef2..b1432969b627 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -76,6 +76,7 @@ struct drm_printer {
 
 void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf);
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf);
+void __drm_puts_seq_file(struct drm_printer *p, const char *str);
 void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf);
 void __drm_printfn_debug(struct drm_printer *p, struct va_format *vaf);
 
@@ -182,6 +183,7 @@ static inline struct drm_printer drm_seq_file_printer(struct seq_file *f)
 {
 	struct drm_printer p = {
 		.printfn = __drm_printfn_seq_file,
+		.puts = __drm_puts_seq_file,
 		.arg = f,
 	};
 	return p;
-- 
cgit v1.2.3


From 5dc634bdbfd6dd9bdf98bce0d6f64878e1d47b1f Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:23 -0600
Subject: drm: Add puts callback for the coredump printer

Add a puts function for the coredump printer to bypass printf()
for constant strings for a speed boost. Reorganize the
coredump printf callback to share as much code as possible.

v2: Try to reuse code between print and puts as suggested by
    Chris Wilson

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/drm_print.c | 84 ++++++++++++++++++++++++++-------------------
 include/drm/drm_print.h     |  2 ++
 2 files changed, 51 insertions(+), 35 deletions(-)

diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index 45d787611723..0e7fc3e7dfb4 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -30,7 +30,7 @@
 #include <drm/drmP.h>
 #include <drm/drm_print.h>
 
-void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
+void __drm_puts_coredump(struct drm_printer *p, const char *str)
 {
 	struct drm_print_iterator *iterator = p->arg;
 	ssize_t len;
@@ -38,26 +38,16 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
 	if (!iterator->remain)
 		return;
 
-	/* Figure out how big the string will be */
-	len = snprintf(NULL, 0, "%pV", vaf);
-
 	if (iterator->offset < iterator->start) {
-		char *buf;
 		ssize_t copy;
 
+		len = strlen(str);
+
 		if (iterator->offset + len <= iterator->start) {
 			iterator->offset += len;
 			return;
 		}
 
-		/* Print the string into a temporary buffer */
-		buf = kmalloc(len + 1,
-			GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
-		if (!buf)
-			return;
-
-		snprintf(buf, len + 1, "%pV", vaf);
-
 		copy = len - (iterator->start - iterator->offset);
 
 		if (copy > iterator->remain)
@@ -65,42 +55,66 @@ void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
 
 		/* Copy out the bit of the string that we need */
 		memcpy(iterator->data,
-			buf + (iterator->start - iterator->offset), copy);
+			str + (iterator->start - iterator->offset), copy);
 
 		iterator->offset = iterator->start + copy;
 		iterator->remain -= copy;
-
-		kfree(buf);
 	} else {
-		char *buf;
 		ssize_t pos = iterator->offset - iterator->start;
 
-		if (len < iterator->remain) {
-			snprintf(((char *) iterator->data) + pos,
-				iterator->remain, "%pV", vaf);
+		len = min_t(ssize_t, strlen(str), iterator->remain);
 
-			iterator->offset += len;
-			iterator->remain -= len;
+		memcpy(iterator->data + pos, str, len);
 
-			return;
-		}
+		iterator->offset += len;
+		iterator->remain -= len;
+	}
+}
+EXPORT_SYMBOL(__drm_puts_coredump);
 
-		/* Print the string into a temporary buffer */
-		buf = kmalloc(len + 1,
-			GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
-		if (!buf)
-			return;
+void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf)
+{
+	struct drm_print_iterator *iterator = p->arg;
+	size_t len;
+	char *buf;
+
+	if (!iterator->remain)
+		return;
+
+	/* Figure out how big the string will be */
+	len = snprintf(NULL, 0, "%pV", vaf);
+
+	/* This is the easiest path, we've already advanced beyond the offset */
+	if (iterator->offset + len <= iterator->start) {
+		iterator->offset += len;
+		return;
+	}
 
-		snprintf(buf, len + 1, "%pV", vaf);
+	/* Then check if we can directly copy into the target buffer */
+	if ((iterator->offset >= iterator->start) && (len < iterator->remain)) {
+		ssize_t pos = iterator->offset - iterator->start;
 
-		/* Copy out the remaining bits */
-		memcpy(iterator->data + pos, buf, iterator->remain);
+		snprintf(((char *) iterator->data) + pos,
+			iterator->remain, "%pV", vaf);
 
-		iterator->offset += iterator->remain;
-		iterator->remain = 0;
+		iterator->offset += len;
+		iterator->remain -= len;
 
-		kfree(buf);
+		return;
 	}
+
+	/*
+	 * Finally, hit the slow path and make a temporary string to copy over
+	 * using _drm_puts_coredump
+	 */
+	buf = kmalloc(len + 1, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY);
+	if (!buf)
+		return;
+
+	snprintf(buf, len + 1, "%pV", vaf);
+	__drm_puts_coredump(p, (const char *) buf);
+
+	kfree(buf);
 }
 EXPORT_SYMBOL(__drm_printfn_coredump);
 
diff --git a/include/drm/drm_print.h b/include/drm/drm_print.h
index b1432969b627..f3e6eed3e79c 100644
--- a/include/drm/drm_print.h
+++ b/include/drm/drm_print.h
@@ -75,6 +75,7 @@ struct drm_printer {
 };
 
 void __drm_printfn_coredump(struct drm_printer *p, struct va_format *vaf);
+void __drm_puts_coredump(struct drm_printer *p, const char *str);
 void __drm_printfn_seq_file(struct drm_printer *p, struct va_format *vaf);
 void __drm_puts_seq_file(struct drm_printer *p, const char *str);
 void __drm_printfn_info(struct drm_printer *p, struct va_format *vaf);
@@ -163,6 +164,7 @@ drm_coredump_printer(struct drm_print_iterator *iter)
 {
 	struct drm_printer p = {
 		.printfn = __drm_printfn_coredump,
+		.puts = __drm_puts_coredump,
 		.arg = iter,
 	};
 
-- 
cgit v1.2.3


From e00e473d9817e03cddbaf181a491c42ae8373482 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:24 -0600
Subject: drm/msm/gpu: Capture the state of the GPU

Add the infrastructure to capture the current state of the GPU and
store it in memory so that it can be dumped later.

For now grab the same basic ringbuffer information and registers
that are provided by the debugfs 'gpu' node but obviously this should
be extended to capture a much larger set of GPU information.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   | 15 +++++++++
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   | 14 +++++++++
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   | 22 +++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 55 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |  3 ++
 drivers/gpu/drm/msm/msm_gpu.h           | 20 ++++++++++++
 6 files changed, 129 insertions(+)

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 3ebbeb3a9b68..b707b5bca9ab 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -427,6 +427,19 @@ static void a3xx_dump(struct msm_gpu *gpu)
 			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
 	adreno_dump(gpu);
 }
+
+static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+
+	if (IS_ERR(state))
+		return state;
+
+	state->rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS);
+
+	return state;
+}
+
 /* Register offset defines for A3XX */
 static const unsigned int a3xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_AXXX_CP_RB_BASE),
@@ -453,6 +466,8 @@ static const struct adreno_gpu_funcs funcs = {
 #ifdef CONFIG_DEBUG_FS
 		.show = a3xx_show,
 #endif
+		.gpu_state_get = a3xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 };
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 16d3d596638e..17e97ebc1077 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -465,6 +465,18 @@ static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m)
 }
 #endif
 
+static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+
+	if (IS_ERR(state))
+		return state;
+
+	state->rbbm_status = gpu_read(gpu, REG_A4XX_RBBM_STATUS);
+
+	return state;
+}
+
 /* Register offset defines for A4XX, in order of enum adreno_regs */
 static const unsigned int a4xx_register_offsets[REG_ADRENO_REGISTER_MAX] = {
 	REG_ADRENO_DEFINE(REG_ADRENO_CP_RB_BASE, REG_A4XX_CP_RB_BASE),
@@ -541,6 +553,8 @@ static const struct adreno_gpu_funcs funcs = {
 #ifdef CONFIG_DEBUG_FS
 		.show = a4xx_show,
 #endif
+		.gpu_state_get = a4xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 	.get_timestamp = a4xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index d39400e5bc42..9e85e4f7016d 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1195,6 +1195,26 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
+static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state;
+
+	/*
+	 * Temporarily disable hardware clock gating before going into
+	 * adreno_show to avoid issues while reading the registers
+	 */
+	a5xx_set_hwcg(gpu, false);
+
+	state = adreno_gpu_state_get(gpu);
+
+	if (!IS_ERR(state))
+		state->rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
+
+	a5xx_set_hwcg(gpu, true);
+
+	return state;
+}
+
 #ifdef CONFIG_DEBUG_FS
 static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
 {
@@ -1244,6 +1264,8 @@ static const struct adreno_gpu_funcs funcs = {
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
+		.gpu_state_get = a5xx_gpu_state_get,
+		.gpu_state_put = adreno_gpu_state_put,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index bcbf9f2a29f9..4286a539f40a 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -368,6 +368,61 @@ bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return false;
 }
 
+struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
+{
+	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+	struct msm_gpu_state *state;
+	int i, count = 0;
+
+	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	do_gettimeofday(&state->time);
+
+	for (i = 0; i < gpu->nr_rings; i++) {
+		state->ring[i].fence = gpu->rb[i]->memptrs->fence;
+		state->ring[i].iova = gpu->rb[i]->iova;
+		state->ring[i].seqno = gpu->rb[i]->seqno;
+		state->ring[i].rptr = get_rptr(adreno_gpu, gpu->rb[i]);
+		state->ring[i].wptr = get_wptr(gpu->rb[i]);
+	}
+
+	/* Count the number of registers */
+	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2)
+		count += adreno_gpu->registers[i + 1] -
+			adreno_gpu->registers[i] + 1;
+
+	state->registers = kcalloc(count * 2, sizeof(u32), GFP_KERNEL);
+	if (state->registers) {
+		int pos = 0;
+
+		for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
+			u32 start = adreno_gpu->registers[i];
+			u32 end   = adreno_gpu->registers[i + 1];
+			u32 addr;
+
+			for (addr = start; addr <= end; addr++) {
+				state->registers[pos++] = addr;
+				state->registers[pos++] = gpu_read(gpu, addr);
+			}
+		}
+
+		state->nr_registers = count;
+	}
+
+	return state;
+}
+
+void adreno_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	kfree(state->registers);
+	kfree(state);
+}
+
 #ifdef CONFIG_DEBUG_FS
 void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
 {
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index bc9ec27e9ed8..734e31a9631f 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -229,6 +229,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
+struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu);
+void adreno_gpu_state_put(struct msm_gpu_state *state);
+
 /* ringbuffer helpers (the parts that are adreno specific) */
 
 static inline void
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index b8241179175a..de71cc04ecf3 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -27,6 +27,7 @@
 
 struct msm_gem_submit;
 struct msm_gpu_perfcntr;
+struct msm_gpu_state;
 
 struct msm_gpu_config {
 	const char *ioname;
@@ -69,6 +70,8 @@ struct msm_gpu_funcs {
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
 	int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value);
+	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
+	void (*gpu_state_put)(struct msm_gpu_state *state);
 };
 
 struct msm_gpu {
@@ -175,6 +178,23 @@ struct msm_gpu_submitqueue {
 	struct kref ref;
 };
 
+struct msm_gpu_state {
+	struct timeval time;
+
+	struct {
+		u64 iova;
+		u32 fence;
+		u32 seqno;
+		u32 rptr;
+		u32 wptr;
+	} ring[MSM_GPU_MAX_RINGS];
+
+	int nr_registers;
+	u32 *registers;
+
+	u32 rbbm_status;
+};
+
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
 {
 	msm_writel(data, gpu->mmio + (reg << 2));
-- 
cgit v1.2.3


From 4f776f4511c7f7b6576dfc38c609b168b9188d72 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:25 -0600
Subject: drm/msm/gpu: Convert the GPU show function to use the GPU state

Convert the existing GPU show function to use the GPU state to
dump the information rather than reading it directly from the hardware.
This will require an additional step to capture the state before
dumping it for the existing nodes but it will greatly facilitate reusing
the same code for dumping a previously captured state from a GPU hang.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   | 11 +---
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   | 12 +----
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   | 18 +------
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 30 +++++------
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |  3 +-
 drivers/gpu/drm/msm/msm_debugfs.c       | 92 ++++++++++++++++++++++++++++++---
 drivers/gpu/drm/msm/msm_gpu.h           |  3 +-
 7 files changed, 104 insertions(+), 65 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index b707b5bca9ab..4cffec2b6adc 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -411,15 +411,6 @@ static const unsigned int a3xx_registers[] = {
 	~0   /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a3xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A3XX_RBBM_STATUS));
-	adreno_show(gpu, m);
-}
-#endif
-
 /* would be nice to not have to duplicate the _show() stuff with printk(): */
 static void a3xx_dump(struct msm_gpu *gpu)
 {
@@ -464,7 +455,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a3xx_irq,
 		.destroy = a3xx_destroy,
 #ifdef CONFIG_DEBUG_FS
-		.show = a3xx_show,
+		.show = adreno_show,
 #endif
 		.gpu_state_get = a3xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 17e97ebc1077..95f08c22e8d7 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -455,16 +455,6 @@ static const unsigned int a4xx_registers[] = {
 	~0 /* sentinel */
 };
 
-#ifdef CONFIG_DEBUG_FS
-static void a4xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A4XX_RBBM_STATUS));
-	adreno_show(gpu, m);
-
-}
-#endif
-
 static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
 {
 	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
@@ -551,7 +541,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
 #ifdef CONFIG_DEBUG_FS
-		.show = a4xx_show,
+		.show = adreno_show,
 #endif
 		.gpu_state_get = a4xx_gpu_state_get,
 		.gpu_state_put = adreno_gpu_state_put,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 9e85e4f7016d..5f1aab3c1cb1 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1215,22 +1215,6 @@ static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
 	return state;
 }
 
-#ifdef CONFIG_DEBUG_FS
-static void a5xx_show(struct msm_gpu *gpu, struct seq_file *m)
-{
-	seq_printf(m, "status:   %08x\n",
-			gpu_read(gpu, REG_A5XX_RBBM_STATUS));
-
-	/*
-	 * Temporarily disable hardware clock gating before going into
-	 * adreno_show to avoid issues while reading the registers
-	 */
-	a5xx_set_hwcg(gpu, false);
-	adreno_show(gpu, m);
-	a5xx_set_hwcg(gpu, true);
-}
-#endif
-
 static struct msm_ringbuffer *a5xx_active_ring(struct msm_gpu *gpu)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
@@ -1260,7 +1244,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
 #ifdef CONFIG_DEBUG_FS
-		.show = a5xx_show,
+		.show = adreno_show,
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 4286a539f40a..42828253ede5 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -424,38 +424,34 @@ void adreno_gpu_state_put(struct msm_gpu_state *state)
 }
 
 #ifdef CONFIG_DEBUG_FS
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m)
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct seq_file *m)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i;
 
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	seq_printf(m, "status:   %08x\n", state->rbbm_status);
 	seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
 	for (i = 0; i < gpu->nr_rings; i++) {
-		struct msm_ringbuffer *ring = gpu->rb[i];
-
 		seq_printf(m, "rb %d: fence:    %d/%d\n", i,
-			ring->memptrs->fence, ring->seqno);
+			state->ring[i].fence, state->ring[i].seqno);
 
-		seq_printf(m, "      rptr:     %d\n",
-			get_rptr(adreno_gpu, ring));
-		seq_printf(m, "rb wptr:  %d\n", get_wptr(ring));
+		seq_printf(m, "      rptr:     %d\n", state->ring[i].rptr);
+		seq_printf(m, "rb wptr:  %d\n", state->ring[i].wptr);
 	}
 
-	/* dump these out in a form that can be parsed by demsm: */
 	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
-	for (i = 0; adreno_gpu->registers[i] != ~0; i += 2) {
-		uint32_t start = adreno_gpu->registers[i];
-		uint32_t end   = adreno_gpu->registers[i+1];
-		uint32_t addr;
-
-		for (addr = start; addr <= end; addr++) {
-			uint32_t val = gpu_read(gpu, addr);
-			seq_printf(m, "IO:R %08x %08x\n", addr<<2, val);
-		}
+	for (i = 0; i < state->nr_registers; i++) {
+		seq_printf(m, "IO:R %08x %08x\n",
+			state->registers[i * 2] << 2,
+			state->registers[(i * 2) + 1]);
 	}
 }
 #endif
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 734e31a9631f..90b6b59252af 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -216,7 +216,8 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
 bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
 #ifdef CONFIG_DEBUG_FS
-void adreno_show(struct msm_gpu *gpu, struct seq_file *m);
+void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct seq_file *m);
 #endif
 void adreno_dump_info(struct msm_gpu *gpu);
 void adreno_dump(struct msm_gpu *gpu);
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index 1ff3fda245d1..c3da12179888 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -16,26 +16,100 @@
  */
 
 #ifdef CONFIG_DEBUG_FS
+#include <linux/debugfs.h>
 #include "msm_drv.h"
 #include "msm_gpu.h"
 #include "msm_kms.h"
 #include "msm_debugfs.h"
 
-static int msm_gpu_show(struct drm_device *dev, struct seq_file *m)
+struct msm_gpu_show_priv {
+	struct msm_gpu_state *state;
+	struct drm_device *dev;
+};
+
+static int msm_gpu_show(struct seq_file *m, void *arg)
+{
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	seq_printf(m, "%s Status:\n", gpu->name);
+	gpu->funcs->show(gpu, show_priv->state, m);
+
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	return 0;
+}
+
+static int msm_gpu_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+	struct msm_gpu_show_priv *show_priv = m->private;
+	struct msm_drm_private *priv = show_priv->dev->dev_private;
+	struct msm_gpu *gpu = priv->gpu;
+	int ret;
+
+	ret = mutex_lock_interruptible(&show_priv->dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	gpu->funcs->gpu_state_put(show_priv->state);
+	mutex_unlock(&show_priv->dev->struct_mutex);
+
+	kfree(show_priv);
+
+	return single_release(inode, file);
+}
+
+static int msm_gpu_open(struct inode *inode, struct file *file)
 {
+	struct drm_device *dev = inode->i_private;
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gpu *gpu = priv->gpu;
+	struct msm_gpu_show_priv *show_priv;
+	int ret;
 
-	if (gpu) {
-		seq_printf(m, "%s Status:\n", gpu->name);
-		pm_runtime_get_sync(&gpu->pdev->dev);
-		gpu->funcs->show(gpu, m);
-		pm_runtime_put_sync(&gpu->pdev->dev);
+	if (!gpu)
+		return -ENODEV;
+
+	show_priv = kmalloc(sizeof(*show_priv), GFP_KERNEL);
+	if (!show_priv)
+		return -ENOMEM;
+
+	ret = mutex_lock_interruptible(&dev->struct_mutex);
+	if (ret)
+		return ret;
+
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	show_priv->state = gpu->funcs->gpu_state_get(gpu);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
+	mutex_unlock(&dev->struct_mutex);
+
+	if (IS_ERR(show_priv->state)) {
+		ret = PTR_ERR(show_priv->state);
+		kfree(show_priv);
+		return ret;
 	}
 
-	return 0;
+	show_priv->dev = dev;
+
+	return single_open(file, msm_gpu_show, show_priv);
 }
 
+static const struct file_operations msm_gpu_fops = {
+	.owner = THIS_MODULE,
+	.open = msm_gpu_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = msm_gpu_release,
+};
+
 static int msm_gem_show(struct drm_device *dev, struct seq_file *m)
 {
 	struct msm_drm_private *priv = dev->dev_private;
@@ -105,7 +179,6 @@ static int show_locked(struct seq_file *m, void *arg)
 }
 
 static struct drm_info_list msm_debugfs_list[] = {
-		{"gpu", show_locked, 0, msm_gpu_show},
 		{"gem", show_locked, 0, msm_gem_show},
 		{ "mm", show_locked, 0, msm_mm_show },
 		{ "fb", show_locked, 0, msm_fb_show },
@@ -158,6 +231,9 @@ int msm_debugfs_init(struct drm_minor *minor)
 		return ret;
 	}
 
+	debugfs_create_file("gpu", S_IRUSR, minor->debugfs_root,
+		dev, &msm_gpu_fops);
+
 	if (priv->kms->funcs->debugfs_init) {
 		ret = priv->kms->funcs->debugfs_init(priv->kms, minor);
 		if (ret)
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index de71cc04ecf3..d204eca8518e 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -65,7 +65,8 @@ struct msm_gpu_funcs {
 	void (*destroy)(struct msm_gpu *gpu);
 #ifdef CONFIG_DEBUG_FS
 	/* show GPU status in debugfs: */
-	void (*show)(struct msm_gpu *gpu, struct seq_file *m);
+	void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state,
+			struct seq_file *m);
 	/* for generation specific debugfs: */
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
-- 
cgit v1.2.3


From 65a3c2748e882da03102369edb6991e1dd88456e Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:26 -0600
Subject: drm/msm/gpu: Rearrange the code that collects the task during a hang

Do a bit of cleanup to prepare for upcoming changes to pass the
hanging task comm and cmdline to the crash dump function.

v2: Use GFP_ATOMIC while holding the rcu lock per Chris Wilson

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/msm_gpu.c | 20 +++++++++++---------
 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 1c09acfb4028..03ba8872cc99 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -314,6 +314,7 @@ static void recover_worker(struct work_struct *work)
 	struct msm_drm_private *priv = dev->dev_private;
 	struct msm_gem_submit *submit;
 	struct msm_ringbuffer *cur_ring = gpu->funcs->active_ring(gpu);
+	char *comm = NULL, *cmd = NULL;
 	int i;
 
 	mutex_lock(&dev->struct_mutex);
@@ -327,7 +328,7 @@ static void recover_worker(struct work_struct *work)
 		rcu_read_lock();
 		task = pid_task(submit->pid, PIDTYPE_PID);
 		if (task) {
-			char *cmd;
+			comm = kstrdup(task->comm, GFP_ATOMIC);
 
 			/*
 			 * So slightly annoying, in other paths like
@@ -340,22 +341,23 @@ static void recover_worker(struct work_struct *work)
 			 * about the submit going away.
 			 */
 			mutex_unlock(&dev->struct_mutex);
-			cmd = kstrdup_quotable_cmdline(task, GFP_KERNEL);
+			cmd = kstrdup_quotable_cmdline(task, GFP_ATOMIC);
 			mutex_lock(&dev->struct_mutex);
+		}
+		rcu_read_unlock();
 
+		if (comm && cmd) {
 			dev_err(dev->dev, "%s: offending task: %s (%s)\n",
-				gpu->name, task->comm, cmd);
+				gpu->name, comm, cmd);
 
 			msm_rd_dump_submit(priv->hangrd, submit,
-				"offending task: %s (%s)", task->comm, cmd);
-
-			kfree(cmd);
-		} else {
+				"offending task: %s (%s)", comm, cmd);
+		} else
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
-		}
-		rcu_read_unlock();
 	}
 
+	kfree(cmd);
+	kfree(comm);
 
 	/*
 	 * Update all the rings with the latest and greatest fence.. this
-- 
cgit v1.2.3


From c0fec7f562ec76404ef0f074a89113a703587f3d Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:27 -0600
Subject: drm/msm/gpu: Capture the GPU state on a GPU hang

Capture the GPU state on a GPU hang and store it for later playback
via the devcoredump facility. Only one crash state is stored at a
time on the assumption that the first hang is usually the most
interesting. The existing crash state can be cleared after capturing
it and then a new one will be captured on the next hang.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/Kconfig             |  1 +
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   |  2 +-
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   |  2 +-
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   |  4 +-
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 36 +++++++++-----
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |  6 +--
 drivers/gpu/drm/msm/msm_debugfs.c       |  5 +-
 drivers/gpu/drm/msm/msm_gpu.c           | 83 ++++++++++++++++++++++++++++++++-
 drivers/gpu/drm/msm/msm_gpu.h           | 38 ++++++++++++++-
 9 files changed, 154 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 38cbde971b48..843a9d40c05e 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -12,6 +12,7 @@ config DRM_MSM
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM
+	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
 	select PM_OPP
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index 4cffec2b6adc..fc502e412132 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -454,7 +454,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a3xx_irq,
 		.destroy = a3xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = adreno_show,
 #endif
 		.gpu_state_get = a3xx_gpu_state_get,
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 95f08c22e8d7..8129cf037db1 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -540,7 +540,7 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = adreno_active_ring,
 		.irq = a4xx_irq,
 		.destroy = a4xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = adreno_show,
 #endif
 		.gpu_state_get = a4xx_gpu_state_get,
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 5f1aab3c1cb1..16074fa6bf1e 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -1243,8 +1243,10 @@ static const struct adreno_gpu_funcs funcs = {
 		.active_ring = a5xx_active_ring,
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 		.show = adreno_show,
+#endif
+#if defined(CONFIG_DEBUG_FS)
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 42828253ede5..c72e3afc43a8 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -378,6 +378,8 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 	if (!state)
 		return ERR_PTR(-ENOMEM);
 
+	kref_init(&state->ref);
+
 	do_gettimeofday(&state->time);
 
 	for (i = 0; i < gpu->nr_rings; i++) {
@@ -414,18 +416,28 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 	return state;
 }
 
-void adreno_gpu_state_put(struct msm_gpu_state *state)
+static void adreno_gpu_state_destroy(struct kref *kref)
 {
-	if (IS_ERR_OR_NULL(state))
-		return;
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
 
+	kfree(state->comm);
+	kfree(state->cmd);
 	kfree(state->registers);
 	kfree(state);
 }
 
-#ifdef CONFIG_DEBUG_FS
+int adreno_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, adreno_gpu_state_destroy);
+}
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
-		struct seq_file *m)
+		struct drm_printer *p)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
 	int i;
@@ -433,23 +445,23 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 	if (IS_ERR_OR_NULL(state))
 		return;
 
-	seq_printf(m, "status:   %08x\n", state->rbbm_status);
-	seq_printf(m, "revision: %d (%d.%d.%d.%d)\n",
+	drm_printf(p, "status:   %08x\n", state->rbbm_status);
+	drm_printf(p, "revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
 	for (i = 0; i < gpu->nr_rings; i++) {
-		seq_printf(m, "rb %d: fence:    %d/%d\n", i,
+		drm_printf(p, "rb %d: fence:    %d/%d\n", i,
 			state->ring[i].fence, state->ring[i].seqno);
 
-		seq_printf(m, "      rptr:     %d\n", state->ring[i].rptr);
-		seq_printf(m, "rb wptr:  %d\n", state->ring[i].wptr);
+		drm_printf(p, "      rptr:     %d\n", state->ring[i].rptr);
+		drm_printf(p, "rb wptr:  %d\n", state->ring[i].wptr);
 	}
 
-	seq_printf(m, "IO:region %s 00000000 00020000\n", gpu->name);
+	drm_printf(p, "IO:region %s 00000000 00020000\n", gpu->name);
 	for (i = 0; i < state->nr_registers; i++) {
-		seq_printf(m, "IO:R %08x %08x\n",
+		drm_printf(p, "IO:R %08x %08x\n",
 			state->registers[i * 2] << 2,
 			state->registers[(i * 2) + 1]);
 	}
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 90b6b59252af..4a868aaf1a70 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -215,9 +215,9 @@ void adreno_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit,
 		struct msm_file_private *ctx);
 void adreno_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
 bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring);
-#ifdef CONFIG_DEBUG_FS
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
 void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
-		struct seq_file *m);
+		struct drm_printer *p);
 #endif
 void adreno_dump_info(struct msm_gpu *gpu);
 void adreno_dump(struct msm_gpu *gpu);
@@ -231,7 +231,7 @@ void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
 struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu);
-void adreno_gpu_state_put(struct msm_gpu_state *state);
+int adreno_gpu_state_put(struct msm_gpu_state *state);
 
 /* ringbuffer helpers (the parts that are adreno specific) */
 
diff --git a/drivers/gpu/drm/msm/msm_debugfs.c b/drivers/gpu/drm/msm/msm_debugfs.c
index c3da12179888..f0da0d3c8a80 100644
--- a/drivers/gpu/drm/msm/msm_debugfs.c
+++ b/drivers/gpu/drm/msm/msm_debugfs.c
@@ -29,6 +29,7 @@ struct msm_gpu_show_priv {
 
 static int msm_gpu_show(struct seq_file *m, void *arg)
 {
+	struct drm_printer p = drm_seq_file_printer(m);
 	struct msm_gpu_show_priv *show_priv = m->private;
 	struct msm_drm_private *priv = show_priv->dev->dev_private;
 	struct msm_gpu *gpu = priv->gpu;
@@ -38,8 +39,8 @@ static int msm_gpu_show(struct seq_file *m, void *arg)
 	if (ret)
 		return ret;
 
-	seq_printf(m, "%s Status:\n", gpu->name);
-	gpu->funcs->show(gpu, show_priv->state, m);
+	drm_printf(&p, "%s Status:\n", gpu->name);
+	gpu->funcs->show(gpu, show_priv->state, &p);
 
 	mutex_unlock(&show_priv->dev->struct_mutex);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 03ba8872cc99..5f39549d9a8b 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -20,10 +20,11 @@
 #include "msm_mmu.h"
 #include "msm_fence.h"
 
+#include <generated/utsrelease.h>
 #include <linux/string_helpers.h>
 #include <linux/pm_opp.h>
 #include <linux/devfreq.h>
-
+#include <linux/devcoredump.h>
 
 /*
  * Power Management:
@@ -273,6 +274,81 @@ int msm_gpu_hw_init(struct msm_gpu *gpu)
 	return ret;
 }
 
+#ifdef CONFIG_DEV_COREDUMP
+static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
+		size_t count, void *data, size_t datalen)
+{
+	struct msm_gpu *gpu = data;
+	struct drm_print_iterator iter;
+	struct drm_printer p;
+	struct msm_gpu_state *state;
+
+	state = msm_gpu_crashstate_get(gpu);
+	if (!state)
+		return 0;
+
+	iter.data = buffer;
+	iter.offset = 0;
+	iter.start = offset;
+	iter.remain = count;
+
+	p = drm_coredump_printer(&iter);
+
+	drm_printf(&p, "---\n");
+	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
+	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
+	drm_printf(&p, "time: %ld.%ld\n",
+		state->time.tv_sec, state->time.tv_usec);
+	if (state->comm)
+		drm_printf(&p, "comm: %s\n", state->comm);
+	if (state->cmd)
+		drm_printf(&p, "cmdline: %s\n", state->cmd);
+
+	gpu->funcs->show(gpu, state, &p);
+
+	msm_gpu_crashstate_put(gpu);
+
+	return count - iter.remain;
+}
+
+static void msm_gpu_devcoredump_free(void *data)
+{
+	struct msm_gpu *gpu = data;
+
+	msm_gpu_crashstate_put(gpu);
+}
+
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
+		char *cmd)
+{
+	struct msm_gpu_state *state;
+
+	/* Only save one crash state at a time */
+	if (gpu->crashstate)
+		return;
+
+	state = gpu->funcs->gpu_state_get(gpu);
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	/* Fill in the additional crash state information */
+	state->comm = kstrdup(comm, GFP_KERNEL);
+	state->cmd = kstrdup(cmd, GFP_KERNEL);
+
+	/* Set the active crash state to be dumped on failure */
+	gpu->crashstate = state;
+
+	/* FIXME: Release the crashstate if this errors out? */
+	dev_coredumpm(gpu->dev->dev, THIS_MODULE, gpu, 0, GFP_KERNEL,
+		msm_gpu_devcoredump_read, msm_gpu_devcoredump_free);
+}
+#else
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
+		char *cmd)
+{
+}
+#endif
+
 /*
  * Hangcheck detection for locked gpu:
  */
@@ -356,6 +432,11 @@ static void recover_worker(struct work_struct *work)
 			msm_rd_dump_submit(priv->hangrd, submit, NULL);
 	}
 
+	/* Record the crash state */
+	pm_runtime_get_sync(&gpu->pdev->dev);
+	msm_gpu_crashstate_capture(gpu, comm, cmd);
+	pm_runtime_put_sync(&gpu->pdev->dev);
+
 	kfree(cmd);
 	kfree(comm);
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index d204eca8518e..b1cb44922441 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -66,13 +66,13 @@ struct msm_gpu_funcs {
 #ifdef CONFIG_DEBUG_FS
 	/* show GPU status in debugfs: */
 	void (*show)(struct msm_gpu *gpu, struct msm_gpu_state *state,
-			struct seq_file *m);
+			struct drm_printer *p);
 	/* for generation specific debugfs: */
 	int (*debugfs_init)(struct msm_gpu *gpu, struct drm_minor *minor);
 #endif
 	int (*gpu_busy)(struct msm_gpu *gpu, uint64_t *value);
 	struct msm_gpu_state *(*gpu_state_get)(struct msm_gpu *gpu);
-	void (*gpu_state_put)(struct msm_gpu_state *state);
+	int (*gpu_state_put)(struct msm_gpu_state *state);
 };
 
 struct msm_gpu {
@@ -133,6 +133,8 @@ struct msm_gpu {
 		u64 busy_cycles;
 		ktime_t time;
 	} devfreq;
+
+	struct msm_gpu_state *crashstate;
 };
 
 /* It turns out that all targets use the same ringbuffer size */
@@ -180,6 +182,7 @@ struct msm_gpu_submitqueue {
 };
 
 struct msm_gpu_state {
+	struct kref ref;
 	struct timeval time;
 
 	struct {
@@ -194,6 +197,9 @@ struct msm_gpu_state {
 	u32 *registers;
 
 	u32 rbbm_status;
+
+	char *comm;
+	char *cmd;
 };
 
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
@@ -275,4 +281,32 @@ static inline void msm_submitqueue_put(struct msm_gpu_submitqueue *queue)
 		kref_put(&queue->ref, msm_submitqueue_destroy);
 }
 
+static inline struct msm_gpu_state *msm_gpu_crashstate_get(struct msm_gpu *gpu)
+{
+	struct msm_gpu_state *state = NULL;
+
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		kref_get(&gpu->crashstate->ref);
+		state = gpu->crashstate;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+
+	return state;
+}
+
+static inline void msm_gpu_crashstate_put(struct msm_gpu *gpu)
+{
+	mutex_lock(&gpu->dev->struct_mutex);
+
+	if (gpu->crashstate) {
+		if (gpu->funcs->gpu_state_put(gpu->crashstate))
+			gpu->crashstate = NULL;
+	}
+
+	mutex_unlock(&gpu->dev->struct_mutex);
+}
+
 #endif /* __MSM_GPU_H__ */
-- 
cgit v1.2.3


From bcf1d9fa5d03c1e86733411b5dc3a76ba7d75e6e Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:28 -0600
Subject: drm/msm/adreno: Convert the show/crash file format

Convert the format of the 'show' debugfs file and the crash
dump to a  format resembling YAML. This should be easier to
parse and be more flexible for future changes and expansions.

v2: Use a standard .rst for the msm crashdump documentation

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 Documentation/gpu/msm-crash-dump.rst    | 71 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 21 ++++++----
 2 files changed, 84 insertions(+), 8 deletions(-)
 create mode 100644 Documentation/gpu/msm-crash-dump.rst

diff --git a/Documentation/gpu/msm-crash-dump.rst b/Documentation/gpu/msm-crash-dump.rst
new file mode 100644
index 000000000000..75ab1d541c03
--- /dev/null
+++ b/Documentation/gpu/msm-crash-dump.rst
@@ -0,0 +1,71 @@
+=====================
+MSM Crash Dump Format
+=====================
+
+Following a GPU hang the MSM driver outputs debugging information via
+/sys/kernel/dri/X/show or via devcoredump (/sys/class/devcoredump/dcdX/data).
+This document describes how the output is formatted.
+
+Each entry is in the form key: value. Sections headers will not have a value
+and all the contents of a section will be indented two spaces from the header.
+Each section might have multiple array entries the start of which is designated
+by a (-).
+
+Mappings
+--------
+
+kernel
+	The kernel version that generated the dump (UTS_RELEASE).
+
+module
+	The module that generated the crashdump.
+
+time
+	The kernel time at crash formated as seconds.microseconds.
+
+comm
+	Comm string for the binary that generated the fault.
+
+cmdline
+	Command line for the binary that generated the fault.
+
+revision
+	ID of the GPU that generated the crash formatted as
+	core.major.minor.patchlevel separated by dots.
+
+rbbm-status
+	The current value of RBBM_STATUS which shows what top level GPU
+	components are in use at the time of crash.
+
+ringbuffer
+	Section containing the contents of each ringbuffer. Each ringbuffer is
+	identified with an id number.
+
+	id
+		Ringbuffer ID (0 based index).  Each ringbuffer in the section
+		will have its own unique id.
+	iova
+		GPU address of the ringbuffer.
+
+	last-fence
+		The last fence that was issued on the ringbuffer
+
+	retired-fence
+		The last fence retired on the ringbuffer.
+
+	rptr
+		The current read pointer (rptr) for the ringbuffer.
+
+	wptr
+		The current write pointer (wptr) for the ringbuffer.
+
+registers
+	Set of registers values. Each entry is on its own line enclosed
+	by brackets { }.
+
+	offset
+		Byte offset of the register from the start of the
+		GPU memory region.
+
+	value
+		Hexadecimal value of the register.
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index c72e3afc43a8..c7a998d9dc85 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -445,23 +445,28 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 	if (IS_ERR_OR_NULL(state))
 		return;
 
-	drm_printf(p, "status:   %08x\n", state->rbbm_status);
 	drm_printf(p, "revision: %d (%d.%d.%d.%d)\n",
 			adreno_gpu->info->revn, adreno_gpu->rev.core,
 			adreno_gpu->rev.major, adreno_gpu->rev.minor,
 			adreno_gpu->rev.patchid);
 
-	for (i = 0; i < gpu->nr_rings; i++) {
-		drm_printf(p, "rb %d: fence:    %d/%d\n", i,
-			state->ring[i].fence, state->ring[i].seqno);
+	drm_printf(p, "rbbm-status: 0x%08x\n", state->rbbm_status);
+
+	drm_puts(p, "ringbuffer:\n");
 
-		drm_printf(p, "      rptr:     %d\n", state->ring[i].rptr);
-		drm_printf(p, "rb wptr:  %d\n", state->ring[i].wptr);
+	for (i = 0; i < gpu->nr_rings; i++) {
+		drm_printf(p, "  - id: %d\n", i);
+		drm_printf(p, "    iova: 0x%016llx\n", state->ring[i].iova);
+		drm_printf(p, "    last-fence: %d\n", state->ring[i].seqno);
+		drm_printf(p, "    retired-fence: %d\n", state->ring[i].fence);
+		drm_printf(p, "    rptr: %d\n", state->ring[i].rptr);
+		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
 	}
 
-	drm_printf(p, "IO:region %s 00000000 00020000\n", gpu->name);
+	drm_puts(p, "registers:\n");
+
 	for (i = 0; i < state->nr_registers; i++) {
-		drm_printf(p, "IO:R %08x %08x\n",
+		drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
 			state->registers[i * 2] << 2,
 			state->registers[(i * 2) + 1]);
 	}
-- 
cgit v1.2.3


From 43a56687d15db09f3cf7b9d53b182bdef86c17c0 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:29 -0600
Subject: drm/msm/adreno: Add ringbuffer data to the GPU state

Add the contents of each ringbuffer to the GPU state and dump the
data in the crash file encoded with ascii85. To save space only
the used portions of the ringbuffer are dumped.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 Documentation/gpu/msm-crash-dump.rst    |  7 ++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 39 +++++++++++++++++++++++++++++++++
 drivers/gpu/drm/msm/msm_gpu.h           |  2 ++
 3 files changed, 48 insertions(+)

diff --git a/Documentation/gpu/msm-crash-dump.rst b/Documentation/gpu/msm-crash-dump.rst
index 75ab1d541c03..35e87004e006 100644
--- a/Documentation/gpu/msm-crash-dump.rst
+++ b/Documentation/gpu/msm-crash-dump.rst
@@ -59,6 +59,13 @@ ringbuffer
 	wptr
 		The current write pointer (wptr) for the ringbuffer.
 
+	size
+		Maximum size of the ringbuffer programmed in the hardware.
+
+	data
+		The contents of the ring encoded as ascii85.  Only the used
+		portions of the ring will be printed.
+
 registers
 	Set of registers values. Each entry is on its own line enclosed
 	by brackets { }.
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index c7a998d9dc85..808d4fc9c4a1 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -17,6 +17,7 @@
  * this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/ascii85.h>
 #include <linux/pm_opp.h>
 #include "adreno_gpu.h"
 #include "msm_gem.h"
@@ -383,11 +384,29 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 	do_gettimeofday(&state->time);
 
 	for (i = 0; i < gpu->nr_rings; i++) {
+		int size = 0, j;
+
 		state->ring[i].fence = gpu->rb[i]->memptrs->fence;
 		state->ring[i].iova = gpu->rb[i]->iova;
 		state->ring[i].seqno = gpu->rb[i]->seqno;
 		state->ring[i].rptr = get_rptr(adreno_gpu, gpu->rb[i]);
 		state->ring[i].wptr = get_wptr(gpu->rb[i]);
+
+		/* Copy at least 'wptr' dwords of the data */
+		size = state->ring[i].wptr;
+
+		/* After wptr find the last non zero dword to save space */
+		for (j = state->ring[i].wptr; j < MSM_GPU_RINGBUFFER_SZ >> 2; j++)
+			if (gpu->rb[i]->start[j])
+				size = j + 1;
+
+		if (size) {
+			state->ring[i].data = kmalloc(size << 2, GFP_KERNEL);
+			if (state->ring[i].data) {
+				memcpy(state->ring[i].data, gpu->rb[i]->start, size << 2);
+				state->ring[i].data_size = size << 2;
+			}
+		}
 	}
 
 	/* Count the number of registers */
@@ -418,9 +437,13 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 
 static void adreno_gpu_state_destroy(struct kref *kref)
 {
+	int i;
 	struct msm_gpu_state *state = container_of(kref,
 		struct msm_gpu_state, ref);
 
+	for (i = 0; i < ARRAY_SIZE(state->ring); i++)
+		kfree(state->ring[i].data);
+
 	kfree(state->comm);
 	kfree(state->cmd);
 	kfree(state->registers);
@@ -461,6 +484,22 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 		drm_printf(p, "    retired-fence: %d\n", state->ring[i].fence);
 		drm_printf(p, "    rptr: %d\n", state->ring[i].rptr);
 		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
+		drm_printf(p, "    size: %d\n", MSM_GPU_RINGBUFFER_SZ);
+
+		if (state->ring[i].data && state->ring[i].data_size) {
+			u32 *ptr = (u32 *) state->ring[i].data;
+			char out[ASCII85_BUFSZ];
+			long len = ascii85_encode_len(state->ring[i].data_size);
+			int j;
+
+			drm_printf(p, "    data: !!ascii85 |\n");
+			drm_printf(p, "     ");
+
+			for (j = 0; j < len; j++)
+				drm_printf(p, ascii85_encode(ptr[j], out));
+
+			drm_printf(p, "\n");
+		}
 	}
 
 	drm_puts(p, "registers:\n");
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index b1cb44922441..878090b57e90 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -191,6 +191,8 @@ struct msm_gpu_state {
 		u32 seqno;
 		u32 rptr;
 		u32 wptr;
+		void *data;
+		int data_size;
 	} ring[MSM_GPU_MAX_RINGS];
 
 	int nr_registers;
-- 
cgit v1.2.3


From 50f8d21863b9b774b198e631d2b14878f6a54b5b Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:30 -0600
Subject: drm/msm/adreno: Add a5xx specific registers for the GPU state

HLSQ, SP and TP registers are only accessible from a special
aperture and to make matters worse the aperture is blocked from
the CPU on targets that can support secure rendering. Luckily the
GPU hardware has its own purpose built register dumper that can
access the registers from the aperture. Add a5xx specific code
to program the crashdumper and retrieve the wayward registers
and dump them for the crash state.

Also, remove a block of registers the regular CPU accessible
list that aren't useful for debug which helps reduce the size
of the crash state file by a goodly amount.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 Documentation/gpu/msm-crash-dump.rst    |   4 +
 drivers/gpu/drm/msm/adreno/a3xx_gpu.c   |   8 +-
 drivers/gpu/drm/msm/adreno/a4xx_gpu.c   |   8 +-
 drivers/gpu/drm/msm/adreno/a5xx_gpu.c   | 236 ++++++++++++++++++++++++++++++--
 drivers/gpu/drm/msm/adreno/adreno_gpu.c |  23 ++--
 drivers/gpu/drm/msm/adreno/adreno_gpu.h |   4 +-
 6 files changed, 252 insertions(+), 31 deletions(-)

diff --git a/Documentation/gpu/msm-crash-dump.rst b/Documentation/gpu/msm-crash-dump.rst
index 35e87004e006..7943f43f70d6 100644
--- a/Documentation/gpu/msm-crash-dump.rst
+++ b/Documentation/gpu/msm-crash-dump.rst
@@ -76,3 +76,7 @@ registers
 
 	value
 		Hexadecimal value of the register.
+
+registers-hlsq
+		(5xx only) Register values from the HLSQ aperture.
+		Same format as the register section.
diff --git a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
index fc502e412132..669c2d4b070d 100644
--- a/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a3xx_gpu.c
@@ -421,10 +421,12 @@ static void a3xx_dump(struct msm_gpu *gpu)
 
 static struct msm_gpu_state *a3xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
 
-	if (IS_ERR(state))
-		return state;
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
 
 	state->rbbm_status = gpu_read(gpu, REG_A3XX_RBBM_STATUS);
 
diff --git a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
index 8129cf037db1..7c4e6dc1ed59 100644
--- a/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a4xx_gpu.c
@@ -457,10 +457,12 @@ static const unsigned int a4xx_registers[] = {
 
 static struct msm_gpu_state *a4xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	struct msm_gpu_state *state = adreno_gpu_state_get(gpu);
+	struct msm_gpu_state *state = kzalloc(sizeof(*state), GFP_KERNEL);
 
-	if (IS_ERR(state))
-		return state;
+	if (!state)
+		return ERR_PTR(-ENOMEM);
+
+	adreno_gpu_state_get(gpu, state);
 
 	state->rbbm_status = gpu_read(gpu, REG_A4XX_RBBM_STATUS);
 
diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
index 16074fa6bf1e..bd84f71d27d8 100644
--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
@@ -19,6 +19,7 @@
 #include <linux/soc/qcom/mdt_loader.h>
 #include <linux/pm_opp.h>
 #include <linux/nvmem-consumer.h>
+#include <linux/iopoll.h>
 #include "msm_gem.h"
 #include "msm_mmu.h"
 #include "a5xx_gpu.h"
@@ -1123,8 +1124,9 @@ static const u32 a5xx_registers[] = {
 	0xE800, 0xE806, 0xE810, 0xE89A, 0xE8A0, 0xE8A4, 0xE8AA, 0xE8EB,
 	0xE900, 0xE905, 0xEB80, 0xEB8F, 0xEBB0, 0xEBB0, 0xEC00, 0xEC05,
 	0xEC08, 0xECE9, 0xECF0, 0xECF0, 0xEA80, 0xEA80, 0xEA82, 0xEAA3,
-	0xEAA5, 0xEAC2, 0xA800, 0xA8FF, 0xAC60, 0xAC60, 0xB000, 0xB97F,
-	0xB9A0, 0xB9BF, ~0
+	0xEAA5, 0xEAC2, 0xA800, 0xA800, 0xA820, 0xA828, 0xA840, 0xA87D,
+	0XA880, 0xA88D, 0xA890, 0xA8A3, 0xA8D0, 0xA8D8, 0xA8E0, 0xA8F5,
+	0xAC60, 0xAC60, ~0,
 };
 
 static void a5xx_dump(struct msm_gpu *gpu)
@@ -1195,25 +1197,233 @@ static int a5xx_get_timestamp(struct msm_gpu *gpu, uint64_t *value)
 	return 0;
 }
 
+struct a5xx_crashdumper {
+	void *ptr;
+	struct drm_gem_object *bo;
+	u64 iova;
+};
+
+struct a5xx_gpu_state {
+	struct msm_gpu_state base;
+	u32 *hlsqregs;
+};
+
+#define gpu_poll_timeout(gpu, addr, val, cond, interval, timeout) \
+	readl_poll_timeout((gpu)->mmio + ((addr) << 2), val, cond, \
+		interval, timeout)
+
+static int a5xx_crashdumper_init(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	dumper->ptr = msm_gem_kernel_new_locked(gpu->dev,
+		SZ_1M, MSM_BO_UNCACHED, gpu->aspace,
+		&dumper->bo, &dumper->iova);
+
+	if (IS_ERR(dumper->ptr))
+		return PTR_ERR(dumper->ptr);
+
+	return 0;
+}
+
+static void a5xx_crashdumper_free(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	msm_gem_put_iova(dumper->bo, gpu->aspace);
+	msm_gem_put_vaddr(dumper->bo);
+
+	drm_gem_object_unreference(dumper->bo);
+}
+
+static int a5xx_crashdumper_run(struct msm_gpu *gpu,
+		struct a5xx_crashdumper *dumper)
+{
+	u32 val;
+
+	if (IS_ERR_OR_NULL(dumper->ptr))
+		return -EINVAL;
+
+	gpu_write64(gpu, REG_A5XX_CP_CRASH_SCRIPT_BASE_LO,
+		REG_A5XX_CP_CRASH_SCRIPT_BASE_HI, dumper->iova);
+
+	gpu_write(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, 1);
+
+	return gpu_poll_timeout(gpu, REG_A5XX_CP_CRASH_DUMP_CNTL, val,
+		val & 0x04, 100, 10000);
+}
+
+/*
+ * These are a list of the registers that need to be read through the HLSQ
+ * aperture through the crashdumper.  These are not nominally accessible from
+ * the CPU on a secure platform.
+ */
+static const struct {
+	u32 type;
+	u32 regoffset;
+	u32 count;
+} a5xx_hlsq_aperture_regs[] = {
+	{ 0x35, 0xe00, 0x32 },   /* HSLQ non-context */
+	{ 0x31, 0x2080, 0x1 },   /* HLSQ 2D context 0 */
+	{ 0x33, 0x2480, 0x1 },   /* HLSQ 2D context 1 */
+	{ 0x32, 0xe780, 0x62 },  /* HLSQ 3D context 0 */
+	{ 0x34, 0xef80, 0x62 },  /* HLSQ 3D context 1 */
+	{ 0x3f, 0x0ec0, 0x40 },  /* SP non-context */
+	{ 0x3d, 0x2040, 0x1 },   /* SP 2D context 0 */
+	{ 0x3b, 0x2440, 0x1 },   /* SP 2D context 1 */
+	{ 0x3e, 0xe580, 0x170 }, /* SP 3D context 0 */
+	{ 0x3c, 0xed80, 0x170 }, /* SP 3D context 1 */
+	{ 0x3a, 0x0f00, 0x1c },  /* TP non-context */
+	{ 0x38, 0x2000, 0xa },   /* TP 2D context 0 */
+	{ 0x36, 0x2400, 0xa },   /* TP 2D context 1 */
+	{ 0x39, 0xe700, 0x80 },  /* TP 3D context 0 */
+	{ 0x37, 0xef00, 0x80 },  /* TP 3D context 1 */
+};
+
+static void a5xx_gpu_state_get_hlsq_regs(struct msm_gpu *gpu,
+		struct a5xx_gpu_state *a5xx_state)
+{
+	struct a5xx_crashdumper dumper = { 0 };
+	u32 offset, count = 0;
+	u64 *ptr;
+	int i;
+
+	if (a5xx_crashdumper_init(gpu, &dumper))
+		return;
+
+	/* The script will be written at offset 0 */
+	ptr = dumper.ptr;
+
+	/* Start writing the data at offset 256k */
+	offset = dumper.iova + (256 * SZ_1K);
+
+	/* Count how many additional registers to get from the HLSQ aperture */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++)
+		count += a5xx_hlsq_aperture_regs[i].count;
+
+	a5xx_state->hlsqregs = kcalloc(count, sizeof(u32), GFP_KERNEL);
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	/* Build the crashdump script */
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 type = a5xx_hlsq_aperture_regs[i].type;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		/* Write the register to select the desired bank */
+		*ptr++ = ((u64) type << 8);
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_READ_SEL) << 44) |
+			(1 << 21) | 1;
+
+		*ptr++ = offset;
+		*ptr++ = (((u64) REG_A5XX_HLSQ_DBG_AHB_READ_APERTURE) << 44)
+			| c;
+
+		offset += c * sizeof(u32);
+	}
+
+	/* Write two zeros to close off the script */
+	*ptr++ = 0;
+	*ptr++ = 0;
+
+	if (a5xx_crashdumper_run(gpu, &dumper)) {
+		kfree(a5xx_state->hlsqregs);
+		a5xx_crashdumper_free(gpu, &dumper);
+		return;
+	}
+
+	/* Copy the data from the crashdumper to the state */
+	memcpy(a5xx_state->hlsqregs, dumper.ptr + (256 * SZ_1K),
+		count * sizeof(u32));
+
+	a5xx_crashdumper_free(gpu, &dumper);
+}
+
 static struct msm_gpu_state *a5xx_gpu_state_get(struct msm_gpu *gpu)
 {
-	struct msm_gpu_state *state;
+	struct a5xx_gpu_state *a5xx_state = kzalloc(sizeof(*a5xx_state),
+			GFP_KERNEL);
 
-	/*
-	 * Temporarily disable hardware clock gating before going into
-	 * adreno_show to avoid issues while reading the registers
-	 */
+	if (!a5xx_state)
+		return ERR_PTR(-ENOMEM);
+
+	/* Temporarily disable hardware clock gating before reading the hw */
 	a5xx_set_hwcg(gpu, false);
 
-	state = adreno_gpu_state_get(gpu);
+	/* First get the generic state from the adreno core */
+	adreno_gpu_state_get(gpu, &(a5xx_state->base));
+
+	a5xx_state->base.rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
 
-	if (!IS_ERR(state))
-		state->rbbm_status = gpu_read(gpu, REG_A5XX_RBBM_STATUS);
+	/* Get the HLSQ regs with the help of the crashdumper */
+	a5xx_gpu_state_get_hlsq_regs(gpu, a5xx_state);
 
 	a5xx_set_hwcg(gpu, true);
 
-	return state;
+	return &a5xx_state->base;
+}
+
+static void a5xx_gpu_state_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	kfree(a5xx_state->hlsqregs);
+
+	adreno_gpu_state_destroy(state);
+	kfree(a5xx_state);
+}
+
+int a5xx_gpu_state_put(struct msm_gpu_state *state)
+{
+	if (IS_ERR_OR_NULL(state))
+		return 1;
+
+	return kref_put(&state->ref, a5xx_gpu_state_destroy);
+}
+
+
+#if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+void a5xx_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
+		struct drm_printer *p)
+{
+	int i, j;
+	u32 pos = 0;
+	struct a5xx_gpu_state *a5xx_state = container_of(state,
+		struct a5xx_gpu_state, base);
+
+	if (IS_ERR_OR_NULL(state))
+		return;
+
+	adreno_show(gpu, state, p);
+
+	/* Dump the additional a5xx HLSQ registers */
+	if (!a5xx_state->hlsqregs)
+		return;
+
+	drm_printf(p, "registers-hlsq:\n");
+
+	for (i = 0; i < ARRAY_SIZE(a5xx_hlsq_aperture_regs); i++) {
+		u32 o = a5xx_hlsq_aperture_regs[i].regoffset;
+		u32 c = a5xx_hlsq_aperture_regs[i].count;
+
+		for (j = 0; j < c; j++, pos++, o++) {
+			/*
+			 * To keep the crashdump simple we pull the entire range
+			 * for each register type but not all of the registers
+			 * in the range are valid. Fortunately invalid registers
+			 * stick out like a sore thumb with a value of
+			 * 0xdeadbeef
+			 */
+			if (a5xx_state->hlsqregs[pos] == 0xdeadbeef)
+				continue;
+
+			drm_printf(p, "  - { offset: 0x%04x, value: 0x%08x }\n",
+				o << 2, a5xx_state->hlsqregs[pos]);
+		}
+	}
 }
+#endif
 
 static struct msm_ringbuffer *a5xx_active_ring(struct msm_gpu *gpu)
 {
@@ -1244,14 +1454,14 @@ static const struct adreno_gpu_funcs funcs = {
 		.irq = a5xx_irq,
 		.destroy = a5xx_destroy,
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
-		.show = adreno_show,
+		.show = a5xx_show,
 #endif
 #if defined(CONFIG_DEBUG_FS)
 		.debugfs_init = a5xx_debugfs_init,
 #endif
 		.gpu_busy = a5xx_gpu_busy,
 		.gpu_state_get = a5xx_gpu_state_get,
-		.gpu_state_put = adreno_gpu_state_put,
+		.gpu_state_put = a5xx_gpu_state_put,
 	},
 	.get_timestamp = a5xx_get_timestamp,
 };
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 808d4fc9c4a1..cd418dab7a62 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -369,16 +369,11 @@ bool adreno_idle(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
 	return false;
 }
 
-struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 {
 	struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
-	struct msm_gpu_state *state;
 	int i, count = 0;
 
-	state = kzalloc(sizeof(*state), GFP_KERNEL);
-	if (!state)
-		return ERR_PTR(-ENOMEM);
-
 	kref_init(&state->ref);
 
 	do_gettimeofday(&state->time);
@@ -432,14 +427,12 @@ struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu)
 		state->nr_registers = count;
 	}
 
-	return state;
+	return 0;
 }
 
-static void adreno_gpu_state_destroy(struct kref *kref)
+void adreno_gpu_state_destroy(struct msm_gpu_state *state)
 {
 	int i;
-	struct msm_gpu_state *state = container_of(kref,
-		struct msm_gpu_state, ref);
 
 	for (i = 0; i < ARRAY_SIZE(state->ring); i++)
 		kfree(state->ring[i].data);
@@ -447,6 +440,14 @@ static void adreno_gpu_state_destroy(struct kref *kref)
 	kfree(state->comm);
 	kfree(state->cmd);
 	kfree(state->registers);
+}
+
+static void adreno_gpu_state_kref_destroy(struct kref *kref)
+{
+	struct msm_gpu_state *state = container_of(kref,
+		struct msm_gpu_state, ref);
+
+	adreno_gpu_state_destroy(state);
 	kfree(state);
 }
 
@@ -455,7 +456,7 @@ int adreno_gpu_state_put(struct msm_gpu_state *state)
 	if (IS_ERR_OR_NULL(state))
 		return 1;
 
-	return kref_put(&state->ref, adreno_gpu_state_destroy);
+	return kref_put(&state->ref, adreno_gpu_state_kref_destroy);
 }
 
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.h b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
index 4a868aaf1a70..4406776597fd 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.h
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.h
@@ -230,7 +230,9 @@ int adreno_gpu_init(struct drm_device *drm, struct platform_device *pdev,
 void adreno_gpu_cleanup(struct adreno_gpu *gpu);
 
 
-struct msm_gpu_state *adreno_gpu_state_get(struct msm_gpu *gpu);
+void adreno_gpu_state_destroy(struct msm_gpu_state *state);
+
+int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state);
 int adreno_gpu_state_put(struct msm_gpu_state *state);
 
 /* ringbuffer helpers (the parts that are adreno specific) */
-- 
cgit v1.2.3


From cdb95931dea32981545e34a3b1dfc9e172425d95 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Tue, 24 Jul 2018 10:33:31 -0600
Subject: drm/msm/gpu: Add the buffer objects from the submit to the crash dump

For hangs, dump copy out the contents of the buffer objects attached to the
guilty submission and print them in the crash dump report.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 Documentation/gpu/msm-crash-dump.rst    | 14 ++++++++
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 58 +++++++++++++++++++++++++++------
 drivers/gpu/drm/msm/msm_gpu.c           | 48 +++++++++++++++++++++++++--
 drivers/gpu/drm/msm/msm_gpu.h           |  9 +++++
 4 files changed, 116 insertions(+), 13 deletions(-)

diff --git a/Documentation/gpu/msm-crash-dump.rst b/Documentation/gpu/msm-crash-dump.rst
index 7943f43f70d6..757cd257e0d8 100644
--- a/Documentation/gpu/msm-crash-dump.rst
+++ b/Documentation/gpu/msm-crash-dump.rst
@@ -66,6 +66,20 @@ ringbuffer
 		The contents of the ring encoded as ascii85.  Only the used
 		portions of the ring will be printed.
 
+bo
+	List of buffers from the hanging submission if available.
+	Each buffer object will have a uinque iova.
+
+	iova
+		GPU address of the buffer object.
+
+	size
+		Allocated size of the buffer object.
+
+	data
+		The contents of the buffer object encoded with ascii85.  Only
+		Trailing zeros at the end of the buffer will be skipped.
+
 registers
 	Set of registers values. Each entry is on its own line enclosed
 	by brackets { }.
diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index cd418dab7a62..08d3c618b7de 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -437,6 +437,10 @@ void adreno_gpu_state_destroy(struct msm_gpu_state *state)
 	for (i = 0; i < ARRAY_SIZE(state->ring); i++)
 		kfree(state->ring[i].data);
 
+	for (i = 0; state->bos && i < state->nr_bos; i++)
+		kvfree(state->bos[i].data);
+
+	kfree(state->bos);
 	kfree(state->comm);
 	kfree(state->cmd);
 	kfree(state->registers);
@@ -460,6 +464,39 @@ int adreno_gpu_state_put(struct msm_gpu_state *state)
 }
 
 #if defined(CONFIG_DEBUG_FS) || defined(CONFIG_DEV_COREDUMP)
+
+static void adreno_show_object(struct drm_printer *p, u32 *ptr, int len)
+{
+	char out[ASCII85_BUFSZ];
+	long l, datalen, i;
+
+	if (!ptr || !len)
+		return;
+
+	/*
+	 * Only dump the non-zero part of the buffer - rarely will any data
+	 * completely fill the entire allocated size of the buffer
+	 */
+	for (datalen = 0, i = 0; i < len >> 2; i++) {
+		if (ptr[i])
+			datalen = (i << 2) + 1;
+	}
+
+	/* Skip printing the object if it is empty */
+	if (datalen == 0)
+		return;
+
+	l = ascii85_encode_len(datalen);
+
+	drm_puts(p, "    data: !!ascii85 |\n");
+	drm_puts(p, "     ");
+
+	for (i = 0; i < l; i++)
+		drm_puts(p, ascii85_encode(ptr[i], out));
+
+	drm_puts(p, "\n");
+}
+
 void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 		struct drm_printer *p)
 {
@@ -487,19 +524,20 @@ void adreno_show(struct msm_gpu *gpu, struct msm_gpu_state *state,
 		drm_printf(p, "    wptr: %d\n", state->ring[i].wptr);
 		drm_printf(p, "    size: %d\n", MSM_GPU_RINGBUFFER_SZ);
 
-		if (state->ring[i].data && state->ring[i].data_size) {
-			u32 *ptr = (u32 *) state->ring[i].data;
-			char out[ASCII85_BUFSZ];
-			long len = ascii85_encode_len(state->ring[i].data_size);
-			int j;
+		adreno_show_object(p, state->ring[i].data,
+			state->ring[i].data_size);
+	}
 
-			drm_printf(p, "    data: !!ascii85 |\n");
-			drm_printf(p, "     ");
+	if (state->bos) {
+		drm_puts(p, "bos:\n");
 
-			for (j = 0; j < len; j++)
-				drm_printf(p, ascii85_encode(ptr[j], out));
+		for (i = 0; i < state->nr_bos; i++) {
+			drm_printf(p, "  - iova: 0x%016llx\n",
+				state->bos[i].iova);
+			drm_printf(p, "    size: %zd\n", state->bos[i].size);
 
-			drm_printf(p, "\n");
+			adreno_show_object(p, state->bos[i].data,
+				state->bos[i].size);
 		}
 	}
 
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 5f39549d9a8b..3cf8e8d29812 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -318,8 +318,39 @@ static void msm_gpu_devcoredump_free(void *data)
 	msm_gpu_crashstate_put(gpu);
 }
 
-static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
-		char *cmd)
+static void msm_gpu_crashstate_get_bo(struct msm_gpu_state *state,
+		struct msm_gem_object *obj, u64 iova, u32 flags)
+{
+	struct msm_gpu_state_bo *state_bo = &state->bos[state->nr_bos];
+
+	/* Don't record write only objects */
+
+	state_bo->size = obj->base.size;
+	state_bo->iova = iova;
+
+	/* Only store the data for buffer objects marked for read */
+	if ((flags & MSM_SUBMIT_BO_READ)) {
+		void *ptr;
+
+		state_bo->data = kvmalloc(obj->base.size, GFP_KERNEL);
+		if (!state_bo->data)
+			return;
+
+		ptr = msm_gem_get_vaddr_active(&obj->base);
+		if (IS_ERR(ptr)) {
+			kvfree(state_bo->data);
+			return;
+		}
+
+		memcpy(state_bo->data, ptr, obj->base.size);
+		msm_gem_put_vaddr(&obj->base);
+	}
+
+	state->nr_bos++;
+}
+
+static void msm_gpu_crashstate_capture(struct msm_gpu *gpu,
+		struct msm_gem_submit *submit, char *comm, char *cmd)
 {
 	struct msm_gpu_state *state;
 
@@ -335,6 +366,17 @@ static void msm_gpu_crashstate_capture(struct msm_gpu *gpu, char *comm,
 	state->comm = kstrdup(comm, GFP_KERNEL);
 	state->cmd = kstrdup(cmd, GFP_KERNEL);
 
+	if (submit) {
+		int i;
+
+		state->bos = kcalloc(submit->nr_bos,
+			sizeof(struct msm_gpu_state_bo), GFP_KERNEL);
+
+		for (i = 0; state->bos && i < submit->nr_bos; i++)
+			msm_gpu_crashstate_get_bo(state, submit->bos[i].obj,
+				submit->bos[i].iova, submit->bos[i].flags);
+	}
+
 	/* Set the active crash state to be dumped on failure */
 	gpu->crashstate = state;
 
@@ -434,7 +476,7 @@ static void recover_worker(struct work_struct *work)
 
 	/* Record the crash state */
 	pm_runtime_get_sync(&gpu->pdev->dev);
-	msm_gpu_crashstate_capture(gpu, comm, cmd);
+	msm_gpu_crashstate_capture(gpu, submit, comm, cmd);
 	pm_runtime_put_sync(&gpu->pdev->dev);
 
 	kfree(cmd);
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 878090b57e90..57380ef8d1f7 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -181,6 +181,12 @@ struct msm_gpu_submitqueue {
 	struct kref ref;
 };
 
+struct msm_gpu_state_bo {
+	u64 iova;
+	size_t size;
+	void *data;
+};
+
 struct msm_gpu_state {
 	struct kref ref;
 	struct timeval time;
@@ -202,6 +208,9 @@ struct msm_gpu_state {
 
 	char *comm;
 	char *cmd;
+
+	int nr_bos;
+	struct msm_gpu_state_bo *bos;
 };
 
 static inline void gpu_write(struct msm_gpu *gpu, u32 reg, u32 data)
-- 
cgit v1.2.3


From 2c1f748d00e0617799c5bdbe9daf3a6a887b1b84 Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Wed, 25 Jul 2018 16:34:43 -0400
Subject: drm/msm: dpu: Use 'vsync' instead of 'vsync_clk' in cmdmode encoder

Should work with the legacy handling in of, but we shouldn't rely on
that.

Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index 035a5fbe1435..e6d02c6947b4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -424,7 +424,7 @@ static void dpu_encoder_phys_cmd_tearcheck_config(
 	 * vsync_count is ratio of MDP VSYNC clock frequency to LCD panel
 	 * frequency divided by the no. of rows (lines) in the LCDpanel.
 	 */
-	vsync_hz = dpu_kms_get_clk_rate(dpu_kms, "vsync_clk");
+	vsync_hz = dpu_kms_get_clk_rate(dpu_kms, "vsync");
 	if (vsync_hz <= 0) {
 		DPU_DEBUG_CMDENC(cmd_enc, "invalid - vsync_hz %u\n",
 				 vsync_hz);
-- 
cgit v1.2.3


From 41a8e8865a82b4fd4ff62b43b7c6d3bc5831f93d Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Wed, 25 Jul 2018 16:34:44 -0400
Subject: drm/msm: dpu: Use clock-names instead of assigned-clock-names

In these cases, we want to enumerate _all_ clocks, not just the ones
that are assigned a rate.

Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
index 8d907faa7496..c1d7eac4fa25 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -147,8 +147,7 @@ int msm_dss_parse_clock(struct platform_device *pdev,
 		return -EINVAL;
 
 	mp->num_clk = 0;
-	num_clk = of_property_count_strings(pdev->dev.of_node,
-					    "assigned-clock-names");
+	num_clk = of_property_count_strings(pdev->dev.of_node, "clock-names");
 	if (num_clk <= 0) {
 		pr_debug("clocks are not defined\n");
 		return 0;
@@ -162,7 +161,7 @@ int msm_dss_parse_clock(struct platform_device *pdev,
 
 	for (i = 0; i < num_clk; i++) {
 		rc = of_property_read_string_index(pdev->dev.of_node,
-						   "assigned-clock-names", i,
+						   "clock-names", i,
 						   &clock_name);
 		if (rc) {
 			dev_err(&pdev->dev, "Failed to get clock name for %d\n",
-- 
cgit v1.2.3


From a6bcddbc2ee1b2797fce016775b9e3faf17a4d0e Mon Sep 17 00:00:00 2001
From: Sean Paul <seanpaul@chromium.org>
Date: Wed, 25 Jul 2018 16:34:45 -0400
Subject: drm/msm: dsi: Handle dual-channel for 6G as well

This fixes up a collision between introducing dual-channel support and
the dsi refactors. This patch applies the same dual-channel
considerations and pclk calculations to both v2 and 6G, with a bit of
abstracting for good measure.

Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/dsi/dsi_host.c | 72 ++++++++++++++++++--------------------
 1 file changed, 35 insertions(+), 37 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
index 319501dcc083..96fb5f635314 100644
--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
+++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
@@ -664,11 +664,9 @@ void dsi_link_clk_disable_v2(struct msm_dsi_host *msm_host)
 	clk_disable_unprepare(msm_host->byte_clk);
 }
 
-int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+static u32 dsi_get_pclk_rate(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
 	struct drm_display_mode *mode = msm_host->mode;
-	u8 lanes = msm_host->lanes;
-	u32 bpp = dsi_get_bpp(msm_host->format);
 	u32 pclk_rate;
 
 	pclk_rate = mode->clock * 1000;
@@ -676,61 +674,61 @@ int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 	/*
 	 * For dual DSI mode, the current DRM mode has the complete width of the
 	 * panel. Since, the complete panel is driven by two DSI controllers,
-	 * theclock rates have to be split between the two dsi controllers.
+	 * the clock rates have to be split between the two dsi controllers.
 	 * Adjust the byte and pixel clock rates for each dsi host accordingly.
 	 */
 	if (is_dual_dsi)
 		pclk_rate /= 2;
 
-	if (lanes > 0) {
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / (8 * lanes);
-	} else {
+	return pclk_rate;
+}
+
+static void dsi_calc_pclk(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+{
+	u8 lanes = msm_host->lanes;
+	u32 bpp = dsi_get_bpp(msm_host->format);
+	u32 pclk_rate = dsi_get_pclk_rate(msm_host, is_dual_dsi);
+	u64 pclk_bpp = (u64)pclk_rate * bpp;
+
+	if (lanes == 0) {
 		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
-		msm_host->byte_clk_rate = (pclk_rate * bpp) / 8;
+		lanes = 1;
 	}
 
-	DBG("pclk=%d, bclk=%d", pclk_rate, msm_host->byte_clk_rate);
+	do_div(pclk_bpp, (8 * lanes));
 
-	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
+	msm_host->pixel_clk_rate = pclk_rate;
+	msm_host->byte_clk_rate = pclk_bpp;
+
+	DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate,
+				msm_host->byte_clk_rate);
+
+}
+
+int dsi_calc_clk_rate_6g(struct msm_dsi_host *msm_host, bool is_dual_dsi)
+{
+	if (!msm_host->mode) {
+		pr_err("%s: mode not set\n", __func__);
+		return -EINVAL;
+	}
 
+	dsi_calc_pclk(msm_host, is_dual_dsi);
+	msm_host->esc_clk_rate = clk_get_rate(msm_host->esc_clk);
 	return 0;
 }
 
 int dsi_calc_clk_rate_v2(struct msm_dsi_host *msm_host, bool is_dual_dsi)
 {
-	struct drm_display_mode *mode = msm_host->mode;
-	u8 lanes = msm_host->lanes;
 	u32 bpp = dsi_get_bpp(msm_host->format);
-	u32 pclk_rate;
 	u64 pclk_bpp;
 	unsigned int esc_mhz, esc_div;
 	unsigned long byte_mhz;
 
-	pclk_rate = mode->clock * 1000;
-
-	/*
-	 * For dual DSI mode, the current DRM mode has the complete width of the
-	 * panel. Since, the complete panel is driven by two DSI controllers,
-	 * theclock rates have to be split between the two dsi controllers.
-	 * Adjust the byte and pixel clock rates for each dsi host accordingly.
-	 */
-	if (is_dual_dsi)
-		pclk_rate /= 2;
-
-	pclk_bpp = pclk_rate * bpp;
-	if (lanes > 0) {
-		do_div(pclk_bpp, (8 * lanes));
-	} else {
-		pr_err("%s: forcing mdss_dsi lanes to 1\n", __func__);
-		do_div(pclk_bpp, 8);
-	}
-	msm_host->pixel_clk_rate = pclk_rate;
-	msm_host->byte_clk_rate = pclk_bpp;
-
-	DBG("pclk=%d, bclk=%d", msm_host->pixel_clk_rate,
-				msm_host->byte_clk_rate);
+	dsi_calc_pclk(msm_host, is_dual_dsi);
 
-	msm_host->src_clk_rate = (pclk_rate * bpp) / 8;
+	pclk_bpp = (u64)dsi_get_pclk_rate(msm_host, is_dual_dsi) * bpp;
+	do_div(pclk_bpp, 8);
+	msm_host->src_clk_rate = pclk_bpp;
 
 	/*
 	 * esc clock is byte clock followed by a 4 bit divider,
-- 
cgit v1.2.3


From 3530a17f4dc8f1f667fee14c16f229162daa79bb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 26 Jul 2018 14:39:25 +0200
Subject: drm/msm/gpu: avoid deprecated do_gettimeofday

All users of do_gettimeofday() have been removed, but this one recently
crept in, along with an incorrect printing of the microseconds portion.

This converts it to using ktime_get_real_timespec64() as a direct
replacement, and adds the leading zeroes. I considered using monotonic
times (ktime_get()) instead, but as this timestamp appears to only
be used for humans rather than compared with other timestamps, the
real time domain is probably good enough.

Fixes: e43b045e2c82 ("drm/msm/gpu: Capture the state of the GPU")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/adreno/adreno_gpu.c | 2 +-
 drivers/gpu/drm/msm/msm_gpu.c           | 4 ++--
 drivers/gpu/drm/msm/msm_gpu.h           | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
index 08d3c618b7de..38ac50b73829 100644
--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
@@ -376,7 +376,7 @@ int adreno_gpu_state_get(struct msm_gpu *gpu, struct msm_gpu_state *state)
 
 	kref_init(&state->ref);
 
-	do_gettimeofday(&state->time);
+	ktime_get_real_ts64(&state->time);
 
 	for (i = 0; i < gpu->nr_rings; i++) {
 		int size = 0, j;
diff --git a/drivers/gpu/drm/msm/msm_gpu.c b/drivers/gpu/drm/msm/msm_gpu.c
index 3cf8e8d29812..f388944c93e2 100644
--- a/drivers/gpu/drm/msm/msm_gpu.c
+++ b/drivers/gpu/drm/msm/msm_gpu.c
@@ -297,8 +297,8 @@ static ssize_t msm_gpu_devcoredump_read(char *buffer, loff_t offset,
 	drm_printf(&p, "---\n");
 	drm_printf(&p, "kernel: " UTS_RELEASE "\n");
 	drm_printf(&p, "module: " KBUILD_MODNAME "\n");
-	drm_printf(&p, "time: %ld.%ld\n",
-		state->time.tv_sec, state->time.tv_usec);
+	drm_printf(&p, "time: %lld.%09ld\n",
+		state->time.tv_sec, state->time.tv_nsec);
 	if (state->comm)
 		drm_printf(&p, "comm: %s\n", state->comm);
 	if (state->cmd)
diff --git a/drivers/gpu/drm/msm/msm_gpu.h b/drivers/gpu/drm/msm/msm_gpu.h
index 57380ef8d1f7..1c6105bc55c7 100644
--- a/drivers/gpu/drm/msm/msm_gpu.h
+++ b/drivers/gpu/drm/msm/msm_gpu.h
@@ -189,7 +189,7 @@ struct msm_gpu_state_bo {
 
 struct msm_gpu_state {
 	struct kref ref;
-	struct timeval time;
+	struct timespec64 time;
 
 	struct {
 		u64 iova;
-- 
cgit v1.2.3


From f4b0f66daf77ac79807711310597e4c102f72bd8 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Tue, 24 Jul 2018 19:51:59 +0800
Subject: drm/msm/dpu: fix mismatch in function argument.

Fix the sparse error. the dpu_rm_init declaration is not consistent
with the implement.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
[robclark un-typo'd subject line]
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
index ef3f67bedaa0..ffd1841a6067 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
@@ -105,7 +105,7 @@ struct dpu_rm_hw_iter {
  */
 int dpu_rm_init(struct dpu_rm *rm,
 		struct dpu_mdss_cfg *cat,
-		void *mmio,
+		void __iomem *mmio,
 		struct drm_device *dev);
 
 /**
-- 
cgit v1.2.3


From 78918cd0eee346c43e2d9dc553fadfacad6cb488 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 24 Jul 2018 17:35:37 +0200
Subject: drm/msm: mark PM functions as __maybe_unused

The suspend/resume functions are not referenced when power
management is disabled:

drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c:1288:12: error: 'dpu_runtime_resume' defined but not used [-Werror=unused-function]
drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c:1261:12: error: 'dpu_runtime_suspend' defined but not used [-Werror=unused-function]

This marks them as __maybe_unused to let the compiler
drop the functions without complaining.

Fixes: 591225291ca2 ("drm/msm: Add SDM845 DPU support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 8d4678d29cc7..1c0838801e78 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -1258,7 +1258,7 @@ static int dpu_dev_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static int dpu_runtime_suspend(struct device *dev)
+static int __maybe_unused dpu_runtime_suspend(struct device *dev)
 {
 	int rc = -1;
 	struct platform_device *pdev = to_platform_device(dev);
@@ -1285,7 +1285,7 @@ exit:
 	return rc;
 }
 
-static int dpu_runtime_resume(struct device *dev)
+static int __maybe_unused dpu_runtime_resume(struct device *dev)
 {
 	int rc = -1;
 	struct platform_device *pdev = to_platform_device(dev);
-- 
cgit v1.2.3


From aff24cd1f531b0dd55e46f6a8f76cf44117f0a24 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 23 Jul 2018 13:46:55 -0500
Subject: drm/msm: Replace PTR_RET with PTR_ERR_OR_ZERO

PTR_RET is deprecated, use PTR_ERR_OR_ZERO instead.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
index c1d7eac4fa25..790d39f816dc 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_io_util.c
@@ -35,7 +35,7 @@ int msm_dss_get_clk(struct device *dev, struct dss_clk *clk_arry, int num_clk)
 
 	for (i = 0; i < num_clk; i++) {
 		clk_arry[i].clk = clk_get(dev, clk_arry[i].clk_name);
-		rc = PTR_RET(clk_arry[i].clk);
+		rc = PTR_ERR_OR_ZERO(clk_arry[i].clk);
 		if (rc) {
 			DEV_ERR("%pS->%s: '%s' get failed. rc=%d\n",
 				__builtin_return_address(0), __func__,
-- 
cgit v1.2.3


From 2c7b48e7267adb0b79a0785563eaa69a35632155 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Thu, 26 Jul 2018 14:30:10 -0600
Subject: drm/msm/disp/dpu: Remove unused code from drm_encoder.c

Remove dpu_encoder_check_mode and dpu_encoder_helper_hw_release
frmo drm_encoder.c as they appear to be unused.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c      | 80 ------------------------
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h      |  8 ---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h |  9 ---
 3 files changed, 97 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 27775feed32b..5c0051af5e98 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -1627,22 +1627,6 @@ static void _dpu_encoder_kickoff_phys(struct dpu_encoder_virt *dpu_enc)
 	spin_unlock_irqrestore(&dpu_enc->enc_spinlock, lock_flags);
 }
 
-bool dpu_encoder_check_mode(struct drm_encoder *drm_enc, u32 mode)
-{
-	struct dpu_encoder_virt *dpu_enc;
-	struct msm_display_info *disp_info;
-
-	if (!drm_enc) {
-		DPU_ERROR("invalid encoder\n");
-		return false;
-	}
-
-	dpu_enc = to_dpu_encoder_virt(drm_enc);
-	disp_info = &dpu_enc->disp_info;
-
-	return (disp_info->capabilities & mode);
-}
-
 void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc;
@@ -1903,70 +1887,6 @@ void dpu_encoder_kickoff(struct drm_encoder *drm_enc)
 	DPU_ATRACE_END("encoder_kickoff");
 }
 
-int dpu_encoder_helper_hw_release(struct dpu_encoder_phys *phys_enc,
-		struct drm_framebuffer *fb)
-{
-	struct drm_encoder *drm_enc;
-	struct dpu_hw_mixer_cfg mixer;
-	struct dpu_rm_hw_iter lm_iter;
-	bool lm_valid = false;
-
-	if (!phys_enc || !phys_enc->parent) {
-		DPU_ERROR("invalid encoder\n");
-		return -EINVAL;
-	}
-
-	drm_enc = phys_enc->parent;
-	memset(&mixer, 0, sizeof(mixer));
-
-	/* reset associated CTL/LMs */
-	if (phys_enc->hw_ctl->ops.clear_pending_flush)
-		phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl);
-	if (phys_enc->hw_ctl->ops.clear_all_blendstages)
-		phys_enc->hw_ctl->ops.clear_all_blendstages(phys_enc->hw_ctl);
-
-	dpu_rm_init_hw_iter(&lm_iter, drm_enc->base.id, DPU_HW_BLK_LM);
-	while (dpu_rm_get_hw(&phys_enc->dpu_kms->rm, &lm_iter)) {
-		struct dpu_hw_mixer *hw_lm = (struct dpu_hw_mixer *)lm_iter.hw;
-
-		if (!hw_lm)
-			continue;
-
-		/* need to flush LM to remove it */
-		if (phys_enc->hw_ctl->ops.get_bitmask_mixer &&
-				phys_enc->hw_ctl->ops.update_pending_flush)
-			phys_enc->hw_ctl->ops.update_pending_flush(
-					phys_enc->hw_ctl,
-					phys_enc->hw_ctl->ops.get_bitmask_mixer(
-					phys_enc->hw_ctl, hw_lm->idx));
-
-		if (fb) {
-			/* assume a single LM if targeting a frame buffer */
-			if (lm_valid)
-				continue;
-
-			mixer.out_height = fb->height;
-			mixer.out_width = fb->width;
-
-			if (hw_lm->ops.setup_mixer_out)
-				hw_lm->ops.setup_mixer_out(hw_lm, &mixer);
-		}
-
-		lm_valid = true;
-
-		/* only enable border color on LM */
-		if (phys_enc->hw_ctl->ops.setup_blendstage)
-			phys_enc->hw_ctl->ops.setup_blendstage(
-					phys_enc->hw_ctl, hw_lm->idx, NULL);
-	}
-
-	if (!lm_valid) {
-		DPU_DEBUG_ENC(to_dpu_encoder_virt(drm_enc), "lm not found\n");
-		return -EFAULT;
-	}
-	return 0;
-}
-
 void dpu_encoder_prepare_commit(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
index ce92901ed227..204e538b0b74 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
@@ -139,14 +139,6 @@ enum dpu_intf_mode dpu_encoder_get_intf_mode(struct drm_encoder *encoder);
  */
 void dpu_encoder_virt_restore(struct drm_encoder *encoder);
 
-/**
- * dpu_encoder_check_mode - check if given mode is supported or not
- * @drm_enc: Pointer to drm encoder object
- * @mode: Mode to be checked
- * @Return: true if it is cmd mode
- */
-bool dpu_encoder_check_mode(struct drm_encoder *drm_enc, u32 mode);
-
 /**
  * dpu_encoder_init - initialize virtual encoder object
  * @dev:        Pointer to drm device structure
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
index 8505edddcc81..dacec1c8eeeb 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -402,15 +402,6 @@ void dpu_encoder_helper_split_config(
 		struct dpu_encoder_phys *phys_enc,
 		enum dpu_intf interface);
 
-/**
- * dpu_encoder_helper_hw_release - prepare for h/w reset during disable
- * @phys_enc: Pointer to physical encoder structure
- * @fb: Optional fb for specifying new mixer output resolution, may be NULL
- * Return: Zero on success
- */
-int dpu_encoder_helper_hw_release(struct dpu_encoder_phys *phys_enc,
-		struct drm_framebuffer *fb);
-
 /**
  * dpu_encoder_helper_report_irq_timeout - utility to report error that irq has
  *	timed out, including reporting frame error event to crtc and debug dump
-- 
cgit v1.2.3


From c17aeda0b01cbcb8e334665fefa64a5148ecd18f Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Thu, 26 Jul 2018 14:30:11 -0600
Subject: drm/msm/disp/dpu: Remove unused code from drm_crtc.c

Remove a chunk of unused code from drm_crtc.c, namely
dpu_crtc_res_add, dpu_crtc_res_get, dpu_crtc_res_put
and associated static functions.

Also zap dpu_crtc_event_queue(), helper functions
and members.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 383 +------------------------------
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h |  61 -----
 2 files changed, 2 insertions(+), 442 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 7ac0e0dda866..80cbf75bc2ff 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -280,289 +280,6 @@ static void _dpu_crtc_rp_reset(struct dpu_crtc_respool *rp,
 	mutex_unlock(rp_lock);
 }
 
-/**
- * _dpu_crtc_rp_add_no_lock - add given resource to resource pool without lock
- * @rp: Pointer to original resource pool
- * @type: Resource type
- * @tag: Search tag for given resource
- * @val: Resource handle
- * @ops: Resource callback operations
- * return: 0 if success; error code otherwise
- */
-static int _dpu_crtc_rp_add_no_lock(struct dpu_crtc_respool *rp, u32 type,
-		u64 tag, void *val, struct dpu_crtc_res_ops *ops)
-{
-	struct dpu_crtc_res *res;
-	struct drm_crtc *crtc;
-
-	if (!rp || !ops) {
-		DPU_ERROR("invalid resource pool/ops\n");
-		return -EINVAL;
-	}
-
-	crtc = _dpu_crtc_rp_to_crtc(rp);
-	if (!crtc) {
-		DPU_ERROR("invalid crtc\n");
-		return -EINVAL;
-	}
-
-	list_for_each_entry(res, &rp->res_list, list) {
-		if (res->type != type || res->tag != tag)
-			continue;
-		DPU_ERROR("crtc%d.%u already exist res:0x%x/0x%llx/%pK/%d\n",
-				crtc->base.id, rp->sequence_id,
-				res->type, res->tag, res->val,
-				atomic_read(&res->refcount));
-		return -EEXIST;
-	}
-	res = kzalloc(sizeof(struct dpu_crtc_res), GFP_KERNEL);
-	if (!res)
-		return -ENOMEM;
-	INIT_LIST_HEAD(&res->list);
-	atomic_set(&res->refcount, 1);
-	res->type = type;
-	res->tag = tag;
-	res->val = val;
-	res->ops = *ops;
-	list_add_tail(&res->list, &rp->res_list);
-	DPU_DEBUG("crtc%d.%u added res:0x%x/0x%llx\n",
-			crtc->base.id, rp->sequence_id, type, tag);
-	return 0;
-}
-
-/**
- * _dpu_crtc_rp_add - add given resource to resource pool
- * @rp: Pointer to original resource pool
- * @type: Resource type
- * @tag: Search tag for given resource
- * @val: Resource handle
- * @ops: Resource callback operations
- * return: 0 if success; error code otherwise
- */
-static int _dpu_crtc_rp_add(struct dpu_crtc_respool *rp, u32 type, u64 tag,
-		void *val, struct dpu_crtc_res_ops *ops)
-{
-	int rc;
-
-	if (!rp) {
-		DPU_ERROR("invalid resource pool\n");
-		return -EINVAL;
-	}
-
-	mutex_lock(rp->rp_lock);
-	rc = _dpu_crtc_rp_add_no_lock(rp, type, tag, val, ops);
-	mutex_unlock(rp->rp_lock);
-	return rc;
-}
-
-/**
- * _dpu_crtc_rp_get - lookup the resource from given resource pool and obtain
- *	if available; otherwise, obtain resource from global pool
- * @rp: Pointer to original resource pool
- * @type: Resource type
- * @tag:  Search tag for given resource
- * return: Resource handle if success; pointer error or null otherwise
- */
-static void *_dpu_crtc_rp_get(struct dpu_crtc_respool *rp, u32 type, u64 tag)
-{
-	struct dpu_crtc_respool *old_rp;
-	struct dpu_crtc_res *res;
-	void *val = NULL;
-	int rc;
-	struct drm_crtc *crtc;
-
-	if (!rp) {
-		DPU_ERROR("invalid resource pool\n");
-		return NULL;
-	}
-
-	crtc = _dpu_crtc_rp_to_crtc(rp);
-	if (!crtc) {
-		DPU_ERROR("invalid crtc\n");
-		return NULL;
-	}
-
-	mutex_lock(rp->rp_lock);
-	list_for_each_entry(res, &rp->res_list, list) {
-		if (res->type != type || res->tag != tag)
-			continue;
-		DPU_DEBUG("crtc%d.%u found res:0x%x/0x%llx/%pK/%d\n",
-				crtc->base.id, rp->sequence_id,
-				res->type, res->tag, res->val,
-				atomic_read(&res->refcount));
-		atomic_inc(&res->refcount);
-		res->flags &= ~DPU_CRTC_RES_FLAG_FREE;
-		mutex_unlock(rp->rp_lock);
-		return res->val;
-	}
-	list_for_each_entry(res, &rp->res_list, list) {
-		if (res->type != type || !(res->flags & DPU_CRTC_RES_FLAG_FREE))
-			continue;
-		DPU_DEBUG("crtc%d.%u retag res:0x%x/0x%llx/%pK/%d\n",
-				crtc->base.id, rp->sequence_id,
-				res->type, res->tag, res->val,
-				atomic_read(&res->refcount));
-		atomic_inc(&res->refcount);
-		res->tag = tag;
-		res->flags &= ~DPU_CRTC_RES_FLAG_FREE;
-		mutex_unlock(rp->rp_lock);
-		return res->val;
-	}
-	/* not in this rp, try to grab from global pool */
-	if (rp->ops.get)
-		val = rp->ops.get(NULL, type, -1);
-	if (!IS_ERR_OR_NULL(val))
-		goto add_res;
-	/*
-	 * Search older resource pools for hw blk with matching type,
-	 * necessary when resource is being used by this object,
-	 * but in previous states not yet cleaned up.
-	 *
-	 * This enables searching of all resources currently owned
-	 * by this crtc even though the resource might not be used
-	 * in the current atomic state. This allows those resources
-	 * to be re-acquired by the new atomic state immediately
-	 * without waiting for the resources to be fully released.
-	 */
-	else if (IS_ERR_OR_NULL(val) && (type < DPU_HW_BLK_MAX)) {
-		list_for_each_entry(old_rp, rp->rp_head, rp_list) {
-			if (old_rp == rp)
-				continue;
-
-			list_for_each_entry(res, &old_rp->res_list, list) {
-				if (res->type != type)
-					continue;
-				DRM_DEBUG_KMS("crtc%d.%u found res:0x%x//%pK/ "
-					      "in crtc%d.%d\n",
-					      crtc->base.id, rp->sequence_id,
-					      res->type, res->val,
-					      crtc->base.id,
-					      old_rp->sequence_id);
-				if (res->ops.get)
-					res->ops.get(res->val, 0, -1);
-				val = res->val;
-				break;
-			}
-
-			if (!IS_ERR_OR_NULL(val))
-				break;
-		}
-	}
-	if (IS_ERR_OR_NULL(val)) {
-		DPU_DEBUG("crtc%d.%u failed to get res:0x%x//\n",
-				crtc->base.id, rp->sequence_id, type);
-		mutex_unlock(rp->rp_lock);
-		return NULL;
-	}
-add_res:
-	rc = _dpu_crtc_rp_add_no_lock(rp, type, tag, val, &rp->ops);
-	if (rc) {
-		DPU_ERROR("crtc%d.%u failed to add res:0x%x/0x%llx\n",
-				crtc->base.id, rp->sequence_id, type, tag);
-		if (rp->ops.put)
-			rp->ops.put(val);
-		val = NULL;
-	}
-	mutex_unlock(rp->rp_lock);
-	return val;
-}
-
-/**
- * _dpu_crtc_rp_put - return given resource to resource pool
- * @rp: Pointer to original resource pool
- * @type: Resource type
- * @tag: Search tag for given resource
- * return: None
- */
-static void _dpu_crtc_rp_put(struct dpu_crtc_respool *rp, u32 type, u64 tag)
-{
-	struct dpu_crtc_res *res, *next;
-	struct drm_crtc *crtc;
-
-	if (!rp) {
-		DPU_ERROR("invalid resource pool\n");
-		return;
-	}
-
-	crtc = _dpu_crtc_rp_to_crtc(rp);
-	if (!crtc) {
-		DPU_ERROR("invalid crtc\n");
-		return;
-	}
-
-	mutex_lock(rp->rp_lock);
-	list_for_each_entry_safe(res, next, &rp->res_list, list) {
-		if (res->type != type || res->tag != tag)
-			continue;
-		DPU_DEBUG("crtc%d.%u found res:0x%x/0x%llx/%pK/%d\n",
-				crtc->base.id, rp->sequence_id,
-				res->type, res->tag, res->val,
-				atomic_read(&res->refcount));
-		if (res->flags & DPU_CRTC_RES_FLAG_FREE)
-			DPU_ERROR(
-				"crtc%d.%u already free res:0x%x/0x%llx/%pK/%d\n",
-					crtc->base.id, rp->sequence_id,
-					res->type, res->tag, res->val,
-					atomic_read(&res->refcount));
-		else if (atomic_dec_return(&res->refcount) == 0)
-			res->flags |= DPU_CRTC_RES_FLAG_FREE;
-
-		mutex_unlock(rp->rp_lock);
-		return;
-	}
-	DPU_ERROR("crtc%d.%u not found res:0x%x/0x%llx\n",
-			crtc->base.id, rp->sequence_id, type, tag);
-	mutex_unlock(rp->rp_lock);
-}
-
-int dpu_crtc_res_add(struct drm_crtc_state *state, u32 type, u64 tag,
-		void *val, struct dpu_crtc_res_ops *ops)
-{
-	struct dpu_crtc_respool *rp;
-
-	if (!state) {
-		DPU_ERROR("invalid parameters\n");
-		return -EINVAL;
-	}
-
-	rp = &to_dpu_crtc_state(state)->rp;
-	return _dpu_crtc_rp_add(rp, type, tag, val, ops);
-}
-
-void *dpu_crtc_res_get(struct drm_crtc_state *state, u32 type, u64 tag)
-{
-	struct dpu_crtc_respool *rp;
-	void *val;
-
-	if (!state) {
-		DPU_ERROR("invalid parameters\n");
-		return NULL;
-	}
-
-	rp = &to_dpu_crtc_state(state)->rp;
-	val = _dpu_crtc_rp_get(rp, type, tag);
-	if (IS_ERR(val)) {
-		DPU_ERROR("failed to get res type:0x%x:0x%llx\n",
-				type, tag);
-		return NULL;
-	}
-
-	return val;
-}
-
-void dpu_crtc_res_put(struct drm_crtc_state *state, u32 type, u64 tag)
-{
-	struct dpu_crtc_respool *rp;
-
-	if (!state) {
-		DPU_ERROR("invalid parameters\n");
-		return;
-	}
-
-	rp = &to_dpu_crtc_state(state)->rp;
-	_dpu_crtc_rp_put(rp, type, tag);
-}
-
 static void dpu_crtc_destroy(struct drm_crtc *crtc)
 {
 	struct dpu_crtc *dpu_crtc = to_dpu_crtc(crtc);
@@ -2364,97 +2081,6 @@ static const struct drm_crtc_helper_funcs dpu_crtc_helper_funcs = {
 	.atomic_flush = dpu_crtc_atomic_flush,
 };
 
-static void _dpu_crtc_event_cb(struct kthread_work *work)
-{
-	struct dpu_crtc_event *event;
-	struct dpu_crtc *dpu_crtc;
-	unsigned long irq_flags;
-
-	if (!work) {
-		DPU_ERROR("invalid work item\n");
-		return;
-	}
-
-	event = container_of(work, struct dpu_crtc_event, kt_work);
-
-	/* set dpu_crtc to NULL for static work structures */
-	dpu_crtc = event->dpu_crtc;
-	if (!dpu_crtc)
-		return;
-
-	if (event->cb_func)
-		event->cb_func(&dpu_crtc->base, event->usr);
-
-	spin_lock_irqsave(&dpu_crtc->event_lock, irq_flags);
-	list_add_tail(&event->list, &dpu_crtc->event_free_list);
-	spin_unlock_irqrestore(&dpu_crtc->event_lock, irq_flags);
-}
-
-int dpu_crtc_event_queue(struct drm_crtc *crtc,
-		void (*func)(struct drm_crtc *crtc, void *usr), void *usr)
-{
-	unsigned long irq_flags;
-	struct dpu_crtc *dpu_crtc;
-	struct msm_drm_private *priv;
-	struct dpu_crtc_event *event = NULL;
-	u32 crtc_id;
-
-	if (!crtc || !crtc->dev || !crtc->dev->dev_private || !func) {
-		DPU_ERROR("invalid parameters\n");
-		return -EINVAL;
-	}
-	dpu_crtc = to_dpu_crtc(crtc);
-	priv = crtc->dev->dev_private;
-	crtc_id = drm_crtc_index(crtc);
-
-	/*
-	 * Obtain an event struct from the private cache. This event
-	 * queue may be called from ISR contexts, so use a private
-	 * cache to avoid calling any memory allocation functions.
-	 */
-	spin_lock_irqsave(&dpu_crtc->event_lock, irq_flags);
-	if (!list_empty(&dpu_crtc->event_free_list)) {
-		event = list_first_entry(&dpu_crtc->event_free_list,
-				struct dpu_crtc_event, list);
-		list_del_init(&event->list);
-	}
-	spin_unlock_irqrestore(&dpu_crtc->event_lock, irq_flags);
-
-	if (!event)
-		return -ENOMEM;
-
-	/* populate event node */
-	event->dpu_crtc = dpu_crtc;
-	event->cb_func = func;
-	event->usr = usr;
-
-	/* queue new event request */
-	kthread_init_work(&event->kt_work, _dpu_crtc_event_cb);
-	kthread_queue_work(&priv->event_thread[crtc_id].worker,
-			&event->kt_work);
-
-	return 0;
-}
-
-static int _dpu_crtc_init_events(struct dpu_crtc *dpu_crtc)
-{
-	int i, rc = 0;
-
-	if (!dpu_crtc) {
-		DPU_ERROR("invalid crtc\n");
-		return -EINVAL;
-	}
-
-	spin_lock_init(&dpu_crtc->event_lock);
-
-	INIT_LIST_HEAD(&dpu_crtc->event_free_list);
-	for (i = 0; i < DPU_CRTC_MAX_EVENT_COUNT; ++i)
-		list_add_tail(&dpu_crtc->event_cache[i].list,
-				&dpu_crtc->event_free_list);
-
-	return rc;
-}
-
 /* initialize crtc */
 struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane)
 {
@@ -2462,7 +2088,7 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane)
 	struct dpu_crtc *dpu_crtc = NULL;
 	struct msm_drm_private *priv = NULL;
 	struct dpu_kms *kms = NULL;
-	int i, rc;
+	int i;
 
 	priv = dev->dev_private;
 	kms = to_dpu_kms(priv->kms);
@@ -2503,12 +2129,7 @@ struct drm_crtc *dpu_crtc_init(struct drm_device *dev, struct drm_plane *plane)
 	snprintf(dpu_crtc->name, DPU_CRTC_NAME_SIZE, "crtc%u", crtc->base.id);
 
 	/* initialize event handling */
-	rc = _dpu_crtc_init_events(dpu_crtc);
-	if (rc) {
-		drm_crtc_cleanup(crtc);
-		kfree(dpu_crtc);
-		return ERR_PTR(rc);
-	}
+	spin_lock_init(&dpu_crtc->event_lock);
 
 	dpu_crtc->phandle = &kms->phandle;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
index 4a97ba16735f..e87109e608e9 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.h
@@ -112,23 +112,6 @@ struct dpu_crtc_frame_event {
 	u32 event;
 };
 
-/**
- * struct dpu_crtc_event - event callback tracking structure
- * @list:     Linked list tracking node
- * @kt_work:  Kthread worker structure
- * @dpu_crtc: Pointer to associated dpu_crtc structure
- * @cb_func:  Pointer to callback function
- * @usr:      Pointer to user data to be provided to the callback
- */
-struct dpu_crtc_event {
-	struct list_head list;
-	struct kthread_work kt_work;
-	void *dpu_crtc;
-
-	void (*cb_func)(struct drm_crtc *crtc, void *usr);
-	void *usr;
-};
-
 /*
  * Maximum number of free event structures to cache
  */
@@ -172,8 +155,6 @@ struct dpu_crtc_event {
  * @frame_done_comp    : for frame_event_done synchronization
  * @event_thread  : Pointer to event handler thread
  * @event_worker  : Event worker queue
- * @event_cache   : Local cache of event worker structures
- * @event_free_list : List of available event structures
  * @event_lock    : Spinlock around event handling code
  * @misr_enable   : boolean entry indicates misr enable/disable status.
  * @misr_frame_count  : misr frame count provided by client
@@ -224,8 +205,6 @@ struct dpu_crtc {
 	struct completion frame_done_comp;
 
 	/* for handling internal event thread */
-	struct dpu_crtc_event event_cache[DPU_CRTC_MAX_EVENT_COUNT];
-	struct list_head event_free_list;
 	spinlock_t event_lock;
 	bool misr_enable;
 	u32 misr_frame_count;
@@ -441,44 +420,4 @@ static inline bool dpu_crtc_is_enabled(struct drm_crtc *crtc)
 	return crtc ? crtc->enabled : false;
 }
 
-/**
- * dpu_crtc_event_queue - request event callback
- * @crtc: Pointer to drm crtc structure
- * @func: Pointer to callback function
- * @usr: Pointer to user data to be passed to callback
- * Returns: Zero on success
- */
-int dpu_crtc_event_queue(struct drm_crtc *crtc,
-		void (*func)(struct drm_crtc *crtc, void *usr), void *usr);
-
-/**
- * dpu_crtc_res_add - add given resource to resource pool in crtc state
- * @state: Pointer to drm crtc state
- * @type: Resource type
- * @tag: Search tag for given resource
- * @val: Resource handle
- * @ops: Resource callback operations
- * return: 0 if success; error code otherwise
- */
-int dpu_crtc_res_add(struct drm_crtc_state *state, u32 type, u64 tag,
-		void *val, struct dpu_crtc_res_ops *ops);
-
-/**
- * dpu_crtc_res_get - get given resource from resource pool in crtc state
- * @state: Pointer to drm crtc state
- * @type: Resource type
- * @tag: Search tag for given resource
- * return: Resource handle if success; pointer error or null otherwise
- */
-void *dpu_crtc_res_get(struct drm_crtc_state *state, u32 type, u64 tag);
-
-/**
- * dpu_crtc_res_put - return given resource to resource pool in crtc state
- * @state: Pointer to drm crtc state
- * @type: Resource type
- * @tag: Search tag for given resource
- * return: None
- */
-void dpu_crtc_res_put(struct drm_crtc_state *state, u32 type, u64 tag);
-
 #endif /* _DPU_CRTC_H_ */
-- 
cgit v1.2.3


From d9c7440dad0d85b29325d89956411e2c57e7d17a Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Thu, 26 Jul 2018 14:30:12 -0600
Subject: drm/msm/disp/dpu: Remove dpu_kms_utils

None of the functions in dpu_kms_utils.c seem to be used so
remove them all.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/Makefile                  |   1 -
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h       | 112 -------------------
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c | 153 --------------------------
 3 files changed, 266 deletions(-)
 delete mode 100644 drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c

diff --git a/drivers/gpu/drm/msm/Makefile b/drivers/gpu/drm/msm/Makefile
index 1639ea8c0d13..7c773e003663 100644
--- a/drivers/gpu/drm/msm/Makefile
+++ b/drivers/gpu/drm/msm/Makefile
@@ -68,7 +68,6 @@ msm-y := \
 	disp/dpu1/dpu_io_util.o \
 	disp/dpu1/dpu_irq.o \
 	disp/dpu1/dpu_kms.o \
-	disp/dpu1/dpu_kms_utils.o \
 	disp/dpu1/dpu_mdss.o \
 	disp/dpu1/dpu_plane.o \
 	disp/dpu1/dpu_power_handle.o \
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index 407c1ed27fe6..66d466628e2b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -270,118 +270,6 @@ void *dpu_debugfs_get_root(struct dpu_kms *dpu_kms);
  */
 #define DPU_KMS_INFO_MAX_SIZE	4096
 
-/**
- * struct dpu_kms_info - connector information structure container
- * @data: Array of information character data
- * @len: Current length of information data
- * @staged_len: Temporary data buffer length, commit to
- *              len using dpu_kms_info_stop
- * @start: Whether or not a partial data entry was just started
- */
-struct dpu_kms_info {
-	char data[DPU_KMS_INFO_MAX_SIZE];
-	uint32_t len;
-	uint32_t staged_len;
-	bool start;
-};
-
-/**
- * DPU_KMS_INFO_DATA - Macro for accessing dpu_kms_info data bytes
- * @S: Pointer to dpu_kms_info structure
- * Returns: Pointer to byte data
- */
-#define DPU_KMS_INFO_DATA(S)    ((S) ? ((struct dpu_kms_info *)(S))->data : 0)
-
-/**
- * DPU_KMS_INFO_DATALEN - Macro for accessing dpu_kms_info data length
- *			it adds an extra character length to count null.
- * @S: Pointer to dpu_kms_info structure
- * Returns: Size of available byte data
- */
-#define DPU_KMS_INFO_DATALEN(S) ((S) ? ((struct dpu_kms_info *)(S))->len + 1 \
-							: 0)
-
-/**
- * dpu_kms_info_reset - reset dpu_kms_info structure
- * @info: Pointer to dpu_kms_info structure
- */
-void dpu_kms_info_reset(struct dpu_kms_info *info);
-
-/**
- * dpu_kms_info_add_keyint - add integer value to 'dpu_kms_info'
- * @info: Pointer to dpu_kms_info structure
- * @key: Pointer to key string
- * @value: Signed 64-bit integer value
- */
-void dpu_kms_info_add_keyint(struct dpu_kms_info *info,
-		const char *key,
-		int64_t value);
-
-/**
- * dpu_kms_info_add_keystr - add string value to 'dpu_kms_info'
- * @info: Pointer to dpu_kms_info structure
- * @key: Pointer to key string
- * @value: Pointer to string value
- */
-void dpu_kms_info_add_keystr(struct dpu_kms_info *info,
-		const char *key,
-		const char *value);
-
-/**
- * dpu_kms_info_start - begin adding key to 'dpu_kms_info'
- * Usage:
- *      dpu_kms_info_start(key)
- *      dpu_kms_info_append(val_1)
- *      ...
- *      dpu_kms_info_append(val_n)
- *      dpu_kms_info_stop
- * @info: Pointer to dpu_kms_info structure
- * @key: Pointer to key string
- */
-void dpu_kms_info_start(struct dpu_kms_info *info,
-		const char *key);
-
-/**
- * dpu_kms_info_append - append value string to 'dpu_kms_info'
- * Usage:
- *      dpu_kms_info_start(key)
- *      dpu_kms_info_append(val_1)
- *      ...
- *      dpu_kms_info_append(val_n)
- *      dpu_kms_info_stop
- * @info: Pointer to dpu_kms_info structure
- * @str: Pointer to partial value string
- */
-void dpu_kms_info_append(struct dpu_kms_info *info,
-		const char *str);
-
-/**
- * dpu_kms_info_append_format - append format code string to 'dpu_kms_info'
- * Usage:
- *      dpu_kms_info_start(key)
- *      dpu_kms_info_append_format(fourcc, modifier)
- *      ...
- *      dpu_kms_info_stop
- * @info: Pointer to dpu_kms_info structure
- * @pixel_format: FOURCC format code
- * @modifier: 64-bit drm format modifier
- */
-void dpu_kms_info_append_format(struct dpu_kms_info *info,
-		uint32_t pixel_format,
-		uint64_t modifier);
-
-/**
- * dpu_kms_info_stop - finish adding key to 'dpu_kms_info'
- * Usage:
- *      dpu_kms_info_start(key)
- *      dpu_kms_info_append(val_1)
- *      ...
- *      dpu_kms_info_append(val_n)
- *      dpu_kms_info_stop
- * @info: Pointer to dpu_kms_info structure
- */
-void dpu_kms_info_stop(struct dpu_kms_info *info);
-
 /**
  * Vblank enable/disable functions
  */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c
deleted file mode 100644
index a80b3da5a9fe..000000000000
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms_utils.c
+++ /dev/null
@@ -1,153 +0,0 @@
-/* Copyright (c) 2015-2018, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-
-#define pr_fmt(fmt)	"dpu-kms_utils:[%s] " fmt, __func__
-
-#include "dpu_kms.h"
-
-void dpu_kms_info_reset(struct dpu_kms_info *info)
-{
-	if (info) {
-		info->len = 0;
-		info->staged_len = 0;
-	}
-}
-
-void dpu_kms_info_add_keyint(struct dpu_kms_info *info,
-		const char *key,
-		int64_t value)
-{
-	uint32_t len;
-
-	if (info && key) {
-		len = snprintf(info->data + info->len,
-				DPU_KMS_INFO_MAX_SIZE - info->len,
-				"%s=%lld\n",
-				key,
-				value);
-
-		/* check if snprintf truncated the string */
-		if ((info->len + len) < DPU_KMS_INFO_MAX_SIZE)
-			info->len += len;
-	}
-}
-
-void dpu_kms_info_add_keystr(struct dpu_kms_info *info,
-		const char *key,
-		const char *value)
-{
-	uint32_t len;
-
-	if (info && key && value) {
-		len = snprintf(info->data + info->len,
-				DPU_KMS_INFO_MAX_SIZE - info->len,
-				"%s=%s\n",
-				key,
-				value);
-
-		/* check if snprintf truncated the string */
-		if ((info->len + len) < DPU_KMS_INFO_MAX_SIZE)
-			info->len += len;
-	}
-}
-
-void dpu_kms_info_start(struct dpu_kms_info *info,
-		const char *key)
-{
-	uint32_t len;
-
-	if (info && key) {
-		len = snprintf(info->data + info->len,
-				DPU_KMS_INFO_MAX_SIZE - info->len,
-				"%s=",
-				key);
-
-		info->start = true;
-
-		/* check if snprintf truncated the string */
-		if ((info->len + len) < DPU_KMS_INFO_MAX_SIZE)
-			info->staged_len = info->len + len;
-	}
-}
-
-void dpu_kms_info_append(struct dpu_kms_info *info,
-		const char *str)
-{
-	uint32_t len;
-
-	if (info) {
-		len = snprintf(info->data + info->staged_len,
-				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
-				"%s",
-				str);
-
-		/* check if snprintf truncated the string */
-		if ((info->staged_len + len) < DPU_KMS_INFO_MAX_SIZE) {
-			info->staged_len += len;
-			info->start = false;
-		}
-	}
-}
-
-void dpu_kms_info_append_format(struct dpu_kms_info *info,
-		uint32_t pixel_format,
-		uint64_t modifier)
-{
-	uint32_t len;
-
-	if (!info)
-		return;
-
-	if (modifier) {
-		len = snprintf(info->data + info->staged_len,
-				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
-				info->start ?
-				"%c%c%c%c/%llX/%llX" : " %c%c%c%c/%llX/%llX",
-				(pixel_format >> 0) & 0xFF,
-				(pixel_format >> 8) & 0xFF,
-				(pixel_format >> 16) & 0xFF,
-				(pixel_format >> 24) & 0xFF,
-				(modifier >> 56) & 0xFF,
-				modifier & ((1ULL << 56) - 1));
-	} else {
-		len = snprintf(info->data + info->staged_len,
-				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
-				info->start ?
-				"%c%c%c%c" : " %c%c%c%c",
-				(pixel_format >> 0) & 0xFF,
-				(pixel_format >> 8) & 0xFF,
-				(pixel_format >> 16) & 0xFF,
-				(pixel_format >> 24) & 0xFF);
-	}
-
-	/* check if snprintf truncated the string */
-	if ((info->staged_len + len) < DPU_KMS_INFO_MAX_SIZE) {
-		info->staged_len += len;
-		info->start = false;
-	}
-}
-
-void dpu_kms_info_stop(struct dpu_kms_info *info)
-{
-	uint32_t len;
-
-	if (info) {
-		/* insert final delimiter */
-		len = snprintf(info->data + info->staged_len,
-				DPU_KMS_INFO_MAX_SIZE - info->staged_len,
-				"\n");
-
-		/* check if snprintf truncated the string */
-		if ((info->staged_len + len) < DPU_KMS_INFO_MAX_SIZE)
-			info->len = info->staged_len + len;
-	}
-}
-- 
cgit v1.2.3


From f2c9a924c1acf42f692f2b5ac77531eea69460a3 Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Thu, 26 Jul 2018 14:30:13 -0600
Subject: drm/msm/disp/dpu: Remove unused functions from dpu_formats.c

Remove dpu_format_get_block_size, dpu_format_get_framebuffer_size,
dpu_set_scaler_v2 and dpu_copy_formats they are unused and unneeded.

Signed-off-by: Jordan Crouse <jcrouse@codeauorora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c | 41 --------------
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h | 31 -----------
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c | 84 -----------------------------
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h | 10 ----
 4 files changed, 166 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 8189539b0620..0cb00612f96f 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -869,47 +869,6 @@ int dpu_format_get_plane_sizes(
 	return _dpu_format_get_plane_sizes_linear(fmt, w, h, layout, pitches);
 }
 
-int dpu_format_get_block_size(const struct dpu_format *fmt,
-		uint32_t *w, uint32_t *h)
-{
-	if (!fmt || !w || !h) {
-		DRM_ERROR("invalid pointer\n");
-		return -EINVAL;
-	}
-
-	/* TP10 is 96x96 and all others are 128x128 */
-	if (DPU_FORMAT_IS_YUV(fmt) && DPU_FORMAT_IS_DX(fmt) &&
-			(fmt->num_planes == 2) && fmt->unpack_tight)
-		*w = *h = 96;
-	else
-		*w = *h = 128;
-
-	return 0;
-}
-
-uint32_t dpu_format_get_framebuffer_size(
-		const uint32_t format,
-		const uint32_t width,
-		const uint32_t height,
-		const uint32_t *pitches,
-		const uint64_t modifiers)
-{
-	const struct dpu_format *fmt;
-	struct dpu_hw_fmt_layout layout;
-
-	fmt = dpu_get_dpu_format_ext(format, modifiers);
-	if (!fmt)
-		return 0;
-
-	if (!pitches)
-		return -EINVAL;
-
-	if (dpu_format_get_plane_sizes(fmt, width, height, &layout, pitches))
-		layout.total_size = 0;
-
-	return layout.total_size;
-}
-
 static int _dpu_format_populate_addrs_ubwc(
 		struct msm_gem_address_space *aspace,
 		struct drm_framebuffer *fb,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
index b55bfd13e296..b3a6592f1a8a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
@@ -72,19 +72,6 @@ int dpu_format_get_plane_sizes(
 		struct dpu_hw_fmt_layout *layout,
 		const uint32_t *pitches);
 
-/**
- * dpu_format_get_block_size - get block size of given format when
- *	operating in block mode
- * @fmt:             pointer to dpu_format
- * @w:               pointer to width of the block
- * @h:               pointer to height of the block
- *
- * Return: 0 if success; error oode otherwise
- */
-int dpu_format_get_block_size(const struct dpu_format *fmt,
-		uint32_t *w, uint32_t *h);
-
-/**
  * dpu_format_check_modified_format - validate format and buffers for
  *                   dpu non-standard, i.e. modified format
  * @kms:             kms driver
@@ -115,22 +102,4 @@ int dpu_format_populate_layout(
 		struct drm_framebuffer *fb,
 		struct dpu_hw_fmt_layout *fmtl);
 
-/**
- * dpu_format_get_framebuffer_size - get framebuffer memory size
- * @format:            DRM pixel format
- * @width:             pixel width
- * @height:            pixel height
- * @pitches:           array of size [DPU_MAX_PLANES] to populate
- *		       pitch for each plane
- * @modifiers:         drm modifier
- *
- * Return: memory size required for frame buffer
- */
-uint32_t dpu_format_get_framebuffer_size(
-		const uint32_t format,
-		const uint32_t width,
-		const uint32_t height,
-		const uint32_t *pitches,
-		const uint64_t modifiers);
-
 #endif /*_DPU_FORMATS_H */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
index 1ba571e94b32..4cabae480a7b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.c
@@ -92,59 +92,6 @@ u32 *dpu_hw_util_get_log_mask_ptr(void)
 	return &dpu_hw_util_log_mask;
 }
 
-void dpu_set_scaler_v2(struct dpu_hw_scaler3_cfg *cfg,
-		const struct dpu_drm_scaler_v2 *scale_v2)
-{
-	int i;
-
-	cfg->enable = scale_v2->enable;
-	cfg->dir_en = scale_v2->dir_en;
-
-	for (i = 0; i < DPU_MAX_PLANES; i++) {
-		cfg->init_phase_x[i] = scale_v2->init_phase_x[i];
-		cfg->phase_step_x[i] = scale_v2->phase_step_x[i];
-		cfg->init_phase_y[i] = scale_v2->init_phase_y[i];
-		cfg->phase_step_y[i] = scale_v2->phase_step_y[i];
-
-		cfg->preload_x[i] = scale_v2->preload_x[i];
-		cfg->preload_y[i] = scale_v2->preload_y[i];
-		cfg->src_width[i] = scale_v2->src_width[i];
-		cfg->src_height[i] = scale_v2->src_height[i];
-	}
-
-	cfg->dst_width = scale_v2->dst_width;
-	cfg->dst_height = scale_v2->dst_height;
-
-	cfg->y_rgb_filter_cfg = scale_v2->y_rgb_filter_cfg;
-	cfg->uv_filter_cfg = scale_v2->uv_filter_cfg;
-	cfg->alpha_filter_cfg = scale_v2->alpha_filter_cfg;
-	cfg->blend_cfg = scale_v2->blend_cfg;
-
-	cfg->lut_flag = scale_v2->lut_flag;
-	cfg->dir_lut_idx = scale_v2->dir_lut_idx;
-	cfg->y_rgb_cir_lut_idx = scale_v2->y_rgb_cir_lut_idx;
-	cfg->uv_cir_lut_idx = scale_v2->uv_cir_lut_idx;
-	cfg->y_rgb_sep_lut_idx = scale_v2->y_rgb_sep_lut_idx;
-	cfg->uv_sep_lut_idx = scale_v2->uv_sep_lut_idx;
-
-	cfg->de.enable = scale_v2->de.enable;
-	cfg->de.sharpen_level1 = scale_v2->de.sharpen_level1;
-	cfg->de.sharpen_level2 = scale_v2->de.sharpen_level2;
-	cfg->de.clip = scale_v2->de.clip;
-	cfg->de.limit = scale_v2->de.limit;
-	cfg->de.thr_quiet = scale_v2->de.thr_quiet;
-	cfg->de.thr_dieout = scale_v2->de.thr_dieout;
-	cfg->de.thr_low = scale_v2->de.thr_low;
-	cfg->de.thr_high = scale_v2->de.thr_high;
-	cfg->de.prec_shift = scale_v2->de.prec_shift;
-
-	for (i = 0; i < DPU_MAX_DE_CURVES; i++) {
-		cfg->de.adjust_a[i] = scale_v2->de.adjust_a[i];
-		cfg->de.adjust_b[i] = scale_v2->de.adjust_b[i];
-		cfg->de.adjust_c[i] = scale_v2->de.adjust_c[i];
-	}
-}
-
 static void _dpu_hw_setup_scaler3_lut(struct dpu_hw_blk_reg_map *c,
 		struct dpu_hw_scaler3_cfg *scaler3_cfg, u32 offset)
 {
@@ -419,34 +366,3 @@ void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map *c,
 	DPU_REG_WRITE(c, csc_reg_off + 0x3c, data->csc_post_bv[1]);
 	DPU_REG_WRITE(c, csc_reg_off + 0x40, data->csc_post_bv[2]);
 }
-
-/**
- * _dpu_copy_formats   - copy formats from src_list to dst_list
- * @dst_list:          pointer to destination list where to copy formats
- * @dst_list_size:     size of destination list
- * @dst_list_pos:      starting position on the list where to copy formats
- * @src_list:          pointer to source list where to copy formats from
- * @src_list_size:     size of source list
- * Return: number of elements populated
- */
-uint32_t dpu_copy_formats(
-		struct dpu_format_extended *dst_list,
-		uint32_t dst_list_size,
-		uint32_t dst_list_pos,
-		const struct dpu_format_extended *src_list,
-		uint32_t src_list_size)
-{
-	uint32_t cur_pos, i;
-
-	if (!dst_list || !src_list || (dst_list_pos >= (dst_list_size - 1)))
-		return 0;
-
-	for (i = 0, cur_pos = dst_list_pos;
-		(cur_pos < (dst_list_size - 1)) && (i < src_list_size)
-		&& src_list[i].fourcc_format; ++i, ++cur_pos)
-		dst_list[cur_pos] = src_list[i];
-
-	dst_list[cur_pos].fourcc_format = 0;
-
-	return i;
-}
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
index 42f1b228d342..1240f505ca53 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_util.h
@@ -333,9 +333,6 @@ int dpu_reg_read(struct dpu_hw_blk_reg_map *c, u32 reg_off);
 
 void *dpu_hw_util_get_dir(void);
 
-void dpu_set_scaler_v2(struct dpu_hw_scaler3_cfg *cfg,
-		const struct dpu_drm_scaler_v2 *scale_v2);
-
 void dpu_hw_setup_scaler3(struct dpu_hw_blk_reg_map *c,
 		struct dpu_hw_scaler3_cfg *scaler3_cfg,
 		u32 scaler_offset, u32 scaler_version,
@@ -348,11 +345,4 @@ void dpu_hw_csc_setup(struct dpu_hw_blk_reg_map  *c,
 		u32 csc_reg_off,
 		struct dpu_csc_cfg *data, bool csc10);
 
-uint32_t dpu_copy_formats(
-		struct dpu_format_extended *dst_list,
-		uint32_t dst_list_size,
-		uint32_t dst_list_pos,
-		const struct dpu_format_extended *src_list,
-		uint32_t src_list_size);
-
 #endif /* _DPU_HW_UTIL_H */
-- 
cgit v1.2.3


From fba33cae6aa3eaa3627a603d62d4652f12308b8d Mon Sep 17 00:00:00 2001
From: Jordan Crouse <jcrouse@codeaurora.org>
Date: Thu, 26 Jul 2018 14:30:14 -0600
Subject: drm/msm/disp/dpu: Mark a handful of functions as static

Mark a number of static functions that are only unsed in the file
that defines them and remove the prototypes from the headers where
needed.

Signed-off-by: Jordan Crouse <jcrouse@codeaurora.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c          |  7 +++++--
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h          |  6 ------
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h     | 14 --------------
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c |  2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c          |  2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h          | 17 -----------------
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c       |  2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c           |  4 ++--
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c           |  2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c              |  2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c             |  2 +-
 11 files changed, 13 insertions(+), 47 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 5c0051af5e98..0bd3eda93e22 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -264,6 +264,9 @@ void dpu_encoder_helper_report_irq_timeout(struct dpu_encoder_phys *phys_enc,
 				DPU_ENCODER_FRAME_EVENT_ERROR);
 }
 
+static int dpu_encoder_helper_wait_event_timeout(int32_t drm_id,
+		int32_t hw_id, struct dpu_encoder_wait_info *info);
+
 int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
 		enum dpu_intr_idx intr_idx,
 		struct dpu_encoder_wait_info *wait_info)
@@ -467,7 +470,7 @@ void dpu_encoder_get_hw_resources(struct drm_encoder *drm_enc,
 	}
 }
 
-void dpu_encoder_destroy(struct drm_encoder *drm_enc)
+static void dpu_encoder_destroy(struct drm_encoder *drm_enc)
 {
 	struct dpu_encoder_virt *dpu_enc = NULL;
 	int i = 0;
@@ -1516,7 +1519,7 @@ void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc)
 	}
 }
 
-int dpu_encoder_helper_wait_event_timeout(
+static int dpu_encoder_helper_wait_event_timeout(
 		int32_t drm_id,
 		int32_t hw_id,
 		struct dpu_encoder_wait_info *info)
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
index 204e538b0b74..60f809fc7c13 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.h
@@ -158,12 +158,6 @@ struct drm_encoder *dpu_encoder_init(
 int dpu_encoder_setup(struct drm_device *dev, struct drm_encoder *enc,
 		struct msm_display_info *disp_info);
 
-/**
- * dpu_encoder_destroy - destroy previously initialized virtual encoder
- * @drm_enc:    Pointer to previously created drm encoder structure
- */
-void dpu_encoder_destroy(struct drm_encoder *drm_enc);
-
 /**
  * dpu_encoder_prepare_commit - prepare encoder at the very beginning of an
  *	atomic commit, before any registers are written
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
index dacec1c8eeeb..c7df8aad6613 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
@@ -355,20 +355,6 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(
  */
 void dpu_encoder_helper_trigger_start(struct dpu_encoder_phys *phys_enc);
 
-/**
- * dpu_encoder_helper_wait_event_timeout - wait for event with timeout
- *	taking into account that jiffies may jump between reads leading to
- *	incorrectly detected timeouts. Prevent failure in this scenario by
- *	making sure that elapsed time during wait is valid.
- * @drm_id: drm object id for logging
- * @hw_id: hw instance id for logging
- * @info: wait info structure
- */
-int dpu_encoder_helper_wait_event_timeout(
-		int32_t drm_id,
-		int32_t hw_id,
-		struct dpu_encoder_wait_info *info);
-
 /**
  * dpu_encoder_helper_hw_reset - issue ctl hw reset
  *	This helper function may be optionally specified by physical
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
index e6d02c6947b4..3084675ed425 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
@@ -349,7 +349,7 @@ end:
 	return ret;
 }
 
-void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
+static void dpu_encoder_phys_cmd_irq_control(struct dpu_encoder_phys *phys_enc,
 		bool enable)
 {
 	struct dpu_encoder_phys_cmd *cmd_enc;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
index 0cb00612f96f..bfcd165e96df 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.c
@@ -846,7 +846,7 @@ static int _dpu_format_get_plane_sizes_linear(
 	return 0;
 }
 
-int dpu_format_get_plane_sizes(
+static int dpu_format_get_plane_sizes(
 		const struct dpu_format *fmt,
 		const uint32_t w,
 		const uint32_t h,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
index b3a6592f1a8a..a54451d8d011 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_formats.h
@@ -55,23 +55,6 @@ uint32_t dpu_populate_formats(
 		uint32_t pixel_formats_max);
 
 /**
- * dpu_format_get_plane_sizes - calculate size and layout of given buffer format
- * @fmt:             pointer to dpu_format
- * @w:               width of the buffer
- * @h:               height of the buffer
- * @layout:          layout of the buffer
- * @pitches:         array of size [DPU_MAX_PLANES] to populate
- *		     pitch for each plane
- *
- * Return: size of the buffer
- */
-int dpu_format_get_plane_sizes(
-		const struct dpu_format *fmt,
-		const uint32_t w,
-		const uint32_t h,
-		struct dpu_hw_fmt_layout *layout,
-		const uint32_t *pitches);
-
  * dpu_format_check_modified_format - validate format and buffers for
  *                   dpu non-standard, i.e. modified format
  * @kms:             kms driver
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
index 1793cfd29a07..44ee06398b1d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
@@ -449,7 +449,7 @@ static struct dpu_perf_cfg sdm845_perf_data = {
  * sdm845_cfg_init(): populate sdm845 dpu sub-blocks reg offsets
  * and instance counts.
  */
-void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
+static void sdm845_cfg_init(struct dpu_mdss_cfg *dpu_cfg)
 {
 	*dpu_cfg = (struct dpu_mdss_cfg){
 		.caps = &sdm845_dpu_caps,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
index da6f0609be5f..554874ba0c3b 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_cdm.c
@@ -217,7 +217,7 @@ static int dpu_hw_cdm_setup_cdwn(struct dpu_hw_cdm *ctx,
 	return 0;
 }
 
-int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx,
+static int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx,
 		struct dpu_hw_cdm_cfg *cdm)
 {
 	struct dpu_hw_blk_reg_map *c = &ctx->hw;
@@ -249,7 +249,7 @@ int dpu_hw_cdm_enable(struct dpu_hw_cdm *ctx,
 	return 0;
 }
 
-void dpu_hw_cdm_disable(struct dpu_hw_cdm *ctx)
+static void dpu_hw_cdm_disable(struct dpu_hw_cdm *ctx)
 {
 	struct cdm_output_cfg cdm_cfg = { 0 };
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
index 42fc72cf48dd..db2798e862fc 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -275,7 +275,7 @@ static void dpu_hw_get_safe_status(struct dpu_hw_mdp *mdp,
 	status->sspp[SSPP_CURSOR1] = (value >> 26) & 0x1;
 }
 
-void dpu_hw_reset_ubwc(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m)
+static void dpu_hw_reset_ubwc(struct dpu_hw_mdp *mdp, struct dpu_mdss_cfg *m)
 {
 	struct dpu_hw_blk_reg_map c;
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index 1c0838801e78..7dd6bd2d6d37 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -819,7 +819,7 @@ static int dpu_kms_pm_resume(struct device *dev)
 	return 0;
 }
 
-void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
+static void _dpu_kms_set_encoder_mode(struct msm_kms *kms,
 				 struct drm_encoder *encoder,
 				 bool cmd_mode)
 {
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
index 6dfc26698a09..9e533b86682c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_mdss.c
@@ -115,7 +115,7 @@ static int _dpu_mdss_irq_domain_add(struct dpu_mdss *dpu_mdss)
 	return 0;
 }
 
-int _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss)
+static int _dpu_mdss_irq_domain_fini(struct dpu_mdss *dpu_mdss)
 {
 	if (dpu_mdss->irq_controller.domain) {
 		irq_domain_remove(dpu_mdss->irq_controller.domain);
-- 
cgit v1.2.3


From 6b0a180ede4884ea5cdd30ca939ddf43ef11cdac Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Fri, 20 Jul 2018 16:42:52 -0400
Subject: dt-bindings: msm/dsi: Add mdp transfer time to msm dsi binding

Adds mdp transfer time to msm dsi binding

Changes in v3:
- Added Rob's R-b

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
Signed-off-by: Rajesh Yadav <ryadav@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 Documentation/devicetree/bindings/display/msm/dsi.txt | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/Documentation/devicetree/bindings/display/msm/dsi.txt b/Documentation/devicetree/bindings/display/msm/dsi.txt
index 518e9cdf0d4b..d22237a88eae 100644
--- a/Documentation/devicetree/bindings/display/msm/dsi.txt
+++ b/Documentation/devicetree/bindings/display/msm/dsi.txt
@@ -121,6 +121,20 @@ Required properties:
 Optional properties:
 - qcom,dsi-phy-regulator-ldo-mode: Boolean value indicating if the LDO mode PHY
   regulator is wanted.
+- qcom,mdss-mdp-transfer-time-us:	Specifies the dsi transfer time for command mode
+					panels in microseconds. Driver uses this number to adjust
+					the clock rate according to the expected transfer time.
+					Increasing this value would slow down the mdp processing
+					and can result in slower performance.
+					Decreasing this value can speed up the mdp processing,
+					but this can also impact power consumption.
+					As a rule this time should not be higher than the time
+					that would be expected with the processing at the
+					dsi link rate since anyways this would be the maximum
+					transfer time that could be achieved.
+					If ping pong split is enabled, this time should not be higher
+					than two times the dsi link rate time.
+					If the property is not specified, then the default value is 14000 us.
 
 [1] Documentation/devicetree/bindings/clock/clock-bindings.txt
 [2] Documentation/devicetree/bindings/graph.txt
@@ -171,6 +185,8 @@ Example:
 		qcom,master-dsi;
 		qcom,sync-dual-dsi;
 
+		qcom,mdss-mdp-transfer-time-us = <12000>;
+
 		pinctrl-names = "default", "sleep";
 		pinctrl-0 = <&dsi_active>;
 		pinctrl-1 = <&dsi_suspend>;
-- 
cgit v1.2.3


From a7663a79343658f9362dc0655f1a06723c7014e3 Mon Sep 17 00:00:00 2001
From: Jeykumar Sankaran <jsanka@codeaurora.org>
Date: Fri, 20 Jul 2018 16:43:09 -0400
Subject: dt-bindings: msm/disp: Add bindings for Snapdragon 845 DPU

Adds bindings for Snapdragon 845 display processing unit

Changes in v2:
- Use SoC specific compatibles for mdss and dpu (Rob Herring)
- Use assigned-clocks to set initial clock frequency (Rob Herring)

Changes in v3 (all suggested by Rob Herring):
- Rename mdss_phys to mdss
- Correct description for clocks/assigned-clocks
- Rename mdp_phys to mdp
- Rename vbif_phys to vbif
- Remove redundant interrupt-parent from mdss_mdp
- Fully specify 'ranges' and use relative reg address in mdss_mdp

Cc: Rob Herring <robh+dt@kernel.org>
Signed-off-by: Jeykumar Sankaran <jsanka@codeaurora.org>
Signed-off-by: Rajesh Yadav <ryadav@codeaurora.org>
Signed-off-by: Sean Paul <seanpaul@chromium.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rob Clark <robdclark@gmail.com>
---
 .../devicetree/bindings/display/msm/dpu.txt        | 131 +++++++++++++++++++++
 1 file changed, 131 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/display/msm/dpu.txt

diff --git a/Documentation/devicetree/bindings/display/msm/dpu.txt b/Documentation/devicetree/bindings/display/msm/dpu.txt
new file mode 100644
index 000000000000..ad2e8830324e
--- /dev/null
+++ b/Documentation/devicetree/bindings/display/msm/dpu.txt
@@ -0,0 +1,131 @@
+Qualcomm Technologies, Inc. DPU KMS
+
+Description:
+
+Device tree bindings for MSM Mobile Display Subsytem(MDSS) that encapsulates
+sub-blocks like DPU display controller, DSI and DP interfaces etc.
+The DPU display controller is found in SDM845 SoC.
+
+MDSS:
+Required properties:
+- compatible: "qcom,sdm845-mdss"
+- reg: physical base address and length of contoller's registers.
+- reg-names: register region names. The following region is required:
+  * "mdss"
+- power-domains: a power domain consumer specifier according to
+  Documentation/devicetree/bindings/power/power_domain.txt
+- clocks: list of clock specifiers for clocks needed by the device.
+- clock-names: device clock names, must be in same order as clocks property.
+  The following clocks are required:
+  * "iface"
+  * "bus"
+  * "core"
+- interrupts: interrupt signal from MDSS.
+- interrupt-controller: identifies the node as an interrupt controller.
+- #interrupt-cells: specifies the number of cells needed to encode an interrupt
+  source, should be 1.
+- iommus: phandle of iommu device node.
+- #address-cells: number of address cells for the MDSS children. Should be 1.
+- #size-cells: Should be 1.
+- ranges: parent bus address space is the same as the child bus address space.
+
+Optional properties:
+- assigned-clocks: list of clock specifiers for clocks needing rate assignment
+- assigned-clock-rates: list of clock frequencies sorted in the same order as
+  the assigned-clocks property.
+
+MDP:
+Required properties:
+- compatible: "qcom,sdm845-dpu"
+- reg: physical base address and length of controller's registers.
+- reg-names : register region names. The following region is required:
+  * "mdp"
+  * "vbif"
+- clocks: list of clock specifiers for clocks needed by the device.
+- clock-names: device clock names, must be in same order as clocks property.
+  The following clocks are required.
+  * "bus"
+  * "iface"
+  * "core"
+  * "vsync"
+- interrupts: interrupt line from DPU to MDSS.
+- ports: contains the list of output ports from DPU device. These ports connect
+  to interfaces that are external to the DPU hardware, such as DSI, DP etc.
+
+  Each output port contains an endpoint that describes how it is connected to an
+  external interface. These are described by the standard properties documented
+  here:
+	Documentation/devicetree/bindings/graph.txt
+	Documentation/devicetree/bindings/media/video-interfaces.txt
+
+	Port 0 -> DPU_INTF1 (DSI1)
+	Port 1 -> DPU_INTF2 (DSI2)
+
+Optional properties:
+- assigned-clocks: list of clock specifiers for clocks needing rate assignment
+- assigned-clock-rates: list of clock frequencies sorted in the same order as
+  the assigned-clocks property.
+
+Example:
+
+	mdss: mdss@ae00000 {
+		compatible = "qcom,sdm845-mdss";
+		reg = <0xae00000 0x1000>;
+		reg-names = "mdss";
+
+		power-domains = <&clock_dispcc 0>;
+
+		clocks = <&gcc GCC_DISP_AHB_CLK>, <&gcc GCC_DISP_AXI_CLK>,
+			 <&clock_dispcc DISP_CC_MDSS_MDP_CLK>;
+		clock-names = "iface", "bus", "core";
+
+		assigned-clocks = <&clock_dispcc DISP_CC_MDSS_MDP_CLK>;
+		assigned-clock-rates = <300000000>;
+
+		interrupts = <GIC_SPI 83 IRQ_TYPE_LEVEL_HIGH>;
+		interrupt-controller;
+		#interrupt-cells = <1>;
+
+		iommus = <&apps_iommu 0>;
+
+		#address-cells = <2>;
+		#size-cells = <1>;
+		ranges = <0 0 0xae00000 0xb2008>;
+
+		mdss_mdp: mdp@ae01000 {
+			compatible = "qcom,sdm845-dpu";
+			reg = <0 0x1000 0x8f000>, <0 0xb0000 0x2008>;
+			reg-names = "mdp", "vbif";
+
+			clocks = <&clock_dispcc DISP_CC_MDSS_AHB_CLK>,
+				 <&clock_dispcc DISP_CC_MDSS_AXI_CLK>,
+				 <&clock_dispcc DISP_CC_MDSS_MDP_CLK>,
+				 <&clock_dispcc DISP_CC_MDSS_VSYNC_CLK>;
+			clock-names = "iface", "bus", "core", "vsync";
+
+			assigned-clocks = <&clock_dispcc DISP_CC_MDSS_MDP_CLK>,
+					  <&clock_dispcc DISP_CC_MDSS_VSYNC_CLK>;
+			assigned-clock-rates = <0 0 300000000 19200000>;
+
+			interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+
+			ports {
+				#address-cells = <1>;
+				#size-cells = <0>;
+
+				port@0 {
+					reg = <0>;
+					dpu_intf1_out: endpoint {
+						remote-endpoint = <&dsi0_in>;
+					};
+				};
+
+				port@1 {
+					reg = <1>;
+					dpu_intf2_out: endpoint {
+						remote-endpoint = <&dsi1_in>;
+					};
+				};
+			};
+		};
+	};
-- 
cgit v1.2.3


From b30cc07de8a903685441f9770b1b21e1422d2468 Mon Sep 17 00:00:00 2001
From: Akihiro Tsukada <tskd08@gmail.com>
Date: Sun, 10 Jun 2018 10:45:31 -0400
Subject: media: dvb-usb/friio, dvb-usb-v2/gl861: decompose friio and merge
 with gl861

Friio device contains "gl861" bridge and "tc90522" demod,
for which the separate drivers are already in the kernel.
But friio driver was monolithic and did not use them,
practically copying those features.
This patch decomposes friio driver into sub drivers and
re-uses existing ones, thus reduces some code.

It adds some features to gl861,
to support the friio-specific init/config of the devices
and implement i2c communications to the tuner via demod
with USB vendor requests.

[mchehab+samsung@kernel.org: fix merge conflicts]
Signed-off-by: Akihiro Tsukada <tskd08@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb-v2/Kconfig |   5 +-
 drivers/media/usb/dvb-usb-v2/gl861.c | 471 +++++++++++++++++++++++++++++++++++
 drivers/media/usb/dvb-usb-v2/gl861.h |   1 +
 drivers/media/usb/dvb-usb/Kconfig    |   6 -
 drivers/media/usb/dvb-usb/Makefile   |   3 -
 5 files changed, 476 insertions(+), 10 deletions(-)

diff --git a/drivers/media/usb/dvb-usb-v2/Kconfig b/drivers/media/usb/dvb-usb-v2/Kconfig
index 082b8d67244b..df4412245a8a 100644
--- a/drivers/media/usb/dvb-usb-v2/Kconfig
+++ b/drivers/media/usb/dvb-usb-v2/Kconfig
@@ -96,10 +96,13 @@ config DVB_USB_GL861
 	tristate "Genesys Logic GL861 USB2.0 support"
 	depends on DVB_USB_V2
 	select DVB_ZL10353 if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_TC90522 if MEDIA_SUBDRV_AUTOSELECT
 	select MEDIA_TUNER_QT1010 if MEDIA_SUBDRV_AUTOSELECT
+	select DVB_PLL if MEDIA_SUBDRV_AUTOSELECT
 	help
 	  Say Y here to support the MSI Megasky 580 (55801) DVB-T USB2.0
-	  receiver with USB ID 0db0:5581.
+	  receiver with USB ID 0db0:5581, Friio White ISDB-T receiver
+	  with USB ID 0x7a69:0001.
 
 config DVB_USB_LME2510
 	tristate "LME DM04/QQBOX DVB-S USB2.0 support"
diff --git a/drivers/media/usb/dvb-usb-v2/gl861.c b/drivers/media/usb/dvb-usb-v2/gl861.c
index fee4b30df778..3338b21d8b25 100644
--- a/drivers/media/usb/dvb-usb-v2/gl861.c
+++ b/drivers/media/usb/dvb-usb-v2/gl861.c
@@ -6,10 +6,14 @@
  *
  * see Documentation/media/dvb-drivers/dvb-usb.rst for more information
  */
+#include <linux/string.h>
+
 #include "gl861.h"
 
 #include "zl10353.h"
 #include "qt1010.h"
+#include "tc90522.h"
+#include "dvb-pll.h"
 
 DVB_DEFINE_MOD_OPT_ADAPTER_NR(adapter_nr);
 
@@ -161,11 +165,478 @@ static struct dvb_usb_device_properties gl861_props = {
 	}
 };
 
+
+/*
+ * For Friio
+ */
+
+struct friio_priv {
+	struct i2c_adapter *demod_sub_i2c;
+	struct i2c_client  *i2c_client_demod;
+	struct i2c_client  *i2c_client_tuner;
+	struct i2c_adapter tuner_adap;
+};
+
+struct friio_config {
+	struct i2c_board_info demod_info;
+	struct tc90522_config demod_cfg;
+
+	struct i2c_board_info tuner_info;
+	struct dvb_pll_config tuner_cfg;
+};
+
+static const struct friio_config friio_config = {
+	.demod_info = { I2C_BOARD_INFO(TC90522_I2C_DEV_TER, 0x18), },
+	.tuner_info = { I2C_BOARD_INFO("tua6034_friio", 0x60), },
+};
+
+/* For another type of I2C:
+ * message sent by a USB control-read/write transaction with data stage.
+ * Used in init/config of Friio.
+ */
+static int
+gl861_i2c_write_ex(struct dvb_usb_device *d, u8 addr, u8 *wbuf, u16 wlen)
+{
+	u8 *buf;
+	int ret;
+
+	buf = kmalloc(wlen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	memcpy(buf, wbuf, wlen);
+	ret = usb_control_msg(d->udev, usb_sndctrlpipe(d->udev, 0),
+				 GL861_REQ_I2C_RAW, GL861_WRITE,
+				 addr << (8 + 1), 0x0100, buf, wlen, 2000);
+	kfree(buf);
+	return ret;
+}
+
+static int
+gl861_i2c_read_ex(struct dvb_usb_device *d, u8 addr, u8 *rbuf, u16 rlen)
+{
+	u8 *buf;
+	int ret;
+
+	buf = kmalloc(rlen, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = usb_control_msg(d->udev, usb_rcvctrlpipe(d->udev, 0),
+				 GL861_REQ_I2C_READ, GL861_READ,
+				 addr << (8 + 1), 0x0100, buf, rlen, 2000);
+	if (ret > 0 && rlen > 0)
+		memcpy(buf, rbuf, rlen);
+	kfree(buf);
+	return ret;
+}
+
+/* For I2C transactions to the tuner of Friio (dvb_pll).
+ *
+ * Friio uses irregular USB encapsulation for tuner i2c transactions:
+ * write transacions are encapsulated with a different USB 'request' value.
+ *
+ * Although all transactions are sent via the demod(tc90522)
+ * and the demod provides an i2c adapter for them, it cannot be used in Friio
+ * since it assumes using the same parent adapter with the demod,
+ * which does not use the request value and uses same one for both read/write.
+ * So we define a dedicated i2c adapter here.
+ */
+
+static int
+friio_i2c_tuner_read(struct dvb_usb_device *d, struct i2c_msg *msg)
+{
+	struct friio_priv *priv;
+	u8 addr;
+
+	priv = d_to_priv(d);
+	addr = priv->i2c_client_demod->addr;
+	return gl861_i2c_read_ex(d, addr, msg->buf, msg->len);
+}
+
+static int
+friio_i2c_tuner_write(struct dvb_usb_device *d, struct i2c_msg *msg)
+{
+	u8 *buf;
+	int ret;
+	struct friio_priv *priv;
+
+	priv = d_to_priv(d);
+
+	if (msg->len < 1)
+		return -EINVAL;
+
+	buf = kmalloc(msg->len + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	buf[0] = msg->addr << 1;
+	memcpy(buf + 1, msg->buf, msg->len);
+
+	ret = usb_control_msg(d->udev, usb_sndctrlpipe(d->udev, 0),
+				 GL861_REQ_I2C_RAW, GL861_WRITE,
+				 priv->i2c_client_demod->addr << (8 + 1),
+				 0xFE, buf, msg->len + 1, 2000);
+	kfree(buf);
+	return ret;
+}
+
+static int friio_tuner_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[],
+				int num)
+{
+	struct dvb_usb_device *d = i2c_get_adapdata(adap);
+	int i;
+
+	if (num > 2)
+		return -EINVAL;
+
+	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
+		return -EAGAIN;
+
+	for (i = 0; i < num; i++) {
+		int ret;
+
+		if (msg[i].flags & I2C_M_RD)
+			ret = friio_i2c_tuner_read(d, &msg[i]);
+		else
+			ret = friio_i2c_tuner_write(d, &msg[i]);
+
+		if (ret < 0)
+			break;
+
+		usleep_range(1000, 2000); /* avoid I2C errors */
+	}
+
+	mutex_unlock(&d->i2c_mutex);
+	return i;
+}
+
+static struct i2c_algorithm friio_tuner_i2c_algo = {
+	.master_xfer   = friio_tuner_i2c_xfer,
+	.functionality = gl861_i2c_func,
+};
+
+/* GPIO control in Friio */
+
+#define FRIIO_CTL_LNB (1 << 0)
+#define FRIIO_CTL_STROBE (1 << 1)
+#define FRIIO_CTL_CLK (1 << 2)
+#define FRIIO_CTL_LED (1 << 3)
+
+#define FRIIO_LED_RUNNING 0x6400ff64
+#define FRIIO_LED_STOPPED 0x96ff00ff
+
+/* control PIC16F676 attached to Friio */
+static int friio_ext_ctl(struct dvb_usb_device *d,
+			    u32 sat_color, int power_on)
+{
+	int i, ret;
+	struct i2c_msg msg;
+	u8 *buf;
+	u32 mask;
+	u8 power = (power_on) ? FRIIO_CTL_LNB : 0;
+
+	buf = kmalloc(2, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	msg.addr = 0x00;
+	msg.flags = 0;
+	msg.len = 2;
+	msg.buf = buf;
+	buf[0] = 0x00;
+
+	/* send 2bit header (&B10) */
+	buf[1] = power | FRIIO_CTL_LED | FRIIO_CTL_STROBE;
+	ret = i2c_transfer(&d->i2c_adap, &msg, 1);
+	buf[1] |= FRIIO_CTL_CLK;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+
+	buf[1] = power | FRIIO_CTL_STROBE;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+	buf[1] |= FRIIO_CTL_CLK;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+
+	/* send 32bit(satur, R, G, B) data in serial */
+	mask = 1 << 31;
+	for (i = 0; i < 32; i++) {
+		buf[1] = power | FRIIO_CTL_STROBE;
+		if (sat_color & mask)
+			buf[1] |= FRIIO_CTL_LED;
+		ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+		buf[1] |= FRIIO_CTL_CLK;
+		ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+		mask >>= 1;
+	}
+
+	/* set the strobe off */
+	buf[1] = power;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+	buf[1] |= FRIIO_CTL_CLK;
+	ret += i2c_transfer(&d->i2c_adap, &msg, 1);
+
+	kfree(buf);
+	return (ret == 70) ? 0 : -EREMOTEIO;
+}
+
+/* init/config of gl861 for Friio */
+/* NOTE:
+ * This function cannot be moved to friio_init()/dvb_usbv2_init(),
+ * because the init defined here must be done before any activities like I2C,
+ * but friio_init() is called by dvb-usbv2 after {_frontend, _tuner}_attach(),
+ * where I2C communication is used.
+ * Thus this function is set to be called from _power_ctl().
+ *
+ * Since it will be called on the early init stage
+ * where the i2c adapter is not initialized yet,
+ * we cannot use i2c_transfer() here.
+ */
+static int friio_reset(struct dvb_usb_device *d)
+{
+	int i, ret;
+	u8 wbuf[2], rbuf[2];
+
+	static const u8 friio_init_cmds[][2] = {
+		{0x33, 0x08}, {0x37, 0x40}, {0x3a, 0x1f}, {0x3b, 0xff},
+		{0x3c, 0x1f}, {0x3d, 0xff}, {0x38, 0x00}, {0x35, 0x00},
+		{0x39, 0x00}, {0x36, 0x00},
+	};
+
+	ret = usb_set_interface(d->udev, 0, 0);
+	if (ret < 0)
+		return ret;
+
+	wbuf[0] = 0x11;
+	wbuf[1] = 0x02;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+	usleep_range(2000, 3000);
+
+	wbuf[0] = 0x11;
+	wbuf[1] = 0x00;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Check if the dev is really a Friio White, since it might be
+	 * another device, Friio Black, with the same VID/PID.
+	 */
+
+	usleep_range(1000, 2000);
+	wbuf[0] = 0x03;
+	wbuf[1] = 0x80;
+	ret = gl861_i2c_write_ex(d, 0x09, wbuf, 2);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(2000, 3000);
+	ret = gl861_i2c_read_ex(d, 0x09, rbuf, 2);
+	if (ret < 0)
+		return ret;
+	if (rbuf[0] != 0xff || rbuf[1] != 0xff)
+		return -ENODEV;
+
+
+	usleep_range(1000, 2000);
+	ret = gl861_i2c_write_ex(d, 0x48, wbuf, 2);
+	if (ret < 0)
+		return ret;
+
+	usleep_range(2000, 3000);
+	ret = gl861_i2c_read_ex(d, 0x48, rbuf, 2);
+	if (ret < 0)
+		return ret;
+	if (rbuf[0] != 0xff || rbuf[1] != 0xff)
+		return -ENODEV;
+
+	wbuf[0] = 0x30;
+	wbuf[1] = 0x04;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	wbuf[0] = 0x00;
+	wbuf[1] = 0x01;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	wbuf[0] = 0x06;
+	wbuf[1] = 0x0f;
+	ret = gl861_i2c_msg(d, 0x00, wbuf, 2, NULL, 0);
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; i < ARRAY_SIZE(friio_init_cmds); i++) {
+		ret = gl861_i2c_msg(d, 0x00, (u8 *)friio_init_cmds[i], 2,
+				      NULL, 0);
+		if (ret < 0)
+			return ret;
+	}
+	return 0;
+}
+
+/*
+ * DVB callbacks for Friio
+ */
+
+static int friio_power_ctrl(struct dvb_usb_device *d, int onoff)
+{
+	return onoff ? friio_reset(d) : 0;
+}
+
+static int friio_frontend_attach(struct dvb_usb_adapter *adap)
+{
+	const struct i2c_board_info *info;
+	struct dvb_usb_device *d;
+	struct tc90522_config cfg;
+	struct i2c_client *cl;
+	struct friio_priv *priv;
+
+	info = &friio_config.demod_info;
+	d = adap_to_d(adap);
+	cl = dvb_module_probe("tc90522", info->type,
+			      &d->i2c_adap, info->addr, &cfg);
+	if (!cl)
+		return -ENODEV;
+	adap->fe[0] = cfg.fe;
+
+	/* ignore cfg.tuner_i2c and create new one */
+	priv = adap_to_priv(adap);
+	priv->i2c_client_demod = cl;
+	priv->tuner_adap.algo = &friio_tuner_i2c_algo;
+	priv->tuner_adap.dev.parent = &d->udev->dev;
+	strlcpy(priv->tuner_adap.name, d->name, sizeof(priv->tuner_adap.name));
+	strlcat(priv->tuner_adap.name, "-tuner", sizeof(priv->tuner_adap.name));
+	priv->demod_sub_i2c = &priv->tuner_adap;
+	i2c_set_adapdata(&priv->tuner_adap, d);
+
+	return i2c_add_adapter(&priv->tuner_adap);
+}
+
+static int friio_frontend_detach(struct dvb_usb_adapter *adap)
+{
+	struct friio_priv *priv;
+
+	priv = adap_to_priv(adap);
+	i2c_del_adapter(&priv->tuner_adap);
+	dvb_module_release(priv->i2c_client_demod);
+	return 0;
+}
+
+static int friio_tuner_attach(struct dvb_usb_adapter *adap)
+{
+	const struct i2c_board_info *info;
+	struct dvb_pll_config cfg;
+	struct i2c_client *cl;
+	struct friio_priv *priv;
+
+	priv = adap_to_priv(adap);
+	info = &friio_config.tuner_info;
+	cfg = friio_config.tuner_cfg;
+	cfg.fe = adap->fe[0];
+
+	cl = dvb_module_probe("dvb_pll", info->type,
+			      priv->demod_sub_i2c, info->addr, &cfg);
+	if (!cl)
+		return -ENODEV;
+	priv->i2c_client_tuner = cl;
+	return 0;
+}
+
+static int friio_tuner_detach(struct dvb_usb_adapter *adap)
+{
+	struct friio_priv *priv;
+
+	priv = adap_to_priv(adap);
+	dvb_module_release(priv->i2c_client_tuner);
+	return 0;
+}
+
+static int friio_init(struct dvb_usb_device *d)
+{
+	int i;
+	int ret;
+	struct friio_priv *priv;
+
+	static const u8 demod_init[][2] = {
+		{0x01, 0x40}, {0x04, 0x38}, {0x05, 0x40}, {0x07, 0x40},
+		{0x0f, 0x4f}, {0x11, 0x21}, {0x12, 0x0b}, {0x13, 0x2f},
+		{0x14, 0x31}, {0x16, 0x02}, {0x21, 0xc4}, {0x22, 0x20},
+		{0x2c, 0x79}, {0x2d, 0x34}, {0x2f, 0x00}, {0x30, 0x28},
+		{0x31, 0x31}, {0x32, 0xdf}, {0x38, 0x01}, {0x39, 0x78},
+		{0x3b, 0x33}, {0x3c, 0x33}, {0x48, 0x90}, {0x51, 0x68},
+		{0x5e, 0x38}, {0x71, 0x00}, {0x72, 0x08}, {0x77, 0x00},
+		{0xc0, 0x21}, {0xc1, 0x10}, {0xe4, 0x1a}, {0xea, 0x1f},
+		{0x77, 0x00}, {0x71, 0x00}, {0x71, 0x00}, {0x76, 0x0c},
+	};
+
+	/* power on LNA? */
+	ret = friio_ext_ctl(d, FRIIO_LED_STOPPED, true);
+	if (ret < 0)
+		return ret;
+	msleep(20);
+
+	/* init/config demod */
+	priv = d_to_priv(d);
+	for (i = 0; i < ARRAY_SIZE(demod_init); i++) {
+		int ret;
+
+		ret = i2c_master_send(priv->i2c_client_demod, demod_init[i], 2);
+		if (ret < 0)
+			return ret;
+	}
+	msleep(100);
+	return 0;
+}
+
+static void friio_exit(struct dvb_usb_device *d)
+{
+	friio_ext_ctl(d, FRIIO_LED_STOPPED, false);
+}
+
+static int friio_streaming_ctrl(struct dvb_frontend *fe, int onoff)
+{
+	u32 led_color;
+
+	led_color = onoff ? FRIIO_LED_RUNNING : FRIIO_LED_STOPPED;
+	return friio_ext_ctl(fe_to_d(fe), led_color, true);
+}
+
+
+static struct dvb_usb_device_properties friio_props = {
+	.driver_name = KBUILD_MODNAME,
+	.owner = THIS_MODULE,
+	.adapter_nr = adapter_nr,
+
+	.size_of_priv = sizeof(struct friio_priv),
+
+	.i2c_algo = &gl861_i2c_algo,
+	.power_ctrl = friio_power_ctrl,
+	.frontend_attach = friio_frontend_attach,
+	.frontend_detach = friio_frontend_detach,
+	.tuner_attach = friio_tuner_attach,
+	.tuner_detach = friio_tuner_detach,
+	.init = friio_init,
+	.exit = friio_exit,
+	.streaming_ctrl = friio_streaming_ctrl,
+
+	.num_adapters = 1,
+	.adapter = {
+		{
+			.stream = DVB_USB_STREAM_BULK(0x01, 8, 16384),
+		}
+	}
+};
+
 static const struct usb_device_id gl861_id_table[] = {
 	{ DVB_USB_DEVICE(USB_VID_MSI, USB_PID_MSI_MEGASKY580_55801,
 		&gl861_props, "MSI Mega Sky 55801 DVB-T USB2.0", NULL) },
 	{ DVB_USB_DEVICE(USB_VID_ALINK, USB_VID_ALINK_DTU,
 		&gl861_props, "A-LINK DTU DVB-T USB2.0", NULL) },
+	{ DVB_USB_DEVICE(USB_VID_774, USB_PID_FRIIO_WHITE,
+		&friio_props, "774 Friio White ISDB-T USB2.0", NULL) },
 	{ }
 };
 MODULE_DEVICE_TABLE(usb, gl861_id_table);
diff --git a/drivers/media/usb/dvb-usb-v2/gl861.h b/drivers/media/usb/dvb-usb-v2/gl861.h
index b651b857e034..02c00e10748a 100644
--- a/drivers/media/usb/dvb-usb-v2/gl861.h
+++ b/drivers/media/usb/dvb-usb-v2/gl861.h
@@ -9,5 +9,6 @@
 
 #define GL861_REQ_I2C_WRITE	0x01
 #define GL861_REQ_I2C_READ	0x02
+#define GL861_REQ_I2C_RAW	0x03
 
 #endif
diff --git a/drivers/media/usb/dvb-usb/Kconfig b/drivers/media/usb/dvb-usb/Kconfig
index b8a1c62a0682..513df955eaa3 100644
--- a/drivers/media/usb/dvb-usb/Kconfig
+++ b/drivers/media/usb/dvb-usb/Kconfig
@@ -312,12 +312,6 @@ config DVB_USB_DTV5100
 	help
 	  Say Y here to support the AME DTV-5100 USB2.0 DVB-T receiver.
 
-config DVB_USB_FRIIO
-	tristate "Friio ISDB-T USB2.0 Receiver support"
-	depends on DVB_USB
-	help
-	  Say Y here to support the Japanese DTV receiver Friio.
-
 config DVB_USB_AZ6027
 	tristate "Azurewave DVB-S/S2 USB2.0 AZ6027 support"
 	depends on DVB_USB
diff --git a/drivers/media/usb/dvb-usb/Makefile b/drivers/media/usb/dvb-usb/Makefile
index 9ad2618408ef..407d90ca8be0 100644
--- a/drivers/media/usb/dvb-usb/Makefile
+++ b/drivers/media/usb/dvb-usb/Makefile
@@ -71,9 +71,6 @@ obj-$(CONFIG_DVB_USB_DTV5100) += dvb-usb-dtv5100.o
 dvb-usb-cinergyT2-objs := cinergyT2-core.o cinergyT2-fe.o
 obj-$(CONFIG_DVB_USB_CINERGY_T2) += dvb-usb-cinergyT2.o
 
-dvb-usb-friio-objs := friio.o friio-fe.o
-obj-$(CONFIG_DVB_USB_FRIIO) += dvb-usb-friio.o
-
 dvb-usb-az6027-objs := az6027.o
 obj-$(CONFIG_DVB_USB_AZ6027) += dvb-usb-az6027.o
 
-- 
cgit v1.2.3


From f917fc0e9b9988982a841b871655cc41bde1e10e Mon Sep 17 00:00:00 2001
From: Akihiro Tsukada <tskd08@gmail.com>
Date: Sun, 10 Jun 2018 10:49:15 -0400
Subject: media: dvb-frontends/dvb-pll: fix module ref-counting

dvb-pll module was 'put' twice on exit:
once by dvb_frontend_detach() and another by dvb_module_release().

Signed-off-by: Akihiro Tsukada <tskd08@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/dvb-pll.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c
index e3894ff403d7..4a663420190e 100644
--- a/drivers/media/dvb-frontends/dvb-pll.c
+++ b/drivers/media/dvb-frontends/dvb-pll.c
@@ -884,6 +884,17 @@ dvb_pll_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	if (!dvb_pll_attach(fe, client->addr, client->adapter, desc_id))
 		return -ENOMEM;
 
+	/*
+	 * Unset tuner_ops.release (== dvb_pll_release)
+	 * which has been just set in the above dvb_pll_attach(),
+	 * because if tuner_ops.release was left defined,
+	 * this module would be 'put' twice on exit:
+	 * once by dvb_frontend_detach() and another by dvb_module_release().
+	 *
+	 * dvb_pll_release is instead executed in the i2c driver's .remove(),
+	 * keeping dvb_pll_attach untouched for legacy (dvb_attach) drivers.
+	 */
+	fe->ops.tuner_ops.release = NULL;
 	dev_info(&client->dev, "DVB Simple Tuner attached.\n");
 	return 0;
 }
-- 
cgit v1.2.3


From 44e2971f9e50aadb8d62eafbe31df014ef55d618 Mon Sep 17 00:00:00 2001
From: Akihiro Tsukada <tskd08@gmail.com>
Date: Sun, 10 Jun 2018 10:58:02 -0400
Subject: media: pci/pt1: suppress compiler warning in xtensa arch

Found and reported by kbuild test robot:
Message ID: <201805052003.MC007f9h%fengguang.wu@intel.com>
and holding an address of an empty struct in .driver.pm does no harm
when CONFIG_PM_SLEEP is not defined.

Signed-off-by: Akihiro Tsukada <tskd08@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/pt1/pt1.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/pci/pt1/pt1.c b/drivers/media/pci/pt1/pt1.c
index fda969a85684..7f878fc41b7e 100644
--- a/drivers/media/pci/pt1/pt1.c
+++ b/drivers/media/pci/pt1/pt1.c
@@ -1443,9 +1443,7 @@ static struct pci_driver pt1_driver = {
 	.probe		= pt1_probe,
 	.remove		= pt1_remove,
 	.id_table	= pt1_id_table,
-#ifdef CONFIG_PM_SLEEP
 	.driver.pm	= &pt1_pm_ops,
-#endif
 };
 
 module_pci_driver(pt1_driver);
-- 
cgit v1.2.3


From f7debfe54090d1a1c38e1f070be20d83bb70a8e0 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sun, 29 Jul 2018 23:03:05 +0200
Subject: ALSA: seq: virmidi: Offload the output event processing

The virmidi sequencer stuff tries to translate the rawmidi bytes to
sequencer events and deliver the packets at trigger callback.  The
amount of the whole process of these translations and deliveries
depends on the incoming rawmidi bytes, and we have no limit for that;
this was the cause of a CPU soft lockup that had been reported and
fixed recently.

Although we've fixed the soft lockup by putting the temporary unlock
and cond_resched(), it's rather a quick band aid.  In this patch,
meanwhile, the event parsing and delivery process is offloaded to a
dedicated work, and the trigger callback just kicks it off.  It has
three merits, at least:

- The processing is always done in a sleepable context, which can
  assure the event delivery with non-atomic flag without hackish
  is_atomic() usage.

- Other relevant codes can be simplified, reducing the lines

- It makes me happier

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/seq_virmidi.h  |   1 +
 sound/core/seq/seq_virmidi.c | 100 ++++++++++++++++++++-----------------------
 2 files changed, 47 insertions(+), 54 deletions(-)

diff --git a/include/sound/seq_virmidi.h b/include/sound/seq_virmidi.h
index 695257ae64ac..d488dcfa3a4e 100644
--- a/include/sound/seq_virmidi.h
+++ b/include/sound/seq_virmidi.h
@@ -41,6 +41,7 @@ struct snd_virmidi {
 	struct snd_seq_event event;
 	struct snd_virmidi_dev *rdev;
 	struct snd_rawmidi_substream *substream;
+	struct work_struct output_work;
 };
 
 #define SNDRV_VIRMIDI_SUBSCRIBE		(1<<0)
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 8ebbca554e99..67ea5d62cebc 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -154,70 +154,58 @@ static void snd_virmidi_input_trigger(struct snd_rawmidi_substream *substream, i
 	}
 }
 
-/*
- * trigger rawmidi stream for output
+/* process rawmidi bytes and send events;
+ * we need no lock here for vmidi->event since it's handled only in this work
  */
-static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, int up)
+static void snd_vmidi_output_work(struct work_struct *work)
 {
-	struct snd_virmidi *vmidi = substream->runtime->private_data;
-	int count, res;
-	unsigned char buf[32], *pbuf;
-	unsigned long flags;
-	bool check_resched = !in_atomic();
+	struct snd_virmidi *vmidi;
+	struct snd_rawmidi_substream *substream;
+	unsigned char input;
+	int ret;
+
+	vmidi = container_of(work, struct snd_virmidi, output_work);
+	substream = vmidi->substream;
+
+	/* discard the outputs in dispatch mode unless subscribed */
+	if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH &&
+	    !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) {
+		while (!snd_rawmidi_transmit_empty(substream))
+			snd_rawmidi_transmit_ack(substream, 1);
+		return;
+	}
 
-	if (up) {
-		vmidi->trigger = 1;
-		if (vmidi->seq_mode == SNDRV_VIRMIDI_SEQ_DISPATCH &&
-		    !(vmidi->rdev->flags & SNDRV_VIRMIDI_SUBSCRIBE)) {
-			while (snd_rawmidi_transmit(substream, buf,
-						    sizeof(buf)) > 0) {
-				/* ignored */
-			}
-			return;
-		}
-		spin_lock_irqsave(&substream->runtime->lock, flags);
+	while (vmidi->trigger) {
+		if (snd_rawmidi_transmit(substream, &input, 1) != 1)
+			break;
+		if (snd_midi_event_encode_byte(vmidi->parser, input,
+					       &vmidi->event) <= 0)
+			continue;
 		if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
-			if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0)
-				goto out;
+			ret = snd_seq_kernel_client_dispatch(vmidi->client,
+							     &vmidi->event,
+							     false, 0);
 			vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
-		}
-		while (1) {
-			count = __snd_rawmidi_transmit_peek(substream, buf, sizeof(buf));
-			if (count <= 0)
+			if (ret < 0)
 				break;
-			pbuf = buf;
-			while (count > 0) {
-				res = snd_midi_event_encode(vmidi->parser, pbuf, count, &vmidi->event);
-				if (res < 0) {
-					snd_midi_event_reset_encode(vmidi->parser);
-					continue;
-				}
-				__snd_rawmidi_transmit_ack(substream, res);
-				pbuf += res;
-				count -= res;
-				if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
-					if (snd_seq_kernel_client_dispatch(vmidi->client, &vmidi->event, in_atomic(), 0) < 0)
-						goto out;
-					vmidi->event.type = SNDRV_SEQ_EVENT_NONE;
-				}
-			}
-			if (!check_resched)
-				continue;
-			/* do temporary unlock & cond_resched() for avoiding
-			 * CPU soft lockup, which may happen via a write from
-			 * a huge rawmidi buffer
-			 */
-			spin_unlock_irqrestore(&substream->runtime->lock, flags);
-			cond_resched();
-			spin_lock_irqsave(&substream->runtime->lock, flags);
 		}
-	out:
-		spin_unlock_irqrestore(&substream->runtime->lock, flags);
-	} else {
-		vmidi->trigger = 0;
+		/* rawmidi input might be huge, allow to have a break */
+		cond_resched();
 	}
 }
 
+/*
+ * trigger rawmidi stream for output
+ */
+static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream, int up)
+{
+	struct snd_virmidi *vmidi = substream->runtime->private_data;
+
+	vmidi->trigger = !!up;
+	if (up)
+		queue_work(system_highpri_wq, &vmidi->output_work);
+}
+
 /*
  * open rawmidi handle for input
  */
@@ -270,6 +258,7 @@ static int snd_virmidi_output_open(struct snd_rawmidi_substream *substream)
 	vmidi->port = rdev->port;
 	snd_virmidi_init_event(vmidi, &vmidi->event);
 	vmidi->rdev = rdev;
+	INIT_WORK(&vmidi->output_work, snd_vmidi_output_work);
 	runtime->private_data = vmidi;
 	return 0;
 }
@@ -299,6 +288,9 @@ static int snd_virmidi_input_close(struct snd_rawmidi_substream *substream)
 static int snd_virmidi_output_close(struct snd_rawmidi_substream *substream)
 {
 	struct snd_virmidi *vmidi = substream->runtime->private_data;
+
+	vmidi->trigger = 0; /* to be sure */
+	cancel_work_sync(&vmidi->output_work);
 	snd_midi_event_free(vmidi->parser);
 	substream->runtime->private_data = NULL;
 	kfree(vmidi);
-- 
cgit v1.2.3


From 8d9404ad6a6dbcca36a788049f716675a1110da8 Mon Sep 17 00:00:00 2001
From: Akihiro Tsukada <tskd08@gmail.com>
Date: Sun, 10 Jun 2018 10:59:31 -0400
Subject: MAINTAINERS: add entries for several media drivers

add entries for the following drivers:
- earth_pt{1,3} DVB adapter drivers
- mxl301rf DVB tuner drivers
- qm1d1{b0004, c0042} DVB tuner drivers
- tc90522 DVB demod driver

Signed-off-by: Akihiro Tsukada <tskd08@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 MAINTAINERS | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index ab739894d257..3908908b1ec8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5066,6 +5066,18 @@ T:	git git://linuxtv.org/anttip/media_tree.git
 S:	Maintained
 F:	drivers/media/tuners/e4000*
 
+EARTH_PT1 MEDIA DRIVER
+M:	Akihiro Tsukada <tskd08@gmail.com>
+L:	linux-media@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/media/pci/pt1/
+
+EARTH_PT3 MEDIA DRIVER
+M:	Akihiro Tsukada <tskd08@gmail.com>
+L:	linux-media@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/media/pci/pt3/
+
 EC100 MEDIA DRIVER
 M:	Antti Palosaari <crope@iki.fi>
 L:	linux-media@vger.kernel.org
@@ -9711,6 +9723,12 @@ L:	linux-usb@vger.kernel.org
 S:	Maintained
 F:	drivers/usb/musb/
 
+MXL301RF MEDIA DRIVER
+M:	Akihiro Tsukada <tskd08@gmail.com>
+L:	linux-media@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/media/tuners/mxl301rf*
+
 MXL5007T MEDIA DRIVER
 M:	Michael Krufky <mkrufky@linuxtv.org>
 L:	linux-media@vger.kernel.org
@@ -11792,6 +11810,18 @@ L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/net/ethernet/qlogic/qlge/
 
+QM1D1B0004 MEDIA DRIVER
+M:	Akihiro Tsukada <tskd08@gmail.com>
+L:	linux-media@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/media/tuners/qm1d1b0004*
+
+QM1D1C0042 MEDIA DRIVER
+M:	Akihiro Tsukada <tskd08@gmail.com>
+L:	linux-media@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/media/tuners/qm1d1c0042*
+
 QNX4 FILESYSTEM
 M:	Anders Larsen <al@alarsen.net>
 W:	http://www.alarsen.net/linux/qnx4fs/
@@ -13896,6 +13926,12 @@ F:	include/uapi/linux/tc_act/
 F:	include/uapi/linux/tc_ematch/
 F:	net/sched/
 
+TC90522 MEDIA DRIVER
+M:	Akihiro Tsukada <tskd08@gmail.com>
+L:	linux-media@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/media/dvb-frontends/tc90522*
+
 TCP LOW PRIORITY MODULE
 M:	"Wong Hoi Sing, Edison" <hswong3i@gmail.com>
 M:	"Hung Hing Lun, Mike" <hlhung3i@gmail.com>
-- 
cgit v1.2.3


From 89b4ab213feb11a5bece544cfa12374f66c2c47c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Mon, 30 Jul 2018 14:48:29 +0200
Subject: ALSA: seq: virmidi: Use READ_ONCE/WRITE_ONCE() macros

The trigger flag in vmidi object can be referred in different contexts
concurrently, hence it's better to be put with READ_ONCE() and
WRITE_ONCE() macros to assure the accesses.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/seq_virmidi.h  |  2 +-
 sound/core/seq/seq_virmidi.c | 14 +++++---------
 2 files changed, 6 insertions(+), 10 deletions(-)

diff --git a/include/sound/seq_virmidi.h b/include/sound/seq_virmidi.h
index d488dcfa3a4e..796ce7772213 100644
--- a/include/sound/seq_virmidi.h
+++ b/include/sound/seq_virmidi.h
@@ -36,7 +36,7 @@ struct snd_virmidi {
 	int seq_mode;
 	int client;
 	int port;
-	unsigned int trigger: 1;
+	bool trigger;
 	struct snd_midi_event *parser;
 	struct snd_seq_event event;
 	struct snd_virmidi_dev *rdev;
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 67ea5d62cebc..03ac5e72dbe6 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -89,7 +89,7 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev,
 	else
 		down_read(&rdev->filelist_sem);
 	list_for_each_entry(vmidi, &rdev->filelist, list) {
-		if (!vmidi->trigger)
+		if (!READ_ONCE(vmidi->trigger))
 			continue;
 		if (ev->type == SNDRV_SEQ_EVENT_SYSEX) {
 			if ((ev->flags & SNDRV_SEQ_EVENT_LENGTH_MASK) != SNDRV_SEQ_EVENT_LENGTH_VARIABLE)
@@ -147,11 +147,7 @@ static void snd_virmidi_input_trigger(struct snd_rawmidi_substream *substream, i
 {
 	struct snd_virmidi *vmidi = substream->runtime->private_data;
 
-	if (up) {
-		vmidi->trigger = 1;
-	} else {
-		vmidi->trigger = 0;
-	}
+	WRITE_ONCE(vmidi->trigger, !!up);
 }
 
 /* process rawmidi bytes and send events;
@@ -175,7 +171,7 @@ static void snd_vmidi_output_work(struct work_struct *work)
 		return;
 	}
 
-	while (vmidi->trigger) {
+	while (READ_ONCE(vmidi->trigger)) {
 		if (snd_rawmidi_transmit(substream, &input, 1) != 1)
 			break;
 		if (snd_midi_event_encode_byte(vmidi->parser, input,
@@ -201,7 +197,7 @@ static void snd_virmidi_output_trigger(struct snd_rawmidi_substream *substream,
 {
 	struct snd_virmidi *vmidi = substream->runtime->private_data;
 
-	vmidi->trigger = !!up;
+	WRITE_ONCE(vmidi->trigger, !!up);
 	if (up)
 		queue_work(system_highpri_wq, &vmidi->output_work);
 }
@@ -289,7 +285,7 @@ static int snd_virmidi_output_close(struct snd_rawmidi_substream *substream)
 {
 	struct snd_virmidi *vmidi = substream->runtime->private_data;
 
-	vmidi->trigger = 0; /* to be sure */
+	WRITE_ONCE(vmidi->trigger, false); /* to be sure */
 	cancel_work_sync(&vmidi->output_work);
 	snd_midi_event_free(vmidi->parser);
 	substream->runtime->private_data = NULL;
-- 
cgit v1.2.3


From 410e8b4f5ca34e026ffc460a86e2354febe06fac Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Date: Mon, 30 Jul 2018 14:50:08 +0300
Subject: regulator: bd71837: adobt MFD changes to regulator driver

MFD part for bd71837 was changed during the review. Clean regulator part to
match changed MFD:
- renamed header file => fix include
- remove unused platdata as also type definition was removed
- Kconfig option for MFD part was changed => fix depends on clause
- Rename Kconfig option for regulators
  As Kconfig option for regulators gets now used (when dependency to MFD is
  satisfied) change it so that it won't require new change when support for
  bd71847 is added.

Signed-off-by: Matti Vaittinen <matti.vaittinen@fi.rohmeurope.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig             | 4 ++--
 drivers/regulator/Makefile            | 2 +-
 drivers/regulator/bd71837-regulator.c | 7 +------
 3 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 8233dc7f0a68..347351e79b1e 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -180,9 +180,9 @@ config REGULATOR_BCM590XX
 	  BCM590xx PMUs. This will enable support for the software
 	  controllable LDO/Switching regulators.
 
-config REGULATOR_BD71837
+config REGULATOR_BD718XX
 	tristate "ROHM BD71837 Power Regulator"
-	depends on MFD_BD71837
+	depends on MFD_ROHM_BD718XX
 	help
 	  This driver supports voltage regulators on ROHM BD71837 PMIC.
 	  This will enable support for the software controllable buck
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index b7839f41591e..18bfed61e7fe 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -27,7 +27,7 @@ obj-$(CONFIG_REGULATOR_AS3711) += as3711-regulator.o
 obj-$(CONFIG_REGULATOR_AS3722) += as3722-regulator.o
 obj-$(CONFIG_REGULATOR_AXP20X) += axp20x-regulator.o
 obj-$(CONFIG_REGULATOR_BCM590XX) += bcm590xx-regulator.o
-obj-$(CONFIG_REGULATOR_BD71837) += bd71837-regulator.o
+obj-$(CONFIG_REGULATOR_BD718XX) += bd71837-regulator.o
 obj-$(CONFIG_REGULATOR_BD9571MWV) += bd9571mwv-regulator.o
 obj-$(CONFIG_REGULATOR_DA903X)	+= da903x.o
 obj-$(CONFIG_REGULATOR_DA9052)	+= da9052-regulator.o
diff --git a/drivers/regulator/bd71837-regulator.c b/drivers/regulator/bd71837-regulator.c
index 3a487255482c..0f8ac8dec3e1 100644
--- a/drivers/regulator/bd71837-regulator.c
+++ b/drivers/regulator/bd71837-regulator.c
@@ -7,7 +7,7 @@
 #include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
-#include <linux/mfd/bd71837.h>
+#include <linux/mfd/rohm-bd718x7.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/driver.h>
@@ -490,7 +490,6 @@ struct reg_init {
 static int bd71837_probe(struct platform_device *pdev)
 {
 	struct bd71837_pmic *pmic;
-	struct bd71837_board *pdata;
 	struct regulator_config config = { 0 };
 	struct reg_init pmic_regulator_inits[] = {
 		{
@@ -558,7 +557,6 @@ static int bd71837_probe(struct platform_device *pdev)
 		goto err;
 	}
 	platform_set_drvdata(pdev, pmic);
-	pdata = dev_get_platdata(pmic->mfd->dev);
 
 	/* Register LOCK release */
 	err = regmap_update_bits(pmic->mfd->regmap, BD71837_REG_REGLOCK,
@@ -578,9 +576,6 @@ static int bd71837_probe(struct platform_device *pdev)
 
 		desc = &pmic->descs[i];
 
-		if (pdata)
-			config.init_data = pdata->init_data[i];
-
 		config.dev = pdev->dev.parent;
 		config.driver_data = pmic;
 		config.regmap = pmic->mfd->regmap;
-- 
cgit v1.2.3


From af3f606e0bbb6d811c50b7b90fe324b07fb7cab8 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Mon, 30 Jul 2018 13:24:12 +0100
Subject: PCI: mobiveil: Fix struct mobiveil_pcie.pcie_reg_base address type

The field pcie_reg_base in struct mobiveil_pcie represents a physical
address so it should be of phys_addr_t type rather than void __iomem*;
this results in the following compilation  warnings:

drivers/pci/controller/pcie-mobiveil.c: In function
'mobiveil_pcie_parse_dt':
drivers/pci/controller/pcie-mobiveil.c:326:22: warning: assignment makes
pointer from integer without a cast [-Wint-conversion]
  pcie->pcie_reg_base = res->start;
                      ^
drivers/pci/controller/pcie-mobiveil.c: In function
'mobiveil_pcie_enable_msi':
drivers/pci/controller/pcie-mobiveil.c:485:25: warning: initialization
makes integer from pointer without a cast [-Wint-conversion]
  phys_addr_t msg_addr = pcie->pcie_reg_base;
                         ^~~~
drivers/pci/controller/pcie-mobiveil.c: In function
'mobiveil_compose_msi_msg':
drivers/pci/controller/pcie-mobiveil.c:640:21: warning: initialization
makes integer from pointer without a cast [-Wint-conversion]
  phys_addr_t addr = pcie->pcie_reg_base + (data->hwirq * sizeof(int));

Fix the type and with it the compilation warnings.

Fixes: 9af6bcb11e12 ("PCI: mobiveil: Add Mobiveil PCIe Host Bridge IP
driver")
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>
---
 drivers/pci/controller/pcie-mobiveil.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index cf0aa7cee5b0..8b45f77d70f9 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -130,7 +130,7 @@ struct mobiveil_pcie {
 	void __iomem *config_axi_slave_base;	/* endpoint config base */
 	void __iomem *csr_axi_slave_base;	/* root port config base */
 	void __iomem *apb_csr_base;	/* MSI register base */
-	void __iomem *pcie_reg_base;	/* Physical PCIe Controller Base */
+	phys_addr_t pcie_reg_base;	/* Physical PCIe Controller Base */
 	struct irq_domain *intx_domain;
 	raw_spinlock_t intx_mask_lock;
 	int irq;
-- 
cgit v1.2.3


From d3743012230f8dab30d47caba1f2ee9e382385e7 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Mon, 30 Jul 2018 13:24:33 +0100
Subject: PCI: mobiveil: Add missing ../pci.h include

PCI mobiveil host controller driver currently fails to compile
with the following error:

drivers/pci/controller/pcie-mobiveil.c: In function
'mobiveil_pcie_probe':
drivers/pci/controller/pcie-mobiveil.c:788:8: error: implicit
declaration of function 'devm_of_pci_get_host_bridge_resources'; did you
mean 'pci_get_host_bridge_device'?
[-Werror=implicit-function-declaration]
  ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff,
        ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
        pci_get_host_bridge_device

Add the missing include file to pull in the required function declaration.

Fixes: 9af6bcb11e12 ("PCI: mobiveil: Add Mobiveil PCIe Host Bridge IP
driver")
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>
---
 drivers/pci/controller/pcie-mobiveil.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index 8b45f77d70f9..a939e8d31735 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -23,6 +23,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
+#include "../pci.h"
+
 /* register offsets and bit positions */
 
 /*
-- 
cgit v1.2.3


From 6f2c73c124b14808d210722fd1c0c8938f9db3ba Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Date: Mon, 30 Jul 2018 13:09:56 +0100
Subject: PCI: mobiveil: Add Kconfig/Makefile entries

commit 9af6bcb11e12 ("PCI: mobiveil: Add Mobiveil PCIe Host Bridge IP
driver") did not add the configuration and build infrastructure to
configure and build the mobiveil controller driver, so at present the
driver code is in the kernel but cannot be compiled.

Add the mobiveil controller driver Kconfig/Makefile infrastructure.

Fixes: 9af6bcb11e12 ("PCI: mobiveil: Add Mobiveil PCIe Host Bridge IP
driver")
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>
---
 drivers/pci/controller/Kconfig  | 10 ++++++++++
 drivers/pci/controller/Makefile |  1 +
 2 files changed, 11 insertions(+)

diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 18fa09b3ac8f..fc4dbcd35e8f 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -242,6 +242,16 @@ config PCIE_MEDIATEK
 	  Say Y here if you want to enable PCIe controller support on
 	  MediaTek SoCs.
 
+config PCIE_MOBIVEIL
+	bool "Mobiveil AXI PCIe controller"
+	depends on ARCH_ZYNQMP || COMPILE_TEST
+	depends on OF
+	depends on PCI_MSI_IRQ_DOMAIN
+	help
+	  Say Y here if you want to enable support for the Mobiveil AXI PCIe
+	  Soft IP. It has up to 8 outbound and inbound windows
+	  for address translation and it is a PCIe Gen4 IP.
+
 config PCIE_TANGO_SMP8759
 	bool "Tango SMP8759 PCIe controller (DANGEROUS)"
 	depends on ARCH_TANGO && PCI_MSI && OF
diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile
index 24322b92f200..d56a507495c5 100644
--- a/drivers/pci/controller/Makefile
+++ b/drivers/pci/controller/Makefile
@@ -26,6 +26,7 @@ obj-$(CONFIG_PCIE_ROCKCHIP) += pcie-rockchip.o
 obj-$(CONFIG_PCIE_ROCKCHIP_EP) += pcie-rockchip-ep.o
 obj-$(CONFIG_PCIE_ROCKCHIP_HOST) += pcie-rockchip-host.o
 obj-$(CONFIG_PCIE_MEDIATEK) += pcie-mediatek.o
+obj-$(CONFIG_PCIE_MOBIVEIL) += pcie-mobiveil.o
 obj-$(CONFIG_PCIE_TANGO_SMP8759) += pcie-tango.o
 obj-$(CONFIG_VMD) += vmd.o
 # pcie-hisi.o quirks are needed even without CONFIG_PCIE_DW
-- 
cgit v1.2.3


From 157eb9a0b75e97ad390c6e50c7381b0a0e02fe97 Mon Sep 17 00:00:00 2001
From: Robert Schlabbach <Robert.Schlabbach@gmx.net>
Date: Sat, 16 Jun 2018 15:04:22 -0400
Subject: media: em28xx: explicitly disable TS packet filter

The em28xx driver never touched the EM2874 register bits that control
the transport stream packet filters, leaving them at whatever default
the firmware has set. E.g. the Pinnacle 290e disables them by default,
while the Hauppauge WinTV dualHD enables discarding NULL packets by
default.

However, some applications require NULL packets, e.g. to determine the
load in DOCSIS segments, so discarding NULL packets is undesired for
such applications.

This patch simply extends the bit mask when starting or stopping the
transport stream packet capture, so that the filter bits are cleared.
It has been verified that this makes the Hauppauge WinTV dualHD pass
an unfiltered DVB-C stream including NULL packets, which it didn't
before.

Signed-off-by: Robert Schlabbach <Robert.Schlabbach@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index f70845e7d8c6..45b24776a695 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -655,12 +655,12 @@ int em28xx_capture_start(struct em28xx *dev, int start)
 			rc = em28xx_write_reg_bits(dev,
 						   EM2874_R5F_TS_ENABLE,
 						   start ? EM2874_TS1_CAPTURE_ENABLE : 0x00,
-						   EM2874_TS1_CAPTURE_ENABLE);
+						   EM2874_TS1_CAPTURE_ENABLE | EM2874_TS1_FILTER_ENABLE | EM2874_TS1_NULL_DISCARD);
 		else
 			rc = em28xx_write_reg_bits(dev,
 						   EM2874_R5F_TS_ENABLE,
 						   start ? EM2874_TS2_CAPTURE_ENABLE : 0x00,
-						   EM2874_TS2_CAPTURE_ENABLE);
+						   EM2874_TS2_CAPTURE_ENABLE | EM2874_TS2_FILTER_ENABLE | EM2874_TS2_NULL_DISCARD);
 	} else {
 		/* FIXME: which is the best order? */
 		/* video registers are sampled by VREF */
-- 
cgit v1.2.3


From 4775ad06b56a151a32b1006accb62f43698c0872 Mon Sep 17 00:00:00 2001
From: Sergei Maksimenko <smaksimenko@quantenna.com>
Date: Thu, 31 May 2018 12:10:59 +0300
Subject: qtnfmac: implement cfg80211 power management callback

Implement set_power_mgmt() callback that forwards power saving
settings to the device firmware.

Signed-off-by: Sergei Maksimenko <smaksimenko@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/cfg80211.c | 21 ++++++++++++++
 drivers/net/wireless/quantenna/qtnfmac/commands.c | 34 +++++++++++++++++++++++
 drivers/net/wireless/quantenna/qtnfmac/commands.h |  1 +
 drivers/net/wireless/quantenna/qtnfmac/qlink.h    | 26 +++++++++++++++++
 4 files changed, 82 insertions(+)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index 656ddc659218..b1dfcc852d4c 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -843,6 +843,22 @@ static int qtnf_set_mac_acl(struct wiphy *wiphy,
 	return ret;
 }
 
+static int qtnf_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
+			       bool enabled, int timeout)
+{
+	struct qtnf_vif *vif = qtnf_netdev_get_priv(dev);
+	int ret;
+
+	ret = qtnf_cmd_send_pm_set(vif, enabled ? QLINK_PM_AUTO_STANDBY :
+				   QLINK_PM_OFF, timeout);
+	if (ret) {
+		pr_err("%s: failed to set PM mode ret=%d\n", dev->name, ret);
+		return ret;
+	}
+
+	return ret;
+}
+
 static struct cfg80211_ops qtn_cfg80211_ops = {
 	.add_virtual_intf	= qtnf_add_virtual_intf,
 	.change_virtual_intf	= qtnf_change_virtual_intf,
@@ -869,6 +885,7 @@ static struct cfg80211_ops qtn_cfg80211_ops = {
 	.channel_switch		= qtnf_channel_switch,
 	.start_radar_detection	= qtnf_start_radar_detection,
 	.set_mac_acl		= qtnf_set_mac_acl,
+	.set_power_mgmt		= qtnf_set_power_mgmt,
 };
 
 static void qtnf_cfg80211_reg_notifier(struct wiphy *wiphy_in,
@@ -921,6 +938,9 @@ struct wiphy *qtnf_wiphy_allocate(struct qtnf_bus *bus)
 	if (bus->hw_info.hw_capab & QLINK_HW_CAPAB_DFS_OFFLOAD)
 		qtn_cfg80211_ops.start_radar_detection = NULL;
 
+	if (!(bus->hw_info.hw_capab & QLINK_HW_CAPAB_PWR_MGMT))
+		qtn_cfg80211_ops.set_power_mgmt	= NULL;
+
 	wiphy = wiphy_new(&qtn_cfg80211_ops, sizeof(struct qtnf_wmac));
 	if (!wiphy)
 		return NULL;
@@ -994,6 +1014,7 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac)
 			WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD |
 			WIPHY_FLAG_AP_UAPSD |
 			WIPHY_FLAG_HAS_CHANNEL_SWITCH;
+	wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
 
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_DFS_OFFLOAD)
 		wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_DFS_OFFLOAD);
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index 42a598f92539..e6894c5d20e9 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -2799,3 +2799,37 @@ int qtnf_cmd_set_mac_acl(const struct qtnf_vif *vif,
 
 	return ret;
 }
+
+int qtnf_cmd_send_pm_set(const struct qtnf_vif *vif, u8 pm_mode, int timeout)
+{
+	struct qtnf_bus *bus = vif->mac->bus;
+	struct sk_buff *cmd_skb;
+	u16 res_code = QLINK_CMD_RESULT_OK;
+	struct qlink_cmd_pm_set *cmd;
+	int ret = 0;
+
+	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
+					    QLINK_CMD_PM_SET, sizeof(*cmd));
+	if (!cmd_skb)
+		return -ENOMEM;
+
+	cmd = (struct qlink_cmd_pm_set *)cmd_skb->data;
+	cmd->pm_mode = pm_mode;
+	cmd->pm_standby_timer = cpu_to_le32(timeout);
+
+	qtnf_bus_lock(bus);
+
+	ret = qtnf_cmd_send(bus, cmd_skb, &res_code);
+
+	if (unlikely(ret))
+		goto out;
+
+	if (unlikely(res_code != QLINK_CMD_RESULT_OK)) {
+		pr_err("cmd exec failed: 0x%.4X\n", res_code);
+		ret = -EFAULT;
+	}
+
+out:
+	qtnf_bus_unlock(bus);
+	return ret;
+}
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.h b/drivers/net/wireless/quantenna/qtnfmac/commands.h
index cf9274add26d..03a57e37a665 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.h
@@ -76,5 +76,6 @@ int qtnf_cmd_start_cac(const struct qtnf_vif *vif,
 		       u32 cac_time_ms);
 int qtnf_cmd_set_mac_acl(const struct qtnf_vif *vif,
 			 const struct cfg80211_acl_data *params);
+int qtnf_cmd_send_pm_set(const struct qtnf_vif *vif, u8 pm_mode, int timeout);
 
 #endif /* QLINK_COMMANDS_H_ */
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
index 4a32967d0479..cbdebf0410df 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
@@ -77,6 +77,7 @@ enum qlink_hw_capab {
 	QLINK_HW_CAPAB_STA_INACT_TIMEOUT	= BIT(1),
 	QLINK_HW_CAPAB_DFS_OFFLOAD		= BIT(2),
 	QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR	= BIT(3),
+	QLINK_HW_CAPAB_PWR_MGMT			= BIT(4),
 };
 
 enum qlink_iface_type {
@@ -256,6 +257,7 @@ enum qlink_cmd_type {
 	QLINK_CMD_CHAN_STATS		= 0x0054,
 	QLINK_CMD_CONNECT		= 0x0060,
 	QLINK_CMD_DISCONNECT		= 0x0061,
+	QLINK_CMD_PM_SET		= 0x0062,
 };
 
 /**
@@ -668,6 +670,30 @@ struct qlink_acl_data {
 	struct qlink_mac_address mac_addrs[0];
 } __packed;
 
+/**
+ * enum qlink_pm_mode - Power Management mode
+ *
+ * @QLINK_PM_OFF: normal mode, no power saving enabled
+ * @QLINK_PM_AUTO_STANDBY: enable auto power save mode
+ */
+enum qlink_pm_mode {
+	QLINK_PM_OFF		= 0,
+	QLINK_PM_AUTO_STANDBY	= 1,
+};
+
+/**
+ * struct qlink_cmd_pm_set - data for QLINK_CMD_PM_SET command
+ *
+ * @pm_standby timer: period of network inactivity in seconds before
+ *	putting a radio in power save mode
+ * @pm_mode: power management mode
+ */
+struct qlink_cmd_pm_set {
+	struct qlink_cmd chdr;
+	__le32 pm_standby_timer;
+	u8 pm_mode;
+} __packed;
+
 /* QLINK Command Responses messages related definitions
  */
 
-- 
cgit v1.2.3


From 8f1180e08ed436fcf3be290e9cf408e9bdb60664 Mon Sep 17 00:00:00 2001
From: Andrey Shevchenko <ashevchenko@quantenna.com>
Date: Thu, 31 May 2018 12:11:00 +0300
Subject: qtnfmac: enable multiple SSIDs scan support

Enable support for multiple SSIDs scans. Get max number of supported
SSIDs from firmware and report to cfg80211 core.

Signed-off-by: Andrey Shevchenko <ashevchenko@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/cfg80211.c | 3 ++-
 drivers/net/wireless/quantenna/qtnfmac/commands.c | 8 +++-----
 drivers/net/wireless/quantenna/qtnfmac/core.h     | 2 +-
 drivers/net/wireless/quantenna/qtnfmac/qlink.h    | 3 +++
 4 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index b1dfcc852d4c..0032fa9fdddd 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -995,7 +995,8 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac)
 	wiphy->retry_long = macinfo->lretry_limit;
 	wiphy->coverage_class = macinfo->coverage_class;
 
-	wiphy->max_scan_ssids = QTNF_MAX_SSID_LIST_LENGTH;
+	wiphy->max_scan_ssids =
+		(hw_info->max_scan_ssids) ? hw_info->max_scan_ssids : 1;
 	wiphy->max_scan_ie_len = QTNF_MAX_VSIE_LEN;
 	wiphy->mgmt_stypes = qtnf_mgmt_stypes;
 	wiphy->max_remain_on_channel_duration = 5000;
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index e6894c5d20e9..7942261961d6 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -1092,6 +1092,9 @@ qtnf_cmd_resp_proc_hw_info(struct qtnf_bus *bus,
 		case QTN_TLV_ID_UBOOT_VER:
 			uboot_ver = (const void *)tlv->val;
 			break;
+		case QTN_TLV_ID_MAX_SCAN_SSIDS:
+			hwinfo->max_scan_ssids = *tlv->val;
+			break;
 		default:
 			break;
 		}
@@ -2260,11 +2263,6 @@ int qtnf_cmd_send_scan(struct qtnf_wmac *mac)
 	int count = 0;
 	int ret;
 
-	if (scan_req->n_ssids > QTNF_MAX_SSID_LIST_LENGTH) {
-		pr_err("MAC%u: too many SSIDs in scan request\n", mac->macid);
-		return -EINVAL;
-	}
-
 	cmd_skb = qtnf_cmd_alloc_new_cmdskb(mac->macid, QLINK_VIFID_RSVD,
 					    QLINK_CMD_SCAN,
 					    sizeof(struct qlink_cmd));
diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.h b/drivers/net/wireless/quantenna/qtnfmac/core.h
index 214435448335..c4808f1ba8b0 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.h
@@ -40,7 +40,6 @@
 #undef pr_fmt
 #define pr_fmt(fmt)	KBUILD_MODNAME ": %s: " fmt, __func__
 
-#define QTNF_MAX_SSID_LIST_LENGTH	2
 #define QTNF_MAX_VSIE_LEN		255
 #define QTNF_MAX_INTF			8
 #define QTNF_MAX_EVENT_QUEUE_LEN	255
@@ -145,6 +144,7 @@ struct qtnf_hw_info {
 	u8 total_rx_chain;
 	char fw_version[ETHTOOL_FWVERS_LEN];
 	u32 hw_version;
+	u8 max_scan_ssids;
 };
 
 struct qtnf_vif *qtnf_mac_get_free_vif(struct qtnf_wmac *mac);
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
index cbdebf0410df..8fbef67fbbb8 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
@@ -1091,6 +1091,8 @@ struct qlink_event_radar {
  * @QTN_TLV_ID_STA_STATS: per-STA statistics as defined by
  *	&struct qlink_sta_stats. Valid values are marked as such in a bitmap
  *	carried by QTN_TLV_ID_STA_STATS_MAP.
+ * @QTN_TLV_ID_MAX_SCAN_SSIDS: maximum number of SSIDs the device can scan
+ *	for in any given scan.
  */
 enum qlink_tlv_id {
 	QTN_TLV_ID_FRAG_THRESH		= 0x0201,
@@ -1119,6 +1121,7 @@ enum qlink_tlv_id {
 	QTN_TLV_ID_CALIBRATION_VER	= 0x0406,
 	QTN_TLV_ID_UBOOT_VER		= 0x0407,
 	QTN_TLV_ID_RANDOM_MAC_ADDR	= 0x0408,
+	QTN_TLV_ID_MAX_SCAN_SSIDS	= 0x0409,
 };
 
 struct qlink_tlv_hdr {
-- 
cgit v1.2.3


From ea8532daee31bc72abfbc9ca7a43cbec0f6c05af Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Wed, 30 May 2018 11:07:05 -0400
Subject: media: videodev2: get rid of VIDIOC_RESERVED

While this ioctl is there at least since Kernel 2.6.12-rc2, it
was never used by any upstream driver.

Get rid of it.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/videodev2.h.rst.exceptions | 1 -
 include/uapi/linux/videodev2.h                 | 1 -
 2 files changed, 2 deletions(-)

diff --git a/Documentation/media/videodev2.h.rst.exceptions b/Documentation/media/videodev2.h.rst.exceptions
index a5cb0a8686ac..ca9f0edc579e 100644
--- a/Documentation/media/videodev2.h.rst.exceptions
+++ b/Documentation/media/videodev2.h.rst.exceptions
@@ -517,7 +517,6 @@ ignore define V4L2_CTRL_WHICH_DEF_VAL
 ignore define V4L2_OUT_CAP_CUSTOM_TIMINGS
 ignore define V4L2_CID_MAX_CTRLS
 
-ignore ioctl VIDIOC_RESERVED
 ignore define BASE_VIDIOC_PRIVATE
 
 # Associate ioctls with their counterparts
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 3ea8097c2470..d8b33095abe0 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -2311,7 +2311,6 @@ struct v4l2_create_buffers {
  *
  */
 #define VIDIOC_QUERYCAP		 _IOR('V',  0, struct v4l2_capability)
-#define VIDIOC_RESERVED		  _IO('V',  1)
 #define VIDIOC_ENUM_FMT         _IOWR('V',  2, struct v4l2_fmtdesc)
 #define VIDIOC_G_FMT		_IOWR('V',  4, struct v4l2_format)
 #define VIDIOC_S_FMT		_IOWR('V',  5, struct v4l2_format)
-- 
cgit v1.2.3


From c454edc21b12dd7d416de6c81555e87aaec9685c Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Mon, 30 Jul 2018 10:10:01 -0400
Subject: block: don't account for split bio's size in cgroup stats

We need to check in blkcg_bio_issue_check if the bio is flagged as
QUEUE_ENTERED, because if it is then we've already accounted for the
size of the IO in the cgroup stats.  We can still however account for
the extra IO since it'll be another request.

Reported-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-cgroup.h | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 3bed5e02a873..f7b910768306 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -769,8 +769,14 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q,
 
 	if (!throtl) {
 		blkg = blkg ?: q->root_blkg;
-		blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
-				bio->bi_iter.bi_size);
+		/*
+		 * If the bio is flagged with BIO_QUEUE_ENTERED it means this
+		 * is a split bio and we would have already accounted for the
+		 * size of the bio.
+		 */
+		if (!bio_flagged(bio, BIO_QUEUE_ENTERED))
+			blkg_rwstat_add(&blkg->stat_bytes, bio->bi_opf,
+					bio->bi_iter.bi_size);
 		blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1);
 	}
 
-- 
cgit v1.2.3


From ddd0bc756983dc4d19000a4fe021b4c7f9d59aab Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Mon, 30 Jul 2018 00:15:31 +0300
Subject: block: move ref_tag calculation func to the block layer

Currently this function is implemented in the scsi layer, but it's
actual place should be the block layer since T10-PI is a general
data integrity feature that is used in the nvme protocol as well.

Suggested-by: Christoph Hellwig <hch@lst.de>
Cc: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/infiniband/ulp/iser/iser_memory.c |  2 +-
 drivers/nvme/host/core.c                  |  3 +--
 drivers/scsi/mpt3sas/mpt3sas_scsih.c      |  2 +-
 drivers/scsi/sd_dif.c                     |  4 ++--
 include/linux/t10-pi.h                    | 10 ++++++++++
 include/scsi/scsi_cmnd.h                  |  7 +------
 6 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index ca844a926e6a..130bf163f066 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -311,7 +311,7 @@ iser_set_dif_domain(struct scsi_cmnd *sc, struct ib_sig_attrs *sig_attrs,
 {
 	domain->sig_type = IB_SIG_TYPE_T10_DIF;
 	domain->sig.dif.pi_interval = scsi_prot_interval(sc);
-	domain->sig.dif.ref_tag = scsi_prot_ref_tag(sc);
+	domain->sig.dif.ref_tag = t10_pi_ref_tag(sc->request);
 	/*
 	 * At the moment we hard code those, but in the future
 	 * we will take them from sc.
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index e77e6418a21c..16c8b86fe95d 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -611,8 +611,7 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 		case NVME_NS_DPS_PI_TYPE2:
 			control |= NVME_RW_PRINFO_PRCHK_GUARD |
 					NVME_RW_PRINFO_PRCHK_REF;
-			cmnd->rw.reftag = cpu_to_le32(
-					nvme_block_nr(ns, blk_rq_pos(req)));
+			cmnd->rw.reftag = cpu_to_le32(t10_pi_ref_tag(req));
 			break;
 		}
 	}
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index b8d131a455d0..dd738ae5c75b 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -4568,7 +4568,7 @@ _scsih_setup_eedp(struct MPT3SAS_ADAPTER *ioc, struct scsi_cmnd *scmd,
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_REFTAG |
 		    MPI2_SCSIIO_EEDPFLAGS_CHECK_GUARD;
 		mpi_request->CDB.EEDP32.PrimaryReferenceTag =
-		    cpu_to_be32(scsi_prot_ref_tag(scmd));
+		    cpu_to_be32(t10_pi_ref_tag(scmd->request));
 		break;
 
 	case SCSI_PROT_DIF_TYPE3:
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 9035380c0dda..d8de43d359ac 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -124,7 +124,7 @@ void sd_dif_prepare(struct scsi_cmnd *scmd)
 	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION)
 		return;
 
-	phys = scsi_prot_ref_tag(scmd);
+	phys = t10_pi_ref_tag(scmd->request);
 
 	__rq_for_each_bio(bio, scmd->request) {
 		struct bio_integrity_payload *bip = bio_integrity(bio);
@@ -176,7 +176,7 @@ void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
 		return;
 
 	intervals = good_bytes / scsi_prot_interval(scmd);
-	phys = scsi_prot_ref_tag(scmd);
+	phys = t10_pi_ref_tag(scmd->request);
 
 	__rq_for_each_bio(bio, scmd->request) {
 		struct bio_integrity_payload *bip = bio_integrity(bio);
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index c6aa8a3c42ed..c40511f4e63d 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -37,6 +37,16 @@ struct t10_pi_tuple {
 #define T10_PI_APP_ESCAPE cpu_to_be16(0xffff)
 #define T10_PI_REF_ESCAPE cpu_to_be32(0xffffffff)
 
+static inline u32 t10_pi_ref_tag(struct request *rq)
+{
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+	return blk_rq_pos(rq) >>
+		(rq->q->integrity.interval_exp - 9) & 0xffffffff;
+#else
+	return -1U;
+#endif
+}
+
 extern const struct blk_integrity_profile t10_pi_type1_crc;
 extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index aaf1e971c6a3..cae229b5395c 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -4,6 +4,7 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/blkdev.h>
+#include <linux/t10-pi.h>
 #include <linux/list.h>
 #include <linux/types.h>
 #include <linux/timer.h>
@@ -313,12 +314,6 @@ static inline unsigned int scsi_prot_interval(struct scsi_cmnd *scmd)
 	return scmd->device->sector_size;
 }
 
-static inline u32 scsi_prot_ref_tag(struct scsi_cmnd *scmd)
-{
-	return blk_rq_pos(scmd->request) >>
-		(ilog2(scsi_prot_interval(scmd)) - 9) & 0xffffffff;
-}
-
 static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd)
 {
 	return cmd->prot_sdb ? cmd->prot_sdb->table.nents : 0;
-- 
cgit v1.2.3


From 10c41ddd61323b27b447bc8e18296ac6c06107ad Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Mon, 30 Jul 2018 00:15:32 +0300
Subject: block: move dif_prepare/dif_complete functions to block layer

Currently these functions are implemented in the scsi layer, but their
actual place should be the block layer since T10-PI is a general data
integrity feature that is used in the nvme protocol as well. Also, use
the tuple size from the integrity profile since it may vary between
integrity types.

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/t10-pi.c         | 110 +++++++++++++++++++++++++++++++++++++++++++++++
 drivers/scsi/sd.c      |   8 ++--
 drivers/scsi/sd.h      |   9 ----
 drivers/scsi/sd_dif.c  | 113 -------------------------------------------------
 include/linux/t10-pi.h |   3 ++
 5 files changed, 118 insertions(+), 125 deletions(-)

diff --git a/block/t10-pi.c b/block/t10-pi.c
index a98db384048f..62aed77d0bb9 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -184,3 +184,113 @@ const struct blk_integrity_profile t10_pi_type3_ip = {
 	.verify_fn		= t10_pi_type3_verify_ip,
 };
 EXPORT_SYMBOL(t10_pi_type3_ip);
+
+/**
+ * t10_pi_prepare - prepare PI prior submitting request to device
+ * @rq:              request with PI that should be prepared
+ * @protection_type: PI type (Type 1/Type 2/Type 3)
+ *
+ * For Type 1/Type 2, the virtual start sector is the one that was
+ * originally submitted by the block layer for the ref_tag usage. Due to
+ * partitioning, MD/DM cloning, etc. the actual physical start sector is
+ * likely to be different. Remap protection information to match the
+ * physical LBA.
+ *
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+void t10_pi_prepare(struct request *rq, u8 protection_type)
+{
+	const int tuple_sz = rq->q->integrity.tuple_size;
+	u32 ref_tag = t10_pi_ref_tag(rq);
+	struct bio *bio;
+
+	if (protection_type == T10_PI_TYPE3_PROTECTION)
+		return;
+
+	__rq_for_each_bio(bio, rq) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
+		u32 virt = bip_get_seed(bip) & 0xffffffff;
+		struct bio_vec iv;
+		struct bvec_iter iter;
+
+		/* Already remapped? */
+		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
+			break;
+
+		bip_for_each_vec(iv, bip, iter) {
+			void *p, *pmap;
+			unsigned int j;
+
+			pmap = kmap_atomic(iv.bv_page);
+			p = pmap + iv.bv_offset;
+			for (j = 0; j < iv.bv_len; j += tuple_sz) {
+				struct t10_pi_tuple *pi = p;
+
+				if (be32_to_cpu(pi->ref_tag) == virt)
+					pi->ref_tag = cpu_to_be32(ref_tag);
+				virt++;
+				ref_tag++;
+				p += tuple_sz;
+			}
+
+			kunmap_atomic(pmap);
+		}
+
+		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
+	}
+}
+EXPORT_SYMBOL(t10_pi_prepare);
+
+/**
+ * t10_pi_complete - prepare PI prior returning request to the block layer
+ * @rq:              request with PI that should be prepared
+ * @protection_type: PI type (Type 1/Type 2/Type 3)
+ * @intervals:       total elements to prepare
+ *
+ * For Type 1/Type 2, the virtual start sector is the one that was
+ * originally submitted by the block layer for the ref_tag usage. Due to
+ * partitioning, MD/DM cloning, etc. the actual physical start sector is
+ * likely to be different. Since the physical start sector was submitted
+ * to the device, we should remap it back to virtual values expected by the
+ * block layer.
+ *
+ * Type 3 does not have a reference tag so no remapping is required.
+ */
+void t10_pi_complete(struct request *rq, u8 protection_type,
+		     unsigned int intervals)
+{
+	const int tuple_sz = rq->q->integrity.tuple_size;
+	u32 ref_tag = t10_pi_ref_tag(rq);
+	struct bio *bio;
+
+	if (protection_type == T10_PI_TYPE3_PROTECTION)
+		return;
+
+	__rq_for_each_bio(bio, rq) {
+		struct bio_integrity_payload *bip = bio_integrity(bio);
+		u32 virt = bip_get_seed(bip) & 0xffffffff;
+		struct bio_vec iv;
+		struct bvec_iter iter;
+
+		bip_for_each_vec(iv, bip, iter) {
+			void *p, *pmap;
+			unsigned int j;
+
+			pmap = kmap_atomic(iv.bv_page);
+			p = pmap + iv.bv_offset;
+			for (j = 0; j < iv.bv_len && intervals; j += tuple_sz) {
+				struct t10_pi_tuple *pi = p;
+
+				if (be32_to_cpu(pi->ref_tag) == ref_tag)
+					pi->ref_tag = cpu_to_be32(virt);
+				virt++;
+				ref_tag++;
+				intervals--;
+				p += tuple_sz;
+			}
+
+			kunmap_atomic(pmap);
+		}
+	}
+}
+EXPORT_SYMBOL(t10_pi_complete);
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 9421d9877730..bbebdc3769b0 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -1119,7 +1119,7 @@ static int sd_setup_read_write_cmnd(struct scsi_cmnd *SCpnt)
 		SCpnt->cmnd[0] = WRITE_6;
 
 		if (blk_integrity_rq(rq))
-			sd_dif_prepare(SCpnt);
+			t10_pi_prepare(SCpnt->request, sdkp->protection_type);
 
 	} else if (rq_data_dir(rq) == READ) {
 		SCpnt->cmnd[0] = READ_6;
@@ -2047,8 +2047,10 @@ static int sd_done(struct scsi_cmnd *SCpnt)
 					   "sd_done: completed %d of %d bytes\n",
 					   good_bytes, scsi_bufflen(SCpnt)));
 
-	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt))
-		sd_dif_complete(SCpnt, good_bytes);
+	if (rq_data_dir(SCpnt->request) == READ && scsi_prot_sg_count(SCpnt) &&
+	    good_bytes)
+		t10_pi_complete(SCpnt->request, sdkp->protection_type,
+				good_bytes / scsi_prot_interval(SCpnt));
 
 	return good_bytes;
 }
diff --git a/drivers/scsi/sd.h b/drivers/scsi/sd.h
index 392c7d078ae3..a7d4f50b67d4 100644
--- a/drivers/scsi/sd.h
+++ b/drivers/scsi/sd.h
@@ -254,21 +254,12 @@ static inline unsigned int sd_prot_flag_mask(unsigned int prot_op)
 #ifdef CONFIG_BLK_DEV_INTEGRITY
 
 extern void sd_dif_config_host(struct scsi_disk *);
-extern void sd_dif_prepare(struct scsi_cmnd *scmd);
-extern void sd_dif_complete(struct scsi_cmnd *, unsigned int);
 
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 static inline void sd_dif_config_host(struct scsi_disk *disk)
 {
 }
-static inline int sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	return 0;
-}
-static inline void sd_dif_complete(struct scsi_cmnd *cmd, unsigned int a)
-{
-}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index d8de43d359ac..db72c82486e3 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -95,116 +95,3 @@ out:
 	blk_integrity_register(disk, &bi);
 }
 
-/*
- * The virtual start sector is the one that was originally submitted
- * by the block layer.	Due to partitioning, MD/DM cloning, etc. the
- * actual physical start sector is likely to be different.  Remap
- * protection information to match the physical LBA.
- *
- * From a protocol perspective there's a slight difference between
- * Type 1 and 2.  The latter uses 32-byte CDBs exclusively, and the
- * reference tag is seeded in the CDB.  This gives us the potential to
- * avoid virt->phys remapping during write.  However, at read time we
- * don't know whether the virt sector is the same as when we wrote it
- * (we could be reading from real disk as opposed to MD/DM device.  So
- * we always remap Type 2 making it identical to Type 1.
- *
- * Type 3 does not have a reference tag so no remapping is required.
- */
-void sd_dif_prepare(struct scsi_cmnd *scmd)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct bio *bio;
-	struct scsi_disk *sdkp;
-	struct t10_pi_tuple *pi;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION)
-		return;
-
-	phys = t10_pi_ref_tag(scmd->request);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-		unsigned int j;
-
-		/* Already remapped? */
-		if (bip->bip_flags & BIP_MAPPED_INTEGRITY)
-			break;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (be32_to_cpu(pi->ref_tag) == virt)
-					pi->ref_tag = cpu_to_be32(phys);
-
-				virt++;
-				phys++;
-			}
-
-			kunmap_atomic(pi);
-		}
-
-		bip->bip_flags |= BIP_MAPPED_INTEGRITY;
-	}
-}
-
-/*
- * Remap physical sector values in the reference tag to the virtual
- * values expected by the block layer.
- */
-void sd_dif_complete(struct scsi_cmnd *scmd, unsigned int good_bytes)
-{
-	const int tuple_sz = sizeof(struct t10_pi_tuple);
-	struct scsi_disk *sdkp;
-	struct bio *bio;
-	struct t10_pi_tuple *pi;
-	unsigned int j, intervals;
-	u32 phys, virt;
-
-	sdkp = scsi_disk(scmd->request->rq_disk);
-
-	if (sdkp->protection_type == T10_PI_TYPE3_PROTECTION || good_bytes == 0)
-		return;
-
-	intervals = good_bytes / scsi_prot_interval(scmd);
-	phys = t10_pi_ref_tag(scmd->request);
-
-	__rq_for_each_bio(bio, scmd->request) {
-		struct bio_integrity_payload *bip = bio_integrity(bio);
-		struct bio_vec iv;
-		struct bvec_iter iter;
-
-		virt = bip_get_seed(bip) & 0xffffffff;
-
-		bip_for_each_vec(iv, bip, iter) {
-			pi = kmap_atomic(iv.bv_page) + iv.bv_offset;
-
-			for (j = 0; j < iv.bv_len; j += tuple_sz, pi++) {
-
-				if (intervals == 0) {
-					kunmap_atomic(pi);
-					return;
-				}
-
-				if (be32_to_cpu(pi->ref_tag) == phys)
-					pi->ref_tag = cpu_to_be32(virt);
-
-				virt++;
-				phys++;
-				intervals--;
-			}
-
-			kunmap_atomic(pi);
-		}
-	}
-}
-
diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index c40511f4e63d..5a427c289f58 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -51,5 +51,8 @@ extern const struct blk_integrity_profile t10_pi_type1_crc;
 extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
 extern const struct blk_integrity_profile t10_pi_type3_ip;
+extern void t10_pi_prepare(struct request *rq, u8 protection_type);
+extern void t10_pi_complete(struct request *rq, u8 protection_type,
+			    unsigned int intervals);
 
 #endif
-- 
cgit v1.2.3


From f7f1fc363aab4601786d373569c1ae802ea593d0 Mon Sep 17 00:00:00 2001
From: Max Gurtovoy <maxg@mellanox.com>
Date: Mon, 30 Jul 2018 00:15:33 +0300
Subject: nvme: use blk API to remap ref tags for IOs with metadata

Also moved the logic of the remapping to the nvme core driver instead
of implementing it in the nvme pci driver. This way all the other nvme
transport drivers will benefit from it (in case they'll implement metadata
support).

Suggested-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Acked-by: Keith Busch <keith.busch@intel.com>
Signed-off-by: Max Gurtovoy <maxg@mellanox.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/core.c | 18 ++++++++++++
 drivers/nvme/host/nvme.h |  9 +-----
 drivers/nvme/host/pci.c  | 75 +-----------------------------------------------
 3 files changed, 20 insertions(+), 82 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 16c8b86fe95d..8f3b1ad1ee14 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -601,6 +601,8 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 			if (WARN_ON_ONCE(!nvme_ns_has_pi(ns)))
 				return BLK_STS_NOTSUPP;
 			control |= NVME_RW_PRINFO_PRACT;
+		} else if (req_op(req) == REQ_OP_WRITE) {
+			t10_pi_prepare(req, ns->pi_type);
 		}
 
 		switch (ns->pi_type) {
@@ -621,6 +623,22 @@ static inline blk_status_t nvme_setup_rw(struct nvme_ns *ns,
 	return 0;
 }
 
+void nvme_cleanup_cmd(struct request *req)
+{
+	if (blk_integrity_rq(req) && req_op(req) == REQ_OP_READ &&
+	    nvme_req(req)->status == 0) {
+		struct nvme_ns *ns = req->rq_disk->private_data;
+
+		t10_pi_complete(req, ns->pi_type,
+				blk_rq_bytes(req) >> ns->lba_shift);
+	}
+	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
+		kfree(page_address(req->special_vec.bv_page) +
+		      req->special_vec.bv_offset);
+	}
+}
+EXPORT_SYMBOL_GPL(nvme_cleanup_cmd);
+
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd)
 {
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index 4ad0c8ad2a27..cf970f9543a6 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -364,14 +364,6 @@ static inline u64 nvme_block_nr(struct nvme_ns *ns, sector_t sector)
 	return (sector >> (ns->lba_shift - 9));
 }
 
-static inline void nvme_cleanup_cmd(struct request *req)
-{
-	if (req->rq_flags & RQF_SPECIAL_PAYLOAD) {
-		kfree(page_address(req->special_vec.bv_page) +
-		      req->special_vec.bv_offset);
-	}
-}
-
 static inline void nvme_end_request(struct request *req, __le16 status,
 		union nvme_result result)
 {
@@ -428,6 +420,7 @@ void nvme_start_freeze(struct nvme_ctrl *ctrl);
 #define NVME_QID_ANY -1
 struct request *nvme_alloc_request(struct request_queue *q,
 		struct nvme_command *cmd, blk_mq_req_flags_t flags, int qid);
+void nvme_cleanup_cmd(struct request *req);
 blk_status_t nvme_setup_cmd(struct nvme_ns *ns, struct request *req,
 		struct nvme_command *cmd);
 int nvme_submit_sync_cmd(struct request_queue *q, struct nvme_command *cmd,
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8dcae11bbf3a..0848e7143311 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -537,73 +537,6 @@ static void nvme_free_iod(struct nvme_dev *dev, struct request *req)
 		mempool_free(iod->sg, dev->iod_mempool);
 }
 
-#ifdef CONFIG_BLK_DEV_INTEGRITY
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == v)
-		pi->ref_tag = cpu_to_be32(p);
-}
-
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-	if (be32_to_cpu(pi->ref_tag) == p)
-		pi->ref_tag = cpu_to_be32(v);
-}
-
-/**
- * nvme_dif_remap - remaps ref tags to bip seed and physical lba
- *
- * The virtual start sector is the one that was originally submitted by the
- * block layer.	Due to partitioning, MD/DM cloning, etc. the actual physical
- * start sector may be different. Remap protection information to match the
- * physical LBA on writes, and back to the original seed on reads.
- *
- * Type 0 and 3 do not have a ref tag, so no remapping required.
- */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-	struct nvme_ns *ns = req->rq_disk->private_data;
-	struct bio_integrity_payload *bip;
-	struct t10_pi_tuple *pi;
-	void *p, *pmap;
-	u32 i, nlb, ts, phys, virt;
-
-	if (!ns->pi_type || ns->pi_type == NVME_NS_DPS_PI_TYPE3)
-		return;
-
-	bip = bio_integrity(req->bio);
-	if (!bip)
-		return;
-
-	pmap = kmap_atomic(bip->bip_vec->bv_page) + bip->bip_vec->bv_offset;
-
-	p = pmap;
-	virt = bip_get_seed(bip);
-	phys = nvme_block_nr(ns, blk_rq_pos(req));
-	nlb = (blk_rq_bytes(req) >> ns->lba_shift);
-	ts = ns->disk->queue->integrity.tuple_size;
-
-	for (i = 0; i < nlb; i++, virt++, phys++) {
-		pi = (struct t10_pi_tuple *)p;
-		dif_swap(phys, virt, pi);
-		p += ts;
-	}
-	kunmap_atomic(pmap);
-}
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-static void nvme_dif_remap(struct request *req,
-			void (*dif_swap)(u32 p, u32 v, struct t10_pi_tuple *pi))
-{
-}
-static void nvme_dif_prep(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-static void nvme_dif_complete(u32 p, u32 v, struct t10_pi_tuple *pi)
-{
-}
-#endif
-
 static void nvme_print_sgl(struct scatterlist *sgl, int nents)
 {
 	int i;
@@ -829,9 +762,6 @@ static blk_status_t nvme_map_data(struct nvme_dev *dev, struct request *req,
 		if (blk_rq_map_integrity_sg(q, req->bio, &iod->meta_sg) != 1)
 			goto out_unmap;
 
-		if (req_op(req) == REQ_OP_WRITE)
-			nvme_dif_remap(req, nvme_dif_prep);
-
 		if (!dma_map_sg(dev->dev, &iod->meta_sg, 1, dma_dir))
 			goto out_unmap;
 	}
@@ -854,11 +784,8 @@ static void nvme_unmap_data(struct nvme_dev *dev, struct request *req)
 
 	if (iod->nents) {
 		dma_unmap_sg(dev->dev, iod->sg, iod->nents, dma_dir);
-		if (blk_integrity_rq(req)) {
-			if (req_op(req) == REQ_OP_READ)
-				nvme_dif_remap(req, nvme_dif_complete);
+		if (blk_integrity_rq(req))
 			dma_unmap_sg(dev->dev, &iod->meta_sg, 1, dma_dir);
-		}
 	}
 
 	nvme_cleanup_cmd(req);
-- 
cgit v1.2.3


From 54648cf1ec2d7f4b6a71767799c45676a138ca24 Mon Sep 17 00:00:00 2001
From: xiao jin <jin.xiao@intel.com>
Date: Mon, 30 Jul 2018 14:11:12 +0800
Subject: block: blk_init_allocated_queue() set q->fq as NULL in the fail case

We find the memory use-after-free issue in __blk_drain_queue()
on the kernel 4.14. After read the latest kernel 4.18-rc6 we
think it has the same problem.

Memory is allocated for q->fq in the blk_init_allocated_queue().
If the elevator init function called with error return, it will
run into the fail case to free the q->fq.

Then the __blk_drain_queue() uses the same memory after the free
of the q->fq, it will lead to the unpredictable event.

The patch is to set q->fq as NULL in the fail case of
blk_init_allocated_queue().

Fixes: commit 7c94e1c157a2 ("block: introduce blk_flush_queue to drive flush machinery")
Cc: <stable@vger.kernel.org>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: xiao jin <jin.xiao@intel.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/block/blk-core.c b/block/blk-core.c
index 03a4ea93a5f3..23cd1b7770e7 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1184,6 +1184,7 @@ out_exit_flush_rq:
 		q->exit_rq_fn(q, q->fq->flush_rq);
 out_free_flush_queue:
 	blk_free_flush_queue(q->fq);
+	q->fq = NULL;
 	return -ENOMEM;
 }
 EXPORT_SYMBOL(blk_init_allocated_queue);
-- 
cgit v1.2.3


From 03d677c50ad7da146571504f25260da61f4158ad Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Mon, 9 Jul 2018 12:20:26 +0200
Subject: mt7601u: use sw encryption for hw unsupported ciphers

Fall back to software encryption for hw unsupported ciphers in order
to enable 802.11w

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt7601u/main.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt7601u/main.c b/drivers/net/wireless/mediatek/mt7601u/main.c
index 7b21016012c3..0f1789020960 100644
--- a/drivers/net/wireless/mediatek/mt7601u/main.c
+++ b/drivers/net/wireless/mediatek/mt7601u/main.c
@@ -308,6 +308,17 @@ mt7601u_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	int idx = key->keyidx;
 	int ret;
 
+	/* fall back to sw encryption for unsupported ciphers */
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+	case WLAN_CIPHER_SUITE_WEP104:
+	case WLAN_CIPHER_SUITE_TKIP:
+	case WLAN_CIPHER_SUITE_CCMP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	if (cmd == SET_KEY) {
 		key->hw_key_idx = wcid->idx;
 		wcid->hw_key_idx = idx;
-- 
cgit v1.2.3


From 53c2cb8df3278481006255660ffc571ff4c5e0f1 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Mon, 9 Jul 2018 12:20:27 +0200
Subject: mt7601u: expose 802.11w support

Set MFP_CAPABLE bit in hw flag capabilities exported by the driver

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt7601u/init.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt7601u/init.c b/drivers/net/wireless/mediatek/mt7601u/init.c
index d3b611aaf061..faea99b7a445 100644
--- a/drivers/net/wireless/mediatek/mt7601u/init.c
+++ b/drivers/net/wireless/mediatek/mt7601u/init.c
@@ -603,6 +603,7 @@ int mt7601u_register_device(struct mt7601u_dev *dev)
 	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
 	ieee80211_hw_set(hw, AMPDU_AGGREGATION);
 	ieee80211_hw_set(hw, SUPPORTS_RC_TABLE);
+	ieee80211_hw_set(hw, MFP_CAPABLE);
 	hw->max_rates = 1;
 	hw->max_report_rates = 7;
 	hw->max_rate_tries = 1;
-- 
cgit v1.2.3


From f24909ab394347e7a3f329ad5c93f470a1d238a9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Wed, 11 Jul 2018 22:02:22 +0200
Subject: mt76x2: add frame protection support

Introduce mac80211 rts threshold handler in order to add frame
protection support to mt76x2 driver

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2.h      |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.c  | 30 ++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2_main.c | 16 +++++++++++++
 3 files changed, 47 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 71fcfa44fb2e..40e57073923e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -222,6 +222,7 @@ int mt76x2_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 			  u32 *tx_info);
 void mt76x2_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 			    struct mt76_queue_entry *e, bool flush);
+void mt76x2_mac_set_tx_protection(struct mt76x2_dev *dev, u32 val);
 
 void mt76x2_pre_tbtt_tasklet(unsigned long arg);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
index fc9af79b3e69..e5e92f79f28a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
@@ -854,3 +854,33 @@ void mt76x2_mac_work(struct work_struct *work)
 	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->mac_work,
 				     MT_CALIBRATE_INTERVAL);
 }
+
+void mt76x2_mac_set_tx_protection(struct mt76x2_dev *dev, u32 val)
+{
+	u32 data = 0;
+
+	if (val != ~0)
+		data = FIELD_PREP(MT_PROT_CFG_CTRL, 1) |
+		       MT_PROT_CFG_RTS_THRESH;
+
+	mt76_rmw_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH, val);
+
+	mt76_rmw(dev, MT_CCK_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_OFDM_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_MM20_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_MM40_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_GF20_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_GF40_PROT_CFG,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG6,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG7,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+	mt76_rmw(dev, MT_TX_PROT_CFG8,
+		 MT_PROT_CFG_CTRL | MT_PROT_CFG_RTS_THRESH, data);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
index 3c0ebe6d231c..1f4d3e5ae64b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
@@ -605,6 +605,21 @@ static int mt76x2_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant,
 	return 0;
 }
 
+static int
+mt76x2_set_rts_threshold(struct ieee80211_hw *hw, u32 val)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	if (val != ~0 && val > 0xffff)
+		return -EINVAL;
+
+	mutex_lock(&dev->mutex);
+	mt76x2_mac_set_tx_protection(dev, val);
+	mutex_unlock(&dev->mutex);
+
+	return 0;
+}
+
 const struct ieee80211_ops mt76x2_ops = {
 	.tx = mt76x2_tx,
 	.start = mt76x2_start,
@@ -631,5 +646,6 @@ const struct ieee80211_ops mt76x2_ops = {
 	.set_tim = mt76x2_set_tim,
 	.set_antenna = mt76x2_set_antenna,
 	.get_antenna = mt76x2_get_antenna,
+	.set_rts_threshold = mt76x2_set_rts_threshold,
 };
 
-- 
cgit v1.2.3


From d0db2f7a02e45dd4791b70404bd90874b20c38a4 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Thu, 12 Jul 2018 10:50:01 +0200
Subject: mt76x2: fix CCK protection control frame rate

Use 11M as tx rate for CCK protection control frames

Fixes: 7bc04215a66b ("mt76: add driver code for MT76x2e")
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_init.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
index 79ab93613e06..8ab9788464e8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
@@ -84,7 +84,13 @@ mt76x2_write_reg_pairs(struct mt76x2_dev *dev,
 static void
 mt76_write_mac_initvals(struct mt76x2_dev *dev)
 {
-#define DEFAULT_PROT_CFG				\
+#define DEFAULT_PROT_CFG_CCK				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x3) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |		\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
+	 MT_PROT_CFG_RTS_THRESH)
+
+#define DEFAULT_PROT_CFG_OFDM				\
 	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
 	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
 	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
@@ -159,8 +165,8 @@ mt76_write_mac_initvals(struct mt76x2_dev *dev)
 		{ MT_HT_CTRL_CFG,		0x000001ff },
 	};
 	struct mt76x2_reg_pair prot_vals[] = {
-		{ MT_CCK_PROT_CFG,		DEFAULT_PROT_CFG },
-		{ MT_OFDM_PROT_CFG,		DEFAULT_PROT_CFG },
+		{ MT_CCK_PROT_CFG,		DEFAULT_PROT_CFG_CCK },
+		{ MT_OFDM_PROT_CFG,		DEFAULT_PROT_CFG_OFDM },
 		{ MT_MM20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
 		{ MT_MM40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
 		{ MT_GF20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
-- 
cgit v1.2.3


From fcacbc3f511338842dd177e2d53d457f9741543b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Jul 2018 16:51:50 -0700
Subject: xfs: remove if_real_bytes

The field is only used for asserts, and to track if we really need to do
realloc when growing the inode fork data.  But the krealloc function
already performs this check internally, so there is no need to keep track
of the real allocation size.

This will free space in the inode fork for keeping a sequence counter of
changes to the extent list.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_inode_fork.c | 19 ++++---------------
 fs/xfs/libxfs/xfs_inode_fork.h |  1 -
 fs/xfs/xfs_inode.c             |  3 +--
 fs/xfs/xfs_inode_item.c        |  4 ----
 4 files changed, 5 insertions(+), 22 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 183ec0cb8921..dee85b0f8846 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -158,7 +158,6 @@ xfs_init_local_fork(
 	}
 
 	ifp->if_bytes = size;
-	ifp->if_real_bytes = real_size;
 	ifp->if_flags &= ~(XFS_IFEXTENTS | XFS_IFBROOT);
 	ifp->if_flags |= XFS_IFINLINE;
 }
@@ -226,7 +225,6 @@ xfs_iformat_extents(
 		return -EFSCORRUPTED;
 	}
 
-	ifp->if_real_bytes = 0;
 	ifp->if_bytes = 0;
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
@@ -317,7 +315,6 @@ xfs_iformat_btree(
 	ifp->if_flags &= ~XFS_IFEXTENTS;
 	ifp->if_flags |= XFS_IFBROOT;
 
-	ifp->if_real_bytes = 0;
 	ifp->if_bytes = 0;
 	ifp->if_u1.if_root = NULL;
 	ifp->if_height = 0;
@@ -501,7 +498,6 @@ xfs_idata_realloc(
 		 */
 		real_size = roundup(new_size, 4);
 		if (ifp->if_u1.if_data == NULL) {
-			ASSERT(ifp->if_real_bytes == 0);
 			ifp->if_u1.if_data = kmem_alloc(real_size,
 							KM_SLEEP | KM_NOFS);
 		} else {
@@ -509,15 +505,12 @@ xfs_idata_realloc(
 			 * Only do the realloc if the underlying size
 			 * is really changing.
 			 */
-			if (ifp->if_real_bytes != real_size) {
-				ifp->if_u1.if_data =
-					kmem_realloc(ifp->if_u1.if_data,
-							real_size,
-							KM_SLEEP | KM_NOFS);
-			}
+			ifp->if_u1.if_data =
+				kmem_realloc(ifp->if_u1.if_data,
+						real_size,
+						KM_SLEEP | KM_NOFS);
 		}
 	}
-	ifp->if_real_bytes = real_size;
 	ifp->if_bytes = new_size;
 	ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
 }
@@ -543,17 +536,13 @@ xfs_idestroy_fork(
 	 */
 	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
 		if (ifp->if_u1.if_data != NULL) {
-			ASSERT(ifp->if_real_bytes != 0);
 			kmem_free(ifp->if_u1.if_data);
 			ifp->if_u1.if_data = NULL;
-			ifp->if_real_bytes = 0;
 		}
 	} else if ((ifp->if_flags & XFS_IFEXTENTS) && ifp->if_height) {
 		xfs_iext_destroy(ifp);
 	}
 
-	ASSERT(ifp->if_real_bytes == 0);
-
 	if (whichfork == XFS_ATTR_FORK) {
 		kmem_zone_free(xfs_ifork_zone, ip->i_afp);
 		ip->i_afp = NULL;
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 781b1603df5e..46242052aad0 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -14,7 +14,6 @@ struct xfs_dinode;
  */
 typedef struct xfs_ifork {
 	int			if_bytes;	/* bytes in if_u1 */
-	int			if_real_bytes;	/* bytes allocated in if_u1 */
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	unsigned char		if_flags;	/* per-fork flags */
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 64c694d2b2a5..54fcfdfc748c 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -927,7 +927,7 @@ xfs_ialloc(
 	case S_IFLNK:
 		ip->i_d.di_format = XFS_DINODE_FMT_EXTENTS;
 		ip->i_df.if_flags = XFS_IFEXTENTS;
-		ip->i_df.if_bytes = ip->i_df.if_real_bytes = 0;
+		ip->i_df.if_bytes = 0;
 		ip->i_df.if_u1.if_root = NULL;
 		break;
 	default:
@@ -1841,7 +1841,6 @@ xfs_inactive(
 	 * to clean up here.
 	 */
 	if (VFS_I(ip)->i_mode == 0) {
-		ASSERT(ip->i_df.if_real_bytes == 0);
 		ASSERT(ip->i_df.if_broot_bytes == 0);
 		return;
 	}
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 2389c34c172d..fa1c4fe2ffbf 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -194,8 +194,6 @@ xfs_inode_item_format_data_fork(
 			 * to be there by xfs_idata_realloc().
 			 */
 			data_bytes = roundup(ip->i_df.if_bytes, 4);
-			ASSERT(ip->i_df.if_real_bytes == 0 ||
-			       ip->i_df.if_real_bytes >= data_bytes);
 			ASSERT(ip->i_df.if_u1.if_data != NULL);
 			ASSERT(ip->i_d.di_size > 0);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
@@ -280,8 +278,6 @@ xfs_inode_item_format_attr_fork(
 			 * to be there by xfs_idata_realloc().
 			 */
 			data_bytes = roundup(ip->i_afp->if_bytes, 4);
-			ASSERT(ip->i_afp->if_real_bytes == 0 ||
-			       ip->i_afp->if_real_bytes >= data_bytes);
 			ASSERT(ip->i_afp->if_u1.if_data != NULL);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
 					ip->i_afp->if_u1.if_data,
-- 
cgit v1.2.3


From 1216b58b353fbf5529454b442cebb3c8f14d93da Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Jul 2018 16:51:50 -0700
Subject: xfs: simplify xfs_idata_realloc

Streamline the code and take advantage of the fact that kmem_realloc
through krealloc will be have like a normal allocation if passing in a
NULL old pointer.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_inode_fork.c | 55 +++++++++++++++---------------------------
 1 file changed, 19 insertions(+), 36 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index dee85b0f8846..a0e3fb804605 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -468,51 +468,34 @@ xfs_iroot_realloc(
  */
 void
 xfs_idata_realloc(
-	xfs_inode_t	*ip,
-	int		byte_diff,
-	int		whichfork)
+	struct xfs_inode	*ip,
+	int			byte_diff,
+	int			whichfork)
 {
-	xfs_ifork_t	*ifp;
-	int		new_size;
-	int		real_size;
-
-	if (byte_diff == 0) {
-		return;
-	}
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	int			new_size = (int)ifp->if_bytes + byte_diff;
 
-	ifp = XFS_IFORK_PTR(ip, whichfork);
-	new_size = (int)ifp->if_bytes + byte_diff;
 	ASSERT(new_size >= 0);
+	ASSERT(new_size <= XFS_IFORK_SIZE(ip, whichfork));
+
+	if (byte_diff == 0)
+		return;
 
 	if (new_size == 0) {
 		kmem_free(ifp->if_u1.if_data);
 		ifp->if_u1.if_data = NULL;
-		real_size = 0;
-	} else {
-		/*
-		 * Stuck with malloc/realloc.
-		 * For inline data, the underlying buffer must be
-		 * a multiple of 4 bytes in size so that it can be
-		 * logged and stay on word boundaries.  We enforce
-		 * that here.
-		 */
-		real_size = roundup(new_size, 4);
-		if (ifp->if_u1.if_data == NULL) {
-			ifp->if_u1.if_data = kmem_alloc(real_size,
-							KM_SLEEP | KM_NOFS);
-		} else {
-			/*
-			 * Only do the realloc if the underlying size
-			 * is really changing.
-			 */
-			ifp->if_u1.if_data =
-				kmem_realloc(ifp->if_u1.if_data,
-						real_size,
-						KM_SLEEP | KM_NOFS);
-		}
+		ifp->if_bytes = 0;
+		return;
 	}
+
+	/*
+	 * For inline data, the underlying buffer must be a multiple of 4 bytes
+	 * in size so that it can be logged and stay on word boundaries.
+	 * We enforce that here.
+	 */
+	ifp->if_u1.if_data = kmem_realloc(ifp->if_u1.if_data,
+			roundup(new_size, 4), KM_SLEEP | KM_NOFS);
 	ifp->if_bytes = new_size;
-	ASSERT(ifp->if_bytes <= XFS_IFORK_SIZE(ip, whichfork));
 }
 
 void
-- 
cgit v1.2.3


From 3ba738df25239f877f6a98ce1cc925fa7e924cd3 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Jul 2018 16:51:50 -0700
Subject: xfs: remove the xfs_ifork_t typedef

We only have a few more callers left, so seize the opportunity and kill
it off.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c  |  6 +++---
 fs/xfs/libxfs/xfs_bmap.c       | 18 +++++++++---------
 fs/xfs/libxfs/xfs_inode_fork.c |  8 ++++----
 fs/xfs/libxfs/xfs_inode_fork.h |  4 ++--
 fs/xfs/xfs_icache.c            |  2 +-
 fs/xfs/xfs_inode.h             |  6 +++---
 fs/xfs/xfs_super.c             |  2 +-
 7 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 088ffcd22fa2..4e7ef79a83c7 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -528,7 +528,7 @@ xfs_attr_shortform_create(xfs_da_args_t *args)
 {
 	xfs_attr_sf_hdr_t *hdr;
 	xfs_inode_t *dp;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_create(args);
 
@@ -563,7 +563,7 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
 	int i, offset, size;
 	xfs_mount_t *mp;
 	xfs_inode_t *dp;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_add(args);
 
@@ -704,7 +704,7 @@ xfs_attr_shortform_lookup(xfs_da_args_t *args)
 	xfs_attr_shortform_t *sf;
 	xfs_attr_sf_entry_t *sfe;
 	int i;
-	xfs_ifork_t *ifp;
+	struct xfs_ifork *ifp;
 
 	trace_xfs_attr_sf_lookup(args);
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 92cd064a2589..a85c0445b38f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -326,7 +326,7 @@ xfs_bmap_check_leaf_extents(
 	xfs_buf_t		*bp;	/* buffer for "block" */
 	int			error;	/* error return value */
 	xfs_extnum_t		i=0, j;	/* index into the extents list */
-	xfs_ifork_t		*ifp;	/* fork structure */
+	struct xfs_ifork	*ifp;	/* fork structure */
 	int			level;	/* btree level, for checking */
 	xfs_mount_t		*mp;	/* file system mount structure */
 	__be64			*pp;	/* pointer to block address */
@@ -594,7 +594,7 @@ xfs_bmap_btree_to_extents(
 	xfs_fsblock_t		cbno;	/* child block number */
 	xfs_buf_t		*cbp;	/* child block's buffer */
 	int			error;	/* error return value */
-	xfs_ifork_t		*ifp;	/* inode fork data */
+	struct xfs_ifork	*ifp;	/* inode fork data */
 	xfs_mount_t		*mp;	/* mount point structure */
 	__be64			*pp;	/* ptr to block address */
 	struct xfs_btree_block	*rblock;/* root btree block */
@@ -817,7 +817,7 @@ xfs_bmap_local_to_extents(
 {
 	int		error = 0;
 	int		flags;		/* logging flags returned */
-	xfs_ifork_t	*ifp;		/* inode fork pointer */
+	struct xfs_ifork *ifp;		/* inode fork pointer */
 	xfs_alloc_arg_t	args;		/* allocation arguments */
 	xfs_buf_t	*bp;		/* buffer for extent block */
 	struct xfs_bmbt_irec rec;
@@ -1471,7 +1471,7 @@ xfs_bmap_one_block(
 	xfs_inode_t	*ip,		/* incore inode */
 	int		whichfork)	/* data or attr fork */
 {
-	xfs_ifork_t	*ifp;		/* inode fork pointer */
+	struct xfs_ifork *ifp;		/* inode fork pointer */
 	int		rval;		/* return value */
 	xfs_bmbt_irec_t	s;		/* internal version of extent */
 	struct xfs_iext_cursor icur;
@@ -1509,7 +1509,7 @@ xfs_bmap_add_extent_delay_real(
 	struct xfs_bmbt_irec	*new = &bma->got;
 	int			error;	/* error return value */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
 	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
 					/* left is 0, right is 1, prev is 2 */
@@ -2018,7 +2018,7 @@ xfs_bmap_add_extent_unwritten_real(
 	xfs_btree_cur_t		*cur;	/* btree cursor */
 	int			error;	/* error return value */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_fileoff_t		new_endoff;	/* end offset of new entry */
 	xfs_bmbt_irec_t		r[3];	/* neighbor extent entries */
 					/* left is 0, right is 1, prev is 2 */
@@ -2486,7 +2486,7 @@ xfs_bmap_add_extent_hole_delay(
 	struct xfs_iext_cursor	*icur,
 	xfs_bmbt_irec_t		*new)	/* new data to add to file extents */
 {
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_bmbt_irec_t		left;	/* left neighbor extent entry */
 	xfs_filblks_t		newlen=0;	/* new indirect size */
 	xfs_filblks_t		oldlen=0;	/* old indirect size */
@@ -4844,7 +4844,7 @@ xfs_bmap_del_extent_real(
 	struct xfs_bmbt_irec	got;	/* current extent entry */
 	xfs_fileoff_t		got_endoff;	/* first offset past got */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
+	struct xfs_ifork	*ifp;	/* inode fork pointer */
 	xfs_mount_t		*mp;	/* mount structure */
 	xfs_filblks_t		nblks;	/* quota/sb block count */
 	xfs_bmbt_irec_t		new;	/* new record to be inserted */
@@ -5092,7 +5092,7 @@ __xfs_bunmapi(
 	int			error;		/* error return value */
 	xfs_extnum_t		extno;		/* extent number in list */
 	struct xfs_bmbt_irec	got;		/* current extent record */
-	xfs_ifork_t		*ifp;		/* inode fork pointer */
+	struct xfs_ifork	*ifp;		/* inode fork pointer */
 	int			isrt;		/* freeing in rt area */
 	int			logflags;	/* transaction logging flags */
 	xfs_extlen_t		mod;		/* rt extent offset */
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index a0e3fb804605..f9acf1d436f6 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -269,7 +269,7 @@ xfs_iformat_btree(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_bmdr_block_t	*dfp;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	/* REFERENCED */
 	int			nrecs;
 	int			size;
@@ -347,7 +347,7 @@ xfs_iroot_realloc(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	int			cur_max;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	struct xfs_btree_block	*new_broot;
 	int			new_max;
 	size_t			new_size;
@@ -503,7 +503,7 @@ xfs_idestroy_fork(
 	xfs_inode_t	*ip,
 	int		whichfork)
 {
-	xfs_ifork_t	*ifp;
+	struct xfs_ifork	*ifp;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if (ifp->if_broot != NULL) {
@@ -592,7 +592,7 @@ xfs_iflush_fork(
 	int			whichfork)
 {
 	char			*cp;
-	xfs_ifork_t		*ifp;
+	struct xfs_ifork	*ifp;
 	xfs_mount_t		*mp;
 	static const short	brootflag[2] =
 		{ XFS_ILOG_DBROOT, XFS_ILOG_ABROOT };
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 46242052aad0..1492143371f3 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -12,7 +12,7 @@ struct xfs_dinode;
 /*
  * File incore extent information, present for each of data & attr forks.
  */
-typedef struct xfs_ifork {
+struct xfs_ifork {
 	int			if_bytes;	/* bytes in if_u1 */
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	short			if_broot_bytes;	/* bytes allocated for root */
@@ -22,7 +22,7 @@ typedef struct xfs_ifork {
 		void		*if_root;	/* extent tree root */
 		char		*if_data;	/* inline file data */
 	} if_u1;
-} xfs_ifork_t;
+};
 
 /*
  * Per-fork incore inode flags.
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 8de94ecd73ae..e5591f5ebe15 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -66,7 +66,7 @@ xfs_inode_alloc(
 	ip->i_cowfp = NULL;
 	ip->i_cnextents = 0;
 	ip->i_cformat = XFS_DINODE_FMT_EXTENTS;
-	memset(&ip->i_df, 0, sizeof(xfs_ifork_t));
+	memset(&ip->i_df, 0, sizeof(ip->i_df));
 	ip->i_flags = 0;
 	ip->i_delayed_blks = 0;
 	memset(&ip->i_d, 0, sizeof(ip->i_d));
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 8db34d6f2835..a67efdac70a6 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -34,9 +34,9 @@ typedef struct xfs_inode {
 	struct xfs_imap		i_imap;		/* location for xfs_imap() */
 
 	/* Extent information. */
-	xfs_ifork_t		*i_afp;		/* attribute fork pointer */
-	xfs_ifork_t		*i_cowfp;	/* copy on write extents */
-	xfs_ifork_t		i_df;		/* data fork */
+	struct xfs_ifork	*i_afp;		/* attribute fork pointer */
+	struct xfs_ifork	*i_cowfp;	/* copy on write extents */
+	struct xfs_ifork	i_df;		/* data fork */
 
 	/* operations vectors */
 	const struct xfs_dir_ops *d_ops;		/* directory ops vector */
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index d2ebacd5975c..207ee302b1bb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1860,7 +1860,7 @@ xfs_init_zones(void)
 	if (!xfs_da_state_zone)
 		goto out_destroy_btree_cur_zone;
 
-	xfs_ifork_zone = kmem_zone_init(sizeof(xfs_ifork_t), "xfs_ifork");
+	xfs_ifork_zone = kmem_zone_init(sizeof(struct xfs_ifork), "xfs_ifork");
 	if (!xfs_ifork_zone)
 		goto out_destroy_da_state_zone;
 
-- 
cgit v1.2.3


From 51d626903083f7bd651d38b031775740ed41758c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Jul 2018 16:51:51 -0700
Subject: xfs: introduce a new xfs_inode_has_cow_data helper

We have a few places that already check if an inode has actual data in
the COW fork to avoid work on reflink inodes that do not actually have
outstanding COW blocks.  There are a few more places that can avoid
working if doing the same check, so add a documented helper for this
condition and use it in all places where it makes sense.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c      |  4 ++--
 fs/xfs/xfs_bmap_util.c |  2 +-
 fs/xfs/xfs_icache.c    | 10 ++++------
 fs/xfs/xfs_inode.c     |  3 +--
 fs/xfs/xfs_inode.h     |  9 +++++++++
 fs/xfs/xfs_reflink.c   |  2 +-
 6 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f4d3252236c1..814100d27343 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -338,7 +338,7 @@ xfs_map_blocks(
 	imap_valid = offset_fsb >= wpc->imap.br_startoff &&
 		     offset_fsb < wpc->imap.br_startoff + wpc->imap.br_blockcount;
 	if (imap_valid &&
-	    (!xfs_is_reflink_inode(ip) || wpc->io_type == XFS_IO_COW))
+	    (!xfs_inode_has_cow_data(ip) || wpc->io_type == XFS_IO_COW))
 		return 0;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -363,7 +363,7 @@ xfs_map_blocks(
 	 * Check if this is offset is covered by a COW extents, and if yes use
 	 * it directly instead of looking up anything in the data fork.
 	 */
-	if (xfs_is_reflink_inode(ip) &&
+	if (xfs_inode_has_cow_data(ip) &&
 	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap) &&
 	    imap.br_startoff <= offset_fsb) {
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index c32ec17048f5..412dc58ae54d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1263,7 +1263,7 @@ xfs_prepare_shift(
 	 * we've flushed all the dirty data out to disk to avoid having
 	 * CoW extents at the wrong offsets.
 	 */
-	if (xfs_is_reflink_inode(ip)) {
+	if (xfs_inode_has_cow_data(ip)) {
 		error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
 				true);
 		if (error)
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index e5591f5ebe15..245483cc282b 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -1697,14 +1697,13 @@ xfs_inode_clear_eofblocks_tag(
  */
 static bool
 xfs_prep_free_cowblocks(
-	struct xfs_inode	*ip,
-	struct xfs_ifork	*ifp)
+	struct xfs_inode	*ip)
 {
 	/*
 	 * Just clear the tag if we have an empty cow fork or none at all. It's
 	 * possible the inode was fully unshared since it was originally tagged.
 	 */
-	if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) {
+	if (!xfs_inode_has_cow_data(ip)) {
 		trace_xfs_inode_free_cowblocks_invalid(ip);
 		xfs_inode_clear_cowblocks_tag(ip);
 		return false;
@@ -1742,11 +1741,10 @@ xfs_inode_free_cowblocks(
 	void			*args)
 {
 	struct xfs_eofblocks	*eofb = args;
-	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	int			match;
 	int			ret = 0;
 
-	if (!xfs_prep_free_cowblocks(ip, ifp))
+	if (!xfs_prep_free_cowblocks(ip))
 		return 0;
 
 	if (eofb) {
@@ -1771,7 +1769,7 @@ xfs_inode_free_cowblocks(
 	 * Check again, nobody else should be able to dirty blocks or change
 	 * the reflink iflag now that we have the first two locks held.
 	 */
-	if (xfs_prep_free_cowblocks(ip, ifp))
+	if (xfs_prep_free_cowblocks(ip))
 		ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 54fcfdfc748c..5fc1815c2b62 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1832,7 +1832,6 @@ xfs_inactive(
 	xfs_inode_t	*ip)
 {
 	struct xfs_mount	*mp;
-	struct xfs_ifork	*cow_ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	int			error;
 	int			truncate = 0;
 
@@ -1853,7 +1852,7 @@ xfs_inactive(
 		return;
 
 	/* Try to clean out the cow blocks if there are any. */
-	if (xfs_is_reflink_inode(ip) && cow_ifp->if_bytes > 0)
+	if (xfs_inode_has_cow_data(ip))
 		xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
 
 	if (VFS_I(ip)->i_nlink != 0) {
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index a67efdac70a6..79a3e61a6991 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -198,6 +198,15 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
 	return ip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
 }
 
+/*
+ * Check if an inode has any data in the COW fork.  This might be often false
+ * even for inodes with the reflink flag when there is no pending COW operation.
+ */
+static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
+{
+	return ip->i_cowfp && ip->i_cowfp->if_bytes;
+}
+
 /*
  * In-core inode flags.
  */
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 68b6921dc3f6..9a0a56526266 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -478,7 +478,7 @@ xfs_reflink_cancel_cow_blocks(
 	struct xfs_iext_cursor		icur;
 	int				error = 0;
 
-	if (!xfs_is_reflink_inode(ip))
+	if (!xfs_inode_has_cow_data(ip))
 		return 0;
 	if (!xfs_iext_lookup_extent_before(ip, ifp, &end_fsb, &icur, &got))
 		return 0;
-- 
cgit v1.2.3


From 45e41bc5259242921da755c60c705ff368beb8ce Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 30 Jul 2018 15:45:46 +0100
Subject: spi: omap2-mcspi: remove several redundant variables

Variable count, l, mcspi and spi_cntrl are being assigned but are
never used hence they are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'count' set but not used [-Wunused-but-set-variable]
warning: variable 'l' set but not used [-Wunused-but-set-variable]
warning: variable 'mcspi' set but not used [-Wunused-but-set-variable]
warning: variable 'spi_cntrl' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-omap2-mcspi.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/spi/spi-omap2-mcspi.c b/drivers/spi/spi-omap2-mcspi.c
index 6c628a54e946..508c61c669e7 100644
--- a/drivers/spi/spi-omap2-mcspi.c
+++ b/drivers/spi/spi-omap2-mcspi.c
@@ -398,11 +398,9 @@ static void omap2_mcspi_tx_dma(struct spi_device *spi,
 {
 	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_dma  *mcspi_dma;
-	unsigned int		count;
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-	count = xfer->len;
 
 	if (mcspi_dma->dma_tx) {
 		struct dma_async_tx_descriptor *tx;
@@ -582,7 +580,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 	struct omap2_mcspi_dma  *mcspi_dma;
 	unsigned int		count;
-	u32			l;
 	u8			*rx;
 	const u8		*tx;
 	struct dma_slave_config	cfg;
@@ -595,8 +592,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 
 	mcspi = spi_master_get_devdata(spi->master);
 	mcspi_dma = &mcspi->dma_channels[spi->chip_select];
-	l = mcspi_cached_chconf0(spi);
-
 
 	if (cs->word_len <= 8) {
 		width = DMA_SLAVE_BUSWIDTH_1_BYTE;
@@ -676,7 +671,6 @@ omap2_mcspi_txrx_dma(struct spi_device *spi, struct spi_transfer *xfer)
 static unsigned
 omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
 {
-	struct omap2_mcspi	*mcspi;
 	struct omap2_mcspi_cs	*cs = spi->controller_state;
 	unsigned int		count, c;
 	u32			l;
@@ -686,7 +680,6 @@ omap2_mcspi_txrx_pio(struct spi_device *spi, struct spi_transfer *xfer)
 	void __iomem		*chstat_reg;
 	int			word_len;
 
-	mcspi = spi_master_get_devdata(spi->master);
 	count = xfer->len;
 	c = count;
 	word_len = cs->word_len;
@@ -883,13 +876,11 @@ static int omap2_mcspi_setup_transfer(struct spi_device *spi,
 {
 	struct omap2_mcspi_cs *cs = spi->controller_state;
 	struct omap2_mcspi *mcspi;
-	struct spi_master *spi_cntrl;
 	u32 l = 0, clkd = 0, div, extclk = 0, clkg = 0;
 	u8 word_len = spi->bits_per_word;
 	u32 speed_hz = spi->max_speed_hz;
 
 	mcspi = spi_master_get_devdata(spi->master);
-	spi_cntrl = mcspi->master;
 
 	if (t != NULL && t->bits_per_word)
 		word_len = t->bits_per_word;
-- 
cgit v1.2.3


From baec8eb323cd59d1bfe148a287610819d5897838 Mon Sep 17 00:00:00 2001
From: Ionela Voinescu <ionela.voinescu@imgtec.com>
Date: Sun, 22 Jul 2018 23:20:06 +0200
Subject: spi: img-spfi: Set device select bits for SPFI port state
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Even if the chip select line is not controlled by the SPFI
hardware, the device select bits need to be set to specify
the chip select line in use for the hardware to know what
parameters to use for the current transfer.

Signed-off-by: Ionela Voinescu <ionela.voinescu@imgtec.com>
Signed-off-by: Andreas Färber <afaerber@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-img-spfi.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/spi/spi-img-spfi.c b/drivers/spi/spi-img-spfi.c
index 7a37090dabbe..e6eb979f1b8a 100644
--- a/drivers/spi/spi-img-spfi.c
+++ b/drivers/spi/spi-img-spfi.c
@@ -419,6 +419,9 @@ static int img_spfi_prepare(struct spi_master *master, struct spi_message *msg)
 	u32 val;
 
 	val = spfi_readl(spfi, SPFI_PORT_STATE);
+	val &= ~(SPFI_PORT_STATE_DEV_SEL_MASK <<
+		 SPFI_PORT_STATE_DEV_SEL_SHIFT);
+	val |= msg->spi->chip_select << SPFI_PORT_STATE_DEV_SEL_SHIFT;
 	if (msg->spi->mode & SPI_CPHA)
 		val |= SPFI_PORT_STATE_CK_PHASE(msg->spi->chip_select);
 	else
-- 
cgit v1.2.3


From 4e133828e2ca6de5b7563842817a65836a45f63f Mon Sep 17 00:00:00 2001
From: Vincent Prince <vincent.prince.fr@gmail.com>
Date: Mon, 30 Jul 2018 11:30:25 +0200
Subject: gpio-it87: add support for IT8786E Super I/O

From the datasheet, the GPIO interface is identical to IT8728 (same
description), so just add it to the same case as the other chip.

Signed-off-by: Vincent Prince <vincent.prince.fr@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-it87.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c
index 7cad14d3f127..7b017f43dc6b 100644
--- a/drivers/gpio/gpio-it87.c
+++ b/drivers/gpio/gpio-it87.c
@@ -41,6 +41,7 @@
 #define IT8732_ID	0x8732
 #define IT8761_ID	0x8761
 #define IT8772_ID	0x8772
+#define IT8786_ID	0x8786
 
 /* IO Ports */
 #define REG		0x2e
@@ -317,6 +318,7 @@ static int __init it87_gpio_init(void)
 	case IT8728_ID:
 	case IT8732_ID:
 	case IT8772_ID:
+	case IT8786_ID:
 		gpio_ba_reg = 0x62;
 		it87_gpio->io_size = 8;
 		it87_gpio->output_base = 0xc8;
-- 
cgit v1.2.3


From dd979b4df817e9976f18fb6f9d134d6bc4a3c317 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 30 Jul 2018 09:42:10 +0200
Subject: net: simplify sock_poll_wait

The wait_address argument is always directly derived from the filp
argument, so remove it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 crypto/af_alg.c        |  2 +-
 include/net/sock.h     | 11 ++++++-----
 net/atm/common.c       |  2 +-
 net/caif/caif_socket.c |  2 +-
 net/core/datagram.c    |  2 +-
 net/dccp/proto.c       |  2 +-
 net/ipv4/tcp.c         |  2 +-
 net/iucv/af_iucv.c     |  2 +-
 net/nfc/llcp_sock.c    |  2 +-
 net/rxrpc/af_rxrpc.c   |  2 +-
 net/smc/af_smc.c       |  2 +-
 net/tipc/socket.c      |  2 +-
 net/unix/af_unix.c     |  4 ++--
 13 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/crypto/af_alg.c b/crypto/af_alg.c
index c166f424871c..b053179e0bc5 100644
--- a/crypto/af_alg.c
+++ b/crypto/af_alg.c
@@ -1071,7 +1071,7 @@ __poll_t af_alg_poll(struct file *file, struct socket *sock,
 	struct af_alg_ctx *ctx = ask->private;
 	__poll_t mask;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	mask = 0;
 
 	if (!ctx->more || ctx->used)
diff --git a/include/net/sock.h b/include/net/sock.h
index 83b747538bd0..0518f61926ec 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2057,16 +2057,17 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
 /**
  * sock_poll_wait - place memory barrier behind the poll_wait call.
  * @filp:           file
- * @wait_address:   socket wait queue
  * @p:              poll_table
  *
  * See the comments in the wq_has_sleeper function.
  */
-static inline void sock_poll_wait(struct file *filp,
-		wait_queue_head_t *wait_address, poll_table *p)
+static inline void sock_poll_wait(struct file *filp, poll_table *p)
 {
-	if (!poll_does_not_wait(p) && wait_address) {
-		poll_wait(filp, wait_address, p);
+	struct socket *sock = filp->private_data;
+	wait_queue_head_t *wq = sk_sleep(sock->sk);
+
+	if (!poll_does_not_wait(p) && wq) {
+		poll_wait(filp, wq, p);
 		/* We need to be sure we are in sync with the
 		 * socket flags modification.
 		 *
diff --git a/net/atm/common.c b/net/atm/common.c
index a7a68e509628..9f8cb0d2e71e 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -653,7 +653,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait)
 	struct atm_vcc *vcc;
 	__poll_t mask;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	mask = 0;
 
 	vcc = ATM_SD(sock);
diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c
index a6fb1b3bcad9..d18965f3291f 100644
--- a/net/caif/caif_socket.c
+++ b/net/caif/caif_socket.c
@@ -941,7 +941,7 @@ static __poll_t caif_poll(struct file *file,
 	__poll_t mask;
 	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	mask = 0;
 
 	/* exceptional events? */
diff --git a/net/core/datagram.c b/net/core/datagram.c
index 9938952c5c78..9aac0d63d53e 100644
--- a/net/core/datagram.c
+++ b/net/core/datagram.c
@@ -837,7 +837,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	__poll_t mask;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	mask = 0;
 
 	/* exceptional events? */
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index 0d56e36a6db7..875858c8b059 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -325,7 +325,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock,
 	__poll_t mask;
 	struct sock *sk = sock->sk;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	if (sk->sk_state == DCCP_LISTEN)
 		return inet_csk_listen_poll(sk);
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 514aaac1626f..f3bfb9f29520 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -507,7 +507,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	const struct tcp_sock *tp = tcp_sk(sk);
 	int state;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 
 	state = inet_sk_state_load(sk);
 	if (state == TCP_LISTEN)
diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 8d1c43f8fed4..92ee91e34395 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -1494,7 +1494,7 @@ __poll_t iucv_sock_poll(struct file *file, struct socket *sock,
 	struct sock *sk = sock->sk;
 	__poll_t mask = 0;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 
 	if (sk->sk_state == IUCV_LISTEN)
 		return iucv_accept_poll(sk);
diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c
index ea0c0c6f1874..dd4adf8b1167 100644
--- a/net/nfc/llcp_sock.c
+++ b/net/nfc/llcp_sock.c
@@ -556,7 +556,7 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock,
 
 	pr_debug("%p\n", sk);
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 
 	if (sk->sk_state == LLCP_LISTEN)
 		return llcp_accept_poll(sk);
diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c
index 2b463047dd7b..ac44d8afffb1 100644
--- a/net/rxrpc/af_rxrpc.c
+++ b/net/rxrpc/af_rxrpc.c
@@ -741,7 +741,7 @@ static __poll_t rxrpc_poll(struct file *file, struct socket *sock,
 	struct rxrpc_sock *rx = rxrpc_sk(sk);
 	__poll_t mask;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	mask = 0;
 
 	/* the socket is readable if there are any messages waiting on the Rx
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index fce7e4751151..0fc94f296e54 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -1535,7 +1535,7 @@ static __poll_t smc_poll(struct file *file, struct socket *sock,
 			mask |= EPOLLERR;
 	} else {
 		if (sk->sk_state != SMC_CLOSED)
-			sock_poll_wait(file, sk_sleep(sk), wait);
+			sock_poll_wait(file, wait);
 		if (sk->sk_err)
 			mask |= EPOLLERR;
 		if ((sk->sk_shutdown == SHUTDOWN_MASK) ||
diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3d21414ba357..3763bedecf5f 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -716,7 +716,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock,
 	struct tipc_sock *tsk = tipc_sk(sk);
 	__poll_t revents = 0;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 
 	if (sk->sk_shutdown & RCV_SHUTDOWN)
 		revents |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index e5473c03d667..1772a0e32665 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2635,7 +2635,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa
 	struct sock *sk = sock->sk;
 	__poll_t mask;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	mask = 0;
 
 	/* exceptional events? */
@@ -2672,7 +2672,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock,
 	unsigned int writable;
 	__poll_t mask;
 
-	sock_poll_wait(file, sk_sleep(sk), wait);
+	sock_poll_wait(file, wait);
 	mask = 0;
 
 	/* exceptional events? */
-- 
cgit v1.2.3


From d8bbd13beeaacd6494954bf5b945b54ccb2af309 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 30 Jul 2018 09:42:11 +0200
Subject: net: don not detour through struct sock to find the poll waitqueue

For any open socket file descriptor sock->sk->sk_wq->wait will always
point to sock->wq->wait.  That means we can do the shorter dereference
and removal a NULL check and don't have to not worry about any RCU
protection.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sock.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 0518f61926ec..2afea5d1bdfe 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2064,10 +2064,9 @@ static inline bool skwq_has_sleeper(struct socket_wq *wq)
 static inline void sock_poll_wait(struct file *filp, poll_table *p)
 {
 	struct socket *sock = filp->private_data;
-	wait_queue_head_t *wq = sk_sleep(sock->sk);
 
-	if (!poll_does_not_wait(p) && wq) {
-		poll_wait(filp, wq, p);
+	if (!poll_does_not_wait(p)) {
+		poll_wait(filp, &sock->wq->wait, p);
 		/* We need to be sure we are in sync with the
 		 * socket flags modification.
 		 *
-- 
cgit v1.2.3


From f641f13b992979b97e595b761a9ba1a64fed7c4e Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 30 Jul 2018 09:42:12 +0200
Subject: net: remove sock_poll_busy_loop

There is no point in hiding this logic in a helper.  Also remove the
useless events != 0 check and only busy loop once we know we actually
have a poll method.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/busy_poll.h | 9 ---------
 net/socket.c            | 5 ++++-
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 9e36fda652b7..85777e68f738 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -121,15 +121,6 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 #endif
 }
 
-static inline void sock_poll_busy_loop(struct socket *sock, __poll_t events)
-{
-	if (sk_can_busy_loop(sock->sk) &&
-	    events && (events & POLL_BUSY_LOOP)) {
-		/* once, only if requested by syscall */
-		sk_busy_loop(sock->sk, 1);
-	}
-}
-
 /* if this socket can poll_ll, tell the system call */
 static inline __poll_t sock_poll_busy_flag(struct socket *sock)
 {
diff --git a/net/socket.c b/net/socket.c
index 85633622c94d..674434127b3a 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1132,9 +1132,12 @@ static __poll_t sock_poll(struct file *file, poll_table *wait)
 	struct socket *sock = file->private_data;
 	__poll_t events = poll_requested_events(wait);
 
-	sock_poll_busy_loop(sock, events);
 	if (!sock->ops->poll)
 		return 0;
+
+	/* poll once if requested by the syscall */
+	if (sk_can_busy_loop(sock->sk) && (events & POLL_BUSY_LOOP))
+		sk_busy_loop(sock->sk, 1);
 	return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
 }
 
-- 
cgit v1.2.3


From a331de3bf0e66ab2437fc8c5b99bd3c0d9da3088 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 30 Jul 2018 09:42:13 +0200
Subject: net: remove sock_poll_busy_flag

Fold it into the only caller to make the code simpler and easier to read.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/busy_poll.h |  6 ------
 net/socket.c            | 16 +++++++++++-----
 2 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 85777e68f738..ba61cdd09eaa 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -121,12 +121,6 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 #endif
 }
 
-/* if this socket can poll_ll, tell the system call */
-static inline __poll_t sock_poll_busy_flag(struct socket *sock)
-{
-	return sk_can_busy_loop(sock->sk) ? POLL_BUSY_LOOP : 0;
-}
-
 /* used in the NIC receive handler to mark the skb */
 static inline void skb_mark_napi_id(struct sk_buff *skb,
 				    struct napi_struct *napi)
diff --git a/net/socket.c b/net/socket.c
index 674434127b3a..5b7df6695f4f 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1130,15 +1130,21 @@ EXPORT_SYMBOL(sock_create_lite);
 static __poll_t sock_poll(struct file *file, poll_table *wait)
 {
 	struct socket *sock = file->private_data;
-	__poll_t events = poll_requested_events(wait);
+	__poll_t events = poll_requested_events(wait), flag = 0;
 
 	if (!sock->ops->poll)
 		return 0;
 
-	/* poll once if requested by the syscall */
-	if (sk_can_busy_loop(sock->sk) && (events & POLL_BUSY_LOOP))
-		sk_busy_loop(sock->sk, 1);
-	return sock->ops->poll(file, sock, wait) | sock_poll_busy_flag(sock);
+	if (sk_can_busy_loop(sock->sk)) {
+		/* poll once if requested by the syscall */
+		if (events & POLL_BUSY_LOOP)
+			sk_busy_loop(sock->sk, 1);
+
+		/* if this socket can poll_ll, tell the system call */
+		flag = POLL_BUSY_LOOP;
+	}
+
+	return sock->ops->poll(file, sock, wait) | flag;
 }
 
 static int sock_mmap(struct file *file, struct vm_area_struct *vma)
-- 
cgit v1.2.3


From c87fffc57adf7b772b3778a9521c3f2ff744ae82 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 30 Jul 2018 19:03:41 +0800
Subject: liquidio: remove redundant function cn23xx_dump_iq_regs

There are no in-tree callers of cn23xx_dump_iq_regs.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/cavium/liquidio/cn23xx_pf_device.c    | 44 ----------------------
 1 file changed, 44 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index e088dedc1747..9f4f3c1d5043 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -1417,50 +1417,6 @@ int validate_cn23xx_pf_config_info(struct octeon_device *oct,
 	return 0;
 }
 
-void cn23xx_dump_iq_regs(struct octeon_device *oct)
-{
-	u32 regval, q_no;
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_DOORBELL_0 [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_IQ_DOORBELL(0),
-		CVM_CAST64(octeon_read_csr64
-			(oct, CN23XX_SLI_IQ_DOORBELL(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_BASEADDR_0 [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_IQ_BASE_ADDR64(0),
-		CVM_CAST64(octeon_read_csr64
-			(oct, CN23XX_SLI_IQ_BASE_ADDR64(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_IQ_FIFO_RSIZE_0 [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_IQ_SIZE(0),
-		CVM_CAST64(octeon_read_csr64(oct, CN23XX_SLI_IQ_SIZE(0))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_CTL_STATUS [0x%x]: 0x%016llx\n",
-		CN23XX_SLI_CTL_STATUS,
-		CVM_CAST64(octeon_read_csr64(oct, CN23XX_SLI_CTL_STATUS)));
-
-	for (q_no = 0; q_no < CN23XX_MAX_INPUT_QUEUES; q_no++) {
-		dev_dbg(&oct->pci_dev->dev, "SLI_PKT[%d]_INPUT_CTL [0x%x]: 0x%016llx\n",
-			q_no, CN23XX_SLI_IQ_PKT_CONTROL64(q_no),
-			CVM_CAST64(octeon_read_csr64
-				(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no))));
-	}
-
-	pci_read_config_dword(oct->pci_dev, CN23XX_CONFIG_PCIE_DEVCTL, &regval);
-	dev_dbg(&oct->pci_dev->dev, "Config DevCtl [0x%x]: 0x%08x\n",
-		CN23XX_CONFIG_PCIE_DEVCTL, regval);
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_PRT[%d]_CFG [0x%llx]: 0x%016llx\n",
-		oct->pcie_port, CN23XX_DPI_SLI_PRTX_CFG(oct->pcie_port),
-		CVM_CAST64(lio_pci_readq(
-			oct, CN23XX_DPI_SLI_PRTX_CFG(oct->pcie_port))));
-
-	dev_dbg(&oct->pci_dev->dev, "SLI_S2M_PORT[%d]_CTL [0x%x]: 0x%016llx\n",
-		oct->pcie_port, CN23XX_SLI_S2M_PORTX_CTL(oct->pcie_port),
-		CVM_CAST64(octeon_read_csr64(
-			oct, CN23XX_SLI_S2M_PORTX_CTL(oct->pcie_port))));
-}
-
 int cn23xx_fw_loaded(struct octeon_device *oct)
 {
 	u64 val;
-- 
cgit v1.2.3


From 802bfb19152c0fb4137c6ba72bcf042ee023e743 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 30 Jul 2018 14:30:42 +0200
Subject: net/sched: user-space can't set unknown tcfa_action values

Currently, when initializing an action, the user-space can specify
and use arbitrary values for the tcfa_action field. If the value
is unknown by the kernel, is implicitly threaded as TC_ACT_UNSPEC.

This change explicitly checks for unknown values at action creation
time, and explicitly convert them to TC_ACT_UNSPEC. No functional
changes are introduced, but this will allow introducing tcfa_action
values not exposed to user-space in a later patch.

Note: we can't use the above to hide TC_ACT_REDIRECT from user-space,
as the latter is already part of uAPI.

v3 -> v4:
 - use an helper to check for action validity (JiriP)
 - emit an extack for invalid actions (JiriP)
v4 -> v5:
 - keep messages on a single line, drop net_warn (Marcelo)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h |  6 ++++--
 net/sched/act_api.c          | 14 ++++++++++++++
 2 files changed, 18 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index b4512254036b..48e5b5d49a34 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -45,6 +45,7 @@ enum {
 				   * the skb and act like everything
 				   * is alright.
 				   */
+#define TC_ACT_VALUE_MAX	TC_ACT_TRAP
 
 /* There is a special kind of actions called "extended actions",
  * which need a value parameter. These have a local opcode located in
@@ -55,11 +56,12 @@ enum {
 #define __TC_ACT_EXT_SHIFT 28
 #define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
 #define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
-#define TC_ACT_EXT_CMP(combined, opcode) \
-	(((combined) & (~TC_ACT_EXT_VAL_MASK)) == opcode)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
 
 #define TC_ACT_JUMP __TC_ACT_EXT(1)
 #define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
 
 /* Action type identifiers*/
 enum {
diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index b43df1e25c6d..229d63c99be2 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -786,6 +786,15 @@ static struct tc_cookie *nla_memdup_cookie(struct nlattr **tb)
 	return c;
 }
 
+static bool tcf_action_valid(int action)
+{
+	int opcode = TC_ACT_EXT_OPCODE(action);
+
+	if (!opcode)
+		return action <= TC_ACT_VALUE_MAX;
+	return opcode <= TC_ACT_EXT_OPCODE_MAX || action == TC_ACT_UNSPEC;
+}
+
 struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 				    struct nlattr *nla, struct nlattr *est,
 				    char *name, int ovr, int bind,
@@ -895,6 +904,11 @@ struct tc_action *tcf_action_init_1(struct net *net, struct tcf_proto *tp,
 		}
 	}
 
+	if (!tcf_action_valid(a->tcfa_action)) {
+		NL_SET_ERR_MSG(extack, "invalid action value, using TC_ACT_UNSPEC instead");
+		a->tcfa_action = TC_ACT_UNSPEC;
+	}
+
 	return a;
 
 err_mod:
-- 
cgit v1.2.3


From 7fd4b288ea6a3e45ad8afbcd5ec39554d57f1ae0 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 30 Jul 2018 14:30:43 +0200
Subject: tc/act: remove unneeded RCU lock in action callback

Each lockless action currently does its own RCU locking in ->act().
This allows using plain RCU accessor, even if the context
is really RCU BH.

This change drops the per action RCU lock, replace the accessors
with the _bh variant, cleans up a bit the surrounding code and
documents the RCU status in the relevant header.
No functional nor performance change is intended.

The goal of this patch is clarifying that the RCU critical section
used by the tc actions extends up to the classifier's caller.

v1 -> v2:
 - preserve rcu lock in act_bpf: it's needed by eBPF helpers,
   as pointed out by Daniel

v3 -> v4:
 - fixed some typos in the commit message (JiriP)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h      |  2 +-
 include/net/sch_generic.h  |  2 ++
 net/sched/act_csum.c       | 12 +++---------
 net/sched/act_ife.c        |  5 +----
 net/sched/act_mirred.c     |  4 +---
 net/sched/act_sample.c     |  4 +---
 net/sched/act_skbedit.c    | 10 +++-------
 net/sched/act_skbmod.c     | 21 +++++++++------------
 net/sched/act_tunnel_key.c |  6 +-----
 net/sched/act_vlan.c       | 19 +++++++------------
 10 files changed, 29 insertions(+), 56 deletions(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 683ce41053d9..8c9bc02d05e1 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -85,7 +85,7 @@ struct tc_action_ops {
 	size_t	size;
 	struct module		*owner;
 	int     (*act)(struct sk_buff *, const struct tc_action *,
-		       struct tcf_result *);
+		       struct tcf_result *); /* called under RCU BH lock*/
 	int     (*dump)(struct sk_buff *, struct tc_action *, int, int);
 	void	(*cleanup)(struct tc_action *);
 	int     (*lookup)(struct net *net, struct tc_action **a, u32 index,
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index c5432362dc26..bcae181c1857 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -285,6 +285,8 @@ struct tcf_proto {
 	/* Fast access part */
 	struct tcf_proto __rcu	*next;
 	void __rcu		*root;
+
+	/* called under RCU BH lock*/
 	int			(*classify)(struct sk_buff *,
 					    const struct tcf_proto *,
 					    struct tcf_result *);
diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 4e8c383f379e..648a3a35b720 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -561,15 +561,14 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a,
 	u32 update_flags;
 	int action;
 
-	rcu_read_lock();
-	params = rcu_dereference(p->params);
+	params = rcu_dereference_bh(p->params);
 
 	tcf_lastuse_update(&p->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(p->common.cpu_bstats), skb);
 
 	action = READ_ONCE(p->tcf_action);
 	if (unlikely(action == TC_ACT_SHOT))
-		goto drop_stats;
+		goto drop;
 
 	update_flags = params->update_flags;
 	switch (tc_skb_protocol(skb)) {
@@ -583,16 +582,11 @@ static int tcf_csum(struct sk_buff *skb, const struct tc_action *a,
 		break;
 	}
 
-unlock:
-	rcu_read_unlock();
 	return action;
 
 drop:
-	action = TC_ACT_SHOT;
-
-drop_stats:
 	qstats_drop_inc(this_cpu_ptr(p->common.cpu_qstats));
-	goto unlock;
+	return TC_ACT_SHOT;
 }
 
 static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 3d6e265758c0..df4060e32d43 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -820,14 +820,11 @@ static int tcf_ife_act(struct sk_buff *skb, const struct tc_action *a,
 	struct tcf_ife_params *p;
 	int ret;
 
-	rcu_read_lock();
-	p = rcu_dereference(ife->params);
+	p = rcu_dereference_bh(ife->params);
 	if (p->flags & IFE_ENCODE) {
 		ret = tcf_ife_encode(skb, a, res, p);
-		rcu_read_unlock();
 		return ret;
 	}
-	rcu_read_unlock();
 
 	return tcf_ife_decode(skb, a, res);
 }
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 6afd89a36c69..eeb335f03102 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -181,11 +181,10 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&m->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb);
 
-	rcu_read_lock();
 	m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit);
 	m_eaction = READ_ONCE(m->tcfm_eaction);
 	retval = READ_ONCE(m->tcf_action);
-	dev = rcu_dereference(m->tcfm_dev);
+	dev = rcu_dereference_bh(m->tcfm_dev);
 	if (unlikely(!dev)) {
 		pr_notice_once("tc mirred: target device is gone\n");
 		goto out;
@@ -236,7 +235,6 @@ out:
 		if (tcf_mirred_is_act_redirect(m_eaction))
 			retval = TC_ACT_SHOT;
 	}
-	rcu_read_unlock();
 
 	return retval;
 }
diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 3079e7be5bde..2608ccc83e5e 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -140,8 +140,7 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
 	bstats_cpu_update(this_cpu_ptr(s->common.cpu_bstats), skb);
 	retval = READ_ONCE(s->tcf_action);
 
-	rcu_read_lock();
-	psample_group = rcu_dereference(s->psample_group);
+	psample_group = rcu_dereference_bh(s->psample_group);
 
 	/* randomly sample packets according to rate */
 	if (psample_group && (prandom_u32() % s->rate == 0)) {
@@ -165,7 +164,6 @@ static int tcf_sample_act(struct sk_buff *skb, const struct tc_action *a,
 			skb_pull(skb, skb->mac_len);
 	}
 
-	rcu_read_unlock();
 	return retval;
 }
 
diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index da56e6938c9e..a6db47ebec11 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -43,8 +43,7 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 	tcf_lastuse_update(&d->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(d->common.cpu_bstats), skb);
 
-	rcu_read_lock();
-	params = rcu_dereference(d->params);
+	params = rcu_dereference_bh(d->params);
 	action = READ_ONCE(d->tcf_action);
 
 	if (params->flags & SKBEDIT_F_PRIORITY)
@@ -77,14 +76,11 @@ static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
 	}
 	if (params->flags & SKBEDIT_F_PTYPE)
 		skb->pkt_type = params->ptype;
-
-unlock:
-	rcu_read_unlock();
 	return action;
+
 err:
 	qstats_drop_inc(this_cpu_ptr(d->common.cpu_qstats));
-	action = TC_ACT_SHOT;
-	goto unlock;
+	return TC_ACT_SHOT;
 }
 
 static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = {
diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index cdc6bacfb190..c437c6d51a71 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -41,20 +41,14 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a,
 	 * then MAX_EDIT_LEN needs to change appropriately
 	*/
 	err = skb_ensure_writable(skb, MAX_EDIT_LEN);
-	if (unlikely(err)) { /* best policy is to drop on the floor */
-		qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
-		return TC_ACT_SHOT;
-	}
+	if (unlikely(err)) /* best policy is to drop on the floor */
+		goto drop;
 
-	rcu_read_lock();
 	action = READ_ONCE(d->tcf_action);
-	if (unlikely(action == TC_ACT_SHOT)) {
-		qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
-		rcu_read_unlock();
-		return action;
-	}
+	if (unlikely(action == TC_ACT_SHOT))
+		goto drop;
 
-	p = rcu_dereference(d->skbmod_p);
+	p = rcu_dereference_bh(d->skbmod_p);
 	flags = p->flags;
 	if (flags & SKBMOD_F_DMAC)
 		ether_addr_copy(eth_hdr(skb)->h_dest, p->eth_dst);
@@ -62,7 +56,6 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a,
 		ether_addr_copy(eth_hdr(skb)->h_source, p->eth_src);
 	if (flags & SKBMOD_F_ETYPE)
 		eth_hdr(skb)->h_proto = p->eth_type;
-	rcu_read_unlock();
 
 	if (flags & SKBMOD_F_SWAPMAC) {
 		u16 tmpaddr[ETH_ALEN / 2]; /* ether_addr_copy() requirement */
@@ -73,6 +66,10 @@ static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a,
 	}
 
 	return action;
+
+drop:
+	qstats_overlimit_inc(this_cpu_ptr(d->common.cpu_qstats));
+	return TC_ACT_SHOT;
 }
 
 static const struct nla_policy skbmod_policy[TCA_SKBMOD_MAX + 1] = {
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index f811850fd1d0..d42d9e112789 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -31,9 +31,7 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 	struct tcf_tunnel_key_params *params;
 	int action;
 
-	rcu_read_lock();
-
-	params = rcu_dereference(t->params);
+	params = rcu_dereference_bh(t->params);
 
 	tcf_lastuse_update(&t->tcf_tm);
 	bstats_cpu_update(this_cpu_ptr(t->common.cpu_bstats), skb);
@@ -53,8 +51,6 @@ static int tunnel_key_act(struct sk_buff *skb, const struct tc_action *a,
 		break;
 	}
 
-	rcu_read_unlock();
-
 	return action;
 }
 
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index ad37f308175a..15a0ee214c9c 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -40,11 +40,9 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 	if (skb_at_tc_ingress(skb))
 		skb_push_rcsum(skb, skb->mac_len);
 
-	rcu_read_lock();
-
 	action = READ_ONCE(v->tcf_action);
 
-	p = rcu_dereference(v->vlan_p);
+	p = rcu_dereference_bh(v->vlan_p);
 
 	switch (p->tcfv_action) {
 	case TCA_VLAN_ACT_POP:
@@ -61,7 +59,7 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 	case TCA_VLAN_ACT_MODIFY:
 		/* No-op if no vlan tag (either hw-accel or in-payload) */
 		if (!skb_vlan_tagged(skb))
-			goto unlock;
+			goto out;
 		/* extract existing tag (and guarantee no hw-accel tag) */
 		if (skb_vlan_tag_present(skb)) {
 			tci = skb_vlan_tag_get(skb);
@@ -86,18 +84,15 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 		BUG();
 	}
 
-	goto unlock;
-
-drop:
-	action = TC_ACT_SHOT;
-	qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats));
-
-unlock:
-	rcu_read_unlock();
+out:
 	if (skb_at_tc_ingress(skb))
 		skb_pull_rcsum(skb, skb->mac_len);
 
 	return action;
+
+drop:
+	qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats));
+	return TC_ACT_SHOT;
 }
 
 static const struct nla_policy vlan_policy[TCA_VLAN_MAX + 1] = {
-- 
cgit v1.2.3


From cd11b164073b719203318227918f9510809d5e10 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 30 Jul 2018 14:30:44 +0200
Subject: net/tc: introduce TC_ACT_REINSERT.

This is similar TC_ACT_REDIRECT, but with a slightly different
semantic:
- on ingress the mirred skbs are passed to the target device
network stack without any additional check not scrubbing.
- the rcu-protected stats provided via the tcf_result struct
  are updated on error conditions.

This new tcfa_action value is not exposed to the user-space
and can be used only internally by clsact.

v1 -> v2: do not touch TC_ACT_REDIRECT code path, introduce
 a new action type instead
v2 -> v3:
 - rename the new action value TC_ACT_REINJECT, update the
   helper accordingly
 - take care of uncloned reinjected packets in XDP generic
   hook
v3 -> v4:
 - renamed again the new action value (JiriP)
v4 -> v5:
 - fix build error with !NET_CLS_ACT (kbuild bot)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h     |  3 +++
 include/net/sch_generic.h | 28 ++++++++++++++++++++++++++++
 net/core/dev.c            |  6 +++++-
 3 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 6d02f31abba8..22bfc3a13c25 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -7,6 +7,9 @@
 #include <net/sch_generic.h>
 #include <net/act_api.h>
 
+/* TC action not accessible from user space */
+#define TC_ACT_REINSERT		(TC_ACT_VALUE_MAX + 1)
+
 /* Basic packet classifier frontend definitions. */
 
 struct tcf_walker {
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index bcae181c1857..a6d00093f35e 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -235,6 +235,12 @@ struct tcf_result {
 			u32		classid;
 		};
 		const struct tcf_proto *goto_tp;
+
+		/* used by the TC_ACT_REINSERT action */
+		struct {
+			bool		ingress;
+			struct gnet_stats_queue *qstats;
+		};
 	};
 };
 
@@ -569,6 +575,15 @@ static inline void skb_reset_tc(struct sk_buff *skb)
 #endif
 }
 
+static inline bool skb_is_tc_redirected(const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	return skb->tc_redirected;
+#else
+	return false;
+#endif
+}
+
 static inline bool skb_at_tc_ingress(const struct sk_buff *skb)
 {
 #ifdef CONFIG_NET_CLS_ACT
@@ -1108,4 +1123,17 @@ void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp,
 void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc,
 			  struct mini_Qdisc __rcu **p_miniq);
 
+static inline void skb_tc_reinsert(struct sk_buff *skb, struct tcf_result *res)
+{
+	struct gnet_stats_queue *stats = res->qstats;
+	int ret;
+
+	if (res->ingress)
+		ret = netif_receive_skb(skb);
+	else
+		ret = dev_queue_xmit(skb);
+	if (ret && stats)
+		qstats_overlimit_inc(res->qstats);
+}
+
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 89031b5fef9f..38b0c414d780 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4252,7 +4252,7 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb,
 	/* Reinjected packets coming from act_mirred or similar should
 	 * not get XDP generic processing.
 	 */
-	if (skb_cloned(skb))
+	if (skb_cloned(skb) || skb_is_tc_redirected(skb))
 		return XDP_PASS;
 
 	/* XDP packets must be linear and must have sufficient headroom
@@ -4602,6 +4602,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		__skb_push(skb, skb->mac_len);
 		skb_do_redirect(skb);
 		return NULL;
+	case TC_ACT_REINSERT:
+		/* this does not scrub the packet, and updates stats on error */
+		skb_tc_reinsert(skb, &cl_res);
+		return NULL;
 	default:
 		break;
 	}
-- 
cgit v1.2.3


From e5cf1baf92cb785b90390db1c624948e70c8b8bd Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 30 Jul 2018 14:30:45 +0200
Subject: act_mirred: use TC_ACT_REINSERT when possible

When mirred is invoked from the ingress path, and it wants to redirect
the processed packet, it can now use the TC_ACT_REINSERT action,
filling the tcf_result accordingly, and avoiding a per packet
skb_clone().

Overall this gives a ~10% improvement in forwarding performance for the
TC S/W data path and TC S/W performances are now comparable to the
kernel openvswitch datapath.

v1 -> v2: use ACT_MIRRED instead of ACT_REDIRECT
v2 -> v3: updated after action rename, fixed typo into the commit
	message
v3 -> v4: updated again after action rename, added more comments to
	the code (JiriP), skip the optimization if the control action
	need to touch the tcf_result (Paolo)
v4 -> v5: fix sparse warning (kbuild bot)

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_mirred.c | 53 ++++++++++++++++++++++++++++++++++++++++----------
 1 file changed, 43 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index eeb335f03102..b26d060da08e 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -25,6 +25,7 @@
 #include <net/net_namespace.h>
 #include <net/netlink.h>
 #include <net/pkt_sched.h>
+#include <net/pkt_cls.h>
 #include <linux/tc_act/tc_mirred.h>
 #include <net/tc_act/tc_mirred.h>
 
@@ -49,6 +50,18 @@ static bool tcf_mirred_act_wants_ingress(int action)
 	}
 }
 
+static bool tcf_mirred_can_reinsert(int action)
+{
+	switch (action) {
+	case TC_ACT_SHOT:
+	case TC_ACT_STOLEN:
+	case TC_ACT_QUEUED:
+	case TC_ACT_TRAP:
+		return true;
+	}
+	return false;
+}
+
 static void tcf_mirred_release(struct tc_action *a)
 {
 	struct tcf_mirred *m = to_mirred(a);
@@ -171,10 +184,13 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 		      struct tcf_result *res)
 {
 	struct tcf_mirred *m = to_mirred(a);
+	struct sk_buff *skb2 = skb;
 	bool m_mac_header_xmit;
 	struct net_device *dev;
-	struct sk_buff *skb2;
 	int retval, err = 0;
+	bool use_reinsert;
+	bool want_ingress;
+	bool is_redirect;
 	int m_eaction;
 	int mac_len;
 
@@ -196,16 +212,25 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 		goto out;
 	}
 
-	skb2 = skb_clone(skb, GFP_ATOMIC);
-	if (!skb2)
-		goto out;
+	/* we could easily avoid the clone only if called by ingress and clsact;
+	 * since we can't easily detect the clsact caller, skip clone only for
+	 * ingress - that covers the TC S/W datapath.
+	 */
+	is_redirect = tcf_mirred_is_act_redirect(m_eaction);
+	use_reinsert = skb_at_tc_ingress(skb) && is_redirect &&
+		       tcf_mirred_can_reinsert(retval);
+	if (!use_reinsert) {
+		skb2 = skb_clone(skb, GFP_ATOMIC);
+		if (!skb2)
+			goto out;
+	}
 
 	/* If action's target direction differs than filter's direction,
 	 * and devices expect a mac header on xmit, then mac push/pull is
 	 * needed.
 	 */
-	if (skb_at_tc_ingress(skb) != tcf_mirred_act_wants_ingress(m_eaction) &&
-	    m_mac_header_xmit) {
+	want_ingress = tcf_mirred_act_wants_ingress(m_eaction);
+	if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) {
 		if (!skb_at_tc_ingress(skb)) {
 			/* caught at egress, act ingress: pull mac */
 			mac_len = skb_network_header(skb) - skb_mac_header(skb);
@@ -216,15 +241,23 @@ static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
 		}
 	}
 
+	skb2->skb_iif = skb->dev->ifindex;
+	skb2->dev = dev;
+
 	/* mirror is always swallowed */
-	if (tcf_mirred_is_act_redirect(m_eaction)) {
+	if (is_redirect) {
 		skb2->tc_redirected = 1;
 		skb2->tc_from_ingress = skb2->tc_at_ingress;
+
+		/* let's the caller reinsert the packet, if possible */
+		if (use_reinsert) {
+			res->ingress = want_ingress;
+			res->qstats = this_cpu_ptr(m->common.cpu_qstats);
+			return TC_ACT_REINSERT;
+		}
 	}
 
-	skb2->skb_iif = skb->dev->ifindex;
-	skb2->dev = dev;
-	if (!tcf_mirred_act_wants_ingress(m_eaction))
+	if (!want_ingress)
 		err = dev_queue_xmit(skb2);
 	else
 		err = netif_receive_skb(skb2);
-- 
cgit v1.2.3


From ad13acce8dcd35cfc15281c1348beb70ca64091b Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Mon, 30 Jul 2018 16:08:33 +0530
Subject: net/tls: Use socket data_ready callback on record availability

On receipt of a complete tls record, use socket's saved data_ready
callback instead of state_change callback. In function tls_queue(),
the TLS record is queued in encrypted state. But the decryption
happen inline when tls_sw_recvmsg() or tls_sw_splice_read() get invoked.
So it should be ok to notify the waiting context about the availability
of data as soon as we could collect a full TLS record. For new data
availability notification, sk_data_ready callback is more appropriate.
It points to sock_def_readable() which wakes up specifically for EPOLLIN
event. This is in contrast to the socket callback sk_state_change which
points to sock_def_wakeup() which issues a wakeup unconditionally
(without event mask).

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 6deceb7c56ba..33838f11fafa 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1028,7 +1028,7 @@ static void tls_queue(struct strparser *strp, struct sk_buff *skb)
 	ctx->recv_pkt = skb;
 	strp_pause(strp);
 
-	strp->sk->sk_state_change(strp->sk);
+	ctx->saved_data_ready(strp->sk);
 }
 
 static void tls_data_ready(struct sock *sk)
-- 
cgit v1.2.3


From 86ff73622a013ceac948390e5920b817e101e0b2 Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@bootlin.com>
Date: Mon, 30 Jul 2018 14:53:13 +0200
Subject: net: phy: mscc: the extended page access register is 16 bits

The Extended Page Access is a 16-bit register, so change the page
parameter of vsc85xx_phy_page_set to a u16.

Signed-off-by: Quentin Schulz <quentin.schulz@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mscc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/mscc.c b/drivers/net/phy/mscc.c
index 650c2667d523..84ca9ff40ae0 100644
--- a/drivers/net/phy/mscc.c
+++ b/drivers/net/phy/mscc.c
@@ -123,7 +123,7 @@ static const struct vsc8531_edge_rate_table edge_table[] = {
 };
 #endif /* CONFIG_OF_MDIO */
 
-static int vsc85xx_phy_page_set(struct phy_device *phydev, u8 page)
+static int vsc85xx_phy_page_set(struct phy_device *phydev, u16 page)
 {
 	int rc;
 
-- 
cgit v1.2.3


From efd112353bf7c0f9d50f928b449ea9da0ee9554b Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Mon, 30 Jul 2018 17:43:39 +0100
Subject: arm64: svc: Ensure hardirq tracing is updated before return

We always run userspace with interrupts enabled, but with the recent
conversion of the syscall entry/exit code to C, we don't inform the
hardirq tracing code that interrupts are about to become enabled by
virtue of restoring the EL0 SPSR.

This patch ensures that trace_hardirqs_on() is called on the syscall
return path when we return to the assembly code with interrupts still
disabled.

Fixes: f37099b6992a ("arm64: convert syscall trace logic to C")
Reported-by: Julien Grall <julien.grall@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/syscall.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c
index be00c85794db..032d22312881 100644
--- a/arch/arm64/kernel/syscall.c
+++ b/arch/arm64/kernel/syscall.c
@@ -91,8 +91,15 @@ static void el0_svc_common(struct pt_regs *regs, int scno, int sc_nr,
 	if (!has_syscall_work(flags) && !IS_ENABLED(CONFIG_DEBUG_RSEQ)) {
 		local_daif_mask();
 		flags = current_thread_info()->flags;
-		if (!has_syscall_work(flags))
+		if (!has_syscall_work(flags)) {
+			/*
+			 * We're off to userspace, where interrupts are
+			 * always enabled after we restore the flags from
+			 * the SPSR.
+			 */
+			trace_hardirqs_on();
 			return;
+		}
 		local_daif_restore(DAIF_PROCCTX);
 	}
 
-- 
cgit v1.2.3


From 778c4d5c5b96a61c7981ad6d841071326a713845 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 30 Jul 2018 21:07:24 +0800
Subject: fib_rules: NULL check before kfree is not needed

kfree(NULL) is safe,so this removes NULL check before freeing the mem

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/fib_rules.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index f64aa13811ea..0ff3953f64aa 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -924,8 +924,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return 0;
 
 errout:
-	if (nlrule)
-		kfree(nlrule);
+	kfree(nlrule);
 	rules_ops_put(ops);
 	return err;
 }
-- 
cgit v1.2.3


From e094574f9bf806fb89a285c0a0263a46a1d536f9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 30 Jul 2018 16:39:46 +0200
Subject: selftests: forwarding: lib: Add require_command()

The logic for testing whether a certain command is available is used
several times in the current code base. The tests in follow-up patches
add more requirements like that.

Therefore extract the logic into a named function, require_command(),
that can be used directly from lib.sh as well as from any test that
wishes to declare dependence on some command.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 19 +++++++++++--------
 1 file changed, 11 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 158d59ffee40..81e36157bf16 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -62,15 +62,18 @@ if [[ "$CHECK_TC" = "yes" ]]; then
 	check_tc_version
 fi
 
-if [[ ! -x "$(command -v jq)" ]]; then
-	echo "SKIP: jq not installed"
-	exit 1
-fi
+require_command()
+{
+	local cmd=$1; shift
 
-if [[ ! -x "$(command -v $MZ)" ]]; then
-	echo "SKIP: $MZ not installed"
-	exit 1
-fi
+	if [[ ! -x "$(command -v "$cmd")" ]]; then
+		echo "SKIP: $cmd not installed"
+		exit 1
+	fi
+}
+
+require_command jq
+require_command $MZ
 
 if [[ ! -v NUM_NETIFS ]]; then
 	echo "SKIP: importer does not define \"NUM_NETIFS\""
-- 
cgit v1.2.3


From 9d9e6bde3df4ec6af0cc7dac328f8d8555aa36f9 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 30 Jul 2018 16:39:52 +0200
Subject: selftests: forwarding: lib: Support team devices

Add team_create() and team_destroy() to manage team netdevices.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 81e36157bf16..3a4eba4f0d08 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -8,6 +8,7 @@
 PING=${PING:=ping}
 PING6=${PING6:=ping6}
 MZ=${MZ:=mausezahn}
+TEAMD=${TEAMD:=teamd}
 WAIT_TIME=${WAIT_TIME:=5}
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
 PAUSE_ON_CLEANUP=${PAUSE_ON_CLEANUP:=no}
@@ -425,6 +426,28 @@ vlan_destroy()
 	ip link del dev $name
 }
 
+team_create()
+{
+	local if_name=$1; shift
+	local mode=$1; shift
+
+	require_command $TEAMD
+	$TEAMD -t $if_name -d -c '{"runner": {"name": "'$mode'"}}'
+	for slave in "$@"; do
+		ip link set dev $slave down
+		ip link set dev $slave master $if_name
+		ip link set dev $slave up
+	done
+	ip link set dev $if_name up
+}
+
+team_destroy()
+{
+	local if_name=$1; shift
+
+	$TEAMD -t $if_name -k
+}
+
 master_name_get()
 {
 	local if_name=$1
-- 
cgit v1.2.3


From ca70a5623823841c179cf792b549d63b5fbe32ab Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 30 Jul 2018 16:39:57 +0200
Subject: selftests: forwarding: Introduce $ARPING

Instead of relying on "arping" being installed everywhere under that
name, introduce a variable $ARPING like the other tools do.

Convert an existing test, mirror_gre_vlan_bridge_1q.sh to
require_command $ARPING and then invoke arping through the variable.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh                       | 1 +
 tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh | 6 ++++--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 3a4eba4f0d08..843a6715924f 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -8,6 +8,7 @@
 PING=${PING:=ping}
 PING6=${PING6:=ping6}
 MZ=${MZ:=mausezahn}
+ARPING=${ARPING:=arping}
 TEAMD=${TEAMD:=teamd}
 WAIT_TIME=${WAIT_TIME:=5}
 PAUSE_ON_FAIL=${PAUSE_ON_FAIL:=no}
diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
index d3e75bb6a2d8..204b25f13934 100755
--- a/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_vlan_bridge_1q.sh
@@ -28,6 +28,8 @@ source mirror_lib.sh
 source mirror_gre_lib.sh
 source mirror_gre_topo_lib.sh
 
+require_command $ARPING
+
 setup_prepare()
 {
 	h1=${NETIFS[p1]}
@@ -149,7 +151,7 @@ test_span_gre_forbidden_egress()
 
 	bridge vlan add dev $swp3 vid 555
 	# Re-prime FDB
-	arping -I br1.555 192.0.2.130 -fqc 1
+	$ARPING -I br1.555 192.0.2.130 -fqc 1
 	sleep 1
 	quick_test_span_gre_dir $tundev ingress
 
@@ -223,7 +225,7 @@ test_span_gre_fdb_roaming()
 
 	bridge fdb del dev $swp2 $h3mac vlan 555 master
 	# Re-prime FDB
-	arping -I br1.555 192.0.2.130 -fqc 1
+	$ARPING -I br1.555 192.0.2.130 -fqc 1
 	sleep 1
 	quick_test_span_gre_dir $tundev ingress
 
-- 
cgit v1.2.3


From a9b33b2001b6e2b2a0df266977472db497a5d1ca Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 30 Jul 2018 16:40:02 +0200
Subject: selftests: forwarding: Test mirror-to-gretap w/ UL team

Test for "tc action mirred egress mirror" that mirrors to gretap when
the underlay route points at a VLAN-aware bridge (802.1q), and the
traffic egresses the bridge through a team device. Test upping and
downing individual team device slaves and verify the traffic flows as
expected.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/mirror_gre_bridge_1q_lag.sh     | 283 +++++++++++++++++++++
 1 file changed, 283 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
new file mode 100755
index 000000000000..61844caf671e
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_bridge_1q_lag.sh
@@ -0,0 +1,283 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# bridge device with vlan filtering (802.1q), and the egress device is a team
+# device.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |     + $h1.333        |                             |        $h1.555 +     |
+# |     | 192.0.2.1/28   |                             |  192.0.2.18/28 |     |
+# +-----|----------------+                             +----------------|-----+
+#       |                               $h1                             |
+#       +--------------------------------+------------------------------+
+#                                        |
+# +--------------------------------------|------------------------------------+
+# | SW                                   o---> mirror                         |
+# |                                      |                                    |
+# |     +--------------------------------+------------------------------+     |
+# |     |                              $swp1                            |     |
+# |     + $swp1.333                                           $swp1.555 +     |
+# |       192.0.2.2/28                                    192.0.2.17/28       |
+# |                                                                           |
+# | +-----------------------------------------------------------------------+ |
+# | |                        BR1 (802.1q)                                   | |
+# | |     + lag (team)       192.0.2.129/28                                 | |
+# | |    / \                 2001:db8:2::1/64                               | |
+# | +---/---\---------------------------------------------------------------+ |
+# |    /     \                                                            ^   |
+# |   |       \                                        + gt4 (gretap)     |   |
+# |   |        \                                         loc=192.0.2.129  |   |
+# |   |         \                                        rem=192.0.2.130 -+   |
+# |   |          \                                       ttl=100              |
+# |   |           \                                      tos=inherit          |
+# |   |            \                                                          |
+# |   |             \_________________________________                        |
+# |   |                                               \                       |
+# |   + $swp3                                          + $swp4                |
+# +---|------------------------------------------------|----------------------+
+#     |                                                |
+# +---|----------------------+                     +---|----------------------+
+# |   + $h3               H3 |                     |   + $h4               H4 |
+# |     192.0.2.130/28       |                     |     192.0.2.130/28       |
+# |     2001:db8:2::2/64     |                     |     2001:db8:2::2/64     |
+# +--------------------------+                     +--------------------------+
+
+ALL_TESTS="
+	test_mirror_gretap_first
+	test_mirror_gretap_second
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+
+require_command $ARPING
+
+vlan_host_create()
+{
+	local if_name=$1; shift
+	local vid=$1; shift
+	local vrf_name=$1; shift
+	local ips=("${@}")
+
+	vrf_create $vrf_name
+	ip link set dev $vrf_name up
+	vlan_create $if_name $vid $vrf_name "${ips[@]}"
+}
+
+vlan_host_destroy()
+{
+	local if_name=$1; shift
+	local vid=$1; shift
+	local vrf_name=$1; shift
+
+	vlan_destroy $if_name $vid
+	ip link set dev $vrf_name down
+	vrf_destroy $vrf_name
+}
+
+h1_create()
+{
+	vlan_host_create $h1 333 vrf-h1 192.0.2.1/28
+	ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2
+}
+
+h1_destroy()
+{
+	ip -4 route del 192.0.2.16/28 vrf vrf-h1
+	vlan_host_destroy $h1 333 vrf-h1
+}
+
+h2_create()
+{
+	vlan_host_create $h1 555 vrf-h2 192.0.2.18/28
+	ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17
+}
+
+h2_destroy()
+{
+	ip -4 route del 192.0.2.0/28 vrf vrf-h2
+	vlan_host_destroy $h1 555 vrf-h2
+}
+
+h3_create()
+{
+	simple_if_init $h3 192.0.2.130/28
+	tc qdisc add dev $h3 clsact
+}
+
+h3_destroy()
+{
+	tc qdisc del dev $h3 clsact
+	simple_if_fini $h3 192.0.2.130/28
+}
+
+h4_create()
+{
+	simple_if_init $h4 192.0.2.130/28
+	tc qdisc add dev $h4 clsact
+}
+
+h4_destroy()
+{
+	tc qdisc del dev $h4 clsact
+	simple_if_fini $h4 192.0.2.130/28
+}
+
+switch_create()
+{
+	ip link set dev $swp1 up
+	tc qdisc add dev $swp1 clsact
+	vlan_create $swp1 333 "" 192.0.2.2/28
+	vlan_create $swp1 555 "" 192.0.2.17/28
+
+	tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+		      ttl 100 tos inherit
+
+	ip link set dev $swp3 up
+	ip link set dev $swp4 up
+
+	ip link add name br1 type bridge vlan_filtering 1
+	ip link set dev br1 up
+	__addr_add_del br1 add 192.0.2.129/32
+	ip -4 route add 192.0.2.130/32 dev br1
+
+	team_create lag loadbalance $swp3 $swp4
+	ip link set dev lag master br1
+}
+
+switch_destroy()
+{
+	ip link set dev lag nomaster
+	team_destroy lag
+
+	ip -4 route del 192.0.2.130/32 dev br1
+	__addr_add_del br1 del 192.0.2.129/32
+	ip link set dev br1 down
+	ip link del dev br1
+
+	ip link set dev $swp4 down
+	ip link set dev $swp3 down
+
+	tunnel_destroy gt4
+
+	vlan_destroy $swp1 555
+	vlan_destroy $swp1 333
+	tc qdisc del dev $swp1 clsact
+	ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp3=${NETIFS[p3]}
+	h3=${NETIFS[p4]}
+
+	swp4=${NETIFS[p5]}
+	h4=${NETIFS[p6]}
+
+	vrf_prepare
+
+	ip link set dev $h1 up
+	h1_create
+	h2_create
+	h3_create
+	h4_create
+	switch_create
+
+	trap_install $h3 ingress
+	trap_install $h4 ingress
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	trap_uninstall $h4 ingress
+	trap_uninstall $h3 ingress
+
+	switch_destroy
+	h4_destroy
+	h3_destroy
+	h2_destroy
+	h1_destroy
+	ip link set dev $h1 down
+
+	vrf_cleanup
+}
+
+test_lag_slave()
+{
+	local host_dev=$1; shift
+	local up_dev=$1; shift
+	local down_dev=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress gt4 \
+		       "proto 802.1q flower vlan_id 333 $tcflags"
+
+	# Test connectivity through $up_dev when $down_dev is set down.
+	ip link set dev $down_dev down
+	setup_wait_dev $up_dev
+	setup_wait_dev $host_dev
+	$ARPING -I br1 192.0.2.130 -qfc 1
+	sleep 2
+	mirror_test vrf-h1 192.0.2.1 192.0.2.18 $host_dev 1 10
+
+	# Test lack of connectivity when both slaves are down.
+	ip link set dev $up_dev down
+	sleep 2
+	mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0
+	mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0
+
+	ip link set dev $up_dev up
+	ip link set dev $down_dev up
+	mirror_uninstall $swp1 ingress
+
+	log_test "$what ($tcflags)"
+}
+
+test_mirror_gretap_first()
+{
+	test_lag_slave $h3 $swp3 $swp4 "mirror to gretap: LAG first slave"
+}
+
+test_mirror_gretap_second()
+{
+	test_lag_slave $h4 $swp4 $swp3 "mirror to gretap: LAG second slave"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 541c6ce30f6738a05a869606f50c14dea89d12e2 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Mon, 30 Jul 2018 16:40:07 +0200
Subject: selftests: forwarding: Test mirror-to-gretap w/ UL team LACP

This tests mirror-to-gretap when an underlay packet path includes a team
device which is not in loadbalance mode, but in LACP mode. The test
manipulates LAG membership to achieve changes in txability, thus making
sure that a driver that offloads mirror-to-gretap doesn't just consider
upness of a device.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/mirror_gre_lag_lacp.sh          | 285 +++++++++++++++++++++
 1 file changed, 285 insertions(+)
 create mode 100755 tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh

diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh
new file mode 100755
index 000000000000..9edf4cb104a8
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/mirror_gre_lag_lacp.sh
@@ -0,0 +1,285 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for "tc action mirred egress mirror" when the underlay route points at a
+# team device.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |    + $h1.333         |                             |        $h1.555 +     |
+# |    | 192.0.2.1/28    |                             |  192.0.2.18/28 |     |
+# +----|-----------------+                             +----------------|-----+
+#      |                                $h1                             |
+#      +---------------------------------+------------------------------+
+#                                        |
+# +--------------------------------------|------------------------------------+
+# | SW                                   o---> mirror                         |
+# |                                      |                                    |
+# |   +----------------------------------+------------------------------+     |
+# |   |                                $swp1                            |     |
+# |   + $swp1.333                                             $swp1.555 +     |
+# |     192.0.2.2/28                                      192.0.2.17/28       |
+# |                                                                           |
+# |                                                                           |
+# |   + gt4 (gretap)      ,-> + lag1 (team)                                   |
+# |     loc=192.0.2.129   |   | 192.0.2.129/28                                |
+# |     rem=192.0.2.130 --'   |                                               |
+# |     ttl=100               |                                               |
+# |     tos=inherit           |                                               |
+# |      _____________________|______________________                         |
+# |     /                                            \                        |
+# |    /                                              \                       |
+# |   + $swp3                                          + $swp4                |
+# +---|------------------------------------------------|----------------------+
+#     |                                                |
+# +---|------------------------------------------------|----------------------+
+# |   + $h3                                            + $h4               H3 |
+# |    \                                              /                       |
+# |     \____________________________________________/                        |
+# |                           |                                               |
+# |                           + lag2 (team)                                   |
+# |                             192.0.2.130/28                                |
+# |                                                                           |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+	test_mirror_gretap_first
+	test_mirror_gretap_second
+"
+
+NUM_NETIFS=6
+source lib.sh
+source mirror_lib.sh
+source mirror_gre_lib.sh
+
+require_command $ARPING
+
+vlan_host_create()
+{
+	local if_name=$1; shift
+	local vid=$1; shift
+	local vrf_name=$1; shift
+	local ips=("${@}")
+
+	vrf_create $vrf_name
+	ip link set dev $vrf_name up
+	vlan_create $if_name $vid $vrf_name "${ips[@]}"
+}
+
+vlan_host_destroy()
+{
+	local if_name=$1; shift
+	local vid=$1; shift
+	local vrf_name=$1; shift
+
+	vlan_destroy $if_name $vid
+	ip link set dev $vrf_name down
+	vrf_destroy $vrf_name
+}
+
+h1_create()
+{
+	vlan_host_create $h1 333 vrf-h1 192.0.2.1/28
+	ip -4 route add 192.0.2.16/28 vrf vrf-h1 nexthop via 192.0.2.2
+}
+
+h1_destroy()
+{
+	ip -4 route del 192.0.2.16/28 vrf vrf-h1
+	vlan_host_destroy $h1 333 vrf-h1
+}
+
+h2_create()
+{
+	vlan_host_create $h1 555 vrf-h2 192.0.2.18/28
+	ip -4 route add 192.0.2.0/28 vrf vrf-h2 nexthop via 192.0.2.17
+}
+
+h2_destroy()
+{
+	ip -4 route del 192.0.2.0/28 vrf vrf-h2
+	vlan_host_destroy $h1 555 vrf-h2
+}
+
+h3_create_team()
+{
+	team_create lag2 lacp $h3 $h4
+	__simple_if_init lag2 vrf-h3 192.0.2.130/32
+	ip -4 route add vrf vrf-h3 192.0.2.129/32 dev lag2
+}
+
+h3_destroy_team()
+{
+	ip -4 route del vrf vrf-h3 192.0.2.129/32 dev lag2
+	__simple_if_fini lag2 192.0.2.130/32
+	team_destroy lag2
+
+	ip link set dev $h3 down
+	ip link set dev $h4 down
+}
+
+h3_create()
+{
+	vrf_create vrf-h3
+	ip link set dev vrf-h3 up
+	tc qdisc add dev $h3 clsact
+	tc qdisc add dev $h4 clsact
+	h3_create_team
+}
+
+h3_destroy()
+{
+	h3_destroy_team
+	tc qdisc del dev $h4 clsact
+	tc qdisc del dev $h3 clsact
+	ip link set dev vrf-h3 down
+	vrf_destroy vrf-h3
+}
+
+switch_create()
+{
+	ip link set dev $swp1 up
+	tc qdisc add dev $swp1 clsact
+	vlan_create $swp1 333 "" 192.0.2.2/28
+	vlan_create $swp1 555 "" 192.0.2.17/28
+
+	tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \
+		      ttl 100 tos inherit
+
+	ip link set dev $swp3 up
+	ip link set dev $swp4 up
+	team_create lag1 lacp $swp3 $swp4
+	__addr_add_del lag1 add 192.0.2.129/32
+	ip -4 route add 192.0.2.130/32 dev lag1
+}
+
+switch_destroy()
+{
+	ip -4 route del 192.0.2.130/32 dev lag1
+	__addr_add_del lag1 del 192.0.2.129/32
+	team_destroy lag1
+
+	ip link set dev $swp4 down
+	ip link set dev $swp3 down
+
+	tunnel_destroy gt4
+
+	vlan_destroy $swp1 555
+	vlan_destroy $swp1 333
+	tc qdisc del dev $swp1 clsact
+	ip link set dev $swp1 down
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp3=${NETIFS[p3]}
+	h3=${NETIFS[p4]}
+
+	swp4=${NETIFS[p5]}
+	h4=${NETIFS[p6]}
+
+	vrf_prepare
+
+	ip link set dev $h1 up
+	h1_create
+	h2_create
+	h3_create
+	switch_create
+
+	trap_install $h3 ingress
+	trap_install $h4 ingress
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	trap_uninstall $h4 ingress
+	trap_uninstall $h3 ingress
+
+	switch_destroy
+	h3_destroy
+	h2_destroy
+	h1_destroy
+	ip link set dev $h1 down
+
+	vrf_cleanup
+}
+
+test_lag_slave()
+{
+	local up_dev=$1; shift
+	local down_dev=$1; shift
+	local what=$1; shift
+
+	RET=0
+
+	mirror_install $swp1 ingress gt4 \
+		       "proto 802.1q flower vlan_id 333 $tcflags"
+
+	# Move $down_dev away from the team. That will prompt change in
+	# txability of the connected device, without changing its upness. The
+	# driver should notice the txability change and move the traffic to the
+	# other slave.
+	ip link set dev $down_dev nomaster
+	sleep 2
+	mirror_test vrf-h1 192.0.2.1 192.0.2.18 $up_dev 1 10
+
+	# Test lack of connectivity when neither slave is txable.
+	ip link set dev $up_dev nomaster
+	sleep 2
+	mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h3 1 0
+	mirror_test vrf-h1 192.0.2.1 192.0.2.18 $h4 1 0
+	mirror_uninstall $swp1 ingress
+
+	# Recreate H3's team device, because mlxsw, which this test is
+	# predominantly mean to test, requires a bottom-up construction and
+	# doesn't allow enslavement to a device that already has an upper.
+	h3_destroy_team
+	h3_create_team
+	# Wait for ${h,swp}{3,4}.
+	setup_wait
+
+	log_test "$what ($tcflags)"
+}
+
+test_mirror_gretap_first()
+{
+	test_lag_slave $h3 $h4 "mirror to gretap: LAG first slave"
+}
+
+test_mirror_gretap_second()
+{
+	test_lag_slave $h4 $h3 "mirror to gretap: LAG second slave"
+}
+
+test_all()
+{
+	slow_path_trap_install $swp1 ingress
+	slow_path_trap_install $swp1 egress
+
+	tests_run
+
+	slow_path_trap_uninstall $swp1 egress
+	slow_path_trap_uninstall $swp1 ingress
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tcflags="skip_hw"
+test_all
+
+if ! tc_offload_check; then
+	echo "WARN: Could not test offloaded functionality"
+else
+	tcflags="skip_sw"
+	test_all
+fi
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 140aada48b5f1a8bed3ba4afb5fc59220651657f Mon Sep 17 00:00:00 2001
From: Dave Kleikamp <dave.kleikamp@oracle.com>
Date: Mon, 30 Jul 2018 10:29:21 -0500
Subject: arm64: kexec: machine_kexec should call __flush_icache_range

machine_kexec flushes the reboot_code_buffer from the icache
after stopping the other cpus.

Commit 3b8c9f1cdfc5 ("arm64: IPI each CPU after invalidating the I-cache
for kernel mappings") added an IPI call to flush_icache_range, which
causes a hang here, so replace the call with __flush_icache_range

Signed-off-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Cc: AKASHI Takahiro <takahiro.akashi@linaro.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/machine_kexec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index f62effc6e064..e8c02832b7ad 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -184,7 +184,7 @@ void machine_kexec(struct kimage *kimage)
 
 	/* Flush the reboot_code_buffer in preparation for its execution. */
 	__flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);
-	flush_icache_range((uintptr_t)reboot_code_buffer,
+	__flush_icache_range((uintptr_t)reboot_code_buffer,
 		arm64_relocate_new_kernel_size);
 
 	/* Flush the kimage list and its buffers. */
-- 
cgit v1.2.3


From 0d0e14770d4487a7ede8df93d82305cbfac2d453 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 27 Jul 2018 18:23:18 -0700
Subject: MIPS: Make (UN)CAC_ADDR() PHYS_OFFSET-agnostic

Converting an address between cached & uncached (typically addresses in
(c)kseg0 & (c)kseg1 or 2 xkphys regions) should not depend upon
PHYS_OFFSET in any way - we're converting from a virtual address in one
unmapped region to a virtual address in another unmapped region.

For some reason our CAC_ADDR() & UNCAC_ADDR() macros make use of
PAGE_OFFSET, which typically includes PHYS_OFFSET. This means that
platforms with a non-zero PHYS_OFFSET typically have to workaround
miscalculation by these 2 macros by also defining UNCAC_BASE to a value
that isn't really correct.

It appears that an attempt has previously been made to address this with
commit 3f4579252aa1 ("MIPS: make CAC_ADDR and UNCAC_ADDR account for
PHYS_OFFSET") which was later undone by commit ed3ce16c3d2b ("Revert
"MIPS: make CAC_ADDR and UNCAC_ADDR account for PHYS_OFFSET"") which
also introduced the ar7 workaround. That attempt at a fix was roughly
equivalent, but essentially caused the CAC_ADDR() & UNCAC_ADDR() macros
to cancel out PHYS_OFFSET by adding & then subtracting it again. In his
revert Leonid is correct that using PHYS_OFFSET makes no sense in the
context of these macros, but appears to have missed its inclusion via
PAGE_OFFSET which means PHYS_OFFSET actually had an effect after the
revert rather than before it.

Here we fix this by modifying CAC_ADDR() & UNCAC_ADDR() to stop using
PAGE_OFFSET (& thus PHYS_OFFSET), instead using __pa() & __va() along
with UNCAC_BASE.

For UNCAC_ADDR(), __pa() will convert a cached address to a physical
address which we can simply use as an offset from UNCAC_BASE to obtain
an address in the uncached region.

For CAC_ADDR() we can undo the effect of UNCAC_ADDR() by subtracting
UNCAC_BASE and using __va() on the result.

With this change made, remove definitions of UNCAC_BASE from the ar7 &
pic32 platforms which appear to have defined them only to workaround
this problem.

Signed-off-by: Paul Burton <paul.burton@mips.com>
References: 3f4579252aa1 ("MIPS: make CAC_ADDR and UNCAC_ADDR account for PHYS_OFFSET")
References: ed3ce16c3d2b ("Revert "MIPS: make CAC_ADDR and UNCAC_ADDR account for PHYS_OFFSET"")
Patchwork: https://patchwork.linux-mips.org/patch/20046/
Cc: Florian Fainelli <f.fainelli@gmail.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: Vladimir Kondratiev <vladimir.kondratiev@intel.com>
---
 arch/mips/include/asm/mach-ar7/spaces.h   | 3 ---
 arch/mips/include/asm/mach-pic32/spaces.h | 1 -
 arch/mips/include/asm/page.h              | 4 ++--
 arch/mips/jazz/jazzdma.c                  | 2 +-
 arch/mips/mm/dma-noncoherent.c            | 2 +-
 5 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/mips/include/asm/mach-ar7/spaces.h b/arch/mips/include/asm/mach-ar7/spaces.h
index 660ab64c0fc9..a004d94dfbdd 100644
--- a/arch/mips/include/asm/mach-ar7/spaces.h
+++ b/arch/mips/include/asm/mach-ar7/spaces.h
@@ -17,9 +17,6 @@
 #define PAGE_OFFSET	_AC(0x94000000, UL)
 #define PHYS_OFFSET	_AC(0x14000000, UL)
 
-#define UNCAC_BASE	_AC(0xb4000000, UL)	/* 0xa0000000 + PHYS_OFFSET */
-#define IO_BASE		UNCAC_BASE
-
 #include <asm/mach-generic/spaces.h>
 
 #endif /* __ASM_AR7_SPACES_H */
diff --git a/arch/mips/include/asm/mach-pic32/spaces.h b/arch/mips/include/asm/mach-pic32/spaces.h
index 046a0a9aa8b3..a1b9783b76ea 100644
--- a/arch/mips/include/asm/mach-pic32/spaces.h
+++ b/arch/mips/include/asm/mach-pic32/spaces.h
@@ -16,7 +16,6 @@
 
 #ifdef CONFIG_PIC32MZDA
 #define PHYS_OFFSET	_AC(0x08000000, UL)
-#define UNCAC_BASE	_AC(0xa8000000, UL)
 #endif
 
 #include <asm/mach-generic/spaces.h>
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index ad461216b5a1..a051b82f8009 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -252,8 +252,8 @@ extern int __virt_addr_valid(const volatile void *kaddr);
 	 ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0) | \
 	 VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
-#define UNCAC_ADDR(addr)	((addr) - PAGE_OFFSET + UNCAC_BASE)
-#define CAC_ADDR(addr)		((addr) - UNCAC_BASE + PAGE_OFFSET)
+#define UNCAC_ADDR(addr)	(UNCAC_BASE + __pa(addr))
+#define CAC_ADDR(addr)		((unsigned long)__va((addr) - UNCAC_BASE))
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/getorder.h>
diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c
index 446fc8c92e1e..d31bc2f01208 100644
--- a/arch/mips/jazz/jazzdma.c
+++ b/arch/mips/jazz/jazzdma.c
@@ -576,7 +576,7 @@ static void *jazz_dma_alloc(struct device *dev, size_t size,
 
 	if (!(attrs & DMA_ATTR_NON_CONSISTENT)) {
 		dma_cache_wback_inv((unsigned long)ret, size);
-		ret = UNCAC_ADDR(ret);
+		ret = (void *)UNCAC_ADDR(ret);
 	}
 	return ret;
 }
diff --git a/arch/mips/mm/dma-noncoherent.c b/arch/mips/mm/dma-noncoherent.c
index 25edf6d6b686..2aca1236af36 100644
--- a/arch/mips/mm/dma-noncoherent.c
+++ b/arch/mips/mm/dma-noncoherent.c
@@ -78,7 +78,7 @@ void *arch_dma_alloc(struct device *dev, size_t size,
 
 	if (!dev_is_coherent(dev) && !(attrs & DMA_ATTR_NON_CONSISTENT)) {
 		dma_cache_wback_inv((unsigned long) ret, size);
-		ret = UNCAC_ADDR(ret);
+		ret = (void *)UNCAC_ADDR(ret);
 	}
 
 	return ret;
-- 
cgit v1.2.3


From 0494d7ffdcebc6935410ea0719b24ab626675351 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 27 Jul 2018 18:23:19 -0700
Subject: MIPS: Fix ISA virt/bus conversion for non-zero PHYS_OFFSET

isa_virt_to_bus() & isa_bus_to_virt() claim to treat ISA bus addresses
as being identical to physical addresses, but they fail to do so in the
presence of a non-zero PHYS_OFFSET.

Correct this by having them use virt_to_phys() & phys_to_virt(), which
consolidates the calculations to one place & ensures that ISA bus
addresses do indeed match physical addresses.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20047/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: Vladimir Kondratiev <vladimir.kondratiev@intel.com>
---
 arch/mips/include/asm/io.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index cd170d920d55..54c730aed327 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -143,14 +143,14 @@ static inline void * phys_to_virt(unsigned long address)
 /*
  * ISA I/O bus memory addresses are 1:1 with the physical address.
  */
-static inline unsigned long isa_virt_to_bus(volatile void * address)
+static inline unsigned long isa_virt_to_bus(volatile void *address)
 {
-	return (unsigned long)address - PAGE_OFFSET;
+	return virt_to_phys(address);
 }
 
-static inline void * isa_bus_to_virt(unsigned long address)
+static inline void *isa_bus_to_virt(unsigned long address)
 {
-	return (void *)(address + PAGE_OFFSET);
+	return phys_to_virt(address);
 }
 
 #define isa_page_to_bus page_to_phys
-- 
cgit v1.2.3


From 6c359eb1dcdb721908f4336171ed8eb6d78190c5 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 27 Jul 2018 18:23:20 -0700
Subject: MIPS: Allow auto-dection of ARCH_PFN_OFFSET & PHYS_OFFSET

On systems where physical memory begins at a non-zero address, defining
PHYS_OFFSET (which influences ARCH_PFN_OFFSET) can save us time & memory
by avoiding book-keeping for pages from address zero to the start of
memory.

Some MIPS platforms already make use of this, but with the definition of
PHYS_OFFSET being compile-time constant it hasn't been possible to
enable this optimization for a kernel which may run on systems with
varying physical memory base addresses.

Introduce a new Kconfig option CONFIG_MIPS_AUTO_PFN_OFFSET which, when
enabled, makes ARCH_PFN_OFFSET a variable & detects it from the boot
memory map (which for example may have been populated from DT). The
relationship with PHYS_OFFSET is reversed, with PHYS_OFFSET now being
based on ARCH_PFN_OFFSET. This is because ARCH_PFN_OFFSET is used far
more often, so avoiding the need for runtime calculation gives us a
smaller impact on kernel text size (0.1% rather than 0.15% for
64r6el_defconfig).

Signed-off-by: Paul Burton <paul.burton@mips.com>
Suggested-by: Vladimir Kondratiev <vladimir.kondratiev@intel.com>
Patchwork: https://patchwork.linux-mips.org/patch/20048/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig                           |  3 +++
 arch/mips/include/asm/mach-generic/spaces.h | 10 +++++++---
 arch/mips/include/asm/page.h                |  7 ++++++-
 arch/mips/kernel/setup.c                    | 14 ++++++++++++--
 4 files changed, 28 insertions(+), 6 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 10256056647c..fbf7f678e856 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2985,6 +2985,9 @@ config PGTABLE_LEVELS
 	default 3 if 64BIT && !PAGE_SIZE_64KB
 	default 2
 
+config MIPS_AUTO_PFN_OFFSET
+	bool
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/mips/include/asm/mach-generic/spaces.h b/arch/mips/include/asm/mach-generic/spaces.h
index 952b0fdfda0e..ee5ebe98f6cf 100644
--- a/arch/mips/include/asm/mach-generic/spaces.h
+++ b/arch/mips/include/asm/mach-generic/spaces.h
@@ -17,9 +17,13 @@
 /*
  * This gives the physical RAM offset.
  */
-#ifndef PHYS_OFFSET
-#define PHYS_OFFSET		_AC(0, UL)
-#endif
+#ifndef __ASSEMBLY__
+# if defined(CONFIG_MIPS_AUTO_PFN_OFFSET)
+#  define PHYS_OFFSET		((unsigned long)PFN_PHYS(ARCH_PFN_OFFSET))
+# elif !defined(PHYS_OFFSET)
+#  define PHYS_OFFSET		_AC(0, UL)
+# endif
+#endif /* __ASSEMBLY__ */
 
 #ifdef CONFIG_32BIT
 #ifdef CONFIG_KVM_GUEST
diff --git a/arch/mips/include/asm/page.h b/arch/mips/include/asm/page.h
index a051b82f8009..e8cc328fce2d 100644
--- a/arch/mips/include/asm/page.h
+++ b/arch/mips/include/asm/page.h
@@ -80,7 +80,12 @@ extern void build_copy_page(void);
  * used in our early mem init code for all memory models.
  * So always define it.
  */
-#define ARCH_PFN_OFFSET		PFN_UP(PHYS_OFFSET)
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+extern unsigned long ARCH_PFN_OFFSET;
+# define ARCH_PFN_OFFSET	ARCH_PFN_OFFSET
+#else
+# define ARCH_PFN_OFFSET	PFN_UP(PHYS_OFFSET)
+#endif
 
 extern void clear_page(void * page);
 extern void copy_page(void * to, void * from);
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 3d4524309b5c..c71d1eb7da59 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -85,6 +85,11 @@ static struct resource bss_resource = { .name = "Kernel bss", };
 
 static void *detect_magic __initdata = detect_memory_region;
 
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+unsigned long ARCH_PFN_OFFSET;
+EXPORT_SYMBOL(ARCH_PFN_OFFSET);
+#endif
+
 void __init add_memory_region(phys_addr_t start, phys_addr_t size, long type)
 {
 	int x = boot_mem_map.nr_map;
@@ -442,6 +447,12 @@ static void __init bootmem_init(void)
 		mapstart = max(reserved_end, start);
 	}
 
+	if (min_low_pfn >= max_low_pfn)
+		panic("Incorrect memory mapping !!!");
+
+#ifdef CONFIG_MIPS_AUTO_PFN_OFFSET
+	ARCH_PFN_OFFSET = PFN_UP(ramstart);
+#else
 	/*
 	 * Reserve any memory between the start of RAM and PHYS_OFFSET
 	 */
@@ -449,8 +460,6 @@ static void __init bootmem_init(void)
 		add_memory_region(PHYS_OFFSET, ramstart - PHYS_OFFSET,
 				  BOOT_MEM_RESERVED);
 
-	if (min_low_pfn >= max_low_pfn)
-		panic("Incorrect memory mapping !!!");
 	if (min_low_pfn > ARCH_PFN_OFFSET) {
 		pr_info("Wasting %lu bytes for tracking %lu unused pages\n",
 			(min_low_pfn - ARCH_PFN_OFFSET) * sizeof(struct page),
@@ -460,6 +469,7 @@ static void __init bootmem_init(void)
 			ARCH_PFN_OFFSET - min_low_pfn);
 	}
 	min_low_pfn = ARCH_PFN_OFFSET;
+#endif
 
 	/*
 	 * Determine low and high memory ranges
-- 
cgit v1.2.3


From 0211d49e5200554eb836c9a12a247d4c11fe571c Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Fri, 27 Jul 2018 18:23:21 -0700
Subject: MIPS: generic: Select MIPS_AUTO_PFN_OFFSET

Enable CONFIG_MIPS_AUTO_PFN_OFFSET for the generic platform, allowing
it to avoid wasted book-keeping for pages with addresses lower than the
physical base address of memory.

This has a minimal impact on kernel text size, with 64r6el_defconfig
gaining 0.1% in size as reported by bloat-o-meter:

  add/remove: 4/1 grow/shrink: 345/13 up/down: 9017/-392 (8625)
  Function                                     old     new   delta
  pcpu_setup_first_chunk                      1444    1780    +336
  pcpu_alloc_first_chunk                       864    1136    +272
  start_kernel                                1064    1288    +224
  initcall_blacklist                           224     372    +148
  try_fill_recv                               2088    2184     +96
  ...
  Total: Before=8457273, After=8465898, chg +0.10%

The gain for systems with large offsets to physical memory & the ability
to continue using generic kernels on such systems seems well worth this
small cost.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Suggested-by: Vladimir Kondratiev <vladimir.kondratiev@intel.com>
Patchwork: https://patchwork.linux-mips.org/patch/20049/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index fbf7f678e856..c95eb5ad0d96 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -98,6 +98,7 @@ config MIPS_GENERIC
 	select HW_HAS_PCI
 	select IRQ_MIPS_CPU
 	select LIBFDT
+	select MIPS_AUTO_PFN_OFFSET
 	select MIPS_CPU_SCACHE
 	select MIPS_GIC
 	select MIPS_L1_CACHE_SHIFT_7
-- 
cgit v1.2.3


From 684ad537abff987886d63fb3c573eeca40d7f2db Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Wed, 25 Jul 2018 16:00:18 -0400
Subject: timekeeping: Prevent false warning when persistent clock is not
 available

On arches with no persistent clock a message like this is printed during
boot:

[    0.000000] Persistent clock returned invalid value

The value is not invalid: Zero means that no persistent clock is available
and the absence of persistent clock should be quietly accepted.

Fixes: 3eca993740b8 ("timekeeping: Replace read_boot_clock64() with read_persistent_wall_and_boot_offset()")
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Cc: sboyd@kernel.org
Cc: john.stultz@linaro.org
Link: https://lkml.kernel.org/r/20180725200018.23722-1-pasha.tatashin@oracle.com
---
 kernel/time/timekeeping.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index 30d7f64ffc87..6183e7460138 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1536,7 +1536,7 @@ void __init timekeeping_init(void)
 	if (timespec64_valid_strict(&wall_time) &&
 	    timespec64_to_ns(&wall_time) > 0) {
 		persistent_clock_exists = true;
-	} else {
+	} else if (timespec64_to_ns(&wall_time) != 0) {
 		pr_warn("Persistent clock returned invalid value");
 		wall_time = (struct timespec64){0};
 	}
-- 
cgit v1.2.3


From bd9f943e5d2a42d864f9692477a25034c9d47dcc Mon Sep 17 00:00:00 2001
From: Pavel Tatashin <pasha.tatashin@oracle.com>
Date: Mon, 30 Jul 2018 09:52:52 -0400
Subject: sched/clock: Disable interrupts when calling
 generic_sched_clock_init()

sched_clock_init() used be called early during boot when interrupts were
still disabled. After the recent changes to utilize sched clock early the
sched_clock_init() call happens when interrupts are already enabled, which
triggers the following warning:

WARNING: CPU: 0 PID: 0 at kernel/time/sched_clock.c:180 sched_clock_register+0x44/0x278
[<c001a13c>] (warn_slowpath_null) from [<c052367c>] (sched_clock_register+0x44/0x278)
[<c052367c>] (sched_clock_register) from [<c05238d8>] (generic_sched_clock_init+0x28/0x88)
[<c05238d8>] (generic_sched_clock_init) from [<c0521a00>] (sched_clock_init+0x54/0x74)
[<c0521a00>] (sched_clock_init) from [<c0519c18>] (start_kernel+0x310/0x3e4)
[<c0519c18>] (start_kernel) from [<00000000>] (  (null))

Disable IRQs for the duration of generic_sched_clock_init().

Fixes: 857baa87b642 ("sched/clock: Enable sched clock early")
Signed-off-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Reported-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: steven.sistare@oracle.com
Cc: daniel.m.jordan@oracle.com
Link: https://lkml.kernel.org/r/20180730135252.24599-1-pasha.tatashin@oracle.com
---
 kernel/sched/clock.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index 811a39aca1ce..e3e3b979f9bd 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -452,7 +452,9 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event);
 void __init sched_clock_init(void)
 {
 	static_branch_inc(&sched_clock_running);
+	local_irq_disable();
 	generic_sched_clock_init();
+	local_irq_enable();
 }
 
 u64 sched_clock_cpu(int cpu)
-- 
cgit v1.2.3


From 608008a45798fe9e2aee04f99b5270ea57c1376f Mon Sep 17 00:00:00 2001
From: Dou Liyang <douly.fnst@cn.fujitsu.com>
Date: Mon, 30 Jul 2018 15:54:20 +0800
Subject: x86/tsc: Consolidate init code

Split out suplicated code from tsc_early_init() and tsc_init() into a
common helper and fixup some comment typos.

[ tglx: Massaged changelog and renamed function ]

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lkml.kernel.org/r/20180730075421.22830-2-douly.fnst@cn.fujitsu.com
---
 arch/x86/kernel/tsc.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 02e416b87ac1..1463468ba9a0 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -182,7 +182,7 @@ static void __init cyc2ns_init_boot_cpu(void)
 }
 
 /*
- * Secondary CPUs do not run through cyc2ns_init(), so set up
+ * Secondary CPUs do not run through tsc_init(), so set up
  * all the scale factors for all CPUs, assuming the same
  * speed as the bootup CPU. (cpufreq notifiers will fix this
  * up if their speed diverges)
@@ -1389,7 +1389,7 @@ static bool __init determine_cpu_tsc_frequencies(bool early)
 	}
 
 	/*
-	 * Trust non-zero tsc_khz as authorative,
+	 * Trust non-zero tsc_khz as authoritative,
 	 * and use it to sanity check cpu_khz,
 	 * which will be off if system timer is off.
 	 */
@@ -1421,6 +1421,14 @@ static unsigned long __init get_loops_per_jiffy(void)
 	return lpj;
 }
 
+static void __init tsc_enable_sched_clock(void)
+{
+	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
+	tsc_store_and_check_tsc_adjust(true);
+	cyc2ns_init_boot_cpu();
+	static_branch_enable(&__use_tsc);
+}
+
 void __init tsc_early_init(void)
 {
 	if (!boot_cpu_has(X86_FEATURE_TSC))
@@ -1429,10 +1437,7 @@ void __init tsc_early_init(void)
 		return;
 	loops_per_jiffy = get_loops_per_jiffy();
 
-	/* Sanitize TSC ADJUST before cyc2ns gets initialized */
-	tsc_store_and_check_tsc_adjust(true);
-	cyc2ns_init_boot_cpu();
-	static_branch_enable(&__use_tsc);
+	tsc_enable_sched_clock();
 }
 
 void __init tsc_init(void)
@@ -1456,13 +1461,10 @@ void __init tsc_init(void)
 			setup_clear_cpu_cap(X86_FEATURE_TSC_DEADLINE_TIMER);
 			return;
 		}
-		/* Sanitize TSC ADJUST before cyc2ns gets initialized */
-		tsc_store_and_check_tsc_adjust(true);
-		cyc2ns_init_boot_cpu();
+		tsc_enable_sched_clock();
 	}
 
 	cyc2ns_init_secondary_cpus();
-	static_branch_enable(&__use_tsc);
 
 	if (!no_sched_irq_time)
 		enable_sched_clock_irqtime();
-- 
cgit v1.2.3


From 1088c6eef261939bda8346ec35b513790a2111d5 Mon Sep 17 00:00:00 2001
From: Dou Liyang <douly.fnst@cn.fujitsu.com>
Date: Mon, 30 Jul 2018 15:54:21 +0800
Subject: x86/kvmclock: Mark kvm_get_preset_lpj() as __init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

kvm_get_preset_lpj() is only called from kvmclock_init(), so mark it __init
as well.

Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Pavel Tatashin <pasha.tatashin@oracle.com>
Cc: <hpa@zytor.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc:   Radim Krčmář<rkrcmar@redhat.com>
Cc:  <kvm@vger.kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: "Radim Krčmář" <rkrcmar@redhat.com>
Cc: kvm@vger.kernel.org
Link: https://lkml.kernel.org/r/20180730075421.22830-3-douly.fnst@cn.fujitsu.com
---
 arch/x86/kernel/kvmclock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 91b94c0ae4e3..d2edd7e6c294 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -145,7 +145,7 @@ static unsigned long kvm_get_tsc_khz(void)
 	return pvclock_tsc_khz(this_cpu_pvti());
 }
 
-static void kvm_get_preset_lpj(void)
+static void __init kvm_get_preset_lpj(void)
 {
 	unsigned long khz;
 	u64 lpj;
-- 
cgit v1.2.3


From 6386889ac23e2c1c8276a111765421577539dd7a Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@bootlin.com>
Date: Wed, 25 Jul 2018 14:26:20 +0200
Subject: MIPS: mscc: ocelot: add interrupt controller properties to GPIO
 controller

The GPIO controller also serves as an interrupt controller for events
on the GPIO it handles.

An interrupt occurs whenever a GPIO line has changed.

Signed-off-by: Quentin Schulz <quentin.schulz@bootlin.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20015/
Cc: robh+dt@kernel.org
Cc: mark.rutland@arm.com
Cc: ralf@linux-mips.org
Cc: jhogan@kernel.org
Cc: linux-gpio@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: thomas.petazzoni@bootlin.com
---
 arch/mips/boot/dts/mscc/ocelot.dtsi | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index d7f0e3551500..afe8fc9011ea 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -168,6 +168,9 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 			gpio-ranges = <&gpio 0 0 22>;
+			interrupt-controller;
+			interrupts = <13>;
+			#interrupt-cells = <2>;
 
 			uart_pins: uart-pins {
 				pins = "GPIO_6", "GPIO_7";
-- 
cgit v1.2.3


From 1e3c43a7f111943fb6bb7cafa9d1e9834d6b2b0e Mon Sep 17 00:00:00 2001
From: Kalle Valo <kvalo@codeaurora.org>
Date: Wed, 25 Jul 2018 10:59:37 +0300
Subject: ath10k: fix open brace location in ath10k_wmi_tlv_op_gen_dbglog_cfg()

Fixes a recently added checkpatch warning:

wmi-tlv.c:2703: open brace '{' following function definitions go on the next line

Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index b04f86f8038a..435295dfe0d4 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -2702,7 +2702,8 @@ ath10k_wmi_tlv_op_gen_force_fw_hang(struct ath10k *ar,
 
 static struct sk_buff *
 ath10k_wmi_tlv_op_gen_dbglog_cfg(struct ath10k *ar, u64 module_enable,
-				 u32 log_level) {
+				 u32 log_level)
+{
 	struct wmi_tlv_dbglog_cmd *cmd;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
-- 
cgit v1.2.3


From 5db1b1e1ee34871b1965b3f890e3ccbdb185fa52 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Mon, 30 Jul 2018 21:44:33 +0800
Subject: x86/boot/KASLR: Make local variable mem_limit static

Fix the following sparse warning:

arch/x86/boot/compressed/kaslr.c:102:20: warning: symbol 'mem_limit' was not declared. Should it be static?

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: <gregkh@linuxfoundation.org>
Link: https://lkml.kernel.org/r/1532958273-47725-1-git-send-email-zhongjiang@huawei.com
---
 arch/x86/boot/compressed/kaslr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index 531c9876f573..302517929932 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -102,7 +102,7 @@ static bool memmap_too_large;
 
 
 /* Store memory limit specified by "mem=nn[KMG]" or "memmap=nn[KMG]" */
-unsigned long long mem_limit = ULLONG_MAX;
+static unsigned long long mem_limit = ULLONG_MAX;
 
 
 enum mem_avoid_index {
-- 
cgit v1.2.3


From cd93b83ad927b2c7979e0add0343ace59328b461 Mon Sep 17 00:00:00 2001
From: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Date: Wed, 25 Jul 2018 10:59:39 +0300
Subject: ath10k: support for multicast rate control

Issues a wmi command to firmware when multicast rate change is received with the
new BSS_CHANGED_MCAST_RATE flag.  Also fixes the incorrect fixed_rate setting
for CCK rates which got introduced with addition of ath10k_rates_rev2 enum.

Tested on QCA9984 with firmware ver 10.4-3.6-00104

Signed-off-by: Pradeep Kumar Chitrapu <pradeepc@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 54 ++++++++++++++++++++++++++++++++---
 1 file changed, 50 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index 95243b48a179..f068e2b9eacc 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -101,6 +101,8 @@ static struct ieee80211_rate ath10k_rates_rev2[] = {
 #define ath10k_g_rates_rev2 (ath10k_rates_rev2 + 0)
 #define ath10k_g_rates_rev2_size (ARRAY_SIZE(ath10k_rates_rev2))
 
+#define ath10k_wmi_legacy_rates ath10k_rates
+
 static bool ath10k_mac_bitrate_is_cck(int bitrate)
 {
 	switch (bitrate) {
@@ -5439,8 +5441,12 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 {
 	struct ath10k *ar = hw->priv;
 	struct ath10k_vif *arvif = (void *)vif->drv_priv;
-	int ret = 0;
+	struct cfg80211_chan_def def;
 	u32 vdev_param, pdev_param, slottime, preamble;
+	u16 bitrate, hw_value;
+	u8 rate;
+	int rateidx, ret = 0;
+	enum nl80211_band band;
 
 	mutex_lock(&ar->conf_mutex);
 
@@ -5608,6 +5614,44 @@ static void ath10k_bss_info_changed(struct ieee80211_hw *hw,
 				    arvif->vdev_id, ret);
 	}
 
+	if (changed & BSS_CHANGED_MCAST_RATE &&
+	    !WARN_ON(ath10k_mac_vif_chan(arvif->vif, &def))) {
+		band = def.chan->band;
+		rateidx = vif->bss_conf.mcast_rate[band] - 1;
+
+		if (ar->phy_capability & WHAL_WLAN_11A_CAPABILITY)
+			rateidx += ATH10K_MAC_FIRST_OFDM_RATE_IDX;
+
+		bitrate = ath10k_wmi_legacy_rates[rateidx].bitrate;
+		hw_value = ath10k_wmi_legacy_rates[rateidx].hw_value;
+		if (ath10k_mac_bitrate_is_cck(bitrate))
+			preamble = WMI_RATE_PREAMBLE_CCK;
+		else
+			preamble = WMI_RATE_PREAMBLE_OFDM;
+
+		rate = ATH10K_HW_RATECODE(hw_value, 0, preamble);
+
+		ath10k_dbg(ar, ATH10K_DBG_MAC,
+			   "mac vdev %d mcast_rate %x\n",
+			   arvif->vdev_id, rate);
+
+		vdev_param = ar->wmi.vdev_param->mcast_data_rate;
+		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id,
+						vdev_param, rate);
+		if (ret)
+			ath10k_warn(ar,
+				    "failed to set mcast rate on vdev %i: %d\n",
+				    arvif->vdev_id,  ret);
+
+		vdev_param = ar->wmi.vdev_param->bcast_data_rate;
+		ret = ath10k_wmi_vdev_set_param(ar, arvif->vdev_id,
+						vdev_param, rate);
+		if (ret)
+			ath10k_warn(ar,
+				    "failed to set bcast rate on vdev %i: %d\n",
+				    arvif->vdev_id,  ret);
+	}
+
 	mutex_unlock(&ar->conf_mutex);
 }
 
@@ -6935,7 +6979,6 @@ ath10k_mac_bitrate_mask_get_single_rate(struct ath10k *ar,
 					const struct cfg80211_bitrate_mask *mask,
 					u8 *rate, u8 *nss)
 {
-	struct ieee80211_supported_band *sband = &ar->mac.sbands[band];
 	int rate_idx;
 	int i;
 	u16 bitrate;
@@ -6945,8 +6988,11 @@ ath10k_mac_bitrate_mask_get_single_rate(struct ath10k *ar,
 	if (hweight32(mask->control[band].legacy) == 1) {
 		rate_idx = ffs(mask->control[band].legacy) - 1;
 
-		hw_rate = sband->bitrates[rate_idx].hw_value;
-		bitrate = sband->bitrates[rate_idx].bitrate;
+		if (ar->phy_capability & WHAL_WLAN_11A_CAPABILITY)
+			rate_idx += ATH10K_MAC_FIRST_OFDM_RATE_IDX;
+
+		hw_rate = ath10k_wmi_legacy_rates[rate_idx].hw_value;
+		bitrate = ath10k_wmi_legacy_rates[rate_idx].bitrate;
 
 		if (ath10k_mac_bitrate_is_cck(bitrate))
 			preamble = WMI_RATE_PREAMBLE_CCK;
-- 
cgit v1.2.3


From 673bc519c55843c68c3aecff71a4101e79d28d2b Mon Sep 17 00:00:00 2001
From: Surabhi Vishnoi <svishnoi@codeaurora.org>
Date: Wed, 25 Jul 2018 10:59:41 +0300
Subject: ath10k: disable bundle mgmt tx completion event support

The tx completion of multiple mgmt frames can be bundled
in a single event and sent by the firmware to host, if this
capability is not disabled explicitly by the host. If the host
cannot handle the bundled mgmt tx completion, this capability
support needs to be disabled in the wmi init cmd, sent to the firmware.

Add the host capability indication flag in the wmi ready command,
to let firmware know the features supported by the host driver.
This field is ignored if it is not supported by firmware.

Set the host capability indication flag(i.e. host_capab) to zero,
for disabling the support of bundle mgmt tx completion. This will
indicate the firmware to send completion event for every mgmt tx
completion, instead of bundling them together and sending in a single
event.

Tested HW: WCN3990
Tested FW: WLAN.HL.2.0-01188-QCAHLSWMTPLZ-1

Signed-off-by: Surabhi Vishnoi <svishnoi@codeaurora.org>
Signed-off-by: Rakesh Pillai <pillair@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 5 +++++
 drivers/net/wireless/ath/ath10k/wmi-tlv.h | 5 +++++
 2 files changed, 10 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 435295dfe0d4..1f8911858a6f 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -1586,6 +1586,11 @@ static struct sk_buff *ath10k_wmi_tlv_op_gen_init(struct ath10k *ar)
 	cfg->keep_alive_pattern_size = __cpu_to_le32(0);
 	cfg->max_tdls_concurrent_sleep_sta = __cpu_to_le32(1);
 	cfg->max_tdls_concurrent_buffer_sta = __cpu_to_le32(1);
+	cfg->wmi_send_separate = __cpu_to_le32(0);
+	cfg->num_ocb_vdevs = __cpu_to_le32(0);
+	cfg->num_ocb_channels = __cpu_to_le32(0);
+	cfg->num_ocb_schedules = __cpu_to_le32(0);
+	cfg->host_capab = __cpu_to_le32(0);
 
 	ath10k_wmi_put_host_mem_chunks(ar, chunks);
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.h b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
index 3e1e340cd834..1cb93d09b8a9 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
@@ -1670,6 +1670,11 @@ struct wmi_tlv_resource_config {
 	__le32 keep_alive_pattern_size;
 	__le32 max_tdls_concurrent_sleep_sta;
 	__le32 max_tdls_concurrent_buffer_sta;
+	__le32 wmi_send_separate;
+	__le32 num_ocb_vdevs;
+	__le32 num_ocb_channels;
+	__le32 num_ocb_schedules;
+	__le32 host_capab;
 } __packed;
 
 struct wmi_tlv_init_cmd {
-- 
cgit v1.2.3


From dc405152bb64d4ae01c9ac669de25b2d1fb6fc2d Mon Sep 17 00:00:00 2001
From: Rakesh Pillai <pillair@codeaurora.org>
Date: Wed, 25 Jul 2018 10:59:45 +0300
Subject: ath10k: handle mgmt tx completion event

WCN3990 transmits management frames via WMI
with reference. Currently, with the management
tx completion not being handled, these frames are
not getting freed even after the transmission status
is returned by the firmware.

The transmitted management frames should be freed
when the firmware sends the over-the-air tx status of
the corresponding management frames.

Handle the wmi mgmt tx completion event and free
the corresponding management frame.

Tested HW: WCN3990
Tested FW: WLAN.HL.2.0-01188-QCAHLSWMTPLZ-1

Signed-off-by: Rakesh Pillai <pillair@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/core.c    |  1 +
 drivers/net/wireless/ath/ath10k/core.h    |  5 ++
 drivers/net/wireless/ath/ath10k/hw.h      |  1 +
 drivers/net/wireless/ath/ath10k/wmi-ops.h | 12 +++++
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 65 ++++++++++++++++++++++-
 drivers/net/wireless/ath/ath10k/wmi-tlv.h | 12 +++++
 drivers/net/wireless/ath/ath10k/wmi.c     | 85 +++++++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath10k/wmi.h     |  7 +++
 8 files changed, 186 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index 85c58ebbfb26..c40cd129afe7 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -2095,6 +2095,7 @@ static int ath10k_core_init_firmware_features(struct ath10k *ar)
 		ar->fw_stats_req_mask = WMI_STAT_PDEV | WMI_STAT_VDEV |
 			WMI_STAT_PEER;
 		ar->max_spatial_stream = WMI_MAX_SPATIAL_STREAM;
+		ar->wmi.mgmt_max_num_pending_tx = TARGET_TLV_MGMT_NUM_MSDU_DESC;
 		break;
 	case ATH10K_FW_WMI_OP_VERSION_10_4:
 		ar->max_num_peers = TARGET_10_4_NUM_PEERS;
diff --git a/drivers/net/wireless/ath/ath10k/core.h b/drivers/net/wireless/ath/ath10k/core.h
index 427ee5752bb0..9feea02e7d37 100644
--- a/drivers/net/wireless/ath/ath10k/core.h
+++ b/drivers/net/wireless/ath/ath10k/core.h
@@ -186,6 +186,11 @@ struct ath10k_wmi {
 	const struct wmi_ops *ops;
 	const struct wmi_peer_flags_map *peer_flags;
 
+	u32 mgmt_max_num_pending_tx;
+
+	/* Protected by data_lock */
+	struct idr mgmt_pending_tx;
+
 	u32 num_mem_chunks;
 	u32 rx_decap_mode;
 	struct ath10k_mem_chunk mem_chunks[WMI_MAX_MEM_REQS];
diff --git a/drivers/net/wireless/ath/ath10k/hw.h b/drivers/net/wireless/ath/ath10k/hw.h
index a274bd809a08..977f79ebb4fd 100644
--- a/drivers/net/wireless/ath/ath10k/hw.h
+++ b/drivers/net/wireless/ath/ath10k/hw.h
@@ -699,6 +699,7 @@ ath10k_rx_desc_get_l3_pad_bytes(struct ath10k_hw_params *hw,
 #define TARGET_TLV_NUM_TIDS			((TARGET_TLV_NUM_PEERS) * 2)
 #define TARGET_TLV_NUM_MSDU_DESC		(1024 + 32)
 #define TARGET_TLV_NUM_WOW_PATTERNS		22
+#define TARGET_TLV_MGMT_NUM_MSDU_DESC		(50)
 
 /* Target specific defines for WMI-HL-1.0 firmware */
 #define TARGET_HL_10_TLV_NUM_PEERS		14
diff --git a/drivers/net/wireless/ath/ath10k/wmi-ops.h b/drivers/net/wireless/ath/ath10k/wmi-ops.h
index 5ecce04005d2..7fd63bbf8e24 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-ops.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-ops.h
@@ -31,6 +31,8 @@ struct wmi_ops {
 			 struct wmi_scan_ev_arg *arg);
 	int (*pull_mgmt_rx)(struct ath10k *ar, struct sk_buff *skb,
 			    struct wmi_mgmt_rx_ev_arg *arg);
+	int (*pull_mgmt_tx_compl)(struct ath10k *ar, struct sk_buff *skb,
+				  struct wmi_tlv_mgmt_tx_compl_ev_arg *arg);
 	int (*pull_ch_info)(struct ath10k *ar, struct sk_buff *skb,
 			    struct wmi_ch_info_ev_arg *arg);
 	int (*pull_vdev_start)(struct ath10k *ar, struct sk_buff *skb,
@@ -261,6 +263,16 @@ ath10k_wmi_pull_scan(struct ath10k *ar, struct sk_buff *skb,
 	return ar->wmi.ops->pull_scan(ar, skb, arg);
 }
 
+static inline int
+ath10k_wmi_pull_mgmt_tx_compl(struct ath10k *ar, struct sk_buff *skb,
+			      struct wmi_tlv_mgmt_tx_compl_ev_arg *arg)
+{
+	if (!ar->wmi.ops->pull_mgmt_tx_compl)
+		return -EOPNOTSUPP;
+
+	return ar->wmi.ops->pull_mgmt_tx_compl(ar, skb, arg);
+}
+
 static inline int
 ath10k_wmi_pull_mgmt_rx(struct ath10k *ar, struct sk_buff *skb,
 			struct wmi_mgmt_rx_ev_arg *arg)
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 1f8911858a6f..95344c3e6505 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -618,6 +618,9 @@ static void ath10k_wmi_tlv_op_rx(struct ath10k *ar, struct sk_buff *skb)
 	case WMI_TLV_TDLS_PEER_EVENTID:
 		ath10k_wmi_event_tdls_peer(ar, skb);
 		break;
+	case WMI_TLV_MGMT_TX_COMPLETION_EVENTID:
+		ath10k_wmi_event_mgmt_tx_compl(ar, skb);
+		break;
 	default:
 		ath10k_warn(ar, "Unknown eventid: %d\n", id);
 		break;
@@ -659,6 +662,31 @@ static int ath10k_wmi_tlv_op_pull_scan_ev(struct ath10k *ar,
 	return 0;
 }
 
+static int
+ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev(struct ath10k *ar, struct sk_buff *skb,
+					struct wmi_tlv_mgmt_tx_compl_ev_arg *arg)
+{
+	const void **tb;
+	const struct wmi_tlv_mgmt_tx_compl_ev *ev;
+	int ret;
+
+	tb = ath10k_wmi_tlv_parse_alloc(ar, skb->data, skb->len, GFP_ATOMIC);
+	if (IS_ERR(tb)) {
+		ret = PTR_ERR(tb);
+		ath10k_warn(ar, "failed to parse tlv: %d\n", ret);
+		return ret;
+	}
+
+	ev = tb[WMI_TLV_TAG_STRUCT_MGMT_TX_COMPL_EVENT];
+
+	arg->desc_id = ev->desc_id;
+	arg->status = ev->status;
+	arg->pdev_id = ev->pdev_id;
+
+	kfree(tb);
+	return 0;
+}
+
 static int ath10k_wmi_tlv_op_pull_mgmt_rx_ev(struct ath10k *ar,
 					     struct sk_buff *skb,
 					     struct wmi_mgmt_rx_ev_arg *arg)
@@ -2612,6 +2640,30 @@ ath10k_wmi_tlv_op_gen_request_stats(struct ath10k *ar, u32 stats_mask)
 	return skb;
 }
 
+static int
+ath10k_wmi_mgmt_tx_alloc_msdu_id(struct ath10k *ar, struct sk_buff *skb,
+				 dma_addr_t paddr)
+{
+	struct ath10k_wmi *wmi = &ar->wmi;
+	struct ath10k_mgmt_tx_pkt_addr *pkt_addr;
+	int ret;
+
+	pkt_addr = kmalloc(sizeof(*pkt_addr), GFP_ATOMIC);
+	if (!pkt_addr)
+		return -ENOMEM;
+
+	pkt_addr->vaddr = skb;
+	pkt_addr->paddr = paddr;
+
+	spin_lock_bh(&ar->data_lock);
+	ret = idr_alloc(&wmi->mgmt_pending_tx, pkt_addr, 0,
+			wmi->mgmt_max_num_pending_tx, GFP_ATOMIC);
+	spin_unlock_bh(&ar->data_lock);
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi mgmt tx alloc msdu_id ret %d\n", ret);
+	return ret;
+}
+
 static struct sk_buff *
 ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 				   dma_addr_t paddr)
@@ -2623,9 +2675,9 @@ ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 	u32 buf_len = msdu->len;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
+	int len, desc_id;
 	u32 vdev_id;
 	void *ptr;
-	int len;
 
 	if (!cb->vif)
 		return ERR_PTR(-EINVAL);
@@ -2656,13 +2708,17 @@ ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 	if (!skb)
 		return ERR_PTR(-ENOMEM);
 
+	desc_id = ath10k_wmi_mgmt_tx_alloc_msdu_id(ar, msdu, paddr);
+	if (desc_id < 0)
+		goto err_free_skb;
+
 	ptr = (void *)skb->data;
 	tlv = ptr;
 	tlv->tag = __cpu_to_le16(WMI_TLV_TAG_STRUCT_MGMT_TX_CMD);
 	tlv->len = __cpu_to_le16(sizeof(*cmd));
 	cmd = (void *)tlv->value;
 	cmd->vdev_id = __cpu_to_le32(vdev_id);
-	cmd->desc_id = 0;
+	cmd->desc_id = __cpu_to_le32(desc_id);
 	cmd->chanfreq = 0;
 	cmd->buf_len = __cpu_to_le32(buf_len);
 	cmd->frame_len = __cpu_to_le32(msdu->len);
@@ -2679,6 +2735,10 @@ ath10k_wmi_tlv_op_gen_mgmt_tx_send(struct ath10k *ar, struct sk_buff *msdu,
 	memcpy(ptr, msdu->data, buf_len);
 
 	return skb;
+
+err_free_skb:
+	dev_kfree_skb(skb);
+	return ERR_PTR(desc_id);
 }
 
 static struct sk_buff *
@@ -3843,6 +3903,7 @@ static const struct wmi_ops wmi_tlv_ops = {
 
 	.pull_scan = ath10k_wmi_tlv_op_pull_scan_ev,
 	.pull_mgmt_rx = ath10k_wmi_tlv_op_pull_mgmt_rx_ev,
+	.pull_mgmt_tx_compl = ath10k_wmi_tlv_op_pull_mgmt_tx_compl_ev,
 	.pull_ch_info = ath10k_wmi_tlv_op_pull_ch_info_ev,
 	.pull_vdev_start = ath10k_wmi_tlv_op_pull_vdev_start_ev,
 	.pull_peer_kick = ath10k_wmi_tlv_op_pull_peer_kick_ev,
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.h b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
index 1cb93d09b8a9..4f0c20c90642 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.h
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.h
@@ -320,6 +320,7 @@ enum wmi_tlv_event_id {
 	WMI_TLV_TBTTOFFSET_UPDATE_EVENTID,
 	WMI_TLV_OFFLOAD_BCN_TX_STATUS_EVENTID,
 	WMI_TLV_OFFLOAD_PROB_RESP_TX_STATUS_EVENTID,
+	WMI_TLV_MGMT_TX_COMPLETION_EVENTID,
 	WMI_TLV_TX_DELBA_COMPLETE_EVENTID = WMI_TLV_EV(WMI_TLV_GRP_BA_NEG),
 	WMI_TLV_TX_ADDBA_COMPLETE_EVENTID,
 	WMI_TLV_BA_RSP_SSN_EVENTID,
@@ -1573,6 +1574,17 @@ struct wmi_tlv {
 	u8 value[0];
 } __packed;
 
+struct ath10k_mgmt_tx_pkt_addr {
+	void *vaddr;
+	dma_addr_t paddr;
+};
+
+struct wmi_tlv_mgmt_tx_compl_ev {
+	__le32 desc_id;
+	__le32 status;
+	__le32 pdev_id;
+};
+
 #define WMI_TLV_MGMT_RX_NUM_RSSI 4
 
 struct wmi_tlv_mgmt_rx_ev {
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 877249ac6fd4..6d20baf5ae5c 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -2313,6 +2313,59 @@ static bool ath10k_wmi_rx_is_decrypted(struct ath10k *ar,
 	return true;
 }
 
+static int wmi_process_mgmt_tx_comp(struct ath10k *ar, u32 desc_id,
+				    u32 status)
+{
+	struct ath10k_mgmt_tx_pkt_addr *pkt_addr;
+	struct ath10k_wmi *wmi = &ar->wmi;
+	struct ieee80211_tx_info *info;
+	struct sk_buff *msdu;
+	int ret;
+
+	spin_lock_bh(&ar->data_lock);
+
+	pkt_addr = idr_find(&wmi->mgmt_pending_tx, desc_id);
+	if (!pkt_addr) {
+		ath10k_warn(ar, "received mgmt tx completion for invalid msdu_id: %d\n",
+			    desc_id);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	msdu = pkt_addr->vaddr;
+	dma_unmap_single(ar->dev, pkt_addr->paddr,
+			 msdu->len, DMA_FROM_DEVICE);
+	info = IEEE80211_SKB_CB(msdu);
+	info->flags |= status;
+	ieee80211_tx_status_irqsafe(ar->hw, msdu);
+
+	ret = 0;
+
+out:
+	idr_remove(&wmi->mgmt_pending_tx, desc_id);
+	spin_unlock_bh(&ar->data_lock);
+	return ret;
+}
+
+int ath10k_wmi_event_mgmt_tx_compl(struct ath10k *ar, struct sk_buff *skb)
+{
+	struct wmi_tlv_mgmt_tx_compl_ev_arg arg;
+	int ret;
+
+	ret = ath10k_wmi_pull_mgmt_tx_compl(ar, skb, &arg);
+	if (ret) {
+		ath10k_warn(ar, "failed to parse mgmt comp event: %d\n", ret);
+		return ret;
+	}
+
+	wmi_process_mgmt_tx_comp(ar, __le32_to_cpu(arg.desc_id),
+				 __le32_to_cpu(arg.status));
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI, "wmi tlv evnt mgmt tx completion\n");
+
+	return 0;
+}
+
 int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb)
 {
 	struct wmi_mgmt_rx_ev_arg arg = {};
@@ -9073,6 +9126,11 @@ int ath10k_wmi_attach(struct ath10k *ar)
 	INIT_WORK(&ar->radar_confirmation_work,
 		  ath10k_radar_confirmation_work);
 
+	if (test_bit(ATH10K_FW_FEATURE_MGMT_TX_BY_REF,
+		     ar->running_fw->fw_file.fw_features)) {
+		idr_init(&ar->wmi.mgmt_pending_tx);
+	}
+
 	return 0;
 }
 
@@ -9091,8 +9149,35 @@ void ath10k_wmi_free_host_mem(struct ath10k *ar)
 	ar->wmi.num_mem_chunks = 0;
 }
 
+static int ath10k_wmi_mgmt_tx_clean_up_pending(int msdu_id, void *ptr,
+					       void *ctx)
+{
+	struct ath10k_mgmt_tx_pkt_addr *pkt_addr = ptr;
+	struct ath10k *ar = ctx;
+	struct sk_buff *msdu;
+
+	ath10k_dbg(ar, ATH10K_DBG_WMI,
+		   "force cleanup mgmt msdu_id %hu\n", msdu_id);
+
+	msdu = pkt_addr->vaddr;
+	dma_unmap_single(ar->dev, pkt_addr->paddr,
+			 msdu->len, DMA_FROM_DEVICE);
+	ieee80211_free_txskb(ar->hw, msdu);
+
+	return 0;
+}
+
 void ath10k_wmi_detach(struct ath10k *ar)
 {
+	if (test_bit(ATH10K_FW_FEATURE_MGMT_TX_BY_REF,
+		     ar->running_fw->fw_file.fw_features)) {
+		spin_lock_bh(&ar->data_lock);
+		idr_for_each(&ar->wmi.mgmt_pending_tx,
+			     ath10k_wmi_mgmt_tx_clean_up_pending, ar);
+		idr_destroy(&ar->wmi.mgmt_pending_tx);
+		spin_unlock_bh(&ar->data_lock);
+	}
+
 	cancel_work_sync(&ar->svc_rdy_work);
 
 	if (ar->svc_rdy_skb)
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index d68afb65402a..2c96380d8021 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -6600,6 +6600,12 @@ struct wmi_scan_ev_arg {
 	__le32 vdev_id;
 };
 
+struct wmi_tlv_mgmt_tx_compl_ev_arg {
+	__le32 desc_id;
+	__le32 status;
+	__le32 pdev_id;
+};
+
 struct wmi_mgmt_rx_ev_arg {
 	__le32 channel;
 	__le32 snr;
@@ -7071,6 +7077,7 @@ int ath10k_wmi_start_scan_verify(const struct wmi_start_scan_arg *arg);
 
 int ath10k_wmi_event_scan(struct ath10k *ar, struct sk_buff *skb);
 int ath10k_wmi_event_mgmt_rx(struct ath10k *ar, struct sk_buff *skb);
+int ath10k_wmi_event_mgmt_tx_compl(struct ath10k *ar, struct sk_buff *skb);
 void ath10k_wmi_event_chan_info(struct ath10k *ar, struct sk_buff *skb);
 void ath10k_wmi_event_echo(struct ath10k *ar, struct sk_buff *skb);
 int ath10k_wmi_event_debug_mesg(struct ath10k *ar, struct sk_buff *skb);
-- 
cgit v1.2.3


From 24cfd8ca1d28331b9dad3b88d1958c976b2cfab6 Mon Sep 17 00:00:00 2001
From: Dou Liyang <douly.fnst@cn.fujitsu.com>
Date: Mon, 30 Jul 2018 15:59:47 +0800
Subject: x86/platform/UV: Mark memblock related init code and data correctly

parse_mem_block_size() and mem_block_size are only used during init. Mark
them accordingly.

Fixes: d7609f4210cb ("x86/platform/UV: Add kernel parameter to set memory block size")
Signed-off-by: Dou Liyang <douly.fnst@cn.fujitsu.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: hpa@zytor.com
Cc: Mike Travis <mike.travis@hpe.com>
Cc: Andrew Banman <andrew.banman@hpe.com>
Link: https://lkml.kernel.org/r/20180730075947.23023-1-douly.fnst@cn.fujitsu.com
---
 arch/x86/kernel/apic/x2apic_uv_x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index d492752f79e1..391f358ebb4c 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -394,10 +394,10 @@ extern int uv_hub_info_version(void)
 EXPORT_SYMBOL(uv_hub_info_version);
 
 /* Default UV memory block size is 2GB */
-static unsigned long mem_block_size = (2UL << 30);
+static unsigned long mem_block_size __initdata = (2UL << 30);
 
 /* Kernel parameter to specify UV mem block size */
-static int parse_mem_block_size(char *ptr)
+static int __init parse_mem_block_size(char *ptr)
 {
 	unsigned long size = memparse(ptr, NULL);
 
-- 
cgit v1.2.3


From e6712aa1244fe7b53776858b73bfd1a94a198681 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 9 Jul 2018 13:34:46 +0100
Subject: ath10k: remove redundant pointers 'dev' and 'noa'

Pointers dev and noa are being assigned but are never used hence they
are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'dev' set but not used [-Wunused-but-set-variable]
warning: variable 'noa' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/ahb.c     | 5 -----
 drivers/net/wireless/ath/ath10k/wmi-tlv.c | 2 --
 2 files changed, 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/ahb.c b/drivers/net/wireless/ath/ath10k/ahb.c
index fa39ffffd34d..c9bd0e2b5db7 100644
--- a/drivers/net/wireless/ath/ath10k/ahb.c
+++ b/drivers/net/wireless/ath/ath10k/ahb.c
@@ -133,11 +133,8 @@ static void ath10k_ahb_clock_deinit(struct ath10k *ar)
 static int ath10k_ahb_clock_enable(struct ath10k *ar)
 {
 	struct ath10k_ahb *ar_ahb = ath10k_ahb_priv(ar);
-	struct device *dev;
 	int ret;
 
-	dev = &ar_ahb->pdev->dev;
-
 	if (IS_ERR_OR_NULL(ar_ahb->cmd_clk) ||
 	    IS_ERR_OR_NULL(ar_ahb->ref_clk) ||
 	    IS_ERR_OR_NULL(ar_ahb->rtc_clk)) {
@@ -451,12 +448,10 @@ static int ath10k_ahb_resource_init(struct ath10k *ar)
 {
 	struct ath10k_ahb *ar_ahb = ath10k_ahb_priv(ar);
 	struct platform_device *pdev;
-	struct device *dev;
 	struct resource *res;
 	int ret;
 
 	pdev = ar_ahb->pdev;
-	dev = &pdev->dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!res) {
diff --git a/drivers/net/wireless/ath/ath10k/wmi-tlv.c b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
index 95344c3e6505..cdc1e64d52ad 100644
--- a/drivers/net/wireless/ath/ath10k/wmi-tlv.c
+++ b/drivers/net/wireless/ath/ath10k/wmi-tlv.c
@@ -1820,7 +1820,6 @@ ath10k_wmi_tlv_op_gen_vdev_start(struct ath10k *ar,
 {
 	struct wmi_tlv_vdev_start_cmd *cmd;
 	struct wmi_channel *ch;
-	struct wmi_p2p_noa_descriptor *noa;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
 	size_t len;
@@ -1878,7 +1877,6 @@ ath10k_wmi_tlv_op_gen_vdev_start(struct ath10k *ar,
 	tlv = ptr;
 	tlv->tag = __cpu_to_le16(WMI_TLV_TAG_ARRAY_STRUCT);
 	tlv->len = 0;
-	noa = (void *)tlv->value;
 
 	/* Note: This is a nested TLV containing:
 	 * [wmi_tlv][wmi_p2p_noa_descriptor][wmi_tlv]..
-- 
cgit v1.2.3


From e8c38062efc6ffa38f602eb8ffb8c8b03bcf2b5f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 9 Jul 2018 13:41:38 +0100
Subject: ath5k: remove redundant pointer rf

Pointer rf is being assigned but is never used hence it is redundant
and can be removed.

Cleans up two clang warnings:
warning: variable 'rf' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath5k/phy.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath5k/phy.c b/drivers/net/wireless/ath/ath5k/phy.c
index b1b8bc326830..ae08572c4b58 100644
--- a/drivers/net/wireless/ath/ath5k/phy.c
+++ b/drivers/net/wireless/ath/ath5k/phy.c
@@ -483,7 +483,6 @@ static u32
 ath5k_hw_rf_gainf_corr(struct ath5k_hw *ah)
 {
 	u32 mix, step;
-	u32 *rf;
 	const struct ath5k_gain_opt *go;
 	const struct ath5k_gain_opt_step *g_step;
 	const struct ath5k_rf_reg *rf_regs;
@@ -502,7 +501,6 @@ ath5k_hw_rf_gainf_corr(struct ath5k_hw *ah)
 	if (ah->ah_rf_banks == NULL)
 		return 0;
 
-	rf = ah->ah_rf_banks;
 	ah->ah_gain.g_f_corr = 0;
 
 	/* No VGA (Variable Gain Amplifier) override, skip */
@@ -549,13 +547,10 @@ ath5k_hw_rf_check_gainf_readback(struct ath5k_hw *ah)
 {
 	const struct ath5k_rf_reg *rf_regs;
 	u32 step, mix_ovr, level[4];
-	u32 *rf;
 
 	if (ah->ah_rf_banks == NULL)
 		return false;
 
-	rf = ah->ah_rf_banks;
-
 	if (ah->ah_radio == AR5K_RF5111) {
 
 		rf_regs = rf_regs_5111;
-- 
cgit v1.2.3


From 843c408905010fbc44a564d2de6a3cd68d986abf Mon Sep 17 00:00:00 2001
From: Yi Wang <wang.yi59@zte.com.cn>
Date: Fri, 27 Jul 2018 14:15:03 +0800
Subject: x86/apic: Trivial coding style fixes

There is inconsistent indenting in calibrate_APIC_clock() and
activate_managed(). Remove the surplus TAB.

Signed-off-by: Yi Wang <wang.yi59@zte.com.cn>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn>
Acked-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: hpa@zytor.com
Cc: douly.fnst@cn.fujitsu.com
Cc: jgross@suse.com
Cc: ville.syrjala@linux.intel.com
Cc: len.brown@intel.com
Cc: gregkh@linuxfoundation.org
Cc: zhong.weidong@zte.com.cn
Link: https://lkml.kernel.org/r/1532672103-32250-1-git-send-email-wang.yi59@zte.com.cn
---
 arch/x86/kernel/apic/apic.c   | 2 +-
 arch/x86/kernel/apic/vector.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 2aabd4cb0e3f..00011bc33263 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -937,7 +937,7 @@ static int __init calibrate_APIC_clock(void)
 
 	if (levt->features & CLOCK_EVT_FEAT_DUMMY) {
 		pr_warning("APIC timer disabled due to verification failure\n");
-			return -1;
+		return -1;
 	}
 
 	return 0;
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index a75de0792942..c943499375c3 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -415,7 +415,7 @@ static int activate_managed(struct irq_data *irqd)
 		pr_err("Managed startup irq %u, no vector available\n",
 		       irqd->irq);
 	}
-       return ret;
+	return ret;
 }
 
 static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
-- 
cgit v1.2.3


From 619c9700a8fe017bdbe60e08c21213962b2de87a Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 9 Jul 2018 14:17:20 +0100
Subject: ath6kl: remove redundant variables netlen, orig_buf, orig_len,
 dropped and stats

Variables netlen, orig_buf, orig_len, dropped and stats are assigned values
but are never used hence they are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'netlen' set but not used [-Wunused-but-set-variable]
warning: variable 'orig_buf' set but not used [-Wunused-but-set-variable]
warning: variable 'orig_len' set but not used [-Wunused-but-set-variable]
warning: variable 'dropped' set but not used [-Wunused-but-set-variable]
warning: variable 'stats' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/htc_pipe.c | 10 ++--------
 drivers/net/wireless/ath/ath6kl/main.c     |  3 +--
 drivers/net/wireless/ath/ath6kl/txrx.c     |  2 --
 3 files changed, 3 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/ath/ath6kl/htc_pipe.c b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
index 546243e11737..434b66829646 100644
--- a/drivers/net/wireless/ath/ath6kl/htc_pipe.c
+++ b/drivers/net/wireless/ath/ath6kl/htc_pipe.c
@@ -746,10 +746,8 @@ static int ath6kl_htc_pipe_tx_complete(struct ath6kl *ar, struct sk_buff *skb)
 	struct htc_endpoint *ep;
 	struct htc_packet *packet;
 	u8 ep_id, *netdata;
-	u32 netlen;
 
 	netdata = skb->data;
-	netlen = skb->len;
 
 	htc_hdr = (struct htc_frame_hdr *) netdata;
 
@@ -855,12 +853,8 @@ static int htc_process_trailer(struct htc_target *target, u8 *buffer,
 {
 	struct htc_credit_report *report;
 	struct htc_record_hdr *record;
-	u8 *record_buf, *orig_buf;
-	int orig_len, status;
-
-	orig_buf = buffer;
-	orig_len = len;
-	status = 0;
+	u8 *record_buf;
+	int status = 0;
 
 	while (len > 0) {
 		if (len < sizeof(struct htc_record_hdr)) {
diff --git a/drivers/net/wireless/ath/ath6kl/main.c b/drivers/net/wireless/ath/ath6kl/main.c
index 808fb30be9ad..0c61dbaa62a4 100644
--- a/drivers/net/wireless/ath/ath6kl/main.c
+++ b/drivers/net/wireless/ath/ath6kl/main.c
@@ -272,7 +272,7 @@ int ath6kl_read_fwlogs(struct ath6kl *ar)
 {
 	struct ath6kl_dbglog_hdr debug_hdr;
 	struct ath6kl_dbglog_buf debug_buf;
-	u32 address, length, dropped, firstbuf, debug_hdr_addr;
+	u32 address, length, firstbuf, debug_hdr_addr;
 	int ret, loop;
 	u8 *buf;
 
@@ -303,7 +303,6 @@ int ath6kl_read_fwlogs(struct ath6kl *ar)
 	address = TARG_VTOP(ar->target_type,
 			    le32_to_cpu(debug_hdr.dbuf_addr));
 	firstbuf = address;
-	dropped = le32_to_cpu(debug_hdr.dropped);
 	ret = ath6kl_diag_read(ar, address, &debug_buf, sizeof(debug_buf));
 	if (ret)
 		goto out;
diff --git a/drivers/net/wireless/ath/ath6kl/txrx.c b/drivers/net/wireless/ath/ath6kl/txrx.c
index 618d12ed4b40..b22ed499f7ba 100644
--- a/drivers/net/wireless/ath/ath6kl/txrx.c
+++ b/drivers/net/wireless/ath/ath6kl/txrx.c
@@ -1701,7 +1701,6 @@ void aggr_recv_addba_req_evt(struct ath6kl_vif *vif, u8 tid_mux, u16 seq_no,
 	struct ath6kl_sta *sta;
 	struct aggr_info_conn *aggr_conn = NULL;
 	struct rxtid *rxtid;
-	struct rxtid_stats *stats;
 	u16 hold_q_size;
 	u8 tid, aid;
 
@@ -1722,7 +1721,6 @@ void aggr_recv_addba_req_evt(struct ath6kl_vif *vif, u8 tid_mux, u16 seq_no,
 		return;
 
 	rxtid = &aggr_conn->rx_tid[tid];
-	stats = &aggr_conn->stat[tid];
 
 	if (win_sz < AGGR_WIN_SZ_MIN || win_sz > AGGR_WIN_SZ_MAX)
 		ath6kl_dbg(ATH6KL_DBG_WLAN_RX, "%s: win_sz %d, tid %d\n",
-- 
cgit v1.2.3


From e82f57c8b9708baf4a58a9282636d9285b5aa2dd Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Sat, 14 Jul 2018 19:38:20 +0200
Subject: ath10k: htt_tx: move lock into id_get function

This is only code refactoring as all call sites of
ath10k_htt_tx_alloc_msdu_id() take the same lock it can be moved into the
id_get function and the assertion dropped.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/htt_tx.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/htt_tx.c b/drivers/net/wireless/ath/ath10k/htt_tx.c
index be5b52aaffa6..7cff0d52338f 100644
--- a/drivers/net/wireless/ath/ath10k/htt_tx.c
+++ b/drivers/net/wireless/ath/ath10k/htt_tx.c
@@ -208,10 +208,10 @@ int ath10k_htt_tx_alloc_msdu_id(struct ath10k_htt *htt, struct sk_buff *skb)
 	struct ath10k *ar = htt->ar;
 	int ret;
 
-	lockdep_assert_held(&htt->tx_lock);
-
+	spin_lock_bh(&htt->tx_lock);
 	ret = idr_alloc(&htt->pending_tx, skb, 0,
 			htt->max_num_pending_tx, GFP_ATOMIC);
+	spin_unlock_bh(&htt->tx_lock);
 
 	ath10k_dbg(ar, ATH10K_DBG_HTT, "htt tx alloc msdu_id %d\n", ret);
 
@@ -1077,9 +1077,7 @@ int ath10k_htt_mgmt_tx(struct ath10k_htt *htt, struct sk_buff *msdu)
 	len += sizeof(cmd->hdr);
 	len += sizeof(cmd->mgmt_tx);
 
-	spin_lock_bh(&htt->tx_lock);
 	res = ath10k_htt_tx_alloc_msdu_id(htt, msdu);
-	spin_unlock_bh(&htt->tx_lock);
 	if (res < 0)
 		goto err;
 
@@ -1161,9 +1159,7 @@ static int ath10k_htt_tx_32(struct ath10k_htt *htt,
 	struct htt_msdu_ext_desc *ext_desc = NULL;
 	struct htt_msdu_ext_desc *ext_desc_t = NULL;
 
-	spin_lock_bh(&htt->tx_lock);
 	res = ath10k_htt_tx_alloc_msdu_id(htt, msdu);
-	spin_unlock_bh(&htt->tx_lock);
 	if (res < 0)
 		goto err;
 
@@ -1363,9 +1359,7 @@ static int ath10k_htt_tx_64(struct ath10k_htt *htt,
 	struct htt_msdu_ext_desc_64 *ext_desc = NULL;
 	struct htt_msdu_ext_desc_64 *ext_desc_t = NULL;
 
-	spin_lock_bh(&htt->tx_lock);
 	res = ath10k_htt_tx_alloc_msdu_id(htt, msdu);
-	spin_unlock_bh(&htt->tx_lock);
 	if (res < 0)
 		goto err;
 
-- 
cgit v1.2.3


From db251d7df4570c7d48df088edfa3d1d510cc67c2 Mon Sep 17 00:00:00 2001
From: Maharaja Kennadyrajan <mkenna@codeaurora.org>
Date: Wed, 18 Jul 2018 19:04:20 +0530
Subject: ath10k: add debugfs file warm_hw_reset

Debugfs support to do hardware warm reset with WMI command
WMI_PDEV_PARAM_PDEV_RESET for 10.4 and 10.2.4(if wmi
service is enabled in the firmware for backward compatibility).

This change is purely for debugging purpose when hardware hangs/mutes.

This hardware reset won't affect the connectivity but there will be small
pause in data traffic. Here we are doing BB/MAC level reset and hence
whenever the BB/MAC watchdog is triggered, it does a hardware_chip_reset.
So the target will be in the active state.

Below command used to warm reset the hardware.
echo 1 > /sys/kernel/debug/ieee80211/phyX/ath10k/warm_hw_reset

Tested in QCA988X with firmware ver 10.2.4.70.45
Tested in QCA4019 with firmware ver 10.4-3.2.1.1-00011

Signed-off-by: Maharaja Kennadyrajan <mkenna@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/debug.c | 49 +++++++++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath10k/wmi.c   |  2 +-
 drivers/net/wireless/ath/ath10k/wmi.h   | 16 ++++++++++-
 3 files changed, 65 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c
index 4926722e0c0d..0baaad90b8d1 100644
--- a/drivers/net/wireless/ath/ath10k/debug.c
+++ b/drivers/net/wireless/ath/ath10k/debug.c
@@ -2297,6 +2297,52 @@ static const struct file_operations fops_tpc_stats_final = {
 	.llseek = default_llseek,
 };
 
+static ssize_t ath10k_write_warm_hw_reset(struct file *file,
+					  const char __user *user_buf,
+					  size_t count, loff_t *ppos)
+{
+	struct ath10k *ar = file->private_data;
+	int ret;
+	bool val;
+
+	if (kstrtobool_from_user(user_buf, count, &val))
+		return -EFAULT;
+
+	if (!val)
+		return -EINVAL;
+
+	mutex_lock(&ar->conf_mutex);
+
+	if (ar->state != ATH10K_STATE_ON) {
+		ret = -ENETDOWN;
+		goto exit;
+	}
+
+	if (!(test_bit(WMI_SERVICE_RESET_CHIP, ar->wmi.svc_map)))
+		ath10k_warn(ar, "wmi service for reset chip is not available\n");
+
+	ret = ath10k_wmi_pdev_set_param(ar, ar->wmi.pdev_param->pdev_reset,
+					WMI_RST_MODE_WARM_RESET);
+
+	if (ret) {
+		ath10k_warn(ar, "failed to enable warm hw reset: %d\n", ret);
+		goto exit;
+	}
+
+	ret = count;
+
+exit:
+	mutex_unlock(&ar->conf_mutex);
+	return ret;
+}
+
+static const struct file_operations fops_warm_hw_reset = {
+	.write = ath10k_write_warm_hw_reset,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 int ath10k_debug_create(struct ath10k *ar)
 {
 	ar->debug.cal_data = vzalloc(ATH10K_DEBUG_CAL_DATA_LEN);
@@ -2425,6 +2471,9 @@ int ath10k_debug_register(struct ath10k *ar)
 				    ar->debug.debugfs_phy, ar,
 				    &fops_tpc_stats_final);
 
+	debugfs_create_file("warm_hw_reset", 0600, ar->debug.debugfs_phy, ar,
+			    &fops_warm_hw_reset);
+
 	return 0;
 }
 
diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c
index 6d20baf5ae5c..fd612d2905b0 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.c
+++ b/drivers/net/wireless/ath/ath10k/wmi.c
@@ -1333,7 +1333,7 @@ static struct wmi_pdev_param_map wmi_10_2_4_pdev_param_map = {
 	.enable_per_tid_ampdu = WMI_PDEV_PARAM_UNSUPPORTED,
 	.cca_threshold = WMI_PDEV_PARAM_UNSUPPORTED,
 	.rts_fixed_rate = WMI_PDEV_PARAM_UNSUPPORTED,
-	.pdev_reset = WMI_PDEV_PARAM_UNSUPPORTED,
+	.pdev_reset = WMI_10X_PDEV_PARAM_PDEV_RESET,
 	.wapi_mbssid_offset = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_srcaddr = WMI_PDEV_PARAM_UNSUPPORTED,
 	.arp_dstaddr = WMI_PDEV_PARAM_UNSUPPORTED,
diff --git a/drivers/net/wireless/ath/ath10k/wmi.h b/drivers/net/wireless/ath/ath10k/wmi.h
index 2c96380d8021..36220258e3c7 100644
--- a/drivers/net/wireless/ath/ath10k/wmi.h
+++ b/drivers/net/wireless/ath/ath10k/wmi.h
@@ -462,6 +462,7 @@ static inline char *wmi_service_name(int service_id)
 	SVCSTR(WMI_SERVICE_HTT_MGMT_TX_COMP_VALID_FLAGS);
 	SVCSTR(WMI_SERVICE_HOST_DFS_CHECK_SUPPORT);
 	SVCSTR(WMI_SERVICE_TPC_STATS_FINAL);
+	SVCSTR(WMI_SERVICE_RESET_CHIP);
 	default:
 		return NULL;
 	}
@@ -3934,7 +3935,11 @@ enum wmi_10x_pdev_param {
 	WMI_10X_PDEV_PARAM_REMOVE_MCAST2UCAST_BUFFER,
 	WMI_10X_PDEV_PARAM_PEER_STA_PS_STATECHG_ENABLE,
 	WMI_10X_PDEV_PARAM_RTS_FIXED_RATE,
-	WMI_10X_PDEV_PARAM_CAL_PERIOD
+	WMI_10X_PDEV_PARAM_CAL_PERIOD,
+	WMI_10X_PDEV_PARAM_ATF_STRICT_SCH,
+	WMI_10X_PDEV_PARAM_ATF_SCHED_DURATION,
+	WMI_10X_PDEV_PARAM_SET_PROMISC_MODE_CMDID,
+	WMI_10X_PDEV_PARAM_PDEV_RESET
 };
 
 enum wmi_10_4_pdev_param {
@@ -6501,6 +6506,15 @@ struct wmi_force_fw_hang_cmd {
 	__le32 delay_ms;
 } __packed;
 
+enum wmi_pdev_reset_mode_type {
+	WMI_RST_MODE_TX_FLUSH = 1,
+	WMI_RST_MODE_WARM_RESET,
+	WMI_RST_MODE_COLD_RESET,
+	WMI_RST_MODE_WARM_RESET_RESTORE_CAL,
+	WMI_RST_MODE_COLD_RESET_RESTORE_CAL,
+	WMI_RST_MODE_MAX,
+};
+
 enum ath10k_dbglog_level {
 	ATH10K_DBGLOG_LEVEL_VERBOSE = 0,
 	ATH10K_DBGLOG_LEVEL_INFO = 1,
-- 
cgit v1.2.3


From d018031f562b9c2eff038969ab1955a370c52d8f Mon Sep 17 00:00:00 2001
From: Mukesh Ojha <mojha@codeaurora.org>
Date: Tue, 24 Jul 2018 20:17:48 +0530
Subject: cpu/hotplug: Clarify CPU hotplug step name for timers

After commit 249d4a9b3246 ("timers: Reinitialize per cpu bases on hotplug")
i.e. the introduction of state CPUHP_TIMERS_PREPARE instead of
CPUHP_TIMERS_DEAD the step name "timers:dead" is not longer accurate.

Rename it to "timers:prepare".

[ tglx: Massaged changelog ]

Signed-off-by: Mukesh Ojha <mojha@codeaurora.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: gkohli@codeaurora.org
Cc: neeraju@codeaurora.org
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Cc: Brendan Jackman <brendan.jackman@arm.com>
Cc: Mathieu Malaterre <malat@debian.org>
Link: https://lkml.kernel.org/r/1532443668-26810-1-git-send-email-mojha@codeaurora.org
---
 kernel/cpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..8e6606ac3d72 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -1274,7 +1274,7 @@ static struct cpuhp_step cpuhp_hp_states[] = {
 	 * otherwise a RCU stall occurs.
 	 */
 	[CPUHP_TIMERS_PREPARE] = {
-		.name			= "timers:dead",
+		.name			= "timers:prepare",
 		.startup.single		= timers_prepare_cpu,
 		.teardown.single	= timers_dead_cpu,
 	},
-- 
cgit v1.2.3


From 6ae746711263bd6da45f709fdb9f12e4f57e22bd Mon Sep 17 00:00:00 2001
From: Yidong Ren <yidren@microsoft.com>
Date: Mon, 30 Jul 2018 17:09:45 +0000
Subject: hv_netvsc: Add per-cpu ethtool stats for netvsc

This patch implements following ethtool stats fields for netvsc:
cpu<n>_tx/rx_packets/bytes
cpu<n>_vf_tx/rx_packets/bytes

Corresponding per-cpu counters already exist in current code. Exposing
these counters will help troubleshooting performance issues.

for_each_present_cpu() was used instead of for_each_possible_cpu().
for_each_possible_cpu() would create very long and useless output.
It is still being used for internal buffer, but not for ethtool
output.

There could be an overflow if cpu was added between ethtool
call netvsc_get_sset_count() and netvsc_get_ethtool_stats() and
netvsc_get_strings(). (still safe if cpu was removed)
ethtool makes these three function calls separately.
As long as we use ethtool, I can't see any clean solution.

Currently and in foreseeable short term, Hyper-V doesn't support
cpu hot-plug. Plus, ethtool is for admin use. Unlikely the admin
would perform such combo operations.

Changes in v2:
  - Remove cpp style comment
  - Resubmit after freeze

Changes in v3:
  - Reimplemented with kvmalloc instead of alloc_percpu

Changes in v4:
  - Fixed inconsistent array size
  - Use kvmalloc_array instead of kvmalloc

Signed-off-by: Yidong Ren <yidren@microsoft.com>
Reviewed-by: Stephen Hemminger <sthemmin@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h |  11 +++++
 drivers/net/hyperv/netvsc_drv.c | 106 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 114 insertions(+), 3 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 4b6e308199d2..a32ded5b4f41 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -873,6 +873,17 @@ struct netvsc_ethtool_stats {
 	unsigned long wake_queue;
 };
 
+struct netvsc_ethtool_pcpu_stats {
+	u64     rx_packets;
+	u64     rx_bytes;
+	u64     tx_packets;
+	u64     tx_bytes;
+	u64     vf_rx_packets;
+	u64     vf_rx_bytes;
+	u64     vf_tx_packets;
+	u64     vf_tx_bytes;
+};
+
 struct netvsc_vf_pcpu_stats {
 	u64     rx_packets;
 	u64     rx_bytes;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index cf4f40a04194..20275d1e6f9a 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -1118,6 +1118,64 @@ static void netvsc_get_vf_stats(struct net_device *net,
 	}
 }
 
+static void netvsc_get_pcpu_stats(struct net_device *net,
+				  struct netvsc_ethtool_pcpu_stats *pcpu_tot)
+{
+	struct net_device_context *ndev_ctx = netdev_priv(net);
+	struct netvsc_device *nvdev = rcu_dereference_rtnl(ndev_ctx->nvdev);
+	int i;
+
+	/* fetch percpu stats of vf */
+	for_each_possible_cpu(i) {
+		const struct netvsc_vf_pcpu_stats *stats =
+			per_cpu_ptr(ndev_ctx->vf_stats, i);
+		struct netvsc_ethtool_pcpu_stats *this_tot = &pcpu_tot[i];
+		unsigned int start;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			this_tot->vf_rx_packets = stats->rx_packets;
+			this_tot->vf_tx_packets = stats->tx_packets;
+			this_tot->vf_rx_bytes = stats->rx_bytes;
+			this_tot->vf_tx_bytes = stats->tx_bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+		this_tot->rx_packets = this_tot->vf_rx_packets;
+		this_tot->tx_packets = this_tot->vf_tx_packets;
+		this_tot->rx_bytes   = this_tot->vf_rx_bytes;
+		this_tot->tx_bytes   = this_tot->vf_tx_bytes;
+	}
+
+	/* fetch percpu stats of netvsc */
+	for (i = 0; i < nvdev->num_chn; i++) {
+		const struct netvsc_channel *nvchan = &nvdev->chan_table[i];
+		const struct netvsc_stats *stats;
+		struct netvsc_ethtool_pcpu_stats *this_tot =
+			&pcpu_tot[nvchan->channel->target_cpu];
+		u64 packets, bytes;
+		unsigned int start;
+
+		stats = &nvchan->tx_stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		this_tot->tx_bytes	+= bytes;
+		this_tot->tx_packets	+= packets;
+
+		stats = &nvchan->rx_stats;
+		do {
+			start = u64_stats_fetch_begin_irq(&stats->syncp);
+			packets = stats->packets;
+			bytes = stats->bytes;
+		} while (u64_stats_fetch_retry_irq(&stats->syncp, start));
+
+		this_tot->rx_bytes	+= bytes;
+		this_tot->rx_packets	+= packets;
+	}
+}
+
 static void netvsc_get_stats64(struct net_device *net,
 			       struct rtnl_link_stats64 *t)
 {
@@ -1215,6 +1273,23 @@ static const struct {
 	{ "rx_no_memory", offsetof(struct netvsc_ethtool_stats, rx_no_memory) },
 	{ "stop_queue", offsetof(struct netvsc_ethtool_stats, stop_queue) },
 	{ "wake_queue", offsetof(struct netvsc_ethtool_stats, wake_queue) },
+}, pcpu_stats[] = {
+	{ "cpu%u_rx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, rx_packets) },
+	{ "cpu%u_rx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, rx_bytes) },
+	{ "cpu%u_tx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, tx_packets) },
+	{ "cpu%u_tx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, tx_bytes) },
+	{ "cpu%u_vf_rx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_packets) },
+	{ "cpu%u_vf_rx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_rx_bytes) },
+	{ "cpu%u_vf_tx_packets",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_packets) },
+	{ "cpu%u_vf_tx_bytes",
+		offsetof(struct netvsc_ethtool_pcpu_stats, vf_tx_bytes) },
 }, vf_stats[] = {
 	{ "vf_rx_packets", offsetof(struct netvsc_vf_pcpu_stats, rx_packets) },
 	{ "vf_rx_bytes",   offsetof(struct netvsc_vf_pcpu_stats, rx_bytes) },
@@ -1226,6 +1301,9 @@ static const struct {
 #define NETVSC_GLOBAL_STATS_LEN	ARRAY_SIZE(netvsc_stats)
 #define NETVSC_VF_STATS_LEN	ARRAY_SIZE(vf_stats)
 
+/* statistics per queue (rx/tx packets/bytes) */
+#define NETVSC_PCPU_STATS_LEN (num_present_cpus() * ARRAY_SIZE(pcpu_stats))
+
 /* 4 statistics per queue (rx/tx packets/bytes) */
 #define NETVSC_QUEUE_STATS_LEN(dev) ((dev)->num_chn * 4)
 
@@ -1241,7 +1319,8 @@ static int netvsc_get_sset_count(struct net_device *dev, int string_set)
 	case ETH_SS_STATS:
 		return NETVSC_GLOBAL_STATS_LEN
 			+ NETVSC_VF_STATS_LEN
-			+ NETVSC_QUEUE_STATS_LEN(nvdev);
+			+ NETVSC_QUEUE_STATS_LEN(nvdev)
+			+ NETVSC_PCPU_STATS_LEN;
 	default:
 		return -EINVAL;
 	}
@@ -1255,9 +1334,10 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 	const void *nds = &ndc->eth_stats;
 	const struct netvsc_stats *qstats;
 	struct netvsc_vf_pcpu_stats sum;
+	struct netvsc_ethtool_pcpu_stats *pcpu_sum;
 	unsigned int start;
 	u64 packets, bytes;
-	int i, j;
+	int i, j, cpu;
 
 	if (!nvdev)
 		return;
@@ -1289,6 +1369,19 @@ static void netvsc_get_ethtool_stats(struct net_device *dev,
 		data[i++] = packets;
 		data[i++] = bytes;
 	}
+
+	pcpu_sum = kvmalloc_array(num_possible_cpus(),
+				  sizeof(struct netvsc_ethtool_pcpu_stats),
+				  GFP_KERNEL);
+	netvsc_get_pcpu_stats(dev, pcpu_sum);
+	for_each_present_cpu(cpu) {
+		struct netvsc_ethtool_pcpu_stats *this_sum = &pcpu_sum[cpu];
+
+		for (j = 0; j < ARRAY_SIZE(pcpu_stats); j++)
+			data[i++] = *(u64 *)((void *)this_sum
+					     + pcpu_stats[j].offset);
+	}
+	kvfree(pcpu_sum);
 }
 
 static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
@@ -1296,7 +1389,7 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 	struct net_device_context *ndc = netdev_priv(dev);
 	struct netvsc_device *nvdev = rtnl_dereference(ndc->nvdev);
 	u8 *p = data;
-	int i;
+	int i, cpu;
 
 	if (!nvdev)
 		return;
@@ -1324,6 +1417,13 @@ static void netvsc_get_strings(struct net_device *dev, u32 stringset, u8 *data)
 			p += ETH_GSTRING_LEN;
 		}
 
+		for_each_present_cpu(cpu) {
+			for (i = 0; i < ARRAY_SIZE(pcpu_stats); i++) {
+				sprintf(p, pcpu_stats[i].name, cpu);
+				p += ETH_GSTRING_LEN;
+			}
+		}
+
 		break;
 	}
 }
-- 
cgit v1.2.3


From fc91a3c4c27acdca0bc13af6fbb68c35cfd519f2 Mon Sep 17 00:00:00 2001
From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
Date: Mon, 23 Jul 2018 14:25:31 -0700
Subject: debugobjects: Make stack check warning more informative

While debugging an issue debugobject tracking warned about an annotation
issue of an object on stack. It turned out that the issue was due to the
object in concern being on a different stack which was due to another
issue.

Thomas suggested to print the pointers and the location of the stack for
the currently running task. This helped to figure out that the object was
on the wrong stack.

As this is general useful information for debugging similar issues, make
the error message more informative by printing the pointers.

[ tglx: Massaged changelog ]

Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Waiman Long <longman@redhat.com>
Acked-by: Yang Shi <yang.shi@linux.alibaba.com>
Cc: kernel-team@android.com
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: astrachan@google.com
Link: https://lkml.kernel.org/r/20180723212531.202328-1-joel@joelfernandes.org
---
 lib/debugobjects.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 994be4805cec..24c1df0d7466 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -360,9 +360,12 @@ static void debug_object_is_on_stack(void *addr, int onstack)
 
 	limit++;
 	if (is_on_stack)
-		pr_warn("object is on stack, but not annotated\n");
+		pr_warn("object %p is on stack %p, but NOT annotated.\n", addr,
+			 task_stack_page(current));
 	else
-		pr_warn("object is not on stack, but annotated\n");
+		pr_warn("object %p is NOT on stack %p, but annotated.\n", addr,
+			 task_stack_page(current));
+
 	WARN_ON(1);
 }
 
-- 
cgit v1.2.3


From b41e44b4cb230747d7ad56e38c9dc65369b1d381 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Wed, 30 May 2018 11:07:03 -0400
Subject: media: dvb/video.h: get rid of unused APIs

There are a number of other ioctls that aren't used anywhere
inside the Kernel tree.

Get rid of them.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../media/uapi/dvb/video-get-frame-rate.rst        |  61 -----------
 Documentation/media/uapi/dvb/video-get-navi.rst    |  84 ---------------
 .../media/uapi/dvb/video-set-attributes.rst        |  93 -----------------
 .../media/uapi/dvb/video-set-highlight.rst         |  86 ----------------
 Documentation/media/uapi/dvb/video-set-id.rst      |  75 --------------
 Documentation/media/uapi/dvb/video-set-spu.rst     |  85 ----------------
 Documentation/media/uapi/dvb/video-set-system.rst  |  77 --------------
 .../media/uapi/dvb/video_function_calls.rst        |   6 --
 Documentation/media/uapi/dvb/video_types.rst       | 113 ---------------------
 Documentation/media/video.h.rst.exceptions         |   2 -
 fs/compat_ioctl.c                                  |   7 --
 include/uapi/linux/dvb/video.h                     |  51 ----------
 12 files changed, 740 deletions(-)
 delete mode 100644 Documentation/media/uapi/dvb/video-get-frame-rate.rst
 delete mode 100644 Documentation/media/uapi/dvb/video-get-navi.rst
 delete mode 100644 Documentation/media/uapi/dvb/video-set-attributes.rst
 delete mode 100644 Documentation/media/uapi/dvb/video-set-highlight.rst
 delete mode 100644 Documentation/media/uapi/dvb/video-set-id.rst
 delete mode 100644 Documentation/media/uapi/dvb/video-set-spu.rst
 delete mode 100644 Documentation/media/uapi/dvb/video-set-system.rst

diff --git a/Documentation/media/uapi/dvb/video-get-frame-rate.rst b/Documentation/media/uapi/dvb/video-get-frame-rate.rst
deleted file mode 100644
index 400042a854cf..000000000000
--- a/Documentation/media/uapi/dvb/video-get-frame-rate.rst
+++ /dev/null
@@ -1,61 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_GET_FRAME_RATE:
-
-====================
-VIDEO_GET_FRAME_RATE
-====================
-
-Name
-----
-
-VIDEO_GET_FRAME_RATE
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(int fd, VIDEO_GET_FRAME_RATE, unsigned int *rate)
-    :name: VIDEO_GET_FRAME_RATE
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_GET_FRAME_RATE for this command.
-
-    -  .. row 3
-
-       -  unsigned int \*rate
-
-       -  Returns the framerate in number of frames per 1000 seconds.
-
-
-Description
------------
-
-This ioctl call asks the Video Device to return the current framerate.
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
diff --git a/Documentation/media/uapi/dvb/video-get-navi.rst b/Documentation/media/uapi/dvb/video-get-navi.rst
deleted file mode 100644
index 114a9ac48b9e..000000000000
--- a/Documentation/media/uapi/dvb/video-get-navi.rst
+++ /dev/null
@@ -1,84 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_GET_NAVI:
-
-==============
-VIDEO_GET_NAVI
-==============
-
-Name
-----
-
-VIDEO_GET_NAVI
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, VIDEO_GET_NAVI , struct video_navi_pack *navipack)
-    :name: VIDEO_GET_NAVI
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_GET_NAVI for this command.
-
-    -  .. row 3
-
-       -  video_navi_pack_t \*navipack
-
-       -  PCI or DSI pack (private stream 2) according to section ??.
-
-
-Description
------------
-
-This ioctl returns navigational information from the DVD stream. This is
-especially needed if an encoded stream has to be decoded by the
-hardware.
-
-.. c:type:: video_navi_pack
-
-.. code-block::c
-
-	typedef struct video_navi_pack {
-		int length;          /* 0 ... 1024 */
-		__u8 data[1024];
-	} video_navi_pack_t;
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EFAULT``
-
-       -  driver is not able to return navigational information
diff --git a/Documentation/media/uapi/dvb/video-set-attributes.rst b/Documentation/media/uapi/dvb/video-set-attributes.rst
deleted file mode 100644
index b2f11a6746e9..000000000000
--- a/Documentation/media/uapi/dvb/video-set-attributes.rst
+++ /dev/null
@@ -1,93 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_SET_ATTRIBUTES:
-
-====================
-VIDEO_SET_ATTRIBUTES
-====================
-
-Name
-----
-
-VIDEO_SET_ATTRIBUTES
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, VIDEO_SET_ATTRIBUTE ,video_attributes_t vattr)
-    :name: VIDEO_SET_ATTRIBUTE
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_SET_ATTRIBUTE for this command.
-
-    -  .. row 3
-
-       -  video_attributes_t vattr
-
-       -  video attributes according to section ??.
-
-
-Description
------------
-
-This ioctl is intended for DVD playback and allows you to set certain
-information about the stream. Some hardware may not need this
-information, but the call also tells the hardware to prepare for DVD
-playback.
-
-.. c:type:: video_attributes_t
-
-.. code-block::c
-
-	typedef __u16 video_attributes_t;
-	/*   bits: descr. */
-	/*   15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */
-	/*   13-12 TV system (0=525/60, 1=625/50) */
-	/*   11-10 Aspect ratio (0=4:3, 3=16:9) */
-	/*    9- 8 permitted display mode on 4:3 monitor (0=both, 1=only pan-sca */
-	/*    7    line 21-1 data present in GOP (1=yes, 0=no) */
-	/*    6    line 21-2 data present in GOP (1=yes, 0=no) */
-	/*    5- 3 source resolution (0=720x480/576, 1=704x480/576, 2=352x480/57 */
-	/*    2    source letterboxed (1=yes, 0=no) */
-	/*    0    film/camera mode (0=camera, 1=film (625/50 only)) */
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  input is not a valid attribute setting.
diff --git a/Documentation/media/uapi/dvb/video-set-highlight.rst b/Documentation/media/uapi/dvb/video-set-highlight.rst
deleted file mode 100644
index 90aeafd923b7..000000000000
--- a/Documentation/media/uapi/dvb/video-set-highlight.rst
+++ /dev/null
@@ -1,86 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_SET_HIGHLIGHT:
-
-===================
-VIDEO_SET_HIGHLIGHT
-===================
-
-Name
-----
-
-VIDEO_SET_HIGHLIGHT
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, VIDEO_SET_HIGHLIGHT, struct video_highlight *vhilite)
-    :name: VIDEO_SET_HIGHLIGHT
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_SET_HIGHLIGHT for this command.
-
-    -  .. row 3
-
-       -  video_highlight_t \*vhilite
-
-       -  SPU Highlight information according to section ??.
-
-
-Description
------------
-
-This ioctl sets the SPU highlight information for the menu access of a
-DVD.
-
-.. c:type:: video_highlight
-
-.. code-block:: c
-
-	typedef
-	struct video_highlight {
-		int     active;      /*    1=show highlight, 0=hide highlight */
-		__u8    contrast1;   /*    7- 4  Pattern pixel contrast */
-				/*    3- 0  Background pixel contrast */
-		__u8    contrast2;   /*    7- 4  Emphasis pixel-2 contrast */
-				/*    3- 0  Emphasis pixel-1 contrast */
-		__u8    color1;      /*    7- 4  Pattern pixel color */
-				/*    3- 0  Background pixel color */
-		__u8    color2;      /*    7- 4  Emphasis pixel-2 color */
-				/*    3- 0  Emphasis pixel-1 color */
-		__u32    ypos;       /*   23-22  auto action mode */
-				/*   21-12  start y */
-				/*    9- 0  end y */
-		__u32    xpos;       /*   23-22  button color number */
-				/*   21-12  start x */
-				/*    9- 0  end x */
-	} video_highlight_t;
-
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
diff --git a/Documentation/media/uapi/dvb/video-set-id.rst b/Documentation/media/uapi/dvb/video-set-id.rst
deleted file mode 100644
index 18f66875ae3f..000000000000
--- a/Documentation/media/uapi/dvb/video-set-id.rst
+++ /dev/null
@@ -1,75 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_SET_ID:
-
-============
-VIDEO_SET_ID
-============
-
-Name
-----
-
-VIDEO_SET_ID
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(int fd, VIDEO_SET_ID, int id)
-    :name: VIDEO_SET_ID
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_SET_ID for this command.
-
-    -  .. row 3
-
-       -  int id
-
-       -  video sub-stream id
-
-
-Description
------------
-
-This ioctl selects which sub-stream is to be decoded if a program or
-system stream is sent to the video device.
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  Invalid sub-stream id.
diff --git a/Documentation/media/uapi/dvb/video-set-spu.rst b/Documentation/media/uapi/dvb/video-set-spu.rst
deleted file mode 100644
index 739e5e7bd133..000000000000
--- a/Documentation/media/uapi/dvb/video-set-spu.rst
+++ /dev/null
@@ -1,85 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_SET_SPU:
-
-=============
-VIDEO_SET_SPU
-=============
-
-Name
-----
-
-VIDEO_SET_SPU
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, VIDEO_SET_SPU , struct video_spu *spu)
-    :name: VIDEO_SET_SPU
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_SET_SPU for this command.
-
-    -  .. row 3
-
-       -  video_spu_t \*spu
-
-       -  SPU decoding (de)activation and subid setting according to section
-	  ??.
-
-
-Description
------------
-
-This ioctl activates or deactivates SPU decoding in a DVD input stream.
-It can only be used, if the driver is able to handle a DVD stream.
-
-.. c:type:: struct video_spu
-
-.. code-block:: c
-
-	typedef struct video_spu {
-		int active;
-		int stream_id;
-	} video_spu_t;
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  input is not a valid spu setting or driver cannot handle SPU.
diff --git a/Documentation/media/uapi/dvb/video-set-system.rst b/Documentation/media/uapi/dvb/video-set-system.rst
deleted file mode 100644
index e39cbe080ef7..000000000000
--- a/Documentation/media/uapi/dvb/video-set-system.rst
+++ /dev/null
@@ -1,77 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _VIDEO_SET_SYSTEM:
-
-================
-VIDEO_SET_SYSTEM
-================
-
-Name
-----
-
-VIDEO_SET_SYSTEM
-
-.. attention:: This ioctl is deprecated.
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, VIDEO_SET_SYSTEM , video_system_t system)
-    :name: VIDEO_SET_SYSTEM
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -  .. row 2
-
-       -  int request
-
-       -  Equals VIDEO_SET_FORMAT for this command.
-
-    -  .. row 3
-
-       -  video_system_t system
-
-       -  video system of TV output.
-
-
-Description
------------
-
-This ioctl sets the television output format. The format (see section
-??) may vary from the color format of the displayed MPEG stream. If the
-hardware is not able to display the requested format the call will
-return an error.
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  system is not a valid or supported video system.
diff --git a/Documentation/media/uapi/dvb/video_function_calls.rst b/Documentation/media/uapi/dvb/video_function_calls.rst
index 8d8383ffaeba..3f4f6c9ffad7 100644
--- a/Documentation/media/uapi/dvb/video_function_calls.rst
+++ b/Documentation/media/uapi/dvb/video_function_calls.rst
@@ -21,7 +21,6 @@ Video Function Calls
     video-get-status
     video-get-frame-count
     video-get-pts
-    video-get-frame-rate
     video-get-event
     video-command
     video-try-command
@@ -31,12 +30,7 @@ Video Function Calls
     video-fast-forward
     video-slowmotion
     video-get-capabilities
-    video-set-id
     video-clear-buffer
     video-set-streamtype
     video-set-format
-    video-set-system
-    video-set-highlight
-    video-set-spu
-    video-get-navi
     video-set-attributes
diff --git a/Documentation/media/uapi/dvb/video_types.rst b/Documentation/media/uapi/dvb/video_types.rst
index 4cfa00e5c934..a0942171596c 100644
--- a/Documentation/media/uapi/dvb/video_types.rst
+++ b/Documentation/media/uapi/dvb/video_types.rst
@@ -246,116 +246,3 @@ following bits set according to the hardwares capabilities.
      #define VIDEO_CAP_SPU    16
      #define VIDEO_CAP_NAVI   32
      #define VIDEO_CAP_CSS    64
-
-
-.. _video-system:
-
-video_system_t
-==============
-
-A call to VIDEO_SET_SYSTEM sets the desired video system for TV
-output. The following system types can be set:
-
-
-.. code-block:: c
-
-    typedef enum {
-	 VIDEO_SYSTEM_PAL,
-	 VIDEO_SYSTEM_NTSC,
-	 VIDEO_SYSTEM_PALN,
-	 VIDEO_SYSTEM_PALNc,
-	 VIDEO_SYSTEM_PALM,
-	 VIDEO_SYSTEM_NTSC60,
-	 VIDEO_SYSTEM_PAL60,
-	 VIDEO_SYSTEM_PALM60
-    } video_system_t;
-
-
-.. c:type:: video_highlight
-
-struct video_highlight
-======================
-
-Calling the ioctl VIDEO_SET_HIGHLIGHTS posts the SPU highlight
-information. The call expects the following format for that information:
-
-
-.. code-block:: c
-
-     typedef
-     struct video_highlight {
-	 boolean active;      /*    1=show highlight, 0=hide highlight */
-	 uint8_t contrast1;   /*    7- 4  Pattern pixel contrast */
-		      /*    3- 0  Background pixel contrast */
-	 uint8_t contrast2;   /*    7- 4  Emphasis pixel-2 contrast */
-		      /*    3- 0  Emphasis pixel-1 contrast */
-	 uint8_t color1;      /*    7- 4  Pattern pixel color */
-		      /*    3- 0  Background pixel color */
-	 uint8_t color2;      /*    7- 4  Emphasis pixel-2 color */
-		      /*    3- 0  Emphasis pixel-1 color */
-	 uint32_t ypos;       /*   23-22  auto action mode */
-		      /*   21-12  start y */
-		      /*    9- 0  end y */
-	 uint32_t xpos;       /*   23-22  button color number */
-		      /*   21-12  start x */
-		      /*    9- 0  end x */
-     } video_highlight_t;
-
-
-.. c:type:: video_spu
-
-struct video_spu
-================
-
-Calling VIDEO_SET_SPU deactivates or activates SPU decoding, according
-to the following format:
-
-
-.. code-block:: c
-
-     typedef
-     struct video_spu {
-	 boolean active;
-	 int stream_id;
-     } video_spu_t;
-
-
-.. c:type:: video_navi_pack
-
-struct video_navi_pack
-======================
-
-In order to get the navigational data the following structure has to be
-passed to the ioctl VIDEO_GET_NAVI:
-
-
-.. code-block:: c
-
-     typedef
-     struct video_navi_pack {
-	 int length;         /* 0 ... 1024 */
-	 uint8_t data[1024];
-     } video_navi_pack_t;
-
-
-.. _video-attributes-t:
-
-video_attributes_t
-==================
-
-The following attributes can be set by a call to VIDEO_SET_ATTRIBUTES:
-
-
-.. code-block:: c
-
-     typedef uint16_t video_attributes_t;
-     /*   bits: descr. */
-     /*   15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */
-     /*   13-12 TV system (0=525/60, 1=625/50) */
-     /*   11-10 Aspect ratio (0=4:3, 3=16:9) */
-     /*    9- 8 permitted display mode on 4:3 monitor (0=both, 1=only pan-sca */
-     /*    7    line 21-1 data present in GOP (1=yes, 0=no) */
-     /*    6    line 21-2 data present in GOP (1=yes, 0=no) */
-     /*    5- 3 source resolution (0=720x480/576, 1=704x480/576, 2=352x480/57 */
-     /*    2    source letterboxed (1=yes, 0=no) */
-     /*    0    film/camera mode (0=camera, 1=film (625/50 only)) */
diff --git a/Documentation/media/video.h.rst.exceptions b/Documentation/media/video.h.rst.exceptions
index 89d7c3ef2da7..371cdbd7d062 100644
--- a/Documentation/media/video.h.rst.exceptions
+++ b/Documentation/media/video.h.rst.exceptions
@@ -34,6 +34,4 @@ replace typedef video_displayformat_t :c:type:`video_displayformat`
 replace typedef video_size_t :c:type:`video_size`
 replace typedef video_stream_source_t :c:type:`video_stream_source`
 replace typedef video_play_state_t :c:type:`video_play_state`
-replace typedef video_highlight_t :c:type:`video_highlight`
-replace typedef video_spu_t :c:type:`video_spu`
 replace typedef video_navi_pack_t :c:type:`video_navi_pack`
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index fdb5ef9b5d06..59216b172003 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1205,16 +1205,9 @@ COMPATIBLE_IOCTL(VIDEO_FAST_FORWARD)
 COMPATIBLE_IOCTL(VIDEO_SLOWMOTION)
 COMPATIBLE_IOCTL(VIDEO_GET_CAPABILITIES)
 COMPATIBLE_IOCTL(VIDEO_CLEAR_BUFFER)
-COMPATIBLE_IOCTL(VIDEO_SET_ID)
 COMPATIBLE_IOCTL(VIDEO_SET_STREAMTYPE)
 COMPATIBLE_IOCTL(VIDEO_SET_FORMAT)
-COMPATIBLE_IOCTL(VIDEO_SET_SYSTEM)
-COMPATIBLE_IOCTL(VIDEO_SET_HIGHLIGHT)
-COMPATIBLE_IOCTL(VIDEO_SET_SPU)
-COMPATIBLE_IOCTL(VIDEO_GET_NAVI)
-COMPATIBLE_IOCTL(VIDEO_SET_ATTRIBUTES)
 COMPATIBLE_IOCTL(VIDEO_GET_SIZE)
-COMPATIBLE_IOCTL(VIDEO_GET_FRAME_RATE)
 /* cec */
 COMPATIBLE_IOCTL(CEC_ADAP_G_CAPS)
 COMPATIBLE_IOCTL(CEC_ADAP_G_LOG_ADDRS)
diff --git a/include/uapi/linux/dvb/video.h b/include/uapi/linux/dvb/video.h
index 6a0c9757b7ba..43ba8b0a3d14 100644
--- a/include/uapi/linux/dvb/video.h
+++ b/include/uapi/linux/dvb/video.h
@@ -37,18 +37,6 @@ typedef enum {
 } video_format_t;
 
 
-typedef enum {
-	 VIDEO_SYSTEM_PAL,
-	 VIDEO_SYSTEM_NTSC,
-	 VIDEO_SYSTEM_PALN,
-	 VIDEO_SYSTEM_PALNc,
-	 VIDEO_SYSTEM_PALM,
-	 VIDEO_SYSTEM_NTSC60,
-	 VIDEO_SYSTEM_PAL60,
-	 VIDEO_SYSTEM_PALM60
-} video_system_t;
-
-
 typedef enum {
 	VIDEO_PAN_SCAN,       /* use pan and scan format */
 	VIDEO_LETTER_BOX,     /* use letterbox format */
@@ -160,38 +148,6 @@ struct video_still_picture {
 };
 
 
-typedef
-struct video_highlight {
-	int     active;      /*    1=show highlight, 0=hide highlight */
-	__u8    contrast1;   /*    7- 4  Pattern pixel contrast */
-			     /*    3- 0  Background pixel contrast */
-	__u8    contrast2;   /*    7- 4  Emphasis pixel-2 contrast */
-			     /*    3- 0  Emphasis pixel-1 contrast */
-	__u8    color1;      /*    7- 4  Pattern pixel color */
-			     /*    3- 0  Background pixel color */
-	__u8    color2;      /*    7- 4  Emphasis pixel-2 color */
-			     /*    3- 0  Emphasis pixel-1 color */
-	__u32    ypos;       /*   23-22  auto action mode */
-			     /*   21-12  start y */
-			     /*    9- 0  end y */
-	__u32    xpos;       /*   23-22  button color number */
-			     /*   21-12  start x */
-			     /*    9- 0  end x */
-} video_highlight_t;
-
-
-typedef struct video_spu {
-	int active;
-	int stream_id;
-} video_spu_t;
-
-
-typedef struct video_navi_pack {
-	int length;          /* 0 ... 1024 */
-	__u8 data[1024];
-} video_navi_pack_t;
-
-
 typedef __u16 video_attributes_t;
 /*   bits: descr. */
 /*   15-14 Video compression mode (0=MPEG-1, 1=MPEG-2) */
@@ -236,16 +192,9 @@ typedef __u16 video_attributes_t;
 #define VIDEO_SLOWMOTION           _IO('o', 32)
 #define VIDEO_GET_CAPABILITIES     _IOR('o', 33, unsigned int)
 #define VIDEO_CLEAR_BUFFER         _IO('o',  34)
-#define VIDEO_SET_ID               _IO('o', 35)
 #define VIDEO_SET_STREAMTYPE       _IO('o', 36)
 #define VIDEO_SET_FORMAT           _IO('o', 37)
-#define VIDEO_SET_SYSTEM           _IO('o', 38)
-#define VIDEO_SET_HIGHLIGHT        _IOW('o', 39, video_highlight_t)
-#define VIDEO_SET_SPU              _IOW('o', 50, video_spu_t)
-#define VIDEO_GET_NAVI             _IOR('o', 52, video_navi_pack_t)
-#define VIDEO_SET_ATTRIBUTES       _IO('o', 53)
 #define VIDEO_GET_SIZE             _IOR('o', 55, video_size_t)
-#define VIDEO_GET_FRAME_RATE       _IOR('o', 56, unsigned int)
 
 /**
  * VIDEO_GET_PTS
-- 
cgit v1.2.3


From d21c249b26311dd193b100e65fc9e7ae96233d40 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Wed, 30 May 2018 11:07:04 -0400
Subject: media: dvb/audio.h: get rid of unused APIs

There are a number of other ioctls that aren't used anywhere
inside the Kernel tree.

Get rid of them.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/audio.h.rst.exceptions         |  3 -
 Documentation/media/uapi/dvb/audio-get-pts.rst     | 65 ---------------------
 .../media/uapi/dvb/audio-set-attributes.rst        | 67 ----------------------
 Documentation/media/uapi/dvb/audio-set-ext-id.rst  | 66 ---------------------
 Documentation/media/uapi/dvb/audio-set-karaoke.rst | 66 ---------------------
 Documentation/media/uapi/dvb/audio_data_types.rst  | 37 ------------
 .../media/uapi/dvb/audio_function_calls.rst        |  4 --
 fs/compat_ioctl.c                                  |  3 -
 include/uapi/linux/dvb/audio.h                     | 37 ------------
 9 files changed, 348 deletions(-)
 delete mode 100644 Documentation/media/uapi/dvb/audio-get-pts.rst
 delete mode 100644 Documentation/media/uapi/dvb/audio-set-attributes.rst
 delete mode 100644 Documentation/media/uapi/dvb/audio-set-ext-id.rst
 delete mode 100644 Documentation/media/uapi/dvb/audio-set-karaoke.rst

diff --git a/Documentation/media/audio.h.rst.exceptions b/Documentation/media/audio.h.rst.exceptions
index f40f3cbfe4c9..940458774cf6 100644
--- a/Documentation/media/audio.h.rst.exceptions
+++ b/Documentation/media/audio.h.rst.exceptions
@@ -1,9 +1,6 @@
 # Ignore header name
 ignore define _DVBAUDIO_H_
 
-# Typedef pointing to structs
-replace typedef audio_karaoke_t :c:type:`audio_karaoke`
-
 # Undocumented audio caps, as this is a deprecated API anyway
 ignore define AUDIO_CAP_DTS
 ignore define AUDIO_CAP_LPCM
diff --git a/Documentation/media/uapi/dvb/audio-get-pts.rst b/Documentation/media/uapi/dvb/audio-get-pts.rst
deleted file mode 100644
index 2d1396b003de..000000000000
--- a/Documentation/media/uapi/dvb/audio-get-pts.rst
+++ /dev/null
@@ -1,65 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _AUDIO_GET_PTS:
-
-=============
-AUDIO_GET_PTS
-=============
-
-Name
-----
-
-AUDIO_GET_PTS
-
-.. attention:: This ioctl is deprecated
-
-Synopsis
---------
-
-.. c:function:: int ioctl(int fd, AUDIO_GET_PTS, __u64 *pts)
-    :name: AUDIO_GET_PTS
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -
-
-       -  __u64 \*pts
-
-       -  Returns the 33-bit timestamp as defined in ITU T-REC-H.222.0 /
-	  ISO/IEC 13818-1.
-
-	  The PTS should belong to the currently played frame if possible,
-	  but may also be a value close to it like the PTS of the last
-	  decoded frame or the last PTS extracted by the PES parser.
-
-
-Description
------------
-
-This ioctl is obsolete. Do not use in new drivers. If you need this
-functionality, then please contact the linux-media mailing list
-(`https://linuxtv.org/lists.php <https://linuxtv.org/lists.php>`__).
-
-This ioctl call asks the Audio Device to return the current PTS
-timestamp.
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
diff --git a/Documentation/media/uapi/dvb/audio-set-attributes.rst b/Documentation/media/uapi/dvb/audio-set-attributes.rst
deleted file mode 100644
index f0c6153ca80f..000000000000
--- a/Documentation/media/uapi/dvb/audio-set-attributes.rst
+++ /dev/null
@@ -1,67 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _AUDIO_SET_ATTRIBUTES:
-
-====================
-AUDIO_SET_ATTRIBUTES
-====================
-
-Name
-----
-
-AUDIO_SET_ATTRIBUTES
-
-.. attention:: This ioctl is deprecated
-
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, AUDIO_SET_ATTRIBUTES, struct audio_attributes *attr )
-    :name: AUDIO_SET_ATTRIBUTES
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -
-
-       -  audio_attributes_t attr
-
-       -  audio attributes according to section ??
-
-
-Description
------------
-
-This ioctl is intended for DVD playback and allows you to set certain
-information about the audio stream.
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  attr is not a valid or supported attribute setting.
diff --git a/Documentation/media/uapi/dvb/audio-set-ext-id.rst b/Documentation/media/uapi/dvb/audio-set-ext-id.rst
deleted file mode 100644
index 8503c47f26bd..000000000000
--- a/Documentation/media/uapi/dvb/audio-set-ext-id.rst
+++ /dev/null
@@ -1,66 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _AUDIO_SET_EXT_ID:
-
-================
-AUDIO_SET_EXT_ID
-================
-
-Name
-----
-
-AUDIO_SET_EXT_ID
-
-.. attention:: This ioctl is deprecated
-
-Synopsis
---------
-
-.. c:function:: int  ioctl(fd, AUDIO_SET_EXT_ID, int id)
-    :name: AUDIO_SET_EXT_ID
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -
-
-       -  int id
-
-       -  audio sub_stream_id
-
-
-Description
------------
-
-This ioctl can be used to set the extension id for MPEG streams in DVD
-playback. Only the first 3 bits are recognized.
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  id is not a valid id.
diff --git a/Documentation/media/uapi/dvb/audio-set-karaoke.rst b/Documentation/media/uapi/dvb/audio-set-karaoke.rst
deleted file mode 100644
index c759952d88aa..000000000000
--- a/Documentation/media/uapi/dvb/audio-set-karaoke.rst
+++ /dev/null
@@ -1,66 +0,0 @@
-.. -*- coding: utf-8; mode: rst -*-
-
-.. _AUDIO_SET_KARAOKE:
-
-=================
-AUDIO_SET_KARAOKE
-=================
-
-Name
-----
-
-AUDIO_SET_KARAOKE
-
-.. attention:: This ioctl is deprecated
-
-Synopsis
---------
-
-.. c:function:: int ioctl(fd, AUDIO_SET_KARAOKE, struct audio_karaoke *karaoke)
-    :name: AUDIO_SET_KARAOKE
-
-
-Arguments
----------
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -
-
-       -  int fd
-
-       -  File descriptor returned by a previous call to open().
-
-    -
-
-       -  audio_karaoke_t \*karaoke
-
-       -  karaoke settings according to section ??.
-
-
-Description
------------
-
-This ioctl allows one to set the mixer settings for a karaoke DVD.
-
-
-Return Value
-------------
-
-On success 0 is returned, on error -1 and the ``errno`` variable is set
-appropriately. The generic error codes are described at the
-:ref:`Generic Error Codes <gen-errors>` chapter.
-
-.. flat-table::
-    :header-rows:  0
-    :stub-columns: 0
-
-
-    -  .. row 1
-
-       -  ``EINVAL``
-
-       -  karaoke is not a valid or supported karaoke setting.
diff --git a/Documentation/media/uapi/dvb/audio_data_types.rst b/Documentation/media/uapi/dvb/audio_data_types.rst
index 6b93359d64f7..5bffa2c98a24 100644
--- a/Documentation/media/uapi/dvb/audio_data_types.rst
+++ b/Documentation/media/uapi/dvb/audio_data_types.rst
@@ -114,40 +114,3 @@ following bits set according to the hardwares capabilities.
      #define AUDIO_CAP_OGG   64
      #define AUDIO_CAP_SDDS 128
      #define AUDIO_CAP_AC3  256
-
-.. c:type:: audio_karaoke
-
-The ioctl AUDIO_SET_KARAOKE uses the following format:
-
-
-.. code-block:: c
-
-    typedef
-    struct audio_karaoke {
-	int vocal1;
-	int vocal2;
-	int melody;
-    } audio_karaoke_t;
-
-If Vocal1 or Vocal2 are non-zero, they get mixed into left and right t
-at 70% each. If both, Vocal1 and Vocal2 are non-zero, Vocal1 gets mixed
-into the left channel and Vocal2 into the right channel at 100% each. Ff
-Melody is non-zero, the melody channel gets mixed into left and right.
-
-
-.. c:type:: audio_attributes
-
-The following attributes can be set by a call to AUDIO_SET_ATTRIBUTES:
-
-
-.. code-block:: c
-
-     typedef uint16_t audio_attributes_t;
-     /*   bits: descr. */
-     /*   15-13 audio coding mode (0=ac3, 2=mpeg1, 3=mpeg2ext, 4=LPCM, 6=DTS, */
-     /*   12    multichannel extension */
-     /*   11-10 audio type (0=not spec, 1=language included) */
-     /*    9- 8 audio application mode (0=not spec, 1=karaoke, 2=surround) */
-     /*    7- 6 Quantization / DRC (mpeg audio: 1=DRC exists)(lpcm: 0=16bit,  */
-     /*    5- 4 Sample frequency fs (0=48kHz, 1=96kHz) */
-     /*    2- 0 number of audio channels (n+1 channels) */
diff --git a/Documentation/media/uapi/dvb/audio_function_calls.rst b/Documentation/media/uapi/dvb/audio_function_calls.rst
index 0bb56f0cfed4..7dba16285dab 100644
--- a/Documentation/media/uapi/dvb/audio_function_calls.rst
+++ b/Documentation/media/uapi/dvb/audio_function_calls.rst
@@ -22,13 +22,9 @@ Audio Function Calls
     audio-set-bypass-mode
     audio-channel-select
     audio-bilingual-channel-select
-    audio-get-pts
     audio-get-status
     audio-get-capabilities
     audio-clear-buffer
     audio-set-id
     audio-set-mixer
     audio-set-streamtype
-    audio-set-ext-id
-    audio-set-attributes
-    audio-set-karaoke
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 59216b172003..a9b00942e87d 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -1178,9 +1178,6 @@ COMPATIBLE_IOCTL(AUDIO_CLEAR_BUFFER)
 COMPATIBLE_IOCTL(AUDIO_SET_ID)
 COMPATIBLE_IOCTL(AUDIO_SET_MIXER)
 COMPATIBLE_IOCTL(AUDIO_SET_STREAMTYPE)
-COMPATIBLE_IOCTL(AUDIO_SET_EXT_ID)
-COMPATIBLE_IOCTL(AUDIO_SET_ATTRIBUTES)
-COMPATIBLE_IOCTL(AUDIO_SET_KARAOKE)
 COMPATIBLE_IOCTL(DMX_START)
 COMPATIBLE_IOCTL(DMX_STOP)
 COMPATIBLE_IOCTL(DMX_SET_FILTER)
diff --git a/include/uapi/linux/dvb/audio.h b/include/uapi/linux/dvb/audio.h
index 69f7a85d81b1..afeae063e640 100644
--- a/include/uapi/linux/dvb/audio.h
+++ b/include/uapi/linux/dvb/audio.h
@@ -67,27 +67,6 @@ typedef struct audio_status {
 } audio_status_t;                              /* separate decoder hardware */
 
 
-typedef
-struct audio_karaoke {  /* if Vocal1 or Vocal2 are non-zero, they get mixed  */
-	int vocal1;    /* into left and right t at 70% each */
-	int vocal2;    /* if both, Vocal1 and Vocal2 are non-zero, Vocal1 gets*/
-	int melody;    /* mixed into the left channel and */
-		       /* Vocal2 into the right channel at 100% each. */
-		       /* if Melody is non-zero, the melody channel gets mixed*/
-} audio_karaoke_t;     /* into left and right  */
-
-
-typedef __u16 audio_attributes_t;
-/*   bits: descr. */
-/*   15-13 audio coding mode (0=ac3, 2=mpeg1, 3=mpeg2ext, 4=LPCM, 6=DTS, */
-/*   12    multichannel extension */
-/*   11-10 audio type (0=not spec, 1=language included) */
-/*    9- 8 audio application mode (0=not spec, 1=karaoke, 2=surround) */
-/*    7- 6 Quantization / DRC (mpeg audio: 1=DRC exists)(lpcm: 0=16bit,  */
-/*    5- 4 Sample frequency fs (0=48kHz, 1=96kHz) */
-/*    2- 0 number of audio channels (n+1 channels) */
-
-
 /* for GET_CAPABILITIES and SET_FORMAT, the latter should only set one bit */
 #define AUDIO_CAP_DTS    1
 #define AUDIO_CAP_LPCM   2
@@ -115,22 +94,6 @@ typedef __u16 audio_attributes_t;
 #define AUDIO_SET_ID               _IO('o', 13)
 #define AUDIO_SET_MIXER            _IOW('o', 14, audio_mixer_t)
 #define AUDIO_SET_STREAMTYPE       _IO('o', 15)
-#define AUDIO_SET_EXT_ID           _IO('o', 16)
-#define AUDIO_SET_ATTRIBUTES       _IOW('o', 17, audio_attributes_t)
-#define AUDIO_SET_KARAOKE          _IOW('o', 18, audio_karaoke_t)
-
-/**
- * AUDIO_GET_PTS
- *
- * Read the 33 bit presentation time stamp as defined
- * in ITU T-REC-H.222.0 / ISO/IEC 13818-1.
- *
- * The PTS should belong to the currently played
- * frame if possible, but may also be a value close to it
- * like the PTS of the last decoded frame or the last PTS
- * extracted by the PES parser.
- */
-#define AUDIO_GET_PTS              _IOR('o', 19, __u64)
 #define AUDIO_BILINGUAL_CHANNEL_SELECT _IO('o', 20)
 
 #endif /* _DVBAUDIO_H_ */
-- 
cgit v1.2.3


From f9dc3af8212b626a62103e7ba8cb3c84482334b8 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:35:58 -0400
Subject: media: dvb-frontends/stv0910: cast the BER denominator shift exp to
 ULL

To avoid miscalculations related to the BER denominator, the shift
expression needs to be casted as ULL.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/stv0910.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/dvb-frontends/stv0910.c b/drivers/media/dvb-frontends/stv0910.c
index 41444fa1c0bb..91b21eb59531 100644
--- a/drivers/media/dvb-frontends/stv0910.c
+++ b/drivers/media/dvb-frontends/stv0910.c
@@ -682,8 +682,8 @@ static int get_bit_error_rate_s(struct stv *state, u32 *bernumerator,
 		return -EINVAL;
 
 	if ((regs[0] & 0x80) == 0) {
-		state->last_berdenominator = 1 << ((state->berscale * 2) +
-						  10 + 3);
+		state->last_berdenominator = 1ULL << ((state->berscale * 2) +
+						     10 + 3);
 		state->last_bernumerator = ((u32)(regs[0] & 0x7F) << 16) |
 			((u32)regs[1] << 8) | regs[2];
 		if (state->last_bernumerator < 256 && state->berscale < 6) {
-- 
cgit v1.2.3


From d33be4327eea80b46701d2b71f15749ec793f92d Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:35:59 -0400
Subject: media: ddbridge: probe for LNBH25 chips before attaching

In demod_attach_stv0910(), the LNBH25 IC is being blindly attached and,
if the result is bad, blindly attached on another possible I2C address.
The LNBH25 uses it's set_voltage function to test for the IC and will
print an error to the kernel log on failure. Prevent this by probing
the possible I2C address and use this (and only this) to attach the
LNBH25 I2C driver. This also allows the stv0910 attach function to be
a bit cleaner.

Picked up from the upstream dddvb GIT and adapted for the LNBH25 driver
variant from the kernel tree.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-core.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index d5b0d1eaf3ad..3f83415b06c7 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1191,6 +1191,13 @@ static const struct lnbh25_config lnbh25_cfg = {
 	.data2_config = LNBH25_TEN
 };
 
+static int has_lnbh25(struct i2c_adapter *i2c, u8 adr)
+{
+	u8 val;
+
+	return i2c_read_reg(i2c, adr, 0, &val) ? 0 : 1;
+}
+
 static int demod_attach_stv0910(struct ddb_input *input, int type, int tsfast)
 {
 	struct i2c_adapter *i2c = &input->port->i2c->adap;
@@ -1224,14 +1231,15 @@ static int demod_attach_stv0910(struct ddb_input *input, int type, int tsfast)
 	/* attach lnbh25 - leftshift by one as the lnbh25 driver expects 8bit
 	 * i2c addresses
 	 */
-	lnbcfg.i2c_address = (((input->nr & 1) ? 0x0d : 0x0c) << 1);
-	if (!dvb_attach(lnbh25_attach, dvb->fe, &lnbcfg, i2c)) {
+	if (has_lnbh25(i2c, 0x0d))
+		lnbcfg.i2c_address = (((input->nr & 1) ? 0x0d : 0x0c) << 1);
+	else
 		lnbcfg.i2c_address = (((input->nr & 1) ? 0x09 : 0x08) << 1);
-		if (!dvb_attach(lnbh25_attach, dvb->fe, &lnbcfg, i2c)) {
-			dev_err(dev, "No LNBH25 found!\n");
-			dvb_frontend_detach(dvb->fe);
-			return -ENODEV;
-		}
+
+	if (!dvb_attach(lnbh25_attach, dvb->fe, &lnbcfg, i2c)) {
+		dev_err(dev, "No LNBH25 found!\n");
+		dvb_frontend_detach(dvb->fe);
+		return -ENODEV;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From ce2280fbe65f14ab13663e2174abe2575b977c32 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:00 -0400
Subject: media: ddbridge: evaluate the actual link when setting up the dummy
 tuner

Devices supporting dummy tuner operation can exist on any link, not only
on link 0, so fix this accordingly.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 3f83415b06c7..55eb151f329e 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1859,7 +1859,7 @@ static void ddb_port_probe(struct ddb_port *port)
 	/* Handle missing ports and ports without I2C */
 
 	if (dummy_tuner && !port->nr &&
-	    dev->link[0].ids.device == 0x0005) {
+	    dev->link[l].ids.device == 0x0005) {
 		port->name = "DUMMY";
 		port->class = DDB_PORT_TUNER;
 		port->type = DDB_TUNER_DUMMY;
-- 
cgit v1.2.3


From d96eeee502cc5c75e0ab7d61468a3b906e609e98 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:01 -0400
Subject: media: ddbridge: report I2C bus errors

The I2C_COMMAND response reports an error in the I2C bus communication
using bit 17. Evaluate the response more thoroughly and log an error
if an I2C problem was detected.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-i2c.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-i2c.c b/drivers/media/pci/ddbridge/ddbridge-i2c.c
index 667340c86ea7..5a28d7611713 100644
--- a/drivers/media/pci/ddbridge/ddbridge-i2c.c
+++ b/drivers/media/pci/ddbridge/ddbridge-i2c.c
@@ -73,7 +73,10 @@ static int ddb_i2c_cmd(struct ddb_i2c *i2c, u32 adr, u32 cmd)
 		}
 		return -EIO;
 	}
-	if (val & 0x70000)
+	val &= 0x70000;
+	if (val == 0x20000)
+		dev_err(dev->dev, "I2C bus error\n");
+	if (val)
 		return -EIO;
 	return 0;
 }
-- 
cgit v1.2.3


From 7b6b9b153ad0127ec031438e3538acdebd677b02 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:02 -0400
Subject: media: ddbridge: remove unused MDIO defines and hwinfo member

ddbridge has a few MDIO related remainders (defines, hwinfo struct) which
aren't of any use for the in-kernel driver at all (they're only used in
conjunction with the OctoNet SAT>IP boxes which the kernel driver doesn't
have any support for), so clean this up.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-regs.h | 8 --------
 drivers/media/pci/ddbridge/ddbridge.h      | 1 -
 2 files changed, 9 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-regs.h b/drivers/media/pci/ddbridge/ddbridge-regs.h
index b978b5991940..f9e1cbb99b53 100644
--- a/drivers/media/pci/ddbridge/ddbridge-regs.h
+++ b/drivers/media/pci/ddbridge/ddbridge-regs.h
@@ -33,14 +33,6 @@
 #define GPIO_INPUT       0x24
 #define GPIO_DIRECTION   0x28
 
-/* ------------------------------------------------------------------------- */
-/* MDIO */
-
-#define MDIO_CTRL        0x20
-#define MDIO_ADR         0x24
-#define MDIO_REG         0x28
-#define MDIO_VAL         0x2C
-
 /* ------------------------------------------------------------------------- */
 
 #define BOARD_CONTROL    0x30
diff --git a/drivers/media/pci/ddbridge/ddbridge.h b/drivers/media/pci/ddbridge/ddbridge.h
index a66b1125cc74..9c645bee428a 100644
--- a/drivers/media/pci/ddbridge/ddbridge.h
+++ b/drivers/media/pci/ddbridge/ddbridge.h
@@ -127,7 +127,6 @@ struct ddb_info {
 	u8    temp_bus;
 	u32   board_control;
 	u32   board_control_2;
-	u8    mdio_num;
 	u8    con_clock; /* use a continuous clock */
 	u8    ts_quirks;
 #define TS_QUIRK_SERIAL   1
-- 
cgit v1.2.3


From 2957e53e57f2d8a791d5d56978e194440844f186 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:03 -0400
Subject: media: ddbridge: link structure access cosmetics in ddb_port_probe()

Throughout the function, dev->link[l] is used several times. Unclutter
this a bit by declaring a ddb_link var at the top of the function, assign
the address of dev->link[l] to it and use that var to access the link[]
struct member.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-core.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 55eb151f329e..408460be00b7 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1850,6 +1850,7 @@ static void ddb_port_probe(struct ddb_port *port)
 {
 	struct ddb *dev = port->dev;
 	u32 l = port->lnr;
+	struct ddb_link *link = &dev->link[l];
 	u8 id, type;
 
 	port->name = "NO MODULE";
@@ -1859,7 +1860,7 @@ static void ddb_port_probe(struct ddb_port *port)
 	/* Handle missing ports and ports without I2C */
 
 	if (dummy_tuner && !port->nr &&
-	    dev->link[l].ids.device == 0x0005) {
+	    link->ids.device == 0x0005) {
 		port->name = "DUMMY";
 		port->class = DDB_PORT_TUNER;
 		port->type = DDB_TUNER_DUMMY;
@@ -1873,14 +1874,14 @@ static void ddb_port_probe(struct ddb_port *port)
 		return;
 	}
 
-	if (port->nr == 1 && dev->link[l].info->type == DDB_OCTOPUS_CI &&
-	    dev->link[l].info->i2c_mask == 1) {
+	if (port->nr == 1 && link->info->type == DDB_OCTOPUS_CI &&
+	    link->info->i2c_mask == 1) {
 		port->name = "NO TAB";
 		port->class = DDB_PORT_NONE;
 		return;
 	}
 
-	if (dev->link[l].info->type == DDB_OCTOPUS_MAX) {
+	if (link->info->type == DDB_OCTOPUS_MAX) {
 		port->name = "DUAL DVB-S2 MAX";
 		port->type_name = "MXL5XX";
 		port->class = DDB_PORT_TUNER;
@@ -1891,8 +1892,8 @@ static void ddb_port_probe(struct ddb_port *port)
 		return;
 	}
 
-	if (dev->link[l].info->type == DDB_OCTOPUS_MCI) {
-		if (port->nr >= dev->link[l].info->mci)
+	if (link->info->type == DDB_OCTOPUS_MCI) {
+		if (port->nr >= link->info->mci)
 			return;
 		port->name = "DUAL MCI";
 		port->type_name = "MCI";
@@ -1901,7 +1902,7 @@ static void ddb_port_probe(struct ddb_port *port)
 		return;
 	}
 
-	if (port->nr > 1 && dev->link[l].info->type == DDB_OCTOPUS_CI) {
+	if (port->nr > 1 && link->info->type == DDB_OCTOPUS_CI) {
 		port->name = "CI internal";
 		port->type_name = "INTERNAL";
 		port->class = DDB_PORT_CI;
@@ -1986,7 +1987,7 @@ static void ddb_port_probe(struct ddb_port *port)
 		port->class = DDB_PORT_TUNER;
 		if (id == 0x51) {
 			if (port->nr == 0 &&
-			    dev->link[l].info->ts_quirks & TS_QUIRK_REVERSED)
+			    link->info->ts_quirks & TS_QUIRK_REVERSED)
 				port->type = DDB_TUNER_DVBS_STV0910_PR;
 			else
 				port->type = DDB_TUNER_DVBS_STV0910_P;
-- 
cgit v1.2.3


From 9f269f1fd2397fe716468579b81a9cd0b2fed2ab Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:04 -0400
Subject: media: ddbridge: change MCI base ID and define a SX8 ID

Change the start of the MCI ID range (internally used only) to 48 and
define an ID for the SX8 card type. Use this new ID to handle device
attachment.

This change is done in preparation for support of more MCI based cards.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-core.c | 4 ++--
 drivers/media/pci/ddbridge/ddbridge.h      | 4 +++-
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 408460be00b7..68ea0ffdad2d 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1592,7 +1592,7 @@ static int dvb_input_attach(struct ddb_input *input)
 		if (demod_attach_dummy(input) < 0)
 			goto err_detach;
 		break;
-	case DDB_TUNER_MCI:
+	case DDB_TUNER_MCI_SX8:
 		if (ddb_fe_attach_mci(input) < 0)
 			goto err_detach;
 		break;
@@ -1898,7 +1898,7 @@ static void ddb_port_probe(struct ddb_port *port)
 		port->name = "DUAL MCI";
 		port->type_name = "MCI";
 		port->class = DDB_PORT_TUNER;
-		port->type = DDB_TUNER_MCI;
+		port->type = DDB_TUNER_MCI_SX8;
 		return;
 	}
 
diff --git a/drivers/media/pci/ddbridge/ddbridge.h b/drivers/media/pci/ddbridge/ddbridge.h
index 9c645bee428a..65bd74d86ed5 100644
--- a/drivers/media/pci/ddbridge/ddbridge.h
+++ b/drivers/media/pci/ddbridge/ddbridge.h
@@ -254,7 +254,6 @@ struct ddb_port {
 #define DDB_CI_EXTERNAL_XO2_B    13
 #define DDB_TUNER_DVBS_STV0910_PR 14
 #define DDB_TUNER_DVBC2T2I_SONY_P 15
-#define DDB_TUNER_MCI            16
 
 #define DDB_TUNER_XO2            32
 #define DDB_TUNER_DVBS_STV0910   (DDB_TUNER_XO2 + 0)
@@ -264,6 +263,9 @@ struct ddb_port {
 #define DDB_TUNER_ATSC_ST        (DDB_TUNER_XO2 + 4)
 #define DDB_TUNER_DVBC2T2I_SONY  (DDB_TUNER_XO2 + 5)
 
+#define DDB_TUNER_MCI            48
+#define DDB_TUNER_MCI_SX8        (DDB_TUNER_MCI + 0)
+
 	struct ddb_input      *input[2];
 	struct ddb_output     *output;
 	struct dvb_ca_en50221 *en;
-- 
cgit v1.2.3


From 3addf0fa820b3da34e0c0e532167afcee8089a3b Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:05 -0400
Subject: media: ddbridge/mci: update copyright year in headers

Update the copyright year information in the MCI headers to 2017-2018.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-mci.c | 6 +++---
 drivers/media/pci/ddbridge/ddbridge-mci.h | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.c b/drivers/media/pci/ddbridge/ddbridge-mci.c
index 4ac634fc96e4..46b20b06e2a6 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.c
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.c
@@ -2,9 +2,9 @@
 /*
  * ddbridge-mci.c: Digital Devices microcode interface
  *
- * Copyright (C) 2017 Digital Devices GmbH
- *                    Ralph Metzler <rjkm@metzlerbros.de>
- *                    Marcus Metzler <mocm@metzlerbros.de>
+ * Copyright (C) 2017-2018 Digital Devices GmbH
+ *                         Ralph Metzler <rjkm@metzlerbros.de>
+ *                         Marcus Metzler <mocm@metzlerbros.de>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index 209cc2b92dff..389f6376603b 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -2,9 +2,9 @@
 /*
  * ddbridge-mci.h: Digital Devices micro code interface
  *
- * Copyright (C) 2017 Digital Devices GmbH
- *                    Marcus Metzler <mocm@metzlerbros.de>
- *                    Ralph Metzler <rjkm@metzlerbros.de>
+ * Copyright (C) 2017-2018 Digital Devices GmbH
+ *                         Marcus Metzler <mocm@metzlerbros.de>
+ *                         Ralph Metzler <rjkm@metzlerbros.de>
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License
-- 
cgit v1.2.3


From 3c7d591121c3f5cb97abb9c5dd2a9c2bd8532674 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:06 -0400
Subject: media: ddbridge/mci: read and report signal strength and SNR

Implement querying signal statistics from the MCI and report this data
in read_status() as DVBv5 statistics.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-mci.c | 47 ++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.c b/drivers/media/pci/ddbridge/ddbridge-mci.c
index 46b20b06e2a6..7d402861fa9e 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.c
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.c
@@ -155,6 +155,47 @@ static void release(struct dvb_frontend *fe)
 	kfree(state);
 }
 
+static int get_info(struct dvb_frontend *fe)
+{
+	int stat;
+	struct mci *state = fe->demodulator_priv;
+	struct mci_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.command = MCI_CMD_GETSIGNALINFO;
+	cmd.demod = state->demod;
+	stat = mci_cmd(state, &cmd, &state->signal_info);
+	return stat;
+}
+
+static int get_snr(struct dvb_frontend *fe)
+{
+	struct mci *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+
+	p->cnr.len = 1;
+	p->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+	p->cnr.stat[0].svalue =
+		(s64)state->signal_info.dvbs2_signal_info.signal_to_noise
+		     * 10;
+	return 0;
+}
+
+static int get_strength(struct dvb_frontend *fe)
+{
+	struct mci *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	s32 str;
+
+	str = 100000 -
+	      (state->signal_info.dvbs2_signal_info.channel_power
+	       * 10 + 108750);
+	p->strength.len = 1;
+	p->strength.stat[0].scale = FE_SCALE_DECIBEL;
+	p->strength.stat[0].svalue = str;
+	return 0;
+}
+
 static int read_status(struct dvb_frontend *fe, enum fe_status *status)
 {
 	int stat;
@@ -168,10 +209,14 @@ static int read_status(struct dvb_frontend *fe, enum fe_status *status)
 	if (stat)
 		return stat;
 	*status = 0x00;
+	get_info(fe);
+	get_strength(fe);
 	if (res.status == SX8_DEMOD_WAIT_MATYPE)
 		*status = 0x0f;
-	if (res.status == SX8_DEMOD_LOCKED)
+	if (res.status == SX8_DEMOD_LOCKED) {
 		*status = 0x1f;
+		get_snr(fe);
+	}
 	return stat;
 }
 
-- 
cgit v1.2.3


From 9b28ba016fc4a387ffefccbc6c390af3fdf37eb9 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:07 -0400
Subject: media: ddbridge/mci: rename defines and fix i/q var types

Adjustments to match the FPGA firmware, and the signal I/Q values are
reported as s16 types from the card firmware.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-mci.c |  2 +-
 drivers/media/pci/ddbridge/ddbridge-mci.h | 56 +++++++++++++++----------------
 2 files changed, 29 insertions(+), 29 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.c b/drivers/media/pci/ddbridge/ddbridge-mci.c
index 7d402861fa9e..fa0d7d0cc6f6 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.c
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.c
@@ -342,7 +342,7 @@ unlock:
 	memset(&cmd, 0, sizeof(cmd));
 
 	if (state->base->iq_mode) {
-		cmd.command = SX8_CMD_SELECT_IQOUT;
+		cmd.command = SX8_CMD_ENABLE_IQOUTPUT;
 		cmd.demod = state->demod;
 		cmd.output = 0;
 		mci_cmd(state, &cmd, NULL);
diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index 389f6376603b..2e74f0544717 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -51,40 +51,40 @@
 #define SX8_TSCONFIG_BURSTSIZE_8K           (0x00000020)
 #define SX8_TSCONFIG_BURSTSIZE_16K          (0x00000030)
 
-#define SX8_DEMOD_STOPPED       (0)
-#define SX8_DEMOD_IQ_MODE       (1)
-#define SX8_DEMOD_WAIT_SIGNAL   (2)
-#define SX8_DEMOD_WAIT_MATYPE   (3)
-#define SX8_DEMOD_TIMEOUT       (14)
-#define SX8_DEMOD_LOCKED        (15)
+#define SX8_DEMOD_STOPPED        (0)
+#define SX8_DEMOD_IQ_MODE        (1)
+#define SX8_DEMOD_WAIT_SIGNAL    (2)
+#define SX8_DEMOD_WAIT_MATYPE    (3)
+#define SX8_DEMOD_TIMEOUT        (14)
+#define SX8_DEMOD_LOCKED         (15)
 
-#define MCI_CMD_STOP            (0x01)
-#define MCI_CMD_GETSTATUS       (0x02)
-#define MCI_CMD_GETSIGNALINFO   (0x03)
-#define MCI_CMD_RFPOWER         (0x04)
+#define MCI_CMD_STOP             (0x01)
+#define MCI_CMD_GETSTATUS        (0x02)
+#define MCI_CMD_GETSIGNALINFO    (0x03)
+#define MCI_CMD_RFPOWER          (0x04)
 
-#define MCI_CMD_SEARCH_DVBS     (0x10)
+#define MCI_CMD_SEARCH_DVBS      (0x10)
 
-#define MCI_CMD_GET_IQSYMBOL    (0x30)
+#define MCI_CMD_GET_IQSYMBOL     (0x30)
 
-#define SX8_CMD_INPUT_ENABLE    (0x40)
-#define SX8_CMD_INPUT_DISABLE   (0x41)
-#define SX8_CMD_START_IQ        (0x42)
-#define SX8_CMD_STOP_IQ         (0x43)
-#define SX8_CMD_SELECT_IQOUT    (0x44)
-#define SX8_CMD_SELECT_TSOUT    (0x45)
+#define SX8_CMD_INPUT_ENABLE     (0x40)
+#define SX8_CMD_INPUT_DISABLE    (0x41)
+#define SX8_CMD_START_IQ         (0x42)
+#define SX8_CMD_STOP_IQ          (0x43)
+#define SX8_CMD_ENABLE_IQOUTPUT  (0x44)
+#define SX8_CMD_DISABLE_IQOUTPUT (0x45)
 
-#define SX8_ERROR_UNSUPPORTED   (0x80)
+#define MCI_ERROR_UNSUPPORTED    (0x80)
 
-#define SX8_SUCCESS(status)     (status < SX8_ERROR_UNSUPPORTED)
+#define MCI_SUCCESS(status)      (status < MCI_ERROR_UNSUPPORTED)
 
-#define SX8_CMD_DIAG_READ8      (0xE0)
-#define SX8_CMD_DIAG_READ32     (0xE1)
-#define SX8_CMD_DIAG_WRITE8     (0xE2)
-#define SX8_CMD_DIAG_WRITE32    (0xE3)
+#define SX8_CMD_DIAG_READ8       (0xE0)
+#define SX8_CMD_DIAG_READ32      (0xE1)
+#define SX8_CMD_DIAG_WRITE8      (0xE2)
+#define SX8_CMD_DIAG_WRITE32     (0xE3)
 
-#define SX8_CMD_DIAG_READRF     (0xE8)
-#define SX8_CMD_DIAG_WRITERF    (0xE9)
+#define SX8_CMD_DIAG_READRF      (0xE8)
+#define SX8_CMD_DIAG_WRITERF     (0xE9)
 
 struct mci_command {
 	union {
@@ -141,8 +141,8 @@ struct mci_result {
 			u32 ber_denominator;
 		} dvbs2_signal_info;
 		struct {
-			u8 i_symbol;
-			u8 q_symbol;
+			s16 i;
+			s16 q;
 		} dvbs2_signal_iq;
 	};
 	u32 version[4];
-- 
cgit v1.2.3


From 6094cbed4e7bee130f8b29c9a174bc336d19990b Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:08 -0400
Subject: media: ddbridge/mci: extend mci_command and mci_result structs

Recent FPGA firmware reports more data and values in sent command
responses. Adjust the mci_command and mci_result structs including it's
unions to match these changes and add a few comments explaining things.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-mci.h | 74 +++++++++++++++++++++++++++----
 1 file changed, 66 insertions(+), 8 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index 2e74f0544717..5e0c9e88b6fc 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -90,16 +90,30 @@ struct mci_command {
 	union {
 		u32 command_word;
 		struct {
-			u8 command;
-			u8 tuner;
-			u8 demod;
-			u8 output;
+			u8  command;
+			u8  tuner;
+			u8  demod;
+			u8  output;
 		};
 	};
 	union {
 		u32 params[31];
 		struct {
+			/*
+			 * Bit 0: DVB-S Enabled
+			 * Bit 1: DVB-S2 Enabled
+			 * Bit 7: InputStreamID
+			 */
 			u8  flags;
+			/*
+			 * Bit 0: QPSK,
+			 * Bit 1: 8PSK/8APSK
+			 * Bit 2: 16APSK
+			 * Bit 3: 32APSK
+			 * Bit 4: 64APSK
+			 * Bit 5: 128APSK
+			 * Bit 6: 256APSK
+			 */
 			u8  s2_modulation_mask;
 			u8  rsvd1;
 			u8  retry;
@@ -108,7 +122,36 @@ struct mci_command {
 			u8  input_stream_id;
 			u8  rsvd2[3];
 			u32 scrambling_sequence_index;
+			u32 frequency_range;
 		} dvbs2_search;
+
+		struct {
+			u8  tap;
+			u8  rsvd;
+			u16 point;
+		} get_iq_symbol;
+
+		struct {
+			/*
+			 * Bit 0: 0=VTM/1=SCAN
+			 * Bit 1: Set Gain
+			 */
+			u8  flags;
+			u8  roll_off;
+			u8  rsvd1;
+			u8  rsvd2;
+			u32 frequency;
+			u32 symbol_rate; /* Only in VTM mode */
+			u16 gain;
+		} sx8_start_iq;
+
+		struct {
+			/*
+			 * Bit 1:0 = STVVGLNA Gain.
+			 *   0 = AGC, 1 = 0dB, 2 = Minimum, 3 = Maximum
+			 */
+			u8  flags;
+		} sx8_input_enable;
 	};
 };
 
@@ -116,34 +159,49 @@ struct mci_result {
 	union {
 		u32 status_word;
 		struct {
-			u8 status;
-			u8 rsvd;
+			u8  status;
+			u8  mode;
 			u16 time;
 		};
 	};
 	union {
 		u32 result[27];
 		struct {
+			/* 1 = DVB-S, 2 = DVB-S2X */
 			u8  standard;
 			/* puncture rate for DVB-S */
 			u8  pls_code;
-			/* 7-6: rolloff, 5-2: rsrvd, 1:short, 0:pilots */
+			/* 2-0: rolloff */
 			u8  roll_off;
 			u8  rsvd;
+			/* actual frequency in Hz */
 			u32 frequency;
+			/* actual symbolrate in Hz */
 			u32 symbol_rate;
+			/* channel power in dBm x 100 */
 			s16 channel_power;
+			/* band power in dBm x 100 */
 			s16 band_power;
+			/*
+			 * SNR in dB x 100
+			 * Note: negative values are valid in DVB-S2
+			 */
 			s16 signal_to_noise;
 			s16 rsvd2;
+			/*
+			 * Counter for packet errors
+			 * (set to 0 on start command)
+			 */
 			u32 packet_errors;
+			/* Bit error rate: PreRS in DVB-S, PreBCH in DVB-S2X */
 			u32 ber_numerator;
 			u32 ber_denominator;
 		} dvbs2_signal_info;
+
 		struct {
 			s16 i;
 			s16 q;
-		} dvbs2_signal_iq;
+		} iq_symbol;
 	};
 	u32 version[4];
 };
-- 
cgit v1.2.3


From 07b12de21258e1d96445572100961d1d42b1b7f7 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:09 -0400
Subject: media: ddbridge/mci: store mci type and number of ports in the hwinfo

For better support for future MCI based cards, rename the mci struct
member to mci_ports to carry the number of ports on the cards, and add a
mci_type member to identify the card type to handle differing hardware.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-core.c | 4 ++--
 drivers/media/pci/ddbridge/ddbridge-hw.c   | 3 ++-
 drivers/media/pci/ddbridge/ddbridge.h      | 9 ++++++---
 3 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 68ea0ffdad2d..67b60da12cf4 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1893,12 +1893,12 @@ static void ddb_port_probe(struct ddb_port *port)
 	}
 
 	if (link->info->type == DDB_OCTOPUS_MCI) {
-		if (port->nr >= link->info->mci)
+		if (port->nr >= link->info->mci_ports)
 			return;
 		port->name = "DUAL MCI";
 		port->type_name = "MCI";
 		port->class = DDB_PORT_TUNER;
-		port->type = DDB_TUNER_MCI_SX8;
+		port->type = DDB_TUNER_MCI + link->info->mci_type;
 		return;
 	}
 
diff --git a/drivers/media/pci/ddbridge/ddbridge-hw.c b/drivers/media/pci/ddbridge/ddbridge-hw.c
index 1d3ee6accdd5..f3cbac07b41f 100644
--- a/drivers/media/pci/ddbridge/ddbridge-hw.c
+++ b/drivers/media/pci/ddbridge/ddbridge-hw.c
@@ -318,7 +318,8 @@ static const struct ddb_info ddb_s2x_48 = {
 	.port_num = 4,
 	.i2c_mask = 0x00,
 	.tempmon_irq = 24,
-	.mci      = 4
+	.mci_ports = 4,
+	.mci_type = 0,
 };
 
 /****************************************************************************/
diff --git a/drivers/media/pci/ddbridge/ddbridge.h b/drivers/media/pci/ddbridge/ddbridge.h
index 65bd74d86ed5..8a354dfb6c22 100644
--- a/drivers/media/pci/ddbridge/ddbridge.h
+++ b/drivers/media/pci/ddbridge/ddbridge.h
@@ -120,20 +120,23 @@ struct ddb_info {
 #define DDB_OCTOPUS_MCI     9
 	char *name;
 	u32   i2c_mask;
+	u32   board_control;
+	u32   board_control_2;
+
 	u8    port_num;
 	u8    led_num;
 	u8    fan_num;
 	u8    temp_num;
 	u8    temp_bus;
-	u32   board_control;
-	u32   board_control_2;
 	u8    con_clock; /* use a continuous clock */
 	u8    ts_quirks;
 #define TS_QUIRK_SERIAL   1
 #define TS_QUIRK_REVERSED 2
 #define TS_QUIRK_ALT_OSC  8
+	u8    mci_ports;
+	u8    mci_type;
+
 	u32   tempmon_irq;
-	u8    mci;
 	const struct ddb_regmap *regmap;
 };
 
-- 
cgit v1.2.3


From 84409a95bbae75c5396c6db9ac43f1d1626d6b75 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:10 -0400
Subject: media: ddbridge/mci: make ddb_mci_cmd() and ddb_mci_config() public

In preparation for splitting all MaxSX8 related code parts from the common
MCI code, prefix both mci_cmd() and mci_config() functions with ddb_,
remove the static marking and add matching function prototypes to
ddbridge-mci.h so these functions can be reused from other files within
the ddbridge driver. As this requires the mci-related structs to be
defined in ddbridge-mci.h, move struct mci and struct mci_base there and
clean them up.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-mci.c | 62 ++++++++-----------------------
 drivers/media/pci/ddbridge/ddbridge-mci.h | 36 ++++++++++++++++++
 2 files changed, 51 insertions(+), 47 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.c b/drivers/media/pci/ddbridge/ddbridge-mci.c
index fa0d7d0cc6f6..a29ff25d9029 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.c
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.c
@@ -26,38 +26,6 @@ static const u32 MCLK = (1550000000 / 12);
 static const u32 MAX_DEMOD_LDPC_BITRATE = (1550000000 / 6);
 static const u32 MAX_LDPC_BITRATE = (720000000);
 
-struct mci_base {
-	struct list_head     mci_list;
-	void                *key;
-	struct ddb_link     *link;
-	struct completion    completion;
-
-	struct device       *dev;
-	struct mutex         tuner_lock; /* concurrent tuner access lock */
-	u8                   adr;
-	struct mutex         mci_lock; /* concurrent MCI access lock */
-	int                  count;
-
-	u8                   tuner_use_count[MCI_TUNER_MAX];
-	u8                   assigned_demod[MCI_DEMOD_MAX];
-	u32                  used_ldpc_bitrate[MCI_DEMOD_MAX];
-	u8                   demod_in_use[MCI_DEMOD_MAX];
-	u32                  iq_mode;
-};
-
-struct mci {
-	struct mci_base     *base;
-	struct dvb_frontend  fe;
-	int                  nr;
-	int                  demod;
-	int                  tuner;
-	int                  first_time_lock;
-	int                  started;
-	struct mci_result    signal_info;
-
-	u32                  bb_mode;
-};
-
 static int mci_reset(struct mci *state)
 {
 	struct ddb_link *link = state->base->link;
@@ -84,7 +52,7 @@ static int mci_reset(struct mci *state)
 	return 0;
 }
 
-static int mci_config(struct mci *state, u32 config)
+int ddb_mci_config(struct mci *state, u32 config)
 {
 	struct ddb_link *link = state->base->link;
 
@@ -122,9 +90,9 @@ static int _mci_cmd_unlocked(struct mci *state,
 	return 0;
 }
 
-static int mci_cmd(struct mci *state,
-		   struct mci_command *command,
-		   struct mci_result *result)
+int ddb_mci_cmd(struct mci *state,
+		struct mci_command *command,
+		struct mci_result *result)
 {
 	int stat;
 
@@ -164,7 +132,7 @@ static int get_info(struct dvb_frontend *fe)
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.command = MCI_CMD_GETSIGNALINFO;
 	cmd.demod = state->demod;
-	stat = mci_cmd(state, &cmd, &state->signal_info);
+	stat = ddb_mci_cmd(state, &cmd, &state->signal_info);
 	return stat;
 }
 
@@ -205,7 +173,7 @@ static int read_status(struct dvb_frontend *fe, enum fe_status *status)
 
 	cmd.command = MCI_CMD_GETSTATUS;
 	cmd.demod = state->demod;
-	stat = mci_cmd(state, &cmd, &res);
+	stat = ddb_mci_cmd(state, &cmd, &res);
 	if (stat)
 		return stat;
 	*status = 0x00;
@@ -228,7 +196,7 @@ static int mci_set_tuner(struct dvb_frontend *fe, u32 tuner, u32 on)
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.tuner = state->tuner;
 	cmd.command = on ? SX8_CMD_INPUT_ENABLE : SX8_CMD_INPUT_DISABLE;
-	return mci_cmd(state, &cmd, NULL);
+	return ddb_mci_cmd(state, &cmd, NULL);
 }
 
 static int stop(struct dvb_frontend *fe)
@@ -241,13 +209,13 @@ static int stop(struct dvb_frontend *fe)
 	if (state->demod != DEMOD_UNUSED) {
 		cmd.command = MCI_CMD_STOP;
 		cmd.demod = state->demod;
-		mci_cmd(state, &cmd, NULL);
+		ddb_mci_cmd(state, &cmd, NULL);
 		if (state->base->iq_mode) {
 			cmd.command = MCI_CMD_STOP;
 			cmd.demod = state->demod;
 			cmd.output = 0;
-			mci_cmd(state, &cmd, NULL);
-			mci_config(state, SX8_TSCONFIG_MODE_NORMAL);
+			ddb_mci_cmd(state, &cmd, NULL);
+			ddb_mci_config(state, SX8_TSCONFIG_MODE_NORMAL);
 		}
 	}
 	mutex_lock(&state->base->tuner_lock);
@@ -345,8 +313,8 @@ unlock:
 		cmd.command = SX8_CMD_ENABLE_IQOUTPUT;
 		cmd.demod = state->demod;
 		cmd.output = 0;
-		mci_cmd(state, &cmd, NULL);
-		mci_config(state, ts_config);
+		ddb_mci_cmd(state, &cmd, NULL);
+		ddb_mci_config(state, ts_config);
 	}
 	if (p->stream_id != NO_STREAM_ID_FILTER && p->stream_id != 0x80000000)
 		flags |= 0x80;
@@ -368,7 +336,7 @@ unlock:
 	cmd.output = state->nr;
 	if (p->stream_id == 0x80000000)
 		cmd.output |= 0x80;
-	stat = mci_cmd(state, &cmd, NULL);
+	stat = ddb_mci_cmd(state, &cmd, NULL);
 	if (stat)
 		stop(fe);
 	return stat;
@@ -413,8 +381,8 @@ unlock:
 	cmd.tuner = state->tuner;
 	cmd.demod = state->demod;
 	cmd.output = 7;
-	mci_config(state, ts_config);
-	stat = mci_cmd(state, &cmd, NULL);
+	ddb_mci_config(state, ts_config);
+	stat = ddb_mci_cmd(state, &cmd, NULL);
 	if (stat)
 		stop(fe);
 	return stat;
diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index 5e0c9e88b6fc..14c8b1ee6358 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -206,6 +206,42 @@ struct mci_result {
 	u32 version[4];
 };
 
+struct mci_base {
+	struct list_head     mci_list;
+	void                *key;
+	struct ddb_link     *link;
+	struct completion    completion;
+
+	struct device       *dev;
+	struct mutex         tuner_lock; /* concurrent tuner access lock */
+	u8                   adr;
+	struct mutex         mci_lock; /* concurrent MCI access lock */
+	int                  count;
+
+	u8                   tuner_use_count[MCI_TUNER_MAX];
+	u8                   assigned_demod[MCI_DEMOD_MAX];
+	u32                  used_ldpc_bitrate[MCI_DEMOD_MAX];
+	u8                   demod_in_use[MCI_DEMOD_MAX];
+	u32                  iq_mode;
+};
+
+struct mci {
+	struct mci_base     *base;
+	struct dvb_frontend  fe;
+	int                  nr;
+	int                  demod;
+	int                  tuner;
+	int                  first_time_lock;
+	int                  started;
+	struct mci_result    signal_info;
+
+	u32                  bb_mode;
+};
+
+int ddb_mci_cmd(struct mci *state, struct mci_command *command,
+		struct mci_result *result);
+int ddb_mci_config(struct mci *state, u32 config);
+
 struct dvb_frontend
 *ddb_mci_attach(struct ddb_input *input,
 		int mci_type, int nr,
-- 
cgit v1.2.3


From e552684809d601c9a6109a73322c816ce1de10bd Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:11 -0400
Subject: media: ddbridge/mci: split MaxSX8 specific code off to ddbridge-sx8.c

Split off all code specific to the MaxSX8 cards to a separate ddbridge-sx8
module and hook it up in the Makefile. This also adds evaluation of the
mci_type to allow for using different attach handling for different cards.
As different cards can implement things differently (ie. support differing
frontend_ops, and have different base structs being put ontop of the
common mci_base struct), this introduces the mci_cfg struct which is
initially used to hold a few specifics to the -sx8 submodule. While at it,
the handling of the i/q mode is adjusted slightly. Besides this and
handling mci_base and sx8_base struct pointers where needed, all code
is copied unmodified from ddbridge-mci.c.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/Makefile        |   3 +-
 drivers/media/pci/ddbridge/ddbridge-core.c |   2 +-
 drivers/media/pci/ddbridge/ddbridge-max.c  |  18 +-
 drivers/media/pci/ddbridge/ddbridge-max.h  |   2 +-
 drivers/media/pci/ddbridge/ddbridge-mci.c  | 408 +------------------------
 drivers/media/pci/ddbridge/ddbridge-mci.h  |  28 +-
 drivers/media/pci/ddbridge/ddbridge-sx8.c  | 474 +++++++++++++++++++++++++++++
 7 files changed, 516 insertions(+), 419 deletions(-)
 create mode 100644 drivers/media/pci/ddbridge/ddbridge-sx8.c

diff --git a/drivers/media/pci/ddbridge/Makefile b/drivers/media/pci/ddbridge/Makefile
index 9b9e35f171b7..5b6d5bbc38af 100644
--- a/drivers/media/pci/ddbridge/Makefile
+++ b/drivers/media/pci/ddbridge/Makefile
@@ -4,7 +4,8 @@
 #
 
 ddbridge-objs := ddbridge-main.o ddbridge-core.o ddbridge-ci.o \
-		ddbridge-hw.o ddbridge-i2c.o ddbridge-max.o ddbridge-mci.o
+		ddbridge-hw.o ddbridge-i2c.o ddbridge-max.o ddbridge-mci.o \
+		ddbridge-sx8.o
 
 obj-$(CONFIG_DVB_DDBRIDGE) += ddbridge.o
 
diff --git a/drivers/media/pci/ddbridge/ddbridge-core.c b/drivers/media/pci/ddbridge/ddbridge-core.c
index 67b60da12cf4..c1b982e8e6c9 100644
--- a/drivers/media/pci/ddbridge/ddbridge-core.c
+++ b/drivers/media/pci/ddbridge/ddbridge-core.c
@@ -1593,7 +1593,7 @@ static int dvb_input_attach(struct ddb_input *input)
 			goto err_detach;
 		break;
 	case DDB_TUNER_MCI_SX8:
-		if (ddb_fe_attach_mci(input) < 0)
+		if (ddb_fe_attach_mci(input, port->type) < 0)
 			goto err_detach;
 		break;
 	default:
diff --git a/drivers/media/pci/ddbridge/ddbridge-max.c b/drivers/media/pci/ddbridge/ddbridge-max.c
index 739e4b444cf4..8da1c7b91577 100644
--- a/drivers/media/pci/ddbridge/ddbridge-max.c
+++ b/drivers/media/pci/ddbridge/ddbridge-max.c
@@ -457,21 +457,29 @@ int ddb_fe_attach_mxl5xx(struct ddb_input *input)
 /******************************************************************************/
 /* MAX MCI related functions */
 
-int ddb_fe_attach_mci(struct ddb_input *input)
+int ddb_fe_attach_mci(struct ddb_input *input, u32 type)
 {
 	struct ddb *dev = input->port->dev;
 	struct ddb_dvb *dvb = &input->port->dvb[input->nr & 1];
 	struct ddb_port *port = input->port;
 	struct ddb_link *link = &dev->link[port->lnr];
 	int demod, tuner;
+	struct mci_cfg cfg;
 
 	demod = input->nr;
 	tuner = demod & 3;
-	if (fmode == 3)
-		tuner = 0;
-	dvb->fe = ddb_mci_attach(input, 0, demod, &dvb->set_input);
+	switch (type) {
+	case DDB_TUNER_MCI_SX8:
+		cfg = ddb_max_sx8_cfg;
+		if (fmode == 3)
+			tuner = 0;
+		break;
+	default:
+		return -EINVAL;
+	}
+	dvb->fe = ddb_mci_attach(input, &cfg, demod, &dvb->set_input);
 	if (!dvb->fe) {
-		dev_err(dev->dev, "No MAXSX8 found!\n");
+		dev_err(dev->dev, "No MCI card found!\n");
 		return -ENODEV;
 	}
 	if (!dvb->set_input) {
diff --git a/drivers/media/pci/ddbridge/ddbridge-max.h b/drivers/media/pci/ddbridge/ddbridge-max.h
index 82efc53baa94..9838c73973b6 100644
--- a/drivers/media/pci/ddbridge/ddbridge-max.h
+++ b/drivers/media/pci/ddbridge/ddbridge-max.h
@@ -25,6 +25,6 @@
 
 int ddb_lnb_init_fmode(struct ddb *dev, struct ddb_link *link, u32 fm);
 int ddb_fe_attach_mxl5xx(struct ddb_input *input);
-int ddb_fe_attach_mci(struct ddb_input *input);
+int ddb_fe_attach_mci(struct ddb_input *input, u32 type);
 
 #endif /* _DDBRIDGE_MAX_H */
diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.c b/drivers/media/pci/ddbridge/ddbridge-mci.c
index a29ff25d9029..97384ae9ad27 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.c
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.c
@@ -22,10 +22,6 @@
 
 static LIST_HEAD(mci_list);
 
-static const u32 MCLK = (1550000000 / 12);
-static const u32 MAX_DEMOD_LDPC_BITRATE = (1550000000 / 6);
-static const u32 MAX_LDPC_BITRATE = (720000000);
-
 static int mci_reset(struct mci *state)
 {
 	struct ddb_link *link = state->base->link;
@@ -99,7 +95,7 @@ int ddb_mci_cmd(struct mci *state,
 	mutex_lock(&state->base->mci_lock);
 	stat = _mci_cmd_unlocked(state,
 				 (u32 *)command, sizeof(*command) / sizeof(u32),
-				 (u32 *)result, sizeof(*result) / sizeof(u32));
+				 (u32 *)result,	sizeof(*result) / sizeof(u32));
 	mutex_unlock(&state->base->mci_lock);
 	return stat;
 }
@@ -111,389 +107,6 @@ static void mci_handler(void *priv)
 	complete(&base->completion);
 }
 
-static void release(struct dvb_frontend *fe)
-{
-	struct mci *state = fe->demodulator_priv;
-
-	state->base->count--;
-	if (state->base->count == 0) {
-		list_del(&state->base->mci_list);
-		kfree(state->base);
-	}
-	kfree(state);
-}
-
-static int get_info(struct dvb_frontend *fe)
-{
-	int stat;
-	struct mci *state = fe->demodulator_priv;
-	struct mci_command cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.command = MCI_CMD_GETSIGNALINFO;
-	cmd.demod = state->demod;
-	stat = ddb_mci_cmd(state, &cmd, &state->signal_info);
-	return stat;
-}
-
-static int get_snr(struct dvb_frontend *fe)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-
-	p->cnr.len = 1;
-	p->cnr.stat[0].scale = FE_SCALE_DECIBEL;
-	p->cnr.stat[0].svalue =
-		(s64)state->signal_info.dvbs2_signal_info.signal_to_noise
-		     * 10;
-	return 0;
-}
-
-static int get_strength(struct dvb_frontend *fe)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	s32 str;
-
-	str = 100000 -
-	      (state->signal_info.dvbs2_signal_info.channel_power
-	       * 10 + 108750);
-	p->strength.len = 1;
-	p->strength.stat[0].scale = FE_SCALE_DECIBEL;
-	p->strength.stat[0].svalue = str;
-	return 0;
-}
-
-static int read_status(struct dvb_frontend *fe, enum fe_status *status)
-{
-	int stat;
-	struct mci *state = fe->demodulator_priv;
-	struct mci_command cmd;
-	struct mci_result res;
-
-	cmd.command = MCI_CMD_GETSTATUS;
-	cmd.demod = state->demod;
-	stat = ddb_mci_cmd(state, &cmd, &res);
-	if (stat)
-		return stat;
-	*status = 0x00;
-	get_info(fe);
-	get_strength(fe);
-	if (res.status == SX8_DEMOD_WAIT_MATYPE)
-		*status = 0x0f;
-	if (res.status == SX8_DEMOD_LOCKED) {
-		*status = 0x1f;
-		get_snr(fe);
-	}
-	return stat;
-}
-
-static int mci_set_tuner(struct dvb_frontend *fe, u32 tuner, u32 on)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct mci_command cmd;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.tuner = state->tuner;
-	cmd.command = on ? SX8_CMD_INPUT_ENABLE : SX8_CMD_INPUT_DISABLE;
-	return ddb_mci_cmd(state, &cmd, NULL);
-}
-
-static int stop(struct dvb_frontend *fe)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct mci_command cmd;
-	u32 input = state->tuner;
-
-	memset(&cmd, 0, sizeof(cmd));
-	if (state->demod != DEMOD_UNUSED) {
-		cmd.command = MCI_CMD_STOP;
-		cmd.demod = state->demod;
-		ddb_mci_cmd(state, &cmd, NULL);
-		if (state->base->iq_mode) {
-			cmd.command = MCI_CMD_STOP;
-			cmd.demod = state->demod;
-			cmd.output = 0;
-			ddb_mci_cmd(state, &cmd, NULL);
-			ddb_mci_config(state, SX8_TSCONFIG_MODE_NORMAL);
-		}
-	}
-	mutex_lock(&state->base->tuner_lock);
-	state->base->tuner_use_count[input]--;
-	if (!state->base->tuner_use_count[input])
-		mci_set_tuner(fe, input, 0);
-	if (state->demod < MCI_DEMOD_MAX)
-		state->base->demod_in_use[state->demod] = 0;
-	state->base->used_ldpc_bitrate[state->nr] = 0;
-	state->demod = DEMOD_UNUSED;
-	state->base->assigned_demod[state->nr] = DEMOD_UNUSED;
-	state->base->iq_mode = 0;
-	mutex_unlock(&state->base->tuner_lock);
-	state->started = 0;
-	return 0;
-}
-
-static int start(struct dvb_frontend *fe, u32 flags, u32 modmask, u32 ts_config)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	u32 used_ldpc_bitrate = 0, free_ldpc_bitrate;
-	u32 used_demods = 0;
-	struct mci_command cmd;
-	u32 input = state->tuner;
-	u32 bits_per_symbol = 0;
-	int i, stat = 0;
-
-	if (p->symbol_rate >= (MCLK / 2))
-		flags &= ~1;
-	if ((flags & 3) == 0)
-		return -EINVAL;
-
-	if (flags & 2) {
-		u32 tmp = modmask;
-
-		bits_per_symbol = 1;
-		while (tmp & 1) {
-			tmp >>= 1;
-			bits_per_symbol++;
-		}
-	}
-
-	mutex_lock(&state->base->tuner_lock);
-	if (state->base->iq_mode) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	for (i = 0; i < MCI_DEMOD_MAX; i++) {
-		used_ldpc_bitrate += state->base->used_ldpc_bitrate[i];
-		if (state->base->demod_in_use[i])
-			used_demods++;
-	}
-	if (used_ldpc_bitrate >= MAX_LDPC_BITRATE ||
-	    ((ts_config & SX8_TSCONFIG_MODE_MASK) >
-	     SX8_TSCONFIG_MODE_NORMAL && used_demods > 0)) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	free_ldpc_bitrate = MAX_LDPC_BITRATE - used_ldpc_bitrate;
-	if (free_ldpc_bitrate > MAX_DEMOD_LDPC_BITRATE)
-		free_ldpc_bitrate = MAX_DEMOD_LDPC_BITRATE;
-
-	while (p->symbol_rate * bits_per_symbol > free_ldpc_bitrate)
-		bits_per_symbol--;
-
-	if (bits_per_symbol < 2) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	i = (p->symbol_rate > (MCLK / 2)) ? 3 : 7;
-	while (i >= 0 && state->base->demod_in_use[i])
-		i--;
-	if (i < 0) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	state->base->demod_in_use[i] = 1;
-	state->base->used_ldpc_bitrate[state->nr] = p->symbol_rate
-						    * bits_per_symbol;
-	state->demod = i;
-	state->base->assigned_demod[state->nr] = i;
-
-	if (!state->base->tuner_use_count[input])
-		mci_set_tuner(fe, input, 1);
-	state->base->tuner_use_count[input]++;
-	state->base->iq_mode = (ts_config > 1);
-unlock:
-	mutex_unlock(&state->base->tuner_lock);
-	if (stat)
-		return stat;
-	memset(&cmd, 0, sizeof(cmd));
-
-	if (state->base->iq_mode) {
-		cmd.command = SX8_CMD_ENABLE_IQOUTPUT;
-		cmd.demod = state->demod;
-		cmd.output = 0;
-		ddb_mci_cmd(state, &cmd, NULL);
-		ddb_mci_config(state, ts_config);
-	}
-	if (p->stream_id != NO_STREAM_ID_FILTER && p->stream_id != 0x80000000)
-		flags |= 0x80;
-	dev_dbg(state->base->dev, "MCI-%d: tuner=%d demod=%d\n",
-		state->nr, state->tuner, state->demod);
-	cmd.command = MCI_CMD_SEARCH_DVBS;
-	cmd.dvbs2_search.flags = flags;
-	cmd.dvbs2_search.s2_modulation_mask =
-		modmask & ((1 << (bits_per_symbol - 1)) - 1);
-	cmd.dvbs2_search.retry = 2;
-	cmd.dvbs2_search.frequency = p->frequency * 1000;
-	cmd.dvbs2_search.symbol_rate = p->symbol_rate;
-	cmd.dvbs2_search.scrambling_sequence_index =
-		p->scrambling_sequence_index;
-	cmd.dvbs2_search.input_stream_id =
-		(p->stream_id != NO_STREAM_ID_FILTER) ? p->stream_id : 0;
-	cmd.tuner = state->tuner;
-	cmd.demod = state->demod;
-	cmd.output = state->nr;
-	if (p->stream_id == 0x80000000)
-		cmd.output |= 0x80;
-	stat = ddb_mci_cmd(state, &cmd, NULL);
-	if (stat)
-		stop(fe);
-	return stat;
-}
-
-static int start_iq(struct dvb_frontend *fe, u32 ts_config)
-{
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	u32 used_demods = 0;
-	struct mci_command cmd;
-	u32 input = state->tuner;
-	int i, stat = 0;
-
-	mutex_lock(&state->base->tuner_lock);
-	if (state->base->iq_mode) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	for (i = 0; i < MCI_DEMOD_MAX; i++)
-		if (state->base->demod_in_use[i])
-			used_demods++;
-	if (used_demods > 0) {
-		stat = -EBUSY;
-		goto unlock;
-	}
-	state->demod = 0;
-	state->base->assigned_demod[state->nr] = 0;
-	if (!state->base->tuner_use_count[input])
-		mci_set_tuner(fe, input, 1);
-	state->base->tuner_use_count[input]++;
-	state->base->iq_mode = (ts_config > 1);
-unlock:
-	mutex_unlock(&state->base->tuner_lock);
-	if (stat)
-		return stat;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.command = SX8_CMD_START_IQ;
-	cmd.dvbs2_search.frequency = p->frequency * 1000;
-	cmd.dvbs2_search.symbol_rate = p->symbol_rate;
-	cmd.tuner = state->tuner;
-	cmd.demod = state->demod;
-	cmd.output = 7;
-	ddb_mci_config(state, ts_config);
-	stat = ddb_mci_cmd(state, &cmd, NULL);
-	if (stat)
-		stop(fe);
-	return stat;
-}
-
-static int set_parameters(struct dvb_frontend *fe)
-{
-	int stat = 0;
-	struct mci *state = fe->demodulator_priv;
-	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
-	u32 ts_config, iq_mode = 0, isi;
-
-	if (state->started)
-		stop(fe);
-
-	isi = p->stream_id;
-	if (isi != NO_STREAM_ID_FILTER)
-		iq_mode = (isi & 0x30000000) >> 28;
-
-	switch (iq_mode) {
-	case 1:
-		ts_config = (SX8_TSCONFIG_TSHEADER | SX8_TSCONFIG_MODE_IQ);
-		break;
-	case 2:
-		ts_config = (SX8_TSCONFIG_TSHEADER | SX8_TSCONFIG_MODE_IQ);
-		break;
-	default:
-		ts_config = SX8_TSCONFIG_MODE_NORMAL;
-		break;
-	}
-
-	if (iq_mode != 2) {
-		u32 flags = 3;
-		u32 mask = 3;
-
-		if (p->modulation == APSK_16 ||
-		    p->modulation == APSK_32) {
-			flags = 2;
-			mask = 15;
-		}
-		stat = start(fe, flags, mask, ts_config);
-	} else {
-		stat = start_iq(fe, ts_config);
-	}
-
-	if (!stat) {
-		state->started = 1;
-		state->first_time_lock = 1;
-		state->signal_info.status = SX8_DEMOD_WAIT_SIGNAL;
-	}
-
-	return stat;
-}
-
-static int tune(struct dvb_frontend *fe, bool re_tune,
-		unsigned int mode_flags,
-		unsigned int *delay, enum fe_status *status)
-{
-	int r;
-
-	if (re_tune) {
-		r = set_parameters(fe);
-		if (r)
-			return r;
-	}
-	r = read_status(fe, status);
-	if (r)
-		return r;
-
-	if (*status & FE_HAS_LOCK)
-		return 0;
-	*delay = HZ / 10;
-	return 0;
-}
-
-static enum dvbfe_algo get_algo(struct dvb_frontend *fe)
-{
-	return DVBFE_ALGO_HW;
-}
-
-static int set_input(struct dvb_frontend *fe, int input)
-{
-	struct mci *state = fe->demodulator_priv;
-
-	state->tuner = input;
-	dev_dbg(state->base->dev, "MCI-%d: input=%d\n", state->nr, input);
-	return 0;
-}
-
-static struct dvb_frontend_ops mci_ops = {
-	.delsys = { SYS_DVBS, SYS_DVBS2 },
-	.info = {
-		.name			= "Digital Devices MaxSX8 MCI DVB-S/S2/S2X",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
-		.symbol_rate_min	= 100000,
-		.symbol_rate_max	= 100000000,
-		.caps			= FE_CAN_INVERSION_AUTO |
-					  FE_CAN_FEC_AUTO       |
-					  FE_CAN_QPSK           |
-					  FE_CAN_2G_MODULATION  |
-					  FE_CAN_MULTISTREAM,
-	},
-	.get_frontend_algo		= get_algo,
-	.tune				= tune,
-	.release			= release,
-	.read_status			= read_status,
-};
-
 static struct mci_base *match_base(void *key)
 {
 	struct mci_base *p;
@@ -511,8 +124,7 @@ static int probe(struct mci *state)
 }
 
 struct dvb_frontend
-*ddb_mci_attach(struct ddb_input *input,
-		int mci_type, int nr,
+*ddb_mci_attach(struct ddb_input *input, struct mci_cfg *cfg, int nr,
 		int (**fn_set_input)(struct dvb_frontend *fe, int input))
 {
 	struct ddb_port *port = input->port;
@@ -520,9 +132,9 @@ struct dvb_frontend
 	struct ddb_link *link = &dev->link[port->lnr];
 	struct mci_base *base;
 	struct mci *state;
-	void *key = mci_type ? (void *)port : (void *)link;
+	void *key = cfg->type ? (void *)port : (void *)link;
 
-	state = kzalloc(sizeof(*state), GFP_KERNEL);
+	state = kzalloc(cfg->state_size, GFP_KERNEL);
 	if (!state)
 		return NULL;
 
@@ -531,7 +143,7 @@ struct dvb_frontend
 		base->count++;
 		state->base = base;
 	} else {
-		base = kzalloc(sizeof(*base), GFP_KERNEL);
+		base = kzalloc(cfg->base_size, GFP_KERNEL);
 		if (!base)
 			goto fail;
 		base->key = key;
@@ -548,15 +160,17 @@ struct dvb_frontend
 			goto fail;
 		}
 		list_add(&base->mci_list, &mci_list);
+		if (cfg->base_init)
+			cfg->base_init(base);
 	}
-	state->fe.ops = mci_ops;
+	memcpy(&state->fe.ops, cfg->fe_ops, sizeof(struct dvb_frontend_ops));
 	state->fe.demodulator_priv = state;
 	state->nr = nr;
-	*fn_set_input = set_input;
-
+	*fn_set_input = cfg->set_input;
 	state->tuner = nr;
 	state->demod = nr;
-
+	if (cfg->init)
+		cfg->init(state);
 	return &state->fe;
 fail:
 	kfree(state);
diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index 14c8b1ee6358..f02bc76e3c98 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -211,18 +211,11 @@ struct mci_base {
 	void                *key;
 	struct ddb_link     *link;
 	struct completion    completion;
-
 	struct device       *dev;
 	struct mutex         tuner_lock; /* concurrent tuner access lock */
-	u8                   adr;
 	struct mutex         mci_lock; /* concurrent MCI access lock */
 	int                  count;
-
-	u8                   tuner_use_count[MCI_TUNER_MAX];
-	u8                   assigned_demod[MCI_DEMOD_MAX];
-	u32                  used_ldpc_bitrate[MCI_DEMOD_MAX];
-	u8                   demod_in_use[MCI_DEMOD_MAX];
-	u32                  iq_mode;
+	int                  type;
 };
 
 struct mci {
@@ -231,20 +224,27 @@ struct mci {
 	int                  nr;
 	int                  demod;
 	int                  tuner;
-	int                  first_time_lock;
-	int                  started;
-	struct mci_result    signal_info;
+};
 
-	u32                  bb_mode;
+struct mci_cfg {
+	int                  type;
+	struct dvb_frontend_ops *fe_ops;
+	u32                  base_size;
+	u32                  state_size;
+	int (*init)(struct mci *mci);
+	int (*base_init)(struct mci_base *mci_base);
+	int (*set_input)(struct dvb_frontend *fe, int input);
 };
 
+/* defined in ddbridge-sx8.c */
+extern const struct mci_cfg ddb_max_sx8_cfg;
+
 int ddb_mci_cmd(struct mci *state, struct mci_command *command,
 		struct mci_result *result);
 int ddb_mci_config(struct mci *state, u32 config);
 
 struct dvb_frontend
-*ddb_mci_attach(struct ddb_input *input,
-		int mci_type, int nr,
+*ddb_mci_attach(struct ddb_input *input, struct mci_cfg *cfg, int nr,
 		int (**fn_set_input)(struct dvb_frontend *fe, int input));
 
 #endif /* _DDBRIDGE_MCI_H_ */
diff --git a/drivers/media/pci/ddbridge/ddbridge-sx8.c b/drivers/media/pci/ddbridge/ddbridge-sx8.c
new file mode 100644
index 000000000000..1a12f2105490
--- /dev/null
+++ b/drivers/media/pci/ddbridge/ddbridge-sx8.c
@@ -0,0 +1,474 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ddbridge-sx8.c: Digital Devices MAX SX8 driver
+ *
+ * Copyright (C) 2018 Digital Devices GmbH
+ *                    Marcus Metzler <mocm@metzlerbros.de>
+ *                    Ralph Metzler <rjkm@metzlerbros.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * version 2 only, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "ddbridge.h"
+#include "ddbridge-io.h"
+#include "ddbridge-mci.h"
+
+static const u32 MCLK = (1550000000 / 12);
+static const u32 MAX_LDPC_BITRATE = (720000000);
+static const u32 MAX_DEMOD_LDPC_BITRATE = (1550000000 / 6);
+
+#define SX8_TUNER_NUM 4
+#define SX8_DEMOD_NUM 8
+#define SX8_DEMOD_NONE 0xff
+
+struct sx8_base {
+	struct mci_base      mci_base;
+
+	u8                   tuner_use_count[SX8_TUNER_NUM];
+	u32                  gain_mode[SX8_TUNER_NUM];
+
+	u32                  used_ldpc_bitrate[SX8_DEMOD_NUM];
+	u8                   demod_in_use[SX8_DEMOD_NUM];
+	u32                  iq_mode;
+	u32                  burst_size;
+	u32                  direct_mode;
+};
+
+struct sx8 {
+	struct mci           mci;
+
+	int                  first_time_lock;
+	int                  started;
+	struct mci_result    signal_info;
+
+	u32                  bb_mode;
+	u32                  local_frequency;
+};
+
+static void release(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+
+	mci_base->count--;
+	if (mci_base->count == 0) {
+		list_del(&mci_base->mci_list);
+		kfree(mci_base);
+	}
+	kfree(state);
+}
+
+static int get_info(struct dvb_frontend *fe)
+{
+	int stat;
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.command = MCI_CMD_GETSIGNALINFO;
+	cmd.demod = state->mci.demod;
+	stat = ddb_mci_cmd(&state->mci, &cmd, &state->signal_info);
+	return stat;
+}
+
+static int get_snr(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+
+	p->cnr.len = 1;
+	p->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+	p->cnr.stat[0].svalue =
+		(s64)state->signal_info.dvbs2_signal_info.signal_to_noise
+		     * 10;
+	return 0;
+}
+
+static int get_strength(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	s32 str;
+
+	str = 100000 -
+	      (state->signal_info.dvbs2_signal_info.channel_power
+	       * 10 + 108750);
+	p->strength.len = 1;
+	p->strength.stat[0].scale = FE_SCALE_DECIBEL;
+	p->strength.stat[0].svalue = str;
+	return 0;
+}
+
+static int read_status(struct dvb_frontend *fe, enum fe_status *status)
+{
+	int stat;
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_command cmd;
+	struct mci_result res;
+
+	cmd.command = MCI_CMD_GETSTATUS;
+	cmd.demod = state->mci.demod;
+	stat = ddb_mci_cmd(&state->mci, &cmd, &res);
+	if (stat)
+		return stat;
+	*status = 0x00;
+	get_info(fe);
+	get_strength(fe);
+	if (res.status == SX8_DEMOD_WAIT_MATYPE)
+		*status = 0x0f;
+	if (res.status == SX8_DEMOD_LOCKED) {
+		*status = 0x1f;
+		get_snr(fe);
+	}
+	return stat;
+}
+
+static int mci_set_tuner(struct dvb_frontend *fe, u32 tuner, u32 on)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct mci_command cmd;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.tuner = state->mci.tuner;
+	cmd.command = on ? SX8_CMD_INPUT_ENABLE : SX8_CMD_INPUT_DISABLE;
+	cmd.sx8_input_enable.flags = sx8_base->gain_mode[state->mci.tuner];
+	return ddb_mci_cmd(&state->mci, &cmd, NULL);
+}
+
+static int stop(struct dvb_frontend *fe)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct mci_command cmd;
+	u32 input = state->mci.tuner;
+
+	memset(&cmd, 0, sizeof(cmd));
+	if (state->mci.demod != SX8_DEMOD_NONE) {
+		cmd.command = MCI_CMD_STOP;
+		cmd.demod = state->mci.demod;
+		ddb_mci_cmd(&state->mci, &cmd, NULL);
+		if (sx8_base->iq_mode) {
+			cmd.command = SX8_CMD_DISABLE_IQOUTPUT;
+			cmd.demod = state->mci.demod;
+			cmd.output = 0;
+			ddb_mci_cmd(&state->mci, &cmd, NULL);
+			ddb_mci_config(&state->mci, SX8_TSCONFIG_MODE_NORMAL);
+		}
+	}
+	mutex_lock(&mci_base->tuner_lock);
+	sx8_base->tuner_use_count[input]--;
+	if (!sx8_base->tuner_use_count[input])
+		mci_set_tuner(fe, input, 0);
+	if (state->mci.demod < SX8_DEMOD_NUM) {
+		sx8_base->demod_in_use[state->mci.demod] = 0;
+		state->mci.demod = SX8_DEMOD_NONE;
+	}
+	sx8_base->used_ldpc_bitrate[state->mci.nr] = 0;
+	sx8_base->iq_mode = 0;
+	mutex_unlock(&mci_base->tuner_lock);
+	state->started = 0;
+	return 0;
+}
+
+static int start(struct dvb_frontend *fe, u32 flags, u32 modmask, u32 ts_config)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	u32 used_ldpc_bitrate = 0, free_ldpc_bitrate;
+	u32 used_demods = 0;
+	struct mci_command cmd;
+	u32 input = state->mci.tuner;
+	u32 bits_per_symbol = 0;
+	int i = -1, stat = 0;
+
+	if (p->symbol_rate >= (MCLK / 2))
+		flags &= ~1;
+	if ((flags & 3) == 0)
+		return -EINVAL;
+
+	if (flags & 2) {
+		u32 tmp = modmask;
+
+		bits_per_symbol = 1;
+		while (tmp & 1) {
+			tmp >>= 1;
+			bits_per_symbol++;
+		}
+	}
+
+	mutex_lock(&mci_base->tuner_lock);
+	if (sx8_base->iq_mode) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+
+	if (sx8_base->direct_mode) {
+		if (p->symbol_rate >= MCLK / 2) {
+			if (state->mci.nr < 4)
+				i = state->mci.nr;
+		} else {
+			i = state->mci.nr;
+		}
+	} else {
+		for (i = 0; i < SX8_DEMOD_NUM; i++) {
+			used_ldpc_bitrate += sx8_base->used_ldpc_bitrate[i];
+			if (sx8_base->demod_in_use[i])
+				used_demods++;
+		}
+		if (used_ldpc_bitrate >= MAX_LDPC_BITRATE ||
+		    ((ts_config & SX8_TSCONFIG_MODE_MASK) >
+		     SX8_TSCONFIG_MODE_NORMAL && used_demods > 0)) {
+			stat = -EBUSY;
+			goto unlock;
+		}
+		free_ldpc_bitrate = MAX_LDPC_BITRATE - used_ldpc_bitrate;
+		if (free_ldpc_bitrate > MAX_DEMOD_LDPC_BITRATE)
+			free_ldpc_bitrate = MAX_DEMOD_LDPC_BITRATE;
+
+		while (p->symbol_rate * bits_per_symbol > free_ldpc_bitrate)
+			bits_per_symbol--;
+		if (bits_per_symbol < 2) {
+			stat = -EBUSY;
+			goto unlock;
+		}
+
+		modmask &= ((1 << (bits_per_symbol - 1)) - 1);
+		if (((flags & 0x02) != 0) && modmask == 0) {
+			stat = -EBUSY;
+			goto unlock;
+		}
+
+		i = (p->symbol_rate > (MCLK / 2)) ? 3 : 7;
+		while (i >= 0 && sx8_base->demod_in_use[i])
+			i--;
+	}
+
+	if (i < 0) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+	sx8_base->demod_in_use[i] = 1;
+	sx8_base->used_ldpc_bitrate[state->mci.nr] = p->symbol_rate
+						     * bits_per_symbol;
+	state->mci.demod = i;
+
+	if (!sx8_base->tuner_use_count[input])
+		mci_set_tuner(fe, input, 1);
+	sx8_base->tuner_use_count[input]++;
+	sx8_base->iq_mode = (ts_config > 1);
+unlock:
+	mutex_unlock(&mci_base->tuner_lock);
+	if (stat)
+		return stat;
+	memset(&cmd, 0, sizeof(cmd));
+
+	if (sx8_base->iq_mode) {
+		cmd.command = SX8_CMD_ENABLE_IQOUTPUT;
+		cmd.demod = state->mci.demod;
+		cmd.output = 0;
+		ddb_mci_cmd(&state->mci, &cmd, NULL);
+		ddb_mci_config(&state->mci, ts_config);
+	}
+	if (p->stream_id != NO_STREAM_ID_FILTER && p->stream_id != 0x80000000)
+		flags |= 0x80;
+	dev_dbg(mci_base->dev, "MCI-%d: tuner=%d demod=%d\n",
+		state->mci.nr, state->mci.tuner, state->mci.demod);
+	cmd.command = MCI_CMD_SEARCH_DVBS;
+	cmd.dvbs2_search.flags = flags;
+	cmd.dvbs2_search.s2_modulation_mask = modmask;
+	cmd.dvbs2_search.retry = 2;
+	cmd.dvbs2_search.frequency = p->frequency * 1000;
+	cmd.dvbs2_search.symbol_rate = p->symbol_rate;
+	cmd.dvbs2_search.scrambling_sequence_index =
+		p->scrambling_sequence_index;
+	cmd.dvbs2_search.input_stream_id =
+		(p->stream_id != NO_STREAM_ID_FILTER) ? p->stream_id : 0;
+	cmd.tuner = state->mci.tuner;
+	cmd.demod = state->mci.demod;
+	cmd.output = state->mci.nr;
+	if (p->stream_id == 0x80000000)
+		cmd.output |= 0x80;
+	stat = ddb_mci_cmd(&state->mci, &cmd, NULL);
+	if (stat)
+		stop(fe);
+	return stat;
+}
+
+static int start_iq(struct dvb_frontend *fe, u32 flags, u32 roll_off,
+		    u32 ts_config)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+	struct sx8_base *sx8_base = (struct sx8_base *)mci_base;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	u32 used_demods = 0;
+	struct mci_command cmd;
+	u32 input = state->mci.tuner;
+	int i, stat = 0;
+
+	mutex_lock(&mci_base->tuner_lock);
+	if (sx8_base->iq_mode) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+	for (i = 0; i < SX8_DEMOD_NUM; i++)
+		if (sx8_base->demod_in_use[i])
+			used_demods++;
+	if (used_demods > 0) {
+		stat = -EBUSY;
+		goto unlock;
+	}
+	state->mci.demod = 0;
+	if (!sx8_base->tuner_use_count[input])
+		mci_set_tuner(fe, input, 1);
+	sx8_base->tuner_use_count[input]++;
+	sx8_base->iq_mode = (ts_config > 1);
+unlock:
+	mutex_unlock(&mci_base->tuner_lock);
+	if (stat)
+		return stat;
+
+	memset(&cmd, 0, sizeof(cmd));
+	cmd.command = SX8_CMD_START_IQ;
+	cmd.sx8_start_iq.flags = flags;
+	cmd.sx8_start_iq.roll_off = roll_off;
+	cmd.sx8_start_iq.frequency = p->frequency * 1000;
+	cmd.sx8_start_iq.symbol_rate = p->symbol_rate;
+	cmd.tuner = state->mci.tuner;
+	cmd.demod = state->mci.demod;
+	stat = ddb_mci_cmd(&state->mci, &cmd, NULL);
+	if (stat)
+		stop(fe);
+	ddb_mci_config(&state->mci, ts_config);
+	return stat;
+}
+
+static int set_parameters(struct dvb_frontend *fe)
+{
+	int stat = 0;
+	struct sx8 *state = fe->demodulator_priv;
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+	u32 ts_config = SX8_TSCONFIG_MODE_NORMAL, iq_mode = 0, isi;
+
+	if (state->started)
+		stop(fe);
+
+	isi = p->stream_id;
+	if (isi != NO_STREAM_ID_FILTER)
+		iq_mode = (isi & 0x30000000) >> 28;
+
+	if (iq_mode)
+		ts_config = (SX8_TSCONFIG_TSHEADER | SX8_TSCONFIG_MODE_IQ);
+	if (iq_mode < 3) {
+		u32 flags = 3;
+		u32 mask = 0x7f;
+
+		if (p->modulation == APSK_16 ||
+		    p->modulation == APSK_32) {
+			flags = 2;
+			mask = 0x0f;
+		}
+		stat = start(fe, flags, mask, ts_config);
+	} else {
+		u32 flags = (iq_mode == 2) ? 1 : 0;
+
+		stat = start_iq(fe, flags, 4, ts_config);
+	}
+	if (!stat) {
+		state->started = 1;
+		state->first_time_lock = 1;
+		state->signal_info.status = SX8_DEMOD_WAIT_SIGNAL;
+	}
+
+	return stat;
+}
+
+static int tune(struct dvb_frontend *fe, bool re_tune,
+		unsigned int mode_flags,
+		unsigned int *delay, enum fe_status *status)
+{
+	int r;
+
+	if (re_tune) {
+		r = set_parameters(fe);
+		if (r)
+			return r;
+	}
+	r = read_status(fe, status);
+	if (r)
+		return r;
+
+	if (*status & FE_HAS_LOCK)
+		return 0;
+	*delay = HZ / 10;
+	return 0;
+}
+
+static enum dvbfe_algo get_algo(struct dvb_frontend *fe)
+{
+	return DVBFE_ALGO_HW;
+}
+
+static int set_input(struct dvb_frontend *fe, int input)
+{
+	struct sx8 *state = fe->demodulator_priv;
+	struct mci_base *mci_base = state->mci.base;
+
+	if (input >= SX8_TUNER_NUM)
+		return -EINVAL;
+
+	state->mci.tuner = input;
+	dev_dbg(mci_base->dev, "MCI-%d: input=%d\n", state->mci.nr, input);
+	return 0;
+}
+
+static struct dvb_frontend_ops sx8_ops = {
+	.delsys = { SYS_DVBS, SYS_DVBS2 },
+	.info = {
+		.name			= "Digital Devices MaxSX8 MCI DVB-S/S2/S2X",
+		.frequency_min		= 950000,
+		.frequency_max		= 2150000,
+		.frequency_stepsize	= 0,
+		.frequency_tolerance	= 0,
+		.symbol_rate_min	= 100000,
+		.symbol_rate_max	= 100000000,
+		.caps			= FE_CAN_INVERSION_AUTO |
+					  FE_CAN_FEC_AUTO       |
+					  FE_CAN_QPSK           |
+					  FE_CAN_2G_MODULATION  |
+					  FE_CAN_MULTISTREAM,
+	},
+	.get_frontend_algo		= get_algo,
+	.tune				= tune,
+	.release			= release,
+	.read_status			= read_status,
+};
+
+static int init(struct mci *mci)
+{
+	struct sx8 *state = (struct sx8 *)mci;
+
+	state->mci.demod = SX8_DEMOD_NONE;
+	return 0;
+}
+
+const struct mci_cfg ddb_max_sx8_cfg = {
+	.type = 0,
+	.fe_ops = &sx8_ops,
+	.base_size = sizeof(struct sx8_base),
+	.state_size = sizeof(struct sx8),
+	.init = init,
+	.set_input = set_input,
+};
-- 
cgit v1.2.3


From 8610326e39cc929dd6fa49161c3472e4babe6bbc Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:12 -0400
Subject: media: ddbridge/mci: add more MCI status codes, improve MCI_SUCCESS
 macro

The MCI can report the command status more finegrained, so, add more
status code defines and update the MCI_SUCCESS macro.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-mci.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index f02bc76e3c98..600a8bc642c4 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -74,9 +74,13 @@
 #define SX8_CMD_ENABLE_IQOUTPUT  (0x44)
 #define SX8_CMD_DISABLE_IQOUTPUT (0x45)
 
-#define MCI_ERROR_UNSUPPORTED    (0x80)
+#define MCI_STATUS_OK            (0x00)
+#define MCI_STATUS_UNSUPPORTED   (0x80)
+#define MCI_STATUS_RETRY         (0xFD)
+#define MCI_STATUS_NOT_READY     (0xFE)
+#define MCI_STATUS_ERROR         (0xFF)
 
-#define MCI_SUCCESS(status)      (status < MCI_ERROR_UNSUPPORTED)
+#define MCI_SUCCESS(status)      ((status & MCI_STATUS_UNSUPPORTED) == 0)
 
 #define SX8_CMD_DIAG_READ8       (0xE0)
 #define SX8_CMD_DIAG_READ32      (0xE1)
-- 
cgit v1.2.3


From 3153dfe2914bec728cab9a5c9d7b2ec71d714d9c Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:13 -0400
Subject: media: ddbridge/sx8: disable automatic PLS code search

The SX8 cards by default do an automatic search for the PLS code. This
is not necessarily wanted as this can eventually be detected wrong, so
disable this.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-sx8.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-sx8.c b/drivers/media/pci/ddbridge/ddbridge-sx8.c
index 1a12f2105490..c87cefa10762 100644
--- a/drivers/media/pci/ddbridge/ddbridge-sx8.c
+++ b/drivers/media/pci/ddbridge/ddbridge-sx8.c
@@ -292,7 +292,7 @@ unlock:
 	cmd.dvbs2_search.frequency = p->frequency * 1000;
 	cmd.dvbs2_search.symbol_rate = p->symbol_rate;
 	cmd.dvbs2_search.scrambling_sequence_index =
-		p->scrambling_sequence_index;
+		p->scrambling_sequence_index | 0x80000000;
 	cmd.dvbs2_search.input_stream_id =
 		(p->stream_id != NO_STREAM_ID_FILTER) ? p->stream_id : 0;
 	cmd.tuner = state->mci.tuner;
-- 
cgit v1.2.3


From e1f84840fd13e5f7ef4c20e3e9d021a0d2f19e11 Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:14 -0400
Subject: media: ddbridge/sx8: enable modulation selection in set_parameters()

Allow for tuning to transponders with specific modulations in
set_parameters(). Setting a specific modulation will also enable lower
modulations.

Picked up from the upstream dddvb GIT. Upstream also has support for
APSK64/128/256 modulations which aren't supported yet by the DVB
API, so comment them out until support for them is added.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-sx8.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-sx8.c b/drivers/media/pci/ddbridge/ddbridge-sx8.c
index c87cefa10762..4418604258d1 100644
--- a/drivers/media/pci/ddbridge/ddbridge-sx8.c
+++ b/drivers/media/pci/ddbridge/ddbridge-sx8.c
@@ -372,15 +372,31 @@ static int set_parameters(struct dvb_frontend *fe)
 	if (iq_mode)
 		ts_config = (SX8_TSCONFIG_TSHEADER | SX8_TSCONFIG_MODE_IQ);
 	if (iq_mode < 3) {
-		u32 flags = 3;
-		u32 mask = 0x7f;
-
-		if (p->modulation == APSK_16 ||
-		    p->modulation == APSK_32) {
-			flags = 2;
+		u32 mask;
+
+		switch (p->modulation) {
+		/* uncomment whenever these modulations hit the DVB API
+		 *	case APSK_256:
+		 *		mask = 0x7f;
+		 *		break;
+		 *	case APSK_128:
+		 *		mask = 0x3f;
+		 *		break;
+		 *	case APSK_64:
+		 *		mask = 0x1f;
+		 *		break;
+		 */
+		case APSK_32:
 			mask = 0x0f;
+			break;
+		case APSK_16:
+			mask = 0x07;
+			break;
+		default:
+			mask = 0x03;
+			break;
 		}
-		stat = start(fe, flags, mask, ts_config);
+		stat = start(fe, 3, mask, ts_config);
 	} else {
 		u32 flags = (iq_mode == 2) ? 1 : 0;
 
-- 
cgit v1.2.3


From 875658af666fb171f2b61a203281fde608bab24a Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sat, 23 Jun 2018 11:36:15 -0400
Subject: media: ddbridge/mci: add SX8 I/Q mode remark and remove DIAG CMD
 defines

Take note that the SX8 IQ mode is only available on a single tuner, and
remove the MCI/SX8 DIAG CMD defines.

Picked up from the upstream dddvb GIT.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/ddbridge/ddbridge-mci.h | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/media/pci/ddbridge/ddbridge-mci.h b/drivers/media/pci/ddbridge/ddbridge-mci.h
index 600a8bc642c4..24241111c634 100644
--- a/drivers/media/pci/ddbridge/ddbridge-mci.h
+++ b/drivers/media/pci/ddbridge/ddbridge-mci.h
@@ -42,6 +42,22 @@
 #define SX8_TSCONFIG_MODE_NORMAL            (0x00000001)
 #define SX8_TSCONFIG_MODE_IQ                (0x00000003)
 
+/*
+ * IQMode is only available on MaxSX8 on a single tuner
+ *
+ * IQ_MODE_SAMPLES
+ *       sampling rate is 1550/24 MHz (64.583 MHz)
+ *       channel agc is frozen, to allow stitching the FFT results together
+ *
+ * IQ_MODE_VTM
+ *       sampling rate is the supplied symbolrate
+ *       channel agc is active
+ *
+ * in both cases down sampling is done with a RRC Filter (currently fixed to
+ * alpha = 0.05) which causes some (ca 5%) aliasing at the edges from
+ * outside the spectrum
+ */
+
 #define SX8_TSCONFIG_TSHEADER               (0x00000004)
 #define SX8_TSCONFIG_BURST                  (0x00000008)
 
@@ -82,14 +98,6 @@
 
 #define MCI_SUCCESS(status)      ((status & MCI_STATUS_UNSUPPORTED) == 0)
 
-#define SX8_CMD_DIAG_READ8       (0xE0)
-#define SX8_CMD_DIAG_READ32      (0xE1)
-#define SX8_CMD_DIAG_WRITE8      (0xE2)
-#define SX8_CMD_DIAG_WRITE32     (0xE3)
-
-#define SX8_CMD_DIAG_READRF      (0xE8)
-#define SX8_CMD_DIAG_WRITERF     (0xE9)
-
 struct mci_command {
 	union {
 		u32 command_word;
-- 
cgit v1.2.3


From ca747d041adbf78d93bbea4d125c7ddc626effba Mon Sep 17 00:00:00 2001
From: Daniel Scheller <d.scheller@gmx.net>
Date: Sun, 24 Jun 2018 09:42:50 -0400
Subject: media: dvb-frontends/tda18271c2dd: fix handling of DVB-T parameters

Add a break statement in set_params() for the SYS_DVBT(2).

As reported by gcc:

    drivers/media/dvb-frontends/tda18271c2dd.c:1144:3: warning: this statement may fall through [-Wimplicit-fallthrough=]

There is a nested switch() inside the code with sets the tuner to
the right standard. Without the break, the code will always set to
DVB-C mode, with can be sub-optimal for DVB-T.

Signed-off-by: Daniel Scheller <d.scheller@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/tda18271c2dd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/dvb-frontends/tda18271c2dd.c b/drivers/media/dvb-frontends/tda18271c2dd.c
index 2e1d36ae943b..fcffc7b4acf7 100644
--- a/drivers/media/dvb-frontends/tda18271c2dd.c
+++ b/drivers/media/dvb-frontends/tda18271c2dd.c
@@ -1154,6 +1154,7 @@ static int set_params(struct dvb_frontend *fe)
 		default:
 			return -EINVAL;
 		}
+		break;
 	case SYS_DVBC_ANNEX_A:
 	case SYS_DVBC_ANNEX_C:
 		if (bw <= 6000000)
-- 
cgit v1.2.3


From bef1fa6ea72bb885e0285d502e35cc01198bee6c Mon Sep 17 00:00:00 2001
From: Robert Schlabbach <Robert.Schlabbach@gmx.net>
Date: Mon, 25 Jun 2018 06:33:58 -0400
Subject: media: em28xx: disable null packet filter for WinTVdualHD

This patch disables the null packet filter for the Hauppauge
WinTV-dualHD. There are applications which require the unfiltered
transport stream (e.g. DOCSIS segment load analyzers).

Tests showed that the device is capable of delivering two unfiltered
EuroDOCSIS 3.0 transport streams simultaneously, i.e. over 100 Mbit/s
worth of data, without any losses.

Signed-off-by: Robert Schlabbach <Robert.Schlabbach@gmx.net>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-cards.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index afdc92998fff..98a428769baa 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -543,7 +543,7 @@ static const struct em28xx_reg_seq hauppauge_dualhd_dvb[] = {
 	{EM2874_R80_GPIO_P0_CTRL,      0xff, 0xff,    100},
 	{EM2874_R80_GPIO_P0_CTRL,      0xdf, 0xff,    100}, /* demod 2 reset */
 	{EM2874_R80_GPIO_P0_CTRL,      0xff, 0xff,    100},
-	{EM2874_R5F_TS_ENABLE,         0x44, 0xff,     50},
+	{EM2874_R5F_TS_ENABLE,         0x00, 0xff,     50}, /* disable TS filters */
 	{EM2874_R5D_TS1_PKT_SIZE,      0x05, 0xff,     50},
 	{EM2874_R5E_TS2_PKT_SIZE,      0x05, 0xff,     50},
 	{-1,                             -1,   -1,     -1},
-- 
cgit v1.2.3


From a8651194f9f61406cb8926feeeb7829258295b2a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 30 Jul 2018 09:38:42 +0200
Subject: PCI: Call dma_debug_add_bus() for pci_bus_type from PCI core

There is nothing arch-specific about PCI or dma-debug, so call
dma_debug_add_bus() from the PCI core just after registering the bus type.

Most of dma-debug is already generic; this just adds reporting of pending
dma-allocations on driver unload for arches other than powerpc, sh, and
x86.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
---
 arch/powerpc/kernel/dma.c | 3 ---
 arch/sh/drivers/pci/pci.c | 2 --
 arch/x86/kernel/pci-dma.c | 3 ---
 drivers/pci/pci-driver.c  | 2 +-
 4 files changed, 1 insertion(+), 9 deletions(-)

diff --git a/arch/powerpc/kernel/dma.c b/arch/powerpc/kernel/dma.c
index 155170d70324..dbfc7056d7df 100644
--- a/arch/powerpc/kernel/dma.c
+++ b/arch/powerpc/kernel/dma.c
@@ -357,9 +357,6 @@ EXPORT_SYMBOL_GPL(dma_get_required_mask);
 
 static int __init dma_init(void)
 {
-#ifdef CONFIG_PCI
-	dma_debug_add_bus(&pci_bus_type);
-#endif
 #ifdef CONFIG_IBMVIO
 	dma_debug_add_bus(&vio_bus_type);
 #endif
diff --git a/arch/sh/drivers/pci/pci.c b/arch/sh/drivers/pci/pci.c
index e5b7437ab4af..8256626bc53c 100644
--- a/arch/sh/drivers/pci/pci.c
+++ b/arch/sh/drivers/pci/pci.c
@@ -160,8 +160,6 @@ static int __init pcibios_init(void)
 	for (hose = hose_head; hose; hose = hose->next)
 		pcibios_scanbus(hose);
 
-	dma_debug_add_bus(&pci_bus_type);
-
 	pci_initialized = 1;
 
 	return 0;
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index ab5d9dd668d2..43f58632f123 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -155,9 +155,6 @@ static int __init pci_iommu_init(void)
 {
 	struct iommu_table_entry *p;
 
-#ifdef CONFIG_PCI
-	dma_debug_add_bus(&pci_bus_type);
-#endif
 	x86_init.iommu.iommu_init();
 
 	for (p = __iommu_table; p < __iommu_table_end; p++) {
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index c125d53033c6..7a02f94fd231 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -1667,7 +1667,7 @@ static int __init pci_driver_init(void)
 	if (ret)
 		return ret;
 #endif
-
+	dma_debug_add_bus(&pci_bus_type);
 	return 0;
 }
 postcore_initcall(pci_driver_init);
-- 
cgit v1.2.3


From 7d735b9ae82d073e23ff7d2648e0aa8056049d16 Mon Sep 17 00:00:00 2001
From: Dominik Dingel <dingel@linux.vnet.ibm.com>
Date: Fri, 13 Jul 2018 11:28:29 +0100
Subject: s390/mm: hugetlb pages within a gmap can not be freed

Guests backed by huge pages could theoretically free unused pages via
the diagnose 10 instruction. We currently don't allow that, so we
don't have to refault it once it's needed again.

Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Reviewed-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
---
 arch/s390/mm/gmap.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index a6738c0c4499..736ed32a83c5 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -706,6 +706,12 @@ void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to)
 		vmaddr |= gaddr & ~PMD_MASK;
 		/* Find vma in the parent mm */
 		vma = find_vma(gmap->mm, vmaddr);
+		/*
+		 * We do not discard pages that are backed by
+		 * hugetlbfs, so we don't have to refault them.
+		 */
+		if (vma && is_vm_hugetlb_page(vma))
+			continue;
 		size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK));
 		zap_page_range(vma, vmaddr, size);
 	}
-- 
cgit v1.2.3


From a9e00d8349c98e0973c8b0d671d69e838f7b5bcc Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:37 +0100
Subject: s390/mm: Add huge page gmap linking support

Let's allow huge pmd linking when enabled through the
KVM_CAP_S390_HPAGE_1M capability. Also we can now restrict gmap
invalidation and notification to the cases where the capability has
been activated and save some cycles when that's not the case.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 arch/s390/include/asm/mmu.h         | 2 ++
 arch/s390/include/asm/mmu_context.h | 1 +
 arch/s390/mm/gmap.c                 | 9 ++++++---
 arch/s390/mm/pgtable.c              | 8 ++++----
 4 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index f5ff9dbad8ac..f31a15044c24 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -24,6 +24,8 @@ typedef struct {
 	unsigned int uses_skeys:1;
 	/* The mmu context uses CMM. */
 	unsigned int uses_cmm:1;
+	/* The gmaps associated with this context are allowed to use huge pages. */
+	unsigned int allow_gmap_hpage_1m:1;
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index d16bc79c30bb..0717ee76885d 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -32,6 +32,7 @@ static inline int init_new_context(struct task_struct *tsk,
 	mm->context.has_pgste = 0;
 	mm->context.uses_skeys = 0;
 	mm->context.uses_cmm = 0;
+	mm->context.allow_gmap_hpage_1m = 0;
 #endif
 	switch (mm->context.asce_limit) {
 	case _REGION2_SIZE:
diff --git a/arch/s390/mm/gmap.c b/arch/s390/mm/gmap.c
index 736ed32a83c5..bb44990c8212 100644
--- a/arch/s390/mm/gmap.c
+++ b/arch/s390/mm/gmap.c
@@ -2,8 +2,10 @@
 /*
  *  KVM guest address space mapping code
  *
- *    Copyright IBM Corp. 2007, 2016
+ *    Copyright IBM Corp. 2007, 2016, 2018
  *    Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com>
+ *		 David Hildenbrand <david@redhat.com>
+ *		 Janosch Frank <frankja@linux.vnet.ibm.com>
  */
 
 #include <linux/kernel.h>
@@ -588,8 +590,8 @@ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr)
 		return -EFAULT;
 	pmd = pmd_offset(pud, vmaddr);
 	VM_BUG_ON(pmd_none(*pmd));
-	/* large pmds cannot yet be handled */
-	if (pmd_large(*pmd))
+	/* Are we allowed to use huge pages? */
+	if (pmd_large(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m)
 		return -EFAULT;
 	/* Link gmap segment table entry location to page table. */
 	rc = radix_tree_preload(GFP_KERNEL);
@@ -1632,6 +1634,7 @@ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce,
 	unsigned long limit;
 	int rc;
 
+	BUG_ON(parent->mm->context.allow_gmap_hpage_1m);
 	BUG_ON(gmap_is_shadow(parent));
 	spin_lock(&parent->shadow_lock);
 	sg = gmap_find_shadow(parent, asce, edat_level);
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index 37d68706f5aa..f2cc7da473e4 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -347,7 +347,7 @@ static inline void pmdp_idte_local(struct mm_struct *mm,
 			    mm->context.asce, IDTE_LOCAL);
 	else
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_LOCAL);
-	if (mm_has_pgste(mm))
+	if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 		gmap_pmdp_idte_local(mm, addr);
 }
 
@@ -357,15 +357,15 @@ static inline void pmdp_idte_global(struct mm_struct *mm,
 	if (MACHINE_HAS_TLB_GUEST) {
 		__pmdp_idte(addr, pmdp, IDTE_NODAT | IDTE_GUEST_ASCE,
 			    mm->context.asce, IDTE_GLOBAL);
-		if (mm_has_pgste(mm))
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_idte_global(mm, addr);
 	} else if (MACHINE_HAS_IDTE) {
 		__pmdp_idte(addr, pmdp, 0, 0, IDTE_GLOBAL);
-		if (mm_has_pgste(mm))
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_idte_global(mm, addr);
 	} else {
 		__pmdp_csp(pmdp);
-		if (mm_has_pgste(mm))
+		if (mm_has_pgste(mm) && mm->context.allow_gmap_hpage_1m)
 			gmap_pmdp_csp(mm, addr);
 	}
 }
-- 
cgit v1.2.3


From a449938297e55e7e8958f8b48583f7d342da1930 Mon Sep 17 00:00:00 2001
From: Janosch Frank <frankja@linux.ibm.com>
Date: Fri, 13 Jul 2018 11:28:31 +0100
Subject: KVM: s390: Add huge page enablement control

General KVM huge page support on s390 has to be enabled via the
kvm.hpage module parameter. Either nested or hpage can be enabled, as
we currently do not support vSIE for huge backed guests. Once the vSIE
support is added we will either drop the parameter or enable it as
default.

For a guest the feature has to be enabled through the new
KVM_CAP_S390_HPAGE_1M capability and the hpage module
parameter. Enabling it means that cmm can't be enabled for the vm and
disables pfmf and storage key interpretation.

This is due to the fact that in some cases, in upcoming patches, we
have to split huge pages in the guest mapping to be able to set more
granular memory protection on 4k pages. These split pages have fake
page tables that are not visible to the Linux memory management which
subsequently will not manage its PGSTEs, while the SIE will. Disabling
these features lets us manage PGSTE data in a consistent matter and
solve that problem.

Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
---
 Documentation/virtual/kvm/api.txt | 16 +++++++++++++++
 arch/s390/kvm/kvm-s390.c          | 42 +++++++++++++++++++++++++++++++++++++--
 include/uapi/linux/kvm.h          |  1 +
 3 files changed, 57 insertions(+), 2 deletions(-)

diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt
index d10944e619d3..cb8db4f9d097 100644
--- a/Documentation/virtual/kvm/api.txt
+++ b/Documentation/virtual/kvm/api.txt
@@ -4391,6 +4391,22 @@ all such vmexits.
 
 Do not enable KVM_FEATURE_PV_UNHALT if you disable HLT exits.
 
+7.14 KVM_CAP_S390_HPAGE_1M
+
+Architectures: s390
+Parameters: none
+Returns: 0 on success, -EINVAL if hpage module parameter was not set
+	 or cmma is enabled
+
+With this capability the KVM support for memory backing with 1m pages
+through hugetlbfs can be enabled for a VM. After the capability is
+enabled, cmma can't be enabled anymore and pfmfi and the storage key
+interpretation are disabled. If cmma has already been enabled or the
+hpage module parameter is not set to 1, -EINVAL is returned.
+
+While it is generally possible to create a huge page backed VM without
+this capability, the VM will not be able to run.
+
 8. Other capabilities.
 ----------------------
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 662f4d8046db..f9d90337e64a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -172,6 +172,10 @@ static int nested;
 module_param(nested, int, S_IRUGO);
 MODULE_PARM_DESC(nested, "Nested virtualization support");
 
+/* allow 1m huge page guest backing, if !nested */
+static int hpage;
+module_param(hpage, int, 0444);
+MODULE_PARM_DESC(hpage, "1m huge page backing support");
 
 /*
  * For now we handle at most 16 double words as this is what the s390 base
@@ -475,6 +479,11 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_AIS_MIGRATION:
 		r = 1;
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		r = 0;
+		if (hpage)
+			r = 1;
+		break;
 	case KVM_CAP_S390_MEM_OP:
 		r = MEM_OP_MAX_SIZE;
 		break;
@@ -678,6 +687,27 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
 		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s",
 			 r ? "(not available)" : "(success)");
 		break;
+	case KVM_CAP_S390_HPAGE_1M:
+		mutex_lock(&kvm->lock);
+		if (kvm->created_vcpus)
+			r = -EBUSY;
+		else if (!hpage || kvm->arch.use_cmma)
+			r = -EINVAL;
+		else {
+			r = 0;
+			kvm->mm->context.allow_gmap_hpage_1m = 1;
+			/*
+			 * We might have to create fake 4k page
+			 * tables. To avoid that the hardware works on
+			 * stale PGSTEs, we emulate these instructions.
+			 */
+			kvm->arch.use_skf = 0;
+			kvm->arch.use_pfmfi = 0;
+		}
+		mutex_unlock(&kvm->lock);
+		VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s",
+			 r ? "(not available)" : "(success)");
+		break;
 	case KVM_CAP_S390_USER_STSI:
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
 		kvm->arch.user_stsi = 1;
@@ -725,10 +755,13 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		if (!sclp.has_cmma)
 			break;
 
-		ret = -EBUSY;
 		VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
 		mutex_lock(&kvm->lock);
-		if (!kvm->created_vcpus) {
+		if (kvm->created_vcpus)
+			ret = -EBUSY;
+		else if (kvm->mm->context.allow_gmap_hpage_1m)
+			ret = -EINVAL;
+		else {
 			kvm->arch.use_cmma = 1;
 			/* Not compatible with cmma. */
 			kvm->arch.use_pfmfi = 0;
@@ -4102,6 +4135,11 @@ static int __init kvm_s390_init(void)
 		return -ENODEV;
 	}
 
+	if (nested && hpage) {
+		pr_info("nested (vSIE) and hpage (huge page backing) can currently not be activated concurrently");
+		return -EINVAL;
+	}
+
 	for (i = 0; i < 16; i++)
 		kvm_s390_fac_base[i] |=
 			S390_lowcore.stfle_fac_list[i] & nonhyp_mask(i);
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index b6270a3b38e9..b955b986b341 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -949,6 +949,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_GET_MSR_FEATURES 153
 #define KVM_CAP_HYPERV_EVENTFD 154
 #define KVM_CAP_HYPERV_TLBFLUSH 155
+#define KVM_CAP_S390_HPAGE_1M 156
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
-- 
cgit v1.2.3


From 8456b99c16d193c4c3b7df305cf431e027f0189c Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 3 Jun 2018 16:40:55 +0200
Subject: udl-kms: change down_interruptible to down

If we leave urbs around, it causes not only leak, but also memory
corruption. This patch fixes the function udl_free_urb_list, so that it
always waits for all urbs that are in progress.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/udl/udl_main.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index d518de8f496b..1239decd46ff 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -170,18 +170,13 @@ static void udl_free_urb_list(struct drm_device *dev)
 	struct list_head *node;
 	struct urb_node *unode;
 	struct urb *urb;
-	int ret;
 	unsigned long flags;
 
 	DRM_DEBUG("Waiting for completes and freeing all render urbs\n");
 
 	/* keep waiting and freeing, until we've got 'em all */
 	while (count--) {
-
-		/* Getting interrupted means a leak, but ok at shutdown*/
-		ret = down_interruptible(&udl->urbs.limit_sem);
-		if (ret)
-			break;
+		down(&udl->urbs.limit_sem);
 
 		spin_lock_irqsave(&udl->urbs.lock, flags);
 
-- 
cgit v1.2.3


From 542bb9788a1f485eb1a2229178f665d8ea166156 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 3 Jun 2018 16:40:56 +0200
Subject: udl-kms: handle allocation failure

Allocations larger than PAGE_ALLOC_COSTLY_ORDER are unreliable and they
may fail anytime. This patch fixes the udl kms driver so that when a large
alloactions fails, it tries to do multiple smaller allocations.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/udl/udl_main.c | 28 ++++++++++++++++++----------
 1 file changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 1239decd46ff..7e9ad926926a 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -200,17 +200,22 @@ static void udl_free_urb_list(struct drm_device *dev)
 static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 {
 	struct udl_device *udl = dev->dev_private;
-	int i = 0;
 	struct urb *urb;
 	struct urb_node *unode;
 	char *buf;
+	size_t wanted_size = count * size;
 
 	spin_lock_init(&udl->urbs.lock);
 
+retry:
 	udl->urbs.size = size;
 	INIT_LIST_HEAD(&udl->urbs.list);
 
-	while (i < count) {
+	sema_init(&udl->urbs.limit_sem, 0);
+	udl->urbs.count = 0;
+	udl->urbs.available = 0;
+
+	while (udl->urbs.count * size < wanted_size) {
 		unode = kzalloc(sizeof(struct urb_node), GFP_KERNEL);
 		if (!unode)
 			break;
@@ -226,11 +231,16 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 		}
 		unode->urb = urb;
 
-		buf = usb_alloc_coherent(udl->udev, MAX_TRANSFER, GFP_KERNEL,
+		buf = usb_alloc_coherent(udl->udev, size, GFP_KERNEL,
 					 &urb->transfer_dma);
 		if (!buf) {
 			kfree(unode);
 			usb_free_urb(urb);
+			if (size > PAGE_SIZE) {
+				size /= 2;
+				udl_free_urb_list(dev);
+				goto retry;
+			}
 			break;
 		}
 
@@ -241,16 +251,14 @@ static int udl_alloc_urb_list(struct drm_device *dev, int count, size_t size)
 
 		list_add_tail(&unode->entry, &udl->urbs.list);
 
-		i++;
+		up(&udl->urbs.limit_sem);
+		udl->urbs.count++;
+		udl->urbs.available++;
 	}
 
-	sema_init(&udl->urbs.limit_sem, i);
-	udl->urbs.count = i;
-	udl->urbs.available = i;
-
-	DRM_DEBUG("allocated %d %d byte urbs\n", i, (int) size);
+	DRM_DEBUG("allocated %d %d byte urbs\n", udl->urbs.count, (int) size);
 
-	return i;
+	return udl->urbs.count;
 }
 
 struct urb *udl_get_urb(struct drm_device *dev)
-- 
cgit v1.2.3


From 09a00abe3a9941c2715ca83eb88172cd2f54d8fd Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 3 Jun 2018 16:40:57 +0200
Subject: udl-kms: fix crash due to uninitialized memory

We must use kzalloc when allocating the fb_deferred_io structure.
Otherwise, the field first_io is undefined and it causes a crash.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/udl/udl_fb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index d5583190f3e4..c3f5867dac91 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -221,7 +221,7 @@ static int udl_fb_open(struct fb_info *info, int user)
 
 		struct fb_deferred_io *fbdefio;
 
-		fbdefio = kmalloc(sizeof(struct fb_deferred_io), GFP_KERNEL);
+		fbdefio = kzalloc(sizeof(struct fb_deferred_io), GFP_KERNEL);
 
 		if (fbdefio) {
 			fbdefio->delay = DL_DEFIO_WRITE_DELAY;
-- 
cgit v1.2.3


From 91ba11fb7d7ca0a3bbe8a512e65e666e2ec1e889 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 3 Jun 2018 16:41:00 +0200
Subject: udl-kms: avoid division

Division is slow, so it shouldn't be done by the pixel generating code.
The driver supports only 2 or 4 bytes per pixel, so we can replace
division with a shift.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/udl/udl_drv.h      |  2 +-
 drivers/gpu/drm/udl/udl_fb.c       | 15 +++++++++------
 drivers/gpu/drm/udl/udl_transfer.c | 39 +++++++++++++++++++-------------------
 3 files changed, 30 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_drv.h b/drivers/gpu/drm/udl/udl_drv.h
index 55c0cc309198..7588a9eb0ee0 100644
--- a/drivers/gpu/drm/udl/udl_drv.h
+++ b/drivers/gpu/drm/udl/udl_drv.h
@@ -112,7 +112,7 @@ udl_fb_user_fb_create(struct drm_device *dev,
 		      struct drm_file *file,
 		      const struct drm_mode_fb_cmd2 *mode_cmd);
 
-int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
+int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
 		     u32 byte_offset, u32 device_byte_offset, u32 byte_width,
 		     int *ident_ptr, int *sent_ptr);
diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index c3f5867dac91..8746eeeec44d 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -90,7 +90,10 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 	int bytes_identical = 0;
 	struct urb *urb;
 	int aligned_x;
-	int bpp = fb->base.format->cpp[0];
+	int log_bpp;
+
+	BUG_ON(!is_power_of_2(fb->base.format->cpp[0]));
+	log_bpp = __ffs(fb->base.format->cpp[0]);
 
 	if (!fb->active_16)
 		return 0;
@@ -125,12 +128,12 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 
 	for (i = y; i < y + height ; i++) {
 		const int line_offset = fb->base.pitches[0] * i;
-		const int byte_offset = line_offset + (x * bpp);
-		const int dev_byte_offset = (fb->base.width * bpp * i) + (x * bpp);
-		if (udl_render_hline(dev, bpp, &urb,
+		const int byte_offset = line_offset + (x << log_bpp);
+		const int dev_byte_offset = (fb->base.width * i + x) << log_bpp;
+		if (udl_render_hline(dev, log_bpp, &urb,
 				     (char *) fb->obj->vmapping,
 				     &cmd, byte_offset, dev_byte_offset,
-				     width * bpp,
+				     width << log_bpp,
 				     &bytes_identical, &bytes_sent))
 			goto error;
 	}
@@ -149,7 +152,7 @@ int udl_handle_damage(struct udl_framebuffer *fb, int x, int y,
 error:
 	atomic_add(bytes_sent, &udl->bytes_sent);
 	atomic_add(bytes_identical, &udl->bytes_identical);
-	atomic_add(width*height*bpp, &udl->bytes_rendered);
+	atomic_add((width * height) << log_bpp, &udl->bytes_rendered);
 	end_cycles = get_cycles();
 	atomic_add(((unsigned int) ((end_cycles - start_cycles)
 		    >> 10)), /* Kcycles */
diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index b992644c17e6..f3331d33547a 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -83,12 +83,12 @@ static inline u16 pixel32_to_be16(const uint32_t pixel)
 		((pixel >> 8) & 0xf800));
 }
 
-static inline u16 get_pixel_val16(const uint8_t *pixel, int bpp)
+static inline u16 get_pixel_val16(const uint8_t *pixel, int log_bpp)
 {
-	u16 pixel_val16 = 0;
-	if (bpp == 2)
+	u16 pixel_val16;
+	if (log_bpp == 1)
 		pixel_val16 = *(const uint16_t *)pixel;
-	else if (bpp == 4)
+	else
 		pixel_val16 = pixel32_to_be16(*(const uint32_t *)pixel);
 	return pixel_val16;
 }
@@ -125,8 +125,9 @@ static void udl_compress_hline16(
 	const u8 *const pixel_end,
 	uint32_t *device_address_ptr,
 	uint8_t **command_buffer_ptr,
-	const uint8_t *const cmd_buffer_end, int bpp)
+	const uint8_t *const cmd_buffer_end, int log_bpp)
 {
+	const int bpp = 1 << log_bpp;
 	const u8 *pixel = *pixel_start_ptr;
 	uint32_t dev_addr  = *device_address_ptr;
 	uint8_t *cmd = *command_buffer_ptr;
@@ -153,12 +154,12 @@ static void udl_compress_hline16(
 		raw_pixels_count_byte = cmd++; /*  we'll know this later */
 		raw_pixel_start = pixel;
 
-		cmd_pixel_end = pixel + min3(MAX_CMD_PIXELS + 1UL,
-					(unsigned long)(pixel_end - pixel) / bpp,
-					(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) * bpp;
+		cmd_pixel_end = pixel + (min3(MAX_CMD_PIXELS + 1UL,
+					(unsigned long)(pixel_end - pixel) >> log_bpp,
+					(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) << log_bpp);
 
 		prefetch_range((void *) pixel, cmd_pixel_end - pixel);
-		pixel_val16 = get_pixel_val16(pixel, bpp);
+		pixel_val16 = get_pixel_val16(pixel, log_bpp);
 
 		while (pixel < cmd_pixel_end) {
 			const u8 *const start = pixel;
@@ -170,7 +171,7 @@ static void udl_compress_hline16(
 			pixel += bpp;
 
 			while (pixel < cmd_pixel_end) {
-				pixel_val16 = get_pixel_val16(pixel, bpp);
+				pixel_val16 = get_pixel_val16(pixel, log_bpp);
 				if (pixel_val16 != repeating_pixel_val16)
 					break;
 				pixel += bpp;
@@ -179,10 +180,10 @@ static void udl_compress_hline16(
 			if (unlikely(pixel > start + bpp)) {
 				/* go back and fill in raw pixel count */
 				*raw_pixels_count_byte = (((start -
-						raw_pixel_start) / bpp) + 1) & 0xFF;
+						raw_pixel_start) >> log_bpp) + 1) & 0xFF;
 
 				/* immediately after raw data is repeat byte */
-				*cmd++ = (((pixel - start) / bpp) - 1) & 0xFF;
+				*cmd++ = (((pixel - start) >> log_bpp) - 1) & 0xFF;
 
 				/* Then start another raw pixel span */
 				raw_pixel_start = pixel;
@@ -192,14 +193,14 @@ static void udl_compress_hline16(
 
 		if (pixel > raw_pixel_start) {
 			/* finalize last RAW span */
-			*raw_pixels_count_byte = ((pixel-raw_pixel_start) / bpp) & 0xFF;
+			*raw_pixels_count_byte = ((pixel - raw_pixel_start) >> log_bpp) & 0xFF;
 		} else {
 			/* undo unused byte */
 			cmd--;
 		}
 
-		*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) / bpp) & 0xFF;
-		dev_addr += ((pixel - cmd_pixel_start) / bpp) * 2;
+		*cmd_pixels_count_byte = ((pixel - cmd_pixel_start) >> log_bpp) & 0xFF;
+		dev_addr += ((pixel - cmd_pixel_start) >> log_bpp) * 2;
 	}
 
 	if (cmd_buffer_end <= MIN_RLX_CMD_BYTES + cmd) {
@@ -222,19 +223,19 @@ static void udl_compress_hline16(
  * (that we can only write to, slowly, and can never read), and (optionally)
  * our shadow copy that tracks what's been sent to that hardware buffer.
  */
-int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
+int udl_render_hline(struct drm_device *dev, int log_bpp, struct urb **urb_ptr,
 		     const char *front, char **urb_buf_ptr,
 		     u32 byte_offset, u32 device_byte_offset,
 		     u32 byte_width,
 		     int *ident_ptr, int *sent_ptr)
 {
 	const u8 *line_start, *line_end, *next_pixel;
-	u32 base16 = 0 + (device_byte_offset / bpp) * 2;
+	u32 base16 = 0 + (device_byte_offset >> log_bpp) * 2;
 	struct urb *urb = *urb_ptr;
 	u8 *cmd = *urb_buf_ptr;
 	u8 *cmd_end = (u8 *) urb->transfer_buffer + urb->transfer_buffer_length;
 
-	BUG_ON(!(bpp == 2 || bpp == 4));
+	BUG_ON(!(log_bpp == 1 || log_bpp == 2));
 
 	line_start = (u8 *) (front + byte_offset);
 	next_pixel = line_start;
@@ -244,7 +245,7 @@ int udl_render_hline(struct drm_device *dev, int bpp, struct urb **urb_ptr,
 
 		udl_compress_hline16(&next_pixel,
 			     line_end, &base16,
-			     (u8 **) &cmd, (u8 *) cmd_end, bpp);
+			     (u8 **) &cmd, (u8 *) cmd_end, log_bpp);
 
 		if (cmd >= cmd_end) {
 			int len = cmd - (u8 *) urb->transfer_buffer;
-- 
cgit v1.2.3


From 58cba7c222e8c87bb6b61fcba21d1536145221b0 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 3 Jun 2018 16:41:01 +0200
Subject: udl-kms: avoid prefetch

Modern processors can detect linear memory accesses and prefetch data
automatically, so there's no need to use prefetch.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/udl/udl_transfer.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_transfer.c b/drivers/gpu/drm/udl/udl_transfer.c
index f3331d33547a..ce87661e544f 100644
--- a/drivers/gpu/drm/udl/udl_transfer.c
+++ b/drivers/gpu/drm/udl/udl_transfer.c
@@ -13,7 +13,6 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/fb.h>
-#include <linux/prefetch.h>
 #include <asm/unaligned.h>
 
 #include <drm/drmP.h>
@@ -51,9 +50,6 @@ static int udl_trim_hline(const u8 *bback, const u8 **bfront, int *width_bytes)
 	int start = width;
 	int end = width;
 
-	prefetch((void *) front);
-	prefetch((void *) back);
-
 	for (j = 0; j < width; j++) {
 		if (back[j] != front[j]) {
 			start = j;
@@ -140,8 +136,6 @@ static void udl_compress_hline16(
 		const u8 *cmd_pixel_start, *cmd_pixel_end = NULL;
 		uint16_t pixel_val16;
 
-		prefetchw((void *) cmd); /* pull in one cache line at least */
-
 		*cmd++ = 0xaf;
 		*cmd++ = 0x6b;
 		*cmd++ = (uint8_t) ((dev_addr >> 16) & 0xFF);
@@ -158,7 +152,6 @@ static void udl_compress_hline16(
 					(unsigned long)(pixel_end - pixel) >> log_bpp,
 					(unsigned long)(cmd_buffer_end - 1 - cmd) / 2) << log_bpp);
 
-		prefetch_range((void *) pixel, cmd_pixel_end - pixel);
 		pixel_val16 = get_pixel_val16(pixel, log_bpp);
 
 		while (pixel < cmd_pixel_end) {
-- 
cgit v1.2.3


From c2f53119b410047e5d97de2a5ec74157d2e58986 Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 3 Jun 2018 16:41:02 +0200
Subject: udl-kms: use spin_lock_irq instead of spin_lock_irqsave

spin_lock_irqsave and spin_unlock_irqrestore is inteded to be called from
a context where it is unknown if interrupts are enabled or disabled (such
as interrupt handlers). From a process context, we should call
spin_lock_irq and spin_unlock_irq, that avoids the costly pushf and popf
instructions.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/udl/udl_main.c    | 10 ++++------
 drivers/gpu/drm/udl/udl_modeset.c |  5 ++---
 2 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_main.c b/drivers/gpu/drm/udl/udl_main.c
index 7e9ad926926a..f455f095a146 100644
--- a/drivers/gpu/drm/udl/udl_main.c
+++ b/drivers/gpu/drm/udl/udl_main.c
@@ -170,7 +170,6 @@ static void udl_free_urb_list(struct drm_device *dev)
 	struct list_head *node;
 	struct urb_node *unode;
 	struct urb *urb;
-	unsigned long flags;
 
 	DRM_DEBUG("Waiting for completes and freeing all render urbs\n");
 
@@ -178,12 +177,12 @@ static void udl_free_urb_list(struct drm_device *dev)
 	while (count--) {
 		down(&udl->urbs.limit_sem);
 
-		spin_lock_irqsave(&udl->urbs.lock, flags);
+		spin_lock_irq(&udl->urbs.lock);
 
 		node = udl->urbs.list.next; /* have reserved one with sem */
 		list_del_init(node);
 
-		spin_unlock_irqrestore(&udl->urbs.lock, flags);
+		spin_unlock_irq(&udl->urbs.lock);
 
 		unode = list_entry(node, struct urb_node, entry);
 		urb = unode->urb;
@@ -268,7 +267,6 @@ struct urb *udl_get_urb(struct drm_device *dev)
 	struct list_head *entry;
 	struct urb_node *unode;
 	struct urb *urb = NULL;
-	unsigned long flags;
 
 	/* Wait for an in-flight buffer to complete and get re-queued */
 	ret = down_timeout(&udl->urbs.limit_sem, GET_URB_TIMEOUT);
@@ -279,14 +277,14 @@ struct urb *udl_get_urb(struct drm_device *dev)
 		goto error;
 	}
 
-	spin_lock_irqsave(&udl->urbs.lock, flags);
+	spin_lock_irq(&udl->urbs.lock);
 
 	BUG_ON(list_empty(&udl->urbs.list)); /* reserved one with limit_sem */
 	entry = udl->urbs.list.next;
 	list_del_init(entry);
 	udl->urbs.available--;
 
-	spin_unlock_irqrestore(&udl->urbs.lock, flags);
+	spin_unlock_irq(&udl->urbs.lock);
 
 	unode = list_entry(entry, struct urb_node, entry);
 	urb = unode->urb;
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index 5bcae7649795..98c6a58bcb07 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -366,7 +366,6 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc,
 {
 	struct udl_framebuffer *ufb = to_udl_fb(fb);
 	struct drm_device *dev = crtc->dev;
-	unsigned long flags;
 
 	struct drm_framebuffer *old_fb = crtc->primary->fb;
 	if (old_fb) {
@@ -377,10 +376,10 @@ static int udl_crtc_page_flip(struct drm_crtc *crtc,
 
 	udl_handle_damage(ufb, 0, 0, fb->width, fb->height);
 
-	spin_lock_irqsave(&dev->event_lock, flags);
+	spin_lock_irq(&dev->event_lock);
 	if (event)
 		drm_crtc_send_vblank_event(crtc, event);
-	spin_unlock_irqrestore(&dev->event_lock, flags);
+	spin_unlock_irq(&dev->event_lock);
 	crtc->primary->fb = fb;
 
 	return 0;
-- 
cgit v1.2.3


From 90991209837ab619555a46a97a88dead7a960d2d Mon Sep 17 00:00:00 2001
From: Mikulas Patocka <mpatocka@redhat.com>
Date: Sun, 3 Jun 2018 16:41:03 +0200
Subject: udl-kms: dont spam the syslog with debug messages

The udl kms driver writes messages to the syslog whenever some application
opens or closes /dev/fb0 and whenever the user switches between the
Xserver and the console.

This patch changes the priority of these messages to debug.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
 drivers/gpu/drm/udl/udl_fb.c      | 6 +++---
 drivers/gpu/drm/udl/udl_modeset.c | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/udl/udl_fb.c b/drivers/gpu/drm/udl/udl_fb.c
index 8746eeeec44d..dbb62f6eb48a 100644
--- a/drivers/gpu/drm/udl/udl_fb.c
+++ b/drivers/gpu/drm/udl/udl_fb.c
@@ -178,7 +178,7 @@ static int udl_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
 
 	pos = (unsigned long)info->fix.smem_start + offset;
 
-	pr_notice("mmap() framebuffer addr:%lu size:%lu\n",
+	pr_debug("mmap() framebuffer addr:%lu size:%lu\n",
 		  pos, size);
 
 	/* We don't want the framebuffer to be mapped encrypted */
@@ -236,7 +236,7 @@ static int udl_fb_open(struct fb_info *info, int user)
 	}
 #endif
 
-	pr_notice("open /dev/fb%d user=%d fb_info=%p count=%d\n",
+	pr_debug("open /dev/fb%d user=%d fb_info=%p count=%d\n",
 		  info->node, user, info, ufbdev->fb_count);
 
 	return 0;
@@ -261,7 +261,7 @@ static int udl_fb_release(struct fb_info *info, int user)
 	}
 #endif
 
-	pr_warn("released /dev/fb%d user=%d count=%d\n",
+	pr_debug("released /dev/fb%d user=%d count=%d\n",
 		info->node, user, ufbdev->fb_count);
 
 	return 0;
diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
index 98c6a58bcb07..7e37765cf5ac 100644
--- a/drivers/gpu/drm/udl/udl_modeset.c
+++ b/drivers/gpu/drm/udl/udl_modeset.c
@@ -243,7 +243,7 @@ static int udl_crtc_write_mode_to_hw(struct drm_crtc *crtc)
 
 	memcpy(buf, udl->mode_buf, udl->mode_buf_len);
 	retval = udl_submit_urb(dev, urb, udl->mode_buf_len);
-	DRM_INFO("write mode info %d\n", udl->mode_buf_len);
+	DRM_DEBUG("write mode info %d\n", udl->mode_buf_len);
 	return retval;
 }
 
-- 
cgit v1.2.3


From fdf82a7856b32d905c39afc85e34364491e46346 Mon Sep 17 00:00:00 2001
From: Jiri Kosina <jkosina@suse.cz>
Date: Thu, 26 Jul 2018 13:14:55 +0200
Subject: x86/speculation: Protect against userspace-userspace spectreRSB

The article "Spectre Returns! Speculation Attacks using the Return Stack
Buffer" [1] describes two new (sub-)variants of spectrev2-like attacks,
making use solely of the RSB contents even on CPUs that don't fallback to
BTB on RSB underflow (Skylake+).

Mitigate userspace-userspace attacks by always unconditionally filling RSB on
context switch when the generic spectrev2 mitigation has been enabled.

[1] https://arxiv.org/pdf/1807.07940.pdf

Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/nycvar.YFH.7.76.1807261308190.997@cbobk.fhfr.pm
---
 arch/x86/kernel/cpu/bugs.c | 38 +++++++-------------------------------
 1 file changed, 7 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 5c0ea39311fe..bc8c43b22460 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -313,23 +313,6 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
 	return cmd;
 }
 
-/* Check for Skylake-like CPUs (for RSB handling) */
-static bool __init is_skylake_era(void)
-{
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6) {
-		switch (boot_cpu_data.x86_model) {
-		case INTEL_FAM6_SKYLAKE_MOBILE:
-		case INTEL_FAM6_SKYLAKE_DESKTOP:
-		case INTEL_FAM6_SKYLAKE_X:
-		case INTEL_FAM6_KABYLAKE_MOBILE:
-		case INTEL_FAM6_KABYLAKE_DESKTOP:
-			return true;
-		}
-	}
-	return false;
-}
-
 static void __init spectre_v2_select_mitigation(void)
 {
 	enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
@@ -390,22 +373,15 @@ retpoline_auto:
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
 	/*
-	 * If neither SMEP nor PTI are available, there is a risk of
-	 * hitting userspace addresses in the RSB after a context switch
-	 * from a shallow call stack to a deeper one. To prevent this fill
-	 * the entire RSB, even when using IBRS.
+	 * If spectre v2 protection has been enabled, unconditionally fill
+	 * RSB during a context switch; this protects against two independent
+	 * issues:
 	 *
-	 * Skylake era CPUs have a separate issue with *underflow* of the
-	 * RSB, when they will predict 'ret' targets from the generic BTB.
-	 * The proper mitigation for this is IBRS. If IBRS is not supported
-	 * or deactivated in favour of retpolines the RSB fill on context
-	 * switch is required.
+	 *	- RSB underflow (and switch to BTB) on Skylake+
+	 *	- SpectreRSB variant of spectre v2 on X86_BUG_SPECTRE_V2 CPUs
 	 */
-	if ((!boot_cpu_has(X86_FEATURE_PTI) &&
-	     !boot_cpu_has(X86_FEATURE_SMEP)) || is_skylake_era()) {
-		setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
-		pr_info("Spectre v2 mitigation: Filling RSB on context switch\n");
-	}
+	setup_force_cpu_cap(X86_FEATURE_RSB_CTXSW);
+	pr_info("Spectre v2 / SpectreRSB mitigation: Filling RSB on context switch\n");
 
 	/* Initialize Indirect Branch Prediction Barrier if supported */
 	if (boot_cpu_has(X86_FEATURE_IBPB)) {
-- 
cgit v1.2.3


From 1ce6a9fc154935d9db771173ecde03fa9b42df4a Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Mon, 30 Jul 2018 10:53:23 +0200
Subject: bpf: fix build error in libbpf with EXTRA_CFLAGS="-Wp,
 -D_FORTIFY_SOURCE=2 -O2"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 531b014e7a2f ("tools: bpf: make use of reallocarray") causes
a compiler error when building the perf tool in the linux-next tree.
Compile file tools/lib/bpf/libbpf.c on a FEDORA 28 installation with
gcc compiler version: gcc (GCC) 8.0.1 20180324 (Red Hat 8.0.1-0.20)
shows this error message:

  [root@p23lp27] # make V=1 EXTRA_CFLAGS="-Wp,-D_FORTIFY_SOURCE=2 -O2"
  [...]
  make -f /home6/tmricht/linux-next/tools/build/Makefile.build
  	dir=./util/scripting-engines obj=libperf
  libbpf.c: In function ‘bpf_object__elf_collect’:
  libbpf.c:811:15: error: ignoring return value of ‘strerror_r’,
  		declared with attribute warn_unused_result [-Werror=unused-result]
       strerror_r(-err, errmsg, sizeof(errmsg));
                 ^
  cc1: all warnings being treated as errors
  mv: cannot stat './.libbpf.o.tmp': No such file or directory
  /home6/tmricht/linux-next/tools/build/Makefile.build:96: recipe for target 'libbpf.o' failed

Replace all occurrences of strerror() by calls to strerror_r(). To
keep the compiler quiet also use the return value from strerror_r()
otherwise a 'variable set but not use' warning which is treated as
error terminates the compile.

Fixes: 531b014e7a2f ("tools: bpf: make use of reallocarray")
Suggested-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Suggested-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 42 +++++++++++++++++++++++++++++-------------
 1 file changed, 29 insertions(+), 13 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 857d3d16968e..79fc7ed6995a 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -467,8 +467,10 @@ static int bpf_object__elf_init(struct bpf_object *obj)
 	} else {
 		obj->efile.fd = open(obj->path, O_RDONLY);
 		if (obj->efile.fd < 0) {
-			pr_warning("failed to open %s: %s\n", obj->path,
-					strerror(errno));
+			char errmsg[STRERR_BUFSIZE];
+			char *cp = strerror_r(errno, errmsg, sizeof(errmsg));
+
+			pr_warning("failed to open %s: %s\n", obj->path, cp);
 			return -errno;
 		}
 
@@ -807,10 +809,11 @@ static int bpf_object__elf_collect(struct bpf_object *obj)
 						      data->d_size, name, idx);
 			if (err) {
 				char errmsg[STRERR_BUFSIZE];
+				char *cp = strerror_r(-err, errmsg,
+						      sizeof(errmsg));
 
-				strerror_r(-err, errmsg, sizeof(errmsg));
 				pr_warning("failed to alloc program %s (%s): %s",
-					   name, obj->path, errmsg);
+					   name, obj->path, cp);
 			}
 		} else if (sh.sh_type == SHT_REL) {
 			void *reloc = obj->efile.reloc;
@@ -1104,6 +1107,7 @@ bpf_object__create_maps(struct bpf_object *obj)
 	for (i = 0; i < obj->nr_maps; i++) {
 		struct bpf_map *map = &obj->maps[i];
 		struct bpf_map_def *def = &map->def;
+		char *cp, errmsg[STRERR_BUFSIZE];
 		int *pfd = &map->fd;
 
 		if (map->fd >= 0) {
@@ -1131,8 +1135,9 @@ bpf_object__create_maps(struct bpf_object *obj)
 
 		*pfd = bpf_create_map_xattr(&create_attr);
 		if (*pfd < 0 && create_attr.btf_key_type_id) {
+			cp = strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n",
-				   map->name, strerror(errno), errno);
+				   map->name, cp, errno);
 			create_attr.btf_fd = 0;
 			create_attr.btf_key_type_id = 0;
 			create_attr.btf_value_type_id = 0;
@@ -1145,9 +1150,9 @@ bpf_object__create_maps(struct bpf_object *obj)
 			size_t j;
 
 			err = *pfd;
+			cp = strerror_r(errno, errmsg, sizeof(errmsg));
 			pr_warning("failed to create map (name: '%s'): %s\n",
-				   map->name,
-				   strerror(errno));
+				   map->name, cp);
 			for (j = 0; j < i; j++)
 				zclose(obj->maps[j].fd);
 			return err;
@@ -1299,6 +1304,7 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	     char *license, u32 kern_version, int *pfd, int prog_ifindex)
 {
 	struct bpf_load_program_attr load_attr;
+	char *cp, errmsg[STRERR_BUFSIZE];
 	char *log_buf;
 	int ret;
 
@@ -1328,7 +1334,8 @@ load_program(enum bpf_prog_type type, enum bpf_attach_type expected_attach_type,
 	}
 
 	ret = -LIBBPF_ERRNO__LOAD;
-	pr_warning("load bpf program failed: %s\n", strerror(errno));
+	cp = strerror_r(errno, errmsg, sizeof(errmsg));
+	pr_warning("load bpf program failed: %s\n", cp);
 
 	if (log_buf && log_buf[0] != '\0') {
 		ret = -LIBBPF_ERRNO__VERIFY;
@@ -1627,6 +1634,7 @@ out:
 
 static int check_path(const char *path)
 {
+	char *cp, errmsg[STRERR_BUFSIZE];
 	struct statfs st_fs;
 	char *dname, *dir;
 	int err = 0;
@@ -1640,7 +1648,8 @@ static int check_path(const char *path)
 
 	dir = dirname(dname);
 	if (statfs(dir, &st_fs)) {
-		pr_warning("failed to statfs %s: %s\n", dir, strerror(errno));
+		cp = strerror_r(errno, errmsg, sizeof(errmsg));
+		pr_warning("failed to statfs %s: %s\n", dir, cp);
 		err = -errno;
 	}
 	free(dname);
@@ -1656,6 +1665,7 @@ static int check_path(const char *path)
 int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 			      int instance)
 {
+	char *cp, errmsg[STRERR_BUFSIZE];
 	int err;
 
 	err = check_path(path);
@@ -1674,7 +1684,8 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 	}
 
 	if (bpf_obj_pin(prog->instances.fds[instance], path)) {
-		pr_warning("failed to pin program: %s\n", strerror(errno));
+		cp = strerror_r(errno, errmsg, sizeof(errmsg));
+		pr_warning("failed to pin program: %s\n", cp);
 		return -errno;
 	}
 	pr_debug("pinned program '%s'\n", path);
@@ -1684,13 +1695,16 @@ int bpf_program__pin_instance(struct bpf_program *prog, const char *path,
 
 static int make_dir(const char *path)
 {
+	char *cp, errmsg[STRERR_BUFSIZE];
 	int err = 0;
 
 	if (mkdir(path, 0700) && errno != EEXIST)
 		err = -errno;
 
-	if (err)
-		pr_warning("failed to mkdir %s: %s\n", path, strerror(-err));
+	if (err) {
+		cp = strerror_r(-err, errmsg, sizeof(errmsg));
+		pr_warning("failed to mkdir %s: %s\n", path, cp);
+	}
 	return err;
 }
 
@@ -1737,6 +1751,7 @@ int bpf_program__pin(struct bpf_program *prog, const char *path)
 
 int bpf_map__pin(struct bpf_map *map, const char *path)
 {
+	char *cp, errmsg[STRERR_BUFSIZE];
 	int err;
 
 	err = check_path(path);
@@ -1749,7 +1764,8 @@ int bpf_map__pin(struct bpf_map *map, const char *path)
 	}
 
 	if (bpf_obj_pin(map->fd, path)) {
-		pr_warning("failed to pin map: %s\n", strerror(errno));
+		cp = strerror_r(errno, errmsg, sizeof(errmsg));
+		pr_warning("failed to pin map: %s\n", cp);
 		return -errno;
 	}
 
-- 
cgit v1.2.3


From 968dc5a0eaca707f8eb2fbad57d9fbbf3284541e Mon Sep 17 00:00:00 2001
From: "谢致邦 (XIE Zhibang)" <Yeking@Red54.com>
Date: Thu, 1 Jun 2017 18:41:34 +0800
Subject: MIPS: Loongson: Set Loongson32 to MIPS32R1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

LS232 (Loonson 2-issue 32-bit, also called GS232 (Godson 2-issue 32-bit))
is the CPU core (microarchitecture) of Loongson 1A/1B/1C.

According to "LS232 用户手册 (LS232 User Manual)", LS232 implements the
MIPS32 Release 1 instruction set, and part of the MIPS32 Release 2
instruction set.

In the manual, LS232 implements all of the MIPS32R2 instruction set
except the FPU instructions, and LS232 also implements 5 FPU
instructions of the MIPS32R2 instruction set: CEIL.L.fmt, CVT.L.fmt,
FLOOR.L.fmt, TRUNC.L.fmt, and ROUND.L.fmt.

But a bug of the DI instruction has been found during tests, the DI
instruction can not disable interrupts in arch_local_irq_disable() with
CONFIG_PREEMPT_NONE=y and CFLAGS='-mno-branch-likely' in some cases.

[paul.burton@mips.com:
  - Remove the _MIPS_ISA redefinition to match the change made for the
    generic MIPSr1 CPUs by commit 344ebf09949c ("MIPS: Always use
    -march=<arch>, not -<arch> shortcuts").]

Signed-off-by: 谢致邦 (XIE Zhibang) <Yeking@Red54.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/16155/
Cc: linux-mips@linux-mips.org
Cc: ralf@linux-mips.org
---
 arch/mips/Kconfig             | 8 +++++---
 arch/mips/loongson32/Platform | 5 +----
 2 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c95eb5ad0d96..642a56e2a1ea 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -1424,7 +1424,8 @@ config CPU_LOONGSON1B
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1B is a 32-bit SoC, which implements the MIPS32
-	  release 2 instruction set.
+	  Release 1 instruction set and part of the MIPS32 Release 2
+	  instruction set.
 
 config CPU_LOONGSON1C
 	bool "Loongson 1C"
@@ -1433,7 +1434,8 @@ config CPU_LOONGSON1C
 	select LEDS_GPIO_REGISTER
 	help
 	  The Loongson 1C is a 32-bit SoC, which implements the MIPS32
-	  release 2 instruction set.
+	  Release 1 instruction set and part of the MIPS32 Release 2
+	  instruction set.
 
 config CPU_MIPS32_R1
 	bool "MIPS32 Release 1"
@@ -1833,7 +1835,7 @@ config CPU_LOONGSON2
 config CPU_LOONGSON1
 	bool
 	select CPU_MIPS32
-	select CPU_MIPSR2
+	select CPU_MIPSR1
 	select CPU_HAS_PREFETCH
 	select CPU_SUPPORTS_32BIT_KERNEL
 	select CPU_SUPPORTS_HIGHMEM
diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform
index ffe01c6d0037..90ac8f3158d3 100644
--- a/arch/mips/loongson32/Platform
+++ b/arch/mips/loongson32/Platform
@@ -1,7 +1,4 @@
-cflags-$(CONFIG_CPU_LOONGSON1)	+= \
-	$(call cc-option,-march=mips32r2,-mips32r2 -U_MIPS_ISA -D_MIPS_ISA=_MIPS_ISA_MIPS32) \
-	-Wa,-mips32r2 -Wa,--trap
-
+cflags-$(CONFIG_CPU_LOONGSON1)		+= -march=mips32 -Wa,--trap
 platform-$(CONFIG_MACH_LOONGSON32)	+= loongson32/
 cflags-$(CONFIG_MACH_LOONGSON32)	+= -I$(srctree)/arch/mips/include/asm/mach-loongson32
 load-$(CONFIG_LOONGSON1_LS1B)		+= 0xffffffff80100000
-- 
cgit v1.2.3


From 60bc84e227d24fdb1ac2211c574a88ecd7c836a0 Mon Sep 17 00:00:00 2001
From: "谢致邦 (XIE Zhibang)" <Yeking@Red54.com>
Date: Wed, 4 Jan 2017 21:30:58 +0800
Subject: MIPS: Loongson: Merge load addresses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Systems based upon the Loongson 1B & 1C CPUs share the same load
address, as do those based upon Loongson 1A. Unify the definition of
this load address to reduce duplication & avoid the need for an extra
Loongson 1A case in future.

[paul.burton@mips.com: Rewrite commit message.]

Signed-off-by: 谢致邦 (XIE Zhibang) <Yeking@Red54.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/14927/
Cc: linux-mips@linux-mips.org
---
 arch/mips/loongson32/Platform | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/mips/loongson32/Platform b/arch/mips/loongson32/Platform
index 90ac8f3158d3..a0dbb3b2f2de 100644
--- a/arch/mips/loongson32/Platform
+++ b/arch/mips/loongson32/Platform
@@ -1,5 +1,4 @@
 cflags-$(CONFIG_CPU_LOONGSON1)		+= -march=mips32 -Wa,--trap
 platform-$(CONFIG_MACH_LOONGSON32)	+= loongson32/
 cflags-$(CONFIG_MACH_LOONGSON32)	+= -I$(srctree)/arch/mips/include/asm/mach-loongson32
-load-$(CONFIG_LOONGSON1_LS1B)		+= 0xffffffff80100000
-load-$(CONFIG_LOONGSON1_LS1C)		+= 0xffffffff80100000
+load-$(CONFIG_CPU_LOONGSON1)		+= 0xffffffff80100000
-- 
cgit v1.2.3


From 7bd1d615a57f3356f41b0079a3fb9ee77ae00a82 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Fri, 13 Jul 2018 03:25:37 +0200
Subject: scsi: mptctl: change strncpy+truncation to strlcpy

Generated by scripts/coccinelle/misc/strncpy_truncation.cocci

Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/message/fusion/mptctl.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/message/fusion/mptctl.c b/drivers/message/fusion/mptctl.c
index 4470630dd545..8d22d6134a89 100644
--- a/drivers/message/fusion/mptctl.c
+++ b/drivers/message/fusion/mptctl.c
@@ -2514,8 +2514,8 @@ mptctl_hp_hostinfo(unsigned long arg, unsigned int data_size)
 				if (mpt_config(ioc, &cfg) == 0) {
 					ManufacturingPage0_t *pdata = (ManufacturingPage0_t *) pbuf;
 					if (strlen(pdata->BoardTracerNumber) > 1) {
-						strncpy(karg.serial_number, 									    pdata->BoardTracerNumber, 24);
-						karg.serial_number[24-1]='\0';
+						strlcpy(karg.serial_number,
+							pdata->BoardTracerNumber, 24);
 					}
 				}
 				pci_free_consistent(ioc->pcidev, hdr.PageLength * 4, pbuf, buf_dma);
-- 
cgit v1.2.3


From a544523887007ba2b6bd73419c4e2f0ab9bb3633 Mon Sep 17 00:00:00 2001
From: Dominique Martinet <asmadeus@codewreck.org>
Date: Fri, 13 Jul 2018 03:25:56 +0200
Subject: scsi: ibmvscsi: change strncpy+truncation to strlcpy

Generated by scripts/coccinelle/misc/strncpy_truncation.cocci

Signed-off-by: Dominique Martinet <asmadeus@codewreck.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ibmvscsi/ibmvscsi.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/scsi/ibmvscsi/ibmvscsi.c b/drivers/scsi/ibmvscsi/ibmvscsi.c
index 02689298325b..9df8a1a2299c 100644
--- a/drivers/scsi/ibmvscsi/ibmvscsi.c
+++ b/drivers/scsi/ibmvscsi/ibmvscsi.c
@@ -1274,14 +1274,12 @@ static void send_mad_capabilities(struct ibmvscsi_host_data *hostdata)
 	if (hostdata->client_migrated)
 		hostdata->caps.flags |= cpu_to_be32(CLIENT_MIGRATED);
 
-	strncpy(hostdata->caps.name, dev_name(&hostdata->host->shost_gendev),
+	strlcpy(hostdata->caps.name, dev_name(&hostdata->host->shost_gendev),
 		sizeof(hostdata->caps.name));
-	hostdata->caps.name[sizeof(hostdata->caps.name) - 1] = '\0';
 
 	location = of_get_property(of_node, "ibm,loc-code", NULL);
 	location = location ? location : dev_name(hostdata->dev);
-	strncpy(hostdata->caps.loc, location, sizeof(hostdata->caps.loc));
-	hostdata->caps.loc[sizeof(hostdata->caps.loc) - 1] = '\0';
+	strlcpy(hostdata->caps.loc, location, sizeof(hostdata->caps.loc));
 
 	req->common.type = cpu_to_be32(VIOSRP_CAPABILITIES_TYPE);
 	req->buffer = cpu_to_be64(hostdata->caps_addr);
-- 
cgit v1.2.3


From cc74e31d4147f26ead6ea06e4649d63a14edc0fe Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 13 Jul 2018 09:39:54 +0100
Subject: scsi: lpfc: remove null check on nvmebuf

The null checks on nvmebuf are redundant as nvmebuf is always obtained from
a container_of() and hence can never be null. Remove all the redundant null
checks. This also cleans up a static analysis warning.

Detected by CoverityScan, CID#1471753 ("Dereference before null check")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_nvmet.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvmet.c b/drivers/scsi/lpfc/lpfc_nvmet.c
index 22f8a204b69f..b766afe10d3d 100644
--- a/drivers/scsi/lpfc/lpfc_nvmet.c
+++ b/drivers/scsi/lpfc/lpfc_nvmet.c
@@ -1745,7 +1745,7 @@ lpfc_nvmet_unsol_ls_buffer(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	fc_hdr = (struct fc_frame_header *)(nvmebuf->hbuf.virt);
 	oxid = be16_to_cpu(fc_hdr->fh_ox_id);
 
-	if (!nvmebuf || !phba->targetport) {
+	if (!phba->targetport) {
 		lpfc_printf_log(phba, KERN_ERR, LOG_NVME_IOERR,
 				"6154 LS Drop IO x%x\n", oxid);
 		oxid = 0;
@@ -1770,8 +1770,7 @@ dropit:
 		lpfc_nvmeio_data(phba, "NVMET LS  DROP: "
 				 "xri x%x sz %d from %06x\n",
 				 oxid, size, sid);
-		if (nvmebuf)
-			lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
 		return;
 	}
 	ctxp->phba = phba;
@@ -1814,8 +1813,7 @@ dropit:
 			ctxp->oxid, rc);
 
 	/* We assume a rcv'ed cmd ALWAYs fits into 1 buffer */
-	if (nvmebuf)
-		lpfc_in_buf_free(phba, &nvmebuf->dbuf);
+	lpfc_in_buf_free(phba, &nvmebuf->dbuf);
 
 	atomic_inc(&tgtp->xmt_ls_abort);
 	lpfc_nvmet_unsol_ls_issue_abort(phba, ctxp, sid, oxid);
-- 
cgit v1.2.3


From 508385001c09ee648c46f3d2bf5584e366007fd7 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 11:47:39 +0800
Subject: scsi: message: fusion: Replace GFP_ATOMIC with GFP_KERNEL

mpt_attach() and mptfc_probe() are never called in atomic context.  They
call kzalloc() and kcalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/message/fusion/mptbase.c | 2 +-
 drivers/message/fusion/mptfc.c   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/message/fusion/mptbase.c b/drivers/message/fusion/mptbase.c
index c8c8186f1148..e6b4ae558767 100644
--- a/drivers/message/fusion/mptbase.c
+++ b/drivers/message/fusion/mptbase.c
@@ -1780,7 +1780,7 @@ mpt_attach(struct pci_dev *pdev, const struct pci_device_id *id)
 	struct proc_dir_entry *dent;
 #endif
 
-	ioc = kzalloc(sizeof(MPT_ADAPTER), GFP_ATOMIC);
+	ioc = kzalloc(sizeof(MPT_ADAPTER), GFP_KERNEL);
 	if (ioc == NULL) {
 		printk(KERN_ERR MYNAM ": ERROR - Insufficient memory to add adapter!\n");
 		return -ENOMEM;
diff --git a/drivers/message/fusion/mptfc.c b/drivers/message/fusion/mptfc.c
index 06b175420be9..b15fdc626fb8 100644
--- a/drivers/message/fusion/mptfc.c
+++ b/drivers/message/fusion/mptfc.c
@@ -1292,7 +1292,7 @@ mptfc_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* SCSI needs scsi_cmnd lookup table!
 	 * (with size equal to req_depth*PtrSz!)
 	 */
-	ioc->ScsiLookup = kcalloc(ioc->req_depth, sizeof(void *), GFP_ATOMIC);
+	ioc->ScsiLookup = kcalloc(ioc->req_depth, sizeof(void *), GFP_KERNEL);
 	if (!ioc->ScsiLookup) {
 		error = -ENOMEM;
 		goto out_mptfc_probe;
-- 
cgit v1.2.3


From d6aec1ca7c7c69e5b83b2cb24a57e7860d15507f Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 17:09:13 +0800
Subject: scsi: a100u2w: Replace mdelay() with msleep()

wait_chip_ready() and wait_firmware_ready() are never called in atomic
context.  They call mdelay() to busy wait which is not necessary.  mdelay()
can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/a100u2w.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/a100u2w.c b/drivers/scsi/a100u2w.c
index b2942ec3d455..23b17621b6d2 100644
--- a/drivers/scsi/a100u2w.c
+++ b/drivers/scsi/a100u2w.c
@@ -143,7 +143,7 @@ static u8 wait_chip_ready(struct orc_host * host)
 	for (i = 0; i < 10; i++) {	/* Wait 1 second for report timeout     */
 		if (inb(host->base + ORC_HCTRL) & HOSTSTOP)	/* Wait HOSTSTOP set */
 			return 1;
-		mdelay(100);
+		msleep(100);
 	}
 	return 0;
 }
@@ -155,7 +155,7 @@ static u8 wait_firmware_ready(struct orc_host * host)
 	for (i = 0; i < 10; i++) {	/* Wait 1 second for report timeout     */
 		if (inb(host->base + ORC_HSTUS) & RREADY)		/* Wait READY set */
 			return 1;
-		mdelay(100);	/* wait 100ms before try again  */
+		msleep(100);	/* wait 100ms before try again  */
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From dcaa0c12661d862bc533239da22ddf2ed90595e7 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 17:13:17 +0800
Subject: scsi: atp870u: Replace mdelay() with msleep()

tscam(), atp870_init(), atp880_init() and atp885_init() are never
called in atomic context.
They call mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/atp870u.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/atp870u.c b/drivers/scsi/atp870u.c
index b46997cf77e2..8996d2329e11 100644
--- a/drivers/scsi/atp870u.c
+++ b/drivers/scsi/atp870u.c
@@ -1055,7 +1055,7 @@ static void tscam(struct Scsi_Host *host, bool wide_chip, u8 scam_on)
 	udelay(2);		/* 2 deskew delay(45ns*2=90ns) */
 	val &= 0x007f;		/* no bsy  */
 	atp_writew_io(dev, 0, 0x1c, val);
-	mdelay(128);
+	msleep(128);
 	val &= 0x00fb;		/* after 1ms no msg */
 	atp_writew_io(dev, 0, 0x1c, val);
 	while ((atp_readb_io(dev, 0, 0x1c) & 0x04) != 0)
@@ -1286,9 +1286,9 @@ static void atp870_init(struct Scsi_Host *shpnt)
 	k = (atp_readb_base(atpdev, 0x3a) & 0xf3) | 0x10;
 	atp_writeb_base(atpdev, 0x3a, k);
 	atp_writeb_base(atpdev, 0x3a, k & 0xdf);
-	mdelay(32);
+	msleep(32);
 	atp_writeb_base(atpdev, 0x3a, k);
-	mdelay(32);
+	msleep(32);
 	atp_set_host_id(atpdev, 0, host_id);
 
 	tscam(shpnt, wide_chip, scam_on);
@@ -1370,9 +1370,9 @@ static void atp880_init(struct Scsi_Host *shpnt)
 	k = atp_readb_base(atpdev, 0x38) & 0x80;
 	atp_writeb_base(atpdev, 0x38, k);
 	atp_writeb_base(atpdev, 0x3b, 0x20);
-	mdelay(32);
+	msleep(32);
 	atp_writeb_base(atpdev, 0x3b, 0);
-	mdelay(32);
+	msleep(32);
 	atp_readb_io(atpdev, 0, 0x1b);
 	atp_readb_io(atpdev, 0, 0x17);
 
@@ -1454,10 +1454,10 @@ static void atp885_init(struct Scsi_Host *shpnt)
 	atp_writeb_base(atpdev, 0x28, k);
 	atp_writeb_pci(atpdev, 0, 1, 0x80);
 	atp_writeb_pci(atpdev, 1, 1, 0x80);
-	mdelay(100);
+	msleep(100);
 	atp_writeb_pci(atpdev, 0, 1, 0);
 	atp_writeb_pci(atpdev, 1, 1, 0);
-	mdelay(1000);
+	msleep(1000);
 	atp_readb_io(atpdev, 0, 0x1b);
 	atp_readb_io(atpdev, 0, 0x17);
 	atp_readb_io(atpdev, 1, 0x1b);
@@ -1473,7 +1473,7 @@ static void atp885_init(struct Scsi_Host *shpnt)
 		k = (k & 0x07) | 0x40;
 	atp_set_host_id(atpdev, 1, k);
 
-	mdelay(600); /* this delay used to be called tscam_885() */
+	msleep(600); /* this delay used to be called tscam_885() */
 	dev_info(&pdev->dev, "Scanning Channel A SCSI Device ...\n");
 	atp_is(atpdev, 0, true, atp_readb_io(atpdev, 0, 0x1b) >> 7);
 	atp_writeb_io(atpdev, 0, 0x16, 0x80);
-- 
cgit v1.2.3


From 4dc98c1995482262e70e83ef029135247fafe0f2 Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Fri, 27 Jul 2018 16:51:57 +0300
Subject: scsi: 3ware: fix return 0 on the error path of probe

tw_probe() returns 0 in case of fail of tw_initialize_device_extension(),
pci_resource_start() or tw_reset_sequence() and releases resources.
twl_probe() returns 0 in case of fail of twl_initialize_device_extension(),
pci_iomap() and twl_reset_sequence().  twa_probe() returns 0 in case of
fail of tw_initialize_device_extension(), ioremap() and
twa_reset_sequence().

The patch adds retval initialization for these cases.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Acked-by: Adam Radford <aradford@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/3w-9xxx.c | 6 +++++-
 drivers/scsi/3w-sas.c  | 3 +++
 drivers/scsi/3w-xxxx.c | 2 ++
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/3w-9xxx.c b/drivers/scsi/3w-9xxx.c
index 99ba4a770406..27521fc3ef5a 100644
--- a/drivers/scsi/3w-9xxx.c
+++ b/drivers/scsi/3w-9xxx.c
@@ -2038,6 +2038,7 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 
 	if (twa_initialize_device_extension(tw_dev)) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x25, "Failed to initialize device extension");
+		retval = -ENOMEM;
 		goto out_free_device_extension;
 	}
 
@@ -2060,6 +2061,7 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	tw_dev->base_addr = ioremap(mem_addr, mem_len);
 	if (!tw_dev->base_addr) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x35, "Failed to ioremap");
+		retval = -ENOMEM;
 		goto out_release_mem_region;
 	}
 
@@ -2067,8 +2069,10 @@ static int twa_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	TW_DISABLE_INTERRUPTS(tw_dev);
 
 	/* Initialize the card */
-	if (twa_reset_sequence(tw_dev, 0))
+	if (twa_reset_sequence(tw_dev, 0)) {
+		retval = -ENOMEM;
 		goto out_iounmap;
+	}
 
 	/* Set host specific parameters */
 	if ((pdev->device == PCI_DEVICE_ID_3WARE_9650SE) ||
diff --git a/drivers/scsi/3w-sas.c b/drivers/scsi/3w-sas.c
index cf9f2a09b47d..40c1e6e64f58 100644
--- a/drivers/scsi/3w-sas.c
+++ b/drivers/scsi/3w-sas.c
@@ -1594,6 +1594,7 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 
 	if (twl_initialize_device_extension(tw_dev)) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1a, "Failed to initialize device extension");
+		retval = -ENOMEM;
 		goto out_free_device_extension;
 	}
 
@@ -1608,6 +1609,7 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	tw_dev->base_addr = pci_iomap(pdev, 1, 0);
 	if (!tw_dev->base_addr) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1c, "Failed to ioremap");
+		retval = -ENOMEM;
 		goto out_release_mem_region;
 	}
 
@@ -1617,6 +1619,7 @@ static int twl_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	/* Initialize the card */
 	if (twl_reset_sequence(tw_dev, 0)) {
 		TW_PRINTK(tw_dev->host, TW_DRIVER, 0x1d, "Controller reset failed during probe");
+		retval = -ENOMEM;
 		goto out_iounmap;
 	}
 
diff --git a/drivers/scsi/3w-xxxx.c b/drivers/scsi/3w-xxxx.c
index a40d353bd8b3..471366945bd4 100644
--- a/drivers/scsi/3w-xxxx.c
+++ b/drivers/scsi/3w-xxxx.c
@@ -2280,6 +2280,7 @@ static int tw_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 
 	if (tw_initialize_device_extension(tw_dev)) {
 		printk(KERN_WARNING "3w-xxxx: Failed to initialize device extension.");
+		retval = -ENOMEM;
 		goto out_free_device_extension;
 	}
 
@@ -2294,6 +2295,7 @@ static int tw_probe(struct pci_dev *pdev, const struct pci_device_id *dev_id)
 	tw_dev->base_addr = pci_resource_start(pdev, 0);
 	if (!tw_dev->base_addr) {
 		printk(KERN_WARNING "3w-xxxx: Failed to get io address.");
+		retval = -ENOMEM;
 		goto out_release_mem_region;
 	}
 
-- 
cgit v1.2.3


From 7382f9d8dc0db271da32787fd8559f1ec9f3f4f9 Mon Sep 17 00:00:00 2001
From: Douglas Gilbert <dgilbert@interlog.com>
Date: Sat, 21 Jul 2018 01:10:04 -0400
Subject: scsi: scsi_debug: add cmd abort option to every_nth

This patch is motivated by a response in the thread:

  Re: [PATCH 0/5]stop normal completion path entering a timeout req

by Jianchao Wang . It generalizes the error injection of
blk_abort_request() to use scsi_debug's "every_nth" mechanism.  Ref with
original patch to scsi_debug:

https://lore.kernel.org/lkml/a68ad043-26a1-d3d8-2009-504ba4230e0f@oracle.com/

Also convert two vmalloc/memset(0) to vzalloc() calls.

Signed-off-by: Douglas Gilbert <dgilbert@interlog.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_debug.c | 47 ++++++++++++++++++++++++++++++++---------------
 1 file changed, 32 insertions(+), 15 deletions(-)

diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c
index 4dda192b8fba..2c816ecb0a92 100644
--- a/drivers/scsi/scsi_debug.c
+++ b/drivers/scsi/scsi_debug.c
@@ -164,29 +164,29 @@ static const char *sdebug_version_date = "20180128";
 #define SDEBUG_OPT_RESET_NOISE		0x2000
 #define SDEBUG_OPT_NO_CDB_NOISE		0x4000
 #define SDEBUG_OPT_HOST_BUSY		0x8000
+#define SDEBUG_OPT_CMD_ABORT		0x10000
 #define SDEBUG_OPT_ALL_NOISE (SDEBUG_OPT_NOISE | SDEBUG_OPT_Q_NOISE | \
 			      SDEBUG_OPT_RESET_NOISE)
 #define SDEBUG_OPT_ALL_INJECTING (SDEBUG_OPT_RECOVERED_ERR | \
 				  SDEBUG_OPT_TRANSPORT_ERR | \
 				  SDEBUG_OPT_DIF_ERR | SDEBUG_OPT_DIX_ERR | \
 				  SDEBUG_OPT_SHORT_TRANSFER | \
-				  SDEBUG_OPT_HOST_BUSY)
+				  SDEBUG_OPT_HOST_BUSY | \
+				  SDEBUG_OPT_CMD_ABORT)
 /* When "every_nth" > 0 then modulo "every_nth" commands:
  *   - a missing response is simulated if SDEBUG_OPT_TIMEOUT is set
  *   - a RECOVERED_ERROR is simulated on successful read and write
  *     commands if SDEBUG_OPT_RECOVERED_ERR is set.
  *   - a TRANSPORT_ERROR is simulated on successful read and write
  *     commands if SDEBUG_OPT_TRANSPORT_ERR is set.
+ *   - similarly for DIF_ERR, DIX_ERR, SHORT_TRANSFER, HOST_BUSY and
+ *     CMD_ABORT
  *
- * When "every_nth" < 0 then after "- every_nth" commands:
- *   - a missing response is simulated if SDEBUG_OPT_TIMEOUT is set
- *   - a RECOVERED_ERROR is simulated on successful read and write
- *     commands if SDEBUG_OPT_RECOVERED_ERR is set.
- *   - a TRANSPORT_ERROR is simulated on successful read and write
- *     commands if _DEBUG_OPT_TRANSPORT_ERR is set.
- * This will continue on every subsequent command until some other action
- * occurs (e.g. the user * writing a new value (other than -1 or 1) to
- * every_nth via sysfs).
+ * When "every_nth" < 0 then after "- every_nth" commands the selected
+ * error will be injected. The error will be injected on every subsequent
+ * command until some other action occurs; for example, the user writing
+ * a new value (other than -1 or 1) to every_nth:
+ *      echo 0 > /sys/bus/pseudo/drivers/scsi_debug/every_nth
  */
 
 /* As indicated in SAM-5 and SPC-4 Unit Attentions (UAs) are returned in
@@ -281,6 +281,7 @@ struct sdebug_defer {
 	int issuing_cpu;
 	bool init_hrt;
 	bool init_wq;
+	bool aborted;	/* true when blk_abort_request() already called */
 	enum sdeb_defer_type defer_t;
 };
 
@@ -296,6 +297,7 @@ struct sdebug_queued_cmd {
 	unsigned int inj_dix:1;
 	unsigned int inj_short:1;
 	unsigned int inj_host_busy:1;
+	unsigned int inj_cmd_abort:1;
 };
 
 struct sdebug_queue {
@@ -3792,6 +3794,7 @@ static struct sdebug_queue *get_queue(struct scsi_cmnd *cmnd)
 /* Queued (deferred) command completions converge here. */
 static void sdebug_q_cmd_complete(struct sdebug_defer *sd_dp)
 {
+	bool aborted = sd_dp->aborted;
 	int qc_idx;
 	int retiring = 0;
 	unsigned long iflags;
@@ -3801,6 +3804,8 @@ static void sdebug_q_cmd_complete(struct sdebug_defer *sd_dp)
 	struct sdebug_dev_info *devip;
 
 	sd_dp->defer_t = SDEB_DEFER_NONE;
+	if (unlikely(aborted))
+		sd_dp->aborted = false;
 	qc_idx = sd_dp->qc_idx;
 	sqp = sdebug_q_arr + sd_dp->sqa_idx;
 	if (sdebug_statistics) {
@@ -3852,6 +3857,11 @@ static void sdebug_q_cmd_complete(struct sdebug_defer *sd_dp)
 			atomic_set(&retired_max_queue, k + 1);
 	}
 	spin_unlock_irqrestore(&sqp->qc_lock, iflags);
+	if (unlikely(aborted)) {
+		if (sdebug_verbose)
+			pr_info("bypassing scsi_done() due to aborted cmd\n");
+		return;
+	}
 	scp->scsi_done(scp); /* callback to mid level */
 }
 
@@ -4312,7 +4322,8 @@ static void setup_inject(struct sdebug_queue *sqp,
 		if (sdebug_every_nth > 0)
 			sqcp->inj_recovered = sqcp->inj_transport
 				= sqcp->inj_dif
-				= sqcp->inj_dix = sqcp->inj_short = 0;
+				= sqcp->inj_dix = sqcp->inj_short
+				= sqcp->inj_host_busy = sqcp->inj_cmd_abort = 0;
 		return;
 	}
 	sqcp->inj_recovered = !!(SDEBUG_OPT_RECOVERED_ERR & sdebug_opts);
@@ -4321,6 +4332,7 @@ static void setup_inject(struct sdebug_queue *sqp,
 	sqcp->inj_dix = !!(SDEBUG_OPT_DIX_ERR & sdebug_opts);
 	sqcp->inj_short = !!(SDEBUG_OPT_SHORT_TRANSFER & sdebug_opts);
 	sqcp->inj_host_busy = !!(SDEBUG_OPT_HOST_BUSY & sdebug_opts);
+	sqcp->inj_cmd_abort = !!(SDEBUG_OPT_CMD_ABORT & sdebug_opts);
 }
 
 /* Complete the processing of the thread that queued a SCSI command to this
@@ -4458,7 +4470,14 @@ static int schedule_resp(struct scsi_cmnd *cmnd, struct sdebug_dev_info *devip,
 		if (sdebug_statistics)
 			sd_dp->issuing_cpu = raw_smp_processor_id();
 		sd_dp->defer_t = SDEB_DEFER_WQ;
+		if (unlikely(sqcp->inj_cmd_abort))
+			sd_dp->aborted = true;
 		schedule_work(&sd_dp->ew.work);
+		if (unlikely(sqcp->inj_cmd_abort)) {
+			sdev_printk(KERN_INFO, sdp, "abort request tag %d\n",
+				    cmnd->request->tag);
+			blk_abort_request(cmnd->request);
+		}
 	}
 	if (unlikely((SDEBUG_OPT_Q_NOISE & sdebug_opts) &&
 		     (scsi_result == device_qfull_result)))
@@ -4844,12 +4863,11 @@ static ssize_t fake_rw_store(struct device_driver *ddp, const char *buf,
 					(unsigned long)sdebug_dev_size_mb *
 					1048576;
 
-				fake_storep = vmalloc(sz);
+				fake_storep = vzalloc(sz);
 				if (NULL == fake_storep) {
 					pr_err("out of memory, 9\n");
 					return -ENOMEM;
 				}
-				memset(fake_storep, 0, sz);
 			}
 			sdebug_fake_rw = n;
 		}
@@ -5391,13 +5409,12 @@ static int __init scsi_debug_init(void)
 	}
 
 	if (sdebug_fake_rw == 0) {
-		fake_storep = vmalloc(sz);
+		fake_storep = vzalloc(sz);
 		if (NULL == fake_storep) {
 			pr_err("out of memory, 1\n");
 			ret = -ENOMEM;
 			goto free_q_arr;
 		}
-		memset(fake_storep, 0, sz);
 		if (sdebug_num_parts > 0)
 			sdebug_build_parts(fake_storep, sz);
 	}
-- 
cgit v1.2.3


From 1360c58a348e4ec551b58b9f40c3222ff5d6270f Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 30 Jul 2018 14:40:18 -0700
Subject: scsi: libiscsi: Annotate locking assumptions

This patch avoids that sparse reports the following:

drivers/scsi/libiscsi.c:1844:23: warning: context imbalance in 'iscsi_exec_task_mgmt_fn' - unexpected unlock

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Lee Duncan <lduncan@suse.com>
Signed-off-by: Chris Leech <cleech@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libiscsi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index d6093838f5f2..b36bafd5a058 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1832,6 +1832,7 @@ static void iscsi_tmf_timedout(struct timer_list *t)
 static int iscsi_exec_task_mgmt_fn(struct iscsi_conn *conn,
 				   struct iscsi_tm *hdr, int age,
 				   int timeout)
+	__must_hold(&session->frwd_lock)
 {
 	struct iscsi_session *session = conn->session;
 	struct iscsi_task *task;
-- 
cgit v1.2.3


From 807cf197fc9a3bc156523cb68786a9cb0ec396b4 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 30 Jul 2018 14:40:19 -0700
Subject: scsi: libiscsi: Annotate fall-through

This patch avoids that building with W=1 causes the compiler to
complain about fall-through.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Lee Duncan <lduncan@suse.com>
Cc: Chris Leech <cleech@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/libiscsi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index b36bafd5a058..d5f2f368040f 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -1705,6 +1705,7 @@ int iscsi_queuecommand(struct Scsi_Host *host, struct scsi_cmnd *sc)
 				sc->result = DID_NO_CONNECT << 16;
 				break;
 			}
+			/* fall through */
 		case ISCSI_STATE_IN_RECOVERY:
 			reason = FAILURE_SESSION_IN_RECOVERY;
 			sc->result = DID_IMM_RETRY << 16;
-- 
cgit v1.2.3


From f0e89aae609bebd430ce7a96d2f642917d89ca57 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:43 -0500
Subject: scsi: target_core_user: fix double unlock

The caller of queue_cmd_ring grabs and releases the lock, so the
tcmu_setup_cmd_timer failure handling inside queue_cmd_ring should not call
mutex_unlock.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 847707a700cf..fafe65fd37f4 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1066,7 +1066,6 @@ static sense_reason_t queue_cmd_ring(struct tcmu_cmd *tcmu_cmd, int *scsi_err)
 				   &udev->cmd_timer);
 	if (ret) {
 		tcmu_cmd_free_data(tcmu_cmd, tcmu_cmd->dbi_cnt);
-		mutex_unlock(&udev->cmdr_lock);
 
 		*scsi_err = TCM_OUT_OF_RESOURCES;
 		return -1;
-- 
cgit v1.2.3


From ff07e4a414d963d5b1ee1446f05a451e591256de Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:44 -0500
Subject: scsi: tcmu: initialize list head

Use INIT_LIST_HEAD to initialize node list head.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index fafe65fd37f4..b010ed7e877b 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1342,6 +1342,7 @@ static struct se_device *tcmu_alloc_device(struct se_hba *hba, const char *name)
 	udev->max_blocks = DATA_BLOCK_BITS_DEF;
 	mutex_init(&udev->cmdr_lock);
 
+	INIT_LIST_HEAD(&udev->node);
 	INIT_LIST_HEAD(&udev->timedout_entry);
 	INIT_LIST_HEAD(&udev->cmdr_queue);
 	idr_init(&udev->commands);
-- 
cgit v1.2.3


From cb0f32e12cded06e12ff19104eaf90c6f8310558 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:45 -0500
Subject: scsi: target: add helper to check if dev is configured

This just adds a helper function to check if a device is configured and it
converts the target users to use it. The next patch will add a backend
module user so those types of modules do not have to know the lio core
details.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_configfs.c        | 8 ++++----
 drivers/target/target_core_device.c          | 6 +++---
 drivers/target/target_core_fabric_configfs.c | 3 ++-
 include/target/target_core_backend.h         | 4 ++++
 4 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 93d3ff34b614..f6b1549f4142 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -810,7 +810,7 @@ static ssize_t pi_prot_type_store(struct config_item *item,
 		       dev->transport->name);
 		return -ENOSYS;
 	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("DIF protection requires device to be configured\n");
 		return -ENODEV;
 	}
@@ -859,7 +859,7 @@ static ssize_t pi_prot_format_store(struct config_item *item,
 		       dev->transport->name);
 		return -ENOSYS;
 	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("DIF protection format requires device to be configured\n");
 		return -ENODEV;
 	}
@@ -1948,7 +1948,7 @@ static ssize_t target_dev_enable_show(struct config_item *item, char *page)
 {
 	struct se_device *dev = to_device(item);
 
-	return snprintf(page, PAGE_SIZE, "%d\n", !!(dev->dev_flags & DF_CONFIGURED));
+	return snprintf(page, PAGE_SIZE, "%d\n", target_dev_configured(dev));
 }
 
 static ssize_t target_dev_enable_store(struct config_item *item,
@@ -2473,7 +2473,7 @@ static ssize_t target_tg_pt_gp_alua_access_state_store(struct config_item *item,
 			" tg_pt_gp ID: %hu\n", tg_pt_gp->tg_pt_gp_valid_id);
 		return -EINVAL;
 	}
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("Unable to set alua_access_state while device is"
 		       " not configured\n");
 		return -ENODEV;
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index 73675eec740d..47b5ef153135 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -900,7 +900,7 @@ static int target_devices_idr_iter(int id, void *p, void *data)
 	 * to allow other callers to access partially setup devices,
 	 * so we skip them here.
 	 */
-	if (!(dev->dev_flags & DF_CONFIGURED))
+	if (!target_dev_configured(dev))
 		return 0;
 
 	iter->prev_item = config_item_get_unless_zero(&dev->dev_group.cg_item);
@@ -940,7 +940,7 @@ int target_configure_device(struct se_device *dev)
 	struct se_hba *hba = dev->se_hba;
 	int ret, id;
 
-	if (dev->dev_flags & DF_CONFIGURED) {
+	if (target_dev_configured(dev)) {
 		pr_err("se_dev->se_dev_ptr already set for storage"
 				" object\n");
 		return -EEXIST;
@@ -1045,7 +1045,7 @@ void target_free_device(struct se_device *dev)
 
 	WARN_ON(!list_empty(&dev->dev_sep_list));
 
-	if (dev->dev_flags & DF_CONFIGURED) {
+	if (target_dev_configured(dev)) {
 		destroy_workqueue(dev->tmr_wq);
 
 		dev->transport->destroy_device(dev);
diff --git a/drivers/target/target_core_fabric_configfs.c b/drivers/target/target_core_fabric_configfs.c
index 1fa436e865f9..aa2f4f632ebe 100644
--- a/drivers/target/target_core_fabric_configfs.c
+++ b/drivers/target/target_core_fabric_configfs.c
@@ -34,6 +34,7 @@
 #include <linux/configfs.h>
 
 #include <target/target_core_base.h>
+#include <target/target_core_backend.h>
 #include <target/target_core_fabric.h>
 
 #include "target_core_internal.h"
@@ -642,7 +643,7 @@ static int target_fabric_port_link(
 	}
 	dev = container_of(to_config_group(se_dev_ci), struct se_device, dev_group);
 
-	if (!(dev->dev_flags & DF_CONFIGURED)) {
+	if (!target_dev_configured(dev)) {
 		pr_err("se_device not configured yet, cannot port link\n");
 		return -ENODEV;
 	}
diff --git a/include/target/target_core_backend.h b/include/target/target_core_backend.h
index c3ac47255218..51b6f50eabee 100644
--- a/include/target/target_core_backend.h
+++ b/include/target/target_core_backend.h
@@ -111,6 +111,10 @@ sector_t target_to_linux_sector(struct se_device *dev, sector_t lb);
 bool target_configure_unmap_from_queue(struct se_dev_attrib *attrib,
 				       struct request_queue *q);
 
+static inline bool target_dev_configured(struct se_device *se_dev)
+{
+	return !!(se_dev->dev_flags & DF_CONFIGURED);
+}
 
 /* Only use get_unaligned_be24() if reading p - 1 is allowed. */
 static inline uint32_t get_unaligned_be24(const uint8_t *const p)
-- 
cgit v1.2.3


From 63d5be0f6a8053ba0c084dd6e2d5538e9376e7da Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:46 -0500
Subject: scsi: tcmu: use lio core se_device configuration helper

Use the lio core helper to check if the device is configured.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index b010ed7e877b..bc8121f97d65 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1908,11 +1908,6 @@ err_bitmap_alloc:
 	return ret;
 }
 
-static bool tcmu_dev_configured(struct tcmu_dev *udev)
-{
-	return udev->uio_info.uio_dev ? true : false;
-}
-
 static void tcmu_free_device(struct se_device *dev)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
@@ -2305,7 +2300,7 @@ static ssize_t tcmu_dev_config_store(struct config_item *item, const char *page,
 		return -EINVAL;
 
 	/* Check if device has been configured before */
-	if (tcmu_dev_configured(udev)) {
+	if (target_dev_configured(&udev->se_dev)) {
 		ret = tcmu_send_dev_config_event(udev, page);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
@@ -2367,7 +2362,7 @@ static ssize_t tcmu_dev_size_store(struct config_item *item, const char *page,
 		return ret;
 
 	/* Check if device has been configured before */
-	if (tcmu_dev_configured(udev)) {
+	if (target_dev_configured(&udev->se_dev)) {
 		ret = tcmu_send_dev_size_event(udev, val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
@@ -2449,7 +2444,7 @@ static ssize_t tcmu_emulate_write_cache_store(struct config_item *item,
 		return ret;
 
 	/* Check if device has been configured before */
-	if (tcmu_dev_configured(udev)) {
+	if (target_dev_configured(&udev->se_dev)) {
 		ret = tcmu_send_emulate_write_cache(udev, val);
 		if (ret) {
 			pr_err("Unable to reconfigure device\n");
-- 
cgit v1.2.3


From a30b0473b62652f9b8ccb1e4f4a3a3c31d2b72b3 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:47 -0500
Subject: scsi: tcmu: check if dev is configured before block/reset

Do not allow userspace to block or reset the ring until the device has been
configured. This will prevent the bug where userspace can write to those
files and access mb_addr before it has been setup.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index bc8121f97d65..d6b402203b20 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -2480,6 +2480,11 @@ static ssize_t tcmu_block_dev_store(struct config_item *item, const char *page,
 	u8 val;
 	int ret;
 
+	if (!target_dev_configured(&udev->se_dev)) {
+		pr_err("Device is not configured.\n");
+		return -EINVAL;
+	}
+
 	ret = kstrtou8(page, 0, &val);
 	if (ret < 0)
 		return ret;
@@ -2507,6 +2512,11 @@ static ssize_t tcmu_reset_ring_store(struct config_item *item, const char *page,
 	u8 val;
 	int ret;
 
+	if (!target_dev_configured(&udev->se_dev)) {
+		pr_err("Device is not configured.\n");
+		return -EINVAL;
+	}
+
 	ret = kstrtou8(page, 0, &val);
 	if (ret < 0)
 		return ret;
-- 
cgit v1.2.3


From dc335a995527fb1ee9ec5649162b22cd1ce728ee Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:48 -0500
Subject: scsi: tcmu: unmap if dev is configured

The tcmu dev is added to the list of tcmu devices during configuration.  At
this time the tcmu setup has completed, but lio core has not completed its
setup. The device is not yet usable so do not try to unmap blocks from it

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index d6b402203b20..31cfe8345ef3 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -2581,6 +2581,11 @@ static void find_free_blocks(void)
 	list_for_each_entry(udev, &root_udev, node) {
 		mutex_lock(&udev->cmdr_lock);
 
+		if (!target_dev_configured(&udev->se_dev)) {
+			mutex_unlock(&udev->cmdr_lock);
+			continue;
+		}
+
 		/* Try to complete the finished commands first */
 		tcmu_handle_completions(udev);
 
-- 
cgit v1.2.3


From c97840c84f5a4362a596a2751e9245a979377a16 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:49 -0500
Subject: scsi: tcmu: do not set max_blocks if data_bitmap has been setup

This patch prevents a bug where data_bitmap is allocated in
tcmu_configure_device, userspace changes the max_blocks setting, the device
is mapped to a LUN, then we try to access the data_bitmap based on the new
max_blocks limit which may now be out of range.

To prevent this, we just check if data_bitmap has been setup. If it has
then we fail the max_blocks update operation.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 73 +++++++++++++++++++++------------------
 1 file changed, 40 insertions(+), 33 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 31cfe8345ef3..969ccbaaccba 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -1811,9 +1811,11 @@ static int tcmu_configure_device(struct se_device *dev)
 
 	info = &udev->uio_info;
 
+	mutex_lock(&udev->cmdr_lock);
 	udev->data_bitmap = kcalloc(BITS_TO_LONGS(udev->max_blocks),
 				    sizeof(unsigned long),
 				    GFP_KERNEL);
+	mutex_unlock(&udev->cmdr_lock);
 	if (!udev->data_bitmap) {
 		ret = -ENOMEM;
 		goto err_bitmap_alloc;
@@ -2018,7 +2020,7 @@ static match_table_t tokens = {
 	{Opt_hw_block_size, "hw_block_size=%u"},
 	{Opt_hw_max_sectors, "hw_max_sectors=%u"},
 	{Opt_nl_reply_supported, "nl_reply_supported=%d"},
-	{Opt_max_data_area_mb, "max_data_area_mb=%u"},
+	{Opt_max_data_area_mb, "max_data_area_mb=%d"},
 	{Opt_err, NULL}
 };
 
@@ -2046,13 +2048,48 @@ static int tcmu_set_dev_attrib(substring_t *arg, u32 *dev_attrib)
 	return 0;
 }
 
+static int tcmu_set_max_blocks_param(struct tcmu_dev *udev, substring_t *arg)
+{
+	int val, ret;
+
+	ret = match_int(arg, &val);
+	if (ret < 0) {
+		pr_err("match_int() failed for max_data_area_mb=. Error %d.\n",
+		       ret);
+		return ret;
+	}
+
+	if (val <= 0) {
+		pr_err("Invalid max_data_area %d.\n", val);
+		return -EINVAL;
+	}
+
+	mutex_lock(&udev->cmdr_lock);
+	if (udev->data_bitmap) {
+		pr_err("Cannot set max_data_area_mb after it has been enabled.\n");
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	udev->max_blocks = TCMU_MBS_TO_BLOCKS(val);
+	if (udev->max_blocks > tcmu_global_max_blocks) {
+		pr_err("%d is too large. Adjusting max_data_area_mb to global limit of %u\n",
+		       val, TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks));
+		udev->max_blocks = tcmu_global_max_blocks;
+	}
+
+unlock:
+	mutex_unlock(&udev->cmdr_lock);
+	return ret;
+}
+
 static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 		const char *page, ssize_t count)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
 	char *orig, *ptr, *opts, *arg_p;
 	substring_t args[MAX_OPT_ARGS];
-	int ret = 0, token, tmpval;
+	int ret = 0, token;
 
 	opts = kstrdup(page, GFP_KERNEL);
 	if (!opts)
@@ -2105,37 +2142,7 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 				pr_err("kstrtoint() failed for nl_reply_supported=\n");
 			break;
 		case Opt_max_data_area_mb:
-			if (dev->export_count) {
-				pr_err("Unable to set max_data_area_mb while exports exist\n");
-				ret = -EINVAL;
-				break;
-			}
-
-			arg_p = match_strdup(&args[0]);
-			if (!arg_p) {
-				ret = -ENOMEM;
-				break;
-			}
-			ret = kstrtoint(arg_p, 0, &tmpval);
-			kfree(arg_p);
-			if (ret < 0) {
-				pr_err("kstrtoint() failed for max_data_area_mb=\n");
-				break;
-			}
-
-			if (tmpval <= 0) {
-				pr_err("Invalid max_data_area %d\n", tmpval);
-				ret = -EINVAL;
-				break;
-			}
-
-			udev->max_blocks = TCMU_MBS_TO_BLOCKS(tmpval);
-			if (udev->max_blocks > tcmu_global_max_blocks) {
-				pr_err("%d is too large. Adjusting max_data_area_mb to global limit of %u\n",
-				       tmpval,
-				       TCMU_BLOCKS_TO_MBS(tcmu_global_max_blocks));
-				udev->max_blocks = tcmu_global_max_blocks;
-			}
+			ret = tcmu_set_max_blocks_param(udev, &args[0]);
 			break;
 		default:
 			break;
-- 
cgit v1.2.3


From b60cb1f80157689d206b09affc43c2dc1cafcbc8 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:50 -0500
Subject: scsi: tcmu: use match_int for dev params

Instead of doing strdup and kstrto* just use match_int for dev params.

It will be ok to use int instead of unsigned long in tcmu_set_dev_attrib
because that is only being used for max sectors and block size and the
supported values for them are well under the max possible integer value.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 37 ++++++++++++++-----------------------
 1 file changed, 14 insertions(+), 23 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index 969ccbaaccba..cfe4f4b8c45c 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -2017,8 +2017,8 @@ enum {
 static match_table_t tokens = {
 	{Opt_dev_config, "dev_config=%s"},
 	{Opt_dev_size, "dev_size=%u"},
-	{Opt_hw_block_size, "hw_block_size=%u"},
-	{Opt_hw_max_sectors, "hw_max_sectors=%u"},
+	{Opt_hw_block_size, "hw_block_size=%d"},
+	{Opt_hw_max_sectors, "hw_max_sectors=%d"},
 	{Opt_nl_reply_supported, "nl_reply_supported=%d"},
 	{Opt_max_data_area_mb, "max_data_area_mb=%d"},
 	{Opt_err, NULL}
@@ -2026,25 +2026,21 @@ static match_table_t tokens = {
 
 static int tcmu_set_dev_attrib(substring_t *arg, u32 *dev_attrib)
 {
-	unsigned long tmp_ul;
-	char *arg_p;
-	int ret;
-
-	arg_p = match_strdup(arg);
-	if (!arg_p)
-		return -ENOMEM;
+	int val, ret;
 
-	ret = kstrtoul(arg_p, 0, &tmp_ul);
-	kfree(arg_p);
+	ret = match_int(arg, &val);
 	if (ret < 0) {
-		pr_err("kstrtoul() failed for dev attrib\n");
+		pr_err("match_int() failed for dev attrib. Error %d.\n",
+		       ret);
 		return ret;
 	}
-	if (!tmp_ul) {
-		pr_err("dev attrib must be nonzero\n");
+
+	if (val <= 0) {
+		pr_err("Invalid dev attrib value %d. Must be greater than zero.\n",
+		       val);
 		return -EINVAL;
 	}
-	*dev_attrib = tmp_ul;
+	*dev_attrib = val;
 	return 0;
 }
 
@@ -2131,15 +2127,10 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 					&(dev->dev_attrib.hw_max_sectors));
 			break;
 		case Opt_nl_reply_supported:
-			arg_p = match_strdup(&args[0]);
-			if (!arg_p) {
-				ret = -ENOMEM;
-				break;
-			}
-			ret = kstrtoint(arg_p, 0, &udev->nl_reply_supported);
-			kfree(arg_p);
+			ret = match_int(&args[0], &udev->nl_reply_supported);
 			if (ret < 0)
-				pr_err("kstrtoint() failed for nl_reply_supported=\n");
+				pr_err("match_int() failed for nl_reply_supported=. Error %d.\n",
+				       ret);
 			break;
 		case Opt_max_data_area_mb:
 			ret = tcmu_set_max_blocks_param(udev, &args[0]);
-- 
cgit v1.2.3


From 0e0d75267107e6a557ea9314d55bcff05a6ede44 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Mon, 23 Jul 2018 14:07:51 -0500
Subject: scsi: tcmu: use u64 for dev_size

We use unsigned long, size_t and u64 for dev_size. This has us standardize
on u64.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Xiubo Li <xiubli@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_user.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/target/target_core_user.c b/drivers/target/target_core_user.c
index cfe4f4b8c45c..b34179ae71ae 100644
--- a/drivers/target/target_core_user.c
+++ b/drivers/target/target_core_user.c
@@ -137,7 +137,7 @@ struct tcmu_dev {
 	struct inode *inode;
 
 	struct tcmu_mailbox *mb_addr;
-	size_t dev_size;
+	uint64_t dev_size;
 	u32 cmdr_size;
 	u32 cmdr_last_cleaned;
 	/* Offset of data area from start of mb */
@@ -2016,7 +2016,7 @@ enum {
 
 static match_table_t tokens = {
 	{Opt_dev_config, "dev_config=%s"},
-	{Opt_dev_size, "dev_size=%u"},
+	{Opt_dev_size, "dev_size=%s"},
 	{Opt_hw_block_size, "hw_block_size=%d"},
 	{Opt_hw_max_sectors, "hw_max_sectors=%d"},
 	{Opt_nl_reply_supported, "nl_reply_supported=%d"},
@@ -2083,7 +2083,7 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 		const char *page, ssize_t count)
 {
 	struct tcmu_dev *udev = TCMU_DEV(dev);
-	char *orig, *ptr, *opts, *arg_p;
+	char *orig, *ptr, *opts;
 	substring_t args[MAX_OPT_ARGS];
 	int ret = 0, token;
 
@@ -2108,15 +2108,10 @@ static ssize_t tcmu_set_configfs_dev_params(struct se_device *dev,
 			pr_debug("TCMU: Referencing Path: %s\n", udev->dev_config);
 			break;
 		case Opt_dev_size:
-			arg_p = match_strdup(&args[0]);
-			if (!arg_p) {
-				ret = -ENOMEM;
-				break;
-			}
-			ret = kstrtoul(arg_p, 0, (unsigned long *) &udev->dev_size);
-			kfree(arg_p);
+			ret = match_u64(&args[0], &udev->dev_size);
 			if (ret < 0)
-				pr_err("kstrtoul() failed for dev_size=\n");
+				pr_err("match_u64() failed for dev_size=. Error %d.\n",
+				       ret);
 			break;
 		case Opt_hw_block_size:
 			ret = tcmu_set_dev_attrib(&args[0],
@@ -2154,7 +2149,7 @@ static ssize_t tcmu_show_configfs_dev_params(struct se_device *dev, char *b)
 
 	bl = sprintf(b + bl, "Config: %s ",
 		     udev->dev_config[0] ? udev->dev_config : "NULL");
-	bl += sprintf(b + bl, "Size: %zu ", udev->dev_size);
+	bl += sprintf(b + bl, "Size: %llu ", udev->dev_size);
 	bl += sprintf(b + bl, "MaxDataAreaMB: %u\n",
 		      TCMU_BLOCKS_TO_MBS(udev->max_blocks));
 
@@ -2323,7 +2318,7 @@ static ssize_t tcmu_dev_size_show(struct config_item *item, char *page)
 						struct se_dev_attrib, da_group);
 	struct tcmu_dev *udev = TCMU_DEV(da->da_dev);
 
-	return snprintf(page, PAGE_SIZE, "%zu\n", udev->dev_size);
+	return snprintf(page, PAGE_SIZE, "%llu\n", udev->dev_size);
 }
 
 static int tcmu_send_dev_size_event(struct tcmu_dev *udev, u64 size)
-- 
cgit v1.2.3


From c8a75afbf72ee4c16dad5339f55f62095879f207 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 26 Jul 2018 10:20:37 -0700
Subject: Revert "scsi: target/iscsi: Reduce number of __iscsit_free_cmd()
 callers"

The cxgbit driver expects that __iscsit_free_cmd() is called before the
target core frees the command page list. Since this patch breaks the
cxgbit driver, revert it.

Reported-by: Varun Prakash <varun@chelsio.com>
Fixes: ed88f055788a ("scsi: target/iscsi: Reduce number of __iscsit_free_cmd() callers")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Varun Prakash <varun@chelsio.com>
Cc: Mike Christie <mchristi@redhat.com>
Cc: Hannes Reinecke <hare@suse.com>
Cc: Christoph Hellwig <hch@lst.de>
Reviewed-by: Mike Christie <mchristi@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/iscsi/iscsi_target.c          | 2 ++
 drivers/target/iscsi/iscsi_target_configfs.c | 1 -
 drivers/target/iscsi/iscsi_target_util.c     | 4 +++-
 3 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index d547dcd625d9..8e223799347a 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -497,6 +497,8 @@ void iscsit_aborted_task(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 	    !(cmd->se_cmd.transport_state & CMD_T_FABRIC_STOP))
 		list_del_init(&cmd->i_conn_node);
 	spin_unlock_bh(&conn->cmd_lock);
+
+	__iscsit_free_cmd(cmd, true);
 }
 EXPORT_SYMBOL(iscsit_aborted_task);
 
diff --git a/drivers/target/iscsi/iscsi_target_configfs.c b/drivers/target/iscsi/iscsi_target_configfs.c
index 1fcd9bc7189d..95d0a22b2ad6 100644
--- a/drivers/target/iscsi/iscsi_target_configfs.c
+++ b/drivers/target/iscsi/iscsi_target_configfs.c
@@ -1544,7 +1544,6 @@ static void lio_release_cmd(struct se_cmd *se_cmd)
 	struct iscsi_cmd *cmd = container_of(se_cmd, struct iscsi_cmd, se_cmd);
 
 	pr_debug("Entering lio_release_cmd for se_cmd: %p\n", se_cmd);
-	__iscsit_free_cmd(cmd, true);
 	iscsit_release_cmd(cmd);
 }
 
diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 5a645b5f1eb4..8cfcf9033507 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -772,8 +772,10 @@ void iscsit_free_cmd(struct iscsi_cmd *cmd, bool shutdown)
 	__iscsit_free_cmd(cmd, shutdown);
 	if (se_cmd) {
 		rc = transport_generic_free_cmd(se_cmd, shutdown);
-		if (!rc && shutdown && se_cmd->se_sess)
+		if (!rc && shutdown && se_cmd->se_sess) {
+			__iscsit_free_cmd(cmd, shutdown);
 			target_put_sess_cmd(se_cmd);
+		}
 	} else {
 		iscsit_release_cmd(cmd);
 	}
-- 
cgit v1.2.3


From 5631909364e1e74b6188ec860d2a4cf216150a26 Mon Sep 17 00:00:00 2001
From: Ganapathi Bhat <gbhat@marvell.com>
Date: Wed, 27 Jun 2018 11:43:38 +0530
Subject: mwifiex: replace rx_pkt_lock by rx_reorder_tbl_lock

At present driver spinlock protects iteration of list
rx_reorder_tbl_ptr with rx_reorder_tbl_lock. To protect the
individual items in this list, it uses rx_pkt_lock. But, we can
use a single rx_reorder_tbl_lock for both purposes. This patch
replaces rx_pkt_lock by rx_reorder_tbl_lock.

Signed-off-by: Ganapathi Bhat <gbhat@marvell.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c | 19 ++++++++++---------
 drivers/net/wireless/marvell/mwifiex/init.c          |  1 -
 drivers/net/wireless/marvell/mwifiex/main.h          |  3 ---
 3 files changed, 10 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
index 7ab44cd32a9d..5380fba652cc 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
@@ -118,18 +118,18 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
 		      tbl->win_size;
 
 	for (i = 0; i < pkt_to_send; ++i) {
-		spin_lock_irqsave(&priv->rx_pkt_lock, flags);
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		rx_tmp_ptr = NULL;
 		if (tbl->rx_reorder_ptr[i]) {
 			rx_tmp_ptr = tbl->rx_reorder_ptr[i];
 			tbl->rx_reorder_ptr[i] = NULL;
 		}
-		spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		if (rx_tmp_ptr)
 			mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr);
 	}
 
-	spin_lock_irqsave(&priv->rx_pkt_lock, flags);
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	/*
 	 * We don't have a circular buffer, hence use rotation to simulate
 	 * circular buffer
@@ -140,7 +140,7 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
 	}
 
 	tbl->start_win = start_win;
-	spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 }
 
 /*
@@ -160,18 +160,19 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
 	unsigned long flags;
 
 	for (i = 0; i < tbl->win_size; ++i) {
-		spin_lock_irqsave(&priv->rx_pkt_lock, flags);
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		if (!tbl->rx_reorder_ptr[i]) {
-			spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
+			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
+					       flags);
 			break;
 		}
 		rx_tmp_ptr = tbl->rx_reorder_ptr[i];
 		tbl->rx_reorder_ptr[i] = NULL;
-		spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr);
 	}
 
-	spin_lock_irqsave(&priv->rx_pkt_lock, flags);
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	/*
 	 * We don't have a circular buffer, hence use rotation to simulate
 	 * circular buffer
@@ -184,7 +185,7 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
 		}
 	}
 	tbl->start_win = (tbl->start_win + i) & (MAX_TID_VALUE - 1);
-	spin_unlock_irqrestore(&priv->rx_pkt_lock, flags);
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 }
 
 /*
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index d239e9248c05..dab02d739629 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -439,7 +439,6 @@ int mwifiex_init_lock_list(struct mwifiex_adapter *adapter)
 	for (i = 0; i < adapter->priv_num; i++) {
 		if (adapter->priv[i]) {
 			priv = adapter->priv[i];
-			spin_lock_init(&priv->rx_pkt_lock);
 			spin_lock_init(&priv->wmm.ra_list_spinlock);
 			spin_lock_init(&priv->curr_bcn_buf_lock);
 			spin_lock_init(&priv->sta_list_spinlock);
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 69ac0a22c28c..d2b54beea3b7 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -616,9 +616,6 @@ struct mwifiex_private {
 	struct list_head rx_reorder_tbl_ptr;
 	/* spin lock for rx_reorder_tbl_ptr queue */
 	spinlock_t rx_reorder_tbl_lock;
-	/* spin lock for Rx packets */
-	spinlock_t rx_pkt_lock;
-
 #define MWIFIEX_ASSOC_RSP_BUF_SIZE  500
 	u8 assoc_rsp_buf[MWIFIEX_ASSOC_RSP_BUF_SIZE];
 	u32 assoc_rsp_size;
-- 
cgit v1.2.3


From 5188d5453bc9380ccd4ae1086138dd485d13aef2 Mon Sep 17 00:00:00 2001
From: Ganapathi Bhat <gbhat@marvell.com>
Date: Wed, 27 Jun 2018 11:43:39 +0530
Subject: mwifiex: restructure rx_reorder_tbl_lock usage

Driver must ensure that whenever it holds a pointer to the list
entry mwifiex_rx_reorder_tbl, it must protect the same with
rx_reorder_tbl_lock. At present there are many places where
driver does not ensure this. To cover all cases, spinlocks in
below funcions are moved out and made sure that the caller will
hold the spinlock:
mwifiex_11n_dispatch_pkt_until_start_win()
mwifiex_11n_scan_and_dispatch()
mwifiex_del_rx_reorder_entry()
mwifiex_11n_get_rx_reorder_tbl()
mwifiex_11n_find_last_seq_num()

Signed-off-by: Ganapathi Bhat <gbhat@marvell.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/11n.c         |  5 +-
 .../net/wireless/marvell/mwifiex/11n_rxreorder.c   | 96 +++++++++++-----------
 drivers/net/wireless/marvell/mwifiex/uap_txrx.c    |  3 +
 3 files changed, 53 insertions(+), 51 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c
index 5d75c971004b..e2addd8b878b 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n.c
@@ -696,10 +696,11 @@ void mwifiex_11n_delba(struct mwifiex_private *priv, int tid)
 				"Send delba to tid=%d, %pM\n",
 				tid, rx_reor_tbl_ptr->ta);
 			mwifiex_send_delba(priv, tid, rx_reor_tbl_ptr->ta, 0);
-			goto exit;
+			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
+					       flags);
+			return;
 		}
 	}
-exit:
 	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 }
 
diff --git a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
index 5380fba652cc..8e63d14c1e1c 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n_rxreorder.c
@@ -103,6 +103,8 @@ static int mwifiex_11n_dispatch_pkt(struct mwifiex_private *priv, void *payload)
  * There could be holes in the buffer, which are skipped by the function.
  * Since the buffer is linear, the function uses rotation to simulate
  * circular buffer.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static void
 mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
@@ -111,25 +113,21 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
 {
 	int pkt_to_send, i;
 	void *rx_tmp_ptr;
-	unsigned long flags;
 
 	pkt_to_send = (start_win > tbl->start_win) ?
 		      min((start_win - tbl->start_win), tbl->win_size) :
 		      tbl->win_size;
 
 	for (i = 0; i < pkt_to_send; ++i) {
-		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		rx_tmp_ptr = NULL;
 		if (tbl->rx_reorder_ptr[i]) {
 			rx_tmp_ptr = tbl->rx_reorder_ptr[i];
 			tbl->rx_reorder_ptr[i] = NULL;
 		}
-		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		if (rx_tmp_ptr)
 			mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr);
 	}
 
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	/*
 	 * We don't have a circular buffer, hence use rotation to simulate
 	 * circular buffer
@@ -140,7 +138,6 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
 	}
 
 	tbl->start_win = start_win;
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 }
 
 /*
@@ -150,6 +147,8 @@ mwifiex_11n_dispatch_pkt_until_start_win(struct mwifiex_private *priv,
  * The start window is adjusted automatically when a hole is located.
  * Since the buffer is linear, the function uses rotation to simulate
  * circular buffer.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static void
 mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
@@ -157,22 +156,15 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
 {
 	int i, j, xchg;
 	void *rx_tmp_ptr;
-	unsigned long flags;
 
 	for (i = 0; i < tbl->win_size; ++i) {
-		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-		if (!tbl->rx_reorder_ptr[i]) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       flags);
+		if (!tbl->rx_reorder_ptr[i])
 			break;
-		}
 		rx_tmp_ptr = tbl->rx_reorder_ptr[i];
 		tbl->rx_reorder_ptr[i] = NULL;
-		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		mwifiex_11n_dispatch_pkt(priv, rx_tmp_ptr);
 	}
 
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	/*
 	 * We don't have a circular buffer, hence use rotation to simulate
 	 * circular buffer
@@ -185,7 +177,6 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
 		}
 	}
 	tbl->start_win = (tbl->start_win + i) & (MAX_TID_VALUE - 1);
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 }
 
 /*
@@ -193,6 +184,8 @@ mwifiex_11n_scan_and_dispatch(struct mwifiex_private *priv,
  *
  * The function stops the associated timer and dispatches all the
  * pending packets in the Rx reorder table before deletion.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static void
 mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv,
@@ -218,11 +211,7 @@ mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv,
 
 	del_timer_sync(&tbl->timer_context.timer);
 	tbl->timer_context.timer_is_set = false;
-
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	list_del(&tbl->list);
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
-
 	kfree(tbl->rx_reorder_ptr);
 	kfree(tbl);
 
@@ -235,22 +224,17 @@ mwifiex_del_rx_reorder_entry(struct mwifiex_private *priv,
 /*
  * This function returns the pointer to an entry in Rx reordering
  * table which matches the given TA/TID pair.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 struct mwifiex_rx_reorder_tbl *
 mwifiex_11n_get_rx_reorder_tbl(struct mwifiex_private *priv, int tid, u8 *ta)
 {
 	struct mwifiex_rx_reorder_tbl *tbl;
-	unsigned long flags;
 
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list) {
-		if (!memcmp(tbl->ta, ta, ETH_ALEN) && tbl->tid == tid) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       flags);
+	list_for_each_entry(tbl, &priv->rx_reorder_tbl_ptr, list)
+		if (!memcmp(tbl->ta, ta, ETH_ALEN) && tbl->tid == tid)
 			return tbl;
-		}
-	}
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	return NULL;
 }
@@ -267,14 +251,9 @@ void mwifiex_11n_del_rx_reorder_tbl_by_ta(struct mwifiex_private *priv, u8 *ta)
 		return;
 
 	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	list_for_each_entry_safe(tbl, tmp, &priv->rx_reorder_tbl_ptr, list) {
-		if (!memcmp(tbl->ta, ta, ETH_ALEN)) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       flags);
+	list_for_each_entry_safe(tbl, tmp, &priv->rx_reorder_tbl_ptr, list)
+		if (!memcmp(tbl->ta, ta, ETH_ALEN))
 			mwifiex_del_rx_reorder_entry(priv, tbl);
-			spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-		}
-	}
 	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	return;
@@ -283,24 +262,18 @@ void mwifiex_11n_del_rx_reorder_tbl_by_ta(struct mwifiex_private *priv, u8 *ta)
 /*
  * This function finds the last sequence number used in the packets
  * buffered in Rx reordering table.
+ *
+ * The caller must hold rx_reorder_tbl_lock spinlock.
  */
 static int
 mwifiex_11n_find_last_seq_num(struct reorder_tmr_cnxt *ctx)
 {
 	struct mwifiex_rx_reorder_tbl *rx_reorder_tbl_ptr = ctx->ptr;
-	struct mwifiex_private *priv = ctx->priv;
-	unsigned long flags;
 	int i;
 
-	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	for (i = rx_reorder_tbl_ptr->win_size - 1; i >= 0; --i) {
-		if (rx_reorder_tbl_ptr->rx_reorder_ptr[i]) {
-			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
-					       flags);
+	for (i = rx_reorder_tbl_ptr->win_size - 1; i >= 0; --i)
+		if (rx_reorder_tbl_ptr->rx_reorder_ptr[i])
 			return i;
-		}
-	}
-	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	return -1;
 }
@@ -318,17 +291,22 @@ mwifiex_flush_data(struct timer_list *t)
 	struct reorder_tmr_cnxt *ctx =
 		from_timer(ctx, t, timer);
 	int start_win, seq_num;
+	unsigned long flags;
 
 	ctx->timer_is_set = false;
+	spin_lock_irqsave(&ctx->priv->rx_reorder_tbl_lock, flags);
 	seq_num = mwifiex_11n_find_last_seq_num(ctx);
 
-	if (seq_num < 0)
+	if (seq_num < 0) {
+		spin_unlock_irqrestore(&ctx->priv->rx_reorder_tbl_lock, flags);
 		return;
+	}
 
 	mwifiex_dbg(ctx->priv->adapter, INFO, "info: flush data %d\n", seq_num);
 	start_win = (ctx->ptr->start_win + seq_num + 1) & (MAX_TID_VALUE - 1);
 	mwifiex_11n_dispatch_pkt_until_start_win(ctx->priv, ctx->ptr,
 						 start_win);
+	spin_unlock_irqrestore(&ctx->priv->rx_reorder_tbl_lock, flags);
 }
 
 /*
@@ -355,11 +333,14 @@ mwifiex_11n_create_rx_reorder_tbl(struct mwifiex_private *priv, u8 *ta,
 	 * If we get a TID, ta pair which is already present dispatch all the
 	 * the packets and move the window size until the ssn
 	 */
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, ta);
 	if (tbl) {
 		mwifiex_11n_dispatch_pkt_until_start_win(priv, tbl, seq_num);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		return;
 	}
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 	/* if !tbl then create one */
 	new_node = kzalloc(sizeof(struct mwifiex_rx_reorder_tbl), GFP_KERNEL);
 	if (!new_node)
@@ -570,16 +551,20 @@ int mwifiex_11n_rx_reorder_pkt(struct mwifiex_private *priv,
 	int prev_start_win, start_win, end_win, win_size;
 	u16 pkt_index;
 	bool init_window_shift = false;
+	unsigned long flags;
 	int ret = 0;
 
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid, ta);
 	if (!tbl) {
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		if (pkt_type != PKT_TYPE_BAR)
 			mwifiex_11n_dispatch_pkt(priv, payload);
 		return ret;
 	}
 
 	if ((pkt_type == PKT_TYPE_AMSDU) && !tbl->amsdu) {
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		mwifiex_11n_dispatch_pkt(priv, payload);
 		return ret;
 	}
@@ -666,6 +651,8 @@ done:
 	if (!tbl->timer_context.timer_is_set ||
 	    prev_start_win != tbl->start_win)
 		mwifiex_11n_rxreorder_timer_restart(tbl);
+
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 	return ret;
 }
 
@@ -694,14 +681,18 @@ mwifiex_del_ba_tbl(struct mwifiex_private *priv, int tid, u8 *peer_mac,
 		    peer_mac, tid, initiator);
 
 	if (cleanup_rx_reorder_tbl) {
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid,
 								 peer_mac);
 		if (!tbl) {
+			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
+					       flags);
 			mwifiex_dbg(priv->adapter, EVENT,
 				    "event: TID, TA not found in table\n");
 			return;
 		}
 		mwifiex_del_rx_reorder_entry(priv, tbl);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 	} else {
 		ptx_tbl = mwifiex_get_ba_tbl(priv, tid, peer_mac);
 		if (!ptx_tbl) {
@@ -735,6 +726,7 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv,
 	int tid, win_size;
 	struct mwifiex_rx_reorder_tbl *tbl;
 	uint16_t block_ack_param_set;
+	unsigned long flags;
 
 	block_ack_param_set = le16_to_cpu(add_ba_rsp->block_ack_param_set);
 
@@ -748,17 +740,20 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv,
 		mwifiex_dbg(priv->adapter, ERROR, "ADDBA RSP: failed %pM tid=%d)\n",
 			    add_ba_rsp->peer_mac_addr, tid);
 
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid,
 						     add_ba_rsp->peer_mac_addr);
 		if (tbl)
 			mwifiex_del_rx_reorder_entry(priv, tbl);
 
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		return 0;
 	}
 
 	win_size = (block_ack_param_set & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK)
 		    >> BLOCKACKPARAM_WINSIZE_POS;
 
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	tbl = mwifiex_11n_get_rx_reorder_tbl(priv, tid,
 					     add_ba_rsp->peer_mac_addr);
 	if (tbl) {
@@ -769,6 +764,7 @@ int mwifiex_ret_11n_addba_resp(struct mwifiex_private *priv,
 		else
 			tbl->amsdu = false;
 	}
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	mwifiex_dbg(priv->adapter, CMD,
 		    "cmd: ADDBA RSP: %pM tid=%d ssn=%d win_size=%d\n",
@@ -808,11 +804,8 @@ void mwifiex_11n_cleanup_reorder_tbl(struct mwifiex_private *priv)
 
 	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	list_for_each_entry_safe(del_tbl_ptr, tmp_node,
-				 &priv->rx_reorder_tbl_ptr, list) {
-		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
+				 &priv->rx_reorder_tbl_ptr, list)
 		mwifiex_del_rx_reorder_entry(priv, del_tbl_ptr);
-		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
-	}
 	INIT_LIST_HEAD(&priv->rx_reorder_tbl_ptr);
 	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
@@ -936,6 +929,7 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv,
 	int tlv_buf_left = len;
 	int ret;
 	u8 *tmp;
+	unsigned long flags;
 
 	mwifiex_dbg_dump(priv->adapter, EVT_D, "RXBA_SYNC event:",
 			 event_buf, len);
@@ -955,14 +949,18 @@ void mwifiex_11n_rxba_sync_event(struct mwifiex_private *priv,
 			    tlv_rxba->mac, tlv_rxba->tid, tlv_seq_num,
 			    tlv_bitmap_len);
 
+		spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 		rx_reor_tbl_ptr =
 			mwifiex_11n_get_rx_reorder_tbl(priv, tlv_rxba->tid,
 						       tlv_rxba->mac);
 		if (!rx_reor_tbl_ptr) {
+			spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock,
+					       flags);
 			mwifiex_dbg(priv->adapter, ERROR,
 				    "Can not find rx_reorder_tbl!");
 			return;
 		}
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 		for (i = 0; i < tlv_bitmap_len; i++) {
 			for (j = 0 ; j < 8; j++) {
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
index 5ce85d5727e4..a83c5afc256a 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_txrx.c
@@ -421,12 +421,15 @@ int mwifiex_process_uap_rx_packet(struct mwifiex_private *priv,
 		spin_unlock_irqrestore(&priv->sta_list_spinlock, flags);
 	}
 
+	spin_lock_irqsave(&priv->rx_reorder_tbl_lock, flags);
 	if (!priv->ap_11n_enabled ||
 	    (!mwifiex_11n_get_rx_reorder_tbl(priv, uap_rx_pd->priority, ta) &&
 	    (le16_to_cpu(uap_rx_pd->rx_pkt_type) != PKT_TYPE_AMSDU))) {
 		ret = mwifiex_handle_uap_rx_forward(priv, skb);
+		spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 		return ret;
 	}
+	spin_unlock_irqrestore(&priv->rx_reorder_tbl_lock, flags);
 
 	/* Reorder and send to kernel */
 	pkt_type = (u8)le16_to_cpu(uap_rx_pd->rx_pkt_type);
-- 
cgit v1.2.3


From fc3a2fcaa1ba9b28f691a9977371d97fb33b8461 Mon Sep 17 00:00:00 2001
From: Ganapathi Bhat <gbhat@marvell.com>
Date: Fri, 13 Jul 2018 17:56:35 +0530
Subject: mwifiex: use atomic bitops to represent adapter status variables

Driver is using boolean variables to maintain vairous status
information of adapter. These status variables are accessed by
multiple threads and there is a possibility of a race. To avoid
this, convert these variables to a set of bitops flags, to be
operated atomically.

Below variables of mwifiex_adapter are converted to bitop flags:
surprise_removed
is_cmd_timedout
is_suspended
is_hs_configured
hs_enabling

Signed-off-by: Ganapathi Bhat <gbhat@marvell.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/cfg80211.c  |  3 ++-
 drivers/net/wireless/marvell/mwifiex/cmdevt.c    | 34 +++++++++++++-----------
 drivers/net/wireless/marvell/mwifiex/debugfs.c   |  2 +-
 drivers/net/wireless/marvell/mwifiex/init.c      |  4 +--
 drivers/net/wireless/marvell/mwifiex/main.c      | 33 ++++++++++++-----------
 drivers/net/wireless/marvell/mwifiex/main.h      | 14 ++++++----
 drivers/net/wireless/marvell/mwifiex/pcie.c      | 12 ++++-----
 drivers/net/wireless/marvell/mwifiex/scan.c      |  3 ++-
 drivers/net/wireless/marvell/mwifiex/sdio.c      | 12 ++++-----
 drivers/net/wireless/marvell/mwifiex/sta_event.c |  3 ++-
 drivers/net/wireless/marvell/mwifiex/sta_ioctl.c |  8 +++---
 drivers/net/wireless/marvell/mwifiex/sta_tx.c    |  2 +-
 drivers/net/wireless/marvell/mwifiex/usb.c       | 25 ++++++++---------
 drivers/net/wireless/marvell/mwifiex/util.c      |  6 +++--
 drivers/net/wireless/marvell/mwifiex/wmm.c       |  2 +-
 15 files changed, 91 insertions(+), 72 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
index c02e02c17c9c..adc88433faa8 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
@@ -2322,7 +2322,8 @@ mwifiex_cfg80211_connect(struct wiphy *wiphy, struct net_device *dev,
 	if (priv->scan_block)
 		priv->scan_block = false;
 
-	if (adapter->surprise_removed || adapter->is_cmd_timedout) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags) ||
+	    test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: Ignore connection.\t"
 			    "Card removed or FW in bad state\n",
diff --git a/drivers/net/wireless/marvell/mwifiex/cmdevt.c b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
index 9cfcdf6bec52..60db2b969e20 100644
--- a/drivers/net/wireless/marvell/mwifiex/cmdevt.c
+++ b/drivers/net/wireless/marvell/mwifiex/cmdevt.c
@@ -372,7 +372,7 @@ static int mwifiex_dnld_sleep_confirm_cmd(struct mwifiex_adapter *adapter)
 		adapter->ps_state = PS_STATE_SLEEP_CFM;
 
 	if (!le16_to_cpu(sleep_cfm_buf->resp_ctrl) &&
-	    (adapter->is_hs_configured &&
+	    (test_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags) &&
 	     !adapter->sleep_period.period)) {
 		adapter->pm_wakeup_card_req = true;
 		mwifiex_hs_activated_event(mwifiex_get_priv
@@ -564,25 +564,26 @@ int mwifiex_send_cmd(struct mwifiex_private *priv, u16 cmd_no,
 		return -1;
 	}
 
-	if (adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: device in suspended state\n");
 		return -1;
 	}
 
-	if (adapter->hs_enabling && cmd_no != HostCmd_CMD_802_11_HS_CFG_ENH) {
+	if (test_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags) &&
+	    cmd_no != HostCmd_CMD_802_11_HS_CFG_ENH) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: host entering sleep state\n");
 		return -1;
 	}
 
-	if (adapter->surprise_removed) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: card is removed\n");
 		return -1;
 	}
 
-	if (adapter->is_cmd_timedout) {
+	if (test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "PREP_CMD: FW is in bad state\n");
 		return -1;
@@ -789,7 +790,8 @@ int mwifiex_exec_next_cmd(struct mwifiex_adapter *adapter)
 	if (priv && (host_cmd->command !=
 	     cpu_to_le16(HostCmd_CMD_802_11_HS_CFG_ENH))) {
 		if (adapter->hs_activated) {
-			adapter->is_hs_configured = false;
+			clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+				  &adapter->work_flags);
 			mwifiex_hs_activated_event(priv, false);
 		}
 	}
@@ -825,7 +827,7 @@ int mwifiex_process_cmdresp(struct mwifiex_adapter *adapter)
 		return -1;
 	}
 
-	adapter->is_cmd_timedout = 0;
+	clear_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags);
 
 	resp = (struct host_cmd_ds_command *) adapter->curr_cmd->resp_skb->data;
 	if (adapter->curr_cmd->cmd_flag & CMD_F_HOSTCMD) {
@@ -927,7 +929,7 @@ mwifiex_cmd_timeout_func(struct timer_list *t)
 	struct mwifiex_adapter *adapter = from_timer(adapter, t, cmd_timer);
 	struct cmd_ctrl_node *cmd_node;
 
-	adapter->is_cmd_timedout = 1;
+	set_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags);
 	if (!adapter->curr_cmd) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: empty curr_cmd\n");
@@ -953,7 +955,8 @@ mwifiex_cmd_timeout_func(struct timer_list *t)
 
 		mwifiex_dbg(adapter, MSG,
 			    "is_cmd_timedout = %d\n",
-			    adapter->is_cmd_timedout);
+			    test_bit(MWIFIEX_IS_CMD_TIMEDOUT,
+				     &adapter->work_flags));
 		mwifiex_dbg(adapter, MSG,
 			    "num_tx_timeout = %d\n",
 			    adapter->dbg.num_tx_timeout);
@@ -1135,7 +1138,8 @@ void
 mwifiex_hs_activated_event(struct mwifiex_private *priv, u8 activated)
 {
 	if (activated) {
-		if (priv->adapter->is_hs_configured) {
+		if (test_bit(MWIFIEX_IS_HS_CONFIGURED,
+			     &priv->adapter->work_flags)) {
 			priv->adapter->hs_activated = true;
 			mwifiex_update_rxreor_flags(priv->adapter,
 						    RXREOR_FORCE_NO_DROP);
@@ -1186,11 +1190,11 @@ int mwifiex_ret_802_11_hs_cfg(struct mwifiex_private *priv,
 			    phs_cfg->params.hs_config.gap);
 	}
 	if (conditions != HS_CFG_CANCEL) {
-		adapter->is_hs_configured = true;
+		set_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 		if (adapter->iface_type == MWIFIEX_USB)
 			mwifiex_hs_activated_event(priv, true);
 	} else {
-		adapter->is_hs_configured = false;
+		clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 		if (adapter->hs_activated)
 			mwifiex_hs_activated_event(priv, false);
 	}
@@ -1212,8 +1216,8 @@ mwifiex_process_hs_config(struct mwifiex_adapter *adapter)
 
 	adapter->if_ops.wakeup(adapter);
 	adapter->hs_activated = false;
-	adapter->is_hs_configured = false;
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	mwifiex_hs_activated_event(mwifiex_get_priv(adapter,
 						    MWIFIEX_BSS_ROLE_ANY),
 				   false);
@@ -1273,7 +1277,7 @@ mwifiex_process_sleep_confirm_resp(struct mwifiex_adapter *adapter,
 		return;
 	}
 	adapter->pm_wakeup_card_req = true;
-	if (adapter->is_hs_configured)
+	if (test_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags))
 		mwifiex_hs_activated_event(mwifiex_get_priv
 						(adapter, MWIFIEX_BSS_ROLE_ANY),
 					   true);
diff --git a/drivers/net/wireless/marvell/mwifiex/debugfs.c b/drivers/net/wireless/marvell/mwifiex/debugfs.c
index 07453932f703..cce70252fd96 100644
--- a/drivers/net/wireless/marvell/mwifiex/debugfs.c
+++ b/drivers/net/wireless/marvell/mwifiex/debugfs.c
@@ -813,7 +813,7 @@ mwifiex_hscfg_write(struct file *file, const char __user *ubuf,
 			      MWIFIEX_SYNC_CMD, &hscfg);
 
 	mwifiex_enable_hs(priv->adapter);
-	priv->adapter->hs_enabling = false;
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &priv->adapter->work_flags);
 	ret = count;
 done:
 	kfree(buf);
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c
index dab02d739629..673e89dff0b5 100644
--- a/drivers/net/wireless/marvell/mwifiex/init.c
+++ b/drivers/net/wireless/marvell/mwifiex/init.c
@@ -233,7 +233,7 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter)
 	adapter->event_received = false;
 	adapter->data_received = false;
 
-	adapter->surprise_removed = false;
+	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
 
@@ -270,7 +270,7 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter)
 
 	adapter->curr_tx_buf_size = MWIFIEX_TX_DATA_BUF_SIZE_2K;
 
-	adapter->is_hs_configured = false;
+	clear_bit(MWIFIEX_IS_HS_CONFIGURED, &adapter->work_flags);
 	adapter->hs_cfg.conditions = cpu_to_le32(HS_CFG_COND_DEF);
 	adapter->hs_cfg.gpio = HS_CFG_GPIO_DEF;
 	adapter->hs_cfg.gap = HS_CFG_GAP_DEF;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index fa3e8ddfe9a9..20cee5c397fb 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -404,7 +404,8 @@ process_start:
 		    !skb_queue_empty(&adapter->tx_data_q)) {
 			mwifiex_process_tx_queue(adapter);
 			if (adapter->hs_activated) {
-				adapter->is_hs_configured = false;
+				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 				mwifiex_hs_activated_event
 					(mwifiex_get_priv
 					(adapter, MWIFIEX_BSS_ROLE_ANY),
@@ -420,7 +421,8 @@ process_start:
 			(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA))) {
 			mwifiex_process_bypass_tx(adapter);
 			if (adapter->hs_activated) {
-				adapter->is_hs_configured = false;
+				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 				mwifiex_hs_activated_event
 					(mwifiex_get_priv
 					 (adapter, MWIFIEX_BSS_ROLE_ANY),
@@ -435,7 +437,8 @@ process_start:
 			(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA))) {
 			mwifiex_wmm_process_tx(adapter);
 			if (adapter->hs_activated) {
-				adapter->is_hs_configured = false;
+				clear_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 				mwifiex_hs_activated_event
 					(mwifiex_get_priv
 					 (adapter, MWIFIEX_BSS_ROLE_ANY),
@@ -647,7 +650,7 @@ err_dnld_fw:
 	if (adapter->if_ops.unregister_dev)
 		adapter->if_ops.unregister_dev(adapter);
 
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 
 	if (adapter->hw_status == MWIFIEX_HW_STATUS_READY) {
@@ -870,7 +873,7 @@ mwifiex_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		    "data: %lu BSS(%d-%d): Data <= kernel\n",
 		    jiffies, priv->bss_type, priv->bss_num);
 
-	if (priv->adapter->surprise_removed) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &priv->adapter->work_flags)) {
 		kfree_skb(skb);
 		priv->stats.tx_dropped++;
 		return 0;
@@ -1372,7 +1375,7 @@ static void mwifiex_rx_work_queue(struct work_struct *work)
 	struct mwifiex_adapter *adapter =
 		container_of(work, struct mwifiex_adapter, rx_work);
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		return;
 	mwifiex_process_rx(adapter);
 }
@@ -1388,7 +1391,7 @@ static void mwifiex_main_work_queue(struct work_struct *work)
 	struct mwifiex_adapter *adapter =
 		container_of(work, struct mwifiex_adapter, main_work);
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		return;
 	mwifiex_main_process(adapter);
 }
@@ -1405,7 +1408,7 @@ static void mwifiex_uninit_sw(struct mwifiex_adapter *adapter)
 	if (adapter->if_ops.disable_int)
 		adapter->if_ops.disable_int(adapter);
 
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 	adapter->int_status = 0;
 
@@ -1493,11 +1496,11 @@ mwifiex_reinit_sw(struct mwifiex_adapter *adapter)
 		adapter->if_ops.up_dev(adapter);
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
-	adapter->surprise_removed = false;
+	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	init_waitqueue_head(&adapter->init_wait_q);
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	adapter->hs_activated = false;
-	adapter->is_cmd_timedout = 0;
+	clear_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags);
 	init_waitqueue_head(&adapter->hs_activate_wait_q);
 	init_waitqueue_head(&adapter->cmd_wait_q.wait);
 	adapter->cmd_wait_q.status = 0;
@@ -1552,7 +1555,7 @@ err_init_fw:
 		adapter->if_ops.unregister_dev(adapter);
 
 err_kmalloc:
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 	if (adapter->hw_status == MWIFIEX_HW_STATUS_READY) {
 		mwifiex_dbg(adapter, ERROR,
@@ -1649,9 +1652,9 @@ mwifiex_add_card(void *card, struct completion *fw_done,
 	adapter->fw_done = fw_done;
 
 	adapter->hw_status = MWIFIEX_HW_STATUS_INITIALIZING;
-	adapter->surprise_removed = false;
+	clear_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	init_waitqueue_head(&adapter->init_wait_q);
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 	adapter->hs_activated = false;
 	init_waitqueue_head(&adapter->hs_activate_wait_q);
 	init_waitqueue_head(&adapter->cmd_wait_q.wait);
@@ -1699,7 +1702,7 @@ err_init_fw:
 	if (adapter->if_ops.unregister_dev)
 		adapter->if_ops.unregister_dev(adapter);
 err_registerdev:
-	adapter->surprise_removed = true;
+	set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 	mwifiex_terminate_workqueue(adapter);
 	if (adapter->hw_status == MWIFIEX_HW_STATUS_READY) {
 		pr_debug("info: %s: shutdown mwifiex\n", __func__);
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index d2b54beea3b7..b025ba164412 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -517,6 +517,14 @@ enum mwifiex_iface_work_flags {
 	MWIFIEX_IFACE_WORK_CARD_RESET,
 };
 
+enum mwifiex_adapter_work_flags {
+	MWIFIEX_SURPRISE_REMOVED,
+	MWIFIEX_IS_CMD_TIMEDOUT,
+	MWIFIEX_IS_SUSPENDED,
+	MWIFIEX_IS_HS_CONFIGURED,
+	MWIFIEX_IS_HS_ENABLING,
+};
+
 struct mwifiex_band_config {
 	u8 chan_band:2;
 	u8 chan_width:2;
@@ -872,7 +880,7 @@ struct mwifiex_adapter {
 	struct device *dev;
 	struct wiphy *wiphy;
 	u8 perm_addr[ETH_ALEN];
-	bool surprise_removed;
+	unsigned long work_flags;
 	u32 fw_release_number;
 	u8 intf_hdr_len;
 	u16 init_wait_q_woken;
@@ -926,7 +934,6 @@ struct mwifiex_adapter {
 	struct cmd_ctrl_node *curr_cmd;
 	/* spin lock for command */
 	spinlock_t mwifiex_cmd_lock;
-	u8 is_cmd_timedout;
 	u16 last_init_cmd;
 	struct timer_list cmd_timer;
 	struct list_head cmd_free_q;
@@ -976,13 +983,10 @@ struct mwifiex_adapter {
 	u16 pps_uapsd_mode;
 	u32 pm_wakeup_fw_try;
 	struct timer_list wakeup_timer;
-	u8 is_hs_configured;
 	struct mwifiex_hs_config_param hs_cfg;
 	u8 hs_activated;
 	u16 hs_activate_wait_q_woken;
 	wait_queue_head_t hs_activate_wait_q;
-	bool is_suspended;
-	bool hs_enabling;
 	u8 event_body[MAX_EVENT_SIZE];
 	u32 hw_dot_11n_dev_cap;
 	u8 hw_dev_mcs_support;
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index 0c42b7296ddd..3fe81b2a929a 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -170,7 +170,7 @@ static int mwifiex_pcie_suspend(struct device *dev)
 	if (!mwifiex_enable_hs(adapter)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: failed to suspend\n");
-		adapter->hs_enabling = false;
+		clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 		mwifiex_disable_wake(adapter);
 		return -EFAULT;
 	}
@@ -178,8 +178,8 @@ static int mwifiex_pcie_suspend(struct device *dev)
 	flush_workqueue(adapter->workqueue);
 
 	/* Indicate device suspended */
-	adapter->is_suspended = true;
-	adapter->hs_enabling = false;
+	set_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 
 	return 0;
 }
@@ -207,13 +207,13 @@ static int mwifiex_pcie_resume(struct device *dev)
 
 	adapter = card->adapter;
 
-	if (!adapter->is_suspended) {
+	if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, WARN,
 			    "Device already resumed\n");
 		return 0;
 	}
 
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 
 	mwifiex_cancel_hs(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA),
 			  MWIFIEX_ASYNC_CMD);
@@ -2430,7 +2430,7 @@ static irqreturn_t mwifiex_pcie_interrupt(int irq, void *context)
 	}
 	adapter = card->adapter;
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		goto exit;
 
 	if (card->msix_enable)
diff --git a/drivers/net/wireless/marvell/mwifiex/scan.c b/drivers/net/wireless/marvell/mwifiex/scan.c
index 895b806cdb03..8e483b0bc3b1 100644
--- a/drivers/net/wireless/marvell/mwifiex/scan.c
+++ b/drivers/net/wireless/marvell/mwifiex/scan.c
@@ -1495,7 +1495,8 @@ int mwifiex_scan_networks(struct mwifiex_private *priv,
 		return -EBUSY;
 	}
 
-	if (adapter->surprise_removed || adapter->is_cmd_timedout) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags) ||
+	    test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "Ignore scan. Card removed or firmware in bad state\n");
 		return -EFAULT;
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index dfdcbc4f141a..d49fbd58afa7 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -181,13 +181,13 @@ static int mwifiex_sdio_resume(struct device *dev)
 
 	adapter = card->adapter;
 
-	if (!adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, WARN,
 			    "device already resumed\n");
 		return 0;
 	}
 
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 
 	/* Disable Host Sleep */
 	mwifiex_cancel_hs(mwifiex_get_priv(adapter, MWIFIEX_BSS_ROLE_STA),
@@ -260,7 +260,7 @@ mwifiex_write_data_sync(struct mwifiex_adapter *adapter,
 				MWIFIEX_SDIO_BLOCK_SIZE) : pkt_len;
 	u32 ioport = (port & MWIFIEX_SDIO_IO_PORT_MASK);
 
-	if (adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: not allowed while suspended\n", __func__);
 		return -1;
@@ -450,7 +450,7 @@ static int mwifiex_sdio_suspend(struct device *dev)
 	if (!mwifiex_enable_hs(adapter)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: failed to suspend\n");
-		adapter->hs_enabling = false;
+		clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 		mwifiex_disable_wake(adapter);
 		return -EFAULT;
 	}
@@ -460,8 +460,8 @@ static int mwifiex_sdio_suspend(struct device *dev)
 	ret = sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER);
 
 	/* Indicate device suspended */
-	adapter->is_suspended = true;
-	adapter->hs_enabling = false;
+	set_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 
 	return ret;
 }
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c
index 03a6492662ca..a327fc5b36e3 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c
@@ -224,7 +224,8 @@ void mwifiex_reset_connect_state(struct mwifiex_private *priv, u16 reason_code,
 	adapter->tx_lock_flag = false;
 	adapter->pps_uapsd_mode = false;
 
-	if (adapter->is_cmd_timedout && adapter->curr_cmd)
+	if (test_bit(MWIFIEX_IS_CMD_TIMEDOUT, &adapter->work_flags) &&
+	    adapter->curr_cmd)
 		return;
 	priv->media_connected = false;
 	mwifiex_dbg(adapter, MSG,
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
index 5414b755cf82..b454b5f85503 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_ioctl.c
@@ -419,7 +419,8 @@ int mwifiex_set_hs_params(struct mwifiex_private *priv, u16 action,
 		}
 		if (hs_cfg->is_invoke_hostcmd) {
 			if (hs_cfg->conditions == HS_CFG_CANCEL) {
-				if (!adapter->is_hs_configured)
+				if (!test_bit(MWIFIEX_IS_HS_CONFIGURED,
+					      &adapter->work_flags))
 					/* Already cancelled */
 					break;
 				/* Save previous condition */
@@ -535,7 +536,7 @@ int mwifiex_enable_hs(struct mwifiex_adapter *adapter)
 	memset(&hscfg, 0, sizeof(hscfg));
 	hscfg.is_invoke_hostcmd = true;
 
-	adapter->hs_enabling = true;
+	set_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 	mwifiex_cancel_all_pending_cmd(adapter);
 
 	if (mwifiex_set_hs_params(mwifiex_get_priv(adapter,
@@ -601,7 +602,8 @@ int mwifiex_get_bss_info(struct mwifiex_private *priv,
 	else
 		info->wep_status = false;
 
-	info->is_hs_configured = adapter->is_hs_configured;
+	info->is_hs_configured = test_bit(MWIFIEX_IS_HS_CONFIGURED,
+					  &adapter->work_flags);
 	info->is_deep_sleep = adapter->is_deep_sleep;
 
 	return 0;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_tx.c b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
index 620f8650a742..37c24b95e642 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_tx.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_tx.c
@@ -143,7 +143,7 @@ int mwifiex_send_null_packet(struct mwifiex_private *priv, u8 flags)
 	int ret;
 	struct mwifiex_txinfo *tx_info = NULL;
 
-	if (adapter->surprise_removed)
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags))
 		return -1;
 
 	if (!priv->media_connected)
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index 88f4c89f89ba..433c6a16870b 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -181,7 +181,8 @@ static void mwifiex_usb_rx_complete(struct urb *urb)
 		atomic_dec(&card->rx_data_urb_pending);
 
 	if (recv_length) {
-		if (urb->status || (adapter->surprise_removed)) {
+		if (urb->status ||
+		    test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags)) {
 			mwifiex_dbg(adapter, ERROR,
 				    "URB status is failed: %d\n", urb->status);
 			/* Do not free skb in case of command ep */
@@ -218,10 +219,10 @@ static void mwifiex_usb_rx_complete(struct urb *urb)
 				dev_kfree_skb_any(skb);
 		}
 	} else if (urb->status) {
-		if (!adapter->is_suspended) {
+		if (!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 			mwifiex_dbg(adapter, FATAL,
 				    "Card is removed: %d\n", urb->status);
-			adapter->surprise_removed = true;
+			set_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags);
 		}
 		dev_kfree_skb_any(skb);
 		return;
@@ -529,7 +530,7 @@ static int mwifiex_usb_suspend(struct usb_interface *intf, pm_message_t message)
 		return 0;
 	}
 
-	if (unlikely(adapter->is_suspended))
+	if (unlikely(test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)))
 		mwifiex_dbg(adapter, WARN,
 			    "Device already suspended\n");
 
@@ -537,19 +538,19 @@ static int mwifiex_usb_suspend(struct usb_interface *intf, pm_message_t message)
 	if (!mwifiex_enable_hs(adapter)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "cmd: failed to suspend\n");
-		adapter->hs_enabling = false;
+		clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 		return -EFAULT;
 	}
 
 
-	/* 'is_suspended' flag indicates device is suspended.
+	/* 'MWIFIEX_IS_SUSPENDED' bit indicates device is suspended.
 	 * It must be set here before the usb_kill_urb() calls. Reason
 	 * is in the complete handlers, urb->status(= -ENOENT) and
 	 * this flag is used in combination to distinguish between a
 	 * 'suspended' state and a 'disconnect' one.
 	 */
-	adapter->is_suspended = true;
-	adapter->hs_enabling = false;
+	set_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
+	clear_bit(MWIFIEX_IS_HS_ENABLING, &adapter->work_flags);
 
 	if (atomic_read(&card->rx_cmd_urb_pending) && card->rx_cmd.urb)
 		usb_kill_urb(card->rx_cmd.urb);
@@ -593,7 +594,7 @@ static int mwifiex_usb_resume(struct usb_interface *intf)
 	}
 	adapter = card->adapter;
 
-	if (unlikely(!adapter->is_suspended)) {
+	if (unlikely(!test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags))) {
 		mwifiex_dbg(adapter, WARN,
 			    "Device already resumed\n");
 		return 0;
@@ -602,7 +603,7 @@ static int mwifiex_usb_resume(struct usb_interface *intf)
 	/* Indicate device resumed. The netdev queue will be resumed only
 	 * after the urbs have been re-submitted
 	 */
-	adapter->is_suspended = false;
+	clear_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags);
 
 	if (!atomic_read(&card->rx_data_urb_pending))
 		for (i = 0; i < MWIFIEX_RX_DATA_URB; i++)
@@ -1158,13 +1159,13 @@ static int mwifiex_usb_host_to_card(struct mwifiex_adapter *adapter, u8 ep,
 	unsigned long flags;
 	int idx, ret;
 
-	if (adapter->is_suspended) {
+	if (test_bit(MWIFIEX_IS_SUSPENDED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR,
 			    "%s: not allowed while suspended\n", __func__);
 		return -1;
 	}
 
-	if (adapter->surprise_removed) {
+	if (test_bit(MWIFIEX_SURPRISE_REMOVED, &adapter->work_flags)) {
 		mwifiex_dbg(adapter, ERROR, "%s: device removed\n", __func__);
 		return -1;
 	}
diff --git a/drivers/net/wireless/marvell/mwifiex/util.c b/drivers/net/wireless/marvell/mwifiex/util.c
index 6dd212898117..f9b71539d33e 100644
--- a/drivers/net/wireless/marvell/mwifiex/util.c
+++ b/drivers/net/wireless/marvell/mwifiex/util.c
@@ -197,9 +197,11 @@ int mwifiex_get_debug_info(struct mwifiex_private *priv,
 		info->is_deep_sleep = adapter->is_deep_sleep;
 		info->pm_wakeup_card_req = adapter->pm_wakeup_card_req;
 		info->pm_wakeup_fw_try = adapter->pm_wakeup_fw_try;
-		info->is_hs_configured = adapter->is_hs_configured;
+		info->is_hs_configured = test_bit(MWIFIEX_IS_HS_CONFIGURED,
+						  &adapter->work_flags);
 		info->hs_activated = adapter->hs_activated;
-		info->is_cmd_timedout = adapter->is_cmd_timedout;
+		info->is_cmd_timedout = test_bit(MWIFIEX_IS_CMD_TIMEDOUT,
+						 &adapter->work_flags);
 		info->num_cmd_host_to_card_failure
 				= adapter->dbg.num_cmd_host_to_card_failure;
 		info->num_cmd_sleep_cfm_host_to_card_failure
diff --git a/drivers/net/wireless/marvell/mwifiex/wmm.c b/drivers/net/wireless/marvell/mwifiex/wmm.c
index 936a0a841af8..407b9932ca4d 100644
--- a/drivers/net/wireless/marvell/mwifiex/wmm.c
+++ b/drivers/net/wireless/marvell/mwifiex/wmm.c
@@ -599,7 +599,7 @@ mwifiex_clean_txrx(struct mwifiex_private *priv)
 	memcpy(tos_to_tid, ac_to_tid, sizeof(tos_to_tid));
 
 	if (priv->adapter->if_ops.clean_pcie_ring &&
-	    !priv->adapter->surprise_removed)
+	    !test_bit(MWIFIEX_SURPRISE_REMOVED, &priv->adapter->work_flags))
 		priv->adapter->if_ops.clean_pcie_ring(priv->adapter);
 	spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags);
 
-- 
cgit v1.2.3


From bfc83ea196ad3e201eae7d156d1a95c403079b85 Mon Sep 17 00:00:00 2001
From: Roman Stratiienko <roman.stratiienko@globallogic.com>
Date: Tue, 24 Jul 2018 14:47:27 +0300
Subject: mwifiex: Fix skipped vendor specific IEs

Mwifiex firmware inserts only Microsoft information element
Allow other vendor specific IEs to pass from userspace

Signed-off-by: Roman Stratiienko <roman.stratiienko@globallogic.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/marvell/mwifiex/ie.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/ie.c b/drivers/net/wireless/marvell/mwifiex/ie.c
index b10baacb51c9..75cbd609d606 100644
--- a/drivers/net/wireless/marvell/mwifiex/ie.c
+++ b/drivers/net/wireless/marvell/mwifiex/ie.c
@@ -355,8 +355,14 @@ static int mwifiex_uap_parse_tail_ies(struct mwifiex_private *priv,
 		case WLAN_EID_HT_OPERATION:
 		case WLAN_EID_VHT_CAPABILITY:
 		case WLAN_EID_VHT_OPERATION:
-		case WLAN_EID_VENDOR_SPECIFIC:
 			break;
+		case WLAN_EID_VENDOR_SPECIFIC:
+			/* Skip only Microsoft WMM IE */
+			if (cfg80211_find_vendor_ie(WLAN_OUI_MICROSOFT,
+						    WLAN_OUI_TYPE_MICROSOFT_WMM,
+						    (const u8 *)hdr,
+						    hdr->len + sizeof(struct ieee_types_header)))
+				break;
 		default:
 			memcpy(gen_ie->ie_buffer + ie_len, hdr,
 			       hdr->len + sizeof(struct ieee_types_header));
-- 
cgit v1.2.3


From 92e9712381383dd244a447b9e96a8065faaf3570 Mon Sep 17 00:00:00 2001
From: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Date: Thu, 5 Jul 2018 18:08:19 +0530
Subject: rsi: fix for low throughput issue

observed low throughput rates during verification. This is because, QoS
enable flag is overridden by sequence number in the data descriptor frame.
Hence, added the fix for same.

Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Sushant Kumar Mishra <sushant.mishra@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_hal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 0761e61591bd..533d9e964430 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -246,7 +246,7 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 		}
 	}
 
-	data_desc->mac_flags = cpu_to_le16(seq_num & 0xfff);
+	data_desc->mac_flags |= cpu_to_le16(seq_num & 0xfff);
 	data_desc->qid_tid = ((skb->priority & 0xf) |
 			      ((tx_params->tid & 0xf) << 4));
 	data_desc->sta_id = tx_params->sta_id;
-- 
cgit v1.2.3


From 38709316d1c927ac639f916e6c6f49b5de6e78ca Mon Sep 17 00:00:00 2001
From: Ganapathi Raju <ganapathi.kondraju@redpinesignals.com>
Date: Thu, 5 Jul 2018 18:08:20 +0530
Subject: rsi: fix for 40MHZ connection issue.

Radio capabilities packet is not prepared properly for 40MHZ case,
ppe_ack_rate is a two byte variable which is initialized wrongly,
hence we are unable to connect, resolved by assigning it properly.

Signed-off-by: Ganapathi Raju <ganapathi.kondraju@redpinesignals.com>
Signed-off-by: Sushant Kumar Mishra <sushant.mishra@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_mgmt.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index d0e5937cad6d..8280f3240802 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -334,20 +334,17 @@ static int rsi_load_radio_caps(struct rsi_common *common)
 			struct ieee80211_conf *conf = &hw->conf;
 
 			if (conf_is_ht40_plus(conf)) {
-				radio_caps->radio_cfg_info =
-					RSI_CMDDESC_LOWER_20_ENABLE;
-				radio_caps->radio_info =
-					RSI_CMDDESC_LOWER_20_ENABLE;
+				radio_caps->ppe_ack_rate =
+					cpu_to_le16(LOWER_20_ENABLE |
+						    (LOWER_20_ENABLE >> 12));
 			} else if (conf_is_ht40_minus(conf)) {
-				radio_caps->radio_cfg_info =
-					RSI_CMDDESC_UPPER_20_ENABLE;
-				radio_caps->radio_info =
-					RSI_CMDDESC_UPPER_20_ENABLE;
+				radio_caps->ppe_ack_rate =
+					cpu_to_le16(UPPER_20_ENABLE |
+						    (UPPER_20_ENABLE >> 12));
 			} else {
-				radio_caps->radio_cfg_info =
-					RSI_CMDDESC_40MHZ;
-				radio_caps->radio_info =
-					RSI_CMDDESC_FULL_40_ENABLE;
+				radio_caps->ppe_ack_rate =
+					cpu_to_le16((BW_40MHZ << 12) |
+						    FULL40M_ENABLE);
 			}
 		}
 	}
-- 
cgit v1.2.3


From 4c837d8c9b0c7718dd9ff14ee77e4704c9be258d Mon Sep 17 00:00:00 2001
From: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Date: Thu, 5 Jul 2018 18:08:21 +0530
Subject: rsi: fix for WoWLAN wakeup in security mode.

System is unable to wake-up through magic-packet in secured connections.
Because key descriptor is getting corrupted and firmware is unable to
decrypt the magic packet. Fixed the issue by properly preparing it
before sending it to firmware.

Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Sushant Kumar Mishra <sushant.mishra@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_mgmt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_mgmt.c b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
index 8280f3240802..1095df7d9573 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mgmt.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mgmt.c
@@ -746,7 +746,7 @@ int rsi_hal_load_key(struct rsi_common *common,
 			key_descriptor |= RSI_CIPHER_TKIP;
 	}
 	key_descriptor |= RSI_PROTECT_DATA_FRAMES;
-	key_descriptor |= ((key_id << RSI_KEY_ID_OFFSET) & RSI_KEY_ID_MASK);
+	key_descriptor |= (key_id << RSI_KEY_ID_OFFSET);
 
 	rsi_set_len_qno(&set_key->desc_dword0.len_qno,
 			(frame_len - FRAME_DESC_SZ), RSI_WIFI_MGMT_Q);
-- 
cgit v1.2.3


From 1d2194562112dc4e5b1077c1946dffd168a6c358 Mon Sep 17 00:00:00 2001
From: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Date: Thu, 5 Jul 2018 18:08:22 +0530
Subject: rsi: optimize virtual interfaces

Due to multiple calls of add interface routine, vif is getting duplicated
and at certain instance, we are out of vifs, causing the driver to behave
abnormal.

Fix: Every vif has a unique mac-id, when we got a vif with same mac-id as
the previous id's, we will override the respective vif.

Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Sushant Kumar Mishra <sushant.mishra@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_mac80211.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_mac80211.c b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
index 2ca7464b7fa3..4e510cbe0a89 100644
--- a/drivers/net/wireless/rsi/rsi_91x_mac80211.c
+++ b/drivers/net/wireless/rsi/rsi_91x_mac80211.c
@@ -416,7 +416,8 @@ static int rsi_mac80211_add_interface(struct ieee80211_hw *hw,
 
 	/* Get free vap index */
 	for (i = 0; i < RSI_MAX_VIFS; i++) {
-		if (!adapter->vifs[i]) {
+		if (!adapter->vifs[i] ||
+		    !memcmp(vif->addr, adapter->vifs[i]->addr, ETH_ALEN)) {
 			vap_idx = i;
 			break;
 		}
-- 
cgit v1.2.3


From 5850874c28a477046e78f7336a47faaf9b5db11d Mon Sep 17 00:00:00 2001
From: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Date: Mon, 16 Jul 2018 19:09:32 +0530
Subject: rsi: remove redundant device ids

Removing redundant device id's from both usb and sdio idtables, as rsi
driver currently supporting only one module(RS9113). Also, replaced ids
with specific defines.

Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_sdio.c | 5 +----
 drivers/net/wireless/rsi/rsi_91x_usb.c  | 6 +-----
 drivers/net/wireless/rsi/rsi_sdio.h     | 3 +++
 drivers/net/wireless/rsi/rsi_usb.h      | 3 +++
 4 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_sdio.c b/drivers/net/wireless/rsi/rsi_91x_sdio.c
index 416981d99229..5733e440ecaf 100644
--- a/drivers/net/wireless/rsi/rsi_91x_sdio.c
+++ b/drivers/net/wireless/rsi/rsi_91x_sdio.c
@@ -1394,10 +1394,7 @@ static const struct dev_pm_ops rsi_pm_ops = {
 #endif
 
 static const struct sdio_device_id rsi_dev_table[] =  {
-	{ SDIO_DEVICE(0x303, 0x100) },
-	{ SDIO_DEVICE(0x041B, 0x0301) },
-	{ SDIO_DEVICE(0x041B, 0x0201) },
-	{ SDIO_DEVICE(0x041B, 0x9330) },
+	{ SDIO_DEVICE(RSI_SDIO_VID_9113, RSI_SDIO_PID_9113) },
 	{ /* Blank */},
 };
 
diff --git a/drivers/net/wireless/rsi/rsi_91x_usb.c b/drivers/net/wireless/rsi/rsi_91x_usb.c
index 6ce6b754df12..c0a163e40402 100644
--- a/drivers/net/wireless/rsi/rsi_91x_usb.c
+++ b/drivers/net/wireless/rsi/rsi_91x_usb.c
@@ -835,11 +835,7 @@ static int rsi_resume(struct usb_interface *intf)
 #endif
 
 static const struct usb_device_id rsi_dev_table[] = {
-	{ USB_DEVICE(0x0303, 0x0100) },
-	{ USB_DEVICE(0x041B, 0x0301) },
-	{ USB_DEVICE(0x041B, 0x0201) },
-	{ USB_DEVICE(0x041B, 0x9330) },
-	{ USB_DEVICE(0x1618, 0x9113) },
+	{ USB_DEVICE(RSI_USB_VID_9113, RSI_USB_PID_9113) },
 	{ /* Blank */},
 };
 
diff --git a/drivers/net/wireless/rsi/rsi_sdio.h b/drivers/net/wireless/rsi/rsi_sdio.h
index 353dbdf31e75..66dcd2ec9051 100644
--- a/drivers/net/wireless/rsi/rsi_sdio.h
+++ b/drivers/net/wireless/rsi/rsi_sdio.h
@@ -28,6 +28,9 @@
 #include <linux/mmc/sdio_ids.h>
 #include "rsi_main.h"
 
+#define RSI_SDIO_VID_9113    0x041B
+#define RSI_SDIO_PID_9113    0x9330
+
 enum sdio_interrupt_type {
 	BUFFER_FULL         = 0x0,
 	BUFFER_AVAILABLE    = 0x2,
diff --git a/drivers/net/wireless/rsi/rsi_usb.h b/drivers/net/wireless/rsi/rsi_usb.h
index b6fe79f0a513..5b2eddd1a2ee 100644
--- a/drivers/net/wireless/rsi/rsi_usb.h
+++ b/drivers/net/wireless/rsi/rsi_usb.h
@@ -22,6 +22,9 @@
 #include "rsi_main.h"
 #include "rsi_common.h"
 
+#define RSI_USB_VID_9113	0x1618
+#define RSI_USB_PID_9113	0x9113
+
 #define USB_INTERNAL_REG_1           0x25000
 #define RSI_USB_READY_MAGIC_NUM      0xab
 #define FW_STATUS_REG                0x41050012
-- 
cgit v1.2.3


From bae402920424e27faa44130507b654ab7beabaa4 Mon Sep 17 00:00:00 2001
From: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Date: Mon, 16 Jul 2018 19:09:33 +0530
Subject: rsi: remove redundant flash_content variable

while cleaning up the driver, observed that flash_content pointer is not
necessary in rsi_load_firmware(). Instead of this, driver can use
'fw_entry->data' directly.Hence, removed redundant flash_content pointer.

Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_hal.c | 23 +++++++----------------
 1 file changed, 7 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 533d9e964430..150c3e688b83 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -842,7 +842,6 @@ static int rsi_load_firmware(struct rsi_hw *adapter)
 	const struct firmware *fw_entry = NULL;
 	u32 regout_val = 0, content_size;
 	u16 tmp_regout_val = 0;
-	u8 *flash_content = NULL;
 	struct ta_metadata *metadata_p;
 	int status;
 
@@ -904,28 +903,22 @@ static int rsi_load_firmware(struct rsi_hw *adapter)
 			__func__, metadata_p->name);
 		return status;
 	}
-	flash_content = kmemdup(fw_entry->data, fw_entry->size, GFP_KERNEL);
-	if (!flash_content) {
-		rsi_dbg(ERR_ZONE, "%s: Failed to copy firmware\n", __func__);
-		status = -EIO;
-		goto fail;
-	}
 	content_size = fw_entry->size;
 	rsi_dbg(INFO_ZONE, "FW Length = %d bytes\n", content_size);
 
 	/* Get the firmware version */
 	common->lmac_ver.ver.info.fw_ver[0] =
-		flash_content[LMAC_VER_OFFSET] & 0xFF;
+		fw_entry->data[LMAC_VER_OFFSET] & 0xFF;
 	common->lmac_ver.ver.info.fw_ver[1] =
-		flash_content[LMAC_VER_OFFSET + 1] & 0xFF;
-	common->lmac_ver.major = flash_content[LMAC_VER_OFFSET + 2] & 0xFF;
+		fw_entry->data[LMAC_VER_OFFSET + 1] & 0xFF;
+	common->lmac_ver.major = fw_entry->data[LMAC_VER_OFFSET + 2] & 0xFF;
 	common->lmac_ver.release_num =
-		flash_content[LMAC_VER_OFFSET + 3] & 0xFF;
-	common->lmac_ver.minor = flash_content[LMAC_VER_OFFSET + 4] & 0xFF;
+		fw_entry->data[LMAC_VER_OFFSET + 3] & 0xFF;
+	common->lmac_ver.minor = fw_entry->data[LMAC_VER_OFFSET + 4] & 0xFF;
 	common->lmac_ver.patch_num = 0;
 	rsi_print_version(common);
 
-	status = bl_write_header(adapter, flash_content, content_size);
+	status = bl_write_header(adapter, (u8 *)fw_entry->data, content_size);
 	if (status) {
 		rsi_dbg(ERR_ZONE,
 			"%s: RPS Image header loading failed\n",
@@ -967,7 +960,7 @@ fw_upgrade:
 
 	rsi_dbg(INFO_ZONE, "Burn Command Pass.. Upgrading the firmware\n");
 
-	status = auto_fw_upgrade(adapter, flash_content, content_size);
+	status = auto_fw_upgrade(adapter, (u8 *)fw_entry->data, content_size);
 	if (status == 0) {
 		rsi_dbg(ERR_ZONE, "Firmware upgradation Done\n");
 		goto load_image_cmd;
@@ -981,13 +974,11 @@ fw_upgrade:
 
 success:
 	rsi_dbg(ERR_ZONE, "***** Firmware Loading successful *****\n");
-	kfree(flash_content);
 	release_firmware(fw_entry);
 	return 0;
 
 fail:
 	rsi_dbg(ERR_ZONE, "##### Firmware loading failed #####\n");
-	kfree(flash_content);
 	release_firmware(fw_entry);
 	return status;
 }
-- 
cgit v1.2.3


From f5fbce65abcf08cb961ddb1bc8f159f461c1a9db Mon Sep 17 00:00:00 2001
From: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Date: Mon, 16 Jul 2018 19:09:34 +0530
Subject: rsi: add firmware support for AP+BT dual mode

Currently, AP mode will work on only WLAN alone firmware. To give support
for AP and BT dual mode, adding firmware entry in 'struct ta_metadata'.
The firmware entry is based on what coex_mode is used in driver and coex
mode '4' for all AP+BT related functionalities. Hence, added the same.

Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_hal.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 150c3e688b83..27e6baf12e90 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -26,6 +26,9 @@ static struct ta_metadata metadata_flash_content[] = {
 	{"flash_content", 0x00010000},
 	{"rsi/rs9113_wlan_qspi.rps", 0x00010000},
 	{"rsi/rs9113_wlan_bt_dual_mode.rps", 0x00010000},
+	{"flash_content", 0x00010000},
+	{"rsi/rs9113_ap_bt_dual_mode.rps", 0x00010000},
+
 };
 
 int rsi_send_pkt_to_bus(struct rsi_common *common, struct sk_buff *skb)
-- 
cgit v1.2.3


From abbe87d339bdd3315b145d9c03ab5ab578febee7 Mon Sep 17 00:00:00 2001
From: Amol Hanwate <amol.hanwate@redpinesignals.com>
Date: Mon, 16 Jul 2018 19:09:35 +0530
Subject: rsi: Correct RSI_NEEDED_HEADROOM in mac80211_attach.

Currently, RSI_NEEDED_HEADROOM is '80' for rsi driver, which is wrong.
As per rsi internal frame format, the RSI_NEEDED_HEADROOM shall be '84',
which is 64(dword_align) + 4(extended_desc) + 16(frame_desc).
Hence, corrected the needed headroom.

Signed-off-by: Amol Hanwate <amol.hanwate@redpinesignals.com>
Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_mgmt.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_mgmt.h b/drivers/net/wireless/rsi/rsi_mgmt.h
index 14620935c925..359fbdf85739 100644
--- a/drivers/net/wireless/rsi/rsi_mgmt.h
+++ b/drivers/net/wireless/rsi/rsi_mgmt.h
@@ -22,7 +22,7 @@
 #include "rsi_main.h"
 
 #define MAX_MGMT_PKT_SIZE               512
-#define RSI_NEEDED_HEADROOM             80
+#define RSI_NEEDED_HEADROOM             84
 #define RSI_RCV_BUFFER_LEN              2000
 
 #define RSI_11B_MODE                    0
-- 
cgit v1.2.3


From 160ee2a11ce03d7276501d2448bfe8b3cbdad3e1 Mon Sep 17 00:00:00 2001
From: Amol Hanwate <amol.hanwate@redpinesignals.com>
Date: Mon, 16 Jul 2018 19:09:36 +0530
Subject: rsi: fill rx_params only once.

rx_params are getting updated two times in driver, which is not required.
Hence, removing duplicate updation of rx_params from rsi_prepare_skb().

Signed-off-by: Amol Hanwate <amol.hanwate@redpinesignals.com>
Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_main.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c
index 1485a0c89df2..34a5d9c06178 100644
--- a/drivers/net/wireless/rsi/rsi_91x_main.c
+++ b/drivers/net/wireless/rsi/rsi_91x_main.c
@@ -122,7 +122,6 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common,
 				       u8 extended_desc)
 {
 	struct ieee80211_tx_info *info;
-	struct skb_info *rx_params;
 	struct sk_buff *skb = NULL;
 	u8 payload_offset;
 	struct ieee80211_vif *vif;
@@ -149,10 +148,6 @@ static struct sk_buff *rsi_prepare_skb(struct rsi_common *common,
 	vif = rsi_get_vif(common->priv, wh->addr1);
 
 	info = IEEE80211_SKB_CB(skb);
-	rx_params = (struct skb_info *)info->driver_data;
-	rx_params->rssi = rsi_get_rssi(buffer);
-	rx_params->channel = rsi_get_connected_channel(vif);
-
 	return skb;
 }
 
-- 
cgit v1.2.3


From 2ddd82eef2ef900dd1505888348ef90ef51481a1 Mon Sep 17 00:00:00 2001
From: Amol Hanwate <amol.hanwate@redpinesignals.com>
Date: Mon, 16 Jul 2018 19:09:37 +0530
Subject: rsi: move init_done flag to end of rsi_91x_init().

common->init_done flag should set after basic initialization. Hence,
moving init_done flag at end of rsi_91x_init().

Signed-off-by: Amol Hanwate <amol.hanwate@redpinesignals.com>
Signed-off-by: Siva Rebbagondla <siva.rebbagondla@redpinesignals.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_main.c b/drivers/net/wireless/rsi/rsi_91x_main.c
index 34a5d9c06178..01d99ed985ee 100644
--- a/drivers/net/wireless/rsi/rsi_91x_main.c
+++ b/drivers/net/wireless/rsi/rsi_91x_main.c
@@ -331,7 +331,6 @@ struct rsi_hw *rsi_91x_init(u16 oper_mode)
 	spin_lock_init(&adapter->ps_lock);
 	timer_setup(&common->roc_timer, rsi_roc_timeout, 0);
 	init_completion(&common->wlan_init_completion);
-	common->init_done = true;
 	adapter->device_model = RSI_DEV_9113;
 	common->oper_mode = oper_mode;
 
@@ -369,6 +368,7 @@ struct rsi_hw *rsi_91x_init(u16 oper_mode)
 	}
 #endif
 
+	common->init_done = true;
 	return adapter;
 
 err:
-- 
cgit v1.2.3


From d01a4e04dab7fa1002722e5d09cfd9c037767348 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 9 Jul 2018 14:38:43 +0100
Subject: airo: remove unused variables len and dev and clean up formatting

Variables len and dev assigned values but are never used hence they
are redundant and can be removed.  Also add in white space in for-loop
and remove some { } braces on if statement.

Cleans up clang warnings:
warning: variable 'len' set but not used [-Wunused-but-set-variable]
warning: variable 'dev' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/cisco/airo.c    | 8 +++-----
 drivers/net/wireless/cisco/airo_cs.c | 3 ---
 2 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/cisco/airo.c b/drivers/net/wireless/cisco/airo.c
index 72046e182745..04dd7a936593 100644
--- a/drivers/net/wireless/cisco/airo.c
+++ b/drivers/net/wireless/cisco/airo.c
@@ -3419,7 +3419,7 @@ done:
 
 static void airo_handle_tx(struct airo_info *ai, u16 status)
 {
-	int i, len = 0, index = -1;
+	int i, index = -1;
 	u16 fid;
 
 	if (test_bit(FLAG_MPI, &ai->flags)) {
@@ -3443,11 +3443,9 @@ static void airo_handle_tx(struct airo_info *ai, u16 status)
 
 	fid = IN4500(ai, TXCOMPLFID);
 
-	for(i = 0; i < MAX_FIDS; i++) {
-		if ((ai->fids[i] & 0xffff) == fid) {
-			len = ai->fids[i] >> 16;
+	for (i = 0; i < MAX_FIDS; i++) {
+		if ((ai->fids[i] & 0xffff) == fid)
 			index = i;
-		}
 	}
 
 	if (index != -1) {
diff --git a/drivers/net/wireless/cisco/airo_cs.c b/drivers/net/wireless/cisco/airo_cs.c
index d9ed22b4cc6b..3718f958c0fc 100644
--- a/drivers/net/wireless/cisco/airo_cs.c
+++ b/drivers/net/wireless/cisco/airo_cs.c
@@ -102,11 +102,8 @@ static int airo_cs_config_check(struct pcmcia_device *p_dev, void *priv_data)
 
 static int airo_config(struct pcmcia_device *link)
 {
-	struct local_info *dev;
 	int ret;
 
-	dev = link->priv;
-
 	dev_dbg(&link->dev, "airo_config\n");
 
 	link->config_flags |= CONF_ENABLE_IRQ | CONF_AUTO_SET_VPP |
-- 
cgit v1.2.3


From 0e139e97f58e8f844fecd77461aaad128f43b734 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 11 Jul 2018 08:12:12 +0100
Subject: ipw2x00: remove redundant variables len, ret, reason and crypt

Variables len, ret, reason and crypt are assigned values that
are never read, hence they are redundant and can be removed.

Note: For the variable ret, a return code is being assigned, but
this is not returned and 0 is currently being returned, I believe
this is OK.

Cleans up clang warnings:
warning: variable 'len' set but not used [-Wunused-but-set-variable]
variable 'ret' set but not used [-Wunused-but-set-variable]
warning: variable 'reason' set but not used [-Wunused-but-set-variable]
warning: variable 'crypt' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/ipw2x00/ipw2100.c   | 7 -------
 drivers/net/wireless/intel/ipw2x00/libipw_wx.c | 2 --
 2 files changed, 9 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2100.c b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
index 1ad83ef5f202..910db46db6a1 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2100.c
@@ -5112,11 +5112,9 @@ static int ipw2100_disassociate_bssid(struct ipw2100_priv *priv)
 		.host_command_length = ETH_ALEN
 	};
 	int err;
-	int len;
 
 	IPW_DEBUG_HC("DISASSOCIATION_BSSID\n");
 
-	len = ETH_ALEN;
 	/* The Firmware currently ignores the BSSID and just disassociates from
 	 * the currently associated AP -- but in the off chance that a future
 	 * firmware does use the BSSID provided here, we go ahead and try and
@@ -7723,7 +7721,6 @@ static int ipw2100_wx_get_auth(struct net_device *dev,
 	struct libipw_device *ieee = priv->ieee;
 	struct lib80211_crypt_data *crypt;
 	struct iw_param *param = &wrqu->param;
-	int ret = 0;
 
 	switch (param->flags & IW_AUTH_INDEX) {
 	case IW_AUTH_WPA_VERSION:
@@ -7733,7 +7730,6 @@ static int ipw2100_wx_get_auth(struct net_device *dev,
 		/*
 		 * wpa_supplicant will control these internally
 		 */
-		ret = -EOPNOTSUPP;
 		break;
 
 	case IW_AUTH_TKIP_COUNTERMEASURES:
@@ -7801,9 +7797,6 @@ static int ipw2100_wx_set_mlme(struct net_device *dev,
 {
 	struct ipw2100_priv *priv = libipw_priv(dev);
 	struct iw_mlme *mlme = (struct iw_mlme *)extra;
-	__le16 reason;
-
-	reason = cpu_to_le16(mlme->reason_code);
 
 	switch (mlme->cmd) {
 	case IW_MLME_DEAUTH:
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_wx.c b/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
index dd29f46d086b..d32d39fa2686 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_wx.c
@@ -479,7 +479,6 @@ int libipw_wx_get_encode(struct libipw_device *ieee,
 {
 	struct iw_point *erq = &(wrqu->encoding);
 	int len, key;
-	struct lib80211_crypt_data *crypt;
 	struct libipw_security *sec = &ieee->sec;
 
 	LIBIPW_DEBUG_WX("GET_ENCODE\n");
@@ -492,7 +491,6 @@ int libipw_wx_get_encode(struct libipw_device *ieee,
 	} else
 		key = ieee->crypt_info.tx_keyidx;
 
-	crypt = ieee->crypt_info.crypt[key];
 	erq->flags = key + 1;
 
 	if (!sec->enabled) {
-- 
cgit v1.2.3


From 454127ad36fb11ee212f487b2640dd82373f3b0c Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 11 Jul 2018 08:42:53 +0100
Subject: iwlegacy: remove several redundant variables

Variables id, unicast, write, conf, a_band, accum_tx and ucode are
assigned a value but it is never read, hence they are redundant and
can be removed.

Cleans up clang warnings:
warning: variable 'id' set but not used [-Wunused-but-set-variable]
warning: variable 'unicast' set but not used [-Wunused-but-set-variable]
warning: variable 'write' set but not used [-Wunused-but-set-variable]
warning: variable 'conf' set but not used [-Wunused-but-set-variable]
warning: variable 'a_band' set but not used [-Wunused-but-set-variable]
warning: variable 'tx' set but not used [-Wunused-but-set-variable]
warning: variable 'accum_tx' set but not used [-Wunused-but-set-variable]
warning: variable 'ucode' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlegacy/3945-mac.c | 10 ----------
 drivers/net/wireless/intel/iwlegacy/3945.c     |  2 --
 drivers/net/wireless/intel/iwlegacy/4965-mac.c |  6 ------
 3 files changed, 18 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/3945-mac.c b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
index 62a9794f952b..57e3b6cca234 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-mac.c
@@ -476,8 +476,6 @@ il3945_tx_skb(struct il_priv *il,
 	int txq_id = skb_get_queue_mapping(skb);
 	u16 len, idx, hdr_len;
 	u16 firstlen, secondlen;
-	u8 id;
-	u8 unicast;
 	u8 sta_id;
 	u8 tid = 0;
 	__le16 fc;
@@ -496,9 +494,6 @@ il3945_tx_skb(struct il_priv *il,
 		goto drop_unlock;
 	}
 
-	unicast = !is_multicast_ether_addr(hdr->addr1);
-	id = 0;
-
 	fc = hdr->frame_control;
 
 #ifdef CONFIG_IWLEGACY_DEBUG
@@ -957,10 +952,8 @@ il3945_rx_queue_restock(struct il_priv *il)
 	struct list_head *element;
 	struct il_rx_buf *rxb;
 	unsigned long flags;
-	int write;
 
 	spin_lock_irqsave(&rxq->lock, flags);
-	write = rxq->write & ~0x7;
 	while (il_rx_queue_space(rxq) > 0 && rxq->free_count) {
 		/* Get next free Rx buffer, remove from free list */
 		element = rxq->rx_free.next;
@@ -2725,7 +2718,6 @@ void
 il3945_post_associate(struct il_priv *il)
 {
 	int rc = 0;
-	struct ieee80211_conf *conf = NULL;
 
 	if (!il->vif || !il->is_open)
 		return;
@@ -2738,8 +2730,6 @@ il3945_post_associate(struct il_priv *il)
 
 	il_scan_cancel_timeout(il, 200);
 
-	conf = &il->hw->conf;
-
 	il->staging.filter_flags &= ~RXON_FILTER_ASSOC_MSK;
 	il3945_commit_rxon(il);
 
diff --git a/drivers/net/wireless/intel/iwlegacy/3945.c b/drivers/net/wireless/intel/iwlegacy/3945.c
index dbf164d48ed3..3e568ce2fb20 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945.c
@@ -1634,7 +1634,6 @@ il3945_hw_reg_set_txpower(struct il_priv *il, s8 power)
 {
 	struct il_channel_info *ch_info;
 	s8 max_power;
-	u8 a_band;
 	u8 i;
 
 	if (il->tx_power_user_lmt == power) {
@@ -1650,7 +1649,6 @@ il3945_hw_reg_set_txpower(struct il_priv *il, s8 power)
 
 	for (i = 0; i < il->channel_count; i++) {
 		ch_info = &il->channel_info[i];
-		a_band = il_is_channel_a_band(ch_info);
 
 		/* find minimum power of all user and regulatory constraints
 		 *    (does not consider h/w clipping limitations) */
diff --git a/drivers/net/wireless/intel/iwlegacy/4965-mac.c b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
index 562e94870a9c..280cd8ae1696 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-mac.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-mac.c
@@ -1338,15 +1338,12 @@ il4965_accumulative_stats(struct il_priv *il, __le32 * stats)
 	u32 *accum_stats;
 	u32 *delta, *max_delta;
 	struct stats_general_common *general, *accum_general;
-	struct stats_tx *tx, *accum_tx;
 
 	prev_stats = (__le32 *) &il->_4965.stats;
 	accum_stats = (u32 *) &il->_4965.accum_stats;
 	size = sizeof(struct il_notif_stats);
 	general = &il->_4965.stats.general.common;
 	accum_general = &il->_4965.accum_stats.general.common;
-	tx = &il->_4965.stats.tx;
-	accum_tx = &il->_4965.accum_stats.tx;
 	delta = (u32 *) &il->_4965.delta_stats;
 	max_delta = (u32 *) &il->_4965.max_delta;
 
@@ -4784,7 +4781,6 @@ static void
 il4965_ucode_callback(const struct firmware *ucode_raw, void *context)
 {
 	struct il_priv *il = context;
-	struct il_ucode_header *ucode;
 	int err;
 	struct il4965_firmware_pieces pieces;
 	const unsigned int api_max = il->cfg->ucode_api_max;
@@ -4814,8 +4810,6 @@ il4965_ucode_callback(const struct firmware *ucode_raw, void *context)
 	}
 
 	/* Data from ucode file:  header followed by uCode images */
-	ucode = (struct il_ucode_header *)ucode_raw->data;
-
 	err = il4965_load_firmware(il, ucode_raw, &pieces);
 
 	if (err)
-- 
cgit v1.2.3


From f21bcefcf91cc4549966e67debd082a2cb14bf73 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 20 Jul 2018 19:07:40 +0100
Subject: ray_cs: remove redundant pointer 'p'

Pointer 'p' is being assigned but is never used hence it is
redundant and can be removed. Also re-work if statement to remove
redundant assignment of p.

Cleans up clang warning:
warning: variable 'p' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ray_cs.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ray_cs.c b/drivers/net/wireless/ray_cs.c
index a7e0a17aa7e8..08c607c031bc 100644
--- a/drivers/net/wireless/ray_cs.c
+++ b/drivers/net/wireless/ray_cs.c
@@ -470,7 +470,6 @@ static inline struct rcs __iomem *rcs_base(ray_dev_t *dev)
 static int ray_init(struct net_device *dev)
 {
 	int i;
-	UCHAR *p;
 	struct ccs __iomem *pccs;
 	ray_dev_t *local = netdev_priv(dev);
 	struct pcmcia_device *link = local->finder;
@@ -513,12 +512,9 @@ static int ray_init(struct net_device *dev)
 	init_startup_params(local);
 
 	/* copy mac address to startup parameters */
-	if (parse_addr(phy_addr, local->sparm.b4.a_mac_addr)) {
-		p = local->sparm.b4.a_mac_addr;
-	} else {
+	if (!parse_addr(phy_addr, local->sparm.b4.a_mac_addr)) {
 		memcpy(&local->sparm.b4.a_mac_addr,
 		       &local->startup_res.station_addr, ADDRLEN);
-		p = local->sparm.b4.a_mac_addr;
 	}
 
 	clear_interrupt(local);	/* Clear any interrupt from the card */
-- 
cgit v1.2.3


From 8b8f3278d241658a7dcb95cefc9793ac85a43c3a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 13 Jul 2018 14:46:58 +0800
Subject: atmel: hide unused procfs helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When CONFIG_PROC_FS isn't set, gcc warning this:

drivers/net/wireless/atmel/atmel.c:1402:12: warning: ‘atmel_proc_show’ defined but not used [-Wunused-function]
 static int atmel_proc_show(struct seq_file *m, void *v)
            ^
fix this by adding #ifdef around it.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/atmel/atmel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index 3ed3d9f6aae9..f4f56f461b61 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -1399,6 +1399,7 @@ static int atmel_validate_channel(struct atmel_private *priv, int channel)
 	return 0;
 }
 
+#ifdef CONFIG_PROC_FS
 static int atmel_proc_show(struct seq_file *m, void *v)
 {
 	struct atmel_private *priv = m->private;
@@ -1481,6 +1482,7 @@ static int atmel_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "Current state:\t\t%s\n", s);
 	return 0;
 }
+#endif
 
 static const struct net_device_ops atmel_netdev_ops = {
 	.ndo_open 		= atmel_open,
-- 
cgit v1.2.3


From 6ade689711eeedb7070944b0764024c936730c9f Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 13 Jul 2018 15:03:17 +0800
Subject: hostap: hide unused procfs helpers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When CONFIG_PROC_FS isn't set, gcc warning this:

drivers/net/wireless/intersil/hostap/hostap_hw.c:2901:12: warning: ‘prism2_registers_proc_show’ defined but not used [-Wunused-function]
 static int prism2_registers_proc_show(struct seq_file *m, void *v)

drivers/net/wireless/intersil/hostap/hostap_proc.c:16:12: warning: ‘prism2_debug_proc_show’ defined but not used [-Wunused-function]
 static int prism2_debug_proc_show(struct seq_file *m, void *v)
            ^
drivers/net/wireless/intersil/hostap/hostap_proc.c:49:12: warning: ‘prism2_stats_proc_show’ defined but not used [-Wunused-function]
 static int prism2_stats_proc_show(struct seq_file *m, void *v)
            ^
drivers/net/wireless/intersil/hostap/hostap_proc.c:177:12: warning: ‘prism2_crypt_proc_show’ defined but not used [-Wunused-function]
 static int prism2_crypt_proc_show(struct seq_file *m, void *v)
            ^

fix this by adding #ifdef around them.
hfa384x_read_reg is only used by prism2_registers_proc_show,so move it
into #ifdef.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intersil/hostap/hostap_ap.c   |  8 ++++----
 drivers/net/wireless/intersil/hostap/hostap_hw.c   | 17 +++++++----------
 drivers/net/wireless/intersil/hostap/hostap_proc.c | 10 ++++++----
 3 files changed, 17 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/intersil/hostap/hostap_ap.c b/drivers/net/wireless/intersil/hostap/hostap_ap.c
index d1884b8913e7..0094b1d2b577 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_ap.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_ap.c
@@ -66,7 +66,7 @@ static void prism2_send_mgmt(struct net_device *dev,
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
 
-#ifndef PRISM2_NO_PROCFS_DEBUG
+#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
 static int ap_debug_proc_show(struct seq_file *m, void *v)
 {
 	struct ap_data *ap = PDE_DATA(file_inode(m->file));
@@ -81,8 +81,7 @@ static int ap_debug_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "tx_drop_nonassoc=%u\n", ap->tx_drop_nonassoc);
 	return 0;
 }
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
+#endif
 
 static void ap_sta_hash_add(struct ap_data *ap, struct sta_info *sta)
 {
@@ -990,7 +989,7 @@ static void prism2_send_mgmt(struct net_device *dev,
 }
 #endif /* PRISM2_NO_KERNEL_IEEE80211_MGMT */
 
-
+#ifdef CONFIG_PROC_FS
 static int prism2_sta_proc_show(struct seq_file *m, void *v)
 {
 	struct sta_info *sta = m->private;
@@ -1059,6 +1058,7 @@ static int prism2_sta_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
+#endif
 
 static void handle_add_proc_queue(struct work_struct *work)
 {
diff --git a/drivers/net/wireless/intersil/hostap/hostap_hw.c b/drivers/net/wireless/intersil/hostap/hostap_hw.c
index 2720aa39f530..ad1aa65fee7f 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_hw.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_hw.c
@@ -151,13 +151,6 @@ static int prism2_get_ram_size(local_info_t *local);
 #define HFA384X_MAGIC 0x8A32
 #endif
 
-
-static u16 hfa384x_read_reg(struct net_device *dev, u16 reg)
-{
-	return HFA384X_INW(reg);
-}
-
-
 static void hfa384x_read_regs(struct net_device *dev,
 			      struct hfa384x_regs *regs)
 {
@@ -2897,7 +2890,12 @@ static void hostap_tick_timer(struct timer_list *t)
 }
 
 
-#ifndef PRISM2_NO_PROCFS_DEBUG
+#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
+static u16 hfa384x_read_reg(struct net_device *dev, u16 reg)
+{
+	return HFA384X_INW(reg);
+}
+
 static int prism2_registers_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -2951,8 +2949,7 @@ static int prism2_registers_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
+#endif
 
 struct set_tim_data {
 	struct list_head list;
diff --git a/drivers/net/wireless/intersil/hostap/hostap_proc.c b/drivers/net/wireless/intersil/hostap/hostap_proc.c
index 5b33ccab9188..703d74cea3c2 100644
--- a/drivers/net/wireless/intersil/hostap/hostap_proc.c
+++ b/drivers/net/wireless/intersil/hostap/hostap_proc.c
@@ -11,8 +11,7 @@
 
 #define PROC_LIMIT (PAGE_SIZE - 80)
 
-
-#ifndef PRISM2_NO_PROCFS_DEBUG
+#if !defined(PRISM2_NO_PROCFS_DEBUG) && defined(CONFIG_PROC_FS)
 static int prism2_debug_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -43,9 +42,9 @@ static int prism2_debug_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
-#endif /* PRISM2_NO_PROCFS_DEBUG */
-
+#endif
 
+#ifdef CONFIG_PROC_FS
 static int prism2_stats_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -82,6 +81,7 @@ static int prism2_stats_proc_show(struct seq_file *m, void *v)
 
 	return 0;
 }
+#endif
 
 static int prism2_wds_proc_show(struct seq_file *m, void *v)
 {
@@ -174,6 +174,7 @@ static const struct seq_operations prism2_bss_list_proc_seqops = {
 	.show	= prism2_bss_list_proc_show,
 };
 
+#ifdef CONFIG_PROC_FS
 static int prism2_crypt_proc_show(struct seq_file *m, void *v)
 {
 	local_info_t *local = m->private;
@@ -190,6 +191,7 @@ static int prism2_crypt_proc_show(struct seq_file *m, void *v)
 	}
 	return 0;
 }
+#endif
 
 static ssize_t prism2_pda_proc_read(struct file *file, char __user *buf,
 				    size_t count, loff_t *_pos)
-- 
cgit v1.2.3


From 1e591c56a65fbbcd5754a4210a0ef0402d5e5f33 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Mon, 9 Jul 2018 06:55:43 +0200
Subject: brcmfmac: specify some features per firmware version
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some features supported by firmware aren't advertised and there is no
way for a driver to query them. This includes e.g. monitor mode details.

Most firmwares support monitor interface but only the latest ones
/announce/ it with a "monitor" flag in the "cap" iovar. There isn't any
reliable detection method for older firmwares (BRCMF_C_MONITOR was tried
but "it only indicates the core part of the stack supports").

Similarly support for tagging monitor frames and building radiotap
headers can't be reliably detected for all firmwares.

This commit adds table that allows mapping features to firmware version.
It adds mappings for 43602a1 and 4366b1 firmwares from
linux-firmware.git. Both were confirmed to be passing monitor frames.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Reviewed-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/broadcom/brcm80211/brcmfmac/feature.c | 38 ++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
index 4db4d444407a..8347da632a5b 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
@@ -93,6 +93,42 @@ static int brcmf_feat_debugfs_read(struct seq_file *seq, void *data)
 }
 #endif /* DEBUG */
 
+struct brcmf_feat_fwfeat {
+	const char * const fwid;
+	u32 feat_flags;
+};
+
+static const struct brcmf_feat_fwfeat brcmf_feat_fwfeat_map[] = {
+	/* brcmfmac43602-pcie.ap.bin from linux-firmware.git commit ea1178515b88 */
+	{ "01-6cb8e269", BIT(BRCMF_FEAT_MONITOR) },
+	/* brcmfmac4366b-pcie.bin from linux-firmware.git commit 52442afee990 */
+	{ "01-c47a91a4", BIT(BRCMF_FEAT_MONITOR) },
+};
+
+static void brcmf_feat_firmware_overrides(struct brcmf_pub *drv)
+{
+	const struct brcmf_feat_fwfeat *e;
+	u32 feat_flags = 0;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(brcmf_feat_fwfeat_map); i++) {
+		e = &brcmf_feat_fwfeat_map[i];
+		if (!strcmp(e->fwid, drv->fwver)) {
+			feat_flags = e->feat_flags;
+			break;
+		}
+	}
+
+	if (!feat_flags)
+		return;
+
+	for (i = 0; i < BRCMF_FEAT_LAST; i++)
+		if (feat_flags & BIT(i))
+			brcmf_dbg(INFO, "enabling firmware feature: %s\n",
+				  brcmf_feat_names[i]);
+	drv->feat_flags |= feat_flags;
+}
+
 /**
  * brcmf_feat_iovar_int_get() - determine feature through iovar query.
  *
@@ -253,6 +289,8 @@ void brcmf_feat_attach(struct brcmf_pub *drvr)
 	}
 	brcmf_feat_iovar_int_get(ifp, BRCMF_FEAT_FWSUP, "sup_wpa");
 
+	brcmf_feat_firmware_overrides(drvr);
+
 	/* set chip related quirks */
 	switch (drvr->bus_if->chip) {
 	case BRCM_CC_43236_CHIP_ID:
-- 
cgit v1.2.3


From 486cdf21583e5b1fad488a3e4f0a5242a31c0ffa Mon Sep 17 00:00:00 2001
From: Mathieu Xhonneux <m.xhonneux@gmail.com>
Date: Thu, 26 Jul 2018 02:10:40 +0000
Subject: bpf: add End.DT6 action to bpf_lwt_seg6_action helper

The seg6local LWT provides the End.DT6 action, which allows to
decapsulate an outer IPv6 header containing a Segment Routing Header
(SRH), full specification is available here:

https://tools.ietf.org/html/draft-filsfils-spring-srv6-network-programming-05

This patch adds this action now to the seg6local BPF
interface. Since it is not mandatory that the inner IPv6 header also
contains a SRH, seg6_bpf_srh_state has been extended with a pointer to
a possible SRH of the outermost IPv6 header. This helps assessing if the
validation must be triggered or not, and avoids some calls to
ipv6_find_hdr.

v3: s/1/true, s/0/false for boolean values
v2: - changed true/false -> 1/0
    - preempt_enable no longer called in first conditional block

Signed-off-by: Mathieu Xhonneux <m.xhonneux@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/seg6_local.h |  4 ++-
 net/core/filter.c        | 88 ++++++++++++++++++++++++++++++++----------------
 net/ipv6/seg6_local.c    | 50 +++++++++++++++++----------
 3 files changed, 94 insertions(+), 48 deletions(-)

diff --git a/include/net/seg6_local.h b/include/net/seg6_local.h
index 661fd5b4d3e0..08359e2d8b35 100644
--- a/include/net/seg6_local.h
+++ b/include/net/seg6_local.h
@@ -21,10 +21,12 @@
 
 extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 			       u32 tbl_id);
+extern bool seg6_bpf_has_valid_srh(struct sk_buff *skb);
 
 struct seg6_bpf_srh_state {
-	bool valid;
+	struct ipv6_sr_hdr *srh;
 	u16 hdrlen;
+	bool valid;
 };
 
 DECLARE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
diff --git a/net/core/filter.c b/net/core/filter.c
index 104d560946da..7df1a0f1d1e1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4542,26 +4542,28 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 {
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
+	struct ipv6_sr_hdr *srh = srh_state->srh;
 	void *srh_tlvs, *srh_end, *ptr;
-	struct ipv6_sr_hdr *srh;
 	int srhoff = 0;
 
-	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+	if (srh == NULL)
 		return -EINVAL;
 
-	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
 	srh_tlvs = (void *)((char *)srh + ((srh->first_segment + 1) << 4));
 	srh_end = (void *)((char *)srh + sizeof(*srh) + srh_state->hdrlen);
 
 	ptr = skb->data + offset;
 	if (ptr >= srh_tlvs && ptr + len <= srh_end)
-		srh_state->valid = 0;
+		srh_state->valid = false;
 	else if (ptr < (void *)&srh->flags ||
 		 ptr + len > (void *)&srh->segments)
 		return -EFAULT;
 
 	if (unlikely(bpf_try_make_writable(skb, offset + len)))
 		return -EFAULT;
+	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+		return -EINVAL;
+	srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
 
 	memcpy(skb->data + offset, from, len);
 	return 0;
@@ -4577,52 +4579,78 @@ static const struct bpf_func_proto bpf_lwt_seg6_store_bytes_proto = {
 	.arg4_type	= ARG_CONST_SIZE
 };
 
-BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
-	   u32, action, void *, param, u32, param_len)
+static void bpf_update_srh_state(struct sk_buff *skb)
 {
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
-	struct ipv6_sr_hdr *srh;
 	int srhoff = 0;
-	int err;
-
-	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
-		return -EINVAL;
-	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
-
-	if (!srh_state->valid) {
-		if (unlikely((srh_state->hdrlen & 7) != 0))
-			return -EBADMSG;
-
-		srh->hdrlen = (u8)(srh_state->hdrlen >> 3);
-		if (unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3)))
-			return -EBADMSG;
 
-		srh_state->valid = 1;
+	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) {
+		srh_state->srh = NULL;
+	} else {
+		srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
+		srh_state->hdrlen = srh_state->srh->hdrlen << 3;
+		srh_state->valid = true;
 	}
+}
+
+BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
+	   u32, action, void *, param, u32, param_len)
+{
+	struct seg6_bpf_srh_state *srh_state =
+		this_cpu_ptr(&seg6_bpf_srh_states);
+	int hdroff = 0;
+	int err;
 
 	switch (action) {
 	case SEG6_LOCAL_ACTION_END_X:
+		if (!seg6_bpf_has_valid_srh(skb))
+			return -EBADMSG;
 		if (param_len != sizeof(struct in6_addr))
 			return -EINVAL;
 		return seg6_lookup_nexthop(skb, (struct in6_addr *)param, 0);
 	case SEG6_LOCAL_ACTION_END_T:
+		if (!seg6_bpf_has_valid_srh(skb))
+			return -EBADMSG;
+		if (param_len != sizeof(int))
+			return -EINVAL;
+		return seg6_lookup_nexthop(skb, NULL, *(int *)param);
+	case SEG6_LOCAL_ACTION_END_DT6:
+		if (!seg6_bpf_has_valid_srh(skb))
+			return -EBADMSG;
 		if (param_len != sizeof(int))
 			return -EINVAL;
+
+		if (ipv6_find_hdr(skb, &hdroff, IPPROTO_IPV6, NULL, NULL) < 0)
+			return -EBADMSG;
+		if (!pskb_pull(skb, hdroff))
+			return -EBADMSG;
+
+		skb_postpull_rcsum(skb, skb_network_header(skb), hdroff);
+		skb_reset_network_header(skb);
+		skb_reset_transport_header(skb);
+		skb->encapsulation = 0;
+
+		bpf_compute_data_pointers(skb);
+		bpf_update_srh_state(skb);
 		return seg6_lookup_nexthop(skb, NULL, *(int *)param);
 	case SEG6_LOCAL_ACTION_END_B6:
+		if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
+			return -EBADMSG;
 		err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6_INLINE,
 					  param, param_len);
 		if (!err)
-			srh_state->hdrlen =
-				((struct ipv6_sr_hdr *)param)->hdrlen << 3;
+			bpf_update_srh_state(skb);
+
 		return err;
 	case SEG6_LOCAL_ACTION_END_B6_ENCAP:
+		if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
+			return -EBADMSG;
 		err = bpf_push_seg6_encap(skb, BPF_LWT_ENCAP_SEG6,
 					  param, param_len);
 		if (!err)
-			srh_state->hdrlen =
-				((struct ipv6_sr_hdr *)param)->hdrlen << 3;
+			bpf_update_srh_state(skb);
+
 		return err;
 	default:
 		return -EINVAL;
@@ -4644,15 +4672,14 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 {
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
+	struct ipv6_sr_hdr *srh = srh_state->srh;
 	void *srh_end, *srh_tlvs, *ptr;
-	struct ipv6_sr_hdr *srh;
 	struct ipv6hdr *hdr;
 	int srhoff = 0;
 	int ret;
 
-	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+	if (unlikely(srh == NULL))
 		return -EINVAL;
-	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
 
 	srh_tlvs = (void *)((unsigned char *)srh + sizeof(*srh) +
 			((srh->first_segment + 1) << 4));
@@ -4682,8 +4709,11 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	hdr = (struct ipv6hdr *)skb->data;
 	hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
 
+	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
+		return -EINVAL;
+	srh_state->srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
 	srh_state->hdrlen += len;
-	srh_state->valid = 0;
+	srh_state->valid = false;
 	return 0;
 }
 
diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c
index e1025b493a18..60325dbfe88b 100644
--- a/net/ipv6/seg6_local.c
+++ b/net/ipv6/seg6_local.c
@@ -459,36 +459,57 @@ drop:
 
 DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
 
+bool seg6_bpf_has_valid_srh(struct sk_buff *skb)
+{
+	struct seg6_bpf_srh_state *srh_state =
+		this_cpu_ptr(&seg6_bpf_srh_states);
+	struct ipv6_sr_hdr *srh = srh_state->srh;
+
+	if (unlikely(srh == NULL))
+		return false;
+
+	if (unlikely(!srh_state->valid)) {
+		if ((srh_state->hdrlen & 7) != 0)
+			return false;
+
+		srh->hdrlen = (u8)(srh_state->hdrlen >> 3);
+		if (!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3))
+			return false;
+
+		srh_state->valid = true;
+	}
+
+	return true;
+}
+
 static int input_action_end_bpf(struct sk_buff *skb,
 				struct seg6_local_lwt *slwt)
 {
 	struct seg6_bpf_srh_state *srh_state =
 		this_cpu_ptr(&seg6_bpf_srh_states);
-	struct seg6_bpf_srh_state local_srh_state;
 	struct ipv6_sr_hdr *srh;
-	int srhoff = 0;
 	int ret;
 
 	srh = get_and_validate_srh(skb);
-	if (!srh)
-		goto drop;
+	if (!srh) {
+		kfree_skb(skb);
+		return -EINVAL;
+	}
 	advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
 
 	/* preempt_disable is needed to protect the per-CPU buffer srh_state,
 	 * which is also accessed by the bpf_lwt_seg6_* helpers
 	 */
 	preempt_disable();
+	srh_state->srh = srh;
 	srh_state->hdrlen = srh->hdrlen << 3;
-	srh_state->valid = 1;
+	srh_state->valid = true;
 
 	rcu_read_lock();
 	bpf_compute_data_pointers(skb);
 	ret = bpf_prog_run_save_cb(slwt->bpf.prog, skb);
 	rcu_read_unlock();
 
-	local_srh_state = *srh_state;
-	preempt_enable();
-
 	switch (ret) {
 	case BPF_OK:
 	case BPF_REDIRECT:
@@ -500,24 +521,17 @@ static int input_action_end_bpf(struct sk_buff *skb,
 		goto drop;
 	}
 
-	if (unlikely((local_srh_state.hdrlen & 7) != 0))
-		goto drop;
-
-	if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0)
-		goto drop;
-	srh = (struct ipv6_sr_hdr *)(skb->data + srhoff);
-	srh->hdrlen = (u8)(local_srh_state.hdrlen >> 3);
-
-	if (!local_srh_state.valid &&
-	    unlikely(!seg6_validate_srh(srh, (srh->hdrlen + 1) << 3)))
+	if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
 		goto drop;
 
+	preempt_enable();
 	if (ret != BPF_REDIRECT)
 		seg6_lookup_nexthop(skb, NULL, 0);
 
 	return dst_input(skb);
 
 drop:
+	preempt_enable();
 	kfree_skb(skb);
 	return -EINVAL;
 }
-- 
cgit v1.2.3


From 18dc5a4bbcc5c44be3062712f74180bae2c3c6b8 Mon Sep 17 00:00:00 2001
From: "H. Nikolaus Schaller" <hns@goldelico.com>
Date: Wed, 25 Jul 2018 07:55:04 +0200
Subject: wlcore: remove duplicate \n for some warnings

wl1271_warning() already appends a \n to the format,
so adding one to the warning string gives empty lines in the log.

Signed-off-by: H. Nikolaus Schaller <hns@goldelico.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/main.c b/drivers/net/wireless/ti/wlcore/main.c
index 37f785f601c1..89b0d0fade9f 100644
--- a/drivers/net/wireless/ti/wlcore/main.c
+++ b/drivers/net/wireless/ti/wlcore/main.c
@@ -6160,16 +6160,16 @@ static int wl1271_register_hw(struct wl1271 *wl)
 	}
 
 	if (oui_addr == 0xdeadbe && nic_addr == 0xef0000) {
-		wl1271_warning("Detected unconfigured mac address in nvs, derive from fuse instead.\n");
+		wl1271_warning("Detected unconfigured mac address in nvs, derive from fuse instead.");
 		if (!strcmp(pdev_data->family->name, "wl18xx")) {
-			wl1271_warning("This default nvs file can be removed from the file system\n");
+			wl1271_warning("This default nvs file can be removed from the file system");
 		} else {
-			wl1271_warning("Your device performance is not optimized.\n");
-			wl1271_warning("Please use the calibrator tool to configure your device.\n");
+			wl1271_warning("Your device performance is not optimized.");
+			wl1271_warning("Please use the calibrator tool to configure your device.");
 		}
 
 		if (wl->fuse_oui_addr == 0 && wl->fuse_nic_addr == 0) {
-			wl1271_warning("Fuse mac address is zero. using random mac\n");
+			wl1271_warning("Fuse mac address is zero. using random mac");
 			/* Use TI oui and a random nic */
 			oui_addr = WLCORE_TI_OUI_ADDRESS;
 			nic_addr = get_random_int();
-- 
cgit v1.2.3


From 37a634f60fd6dfbda2c312657eec7ef0750546e7 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Fri, 27 Jul 2018 18:30:23 +0200
Subject: wlcore: Set rx_status boottime_ns field on rx

When receiving a beacon or probe response, we should update the
boottime_ns field which is the timestamp the frame was received at.
(cf mac80211.h)

This fixes a scanning issue with Android since it relies on this
timestamp to determine when the AP has been seen for the last time
(via the nl80211 BSS_LAST_SEEN_BOOTTIME parameter).

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ti/wlcore/rx.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ti/wlcore/rx.c b/drivers/net/wireless/ti/wlcore/rx.c
index 0f15696195f8..078a4940bc5c 100644
--- a/drivers/net/wireless/ti/wlcore/rx.c
+++ b/drivers/net/wireless/ti/wlcore/rx.c
@@ -59,7 +59,7 @@ static u32 wlcore_rx_get_align_buf_size(struct wl1271 *wl, u32 pkt_len)
 static void wl1271_rx_status(struct wl1271 *wl,
 			     struct wl1271_rx_descriptor *desc,
 			     struct ieee80211_rx_status *status,
-			     u8 beacon)
+			     u8 beacon, u8 probe_rsp)
 {
 	memset(status, 0, sizeof(struct ieee80211_rx_status));
 
@@ -106,6 +106,9 @@ static void wl1271_rx_status(struct wl1271 *wl,
 		}
 	}
 
+	if (beacon || probe_rsp)
+		status->boottime_ns = ktime_get_boot_ns();
+
 	if (beacon)
 		wlcore_set_pending_regdomain_ch(wl, (u16)desc->channel,
 						status->band);
@@ -191,7 +194,8 @@ static int wl1271_rx_handle_data(struct wl1271 *wl, u8 *data, u32 length,
 	if (ieee80211_is_data_present(hdr->frame_control))
 		is_data = 1;
 
-	wl1271_rx_status(wl, desc, IEEE80211_SKB_RXCB(skb), beacon);
+	wl1271_rx_status(wl, desc, IEEE80211_SKB_RXCB(skb), beacon,
+			 ieee80211_is_probe_resp(hdr->frame_control));
 	wlcore_hw_set_rx_csum(wl, desc, skb);
 
 	seq_num = (le16_to_cpu(hdr->seq_ctrl) & IEEE80211_SCTL_SEQ) >> 4;
-- 
cgit v1.2.3


From 5685bee313e9e8577faebcb349706e299f486db5 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:45:35 +0800
Subject: atmel: Replace mdelay() with msleep() in probe_atmel_card()

probe_atmel_card() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/atmel/atmel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/atmel/atmel.c b/drivers/net/wireless/atmel/atmel.c
index f4f56f461b61..74538085cfb7 100644
--- a/drivers/net/wireless/atmel/atmel.c
+++ b/drivers/net/wireless/atmel/atmel.c
@@ -3677,7 +3677,7 @@ static int probe_atmel_card(struct net_device *dev)
 		atmel_write16(dev, GCR, 0x0060);
 
 	atmel_write16(dev, GCR, 0x0040);
-	mdelay(500);
+	msleep(500);
 
 	if (atmel_read16(dev, MR2) == 0) {
 		/* No stored firmware so load a small stub which just
-- 
cgit v1.2.3


From 1f821611f49a89d2258d256efedd618eda6344be Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Mon, 30 Jul 2018 22:22:59 +0900
Subject: lwt_bpf: remove unnecessary rcu_read_lock in run_lwt_bpf

run_lwt_bpf is called by bpf_{input/output/xmit}.
These functions are already protected by rcu_read_lock.
because lwtunnel_{input/output/xmit} holds rcu_read_lock
and then calls bpf_{input/output/xmit}.
So that rcu_read_lock in the run_lwt_bpf is unnecessary.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/lwt_bpf.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c
index e7e626fb87bb..a49c7baf62f8 100644
--- a/net/core/lwt_bpf.c
+++ b/net/core/lwt_bpf.c
@@ -50,10 +50,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 	 * mixing with BH RCU lock doesn't work.
 	 */
 	preempt_disable();
-	rcu_read_lock();
 	bpf_compute_data_pointers(skb);
 	ret = bpf_prog_run_save_cb(lwt->prog, skb);
-	rcu_read_unlock();
 
 	switch (ret) {
 	case BPF_OK:
-- 
cgit v1.2.3


From 622e938240db71365958824cc91af1bb5c481f5e Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:50:45 +0800
Subject: rtl818x: Replace mdelay() with msleep() in rtl8225se_rf_init

rtl8225se_rf_init() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().
This patch only replaces the mdelay() that has >20ms time to wait.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c b/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c
index fde89866fa8d..51e32df6120b 100644
--- a/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c
+++ b/drivers/net/wireless/realtek/rtl818x/rtl8180/rtl8225se.c
@@ -363,7 +363,7 @@ void rtl8225se_rf_init(struct ieee80211_hw *dev)
 	rtl8187se_rf_writereg(dev, 0x00, 0x0037); mdelay(11);
 	rtl8187se_rf_writereg(dev, 0x04, 0x0160); mdelay(11);
 	rtl8187se_rf_writereg(dev, 0x07, 0x0080); mdelay(11);
-	rtl8187se_rf_writereg(dev, 0x02, 0x088D); mdelay(221);
+	rtl8187se_rf_writereg(dev, 0x02, 0x088D); msleep(221);
 	rtl8187se_rf_writereg(dev, 0x00, 0x0137); mdelay(11);
 	rtl8187se_rf_writereg(dev, 0x07, 0x0000); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x07, 0x0180); mdelay(1);
@@ -386,7 +386,7 @@ void rtl8225se_rf_init(struct ieee80211_hw *dev)
 	rtl8187se_rf_writereg(dev, 0x00, 0x00BF); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x0D, 0x08DF); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x02, 0x004D); mdelay(1);
-	rtl8187se_rf_writereg(dev, 0x04, 0x0975); mdelay(31);
+	rtl8187se_rf_writereg(dev, 0x04, 0x0975); msleep(31);
 	rtl8187se_rf_writereg(dev, 0x00, 0x0197); mdelay(1);
 	rtl8187se_rf_writereg(dev, 0x05, 0x05AB); mdelay(1);
 
-- 
cgit v1.2.3


From 24ebfcbdd1ba623daa1ba140067d7b6102bcfe0d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 27 Jul 2018 21:05:49 +0800
Subject: rt2x00: remove redundant functions rt2x00mac_sta_{add/remove}

Only rt2800 subdriver of rt2x00 implement sta_add() and sta_remove(),
rt2x00mac_sta_add and rt2x00mac_sta_remove has no callers after
commit 9c87758cf089 ("rt2x00: call sta_add/remove directly in rt2800").
So can be removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ralink/rt2x00/rt2x00mac.c | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
index c380c1f56ba6..fa2fd64084ac 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00mac.c
@@ -527,24 +527,6 @@ int rt2x00mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 EXPORT_SYMBOL_GPL(rt2x00mac_set_key);
 #endif /* CONFIG_RT2X00_LIB_CRYPTO */
 
-int rt2x00mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		      struct ieee80211_sta *sta)
-{
-	struct rt2x00_dev *rt2x00dev = hw->priv;
-
-	return rt2x00dev->ops->lib->sta_add(rt2x00dev, vif, sta);
-}
-EXPORT_SYMBOL_GPL(rt2x00mac_sta_add);
-
-int rt2x00mac_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			 struct ieee80211_sta *sta)
-{
-	struct rt2x00_dev *rt2x00dev = hw->priv;
-
-	return rt2x00dev->ops->lib->sta_remove(rt2x00dev, sta);
-}
-EXPORT_SYMBOL_GPL(rt2x00mac_sta_remove);
-
 void rt2x00mac_sw_scan_start(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif,
 			     const u8 *mac_addr)
-- 
cgit v1.2.3


From 240b74fde35293f718c6cdfa486b3a005c4243c9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 30 Jul 2018 20:33:15 -0700
Subject: nfp: fix variable dereferenced before check in nfp_app_ctrl_rx_raw()

'app' is dereferenced before used for the devlink trace point.
In case FW is buggy and sends a control message to a VF queue
we should make sure app is not NULL.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_app.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h
index ccb244cf6c30..4e1eb3395648 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_app.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h
@@ -392,10 +392,11 @@ static inline void nfp_app_ctrl_rx(struct nfp_app *app, struct sk_buff *skb)
 static inline void
 nfp_app_ctrl_rx_raw(struct nfp_app *app, const void *data, unsigned int len)
 {
-	trace_devlink_hwmsg(priv_to_devlink(app->pf), true, 0, data, len);
+	if (!app || !app->type->ctrl_msg_rx_raw)
+		return;
 
-	if (app && app->type->ctrl_msg_rx_raw)
-		app->type->ctrl_msg_rx_raw(app, data, len);
+	trace_devlink_hwmsg(priv_to_devlink(app->pf), true, 0, data, len);
+	app->type->ctrl_msg_rx_raw(app, data, len);
 }
 
 static inline int nfp_app_eswitch_mode_get(struct nfp_app *app, u16 *mode)
-- 
cgit v1.2.3


From d692f1138a4bac2efd2c8656ca15556b63479e82 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 30 Jul 2018 17:42:28 -0700
Subject: bpf: Support bpf_get_socket_cookie in more prog types

bpf_get_socket_cookie() helper can be used to identify skb that
correspond to the same socket.

Though socket cookie can be useful in many other use-cases where socket is
available in program context. Specifically BPF_PROG_TYPE_CGROUP_SOCK_ADDR
and BPF_PROG_TYPE_SOCK_OPS programs can benefit from it so that one of
them can augment a value in a map prepared earlier by other program for
the same socket.

The patch adds support to call bpf_get_socket_cookie() from
BPF_PROG_TYPE_CGROUP_SOCK_ADDR and BPF_PROG_TYPE_SOCK_OPS.

It doesn't introduce new helpers. Instead it reuses same helper name
bpf_get_socket_cookie() but adds support to this helper to accept
`struct bpf_sock_addr` and `struct bpf_sock_ops`.

Documentation in bpf.h is changed in a way that should not break
automatic generation of markdown.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/uapi/linux/bpf.h | 14 ++++++++++++++
 net/core/filter.c        | 28 ++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 870113916cac..0ebaaf7f3568 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1371,6 +1371,20 @@ union bpf_attr {
  * 		A 8-byte long non-decreasing number on success, or 0 if the
  * 		socket field is missing inside *skb*.
  *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
+ * 	Description
+ * 		Equivalent to bpf_get_socket_cookie() helper that accepts
+ * 		*skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * 	Return
+ * 		A 8-byte long non-decreasing number.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
+ * 	Description
+ * 		Equivalent to bpf_get_socket_cookie() helper that accepts
+ * 		*skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * 	Return
+ * 		A 8-byte long non-decreasing number.
+ *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
diff --git a/net/core/filter.c b/net/core/filter.c
index 7df1a0f1d1e1..9bb9a4488e25 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3812,6 +3812,30 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx)
+{
+	return sock_gen_cookie(ctx->sk);
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = {
+	.func		= bpf_get_socket_cookie_sock_addr,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx)
+{
+	return sock_gen_cookie(ctx->sk);
+}
+
+static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = {
+	.func		= bpf_get_socket_cookie_sock_ops,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 BPF_CALL_1(bpf_get_socket_uid, struct sk_buff *, skb)
 {
 	struct sock *sk = sk_to_full_sk(skb->sk);
@@ -4818,6 +4842,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		default:
 			return NULL;
 		}
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_sock_addr_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -4960,6 +4986,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_map_update_proto;
 	case BPF_FUNC_sock_hash_update:
 		return &bpf_sock_hash_update_proto;
+	case BPF_FUNC_get_socket_cookie:
+		return &bpf_get_socket_cookie_sock_ops_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
-- 
cgit v1.2.3


From a40b712e4c4d09f6fa234872384da9705443d4e9 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 30 Jul 2018 17:42:29 -0700
Subject: bpf: Sync bpf.h to tools/

Sync bpf_get_socket_cookie() related bpf UAPI changes to tools/.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 870113916cac..0ebaaf7f3568 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1371,6 +1371,20 @@ union bpf_attr {
  * 		A 8-byte long non-decreasing number on success, or 0 if the
  * 		socket field is missing inside *skb*.
  *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
+ * 	Description
+ * 		Equivalent to bpf_get_socket_cookie() helper that accepts
+ * 		*skb*, but gets socket from **struct bpf_sock_addr** contex.
+ * 	Return
+ * 		A 8-byte long non-decreasing number.
+ *
+ * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
+ * 	Description
+ * 		Equivalent to bpf_get_socket_cookie() helper that accepts
+ * 		*skb*, but gets socket from **struct bpf_sock_ops** contex.
+ * 	Return
+ * 		A 8-byte long non-decreasing number.
+ *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  * 	Return
  * 		The owner UID of the socket associated to *skb*. If the socket
-- 
cgit v1.2.3


From 0289a2cca0a5b75a0167243429d9163ec3fdf279 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 30 Jul 2018 17:42:30 -0700
Subject: selftests/bpf: Add bpf_get_socket_cookie to bpf_helpers.h

Add missing helper to bpf_helpers.h that is used in tests and samples.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/bpf_helpers.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index f2f28b6c8915..19a424483f6e 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -65,6 +65,8 @@ static int (*bpf_xdp_adjust_head)(void *ctx, int offset) =
 	(void *) BPF_FUNC_xdp_adjust_head;
 static int (*bpf_xdp_adjust_meta)(void *ctx, int offset) =
 	(void *) BPF_FUNC_xdp_adjust_meta;
+static int (*bpf_get_socket_cookie)(void *ctx) =
+	(void *) BPF_FUNC_get_socket_cookie;
 static int (*bpf_setsockopt)(void *ctx, int level, int optname, void *optval,
 			     int optlen) =
 	(void *) BPF_FUNC_setsockopt;
-- 
cgit v1.2.3


From 194db0d95802fb48d03034fb6bfead1235de3450 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Mon, 30 Jul 2018 17:42:31 -0700
Subject: selftests/bpf: Test for get_socket_cookie

Add test to use get_socket_cookie() from BPF programs of types
BPF_PROG_TYPE_SOCK_OPS and BPF_PROG_TYPE_CGROUP_SOCK_ADDR.

The test attaches two programs to cgroup, runs TCP server and client in
the cgroup and checks that two operations are done properly on client
socket when user calls connect(2):

1. In BPF_CGROUP_INET6_CONNECT socket cookie is used as the key to write
   new value in a map for client socket.

2. In BPF_CGROUP_SOCK_OPS (BPF_SOCK_OPS_TCP_CONNECT_CB callback) the
   value written in "1." is found by socket cookie, since it's the same
   socket, and updated.

Finally the test verifies the value in the map.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile             |   6 +-
 tools/testing/selftests/bpf/socket_cookie_prog.c |  60 ++++++
 tools/testing/selftests/bpf/test_socket_cookie.c | 225 +++++++++++++++++++++++
 3 files changed, 289 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/socket_cookie_prog.c
 create mode 100644 tools/testing/selftests/bpf/test_socket_cookie.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 478bf1bcbbf5..1b28277998e2 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -22,7 +22,8 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 # Order correspond to 'make run_tests' order
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
-	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user
+	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
+	test_socket_cookie
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
@@ -33,7 +34,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
-	get_cgroup_id_kern.o
+	get_cgroup_id_kern.o socket_cookie_prog.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -60,6 +61,7 @@ $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
 $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
+$(OUTPUT)/test_socket_cookie: cgroup_helpers.c
 $(OUTPUT)/test_sockmap: cgroup_helpers.c
 $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
diff --git a/tools/testing/selftests/bpf/socket_cookie_prog.c b/tools/testing/selftests/bpf/socket_cookie_prog.c
new file mode 100644
index 000000000000..9ff8ac4b0bf6
--- /dev/null
+++ b/tools/testing/selftests/bpf/socket_cookie_prog.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/bpf.h>
+#include <sys/socket.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+struct bpf_map_def SEC("maps") socket_cookies = {
+	.type = BPF_MAP_TYPE_HASH,
+	.key_size = sizeof(__u64),
+	.value_size = sizeof(__u32),
+	.max_entries = 1 << 8,
+};
+
+SEC("cgroup/connect6")
+int set_cookie(struct bpf_sock_addr *ctx)
+{
+	__u32 cookie_value = 0xFF;
+	__u64 cookie_key;
+
+	if (ctx->family != AF_INET6 || ctx->user_family != AF_INET6)
+		return 1;
+
+	cookie_key = bpf_get_socket_cookie(ctx);
+	if (bpf_map_update_elem(&socket_cookies, &cookie_key, &cookie_value, 0))
+		return 0;
+
+	return 1;
+}
+
+SEC("sockops")
+int update_cookie(struct bpf_sock_ops *ctx)
+{
+	__u32 new_cookie_value;
+	__u32 *cookie_value;
+	__u64 cookie_key;
+
+	if (ctx->family != AF_INET6)
+		return 1;
+
+	if (ctx->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		return 1;
+
+	cookie_key = bpf_get_socket_cookie(ctx);
+
+	cookie_value = bpf_map_lookup_elem(&socket_cookies, &cookie_key);
+	if (!cookie_value)
+		return 1;
+
+	new_cookie_value = (ctx->local_port << 8) | *cookie_value;
+	bpf_map_update_elem(&socket_cookies, &cookie_key, &new_cookie_value, 0);
+
+	return 1;
+}
+
+int _version SEC("version") = 1;
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_socket_cookie.c b/tools/testing/selftests/bpf/test_socket_cookie.c
new file mode 100644
index 000000000000..68e108e4687a
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_socket_cookie.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+#define CG_PATH			"/foo"
+#define SOCKET_COOKIE_PROG	"./socket_cookie_prog.o"
+
+static int start_server(void)
+{
+	struct sockaddr_in6 addr;
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1) {
+		log_err("Failed to create server socket");
+		goto out;
+	}
+
+	memset(&addr, 0, sizeof(addr));
+	addr.sin6_family = AF_INET6;
+	addr.sin6_addr = in6addr_loopback;
+	addr.sin6_port = 0;
+
+	if (bind(fd, (const struct sockaddr *)&addr, sizeof(addr)) == -1) {
+		log_err("Failed to bind server socket");
+		goto close_out;
+	}
+
+	if (listen(fd, 128) == -1) {
+		log_err("Failed to listen on server socket");
+		goto close_out;
+	}
+
+	goto out;
+
+close_out:
+	close(fd);
+	fd = -1;
+out:
+	return fd;
+}
+
+static int connect_to_server(int server_fd)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	int fd;
+
+	fd = socket(AF_INET6, SOCK_STREAM, 0);
+	if (fd == -1) {
+		log_err("Failed to create client socket");
+		goto out;
+	}
+
+	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+		log_err("Failed to get server addr");
+		goto close_out;
+	}
+
+	if (connect(fd, (const struct sockaddr *)&addr, len) == -1) {
+		log_err("Fail to connect to server");
+		goto close_out;
+	}
+
+	goto out;
+
+close_out:
+	close(fd);
+	fd = -1;
+out:
+	return fd;
+}
+
+static int validate_map(struct bpf_map *map, int client_fd)
+{
+	__u32 cookie_expected_value;
+	struct sockaddr_in6 addr;
+	socklen_t len = sizeof(addr);
+	__u32 cookie_value;
+	__u64 cookie_key;
+	int err = 0;
+	int map_fd;
+
+	if (!map) {
+		log_err("Map not found in BPF object");
+		goto err;
+	}
+
+	map_fd = bpf_map__fd(map);
+
+	err = bpf_map_get_next_key(map_fd, NULL, &cookie_key);
+	if (err) {
+		log_err("Can't get cookie key from map");
+		goto out;
+	}
+
+	err = bpf_map_lookup_elem(map_fd, &cookie_key, &cookie_value);
+	if (err) {
+		log_err("Can't get cookie value from map");
+		goto out;
+	}
+
+	err = getsockname(client_fd, (struct sockaddr *)&addr, &len);
+	if (err) {
+		log_err("Can't get client local addr");
+		goto out;
+	}
+
+	cookie_expected_value = (ntohs(addr.sin6_port) << 8) | 0xFF;
+	if (cookie_value != cookie_expected_value) {
+		log_err("Unexpected value in map: %x != %x", cookie_value,
+			cookie_expected_value);
+		goto err;
+	}
+
+	goto out;
+err:
+	err = -1;
+out:
+	return err;
+}
+
+static int run_test(int cgfd)
+{
+	enum bpf_attach_type attach_type;
+	struct bpf_prog_load_attr attr;
+	struct bpf_program *prog;
+	struct bpf_object *pobj;
+	const char *prog_name;
+	int server_fd = -1;
+	int client_fd = -1;
+	int prog_fd = -1;
+	int err = 0;
+
+	memset(&attr, 0, sizeof(attr));
+	attr.file = SOCKET_COOKIE_PROG;
+	attr.prog_type = BPF_PROG_TYPE_UNSPEC;
+
+	err = bpf_prog_load_xattr(&attr, &pobj, &prog_fd);
+	if (err) {
+		log_err("Failed to load %s", attr.file);
+		goto out;
+	}
+
+	bpf_object__for_each_program(prog, pobj) {
+		prog_name = bpf_program__title(prog, /*needs_copy*/ false);
+
+		if (strcmp(prog_name, "cgroup/connect6") == 0) {
+			attach_type = BPF_CGROUP_INET6_CONNECT;
+		} else if (strcmp(prog_name, "sockops") == 0) {
+			attach_type = BPF_CGROUP_SOCK_OPS;
+		} else {
+			log_err("Unexpected prog: %s", prog_name);
+			goto err;
+		}
+
+		err = bpf_prog_attach(bpf_program__fd(prog), cgfd, attach_type,
+				      BPF_F_ALLOW_OVERRIDE);
+		if (err) {
+			log_err("Failed to attach prog %s", prog_name);
+			goto out;
+		}
+	}
+
+	server_fd = start_server();
+	if (server_fd == -1)
+		goto err;
+
+	client_fd = connect_to_server(server_fd);
+	if (client_fd == -1)
+		goto err;
+
+	if (validate_map(bpf_map__next(NULL, pobj), client_fd))
+		goto err;
+
+	goto out;
+err:
+	err = -1;
+out:
+	close(client_fd);
+	close(server_fd);
+	bpf_object__close(pobj);
+	printf("%s\n", err ? "FAILED" : "PASSED");
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	int cgfd = -1;
+	int err = 0;
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cgfd = create_and_get_cgroup(CG_PATH);
+	if (!cgfd)
+		goto err;
+
+	if (join_cgroup(CG_PATH))
+		goto err;
+
+	if (run_test(cgfd))
+		goto err;
+
+	goto out;
+err:
+	err = -1;
+out:
+	close(cgfd);
+	cleanup_cgroup_environment();
+	return err;
+}
-- 
cgit v1.2.3


From ebfac1d0c1663a47f6a0912930b9b8db4306e38b Mon Sep 17 00:00:00 2001
From: Kalle Valo <kvalo@codeaurora.org>
Date: Mon, 30 Jul 2018 21:56:43 +0300
Subject: ath10k: fix parenthesis alignment

These were recently introduced and found by checkpatch:

drivers/net/wireless/ath/ath10k/mac.c:6118: Alignment should match open parenthesis
drivers/net/wireless/ath/ath10k/mac.c:6121: Alignment should match open parenthesis
drivers/net/wireless/ath/ath10k/mac.c:6124: Alignment should match open parenthesis

Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index f068e2b9eacc..b6830fa16e99 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -6107,13 +6107,13 @@ static void ath10k_sta_rc_update_wk(struct work_struct *wk)
 
 		mode = chan_to_phymode(&def);
 		ath10k_dbg(ar, ATH10K_DBG_MAC, "mac update sta %pM peer bw %d phymode %d\n",
-				sta->addr, bw, mode);
+			   sta->addr, bw, mode);
 
 		err = ath10k_wmi_peer_set_param(ar, arvif->vdev_id, sta->addr,
-				WMI_PEER_PHYMODE, mode);
+						WMI_PEER_PHYMODE, mode);
 		if (err) {
 			ath10k_warn(ar, "failed to update STA %pM peer phymode %d: %d\n",
-					sta->addr, mode, err);
+				    sta->addr, mode, err);
 			goto exit;
 		}
 
-- 
cgit v1.2.3


From c81d28ad4fe8899f3a17b204eeec6d37d698dd5b Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:56:50 +0200
Subject: mtd: rawnand: orion: Avoid direct inclusion of asm headers

Include linux/sizes.h instead of asm/sizes.h to make code completely
arch independent.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/orion_nand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 1a4828442675..27cc902545f3 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -18,7 +18,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/io.h>
-#include <asm/sizes.h>
+#include <linux/sizes.h>
 #include <linux/platform_data/mtd-orion_nand.h>
 
 struct orion_nand_info {
-- 
cgit v1.2.3


From d166541e9031daff120cac212f1917eff93c07d3 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Wed, 18 Jul 2018 10:56:51 +0200
Subject: mtd: rawnand: orion: Handle cases where __LINUX_ARM_ARCH__ is not
 defined

Make sure __LINUX_ARM_ARCH__ is defined before testing its value.
This is needed if we want to allow selection of this driver when
COMPILE_TEST=y.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/orion_nand.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/orion_nand.c b/drivers/mtd/nand/raw/orion_nand.c
index 27cc902545f3..52d435285a3f 100644
--- a/drivers/mtd/nand/raw/orion_nand.c
+++ b/drivers/mtd/nand/raw/orion_nand.c
@@ -52,7 +52,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	void __iomem *io_base = chip->IO_ADDR_R;
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	uint64_t *buf64;
 #endif
 	int i = 0;
@@ -61,7 +61,7 @@ static void orion_nand_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 		*buf++ = readb(io_base);
 		len--;
 	}
-#if __LINUX_ARM_ARCH__ >= 5
+#if defined(__LINUX_ARM_ARCH__) && __LINUX_ARM_ARCH__ >= 5
 	buf64 = (uint64_t *)buf;
 	while (i < len/8) {
 		/*
-- 
cgit v1.2.3


From 760c435e0f85ed19e48a90d746ce1de2cd02def7 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 19 Jul 2018 00:09:12 +0200
Subject: mtd: rawnand: make subop helpers return unsigned values

A report from Colin Ian King pointed a CoverityScan issue where error
values on these helpers where not checked in the drivers. These
helpers can error out only in case of a software bug in driver code,
not because of a runtime/hardware error. Hence, let's WARN_ON() in this
case and return 0 which is harmless anyway.

Fixes: 8878b126df76 ("mtd: nand: add ->exec_op() implementation")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 44 ++++++++++++++++++++--------------------
 include/linux/mtd/rawnand.h      | 16 +++++++--------
 2 files changed, 30 insertions(+), 30 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index c4b74630f4c5..ef10beab99f5 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -2668,8 +2668,8 @@ static bool nand_subop_instr_is_valid(const struct nand_subop *subop,
 	return subop && instr_idx < subop->ninstrs;
 }
 
-static int nand_subop_get_start_off(const struct nand_subop *subop,
-				    unsigned int instr_idx)
+static unsigned int nand_subop_get_start_off(const struct nand_subop *subop,
+					     unsigned int instr_idx)
 {
 	if (instr_idx)
 		return 0;
@@ -2688,12 +2688,12 @@ static int nand_subop_get_start_off(const struct nand_subop *subop,
  *
  * Given an address instruction, returns the offset of the first cycle to issue.
  */
-int nand_subop_get_addr_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2710,14 +2710,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_addr_start_off);
  *
  * Given an address instruction, returns the number of address cycle to issue.
  */
-int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
-				unsigned int instr_idx)
+unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
+					 unsigned int instr_idx)
 {
 	int start_off, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR)
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    subop->instrs[instr_idx].type != NAND_OP_ADDR_INSTR))
+		return 0;
 
 	start_off = nand_subop_get_addr_start_off(subop, instr_idx);
 
@@ -2742,12 +2742,12 @@ EXPORT_SYMBOL_GPL(nand_subop_get_num_addr_cyc);
  *
  * Given a data instruction, returns the offset to start from.
  */
-int nand_subop_get_data_start_off(const struct nand_subop *subop,
-				  unsigned int instr_idx)
+unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop,
+					   unsigned int instr_idx)
 {
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	return nand_subop_get_start_off(subop, instr_idx);
 }
@@ -2764,14 +2764,14 @@ EXPORT_SYMBOL_GPL(nand_subop_get_data_start_off);
  *
  * Returns the length of the chunk of data to send/receive.
  */
-int nand_subop_get_data_len(const struct nand_subop *subop,
-			    unsigned int instr_idx)
+unsigned int nand_subop_get_data_len(const struct nand_subop *subop,
+				     unsigned int instr_idx)
 {
 	int start_off = 0, end_off;
 
-	if (!nand_subop_instr_is_valid(subop, instr_idx) ||
-	    !nand_instr_is_data(&subop->instrs[instr_idx]))
-		return -EINVAL;
+	if (WARN_ON(!nand_subop_instr_is_valid(subop, instr_idx) ||
+		    !nand_instr_is_data(&subop->instrs[instr_idx])))
+		return 0;
 
 	start_off = nand_subop_get_data_start_off(subop, instr_idx);
 
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index f60fad29eae6..598d356de83f 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -1007,14 +1007,14 @@ struct nand_subop {
 	unsigned int last_instr_end_off;
 };
 
-int nand_subop_get_addr_start_off(const struct nand_subop *subop,
-				  unsigned int op_id);
-int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
-				unsigned int op_id);
-int nand_subop_get_data_start_off(const struct nand_subop *subop,
-				  unsigned int op_id);
-int nand_subop_get_data_len(const struct nand_subop *subop,
-			    unsigned int op_id);
+unsigned int nand_subop_get_addr_start_off(const struct nand_subop *subop,
+					   unsigned int op_id);
+unsigned int nand_subop_get_num_addr_cyc(const struct nand_subop *subop,
+					 unsigned int op_id);
+unsigned int nand_subop_get_data_start_off(const struct nand_subop *subop,
+					   unsigned int op_id);
+unsigned int nand_subop_get_data_len(const struct nand_subop *subop,
+				     unsigned int op_id);
 
 /**
  * struct nand_op_parser_addr_constraints - Constraints for address instructions
-- 
cgit v1.2.3


From bdc4e58d5395fb45e22a54e01312f1abb22523ef Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 19 Jul 2018 22:53:50 +0200
Subject: mtd: rawnand: s3c2410: Error out when ->nrsets < 0 or ->sets == NULL

All of the code in the probe path assumes ->sets != NULL and
->nrsets > 0. Error out if that's not the case to avoid dereferencing a
NULL pointer.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/s3c2410.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 10d81f367d26..5a4a68790653 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -1134,8 +1134,13 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "mapped registers at %p\n", info->regs);
 
-	sets = (plat != NULL) ? plat->sets : NULL;
-	nr_sets = (plat != NULL) ? plat->nr_sets : 1;
+	if (!plat->sets || plat->nr_sets < 1) {
+		err = -EINVAL;
+		goto exit_error;
+	}
+
+	sets = plat->sets;
+	nr_sets = plat->nr_sets;
 
 	info->mtd_count = nr_sets;
 
@@ -1152,7 +1157,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	nmtd = info->mtds;
 
-	for (setno = 0; setno < nr_sets; setno++, nmtd++) {
+	for (setno = 0; setno < nr_sets; setno++, nmtd++, sets++) {
 		struct mtd_info *mtd = nand_to_mtd(&nmtd->chip);
 
 		pr_debug("initialising set %d (%p, info %p)\n",
@@ -1174,9 +1179,6 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 			goto exit_error;
 
 		s3c2410_nand_add_partition(info, nmtd, sets);
-
-		if (sets != NULL)
-			sets++;
 	}
 
 	/* initialise the hardware */
-- 
cgit v1.2.3


From 110ab1582670392c1d8b805e701f5b7b7efcb120 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Thu, 19 Jul 2018 22:47:38 +0200
Subject: mtd: rawnand: Remove unused caller_is_module() definition

Commit 260e89a6e0d6 ("mtd: core: tone down suggestion that dev.parent
should be set") removed the only user of caller_is_module() but forgot
to remove the definition itself. Let's remove it now.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index ef10beab99f5..e545e03a214e 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -6718,18 +6718,6 @@ err_free_buf:
 }
 EXPORT_SYMBOL(nand_scan_tail);
 
-/*
- * is_module_text_address() isn't exported, and it's mostly a pointless
- * test if this is a module _anyway_ -- they'd have to try _really_ hard
- * to call us from in-kernel code if the core NAND support is modular.
- */
-#ifdef MODULE
-#define caller_is_module() (1)
-#else
-#define caller_is_module() \
-	is_module_text_address((unsigned long)__builtin_return_address(0))
-#endif
-
 /**
  * nand_scan_with_ids - [NAND Interface] Scan for the NAND device
  * @mtd: MTD device structure
-- 
cgit v1.2.3


From 7da45139d264f3b7ead04e00ebb29b189cf9826e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Tue, 17 Jul 2018 09:08:02 +0200
Subject: mtd: rawnand: better name for the controller structure

In the raw NAND core, a NAND chip is described by a nand_chip structure,
while a NAND controller is described with a nand_hw_control structure
which is not very meaningful.

Rename this structure nand_controller.

As the structure gets renamed, it is logical to also rename the core
function initializing it from nand_hw_control_init() to
nand_controller_init().

Lastly, the 'hwcontrol' entry of the nand_chip structure is not
meaningful neither while it has the role of fallback when no controller
structure is provided by the driver (the controller driver is dumb and
can only control a single chip). Thus, it is renamed dummy_controller.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 10 +++++-----
 drivers/mtd/nand/raw/brcmnand/brcmnand.c     |  4 ++--
 drivers/mtd/nand/raw/docg4.c                 |  4 ++--
 drivers/mtd/nand/raw/fsl_elbc_nand.c         |  4 ++--
 drivers/mtd/nand/raw/fsl_ifc_nand.c          |  4 ++--
 drivers/mtd/nand/raw/jz4780_nand.c           |  7 ++++---
 drivers/mtd/nand/raw/marvell_nand.c          |  6 +++---
 drivers/mtd/nand/raw/mtk_nand.c              |  2 +-
 drivers/mtd/nand/raw/nand_base.c             |  4 ++--
 drivers/mtd/nand/raw/ndfc.c                  |  4 ++--
 drivers/mtd/nand/raw/omap2.c                 |  2 +-
 drivers/mtd/nand/raw/oxnas_nand.c            |  4 ++--
 drivers/mtd/nand/raw/qcom_nandc.c            |  4 ++--
 drivers/mtd/nand/raw/s3c2410.c               |  4 ++--
 drivers/mtd/nand/raw/sunxi_nand.c            |  6 +++---
 drivers/mtd/nand/raw/tango_nand.c            |  4 ++--
 drivers/mtd/nand/raw/tegra_nand.c            |  6 +++---
 drivers/mtd/nand/raw/txx9ndfmc.c             |  4 ++--
 include/linux/mtd/rawnand.h                  | 14 ++++++++------
 19 files changed, 50 insertions(+), 47 deletions(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 30dae4c9d439..855cc7729c43 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -216,7 +216,7 @@ struct atmel_nand_controller_caps {
 };
 
 struct atmel_nand_controller {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	const struct atmel_nand_controller_caps *caps;
 	struct device *dev;
 	struct regmap *smc;
@@ -227,7 +227,7 @@ struct atmel_nand_controller {
 };
 
 static inline struct atmel_nand_controller *
-to_nand_controller(struct nand_hw_control *ctl)
+to_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(ctl, struct atmel_nand_controller, base);
 }
@@ -239,7 +239,7 @@ struct atmel_smc_nand_controller {
 };
 
 static inline struct atmel_smc_nand_controller *
-to_smc_nand_controller(struct nand_hw_control *ctl)
+to_smc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_smc_nand_controller, base);
@@ -263,7 +263,7 @@ struct atmel_hsmc_nand_controller {
 };
 
 static inline struct atmel_hsmc_nand_controller *
-to_hsmc_nand_controller(struct nand_hw_control *ctl)
+to_hsmc_nand_controller(struct nand_controller *ctl)
 {
 	return container_of(to_nand_controller(ctl),
 			    struct atmel_hsmc_nand_controller, base);
@@ -1966,7 +1966,7 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 	struct device_node *np = dev->of_node;
 	int ret;
 
-	nand_hw_control_init(&nc->base);
+	nand_controller_init(&nc->base);
 	INIT_LIST_HEAD(&nc->chips);
 	nc->dev = dev;
 	nc->caps = caps;
diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 1306aaa7a8bf..2e5efa0f9ea2 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -114,7 +114,7 @@ enum {
 
 struct brcmnand_controller {
 	struct device		*dev;
-	struct nand_hw_control	controller;
+	struct nand_controller	controller;
 	void __iomem		*nand_base;
 	void __iomem		*nand_fc; /* flash cache */
 	void __iomem		*flash_dma_base;
@@ -2433,7 +2433,7 @@ int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc)
 
 	init_completion(&ctrl->done);
 	init_completion(&ctrl->dma_done);
-	nand_hw_control_init(&ctrl->controller);
+	nand_controller_init(&ctrl->controller);
 	INIT_LIST_HEAD(&ctrl->host_list);
 
 	/* NAND register range */
diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c
index bb96cb33cd6b..4dccdfba6140 100644
--- a/drivers/mtd/nand/raw/docg4.c
+++ b/drivers/mtd/nand/raw/docg4.c
@@ -1257,8 +1257,8 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	nand->ecc.strength = DOCG4_T;
 	nand->options = NAND_BUSWIDTH_16 | NAND_NO_SUBPAGE_WRITE;
 	nand->IO_ADDR_R = nand->IO_ADDR_W = doc->virtadr + DOC_IOSPACE_DATA;
-	nand->controller = &nand->hwcontrol;
-	nand_hw_control_init(nand->controller);
+	nand->controller = &nand->dummy_controller;
+	nand_controller_init(nand->controller);
 
 	/* methods */
 	nand->cmdfunc = docg4_command;
diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index 51f0b340bc0d..0aa54a949653 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -61,7 +61,7 @@ struct fsl_elbc_mtd {
 /* Freescale eLBC FCM controller information */
 
 struct fsl_elbc_fcm_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_elbc_mtd *chips[MAX_BANKS];
 
 	u8 __iomem *addr;        /* Address of assigned FCM buffer        */
@@ -879,7 +879,7 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 		}
 		elbc_fcm_ctrl->counter++;
 
-		nand_hw_control_init(&elbc_fcm_ctrl->controller);
+		nand_controller_init(&elbc_fcm_ctrl->controller);
 		fsl_lbc_ctrl_dev->nand = elbc_fcm_ctrl;
 	} else {
 		elbc_fcm_ctrl = fsl_lbc_ctrl_dev->nand;
diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 75d3c951f61a..96130d91e32c 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -51,7 +51,7 @@ struct fsl_ifc_mtd {
 
 /* overview of the fsl ifc controller */
 struct fsl_ifc_nand_ctrl {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct fsl_ifc_mtd *chips[FSL_IFC_BANK_COUNT];
 
 	void __iomem *addr;	/* Address of assigned IFC buffer	*/
@@ -1004,7 +1004,7 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 		ifc_nand_ctrl->addr = NULL;
 		fsl_ifc_ctrl_dev->nand = ifc_nand_ctrl;
 
-		nand_hw_control_init(&ifc_nand_ctrl->controller);
+		nand_controller_init(&ifc_nand_ctrl->controller);
 	} else {
 		ifc_nand_ctrl = fsl_ifc_ctrl_dev->nand;
 	}
diff --git a/drivers/mtd/nand/raw/jz4780_nand.c b/drivers/mtd/nand/raw/jz4780_nand.c
index e69f6ae4c539..49841dad347c 100644
--- a/drivers/mtd/nand/raw/jz4780_nand.c
+++ b/drivers/mtd/nand/raw/jz4780_nand.c
@@ -44,7 +44,7 @@ struct jz4780_nand_cs {
 struct jz4780_nand_controller {
 	struct device *dev;
 	struct jz4780_bch *bch;
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	unsigned int num_banks;
 	struct list_head chips;
 	int selected;
@@ -65,7 +65,8 @@ static inline struct jz4780_nand_chip *to_jz4780_nand_chip(struct mtd_info *mtd)
 	return container_of(mtd_to_nand(mtd), struct jz4780_nand_chip, chip);
 }
 
-static inline struct jz4780_nand_controller *to_jz4780_nand_controller(struct nand_hw_control *ctrl)
+static inline struct jz4780_nand_controller
+*to_jz4780_nand_controller(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct jz4780_nand_controller, controller);
 }
@@ -368,7 +369,7 @@ static int jz4780_nand_probe(struct platform_device *pdev)
 	nfc->dev = dev;
 	nfc->num_banks = num_banks;
 
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	ret = jz4780_nand_init_chips(nfc, pdev);
diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index 80a074cccb82..bd5f9a4b7b16 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -318,7 +318,7 @@ struct marvell_nfc_caps {
  * @dma_buf:		32-bit aligned buffer for DMA transfers (NFCv1 only)
  */
 struct marvell_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *core_clk;
@@ -335,7 +335,7 @@ struct marvell_nfc {
 	u8 *dma_buf;
 };
 
-static inline struct marvell_nfc *to_marvell_nfc(struct nand_hw_control *ctrl)
+static inline struct marvell_nfc *to_marvell_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct marvell_nfc, controller);
 }
@@ -2745,7 +2745,7 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index e6b14b79c8a8..7bc6be3f6ec0 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -145,7 +145,7 @@ struct mtk_nfc_clk {
 };
 
 struct mtk_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct mtk_ecc_config ecc_cfg;
 	struct mtk_nfc_clk clk;
 	struct mtk_ecc *ecc;
diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index e545e03a214e..dcdf0f373100 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5000,8 +5000,8 @@ static void nand_set_defaults(struct nand_chip *chip)
 		chip->read_buf = busw ? nand_read_buf16 : nand_read_buf;
 
 	if (!chip->controller) {
-		chip->controller = &chip->hwcontrol;
-		nand_hw_control_init(chip->controller);
+		chip->controller = &chip->dummy_controller;
+		nand_controller_init(chip->controller);
 	}
 
 	if (!chip->buf_align)
diff --git a/drivers/mtd/nand/raw/ndfc.c b/drivers/mtd/nand/raw/ndfc.c
index d8a806894937..540fa1a0ea24 100644
--- a/drivers/mtd/nand/raw/ndfc.c
+++ b/drivers/mtd/nand/raw/ndfc.c
@@ -39,7 +39,7 @@ struct ndfc_controller {
 	void __iomem *ndfcbase;
 	struct nand_chip chip;
 	int chip_select;
-	struct nand_hw_control ndfc_control;
+	struct nand_controller ndfc_control;
 };
 
 static struct ndfc_controller ndfc_ctrl[NDFC_MAX_CS];
@@ -218,7 +218,7 @@ static int ndfc_probe(struct platform_device *ofdev)
 	ndfc = &ndfc_ctrl[cs];
 	ndfc->chip_select = cs;
 
-	nand_hw_control_init(&ndfc->ndfc_control);
+	nand_controller_init(&ndfc->ndfc_control);
 	ndfc->ofdev = ofdev;
 	dev_set_drvdata(&ofdev->dev, ndfc);
 
diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index e50c64adc3c8..e943b2e5a5e2 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -145,7 +145,7 @@ static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
 
 /* Shared among all NAND instances to synchronize access to the ECC Engine */
-static struct nand_hw_control omap_gpmc_controller = {
+static struct nand_controller omap_gpmc_controller = {
 	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
 	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
 };
diff --git a/drivers/mtd/nand/raw/oxnas_nand.c b/drivers/mtd/nand/raw/oxnas_nand.c
index d649d5944826..01b00bb69c1e 100644
--- a/drivers/mtd/nand/raw/oxnas_nand.c
+++ b/drivers/mtd/nand/raw/oxnas_nand.c
@@ -32,7 +32,7 @@
 #define OXNAS_NAND_MAX_CHIPS	1
 
 struct oxnas_nand_ctrl {
-	struct nand_hw_control base;
+	struct nand_controller base;
 	void __iomem *io_base;
 	struct clk *clk;
 	struct nand_chip *chips[OXNAS_NAND_MAX_CHIPS];
@@ -96,7 +96,7 @@ static int oxnas_nand_probe(struct platform_device *pdev)
 	if (!oxnas)
 		return -ENOMEM;
 
-	nand_hw_control_init(&oxnas->base);
+	nand_controller_init(&oxnas->base);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	oxnas->io_base = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 645630953f38..aa6c3e026ef1 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -365,7 +365,7 @@ struct nandc_regs {
  *				from all connected NAND devices pagesize
  */
 struct qcom_nand_controller {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct list_head host_list;
 
 	struct device *dev;
@@ -2728,7 +2728,7 @@ static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 	INIT_LIST_HEAD(&nandc->desc_list);
 	INIT_LIST_HEAD(&nandc->host_list);
 
-	nand_hw_control_init(&nandc->controller);
+	nand_controller_init(&nandc->controller);
 
 	return 0;
 }
diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index 5a4a68790653..e8bf64832213 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -162,7 +162,7 @@ enum s3c_nand_clk_state {
  */
 struct s3c2410_nand_info {
 	/* mtd info */
-	struct nand_hw_control		controller;
+	struct nand_controller		controller;
 	struct s3c2410_nand_mtd		*mtds;
 	struct s3c2410_platform_nand	*platform;
 
@@ -1094,7 +1094,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, info);
 
-	nand_hw_control_init(&info->controller);
+	nand_controller_init(&info->controller);
 
 	/* get the clock source and enable it */
 
diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 4b11cd4a79be..07f3ff9a28f2 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -234,7 +234,7 @@ static inline struct sunxi_nand_chip *to_sunxi_nand(struct nand_chip *nand)
  *			controller events
  */
 struct sunxi_nfc {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	struct clk *ahb_clk;
@@ -247,7 +247,7 @@ struct sunxi_nfc {
 	struct dma_chan *dmac;
 };
 
-static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_hw_control *ctrl)
+static inline struct sunxi_nfc *to_sunxi_nfc(struct nand_controller *ctrl)
 {
 	return container_of(ctrl, struct sunxi_nfc, controller);
 }
@@ -2012,7 +2012,7 @@ static int sunxi_nfc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	nfc->dev = dev;
-	nand_hw_control_init(&nfc->controller);
+	nand_controller_init(&nfc->controller);
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index f2052fae21c7..dd7a26efdf4f 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -83,7 +83,7 @@
 #define MAX_CS		4
 
 struct tango_nfc {
-	struct nand_hw_control hw;
+	struct nand_controller hw;
 	void __iomem *reg_base;
 	void __iomem *mem_base;
 	void __iomem *pbus_base;
@@ -654,7 +654,7 @@ static int tango_nand_probe(struct platform_device *pdev)
 		return PTR_ERR(nfc->chan);
 
 	platform_set_drvdata(pdev, nfc);
-	nand_hw_control_init(&nfc->hw);
+	nand_controller_init(&nfc->hw);
 	nfc->freq_kHz = clk_get_rate(clk) / 1000;
 
 	for_each_child_of_node(pdev->dev.of_node, np) {
diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 56c0aa1bc81f..31c0d9ca9d23 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -164,7 +164,7 @@
 				HWSTATUS_RBSY_VALUE(NAND_STATUS_READY))
 
 struct tegra_nand_controller {
-	struct nand_hw_control controller;
+	struct nand_controller controller;
 	struct device *dev;
 	void __iomem *regs;
 	int irq;
@@ -187,7 +187,7 @@ struct tegra_nand_chip {
 };
 
 static inline struct tegra_nand_controller *
-			to_tegra_ctrl(struct nand_hw_control *hw_ctrl)
+			to_tegra_ctrl(struct nand_controller *hw_ctrl)
 {
 	return container_of(hw_ctrl, struct tegra_nand_controller, controller);
 }
@@ -1136,7 +1136,7 @@ static int tegra_nand_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	ctrl->dev = &pdev->dev;
-	nand_hw_control_init(&ctrl->controller);
+	nand_controller_init(&ctrl->controller);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ctrl->regs = devm_ioremap_resource(&pdev->dev, res);
diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 5fe9da8b4a0a..8f5bbbac4612 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -73,7 +73,7 @@ struct txx9ndfmc_drvdata {
 	void __iomem *base;
 	unsigned char hold;	/* in gbusclock */
 	unsigned char spw;	/* in gbusclock */
-	struct nand_hw_control hw_control;
+	struct nand_controller hw_control;
 };
 
 static struct platform_device *mtd_to_platdev(struct mtd_info *mtd)
@@ -303,7 +303,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 	dev_info(&dev->dev, "CLK:%ldMHz HOLD:%d SPW:%d\n",
 		 (gbusclk + 500000) / 1000000, hold, spw);
 
-	nand_hw_control_init(&drvdata->hw_control);
+	nand_controller_init(&drvdata->hw_control);
 
 	platform_set_drvdata(dev, drvdata);
 	txx9ndfmc_initialize(dev);
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 598d356de83f..93a2678e0f0d 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -510,20 +510,21 @@ struct nand_id {
 };
 
 /**
- * struct nand_hw_control - Control structure for hardware controller (e.g ECC generator) shared among independent devices
+ * struct nand_controller - Structure used to describe a NAND controller
+ *
  * @lock:               protection lock
  * @active:		the mtd device which holds the controller currently
  * @wq:			wait queue to sleep on if a NAND operation is in
  *			progress used instead of the per chip wait queue
  *			when a hw controller is available.
  */
-struct nand_hw_control {
+struct nand_controller {
 	spinlock_t lock;
 	struct nand_chip *active;
 	wait_queue_head_t wq;
 };
 
-static inline void nand_hw_control_init(struct nand_hw_control *nfc)
+static inline void nand_controller_init(struct nand_controller *nfc)
 {
 	nfc->active = NULL;
 	spin_lock_init(&nfc->lock);
@@ -1197,7 +1198,8 @@ int nand_op_parser_exec_op(struct nand_chip *chip,
  *			setting the read-retry mode. Mostly needed for MLC NAND.
  * @ecc:		[BOARDSPECIFIC] ECC control structure
  * @buf_align:		minimum buffer alignment required by a platform
- * @hwcontrol:		platform-specific hardware control structure
+ * @dummy_controller:	dummy controller implementation for drivers that can
+ *			only control a single chip
  * @erase:		[REPLACEABLE] erase function
  * @chip_delay:		[BOARDSPECIFIC] chip dependent delay for transferring
  *			data from array to read regs (tR).
@@ -1333,11 +1335,11 @@ struct nand_chip {
 	flstate_t state;
 
 	uint8_t *oob_poi;
-	struct nand_hw_control *controller;
+	struct nand_controller *controller;
 
 	struct nand_ecc_ctrl ecc;
 	unsigned long buf_align;
-	struct nand_hw_control hwcontrol;
+	struct nand_controller dummy_controller;
 
 	uint8_t *bbt;
 	struct nand_bbt_descr *bbt_td;
-- 
cgit v1.2.3


From 05b54c7bac906c443fd0b23ab8954e0560b33e5c Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Thu, 19 Jul 2018 01:05:46 +0200
Subject: mtd: rawnand: add hooks that may be called during nand_scan()

In order to remove the limitation that forbids dynamic allocation in
nand_scan_ident(), we must create a path that will be the same for all
controller drivers. The idea is to use nand_scan() instead of the widely
used nand_scan_ident()/nand_scan_tail() couple. In order to achieve
this, controller drivers will need to adjust some parameters between
these two functions depending on the NAND chip wired on them.

This takes the form of two new hooks (->{attach,detach}_chip()) that are
placed in a new nand_controller_ops structure, which is then attached
to the nand_controller object at driver initialization time.
->attach_chip() is called between nand_scan_ident() and
nand_scan_tail(), and ->detach_chip() is called in the error path of
nand_scan() and in nand_cleanup().

Note that some NAND controller drivers don't have a dedicated
nand_controller object and instead rely on the default/dummy one
embedded in nand_chip. If you're in this case and still want to
initialize the controller ops, you'll have to manipulate
chip->dummy_controller directly.

Last but not least, it's worth mentioning that we plan to move some of
the controller related hooks placed in nand_chip into
nand_controller_ops to make the separation between NAND chip and NAND
controller methods clearer.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 32 ++++++++++++++++++++++++++++++--
 include/linux/mtd/rawnand.h      | 21 +++++++++++++++++++++
 2 files changed, 51 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index dcdf0f373100..dea41fa25be1 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -6718,6 +6718,20 @@ err_free_buf:
 }
 EXPORT_SYMBOL(nand_scan_tail);
 
+static int nand_attach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->attach_chip)
+		return chip->controller->ops->attach_chip(chip);
+
+	return 0;
+}
+
+static void nand_detach(struct nand_chip *chip)
+{
+	if (chip->controller->ops && chip->controller->ops->detach_chip)
+		chip->controller->ops->detach_chip(chip);
+}
+
 /**
  * nand_scan_with_ids - [NAND Interface] Scan for the NAND device
  * @mtd: MTD device structure
@@ -6731,11 +6745,21 @@ EXPORT_SYMBOL(nand_scan_tail);
 int nand_scan_with_ids(struct mtd_info *mtd, int maxchips,
 		       struct nand_flash_dev *ids)
 {
+	struct nand_chip *chip = mtd_to_nand(mtd);
 	int ret;
 
 	ret = nand_scan_ident(mtd, maxchips, ids);
-	if (!ret)
-		ret = nand_scan_tail(mtd);
+	if (ret)
+		return ret;
+
+	ret = nand_attach(chip);
+	if (ret)
+		return ret;
+
+	ret = nand_scan_tail(mtd);
+	if (ret)
+		nand_detach(chip);
+
 	return ret;
 }
 EXPORT_SYMBOL(nand_scan_with_ids);
@@ -6763,7 +6787,11 @@ void nand_cleanup(struct nand_chip *chip)
 
 	/* Free manufacturer priv data. */
 	nand_manufacturer_cleanup(chip);
+
+	/* Free controller specific allocations after chip identification */
+	nand_detach(chip);
 }
+
 EXPORT_SYMBOL_GPL(nand_cleanup);
 
 /**
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 93a2678e0f0d..fbd6b29cf22c 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -509,6 +509,25 @@ struct nand_id {
 	int len;
 };
 
+/**
+ * struct nand_controller_ops - Controller operations
+ *
+ * @attach_chip: this method is called after the NAND detection phase after
+ *		 flash ID and MTD fields such as erase size, page size and OOB
+ *		 size have been set up. ECC requirements are available if
+ *		 provided by the NAND chip or device tree. Typically used to
+ *		 choose the appropriate ECC configuration and allocate
+ *		 associated resources.
+ *		 This hook is optional.
+ * @detach_chip: free all resources allocated/claimed in
+ *		 nand_controller_ops->attach_chip().
+ *		 This hook is optional.
+ */
+struct nand_controller_ops {
+	int (*attach_chip)(struct nand_chip *chip);
+	void (*detach_chip)(struct nand_chip *chip);
+};
+
 /**
  * struct nand_controller - Structure used to describe a NAND controller
  *
@@ -517,11 +536,13 @@ struct nand_id {
  * @wq:			wait queue to sleep on if a NAND operation is in
  *			progress used instead of the per chip wait queue
  *			when a hw controller is available.
+ * @ops:		NAND controller operations.
  */
 struct nand_controller {
 	spinlock_t lock;
 	struct nand_chip *active;
 	wait_queue_head_t wq;
+	const struct nand_controller_ops *ops;
 };
 
 static inline void nand_controller_init(struct nand_controller *nfc)
-- 
cgit v1.2.3


From d05a9524d7ec513648ad5e0fbd944e6ff3ddbd84 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 20 Jul 2018 00:38:13 +0200
Subject: mtd: rawnand: jz4740: Include gpio/consumer.h instead of gpio.h

GPIO consumers should no longer include <linux/gpio.h>, and instead
include <linux/gpio/consumer.h>.

Also, explicitly include <include/io.h> since it seems to be missing
after switching to <linux/gpio/consumer.h>.

This fixes a build error when selecting the driver without selecting
GPIOLIB, which can happen when COMPILE_TEST=y.

Fixes: 6968e07e8169 ("mtd: rawnand: jz4740: Allow selection of this driver when COMPILE_TEST=y")
Reported-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/jz4740_nand.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index 9bb8a89e09f9..a4052b03249c 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -13,6 +13,7 @@
  *
  */
 
+#include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -23,7 +24,7 @@
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 #include <linux/platform_data/jz4740/jz4740_nand.h>
 
-- 
cgit v1.2.3


From 49919d9c9e960c95712288ff08b96d4980464a5a Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 20 Jul 2018 11:57:38 +0200
Subject: mtd: rawnand: sunxi: Remove gpio.h and of_gpio.h inclusions

Commit ddd5ed3a90e7 ("mtd: rawnand: sunxi: Remove support for
GPIO-based Ready/Busy polling") removed GPIO-based RB polling. We no
longer need to include gpio headers.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/sunxi_nand.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 07f3ff9a28f2..2c0cbe72b449 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -29,14 +29,12 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/rawnand.h>
 #include <linux/mtd/partitions.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/dmaengine.h>
-#include <linux/gpio.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/reset.h>
-- 
cgit v1.2.3


From 89956d118e5a95afc00f51c8f2757a453d8848b9 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 20 Jul 2018 11:57:39 +0200
Subject: mtd: rawnand: atmel: Stop including gpio.h

gpio/consumer.h defines everything we need, and it's clearly stated in
gpio.h that GPIO consumers should directly stop including gpio.h if they
can.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 855cc7729c43..4d27401f1299 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -52,7 +52,6 @@
 #include <linux/dma-mapping.h>
 #include <linux/dmaengine.h>
 #include <linux/genalloc.h>
-#include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/mfd/syscon.h>
-- 
cgit v1.2.3


From c1070db3839fb12513d0717e1e03d04eda1e2d93 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 20 Jul 2018 11:57:40 +0200
Subject: mtd: rawnand: au1550nd: Remove unneeded gpio.h inclusion

We don't use the GPIO API in this driver, let's just remove the
<linux/gpio.h> inclusion.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/au1550nd.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/au1550nd.c b/drivers/mtd/nand/raw/au1550nd.c
index df0ef1f1e2f5..35f5c84cd331 100644
--- a/drivers/mtd/nand/raw/au1550nd.c
+++ b/drivers/mtd/nand/raw/au1550nd.c
@@ -8,7 +8,6 @@
  */
 
 #include <linux/slab.h>
-#include <linux/gpio.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
 #include <linux/mtd/mtd.h>
-- 
cgit v1.2.3


From b2342c1c80cebee38a2c219437f9382c2a2a1b5d Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:14:55 +0200
Subject: mtd: rawnand: davinci: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Also change the unused "struct device *dev" parameter of the driver
structure into a platform device to reuse it in the ->attach_chip()
hook.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/davinci_nand.c | 195 +++++++++++++++++++-----------------
 1 file changed, 102 insertions(+), 93 deletions(-)

diff --git a/drivers/mtd/nand/raw/davinci_nand.c b/drivers/mtd/nand/raw/davinci_nand.c
index 626c9363e460..40145e206a6b 100644
--- a/drivers/mtd/nand/raw/davinci_nand.c
+++ b/drivers/mtd/nand/raw/davinci_nand.c
@@ -53,7 +53,7 @@
 struct davinci_nand_info {
 	struct nand_chip	chip;
 
-	struct device		*dev;
+	struct platform_device	*pdev;
 
 	bool			is_readmode;
 
@@ -605,6 +605,104 @@ static struct davinci_nand_pdata
 }
 #endif
 
+static int davinci_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct davinci_nand_info *info = to_davinci_nand(mtd);
+	struct davinci_nand_pdata *pdata = nand_davinci_get_pdata(info->pdev);
+	int ret = 0;
+
+	if (IS_ERR(pdata))
+		return PTR_ERR(pdata);
+
+	switch (info->chip.ecc.mode) {
+	case NAND_ECC_NONE:
+		pdata->ecc_bits = 0;
+		break;
+	case NAND_ECC_SOFT:
+		pdata->ecc_bits = 0;
+		/*
+		 * This driver expects Hamming based ECC when ecc_mode is set
+		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
+		 * avoid adding an extra ->ecc_algo field to
+		 * davinci_nand_pdata.
+		 */
+		info->chip.ecc.algo = NAND_ECC_HAMMING;
+		break;
+	case NAND_ECC_HW:
+		if (pdata->ecc_bits == 4) {
+			/*
+			 * No sanity checks:  CPUs must support this,
+			 * and the chips may not use NAND_BUSWIDTH_16.
+			 */
+
+			/* No sharing 4-bit hardware between chipselects yet */
+			spin_lock_irq(&davinci_nand_lock);
+			if (ecc4_busy)
+				ret = -EBUSY;
+			else
+				ecc4_busy = true;
+			spin_unlock_irq(&davinci_nand_lock);
+
+			if (ret == -EBUSY)
+				return ret;
+
+			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
+			info->chip.ecc.correct = nand_davinci_correct_4bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
+			info->chip.ecc.bytes = 10;
+			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
+			info->chip.ecc.algo = NAND_ECC_BCH;
+		} else {
+			/* 1bit ecc hamming */
+			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
+			info->chip.ecc.correct = nand_davinci_correct_1bit;
+			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
+			info->chip.ecc.bytes = 3;
+			info->chip.ecc.algo = NAND_ECC_HAMMING;
+		}
+		info->chip.ecc.size = 512;
+		info->chip.ecc.strength = pdata->ecc_bits;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/*
+	 * Update ECC layout if needed ... for 1-bit HW ECC, the default
+	 * is OK, but it allocates 6 bytes when only 3 are needed (for
+	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
+	 * usable:  10 bytes are needed, not 6.
+	 */
+	if (pdata->ecc_bits == 4) {
+		int chunks = mtd->writesize / 512;
+
+		if (!chunks || mtd->oobsize < 16) {
+			dev_dbg(&info->pdev->dev, "too small\n");
+			return -EINVAL;
+		}
+
+		/* For small page chips, preserve the manufacturer's
+		 * badblock marking data ... and make sure a flash BBT
+		 * table marker fits in the free bytes.
+		 */
+		if (chunks == 1) {
+			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
+		} else if (chunks == 4 || chunks == 8) {
+			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
+		} else {
+			return -EIO;
+		}
+	}
+
+	return ret;
+}
+
+static const struct nand_controller_ops davinci_nand_controller_ops = {
+	.attach_chip = davinci_nand_attach_chip,
+};
+
 static int nand_davinci_probe(struct platform_device *pdev)
 {
 	struct davinci_nand_pdata	*pdata;
@@ -658,7 +756,7 @@ static int nand_davinci_probe(struct platform_device *pdev)
 		return -EADDRNOTAVAIL;
 	}
 
-	info->dev		= &pdev->dev;
+	info->pdev		= pdev;
 	info->base		= base;
 	info->vaddr		= vaddr;
 
@@ -708,97 +806,13 @@ static int nand_davinci_probe(struct platform_device *pdev)
 	spin_unlock_irq(&davinci_nand_lock);
 
 	/* Scan to find existence of the device(s) */
-	ret = nand_scan_ident(mtd, pdata->mask_chipsel ? 2 : 1, NULL);
+	info->chip.dummy_controller.ops = &davinci_nand_controller_ops;
+	ret = nand_scan(mtd, pdata->mask_chipsel ? 2 : 1);
 	if (ret < 0) {
 		dev_dbg(&pdev->dev, "no NAND chip(s) found\n");
 		return ret;
 	}
 
-	switch (info->chip.ecc.mode) {
-	case NAND_ECC_NONE:
-		pdata->ecc_bits = 0;
-		break;
-	case NAND_ECC_SOFT:
-		pdata->ecc_bits = 0;
-		/*
-		 * This driver expects Hamming based ECC when ecc_mode is set
-		 * to NAND_ECC_SOFT. Force ecc.algo to NAND_ECC_HAMMING to
-		 * avoid adding an extra ->ecc_algo field to
-		 * davinci_nand_pdata.
-		 */
-		info->chip.ecc.algo = NAND_ECC_HAMMING;
-		break;
-	case NAND_ECC_HW:
-		if (pdata->ecc_bits == 4) {
-			/* No sanity checks:  CPUs must support this,
-			 * and the chips may not use NAND_BUSWIDTH_16.
-			 */
-
-			/* No sharing 4-bit hardware between chipselects yet */
-			spin_lock_irq(&davinci_nand_lock);
-			if (ecc4_busy)
-				ret = -EBUSY;
-			else
-				ecc4_busy = true;
-			spin_unlock_irq(&davinci_nand_lock);
-
-			if (ret == -EBUSY)
-				return ret;
-
-			info->chip.ecc.calculate = nand_davinci_calculate_4bit;
-			info->chip.ecc.correct = nand_davinci_correct_4bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_4bit;
-			info->chip.ecc.bytes = 10;
-			info->chip.ecc.options = NAND_ECC_GENERIC_ERASED_CHECK;
-			info->chip.ecc.algo = NAND_ECC_BCH;
-		} else {
-			/* 1bit ecc hamming */
-			info->chip.ecc.calculate = nand_davinci_calculate_1bit;
-			info->chip.ecc.correct = nand_davinci_correct_1bit;
-			info->chip.ecc.hwctl = nand_davinci_hwctl_1bit;
-			info->chip.ecc.bytes = 3;
-			info->chip.ecc.algo = NAND_ECC_HAMMING;
-		}
-		info->chip.ecc.size = 512;
-		info->chip.ecc.strength = pdata->ecc_bits;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* Update ECC layout if needed ... for 1-bit HW ECC, the default
-	 * is OK, but it allocates 6 bytes when only 3 are needed (for
-	 * each 512 bytes).  For the 4-bit HW ECC, that default is not
-	 * usable:  10 bytes are needed, not 6.
-	 */
-	if (pdata->ecc_bits == 4) {
-		int	chunks = mtd->writesize / 512;
-
-		if (!chunks || mtd->oobsize < 16) {
-			dev_dbg(&pdev->dev, "too small\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		/* For small page chips, preserve the manufacturer's
-		 * badblock marking data ... and make sure a flash BBT
-		 * table marker fits in the free bytes.
-		 */
-		if (chunks == 1) {
-			mtd_set_ooblayout(mtd, &hwecc4_small_ooblayout_ops);
-		} else if (chunks == 4 || chunks == 8) {
-			mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-			info->chip.ecc.mode = NAND_ECC_HW_OOB_FIRST;
-		} else {
-			ret = -EIO;
-			goto err;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret < 0)
-		goto err;
-
 	if (pdata->parts)
 		ret = mtd_device_register(mtd, pdata->parts, pdata->nr_parts);
 	else
@@ -815,11 +829,6 @@ static int nand_davinci_probe(struct platform_device *pdev)
 err_cleanup_nand:
 	nand_cleanup(&info->chip);
 
-err:
-	spin_lock_irq(&davinci_nand_lock);
-	if (info->chip.ecc.mode == NAND_ECC_HW_SYNDROME)
-		ecc4_busy = false;
-	spin_unlock_irq(&davinci_nand_lock);
 	return ret;
 }
 
-- 
cgit v1.2.3


From d03af162bb09cdd321e422e375c2715f705c094b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:14:56 +0200
Subject: mtd: rawnand: denali: convert to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 drivers/mtd/nand/raw/denali.c | 139 +++++++++++++++++++++++-------------------
 1 file changed, 77 insertions(+), 62 deletions(-)

diff --git a/drivers/mtd/nand/raw/denali.c b/drivers/mtd/nand/raw/denali.c
index 4d53f41ada08..ca18612c4201 100644
--- a/drivers/mtd/nand/raw/denali.c
+++ b/drivers/mtd/nand/raw/denali.c
@@ -1205,62 +1205,12 @@ static int denali_multidev_fixup(struct denali_nand_info *denali)
 	return 0;
 }
 
-int denali_init(struct denali_nand_info *denali)
+static int denali_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &denali->nand;
 	struct mtd_info *mtd = nand_to_mtd(chip);
-	u32 features = ioread32(denali->reg + FEATURES);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
 	int ret;
 
-	mtd->dev.parent = denali->dev;
-	denali_hw_init(denali);
-
-	init_completion(&denali->complete);
-	spin_lock_init(&denali->irq_lock);
-
-	denali_clear_irq_all(denali);
-
-	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
-			       IRQF_SHARED, DENALI_NAND_NAME, denali);
-	if (ret) {
-		dev_err(denali->dev, "Unable to request IRQ\n");
-		return ret;
-	}
-
-	denali_enable_irq(denali);
-	denali_reset_banks(denali);
-
-	denali->active_bank = DENALI_INVALID_BANK;
-
-	nand_set_flash_node(chip, denali->dev->of_node);
-	/* Fallback to the default name if DT did not give "label" property */
-	if (!mtd->name)
-		mtd->name = "denali-nand";
-
-	chip->select_chip = denali_select_chip;
-	chip->read_byte = denali_read_byte;
-	chip->write_byte = denali_write_byte;
-	chip->read_word = denali_read_word;
-	chip->cmd_ctrl = denali_cmd_ctrl;
-	chip->dev_ready = denali_dev_ready;
-	chip->waitfunc = denali_waitfunc;
-
-	if (features & FEATURES__INDEX_ADDR) {
-		denali->host_read = denali_indexed_read;
-		denali->host_write = denali_indexed_write;
-	} else {
-		denali->host_read = denali_direct_read;
-		denali->host_write = denali_direct_write;
-	}
-
-	/* clk rate info is needed for setup_data_interface */
-	if (denali->clk_rate && denali->clk_x_rate)
-		chip->setup_data_interface = denali_setup_data_interface;
-
-	ret = nand_scan_ident(mtd, denali->max_banks, NULL);
-	if (ret)
-		goto disable_irq;
-
 	if (ioread32(denali->reg + FEATURES) & FEATURES__DMA)
 		denali->dma_avail = 1;
 
@@ -1293,7 +1243,7 @@ int denali_init(struct denali_nand_info *denali)
 				   mtd->oobsize - denali->oob_skip_bytes);
 	if (ret) {
 		dev_err(denali->dev, "Failed to setup ECC settings.\n");
-		goto disable_irq;
+		return ret;
 	}
 
 	dev_dbg(denali->dev,
@@ -1337,7 +1287,7 @@ int denali_init(struct denali_nand_info *denali)
 
 	ret = denali_multidev_fixup(denali);
 	if (ret)
-		goto disable_irq;
+		return ret;
 
 	/*
 	 * This buffer is DMA-mapped by denali_{read,write}_page_raw.  Do not
@@ -1345,26 +1295,92 @@ int denali_init(struct denali_nand_info *denali)
 	 * guarantee DMA-safe alignment.
 	 */
 	denali->buf = kmalloc(mtd->writesize + mtd->oobsize, GFP_KERNEL);
-	if (!denali->buf) {
-		ret = -ENOMEM;
-		goto disable_irq;
+	if (!denali->buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void denali_detach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct denali_nand_info *denali = mtd_to_denali(mtd);
+
+	kfree(denali->buf);
+}
+
+static const struct nand_controller_ops denali_controller_ops = {
+	.attach_chip = denali_attach_chip,
+	.detach_chip = denali_detach_chip,
+};
+
+int denali_init(struct denali_nand_info *denali)
+{
+	struct nand_chip *chip = &denali->nand;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	u32 features = ioread32(denali->reg + FEATURES);
+	int ret;
+
+	mtd->dev.parent = denali->dev;
+	denali_hw_init(denali);
+
+	init_completion(&denali->complete);
+	spin_lock_init(&denali->irq_lock);
+
+	denali_clear_irq_all(denali);
+
+	ret = devm_request_irq(denali->dev, denali->irq, denali_isr,
+			       IRQF_SHARED, DENALI_NAND_NAME, denali);
+	if (ret) {
+		dev_err(denali->dev, "Unable to request IRQ\n");
+		return ret;
+	}
+
+	denali_enable_irq(denali);
+	denali_reset_banks(denali);
+
+	denali->active_bank = DENALI_INVALID_BANK;
+
+	nand_set_flash_node(chip, denali->dev->of_node);
+	/* Fallback to the default name if DT did not give "label" property */
+	if (!mtd->name)
+		mtd->name = "denali-nand";
+
+	chip->select_chip = denali_select_chip;
+	chip->read_byte = denali_read_byte;
+	chip->write_byte = denali_write_byte;
+	chip->read_word = denali_read_word;
+	chip->cmd_ctrl = denali_cmd_ctrl;
+	chip->dev_ready = denali_dev_ready;
+	chip->waitfunc = denali_waitfunc;
+
+	if (features & FEATURES__INDEX_ADDR) {
+		denali->host_read = denali_indexed_read;
+		denali->host_write = denali_indexed_write;
+	} else {
+		denali->host_read = denali_direct_read;
+		denali->host_write = denali_direct_write;
 	}
 
-	ret = nand_scan_tail(mtd);
+	/* clk rate info is needed for setup_data_interface */
+	if (denali->clk_rate && denali->clk_x_rate)
+		chip->setup_data_interface = denali_setup_data_interface;
+
+	chip->dummy_controller.ops = &denali_controller_ops;
+	ret = nand_scan(mtd, denali->max_banks);
 	if (ret)
-		goto free_buf;
+		goto disable_irq;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(denali->dev, "Failed to register MTD: %d\n", ret);
 		goto cleanup_nand;
 	}
+
 	return 0;
 
 cleanup_nand:
 	nand_cleanup(chip);
-free_buf:
-	kfree(denali->buf);
 disable_irq:
 	denali_disable_irq(denali);
 
@@ -1377,7 +1393,6 @@ void denali_remove(struct denali_nand_info *denali)
 	struct mtd_info *mtd = nand_to_mtd(&denali->nand);
 
 	nand_release(mtd);
-	kfree(denali->buf);
 	denali_disable_irq(denali);
 }
 EXPORT_SYMBOL(denali_remove);
-- 
cgit v1.2.3


From 99dc9d95ec5a20dddb9f4462d576c63bfc06d8ad Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 10:35:57 +0200
Subject: mtd: rawnand: fsl_elbc: return meaningful values

Return -ENOTSUPP instead of -1 from ->chip_init_tail() before migrating
this driver to use nand_scan() and transform this function to be a
callback run by the core.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/fsl_elbc_nand.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index 0aa54a949653..b5637dce6d47 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -700,7 +700,7 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
 		dev_err(priv->dev,
 		        "fsl_elbc_init: page size %d is not supported\n",
 		        mtd->writesize);
-		return -1;
+		return -ENOTSUPP;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 5bf3e76b0abf6f527ae2223a308b7decebcdd23e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 10:37:40 +0200
Subject: mtd: rawnand: fsl_elbc: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>

Notes:
    "pw 947037"
---
 drivers/mtd/nand/raw/fsl_elbc_nand.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/mtd/nand/raw/fsl_elbc_nand.c b/drivers/mtd/nand/raw/fsl_elbc_nand.c
index b5637dce6d47..55f449b711fd 100644
--- a/drivers/mtd/nand/raw/fsl_elbc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_elbc_nand.c
@@ -637,9 +637,9 @@ static int fsl_elbc_wait(struct mtd_info *mtd, struct nand_chip *chip)
 	return (elbc_fcm_ctrl->mdr & 0xff) | NAND_STATUS_WP;
 }
 
-static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_elbc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_elbc_mtd *priv = nand_get_controller_data(chip);
 	struct fsl_lbc_ctrl *ctrl = priv->ctrl;
 	struct fsl_lbc_regs __iomem *lbc = ctrl->regs;
@@ -706,6 +706,10 @@ static int fsl_elbc_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_elbc_controller_ops = {
+	.attach_chip = fsl_elbc_attach_chip,
+};
+
 static int fsl_elbc_read_page(struct mtd_info *mtd, struct nand_chip *chip,
 			      uint8_t *buf, int oob_required, int page)
 {
@@ -910,15 +914,8 @@ static int fsl_elbc_nand_probe(struct platform_device *pdev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_elbc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_elbc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
-- 
cgit v1.2.3


From 37b0375d7398468b61c5e472e2634a4173f36627 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:14:58 +0200
Subject: mtd: rawnand: fsl_ifc: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/fsl_ifc_nand.c | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/mtd/nand/raw/fsl_ifc_nand.c b/drivers/mtd/nand/raw/fsl_ifc_nand.c
index 96130d91e32c..24f59d0066af 100644
--- a/drivers/mtd/nand/raw/fsl_ifc_nand.c
+++ b/drivers/mtd/nand/raw/fsl_ifc_nand.c
@@ -714,9 +714,9 @@ static int fsl_ifc_write_page(struct mtd_info *mtd, struct nand_chip *chip,
 	return nand_prog_page_end_op(chip);
 }
 
-static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
+static int fsl_ifc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct fsl_ifc_mtd *priv = nand_get_controller_data(chip);
 
 	dev_dbg(priv->dev, "%s: nand->numchips = %d\n", __func__,
@@ -757,6 +757,10 @@ static int fsl_ifc_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops fsl_ifc_controller_ops = {
+	.attach_chip = fsl_ifc_attach_chip,
+};
+
 static void fsl_ifc_sram_init(struct fsl_ifc_mtd *priv)
 {
 	struct fsl_ifc_ctrl *ctrl = priv->ctrl;
@@ -1046,15 +1050,8 @@ static int fsl_ifc_nand_probe(struct platform_device *dev)
 	if (ret)
 		goto err;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		goto err;
-
-	ret = fsl_ifc_chip_init_tail(mtd);
-	if (ret)
-		goto err;
-
-	ret = nand_scan_tail(mtd);
+	priv->chip.controller->ops = &fsl_ifc_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto err;
 
-- 
cgit v1.2.3


From 3bbddfa3d292c5d228049ab09a94076286d9e906 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:14:59 +0200
Subject: mtd: rawnand: fsmc: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/fsmc_nand.c | 148 +++++++++++++++++++++------------------
 1 file changed, 78 insertions(+), 70 deletions(-)

diff --git a/drivers/mtd/nand/raw/fsmc_nand.c b/drivers/mtd/nand/raw/fsmc_nand.c
index 59524d181bfe..f418236fa020 100644
--- a/drivers/mtd/nand/raw/fsmc_nand.c
+++ b/drivers/mtd/nand/raw/fsmc_nand.c
@@ -919,6 +919,82 @@ static int fsmc_nand_probe_config_dt(struct platform_device *pdev,
 	return 0;
 }
 
+static int fsmc_nand_attach_chip(struct nand_chip *nand)
+{
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct fsmc_nand_data *host = mtd_to_fsmc(mtd);
+
+	if (AMBA_REV_BITS(host->pid) >= 8) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+		case 224:
+		case 256:
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+
+		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
+
+		return 0;
+	}
+
+	switch (nand->ecc.mode) {
+	case NAND_ECC_HW:
+		dev_info(host->dev, "Using 1-bit HW ECC scheme\n");
+		nand->ecc.calculate = fsmc_read_hwecc_ecc1;
+		nand->ecc.correct = nand_correct_data;
+		nand->ecc.bytes = 3;
+		nand->ecc.strength = 1;
+		break;
+
+	case NAND_ECC_SOFT:
+		if (nand->ecc.algo == NAND_ECC_BCH) {
+			dev_info(host->dev,
+				 "Using 4-bit SW BCH ECC scheme\n");
+			break;
+		}
+
+	case NAND_ECC_ON_DIE:
+		break;
+
+	default:
+		dev_err(host->dev, "Unsupported ECC mode!\n");
+		return -ENOTSUPP;
+	}
+
+	/*
+	 * Don't set layout for BCH4 SW ECC. This will be
+	 * generated later in nand_bch_init() later.
+	 */
+	if (nand->ecc.mode == NAND_ECC_HW) {
+		switch (mtd->oobsize) {
+		case 16:
+		case 64:
+		case 128:
+			mtd_set_ooblayout(mtd,
+					  &fsmc_ecc1_ooblayout_ops);
+			break;
+		default:
+			dev_warn(host->dev,
+				 "No oob scheme defined for oobsize %d\n",
+				 mtd->oobsize);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops fsmc_nand_controller_ops = {
+	.attach_chip = fsmc_nand_attach_chip,
+};
+
 /*
  * fsmc_nand_probe - Probe function
  * @pdev:       platform device structure
@@ -1048,76 +1124,8 @@ static int __init fsmc_nand_probe(struct platform_device *pdev)
 	/*
 	 * Scan to find existence of the device
 	 */
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret) {
-		dev_err(&pdev->dev, "No NAND Device found!\n");
-		goto release_dma_write_chan;
-	}
-
-	if (AMBA_REV_BITS(host->pid) >= 8) {
-		switch (mtd->oobsize) {
-		case 16:
-		case 64:
-		case 128:
-		case 224:
-		case 256:
-			break;
-		default:
-			dev_warn(&pdev->dev, "No oob scheme defined for oobsize %d\n",
-				 mtd->oobsize);
-			ret = -EINVAL;
-			goto release_dma_write_chan;
-		}
-
-		mtd_set_ooblayout(mtd, &fsmc_ecc4_ooblayout_ops);
-	} else {
-		switch (nand->ecc.mode) {
-		case NAND_ECC_HW:
-			dev_info(&pdev->dev, "Using 1-bit HW ECC scheme\n");
-			nand->ecc.calculate = fsmc_read_hwecc_ecc1;
-			nand->ecc.correct = nand_correct_data;
-			nand->ecc.bytes = 3;
-			nand->ecc.strength = 1;
-			break;
-
-		case NAND_ECC_SOFT:
-			if (nand->ecc.algo == NAND_ECC_BCH) {
-				dev_info(&pdev->dev, "Using 4-bit SW BCH ECC scheme\n");
-				break;
-			}
-
-		case NAND_ECC_ON_DIE:
-			break;
-
-		default:
-			dev_err(&pdev->dev, "Unsupported ECC mode!\n");
-			goto release_dma_write_chan;
-		}
-
-		/*
-		 * Don't set layout for BCH4 SW ECC. This will be
-		 * generated later in nand_bch_init() later.
-		 */
-		if (nand->ecc.mode == NAND_ECC_HW) {
-			switch (mtd->oobsize) {
-			case 16:
-			case 64:
-			case 128:
-				mtd_set_ooblayout(mtd,
-						  &fsmc_ecc1_ooblayout_ops);
-				break;
-			default:
-				dev_warn(&pdev->dev,
-					 "No oob scheme defined for oobsize %d\n",
-					 mtd->oobsize);
-				ret = -EINVAL;
-				goto release_dma_write_chan;
-			}
-		}
-	}
-
-	/* Second stage of scan to fill MTD data-structures */
-	ret = nand_scan_tail(mtd);
+	nand->dummy_controller.ops = &fsmc_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		goto release_dma_write_chan;
 
-- 
cgit v1.2.3


From 5f8374d9b8b564e3be3309205d4d02d285c8d64a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:00 +0200
Subject: mtd: rawnand: gpmi: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c | 56 ++++++++++++++++++------------
 1 file changed, 33 insertions(+), 23 deletions(-)

diff --git a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
index 6294d018df65..1c1ebbc82824 100644
--- a/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
+++ b/drivers/mtd/nand/raw/gpmi-nand/gpmi-nand.c
@@ -744,9 +744,9 @@ static int gpmi_alloc_dma_buffer(struct gpmi_nand_data *this)
 	 * [2] Allocate a read/write data buffer.
 	 *     The gpmi_alloc_dma_buffer can be called twice.
 	 *     We allocate a PAGE_SIZE length buffer if gpmi_alloc_dma_buffer
-	 *     is called before the nand_scan_ident; and we allocate a buffer
-	 *     of the real NAND page size when the gpmi_alloc_dma_buffer is
-	 *     called after the nand_scan_ident.
+	 *     is called before the NAND identification; and we allocate a
+	 *     buffer of the real NAND page size when the gpmi_alloc_dma_buffer
+	 *     is called after.
 	 */
 	this->data_buffer_dma = kzalloc(mtd->writesize ?: PAGE_SIZE,
 					GFP_DMA | GFP_KERNEL);
@@ -1865,6 +1865,34 @@ static int gpmi_init_last(struct gpmi_nand_data *this)
 	return 0;
 }
 
+static int gpmi_nand_attach_chip(struct nand_chip *chip)
+{
+	struct gpmi_nand_data *this = nand_get_controller_data(chip);
+	int ret;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+		if (of_property_read_bool(this->dev->of_node,
+					  "fsl,no-blockmark-swap"))
+			this->swap_block_mark = false;
+	}
+	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
+		this->swap_block_mark ? "en" : "dis");
+
+	ret = gpmi_init_last(this);
+	if (ret)
+		return ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
+
+	return 0;
+}
+
+static const struct nand_controller_ops gpmi_nand_controller_ops = {
+	.attach_chip = gpmi_nand_attach_chip,
+};
+
 static int gpmi_nand_init(struct gpmi_nand_data *this)
 {
 	struct nand_chip *chip = &this->nand;
@@ -1905,26 +1933,8 @@ static int gpmi_nand_init(struct gpmi_nand_data *this)
 	if (ret)
 		goto err_out;
 
-	ret = nand_scan_ident(mtd, GPMI_IS_MX6(this) ? 2 : 1, NULL);
-	if (ret)
-		goto err_out;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-		if (of_property_read_bool(this->dev->of_node,
-						"fsl,no-blockmark-swap"))
-			this->swap_block_mark = false;
-	}
-	dev_dbg(this->dev, "Blockmark swapping %sabled\n",
-		this->swap_block_mark ? "en" : "dis");
-
-	ret = gpmi_init_last(this);
-	if (ret)
-		goto err_out;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-	ret = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &gpmi_nand_controller_ops;
+	ret = nand_scan(mtd, GPMI_IS_MX6(this) ? 2 : 1);
 	if (ret)
 		goto err_out;
 
-- 
cgit v1.2.3


From 07c1a4b3d8231910424bffabff5c0d51c80e2f6b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:01 +0200
Subject: mtd: rawnand: hisi504: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/hisi504_nand.c | 78 +++++++++++++++++++++----------------
 1 file changed, 44 insertions(+), 34 deletions(-)

diff --git a/drivers/mtd/nand/raw/hisi504_nand.c b/drivers/mtd/nand/raw/hisi504_nand.c
index a1e009c8e556..950dc7789296 100644
--- a/drivers/mtd/nand/raw/hisi504_nand.c
+++ b/drivers/mtd/nand/raw/hisi504_nand.c
@@ -709,9 +709,50 @@ static int hisi_nfc_ecc_probe(struct hinfc_host *host)
 	return 0;
 }
 
+static int hisi_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct hinfc_host *host = nand_get_controller_data(chip);
+	int flag;
+
+	host->buffer = dmam_alloc_coherent(host->dev,
+					   mtd->writesize + mtd->oobsize,
+					   &host->dma_buffer, GFP_KERNEL);
+	if (!host->buffer)
+		return -ENOMEM;
+
+	host->dma_oob = host->dma_buffer + mtd->writesize;
+	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
+
+	flag = hinfc_read(host, HINFC504_CON);
+	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
+	switch (mtd->writesize) {
+	case 2048:
+		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT);
+		break;
+	/*
+	 * TODO: add more pagesize support,
+	 * default pagesize has been set in hisi_nfc_host_init
+	 */
+	default:
+		dev_err(host->dev, "NON-2KB page size nand flash\n");
+		return -EINVAL;
+	}
+	hinfc_write(host, flag, HINFC504_CON);
+
+	if (chip->ecc.mode == NAND_ECC_HW)
+		hisi_nfc_ecc_probe(host);
+
+	return 0;
+}
+
+static const struct nand_controller_ops hisi_nfc_controller_ops = {
+	.attach_chip = hisi_nfc_attach_chip,
+};
+
 static int hisi_nfc_probe(struct platform_device *pdev)
 {
-	int ret = 0, irq, flag, max_chips = HINFC504_MAX_CHIP;
+	int ret = 0, irq, max_chips = HINFC504_MAX_CHIP;
 	struct device *dev = &pdev->dev;
 	struct hinfc_host *host;
 	struct nand_chip  *chip;
@@ -769,42 +810,11 @@ static int hisi_nfc_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = nand_scan_ident(mtd, max_chips, NULL);
+	chip->dummy_controller.ops = &hisi_nfc_controller_ops;
+	ret = nand_scan(mtd, max_chips);
 	if (ret)
 		return ret;
 
-	host->buffer = dmam_alloc_coherent(dev, mtd->writesize + mtd->oobsize,
-		&host->dma_buffer, GFP_KERNEL);
-	if (!host->buffer)
-		return -ENOMEM;
-
-	host->dma_oob = host->dma_buffer + mtd->writesize;
-	memset(host->buffer, 0xff, mtd->writesize + mtd->oobsize);
-
-	flag = hinfc_read(host, HINFC504_CON);
-	flag &= ~(HINFC504_CON_PAGESIZE_MASK << HINFC504_CON_PAGEISZE_SHIFT);
-	switch (mtd->writesize) {
-	case 2048:
-		flag |= (0x001 << HINFC504_CON_PAGEISZE_SHIFT); break;
-	/*
-	 * TODO: add more pagesize support,
-	 * default pagesize has been set in hisi_nfc_host_init
-	 */
-	default:
-		dev_err(dev, "NON-2KB page size nand flash\n");
-		return -EINVAL;
-	}
-	hinfc_write(host, flag, HINFC504_CON);
-
-	if (chip->ecc.mode == NAND_ECC_HW)
-		hisi_nfc_ecc_probe(host);
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "Err MTD partition=%d\n", ret);
-- 
cgit v1.2.3


From eef2b13a33141aa49e17831937acd744cc049844 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:02 +0200
Subject: mtd: rawnand: jz4780: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Harvey Hunt <harveyhuntnexus@gmail.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/jz4780_nand.c | 34 ++++++++++++++++------------------
 1 file changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/mtd/nand/raw/jz4780_nand.c b/drivers/mtd/nand/raw/jz4780_nand.c
index 49841dad347c..db4fa60bd52a 100644
--- a/drivers/mtd/nand/raw/jz4780_nand.c
+++ b/drivers/mtd/nand/raw/jz4780_nand.c
@@ -158,9 +158,8 @@ static int jz4780_nand_ecc_correct(struct mtd_info *mtd, u8 *dat,
 	return jz4780_bch_correct(nfc->bch, &params, dat, read_ecc);
 }
 
-static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *dev)
+static int jz4780_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct jz4780_nand_controller *nfc = to_jz4780_nand_controller(chip->controller);
 	int eccbytes;
@@ -171,7 +170,8 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	switch (chip->ecc.mode) {
 	case NAND_ECC_HW:
 		if (!nfc->bch) {
-			dev_err(dev, "HW BCH selected, but BCH controller not found\n");
+			dev_err(nfc->dev,
+				"HW BCH selected, but BCH controller not found\n");
 			return -ENODEV;
 		}
 
@@ -180,15 +180,16 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 		chip->ecc.correct = jz4780_nand_ecc_correct;
 		/* fall through */
 	case NAND_ECC_SOFT:
-		dev_info(dev, "using %s (strength %d, size %d, bytes %d)\n",
-			(nfc->bch) ? "hardware BCH" : "software ECC",
-			chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
+		dev_info(nfc->dev, "using %s (strength %d, size %d, bytes %d)\n",
+			 (nfc->bch) ? "hardware BCH" : "software ECC",
+			 chip->ecc.strength, chip->ecc.size, chip->ecc.bytes);
 		break;
 	case NAND_ECC_NONE:
-		dev_info(dev, "not using ECC\n");
+		dev_info(nfc->dev, "not using ECC\n");
 		break;
 	default:
-		dev_err(dev, "ECC mode %d not supported\n", chip->ecc.mode);
+		dev_err(nfc->dev, "ECC mode %d not supported\n",
+			chip->ecc.mode);
 		return -EINVAL;
 	}
 
@@ -200,7 +201,7 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	eccbytes = mtd->writesize / chip->ecc.size * chip->ecc.bytes;
 
 	if (eccbytes > mtd->oobsize - 2) {
-		dev_err(dev,
+		dev_err(nfc->dev,
 			"invalid ECC config: required %d ECC bytes, but only %d are available",
 			eccbytes, mtd->oobsize - 2);
 		return -EINVAL;
@@ -211,6 +212,10 @@ static int jz4780_nand_init_ecc(struct jz4780_nand_chip *nand, struct device *de
 	return 0;
 }
 
+static const struct nand_controller_ops jz4780_nand_controller_ops = {
+	.attach_chip = jz4780_nand_attach_chip,
+};
+
 static int jz4780_nand_init_chip(struct platform_device *pdev,
 				struct jz4780_nand_controller *nfc,
 				struct device_node *np,
@@ -280,15 +285,8 @@ static int jz4780_nand_init_chip(struct platform_device *pdev,
 	chip->controller = &nfc->controller;
 	nand_set_flash_node(chip, np);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = jz4780_nand_init_ecc(nand, dev);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	chip->controller->ops = &jz4780_nand_controller_ops;
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From f4a48d7bf89e073fb76a1ef18935d36169a3b6b1 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:04 +0200
Subject: mtd: rawnand: lpc32xx_slc: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/lpc32xx_slc.c | 77 +++++++++++++++++++++-----------------
 1 file changed, 42 insertions(+), 35 deletions(-)

diff --git a/drivers/mtd/nand/raw/lpc32xx_slc.c b/drivers/mtd/nand/raw/lpc32xx_slc.c
index 42820aa1abab..a4e8b7e75135 100644
--- a/drivers/mtd/nand/raw/lpc32xx_slc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_slc.c
@@ -779,6 +779,46 @@ static struct lpc32xx_nand_cfg_slc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+
+	/* OOB and ECC CPU and DMA work areas */
+	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
+
+	/*
+	 * Small page FLASH has a unique OOB layout, but large and huge
+	 * page FLASH use the standard layout. Small page FLASH uses a
+	 * custom BBT marker layout.
+	 */
+	if (mtd->writesize <= 512)
+		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+
+	/* These sizes remain the same regardless of page size */
+	chip->ecc.size = 256;
+	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
+	chip->ecc.prepad = 0;
+	chip->ecc.postpad = 0;
+
+	/*
+	 * Use a custom BBT marker setup for small page FLASH that
+	 * won't interfere with the ECC layout. Large and huge page
+	 * FLASH use the standard layout.
+	 */
+	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
+	    mtd->writesize <= 512) {
+		chip->bbt_td = &bbt_smallpage_main_descr;
+		chip->bbt_md = &bbt_smallpage_mirror_descr;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -884,41 +924,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/* Find NAND device */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma;
-
-	/* OOB and ECC CPU and DMA work areas */
-	host->ecc_buf = (uint32_t *)(host->data_buf + LPC32XX_DMA_DATA_SIZE);
-
-	/*
-	 * Small page FLASH has a unique OOB layout, but large and huge
-	 * page FLASH use the standard layout. Small page FLASH uses a
-	 * custom BBT marker layout.
-	 */
-	if (mtd->writesize <= 512)
-		mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-
-	/* These sizes remain the same regardless of page size */
-	chip->ecc.size = 256;
-	chip->ecc.bytes = LPC32XX_SLC_DEV_ECC_BYTES;
-	chip->ecc.prepad = chip->ecc.postpad = 0;
-
-	/*
-	 * Use a custom BBT marker setup for small page FLASH that
-	 * won't interfere with the ECC layout. Large and huge page
-	 * FLASH use the standard layout.
-	 */
-	if ((chip->bbt_options & NAND_BBT_USE_FLASH) &&
-	    mtd->writesize <= 512) {
-		chip->bbt_td = &bbt_smallpage_main_descr;
-		chip->bbt_md = &bbt_smallpage_mirror_descr;
-	}
-
-	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 */
-	res = nand_scan_tail(mtd);
+	chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto release_dma;
 
-- 
cgit v1.2.3


From 8831e48bad1425d237219dedde547f6061081807 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:05 +0200
Subject: mtd: rawnand: marvell: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/marvell_nand.c | 205 +++++++++++++++++++-----------------
 1 file changed, 108 insertions(+), 97 deletions(-)

diff --git a/drivers/mtd/nand/raw/marvell_nand.c b/drivers/mtd/nand/raw/marvell_nand.c
index bd5f9a4b7b16..218e09431d3d 100644
--- a/drivers/mtd/nand/raw/marvell_nand.c
+++ b/drivers/mtd/nand/raw/marvell_nand.c
@@ -2290,6 +2290,111 @@ static int marvell_nfc_setup_data_interface(struct mtd_info *mtd, int chipnr,
 	return 0;
 }
 
+static int marvell_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct marvell_nand_chip *marvell_nand = to_marvell_nand(chip);
+	struct marvell_nfc *nfc = to_marvell_nfc(chip->controller);
+	struct pxa3xx_nand_platform_data *pdata = dev_get_platdata(nfc->dev);
+	int ret;
+
+	if (pdata && pdata->flash_bbt)
+		chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		/*
+		 * We'll use a bad block table stored in-flash and don't
+		 * allow writing the bad block marker to the flash.
+		 */
+		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Save the chip-specific fields of NDCR */
+	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
+	if (chip->options & NAND_BUSWIDTH_16)
+		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
+
+	/*
+	 * On small page NANDs, only one cycle is needed to pass the
+	 * column address.
+	 */
+	if (mtd->writesize <= 512) {
+		marvell_nand->addr_cyc = 1;
+	} else {
+		marvell_nand->addr_cyc = 2;
+		marvell_nand->ndcr |= NDCR_RA_START;
+	}
+
+	/*
+	 * Now add the number of cycles needed to pass the row
+	 * address.
+	 *
+	 * Addressing a chip using CS 2 or 3 should also need the third row
+	 * cycle but due to inconsistance in the documentation and lack of
+	 * hardware to test this situation, this case is not supported.
+	 */
+	if (chip->options & NAND_ROW_ADDR_3)
+		marvell_nand->addr_cyc += 3;
+	else
+		marvell_nand->addr_cyc += 2;
+
+	if (pdata) {
+		chip->ecc.size = pdata->ecc_step_size;
+		chip->ecc.strength = pdata->ecc_strength;
+	}
+
+	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
+	if (ret) {
+		dev_err(nfc->dev, "ECC init failed: %d\n", ret);
+		return ret;
+	}
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		/*
+		 * Subpage write not available with hardware ECC, prohibit also
+		 * subpage read as in userspace subpage access would still be
+		 * allowed and subpage write, if used, would lead to numerous
+		 * uncorrectable ECC errors.
+		 */
+		chip->options |= NAND_NO_SUBPAGE_WRITE;
+	}
+
+	if (pdata || nfc->caps->legacy_of_bindings) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "pxa3xx_nand-0";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your NAND node, ie:
+		 *
+		 *	label = "main-storage";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nfc->dev),
+					   marvell_nand->sels[0].cs);
+		if (!mtd->name) {
+			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops marvell_nand_controller_ops = {
+	.attach_chip = marvell_nand_attach_chip,
+};
+
 static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 				  struct device_node *np)
 {
@@ -2432,105 +2537,10 @@ static int marvell_nand_chip_init(struct device *dev, struct marvell_nfc *nfc,
 	marvell_nand->ndtr1 = readl_relaxed(nfc->regs + NDTR1);
 
 	chip->options |= NAND_BUSWIDTH_AUTO;
-	ret = nand_scan_ident(mtd, marvell_nand->nsels, NULL);
-	if (ret) {
-		dev_err(dev, "could not identify the nand chip\n");
-		return ret;
-	}
-
-	if (pdata && pdata->flash_bbt)
-		chip->bbt_options |= NAND_BBT_USE_FLASH;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
-		/*
-		 * We'll use a bad block table stored in-flash and don't
-		 * allow writing the bad block marker to the flash.
-		 */
-		chip->bbt_options |= NAND_BBT_NO_OOB_BBM;
-		chip->bbt_td = &bbt_main_descr;
-		chip->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* Save the chip-specific fields of NDCR */
-	marvell_nand->ndcr = NDCR_PAGE_SZ(mtd->writesize);
-	if (chip->options & NAND_BUSWIDTH_16)
-		marvell_nand->ndcr |= NDCR_DWIDTH_M | NDCR_DWIDTH_C;
-
-	/*
-	 * On small page NANDs, only one cycle is needed to pass the
-	 * column address.
-	 */
-	if (mtd->writesize <= 512) {
-		marvell_nand->addr_cyc = 1;
-	} else {
-		marvell_nand->addr_cyc = 2;
-		marvell_nand->ndcr |= NDCR_RA_START;
-	}
-
-	/*
-	 * Now add the number of cycles needed to pass the row
-	 * address.
-	 *
-	 * Addressing a chip using CS 2 or 3 should also need the third row
-	 * cycle but due to inconsistance in the documentation and lack of
-	 * hardware to test this situation, this case is not supported.
-	 */
-	if (chip->options & NAND_ROW_ADDR_3)
-		marvell_nand->addr_cyc += 3;
-	else
-		marvell_nand->addr_cyc += 2;
-
-	if (pdata) {
-		chip->ecc.size = pdata->ecc_step_size;
-		chip->ecc.strength = pdata->ecc_strength;
-	}
-
-	ret = marvell_nand_ecc_init(mtd, &chip->ecc);
-	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		/*
-		 * Subpage write not available with hardware ECC, prohibit also
-		 * subpage read as in userspace subpage access would still be
-		 * allowed and subpage write, if used, would lead to numerous
-		 * uncorrectable ECC errors.
-		 */
-		chip->options |= NAND_NO_SUBPAGE_WRITE;
-	}
-
-	if (pdata || nfc->caps->legacy_of_bindings) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "pxa3xx_nand-0";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your NAND node, ie:
-		 *
-		 *	label = "main-storage";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nfc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nfc->dev),
-					   marvell_nand->sels[0].cs);
-		if (!mtd->name) {
-			dev_err(nfc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
 
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, marvell_nand->nsels);
 	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
+		dev_err(dev, "could not scan the nand chip\n");
 		return ret;
 	}
 
@@ -2746,6 +2756,7 @@ static int marvell_nfc_probe(struct platform_device *pdev)
 
 	nfc->dev = dev;
 	nand_controller_init(&nfc->controller);
+	nfc->controller.ops = &marvell_nand_controller_ops;
 	INIT_LIST_HEAD(&nfc->chips);
 
 	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-- 
cgit v1.2.3


From 1ce7826d7f178ab683d40d280ca079cf281aecff Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:06 +0200
Subject: mtd: rawnand: mtk: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Xiaolei Li <xiaolei.li@mediatek.com>
---
 drivers/mtd/nand/raw/mtk_nand.c | 75 ++++++++++++++++++++++++-----------------
 1 file changed, 44 insertions(+), 31 deletions(-)

diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
index 7bc6be3f6ec0..57b5ed1699e3 100644
--- a/drivers/mtd/nand/raw/mtk_nand.c
+++ b/drivers/mtd/nand/raw/mtk_nand.c
@@ -1250,13 +1250,54 @@ static int mtk_nfc_ecc_init(struct device *dev, struct mtd_info *mtd)
 	return 0;
 }
 
+static int mtk_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct mtk_nfc *nfc = nand_get_controller_data(chip);
+	struct mtk_nfc_nand_chip *mtk_nand = to_mtk_nand(chip);
+	int len;
+	int ret;
+
+	if (chip->options & NAND_BUSWIDTH_16) {
+		dev_err(dev, "16bits buswidth not supported");
+		return -EINVAL;
+	}
+
+	/* store bbt magic in page, cause OOB is not protected */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	ret = mtk_nfc_ecc_init(dev, mtd);
+	if (ret)
+		return ret;
+
+	ret = mtk_nfc_set_spare_per_sector(&mtk_nand->spare_per_sector, mtd);
+	if (ret)
+		return ret;
+
+	mtk_nfc_set_fdm(&mtk_nand->fdm, mtd);
+	mtk_nfc_set_bad_mark_ctl(&mtk_nand->bad_mark, mtd);
+
+	len = mtd->writesize + mtd->oobsize;
+	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
+	if (!nfc->buffer)
+		return  -ENOMEM;
+
+	return 0;
+}
+
+static const struct nand_controller_ops mtk_nfc_controller_ops = {
+	.attach_chip = mtk_nfc_attach_chip,
+};
+
 static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 				  struct device_node *np)
 {
 	struct mtk_nfc_nand_chip *chip;
 	struct nand_chip *nand;
 	struct mtd_info *mtd;
-	int nsels, len;
+	int nsels;
 	u32 tmp;
 	int ret;
 	int i;
@@ -1324,36 +1365,7 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
 
 	mtk_nfc_hw_init(nfc);
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
-	if (ret)
-		return ret;
-
-	/* store bbt magic in page, cause OOB is not protected */
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	ret = mtk_nfc_ecc_init(dev, mtd);
-	if (ret)
-		return -EINVAL;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		dev_err(dev, "16bits buswidth not supported");
-		return -EINVAL;
-	}
-
-	ret = mtk_nfc_set_spare_per_sector(&chip->spare_per_sector, mtd);
-	if (ret)
-		return ret;
-
-	mtk_nfc_set_fdm(&chip->fdm, mtd);
-	mtk_nfc_set_bad_mark_ctl(&chip->bad_mark, mtd);
-
-	len = mtd->writesize + mtd->oobsize;
-	nfc->buffer = devm_kzalloc(dev, len, GFP_KERNEL);
-	if (!nfc->buffer)
-		return  -ENOMEM;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
@@ -1443,6 +1455,7 @@ static int mtk_nfc_probe(struct platform_device *pdev)
 	spin_lock_init(&nfc->controller.lock);
 	init_waitqueue_head(&nfc->controller.wq);
 	INIT_LIST_HEAD(&nfc->chips);
+	nfc->controller.ops = &mtk_nfc_controller_ops;
 
 	/* probe defer if not ready */
 	nfc->ecc = of_mtk_ecc_get(np);
-- 
cgit v1.2.3


From 96fa8e6e2619c0fe5b5935404d6cc18bae92c7ae Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:07 +0200
Subject: mtd: rawnand: mxc: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/mxc_nand.c | 136 +++++++++++++++++++++-------------------
 1 file changed, 71 insertions(+), 65 deletions(-)

diff --git a/drivers/mtd/nand/raw/mxc_nand.c b/drivers/mtd/nand/raw/mxc_nand.c
index c6eff61e909d..4c9214dea424 100644
--- a/drivers/mtd/nand/raw/mxc_nand.c
+++ b/drivers/mtd/nand/raw/mxc_nand.c
@@ -1691,6 +1691,74 @@ static int mxcnd_probe_dt(struct mxc_nand_host *host)
 }
 #endif
 
+static int mxcnd_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct mxc_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = mtd->dev.parent;
+
+	switch (chip->ecc.mode) {
+	case NAND_ECC_HW:
+		chip->ecc.read_page = mxc_nand_read_page;
+		chip->ecc.read_page_raw = mxc_nand_read_page_raw;
+		chip->ecc.read_oob = mxc_nand_read_oob;
+		chip->ecc.write_page = mxc_nand_write_page_ecc;
+		chip->ecc.write_page_raw = mxc_nand_write_page_raw;
+		chip->ecc.write_oob = mxc_nand_write_oob;
+		break;
+
+	case NAND_ECC_SOFT:
+		break;
+
+	default:
+		return -EINVAL;
+	}
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH) {
+		chip->bbt_td = &bbt_main_descr;
+		chip->bbt_md = &bbt_mirror_descr;
+	}
+
+	/* Allocate the right size buffer now */
+	devm_kfree(dev, (void *)host->data_buf);
+	host->data_buf = devm_kzalloc(dev, mtd->writesize + mtd->oobsize,
+				      GFP_KERNEL);
+	if (!host->data_buf)
+		return -ENOMEM;
+
+	/* Call preset again, with correct writesize chip time */
+	host->devtype_data->preset(mtd);
+
+	if (!chip->ecc.bytes) {
+		if (host->eccsize == 8)
+			chip->ecc.bytes = 18;
+		else if (host->eccsize == 4)
+			chip->ecc.bytes = 9;
+	}
+
+	/*
+	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
+	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
+	 * into copying invalid data to/from the spare IO buffer, as this
+	 * might cause ECC data corruption when doing sub-page write to a
+	 * partially written page.
+	 */
+	host->used_oobsize = min(mtd->oobsize, 218U);
+
+	if (chip->ecc.mode == NAND_ECC_HW) {
+		if (is_imx21_nfc(host) || is_imx27_nfc(host))
+			chip->ecc.strength = 1;
+		else
+			chip->ecc.strength = (host->eccsize == 4) ? 4 : 8;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops mxcnd_controller_ops = {
+	.attach_chip = mxcnd_attach_chip,
+};
+
 static int mxcnd_probe(struct platform_device *pdev)
 {
 	struct nand_chip *this;
@@ -1830,71 +1898,9 @@ static int mxcnd_probe(struct platform_device *pdev)
 		host->devtype_data->irq_control(host, 1);
 	}
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, is_imx25_nfc(host) ? 4 : 1, NULL);
-	if (err)
-		goto escan;
-
-	switch (this->ecc.mode) {
-	case NAND_ECC_HW:
-		this->ecc.read_page = mxc_nand_read_page;
-		this->ecc.read_page_raw = mxc_nand_read_page_raw;
-		this->ecc.read_oob = mxc_nand_read_oob;
-		this->ecc.write_page = mxc_nand_write_page_ecc;
-		this->ecc.write_page_raw = mxc_nand_write_page_raw;
-		this->ecc.write_oob = mxc_nand_write_oob;
-		break;
-
-	case NAND_ECC_SOFT:
-		break;
-
-	default:
-		err = -EINVAL;
-		goto escan;
-	}
-
-	if (this->bbt_options & NAND_BBT_USE_FLASH) {
-		this->bbt_td = &bbt_main_descr;
-		this->bbt_md = &bbt_mirror_descr;
-	}
-
-	/* allocate the right size buffer now */
-	devm_kfree(&pdev->dev, (void *)host->data_buf);
-	host->data_buf = devm_kzalloc(&pdev->dev, mtd->writesize + mtd->oobsize,
-					GFP_KERNEL);
-	if (!host->data_buf) {
-		err = -ENOMEM;
-		goto escan;
-	}
-
-	/* Call preset again, with correct writesize this time */
-	host->devtype_data->preset(mtd);
-
-	if (!this->ecc.bytes) {
-		if (host->eccsize == 8)
-			this->ecc.bytes = 18;
-		else if (host->eccsize == 4)
-			this->ecc.bytes = 9;
-	}
-
-	/*
-	 * Experimentation shows that i.MX NFC can only handle up to 218 oob
-	 * bytes. Limit used_oobsize to 218 so as to not confuse copy_spare()
-	 * into copying invalid data to/from the spare IO buffer, as this
-	 * might cause ECC data corruption when doing sub-page write to a
-	 * partially written page.
-	 */
-	host->used_oobsize = min(mtd->oobsize, 218U);
-
-	if (this->ecc.mode == NAND_ECC_HW) {
-		if (is_imx21_nfc(host) || is_imx27_nfc(host))
-			this->ecc.strength = 1;
-		else
-			this->ecc.strength = (host->eccsize == 4) ? 4 : 8;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND device */
+	this->dummy_controller.ops = &mxcnd_controller_ops;
+	err = nand_scan(mtd, is_imx25_nfc(host) ? 4 : 1);
 	if (err)
 		goto escan;
 
-- 
cgit v1.2.3


From 5cbad9e3da60db9b3e5cf7e5b6a609578cbf93e0 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:08 +0200
Subject: mtd: rawnand: nandsim: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/nandsim.c | 82 +++++++++++++++++++++++-------------------
 1 file changed, 45 insertions(+), 37 deletions(-)

diff --git a/drivers/mtd/nand/raw/nandsim.c b/drivers/mtd/nand/raw/nandsim.c
index 8a3b36cfe5ea..71ac034aee9c 100644
--- a/drivers/mtd/nand/raw/nandsim.c
+++ b/drivers/mtd/nand/raw/nandsim.c
@@ -2192,6 +2192,48 @@ static void ns_nand_read_buf(struct mtd_info *mtd, u_char *buf, int len)
 	return;
 }
 
+static int ns_attach_chip(struct nand_chip *chip)
+{
+	unsigned int eccsteps, eccbytes;
+
+	if (!bch)
+		return 0;
+
+	if (!mtd_nand_has_bch()) {
+		NS_ERR("BCH ECC support is disabled\n");
+		return -EINVAL;
+	}
+
+	/* Use 512-byte ecc blocks */
+	eccsteps = nsmtd->writesize / 512;
+	eccbytes = ((bch * 13) + 7) / 8;
+
+	/* Do not bother supporting small page devices */
+	if (nsmtd->oobsize < 64 || !eccsteps) {
+		NS_ERR("BCH not available on small page devices\n");
+		return -EINVAL;
+	}
+
+	if (((eccbytes * eccsteps) + 2) > nsmtd->oobsize) {
+		NS_ERR("Invalid BCH value %u\n", bch);
+		return -EINVAL;
+	}
+
+	chip->ecc.mode = NAND_ECC_SOFT;
+	chip->ecc.algo = NAND_ECC_BCH;
+	chip->ecc.size = 512;
+	chip->ecc.strength = bch;
+	chip->ecc.bytes = eccbytes;
+
+	NS_INFO("Using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
+
+	return 0;
+}
+
+static const struct nand_controller_ops ns_controller_ops = {
+	.attach_chip = ns_attach_chip,
+};
+
 /*
  * Module initialization function
  */
@@ -2276,44 +2318,10 @@ static int __init ns_init_module(void)
 	if ((retval = parse_gravepages()) != 0)
 		goto error;
 
-	retval = nand_scan_ident(nsmtd, 1, NULL);
-	if (retval) {
-		NS_ERR("cannot scan NAND Simulator device\n");
-		goto error;
-	}
-
-	if (bch) {
-		unsigned int eccsteps, eccbytes;
-		if (!mtd_nand_has_bch()) {
-			NS_ERR("BCH ECC support is disabled\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		/* use 512-byte ecc blocks */
-		eccsteps = nsmtd->writesize/512;
-		eccbytes = (bch*13+7)/8;
-		/* do not bother supporting small page devices */
-		if ((nsmtd->oobsize < 64) || !eccsteps) {
-			NS_ERR("bch not available on small page devices\n");
-			retval = -EINVAL;
-			goto error;
-		}
-		if ((eccbytes*eccsteps+2) > nsmtd->oobsize) {
-			NS_ERR("invalid bch value %u\n", bch);
-			retval = -EINVAL;
-			goto error;
-		}
-		chip->ecc.mode = NAND_ECC_SOFT;
-		chip->ecc.algo = NAND_ECC_BCH;
-		chip->ecc.size = 512;
-		chip->ecc.strength = bch;
-		chip->ecc.bytes = eccbytes;
-		NS_INFO("using %u-bit/%u bytes BCH ECC\n", bch, chip->ecc.size);
-	}
-
-	retval = nand_scan_tail(nsmtd);
+	chip->dummy_controller.ops = &ns_controller_ops;
+	retval = nand_scan(nsmtd, 1);
 	if (retval) {
-		NS_ERR("can't register NAND Simulator\n");
+		NS_ERR("Could not scan NAND Simulator device\n");
 		goto error;
 	}
 
-- 
cgit v1.2.3


From 127483187a4afc143d59cb2809ccdb9399f7d27e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:10 +0200
Subject: mtd: rawnand: s3c2410: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/s3c2410.c | 30 +++++++++++++-----------------
 1 file changed, 13 insertions(+), 17 deletions(-)

diff --git a/drivers/mtd/nand/raw/s3c2410.c b/drivers/mtd/nand/raw/s3c2410.c
index e8bf64832213..c21e8892394a 100644
--- a/drivers/mtd/nand/raw/s3c2410.c
+++ b/drivers/mtd/nand/raw/s3c2410.c
@@ -915,20 +915,19 @@ static void s3c2410_nand_init_chip(struct s3c2410_nand_info *info,
 }
 
 /**
- * s3c2410_nand_update_chip - post probe update
- * @info: The controller instance.
- * @nmtd: The driver version of the MTD instance.
+ * s3c2410_nand_attach_chip - Init the ECC engine after NAND scan
+ * @chip: The NAND chip
  *
- * This routine is called after the chip probe has successfully completed
- * and the relevant per-chip information updated. This call ensure that
+ * This hook is called by the core after the identification of the NAND chip,
+ * once the relevant per-chip information is up to date.. This call ensure that
  * we update the internal state accordingly.
  *
  * The internal state is currently limited to the ECC state information.
 */
-static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
-				    struct s3c2410_nand_mtd *nmtd)
+static int s3c2410_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nmtd->chip;
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct s3c2410_nand_info *info = s3c2410_nand_mtd_toinfo(mtd);
 
 	switch (chip->ecc.mode) {
 
@@ -998,6 +997,10 @@ static int s3c2410_nand_update_chip(struct s3c2410_nand_info *info,
 	return 0;
 }
 
+static const struct nand_controller_ops s3c24xx_nand_controller_ops = {
+	.attach_chip = s3c2410_nand_attach_chip,
+};
+
 static const struct of_device_id s3c24xx_nand_dt_ids[] = {
 	{
 		.compatible = "samsung,s3c2410-nand",
@@ -1095,6 +1098,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, info);
 
 	nand_controller_init(&info->controller);
+	info->controller.ops = &s3c24xx_nand_controller_ops;
 
 	/* get the clock source and enable it */
 
@@ -1166,15 +1170,7 @@ static int s3c24xx_nand_probe(struct platform_device *pdev)
 		mtd->dev.parent = &pdev->dev;
 		s3c2410_nand_init_chip(info, nmtd, sets);
 
-		err = nand_scan_ident(mtd, (sets) ? sets->nr_chips : 1, NULL);
-		if (err)
-			goto exit_error;
-
-		err = s3c2410_nand_update_chip(info, nmtd);
-		if (err < 0)
-			goto exit_error;
-
-		err = nand_scan_tail(mtd);
+		err = nand_scan(mtd, sets ? sets->nr_chips : 1);
 		if (err)
 			goto exit_error;
 
-- 
cgit v1.2.3


From 5f20da0fe8af638266a5e8449ab5ebfe6112c2c0 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:11 +0200
Subject: mtd: rawnand: sh_flctl: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/sh_flctl.c | 36 +++++++++++++++---------------------
 1 file changed, 15 insertions(+), 21 deletions(-)

diff --git a/drivers/mtd/nand/raw/sh_flctl.c b/drivers/mtd/nand/raw/sh_flctl.c
index c7abceffcc40..bb8866e05ff7 100644
--- a/drivers/mtd/nand/raw/sh_flctl.c
+++ b/drivers/mtd/nand/raw/sh_flctl.c
@@ -1002,10 +1002,17 @@ static void flctl_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	flctl->index += len;
 }
 
-static int flctl_chip_init_tail(struct mtd_info *mtd)
+static int flctl_chip_attach_chip(struct nand_chip *chip)
 {
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct sh_flctl *flctl = mtd_to_flctl(mtd);
-	struct nand_chip *chip = &flctl->chip;
+
+	/*
+	 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
+	 * Add the SEL_16BIT flag in flctl->flcmncr_base.
+	 */
+	if (chip->options & NAND_BUSWIDTH_16)
+		flctl->flcmncr_base |= SEL_16BIT;
 
 	if (mtd->writesize == 512) {
 		flctl->page_size = 0;
@@ -1063,6 +1070,10 @@ static int flctl_chip_init_tail(struct mtd_info *mtd)
 	return 0;
 }
 
+static const struct nand_controller_ops flctl_nand_controller_ops = {
+	.attach_chip = flctl_chip_attach_chip,
+};
+
 static irqreturn_t flctl_handle_flste(int irq, void *dev_id)
 {
 	struct sh_flctl *flctl = dev_id;
@@ -1191,25 +1202,8 @@ static int flctl_probe(struct platform_device *pdev)
 
 	flctl_setup_dma(flctl);
 
-	ret = nand_scan_ident(flctl_mtd, 1, NULL);
-	if (ret)
-		goto err_chip;
-
-	if (nand->options & NAND_BUSWIDTH_16) {
-		/*
-		 * NAND_BUSWIDTH_16 may have been set by nand_scan_ident().
-		 * Add the SEL_16BIT flag in pdata->flcmncr_val and re-assign
-		 * flctl->flcmncr_base to pdata->flcmncr_val.
-		 */
-		pdata->flcmncr_val |= SEL_16BIT;
-		flctl->flcmncr_base = pdata->flcmncr_val;
-	}
-
-	ret = flctl_chip_init_tail(flctl_mtd);
-	if (ret)
-		goto err_chip;
-
-	ret = nand_scan_tail(flctl_mtd);
+	nand->dummy_controller.ops = &flctl_nand_controller_ops;
+	ret = nand_scan(flctl_mtd, 1);
 	if (ret)
 		goto err_chip;
 
-- 
cgit v1.2.3


From 2a4d9c16e8d10ecee4422f90f6a47acf737e3447 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:13 +0200
Subject: mtd: rawnand: sunxi: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/sunxi_nand.c | 43 +++++++++++++++++----------------------
 1 file changed, 19 insertions(+), 24 deletions(-)

diff --git a/drivers/mtd/nand/raw/sunxi_nand.c b/drivers/mtd/nand/raw/sunxi_nand.c
index 2c0cbe72b449..1f0b7ee38df5 100644
--- a/drivers/mtd/nand/raw/sunxi_nand.c
+++ b/drivers/mtd/nand/raw/sunxi_nand.c
@@ -1814,12 +1814,21 @@ static void sunxi_nand_ecc_cleanup(struct nand_ecc_ctrl *ecc)
 	}
 }
 
-static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
-			       struct device_node *np)
+static int sunxi_nand_attach_chip(struct nand_chip *nand)
 {
-	struct nand_chip *nand = mtd_to_nand(mtd);
+	struct mtd_info *mtd = nand_to_mtd(nand);
+	struct nand_ecc_ctrl *ecc = &nand->ecc;
+	struct device_node *np = nand_get_flash_node(nand);
 	int ret;
 
+	if (nand->bbt_options & NAND_BBT_USE_FLASH)
+		nand->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (nand->options & NAND_NEED_SCRAMBLING)
+		nand->options |= NAND_NO_SUBPAGE_WRITE;
+
+	nand->options |= NAND_SUBPAGE_READ;
+
 	if (!ecc->size) {
 		ecc->size = nand->ecc_step_ds;
 		ecc->strength = nand->ecc_strength_ds;
@@ -1844,6 +1853,10 @@ static int sunxi_nand_ecc_init(struct mtd_info *mtd, struct nand_ecc_ctrl *ecc,
 	return 0;
 }
 
+static const struct nand_controller_ops sunxi_nand_controller_ops = {
+	.attach_chip = sunxi_nand_attach_chip,
+};
+
 static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 				struct device_node *np)
 {
@@ -1909,6 +1922,8 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	/* Default tR value specified in the ONFI spec (chapter 4.15.1) */
 	nand->chip_delay = 200;
 	nand->controller = &nfc->controller;
+	nand->controller->ops = &sunxi_nand_controller_ops;
+
 	/*
 	 * Set the ECC mode to the default value in case nothing is specified
 	 * in the DT.
@@ -1925,30 +1940,10 @@ static int sunxi_nand_chip_init(struct device *dev, struct sunxi_nfc *nfc,
 	mtd = nand_to_mtd(nand);
 	mtd->dev.parent = dev;
 
-	ret = nand_scan_ident(mtd, nsels, NULL);
+	ret = nand_scan(mtd, nsels);
 	if (ret)
 		return ret;
 
-	if (nand->bbt_options & NAND_BBT_USE_FLASH)
-		nand->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (nand->options & NAND_NEED_SCRAMBLING)
-		nand->options |= NAND_NO_SUBPAGE_WRITE;
-
-	nand->options |= NAND_SUBPAGE_READ;
-
-	ret = sunxi_nand_ecc_init(mtd, &nand->ecc, np);
-	if (ret) {
-		dev_err(dev, "ECC init failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(dev, "nand_scan_tail failed: %d\n", ret);
-		return ret;
-	}
-
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret) {
 		dev_err(dev, "failed to register mtd device: %d\n", ret);
-- 
cgit v1.2.3


From 6a9035ceb980ac7ded378fa83f73d9664128777c Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:14 +0200
Subject: mtd: rawnand: tango: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/tango_nand.c | 40 +++++++++++++++++++++++----------------
 1 file changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/mtd/nand/raw/tango_nand.c b/drivers/mtd/nand/raw/tango_nand.c
index dd7a26efdf4f..72698691727d 100644
--- a/drivers/mtd/nand/raw/tango_nand.c
+++ b/drivers/mtd/nand/raw/tango_nand.c
@@ -517,6 +517,28 @@ static int tango_set_timings(struct mtd_info *mtd, int csline,
 	return 0;
 }
 
+static int tango_attach_chip(struct nand_chip *chip)
+{
+	struct nand_ecc_ctrl *ecc = &chip->ecc;
+
+	ecc->mode = NAND_ECC_HW;
+	ecc->algo = NAND_ECC_BCH;
+	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
+
+	ecc->read_page_raw = tango_read_page_raw;
+	ecc->write_page_raw = tango_write_page_raw;
+	ecc->read_page = tango_read_page;
+	ecc->write_page = tango_write_page;
+	ecc->read_oob = tango_read_oob;
+	ecc->write_oob = tango_write_oob;
+
+	return 0;
+}
+
+static const struct nand_controller_ops tango_controller_ops = {
+	.attach_chip = tango_attach_chip,
+};
+
 static int chip_init(struct device *dev, struct device_node *np)
 {
 	u32 cs;
@@ -566,22 +588,7 @@ static int chip_init(struct device *dev, struct device_node *np)
 	mtd_set_ooblayout(mtd, &tango_nand_ooblayout_ops);
 	mtd->dev.parent = dev;
 
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		return err;
-
-	ecc->mode = NAND_ECC_HW;
-	ecc->algo = NAND_ECC_BCH;
-	ecc->bytes = DIV_ROUND_UP(ecc->strength * FIELD_ORDER, BITS_PER_BYTE);
-
-	ecc->read_page_raw = tango_read_page_raw;
-	ecc->write_page_raw = tango_write_page_raw;
-	ecc->read_page = tango_read_page;
-	ecc->write_page = tango_write_page;
-	ecc->read_oob = tango_read_oob;
-	ecc->write_oob = tango_write_oob;
-
-	err = nand_scan_tail(mtd);
+	err = nand_scan(mtd, 1);
 	if (err)
 		return err;
 
@@ -655,6 +662,7 @@ static int tango_nand_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, nfc);
 	nand_controller_init(&nfc->hw);
+	nfc->hw.ops = &tango_controller_ops;
 	nfc->freq_kHz = clk_get_rate(clk) / 1000;
 
 	for_each_child_of_node(pdev->dev.of_node, np) {
-- 
cgit v1.2.3


From a001058a9aa291ee85ba5454891aa947658ae694 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:15 +0200
Subject: mtd: rawnand: txx9ndfmc: rename nand controller internal structure

As already done in the core, calling a struct nand_controller
'hw_control' is misleading. Use the same name as in nand_base.c:
'controller'.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/txx9ndfmc.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 8f5bbbac4612..9019022774f7 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -73,7 +73,7 @@ struct txx9ndfmc_drvdata {
 	void __iomem *base;
 	unsigned char hold;	/* in gbusclock */
 	unsigned char spw;	/* in gbusclock */
-	struct nand_controller hw_control;
+	struct nand_controller controller;
 };
 
 static struct platform_device *mtd_to_platdev(struct mtd_info *mtd)
@@ -303,7 +303,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 	dev_info(&dev->dev, "CLK:%ldMHz HOLD:%d SPW:%d\n",
 		 (gbusclk + 500000) / 1000000, hold, spw);
 
-	nand_controller_init(&drvdata->hw_control);
+	nand_controller_init(&drvdata->controller);
 
 	platform_set_drvdata(dev, drvdata);
 	txx9ndfmc_initialize(dev);
@@ -337,7 +337,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->ecc.bytes = 3;
 		chip->ecc.strength = 1;
 		chip->chip_delay = 100;
-		chip->controller = &drvdata->hw_control;
+		chip->controller = &drvdata->controller;
 
 		nand_set_controller_data(chip, txx9_priv);
 		txx9_priv->dev = dev;
-- 
cgit v1.2.3


From 962c35ef1e68346ae9c9691e14670f0ee96dcdbd Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:17 +0200
Subject: mtd: rawnand: vf610: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Reviewed-by: Stefan Agner <stefan@agner.ch>
---
 drivers/mtd/nand/raw/vf610_nfc.c | 127 ++++++++++++++++++++-------------------
 1 file changed, 66 insertions(+), 61 deletions(-)

diff --git a/drivers/mtd/nand/raw/vf610_nfc.c b/drivers/mtd/nand/raw/vf610_nfc.c
index d5a22fc96878..6f6dcbf9095b 100644
--- a/drivers/mtd/nand/raw/vf610_nfc.c
+++ b/drivers/mtd/nand/raw/vf610_nfc.c
@@ -747,6 +747,69 @@ static void vf610_nfc_init_controller(struct vf610_nfc *nfc)
 	}
 }
 
+static int vf610_nfc_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct vf610_nfc *nfc = mtd_to_nfc(mtd);
+
+	vf610_nfc_init_controller(nfc);
+
+	/* Bad block options. */
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	/* Single buffer only, max 256 OOB minus ECC status */
+	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
+		dev_err(nfc->dev, "Unsupported flash page size\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.mode != NAND_ECC_HW)
+		return 0;
+
+	if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
+		dev_err(nfc->dev, "Unsupported flash with hwecc\n");
+		return -ENXIO;
+	}
+
+	if (chip->ecc.size != mtd->writesize) {
+		dev_err(nfc->dev, "Step size needs to be page size\n");
+		return -ENXIO;
+	}
+
+	/* Only 64 byte ECC layouts known */
+	if (mtd->oobsize > 64)
+		mtd->oobsize = 64;
+
+	/* Use default large page ECC layout defined in NAND core */
+	mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
+	if (chip->ecc.strength == 32) {
+		nfc->ecc_mode = ECC_60_BYTE;
+		chip->ecc.bytes = 60;
+	} else if (chip->ecc.strength == 24) {
+		nfc->ecc_mode = ECC_45_BYTE;
+		chip->ecc.bytes = 45;
+	} else {
+		dev_err(nfc->dev, "Unsupported ECC strength\n");
+		return -ENXIO;
+	}
+
+	chip->ecc.read_page = vf610_nfc_read_page;
+	chip->ecc.write_page = vf610_nfc_write_page;
+	chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
+	chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
+	chip->ecc.read_oob = vf610_nfc_read_oob;
+	chip->ecc.write_oob = vf610_nfc_write_oob;
+
+	chip->ecc.size = PAGE_2K;
+
+	return 0;
+}
+
+static const struct nand_controller_ops vf610_nfc_controller_ops = {
+	.attach_chip = vf610_nfc_attach_chip,
+};
+
 static int vf610_nfc_probe(struct platform_device *pdev)
 {
 	struct vf610_nfc *nfc;
@@ -827,67 +890,9 @@ static int vf610_nfc_probe(struct platform_device *pdev)
 
 	vf610_nfc_preinit_controller(nfc);
 
-	/* first scan to find the device and get the page size */
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err)
-		goto err_disable_clk;
-
-	vf610_nfc_init_controller(nfc);
-
-	/* Bad block options. */
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	/* Single buffer only, max 256 OOB minus ECC status */
-	if (mtd->writesize + mtd->oobsize > PAGE_2K + OOB_MAX - 8) {
-		dev_err(nfc->dev, "Unsupported flash page size\n");
-		err = -ENXIO;
-		goto err_disable_clk;
-	}
-
-	if (chip->ecc.mode == NAND_ECC_HW) {
-		if (mtd->writesize != PAGE_2K && mtd->oobsize < 64) {
-			dev_err(nfc->dev, "Unsupported flash with hwecc\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		if (chip->ecc.size != mtd->writesize) {
-			dev_err(nfc->dev, "Step size needs to be page size\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		/* Only 64 byte ECC layouts known */
-		if (mtd->oobsize > 64)
-			mtd->oobsize = 64;
-
-		/* Use default large page ECC layout defined in NAND core */
-		mtd_set_ooblayout(mtd, &nand_ooblayout_lp_ops);
-		if (chip->ecc.strength == 32) {
-			nfc->ecc_mode = ECC_60_BYTE;
-			chip->ecc.bytes = 60;
-		} else if (chip->ecc.strength == 24) {
-			nfc->ecc_mode = ECC_45_BYTE;
-			chip->ecc.bytes = 45;
-		} else {
-			dev_err(nfc->dev, "Unsupported ECC strength\n");
-			err = -ENXIO;
-			goto err_disable_clk;
-		}
-
-		chip->ecc.read_page = vf610_nfc_read_page;
-		chip->ecc.write_page = vf610_nfc_write_page;
-		chip->ecc.read_page_raw = vf610_nfc_read_page_raw;
-		chip->ecc.write_page_raw = vf610_nfc_write_page_raw;
-		chip->ecc.read_oob = vf610_nfc_read_oob;
-		chip->ecc.write_oob = vf610_nfc_write_oob;
-
-		chip->ecc.size = PAGE_2K;
-	}
-
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	/* Scan the NAND chip */
+	chip->dummy_controller.ops = &vf610_nfc_controller_ops;
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto err_disable_clk;
 
-- 
cgit v1.2.3


From 92aa292d2e47be6210c0ba6074fc0ddfc02f7856 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Sun, 25 Feb 2018 23:09:14 +0100
Subject: mtd: rawnand: sm_common: fix the probe function error path

nand_cleanup() should be called upon error after a successful
nand_scan_tail().

Rework the error path to follow this rule .

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/sm_common.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/mtd/nand/raw/sm_common.c b/drivers/mtd/nand/raw/sm_common.c
index 7f5044a79f01..8bd16639ef85 100644
--- a/drivers/mtd/nand/raw/sm_common.c
+++ b/drivers/mtd/nand/raw/sm_common.c
@@ -192,7 +192,11 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia)
 	if (ret)
 		return ret;
 
-	return mtd_device_register(mtd, NULL, 0);
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret)
+		nand_cleanup(chip);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(sm_register_device);
 
-- 
cgit v1.2.3


From fe13ae02b07a1d14f47b0cbd63bc624b5f3cb890 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 27 Jul 2018 01:18:05 +0200
Subject: mtd: rawnand: sm_common: convert driver to nand_scan_with_ids()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan_with_ids() (alternative to nand_scan() for passing
a flash IDs table) instead of the nand_scan_ident() + nand_scan_tail()
pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/sm_common.c | 33 ++++++++++++++++++++-------------
 1 file changed, 20 insertions(+), 13 deletions(-)

diff --git a/drivers/mtd/nand/raw/sm_common.c b/drivers/mtd/nand/raw/sm_common.c
index 8bd16639ef85..73aafe8c3ef3 100644
--- a/drivers/mtd/nand/raw/sm_common.c
+++ b/drivers/mtd/nand/raw/sm_common.c
@@ -160,19 +160,9 @@ static struct nand_flash_dev nand_xd_flash_ids[] = {
 	{NULL}
 };
 
-int sm_register_device(struct mtd_info *mtd, int smartmedia)
+static int sm_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	chip->options |= NAND_SKIP_BBTSCAN;
-
-	/* Scan for card properties */
-	ret = nand_scan_ident(mtd, 1, smartmedia ?
-		nand_smartmedia_flash_ids : nand_xd_flash_ids);
-
-	if (ret)
-		return ret;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 
 	/* Bad block marker position */
 	chip->badblockpos = 0x05;
@@ -187,8 +177,25 @@ int sm_register_device(struct mtd_info *mtd, int smartmedia)
 	else
 		return -ENODEV;
 
-	ret = nand_scan_tail(mtd);
+	return 0;
+}
+
+static const struct nand_controller_ops sm_controller_ops = {
+	.attach_chip = sm_attach_chip,
+};
 
+int sm_register_device(struct mtd_info *mtd, int smartmedia)
+{
+	struct nand_chip *chip = mtd_to_nand(mtd);
+	struct nand_flash_dev *flash_ids;
+	int ret;
+
+	chip->options |= NAND_SKIP_BBTSCAN;
+
+	/* Scan for card properties */
+	chip->dummy_controller.ops = &sm_controller_ops;
+	flash_ids = smartmedia ? nand_smartmedia_flash_ids : nand_xd_flash_ids;
+	ret = nand_scan_with_ids(mtd, 1, flash_ids);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From 6a3cec64f18c118c776ee3185f026814e3fe45d4 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Fri, 20 Jul 2018 17:15:22 +0200
Subject: mtd: rawnand: qcom: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 71 +++++++++++++--------------------------
 1 file changed, 24 insertions(+), 47 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index aa6c3e026ef1..d1d470bb32e4 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -2475,10 +2475,10 @@ qcom_nandc_calc_ecc_bytes(int step_size, int strength)
 NAND_ECC_CAPS_SINGLE(qcom_nandc_ecc_caps, qcom_nandc_calc_ecc_bytes,
 		     NANDC_STEP_SIZE, 4, 8);
 
-static int qcom_nand_host_setup(struct qcom_nand_host *host)
+static int qcom_nand_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct qcom_nand_host *host = to_qcom_nand_host(chip);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	int cwperpage, bad_block_byte, ret;
@@ -2640,6 +2640,10 @@ static int qcom_nand_host_setup(struct qcom_nand_host *host)
 	return 0;
 }
 
+static const struct nand_controller_ops qcom_nandc_ops = {
+	.attach_chip = qcom_nand_attach_chip,
+};
+
 static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 {
 	int ret;
@@ -2729,6 +2733,7 @@ static int qcom_nandc_alloc(struct qcom_nand_controller *nandc)
 	INIT_LIST_HEAD(&nandc->host_list);
 
 	nand_controller_init(&nandc->controller);
+	nandc->controller.ops = &qcom_nandc_ops;
 
 	return 0;
 }
@@ -2781,9 +2786,9 @@ static int qcom_nandc_setup(struct qcom_nand_controller *nandc)
 	return 0;
 }
 
-static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
-			       struct qcom_nand_host *host,
-			       struct device_node *dn)
+static int qcom_nand_host_init_and_register(struct qcom_nand_controller *nandc,
+					    struct qcom_nand_host *host,
+					    struct device_node *dn)
 {
 	struct nand_chip *chip = &host->chip;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -2830,30 +2835,13 @@ static int qcom_nand_host_init(struct qcom_nand_controller *nandc,
 	/* set up initial status value */
 	host->status = NAND_STATUS_READY | NAND_STATUS_WP;
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	ret = qcom_nand_host_setup(host);
-
-	return ret;
-}
-
-static int qcom_nand_mtd_register(struct qcom_nand_controller *nandc,
-				  struct qcom_nand_host *host,
-				  struct device_node *dn)
-{
-	struct nand_chip *chip = &host->chip;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	int ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
 	ret = mtd_device_register(mtd, NULL, 0);
 	if (ret)
-		nand_cleanup(mtd_to_nand(mtd));
+		nand_cleanup(chip);
 
 	return ret;
 }
@@ -2862,28 +2850,9 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 {
 	struct device *dev = nandc->dev;
 	struct device_node *dn = dev->of_node, *child;
-	struct qcom_nand_host *host, *tmp;
+	struct qcom_nand_host *host;
 	int ret;
 
-	for_each_available_child_of_node(dn, child) {
-		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
-		if (!host) {
-			of_node_put(child);
-			return -ENOMEM;
-		}
-
-		ret = qcom_nand_host_init(nandc, host, child);
-		if (ret) {
-			devm_kfree(dev, host);
-			continue;
-		}
-
-		list_add_tail(&host->node, &nandc->host_list);
-	}
-
-	if (list_empty(&nandc->host_list))
-		return -ENODEV;
-
 	if (nandc->props->is_bam) {
 		free_bam_transaction(nandc);
 		nandc->bam_txn = alloc_bam_transaction(nandc);
@@ -2894,12 +2863,20 @@ static int qcom_probe_nand_devices(struct qcom_nand_controller *nandc)
 		}
 	}
 
-	list_for_each_entry_safe(host, tmp, &nandc->host_list, node) {
-		ret = qcom_nand_mtd_register(nandc, host, child);
+	for_each_available_child_of_node(dn, child) {
+		host = devm_kzalloc(dev, sizeof(*host), GFP_KERNEL);
+		if (!host) {
+			of_node_put(child);
+			return -ENOMEM;
+		}
+
+		ret = qcom_nand_host_init_and_register(nandc, host, child);
 		if (ret) {
-			list_del(&host->node);
 			devm_kfree(dev, host);
+			continue;
 		}
+
+		list_add_tail(&host->node, &nandc->host_list);
 	}
 
 	if (list_empty(&nandc->host_list))
-- 
cgit v1.2.3


From 0bbf47eab4697557718fccc1ec9835c44c47fe7f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 25 Jul 2018 11:17:20 +0200
Subject: ia64: use asm-generic/io.h

asm-generic/io.h provides a generic implementation of all I/O accessors,
which the architectures can override.

Since ia64 does not provide readsl/writesl etc, any driver using those
fails to build, and including asm-generic/io.h will provide the
missing interfaces, as well as any other future interfaces that get
added there. We need to #define a couple of symbols to themselves
in the ia64 to ensure that we use the ia64 specific version of those
rather than the generic one.

There should be no other effect than adding {read,write}s{b,w,l}()
as well as {in,out}s{b,w,l}_p(), which were also not provided
by ia64 but are provided by the generic header for historic reasons.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Tested-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 arch/ia64/include/asm/io.h | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/arch/ia64/include/asm/io.h b/arch/ia64/include/asm/io.h
index fb0651961e2c..6f952171abf9 100644
--- a/arch/ia64/include/asm/io.h
+++ b/arch/ia64/include/asm/io.h
@@ -83,12 +83,14 @@ virt_to_phys (volatile void *address)
 {
 	return (unsigned long) address - PAGE_OFFSET;
 }
+#define virt_to_phys virt_to_phys
 
 static inline void*
 phys_to_virt (unsigned long address)
 {
 	return (void *) (address + PAGE_OFFSET);
 }
+#define phys_to_virt phys_to_virt
 
 #define ARCH_HAS_VALID_PHYS_ADDR_RANGE
 extern u64 kern_mem_attribute (unsigned long phys_addr, unsigned long size);
@@ -433,9 +435,11 @@ static inline void __iomem * ioremap_cache (unsigned long phys_addr, unsigned lo
 {
 	return ioremap(phys_addr, size);
 }
+#define ioremap ioremap
+#define ioremap_nocache ioremap_nocache
 #define ioremap_cache ioremap_cache
 #define ioremap_uc ioremap_nocache
-
+#define iounmap iounmap
 
 /*
  * String version of IO memory access ops:
@@ -444,6 +448,13 @@ extern void memcpy_fromio(void *dst, const volatile void __iomem *src, long n);
 extern void memcpy_toio(volatile void __iomem *dst, const void *src, long n);
 extern void memset_io(volatile void __iomem *s, int c, long n);
 
+#define memcpy_fromio memcpy_fromio
+#define memcpy_toio memcpy_toio
+#define memset_io memset_io
+#define xlate_dev_kmem_ptr xlate_dev_kmem_ptr
+#define xlate_dev_mem_ptr xlate_dev_mem_ptr
+#include <asm-generic/io.h>
+
 # endif /* __KERNEL__ */
 
 #endif /* _ASM_IA64_IO_H */
-- 
cgit v1.2.3


From 15280e8107e17a5ee40509e3d1384ad28d6fdcf4 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 25 Jul 2018 11:18:34 +0200
Subject: sparc64: add reads{b,w,l}/writes{b,w,l}

Some drivers need these for compile-testing. On most architectures
they come from asm-generic/io.h, but not on sparc64, which has its
own definitions.

Since we already have ioread*_rep()/iowrite*_rep() that have the
same behavior on sparc64 (i.e. all PCI I/O space is memory mapped),
we can rename the existing helpers and add macros to define them
to the same implementation.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: David S. Miller <davem@davemloft.net>
Tested-by: Boris Brezillon <boris.brezillon@bootlin>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 arch/sparc/include/asm/io_64.h | 19 +++++++++++++------
 1 file changed, 13 insertions(+), 6 deletions(-)

diff --git a/arch/sparc/include/asm/io_64.h b/arch/sparc/include/asm/io_64.h
index 9a1e9cbc7e6d..b162c23ae8c2 100644
--- a/arch/sparc/include/asm/io_64.h
+++ b/arch/sparc/include/asm/io_64.h
@@ -243,35 +243,42 @@ void insb(unsigned long, void *, unsigned long);
 void insw(unsigned long, void *, unsigned long);
 void insl(unsigned long, void *, unsigned long);
 
-static inline void ioread8_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsb(void __iomem *port, void *buf, unsigned long count)
 {
 	insb((unsigned long __force)port, buf, count);
 }
-static inline void ioread16_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsw(void __iomem *port, void *buf, unsigned long count)
 {
 	insw((unsigned long __force)port, buf, count);
 }
 
-static inline void ioread32_rep(void __iomem *port, void *buf, unsigned long count)
+static inline void readsl(void __iomem *port, void *buf, unsigned long count)
 {
 	insl((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite8_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesb(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsb((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite16_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesw(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsw((unsigned long __force)port, buf, count);
 }
 
-static inline void iowrite32_rep(void __iomem *port, const void *buf, unsigned long count)
+static inline void writesl(void __iomem *port, const void *buf, unsigned long count)
 {
 	outsl((unsigned long __force)port, buf, count);
 }
 
+#define ioread8_rep(p,d,l)	readsb(p,d,l)
+#define ioread16_rep(p,d,l)	readsw(p,d,l)
+#define ioread32_rep(p,d,l)	readsl(p,d,l)
+#define iowrite8_rep(p,d,l)	writesb(p,d,l)
+#define iowrite16_rep(p,d,l)	writesw(p,d,l)
+#define iowrite32_rep(p,d,l)	writesl(p,d,l)
+
 /* Valid I/O Space regions are anywhere, because each PCI bus supported
  * can live in an arbitrary area of the physical address range.
  */
-- 
cgit v1.2.3


From 16909c81c6298c2db5587340106523e0a6c2bfe2 Mon Sep 17 00:00:00 2001
From: Anders Roxell <anders.roxell@linaro.org>
Date: Wed, 25 Jul 2018 11:19:28 +0200
Subject: drivers/memory/Kconfig: Add CONFIG_OF dependency
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

JZ4780_NEMC doesn't depend on OF, and if OF isn't enabled we get this
error:
drivers/memory/jz4780-nemc.c: In function ‘jz4780_nemc_num_banks’:
drivers/memory/jz4780-nemc.c:72:10: error: implicit declaration of
 function ‘of_read_number’; did you mean ‘down_read_nested’?
 [-Werror=implicit-function-declaration]
   bank = of_read_number(prop, 1);
          ^~~~~~~~~~~~~~
          down_read_nested

Make JZ4780_NEMC depend on OF.

Fixes: ab99e11062c1 ("memory: jz4780-nemc: Allow selection of this driver when COMPILE_TEST=y")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Anders Roxell <anders.roxell@linaro.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/memory/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
index a642552dfdc9..63389f075f1d 100644
--- a/drivers/memory/Kconfig
+++ b/drivers/memory/Kconfig
@@ -123,7 +123,7 @@ config JZ4780_NEMC
 	bool "Ingenic JZ4780 SoC NEMC driver"
 	default y
 	depends on MACH_JZ4780 || COMPILE_TEST
-	depends on HAS_IOMEM
+	depends on HAS_IOMEM && OF
 	help
 	  This driver is for the NAND/External Memory Controller (NEMC) in
 	  the Ingenic JZ4780. This controller is used to handle external
-- 
cgit v1.2.3


From 4918b905736fddc67f14618d5c82f7edc5944db8 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:36 +0200
Subject: mtd: rawnand: brcmnand: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/brcmnand/brcmnand.c | 63 ++++++++++++++++++--------------
 1 file changed, 36 insertions(+), 27 deletions(-)

diff --git a/drivers/mtd/nand/raw/brcmnand/brcmnand.c b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
index 2e5efa0f9ea2..4b90d5b380c2 100644
--- a/drivers/mtd/nand/raw/brcmnand/brcmnand.c
+++ b/drivers/mtd/nand/raw/brcmnand/brcmnand.c
@@ -2208,6 +2208,40 @@ static int brcmnand_setup_dev(struct brcmnand_host *host)
 	return 0;
 }
 
+static int brcmnand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct brcmnand_host *host = nand_get_controller_data(chip);
+	int ret;
+
+	chip->options |= NAND_NO_SUBPAGE_WRITE;
+	/*
+	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
+	 * to/from, and have nand_base pass us a bounce buffer instead, as
+	 * needed.
+	 */
+	chip->options |= NAND_USE_BOUNCE_BUFFER;
+
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
+
+	if (brcmnand_setup_dev(host))
+		return -ENXIO;
+
+	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
+
+	/* only use our internal HW threshold */
+	mtd->bitflip_threshold = 1;
+
+	ret = brcmstb_choose_ecc_layout(host);
+
+	return ret;
+}
+
+static const struct nand_controller_ops brcmnand_controller_ops = {
+	.attach_chip = brcmnand_attach_chip,
+};
+
 static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 {
 	struct brcmnand_controller *ctrl = host->ctrl;
@@ -2267,33 +2301,7 @@ static int brcmnand_init_cs(struct brcmnand_host *host, struct device_node *dn)
 	nand_writereg(ctrl, cfg_offs,
 		      nand_readreg(ctrl, cfg_offs) & ~CFG_BUS_WIDTH);
 
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
-
-	chip->options |= NAND_NO_SUBPAGE_WRITE;
-	/*
-	 * Avoid (for instance) kmap()'d buffers from JFFS2, which we can't DMA
-	 * to/from, and have nand_base pass us a bounce buffer instead, as
-	 * needed.
-	 */
-	chip->options |= NAND_USE_BOUNCE_BUFFER;
-
-	if (chip->bbt_options & NAND_BBT_USE_FLASH)
-		chip->bbt_options |= NAND_BBT_NO_OOB;
-
-	if (brcmnand_setup_dev(host))
-		return -ENXIO;
-
-	chip->ecc.size = host->hwcfg.sector_size_1k ? 1024 : 512;
-	/* only use our internal HW threshold */
-	mtd->bitflip_threshold = 1;
-
-	ret = brcmstb_choose_ecc_layout(host);
-	if (ret)
-		return ret;
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -2434,6 +2442,7 @@ int brcmnand_probe(struct platform_device *pdev, struct brcmnand_soc *soc)
 	init_completion(&ctrl->done);
 	init_completion(&ctrl->dma_done);
 	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &brcmnand_controller_ops;
 	INIT_LIST_HEAD(&ctrl->host_list);
 
 	/* NAND register range */
-- 
cgit v1.2.3


From 73a27db8658125faadb857f1919559de8a5f71b0 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:37 +0200
Subject: mtd: rawnand: cafe: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/cafe_nand.c | 135 ++++++++++++++++++++++-----------------
 1 file changed, 78 insertions(+), 57 deletions(-)

diff --git a/drivers/mtd/nand/raw/cafe_nand.c b/drivers/mtd/nand/raw/cafe_nand.c
index ac0be933a490..1dbe43adcfe7 100644
--- a/drivers/mtd/nand/raw/cafe_nand.c
+++ b/drivers/mtd/nand/raw/cafe_nand.c
@@ -67,6 +67,7 @@ struct cafe_priv {
 	int nr_data;
 	int data_pos;
 	int page_addr;
+	bool usedma;
 	dma_addr_t dmaaddr;
 	unsigned char *dmabuf;
 };
@@ -121,7 +122,7 @@ static void cafe_write_buf(struct mtd_info *mtd, const uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(cafe->dmabuf + cafe->datalen, buf, len);
 	else
 		memcpy_toio(cafe->mmio + CAFE_NAND_WRITE_DATA + cafe->datalen, buf, len);
@@ -137,7 +138,7 @@ static void cafe_read_buf(struct mtd_info *mtd, uint8_t *buf, int len)
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct cafe_priv *cafe = nand_get_controller_data(chip);
 
-	if (usedma)
+	if (cafe->usedma)
 		memcpy(buf, cafe->dmabuf + cafe->datalen, len);
 	else
 		memcpy_fromio(buf, cafe->mmio + CAFE_NAND_READ_DATA + cafe->datalen, len);
@@ -253,7 +254,7 @@ static void cafe_nand_cmdfunc(struct mtd_info *mtd, unsigned command,
 	/* NB: The datasheet lies -- we really should be subtracting 1 here */
 	cafe_writel(cafe, cafe->datalen, NAND_DATA_LEN);
 	cafe_writel(cafe, 0x90000000, NAND_IRQ);
-	if (usedma && (ctl1 & (3<<25))) {
+	if (cafe->usedma && (ctl1 & (3<<25))) {
 		uint32_t dmactl = 0xc0000000 + cafe->datalen;
 		/* If WR or RD bits set, set up DMA */
 		if (ctl1 & (1<<26)) {
@@ -593,6 +594,76 @@ static int cafe_mul(int x)
 	return gf4096_mul(x, 0xe01);
 }
 
+static int cafe_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+	int err = 0;
+
+	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
+					  &cafe->dmaaddr, GFP_KERNEL);
+	if (!cafe->dmabuf)
+		return -ENOMEM;
+
+	/* Set up DMA address */
+	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
+	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
+
+	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
+		     cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
+
+	/* Restore the DMA flag */
+	cafe->usedma = usedma;
+
+	cafe->ctl2 = BIT(27); /* Reed-Solomon ECC */
+	if (mtd->writesize == 2048)
+		cafe->ctl2 |= BIT(29); /* 2KiB page size */
+
+	/* Set up ECC according to the type of chip we found */
+	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
+	if (mtd->writesize == 2048) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
+	} else if (mtd->writesize == 512) {
+		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
+		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
+	} else {
+		dev_warn(&cafe->pdev->dev,
+			 "Unexpected NAND flash writesize %d. Aborting\n",
+			 mtd->writesize);
+		err = -ENOTSUPP;
+		goto out_free_dma;
+	}
+
+	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
+	cafe->nand.ecc.size = mtd->writesize;
+	cafe->nand.ecc.bytes = 14;
+	cafe->nand.ecc.strength = 4;
+	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
+	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
+	cafe->nand.ecc.read_page = cafe_nand_read_page;
+	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
+
+	return 0;
+
+ out_free_dma:
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+
+	return err;
+}
+
+static void cafe_nand_detach_chip(struct nand_chip *chip)
+{
+	struct cafe_priv *cafe = nand_get_controller_data(chip);
+
+	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
+}
+
+static const struct nand_controller_ops cafe_nand_controller_ops = {
+	.attach_chip = cafe_nand_attach_chip,
+	.detach_chip = cafe_nand_detach_chip,
+};
+
 static int cafe_nand_probe(struct pci_dev *pdev,
 				     const struct pci_device_id *ent)
 {
@@ -600,7 +671,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 	struct cafe_priv *cafe;
 	uint32_t ctrl;
 	int err = 0;
-	int old_dma;
 
 	/* Very old versions shared the same PCI ident for all three
 	   functions on the chip. Verify the class too... */
@@ -708,62 +778,15 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 		cafe_readl(cafe, GLOBAL_CTRL),
 		cafe_readl(cafe, GLOBAL_IRQ_MASK));
 
-	/* Do not use the DMA for the nand_scan_ident() */
-	old_dma = usedma;
-	usedma = 0;
+	/* Do not use the DMA during the NAND identification */
+	cafe->usedma = 0;
 
 	/* Scan to find existence of the device */
-	err = nand_scan_ident(mtd, 2, NULL);
+	cafe->nand.dummy_controller.ops = &cafe_nand_controller_ops;
+	err = nand_scan(mtd, 2);
 	if (err)
 		goto out_irq;
 
-	cafe->dmabuf = dma_alloc_coherent(&cafe->pdev->dev, 2112,
-					  &cafe->dmaaddr, GFP_KERNEL);
-	if (!cafe->dmabuf) {
-		err = -ENOMEM;
-		goto out_irq;
-	}
-
-	/* Set up DMA address */
-	cafe_writel(cafe, lower_32_bits(cafe->dmaaddr), NAND_DMA_ADDR0);
-	cafe_writel(cafe, upper_32_bits(cafe->dmaaddr), NAND_DMA_ADDR1);
-
-	cafe_dev_dbg(&cafe->pdev->dev, "Set DMA address to %x (virt %p)\n",
-		cafe_readl(cafe, NAND_DMA_ADDR0), cafe->dmabuf);
-
-	/* Restore the DMA flag */
-	usedma = old_dma;
-
-	cafe->ctl2 = 1<<27; /* Reed-Solomon ECC */
-	if (mtd->writesize == 2048)
-		cafe->ctl2 |= 1<<29; /* 2KiB page size */
-
-	/* Set up ECC according to the type of chip we found */
-	mtd_set_ooblayout(mtd, &cafe_ooblayout_ops);
-	if (mtd->writesize == 2048) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_2048;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_2048;
-	} else if (mtd->writesize == 512) {
-		cafe->nand.bbt_td = &cafe_bbt_main_descr_512;
-		cafe->nand.bbt_md = &cafe_bbt_mirror_descr_512;
-	} else {
-		pr_warn("Unexpected NAND flash writesize %d. Aborting\n",
-			mtd->writesize);
-		goto out_free_dma;
-	}
-	cafe->nand.ecc.mode = NAND_ECC_HW_SYNDROME;
-	cafe->nand.ecc.size = mtd->writesize;
-	cafe->nand.ecc.bytes = 14;
-	cafe->nand.ecc.strength = 4;
-	cafe->nand.ecc.write_page = cafe_nand_write_page_lowlevel;
-	cafe->nand.ecc.write_oob = cafe_nand_write_oob;
-	cafe->nand.ecc.read_page = cafe_nand_read_page;
-	cafe->nand.ecc.read_oob = cafe_nand_read_oob;
-
-	err = nand_scan_tail(mtd);
-	if (err)
-		goto out_free_dma;
-
 	pci_set_drvdata(pdev, mtd);
 
 	mtd->name = "cafe_nand";
@@ -775,8 +798,6 @@ static int cafe_nand_probe(struct pci_dev *pdev,
 
  out_cleanup_nand:
 	nand_cleanup(&cafe->nand);
- out_free_dma:
-	dma_free_coherent(&cafe->pdev->dev, 2112, cafe->dmabuf, cafe->dmaaddr);
  out_irq:
 	/* Disable NAND IRQ in global IRQ mask register */
 	cafe_writel(cafe, ~1 & cafe_readl(cafe, GLOBAL_IRQ_MASK), GLOBAL_IRQ_MASK);
-- 
cgit v1.2.3


From c49f3bee8cb5435ad5832930829f913a391a8a58 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:38 +0200
Subject: mtd: rawnand: lpc32xx_mlc: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/lpc32xx_mlc.c | 61 +++++++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 28 deletions(-)

diff --git a/drivers/mtd/nand/raw/lpc32xx_mlc.c b/drivers/mtd/nand/raw/lpc32xx_mlc.c
index 052d123a8304..e82abada130a 100644
--- a/drivers/mtd/nand/raw/lpc32xx_mlc.c
+++ b/drivers/mtd/nand/raw/lpc32xx_mlc.c
@@ -184,6 +184,7 @@ static struct nand_bbt_descr lpc32xx_nand_bbt_mirror = {
 };
 
 struct lpc32xx_nand_host {
+	struct platform_device	*pdev;
 	struct nand_chip	nand_chip;
 	struct lpc32xx_mlc_platform_data *pdata;
 	struct clk		*clk;
@@ -653,6 +654,32 @@ static struct lpc32xx_nand_cfg_mlc *lpc32xx_parse_dt(struct device *dev)
 	return ncfg;
 }
 
+static int lpc32xx_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct lpc32xx_nand_host *host = nand_get_controller_data(chip);
+	struct device *dev = &host->pdev->dev;
+
+	host->dma_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dma_buf)
+		return -ENOMEM;
+
+	host->dummy_buf = devm_kzalloc(dev, mtd->writesize, GFP_KERNEL);
+	if (!host->dummy_buf)
+		return -ENOMEM;
+
+	chip->ecc.mode = NAND_ECC_HW;
+	chip->ecc.size = 512;
+	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
+	host->mlcsubpages = mtd->writesize / 512;
+
+	return 0;
+}
+
+static const struct nand_controller_ops lpc32xx_nand_controller_ops = {
+	.attach_chip = lpc32xx_nand_attach_chip,
+};
+
 /*
  * Probe for NAND controller
  */
@@ -669,6 +696,8 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	if (!host)
 		return -ENOMEM;
 
+	host->pdev = pdev;
+
 	rc = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	host->io_base = devm_ioremap_resource(&pdev->dev, rc);
 	if (IS_ERR(host->io_base))
@@ -748,31 +777,6 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 		}
 	}
 
-	/*
-	 * Scan to find existance of the device and
-	 * Get the type of NAND device SMALL block or LARGE block
-	 */
-	res = nand_scan_ident(mtd, 1, NULL);
-	if (res)
-		goto release_dma_chan;
-
-	host->dma_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dma_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	host->dummy_buf = devm_kzalloc(&pdev->dev, mtd->writesize, GFP_KERNEL);
-	if (!host->dummy_buf) {
-		res = -ENOMEM;
-		goto release_dma_chan;
-	}
-
-	nand_chip->ecc.mode = NAND_ECC_HW;
-	nand_chip->ecc.size = 512;
-	mtd_set_ooblayout(mtd, &lpc32xx_ooblayout_ops);
-	host->mlcsubpages = mtd->writesize / 512;
-
 	/* initially clear interrupt status */
 	readb(MLC_IRQ_SR(host->io_base));
 
@@ -794,10 +798,11 @@ static int lpc32xx_nand_probe(struct platform_device *pdev)
 	}
 
 	/*
-	 * Fills out all the uninitialized function pointers with the defaults
-	 * And scans for a bad block table if appropriate.
+	 * Scan to find existence of the device and get the type of NAND device:
+	 * SMALL block or LARGE block.
 	 */
-	res = nand_scan_tail(mtd);
+	nand_chip->dummy_controller.ops = &lpc32xx_nand_controller_ops;
+	res = nand_scan(mtd, 1);
 	if (res)
 		goto free_irq;
 
-- 
cgit v1.2.3


From e1e6255c311bae4f89bf627fe54ced88bb5caa7e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:39 +0200
Subject: mtd: rawnand: omap2: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/omap2.c | 463 +++++++++++++++++++++----------------------
 1 file changed, 230 insertions(+), 233 deletions(-)

diff --git a/drivers/mtd/nand/raw/omap2.c b/drivers/mtd/nand/raw/omap2.c
index e943b2e5a5e2..4546ac0bed4a 100644
--- a/drivers/mtd/nand/raw/omap2.c
+++ b/drivers/mtd/nand/raw/omap2.c
@@ -144,12 +144,6 @@ static u_char bch8_vector[] = {0xf3, 0xdb, 0x14, 0x16, 0x8b, 0xd2, 0xbe, 0xcc,
 	0xac, 0x6b, 0xff, 0x99, 0x7b};
 static u_char bch4_vector[] = {0x00, 0x6b, 0x31, 0xdd, 0x41, 0xbc, 0x10};
 
-/* Shared among all NAND instances to synchronize access to the ECC Engine */
-static struct nand_controller omap_gpmc_controller = {
-	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
-	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
-};
-
 struct omap_nand_info {
 	struct nand_chip		nand;
 	struct platform_device		*pdev;
@@ -1915,106 +1909,26 @@ static const struct mtd_ooblayout_ops omap_sw_ooblayout_ops = {
 	.free = omap_sw_ooblayout_free,
 };
 
-static int omap_nand_probe(struct platform_device *pdev)
+static int omap_nand_attach_chip(struct nand_chip *chip)
 {
-	struct omap_nand_info		*info;
-	struct mtd_info			*mtd;
-	struct nand_chip		*nand_chip;
-	int				err;
-	dma_cap_mask_t			mask;
-	struct resource			*res;
-	struct device			*dev = &pdev->dev;
-	int				min_oobbytes = BADBLOCK_MARKER_LENGTH;
-	int				oobbytes_per_step;
-
-	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
-				GFP_KERNEL);
-	if (!info)
-		return -ENOMEM;
-
-	info->pdev = pdev;
-
-	err = omap_get_dt_info(dev, info);
-	if (err)
-		return err;
-
-	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
-	if (!info->ops) {
-		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
-		return -ENODEV;
-	}
-
-	nand_chip		= &info->nand;
-	mtd			= nand_to_mtd(nand_chip);
-	mtd->dev.parent		= &pdev->dev;
-	nand_chip->ecc.priv	= NULL;
-	nand_set_flash_node(nand_chip, dev->of_node);
-
-	if (!mtd->name) {
-		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
-					   "omap2-nand.%d", info->gpmc_cs);
-		if (!mtd->name) {
-			dev_err(&pdev->dev, "Failed to set MTD name\n");
-			return -ENOMEM;
-		}
-	}
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(nand_chip->IO_ADDR_R))
-		return PTR_ERR(nand_chip->IO_ADDR_R);
-
-	info->phys_base = res->start;
-
-	nand_chip->controller = &omap_gpmc_controller;
-
-	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
-	nand_chip->cmd_ctrl  = omap_hwcontrol;
-
-	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
-						    GPIOD_IN);
-	if (IS_ERR(info->ready_gpiod)) {
-		dev_err(dev, "failed to get ready gpio\n");
-		return PTR_ERR(info->ready_gpiod);
-	}
-
-	/*
-	 * If RDY/BSY line is connected to OMAP then use the omap ready
-	 * function and the generic nand_wait function which reads the status
-	 * register after monitoring the RDY/BSY line. Otherwise use a standard
-	 * chip delay which is slightly more than tR (AC Timing) of the NAND
-	 * device and read status register until you get a failure or success
-	 */
-	if (info->ready_gpiod) {
-		nand_chip->dev_ready = omap_dev_ready;
-		nand_chip->chip_delay = 0;
-	} else {
-		nand_chip->waitfunc = omap_wait;
-		nand_chip->chip_delay = 50;
-	}
-
-	if (info->flash_bbt)
-		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
-
-	/* scan NAND device connected to chip controller */
-	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
-	err = nand_scan_ident(mtd, 1, NULL);
-	if (err) {
-		dev_err(&info->pdev->dev,
-			"scan failed, may be bus-width mismatch\n");
-		goto return_error;
-	}
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct omap_nand_info *info = mtd_to_omap(mtd);
+	struct device *dev = &info->pdev->dev;
+	int min_oobbytes = BADBLOCK_MARKER_LENGTH;
+	int oobbytes_per_step;
+	dma_cap_mask_t mask;
+	int err;
 
-	if (nand_chip->bbt_options & NAND_BBT_USE_FLASH)
-		nand_chip->bbt_options |= NAND_BBT_NO_OOB;
+	if (chip->bbt_options & NAND_BBT_USE_FLASH)
+		chip->bbt_options |= NAND_BBT_NO_OOB;
 	else
-		nand_chip->options |= NAND_SKIP_BBTSCAN;
+		chip->options |= NAND_SKIP_BBTSCAN;
 
-	/* re-populate low-level callbacks based on xfer modes */
+	/* Re-populate low-level callbacks based on xfer modes */
 	switch (info->xfer_type) {
 	case NAND_OMAP_PREFETCH_POLLED:
-		nand_chip->read_buf   = omap_read_buf_pref;
-		nand_chip->write_buf  = omap_write_buf_pref;
+		chip->read_buf = omap_read_buf_pref;
+		chip->write_buf = omap_write_buf_pref;
 		break;
 
 	case NAND_OMAP_POLLED:
@@ -2024,12 +1938,11 @@ static int omap_nand_probe(struct platform_device *pdev)
 	case NAND_OMAP_PREFETCH_DMA:
 		dma_cap_zero(mask);
 		dma_cap_set(DMA_SLAVE, mask);
-		info->dma = dma_request_chan(pdev->dev.parent, "rxtx");
+		info->dma = dma_request_chan(dev, "rxtx");
 
 		if (IS_ERR(info->dma)) {
-			dev_err(&pdev->dev, "DMA engine request failed\n");
-			err = PTR_ERR(info->dma);
-			goto return_error;
+			dev_err(dev, "DMA engine request failed\n");
+			return PTR_ERR(info->dma);
 		} else {
 			struct dma_slave_config cfg;
 
@@ -2042,222 +1955,306 @@ static int omap_nand_probe(struct platform_device *pdev)
 			cfg.dst_maxburst = 16;
 			err = dmaengine_slave_config(info->dma, &cfg);
 			if (err) {
-				dev_err(&pdev->dev, "DMA engine slave config failed: %d\n",
+				dev_err(dev,
+					"DMA engine slave config failed: %d\n",
 					err);
-				goto return_error;
+				return err;
 			}
-			nand_chip->read_buf   = omap_read_buf_dma_pref;
-			nand_chip->write_buf  = omap_write_buf_dma_pref;
+			chip->read_buf = omap_read_buf_dma_pref;
+			chip->write_buf = omap_write_buf_dma_pref;
 		}
 		break;
 
 	case NAND_OMAP_PREFETCH_IRQ:
-		info->gpmc_irq_fifo = platform_get_irq(pdev, 0);
+		info->gpmc_irq_fifo = platform_get_irq(info->pdev, 0);
 		if (info->gpmc_irq_fifo <= 0) {
-			dev_err(&pdev->dev, "error getting fifo irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting fifo IRQ\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_fifo,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-fifo", info);
+		err = devm_request_irq(dev, info->gpmc_irq_fifo,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-fifo", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_fifo, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_fifo, err);
 			info->gpmc_irq_fifo = 0;
-			goto return_error;
+			return err;
 		}
 
-		info->gpmc_irq_count = platform_get_irq(pdev, 1);
+		info->gpmc_irq_count = platform_get_irq(info->pdev, 1);
 		if (info->gpmc_irq_count <= 0) {
-			dev_err(&pdev->dev, "error getting count irq\n");
-			err = -ENODEV;
-			goto return_error;
+			dev_err(dev, "Error getting IRQ count\n");
+			return -ENODEV;
 		}
-		err = devm_request_irq(&pdev->dev, info->gpmc_irq_count,
-					omap_nand_irq, IRQF_SHARED,
-					"gpmc-nand-count", info);
+		err = devm_request_irq(dev, info->gpmc_irq_count,
+				       omap_nand_irq, IRQF_SHARED,
+				       "gpmc-nand-count", info);
 		if (err) {
-			dev_err(&pdev->dev, "requesting irq(%d) error:%d",
-						info->gpmc_irq_count, err);
+			dev_err(dev, "Requesting IRQ %d, error %d\n",
+				info->gpmc_irq_count, err);
 			info->gpmc_irq_count = 0;
-			goto return_error;
+			return err;
 		}
 
-		nand_chip->read_buf  = omap_read_buf_irq_pref;
-		nand_chip->write_buf = omap_write_buf_irq_pref;
+		chip->read_buf = omap_read_buf_irq_pref;
+		chip->write_buf = omap_write_buf_irq_pref;
 
 		break;
 
 	default:
-		dev_err(&pdev->dev,
-			"xfer_type(%d) not supported!\n", info->xfer_type);
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "xfer_type %d not supported!\n", info->xfer_type);
+		return -EINVAL;
 	}
 
-	if (!omap2_nand_ecc_check(info)) {
-		err = -EINVAL;
-		goto return_error;
-	}
+	if (!omap2_nand_ecc_check(info))
+		return -EINVAL;
 
 	/*
 	 * Bail out earlier to let NAND_ECC_SOFT code create its own
 	 * ooblayout instead of using ours.
 	 */
 	if (info->ecc_opt == OMAP_ECC_HAM1_CODE_SW) {
-		nand_chip->ecc.mode = NAND_ECC_SOFT;
-		nand_chip->ecc.algo = NAND_ECC_HAMMING;
-		goto scan_tail;
+		chip->ecc.mode = NAND_ECC_SOFT;
+		chip->ecc.algo = NAND_ECC_HAMMING;
+		return 0;
 	}
 
-	/* populate MTD interface based on ECC scheme */
+	/* Populate MTD interface based on ECC scheme */
 	switch (info->ecc_opt) {
 	case OMAP_ECC_HAM1_CODE_HW:
-		pr_info("nand: using OMAP_ECC_HAM1_CODE_HW\n");
-		nand_chip->ecc.mode             = NAND_ECC_HW;
-		nand_chip->ecc.bytes            = 3;
-		nand_chip->ecc.size             = 512;
-		nand_chip->ecc.strength         = 1;
-		nand_chip->ecc.calculate        = omap_calculate_ecc;
-		nand_chip->ecc.hwctl            = omap_enable_hwecc;
-		nand_chip->ecc.correct          = omap_correct_data;
+		dev_info(dev, "nand: using OMAP_ECC_HAM1_CODE_HW\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.bytes		= 3;
+		chip->ecc.size		= 512;
+		chip->ecc.strength	= 1;
+		chip->ecc.calculate	= omap_calculate_ecc;
+		chip->ecc.hwctl		= omap_enable_hwecc;
+		chip->ecc.correct	= omap_correct_data;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
-		if (!(nand_chip->options & NAND_BUSWIDTH_16))
-			min_oobbytes		= 1;
+		if (!(chip->options & NAND_BUSWIDTH_16))
+			min_oobbytes	= 1;
 
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 7;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 7;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "Unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH4_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH4_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 7 + 1;
-		nand_chip->ecc.strength		= 4;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 7 + 1;
+		chip->ecc.strength	= 4;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH4_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW_DETECTION_SW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW_DETECTION_SW\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 13;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= nand_bch_correct_data;
-		nand_chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 13;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= nand_bch_correct_data;
+		chip->ecc.calculate	= omap_calculate_ecc_bch_sw;
 		mtd_set_ooblayout(mtd, &omap_sw_ooblayout_ops);
 		/* Reserve one byte for the OMAP marker */
-		oobbytes_per_step		= nand_chip->ecc.bytes + 1;
-		/* software bch library is used for locating errors */
-		nand_chip->ecc.priv		= nand_bch_init(mtd);
-		if (!nand_chip->ecc.priv) {
-			dev_err(&info->pdev->dev, "unable to use BCH library\n");
-			err = -EINVAL;
-			goto return_error;
+		oobbytes_per_step	= chip->ecc.bytes + 1;
+		/* Software BCH library is used for locating errors */
+		chip->ecc.priv		= nand_bch_init(mtd);
+		if (!chip->ecc.priv) {
+			dev_err(dev, "unable to use BCH library\n");
+			return -EINVAL;
 		}
 		break;
 
 	case OMAP_ECC_BCH8_CODE_HW:
 		pr_info("nand: using OMAP_ECC_BCH8_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
 		/* 14th bit is kept reserved for ROM-code compatibility */
-		nand_chip->ecc.bytes		= 13 + 1;
-		nand_chip->ecc.strength		= 8;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		chip->ecc.bytes		= 13 + 1;
+		chip->ecc.strength	= 8;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH8_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 
 	case OMAP_ECC_BCH16_CODE_HW:
-		pr_info("using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
-		nand_chip->ecc.mode		= NAND_ECC_HW;
-		nand_chip->ecc.size		= 512;
-		nand_chip->ecc.bytes		= 26;
-		nand_chip->ecc.strength		= 16;
-		nand_chip->ecc.hwctl		= omap_enable_hwecc_bch;
-		nand_chip->ecc.correct		= omap_elm_correct_data;
-		nand_chip->ecc.read_page	= omap_read_page_bch;
-		nand_chip->ecc.write_page	= omap_write_page_bch;
-		nand_chip->ecc.write_subpage	= omap_write_subpage_bch;
+		pr_info("Using OMAP_ECC_BCH16_CODE_HW ECC scheme\n");
+		chip->ecc.mode		= NAND_ECC_HW;
+		chip->ecc.size		= 512;
+		chip->ecc.bytes		= 26;
+		chip->ecc.strength	= 16;
+		chip->ecc.hwctl		= omap_enable_hwecc_bch;
+		chip->ecc.correct	= omap_elm_correct_data;
+		chip->ecc.read_page	= omap_read_page_bch;
+		chip->ecc.write_page	= omap_write_page_bch;
+		chip->ecc.write_subpage	= omap_write_subpage_bch;
 		mtd_set_ooblayout(mtd, &omap_ooblayout_ops);
-		oobbytes_per_step		= nand_chip->ecc.bytes;
+		oobbytes_per_step	= chip->ecc.bytes;
 
 		err = elm_config(info->elm_dev, BCH16_ECC,
-				 mtd->writesize / nand_chip->ecc.size,
-				 nand_chip->ecc.size, nand_chip->ecc.bytes);
+				 mtd->writesize / chip->ecc.size,
+				 chip->ecc.size, chip->ecc.bytes);
 		if (err < 0)
-			goto return_error;
+			return err;
 
 		break;
 	default:
-		dev_err(&info->pdev->dev, "invalid or unsupported ECC scheme\n");
-		err = -EINVAL;
-		goto return_error;
+		dev_err(dev, "Invalid or unsupported ECC scheme\n");
+		return -EINVAL;
 	}
 
-	/* check if NAND device's OOB is enough to store ECC signatures */
+	/* Check if NAND device's OOB is enough to store ECC signatures */
 	min_oobbytes += (oobbytes_per_step *
-			 (mtd->writesize / nand_chip->ecc.size));
+			 (mtd->writesize / chip->ecc.size));
 	if (mtd->oobsize < min_oobbytes) {
-		dev_err(&info->pdev->dev,
-			"not enough OOB bytes required = %d, available=%d\n",
+		dev_err(dev,
+			"Not enough OOB bytes: required = %d, available=%d\n",
 			min_oobbytes, mtd->oobsize);
-		err = -EINVAL;
-		goto return_error;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops omap_nand_controller_ops = {
+	.attach_chip = omap_nand_attach_chip,
+};
+
+/* Shared among all NAND instances to synchronize access to the ECC Engine */
+static struct nand_controller omap_gpmc_controller = {
+	.lock = __SPIN_LOCK_UNLOCKED(omap_gpmc_controller.lock),
+	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(omap_gpmc_controller.wq),
+	.ops = &omap_nand_controller_ops,
+};
+
+static int omap_nand_probe(struct platform_device *pdev)
+{
+	struct omap_nand_info		*info;
+	struct mtd_info			*mtd;
+	struct nand_chip		*nand_chip;
+	int				err;
+	struct resource			*res;
+	struct device			*dev = &pdev->dev;
+
+	info = devm_kzalloc(&pdev->dev, sizeof(struct omap_nand_info),
+				GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->pdev = pdev;
+
+	err = omap_get_dt_info(dev, info);
+	if (err)
+		return err;
+
+	info->ops = gpmc_omap_get_nand_ops(&info->reg, info->gpmc_cs);
+	if (!info->ops) {
+		dev_err(&pdev->dev, "Failed to get GPMC->NAND interface\n");
+		return -ENODEV;
+	}
+
+	nand_chip		= &info->nand;
+	mtd			= nand_to_mtd(nand_chip);
+	mtd->dev.parent		= &pdev->dev;
+	nand_chip->ecc.priv	= NULL;
+	nand_set_flash_node(nand_chip, dev->of_node);
+
+	if (!mtd->name) {
+		mtd->name = devm_kasprintf(&pdev->dev, GFP_KERNEL,
+					   "omap2-nand.%d", info->gpmc_cs);
+		if (!mtd->name) {
+			dev_err(&pdev->dev, "Failed to set MTD name\n");
+			return -ENOMEM;
+		}
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	nand_chip->IO_ADDR_R = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(nand_chip->IO_ADDR_R))
+		return PTR_ERR(nand_chip->IO_ADDR_R);
+
+	info->phys_base = res->start;
+
+	nand_chip->controller = &omap_gpmc_controller;
+
+	nand_chip->IO_ADDR_W = nand_chip->IO_ADDR_R;
+	nand_chip->cmd_ctrl  = omap_hwcontrol;
+
+	info->ready_gpiod = devm_gpiod_get_optional(&pdev->dev, "rb",
+						    GPIOD_IN);
+	if (IS_ERR(info->ready_gpiod)) {
+		dev_err(dev, "failed to get ready gpio\n");
+		return PTR_ERR(info->ready_gpiod);
+	}
+
+	/*
+	 * If RDY/BSY line is connected to OMAP then use the omap ready
+	 * function and the generic nand_wait function which reads the status
+	 * register after monitoring the RDY/BSY line. Otherwise use a standard
+	 * chip delay which is slightly more than tR (AC Timing) of the NAND
+	 * device and read status register until you get a failure or success
+	 */
+	if (info->ready_gpiod) {
+		nand_chip->dev_ready = omap_dev_ready;
+		nand_chip->chip_delay = 0;
+	} else {
+		nand_chip->waitfunc = omap_wait;
+		nand_chip->chip_delay = 50;
 	}
 
-scan_tail:
-	/* second phase scan */
-	err = nand_scan_tail(mtd);
+	if (info->flash_bbt)
+		nand_chip->bbt_options |= NAND_BBT_USE_FLASH;
+
+	/* scan NAND device connected to chip controller */
+	nand_chip->options |= info->devsize & NAND_BUSWIDTH_16;
+
+	err = nand_scan(mtd, 1);
 	if (err)
 		goto return_error;
 
-- 
cgit v1.2.3


From 7928225ffcb3d01c424983af30aba3c16ab5a585 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:40 +0200
Subject: mtd: rawnand: atmel: clarify NAND addition/removal paths

No need for an atmel_nand_register() function, let's move the code in
it directly where the function was called: in
atmel_nand_controller_add_nand(). To make things consistent, also
rename atmel_nand_unregister() into
atmel_nand_controller_remove_nand().

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 102 ++++++++++++---------------
 1 file changed, 45 insertions(+), 57 deletions(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 4d27401f1299..143d029710f0 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -1573,7 +1573,7 @@ static int atmel_nand_detect(struct atmel_nand *nand)
 	return ret;
 }
 
-static int atmel_nand_unregister(struct atmel_nand *nand)
+static int atmel_nand_controller_remove_nand(struct atmel_nand *nand)
 {
 	struct nand_chip *chip = &nand->base;
 	struct mtd_info *mtd = nand_to_mtd(chip);
@@ -1589,60 +1589,6 @@ static int atmel_nand_unregister(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_nand_register(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "atmel_nand";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your nand node:
-		 *
-		 *	label = "atmel_nand";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nc->dev),
-					   nand->cs[0].id);
-		if (!mtd->name) {
-			dev_err(nc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(nc->dev, "nand_scan_tail() failed: %d\n", ret);
-		return ret;
-	}
-
-	ret = mtd_device_register(mtd, NULL, 0);
-	if (ret) {
-		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
-		nand_cleanup(chip);
-		return ret;
-	}
-
-	list_add_tail(&nand->node, &nc->chips);
-
-	return 0;
-}
-
 static struct atmel_nand *atmel_nand_create(struct atmel_nand_controller *nc,
 					    struct device_node *np,
 					    int reg_cells)
@@ -1772,7 +1718,49 @@ atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 	if (ret)
 		return ret;
 
-	return atmel_nand_register(nand);
+	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "atmel_nand";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your nand node:
+		 *
+		 *	label = "atmel_nand";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nc->dev),
+					   nand->cs[0].id);
+		if (!mtd->name) {
+			dev_err(nc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	ret = nand_scan_tail(mtd);
+	if (ret) {
+		dev_err(nc->dev, "nand_scan_tail() failed: %d\n", ret);
+		return ret;
+	}
+
+	ret = mtd_device_register(mtd, NULL, 0);
+	if (ret) {
+		dev_err(nc->dev, "Failed to register mtd device: %d\n", ret);
+		nand_cleanup(chip);
+		return ret;
+	}
+
+	list_add_tail(&nand->node, &nc->chips);
+
+	return 0;
 }
 
 static int
@@ -1782,7 +1770,7 @@ atmel_nand_controller_remove_nands(struct atmel_nand_controller *nc)
 	int ret;
 
 	list_for_each_entry_safe(nand, tmp, &nc->chips, node) {
-		ret = atmel_nand_unregister(nand);
+		ret = atmel_nand_controller_remove_nand(nand);
 		if (ret)
 			return ret;
 	}
-- 
cgit v1.2.3


From 577e010c24bceb80dbbc146b2a4bd7ff0527fa9b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:41 +0200
Subject: mtd: rawnand: atmel: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/atmel/nand-controller.c | 113 +++++++++++++--------------
 1 file changed, 54 insertions(+), 59 deletions(-)

diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c
index 143d029710f0..a068b214ebaa 100644
--- a/drivers/mtd/nand/raw/atmel/nand-controller.c
+++ b/drivers/mtd/nand/raw/atmel/nand-controller.c
@@ -201,7 +201,7 @@ struct atmel_nand_controller_ops {
 	int (*remove)(struct atmel_nand_controller *nc);
 	void (*nand_init)(struct atmel_nand_controller *nc,
 			  struct atmel_nand *nand);
-	int (*ecc_init)(struct atmel_nand *nand);
+	int (*ecc_init)(struct nand_chip *chip);
 	int (*setup_data_interface)(struct atmel_nand *nand, int csline,
 				    const struct nand_data_interface *conf);
 };
@@ -1132,9 +1132,8 @@ static int atmel_nand_pmecc_init(struct nand_chip *chip)
 	return 0;
 }
 
-static int atmel_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	struct atmel_nand_controller *nc;
 	int ret;
 
@@ -1169,12 +1168,11 @@ static int atmel_nand_ecc_init(struct atmel_nand *nand)
 	return 0;
 }
 
-static int atmel_hsmc_nand_ecc_init(struct atmel_nand *nand)
+static int atmel_hsmc_nand_ecc_init(struct nand_chip *chip)
 {
-	struct nand_chip *chip = &nand->base;
 	int ret;
 
-	ret = atmel_nand_ecc_init(nand);
+	ret = atmel_nand_ecc_init(chip);
 	if (ret)
 		return ret;
 
@@ -1557,22 +1555,6 @@ static void atmel_hsmc_nand_init(struct atmel_nand_controller *nc,
 	chip->select_chip = atmel_hsmc_nand_select_chip;
 }
 
-static int atmel_nand_detect(struct atmel_nand *nand)
-{
-	struct nand_chip *chip = &nand->base;
-	struct mtd_info *mtd = nand_to_mtd(chip);
-	struct atmel_nand_controller *nc;
-	int ret;
-
-	nc = to_nand_controller(chip->controller);
-
-	ret = nand_scan_ident(mtd, nand->numcs, NULL);
-	if (ret)
-		dev_err(nc->dev, "nand_scan_ident() failed: %d\n", ret);
-
-	return ret;
-}
-
 static int atmel_nand_controller_remove_nand(struct atmel_nand *nand)
 {
 	struct nand_chip *chip = &nand->base;
@@ -1700,6 +1682,8 @@ static int
 atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 			       struct atmel_nand *nand)
 {
+	struct nand_chip *chip = &nand->base;
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	int ret;
 
 	/* No card inserted, skip this NAND. */
@@ -1710,44 +1694,9 @@ atmel_nand_controller_add_nand(struct atmel_nand_controller *nc,
 
 	nc->caps->ops->nand_init(nc, nand);
 
-	ret = atmel_nand_detect(nand);
-	if (ret)
-		return ret;
-
-	ret = nc->caps->ops->ecc_init(nand);
-	if (ret)
-		return ret;
-
-	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
-		/*
-		 * We keep the MTD name unchanged to avoid breaking platforms
-		 * where the MTD cmdline parser is used and the bootloader
-		 * has not been updated to use the new naming scheme.
-		 */
-		mtd->name = "atmel_nand";
-	} else if (!mtd->name) {
-		/*
-		 * If the new bindings are used and the bootloader has not been
-		 * updated to pass a new mtdparts parameter on the cmdline, you
-		 * should define the following property in your nand node:
-		 *
-		 *	label = "atmel_nand";
-		 *
-		 * This way, mtd->name will be set by the core when
-		 * nand_set_flash_node() is called.
-		 */
-		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
-					   "%s:nand.%d", dev_name(nc->dev),
-					   nand->cs[0].id);
-		if (!mtd->name) {
-			dev_err(nc->dev, "Failed to allocate mtd->name\n");
-			return -ENOMEM;
-		}
-	}
-
-	ret = nand_scan_tail(mtd);
+	ret = nand_scan(mtd, nand->numcs);
 	if (ret) {
-		dev_err(nc->dev, "nand_scan_tail() failed: %d\n", ret);
+		dev_err(nc->dev, "NAND scan failed: %d\n", ret);
 		return ret;
 	}
 
@@ -1945,6 +1894,51 @@ static const struct of_device_id atmel_matrix_of_ids[] = {
 	{ /* sentinel */ },
 };
 
+static int atmel_nand_attach_chip(struct nand_chip *chip)
+{
+	struct atmel_nand_controller *nc = to_nand_controller(chip->controller);
+	struct atmel_nand *nand = to_atmel_nand(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	int ret;
+
+	ret = nc->caps->ops->ecc_init(chip);
+	if (ret)
+		return ret;
+
+	if (nc->caps->legacy_of_bindings || !nc->dev->of_node) {
+		/*
+		 * We keep the MTD name unchanged to avoid breaking platforms
+		 * where the MTD cmdline parser is used and the bootloader
+		 * has not been updated to use the new naming scheme.
+		 */
+		mtd->name = "atmel_nand";
+	} else if (!mtd->name) {
+		/*
+		 * If the new bindings are used and the bootloader has not been
+		 * updated to pass a new mtdparts parameter on the cmdline, you
+		 * should define the following property in your nand node:
+		 *
+		 *	label = "atmel_nand";
+		 *
+		 * This way, mtd->name will be set by the core when
+		 * nand_set_flash_node() is called.
+		 */
+		mtd->name = devm_kasprintf(nc->dev, GFP_KERNEL,
+					   "%s:nand.%d", dev_name(nc->dev),
+					   nand->cs[0].id);
+		if (!mtd->name) {
+			dev_err(nc->dev, "Failed to allocate mtd->name\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
+static const struct nand_controller_ops atmel_nand_controller_ops = {
+	.attach_chip = atmel_nand_attach_chip,
+};
+
 static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 				struct platform_device *pdev,
 				const struct atmel_nand_controller_caps *caps)
@@ -1954,6 +1948,7 @@ static int atmel_nand_controller_init(struct atmel_nand_controller *nc,
 	int ret;
 
 	nand_controller_init(&nc->base);
+	nc->base.ops = &atmel_nand_controller_ops;
 	INIT_LIST_HEAD(&nc->chips);
 	nc->dev = dev;
 	nc->caps = caps;
-- 
cgit v1.2.3


From 49aa76b166765188af6682cd22985cbda1bb39c2 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:42 +0200
Subject: mtd: rawnand: do not execute nand_scan_ident() if maxchips is zero

Some driver (eg. docg4) will need to handle themselves the
identification phase. As part of the migration to use nand_scan()
everywhere (which will unconditionnaly call nand_scan_ident()), we add
a condition at the start of nand_scan_with_ids() to jump over
nand_scan_ident() if the maxchips parameters is zero, meaning that the
driver does not want the core to handle this phase.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index dea41fa25be1..42a7a934a17b 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -6735,7 +6735,9 @@ static void nand_detach(struct nand_chip *chip)
 /**
  * nand_scan_with_ids - [NAND Interface] Scan for the NAND device
  * @mtd: MTD device structure
- * @maxchips: number of chips to scan for
+ * @maxchips: number of chips to scan for. @nand_scan_ident() will not be run if
+ *	      this parameter is zero (useful for specific drivers that must
+ *	      handle this part of the process themselves, e.g docg4).
  * @ids: optional flash IDs table
  *
  * This fills out all the uninitialized function pointers with the defaults.
@@ -6748,9 +6750,11 @@ int nand_scan_with_ids(struct mtd_info *mtd, int maxchips,
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	int ret;
 
-	ret = nand_scan_ident(mtd, maxchips, ids);
-	if (ret)
-		return ret;
+	if (maxchips) {
+		ret = nand_scan_ident(mtd, maxchips, ids);
+		if (ret)
+			return ret;
+	}
 
 	ret = nand_attach(chip);
 	if (ret)
-- 
cgit v1.2.3


From 66a38478dcc5b5a35e49055f2eb301f8ac594e3f Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:43 +0200
Subject: mtd: rawnand: docg4: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/docg4.c | 71 ++++++++++++++++++++++++++++----------------
 1 file changed, 45 insertions(+), 26 deletions(-)

diff --git a/drivers/mtd/nand/raw/docg4.c b/drivers/mtd/nand/raw/docg4.c
index 4dccdfba6140..a3f04315c05c 100644
--- a/drivers/mtd/nand/raw/docg4.c
+++ b/drivers/mtd/nand/raw/docg4.c
@@ -1227,10 +1227,9 @@ static void __init init_mtd_structs(struct mtd_info *mtd)
 	 * required within a nand driver because they are performed by the nand
 	 * infrastructure code as part of nand_scan().  In this case they need
 	 * to be initialized here because we skip call to nand_scan_ident() (the
-	 * first half of nand_scan()).  The call to nand_scan_ident() is skipped
-	 * because for this device the chip id is not read in the manner of a
-	 * standard nand device.  Unfortunately, nand_scan_ident() does other
-	 * things as well, such as call nand_set_defaults().
+	 * first half of nand_scan()).  The call to nand_scan_ident() could be
+	 * skipped because for this device the chip id is not read in the manner
+	 * of a standard nand device.
 	 */
 
 	struct nand_chip *nand = mtd_to_nand(mtd);
@@ -1315,6 +1314,40 @@ static int __init read_id_reg(struct mtd_info *mtd)
 
 static char const *part_probes[] = { "cmdlinepart", "saftlpart", NULL };
 
+static int docg4_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+	int ret;
+
+	init_mtd_structs(mtd);
+
+	/* Initialize kernel BCH algorithm */
+	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
+	if (!doc->bch)
+		return -EINVAL;
+
+	reset(mtd);
+
+	ret = read_id_reg(mtd);
+	if (ret)
+		free_bch(doc->bch);
+
+	return ret;
+}
+
+static void docg4_detach_chip(struct nand_chip *chip)
+{
+	struct docg4_priv *doc = (struct docg4_priv *)(chip + 1);
+
+	free_bch(doc->bch);
+}
+
+static const struct nand_controller_ops docg4_controller_ops = {
+	.attach_chip = docg4_attach_chip,
+	.detach_chip = docg4_detach_chip,
+};
+
 static int __init probe_docg4(struct platform_device *pdev)
 {
 	struct mtd_info *mtd;
@@ -1350,28 +1383,17 @@ static int __init probe_docg4(struct platform_device *pdev)
 	mtd->dev.parent = &pdev->dev;
 	doc->virtadr = virtadr;
 	doc->dev = dev;
-
-	init_mtd_structs(mtd);
-
-	/* initialize kernel bch algorithm */
-	doc->bch = init_bch(DOCG4_M, DOCG4_T, DOCG4_PRIMITIVE_POLY);
-	if (doc->bch == NULL) {
-		retval = -EINVAL;
-		goto free_nand;
-	}
-
 	platform_set_drvdata(pdev, doc);
 
-	reset(mtd);
-	retval = read_id_reg(mtd);
-	if (retval == -ENODEV) {
-		dev_warn(dev, "No diskonchip G4 device found.\n");
-		goto free_bch;
-	}
-
-	retval = nand_scan_tail(mtd);
+	/*
+	 * Running nand_scan() with maxchips == 0 will skip nand_scan_ident(),
+	 * which is a specific operation with this driver and done in the
+	 * ->attach_chip callback.
+	 */
+	nand->dummy_controller.ops = &docg4_controller_ops;
+	retval = nand_scan(mtd, 0);
 	if (retval)
-		goto free_bch;
+		goto free_nand;
 
 	retval = read_factory_bbt(mtd);
 	if (retval)
@@ -1387,8 +1409,6 @@ static int __init probe_docg4(struct platform_device *pdev)
 
 cleanup_nand:
 	nand_cleanup(nand);
-free_bch:
-	free_bch(doc->bch);
 free_nand:
 	kfree(nand);
 unmap:
@@ -1401,7 +1421,6 @@ static int __exit cleanup_docg4(struct platform_device *pdev)
 {
 	struct docg4_priv *doc = platform_get_drvdata(pdev);
 	nand_release(doc->mtd);
-	free_bch(doc->bch);
 	kfree(mtd_to_nand(doc->mtd));
 	iounmap(doc->virtadr);
 	return 0;
-- 
cgit v1.2.3


From f57bbfb9e3f47b6d4eecb1d8037dab1cda9996a4 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:44 +0200
Subject: mtd: rawnand: jz4740: fix probe function error path

An error after nand_scan_tail() should trigger a nand_cleanup(), not a
nand_release() as mtd_device_register() (or one of its variants) has not
been called and there is no need to deregister any MTD device yet.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/jz4740_nand.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index a4052b03249c..3abf87420c10 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -472,15 +472,15 @@ static int jz_nand_probe(struct platform_device *pdev)
 
 	if (ret) {
 		dev_err(&pdev->dev, "Failed to add mtd device\n");
-		goto err_nand_release;
+		goto err_cleanup_nand;
 	}
 
 	dev_info(&pdev->dev, "Successfully registered JZ4740 NAND driver\n");
 
 	return 0;
 
-err_nand_release:
-	nand_release(mtd);
+err_cleanup_nand:
+	nand_cleanup(chip);
 err_unclaim_banks:
 	while (chipnr--) {
 		unsigned char bank = nand->banks[chipnr];
-- 
cgit v1.2.3


From 2f2173449b0350a206faf0d1aa71595602a40c98 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:45 +0200
Subject: mtd: rawnand: jz4740: group nand_scan_{ident, tail} calls

Prepare the migration to nand_scan() by moving both calls to
nand_scan_ident() and nand_scan_tail() in a single spot.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/jz4740_nand.c | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index 3abf87420c10..ccd8f897db7c 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -309,6 +309,7 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 			       size_t chipnr, uint8_t *nand_maf_id,
 			       uint8_t *nand_dev_id)
 {
+	struct jz_nand_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int ret;
 	char res_name[6];
 	uint32_t ctrl;
@@ -335,6 +336,16 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 		if (ret)
 			goto notfound_id;
 
+		if (pdata && pdata->ident_callback)
+			pdata->ident_callback(pdev, mtd, &pdata->partitions,
+					      &pdata->num_partitions);
+
+		ret = nand_scan_tail(mtd);
+		if (ret) {
+			dev_err(&pdev->dev,  "Failed to scan NAND\n");
+			goto notfound_id;
+		}
+
 		/* Retrieve the IDs from the first chip. */
 		chip->select_chip(mtd, 0);
 		nand_reset_op(chip);
@@ -456,17 +467,6 @@ static int jz_nand_probe(struct platform_device *pdev)
 		goto err_iounmap_mmio;
 	}
 
-	if (pdata && pdata->ident_callback) {
-		pdata->ident_callback(pdev, mtd, &pdata->partitions,
-					&pdata->num_partitions);
-	}
-
-	ret = nand_scan_tail(mtd);
-	if (ret) {
-		dev_err(&pdev->dev,  "Failed to scan NAND\n");
-		goto err_unclaim_banks;
-	}
-
 	ret = mtd_device_register(mtd, pdata ? pdata->partitions : NULL,
 				  pdata ? pdata->num_partitions : 0);
 
@@ -481,7 +481,6 @@ static int jz_nand_probe(struct platform_device *pdev)
 
 err_cleanup_nand:
 	nand_cleanup(chip);
-err_unclaim_banks:
 	while (chipnr--) {
 		unsigned char bank = nand->banks[chipnr];
 		jz_nand_iounmap_resource(nand->bank_mem[bank - 1],
-- 
cgit v1.2.3


From ccadc14975c9bbd17da3a4b0b443325a5bda0ba2 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:46 +0200
Subject: mtd: rawnand: jz4740: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/jz4740_nand.c | 32 ++++++++++++++++++++------------
 1 file changed, 20 insertions(+), 12 deletions(-)

diff --git a/drivers/mtd/nand/raw/jz4740_nand.c b/drivers/mtd/nand/raw/jz4740_nand.c
index ccd8f897db7c..a7515452bc59 100644
--- a/drivers/mtd/nand/raw/jz4740_nand.c
+++ b/drivers/mtd/nand/raw/jz4740_nand.c
@@ -309,7 +309,6 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 			       size_t chipnr, uint8_t *nand_maf_id,
 			       uint8_t *nand_dev_id)
 {
-	struct jz_nand_platform_data *pdata = dev_get_platdata(&pdev->dev);
 	int ret;
 	char res_name[6];
 	uint32_t ctrl;
@@ -332,20 +331,10 @@ static int jz_nand_detect_bank(struct platform_device *pdev,
 
 	if (chipnr == 0) {
 		/* Detect first chip. */
-		ret = nand_scan_ident(mtd, 1, NULL);
+		ret = nand_scan(mtd, 1);
 		if (ret)
 			goto notfound_id;
 
-		if (pdata && pdata->ident_callback)
-			pdata->ident_callback(pdev, mtd, &pdata->partitions,
-					      &pdata->num_partitions);
-
-		ret = nand_scan_tail(mtd);
-		if (ret) {
-			dev_err(&pdev->dev,  "Failed to scan NAND\n");
-			goto notfound_id;
-		}
-
 		/* Retrieve the IDs from the first chip. */
 		chip->select_chip(mtd, 0);
 		nand_reset_op(chip);
@@ -379,6 +368,24 @@ notfound_id:
 	return ret;
 }
 
+static int jz_nand_attach_chip(struct nand_chip *chip)
+{
+	struct mtd_info *mtd = nand_to_mtd(chip);
+	struct device *dev = mtd->dev.parent;
+	struct jz_nand_platform_data *pdata = dev_get_platdata(dev);
+	struct platform_device *pdev = to_platform_device(dev);
+
+	if (pdata && pdata->ident_callback)
+		pdata->ident_callback(pdev, mtd, &pdata->partitions,
+				      &pdata->num_partitions);
+
+	return 0;
+}
+
+static const struct nand_controller_ops jz_nand_controller_ops = {
+	.attach_chip = jz_nand_attach_chip,
+};
+
 static int jz_nand_probe(struct platform_device *pdev)
 {
 	int ret;
@@ -422,6 +429,7 @@ static int jz_nand_probe(struct platform_device *pdev)
 	chip->chip_delay = 50;
 	chip->cmd_ctrl = jz_nand_cmd_ctrl;
 	chip->select_chip = jz_nand_select_chip;
+	chip->dummy_controller.ops = &jz_nand_controller_ops;
 
 	if (nand->busy_gpio)
 		chip->dev_ready = jz_nand_dev_ready;
-- 
cgit v1.2.3


From 176fc2f28ee5ebd494c39d25dda3e0a71e0b649a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:47 +0200
Subject: mtd: rawnand: tegra: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/tegra_nand.c | 162 +++++++++++++++++++++-----------------
 1 file changed, 88 insertions(+), 74 deletions(-)

diff --git a/drivers/mtd/nand/raw/tegra_nand.c b/drivers/mtd/nand/raw/tegra_nand.c
index 31c0d9ca9d23..79da1efc88d1 100644
--- a/drivers/mtd/nand/raw/tegra_nand.c
+++ b/drivers/mtd/nand/raw/tegra_nand.c
@@ -906,74 +906,13 @@ static int tegra_nand_select_strength(struct nand_chip *chip, int oobsize)
 				       bits_per_step, oobsize);
 }
 
-static int tegra_nand_chips_init(struct device *dev,
-				 struct tegra_nand_controller *ctrl)
+static int tegra_nand_attach_chip(struct nand_chip *chip)
 {
-	struct device_node *np = dev->of_node;
-	struct device_node *np_nand;
-	int nsels, nchips = of_get_child_count(np);
-	struct tegra_nand_chip *nand;
-	struct mtd_info *mtd;
-	struct nand_chip *chip;
+	struct tegra_nand_controller *ctrl = to_tegra_ctrl(chip->controller);
+	struct tegra_nand_chip *nand = to_tegra_chip(chip);
+	struct mtd_info *mtd = nand_to_mtd(chip);
 	int bits_per_step;
 	int ret;
-	u32 cs;
-
-	if (nchips != 1) {
-		dev_err(dev, "Currently only one NAND chip supported\n");
-		return -EINVAL;
-	}
-
-	np_nand = of_get_next_child(np, NULL);
-
-	nsels = of_property_count_elems_of_size(np_nand, "reg", sizeof(u32));
-	if (nsels != 1) {
-		dev_err(dev, "Missing/invalid reg property\n");
-		return -EINVAL;
-	}
-
-	/* Retrieve CS id, currently only single die NAND supported */
-	ret = of_property_read_u32(np_nand, "reg", &cs);
-	if (ret) {
-		dev_err(dev, "could not retrieve reg property: %d\n", ret);
-		return ret;
-	}
-
-	nand = devm_kzalloc(dev, sizeof(*nand), GFP_KERNEL);
-	if (!nand)
-		return -ENOMEM;
-
-	nand->cs[0] = cs;
-
-	nand->wp_gpio = devm_gpiod_get_optional(dev, "wp", GPIOD_OUT_LOW);
-
-	if (IS_ERR(nand->wp_gpio)) {
-		ret = PTR_ERR(nand->wp_gpio);
-		dev_err(dev, "Failed to request WP GPIO: %d\n", ret);
-		return ret;
-	}
-
-	chip = &nand->chip;
-	chip->controller = &ctrl->controller;
-
-	mtd = nand_to_mtd(chip);
-
-	mtd->dev.parent = dev;
-	mtd->owner = THIS_MODULE;
-
-	nand_set_flash_node(chip, np_nand);
-
-	if (!mtd->name)
-		mtd->name = "tegra_nand";
-
-	chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER;
-	chip->exec_op = tegra_nand_exec_op;
-	chip->select_chip = tegra_nand_select_chip;
-	chip->setup_data_interface = tegra_nand_setup_data_interface;
-
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (ret)
-		return ret;
 
 	if (chip->bbt_options & NAND_BBT_USE_FLASH)
 		chip->bbt_options |= NAND_BBT_NO_OOB;
@@ -982,7 +921,8 @@ static int tegra_nand_chips_init(struct device *dev,
 	chip->ecc.size = 512;
 	chip->ecc.steps = mtd->writesize / chip->ecc.size;
 	if (chip->ecc_step_ds != 512) {
-		dev_err(dev, "Unsupported step size %d\n", chip->ecc_step_ds);
+		dev_err(ctrl->dev, "Unsupported step size %d\n",
+			chip->ecc_step_ds);
 		return -EINVAL;
 	}
 
@@ -1004,14 +944,15 @@ static int tegra_nand_chips_init(struct device *dev,
 	}
 
 	if (chip->ecc.algo == NAND_ECC_BCH && mtd->writesize < 2048) {
-		dev_err(dev, "BCH supports 2K or 4K page size only\n");
+		dev_err(ctrl->dev, "BCH supports 2K or 4K page size only\n");
 		return -EINVAL;
 	}
 
 	if (!chip->ecc.strength) {
 		ret = tegra_nand_select_strength(chip, mtd->oobsize);
 		if (ret < 0) {
-			dev_err(dev, "No valid strength found, minimum %d\n",
+			dev_err(ctrl->dev,
+				"No valid strength found, minimum %d\n",
 				chip->ecc_strength_ds);
 			return ret;
 		}
@@ -1039,7 +980,7 @@ static int tegra_nand_chips_init(struct device *dev,
 			nand->config_ecc |= CONFIG_TVAL_8;
 			break;
 		default:
-			dev_err(dev, "ECC strength %d not supported\n",
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
 				chip->ecc.strength);
 			return -EINVAL;
 		}
@@ -1062,17 +1003,17 @@ static int tegra_nand_chips_init(struct device *dev,
 			nand->bch_config |= BCH_TVAL_16;
 			break;
 		default:
-			dev_err(dev, "ECC strength %d not supported\n",
+			dev_err(ctrl->dev, "ECC strength %d not supported\n",
 				chip->ecc.strength);
 			return -EINVAL;
 		}
 		break;
 	default:
-		dev_err(dev, "ECC algorithm not supported\n");
+		dev_err(ctrl->dev, "ECC algorithm not supported\n");
 		return -EINVAL;
 	}
 
-	dev_info(dev, "Using %s with strength %d per 512 byte step\n",
+	dev_info(ctrl->dev, "Using %s with strength %d per 512 byte step\n",
 		 chip->ecc.algo == NAND_ECC_BCH ? "BCH" : "RS",
 		 chip->ecc.strength);
 
@@ -1095,7 +1036,8 @@ static int tegra_nand_chips_init(struct device *dev,
 		nand->config |= CONFIG_PS_4096;
 		break;
 	default:
-		dev_err(dev, "Unsupported writesize %d\n", mtd->writesize);
+		dev_err(ctrl->dev, "Unsupported writesize %d\n",
+			mtd->writesize);
 		return -ENODEV;
 	}
 
@@ -1106,7 +1048,78 @@ static int tegra_nand_chips_init(struct device *dev,
 	nand->config |= CONFIG_TAG_BYTE_SIZE(mtd->oobsize - 1);
 	writel_relaxed(nand->config, ctrl->regs + CONFIG);
 
-	ret = nand_scan_tail(mtd);
+	return 0;
+}
+
+static const struct nand_controller_ops tegra_nand_controller_ops = {
+	.attach_chip = &tegra_nand_attach_chip,
+};
+
+static int tegra_nand_chips_init(struct device *dev,
+				 struct tegra_nand_controller *ctrl)
+{
+	struct device_node *np = dev->of_node;
+	struct device_node *np_nand;
+	int nsels, nchips = of_get_child_count(np);
+	struct tegra_nand_chip *nand;
+	struct mtd_info *mtd;
+	struct nand_chip *chip;
+	int ret;
+	u32 cs;
+
+	if (nchips != 1) {
+		dev_err(dev, "Currently only one NAND chip supported\n");
+		return -EINVAL;
+	}
+
+	np_nand = of_get_next_child(np, NULL);
+
+	nsels = of_property_count_elems_of_size(np_nand, "reg", sizeof(u32));
+	if (nsels != 1) {
+		dev_err(dev, "Missing/invalid reg property\n");
+		return -EINVAL;
+	}
+
+	/* Retrieve CS id, currently only single die NAND supported */
+	ret = of_property_read_u32(np_nand, "reg", &cs);
+	if (ret) {
+		dev_err(dev, "could not retrieve reg property: %d\n", ret);
+		return ret;
+	}
+
+	nand = devm_kzalloc(dev, sizeof(*nand), GFP_KERNEL);
+	if (!nand)
+		return -ENOMEM;
+
+	nand->cs[0] = cs;
+
+	nand->wp_gpio = devm_gpiod_get_optional(dev, "wp", GPIOD_OUT_LOW);
+
+	if (IS_ERR(nand->wp_gpio)) {
+		ret = PTR_ERR(nand->wp_gpio);
+		dev_err(dev, "Failed to request WP GPIO: %d\n", ret);
+		return ret;
+	}
+
+	chip = &nand->chip;
+	chip->controller = &ctrl->controller;
+
+	mtd = nand_to_mtd(chip);
+
+	mtd->dev.parent = dev;
+	mtd->owner = THIS_MODULE;
+
+	nand_set_flash_node(chip, np_nand);
+
+	if (!mtd->name)
+		mtd->name = "tegra_nand";
+
+	chip->options = NAND_NO_SUBPAGE_WRITE | NAND_USE_BOUNCE_BUFFER;
+	chip->exec_op = tegra_nand_exec_op;
+	chip->select_chip = tegra_nand_select_chip;
+	chip->setup_data_interface = tegra_nand_setup_data_interface;
+
+	ret = nand_scan(mtd, 1);
 	if (ret)
 		return ret;
 
@@ -1137,6 +1150,7 @@ static int tegra_nand_probe(struct platform_device *pdev)
 
 	ctrl->dev = &pdev->dev;
 	nand_controller_init(&ctrl->controller);
+	ctrl->controller.ops = &tegra_nand_controller_ops;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	ctrl->regs = devm_ioremap_resource(&pdev->dev, res);
-- 
cgit v1.2.3


From abe23d1c5cdf888639313bf87880d2692d0b8724 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:48 +0200
Subject: mtd: rawnand: txx9ndfmc: clarify ECC parameters assignation

A comment in the probe declares that values are assigned to ecc.size
and ecc.bytes, but these values will be overwritten. This is not
entirely right as they are overwritten only if
mtd->writesize >= 512. Let's clarify this by moving these assignations
to txx9ndfmc_nand_scan().

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/txx9ndfmc.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 9019022774f7..9808b18b15e2 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -262,10 +262,13 @@ static int txx9ndfmc_nand_scan(struct mtd_info *mtd)
 	ret = nand_scan_ident(mtd, 1, NULL);
 	if (!ret) {
 		if (mtd->writesize >= 512) {
-			/* Hardware ECC 6 byte ECC per 512 Byte data */
 			chip->ecc.size = 512;
 			chip->ecc.bytes = 6;
+		} else {
+			chip->ecc.size = 256;
+			chip->ecc.bytes = 3;
 		}
+
 		ret = nand_scan_tail(mtd);
 	}
 	return ret;
@@ -332,9 +335,6 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		chip->ecc.correct = txx9ndfmc_correct_data;
 		chip->ecc.hwctl = txx9ndfmc_enable_hwecc;
 		chip->ecc.mode = NAND_ECC_HW;
-		/* txx9ndfmc_nand_scan will overwrite ecc.size and ecc.bytes */
-		chip->ecc.size = 256;
-		chip->ecc.bytes = 3;
 		chip->ecc.strength = 1;
 		chip->chip_delay = 100;
 		chip->controller = &drvdata->controller;
-- 
cgit v1.2.3


From ee1af8296dbc34c8198cbdd54cc244c19a10321e Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:49 +0200
Subject: mtd: rawnand: txx9ndfmc: convert driver to nand_scan()

Two helpers have been added to the core to do all kind of controller
side configuration/initialization between the detection phase and the
final NAND scan. Implement these hooks so that we can convert the driver
to just use nand_scan() instead of the nand_scan_ident() +
nand_scan_tail() pair.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/txx9ndfmc.c | 34 +++++++++++++++++-----------------
 1 file changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/mtd/nand/raw/txx9ndfmc.c b/drivers/mtd/nand/raw/txx9ndfmc.c
index 9808b18b15e2..4d61a14fcb65 100644
--- a/drivers/mtd/nand/raw/txx9ndfmc.c
+++ b/drivers/mtd/nand/raw/txx9ndfmc.c
@@ -254,26 +254,25 @@ static void txx9ndfmc_initialize(struct platform_device *dev)
 #define TXX9NDFMC_NS_TO_CYC(gbusclk, ns) \
 	DIV_ROUND_UP((ns) * DIV_ROUND_UP(gbusclk, 1000), 1000000)
 
-static int txx9ndfmc_nand_scan(struct mtd_info *mtd)
+static int txx9ndfmc_attach_chip(struct nand_chip *chip)
 {
-	struct nand_chip *chip = mtd_to_nand(mtd);
-	int ret;
-
-	ret = nand_scan_ident(mtd, 1, NULL);
-	if (!ret) {
-		if (mtd->writesize >= 512) {
-			chip->ecc.size = 512;
-			chip->ecc.bytes = 6;
-		} else {
-			chip->ecc.size = 256;
-			chip->ecc.bytes = 3;
-		}
-
-		ret = nand_scan_tail(mtd);
+	struct mtd_info *mtd = nand_to_mtd(chip);
+
+	if (mtd->writesize >= 512) {
+		chip->ecc.size = 512;
+		chip->ecc.bytes = 6;
+	} else {
+		chip->ecc.size = 256;
+		chip->ecc.bytes = 3;
 	}
-	return ret;
+
+	return 0;
 }
 
+static const struct nand_controller_ops txx9ndfmc_controller_ops = {
+	.attach_chip = txx9ndfmc_attach_chip,
+};
+
 static int __init txx9ndfmc_probe(struct platform_device *dev)
 {
 	struct txx9ndfmc_platform_data *plat = dev_get_platdata(&dev->dev);
@@ -307,6 +306,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		 (gbusclk + 500000) / 1000000, hold, spw);
 
 	nand_controller_init(&drvdata->controller);
+	drvdata->controller.ops = &txx9ndfmc_controller_ops;
 
 	platform_set_drvdata(dev, drvdata);
 	txx9ndfmc_initialize(dev);
@@ -359,7 +359,7 @@ static int __init txx9ndfmc_probe(struct platform_device *dev)
 		if (plat->wide_mask & (1 << i))
 			chip->options |= NAND_BUSWIDTH_16;
 
-		if (txx9ndfmc_nand_scan(mtd)) {
+		if (nand_scan(mtd, 1)) {
 			kfree(txx9_priv->mtdname);
 			kfree(txx9_priv);
 			continue;
-- 
cgit v1.2.3


From 98732da1a08ebb666983d469981a8b994e77d556 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:50 +0200
Subject: mtd: rawnand: do not export nand_scan_[ident|tail]() anymore

Both nand_scan_ident() and nand_scan_tail() helpers used to be called
directly from controller drivers that needed to tweak some ECC-related
parameters before nand_scan_tail(). This separation prevented dynamic
allocations during the phase of NAND identification, which was
inconvenient.

All controller drivers have been moved to use nand_scan(), in
conjunction with the chip->ecc.[attach|detach]_chip() hooks that
actually do the required tweaking sequence between both ident/tail
calls, allowing programmers to use dynamic allocation as they need all
across the scanning sequence.

Declare nand_scan_[ident|tail]() statically now.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 16 +++++++++-------
 include/linux/mtd/rawnand.h      | 18 ++++++------------
 2 files changed, 15 insertions(+), 19 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 42a7a934a17b..34ea44f90fd8 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5924,7 +5924,7 @@ static int nand_dt_init(struct nand_chip *chip)
 }
 
 /**
- * nand_scan_ident - [NAND Interface] Scan for the NAND device
+ * nand_scan_ident - Scan for the NAND device
  * @mtd: MTD device structure
  * @maxchips: number of chips to scan for
  * @table: alternative NAND ID table
@@ -5932,9 +5932,13 @@ static int nand_dt_init(struct nand_chip *chip)
  * This is the first phase of the normal nand_scan() function. It reads the
  * flash ID and sets up MTD fields accordingly.
  *
+ * This helper used to be called directly from controller drivers that needed
+ * to tweak some ECC-related parameters before nand_scan_tail(). This separation
+ * prevented dynamic allocations during this phase which was unconvenient and
+ * as been banned for the benefit of the ->init_ecc()/cleanup_ecc() hooks.
  */
-int nand_scan_ident(struct mtd_info *mtd, int maxchips,
-		    struct nand_flash_dev *table)
+static int nand_scan_ident(struct mtd_info *mtd, int maxchips,
+			   struct nand_flash_dev *table)
 {
 	int i, nand_maf_id, nand_dev_id;
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -6008,7 +6012,6 @@ int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 
 	return 0;
 }
-EXPORT_SYMBOL(nand_scan_ident);
 
 static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
 {
@@ -6385,14 +6388,14 @@ static bool nand_ecc_strength_good(struct mtd_info *mtd)
 }
 
 /**
- * nand_scan_tail - [NAND Interface] Scan for the NAND device
+ * nand_scan_tail - Scan for the NAND device
  * @mtd: MTD device structure
  *
  * This is the second phase of the normal nand_scan() function. It fills out
  * all the uninitialized function pointers with the defaults and scans for a
  * bad block table if appropriate.
  */
-int nand_scan_tail(struct mtd_info *mtd)
+static int nand_scan_tail(struct mtd_info *mtd)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
 	struct nand_ecc_ctrl *ecc = &chip->ecc;
@@ -6716,7 +6719,6 @@ err_free_buf:
 
 	return ret;
 }
-EXPORT_SYMBOL(nand_scan_tail);
 
 static int nand_attach(struct nand_chip *chip)
 {
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index fbd6b29cf22c..71571ed23a20 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -35,17 +35,6 @@ static inline int nand_scan(struct mtd_info *mtd, int max_chips)
 	return nand_scan_with_ids(mtd, max_chips, NULL);
 }
 
-/*
- * Separate phases of nand_scan(), allowing board driver to intervene
- * and override command or ECC setup according to flash type.
- */
-int nand_scan_ident(struct mtd_info *mtd, int max_chips,
-			   struct nand_flash_dev *table);
-int nand_scan_tail(struct mtd_info *mtd);
-
-/* Unregister the MTD device and free resources held by the NAND device */
-void nand_release(struct mtd_info *mtd);
-
 /* Internal helper for board drivers which need to override command function */
 void nand_wait_ready(struct mtd_info *mtd);
 
@@ -1745,8 +1734,13 @@ int nand_read_data_op(struct nand_chip *chip, void *buf, unsigned int len,
 int nand_write_data_op(struct nand_chip *chip, const void *buf,
 		       unsigned int len, bool force_8bit);
 
-/* Free resources held by the NAND device */
+/*
+ * Free resources held by the NAND device, must be called on error after a
+ * sucessful nand_scan().
+ */
 void nand_cleanup(struct nand_chip *chip);
+/* Unregister the MTD device and calls nand_cleanup() */
+void nand_release(struct mtd_info *mtd);
 
 /* Default extended ID decoding function */
 void nand_decode_ext_id(struct nand_chip *chip);
-- 
cgit v1.2.3


From 2023f1fa216f30b1877d65be2057fbaf0bbd49b3 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:51 +0200
Subject: mtd: rawnand: allocate model parameter dynamically

Thanks to the migration of all drivers to use nand_scan() and the
related nand_controller_ops, we can now allocate data during the
detection phase. Let's do it first for the NAND model parameter which
is allocated in nand_detect().

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c | 52 +++++++++++++++++++++++++++++++---------
 include/linux/mtd/rawnand.h      |  2 +-
 2 files changed, 42 insertions(+), 12 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 34ea44f90fd8..00e80781124a 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5225,8 +5225,11 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_onfi_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5356,8 +5359,11 @@ static int nand_flash_detect_jedec(struct nand_chip *chip)
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
 	sanitize_string(p->model, sizeof(p->model));
-	strncpy(chip->parameters.model, p->model,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(p->model, GFP_KERNEL);
+	if (!chip->parameters.model) {
+		ret = -ENOMEM;
+		goto free_jedec_param_page;
+	}
 
 	mtd->writesize = le32_to_cpu(p->byte_per_page);
 
@@ -5546,8 +5552,9 @@ static bool find_full_id_nand(struct nand_chip *chip,
 		chip->onfi_timing_mode_default =
 					type->onfi_timing_mode_default;
 
-		strncpy(chip->parameters.model, type->name,
-			sizeof(chip->parameters.model) - 1);
+		chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+		if (!chip->parameters.model)
+			return false;
 
 		return true;
 	}
@@ -5706,8 +5713,9 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 	if (!type->name)
 		return -ENODEV;
 
-	strncpy(chip->parameters.model, type->name,
-		sizeof(chip->parameters.model) - 1);
+	chip->parameters.model = kstrdup(type->name, GFP_KERNEL);
+	if (!chip->parameters.model)
+		return -ENOMEM;
 
 	chip->chipsize = (uint64_t)type->chipsize << 20;
 
@@ -5737,7 +5745,9 @@ ident_done:
 			mtd->name);
 		pr_warn("bus width %d instead of %d bits\n", busw ? 16 : 8,
 			(chip->options & NAND_BUSWIDTH_16) ? 16 : 8);
-		return -EINVAL;
+		ret = -EINVAL;
+
+		goto free_detect_allocation;
 	}
 
 	nand_decode_bbm_options(chip);
@@ -5774,6 +5784,11 @@ ident_done:
 		(int)(chip->chipsize >> 20), nand_is_slc(chip) ? "SLC" : "MLC",
 		mtd->erasesize >> 10, mtd->writesize, mtd->oobsize);
 	return 0;
+
+free_detect_allocation:
+	kfree(chip->parameters.model);
+
+	return ret;
 }
 
 static const char * const nand_ecc_modes[] = {
@@ -6013,6 +6028,11 @@ static int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 	return 0;
 }
 
+static void nand_scan_ident_cleanup(struct nand_chip *chip)
+{
+	kfree(chip->parameters.model);
+}
+
 static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
 {
 	struct nand_chip *chip = mtd_to_nand(mtd);
@@ -6760,11 +6780,18 @@ int nand_scan_with_ids(struct mtd_info *mtd, int maxchips,
 
 	ret = nand_attach(chip);
 	if (ret)
-		return ret;
+		goto cleanup_ident;
 
 	ret = nand_scan_tail(mtd);
 	if (ret)
-		nand_detach(chip);
+		goto detach_chip;
+
+	return 0;
+
+detach_chip:
+	nand_detach(chip);
+cleanup_ident:
+	nand_scan_ident_cleanup(chip);
 
 	return ret;
 }
@@ -6796,6 +6823,9 @@ void nand_cleanup(struct nand_chip *chip)
 
 	/* Free controller specific allocations after chip identification */
 	nand_detach(chip);
+
+	/* Free identification phase allocations */
+	nand_scan_ident_cleanup(chip);
 }
 
 EXPORT_SYMBOL_GPL(nand_cleanup);
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 71571ed23a20..099fa166569a 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -476,7 +476,7 @@ struct onfi_params {
  */
 struct nand_parameters {
 	/* Generic parameters */
-	char model[100];
+	const char *model;
 	bool supports_set_get_features;
 	DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER);
 	DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER);
-- 
cgit v1.2.3


From 3f259111583801013cb605bb4414aa529adccf1c Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven.eckelmann@openmesh.com>
Date: Thu, 26 Jul 2018 15:59:48 +0200
Subject: ath10k: prevent active scans on potential unusable channels

The QCA4019 hw1.0 firmware 10.4-3.2.1-00050 and 10.4-3.5.3-00053 (and most
likely all other) seem to ignore the WMI_CHAN_FLAG_DFS flag during the
scan. This results in transmission (probe requests) on channels which are
not "available" for transmissions.

Since the firmware is closed source and nothing can be done from our side
to fix the problem in it, the driver has to work around this problem. The
WMI_CHAN_FLAG_PASSIVE seems to be interpreted by the firmware to not
scan actively on a channel unless an AP was detected on it. Simple probe
requests will then be transmitted by the STA on the channel.

ath10k must therefore also use this flag when it queues a radar channel for
scanning. This should reduce the chance of an active scan when the channel
might be "unusable" for transmissions.

Fixes: e8a50f8ba44b ("ath10k: introduce DFS implementation")
Signed-off-by: Sven Eckelmann <sven.eckelmann@openmesh.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath10k/mac.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/ath/ath10k/mac.c b/drivers/net/wireless/ath/ath10k/mac.c
index b6830fa16e99..90f9372dec25 100644
--- a/drivers/net/wireless/ath/ath10k/mac.c
+++ b/drivers/net/wireless/ath/ath10k/mac.c
@@ -3087,6 +3087,13 @@ static int ath10k_update_channel_list(struct ath10k *ar)
 			passive = channel->flags & IEEE80211_CHAN_NO_IR;
 			ch->passive = passive;
 
+			/* the firmware is ignoring the "radar" flag of the
+			 * channel and is scanning actively using Probe Requests
+			 * on "Radar detection"/DFS channels which are not
+			 * marked as "available"
+			 */
+			ch->passive |= ch->chan_radar;
+
 			ch->freq = channel->center_freq;
 			ch->band_center_freq1 = channel->center_freq;
 			ch->min_power = 0;
-- 
cgit v1.2.3


From bfc55fe65987743e534808a18217ccd5783e00bb Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 27 Jul 2018 16:43:18 +0800
Subject: ath6kl: replace GFP_ATOMIC with GFP_KERNEL in ath6kl_bmi_init()

ath6kl_bmi_init() is never called in atomic context.
It calls kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath6kl/bmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath6kl/bmi.c b/drivers/net/wireless/ath/ath6kl/bmi.c
index 334dbd834b3a..bde5a10d470c 100644
--- a/drivers/net/wireless/ath/ath6kl/bmi.c
+++ b/drivers/net/wireless/ath/ath6kl/bmi.c
@@ -534,7 +534,7 @@ int ath6kl_bmi_init(struct ath6kl *ar)
 	/* cmd + addr + len + data_size */
 	ar->bmi.max_cmd_size = ar->bmi.max_data_size + (sizeof(u32) * 3);
 
-	ar->bmi.cmd_buf = kzalloc(ar->bmi.max_cmd_size, GFP_ATOMIC);
+	ar->bmi.cmd_buf = kzalloc(ar->bmi.max_cmd_size, GFP_KERNEL);
 	if (!ar->bmi.cmd_buf)
 		return -ENOMEM;
 
-- 
cgit v1.2.3


From a2a49e86b325fa2e44b0b7407f07e6eab6cc3edd Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:15 +0300
Subject: ath9k_hw: set spectral scan enable bit on trigger for AR9003+

AR9002 code and the QCA AR9003+ reference code do the same.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ar9003_phy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index fe5102ca5010..98c5f524a360 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -1800,6 +1800,8 @@ static void ar9003_hw_spectral_scan_config(struct ath_hw *ah,
 
 static void ar9003_hw_spectral_scan_trigger(struct ath_hw *ah)
 {
+	REG_SET_BIT(ah, AR_PHY_SPECTRAL_SCAN,
+		    AR_PHY_SPECTRAL_SCAN_ENABLE);
 	/* Activate spectral scan */
 	REG_SET_BIT(ah, AR_PHY_SPECTRAL_SCAN,
 		    AR_PHY_SPECTRAL_SCAN_ACTIVE);
-- 
cgit v1.2.3


From 3a69dd366866b066b329f6074189a1a6eb056b93 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:17 +0300
Subject: ath9k: don't run periodic and nf calibation at the same time

The checks already prevents periodic cal from being started while noise
floor calibration runs. It is missing checks for the other way around.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/ar9002_calib.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ar9002_calib.c b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
index 50fcd343c41a..fd9db8ca99d7 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
@@ -676,10 +676,10 @@ static int ar9002_hw_calibrate(struct ath_hw *ah, struct ath9k_channel *chan,
 			return 0;
 
 		ah->cal_list_curr = currCal = currCal->calNext;
-		if (currCal->calState == CAL_WAITING) {
+		if (currCal->calState == CAL_WAITING)
 			ath9k_hw_reset_calibration(ah, currCal);
-			return 0;
-		}
+
+		return 0;
 	}
 
 	/* Do NF cal only at longer intervals */
-- 
cgit v1.2.3


From 11f7f4f9c0d28a0742b238fdb851eb3698ad6d9a Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:19 +0300
Subject: ath9k: fix moredata bit in PS buffered frame release

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/xmit.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 7fdb152be0bb..cab24b43ac88 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -1659,6 +1659,22 @@ void ath_tx_aggr_wakeup(struct ath_softc *sc, struct ath_node *an)
 	}
 }
 
+
+static void
+ath9k_set_moredata(struct ath_softc *sc, struct ath_buf *bf, bool val)
+{
+	struct ieee80211_hdr *hdr;
+	u16 mask = cpu_to_le16(IEEE80211_FCTL_MOREDATA);
+	u16 mask_val = mask * val;
+
+	hdr = (struct ieee80211_hdr *) bf->bf_mpdu->data;
+	if ((hdr->frame_control & mask) != mask_val) {
+		hdr->frame_control = (hdr->frame_control & ~mask) | mask_val;
+		dma_sync_single_for_device(sc->dev, bf->bf_buf_addr,
+			sizeof(*hdr), DMA_TO_DEVICE);
+	}
+}
+
 void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 				   struct ieee80211_sta *sta,
 				   u16 tids, int nframes,
@@ -1689,6 +1705,7 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 			if (!bf)
 				break;
 
+			ath9k_set_moredata(sc, bf, true);
 			list_add_tail(&bf->list, &bf_q);
 			ath_set_rates(tid->an->vif, tid->an->sta, bf);
 			if (bf_isampdu(bf)) {
@@ -1712,6 +1729,9 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 	if (list_empty(&bf_q))
 		return;
 
+	if (!more_data)
+		ath9k_set_moredata(sc, bf_tail, false);
+
 	info = IEEE80211_SKB_CB(bf_tail->bf_mpdu);
 	info->flags |= IEEE80211_TX_STATUS_EOSP;
 
-- 
cgit v1.2.3


From e20c7c91ef60cb3a3534f73d14007ec0728d1620 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:21 +0300
Subject: ath9k: clear potentially stale EOSP status bit in intermediate queues

Prevents spurious ieee80211_sta_eosp calls.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/xmit.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index cab24b43ac88..56a0d1b7527a 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -969,7 +969,8 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 		bf->bf_lastbf = bf;
 
 		tx_info = IEEE80211_SKB_CB(skb);
-		tx_info->flags &= ~IEEE80211_TX_CTL_CLEAR_PS_FILT;
+		tx_info->flags &= ~(IEEE80211_TX_CTL_CLEAR_PS_FILT |
+				    IEEE80211_TX_STATUS_EOSP);
 
 		/*
 		 * No aggregation session is running, but there may be frames
-- 
cgit v1.2.3


From 36e14a787dd0b459760de3622e9709edb745a6af Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:23 +0300
Subject: ath9k: report tx status on EOSP

Fixes missed indications of end of U-APSD service period to mac80211

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/xmit.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index 56a0d1b7527a..d366170f01cf 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -86,7 +86,8 @@ static void ath_tx_status(struct ieee80211_hw *hw, struct sk_buff *skb)
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_sta *sta = info->status.status_driver_data[0];
 
-	if (info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS) {
+	if (info->flags & (IEEE80211_TX_CTL_REQ_TX_STATUS |
+			   IEEE80211_TX_STATUS_EOSP)) {
 		ieee80211_tx_status(hw, skb);
 		return;
 	}
-- 
cgit v1.2.3


From 1226f9e1029637ebdab6bd80928213b8c1ad965c Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:26 +0300
Subject: ath9k: fix block-ack window tracking issues

Ensure that a buffer gets tracked as part of the block-ack window as
soon as it's dequeued from the tid for the first time. Ensure that
double calls to ath_tx_addto_baw (e.g. on retransmission) don't cause
any issues.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/xmit.c | 29 ++++++++++++++++++-----------
 1 file changed, 18 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index d366170f01cf..bae0f6c045e1 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -62,7 +62,7 @@ static void ath_tx_rc_status(struct ath_softc *sc, struct ath_buf *bf,
 			     struct ath_tx_status *ts, int nframes, int nbad,
 			     int txok);
 static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid,
-			      int seqno);
+			      struct ath_buf *bf);
 static struct ath_buf *ath_tx_setup_buffer(struct ath_softc *sc,
 					   struct ath_txq *txq,
 					   struct ath_atx_tid *tid,
@@ -296,7 +296,7 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
 		}
 
 		if (fi->baw_tracked) {
-			ath_tx_update_baw(sc, tid, bf->bf_state.seqno);
+			ath_tx_update_baw(sc, tid, bf);
 			sendbar = true;
 		}
 
@@ -312,10 +312,15 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid)
 }
 
 static void ath_tx_update_baw(struct ath_softc *sc, struct ath_atx_tid *tid,
-			      int seqno)
+			      struct ath_buf *bf)
 {
+	struct ath_frame_info *fi = get_frame_info(bf->bf_mpdu);
+	u16 seqno = bf->bf_state.seqno;
 	int index, cindex;
 
+	if (!fi->baw_tracked)
+		return;
+
 	index  = ATH_BA_INDEX(tid->seq_start, seqno);
 	cindex = (tid->baw_head + index) & (ATH_TID_MAX_BUFS - 1);
 
@@ -336,6 +341,9 @@ static void ath_tx_addto_baw(struct ath_softc *sc, struct ath_atx_tid *tid,
 	u16 seqno = bf->bf_state.seqno;
 	int index, cindex;
 
+	if (fi->baw_tracked)
+		return;
+
 	index  = ATH_BA_INDEX(tid->seq_start, seqno);
 	cindex = (tid->baw_head + index) & (ATH_TID_MAX_BUFS - 1);
 	__set_bit(cindex, tid->tx_buf);
@@ -612,7 +620,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq,
 			 * complete the acked-ones/xretried ones; update
 			 * block-ack window
 			 */
-			ath_tx_update_baw(sc, tid, seqno);
+			ath_tx_update_baw(sc, tid, bf);
 
 			if (rc_update && (acked_cnt == 1 || txfail_cnt == 1)) {
 				memcpy(tx_info->control.rates, rates, sizeof(rates));
@@ -642,7 +650,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq,
 				 * run out of tx buf.
 				 */
 				if (!tbf) {
-					ath_tx_update_baw(sc, tid, seqno);
+					ath_tx_update_baw(sc, tid, bf);
 
 					ath_tx_complete_buf(sc, bf, txq,
 							    &bf_head, NULL, ts,
@@ -1011,11 +1019,14 @@ ath_tx_get_tid_subframe(struct ath_softc *sc, struct ath_txq *txq,
 
 			INIT_LIST_HEAD(&bf_head);
 			list_add(&bf->list, &bf_head);
-			ath_tx_update_baw(sc, tid, seqno);
+			ath_tx_update_baw(sc, tid, bf);
 			ath_tx_complete_buf(sc, bf, txq, &bf_head, NULL, &ts, 0);
 			continue;
 		}
 
+		if (bf_isampdu(bf))
+			ath_tx_addto_baw(sc, tid, bf);
+
 		return bf;
 	}
 
@@ -1073,8 +1084,6 @@ ath_tx_form_aggr(struct ath_softc *sc, struct ath_txq *txq,
 		bf->bf_next = NULL;
 
 		/* link buffers of this frame to the aggregate */
-		if (!fi->baw_tracked)
-			ath_tx_addto_baw(sc, tid, bf);
 		bf->bf_state.ndelim = ndelim;
 
 		list_add_tail(&bf->list, bf_q);
@@ -1710,10 +1719,8 @@ void ath9k_release_buffered_frames(struct ieee80211_hw *hw,
 			ath9k_set_moredata(sc, bf, true);
 			list_add_tail(&bf->list, &bf_q);
 			ath_set_rates(tid->an->vif, tid->an->sta, bf);
-			if (bf_isampdu(bf)) {
-				ath_tx_addto_baw(sc, tid, bf);
+			if (bf_isampdu(bf))
 				bf->bf_state.bf_type &= ~BUF_AGGR;
-			}
 			if (bf_tail)
 				bf_tail->bf_next = bf;
 
-- 
cgit v1.2.3


From 461d8a6bb9879b0e619752d040292e67aa06f1d2 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:28 +0300
Subject: ath9k_hw: fix channel maximum power level test

The tx power applied by set_txpower is limited by the CTL (conformance
test limit) entries in the EEPROM. These can change based on the user
configured regulatory domain.
Depending on the EEPROM data this can cause the tx power to become too
limited, if the original regdomain CTLs impose lower limits than the CTLs
of the user configured regdomain.

To fix this issue, set the initial channel limits without any CTL
restrictions and only apply the CTL at run time when setting the channel
and the real tx power.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/hw.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 32fb85e076d6..bb319f22761f 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -2942,16 +2942,19 @@ void ath9k_hw_apply_txpower(struct ath_hw *ah, struct ath9k_channel *chan,
 	struct ath_regulatory *reg = ath9k_hw_regulatory(ah);
 	struct ieee80211_channel *channel;
 	int chan_pwr, new_pwr;
+	u16 ctl = NO_CTL;
 
 	if (!chan)
 		return;
 
+	if (!test)
+		ctl = ath9k_regd_get_ctl(reg, chan);
+
 	channel = chan->chan;
 	chan_pwr = min_t(int, channel->max_power * 2, MAX_RATE_POWER);
 	new_pwr = min_t(int, chan_pwr, reg->power_limit);
 
-	ah->eep_ops->set_txpower(ah, chan,
-				 ath9k_regd_get_ctl(reg, chan),
+	ah->eep_ops->set_txpower(ah, chan, ctl,
 				 get_antenna_gain(ah, chan), new_pwr, test);
 }
 
-- 
cgit v1.2.3


From 52d7e0e5339b429171c032fbc03a45a47f6026a3 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 30 Jul 2018 21:31:30 +0300
Subject: ath9k: fix more-data flag for buffered multicast packets

The flag needs to be cleared for the last packet in the list, not the
first one. Fixes some issues with multicast packet loss for powersave
clients connected to an ath9k AP.

Signed-off-by: Felix Fietkau <nbd@nbd.name>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/xmit.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index bae0f6c045e1..43b6c8508e49 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -2436,7 +2436,6 @@ void ath_tx_cabq(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		.txq = sc->beacon.cabq
 	};
 	struct ath_tx_info info = {};
-	struct ieee80211_hdr *hdr;
 	struct ath_buf *bf_tail = NULL;
 	struct ath_buf *bf;
 	LIST_HEAD(bf_q);
@@ -2480,15 +2479,10 @@ void ath_tx_cabq(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (list_empty(&bf_q))
 		return;
 
-	bf = list_first_entry(&bf_q, struct ath_buf, list);
-	hdr = (struct ieee80211_hdr *) bf->bf_mpdu->data;
-
-	if (hdr->frame_control & cpu_to_le16(IEEE80211_FCTL_MOREDATA)) {
-		hdr->frame_control &= ~cpu_to_le16(IEEE80211_FCTL_MOREDATA);
-		dma_sync_single_for_device(sc->dev, bf->bf_buf_addr,
-			sizeof(*hdr), DMA_TO_DEVICE);
-	}
+	bf = list_last_entry(&bf_q, struct ath_buf, list);
+	ath9k_set_moredata(sc, bf, false);
 
+	bf = list_first_entry(&bf_q, struct ath_buf, list);
 	ath_txq_lock(sc, txctl.txq);
 	ath_tx_fill_desc(sc, bf, txctl.txq, 0);
 	ath_tx_txqaddbuf(sc, txctl.txq, &bf_q, false);
-- 
cgit v1.2.3


From 1bd82ee09aeae74c9f68e6f4147132a3e30e721e Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:22 +0300
Subject: wil6210: Rx multicast packets duplicate detection

Store the last received multicast sequence number (SN) part of the TID
info. Drop Rx multicast packets with retry bit set which their SN
is equal to the last received.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c    |  7 ++++---
 drivers/net/wireless/ath/wil6210/rx_reorder.c | 23 ++++++++++++++++-------
 drivers/net/wireless/ath/wil6210/txrx.c       |  3 ++-
 drivers/net/wireless/ath/wil6210/txrx.h       |  5 +++++
 drivers/net/wireless/ath/wil6210/txrx_edma.c  |  3 ++-
 drivers/net/wireless/ath/wil6210/txrx_edma.h  |  6 ++++++
 drivers/net/wireless/ath/wil6210/wil6210.h    |  6 +++++-
 7 files changed, 40 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 58ce044b1130..7d621264ddd0 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1640,6 +1640,7 @@ static void wil_print_rxtid(struct seq_file *s, struct wil_tid_ampdu_rx *r)
 	int i;
 	u16 index = ((r->head_seq_num - r->ssn) & 0xfff) % r->buf_size;
 	unsigned long long drop_dup = r->drop_dup, drop_old = r->drop_old;
+	unsigned long long drop_dup_mcast = r->drop_dup_mcast;
 
 	seq_printf(s, "([%2d]) 0x%03x [", r->buf_size, r->head_seq_num);
 	for (i = 0; i < r->buf_size; i++) {
@@ -1649,9 +1650,9 @@ static void wil_print_rxtid(struct seq_file *s, struct wil_tid_ampdu_rx *r)
 			seq_printf(s, "%c", r->reorder_buf[i] ? '*' : '_');
 	}
 	seq_printf(s,
-		   "] total %llu drop %llu (dup %llu + old %llu) last 0x%03x\n",
-		   r->total, drop_dup + drop_old, drop_dup, drop_old,
-		   r->ssn_last_drop);
+		   "] total %llu drop %llu (dup %llu + old %llu + dup mcast %llu) last 0x%03x\n",
+		   r->total, drop_dup + drop_old + drop_dup_mcast, drop_dup,
+		   drop_old, drop_dup_mcast, r->ssn_last_drop);
 }
 
 static void wil_print_rxtid_crypto(struct seq_file *s, int tid,
diff --git a/drivers/net/wireless/ath/wil6210/rx_reorder.c b/drivers/net/wireless/ath/wil6210/rx_reorder.c
index 22475a1ddb7f..ba4e93f53b4a 100644
--- a/drivers/net/wireless/ath/wil6210/rx_reorder.c
+++ b/drivers/net/wireless/ath/wil6210/rx_reorder.c
@@ -95,7 +95,7 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 {
 	struct wil6210_vif *vif;
 	struct net_device *ndev;
-	int tid, cid, mid, mcast;
+	int tid, cid, mid, mcast, retry;
 	u16 seq;
 	struct wil_sta_info *sta;
 	struct wil_tid_ampdu_rx *r;
@@ -103,7 +103,7 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	int index;
 
 	wil->txrx_ops.get_reorder_params(wil, skb, &tid, &cid, &mid, &seq,
-					 &mcast);
+					 &mcast, &retry);
 	sta = &wil->sta[cid];
 
 	wil_dbg_txrx(wil, "MID %d CID %d TID %d Seq 0x%03x mcast %01x\n",
@@ -117,11 +117,6 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	}
 	ndev = vif_to_ndev(vif);
 
-	if (unlikely(mcast)) {
-		wil_netif_rx_any(skb, ndev);
-		return;
-	}
-
 	spin_lock(&sta->tid_rx_lock);
 
 	r = sta->tid_rx[tid];
@@ -130,6 +125,19 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 		goto out;
 	}
 
+	if (unlikely(mcast)) {
+		if (retry && seq == r->mcast_last_seq) {
+			r->drop_dup_mcast++;
+			wil_dbg_txrx(wil, "Rx drop: dup mcast seq 0x%03x\n",
+				     seq);
+			dev_kfree_skb(skb);
+			goto out;
+		}
+		r->mcast_last_seq = seq;
+		wil_netif_rx_any(skb, ndev);
+		goto out;
+	}
+
 	r->total++;
 	hseq = r->head_seq_num;
 
@@ -262,6 +270,7 @@ struct wil_tid_ampdu_rx *wil_tid_ampdu_rx_alloc(struct wil6210_priv *wil,
 	r->buf_size = size;
 	r->stored_mpdu_num = 0;
 	r->first_time = true;
+	r->mcast_last_seq = U16_MAX;
 	return r;
 }
 
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 2098f3cc1cec..ad40a96821ed 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -2180,7 +2180,7 @@ static inline void wil_tx_fini(struct wil6210_priv *wil) {}
 
 static void wil_get_reorder_params(struct wil6210_priv *wil,
 				   struct sk_buff *skb, int *tid, int *cid,
-				   int *mid, u16 *seq, int *mcast)
+				   int *mid, u16 *seq, int *mcast, int *retry)
 {
 	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
 
@@ -2189,6 +2189,7 @@ static void wil_get_reorder_params(struct wil6210_priv *wil,
 	*mid = wil_rxdesc_mid(d);
 	*seq = wil_rxdesc_seq(d);
 	*mcast = wil_rxdesc_mcast(d);
+	*retry = wil_rxdesc_retry(d);
 }
 
 void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil)
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index f361423628f5..3dfd7f916137 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -500,6 +500,11 @@ static inline int wil_rxdesc_ext_subtype(struct vring_rx_desc *d)
 	return WIL_GET_BITS(d->mac.d0, 28, 31);
 }
 
+static inline int wil_rxdesc_retry(struct vring_rx_desc *d)
+{
+	return WIL_GET_BITS(d->mac.d0, 31, 31);
+}
+
 static inline int wil_rxdesc_key_id(struct vring_rx_desc *d)
 {
 	return WIL_GET_BITS(d->mac.d1, 4, 5);
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 95f38e65d969..194034779b9f 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -503,7 +503,7 @@ out_free:
 static void wil_get_reorder_params_edma(struct wil6210_priv *wil,
 					struct sk_buff *skb, int *tid,
 					int *cid, int *mid, u16 *seq,
-					int *mcast)
+					int *mcast, int *retry)
 {
 	struct wil_rx_status_extended *s = wil_skb_rxstatus(skb);
 
@@ -512,6 +512,7 @@ static void wil_get_reorder_params_edma(struct wil6210_priv *wil,
 	*mid = wil_rx_status_get_mid(s);
 	*seq = le16_to_cpu(wil_rx_status_get_seq(wil, s));
 	*mcast = wil_rx_status_get_mcast(s);
+	*retry = wil_rx_status_get_retry(s);
 }
 
 static void wil_get_netif_rx_params_edma(struct sk_buff *skb, int *cid,
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.h b/drivers/net/wireless/ath/wil6210/txrx_edma.h
index e86fc2dc0ce0..a7fe9292fda3 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.h
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.h
@@ -471,6 +471,12 @@ static inline __le16 wil_rx_status_get_seq(struct wil6210_priv *wil, void *msg)
 	return ((struct wil_rx_status_extended *)msg)->ext.seq_num;
 }
 
+static inline u8 wil_rx_status_get_retry(void *msg)
+{
+	/* retry bit is missing in EDMA HW. return 1 to be on the safe side */
+	return 1;
+}
+
 static inline int wil_rx_status_get_mid(void *msg)
 {
 	if (!(((struct wil_rx_status_compressed *)msg)->d0 &
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index d963c76b679e..9b1467c49ccc 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -572,7 +572,7 @@ struct wil_txrx_ops {
 				 u16 agg_wsize, u16 timeout);
 	void (*get_reorder_params)(struct wil6210_priv *wil,
 				   struct sk_buff *skb, int *tid, int *cid,
-				   int *mid, u16 *seq, int *mcast);
+				   int *mid, u16 *seq, int *mcast, int *retry);
 	void (*get_netif_rx_params)(struct sk_buff *skb,
 				    int *cid, int *security);
 	int (*rx_crypto_check)(struct wil6210_priv *wil, struct sk_buff *skb);
@@ -625,6 +625,8 @@ struct pci_dev;
  * @drop_dup: duplicate frames dropped for this reorder buffer
  * @drop_old: old frames dropped for this reorder buffer
  * @first_time: true when this buffer used 1-st time
+ * @mcast_last_seq: sequence number (SN) of last received multicast packet
+ * @drop_dup_mcast: duplicate multicast frames dropped for this reorder buffer
  */
 struct wil_tid_ampdu_rx {
 	struct sk_buff **reorder_buf;
@@ -638,6 +640,8 @@ struct wil_tid_ampdu_rx {
 	unsigned long long drop_dup;
 	unsigned long long drop_old;
 	bool first_time; /* is it 1-st time this buffer used? */
+	u16 mcast_last_seq; /* multicast dup detection */
+	unsigned long long drop_dup_mcast;
 };
 
 /**
-- 
cgit v1.2.3


From e15af41c05eda216a43b9e7a22c2399e0ad720ff Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:23 +0300
Subject: wil6210: drop Rx packets with L2 error indication from HW

Due to recent change in FW, driver will be notified of corrupted Rx
packets (e.g. MIC error).
Drop such packets before they are delivered to network stack.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c   | 12 ++++----
 drivers/net/wireless/ath/wil6210/txrx.c      | 22 ++++++++++++++
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 16 ++++------
 drivers/net/wireless/ath/wil6210/wil6210.h   | 44 +++++++++++++++-------------
 4 files changed, 55 insertions(+), 39 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 7d621264ddd0..99b1fc5b796f 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1734,13 +1734,11 @@ __acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
 				   p->stats.rx_short_frame,
 				   p->stats.rx_large_frame,
 				   p->stats.rx_replay);
-
-			if (wil->use_enhanced_dma_hw)
-				seq_printf(s,
-					   "mic error  %lu, key error %lu, amsdu error %lu\n",
-					   p->stats.rx_mic_error,
-					   p->stats.rx_key_error,
-					   p->stats.rx_amsdu_error);
+			seq_printf(s,
+				   "mic error %lu, key error %lu, amsdu error %lu\n",
+				   p->stats.rx_mic_error,
+				   p->stats.rx_key_error,
+				   p->stats.rx_amsdu_error);
 
 			seq_puts(s, "Rx/MCS:");
 			for (mcs = 0; mcs < ARRAY_SIZE(p->stats.rx_per_mcs);
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index ad40a96821ed..9ac867445a5b 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -678,6 +678,21 @@ static int wil_rx_crypto_check(struct wil6210_priv *wil, struct sk_buff *skb)
 	return 0;
 }
 
+static int wil_rx_error_check(struct wil6210_priv *wil, struct sk_buff *skb,
+			      struct wil_net_stats *stats)
+{
+	struct vring_rx_desc *d = wil_skb_rxdesc(skb);
+
+	if ((d->dma.status & RX_DMA_STATUS_ERROR) &&
+	    (d->dma.error & RX_DMA_ERROR_MIC)) {
+		stats->rx_mic_error++;
+		wil_dbg_txrx(wil, "MIC error, dropping packet\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 static void wil_get_netif_rx_params(struct sk_buff *skb, int *cid,
 				    int *security)
 {
@@ -736,6 +751,12 @@ void wil_netif_rx_any(struct sk_buff *skb, struct net_device *ndev)
 		goto stats;
 	}
 
+	/* check errors reported by HW and update statistics */
+	if (unlikely(wil->txrx_ops.rx_error_check(wil, skb, stats))) {
+		dev_kfree_skb(skb);
+		return;
+	}
+
 	if (wdev->iftype == NL80211_IFTYPE_AP && !vif->ap_isolate) {
 		if (mcast) {
 			/* send multicast frames both to higher layers in
@@ -2212,6 +2233,7 @@ void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil)
 	wil->txrx_ops.get_netif_rx_params =
 		wil_get_netif_rx_params;
 	wil->txrx_ops.rx_crypto_check = wil_rx_crypto_check;
+	wil->txrx_ops.rx_error_check = wil_rx_error_check;
 	wil->txrx_ops.is_rx_idle = wil_is_rx_idle;
 	wil->txrx_ops.rx_fini = wil_rx_fini;
 }
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 194034779b9f..b5d399f1c1c7 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -795,14 +795,15 @@ static int wil_check_bar(struct wil6210_priv *wil, void *msg, int cid,
 	return -EAGAIN;
 }
 
-static int wil_rx_edma_check_errors(struct wil6210_priv *wil, void *msg,
-				    struct wil_net_stats *stats,
-				    struct sk_buff *skb)
+static int wil_rx_error_check_edma(struct wil6210_priv *wil,
+				   struct sk_buff *skb,
+				   struct wil_net_stats *stats)
 {
 	int error;
 	int l2_rx_status;
 	int l3_rx_status;
 	int l4_rx_status;
+	void *msg = wil_skb_rxstatus(skb);
 
 	error = wil_rx_status_get_error(msg);
 	if (!error) {
@@ -865,7 +866,6 @@ static struct sk_buff *wil_sring_reap_rx_edma(struct wil6210_priv *wil,
 	struct wil_net_stats *stats = NULL;
 	u16 dmalen;
 	int cid;
-	int rc;
 	bool eop, headstolen;
 	int delta;
 	u8 dr_bit;
@@ -937,13 +937,6 @@ again:
 		goto skipping;
 	}
 
-	/* Check and treat errors reported by HW */
-	rc = wil_rx_edma_check_errors(wil, msg, stats, skb);
-	if (rc) {
-		rxdata->skipping = true;
-		goto skipping;
-	}
-
 	if (unlikely(dmalen > sz)) {
 		wil_err(wil, "Rx size too large: %d bytes!\n", dmalen);
 		stats->rx_large_frame++;
@@ -1593,6 +1586,7 @@ void wil_init_txrx_ops_edma(struct wil6210_priv *wil)
 	wil->txrx_ops.get_reorder_params = wil_get_reorder_params_edma;
 	wil->txrx_ops.get_netif_rx_params = wil_get_netif_rx_params_edma;
 	wil->txrx_ops.rx_crypto_check = wil_rx_crypto_check_edma;
+	wil->txrx_ops.rx_error_check = wil_rx_error_check_edma;
 	wil->txrx_ops.is_rx_idle = wil_is_rx_idle_edma;
 	wil->txrx_ops.rx_fini = wil_rx_fini_edma;
 }
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 9b1467c49ccc..002d336cbde5 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -543,6 +543,27 @@ struct wil_status_ring {
 	struct wil_ring_rx_data rx_data;
 };
 
+#define WIL_STA_TID_NUM (16)
+#define WIL_MCS_MAX (12) /* Maximum MCS supported */
+
+struct wil_net_stats {
+	unsigned long	rx_packets;
+	unsigned long	tx_packets;
+	unsigned long	rx_bytes;
+	unsigned long	tx_bytes;
+	unsigned long	tx_errors;
+	unsigned long	rx_dropped;
+	unsigned long	rx_non_data_frame;
+	unsigned long	rx_short_frame;
+	unsigned long	rx_large_frame;
+	unsigned long	rx_replay;
+	unsigned long	rx_mic_error;
+	unsigned long	rx_key_error; /* eDMA specific */
+	unsigned long	rx_amsdu_error; /* eDMA specific */
+	u16 last_mcs_rx;
+	u64 rx_per_mcs[WIL_MCS_MAX + 1];
+};
+
 /**
  * struct tx_rx_ops - different TX/RX ops for legacy and enhanced
  * DMA flow
@@ -576,6 +597,8 @@ struct wil_txrx_ops {
 	void (*get_netif_rx_params)(struct sk_buff *skb,
 				    int *cid, int *security);
 	int (*rx_crypto_check)(struct wil6210_priv *wil, struct sk_buff *skb);
+	int (*rx_error_check)(struct wil6210_priv *wil, struct sk_buff *skb,
+			      struct wil_net_stats *stats);
 	bool (*is_rx_idle)(struct wil6210_priv *wil);
 	irqreturn_t (*irq_rx)(int irq, void *cookie);
 };
@@ -676,27 +699,6 @@ enum wil_sta_status {
 	wil_sta_connected = 2,
 };
 
-#define WIL_STA_TID_NUM (16)
-#define WIL_MCS_MAX (12) /* Maximum MCS supported */
-
-struct wil_net_stats {
-	unsigned long	rx_packets;
-	unsigned long	tx_packets;
-	unsigned long	rx_bytes;
-	unsigned long	tx_bytes;
-	unsigned long	tx_errors;
-	unsigned long	rx_dropped;
-	unsigned long	rx_non_data_frame;
-	unsigned long	rx_short_frame;
-	unsigned long	rx_large_frame;
-	unsigned long	rx_replay;
-	unsigned long	rx_mic_error; /* eDMA specific */
-	unsigned long	rx_key_error; /* eDMA specific */
-	unsigned long	rx_amsdu_error; /* eDMA specific */
-	u16 last_mcs_rx;
-	u64 rx_per_mcs[WIL_MCS_MAX + 1];
-};
-
 /**
  * struct wil_sta_info - data for peer
  *
-- 
cgit v1.2.3


From a24a3d6abb978d4abc25d541e787981e7ef555c8 Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:24 +0300
Subject: wil6210: add TX latency statistics

Collect statistics of TX latency. The latency is measured from the time
the HW gets aware of new SKB to transmit until the HW indicates tx
complete for this SKB.
The statistics are shown via new "tx_latency" debugfs.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c   | 125 +++++++++++++++++++++++++++
 drivers/net/wireless/ath/wil6210/main.c      |   1 +
 drivers/net/wireless/ath/wil6210/txrx.c      |  38 ++++++++
 drivers/net/wireless/ath/wil6210/txrx.h      |   2 +
 drivers/net/wireless/ath/wil6210/txrx_edma.c |   8 ++
 drivers/net/wireless/ath/wil6210/wil6210.h   |  14 +++
 6 files changed, 188 insertions(+)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 99b1fc5b796f..5d1e48d80f0d 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1800,6 +1800,126 @@ static const struct file_operations fops_mids = {
 	.llseek		= seq_lseek,
 };
 
+static int wil_tx_latency_debugfs_show(struct seq_file *s, void *data)
+__acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
+{
+	struct wil6210_priv *wil = s->private;
+	int i, bin;
+
+	for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
+		struct wil_sta_info *p = &wil->sta[i];
+		char *status = "unknown";
+		u8 aid = 0;
+		u8 mid;
+
+		if (!p->tx_latency_bins)
+			continue;
+
+		switch (p->status) {
+		case wil_sta_unused:
+			status = "unused   ";
+			break;
+		case wil_sta_conn_pending:
+			status = "pending  ";
+			break;
+		case wil_sta_connected:
+			status = "connected";
+			aid = p->aid;
+			break;
+		}
+		mid = (p->status != wil_sta_unused) ? p->mid : U8_MAX;
+		seq_printf(s, "[%d] %pM %s MID %d AID %d\n", i, p->addr, status,
+			   mid, aid);
+
+		if (p->status == wil_sta_connected) {
+			u64 num_packets = 0;
+			u64 tx_latency_avg = p->stats.tx_latency_total_us;
+
+			seq_puts(s, "Tx/Latency bin:");
+			for (bin = 0; bin < WIL_NUM_LATENCY_BINS; bin++) {
+				seq_printf(s, " %lld",
+					   p->tx_latency_bins[bin]);
+				num_packets += p->tx_latency_bins[bin];
+			}
+			seq_puts(s, "\n");
+			if (!num_packets)
+				continue;
+			do_div(tx_latency_avg, num_packets);
+			seq_printf(s, "Tx/Latency min/avg/max (us): %d/%lld/%d",
+				   p->stats.tx_latency_min_us,
+				   tx_latency_avg,
+				   p->stats.tx_latency_max_us);
+
+			seq_puts(s, "\n");
+		}
+	}
+
+	return 0;
+}
+
+static int wil_tx_latency_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_tx_latency_debugfs_show,
+			   inode->i_private);
+}
+
+static ssize_t wil_tx_latency_write(struct file *file, const char __user *buf,
+				    size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int val, rc, i;
+	bool enable;
+
+	rc = kstrtoint_from_user(buf, len, 0, &val);
+	if (rc) {
+		wil_err(wil, "Invalid argument\n");
+		return rc;
+	}
+	if (val == 1)
+		/* default resolution */
+		val = 500;
+	if (val && (val < 50 || val > 1000)) {
+		wil_err(wil, "Invalid resolution %d\n", val);
+		return -EINVAL;
+	}
+
+	enable = !!val;
+	if (wil->tx_latency == enable)
+		return len;
+
+	wil_info(wil, "%s TX latency measurements (resolution %dusec)\n",
+		 enable ? "Enabling" : "Disabling", val);
+
+	if (enable) {
+		size_t sz = sizeof(u64) * WIL_NUM_LATENCY_BINS;
+
+		wil->tx_latency_res = val;
+		for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
+			struct wil_sta_info *sta = &wil->sta[i];
+
+			kfree(sta->tx_latency_bins);
+			sta->tx_latency_bins = kzalloc(sz, GFP_KERNEL);
+			if (!sta->tx_latency_bins)
+				return -ENOMEM;
+			sta->stats.tx_latency_min_us = U32_MAX;
+			sta->stats.tx_latency_max_us = 0;
+			sta->stats.tx_latency_total_us = 0;
+		}
+	}
+	wil->tx_latency = enable;
+
+	return len;
+}
+
+static const struct file_operations fops_tx_latency = {
+	.open		= wil_tx_latency_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.write		= wil_tx_latency_write,
+	.llseek		= seq_lseek,
+};
+
 static ssize_t wil_read_file_led_cfg(struct file *file, char __user *user_buf,
 				     size_t count, loff_t *ppos)
 {
@@ -2133,6 +2253,7 @@ static const struct {
 	{"srings",	0444,		&fops_srings},
 	{"status_msg",	0444,		&fops_status_msg},
 	{"rx_buff_mgmt",	0444,	&fops_rx_buff_mgmt},
+	{"tx_latency",	0644,		&fops_tx_latency},
 };
 
 static void wil6210_debugfs_init_files(struct wil6210_priv *wil,
@@ -2249,10 +2370,14 @@ int wil6210_debugfs_init(struct wil6210_priv *wil)
 
 void wil6210_debugfs_remove(struct wil6210_priv *wil)
 {
+	int i;
+
 	debugfs_remove_recursive(wil->debug);
 	wil->debug = NULL;
 
 	kfree(wil->dbg_data.data_arr);
+	for (i = 0; i < ARRAY_SIZE(wil->sta); i++)
+		kfree(wil->sta[i].tx_latency_bins);
 
 	/* free pmc memory without sending command to fw, as it will
 	 * be reset on the way down anyway
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 4de19bd40a58..7e4ccd9ac2bc 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -278,6 +278,7 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	}
 	/* statistics */
 	memset(&sta->stats, 0, sizeof(sta->stats));
+	sta->stats.tx_latency_min_us = U32_MAX;
 }
 
 static bool wil_vif_is_connected(struct wil6210_priv *wil, u8 mid)
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 9ac867445a5b..6707af60a24d 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -1693,6 +1693,11 @@ static int __wil_tx_vring_tso(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	 */
 	wmb();
 
+	if (wil->tx_latency)
+		*(ktime_t *)&skb->cb = ktime_get();
+	else
+		memset(skb->cb, 0, sizeof(ktime_t));
+
 	wil_w(wil, vring->hwtail, vring->swhead);
 	return 0;
 
@@ -1844,6 +1849,11 @@ static int __wil_tx_ring(struct wil6210_priv *wil, struct wil6210_vif *vif,
 	 */
 	wmb();
 
+	if (wil->tx_latency)
+		*(ktime_t *)&skb->cb = ktime_get();
+	else
+		memset(skb->cb, 0, sizeof(ktime_t));
+
 	wil_w(wil, ring->hwtail, ring->swhead);
 
 	return 0;
@@ -2065,6 +2075,31 @@ netdev_tx_t wil_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	return NET_XMIT_DROP;
 }
 
+void wil_tx_latency_calc(struct wil6210_priv *wil, struct sk_buff *skb,
+			 struct wil_sta_info *sta)
+{
+	int skb_time_us;
+	int bin;
+
+	if (!wil->tx_latency)
+		return;
+
+	if (ktime_to_ms(*(ktime_t *)&skb->cb) == 0)
+		return;
+
+	skb_time_us = ktime_us_delta(ktime_get(), *(ktime_t *)&skb->cb);
+	bin = skb_time_us / wil->tx_latency_res;
+	bin = min_t(int, bin, WIL_NUM_LATENCY_BINS - 1);
+
+	wil_dbg_txrx(wil, "skb time %dus => bin %d\n", skb_time_us, bin);
+	sta->tx_latency_bins[bin]++;
+	sta->stats.tx_latency_total_us += skb_time_us;
+	if (skb_time_us < sta->stats.tx_latency_min_us)
+		sta->stats.tx_latency_min_us = skb_time_us;
+	if (skb_time_us > sta->stats.tx_latency_max_us)
+		sta->stats.tx_latency_max_us = skb_time_us;
+}
+
 /**
  * Clean up transmitted skb's from the Tx VRING
  *
@@ -2151,6 +2186,9 @@ int wil_tx_complete(struct wil6210_vif *vif, int ringid)
 					if (stats) {
 						stats->tx_packets++;
 						stats->tx_bytes += skb->len;
+
+						wil_tx_latency_calc(wil, skb,
+							&wil->sta[cid]);
 					}
 				} else {
 					ndev->stats.tx_errors++;
diff --git a/drivers/net/wireless/ath/wil6210/txrx.h b/drivers/net/wireless/ath/wil6210/txrx.h
index 3dfd7f916137..9d83be481839 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.h
+++ b/drivers/net/wireless/ath/wil6210/txrx.h
@@ -620,5 +620,7 @@ void wil_tid_ampdu_rx_free(struct wil6210_priv *wil,
 			   struct wil_tid_ampdu_rx *r);
 void wil_tx_data_init(struct wil_ring_tx_data *txdata);
 void wil_init_txrx_ops_legacy_dma(struct wil6210_priv *wil);
+void wil_tx_latency_calc(struct wil6210_priv *wil, struct sk_buff *skb,
+			 struct wil_sta_info *sta);
 
 #endif /* WIL6210_TXRX_H */
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index b5d399f1c1c7..2ea9767b01d1 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -1217,6 +1217,9 @@ int wil_tx_sring_handler(struct wil6210_priv *wil,
 					if (stats) {
 						stats->tx_packets++;
 						stats->tx_bytes += skb->len;
+
+						wil_tx_latency_calc(wil, skb,
+							&wil->sta[cid]);
 					}
 				} else {
 					ndev->stats.tx_errors++;
@@ -1467,6 +1470,11 @@ static int __wil_tx_ring_tso_edma(struct wil6210_priv *wil,
 	 */
 	wmb();
 
+	if (wil->tx_latency)
+		*(ktime_t *)&skb->cb = ktime_get();
+	else
+		memset(skb->cb, 0, sizeof(ktime_t));
+
 	wil_w(wil, ring->hwtail, ring->swhead);
 
 	return 0;
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 002d336cbde5..1a7a1ad1534f 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -55,6 +55,8 @@ union wil_tx_desc;
 #define WIL_DEFAULT_BUS_REQUEST_KBPS 128000 /* ~1Gbps */
 #define WIL_MAX_BUS_REQUEST_KBPS 800000 /* ~6.1Gbps */
 
+#define WIL_NUM_LATENCY_BINS 200
+
 /* maximum number of virtual interfaces the driver supports
  * (including the main interface)
  */
@@ -552,6 +554,9 @@ struct wil_net_stats {
 	unsigned long	rx_bytes;
 	unsigned long	tx_bytes;
 	unsigned long	tx_errors;
+	u32 tx_latency_min_us;
+	u32 tx_latency_max_us;
+	u64 tx_latency_total_us;
 	unsigned long	rx_dropped;
 	unsigned long	rx_non_data_frame;
 	unsigned long	rx_short_frame;
@@ -712,6 +717,13 @@ struct wil_sta_info {
 	u8 mid;
 	enum wil_sta_status status;
 	struct wil_net_stats stats;
+	/**
+	 * 20 latency bins. 1st bin counts packets with latency
+	 * of 0..tx_latency_res, last bin counts packets with latency
+	 * of 19*tx_latency_res and above.
+	 * tx_latency_res is configured from "tx_latency" debug-fs.
+	 */
+	u64 *tx_latency_bins;
 	/* Rx BACK */
 	struct wil_tid_ampdu_rx *tid_rx[WIL_STA_TID_NUM];
 	spinlock_t tid_rx_lock; /* guarding tid_rx array */
@@ -943,6 +955,8 @@ struct wil6210_priv {
 	u8 wakeup_trigger;
 	struct wil_suspend_stats suspend_stats;
 	struct wil_debugfs_data dbg_data;
+	bool tx_latency; /* collect TX latency measurements */
+	size_t tx_latency_res; /* bin resolution in usec */
 
 	void *platform_handle;
 	struct wil_platform_ops platform_ops;
-- 
cgit v1.2.3


From 6d9eb7ebae3d7e951bc0999235ae7028eb4cae4f Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:25 +0300
Subject: wil6210: fix temperature debugfs

For negative temperatures, "temp" debugfs is showing wrong values.
Use signed types so proper calculations is done for sub zero
temperatures.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 5d1e48d80f0d..4356b3268c69 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1388,7 +1388,7 @@ static const struct file_operations fops_bf = {
 };
 
 /*---------temp------------*/
-static void print_temp(struct seq_file *s, const char *prefix, u32 t)
+static void print_temp(struct seq_file *s, const char *prefix, s32 t)
 {
 	switch (t) {
 	case 0:
@@ -1396,7 +1396,8 @@ static void print_temp(struct seq_file *s, const char *prefix, u32 t)
 		seq_printf(s, "%s N/A\n", prefix);
 	break;
 	default:
-		seq_printf(s, "%s %d.%03d\n", prefix, t / 1000, t % 1000);
+		seq_printf(s, "%s %s%d.%03d\n", prefix, (t < 0 ? "-" : ""),
+			   abs(t / 1000), abs(t % 1000));
 		break;
 	}
 }
@@ -1404,7 +1405,7 @@ static void print_temp(struct seq_file *s, const char *prefix, u32 t)
 static int wil_temp_debugfs_show(struct seq_file *s, void *data)
 {
 	struct wil6210_priv *wil = s->private;
-	u32 t_m, t_r;
+	s32 t_m, t_r;
 	int rc = wmi_get_temperature(wil, &t_m, &t_r);
 
 	if (rc) {
-- 
cgit v1.2.3


From 0b8532102293b1abb70385232e88ea75d098c808 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:26 +0300
Subject: wil6210: fix RX checksum report to network stack

Currently the driver sets CHECKSUM_UNNECESSARY only in case the HW
doesn't report checksum error.
As ip_summed value is not initialized it is not clear what
the driver will report to the network stack in case of HW checksum
error or in case HW doesn't calculate checksum.
Initialize ip_summed to CHECKSUM_NONE to guarantee checksum
calculation by the network stack in the above cases.

Signed-off-by: Gidon Studinski <gidons@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c   | 5 +++--
 drivers/net/wireless/ath/wil6210/txrx.c      | 8 ++++++++
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 8 ++++++++
 drivers/net/wireless/ath/wil6210/wil6210.h   | 1 +
 4 files changed, 20 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index 4356b3268c69..f2eab39376ee 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1736,10 +1736,11 @@ __acquires(&p->tid_rx_lock) __releases(&p->tid_rx_lock)
 				   p->stats.rx_large_frame,
 				   p->stats.rx_replay);
 			seq_printf(s,
-				   "mic error %lu, key error %lu, amsdu error %lu\n",
+				   "mic error %lu, key error %lu, amsdu error %lu, csum error %lu\n",
 				   p->stats.rx_mic_error,
 				   p->stats.rx_key_error,
-				   p->stats.rx_amsdu_error);
+				   p->stats.rx_amsdu_error,
+				   p->stats.rx_csum_err);
 
 			seq_puts(s, "Rx/MCS:");
 			for (mcs = 0; mcs < ARRAY_SIZE(p->stats.rx_per_mcs);
diff --git a/drivers/net/wireless/ath/wil6210/txrx.c b/drivers/net/wireless/ath/wil6210/txrx.c
index 6707af60a24d..6a7943e487fb 100644
--- a/drivers/net/wireless/ath/wil6210/txrx.c
+++ b/drivers/net/wireless/ath/wil6210/txrx.c
@@ -281,6 +281,12 @@ static int wil_vring_alloc_skb(struct wil6210_priv *wil, struct wil_ring *vring,
 	skb_reserve(skb, headroom);
 	skb_put(skb, sz);
 
+	/**
+	 * Make sure that the network stack calculates checksum for packets
+	 * which failed the HW checksum calculation
+	 */
+	skb->ip_summed = CHECKSUM_NONE;
+
 	pa = dma_map_single(dev, skb->data, skb->len, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(dev, pa))) {
 		kfree_skb(skb);
@@ -569,6 +575,8 @@ again:
 		 * mis-calculates TCP checksum - if it should be 0x0,
 		 * it writes 0xffff in violation of RFC 1624
 		 */
+		else
+			stats->rx_csum_err++;
 	}
 
 	if (snaplen) {
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 2ea9767b01d1..9ef2b66f7561 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -182,6 +182,12 @@ static int wil_ring_alloc_skb_edma(struct wil6210_priv *wil,
 
 	skb_put(skb, sz);
 
+	/**
+	 * Make sure that the network stack calculates checksum for packets
+	 * which failed the HW checksum calculation
+	 */
+	skb->ip_summed = CHECKSUM_NONE;
+
 	pa = dma_map_single(dev, skb->data, skb->len, DMA_FROM_DEVICE);
 	if (unlikely(dma_mapping_error(dev, pa))) {
 		kfree_skb(skb);
@@ -847,6 +853,8 @@ static int wil_rx_error_check_edma(struct wil6210_priv *wil,
 	 * mis-calculates TCP checksum - if it should be 0x0,
 	 * it writes 0xffff in violation of RFC 1624
 	 */
+	else
+		stats->rx_csum_err++;
 
 	return 0;
 }
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 1a7a1ad1534f..b06cba528a1b 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -565,6 +565,7 @@ struct wil_net_stats {
 	unsigned long	rx_mic_error;
 	unsigned long	rx_key_error; /* eDMA specific */
 	unsigned long	rx_amsdu_error; /* eDMA specific */
+	unsigned long	rx_csum_err;
 	u16 last_mcs_rx;
 	u64 rx_per_mcs[WIL_MCS_MAX + 1];
 };
-- 
cgit v1.2.3


From 1c0dd5f5f3ad2af511b8e46392028e0f38f06aa1 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:27 +0300
Subject: wil6210: support Talyn specific FW file

FW file name for Talyn device is different from the default name.
This patch searches for Talyn specific FW file name and fallback
to the default FW file in case it is not present.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/pcie_bus.c | 8 ++++++++
 drivers/net/wireless/ath/wil6210/wil6210.h  | 3 +++
 2 files changed, 11 insertions(+)

diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 8b148cb91372..7192d9a91278 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -93,6 +93,10 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		if (wil_r(wil, RGF_USER_OTP_HW_RD_MACHINE_1) &
 		    BIT_NO_FLASH_INDICATION)
 			set_bit(hw_capa_no_flash, wil->hw_capa);
+		wil_fw_name = ftm_mode ? WIL_FW_NAME_FTM_TALYN :
+			      WIL_FW_NAME_TALYN;
+		if (wil_fw_verify_file_exists(wil, wil_fw_name))
+			wil->wil_fw_name = wil_fw_name;
 		break;
 	case JTAG_DEV_ID_TALYN_MB:
 		wil->hw_name = "Talyn-MB";
@@ -104,6 +108,10 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 		set_bit(hw_capa_no_flash, wil->hw_capa);
 		wil->use_enhanced_dma_hw = true;
 		wil->use_rx_hw_reordering = true;
+		wil_fw_name = ftm_mode ? WIL_FW_NAME_FTM_TALYN :
+			      WIL_FW_NAME_TALYN;
+		if (wil_fw_verify_file_exists(wil, wil_fw_name))
+			wil->wil_fw_name = wil_fw_name;
 		break;
 	default:
 		wil_err(wil, "Unknown board hardware, chip_id 0x%08x, chip_revision 0x%08x\n",
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index b06cba528a1b..00719a018a4a 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -50,6 +50,9 @@ union wil_tx_desc;
 #define WIL_FW_NAME_SPARROW_PLUS "wil6210_sparrow_plus.fw"
 #define WIL_FW_NAME_FTM_SPARROW_PLUS "wil6210_sparrow_plus_ftm.fw"
 
+#define WIL_FW_NAME_TALYN "wil6436.fw"
+#define WIL_FW_NAME_FTM_TALYN "wil6436_ftm.fw"
+
 #define WIL_BOARD_FILE_NAME "wil6210.brd" /* board & radio parameters */
 
 #define WIL_DEFAULT_BUS_REQUEST_KBPS 128000 /* ~1Gbps */
-- 
cgit v1.2.3


From b5aeff16b20f65e6bb9ebafd06c1c96c2b503089 Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:28 +0300
Subject: wil6210: align to latest auto generated wmi.h

Align to latest version of the auto generated wmi file
describing the interface with FW.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/wmi.h | 459 +++++++++++++++++++++++++++++++--
 1 file changed, 434 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index abf6f05c4801..13f6f6210117 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -53,6 +53,17 @@
  * must always be kept equal to (WMI_RF_RX2TX_LENGTH+1)
  */
 #define WMI_RF_RX2TX_CONF_LENGTH	(4)
+/* Qos configuration */
+#define WMI_QOS_NUM_OF_PRIORITY		(4)
+#define WMI_QOS_MIN_DEFAULT_WEIGHT	(10)
+#define WMI_QOS_VRING_SLOT_MIN_MS	(2)
+#define WMI_QOS_VRING_SLOT_MAX_MS	(10)
+/* (WMI_QOS_MIN_DEFAULT_WEIGHT * WMI_QOS_VRING_SLOT_MAX_MS /
+ * WMI_QOS_VRING_SLOT_MIN_MS)
+ */
+#define WMI_QOS_MAX_WEIGHT		50
+#define WMI_QOS_SET_VIF_PRIORITY	(0xFF)
+#define WMI_QOS_DEFAULT_PRIORITY	(WMI_QOS_NUM_OF_PRIORITY)
 
 /* Mailbox interface
  * used for commands and events
@@ -86,6 +97,8 @@ enum wmi_fw_capability {
 	WMI_FW_CAPABILITY_PNO				= 15,
 	WMI_FW_CAPABILITY_REF_CLOCK_CONTROL		= 18,
 	WMI_FW_CAPABILITY_AP_SME_OFFLOAD_NONE		= 19,
+	WMI_FW_CAPABILITY_MULTI_VIFS			= 20,
+	WMI_FW_CAPABILITY_FT_ROAMING			= 21,
 	WMI_FW_CAPABILITY_AMSDU				= 23,
 	WMI_FW_CAPABILITY_MAX,
 };
@@ -110,6 +123,9 @@ enum wmi_command_id {
 	WMI_SET_PROBED_SSID_CMDID			= 0x0A,
 	/* deprecated */
 	WMI_SET_LISTEN_INT_CMDID			= 0x0B,
+	WMI_FT_AUTH_CMDID				= 0x0C,
+	WMI_FT_REASSOC_CMDID				= 0x0D,
+	WMI_UPDATE_FT_IES_CMDID				= 0x0E,
 	WMI_BCON_CTRL_CMDID				= 0x0F,
 	WMI_ADD_CIPHER_KEY_CMDID			= 0x16,
 	WMI_DELETE_CIPHER_KEY_CMDID			= 0x17,
@@ -207,7 +223,12 @@ enum wmi_command_id {
 	WMI_GET_PCP_FACTOR_CMDID			= 0x91B,
 	/* Power Save Configuration Commands */
 	WMI_PS_DEV_PROFILE_CFG_CMDID			= 0x91C,
+	WMI_RS_ENABLE_CMDID				= 0x91E,
+	WMI_RS_CFG_EX_CMDID				= 0x91F,
+	WMI_GET_DETAILED_RS_RES_EX_CMDID		= 0x920,
+	/* deprecated */
 	WMI_RS_CFG_CMDID				= 0x921,
+	/* deprecated */
 	WMI_GET_DETAILED_RS_RES_CMDID			= 0x922,
 	WMI_AOA_MEAS_CMDID				= 0x923,
 	WMI_BRP_SET_ANT_LIMIT_CMDID			= 0x924,
@@ -236,7 +257,9 @@ enum wmi_command_id {
 	WMI_PRIO_TX_SECTORS_ORDER_CMDID			= 0x9A5,
 	WMI_PRIO_TX_SECTORS_NUMBER_CMDID		= 0x9A6,
 	WMI_PRIO_TX_SECTORS_SET_DEFAULT_CFG_CMDID	= 0x9A7,
+	/* deprecated */
 	WMI_BF_CONTROL_CMDID				= 0x9AA,
+	WMI_BF_CONTROL_EX_CMDID				= 0x9AB,
 	WMI_TX_STATUS_RING_ADD_CMDID			= 0x9C0,
 	WMI_RX_STATUS_RING_ADD_CMDID			= 0x9C1,
 	WMI_TX_DESC_RING_ADD_CMDID			= 0x9C2,
@@ -252,6 +275,11 @@ enum wmi_command_id {
 	WMI_GET_CCA_INDICATIONS_CMDID			= 0xA07,
 	WMI_SET_CCA_INDICATIONS_BI_AVG_NUM_CMDID	= 0xA08,
 	WMI_INTERNAL_FW_IOCTL_CMDID			= 0xA0B,
+	WMI_LINK_STATS_CMDID				= 0xA0C,
+	WMI_SET_GRANT_MCS_CMDID				= 0xA0E,
+	WMI_SET_AP_SLOT_SIZE_CMDID			= 0xA0F,
+	WMI_SET_VRING_PRIORITY_WEIGHT_CMDID		= 0xA10,
+	WMI_SET_VRING_PRIORITY_CMDID			= 0xA11,
 	WMI_SET_MAC_ADDRESS_CMDID			= 0xF003,
 	WMI_ABORT_SCAN_CMDID				= 0xF007,
 	WMI_SET_PROMISCUOUS_MODE_CMDID			= 0xF041,
@@ -450,6 +478,30 @@ struct wmi_start_sched_scan_cmd {
 	struct wmi_sched_scan_plan scan_plans[WMI_MAX_PLANS_NUM];
 } __packed;
 
+/* WMI_FT_AUTH_CMDID */
+struct wmi_ft_auth_cmd {
+	u8 bssid[WMI_MAC_LEN];
+	/* enum wmi_channel */
+	u8 channel;
+	/* enum wmi_channel */
+	u8 edmg_channel;
+	u8 reserved[4];
+} __packed;
+
+/* WMI_FT_REASSOC_CMDID */
+struct wmi_ft_reassoc_cmd {
+	u8 bssid[WMI_MAC_LEN];
+	u8 reserved[2];
+} __packed;
+
+/* WMI_UPDATE_FT_IES_CMDID */
+struct wmi_update_ft_ies_cmd {
+	/* Length of the FT IEs */
+	__le16 ie_len;
+	u8 reserved[2];
+	u8 ie_info[0];
+} __packed;
+
 /* WMI_SET_PROBED_SSID_CMDID */
 #define MAX_PROBED_SSID_INDEX	(3)
 
@@ -744,7 +796,11 @@ struct wmi_vring_cfg {
 	u8 cid;
 	/* Used when cidxtid = CIDXTID_EXTENDED_CID_TID */
 	u8 tid;
-	u8 reserved[2];
+	/* Update the vring's priority for Qos purpose. Set to
+	 * WMI_QOS_DEFAULT_PRIORITY to use MID's QoS priority
+	 */
+	u8 qos_priority;
+	u8 reserved;
 } __packed;
 
 enum wmi_vring_cfg_cmd_action {
@@ -775,20 +831,6 @@ struct wmi_bcast_vring_cfg_cmd {
 	struct wmi_bcast_vring_cfg vring_cfg;
 } __packed;
 
-/* WMI_LO_POWER_CALIB_FROM_OTP_CMDID */
-struct wmi_lo_power_calib_from_otp_cmd {
-	/* index to read from OTP. zero based */
-	u8 index;
-	u8 reserved[3];
-} __packed;
-
-/* WMI_LO_POWER_CALIB_FROM_OTP_EVENTID */
-struct wmi_lo_power_calib_from_otp_event {
-	/* wmi_fw_status */
-	u8 status;
-	u8 reserved[3];
-} __packed;
-
 struct wmi_edma_ring_cfg {
 	__le64 ring_mem_base;
 	/* size in number of items */
@@ -861,6 +903,20 @@ struct wmi_bcast_desc_ring_add_cmd {
 	u8 reserved[4];
 } __packed;
 
+/* WMI_LO_POWER_CALIB_FROM_OTP_CMDID */
+struct wmi_lo_power_calib_from_otp_cmd {
+	/* index to read from OTP. zero based */
+	u8 index;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_LO_POWER_CALIB_FROM_OTP_EVENTID */
+struct wmi_lo_power_calib_from_otp_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 /* WMI_RING_BA_EN_CMDID */
 struct wmi_ring_ba_en_cmd {
 	u8 ring_id;
@@ -1419,6 +1475,10 @@ struct wmi_fixed_scheduling_config_complete_event {
 	u8 reserved[3];
 } __packed;
 
+/* This value exists for backwards compatibility only.
+ * Do not use it in new commands.
+ * Use dynamic arrays where possible.
+ */
 #define WMI_NUM_MCS	(13)
 
 /* WMI_FIXED_SCHEDULING_CONFIG_CMDID */
@@ -1478,12 +1538,12 @@ struct wmi_set_long_range_config_complete_event {
 	u8 reserved[3];
 } __packed;
 
-/* payload max size is 236 bytes: max event buffer size (256) - WMI headers
+/* payload max size is 1024 bytes: max event buffer size (1044) - WMI headers
  * (16) - prev struct field size (4)
  */
-#define WMI_MAX_IOCTL_PAYLOAD_SIZE		(236)
-#define WMI_MAX_IOCTL_REPLY_PAYLOAD_SIZE	(236)
-#define WMI_MAX_INTERNAL_EVENT_PAYLOAD_SIZE	(236)
+#define WMI_MAX_IOCTL_PAYLOAD_SIZE		(1024)
+#define WMI_MAX_IOCTL_REPLY_PAYLOAD_SIZE	(1024)
+#define WMI_MAX_INTERNAL_EVENT_PAYLOAD_SIZE	(1024)
 
 enum wmi_internal_fw_ioctl_code {
 	WMI_INTERNAL_FW_CODE_NONE	= 0x0,
@@ -1523,7 +1583,37 @@ struct wmi_internal_fw_event_event {
 	__le32 payload[0];
 } __packed;
 
-/* WMI_BF_CONTROL_CMDID */
+/* WMI_SET_VRING_PRIORITY_WEIGHT_CMDID */
+struct wmi_set_vring_priority_weight_cmd {
+	/* Array of weights. Valid values are
+	 * WMI_QOS_MIN_DEFAULT_WEIGHT...WMI_QOS_MAX_WEIGHT. Weight #0 is
+	 * hard-coded WMI_QOS_MIN_WEIGHT. This array provide the weights
+	 * #1..#3
+	 */
+	u8 weight[3];
+	u8 reserved;
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_CMDID */
+struct wmi_vring_priority {
+	u8 vring_idx;
+	/* Weight index. Valid value is 0-3 */
+	u8 priority;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_CMDID */
+struct wmi_set_vring_priority_cmd {
+	/* number of entries in vring_priority. Set to
+	 * WMI_QOS_SET_VIF_PRIORITY to update the VIF's priority, and there
+	 * will be only one entry in vring_priority
+	 */
+	u8 num_of_vrings;
+	u8 reserved[3];
+	struct wmi_vring_priority vring_priority[0];
+} __packed;
+
+/* WMI_BF_CONTROL_CMDID - deprecated */
 struct wmi_bf_control_cmd {
 	/* wmi_bf_triggers */
 	__le32 triggers;
@@ -1565,6 +1655,97 @@ struct wmi_bf_control_cmd {
 	u8 reserved2[2];
 } __packed;
 
+/* BF configuration for each MCS */
+struct wmi_bf_control_ex_mcs {
+	/* Long term throughput threshold [Mbps] */
+	u8 long_term_mbps_th_tbl;
+	u8 reserved;
+	/* Long term timeout threshold table [msec] */
+	__le16 long_term_trig_timeout_per_mcs;
+} __packed;
+
+/* WMI_BF_CONTROL_EX_CMDID */
+struct wmi_bf_control_ex_cmd {
+	/* wmi_bf_triggers */
+	__le32 triggers;
+	/* enum wmi_edmg_tx_mode */
+	u8 tx_mode;
+	/* DISABLED = 0, ENABLED = 1 , DRY_RUN = 2 */
+	u8 txss_mode;
+	/* DISABLED = 0, ENABLED = 1, DRY_RUN = 2 */
+	u8 brp_mode;
+	/* Max cts threshold (correspond to
+	 * WMI_BF_TRIGGER_MAX_CTS_FAILURE_IN_TXOP)
+	 */
+	u8 bf_trigger_max_cts_failure_thr;
+	/* Max cts threshold in dense (correspond to
+	 * WMI_BF_TRIGGER_MAX_CTS_FAILURE_IN_TXOP)
+	 */
+	u8 bf_trigger_max_cts_failure_dense_thr;
+	/* Max b-ack threshold (correspond to
+	 * WMI_BF_TRIGGER_MAX_BACK_FAILURE)
+	 */
+	u8 bf_trigger_max_back_failure_thr;
+	/* Max b-ack threshold in dense (correspond to
+	 * WMI_BF_TRIGGER_MAX_BACK_FAILURE)
+	 */
+	u8 bf_trigger_max_back_failure_dense_thr;
+	u8 reserved0;
+	/* Wrong sectors threshold */
+	__le32 wrong_sector_bis_thr;
+	/* BOOL to enable/disable long term trigger */
+	u8 long_term_enable;
+	/* 1 = Update long term thresholds from the long_term_mbps_th_tbl and
+	 * long_term_trig_timeout_per_mcs arrays, 0 = Ignore
+	 */
+	u8 long_term_update_thr;
+	u8 each_mcs_cfg_size;
+	u8 reserved1;
+	/* Configuration for each MCS */
+	struct wmi_bf_control_ex_mcs each_mcs_cfg[0];
+} __packed;
+
+/* WMI_LINK_STATS_CMD */
+enum wmi_link_stats_action {
+	WMI_LINK_STATS_SNAPSHOT		= 0x00,
+	WMI_LINK_STATS_PERIODIC		= 0x01,
+	WMI_LINK_STATS_STOP_PERIODIC	= 0x02,
+};
+
+/* WMI_LINK_STATS_EVENT record identifiers */
+enum wmi_link_stats_record_type {
+	WMI_LINK_STATS_TYPE_BASIC	= 0x01,
+	WMI_LINK_STATS_TYPE_MAC		= 0x02,
+	WMI_LINK_STATS_TYPE_PHY		= 0x04,
+	WMI_LINK_STATS_TYPE_OTA		= 0x08,
+};
+
+/* WMI_LINK_STATS_CMDID */
+struct wmi_link_stats_cmd {
+	/* bitmask of required record types
+	 * (wmi_link_stats_record_type_e)
+	 */
+	__le32 record_type_mask;
+	/* 0xff for all cids */
+	u8 cid;
+	/* wmi_link_stats_action_e */
+	u8 action;
+	u8 reserved[6];
+	/* for WMI_LINK_STATS_PERIODIC */
+	__le32 interval_msec;
+} __packed;
+
+/* WMI_SET_GRANT_MCS_CMDID */
+struct wmi_set_grant_mcs_cmd {
+	u8 mcs;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_AP_SLOT_SIZE_CMDID */
+struct wmi_set_ap_slot_size_cmd {
+	__le32 slot_size;
+} __packed;
+
 /* WMI Events
  * List of Events (target to host)
  */
@@ -1577,6 +1758,8 @@ enum wmi_event_id {
 	WMI_SCHED_SCAN_RESULT_EVENTID			= 0x1007,
 	WMI_SCAN_COMPLETE_EVENTID			= 0x100A,
 	WMI_REPORT_STATISTICS_EVENTID			= 0x100B,
+	WMI_FT_AUTH_STATUS_EVENTID			= 0x100C,
+	WMI_FT_REASSOC_STATUS_EVENTID			= 0x100D,
 	WMI_RD_MEM_RSP_EVENTID				= 0x1800,
 	WMI_FW_READY_EVENTID				= 0x1801,
 	WMI_EXIT_FAST_MEM_ACC_MODE_EVENTID		= 0x200,
@@ -1653,7 +1836,12 @@ enum wmi_event_id {
 	WMI_PCP_FACTOR_EVENTID				= 0x191A,
 	/* Power Save Configuration Events */
 	WMI_PS_DEV_PROFILE_CFG_EVENTID			= 0x191C,
+	WMI_RS_ENABLE_EVENTID				= 0x191E,
+	WMI_RS_CFG_EX_EVENTID				= 0x191F,
+	WMI_GET_DETAILED_RS_RES_EX_EVENTID		= 0x1920,
+	/* deprecated */
 	WMI_RS_CFG_DONE_EVENTID				= 0x1921,
+	/* deprecated */
 	WMI_GET_DETAILED_RS_RES_EVENTID			= 0x1922,
 	WMI_AOA_MEAS_EVENTID				= 0x1923,
 	WMI_BRP_SET_ANT_LIMIT_EVENTID			= 0x1924,
@@ -1681,7 +1869,9 @@ enum wmi_event_id {
 	WMI_PRIO_TX_SECTORS_ORDER_EVENTID		= 0x19A5,
 	WMI_PRIO_TX_SECTORS_NUMBER_EVENTID		= 0x19A6,
 	WMI_PRIO_TX_SECTORS_SET_DEFAULT_CFG_EVENTID	= 0x19A7,
+	/* deprecated */
 	WMI_BF_CONTROL_EVENTID				= 0x19AA,
+	WMI_BF_CONTROL_EX_EVENTID			= 0x19AB,
 	WMI_TX_STATUS_RING_CFG_DONE_EVENTID		= 0x19C0,
 	WMI_RX_STATUS_RING_CFG_DONE_EVENTID		= 0x19C1,
 	WMI_TX_DESC_RING_CFG_DONE_EVENTID		= 0x19C2,
@@ -1697,6 +1887,12 @@ enum wmi_event_id {
 	WMI_SET_CCA_INDICATIONS_BI_AVG_NUM_EVENTID	= 0x1A08,
 	WMI_INTERNAL_FW_EVENT_EVENTID			= 0x1A0A,
 	WMI_INTERNAL_FW_IOCTL_EVENTID			= 0x1A0B,
+	WMI_LINK_STATS_CONFIG_DONE_EVENTID		= 0x1A0C,
+	WMI_LINK_STATS_EVENTID				= 0x1A0D,
+	WMI_SET_GRANT_MCS_EVENTID			= 0x1A0E,
+	WMI_SET_AP_SLOT_SIZE_EVENTID			= 0x1A0F,
+	WMI_SET_VRING_PRIORITY_WEIGHT_EVENTID		= 0x1A10,
+	WMI_SET_VRING_PRIORITY_EVENTID			= 0x1A11,
 	WMI_SET_CHANNEL_EVENTID				= 0x9000,
 	WMI_ASSOC_REQ_EVENTID				= 0x9001,
 	WMI_EAPOL_RX_EVENTID				= 0x9002,
@@ -1961,6 +2157,33 @@ struct wmi_scan_complete_event {
 	__le32 status;
 } __packed;
 
+/* WMI_FT_AUTH_STATUS_EVENTID */
+struct wmi_ft_auth_status_event {
+	/* enum wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+	u8 mac_addr[WMI_MAC_LEN];
+	__le16 ie_len;
+	u8 ie_info[0];
+} __packed;
+
+/* WMI_FT_REASSOC_STATUS_EVENTID */
+struct wmi_ft_reassoc_status_event {
+	/* enum wmi_fw_status */
+	u8 status;
+	/* association id received from new AP */
+	u8 aid;
+	/* enum wmi_channel */
+	u8 channel;
+	/* enum wmi_channel */
+	u8 edmg_channel;
+	u8 mac_addr[WMI_MAC_LEN];
+	__le16 beacon_ie_len;
+	__le16 reassoc_req_ie_len;
+	__le16 reassoc_resp_ie_len;
+	u8 ie_info[0];
+} __packed;
+
 /* wmi_rx_mgmt_info */
 struct wmi_rx_mgmt_info {
 	u8 mcs;
@@ -2455,6 +2678,81 @@ struct wmi_rs_cfg {
 	__le32 mcs_en_vec;
 } __packed;
 
+enum wmi_edmg_tx_mode {
+	WMI_TX_MODE_DMG			= 0x0,
+	WMI_TX_MODE_EDMG_CB1		= 0x1,
+	WMI_TX_MODE_EDMG_CB2		= 0x2,
+	WMI_TX_MODE_EDMG_CB1_LONG_LDPC	= 0x3,
+	WMI_TX_MODE_EDMG_CB2_LONG_LDPC	= 0x4,
+	WMI_TX_MODE_MAX,
+};
+
+/* Rate search parameters common configuration */
+struct wmi_rs_cfg_ex_common {
+	/* enum wmi_edmg_tx_mode */
+	u8 mode;
+	/* stop threshold [0-100] */
+	u8 stop_th;
+	/* MCS1 stop threshold [0-100] */
+	u8 mcs1_fail_th;
+	u8 max_back_failure_th;
+	/* Debug feature for disabling internal RS trigger (which is
+	 * currently triggered by BF Done)
+	 */
+	u8 dbg_disable_internal_trigger;
+	u8 reserved[3];
+	__le32 back_failure_mask;
+} __packed;
+
+/* Rate search parameters configuration per MCS */
+struct wmi_rs_cfg_ex_mcs {
+	/* The maximal allowed PER for each MCS
+	 * MCS will be considered as failed if PER during RS is higher
+	 */
+	u8 per_threshold;
+	/* Number of MPDUs for each MCS
+	 * this is the minimal statistic required to make an educated
+	 * decision
+	 */
+	u8 min_frame_cnt;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_RS_CFG_EX_CMDID */
+struct wmi_rs_cfg_ex_cmd {
+	/* Configuration for all MCSs */
+	struct wmi_rs_cfg_ex_common common_cfg;
+	u8 each_mcs_cfg_size;
+	u8 reserved[3];
+	/* Configuration for each MCS */
+	struct wmi_rs_cfg_ex_mcs each_mcs_cfg[0];
+} __packed;
+
+/* WMI_RS_CFG_EX_EVENTID */
+struct wmi_rs_cfg_ex_event {
+	/* enum wmi_edmg_tx_mode */
+	u8 mode;
+	/* enum wmi_fw_status */
+	u8 status;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_RS_ENABLE_CMDID */
+struct wmi_rs_enable_cmd {
+	u8 cid;
+	/* enable or disable rate search */
+	u8 rs_enable;
+	u8 reserved[2];
+	__le32 mcs_en_vec;
+} __packed;
+
+/* WMI_RS_ENABLE_EVENTID */
+struct wmi_rs_enable_event {
+	/* enum wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 /* Slot types */
 enum wmi_sched_scheme_slot_type {
 	WMI_SCHED_SLOT_SP		= 0x0,
@@ -2547,7 +2845,7 @@ struct wmi_scheduling_scheme_event {
 	u8 reserved[1];
 } __packed;
 
-/* WMI_RS_CFG_CMDID */
+/* WMI_RS_CFG_CMDID - deprecated */
 struct wmi_rs_cfg_cmd {
 	/* connection id */
 	u8 cid;
@@ -2557,7 +2855,7 @@ struct wmi_rs_cfg_cmd {
 	struct wmi_rs_cfg rs_cfg;
 } __packed;
 
-/* WMI_RS_CFG_DONE_EVENTID */
+/* WMI_RS_CFG_DONE_EVENTID - deprecated */
 struct wmi_rs_cfg_done_event {
 	u8 cid;
 	/* enum wmi_fw_status */
@@ -2565,7 +2863,7 @@ struct wmi_rs_cfg_done_event {
 	u8 reserved[2];
 } __packed;
 
-/* WMI_GET_DETAILED_RS_RES_CMDID */
+/* WMI_GET_DETAILED_RS_RES_CMDID - deprecated */
 struct wmi_get_detailed_rs_res_cmd {
 	/* connection id */
 	u8 cid;
@@ -2590,7 +2888,7 @@ struct wmi_rs_results {
 	u8 mcs;
 } __packed;
 
-/* WMI_GET_DETAILED_RS_RES_EVENTID */
+/* WMI_GET_DETAILED_RS_RES_EVENTID - deprecated */
 struct wmi_get_detailed_rs_res_event {
 	u8 cid;
 	/* enum wmi_rs_results_status */
@@ -2600,6 +2898,45 @@ struct wmi_get_detailed_rs_res_event {
 	u8 reserved[3];
 } __packed;
 
+/* WMI_GET_DETAILED_RS_RES_EX_CMDID */
+struct wmi_get_detailed_rs_res_ex_cmd {
+	u8 cid;
+	u8 reserved[3];
+} __packed;
+
+/* Rate search results */
+struct wmi_rs_results_ex_common {
+	/* RS timestamp */
+	__le32 tsf;
+	/* RS selected MCS */
+	u8 mcs;
+	/* enum wmi_edmg_tx_mode */
+	u8 mode;
+	u8 reserved[2];
+} __packed;
+
+/* Rate search results */
+struct wmi_rs_results_ex_mcs {
+	/* number of sent MPDUs */
+	u8 num_of_tx_pkt;
+	/* number of non-acked MPDUs */
+	u8 num_of_non_acked_pkt;
+	u8 reserved[2];
+} __packed;
+
+/* WMI_GET_DETAILED_RS_RES_EX_EVENTID */
+struct wmi_get_detailed_rs_res_ex_event {
+	u8 cid;
+	/* enum wmi_rs_results_status */
+	u8 status;
+	u8 reserved0[2];
+	struct wmi_rs_results_ex_common common_rs_results;
+	u8 each_mcs_results_size;
+	u8 reserved1[3];
+	/* Results for each MCS */
+	struct wmi_rs_results_ex_mcs each_mcs_results[0];
+} __packed;
+
 /* BRP antenna limit mode */
 enum wmi_brp_ant_limit_mode {
 	/* Disable BRP force antenna limit */
@@ -3350,13 +3687,20 @@ struct wmi_get_assoc_list_res_event {
 	u8 reserved[3];
 } __packed;
 
-/* WMI_BF_CONTROL_EVENTID */
+/* WMI_BF_CONTROL_EVENTID - deprecated */
 struct wmi_bf_control_event {
 	/* wmi_fw_status */
 	u8 status;
 	u8 reserved[3];
 } __packed;
 
+/* WMI_BF_CONTROL_EX_EVENTID */
+struct wmi_bf_control_ex_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 /* WMI_COMMAND_NOT_SUPPORTED_EVENTID */
 struct wmi_command_not_supported_event {
 	/* device id */
@@ -3426,4 +3770,69 @@ struct wmi_internal_fw_set_channel_event {
 	u8 reserved[3];
 } __packed;
 
+/* WMI_LINK_STATS_CONFIG_DONE_EVENTID */
+struct wmi_link_stats_config_done_event {
+	/* wmi_fw_status_e */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_LINK_STATS_EVENTID */
+struct wmi_link_stats_event {
+	__le16 payload_size;
+	u8 has_next;
+	u8 reserved[5];
+	/* a stream of records, e.g. wmi_link_stats_basic_s */
+	u8 payload[0];
+} __packed;
+
+/* WMI_LINK_STATS_EVENT record struct */
+struct wmi_link_stats_basic {
+	/* WMI_LINK_STATS_TYPE_BASIC */
+	u8 record_type_id;
+	u8 cid;
+	/* 0: fail; 1: OK; 2: retrying */
+	u8 bf_status;
+	s8 rssi;
+	u8 sqi;
+	u8 selected_rfc;
+	__le16 bf_mcs;
+	__le32 tx_tpt;
+	__le32 tx_goodput;
+	__le32 rx_goodput;
+	__le16 my_rx_sector;
+	__le16 my_tx_sector;
+	__le16 other_rx_sector;
+	__le16 other_tx_sector;
+	__le32 reserved[2];
+} __packed;
+
+/* WMI_SET_GRANT_MCS_EVENTID */
+struct wmi_set_grant_mcs_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_AP_SLOT_SIZE_EVENTID */
+struct wmi_set_ap_slot_size_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_WEIGHT_EVENTID */
+struct wmi_set_vring_priority_weight_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_SET_VRING_PRIORITY_EVENTID */
+struct wmi_set_vring_priority_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 #endif /* __WILOCITY_WMI_H__ */
-- 
cgit v1.2.3


From aea2f8b781b2a76fb0af4de2273d0c56c6d256a4 Mon Sep 17 00:00:00 2001
From: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:29 +0300
Subject: wil6210: add 3-MSI support

Extend MSI support to 3-MSI in order to load balance the tx\rx
interrupts between different cores.
use_msi module parameter has changed to n_msi. Usage:
- Set n_msi to 0 for using INTx
- Set n_msi to 1 for using single MSI
- Set n_msi to 3 for using 3-MSI

In 3-MSI configuration MSI 0 is used for TX interrupts, MSI 1
is used for RX interrupts and MSI 2 is used for MISC interrupts.

Signed-off-by: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/interrupt.c    | 64 ++++++++++++++++++++++---
 drivers/net/wireless/ath/wil6210/main.c         |  3 ++
 drivers/net/wireless/ath/wil6210/pcie_bus.c     | 60 +++++++++++++++++------
 drivers/net/wireless/ath/wil6210/wil6210.h      |  3 +-
 drivers/net/wireless/ath/wil6210/wil_platform.h |  1 +
 5 files changed, 110 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/interrupt.c b/drivers/net/wireless/ath/wil6210/interrupt.c
index d7e112da6a8d..5d287a8e1b45 100644
--- a/drivers/net/wireless/ath/wil6210/interrupt.c
+++ b/drivers/net/wireless/ath/wil6210/interrupt.c
@@ -625,6 +625,15 @@ static irqreturn_t wil6210_irq_misc_thread(int irq, void *cookie)
 
 	wil6210_unmask_irq_misc(wil, false);
 
+	/* in non-triple MSI case, this is done inside wil6210_thread_irq
+	 * because it has to be done after unmasking the pseudo.
+	 */
+	if (wil->n_msi == 3 && wil->suspend_resp_rcvd) {
+		wil_dbg_irq(wil, "set suspend_resp_comp to true\n");
+		wil->suspend_resp_comp = true;
+		wake_up_interruptible(&wil->wq);
+	}
+
 	return IRQ_HANDLED;
 }
 
@@ -782,6 +791,40 @@ static irqreturn_t wil6210_hardirq(int irq, void *cookie)
 	return rc;
 }
 
+static int wil6210_request_3msi(struct wil6210_priv *wil, int irq)
+{
+	int rc;
+
+	/* IRQ's are in the following order:
+	 * - Tx
+	 * - Rx
+	 * - Misc
+	 */
+	rc = request_irq(irq, wil->txrx_ops.irq_tx, IRQF_SHARED,
+			 WIL_NAME "_tx", wil);
+	if (rc)
+		return rc;
+
+	rc = request_irq(irq + 1, wil->txrx_ops.irq_rx, IRQF_SHARED,
+			 WIL_NAME "_rx", wil);
+	if (rc)
+		goto free0;
+
+	rc = request_threaded_irq(irq + 2, wil6210_irq_misc,
+				  wil6210_irq_misc_thread,
+				  IRQF_SHARED, WIL_NAME "_misc", wil);
+	if (rc)
+		goto free1;
+
+	return 0;
+free1:
+	free_irq(irq + 1, wil);
+free0:
+	free_irq(irq, wil);
+
+	return rc;
+}
+
 /* can't use wil_ioread32_and_clear because ICC value is not set yet */
 static inline void wil_clear32(void __iomem *addr)
 {
@@ -822,11 +865,12 @@ void wil6210_clear_halp(struct wil6210_priv *wil)
 	wil6210_unmask_halp(wil);
 }
 
-int wil6210_init_irq(struct wil6210_priv *wil, int irq, bool use_msi)
+int wil6210_init_irq(struct wil6210_priv *wil, int irq)
 {
 	int rc;
 
-	wil_dbg_misc(wil, "init_irq: %s\n", use_msi ? "MSI" : "INTx");
+	wil_dbg_misc(wil, "init_irq: %s, n_msi=%d\n",
+		     wil->n_msi ? "MSI" : "INTx", wil->n_msi);
 
 	if (wil->use_enhanced_dma_hw) {
 		wil->txrx_ops.irq_tx = wil6210_irq_tx_edma;
@@ -835,10 +879,14 @@ int wil6210_init_irq(struct wil6210_priv *wil, int irq, bool use_msi)
 		wil->txrx_ops.irq_tx = wil6210_irq_tx;
 		wil->txrx_ops.irq_rx = wil6210_irq_rx;
 	}
-	rc = request_threaded_irq(irq, wil6210_hardirq,
-				  wil6210_thread_irq,
-				  use_msi ? 0 : IRQF_SHARED,
-				  WIL_NAME, wil);
+
+	if (wil->n_msi == 3)
+		rc = wil6210_request_3msi(wil, irq);
+	else
+		rc = request_threaded_irq(irq, wil6210_hardirq,
+					  wil6210_thread_irq,
+					  wil->n_msi ? 0 : IRQF_SHARED,
+					  WIL_NAME, wil);
 	return rc;
 }
 
@@ -848,4 +896,8 @@ void wil6210_fini_irq(struct wil6210_priv *wil, int irq)
 
 	wil_mask_irq(wil);
 	free_irq(irq, wil);
+	if (wil->n_msi == 3) {
+		free_irq(irq + 1, wil);
+		free_irq(irq + 2, wil);
+	}
 }
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 7e4ccd9ac2bc..9495c6cb8288 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1136,6 +1136,9 @@ void wil_refresh_fw_capabilities(struct wil6210_priv *wil)
 				     wil->platform_capa)) ?
 			BIT(WIL_PLATFORM_FEATURE_FW_EXT_CLK_CONTROL) : 0;
 
+		if (wil->n_msi == 3)
+			features |= BIT(WIL_PLATFORM_FEATURE_TRIPLE_MSI);
+
 		wil->platform_ops.set_features(wil->platform_handle, features);
 	}
 }
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 7192d9a91278..095c16fc5e8a 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -24,9 +24,9 @@
 #include <linux/rtnetlink.h>
 #include <linux/pm_runtime.h>
 
-static bool use_msi = true;
-module_param(use_msi, bool, 0444);
-MODULE_PARM_DESC(use_msi, " Use MSI interrupt, default - true");
+static int n_msi = 1;
+module_param(n_msi, int, 0444);
+MODULE_PARM_DESC(n_msi, " Use MSI interrupt: 0 - use INTx, 1 - (default) - single, or 3");
 
 static bool ftm_mode;
 module_param(ftm_mode, bool, 0444);
@@ -150,12 +150,24 @@ int wil_set_capabilities(struct wil6210_priv *wil)
 
 void wil_disable_irq(struct wil6210_priv *wil)
 {
-	disable_irq(wil->pdev->irq);
+	int irq = wil->pdev->irq;
+
+	disable_irq(irq);
+	if (wil->n_msi == 3) {
+		disable_irq(irq + 1);
+		disable_irq(irq + 2);
+	}
 }
 
 void wil_enable_irq(struct wil6210_priv *wil)
 {
-	enable_irq(wil->pdev->irq);
+	int irq = wil->pdev->irq;
+
+	enable_irq(irq);
+	if (wil->n_msi == 3) {
+		enable_irq(irq + 1);
+		enable_irq(irq + 2);
+	}
 }
 
 static void wil_remove_all_additional_vifs(struct wil6210_priv *wil)
@@ -182,28 +194,47 @@ static int wil_if_pcie_enable(struct wil6210_priv *wil)
 	 * and only MSI should be used
 	 */
 	int msi_only = pdev->msi_enabled;
-	bool _use_msi = use_msi;
 
 	wil_dbg_misc(wil, "if_pcie_enable\n");
 
 	pci_set_master(pdev);
 
-	wil_dbg_misc(wil, "Setup %s interrupt\n", use_msi ? "MSI" : "INTx");
+	/* how many MSI interrupts to request? */
+	switch (n_msi) {
+	case 3:
+	case 1:
+		wil_dbg_misc(wil, "Setup %d MSI interrupts\n", n_msi);
+		break;
+	case 0:
+		wil_dbg_misc(wil, "MSI interrupts disabled, use INTx\n");
+		break;
+	default:
+		wil_err(wil, "Invalid n_msi=%d, default to 1\n", n_msi);
+		n_msi = 1;
+	}
+
+	if (n_msi == 3 &&
+	    pci_alloc_irq_vectors(pdev, n_msi, n_msi, PCI_IRQ_MSI) < n_msi) {
+		wil_err(wil, "3 MSI mode failed, try 1 MSI\n");
+		n_msi = 1;
+	}
 
-	if (use_msi && pci_enable_msi(pdev)) {
+	if (n_msi == 1 && pci_enable_msi(pdev)) {
 		wil_err(wil, "pci_enable_msi failed, use INTx\n");
-		_use_msi = false;
+		n_msi = 0;
 	}
 
-	if (!_use_msi && msi_only) {
+	wil->n_msi = n_msi;
+
+	if (wil->n_msi == 0 && msi_only) {
 		wil_err(wil, "Interrupt pin not routed, unable to use INTx\n");
 		rc = -ENODEV;
 		goto stop_master;
 	}
 
-	rc = wil6210_init_irq(wil, pdev->irq, _use_msi);
+	rc = wil6210_init_irq(wil, pdev->irq);
 	if (rc)
-		goto stop_master;
+		goto release_vectors;
 
 	/* need reset here to obtain MAC */
 	mutex_lock(&wil->mutex);
@@ -216,8 +247,9 @@ static int wil_if_pcie_enable(struct wil6210_priv *wil)
 
  release_irq:
 	wil6210_fini_irq(wil, pdev->irq);
-	/* safe to call if no MSI */
-	pci_disable_msi(pdev);
+ release_vectors:
+	/* safe to call if no allocation */
+	pci_free_irq_vectors(pdev);
  stop_master:
 	pci_clear_master(pdev);
 	return rc;
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 00719a018a4a..379f7ce664c5 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -874,6 +874,7 @@ struct wil6210_priv {
 	u32 bar_size;
 	struct wiphy *wiphy;
 	struct net_device *main_ndev;
+	int n_msi;
 	void __iomem *csr;
 	DECLARE_BITMAP(status, wil_status_last);
 	u8 fw_version[ETHTOOL_FWVERS_LEN];
@@ -1206,7 +1207,7 @@ int wil_addba_rx_request(struct wil6210_priv *wil, u8 mid,
 int wil_addba_tx_request(struct wil6210_priv *wil, u8 ringid, u16 wsize);
 
 void wil6210_clear_irq(struct wil6210_priv *wil);
-int wil6210_init_irq(struct wil6210_priv *wil, int irq, bool use_msi);
+int wil6210_init_irq(struct wil6210_priv *wil, int irq);
 void wil6210_fini_irq(struct wil6210_priv *wil, int irq);
 void wil_mask_irq(struct wil6210_priv *wil);
 void wil_unmask_irq(struct wil6210_priv *wil);
diff --git a/drivers/net/wireless/ath/wil6210/wil_platform.h b/drivers/net/wireless/ath/wil6210/wil_platform.h
index 177026e5323b..bca090611477 100644
--- a/drivers/net/wireless/ath/wil6210/wil_platform.h
+++ b/drivers/net/wireless/ath/wil6210/wil_platform.h
@@ -29,6 +29,7 @@ enum wil_platform_event {
 
 enum wil_platform_features {
 	WIL_PLATFORM_FEATURE_FW_EXT_CLK_CONTROL = 0,
+	WIL_PLATFORM_FEATURE_TRIPLE_MSI = 1,
 	WIL_PLATFORM_FEATURE_MAX,
 };
 
-- 
cgit v1.2.3


From 65e6ffdcc4507cbdd38f374ae311263106ee46fe Mon Sep 17 00:00:00 2001
From: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:30 +0300
Subject: wil6210: fix min() compilation errors

With some tool chains compilation fails due to type
mismatch of the arguments passed to min().
Use min_t() to solve these compilation errors.

Signed-off-by: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/fw_inc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/wil6210/fw_inc.c b/drivers/net/wireless/ath/wil6210/fw_inc.c
index 718161b829c2..388b3d4717ca 100644
--- a/drivers/net/wireless/ath/wil6210/fw_inc.c
+++ b/drivers/net/wireless/ath/wil6210/fw_inc.c
@@ -145,7 +145,7 @@ fw_handle_capabilities(struct wil6210_priv *wil, const void *data,
 				    capabilities);
 	bitmap_zero(wil->fw_capabilities, WMI_FW_CAPABILITY_MAX);
 	memcpy(wil->fw_capabilities, rec->capabilities,
-	       min(sizeof(wil->fw_capabilities), capa_size));
+	       min_t(size_t, sizeof(wil->fw_capabilities), capa_size));
 	wil_hex_dump_fw("CAPA", DUMP_PREFIX_OFFSET, 16, 1,
 			rec->capabilities, capa_size, false);
 	return 0;
-- 
cgit v1.2.3


From 0c936b3c96337c3fd5ad4951ca7bdc54fa578a02 Mon Sep 17 00:00:00 2001
From: Dedy Lansky <dlansky@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:31 +0300
Subject: wil6210: add support for link statistics

Driver can request FW to report link statistics using
WMI_LINK_STATS_CMDID.
FW will report statistics with WMI_LINK_STATS_EVENTID.
Two categories of statistics defined: basic and global.

New "link_stats" debugfs is used for requesting basic statistics
report (write) and for reading the basic statistics (read).
"link_stats_global" debugfs is used for requesting and reading the
global statistics.

Signed-off-by: Dedy Lansky <dlansky@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/debugfs.c | 219 +++++++++++++++++++++++++++++
 drivers/net/wireless/ath/wil6210/wil6210.h |  12 ++
 drivers/net/wireless/ath/wil6210/wmi.c     | 165 ++++++++++++++++++++++
 drivers/net/wireless/ath/wil6210/wmi.h     |  57 +++++---
 4 files changed, 437 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/debugfs.c b/drivers/net/wireless/ath/wil6210/debugfs.c
index f2eab39376ee..51c3330bc316 100644
--- a/drivers/net/wireless/ath/wil6210/debugfs.c
+++ b/drivers/net/wireless/ath/wil6210/debugfs.c
@@ -1922,6 +1922,223 @@ static const struct file_operations fops_tx_latency = {
 	.llseek		= seq_lseek,
 };
 
+static void wil_link_stats_print_basic(struct wil6210_vif *vif,
+				       struct seq_file *s,
+				       struct wmi_link_stats_basic *basic)
+{
+	char per[5] = "?";
+
+	if (basic->per_average != 0xff)
+		snprintf(per, sizeof(per), "%d%%", basic->per_average);
+
+	seq_printf(s, "CID %d {\n"
+		   "\tTxMCS %d TxTpt %d\n"
+		   "\tGoodput(rx:tx) %d:%d\n"
+		   "\tRxBcastFrames %d\n"
+		   "\tRSSI %d SQI %d SNR %d PER %s\n"
+		   "\tRx RFC %d Ant num %d\n"
+		   "\tSectors(rx:tx) my %d:%d peer %d:%d\n"
+		   "}\n",
+		   basic->cid,
+		   basic->bf_mcs, le32_to_cpu(basic->tx_tpt),
+		   le32_to_cpu(basic->rx_goodput),
+		   le32_to_cpu(basic->tx_goodput),
+		   le32_to_cpu(basic->rx_bcast_frames),
+		   basic->rssi, basic->sqi, basic->snr, per,
+		   basic->selected_rfc, basic->rx_effective_ant_num,
+		   basic->my_rx_sector, basic->my_tx_sector,
+		   basic->other_rx_sector, basic->other_tx_sector);
+}
+
+static void wil_link_stats_print_global(struct wil6210_priv *wil,
+					struct seq_file *s,
+					struct wmi_link_stats_global *global)
+{
+	seq_printf(s, "Frames(rx:tx) %d:%d\n"
+		   "BA Frames(rx:tx) %d:%d\n"
+		   "Beacons %d\n"
+		   "Rx Errors (MIC:CRC) %d:%d\n"
+		   "Tx Errors (no ack) %d\n",
+		   le32_to_cpu(global->rx_frames),
+		   le32_to_cpu(global->tx_frames),
+		   le32_to_cpu(global->rx_ba_frames),
+		   le32_to_cpu(global->tx_ba_frames),
+		   le32_to_cpu(global->tx_beacons),
+		   le32_to_cpu(global->rx_mic_errors),
+		   le32_to_cpu(global->rx_crc_errors),
+		   le32_to_cpu(global->tx_fail_no_ack));
+}
+
+static void wil_link_stats_debugfs_show_vif(struct wil6210_vif *vif,
+					    struct seq_file *s)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wmi_link_stats_basic *stats;
+	int i;
+
+	if (!vif->fw_stats_ready) {
+		seq_puts(s, "no statistics\n");
+		return;
+	}
+
+	seq_printf(s, "TSF %lld\n", vif->fw_stats_tsf);
+	for (i = 0; i < ARRAY_SIZE(wil->sta); i++) {
+		if (wil->sta[i].status == wil_sta_unused)
+			continue;
+		if (wil->sta[i].mid != vif->mid)
+			continue;
+
+		stats = &wil->sta[i].fw_stats_basic;
+		wil_link_stats_print_basic(vif, s, stats);
+	}
+}
+
+static int wil_link_stats_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+	struct wil6210_vif *vif;
+	int i, rc;
+
+	rc = mutex_lock_interruptible(&wil->vif_mutex);
+	if (rc)
+		return rc;
+
+	/* iterate over all MIDs and show per-cid statistics. Then show the
+	 * global statistics
+	 */
+	for (i = 0; i < wil->max_vifs; i++) {
+		vif = wil->vifs[i];
+
+		seq_printf(s, "MID %d ", i);
+		if (!vif) {
+			seq_puts(s, "unused\n");
+			continue;
+		}
+
+		wil_link_stats_debugfs_show_vif(vif, s);
+	}
+
+	mutex_unlock(&wil->vif_mutex);
+
+	return 0;
+}
+
+static int wil_link_stats_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_link_stats_debugfs_show, inode->i_private);
+}
+
+static ssize_t wil_link_stats_write(struct file *file, const char __user *buf,
+				    size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int cid, interval, rc, i;
+	struct wil6210_vif *vif;
+	char *kbuf = kmalloc(len + 1, GFP_KERNEL);
+
+	if (!kbuf)
+		return -ENOMEM;
+
+	rc = simple_write_to_buffer(kbuf, len, ppos, buf, len);
+	if (rc != len) {
+		kfree(kbuf);
+		return rc >= 0 ? -EIO : rc;
+	}
+
+	kbuf[len] = '\0';
+	/* specify cid (use -1 for all cids) and snapshot interval in ms */
+	rc = sscanf(kbuf, "%d %d", &cid, &interval);
+	kfree(kbuf);
+	if (rc < 0)
+		return rc;
+	if (rc < 2 || interval < 0)
+		return -EINVAL;
+
+	wil_info(wil, "request link statistics, cid %d interval %d\n",
+		 cid, interval);
+
+	rc = mutex_lock_interruptible(&wil->vif_mutex);
+	if (rc)
+		return rc;
+
+	for (i = 0; i < wil->max_vifs; i++) {
+		vif = wil->vifs[i];
+		if (!vif)
+			continue;
+
+		rc = wmi_link_stats_cfg(vif, WMI_LINK_STATS_TYPE_BASIC,
+					(cid == -1 ? 0xff : cid), interval);
+		if (rc)
+			wil_err(wil, "link statistics failed for mid %d\n", i);
+	}
+	mutex_unlock(&wil->vif_mutex);
+
+	return len;
+}
+
+static const struct file_operations fops_link_stats = {
+	.open		= wil_link_stats_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.write		= wil_link_stats_write,
+	.llseek		= seq_lseek,
+};
+
+static int
+wil_link_stats_global_debugfs_show(struct seq_file *s, void *data)
+{
+	struct wil6210_priv *wil = s->private;
+
+	if (!wil->fw_stats_global.ready)
+		return 0;
+
+	seq_printf(s, "TSF %lld\n", wil->fw_stats_global.tsf);
+	wil_link_stats_print_global(wil, s, &wil->fw_stats_global.stats);
+
+	return 0;
+}
+
+static int
+wil_link_stats_global_seq_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, wil_link_stats_global_debugfs_show,
+			   inode->i_private);
+}
+
+static ssize_t
+wil_link_stats_global_write(struct file *file, const char __user *buf,
+			    size_t len, loff_t *ppos)
+{
+	struct seq_file *s = file->private_data;
+	struct wil6210_priv *wil = s->private;
+	int interval, rc;
+	struct wil6210_vif *vif = ndev_to_vif(wil->main_ndev);
+
+	/* specify snapshot interval in ms */
+	rc = kstrtoint_from_user(buf, len, 0, &interval);
+	if (rc || interval < 0) {
+		wil_err(wil, "Invalid argument\n");
+		return -EINVAL;
+	}
+
+	wil_info(wil, "request global link stats, interval %d\n", interval);
+
+	rc = wmi_link_stats_cfg(vif, WMI_LINK_STATS_TYPE_GLOBAL, 0, interval);
+	if (rc)
+		wil_err(wil, "global link stats failed %d\n", rc);
+
+	return rc ? rc : len;
+}
+
+static const struct file_operations fops_link_stats_global = {
+	.open		= wil_link_stats_global_seq_open,
+	.release	= single_release,
+	.read		= seq_read,
+	.write		= wil_link_stats_global_write,
+	.llseek		= seq_lseek,
+};
+
 static ssize_t wil_read_file_led_cfg(struct file *file, char __user *user_buf,
 				     size_t count, loff_t *ppos)
 {
@@ -2256,6 +2473,8 @@ static const struct {
 	{"status_msg",	0444,		&fops_status_msg},
 	{"rx_buff_mgmt",	0444,	&fops_rx_buff_mgmt},
 	{"tx_latency",	0644,		&fops_tx_latency},
+	{"link_stats",	0644,		&fops_link_stats},
+	{"link_stats_global",	0644,	&fops_link_stats_global},
 };
 
 static void wil6210_debugfs_init_files(struct wil6210_priv *wil,
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 379f7ce664c5..e87c88957033 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -728,6 +728,7 @@ struct wil_sta_info {
 	 * tx_latency_res is configured from "tx_latency" debug-fs.
 	 */
 	u64 *tx_latency_bins;
+	struct wmi_link_stats_basic fw_stats_basic;
 	/* Rx BACK */
 	struct wil_tid_ampdu_rx *tid_rx[WIL_STA_TID_NUM];
 	spinlock_t tid_rx_lock; /* guarding tid_rx array */
@@ -842,6 +843,8 @@ struct wil6210_vif {
 	struct mutex probe_client_mutex; /* protect @probe_client_pending */
 	struct work_struct probe_client_worker;
 	int net_queue_stopped; /* netif_tx_stop_all_queues invoked */
+	bool fw_stats_ready; /* per-cid statistics are ready inside sta_info */
+	u64 fw_stats_tsf; /* measurement timestamp */
 };
 
 /**
@@ -869,6 +872,12 @@ struct wil_rx_buff_mgmt {
 	unsigned long free_list_empty_cnt; /* statistics */
 };
 
+struct wil_fw_stats_global {
+	bool ready;
+	u64 tsf; /* measurement timestamp */
+	struct wmi_link_stats_global stats;
+};
+
 struct wil6210_priv {
 	struct pci_dev *pdev;
 	u32 bar_size;
@@ -1002,6 +1011,8 @@ struct wil6210_priv {
 	bool use_rx_hw_reordering;
 	bool secured_boot;
 	u8 boot_config;
+
+	struct wil_fw_stats_global fw_stats_global;
 };
 
 #define wil_to_wiphy(i) (i->wiphy)
@@ -1201,6 +1212,7 @@ int wmi_new_sta(struct wil6210_vif *vif, const u8 *mac, u8 aid);
 int wmi_port_allocate(struct wil6210_priv *wil, u8 mid,
 		      const u8 *mac, enum nl80211_iftype iftype);
 int wmi_port_delete(struct wil6210_priv *wil, u8 mid);
+int wmi_link_stats_cfg(struct wil6210_vif *vif, u32 type, u8 cid, u32 interval);
 int wil_addba_rx_request(struct wil6210_priv *wil, u8 mid,
 			 u8 cidxtid, u8 dialog_token, __le16 ba_param_set,
 			 __le16 ba_timeout, __le16 ba_seq_ctrl);
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 71056c834fff..45a71fd7cc28 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -464,6 +464,8 @@ static const char *cmdid2name(u16 cmdid)
 		return "WMI_BCAST_DESC_RING_ADD_CMD";
 	case WMI_CFG_DEF_RX_OFFLOAD_CMDID:
 		return "WMI_CFG_DEF_RX_OFFLOAD_CMD";
+	case WMI_LINK_STATS_CMDID:
+		return "WMI_LINK_STATS_CMD";
 	default:
 		return "Untracked CMD";
 	}
@@ -598,6 +600,10 @@ static const char *eventid2name(u16 eventid)
 		return "WMI_RX_DESC_RING_CFG_DONE_EVENT";
 	case WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENTID:
 		return "WMI_CFG_DEF_RX_OFFLOAD_DONE_EVENT";
+	case WMI_LINK_STATS_CONFIG_DONE_EVENTID:
+		return "WMI_LINK_STATS_CONFIG_DONE_EVENT";
+	case WMI_LINK_STATS_EVENTID:
+		return "WMI_LINK_STATS_EVENT";
 	default:
 		return "Untracked EVENT";
 	}
@@ -1329,6 +1335,130 @@ wmi_evt_sched_scan_result(struct wil6210_vif *vif, int id, void *d, int len)
 	cfg80211_sched_scan_results(wiphy, 0);
 }
 
+static void wil_link_stats_store_basic(struct wil6210_vif *vif,
+				       struct wmi_link_stats_basic *basic)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	u8 cid = basic->cid;
+	struct wil_sta_info *sta;
+
+	if (cid < 0 || cid >= WIL6210_MAX_CID) {
+		wil_err(wil, "invalid cid %d\n", cid);
+		return;
+	}
+
+	sta = &wil->sta[cid];
+	sta->fw_stats_basic = *basic;
+}
+
+static void wil_link_stats_store_global(struct wil6210_vif *vif,
+					struct wmi_link_stats_global *global)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+
+	wil->fw_stats_global.stats = *global;
+}
+
+static void wmi_link_stats_parse(struct wil6210_vif *vif, u64 tsf,
+				 bool has_next, void *payload,
+				 size_t payload_size)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	size_t hdr_size = sizeof(struct wmi_link_stats_record);
+	size_t stats_size, record_size, expected_size;
+	struct wmi_link_stats_record *hdr;
+
+	if (payload_size < hdr_size) {
+		wil_err(wil, "link stats wrong event size %zu\n", payload_size);
+		return;
+	}
+
+	while (payload_size >= hdr_size) {
+		hdr = payload;
+		stats_size = le16_to_cpu(hdr->record_size);
+		record_size = hdr_size + stats_size;
+
+		if (payload_size < record_size) {
+			wil_err(wil, "link stats payload ended unexpectedly, size %zu < %zu\n",
+				payload_size, record_size);
+			return;
+		}
+
+		switch (hdr->record_type_id) {
+		case WMI_LINK_STATS_TYPE_BASIC:
+			expected_size = sizeof(struct wmi_link_stats_basic);
+			if (stats_size < expected_size) {
+				wil_err(wil, "link stats invalid basic record size %zu < %zu\n",
+					stats_size, expected_size);
+				return;
+			}
+			if (vif->fw_stats_ready) {
+				/* clean old statistics */
+				vif->fw_stats_tsf = 0;
+				vif->fw_stats_ready = 0;
+			}
+
+			wil_link_stats_store_basic(vif, payload + hdr_size);
+
+			if (!has_next) {
+				vif->fw_stats_tsf = tsf;
+				vif->fw_stats_ready = 1;
+			}
+
+			break;
+		case WMI_LINK_STATS_TYPE_GLOBAL:
+			expected_size = sizeof(struct wmi_link_stats_global);
+			if (stats_size < sizeof(struct wmi_link_stats_global)) {
+				wil_err(wil, "link stats invalid global record size %zu < %zu\n",
+					stats_size, expected_size);
+				return;
+			}
+
+			if (wil->fw_stats_global.ready) {
+				/* clean old statistics */
+				wil->fw_stats_global.tsf = 0;
+				wil->fw_stats_global.ready = 0;
+			}
+
+			wil_link_stats_store_global(vif, payload + hdr_size);
+
+			if (!has_next) {
+				wil->fw_stats_global.tsf = tsf;
+				wil->fw_stats_global.ready = 1;
+			}
+
+			break;
+		default:
+			break;
+		}
+
+		/* skip to next record */
+		payload += record_size;
+		payload_size -= record_size;
+	}
+}
+
+static void
+wmi_evt_link_stats(struct wil6210_vif *vif, int id, void *d, int len)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wmi_link_stats_event *evt = d;
+	size_t payload_size;
+
+	if (len < offsetof(struct wmi_link_stats_event, payload)) {
+		wil_err(wil, "stats event way too short %d\n", len);
+		return;
+	}
+	payload_size = le16_to_cpu(evt->payload_size);
+	if (len < sizeof(struct wmi_link_stats_event) + payload_size) {
+		wil_err(wil, "stats event too short %d\n", len);
+		return;
+	}
+
+	wmi_link_stats_parse(vif, le64_to_cpu(evt->tsf), evt->has_next,
+			     evt->payload, payload_size);
+}
+
 /**
  * Some events are ignored for purpose; and need not be interpreted as
  * "unhandled events"
@@ -1359,6 +1489,7 @@ static const struct {
 	{WMI_RING_EN_EVENTID,		wmi_evt_ring_en},
 	{WMI_DATA_PORT_OPEN_EVENTID,		wmi_evt_ignore},
 	{WMI_SCHED_SCAN_RESULT_EVENTID,		wmi_evt_sched_scan_result},
+	{WMI_LINK_STATS_EVENTID,		wmi_evt_link_stats},
 };
 
 /*
@@ -3242,3 +3373,37 @@ int wil_wmi_bcast_desc_ring_add(struct wil6210_vif *vif, int ring_id)
 
 	return 0;
 }
+
+int wmi_link_stats_cfg(struct wil6210_vif *vif, u32 type, u8 cid, u32 interval)
+{
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct wmi_link_stats_cmd cmd = {
+		.record_type_mask = cpu_to_le32(type),
+		.cid = cid,
+		.action = WMI_LINK_STATS_SNAPSHOT,
+		.interval_msec = cpu_to_le32(interval),
+	};
+	struct {
+		struct wmi_cmd_hdr wmi;
+		struct wmi_link_stats_config_done_event evt;
+	} __packed reply = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+	int rc;
+
+	rc = wmi_call(wil, WMI_LINK_STATS_CMDID, vif->mid, &cmd, sizeof(cmd),
+		      WMI_LINK_STATS_CONFIG_DONE_EVENTID, &reply,
+		      sizeof(reply), WIL_WMI_CALL_GENERAL_TO_MS);
+	if (rc) {
+		wil_err(wil, "WMI_LINK_STATS_CMDID failed, rc %d\n", rc);
+		return rc;
+	}
+
+	if (reply.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "Link statistics config failed, status %d\n",
+			reply.evt.status);
+		return -EINVAL;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index 13f6f6210117..00cf3c422133 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -1715,9 +1715,7 @@ enum wmi_link_stats_action {
 /* WMI_LINK_STATS_EVENT record identifiers */
 enum wmi_link_stats_record_type {
 	WMI_LINK_STATS_TYPE_BASIC	= 0x01,
-	WMI_LINK_STATS_TYPE_MAC		= 0x02,
-	WMI_LINK_STATS_TYPE_PHY		= 0x04,
-	WMI_LINK_STATS_TYPE_OTA		= 0x08,
+	WMI_LINK_STATS_TYPE_GLOBAL	= 0x02,
 };
 
 /* WMI_LINK_STATS_CMDID */
@@ -1731,7 +1729,7 @@ struct wmi_link_stats_cmd {
 	/* wmi_link_stats_action_e */
 	u8 action;
 	u8 reserved[6];
-	/* for WMI_LINK_STATS_PERIODIC */
+	/* range = 100 - 10000 */
 	__le32 interval_msec;
 } __packed;
 
@@ -3779,32 +3777,59 @@ struct wmi_link_stats_config_done_event {
 
 /* WMI_LINK_STATS_EVENTID */
 struct wmi_link_stats_event {
+	__le64 tsf;
 	__le16 payload_size;
 	u8 has_next;
 	u8 reserved[5];
-	/* a stream of records, e.g. wmi_link_stats_basic_s */
+	/* a stream of wmi_link_stats_record_s */
 	u8 payload[0];
 } __packed;
 
-/* WMI_LINK_STATS_EVENT record struct */
-struct wmi_link_stats_basic {
-	/* WMI_LINK_STATS_TYPE_BASIC */
+/* WMI_LINK_STATS_EVENT */
+struct wmi_link_stats_record {
+	/* wmi_link_stats_record_type_e */
 	u8 record_type_id;
+	u8 reserved;
+	__le16 record_size;
+	u8 record[0];
+} __packed;
+
+/* WMI_LINK_STATS_TYPE_BASIC */
+struct wmi_link_stats_basic {
 	u8 cid;
-	/* 0: fail; 1: OK; 2: retrying */
-	u8 bf_status;
 	s8 rssi;
 	u8 sqi;
+	u8 bf_mcs;
+	u8 per_average;
 	u8 selected_rfc;
-	__le16 bf_mcs;
+	u8 rx_effective_ant_num;
+	u8 my_rx_sector;
+	u8 my_tx_sector;
+	u8 other_rx_sector;
+	u8 other_tx_sector;
+	u8 reserved[7];
+	/* 1/4 Db units */
+	__le16 snr;
 	__le32 tx_tpt;
 	__le32 tx_goodput;
 	__le32 rx_goodput;
-	__le16 my_rx_sector;
-	__le16 my_tx_sector;
-	__le16 other_rx_sector;
-	__le16 other_tx_sector;
-	__le32 reserved[2];
+	__le32 bf_count;
+	__le32 rx_bcast_frames;
+} __packed;
+
+/* WMI_LINK_STATS_TYPE_GLOBAL */
+struct wmi_link_stats_global {
+	/* all ack-able frames */
+	__le32 rx_frames;
+	/* all ack-able frames */
+	__le32 tx_frames;
+	__le32 rx_ba_frames;
+	__le32 tx_ba_frames;
+	__le32 tx_beacons;
+	__le32 rx_mic_errors;
+	__le32 rx_crc_errors;
+	__le32 tx_fail_no_ack;
+	u8 reserved[8];
 } __packed;
 
 /* WMI_SET_GRANT_MCS_EVENTID */
-- 
cgit v1.2.3


From af2cd85e8dbd4241c21c0136d13e36b0043604ba Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:32 +0300
Subject: wil6210: allow scan on AP interface

Scan is allowed only on client interfaces (STA/P2P).
Allow scan on AP interface so that the AP can discover rouge
or unauthorized neighbor APs.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/cfg80211.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index e63b07830f2c..3c754abb008c 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -689,11 +689,12 @@ static int wil_cfg80211_scan(struct wiphy *wiphy,
 
 	wil_dbg_misc(wil, "scan: wdev=0x%p iftype=%d\n", wdev, wdev->iftype);
 
-	/* check we are client side */
+	/* scan is supported on client interfaces and on AP interface */
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_STATION:
 	case NL80211_IFTYPE_P2P_CLIENT:
 	case NL80211_IFTYPE_P2P_DEVICE:
+	case NL80211_IFTYPE_AP:
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 1b99197dc00cbb34cb39be70ad5beb4a5a84be4b Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:33 +0300
Subject: wil6210: support max aggregation window size 64

FW can support BACK window size 64 for performance improvements.
A new FW capability is added for notifying the host on the increased
max BACK win size support.
Defining WIL_MAX_AGG_WSIZE_64 and WIL_MAX_AMPDU_SIZE_128 to be used
in this case.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c       | 9 +++++++++
 drivers/net/wireless/ath/wil6210/rx_reorder.c | 8 ++++----
 drivers/net/wireless/ath/wil6210/wil6210.h    | 5 +++++
 drivers/net/wireless/ath/wil6210/wmi.h        | 1 +
 4 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 9495c6cb8288..a949e919061b 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1141,6 +1141,15 @@ void wil_refresh_fw_capabilities(struct wil6210_priv *wil)
 
 		wil->platform_ops.set_features(wil->platform_handle, features);
 	}
+
+	if (test_bit(WMI_FW_CAPABILITY_BACK_WIN_SIZE_64,
+		     wil->fw_capabilities)) {
+		wil->max_agg_wsize = WIL_MAX_AGG_WSIZE_64;
+		wil->max_ampdu_size = WIL_MAX_AMPDU_SIZE_128;
+	} else {
+		wil->max_agg_wsize = WIL_MAX_AGG_WSIZE;
+		wil->max_ampdu_size = WIL_MAX_AMPDU_SIZE;
+	}
 }
 
 void wil_mbox_ring_le2cpus(struct wil6210_mbox_ring *r)
diff --git a/drivers/net/wireless/ath/wil6210/rx_reorder.c b/drivers/net/wireless/ath/wil6210/rx_reorder.c
index ba4e93f53b4a..b608aa16b4f1 100644
--- a/drivers/net/wireless/ath/wil6210/rx_reorder.c
+++ b/drivers/net/wireless/ath/wil6210/rx_reorder.c
@@ -297,7 +297,7 @@ void wil_tid_ampdu_rx_free(struct wil6210_priv *wil,
 /* ADDBA processing */
 static u16 wil_agg_size(struct wil6210_priv *wil, u16 req_agg_wsize)
 {
-	u16 max_agg_size = min_t(u16, WIL_MAX_AGG_WSIZE, WIL_MAX_AMPDU_SIZE /
+	u16 max_agg_size = min_t(u16, wil->max_agg_wsize, wil->max_ampdu_size /
 				 (mtu_max + WIL_MAX_MPDU_OVERHEAD));
 
 	if (!req_agg_wsize)
@@ -364,11 +364,11 @@ __acquires(&sta->tid_rx_lock) __releases(&sta->tid_rx_lock)
 	if (status == WLAN_STATUS_SUCCESS) {
 		if (req_agg_wsize == 0) {
 			wil_dbg_misc(wil, "Suggest BACK wsize %d\n",
-				     WIL_MAX_AGG_WSIZE);
-			agg_wsize = WIL_MAX_AGG_WSIZE;
+				     wil->max_agg_wsize);
+			agg_wsize = wil->max_agg_wsize;
 		} else {
 			agg_wsize = min_t(u16,
-					  WIL_MAX_AGG_WSIZE, req_agg_wsize);
+					  wil->max_agg_wsize, req_agg_wsize);
 		}
 	}
 
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index e87c88957033..b5d8ad2d95a8 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -90,6 +90,8 @@ static inline u32 WIL_GET_BITS(u32 x, int b0, int b1)
 #define WIL6210_NAPI_BUDGET	(16) /* arbitrary */
 #define WIL_MAX_AMPDU_SIZE	(64 * 1024) /* FW/HW limit */
 #define WIL_MAX_AGG_WSIZE	(32) /* FW/HW limit */
+#define WIL_MAX_AMPDU_SIZE_128	(128 * 1024) /* FW/HW limit */
+#define WIL_MAX_AGG_WSIZE_64	(64) /* FW/HW limit */
 #define WIL6210_MAX_STATUS_RINGS	(8)
 
 /* Hardware offload block adds the following:
@@ -1013,6 +1015,9 @@ struct wil6210_priv {
 	u8 boot_config;
 
 	struct wil_fw_stats_global fw_stats_global;
+
+	u32 max_agg_wsize;
+	u32 max_ampdu_size;
 };
 
 #define wil_to_wiphy(i) (i->wiphy)
diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index 00cf3c422133..719f3109e91e 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -99,6 +99,7 @@ enum wmi_fw_capability {
 	WMI_FW_CAPABILITY_AP_SME_OFFLOAD_NONE		= 19,
 	WMI_FW_CAPABILITY_MULTI_VIFS			= 20,
 	WMI_FW_CAPABILITY_FT_ROAMING			= 21,
+	WMI_FW_CAPABILITY_BACK_WIN_SIZE_64		= 22,
 	WMI_FW_CAPABILITY_AMSDU				= 23,
 	WMI_FW_CAPABILITY_MAX,
 };
-- 
cgit v1.2.3


From 6ccae584014ef7074359eb4151086beef66ecfa9 Mon Sep 17 00:00:00 2001
From: Hamad Kadmany <hkadmany@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:34 +0300
Subject: wil6210: increase firmware ready timeout

Firmware ready event may take longer than
current timeout in some scenarios, for example
with multiple RFs connected where each
requires an initial calibration.

Increase the timeout to support these scenarios.

Signed-off-by: Hamad Kadmany <hkadmany@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index a949e919061b..7dcbd4629e0d 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1282,7 +1282,7 @@ static int wil_get_otp_info(struct wil6210_priv *wil)
 
 static int wil_wait_for_fw_ready(struct wil6210_priv *wil)
 {
-	ulong to = msecs_to_jiffies(1000);
+	ulong to = msecs_to_jiffies(2000);
 	ulong left = wait_for_completion_timeout(&wil->wmi_ready, to);
 
 	if (0 == left) {
-- 
cgit v1.2.3


From 631d3b4f7eeb76ffb865ff7805b495b50ee623f8 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:35 +0300
Subject: wil6210: support Talyn specific board file

FW file name for Talyn device can be different from the default name.
In such a case use a corresponding board file name.
If such a board file is not present FW download procedure will fail.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/fw.c       |  3 +++
 drivers/net/wireless/ath/wil6210/main.c     | 35 ++++++++++++++++++++++++-----
 drivers/net/wireless/ath/wil6210/pcie_bus.c |  2 +-
 drivers/net/wireless/ath/wil6210/wil6210.h  |  4 ++++
 4 files changed, 38 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/fw.c b/drivers/net/wireless/ath/wil6210/fw.c
index 540fc20984d8..3e2bbbceca06 100644
--- a/drivers/net/wireless/ath/wil6210/fw.c
+++ b/drivers/net/wireless/ath/wil6210/fw.c
@@ -1,5 +1,6 @@
 /*
  * Copyright (c) 2014-2015,2017 Qualcomm Atheros, Inc.
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -22,6 +23,8 @@
 MODULE_FIRMWARE(WIL_FW_NAME_DEFAULT);
 MODULE_FIRMWARE(WIL_FW_NAME_SPARROW_PLUS);
 MODULE_FIRMWARE(WIL_BOARD_FILE_NAME);
+MODULE_FIRMWARE(WIL_FW_NAME_TALYN);
+MODULE_FIRMWARE(WIL_BRD_NAME_TALYN);
 
 static
 void wil_memset_toio_32(volatile void __iomem *dst, u32 val,
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 7dcbd4629e0d..64de67975866 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -28,6 +28,7 @@
 #define WAIT_FOR_HALP_VOTE_MS 100
 #define WAIT_FOR_SCAN_ABORT_MS 1000
 #define WIL_DEFAULT_NUM_RX_STATUS_RINGS 1
+#define WIL_BOARD_FILE_MAX_NAMELEN 128
 
 bool debug_fw; /* = false; */
 module_param(debug_fw, bool, 0444);
@@ -1161,6 +1162,28 @@ void wil_mbox_ring_le2cpus(struct wil6210_mbox_ring *r)
 	le32_to_cpus(&r->head);
 }
 
+/* construct actual board file name to use */
+void wil_get_board_file(struct wil6210_priv *wil, char *buf, size_t len)
+{
+	const char *board_file;
+	const char *wil_talyn_fw_name = ftm_mode ? WIL_FW_NAME_FTM_TALYN :
+			      WIL_FW_NAME_TALYN;
+
+	if (wil->board_file) {
+		board_file = wil->board_file;
+	} else {
+		/* If specific FW file is used for Talyn,
+		 * use specific board file
+		 */
+		if (strcmp(wil->wil_fw_name, wil_talyn_fw_name) == 0)
+			board_file = WIL_BRD_NAME_TALYN;
+		else
+			board_file = WIL_BOARD_FILE_NAME;
+	}
+
+	strlcpy(buf, board_file, len);
+}
+
 static int wil_get_bl_info(struct wil6210_priv *wil)
 {
 	struct net_device *ndev = wil->main_ndev;
@@ -1532,8 +1555,12 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 
 	wil_set_oob_mode(wil, oob_mode);
 	if (load_fw) {
+		char board_file[WIL_BOARD_FILE_MAX_NAMELEN];
+
+		board_file[0] = '\0';
+		wil_get_board_file(wil, board_file, sizeof(board_file));
 		wil_info(wil, "Use firmware <%s> + board <%s>\n",
-			 wil->wil_fw_name, WIL_BOARD_FILE_NAME);
+			 wil->wil_fw_name, board_file);
 
 		if (!no_flash)
 			wil_bl_prepare_halt(wil);
@@ -1545,11 +1572,9 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 		if (rc)
 			goto out;
 		if (wil->brd_file_addr)
-			rc = wil_request_board(wil, WIL_BOARD_FILE_NAME);
+			rc = wil_request_board(wil, board_file);
 		else
-			rc = wil_request_firmware(wil,
-						  WIL_BOARD_FILE_NAME,
-						  true);
+			rc = wil_request_firmware(wil, board_file, true);
 		if (rc)
 			goto out;
 
diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index 095c16fc5e8a..e44b4ad1de65 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -28,7 +28,7 @@ static int n_msi = 1;
 module_param(n_msi, int, 0444);
 MODULE_PARM_DESC(n_msi, " Use MSI interrupt: 0 - use INTx, 1 - (default) - single, or 3");
 
-static bool ftm_mode;
+bool ftm_mode;
 module_param(ftm_mode, bool, 0444);
 MODULE_PARM_DESC(ftm_mode, " Set factory test mode, default - false");
 
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index b5d8ad2d95a8..542075da69f1 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -37,6 +37,7 @@ extern bool rx_align_2;
 extern bool rx_large_buf;
 extern bool debug_fw;
 extern bool disable_ap_sme;
+extern bool ftm_mode;
 
 struct wil6210_priv;
 struct wil6210_vif;
@@ -52,6 +53,7 @@ union wil_tx_desc;
 
 #define WIL_FW_NAME_TALYN "wil6436.fw"
 #define WIL_FW_NAME_FTM_TALYN "wil6436_ftm.fw"
+#define WIL_BRD_NAME_TALYN "wil6436.brd"
 
 #define WIL_BOARD_FILE_NAME "wil6210.brd" /* board & radio parameters */
 
@@ -1101,6 +1103,8 @@ static inline void wil_c(struct wil6210_priv *wil, u32 reg, u32 val)
 	wil_w(wil, reg, wil_r(wil, reg) & ~val);
 }
 
+void wil_get_board_file(struct wil6210_priv *wil, char *buf, size_t len);
+
 #if defined(CONFIG_DYNAMIC_DEBUG)
 #define wil_hex_dump_txrx(prefix_str, prefix_type, rowsize,	\
 			  groupsize, buf, len, ascii)		\
-- 
cgit v1.2.3


From 7f10f8ba02207af13db0c33fa97e5904ec3ea39e Mon Sep 17 00:00:00 2001
From: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:36 +0300
Subject: wil6210: set default 3-MSI

Single MSI is the current default configuration.
With multiple MSI interrupts configuration, Tx/Rx processing could
run in parallel on different CPU cores and allow better balance
between the cores.

Signed-off-by: Alexei Avshalom Lazar <ailizaro@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/pcie_bus.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/pcie_bus.c b/drivers/net/wireless/ath/wil6210/pcie_bus.c
index e44b4ad1de65..89119e7facd0 100644
--- a/drivers/net/wireless/ath/wil6210/pcie_bus.c
+++ b/drivers/net/wireless/ath/wil6210/pcie_bus.c
@@ -24,9 +24,9 @@
 #include <linux/rtnetlink.h>
 #include <linux/pm_runtime.h>
 
-static int n_msi = 1;
+static int n_msi = 3;
 module_param(n_msi, int, 0444);
-MODULE_PARM_DESC(n_msi, " Use MSI interrupt: 0 - use INTx, 1 - (default) - single, or 3");
+MODULE_PARM_DESC(n_msi, " Use MSI interrupt: 0 - use INTx, 1 - single, or 3 - (default) ");
 
 bool ftm_mode;
 module_param(ftm_mode, bool, 0444);
-- 
cgit v1.2.3


From 6a363e8aa3828621eb4bc5e506f35f6ca9016d57 Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:37 +0300
Subject: wil6210: align to latest auto generated wmi.h

Align to latest version of the auto generated wmi file
describing the interface with FW.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/wmi.h | 200 ++++++++++++++++++++++++++++++++-
 1 file changed, 197 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/wmi.h b/drivers/net/wireless/ath/wil6210/wmi.h
index 719f3109e91e..139acb2caf92 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.h
+++ b/drivers/net/wireless/ath/wil6210/wmi.h
@@ -101,6 +101,8 @@ enum wmi_fw_capability {
 	WMI_FW_CAPABILITY_FT_ROAMING			= 21,
 	WMI_FW_CAPABILITY_BACK_WIN_SIZE_64		= 22,
 	WMI_FW_CAPABILITY_AMSDU				= 23,
+	WMI_FW_CAPABILITY_RAW_MODE			= 24,
+	WMI_FW_CAPABILITY_TX_REQ_EXT			= 25,
 	WMI_FW_CAPABILITY_MAX,
 };
 
@@ -135,6 +137,12 @@ enum wmi_command_id {
 	WMI_SET_WSC_STATUS_CMDID			= 0x41,
 	WMI_PXMT_RANGE_CFG_CMDID			= 0x42,
 	WMI_PXMT_SNR2_RANGE_CFG_CMDID			= 0x43,
+	WMI_RADAR_GENERAL_CONFIG_CMDID			= 0x100,
+	WMI_RADAR_CONFIG_SELECT_CMDID			= 0x101,
+	WMI_RADAR_PARAMS_CONFIG_CMDID			= 0x102,
+	WMI_RADAR_SET_MODE_CMDID			= 0x103,
+	WMI_RADAR_CONTROL_CMDID				= 0x104,
+	WMI_RADAR_PCI_CONTROL_CMDID			= 0x105,
 	WMI_MEM_READ_CMDID				= 0x800,
 	WMI_MEM_WR_CMDID				= 0x801,
 	WMI_ECHO_CMDID					= 0x803,
@@ -175,6 +183,10 @@ enum wmi_command_id {
 	WMI_SET_PCP_CHANNEL_CMDID			= 0x829,
 	WMI_GET_PCP_CHANNEL_CMDID			= 0x82A,
 	WMI_SW_TX_REQ_CMDID				= 0x82B,
+	/* Event is shared between WMI_SW_TX_REQ_CMDID and
+	 * WMI_SW_TX_REQ_EXT_CMDID
+	 */
+	WMI_SW_TX_REQ_EXT_CMDID				= 0x82C,
 	WMI_MLME_PUSH_CMDID				= 0x835,
 	WMI_BEAMFORMING_MGMT_CMDID			= 0x836,
 	WMI_BF_TXSS_MGMT_CMDID				= 0x837,
@@ -559,6 +571,109 @@ struct wmi_pxmt_snr2_range_cfg_cmd {
 	s8 snr2range_arr[2];
 } __packed;
 
+/* WMI_RADAR_GENERAL_CONFIG_CMDID */
+struct wmi_radar_general_config_cmd {
+	/* Number of pulses (CIRs) in FW FIFO to initiate pulses transfer
+	 * from FW to Host
+	 */
+	__le32 fifo_watermark;
+	/* In unit of us, in the range [100, 1000000] */
+	__le32 t_burst;
+	/* Valid in the range [1, 32768], 0xFFFF means infinite */
+	__le32 n_bursts;
+	/* In unit of 330Mhz clk, in the range [4, 2000]*330 */
+	__le32 t_pulse;
+	/* In the range of [1,4096] */
+	__le16 n_pulses;
+	/* Number of taps after cTap per CIR */
+	__le16 n_samples;
+	/* Offset from the main tap (0 = zero-distance). In the range of [0,
+	 * 255]
+	 */
+	u8 first_sample_offset;
+	/* Number of Pulses to average, 1, 2, 4, 8 */
+	u8 pulses_to_avg;
+	/* Number of adjacent taps to average, 1, 2, 4, 8 */
+	u8 samples_to_avg;
+	/* The index to config general params */
+	u8 general_index;
+	u8 reserved[4];
+} __packed;
+
+/* WMI_RADAR_CONFIG_SELECT_CMDID */
+struct wmi_radar_config_select_cmd {
+	/* Select the general params index to use */
+	u8 general_index;
+	u8 reserved[3];
+	/* 0 means don't update burst_active_vector */
+	__le32 burst_active_vector;
+	/* 0 means don't update pulse_active_vector */
+	__le32 pulse_active_vector;
+} __packed;
+
+/* WMI_RADAR_PARAMS_CONFIG_CMDID */
+struct wmi_radar_params_config_cmd {
+	/* The burst index selected to config */
+	u8 burst_index;
+	/* 0-not active, 1-active */
+	u8 burst_en;
+	/* The pulse index selected to config */
+	u8 pulse_index;
+	/* 0-not active, 1-active */
+	u8 pulse_en;
+	/* TX RF to use on current pulse */
+	u8 tx_rfc_idx;
+	u8 tx_sector;
+	/* Offset from calibrated value.(expected to be 0)(value is row in
+	 * Gain-LUT, not dB)
+	 */
+	s8 tx_rf_gain_comp;
+	/* expected to be 0 */
+	s8 tx_bb_gain_comp;
+	/* RX RF to use on current pulse */
+	u8 rx_rfc_idx;
+	u8 rx_sector;
+	/* Offset from calibrated value.(expected to be 0)(value is row in
+	 * Gain-LUT, not dB)
+	 */
+	s8 rx_rf_gain_comp;
+	/* Value in dB.(expected to be 0) */
+	s8 rx_bb_gain_comp;
+	/* Offset from calibrated value.(expected to be 0) */
+	s8 rx_timing_offset;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_SET_MODE_CMDID */
+struct wmi_radar_set_mode_cmd {
+	/* 0-disable/1-enable */
+	u8 enable;
+	/* enum wmi_channel */
+	u8 channel;
+	/* In the range of [0,7], 0xff means use default */
+	u8 tx_rfc_idx;
+	/* In the range of [0,7], 0xff means use default */
+	u8 rx_rfc_idx;
+} __packed;
+
+/* WMI_RADAR_CONTROL_CMDID */
+struct wmi_radar_control_cmd {
+	/* 0-stop/1-start */
+	u8 start;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_PCI_CONTROL_CMDID */
+struct wmi_radar_pci_control_cmd {
+	/* pcie host buffer start address */
+	__le64 base_addr;
+	/* pcie host control block address */
+	__le64 control_block_addr;
+	/* pcie host buffer size */
+	__le32 buffer_size;
+	__le32 reserved;
+} __packed;
+
 /* WMI_RF_MGMT_CMDID */
 enum wmi_rf_mgmt_type {
 	WMI_RF_MGMT_W_DISABLE	= 0x00,
@@ -696,12 +811,18 @@ struct wmi_pcp_start_cmd {
 	u8 pcp_max_assoc_sta;
 	u8 hidden_ssid;
 	u8 is_go;
-	u8 reserved0[5];
+	/* enum wmi_channel WMI_CHANNEL_9..WMI_CHANNEL_12 */
+	u8 edmg_channel;
+	u8 raw_mode;
+	u8 reserved[3];
 	/* A-BFT length override if non-0 */
 	u8 abft_len;
 	/* enum wmi_ap_sme_offload_mode_e */
 	u8 ap_sme_offload_mode;
 	u8 network_type;
+	/* enum wmi_channel WMI_CHANNEL_1..WMI_CHANNEL_6; for EDMG this is
+	 * the primary channel number
+	 */
 	u8 channel;
 	u8 disable_sec_offload;
 	u8 disable_sec;
@@ -714,6 +835,17 @@ struct wmi_sw_tx_req_cmd {
 	u8 payload[0];
 } __packed;
 
+/* WMI_SW_TX_REQ_EXT_CMDID */
+struct wmi_sw_tx_req_ext_cmd {
+	u8 dst_mac[WMI_MAC_LEN];
+	__le16 len;
+	__le16 duration_ms;
+	/* Channel to use, 0xFF for currently active channel */
+	u8 channel;
+	u8 reserved[5];
+	u8 payload[0];
+} __packed;
+
 /* WMI_VRING_SWITCH_TIMING_CONFIG_CMDID */
 struct wmi_vring_switch_timing_config_cmd {
 	/* Set vring timing configuration:
@@ -740,6 +872,7 @@ struct wmi_vring_cfg_schd {
 enum wmi_vring_cfg_encap_trans_type {
 	WMI_VRING_ENC_TYPE_802_3	= 0x00,
 	WMI_VRING_ENC_TYPE_NATIVE_WIFI	= 0x01,
+	WMI_VRING_ENC_TYPE_NONE		= 0x02,
 };
 
 enum wmi_vring_cfg_ds_cfg {
@@ -1151,8 +1284,8 @@ struct wmi_echo_cmd {
 } __packed;
 
 /* WMI_DEEP_ECHO_CMDID
- * Check FW and ucode are alive
- * Returned event: WMI_ECHO_RSP_EVENTID
+ * Check FW and uCode is alive
+ * Returned event: WMI_DEEP_ECHO_RSP_EVENTID
  */
 struct wmi_deep_echo_cmd {
 	__le32 value;
@@ -1527,6 +1660,52 @@ struct wmi_set_multi_directed_omnis_config_event {
 	u8 reserved[3];
 } __packed;
 
+/* WMI_RADAR_GENERAL_CONFIG_EVENTID */
+struct wmi_radar_general_config_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_CONFIG_SELECT_EVENTID */
+struct wmi_radar_config_select_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+	/* In unit of bytes */
+	__le32 fifo_size;
+	/* In unit of bytes */
+	__le32 pulse_size;
+} __packed;
+
+/* WMI_RADAR_PARAMS_CONFIG_EVENTID */
+struct wmi_radar_params_config_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_SET_MODE_EVENTID */
+struct wmi_radar_set_mode_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_CONTROL_EVENTID */
+struct wmi_radar_control_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
+/* WMI_RADAR_PCI_CONTROL_EVENTID */
+struct wmi_radar_pci_control_event {
+	/* wmi_fw_status */
+	u8 status;
+	u8 reserved[3];
+} __packed;
+
 /* WMI_SET_LONG_RANGE_CONFIG_CMDID */
 struct wmi_set_long_range_config_cmd {
 	__le32 reserved;
@@ -1759,10 +1938,17 @@ enum wmi_event_id {
 	WMI_REPORT_STATISTICS_EVENTID			= 0x100B,
 	WMI_FT_AUTH_STATUS_EVENTID			= 0x100C,
 	WMI_FT_REASSOC_STATUS_EVENTID			= 0x100D,
+	WMI_RADAR_GENERAL_CONFIG_EVENTID		= 0x1100,
+	WMI_RADAR_CONFIG_SELECT_EVENTID			= 0x1101,
+	WMI_RADAR_PARAMS_CONFIG_EVENTID			= 0x1102,
+	WMI_RADAR_SET_MODE_EVENTID			= 0x1103,
+	WMI_RADAR_CONTROL_EVENTID			= 0x1104,
+	WMI_RADAR_PCI_CONTROL_EVENTID			= 0x1105,
 	WMI_RD_MEM_RSP_EVENTID				= 0x1800,
 	WMI_FW_READY_EVENTID				= 0x1801,
 	WMI_EXIT_FAST_MEM_ACC_MODE_EVENTID		= 0x200,
 	WMI_ECHO_RSP_EVENTID				= 0x1803,
+	WMI_DEEP_ECHO_RSP_EVENTID			= 0x1804,
 	/* deprecated */
 	WMI_FS_TUNE_DONE_EVENTID			= 0x180A,
 	/* deprecated */
@@ -1788,6 +1974,9 @@ enum wmi_event_id {
 	WMI_DELBA_EVENTID				= 0x1826,
 	WMI_GET_SSID_EVENTID				= 0x1828,
 	WMI_GET_PCP_CHANNEL_EVENTID			= 0x182A,
+	/* Event is shared between WMI_SW_TX_REQ_CMDID and
+	 * WMI_SW_TX_REQ_EXT_CMDID
+	 */
 	WMI_SW_TX_COMPLETE_EVENTID			= 0x182B,
 	WMI_BEAMFORMING_MGMT_DONE_EVENTID		= 0x1836,
 	WMI_BF_TXSS_MGMT_DONE_EVENTID			= 0x1837,
@@ -2539,6 +2728,11 @@ struct wmi_echo_rsp_event {
 	__le32 echoed_value;
 } __packed;
 
+/* WMI_DEEP_ECHO_RSP_EVENTID */
+struct wmi_deep_echo_rsp_event {
+	__le32 echoed_value;
+} __packed;
+
 /* WMI_RF_PWR_ON_DELAY_RSP_EVENTID */
 struct wmi_rf_pwr_on_delay_rsp_event {
 	/* wmi_fw_status */
-- 
cgit v1.2.3


From b698e2dfc24cd148ce32f622a20938037ebe06b7 Mon Sep 17 00:00:00 2001
From: Ahmad Masri <amasri@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:38 +0300
Subject: wil6210: off channel transmit management frames in AP mode

Currently wil6210 ignores the channel field in the
cfg80211_mgmt_tx_params struct for wil_cfg80211_ops mgmt_tx operation
and sends all management frames on the serving channel.

Add support for off-channel transmission of management frames
(WIPHY_FLAG_OFFCHAN_TX) in AP mode. This is useful in enterprise APs
for sending custom probe request frames.

Signed-off-by: Ahmad Masri <amasri@codeaurora.org>
Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/cfg80211.c | 47 ++++++++++++++++++++----
 drivers/net/wireless/ath/wil6210/main.c     |  3 ++
 drivers/net/wireless/ath/wil6210/wil6210.h  |  2 ++
 drivers/net/wireless/ath/wil6210/wmi.c      | 56 +++++++++++++++++++++++++++++
 4 files changed, 101 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/cfg80211.c b/drivers/net/wireless/ath/wil6210/cfg80211.c
index 3c754abb008c..f79c337105cb 100644
--- a/drivers/net/wireless/ath/wil6210/cfg80211.c
+++ b/drivers/net/wireless/ath/wil6210/cfg80211.c
@@ -1090,18 +1090,51 @@ int wil_cfg80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
 	int rc;
 	bool tx_status;
 
-	/* Note, currently we do not support the "wait" parameter, user-space
-	 * must call remain_on_channel before mgmt_tx or listen on a channel
-	 * another way (AP/PCP or connected station)
-	 * in addition we need to check if specified "chan" argument is
-	 * different from currently "listened" channel and fail if it is.
+	wil_dbg_misc(wil, "mgmt_tx: channel %d offchan %d, wait %d\n",
+		     params->chan ? params->chan->hw_value : -1,
+		     params->offchan,
+		     params->wait);
+
+	/* Note, currently we support the "wait" parameter only on AP mode.
+	 * In other modes, user-space must call remain_on_channel before
+	 * mgmt_tx or listen on a channel other than active one.
 	 */
 
-	rc = wmi_mgmt_tx(vif, buf, len);
-	tx_status = (rc == 0);
+	if (params->chan && params->chan->hw_value == 0) {
+		wil_err(wil, "invalid channel\n");
+		return -EINVAL;
+	}
+
+	if (wdev->iftype != NL80211_IFTYPE_AP) {
+		wil_dbg_misc(wil,
+			     "send WMI_SW_TX_REQ_CMDID on non-AP interfaces\n");
+		rc = wmi_mgmt_tx(vif, buf, len);
+		goto out;
+	}
 
+	if (!params->chan || params->chan->hw_value == vif->channel) {
+		wil_dbg_misc(wil,
+			     "send WMI_SW_TX_REQ_CMDID for on-channel\n");
+		rc = wmi_mgmt_tx(vif, buf, len);
+		goto out;
+	}
+
+	if (params->offchan == 0) {
+		wil_err(wil,
+			"invalid channel params: current %d requested %d, off-channel not allowed\n",
+			vif->channel, params->chan->hw_value);
+		return -EBUSY;
+	}
+
+	/* use the wmi_mgmt_tx_ext only on AP mode and off-channel */
+	rc = wmi_mgmt_tx_ext(vif, buf, len, params->chan->hw_value,
+			     params->wait);
+
+out:
+	tx_status = (rc == 0);
 	cfg80211_mgmt_tx_status(wdev, cookie ? *cookie : 0, buf, len,
 				tx_status, GFP_KERNEL);
+
 	return rc;
 }
 
diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 64de67975866..7ad22dfd6698 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1130,6 +1130,9 @@ void wil_refresh_fw_capabilities(struct wil6210_priv *wil)
 		wiphy->max_sched_scan_plans = WMI_MAX_PLANS_NUM;
 	}
 
+	if (test_bit(WMI_FW_CAPABILITY_TX_REQ_EXT, wil->fw_capabilities))
+		wiphy->flags |= WIPHY_FLAG_OFFCHAN_TX;
+
 	if (wil->platform_ops.set_features) {
 		features = (test_bit(WMI_FW_CAPABILITY_REF_CLOCK_CONTROL,
 				     wil->fw_capabilities) &&
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 542075da69f1..9fc51f79d75b 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -1350,6 +1350,8 @@ int wmi_start_sched_scan(struct wil6210_priv *wil,
 			 struct cfg80211_sched_scan_request *request);
 int wmi_stop_sched_scan(struct wil6210_priv *wil);
 int wmi_mgmt_tx(struct wil6210_vif *vif, const u8 *buf, size_t len);
+int wmi_mgmt_tx_ext(struct wil6210_vif *vif, const u8 *buf, size_t len,
+		    u8 channel, u16 duration_ms);
 
 int reverse_memcmp(const void *cs, const void *ct, size_t count);
 
diff --git a/drivers/net/wireless/ath/wil6210/wmi.c b/drivers/net/wireless/ath/wil6210/wmi.c
index 45a71fd7cc28..42c02a20ec97 100644
--- a/drivers/net/wireless/ath/wil6210/wmi.c
+++ b/drivers/net/wireless/ath/wil6210/wmi.c
@@ -466,6 +466,8 @@ static const char *cmdid2name(u16 cmdid)
 		return "WMI_CFG_DEF_RX_OFFLOAD_CMD";
 	case WMI_LINK_STATS_CMDID:
 		return "WMI_LINK_STATS_CMD";
+	case WMI_SW_TX_REQ_EXT_CMDID:
+		return "WMI_SW_TX_REQ_EXT_CMDID";
 	default:
 		return "Untracked CMD";
 	}
@@ -3114,6 +3116,60 @@ int wmi_mgmt_tx(struct wil6210_vif *vif, const u8 *buf, size_t len)
 	return rc;
 }
 
+int wmi_mgmt_tx_ext(struct wil6210_vif *vif, const u8 *buf, size_t len,
+		    u8 channel, u16 duration_ms)
+{
+	size_t total;
+	struct wil6210_priv *wil = vif_to_wil(vif);
+	struct ieee80211_mgmt *mgmt_frame = (void *)buf;
+	struct wmi_sw_tx_req_ext_cmd *cmd;
+	struct {
+		struct wmi_cmd_hdr wmi;
+		struct wmi_sw_tx_complete_event evt;
+	} __packed evt = {
+		.evt = {.status = WMI_FW_STATUS_FAILURE},
+	};
+	int rc;
+
+	wil_dbg_wmi(wil, "mgmt_tx_ext mid %d channel %d duration %d\n",
+		    vif->mid, channel, duration_ms);
+	wil_hex_dump_wmi("mgmt_tx_ext frame ", DUMP_PREFIX_OFFSET, 16, 1, buf,
+			 len, true);
+
+	if (len < sizeof(struct ieee80211_hdr_3addr)) {
+		wil_err(wil, "short frame. len %zu\n", len);
+		return -EINVAL;
+	}
+
+	total = sizeof(*cmd) + len;
+	if (total < len) {
+		wil_err(wil, "mgmt_tx_ext invalid len %zu\n", len);
+		return -EINVAL;
+	}
+
+	cmd = kzalloc(total, GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	memcpy(cmd->dst_mac, mgmt_frame->da, WMI_MAC_LEN);
+	cmd->len = cpu_to_le16(len);
+	memcpy(cmd->payload, buf, len);
+	cmd->channel = channel - 1;
+	cmd->duration_ms = cpu_to_le16(duration_ms);
+
+	rc = wmi_call(wil, WMI_SW_TX_REQ_EXT_CMDID, vif->mid, cmd, total,
+		      WMI_SW_TX_COMPLETE_EVENTID, &evt, sizeof(evt), 2000);
+	if (!rc && evt.evt.status != WMI_FW_STATUS_SUCCESS) {
+		wil_err(wil, "mgmt_tx_ext failed with status %d\n",
+			evt.evt.status);
+		rc = -EINVAL;
+	}
+
+	kfree(cmd);
+
+	return rc;
+}
+
 int wil_wmi_tx_sring_cfg(struct wil6210_priv *wil, int ring_id)
 {
 	int rc;
-- 
cgit v1.2.3


From d554edcd972d46179bf10258379e80f609bb52e5 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:39 +0300
Subject: wil6210: prevent FW download if HW is configured for secured boot

Currently the driver doesn't support secured boot flow, hence
prevent FW download in case HW is configured for such a flow.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 7ad22dfd6698..1d4ce8e22483 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1560,6 +1560,11 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 	if (load_fw) {
 		char board_file[WIL_BOARD_FILE_MAX_NAMELEN];
 
+		if  (wil->secured_boot) {
+			wil_err(wil, "secured boot is not supported\n");
+			return -ENOTSUPP;
+		}
+
 		board_file[0] = '\0';
 		wil_get_board_file(wil, board_file, sizeof(board_file));
 		wil_info(wil, "Use firmware <%s> + board <%s>\n",
-- 
cgit v1.2.3


From 1bb38e8bb81e5c43bc1a2b44bc8e340783005f58 Mon Sep 17 00:00:00 2001
From: Maya Erez <merez@codeaurora.org>
Date: Tue, 24 Jul 2018 10:44:40 +0300
Subject: wil6210: fix eDMA RX chaining

HW requires Rx buffers to be 4 bytes aligned. Modify the driver to
meet this requirement.
Enable OFU rdy valid bug fix, to prevent hang in oful34_rx while
there is back-pressure from host during RX.

Signed-off-by: Maya Erez <merez@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/wil6210/main.c      |  7 +++++++
 drivers/net/wireless/ath/wil6210/txrx_edma.c | 13 ++++++-------
 drivers/net/wireless/ath/wil6210/wil6210.h   |  2 ++
 3 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/wil6210/main.c b/drivers/net/wireless/ath/wil6210/main.c
index 1d4ce8e22483..7debed6bec06 100644
--- a/drivers/net/wireless/ath/wil6210/main.c
+++ b/drivers/net/wireless/ath/wil6210/main.c
@@ -1614,6 +1614,13 @@ int wil_reset(struct wil6210_priv *wil, bool load_fw)
 
 		wil->txrx_ops.configure_interrupt_moderation(wil);
 
+		/* Enable OFU rdy valid bug fix, to prevent hang in oful34_rx
+		 * while there is back-pressure from Host during RX
+		 */
+		if (wil->hw_version >= HW_VER_TALYN_MB)
+			wil_s(wil, RGF_DMA_MISC_CTL,
+			      BIT_OFUL34_RDY_VALID_BUG_FIX_EN);
+
 		rc = wil_restore_vifs(wil);
 		if (rc) {
 			wil_err(wil, "failed to restore vifs, rc %d\n", rc);
diff --git a/drivers/net/wireless/ath/wil6210/txrx_edma.c b/drivers/net/wireless/ath/wil6210/txrx_edma.c
index 9ef2b66f7561..bca61cb44c37 100644
--- a/drivers/net/wireless/ath/wil6210/txrx_edma.c
+++ b/drivers/net/wireless/ath/wil6210/txrx_edma.c
@@ -27,6 +27,8 @@
 #include "trace.h"
 
 #define WIL_EDMA_MAX_DATA_OFFSET (2)
+/* RX buffer size must be aligned to 4 bytes */
+#define WIL_EDMA_RX_BUF_LEN_DEFAULT (2048)
 
 static void wil_tx_desc_unmap_edma(struct device *dev,
 				   union wil_tx_desc *desc,
@@ -158,8 +160,7 @@ static int wil_ring_alloc_skb_edma(struct wil6210_priv *wil,
 				   struct wil_ring *ring, u32 i)
 {
 	struct device *dev = wil_to_dev(wil);
-	unsigned int sz = wil->rx_buf_len + ETH_HLEN +
-		WIL_EDMA_MAX_DATA_OFFSET;
+	unsigned int sz = ALIGN(wil->rx_buf_len, 4);
 	dma_addr_t pa;
 	u16 buff_id;
 	struct list_head *active = &wil->rx_buff_mgmt.active;
@@ -600,7 +601,7 @@ static bool wil_is_rx_idle_edma(struct wil6210_priv *wil)
 static void wil_rx_buf_len_init_edma(struct wil6210_priv *wil)
 {
 	wil->rx_buf_len = rx_large_buf ?
-		WIL_MAX_ETH_MTU : TXRX_BUF_LEN_DEFAULT - WIL_MAX_MPDU_OVERHEAD;
+		WIL_MAX_ETH_MTU : WIL_EDMA_RX_BUF_LEN_DEFAULT;
 }
 
 static int wil_rx_init_edma(struct wil6210_priv *wil, u16 desc_ring_size)
@@ -633,8 +634,7 @@ static int wil_rx_init_edma(struct wil6210_priv *wil, u16 desc_ring_size)
 
 	wil_rx_buf_len_init_edma(wil);
 
-	max_rx_pl_per_desc = wil->rx_buf_len + ETH_HLEN +
-		WIL_EDMA_MAX_DATA_OFFSET;
+	max_rx_pl_per_desc = ALIGN(wil->rx_buf_len, 4);
 
 	/* Use debugfs dbg_num_rx_srings if set, reserve one sring for TX */
 	if (wil->num_rx_status_rings > WIL6210_MAX_STATUS_RINGS - 1)
@@ -869,8 +869,7 @@ static struct sk_buff *wil_sring_reap_rx_edma(struct wil6210_priv *wil,
 	struct sk_buff *skb;
 	dma_addr_t pa;
 	struct wil_ring_rx_data *rxdata = &sring->rx_data;
-	unsigned int sz = wil->rx_buf_len + ETH_HLEN +
-		WIL_EDMA_MAX_DATA_OFFSET;
+	unsigned int sz = ALIGN(wil->rx_buf_len, 4);
 	struct wil_net_stats *stats = NULL;
 	u16 dmalen;
 	int cid;
diff --git a/drivers/net/wireless/ath/wil6210/wil6210.h b/drivers/net/wireless/ath/wil6210/wil6210.h
index 9fc51f79d75b..17c294b1ead1 100644
--- a/drivers/net/wireless/ath/wil6210/wil6210.h
+++ b/drivers/net/wireless/ath/wil6210/wil6210.h
@@ -302,6 +302,8 @@ struct RGF_ICR {
 	#define BIT_DMA_ITR_RX_IDL_CNT_CTL_FOREVER		BIT(2)
 	#define BIT_DMA_ITR_RX_IDL_CNT_CTL_CLR			BIT(3)
 	#define BIT_DMA_ITR_RX_IDL_CNT_CTL_REACHED_TRESH	BIT(4)
+#define RGF_DMA_MISC_CTL				(0x881d6c)
+	#define BIT_OFUL34_RDY_VALID_BUG_FIX_EN			BIT(7)
 
 #define RGF_DMA_PSEUDO_CAUSE		(0x881c68)
 #define RGF_DMA_PSEUDO_CAUSE_MASK_SW	(0x881c6c)
-- 
cgit v1.2.3


From 5223c671674c507cc9bcabdfc5a9b449c178330a Mon Sep 17 00:00:00 2001
From: Hendrik Brueckner <brueckner@linux.ibm.com>
Date: Mon, 16 Jul 2018 11:08:06 +0200
Subject: s390/cpum_sf: save TOD clock base in SDBs for time conversion

Processing the samples in the AUX-area by perf requires the computation
of respective time stamps.  The time stamps used by perf are based on
the monotonic clock.  To convert the TOD clock value contained in an
SDB to a monotonic clock value, the TOD clock base is required.  Hence,
also save the TOD clock base in the SDB.

Suggested-by: Thomas Richter <tmricht@linux.ibm.com>
Signed-off-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/include/asm/cpu_mf.h  | 12 +++++++++---
 arch/s390/kernel/perf_cpum_sf.c | 14 +++++++++++++-
 2 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/arch/s390/include/asm/cpu_mf.h b/arch/s390/include/asm/cpu_mf.h
index de023a9a88ca..bf2cbff926ef 100644
--- a/arch/s390/include/asm/cpu_mf.h
+++ b/arch/s390/include/asm/cpu_mf.h
@@ -2,7 +2,7 @@
 /*
  * CPU-measurement facilities
  *
- *  Copyright IBM Corp. 2012
+ *  Copyright IBM Corp. 2012, 2018
  *  Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  *	       Jan Glauber <jang@linux.vnet.ibm.com>
  */
@@ -139,8 +139,14 @@ struct hws_trailer_entry {
 	unsigned char timestamp[16];	 /* 16 - 31 timestamp		      */
 	unsigned long long reserved1;	 /* 32 -Reserved		      */
 	unsigned long long reserved2;	 /*				      */
-	unsigned long long progusage1;	 /* 48 - reserved for programming use */
-	unsigned long long progusage2;	 /*				      */
+	union {				 /* 48 - reserved for programming use */
+		struct {
+			unsigned int clock_base:1; /* in progusage2 */
+			unsigned long long progusage1:63;
+			unsigned long long progusage2;
+		};
+		unsigned long long progusage[2];
+	};
 } __packed;
 
 /* Load program parameter */
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index 0292d68e7dde..cb198d4a6dca 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -2,7 +2,7 @@
 /*
  * Performance event support for the System z CPU-measurement Sampling Facility
  *
- * Copyright IBM Corp. 2013
+ * Copyright IBM Corp. 2013, 2018
  * Author(s): Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
  */
 #define KMSG_COMPONENT	"cpum_sf"
@@ -1587,6 +1587,17 @@ static void aux_buffer_free(void *data)
 			    "%lu SDBTs\n", num_sdbt);
 }
 
+static void aux_sdb_init(unsigned long sdb)
+{
+	struct hws_trailer_entry *te;
+
+	te = (struct hws_trailer_entry *)trailer_entry_ptr(sdb);
+
+	/* Save clock base */
+	te->clock_base = 1;
+	memcpy(&te->progusage2, &tod_clock_base[1], 8);
+}
+
 /*
  * aux_buffer_setup() - Setup AUX buffer for diagnostic mode sampling
  * @cpu:	On which to allocate, -1 means current
@@ -1666,6 +1677,7 @@ static void *aux_buffer_setup(int cpu, void **pages, int nr_pages,
 		/* Tail is the entry in a SDBT */
 		*tail = (unsigned long)pages[i];
 		aux->sdb_index[i] = (unsigned long)pages[i];
+		aux_sdb_init((unsigned long)pages[i]);
 	}
 	sfb->num_sdb = nr_pages;
 
-- 
cgit v1.2.3


From d26de6c9f458f702b778731b7cb578ccd83623c9 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Tue, 31 Jul 2018 09:35:45 +0200
Subject: arm64: drop unused kernel_neon_begin_partial() macro

When kernel mode NEON was first introduced to the arm64 kernel,
every call to kernel_neon_begin()/_end() stacked resp. unstacked
the entire NEON register file, making it worthwile to reduce the
number of used NEON registers to a bare minimum, and only stack
those. kernel_neon_begin_partial() was introduced for this purpose,
but after the refactoring for SVE and other changes, it no longer
exists and was simply #define'd to kernel_neon_begin() directly.

In the mean time, all users have been updated, so let's remove
the fallback macro.

Reviewed-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/include/asm/neon.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/arch/arm64/include/asm/neon.h b/arch/arm64/include/asm/neon.h
index f922eaf780f9..fb9d137256a6 100644
--- a/arch/arm64/include/asm/neon.h
+++ b/arch/arm64/include/asm/neon.h
@@ -19,11 +19,4 @@
 void kernel_neon_begin(void);
 void kernel_neon_end(void);
 
-/*
- * Temporary macro to allow the crypto code to compile. Note that the
- * semantics of kernel_neon_begin_partial() are now different from the
- * original as it does not allow being called in an interrupt context.
- */
-#define kernel_neon_begin_partial(num_regs)	kernel_neon_begin()
-
 #endif /* ! __ASM_NEON_H */
-- 
cgit v1.2.3


From ce279d374ff315264efcbcef75cc21b9fef8b36f Mon Sep 17 00:00:00 2001
From: Laura Abbott <labbott@redhat.com>
Date: Mon, 30 Jul 2018 11:31:18 -0700
Subject: efi/libstub: Only disable stackleak plugin for arm64

arm64 uses the full KBUILD_CFLAGS for building libstub as opposed
to x86 which doesn't. This means that x86 doesn't pick up
the gcc-plugins. We need to disable the stackleak plugin but
doing this unconditionally breaks x86 build since it doesn't
have any plugins. Switch to disabling the stackleak plugin for
arm64 only.

Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Laura Abbott <labbott@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 drivers/firmware/efi/libstub/Makefile | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 25dd2a14560d..88c322d7c71e 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -11,7 +11,10 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -O2 \
 				   -fPIC -fno-strict-aliasing -mno-red-zone \
 				   -mno-mmx -mno-sse -fshort-wchar
 
-cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie
+# arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
+# disable the stackleak plugin
+cflags-$(CONFIG_ARM64)		:= $(subst -pg,,$(KBUILD_CFLAGS)) -fpie \
+				   $(DISABLE_STACKLEAK_PLUGIN)
 cflags-$(CONFIG_ARM)		:= $(subst -pg,,$(KBUILD_CFLAGS)) \
 				   -fno-builtin -fpic -mno-single-pic-base
 
@@ -21,7 +24,6 @@ KBUILD_CFLAGS			:= $(cflags-y) -DDISABLE_BRANCH_PROFILING \
 				   -D__NO_FORTIFY \
 				   $(call cc-option,-ffreestanding) \
 				   $(call cc-option,-fno-stack-protector) \
-				   $(DISABLE_STACKLEAK_PLUGIN)
 
 GCOV_PROFILE			:= n
 KASAN_SANITIZE			:= n
-- 
cgit v1.2.3


From 9d2dcc8fc66087d7fd365e07cd4292adc873e568 Mon Sep 17 00:00:00 2001
From: Michael O'Farrell <micpof@gmail.com>
Date: Mon, 30 Jul 2018 13:14:34 -0700
Subject: arm64: perf: Add cap_user_time aarch64

It is useful to get the running time of a thread.  Doing so in an
efficient manner can be important for performance of user applications.
Avoiding system calls in `clock_gettime` when handling
CLOCK_THREAD_CPUTIME_ID is important.  Other clocks are handled in the
VDSO, but CLOCK_THREAD_CPUTIME_ID falls back on the system call.

CLOCK_THREAD_CPUTIME_ID is not handled in the VDSO since it would have
costs associated with maintaining updated user space accessible time
offsets.  These offsets have to be updated everytime the a thread is
scheduled/descheduled.  However, for programs regularly checking the
running time of a thread, this is a performance improvement.

This patch takes a middle ground, and adds support for cap_user_time an
optional feature of the perf_event API.  This way costs are only
incurred when the perf_event api is enabled.  This is done the same way
as it is in x86.

Ultimately this allows calculating the thread running time in userspace
on aarch64 as follows (adapted from perf_event_open manpage):

u32 seq, time_mult, time_shift;
u64 running, count, time_offset, quot, rem, delta;
struct perf_event_mmap_page *pc;
pc = buf;  // buf is the perf event mmaped page as documented in the API.

if (pc->cap_usr_time) {
    do {
        seq = pc->lock;
        barrier();
        running = pc->time_running;

        count = readCNTVCT_EL0();  // Read ARM hardware clock.
        time_offset = pc->time_offset;
        time_mult   = pc->time_mult;
        time_shift  = pc->time_shift;

        barrier();
    } while (pc->lock != seq);

    quot = (count >> time_shift);
    rem = count & (((u64)1 << time_shift) - 1);
    delta = time_offset + quot * time_mult +
            ((rem * time_mult) >> time_shift);

    running += delta;
    // running now has the current nanosecond level thread time.
}

Summary of changes in the patch:

For aarch64 systems, make arch_perf_update_userpage update the timing
information stored in the perf_event page.  Requiring the following
calculations:
  - Calculate the appropriate time_mult, and time_shift factors to convert
    ticks to nano seconds for the current clock frequency.
  - Adjust the mult and shift factors to avoid shift factors of 32 bits.
    (possibly unnecessary)
  - The time_offset userspace should apply when doing calculations:
    negative the current sched time (now), because time_running and
    time_enabled fields of the perf_event page have just been updated.
Toggle bits to appropriate values:
  - Enable cap_user_time

Signed-off-by: Michael O'Farrell <micpof@gmail.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/perf_event.c | 30 ++++++++++++++++++++++++++++++
 kernel/events/core.c           |  4 ++--
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index dfff5ed5c625..8e38d5267f22 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -25,6 +25,7 @@
 #include <asm/virt.h>
 
 #include <linux/acpi.h>
+#include <linux/clocksource.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
@@ -1278,3 +1279,32 @@ static int __init armv8_pmu_driver_init(void)
 		return arm_pmu_acpi_probe(armv8_pmuv3_init);
 }
 device_initcall(armv8_pmu_driver_init)
+
+void arch_perf_update_userpage(struct perf_event *event,
+			       struct perf_event_mmap_page *userpg, u64 now)
+{
+	u32 freq;
+	u32 shift;
+
+	/*
+	 * Internal timekeeping for enabled/running/stopped times
+	 * is always computed with the sched_clock.
+	 */
+	freq = arch_timer_get_rate();
+	userpg->cap_user_time = 1;
+
+	clocks_calc_mult_shift(&userpg->time_mult, &shift, freq,
+			NSEC_PER_SEC, 0);
+	/*
+	 * time_shift is not expected to be greater than 31 due to
+	 * the original published conversion algorithm shifting a
+	 * 32-bit value (now specifies a 64-bit value) - refer
+	 * perf_event_mmap_page documentation in perf_event.h.
+	 */
+	if (shift == 32) {
+		shift = 31;
+		userpg->time_mult >>= 1;
+	}
+	userpg->time_shift = (u16)shift;
+	userpg->time_offset = -now;
+}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 8f0434a9951a..1a16dcca0da2 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5246,8 +5246,8 @@ void perf_event_update_userpage(struct perf_event *event)
 
 	userpg = rb->user_page;
 	/*
-	 * Disable preemption so as to not let the corresponding user-space
-	 * spin too long if we get preempted.
+	 * Disable preemption to guarantee consistent time stamps are stored to
+	 * the user page.
 	 */
 	preempt_disable();
 	++userpg->lock;
-- 
cgit v1.2.3


From e401b7c2c69008ad2fcdc154f7c5421281c90042 Mon Sep 17 00:00:00 2001
From: Bhupesh Sharma <bhsharma@redhat.com>
Date: Mon, 30 Jul 2018 11:54:43 +0530
Subject: arm64, kaslr: export offset in VMCOREINFO ELF notes

Include KASLR offset in arm64 VMCOREINFO ELF notes to assist in
debugging. vmcore parsing in user-space already expects this value in
the notes and we are providing it for portability of those existing
tools with x86.

Ideally we would like core code to do this (so that way this
information won't be missed when an architecture adds KASLR support),
but mips has CONFIG_RANDOMIZE_BASE, and doesn't provide kaslr_offset(),
so I am not sure if this is needed for mips (and other such similar arch
cases in future). So, lets keep this architecture specific for now.

As an example of a user-space use-case, consider the
makedumpfile user-space utility which will need fixup to use this
KASLR offset to work with cases where we need to find a way to
translate symbol address from vmlinux to kernel run time address
in case of KASLR boot on arm64.

I have already submitted the makedumpfile user-space patch upstream
and the maintainer has suggested to wait for the kernel changes to be
included (see [0]).

I tested this on my qualcomm amberwing board both for KASLR and
non-KASLR boot cases:

Without this patch:
   # cat > scrub.conf << EOF
   [vmlinux]
   erase jiffies
   erase init_task.utime
   for tsk in init_task.tasks.next within task_struct:tasks
       erase tsk.utime
   endfor
   EOF

  # makedumpfile --split -d 31 -x vmlinux --config scrub.conf vmcore dumpfile_{1,2,3}
  readpage_elf: Attempt to read non-existent page at 0xffffa8a5bf180000.
  readmem: type_addr: 1, addr:ffffa8a5bf180000, size:8
  vaddr_to_paddr_arm64: Can't read pgd
  readmem: Can't convert a virtual address(ffff0000092a542c) to physical
  address.
  readmem: type_addr: 0, addr:ffff0000092a542c, size:390
  check_release: Can't get the address of system_utsname

After this patch check_release() is ok, and also we are able to erase
symbol from vmcore (I checked this with kernel 4.18.0-rc4+):

  # makedumpfile --split -d 31 -x vmlinux --config scrub.conf vmcore dumpfile_{1,2,3}
  The kernel version is not supported.
  The makedumpfile operation may be incomplete.
  Checking for memory holes                         : [100.0 %] \
  Checking for memory holes                         : [100.0 %] |
  Checking foExcluding unnecessary pages                       : [100.0 %]
  \
  Excluding unnecessary pages                       : [100.0 %] \

  The dumpfiles are saved to dumpfile_1, dumpfile_2, and dumpfile_3.

  makedumpfile Completed.

[0] https://www.spinics.net/lists/kexec/msg21195.html

Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>
Acked-by: James Morse <james.morse@arm.com>
Signed-off-by: Bhupesh Sharma <bhsharma@redhat.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/machine_kexec.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index e8c02832b7ad..4c0eb30bfede 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -360,4 +360,5 @@ void arch_crash_save_vmcoreinfo(void)
 						kimage_voffset);
 	vmcoreinfo_append_str("NUMBER(PHYS_OFFSET)=0x%llx\n",
 						PHYS_OFFSET);
+	vmcoreinfo_append_str("KERNELOFFSET=%lx\n", kaslr_offset());
 }
-- 
cgit v1.2.3


From eab1cecc1223378fee700ab6acebf0f39fa6da81 Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 31 Jul 2018 12:02:18 +0100
Subject: arm64: sdei: Mark sdei stack helper functions as static

The SDEI stack helper functions are only used by _on_sdei_stack() and
refer to symbols (e.g. sdei_stack_normal_ptr) that are only defined if
CONFIG_VMAP_STACK=y.

Mark these functions as static, so we don't run into errors at link-time
due to references to undefined symbols. Stick all the parameters onto
the same line whilst we're passing through.

Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/sdei.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/sdei.c b/arch/arm64/kernel/sdei.c
index a94a868f0532..5ba4465e44f0 100644
--- a/arch/arm64/kernel/sdei.c
+++ b/arch/arm64/kernel/sdei.c
@@ -89,8 +89,7 @@ static int init_sdei_stacks(void)
 	return err;
 }
 
-bool on_sdei_normal_stack(unsigned long sp,
-			struct stack_info *info)
+static bool on_sdei_normal_stack(unsigned long sp, struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_normal_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
@@ -107,8 +106,7 @@ bool on_sdei_normal_stack(unsigned long sp,
 	return true;
 }
 
-bool on_sdei_critical_stack(unsigned long sp,
-			struct stack_info *info)
+static bool on_sdei_critical_stack(unsigned long sp, struct stack_info *info)
 {
 	unsigned long low = (unsigned long)raw_cpu_read(sdei_stack_critical_ptr);
 	unsigned long high = low + SDEI_STACK_SIZE;
@@ -125,8 +123,7 @@ bool on_sdei_critical_stack(unsigned long sp,
 	return true;
 }
 
-bool _on_sdei_stack(unsigned long sp,
-		struct stack_info *info)
+bool _on_sdei_stack(unsigned long sp, struct stack_info *info)
 {
 	if (!IS_ENABLED(CONFIG_VMAP_STACK))
 		return false;
-- 
cgit v1.2.3


From dcab90d90935f990407c86b671a7f1ac285d106c Mon Sep 17 00:00:00 2001
From: Will Deacon <will.deacon@arm.com>
Date: Tue, 31 Jul 2018 12:09:03 +0100
Subject: arm64: kexec: Add comment to explain use of __flush_icache_range()

Now that we understand the deadlock arising from flush_icache_range()
on the kexec crash kernel path, add a comment to justify the use of
__flush_icache_range() here.

Reported-by: Dave Kleikamp <dave.kleikamp@oracle.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/machine_kexec.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c
index 4c0eb30bfede..f6a5c6bc1434 100644
--- a/arch/arm64/kernel/machine_kexec.c
+++ b/arch/arm64/kernel/machine_kexec.c
@@ -184,8 +184,15 @@ void machine_kexec(struct kimage *kimage)
 
 	/* Flush the reboot_code_buffer in preparation for its execution. */
 	__flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size);
+
+	/*
+	 * Although we've killed off the secondary CPUs, we don't update
+	 * the online mask if we're handling a crash kernel and consequently
+	 * need to avoid flush_icache_range(), which will attempt to IPI
+	 * the offline CPUs. Therefore, we must use the __* variant here.
+	 */
 	__flush_icache_range((uintptr_t)reboot_code_buffer,
-		arm64_relocate_new_kernel_size);
+			     arm64_relocate_new_kernel_size);
 
 	/* Flush the kimage list and its buffers. */
 	kexec_list_flush(kimage);
-- 
cgit v1.2.3


From 61b229ce2c152e7700ca603c7b86cdd99619db01 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 25 Jul 2018 14:24:02 -0300
Subject: perf trace beauty: Default header_dir to cwd to work without parms

Useful when checking the effects of header synchs for the files it uses
as a input to generate string tables, in retrospect this is how it
should've been done from day 1, not requiring the header_dir to be set
on the Makefile, will change everything later, so that the only parm,
common to all generators will be $(srctree) and $(beauty_outdir).

So, to see what it generates, just call it without any parameters:

  $ tools/perf/trace/beauty/vhost_virtio_ioctl.sh
  static const char *vhost_virtio_ioctl_cmds[] = {
	[0x00] = "SET_FEATURES",
	[0x01] = "SET_OWNER",
	[0x02] = "RESET_OWNER",
	[0x03] = "SET_MEM_TABLE",
	[0x04] = "SET_LOG_BASE",
	[0x07] = "SET_LOG_FD",
	[0x10] = "SET_VRING_NUM",
	[0x11] = "SET_VRING_ADDR",
	[0x12] = "SET_VRING_BASE",
	[0x13] = "SET_VRING_ENDIAN",
	[0x14] = "GET_VRING_ENDIAN",
	[0x20] = "SET_VRING_KICK",
	[0x21] = "SET_VRING_CALL",
	[0x22] = "SET_VRING_ERR",
	[0x23] = "SET_VRING_BUSYLOOP_TIMEOUT",
	[0x24] = "GET_VRING_BUSYLOOP_TIMEOUT",
	[0x30] = "NET_SET_BACKEND",
	[0x40] = "SCSI_SET_ENDPOINT",
	[0x41] = "SCSI_CLEAR_ENDPOINT",
	[0x42] = "SCSI_GET_ABI_VERSION",
	[0x43] = "SCSI_SET_EVENTS_MISSED",
	[0x44] = "SCSI_GET_EVENTS_MISSED",
	[0x60] = "VSOCK_SET_GUEST_CID",
	[0x61] = "VSOCK_SET_RUNNING",
  };
  static const char *vhost_virtio_ioctl_read_cmds[] = {
	[0x00] = "GET_FEATURES",
	[0x12] = "GET_VRING_BASE",
  };
  $

Or:

  $ tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
  static const char *sndrv_pcm_ioctl_cmds[] = {
	[0x00] = "PVERSION",
	[0x01] = "INFO",
	[0x02] = "TSTAMP",
	[0x03] = "TTSTAMP",
	[0x04] = "USER_PVERSION",
	[0x10] = "HW_REFINE",
	[0x11] = "HW_PARAMS",
	[0x12] = "HW_FREE",
	[0x13] = "SW_PARAMS",
	[0x20] = "STATUS",
	[0x21] = "DELAY",
	[0x22] = "HWSYNC",
	[0x23] = "SYNC_PTR",
	[0x24] = "STATUS_EXT",
	[0x32] = "CHANNEL_INFO",
	[0x40] = "PREPARE",
	[0x41] = "RESET",
	[0x42] = "START",
	[0x43] = "DROP",
	[0x44] = "DRAIN",
	[0x45] = "PAUSE",
	[0x46] = "REWIND",
	[0x47] = "RESUME",
	[0x48] = "XRUN",
	[0x49] = "FORWARD",
	[0x50] = "WRITEI_FRAMES",
	[0x51] = "READI_FRAMES",
	[0x52] = "WRITEN_FRAMES",
	[0x53] = "READN_FRAMES",
	[0x60] = "LINK",
	[0x61] = "UNLINK",
  };
  $

Etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-90am4vm8hh1osms894dp2otr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/drm_ioctl.sh                | 9 +++++----
 tools/perf/trace/beauty/kcmp_type.sh                | 2 +-
 tools/perf/trace/beauty/kvm_ioctl.sh                | 4 ++--
 tools/perf/trace/beauty/madvise_behavior.sh         | 2 +-
 tools/perf/trace/beauty/perf_ioctl.sh               | 2 +-
 tools/perf/trace/beauty/pkey_alloc_access_rights.sh | 2 +-
 tools/perf/trace/beauty/sndrv_ctl_ioctl.sh          | 4 ++--
 tools/perf/trace/beauty/sndrv_pcm_ioctl.sh          | 4 ++--
 tools/perf/trace/beauty/vhost_virtio_ioctl.sh       | 6 +++---
 9 files changed, 18 insertions(+), 17 deletions(-)

diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 2149d3a98e42..9d3816815e60 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,13 +1,14 @@
 #!/bin/sh
 
-drm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
+
 printf "#ifndef DRM_COMMAND_BASE\n"
-grep "#define DRM_COMMAND_BASE" $drm_header_dir/drm.h
+grep "#define DRM_COMMAND_BASE" $header_dir/drm.h
 printf "#endif\n"
 
 printf "static const char *drm_ioctl_cmds[] = {\n"
-grep "^#define DRM_IOCTL.*DRM_IO" $drm_header_dir/drm.h | \
+grep "^#define DRM_IOCTL.*DRM_IO" $header_dir/drm.h | \
 	sed -r 's/^#define +DRM_IOCTL_([A-Z0-9_]+)[	 ]+DRM_IO[A-Z]* *\( *(0x[[:xdigit:]]+),*.*/	[\2] = "\1",/g'
-grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $drm_header_dir/i915_drm.h | \
+grep "^#define DRM_I915_[A-Z_0-9]\+[	 ]\+0x" $header_dir/i915_drm.h | \
 	sed -r 's/^#define +DRM_I915_([A-Z0-9_]+)[	 ]+(0x[[:xdigit:]]+)/\t[DRM_COMMAND_BASE + \2] = "I915_\1",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index 40d063b8c082..a3c304caa336 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kcmp_types[] = {\n"
 regex='^[[:space:]]+(KCMP_(\w+)),'
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index bd28817afced..c4699fd46bb6 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,10 +1,10 @@
 #!/bin/sh
 
-kvm_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *kvm_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+KVM_(\w+)[[:space:]]+_IO[RW]*\([[:space:]]*KVMIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${kvm_header_dir}/kvm.h	| \
+egrep $regex ${header_dir}/kvm.h	| \
 	sed -r "s/$regex/\2 \1/g"	| \
 	egrep -v " ((ARM|PPC|S390)_|[GS]ET_(DEBUGREGS|PIT2|XSAVE|TSC_KHZ)|CREATE_SPAPR_TCE_64)" | \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 60ef8640ee70..431639eb4d29 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *madvise_advices[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MADV_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index faea4237c793..6492c74df928 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *perf_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+PERF_EVENT_IOC_(\w+)[[:space:]]+_IO[RW]*[[:space:]]*\([[:space:]]*.\$.[[:space:]]*,[[:space:]]*([[:digit:]]+).*'
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index 62e51a02b839..e0a51aeb20b2 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,6 +1,6 @@
 #!/bin/sh
 
-header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
 printf "static const char *pkey_alloc_access_rights[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+PKEY_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*'
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index aad5ab130539..eb511bb5fbd3 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index b7e9ef6b2f55..6818392968b2 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,8 +1,8 @@
 #!/bin/sh
 
-sound_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $sound_header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 76f1de697787..0f6a5197d0be 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,17 +1,17 @@
 #!/bin/sh
 
-vhost_virtio_header_dir=$1
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-egrep $regex ${vhost_virtio_header_dir}/vhost.h | \
+egrep $regex ${header_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
-- 
cgit v1.2.3


From 95035c5e167ae6e740b1ddd30210ae0eaf39a5db Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Mon, 9 Jul 2018 07:15:22 -0700
Subject: perf evlist: Fix error out while applying initial delay and LBR

'perf record' will error out if both --delay and LBR are applied.

For example:

  # perf record -D 1000 -a -e cycles -j any -- sleep 2
  Error:
  dummy:HG: PMU Hardware doesn't support sampling/overflow-interrupts.
  Try 'perf stat'
  #

A dummy event is added implicitly for initial delay, which has the same
configurations as real sampling events. The dummy event is a software
event. If LBR is configured, perf must error out.

The dummy event will only be used to track PERF_RECORD_MMAP while perf
waits for the initial delay to enable the real events. The BRANCH_STACK
bit can be safely cleared for the dummy event.

After applying the patch:

  # perf record -D 1000 -a -e cycles -j any -- sleep 2
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 1.054 MB perf.data (828 samples) ]
  #

Reported-by: Sunil K Pandey <sunil.k.pandey@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1531145722-16404-1-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/evsel.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5285da0417c5..ddf84b941abf 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -859,6 +859,12 @@ static void apply_config_terms(struct perf_evsel *evsel,
 	}
 }
 
+static bool is_dummy_event(struct perf_evsel *evsel)
+{
+	return (evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+	       (evsel->attr.config == PERF_COUNT_SW_DUMMY);
+}
+
 /*
  * The enable_on_exec/disabled value strategy:
  *
@@ -1097,6 +1103,14 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,
 		else
 			perf_evsel__reset_sample_bit(evsel, PERIOD);
 	}
+
+	/*
+	 * For initial_delay, a dummy event is added implicitly.
+	 * The software event will trigger -EOPNOTSUPP error out,
+	 * if BRANCH_STACK bit is set.
+	 */
+	if (opts->initial_delay && is_dummy_event(evsel))
+		perf_evsel__reset_sample_bit(evsel, BRANCH_STACK);
 }
 
 static int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
-- 
cgit v1.2.3


From 11785ef53228d23ec386f5fe4a34601536f0c891 Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Tue, 31 Jul 2018 13:28:42 +0100
Subject: ALSA: usb-audio: Initial Power Domain support

Thee USB Audio Class 3 (UAC3) introduces Power Domains as a new
feature to let a host turn individual parts of an audio function
to different power states via USB requests. This lets the device
get to know a bit amore about what the host is up to in order to
optimize power consumption efficiently.

The Power Domains are optional for UAC3 configuration but all
UAC3 devices shall include at least one BADD configuration where
the support for Power Domains is compulsory.

This patch adds a set of features/helpers to parse these power
domains and change their status.

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/linux/usb/audio-v3.h |   4 ++
 sound/usb/Makefile           |   1 +
 sound/usb/power.c            | 104 +++++++++++++++++++++++++++++++++++++++++++
 sound/usb/power.h            |  19 ++++++++
 4 files changed, 128 insertions(+)
 create mode 100644 sound/usb/power.c

diff --git a/include/linux/usb/audio-v3.h b/include/linux/usb/audio-v3.h
index 334bfa6dfb47..6b708434b7f9 100644
--- a/include/linux/usb/audio-v3.h
+++ b/include/linux/usb/audio-v3.h
@@ -447,4 +447,8 @@ struct uac3_interrupt_data_msg {
 /* BADD sample rate is always fixed to 48kHz */
 #define UAC3_BADD_SAMPLING_RATE				48000
 
+/* BADD power domains recovery times in 50us increments */
+#define UAC3_BADD_PD_RECOVER_D1D0			0x0258	/* 30ms */
+#define UAC3_BADD_PD_RECOVER_D2D0			0x1770	/* 300ms */
+
 #endif /* __LINUX_USB_AUDIO_V3_H */
diff --git a/sound/usb/Makefile b/sound/usb/Makefile
index 05440e2df8d9..d330f74c90e6 100644
--- a/sound/usb/Makefile
+++ b/sound/usb/Makefile
@@ -13,6 +13,7 @@ snd-usb-audio-objs := 	card.o \
 			mixer_scarlett.o \
 			mixer_us16x08.o \
 			pcm.o \
+			power.o \
 			proc.o \
 			quirks.o \
 			stream.o
diff --git a/sound/usb/power.c b/sound/usb/power.c
new file mode 100644
index 000000000000..bd303a1ba1b7
--- /dev/null
+++ b/sound/usb/power.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *   UAC3 Power Domain state management functions
+ */
+
+#include <linux/slab.h>
+#include <linux/usb.h>
+#include <linux/usb/audio.h>
+#include <linux/usb/audio-v2.h>
+#include <linux/usb/audio-v3.h>
+
+#include "usbaudio.h"
+#include "helper.h"
+#include "power.h"
+
+struct snd_usb_power_domain *
+snd_usb_find_power_domain(struct usb_host_interface *ctrl_iface,
+			  unsigned char id)
+{
+	struct snd_usb_power_domain *pd;
+	void *p;
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return NULL;
+
+	p = NULL;
+	while ((p = snd_usb_find_csint_desc(ctrl_iface->extra,
+					    ctrl_iface->extralen,
+					    p, UAC3_POWER_DOMAIN)) != NULL) {
+		struct uac3_power_domain_descriptor *pd_desc = p;
+		int i;
+
+		for (i = 0; i < pd_desc->bNrEntities; i++) {
+			if (pd_desc->baEntityID[i] == id) {
+				pd->pd_id = pd_desc->bPowerDomainID;
+				pd->pd_d1d0_rec =
+					le16_to_cpu(pd_desc->waRecoveryTime1);
+				pd->pd_d2d0_rec =
+					le16_to_cpu(pd_desc->waRecoveryTime2);
+				return pd;
+			}
+		}
+	}
+
+	kfree(pd);
+	return NULL;
+}
+
+int snd_usb_power_domain_set(struct snd_usb_audio *chip,
+			     struct snd_usb_power_domain *pd,
+			     unsigned char state)
+{
+	struct usb_device *dev = chip->dev;
+	unsigned char current_state;
+	int err, idx;
+
+	idx = snd_usb_ctrl_intf(chip) | (pd->pd_id << 8);
+
+	err = snd_usb_ctl_msg(chip->dev, usb_rcvctrlpipe(chip->dev, 0),
+			      UAC2_CS_CUR,
+			      USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_IN,
+			      UAC3_AC_POWER_DOMAIN_CONTROL << 8, idx,
+			      &current_state, sizeof(current_state));
+	if (err < 0) {
+		dev_err(&dev->dev, "Can't get UAC3 power state for id %d\n",
+			pd->pd_id);
+		return err;
+	}
+
+	if (current_state == state) {
+		dev_dbg(&dev->dev, "UAC3 power domain id %d already in state %d\n",
+			pd->pd_id, state);
+		return 0;
+	}
+
+	err = snd_usb_ctl_msg(chip->dev, usb_sndctrlpipe(chip->dev, 0), UAC2_CS_CUR,
+			      USB_RECIP_INTERFACE | USB_TYPE_CLASS | USB_DIR_OUT,
+			      UAC3_AC_POWER_DOMAIN_CONTROL << 8, idx,
+			      &state, sizeof(state));
+	if (err < 0) {
+		dev_err(&dev->dev, "Can't set UAC3 power state to %d for id %d\n",
+			state, pd->pd_id);
+		return err;
+	}
+
+	if (state == UAC3_PD_STATE_D0) {
+		switch (current_state) {
+		case UAC3_PD_STATE_D2:
+			udelay(pd->pd_d2d0_rec * 50);
+			break;
+		case UAC3_PD_STATE_D1:
+			udelay(pd->pd_d1d0_rec * 50);
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	dev_dbg(&dev->dev, "UAC3 power domain id %d change to state %d\n",
+		pd->pd_id, state);
+
+	return 0;
+}
diff --git a/sound/usb/power.h b/sound/usb/power.h
index b2e25f60c5a2..6004231a7c75 100644
--- a/sound/usb/power.h
+++ b/sound/usb/power.h
@@ -2,6 +2,25 @@
 #ifndef __USBAUDIO_POWER_H
 #define __USBAUDIO_POWER_H
 
+struct snd_usb_power_domain {
+	int pd_id;              /* UAC3 Power Domain ID */
+	int pd_d1d0_rec;        /* D1 to D0 recovery time */
+	int pd_d2d0_rec;        /* D2 to D0 recovery time */
+};
+
+enum {
+	UAC3_PD_STATE_D0,
+	UAC3_PD_STATE_D1,
+	UAC3_PD_STATE_D2,
+};
+
+int snd_usb_power_domain_set(struct snd_usb_audio *chip,
+			     struct snd_usb_power_domain *pd,
+			     unsigned char state);
+struct snd_usb_power_domain *
+snd_usb_find_power_domain(struct usb_host_interface *ctrl_iface,
+			  unsigned char id);
+
 #ifdef CONFIG_PM
 int snd_usb_autoresume(struct snd_usb_audio *chip);
 void snd_usb_autosuspend(struct snd_usb_audio *chip);
-- 
cgit v1.2.3


From 7edf3b5e6a4544b42d3572a7058f8ffe96349ee8 Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Tue, 31 Jul 2018 13:28:43 +0100
Subject: ALSA: usb-audio: AudioStreaming Power Domain parsing

Power Domains in the UAC3 spec are mainly intended to be
associated to an Input or Output Terminal so the host
changes the power state of the entire capture or playback
path within the topology.

This patch adds support for finding Power Domains associated
to an Audio Streaming Interface (bTerminalLink) and adds a
reference to them in the usb audio substreams (snd_usb_substream).

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/card.h   |  2 ++
 sound/usb/stream.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++-------
 2 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/sound/usb/card.h b/sound/usb/card.h
index 9b41b7dda84f..ac785d15ced4 100644
--- a/sound/usb/card.h
+++ b/sound/usb/card.h
@@ -37,6 +37,7 @@ struct audioformat {
 
 struct snd_usb_substream;
 struct snd_usb_endpoint;
+struct snd_usb_power_domain;
 
 struct snd_urb_ctx {
 	struct urb *urb;
@@ -115,6 +116,7 @@ struct snd_usb_substream {
 	int interface;	/* current interface */
 	int endpoint;	/* assigned endpoint */
 	struct audioformat *cur_audiofmt;	/* current audioformat pointer (for hw_params callback) */
+	struct snd_usb_power_domain *str_pd;	/* UAC3 Power Domain for streaming path */
 	snd_pcm_format_t pcm_format;	/* current audio format (for hw_params callback) */
 	unsigned int channels;		/* current number of channels (for hw_params callback) */
 	unsigned int channels_max;	/* max channels in the all audiofmts */
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 729afd808cc4..c0567fa1e84b 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -37,6 +37,7 @@
 #include "format.h"
 #include "clock.h"
 #include "stream.h"
+#include "power.h"
 
 /*
  * free a substream
@@ -53,6 +54,7 @@ static void free_substream(struct snd_usb_substream *subs)
 		kfree(fp);
 	}
 	kfree(subs->rate_list.list);
+	kfree(subs->str_pd);
 }
 
 
@@ -82,7 +84,8 @@ static void snd_usb_audio_pcm_free(struct snd_pcm *pcm)
 
 static void snd_usb_init_substream(struct snd_usb_stream *as,
 				   int stream,
-				   struct audioformat *fp)
+				   struct audioformat *fp,
+				   struct snd_usb_power_domain *pd)
 {
 	struct snd_usb_substream *subs = &as->substream[stream];
 
@@ -107,6 +110,9 @@ static void snd_usb_init_substream(struct snd_usb_stream *as,
 	if (fp->channels > subs->channels_max)
 		subs->channels_max = fp->channels;
 
+	if (pd)
+		subs->str_pd = pd;
+
 	snd_usb_preallocate_buffer(subs);
 }
 
@@ -468,9 +474,11 @@ snd_pcm_chmap_elem *convert_chmap_v3(struct uac3_cluster_header_descriptor
  * fmt_list and will be freed on the chip instance release. do not free
  * fp or do remove it from the substream fmt_list to avoid double-free.
  */
-int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
-			     int stream,
-			     struct audioformat *fp)
+static int __snd_usb_add_audio_stream(struct snd_usb_audio *chip,
+				      int stream,
+				      struct audioformat *fp,
+				      struct snd_usb_power_domain *pd)
+
 {
 	struct snd_usb_stream *as;
 	struct snd_usb_substream *subs;
@@ -498,7 +506,7 @@ int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 		err = snd_pcm_new_stream(as->pcm, stream, 1);
 		if (err < 0)
 			return err;
-		snd_usb_init_substream(as, stream, fp);
+		snd_usb_init_substream(as, stream, fp, pd);
 		return add_chmap(as->pcm, stream, subs);
 	}
 
@@ -526,7 +534,7 @@ int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 	else
 		strcpy(pcm->name, "USB Audio");
 
-	snd_usb_init_substream(as, stream, fp);
+	snd_usb_init_substream(as, stream, fp, pd);
 
 	/*
 	 * Keep using head insertion for M-Audio Audiophile USB (tm) which has a
@@ -544,6 +552,21 @@ int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
 	return add_chmap(pcm, stream, &as->substream[stream]);
 }
 
+int snd_usb_add_audio_stream(struct snd_usb_audio *chip,
+			     int stream,
+			     struct audioformat *fp)
+{
+	return __snd_usb_add_audio_stream(chip, stream, fp, NULL);
+}
+
+static int snd_usb_add_audio_stream_v3(struct snd_usb_audio *chip,
+				       int stream,
+				       struct audioformat *fp,
+				       struct snd_usb_power_domain *pd)
+{
+	return __snd_usb_add_audio_stream(chip, stream, fp, pd);
+}
+
 static int parse_uac_endpoint_attributes(struct snd_usb_audio *chip,
 					 struct usb_host_interface *alts,
 					 int protocol, int iface_no)
@@ -819,6 +842,7 @@ found_clock:
 static struct audioformat *
 snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip,
 			     struct usb_host_interface *alts,
+			     struct snd_usb_power_domain **pd_out,
 			     int iface_no, int altset_idx,
 			     int altno, int stream)
 {
@@ -829,6 +853,7 @@ snd_usb_get_audioformat_uac3(struct snd_usb_audio *chip,
 	struct uac3_as_header_descriptor *as = NULL;
 	struct uac3_hc_descriptor_header hc_header;
 	struct snd_pcm_chmap_elem *chmap;
+	struct snd_usb_power_domain *pd;
 	unsigned char badd_profile;
 	u64 badd_formats = 0;
 	unsigned int num_channels;
@@ -1008,12 +1033,28 @@ found_clock:
 		fp->rate_max = UAC3_BADD_SAMPLING_RATE;
 		fp->rates = SNDRV_PCM_RATE_CONTINUOUS;
 
+		pd = kzalloc(sizeof(pd), GFP_KERNEL);
+		if (!pd) {
+			kfree(fp->rate_table);
+			kfree(fp);
+			return NULL;
+		}
+		pd->pd_id = (stream == SNDRV_PCM_STREAM_PLAYBACK) ?
+					UAC3_BADD_PD_ID10 : UAC3_BADD_PD_ID11;
+		pd->pd_d1d0_rec = UAC3_BADD_PD_RECOVER_D1D0;
+		pd->pd_d2d0_rec = UAC3_BADD_PD_RECOVER_D2D0;
+
 	} else {
 		fp->attributes = parse_uac_endpoint_attributes(chip, alts,
 							       UAC_VERSION_3,
 							       iface_no);
+
+		pd = snd_usb_find_power_domain(chip->ctrl_intf,
+					       as->bTerminalLink);
+
 		/* ok, let's parse further... */
 		if (snd_usb_parse_audio_format_v3(chip, fp, as, stream) < 0) {
+			kfree(pd);
 			kfree(fp->chmap);
 			kfree(fp->rate_table);
 			kfree(fp);
@@ -1021,6 +1062,9 @@ found_clock:
 		}
 	}
 
+	if (pd)
+		*pd_out = pd;
+
 	return fp;
 }
 
@@ -1032,6 +1076,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 	struct usb_interface_descriptor *altsd;
 	int i, altno, err, stream;
 	struct audioformat *fp = NULL;
+	struct snd_usb_power_domain *pd = NULL;
 	int num, protocol;
 
 	dev = chip->dev;
@@ -1114,7 +1159,7 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 			break;
 		}
 		case UAC_VERSION_3:
-			fp = snd_usb_get_audioformat_uac3(chip, alts,
+			fp = snd_usb_get_audioformat_uac3(chip, alts, &pd,
 						iface_no, i, altno, stream);
 			break;
 		}
@@ -1125,9 +1170,14 @@ int snd_usb_parse_audio_interface(struct snd_usb_audio *chip, int iface_no)
 			return PTR_ERR(fp);
 
 		dev_dbg(&dev->dev, "%u:%d: add audio endpoint %#x\n", iface_no, altno, fp->endpoint);
-		err = snd_usb_add_audio_stream(chip, stream, fp);
+		if (protocol == UAC_VERSION_3)
+			err = snd_usb_add_audio_stream_v3(chip, stream, fp, pd);
+		else
+			err = snd_usb_add_audio_stream(chip, stream, fp);
+
 		if (err < 0) {
 			list_del(&fp->list); /* unlink for avoiding double-free */
+			kfree(pd);
 			kfree(fp->rate_table);
 			kfree(fp->chmap);
 			kfree(fp);
-- 
cgit v1.2.3


From 3f59aa11c6776da8d0f9f50c741ef02bfc4a8766 Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Tue, 31 Jul 2018 13:28:44 +0100
Subject: ALSA: usb-audio: Add UAC3 Power Domains to suspend/resume

Set the UAC3 Power Domain state for an Audio Streaming interface
to D2 state before suspending the device (usb_driver callback).
This lets the device know there is no intention to use any of the
Units in the Audio Function and that the host is not going to
even listen for wake-up events (interrupts) on the units.

When the usb_driver gets resumed, the state D0 (fully powered) will
be set. This ties up the UAC3 Power Domains to the runtime PM.

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/card.c |  9 +++++++++
 sound/usb/pcm.c  | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 sound/usb/pcm.h  |  2 ++
 3 files changed, 59 insertions(+)

diff --git a/sound/usb/card.c b/sound/usb/card.c
index a1ed798a1c6b..2bfe4e80a6b9 100644
--- a/sound/usb/card.c
+++ b/sound/usb/card.c
@@ -809,6 +809,7 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 	if (!chip->num_suspended_intf++) {
 		list_for_each_entry(as, &chip->pcm_list, list) {
 			snd_pcm_suspend_all(as->pcm);
+			snd_usb_pcm_suspend(as);
 			as->substream[0].need_setup_ep =
 				as->substream[1].need_setup_ep = true;
 		}
@@ -824,6 +825,7 @@ static int usb_audio_suspend(struct usb_interface *intf, pm_message_t message)
 static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 {
 	struct snd_usb_audio *chip = usb_get_intfdata(intf);
+	struct snd_usb_stream *as;
 	struct usb_mixer_interface *mixer;
 	struct list_head *p;
 	int err = 0;
@@ -834,6 +836,13 @@ static int __usb_audio_resume(struct usb_interface *intf, bool reset_resume)
 		return 0;
 
 	atomic_inc(&chip->active); /* avoid autopm */
+
+	list_for_each_entry(as, &chip->pcm_list, list) {
+		err = snd_usb_pcm_resume(as);
+		if (err < 0)
+			goto err_out;
+	}
+
 	/*
 	 * ALSA leaves material resumption to user space
 	 * we just notify and restart the mixers
diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 4b930fa47277..99ec9d5caa58 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -711,6 +711,54 @@ static int configure_endpoint(struct snd_usb_substream *subs)
 	return ret;
 }
 
+static int snd_usb_pcm_change_state(struct snd_usb_substream *subs, int state)
+{
+	int ret;
+
+	if (!subs->str_pd)
+		return 0;
+
+	ret = snd_usb_power_domain_set(subs->stream->chip, subs->str_pd, state);
+	if (ret < 0) {
+		dev_err(&subs->dev->dev,
+			"Cannot change Power Domain ID: %d to state: %d. Err: %d\n",
+			subs->str_pd->pd_id, state, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+int snd_usb_pcm_suspend(struct snd_usb_stream *as)
+{
+	int ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[0], UAC3_PD_STATE_D2);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[1], UAC3_PD_STATE_D2);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+int snd_usb_pcm_resume(struct snd_usb_stream *as)
+{
+	int ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[0], UAC3_PD_STATE_D0);
+	if (ret < 0)
+		return ret;
+
+	ret = snd_usb_pcm_change_state(&as->substream[1], UAC3_PD_STATE_D0);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
 /*
  * hw_params callback
  *
diff --git a/sound/usb/pcm.h b/sound/usb/pcm.h
index f77ec58bf1a1..9833627c1eca 100644
--- a/sound/usb/pcm.h
+++ b/sound/usb/pcm.h
@@ -6,6 +6,8 @@ snd_pcm_uframes_t snd_usb_pcm_delay(struct snd_usb_substream *subs,
 				    unsigned int rate);
 
 void snd_usb_set_pcm_ops(struct snd_pcm *pcm, int stream);
+int snd_usb_pcm_suspend(struct snd_usb_stream *as);
+int snd_usb_pcm_resume(struct snd_usb_stream *as);
 
 int snd_usb_init_pitch(struct snd_usb_audio *chip, int iface,
 		       struct usb_host_interface *alts,
-- 
cgit v1.2.3


From a0a4959eb4e94ce98ee5549dd7d1296d41162ca8 Mon Sep 17 00:00:00 2001
From: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Date: Tue, 31 Jul 2018 13:28:45 +0100
Subject: ALSA: usb-audio: Operate UAC3 Power Domains in PCM callbacks

Make use of UAC3 Power Domains associated to an Audio Streaming
path within the PCM's logic. This means, when there is no audio
being transferred (pcm is closed), the host will set the Power Domain
associated to that substream to state D1. When audio is being transferred
(from hw_params onwards), the Power Domain will be set to D0 state.

This is the way the host lets the device know which Terminal
is going to be actively used and it is for the device to
manage its own internal resources on that UAC3 Power Domain.

Note the resume method now sets the Power Domain to D1 state as
resuming the device doesn't mean audio streaming will occur.

Signed-off-by: Jorge Sanjuan <jorge.sanjuan@codethink.co.uk>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/pcm.c    | 24 +++++++++++++++++++-----
 sound/usb/stream.c |  6 +++++-
 2 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index 99ec9d5caa58..bbc7116c9543 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -748,11 +748,11 @@ int snd_usb_pcm_resume(struct snd_usb_stream *as)
 {
 	int ret;
 
-	ret = snd_usb_pcm_change_state(&as->substream[0], UAC3_PD_STATE_D0);
+	ret = snd_usb_pcm_change_state(&as->substream[0], UAC3_PD_STATE_D1);
 	if (ret < 0)
 		return ret;
 
-	ret = snd_usb_pcm_change_state(&as->substream[1], UAC3_PD_STATE_D0);
+	ret = snd_usb_pcm_change_state(&as->substream[1], UAC3_PD_STATE_D1);
 	if (ret < 0)
 		return ret;
 
@@ -803,16 +803,22 @@ static int snd_usb_hw_params(struct snd_pcm_substream *substream,
 	ret = snd_usb_lock_shutdown(subs->stream->chip);
 	if (ret < 0)
 		return ret;
+
+	ret = snd_usb_pcm_change_state(subs, UAC3_PD_STATE_D0);
+	if (ret < 0)
+		goto unlock;
+
 	ret = set_format(subs, fmt);
-	snd_usb_unlock_shutdown(subs->stream->chip);
 	if (ret < 0)
-		return ret;
+		goto unlock;
 
 	subs->interface = fmt->iface;
 	subs->altset_idx = fmt->altset_idx;
 	subs->need_setup_ep = true;
 
-	return 0;
+ unlock:
+	snd_usb_unlock_shutdown(subs->stream->chip);
+	return ret;
 }
 
 /*
@@ -869,6 +875,10 @@ static int snd_usb_pcm_prepare(struct snd_pcm_substream *substream)
 	snd_usb_endpoint_sync_pending_stop(subs->sync_endpoint);
 	snd_usb_endpoint_sync_pending_stop(subs->data_endpoint);
 
+	ret = snd_usb_pcm_change_state(subs, UAC3_PD_STATE_D0);
+	if (ret < 0)
+		goto unlock;
+
 	ret = set_format(subs, subs->cur_audiofmt);
 	if (ret < 0)
 		goto unlock;
@@ -1313,6 +1323,7 @@ static int snd_usb_pcm_close(struct snd_pcm_substream *substream)
 	int direction = substream->stream;
 	struct snd_usb_stream *as = snd_pcm_substream_chip(substream);
 	struct snd_usb_substream *subs = &as->substream[direction];
+	int ret;
 
 	stop_endpoints(subs, true);
 
@@ -1321,7 +1332,10 @@ static int snd_usb_pcm_close(struct snd_pcm_substream *substream)
 	    !snd_usb_lock_shutdown(subs->stream->chip)) {
 		usb_set_interface(subs->dev, subs->interface, 0);
 		subs->interface = -1;
+		ret = snd_usb_pcm_change_state(subs, UAC3_PD_STATE_D1);
 		snd_usb_unlock_shutdown(subs->stream->chip);
+		if (ret < 0)
+			return ret;
 	}
 
 	subs->pcm_substream = NULL;
diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index c0567fa1e84b..8fe3b0e00e45 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -110,8 +110,12 @@ static void snd_usb_init_substream(struct snd_usb_stream *as,
 	if (fp->channels > subs->channels_max)
 		subs->channels_max = fp->channels;
 
-	if (pd)
+	if (pd) {
 		subs->str_pd = pd;
+		/* Initialize Power Domain to idle status D1 */
+		snd_usb_power_domain_set(subs->stream->chip, pd,
+					 UAC3_PD_STATE_D1);
+	}
 
 	snd_usb_preallocate_buffer(subs);
 }
-- 
cgit v1.2.3


From a6f39cecf71537d105f4bf87b8d4760851960838 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Thu, 26 Jul 2018 16:25:02 +0530
Subject: perf tests: Fix complex event name parsing

The 'umask' event parameter is unsupported on some architectures like
powerpc64.

This can be observed on a powerpc64le system running Fedora 27 as shown
below.

  # perf test "Parse event definition strings" -v
   6: Parse event definition strings                        :
  --- start ---
  test child forked, pid 45915
  ...
  running test 3 'cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp'Invalid event/parameter 'umask'
  Invalid event/parameter 'umask'
  failed to parse event 'cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp', err 1, str 'unknown term'
  event syntax error: '..,event=0x2,umask=0x3/ukp'
                                    \___ unknown term

  valid terms: event,mark,pmc,cache_sel,pmcxsel,unit,thresh_stop,thresh_start,combine,thresh_sel,thresh_cmp,sample_mode,config,config1,config2,name,period,freq,branch_type,time,call-graph,stack-size,no-inherit,inherit,max-stack,no-overwrite,overwrite,driver-config

  mem_access -> cpu/event=0x10401e0/
  running test 0 'config=10,config1,config2=3,umask=1'
  test child finished with 1
  ---- end ----
  Parse event definition strings: FAILED!

Committer testing:

After applying the patch these test passes and in verbose mode we get:

  # perf test -v "event definition"
   6: Parse event definition strings:
  --- start ---
  test child forked, pid 11061
  running test 0 'syscalls:sys_enter_openat'Using CPUID GenuineIntel-6-9E
  <SNIP>
  running test 53 'cycles/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks'/Duk'
  running test 0 'cpu/config=10,config1,config2=3,period=1000/u'
  running test 1 'cpu/config=1,name=krava/u,cpu/config=2/u'
  running test 2 'cpu/config=1,call-graph=fp,time,period=100000/,cpu/config=2,call-graph=no,time=0,period=2000/'
  running test 3 'cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp'
  <SNIP>
  test child finished with 0
  ---- end ----
  Parse event definition strings: Ok
  #

Suggested-by: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Fixes: 06dc5bf21f3f ("perf tests: Check that complex event name is parsed correctly")
Link: http://lkml.kernel.org/r/20180726105502.31670-1-sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/parse-events.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index a36313daec4e..3b97ac018d5a 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -1690,7 +1690,7 @@ static struct evlist_test test__events_pmu[] = {
 		.id    = 2,
 	},
 	{
-		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2,umask=0x3/ukp",
+		.name  = "cpu/name='COMPLEX_CYCLES_NAME:orig=cycles,desc=chip-clock-ticks',period=0x1,event=0x2/ukp",
 		.check = test__checkevent_complex_name,
 		.id    = 3,
 	}
-- 
cgit v1.2.3


From a4b2061242ecc024b1ee975e066b6e38db1c6b9e Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 26 Jul 2018 09:26:13 -0300
Subject: tools include uapi: Grab a copy of linux/in.h

We'll use it to create tables for the 'protocol' argument to the
socket syscall when the 'family' arg is one of AF_INET or AF_INET6.

Add it to check_headers.sh so that when a new protocol gets added we get
a notification during the build process.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2amnveu1ns4emjn70xuavpje@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/in.h | 301 ++++++++++++++++++++++++++++++++++++++++++
 tools/perf/check-headers.sh   |   1 +
 2 files changed, 302 insertions(+)
 create mode 100644 tools/include/uapi/linux/in.h

diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
new file mode 100644
index 000000000000..48e8a225b985
--- /dev/null
+++ b/tools/include/uapi/linux/in.h
@@ -0,0 +1,301 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Definitions of the Internet Protocol.
+ *
+ * Version:	@(#)in.h	1.0.1	04/21/93
+ *
+ * Authors:	Original taken from the GNU Project <netinet/in.h> file.
+ *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_LINUX_IN_H
+#define _UAPI_LINUX_IN_H
+
+#include <linux/types.h>
+#include <linux/libc-compat.h>
+#include <linux/socket.h>
+
+#if __UAPI_DEF_IN_IPPROTO
+/* Standard well-defined IP protocols.  */
+enum {
+  IPPROTO_IP = 0,		/* Dummy protocol for TCP		*/
+#define IPPROTO_IP		IPPROTO_IP
+  IPPROTO_ICMP = 1,		/* Internet Control Message Protocol	*/
+#define IPPROTO_ICMP		IPPROTO_ICMP
+  IPPROTO_IGMP = 2,		/* Internet Group Management Protocol	*/
+#define IPPROTO_IGMP		IPPROTO_IGMP
+  IPPROTO_IPIP = 4,		/* IPIP tunnels (older KA9Q tunnels use 94) */
+#define IPPROTO_IPIP		IPPROTO_IPIP
+  IPPROTO_TCP = 6,		/* Transmission Control Protocol	*/
+#define IPPROTO_TCP		IPPROTO_TCP
+  IPPROTO_EGP = 8,		/* Exterior Gateway Protocol		*/
+#define IPPROTO_EGP		IPPROTO_EGP
+  IPPROTO_PUP = 12,		/* PUP protocol				*/
+#define IPPROTO_PUP		IPPROTO_PUP
+  IPPROTO_UDP = 17,		/* User Datagram Protocol		*/
+#define IPPROTO_UDP		IPPROTO_UDP
+  IPPROTO_IDP = 22,		/* XNS IDP protocol			*/
+#define IPPROTO_IDP		IPPROTO_IDP
+  IPPROTO_TP = 29,		/* SO Transport Protocol Class 4	*/
+#define IPPROTO_TP		IPPROTO_TP
+  IPPROTO_DCCP = 33,		/* Datagram Congestion Control Protocol */
+#define IPPROTO_DCCP		IPPROTO_DCCP
+  IPPROTO_IPV6 = 41,		/* IPv6-in-IPv4 tunnelling		*/
+#define IPPROTO_IPV6		IPPROTO_IPV6
+  IPPROTO_RSVP = 46,		/* RSVP Protocol			*/
+#define IPPROTO_RSVP		IPPROTO_RSVP
+  IPPROTO_GRE = 47,		/* Cisco GRE tunnels (rfc 1701,1702)	*/
+#define IPPROTO_GRE		IPPROTO_GRE
+  IPPROTO_ESP = 50,		/* Encapsulation Security Payload protocol */
+#define IPPROTO_ESP		IPPROTO_ESP
+  IPPROTO_AH = 51,		/* Authentication Header protocol	*/
+#define IPPROTO_AH		IPPROTO_AH
+  IPPROTO_MTP = 92,		/* Multicast Transport Protocol		*/
+#define IPPROTO_MTP		IPPROTO_MTP
+  IPPROTO_BEETPH = 94,		/* IP option pseudo header for BEET	*/
+#define IPPROTO_BEETPH		IPPROTO_BEETPH
+  IPPROTO_ENCAP = 98,		/* Encapsulation Header			*/
+#define IPPROTO_ENCAP		IPPROTO_ENCAP
+  IPPROTO_PIM = 103,		/* Protocol Independent Multicast	*/
+#define IPPROTO_PIM		IPPROTO_PIM
+  IPPROTO_COMP = 108,		/* Compression Header Protocol		*/
+#define IPPROTO_COMP		IPPROTO_COMP
+  IPPROTO_SCTP = 132,		/* Stream Control Transport Protocol	*/
+#define IPPROTO_SCTP		IPPROTO_SCTP
+  IPPROTO_UDPLITE = 136,	/* UDP-Lite (RFC 3828)			*/
+#define IPPROTO_UDPLITE		IPPROTO_UDPLITE
+  IPPROTO_MPLS = 137,		/* MPLS in IP (RFC 4023)		*/
+#define IPPROTO_MPLS		IPPROTO_MPLS
+  IPPROTO_RAW = 255,		/* Raw IP packets			*/
+#define IPPROTO_RAW		IPPROTO_RAW
+  IPPROTO_MAX
+};
+#endif
+
+#if __UAPI_DEF_IN_ADDR
+/* Internet address. */
+struct in_addr {
+	__be32	s_addr;
+};
+#endif
+
+#define IP_TOS		1
+#define IP_TTL		2
+#define IP_HDRINCL	3
+#define IP_OPTIONS	4
+#define IP_ROUTER_ALERT	5
+#define IP_RECVOPTS	6
+#define IP_RETOPTS	7
+#define IP_PKTINFO	8
+#define IP_PKTOPTIONS	9
+#define IP_MTU_DISCOVER	10
+#define IP_RECVERR	11
+#define IP_RECVTTL	12
+#define	IP_RECVTOS	13
+#define IP_MTU		14
+#define IP_FREEBIND	15
+#define IP_IPSEC_POLICY	16
+#define IP_XFRM_POLICY	17
+#define IP_PASSSEC	18
+#define IP_TRANSPARENT	19
+
+/* BSD compatibility */
+#define IP_RECVRETOPTS	IP_RETOPTS
+
+/* TProxy original addresses */
+#define IP_ORIGDSTADDR       20
+#define IP_RECVORIGDSTADDR   IP_ORIGDSTADDR
+
+#define IP_MINTTL       21
+#define IP_NODEFRAG     22
+#define IP_CHECKSUM	23
+#define IP_BIND_ADDRESS_NO_PORT	24
+#define IP_RECVFRAGSIZE	25
+
+/* IP_MTU_DISCOVER values */
+#define IP_PMTUDISC_DONT		0	/* Never send DF frames */
+#define IP_PMTUDISC_WANT		1	/* Use per route hints	*/
+#define IP_PMTUDISC_DO			2	/* Always DF		*/
+#define IP_PMTUDISC_PROBE		3       /* Ignore dst pmtu      */
+/* Always use interface mtu (ignores dst pmtu) but don't set DF flag.
+ * Also incoming ICMP frag_needed notifications will be ignored on
+ * this socket to prevent accepting spoofed ones.
+ */
+#define IP_PMTUDISC_INTERFACE		4
+/* weaker version of IP_PMTUDISC_INTERFACE, which allos packets to get
+ * fragmented if they exeed the interface mtu
+ */
+#define IP_PMTUDISC_OMIT		5
+
+#define IP_MULTICAST_IF			32
+#define IP_MULTICAST_TTL 		33
+#define IP_MULTICAST_LOOP 		34
+#define IP_ADD_MEMBERSHIP		35
+#define IP_DROP_MEMBERSHIP		36
+#define IP_UNBLOCK_SOURCE		37
+#define IP_BLOCK_SOURCE			38
+#define IP_ADD_SOURCE_MEMBERSHIP	39
+#define IP_DROP_SOURCE_MEMBERSHIP	40
+#define IP_MSFILTER			41
+#define MCAST_JOIN_GROUP		42
+#define MCAST_BLOCK_SOURCE		43
+#define MCAST_UNBLOCK_SOURCE		44
+#define MCAST_LEAVE_GROUP		45
+#define MCAST_JOIN_SOURCE_GROUP		46
+#define MCAST_LEAVE_SOURCE_GROUP	47
+#define MCAST_MSFILTER			48
+#define IP_MULTICAST_ALL		49
+#define IP_UNICAST_IF			50
+
+#define MCAST_EXCLUDE	0
+#define MCAST_INCLUDE	1
+
+/* These need to appear somewhere around here */
+#define IP_DEFAULT_MULTICAST_TTL        1
+#define IP_DEFAULT_MULTICAST_LOOP       1
+
+/* Request struct for multicast socket ops */
+
+#if __UAPI_DEF_IP_MREQ
+struct ip_mreq  {
+	struct in_addr imr_multiaddr;	/* IP multicast address of group */
+	struct in_addr imr_interface;	/* local IP address of interface */
+};
+
+struct ip_mreqn {
+	struct in_addr	imr_multiaddr;		/* IP multicast address of group */
+	struct in_addr	imr_address;		/* local IP address of interface */
+	int		imr_ifindex;		/* Interface index */
+};
+
+struct ip_mreq_source {
+	__be32		imr_multiaddr;
+	__be32		imr_interface;
+	__be32		imr_sourceaddr;
+};
+
+struct ip_msfilter {
+	__be32		imsf_multiaddr;
+	__be32		imsf_interface;
+	__u32		imsf_fmode;
+	__u32		imsf_numsrc;
+	__be32		imsf_slist[1];
+};
+
+#define IP_MSFILTER_SIZE(numsrc) \
+	(sizeof(struct ip_msfilter) - sizeof(__u32) \
+	+ (numsrc) * sizeof(__u32))
+
+struct group_req {
+	__u32				 gr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gr_group;	/* group address */
+};
+
+struct group_source_req {
+	__u32				 gsr_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gsr_group;	/* group address */
+	struct __kernel_sockaddr_storage gsr_source;	/* source address */
+};
+
+struct group_filter {
+	__u32				 gf_interface;	/* interface index */
+	struct __kernel_sockaddr_storage gf_group;	/* multicast address */
+	__u32				 gf_fmode;	/* filter mode */
+	__u32				 gf_numsrc;	/* number of sources */
+	struct __kernel_sockaddr_storage gf_slist[1];	/* interface index */
+};
+
+#define GROUP_FILTER_SIZE(numsrc) \
+	(sizeof(struct group_filter) - sizeof(struct __kernel_sockaddr_storage) \
+	+ (numsrc) * sizeof(struct __kernel_sockaddr_storage))
+#endif
+
+#if __UAPI_DEF_IN_PKTINFO
+struct in_pktinfo {
+	int		ipi_ifindex;
+	struct in_addr	ipi_spec_dst;
+	struct in_addr	ipi_addr;
+};
+#endif
+
+/* Structure describing an Internet (IP) socket address. */
+#if  __UAPI_DEF_SOCKADDR_IN
+#define __SOCK_SIZE__	16		/* sizeof(struct sockaddr)	*/
+struct sockaddr_in {
+  __kernel_sa_family_t	sin_family;	/* Address family		*/
+  __be16		sin_port;	/* Port number			*/
+  struct in_addr	sin_addr;	/* Internet address		*/
+
+  /* Pad to size of `struct sockaddr'. */
+  unsigned char		__pad[__SOCK_SIZE__ - sizeof(short int) -
+			sizeof(unsigned short int) - sizeof(struct in_addr)];
+};
+#define sin_zero	__pad		/* for BSD UNIX comp. -FvK	*/
+#endif
+
+#if __UAPI_DEF_IN_CLASS
+/*
+ * Definitions of the bits in an Internet address integer.
+ * On subnets, host and network parts are found according
+ * to the subnet mask, not these masks.
+ */
+#define	IN_CLASSA(a)		((((long int) (a)) & 0x80000000) == 0)
+#define	IN_CLASSA_NET		0xff000000
+#define	IN_CLASSA_NSHIFT	24
+#define	IN_CLASSA_HOST		(0xffffffff & ~IN_CLASSA_NET)
+#define	IN_CLASSA_MAX		128
+
+#define	IN_CLASSB(a)		((((long int) (a)) & 0xc0000000) == 0x80000000)
+#define	IN_CLASSB_NET		0xffff0000
+#define	IN_CLASSB_NSHIFT	16
+#define	IN_CLASSB_HOST		(0xffffffff & ~IN_CLASSB_NET)
+#define	IN_CLASSB_MAX		65536
+
+#define	IN_CLASSC(a)		((((long int) (a)) & 0xe0000000) == 0xc0000000)
+#define	IN_CLASSC_NET		0xffffff00
+#define	IN_CLASSC_NSHIFT	8
+#define	IN_CLASSC_HOST		(0xffffffff & ~IN_CLASSC_NET)
+
+#define	IN_CLASSD(a)		((((long int) (a)) & 0xf0000000) == 0xe0000000)
+#define	IN_MULTICAST(a)		IN_CLASSD(a)
+#define IN_MULTICAST_NET	0xF0000000
+
+#define	IN_EXPERIMENTAL(a)	((((long int) (a)) & 0xf0000000) == 0xf0000000)
+#define	IN_BADCLASS(a)		IN_EXPERIMENTAL((a))
+
+/* Address to accept any incoming messages. */
+#define	INADDR_ANY		((unsigned long int) 0x00000000)
+
+/* Address to send to all hosts. */
+#define	INADDR_BROADCAST	((unsigned long int) 0xffffffff)
+
+/* Address indicating an error return. */
+#define	INADDR_NONE		((unsigned long int) 0xffffffff)
+
+/* Network number for local host loopback. */
+#define	IN_LOOPBACKNET		127
+
+/* Address to loopback in software to local host.  */
+#define	INADDR_LOOPBACK		0x7f000001	/* 127.0.0.1   */
+#define	IN_LOOPBACK(a)		((((long int) (a)) & 0xff000000) == 0x7f000000)
+
+/* Defines for Multicast INADDR */
+#define INADDR_UNSPEC_GROUP   	0xe0000000U	/* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
+#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
+#endif
+
+/* <asm/byteorder.h> contains the htonl type stuff.. */
+#include <asm/byteorder.h> 
+
+
+#endif /* _UAPI_LINUX_IN_H */
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 814aaf269949..de28466c0186 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -7,6 +7,7 @@ include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
+include/uapi/linux/in.h
 include/uapi/linux/perf_event.h
 include/uapi/linux/prctl.h
 include/uapi/linux/sched.h
-- 
cgit v1.2.3


From 9849eec3a44c6f47948117c14d7afb8cf53bf0fb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 26 Jul 2018 09:26:13 -0300
Subject: perf beauty: Add a generator for IPPROTO_ socket's protocol constants

It'll use tools/include copy of linux/in.h to generate a table to be
used by tools, initially by the 'socket' and 'socketpair' beautifiers in
'perf trace', but that could also be used to translate from a string
constant to the integer value to be used in a eBPF or tracefs tracepoint
filter.

When used without any args it produces:

  $ tools/perf/trace/beauty/socket_ipproto.sh
  static const char *socket_ipproto[] = {
	[0] = "IP",
	[103] = "PIM",
	[108] = "COMP",
	[12] = "PUP",
	[132] = "SCTP",
	[136] = "UDPLITE",
	[137] = "MPLS",
	[17] = "UDP",
	[1] = "ICMP",
	[22] = "IDP",
	[255] = "RAW",
	[29] = "TP",
	[2] = "IGMP",
	[33] = "DCCP",
	[41] = "IPV6",
	[46] = "RSVP",
	[47] = "GRE",
	[4] = "IPIP",
	[50] = "ESP",
	[51] = "AH",
	[6] = "TCP",
	[8] = "EGP",
	[92] = "MTP",
	[94] = "BEETPH",
	[98] = "ENCAP",
  };
  $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-v9rafqh3qn6b9kp9vfvj9f8s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/trace/beauty/socket_ipproto.sh | 11 +++++++++++
 1 file changed, 11 insertions(+)
 create mode 100755 tools/perf/trace/beauty/socket_ipproto.sh

diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
new file mode 100755
index 000000000000..a3cc24633bec
--- /dev/null
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *socket_ipproto[] = {\n"
+regex='^[[:space:]]+IPPROTO_(\w+)[[:space:]]+=[[:space:]]+([[:digit:]]+),.*'
+
+egrep $regex ${header_dir}/in.h | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	sort | xargs printf "\t[%s] = \"%s\",\n"
+printf "};\n"
-- 
cgit v1.2.3


From bc972ada4f85450ebf20c4981ee84a1a4b060161 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 26 Jul 2018 15:30:33 -0300
Subject: perf trace beauty: Do not print NULL strarray entries

We may have string tables where not all slots have values, in those
cases its better to print the numeric value, for instance:

In the table below we would show "protocol: (null)" for

      socket_ipproto[3]

Where it would be better to show "protocol: 3".

      $ tools/perf/trace/beauty/socket_ipproto.sh
      static const char *socket_ipproto[] = {
            [0] = "IP",
            [103] = "PIM",
            [108] = "COMP",
            [12] = "PUP",
            [132] = "SCTP",
            [136] = "UDPLITE",
            [137] = "MPLS",
            [17] = "UDP",
            [1] = "ICMP",
            [22] = "IDP",
            [255] = "RAW",
            [29] = "TP",
            [2] = "IGMP",
            [33] = "DCCP",
            [41] = "IPV6",
            [46] = "RSVP",
            [47] = "GRE",
            [4] = "IPIP",
            [50] = "ESP",
            [51] = "AH",
            [6] = "TCP",
            [8] = "EGP",
            [92] = "MTP",
            [94] = "BEETPH",
            [98] = "ENCAP",
      };
      $

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-7djfak94eb3b9ltr79cpn3ti@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 6a748eca2edb..632ef5f8f060 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -291,7 +291,7 @@ size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const cha
 {
 	int idx = val - sa->offset;
 
-	if (idx < 0 || idx >= sa->nr_entries)
+	if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL)
 		return scnprintf(bf, size, intfmt, val);
 
 	return scnprintf(bf, size, "%s", sa->entries[idx]);
-- 
cgit v1.2.3


From 03aeb6c818b608a2b344e21bb978030c41158045 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 26 Jul 2018 09:26:13 -0300
Subject: perf trace beauty: Add beautifiers for 'socket''s 'protocol' arg

It'll be wired to 'perf trace' in the next cset.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2i9vkvm1ik8yu4hgjmxhsyjv@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.perf         | 10 ++++++++++
 tools/perf/trace/beauty/Build    |  1 +
 tools/perf/trace/beauty/beauty.h |  3 +++
 tools/perf/trace/beauty/socket.c | 28 ++++++++++++++++++++++++++++
 4 files changed, 42 insertions(+)
 create mode 100644 tools/perf/trace/beauty/socket.c

diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index ecc9fc952655..b3d1b12a5081 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -384,6 +384,8 @@ export INSTALL SHELL_PATH
 
 SHELL = $(SHELL_PATH)
 
+linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
 drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
@@ -431,6 +433,12 @@ kvm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/kvm_ioctl.sh
 $(kvm_ioctl_array): $(kvm_hdr_dir)/kvm.h $(kvm_ioctl_tbl)
 	$(Q)$(SHELL) '$(kvm_ioctl_tbl)' $(kvm_hdr_dir) > $@
 
+socket_ipproto_array := $(beauty_outdir)/socket_ipproto_array.c
+socket_ipproto_tbl := $(srctree)/tools/perf/trace/beauty/socket_ipproto.sh
+
+$(socket_ipproto_array): $(linux_uapi_dir)/in.h $(socket_ipproto_tbl)
+	$(Q)$(SHELL) '$(socket_ipproto_tbl)' $(linux_uapi_dir) > $@
+
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
 vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -566,6 +574,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
 	$(sndrv_ctl_ioctl_array) \
 	$(kcmp_type_array) \
 	$(kvm_ioctl_array) \
+	$(socket_ipproto_array) \
 	$(vhost_virtio_ioctl_array) \
 	$(madvise_behavior_array) \
 	$(perf_ioctl_array) \
@@ -860,6 +869,7 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
 		$(OUTPUT)$(sndrv_pcm_ioctl_array) \
 		$(OUTPUT)$(kvm_ioctl_array) \
 		$(OUTPUT)$(kcmp_type_array) \
+		$(OUTPUT)$(socket_ipproto_array) \
 		$(OUTPUT)$(vhost_virtio_ioctl_array) \
 		$(OUTPUT)$(perf_ioctl_array) \
 		$(OUTPUT)$(prctl_option_array) \
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index 66330d4b739b..f528ba35e140 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -7,4 +7,5 @@ endif
 libperf-y += kcmp.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
+libperf-y += socket.o
 libperf-y += statx.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 984a504d335c..9615af5d412b 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -106,6 +106,9 @@ size_t syscall_arg__scnprintf_prctl_arg2(char *bf, size_t size, struct syscall_a
 size_t syscall_arg__scnprintf_prctl_arg3(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PRCTL_ARG3 syscall_arg__scnprintf_prctl_arg3
 
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_SK_PROTO syscall_arg__scnprintf_socket_protocol
+
 size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
 
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
new file mode 100644
index 000000000000..65227269384b
--- /dev/null
+++ b/tools/perf/trace/beauty/socket.c
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * trace/beauty/socket.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <sys/socket.h>
+
+static size_t socket__scnprintf_ipproto(int protocol, char *bf, size_t size)
+{
+#include "trace/beauty/generated/socket_ipproto_array.c"
+	static DEFINE_STRARRAY(socket_ipproto);
+
+	return strarray__scnprintf(&strarray__socket_ipproto, bf, size, "%d", protocol);
+}
+
+size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct syscall_arg *arg)
+{
+	int domain = syscall_arg__val(arg, 0);
+
+	if (domain == AF_INET || domain == AF_INET6)
+		return socket__scnprintf_ipproto(arg->val, bf, size);
+
+	return syscall_arg__scnprintf_int(bf, size, arg);
+}
-- 
cgit v1.2.3


From 162d3edbe591a97939516b546162b9ba05ec62cb Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Thu, 26 Jul 2018 09:26:13 -0300
Subject: perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall
 'protocol' args

For instance:

  $ trace -e socket* ssh sandy
     0.000 ( 0.031 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK                   ) = 3
     0.052 ( 0.015 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK                   ) = 3
     1.568 ( 0.020 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK                   ) = 3
     1.603 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK                   ) = 3
     1.699 ( 0.014 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK                   ) = 3
     1.724 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK                   ) = 3
     1.804 ( 0.020 ms): ssh/19919 socket(family: INET, type: STREAM, protocol: TCP                      ) = 3
    17.549 ( 0.098 ms): ssh/19919 socket(family: LOCAL, type: STREAM                                    ) = 4
  acme@sandy's password:

Just like with other syscall args, the common bits are supressed so that
the output is more compact, i.e. we use "TCP" instead of "IPPROTO_TCP",
but we can make this show the original constant names if we like it by
using some command line knob or ~/.perfconfig "[trace]" section
variable.

Also needed is to make perf's event parser accept things like:

  $ perf trace -e socket*/protocol=TCP/

By using both the tracefs event 'format' files and these tables built
from the kernel sources.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-l39jz1vnyda0b6jsufuc8bz7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 632ef5f8f060..9aca65e6b9aa 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -761,10 +761,12 @@ static struct syscall_fmt {
 	  .arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
 	{ .name	    = "socket",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "socketpair",
 	  .arg = { [0] = STRARRAY(family, socket_families),
-		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ }, }, },
+		   [1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
+		   [2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
 	{ .name	    = "stat", .alias = "newstat", },
 	{ .name	    = "statx",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	 /* fdat */ },
-- 
cgit v1.2.3


From aa90f9f9554616d5738f7bedb4a8f0e5e14d1bc6 Mon Sep 17 00:00:00 2001
From: Sandipan Das <sandipan@linux.ibm.com>
Date: Thu, 26 Jul 2018 22:47:33 +0530
Subject: perf tests: Fix indexing when invoking subtests

Recently, the subtest numbering was changed to start from 1.  While it
is fine for displaying results, this should not be the case when the
subtests are actually invoked.

Typically, the subtests are stored in zero-indexed arrays and invoked
based on the index passed to the main test function.  Since the index
now starts from 1, the second subtest in the array (index 1) gets
invoked instead of the first (index 0).  This applies to all of the
following subtests but for the last one, the subtest always fails
because it does not meet the boundary condition of the subtest index
being lesser than the number of subtests.

This can be observed on powerpc64 and x86_64 systems running Fedora 28
as shown below.

Before:

  # perf test "builtin clang support"
  55: builtin clang support                                 :
  55.1: builtin clang compile C source to IR                : Ok
  55.2: builtin clang compile C source to ELF object        : FAILED!

  # perf test "LLVM search and compile"
  38: LLVM search and compile                               :
  38.1: Basic BPF llvm compile                              : Ok
  38.2: kbuild searching                                    : Ok
  38.3: Compile source for BPF prologue generation          : Ok
  38.4: Compile source for BPF relocation                   : FAILED!

  # perf test "BPF filter"
  40: BPF filter                                            :
  40.1: Basic BPF filtering                                 : Ok
  40.2: BPF pinning                                         : Ok
  40.3: BPF prologue generation                             : Ok
  40.4: BPF relocation checker                              : FAILED!

After:

  # perf test "builtin clang support"
  55: builtin clang support                                 :
  55.1: builtin clang compile C source to IR                : Ok
  55.2: builtin clang compile C source to ELF object        : Ok

  # perf test "LLVM search and compile"
  38: LLVM search and compile                               :
  38.1: Basic BPF llvm compile                              : Ok
  38.2: kbuild searching                                    : Ok
  38.3: Compile source for BPF prologue generation          : Ok
  38.4: Compile source for BPF relocation                   : Ok

  # perf test "BPF filter"
  40: BPF filter                                            :
  40.1: Basic BPF filtering                                 : Ok
  40.2: BPF pinning                                         : Ok
  40.3: BPF prologue generation                             : Ok
  40.4: BPF relocation checker                              : Ok

Signed-off-by: Sandipan Das <sandipan@linux.ibm.com>
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Fixes: 9ef0112442bd ("perf test: Fix subtest number when showing results")
Link: http://lkml.kernel.org/r/20180726171733.33208-1-sandipan@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/tests/builtin-test.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 4f5de8245b32..d7a5e1b9aa6f 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -385,7 +385,7 @@ static int test_and_print(struct test *t, bool force_skip, int subtest)
 	if (!t->subtest.get_nr)
 		pr_debug("%s:", t->desc);
 	else
-		pr_debug("%s subtest %d:", t->desc, subtest);
+		pr_debug("%s subtest %d:", t->desc, subtest + 1);
 
 	switch (err) {
 	case TEST_OK:
@@ -599,7 +599,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			for (subi = 0; subi < subn; subi++) {
 				pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
 					t->subtest.get_desc(subi));
-				err = test_and_print(t, skip, subi + 1);
+				err = test_and_print(t, skip, subi);
 				if (err != TEST_OK && t->subtest.skip_if_fail)
 					skip = true;
 			}
-- 
cgit v1.2.3


From 73978332572ccf5e364c31e9a70ba953f8202b46 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@kernel.org>
Date: Tue, 24 Jul 2018 08:20:08 +0200
Subject: perf c2c report: Fix crash for empty browser

'perf c2c' scans read/write accesses and tries to find false sharing
cases, so when the events it wants were not asked for or ended up not
taking place, we get no histograms.

So do not try to display entry details if there's not any. Currently
this ends up in crash:

  $ perf c2c report # then press 'd'
  perf: Segmentation fault
  $

Committer testing:

Before:

Record a perf.data file without events of interest to 'perf c2c report',
then call it and press 'd':

  # perf record sleep 1
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.001 MB perf.data (6 samples) ]
  # perf c2c report
  perf: Segmentation fault
  -------- backtrace --------
  perf[0x5b1d2a]
  /lib64/libc.so.6(+0x346df)[0x7fcb566e36df]
  perf[0x46fcae]
  perf[0x4a9f1e]
  perf[0x4aa220]
  perf(main+0x301)[0x42c561]
  /lib64/libc.so.6(__libc_start_main+0xe9)[0x7fcb566cff29]
  perf(_start+0x29)[0x42c999]
  #

After the patch the segfault doesn't take place, a follow up patch to
tell the user why nothing changes when 'd' is pressed would be good.

Reported-by: rodia@autistici.org
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Joe Mario <jmario@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: f1c5fd4d0bb9 ("perf c2c report: Add TUI cacheline browser")
Link: http://lkml.kernel.org/r/20180724062008.26126-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-c2c.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index f2ea85ee573f..f3aa9d02a5ab 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2349,6 +2349,9 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
 	" s             Toggle full length of symbol and source line columns \n"
 	" q             Return back to cacheline list \n";
 
+	if (!he)
+		return 0;
+
 	/* Display compact version first. */
 	c2c.symbol_full = false;
 
-- 
cgit v1.2.3


From 83868bf71d2eb7700b37f1ea188007f0125e4ee4 Mon Sep 17 00:00:00 2001
From: Thomas Richter <tmricht@linux.ibm.com>
Date: Tue, 31 Jul 2018 09:32:54 +0200
Subject: perf build: Fix installation directory for eBPF

The perf tool build and install is controlled via a Makefile. The
'install' rule creates directories and copies files. Among them are
header files installed in /usr/lib/include/perf/bpf/.

However all listed examples are installing its header files in

  /usr/lib/<tool-name>/...[/include]/header.h

and not in

  /usr/lib/include/<tool-name>/.../header.h.

Background information:

Building the Fedora 28 glibc RPM on s390x and s390 fails on s390 (gcc
-m31) as gcc is not able to find header-files like stdbool.h.

In the glibc.spec file, you can see that glibc is configured with
"--with-headers". In this case, first -nostdinc is added to the CFLAGS
and then further include paths are added via -isystem.  One of those
paths should contain header files like stdbool.h.

In order to get this path, gcc is invoked with:

- on Fedora 28 (with 4.18 kernel):

  $ gcc -print-file-name=include
  /usr/lib/gcc/s390x-redhat-linux/8/include
  $ gcc -m31 -print-file-name=include
  /usr/lib/gcc/s390x-redhat-linux/8/../../../../lib/include
  => If perf is installed, this is: /usr/lib/include
  On my machine this directory is only containing the directory "perf".
  If perf is not installed gcc returns: /usr/lib/gcc/s390x-redhat-linux/8/include

- on Ubuntu 18.04 (with 4.15 kernel):

  $ gcc  -print-file-name=include
  /usr/lib/gcc/s390x-linux-gnu/7/include
  $ gcc -m31 -print-file-name=include
  /usr/lib/gcc/s390x-linux-gnu/7/include
  => gcc returns the correct path even if perf is installed.

In each case, the introduction of the subdirectory /usr/lib/include
leads to the regression that one can not build the glibc RPM for s390
anymore as gcc can not find headers like stdbool.h.

To remedy this install bpf.h to /usr/lib/perf/include/bpf/bpf.h

Output before using the command 'perf test -Fv 40':

  echo '...[bpf-program-source]...' | /usr/bin/clang ... \
		   -I/root/lib/include/perf/bpf ...
                               ^^^^^^^^^^^^
...
  [root@p23lp27 perf]# perf test -F 40
  40: BPF filter                                            :
  40.1: Basic BPF filtering                                 : Ok
  40.2: BPF pinning                                         : Ok
  40.3: BPF prologue generation                             : Ok
  40.4: BPF relocation checker                              : Ok
  [root@p23lp27 perf]#

Output after using command 'perf test -Fv 40':

  echo '...[bpf-program-source]...' | /usr/bin/clang ... \
		 -I/root/lib/perf/include/bpf ...
                             ^^^^^^^^^^^^
...
  [root@p23lp27 perf]# perf test -F 40
  40: BPF filter                                            :
  40.1: Basic BPF filtering                                 : Ok
  40.2: BPF pinning                                         : Ok
  40.3: BPF prologue generation                             : Ok
  40.4: BPF relocation checker                              : Ok
  [root@p23lp27 perf]#

Committer testing:

While the above 'perf test -F 40' (or 'perf test bpf') will allow us
to see that the correct path is now added via -I, to actually test this
we better try to use a bpf script that includes files in the changed
directory.

We have the files that now reside in /root/lib/perf/examples/bpf/ to do
just that:

  # tail -8 /root/lib/perf/examples/bpf/5sec.c
  #include <bpf.h>

  int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
  {
	  return sec == 5;
  }

  license(GPL);
  # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 4
       0.333 (4000.086 ms): sleep/9248 nanosleep(rqtp: 0x7ffc155f3300) = 0
  # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 5
       0.287 (         ): sleep/9659 nanosleep(rqtp: 0x7ffeafe38200) ...
       0.290 (         ): perf_bpf_probe:hrtimer_nanosleep:(ffffffff9911efe0) tv_sec=5
       0.287 (5000.059 ms): sleep/9659  ... [continued]: nanosleep()) = 0
  # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 6
       0.247 (5999.951 ms): sleep/10068 nanosleep(rqtp: 0x7fff2086d900) = 0
  # perf trace -e *sleep -e /root/lib/perf/examples/bpf/5sec.c sleep 5.987
       0.293 (         ): sleep/10489 nanosleep(rqtp: 0x7ffdd4fc10e0) ...
       0.296 (         ): perf_bpf_probe:hrtimer_nanosleep:(ffffffff9911efe0) tv_sec=5
       0.293 (5986.912 ms): sleep/10489  ... [continued]: nanosleep()) = 0
  #

Suggested-by: Stefan Liebler <stli@linux.ibm.com>
Suggested-by: Arnaldo Carvalho de Melo <acme@kernel.org>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Fixes: 1b16fffa389d ("perf llvm-utils: Add bpf include path to clang command line")
Link: http://lkml.kernel.org/r/20180731073254.91090-1-tmricht@linux.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/Makefile.config | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index d3318f99006c..f6d1a03c7523 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -907,8 +907,8 @@ bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
-perf_include_dir = lib/include/perf
-perf_examples_dir = lib/examples/perf
+perf_include_dir = lib/perf/include
+perf_examples_dir = lib/perf/examples
 sharedir = $(prefix)/share
 template_dir = share/perf-core/templates
 STRACE_GROUPS_DIR = share/perf-core/strace/groups
-- 
cgit v1.2.3


From 3eb3e07bcfee0670d7142f839c76f33f3d265793 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Wed, 11 Jul 2018 15:45:42 +0800
Subject: perf cs-etm: Fix start tracing packet handling

Usually the start tracing packet is a CS_ETM_TRACE_ON packet, this
packet is passed to cs_etm__flush();  cs_etm__flush() will check the
condition 'prev_packet->sample_type == CS_ETM_RANGE' but 'prev_packet'
is allocated by zalloc() so 'prev_packet->sample_type' is zero in
initialization and this condition is false.  So cs_etm__flush() will
directly bail out without handling the start tracing packet.

This patch is to introduce a new sample type CS_ETM_EMPTY, which is used
to indicate the packet is an empty packet.  cs_etm__flush() will swap
packets when it finds the previous packet is empty, so this can record
the start tracing packet into 'etmq->prev_packet'.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1531295145-596-4-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm-decoder/cs-etm-decoder.h |  1 +
 tools/perf/util/cs-etm.c                        | 19 ++++++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 743f5f444304..612b5755f742 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -23,6 +23,7 @@ struct cs_etm_buffer {
 };
 
 enum cs_etm_sample_type {
+	CS_ETM_EMPTY = 0,
 	CS_ETM_RANGE = 1 << 0,
 	CS_ETM_TRACE_ON = 1 << 1,
 };
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 8b2c099e750a..ae7c9c880cb2 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -924,8 +924,14 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 	int err = 0;
 	struct cs_etm_packet *tmp;
 
+	if (!etmq->prev_packet)
+		return 0;
+
+	/* Handle start tracing packet */
+	if (etmq->prev_packet->sample_type == CS_ETM_EMPTY)
+		goto swap_packet;
+
 	if (etmq->etm->synth_opts.last_branch &&
-	    etmq->prev_packet &&
 	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
 		/*
 		 * Generate a last branch event for the branches left in the
@@ -944,6 +950,10 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 
 		etmq->period_instructions = 0;
 
+	}
+
+swap_packet:
+	if (etmq->etm->synth_opts.last_branch) {
 		/*
 		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
 		 * the next incoming packet.
@@ -1023,6 +1033,13 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 					 */
 					cs_etm__flush(etmq);
 					break;
+				case CS_ETM_EMPTY:
+					/*
+					 * Should not receive empty packet,
+					 * report error.
+					 */
+					pr_err("CS ETM Trace: empty packet\n");
+					return -EINVAL;
 				default:
 					break;
 				}
-- 
cgit v1.2.3


From 6035b6804bdfd662c8ee6226dc90f3764060ec73 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Wed, 11 Jul 2018 15:45:43 +0800
Subject: perf cs-etm: Support dummy address value for CS_ETM_TRACE_ON packet

For CS_ETM_TRACE_ON packet, its fields 'packet->start_addr' and
'packet->end_addr' equal to 0xdeadbeefdeadbeefUL which are emitted in
the decoder layer as dummy value, but the dummy value is pointless for
branch sample when we use 'perf script' command to check program flow.

This patch is a preparation to support CS_ETM_TRACE_ON packet for branch
sample, it converts the dummy address value to zero for more readable;
this is accomplished by cs_etm__last_executed_instr() and
cs_etm__first_executed_instr().  The later one is a new function
introduced by this patch.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1531295145-596-5-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index ae7c9c880cb2..976db8483478 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -494,6 +494,10 @@ static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
 
 static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 {
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
 	/*
 	 * The packet records the execution range with an exclusive end address
 	 *
@@ -505,6 +509,15 @@ static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
 	return packet->end_addr - A64_INSTR_SIZE;
 }
 
+static inline u64 cs_etm__first_executed_instr(struct cs_etm_packet *packet)
+{
+	/* Returns 0 for the CS_ETM_TRACE_ON packet */
+	if (packet->sample_type == CS_ETM_TRACE_ON)
+		return 0;
+
+	return packet->start_addr;
+}
+
 static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
 {
 	/*
@@ -546,7 +559,7 @@ static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
 
 	be       = &bs->entries[etmq->last_branch_pos];
 	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
-	be->to	 = etmq->packet->start_addr;
+	be->to	 = cs_etm__first_executed_instr(etmq->packet);
 	/* No support for mispredict */
 	be->flags.mispred = 0;
 	be->flags.predicted = 1;
@@ -701,7 +714,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = etmq->packet->start_addr;
+	sample.addr = cs_etm__first_executed_instr(etmq->packet);
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
-- 
cgit v1.2.3


From d603b4e9f9c3181f2dacb989bba60081b99befe4 Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Wed, 11 Jul 2018 15:45:44 +0800
Subject: perf cs-etm: Generate branch sample when receiving a CS_ETM_TRACE_ON
 packet

If one CS_ETM_TRACE_ON packet is inserted, we miss to generate branch
sample for the previous CS_ETM_RANGE packet.

This patch is to generate branch sample when receiving a CS_ETM_TRACE_ON
packet, so this can save complete info for the previous CS_ETM_RANGE
packet just before CS_ETM_TRACE_ON packet.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1531295145-596-6-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 976db8483478..d3b794286bca 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -935,6 +935,7 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 static int cs_etm__flush(struct cs_etm_queue *etmq)
 {
 	int err = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct cs_etm_packet *tmp;
 
 	if (!etmq->prev_packet)
@@ -965,6 +966,13 @@ static int cs_etm__flush(struct cs_etm_queue *etmq)
 
 	}
 
+	if (etm->sample_branches &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		err = cs_etm__synth_branch_sample(etmq);
+		if (err)
+			return err;
+	}
+
 swap_packet:
 	if (etmq->etm->synth_opts.last_branch) {
 		/*
-- 
cgit v1.2.3


From 14a85b1eca348e00a9f209b522f94ec3ead94acb Mon Sep 17 00:00:00 2001
From: Leo Yan <leo.yan@linaro.org>
Date: Wed, 11 Jul 2018 15:45:45 +0800
Subject: perf cs-etm: Generate branch sample for CS_ETM_TRACE_ON packet

CS_ETM_TRACE_ON packet itself can give the info that there have a
discontinuity in the trace, this patch is to add branch sample for
CS_ETM_TRACE_ON packet if it is inserted in the middle of CS_ETM_RANGE
packets; as result we can have hint for the trace discontinuity.

Signed-off-by: Leo Yan <leo.yan@linaro.org>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kim Phillips <kim.phillips@arm.com>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Walker <robert.walker@arm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/1531295145-596-7-git-send-email-leo.yan@linaro.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/cs-etm.c | 24 +++++++++++++++++-------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index d3b794286bca..2ae640257fdb 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -910,13 +910,23 @@ static int cs_etm__sample(struct cs_etm_queue *etmq)
 		etmq->period_instructions = instrs_over;
 	}
 
-	if (etm->sample_branches &&
-	    etmq->prev_packet &&
-	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
-	    etmq->prev_packet->last_instr_taken_branch) {
-		ret = cs_etm__synth_branch_sample(etmq);
-		if (ret)
-			return ret;
+	if (etm->sample_branches && etmq->prev_packet) {
+		bool generate_sample = false;
+
+		/* Generate sample for tracing on packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_TRACE_ON)
+			generate_sample = true;
+
+		/* Generate sample for branch taken packet */
+		if (etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+		    etmq->prev_packet->last_instr_taken_branch)
+			generate_sample = true;
+
+		if (generate_sample) {
+			ret = cs_etm__synth_branch_sample(etmq);
+			if (ret)
+				return ret;
+		}
 	}
 
 	if (etm->sample_branches || etm->synth_opts.last_branch) {
-- 
cgit v1.2.3


From b9b77222d4ff6b5bb8f5d87fca20de0910618bb9 Mon Sep 17 00:00:00 2001
From: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Date: Tue, 31 Jul 2018 15:32:51 +0530
Subject: perf vendor events arm64: Update ThunderX2 implementation defined pmu
 core events

Signed-off-by: Ganapatrao Kulkarni <ganapatrao.kulkarni@cavium.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ganapatrao Kulkarni <gklkml16@gmail.com>
Cc: Jan Glauber <jan.glauber@cavium.com>
Cc: Jayachandran C <jnair@caviumnetworks.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Robert Richter <robert.richter@cavium.com>
Cc: Vadim Lomovtsev <vadim.lomovtsev@cavium.com>
Cc: Will Deacon <will.deacon@arm.com>
Link: http://lkml.kernel.org/r/20180731100251.23575-1-ganapatrao.kulkarni@cavium.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 .../arch/arm64/cavium/thunderx2/core-imp-def.json  | 87 +++++++++++++++++++++-
 1 file changed, 84 insertions(+), 3 deletions(-)

diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
index bc03c06c3918..752e47eb6977 100644
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -11,6 +11,21 @@
     {
         "ArchStdEvent": "L1D_CACHE_REFILL_WR",
     },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
     {
         "ArchStdEvent": "L1D_TLB_REFILL_RD",
     },
@@ -23,10 +38,76 @@
     {
         "ArchStdEvent": "L1D_TLB_WR",
     },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR",
+    },
     {
         "ArchStdEvent": "BUS_ACCESS_RD",
-   },
-   {
+    },
+    {
         "ArchStdEvent": "BUS_ACCESS_WR",
-   }
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD",
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC",
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC",
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF",
+    },
+    {
+        "ArchStdEvent": "EXC_SVC",
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ",
+    },
+    {
+        "ArchStdEvent": "EXC_SMC",
+    },
+    {
+        "ArchStdEvent": "EXC_HVC",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ",
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ",
+    }
 ]
-- 
cgit v1.2.3


From 95f04328e42dc7d1eb08f3cb38150c1f2ec09f57 Mon Sep 17 00:00:00 2001
From: Michael Petlan <mpetlan@redhat.com>
Date: Mon, 30 Jul 2018 17:35:04 -0400
Subject: perf list: Unify metric group description format with PMU event
 description

PMU event descriptions use 7 spaces + '[' or 8 spaces as indentation.
Metric groups used a tab + '['. This patch unifies it to the way PMU
event descriptions are indented.

BEFORE:

  $ perf list
  [...]
  Metric Groups:

  DSB:
    DSB_Coverage
	  [Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)]
  [...]

AFTER:

  $ perf list
  [...]
  Metric Groups:

  DSB:
    DSB_Coverage
         [Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)]
  [...]

Signed-off-by: Michael Petlan <mpetlan@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Kim Phillips <kim.phillips@arm.com>
LPU-Reference: 771439042.22924766.1532986504631.JavaMail.zimbra@redhat.com
Link: https://lkml.kernel.org/n/tip-mlo850517m6u1rbjndvd1bwr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/metricgroup.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 96eab4ec34ff..a28f9b5cc4ff 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -326,8 +326,8 @@ void metricgroup__print(bool metrics, bool metricgroups, char *filter,
 				if (raw)
 					s = (char *)pe->metric_name;
 				else {
-					if (asprintf(&s, "%s\n\t[%s]",
-						     pe->metric_name, pe->desc) < 0)
+					if (asprintf(&s, "%s\n%*s%s]",
+						     pe->metric_name, 8, "[", pe->desc) < 0)
 						return;
 				}
 
-- 
cgit v1.2.3


From f09757ab401ff332030f8e3a41cec6a44e6d9461 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 31 Jul 2018 16:38:53 +0200
Subject: spi: dw: document Microsemi integration

The integration of the Designware SPI controller on Microsemi SoCs requires
an extra register set to be able to give the IP control of the SPI
interface.

Cc: Rob Herring <robh+dt@kernel.org>
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
index 204b311e0400..642d3fb1ef85 100644
--- a/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
+++ b/Documentation/devicetree/bindings/spi/snps,dw-apb-ssi.txt
@@ -1,8 +1,10 @@
 Synopsys DesignWare AMBA 2.0 Synchronous Serial Interface.
 
 Required properties:
-- compatible : "snps,dw-apb-ssi"
-- reg : The register base for the controller.
+- compatible : "snps,dw-apb-ssi" or "mscc,<soc>-spi", where soc is "ocelot" or
+  "jaguar2"
+- reg : The register base for the controller. For "mscc,<soc>-spi", a second
+  register set is required (named ICPU_CFG:SPI_MST)
 - interrupts : One interrupt, used by the controller.
 - #address-cells : <1>, as required by generic SPI binding.
 - #size-cells : <0>, also as required by generic SPI binding.
-- 
cgit v1.2.3


From 739e2edc848af30fefa66d6c422c00ca9a701c06 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Tue, 31 Jul 2018 11:58:57 -0300
Subject: perf bpf: Show better message when failing to load an object

Before:

  libbpf: license of tools/perf/examples/bpf/etcsnoop.c is GPL
  libbpf: section(6) version, size 4, link 0, flags 3, type=1
  libbpf: kernel version of tools/perf/examples/bpf/etcsnoop.c is 41200
  libbpf: section(7) .symtab, size 120, link 1, flags 0, type=2
  bpf: config program 'syscalls:sys_enter_openat'
  libbpf: load bpf program failed: Operation not permitted
  libbpf: failed to load program 'syscalls:sys_enter_openat'
  libbpf: failed to load object 'tools/perf/examples/bpf/etcsnoop.c'
  bpf: load objects failed

After: (just the last line changes)

  bpf: load objects failed: err=-4009: (Incorrect kernel version)

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-wi44iid0yjfht3lcvplc75fm@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/util/bpf-loader.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index cee658733e2c..3d02ae38ec56 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -747,7 +747,9 @@ int bpf__load(struct bpf_object *obj)
 
 	err = bpf_object__load(obj);
 	if (err) {
-		pr_debug("bpf: load objects failed\n");
+		char bf[128];
+		libbpf_strerror(err, bf, sizeof(bf));
+		pr_debug("bpf: load objects failed: err=%d: (%s)\n", err, bf);
 		return err;
 	}
 	return 0;
-- 
cgit v1.2.3


From 08fcf813281ebcf72c69487c1501ad91b7121cdb Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 31 Jul 2018 09:10:26 -0600
Subject: t10-pi: provide empty t10_pi_complete() for !CONFIG_BLK_DEV_INTEGRITY

Fixes a link failure whtn BLK_DEV_INTEGRITY isn't defined.

Fixes: 10c41ddd6132 ("block: move dif_prepare/dif_complete functions to block layer")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/t10-pi.h | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/include/linux/t10-pi.h b/include/linux/t10-pi.h
index 5a427c289f58..b9626aa7e90c 100644
--- a/include/linux/t10-pi.h
+++ b/include/linux/t10-pi.h
@@ -51,8 +51,19 @@ extern const struct blk_integrity_profile t10_pi_type1_crc;
 extern const struct blk_integrity_profile t10_pi_type1_ip;
 extern const struct blk_integrity_profile t10_pi_type3_crc;
 extern const struct blk_integrity_profile t10_pi_type3_ip;
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
 extern void t10_pi_prepare(struct request *rq, u8 protection_type);
 extern void t10_pi_complete(struct request *rq, u8 protection_type,
 			    unsigned int intervals);
+#else
+static inline void t10_pi_complete(struct request *rq, u8 protection_type,
+				   unsigned int intervals)
+{
+}
+static inline void t10_pi_prepare(struct request *rq, u8 protection_type)
+{
+}
+#endif
 
 #endif
-- 
cgit v1.2.3


From 5c7e5a22c126e4d7839e6bdcc05b3c4dfa945a72 Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Fri, 8 Dec 2017 20:37:34 +0100
Subject: drm/arm/hdlcd: Use drm_mode_config_helper_suspend/resume()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace driver's code with the generic helpers that do the same thing
including the NULL check.

Cc: Liviu Dudau <liviu.dudau@arm.com>
Cc: Brian Starkey <brian.starkey@arm.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/hdlcd_drv.c | 25 +++----------------------
 drivers/gpu/drm/arm/hdlcd_drv.h |  1 -
 2 files changed, 3 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index feaa8bc3d7b7..9800a9e388ef 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -27,6 +27,7 @@
 #include <drm/drm_fb_cma_helper.h>
 #include <drm/drm_gem_cma_helper.h>
 #include <drm/drm_gem_framebuffer_helper.h>
+#include <drm/drm_modeset_helper.h>
 #include <drm/drm_of.h>
 
 #include "hdlcd_drv.h"
@@ -427,35 +428,15 @@ MODULE_DEVICE_TABLE(of, hdlcd_of_match);
 static int __maybe_unused hdlcd_pm_suspend(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
 
-	if (!hdlcd)
-		return 0;
-
-	drm_kms_helper_poll_disable(drm);
-	drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 1);
-
-	hdlcd->state = drm_atomic_helper_suspend(drm);
-	if (IS_ERR(hdlcd->state)) {
-		drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
-		drm_kms_helper_poll_enable(drm);
-		return PTR_ERR(hdlcd->state);
-	}
-
-	return 0;
+	return drm_mode_config_helper_suspend(drm);
 }
 
 static int __maybe_unused hdlcd_pm_resume(struct device *dev)
 {
 	struct drm_device *drm = dev_get_drvdata(dev);
-	struct hdlcd_drm_private *hdlcd = drm ? drm->dev_private : NULL;
-
-	if (!hdlcd)
-		return 0;
 
-	drm_atomic_helper_resume(drm, hdlcd->state);
-	drm_fbdev_cma_set_suspend_unlocked(hdlcd->fbdev, 0);
-	drm_kms_helper_poll_enable(drm);
+	drm_mode_config_helper_resume(drm);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index 56f34dfff640..58d75d7e1b20 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -12,7 +12,6 @@ struct hdlcd_drm_private {
 	struct drm_fbdev_cma		*fbdev;
 	struct drm_crtc			crtc;
 	struct drm_plane		*plane;
-	struct drm_atomic_state		*state;
 #ifdef CONFIG_DEBUG_FS
 	atomic_t buffer_underrun_count;
 	atomic_t bus_error_count;
-- 
cgit v1.2.3


From 1785dbc412c257879274e8807afd6dfdfe06c47b Mon Sep 17 00:00:00 2001
From: Noralf Trønnes <noralf@tronnes.org>
Date: Fri, 8 Dec 2017 20:37:35 +0100
Subject: drm/arm/hdlcd: Use drm_fb_cma_fbdev_init/fini()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use drm_fb_cma_fbdev_init() and drm_fb_cma_fbdev_fini() which relies on
the fact that drm_device holds a pointer to the drm_fb_helper structure.
This means that the driver doesn't have to keep track of that.
Also use the drm_fb_helper functions directly.

Cc: Liviu Dudau <liviu.dudau@arm.com>
Cc: Brian Starkey <brian.starkey@arm.com>
Signed-off-by: Noralf Trønnes <noralf@tronnes.org>
Acked-by: Liviu Dudau <liviu.dudau@arm.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/hdlcd_drv.c | 37 ++++++-------------------------------
 drivers/gpu/drm/arm/hdlcd_drv.h |  1 -
 2 files changed, 6 insertions(+), 32 deletions(-)

diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index 9800a9e388ef..fd5b8c44af14 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -101,16 +101,9 @@ setup_fail:
 	return ret;
 }
 
-static void hdlcd_fb_output_poll_changed(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-
-	drm_fbdev_cma_hotplug_event(hdlcd->fbdev);
-}
-
 static const struct drm_mode_config_funcs hdlcd_mode_config_funcs = {
 	.fb_create = drm_gem_fb_create,
-	.output_poll_changed = hdlcd_fb_output_poll_changed,
+	.output_poll_changed = drm_fb_helper_output_poll_changed,
 	.atomic_check = drm_atomic_helper_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
@@ -125,13 +118,6 @@ static void hdlcd_setup_mode_config(struct drm_device *drm)
 	drm->mode_config.funcs = &hdlcd_mode_config_funcs;
 }
 
-static void hdlcd_lastclose(struct drm_device *drm)
-{
-	struct hdlcd_drm_private *hdlcd = drm->dev_private;
-
-	drm_fbdev_cma_restore_mode(hdlcd->fbdev);
-}
-
 static irqreturn_t hdlcd_irq(int irq, void *arg)
 {
 	struct drm_device *drm = arg;
@@ -247,7 +233,7 @@ static struct drm_driver hdlcd_driver = {
 	.driver_features = DRIVER_HAVE_IRQ | DRIVER_GEM |
 			   DRIVER_MODESET | DRIVER_PRIME |
 			   DRIVER_ATOMIC,
-	.lastclose = hdlcd_lastclose,
+	.lastclose = drm_fb_helper_lastclose,
 	.irq_handler = hdlcd_irq,
 	.irq_preinstall = hdlcd_irq_preinstall,
 	.irq_postinstall = hdlcd_irq_postinstall,
@@ -322,14 +308,9 @@ static int hdlcd_drm_bind(struct device *dev)
 	drm_mode_config_reset(drm);
 	drm_kms_helper_poll_init(drm);
 
-	hdlcd->fbdev = drm_fbdev_cma_init(drm, 32,
-					  drm->mode_config.num_connector);
-
-	if (IS_ERR(hdlcd->fbdev)) {
-		ret = PTR_ERR(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
+	ret = drm_fb_cma_fbdev_init(drm, 32, 0);
+	if (ret)
 		goto err_fbdev;
-	}
 
 	ret = drm_dev_register(drm, 0);
 	if (ret)
@@ -338,10 +319,7 @@ static int hdlcd_drm_bind(struct device *dev)
 	return 0;
 
 err_register:
-	if (hdlcd->fbdev) {
-		drm_fbdev_cma_fini(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
-	}
+	drm_fb_cma_fbdev_fini(drm);
 err_fbdev:
 	drm_kms_helper_poll_fini(drm);
 err_vblank:
@@ -367,10 +345,7 @@ static void hdlcd_drm_unbind(struct device *dev)
 	struct hdlcd_drm_private *hdlcd = drm->dev_private;
 
 	drm_dev_unregister(drm);
-	if (hdlcd->fbdev) {
-		drm_fbdev_cma_fini(hdlcd->fbdev);
-		hdlcd->fbdev = NULL;
-	}
+	drm_fb_cma_fbdev_fini(drm);
 	drm_kms_helper_poll_fini(drm);
 	component_unbind_all(dev, drm);
 	of_node_put(hdlcd->crtc.port);
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.h b/drivers/gpu/drm/arm/hdlcd_drv.h
index 58d75d7e1b20..fd438d177b64 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.h
+++ b/drivers/gpu/drm/arm/hdlcd_drv.h
@@ -9,7 +9,6 @@
 struct hdlcd_drm_private {
 	void __iomem			*mmio;
 	struct clk			*clk;
-	struct drm_fbdev_cma		*fbdev;
 	struct drm_crtc			crtc;
 	struct drm_plane		*plane;
 #ifdef CONFIG_DEBUG_FS
-- 
cgit v1.2.3


From 8df24d57d34cd229e7094cfd1b927b585585202d Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Wed, 17 Jan 2018 23:55:27 +0200
Subject: drm: arm: hdlcd: Don't destroy plane manually in hdlcd_setup_crtc()

The top-level error handler calls drm_mode_config_cleanup() which will
destroy all planes. There's no need to destroy them manually in lower
error handlers.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/hdlcd_crtc.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index f3f08cd6e9ef..c36c75bef6d9 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -334,10 +334,8 @@ int hdlcd_setup_crtc(struct drm_device *drm)
 
 	ret = drm_crtc_init_with_planes(drm, &hdlcd->crtc, primary, NULL,
 					&hdlcd_crtc_funcs, NULL);
-	if (ret) {
-		hdlcd_plane_destroy(primary);
+	if (ret)
 		return ret;
-	}
 
 	drm_crtc_helper_add(&hdlcd->crtc, &hdlcd_crtc_helper_funcs);
 	return 0;
-- 
cgit v1.2.3


From 9fd466f54f89fc3a2dc6f86fce2ea0b993ff83bd Mon Sep 17 00:00:00 2001
From: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Date: Wed, 17 Jan 2018 23:55:28 +0200
Subject: drm: arm: hdlcd: Use drm_atomic_helper_shutdown() to disable planes
 on removal

The plane cleanup handler currently calls drm_plane_helper_disable(),
which is a legacy helper function. Replace it with a call to
drm_atomic_helper_shutdown() at removal time. The plane .destroy()
handler now consisting only of a call to drm_plane_cleanup(), replace it
with direct calls to that function.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/hdlcd_crtc.c | 8 +-------
 drivers/gpu/drm/arm/hdlcd_drv.c  | 1 +
 2 files changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index c36c75bef6d9..8978d82159e5 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -280,16 +280,10 @@ static const struct drm_plane_helper_funcs hdlcd_plane_helper_funcs = {
 	.atomic_update = hdlcd_plane_atomic_update,
 };
 
-static void hdlcd_plane_destroy(struct drm_plane *plane)
-{
-	drm_plane_helper_disable(plane, NULL);
-	drm_plane_cleanup(plane);
-}
-
 static const struct drm_plane_funcs hdlcd_plane_funcs = {
 	.update_plane		= drm_atomic_helper_update_plane,
 	.disable_plane		= drm_atomic_helper_disable_plane,
-	.destroy		= hdlcd_plane_destroy,
+	.destroy		= drm_plane_cleanup,
 	.reset			= drm_atomic_helper_plane_reset,
 	.atomic_duplicate_state = drm_atomic_helper_plane_duplicate_state,
 	.atomic_destroy_state	= drm_atomic_helper_plane_destroy_state,
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index fd5b8c44af14..70fca288313a 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -355,6 +355,7 @@ static void hdlcd_drm_unbind(struct device *dev)
 	pm_runtime_put_sync(drm->dev);
 	pm_runtime_disable(drm->dev);
 	of_reserved_mem_device_release(drm->dev);
+	drm_atomic_helper_shutdown(drm);
 	drm_mode_config_cleanup(drm);
 	drm_dev_put(drm);
 	drm->dev_private = NULL;
-- 
cgit v1.2.3


From d664b851eb2bcdf84a3c063cf59457bb15bc6120 Mon Sep 17 00:00:00 2001
From: Liviu Dudau <Liviu.Dudau@arm.com>
Date: Mon, 23 Jul 2018 12:05:53 +0100
Subject: drm/arm/hdlcd: Reject atomic commits that disable only the plane

The HDLCD engine needs an active plane while the CRTC is active, as
it will start scanning out data from HDLCD_REG_FB_BASE once it gets
enabled. Make sure that the only available plane doesn't get disabled
while the CRTC remains active, as this will scanout invalid data.

Signed-off-by: Liviu Dudau <liviu.dudau@arm.com>
---
 drivers/gpu/drm/arm/hdlcd_crtc.c | 23 +++++++++++------------
 drivers/gpu/drm/arm/hdlcd_drv.c  | 13 ++++++++-----
 2 files changed, 19 insertions(+), 17 deletions(-)

diff --git a/drivers/gpu/drm/arm/hdlcd_crtc.c b/drivers/gpu/drm/arm/hdlcd_crtc.c
index 8978d82159e5..e4d67b70244d 100644
--- a/drivers/gpu/drm/arm/hdlcd_crtc.c
+++ b/drivers/gpu/drm/arm/hdlcd_crtc.c
@@ -229,6 +229,8 @@ static const struct drm_crtc_helper_funcs hdlcd_crtc_helper_funcs = {
 static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 				    struct drm_plane_state *state)
 {
+	int i;
+	struct drm_crtc *crtc;
 	struct drm_crtc_state *crtc_state;
 	u32 src_h = state->src_h >> 16;
 
@@ -238,20 +240,17 @@ static int hdlcd_plane_atomic_check(struct drm_plane *plane,
 		return -EINVAL;
 	}
 
-	if (!state->fb || !state->crtc)
-		return 0;
-
-	crtc_state = drm_atomic_get_existing_crtc_state(state->state,
-							state->crtc);
-	if (!crtc_state) {
-		DRM_DEBUG_KMS("Invalid crtc state\n");
-		return -EINVAL;
+	for_each_new_crtc_in_state(state->state, crtc, crtc_state, i) {
+		/* we cannot disable the plane while the CRTC is active */
+		if (!state->fb && crtc_state->active)
+			return -EINVAL;
+		return drm_atomic_helper_check_plane_state(state, crtc_state,
+						DRM_PLANE_HELPER_NO_SCALING,
+						DRM_PLANE_HELPER_NO_SCALING,
+						false, true);
 	}
 
-	return drm_atomic_helper_check_plane_state(state, crtc_state,
-						   DRM_PLANE_HELPER_NO_SCALING,
-						   DRM_PLANE_HELPER_NO_SCALING,
-						   false, true);
+	return 0;
 }
 
 static void hdlcd_plane_atomic_update(struct drm_plane *plane,
diff --git a/drivers/gpu/drm/arm/hdlcd_drv.c b/drivers/gpu/drm/arm/hdlcd_drv.c
index 70fca288313a..0ed1cde98cf8 100644
--- a/drivers/gpu/drm/arm/hdlcd_drv.c
+++ b/drivers/gpu/drm/arm/hdlcd_drv.c
@@ -325,6 +325,7 @@ err_fbdev:
 err_vblank:
 	pm_runtime_disable(drm->dev);
 err_pm_active:
+	drm_atomic_helper_shutdown(drm);
 	component_unbind_all(dev, drm);
 err_unload:
 	of_node_put(hdlcd->crtc.port);
@@ -350,16 +351,18 @@ static void hdlcd_drm_unbind(struct device *dev)
 	component_unbind_all(dev, drm);
 	of_node_put(hdlcd->crtc.port);
 	hdlcd->crtc.port = NULL;
-	pm_runtime_get_sync(drm->dev);
+	pm_runtime_get_sync(dev);
+	drm_crtc_vblank_off(&hdlcd->crtc);
 	drm_irq_uninstall(drm);
-	pm_runtime_put_sync(drm->dev);
-	pm_runtime_disable(drm->dev);
-	of_reserved_mem_device_release(drm->dev);
 	drm_atomic_helper_shutdown(drm);
+	pm_runtime_put(dev);
+	if (pm_runtime_enabled(dev))
+		pm_runtime_disable(dev);
+	of_reserved_mem_device_release(dev);
 	drm_mode_config_cleanup(drm);
-	drm_dev_put(drm);
 	drm->dev_private = NULL;
 	dev_set_drvdata(dev, NULL);
+	drm_dev_put(drm);
 }
 
 static const struct component_master_ops hdlcd_master_ops = {
-- 
cgit v1.2.3


From f7368a550275ee56da70fd4d603d5a3eb4b614e9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 30 Jul 2018 00:03:42 +0200
Subject: PCI: Use IRQF_ONESHOT if pci_request_irq() called with no handler

If we have a threaded interrupt with the handler being NULL, then
request_threaded_irq() -> __setup_irq() will complain and bail out if the
IRQF_ONESHOT flag isn't set.  Therefore check for the handler being NULL
and set IRQF_ONESHOT in this case.

This change is needed to migrate the mei_me driver to
pci_alloc_irq_vectors() and pci_request_irq().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
---
 drivers/pci/irq.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/irq.c b/drivers/pci/irq.c
index 2a808e10645f..a1de501a2729 100644
--- a/drivers/pci/irq.c
+++ b/drivers/pci/irq.c
@@ -86,13 +86,17 @@ int pci_request_irq(struct pci_dev *dev, unsigned int nr, irq_handler_t handler,
 	va_list ap;
 	int ret;
 	char *devname;
+	unsigned long irqflags = IRQF_SHARED;
+
+	if (!handler)
+		irqflags |= IRQF_ONESHOT;
 
 	va_start(ap, fmt);
 	devname = kvasprintf(GFP_KERNEL, fmt, ap);
 	va_end(ap);
 
 	ret = request_threaded_irq(pci_irq_vector(dev, nr), handler, thread_fn,
-			IRQF_SHARED, devname, dev_id);
+				   irqflags, devname, dev_id);
 	if (ret)
 		kfree(devname);
 	return ret;
-- 
cgit v1.2.3


From 8cce437fbb5c1f2af2f63834fa05082596beca5d Mon Sep 17 00:00:00 2001
From: Philipp Rudo <prudo@linux.ibm.com>
Date: Thu, 19 Jul 2018 11:13:45 +0200
Subject: s390/kdump: Fix elfcorehdr size calculation

Before the memory for the elfcorehdr is allocated the required size is
estimated with

       alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
               mem_chunk_cnt * sizeof(Elf64_Phdr);

Where 0x4a0 is used as size for the ELF notes to store the register
contend. This size is 8 bytes too small. Usually this does not immediately
cause a problem because the page reserved for overhead (Elf_Ehdr,
vmcoreinfo, etc.) is pretty generous. So usually there is enough spare
memory to counter the mis-calculated per cpu size. However, with growing
overhead and/or a huge cpu count the allocated size gets too small for the
elfcorehdr. Ultimately a BUG_ON is triggered causing the crash kernel to
panic.

Fix this by properly calculating the required size instead of relying on
magic numbers.

Fixes: a62bc07392539 ("s390/kdump: add support for vector extension")
Signed-off-by: Philipp Rudo <prudo@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/kernel/crash_dump.c | 104 +++++++++++++++++++++++++++++++++++++++---
 1 file changed, 98 insertions(+), 6 deletions(-)

diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c
index 9f5ea9d87069..c3620bafc374 100644
--- a/arch/s390/kernel/crash_dump.c
+++ b/arch/s390/kernel/crash_dump.c
@@ -306,6 +306,15 @@ static void *kzalloc_panic(int len)
 	return rc;
 }
 
+static const char *nt_name(Elf64_Word type)
+{
+	const char *name = "LINUX";
+
+	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
+		name = KEXEC_CORE_NOTE_NAME;
+	return name;
+}
+
 /*
  * Initialize ELF note
  */
@@ -332,11 +341,26 @@ static void *nt_init_name(void *buf, Elf64_Word type, void *desc, int d_len,
 
 static inline void *nt_init(void *buf, Elf64_Word type, void *desc, int d_len)
 {
-	const char *note_name = "LINUX";
+	return nt_init_name(buf, type, desc, d_len, nt_name(type));
+}
+
+/*
+ * Calculate the size of ELF note
+ */
+static size_t nt_size_name(int d_len, const char *name)
+{
+	size_t size;
 
-	if (type == NT_PRPSINFO || type == NT_PRSTATUS || type == NT_PRFPREG)
-		note_name = KEXEC_CORE_NOTE_NAME;
-	return nt_init_name(buf, type, desc, d_len, note_name);
+	size = sizeof(Elf64_Nhdr);
+	size += roundup(strlen(name) + 1, 4);
+	size += roundup(d_len, 4);
+
+	return size;
+}
+
+static inline size_t nt_size(Elf64_Word type, int d_len)
+{
+	return nt_size_name(d_len, nt_name(type));
 }
 
 /*
@@ -374,6 +398,29 @@ static void *fill_cpu_elf_notes(void *ptr, int cpu, struct save_area *sa)
 	return ptr;
 }
 
+/*
+ * Calculate size of ELF notes per cpu
+ */
+static size_t get_cpu_elf_notes_size(void)
+{
+	struct save_area *sa = NULL;
+	size_t size;
+
+	size =	nt_size(NT_PRSTATUS, sizeof(struct elf_prstatus));
+	size +=  nt_size(NT_PRFPREG, sizeof(elf_fpregset_t));
+	size +=  nt_size(NT_S390_TIMER, sizeof(sa->timer));
+	size +=  nt_size(NT_S390_TODCMP, sizeof(sa->todcmp));
+	size +=  nt_size(NT_S390_TODPREG, sizeof(sa->todpreg));
+	size +=  nt_size(NT_S390_CTRS, sizeof(sa->ctrs));
+	size +=  nt_size(NT_S390_PREFIX, sizeof(sa->prefix));
+	if (MACHINE_HAS_VX) {
+		size += nt_size(NT_S390_VXRS_HIGH, sizeof(sa->vxrs_high));
+		size += nt_size(NT_S390_VXRS_LOW, sizeof(sa->vxrs_low));
+	}
+
+	return size;
+}
+
 /*
  * Initialize prpsinfo note (new kernel)
  */
@@ -429,6 +476,30 @@ static void *nt_vmcoreinfo(void *ptr)
 	return nt_init_name(ptr, 0, vmcoreinfo, size, "VMCOREINFO");
 }
 
+static size_t nt_vmcoreinfo_size(void)
+{
+	const char *name = "VMCOREINFO";
+	char nt_name[11];
+	Elf64_Nhdr note;
+	void *addr;
+
+	if (copy_oldmem_kernel(&addr, &S390_lowcore.vmcore_info, sizeof(addr)))
+		return 0;
+
+	if (copy_oldmem_kernel(&note, addr, sizeof(note)))
+		return 0;
+
+	memset(nt_name, 0, sizeof(nt_name));
+	if (copy_oldmem_kernel(nt_name, addr + sizeof(note),
+			       sizeof(nt_name) - 1))
+		return 0;
+
+	if (strcmp(nt_name, name) != 0)
+		return 0;
+
+	return nt_size_name(note.n_descsz, name);
+}
+
 /*
  * Initialize final note (needed for /proc/vmcore code)
  */
@@ -539,6 +610,27 @@ static void *notes_init(Elf64_Phdr *phdr, void *ptr, u64 notes_offset)
 	return ptr;
 }
 
+static size_t get_elfcorehdr_size(int mem_chunk_cnt)
+{
+	size_t size;
+
+	size = sizeof(Elf64_Ehdr);
+	/* PT_NOTES */
+	size += sizeof(Elf64_Phdr);
+	/* nt_prpsinfo */
+	size += nt_size(NT_PRPSINFO, sizeof(struct elf_prpsinfo));
+	/* regsets */
+	size += get_cpu_cnt() * get_cpu_elf_notes_size();
+	/* nt_vmcoreinfo */
+	size += nt_vmcoreinfo_size();
+	/* nt_final */
+	size += sizeof(Elf64_Nhdr);
+	/* PT_LOADS */
+	size += mem_chunk_cnt * sizeof(Elf64_Phdr);
+
+	return size;
+}
+
 /*
  * Create ELF core header (new kernel)
  */
@@ -566,8 +658,8 @@ int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
 
 	mem_chunk_cnt = get_mem_chunk_cnt();
 
-	alloc_size = 0x1000 + get_cpu_cnt() * 0x4a0 +
-		mem_chunk_cnt * sizeof(Elf64_Phdr);
+	alloc_size = get_elfcorehdr_size(mem_chunk_cnt);
+
 	hdr = kzalloc_panic(alloc_size);
 	/* Init elf header */
 	ptr = ehdr_init(hdr, mem_chunk_cnt);
-- 
cgit v1.2.3


From 5b3f7b7d062bc839fe0744bdfd0cfd7e8d1c4cd9 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sat, 28 Jul 2018 07:18:00 +0200
Subject: PCI: pciehp: Avoid slot access during reset

The ->reset_slot callback introduced by commits:

  2e35afaefe64 ("PCI: pciehp: Add reset_slot() method") and
  06a8d89af551 ("PCI: pciehp: Disable link notification across slot reset")

disables notification of Presence Detect Changed and Data Link Layer
State Changed events for the duration of a secondary bus reset.

However a bus reset not only triggers these events, but may also clear
the Presence Detect State bit in the Slot Status register and the Data
Link Layer Link Active bit in the Link Status register momentarily.
According to Sinan Kaya:

 "I know for a fact that bus reset clears the Data Link Layer Active bit
  as soon as link goes down.  It gets set again following link up.
  Presence detect depends on the HW implementation.  QDT root ports
  don't change presence detect for instance since nobody actually
  removed the card.  If an implementation supports in-band presence
  detect, the answer is yes.  As soon as the link goes down, presence
  detect bit will get cleared until recovery."
  https://lkml.kernel.org/r/42e72f83-3b24-f7ef-e5bc-290fae99259a@codeaurora.org

  In-band presence detect is also covered in Table 4-15 in PCIe r4.0,
  sec 4.2.6.

pciehp should therefore ensure that any parts of the driver that access
those bits do not run concurrently to a bus reset.  The only precaution
the commits took to that effect was to halt interrupt polling.  They
made no effort to drain the slot workqueue, cancel an outstanding
Attention Button work, or block slot enable/disable requests via sysfs
and in the ->probe hook.

Now that pciehp is converted to enable/disable the slot exclusively from
the IRQ thread, the only places accessing the two above-mentioned bits
are the IRQ thread and the ->probe hook.  Add locking to serialize them
with a bus reset.  This obviates the need to halt interrupt polling.
Do not add locking to the ->get_adapter_status sysfs callback to afford
users unfettered access to that bit.  Use an rw_semaphore in lieu of a
regular mutex to allow parallel execution of the non-reset code paths
accessing the critical bits, i.e. the IRQ thread and the ->probe hook.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rajat Jain <rajatja@google.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Sinan Kaya <okaya@kernel.org>
---
 drivers/pci/hotplug/pciehp.h      |  5 +++++
 drivers/pci/hotplug/pciehp_core.c |  2 ++
 drivers/pci/hotplug/pciehp_hpc.c  | 14 +++++++-------
 3 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 47cd9af5caf3..bb015be34894 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -21,6 +21,7 @@
 #include <linux/delay.h>
 #include <linux/sched/signal.h>		/* signal_pending() */
 #include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/workqueue.h>
 
 #include "../pcie/portdrv.h"
@@ -80,6 +81,9 @@ struct slot {
  * struct controller - PCIe hotplug controller
  * @ctrl_lock: serializes writes to the Slot Control register
  * @pcie: pointer to the controller's PCIe port service device
+ * @reset_lock: prevents access to the Data Link Layer Link Active bit in the
+ *	Link Status register and to the Presence Detect State bit in the Slot
+ *	Status register during a slot reset which may cause them to flap
  * @slot: pointer to the controller's slot structure
  * @queue: wait queue to wake up on reception of a Command Completed event,
  *	used for synchronous writes to the Slot Control register
@@ -109,6 +113,7 @@ struct slot {
 struct controller {
 	struct mutex ctrl_lock;
 	struct pcie_device *pcie;
+	struct rw_semaphore reset_lock;
 	struct slot *slot;
 	wait_queue_head_t queue;
 	u32 slot_cap;
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index f4eaa9944699..1be8871e7439 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -237,6 +237,7 @@ static int pciehp_probe(struct pcie_device *dev)
 	}
 
 	/* Check if slot is occupied */
+	down_read(&ctrl->reset_lock);
 	mutex_lock(&slot->lock);
 	pciehp_get_adapter_status(slot, &occupied);
 	pciehp_get_power_status(slot, &poweron);
@@ -249,6 +250,7 @@ static int pciehp_probe(struct pcie_device *dev)
 	if (!occupied && poweron && POWER_CTRL(ctrl))
 		pciehp_power_off_slot(slot);
 	mutex_unlock(&slot->lock);
+	up_read(&ctrl->reset_lock);
 
 	return 0;
 
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 712f3de78b09..41398b15d306 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -603,10 +603,12 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 	 * Disable requests have higher priority than Presence Detect Changed
 	 * or Data Link Layer State Changed events.
 	 */
+	down_read(&ctrl->reset_lock);
 	if (events & DISABLE_SLOT)
 		pciehp_handle_disable_request(slot);
 	else if (events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC))
 		pciehp_handle_presence_or_link_change(slot, events);
+	up_read(&ctrl->reset_lock);
 
 	/* Check Power Fault Detected */
 	if ((events & PCI_EXP_SLTSTA_PFD) && !ctrl->power_fault_detected) {
@@ -627,9 +629,6 @@ static int pciehp_poll(void *data)
 	schedule_timeout_idle(10 * HZ); /* start with 10 sec delay */
 
 	while (!kthread_should_stop()) {
-		if (kthread_should_park())
-			kthread_parkme();
-
 		/* poll for interrupt events or user requests */
 		while (pciehp_isr(IRQ_NOTCONNECTED, ctrl) == IRQ_WAKE_THREAD ||
 		       atomic_read(&ctrl->pending_events))
@@ -723,6 +722,8 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	if (probe)
 		return 0;
 
+	down_write(&ctrl->reset_lock);
+
 	if (!ATTN_BUTTN(ctrl)) {
 		ctrl_mask |= PCI_EXP_SLTCTL_PDCE;
 		stat_mask |= PCI_EXP_SLTSTA_PDC;
@@ -733,8 +734,6 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	pcie_write_cmd(ctrl, 0, ctrl_mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
-	if (pciehp_poll_mode)
-		kthread_park(ctrl->poll_thread);
 
 	pci_reset_bridge_secondary_bus(ctrl->pcie->port);
 
@@ -742,8 +741,8 @@ int pciehp_reset_slot(struct slot *slot, int probe)
 	pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask);
-	if (pciehp_poll_mode)
-		kthread_unpark(ctrl->poll_thread);
+
+	up_write(&ctrl->reset_lock);
 	return 0;
 }
 
@@ -835,6 +834,7 @@ struct controller *pcie_init(struct pcie_device *dev)
 
 	ctrl->slot_cap = slot_cap;
 	mutex_init(&ctrl->ctrl_lock);
+	init_rwsem(&ctrl->reset_lock);
 	init_waitqueue_head(&ctrl->requester);
 	init_waitqueue_head(&ctrl->queue);
 	dbg_ctrl(ctrl);
-- 
cgit v1.2.3


From 6ccb127ba6dff251b75fa72e8c7777eaf12d9675 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:52 -0500
Subject: PCI: portdrv: Deduplicate PM callback iterator

Replace suspend_iter() and resume_iter() with a single function pm_iter()
to allow addition of port service callbacks for further power management
phases without having to add another iterator each time.

No functional change intended.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/portdrv_core.c | 30 ++++++++++++------------------
 1 file changed, 12 insertions(+), 18 deletions(-)

diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index e0261ad4bcdd..13a248575a14 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -353,14 +353,19 @@ error_disable:
 }
 
 #ifdef CONFIG_PM
-static int suspend_iter(struct device *dev, void *data)
+typedef int (*pcie_pm_callback_t)(struct pcie_device *);
+
+static int pm_iter(struct device *dev, void *data)
 {
 	struct pcie_port_service_driver *service_driver;
+	size_t offset = *(size_t *)data;
+	pcie_pm_callback_t cb;
 
 	if ((dev->bus == &pcie_port_bus_type) && dev->driver) {
 		service_driver = to_service_driver(dev->driver);
-		if (service_driver->suspend)
-			service_driver->suspend(to_pcie_device(dev));
+		cb = *(pcie_pm_callback_t *)((void *)service_driver + offset);
+		if (cb)
+			return cb(to_pcie_device(dev));
 	}
 	return 0;
 }
@@ -371,20 +376,8 @@ static int suspend_iter(struct device *dev, void *data)
  */
 int pcie_port_device_suspend(struct device *dev)
 {
-	return device_for_each_child(dev, NULL, suspend_iter);
-}
-
-static int resume_iter(struct device *dev, void *data)
-{
-	struct pcie_port_service_driver *service_driver;
-
-	if ((dev->bus == &pcie_port_bus_type) &&
-	    (dev->driver)) {
-		service_driver = to_service_driver(dev->driver);
-		if (service_driver->resume)
-			service_driver->resume(to_pcie_device(dev));
-	}
-	return 0;
+	size_t off = offsetof(struct pcie_port_service_driver, suspend);
+	return device_for_each_child(dev, &off, pm_iter);
 }
 
 /**
@@ -393,7 +386,8 @@ static int resume_iter(struct device *dev, void *data)
  */
 int pcie_port_device_resume(struct device *dev)
 {
-	return device_for_each_child(dev, NULL, resume_iter);
+	size_t off = offsetof(struct pcie_port_service_driver, resume);
+	return device_for_each_child(dev, &off, pm_iter);
 }
 #endif /* PM */
 
-- 
cgit v1.2.3


From 7903782460ee1813d6779c968b28d0ac71b9b3ae Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:53 -0500
Subject: PCI: pciehp: Clear spurious events earlier on resume

Thunderbolt hotplug ports that were occupied before system sleep resume
with their downstream link in "off" state.  Only after the Thunderbolt
controller has reestablished the PCIe tunnels does the link go up.
As a result, a spurious Presence Detect Changed and/or Data Link Layer
State Changed event occurs.

The events are not immediately acted upon because tunnel reestablishment
happens in the ->resume_noirq phase, when interrupts are still disabled.
Also, notification of events may initially be disabled in the Slot
Control register when coming out of system sleep and is reenabled in the
->resume_noirq phase through:

  pci_pm_resume_noirq()
    pci_pm_default_resume_early()
      pci_restore_state()
        pci_restore_pcie_state()

It is not guaranteed that the events are acted upon at all:  PCIe r4.0,
sec 6.7.3.4 says that "a port may optionally send an MSI when there are
hot-plug events that occur while interrupt generation is disabled, and
interrupt generation is subsequently enabled."  Note the "optionally".

If an MSI is sent, pciehp will gratuitously turn the slot off and back
on once the ->resume_early phase has commenced.

If an MSI is not sent, the extant, unacknowledged events in the Slot
Status register will prevent future notification of presence or link
changes.

Commit 13c65840feab ("PCI: pciehp: Clear Presence Detect and Data Link
Layer Status Changed on resume") fixed the latter by clearing the events
in the ->resume phase.  Move this to the ->resume_noirq phase to also
fix the gratuitous disable/enablement of the slot.

The commit further restored the Slot Control register in the ->resume
phase, but that's dispensable because as shown above it's already been
done in the ->resume_noirq phase.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pci/hotplug/pciehp.h      |  2 +-
 drivers/pci/hotplug/pciehp_core.c | 17 +++++++++++++----
 drivers/pci/hotplug/pciehp_hpc.c  | 17 ++++++-----------
 drivers/pci/pcie/portdrv.h        |  2 ++
 drivers/pci/pcie/portdrv_core.c   |  6 ++++++
 drivers/pci/pcie/portdrv_pci.c    |  2 ++
 6 files changed, 30 insertions(+), 16 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index bb015be34894..247681963063 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -181,7 +181,7 @@ void pciehp_queue_pushbutton_work(struct work_struct *work);
 struct controller *pcie_init(struct pcie_device *dev);
 int pcie_init_notification(struct controller *ctrl);
 void pcie_shutdown_notification(struct controller *ctrl);
-void pcie_reenable_notification(struct controller *ctrl);
+void pcie_clear_hotplug_events(struct controller *ctrl);
 int pciehp_power_on_slot(struct slot *slot);
 void pciehp_power_off_slot(struct slot *slot);
 void pciehp_get_power_status(struct slot *slot, u8 *status);
diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 1be8871e7439..a5bd3b055c0e 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -279,6 +279,18 @@ static int pciehp_suspend(struct pcie_device *dev)
 	return 0;
 }
 
+static int pciehp_resume_noirq(struct pcie_device *dev)
+{
+	struct controller *ctrl = get_service_data(dev);
+	struct slot *slot = ctrl->slot;
+
+	/* clear spurious events from rediscovery of inserted card */
+	if (slot->state == ON_STATE || slot->state == BLINKINGOFF_STATE)
+		pcie_clear_hotplug_events(ctrl);
+
+	return 0;
+}
+
 static int pciehp_resume(struct pcie_device *dev)
 {
 	struct controller *ctrl;
@@ -286,10 +298,6 @@ static int pciehp_resume(struct pcie_device *dev)
 	u8 status;
 
 	ctrl = get_service_data(dev);
-
-	/* reinitialize the chipset's event detection logic */
-	pcie_reenable_notification(ctrl);
-
 	slot = ctrl->slot;
 
 	/* Check if slot is occupied */
@@ -316,6 +324,7 @@ static struct pcie_port_service_driver hpdriver_portdrv = {
 
 #ifdef	CONFIG_PM
 	.suspend	= pciehp_suspend,
+	.resume_noirq	= pciehp_resume_noirq,
 	.resume		= pciehp_resume,
 #endif	/* PM */
 };
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 41398b15d306..6313ddf38a51 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -681,17 +681,6 @@ static void pcie_enable_notification(struct controller *ctrl)
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, cmd);
 }
 
-void pcie_reenable_notification(struct controller *ctrl)
-{
-	/*
-	 * Clear both Presence and Data Link Layer Changed to make sure
-	 * those events still fire after we have re-enabled them.
-	 */
-	pcie_capability_write_word(ctrl->pcie->port, PCI_EXP_SLTSTA,
-				   PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC);
-	pcie_enable_notification(ctrl);
-}
-
 static void pcie_disable_notification(struct controller *ctrl)
 {
 	u16 mask;
@@ -705,6 +694,12 @@ static void pcie_disable_notification(struct controller *ctrl)
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0);
 }
 
+void pcie_clear_hotplug_events(struct controller *ctrl)
+{
+	pcie_capability_write_word(ctrl_dev(ctrl), PCI_EXP_SLTSTA,
+				   PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC);
+}
+
 /*
  * pciehp has a 1:1 bus:slot relationship so we ultimately want a secondary
  * bus reset of the bridge, but at the same time we want to ensure that it is
diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h
index 6ffc797a0dc1..d59afa42fc14 100644
--- a/drivers/pci/pcie/portdrv.h
+++ b/drivers/pci/pcie/portdrv.h
@@ -50,6 +50,7 @@ struct pcie_port_service_driver {
 	int (*probe) (struct pcie_device *dev);
 	void (*remove) (struct pcie_device *dev);
 	int (*suspend) (struct pcie_device *dev);
+	int (*resume_noirq) (struct pcie_device *dev);
 	int (*resume) (struct pcie_device *dev);
 
 	/* Device driver may resume normal operations */
@@ -82,6 +83,7 @@ extern struct bus_type pcie_port_bus_type;
 int pcie_port_device_register(struct pci_dev *dev);
 #ifdef CONFIG_PM
 int pcie_port_device_suspend(struct device *dev);
+int pcie_port_device_resume_noirq(struct device *dev);
 int pcie_port_device_resume(struct device *dev);
 #endif
 void pcie_port_device_remove(struct pci_dev *dev);
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 13a248575a14..7c37d815229e 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -380,6 +380,12 @@ int pcie_port_device_suspend(struct device *dev)
 	return device_for_each_child(dev, &off, pm_iter);
 }
 
+int pcie_port_device_resume_noirq(struct device *dev)
+{
+	size_t off = offsetof(struct pcie_port_service_driver, resume_noirq);
+	return device_for_each_child(dev, &off, pm_iter);
+}
+
 /**
  * pcie_port_device_resume - resume port services associated with a PCIe port
  * @dev: PCI Express port to handle
diff --git a/drivers/pci/pcie/portdrv_pci.c b/drivers/pci/pcie/portdrv_pci.c
index 973f1b80a038..5e0f02c68faa 100644
--- a/drivers/pci/pcie/portdrv_pci.c
+++ b/drivers/pci/pcie/portdrv_pci.c
@@ -76,10 +76,12 @@ static int pcie_port_runtime_idle(struct device *dev)
 
 static const struct dev_pm_ops pcie_portdrv_pm_ops = {
 	.suspend	= pcie_port_device_suspend,
+	.resume_noirq	= pcie_port_device_resume_noirq,
 	.resume		= pcie_port_device_resume,
 	.freeze		= pcie_port_device_suspend,
 	.thaw		= pcie_port_device_resume,
 	.poweroff	= pcie_port_device_suspend,
+	.restore_noirq	= pcie_port_device_resume_noirq,
 	.restore	= pcie_port_device_resume,
 	.runtime_suspend = pcie_port_runtime_suspend,
 	.runtime_resume	= pcie_port_runtime_resume,
-- 
cgit v1.2.3


From 469e764c4a3c7260b353b7bc1bd56c283cb001da Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:54 -0500
Subject: PCI: pciehp: Obey compulsory command delay after resume

Upon resume from system sleep, the Slot Control register is written via:

  pci_pm_resume_noirq()
    pci_pm_default_resume_early()
      pci_restore_state()
        pci_restore_pcie_state()

PCIe r4.0, sec 6.7.3.2 says that after "issuing a write transaction that
targets any portion of the Port's Slot Control register, [...] software
must wait for [the] command to complete before issuing the next command".

pciehp currently fails to enforce that rule after the above-mentioned
write.  Fix it.

(Moving restoration of the Slot Control register to pciehp doesn't seem
to make sense because the other PCIe hotplug drivers may need it as
well.)

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/hotplug/pciehp_core.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index a5bd3b055c0e..3e73b12ed656 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -284,6 +284,10 @@ static int pciehp_resume_noirq(struct pcie_device *dev)
 	struct controller *ctrl = get_service_data(dev);
 	struct slot *slot = ctrl->slot;
 
+	/* pci_restore_state() just wrote to the Slot Control register */
+	ctrl->cmd_started = jiffies;
+	ctrl->cmd_busy = true;
+
 	/* clear spurious events from rediscovery of inserted card */
 	if (slot->state == ON_STATE || slot->state == BLINKINGOFF_STATE)
 		pcie_clear_hotplug_events(ctrl);
-- 
cgit v1.2.3


From 6b08c3854cfdc5d13165880e2b54642c47edc405 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sat, 28 Jul 2018 07:18:00 +0200
Subject: PCI: pciehp: Support interrupts sent from D3hot

If a hotplug port is able to send an interrupt, one would naively assume
that it is accessible at that moment.  After all, if it wouldn't be
accessible, i.e. if its parent is in D3hot and the link to the hotplug
port is thus down, how should an interrupt come through?

It turns out that assumption is wrong at least for Thunderbolt:  Even
though its parents are in D3hot, a Thunderbolt hotplug port is able to
signal interrupts.  Because the port's config space is inaccessible and
resuming the parents may sleep, the hard IRQ handler has to defer
runtime resuming the parents and reading the Slot Status register to the
IRQ thread.

If the hotplug port uses a level-triggered INTx interrupt, it needs to
be masked until the IRQ thread has cleared the signaled events.  For
simplicity, this commit also masks edge-triggered MSI/MSI-X interrupts.
Note that if the interrupt is shared (which can only happen for INTx),
other devices are starved from receiving interrupts until the IRQ thread
is scheduled, has runtime resumed the hotplug port's parents and has
read and cleared the Slot Status register.

That delay is dominated by the 10 ms D3hot->D0 transition time of each
parent port.  The worst case is a Thunderbolt downstream port at the
end of a daisy chain:  There may be up to six Thunderbolt controllers
in-between it and the root port, each comprising an upstream and
downstream port, plus its own upstream port.  That's 13 x 10 = 130 ms.
Possible mitigations are polling the interrupt while it's disabled or
reducing the d3_delay of Thunderbolt ports if possible.

Open code masking of the interrupt instead of requesting it with the
IRQF_ONESHOT flag to minimize the period during which it is masked.
(IRQF_ONESHOT unmasks the IRQ only after the IRQ thread has finished.)

PCIe r4.0 sec 6.7.3.4 states that "If wake generation is required by the
associated form factor specification, a hotplug capable Downstream Port
must support generation of a wakeup event (using the PME mechanism) on
hotplug events that occur when the system is in a sleep state or the
Port is in device state D1, D2, or D3Hot."

This would seem to imply that PME needs to be enabled on the hotplug
port when it is runtime suspended.  pci_enable_wake() currently doesn't
enable PME on bridges, it may be necessary to add an exemption for
hotplug bridges there.  On "Light Ridge" Thunderbolt controllers, the
PME_Status bit is not set when an interrupt occurs while the hotplug
port is in D3hot, even if PME is enabled.  (I've tested this on a Mac
and we hardcode the OSC_PCI_EXPRESS_PME_CONTROL bit to 0 on Macs in
negotiate_os_control(), modifying it to 1 didn't change the behavior.)

(Side note:  Section 6.7.3.4 also states that "PME and Hot-Plug Event
interrupts (when both are implemented) always share the same MSI or
MSI-X vector".  That would only seem to apply to Root Ports, however
the section never mentions Root Ports, only Downstream Ports.  This is
explained in the definition of "Downstream Port" in the "Terms and
Acronyms" section of the PCIe Base Spec:  "The Ports on a Switch that
are not the Upstream Port are Downstream Ports.  All Ports on a Root
Complex are Downstream Ports.")

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
---
 drivers/pci/hotplug/pciehp.h     |  5 +++++
 drivers/pci/hotplug/pciehp_hpc.c | 45 ++++++++++++++++++++++++++++++++++++++--
 2 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h
index 247681963063..811cf83f956d 100644
--- a/drivers/pci/hotplug/pciehp.h
+++ b/drivers/pci/hotplug/pciehp.h
@@ -156,8 +156,13 @@ struct controller {
  *
  * %DISABLE_SLOT: Disable the slot in response to a user request via sysfs or
  *	an Attention Button press after the 5 second delay
+ * %RERUN_ISR: Used by the IRQ handler to inform the IRQ thread that the
+ *	hotplug port was inaccessible when the interrupt occurred, requiring
+ *	that the IRQ handler is rerun by the IRQ thread after it has made the
+ *	hotplug port accessible by runtime resuming its parents to D0
  */
 #define DISABLE_SLOT		(1 << 16)
+#define RERUN_ISR		(1 << 17)
 
 #define ATTN_BUTTN(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_ABP)
 #define POWER_CTRL(ctrl)	((ctrl)->slot_cap & PCI_EXP_SLTCAP_PCP)
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 6313ddf38a51..6e9b4330ad82 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -19,6 +19,7 @@
 #include <linux/jiffies.h>
 #include <linux/kthread.h>
 #include <linux/pci.h>
+#include <linux/pm_runtime.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/slab.h>
@@ -521,6 +522,7 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 {
 	struct controller *ctrl = (struct controller *)dev_id;
 	struct pci_dev *pdev = ctrl_dev(ctrl);
+	struct device *parent = pdev->dev.parent;
 	u16 status, events;
 
 	/*
@@ -529,9 +531,26 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	if (pdev->current_state == PCI_D3cold)
 		return IRQ_NONE;
 
+	/*
+	 * Keep the port accessible by holding a runtime PM ref on its parent.
+	 * Defer resume of the parent to the IRQ thread if it's suspended.
+	 * Mask the interrupt until then.
+	 */
+	if (parent) {
+		pm_runtime_get_noresume(parent);
+		if (!pm_runtime_active(parent)) {
+			pm_runtime_put(parent);
+			disable_irq_nosync(irq);
+			atomic_or(RERUN_ISR, &ctrl->pending_events);
+			return IRQ_WAKE_THREAD;
+		}
+	}
+
 	pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &status);
 	if (status == (u16) ~0) {
 		ctrl_info(ctrl, "%s: no response from device\n", __func__);
+		if (parent)
+			pm_runtime_put(parent);
 		return IRQ_NONE;
 	}
 
@@ -550,11 +569,16 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 	if (ctrl->power_fault_detected)
 		events &= ~PCI_EXP_SLTSTA_PFD;
 
-	if (!events)
+	if (!events) {
+		if (parent)
+			pm_runtime_put(parent);
 		return IRQ_NONE;
+	}
 
 	pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, events);
 	ctrl_dbg(ctrl, "pending interrupts %#06x from Slot Status\n", events);
+	if (parent)
+		pm_runtime_put(parent);
 
 	/*
 	 * Command Completed notifications are not deferred to the
@@ -584,13 +608,29 @@ static irqreturn_t pciehp_isr(int irq, void *dev_id)
 static irqreturn_t pciehp_ist(int irq, void *dev_id)
 {
 	struct controller *ctrl = (struct controller *)dev_id;
+	struct pci_dev *pdev = ctrl_dev(ctrl);
 	struct slot *slot = ctrl->slot;
+	irqreturn_t ret;
 	u32 events;
 
+	pci_config_pm_runtime_get(pdev);
+
+	/* rerun pciehp_isr() if the port was inaccessible on interrupt */
+	if (atomic_fetch_and(~RERUN_ISR, &ctrl->pending_events) & RERUN_ISR) {
+		ret = pciehp_isr(irq, dev_id);
+		enable_irq(irq);
+		if (ret != IRQ_WAKE_THREAD) {
+			pci_config_pm_runtime_put(pdev);
+			return ret;
+		}
+	}
+
 	synchronize_hardirq(irq);
 	events = atomic_xchg(&ctrl->pending_events, 0);
-	if (!events)
+	if (!events) {
+		pci_config_pm_runtime_put(pdev);
 		return IRQ_NONE;
+	}
 
 	/* Check Attention Button Pressed */
 	if (events & PCI_EXP_SLTSTA_ABP) {
@@ -618,6 +658,7 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id)
 		pciehp_green_led_off(slot);
 	}
 
+	pci_config_pm_runtime_put(pdev);
 	wake_up(&ctrl->requester);
 	return IRQ_HANDLED;
 }
-- 
cgit v1.2.3


From 8350307454240abeebe52ff5a73810d9ba93dd60 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:56 -0500
Subject: PCI: pciehp: Resume to D0 on enable/disable

pciehp's IRQ thread ensures accessibility of the port by runtime resuming
its parent to D0.  However when the slot is enabled/disabled, the port
itself needs to be in D0 because its secondary bus is accessed in:

    pciehp_check_link_status(),
    pciehp_configure_device() (both called from board_added())
and
    pciehp_unconfigure_device() (called from remove_board()).

Thus, acquire a runtime PM ref on enable/disablement of the slot.

Yinghai Lu additionally discovered that some SkyLake servers feature a
Power Controller for their PCIe hotplug ports (PCIe r3.1, sec 6.7.1.8)
which requires the port to be in D0 when invoking

    pciehp_power_on_slot() (likewise called from board_added()).

If slot power is turned on while in D3hot, link training later fails:
https://lkml.kernel.org/r/20170205073454.GA253@wunner.de

The spec is silent about such a requirement, but it seems prudent to
assume that any hotplug port with a Power Controller may need this.

The present commit holds a runtime PM ref whenever slot power is turned
on and off, but it doesn't keep the port in D0 as long as slot power is
on.  If vendors determine that's necessary, they need to amend pciehp to
acquire a runtime PM ref in pciehp_power_on_slot() and release one in
pciehp_power_off_slot().

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
---
 drivers/pci/hotplug/pciehp_ctrl.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 811019902ada..6855933ab372 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -17,6 +17,7 @@
 #include <linux/kernel.h>
 #include <linux/types.h>
 #include <linux/slab.h>
+#include <linux/pm_runtime.h>
 #include <linux/pci.h>
 #include "../pci.h"
 #include "pciehp.h"
@@ -310,9 +311,11 @@ static int pciehp_enable_slot(struct slot *slot)
 	struct controller *ctrl = slot->ctrl;
 	int ret;
 
+	pm_runtime_get_sync(&ctrl->pcie->port->dev);
 	ret = __pciehp_enable_slot(slot);
 	if (ret && ATTN_BUTTN(ctrl))
 		pciehp_green_led_off(slot); /* may be blinking */
+	pm_runtime_put(&ctrl->pcie->port->dev);
 
 	mutex_lock(&slot->lock);
 	slot->state = ret ? OFF_STATE : ON_STATE;
@@ -341,9 +344,12 @@ static int __pciehp_disable_slot(struct slot *p_slot)
 
 static int pciehp_disable_slot(struct slot *slot)
 {
+	struct controller *ctrl = slot->ctrl;
 	int ret;
 
+	pm_runtime_get_sync(&ctrl->pcie->port->dev);
 	ret = __pciehp_disable_slot(slot);
+	pm_runtime_put(&ctrl->pcie->port->dev);
 
 	mutex_lock(&slot->lock);
 	slot->state = OFF_STATE;
-- 
cgit v1.2.3


From 4417aa45c185376ece278430e33b6a1891a1dc36 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:57 -0500
Subject: PCI: pciehp: Resume parent to D0 on config space access

Ensure accessibility of a hotplug port's config space when accessed via
sysfs by resuming its parent to D0.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
---
 drivers/pci/hotplug/pciehp_core.c | 14 ++++++++++++++
 drivers/pci/hotplug/pciehp_hpc.c  |  7 +++++++
 2 files changed, 21 insertions(+)

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 3e73b12ed656..01fcf1fa0f66 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -26,6 +26,8 @@
 #include <linux/interrupt.h>
 #include <linux/time.h>
 
+#include "../pci.h"
+
 /* Global variables */
 bool pciehp_debug;
 bool pciehp_poll_mode;
@@ -126,8 +128,11 @@ static void cleanup_slot(struct controller *ctrl)
 static int set_attention_status(struct hotplug_slot *hotplug_slot, u8 status)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_set_attention_status(slot, status);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
@@ -150,8 +155,11 @@ static int disable_slot(struct hotplug_slot *hotplug_slot)
 static int get_power_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_get_power_status(slot, value);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
@@ -166,16 +174,22 @@ static int get_attention_status(struct hotplug_slot *hotplug_slot, u8 *value)
 static int get_latch_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_get_latch_status(slot, value);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
 static int get_adapter_status(struct hotplug_slot *hotplug_slot, u8 *value)
 {
 	struct slot *slot = hotplug_slot->private;
+	struct pci_dev *pdev = slot->ctrl->pcie->port;
 
+	pci_config_pm_runtime_get(pdev);
 	pciehp_get_adapter_status(slot, value);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 6e9b4330ad82..6f7de0819c88 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -322,7 +322,9 @@ int pciehp_get_raw_indicator_status(struct hotplug_slot *hotplug_slot,
 	struct pci_dev *pdev = ctrl_dev(slot->ctrl);
 	u16 slot_ctrl;
 
+	pci_config_pm_runtime_get(pdev);
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl);
+	pci_config_pm_runtime_put(pdev);
 	*status = (slot_ctrl & (PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC)) >> 6;
 	return 0;
 }
@@ -333,7 +335,9 @@ void pciehp_get_attention_status(struct slot *slot, u8 *status)
 	struct pci_dev *pdev = ctrl_dev(ctrl);
 	u16 slot_ctrl;
 
+	pci_config_pm_runtime_get(pdev);
 	pcie_capability_read_word(pdev, PCI_EXP_SLTCTL, &slot_ctrl);
+	pci_config_pm_runtime_put(pdev);
 	ctrl_dbg(ctrl, "%s: SLOTCTRL %x, value read %x\n", __func__,
 		 pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, slot_ctrl);
 
@@ -408,9 +412,12 @@ int pciehp_set_raw_indicator_status(struct hotplug_slot *hotplug_slot,
 {
 	struct slot *slot = hotplug_slot->private;
 	struct controller *ctrl = slot->ctrl;
+	struct pci_dev *pdev = ctrl_dev(ctrl);
 
+	pci_config_pm_runtime_get(pdev);
 	pcie_write_cmd_nowait(ctrl, status << 6,
 			      PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC);
+	pci_config_pm_runtime_put(pdev);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 82c3fbff6ed3582f2b14b5548fb976c22d7a7255 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:58 -0500
Subject: PCI: sysfs: Resume to D0 on function reset

When performing a function reset via sysfs, the device's config space is
accessed in places such as pcie_flr() and its MMIO space is accessed e.g.
in reset_ivb_igd(), so ensure accessibility by resuming the device to D0.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
---
 drivers/pci/pci-sysfs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 0c4653c1d2ce..a3df6b57df0f 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -1449,7 +1449,9 @@ static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
 	if (val != 1)
 		return -EINVAL;
 
+	pm_runtime_get_sync(dev);
 	result = pci_reset_function(pdev);
+	pm_runtime_put(dev);
 	if (result < 0)
 		return result;
 
-- 
cgit v1.2.3


From eb3b5bf1a88d0cc1cd7acc7464eb211d69779808 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:27:59 -0500
Subject: PCI: Whitelist native hotplug ports for runtime D3

Previously we blacklisted PCIe hotplug ports for runtime D3 because:

(a) Ports handled by the firmware must not be transitioned to D3 by the
    OS behind the firmware's back:
    https://bugzilla.kernel.org/show_bug.cgi?id=53811

(b) Ports handled natively by the OS lacked runtime D3 support in the
    pciehp driver.

We've just rectified the latter, so allow users to manually enable and
test it by passing pcie_port_pm=force on the command line.  Vendors are
thus put in a position to validate hotplug ports for runtime D3 and
perhaps we can someday enable it by default, but with a BIOS cutoff date.

Ashok Raj tested runtime D3 on hotplug ports of a SkyLake Xeon-SP in
2017 and encountered Hardware Error NMIs, so this feature clearly cannot
be enabled for everyone yet:
https://lkml.kernel.org/r/20170503180426.GA4058@otc-nc-03

While at it, remove an erroneous code comment I added with 97a90aee5dab
("PCI: Consolidate conditions to allow runtime PM on PCIe ports") which
claims that parents of a hotplug port must stay awake lest interrupts
cannot be delivered.  That has turned out to be wrong at least for
Thunderbolt hotplug ports.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Ashok Raj <ashok.raj@intel.com>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Yinghai Lu <yinghai@kernel.org>
---
 drivers/pci/pci.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..4099a6c14b6d 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2305,18 +2305,23 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge)
 			return false;
 
 		/*
-		 * Hotplug interrupts cannot be delivered if the link is down,
-		 * so parents of a hotplug port must stay awake. In addition,
-		 * hotplug ports handled by firmware in System Management Mode
+		 * Hotplug ports handled by firmware in System Management Mode
 		 * may not be put into D3 by the OS (Thunderbolt on non-Macs).
-		 * For simplicity, disallow in general for now.
 		 */
-		if (bridge->is_hotplug_bridge)
+		if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge))
 			return false;
 
 		if (pci_bridge_d3_force)
 			return true;
 
+		/*
+		 * Hotplug ports handled natively by the OS were not validated
+		 * by vendors for runtime D3 at least until 2018 because there
+		 * was no OS support.
+		 */
+		if (bridge->is_hotplug_bridge)
+			return false;
+
 		/*
 		 * It should be safe to put PCIe ports from 2015 or newer
 		 * to D3.
-- 
cgit v1.2.3


From 47a8e237ed443c174f8f73402755c458c56eb611 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Thu, 19 Jul 2018 17:28:00 -0500
Subject: PCI: Whitelist Thunderbolt ports for runtime D3

Thunderbolt controllers can be runtime suspended to D3cold to save ~1.5W.
This requires that runtime D3 is allowed on its PCIe ports, so whitelist
them.

The 2015 BIOS cutoff that we've instituted for runtime D3 on PCIe ports
is unnecessary on Thunderbolt because we know that even the oldest
controller, Light Ridge (2010), is able to suspend its ports to D3 just
fine -- specifically including its hotplug ports.  And the power saving
should be afforded to machines even if their BIOS predates 2015.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Cc: Andreas Noever <andreas.noever@gmail.com>
---
 drivers/pci/pci.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 4099a6c14b6d..c4d10726c59a 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2290,7 +2290,7 @@ void pci_config_pm_runtime_put(struct pci_dev *pdev)
  * @bridge: Bridge to check
  *
  * This function checks if it is possible to move the bridge to D3.
- * Currently we only allow D3 for recent enough PCIe ports.
+ * Currently we only allow D3 for recent enough PCIe ports and Thunderbolt.
  */
 bool pci_bridge_d3_possible(struct pci_dev *bridge)
 {
@@ -2314,6 +2314,10 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge)
 		if (pci_bridge_d3_force)
 			return true;
 
+		/* Even the oldest 2010 Thunderbolt controller supports D3. */
+		if (bridge->is_thunderbolt)
+			return true;
+
 		/*
 		 * Hotplug ports handled natively by the OS were not validated
 		 * by vendors for runtime D3 at least until 2018 because there
-- 
cgit v1.2.3


From 39c64d8c876622e766dd2112baf81151dd82da02 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Mon, 30 Jul 2018 19:49:08 +0200
Subject: mlx5: handle DMA mapping error case for XDP redirect

Commit 58b99ee3e3eb ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
forgot to return/free the xdp_frame in case the DMA mapping failed, correct this.

Also DMA unmap the frame in case mlx5e_xmit_xdp_frame() fails.

Fixes: 58b99ee3e3eb ("net/mlx5e: Add support for XDP_REDIRECT in device-out side")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index bab8cd44d1c5..1881468dbcfa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -283,6 +283,7 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		xdpi.dma_addr = dma_map_single(sq->pdev, xdpf->data, xdpf->len,
 					       DMA_TO_DEVICE);
 		if (unlikely(dma_mapping_error(sq->pdev, xdpi.dma_addr))) {
+			xdp_return_frame_rx_napi(xdpf);
 			drops++;
 			continue;
 		}
@@ -290,6 +291,8 @@ int mlx5e_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		xdpi.xdpf = xdpf;
 
 		if (unlikely(!mlx5e_xmit_xdp_frame(sq, &xdpi))) {
+			dma_unmap_single(sq->pdev, xdpi.dma_addr,
+					 xdpf->len, DMA_TO_DEVICE);
 			xdp_return_frame_rx_napi(xdpf);
 			drops++;
 		}
-- 
cgit v1.2.3


From c29c2ebd2ae0066c026045a21aa33ccbfcd8bb3c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 30 Jul 2018 20:43:51 -0700
Subject: net: update real_num_rx_queues even when !CONFIG_SYSFS

We used to depend on real_num_rx_queues as a upper bound for sanity
checks.  For AF_XDP socket validation it's useful if the check behaves
the same regardless of CONFIG_SYSFS setting.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9c917467a2c7..3bf7e93c9e96 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3431,8 +3431,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
 int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
 #else
 static inline int netif_set_real_num_rx_queues(struct net_device *dev,
-						unsigned int rxq)
+						unsigned int rxqs)
 {
+	dev->real_num_rx_queues = rxqs;
 	return 0;
 }
 #endif
-- 
cgit v1.2.3


From f734607e819b951bae3b436b026ec672082e9241 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 30 Jul 2018 20:43:52 -0700
Subject: xsk: refactor xdp_umem_assign_dev()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return early and only take the ref on dev once there is no possibility
of failing.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Björn Töpel <bjorn.topel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/xdp/xdp_umem.c | 49 +++++++++++++++++++++----------------------------
 1 file changed, 21 insertions(+), 28 deletions(-)

diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index f47abb46c587..c199d66b5f3f 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -56,41 +56,34 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	if (force_copy)
 		return 0;
 
-	dev_hold(dev);
+	if (!dev->netdev_ops->ndo_bpf || !dev->netdev_ops->ndo_xsk_async_xmit)
+		return force_zc ? -ENOTSUPP : 0; /* fail or fallback */
 
-	if (dev->netdev_ops->ndo_bpf && dev->netdev_ops->ndo_xsk_async_xmit) {
-		bpf.command = XDP_QUERY_XSK_UMEM;
+	bpf.command = XDP_QUERY_XSK_UMEM;
 
-		rtnl_lock();
-		err = dev->netdev_ops->ndo_bpf(dev, &bpf);
-		rtnl_unlock();
+	rtnl_lock();
+	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
+	rtnl_unlock();
 
-		if (err) {
-			dev_put(dev);
-			return force_zc ? -ENOTSUPP : 0;
-		}
+	if (err)
+		return force_zc ? -ENOTSUPP : 0;
 
-		bpf.command = XDP_SETUP_XSK_UMEM;
-		bpf.xsk.umem = umem;
-		bpf.xsk.queue_id = queue_id;
+	bpf.command = XDP_SETUP_XSK_UMEM;
+	bpf.xsk.umem = umem;
+	bpf.xsk.queue_id = queue_id;
 
-		rtnl_lock();
-		err = dev->netdev_ops->ndo_bpf(dev, &bpf);
-		rtnl_unlock();
+	rtnl_lock();
+	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
+	rtnl_unlock();
 
-		if (err) {
-			dev_put(dev);
-			return force_zc ? err : 0; /* fail or fallback */
-		}
-
-		umem->dev = dev;
-		umem->queue_id = queue_id;
-		umem->zc = true;
-		return 0;
-	}
+	if (err)
+		return force_zc ? err : 0; /* fail or fallback */
 
-	dev_put(dev);
-	return force_zc ? -ENOTSUPP : 0; /* fail or fallback */
+	dev_hold(dev);
+	umem->dev = dev;
+	umem->queue_id = queue_id;
+	umem->zc = true;
+	return 0;
 }
 
 static void xdp_umem_clear_dev(struct xdp_umem *umem)
-- 
cgit v1.2.3


From 84c6b86875e01a08a0daa6fdd4a01b36bf0bf0b2 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 30 Jul 2018 20:43:53 -0700
Subject: xsk: don't allow umem replace at stack level
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently drivers have to check if they already have a umem
installed for a given queue and return an error if so.  Make
better use of XDP_QUERY_XSK_UMEM and move this functionality
to the core.

We need to keep rtnl across the calls now.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Acked-by: Björn Töpel <bjorn.topel@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h |  7 ++++---
 net/xdp/xdp_umem.c        | 37 ++++++++++++++++++++++++++++---------
 2 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 3bf7e93c9e96..282e2e95ad5b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -872,10 +872,10 @@ struct netdev_bpf {
 		struct {
 			struct bpf_offloaded_map *offmap;
 		};
-		/* XDP_SETUP_XSK_UMEM */
+		/* XDP_QUERY_XSK_UMEM, XDP_SETUP_XSK_UMEM */
 		struct {
-			struct xdp_umem *umem;
-			u16 queue_id;
+			struct xdp_umem *umem; /* out for query*/
+			u16 queue_id; /* in for query */
 		} xsk;
 	};
 };
@@ -3568,6 +3568,7 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, u32 flags);
 u32 __dev_xdp_query(struct net_device *dev, bpf_op_t xdp_op,
 		    enum bpf_netdev_command cmd);
+int xdp_umem_query(struct net_device *dev, u16 queue_id);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index c199d66b5f3f..911ca6d3cb5a 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -11,6 +11,8 @@
 #include <linux/slab.h>
 #include <linux/bpf.h>
 #include <linux/mm.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
 
 #include "xdp_umem.h"
 #include "xsk_queue.h"
@@ -40,6 +42,21 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 	}
 }
 
+int xdp_umem_query(struct net_device *dev, u16 queue_id)
+{
+	struct netdev_bpf bpf;
+
+	ASSERT_RTNL();
+
+	memset(&bpf, 0, sizeof(bpf));
+	bpf.command = XDP_QUERY_XSK_UMEM;
+	bpf.xsk.queue_id = queue_id;
+
+	if (!dev->netdev_ops->ndo_bpf)
+		return 0;
+	return dev->netdev_ops->ndo_bpf(dev, &bpf) ?: !!bpf.xsk.umem;
+}
+
 int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 			u32 queue_id, u16 flags)
 {
@@ -62,28 +79,30 @@ int xdp_umem_assign_dev(struct xdp_umem *umem, struct net_device *dev,
 	bpf.command = XDP_QUERY_XSK_UMEM;
 
 	rtnl_lock();
-	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
-	rtnl_unlock();
-
-	if (err)
-		return force_zc ? -ENOTSUPP : 0;
+	err = xdp_umem_query(dev, queue_id);
+	if (err) {
+		err = err < 0 ? -ENOTSUPP : -EBUSY;
+		goto err_rtnl_unlock;
+	}
 
 	bpf.command = XDP_SETUP_XSK_UMEM;
 	bpf.xsk.umem = umem;
 	bpf.xsk.queue_id = queue_id;
 
-	rtnl_lock();
 	err = dev->netdev_ops->ndo_bpf(dev, &bpf);
-	rtnl_unlock();
-
 	if (err)
-		return force_zc ? err : 0; /* fail or fallback */
+		goto err_rtnl_unlock;
+	rtnl_unlock();
 
 	dev_hold(dev);
 	umem->dev = dev;
 	umem->queue_id = queue_id;
 	umem->zc = true;
 	return 0;
+
+err_rtnl_unlock:
+	rtnl_unlock();
+	return force_zc ? err : 0; /* fail or fallback */
 }
 
 static void xdp_umem_clear_dev(struct xdp_umem *umem)
-- 
cgit v1.2.3


From 2789e83c933d7da583e592d7958e87493c889605 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 31 Jul 2018 15:02:25 +0100
Subject: xen/gntdev: don't dereference a null gntdev_dmabuf on allocation
 failure

Currently when the allocation of gntdev_dmabuf fails, the error exit
path will call dmabuf_imp_free_storage and causes a null pointer
dereference on gntdev_dmabuf.  Fix this by adding an error exit path
that won't free gntdev_dmabuf.

Detected by CoverityScan, CID#1472124 ("Dereference after null check")

Fixes: bf8dc55b1358 ("xen/gntdev: Implement dma-buf import functionality")
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/gntdev-dmabuf.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/xen/gntdev-dmabuf.c b/drivers/xen/gntdev-dmabuf.c
index faaa4d3970ea..589fd923c550 100644
--- a/drivers/xen/gntdev-dmabuf.c
+++ b/drivers/xen/gntdev-dmabuf.c
@@ -569,7 +569,7 @@ static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
 
 	gntdev_dmabuf = kzalloc(sizeof(*gntdev_dmabuf), GFP_KERNEL);
 	if (!gntdev_dmabuf)
-		goto fail;
+		goto fail_no_free;
 
 	gntdev_dmabuf->u.imp.refs = kcalloc(count,
 					    sizeof(gntdev_dmabuf->u.imp.refs[0]),
@@ -592,6 +592,7 @@ static struct gntdev_dmabuf *dmabuf_imp_alloc_storage(int count)
 
 fail:
 	dmabuf_imp_free_storage(gntdev_dmabuf);
+fail_no_free:
 	return ERR_PTR(-ENOMEM);
 }
 
-- 
cgit v1.2.3


From ca9e83b4a55bfa1cc1395b48c3bf70381833526b Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 31 Jul 2018 17:43:38 +0800
Subject: virtio-net: correctly update XDP_TX counters

Commit 5b8f3c8d30a6 ("virtio_net: Add XDP related stats") tries to
count TX XDP stats in virtnet_receive(). This will cause several
issues:

- virtnet_xdp_sq() was called without checking whether or not XDP is
  set. This may cause out of bound access when there's no enough txq
  for XDP.
- Stats were updated even if there's no XDP/XDP_TX.

Fixing this by reusing virtnet_xdp_xmit() for XDP_TX which can counts
TX XDP counter itself and remove the unnecessary tx stats embedded in
rx stats.

Reported-by: syzbot+604f8271211546f5b3c7@syzkaller.appspotmail.com
Fixes: 5b8f3c8d30a6 ("virtio_net: Add XDP related stats")
Cc: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 39 ++++-----------------------------------
 1 file changed, 4 insertions(+), 35 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1880c86e84b4..72d3f6888561 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -105,10 +105,6 @@ struct virtnet_rq_stats {
 
 struct virtnet_rx_stats {
 	struct virtnet_rq_stat_items rx;
-	struct {
-		unsigned int xdp_tx;
-		unsigned int xdp_tx_drops;
-	} tx;
 };
 
 #define VIRTNET_SQ_STAT(m)	offsetof(struct virtnet_sq_stats, m)
@@ -485,22 +481,6 @@ static struct send_queue *virtnet_xdp_sq(struct virtnet_info *vi)
 	return &vi->sq[qp];
 }
 
-static int __virtnet_xdp_tx_xmit(struct virtnet_info *vi,
-				   struct xdp_frame *xdpf)
-{
-	struct xdp_frame *xdpf_sent;
-	struct send_queue *sq;
-	unsigned int len;
-
-	sq = virtnet_xdp_sq(vi);
-
-	/* Free up any pending old buffers before queueing new ones. */
-	while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL)
-		xdp_return_frame(xdpf_sent);
-
-	return __virtnet_xdp_xmit_one(vi, sq, xdpf);
-}
-
 static int virtnet_xdp_xmit(struct net_device *dev,
 			    int n, struct xdp_frame **frames, u32 flags)
 {
@@ -707,10 +687,8 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
-			stats->tx.xdp_tx++;
-			err = __virtnet_xdp_tx_xmit(vi, xdpf);
-			if (unlikely(err)) {
-				stats->tx.xdp_tx_drops++;
+			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
+			if (unlikely(err < 0)) {
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				goto err_xdp;
 			}
@@ -879,10 +857,8 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
-			stats->tx.xdp_tx++;
-			err = __virtnet_xdp_tx_xmit(vi, xdpf);
-			if (unlikely(err)) {
-				stats->tx.xdp_tx_drops++;
+			err = virtnet_xdp_xmit(dev, 1, &xdpf, 0);
+			if (unlikely(err < 0)) {
 				trace_xdp_exception(vi->dev, xdp_prog, act);
 				if (unlikely(xdp_page != page))
 					put_page(xdp_page);
@@ -1315,7 +1291,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct virtnet_rx_stats stats = {};
-	struct send_queue *sq;
 	unsigned int len;
 	void *buf;
 	int i;
@@ -1351,12 +1326,6 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	}
 	u64_stats_update_end(&rq->stats.syncp);
 
-	sq = virtnet_xdp_sq(vi);
-	u64_stats_update_begin(&sq->stats.syncp);
-	sq->stats.xdp_tx += stats.tx.xdp_tx;
-	sq->stats.xdp_tx_drops += stats.tx.xdp_tx_drops;
-	u64_stats_update_end(&sq->stats.syncp);
-
 	return stats.rx.packets;
 }
 
-- 
cgit v1.2.3


From d46eeeaf99bcfab884e3d658e2ba1356939ea783 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 31 Jul 2018 17:43:39 +0800
Subject: virtio-net: get rid of unnecessary container of rq stats

We don't maintain tx counters in rx stats any more. There's no need
for an extra container of rq stats.

Cc: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 80 ++++++++++++++++++++++--------------------------
 1 file changed, 36 insertions(+), 44 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 72d3f6888561..14f661cbae18 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -87,7 +87,8 @@ struct virtnet_sq_stats {
 	u64 kicks;
 };
 
-struct virtnet_rq_stat_items {
+struct virtnet_rq_stats {
+	struct u64_stats_sync syncp;
 	u64 packets;
 	u64 bytes;
 	u64 drops;
@@ -98,17 +99,8 @@ struct virtnet_rq_stat_items {
 	u64 kicks;
 };
 
-struct virtnet_rq_stats {
-	struct u64_stats_sync syncp;
-	struct virtnet_rq_stat_items items;
-};
-
-struct virtnet_rx_stats {
-	struct virtnet_rq_stat_items rx;
-};
-
 #define VIRTNET_SQ_STAT(m)	offsetof(struct virtnet_sq_stats, m)
-#define VIRTNET_RQ_STAT(m)	offsetof(struct virtnet_rq_stat_items, m)
+#define VIRTNET_RQ_STAT(m)	offsetof(struct virtnet_rq_stats, m)
 
 static const struct virtnet_stat_desc virtnet_sq_stats_desc[] = {
 	{ "packets",		VIRTNET_SQ_STAT(packets) },
@@ -617,7 +609,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 				     void *buf, void *ctx,
 				     unsigned int len,
 				     unsigned int *xdp_xmit,
-				     struct virtnet_rx_stats *stats)
+				     struct virtnet_rq_stats *stats)
 {
 	struct sk_buff *skb;
 	struct bpf_prog *xdp_prog;
@@ -632,7 +624,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 	int err;
 
 	len -= vi->hdr_len;
-	stats->rx.bytes += len;
+	stats->bytes += len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -674,7 +666,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 		xdp.rxq = &rq->xdp_rxq;
 		orig_data = xdp.data;
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
-		stats->rx.xdp_packets++;
+		stats->xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
@@ -683,7 +675,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			len = xdp.data_end - xdp.data;
 			break;
 		case XDP_TX:
-			stats->rx.xdp_tx++;
+			stats->xdp_tx++;
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
@@ -696,7 +688,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
-			stats->rx.xdp_redirects++;
+			stats->xdp_redirects++;
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err)
 				goto err_xdp;
@@ -730,8 +722,8 @@ err:
 
 err_xdp:
 	rcu_read_unlock();
-	stats->rx.xdp_drops++;
-	stats->rx.drops++;
+	stats->xdp_drops++;
+	stats->drops++;
 	put_page(page);
 xdp_xmit:
 	return NULL;
@@ -742,19 +734,19 @@ static struct sk_buff *receive_big(struct net_device *dev,
 				   struct receive_queue *rq,
 				   void *buf,
 				   unsigned int len,
-				   struct virtnet_rx_stats *stats)
+				   struct virtnet_rq_stats *stats)
 {
 	struct page *page = buf;
 	struct sk_buff *skb = page_to_skb(vi, rq, page, 0, len, PAGE_SIZE);
 
-	stats->rx.bytes += len - vi->hdr_len;
+	stats->bytes += len - vi->hdr_len;
 	if (unlikely(!skb))
 		goto err;
 
 	return skb;
 
 err:
-	stats->rx.drops++;
+	stats->drops++;
 	give_pages(rq, page);
 	return NULL;
 }
@@ -766,7 +758,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 					 void *ctx,
 					 unsigned int len,
 					 unsigned int *xdp_xmit,
-					 struct virtnet_rx_stats *stats)
+					 struct virtnet_rq_stats *stats)
 {
 	struct virtio_net_hdr_mrg_rxbuf *hdr = buf;
 	u16 num_buf = virtio16_to_cpu(vi->vdev, hdr->num_buffers);
@@ -779,7 +771,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 	int err;
 
 	head_skb = NULL;
-	stats->rx.bytes += len - vi->hdr_len;
+	stats->bytes += len - vi->hdr_len;
 
 	rcu_read_lock();
 	xdp_prog = rcu_dereference(rq->xdp_prog);
@@ -828,7 +820,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 		xdp.rxq = &rq->xdp_rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
-		stats->rx.xdp_packets++;
+		stats->xdp_packets++;
 
 		switch (act) {
 		case XDP_PASS:
@@ -853,7 +845,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			}
 			break;
 		case XDP_TX:
-			stats->rx.xdp_tx++;
+			stats->xdp_tx++;
 			xdpf = convert_to_xdp_frame(&xdp);
 			if (unlikely(!xdpf))
 				goto err_xdp;
@@ -870,7 +862,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			rcu_read_unlock();
 			goto xdp_xmit;
 		case XDP_REDIRECT:
-			stats->rx.xdp_redirects++;
+			stats->xdp_redirects++;
 			err = xdp_do_redirect(dev, &xdp, xdp_prog);
 			if (err) {
 				if (unlikely(xdp_page != page))
@@ -920,7 +912,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto err_buf;
 		}
 
-		stats->rx.bytes += len;
+		stats->bytes += len;
 		page = virt_to_head_page(buf);
 
 		truesize = mergeable_ctx_to_truesize(ctx);
@@ -966,7 +958,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 
 err_xdp:
 	rcu_read_unlock();
-	stats->rx.xdp_drops++;
+	stats->xdp_drops++;
 err_skb:
 	put_page(page);
 	while (num_buf-- > 1) {
@@ -977,12 +969,12 @@ err_skb:
 			dev->stats.rx_length_errors++;
 			break;
 		}
-		stats->rx.bytes += len;
+		stats->bytes += len;
 		page = virt_to_head_page(buf);
 		put_page(page);
 	}
 err_buf:
-	stats->rx.drops++;
+	stats->drops++;
 	dev_kfree_skb(head_skb);
 xdp_xmit:
 	return NULL;
@@ -991,7 +983,7 @@ xdp_xmit:
 static void receive_buf(struct virtnet_info *vi, struct receive_queue *rq,
 			void *buf, unsigned int len, void **ctx,
 			unsigned int *xdp_xmit,
-			struct virtnet_rx_stats *stats)
+			struct virtnet_rq_stats *stats)
 {
 	struct net_device *dev = vi->dev;
 	struct sk_buff *skb;
@@ -1212,7 +1204,7 @@ static bool try_fill_recv(struct virtnet_info *vi, struct receive_queue *rq,
 	} while (rq->vq->num_free);
 	if (virtqueue_kick_prepare(rq->vq) && virtqueue_notify(rq->vq)) {
 		u64_stats_update_begin(&rq->stats.syncp);
-		rq->stats.items.kicks++;
+		rq->stats.kicks++;
 		u64_stats_update_end(&rq->stats.syncp);
 	}
 
@@ -1290,7 +1282,7 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 			   unsigned int *xdp_xmit)
 {
 	struct virtnet_info *vi = rq->vq->vdev->priv;
-	struct virtnet_rx_stats stats = {};
+	struct virtnet_rq_stats stats = {};
 	unsigned int len;
 	void *buf;
 	int i;
@@ -1298,16 +1290,16 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 	if (!vi->big_packets || vi->mergeable_rx_bufs) {
 		void *ctx;
 
-		while (stats.rx.packets < budget &&
+		while (stats.packets < budget &&
 		       (buf = virtqueue_get_buf_ctx(rq->vq, &len, &ctx))) {
 			receive_buf(vi, rq, buf, len, ctx, xdp_xmit, &stats);
-			stats.rx.packets++;
+			stats.packets++;
 		}
 	} else {
-		while (stats.rx.packets < budget &&
+		while (stats.packets < budget &&
 		       (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
 			receive_buf(vi, rq, buf, len, NULL, xdp_xmit, &stats);
-			stats.rx.packets++;
+			stats.packets++;
 		}
 	}
 
@@ -1321,12 +1313,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
 		size_t offset = virtnet_rq_stats_desc[i].offset;
 		u64 *item;
 
-		item = (u64 *)((u8 *)&rq->stats.items + offset);
-		*item += *(u64 *)((u8 *)&stats.rx + offset);
+		item = (u64 *)((u8 *)&rq->stats + offset);
+		*item += *(u64 *)((u8 *)&stats + offset);
 	}
 	u64_stats_update_end(&rq->stats.syncp);
 
-	return stats.rx.packets;
+	return stats.packets;
 }
 
 static void free_old_xmit_skbs(struct send_queue *sq)
@@ -1686,9 +1678,9 @@ static void virtnet_stats(struct net_device *dev,
 
 		do {
 			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
-			rpackets = rq->stats.items.packets;
-			rbytes   = rq->stats.items.bytes;
-			rdrops   = rq->stats.items.drops;
+			rpackets = rq->stats.packets;
+			rbytes   = rq->stats.bytes;
+			rdrops   = rq->stats.drops;
 		} while (u64_stats_fetch_retry_irq(&rq->stats.syncp, start));
 
 		tot->rx_packets += rpackets;
@@ -2078,7 +2070,7 @@ static void virtnet_get_ethtool_stats(struct net_device *dev,
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		struct receive_queue *rq = &vi->rq[i];
 
-		stats_base = (u8 *)&rq->stats.items;
+		stats_base = (u8 *)&rq->stats;
 		do {
 			start = u64_stats_fetch_begin_irq(&rq->stats.syncp);
 			for (j = 0; j < VIRTNET_RQ_STATS_LEN; j++) {
-- 
cgit v1.2.3


From 1877c9fda1b7ba2ee2d9b108b9c9298e69b5b488 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 27 Jul 2018 13:17:57 +0100
Subject: ASoC: dt-bindings: add dt bindings for wcd9335 audio codec

This patch adds bindings for wcd9335 audio codec which can support both SLIMbus
and I2S/I2C interface.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/qcom,wcd9335.txt     | 123 +++++++++++++++++++++
 1 file changed, 123 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/qcom,wcd9335.txt

diff --git a/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt b/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt
new file mode 100644
index 000000000000..1d8d49e30af7
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,wcd9335.txt
@@ -0,0 +1,123 @@
+QCOM WCD9335 Codec
+
+Qualcomm WCD9335 Codec is a standalone Hi-Fi audio codec IC, supports
+Qualcomm Technologies, Inc. (QTI) multimedia solutions, including
+the MSM8996, MSM8976, and MSM8956 chipsets. It has in-built
+Soundwire controller, interrupt mux. It supports both I2S/I2C and
+SLIMbus audio interfaces.
+
+Required properties with SLIMbus Interface:
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: For SLIMbus interface it should be "slimMID,PID",
+		    textual representation of Manufacturer ID, Product Code,
+		    shall be in lower case hexadecimal with leading zeroes
+		    suppressed.  Refer to slimbus/bus.txt for details.
+		    Should be:
+		    "slim217,1a0" for MSM8996 and APQ8096 SoCs with SLIMbus.
+
+- reg
+	Usage: required
+	Value type: <u32 u32>
+	Definition: Should be ('Device index', 'Instance ID')
+
+- interrupts
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: Interrupts via WCD INTR1 and INTR2 pins
+
+- interrupt-names:
+	Usage: required
+	Value type: <String array>
+	Definition: Interrupt names of WCD INTR1 and INTR2
+	Should be: "intr1", "intr2"
+
+- reset-gpio:
+	Usage: required
+	Value type: <String Array>
+	Definition: Reset gpio line
+
+- qcom,ifd:
+	Usage: required
+	Value type: <phandle>
+	Definition: SLIM interface device
+
+- clocks:
+	Usage: required
+	Value type: <prop-encoded-array>
+	Definition: See clock-bindings.txt section "consumers". List of
+                three clock specifiers for mclk, mclk2 and slimbus clock.
+
+- clock-names:
+	Usage: required
+	Value type: <string>
+	Definition: Must contain "mclk", "mclk2" and "slimbus" strings.
+
+- vdd-buck-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V buck supply
+
+- vdd-buck-sido-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V SIDO buck supply
+
+- vdd-rx-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V rx supply
+
+- vdd-tx-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V tx supply
+
+- vdd-vbat-supply:
+	Usage: Optional
+	Value type: <phandle>
+	Definition: Should contain a reference to the vbat supply
+
+- vdd-micbias-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the micbias supply
+
+- vdd-io-supply:
+	Usage: required
+	Value type: <phandle>
+	Definition: Should contain a reference to the 1.8V io supply
+
+- interrupt-controller:
+	Usage: required
+	Definition: Indicating that this is a interrupt controller
+
+- #interrupt-cells:
+	Usage: required
+	Value type: <int>
+	Definition: should be 1
+
+#sound-dai-cells
+	Usage: required
+	Value type: <u32>
+	Definition: Must be 1
+
+codec@1{
+	compatible = "slim217,1a0";
+	reg  = <1 0>;
+	interrupts = <&msmgpio 54 IRQ_TYPE_LEVEL_HIGH>;
+	interrupt-names = "intr2"
+	reset-gpio = <&msmgpio 64 0>;
+	qcom,ifd  = <&wc9335_ifd>;
+	clock-names = "mclk", "native";
+	clocks = <&rpmcc RPM_SMD_DIV_CLK1>,
+		 <&rpmcc RPM_SMD_BB_CLK1>;
+	vdd-buck-supply = <&pm8994_s4>;
+	vdd-rx-supply = <&pm8994_s4>;
+	vdd-buck-sido-supply = <&pm8994_s4>;
+	vdd-tx-supply = <&pm8994_s4>;
+	vdd-io-supply = <&pm8994_s4>;
+	#sound-dai-cells = <1>;
+}
-- 
cgit v1.2.3


From e57d4ca882e289a2ddc844e82fa33ad1453e9871 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 27 Jul 2018 13:18:00 +0100
Subject: ASoC: wcd9335: add support to wcd9335 codec

Qualcomm WCD9335 Codec is a standalone Hi-Fi audio codec IC,
It supports both I2S/I2C and SLIMbus audio interfaces.
On slimbus interface it supports two data lanes; 16 Tx ports
and 8 Rx ports. It has Seven DACs and nine dedicated interpolators,
Seven (six audio ADCs, and one VBAT ADC), Multibutton headset
control (MBHC), Active noise cancellation and Sidetone paths
and processing.

This patchset adds very basic support for playback and capture
via the 9 interpolators and ADC respectively.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Kconfig   |    5 +
 sound/soc/codecs/Makefile  |    2 +
 sound/soc/codecs/wcd9335.c | 1154 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 1161 insertions(+)
 create mode 100644 sound/soc/codecs/wcd9335.c

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index efb095dbcd71..cb09abf18dde 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1066,6 +1066,11 @@ config SND_SOC_UDA1380
         tristate
 	depends on I2C
 
+config SND_SOC_WCD9335
+	tristate "WCD9335 Codec"
+	depends on MFD_WCD9335
+        tristate
+
 config SND_SOC_WL1273
 	tristate
 
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index 7ae7c85e8219..01410b63daac 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -192,6 +192,7 @@ snd-soc-twl4030-objs := twl4030.o
 snd-soc-twl6040-objs := twl6040.o
 snd-soc-uda134x-objs := uda134x.o
 snd-soc-uda1380-objs := uda1380.o
+snd-soc-wcd9335-objs := wcd9335.o
 snd-soc-wl1273-objs := wl1273.o
 snd-soc-wm-adsp-objs := wm_adsp.o
 snd-soc-wm0010-objs := wm0010.o
@@ -451,6 +452,7 @@ obj-$(CONFIG_SND_SOC_TWL4030)	+= snd-soc-twl4030.o
 obj-$(CONFIG_SND_SOC_TWL6040)	+= snd-soc-twl6040.o
 obj-$(CONFIG_SND_SOC_UDA134X)	+= snd-soc-uda134x.o
 obj-$(CONFIG_SND_SOC_UDA1380)	+= snd-soc-uda1380.o
+obj-$(CONFIG_SND_SOC_WCD9335)	+= snd-soc-wcd9335.o
 obj-$(CONFIG_SND_SOC_WL1273)	+= snd-soc-wl1273.o
 obj-$(CONFIG_SND_SOC_WM0010)	+= snd-soc-wm0010.o
 obj-$(CONFIG_SND_SOC_WM1250_EV1) += snd-soc-wm1250-ev1.o
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
new file mode 100644
index 000000000000..bd9de5d45fa9
--- /dev/null
+++ b/sound/soc/codecs/wcd9335.c
@@ -0,0 +1,1154 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+// Copyright (c) 2017-2018, Linaro Limited
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/device.h>
+#include <linux/wait.h>
+#include <linux/bitops.h>
+#include <linux/regulator/consumer.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/kernel.h>
+#include <linux/slimbus.h>
+#include <sound/soc.h>
+#include <sound/pcm_params.h>
+#include <sound/soc-dapm.h>
+#include <sound/tlv.h>
+#include <sound/info.h>
+#include <dt-bindings/mfd/wcd9335.h>
+#include <linux/mfd/wcd9335/wcd9335.h>
+#include <linux/mfd/wcd9335/registers.h>
+
+#define WCD9335_RATES_MASK (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
+			    SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000 |\
+			    SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_192000)
+/* Fractional Rates */
+#define WCD9335_FRAC_RATES_MASK (SNDRV_PCM_RATE_44100)
+#define WCD9335_FORMATS_S16_S24_LE (SNDRV_PCM_FMTBIT_S16_LE | \
+				  SNDRV_PCM_FMTBIT_S24_LE)
+
+/* slave port water mark level
+ *   (0: 6bytes, 1: 9bytes, 2: 12 bytes, 3: 15 bytes)
+ */
+#define SLAVE_PORT_WATER_MARK_6BYTES  0
+#define SLAVE_PORT_WATER_MARK_9BYTES  1
+#define SLAVE_PORT_WATER_MARK_12BYTES 2
+#define SLAVE_PORT_WATER_MARK_15BYTES 3
+#define SLAVE_PORT_WATER_MARK_SHIFT 1
+#define SLAVE_PORT_ENABLE           1
+#define SLAVE_PORT_DISABLE          0
+#define WCD9335_SLIM_WATER_MARK_VAL \
+	((SLAVE_PORT_WATER_MARK_12BYTES << SLAVE_PORT_WATER_MARK_SHIFT) | \
+	 (SLAVE_PORT_ENABLE))
+
+#define WCD9335_SLIM_NUM_PORT_REG 3
+#define WCD9335_SLIM_PGD_PORT_INT_TX_EN0 (WCD9335_SLIM_PGD_PORT_INT_EN0 + 2)
+
+#define WCD9335_MCLK_CLK_12P288MHZ	12288000
+#define WCD9335_MCLK_CLK_9P6MHZ		9600000
+
+#define WCD9335_SLIM_CLOSE_TIMEOUT 1000
+#define WCD9335_SLIM_IRQ_OVERFLOW (1 << 0)
+#define WCD9335_SLIM_IRQ_UNDERFLOW (1 << 1)
+#define WCD9335_SLIM_IRQ_PORT_CLOSED (1 << 2)
+
+#define WCD9335_NUM_INTERPOLATORS 9
+#define WCD9335_RX_START	16
+#define WCD9335_SLIM_CH_START 128
+
+#define WCD9335_SLIM_RX_CH(p) \
+	{.port = p + WCD9335_RX_START, .shift = p,}
+
+/* vout step value */
+#define WCD9335_CALCULATE_VOUT_D(req_mv) (((req_mv - 650) * 10) / 25)
+
+enum {
+	WCD9335_RX0 = 0,
+	WCD9335_RX1,
+	WCD9335_RX2,
+	WCD9335_RX3,
+	WCD9335_RX4,
+	WCD9335_RX5,
+	WCD9335_RX6,
+	WCD9335_RX7,
+	WCD9335_RX8,
+	WCD9335_RX9,
+	WCD9335_RX10,
+	WCD9335_RX11,
+	WCD9335_RX12,
+	WCD9335_RX_MAX,
+};
+
+enum {
+	SIDO_SOURCE_INTERNAL = 0,
+	SIDO_SOURCE_RCO_BG,
+};
+
+enum wcd9335_sido_voltage {
+	SIDO_VOLTAGE_SVS_MV = 950,
+	SIDO_VOLTAGE_NOMINAL_MV = 1100,
+};
+
+enum {
+	AIF1_PB = 0,
+	AIF1_CAP,
+	AIF2_PB,
+	AIF2_CAP,
+	AIF3_PB,
+	AIF3_CAP,
+	AIF4_PB,
+	NUM_CODEC_DAIS,
+};
+
+enum {
+	INTn_2_INP_SEL_ZERO = 0,
+	INTn_2_INP_SEL_RX0,
+	INTn_2_INP_SEL_RX1,
+	INTn_2_INP_SEL_RX2,
+	INTn_2_INP_SEL_RX3,
+	INTn_2_INP_SEL_RX4,
+	INTn_2_INP_SEL_RX5,
+	INTn_2_INP_SEL_RX6,
+	INTn_2_INP_SEL_RX7,
+	INTn_2_INP_SEL_PROXIMITY,
+};
+
+enum {
+	INTn_1_MIX_INP_SEL_ZERO = 0,
+	INTn_1_MIX_INP_SEL_DEC0,
+	INTn_1_MIX_INP_SEL_DEC1,
+	INTn_1_MIX_INP_SEL_IIR0,
+	INTn_1_MIX_INP_SEL_IIR1,
+	INTn_1_MIX_INP_SEL_RX0,
+	INTn_1_MIX_INP_SEL_RX1,
+	INTn_1_MIX_INP_SEL_RX2,
+	INTn_1_MIX_INP_SEL_RX3,
+	INTn_1_MIX_INP_SEL_RX4,
+	INTn_1_MIX_INP_SEL_RX5,
+	INTn_1_MIX_INP_SEL_RX6,
+	INTn_1_MIX_INP_SEL_RX7,
+
+};
+
+enum wcd_clock_type {
+	WCD_CLK_OFF,
+	WCD_CLK_RCO,
+	WCD_CLK_MCLK,
+};
+
+struct wcd9335_slim_ch {
+	u32 ch_num;
+	u16 port;
+	u16 shift;
+	struct list_head list;
+};
+
+struct wcd_slim_codec_dai_data {
+	struct list_head slim_ch_list;
+	struct slim_stream_config sconfig;
+	struct slim_stream_runtime *sruntime;
+};
+
+struct wcd9335_codec {
+	struct device *dev;
+	struct clk *mclk;
+	struct clk *native_clk;
+	u32 mclk_rate;
+	u8 intf_type;
+	u8 version;
+
+	struct slim_device *slim;
+	struct slim_device *slim_ifd;
+	struct regmap *regmap;
+	struct regmap *if_regmap;
+	struct regmap_irq_chip_data *irq_data;
+
+	struct wcd9335_slim_ch rx_chs[WCD9335_RX_MAX];
+	u32 num_rx_port;
+
+	int sido_input_src;
+	enum wcd9335_sido_voltage sido_voltage;
+
+	struct wcd_slim_codec_dai_data dai[NUM_CODEC_DAIS];
+	struct snd_soc_component *component;
+
+	int master_bias_users;
+	int clk_mclk_users;
+	int clk_rco_users;
+	int sido_ccl_cnt;
+	enum wcd_clock_type clk_type;
+
+	u32 hph_mode;
+};
+
+static const struct wcd9335_slim_ch wcd9335_rx_chs[WCD9335_RX_MAX] = {
+	WCD9335_SLIM_RX_CH(0),	 /* 16 */
+	WCD9335_SLIM_RX_CH(1),	 /* 17 */
+	WCD9335_SLIM_RX_CH(2),
+	WCD9335_SLIM_RX_CH(3),
+	WCD9335_SLIM_RX_CH(4),
+	WCD9335_SLIM_RX_CH(5),
+	WCD9335_SLIM_RX_CH(6),
+	WCD9335_SLIM_RX_CH(7),
+	WCD9335_SLIM_RX_CH(8),
+	WCD9335_SLIM_RX_CH(9),
+	WCD9335_SLIM_RX_CH(10),
+	WCD9335_SLIM_RX_CH(11),
+	WCD9335_SLIM_RX_CH(12),
+};
+
+struct interp_sample_rate {
+	int rate;
+	int rate_val;
+};
+
+static struct interp_sample_rate int_mix_rate_val[] = {
+	{48000, 0x4},	/* 48K */
+	{96000, 0x5},	/* 96K */
+	{192000, 0x6},	/* 192K */
+};
+
+static struct interp_sample_rate int_prim_rate_val[] = {
+	{8000, 0x0},	/* 8K */
+	{16000, 0x1},	/* 16K */
+	{24000, -EINVAL},/* 24K */
+	{32000, 0x3},	/* 32K */
+	{48000, 0x4},	/* 48K */
+	{96000, 0x5},	/* 96K */
+	{192000, 0x6},	/* 192K */
+	{384000, 0x7},	/* 384K */
+	{44100, 0x8}, /* 44.1K */
+};
+
+struct wcd9335_reg_mask_val {
+	u16 reg;
+	u8 mask;
+	u8 val;
+};
+
+static const struct wcd9335_reg_mask_val wcd9335_codec_reg_init_val_2_0[] = {
+	{WCD9335_RCO_CTRL_2, 0x0F, 0x08},
+	{WCD9335_RX_BIAS_FLYB_MID_RST, 0xF0, 0x10},
+	{WCD9335_FLYBACK_CTRL_1, 0x20, 0x20},
+	{WCD9335_HPH_OCP_CTL, 0xFF, 0x5A},
+	{WCD9335_HPH_L_TEST, 0x01, 0x01},
+	{WCD9335_HPH_R_TEST, 0x01, 0x01},
+	{WCD9335_CDC_BOOST0_BOOST_CFG1, 0x3F, 0x12},
+	{WCD9335_CDC_BOOST0_BOOST_CFG2, 0x1C, 0x08},
+	{WCD9335_CDC_COMPANDER7_CTL7, 0x1E, 0x18},
+	{WCD9335_CDC_BOOST1_BOOST_CFG1, 0x3F, 0x12},
+	{WCD9335_CDC_BOOST1_BOOST_CFG2, 0x1C, 0x08},
+	{WCD9335_CDC_COMPANDER8_CTL7, 0x1E, 0x18},
+	{WCD9335_CDC_TX0_TX_PATH_SEC7, 0xFF, 0x45},
+	{WCD9335_CDC_RX0_RX_PATH_SEC0, 0xFC, 0xF4},
+	{WCD9335_HPH_REFBUFF_LP_CTL, 0x08, 0x08},
+	{WCD9335_HPH_REFBUFF_LP_CTL, 0x06, 0x02},
+};
+
+static const struct wcd9335_reg_mask_val wcd9335_codec_reg_init_common_val[] = {
+	/* Rbuckfly/R_EAR(32) */
+	{WCD9335_CDC_CLSH_K2_MSB, 0x0F, 0x00},
+	{WCD9335_CDC_CLSH_K2_LSB, 0xFF, 0x60},
+	{WCD9335_CPE_SS_DMIC_CFG, 0x80, 0x00},
+	{WCD9335_CDC_BOOST0_BOOST_CTL, 0x70, 0x50},
+	{WCD9335_CDC_BOOST1_BOOST_CTL, 0x70, 0x50},
+	{WCD9335_CDC_RX7_RX_PATH_CFG1, 0x08, 0x08},
+	{WCD9335_CDC_RX8_RX_PATH_CFG1, 0x08, 0x08},
+	{WCD9335_ANA_LO_1_2, 0x3C, 0X3C},
+	{WCD9335_DIFF_LO_COM_SWCAP_REFBUF_FREQ, 0x70, 0x00},
+	{WCD9335_DIFF_LO_COM_PA_FREQ, 0x70, 0x40},
+	{WCD9335_SOC_MAD_AUDIO_CTL_2, 0x03, 0x03},
+	{WCD9335_CDC_TOP_TOP_CFG1, 0x02, 0x02},
+	{WCD9335_CDC_TOP_TOP_CFG1, 0x01, 0x01},
+	{WCD9335_EAR_CMBUFF, 0x08, 0x00},
+	{WCD9335_CDC_TX9_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_TX10_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_TX11_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_TX12_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_COMPANDER7_CTL3, 0x80, 0x80},
+	{WCD9335_CDC_COMPANDER8_CTL3, 0x80, 0x80},
+	{WCD9335_CDC_COMPANDER7_CTL7, 0x01, 0x01},
+	{WCD9335_CDC_COMPANDER8_CTL7, 0x01, 0x01},
+	{WCD9335_CDC_RX0_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX1_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX2_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX3_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX4_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX5_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX6_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX7_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX8_RX_PATH_CFG0, 0x01, 0x01},
+	{WCD9335_CDC_RX0_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX1_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX2_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX3_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX4_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX5_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX6_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX7_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_CDC_RX8_RX_PATH_MIX_CFG, 0x01, 0x01},
+	{WCD9335_VBADC_IBIAS_FE, 0x0C, 0x08},
+};
+
+static int wcd9335_set_mix_interpolator_rate(struct snd_soc_dai *dai,
+					     int rate_val,
+					     u32 rate)
+{
+	struct snd_soc_component *component = dai->component;
+	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
+	struct wcd9335_slim_ch *ch;
+	int val, j;
+
+	list_for_each_entry(ch, &wcd->dai[dai->id].slim_ch_list, list) {
+		for (j = 0; j < WCD9335_NUM_INTERPOLATORS; j++) {
+			val = snd_soc_component_read32(component,
+					WCD9335_CDC_RX_INP_MUX_RX_INT_CFG1(j)) &
+					WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
+
+			if (val == (ch->shift + INTn_2_INP_SEL_RX0))
+				snd_soc_component_update_bits(component,
+						WCD9335_CDC_RX_PATH_MIX_CTL(j),
+						WCD9335_CDC_MIX_PCM_RATE_MASK,
+						rate_val);
+		}
+	}
+
+	return 0;
+}
+
+static int wcd9335_set_prim_interpolator_rate(struct snd_soc_dai *dai,
+					      u8 rate_val,
+					      u32 rate)
+{
+	struct snd_soc_component *comp = dai->component;
+	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
+	struct wcd9335_slim_ch *ch;
+	u8 cfg0, cfg1, inp0_sel, inp1_sel, inp2_sel;
+	int inp, j;
+
+	list_for_each_entry(ch, &wcd->dai[dai->id].slim_ch_list, list) {
+		inp = ch->shift + INTn_1_MIX_INP_SEL_RX0;
+		/*
+		 * Loop through all interpolator MUX inputs and find out
+		 * to which interpolator input, the slim rx port
+		 * is connected
+		 */
+		for (j = 0; j < WCD9335_NUM_INTERPOLATORS; j++) {
+			cfg0 = snd_soc_component_read32(comp,
+					WCD9335_CDC_RX_INP_MUX_RX_INT_CFG0(j));
+			cfg1 = snd_soc_component_read32(comp,
+					WCD9335_CDC_RX_INP_MUX_RX_INT_CFG1(j));
+
+			inp0_sel = cfg0 & WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
+			inp1_sel = (cfg0 >> 4) & WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
+			inp2_sel = (cfg1 >> 4) & WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
+
+			if ((inp0_sel == inp) ||  (inp1_sel == inp) ||
+			    (inp2_sel == inp)) {
+				/* rate is in Hz */
+				if ((j == 0) && (rate == 44100))
+					dev_info(wcd->dev,
+						"Cannot set 44.1KHz on INT0\n");
+				else
+					snd_soc_component_update_bits(comp,
+						WCD9335_CDC_RX_PATH_CTL(j),
+						WCD9335_CDC_MIX_PCM_RATE_MASK,
+						rate_val);
+			}
+		}
+	}
+
+	return 0;
+}
+
+static int wcd9335_set_interpolator_rate(struct snd_soc_dai *dai, u32 rate)
+{
+	int i;
+
+	/* set mixing path rate */
+	for (i = 0; i < ARRAY_SIZE(int_mix_rate_val); i++) {
+		if (rate == int_mix_rate_val[i].rate) {
+			wcd9335_set_mix_interpolator_rate(dai,
+					int_mix_rate_val[i].rate_val, rate);
+			break;
+		}
+	}
+
+	/* set primary path sample rate */
+	for (i = 0; i < ARRAY_SIZE(int_prim_rate_val); i++) {
+		if (rate == int_prim_rate_val[i].rate) {
+			wcd9335_set_prim_interpolator_rate(dai,
+					int_prim_rate_val[i].rate_val, rate);
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static int wcd9335_slim_set_hw_params(struct wcd9335_codec *wcd,
+				 struct wcd_slim_codec_dai_data *dai_data,
+				 int direction)
+{
+	struct list_head *slim_ch_list = &dai_data->slim_ch_list;
+	struct slim_stream_config *cfg = &dai_data->sconfig;
+	struct wcd9335_slim_ch *ch;
+	u16 payload = 0;
+	int ret, i;
+
+	cfg->ch_count = 0;
+	cfg->direction = direction;
+	cfg->port_mask = 0;
+
+	/* Configure slave interface device */
+	list_for_each_entry(ch, slim_ch_list, list) {
+		cfg->ch_count++;
+		payload |= 1 << ch->shift;
+		cfg->port_mask |= BIT(ch->port);
+	}
+
+	cfg->chs = kcalloc(cfg->ch_count, sizeof(unsigned int), GFP_KERNEL);
+	if (!cfg->chs)
+		return -ENOMEM;
+
+	i = 0;
+	list_for_each_entry(ch, slim_ch_list, list) {
+		cfg->chs[i++] = ch->ch_num;
+		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
+			/* write to interface device */
+			ret = regmap_write(wcd->if_regmap,
+				WCD9335_SLIM_PGD_RX_PORT_MULTI_CHNL_0(ch->port),
+				payload);
+
+			if (ret < 0)
+				goto err;
+
+			/* configure the slave port for water mark and enable*/
+			ret = regmap_write(wcd->if_regmap,
+					WCD9335_SLIM_PGD_RX_PORT_CFG(ch->port),
+					WCD9335_SLIM_WATER_MARK_VAL);
+			if (ret < 0)
+				goto err;
+		}
+	}
+
+	dai_data->sruntime = slim_stream_allocate(wcd->slim, "WCD9335-SLIM");
+	slim_stream_prepare(dai_data->sruntime, cfg);
+
+	return 0;
+
+err:
+	dev_err(wcd->dev, "Error Setting slim hw params\n");
+	kfree(cfg->chs);
+	cfg->chs = NULL;
+
+	return ret;
+}
+
+static int wcd9335_hw_params(struct snd_pcm_substream *substream,
+			   struct snd_pcm_hw_params *params,
+			   struct snd_soc_dai *dai)
+{
+	struct wcd9335_codec *wcd;
+	int ret;
+
+	wcd = snd_soc_component_get_drvdata(dai->component);
+
+	switch (substream->stream) {
+	case SNDRV_PCM_STREAM_PLAYBACK:
+		ret = wcd9335_set_interpolator_rate(dai, params_rate(params));
+		if (ret) {
+			dev_err(wcd->dev, "cannot set sample rate: %u\n",
+				params_rate(params));
+			return ret;
+		}
+		switch (params_width(params)) {
+		case 16 ... 24:
+			wcd->dai[dai->id].sconfig.bps = params_width(params);
+			break;
+		default:
+			dev_err(wcd->dev, "%s: Invalid format 0x%x\n",
+				__func__, params_width(params));
+			return -EINVAL;
+		}
+		break;
+	default:
+		dev_err(wcd->dev, "Invalid stream type %d\n",
+			substream->stream);
+		return -EINVAL;
+	};
+
+	wcd->dai[dai->id].sconfig.rate = params_rate(params);
+	wcd9335_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream);
+
+	return 0;
+}
+
+static int wcd9335_prepare(struct snd_pcm_substream *substream,
+			   struct snd_soc_dai *dai)
+{
+	struct wcd_slim_codec_dai_data *dai_data;
+	struct wcd9335_codec *wcd;
+
+	wcd = snd_soc_component_get_drvdata(dai->component);
+	dai_data = &wcd->dai[dai->id];
+	slim_stream_enable(dai_data->sruntime);
+
+	return 0;
+}
+
+static int wcd9335_set_channel_map(struct snd_soc_dai *dai,
+				   unsigned int tx_num, unsigned int *tx_slot,
+				   unsigned int rx_num, unsigned int *rx_slot)
+{
+	struct wcd9335_codec *wcd;
+	int i;
+
+	wcd = snd_soc_component_get_drvdata(dai->component);
+
+	if (!tx_slot || !rx_slot) {
+		dev_err(wcd->dev, "Invalid tx_slot=%p, rx_slot=%p\n",
+			tx_slot, rx_slot);
+		return -EINVAL;
+	}
+
+	if (wcd->rx_chs) {
+		wcd->num_rx_port = rx_num;
+		for (i = 0; i < rx_num; i++) {
+			wcd->rx_chs[i].ch_num = rx_slot[i];
+			INIT_LIST_HEAD(&wcd->rx_chs[i].list);
+		}
+	}
+
+	return 0;
+}
+
+static int wcd9335_get_channel_map(struct snd_soc_dai *dai,
+				   unsigned int *tx_num, unsigned int *tx_slot,
+				   unsigned int *rx_num, unsigned int *rx_slot)
+{
+	struct wcd9335_slim_ch *ch;
+	struct wcd9335_codec *wcd;
+	int i = 0;
+
+	wcd = snd_soc_component_get_drvdata(dai->component);
+
+	switch (dai->id) {
+	case AIF1_PB:
+	case AIF2_PB:
+	case AIF3_PB:
+	case AIF4_PB:
+		if (!rx_slot || !rx_num) {
+			dev_err(wcd->dev, "Invalid rx_slot %p or rx_num %p\n",
+				rx_slot, rx_num);
+			return -EINVAL;
+		}
+
+		list_for_each_entry(ch, &wcd->dai[dai->id].slim_ch_list, list)
+			rx_slot[i++] = ch->ch_num;
+
+		*rx_num = i;
+		break;
+	default:
+		dev_err(wcd->dev, "Invalid DAI ID %x\n", dai->id);
+		break;
+	}
+
+	return 0;
+}
+
+static struct snd_soc_dai_ops wcd9335_dai_ops = {
+	.hw_params = wcd9335_hw_params,
+	.prepare = wcd9335_prepare,
+	.set_channel_map = wcd9335_set_channel_map,
+	.get_channel_map = wcd9335_get_channel_map,
+};
+
+static struct snd_soc_dai_driver wcd9335_slim_dais[] = {
+	[0] = {
+		.name = "wcd9335_rx1",
+		.id = AIF1_PB,
+		.playback = {
+			.stream_name = "AIF1 Playback",
+			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
+			.formats = WCD9335_FORMATS_S16_S24_LE,
+			.rate_max = 192000,
+			.rate_min = 8000,
+			.channels_min = 1,
+			.channels_max = 2,
+		},
+		.ops = &wcd9335_dai_ops,
+	},
+	[1] = {
+		.name = "wcd9335_tx1",
+		.id = AIF1_CAP,
+		.capture = {
+			.stream_name = "AIF1 Capture",
+			.rates = WCD9335_RATES_MASK,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.rate_min = 8000,
+			.rate_max = 192000,
+			.channels_min = 1,
+			.channels_max = 4,
+		},
+		.ops = &wcd9335_dai_ops,
+	},
+	[2] = {
+		.name = "wcd9335_rx2",
+		.id = AIF2_PB,
+		.playback = {
+			.stream_name = "AIF2 Playback",
+			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
+			.formats = WCD9335_FORMATS_S16_S24_LE,
+			.rate_min = 8000,
+			.rate_max = 192000,
+			.channels_min = 1,
+			.channels_max = 2,
+		},
+		.ops = &wcd9335_dai_ops,
+	},
+	[3] = {
+		.name = "wcd9335_tx2",
+		.id = AIF2_CAP,
+		.capture = {
+			.stream_name = "AIF2 Capture",
+			.rates = WCD9335_RATES_MASK,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.rate_min = 8000,
+			.rate_max = 192000,
+			.channels_min = 1,
+			.channels_max = 4,
+		},
+		.ops = &wcd9335_dai_ops,
+	},
+	[4] = {
+		.name = "wcd9335_rx3",
+		.id = AIF3_PB,
+		.playback = {
+			.stream_name = "AIF3 Playback",
+			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
+			.formats = WCD9335_FORMATS_S16_S24_LE,
+			.rate_min = 8000,
+			.rate_max = 192000,
+			.channels_min = 1,
+			.channels_max = 2,
+		},
+		.ops = &wcd9335_dai_ops,
+	},
+	[5] = {
+		.name = "wcd9335_tx3",
+		.id = AIF3_CAP,
+		.capture = {
+			.stream_name = "AIF3 Capture",
+			.rates = WCD9335_RATES_MASK,
+			.formats = SNDRV_PCM_FMTBIT_S16_LE,
+			.rate_min = 8000,
+			.rate_max = 192000,
+			.channels_min = 1,
+			.channels_max = 4,
+		},
+		.ops = &wcd9335_dai_ops,
+	},
+	[6] = {
+		.name = "wcd9335_rx4",
+		.id = AIF4_PB,
+		.playback = {
+			.stream_name = "AIF4 Playback",
+			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
+			.formats = WCD9335_FORMATS_S16_S24_LE,
+			.rate_min = 8000,
+			.rate_max = 192000,
+			.channels_min = 1,
+			.channels_max = 2,
+		},
+		.ops = &wcd9335_dai_ops,
+	},
+};
+
+static irqreturn_t wcd9335_slimbus_irq(int irq, void *data)
+{
+	struct wcd9335_codec *wcd = data;
+	unsigned long status = 0;
+	int i, j, port_id;
+	unsigned int val, int_val = 0;
+	bool tx;
+	unsigned short reg = 0;
+
+	for (i = WCD9335_SLIM_PGD_PORT_INT_STATUS_RX_0, j = 0;
+	     i <= WCD9335_SLIM_PGD_PORT_INT_STATUS_TX_1; i++, j++) {
+		regmap_read(wcd->if_regmap, i, &val);
+		status |= ((u32)val << (8 * j));
+	}
+
+	for_each_set_bit(j, &status, 32) {
+		tx = (j >= 16 ? true : false);
+		port_id = (tx ? j - 16 : j);
+		regmap_read(wcd->if_regmap,
+				WCD9335_SLIM_PGD_PORT_INT_RX_SOURCE0 + j, &val);
+		if (val) {
+			if (!tx)
+				reg = WCD9335_SLIM_PGD_PORT_INT_EN0 +
+					(port_id / 8);
+			else
+				reg = WCD9335_SLIM_PGD_PORT_INT_TX_EN0 +
+					(port_id / 8);
+			regmap_read(
+				wcd->if_regmap, reg, &int_val);
+			/*
+			 * Ignore interrupts for ports for which the
+			 * interrupts are not specifically enabled.
+			 */
+			if (!(int_val & (1 << (port_id % 8))))
+				continue;
+		}
+		if (val & WCD9335_SLIM_IRQ_OVERFLOW)
+			dev_err_ratelimited(wcd->dev,
+			   "%s: overflow error on %s port %d, value %x\n",
+			   __func__, (tx ? "TX" : "RX"), port_id, val);
+		if (val & WCD9335_SLIM_IRQ_UNDERFLOW)
+			dev_err_ratelimited(wcd->dev,
+			   "%s: underflow error on %s port %d, value %x\n",
+			   __func__, (tx ? "TX" : "RX"), port_id, val);
+		if ((val & WCD9335_SLIM_IRQ_OVERFLOW) ||
+			(val & WCD9335_SLIM_IRQ_UNDERFLOW)) {
+			if (!tx)
+				reg = WCD9335_SLIM_PGD_PORT_INT_EN0 +
+					(port_id / 8);
+			else
+				reg = WCD9335_SLIM_PGD_PORT_INT_TX_EN0 +
+					(port_id / 8);
+			regmap_read(
+				wcd->if_regmap, reg, &int_val);
+			if (int_val & (1 << (port_id % 8))) {
+				int_val = int_val ^ (1 << (port_id % 8));
+				regmap_write(wcd->if_regmap,
+					reg, int_val);
+			}
+		}
+
+		regmap_write(wcd->if_regmap,
+				WCD9335_SLIM_PGD_PORT_INT_CLR_RX_0 + (j / 8),
+				BIT(j % 8));
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int wcd9335_setup_irqs(struct wcd9335_codec *wcd)
+{
+	int slim_irq = regmap_irq_get_virq(wcd->irq_data, WCD9335_IRQ_SLIMBUS);
+	int i, ret = 0;
+
+	ret = request_threaded_irq(slim_irq, NULL, wcd9335_slimbus_irq,
+				   IRQF_TRIGGER_RISING, "SLIMBus Slave", wcd);
+	if (ret) {
+		dev_err(wcd->dev, "Failed to request SLIMBUS irq\n");
+		return ret;
+	}
+
+	/* enable interrupts on all slave ports */
+	for (i = 0; i < WCD9335_SLIM_NUM_PORT_REG; i++)
+		regmap_write(wcd->if_regmap, WCD9335_SLIM_PGD_PORT_INT_EN0 + i,
+			     0xFF);
+
+	return ret;
+}
+
+static void wcd9335_cdc_sido_ccl_enable(struct wcd9335_codec *wcd,
+					bool ccl_flag)
+{
+	struct snd_soc_component *comp = wcd->component;
+
+	if (ccl_flag) {
+		if (++wcd->sido_ccl_cnt == 1)
+			snd_soc_component_write(comp, WCD9335_SIDO_SIDO_CCL_10,
+					WCD9335_SIDO_SIDO_CCL_DEF_VALUE);
+	} else {
+		if (wcd->sido_ccl_cnt == 0) {
+			dev_err(wcd->dev, "sido_ccl already disabled\n");
+			return;
+		}
+		if (--wcd->sido_ccl_cnt == 0)
+			snd_soc_component_write(comp, WCD9335_SIDO_SIDO_CCL_10,
+				WCD9335_SIDO_SIDO_CCL_10_ICHARG_PWR_SEL_C320FF);
+	}
+}
+
+static int wcd9335_enable_master_bias(struct wcd9335_codec *wcd)
+{
+	wcd->master_bias_users++;
+	if (wcd->master_bias_users == 1) {
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
+					WCD9335_ANA_BIAS_EN_MASK,
+					WCD9335_ANA_BIAS_ENABLE);
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
+					WCD9335_ANA_BIAS_PRECHRG_EN_MASK,
+					WCD9335_ANA_BIAS_PRECHRG_ENABLE);
+		/*
+		 * 1ms delay is required after pre-charge is enabled
+		 * as per HW requirement
+		 */
+		usleep_range(1000, 1100);
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
+					WCD9335_ANA_BIAS_PRECHRG_EN_MASK,
+					WCD9335_ANA_BIAS_PRECHRG_DISABLE);
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
+				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE,
+				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE_MANUAL);
+	}
+
+	return 0;
+}
+
+static int wcd9335_enable_mclk(struct wcd9335_codec *wcd)
+{
+	/* Enable mclk requires master bias to be enabled first */
+	if (wcd->master_bias_users <= 0)
+		return -EINVAL;
+
+	if (((wcd->clk_mclk_users == 0) && (wcd->clk_type == WCD_CLK_MCLK)) ||
+	    ((wcd->clk_mclk_users > 0) && (wcd->clk_type != WCD_CLK_MCLK))) {
+		dev_err(wcd->dev, "Error enabling MCLK, clk_type: %d\n",
+			wcd->clk_type);
+		return -EINVAL;
+	}
+
+	if (++wcd->clk_mclk_users == 1) {
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
+					WCD9335_ANA_CLK_EXT_CLKBUF_EN_MASK,
+					WCD9335_ANA_CLK_EXT_CLKBUF_ENABLE);
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
+					WCD9335_ANA_CLK_MCLK_SRC_MASK,
+					WCD9335_ANA_CLK_MCLK_SRC_EXTERNAL);
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
+					WCD9335_ANA_CLK_MCLK_EN_MASK,
+					WCD9335_ANA_CLK_MCLK_ENABLE);
+		regmap_update_bits(wcd->regmap,
+				   WCD9335_CDC_CLK_RST_CTRL_FS_CNT_CONTROL,
+				   WCD9335_CDC_CLK_RST_CTRL_FS_CNT_EN_MASK,
+				   WCD9335_CDC_CLK_RST_CTRL_FS_CNT_ENABLE);
+		regmap_update_bits(wcd->regmap,
+				   WCD9335_CDC_CLK_RST_CTRL_MCLK_CONTROL,
+				   WCD9335_CDC_CLK_RST_CTRL_MCLK_EN_MASK,
+				   WCD9335_CDC_CLK_RST_CTRL_MCLK_ENABLE);
+		/*
+		 * 10us sleep is required after clock is enabled
+		 * as per HW requirement
+		 */
+		usleep_range(10, 15);
+	}
+
+	wcd->clk_type = WCD_CLK_MCLK;
+
+	return 0;
+}
+
+static int wcd9335_disable_mclk(struct wcd9335_codec *wcd)
+{
+	if (wcd->clk_mclk_users <= 0)
+		return -EINVAL;
+
+	if (--wcd->clk_mclk_users == 0) {
+		if (wcd->clk_rco_users > 0) {
+			/* MCLK to RCO switch */
+			regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
+					WCD9335_ANA_CLK_MCLK_SRC_MASK,
+					WCD9335_ANA_CLK_MCLK_SRC_RCO);
+			wcd->clk_type = WCD_CLK_RCO;
+		} else {
+			regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
+					WCD9335_ANA_CLK_MCLK_EN_MASK,
+					WCD9335_ANA_CLK_MCLK_DISABLE);
+			wcd->clk_type = WCD_CLK_OFF;
+		}
+
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
+					WCD9335_ANA_CLK_EXT_CLKBUF_EN_MASK,
+					WCD9335_ANA_CLK_EXT_CLKBUF_DISABLE);
+	}
+
+	return 0;
+}
+
+static int wcd9335_disable_master_bias(struct wcd9335_codec *wcd)
+{
+	if (wcd->master_bias_users <= 0)
+		return -EINVAL;
+
+	wcd->master_bias_users--;
+	if (wcd->master_bias_users == 0) {
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
+				WCD9335_ANA_BIAS_EN_MASK,
+				WCD9335_ANA_BIAS_DISABLE);
+		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
+				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE,
+				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE_MANUAL);
+	}
+	return 0;
+}
+
+static int wcd9335_cdc_req_mclk_enable(struct wcd9335_codec *wcd,
+				     bool enable)
+{
+	int ret = 0;
+
+	if (enable) {
+		wcd9335_cdc_sido_ccl_enable(wcd, true);
+		ret = clk_prepare_enable(wcd->mclk);
+		if (ret) {
+			dev_err(wcd->dev, "%s: ext clk enable failed\n",
+				__func__);
+			goto err;
+		}
+		/* get BG */
+		wcd9335_enable_master_bias(wcd);
+		/* get MCLK */
+		wcd9335_enable_mclk(wcd);
+
+	} else {
+		/* put MCLK */
+		wcd9335_disable_mclk(wcd);
+		/* put BG */
+		wcd9335_disable_master_bias(wcd);
+		clk_disable_unprepare(wcd->mclk);
+		wcd9335_cdc_sido_ccl_enable(wcd, false);
+	}
+err:
+	return ret;
+}
+
+static void wcd9335_codec_apply_sido_voltage(struct wcd9335_codec *wcd,
+					     enum wcd9335_sido_voltage req_mv)
+{
+	struct snd_soc_component *comp = wcd->component;
+	int vout_d_val;
+
+	if (req_mv == wcd->sido_voltage)
+		return;
+
+	/* compute the vout_d step value */
+	vout_d_val = WCD9335_CALCULATE_VOUT_D(req_mv) &
+			WCD9335_ANA_BUCK_VOUT_MASK;
+	snd_soc_component_write(comp, WCD9335_ANA_BUCK_VOUT_D, vout_d_val);
+	snd_soc_component_update_bits(comp, WCD9335_ANA_BUCK_CTL,
+				WCD9335_ANA_BUCK_CTL_RAMP_START_MASK,
+				WCD9335_ANA_BUCK_CTL_RAMP_START_ENABLE);
+
+	/* 1 msec sleep required after SIDO Vout_D voltage change */
+	usleep_range(1000, 1100);
+	wcd->sido_voltage = req_mv;
+	snd_soc_component_update_bits(comp, WCD9335_ANA_BUCK_CTL,
+				WCD9335_ANA_BUCK_CTL_RAMP_START_MASK,
+				WCD9335_ANA_BUCK_CTL_RAMP_START_DISABLE);
+}
+
+static int wcd9335_codec_update_sido_voltage(struct wcd9335_codec *wcd,
+					     enum wcd9335_sido_voltage req_mv)
+{
+	int ret = 0;
+
+	/* enable mclk before setting SIDO voltage */
+	ret = wcd9335_cdc_req_mclk_enable(wcd, true);
+	if (ret) {
+		dev_err(wcd->dev, "Ext clk enable failed\n");
+		goto err;
+	}
+
+	wcd9335_codec_apply_sido_voltage(wcd, req_mv);
+	wcd9335_cdc_req_mclk_enable(wcd, false);
+
+err:
+	return ret;
+}
+
+static int _wcd9335_codec_enable_mclk(struct snd_soc_component *component,
+				      int enable)
+{
+	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
+	int ret;
+
+	if (enable) {
+		ret = wcd9335_cdc_req_mclk_enable(wcd, true);
+		if (ret)
+			return ret;
+
+		wcd9335_codec_apply_sido_voltage(wcd,
+				SIDO_VOLTAGE_NOMINAL_MV);
+	} else {
+		wcd9335_codec_update_sido_voltage(wcd,
+					wcd->sido_voltage);
+		wcd9335_cdc_req_mclk_enable(wcd, false);
+	}
+
+	return 0;
+}
+
+static void wcd9335_enable_sido_buck(struct snd_soc_component *component)
+{
+	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
+
+	snd_soc_component_update_bits(component, WCD9335_ANA_RCO,
+					WCD9335_ANA_RCO_BG_EN_MASK,
+					WCD9335_ANA_RCO_BG_ENABLE);
+	snd_soc_component_update_bits(component, WCD9335_ANA_BUCK_CTL,
+					WCD9335_ANA_BUCK_CTL_VOUT_D_IREF_MASK,
+					WCD9335_ANA_BUCK_CTL_VOUT_D_IREF_EXT);
+	/* 100us sleep needed after IREF settings */
+	usleep_range(100, 110);
+	snd_soc_component_update_bits(component, WCD9335_ANA_BUCK_CTL,
+					WCD9335_ANA_BUCK_CTL_VOUT_D_VREF_MASK,
+					WCD9335_ANA_BUCK_CTL_VOUT_D_VREF_EXT);
+	/* 100us sleep needed after VREF settings */
+	usleep_range(100, 110);
+	wcd->sido_input_src = SIDO_SOURCE_RCO_BG;
+}
+
+static int wcd9335_enable_efuse_sensing(struct snd_soc_component *comp)
+{
+	_wcd9335_codec_enable_mclk(comp, true);
+	snd_soc_component_update_bits(comp,
+				WCD9335_CHIP_TIER_CTRL_EFUSE_CTL,
+				WCD9335_CHIP_TIER_CTRL_EFUSE_EN_MASK,
+				WCD9335_CHIP_TIER_CTRL_EFUSE_ENABLE);
+	/*
+	 * 5ms sleep required after enabling efuse control
+	 * before checking the status.
+	 */
+	usleep_range(5000, 5500);
+
+	if (!(snd_soc_component_read32(comp,
+					WCD9335_CHIP_TIER_CTRL_EFUSE_STATUS) &
+					WCD9335_CHIP_TIER_CTRL_EFUSE_EN_MASK))
+		WARN(1, "%s: Efuse sense is not complete\n", __func__);
+
+	wcd9335_enable_sido_buck(comp);
+	_wcd9335_codec_enable_mclk(comp, false);
+
+	return 0;
+}
+
+static void wcd9335_codec_init(struct snd_soc_component *component)
+{
+	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
+	int i;
+
+	/* ungate MCLK and set clk rate */
+	regmap_update_bits(wcd->regmap, WCD9335_CODEC_RPM_CLK_GATE,
+				WCD9335_CODEC_RPM_CLK_GATE_MCLK_GATE_MASK, 0);
+
+	regmap_update_bits(wcd->regmap, WCD9335_CODEC_RPM_CLK_MCLK_CFG,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG_9P6MHZ);
+
+	for (i = 0; i < ARRAY_SIZE(wcd9335_codec_reg_init_common_val); i++)
+		snd_soc_component_update_bits(component,
+				wcd9335_codec_reg_init_common_val[i].reg,
+				wcd9335_codec_reg_init_common_val[i].mask,
+				wcd9335_codec_reg_init_common_val[i].val);
+
+	if (WCD9335_IS_2_0(wcd->version)) {
+		for (i = 0; i < ARRAY_SIZE(wcd9335_codec_reg_init_val_2_0); i++)
+			snd_soc_component_update_bits(component,
+					wcd9335_codec_reg_init_val_2_0[i].reg,
+					wcd9335_codec_reg_init_val_2_0[i].mask,
+					wcd9335_codec_reg_init_val_2_0[i].val);
+	}
+
+	wcd9335_enable_efuse_sensing(component);
+}
+
+static int wcd9335_codec_probe(struct snd_soc_component *component)
+{
+	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
+	int i;
+
+	snd_soc_component_init_regmap(component, wcd->regmap);
+	wcd->component = component;
+
+	wcd9335_codec_init(component);
+
+	for (i = 0; i < NUM_CODEC_DAIS; i++)
+		INIT_LIST_HEAD(&wcd->dai[i].slim_ch_list);
+
+	return wcd9335_setup_irqs(wcd);
+}
+
+static void wcd9335_codec_remove(struct snd_soc_component *comp)
+{
+	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
+
+	free_irq(regmap_irq_get_virq(wcd->irq_data, WCD9335_IRQ_SLIMBUS), wcd);
+}
+
+static int wcd9335_codec_set_sysclk(struct snd_soc_component *comp,
+				    int clk_id, int source,
+				    unsigned int freq, int dir)
+{
+	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
+
+	wcd->mclk_rate = freq;
+
+	if (wcd->mclk_rate == WCD9335_MCLK_CLK_12P288MHZ)
+		snd_soc_component_update_bits(comp,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG_12P288MHZ);
+	else if (wcd->mclk_rate == WCD9335_MCLK_CLK_9P6MHZ)
+		snd_soc_component_update_bits(comp,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK,
+				WCD9335_CODEC_RPM_CLK_MCLK_CFG_9P6MHZ);
+
+	return clk_set_rate(wcd->mclk, freq);
+}
+
+static const struct snd_soc_component_driver wcd9335_component_drv = {
+	.probe = wcd9335_codec_probe,
+	.remove = wcd9335_codec_remove,
+	.set_sysclk = wcd9335_codec_set_sysclk,
+};
+
+static int wcd9335_probe(struct platform_device *pdev)
+{
+	struct wcd9335 *pdata = dev_get_drvdata(pdev->dev.parent);
+	struct device *dev = &pdev->dev;
+	struct wcd9335_codec *wcd;
+
+	wcd = devm_kzalloc(dev, sizeof(*wcd), GFP_KERNEL);
+	if (!wcd)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, wcd);
+
+	memcpy(wcd->rx_chs, wcd9335_rx_chs, sizeof(wcd9335_rx_chs));
+
+	wcd->regmap = pdata->regmap;
+	wcd->if_regmap = pdata->ifd_regmap;
+	wcd->slim = pdata->slim;
+	wcd->slim_ifd = pdata->slim_ifd;
+	wcd->irq_data = pdata->irq_data;
+	wcd->version = pdata->version;
+	wcd->intf_type = pdata->intf_type;
+	wcd->dev = dev;
+	wcd->mclk = pdata->mclk;
+	wcd->native_clk = pdata->native_clk;
+	wcd->sido_input_src = SIDO_SOURCE_INTERNAL;
+	wcd->sido_voltage = SIDO_VOLTAGE_NOMINAL_MV;
+
+	return devm_snd_soc_register_component(dev, &wcd9335_component_drv,
+					       wcd9335_slim_dais,
+					       ARRAY_SIZE(wcd9335_slim_dais));
+}
+
+static struct platform_driver wcd9335_codec_driver = {
+	.probe = wcd9335_probe,
+	.driver = {
+		.name = "wcd9335-codec",
+	},
+};
+module_platform_driver(wcd9335_codec_driver);
+MODULE_DESCRIPTION("WCD9335 Codec driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From c8cb5f775c8dacb605e628a320ded42be3bd9453 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 27 Jul 2018 13:18:01 +0100
Subject: ASoC: wcd9335: add CLASS-H Controller support

CLASS-H controller/Amplifier is common accorss Qualcomm WCD codec series.
This patchset adds basic CLASS-H controller apis for WCD codecs after
wcd9335 to use.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Makefile   |   2 +-
 sound/soc/codecs/wcd-clsh.c | 605 ++++++++++++++++++++++++++++++++++++++++++++
 sound/soc/codecs/wcd-clsh.h |  49 ++++
 sound/soc/codecs/wcd9335.c  |  10 +
 4 files changed, 665 insertions(+), 1 deletion(-)
 create mode 100644 sound/soc/codecs/wcd-clsh.c
 create mode 100644 sound/soc/codecs/wcd-clsh.h

diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index 01410b63daac..e3a3d4694e15 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -192,7 +192,7 @@ snd-soc-twl4030-objs := twl4030.o
 snd-soc-twl6040-objs := twl6040.o
 snd-soc-uda134x-objs := uda134x.o
 snd-soc-uda1380-objs := uda1380.o
-snd-soc-wcd9335-objs := wcd9335.o
+snd-soc-wcd9335-objs := wcd-clsh.o wcd9335.o
 snd-soc-wl1273-objs := wl1273.o
 snd-soc-wm-adsp-objs := wm_adsp.o
 snd-soc-wm0010-objs := wm0010.o
diff --git a/sound/soc/codecs/wcd-clsh.c b/sound/soc/codecs/wcd-clsh.c
new file mode 100644
index 000000000000..2393456cbd97
--- /dev/null
+++ b/sound/soc/codecs/wcd-clsh.c
@@ -0,0 +1,605 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
+// Copyright (c) 2017-2018, Linaro Limited
+
+#include <linux/slab.h>
+#include <sound/soc.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/mfd/wcd9335/wcd9335.h>
+#include <linux/mfd/wcd9335/registers.h>
+#include "wcd-clsh.h"
+
+struct wcd_clsh_ctrl {
+	int state;
+	int mode;
+	int flyback_users;
+	int buck_users;
+	int clsh_users;
+	int codec_version;
+	struct snd_soc_component *comp;
+};
+
+/* Class-H registers for codecs from and above WCD9335 */
+#define WCD9XXX_A_CDC_RX0_RX_PATH_CFG0			WCD9335_REG(0xB, 0x42)
+#define WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK		BIT(6)
+#define WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE		BIT(6)
+#define WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE		0
+#define WCD9XXX_A_CDC_RX1_RX_PATH_CFG0			WCD9335_REG(0xB, 0x56)
+#define WCD9XXX_A_CDC_RX2_RX_PATH_CFG0			WCD9335_REG(0xB, 0x6A)
+#define WCD9XXX_A_CDC_CLSH_K1_MSB			WCD9335_REG(0xC, 0x08)
+#define WCD9XXX_A_CDC_CLSH_K1_MSB_COEF_MASK		GENMASK(3, 0)
+#define WCD9XXX_A_CDC_CLSH_K1_LSB			WCD9335_REG(0xC, 0x09)
+#define WCD9XXX_A_CDC_CLSH_K1_LSB_COEF_MASK		GENMASK(7, 0)
+#define WCD9XXX_A_ANA_RX_SUPPLIES			WCD9335_REG(0x6, 0x08)
+#define WCD9XXX_A_ANA_RX_REGULATOR_MODE_MASK		BIT(1)
+#define WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_H		0
+#define WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_AB		BIT(1)
+#define WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_MASK		BIT(2)
+#define WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_UHQA		BIT(2)
+#define WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_DEFAULT		0
+#define WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_MASK		BIT(3)
+#define WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_UHQA		BIT(3)
+#define WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_DEFAULT		0
+#define WCD9XXX_A_ANA_RX_VNEG_EN_MASK			BIT(6)
+#define WCD9XXX_A_ANA_RX_VNEG_EN_SHIFT			6
+#define WCD9XXX_A_ANA_RX_VNEG_ENABLE			BIT(6)
+#define WCD9XXX_A_ANA_RX_VNEG_DISABLE			0
+#define WCD9XXX_A_ANA_RX_VPOS_EN_MASK			BIT(7)
+#define WCD9XXX_A_ANA_RX_VPOS_EN_SHIFT			7
+#define WCD9XXX_A_ANA_RX_VPOS_ENABLE			BIT(7)
+#define WCD9XXX_A_ANA_RX_VPOS_DISABLE			0
+#define WCD9XXX_A_ANA_HPH				WCD9335_REG(0x6, 0x09)
+#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_MASK		GENMASK(3, 2)
+#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_UHQA		0x08
+#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_LP			0x04
+#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_NORMAL		0x0
+#define WCD9XXX_A_CDC_CLSH_CRC				WCD9335_REG(0xC, 0x01)
+#define WCD9XXX_A_CDC_CLSH_CRC_CLK_EN_MASK		BIT(0)
+#define WCD9XXX_A_CDC_CLSH_CRC_CLK_ENABLE		BIT(0)
+#define WCD9XXX_A_CDC_CLSH_CRC_CLK_DISABLE		0
+#define WCD9XXX_FLYBACK_EN				WCD9335_REG(0x6, 0xA4)
+#define WCD9XXX_FLYBACK_EN_DELAY_SEL_MASK		GENMASK(6, 5)
+#define WCD9XXX_FLYBACK_EN_DELAY_26P25_US		0x40
+#define WCD9XXX_FLYBACK_EN_RESET_BY_EXT_MASK		BIT(4)
+#define WCD9XXX_FLYBACK_EN_PWDN_WITHOUT_DELAY		BIT(4)
+#define WCD9XXX_FLYBACK_EN_PWDN_WITH_DELAY			0
+#define WCD9XXX_RX_BIAS_FLYB_BUFF			WCD9335_REG(0x6, 0xC7)
+#define WCD9XXX_RX_BIAS_FLYB_VNEG_5_UA_MASK		GENMASK(7, 4)
+#define WCD9XXX_RX_BIAS_FLYB_VPOS_5_UA_MASK		GENMASK(0, 3)
+#define WCD9XXX_HPH_L_EN				WCD9335_REG(0x6, 0xD3)
+#define WCD9XXX_HPH_CONST_SEL_L_MASK			GENMASK(7, 3)
+#define WCD9XXX_HPH_CONST_SEL_BYPASS			0
+#define WCD9XXX_HPH_CONST_SEL_LP_PATH			0x40
+#define WCD9XXX_HPH_CONST_SEL_HQ_PATH			0x80
+#define WCD9XXX_HPH_R_EN				WCD9335_REG(0x6, 0xD6)
+#define WCD9XXX_HPH_REFBUFF_UHQA_CTL			WCD9335_REG(0x6, 0xDD)
+#define WCD9XXX_HPH_REFBUFF_UHQA_GAIN_MASK		GENMASK(2, 0)
+#define WCD9XXX_CLASSH_CTRL_VCL_2                       WCD9335_REG(0x6, 0x9B)
+#define WCD9XXX_CLASSH_CTRL_VCL_2_VREF_FILT_1_MASK	GENMASK(5, 4)
+#define WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_50KOHM	0x20
+#define WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_0KOHM	0x0
+#define WCD9XXX_CDC_RX1_RX_PATH_CTL			WCD9335_REG(0xB, 0x55)
+#define WCD9XXX_CDC_RX2_RX_PATH_CTL			WCD9335_REG(0xB, 0x69)
+#define WCD9XXX_CDC_CLK_RST_CTRL_MCLK_CONTROL		WCD9335_REG(0xD, 0x41)
+#define WCD9XXX_CDC_CLK_RST_CTRL_MCLK_EN_MASK		BIT(0)
+#define WCD9XXX_CDC_CLK_RST_CTRL_MCLK_11P3_EN_MASK	BIT(1)
+#define WCD9XXX_CLASSH_CTRL_CCL_1                       WCD9335_REG(0x6, 0x9C)
+#define WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_MASK	GENMASK(7, 4)
+#define WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA	0x50
+#define WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_30MA	0x30
+
+#define CLSH_REQ_ENABLE		true
+#define CLSH_REQ_DISABLE	false
+#define WCD_USLEEP_RANGE	50
+
+enum {
+	DAC_GAIN_0DB = 0,
+	DAC_GAIN_0P2DB,
+	DAC_GAIN_0P4DB,
+	DAC_GAIN_0P6DB,
+	DAC_GAIN_0P8DB,
+	DAC_GAIN_M0P2DB,
+	DAC_GAIN_M0P4DB,
+	DAC_GAIN_M0P6DB,
+};
+
+static inline void wcd_enable_clsh_block(struct wcd_clsh_ctrl *ctrl,
+					 bool enable)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	if ((enable && ++ctrl->clsh_users == 1) ||
+	    (!enable && --ctrl->clsh_users == 0))
+		snd_soc_component_update_bits(comp, WCD9XXX_A_CDC_CLSH_CRC,
+				      WCD9XXX_A_CDC_CLSH_CRC_CLK_EN_MASK,
+				      enable);
+	if (ctrl->clsh_users < 0)
+		ctrl->clsh_users = 0;
+}
+
+static inline bool wcd_clsh_enable_status(struct snd_soc_component *comp)
+{
+	return snd_soc_component_read32(comp, WCD9XXX_A_CDC_CLSH_CRC) &
+					WCD9XXX_A_CDC_CLSH_CRC_CLK_EN_MASK;
+}
+
+static inline void wcd_clsh_set_buck_mode(struct snd_soc_component *comp,
+					  int mode)
+{
+	/* set to HIFI */
+	if (mode == CLS_H_HIFI)
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_MASK,
+					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_UHQA);
+	else
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_MASK,
+					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_DEFAULT);
+}
+
+static inline void wcd_clsh_set_flyback_mode(struct snd_soc_component *comp,
+					     int mode)
+{
+	/* set to HIFI */
+	if (mode == CLS_H_HIFI)
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_MASK,
+					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_UHQA);
+	else
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_MASK,
+					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_DEFAULT);
+}
+
+static void wcd_clsh_buck_ctrl(struct wcd_clsh_ctrl *ctrl,
+			       int mode,
+			       bool enable)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	/* enable/disable buck */
+	if ((enable && (++ctrl->buck_users == 1)) ||
+	   (!enable && (--ctrl->buck_users == 0)))
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+				WCD9XXX_A_ANA_RX_VPOS_EN_MASK,
+				enable << WCD9XXX_A_ANA_RX_VPOS_EN_SHIFT);
+	/*
+	 * 500us sleep is required after buck enable/disable
+	 * as per HW requirement
+	 */
+	usleep_range(500, 500 + WCD_USLEEP_RANGE);
+}
+
+static void wcd_clsh_flyback_ctrl(struct wcd_clsh_ctrl *ctrl,
+				  int mode,
+				  bool enable)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	int vneg[] = {0x00, 0x40};
+
+	/* enable/disable flyback */
+	if ((enable && (++ctrl->flyback_users == 1)) ||
+	   (!enable && (--ctrl->flyback_users == 0))) {
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+				WCD9XXX_A_ANA_RX_VNEG_EN_MASK,
+				enable << WCD9XXX_A_ANA_RX_VNEG_EN_SHIFT);
+		/* 100usec delay is needed as per HW requirement */
+		usleep_range(100, 110);
+
+		if (enable && (WCD9335_IS_1_1(ctrl->codec_version))) {
+			wcd_clsh_set_flyback_mode(comp, CLS_H_HIFI);
+			snd_soc_component_update_bits(comp, WCD9XXX_FLYBACK_EN,
+					WCD9XXX_FLYBACK_EN_DELAY_SEL_MASK,
+					WCD9XXX_FLYBACK_EN_DELAY_26P25_US);
+			snd_soc_component_update_bits(comp, WCD9XXX_FLYBACK_EN,
+					WCD9XXX_FLYBACK_EN_RESET_BY_EXT_MASK,
+					WCD9XXX_FLYBACK_EN_PWDN_WITHOUT_DELAY);
+			vneg[0] = snd_soc_component_read32(comp,
+					       WCD9XXX_A_ANA_RX_SUPPLIES);
+			vneg[0] &= ~(0x40);
+			vneg[1] = vneg[0] | 0x40;
+
+			snd_soc_component_write(comp,
+					WCD9XXX_A_ANA_RX_SUPPLIES, vneg[0]);
+			snd_soc_component_write(comp,
+					WCD9XXX_A_ANA_RX_SUPPLIES, vneg[1]);
+			/* 500usec delay is needed as per HW requirement */
+			usleep_range(500, 510);
+			snd_soc_component_update_bits(comp, WCD9XXX_FLYBACK_EN,
+					WCD9XXX_FLYBACK_EN_RESET_BY_EXT_MASK,
+					WCD9XXX_FLYBACK_EN_PWDN_WITH_DELAY);
+			wcd_clsh_set_flyback_mode(comp, mode);
+		}
+
+	}
+	/*
+	 * 500us sleep is required after flyback enable/disable
+	 * as per HW requirement
+	 */
+	usleep_range(500, 500 + WCD_USLEEP_RANGE);
+}
+
+static void wcd_clsh_set_gain_path(struct wcd_clsh_ctrl *ctrl, int mode)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+	int val = 0;
+
+	switch (mode) {
+	case CLS_H_NORMAL:
+	case CLS_AB:
+		val = WCD9XXX_HPH_CONST_SEL_BYPASS;
+		break;
+	case CLS_H_HIFI:
+		val = WCD9XXX_HPH_CONST_SEL_HQ_PATH;
+		break;
+	case CLS_H_LP:
+		val = WCD9XXX_HPH_CONST_SEL_LP_PATH;
+		break;
+	};
+
+	snd_soc_component_update_bits(comp, WCD9XXX_HPH_L_EN,
+					WCD9XXX_HPH_CONST_SEL_L_MASK,
+					val);
+
+	snd_soc_component_update_bits(comp, WCD9XXX_HPH_R_EN,
+					WCD9XXX_HPH_CONST_SEL_L_MASK,
+					val);
+}
+
+static void wcd_clsh_set_hph_mode(struct snd_soc_component *comp,
+				  int mode)
+{
+	int val = 0, gain = 0, res_val;
+	int ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
+
+	res_val = WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_0KOHM;
+	switch (mode) {
+	case CLS_H_NORMAL:
+		res_val = WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_50KOHM;
+		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_NORMAL;
+		gain = DAC_GAIN_0DB;
+		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
+		break;
+	case CLS_AB:
+		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_NORMAL;
+		gain = DAC_GAIN_0DB;
+		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
+		break;
+	case CLS_H_HIFI:
+		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_UHQA;
+		gain = DAC_GAIN_M0P2DB;
+		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
+		break;
+	case CLS_H_LP:
+		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_LP;
+		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_30MA;
+		break;
+	};
+
+	snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_HPH,
+					WCD9XXX_A_ANA_HPH_PWR_LEVEL_MASK, val);
+	snd_soc_component_update_bits(comp, WCD9XXX_CLASSH_CTRL_VCL_2,
+				WCD9XXX_CLASSH_CTRL_VCL_2_VREF_FILT_1_MASK,
+				res_val);
+	if (mode != CLS_H_LP)
+		snd_soc_component_update_bits(comp,
+					WCD9XXX_HPH_REFBUFF_UHQA_CTL,
+					WCD9XXX_HPH_REFBUFF_UHQA_GAIN_MASK,
+					gain);
+	snd_soc_component_update_bits(comp, WCD9XXX_CLASSH_CTRL_CCL_1,
+				WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_MASK,
+				ipeak);
+}
+
+static void wcd_clsh_set_flyback_current(struct snd_soc_component *comp,
+					 int mode)
+{
+
+	snd_soc_component_update_bits(comp, WCD9XXX_RX_BIAS_FLYB_BUFF,
+				WCD9XXX_RX_BIAS_FLYB_VPOS_5_UA_MASK, 0x0A);
+	snd_soc_component_update_bits(comp, WCD9XXX_RX_BIAS_FLYB_BUFF,
+				WCD9XXX_RX_BIAS_FLYB_VNEG_5_UA_MASK, 0x0A);
+	/* Sleep needed to avoid click and pop as per HW requirement */
+	usleep_range(100, 110);
+}
+
+static void wcd_clsh_set_buck_regulator_mode(struct snd_soc_component *comp,
+					     int mode)
+{
+	if (mode == CLS_AB)
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+					WCD9XXX_A_ANA_RX_REGULATOR_MODE_MASK,
+					WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_AB);
+	else
+		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
+					WCD9XXX_A_ANA_RX_REGULATOR_MODE_MASK,
+					WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_H);
+}
+
+static void wcd_clsh_state_lo(struct wcd_clsh_ctrl *ctrl, int req_state,
+			      bool is_enable, int mode)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	if (mode != CLS_AB) {
+		dev_err(comp->dev, "%s: LO cannot be in this mode: %d\n",
+			__func__, mode);
+		return;
+	}
+
+	if (is_enable) {
+		wcd_clsh_set_buck_regulator_mode(comp, mode);
+		wcd_clsh_set_buck_mode(comp, mode);
+		wcd_clsh_set_flyback_mode(comp, mode);
+		wcd_clsh_flyback_ctrl(ctrl, mode, true);
+		wcd_clsh_set_flyback_current(comp, mode);
+		wcd_clsh_buck_ctrl(ctrl, mode, true);
+	} else {
+		wcd_clsh_buck_ctrl(ctrl, mode, false);
+		wcd_clsh_flyback_ctrl(ctrl, mode, false);
+		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
+		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
+		wcd_clsh_set_buck_regulator_mode(comp, CLS_H_NORMAL);
+	}
+}
+
+static void wcd_clsh_state_hph_r(struct wcd_clsh_ctrl *ctrl, int req_state,
+				 bool is_enable, int mode)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	if (mode == CLS_H_NORMAL) {
+		dev_err(comp->dev, "%s: Normal mode not applicable for hph_r\n",
+			__func__);
+		return;
+	}
+
+	if (is_enable) {
+		if (mode != CLS_AB) {
+			wcd_enable_clsh_block(ctrl, true);
+			/*
+			 * These K1 values depend on the Headphone Impedance
+			 * For now it is assumed to be 16 ohm
+			 */
+			snd_soc_component_update_bits(comp,
+					WCD9XXX_A_CDC_CLSH_K1_MSB,
+					WCD9XXX_A_CDC_CLSH_K1_MSB_COEF_MASK,
+					0x00);
+			snd_soc_component_update_bits(comp,
+					WCD9XXX_A_CDC_CLSH_K1_LSB,
+					WCD9XXX_A_CDC_CLSH_K1_LSB_COEF_MASK,
+					0xC0);
+			snd_soc_component_update_bits(comp,
+					    WCD9XXX_A_CDC_RX2_RX_PATH_CFG0,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE);
+		}
+		wcd_clsh_set_buck_regulator_mode(comp, mode);
+		wcd_clsh_set_flyback_mode(comp, mode);
+		wcd_clsh_flyback_ctrl(ctrl, mode, true);
+		wcd_clsh_set_flyback_current(comp, mode);
+		wcd_clsh_set_buck_mode(comp, mode);
+		wcd_clsh_buck_ctrl(ctrl, mode, true);
+		wcd_clsh_set_hph_mode(comp, mode);
+		wcd_clsh_set_gain_path(ctrl, mode);
+	} else {
+		wcd_clsh_set_hph_mode(comp, CLS_H_NORMAL);
+
+		if (mode != CLS_AB) {
+			snd_soc_component_update_bits(comp,
+					    WCD9XXX_A_CDC_RX2_RX_PATH_CFG0,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE);
+			wcd_enable_clsh_block(ctrl, false);
+		}
+		/* buck and flyback set to default mode and disable */
+		wcd_clsh_buck_ctrl(ctrl, CLS_H_NORMAL, false);
+		wcd_clsh_flyback_ctrl(ctrl, CLS_H_NORMAL, false);
+		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
+		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
+		wcd_clsh_set_buck_regulator_mode(comp, CLS_H_NORMAL);
+	}
+}
+
+static void wcd_clsh_state_hph_l(struct wcd_clsh_ctrl *ctrl, int req_state,
+				 bool is_enable, int mode)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	if (mode == CLS_H_NORMAL) {
+		dev_err(comp->dev, "%s: Normal mode not applicable for hph_l\n",
+			__func__);
+		return;
+	}
+
+	if (is_enable) {
+		if (mode != CLS_AB) {
+			wcd_enable_clsh_block(ctrl, true);
+			/*
+			 * These K1 values depend on the Headphone Impedance
+			 * For now it is assumed to be 16 ohm
+			 */
+			snd_soc_component_update_bits(comp,
+					WCD9XXX_A_CDC_CLSH_K1_MSB,
+					WCD9XXX_A_CDC_CLSH_K1_MSB_COEF_MASK,
+					0x00);
+			snd_soc_component_update_bits(comp,
+					WCD9XXX_A_CDC_CLSH_K1_LSB,
+					WCD9XXX_A_CDC_CLSH_K1_LSB_COEF_MASK,
+					0xC0);
+			snd_soc_component_update_bits(comp,
+					    WCD9XXX_A_CDC_RX1_RX_PATH_CFG0,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE);
+		}
+		wcd_clsh_set_buck_regulator_mode(comp, mode);
+		wcd_clsh_set_flyback_mode(comp, mode);
+		wcd_clsh_flyback_ctrl(ctrl, mode, true);
+		wcd_clsh_set_flyback_current(comp, mode);
+		wcd_clsh_set_buck_mode(comp, mode);
+		wcd_clsh_buck_ctrl(ctrl, mode, true);
+		wcd_clsh_set_hph_mode(comp, mode);
+		wcd_clsh_set_gain_path(ctrl, mode);
+	} else {
+		wcd_clsh_set_hph_mode(comp, CLS_H_NORMAL);
+
+		if (mode != CLS_AB) {
+			snd_soc_component_update_bits(comp,
+					    WCD9XXX_A_CDC_RX1_RX_PATH_CFG0,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
+					    WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE);
+			wcd_enable_clsh_block(ctrl, false);
+		}
+		/* set buck and flyback to Default Mode */
+		wcd_clsh_buck_ctrl(ctrl, CLS_H_NORMAL, false);
+		wcd_clsh_flyback_ctrl(ctrl, CLS_H_NORMAL, false);
+		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
+		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
+		wcd_clsh_set_buck_regulator_mode(comp, CLS_H_NORMAL);
+	}
+}
+
+static void wcd_clsh_state_ear(struct wcd_clsh_ctrl *ctrl, int req_state,
+			       bool is_enable, int mode)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	if (mode != CLS_H_NORMAL) {
+		dev_err(comp->dev, "%s: mode: %d cannot be used for EAR\n",
+			__func__, mode);
+		return;
+	}
+
+	if (is_enable) {
+		wcd_enable_clsh_block(ctrl, true);
+		snd_soc_component_update_bits(comp,
+					WCD9XXX_A_CDC_RX0_RX_PATH_CFG0,
+					WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
+					WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE);
+		wcd_clsh_set_buck_mode(comp, mode);
+		wcd_clsh_set_flyback_mode(comp, mode);
+		wcd_clsh_flyback_ctrl(ctrl, mode, true);
+		wcd_clsh_set_flyback_current(comp, mode);
+		wcd_clsh_buck_ctrl(ctrl, mode, true);
+	} else {
+		snd_soc_component_update_bits(comp,
+					WCD9XXX_A_CDC_RX0_RX_PATH_CFG0,
+					WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
+					WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE);
+		wcd_enable_clsh_block(ctrl, false);
+		wcd_clsh_buck_ctrl(ctrl, mode, false);
+		wcd_clsh_flyback_ctrl(ctrl, mode, false);
+		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
+		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
+	}
+}
+
+static int _wcd_clsh_ctrl_set_state(struct wcd_clsh_ctrl *ctrl, int req_state,
+				    bool is_enable, int mode)
+{
+	switch (req_state) {
+	case WCD_CLSH_STATE_EAR:
+		wcd_clsh_state_ear(ctrl, req_state, is_enable, mode);
+		break;
+	case WCD_CLSH_STATE_HPHL:
+		wcd_clsh_state_hph_l(ctrl, req_state, is_enable, mode);
+		break;
+	case WCD_CLSH_STATE_HPHR:
+		wcd_clsh_state_hph_r(ctrl, req_state, is_enable, mode);
+		break;
+		break;
+	case WCD_CLSH_STATE_LO:
+		wcd_clsh_state_lo(ctrl, req_state, is_enable, mode);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+/*
+ * Function: wcd_clsh_is_state_valid
+ * Params: state
+ * Description:
+ * Provides information on valid states of Class H configuration
+ */
+static bool wcd_clsh_is_state_valid(int state)
+{
+	switch (state) {
+	case WCD_CLSH_STATE_IDLE:
+	case WCD_CLSH_STATE_EAR:
+	case WCD_CLSH_STATE_HPHL:
+	case WCD_CLSH_STATE_HPHR:
+	case WCD_CLSH_STATE_LO:
+		return true;
+	default:
+		return false;
+	};
+}
+
+/*
+ * Function: wcd_clsh_fsm
+ * Params: ctrl, req_state, req_type, clsh_event
+ * Description:
+ * This function handles PRE DAC and POST DAC conditions of different devices
+ * and updates class H configuration of different combination of devices
+ * based on validity of their states. ctrl will contain current
+ * class h state information
+ */
+int wcd_clsh_ctrl_set_state(struct wcd_clsh_ctrl *ctrl,
+			    enum wcd_clsh_event clsh_event,
+			    int nstate,
+			    enum wcd_clsh_mode mode)
+{
+	struct snd_soc_component *comp = ctrl->comp;
+
+	if (nstate == ctrl->state)
+		return 0;
+
+	if (!wcd_clsh_is_state_valid(nstate)) {
+		dev_err(comp->dev, "Class-H not a valid new state:\n");
+		return -EINVAL;
+	}
+
+	switch (clsh_event) {
+	case WCD_CLSH_EVENT_PRE_DAC:
+		_wcd_clsh_ctrl_set_state(ctrl, nstate, CLSH_REQ_ENABLE, mode);
+		break;
+	case WCD_CLSH_EVENT_POST_PA:
+		_wcd_clsh_ctrl_set_state(ctrl, nstate, CLSH_REQ_DISABLE, mode);
+		break;
+	};
+
+	ctrl->state = nstate;
+	ctrl->mode = mode;
+
+	return 0;
+}
+
+int wcd_clsh_ctrl_get_state(struct wcd_clsh_ctrl *ctrl)
+{
+	return ctrl->state;
+}
+
+struct wcd_clsh_ctrl *wcd_clsh_ctrl_alloc(struct snd_soc_component *comp,
+					  int version)
+{
+	struct wcd_clsh_ctrl *ctrl;
+
+	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
+	if (!ctrl)
+		return ERR_PTR(-ENOMEM);
+
+	ctrl->state = WCD_CLSH_STATE_IDLE;
+	ctrl->comp = comp;
+
+	return ctrl;
+}
+
+void wcd_clsh_ctrl_free(struct wcd_clsh_ctrl *ctrl)
+{
+	kfree(ctrl);
+}
diff --git a/sound/soc/codecs/wcd-clsh.h b/sound/soc/codecs/wcd-clsh.h
new file mode 100644
index 000000000000..a902f9893467
--- /dev/null
+++ b/sound/soc/codecs/wcd-clsh.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _WCD_CLSH_V2_H_
+#define _WCD_CLSH_V2_H_
+#include <sound/soc.h>
+
+enum wcd_clsh_event {
+	WCD_CLSH_EVENT_PRE_DAC = 1,
+	WCD_CLSH_EVENT_POST_PA,
+};
+
+/*
+ * Basic states for Class H state machine.
+ * represented as a bit mask within a u8 data type
+ * bit 0: EAR mode
+ * bit 1: HPH Left mode
+ * bit 2: HPH Right mode
+ * bit 3: Lineout mode
+ */
+#define	WCD_CLSH_STATE_IDLE	0
+#define	WCD_CLSH_STATE_EAR	BIT(0)
+#define	WCD_CLSH_STATE_HPHL	BIT(1)
+#define	WCD_CLSH_STATE_HPHR	BIT(2)
+#define	WCD_CLSH_STATE_LO	BIT(3)
+#define WCD_CLSH_STATE_MAX	4
+#define NUM_CLSH_STATES_V2	BIT(WCD_CLSH_STATE_MAX)
+
+enum wcd_clsh_mode {
+	CLS_H_NORMAL = 0, /* Class-H Default */
+	CLS_H_HIFI, /* Class-H HiFi */
+	CLS_H_LP, /* Class-H Low Power */
+	CLS_AB, /* Class-AB */
+	CLS_H_LOHIFI, /* LoHIFI */
+	CLS_NONE, /* None of the above modes */
+};
+
+struct wcd_clsh_ctrl;
+
+extern struct wcd_clsh_ctrl *wcd_clsh_ctrl_alloc(
+				struct snd_soc_component *component,
+				int version);
+extern void wcd_clsh_ctrl_free(struct wcd_clsh_ctrl *ctrl);
+extern int wcd_clsh_ctrl_get_state(struct wcd_clsh_ctrl *ctrl);
+extern int wcd_clsh_ctrl_set_state(struct wcd_clsh_ctrl *ctrl,
+				   enum wcd_clsh_event event,
+				   int state,
+				   enum wcd_clsh_mode mode);
+
+#endif /* _WCD_CLSH_V2_H_ */
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index bd9de5d45fa9..06c73699f16f 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -21,6 +21,7 @@
 #include <dt-bindings/mfd/wcd9335.h>
 #include <linux/mfd/wcd9335/wcd9335.h>
 #include <linux/mfd/wcd9335/registers.h>
+#include "wcd-clsh.h"
 
 #define WCD9335_RATES_MASK (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
 			    SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000 |\
@@ -181,6 +182,7 @@ struct wcd9335_codec {
 	int sido_ccl_cnt;
 	enum wcd_clock_type clk_type;
 
+	struct wcd_clsh_ctrl *clsh_ctrl;
 	u32 hph_mode;
 };
 
@@ -1066,6 +1068,13 @@ static int wcd9335_codec_probe(struct snd_soc_component *component)
 	int i;
 
 	snd_soc_component_init_regmap(component, wcd->regmap);
+	/* Class-H Init*/
+	wcd->clsh_ctrl = wcd_clsh_ctrl_alloc(component, wcd->version);
+	if (IS_ERR(wcd->clsh_ctrl))
+		return PTR_ERR(wcd->clsh_ctrl);
+
+	/* Default HPH Mode to Class-H HiFi */
+	wcd->hph_mode = CLS_H_HIFI;
 	wcd->component = component;
 
 	wcd9335_codec_init(component);
@@ -1080,6 +1089,7 @@ static void wcd9335_codec_remove(struct snd_soc_component *comp)
 {
 	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
 
+	wcd_clsh_ctrl_free(wcd->clsh_ctrl);
 	free_irq(regmap_irq_get_virq(wcd->irq_data, WCD9335_IRQ_SLIMBUS), wcd);
 }
 
-- 
cgit v1.2.3


From 9eaf3ba5e0557eef9c3d9a64c72b9352cdc49d50 Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 31 Jul 2018 16:38:54 +0200
Subject: mips: dts: mscc: Add spi on Ocelot

Add support for the SPI controller

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20101/
Cc: Mark Brown <broonie@kernel.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-spi@vger.kernel.org
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Cc: Allan Nielsen <allan.nielsen@microsemi.com>
---
 arch/mips/boot/dts/mscc/ocelot.dtsi | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/mips/boot/dts/mscc/ocelot.dtsi b/arch/mips/boot/dts/mscc/ocelot.dtsi
index afe8fc9011ea..f7eb612b46ba 100644
--- a/arch/mips/boot/dts/mscc/ocelot.dtsi
+++ b/arch/mips/boot/dts/mscc/ocelot.dtsi
@@ -91,6 +91,17 @@
 			status = "disabled";
 		};
 
+		spi: spi@101000 {
+			compatible = "mscc,ocelot-spi", "snps,dw-apb-ssi";
+			#address-cells = <1>;
+			#size-cells = <0>;
+			reg = <0x101000 0x100>, <0x3c 0x18>;
+			interrupts = <9>;
+			clocks = <&ahb_clk>;
+
+			status = "disabled";
+		};
+
 		switch@1010000 {
 			compatible = "mscc,vsc7514-switch";
 			reg = <0x1010000 0x10000>,
-- 
cgit v1.2.3


From 84a7f564fa14bf4713240f614c0b9a18730418fa Mon Sep 17 00:00:00 2001
From: Alexandre Belloni <alexandre.belloni@bootlin.com>
Date: Tue, 31 Jul 2018 16:38:55 +0200
Subject: mips: dts: mscc: enable spi and NOR flash support on ocelot PCB123

Ocelot PCB123 has a SPI NOR connected on its SPI bus.

Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20103/
Cc: Mark Brown <broonie@kernel.org>
Cc: James Hogan <jhogan@kernel.org>
Cc: linux-spi@vger.kernel.org
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Cc: Allan Nielsen <allan.nielsen@microsemi.com>
---
 arch/mips/boot/dts/mscc/ocelot_pcb123.dts | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
index 4ccd65379059..2266027759f9 100644
--- a/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
+++ b/arch/mips/boot/dts/mscc/ocelot_pcb123.dts
@@ -26,6 +26,16 @@
 	status = "okay";
 };
 
+&spi {
+	status = "okay";
+
+	flash@0 {
+		compatible = "macronix,mx25l25635f", "jedec,spi-nor";
+		spi-max-frequency = <20000000>;
+		reg = <0>;
+	};
+};
+
 &mdio0 {
 	status = "okay";
 };
-- 
cgit v1.2.3


From 8bb46b079d05be4435892869dad23e9af23098ab Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sat, 28 Jul 2018 07:22:00 +0200
Subject: PCI: pciehp: Avoid implicit fallthroughs in switch statements

Per Mika's request, add an explicit break to the last case of switch
statements everywhere in pciehp to be more defensive towards future
amendments.

Per Gustavo's request, mark all non-empty implicit fallthroughs with a
comment to silence warnings triggered by -Wimplicit-fallthrough=2.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
---
 drivers/pci/hotplug/pciehp_ctrl.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c
index 6855933ab372..da7c72372ffc 100644
--- a/drivers/pci/hotplug/pciehp_ctrl.c
+++ b/drivers/pci/hotplug/pciehp_ctrl.c
@@ -211,6 +211,7 @@ void pciehp_handle_disable_request(struct slot *slot)
 	case BLINKINGON_STATE:
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&slot->work);
+		break;
 	}
 	slot->state = POWEROFF_STATE;
 	mutex_unlock(&slot->lock);
@@ -232,6 +233,7 @@ void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events)
 	switch (slot->state) {
 	case BLINKINGOFF_STATE:
 		cancel_delayed_work(&slot->work);
+		/* fall through */
 	case ON_STATE:
 		slot->state = POWEROFF_STATE;
 		mutex_unlock(&slot->lock);
@@ -245,6 +247,7 @@ void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events)
 		break;
 	default:
 		mutex_unlock(&slot->lock);
+		break;
 	}
 
 	/* Turn the slot on if it's occupied or link is up */
@@ -259,6 +262,7 @@ void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events)
 	switch (slot->state) {
 	case BLINKINGON_STATE:
 		cancel_delayed_work(&slot->work);
+		/* fall through */
 	case OFF_STATE:
 		slot->state = POWERON_STATE;
 		mutex_unlock(&slot->lock);
@@ -272,6 +276,7 @@ void pciehp_handle_presence_or_link_change(struct slot *slot, u32 events)
 		break;
 	default:
 		mutex_unlock(&slot->lock);
+		break;
 	}
 }
 
-- 
cgit v1.2.3


From 4e6a13356f1c1dc27ff48ff35576a478d73f8713 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sat, 28 Jul 2018 07:22:00 +0200
Subject: PCI: pciehp: Deduplicate presence check on probe & resume

On driver probe and on resume from system sleep, pciehp checks the
Presence Detect State bit in the Slot Status register to bring up an
occupied slot or bring down an unoccupied slot.  Both code paths are
identical, so deduplicate them per Mika's request.

On probe, an additional check is performed to disable power of an
unoccupied slot.  This can e.g. happen if power was enabled by BIOS.
It cannot happen once pciehp has taken control, hence is not necessary
on resume:  The Slot Control register is set to the same value that it
had on suspend by pci_restore_state(), so if the slot was occupied,
power is enabled and if it wasn't, power is disabled.  Should occupancy
have changed during the system sleep transition, power is adjusted by
bringing up or down the slot per the paragraph above.

To allow for deduplication of the presence check, move the power check
to pcie_init().  This seems safer anyway, because right now it is
performed while interrupts are already enabled, and although I can't
think of a scenario where pciehp_power_off_slot() and the IRQ thread
collide, it does feel brittle.

However this means that pcie_init() may now write to the Slot Control
register before the IRQ is requested.  If both the CCIE and HPIE bits
happen to be set, pcie_wait_cmd() will wait for an interrupt (instead
of polling the Command Completed bit) and eventually emit a timeout
message.  Additionally, if a level-triggered INTx interrupt is used,
the user may see a spurious interrupt splat.  Avoid by disabling
interrupts before disabling power.  (Normally the HPIE and CCIE bits
should be clear on probe, but conceivably they may already have been
set e.g. by BIOS.)

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/pci/hotplug/pciehp_core.c | 63 ++++++++++++++++++++-------------------
 drivers/pci/hotplug/pciehp_hpc.c  | 14 +++++++++
 2 files changed, 46 insertions(+), 31 deletions(-)

diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c
index 01fcf1fa0f66..ec48c9433ae5 100644
--- a/drivers/pci/hotplug/pciehp_core.c
+++ b/drivers/pci/hotplug/pciehp_core.c
@@ -200,12 +200,40 @@ static int reset_slot(struct hotplug_slot *hotplug_slot, int probe)
 	return pciehp_reset_slot(slot, probe);
 }
 
+/**
+ * pciehp_check_presence() - synthesize event if presence has changed
+ *
+ * On probe and resume, an explicit presence check is necessary to bring up an
+ * occupied slot or bring down an unoccupied slot.  This can't be triggered by
+ * events in the Slot Status register, they may be stale and are therefore
+ * cleared.  Secondly, sending an interrupt for "events that occur while
+ * interrupt generation is disabled [when] interrupt generation is subsequently
+ * enabled" is optional per PCIe r4.0, sec 6.7.3.4.
+ */
+static void pciehp_check_presence(struct controller *ctrl)
+{
+	struct slot *slot = ctrl->slot;
+	u8 occupied;
+
+	down_read(&ctrl->reset_lock);
+	mutex_lock(&slot->lock);
+
+	pciehp_get_adapter_status(slot, &occupied);
+	if ((occupied && (slot->state == OFF_STATE ||
+			  slot->state == BLINKINGON_STATE)) ||
+	    (!occupied && (slot->state == ON_STATE ||
+			   slot->state == BLINKINGOFF_STATE)))
+		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
+
+	mutex_unlock(&slot->lock);
+	up_read(&ctrl->reset_lock);
+}
+
 static int pciehp_probe(struct pcie_device *dev)
 {
 	int rc;
 	struct controller *ctrl;
 	struct slot *slot;
-	u8 occupied, poweron;
 
 	/* If this is not a "hotplug" service, we have no business here. */
 	if (dev->service != PCIE_PORT_SERVICE_HP)
@@ -250,21 +278,7 @@ static int pciehp_probe(struct pcie_device *dev)
 		goto err_out_shutdown_notification;
 	}
 
-	/* Check if slot is occupied */
-	down_read(&ctrl->reset_lock);
-	mutex_lock(&slot->lock);
-	pciehp_get_adapter_status(slot, &occupied);
-	pciehp_get_power_status(slot, &poweron);
-	if ((occupied && (slot->state == OFF_STATE ||
-			  slot->state == BLINKINGON_STATE)) ||
-	    (!occupied && (slot->state == ON_STATE ||
-			   slot->state == BLINKINGOFF_STATE)))
-		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
-	/* If empty slot's power status is on, turn power off */
-	if (!occupied && poweron && POWER_CTRL(ctrl))
-		pciehp_power_off_slot(slot);
-	mutex_unlock(&slot->lock);
-	up_read(&ctrl->reset_lock);
+	pciehp_check_presence(ctrl);
 
 	return 0;
 
@@ -311,22 +325,9 @@ static int pciehp_resume_noirq(struct pcie_device *dev)
 
 static int pciehp_resume(struct pcie_device *dev)
 {
-	struct controller *ctrl;
-	struct slot *slot;
-	u8 status;
-
-	ctrl = get_service_data(dev);
-	slot = ctrl->slot;
+	struct controller *ctrl = get_service_data(dev);
 
-	/* Check if slot is occupied */
-	pciehp_get_adapter_status(slot, &status);
-	mutex_lock(&slot->lock);
-	if ((status && (slot->state == OFF_STATE ||
-			slot->state == BLINKINGON_STATE)) ||
-	    (!status && (slot->state == ON_STATE ||
-			 slot->state == BLINKINGOFF_STATE)))
-		pciehp_request(ctrl, PCI_EXP_SLTSTA_PDC);
-	mutex_unlock(&slot->lock);
+	pciehp_check_presence(ctrl);
 
 	return 0;
 }
diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
index 6f7de0819c88..5b15e76f3564 100644
--- a/drivers/pci/hotplug/pciehp_hpc.c
+++ b/drivers/pci/hotplug/pciehp_hpc.c
@@ -856,6 +856,7 @@ struct controller *pcie_init(struct pcie_device *dev)
 {
 	struct controller *ctrl;
 	u32 slot_cap, link_cap;
+	u8 occupied, poweron;
 	struct pci_dev *pdev = dev->port;
 
 	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
@@ -910,6 +911,19 @@ struct controller *pcie_init(struct pcie_device *dev)
 	if (pcie_init_slot(ctrl))
 		goto abort_ctrl;
 
+	/*
+	 * If empty slot's power status is on, turn power off.  The IRQ isn't
+	 * requested yet, so avoid triggering a notification with this command.
+	 */
+	if (POWER_CTRL(ctrl)) {
+		pciehp_get_adapter_status(ctrl->slot, &occupied);
+		pciehp_get_power_status(ctrl->slot, &poweron);
+		if (!occupied && poweron) {
+			pcie_disable_notification(ctrl);
+			pciehp_power_off_slot(ctrl->slot);
+		}
+	}
+
 	return ctrl;
 
 abort_ctrl:
-- 
cgit v1.2.3


From e6476c21447c4b17c47e476aade6facf050f31e8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 30 Jul 2018 09:45:07 +0200
Subject: net: remove bogus RCU annotations on socket.wq

We never use RCU protection for it, just a lot of cargo-cult
rcu_deference_protects calls.

Note that we do keep the kfree_rcu call for it, as the references through
struct sock are RCU protected and thus might require a grace period before
freeing.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Acked-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/net.h |  2 +-
 include/net/sock.h  |  2 +-
 net/socket.c        | 10 ++++------
 3 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/include/linux/net.h b/include/linux/net.h
index 6554d3ba4396..e0930678c8bf 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -114,7 +114,7 @@ struct socket {
 
 	unsigned long		flags;
 
-	struct socket_wq __rcu	*wq;
+	struct socket_wq	*wq;
 
 	struct file		*file;
 	struct sock		*sk;
diff --git a/include/net/sock.h b/include/net/sock.h
index 2afea5d1bdfe..433f45fc2d68 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1788,7 +1788,7 @@ static inline void sock_graft(struct sock *sk, struct socket *parent)
 {
 	WARN_ON(parent->sk);
 	write_lock_bh(&sk->sk_callback_lock);
-	sk->sk_wq = parent->wq;
+	rcu_assign_pointer(sk->sk_wq, parent->wq);
 	parent->sk = sk;
 	sk_set_socket(sk, parent);
 	sk->sk_uid = SOCK_INODE(parent)->i_uid;
diff --git a/net/socket.c b/net/socket.c
index 5b7df6695f4f..475247e347ae 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -251,7 +251,7 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 	init_waitqueue_head(&wq->wait);
 	wq->fasync_list = NULL;
 	wq->flags = 0;
-	RCU_INIT_POINTER(ei->socket.wq, wq);
+	ei->socket.wq = wq;
 
 	ei->socket.state = SS_UNCONNECTED;
 	ei->socket.flags = 0;
@@ -265,11 +265,9 @@ static struct inode *sock_alloc_inode(struct super_block *sb)
 static void sock_destroy_inode(struct inode *inode)
 {
 	struct socket_alloc *ei;
-	struct socket_wq *wq;
 
 	ei = container_of(inode, struct socket_alloc, vfs_inode);
-	wq = rcu_dereference_protected(ei->socket.wq, 1);
-	kfree_rcu(wq, rcu);
+	kfree_rcu(ei->socket.wq, rcu);
 	kmem_cache_free(sock_inode_cachep, ei);
 }
 
@@ -603,7 +601,7 @@ static void __sock_release(struct socket *sock, struct inode *inode)
 		module_put(owner);
 	}
 
-	if (rcu_dereference_protected(sock->wq, 1)->fasync_list)
+	if (sock->wq->fasync_list)
 		pr_err("%s: fasync list not empty!\n", __func__);
 
 	if (!sock->file) {
@@ -1181,7 +1179,7 @@ static int sock_fasync(int fd, struct file *filp, int on)
 		return -EINVAL;
 
 	lock_sock(sk);
-	wq = rcu_dereference_protected(sock->wq, lockdep_sock_is_held(sk));
+	wq = sock->wq;
 	fasync_helper(fd, filp, on, &wq->fasync_list);
 
 	if (!wq->fasync_list)
-- 
cgit v1.2.3


From fbeb1603bf4e9baa82da8f794de42949d0fe5e25 Mon Sep 17 00:00:00 2001
From: Arthur Fabre <afabre@cloudflare.com>
Date: Tue, 31 Jul 2018 18:17:22 +0100
Subject: bpf: verifier: MOV64 don't mark dst reg unbounded

When check_alu_op() handles a BPF_MOV64 between two registers,
it calls check_reg_arg(DST_OP) on the dst register, marking it
as unbounded. If the src and dst register are the same, this
marks the src as unbounded, which can lead to unexpected errors
for further checks that rely on bounds info. For example:

	BPF_MOV64_IMM(BPF_REG_2, 0),
	BPF_MOV64_REG(BPF_REG_2, BPF_REG_2),
	BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
	BPF_MOV64_IMM(BPF_REG_0, 0),
	BPF_EXIT_INSN(),

Results in:

	"math between ctx pointer and register with unbounded
	min value is not allowed"

check_alu_op() now uses check_reg_arg(DST_OP_NO_MARK), and MOVs
that need to mark the dst register (MOVIMM, MOV32) do so.

Added a test case for MOV64 dst == src, and dst != src.

Signed-off-by: Arthur Fabre <afabre@cloudflare.com>
Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/verifier.c                       |  6 ++++--
 tools/testing/selftests/bpf/test_verifier.c | 26 ++++++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 25e47c195874..e948303a0ea8 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -3238,8 +3238,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			}
 		}
 
-		/* check dest operand */
-		err = check_reg_arg(env, insn->dst_reg, DST_OP);
+		/* check dest operand, mark as required later */
+		err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
 		if (err)
 			return err;
 
@@ -3265,6 +3265,8 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 			/* case: R = imm
 			 * remember the value we stored into this reg
 			 */
+			/* clear any state __mark_reg_known doesn't set */
+			mark_reg_unknown(env, regs, insn->dst_reg);
 			regs[insn->dst_reg].type = SCALAR_VALUE;
 			if (BPF_CLASS(insn->code) == BPF_ALU64) {
 				__mark_reg_known(regs + insn->dst_reg,
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index f5f7bcc96046..c582afba9d1f 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -12332,6 +12332,32 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.errstr = "variable ctx access var_off=(0x0; 0x4)",
 	},
+	{
+		"mov64 src == dst",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_2),
+			// Check bounds are OK
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
+	{
+		"mov64 src != dst",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_3, 0),
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_3),
+			// Check bounds are OK
+			BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_2),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+		.result = ACCEPT,
+	},
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
-- 
cgit v1.2.3


From 86d969b425d7ecf774799b70142b957dc267575b Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Mon, 30 Jul 2018 11:18:13 -0700
Subject: xfs: refactor the xrep_extent_list into xfs_bitmap

As mentioned previously, the xrep_extent_list basically implements a
bitmap with two functions: set and disjoint union.  Rename all these
functions to xfs_bitmap to shorten the name and make it more obvious
what we're doing.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/bitmap.c | 183 +++++++++++++++++++++++++-------------------------
 fs/xfs/scrub/bitmap.h |  35 +++++-----
 fs/xfs/scrub/repair.c |  85 +++++++++++------------
 fs/xfs/scrub/repair.h |   8 +--
 fs/xfs/scrub/trace.h  |   1 -
 5 files changed, 149 insertions(+), 163 deletions(-)

diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index a7c2f4773f98..c770e2d0b6aa 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -16,183 +16,186 @@
 #include "scrub/repair.h"
 #include "scrub/bitmap.h"
 
-/* Collect a dead btree extent for later disposal. */
+/*
+ * Set a range of this bitmap.  Caller must ensure the range is not set.
+ *
+ * This is the logical equivalent of bitmap |= mask(start, len).
+ */
 int
-xrep_collect_btree_extent(
-	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist,
-	xfs_fsblock_t		fsbno,
-	xfs_extlen_t		len)
+xfs_bitmap_set(
+	struct xfs_bitmap	*bitmap,
+	uint64_t		start,
+	uint64_t		len)
 {
-	struct xrep_extent	*rex;
+	struct xfs_bitmap_range	*bmr;
 
-	trace_xrep_collect_btree_extent(sc->mp,
-			XFS_FSB_TO_AGNO(sc->mp, fsbno),
-			XFS_FSB_TO_AGBNO(sc->mp, fsbno), len);
-
-	rex = kmem_alloc(sizeof(struct xrep_extent), KM_MAYFAIL);
-	if (!rex)
+	bmr = kmem_alloc(sizeof(struct xfs_bitmap_range), KM_MAYFAIL);
+	if (!bmr)
 		return -ENOMEM;
 
-	INIT_LIST_HEAD(&rex->list);
-	rex->fsbno = fsbno;
-	rex->len = len;
-	list_add_tail(&rex->list, &exlist->list);
+	INIT_LIST_HEAD(&bmr->list);
+	bmr->start = start;
+	bmr->len = len;
+	list_add_tail(&bmr->list, &bitmap->list);
 
 	return 0;
 }
 
-/*
- * An error happened during the rebuild so the transaction will be cancelled.
- * The fs will shut down, and the administrator has to unmount and run repair.
- * Therefore, free all the memory associated with the list so we can die.
- */
+/* Free everything related to this bitmap. */
 void
-xrep_cancel_btree_extents(
-	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist)
+xfs_bitmap_destroy(
+	struct xfs_bitmap	*bitmap)
 {
-	struct xrep_extent	*rex;
-	struct xrep_extent	*n;
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
 
-	for_each_xrep_extent_safe(rex, n, exlist) {
-		list_del(&rex->list);
-		kmem_free(rex);
+	for_each_xfs_bitmap_extent(bmr, n, bitmap) {
+		list_del(&bmr->list);
+		kmem_free(bmr);
 	}
 }
 
+/* Set up a per-AG block bitmap. */
+void
+xfs_bitmap_init(
+	struct xfs_bitmap	*bitmap)
+{
+	INIT_LIST_HEAD(&bitmap->list);
+}
+
 /* Compare two btree extents. */
 static int
-xrep_btree_extent_cmp(
+xfs_bitmap_range_cmp(
 	void			*priv,
 	struct list_head	*a,
 	struct list_head	*b)
 {
-	struct xrep_extent	*ap;
-	struct xrep_extent	*bp;
+	struct xfs_bitmap_range	*ap;
+	struct xfs_bitmap_range	*bp;
 
-	ap = container_of(a, struct xrep_extent, list);
-	bp = container_of(b, struct xrep_extent, list);
+	ap = container_of(a, struct xfs_bitmap_range, list);
+	bp = container_of(b, struct xfs_bitmap_range, list);
 
-	if (ap->fsbno > bp->fsbno)
+	if (ap->start > bp->start)
 		return 1;
-	if (ap->fsbno < bp->fsbno)
+	if (ap->start < bp->start)
 		return -1;
 	return 0;
 }
 
 /*
- * Remove all the blocks mentioned in @sublist from the extents in @exlist.
+ * Remove all the blocks mentioned in @sub from the extents in @bitmap.
  *
  * The intent is that callers will iterate the rmapbt for all of its records
- * for a given owner to generate @exlist; and iterate all the blocks of the
+ * for a given owner to generate @bitmap; and iterate all the blocks of the
  * metadata structures that are not being rebuilt and have the same rmapbt
- * owner to generate @sublist.  This routine subtracts all the extents
- * mentioned in sublist from all the extents linked in @exlist, which leaves
- * @exlist as the list of blocks that are not accounted for, which we assume
+ * owner to generate @sub.  This routine subtracts all the extents
+ * mentioned in sub from all the extents linked in @bitmap, which leaves
+ * @bitmap as the list of blocks that are not accounted for, which we assume
  * are the dead blocks of the old metadata structure.  The blocks mentioned in
- * @exlist can be reaped.
+ * @bitmap can be reaped.
+ *
+ * This is the logical equivalent of bitmap &= ~sub.
  */
 #define LEFT_ALIGNED	(1 << 0)
 #define RIGHT_ALIGNED	(1 << 1)
 int
-xrep_subtract_extents(
-	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist,
-	struct xrep_extent_list	*sublist)
+xfs_bitmap_disunion(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_bitmap	*sub)
 {
 	struct list_head	*lp;
-	struct xrep_extent	*ex;
-	struct xrep_extent	*newex;
-	struct xrep_extent	*subex;
-	xfs_fsblock_t		sub_fsb;
-	xfs_extlen_t		sub_len;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*new_br;
+	struct xfs_bitmap_range	*sub_br;
+	uint64_t		sub_start;
+	uint64_t		sub_len;
 	int			state;
 	int			error = 0;
 
-	if (list_empty(&exlist->list) || list_empty(&sublist->list))
+	if (list_empty(&bitmap->list) || list_empty(&sub->list))
 		return 0;
-	ASSERT(!list_empty(&sublist->list));
+	ASSERT(!list_empty(&sub->list));
 
-	list_sort(NULL, &exlist->list, xrep_btree_extent_cmp);
-	list_sort(NULL, &sublist->list, xrep_btree_extent_cmp);
+	list_sort(NULL, &bitmap->list, xfs_bitmap_range_cmp);
+	list_sort(NULL, &sub->list, xfs_bitmap_range_cmp);
 
 	/*
-	 * Now that we've sorted both lists, we iterate exlist once, rolling
-	 * forward through sublist and/or exlist as necessary until we find an
+	 * Now that we've sorted both lists, we iterate bitmap once, rolling
+	 * forward through sub and/or bitmap as necessary until we find an
 	 * overlap or reach the end of either list.  We do not reset lp to the
-	 * head of exlist nor do we reset subex to the head of sublist.  The
+	 * head of bitmap nor do we reset sub_br to the head of sub.  The
 	 * list traversal is similar to merge sort, but we're deleting
 	 * instead.  In this manner we avoid O(n^2) operations.
 	 */
-	subex = list_first_entry(&sublist->list, struct xrep_extent,
+	sub_br = list_first_entry(&sub->list, struct xfs_bitmap_range,
 			list);
-	lp = exlist->list.next;
-	while (lp != &exlist->list) {
-		ex = list_entry(lp, struct xrep_extent, list);
+	lp = bitmap->list.next;
+	while (lp != &bitmap->list) {
+		br = list_entry(lp, struct xfs_bitmap_range, list);
 
 		/*
-		 * Advance subex and/or ex until we find a pair that
+		 * Advance sub_br and/or br until we find a pair that
 		 * intersect or we run out of extents.
 		 */
-		while (subex->fsbno + subex->len <= ex->fsbno) {
-			if (list_is_last(&subex->list, &sublist->list))
+		while (sub_br->start + sub_br->len <= br->start) {
+			if (list_is_last(&sub_br->list, &sub->list))
 				goto out;
-			subex = list_next_entry(subex, list);
+			sub_br = list_next_entry(sub_br, list);
 		}
-		if (subex->fsbno >= ex->fsbno + ex->len) {
+		if (sub_br->start >= br->start + br->len) {
 			lp = lp->next;
 			continue;
 		}
 
-		/* trim subex to fit the extent we have */
-		sub_fsb = subex->fsbno;
-		sub_len = subex->len;
-		if (subex->fsbno < ex->fsbno) {
-			sub_len -= ex->fsbno - subex->fsbno;
-			sub_fsb = ex->fsbno;
+		/* trim sub_br to fit the extent we have */
+		sub_start = sub_br->start;
+		sub_len = sub_br->len;
+		if (sub_br->start < br->start) {
+			sub_len -= br->start - sub_br->start;
+			sub_start = br->start;
 		}
-		if (sub_len > ex->len)
-			sub_len = ex->len;
+		if (sub_len > br->len)
+			sub_len = br->len;
 
 		state = 0;
-		if (sub_fsb == ex->fsbno)
+		if (sub_start == br->start)
 			state |= LEFT_ALIGNED;
-		if (sub_fsb + sub_len == ex->fsbno + ex->len)
+		if (sub_start + sub_len == br->start + br->len)
 			state |= RIGHT_ALIGNED;
 		switch (state) {
 		case LEFT_ALIGNED:
 			/* Coincides with only the left. */
-			ex->fsbno += sub_len;
-			ex->len -= sub_len;
+			br->start += sub_len;
+			br->len -= sub_len;
 			break;
 		case RIGHT_ALIGNED:
 			/* Coincides with only the right. */
-			ex->len -= sub_len;
+			br->len -= sub_len;
 			lp = lp->next;
 			break;
 		case LEFT_ALIGNED | RIGHT_ALIGNED:
 			/* Total overlap, just delete ex. */
 			lp = lp->next;
-			list_del(&ex->list);
-			kmem_free(ex);
+			list_del(&br->list);
+			kmem_free(br);
 			break;
 		case 0:
 			/*
 			 * Deleting from the middle: add the new right extent
 			 * and then shrink the left extent.
 			 */
-			newex = kmem_alloc(sizeof(struct xrep_extent),
+			new_br = kmem_alloc(sizeof(struct xfs_bitmap_range),
 					KM_MAYFAIL);
-			if (!newex) {
+			if (!new_br) {
 				error = -ENOMEM;
 				goto out;
 			}
-			INIT_LIST_HEAD(&newex->list);
-			newex->fsbno = sub_fsb + sub_len;
-			newex->len = ex->fsbno + ex->len - newex->fsbno;
-			list_add(&newex->list, &ex->list);
-			ex->len = sub_fsb - ex->fsbno;
+			INIT_LIST_HEAD(&new_br->list);
+			new_br->start = sub_start + sub_len;
+			new_br->len = br->start + br->len - new_br->start;
+			list_add(&new_br->list, &br->list);
+			br->len = sub_start - br->start;
 			lp = lp->next;
 			break;
 		default:
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
index 1038157695a8..dad652ee9177 100644
--- a/fs/xfs/scrub/bitmap.h
+++ b/fs/xfs/scrub/bitmap.h
@@ -6,32 +6,27 @@
 #ifndef __XFS_SCRUB_BITMAP_H__
 #define __XFS_SCRUB_BITMAP_H__
 
-struct xrep_extent {
+struct xfs_bitmap_range {
 	struct list_head	list;
-	xfs_fsblock_t		fsbno;
-	xfs_extlen_t		len;
+	uint64_t		start;
+	uint64_t		len;
 };
 
-struct xrep_extent_list {
+struct xfs_bitmap {
 	struct list_head	list;
 };
 
-static inline void
-xrep_init_extent_list(
-	struct xrep_extent_list		*exlist)
-{
-	INIT_LIST_HEAD(&exlist->list);
-}
+void xfs_bitmap_init(struct xfs_bitmap *bitmap);
+void xfs_bitmap_destroy(struct xfs_bitmap *bitmap);
 
-#define for_each_xrep_extent_safe(rbe, n, exlist) \
-	list_for_each_entry_safe((rbe), (n), &(exlist)->list, list)
-int xrep_collect_btree_extent(struct xfs_scrub *sc,
-		struct xrep_extent_list *btlist, xfs_fsblock_t fsbno,
-		xfs_extlen_t len);
-void xrep_cancel_btree_extents(struct xfs_scrub *sc,
-		struct xrep_extent_list *btlist);
-int xrep_subtract_extents(struct xfs_scrub *sc,
-		struct xrep_extent_list *exlist,
-		struct xrep_extent_list *sublist);
+#define for_each_xfs_bitmap_extent(bex, n, bitmap) \
+	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list)
+
+#define for_each_xfs_bitmap_block(b, bex, n, bitmap) \
+	list_for_each_entry_safe((bex), (n), &(bitmap)->list, list) \
+		for ((b) = bex->start; (b) < bex->start + bex->len; (b)++)
+
+int xfs_bitmap_set(struct xfs_bitmap *bitmap, uint64_t start, uint64_t len);
+int xfs_bitmap_disunion(struct xfs_bitmap *bitmap, struct xfs_bitmap *sub);
 
 #endif	/* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 27a904ef6189..85b048b341a0 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -368,17 +368,17 @@ xrep_init_btblock(
  *
  * However, that leaves the matter of removing all the metadata describing the
  * old broken structure.  For primary metadata we use the rmap data to collect
- * every extent with a matching rmap owner (exlist); we then iterate all other
+ * every extent with a matching rmap owner (bitmap); we then iterate all other
  * metadata structures with the same rmap owner to collect the extents that
- * cannot be removed (sublist).  We then subtract sublist from exlist to
+ * cannot be removed (sublist).  We then subtract sublist from bitmap to
  * derive the blocks that were used by the old btree.  These blocks can be
  * reaped.
  *
  * For rmapbt reconstructions we must use different tactics for extent
  * collection.  First we iterate all primary metadata (this excludes the old
  * rmapbt, obviously) to generate new rmap records.  The gaps in the rmap
- * records are collected as exlist.  The bnobt records are collected as
- * sublist.  As with the other btrees we subtract sublist from exlist, and the
+ * records are collected as bitmap.  The bnobt records are collected as
+ * sublist.  As with the other btrees we subtract sublist from bitmap, and the
  * result (since the rmapbt lives in the free space) are the blocks from the
  * old rmapbt.
  *
@@ -386,11 +386,11 @@ xrep_init_btblock(
  *
  * Now that we've constructed a new btree to replace the damaged one, we want
  * to dispose of the blocks that (we think) the old btree was using.
- * Previously, we used the rmapbt to collect the extents (exlist) with the
+ * Previously, we used the rmapbt to collect the extents (bitmap) with the
  * rmap owner corresponding to the tree we rebuilt, collected extents for any
  * blocks with the same rmap owner that are owned by another data structure
- * (sublist), and subtracted sublist from exlist.  In theory the extents
- * remaining in exlist are the old btree's blocks.
+ * (sublist), and subtracted sublist from bitmap.  In theory the extents
+ * remaining in bitmap are the old btree's blocks.
  *
  * Unfortunately, it's possible that the btree was crosslinked with other
  * blocks on disk.  The rmap data can tell us if there are multiple owners, so
@@ -406,7 +406,7 @@ xrep_init_btblock(
  * If there are no rmap records at all, we also free the block.  If the btree
  * being rebuilt lives in the free space (bnobt/cntbt/rmapbt) then there isn't
  * supposed to be a rmap record and everything is ok.  For other btrees there
- * had to have been an rmap entry for the block to have ended up on @exlist,
+ * had to have been an rmap entry for the block to have ended up on @bitmap,
  * so if it's gone now there's something wrong and the fs will shut down.
  *
  * Note: If there are multiple rmap records with only the same rmap owner as
@@ -419,7 +419,7 @@ xrep_init_btblock(
  * The caller is responsible for locking the AG headers for the entire rebuild
  * operation so that nothing else can sneak in and change the AG state while
  * we're not looking.  We also assume that the caller already invalidated any
- * buffers associated with @exlist.
+ * buffers associated with @bitmap.
  */
 
 /*
@@ -429,13 +429,12 @@ xrep_init_btblock(
 int
 xrep_invalidate_blocks(
 	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist)
+	struct xfs_bitmap	*bitmap)
 {
-	struct xrep_extent	*rex;
-	struct xrep_extent	*n;
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
 	struct xfs_buf		*bp;
 	xfs_fsblock_t		fsbno;
-	xfs_agblock_t		i;
 
 	/*
 	 * For each block in each extent, see if there's an incore buffer for
@@ -445,18 +444,16 @@ xrep_invalidate_blocks(
 	 * because we never own those; and if we can't TRYLOCK the buffer we
 	 * assume it's owned by someone else.
 	 */
-	for_each_xrep_extent_safe(rex, n, exlist) {
-		for (fsbno = rex->fsbno, i = rex->len; i > 0; fsbno++, i--) {
-			/* Skip AG headers and post-EOFS blocks */
-			if (!xfs_verify_fsbno(sc->mp, fsbno))
-				continue;
-			bp = xfs_buf_incore(sc->mp->m_ddev_targp,
-					XFS_FSB_TO_DADDR(sc->mp, fsbno),
-					XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
-			if (bp) {
-				xfs_trans_bjoin(sc->tp, bp);
-				xfs_trans_binval(sc->tp, bp);
-			}
+	for_each_xfs_bitmap_block(fsbno, bmr, n, bitmap) {
+		/* Skip AG headers and post-EOFS blocks */
+		if (!xfs_verify_fsbno(sc->mp, fsbno))
+			continue;
+		bp = xfs_buf_incore(sc->mp->m_ddev_targp,
+				XFS_FSB_TO_DADDR(sc->mp, fsbno),
+				XFS_FSB_TO_BB(sc->mp, 1), XBF_TRYLOCK);
+		if (bp) {
+			xfs_trans_bjoin(sc->tp, bp);
+			xfs_trans_binval(sc->tp, bp);
 		}
 	}
 
@@ -519,9 +516,9 @@ xrep_put_freelist(
 	return 0;
 }
 
-/* Dispose of a single metadata block. */
+/* Dispose of a single block. */
 STATIC int
-xrep_dispose_btree_block(
+xrep_reap_block(
 	struct xfs_scrub	*sc,
 	xfs_fsblock_t		fsbno,
 	struct xfs_owner_info	*oinfo,
@@ -593,41 +590,35 @@ out_free:
 	return error;
 }
 
-/* Dispose of btree blocks from an old per-AG btree. */
+/* Dispose of every block of every extent in the bitmap. */
 int
-xrep_reap_btree_extents(
+xrep_reap_extents(
 	struct xfs_scrub	*sc,
-	struct xrep_extent_list	*exlist,
+	struct xfs_bitmap	*bitmap,
 	struct xfs_owner_info	*oinfo,
 	enum xfs_ag_resv_type	type)
 {
-	struct xrep_extent	*rex;
-	struct xrep_extent	*n;
+	struct xfs_bitmap_range	*bmr;
+	struct xfs_bitmap_range	*n;
+	xfs_fsblock_t		fsbno;
 	int			error = 0;
 
 	ASSERT(xfs_sb_version_hasrmapbt(&sc->mp->m_sb));
 
-	/* Dispose of every block from the old btree. */
-	for_each_xrep_extent_safe(rex, n, exlist) {
+	for_each_xfs_bitmap_block(fsbno, bmr, n, bitmap) {
 		ASSERT(sc->ip != NULL ||
-		       XFS_FSB_TO_AGNO(sc->mp, rex->fsbno) == sc->sa.agno);
-
+		       XFS_FSB_TO_AGNO(sc->mp, fsbno) == sc->sa.agno);
 		trace_xrep_dispose_btree_extent(sc->mp,
-				XFS_FSB_TO_AGNO(sc->mp, rex->fsbno),
-				XFS_FSB_TO_AGBNO(sc->mp, rex->fsbno), rex->len);
+				XFS_FSB_TO_AGNO(sc->mp, fsbno),
+				XFS_FSB_TO_AGBNO(sc->mp, fsbno), 1);
 
-		for (; rex->len > 0; rex->len--, rex->fsbno++) {
-			error = xrep_dispose_btree_block(sc, rex->fsbno,
-					oinfo, type);
-			if (error)
-				goto out;
-		}
-		list_del(&rex->list);
-		kmem_free(rex);
+		error = xrep_reap_block(sc, fsbno, oinfo, type);
+		if (error)
+			goto out;
 	}
 
 out:
-	xrep_cancel_btree_extents(sc, exlist);
+	xfs_bitmap_destroy(bitmap);
 	return error;
 }
 
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index a3d491a438f4..5a4e92221916 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -27,13 +27,11 @@ int xrep_init_btblock(struct xfs_scrub *sc, xfs_fsblock_t fsb,
 		struct xfs_buf **bpp, xfs_btnum_t btnum,
 		const struct xfs_buf_ops *ops);
 
-struct xrep_extent_list;
+struct xfs_bitmap;
 
 int xrep_fix_freelist(struct xfs_scrub *sc, bool can_shrink);
-int xrep_invalidate_blocks(struct xfs_scrub *sc,
-		struct xrep_extent_list *btlist);
-int xrep_reap_btree_extents(struct xfs_scrub *sc,
-		struct xrep_extent_list *exlist,
+int xrep_invalidate_blocks(struct xfs_scrub *sc, struct xfs_bitmap *btlist);
+int xrep_reap_extents(struct xfs_scrub *sc, struct xfs_bitmap *exlist,
 		struct xfs_owner_info *oinfo, enum xfs_ag_resv_type type);
 
 struct xrep_find_ag_btree {
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 93db22c39b51..4e20f0e48232 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -511,7 +511,6 @@ DEFINE_EVENT(xrep_extent_class, name, \
 		 xfs_agblock_t agbno, xfs_extlen_t len), \
 	TP_ARGS(mp, agno, agbno, len))
 DEFINE_REPAIR_EXTENT_EVENT(xrep_dispose_btree_extent);
-DEFINE_REPAIR_EXTENT_EVENT(xrep_collect_btree_extent);
 DEFINE_REPAIR_EXTENT_EVENT(xrep_agfl_insert);
 
 DECLARE_EVENT_CLASS(xrep_rmap_class,
-- 
cgit v1.2.3


From eca383fcd63b452cf533505154135da2a1f70227 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Sun, 29 Jul 2018 13:10:44 -0700
Subject: xfs: refactor superblock verifiers

Split the superblock verifier into the common checks, the read-time
checks, and the write-time check functions.  No functional changes, but
we're setting up to add more write-only checks.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
---
 fs/xfs/libxfs/xfs_sb.c | 205 ++++++++++++++++++++++++++-----------------------
 1 file changed, 111 insertions(+), 94 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index b3ad15956366..f3835e923893 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -96,80 +96,94 @@ xfs_perag_put(
 	trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
 }
 
-/*
- * Check the validity of the SB found.
- */
+/* Check all the superblock fields we care about when reading one in. */
 STATIC int
-xfs_mount_validate_sb(
-	xfs_mount_t	*mp,
-	xfs_sb_t	*sbp,
-	bool		check_inprogress,
-	bool		check_version)
+xfs_validate_sb_read(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
 {
-	uint32_t	agcount = 0;
-	uint32_t	rem;
-
-	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
-		xfs_warn(mp, "bad magic number");
-		return -EWRONGFS;
-	}
-
-
-	if (!xfs_sb_good_version(sbp)) {
-		xfs_warn(mp, "bad version");
-		return -EWRONGFS;
-	}
+	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
+		return 0;
 
 	/*
-	 * Version 5 superblock feature mask validation. Reject combinations the
-	 * kernel cannot support up front before checking anything else. For
-	 * write validation, we don't need to check feature masks.
+	 * Version 5 superblock feature mask validation. Reject combinations
+	 * the kernel cannot support up front before checking anything else.
 	 */
-	if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
-		if (xfs_sb_has_compat_feature(sbp,
-					XFS_SB_FEAT_COMPAT_UNKNOWN)) {
-			xfs_warn(mp,
+	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
+		xfs_warn(mp,
 "Superblock has unknown compatible features (0x%x) enabled.",
-				(sbp->sb_features_compat &
-						XFS_SB_FEAT_COMPAT_UNKNOWN));
-			xfs_warn(mp,
+			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
+		xfs_warn(mp,
 "Using a more recent kernel is recommended.");
-		}
+	}
 
-		if (xfs_sb_has_ro_compat_feature(sbp,
-					XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
-			xfs_alert(mp,
+	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+		xfs_alert(mp,
 "Superblock has unknown read-only compatible features (0x%x) enabled.",
-				(sbp->sb_features_ro_compat &
-						XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
-			if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
-				xfs_warn(mp,
+			(sbp->sb_features_ro_compat &
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+		if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
+			xfs_warn(mp,
 "Attempted to mount read-only compatible filesystem read-write.");
-				xfs_warn(mp,
+			xfs_warn(mp,
 "Filesystem can only be safely mounted read only.");
 
-				return -EINVAL;
-			}
-		}
-		if (xfs_sb_has_incompat_feature(sbp,
-					XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
-			xfs_warn(mp,
-"Superblock has unknown incompatible features (0x%x) enabled.",
-				(sbp->sb_features_incompat &
-						XFS_SB_FEAT_INCOMPAT_UNKNOWN));
-			xfs_warn(mp,
-"Filesystem can not be safely mounted by this kernel.");
 			return -EINVAL;
 		}
-	} else if (xfs_sb_version_hascrc(sbp)) {
-		/*
-		 * We can't read verify the sb LSN because the read verifier is
-		 * called before the log is allocated and processed. We know the
-		 * log is set up before write verifier (!check_version) calls,
-		 * so just check it here.
-		 */
-		if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
-			return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Superblock has unknown incompatible features (0x%x) enabled.",
+			(sbp->sb_features_incompat &
+					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
+		xfs_warn(mp,
+"Filesystem cannot be safely mounted by this kernel.");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/* Check all the superblock fields we care about when writing one out. */
+STATIC int
+xfs_validate_sb_write(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
+{
+	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
+		return 0;
+
+	/* XXX: For write validation, we don't need to check feature masks?? */
+
+	/*
+	 * We can't read verify the sb LSN because the read verifier is called
+	 * before the log is allocated and processed. We know the log is set up
+	 * before write verifier calls, so check it here.
+	 */
+	if (!xfs_log_check_lsn(mp, sbp->sb_lsn))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/* Check the validity of the SB. */
+STATIC int
+xfs_validate_sb_common(
+	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
+	struct xfs_sb		*sbp)
+{
+	uint32_t		agcount = 0;
+	uint32_t		rem;
+
+	if (sbp->sb_magicnum != XFS_SB_MAGIC) {
+		xfs_warn(mp, "bad magic number");
+		return -EWRONGFS;
+	}
+
+	if (!xfs_sb_good_version(sbp)) {
+		xfs_warn(mp, "bad version");
+		return -EWRONGFS;
 	}
 
 	if (xfs_sb_version_has_pquotino(sbp)) {
@@ -321,7 +335,12 @@ xfs_mount_validate_sb(
 		return -EFBIG;
 	}
 
-	if (check_inprogress && sbp->sb_inprogress) {
+	/*
+	 * Don't touch the filesystem if a user tool thinks it owns the primary
+	 * superblock.  mkfs doesn't clear the flag from secondary supers, so
+	 * we don't check them at all.
+	 */
+	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && sbp->sb_inprogress) {
 		xfs_warn(mp, "Offline file system operation in progress!");
 		return -EFSCORRUPTED;
 	}
@@ -596,29 +615,6 @@ xfs_sb_to_disk(
 	}
 }
 
-static int
-xfs_sb_verify(
-	struct xfs_buf	*bp,
-	bool		check_version)
-{
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_sb	sb;
-
-	/*
-	 * Use call variant which doesn't convert quota flags from disk 
-	 * format, because xfs_mount_validate_sb checks the on-disk flags.
-	 */
-	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
-
-	/*
-	 * Only check the in progress field for the primary superblock as
-	 * mkfs.xfs doesn't clear it from secondary superblocks.
-	 */
-	return xfs_mount_validate_sb(mp, &sb,
-				     bp->b_maps[0].bm_bn == XFS_SB_DADDR,
-				     check_version);
-}
-
 /*
  * If the superblock has the CRC feature bit set or the CRC field is non-null,
  * check that the CRC is valid.  We check the CRC field is non-null because a
@@ -633,11 +629,12 @@ xfs_sb_verify(
  */
 static void
 xfs_sb_read_verify(
-	struct xfs_buf	*bp)
+	struct xfs_buf		*bp)
 {
-	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_dsb	*dsb = XFS_BUF_TO_SBP(bp);
-	int		error;
+	struct xfs_sb		sb;
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_dsb		*dsb = XFS_BUF_TO_SBP(bp);
+	int			error;
 
 	/*
 	 * open code the version check to avoid needing to convert the entire
@@ -657,7 +654,16 @@ xfs_sb_read_verify(
 			}
 		}
 	}
-	error = xfs_sb_verify(bp, true);
+
+	/*
+	 * Check all the superblock fields.  Don't byteswap the xquota flags
+	 * because _verify_common checks the on-disk values.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
+	error = xfs_validate_sb_common(mp, bp, &sb);
+	if (error)
+		goto out_error;
+	error = xfs_validate_sb_read(mp, &sb);
 
 out_error:
 	if (error == -EFSCORRUPTED || error == -EFSBADCRC)
@@ -691,15 +697,22 @@ static void
 xfs_sb_write_verify(
 	struct xfs_buf		*bp)
 {
+	struct xfs_sb		sb;
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_buf_log_item	*bip = bp->b_log_item;
 	int			error;
 
-	error = xfs_sb_verify(bp, false);
-	if (error) {
-		xfs_verifier_error(bp, error, __this_address);
-		return;
-	}
+	/*
+	 * Check all the superblock fields.  Don't byteswap the xquota flags
+	 * because _verify_common checks the on-disk values.
+	 */
+	__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
+	error = xfs_validate_sb_common(mp, bp, &sb);
+	if (error)
+		goto out_error;
+	error = xfs_validate_sb_write(mp, &sb);
+	if (error)
+		goto out_error;
 
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
 		return;
@@ -708,6 +721,10 @@ xfs_sb_write_verify(
 		XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
 
 	xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF);
+	return;
+
+out_error:
+	xfs_verifier_error(bp, error, __this_address);
 }
 
 const struct xfs_buf_ops xfs_sb_buf_ops = {
-- 
cgit v1.2.3


From 8756a5af18191a471e670cc577aea60b652fea4c Mon Sep 17 00:00:00 2001
From: Bill O'Donnell <billodo@redhat.com>
Date: Thu, 26 Jul 2018 10:10:34 -0700
Subject: libxfs: add more bounds checking to sb sanity checks

Current sb verifier doesn't check bounds on sb_fdblocks and sb_ifree.
Add sanity checks for these parameters.

Signed-off-by: Bill O'Donnell <billodo@redhat.com>
[darrick: port to refactored sb validation predicates]
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
---
 fs/xfs/libxfs/xfs_sb.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index f3835e923893..3d29f4a5242f 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -150,6 +150,18 @@ xfs_validate_sb_write(
 	struct xfs_mount	*mp,
 	struct xfs_sb		*sbp)
 {
+	/*
+	 * Carry out additional sb summary counter sanity checks when we write
+	 * the superblock.  We skip this in the read validator because there
+	 * could be newer superblocks in the log and if the values are garbage
+	 * we'll recalculate them at the end of log mount.
+	 */
+	if (sbp->sb_fdblocks > sbp->sb_dblocks ||
+	    sbp->sb_ifree > sbp->sb_icount) {
+		xfs_warn(mp, "SB summary counter sanity check failed");
+		return -EFSCORRUPTED;
+	}
+
 	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
 		return 0;
 
-- 
cgit v1.2.3


From 69775fd15dc78e0547af45fb3e375d5423cb21b1 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 26 Jul 2018 10:10:42 -0700
Subject: xfs: verify icount in superblock write

Add a helper predicate to check the inode count for sanity, then use it
in the superblock write verifier to inspect sb_icount.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
---
 fs/xfs/libxfs/xfs_sb.c    |  3 ++-
 fs/xfs/libxfs/xfs_types.c | 34 ++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_types.h |  1 +
 3 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 3d29f4a5242f..05e7ed1b8022 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -154,9 +154,10 @@ xfs_validate_sb_write(
 	 * Carry out additional sb summary counter sanity checks when we write
 	 * the superblock.  We skip this in the read validator because there
 	 * could be newer superblocks in the log and if the values are garbage
-	 * we'll recalculate them at the end of log mount.
+	 * even after replay we'll recalculate them at the end of log mount.
 	 */
 	if (sbp->sb_fdblocks > sbp->sb_dblocks ||
+	    !xfs_verify_icount(mp, sbp->sb_icount) ||
 	    sbp->sb_ifree > sbp->sb_icount) {
 		xfs_warn(mp, "SB summary counter sanity check failed");
 		return -EFSCORRUPTED;
diff --git a/fs/xfs/libxfs/xfs_types.c b/fs/xfs/libxfs/xfs_types.c
index 2e2a243cef2e..33a5ca346baf 100644
--- a/fs/xfs/libxfs/xfs_types.c
+++ b/fs/xfs/libxfs/xfs_types.c
@@ -171,3 +171,37 @@ xfs_verify_rtbno(
 {
 	return rtbno < mp->m_sb.sb_rblocks;
 }
+
+/* Calculate the range of valid icount values. */
+static void
+xfs_icount_range(
+	struct xfs_mount	*mp,
+	unsigned long long	*min,
+	unsigned long long	*max)
+{
+	unsigned long long	nr_inos = 0;
+	xfs_agnumber_t		agno;
+
+	/* root, rtbitmap, rtsum all live in the first chunk */
+	*min = XFS_INODES_PER_CHUNK;
+
+	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+		xfs_agino_t	first, last;
+
+		xfs_agino_range(mp, agno, &first, &last);
+		nr_inos += last - first + 1;
+	}
+	*max = nr_inos;
+}
+
+/* Sanity-checking of inode counts. */
+bool
+xfs_verify_icount(
+	struct xfs_mount	*mp,
+	unsigned long long	icount)
+{
+	unsigned long long	min, max;
+
+	xfs_icount_range(mp, &min, &max);
+	return icount >= min && icount <= max;
+}
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 4055d62f690c..b9e6c89284c3 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -165,5 +165,6 @@ bool xfs_verify_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_dir_ino(struct xfs_mount *mp, xfs_ino_t ino);
 bool xfs_verify_rtbno(struct xfs_mount *mp, xfs_rtblock_t rtbno);
+bool xfs_verify_icount(struct xfs_mount *mp, unsigned long long icount);
 
 #endif	/* __XFS_TYPES_H__ */
-- 
cgit v1.2.3


From 9e037cb7972fab5a9f55bca4ebe6e4dbf7e160bc Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Mon, 30 Jul 2018 16:45:35 -0700
Subject: xfs: check for unknown v5 feature bits in superblock write verifier

Make sure we never try to write the superblock with unknown feature bits
set.  We checked those at mount time, so if they're set now then memory
is corrupt.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
---
 fs/xfs/libxfs/xfs_sb.c | 35 ++++++++++++++++++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 05e7ed1b8022..ca1b3a7a9171 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -166,7 +166,40 @@ xfs_validate_sb_write(
 	if (XFS_SB_VERSION_NUM(sbp) != XFS_SB_VERSION_5)
 		return 0;
 
-	/* XXX: For write validation, we don't need to check feature masks?? */
+	/*
+	 * Version 5 superblock feature mask validation. Reject combinations
+	 * the kernel cannot support since we checked for unsupported bits in
+	 * the read verifier, which means that memory is corrupt.
+	 */
+	if (xfs_sb_has_compat_feature(sbp, XFS_SB_FEAT_COMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock compatible features (0x%x)!",
+			(sbp->sb_features_compat & XFS_SB_FEAT_COMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+
+	if (xfs_sb_has_ro_compat_feature(sbp, XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
+		xfs_alert(mp,
+"Corruption detected in superblock read-only compatible features (0x%x)!",
+			(sbp->sb_features_ro_compat &
+					XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_feature(sbp, XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock incompatible features (0x%x)!",
+			(sbp->sb_features_incompat &
+					XFS_SB_FEAT_INCOMPAT_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
+	if (xfs_sb_has_incompat_log_feature(sbp,
+			XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN)) {
+		xfs_warn(mp,
+"Corruption detected in superblock incompatible log features (0x%x)!",
+			(sbp->sb_features_log_incompat &
+					XFS_SB_FEAT_INCOMPAT_LOG_UNKNOWN));
+		return -EFSCORRUPTED;
+	}
 
 	/*
 	 * We can't read verify the sb LSN because the read verifier is called
-- 
cgit v1.2.3


From 745b3f76d1c889d738a1c4537a3c491bc1ecac4d Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Jul 2018 16:51:51 -0700
Subject: xfs: maintain a sequence count for inode fork manipulations

Add a simple 32-bit unsigned integer as the sequence count for
modifications to the extent list in the inode fork.  This will be
used to optimize away extent list lookups in the writeback code.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_iext_tree.c  | 6 ++++++
 fs/xfs/libxfs/xfs_inode_fork.h | 1 +
 2 files changed, 7 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index b80c63faace2..8a7aea041ee1 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -624,6 +624,8 @@ xfs_iext_insert(
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
 
+	ifp->if_seq++;
+
 	if (ifp->if_height == 0)
 		xfs_iext_alloc_root(ifp, cur);
 	else if (ifp->if_height == 1)
@@ -864,6 +866,8 @@ xfs_iext_remove(
 	ASSERT(ifp->if_u1.if_root != NULL);
 	ASSERT(xfs_iext_valid(ifp, cur));
 
+	ifp->if_seq++;
+
 	nr_entries = xfs_iext_leaf_nr_entries(ifp, leaf, cur->pos) - 1;
 	for (i = cur->pos; i < nr_entries; i++)
 		leaf->recs[i] = leaf->recs[i + 1];
@@ -970,6 +974,8 @@ xfs_iext_update_extent(
 {
 	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
 
+	ifp->if_seq++;
+
 	if (cur->pos == 0) {
 		struct xfs_bmbt_irec	old;
 
diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h
index 1492143371f3..60361d2d74a1 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.h
+++ b/fs/xfs/libxfs/xfs_inode_fork.h
@@ -14,6 +14,7 @@ struct xfs_dinode;
  */
 struct xfs_ifork {
 	int			if_bytes;	/* bytes in if_u1 */
+	unsigned int		if_seq;		/* cow fork mod counter */
 	struct xfs_btree_block	*if_broot;	/* file's incore btree root */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	unsigned char		if_flags;	/* per-fork flags */
-- 
cgit v1.2.3


From e666aa37f4330cb93a5004a89b7a938312e74e36 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Jul 2018 16:51:52 -0700
Subject: xfs: avoid COW fork extent lookups in writeback if the fork didn't
 change

Used the per-fork sequence counter to avoid lookups in the writeback code
unless the COW fork actually changed.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_aops.c  | 38 +++++++++++++++++++++++++++++++++-----
 fs/xfs/xfs_iomap.c |  5 ++++-
 fs/xfs/xfs_iomap.h |  2 +-
 3 files changed, 38 insertions(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 814100d27343..235b4ddcd324 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -29,6 +29,7 @@
 struct xfs_writepage_ctx {
 	struct xfs_bmbt_irec    imap;
 	unsigned int		io_type;
+	unsigned int		cow_seq;
 	struct xfs_ioend	*ioend;
 };
 
@@ -310,6 +311,7 @@ xfs_map_blocks(
 	struct xfs_mount	*mp = ip->i_mount;
 	ssize_t			count = i_blocksize(inode);
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset), end_fsb;
+	xfs_fileoff_t		cow_fsb = NULLFILEOFF;
 	struct xfs_bmbt_irec	imap;
 	int			whichfork = XFS_DATA_FORK;
 	struct xfs_iext_cursor	icur;
@@ -333,12 +335,23 @@ xfs_map_blocks(
 	 * COW fork blocks can overlap data fork blocks even if the blocks
 	 * aren't shared.  COW I/O always takes precedent, so we must always
 	 * check for overlap on reflink inodes unless the mapping is already a
-	 * COW one.
+	 * COW one, or the COW fork hasn't changed from the last time we looked
+	 * at it.
+	 *
+	 * It's safe to check the COW fork if_seq here without the ILOCK because
+	 * we've indirectly protected against concurrent updates: writeback has
+	 * the page locked, which prevents concurrent invalidations by reflink
+	 * and directio and prevents concurrent buffered writes to the same
+	 * page.  Changes to if_seq always happen under i_lock, which protects
+	 * against concurrent updates and provides a memory barrier on the way
+	 * out that ensures that we always see the current value.
 	 */
 	imap_valid = offset_fsb >= wpc->imap.br_startoff &&
 		     offset_fsb < wpc->imap.br_startoff + wpc->imap.br_blockcount;
 	if (imap_valid &&
-	    (!xfs_inode_has_cow_data(ip) || wpc->io_type == XFS_IO_COW))
+	    (!xfs_inode_has_cow_data(ip) ||
+	     wpc->io_type == XFS_IO_COW ||
+	     wpc->cow_seq == ip->i_cowfp->if_seq))
 		return 0;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -364,8 +377,10 @@ xfs_map_blocks(
 	 * it directly instead of looking up anything in the data fork.
 	 */
 	if (xfs_inode_has_cow_data(ip) &&
-	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap) &&
-	    imap.br_startoff <= offset_fsb) {
+	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
+		cow_fsb = imap.br_startoff;
+	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
+		wpc->cow_seq = ip->i_cowfp->if_seq;
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		/*
 		 * Truncate can race with writeback since writeback doesn't
@@ -411,6 +426,16 @@ xfs_map_blocks(
 		imap.br_startblock = HOLESTARTBLOCK;
 		wpc->io_type = XFS_IO_HOLE;
 	} else {
+		/*
+		 * Truncate to the next COW extent if there is one.  This is the
+		 * only opportunity to do this because we can skip COW fork
+		 * lookups for the subsequent blocks in the mapping; however,
+		 * the requirement to treat the COW range separately remains.
+		 */
+		if (cow_fsb != NULLFILEOFF &&
+		    cow_fsb < imap.br_startoff + imap.br_blockcount)
+			imap.br_blockcount = cow_fsb - imap.br_startoff;
+
 		if (isnullstartblock(imap.br_startblock)) {
 			/* got a delalloc extent */
 			wpc->io_type = XFS_IO_DELALLOC;
@@ -427,9 +452,12 @@ xfs_map_blocks(
 	trace_xfs_map_blocks_found(ip, offset, count, wpc->io_type, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_iomap_write_allocate(ip, whichfork, offset, &imap);
+	error = xfs_iomap_write_allocate(ip, whichfork, offset, &imap,
+			&wpc->cow_seq);
 	if (error)
 		return error;
+	ASSERT(whichfork == XFS_COW_FORK || cow_fsb == NULLFILEOFF ||
+	       imap.br_startoff + imap.br_blockcount <= cow_fsb);
 	wpc->imap = imap;
 	trace_xfs_map_blocks_alloc(ip, offset, count, wpc->io_type, &imap);
 	return 0;
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 8e8ca9f03f0e..3282575e2df4 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -651,7 +651,8 @@ xfs_iomap_write_allocate(
 	xfs_inode_t	*ip,
 	int		whichfork,
 	xfs_off_t	offset,
-	xfs_bmbt_irec_t *imap)
+	xfs_bmbt_irec_t *imap,
+	unsigned int	*cow_seq)
 {
 	xfs_mount_t	*mp = ip->i_mount;
 	xfs_fileoff_t	offset_fsb, last_block;
@@ -766,6 +767,8 @@ xfs_iomap_write_allocate(
 			if (error)
 				goto error0;
 
+			if (whichfork == XFS_COW_FORK)
+				*cow_seq = XFS_IFORK_PTR(ip, whichfork)->if_seq;
 			xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		}
 
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 83474c9cede9..c6170548831b 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -14,7 +14,7 @@ struct xfs_bmbt_irec;
 int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
 			struct xfs_bmbt_irec *, int);
 int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t,
-			struct xfs_bmbt_irec *);
+			struct xfs_bmbt_irec *, unsigned int *);
 int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
 
 void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
-- 
cgit v1.2.3


From ff23f4af7efd86cbb1bda42fe2171e0790f9cb5a Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Tue, 31 Jul 2018 13:18:02 -0700
Subject: xfs: move extent busy tree initialization to xfs_initialize_perag

Move the per-AG busy extent tree initialization to the per-ag structure
initialization since we don't want online repair to leak the old tree.
We only deconstruct the tree at unmount time, so this should be safe.
This also enables us to eliminate the commented out initialization in
the xfsprogs libxfs.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
---
 fs/xfs/libxfs/xfs_alloc.c | 3 ---
 fs/xfs/xfs_mount.c        | 3 +++
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3c3f2d5119ea..9847c1632712 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2755,9 +2755,6 @@ xfs_alloc_read_agf(
 		pag->pagf_levels[XFS_BTNUM_RMAPi] =
 			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
 		pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
-		spin_lock_init(&pag->pagb_lock);
-		pag->pagb_count = 0;
-		pag->pagb_tree = RB_ROOT;
 		pag->pagf_init = 1;
 		pag->pagf_agflreset = xfs_agfl_needs_reset(mp, agf);
 	}
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 8f739e4d0d1c..99db27d6ac8a 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -207,6 +207,9 @@ xfs_initialize_perag(
 		if (xfs_buf_hash_init(pag))
 			goto out_free_pag;
 		init_waitqueue_head(&pag->pagb_wait);
+		spin_lock_init(&pag->pagb_lock);
+		pag->pagb_count = 0;
+		pag->pagb_tree = RB_ROOT;
 
 		if (radix_tree_preload(GFP_NOFS))
 			goto out_hash_destroy;
-- 
cgit v1.2.3


From 944d58595be02634cc295e341306ccda2365554d Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Tue, 31 Jul 2018 16:26:09 -0500
Subject: PCI/AER: Remove duplicate PCI_EXP_AER_FLAGS definition

PCI_EXP_AER_FLAGS was defined twice (with identical definitions), once
under #ifdef CONFIG_ACPI_APEI, and again at the top level.  This looks like
my merge error from these commits:

  fd3362cb73de ("PCI/AER: Squash aerdrv_core.c into aerdrv.c")
  41cbc9eb1a82 ("PCI/AER: Squash ecrc.c into aerdrv.c")

Remove the duplicate PCI_EXP_AER_FLAGS definition.

Fixes: 41cbc9eb1a82 ("PCI/AER: Squash ecrc.c into aerdrv.c")
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Oza Pawandeep <poza@codeaurora.org>
---
 drivers/pci/pcie/aer.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 2b344c9e2d46..c6cc855bfa22 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -329,8 +329,6 @@ int pcie_aer_get_firmware_first(struct pci_dev *dev)
 		aer_set_firmware_first(dev);
 	return dev->__aer_firmware_first;
 }
-#define	PCI_EXP_AER_FLAGS	(PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \
-				 PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE)
 
 static bool aer_firmware_first;
 
-- 
cgit v1.2.3


From 2d227ec2c11c568910299e8f913bac2dda47397c Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Fri, 20 Jul 2018 16:26:46 +0800
Subject: drm/amd/pp/Polaris12: Fix a chunk of registers missed to program

DIDTConfig_Polaris12[] table missed a big chunk of data.

Pointed by aidan.fabius <aidan.fabius@coreavi.com>

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c   | 43 ++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
index c952845833d7..5e19f5977eb1 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu7_powertune.c
@@ -403,6 +403,49 @@ static const struct gpu_pt_config_reg DIDTConfig_Polaris12[] = {
 	{   ixDIDT_SQ_CTRL1,                   DIDT_SQ_CTRL1__MAX_POWER_MASK,                      DIDT_SQ_CTRL1__MAX_POWER__SHIFT,                    0xffff,     GPU_CONFIGREG_DIDT_IND },
 
 	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__UNUSED_0_MASK,                    DIDT_SQ_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL_OCP,                DIDT_SQ_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_SQ_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_SQ_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3853,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_0_MASK,                       DIDT_SQ_CTRL2__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE_MASK,       DIDT_SQ_CTRL2__SHORT_TERM_INTERVAL_SIZE__SHIFT,     0x005a,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_1_MASK,                       DIDT_SQ_CTRL2__UNUSED_1__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO_MASK,       DIDT_SQ_CTRL2__LONG_TERM_INTERVAL_RATIO__SHIFT,     0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL2,                   DIDT_SQ_CTRL2__UNUSED_2_MASK,                       DIDT_SQ_CTRL2__UNUSED_2__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE_MASK,    DIDT_SQ_STALL_CTRL__DIDT_STALL_CTRL_ENABLE__SHIFT,  0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_HI__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO_MASK,       DIDT_SQ_STALL_CTRL__DIDT_STALL_DELAY_LO__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD_MASK,   DIDT_SQ_STALL_CTRL__DIDT_HI_POWER_THRESHOLD__SHIFT, 0x0ebb,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_STALL_CTRL,              DIDT_SQ_STALL_CTRL__UNUSED_0_MASK,                  DIDT_SQ_STALL_CTRL__UNUSED_0__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE_MASK,       DIDT_SQ_TUNING_CTRL__DIDT_TUNING_ENABLE__SHIFT,     0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_HI__SHIFT,     0x3853,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO_MASK,       DIDT_SQ_TUNING_CTRL__MAX_POWER_DELTA_LO__SHIFT,     0x3153,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_TUNING_CTRL,             DIDT_SQ_TUNING_CTRL__UNUSED_0_MASK,                 DIDT_SQ_TUNING_CTRL__UNUSED_0__SHIFT,               0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN_MASK,                   DIDT_SQ_CTRL0__DIDT_CTRL_EN__SHIFT,                 0x0001,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__USE_REF_CLOCK_MASK,                  DIDT_SQ_CTRL0__USE_REF_CLOCK__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__PHASE_OFFSET_MASK,                   DIDT_SQ_CTRL0__PHASE_OFFSET__SHIFT,                 0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CTRL_RST_MASK,                  DIDT_SQ_CTRL0__DIDT_CTRL_RST__SHIFT,                0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE_MASK,           DIDT_SQ_CTRL0__DIDT_CLK_EN_OVERRIDE__SHIFT,         0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_HI__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO_MASK,     DIDT_SQ_CTRL0__DIDT_MAX_STALLS_ALLOWED_LO__SHIFT,   0x0010,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_SQ_CTRL0,                   DIDT_SQ_CTRL0__UNUSED_0_MASK,                       DIDT_SQ_CTRL0__UNUSED_0__SHIFT,                     0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT0_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT0__SHIFT,                  0x000a,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT1_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT1__SHIFT,                  0x0010,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT2_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT2__SHIFT,                  0x0017,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT0_3,               DIDT_TD_WEIGHT0_3__WEIGHT3_MASK,                    DIDT_TD_WEIGHT0_3__WEIGHT3__SHIFT,                  0x002f,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT4_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT4__SHIFT,                  0x0046,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT5_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT5__SHIFT,                  0x005d,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT6_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT6__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_WEIGHT4_7,               DIDT_TD_WEIGHT4_7__WEIGHT7_MASK,                    DIDT_TD_WEIGHT4_7__WEIGHT7__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MIN_POWER_MASK,                      DIDT_TD_CTRL1__MIN_POWER__SHIFT,                    0x0000,     GPU_CONFIGREG_DIDT_IND },
+	{   ixDIDT_TD_CTRL1,                   DIDT_TD_CTRL1__MAX_POWER_MASK,                      DIDT_TD_CTRL1__MAX_POWER__SHIFT,                    0xffff,     GPU_CONFIGREG_DIDT_IND },
+
+	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__UNUSED_0_MASK,                    DIDT_TD_CTRL_OCP__UNUSED_0__SHIFT,                  0x0000,     GPU_CONFIGREG_DIDT_IND },
 	{   ixDIDT_TD_CTRL_OCP,                DIDT_TD_CTRL_OCP__OCP_MAX_POWER_MASK,               DIDT_TD_CTRL_OCP__OCP_MAX_POWER__SHIFT,             0x00ff,     GPU_CONFIGREG_DIDT_IND },
 
 	{   ixDIDT_TD_CTRL2,                   DIDT_TD_CTRL2__MAX_POWER_DELTA_MASK,                DIDT_TD_CTRL2__MAX_POWER_DELTA__SHIFT,              0x3fff,     GPU_CONFIGREG_DIDT_IND },
-- 
cgit v1.2.3


From 90983631a6486f68c1e95bf30713a179ac0a083f Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Fri, 20 Jul 2018 18:19:00 +0800
Subject: drm/amd/pp: Delete unused temp variables

Only delete the dead temp variables in Polaris.

Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/powerplay/smumgr/polaris10_smumgr.c    | 22 ++++++----------------
 1 file changed, 6 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
index a4ce199af475..1276f168ff68 100644
--- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
+++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c
@@ -1204,7 +1204,6 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	SMIO_Pattern vol_level;
 	uint32_t mvdd;
-	uint16_t us_mvdd;
 
 	table->ACPILevel.Flags &= ~PPSMC_SWSTATE_FLAG_DC;
 
@@ -1255,16 +1254,11 @@ static int polaris10_populate_smc_acpi_level(struct pp_hwmgr *hwmgr,
 			"in Clock Dependency Table",
 			);
 
-	us_mvdd = 0;
-	if ((SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
-			(data->mclk_dpm_key_disabled))
-		us_mvdd = data->vbios_boot_state.mvdd_bootup_value;
-	else {
-		if (!polaris10_populate_mvdd_value(hwmgr,
+	if (!((SMU7_VOLTAGE_CONTROL_NONE == data->mvdd_control) ||
+			(data->mclk_dpm_key_disabled)))
+		polaris10_populate_mvdd_value(hwmgr,
 				data->dpm_table.mclk_table.dpm_levels[0].value,
-				&vol_level))
-			us_mvdd = vol_level.Voltage;
-	}
+				&vol_level);
 
 	if (0 == polaris10_populate_mvdd_value(hwmgr, 0, &vol_level))
 		table->MemoryACPILevel.MinMvdd = PP_HOST_TO_SMC_UL(vol_level.Voltage);
@@ -1517,7 +1511,7 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 	uint32_t ro, efuse, volt_without_cks, volt_with_cks, value, max, min;
 	struct polaris10_smumgr *smu_data = (struct polaris10_smumgr *)(hwmgr->smu_backend);
 
-	uint8_t i, stretch_amount, stretch_amount2, volt_offset = 0;
+	uint8_t i, stretch_amount, volt_offset = 0;
 	struct phm_ppt_v1_information *table_info =
 			(struct phm_ppt_v1_information *)(hwmgr->pptable);
 	struct phm_ppt_v1_clock_voltage_dependency_table *sclk_table =
@@ -1568,11 +1562,7 @@ static int polaris10_populate_clock_stretcher_data_table(struct pp_hwmgr *hwmgr)
 
 	smu_data->smc_state_table.LdoRefSel = (table_info->cac_dtp_table->ucCKS_LDO_REFSEL != 0) ? table_info->cac_dtp_table->ucCKS_LDO_REFSEL : 6;
 	/* Populate CKS Lookup Table */
-	if (stretch_amount == 1 || stretch_amount == 2 || stretch_amount == 5)
-		stretch_amount2 = 0;
-	else if (stretch_amount == 3 || stretch_amount == 4)
-		stretch_amount2 = 1;
-	else {
+	if (stretch_amount == 0 || stretch_amount > 5) {
 		phm_cap_unset(hwmgr->platform_descriptor.platformCaps,
 				PHM_PlatformCaps_ClockStretcher);
 		PP_ASSERT_WITH_CODE(false,
-- 
cgit v1.2.3


From 8a50bb47a863c3cb8950a2e810448c9a82a9d446 Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Wed, 25 Jul 2018 11:45:03 +0800
Subject: drm/amd/pp: Convert voltage unit in mV*4 to mV on CZ/ST

the voltage showed in debugfs and hwmon should be in mV

Reviewed-by: Evan Quan <evan.quan@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
index 288802f209dd..0adfc5392cd3 100644
--- a/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
+++ b/drivers/gpu/drm/amd/powerplay/hwmgr/smu8_hwmgr.c
@@ -244,6 +244,7 @@ static int smu8_initialize_dpm_defaults(struct pp_hwmgr *hwmgr)
 	return 0;
 }
 
+/* convert form 8bit vid to real voltage in mV*4 */
 static uint32_t smu8_convert_8Bit_index_to_voltage(
 			struct pp_hwmgr *hwmgr, uint16_t voltage)
 {
@@ -1702,13 +1703,13 @@ static int smu8_read_sensor(struct pp_hwmgr *hwmgr, int idx,
 	case AMDGPU_PP_SENSOR_VDDNB:
 		tmp = (cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixSMUSVI_NB_CURRENTVID) &
 			CURRENT_NB_VID_MASK) >> CURRENT_NB_VID__SHIFT;
-		vddnb = smu8_convert_8Bit_index_to_voltage(hwmgr, tmp);
+		vddnb = smu8_convert_8Bit_index_to_voltage(hwmgr, tmp) / 4;
 		*((uint32_t *)value) = vddnb;
 		return 0;
 	case AMDGPU_PP_SENSOR_VDDGFX:
 		tmp = (cgs_read_ind_register(hwmgr->device, CGS_IND_REG__SMC, ixSMUSVI_GFX_CURRENTVID) &
 			CURRENT_GFX_VID_MASK) >> CURRENT_GFX_VID__SHIFT;
-		vddgfx = smu8_convert_8Bit_index_to_voltage(hwmgr, (u16)tmp);
+		vddgfx = smu8_convert_8Bit_index_to_voltage(hwmgr, (u16)tmp) / 4;
 		*((uint32_t *)value) = vddgfx;
 		return 0;
 	case AMDGPU_PP_SENSOR_UVD_VCLK:
-- 
cgit v1.2.3


From ccf9ef0b0d10434dec5046bcfc4e834a7b1830fd Mon Sep 17 00:00:00 2001
From: Rex Zhu <rex.zhu@amd.com>
Date: Wed, 25 Jul 2018 11:51:46 +0800
Subject: drm/amdgpu: fix a reversed condition

This test was reversed so it would end up leading to vddnb value
can't be read via hwmon on APU.

Reviewed-by: Evan Quan <evan.quan@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Rex Zhu <Rex.Zhu@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 15a1192c1ec5..23fc1d32b937 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -1185,7 +1185,7 @@ static ssize_t amdgpu_hwmon_show_vddnb(struct device *dev,
 	int r, size = sizeof(vddnb);
 
 	/* only APUs have vddnb */
-	if  (adev->flags & AMD_IS_APU)
+	if  (!(adev->flags & AMD_IS_APU))
 		return -EINVAL;
 
 	/* Can't get voltage when the card is off */
-- 
cgit v1.2.3


From 52c054caf83012fe9fe858ee86d90b4ea2cc3cca Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 27 Jul 2018 15:32:04 +0200
Subject: drm/amdgpu: add proper error handling to amdgpu_bo_list_get
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise we silently don't use a BO list when the handle is invalid.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming Zhou <david1.zhou@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h         |  4 ++--
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 28 ++++++++++------------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c      | 11 ++++++++---
 3 files changed, 20 insertions(+), 23 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 1f6345dda6ea..4d4d6697fbce 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -713,8 +713,8 @@ struct amdgpu_bo_list {
 	struct amdgpu_bo_list_entry *array;
 };
 
-struct amdgpu_bo_list *
-amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id);
+int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
+		       struct amdgpu_bo_list **result);
 void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 			     struct list_head *validated);
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 7679c068c89a..944868e47119 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -180,27 +180,20 @@ error_free:
 	return r;
 }
 
-struct amdgpu_bo_list *
-amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id)
+int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
+		       struct amdgpu_bo_list **result)
 {
-	struct amdgpu_bo_list *result;
-
 	rcu_read_lock();
-	result = idr_find(&fpriv->bo_list_handles, id);
+	*result = idr_find(&fpriv->bo_list_handles, id);
 
-	if (result) {
-		if (kref_get_unless_zero(&result->refcount)) {
-			rcu_read_unlock();
-			mutex_lock(&result->lock);
-		} else {
-			rcu_read_unlock();
-			result = NULL;
-		}
-	} else {
+	if (*result && kref_get_unless_zero(&(*result)->refcount)) {
 		rcu_read_unlock();
+		mutex_lock(&(*result)->lock);
+		return 0;
 	}
 
-	return result;
+	rcu_read_unlock();
+	return -ENOENT;
 }
 
 void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
@@ -335,9 +328,8 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		break;
 
 	case AMDGPU_BO_LIST_OP_UPDATE:
-		r = -ENOENT;
-		list = amdgpu_bo_list_get(fpriv, handle);
-		if (!list)
+		r = amdgpu_bo_list_get(fpriv, handle, &list);
+		if (r)
 			goto error_free;
 
 		r = amdgpu_bo_list_set(adev, filp, list, info,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 533b2e7656c0..8a49c3b97bd4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -572,11 +572,16 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	INIT_LIST_HEAD(&p->validated);
 
 	/* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */
-	if (!p->bo_list)
-		p->bo_list = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle);
-	else
+	if (p->bo_list) {
 		mutex_lock(&p->bo_list->lock);
 
+	} else if (cs->in.bo_list_handle) {
+		r = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle,
+				       &p->bo_list);
+		if (r)
+			return r;
+	}
+
 	if (p->bo_list) {
 		amdgpu_bo_list_get_list(p->bo_list, &p->validated);
 		if (p->bo_list->first_userptr != p->bo_list->num_entries)
-- 
cgit v1.2.3


From ba7f47831ebdad141791be53a51049d6771156cd Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Fri, 6 Jul 2018 14:12:11 +0900
Subject: drm/sched: remove unneeded -Iinclude/drm compiler flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I refactored the include directives under include/drm/ some time ago.
This flag is unneeded.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Acked-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/Makefile | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/scheduler/Makefile b/drivers/gpu/drm/scheduler/Makefile
index bd0377c0d2ee..7665883f81d4 100644
--- a/drivers/gpu/drm/scheduler/Makefile
+++ b/drivers/gpu/drm/scheduler/Makefile
@@ -20,7 +20,6 @@
 # OTHER DEALINGS IN THE SOFTWARE.
 #
 #
-ccflags-y := -Iinclude/drm
 gpu-sched-y := gpu_scheduler.o sched_fence.o
 
 obj-$(CONFIG_DRM_SCHED) += gpu-sched.o
-- 
cgit v1.2.3


From 275105ce7be37a2cc80eb1b60e6526355f54df94 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 15:33:34 +0200
Subject: drm/amdgpu: fix total size calculation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

long might only be 32bit in size and we can easily use more than 4GB
here.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 944868e47119..6728448167ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -105,9 +105,9 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 	struct amdgpu_bo *oa_obj = adev->gds.oa_gfx_bo;
 
 	unsigned last_entry = 0, first_userptr = num_entries;
+	uint64_t total_size = 0;
 	unsigned i;
 	int r;
-	unsigned long total_size = 0;
 
 	array = kvmalloc_array(num_entries, sizeof(struct amdgpu_bo_list_entry), GFP_KERNEL);
 	if (!array)
-- 
cgit v1.2.3


From 0cb7c1f03bfb3991120313c5927c1749041ef800 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 16:18:54 +0200
Subject: drm/amdgpu: return error if both BOs and bo_list handle is given
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return -EINVAL when both the BOs as well as a list handle is provided in
the IOCTL.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 8a49c3b97bd4..d41cea78e4aa 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -572,14 +572,17 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	INIT_LIST_HEAD(&p->validated);
 
 	/* p->bo_list could already be assigned if AMDGPU_CHUNK_ID_BO_HANDLES is present */
-	if (p->bo_list) {
-		mutex_lock(&p->bo_list->lock);
+	if (cs->in.bo_list_handle) {
+		if (p->bo_list)
+			return -EINVAL;
 
-	} else if (cs->in.bo_list_handle) {
 		r = amdgpu_bo_list_get(fpriv, cs->in.bo_list_handle,
 				       &p->bo_list);
 		if (r)
 			return r;
+
+	} else if (p->bo_list) {
+		mutex_lock(&p->bo_list->lock);
 	}
 
 	if (p->bo_list) {
-- 
cgit v1.2.3


From 8ab19ea619aeed8ca4a36c124e8edfd9b9491aba Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Fri, 27 Jul 2018 16:56:34 +0200
Subject: drm/amdgpu: add new amdgpu_vm_bo_trace_cs() function v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This allows us to trace all VM ranges which should be valid inside a CS.

v2: dump mappings without BO as well

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Reviewed-and-tested-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com> (v1)
Reviewed-by: Huang Rui <ray.huang@amd.com> (v1)
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c    |  2 ++
 drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h |  5 +++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c    | 29 +++++++++++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h    |  1 +
 4 files changed, 37 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index d41cea78e4aa..0295666968da 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -1223,6 +1223,7 @@ static void amdgpu_cs_post_dependencies(struct amdgpu_cs_parser *p)
 static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 			    union drm_amdgpu_cs *cs)
 {
+	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_ring *ring = p->ring;
 	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	enum drm_sched_priority priority;
@@ -1275,6 +1276,7 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	amdgpu_job_free_resources(job);
 
 	trace_amdgpu_cs_ioctl(job);
+	amdgpu_vm_bo_trace_cs(&fpriv->vm, &p->ticket);
 	priority = job->base.s_priority;
 	drm_sched_entity_push_job(&job->base, entity);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
index 11f262f15200..7206a0025b17 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_trace.h
@@ -314,6 +314,11 @@ DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_mapping,
 	    TP_ARGS(mapping)
 );
 
+DEFINE_EVENT(amdgpu_vm_mapping, amdgpu_vm_bo_cs,
+	    TP_PROTO(struct amdgpu_bo_va_mapping *mapping),
+	    TP_ARGS(mapping)
+);
+
 TRACE_EVENT(amdgpu_vm_set_ptes,
 	    TP_PROTO(uint64_t pe, uint64_t addr, unsigned count,
 		     uint32_t incr, uint64_t flags),
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 5d7d7900ccab..015613b4f98b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2343,6 +2343,35 @@ struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
 	return amdgpu_vm_it_iter_first(&vm->va, addr, addr);
 }
 
+/**
+ * amdgpu_vm_bo_trace_cs - trace all reserved mappings
+ *
+ * @vm: the requested vm
+ * @ticket: CS ticket
+ *
+ * Trace all mappings of BOs reserved during a command submission.
+ */
+void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket)
+{
+	struct amdgpu_bo_va_mapping *mapping;
+
+	if (!trace_amdgpu_vm_bo_cs_enabled())
+		return;
+
+	for (mapping = amdgpu_vm_it_iter_first(&vm->va, 0, U64_MAX); mapping;
+	     mapping = amdgpu_vm_it_iter_next(mapping, 0, U64_MAX)) {
+		if (mapping->bo_va && mapping->bo_va->base.bo) {
+			struct amdgpu_bo *bo;
+
+			bo = mapping->bo_va->base.bo;
+			if (READ_ONCE(bo->tbo.resv->lock.ctx) != ticket)
+				continue;
+		}
+
+		trace_amdgpu_vm_bo_cs(mapping);
+	}
+}
+
 /**
  * amdgpu_vm_bo_rmv - remove a bo to a specific vm
  *
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
index d416f895233d..67a15d439ac0 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.h
@@ -318,6 +318,7 @@ int amdgpu_vm_bo_clear_mappings(struct amdgpu_device *adev,
 				uint64_t saddr, uint64_t size);
 struct amdgpu_bo_va_mapping *amdgpu_vm_bo_lookup_mapping(struct amdgpu_vm *vm,
 							 uint64_t addr);
+void amdgpu_vm_bo_trace_cs(struct amdgpu_vm *vm, struct ww_acquire_ctx *ticket);
 void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
 		      struct amdgpu_bo_va *bo_va);
 void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint32_t vm_size,
-- 
cgit v1.2.3


From 4a8c21a1e9b3c35b21c5a4a4c16a009a193389bd Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 13:27:09 +0200
Subject: drm/amdgpu: move bo_list defines to amdgpu_bo_list.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Further demangle amdgpu.h

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu.h         | 40 +----------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h | 70 +++++++++++++++++++++++++++++
 2 files changed, 71 insertions(+), 39 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 4d4d6697fbce..447c4c7a36d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -74,6 +74,7 @@
 #include "amdgpu_gart.h"
 #include "amdgpu_debugfs.h"
 #include "amdgpu_job.h"
+#include "amdgpu_bo_list.h"
 
 /*
  * Modules parameters.
@@ -689,45 +690,6 @@ struct amdgpu_fpriv {
 	struct amdgpu_ctx_mgr	ctx_mgr;
 };
 
-/*
- * residency list
- */
-struct amdgpu_bo_list_entry {
-	struct amdgpu_bo		*robj;
-	struct ttm_validate_buffer	tv;
-	struct amdgpu_bo_va		*bo_va;
-	uint32_t			priority;
-	struct page			**user_pages;
-	int				user_invalidated;
-};
-
-struct amdgpu_bo_list {
-	struct mutex lock;
-	struct rcu_head rhead;
-	struct kref refcount;
-	struct amdgpu_bo *gds_obj;
-	struct amdgpu_bo *gws_obj;
-	struct amdgpu_bo *oa_obj;
-	unsigned first_userptr;
-	unsigned num_entries;
-	struct amdgpu_bo_list_entry *array;
-};
-
-int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
-		       struct amdgpu_bo_list **result);
-void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
-			     struct list_head *validated);
-void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
-void amdgpu_bo_list_free(struct amdgpu_bo_list *list);
-int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
-				      struct drm_amdgpu_bo_list_entry **info_param);
-
-int amdgpu_bo_list_create(struct amdgpu_device *adev,
-				 struct drm_file *filp,
-				 struct drm_amdgpu_bo_list_entry *info,
-				 unsigned num_entries,
-				 struct amdgpu_bo_list **list);
-
 /*
  * GFX stuff
  */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
new file mode 100644
index 000000000000..833f846bfdad
--- /dev/null
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -0,0 +1,70 @@
+/*
+ * Copyright 2018 Advanced Micro Devices, Inc.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
+ * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR
+ * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE,
+ * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
+ * OTHER DEALINGS IN THE SOFTWARE.
+ *
+ */
+#ifndef __AMDGPU_BO_LIST_H__
+#define __AMDGPU_BO_LIST_H__
+
+#include <drm/ttm/ttm_execbuf_util.h>
+#include <drm/amdgpu_drm.h>
+
+struct amdgpu_device;
+struct amdgpu_bo;
+struct amdgpu_bo_va;
+struct amdgpu_fpriv;
+
+struct amdgpu_bo_list_entry {
+	struct amdgpu_bo		*robj;
+	struct ttm_validate_buffer	tv;
+	struct amdgpu_bo_va		*bo_va;
+	uint32_t			priority;
+	struct page			**user_pages;
+	int				user_invalidated;
+};
+
+struct amdgpu_bo_list {
+	struct mutex lock;
+	struct rcu_head rhead;
+	struct kref refcount;
+	struct amdgpu_bo *gds_obj;
+	struct amdgpu_bo *gws_obj;
+	struct amdgpu_bo *oa_obj;
+	unsigned first_userptr;
+	unsigned num_entries;
+	struct amdgpu_bo_list_entry *array;
+};
+
+int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
+		       struct amdgpu_bo_list **result);
+void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
+			     struct list_head *validated);
+void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
+void amdgpu_bo_list_free(struct amdgpu_bo_list *list);
+int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
+				      struct drm_amdgpu_bo_list_entry **info_param);
+
+int amdgpu_bo_list_create(struct amdgpu_device *adev,
+				 struct drm_file *filp,
+				 struct drm_amdgpu_bo_list_entry *info,
+				 unsigned num_entries,
+				 struct amdgpu_bo_list **list);
+
+#endif
-- 
cgit v1.2.3


From 81c6dabcc990c341793368db985ee8aca5713b16 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 13:46:04 +0200
Subject: drm/amdgpu: always recreate bo_list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The bo_list handle is allocated by OP_CREATE, so in OP_UPDATE here we just
re-create the bo_list object and replace the handle. This way we don't
need locking to protect the bo_list because it's always re-created when
changed.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 23 ++++++++++++-----------
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c      |  3 ---
 3 files changed, 12 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 6728448167ba..556040e45931 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -50,7 +50,6 @@ static void amdgpu_bo_list_release_rcu(struct kref *ref)
 	for (i = 0; i < list->num_entries; ++i)
 		amdgpu_bo_unref(&list->array[i].robj);
 
-	mutex_destroy(&list->lock);
 	kvfree(list->array);
 	kfree_rcu(list, rhead);
 }
@@ -70,7 +69,6 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev,
 		return -ENOMEM;
 
 	/* initialize bo list*/
-	mutex_init(&list->lock);
 	kref_init(&list->refcount);
 	r = amdgpu_bo_list_set(adev, filp, list, info, num_entries);
 	if (r) {
@@ -188,7 +186,6 @@ int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
 
 	if (*result && kref_get_unless_zero(&(*result)->refcount)) {
 		rcu_read_unlock();
-		mutex_lock(&(*result)->lock);
 		return 0;
 	}
 
@@ -231,7 +228,6 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list)
 {
-	mutex_unlock(&list->lock);
 	kref_put(&list->refcount, amdgpu_bo_list_release_rcu);
 }
 
@@ -242,7 +238,6 @@ void amdgpu_bo_list_free(struct amdgpu_bo_list *list)
 	for (i = 0; i < list->num_entries; ++i)
 		amdgpu_bo_unref(&list->array[i].robj);
 
-	mutex_destroy(&list->lock);
 	kvfree(list->array);
 	kfree(list);
 }
@@ -297,7 +292,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 	union drm_amdgpu_bo_list *args = data;
 	uint32_t handle = args->in.list_handle;
 	struct drm_amdgpu_bo_list_entry *info = NULL;
-	struct amdgpu_bo_list *list;
+	struct amdgpu_bo_list *list, *old;
 	int r;
 
 	r = amdgpu_bo_create_list_entry_array(&args->in, &info);
@@ -328,16 +323,22 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		break;
 
 	case AMDGPU_BO_LIST_OP_UPDATE:
-		r = amdgpu_bo_list_get(fpriv, handle, &list);
+		r = amdgpu_bo_list_create(adev, filp, info, args->in.bo_number,
+					  &list);
 		if (r)
 			goto error_free;
 
-		r = amdgpu_bo_list_set(adev, filp, list, info,
-					      args->in.bo_number);
-		amdgpu_bo_list_put(list);
-		if (r)
+		mutex_lock(&fpriv->bo_list_lock);
+		old = idr_replace(&fpriv->bo_list_handles, list, handle);
+		mutex_unlock(&fpriv->bo_list_lock);
+
+		if (IS_ERR(old)) {
+			amdgpu_bo_list_put(list);
+			r = PTR_ERR(old);
 			goto error_free;
+		}
 
+		amdgpu_bo_list_put(old);
 		break;
 
 	default:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
index 833f846bfdad..89195fdcb1ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -41,7 +41,6 @@ struct amdgpu_bo_list_entry {
 };
 
 struct amdgpu_bo_list {
-	struct mutex lock;
 	struct rcu_head rhead;
 	struct kref refcount;
 	struct amdgpu_bo *gds_obj;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 0295666968da..f7154f3ed807 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -580,9 +580,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 				       &p->bo_list);
 		if (r)
 			return r;
-
-	} else if (p->bo_list) {
-		mutex_lock(&p->bo_list->lock);
 	}
 
 	if (p->bo_list) {
-- 
cgit v1.2.3


From a0f208453b97565dab8c334ff013aa5ab3c66d0c Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 14:17:41 +0200
Subject: drm/amdgpu: nuke amdgpu_bo_list_free
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The RCU grace period is harmless and avoiding it is not worth the effort
of doubling the implementation.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 13 +------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h |  1 -
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c     |  2 +-
 3 files changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 556040e45931..5335f1b5459f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -231,17 +231,6 @@ void amdgpu_bo_list_put(struct amdgpu_bo_list *list)
 	kref_put(&list->refcount, amdgpu_bo_list_release_rcu);
 }
 
-void amdgpu_bo_list_free(struct amdgpu_bo_list *list)
-{
-	unsigned i;
-
-	for (i = 0; i < list->num_entries; ++i)
-		amdgpu_bo_unref(&list->array[i].robj);
-
-	kvfree(list->array);
-	kfree(list);
-}
-
 int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
 				      struct drm_amdgpu_bo_list_entry **info_param)
 {
@@ -310,7 +299,7 @@ int amdgpu_bo_list_ioctl(struct drm_device *dev, void *data,
 		r = idr_alloc(&fpriv->bo_list_handles, list, 1, 0, GFP_KERNEL);
 		mutex_unlock(&fpriv->bo_list_lock);
 		if (r < 0) {
-			amdgpu_bo_list_free(list);
+			amdgpu_bo_list_put(list);
 			return r;
 		}
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
index 89195fdcb1ef..0ce540203db1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -56,7 +56,6 @@ int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
 void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 			     struct list_head *validated);
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list);
-void amdgpu_bo_list_free(struct amdgpu_bo_list *list);
 int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
 				      struct drm_amdgpu_bo_list_entry **info_param);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index dd2132fa2b89..bd98cc5fb97b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -967,7 +967,7 @@ void amdgpu_driver_postclose_kms(struct drm_device *dev,
 	amdgpu_bo_unref(&pd);
 
 	idr_for_each_entry(&fpriv->bo_list_handles, list, handle)
-		amdgpu_bo_list_free(list);
+		amdgpu_bo_list_put(list);
 
 	idr_destroy(&fpriv->bo_list_handles);
 	mutex_destroy(&fpriv->bo_list_lock);
-- 
cgit v1.2.3


From 39f7f69a6054bb9777b47b6afdb5ce2fae30dbee Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 15:37:46 +0200
Subject: drm/amdgpu: add bo_list iterators
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add helpers to iterate over all entries in a bo_list.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Acked-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 21 ++++++------
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h | 10 ++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c      | 51 +++++++++++++----------------
 3 files changed, 43 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 5335f1b5459f..096bcf4a6334 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -43,12 +43,12 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 
 static void amdgpu_bo_list_release_rcu(struct kref *ref)
 {
-	unsigned i;
 	struct amdgpu_bo_list *list = container_of(ref, struct amdgpu_bo_list,
 						   refcount);
+	struct amdgpu_bo_list_entry *e;
 
-	for (i = 0; i < list->num_entries; ++i)
-		amdgpu_bo_unref(&list->array[i].robj);
+	amdgpu_bo_list_for_each_entry(e, list)
+		amdgpu_bo_unref(&e->robj);
 
 	kvfree(list->array);
 	kfree_rcu(list, rhead);
@@ -103,6 +103,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 	struct amdgpu_bo *oa_obj = adev->gds.oa_gfx_bo;
 
 	unsigned last_entry = 0, first_userptr = num_entries;
+	struct amdgpu_bo_list_entry *e;
 	uint64_t total_size = 0;
 	unsigned i;
 	int r;
@@ -156,7 +157,7 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 		trace_amdgpu_bo_list_set(list, entry->robj);
 	}
 
-	for (i = 0; i < list->num_entries; ++i)
+	amdgpu_bo_list_for_each_entry(e, list)
 		amdgpu_bo_unref(&list->array[i].robj);
 
 	kvfree(list->array);
@@ -201,6 +202,7 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 	 * concatenated in descending order.
 	 */
 	struct list_head bucket[AMDGPU_BO_LIST_NUM_BUCKETS];
+	struct amdgpu_bo_list_entry *e;
 	unsigned i;
 
 	for (i = 0; i < AMDGPU_BO_LIST_NUM_BUCKETS; i++)
@@ -211,14 +213,13 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 	 * in the list, the sort mustn't change the ordering of buffers
 	 * with the same priority, i.e. it must be stable.
 	 */
-	for (i = 0; i < list->num_entries; i++) {
-		unsigned priority = list->array[i].priority;
+	amdgpu_bo_list_for_each_entry(e, list) {
+		unsigned priority = e->priority;
 
-		if (!list->array[i].robj->parent)
-			list_add_tail(&list->array[i].tv.head,
-				      &bucket[priority]);
+		if (!e->robj->parent)
+			list_add_tail(&e->tv.head, &bucket[priority]);
 
-		list->array[i].user_pages = NULL;
+		e->user_pages = NULL;
 	}
 
 	/* Connect the sorted buckets in the output list. */
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
index 0ce540203db1..3d77abfcd4a6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -65,4 +65,14 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev,
 				 unsigned num_entries,
 				 struct amdgpu_bo_list **list);
 
+#define amdgpu_bo_list_for_each_entry(e, list) \
+	for (e = &(list)->array[0]; \
+	     e != &(list)->array[(list)->num_entries]; \
+	     ++e)
+
+#define amdgpu_bo_list_for_each_userptr_entry(e, list) \
+	for (e = &(list)->array[(list)->first_userptr]; \
+	     e != &(list)->array[(list)->num_entries]; \
+	     ++e)
+
 #endif
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index f7154f3ed807..1d7292ab2b62 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -563,10 +563,10 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
 	struct amdgpu_bo_list_entry *e;
 	struct list_head duplicates;
-	unsigned i, tries = 10;
 	struct amdgpu_bo *gds;
 	struct amdgpu_bo *gws;
 	struct amdgpu_bo *oa;
+	unsigned tries = 10;
 	int r;
 
 	INIT_LIST_HEAD(&p->validated);
@@ -596,7 +596,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	while (1) {
 		struct list_head need_pages;
-		unsigned i;
 
 		r = ttm_eu_reserve_buffers(&p->ticket, &p->validated, true,
 					   &duplicates);
@@ -611,12 +610,8 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			break;
 
 		INIT_LIST_HEAD(&need_pages);
-		for (i = p->bo_list->first_userptr;
-		     i < p->bo_list->num_entries; ++i) {
-			struct amdgpu_bo *bo;
-
-			e = &p->bo_list->array[i];
-			bo = e->robj;
+		amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+			struct amdgpu_bo *bo = e->robj;
 
 			if (amdgpu_ttm_tt_userptr_invalidated(bo->tbo.ttm,
 				 &e->user_invalidated) && e->user_pages) {
@@ -710,16 +705,14 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 
 	if (p->bo_list) {
 		struct amdgpu_vm *vm = &fpriv->vm;
-		unsigned i;
+		struct amdgpu_bo_list_entry *e;
 
 		gds = p->bo_list->gds_obj;
 		gws = p->bo_list->gws_obj;
 		oa = p->bo_list->oa_obj;
-		for (i = 0; i < p->bo_list->num_entries; i++) {
-			struct amdgpu_bo *bo = p->bo_list->array[i].robj;
 
-			p->bo_list->array[i].bo_va = amdgpu_vm_bo_find(vm, bo);
-		}
+		amdgpu_bo_list_for_each_entry(e, p->bo_list)
+			e->bo_va = amdgpu_vm_bo_find(vm, e->robj);
 	} else {
 		gds = p->adev->gds.gds_gfx_bo;
 		gws = p->adev->gds.gws_gfx_bo;
@@ -753,10 +746,7 @@ error_validate:
 error_free_pages:
 
 	if (p->bo_list) {
-		for (i = p->bo_list->first_userptr;
-		     i < p->bo_list->num_entries; ++i) {
-			e = &p->bo_list->array[i];
-
+		amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
 			if (!e->user_pages)
 				continue;
 
@@ -830,7 +820,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_va *bo_va;
 	struct amdgpu_bo *bo;
-	int i, r;
+	int r;
 
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
@@ -861,15 +851,17 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	}
 
 	if (p->bo_list) {
-		for (i = 0; i < p->bo_list->num_entries; i++) {
+		struct amdgpu_bo_list_entry *e;
+
+		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
 			struct dma_fence *f;
 
 			/* ignore duplicates */
-			bo = p->bo_list->array[i].robj;
+			bo = e->robj;
 			if (!bo)
 				continue;
 
-			bo_va = p->bo_list->array[i].bo_va;
+			bo_va = e->bo_va;
 			if (bo_va == NULL)
 				continue;
 
@@ -898,14 +890,15 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 		return r;
 
 	if (amdgpu_vm_debug && p->bo_list) {
+		struct amdgpu_bo_list_entry *e;
+
 		/* Invalidate all BOs to test for userspace bugs */
-		for (i = 0; i < p->bo_list->num_entries; i++) {
+		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
 			/* ignore duplicates */
-			bo = p->bo_list->array[i].robj;
-			if (!bo)
+			if (!e->robj)
 				continue;
 
-			amdgpu_vm_bo_invalidate(adev, bo, false);
+			amdgpu_vm_bo_invalidate(adev, e->robj, false);
 		}
 	}
 
@@ -1225,16 +1218,16 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	enum drm_sched_priority priority;
 	struct amdgpu_job *job;
-	unsigned i;
 	uint64_t seq;
 
 	int r;
 
 	amdgpu_mn_lock(p->mn);
 	if (p->bo_list) {
-		for (i = p->bo_list->first_userptr;
-		     i < p->bo_list->num_entries; ++i) {
-			struct amdgpu_bo *bo = p->bo_list->array[i].robj;
+		struct amdgpu_bo_list_entry *e;
+
+		amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+			struct amdgpu_bo *bo = e->robj;
 
 			if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm)) {
 				amdgpu_mn_unlock(p->mn);
-- 
cgit v1.2.3


From 920990cb080a44203bf6c8eb706e79ad23241ad3 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 16:16:01 +0200
Subject: drm/amdgpu: allocate the bo_list array after the list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This avoids multiple allocations for the head and the array.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c | 114 +++++++++++-----------------
 drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h |  17 +++--
 2 files changed, 57 insertions(+), 74 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
index 096bcf4a6334..d472a2c8399f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.c
@@ -35,13 +35,15 @@
 #define AMDGPU_BO_LIST_MAX_PRIORITY	32u
 #define AMDGPU_BO_LIST_NUM_BUCKETS	(AMDGPU_BO_LIST_MAX_PRIORITY + 1)
 
-static int amdgpu_bo_list_set(struct amdgpu_device *adev,
-				     struct drm_file *filp,
-				     struct amdgpu_bo_list *list,
-				     struct drm_amdgpu_bo_list_entry *info,
-				     unsigned num_entries);
+static void amdgpu_bo_list_free_rcu(struct rcu_head *rcu)
+{
+	struct amdgpu_bo_list *list = container_of(rcu, struct amdgpu_bo_list,
+						   rhead);
+
+	kvfree(list);
+}
 
-static void amdgpu_bo_list_release_rcu(struct kref *ref)
+static void amdgpu_bo_list_free(struct kref *ref)
 {
 	struct amdgpu_bo_list *list = container_of(ref, struct amdgpu_bo_list,
 						   refcount);
@@ -50,67 +52,36 @@ static void amdgpu_bo_list_release_rcu(struct kref *ref)
 	amdgpu_bo_list_for_each_entry(e, list)
 		amdgpu_bo_unref(&e->robj);
 
-	kvfree(list->array);
-	kfree_rcu(list, rhead);
+	call_rcu(&list->rhead, amdgpu_bo_list_free_rcu);
 }
 
-int amdgpu_bo_list_create(struct amdgpu_device *adev,
-				 struct drm_file *filp,
-				 struct drm_amdgpu_bo_list_entry *info,
-				 unsigned num_entries,
-				 struct amdgpu_bo_list **list_out)
+int amdgpu_bo_list_create(struct amdgpu_device *adev, struct drm_file *filp,
+			  struct drm_amdgpu_bo_list_entry *info,
+			  unsigned num_entries, struct amdgpu_bo_list **result)
 {
+	unsigned last_entry = 0, first_userptr = num_entries;
+	struct amdgpu_bo_list_entry *array;
 	struct amdgpu_bo_list *list;
+	uint64_t total_size = 0;
+	size_t size;
+	unsigned i;
 	int r;
 
+	if (num_entries > SIZE_MAX / sizeof(struct amdgpu_bo_list_entry))
+		return -EINVAL;
 
-	list = kzalloc(sizeof(struct amdgpu_bo_list), GFP_KERNEL);
+	size = sizeof(struct amdgpu_bo_list);
+	size += num_entries * sizeof(struct amdgpu_bo_list_entry);
+	list = kvmalloc(size, GFP_KERNEL);
 	if (!list)
 		return -ENOMEM;
 
-	/* initialize bo list*/
 	kref_init(&list->refcount);
-	r = amdgpu_bo_list_set(adev, filp, list, info, num_entries);
-	if (r) {
-		kfree(list);
-		return r;
-	}
-
-	*list_out = list;
-	return 0;
-}
-
-static void amdgpu_bo_list_destroy(struct amdgpu_fpriv *fpriv, int id)
-{
-	struct amdgpu_bo_list *list;
-
-	mutex_lock(&fpriv->bo_list_lock);
-	list = idr_remove(&fpriv->bo_list_handles, id);
-	mutex_unlock(&fpriv->bo_list_lock);
-	if (list)
-		kref_put(&list->refcount, amdgpu_bo_list_release_rcu);
-}
-
-static int amdgpu_bo_list_set(struct amdgpu_device *adev,
-				     struct drm_file *filp,
-				     struct amdgpu_bo_list *list,
-				     struct drm_amdgpu_bo_list_entry *info,
-				     unsigned num_entries)
-{
-	struct amdgpu_bo_list_entry *array;
-	struct amdgpu_bo *gds_obj = adev->gds.gds_gfx_bo;
-	struct amdgpu_bo *gws_obj = adev->gds.gws_gfx_bo;
-	struct amdgpu_bo *oa_obj = adev->gds.oa_gfx_bo;
-
-	unsigned last_entry = 0, first_userptr = num_entries;
-	struct amdgpu_bo_list_entry *e;
-	uint64_t total_size = 0;
-	unsigned i;
-	int r;
+	list->gds_obj = adev->gds.gds_gfx_bo;
+	list->gws_obj = adev->gds.gws_gfx_bo;
+	list->oa_obj = adev->gds.oa_gfx_bo;
 
-	array = kvmalloc_array(num_entries, sizeof(struct amdgpu_bo_list_entry), GFP_KERNEL);
-	if (!array)
-		return -ENOMEM;
+	array = amdgpu_bo_list_array_entry(list, 0);
 	memset(array, 0, num_entries * sizeof(struct amdgpu_bo_list_entry));
 
 	for (i = 0; i < num_entries; ++i) {
@@ -147,36 +118,41 @@ static int amdgpu_bo_list_set(struct amdgpu_device *adev,
 		entry->tv.shared = !entry->robj->prime_shared_count;
 
 		if (entry->robj->preferred_domains == AMDGPU_GEM_DOMAIN_GDS)
-			gds_obj = entry->robj;
+			list->gds_obj = entry->robj;
 		if (entry->robj->preferred_domains == AMDGPU_GEM_DOMAIN_GWS)
-			gws_obj = entry->robj;
+			list->gws_obj = entry->robj;
 		if (entry->robj->preferred_domains == AMDGPU_GEM_DOMAIN_OA)
-			oa_obj = entry->robj;
+			list->oa_obj = entry->robj;
 
 		total_size += amdgpu_bo_size(entry->robj);
 		trace_amdgpu_bo_list_set(list, entry->robj);
 	}
 
-	amdgpu_bo_list_for_each_entry(e, list)
-		amdgpu_bo_unref(&list->array[i].robj);
-
-	kvfree(list->array);
-
-	list->gds_obj = gds_obj;
-	list->gws_obj = gws_obj;
-	list->oa_obj = oa_obj;
 	list->first_userptr = first_userptr;
-	list->array = array;
 	list->num_entries = num_entries;
 
 	trace_amdgpu_cs_bo_status(list->num_entries, total_size);
+
+	*result = list;
 	return 0;
 
 error_free:
 	while (i--)
 		amdgpu_bo_unref(&array[i].robj);
-	kvfree(array);
+	kvfree(list);
 	return r;
+
+}
+
+static void amdgpu_bo_list_destroy(struct amdgpu_fpriv *fpriv, int id)
+{
+	struct amdgpu_bo_list *list;
+
+	mutex_lock(&fpriv->bo_list_lock);
+	list = idr_remove(&fpriv->bo_list_handles, id);
+	mutex_unlock(&fpriv->bo_list_lock);
+	if (list)
+		kref_put(&list->refcount, amdgpu_bo_list_free);
 }
 
 int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
@@ -229,7 +205,7 @@ void amdgpu_bo_list_get_list(struct amdgpu_bo_list *list,
 
 void amdgpu_bo_list_put(struct amdgpu_bo_list *list)
 {
-	kref_put(&list->refcount, amdgpu_bo_list_release_rcu);
+	kref_put(&list->refcount, amdgpu_bo_list_free);
 }
 
 int amdgpu_bo_create_list_entry_array(struct drm_amdgpu_bo_list_in *in,
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
index 3d77abfcd4a6..61b089768e1c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bo_list.h
@@ -48,7 +48,6 @@ struct amdgpu_bo_list {
 	struct amdgpu_bo *oa_obj;
 	unsigned first_userptr;
 	unsigned num_entries;
-	struct amdgpu_bo_list_entry *array;
 };
 
 int amdgpu_bo_list_get(struct amdgpu_fpriv *fpriv, int id,
@@ -65,14 +64,22 @@ int amdgpu_bo_list_create(struct amdgpu_device *adev,
 				 unsigned num_entries,
 				 struct amdgpu_bo_list **list);
 
+static inline struct amdgpu_bo_list_entry *
+amdgpu_bo_list_array_entry(struct amdgpu_bo_list *list, unsigned index)
+{
+	struct amdgpu_bo_list_entry *array = (void *)&list[1];
+
+	return &array[index];
+}
+
 #define amdgpu_bo_list_for_each_entry(e, list) \
-	for (e = &(list)->array[0]; \
-	     e != &(list)->array[(list)->num_entries]; \
+	for (e = amdgpu_bo_list_array_entry(list, 0); \
+	     e != amdgpu_bo_list_array_entry(list, (list)->num_entries); \
 	     ++e)
 
 #define amdgpu_bo_list_for_each_userptr_entry(e, list) \
-	for (e = &(list)->array[(list)->first_userptr]; \
-	     e != &(list)->array[(list)->num_entries]; \
+	for (e = amdgpu_bo_list_array_entry(list, (list)->first_userptr); \
+	     e != amdgpu_bo_list_array_entry(list, (list)->num_entries); \
 	     ++e)
 
 #endif
-- 
cgit v1.2.3


From 4a102ad4ba0daf886dcf0927ce2a7f6c3b3a615c Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 16:44:14 +0200
Subject: drm/amdgpu: create an empty bo_list if no handle is provided
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead of having extra handling just create an empty bo_list when no
handle is provided.

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Chunming  Zhou <david1.zhou@amd.com>
Reviewed-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c | 111 ++++++++++++++-------------------
 1 file changed, 46 insertions(+), 65 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
index 1d7292ab2b62..502b94fb116a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -561,6 +561,7 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 				union drm_amdgpu_cs *cs)
 {
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+	struct amdgpu_vm *vm = &fpriv->vm;
 	struct amdgpu_bo_list_entry *e;
 	struct list_head duplicates;
 	struct amdgpu_bo *gds;
@@ -580,13 +581,17 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 				       &p->bo_list);
 		if (r)
 			return r;
+	} else if (!p->bo_list) {
+		/* Create a empty bo_list when no handle is provided */
+		r = amdgpu_bo_list_create(p->adev, p->filp, NULL, 0,
+					  &p->bo_list);
+		if (r)
+			return r;
 	}
 
-	if (p->bo_list) {
-		amdgpu_bo_list_get_list(p->bo_list, &p->validated);
-		if (p->bo_list->first_userptr != p->bo_list->num_entries)
-			p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
-	}
+	amdgpu_bo_list_get_list(p->bo_list, &p->validated);
+	if (p->bo_list->first_userptr != p->bo_list->num_entries)
+		p->mn = amdgpu_mn_get(p->adev, AMDGPU_MN_TYPE_GFX);
 
 	INIT_LIST_HEAD(&duplicates);
 	amdgpu_vm_get_pd_bo(&fpriv->vm, &p->validated, &p->vm_pd);
@@ -605,10 +610,6 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 			goto error_free_pages;
 		}
 
-		/* Without a BO list we don't have userptr BOs */
-		if (!p->bo_list)
-			break;
-
 		INIT_LIST_HEAD(&need_pages);
 		amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
 			struct amdgpu_bo *bo = e->robj;
@@ -703,21 +704,12 @@ static int amdgpu_cs_parser_bos(struct amdgpu_cs_parser *p,
 	amdgpu_cs_report_moved_bytes(p->adev, p->bytes_moved,
 				     p->bytes_moved_vis);
 
-	if (p->bo_list) {
-		struct amdgpu_vm *vm = &fpriv->vm;
-		struct amdgpu_bo_list_entry *e;
+	gds = p->bo_list->gds_obj;
+	gws = p->bo_list->gws_obj;
+	oa = p->bo_list->oa_obj;
 
-		gds = p->bo_list->gds_obj;
-		gws = p->bo_list->gws_obj;
-		oa = p->bo_list->oa_obj;
-
-		amdgpu_bo_list_for_each_entry(e, p->bo_list)
-			e->bo_va = amdgpu_vm_bo_find(vm, e->robj);
-	} else {
-		gds = p->adev->gds.gds_gfx_bo;
-		gws = p->adev->gds.gws_gfx_bo;
-		oa = p->adev->gds.oa_gfx_bo;
-	}
+	amdgpu_bo_list_for_each_entry(e, p->bo_list)
+		e->bo_va = amdgpu_vm_bo_find(vm, e->robj);
 
 	if (gds) {
 		p->job->gds_base = amdgpu_bo_gpu_offset(gds);
@@ -745,15 +737,13 @@ error_validate:
 
 error_free_pages:
 
-	if (p->bo_list) {
-		amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
-			if (!e->user_pages)
-				continue;
+	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+		if (!e->user_pages)
+			continue;
 
-			release_pages(e->user_pages,
-				      e->robj->tbo.ttm->num_pages);
-			kvfree(e->user_pages);
-		}
+		release_pages(e->user_pages,
+			      e->robj->tbo.ttm->num_pages);
+		kvfree(e->user_pages);
 	}
 
 	return r;
@@ -815,9 +805,10 @@ static void amdgpu_cs_parser_fini(struct amdgpu_cs_parser *parser, int error,
 
 static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 {
-	struct amdgpu_device *adev = p->adev;
 	struct amdgpu_fpriv *fpriv = p->filp->driver_priv;
+	struct amdgpu_device *adev = p->adev;
 	struct amdgpu_vm *vm = &fpriv->vm;
+	struct amdgpu_bo_list_entry *e;
 	struct amdgpu_bo_va *bo_va;
 	struct amdgpu_bo *bo;
 	int r;
@@ -850,31 +841,26 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 			return r;
 	}
 
-	if (p->bo_list) {
-		struct amdgpu_bo_list_entry *e;
-
-		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
-			struct dma_fence *f;
-
-			/* ignore duplicates */
-			bo = e->robj;
-			if (!bo)
-				continue;
+	amdgpu_bo_list_for_each_entry(e, p->bo_list) {
+		struct dma_fence *f;
 
-			bo_va = e->bo_va;
-			if (bo_va == NULL)
-				continue;
+		/* ignore duplicates */
+		bo = e->robj;
+		if (!bo)
+			continue;
 
-			r = amdgpu_vm_bo_update(adev, bo_va, false);
-			if (r)
-				return r;
+		bo_va = e->bo_va;
+		if (bo_va == NULL)
+			continue;
 
-			f = bo_va->last_pt_update;
-			r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
-			if (r)
-				return r;
-		}
+		r = amdgpu_vm_bo_update(adev, bo_va, false);
+		if (r)
+			return r;
 
+		f = bo_va->last_pt_update;
+		r = amdgpu_sync_fence(adev, &p->job->sync, f, false);
+		if (r)
+			return r;
 	}
 
 	r = amdgpu_vm_handle_moved(adev, vm);
@@ -889,9 +875,7 @@ static int amdgpu_bo_vm_update_pte(struct amdgpu_cs_parser *p)
 	if (r)
 		return r;
 
-	if (amdgpu_vm_debug && p->bo_list) {
-		struct amdgpu_bo_list_entry *e;
-
+	if (amdgpu_vm_debug) {
 		/* Invalidate all BOs to test for userspace bugs */
 		amdgpu_bo_list_for_each_entry(e, p->bo_list) {
 			/* ignore duplicates */
@@ -1217,22 +1201,19 @@ static int amdgpu_cs_submit(struct amdgpu_cs_parser *p,
 	struct amdgpu_ring *ring = p->ring;
 	struct drm_sched_entity *entity = &p->ctx->rings[ring->idx].entity;
 	enum drm_sched_priority priority;
+	struct amdgpu_bo_list_entry *e;
 	struct amdgpu_job *job;
 	uint64_t seq;
 
 	int r;
 
 	amdgpu_mn_lock(p->mn);
-	if (p->bo_list) {
-		struct amdgpu_bo_list_entry *e;
+	amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
+		struct amdgpu_bo *bo = e->robj;
 
-		amdgpu_bo_list_for_each_userptr_entry(e, p->bo_list) {
-			struct amdgpu_bo *bo = e->robj;
-
-			if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm)) {
-				amdgpu_mn_unlock(p->mn);
-				return -ERESTARTSYS;
-			}
+		if (amdgpu_ttm_tt_userptr_needs_pages(bo->tbo.ttm)) {
+			amdgpu_mn_unlock(p->mn);
+			return -ERESTARTSYS;
 		}
 	}
 
-- 
cgit v1.2.3


From 43bce41cf48eb51eab5ad9e0d40ed382a7bb61d7 Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Thu, 26 Jul 2018 13:43:49 +0200
Subject: drm/scheduler: only kill entity if last user is killed v2
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Note which task is using the entity and only kill it if the last user of
the entity is killed. This should prevent problems when entities are leaked to
child processes.

v2: add missing kernel doc

Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
Acked-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 6 +++++-
 include/drm/gpu_scheduler.h               | 2 ++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 3f2fc5e8242a..f563e4fbb4b6 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -275,6 +275,7 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 {
 	struct drm_gpu_scheduler *sched;
+	struct task_struct *last_user;
 	long ret = timeout;
 
 	sched = entity->rq->sched;
@@ -295,7 +296,9 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 
 
 	/* For killed process disable any more IBs enqueue right now */
-	if ((current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
+	last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
+	if ((!last_user || last_user == current->group_leader) &&
+	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
 		drm_sched_entity_set_rq(entity, NULL);
 
 	return ret;
@@ -541,6 +544,7 @@ void drm_sched_entity_push_job(struct drm_sched_job *sched_job,
 
 	trace_drm_sched_job(sched_job, entity);
 
+	WRITE_ONCE(entity->last_user, current->group_leader);
 	first = spsc_queue_push(&entity->job_queue, &sched_job->queue_node);
 
 	/* first job wakes up scheduler */
diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h
index 091b9afcd184..21c648b0b2a1 100644
--- a/include/drm/gpu_scheduler.h
+++ b/include/drm/gpu_scheduler.h
@@ -66,6 +66,7 @@ enum drm_sched_priority {
  * @guilty: points to ctx's guilty.
  * @fini_status: contains the exit status in case the process was signalled.
  * @last_scheduled: points to the finished fence of the last scheduled job.
+ * @last_user: last group leader pushing a job into the entity.
  *
  * Entities will emit jobs in order to their corresponding hardware
  * ring, and the scheduler will alternate between entities based on
@@ -85,6 +86,7 @@ struct drm_sched_entity {
 	struct dma_fence_cb		cb;
 	atomic_t			*guilty;
 	struct dma_fence                *last_scheduled;
+	struct task_struct		*last_user;
 };
 
 /**
-- 
cgit v1.2.3


From a875f58e237a0009c337dd140e4f92a7cffab7af Mon Sep 17 00:00:00 2001
From: Christian König <christian.koenig@amd.com>
Date: Mon, 30 Jul 2018 11:40:06 +0200
Subject: drm/scheduler: stop setting rq to NULL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We removed the redundancy of having an extra scheduler field, so we
can't set the rq to NULL any more or otherwise won't know which
scheduler to use for the cleanup.

Just remove the entity from the scheduling list instead.

Signed-off-by: Christian König <christian.koenig@amd.com>
Acked-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Bug: https://bugs.freedesktop.org/show_bug.cgi?id=107367
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 35 +++++++------------------------
 1 file changed, 8 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index f563e4fbb4b6..1b733229201e 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -198,21 +198,6 @@ int drm_sched_entity_init(struct drm_sched_entity *entity,
 }
 EXPORT_SYMBOL(drm_sched_entity_init);
 
-/**
- * drm_sched_entity_is_initialized - Query if entity is initialized
- *
- * @sched: Pointer to scheduler instance
- * @entity: The pointer to a valid scheduler entity
- *
- * return true if entity is initialized, false otherwise
-*/
-static bool drm_sched_entity_is_initialized(struct drm_gpu_scheduler *sched,
-					    struct drm_sched_entity *entity)
-{
-	return entity->rq != NULL &&
-		entity->rq->sched == sched;
-}
-
 /**
  * drm_sched_entity_is_idle - Check if entity is idle
  *
@@ -224,7 +209,8 @@ static bool drm_sched_entity_is_idle(struct drm_sched_entity *entity)
 {
 	rmb();
 
-	if (!entity->rq || spsc_queue_peek(&entity->job_queue) == NULL)
+	if (list_empty(&entity->list) ||
+	    spsc_queue_peek(&entity->job_queue) == NULL)
 		return true;
 
 	return false;
@@ -279,8 +265,6 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 	long ret = timeout;
 
 	sched = entity->rq->sched;
-	if (!drm_sched_entity_is_initialized(sched, entity))
-		return ret;
 	/**
 	 * The client will not queue more IBs during this fini, consume existing
 	 * queued IBs or discard them on SIGKILL
@@ -299,7 +283,7 @@ long drm_sched_entity_flush(struct drm_sched_entity *entity, long timeout)
 	last_user = cmpxchg(&entity->last_user, current->group_leader, NULL);
 	if ((!last_user || last_user == current->group_leader) &&
 	    (current->flags & PF_EXITING) && (current->exit_code == SIGKILL))
-		drm_sched_entity_set_rq(entity, NULL);
+		drm_sched_rq_remove_entity(entity->rq, entity);
 
 	return ret;
 }
@@ -320,7 +304,7 @@ void drm_sched_entity_fini(struct drm_sched_entity *entity)
 	struct drm_gpu_scheduler *sched;
 
 	sched = entity->rq->sched;
-	drm_sched_entity_set_rq(entity, NULL);
+	drm_sched_rq_remove_entity(entity->rq, entity);
 
 	/* Consumption of existing IBs wasn't completed. Forcefully
 	 * remove them here.
@@ -416,15 +400,12 @@ void drm_sched_entity_set_rq(struct drm_sched_entity *entity,
 	if (entity->rq == rq)
 		return;
 
-	spin_lock(&entity->rq_lock);
-
-	if (entity->rq)
-		drm_sched_rq_remove_entity(entity->rq, entity);
+	BUG_ON(!rq);
 
+	spin_lock(&entity->rq_lock);
+	drm_sched_rq_remove_entity(entity->rq, entity);
 	entity->rq = rq;
-	if (rq)
-		drm_sched_rq_add_entity(rq, entity);
-
+	drm_sched_rq_add_entity(rq, entity);
 	spin_unlock(&entity->rq_lock);
 }
 EXPORT_SYMBOL(drm_sched_entity_set_rq);
-- 
cgit v1.2.3


From 71d5ef11273b3dbdb57be7d2940dcee70007ae84 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 31 Jul 2018 09:12:35 +0200
Subject: drm/amdgpu: Replace ttm_bo_reference with ttm_bo_get
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function ttm_bo_get acquires a reference on a TTM buffer object. The
function's name is more aligned to the Linux kernel convention of naming
ref-counting function _get and _put.

v2:
 * changed prefix to drm/amdgpu

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index 21bfa2d8039e..f7ac9abf9cc1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -825,7 +825,7 @@ struct amdgpu_bo *amdgpu_bo_ref(struct amdgpu_bo *bo)
 	if (bo == NULL)
 		return NULL;
 
-	ttm_bo_reference(&bo->tbo);
+	ttm_bo_get(&bo->tbo);
 	return bo;
 }
 
-- 
cgit v1.2.3


From fea872b279c8cd9433a3c9bb91949643cf645e07 Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 31 Jul 2018 09:12:36 +0200
Subject: drm/amdgpu: Replace ttm_bo_unref with ttm_bo_put
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function ttm_bo_put releases a reference to a TTM buffer object. The
function's name is more aligned to the Linux kernel convention of naming
ref-counting function _get and _put.

A call to ttm_bo_unref takes the address of the TTM BO object's pointer and
clears the pointer's value to NULL. This is not necessary in most cases and
sometimes even worked around by the calling code. A call to ttm_bo_put only
releases the reference without clearing the pointer.

The current behaviour of cleaning the pointer is kept in the calling code,
but should be removed if not required in a later patch.

v2:
 * set prefix to drm/amdgpu

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_object.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
index f7ac9abf9cc1..b0e14a3d54ef 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -843,9 +843,8 @@ void amdgpu_bo_unref(struct amdgpu_bo **bo)
 		return;
 
 	tbo = &((*bo)->tbo);
-	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
+	ttm_bo_put(tbo);
+	*bo = NULL;
 }
 
 /**
-- 
cgit v1.2.3


From 269a8b6e342501fa221a398dd2730b7af7e94a5d Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 31 Jul 2018 08:16:58 +0200
Subject: drm/radeon: Replace ttm_bo_reference with ttm_bo_get
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function ttm_bo_get acquires a reference on a TTM buffer object. The
function's name is more aligned to the Linux kernel convention of naming
ref-counting function _get and _put.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_object.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index edbb4cd519fd..1a9d4f547024 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -307,7 +307,7 @@ struct radeon_bo *radeon_bo_ref(struct radeon_bo *bo)
 	if (bo == NULL)
 		return NULL;
 
-	ttm_bo_reference(&bo->tbo);
+	ttm_bo_get(&bo->tbo);
 	return bo;
 }
 
-- 
cgit v1.2.3


From 77605e43701578892e98a39383071f1a8503ff8f Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 31 Jul 2018 08:16:59 +0200
Subject: drm/radeon: Replace ttm_bo_unref with ttm_bo_put
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function ttm_bo_put releases a reference to a TTM buffer object. The
function's name is more aligned to the Linux kernel convention of naming
ref-counting function _get and _put.

A call to ttm_bo_unref takes the address of the TTM BO object's pointer and
clears the pointer's value to NULL. This is not necessary in most cases and
sometimes even worked around by the calling code. A call to ttm_bo_put only
releases the reference without clearing the pointer.

The current behaviour of cleaning the pointer is kept in the calling code,
but should be removed if not required in a later patch.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/radeon/radeon_object.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/radeon_object.c b/drivers/gpu/drm/radeon/radeon_object.c
index 1a9d4f547024..ba2fd295697f 100644
--- a/drivers/gpu/drm/radeon/radeon_object.c
+++ b/drivers/gpu/drm/radeon/radeon_object.c
@@ -320,9 +320,8 @@ void radeon_bo_unref(struct radeon_bo **bo)
 		return;
 	rdev = (*bo)->rdev;
 	tbo = &((*bo)->tbo);
-	ttm_bo_unref(&tbo);
-	if (tbo == NULL)
-		*bo = NULL;
+	ttm_bo_put(tbo);
+	*bo = NULL;
 }
 
 int radeon_bo_pin_restricted(struct radeon_bo *bo, u32 domain, u64 max_offset,
-- 
cgit v1.2.3


From 7ac7aebe85d3b3b57a58efefcdde2bd5d398550d Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 31 Jul 2018 11:42:54 +0100
Subject: drm/amd/display: add missing void parameter to
 dc_create_transfer_func

Add a missing void parameter to function dc_create_transfer_func, fixes
sparse warning:

warning: non-ANSI function declaration of function 'dc_create_transfer_func'

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_surface.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
index 815dfb50089b..8fb3aefd195c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
@@ -192,7 +192,7 @@ void dc_transfer_func_release(struct dc_transfer_func *tf)
 	kref_put(&tf->refcount, dc_transfer_func_free);
 }
 
-struct dc_transfer_func *dc_create_transfer_func()
+struct dc_transfer_func *dc_create_transfer_func(void)
 {
 	struct dc_transfer_func *tf = kvzalloc(sizeof(*tf), GFP_KERNEL);
 
-- 
cgit v1.2.3


From ddf74e79a54070f277ae520722d3bab7f7a6c67a Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 23 Jul 2018 11:32:32 -0500
Subject: drm/amdgpu/pm: Fix potential Spectre v1

idx can be indirectly controlled by user-space, hence leading to a
potential exploitation of the Spectre variant 1 vulnerability.

This issue was detected with the help of Smatch:

drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c:408 amdgpu_set_pp_force_state()
warn: potential spectre issue 'data.states'

Fix this by sanitizing idx before using it to index data.states

Notice that given that speculation windows are large, the policy is
to kill the speculation on the first load and not worry if it can be
completed with a dependent load/store [1].

[1] https://marc.info/?l=linux-kernel&m=152449131114778&w=2

Cc: stable@vger.kernel.org
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
index 23fc1d32b937..8f98629fbe59 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c
@@ -31,7 +31,7 @@
 #include <linux/power_supply.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
-
+#include <linux/nospec.h>
 
 static int amdgpu_debugfs_pm_init(struct amdgpu_device *adev);
 
@@ -403,6 +403,7 @@ static ssize_t amdgpu_set_pp_force_state(struct device *dev,
 			count = -EINVAL;
 			goto fail;
 		}
+		idx = array_index_nospec(idx, ARRAY_SIZE(data.states));
 
 		amdgpu_dpm_get_pp_num_states(adev, &data);
 		state = data.states[idx];
-- 
cgit v1.2.3


From 546c596cf5491fda1516536e049c6a36836eb884 Mon Sep 17 00:00:00 2001
From: Shunyong Yang <shunyong.yang@hxt-semitech.com>
Date: Wed, 18 Jul 2018 09:40:35 +0800
Subject: PCI: Unify PCI and normal DMA direction definitions

Current DMA direction definitions in pci-dma-compat.h and dma-direction.h
are mirrored in value.  Unify them to enhance readability and avoid
possible inconsistency.

Signed-off-by: Shunyong Yang <shunyong.yang@hxt-semitech.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: Joey Zheng <yu.zheng@hxt-semitech.com>
---
 include/linux/dma-direction.h  | 6 ++----
 include/linux/pci-dma-compat.h | 8 ++++----
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/include/linux/dma-direction.h b/include/linux/dma-direction.h
index 3649a031893a..9c96e30e6a0b 100644
--- a/include/linux/dma-direction.h
+++ b/include/linux/dma-direction.h
@@ -1,14 +1,12 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_DMA_DIRECTION_H
 #define _LINUX_DMA_DIRECTION_H
-/*
- * These definitions mirror those in pci.h, so they can be used
- * interchangeably with their PCI_ counterparts.
- */
+
 enum dma_data_direction {
 	DMA_BIDIRECTIONAL = 0,
 	DMA_TO_DEVICE = 1,
 	DMA_FROM_DEVICE = 2,
 	DMA_NONE = 3,
 };
+
 #endif
diff --git a/include/linux/pci-dma-compat.h b/include/linux/pci-dma-compat.h
index 0dd1a3f7b309..c3f1b44ade29 100644
--- a/include/linux/pci-dma-compat.h
+++ b/include/linux/pci-dma-compat.h
@@ -8,10 +8,10 @@
 #include <linux/dma-mapping.h>
 
 /* This defines the direction arg to the DMA mapping routines. */
-#define PCI_DMA_BIDIRECTIONAL	0
-#define PCI_DMA_TODEVICE	1
-#define PCI_DMA_FROMDEVICE	2
-#define PCI_DMA_NONE		3
+#define PCI_DMA_BIDIRECTIONAL	DMA_BIDIRECTIONAL
+#define PCI_DMA_TODEVICE	DMA_TO_DEVICE
+#define PCI_DMA_FROMDEVICE	DMA_FROM_DEVICE
+#define PCI_DMA_NONE		DMA_NONE
 
 static inline void *
 pci_alloc_consistent(struct pci_dev *hwdev, size_t size,
-- 
cgit v1.2.3


From fb7d7518b0d65955f91c7b875c36eae7694c69bd Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Tue, 31 Jul 2018 16:14:18 +0200
Subject: s390/numa: move initial setup of node_to_cpumask_map

The numa_init_early initcall sets the node_to_cpumask_map[0] to the
full cpu_possible_mask. Unfortunately this early_initcall is too late,
the NUMA setup for numa=emu is done even earlier. The order of calls
is numa_setup() -> emu_update_cpu_topology(), then the early_initcalls(),
followed by sched_init_domains().

Starting with git commit 051f3ca02e46432c0965e8948f00c07d8a2f09c0
"sched/topology: Introduce NUMA identity node sched domain"
the incorrect node_to_cpumask_map[0] really screws up the domain
setup and the kernel panics with the follow oops:

Cc: <stable@vger.kernel.org> # v4.15+
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/numa/numa.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c
index 06a80434cfe6..5bd374491f94 100644
--- a/arch/s390/numa/numa.c
+++ b/arch/s390/numa/numa.c
@@ -134,26 +134,14 @@ void __init numa_setup(void)
 {
 	pr_info("NUMA mode: %s\n", mode->name);
 	nodes_clear(node_possible_map);
+	/* Initially attach all possible CPUs to node 0. */
+	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
 	if (mode->setup)
 		mode->setup();
 	numa_setup_memory();
 	memblock_dump_all();
 }
 
-/*
- * numa_init_early() - Initialization initcall
- *
- * This runs when only one CPU is online and before the first
- * topology update is called for by the scheduler.
- */
-static int __init numa_init_early(void)
-{
-	/* Attach all possible CPUs to node 0 for now. */
-	cpumask_copy(&node_to_cpumask_map[0], cpu_possible_mask);
-	return 0;
-}
-early_initcall(numa_init_early);
-
 /*
  * numa_init_late() - Initialization initcall
  *
-- 
cgit v1.2.3


From 7992c18810e568b95c869b227137a2215702a805 Mon Sep 17 00:00:00 2001
From: Mark Salyzyn <salyzyn@android.com>
Date: Tue, 31 Jul 2018 15:02:13 -0700
Subject: Bluetooth: hidp: buffer overflow in hidp_process_report

CVE-2018-9363

The buffer length is unsigned at all layers, but gets cast to int and
checked in hidp_process_report and can lead to a buffer overflow.
Switch len parameter to unsigned int to resolve issue.

This affects 3.18 and newer kernels.

Signed-off-by: Mark Salyzyn <salyzyn@android.com>
Fixes: a4b1b5877b514b276f0f31efe02388a9c2836728 ("HID: Bluetooth: hidp: make sure input buffers are big enough")
Cc: Marcel Holtmann <marcel@holtmann.org>
Cc: Johan Hedberg <johan.hedberg@gmail.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Cc: linux-bluetooth@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: security@kernel.org
Cc: kernel-team@android.com
Acked-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 net/bluetooth/hidp/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hidp/core.c b/net/bluetooth/hidp/core.c
index 6f3eaf2fb94f..253975cce943 100644
--- a/net/bluetooth/hidp/core.c
+++ b/net/bluetooth/hidp/core.c
@@ -431,8 +431,8 @@ static void hidp_del_timer(struct hidp_session *session)
 		del_timer(&session->timer);
 }
 
-static void hidp_process_report(struct hidp_session *session,
-				int type, const u8 *data, int len, int intr)
+static void hidp_process_report(struct hidp_session *session, int type,
+				const u8 *data, unsigned int len, int intr)
 {
 	if (len > HID_MAX_BUFFER_SIZE)
 		len = HID_MAX_BUFFER_SIZE;
-- 
cgit v1.2.3


From de217c1cca435a39f79cf9cb9279764688fc1cc4 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Mon, 4 Jun 2018 11:46:33 +0300
Subject: mtd: spi-nor: atmel-quadspi: add suspend/resume hooks

Implement suspend/resume hooks.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Reviewed-by: Tudor Ambarus <tudor.ambarus@microchip.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/spi-nor/atmel-quadspi.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
index 6c5708bacad8..ceaaef47f02e 100644
--- a/drivers/mtd/spi-nor/atmel-quadspi.c
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -737,6 +737,26 @@ static int atmel_qspi_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static int __maybe_unused atmel_qspi_suspend(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_disable_unprepare(aq->clk);
+
+	return 0;
+}
+
+static int __maybe_unused atmel_qspi_resume(struct device *dev)
+{
+	struct atmel_qspi *aq = dev_get_drvdata(dev);
+
+	clk_prepare_enable(aq->clk);
+
+	return atmel_qspi_init(aq);
+}
+
+static SIMPLE_DEV_PM_OPS(atmel_qspi_pm_ops, atmel_qspi_suspend,
+			 atmel_qspi_resume);
 
 static const struct of_device_id atmel_qspi_dt_ids[] = {
 	{ .compatible = "atmel,sama5d2-qspi" },
@@ -749,6 +769,7 @@ static struct platform_driver atmel_qspi_driver = {
 	.driver = {
 		.name	= "atmel_qspi",
 		.of_match_table	= atmel_qspi_dt_ids,
+		.pm	= &atmel_qspi_pm_ops,
 	},
 	.probe		= atmel_qspi_probe,
 	.remove		= atmel_qspi_remove,
-- 
cgit v1.2.3


From 5f0d02270d0a7a71dde2d4be3566733bba4d951e Mon Sep 17 00:00:00 2001
From: Benjamin Gaignard <benjamin.gaignard@linaro.org>
Date: Fri, 6 Jul 2018 15:05:25 +0200
Subject: mtd: spi-nor: stm32-quadspi: replace "%p" with "%pK"

The format specifier "%p" can leak kernel addresses.
Use "%pK" instead.

Signed-off-by: Benjamin Gaignard <benjamin.gaignard@st.com>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/spi-nor/stm32-quadspi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mtd/spi-nor/stm32-quadspi.c b/drivers/mtd/spi-nor/stm32-quadspi.c
index 72553506a00b..13e9fc961d3b 100644
--- a/drivers/mtd/spi-nor/stm32-quadspi.c
+++ b/drivers/mtd/spi-nor/stm32-quadspi.c
@@ -355,7 +355,7 @@ static int stm32_qspi_read_reg(struct spi_nor *nor,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "read_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -376,7 +376,7 @@ static int stm32_qspi_write_reg(struct spi_nor *nor, u8 opcode,
 	struct device *dev = flash->qspi->dev;
 	struct stm32_qspi_cmd cmd;
 
-	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%p len:%#x\n", opcode, buf, len);
+	dev_dbg(dev, "write_reg: cmd:%#.2x buf:%pK len:%#x\n", opcode, buf, len);
 
 	memset(&cmd, 0, sizeof(cmd));
 	cmd.opcode = opcode;
@@ -398,7 +398,7 @@ static ssize_t stm32_qspi_read(struct spi_nor *nor, loff_t from, size_t len,
 	struct stm32_qspi_cmd cmd;
 	int err;
 
-	dev_dbg(qspi->dev, "read(%#.2x): buf:%p from:%#.8x len:%#zx\n",
+	dev_dbg(qspi->dev, "read(%#.2x): buf:%pK from:%#.8x len:%#zx\n",
 		nor->read_opcode, buf, (u32)from, len);
 
 	memset(&cmd, 0, sizeof(cmd));
-- 
cgit v1.2.3


From 11edc1133e3023e6452d6934c3f22d65a9c05fe8 Mon Sep 17 00:00:00 2001
From: Rafał Miłecki <rafal@milecki.pl>
Date: Sat, 21 Jul 2018 13:55:10 +0200
Subject: mtd: spi-nor: intel-spi: use mtd_device_register()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This driver doesn't specify parsers so it can use that little helper.

Signed-off-by: Rafał Miłecki <rafal@milecki.pl>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/spi-nor/intel-spi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/spi-nor/intel-spi.c b/drivers/mtd/spi-nor/intel-spi.c
index d2cbfc27826e..af0a22019516 100644
--- a/drivers/mtd/spi-nor/intel-spi.c
+++ b/drivers/mtd/spi-nor/intel-spi.c
@@ -908,7 +908,7 @@ struct intel_spi *intel_spi_probe(struct device *dev,
 	if (!ispi->writeable || !writeable)
 		ispi->nor.mtd.flags &= ~MTD_WRITEABLE;
 
-	ret = mtd_device_parse_register(&ispi->nor.mtd, NULL, NULL, &part, 1);
+	ret = mtd_device_register(&ispi->nor.mtd, &part, 1);
 	if (ret)
 		return ERR_PTR(ret);
 
-- 
cgit v1.2.3


From 261b354caf299a3ff54ba5b35636687c857a0075 Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 20 Jul 2018 11:57:41 +0200
Subject: mtd: spi-nor: atmel-quadspi: Include gpio/consumer.h instead of
 gpio.h

GPIO consumers now include <linux/gpio/consumer.h> instead of
<linux/gpio.h> if they can.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/spi-nor/atmel-quadspi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/spi-nor/atmel-quadspi.c b/drivers/mtd/spi-nor/atmel-quadspi.c
index ceaaef47f02e..820048726b4f 100644
--- a/drivers/mtd/spi-nor/atmel-quadspi.c
+++ b/drivers/mtd/spi-nor/atmel-quadspi.c
@@ -34,7 +34,7 @@
 #include <linux/of.h>
 
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
 
 /* QSPI register offsets */
 #define QSPI_CR      0x0000  /* Control Register */
-- 
cgit v1.2.3


From 3938c0d4cf60477ec776c9a7751226b06bb3c3c0 Mon Sep 17 00:00:00 2001
From: Nicholas Mc Guire <hofrat@osadl.org>
Date: Sat, 21 Jul 2018 16:21:51 +0200
Subject: mtd: spi-nor: cadence-quadspi: fix timeout handling

wait_for_completion_timeout returns an unsigned long not an int, so
let's check its return value directly instead of storing it in ret,
and avoid checking for negative values since this cannot happen.

Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/spi-nor/cadence-quadspi.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/mtd/spi-nor/cadence-quadspi.c b/drivers/mtd/spi-nor/cadence-quadspi.c
index c3f7aaa5d18f..7a19dae717fa 100644
--- a/drivers/mtd/spi-nor/cadence-quadspi.c
+++ b/drivers/mtd/spi-nor/cadence-quadspi.c
@@ -525,15 +525,14 @@ static int cqspi_indirect_read_execute(struct spi_nor *nor, u8 *rxbuf,
 	       reg_base + CQSPI_REG_INDIRECTRD);
 
 	while (remaining > 0) {
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_READ_TIMEOUT_MS));
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+				msecs_to_jiffies(CQSPI_READ_TIMEOUT_MS)))
+			ret = -ETIMEDOUT;
 
 		bytes_to_read = cqspi_get_rd_sram_level(cqspi);
 
-		if (!ret && bytes_to_read == 0) {
+		if (ret && bytes_to_read == 0) {
 			dev_err(nor->dev, "Indirect read timeout, no bytes\n");
-			ret = -ETIMEDOUT;
 			goto failrd;
 		}
 
@@ -649,10 +648,8 @@ static int cqspi_indirect_write_execute(struct spi_nor *nor, loff_t to_addr,
 		iowrite32_rep(cqspi->ahb_base, txbuf,
 			      DIV_ROUND_UP(write_bytes, 4));
 
-		ret = wait_for_completion_timeout(&cqspi->transfer_complete,
-						  msecs_to_jiffies
-						  (CQSPI_TIMEOUT_MS));
-		if (!ret) {
+		if (!wait_for_completion_timeout(&cqspi->transfer_complete,
+					msecs_to_jiffies(CQSPI_TIMEOUT_MS))) {
 			dev_err(nor->dev, "Indirect write timeout\n");
 			ret = -ETIMEDOUT;
 			goto failwr;
@@ -986,9 +983,8 @@ static int cqspi_direct_read_execute(struct spi_nor *nor, u_char *buf,
 	}
 
 	dma_async_issue_pending(cqspi->rx_chan);
-	ret = wait_for_completion_timeout(&cqspi->rx_dma_complete,
-					  msecs_to_jiffies(len));
-	if (ret <= 0) {
+	if (!wait_for_completion_timeout(&cqspi->rx_dma_complete,
+					 msecs_to_jiffies(len))) {
 		dmaengine_terminate_sync(cqspi->rx_chan);
 		dev_err(nor->dev, "DMA wait_for_completion_timeout\n");
 		ret = -ETIMEDOUT;
-- 
cgit v1.2.3


From bb276262e88dae52cc717bb636b7468f66bb234e Mon Sep 17 00:00:00 2001
From: Brian Norris <computersforpeace@gmail.com>
Date: Fri, 27 Jul 2018 11:33:13 -0700
Subject: mtd: spi-nor: only apply reset hacks to broken hardware

Commit 59b356ffd0b0 ("mtd: m25p80: restore the status of SPI flash when
exiting") is the latest from a long history of attempts to add reboot
handling to handle stateful addressing modes on SPI flash. Some prior
mostly-related discussions:

http://lists.infradead.org/pipermail/linux-mtd/2013-March/046343.html
[PATCH 1/3] mtd: m25p80: utilize dedicated 4-byte addressing commands

http://lists.infradead.org/pipermail/barebox/2014-September/020682.html
[RFC] MTD m25p80 3-byte addressing and boot problem

http://lists.infradead.org/pipermail/linux-mtd/2015-February/057683.html
[PATCH 2/2] m25p80: if supported put chip to deep power down if not used

Previously, attempts to add reboot-time software reset handling were
rejected, but the latest attempt was not.

Quick summary of the problem:
Some systems (e.g., boot ROM or bootloader) assume that they can read
initial boot code from their SPI flash using 3-byte addressing. If the
flash is left in 4-byte mode after reset, these systems won't boot. The
above patch provided a shutdown/remove hook to attempt to reset the
addressing mode before we reboot. Notably, this patch misses out on
huge classes of unexpected reboots (e.g., crashes, watchdog resets).

Unfortunately, it is essentially impossible to solve this problem 100%:
if your system doesn't know how to reset the SPI flash to power-on
defaults at initialization time, no amount of software can really rescue
you -- there will always be a chance of some unexpected reset that
leaves your flash in an addressing mode that your boot sequence didn't
expect.

While it is not directly harmful to perform hacks like the
aforementioned commit on all 4-byte addressing flash, a
properly-designed system should not need the hack -- and in fact,
providing this hack may mask the fact that a given system is indeed
broken. So this patch attempts to apply this unsound hack more narrowly,
providing a strong suggestion to developers and system designers that
this is truly a hack. With luck, system designers can catch their errors
early on in their development cycle, rather than applying this hack long
term. But apparently enough systems are out in the wild that we still
have to provide this hack.

Document a new device tree property to denote systems that do not have a
proper hardware (or software) reset mechanism, and apply the hack (with
a loud warning) only in this case.

Signed-off-by: Brian Norris <computersforpeace@gmail.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 .../devicetree/bindings/mtd/jedec,spi-nor.txt          |  9 +++++++++
 drivers/mtd/spi-nor/spi-nor.c                          | 18 ++++++++++++++++--
 include/linux/mtd/spi-nor.h                            |  1 +
 3 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
index 956bb046e599..f03be904d3c2 100644
--- a/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
+++ b/Documentation/devicetree/bindings/mtd/jedec,spi-nor.txt
@@ -69,6 +69,15 @@ Optional properties:
                    all chips and support for it can not be detected at runtime.
                    Refer to your chips' datasheet to check if this is supported
                    by your chip.
+- broken-flash-reset : Some flash devices utilize stateful addressing modes
+		   (e.g., for 32-bit addressing) which need to be managed
+		   carefully by a system. Because these sorts of flash don't
+		   have a standardized software reset command, and because some
+		   systems don't toggle the flash RESET# pin upon system reset
+		   (if the pin even exists at all), there are systems which
+		   cannot reboot properly if the flash is left in the "wrong"
+		   state. This boolean flag can be used on such systems, to
+		   denote the absence of a reliable reset mechanism.
 
 Example:
 
diff --git a/drivers/mtd/spi-nor/spi-nor.c b/drivers/mtd/spi-nor/spi-nor.c
index d9c368c44194..f028277fb1ce 100644
--- a/drivers/mtd/spi-nor/spi-nor.c
+++ b/drivers/mtd/spi-nor/spi-nor.c
@@ -2757,8 +2757,18 @@ static int spi_nor_init(struct spi_nor *nor)
 
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES)) {
+		/*
+		 * If the RESET# pin isn't hooked up properly, or the system
+		 * otherwise doesn't perform a reset command in the boot
+		 * sequence, it's impossible to 100% protect against unexpected
+		 * reboots (e.g., crashes). Warn the user (or hopefully, system
+		 * designer) that this is bad.
+		 */
+		WARN_ONCE(nor->flags & SNOR_F_BROKEN_RESET,
+			  "enabling reset hack; may not recover from unexpected reboots\n");
 		set_4byte(nor, nor->info, 1);
+	}
 
 	return 0;
 }
@@ -2781,7 +2791,8 @@ void spi_nor_restore(struct spi_nor *nor)
 	/* restore the addressing mode */
 	if ((nor->addr_width == 4) &&
 	    (JEDEC_MFR(nor->info) != SNOR_MFR_SPANSION) &&
-	    !(nor->info->flags & SPI_NOR_4B_OPCODES))
+	    !(nor->info->flags & SPI_NOR_4B_OPCODES) &&
+	    (nor->flags & SNOR_F_BROKEN_RESET))
 		set_4byte(nor, nor->info, 0);
 }
 EXPORT_SYMBOL_GPL(spi_nor_restore);
@@ -2911,6 +2922,9 @@ int spi_nor_scan(struct spi_nor *nor, const char *name,
 		params.hwcaps.mask |= SNOR_HWCAPS_READ_FAST;
 	}
 
+	if (of_property_read_bool(np, "broken-flash-reset"))
+		nor->flags |= SNOR_F_BROKEN_RESET;
+
 	/* Some devices cannot do fast-read, no matter what DT tells us */
 	if (info->flags & SPI_NOR_NO_FR)
 		params.hwcaps.mask &= ~SNOR_HWCAPS_READ_FAST;
diff --git a/include/linux/mtd/spi-nor.h b/include/linux/mtd/spi-nor.h
index e60da0d34cc1..c922e97f205a 100644
--- a/include/linux/mtd/spi-nor.h
+++ b/include/linux/mtd/spi-nor.h
@@ -235,6 +235,7 @@ enum spi_nor_option_flags {
 	SNOR_F_S3AN_ADDR_DEFAULT = BIT(3),
 	SNOR_F_READY_XSR_RDY	= BIT(4),
 	SNOR_F_USE_CLSR		= BIT(5),
+	SNOR_F_BROKEN_RESET	= BIT(6),
 };
 
 /**
-- 
cgit v1.2.3


From 64f2cafc3da77da7b176f2cdc3eb3fdb031c639f Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Wed, 1 Aug 2018 00:58:33 +0530
Subject: drm/imx: Convert drm_atomic_helper_suspend/resume()

convert drm_atomic_helper_suspend/resume() to use
drm_mode_config_helper_suspend/resume().

with this conversion, the remaining member of struct
imx_drm_device, state, will be no more useful and it
could be removed forever.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Signed-off-by: Ajit Negi <ajitn.linux@gmail.com>
[p.zabel@pengutronix.de: rebased onto drm-next, updated commit message]
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/drm/imx/imx-drm-core.c | 42 ++------------------------------------
 1 file changed, 2 insertions(+), 40 deletions(-)

diff --git a/drivers/gpu/drm/imx/imx-drm-core.c b/drivers/gpu/drm/imx/imx-drm-core.c
index f0122afcf2a8..5ea0c82f9957 100644
--- a/drivers/gpu/drm/imx/imx-drm-core.c
+++ b/drivers/gpu/drm/imx/imx-drm-core.c
@@ -35,11 +35,6 @@
 
 #define MAX_CRTC	4
 
-struct imx_drm_device {
-	struct drm_device			*drm;
-	struct drm_atomic_state			*state;
-};
-
 #if IS_ENABLED(CONFIG_DRM_FBDEV_EMULATION)
 static int legacyfb_depth = 16;
 module_param(legacyfb_depth, int, 0444);
@@ -218,22 +213,12 @@ static int compare_of(struct device *dev, void *data)
 static int imx_drm_bind(struct device *dev)
 {
 	struct drm_device *drm;
-	struct imx_drm_device *imxdrm;
 	int ret;
 
 	drm = drm_dev_alloc(&imx_drm_driver, dev);
 	if (IS_ERR(drm))
 		return PTR_ERR(drm);
 
-	imxdrm = devm_kzalloc(dev, sizeof(*imxdrm), GFP_KERNEL);
-	if (!imxdrm) {
-		ret = -ENOMEM;
-		goto err_put;
-	}
-
-	imxdrm->drm = drm;
-	drm->dev_private = imxdrm;
-
 	/*
 	 * enable drm irq mode.
 	 * - with irq_enabled = true, we can use the vblank feature.
@@ -305,7 +290,6 @@ err_unbind:
 	component_unbind_all(drm->dev, drm);
 err_kms:
 	drm_mode_config_cleanup(drm);
-err_put:
 	drm_dev_put(drm);
 
 	return ret;
@@ -354,37 +338,15 @@ static int imx_drm_platform_remove(struct platform_device *pdev)
 static int imx_drm_suspend(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct imx_drm_device *imxdrm;
-
-	/* The drm_dev is NULL before .load hook is called */
-	if (drm_dev == NULL)
-		return 0;
-
-	drm_kms_helper_poll_disable(drm_dev);
 
-	imxdrm = drm_dev->dev_private;
-	imxdrm->state = drm_atomic_helper_suspend(drm_dev);
-	if (IS_ERR(imxdrm->state)) {
-		drm_kms_helper_poll_enable(drm_dev);
-		return PTR_ERR(imxdrm->state);
-	}
-
-	return 0;
+	return drm_mode_config_helper_suspend(drm_dev);
 }
 
 static int imx_drm_resume(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
-	struct imx_drm_device *imx_drm;
 
-	if (drm_dev == NULL)
-		return 0;
-
-	imx_drm = drm_dev->dev_private;
-	drm_atomic_helper_resume(drm_dev, imx_drm->state);
-	drm_kms_helper_poll_enable(drm_dev);
-
-	return 0;
+	return drm_mode_config_helper_resume(drm_dev);
 }
 #endif
 
-- 
cgit v1.2.3


From 3d3fe3c05d5a17ebdf55b936c51017c127c0ed44 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 15:31:52 +0200
Subject: mtd: rawnand: allocate dynamically ONFI parameters during detection

Now that it is possible to do dynamic allocations during the
identification phase, convert the onfi_params structure (which is only
needed with ONFI compliant chips) into a pointer that will be allocated
only if needed.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
---
 drivers/mtd/nand/raw/nand_base.c    | 54 +++++++++++++++++++++++--------------
 drivers/mtd/nand/raw/nand_micron.c  |  7 ++---
 drivers/mtd/nand/raw/nand_timings.c | 12 ++++-----
 include/linux/mtd/rawnand.h         |  6 ++---
 4 files changed, 47 insertions(+), 32 deletions(-)

diff --git a/drivers/mtd/nand/raw/nand_base.c b/drivers/mtd/nand/raw/nand_base.c
index 00e80781124a..d527e448ce19 100644
--- a/drivers/mtd/nand/raw/nand_base.c
+++ b/drivers/mtd/nand/raw/nand_base.c
@@ -5151,6 +5151,8 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 {
 	struct mtd_info *mtd = nand_to_mtd(chip);
 	struct nand_onfi_params *p;
+	struct onfi_params *onfi;
+	int onfi_version = 0;
 	char id[4];
 	int i, ret, val;
 
@@ -5206,21 +5208,19 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 	/* Check version */
 	val = le16_to_cpu(p->revision);
 	if (val & ONFI_VERSION_2_3)
-		chip->parameters.onfi.version = 23;
+		onfi_version = 23;
 	else if (val & ONFI_VERSION_2_2)
-		chip->parameters.onfi.version = 22;
+		onfi_version = 22;
 	else if (val & ONFI_VERSION_2_1)
-		chip->parameters.onfi.version = 21;
+		onfi_version = 21;
 	else if (val & ONFI_VERSION_2_0)
-		chip->parameters.onfi.version = 20;
+		onfi_version = 20;
 	else if (val & ONFI_VERSION_1_0)
-		chip->parameters.onfi.version = 10;
+		onfi_version = 10;
 
-	if (!chip->parameters.onfi.version) {
+	if (!onfi_version) {
 		pr_info("unsupported ONFI version: %d\n", val);
 		goto free_onfi_param_page;
-	} else {
-		ret = 1;
 	}
 
 	sanitize_string(p->manufacturer, sizeof(p->manufacturer));
@@ -5257,7 +5257,7 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 	if (p->ecc_bits != 0xff) {
 		chip->ecc_strength_ds = p->ecc_bits;
 		chip->ecc_step_ds = 512;
-	} else if (chip->parameters.onfi.version >= 21 &&
+	} else if (onfi_version >= 21 &&
 		(le16_to_cpu(p->features) & ONFI_FEATURE_EXT_PARAM_PAGE)) {
 
 		/*
@@ -5284,19 +5284,33 @@ static int nand_flash_detect_onfi(struct nand_chip *chip)
 		bitmap_set(chip->parameters.set_feature_list,
 			   ONFI_FEATURE_ADDR_TIMING_MODE, 1);
 	}
-	chip->parameters.onfi.tPROG = le16_to_cpu(p->t_prog);
-	chip->parameters.onfi.tBERS = le16_to_cpu(p->t_bers);
-	chip->parameters.onfi.tR = le16_to_cpu(p->t_r);
-	chip->parameters.onfi.tCCS = le16_to_cpu(p->t_ccs);
-	chip->parameters.onfi.async_timing_mode =
-		le16_to_cpu(p->async_timing_mode);
-	chip->parameters.onfi.vendor_revision =
-		le16_to_cpu(p->vendor_revision);
-	memcpy(chip->parameters.onfi.vendor, p->vendor,
-	       sizeof(p->vendor));
 
+	onfi = kzalloc(sizeof(*onfi), GFP_KERNEL);
+	if (!onfi) {
+		ret = -ENOMEM;
+		goto free_model;
+	}
+
+	onfi->version = onfi_version;
+	onfi->tPROG = le16_to_cpu(p->t_prog);
+	onfi->tBERS = le16_to_cpu(p->t_bers);
+	onfi->tR = le16_to_cpu(p->t_r);
+	onfi->tCCS = le16_to_cpu(p->t_ccs);
+	onfi->async_timing_mode = le16_to_cpu(p->async_timing_mode);
+	onfi->vendor_revision = le16_to_cpu(p->vendor_revision);
+	memcpy(onfi->vendor, p->vendor, sizeof(p->vendor));
+	chip->parameters.onfi = onfi;
+
+	/* Identification done, free the full ONFI parameter page and exit */
+	kfree(p);
+
+	return 1;
+
+free_model:
+	kfree(chip->parameters.model);
 free_onfi_param_page:
 	kfree(p);
+
 	return ret;
 }
 
@@ -5693,7 +5707,6 @@ static int nand_detect(struct nand_chip *chip, struct nand_flash_dev *type)
 		}
 	}
 
-	chip->parameters.onfi.version = 0;
 	if (!type->name || !type->pagesize) {
 		/* Check if the chip is ONFI compliant */
 		ret = nand_flash_detect_onfi(chip);
@@ -6031,6 +6044,7 @@ static int nand_scan_ident(struct mtd_info *mtd, int maxchips,
 static void nand_scan_ident_cleanup(struct nand_chip *chip)
 {
 	kfree(chip->parameters.model);
+	kfree(chip->parameters.onfi);
 }
 
 static int nand_set_ecc_soft_ops(struct mtd_info *mtd)
diff --git a/drivers/mtd/nand/raw/nand_micron.c b/drivers/mtd/nand/raw/nand_micron.c
index 656947d91841..f5dc0a7a2456 100644
--- a/drivers/mtd/nand/raw/nand_micron.c
+++ b/drivers/mtd/nand/raw/nand_micron.c
@@ -88,9 +88,10 @@ static int micron_nand_setup_read_retry(struct mtd_info *mtd, int retry_mode)
 static int micron_nand_onfi_init(struct nand_chip *chip)
 {
 	struct nand_parameters *p = &chip->parameters;
-	struct nand_onfi_vendor_micron *micron = (void *)p->onfi.vendor;
 
-	if (chip->parameters.onfi.version && p->onfi.vendor_revision) {
+	if (p->onfi) {
+		struct nand_onfi_vendor_micron *micron = (void *)p->onfi->vendor;
+
 		chip->read_retries = micron->read_retry_options;
 		chip->setup_read_retry = micron_nand_setup_read_retry;
 	}
@@ -382,7 +383,7 @@ static int micron_supports_on_die_ecc(struct nand_chip *chip)
 	u8 id[5];
 	int ret;
 
-	if (!chip->parameters.onfi.version)
+	if (!chip->parameters.onfi)
 		return MICRON_ON_DIE_UNSUPPORTED;
 
 	if (chip->bits_per_cell != 1)
diff --git a/drivers/mtd/nand/raw/nand_timings.c b/drivers/mtd/nand/raw/nand_timings.c
index 9bb599106a31..ebc7b5f76f77 100644
--- a/drivers/mtd/nand/raw/nand_timings.c
+++ b/drivers/mtd/nand/raw/nand_timings.c
@@ -294,6 +294,7 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 			     int timing_mode)
 {
 	struct nand_data_interface *iface = &chip->data_interface;
+	struct onfi_params *onfi = chip->parameters.onfi;
 
 	if (type != NAND_SDR_IFACE)
 		return -EINVAL;
@@ -308,17 +309,16 @@ int onfi_fill_data_interface(struct nand_chip *chip,
 	 * tPROG, tBERS, tR and tCCS.
 	 * These information are part of the ONFI parameter page.
 	 */
-	if (chip->parameters.onfi.version) {
-		struct nand_parameters *params = &chip->parameters;
+	if (onfi) {
 		struct nand_sdr_timings *timings = &iface->timings.sdr;
 
 		/* microseconds -> picoseconds */
-		timings->tPROG_max = 1000000ULL * params->onfi.tPROG;
-		timings->tBERS_max = 1000000ULL * params->onfi.tBERS;
-		timings->tR_max = 1000000ULL * params->onfi.tR;
+		timings->tPROG_max = 1000000ULL * onfi->tPROG;
+		timings->tBERS_max = 1000000ULL * onfi->tBERS;
+		timings->tR_max = 1000000ULL * onfi->tR;
 
 		/* nanoseconds -> picoseconds */
-		timings->tCCS_min = 1000UL * params->onfi.tCCS;
+		timings->tCCS_min = 1000UL * onfi->tCCS;
 	} else {
 		struct nand_sdr_timings *timings = &iface->timings.sdr;
 		/*
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 099fa166569a..efb2345359bb 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -482,7 +482,7 @@ struct nand_parameters {
 	DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER);
 
 	/* ONFI parameters */
-	struct onfi_params onfi;
+	struct onfi_params *onfi;
 };
 
 /* The maximum expected count of bytes in the NAND ID sequence */
@@ -1618,10 +1618,10 @@ struct platform_nand_data {
 /* return the supported asynchronous timing mode. */
 static inline int onfi_get_async_timing_mode(struct nand_chip *chip)
 {
-	if (!chip->parameters.onfi.version)
+	if (!chip->parameters.onfi)
 		return ONFI_TIMING_MODE_UNKNOWN;
 
-	return chip->parameters.onfi.async_timing_mode;
+	return chip->parameters.onfi->async_timing_mode;
 }
 
 int onfi_fill_data_interface(struct nand_chip *chip,
-- 
cgit v1.2.3


From ed128e8b757b4e759e5585df720888b30a7f2196 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 25 Jul 2018 16:56:28 +0200
Subject: MAINTAINERS: drop Wenyou Yang from Atmel NAND driver support

Mails to wenyou.yang@microchip.com are not deliverable.
Drop him as Microchip/Atmel NAND controller driver maintainer.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 63700cefbf56..418e7b966e07 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9345,7 +9345,6 @@ F:	drivers/media/platform/atmel/atmel-isc-regs.h
 F:	devicetree/bindings/media/atmel-isc.txt
 
 MICROCHIP / ATMEL NAND DRIVER
-M:	Wenyou Yang <wenyou.yang@microchip.com>
 M:	Josh Wu <rainyfeeling@outlook.com>
 L:	linux-mtd@lists.infradead.org
 S:	Supported
-- 
cgit v1.2.3


From 4dcd5c2781f3c5c7851800649047658956d590af Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Wed, 1 Aug 2018 16:29:11 +0900
Subject: spi: add DT bindings for UniPhier SPI controller

Add DT bindings for SPI controller implemented in UniPhier SoCs.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Keiji Hayashibara <hayashibara.keiji@socionext.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/spi/spi-uniphier.txt       | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/spi/spi-uniphier.txt

diff --git a/Documentation/devicetree/bindings/spi/spi-uniphier.txt b/Documentation/devicetree/bindings/spi/spi-uniphier.txt
new file mode 100644
index 000000000000..504a4ecfc7b1
--- /dev/null
+++ b/Documentation/devicetree/bindings/spi/spi-uniphier.txt
@@ -0,0 +1,22 @@
+Socionext UniPhier SPI controller driver
+
+UniPhier SoCs have SCSSI which supports SPI single channel.
+
+Required properties:
+ - compatible: should be "socionext,uniphier-scssi"
+ - reg: address and length of the spi master registers
+ - #address-cells: must be <1>, see spi-bus.txt
+ - #size-cells: must be <0>, see spi-bus.txt
+ - clocks: A phandle to the clock for the device.
+ - resets: A phandle to the reset control for the device.
+
+Example:
+
+spi0: spi@54006000 {
+	compatible = "socionext,uniphier-scssi";
+	reg = <0x54006000 0x100>;
+	#address-cells = <1>;
+	#size-cells = <0>;
+	clocks = <&peri_clk 11>;
+	resets = <&peri_rst 11>;
+};
-- 
cgit v1.2.3


From 5ba155a4d4cc8e4cdd3db6df7d03271a3bd91177 Mon Sep 17 00:00:00 2001
From: Keiji Hayashibara <hayashibara.keiji@socionext.com>
Date: Wed, 1 Aug 2018 16:29:12 +0900
Subject: spi: add SPI controller driver for UniPhier SoC

Add SPI controller driver implemented in Socionext UniPhier SoCs.

UniPhier SoCs have two types SPI controllers; SCSSI supports a
single channel, and MCSSI supports multiple channels.
This driver supports SCSSI only.

This controller has 32bit TX/RX FIFO with depth of eight entry,
and supports the SPI master mode only.

This commit is implemented in PIO transfer mode, not DMA transfer.

Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Signed-off-by: Keiji Hayashibara <hayashibara.keiji@socionext.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/Kconfig        |  13 ++
 drivers/spi/Makefile       |   1 +
 drivers/spi/spi-uniphier.c | 525 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 539 insertions(+)
 create mode 100644 drivers/spi/spi-uniphier.c

diff --git a/drivers/spi/Kconfig b/drivers/spi/Kconfig
index ad5d68e1dab7..671d078349cc 100644
--- a/drivers/spi/Kconfig
+++ b/drivers/spi/Kconfig
@@ -688,6 +688,19 @@ config SPI_TXX9
 	help
 	  SPI driver for Toshiba TXx9 MIPS SoCs
 
+config SPI_UNIPHIER
+	tristate "Socionext UniPhier SPI Controller"
+	depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF
+	help
+	  This enables a driver for the Socionext UniPhier SoC SCSSI SPI controller.
+
+	  UniPhier SoCs have SCSSI and MCSSI SPI controllers.
+	  Every UniPhier SoC has SCSSI which supports single channel.
+	  Older UniPhier Pro4/Pro5 also has MCSSI which support multiple channels.
+	  This driver supports SCSSI only.
+
+	  If your SoC supports SCSSI, say Y here.
+
 config SPI_XCOMM
 	tristate "Analog Devices AD-FMCOMMS1-EBZ SPI-I2C-bridge driver"
 	depends on I2C
diff --git a/drivers/spi/Makefile b/drivers/spi/Makefile
index cb1f4378b87c..a90d55970036 100644
--- a/drivers/spi/Makefile
+++ b/drivers/spi/Makefile
@@ -101,6 +101,7 @@ spi-thunderx-objs			:= spi-cavium.o spi-cavium-thunderx.o
 obj-$(CONFIG_SPI_THUNDERX)		+= spi-thunderx.o
 obj-$(CONFIG_SPI_TOPCLIFF_PCH)		+= spi-topcliff-pch.o
 obj-$(CONFIG_SPI_TXX9)			+= spi-txx9.o
+obj-$(CONFIG_SPI_UNIPHIER)		+= spi-uniphier.o
 obj-$(CONFIG_SPI_XCOMM)		+= spi-xcomm.o
 obj-$(CONFIG_SPI_XILINX)		+= spi-xilinx.o
 obj-$(CONFIG_SPI_XLP)			+= spi-xlp.o
diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c
new file mode 100644
index 000000000000..089985465890
--- /dev/null
+++ b/drivers/spi/spi-uniphier.c
@@ -0,0 +1,525 @@
+// SPDX-License-Identifier: GPL-2.0
+// spi-uniphier.c - Socionext UniPhier SPI controller driver
+// Copyright 2012      Panasonic Corporation
+// Copyright 2016-2018 Socionext Inc.
+
+#include <linux/kernel.h>
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/spi/spi.h>
+
+#include <asm/unaligned.h>
+
+#define SSI_TIMEOUT_MS		2000
+#define SSI_MAX_CLK_DIVIDER	254
+#define SSI_MIN_CLK_DIVIDER	4
+
+struct uniphier_spi_priv {
+	void __iomem *base;
+	struct clk *clk;
+	struct spi_master *master;
+	struct completion xfer_done;
+
+	int error;
+	unsigned int tx_bytes;
+	unsigned int rx_bytes;
+	const u8 *tx_buf;
+	u8 *rx_buf;
+
+	bool is_save_param;
+	u8 bits_per_word;
+	u16 mode;
+	u32 speed_hz;
+};
+
+#define SSI_CTL			0x00
+#define   SSI_CTL_EN		BIT(0)
+
+#define SSI_CKS			0x04
+#define   SSI_CKS_CKRAT_MASK	GENMASK(7, 0)
+#define   SSI_CKS_CKPHS		BIT(14)
+#define   SSI_CKS_CKINIT	BIT(13)
+#define   SSI_CKS_CKDLY		BIT(12)
+
+#define SSI_TXWDS		0x08
+#define   SSI_TXWDS_WDLEN_MASK	GENMASK(13, 8)
+#define   SSI_TXWDS_TDTF_MASK	GENMASK(7, 6)
+#define   SSI_TXWDS_DTLEN_MASK	GENMASK(5, 0)
+
+#define SSI_RXWDS		0x0c
+#define   SSI_RXWDS_DTLEN_MASK	GENMASK(5, 0)
+
+#define SSI_FPS			0x10
+#define   SSI_FPS_FSPOL		BIT(15)
+#define   SSI_FPS_FSTRT		BIT(14)
+
+#define SSI_SR			0x14
+#define   SSI_SR_RNE		BIT(0)
+
+#define SSI_IE			0x18
+#define   SSI_IE_RCIE		BIT(3)
+#define   SSI_IE_RORIE		BIT(0)
+
+#define SSI_IS			0x1c
+#define   SSI_IS_RXRS		BIT(9)
+#define   SSI_IS_RCID		BIT(3)
+#define   SSI_IS_RORID		BIT(0)
+
+#define SSI_IC			0x1c
+#define   SSI_IC_TCIC		BIT(4)
+#define   SSI_IC_RCIC		BIT(3)
+#define   SSI_IC_RORIC		BIT(0)
+
+#define SSI_FC			0x20
+#define   SSI_FC_TXFFL		BIT(12)
+#define   SSI_FC_TXFTH_MASK	GENMASK(11, 8)
+#define   SSI_FC_RXFFL		BIT(4)
+#define   SSI_FC_RXFTH_MASK	GENMASK(3, 0)
+
+#define SSI_TXDR		0x24
+#define SSI_RXDR		0x24
+
+#define SSI_FIFO_DEPTH		8U
+
+static inline unsigned int bytes_per_word(unsigned int bits)
+{
+	return bits <= 8 ? 1 : (bits <= 16 ? 2 : 4);
+}
+
+static inline void uniphier_spi_irq_enable(struct spi_device *spi, u32 mask)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_IE);
+	val |= mask;
+	writel(val, priv->base + SSI_IE);
+}
+
+static inline void uniphier_spi_irq_disable(struct spi_device *spi, u32 mask)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_IE);
+	val &= ~mask;
+	writel(val, priv->base + SSI_IE);
+}
+
+static void uniphier_spi_set_mode(struct spi_device *spi)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val1, val2;
+
+	/*
+	 * clock setting
+	 * CKPHS    capture timing. 0:rising edge, 1:falling edge
+	 * CKINIT   clock initial level. 0:low, 1:high
+	 * CKDLY    clock delay. 0:no delay, 1:delay depending on FSTRT
+	 *          (FSTRT=0: 1 clock, FSTRT=1: 0.5 clock)
+	 *
+	 * frame setting
+	 * FSPOL    frame signal porarity. 0: low, 1: high
+	 * FSTRT    start frame timing
+	 *          0: rising edge of clock, 1: falling edge of clock
+	 */
+	switch (spi->mode & (SPI_CPOL | SPI_CPHA)) {
+	case SPI_MODE_0:
+		/* CKPHS=1, CKINIT=0, CKDLY=1, FSTRT=0 */
+		val1 = SSI_CKS_CKPHS | SSI_CKS_CKDLY;
+		val2 = 0;
+		break;
+	case SPI_MODE_1:
+		/* CKPHS=0, CKINIT=0, CKDLY=0, FSTRT=1 */
+		val1 = 0;
+		val2 = SSI_FPS_FSTRT;
+		break;
+	case SPI_MODE_2:
+		/* CKPHS=0, CKINIT=1, CKDLY=1, FSTRT=1 */
+		val1 = SSI_CKS_CKINIT | SSI_CKS_CKDLY;
+		val2 = SSI_FPS_FSTRT;
+		break;
+	case SPI_MODE_3:
+		/* CKPHS=1, CKINIT=1, CKDLY=0, FSTRT=0 */
+		val1 = SSI_CKS_CKPHS | SSI_CKS_CKINIT;
+		val2 = 0;
+		break;
+	}
+
+	if (!(spi->mode & SPI_CS_HIGH))
+		val2 |= SSI_FPS_FSPOL;
+
+	writel(val1, priv->base + SSI_CKS);
+	writel(val2, priv->base + SSI_FPS);
+
+	val1 = 0;
+	if (spi->mode & SPI_LSB_FIRST)
+		val1 |= FIELD_PREP(SSI_TXWDS_TDTF_MASK, 1);
+	writel(val1, priv->base + SSI_TXWDS);
+	writel(val1, priv->base + SSI_RXWDS);
+}
+
+static void uniphier_spi_set_transfer_size(struct spi_device *spi, int size)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_TXWDS);
+	val &= ~(SSI_TXWDS_WDLEN_MASK | SSI_TXWDS_DTLEN_MASK);
+	val |= FIELD_PREP(SSI_TXWDS_WDLEN_MASK, size);
+	val |= FIELD_PREP(SSI_TXWDS_DTLEN_MASK, size);
+	writel(val, priv->base + SSI_TXWDS);
+
+	val = readl(priv->base + SSI_RXWDS);
+	val &= ~SSI_RXWDS_DTLEN_MASK;
+	val |= FIELD_PREP(SSI_RXWDS_DTLEN_MASK, size);
+	writel(val, priv->base + SSI_RXWDS);
+}
+
+static void uniphier_spi_set_baudrate(struct spi_device *spi,
+				      unsigned int speed)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val, ckdiv;
+
+	/*
+	 * the supported rates are even numbers from 4 to 254. (4,6,8...254)
+	 * round up as we look for equal or less speed
+	 */
+	ckdiv = DIV_ROUND_UP(clk_get_rate(priv->clk), speed);
+	ckdiv = round_up(ckdiv, 2);
+
+	val = readl(priv->base + SSI_CKS);
+	val &= ~SSI_CKS_CKRAT_MASK;
+	val |= ckdiv & SSI_CKS_CKRAT_MASK;
+	writel(val, priv->base + SSI_CKS);
+}
+
+static void uniphier_spi_setup_transfer(struct spi_device *spi,
+				       struct spi_transfer *t)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	priv->error = 0;
+	priv->tx_buf = t->tx_buf;
+	priv->rx_buf = t->rx_buf;
+	priv->tx_bytes = priv->rx_bytes = t->len;
+
+	if (!priv->is_save_param || priv->mode != spi->mode) {
+		uniphier_spi_set_mode(spi);
+		priv->mode = spi->mode;
+	}
+
+	if (!priv->is_save_param || priv->bits_per_word != t->bits_per_word) {
+		uniphier_spi_set_transfer_size(spi, t->bits_per_word);
+		priv->bits_per_word = t->bits_per_word;
+	}
+
+	if (!priv->is_save_param || priv->speed_hz != t->speed_hz) {
+		uniphier_spi_set_baudrate(spi, t->speed_hz);
+		priv->speed_hz = t->speed_hz;
+	}
+
+	if (!priv->is_save_param)
+		priv->is_save_param = true;
+
+	/* reset FIFOs */
+	val = SSI_FC_TXFFL | SSI_FC_RXFFL;
+	writel(val, priv->base + SSI_FC);
+}
+
+static void uniphier_spi_send(struct uniphier_spi_priv *priv)
+{
+	int wsize;
+	u32 val = 0;
+
+	wsize = min(bytes_per_word(priv->bits_per_word), priv->tx_bytes);
+	priv->tx_bytes -= wsize;
+
+	if (priv->tx_buf) {
+		switch (wsize) {
+		case 1:
+			val = *priv->tx_buf;
+			break;
+		case 2:
+			val = get_unaligned_le16(priv->tx_buf);
+			break;
+		case 4:
+			val = get_unaligned_le32(priv->tx_buf);
+			break;
+		}
+
+		priv->tx_buf += wsize;
+	}
+
+	writel(val, priv->base + SSI_TXDR);
+}
+
+static void uniphier_spi_recv(struct uniphier_spi_priv *priv)
+{
+	int rsize;
+	u32 val;
+
+	rsize = min(bytes_per_word(priv->bits_per_word), priv->rx_bytes);
+	priv->rx_bytes -= rsize;
+
+	val = readl(priv->base + SSI_RXDR);
+
+	if (priv->rx_buf) {
+		switch (rsize) {
+		case 1:
+			*priv->rx_buf = val;
+			break;
+		case 2:
+			put_unaligned_le16(val, priv->rx_buf);
+			break;
+		case 4:
+			put_unaligned_le32(val, priv->rx_buf);
+			break;
+		}
+
+		priv->rx_buf += rsize;
+	}
+}
+
+static void uniphier_spi_fill_tx_fifo(struct uniphier_spi_priv *priv)
+{
+	unsigned int tx_count;
+	u32 val;
+
+	tx_count = DIV_ROUND_UP(priv->tx_bytes,
+				bytes_per_word(priv->bits_per_word));
+	tx_count = min(tx_count, SSI_FIFO_DEPTH);
+
+	/* set fifo threshold */
+	val = readl(priv->base + SSI_FC);
+	val &= ~(SSI_FC_TXFTH_MASK | SSI_FC_RXFTH_MASK);
+	val |= FIELD_PREP(SSI_FC_TXFTH_MASK, tx_count);
+	val |= FIELD_PREP(SSI_FC_RXFTH_MASK, tx_count);
+	writel(val, priv->base + SSI_FC);
+
+	while (tx_count--)
+		uniphier_spi_send(priv);
+}
+
+static void uniphier_spi_set_cs(struct spi_device *spi, bool enable)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(spi->master);
+	u32 val;
+
+	val = readl(priv->base + SSI_FPS);
+
+	if (enable)
+		val |= SSI_FPS_FSPOL;
+	else
+		val &= ~SSI_FPS_FSPOL;
+
+	writel(val, priv->base + SSI_FPS);
+}
+
+static int uniphier_spi_transfer_one(struct spi_master *master,
+				     struct spi_device *spi,
+				     struct spi_transfer *t)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+	int status;
+
+	uniphier_spi_setup_transfer(spi, t);
+
+	reinit_completion(&priv->xfer_done);
+
+	uniphier_spi_fill_tx_fifo(priv);
+
+	uniphier_spi_irq_enable(spi, SSI_IE_RCIE | SSI_IE_RORIE);
+
+	status = wait_for_completion_timeout(&priv->xfer_done,
+					     msecs_to_jiffies(SSI_TIMEOUT_MS));
+
+	uniphier_spi_irq_disable(spi, SSI_IE_RCIE | SSI_IE_RORIE);
+
+	if (status < 0)
+		return status;
+
+	return priv->error;
+}
+
+static int uniphier_spi_prepare_transfer_hardware(struct spi_master *master)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+
+	writel(SSI_CTL_EN, priv->base + SSI_CTL);
+
+	return 0;
+}
+
+static int uniphier_spi_unprepare_transfer_hardware(struct spi_master *master)
+{
+	struct uniphier_spi_priv *priv = spi_master_get_devdata(master);
+
+	writel(0, priv->base + SSI_CTL);
+
+	return 0;
+}
+
+static irqreturn_t uniphier_spi_handler(int irq, void *dev_id)
+{
+	struct uniphier_spi_priv *priv = dev_id;
+	u32 val, stat;
+
+	stat = readl(priv->base + SSI_IS);
+	val = SSI_IC_TCIC | SSI_IC_RCIC | SSI_IC_RORIC;
+	writel(val, priv->base + SSI_IC);
+
+	/* rx fifo overrun */
+	if (stat & SSI_IS_RORID) {
+		priv->error = -EIO;
+		goto done;
+	}
+
+	/* rx complete */
+	if ((stat & SSI_IS_RCID) && (stat & SSI_IS_RXRS)) {
+		while ((readl(priv->base + SSI_SR) & SSI_SR_RNE) &&
+				(priv->rx_bytes - priv->tx_bytes) > 0)
+			uniphier_spi_recv(priv);
+
+		if ((readl(priv->base + SSI_SR) & SSI_SR_RNE) ||
+				(priv->rx_bytes != priv->tx_bytes)) {
+			priv->error = -EIO;
+			goto done;
+		} else if (priv->rx_bytes == 0)
+			goto done;
+
+		/* next tx transfer */
+		uniphier_spi_fill_tx_fifo(priv);
+
+		return IRQ_HANDLED;
+	}
+
+	return IRQ_NONE;
+
+done:
+	complete(&priv->xfer_done);
+	return IRQ_HANDLED;
+}
+
+static int uniphier_spi_probe(struct platform_device *pdev)
+{
+	struct uniphier_spi_priv *priv;
+	struct spi_master *master;
+	struct resource *res;
+	unsigned long clk_rate;
+	int irq;
+	int ret;
+
+	master = spi_alloc_master(&pdev->dev, sizeof(*priv));
+	if (!master)
+		return -ENOMEM;
+
+	platform_set_drvdata(pdev, master);
+
+	priv = spi_master_get_devdata(master);
+	priv->master = master;
+	priv->is_save_param = false;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(priv->base)) {
+		ret = PTR_ERR(priv->base);
+		goto out_master_put;
+	}
+
+	priv->clk = devm_clk_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(&pdev->dev, "failed to get clock\n");
+		ret = PTR_ERR(priv->clk);
+		goto out_master_put;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		goto out_master_put;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(&pdev->dev, "failed to get IRQ\n");
+		ret = irq;
+		goto out_disable_clk;
+	}
+
+	ret = devm_request_irq(&pdev->dev, irq, uniphier_spi_handler,
+			       0, "uniphier-spi", priv);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to request IRQ\n");
+		goto out_disable_clk;
+	}
+
+	init_completion(&priv->xfer_done);
+
+	clk_rate = clk_get_rate(priv->clk);
+
+	master->max_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MIN_CLK_DIVIDER);
+	master->min_speed_hz = DIV_ROUND_UP(clk_rate, SSI_MAX_CLK_DIVIDER);
+	master->mode_bits = SPI_CPOL | SPI_CPHA | SPI_CS_HIGH | SPI_LSB_FIRST;
+	master->dev.of_node = pdev->dev.of_node;
+	master->bus_num = pdev->id;
+	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
+
+	master->set_cs = uniphier_spi_set_cs;
+	master->transfer_one = uniphier_spi_transfer_one;
+	master->prepare_transfer_hardware
+				= uniphier_spi_prepare_transfer_hardware;
+	master->unprepare_transfer_hardware
+				= uniphier_spi_unprepare_transfer_hardware;
+	master->num_chipselect = 1;
+
+	ret = devm_spi_register_master(&pdev->dev, master);
+	if (ret)
+		goto out_disable_clk;
+
+	return 0;
+
+out_disable_clk:
+	clk_disable_unprepare(priv->clk);
+
+out_master_put:
+	spi_master_put(master);
+	return ret;
+}
+
+static int uniphier_spi_remove(struct platform_device *pdev)
+{
+	struct uniphier_spi_priv *priv = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(priv->clk);
+
+	return 0;
+}
+
+static const struct of_device_id uniphier_spi_match[] = {
+	{ .compatible = "socionext,uniphier-scssi" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, uniphier_spi_match);
+
+static struct platform_driver uniphier_spi_driver = {
+	.probe = uniphier_spi_probe,
+	.remove = uniphier_spi_remove,
+	.driver = {
+		.name = "uniphier-spi",
+		.of_match_table = uniphier_spi_match,
+	},
+};
+module_platform_driver(uniphier_spi_driver);
+
+MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
+MODULE_AUTHOR("Keiji Hayashibara <hayashibara.keiji@socionext.com>");
+MODULE_DESCRIPTION("Socionext UniPhier SPI controller driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 00bc22e3eea0346b594442331df53d0d1e7104dd Mon Sep 17 00:00:00 2001
From: Rohit kumar <rohitkr@codeaurora.org>
Date: Wed, 1 Aug 2018 14:31:06 +0530
Subject: ASoC: qcom: dt-bindings: Add sdm845 machine bindings

Add devicetree bindings documentation file for SDM845 sound card.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rohit kumar <rohitkr@codeaurora.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../devicetree/bindings/sound/qcom,sdm845.txt      | 80 ++++++++++++++++++++++
 1 file changed, 80 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/sound/qcom,sdm845.txt

diff --git a/Documentation/devicetree/bindings/sound/qcom,sdm845.txt b/Documentation/devicetree/bindings/sound/qcom,sdm845.txt
new file mode 100644
index 000000000000..408c4837e6d5
--- /dev/null
+++ b/Documentation/devicetree/bindings/sound/qcom,sdm845.txt
@@ -0,0 +1,80 @@
+* Qualcomm Technologies Inc. SDM845 ASoC sound card driver
+
+This binding describes the SDM845 sound card, which uses qdsp for audio.
+
+- compatible:
+	Usage: required
+	Value type: <stringlist>
+	Definition: must be "qcom,sdm845-sndcard"
+
+- audio-routing:
+	Usage: Optional
+	Value type: <stringlist>
+	Definition:  A list of the connections between audio components.
+		  Each entry is a pair of strings, the first being the
+		  connection's sink, the second being the connection's
+		  source. Valid names could be power supplies, MicBias
+		  of codec and the jacks on the board.
+
+- model:
+	Usage: required
+	Value type: <stringlist>
+	Definition: The user-visible name of this sound card.
+
+= dailinks
+Each subnode of sndcard represents either a dailink, and subnodes of each
+dailinks would be cpu/codec/platform dais.
+
+- link-name:
+	Usage: required
+	Value type: <string>
+	Definition: User friendly name for dai link
+
+= CPU, PLATFORM, CODEC dais subnodes
+- cpu:
+	Usage: required
+	Value type: <subnode>
+	Definition: cpu dai sub-node
+
+- codec:
+	Usage: required
+	Value type: <subnode>
+	Definition: codec dai sub-node
+
+- platform:
+	Usage: Optional
+	Value type: <subnode>
+	Definition: platform dai sub-node
+
+- sound-dai:
+	Usage: required
+	Value type: <phandle>
+	Definition: dai phandle/s and port of CPU/CODEC/PLATFORM node.
+
+Example:
+
+audio {
+	compatible = "qcom,sdm845-sndcard";
+	model = "sdm845-snd-card";
+	pinctrl-names = "default", "sleep";
+	pinctrl-0 = <&pri_mi2s_active &pri_mi2s_ws_active>;
+	pinctrl-1 = <&pri_mi2s_sleep &pri_mi2s_ws_sleep>;
+
+	mm1-dai-link {
+		link-name = "MultiMedia1";
+		cpu {
+			sound-dai = <&q6asmdai MSM_FRONTEND_DAI_MULTIMEDIA1>;
+		};
+	};
+
+	pri-mi2s-dai-link {
+		link-name = "PRI MI2S Playback";
+		cpu {
+			sound-dai = <&q6afedai PRIMARY_MI2S_RX>;
+		};
+
+		platform {
+			sound-dai = <&q6routing>;
+		};
+	};
+};
-- 
cgit v1.2.3


From 0c901e8cea15ba1e318d8f4342f7dc27a80b5978 Mon Sep 17 00:00:00 2001
From: Rohit kumar <rohitkr@codeaurora.org>
Date: Wed, 1 Aug 2018 14:31:07 +0530
Subject: ASoC: dt-bindings: Update dt binding name for apq8096

Remove qcom prefix from machine driver dt bindings of
apq8096 SoC.

Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Rohit kumar <rohitkr@codeaurora.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 Documentation/devicetree/bindings/sound/qcom,apq8096.txt | 15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
index aa54e49fc8a2..20bc034f6c01 100644
--- a/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
+++ b/Documentation/devicetree/bindings/sound/qcom,apq8096.txt
@@ -7,7 +7,7 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio.
 	Value type: <stringlist>
 	Definition: must be "qcom,apq8096-sndcard"
 
-- qcom,audio-routing:
+- audio-routing:
 	Usage: Optional
 	Value type: <stringlist>
 	Definition:  A list of the connections between audio components.
@@ -49,6 +49,12 @@ This binding describes the APQ8096 sound card, which uses qdsp for audio.
 			"DMIC1"
 			"DMIC2"
 			"DMIC3"
+
+- model:
+	Usage: required
+	Value type: <stringlist>
+	Definition: The user-visible name of this sound card.
+
 = dailinks
 Each subnode of sndcard represents either a dailink, and subnodes of each
 dailinks would be cpu/codec/platform dais.
@@ -79,11 +85,16 @@ dailinks would be cpu/codec/platform dais.
 	Value type: <phandle with arguments>
 	Definition: dai phandle/s and port of CPU/CODEC/PLATFORM node.
 
+Obsolete:
+	qcom,model: String for soundcard name (Use model instead)
+	qcom,audio-routing: A list of the connections between audio components.
+			    (Use audio-routing instead)
+
 Example:
 
 audio {
 	compatible = "qcom,apq8096-sndcard";
-	qcom,model = "DB820c";
+	model = "DB820c";
 
 	mm1-dai-link {
 		link-name = "MultiMedia1";
-- 
cgit v1.2.3


From c25e295cd77b37903ddc9ee27384e17aad08f27c Mon Sep 17 00:00:00 2001
From: Rohit kumar <rohitkr@codeaurora.org>
Date: Wed, 1 Aug 2018 14:31:08 +0530
Subject: ASoC: qcom: Add support to parse common audio device nodes

This adds support to parse cpu, platform and codec
device nodes and add them in dai-links. Also, update
apq8096 machine driver to use the common API.

Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Rohit kumar <rohitkr@codeaurora.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/Makefile  |   2 +-
 sound/soc/qcom/apq8096.c | 111 +++++-----------------------------------------
 sound/soc/qcom/common.c  | 112 +++++++++++++++++++++++++++++++++++++++++++++++
 sound/soc/qcom/common.h  |  12 +++++
 4 files changed, 136 insertions(+), 101 deletions(-)
 create mode 100644 sound/soc/qcom/common.c
 create mode 100644 sound/soc/qcom/common.h

diff --git a/sound/soc/qcom/Makefile b/sound/soc/qcom/Makefile
index 206945bb9ba1..fefecc072265 100644
--- a/sound/soc/qcom/Makefile
+++ b/sound/soc/qcom/Makefile
@@ -13,7 +13,7 @@ obj-$(CONFIG_SND_SOC_LPASS_APQ8016) += snd-soc-lpass-apq8016.o
 # Machine
 snd-soc-storm-objs := storm.o
 snd-soc-apq8016-sbc-objs := apq8016_sbc.o
-snd-soc-apq8096-objs := apq8096.o
+snd-soc-apq8096-objs := apq8096.o common.o
 
 obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
 obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index a56156281c8d..1e4a90d59228 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -9,6 +9,7 @@
 #include <sound/soc.h>
 #include <sound/soc-dapm.h>
 #include <sound/pcm.h>
+#include "common.h"
 
 static int apq8096_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 				      struct snd_pcm_hw_params *params)
@@ -24,109 +25,16 @@ static int apq8096_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
 	return 0;
 }
 
-static int apq8096_sbc_parse_of(struct snd_soc_card *card)
+static void apq8096_add_be_ops(struct snd_soc_card *card)
 {
-	struct device_node *np;
-	struct device_node *codec = NULL;
-	struct device_node *platform = NULL;
-	struct device_node *cpu = NULL;
-	struct device *dev = card->dev;
-	struct snd_soc_dai_link *link;
-	int ret, num_links;
-
-	ret = snd_soc_of_parse_card_name(card, "qcom,model");
-	if (ret) {
-		dev_err(dev, "Error parsing card name: %d\n", ret);
-		return ret;
-	}
-
-	/* DAPM routes */
-	if (of_property_read_bool(dev->of_node, "qcom,audio-routing")) {
-		ret = snd_soc_of_parse_audio_routing(card,
-					"qcom,audio-routing");
-		if (ret)
-			return ret;
-	}
-
-	/* Populate links */
-	num_links = of_get_child_count(dev->of_node);
-
-	/* Allocate the DAI link array */
-	card->dai_link = kcalloc(num_links, sizeof(*link), GFP_KERNEL);
-	if (!card->dai_link)
-		return -ENOMEM;
+	struct snd_soc_dai_link *link = card->dai_link;
+	int i, num_links = card->num_links;
 
-	card->num_links	= num_links;
-	link = card->dai_link;
-
-	for_each_child_of_node(dev->of_node, np) {
-		cpu = of_get_child_by_name(np, "cpu");
-		if (!cpu) {
-			dev_err(dev, "Can't find cpu DT node\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		link->cpu_of_node = of_parse_phandle(cpu, "sound-dai", 0);
-		if (!link->cpu_of_node) {
-			dev_err(card->dev, "error getting cpu phandle\n");
-			ret = -EINVAL;
-			goto err;
-		}
-
-		ret = snd_soc_of_get_dai_name(cpu, &link->cpu_dai_name);
-		if (ret) {
-			dev_err(card->dev, "error getting cpu dai name\n");
-			goto err;
-		}
-
-		platform = of_get_child_by_name(np, "platform");
-		codec = of_get_child_by_name(np, "codec");
-		if (codec && platform) {
-			link->platform_of_node = of_parse_phandle(platform,
-								  "sound-dai",
-								   0);
-			if (!link->platform_of_node) {
-				dev_err(card->dev, "platform dai not found\n");
-				ret = -EINVAL;
-				goto err;
-			}
-
-			ret = snd_soc_of_get_dai_link_codecs(dev, codec, link);
-			if (ret < 0) {
-				dev_err(card->dev, "codec dai not found\n");
-				goto err;
-			}
-			link->no_pcm = 1;
-			link->ignore_pmdown_time = 1;
+	for (i = 0; i < num_links; i++) {
+		if (link->no_pcm == 1)
 			link->be_hw_params_fixup = apq8096_be_hw_params_fixup;
-		} else {
-			link->platform_of_node = link->cpu_of_node;
-			link->codec_dai_name = "snd-soc-dummy-dai";
-			link->codec_name = "snd-soc-dummy";
-			link->dynamic = 1;
-		}
-
-		link->ignore_suspend = 1;
-		ret = of_property_read_string(np, "link-name", &link->name);
-		if (ret) {
-			dev_err(card->dev, "error getting codec dai_link name\n");
-			goto err;
-		}
-
-		link->dpcm_playback = 1;
-		link->dpcm_capture = 1;
-		link->stream_name = link->name;
 		link++;
 	}
-
-	return 0;
-err:
-	of_node_put(cpu);
-	of_node_put(codec);
-	of_node_put(platform);
-	kfree(card->dai_link);
-	return ret;
 }
 
 static int apq8096_platform_probe(struct platform_device *pdev)
@@ -142,18 +50,21 @@ static int apq8096_platform_probe(struct platform_device *pdev)
 	card->dev = dev;
 	card->auto_bind = true;
 	dev_set_drvdata(dev, card);
-	ret = apq8096_sbc_parse_of(card);
+	ret = qcom_snd_parse_of(card);
 	if (ret) {
 		dev_err(dev, "Error parsing OF data\n");
 		goto err;
 	}
 
+	apq8096_add_be_ops(card);
 	ret = snd_soc_register_card(card);
 	if (ret)
-		goto err;
+		goto err_card_register;
 
 	return 0;
 
+err_card_register:
+	kfree(card->dai_link);
 err:
 	kfree(card);
 	return ret;
diff --git a/sound/soc/qcom/common.c b/sound/soc/qcom/common.c
new file mode 100644
index 000000000000..eb1b9da05dd4
--- /dev/null
+++ b/sound/soc/qcom/common.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, Linaro Limited.
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#include <linux/module.h>
+#include "common.h"
+
+int qcom_snd_parse_of(struct snd_soc_card *card)
+{
+	struct device_node *np;
+	struct device_node *codec = NULL;
+	struct device_node *platform = NULL;
+	struct device_node *cpu = NULL;
+	struct device *dev = card->dev;
+	struct snd_soc_dai_link *link;
+	int ret, num_links;
+
+	ret = snd_soc_of_parse_card_name(card, "model");
+	if (ret) {
+		dev_err(dev, "Error parsing card name: %d\n", ret);
+		return ret;
+	}
+
+	/* DAPM routes */
+	if (of_property_read_bool(dev->of_node, "audio-routing")) {
+		ret = snd_soc_of_parse_audio_routing(card,
+				"audio-routing");
+		if (ret)
+			return ret;
+	}
+
+	/* Populate links */
+	num_links = of_get_child_count(dev->of_node);
+
+	/* Allocate the DAI link array */
+	card->dai_link = kcalloc(num_links, sizeof(*link), GFP_KERNEL);
+	if (!card->dai_link)
+		return -ENOMEM;
+
+	card->num_links = num_links;
+	link = card->dai_link;
+	for_each_child_of_node(dev->of_node, np) {
+		cpu = of_get_child_by_name(np, "cpu");
+		if (!cpu) {
+			dev_err(dev, "Can't find cpu DT node\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
+		link->cpu_of_node = of_parse_phandle(cpu, "sound-dai", 0);
+		if (!link->cpu_of_node) {
+			dev_err(card->dev, "error getting cpu phandle\n");
+			ret = -EINVAL;
+			goto err;
+		}
+
+		ret = snd_soc_of_get_dai_name(cpu, &link->cpu_dai_name);
+		if (ret) {
+			dev_err(card->dev, "error getting cpu dai name\n");
+			goto err;
+		}
+
+		platform = of_get_child_by_name(np, "platform");
+		codec = of_get_child_by_name(np, "codec");
+		if (codec && platform) {
+			link->platform_of_node = of_parse_phandle(platform,
+					"sound-dai",
+					0);
+			if (!link->platform_of_node) {
+				dev_err(card->dev, "platform dai not found\n");
+				ret = -EINVAL;
+				goto err;
+			}
+
+			ret = snd_soc_of_get_dai_link_codecs(dev, codec, link);
+			if (ret < 0) {
+				dev_err(card->dev, "codec dai not found\n");
+				goto err;
+			}
+			link->no_pcm = 1;
+			link->ignore_pmdown_time = 1;
+		} else {
+			link->platform_of_node = link->cpu_of_node;
+			link->codec_dai_name = "snd-soc-dummy-dai";
+			link->codec_name = "snd-soc-dummy";
+			link->dynamic = 1;
+		}
+
+		link->ignore_suspend = 1;
+		ret = of_property_read_string(np, "link-name", &link->name);
+		if (ret) {
+			dev_err(card->dev, "error getting codec dai_link name\n");
+			goto err;
+		}
+
+		link->dpcm_playback = 1;
+		link->dpcm_capture = 1;
+		link->stream_name = link->name;
+		link++;
+	}
+
+	return 0;
+err:
+	of_node_put(cpu);
+	of_node_put(codec);
+	of_node_put(platform);
+	kfree(card->dai_link);
+	return ret;
+}
+EXPORT_SYMBOL(qcom_snd_parse_of);
+
+MODULE_LICENSE("GPL v2");
diff --git a/sound/soc/qcom/common.h b/sound/soc/qcom/common.h
new file mode 100644
index 000000000000..ad5d2cf27459
--- /dev/null
+++ b/sound/soc/qcom/common.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#ifndef __QCOM_SND_COMMON_H__
+#define __QCOM_SND_COMMON_H__
+
+#include <linux/component.h>
+#include <sound/soc.h>
+
+int qcom_snd_parse_of(struct snd_soc_card *card);
+
+#endif
-- 
cgit v1.2.3


From 6b1687bf76ef84cb1e31386c4871a01fe66937bf Mon Sep 17 00:00:00 2001
From: Rohit kumar <rohitkr@codeaurora.org>
Date: Wed, 1 Aug 2018 14:31:09 +0530
Subject: ASoC: qcom: add sdm845 sound card support

This patch adds sdm845 audio machine driver support.

Acked-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Rohit kumar <rohitkr@codeaurora.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/Kconfig  |   8 ++
 sound/soc/qcom/Makefile |   2 +
 sound/soc/qcom/sdm845.c | 286 ++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 296 insertions(+)
 create mode 100644 sound/soc/qcom/sdm845.c

diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 87838fa27997..350730839c6f 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -90,3 +90,11 @@ config SND_SOC_MSM8996
           Support for Qualcomm Technologies LPASS audio block in
           APQ8096 SoC-based systems.
           Say Y if you want to use audio device on this SoCs
+
+config SND_SOC_SDM845
+	tristate "SoC Machine driver for SDM845 boards"
+	select SND_SOC_QDSP6
+	help
+	  To add support for audio on Qualcomm Technologies Inc.
+	  SDM845 SoC-based systems.
+	  Say Y if you want to use audio device on this SoCs.
diff --git a/sound/soc/qcom/Makefile b/sound/soc/qcom/Makefile
index fefecc072265..f0e94d48ba98 100644
--- a/sound/soc/qcom/Makefile
+++ b/sound/soc/qcom/Makefile
@@ -14,10 +14,12 @@ obj-$(CONFIG_SND_SOC_LPASS_APQ8016) += snd-soc-lpass-apq8016.o
 snd-soc-storm-objs := storm.o
 snd-soc-apq8016-sbc-objs := apq8016_sbc.o
 snd-soc-apq8096-objs := apq8096.o common.o
+snd-soc-sdm845-objs := sdm845.o common.o
 
 obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
 obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
 obj-$(CONFIG_SND_SOC_MSM8996) += snd-soc-apq8096.o
+obj-$(CONFIG_SND_SOC_SDM845) += snd-soc-sdm845.o
 
 #DSP lib
 obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/
diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
new file mode 100644
index 000000000000..bf4ec4646906
--- /dev/null
+++ b/sound/soc/qcom/sdm845.c
@@ -0,0 +1,286 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/atomic.h>
+#include <linux/of_device.h>
+#include <sound/pcm.h>
+#include <sound/pcm_params.h>
+#include <linux/soc/qcom/apr.h>
+#include "common.h"
+#include "qdsp6/q6afe.h"
+
+#define DEFAULT_SAMPLE_RATE_48K		48000
+#define DEFAULT_MCLK_RATE		24576000
+#define DEFAULT_BCLK_RATE		12288000
+
+struct sdm845_snd_data {
+	struct snd_soc_card *card;
+	uint32_t pri_mi2s_clk_count;
+	uint32_t quat_tdm_clk_count;
+};
+
+static unsigned int tdm_slot_offset[8] = {0, 4, 8, 12, 16, 20, 24, 28};
+
+static int sdm845_tdm_snd_hw_params(struct snd_pcm_substream *substream,
+					struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	int ret = 0;
+	int channels, slot_width;
+
+	switch (params_format(params)) {
+	case SNDRV_PCM_FORMAT_S16_LE:
+		slot_width = 32;
+		break;
+	default:
+		dev_err(rtd->dev, "%s: invalid param format 0x%x\n",
+				__func__, params_format(params));
+		return -EINVAL;
+	}
+
+	channels = params_channels(params);
+	if (substream->stream == SNDRV_PCM_STREAM_PLAYBACK) {
+		ret = snd_soc_dai_set_tdm_slot(cpu_dai, 0, 0x3,
+				8, slot_width);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set tdm slot, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+
+		ret = snd_soc_dai_set_channel_map(cpu_dai, 0, NULL,
+				channels, tdm_slot_offset);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set channel map, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+	} else {
+		ret = snd_soc_dai_set_tdm_slot(cpu_dai, 0xf, 0,
+				8, slot_width);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set tdm slot, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+
+		ret = snd_soc_dai_set_channel_map(cpu_dai, channels,
+				tdm_slot_offset, 0, NULL);
+		if (ret < 0) {
+			dev_err(rtd->dev, "%s: failed to set channel map, err:%d\n",
+					__func__, ret);
+			goto end;
+		}
+	}
+end:
+	return ret;
+}
+
+static int sdm845_snd_hw_params(struct snd_pcm_substream *substream,
+					struct snd_pcm_hw_params *params)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+	int ret = 0;
+
+	switch (cpu_dai->id) {
+	case QUATERNARY_TDM_RX_0:
+	case QUATERNARY_TDM_TX_0:
+		ret = sdm845_tdm_snd_hw_params(substream, params);
+		break;
+	default:
+		pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id);
+		break;
+	}
+	return ret;
+}
+
+static int sdm845_snd_startup(struct snd_pcm_substream *substream)
+{
+	unsigned int fmt = SND_SOC_DAIFMT_CBS_CFS;
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+
+	switch (cpu_dai->id) {
+	case PRIMARY_MI2S_RX:
+	case PRIMARY_MI2S_TX:
+		if (++(data->pri_mi2s_clk_count) == 1) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_MCLK_1,
+				DEFAULT_MCLK_RATE, SNDRV_PCM_STREAM_PLAYBACK);
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_PRI_MI2S_IBIT,
+				DEFAULT_BCLK_RATE, SNDRV_PCM_STREAM_PLAYBACK);
+		}
+		snd_soc_dai_set_fmt(cpu_dai, fmt);
+		break;
+
+	case QUATERNARY_TDM_RX_0:
+	case QUATERNARY_TDM_TX_0:
+		if (++(data->quat_tdm_clk_count) == 1) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_QUAD_TDM_IBIT,
+				DEFAULT_BCLK_RATE, SNDRV_PCM_STREAM_PLAYBACK);
+		}
+		break;
+
+	default:
+		pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id);
+		break;
+	}
+	return 0;
+}
+
+static void  sdm845_snd_shutdown(struct snd_pcm_substream *substream)
+{
+	struct snd_soc_pcm_runtime *rtd = substream->private_data;
+	struct snd_soc_card *card = rtd->card;
+	struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card);
+	struct snd_soc_dai *cpu_dai = rtd->cpu_dai;
+
+	switch (cpu_dai->id) {
+	case PRIMARY_MI2S_RX:
+	case PRIMARY_MI2S_TX:
+		if (--(data->pri_mi2s_clk_count) == 0) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_MCLK_1,
+				0, SNDRV_PCM_STREAM_PLAYBACK);
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_PRI_MI2S_IBIT,
+				0, SNDRV_PCM_STREAM_PLAYBACK);
+		};
+		break;
+
+	case QUATERNARY_TDM_RX_0:
+	case QUATERNARY_TDM_TX_0:
+		if (--(data->quat_tdm_clk_count) == 0) {
+			snd_soc_dai_set_sysclk(cpu_dai,
+				Q6AFE_LPASS_CLK_ID_QUAD_TDM_IBIT,
+				0, SNDRV_PCM_STREAM_PLAYBACK);
+		}
+		break;
+
+	default:
+		pr_err("%s: invalid dai id 0x%x\n", __func__, cpu_dai->id);
+		break;
+	}
+}
+
+static struct snd_soc_ops sdm845_be_ops = {
+	.hw_params = sdm845_snd_hw_params,
+	.startup = sdm845_snd_startup,
+	.shutdown = sdm845_snd_shutdown,
+};
+
+static int sdm845_be_hw_params_fixup(struct snd_soc_pcm_runtime *rtd,
+				struct snd_pcm_hw_params *params)
+{
+	struct snd_interval *rate = hw_param_interval(params,
+					SNDRV_PCM_HW_PARAM_RATE);
+	struct snd_interval *channels = hw_param_interval(params,
+					SNDRV_PCM_HW_PARAM_CHANNELS);
+	struct snd_mask *fmt = hw_param_mask(params, SNDRV_PCM_HW_PARAM_FORMAT);
+
+	rate->min = rate->max = DEFAULT_SAMPLE_RATE_48K;
+	channels->min = channels->max = 2;
+	snd_mask_set_format(fmt, SNDRV_PCM_FORMAT_S16_LE);
+
+	return 0;
+}
+
+static void sdm845_add_be_ops(struct snd_soc_card *card)
+{
+	struct snd_soc_dai_link *link = card->dai_link;
+	int i, num_links = card->num_links;
+
+	for (i = 0; i < num_links; i++) {
+		if (link->no_pcm == 1) {
+			link->ops = &sdm845_be_ops;
+			link->be_hw_params_fixup = sdm845_be_hw_params_fixup;
+		}
+		link++;
+	}
+}
+
+static int sdm845_snd_platform_probe(struct platform_device *pdev)
+{
+	struct snd_soc_card *card;
+	struct sdm845_snd_data *data;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	card = kzalloc(sizeof(*card), GFP_KERNEL);
+	if (!card)
+		return -ENOMEM;
+
+	/* Allocate the private data */
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	card->dev = dev;
+	card->auto_bind = true;
+	dev_set_drvdata(dev, card);
+	ret = qcom_snd_parse_of(card);
+	if (ret) {
+		dev_err(dev, "Error parsing OF data\n");
+		goto parse_dt_fail;
+	}
+
+	data->card = card;
+	snd_soc_card_set_drvdata(card, data);
+
+	sdm845_add_be_ops(card);
+	ret = snd_soc_register_card(card);
+	if (ret) {
+		dev_err(dev, "Sound card registration failed\n");
+		goto register_card_fail;
+	}
+	return ret;
+
+register_card_fail:
+	kfree(card->dai_link);
+parse_dt_fail:
+	kfree(data);
+	kfree(card);
+	return ret;
+}
+
+static int sdm845_snd_platform_remove(struct platform_device *pdev)
+{
+	struct snd_soc_card *card = dev_get_drvdata(&pdev->dev);
+	struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card);
+
+	card->auto_bind = false;
+	snd_soc_unregister_card(card);
+	kfree(card->dai_link);
+	kfree(data);
+	kfree(card);
+	return 0;
+}
+
+static const struct of_device_id sdm845_snd_device_id[]  = {
+	{ .compatible = "qcom,sdm845-sndcard" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, sdm845_snd_device_id);
+
+static struct platform_driver sdm845_snd_driver = {
+	.probe = sdm845_snd_platform_probe,
+	.remove = sdm845_snd_platform_remove,
+	.driver = {
+		.name = "msm-snd-sdm845",
+		.of_match_table = sdm845_snd_device_id,
+	},
+};
+module_platform_driver(sdm845_snd_driver);
+
+MODULE_DESCRIPTION("sdm845 ASoC Machine Driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From d101f9b96ee08f0454989bc3adb10e6cf7f3f953 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:39 +0100
Subject: ASoC: nau8540: remove redundant variable osrate

Variable osrate is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'osrate' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/nau8540.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/sound/soc/codecs/nau8540.c b/sound/soc/codecs/nau8540.c
index 17104f8dc1a9..e3c8cd17daf2 100644
--- a/sound/soc/codecs/nau8540.c
+++ b/sound/soc/codecs/nau8540.c
@@ -362,11 +362,8 @@ static const struct snd_soc_dapm_route nau8540_dapm_routes[] = {
 
 static int nau8540_clock_check(struct nau8540 *nau8540, int rate, int osr)
 {
-	int osrate;
-
 	if (osr >= ARRAY_SIZE(osr_adc_sel))
 		return -EINVAL;
-	osrate = osr_adc_sel[osr].osr;
 
 	if (rate * osr > CLK_ADC_MAX) {
 		dev_err(nau8540->dev, "exceed the maximum frequency of CLK_ADC\n");
-- 
cgit v1.2.3


From 18127744cf446f113ca33f07e5cea893388f781a Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:40 +0100
Subject: ASoC: stm32: remove redundant pointers 'priv' and 'rtd'

Pointer 'priv' is assigned and not used, removing this allows
the removal of pointer 'rtd'.

Cleans up clang warning:
warning: variable 'priv' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/stm/stm32_adfsdm.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/sound/soc/stm/stm32_adfsdm.c b/sound/soc/stm/stm32_adfsdm.c
index 0e9373064032..706ff005234f 100644
--- a/sound/soc/stm/stm32_adfsdm.c
+++ b/sound/soc/stm/stm32_adfsdm.c
@@ -269,16 +269,10 @@ static int stm32_adfsdm_pcm_new(struct snd_soc_pcm_runtime *rtd)
 static void stm32_adfsdm_pcm_free(struct snd_pcm *pcm)
 {
 	struct snd_pcm_substream *substream;
-	struct snd_soc_pcm_runtime *rtd;
-	struct stm32_adfsdm_priv *priv;
 
 	substream = pcm->streams[SNDRV_PCM_STREAM_CAPTURE].substream;
-	if (substream) {
-		rtd = substream->private_data;
-		priv = snd_soc_dai_get_drvdata(rtd->cpu_dai);
-
+	if (substream)
 		snd_pcm_lib_preallocate_free_for_all(pcm);
-	}
 }
 
 static struct snd_soc_component_driver stm32_adfsdm_soc_platform = {
-- 
cgit v1.2.3


From 96963dedd000605a0e84e2ac6e41263a50f05953 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:34 +0100
Subject: ALSA: asihpi: remove redundant variable max_streams

Variable max_streams is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'max_streams' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/asihpi/hpi6205.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/sound/pci/asihpi/hpi6205.c b/sound/pci/asihpi/hpi6205.c
index 8d5abfa4e24b..2864698436a5 100644
--- a/sound/pci/asihpi/hpi6205.c
+++ b/sound/pci/asihpi/hpi6205.c
@@ -635,7 +635,6 @@ static u16 create_adapter_obj(struct hpi_adapter_obj *pao,
 	{
 		struct hpi_message hm;
 		struct hpi_response hr;
-		u32 max_streams;
 
 		HPI_DEBUG_LOG(VERBOSE, "init ADAPTER_GET_INFO\n");
 		memset(&hm, 0, sizeof(hm));
@@ -660,10 +659,6 @@ static u16 create_adapter_obj(struct hpi_adapter_obj *pao,
 		pao->type = hr.u.ax.info.adapter_type;
 		pao->index = hr.u.ax.info.adapter_index;
 
-		max_streams =
-			hr.u.ax.info.num_outstreams +
-			hr.u.ax.info.num_instreams;
-
 		HPI_DEBUG_LOG(VERBOSE,
 			"got adapter info type %x index %d serial %d\n",
 			hr.u.ax.info.adapter_type, hr.u.ax.info.adapter_index,
-- 
cgit v1.2.3


From 45bf41005ac0d7cae0c1caa85d06cb35976823fa Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:35 +0100
Subject: ALSA: cs5535audio: remove redundant pointer 'dma'

Pointer 'dma' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up two clang warnings:
warning: variable 'dma' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/cs5535audio/cs5535audio.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/sound/pci/cs5535audio/cs5535audio.c b/sound/pci/cs5535audio/cs5535audio.c
index de409cda50aa..4590086d9cd8 100644
--- a/sound/pci/cs5535audio/cs5535audio.c
+++ b/sound/pci/cs5535audio/cs5535audio.c
@@ -192,8 +192,6 @@ static void process_bm0_irq(struct cs5535audio *cs5535au)
 	bm_stat = cs_readb(cs5535au, ACC_BM0_STATUS);
 	spin_unlock(&cs5535au->reg_lock);
 	if (bm_stat & EOP) {
-		struct cs5535audio_dma *dma;
-		dma = cs5535au->playback_substream->runtime->private_data;
 		snd_pcm_period_elapsed(cs5535au->playback_substream);
 	} else {
 		dev_err(cs5535au->card->dev,
@@ -208,11 +206,8 @@ static void process_bm1_irq(struct cs5535audio *cs5535au)
 	spin_lock(&cs5535au->reg_lock);
 	bm_stat = cs_readb(cs5535au, ACC_BM1_STATUS);
 	spin_unlock(&cs5535au->reg_lock);
-	if (bm_stat & EOP) {
-		struct cs5535audio_dma *dma;
-		dma = cs5535au->capture_substream->runtime->private_data;
+	if (bm_stat & EOP)
 		snd_pcm_period_elapsed(cs5535au->capture_substream);
-	}
 }
 
 static irqreturn_t snd_cs5535audio_interrupt(int irq, void *dev_id)
-- 
cgit v1.2.3


From de42b4b96ebe29058ce1cb59a1f98d58b8abd132 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:36 +0100
Subject: ALSA: emu10k1: remove redundant variable attn

Variable attn is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'attn' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/emu10k1/emupcm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index 69f9b100bd24..26f6eda3e766 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -290,7 +290,7 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu,
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	unsigned int silent_page, tmp;
 	int voice, stereo, w_16;
-	unsigned char attn, send_amount[8];
+	unsigned char send_amount[8];
 	unsigned char send_routing[8];
 	unsigned long flags;
 	unsigned int pitch_target;
@@ -313,7 +313,6 @@ static void snd_emu10k1_pcm_init_voice(struct snd_emu10k1 *emu,
 
 	/* volume parameters */
 	if (extra) {
-		attn = 0;
 		memset(send_routing, 0, sizeof(send_routing));
 		send_routing[0] = 0;
 		send_routing[1] = 1;
-- 
cgit v1.2.3


From 3b0cbc7812d759ffb38d881e75c0318512283d00 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:37 +0100
Subject: ALSA: ens137x: remove redundant array pcm_devs

The array pcm_devs is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'pcm_devs' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ens1370.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/sound/pci/ens1370.c b/sound/pci/ens1370.c
index 39f79a6b5283..727eb3da1fda 100644
--- a/sound/pci/ens1370.c
+++ b/sound/pci/ens1370.c
@@ -2392,7 +2392,7 @@ static int snd_audiopci_probe(struct pci_dev *pci,
 	static int dev;
 	struct snd_card *card;
 	struct ensoniq *ensoniq;
-	int err, pcm_devs[2];
+	int err;
 
 	if (dev >= SNDRV_CARDS)
 		return -ENODEV;
@@ -2412,7 +2412,6 @@ static int snd_audiopci_probe(struct pci_dev *pci,
 	}
 	card->private_data = ensoniq;
 
-	pcm_devs[0] = 0; pcm_devs[1] = 1;
 #ifdef CHIP1370
 	if ((err = snd_ensoniq_1370_mixer(ensoniq)) < 0) {
 		snd_card_free(card);
-- 
cgit v1.2.3


From 0d00085b905c904d6de4296aa6a1e3613d0a4d67 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:38 +0100
Subject: ALSA: sonicvibes: remove redundant pointer 'dir'

Pointer 'dir' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'dir' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/sonicvibes.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/pci/sonicvibes.c b/sound/pci/sonicvibes.c
index 7fbdb703bfcd..7218f38b59db 100644
--- a/sound/pci/sonicvibes.c
+++ b/sound/pci/sonicvibes.c
@@ -1433,14 +1433,12 @@ static int snd_sonicvibes_midi(struct sonicvibes *sonic,
 {
 	struct snd_mpu401 * mpu = rmidi->private_data;
 	struct snd_card *card = sonic->card;
-	struct snd_rawmidi_str *dir;
 	unsigned int idx;
 	int err;
 
 	mpu->private_data = sonic;
 	mpu->open_input = snd_sonicvibes_midi_input_open;
 	mpu->close_input = snd_sonicvibes_midi_input_close;
-	dir = &rmidi->streams[SNDRV_RAWMIDI_STREAM_OUTPUT];
 	for (idx = 0; idx < ARRAY_SIZE(snd_sonicvibes_midi_controls); idx++)
 		if ((err = snd_ctl_add(card, snd_ctl_new1(&snd_sonicvibes_midi_controls[idx], sonic))) < 0)
 			return err;
-- 
cgit v1.2.3


From d36455a38ed82e7d1e6807573935874f0b279f45 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:41 +0100
Subject: ALSA: usb-audio: remove redundant pointer 'urb'

Pointer 'urb' is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'urb' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/endpoint.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/usb/endpoint.c b/sound/usb/endpoint.c
index c90607ebe155..d86be8bfe412 100644
--- a/sound/usb/endpoint.c
+++ b/sound/usb/endpoint.c
@@ -325,7 +325,6 @@ static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
 		unsigned long flags;
 		struct snd_usb_packet_info *uninitialized_var(packet);
 		struct snd_urb_ctx *ctx = NULL;
-		struct urb *urb;
 		int err, i;
 
 		spin_lock_irqsave(&ep->lock, flags);
@@ -345,7 +344,6 @@ static void queue_pending_output_urbs(struct snd_usb_endpoint *ep)
 			return;
 
 		list_del_init(&ctx->ready_list);
-		urb = ctx->urb;
 
 		/* copy over the length information */
 		for (i = 0; i < packet->packets; i++)
-- 
cgit v1.2.3


From f597a5792ada511e3c69ecf7201fc178c574d822 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 17:52:34 +0800
Subject: rxrpc: remove redundant variables 'sp' and 'did_discard'

Variables 'sp' and 'did_discard' are being assigned,
but are never used, hence they are redundant and can be removed.

fix following warning:

net/rxrpc/call_event.c:165:25: warning: variable 'sp' set but not used [-Wunused-but-set-variable]
net/rxrpc/conn_client.c:1054:7: warning: variable 'did_discard' set but not used [-Wunused-but-set-variable]

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/call_event.c  | 2 --
 net/rxrpc/conn_client.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c
index 20210418904b..8e7434e92097 100644
--- a/net/rxrpc/call_event.c
+++ b/net/rxrpc/call_event.c
@@ -162,7 +162,6 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call)
  */
 static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 {
-	struct rxrpc_skb_priv *sp;
 	struct sk_buff *skb;
 	unsigned long resend_at;
 	rxrpc_seq_t cursor, seq, top;
@@ -207,7 +206,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j)
 
 		skb = call->rxtx_buffer[ix];
 		rxrpc_see_skb(skb, rxrpc_skb_tx_seen);
-		sp = rxrpc_skb(skb);
 
 		if (anno_type == RXRPC_TX_ANNO_UNACK) {
 			if (ktime_after(skb->tstamp, max_age)) {
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index 5736f643c516..e4bfbd7e48a8 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -1051,7 +1051,6 @@ void rxrpc_discard_expired_client_conns(struct work_struct *work)
 		container_of(work, struct rxrpc_net, client_conn_reaper);
 	unsigned long expiry, conn_expires_at, now;
 	unsigned int nr_conns;
-	bool did_discard = false;
 
 	_enter("");
 
@@ -1113,7 +1112,6 @@ next:
 	 * If someone re-sets the flag and re-gets the ref, that's fine.
 	 */
 	rxrpc_put_connection(conn);
-	did_discard = true;
 	nr_conns--;
 	goto next;
 
-- 
cgit v1.2.3


From 887763bbc34112f4126ec52d16072ba736c83a6f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:36 +0100
Subject: rxrpc: Display call expect-receive-by timeout in proc

Display in /proc/net/rxrpc/calls the timeout by which a call next expects
to receive a packet.

This makes it easier to debug timeout issues.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/proc.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index d9fca8c4bcdc..bc6f27c8869d 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -63,6 +63,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	struct rxrpc_peer *peer;
 	struct rxrpc_call *call;
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
+	unsigned long timeout = 0, nowj;
 	rxrpc_seq_t tx_hard_ack, rx_hard_ack;
 	char lbuff[50], rbuff[50];
 
@@ -71,7 +72,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 			 "Proto Local                                          "
 			 " Remote                                         "
 			 " SvID ConnID   CallID   End Use State    Abort   "
-			 " UserID\n");
+			 " UserID           TxSeq    TW RxSeq    RW RxTimo\n");
 		return 0;
 	}
 
@@ -94,11 +95,17 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	else
 		strcpy(rbuff, "no_connection");
 
+	if (call->state != RXRPC_CALL_SERVER_PREALLOC) {
+		timeout = READ_ONCE(call->expect_rx_by);
+		nowj = jiffies;
+		timeout -= jiffies;
+	}
+
 	tx_hard_ack = READ_ONCE(call->tx_hard_ack);
 	rx_hard_ack = READ_ONCE(call->rx_hard_ack);
 	seq_printf(seq,
 		   "UDP   %-47.47s %-47.47s %4x %08x %08x %s %3u"
-		   " %-8.8s %08x %lx %08x %02x %08x %02x\n",
+		   " %-8.8s %08x %lx %08x %02x %08x %02x %06lx\n",
 		   lbuff,
 		   rbuff,
 		   call->service_id,
@@ -110,7 +117,8 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 		   call->abort_code,
 		   call->user_call_ID,
 		   tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack,
-		   rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack);
+		   rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack,
+		   timeout);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 6b97bd7a272cddc48adb384142db99a935834765 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:36 +0100
Subject: rxrpc: Show some more information through /proc files

Show the four current call IDs in /proc/net/rxrpc/conns.

Show the current packet Rx serial number in /proc/net/rxrpc/calls.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/proc.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index bc6f27c8869d..163d05df339d 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -72,7 +72,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 			 "Proto Local                                          "
 			 " Remote                                         "
 			 " SvID ConnID   CallID   End Use State    Abort   "
-			 " UserID           TxSeq    TW RxSeq    RW RxTimo\n");
+			 " UserID           TxSeq    TW RxSeq    RW RxSerial RxTimo\n");
 		return 0;
 	}
 
@@ -105,7 +105,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	rx_hard_ack = READ_ONCE(call->rx_hard_ack);
 	seq_printf(seq,
 		   "UDP   %-47.47s %-47.47s %4x %08x %08x %s %3u"
-		   " %-8.8s %08x %lx %08x %02x %08x %02x %06lx\n",
+		   " %-8.8s %08x %lx %08x %02x %08x %02x %08x %06lx\n",
 		   lbuff,
 		   rbuff,
 		   call->service_id,
@@ -118,6 +118,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 		   call->user_call_ID,
 		   tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack,
 		   rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack,
+		   call->rx_serial,
 		   timeout);
 
 	return 0;
@@ -187,7 +188,7 @@ static int rxrpc_connection_seq_show(struct seq_file *seq, void *v)
 print:
 	seq_printf(seq,
 		   "UDP   %-47.47s %-47.47s %4x %08x %s %3u"
-		   " %s %08x %08x %08x\n",
+		   " %s %08x %08x %08x %08x %08x %08x %08x\n",
 		   lbuff,
 		   rbuff,
 		   conn->service_id,
@@ -197,7 +198,11 @@ print:
 		   rxrpc_conn_states[conn->state],
 		   key_serial(conn->params.key),
 		   atomic_read(&conn->serial),
-		   conn->hi_serial);
+		   conn->hi_serial,
+		   conn->channels[0].call_id,
+		   conn->channels[1].call_id,
+		   conn->channels[2].call_id,
+		   conn->channels[3].call_id);
 
 	return 0;
 }
-- 
cgit v1.2.3


From f3f8337c9e2a4964671c652469202ec485afddc0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:36 +0100
Subject: rxrpc: Fix the trace for terminal ACK (re)transmission

Fix the trace for terminal ACK (re)transmission to put in the right
parameters.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/conn_event.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index 8229a52c2acd..d46a68807f08 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -129,8 +129,10 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 		_proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort);
 		break;
 	case RXRPC_PACKET_TYPE_ACK:
-		trace_rxrpc_tx_ack(NULL, serial, chan->last_seq, 0,
-				   RXRPC_ACK_DUPLICATE, 0);
+		trace_rxrpc_tx_ack(NULL, serial,
+				   ntohl(pkt.ack.firstPacket),
+				   ntohl(pkt.ack.serial),
+				   pkt.ack.reason, 0);
 		_proto("Tx ACK %%%u [re]", serial);
 		break;
 	}
-- 
cgit v1.2.3


From 4764c0da69dc500791c840c88dfd940d13b452e7 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:37 +0100
Subject: rxrpc: Trace packet transmission

Trace successful packet transmission (kernel_sendmsg() succeeded, that is)
in AF_RXRPC.  We can share the enum that defines the transmission points
with the trace_rxrpc_tx_fail() tracepoint, so rename its constants to be
applicable to both.

Also, save the internal call->debug_id in the rxrpc_channel struct so that
it can be used in retransmission trace lines.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h | 107 +++++++++++++++++++++++++++++--------------
 net/rxrpc/ar-internal.h      |   1 +
 net/rxrpc/conn_client.c      |   1 +
 net/rxrpc/conn_event.c       |  13 ++++--
 net/rxrpc/input.c            |  11 ++++-
 net/rxrpc/local_event.c      |   5 +-
 net/rxrpc/output.c           |  32 ++++++++++---
 net/rxrpc/rxkad.c            |   7 ++-
 8 files changed, 127 insertions(+), 50 deletions(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 4fff00e9da8a..2aa6f615b60d 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -211,18 +211,18 @@ enum rxrpc_congest_change {
 	rxrpc_cong_saw_nack,
 };
 
-enum rxrpc_tx_fail_trace {
-	rxrpc_tx_fail_call_abort,
-	rxrpc_tx_fail_call_ack,
-	rxrpc_tx_fail_call_data_frag,
-	rxrpc_tx_fail_call_data_nofrag,
-	rxrpc_tx_fail_call_final_resend,
-	rxrpc_tx_fail_conn_abort,
-	rxrpc_tx_fail_conn_challenge,
-	rxrpc_tx_fail_conn_response,
-	rxrpc_tx_fail_reject,
-	rxrpc_tx_fail_version_keepalive,
-	rxrpc_tx_fail_version_reply,
+enum rxrpc_tx_point {
+	rxrpc_tx_point_call_abort,
+	rxrpc_tx_point_call_ack,
+	rxrpc_tx_point_call_data_frag,
+	rxrpc_tx_point_call_data_nofrag,
+	rxrpc_tx_point_call_final_resend,
+	rxrpc_tx_point_conn_abort,
+	rxrpc_tx_point_rxkad_challenge,
+	rxrpc_tx_point_rxkad_response,
+	rxrpc_tx_point_reject,
+	rxrpc_tx_point_version_keepalive,
+	rxrpc_tx_point_version_reply,
 };
 
 #endif /* end __RXRPC_DECLARE_TRACE_ENUMS_ONCE_ONLY */
@@ -452,18 +452,18 @@ enum rxrpc_tx_fail_trace {
 	EM(RXRPC_CALL_LOCAL_ERROR,		"LocalError") \
 	E_(RXRPC_CALL_NETWORK_ERROR,		"NetError")
 
-#define rxrpc_tx_fail_traces \
-	EM(rxrpc_tx_fail_call_abort,		"CallAbort") \
-	EM(rxrpc_tx_fail_call_ack,		"CallAck") \
-	EM(rxrpc_tx_fail_call_data_frag,	"CallDataFrag") \
-	EM(rxrpc_tx_fail_call_data_nofrag,	"CallDataNofrag") \
-	EM(rxrpc_tx_fail_call_final_resend,	"CallFinalResend") \
-	EM(rxrpc_tx_fail_conn_abort,		"ConnAbort") \
-	EM(rxrpc_tx_fail_conn_challenge,	"ConnChall") \
-	EM(rxrpc_tx_fail_conn_response,		"ConnResp") \
-	EM(rxrpc_tx_fail_reject,		"Reject") \
-	EM(rxrpc_tx_fail_version_keepalive,	"VerKeepalive") \
-	E_(rxrpc_tx_fail_version_reply,		"VerReply")
+#define rxrpc_tx_points \
+	EM(rxrpc_tx_point_call_abort,		"CallAbort") \
+	EM(rxrpc_tx_point_call_ack,		"CallAck") \
+	EM(rxrpc_tx_point_call_data_frag,	"CallDataFrag") \
+	EM(rxrpc_tx_point_call_data_nofrag,	"CallDataNofrag") \
+	EM(rxrpc_tx_point_call_final_resend,	"CallFinalResend") \
+	EM(rxrpc_tx_point_conn_abort,		"ConnAbort") \
+	EM(rxrpc_tx_point_reject,		"Reject") \
+	EM(rxrpc_tx_point_rxkad_challenge,	"RxkadChall") \
+	EM(rxrpc_tx_point_rxkad_response,	"RxkadResp") \
+	EM(rxrpc_tx_point_version_keepalive,	"VerKeepalive") \
+	E_(rxrpc_tx_point_version_reply,	"VerReply")
 
 /*
  * Export enum symbols via userspace.
@@ -488,7 +488,7 @@ rxrpc_propose_ack_traces;
 rxrpc_propose_ack_outcomes;
 rxrpc_congest_modes;
 rxrpc_congest_changes;
-rxrpc_tx_fail_traces;
+rxrpc_tx_points;
 
 /*
  * Now redefine the EM() and E_() macros to map the enums to the strings that
@@ -801,7 +801,7 @@ TRACE_EVENT(rxrpc_transmit,
 	    );
 
 TRACE_EVENT(rxrpc_rx_data,
-	    TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq,
+	    TP_PROTO(unsigned int call, rxrpc_seq_t seq,
 		     rxrpc_serial_t serial, u8 flags, u8 anno),
 
 	    TP_ARGS(call, seq, serial, flags, anno),
@@ -815,7 +815,7 @@ TRACE_EVENT(rxrpc_rx_data,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call->debug_id;
+		    __entry->call = call;
 		    __entry->seq = seq;
 		    __entry->serial = serial;
 		    __entry->flags = flags;
@@ -918,6 +918,37 @@ TRACE_EVENT(rxrpc_rx_rwind_change,
 		      __entry->wake ? " wake" : "")
 	    );
 
+TRACE_EVENT(rxrpc_tx_packet,
+	    TP_PROTO(unsigned int call_id, struct rxrpc_wire_header *whdr,
+		     enum rxrpc_tx_point where),
+
+	    TP_ARGS(call_id, whdr, where),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,			call	)
+		    __field(enum rxrpc_tx_point,		where	)
+		    __field_struct(struct rxrpc_wire_header,	whdr	)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->call = call_id;
+		    memcpy(&__entry->whdr, whdr, sizeof(__entry->whdr));
+			   ),
+
+	    TP_printk("c=%08x %08x:%08x:%08x:%04x %08x %08x %02x %02x %s %s",
+		      __entry->call,
+		      ntohl(__entry->whdr.epoch),
+		      ntohl(__entry->whdr.cid),
+		      ntohl(__entry->whdr.callNumber),
+		      ntohs(__entry->whdr.serviceId),
+		      ntohl(__entry->whdr.serial),
+		      ntohl(__entry->whdr.seq),
+		      __entry->whdr.type, __entry->whdr.flags,
+		      __entry->whdr.type <= 15 ?
+		      __print_symbolic(__entry->whdr.type, rxrpc_pkts) : "?UNK",
+		      __print_symbolic(__entry->where, rxrpc_tx_points))
+	    );
+
 TRACE_EVENT(rxrpc_tx_data,
 	    TP_PROTO(struct rxrpc_call *call, rxrpc_seq_t seq,
 		     rxrpc_serial_t serial, u8 flags, bool retrans, bool lose),
@@ -928,6 +959,8 @@ TRACE_EVENT(rxrpc_tx_data,
 		    __field(unsigned int,		call		)
 		    __field(rxrpc_seq_t,		seq		)
 		    __field(rxrpc_serial_t,		serial		)
+		    __field(u32,			cid		)
+		    __field(u32,			call_id		)
 		    __field(u8,				flags		)
 		    __field(bool,			retrans		)
 		    __field(bool,			lose		)
@@ -935,6 +968,8 @@ TRACE_EVENT(rxrpc_tx_data,
 
 	    TP_fast_assign(
 		    __entry->call = call->debug_id;
+		    __entry->cid = call->cid;
+		    __entry->call_id = call->call_id;
 		    __entry->seq = seq;
 		    __entry->serial = serial;
 		    __entry->flags = flags;
@@ -942,8 +977,10 @@ TRACE_EVENT(rxrpc_tx_data,
 		    __entry->lose = lose;
 			   ),
 
-	    TP_printk("c=%08x DATA %08x q=%08x fl=%02x%s%s",
+	    TP_printk("c=%08x DATA %08x:%08x %08x q=%08x fl=%02x%s%s",
 		      __entry->call,
+		      __entry->cid,
+		      __entry->call_id,
 		      __entry->serial,
 		      __entry->seq,
 		      __entry->flags,
@@ -952,7 +989,7 @@ TRACE_EVENT(rxrpc_tx_data,
 	    );
 
 TRACE_EVENT(rxrpc_tx_ack,
-	    TP_PROTO(struct rxrpc_call *call, rxrpc_serial_t serial,
+	    TP_PROTO(unsigned int call, rxrpc_serial_t serial,
 		     rxrpc_seq_t ack_first, rxrpc_serial_t ack_serial,
 		     u8 reason, u8 n_acks),
 
@@ -968,7 +1005,7 @@ TRACE_EVENT(rxrpc_tx_ack,
 			     ),
 
 	    TP_fast_assign(
-		    __entry->call = call ? call->debug_id : 0;
+		    __entry->call = call;
 		    __entry->serial = serial;
 		    __entry->ack_first = ack_first;
 		    __entry->ack_serial = ack_serial;
@@ -1434,29 +1471,29 @@ TRACE_EVENT(rxrpc_rx_icmp,
 
 TRACE_EVENT(rxrpc_tx_fail,
 	    TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial, int ret,
-		     enum rxrpc_tx_fail_trace what),
+		     enum rxrpc_tx_point where),
 
-	    TP_ARGS(debug_id, serial, ret, what),
+	    TP_ARGS(debug_id, serial, ret, where),
 
 	    TP_STRUCT__entry(
 		    __field(unsigned int,		debug_id	)
 		    __field(rxrpc_serial_t,		serial		)
 		    __field(int,			ret		)
-		    __field(enum rxrpc_tx_fail_trace,   what		)
+		    __field(enum rxrpc_tx_point,	where		)
 			     ),
 
 	    TP_fast_assign(
 		    __entry->debug_id = debug_id;
 		    __entry->serial = serial;
 		    __entry->ret = ret;
-		    __entry->what = what;
+		    __entry->where = where;
 			   ),
 
 	    TP_printk("c=%08x r=%x ret=%d %s",
 		      __entry->debug_id,
 		      __entry->serial,
 		      __entry->ret,
-		      __print_symbolic(__entry->what, rxrpc_tx_fail_traces))
+		      __print_symbolic(__entry->where, rxrpc_tx_points))
 	    );
 
 TRACE_EVENT(rxrpc_call_reset,
diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5fb7d3254d9e..7eee955a768a 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -420,6 +420,7 @@ struct rxrpc_connection {
 	struct rxrpc_channel {
 		unsigned long		final_ack_at;	/* Time at which to issue final ACK */
 		struct rxrpc_call __rcu	*call;		/* Active call */
+		unsigned int		call_debug_id;	/* call->debug_id */
 		u32			call_id;	/* ID of current call */
 		u32			call_counter;	/* Call ID counter */
 		u32			last_call;	/* ID of last call */
diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c
index e4bfbd7e48a8..f8f37188a932 100644
--- a/net/rxrpc/conn_client.c
+++ b/net/rxrpc/conn_client.c
@@ -590,6 +590,7 @@ static void rxrpc_activate_one_channel(struct rxrpc_connection *conn,
 	 */
 	smp_wmb();
 	chan->call_id	= call_id;
+	chan->call_debug_id = call->debug_id;
 	rcu_assign_pointer(chan->call, call);
 	wake_up(&call->waitq);
 }
diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c
index d46a68807f08..84d40ba9856f 100644
--- a/net/rxrpc/conn_event.c
+++ b/net/rxrpc/conn_event.c
@@ -129,7 +129,7 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 		_proto("Tx ABORT %%%u { %d } [re]", serial, conn->local_abort);
 		break;
 	case RXRPC_PACKET_TYPE_ACK:
-		trace_rxrpc_tx_ack(NULL, serial,
+		trace_rxrpc_tx_ack(chan->call_debug_id, serial,
 				   ntohl(pkt.ack.firstPacket),
 				   ntohl(pkt.ack.serial),
 				   pkt.ack.reason, 0);
@@ -140,8 +140,11 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn,
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, ioc, len);
 	conn->params.peer->last_tx_at = ktime_get_real();
 	if (ret < 0)
-		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
-				    rxrpc_tx_fail_call_final_resend);
+		trace_rxrpc_tx_fail(chan->call_debug_id, serial, ret,
+				    rxrpc_tx_point_call_final_resend);
+	else
+		trace_rxrpc_tx_packet(chan->call_debug_id, &pkt.whdr,
+				      rxrpc_tx_point_call_final_resend);
 
 	_leave("");
 }
@@ -242,11 +245,13 @@ static int rxrpc_abort_connection(struct rxrpc_connection *conn,
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
-				    rxrpc_tx_fail_conn_abort);
+				    rxrpc_tx_point_conn_abort);
 		_debug("sendmsg failed: %d", ret);
 		return -EAGAIN;
 	}
 
+	trace_rxrpc_tx_packet(conn->debug_id, &whdr, rxrpc_tx_point_conn_abort);
+
 	conn->params.peer->last_tx_at = ktime_get_real();
 
 	_leave(" = 0");
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 608d078a4981..8989d760b6b2 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -496,7 +496,7 @@ next_subpacket:
 			return rxrpc_proto_abort("LSA", call, seq);
 	}
 
-	trace_rxrpc_rx_data(call, seq, serial, flags, annotation);
+	trace_rxrpc_rx_data(call->debug_id, seq, serial, flags, annotation);
 	if (before_eq(seq, hard_ack)) {
 		ack = RXRPC_ACK_DUPLICATE;
 		ack_serial = serial;
@@ -592,6 +592,10 @@ ack:
 		rxrpc_propose_ACK(call, ack, skew, ack_serial,
 				  immediate_ack, true,
 				  rxrpc_propose_ack_input_data);
+	else
+		rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial,
+				  false, true,
+				  rxrpc_propose_ack_input_data);
 
 	if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1)
 		rxrpc_notify_socket(call);
@@ -1262,6 +1266,11 @@ void rxrpc_data_ready(struct sock *udp_sk)
 			/* But otherwise we need to retransmit the final packet
 			 * from data cached in the connection record.
 			 */
+			if (sp->hdr.type == RXRPC_PACKET_TYPE_DATA)
+				trace_rxrpc_rx_data(chan->call_debug_id,
+						    sp->hdr.seq,
+						    sp->hdr.serial,
+						    sp->hdr.flags, 0);
 			rxrpc_post_packet_to_conn(conn, skb);
 			goto out_unlock;
 		}
diff --git a/net/rxrpc/local_event.c b/net/rxrpc/local_event.c
index 8325f1b86840..13bd8a4dfac7 100644
--- a/net/rxrpc/local_event.c
+++ b/net/rxrpc/local_event.c
@@ -72,7 +72,10 @@ static void rxrpc_send_version_request(struct rxrpc_local *local,
 	ret = kernel_sendmsg(local->socket, &msg, iov, 2, len);
 	if (ret < 0)
 		trace_rxrpc_tx_fail(local->debug_id, 0, ret,
-				    rxrpc_tx_fail_version_reply);
+				    rxrpc_tx_point_version_reply);
+	else
+		trace_rxrpc_tx_packet(local->debug_id, &whdr,
+				      rxrpc_tx_point_version_reply);
 
 	_leave("");
 }
diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c
index f03de1c59ba3..801dbf3d3478 100644
--- a/net/rxrpc/output.c
+++ b/net/rxrpc/output.c
@@ -183,7 +183,7 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 
 	serial = atomic_inc_return(&conn->serial);
 	pkt->whdr.serial = htonl(serial);
-	trace_rxrpc_tx_ack(call, serial,
+	trace_rxrpc_tx_ack(call->debug_id, serial,
 			   ntohl(pkt->ack.firstPacket),
 			   ntohl(pkt->ack.serial),
 			   pkt->ack.reason, pkt->ack.nAcks);
@@ -212,7 +212,10 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping,
 	conn->params.peer->last_tx_at = ktime_get_real();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
-				    rxrpc_tx_fail_call_ack);
+				    rxrpc_tx_point_call_ack);
+	else
+		trace_rxrpc_tx_packet(call->debug_id, &pkt->whdr,
+				      rxrpc_tx_point_call_ack);
 
 	if (call->state < RXRPC_CALL_COMPLETE) {
 		if (ret < 0) {
@@ -299,7 +302,10 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call)
 	conn->params.peer->last_tx_at = ktime_get_real();
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
-				    rxrpc_tx_fail_call_abort);
+				    rxrpc_tx_point_call_abort);
+	else
+		trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr,
+				      rxrpc_tx_point_call_abort);
 
 
 	rxrpc_put_connection(conn);
@@ -396,7 +402,10 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	up_read(&conn->params.local->defrag_sem);
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
-				    rxrpc_tx_fail_call_data_nofrag);
+				    rxrpc_tx_point_call_data_nofrag);
+	else
+		trace_rxrpc_tx_packet(call->debug_id, &whdr,
+				      rxrpc_tx_point_call_data_nofrag);
 	if (ret == -EMSGSIZE)
 		goto send_fragmentable;
 
@@ -488,7 +497,10 @@ send_fragmentable:
 
 	if (ret < 0)
 		trace_rxrpc_tx_fail(call->debug_id, serial, ret,
-				    rxrpc_tx_fail_call_data_frag);
+				    rxrpc_tx_point_call_data_frag);
+	else
+		trace_rxrpc_tx_packet(call->debug_id, &whdr,
+				      rxrpc_tx_point_call_data_frag);
 
 	up_write(&conn->params.local->defrag_sem);
 	goto done;
@@ -545,7 +557,10 @@ void rxrpc_reject_packets(struct rxrpc_local *local)
 			ret = kernel_sendmsg(local->socket, &msg, iov, 2, size);
 			if (ret < 0)
 				trace_rxrpc_tx_fail(local->debug_id, 0, ret,
-						    rxrpc_tx_fail_reject);
+						    rxrpc_tx_point_reject);
+			else
+				trace_rxrpc_tx_packet(local->debug_id, &whdr,
+						      rxrpc_tx_point_reject);
 		}
 
 		rxrpc_free_skb(skb, rxrpc_skb_rx_freed);
@@ -597,7 +612,10 @@ void rxrpc_send_keepalive(struct rxrpc_peer *peer)
 	ret = kernel_sendmsg(peer->local->socket, &msg, iov, 2, len);
 	if (ret < 0)
 		trace_rxrpc_tx_fail(peer->debug_id, 0, ret,
-				    rxrpc_tx_fail_version_keepalive);
+				    rxrpc_tx_point_version_keepalive);
+	else
+		trace_rxrpc_tx_packet(peer->debug_id, &whdr,
+				      rxrpc_tx_point_version_keepalive);
 
 	peer->last_tx_at = ktime_get_real();
 	_leave("");
diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 278ac0807a60..6988073ae842 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -665,11 +665,13 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn)
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 2, len);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
-				    rxrpc_tx_fail_conn_challenge);
+				    rxrpc_tx_point_rxkad_challenge);
 		return -EAGAIN;
 	}
 
 	conn->params.peer->last_tx_at = ktime_get_real();
+	trace_rxrpc_tx_packet(conn->debug_id, &whdr,
+			      rxrpc_tx_point_rxkad_challenge);
 	_leave(" = 0");
 	return 0;
 }
@@ -721,11 +723,12 @@ static int rxkad_send_response(struct rxrpc_connection *conn,
 	ret = kernel_sendmsg(conn->params.local->socket, &msg, iov, 3, len);
 	if (ret < 0) {
 		trace_rxrpc_tx_fail(conn->debug_id, serial, ret,
-				    rxrpc_tx_fail_conn_response);
+				    rxrpc_tx_point_rxkad_response);
 		return -EAGAIN;
 	}
 
 	conn->params.peer->last_tx_at = ktime_get_real();
+	trace_rxrpc_tx_packet(0, &whdr, rxrpc_tx_point_rxkad_response);
 	_leave(" = 0");
 	return 0;
 }
-- 
cgit v1.2.3


From 197445aff13c164794efb6d87a28762e843622d8 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:37 +0100
Subject: rxrpc: Fix ACK proposal tracepoint

Fix the ACK proposal tracepoint outcomes list by making the one that's an
empty string not an empty string - which gets rendered as a hex number
string instead.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index 2aa6f615b60d..c1a800a6dee3 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -396,7 +396,7 @@ enum rxrpc_tx_point {
 #define rxrpc_propose_ack_outcomes \
 	EM(rxrpc_propose_ack_subsume,		" Subsume") \
 	EM(rxrpc_propose_ack_update,		" Update") \
-	E_(rxrpc_propose_ack_use,		"")
+	E_(rxrpc_propose_ack_use,		" New")
 
 #define rxrpc_congest_modes \
 	EM(RXRPC_CALL_CONGEST_AVOIDANCE,	"CongAvoid") \
-- 
cgit v1.2.3


From 4272d3034e69aea6e17085ba285d14f5824b430d Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:37 +0100
Subject: rxrpc: Trace socket notification

Trace notifications from the softirq side of the socket to the
process-context side.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 include/trace/events/rxrpc.h | 20 ++++++++++++++++++++
 net/rxrpc/input.c            |  4 +++-
 2 files changed, 23 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/rxrpc.h b/include/trace/events/rxrpc.h
index c1a800a6dee3..196587b8f204 100644
--- a/include/trace/events/rxrpc.h
+++ b/include/trace/events/rxrpc.h
@@ -1528,6 +1528,26 @@ TRACE_EVENT(rxrpc_call_reset,
 		      __entry->tx_seq, __entry->rx_seq)
 	    );
 
+TRACE_EVENT(rxrpc_notify_socket,
+	    TP_PROTO(unsigned int debug_id, rxrpc_serial_t serial),
+
+	    TP_ARGS(debug_id, serial),
+
+	    TP_STRUCT__entry(
+		    __field(unsigned int,		debug_id	)
+		    __field(rxrpc_serial_t,		serial		)
+			     ),
+
+	    TP_fast_assign(
+		    __entry->debug_id = debug_id;
+		    __entry->serial = serial;
+			   ),
+
+	    TP_printk("c=%08x r=%08x",
+		      __entry->debug_id,
+		      __entry->serial)
+	    );
+
 #endif /* _TRACE_RXRPC_H */
 
 /* This part must be outside protection */
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 8989d760b6b2..cfdc199c6351 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -597,8 +597,10 @@ ack:
 				  false, true,
 				  rxrpc_propose_ack_input_data);
 
-	if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1)
+	if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) {
+		trace_rxrpc_notify_socket(call->debug_id, serial);
 		rxrpc_notify_socket(call);
+	}
 	_leave(" [queued]");
 }
 
-- 
cgit v1.2.3


From 4075295ab87670e33eaf98389e319ce84c54c8e4 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:37 +0100
Subject: rxrpc: Increase the size of a call's Rx window

Increase the size of a call's Rx window from 32 to 63 - ie. one less than
the size of the ring buffer.  This makes large data transfers perform
better when the Tx window on the other side is around 64 (as is the case
with Auristor's YFS fileserver).

If the server window size is ~32 or smaller, this should make no
difference.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/ar-internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 7eee955a768a..e791d35ee34b 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -589,7 +589,7 @@ struct rxrpc_call {
 	 */
 #define RXRPC_RXTX_BUFF_SIZE	64
 #define RXRPC_RXTX_BUFF_MASK	(RXRPC_RXTX_BUFF_SIZE - 1)
-#define RXRPC_INIT_RX_WINDOW_SIZE 32
+#define RXRPC_INIT_RX_WINDOW_SIZE 63
 	struct sk_buff		**rxtx_buffer;
 	u8			*rxtx_annotations;
 #define RXRPC_TX_ANNO_ACK	0
-- 
cgit v1.2.3


From a71a2651bdd3ad9ccae7d8e8c6782727c7ecba98 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:37 +0100
Subject: rxrpc: Propose, but don't immediately transmit, the final ACK for a
 call

The final ACK that closes out an rxrpc call needs to be transmitted by the
client unless we're going to follow up with a DATA packet for a new call on
the same channel (which implicitly ACK's the previous call, thereby saving
an ACK).

Currently, we don't do that, so if no follow on call is immediately
forthcoming, the server will resend the last DATA packet - at which point
rxrpc_conn_retransmit_call() will be triggered and will (re)send the final
ACK.  But the server has to hold on to the last packet until the ACK is
received, thereby holding up its resources.

Fix the client side to propose a delayed final ACK, to be transmitted after
a short delay, assuming the call isn't superseded by a new one.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/recvmsg.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 7bff716e911e..02f1f768e16a 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -144,13 +144,11 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial)
 	trace_rxrpc_receive(call, rxrpc_receive_end, 0, call->rx_top);
 	ASSERTCMP(call->rx_hard_ack, ==, call->rx_top);
 
-#if 0 // TODO: May want to transmit final ACK under some circumstances anyway
 	if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) {
-		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, true, false,
+		rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true,
 				  rxrpc_propose_ack_terminal_ack);
-		rxrpc_send_ack_packet(call, false, NULL);
+		//rxrpc_send_ack_packet(call, false, NULL);
 	}
-#endif
 
 	write_lock_bh(&call->state_lock);
 
-- 
cgit v1.2.3


From d0b35a42031a3107a5735e0d0a605a68f530a96b Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Mon, 23 Jul 2018 17:18:38 +0100
Subject: rxrpc: Transmit more ACKs during data reception

Immediately flush any outstanding ACK on entry to rxrpc_recvmsg_data() -
which transfers data to the target buffers - if we previously had an Rx
underrun (ie. we returned -EAGAIN because we ran out of received data).
This lets the server know what we've managed to receive something.

Also flush any outstanding ACK after calling the function if it hit -EAGAIN
to let the server know we processed some data.

It might be better to send more ACKs, possibly on a time-based scheme, but
that needs some more consideration.

With this and some additional AFS patches, it is possible to get large
unencrypted O_DIRECT reads to be almost as fast as NFS over TCP.  It looks
like it might be theoretically possible to improve performance yet more for
a server running a single operation as investigation of packet timestamps
indicates that the server keeps stalling.

The issue appears to be that rxrpc runs in to trouble with ACK packets
getting batched together (up to ~32 at a time) somewhere between the IP
transmit queue on the client and the ethernet receive queue on the server.

However, this case isn't too much of a worry as even a lightly loaded
server should be receiving sufficient packet flux to flush the ACK packets
to the UDP socket.

Signed-off-by: David Howells <dhowells@redhat.com>
---
 net/rxrpc/ar-internal.h |  1 +
 net/rxrpc/recvmsg.c     | 17 +++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index e791d35ee34b..9d9278a13d91 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -479,6 +479,7 @@ enum rxrpc_call_flag {
 	RXRPC_CALL_RETRANS_TIMEOUT,	/* Retransmission due to timeout occurred */
 	RXRPC_CALL_BEGAN_RX_TIMER,	/* We began the expect_rx_by timer */
 	RXRPC_CALL_RX_HEARD,		/* The peer responded at least once to this call */
+	RXRPC_CALL_RX_UNDERRUN,		/* Got data underrun */
 };
 
 /*
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index 02f1f768e16a..a57ea96c84ea 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -313,6 +313,10 @@ static int rxrpc_recvmsg_data(struct socket *sock, struct rxrpc_call *call,
 	unsigned int rx_pkt_offset, rx_pkt_len;
 	int ix, copy, ret = -EAGAIN, ret2;
 
+	if (test_and_clear_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags) &&
+	    call->ackr_reason)
+		rxrpc_send_ack_packet(call, false, NULL);
+
 	rx_pkt_offset = call->rx_pkt_offset;
 	rx_pkt_len = call->rx_pkt_len;
 
@@ -412,6 +416,8 @@ out:
 done:
 	trace_rxrpc_recvmsg(call, rxrpc_recvmsg_data_return, seq,
 			    rx_pkt_offset, rx_pkt_len, ret);
+	if (ret == -EAGAIN)
+		set_bit(RXRPC_CALL_RX_UNDERRUN, &call->flags);
 	return ret;
 }
 
@@ -684,6 +690,17 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 read_phase_complete:
 	ret = 1;
 out:
+	switch (call->ackr_reason) {
+	case RXRPC_ACK_IDLE:
+		break;
+	case RXRPC_ACK_DELAY:
+		if (ret != -EAGAIN)
+			break;
+		/* Fall through */
+	default:
+		rxrpc_send_ack_packet(call, false, NULL);
+	}
+
 	if (_service)
 		*_service = call->service_id;
 	mutex_unlock(&call->user_mutex);
-- 
cgit v1.2.3


From b0a39d356ae1478a5876bb02ba08af155a3a5554 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 1 Aug 2018 14:18:50 +0100
Subject: ASoC: wcd9335: Fix build due to CLASS-H Controller support

This reverts commit c8cb5f775c8dac (ASoC: vert "ASoC: wcd9335: add
CLASS-H Controller support) due to missing dependencies.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Makefile   |   2 +-
 sound/soc/codecs/wcd-clsh.c | 605 --------------------------------------------
 sound/soc/codecs/wcd-clsh.h |  49 ----
 sound/soc/codecs/wcd9335.c  |  10 -
 4 files changed, 1 insertion(+), 665 deletions(-)
 delete mode 100644 sound/soc/codecs/wcd-clsh.c
 delete mode 100644 sound/soc/codecs/wcd-clsh.h

diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index e3a3d4694e15..01410b63daac 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -192,7 +192,7 @@ snd-soc-twl4030-objs := twl4030.o
 snd-soc-twl6040-objs := twl6040.o
 snd-soc-uda134x-objs := uda134x.o
 snd-soc-uda1380-objs := uda1380.o
-snd-soc-wcd9335-objs := wcd-clsh.o wcd9335.o
+snd-soc-wcd9335-objs := wcd9335.o
 snd-soc-wl1273-objs := wl1273.o
 snd-soc-wm-adsp-objs := wm_adsp.o
 snd-soc-wm0010-objs := wm0010.o
diff --git a/sound/soc/codecs/wcd-clsh.c b/sound/soc/codecs/wcd-clsh.c
deleted file mode 100644
index 2393456cbd97..000000000000
--- a/sound/soc/codecs/wcd-clsh.c
+++ /dev/null
@@ -1,605 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
-// Copyright (c) 2017-2018, Linaro Limited
-
-#include <linux/slab.h>
-#include <sound/soc.h>
-#include <linux/kernel.h>
-#include <linux/delay.h>
-#include <linux/mfd/wcd9335/wcd9335.h>
-#include <linux/mfd/wcd9335/registers.h>
-#include "wcd-clsh.h"
-
-struct wcd_clsh_ctrl {
-	int state;
-	int mode;
-	int flyback_users;
-	int buck_users;
-	int clsh_users;
-	int codec_version;
-	struct snd_soc_component *comp;
-};
-
-/* Class-H registers for codecs from and above WCD9335 */
-#define WCD9XXX_A_CDC_RX0_RX_PATH_CFG0			WCD9335_REG(0xB, 0x42)
-#define WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK		BIT(6)
-#define WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE		BIT(6)
-#define WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE		0
-#define WCD9XXX_A_CDC_RX1_RX_PATH_CFG0			WCD9335_REG(0xB, 0x56)
-#define WCD9XXX_A_CDC_RX2_RX_PATH_CFG0			WCD9335_REG(0xB, 0x6A)
-#define WCD9XXX_A_CDC_CLSH_K1_MSB			WCD9335_REG(0xC, 0x08)
-#define WCD9XXX_A_CDC_CLSH_K1_MSB_COEF_MASK		GENMASK(3, 0)
-#define WCD9XXX_A_CDC_CLSH_K1_LSB			WCD9335_REG(0xC, 0x09)
-#define WCD9XXX_A_CDC_CLSH_K1_LSB_COEF_MASK		GENMASK(7, 0)
-#define WCD9XXX_A_ANA_RX_SUPPLIES			WCD9335_REG(0x6, 0x08)
-#define WCD9XXX_A_ANA_RX_REGULATOR_MODE_MASK		BIT(1)
-#define WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_H		0
-#define WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_AB		BIT(1)
-#define WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_MASK		BIT(2)
-#define WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_UHQA		BIT(2)
-#define WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_DEFAULT		0
-#define WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_MASK		BIT(3)
-#define WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_UHQA		BIT(3)
-#define WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_DEFAULT		0
-#define WCD9XXX_A_ANA_RX_VNEG_EN_MASK			BIT(6)
-#define WCD9XXX_A_ANA_RX_VNEG_EN_SHIFT			6
-#define WCD9XXX_A_ANA_RX_VNEG_ENABLE			BIT(6)
-#define WCD9XXX_A_ANA_RX_VNEG_DISABLE			0
-#define WCD9XXX_A_ANA_RX_VPOS_EN_MASK			BIT(7)
-#define WCD9XXX_A_ANA_RX_VPOS_EN_SHIFT			7
-#define WCD9XXX_A_ANA_RX_VPOS_ENABLE			BIT(7)
-#define WCD9XXX_A_ANA_RX_VPOS_DISABLE			0
-#define WCD9XXX_A_ANA_HPH				WCD9335_REG(0x6, 0x09)
-#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_MASK		GENMASK(3, 2)
-#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_UHQA		0x08
-#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_LP			0x04
-#define WCD9XXX_A_ANA_HPH_PWR_LEVEL_NORMAL		0x0
-#define WCD9XXX_A_CDC_CLSH_CRC				WCD9335_REG(0xC, 0x01)
-#define WCD9XXX_A_CDC_CLSH_CRC_CLK_EN_MASK		BIT(0)
-#define WCD9XXX_A_CDC_CLSH_CRC_CLK_ENABLE		BIT(0)
-#define WCD9XXX_A_CDC_CLSH_CRC_CLK_DISABLE		0
-#define WCD9XXX_FLYBACK_EN				WCD9335_REG(0x6, 0xA4)
-#define WCD9XXX_FLYBACK_EN_DELAY_SEL_MASK		GENMASK(6, 5)
-#define WCD9XXX_FLYBACK_EN_DELAY_26P25_US		0x40
-#define WCD9XXX_FLYBACK_EN_RESET_BY_EXT_MASK		BIT(4)
-#define WCD9XXX_FLYBACK_EN_PWDN_WITHOUT_DELAY		BIT(4)
-#define WCD9XXX_FLYBACK_EN_PWDN_WITH_DELAY			0
-#define WCD9XXX_RX_BIAS_FLYB_BUFF			WCD9335_REG(0x6, 0xC7)
-#define WCD9XXX_RX_BIAS_FLYB_VNEG_5_UA_MASK		GENMASK(7, 4)
-#define WCD9XXX_RX_BIAS_FLYB_VPOS_5_UA_MASK		GENMASK(0, 3)
-#define WCD9XXX_HPH_L_EN				WCD9335_REG(0x6, 0xD3)
-#define WCD9XXX_HPH_CONST_SEL_L_MASK			GENMASK(7, 3)
-#define WCD9XXX_HPH_CONST_SEL_BYPASS			0
-#define WCD9XXX_HPH_CONST_SEL_LP_PATH			0x40
-#define WCD9XXX_HPH_CONST_SEL_HQ_PATH			0x80
-#define WCD9XXX_HPH_R_EN				WCD9335_REG(0x6, 0xD6)
-#define WCD9XXX_HPH_REFBUFF_UHQA_CTL			WCD9335_REG(0x6, 0xDD)
-#define WCD9XXX_HPH_REFBUFF_UHQA_GAIN_MASK		GENMASK(2, 0)
-#define WCD9XXX_CLASSH_CTRL_VCL_2                       WCD9335_REG(0x6, 0x9B)
-#define WCD9XXX_CLASSH_CTRL_VCL_2_VREF_FILT_1_MASK	GENMASK(5, 4)
-#define WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_50KOHM	0x20
-#define WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_0KOHM	0x0
-#define WCD9XXX_CDC_RX1_RX_PATH_CTL			WCD9335_REG(0xB, 0x55)
-#define WCD9XXX_CDC_RX2_RX_PATH_CTL			WCD9335_REG(0xB, 0x69)
-#define WCD9XXX_CDC_CLK_RST_CTRL_MCLK_CONTROL		WCD9335_REG(0xD, 0x41)
-#define WCD9XXX_CDC_CLK_RST_CTRL_MCLK_EN_MASK		BIT(0)
-#define WCD9XXX_CDC_CLK_RST_CTRL_MCLK_11P3_EN_MASK	BIT(1)
-#define WCD9XXX_CLASSH_CTRL_CCL_1                       WCD9335_REG(0x6, 0x9C)
-#define WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_MASK	GENMASK(7, 4)
-#define WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA	0x50
-#define WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_30MA	0x30
-
-#define CLSH_REQ_ENABLE		true
-#define CLSH_REQ_DISABLE	false
-#define WCD_USLEEP_RANGE	50
-
-enum {
-	DAC_GAIN_0DB = 0,
-	DAC_GAIN_0P2DB,
-	DAC_GAIN_0P4DB,
-	DAC_GAIN_0P6DB,
-	DAC_GAIN_0P8DB,
-	DAC_GAIN_M0P2DB,
-	DAC_GAIN_M0P4DB,
-	DAC_GAIN_M0P6DB,
-};
-
-static inline void wcd_enable_clsh_block(struct wcd_clsh_ctrl *ctrl,
-					 bool enable)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	if ((enable && ++ctrl->clsh_users == 1) ||
-	    (!enable && --ctrl->clsh_users == 0))
-		snd_soc_component_update_bits(comp, WCD9XXX_A_CDC_CLSH_CRC,
-				      WCD9XXX_A_CDC_CLSH_CRC_CLK_EN_MASK,
-				      enable);
-	if (ctrl->clsh_users < 0)
-		ctrl->clsh_users = 0;
-}
-
-static inline bool wcd_clsh_enable_status(struct snd_soc_component *comp)
-{
-	return snd_soc_component_read32(comp, WCD9XXX_A_CDC_CLSH_CRC) &
-					WCD9XXX_A_CDC_CLSH_CRC_CLK_EN_MASK;
-}
-
-static inline void wcd_clsh_set_buck_mode(struct snd_soc_component *comp,
-					  int mode)
-{
-	/* set to HIFI */
-	if (mode == CLS_H_HIFI)
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_MASK,
-					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_UHQA);
-	else
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_MASK,
-					WCD9XXX_A_ANA_RX_VPOS_PWR_LVL_DEFAULT);
-}
-
-static inline void wcd_clsh_set_flyback_mode(struct snd_soc_component *comp,
-					     int mode)
-{
-	/* set to HIFI */
-	if (mode == CLS_H_HIFI)
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_MASK,
-					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_UHQA);
-	else
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_MASK,
-					WCD9XXX_A_ANA_RX_VNEG_PWR_LVL_DEFAULT);
-}
-
-static void wcd_clsh_buck_ctrl(struct wcd_clsh_ctrl *ctrl,
-			       int mode,
-			       bool enable)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	/* enable/disable buck */
-	if ((enable && (++ctrl->buck_users == 1)) ||
-	   (!enable && (--ctrl->buck_users == 0)))
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-				WCD9XXX_A_ANA_RX_VPOS_EN_MASK,
-				enable << WCD9XXX_A_ANA_RX_VPOS_EN_SHIFT);
-	/*
-	 * 500us sleep is required after buck enable/disable
-	 * as per HW requirement
-	 */
-	usleep_range(500, 500 + WCD_USLEEP_RANGE);
-}
-
-static void wcd_clsh_flyback_ctrl(struct wcd_clsh_ctrl *ctrl,
-				  int mode,
-				  bool enable)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	int vneg[] = {0x00, 0x40};
-
-	/* enable/disable flyback */
-	if ((enable && (++ctrl->flyback_users == 1)) ||
-	   (!enable && (--ctrl->flyback_users == 0))) {
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-				WCD9XXX_A_ANA_RX_VNEG_EN_MASK,
-				enable << WCD9XXX_A_ANA_RX_VNEG_EN_SHIFT);
-		/* 100usec delay is needed as per HW requirement */
-		usleep_range(100, 110);
-
-		if (enable && (WCD9335_IS_1_1(ctrl->codec_version))) {
-			wcd_clsh_set_flyback_mode(comp, CLS_H_HIFI);
-			snd_soc_component_update_bits(comp, WCD9XXX_FLYBACK_EN,
-					WCD9XXX_FLYBACK_EN_DELAY_SEL_MASK,
-					WCD9XXX_FLYBACK_EN_DELAY_26P25_US);
-			snd_soc_component_update_bits(comp, WCD9XXX_FLYBACK_EN,
-					WCD9XXX_FLYBACK_EN_RESET_BY_EXT_MASK,
-					WCD9XXX_FLYBACK_EN_PWDN_WITHOUT_DELAY);
-			vneg[0] = snd_soc_component_read32(comp,
-					       WCD9XXX_A_ANA_RX_SUPPLIES);
-			vneg[0] &= ~(0x40);
-			vneg[1] = vneg[0] | 0x40;
-
-			snd_soc_component_write(comp,
-					WCD9XXX_A_ANA_RX_SUPPLIES, vneg[0]);
-			snd_soc_component_write(comp,
-					WCD9XXX_A_ANA_RX_SUPPLIES, vneg[1]);
-			/* 500usec delay is needed as per HW requirement */
-			usleep_range(500, 510);
-			snd_soc_component_update_bits(comp, WCD9XXX_FLYBACK_EN,
-					WCD9XXX_FLYBACK_EN_RESET_BY_EXT_MASK,
-					WCD9XXX_FLYBACK_EN_PWDN_WITH_DELAY);
-			wcd_clsh_set_flyback_mode(comp, mode);
-		}
-
-	}
-	/*
-	 * 500us sleep is required after flyback enable/disable
-	 * as per HW requirement
-	 */
-	usleep_range(500, 500 + WCD_USLEEP_RANGE);
-}
-
-static void wcd_clsh_set_gain_path(struct wcd_clsh_ctrl *ctrl, int mode)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-	int val = 0;
-
-	switch (mode) {
-	case CLS_H_NORMAL:
-	case CLS_AB:
-		val = WCD9XXX_HPH_CONST_SEL_BYPASS;
-		break;
-	case CLS_H_HIFI:
-		val = WCD9XXX_HPH_CONST_SEL_HQ_PATH;
-		break;
-	case CLS_H_LP:
-		val = WCD9XXX_HPH_CONST_SEL_LP_PATH;
-		break;
-	};
-
-	snd_soc_component_update_bits(comp, WCD9XXX_HPH_L_EN,
-					WCD9XXX_HPH_CONST_SEL_L_MASK,
-					val);
-
-	snd_soc_component_update_bits(comp, WCD9XXX_HPH_R_EN,
-					WCD9XXX_HPH_CONST_SEL_L_MASK,
-					val);
-}
-
-static void wcd_clsh_set_hph_mode(struct snd_soc_component *comp,
-				  int mode)
-{
-	int val = 0, gain = 0, res_val;
-	int ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
-
-	res_val = WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_0KOHM;
-	switch (mode) {
-	case CLS_H_NORMAL:
-		res_val = WCD9XXX_CLASSH_CTRL_VCL_VREF_FILT_R_50KOHM;
-		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_NORMAL;
-		gain = DAC_GAIN_0DB;
-		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
-		break;
-	case CLS_AB:
-		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_NORMAL;
-		gain = DAC_GAIN_0DB;
-		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
-		break;
-	case CLS_H_HIFI:
-		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_UHQA;
-		gain = DAC_GAIN_M0P2DB;
-		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_50MA;
-		break;
-	case CLS_H_LP:
-		val = WCD9XXX_A_ANA_HPH_PWR_LEVEL_LP;
-		ipeak = WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_30MA;
-		break;
-	};
-
-	snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_HPH,
-					WCD9XXX_A_ANA_HPH_PWR_LEVEL_MASK, val);
-	snd_soc_component_update_bits(comp, WCD9XXX_CLASSH_CTRL_VCL_2,
-				WCD9XXX_CLASSH_CTRL_VCL_2_VREF_FILT_1_MASK,
-				res_val);
-	if (mode != CLS_H_LP)
-		snd_soc_component_update_bits(comp,
-					WCD9XXX_HPH_REFBUFF_UHQA_CTL,
-					WCD9XXX_HPH_REFBUFF_UHQA_GAIN_MASK,
-					gain);
-	snd_soc_component_update_bits(comp, WCD9XXX_CLASSH_CTRL_CCL_1,
-				WCD9XXX_CLASSH_CTRL_CCL_1_DELTA_IPEAK_MASK,
-				ipeak);
-}
-
-static void wcd_clsh_set_flyback_current(struct snd_soc_component *comp,
-					 int mode)
-{
-
-	snd_soc_component_update_bits(comp, WCD9XXX_RX_BIAS_FLYB_BUFF,
-				WCD9XXX_RX_BIAS_FLYB_VPOS_5_UA_MASK, 0x0A);
-	snd_soc_component_update_bits(comp, WCD9XXX_RX_BIAS_FLYB_BUFF,
-				WCD9XXX_RX_BIAS_FLYB_VNEG_5_UA_MASK, 0x0A);
-	/* Sleep needed to avoid click and pop as per HW requirement */
-	usleep_range(100, 110);
-}
-
-static void wcd_clsh_set_buck_regulator_mode(struct snd_soc_component *comp,
-					     int mode)
-{
-	if (mode == CLS_AB)
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-					WCD9XXX_A_ANA_RX_REGULATOR_MODE_MASK,
-					WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_AB);
-	else
-		snd_soc_component_update_bits(comp, WCD9XXX_A_ANA_RX_SUPPLIES,
-					WCD9XXX_A_ANA_RX_REGULATOR_MODE_MASK,
-					WCD9XXX_A_ANA_RX_REGULATOR_MODE_CLS_H);
-}
-
-static void wcd_clsh_state_lo(struct wcd_clsh_ctrl *ctrl, int req_state,
-			      bool is_enable, int mode)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	if (mode != CLS_AB) {
-		dev_err(comp->dev, "%s: LO cannot be in this mode: %d\n",
-			__func__, mode);
-		return;
-	}
-
-	if (is_enable) {
-		wcd_clsh_set_buck_regulator_mode(comp, mode);
-		wcd_clsh_set_buck_mode(comp, mode);
-		wcd_clsh_set_flyback_mode(comp, mode);
-		wcd_clsh_flyback_ctrl(ctrl, mode, true);
-		wcd_clsh_set_flyback_current(comp, mode);
-		wcd_clsh_buck_ctrl(ctrl, mode, true);
-	} else {
-		wcd_clsh_buck_ctrl(ctrl, mode, false);
-		wcd_clsh_flyback_ctrl(ctrl, mode, false);
-		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
-		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
-		wcd_clsh_set_buck_regulator_mode(comp, CLS_H_NORMAL);
-	}
-}
-
-static void wcd_clsh_state_hph_r(struct wcd_clsh_ctrl *ctrl, int req_state,
-				 bool is_enable, int mode)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	if (mode == CLS_H_NORMAL) {
-		dev_err(comp->dev, "%s: Normal mode not applicable for hph_r\n",
-			__func__);
-		return;
-	}
-
-	if (is_enable) {
-		if (mode != CLS_AB) {
-			wcd_enable_clsh_block(ctrl, true);
-			/*
-			 * These K1 values depend on the Headphone Impedance
-			 * For now it is assumed to be 16 ohm
-			 */
-			snd_soc_component_update_bits(comp,
-					WCD9XXX_A_CDC_CLSH_K1_MSB,
-					WCD9XXX_A_CDC_CLSH_K1_MSB_COEF_MASK,
-					0x00);
-			snd_soc_component_update_bits(comp,
-					WCD9XXX_A_CDC_CLSH_K1_LSB,
-					WCD9XXX_A_CDC_CLSH_K1_LSB_COEF_MASK,
-					0xC0);
-			snd_soc_component_update_bits(comp,
-					    WCD9XXX_A_CDC_RX2_RX_PATH_CFG0,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE);
-		}
-		wcd_clsh_set_buck_regulator_mode(comp, mode);
-		wcd_clsh_set_flyback_mode(comp, mode);
-		wcd_clsh_flyback_ctrl(ctrl, mode, true);
-		wcd_clsh_set_flyback_current(comp, mode);
-		wcd_clsh_set_buck_mode(comp, mode);
-		wcd_clsh_buck_ctrl(ctrl, mode, true);
-		wcd_clsh_set_hph_mode(comp, mode);
-		wcd_clsh_set_gain_path(ctrl, mode);
-	} else {
-		wcd_clsh_set_hph_mode(comp, CLS_H_NORMAL);
-
-		if (mode != CLS_AB) {
-			snd_soc_component_update_bits(comp,
-					    WCD9XXX_A_CDC_RX2_RX_PATH_CFG0,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE);
-			wcd_enable_clsh_block(ctrl, false);
-		}
-		/* buck and flyback set to default mode and disable */
-		wcd_clsh_buck_ctrl(ctrl, CLS_H_NORMAL, false);
-		wcd_clsh_flyback_ctrl(ctrl, CLS_H_NORMAL, false);
-		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
-		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
-		wcd_clsh_set_buck_regulator_mode(comp, CLS_H_NORMAL);
-	}
-}
-
-static void wcd_clsh_state_hph_l(struct wcd_clsh_ctrl *ctrl, int req_state,
-				 bool is_enable, int mode)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	if (mode == CLS_H_NORMAL) {
-		dev_err(comp->dev, "%s: Normal mode not applicable for hph_l\n",
-			__func__);
-		return;
-	}
-
-	if (is_enable) {
-		if (mode != CLS_AB) {
-			wcd_enable_clsh_block(ctrl, true);
-			/*
-			 * These K1 values depend on the Headphone Impedance
-			 * For now it is assumed to be 16 ohm
-			 */
-			snd_soc_component_update_bits(comp,
-					WCD9XXX_A_CDC_CLSH_K1_MSB,
-					WCD9XXX_A_CDC_CLSH_K1_MSB_COEF_MASK,
-					0x00);
-			snd_soc_component_update_bits(comp,
-					WCD9XXX_A_CDC_CLSH_K1_LSB,
-					WCD9XXX_A_CDC_CLSH_K1_LSB_COEF_MASK,
-					0xC0);
-			snd_soc_component_update_bits(comp,
-					    WCD9XXX_A_CDC_RX1_RX_PATH_CFG0,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE);
-		}
-		wcd_clsh_set_buck_regulator_mode(comp, mode);
-		wcd_clsh_set_flyback_mode(comp, mode);
-		wcd_clsh_flyback_ctrl(ctrl, mode, true);
-		wcd_clsh_set_flyback_current(comp, mode);
-		wcd_clsh_set_buck_mode(comp, mode);
-		wcd_clsh_buck_ctrl(ctrl, mode, true);
-		wcd_clsh_set_hph_mode(comp, mode);
-		wcd_clsh_set_gain_path(ctrl, mode);
-	} else {
-		wcd_clsh_set_hph_mode(comp, CLS_H_NORMAL);
-
-		if (mode != CLS_AB) {
-			snd_soc_component_update_bits(comp,
-					    WCD9XXX_A_CDC_RX1_RX_PATH_CFG0,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
-					    WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE);
-			wcd_enable_clsh_block(ctrl, false);
-		}
-		/* set buck and flyback to Default Mode */
-		wcd_clsh_buck_ctrl(ctrl, CLS_H_NORMAL, false);
-		wcd_clsh_flyback_ctrl(ctrl, CLS_H_NORMAL, false);
-		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
-		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
-		wcd_clsh_set_buck_regulator_mode(comp, CLS_H_NORMAL);
-	}
-}
-
-static void wcd_clsh_state_ear(struct wcd_clsh_ctrl *ctrl, int req_state,
-			       bool is_enable, int mode)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	if (mode != CLS_H_NORMAL) {
-		dev_err(comp->dev, "%s: mode: %d cannot be used for EAR\n",
-			__func__, mode);
-		return;
-	}
-
-	if (is_enable) {
-		wcd_enable_clsh_block(ctrl, true);
-		snd_soc_component_update_bits(comp,
-					WCD9XXX_A_CDC_RX0_RX_PATH_CFG0,
-					WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
-					WCD9XXX_A_CDC_RX_PATH_CLSH_ENABLE);
-		wcd_clsh_set_buck_mode(comp, mode);
-		wcd_clsh_set_flyback_mode(comp, mode);
-		wcd_clsh_flyback_ctrl(ctrl, mode, true);
-		wcd_clsh_set_flyback_current(comp, mode);
-		wcd_clsh_buck_ctrl(ctrl, mode, true);
-	} else {
-		snd_soc_component_update_bits(comp,
-					WCD9XXX_A_CDC_RX0_RX_PATH_CFG0,
-					WCD9XXX_A_CDC_RX_PATH_CLSH_EN_MASK,
-					WCD9XXX_A_CDC_RX_PATH_CLSH_DISABLE);
-		wcd_enable_clsh_block(ctrl, false);
-		wcd_clsh_buck_ctrl(ctrl, mode, false);
-		wcd_clsh_flyback_ctrl(ctrl, mode, false);
-		wcd_clsh_set_flyback_mode(comp, CLS_H_NORMAL);
-		wcd_clsh_set_buck_mode(comp, CLS_H_NORMAL);
-	}
-}
-
-static int _wcd_clsh_ctrl_set_state(struct wcd_clsh_ctrl *ctrl, int req_state,
-				    bool is_enable, int mode)
-{
-	switch (req_state) {
-	case WCD_CLSH_STATE_EAR:
-		wcd_clsh_state_ear(ctrl, req_state, is_enable, mode);
-		break;
-	case WCD_CLSH_STATE_HPHL:
-		wcd_clsh_state_hph_l(ctrl, req_state, is_enable, mode);
-		break;
-	case WCD_CLSH_STATE_HPHR:
-		wcd_clsh_state_hph_r(ctrl, req_state, is_enable, mode);
-		break;
-		break;
-	case WCD_CLSH_STATE_LO:
-		wcd_clsh_state_lo(ctrl, req_state, is_enable, mode);
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-/*
- * Function: wcd_clsh_is_state_valid
- * Params: state
- * Description:
- * Provides information on valid states of Class H configuration
- */
-static bool wcd_clsh_is_state_valid(int state)
-{
-	switch (state) {
-	case WCD_CLSH_STATE_IDLE:
-	case WCD_CLSH_STATE_EAR:
-	case WCD_CLSH_STATE_HPHL:
-	case WCD_CLSH_STATE_HPHR:
-	case WCD_CLSH_STATE_LO:
-		return true;
-	default:
-		return false;
-	};
-}
-
-/*
- * Function: wcd_clsh_fsm
- * Params: ctrl, req_state, req_type, clsh_event
- * Description:
- * This function handles PRE DAC and POST DAC conditions of different devices
- * and updates class H configuration of different combination of devices
- * based on validity of their states. ctrl will contain current
- * class h state information
- */
-int wcd_clsh_ctrl_set_state(struct wcd_clsh_ctrl *ctrl,
-			    enum wcd_clsh_event clsh_event,
-			    int nstate,
-			    enum wcd_clsh_mode mode)
-{
-	struct snd_soc_component *comp = ctrl->comp;
-
-	if (nstate == ctrl->state)
-		return 0;
-
-	if (!wcd_clsh_is_state_valid(nstate)) {
-		dev_err(comp->dev, "Class-H not a valid new state:\n");
-		return -EINVAL;
-	}
-
-	switch (clsh_event) {
-	case WCD_CLSH_EVENT_PRE_DAC:
-		_wcd_clsh_ctrl_set_state(ctrl, nstate, CLSH_REQ_ENABLE, mode);
-		break;
-	case WCD_CLSH_EVENT_POST_PA:
-		_wcd_clsh_ctrl_set_state(ctrl, nstate, CLSH_REQ_DISABLE, mode);
-		break;
-	};
-
-	ctrl->state = nstate;
-	ctrl->mode = mode;
-
-	return 0;
-}
-
-int wcd_clsh_ctrl_get_state(struct wcd_clsh_ctrl *ctrl)
-{
-	return ctrl->state;
-}
-
-struct wcd_clsh_ctrl *wcd_clsh_ctrl_alloc(struct snd_soc_component *comp,
-					  int version)
-{
-	struct wcd_clsh_ctrl *ctrl;
-
-	ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL);
-	if (!ctrl)
-		return ERR_PTR(-ENOMEM);
-
-	ctrl->state = WCD_CLSH_STATE_IDLE;
-	ctrl->comp = comp;
-
-	return ctrl;
-}
-
-void wcd_clsh_ctrl_free(struct wcd_clsh_ctrl *ctrl)
-{
-	kfree(ctrl);
-}
diff --git a/sound/soc/codecs/wcd-clsh.h b/sound/soc/codecs/wcd-clsh.h
deleted file mode 100644
index a902f9893467..000000000000
--- a/sound/soc/codecs/wcd-clsh.h
+++ /dev/null
@@ -1,49 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-
-#ifndef _WCD_CLSH_V2_H_
-#define _WCD_CLSH_V2_H_
-#include <sound/soc.h>
-
-enum wcd_clsh_event {
-	WCD_CLSH_EVENT_PRE_DAC = 1,
-	WCD_CLSH_EVENT_POST_PA,
-};
-
-/*
- * Basic states for Class H state machine.
- * represented as a bit mask within a u8 data type
- * bit 0: EAR mode
- * bit 1: HPH Left mode
- * bit 2: HPH Right mode
- * bit 3: Lineout mode
- */
-#define	WCD_CLSH_STATE_IDLE	0
-#define	WCD_CLSH_STATE_EAR	BIT(0)
-#define	WCD_CLSH_STATE_HPHL	BIT(1)
-#define	WCD_CLSH_STATE_HPHR	BIT(2)
-#define	WCD_CLSH_STATE_LO	BIT(3)
-#define WCD_CLSH_STATE_MAX	4
-#define NUM_CLSH_STATES_V2	BIT(WCD_CLSH_STATE_MAX)
-
-enum wcd_clsh_mode {
-	CLS_H_NORMAL = 0, /* Class-H Default */
-	CLS_H_HIFI, /* Class-H HiFi */
-	CLS_H_LP, /* Class-H Low Power */
-	CLS_AB, /* Class-AB */
-	CLS_H_LOHIFI, /* LoHIFI */
-	CLS_NONE, /* None of the above modes */
-};
-
-struct wcd_clsh_ctrl;
-
-extern struct wcd_clsh_ctrl *wcd_clsh_ctrl_alloc(
-				struct snd_soc_component *component,
-				int version);
-extern void wcd_clsh_ctrl_free(struct wcd_clsh_ctrl *ctrl);
-extern int wcd_clsh_ctrl_get_state(struct wcd_clsh_ctrl *ctrl);
-extern int wcd_clsh_ctrl_set_state(struct wcd_clsh_ctrl *ctrl,
-				   enum wcd_clsh_event event,
-				   int state,
-				   enum wcd_clsh_mode mode);
-
-#endif /* _WCD_CLSH_V2_H_ */
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
index 06c73699f16f..bd9de5d45fa9 100644
--- a/sound/soc/codecs/wcd9335.c
+++ b/sound/soc/codecs/wcd9335.c
@@ -21,7 +21,6 @@
 #include <dt-bindings/mfd/wcd9335.h>
 #include <linux/mfd/wcd9335/wcd9335.h>
 #include <linux/mfd/wcd9335/registers.h>
-#include "wcd-clsh.h"
 
 #define WCD9335_RATES_MASK (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
 			    SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000 |\
@@ -182,7 +181,6 @@ struct wcd9335_codec {
 	int sido_ccl_cnt;
 	enum wcd_clock_type clk_type;
 
-	struct wcd_clsh_ctrl *clsh_ctrl;
 	u32 hph_mode;
 };
 
@@ -1068,13 +1066,6 @@ static int wcd9335_codec_probe(struct snd_soc_component *component)
 	int i;
 
 	snd_soc_component_init_regmap(component, wcd->regmap);
-	/* Class-H Init*/
-	wcd->clsh_ctrl = wcd_clsh_ctrl_alloc(component, wcd->version);
-	if (IS_ERR(wcd->clsh_ctrl))
-		return PTR_ERR(wcd->clsh_ctrl);
-
-	/* Default HPH Mode to Class-H HiFi */
-	wcd->hph_mode = CLS_H_HIFI;
 	wcd->component = component;
 
 	wcd9335_codec_init(component);
@@ -1089,7 +1080,6 @@ static void wcd9335_codec_remove(struct snd_soc_component *comp)
 {
 	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
 
-	wcd_clsh_ctrl_free(wcd->clsh_ctrl);
 	free_irq(regmap_irq_get_virq(wcd->irq_data, WCD9335_IRQ_SLIMBUS), wcd);
 }
 
-- 
cgit v1.2.3


From b74fd69043262003c5b7ce545e59f5a7234ab290 Mon Sep 17 00:00:00 2001
From: Mark Brown <broonie@kernel.org>
Date: Wed, 1 Aug 2018 14:22:56 +0100
Subject: ASoC: wcd9335: Fix build

This reverts commit e57d4ca882e28 (ASoC: wcd9335: add support to wcd9335
codec) due to build failures caused by missing dependencies.

Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/Kconfig   |    5 -
 sound/soc/codecs/Makefile  |    2 -
 sound/soc/codecs/wcd9335.c | 1154 --------------------------------------------
 3 files changed, 1161 deletions(-)
 delete mode 100644 sound/soc/codecs/wcd9335.c

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index cb09abf18dde..efb095dbcd71 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -1066,11 +1066,6 @@ config SND_SOC_UDA1380
         tristate
 	depends on I2C
 
-config SND_SOC_WCD9335
-	tristate "WCD9335 Codec"
-	depends on MFD_WCD9335
-        tristate
-
 config SND_SOC_WL1273
 	tristate
 
diff --git a/sound/soc/codecs/Makefile b/sound/soc/codecs/Makefile
index 01410b63daac..7ae7c85e8219 100644
--- a/sound/soc/codecs/Makefile
+++ b/sound/soc/codecs/Makefile
@@ -192,7 +192,6 @@ snd-soc-twl4030-objs := twl4030.o
 snd-soc-twl6040-objs := twl6040.o
 snd-soc-uda134x-objs := uda134x.o
 snd-soc-uda1380-objs := uda1380.o
-snd-soc-wcd9335-objs := wcd9335.o
 snd-soc-wl1273-objs := wl1273.o
 snd-soc-wm-adsp-objs := wm_adsp.o
 snd-soc-wm0010-objs := wm0010.o
@@ -452,7 +451,6 @@ obj-$(CONFIG_SND_SOC_TWL4030)	+= snd-soc-twl4030.o
 obj-$(CONFIG_SND_SOC_TWL6040)	+= snd-soc-twl6040.o
 obj-$(CONFIG_SND_SOC_UDA134X)	+= snd-soc-uda134x.o
 obj-$(CONFIG_SND_SOC_UDA1380)	+= snd-soc-uda1380.o
-obj-$(CONFIG_SND_SOC_WCD9335)	+= snd-soc-wcd9335.o
 obj-$(CONFIG_SND_SOC_WL1273)	+= snd-soc-wl1273.o
 obj-$(CONFIG_SND_SOC_WM0010)	+= snd-soc-wm0010.o
 obj-$(CONFIG_SND_SOC_WM1250_EV1) += snd-soc-wm1250-ev1.o
diff --git a/sound/soc/codecs/wcd9335.c b/sound/soc/codecs/wcd9335.c
deleted file mode 100644
index bd9de5d45fa9..000000000000
--- a/sound/soc/codecs/wcd9335.c
+++ /dev/null
@@ -1,1154 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-// Copyright (c) 2015-2016, The Linux Foundation. All rights reserved.
-// Copyright (c) 2017-2018, Linaro Limited
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/platform_device.h>
-#include <linux/device.h>
-#include <linux/wait.h>
-#include <linux/bitops.h>
-#include <linux/regulator/consumer.h>
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/kernel.h>
-#include <linux/slimbus.h>
-#include <sound/soc.h>
-#include <sound/pcm_params.h>
-#include <sound/soc-dapm.h>
-#include <sound/tlv.h>
-#include <sound/info.h>
-#include <dt-bindings/mfd/wcd9335.h>
-#include <linux/mfd/wcd9335/wcd9335.h>
-#include <linux/mfd/wcd9335/registers.h>
-
-#define WCD9335_RATES_MASK (SNDRV_PCM_RATE_8000 | SNDRV_PCM_RATE_16000 |\
-			    SNDRV_PCM_RATE_32000 | SNDRV_PCM_RATE_48000 |\
-			    SNDRV_PCM_RATE_96000 | SNDRV_PCM_RATE_192000)
-/* Fractional Rates */
-#define WCD9335_FRAC_RATES_MASK (SNDRV_PCM_RATE_44100)
-#define WCD9335_FORMATS_S16_S24_LE (SNDRV_PCM_FMTBIT_S16_LE | \
-				  SNDRV_PCM_FMTBIT_S24_LE)
-
-/* slave port water mark level
- *   (0: 6bytes, 1: 9bytes, 2: 12 bytes, 3: 15 bytes)
- */
-#define SLAVE_PORT_WATER_MARK_6BYTES  0
-#define SLAVE_PORT_WATER_MARK_9BYTES  1
-#define SLAVE_PORT_WATER_MARK_12BYTES 2
-#define SLAVE_PORT_WATER_MARK_15BYTES 3
-#define SLAVE_PORT_WATER_MARK_SHIFT 1
-#define SLAVE_PORT_ENABLE           1
-#define SLAVE_PORT_DISABLE          0
-#define WCD9335_SLIM_WATER_MARK_VAL \
-	((SLAVE_PORT_WATER_MARK_12BYTES << SLAVE_PORT_WATER_MARK_SHIFT) | \
-	 (SLAVE_PORT_ENABLE))
-
-#define WCD9335_SLIM_NUM_PORT_REG 3
-#define WCD9335_SLIM_PGD_PORT_INT_TX_EN0 (WCD9335_SLIM_PGD_PORT_INT_EN0 + 2)
-
-#define WCD9335_MCLK_CLK_12P288MHZ	12288000
-#define WCD9335_MCLK_CLK_9P6MHZ		9600000
-
-#define WCD9335_SLIM_CLOSE_TIMEOUT 1000
-#define WCD9335_SLIM_IRQ_OVERFLOW (1 << 0)
-#define WCD9335_SLIM_IRQ_UNDERFLOW (1 << 1)
-#define WCD9335_SLIM_IRQ_PORT_CLOSED (1 << 2)
-
-#define WCD9335_NUM_INTERPOLATORS 9
-#define WCD9335_RX_START	16
-#define WCD9335_SLIM_CH_START 128
-
-#define WCD9335_SLIM_RX_CH(p) \
-	{.port = p + WCD9335_RX_START, .shift = p,}
-
-/* vout step value */
-#define WCD9335_CALCULATE_VOUT_D(req_mv) (((req_mv - 650) * 10) / 25)
-
-enum {
-	WCD9335_RX0 = 0,
-	WCD9335_RX1,
-	WCD9335_RX2,
-	WCD9335_RX3,
-	WCD9335_RX4,
-	WCD9335_RX5,
-	WCD9335_RX6,
-	WCD9335_RX7,
-	WCD9335_RX8,
-	WCD9335_RX9,
-	WCD9335_RX10,
-	WCD9335_RX11,
-	WCD9335_RX12,
-	WCD9335_RX_MAX,
-};
-
-enum {
-	SIDO_SOURCE_INTERNAL = 0,
-	SIDO_SOURCE_RCO_BG,
-};
-
-enum wcd9335_sido_voltage {
-	SIDO_VOLTAGE_SVS_MV = 950,
-	SIDO_VOLTAGE_NOMINAL_MV = 1100,
-};
-
-enum {
-	AIF1_PB = 0,
-	AIF1_CAP,
-	AIF2_PB,
-	AIF2_CAP,
-	AIF3_PB,
-	AIF3_CAP,
-	AIF4_PB,
-	NUM_CODEC_DAIS,
-};
-
-enum {
-	INTn_2_INP_SEL_ZERO = 0,
-	INTn_2_INP_SEL_RX0,
-	INTn_2_INP_SEL_RX1,
-	INTn_2_INP_SEL_RX2,
-	INTn_2_INP_SEL_RX3,
-	INTn_2_INP_SEL_RX4,
-	INTn_2_INP_SEL_RX5,
-	INTn_2_INP_SEL_RX6,
-	INTn_2_INP_SEL_RX7,
-	INTn_2_INP_SEL_PROXIMITY,
-};
-
-enum {
-	INTn_1_MIX_INP_SEL_ZERO = 0,
-	INTn_1_MIX_INP_SEL_DEC0,
-	INTn_1_MIX_INP_SEL_DEC1,
-	INTn_1_MIX_INP_SEL_IIR0,
-	INTn_1_MIX_INP_SEL_IIR1,
-	INTn_1_MIX_INP_SEL_RX0,
-	INTn_1_MIX_INP_SEL_RX1,
-	INTn_1_MIX_INP_SEL_RX2,
-	INTn_1_MIX_INP_SEL_RX3,
-	INTn_1_MIX_INP_SEL_RX4,
-	INTn_1_MIX_INP_SEL_RX5,
-	INTn_1_MIX_INP_SEL_RX6,
-	INTn_1_MIX_INP_SEL_RX7,
-
-};
-
-enum wcd_clock_type {
-	WCD_CLK_OFF,
-	WCD_CLK_RCO,
-	WCD_CLK_MCLK,
-};
-
-struct wcd9335_slim_ch {
-	u32 ch_num;
-	u16 port;
-	u16 shift;
-	struct list_head list;
-};
-
-struct wcd_slim_codec_dai_data {
-	struct list_head slim_ch_list;
-	struct slim_stream_config sconfig;
-	struct slim_stream_runtime *sruntime;
-};
-
-struct wcd9335_codec {
-	struct device *dev;
-	struct clk *mclk;
-	struct clk *native_clk;
-	u32 mclk_rate;
-	u8 intf_type;
-	u8 version;
-
-	struct slim_device *slim;
-	struct slim_device *slim_ifd;
-	struct regmap *regmap;
-	struct regmap *if_regmap;
-	struct regmap_irq_chip_data *irq_data;
-
-	struct wcd9335_slim_ch rx_chs[WCD9335_RX_MAX];
-	u32 num_rx_port;
-
-	int sido_input_src;
-	enum wcd9335_sido_voltage sido_voltage;
-
-	struct wcd_slim_codec_dai_data dai[NUM_CODEC_DAIS];
-	struct snd_soc_component *component;
-
-	int master_bias_users;
-	int clk_mclk_users;
-	int clk_rco_users;
-	int sido_ccl_cnt;
-	enum wcd_clock_type clk_type;
-
-	u32 hph_mode;
-};
-
-static const struct wcd9335_slim_ch wcd9335_rx_chs[WCD9335_RX_MAX] = {
-	WCD9335_SLIM_RX_CH(0),	 /* 16 */
-	WCD9335_SLIM_RX_CH(1),	 /* 17 */
-	WCD9335_SLIM_RX_CH(2),
-	WCD9335_SLIM_RX_CH(3),
-	WCD9335_SLIM_RX_CH(4),
-	WCD9335_SLIM_RX_CH(5),
-	WCD9335_SLIM_RX_CH(6),
-	WCD9335_SLIM_RX_CH(7),
-	WCD9335_SLIM_RX_CH(8),
-	WCD9335_SLIM_RX_CH(9),
-	WCD9335_SLIM_RX_CH(10),
-	WCD9335_SLIM_RX_CH(11),
-	WCD9335_SLIM_RX_CH(12),
-};
-
-struct interp_sample_rate {
-	int rate;
-	int rate_val;
-};
-
-static struct interp_sample_rate int_mix_rate_val[] = {
-	{48000, 0x4},	/* 48K */
-	{96000, 0x5},	/* 96K */
-	{192000, 0x6},	/* 192K */
-};
-
-static struct interp_sample_rate int_prim_rate_val[] = {
-	{8000, 0x0},	/* 8K */
-	{16000, 0x1},	/* 16K */
-	{24000, -EINVAL},/* 24K */
-	{32000, 0x3},	/* 32K */
-	{48000, 0x4},	/* 48K */
-	{96000, 0x5},	/* 96K */
-	{192000, 0x6},	/* 192K */
-	{384000, 0x7},	/* 384K */
-	{44100, 0x8}, /* 44.1K */
-};
-
-struct wcd9335_reg_mask_val {
-	u16 reg;
-	u8 mask;
-	u8 val;
-};
-
-static const struct wcd9335_reg_mask_val wcd9335_codec_reg_init_val_2_0[] = {
-	{WCD9335_RCO_CTRL_2, 0x0F, 0x08},
-	{WCD9335_RX_BIAS_FLYB_MID_RST, 0xF0, 0x10},
-	{WCD9335_FLYBACK_CTRL_1, 0x20, 0x20},
-	{WCD9335_HPH_OCP_CTL, 0xFF, 0x5A},
-	{WCD9335_HPH_L_TEST, 0x01, 0x01},
-	{WCD9335_HPH_R_TEST, 0x01, 0x01},
-	{WCD9335_CDC_BOOST0_BOOST_CFG1, 0x3F, 0x12},
-	{WCD9335_CDC_BOOST0_BOOST_CFG2, 0x1C, 0x08},
-	{WCD9335_CDC_COMPANDER7_CTL7, 0x1E, 0x18},
-	{WCD9335_CDC_BOOST1_BOOST_CFG1, 0x3F, 0x12},
-	{WCD9335_CDC_BOOST1_BOOST_CFG2, 0x1C, 0x08},
-	{WCD9335_CDC_COMPANDER8_CTL7, 0x1E, 0x18},
-	{WCD9335_CDC_TX0_TX_PATH_SEC7, 0xFF, 0x45},
-	{WCD9335_CDC_RX0_RX_PATH_SEC0, 0xFC, 0xF4},
-	{WCD9335_HPH_REFBUFF_LP_CTL, 0x08, 0x08},
-	{WCD9335_HPH_REFBUFF_LP_CTL, 0x06, 0x02},
-};
-
-static const struct wcd9335_reg_mask_val wcd9335_codec_reg_init_common_val[] = {
-	/* Rbuckfly/R_EAR(32) */
-	{WCD9335_CDC_CLSH_K2_MSB, 0x0F, 0x00},
-	{WCD9335_CDC_CLSH_K2_LSB, 0xFF, 0x60},
-	{WCD9335_CPE_SS_DMIC_CFG, 0x80, 0x00},
-	{WCD9335_CDC_BOOST0_BOOST_CTL, 0x70, 0x50},
-	{WCD9335_CDC_BOOST1_BOOST_CTL, 0x70, 0x50},
-	{WCD9335_CDC_RX7_RX_PATH_CFG1, 0x08, 0x08},
-	{WCD9335_CDC_RX8_RX_PATH_CFG1, 0x08, 0x08},
-	{WCD9335_ANA_LO_1_2, 0x3C, 0X3C},
-	{WCD9335_DIFF_LO_COM_SWCAP_REFBUF_FREQ, 0x70, 0x00},
-	{WCD9335_DIFF_LO_COM_PA_FREQ, 0x70, 0x40},
-	{WCD9335_SOC_MAD_AUDIO_CTL_2, 0x03, 0x03},
-	{WCD9335_CDC_TOP_TOP_CFG1, 0x02, 0x02},
-	{WCD9335_CDC_TOP_TOP_CFG1, 0x01, 0x01},
-	{WCD9335_EAR_CMBUFF, 0x08, 0x00},
-	{WCD9335_CDC_TX9_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_TX10_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_TX11_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_TX12_SPKR_PROT_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_COMPANDER7_CTL3, 0x80, 0x80},
-	{WCD9335_CDC_COMPANDER8_CTL3, 0x80, 0x80},
-	{WCD9335_CDC_COMPANDER7_CTL7, 0x01, 0x01},
-	{WCD9335_CDC_COMPANDER8_CTL7, 0x01, 0x01},
-	{WCD9335_CDC_RX0_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX1_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX2_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX3_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX4_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX5_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX6_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX7_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX8_RX_PATH_CFG0, 0x01, 0x01},
-	{WCD9335_CDC_RX0_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX1_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX2_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX3_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX4_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX5_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX6_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX7_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_CDC_RX8_RX_PATH_MIX_CFG, 0x01, 0x01},
-	{WCD9335_VBADC_IBIAS_FE, 0x0C, 0x08},
-};
-
-static int wcd9335_set_mix_interpolator_rate(struct snd_soc_dai *dai,
-					     int rate_val,
-					     u32 rate)
-{
-	struct snd_soc_component *component = dai->component;
-	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
-	struct wcd9335_slim_ch *ch;
-	int val, j;
-
-	list_for_each_entry(ch, &wcd->dai[dai->id].slim_ch_list, list) {
-		for (j = 0; j < WCD9335_NUM_INTERPOLATORS; j++) {
-			val = snd_soc_component_read32(component,
-					WCD9335_CDC_RX_INP_MUX_RX_INT_CFG1(j)) &
-					WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
-
-			if (val == (ch->shift + INTn_2_INP_SEL_RX0))
-				snd_soc_component_update_bits(component,
-						WCD9335_CDC_RX_PATH_MIX_CTL(j),
-						WCD9335_CDC_MIX_PCM_RATE_MASK,
-						rate_val);
-		}
-	}
-
-	return 0;
-}
-
-static int wcd9335_set_prim_interpolator_rate(struct snd_soc_dai *dai,
-					      u8 rate_val,
-					      u32 rate)
-{
-	struct snd_soc_component *comp = dai->component;
-	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
-	struct wcd9335_slim_ch *ch;
-	u8 cfg0, cfg1, inp0_sel, inp1_sel, inp2_sel;
-	int inp, j;
-
-	list_for_each_entry(ch, &wcd->dai[dai->id].slim_ch_list, list) {
-		inp = ch->shift + INTn_1_MIX_INP_SEL_RX0;
-		/*
-		 * Loop through all interpolator MUX inputs and find out
-		 * to which interpolator input, the slim rx port
-		 * is connected
-		 */
-		for (j = 0; j < WCD9335_NUM_INTERPOLATORS; j++) {
-			cfg0 = snd_soc_component_read32(comp,
-					WCD9335_CDC_RX_INP_MUX_RX_INT_CFG0(j));
-			cfg1 = snd_soc_component_read32(comp,
-					WCD9335_CDC_RX_INP_MUX_RX_INT_CFG1(j));
-
-			inp0_sel = cfg0 & WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
-			inp1_sel = (cfg0 >> 4) & WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
-			inp2_sel = (cfg1 >> 4) & WCD9335_CDC_RX_INP_MUX_RX_INT_SEL_MASK;
-
-			if ((inp0_sel == inp) ||  (inp1_sel == inp) ||
-			    (inp2_sel == inp)) {
-				/* rate is in Hz */
-				if ((j == 0) && (rate == 44100))
-					dev_info(wcd->dev,
-						"Cannot set 44.1KHz on INT0\n");
-				else
-					snd_soc_component_update_bits(comp,
-						WCD9335_CDC_RX_PATH_CTL(j),
-						WCD9335_CDC_MIX_PCM_RATE_MASK,
-						rate_val);
-			}
-		}
-	}
-
-	return 0;
-}
-
-static int wcd9335_set_interpolator_rate(struct snd_soc_dai *dai, u32 rate)
-{
-	int i;
-
-	/* set mixing path rate */
-	for (i = 0; i < ARRAY_SIZE(int_mix_rate_val); i++) {
-		if (rate == int_mix_rate_val[i].rate) {
-			wcd9335_set_mix_interpolator_rate(dai,
-					int_mix_rate_val[i].rate_val, rate);
-			break;
-		}
-	}
-
-	/* set primary path sample rate */
-	for (i = 0; i < ARRAY_SIZE(int_prim_rate_val); i++) {
-		if (rate == int_prim_rate_val[i].rate) {
-			wcd9335_set_prim_interpolator_rate(dai,
-					int_prim_rate_val[i].rate_val, rate);
-			break;
-		}
-	}
-
-	return 0;
-}
-
-static int wcd9335_slim_set_hw_params(struct wcd9335_codec *wcd,
-				 struct wcd_slim_codec_dai_data *dai_data,
-				 int direction)
-{
-	struct list_head *slim_ch_list = &dai_data->slim_ch_list;
-	struct slim_stream_config *cfg = &dai_data->sconfig;
-	struct wcd9335_slim_ch *ch;
-	u16 payload = 0;
-	int ret, i;
-
-	cfg->ch_count = 0;
-	cfg->direction = direction;
-	cfg->port_mask = 0;
-
-	/* Configure slave interface device */
-	list_for_each_entry(ch, slim_ch_list, list) {
-		cfg->ch_count++;
-		payload |= 1 << ch->shift;
-		cfg->port_mask |= BIT(ch->port);
-	}
-
-	cfg->chs = kcalloc(cfg->ch_count, sizeof(unsigned int), GFP_KERNEL);
-	if (!cfg->chs)
-		return -ENOMEM;
-
-	i = 0;
-	list_for_each_entry(ch, slim_ch_list, list) {
-		cfg->chs[i++] = ch->ch_num;
-		if (direction == SNDRV_PCM_STREAM_PLAYBACK) {
-			/* write to interface device */
-			ret = regmap_write(wcd->if_regmap,
-				WCD9335_SLIM_PGD_RX_PORT_MULTI_CHNL_0(ch->port),
-				payload);
-
-			if (ret < 0)
-				goto err;
-
-			/* configure the slave port for water mark and enable*/
-			ret = regmap_write(wcd->if_regmap,
-					WCD9335_SLIM_PGD_RX_PORT_CFG(ch->port),
-					WCD9335_SLIM_WATER_MARK_VAL);
-			if (ret < 0)
-				goto err;
-		}
-	}
-
-	dai_data->sruntime = slim_stream_allocate(wcd->slim, "WCD9335-SLIM");
-	slim_stream_prepare(dai_data->sruntime, cfg);
-
-	return 0;
-
-err:
-	dev_err(wcd->dev, "Error Setting slim hw params\n");
-	kfree(cfg->chs);
-	cfg->chs = NULL;
-
-	return ret;
-}
-
-static int wcd9335_hw_params(struct snd_pcm_substream *substream,
-			   struct snd_pcm_hw_params *params,
-			   struct snd_soc_dai *dai)
-{
-	struct wcd9335_codec *wcd;
-	int ret;
-
-	wcd = snd_soc_component_get_drvdata(dai->component);
-
-	switch (substream->stream) {
-	case SNDRV_PCM_STREAM_PLAYBACK:
-		ret = wcd9335_set_interpolator_rate(dai, params_rate(params));
-		if (ret) {
-			dev_err(wcd->dev, "cannot set sample rate: %u\n",
-				params_rate(params));
-			return ret;
-		}
-		switch (params_width(params)) {
-		case 16 ... 24:
-			wcd->dai[dai->id].sconfig.bps = params_width(params);
-			break;
-		default:
-			dev_err(wcd->dev, "%s: Invalid format 0x%x\n",
-				__func__, params_width(params));
-			return -EINVAL;
-		}
-		break;
-	default:
-		dev_err(wcd->dev, "Invalid stream type %d\n",
-			substream->stream);
-		return -EINVAL;
-	};
-
-	wcd->dai[dai->id].sconfig.rate = params_rate(params);
-	wcd9335_slim_set_hw_params(wcd, &wcd->dai[dai->id], substream->stream);
-
-	return 0;
-}
-
-static int wcd9335_prepare(struct snd_pcm_substream *substream,
-			   struct snd_soc_dai *dai)
-{
-	struct wcd_slim_codec_dai_data *dai_data;
-	struct wcd9335_codec *wcd;
-
-	wcd = snd_soc_component_get_drvdata(dai->component);
-	dai_data = &wcd->dai[dai->id];
-	slim_stream_enable(dai_data->sruntime);
-
-	return 0;
-}
-
-static int wcd9335_set_channel_map(struct snd_soc_dai *dai,
-				   unsigned int tx_num, unsigned int *tx_slot,
-				   unsigned int rx_num, unsigned int *rx_slot)
-{
-	struct wcd9335_codec *wcd;
-	int i;
-
-	wcd = snd_soc_component_get_drvdata(dai->component);
-
-	if (!tx_slot || !rx_slot) {
-		dev_err(wcd->dev, "Invalid tx_slot=%p, rx_slot=%p\n",
-			tx_slot, rx_slot);
-		return -EINVAL;
-	}
-
-	if (wcd->rx_chs) {
-		wcd->num_rx_port = rx_num;
-		for (i = 0; i < rx_num; i++) {
-			wcd->rx_chs[i].ch_num = rx_slot[i];
-			INIT_LIST_HEAD(&wcd->rx_chs[i].list);
-		}
-	}
-
-	return 0;
-}
-
-static int wcd9335_get_channel_map(struct snd_soc_dai *dai,
-				   unsigned int *tx_num, unsigned int *tx_slot,
-				   unsigned int *rx_num, unsigned int *rx_slot)
-{
-	struct wcd9335_slim_ch *ch;
-	struct wcd9335_codec *wcd;
-	int i = 0;
-
-	wcd = snd_soc_component_get_drvdata(dai->component);
-
-	switch (dai->id) {
-	case AIF1_PB:
-	case AIF2_PB:
-	case AIF3_PB:
-	case AIF4_PB:
-		if (!rx_slot || !rx_num) {
-			dev_err(wcd->dev, "Invalid rx_slot %p or rx_num %p\n",
-				rx_slot, rx_num);
-			return -EINVAL;
-		}
-
-		list_for_each_entry(ch, &wcd->dai[dai->id].slim_ch_list, list)
-			rx_slot[i++] = ch->ch_num;
-
-		*rx_num = i;
-		break;
-	default:
-		dev_err(wcd->dev, "Invalid DAI ID %x\n", dai->id);
-		break;
-	}
-
-	return 0;
-}
-
-static struct snd_soc_dai_ops wcd9335_dai_ops = {
-	.hw_params = wcd9335_hw_params,
-	.prepare = wcd9335_prepare,
-	.set_channel_map = wcd9335_set_channel_map,
-	.get_channel_map = wcd9335_get_channel_map,
-};
-
-static struct snd_soc_dai_driver wcd9335_slim_dais[] = {
-	[0] = {
-		.name = "wcd9335_rx1",
-		.id = AIF1_PB,
-		.playback = {
-			.stream_name = "AIF1 Playback",
-			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
-			.formats = WCD9335_FORMATS_S16_S24_LE,
-			.rate_max = 192000,
-			.rate_min = 8000,
-			.channels_min = 1,
-			.channels_max = 2,
-		},
-		.ops = &wcd9335_dai_ops,
-	},
-	[1] = {
-		.name = "wcd9335_tx1",
-		.id = AIF1_CAP,
-		.capture = {
-			.stream_name = "AIF1 Capture",
-			.rates = WCD9335_RATES_MASK,
-			.formats = SNDRV_PCM_FMTBIT_S16_LE,
-			.rate_min = 8000,
-			.rate_max = 192000,
-			.channels_min = 1,
-			.channels_max = 4,
-		},
-		.ops = &wcd9335_dai_ops,
-	},
-	[2] = {
-		.name = "wcd9335_rx2",
-		.id = AIF2_PB,
-		.playback = {
-			.stream_name = "AIF2 Playback",
-			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
-			.formats = WCD9335_FORMATS_S16_S24_LE,
-			.rate_min = 8000,
-			.rate_max = 192000,
-			.channels_min = 1,
-			.channels_max = 2,
-		},
-		.ops = &wcd9335_dai_ops,
-	},
-	[3] = {
-		.name = "wcd9335_tx2",
-		.id = AIF2_CAP,
-		.capture = {
-			.stream_name = "AIF2 Capture",
-			.rates = WCD9335_RATES_MASK,
-			.formats = SNDRV_PCM_FMTBIT_S16_LE,
-			.rate_min = 8000,
-			.rate_max = 192000,
-			.channels_min = 1,
-			.channels_max = 4,
-		},
-		.ops = &wcd9335_dai_ops,
-	},
-	[4] = {
-		.name = "wcd9335_rx3",
-		.id = AIF3_PB,
-		.playback = {
-			.stream_name = "AIF3 Playback",
-			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
-			.formats = WCD9335_FORMATS_S16_S24_LE,
-			.rate_min = 8000,
-			.rate_max = 192000,
-			.channels_min = 1,
-			.channels_max = 2,
-		},
-		.ops = &wcd9335_dai_ops,
-	},
-	[5] = {
-		.name = "wcd9335_tx3",
-		.id = AIF3_CAP,
-		.capture = {
-			.stream_name = "AIF3 Capture",
-			.rates = WCD9335_RATES_MASK,
-			.formats = SNDRV_PCM_FMTBIT_S16_LE,
-			.rate_min = 8000,
-			.rate_max = 192000,
-			.channels_min = 1,
-			.channels_max = 4,
-		},
-		.ops = &wcd9335_dai_ops,
-	},
-	[6] = {
-		.name = "wcd9335_rx4",
-		.id = AIF4_PB,
-		.playback = {
-			.stream_name = "AIF4 Playback",
-			.rates = WCD9335_RATES_MASK | WCD9335_FRAC_RATES_MASK,
-			.formats = WCD9335_FORMATS_S16_S24_LE,
-			.rate_min = 8000,
-			.rate_max = 192000,
-			.channels_min = 1,
-			.channels_max = 2,
-		},
-		.ops = &wcd9335_dai_ops,
-	},
-};
-
-static irqreturn_t wcd9335_slimbus_irq(int irq, void *data)
-{
-	struct wcd9335_codec *wcd = data;
-	unsigned long status = 0;
-	int i, j, port_id;
-	unsigned int val, int_val = 0;
-	bool tx;
-	unsigned short reg = 0;
-
-	for (i = WCD9335_SLIM_PGD_PORT_INT_STATUS_RX_0, j = 0;
-	     i <= WCD9335_SLIM_PGD_PORT_INT_STATUS_TX_1; i++, j++) {
-		regmap_read(wcd->if_regmap, i, &val);
-		status |= ((u32)val << (8 * j));
-	}
-
-	for_each_set_bit(j, &status, 32) {
-		tx = (j >= 16 ? true : false);
-		port_id = (tx ? j - 16 : j);
-		regmap_read(wcd->if_regmap,
-				WCD9335_SLIM_PGD_PORT_INT_RX_SOURCE0 + j, &val);
-		if (val) {
-			if (!tx)
-				reg = WCD9335_SLIM_PGD_PORT_INT_EN0 +
-					(port_id / 8);
-			else
-				reg = WCD9335_SLIM_PGD_PORT_INT_TX_EN0 +
-					(port_id / 8);
-			regmap_read(
-				wcd->if_regmap, reg, &int_val);
-			/*
-			 * Ignore interrupts for ports for which the
-			 * interrupts are not specifically enabled.
-			 */
-			if (!(int_val & (1 << (port_id % 8))))
-				continue;
-		}
-		if (val & WCD9335_SLIM_IRQ_OVERFLOW)
-			dev_err_ratelimited(wcd->dev,
-			   "%s: overflow error on %s port %d, value %x\n",
-			   __func__, (tx ? "TX" : "RX"), port_id, val);
-		if (val & WCD9335_SLIM_IRQ_UNDERFLOW)
-			dev_err_ratelimited(wcd->dev,
-			   "%s: underflow error on %s port %d, value %x\n",
-			   __func__, (tx ? "TX" : "RX"), port_id, val);
-		if ((val & WCD9335_SLIM_IRQ_OVERFLOW) ||
-			(val & WCD9335_SLIM_IRQ_UNDERFLOW)) {
-			if (!tx)
-				reg = WCD9335_SLIM_PGD_PORT_INT_EN0 +
-					(port_id / 8);
-			else
-				reg = WCD9335_SLIM_PGD_PORT_INT_TX_EN0 +
-					(port_id / 8);
-			regmap_read(
-				wcd->if_regmap, reg, &int_val);
-			if (int_val & (1 << (port_id % 8))) {
-				int_val = int_val ^ (1 << (port_id % 8));
-				regmap_write(wcd->if_regmap,
-					reg, int_val);
-			}
-		}
-
-		regmap_write(wcd->if_regmap,
-				WCD9335_SLIM_PGD_PORT_INT_CLR_RX_0 + (j / 8),
-				BIT(j % 8));
-	}
-
-	return IRQ_HANDLED;
-}
-
-static int wcd9335_setup_irqs(struct wcd9335_codec *wcd)
-{
-	int slim_irq = regmap_irq_get_virq(wcd->irq_data, WCD9335_IRQ_SLIMBUS);
-	int i, ret = 0;
-
-	ret = request_threaded_irq(slim_irq, NULL, wcd9335_slimbus_irq,
-				   IRQF_TRIGGER_RISING, "SLIMBus Slave", wcd);
-	if (ret) {
-		dev_err(wcd->dev, "Failed to request SLIMBUS irq\n");
-		return ret;
-	}
-
-	/* enable interrupts on all slave ports */
-	for (i = 0; i < WCD9335_SLIM_NUM_PORT_REG; i++)
-		regmap_write(wcd->if_regmap, WCD9335_SLIM_PGD_PORT_INT_EN0 + i,
-			     0xFF);
-
-	return ret;
-}
-
-static void wcd9335_cdc_sido_ccl_enable(struct wcd9335_codec *wcd,
-					bool ccl_flag)
-{
-	struct snd_soc_component *comp = wcd->component;
-
-	if (ccl_flag) {
-		if (++wcd->sido_ccl_cnt == 1)
-			snd_soc_component_write(comp, WCD9335_SIDO_SIDO_CCL_10,
-					WCD9335_SIDO_SIDO_CCL_DEF_VALUE);
-	} else {
-		if (wcd->sido_ccl_cnt == 0) {
-			dev_err(wcd->dev, "sido_ccl already disabled\n");
-			return;
-		}
-		if (--wcd->sido_ccl_cnt == 0)
-			snd_soc_component_write(comp, WCD9335_SIDO_SIDO_CCL_10,
-				WCD9335_SIDO_SIDO_CCL_10_ICHARG_PWR_SEL_C320FF);
-	}
-}
-
-static int wcd9335_enable_master_bias(struct wcd9335_codec *wcd)
-{
-	wcd->master_bias_users++;
-	if (wcd->master_bias_users == 1) {
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
-					WCD9335_ANA_BIAS_EN_MASK,
-					WCD9335_ANA_BIAS_ENABLE);
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
-					WCD9335_ANA_BIAS_PRECHRG_EN_MASK,
-					WCD9335_ANA_BIAS_PRECHRG_ENABLE);
-		/*
-		 * 1ms delay is required after pre-charge is enabled
-		 * as per HW requirement
-		 */
-		usleep_range(1000, 1100);
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
-					WCD9335_ANA_BIAS_PRECHRG_EN_MASK,
-					WCD9335_ANA_BIAS_PRECHRG_DISABLE);
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
-				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE,
-				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE_MANUAL);
-	}
-
-	return 0;
-}
-
-static int wcd9335_enable_mclk(struct wcd9335_codec *wcd)
-{
-	/* Enable mclk requires master bias to be enabled first */
-	if (wcd->master_bias_users <= 0)
-		return -EINVAL;
-
-	if (((wcd->clk_mclk_users == 0) && (wcd->clk_type == WCD_CLK_MCLK)) ||
-	    ((wcd->clk_mclk_users > 0) && (wcd->clk_type != WCD_CLK_MCLK))) {
-		dev_err(wcd->dev, "Error enabling MCLK, clk_type: %d\n",
-			wcd->clk_type);
-		return -EINVAL;
-	}
-
-	if (++wcd->clk_mclk_users == 1) {
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
-					WCD9335_ANA_CLK_EXT_CLKBUF_EN_MASK,
-					WCD9335_ANA_CLK_EXT_CLKBUF_ENABLE);
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
-					WCD9335_ANA_CLK_MCLK_SRC_MASK,
-					WCD9335_ANA_CLK_MCLK_SRC_EXTERNAL);
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
-					WCD9335_ANA_CLK_MCLK_EN_MASK,
-					WCD9335_ANA_CLK_MCLK_ENABLE);
-		regmap_update_bits(wcd->regmap,
-				   WCD9335_CDC_CLK_RST_CTRL_FS_CNT_CONTROL,
-				   WCD9335_CDC_CLK_RST_CTRL_FS_CNT_EN_MASK,
-				   WCD9335_CDC_CLK_RST_CTRL_FS_CNT_ENABLE);
-		regmap_update_bits(wcd->regmap,
-				   WCD9335_CDC_CLK_RST_CTRL_MCLK_CONTROL,
-				   WCD9335_CDC_CLK_RST_CTRL_MCLK_EN_MASK,
-				   WCD9335_CDC_CLK_RST_CTRL_MCLK_ENABLE);
-		/*
-		 * 10us sleep is required after clock is enabled
-		 * as per HW requirement
-		 */
-		usleep_range(10, 15);
-	}
-
-	wcd->clk_type = WCD_CLK_MCLK;
-
-	return 0;
-}
-
-static int wcd9335_disable_mclk(struct wcd9335_codec *wcd)
-{
-	if (wcd->clk_mclk_users <= 0)
-		return -EINVAL;
-
-	if (--wcd->clk_mclk_users == 0) {
-		if (wcd->clk_rco_users > 0) {
-			/* MCLK to RCO switch */
-			regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
-					WCD9335_ANA_CLK_MCLK_SRC_MASK,
-					WCD9335_ANA_CLK_MCLK_SRC_RCO);
-			wcd->clk_type = WCD_CLK_RCO;
-		} else {
-			regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
-					WCD9335_ANA_CLK_MCLK_EN_MASK,
-					WCD9335_ANA_CLK_MCLK_DISABLE);
-			wcd->clk_type = WCD_CLK_OFF;
-		}
-
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_CLK_TOP,
-					WCD9335_ANA_CLK_EXT_CLKBUF_EN_MASK,
-					WCD9335_ANA_CLK_EXT_CLKBUF_DISABLE);
-	}
-
-	return 0;
-}
-
-static int wcd9335_disable_master_bias(struct wcd9335_codec *wcd)
-{
-	if (wcd->master_bias_users <= 0)
-		return -EINVAL;
-
-	wcd->master_bias_users--;
-	if (wcd->master_bias_users == 0) {
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
-				WCD9335_ANA_BIAS_EN_MASK,
-				WCD9335_ANA_BIAS_DISABLE);
-		regmap_update_bits(wcd->regmap, WCD9335_ANA_BIAS,
-				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE,
-				WCD9335_ANA_BIAS_PRECHRG_CTL_MODE_MANUAL);
-	}
-	return 0;
-}
-
-static int wcd9335_cdc_req_mclk_enable(struct wcd9335_codec *wcd,
-				     bool enable)
-{
-	int ret = 0;
-
-	if (enable) {
-		wcd9335_cdc_sido_ccl_enable(wcd, true);
-		ret = clk_prepare_enable(wcd->mclk);
-		if (ret) {
-			dev_err(wcd->dev, "%s: ext clk enable failed\n",
-				__func__);
-			goto err;
-		}
-		/* get BG */
-		wcd9335_enable_master_bias(wcd);
-		/* get MCLK */
-		wcd9335_enable_mclk(wcd);
-
-	} else {
-		/* put MCLK */
-		wcd9335_disable_mclk(wcd);
-		/* put BG */
-		wcd9335_disable_master_bias(wcd);
-		clk_disable_unprepare(wcd->mclk);
-		wcd9335_cdc_sido_ccl_enable(wcd, false);
-	}
-err:
-	return ret;
-}
-
-static void wcd9335_codec_apply_sido_voltage(struct wcd9335_codec *wcd,
-					     enum wcd9335_sido_voltage req_mv)
-{
-	struct snd_soc_component *comp = wcd->component;
-	int vout_d_val;
-
-	if (req_mv == wcd->sido_voltage)
-		return;
-
-	/* compute the vout_d step value */
-	vout_d_val = WCD9335_CALCULATE_VOUT_D(req_mv) &
-			WCD9335_ANA_BUCK_VOUT_MASK;
-	snd_soc_component_write(comp, WCD9335_ANA_BUCK_VOUT_D, vout_d_val);
-	snd_soc_component_update_bits(comp, WCD9335_ANA_BUCK_CTL,
-				WCD9335_ANA_BUCK_CTL_RAMP_START_MASK,
-				WCD9335_ANA_BUCK_CTL_RAMP_START_ENABLE);
-
-	/* 1 msec sleep required after SIDO Vout_D voltage change */
-	usleep_range(1000, 1100);
-	wcd->sido_voltage = req_mv;
-	snd_soc_component_update_bits(comp, WCD9335_ANA_BUCK_CTL,
-				WCD9335_ANA_BUCK_CTL_RAMP_START_MASK,
-				WCD9335_ANA_BUCK_CTL_RAMP_START_DISABLE);
-}
-
-static int wcd9335_codec_update_sido_voltage(struct wcd9335_codec *wcd,
-					     enum wcd9335_sido_voltage req_mv)
-{
-	int ret = 0;
-
-	/* enable mclk before setting SIDO voltage */
-	ret = wcd9335_cdc_req_mclk_enable(wcd, true);
-	if (ret) {
-		dev_err(wcd->dev, "Ext clk enable failed\n");
-		goto err;
-	}
-
-	wcd9335_codec_apply_sido_voltage(wcd, req_mv);
-	wcd9335_cdc_req_mclk_enable(wcd, false);
-
-err:
-	return ret;
-}
-
-static int _wcd9335_codec_enable_mclk(struct snd_soc_component *component,
-				      int enable)
-{
-	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
-	int ret;
-
-	if (enable) {
-		ret = wcd9335_cdc_req_mclk_enable(wcd, true);
-		if (ret)
-			return ret;
-
-		wcd9335_codec_apply_sido_voltage(wcd,
-				SIDO_VOLTAGE_NOMINAL_MV);
-	} else {
-		wcd9335_codec_update_sido_voltage(wcd,
-					wcd->sido_voltage);
-		wcd9335_cdc_req_mclk_enable(wcd, false);
-	}
-
-	return 0;
-}
-
-static void wcd9335_enable_sido_buck(struct snd_soc_component *component)
-{
-	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
-
-	snd_soc_component_update_bits(component, WCD9335_ANA_RCO,
-					WCD9335_ANA_RCO_BG_EN_MASK,
-					WCD9335_ANA_RCO_BG_ENABLE);
-	snd_soc_component_update_bits(component, WCD9335_ANA_BUCK_CTL,
-					WCD9335_ANA_BUCK_CTL_VOUT_D_IREF_MASK,
-					WCD9335_ANA_BUCK_CTL_VOUT_D_IREF_EXT);
-	/* 100us sleep needed after IREF settings */
-	usleep_range(100, 110);
-	snd_soc_component_update_bits(component, WCD9335_ANA_BUCK_CTL,
-					WCD9335_ANA_BUCK_CTL_VOUT_D_VREF_MASK,
-					WCD9335_ANA_BUCK_CTL_VOUT_D_VREF_EXT);
-	/* 100us sleep needed after VREF settings */
-	usleep_range(100, 110);
-	wcd->sido_input_src = SIDO_SOURCE_RCO_BG;
-}
-
-static int wcd9335_enable_efuse_sensing(struct snd_soc_component *comp)
-{
-	_wcd9335_codec_enable_mclk(comp, true);
-	snd_soc_component_update_bits(comp,
-				WCD9335_CHIP_TIER_CTRL_EFUSE_CTL,
-				WCD9335_CHIP_TIER_CTRL_EFUSE_EN_MASK,
-				WCD9335_CHIP_TIER_CTRL_EFUSE_ENABLE);
-	/*
-	 * 5ms sleep required after enabling efuse control
-	 * before checking the status.
-	 */
-	usleep_range(5000, 5500);
-
-	if (!(snd_soc_component_read32(comp,
-					WCD9335_CHIP_TIER_CTRL_EFUSE_STATUS) &
-					WCD9335_CHIP_TIER_CTRL_EFUSE_EN_MASK))
-		WARN(1, "%s: Efuse sense is not complete\n", __func__);
-
-	wcd9335_enable_sido_buck(comp);
-	_wcd9335_codec_enable_mclk(comp, false);
-
-	return 0;
-}
-
-static void wcd9335_codec_init(struct snd_soc_component *component)
-{
-	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
-	int i;
-
-	/* ungate MCLK and set clk rate */
-	regmap_update_bits(wcd->regmap, WCD9335_CODEC_RPM_CLK_GATE,
-				WCD9335_CODEC_RPM_CLK_GATE_MCLK_GATE_MASK, 0);
-
-	regmap_update_bits(wcd->regmap, WCD9335_CODEC_RPM_CLK_MCLK_CFG,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG_9P6MHZ);
-
-	for (i = 0; i < ARRAY_SIZE(wcd9335_codec_reg_init_common_val); i++)
-		snd_soc_component_update_bits(component,
-				wcd9335_codec_reg_init_common_val[i].reg,
-				wcd9335_codec_reg_init_common_val[i].mask,
-				wcd9335_codec_reg_init_common_val[i].val);
-
-	if (WCD9335_IS_2_0(wcd->version)) {
-		for (i = 0; i < ARRAY_SIZE(wcd9335_codec_reg_init_val_2_0); i++)
-			snd_soc_component_update_bits(component,
-					wcd9335_codec_reg_init_val_2_0[i].reg,
-					wcd9335_codec_reg_init_val_2_0[i].mask,
-					wcd9335_codec_reg_init_val_2_0[i].val);
-	}
-
-	wcd9335_enable_efuse_sensing(component);
-}
-
-static int wcd9335_codec_probe(struct snd_soc_component *component)
-{
-	struct wcd9335_codec *wcd = dev_get_drvdata(component->dev);
-	int i;
-
-	snd_soc_component_init_regmap(component, wcd->regmap);
-	wcd->component = component;
-
-	wcd9335_codec_init(component);
-
-	for (i = 0; i < NUM_CODEC_DAIS; i++)
-		INIT_LIST_HEAD(&wcd->dai[i].slim_ch_list);
-
-	return wcd9335_setup_irqs(wcd);
-}
-
-static void wcd9335_codec_remove(struct snd_soc_component *comp)
-{
-	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
-
-	free_irq(regmap_irq_get_virq(wcd->irq_data, WCD9335_IRQ_SLIMBUS), wcd);
-}
-
-static int wcd9335_codec_set_sysclk(struct snd_soc_component *comp,
-				    int clk_id, int source,
-				    unsigned int freq, int dir)
-{
-	struct wcd9335_codec *wcd = dev_get_drvdata(comp->dev);
-
-	wcd->mclk_rate = freq;
-
-	if (wcd->mclk_rate == WCD9335_MCLK_CLK_12P288MHZ)
-		snd_soc_component_update_bits(comp,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG_12P288MHZ);
-	else if (wcd->mclk_rate == WCD9335_MCLK_CLK_9P6MHZ)
-		snd_soc_component_update_bits(comp,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG_MCLK_MASK,
-				WCD9335_CODEC_RPM_CLK_MCLK_CFG_9P6MHZ);
-
-	return clk_set_rate(wcd->mclk, freq);
-}
-
-static const struct snd_soc_component_driver wcd9335_component_drv = {
-	.probe = wcd9335_codec_probe,
-	.remove = wcd9335_codec_remove,
-	.set_sysclk = wcd9335_codec_set_sysclk,
-};
-
-static int wcd9335_probe(struct platform_device *pdev)
-{
-	struct wcd9335 *pdata = dev_get_drvdata(pdev->dev.parent);
-	struct device *dev = &pdev->dev;
-	struct wcd9335_codec *wcd;
-
-	wcd = devm_kzalloc(dev, sizeof(*wcd), GFP_KERNEL);
-	if (!wcd)
-		return -ENOMEM;
-
-	dev_set_drvdata(dev, wcd);
-
-	memcpy(wcd->rx_chs, wcd9335_rx_chs, sizeof(wcd9335_rx_chs));
-
-	wcd->regmap = pdata->regmap;
-	wcd->if_regmap = pdata->ifd_regmap;
-	wcd->slim = pdata->slim;
-	wcd->slim_ifd = pdata->slim_ifd;
-	wcd->irq_data = pdata->irq_data;
-	wcd->version = pdata->version;
-	wcd->intf_type = pdata->intf_type;
-	wcd->dev = dev;
-	wcd->mclk = pdata->mclk;
-	wcd->native_clk = pdata->native_clk;
-	wcd->sido_input_src = SIDO_SOURCE_INTERNAL;
-	wcd->sido_voltage = SIDO_VOLTAGE_NOMINAL_MV;
-
-	return devm_snd_soc_register_component(dev, &wcd9335_component_drv,
-					       wcd9335_slim_dais,
-					       ARRAY_SIZE(wcd9335_slim_dais));
-}
-
-static struct platform_driver wcd9335_codec_driver = {
-	.probe = wcd9335_probe,
-	.driver = {
-		.name = "wcd9335-codec",
-	},
-};
-module_platform_driver(wcd9335_codec_driver);
-MODULE_DESCRIPTION("WCD9335 Codec driver");
-MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 9fb4c2bf130b922c77c16a8368732699799c40de Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Wed, 1 Aug 2018 15:37:33 +0530
Subject: ASoC: soc-pcm: Use delay set in component pointer function

Take into account the base delay set in pointer callback.

There are cases where a pointer function populates
runtime->delay, such as:
./sound/pci/hda/hda_controller.c
./sound/soc/intel/atom/sst-mfld-platform-pcm.c

This delay was getting lost and was overwritten by delays
from codec or cpu dai delay function if exposed.

Now,
Total delay = base delay + cpu_dai delay + codec_dai delay

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Reviewed-by: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-pcm.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/soc/soc-pcm.c b/sound/soc/soc-pcm.c
index 4019bc10897c..9833e53754cb 100644
--- a/sound/soc/soc-pcm.c
+++ b/sound/soc/soc-pcm.c
@@ -1179,6 +1179,9 @@ static snd_pcm_uframes_t soc_pcm_pointer(struct snd_pcm_substream *substream)
 	snd_pcm_sframes_t codec_delay = 0;
 	int i;
 
+	/* clearing the previous total delay */
+	runtime->delay = 0;
+
 	for_each_rtdcom(rtd, rtdcom) {
 		component = rtdcom->component;
 
@@ -1190,6 +1193,8 @@ static snd_pcm_uframes_t soc_pcm_pointer(struct snd_pcm_substream *substream)
 		offset = component->driver->ops->pointer(substream);
 		break;
 	}
+	/* base delay if assigned in pointer callback */
+	delay = runtime->delay;
 
 	if (cpu_dai->driver->ops->delay)
 		delay += cpu_dai->driver->ops->delay(substream, cpu_dai);
-- 
cgit v1.2.3


From 304d34360b099020a12af2abb7e1ac506f4ba16d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 28 Jul 2018 10:19:13 +0200
Subject: spi: add flags parameter to txrx_word function pointers

Add the capability to specify the flag parameter used in
bitbang_txrx_be_cpha{0,1} through the txrx_word function pointers of
spi_bitbang data structure. That feature will be used to add spi-3wire
support to the spi-gpio controller

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-ath79.c         |  2 +-
 drivers/spi/spi-bitbang.c       | 34 +++++++++++++++++++++-------------
 drivers/spi/spi-butterfly.c     |  4 ++--
 drivers/spi/spi-gpio.c          | 32 ++++++++++++++++----------------
 drivers/spi/spi-lm70llp.c       |  5 +++--
 drivers/spi/spi-sh-sci.c        | 20 ++++++++++++--------
 drivers/spi/spi-xtensa-xtfpga.c |  2 +-
 include/linux/spi/spi_bitbang.h |  2 +-
 8 files changed, 57 insertions(+), 44 deletions(-)

diff --git a/drivers/spi/spi-ath79.c b/drivers/spi/spi-ath79.c
index 0719bd484891..3f6b657394de 100644
--- a/drivers/spi/spi-ath79.c
+++ b/drivers/spi/spi-ath79.c
@@ -176,7 +176,7 @@ static void ath79_spi_cleanup(struct spi_device *spi)
 }
 
 static u32 ath79_spi_txrx_mode0(struct spi_device *spi, unsigned int nsecs,
-			       u32 word, u8 bits)
+			       u32 word, u8 bits, unsigned flags)
 {
 	struct ath79_spi *sp = ath79_spidev_to_sp(spi);
 	u32 ioc = sp->ioc_base;
diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index 3aa9e6e3dac8..76f1b534bdd7 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -49,22 +49,26 @@
 struct spi_bitbang_cs {
 	unsigned	nsecs;	/* (clock cycle time)/2 */
 	u32		(*txrx_word)(struct spi_device *spi, unsigned nsecs,
-					u32 word, u8 bits);
+					u32 word, u8 bits, unsigned flags);
 	unsigned	(*txrx_bufs)(struct spi_device *,
 					u32 (*txrx_word)(
 						struct spi_device *spi,
 						unsigned nsecs,
-						u32 word, u8 bits),
-					unsigned, struct spi_transfer *);
+						u32 word, u8 bits,
+						unsigned flags),
+					unsigned, struct spi_transfer *,
+					unsigned);
 };
 
 static unsigned bitbang_txrx_8(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -76,7 +80,7 @@ static unsigned bitbang_txrx_8(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 1;
@@ -88,9 +92,11 @@ static unsigned bitbang_txrx_16(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -102,7 +108,7 @@ static unsigned bitbang_txrx_16(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 2;
@@ -114,9 +120,11 @@ static unsigned bitbang_txrx_32(
 	struct spi_device	*spi,
 	u32			(*txrx_word)(struct spi_device *spi,
 					unsigned nsecs,
-					u32 word, u8 bits),
+					u32 word, u8 bits,
+					unsigned flags),
 	unsigned		ns,
-	struct spi_transfer	*t
+	struct spi_transfer	*t,
+	unsigned flags
 ) {
 	unsigned		bits = t->bits_per_word;
 	unsigned		count = t->len;
@@ -128,7 +136,7 @@ static unsigned bitbang_txrx_32(
 
 		if (tx)
 			word = *tx++;
-		word = txrx_word(spi, ns, word, bits);
+		word = txrx_word(spi, ns, word, bits, flags);
 		if (rx)
 			*rx++ = word;
 		count -= 4;
@@ -236,7 +244,7 @@ static int spi_bitbang_bufs(struct spi_device *spi, struct spi_transfer *t)
 	struct spi_bitbang_cs	*cs = spi->controller_state;
 	unsigned		nsecs = cs->nsecs;
 
-	return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t);
+	return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, 0);
 }
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/spi/spi-butterfly.c b/drivers/spi/spi-butterfly.c
index 22a31e4a1a11..1a3510215841 100644
--- a/drivers/spi/spi-butterfly.c
+++ b/drivers/spi/spi-butterfly.c
@@ -144,9 +144,9 @@ static void butterfly_chipselect(struct spi_device *spi, int value)
 
 static u32
 butterfly_txrx_word_mode0(struct spi_device *spi, unsigned nsecs, u32 word,
-			  u8 bits)
+			  u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 /*----------------------------------------------------------------------*/
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index 6ae92d4dca19..be68298cbd9c 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -149,27 +149,27 @@ static inline int getmiso(const struct spi_device *spi)
  */
 
 static u32 spi_gpio_txrx_word_mode0(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode1(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode2(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
 /*
@@ -183,30 +183,30 @@ static u32 spi_gpio_txrx_word_mode3(struct spi_device *spi,
  */
 
 static u32 spi_gpio_spec_txrx_word_mode0(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode1(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode2(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 spi_gpio_spec_txrx_word_mode3(struct spi_device *spi,
-		unsigned nsecs, u32 word, u8 bits)
+		unsigned nsecs, u32 word, u8 bits, unsigned flags)
 {
-	unsigned flags = spi->master->flags;
+	flags = spi->master->flags;
 	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
diff --git a/drivers/spi/spi-lm70llp.c b/drivers/spi/spi-lm70llp.c
index 61ee0f4269ae..4549efd792da 100644
--- a/drivers/spi/spi-lm70llp.c
+++ b/drivers/spi/spi-lm70llp.c
@@ -188,9 +188,10 @@ static void lm70_chipselect(struct spi_device *spi, int value)
 /*
  * Our actual bitbanger routine.
  */
-static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits)
+static u32 lm70_txrx(struct spi_device *spi, unsigned nsecs, u32 word, u8 bits,
+		     unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static void spi_lm70llp_attach(struct parport *p)
diff --git a/drivers/spi/spi-sh-sci.c b/drivers/spi/spi-sh-sci.c
index a9beeeed812c..393701cfca3c 100644
--- a/drivers/spi/spi-sh-sci.c
+++ b/drivers/spi/spi-sh-sci.c
@@ -80,27 +80,31 @@ static inline u32 getmiso(struct spi_device *dev)
 #include "spi-bitbang-txrx.h"
 
 static u32 sh_sci_spi_txrx_mode0(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode1(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 0, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 0, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode2(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha0(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha0(spi, nsecs, 1, flags, word, bits);
 }
 
 static u32 sh_sci_spi_txrx_mode3(struct spi_device *spi,
-				      unsigned nsecs, u32 word, u8 bits)
+				 unsigned nsecs, u32 word, u8 bits,
+				 unsigned flags)
 {
-	return bitbang_txrx_be_cpha1(spi, nsecs, 1, 0, word, bits);
+	return bitbang_txrx_be_cpha1(spi, nsecs, 1, flags, word, bits);
 }
 
 static void sh_sci_spi_chipselect(struct spi_device *dev, int value)
diff --git a/drivers/spi/spi-xtensa-xtfpga.c b/drivers/spi/spi-xtensa-xtfpga.c
index be6155cba9de..8ce04f829a80 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -54,7 +54,7 @@ static inline void xtfpga_spi_wait_busy(struct xtfpga_spi *xspi)
 }
 
 static u32 xtfpga_spi_txrx_word(struct spi_device *spi, unsigned nsecs,
-				u32 v, u8 bits)
+				u32 v, u8 bits, unsigned flags)
 {
 	struct xtfpga_spi *xspi = spi_master_get_devdata(spi->master);
 
diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h
index c1e61641a7f1..5847f00ef9cf 100644
--- a/include/linux/spi/spi_bitbang.h
+++ b/include/linux/spi/spi_bitbang.h
@@ -30,7 +30,7 @@ struct spi_bitbang {
 	/* txrx_word[SPI_MODE_*]() just looks like a shift register */
 	u32	(*txrx_word[4])(struct spi_device *spi,
 			unsigned nsecs,
-			u32 word, u8 bits);
+			u32 word, u8 bits, unsigned flags);
 };
 
 /* you can call these default bitbang->master methods from your custom
-- 
cgit v1.2.3


From 4b859db2c60692560afbfef1b030d0ddef57b7ee Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Sat, 28 Jul 2018 10:19:14 +0200
Subject: spi: spi-gpio: add SPI_3WIRE support

Add SPI_3WIRE support to spi-gpio controller introducing
set_line_direction function pointer in spi_bitbang data structure.
Spi-gpio controller has been tested using hts221 temp/rh iio sensor
running in 3wire mode and lsm6dsm running in 4wire mode

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-bitbang.c       | 16 ++++++++++++++++
 drivers/spi/spi-gpio.c          | 17 ++++++++++++++++-
 include/linux/spi/spi_bitbang.h |  1 +
 3 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/spi/spi-bitbang.c b/drivers/spi/spi-bitbang.c
index 76f1b534bdd7..f29176000b8d 100644
--- a/drivers/spi/spi-bitbang.c
+++ b/drivers/spi/spi-bitbang.c
@@ -243,7 +243,23 @@ static int spi_bitbang_bufs(struct spi_device *spi, struct spi_transfer *t)
 {
 	struct spi_bitbang_cs	*cs = spi->controller_state;
 	unsigned		nsecs = cs->nsecs;
+	struct spi_bitbang	*bitbang;
+
+	bitbang = spi_master_get_devdata(spi->master);
+	if (bitbang->set_line_direction) {
+		int err;
 
+		err = bitbang->set_line_direction(spi, !!(t->tx_buf));
+		if (err < 0)
+			return err;
+	}
+
+	if (spi->mode & SPI_3WIRE) {
+		unsigned flags;
+
+		flags = t->tx_buf ? SPI_MASTER_NO_RX : SPI_MASTER_NO_TX;
+		return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, flags);
+	}
 	return cs->txrx_bufs(spi, cs->txrx_word, nsecs, t, 0);
 }
 
diff --git a/drivers/spi/spi-gpio.c b/drivers/spi/spi-gpio.c
index be68298cbd9c..0626e6e3ea0c 100644
--- a/drivers/spi/spi-gpio.c
+++ b/drivers/spi/spi-gpio.c
@@ -121,7 +121,10 @@ static inline int getmiso(const struct spi_device *spi)
 {
 	struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi);
 
-	return !!gpiod_get_value_cansleep(spi_gpio->miso);
+	if (spi->mode & SPI_3WIRE)
+		return !!gpiod_get_value_cansleep(spi_gpio->mosi);
+	else
+		return !!gpiod_get_value_cansleep(spi_gpio->miso);
 }
 
 /*
@@ -250,6 +253,16 @@ static int spi_gpio_setup(struct spi_device *spi)
 	return status;
 }
 
+static int spi_gpio_set_direction(struct spi_device *spi, bool output)
+{
+	struct spi_gpio *spi_gpio = spi_to_spi_gpio(spi);
+
+	if (output)
+		return gpiod_direction_output(spi_gpio->mosi, 1);
+	else
+		return gpiod_direction_input(spi_gpio->mosi);
+}
+
 static void spi_gpio_cleanup(struct spi_device *spi)
 {
 	spi_bitbang_cleanup(spi);
@@ -395,6 +408,7 @@ static int spi_gpio_probe(struct platform_device *pdev)
 		return status;
 
 	master->bits_per_word_mask = SPI_BPW_RANGE_MASK(1, 32);
+	master->mode_bits = SPI_3WIRE | SPI_CPHA | SPI_CPOL;
 	master->flags = master_flags;
 	master->bus_num = pdev->id;
 	/* The master needs to think there is a chipselect even if not connected */
@@ -407,6 +421,7 @@ static int spi_gpio_probe(struct platform_device *pdev)
 
 	spi_gpio->bitbang.master = master;
 	spi_gpio->bitbang.chipselect = spi_gpio_chipselect;
+	spi_gpio->bitbang.set_line_direction = spi_gpio_set_direction;
 
 	if ((master_flags & (SPI_MASTER_NO_TX | SPI_MASTER_NO_RX)) == 0) {
 		spi_gpio->bitbang.txrx_word[SPI_MODE_0] = spi_gpio_txrx_word_mode0;
diff --git a/include/linux/spi/spi_bitbang.h b/include/linux/spi/spi_bitbang.h
index 5847f00ef9cf..b7e021b274dc 100644
--- a/include/linux/spi/spi_bitbang.h
+++ b/include/linux/spi/spi_bitbang.h
@@ -31,6 +31,7 @@ struct spi_bitbang {
 	u32	(*txrx_word[4])(struct spi_device *spi,
 			unsigned nsecs,
 			u32 word, u8 bits, unsigned flags);
+	int	(*set_line_direction)(struct spi_device *spi, bool output);
 };
 
 /* you can call these default bitbang->master methods from your custom
-- 
cgit v1.2.3


From 0c60d3aa0e2d007e7f79c96c118da25f594afe02 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 1 Aug 2018 07:40:48 -0700
Subject: xfs: refactor log recovery check

Add a predicate to decide if the log is actively in recovery and use
that instead of open-coding a pagf_init check in the attr leaf verifier.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/libxfs/xfs_attr_leaf.c | 3 +--
 fs/xfs/xfs_log.c              | 9 +++++++++
 fs/xfs/xfs_log.h              | 1 +
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 4e7ef79a83c7..6fc5425b1474 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -242,7 +242,6 @@ xfs_attr3_leaf_verify(
 	struct xfs_attr3_icleaf_hdr	ichdr;
 	struct xfs_mount		*mp = bp->b_target->bt_mount;
 	struct xfs_attr_leafblock	*leaf = bp->b_addr;
-	struct xfs_perag		*pag = bp->b_pag;
 	struct xfs_attr_leaf_entry	*entries;
 	uint16_t			end;
 	int				i;
@@ -270,7 +269,7 @@ xfs_attr3_leaf_verify(
 	 * because we may have transitioned an empty shortform attr to a leaf
 	 * if the attr didn't fit in shortform.
 	 */
-	if (pag && pag->pagf_init && ichdr.count == 0)
+	if (!xfs_log_in_recovery(mp) && ichdr.count == 0)
 		return __this_address;
 
 	/*
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index fd10b1426382..00df4f39093a 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -4104,3 +4104,12 @@ xfs_log_check_lsn(
 
 	return valid;
 }
+
+bool
+xfs_log_in_recovery(
+	struct xfs_mount	*mp)
+{
+	struct xlog		*log = mp->m_log;
+
+	return log->l_flags & XLOG_ACTIVE_RECOVERY;
+}
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 3c1f6a8b4b70..73a64bf32f6f 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -153,5 +153,6 @@ bool	xfs_log_item_in_current_chkpt(struct xfs_log_item *lip);
 void	xfs_log_work_queue(struct xfs_mount *mp);
 void	xfs_log_quiesce(struct xfs_mount *mp);
 bool	xfs_log_check_lsn(struct xfs_mount *, xfs_lsn_t);
+bool	xfs_log_in_recovery(struct xfs_mount *);
 
 #endif	/* __XFS_LOG_H__ */
-- 
cgit v1.2.3


From 611995db2ce210d20d51c5270639b750476534e5 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 1 Aug 2018 07:40:48 -0700
Subject: xfs: use a local variable for magic number in xfs_da3_node_lookup_int

Use a local variable for the block magic number checks instead of
abusing blk->magic.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/libxfs/xfs_da_btree.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 9efbd2038ffb..8ffe17b223da 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -1481,6 +1481,7 @@ xfs_da3_node_lookup_int(
 	int			error;
 	int			retval;
 	unsigned int		expected_level = 0;
+	uint16_t		magic;
 	struct xfs_inode	*dp = state->args->dp;
 
 	args = state->args;
@@ -1505,17 +1506,17 @@ xfs_da3_node_lookup_int(
 			return error;
 		}
 		curr = blk->bp->b_addr;
-		blk->magic = be16_to_cpu(curr->magic);
+		magic = be16_to_cpu(curr->magic);
 
-		if (blk->magic == XFS_ATTR_LEAF_MAGIC ||
-		    blk->magic == XFS_ATTR3_LEAF_MAGIC) {
+		if (magic == XFS_ATTR_LEAF_MAGIC ||
+		    magic == XFS_ATTR3_LEAF_MAGIC) {
 			blk->magic = XFS_ATTR_LEAF_MAGIC;
 			blk->hashval = xfs_attr_leaf_lasthash(blk->bp, NULL);
 			break;
 		}
 
-		if (blk->magic == XFS_DIR2_LEAFN_MAGIC ||
-		    blk->magic == XFS_DIR3_LEAFN_MAGIC) {
+		if (magic == XFS_DIR2_LEAFN_MAGIC ||
+		    magic == XFS_DIR3_LEAFN_MAGIC) {
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
 							      blk->bp, NULL);
-- 
cgit v1.2.3


From 56830d6cc114f76f656d5e65ab355b070d5a695e Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 1 Aug 2018 07:40:48 -0700
Subject: xfs: check da node magic in _node_lookup_int

Before we start processing what we /think/ is a da3 node block, actually
check the magic to make sure that we're looking at a node block.  This
way we won't blow the asserts in _node_hdr_from_disk on corrupted
metadata.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/libxfs/xfs_da_btree.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index 8ffe17b223da..376bee94b5dd 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -1523,8 +1523,10 @@ xfs_da3_node_lookup_int(
 			break;
 		}
 
-		blk->magic = XFS_DA_NODE_MAGIC;
+		if (magic != XFS_DA_NODE_MAGIC && magic != XFS_DA3_NODE_MAGIC)
+			return -EFSCORRUPTED;
 
+		blk->magic = XFS_DA_NODE_MAGIC;
 
 		/*
 		 * Search an intermediate node for a match.
-- 
cgit v1.2.3


From 81351776c9fbbbd0de1dc1542f30aacfe68efc4e Mon Sep 17 00:00:00 2001
From: Taniya Das <tdas@codeaurora.org>
Date: Mon, 23 Jul 2018 16:24:35 +0530
Subject: clk: qcom: Add display clock controller driver for SDM845

Add support for the display clock controller found on SDM845
based devices. This would allow display drivers to probe and
control their clocks.

Signed-off-by: Taniya Das <tdas@codeaurora.org>
[sboyd@kernel.org: Remove CLK_GET_RATE_NOCACHE everywhere]
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/Kconfig         |  10 +
 drivers/clk/qcom/Makefile        |   1 +
 drivers/clk/qcom/dispcc-sdm845.c | 685 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 696 insertions(+)
 create mode 100644 drivers/clk/qcom/dispcc-sdm845.c

diff --git a/drivers/clk/qcom/Kconfig b/drivers/clk/qcom/Kconfig
index 9c3480dcc38a..730057471932 100644
--- a/drivers/clk/qcom/Kconfig
+++ b/drivers/clk/qcom/Kconfig
@@ -245,6 +245,16 @@ config SDM_VIDEOCC_845
 	  Say Y if you want to support video devices and functionality such as
 	  video encode and decode.
 
+config SDM_DISPCC_845
+	tristate "SDM845 Display Clock Controller"
+	select SDM_GCC_845
+	depends on COMMON_CLK_QCOM
+	help
+	  Support for the display clock controller on Qualcomm Technologies, Inc
+	  SDM845 devices.
+	  Say Y if you want to support display devices and functionality such as
+	  splash screen.
+
 config SPMI_PMIC_CLKDIV
 	tristate "SPMI PMIC clkdiv Support"
 	depends on (COMMON_CLK_QCOM && SPMI) || COMPILE_TEST
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 762c01137c2f..2b041b2db30a 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -38,6 +38,7 @@ obj-$(CONFIG_QCOM_A53PLL) += a53-pll.o
 obj-$(CONFIG_QCOM_CLK_APCS_MSM8916) += apcs-msm8916.o
 obj-$(CONFIG_QCOM_CLK_RPM) += clk-rpm.o
 obj-$(CONFIG_QCOM_CLK_SMD_RPM) += clk-smd-rpm.o
+obj-$(CONFIG_SDM_DISPCC_845) += dispcc-sdm845.o
 obj-$(CONFIG_SDM_GCC_845) += gcc-sdm845.o
 obj-$(CONFIG_SDM_VIDEOCC_845) += videocc-sdm845.o
 obj-$(CONFIG_SPMI_PMIC_CLKDIV) += clk-spmi-pmic-div.o
diff --git a/drivers/clk/qcom/dispcc-sdm845.c b/drivers/clk/qcom/dispcc-sdm845.c
new file mode 100644
index 000000000000..0cc4909b5dbe
--- /dev/null
+++ b/drivers/clk/qcom/dispcc-sdm845.c
@@ -0,0 +1,685 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset-controller.h>
+
+#include <dt-bindings/clock/qcom,dispcc-sdm845.h>
+
+#include "clk-alpha-pll.h"
+#include "clk-branch.h"
+#include "clk-rcg.h"
+#include "clk-regmap-divider.h"
+#include "common.h"
+#include "gdsc.h"
+#include "reset.h"
+
+enum {
+	P_BI_TCXO,
+	P_CORE_BI_PLL_TEST_SE,
+	P_DISP_CC_PLL0_OUT_MAIN,
+	P_DSI0_PHY_PLL_OUT_BYTECLK,
+	P_DSI0_PHY_PLL_OUT_DSICLK,
+	P_DSI1_PHY_PLL_OUT_BYTECLK,
+	P_DSI1_PHY_PLL_OUT_DSICLK,
+	P_GPLL0_OUT_MAIN,
+	P_GPLL0_OUT_MAIN_DIV,
+};
+
+static const struct parent_map disp_cc_parent_map_0[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DSI0_PHY_PLL_OUT_BYTECLK, 1 },
+	{ P_DSI1_PHY_PLL_OUT_BYTECLK, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_0[] = {
+	"bi_tcxo",
+	"dsi0_phy_pll_out_byteclk",
+	"dsi1_phy_pll_out_byteclk",
+	"core_bi_pll_test_se",
+};
+
+static const struct parent_map disp_cc_parent_map_2[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_2[] = {
+	"bi_tcxo",
+	"core_bi_pll_test_se",
+};
+
+static const struct parent_map disp_cc_parent_map_3[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DISP_CC_PLL0_OUT_MAIN, 1 },
+	{ P_GPLL0_OUT_MAIN, 4 },
+	{ P_GPLL0_OUT_MAIN_DIV, 5 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_3[] = {
+	"bi_tcxo",
+	"disp_cc_pll0",
+	"gcc_disp_gpll0_clk_src",
+	"gcc_disp_gpll0_div_clk_src",
+	"core_bi_pll_test_se",
+};
+
+static const struct parent_map disp_cc_parent_map_4[] = {
+	{ P_BI_TCXO, 0 },
+	{ P_DSI0_PHY_PLL_OUT_DSICLK, 1 },
+	{ P_DSI1_PHY_PLL_OUT_DSICLK, 2 },
+	{ P_CORE_BI_PLL_TEST_SE, 7 },
+};
+
+static const char * const disp_cc_parent_names_4[] = {
+	"bi_tcxo",
+	"dsi0_phy_pll_out_dsiclk",
+	"dsi1_phy_pll_out_dsiclk",
+	"core_bi_pll_test_se",
+};
+
+static struct clk_alpha_pll disp_cc_pll0 = {
+	.offset = 0x0,
+	.regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_FABIA],
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_pll0",
+			.parent_names = (const char *[]){ "bi_tcxo" },
+			.num_parents = 1,
+			.ops = &clk_alpha_pll_fabia_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_byte0_clk_src = {
+	.cmd_rcgr = 0x20d0,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_byte0_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_byte1_clk_src = {
+	.cmd_rcgr = 0x20ec,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_byte1_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_byte2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_esc0_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_esc0_clk_src = {
+	.cmd_rcgr = 0x2108,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.freq_tbl = ftbl_disp_cc_mdss_esc0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_esc0_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_esc1_clk_src = {
+	.cmd_rcgr = 0x2120,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_0,
+	.freq_tbl = ftbl_disp_cc_mdss_esc0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_esc1_clk_src",
+		.parent_names = disp_cc_parent_names_0,
+		.num_parents = 4,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_mdp_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(85714286, P_GPLL0_OUT_MAIN, 7, 0, 0),
+	F(100000000, P_GPLL0_OUT_MAIN, 6, 0, 0),
+	F(150000000, P_GPLL0_OUT_MAIN, 4, 0, 0),
+	F(171428571, P_GPLL0_OUT_MAIN, 3.5, 0, 0),
+	F(200000000, P_GPLL0_OUT_MAIN, 3, 0, 0),
+	F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0),
+	F(344000000, P_DISP_CC_PLL0_OUT_MAIN, 2.5, 0, 0),
+	F(430000000, P_DISP_CC_PLL0_OUT_MAIN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_mdp_clk_src = {
+	.cmd_rcgr = 0x2088,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_3,
+	.freq_tbl = ftbl_disp_cc_mdss_mdp_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_mdp_clk_src",
+		.parent_names = disp_cc_parent_names_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_pclk0_clk_src = {
+	.cmd_rcgr = 0x2058,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_pclk0_clk_src",
+		.parent_names = disp_cc_parent_names_4,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_pixel_ops,
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_rcg2 disp_cc_mdss_pclk1_clk_src = {
+	.cmd_rcgr = 0x2070,
+	.mnd_width = 8,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_4,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_pclk1_clk_src",
+		.parent_names = disp_cc_parent_names_4,
+		.num_parents = 4,
+		.flags = CLK_SET_RATE_PARENT,
+		.ops = &clk_pixel_ops,
+	},
+};
+
+static const struct freq_tbl ftbl_disp_cc_mdss_rot_clk_src[] = {
+	F(19200000, P_BI_TCXO, 1, 0, 0),
+	F(171428571, P_GPLL0_OUT_MAIN, 3.5, 0, 0),
+	F(300000000, P_GPLL0_OUT_MAIN, 2, 0, 0),
+	F(344000000, P_DISP_CC_PLL0_OUT_MAIN, 2.5, 0, 0),
+	F(430000000, P_DISP_CC_PLL0_OUT_MAIN, 2, 0, 0),
+	{ }
+};
+
+static struct clk_rcg2 disp_cc_mdss_rot_clk_src = {
+	.cmd_rcgr = 0x20a0,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_3,
+	.freq_tbl = ftbl_disp_cc_mdss_rot_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_rot_clk_src",
+		.parent_names = disp_cc_parent_names_3,
+		.num_parents = 5,
+		.ops = &clk_rcg2_shared_ops,
+	},
+};
+
+static struct clk_rcg2 disp_cc_mdss_vsync_clk_src = {
+	.cmd_rcgr = 0x20b8,
+	.mnd_width = 0,
+	.hid_width = 5,
+	.parent_map = disp_cc_parent_map_2,
+	.freq_tbl = ftbl_disp_cc_mdss_esc0_clk_src,
+	.clkr.hw.init = &(struct clk_init_data){
+		.name = "disp_cc_mdss_vsync_clk_src",
+		.parent_names = disp_cc_parent_names_2,
+		.num_parents = 2,
+		.ops = &clk_rcg2_ops,
+	},
+};
+
+static struct clk_branch disp_cc_mdss_ahb_clk = {
+	.halt_reg = 0x4004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x4004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_axi_clk = {
+	.halt_reg = 0x4008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x4008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_axi_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte0_clk = {
+	.halt_reg = 0x2028,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2028,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = {
+	.reg = 0x20e8,
+	.shift = 0,
+	.width = 2,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_div_clk_src",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte0_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte0_intf_clk = {
+	.halt_reg = 0x202c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x202c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte0_intf_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte0_div_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte1_clk = {
+	.halt_reg = 0x2030,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2030,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte1_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_regmap_div disp_cc_mdss_byte1_div_clk_src = {
+	.reg = 0x2104,
+	.shift = 0,
+	.width = 2,
+	.clkr = {
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte1_div_clk_src",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte1_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_div_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_byte1_intf_clk = {
+	.halt_reg = 0x2034,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2034,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_byte1_intf_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_byte1_div_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_esc0_clk = {
+	.halt_reg = 0x2038,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2038,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_esc0_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_esc0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_esc1_clk = {
+	.halt_reg = 0x203c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x203c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_esc1_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_esc1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_mdp_clk = {
+	.halt_reg = 0x200c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x200c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_mdp_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_mdp_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_mdp_lut_clk = {
+	.halt_reg = 0x201c,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x201c,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_mdp_lut_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_mdp_clk_src",
+			},
+			.num_parents = 1,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_pclk0_clk = {
+	.halt_reg = 0x2004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_pclk0_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_pclk0_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+/* Return the HW recalc rate for idle use case */
+static struct clk_branch disp_cc_mdss_pclk1_clk = {
+	.halt_reg = 0x2008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_pclk1_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_pclk1_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rot_clk = {
+	.halt_reg = 0x2014,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2014,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rot_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_rot_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rscc_ahb_clk = {
+	.halt_reg = 0x5004,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5004,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rscc_ahb_clk",
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_rscc_vsync_clk = {
+	.halt_reg = 0x5008,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x5008,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_rscc_vsync_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_vsync_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct clk_branch disp_cc_mdss_vsync_clk = {
+	.halt_reg = 0x2024,
+	.halt_check = BRANCH_HALT,
+	.clkr = {
+		.enable_reg = 0x2024,
+		.enable_mask = BIT(0),
+		.hw.init = &(struct clk_init_data){
+			.name = "disp_cc_mdss_vsync_clk",
+			.parent_names = (const char *[]){
+				"disp_cc_mdss_vsync_clk_src",
+			},
+			.num_parents = 1,
+			.flags = CLK_SET_RATE_PARENT,
+			.ops = &clk_branch2_ops,
+		},
+	},
+};
+
+static struct gdsc mdss_gdsc = {
+	.gdscr = 0x3000,
+	.pd = {
+		.name = "mdss_gdsc",
+	},
+	.pwrsts = PWRSTS_OFF_ON,
+	.flags = HW_CTRL | POLL_CFG_GDSCR,
+};
+
+static struct clk_regmap *disp_cc_sdm845_clocks[] = {
+	[DISP_CC_MDSS_AHB_CLK] = &disp_cc_mdss_ahb_clk.clkr,
+	[DISP_CC_MDSS_AXI_CLK] = &disp_cc_mdss_axi_clk.clkr,
+	[DISP_CC_MDSS_BYTE0_CLK] = &disp_cc_mdss_byte0_clk.clkr,
+	[DISP_CC_MDSS_BYTE0_CLK_SRC] = &disp_cc_mdss_byte0_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE0_INTF_CLK] = &disp_cc_mdss_byte0_intf_clk.clkr,
+	[DISP_CC_MDSS_BYTE0_DIV_CLK_SRC] =
+					&disp_cc_mdss_byte0_div_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE1_CLK] = &disp_cc_mdss_byte1_clk.clkr,
+	[DISP_CC_MDSS_BYTE1_CLK_SRC] = &disp_cc_mdss_byte1_clk_src.clkr,
+	[DISP_CC_MDSS_BYTE1_INTF_CLK] = &disp_cc_mdss_byte1_intf_clk.clkr,
+	[DISP_CC_MDSS_BYTE1_DIV_CLK_SRC] =
+					&disp_cc_mdss_byte1_div_clk_src.clkr,
+	[DISP_CC_MDSS_ESC0_CLK] = &disp_cc_mdss_esc0_clk.clkr,
+	[DISP_CC_MDSS_ESC0_CLK_SRC] = &disp_cc_mdss_esc0_clk_src.clkr,
+	[DISP_CC_MDSS_ESC1_CLK] = &disp_cc_mdss_esc1_clk.clkr,
+	[DISP_CC_MDSS_ESC1_CLK_SRC] = &disp_cc_mdss_esc1_clk_src.clkr,
+	[DISP_CC_MDSS_MDP_CLK] = &disp_cc_mdss_mdp_clk.clkr,
+	[DISP_CC_MDSS_MDP_CLK_SRC] = &disp_cc_mdss_mdp_clk_src.clkr,
+	[DISP_CC_MDSS_MDP_LUT_CLK] = &disp_cc_mdss_mdp_lut_clk.clkr,
+	[DISP_CC_MDSS_PCLK0_CLK] = &disp_cc_mdss_pclk0_clk.clkr,
+	[DISP_CC_MDSS_PCLK0_CLK_SRC] = &disp_cc_mdss_pclk0_clk_src.clkr,
+	[DISP_CC_MDSS_PCLK1_CLK] = &disp_cc_mdss_pclk1_clk.clkr,
+	[DISP_CC_MDSS_PCLK1_CLK_SRC] = &disp_cc_mdss_pclk1_clk_src.clkr,
+	[DISP_CC_MDSS_ROT_CLK] = &disp_cc_mdss_rot_clk.clkr,
+	[DISP_CC_MDSS_ROT_CLK_SRC] = &disp_cc_mdss_rot_clk_src.clkr,
+	[DISP_CC_MDSS_RSCC_AHB_CLK] = &disp_cc_mdss_rscc_ahb_clk.clkr,
+	[DISP_CC_MDSS_RSCC_VSYNC_CLK] = &disp_cc_mdss_rscc_vsync_clk.clkr,
+	[DISP_CC_MDSS_VSYNC_CLK] = &disp_cc_mdss_vsync_clk.clkr,
+	[DISP_CC_MDSS_VSYNC_CLK_SRC] = &disp_cc_mdss_vsync_clk_src.clkr,
+	[DISP_CC_PLL0] = &disp_cc_pll0.clkr,
+};
+
+static const struct qcom_reset_map disp_cc_sdm845_resets[] = {
+	[DISP_CC_MDSS_RSCC_BCR] = { 0x5000 },
+};
+
+static struct gdsc *disp_cc_sdm845_gdscs[] = {
+	[MDSS_GDSC] = &mdss_gdsc,
+};
+
+static const struct regmap_config disp_cc_sdm845_regmap_config = {
+	.reg_bits	= 32,
+	.reg_stride	= 4,
+	.val_bits	= 32,
+	.max_register	= 0x10000,
+	.fast_io	= true,
+};
+
+static const struct qcom_cc_desc disp_cc_sdm845_desc = {
+	.config = &disp_cc_sdm845_regmap_config,
+	.clks = disp_cc_sdm845_clocks,
+	.num_clks = ARRAY_SIZE(disp_cc_sdm845_clocks),
+	.resets = disp_cc_sdm845_resets,
+	.num_resets = ARRAY_SIZE(disp_cc_sdm845_resets),
+	.gdscs = disp_cc_sdm845_gdscs,
+	.num_gdscs = ARRAY_SIZE(disp_cc_sdm845_gdscs),
+};
+
+static const struct of_device_id disp_cc_sdm845_match_table[] = {
+	{ .compatible = "qcom,sdm845-dispcc" },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, disp_cc_sdm845_match_table);
+
+static int disp_cc_sdm845_probe(struct platform_device *pdev)
+{
+	struct regmap *regmap;
+	struct alpha_pll_config disp_cc_pll0_config = {};
+
+	regmap = qcom_cc_map(pdev, &disp_cc_sdm845_desc);
+	if (IS_ERR(regmap))
+		return PTR_ERR(regmap);
+
+	disp_cc_pll0_config.l = 0x2c;
+	disp_cc_pll0_config.alpha = 0xcaaa;
+
+	clk_fabia_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config);
+
+	/* Enable hardware clock gating for DSI and MDP clocks */
+	regmap_update_bits(regmap, 0x8000, 0x7f0, 0x7f0);
+
+	return qcom_cc_really_probe(pdev, &disp_cc_sdm845_desc, regmap);
+}
+
+static struct platform_driver disp_cc_sdm845_driver = {
+	.probe		= disp_cc_sdm845_probe,
+	.driver		= {
+		.name	= "disp_cc-sdm845",
+		.of_match_table = disp_cc_sdm845_match_table,
+	},
+};
+
+static int __init disp_cc_sdm845_init(void)
+{
+	return platform_driver_register(&disp_cc_sdm845_driver);
+}
+subsys_initcall(disp_cc_sdm845_init);
+
+static void __exit disp_cc_sdm845_exit(void)
+{
+	platform_driver_unregister(&disp_cc_sdm845_driver);
+}
+module_exit(disp_cc_sdm845_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("QTI DISPCC SDM845 Driver");
-- 
cgit v1.2.3


From 4725549192c9633b6a3740bf23770cb758bee4a0 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 1 Aug 2018 00:13:14 +0800
Subject: block/bsg-lib: use PTR_ERR_OR_ZERO to simplify the flow path

Simplify the code by using the PTR_ERR_OR_ZERO, instead of the
open code. It is better.

Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bsg-lib.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index 9419def8c017..f3501cdaf1a6 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -48,9 +48,8 @@ static int bsg_transport_fill_hdr(struct request *rq, struct sg_io_v4 *hdr,
 
 	job->request_len = hdr->request_len;
 	job->request = memdup_user(uptr64(hdr->request), hdr->request_len);
-	if (IS_ERR(job->request))
-		return PTR_ERR(job->request);
-	return 0;
+
+	return PTR_ERR_OR_ZERO(job->request);
 }
 
 static int bsg_transport_complete_rq(struct request *rq, struct sg_io_v4 *hdr)
-- 
cgit v1.2.3


From 52a1199ccd426ad583ade4eb678b3b5846c58f43 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Tue, 31 Jul 2018 12:39:02 -0400
Subject: blk-iolatency: fix blkg leak in timer_fn

At this point we have a ref on the blkg, we need to drop it if we don't
have a iolat.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-iolatency.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index bb59b2929e0d..b0dc4fc64b3e 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -627,7 +627,7 @@ static void blkiolatency_timer_fn(struct timer_list *t)
 
 		iolat = blkg_to_lat(blkg);
 		if (!iolat)
-			continue;
+			goto next;
 
 		lat_info = &iolat->child_lat;
 		cookie = atomic_read(&lat_info->scale_cookie);
-- 
cgit v1.2.3


From cc7ecc258562b065ef638c4b45e20953d57fb564 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Tue, 31 Jul 2018 12:39:03 -0400
Subject: blk-cgroup: hold the queue ref during throttling

The blkg lifetime is protected by the queue lifetime, so we need to put
the queue _after_ we're done using the blkg.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-cgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index 1942357d7165..694595b29b8f 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -1759,10 +1759,10 @@ void blkcg_maybe_throttle_current(void)
 	if (!blkg)
 		goto out;
 	rcu_read_unlock();
-	blk_put_queue(q);
 
 	blkcg_maybe_throttle_blkg(blkg, use_memdelay);
 	blkg_put(blkg);
+	blk_put_queue(q);
 	return;
 out:
 	rcu_read_unlock();
-- 
cgit v1.2.3


From 2c323017e381c55c5ce2a603b8305bb18c1162cc Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Tue, 31 Jul 2018 12:39:04 -0400
Subject: blk-cgroup: clear the throttle queue on fork

We were hitting a panic in production where we put too many times on the
request queue.  This is because we'd get the throttle_queue of the
parent if we fork()'ed while we needed to be throttled, but we didn't
have a reference on it.  Instead just clear these flags on fork so the
child doesn't pay for the sins of its father.

Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 kernel/fork.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/fork.c b/kernel/fork.c
index 9440d61b925c..694ae0e56866 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -843,6 +843,11 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node)
 	tsk->fail_nth = 0;
 #endif
 
+#ifdef CONFIG_BLK_CGROUP
+	tsk->throttle_queue = NULL;
+	tsk->use_memdelay = 0;
+#endif
+
 	return tsk;
 
 free_stack:
-- 
cgit v1.2.3


From 21b8732eb4479b579bda9ee38e62b2c312c2a0e5 Mon Sep 17 00:00:00 2001
From: Christophe Leroy <christophe.leroy@c-s.fr>
Date: Fri, 22 Sep 2017 13:20:43 +0200
Subject: perf tools: Allow overriding MAX_NR_CPUS at compile time

After update of kernel, the perf tool doesn't run anymore on my 32MB RAM
powerpc board, but still runs on a 128MB RAM board:

  ~# strace perf
  execve("/usr/sbin/perf", ["perf"], [/* 12 vars */]) = -1 ENOMEM (Cannot allocate memory)
  --- SIGSEGV {si_signo=SIGSEGV, si_code=SI_KERNEL, si_addr=0} ---
  +++ killed by SIGSEGV +++
  Segmentation fault

objdump -x shows that .bss section has a huge size of 24Mbytes:

 27 .bss          016baca8  101cebb8  101cebb8  001cd988  2**3

With especially the following objects having quite big size:

  10205f80 l     O .bss	00140000     runtime_cycles_stats
  10345f80 l     O .bss	00140000     runtime_stalled_cycles_front_stats
  10485f80 l     O .bss	00140000     runtime_stalled_cycles_back_stats
  105c5f80 l     O .bss	00140000     runtime_branches_stats
  10705f80 l     O .bss	00140000     runtime_cacherefs_stats
  10845f80 l     O .bss	00140000     runtime_l1_dcache_stats
  10985f80 l     O .bss	00140000     runtime_l1_icache_stats
  10ac5f80 l     O .bss	00140000     runtime_ll_cache_stats
  10c05f80 l     O .bss	00140000     runtime_itlb_cache_stats
  10d45f80 l     O .bss	00140000     runtime_dtlb_cache_stats
  10e85f80 l     O .bss	00140000     runtime_cycles_in_tx_stats
  10fc5f80 l     O .bss	00140000     runtime_transaction_stats
  11105f80 l     O .bss	00140000     runtime_elision_stats
  11245f80 l     O .bss	00140000     runtime_topdown_total_slots
  11385f80 l     O .bss	00140000     runtime_topdown_slots_retired
  114c5f80 l     O .bss	00140000     runtime_topdown_slots_issued
  11605f80 l     O .bss	00140000     runtime_topdown_fetch_bubbles
  11745f80 l     O .bss	00140000     runtime_topdown_recovery_bubbles

This is due to commit 4d255766d28b1 ("perf: Bump max number of cpus
to 1024"), because many tables are sized with MAX_NR_CPUS

This patch gives the opportunity to redefine MAX_NR_CPUS via

  $ make EXTRA_CFLAGS=-DMAX_NR_CPUS=1

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/20170922112043.8349468C57@po15668-vm-win7.idsi0.si.c-s.fr
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/perf.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index d215714f48df..21bf7f5a3cf5 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -25,7 +25,9 @@ static inline unsigned long long rdclock(void)
 	return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
 }
 
+#ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS			1024
+#endif
 
 extern const char *input_name;
 extern bool perf_host, perf_guest;
-- 
cgit v1.2.3


From 822c2621daadcf9e8fa8f11f7334e3c349434154 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 1 Aug 2018 10:50:51 -0300
Subject: perf bpf: Include uapi/linux/bpf.h from the 'perf trace' script's
 bpf.h

The next example scripts need the definition for the BPF functions, i.e.
things like BPF_FUNC_probe_read, and in time will require lots of other
definitions found in uapi/linux/bpf.h, so include it from the bpf.h file
included from the eBPF scripts build with clang via '-e bpf_script.c'
like in this example:

  $ tail -8 tools/perf/examples/bpf/5sec.c
  #include <bpf.h>

  int probe(hrtimer_nanosleep, rqtp->tv_sec)(void *ctx, int err, long sec)
  {
	return sec == 5;
  }

  license(GPL);
  $

That 'bpf.h' include in the 5sec.c eBPF example will come from a set of
header files crafted for building eBPF objects, that in a end-user
system will come from:

  /usr/lib/perf/include/bpf/bpf.h

And will include <uapi/linux/bpf.h> either from the place where the
kernel was built, or from a kernel-devel rpm package like:

  -working-directory /lib/modules/4.17.9-100.fc27.x86_64/build

That is set up by tools/perf/util/llvm-utils.c, and can be overriden
by setting the 'kbuild-dir' variable in the "llvm" ~/.perfconfig file,
like:

  # cat ~/.perfconfig
  [llvm]
       kbuild-dir = /home/foo/git/build/linux

This usually doesn't need any change, just documenting here my findings
while working with this code.

In the future we may want to instead just use what is in
/usr/include/linux/bpf.h, that comes from the UAPI provided from the
kernel sources, for now, to avoid getting the kernel's non-UAPI
"linux/bpf.h" file, that will cause clang to fail and is not what we
want anyway (no BPF function definitions, etc), do it explicitely by
asking for "uapi/linux/bpf.h".

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-zd8zeyhr2sappevojdem9xxt@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/include/bpf/bpf.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/perf/include/bpf/bpf.h b/tools/perf/include/bpf/bpf.h
index dd764ad5efdf..a63aa6241b7f 100644
--- a/tools/perf/include/bpf/bpf.h
+++ b/tools/perf/include/bpf/bpf.h
@@ -1,6 +1,9 @@
 // SPDX-License-Identifier: GPL-2.0
 #ifndef _PERF_BPF_H
 #define _PERF_BPF_H
+
+#include <uapi/linux/bpf.h>
+
 #define SEC(NAME) __attribute__((section(NAME),  used))
 
 #define probe(function, vars) \
-- 
cgit v1.2.3


From 5ef2a69993676a0dfd49bf60ae1323eb8a288366 Mon Sep 17 00:00:00 2001
From: Wang Shilong <wshilong@ddn.com>
Date: Wed, 1 Aug 2018 12:02:31 -0400
Subject: ext4: use ext4_warning() for sb_getblk failure

Out of memory should not be considered as critical errors; so replace
ext4_error() with ext4_warnig().

Signed-off-by: Wang Shilong <wshilong@ddn.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/balloc.c | 6 +++---
 fs/ext4/ialloc.c | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index aa52d87985aa..e5d6ee61ff48 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -426,9 +426,9 @@ ext4_read_block_bitmap_nowait(struct super_block *sb, ext4_group_t block_group)
 	}
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot get buffer for block bitmap - "
-			   "block_group = %u, block_bitmap = %llu",
-			   block_group, bitmap_blk);
+		ext4_warning(sb, "Cannot get buffer for block bitmap - "
+			     "block_group = %u, block_bitmap = %llu",
+			     block_group, bitmap_blk);
 		return ERR_PTR(-ENOMEM);
 	}
 
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index dffd21de2694..2addcb8730e1 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -138,9 +138,9 @@ ext4_read_inode_bitmap(struct super_block *sb, ext4_group_t block_group)
 	}
 	bh = sb_getblk(sb, bitmap_blk);
 	if (unlikely(!bh)) {
-		ext4_error(sb, "Cannot read inode bitmap - "
-			    "block_group = %u, inode_bitmap = %llu",
-			    block_group, bitmap_blk);
+		ext4_warning(sb, "Cannot read inode bitmap - "
+			     "block_group = %u, inode_bitmap = %llu",
+			     block_group, bitmap_blk);
 		return ERR_PTR(-ENOMEM);
 	}
 	if (bitmap_uptodate(bh))
-- 
cgit v1.2.3


From 5a6cd13d4faef48bdcb7ae9c1e98175332ced7cd Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 10:58:25 -0500
Subject: ALSA: pcm: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1357375 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/oss/pcm_plugin.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/core/oss/pcm_plugin.c b/sound/core/oss/pcm_plugin.c
index 85bab922ce69..0391cb1a4f19 100644
--- a/sound/core/oss/pcm_plugin.c
+++ b/sound/core/oss/pcm_plugin.c
@@ -353,6 +353,7 @@ snd_pcm_format_t snd_pcm_plug_slave_format(snd_pcm_format_t format,
 				if (snd_mask_test(format_mask, (__force int)format1))
 					return format1;
 			}
+			/* fall through */
 		default:
 			return (__force snd_pcm_format_t)-EINVAL;
 		}
-- 
cgit v1.2.3


From fea49f60c9b748abf4a1a9b2e9391d0c5b003848 Mon Sep 17 00:00:00 2001
From: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Date: Tue, 31 Jul 2018 01:05:39 +0300
Subject: net: ethernet: ti: cpsw: replace unnecessarily macroses on functions

Replace ugly macroses on functions.

Reviewed-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Ivan Khoronzhuk <ivan.khoronzhuk@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpsw.c | 58 +++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 1b54c26c2bec..f051ce35a440 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -565,40 +565,28 @@ static const struct cpsw_stats cpsw_gstrings_ch_stats[] = {
 				(func)(slave++, ##arg);			\
 	} while (0)
 
-#define cpsw_dual_emac_src_port_detect(cpsw, status, ndev, skb)		\
-	do {								\
-		if (!cpsw->data.dual_emac)				\
-			break;						\
-		if (CPDMA_RX_SOURCE_PORT(status) == 1) {		\
-			ndev = cpsw->slaves[0].ndev;			\
-			skb->dev = ndev;				\
-		} else if (CPDMA_RX_SOURCE_PORT(status) == 2) {		\
-			ndev = cpsw->slaves[1].ndev;			\
-			skb->dev = ndev;				\
-		}							\
-	} while (0)
-#define cpsw_add_mcast(cpsw, priv, addr)				\
-	do {								\
-		if (cpsw->data.dual_emac) {				\
-			struct cpsw_slave *slave = cpsw->slaves +	\
-						priv->emac_port;	\
-			int slave_port = cpsw_get_slave_port(		\
-						slave->slave_num);	\
-			cpsw_ale_add_mcast(cpsw->ale, addr,		\
-				1 << slave_port | ALE_PORT_HOST,	\
-				ALE_VLAN, slave->port_vlan, 0);		\
-		} else {						\
-			cpsw_ale_add_mcast(cpsw->ale, addr,		\
-				ALE_ALL_PORTS,				\
-				0, 0, 0);				\
-		}							\
-	} while (0)
-
 static inline int cpsw_get_slave_port(u32 slave_num)
 {
 	return slave_num + 1;
 }
 
+static void cpsw_add_mcast(struct cpsw_priv *priv, u8 *addr)
+{
+	struct cpsw_common *cpsw = priv->cpsw;
+
+	if (cpsw->data.dual_emac) {
+		struct cpsw_slave *slave = cpsw->slaves + priv->emac_port;
+		int slave_port = cpsw_get_slave_port(slave->slave_num);
+
+		cpsw_ale_add_mcast(cpsw->ale, addr,
+				   1 << slave_port | ALE_PORT_HOST,
+				   ALE_VLAN, slave->port_vlan, 0);
+		return;
+	}
+
+	cpsw_ale_add_mcast(cpsw->ale, addr, ALE_ALL_PORTS, 0, 0, 0);
+}
+
 static void cpsw_set_promiscious(struct net_device *ndev, bool enable)
 {
 	struct cpsw_common *cpsw = ndev_to_cpsw(ndev);
@@ -706,7 +694,7 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev)
 
 		/* program multicast address list into ALE register */
 		netdev_for_each_mc_addr(ha, ndev) {
-			cpsw_add_mcast(cpsw, priv, (u8 *)ha->addr);
+			cpsw_add_mcast(priv, ha->addr);
 		}
 	}
 }
@@ -798,10 +786,16 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	struct sk_buff		*skb = token;
 	struct sk_buff		*new_skb;
 	struct net_device	*ndev = skb->dev;
-	int			ret = 0;
+	int			ret = 0, port;
 	struct cpsw_common	*cpsw = ndev_to_cpsw(ndev);
 
-	cpsw_dual_emac_src_port_detect(cpsw, status, ndev, skb);
+	if (cpsw->data.dual_emac) {
+		port = CPDMA_RX_SOURCE_PORT(status);
+		if (port) {
+			ndev = cpsw->slaves[--port].ndev;
+			skb->dev = ndev;
+		}
+	}
 
 	if (unlikely(status < 0) || unlikely(!netif_running(ndev))) {
 		/* In dual emac mode check for all interfaces */
-- 
cgit v1.2.3


From f394ad28feffbeebab77c8bf9a203bd49b957c9a Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Mon, 30 Jul 2018 22:48:41 -0700
Subject: rds: rds_ib_recv_alloc_cache() should call alloc_percpu_gfp() instead

Currently, rds_ib_conn_alloc() calls rds_ib_recv_alloc_caches()
without passing along the gfp_t flag.  But rds_ib_recv_alloc_caches()
and rds_ib_recv_alloc_cache() should take a gfp_t parameter so that
rds_ib_recv_alloc_cache() can call alloc_percpu_gfp() using the
correct flag instead of calling alloc_percpu().

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib.h      |  2 +-
 net/rds/ib_cm.c   |  2 +-
 net/rds/ib_recv.c | 10 +++++-----
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/rds/ib.h b/net/rds/ib.h
index beb95b893f78..73427ff439f9 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -400,7 +400,7 @@ void rds_ib_mr_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc);
 int rds_ib_recv_init(void);
 void rds_ib_recv_exit(void);
 int rds_ib_recv_path(struct rds_conn_path *conn);
-int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic);
+int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp);
 void rds_ib_recv_free_caches(struct rds_ib_connection *ic);
 void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp);
 void rds_ib_inc_free(struct rds_incoming *inc);
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index a33b82dc0804..0d654d99fe41 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -1102,7 +1102,7 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 	if (!ic)
 		return -ENOMEM;
 
-	ret = rds_ib_recv_alloc_caches(ic);
+	ret = rds_ib_recv_alloc_caches(ic, gfp);
 	if (ret) {
 		kfree(ic);
 		return ret;
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 557ccbb1ce00..d300186b8dc0 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -98,12 +98,12 @@ static void rds_ib_cache_xfer_to_ready(struct rds_ib_refill_cache *cache)
 	}
 }
 
-static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache)
+static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache, gfp_t gfp)
 {
 	struct rds_ib_cache_head *head;
 	int cpu;
 
-	cache->percpu = alloc_percpu(struct rds_ib_cache_head);
+	cache->percpu = alloc_percpu_gfp(struct rds_ib_cache_head, gfp);
 	if (!cache->percpu)
 	       return -ENOMEM;
 
@@ -118,13 +118,13 @@ static int rds_ib_recv_alloc_cache(struct rds_ib_refill_cache *cache)
 	return 0;
 }
 
-int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic)
+int rds_ib_recv_alloc_caches(struct rds_ib_connection *ic, gfp_t gfp)
 {
 	int ret;
 
-	ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs);
+	ret = rds_ib_recv_alloc_cache(&ic->i_cache_incs, gfp);
 	if (!ret) {
-		ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags);
+		ret = rds_ib_recv_alloc_cache(&ic->i_cache_frags, gfp);
 		if (ret)
 			free_percpu(ic->i_cache_incs.percpu);
 	}
-- 
cgit v1.2.3


From e65d4d96334e3ff4fe0064612a93a51c63de08de Mon Sep 17 00:00:00 2001
From: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Date: Mon, 30 Jul 2018 22:48:42 -0700
Subject: rds: Remove IPv6 dependency

This patch removes the IPv6 dependency from RDS.

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/Kconfig          |  2 +-
 net/rds/af_rds.c         | 32 +++++++++++++++++++-------------
 net/rds/bind.c           |  4 +++-
 net/rds/connection.c     | 26 ++++++++++++++++++++++++--
 net/rds/ib.c             | 31 ++++++++++++++++++++++++++-----
 net/rds/ib_cm.c          |  9 +++++++++
 net/rds/ib_rdma.c        |  2 ++
 net/rds/rdma_transport.c | 10 ++++++++++
 net/rds/recv.c           |  2 ++
 net/rds/send.c           |  2 ++
 net/rds/tcp.c            | 25 +++++++++++++++++++++++++
 net/rds/tcp_listen.c     | 21 +++++++++++++++++----
 12 files changed, 140 insertions(+), 26 deletions(-)

diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index 4c7f2595d919..41f75563b54b 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -1,7 +1,7 @@
 
 config RDS
 	tristate "The RDS Protocol"
-	depends on INET && IPV6
+	depends on INET
 	---help---
 	  The RDS (Reliable Datagram Sockets) protocol provides reliable,
 	  sequenced delivery of datagrams over Infiniband or TCP.
diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c
index fc5c48b248fe..65387e1e6964 100644
--- a/net/rds/af_rds.c
+++ b/net/rds/af_rds.c
@@ -156,18 +156,20 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
 				return sizeof(*sin);
 			}
 
-			if (ipv6_addr_type(&rs->rs_conn_addr) &
-			    IPV6_ADDR_MAPPED) {
-				sin = (struct sockaddr_in *)uaddr;
-				memset(sin, 0, sizeof(*sin));
-				sin->sin_family = AF_INET;
-				return sizeof(*sin);
+#if IS_ENABLED(CONFIG_IPV6)
+			if (!(ipv6_addr_type(&rs->rs_conn_addr) &
+			      IPV6_ADDR_MAPPED)) {
+				sin6 = (struct sockaddr_in6 *)uaddr;
+				memset(sin6, 0, sizeof(*sin6));
+				sin6->sin6_family = AF_INET6;
+				return sizeof(*sin6);
 			}
+#endif
 
-			sin6 = (struct sockaddr_in6 *)uaddr;
-			memset(sin6, 0, sizeof(*sin6));
-			sin6->sin6_family = AF_INET6;
-			return sizeof(*sin6);
+			sin = (struct sockaddr_in *)uaddr;
+			memset(sin, 0, sizeof(*sin));
+			sin->sin_family = AF_INET;
+			return sizeof(*sin);
 		}
 		if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
 			sin = (struct sockaddr_in *)uaddr;
@@ -501,9 +503,7 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_in *sin;
-	struct sockaddr_in6 *sin6;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
-	int addr_type;
 	int ret = 0;
 
 	lock_sock(sk);
@@ -528,7 +528,11 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 		rs->rs_conn_port = sin->sin_port;
 		break;
 
-	case AF_INET6:
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6: {
+		struct sockaddr_in6 *sin6;
+		int addr_type;
+
 		sin6 = (struct sockaddr_in6 *)uaddr;
 		if (addr_len < sizeof(struct sockaddr_in6)) {
 			ret = -EINVAL;
@@ -575,6 +579,8 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 		rs->rs_conn_addr = sin6->sin6_addr;
 		rs->rs_conn_port = sin6->sin6_port;
 		break;
+	}
+#endif
 
 	default:
 		ret = -EAFNOSUPPORT;
diff --git a/net/rds/bind.c b/net/rds/bind.c
index ba778760cbc2..3ab55784b637 100644
--- a/net/rds/bind.c
+++ b/net/rds/bind.c
@@ -165,7 +165,6 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	struct in6_addr v6addr, *binding_addr;
 	struct rds_transport *trans;
 	__u32 scope_id = 0;
-	int addr_type;
 	int ret = 0;
 	__be16 port;
 
@@ -183,8 +182,10 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &v6addr);
 		binding_addr = &v6addr;
 		port = sin->sin_port;
+#if IS_ENABLED(CONFIG_IPV6)
 	} else if (uaddr->sa_family == AF_INET6) {
 		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)uaddr;
+		int addr_type;
 
 		if (addr_len < sizeof(struct sockaddr_in6))
 			return -EINVAL;
@@ -212,6 +213,7 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		}
 		binding_addr = &sin6->sin6_addr;
 		port = sin6->sin6_port;
+#endif
 	} else {
 		return -EINVAL;
 	}
diff --git a/net/rds/connection.c b/net/rds/connection.c
index 051e35c1e7c6..3bd2f4a5a30d 100644
--- a/net/rds/connection.c
+++ b/net/rds/connection.c
@@ -63,8 +63,12 @@ static struct hlist_head *rds_conn_bucket(const struct in6_addr *laddr,
 	net_get_random_once(&rds6_hash_secret, sizeof(rds6_hash_secret));
 
 	lhash = (__force u32)laddr->s6_addr32[3];
+#if IS_ENABLED(CONFIG_IPV6)
 	fhash = __ipv6_addr_jhash(faddr, rds6_hash_secret);
-	hash = __inet6_ehashfn(lhash, 0, fhash, 0, rds_hash_secret);
+#else
+	fhash = (__force u32)faddr->s6_addr32[3];
+#endif
+	hash = __inet_ehashfn(lhash, 0, fhash, 0, rds_hash_secret);
 
 	return &rds_conn_hash[hash & RDS_CONNECTION_HASH_MASK];
 }
@@ -201,6 +205,8 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	conn->c_isv6 = !ipv6_addr_v4mapped(laddr);
 	conn->c_faddr = *faddr;
 	conn->c_dev_if = dev_if;
+
+#if IS_ENABLED(CONFIG_IPV6)
 	/* If the local address is link local, set c_bound_if to be the
 	 * index used for this connection.  Otherwise, set it to 0 as
 	 * the socket is not bound to an interface.  c_bound_if is used
@@ -209,6 +215,7 @@ static struct rds_connection *__rds_conn_create(struct net *net,
 	if (ipv6_addr_type(laddr) & IPV6_ADDR_LINKLOCAL)
 		conn->c_bound_if = dev_if;
 	else
+#endif
 		conn->c_bound_if = 0;
 
 	rds_conn_net_set(conn, net);
@@ -500,9 +507,11 @@ static void __rds_inc_msg_cp(struct rds_incoming *inc,
 			     struct rds_info_iterator *iter,
 			     void *saddr, void *daddr, int flip, bool isv6)
 {
+#if IS_ENABLED(CONFIG_IPV6)
 	if (isv6)
 		rds6_inc_info_copy(inc, iter, saddr, daddr, flip);
 	else
+#endif
 		rds_inc_info_copy(inc, iter, *(__be32 *)saddr,
 				  *(__be32 *)daddr, flip);
 }
@@ -581,6 +590,7 @@ static void rds_conn_message_info(struct socket *sock, unsigned int len,
 	rds_conn_message_info_cmn(sock, len, iter, lens, want_send, false);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static void rds6_conn_message_info(struct socket *sock, unsigned int len,
 				   struct rds_info_iterator *iter,
 				   struct rds_info_lengths *lens,
@@ -588,6 +598,7 @@ static void rds6_conn_message_info(struct socket *sock, unsigned int len,
 {
 	rds_conn_message_info_cmn(sock, len, iter, lens, want_send, true);
 }
+#endif
 
 static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
 				       struct rds_info_iterator *iter,
@@ -596,12 +607,14 @@ static void rds_conn_message_info_send(struct socket *sock, unsigned int len,
 	rds_conn_message_info(sock, len, iter, lens, 1);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static void rds6_conn_message_info_send(struct socket *sock, unsigned int len,
 					struct rds_info_iterator *iter,
 					struct rds_info_lengths *lens)
 {
 	rds6_conn_message_info(sock, len, iter, lens, 1);
 }
+#endif
 
 static void rds_conn_message_info_retrans(struct socket *sock,
 					  unsigned int len,
@@ -611,6 +624,7 @@ static void rds_conn_message_info_retrans(struct socket *sock,
 	rds_conn_message_info(sock, len, iter, lens, 0);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static void rds6_conn_message_info_retrans(struct socket *sock,
 					   unsigned int len,
 					   struct rds_info_iterator *iter,
@@ -618,6 +632,7 @@ static void rds6_conn_message_info_retrans(struct socket *sock,
 {
 	rds6_conn_message_info(sock, len, iter, lens, 0);
 }
+#endif
 
 void rds_for_each_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
@@ -734,6 +749,7 @@ static int rds_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 	return 1;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 {
 	struct rds6_info_connection *cinfo6 = buffer;
@@ -761,6 +777,7 @@ static int rds6_conn_info_visitor(struct rds_conn_path *cp, void *buffer)
 	 */
 	return 1;
 }
+#endif
 
 static void rds_conn_info(struct socket *sock, unsigned int len,
 			  struct rds_info_iterator *iter,
@@ -774,6 +791,7 @@ static void rds_conn_info(struct socket *sock, unsigned int len,
 				sizeof(struct rds_info_connection));
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 static void rds6_conn_info(struct socket *sock, unsigned int len,
 			   struct rds_info_iterator *iter,
 			   struct rds_info_lengths *lens)
@@ -785,6 +803,7 @@ static void rds6_conn_info(struct socket *sock, unsigned int len,
 				buffer,
 				sizeof(struct rds6_info_connection));
 }
+#endif
 
 int rds_conn_init(void)
 {
@@ -807,12 +826,13 @@ int rds_conn_init(void)
 			       rds_conn_message_info_send);
 	rds_info_register_func(RDS_INFO_RETRANS_MESSAGES,
 			       rds_conn_message_info_retrans);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds_info_register_func(RDS6_INFO_CONNECTIONS, rds6_conn_info);
 	rds_info_register_func(RDS6_INFO_SEND_MESSAGES,
 			       rds6_conn_message_info_send);
 	rds_info_register_func(RDS6_INFO_RETRANS_MESSAGES,
 			       rds6_conn_message_info_retrans);
-
+#endif
 	return 0;
 }
 
@@ -830,11 +850,13 @@ void rds_conn_exit(void)
 				 rds_conn_message_info_send);
 	rds_info_deregister_func(RDS_INFO_RETRANS_MESSAGES,
 				 rds_conn_message_info_retrans);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds_info_deregister_func(RDS6_INFO_CONNECTIONS, rds6_conn_info);
 	rds_info_deregister_func(RDS6_INFO_SEND_MESSAGES,
 				 rds6_conn_message_info_send);
 	rds_info_deregister_func(RDS6_INFO_RETRANS_MESSAGES,
 				 rds6_conn_message_info_retrans);
+#endif
 }
 
 /*
diff --git a/net/rds/ib.c b/net/rds/ib.c
index a4245c42d43b..89c6333ecd39 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -321,6 +321,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
 	return 1;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 /* IPv6 version of rds_ib_conn_info_visitor(). */
 static int rds6_ib_conn_info_visitor(struct rds_connection *conn,
 				     void *buffer)
@@ -357,6 +358,7 @@ static int rds6_ib_conn_info_visitor(struct rds_connection *conn,
 	}
 	return 1;
 }
+#endif
 
 static void rds_ib_ic_info(struct socket *sock, unsigned int len,
 			   struct rds_info_iterator *iter,
@@ -370,6 +372,7 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
 				sizeof(struct rds_info_rdma_connection));
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 /* IPv6 version of rds_ib_ic_info(). */
 static void rds6_ib_ic_info(struct socket *sock, unsigned int len,
 			    struct rds_info_iterator *iter,
@@ -382,6 +385,7 @@ static void rds6_ib_ic_info(struct socket *sock, unsigned int len,
 			       buffer,
 			       sizeof(struct rds6_info_rdma_connection));
 }
+#endif
 
 /*
  * Early RDS/IB was built to only bind to an address if there is an IPoIB
@@ -398,7 +402,9 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
 {
 	int ret;
 	struct rdma_cm_id *cm_id;
+#if IS_ENABLED(CONFIG_IPV6)
 	struct sockaddr_in6 sin6;
+#endif
 	struct sockaddr_in sin;
 	struct sockaddr *sa;
 	bool isv4;
@@ -418,6 +424,7 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
 		sin.sin_addr.s_addr = addr->s6_addr32[3];
 		sa = (struct sockaddr *)&sin;
 	} else {
+#if IS_ENABLED(CONFIG_IPV6)
 		memset(&sin6, 0, sizeof(sin6));
 		sin6.sin6_family = AF_INET6;
 		sin6.sin6_addr = *addr;
@@ -432,21 +439,30 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
 		if (ipv6_addr_type(addr) & IPV6_ADDR_LINKLOCAL) {
 			struct net_device *dev;
 
-			if (scope_id == 0)
-				return -EADDRNOTAVAIL;
+			if (scope_id == 0) {
+				ret = -EADDRNOTAVAIL;
+				goto out;
+			}
 
 			/* Use init_net for now as RDS is not network
 			 * name space aware.
 			 */
 			dev = dev_get_by_index(&init_net, scope_id);
-			if (!dev)
-				return -EADDRNOTAVAIL;
+			if (!dev) {
+				ret = -EADDRNOTAVAIL;
+				goto out;
+			}
 			if (!ipv6_chk_addr(&init_net, addr, dev, 1)) {
 				dev_put(dev);
-				return -EADDRNOTAVAIL;
+				ret = -EADDRNOTAVAIL;
+				goto out;
 			}
 			dev_put(dev);
 		}
+#else
+		ret = -EADDRNOTAVAIL;
+		goto out;
+#endif
 	}
 
 	/* rdma_bind_addr will only succeed for IB & iWARP devices */
@@ -461,6 +477,7 @@ static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
 		 addr, scope_id, ret,
 		 cm_id->device ? cm_id->device->node_type : -1);
 
+out:
 	rdma_destroy_id(cm_id);
 
 	return ret;
@@ -491,7 +508,9 @@ void rds_ib_exit(void)
 	rds_ib_set_unloading();
 	synchronize_rcu();
 	rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds_info_deregister_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info);
+#endif
 	rds_ib_unregister_client();
 	rds_ib_destroy_nodev_conns();
 	rds_ib_sysctl_exit();
@@ -553,7 +572,9 @@ int rds_ib_init(void)
 	rds_trans_register(&rds_ib_transport);
 
 	rds_info_register_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds_info_register_func(RDS6_INFO_IB_CONNECTIONS, rds6_ib_ic_info);
+#endif
 
 	goto out;
 
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 0d654d99fe41..bfbb31f0c7fd 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -678,6 +678,7 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
 	return version;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 /* Given an IPv6 address, find the net_device which hosts that address and
  * return its index.  This is used by the rds_ib_cm_handle_connect() code to
  * find the interface index of where an incoming request comes from when
@@ -704,6 +705,7 @@ static u32 __rds_find_ifindex(struct net *net, const struct in6_addr *addr)
 
 	return idx;
 }
+#endif
 
 int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 			     struct rdma_cm_event *event, bool isv6)
@@ -732,6 +734,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 
 	dp = event->param.conn.private_data;
 	if (isv6) {
+#if IS_ENABLED(CONFIG_IPV6)
 		dp_cmn = &dp->ricp_v6.dp_cmn;
 		saddr6 = &dp->ricp_v6.dp_saddr;
 		daddr6 = &dp->ricp_v6.dp_daddr;
@@ -756,6 +759,10 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 				goto out;
 			}
 		}
+#else
+		err = -EOPNOTSUPP;
+		goto out;
+#endif
 	} else {
 		dp_cmn = &dp->ricp_v4.dp_cmn;
 		ipv6_addr_set_v4mapped(dp->ricp_v4.dp_saddr, &s_mapped_addr);
@@ -893,9 +900,11 @@ int rds_ib_conn_path_connect(struct rds_conn_path *cp)
 
 	/* XXX I wonder what affect the port space has */
 	/* delegate cm event handler to rdma_transport */
+#if IS_ENABLED(CONFIG_IPV6)
 	if (conn->c_isv6)
 		handler = rds6_rdma_cm_event_handler;
 	else
+#endif
 		handler = rds_rdma_cm_event_handler;
 	ic->i_cm_id = rdma_create_id(&init_net, handler, conn,
 				     RDMA_PS_TCP, IB_QPT_RC);
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index e3c8bbbdb43f..99ccafb90410 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -180,6 +180,7 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_co
 	iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages;
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
 			 struct rds6_info_rdma_connection *iinfo6)
 {
@@ -188,6 +189,7 @@ void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
 	iinfo6->rdma_mr_max = pool_1m->max_items;
 	iinfo6->rdma_mr_size = pool_1m->fmr_attr.max_pages;
 }
+#endif
 
 struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
 {
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index ad78929036ef..6b0f57c83a2a 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -39,7 +39,9 @@
 
 /* Global IPv4 and IPv6 RDS RDMA listener cm_id */
 static struct rdma_cm_id *rds_rdma_listen_id;
+#if IS_ENABLED(CONFIG_IPV6)
 static struct rdma_cm_id *rds6_rdma_listen_id;
+#endif
 
 static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 					 struct rdma_cm_event *event,
@@ -155,11 +157,13 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 	return rds_rdma_cm_event_handler_cmn(cm_id, event, false);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 			       struct rdma_cm_event *event)
 {
 	return rds_rdma_cm_event_handler_cmn(cm_id, event, true);
 }
+#endif
 
 static int rds_rdma_listen_init_common(rdma_cm_event_handler handler,
 				       struct sockaddr *sa,
@@ -214,7 +218,9 @@ out:
 static int rds_rdma_listen_init(void)
 {
 	int ret;
+#if IS_ENABLED(CONFIG_IPV6)
 	struct sockaddr_in6 sin6;
+#endif
 	struct sockaddr_in sin;
 
 	sin.sin_family = PF_INET;
@@ -226,6 +232,7 @@ static int rds_rdma_listen_init(void)
 	if (ret != 0)
 		return ret;
 
+#if IS_ENABLED(CONFIG_IPV6)
 	sin6.sin6_family = PF_INET6;
 	sin6.sin6_addr = in6addr_any;
 	sin6.sin6_port = htons(RDS_CM_PORT);
@@ -237,6 +244,7 @@ static int rds_rdma_listen_init(void)
 	/* Keep going even when IPv6 is not enabled in the system. */
 	if (ret != 0)
 		rdsdebug("Cannot set up IPv6 RDMA listener\n");
+#endif
 	return 0;
 }
 
@@ -247,11 +255,13 @@ static void rds_rdma_listen_stop(void)
 		rdma_destroy_id(rds_rdma_listen_id);
 		rds_rdma_listen_id = NULL;
 	}
+#if IS_ENABLED(CONFIG_IPV6)
 	if (rds6_rdma_listen_id) {
 		rdsdebug("cm %p\n", rds6_rdma_listen_id);
 		rdma_destroy_id(rds6_rdma_listen_id);
 		rds6_rdma_listen_id = NULL;
 	}
+#endif
 }
 
 static int rds_rdma_init(void)
diff --git a/net/rds/recv.c b/net/rds/recv.c
index 03cd8df54c26..504cd6bcc54c 100644
--- a/net/rds/recv.c
+++ b/net/rds/recv.c
@@ -793,6 +793,7 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 void rds6_inc_info_copy(struct rds_incoming *inc,
 			struct rds_info_iterator *iter,
 			struct in6_addr *saddr, struct in6_addr *daddr,
@@ -817,3 +818,4 @@ void rds6_inc_info_copy(struct rds_incoming *inc,
 
 	rds_info_copy(iter, &minfo6, sizeof(minfo6));
 }
+#endif
diff --git a/net/rds/send.c b/net/rds/send.c
index 18e2b4d3931f..36a5dba56a43 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1103,6 +1103,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			dport = usin->sin_port;
 			break;
 
+#if IS_ENABLED(CONFIG_IPV6)
 		case AF_INET6: {
 			int addr_type;
 
@@ -1142,6 +1143,7 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			dport = sin6->sin6_port;
 			break;
 		}
+#endif
 
 		default:
 			ret = -EINVAL;
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index f23925af0b8d..2c7b7c352d3e 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -51,7 +51,9 @@ static LIST_HEAD(rds_tcp_tc_list);
  * rds6_tcp_tc_count counts both IPv4 and IPv6 connections.
  */
 static unsigned int rds_tcp_tc_count;
+#if IS_ENABLED(CONFIG_IPV6)
 static unsigned int rds6_tcp_tc_count;
+#endif
 
 /* Track rds_tcp_connection structs so they can be cleaned up */
 static DEFINE_SPINLOCK(rds_tcp_conn_lock);
@@ -118,7 +120,9 @@ void rds_tcp_restore_callbacks(struct socket *sock,
 	/* done under the callback_lock to serialize with write_space */
 	spin_lock(&rds_tcp_tc_list_lock);
 	list_del_init(&tc->t_list_item);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds6_tcp_tc_count--;
+#endif
 	if (!tc->t_cpath->cp_conn->c_isv6)
 		rds_tcp_tc_count--;
 	spin_unlock(&rds_tcp_tc_list_lock);
@@ -207,7 +211,9 @@ void rds_tcp_set_callbacks(struct socket *sock, struct rds_conn_path *cp)
 	/* done under the callback_lock to serialize with write_space */
 	spin_lock(&rds_tcp_tc_list_lock);
 	list_add_tail(&tc->t_list_item, &rds_tcp_tc_list);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds6_tcp_tc_count++;
+#endif
 	if (!tc->t_cpath->cp_conn->c_isv6)
 		rds_tcp_tc_count++;
 	spin_unlock(&rds_tcp_tc_list_lock);
@@ -273,6 +279,7 @@ out:
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
 
+#if IS_ENABLED(CONFIG_IPV6)
 /* Handle RDS6_INFO_TCP_SOCKETS socket option. It returns both IPv4 and
  * IPv6 connections. IPv4 connection address is returned in an IPv4 mapped
  * address.
@@ -314,12 +321,15 @@ out:
 
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
+#endif
 
 static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
 			       __u32 scope_id)
 {
 	struct net_device *dev = NULL;
+#if IS_ENABLED(CONFIG_IPV6)
 	int ret;
+#endif
 
 	if (ipv6_addr_v4mapped(addr)) {
 		if (inet_addr_type(net, addr->s6_addr32[3]) == RTN_LOCAL)
@@ -340,9 +350,11 @@ static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
 		}
 		rcu_read_unlock();
 	}
+#if IS_ENABLED(CONFIG_IPV6)
 	ret = ipv6_chk_addr(net, addr, dev, 0);
 	if (ret)
 		return 0;
+#endif
 	return -EADDRNOTAVAIL;
 }
 
@@ -545,18 +557,27 @@ static __net_init int rds_tcp_init_net(struct net *net)
 		err = -ENOMEM;
 		goto fail;
 	}
+
+#if IS_ENABLED(CONFIG_IPV6)
 	rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, true);
+#else
+	rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, false);
+#endif
 	if (!rtn->rds_tcp_listen_sock) {
 		pr_warn("could not set up IPv6 listen sock\n");
 
+#if IS_ENABLED(CONFIG_IPV6)
 		/* Try IPv4 as some systems disable IPv6 */
 		rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net, false);
 		if (!rtn->rds_tcp_listen_sock) {
+#endif
 			unregister_net_sysctl_table(rtn->rds_tcp_sysctl);
 			rtn->rds_tcp_sysctl = NULL;
 			err = -EAFNOSUPPORT;
 			goto fail;
+#if IS_ENABLED(CONFIG_IPV6)
 		}
+#endif
 	}
 	INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker);
 	return 0;
@@ -670,7 +691,9 @@ static void rds_tcp_exit(void)
 	rds_tcp_set_unloading();
 	synchronize_rcu();
 	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds_info_deregister_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info);
+#endif
 	unregister_pernet_device(&rds_tcp_net_ops);
 	rds_tcp_destroy_conns();
 	rds_trans_unregister(&rds_tcp_transport);
@@ -702,7 +725,9 @@ static int rds_tcp_init(void)
 	rds_trans_register(&rds_tcp_transport);
 
 	rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+#if IS_ENABLED(CONFIG_IPV6)
 	rds_info_register_func(RDS6_INFO_TCP_SOCKETS, rds6_tcp_tc_info);
+#endif
 
 	goto out;
 out_recv:
diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 0cf0147117d8..c12203f646da 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -132,7 +132,10 @@ int rds_tcp_accept_one(struct socket *sock)
 	int conn_state;
 	struct rds_conn_path *cp;
 	struct in6_addr *my_addr, *peer_addr;
-	int dev_if;
+#if !IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr saddr, daddr;
+#endif
+	int dev_if = 0;
 
 	if (!sock) /* module unload or netns delete in progress */
 		return -ENETUNREACH;
@@ -165,12 +168,21 @@ int rds_tcp_accept_one(struct socket *sock)
 
 	inet = inet_sk(new_sock->sk);
 
+#if IS_ENABLED(CONFIG_IPV6)
 	my_addr = &new_sock->sk->sk_v6_rcv_saddr;
 	peer_addr = &new_sock->sk->sk_v6_daddr;
-	rdsdebug("accepted tcp %pI6c:%u -> %pI6c:%u\n",
+#else
+	ipv6_addr_set_v4mapped(inet->inet_saddr, &saddr);
+	ipv6_addr_set_v4mapped(inet->inet_daddr, &daddr);
+	my_addr = &saddr;
+	peer_addr = &daddr;
+#endif
+	rdsdebug("accepted family %d tcp %pI6c:%u -> %pI6c:%u\n",
+		 sock->sk->sk_family,
 		 my_addr, ntohs(inet->inet_sport),
 		 peer_addr, ntohs(inet->inet_dport));
 
+#if IS_ENABLED(CONFIG_IPV6)
 	/* sk_bound_dev_if is not set if the peer address is not link local
 	 * address.  In this case, it happens that mcast_oif is set.  So
 	 * just use it.
@@ -184,9 +196,10 @@ int rds_tcp_accept_one(struct socket *sock)
 	} else {
 		dev_if = new_sock->sk->sk_bound_dev_if;
 	}
+#endif
+
 	conn = rds_conn_create(sock_net(sock->sk),
-			       &new_sock->sk->sk_v6_rcv_saddr,
-			       &new_sock->sk->sk_v6_daddr,
+			       my_addr, peer_addr,
 			       &rds_tcp_transport, GFP_KERNEL, dev_if);
 
 	if (IS_ERR(conn)) {
-- 
cgit v1.2.3


From 7d95178c77014dbd8dce36ee40bbbc5e6c121ff5 Mon Sep 17 00:00:00 2001
From: Theodore Ts'o <tytso@mit.edu>
Date: Wed, 1 Aug 2018 12:36:52 -0400
Subject: ext4: check for NUL characters in extended attribute's name

Extended attribute names are defined to be NUL-terminated, so the name
must not contain a NUL character.  This is important because there are
places when remove extended attribute, the code uses strlen to
determine the length of the entry.  That should probably be fixed at
some point, but code is currently really messy, so the simplest fix
for now is to simply validate that the extended attributes are sane.

https://bugzilla.kernel.org/show_bug.cgi?id=200401

Reported-by: Wen Xu <wen.xu@gatech.edu>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/xattr.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 723df14f4084..f36fc5d5b257 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -190,6 +190,8 @@ ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
 		struct ext4_xattr_entry *next = EXT4_XATTR_NEXT(e);
 		if ((void *)next >= end)
 			return -EFSCORRUPTED;
+		if (strnlen(e->e_name, e->e_name_len) != e->e_name_len)
+			return -EFSCORRUPTED;
 		e = next;
 	}
 
-- 
cgit v1.2.3


From bf774d141a33ea13e8cd11034ada395d3f23ef51 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 31 Jul 2018 22:12:30 +0800
Subject: qed: Make some functions static

Fixes the following sparse warning:

drivers/net/ethernet/qlogic/qed/qed_cxt.c:1534:6: warning: symbol 'qed_cm_init_pf' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_dev.c:233:4: warning: symbol 'qed_init_qm_get_num_tcs' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_dev.c:238:5: warning: symbol 'qed_init_qm_get_num_vfs' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_dev.c:246:5: warning: symbol 'qed_init_qm_get_num_pf_rls' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_dev.c:264:5: warning: symbol 'qed_init_qm_get_num_vports' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_dev.c:276:5: warning: symbol 'qed_init_qm_get_num_pqs' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_mcp.c:573:5: warning: symbol 'qed_mcp_nvm_wr_cmd' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_mcp.c:3012:1: warning: symbol '__qed_mcp_resc_lock' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_dcbx.c:870:6: warning: symbol 'qed_dcbx_aen' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_debug.c:7841:5: warning: symbol 'qed_dbg_nvm_image_length' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_debug.c:7857:5: warning: symbol 'qed_dbg_nvm_image' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_sriov.c:675:6: warning: symbol '_qed_iov_pf_sanity_check' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_sriov.c:690:6: warning: symbol 'qed_iov_pf_sanity_check' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_sriov.c:3982:6: warning: symbol 'qed_iov_pf_get_pending_events' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_vf.c:172:5: warning: symbol '_qed_vf_pf_release' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_rdma.c:137:5: warning: symbol 'qed_rdma_get_sb_id' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_rdma.c:709:5: warning: symbol 'qed_rdma_stop' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_ll2.c:161:6: warning: symbol 'qed_ll2b_complete_rx_packet' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_roce.c:160:6: warning: symbol 'qed_roce_free_cid_pair' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:380:12: warning: symbol 'iwarp_state_names' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:946:1: warning: symbol 'qed_iwarp_parse_private_data' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:971:1: warning: symbol 'qed_iwarp_mpa_reply_arrived' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:2504:1: warning: symbol 'qed_iwarp_ll2_slowpath' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:2806:6: warning: symbol 'qed_iwarp_qp_in_error' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:2827:6: warning: symbol 'qed_iwarp_exception_received' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iwarp.c:2958:1: warning: symbol 'qed_iwarp_connect_complete' was not declared. Should it be static?
drivers/net/ethernet/qlogic/qed/qed_iscsi.c:876:6: warning: symbol 'qed_iscsi_free_connection' was not declared. Should it be static?

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Denis Bolotin <Denis.Bolotin@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_cxt.c   |  2 +-
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c  |  2 +-
 drivers/net/ethernet/qlogic/qed/qed_debug.c |  9 +++++----
 drivers/net/ethernet/qlogic/qed/qed_dev.c   | 10 +++++-----
 drivers/net/ethernet/qlogic/qed/qed_iscsi.c |  4 ++--
 drivers/net/ethernet/qlogic/qed/qed_iwarp.c | 20 +++++++++++---------
 drivers/net/ethernet/qlogic/qed/qed_ll2.c   |  3 ++-
 drivers/net/ethernet/qlogic/qed/qed_mcp.c   | 15 ++++++++-------
 drivers/net/ethernet/qlogic/qed/qed_rdma.c  |  4 ++--
 drivers/net/ethernet/qlogic/qed/qed_roce.c  |  2 +-
 drivers/net/ethernet/qlogic/qed/qed_sriov.c |  8 ++++----
 drivers/net/ethernet/qlogic/qed/qed_vf.c    |  2 +-
 12 files changed, 43 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_cxt.c b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
index b5b5ff725426..f1977aa440e5 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_cxt.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_cxt.c
@@ -1531,7 +1531,7 @@ void qed_qm_init_pf(struct qed_hwfn *p_hwfn,
 }
 
 /* CM PF */
-void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
+static void qed_cm_init_pf(struct qed_hwfn *p_hwfn)
 {
 	/* XCM pure-LB queue */
 	STORE_RT_REG(p_hwfn, XCM_REG_CON_PHY_Q3_RT_OFFSET,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 12b4c2ab5796..d02e774c8d66 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -867,7 +867,7 @@ static int qed_dcbx_read_mib(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-void qed_dcbx_aen(struct qed_hwfn *hwfn, u32 mib_type)
+static void qed_dcbx_aen(struct qed_hwfn *hwfn, u32 mib_type)
 {
 	struct qed_common_cb_ops *op = hwfn->cdev->protocol_ops.common;
 	void *cookie = hwfn->cdev->ops_cookie;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 4340c4c90bcb..1aa9fc1c5890 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -7838,8 +7838,8 @@ int qed_dbg_igu_fifo_size(struct qed_dev *cdev)
 	return qed_dbg_feature_size(cdev, DBG_FEATURE_IGU_FIFO);
 }
 
-int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn,
-			     enum qed_nvm_images image_id, u32 *length)
+static int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn,
+				    enum qed_nvm_images image_id, u32 *length)
 {
 	struct qed_nvm_image_att image_att;
 	int rc;
@@ -7854,8 +7854,9 @@ int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
-		      u32 *num_dumped_bytes, enum qed_nvm_images image_id)
+static int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer,
+			     u32 *num_dumped_bytes,
+			     enum qed_nvm_images image_id)
 {
 	struct qed_hwfn *p_hwfn =
 		&cdev->hwfns[cdev->dbg_params.engine_for_debug];
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 37817b3e8fa3..6a0b46f214f4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -230,12 +230,12 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 }
 
 /* Getters for resource amounts necessary for qm initialization */
-u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn)
+static u8 qed_init_qm_get_num_tcs(struct qed_hwfn *p_hwfn)
 {
 	return p_hwfn->hw_info.num_hw_tc;
 }
 
-u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
 {
 	return IS_QED_SRIOV(p_hwfn->cdev) ?
 	       p_hwfn->cdev->p_iov_info->total_vfs : 0;
@@ -243,7 +243,7 @@ u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
 
 #define NUM_DEFAULT_RLS 1
 
-u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
 {
 	u16 num_pf_rls, num_vfs = qed_init_qm_get_num_vfs(p_hwfn);
 
@@ -261,7 +261,7 @@ u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
 	return num_pf_rls;
 }
 
-u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
 {
 	u32 pq_flags = qed_get_pq_flags(p_hwfn);
 
@@ -273,7 +273,7 @@ u16 qed_init_qm_get_num_vports(struct qed_hwfn *p_hwfn)
 }
 
 /* calc amount of PQs according to the requested flags */
-u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
+static u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
 {
 	u32 pq_flags = qed_get_pq_flags(p_hwfn);
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
index c0d4a54a5edb..1135387bd99d 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iscsi.c
@@ -873,8 +873,8 @@ static void qed_iscsi_release_connection(struct qed_hwfn *p_hwfn,
 	spin_unlock_bh(&p_hwfn->p_iscsi_info->lock);
 }
 
-void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn,
-			       struct qed_iscsi_conn *p_conn)
+static void qed_iscsi_free_connection(struct qed_hwfn *p_hwfn,
+				      struct qed_iscsi_conn *p_conn)
 {
 	qed_chain_free(p_hwfn->cdev, &p_conn->xhq);
 	qed_chain_free(p_hwfn->cdev, &p_conn->uhq);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
index 90a2b53096e2..17f3dfa2cc94 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c
@@ -377,7 +377,7 @@ qed_iwarp2roce_state(enum qed_iwarp_qp_state state)
 	}
 }
 
-const char *iwarp_state_names[] = {
+const static char *iwarp_state_names[] = {
 	"IDLE",
 	"RTS",
 	"TERMINATE",
@@ -942,7 +942,7 @@ qed_iwarp_return_ep(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->iwarp.iw_lock);
 }
 
-void
+static void
 qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 {
 	struct mpa_v2_hdr *mpa_v2_params;
@@ -967,7 +967,7 @@ qed_iwarp_parse_private_data(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 				       mpa_data_size;
 }
 
-void
+static void
 qed_iwarp_mpa_reply_arrived(struct qed_hwfn *p_hwfn, struct qed_iwarp_ep *ep)
 {
 	struct qed_iwarp_cm_event_params params;
@@ -2500,7 +2500,7 @@ static void qed_iwarp_ll2_rel_tx_pkt(void *cxt, u8 connection_handle,
 /* The only slowpath for iwarp ll2 is unalign flush. When this completion
  * is received, need to reset the FPDU.
  */
-void
+static void
 qed_iwarp_ll2_slowpath(void *cxt,
 		       u8 connection_handle,
 		       u32 opaque_data_0, u32 opaque_data_1)
@@ -2803,8 +2803,9 @@ int qed_iwarp_stop(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 	return qed_iwarp_ll2_stop(p_hwfn, p_ptt);
 }
 
-void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
-			   struct qed_iwarp_ep *ep, u8 fw_return_code)
+static void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
+				  struct qed_iwarp_ep *ep,
+				  u8 fw_return_code)
 {
 	struct qed_iwarp_cm_event_params params;
 
@@ -2824,8 +2825,9 @@ void qed_iwarp_qp_in_error(struct qed_hwfn *p_hwfn,
 	ep->event_cb(ep->cb_context, &params);
 }
 
-void qed_iwarp_exception_received(struct qed_hwfn *p_hwfn,
-				  struct qed_iwarp_ep *ep, int fw_ret_code)
+static void qed_iwarp_exception_received(struct qed_hwfn *p_hwfn,
+					 struct qed_iwarp_ep *ep,
+					 int fw_ret_code)
 {
 	struct qed_iwarp_cm_event_params params;
 	bool event_cb = false;
@@ -2954,7 +2956,7 @@ qed_iwarp_tcp_connect_unsuccessful(struct qed_hwfn *p_hwfn,
 	}
 }
 
-void
+static void
 qed_iwarp_connect_complete(struct qed_hwfn *p_hwfn,
 			   struct qed_iwarp_ep *ep, u8 fw_return_code)
 {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
index 012973d75ad0..14ac9cab2653 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c
@@ -158,7 +158,8 @@ static void qed_ll2_kill_buffers(struct qed_dev *cdev)
 		qed_ll2_dealloc_buffer(cdev, buffer);
 }
 
-void qed_ll2b_complete_rx_packet(void *cxt, struct qed_ll2_comp_rx_data *data)
+static void qed_ll2b_complete_rx_packet(void *cxt,
+					struct qed_ll2_comp_rx_data *data)
 {
 	struct qed_hwfn *p_hwfn = cxt;
 	struct qed_ll2_buffer *buffer = data->cookie;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 96a67efac308..8e4f60e4520a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -570,12 +570,13 @@ int qed_mcp_cmd(struct qed_hwfn *p_hwfn,
 	return 0;
 }
 
-int qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn,
-		       struct qed_ptt *p_ptt,
-		       u32 cmd,
-		       u32 param,
-		       u32 *o_mcp_resp,
-		       u32 *o_mcp_param, u32 i_txn_size, u32 *i_buf)
+static int
+qed_mcp_nvm_wr_cmd(struct qed_hwfn *p_hwfn,
+		   struct qed_ptt *p_ptt,
+		   u32 cmd,
+		   u32 param,
+		   u32 *o_mcp_resp,
+		   u32 *o_mcp_param, u32 i_txn_size, u32 *i_buf)
 {
 	struct qed_mcp_mb_params mb_params;
 	int rc;
@@ -3008,7 +3009,7 @@ static int qed_mcp_resource_cmd(struct qed_hwfn *p_hwfn,
 	return rc;
 }
 
-int
+static int
 __qed_mcp_resc_lock(struct qed_hwfn *p_hwfn,
 		    struct qed_ptt *p_ptt,
 		    struct qed_resc_lock_params *p_params)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_rdma.c b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
index 101d677114f2..be941cfaa2d4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_rdma.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_rdma.c
@@ -134,7 +134,7 @@ static bool qed_bmap_is_empty(struct qed_bmap *bmap)
 	return bmap->max_count == find_first_bit(bmap->bitmap, bmap->max_count);
 }
 
-u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
+static u32 qed_rdma_get_sb_id(void *p_hwfn, u32 rel_sb_id)
 {
 	/* First sb id for RoCE is after all the l2 sb */
 	return FEAT_NUM((struct qed_hwfn *)p_hwfn, QED_PF_L2_QUE) + rel_sb_id;
@@ -706,7 +706,7 @@ static int qed_rdma_setup(struct qed_hwfn *p_hwfn,
 	return qed_rdma_start_fw(p_hwfn, params, p_ptt);
 }
 
-int qed_rdma_stop(void *rdma_cxt)
+static int qed_rdma_stop(void *rdma_cxt)
 {
 	struct qed_hwfn *p_hwfn = (struct qed_hwfn *)rdma_cxt;
 	struct rdma_close_func_ramrod_data *p_ramrod;
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index b5ce1581645f..ada4c1810864 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -157,7 +157,7 @@ static enum roce_flavor qed_roce_mode_to_flavor(enum roce_mode roce_mode)
 	return flavor;
 }
 
-void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
+static void qed_roce_free_cid_pair(struct qed_hwfn *p_hwfn, u16 cid)
 {
 	spin_lock_bh(&p_hwfn->p_rdma_info->lock);
 	qed_bmap_release_id(p_hwfn, &p_hwfn->p_rdma_info->cid_map, cid);
diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index 26e918d7f2f9..9b08a9d9e151 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -672,8 +672,8 @@ int qed_iov_hw_info(struct qed_hwfn *p_hwfn)
 	return 0;
 }
 
-bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn,
-			      int vfid, bool b_fail_malicious)
+static bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn,
+				     int vfid, bool b_fail_malicious)
 {
 	/* Check PF supports sriov */
 	if (IS_VF(p_hwfn->cdev) || !IS_QED_SRIOV(p_hwfn->cdev) ||
@@ -687,7 +687,7 @@ bool _qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn,
 	return true;
 }
 
-bool qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, int vfid)
+static bool qed_iov_pf_sanity_check(struct qed_hwfn *p_hwfn, int vfid)
 {
 	return _qed_iov_pf_sanity_check(p_hwfn, vfid, true);
 }
@@ -3979,7 +3979,7 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn,
 	}
 }
 
-void qed_iov_pf_get_pending_events(struct qed_hwfn *p_hwfn, u64 *events)
+static void qed_iov_pf_get_pending_events(struct qed_hwfn *p_hwfn, u64 *events)
 {
 	int i;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c
index be6ddde1a104..3d4269659820 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_vf.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c
@@ -169,7 +169,7 @@ static void qed_vf_pf_add_qid(struct qed_hwfn *p_hwfn,
 	p_qid_tlv->qid = p_cid->qid_usage_idx;
 }
 
-int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final)
+static int _qed_vf_pf_release(struct qed_hwfn *p_hwfn, bool b_final)
 {
 	struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info;
 	struct pfvf_def_resp_tlv *resp;
-- 
cgit v1.2.3


From 96d395020e87607b3454edc2f49a03ddcfbef986 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 31 Jul 2018 09:21:57 -0500
Subject: net/mlx5e: Fix uninitialized variable

There is a potential execution path in which variable *err* is returned
without being properly initialized previously.

Fix this by initializing variable *err* to 0.

Addresses-Coverity-ID: 1472116 ("Uninitialized scalar variable")
Fixes: 0ec13877ce95 ("net/mlx5e: Gather all XDP pre-requisite checks in a single function")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Tariq Toukan <tariqt@mellanox.com>
Acked-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index fde35021a257..de2827ad0e67 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4215,7 +4215,7 @@ static int mlx5e_xdp_set(struct net_device *netdev, struct bpf_prog *prog)
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	struct bpf_prog *old_prog;
 	bool reset, was_opened;
-	int err;
+	int err = 0;
 	int i;
 
 	mutex_lock(&priv->state_lock);
-- 
cgit v1.2.3


From 7bee9bd21b404a2fa76c1a8e0ff68379aeef2b91 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@mellanox.com>
Date: Mon, 25 Jun 2018 16:44:30 -0600
Subject: clang-format: Set IndentWrappedFunctionNames false

The true option causes this indenting for functions:

static struct something_very_very_long *
    function(void *arg)
{

While a quick survey suggests that the usual Linux fallback is the GNU
style:

static struct something_very_very_long *
function(void *arg)
{

Eg as seen in:

kernel/cpu.c
kernel/fork.c
etc

Acked-by: Joe Perches <joe@perches.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
---
 .clang-format | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.clang-format b/.clang-format
index faffc0d5af4e..1d5da22e0ba5 100644
--- a/.clang-format
+++ b/.clang-format
@@ -382,7 +382,7 @@ IncludeIsMainRegex: '(Test)?$'
 IndentCaseLabels: false
 #IndentPPDirectives: None # Unknown to clang-format-5.0
 IndentWidth: 8
-IndentWrappedFunctionNames: true
+IndentWrappedFunctionNames: false
 JavaScriptQuotes: Leave
 JavaScriptWrapImports: true
 KeepEmptyLinesAtTheStartOfBlocks: false
-- 
cgit v1.2.3


From c1b3bdb2ffa9a343ded117e01d6b4b43b9df53f8 Mon Sep 17 00:00:00 2001
From: Suresh Reddy <suresh.reddy@broadcom.com>
Date: Tue, 31 Jul 2018 11:39:42 -0400
Subject: be2net: gather debug info and reset adapter (only for Lancer) on a
 tx-timeout

This patch handles a TX-timeout as follows:

1) This patch gathers and prints the following info that can
   help in diagnosing the cause of a TX-timeout.
   a) TX queue and completion queue entries.
   b) SKB and TCP/UDP header details.

2) For Lancer NICs (TX-timeout recovery is not supported for
   BE3/Skyhawk-R NICs), it recovers from the TX timeout as follows:

   a) On a TX-timeout, driver sets the PHYSDEV_CONTROL_FW_RESET_MASK
      bit in the PHYSDEV_CONTROL register. Lancer firmware goes into
      an error state and indicates this back to the driver via a bit
      in a doorbell register.
   b) Driver detects this and calls be_err_recover(). DMA is disabled,
      all pending TX skbs are unmapped and freed (be_close()). All rings
      are destroyed (be_clear()).
   c) The driver waits for the FW to re-initialize and re-creates all
      rings along with other data structs (be_resume())

Signed-off-by: Suresh Reddy <suresh.reddy@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 80 ++++++++++++++++++++++++++++-
 1 file changed, 79 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 05e4c0bb25f4..580cdec2d2ce 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1412,6 +1412,83 @@ drop:
 	return NETDEV_TX_OK;
 }
 
+static void be_tx_timeout(struct net_device *netdev)
+{
+	struct be_adapter *adapter = netdev_priv(netdev);
+	struct device *dev = &adapter->pdev->dev;
+	struct be_tx_obj *txo;
+	struct sk_buff *skb;
+	struct tcphdr *tcphdr;
+	struct udphdr *udphdr;
+	u32 *entry;
+	int status;
+	int i, j;
+
+	for_all_tx_queues(adapter, txo, i) {
+		dev_info(dev, "TXQ Dump: %d H: %d T: %d used: %d, qid: 0x%x\n",
+			 i, txo->q.head, txo->q.tail,
+			 atomic_read(&txo->q.used), txo->q.id);
+
+		entry = txo->q.dma_mem.va;
+		for (j = 0; j < TX_Q_LEN * 4; j += 4) {
+			if (entry[j] != 0 || entry[j + 1] != 0 ||
+			    entry[j + 2] != 0 || entry[j + 3] != 0) {
+				dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n",
+					 j, entry[j], entry[j + 1],
+					 entry[j + 2], entry[j + 3]);
+			}
+		}
+
+		entry = txo->cq.dma_mem.va;
+		dev_info(dev, "TXCQ Dump: %d  H: %d T: %d used: %d\n",
+			 i, txo->cq.head, txo->cq.tail,
+			 atomic_read(&txo->cq.used));
+		for (j = 0; j < TX_CQ_LEN * 4; j += 4) {
+			if (entry[j] != 0 || entry[j + 1] != 0 ||
+			    entry[j + 2] != 0 || entry[j + 3] != 0) {
+				dev_info(dev, "Entry %d 0x%x 0x%x 0x%x 0x%x\n",
+					 j, entry[j], entry[j + 1],
+					 entry[j + 2], entry[j + 3]);
+			}
+		}
+
+		for (j = 0; j < TX_Q_LEN; j++) {
+			if (txo->sent_skb_list[j]) {
+				skb = txo->sent_skb_list[j];
+				if (ip_hdr(skb)->protocol == IPPROTO_TCP) {
+					tcphdr = tcp_hdr(skb);
+					dev_info(dev, "TCP source port %d\n",
+						 ntohs(tcphdr->source));
+					dev_info(dev, "TCP dest port %d\n",
+						 ntohs(tcphdr->dest));
+					dev_info(dev, "TCP seqence num %d\n",
+						 ntohs(tcphdr->seq));
+					dev_info(dev, "TCP ack_seq %d\n",
+						 ntohs(tcphdr->ack_seq));
+				} else if (ip_hdr(skb)->protocol ==
+					   IPPROTO_UDP) {
+					udphdr = udp_hdr(skb);
+					dev_info(dev, "UDP source port %d\n",
+						 ntohs(udphdr->source));
+					dev_info(dev, "UDP dest port %d\n",
+						 ntohs(udphdr->dest));
+				}
+				dev_info(dev, "skb[%d] %p len %d proto 0x%x\n",
+					 j, skb, skb->len, skb->protocol);
+			}
+		}
+	}
+
+	if (lancer_chip(adapter)) {
+		dev_info(dev, "Initiating reset due to tx timeout\n");
+		dev_info(dev, "Resetting adapter\n");
+		status = lancer_physdev_ctrl(adapter,
+					     PHYSDEV_CONTROL_FW_RESET_MASK);
+		if (status)
+			dev_err(dev, "Reset failed .. Reboot server\n");
+	}
+}
+
 static inline bool be_in_all_promisc(struct be_adapter *adapter)
 {
 	return (adapter->if_flags & BE_IF_FLAGS_ALL_PROMISCUOUS) ==
@@ -3274,7 +3351,7 @@ void be_detect_error(struct be_adapter *adapter)
 			/* Do not log error messages if its a FW reset */
 			if (sliport_err1 == SLIPORT_ERROR_FW_RESET1 &&
 			    sliport_err2 == SLIPORT_ERROR_FW_RESET2) {
-				dev_info(dev, "Firmware update in progress\n");
+				dev_info(dev, "Reset is in progress\n");
 			} else {
 				dev_err(dev, "Error detected in the card\n");
 				dev_err(dev, "ERR: sliport status 0x%x\n",
@@ -5218,6 +5295,7 @@ static const struct net_device_ops be_netdev_ops = {
 	.ndo_get_vf_config	= be_get_vf_config,
 	.ndo_set_vf_link_state  = be_set_vf_link_state,
 	.ndo_set_vf_spoofchk    = be_set_vf_spoofchk,
+	.ndo_tx_timeout		= be_tx_timeout,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller	= be_netpoll,
 #endif
-- 
cgit v1.2.3


From 40c0066412be25aa6a706ba5eae54db23ee8ade2 Mon Sep 17 00:00:00 2001
From: Suresh Reddy <suresh.reddy@broadcom.com>
Date: Tue, 31 Jul 2018 11:39:43 -0400
Subject: be2net: Update the driver version to 12.0.0.0

Signed-off-by: Suresh Reddy <suresh.reddy@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index 7005949dc17b..d80fe03d3107 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -37,7 +37,7 @@
 #include "be_hw.h"
 #include "be_roce.h"
 
-#define DRV_VER			"11.4.0.0"
+#define DRV_VER			"12.0.0.0"
 #define DRV_NAME		"be2net"
 #define BE_NAME			"Emulex BladeEngine2"
 #define BE3_NAME		"Emulex BladeEngine3"
-- 
cgit v1.2.3


From 16b7db4c8150ba12e7eb63a5de962e1b05b3b612 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
Date: Mon, 30 Jul 2018 18:24:31 +0200
Subject: MAINTAINERS: Add .clang-format entry

As discussed in https://lkml.org/lkml/2018/6/25/877

Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
---
 MAINTAINERS | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 32fbc6f732d4..db759f040fcf 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3514,6 +3514,11 @@ M:	Dave Goodell <dgoodell@cisco.com>
 S:	Supported
 F:	drivers/infiniband/hw/usnic/
 
+CLANG-FORMAT FILE
+M:	Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
+S:	Maintained
+F:	.clang-format
+
 CLEANCACHE API
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
 L:	linux-kernel@vger.kernel.org
-- 
cgit v1.2.3


From b053fcc4a1c3c8f9080e2904acee73481fb58c44 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 31 Jul 2018 17:01:37 +0100
Subject: net/tipc: remove redundant variables 'tn' and 'oport'

Variables 'tn' and 'oport'  are being assigned but are never used hence
they are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'oport' set but not used [-Wunused-but-set-variable]
warning: variable 'tn' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Ying Xue <ying.xue@windriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tipc/socket.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/net/tipc/socket.c b/net/tipc/socket.c
index 3763bedecf5f..c1e93c9515bc 100644
--- a/net/tipc/socket.c
+++ b/net/tipc/socket.c
@@ -411,7 +411,6 @@ static int tipc_sk_sock_err(struct socket *sock, long *timeout)
 static int tipc_sk_create(struct net *net, struct socket *sock,
 			  int protocol, int kern)
 {
-	struct tipc_net *tn;
 	const struct proto_ops *ops;
 	struct sock *sk;
 	struct tipc_sock *tsk;
@@ -446,7 +445,6 @@ static int tipc_sk_create(struct net *net, struct socket *sock,
 	INIT_LIST_HEAD(&tsk->publications);
 	INIT_LIST_HEAD(&tsk->cong_links);
 	msg = &tsk->phdr;
-	tn = net_generic(sock_net(sk), tipc_net_id);
 
 	/* Finish initializing socket data structures */
 	sock->ops = ops;
@@ -1117,7 +1115,7 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 	u32 self = tipc_own_addr(net);
 	u32 type, lower, upper, scope;
 	struct sk_buff *skb, *_skb;
-	u32 portid, oport, onode;
+	u32 portid, onode;
 	struct sk_buff_head tmpq;
 	struct list_head dports;
 	struct tipc_msg *hdr;
@@ -1133,7 +1131,6 @@ void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
 		user = msg_user(hdr);
 		mtyp = msg_type(hdr);
 		hlen = skb_headroom(skb) + msg_hdr_sz(hdr);
-		oport = msg_origport(hdr);
 		onode = msg_orignode(hdr);
 		type = msg_nametype(hdr);
 
-- 
cgit v1.2.3


From 969d509003b8d64f5766a16143bf22d56c1b66fe Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 1 Aug 2018 00:50:24 +0800
Subject: net/tls: Use kmemdup to simplify the code

Kmemdup is better than kmalloc+memcpy. So replace them.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_device.c | 3 +--
 net/tls/tls_sw.c     | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index 1e968d238adf..292742e50bfa 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -716,12 +716,11 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
 	memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
 
 	ctx->tx.rec_seq_size = rec_seq_size;
-	ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
+	ctx->tx.rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL);
 	if (!ctx->tx.rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
 	}
-	memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size);
 
 	rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info);
 	if (rc)
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 33838f11fafa..ff3a6904a722 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -1173,12 +1173,11 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx)
 	memcpy(cctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
 	memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);
 	cctx->rec_seq_size = rec_seq_size;
-	cctx->rec_seq = kmalloc(rec_seq_size, GFP_KERNEL);
+	cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL);
 	if (!cctx->rec_seq) {
 		rc = -ENOMEM;
 		goto free_iv;
 	}
-	memcpy(cctx->rec_seq, rec_seq, rec_seq_size);
 
 	if (sw_ctx_tx) {
 		sg_init_table(sw_ctx_tx->sg_encrypted_data,
-- 
cgit v1.2.3


From d39db3b4d60c9bc4282b36753a7255d2a5ef0384 Mon Sep 17 00:00:00 2001
From: Jon Mason <jdmason@kudzu.us>
Date: Tue, 31 Jul 2018 11:56:19 -0400
Subject: net: change Exar/Neterion menu items to be alphabetical

Neterion was standalone for several years, then acquired by Exar and
shutdown in 11 months without ever making any new Exar branded adapters.
Users would probably think of them as Neterion and not Exar (as there
have been no follow-on adapters and the vast majority ever sold were
under the Neterion name).

6c541b4595a2 ("net: ethernet: Sort Kconfig sourcing alphabetically")
sorted Kconfig sourcing based on directory names, but in a couple cases,
the menu item text is quite different from the directory name and is not
sorted correctly:

  drivers/net/ethernet/neterion/Kconfig    => "Exar devices"

To address that and clear up any confusion about the name, "Exar" was
changed to "Neterion (Exar)" and the relevant entries in the Makefile
and Kconfig were reordered to match the alphabetical organization.

Inspired-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Jon Mason <jdmason@kudzu.us>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/Kconfig          |  2 +-
 drivers/net/ethernet/Makefile         |  2 +-
 drivers/net/ethernet/neterion/Kconfig | 23 ++++++++++++++---------
 3 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index af766fd61151..6fde68aa13a4 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -81,7 +81,6 @@ source "drivers/net/ethernet/huawei/Kconfig"
 source "drivers/net/ethernet/i825xx/Kconfig"
 source "drivers/net/ethernet/ibm/Kconfig"
 source "drivers/net/ethernet/intel/Kconfig"
-source "drivers/net/ethernet/neterion/Kconfig"
 source "drivers/net/ethernet/xscale/Kconfig"
 
 config JME
@@ -128,6 +127,7 @@ config FEALNX
 	  cards. <http://www.myson.com.tw/>
 
 source "drivers/net/ethernet/natsemi/Kconfig"
+source "drivers/net/ethernet/neterion/Kconfig"
 source "drivers/net/ethernet/netronome/Kconfig"
 source "drivers/net/ethernet/ni/Kconfig"
 source "drivers/net/ethernet/8390/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 22555e7fa752..b45d5f626b59 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -36,7 +36,6 @@ obj-$(CONFIG_NET_VENDOR_DEC) += dec/
 obj-$(CONFIG_NET_VENDOR_DLINK) += dlink/
 obj-$(CONFIG_NET_VENDOR_EMULEX) += emulex/
 obj-$(CONFIG_NET_VENDOR_EZCHIP) += ezchip/
-obj-$(CONFIG_NET_VENDOR_EXAR) += neterion/
 obj-$(CONFIG_NET_VENDOR_FARADAY) += faraday/
 obj-$(CONFIG_NET_VENDOR_FREESCALE) += freescale/
 obj-$(CONFIG_NET_VENDOR_FUJITSU) += fujitsu/
@@ -60,6 +59,7 @@ obj-$(CONFIG_NET_VENDOR_MOXART) += moxa/
 obj-$(CONFIG_NET_VENDOR_MYRI) += myricom/
 obj-$(CONFIG_FEALNX) += fealnx.o
 obj-$(CONFIG_NET_VENDOR_NATSEMI) += natsemi/
+obj-$(CONFIG_NET_VENDOR_NETERION) += neterion/
 obj-$(CONFIG_NET_VENDOR_NETRONOME) += netronome/
 obj-$(CONFIG_NET_VENDOR_NI) += ni/
 obj-$(CONFIG_NET_NETX) += netx-eth.o
diff --git a/drivers/net/ethernet/neterion/Kconfig b/drivers/net/ethernet/neterion/Kconfig
index 71899009c468..c26e0f70c494 100644
--- a/drivers/net/ethernet/neterion/Kconfig
+++ b/drivers/net/ethernet/neterion/Kconfig
@@ -2,8 +2,8 @@
 # Exar device configuration
 #
 
-config NET_VENDOR_EXAR
-	bool "Exar devices"
+config NET_VENDOR_NETERION
+	bool "Neterion (Exar) devices"
 	default y
 	depends on PCI
 	---help---
@@ -11,16 +11,19 @@ config NET_VENDOR_EXAR
 
 	  Note that the answer to this question doesn't directly affect the
 	  kernel: saying N will just cause the configurator to skip all
-	  the questions about Exar cards. If you say Y, you will be asked for
-	  your specific card in the following questions.
+	  the questions about Neterion/Exar cards. If you say Y, you will be
+	  asked for your specific card in the following questions.
 
-if NET_VENDOR_EXAR
+if NET_VENDOR_NETERION
 
 config S2IO
-	tristate "Exar Xframe 10Gb Ethernet Adapter"
+	tristate "Neterion (Exar) Xframe 10Gb Ethernet Adapter"
 	depends on PCI
 	---help---
 	  This driver supports Exar Corp's Xframe Series 10Gb Ethernet Adapters.
+	  These were originally released from S2IO, which renamed itself
+	  Neterion.  So, the adapters might be labeled as either one, depending
+	  on its age.
 
 	  More specific information on configuring the driver is in
 	  <file:Documentation/networking/s2io.txt>.
@@ -29,11 +32,13 @@ config S2IO
 	  will be called s2io.
 
 config VXGE
-	tristate "Exar X3100 Series 10GbE PCIe Server Adapter"
+	tristate "Neterion (Exar) X3100 Series 10GbE PCIe Server Adapter"
 	depends on PCI
 	---help---
 	  This driver supports Exar Corp's X3100 Series 10 GbE PCIe
-	  I/O Virtualized Server Adapter.
+	  I/O Virtualized Server Adapter.  These were originally released from
+	  Neterion, which was later acquired by Exar.  So, the adapters might be
+	  labeled as either one, depending on its age.
 
 	  More specific information on configuring the driver is in
 	  <file:Documentation/networking/vxge.txt>.
@@ -50,4 +55,4 @@ config VXGE_DEBUG_TRACE_ALL
 	  the vxge driver. By default only few debug trace statements are
 	  enabled.
 
-endif # NET_VENDOR_EXAR
+endif # NET_VENDOR_NETERION
-- 
cgit v1.2.3


From 83ba4645152d1177c161750e1064e3a8e7cee19b Mon Sep 17 00:00:00 2001
From: Vincent Bernat <vincent@bernat.im>
Date: Tue, 31 Jul 2018 21:18:11 +0200
Subject: net: add helpers checking if socket can be bound to nonlocal address

The construction "net->ipv4.sysctl_ip_nonlocal_bind || inet->freebind
|| inet->transparent" is present three times and its IPv6 counterpart
is also present three times. We introduce two small helpers to
characterize these tests uniformly.

Signed-off-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_sock.h | 8 ++++++++
 include/net/ipv6.h      | 7 +++++++
 net/ipv4/af_inet.c      | 3 +--
 net/ipv4/ping.c         | 6 ++----
 net/ipv6/af_inet6.c     | 6 ++----
 net/ipv6/datagram.c     | 3 +--
 6 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index 314be484c696..e03b93360f33 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -359,4 +359,12 @@ static inline bool inet_get_convert_csum(struct sock *sk)
 	return !!inet_sk(sk)->convert_csum;
 }
 
+
+static inline bool inet_can_nonlocal_bind(struct net *net,
+					  struct inet_sock *inet)
+{
+	return net->ipv4.sysctl_ip_nonlocal_bind ||
+		inet->freebind || inet->transparent;
+}
+
 #endif	/* _INET_SOCK_H */
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index a44509f4e985..82deb684ba73 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -766,6 +766,13 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6,
 	return hlimit;
 }
 
+static inline bool ipv6_can_nonlocal_bind(struct net *net,
+					  struct inet_sock *inet)
+{
+	return net->ipv6.sysctl.ip_nonlocal_bind ||
+		inet->freebind || inet->transparent;
+}
+
 /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store
  * Equivalent to :	flow->v6addrs.src = iph->saddr;
  *			flow->v6addrs.dst = iph->daddr;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index f2a0a3bab6b5..ee707b91d1a7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -486,8 +486,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 	 *  is temporarily down)
 	 */
 	err = -EADDRNOTAVAIL;
-	if (!net->ipv4.sysctl_ip_nonlocal_bind &&
-	    !(inet->freebind || inet->transparent) &&
+	if (!inet_can_nonlocal_bind(net, inet) &&
 	    addr->sin_addr.s_addr != htonl(INADDR_ANY) &&
 	    chk_addr_ret != RTN_LOCAL &&
 	    chk_addr_ret != RTN_MULTICAST &&
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index b54c964ad925..8d7aaf118a30 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -320,8 +320,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
 			chk_addr_ret = RTN_LOCAL;
 
-		if ((net->ipv4.sysctl_ip_nonlocal_bind == 0 &&
-		    isk->freebind == 0 && isk->transparent == 0 &&
+		if ((!inet_can_nonlocal_bind(net, isk) &&
 		     chk_addr_ret != RTN_LOCAL) ||
 		    chk_addr_ret == RTN_MULTICAST ||
 		    chk_addr_ret == RTN_BROADCAST)
@@ -361,8 +360,7 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
 						    scoped);
 		rcu_read_unlock();
 
-		if (!(net->ipv6.sysctl.ip_nonlocal_bind ||
-		      isk->freebind || isk->transparent || has_addr ||
+		if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr ||
 		      addr_type == IPV6_ADDR_ANY))
 			return -EADDRNOTAVAIL;
 
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index c9535354149f..020f6e14a7af 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -322,8 +322,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 		/* Reproduce AF_INET checks to make the bindings consistent */
 		v4addr = addr->sin6_addr.s6_addr32[3];
 		chk_addr_ret = inet_addr_type(net, v4addr);
-		if (!net->ipv4.sysctl_ip_nonlocal_bind &&
-		    !(inet->freebind || inet->transparent) &&
+		if (!inet_can_nonlocal_bind(net, inet) &&
 		    v4addr != htonl(INADDR_ANY) &&
 		    chk_addr_ret != RTN_LOCAL &&
 		    chk_addr_ret != RTN_MULTICAST &&
@@ -362,8 +361,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 			 */
 			v4addr = LOOPBACK4_IPV6;
 			if (!(addr_type & IPV6_ADDR_MULTICAST))	{
-				if (!net->ipv6.sysctl.ip_nonlocal_bind &&
-				    !(inet->freebind || inet->transparent) &&
+				if (!ipv6_can_nonlocal_bind(net, inet) &&
 				    !ipv6_chk_addr(net, &addr->sin6_addr,
 						   dev, 0)) {
 					err = -EADDRNOTAVAIL;
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index f0264dfd38de..1ede7a16a0be 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -803,8 +803,7 @@ int ip6_datagram_send_ctl(struct net *net, struct sock *sk,
 
 			if (addr_type != IPV6_ADDR_ANY) {
 				int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL;
-				if (!(net->ipv6.sysctl.ip_nonlocal_bind ||
-				      inet_sk(sk)->freebind || inet_sk(sk)->transparent) &&
+				if (!ipv6_can_nonlocal_bind(net, inet_sk(sk)) &&
 				    !ipv6_chk_addr_and_flags(net, &src_info->ipi6_addr,
 							     dev, !strict, 0,
 							     IFA_F_TENTATIVE) &&
-- 
cgit v1.2.3


From 432e05d328921c68c35bfdeff7d7b7400b8e3d1a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 1 Aug 2018 00:36:03 +0200
Subject: net: ipv4: Control SKB reprioritization after forwarding

After IPv4 packets are forwarded, the priority of the corresponding SKB
is updated according to the TOS field of IPv4 header. This overrides any
prioritization done earlier by e.g. an skbedit action or ingress-qos-map
defined at a vlan device.

Such overriding may not always be desirable. Even if the packet ends up
being routed, which implies this is an L3 network node, an administrator
may wish to preserve whatever prioritization was done earlier on in the
pipeline.

Therefore introduce a sysctl that controls this behavior. Keep the
default value at 1 to maintain backward-compatible behavior.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt | 9 +++++++++
 include/net/netns/ipv4.h               | 1 +
 net/ipv4/af_inet.c                     | 1 +
 net/ipv4/ip_forward.c                  | 3 ++-
 net/ipv4/sysctl_net_ipv4.c             | 9 +++++++++
 5 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 77c37fb0b6a6..e74515ecaa9c 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -81,6 +81,15 @@ fib_multipath_hash_policy - INTEGER
 	0 - Layer 3
 	1 - Layer 4
 
+ip_forward_update_priority - INTEGER
+	Whether to update SKB priority from "TOS" field in IPv4 header after it
+	is forwarded. The new SKB priority is mapped from TOS field value
+	according to an rt_tos2priority table (see e.g. man tc-prio).
+	Default: 1 (Update priority.)
+	Possible values:
+	0 - Do not update priority.
+	1 - Update priority.
+
 route/max_size - INTEGER
 	Maximum number of routes allowed in the kernel.  Increase
 	this when using large numbers of interfaces and/or routes.
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 661348f23ea5..e47503b4e4d1 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -98,6 +98,7 @@ struct netns_ipv4 {
 	int sysctl_ip_default_ttl;
 	int sysctl_ip_no_pmtu_disc;
 	int sysctl_ip_fwd_use_pmtu;
+	int sysctl_ip_fwd_update_priority;
 	int sysctl_ip_nonlocal_bind;
 	/* Shall we try to damage output packets if routing dev changes? */
 	int sysctl_ip_dynaddr;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ee707b91d1a7..20fda8fb8ffd 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1801,6 +1801,7 @@ static __net_init int inet_init_net(struct net *net)
 	 * We set them here, in case sysctl is not compiled.
 	 */
 	net->ipv4.sysctl_ip_default_ttl = IPDEFTTL;
+	net->ipv4.sysctl_ip_fwd_update_priority = 1;
 	net->ipv4.sysctl_ip_dynaddr = 0;
 	net->ipv4.sysctl_ip_early_demux = 1;
 	net->ipv4.sysctl_udp_early_demux = 1;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index b54b948b0596..32662e9e5d21 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -143,7 +143,8 @@ int ip_forward(struct sk_buff *skb)
 	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
-	skb->priority = rt_tos2priority(iph->tos);
+	if (net->ipv4.sysctl_ip_fwd_update_priority)
+		skb->priority = rt_tos2priority(iph->tos);
 
 	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
 		       net, NULL, skb, skb->dev, rt->dst.dev,
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 5fa335fd3852..e21dda015513 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -663,6 +663,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
+	{
+		.procname	= "ip_forward_update_priority",
+		.data		= &init_net.ipv4.sysctl_ip_fwd_update_priority,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler   = proc_dointvec_minmax,
+		.extra1		= &zero,
+		.extra2		= &one,
+	},
 	{
 		.procname	= "ip_nonlocal_bind",
 		.data		= &init_net.ipv4.sysctl_ip_nonlocal_bind,
-- 
cgit v1.2.3


From d18c5d1995aa322b722fa731397e28ebcd00b3c6 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 1 Aug 2018 00:36:42 +0200
Subject: net: ipv4: Notify about changes to ip_forward_update_priority

Drivers may make offloading decision based on whether
ip_forward_update_priority is enabled or not. Therefore distribute
netevent notifications to give them a chance to react to a change.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/netevent.h     |  1 +
 net/ipv4/sysctl_net_ipv4.c | 19 ++++++++++++++++++-
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/include/net/netevent.h b/include/net/netevent.h
index d9918261701c..4107016c3bb4 100644
--- a/include/net/netevent.h
+++ b/include/net/netevent.h
@@ -28,6 +28,7 @@ enum netevent_notif_type {
 	NETEVENT_DELAY_PROBE_TIME_UPDATE, /* arg is struct neigh_parms ptr */
 	NETEVENT_IPV4_MPATH_HASH_UPDATE, /* arg is struct net ptr */
 	NETEVENT_IPV6_MPATH_HASH_UPDATE, /* arg is struct net ptr */
+	NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE, /* arg is struct net ptr */
 };
 
 int register_netevent_notifier(struct notifier_block *nb);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e21dda015513..b92f422f2fa8 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -201,6 +201,23 @@ static int ipv4_ping_group_range(struct ctl_table *table, int write,
 	return ret;
 }
 
+static int ipv4_fwd_update_priority(struct ctl_table *table, int write,
+				    void __user *buffer,
+				    size_t *lenp, loff_t *ppos)
+{
+	struct net *net;
+	int ret;
+
+	net = container_of(table->data, struct net,
+			   ipv4.sysctl_ip_fwd_update_priority);
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		call_netevent_notifiers(NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE,
+					net);
+
+	return ret;
+}
+
 static int proc_tcp_congestion_control(struct ctl_table *ctl, int write,
 				       void __user *buffer, size_t *lenp, loff_t *ppos)
 {
@@ -668,7 +685,7 @@ static struct ctl_table ipv4_net_table[] = {
 		.data		= &init_net.ipv4.sysctl_ip_fwd_update_priority,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler   = proc_dointvec_minmax,
+		.proc_handler   = ipv4_fwd_update_priority,
 		.extra1		= &zero,
 		.extra2		= &one,
 	},
-- 
cgit v1.2.3


From 1f65a33fc7e22de96055778b0e4f214e005291e7 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 1 Aug 2018 00:37:36 +0200
Subject: mlxsw: spectrum: Extract work-scheduling into a new function

The boilerplate to schedule NETEVENT_IPV4_MPATH_HASH_UPDATE and
NETEVENT_IPV6_MPATH_HASH_UPDATE handling is almost equivalent to that of
NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE that's coming in the next
patch. The only difference is which actual worker function should be
called. Extract this boilerplate into a named function in order to allow
reuse.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 38 +++++++++++++---------
 1 file changed, 23 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 8d67f0123699..5ee927626567 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2436,17 +2436,36 @@ static void mlxsw_sp_router_mp_hash_event_work(struct work_struct *work)
 	kfree(net_work);
 }
 
+static int mlxsw_sp_router_schedule_work(struct net *net,
+					 struct notifier_block *nb,
+					 void (*cb)(struct work_struct *))
+{
+	struct mlxsw_sp_netevent_work *net_work;
+	struct mlxsw_sp_router *router;
+
+	if (!net_eq(net, &init_net))
+		return NOTIFY_DONE;
+
+	net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC);
+	if (!net_work)
+		return NOTIFY_BAD;
+
+	router = container_of(nb, struct mlxsw_sp_router, netevent_nb);
+	INIT_WORK(&net_work->work, cb);
+	net_work->mlxsw_sp = router->mlxsw_sp;
+	mlxsw_core_schedule_work(&net_work->work);
+	return NOTIFY_DONE;
+}
+
 static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 					  unsigned long event, void *ptr)
 {
 	struct mlxsw_sp_netevent_work *net_work;
 	struct mlxsw_sp_port *mlxsw_sp_port;
-	struct mlxsw_sp_router *router;
 	struct mlxsw_sp *mlxsw_sp;
 	unsigned long interval;
 	struct neigh_parms *p;
 	struct neighbour *n;
-	struct net *net;
 
 	switch (event) {
 	case NETEVENT_DELAY_PROBE_TIME_UPDATE:
@@ -2500,20 +2519,9 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 		break;
 	case NETEVENT_IPV4_MPATH_HASH_UPDATE:
 	case NETEVENT_IPV6_MPATH_HASH_UPDATE:
-		net = ptr;
+		return mlxsw_sp_router_schedule_work(ptr, nb,
+				mlxsw_sp_router_mp_hash_event_work);
 
-		if (!net_eq(net, &init_net))
-			return NOTIFY_DONE;
-
-		net_work = kzalloc(sizeof(*net_work), GFP_ATOMIC);
-		if (!net_work)
-			return NOTIFY_BAD;
-
-		router = container_of(nb, struct mlxsw_sp_router, netevent_nb);
-		INIT_WORK(&net_work->work, mlxsw_sp_router_mp_hash_event_work);
-		net_work->mlxsw_sp = router->mlxsw_sp;
-		mlxsw_core_schedule_work(&net_work->work);
-		break;
 	}
 
 	return NOTIFY_DONE;
-- 
cgit v1.2.3


From 6495342365e859400023c09063c2b31a12d68261 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 1 Aug 2018 00:38:03 +0200
Subject: mlxsw: spectrum_router: Handle sysctl_ip_fwd_update_priority

This sysctl setting controls whether packet priority should be updated
after forwarding. Configure RGCR.usp accordingly so that the device is
in sync with the kernel handling.

Note that RGCR doesn't allow changing arbitrary parameters
mid-operation, however "usp" is exempt and can be reconfigured.

Also react to NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE notifications
that signify change in this configuration.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 5ee927626567..eec7166fad62 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -2436,6 +2436,18 @@ static void mlxsw_sp_router_mp_hash_event_work(struct work_struct *work)
 	kfree(net_work);
 }
 
+static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp);
+
+static void mlxsw_sp_router_update_priority_work(struct work_struct *work)
+{
+	struct mlxsw_sp_netevent_work *net_work =
+		container_of(work, struct mlxsw_sp_netevent_work, work);
+	struct mlxsw_sp *mlxsw_sp = net_work->mlxsw_sp;
+
+	__mlxsw_sp_router_init(mlxsw_sp);
+	kfree(net_work);
+}
+
 static int mlxsw_sp_router_schedule_work(struct net *net,
 					 struct notifier_block *nb,
 					 void (*cb)(struct work_struct *))
@@ -2522,6 +2534,9 @@ static int mlxsw_sp_router_netevent_event(struct notifier_block *nb,
 		return mlxsw_sp_router_schedule_work(ptr, nb,
 				mlxsw_sp_router_mp_hash_event_work);
 
+	case NETEVENT_IPV4_FWD_UPDATE_PRIORITY_UPDATE:
+		return mlxsw_sp_router_schedule_work(ptr, nb,
+				mlxsw_sp_router_update_priority_work);
 	}
 
 	return NOTIFY_DONE;
@@ -7390,6 +7405,7 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp)
 
 static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
+	bool usp = init_net.ipv4.sysctl_ip_fwd_update_priority;
 	char rgcr_pl[MLXSW_REG_RGCR_LEN];
 	u64 max_rifs;
 	int err;
@@ -7400,7 +7416,7 @@ static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 
 	mlxsw_reg_rgcr_pack(rgcr_pl, true, true);
 	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
-	mlxsw_reg_rgcr_usp_set(rgcr_pl, true);
+	mlxsw_reg_rgcr_usp_set(rgcr_pl, usp);
 	err = mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(rgcr), rgcr_pl);
 	if (err)
 		return err;
-- 
cgit v1.2.3


From 989133bf7ff3fe6ebcb9c1e7b5e13bebac175d35 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 1 Aug 2018 00:38:59 +0200
Subject: selftests: forwarding: Move lldpad waiting to lib.sh

The function lldpad_wait() will be useful for a test added by a
following patch. Likewise would the "sleep 5" with its extensive
comment.

Therefore move lldpad_wait() to lib.sh in order to allow reuse. Rename
it to lldpad_app_wait_set() to recognize that what this is intended to
wait on are the pending APP sets.

For the sleeping, add a function lldpad_app_wait_del(). That will serve
to hold the related explanatory comment (which edit for clarity), and as
a token in the caller to identify the sites where this sort of waiting
takes place. That will serve when/if a better way to handle this
business is found.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_dscp_bridge.sh | 23 +++-------------------
 tools/testing/selftests/net/forwarding/lib.sh      | 21 ++++++++++++++++++++
 2 files changed, 24 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
index cc527660a022..9e875ee8dc1c 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
@@ -103,16 +103,6 @@ dscp_map()
 	done
 }
 
-lldpad_wait()
-{
-	local dev=$1; shift
-
-	while lldptool -t -i $dev -V APP -c app | grep -q pending; do
-	    echo "$dev: waiting for lldpad to push pending APP updates"
-	    sleep 5
-	done
-}
-
 switch_create()
 {
 	ip link add name br1 type bridge vlan_filtering 1
@@ -124,22 +114,15 @@ switch_create()
 
 	lldptool -T -i $swp1 -V APP $(dscp_map 10) >/dev/null
 	lldptool -T -i $swp2 -V APP $(dscp_map 20) >/dev/null
-	lldpad_wait $swp1
-	lldpad_wait $swp2
+	lldpad_app_wait_set $swp1
+	lldpad_app_wait_set $swp2
 }
 
 switch_destroy()
 {
 	lldptool -T -i $swp2 -V APP -d $(dscp_map 20) >/dev/null
 	lldptool -T -i $swp1 -V APP -d $(dscp_map 10) >/dev/null
-
-	# Give lldpad a chance to push down the changes. If the device is downed
-	# too soon, the updates will be left pending, but will have been struck
-	# off the lldpad's DB already, and we won't be able to tell. Then on
-	# next test iteration this would cause weirdness as newly-added APP
-	# rules conflict with the old ones, sometimes getting stuck in an
-	# "unknown" state.
-	sleep 5
+	lldpad_app_wait_del
 
 	ip link set dev $swp2 nomaster
 	ip link set dev $swp1 nomaster
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 843a6715924f..90af5cd23417 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -247,6 +247,27 @@ setup_wait()
 	sleep $WAIT_TIME
 }
 
+lldpad_app_wait_set()
+{
+	local dev=$1; shift
+
+	while lldptool -t -i $dev -V APP -c app | grep -q pending; do
+		echo "$dev: waiting for lldpad to push pending APP updates"
+		sleep 5
+	done
+}
+
+lldpad_app_wait_del()
+{
+	# Give lldpad a chance to push down the changes. If the device is downed
+	# too soon, the updates will be left pending. However, they will have
+	# been struck off the lldpad's DB already, so we won't be able to tell
+	# they are pending. Then on next test iteration this would cause
+	# weirdness as newly-added APP rules conflict with the old ones,
+	# sometimes getting stuck in an "unknown" state.
+	sleep 5
+}
+
 pre_cleanup()
 {
 	if [ "${PAUSE_ON_CLEANUP}" = "yes" ]; then
-- 
cgit v1.2.3


From cf60869814bcdfbeec02e92ce9e6b38562707edd Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 1 Aug 2018 00:39:25 +0200
Subject: selftests: forwarding: Move DSCP capture to lib.sh

dscp_capture_install() and dscp_capture_uninstall() are going to be
useful for a test added by a following patch, move them therefore to
lib.sh together with related helpers.

While doing so, change the rule preference from mere DSCP value to
DSCP+100 in order to support adding captures of packets with DSCP of 0.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_dscp_bridge.sh | 42 ----------------------
 tools/testing/selftests/net/forwarding/lib.sh      | 42 ++++++++++++++++++++++
 2 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
index 9e875ee8dc1c..1ca631d5aaba 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_bridge.sh
@@ -34,36 +34,6 @@ lib_dir=$(dirname $0)/../../../net/forwarding
 NUM_NETIFS=4
 source $lib_dir/lib.sh
 
-__dscp_capture_add_del()
-{
-	local add_del=$1; shift
-	local dev=$1; shift
-	local base=$1; shift
-	local dscp;
-
-	for prio in {0..7}; do
-		dscp=$((base + prio))
-		__icmp_capture_add_del $add_del $dscp "" $dev \
-				       "ip_tos $((dscp << 2))"
-	done
-}
-
-dscp_capture_install()
-{
-	local dev=$1; shift
-	local base=$1; shift
-
-	__dscp_capture_add_del add $dev $base
-}
-
-dscp_capture_uninstall()
-{
-	local dev=$1; shift
-	local base=$1; shift
-
-	__dscp_capture_add_del del $dev $base
-}
-
 h1_create()
 {
 	local dscp;
@@ -155,18 +125,6 @@ cleanup()
 	vrf_cleanup
 }
 
-dscp_fetch_stats()
-{
-	local dev=$1; shift
-	local base=$1; shift
-
-	for prio in {0..7}; do
-		local dscp=$((base + prio))
-		local t=$(tc_rule_stats_get $dev $dscp)
-		echo "[$dscp]=$t "
-	done
-}
-
 ping_ipv4()
 {
 	ping_test $h1 192.0.2.2
diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 90af5cd23417..ca53b539aa2d 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -653,6 +653,48 @@ vlan_capture_uninstall()
 	__vlan_capture_add_del del 100 "$@"
 }
 
+__dscp_capture_add_del()
+{
+	local add_del=$1; shift
+	local dev=$1; shift
+	local base=$1; shift
+	local dscp;
+
+	for prio in {0..7}; do
+		dscp=$((base + prio))
+		__icmp_capture_add_del $add_del $((dscp + 100)) "" $dev \
+				       "skip_hw ip_tos $((dscp << 2))"
+	done
+}
+
+dscp_capture_install()
+{
+	local dev=$1; shift
+	local base=$1; shift
+
+	__dscp_capture_add_del add $dev $base
+}
+
+dscp_capture_uninstall()
+{
+	local dev=$1; shift
+	local base=$1; shift
+
+	__dscp_capture_add_del del $dev $base
+}
+
+dscp_fetch_stats()
+{
+	local dev=$1; shift
+	local base=$1; shift
+
+	for prio in {0..7}; do
+		local dscp=$((base + prio))
+		local t=$(tc_rule_stats_get $dev $((dscp + 100)))
+		echo "[$dscp]=$t "
+	done
+}
+
 matchall_sink_create()
 {
 	local dev=$1; shift
-- 
cgit v1.2.3


From 9bae0451b7dcca54db376d2ea2cb8d9fc763a683 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Wed, 1 Aug 2018 00:39:29 +0200
Subject: selftests: mlxsw: Add test for ip_forward_update_priority

Verify that with that sysctl turned off, DSCP prioritization and rewrite
works the same way as in qos_dscp_bridge test. However when the sysctl
is charged, there should be a reprioritization after routing stage,
which will be observed by a different DSCP rewrite on egress.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/drivers/net/mlxsw/qos_dscp_router.sh | 233 +++++++++++++++++++++
 1 file changed, 233 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
new file mode 100755
index 000000000000..281d90766e12
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/qos_dscp_router.sh
@@ -0,0 +1,233 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test for DSCP prioritization in the router.
+#
+# With ip_forward_update_priority disabled, the packets are expected to keep
+# their DSCP (which in this test uses only values 0..7) intact as they are
+# forwarded by the switch. That is verified at $h2. ICMP responses are formed
+# with the same DSCP as the requests, and likewise pass through the switch
+# intact, which is verified at $h1.
+#
+# With ip_forward_update_priority enabled, router reprioritizes the packets
+# according to the table in reprioritize(). Thus, say, DSCP 7 maps to priority
+# 4, which on egress maps back to DSCP 4. The response packet then gets
+# reprioritized to 6, getting DSCP 6 on egress.
+#
+# +----------------------+                             +----------------------+
+# | H1                   |                             |                   H2 |
+# |    + $h1             |                             |            $h2 +     |
+# |    | 192.0.2.1/28    |                             |  192.0.2.18/28 |     |
+# +----|-----------------+                             +----------------|-----+
+#      |                                                                |
+# +----|----------------------------------------------------------------|-----+
+# | SW |                                                                |     |
+# |    + $swp1                                                    $swp2 +     |
+# |      192.0.2.2/28                                     192.0.2.17/28       |
+# |      APP=0,5,0 .. 7,5,7                          APP=0,5,0 .. 7,5,7       |
+# +---------------------------------------------------------------------------+
+
+ALL_TESTS="
+	ping_ipv4
+	test_update
+	test_no_update
+"
+
+lib_dir=$(dirname $0)/../../../net/forwarding
+
+NUM_NETIFS=4
+source $lib_dir/lib.sh
+
+reprioritize()
+{
+	local in=$1; shift
+
+	# This is based on rt_tos2priority in include/net/route.h. Assuming 1:1
+	# mapping between priorities and TOS, it yields a new priority for a
+	# packet with ingress priority of $in.
+	local -a reprio=(0 0 2 2 6 6 4 4)
+
+	echo ${reprio[$in]}
+}
+
+h1_create()
+{
+	local dscp;
+
+	simple_if_init $h1 192.0.2.1/28
+	tc qdisc add dev $h1 clsact
+	dscp_capture_install $h1 0
+	ip route add vrf v$h1 192.0.2.16/28 via 192.0.2.2
+}
+
+h1_destroy()
+{
+	ip route del vrf v$h1 192.0.2.16/28 via 192.0.2.2
+	dscp_capture_uninstall $h1 0
+	tc qdisc del dev $h1 clsact
+	simple_if_fini $h1 192.0.2.1/28
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.18/28
+	tc qdisc add dev $h2 clsact
+	dscp_capture_install $h2 0
+	ip route add vrf v$h2 192.0.2.0/28 via 192.0.2.17
+}
+
+h2_destroy()
+{
+	ip route del vrf v$h2 192.0.2.0/28 via 192.0.2.17
+	dscp_capture_uninstall $h2 0
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2 192.0.2.18/28
+}
+
+dscp_map()
+{
+	local base=$1; shift
+
+	for prio in {0..7}; do
+		echo app=$prio,5,$((base + prio))
+	done
+}
+
+switch_create()
+{
+	simple_if_init $swp1 192.0.2.2/28
+	__simple_if_init $swp2 v$swp1 192.0.2.17/28
+
+	lldptool -T -i $swp1 -V APP $(dscp_map 0) >/dev/null
+	lldptool -T -i $swp2 -V APP $(dscp_map 0) >/dev/null
+	lldpad_app_wait_set $swp1
+	lldpad_app_wait_set $swp2
+}
+
+switch_destroy()
+{
+	lldptool -T -i $swp2 -V APP -d $(dscp_map 0) >/dev/null
+	lldptool -T -i $swp1 -V APP -d $(dscp_map 0) >/dev/null
+	lldpad_app_wait_del
+
+	__simple_if_fini $swp2 192.0.2.17/28
+	simple_if_fini $swp1 192.0.2.2/28
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	swp1=${NETIFS[p2]}
+
+	swp2=${NETIFS[p3]}
+	h2=${NETIFS[p4]}
+
+	vrf_prepare
+
+	sysctl_set net.ipv4.ip_forward_update_priority 1
+	h1_create
+	h2_create
+	switch_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	switch_destroy
+	h2_destroy
+	h1_destroy
+	sysctl_restore net.ipv4.ip_forward_update_priority
+
+	vrf_cleanup
+}
+
+ping_ipv4()
+{
+	ping_test $h1 192.0.2.18
+}
+
+dscp_ping_test()
+{
+	local vrf_name=$1; shift
+	local sip=$1; shift
+	local dip=$1; shift
+	local prio=$1; shift
+	local reprio=$1; shift
+	local dev1=$1; shift
+	local dev2=$1; shift
+
+	local prio2=$($reprio $prio)   # ICMP Request egress prio
+	local prio3=$($reprio $prio2)  # ICMP Response egress prio
+
+	local dscp=$((prio << 2))     # ICMP Request ingress DSCP
+	local dscp2=$((prio2 << 2))   # ICMP Request egress DSCP
+	local dscp3=$((prio3 << 2))   # ICMP Response egress DSCP
+
+	RET=0
+
+	eval "local -A dev1_t0s=($(dscp_fetch_stats $dev1 0))"
+	eval "local -A dev2_t0s=($(dscp_fetch_stats $dev2 0))"
+
+	ip vrf exec $vrf_name \
+	   ${PING} -Q $dscp ${sip:+-I $sip} $dip \
+		   -c 10 -i 0.1 -w 2 &> /dev/null
+
+	eval "local -A dev1_t1s=($(dscp_fetch_stats $dev1 0))"
+	eval "local -A dev2_t1s=($(dscp_fetch_stats $dev2 0))"
+
+	for i in {0..7}; do
+		local dscpi=$((i << 2))
+		local expect2=0
+		local expect3=0
+
+		if ((i == prio2)); then
+			expect2=10
+		fi
+		if ((i == prio3)); then
+			expect3=10
+		fi
+
+		local delta=$((dev2_t1s[$i] - dev2_t0s[$i]))
+		((expect2 == delta))
+		check_err $? "DSCP $dscpi@$dev2: Expected to capture $expect2 packets, got $delta."
+
+		delta=$((dev1_t1s[$i] - dev1_t0s[$i]))
+		((expect3 == delta))
+		check_err $? "DSCP $dscpi@$dev1: Expected to capture $expect3 packets, got $delta."
+	done
+
+	log_test "DSCP rewrite: $dscp-(prio $prio2)-$dscp2-(prio $prio3)-$dscp3"
+}
+
+__test_update()
+{
+	local update=$1; shift
+	local reprio=$1; shift
+
+	sysctl_restore net.ipv4.ip_forward_update_priority
+	sysctl_set net.ipv4.ip_forward_update_priority $update
+
+	for prio in {0..7}; do
+		dscp_ping_test v$h1 192.0.2.1 192.0.2.18 $prio $reprio $h1 $h2
+	done
+}
+
+test_update()
+{
+	__test_update 1 reprioritize
+}
+
+test_no_update()
+{
+	__test_update 0 echo
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 171613926abc9980e58cb36d5d54fe60e58a03a5 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Fri, 26 Jan 2018 23:19:15 +0800
Subject: auxdisplay: charlcd: delete mdelay in long_sleep

The function long_sleep() calls mdelay() when in an interrupt handler.
But only charlcd_clear_display() and charlcd_init_display calls
long_sleep(), and my tool finds that the two functions
are never called in an interrupt handler.
Thus mdelay() and in_interrupt() are not necessary.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Acked-by: Willy Tarreau <w@1wt.eu>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
---
 drivers/auxdisplay/charlcd.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/auxdisplay/charlcd.c b/drivers/auxdisplay/charlcd.c
index 8673fc2b9eb8..81c22d20d9d9 100644
--- a/drivers/auxdisplay/charlcd.c
+++ b/drivers/auxdisplay/charlcd.c
@@ -99,10 +99,7 @@ static atomic_t charlcd_available = ATOMIC_INIT(1);
 /* sleeps that many milliseconds with a reschedule */
 static void long_sleep(int ms)
 {
-	if (in_interrupt())
-		mdelay(ms);
-	else
-		schedule_timeout_interruptible(msecs_to_jiffies(ms));
+	schedule_timeout_interruptible(msecs_to_jiffies(ms));
 }
 
 /* turn the backlight on or off */
-- 
cgit v1.2.3


From 984988aa72188453f8c8a42dcf94bba1c57e73aa Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 31 Jul 2018 17:46:20 -0700
Subject: tcp: add a helper to calculate size of opt_stats

This is to refactor the calculation of the size of opt_stats to a helper
function to make the code cleaner and easier for later changes.

Suggested-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f3bfb9f29520..27bbe6a792b7 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3205,6 +3205,29 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
 
+static size_t tcp_opt_stats_get_size(void)
+{
+	return
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BUSY */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_RWND_LIMITED */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_SNDBUF_LIMITED */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DATA_SEGS_OUT */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_TOTAL_RETRANS */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_PACING_RATE */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_DELIVERY_RATE */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_CWND */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_REORDERING */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_MIN_RTT */
+		nla_total_size(sizeof(u8)) + /* TCP_NLA_RECUR_RETRANS */
+		nla_total_size(sizeof(u8)) + /* TCP_NLA_DELIVERY_RATE_APP_LMT */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_SNDQ_SIZE */
+		nla_total_size(sizeof(u8)) + /* TCP_NLA_CA_STATE */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
+		0;
+}
+
 struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
@@ -3213,9 +3236,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	u64 rate64;
 	u32 rate;
 
-	stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) +
-			  7 * nla_total_size(sizeof(u32)) +
-			  3 * nla_total_size(sizeof(u8)), GFP_ATOMIC);
+	stats = alloc_skb(tcp_opt_stats_get_size(), GFP_ATOMIC);
 	if (!stats)
 		return NULL;
 
-- 
cgit v1.2.3


From ba113c3aa79a7f941ac162d05a3620bdc985c58d Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 31 Jul 2018 17:46:21 -0700
Subject: tcp: add data bytes sent stats

Introduce a new TCP stat to record the number of bytes sent
(RFC4898 tcpEStatsPerfHCDataOctetsOut) and expose it in both tcp_info
(TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS).

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      | 3 +++
 include/uapi/linux/tcp.h | 4 +++-
 net/ipv4/tcp.c           | 6 ++++++
 net/ipv4/tcp_output.c    | 1 +
 4 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 58a8d7d71354..d0798dcd2cab 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -181,6 +181,9 @@ struct tcp_sock {
 	u32	data_segs_out;	/* RFC4898 tcpEStatsPerfDataSegsOut
 				 * total number of data segments sent.
 				 */
+	u64	bytes_sent;	/* RFC4898 tcpEStatsPerfHCDataOctetsOut
+				 * total number of data bytes sent.
+				 */
 	u64	bytes_acked;	/* RFC4898 tcpEStatsAppHCThruOctetsAcked
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index e3f6ed8a7064..1c70ed287c3b 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -235,6 +235,8 @@ struct tcp_info {
 
 	__u32	tcpi_delivered;
 	__u32	tcpi_delivered_ce;
+
+	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -257,7 +259,7 @@ enum {
 	TCP_NLA_SND_SSTHRESH,	/* Slow start size threshold */
 	TCP_NLA_DELIVERED,	/* Data pkts delivered incl. out-of-order */
 	TCP_NLA_DELIVERED_CE,	/* Like above but only ones w/ CE marks */
-
+	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 27bbe6a792b7..873cb9968ff5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2594,6 +2594,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	sk->sk_rx_dst = NULL;
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
+	tp->bytes_sent = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3201,6 +3202,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_delivery_rate = rate64;
 	info->tcpi_delivered = tp->delivered;
 	info->tcpi_delivered_ce = tp->delivered_ce;
+	info->tcpi_bytes_sent = tp->bytes_sent;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3225,6 +3227,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_SND_SSTHRESH */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
 		0;
 }
 
@@ -3272,6 +3275,9 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una);
 	nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state);
 
+	nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent,
+			  TCP_NLA_PAD);
+
 	return stats;
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 490df62f26d4..861531fe0e97 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1136,6 +1136,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	if (skb->len != tcp_header_size) {
 		tcp_event_data_sent(tp, sk);
 		tp->data_segs_out += tcp_skb_pcount(skb);
+		tp->bytes_sent += skb->len - tcp_header_size;
 		tcp_internal_pacing(sk, skb);
 	}
 
-- 
cgit v1.2.3


From fb31c9b9f6c85b1bad569ecedbde78d9e37cd87b Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 31 Jul 2018 17:46:22 -0700
Subject: tcp: add data bytes retransmitted stats

Introduce a new TCP stat to record the number of bytes retransmitted
(RFC4898 tcpEStatsPerfOctetsRetrans) and expose it in both tcp_info
(TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS).

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      | 3 +++
 include/uapi/linux/tcp.h | 2 ++
 net/ipv4/tcp.c           | 5 +++++
 net/ipv4/tcp_output.c    | 1 +
 4 files changed, 11 insertions(+)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index d0798dcd2cab..fb67f9a51b95 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -333,6 +333,9 @@ struct tcp_sock {
 				 * the first SYN. */
 	u32	undo_marker;	/* snd_una upon a new recovery episode. */
 	int	undo_retrans;	/* number of undoable retransmissions. */
+	u64	bytes_retrans;	/* RFC4898 tcpEStatsPerfOctetsRetrans
+				 * Total data bytes retransmitted
+				 */
 	u32	total_retrans;	/* Total retransmits for entire connection */
 
 	u32	urg_seq;	/* Seq of received urgent pointer */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 1c70ed287c3b..c31f5100b744 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -237,6 +237,7 @@ struct tcp_info {
 	__u32	tcpi_delivered_ce;
 
 	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
+	__u64	tcpi_bytes_retrans;  /* RFC4898 tcpEStatsPerfOctetsRetrans */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -260,6 +261,7 @@ enum {
 	TCP_NLA_DELIVERED,	/* Data pkts delivered incl. out-of-order */
 	TCP_NLA_DELIVERED_CE,	/* Like above but only ones w/ CE marks */
 	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
+	TCP_NLA_BYTES_RETRANS,	/* Data bytes retransmitted */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 873cb9968ff5..5ed1be88e922 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2595,6 +2595,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tcp_saved_syn_free(tp);
 	tp->compressed_ack = 0;
 	tp->bytes_sent = 0;
+	tp->bytes_retrans = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3203,6 +3204,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_delivered = tp->delivered;
 	info->tcpi_delivered_ce = tp->delivered_ce;
 	info->tcpi_bytes_sent = tp->bytes_sent;
+	info->tcpi_bytes_retrans = tp->bytes_retrans;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3228,6 +3230,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
+		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
 		0;
 }
 
@@ -3277,6 +3280,8 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 
 	nla_put_u64_64bit(stats, TCP_NLA_BYTES_SENT, tp->bytes_sent,
 			  TCP_NLA_PAD);
+	nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
+			  TCP_NLA_PAD);
 
 	return stats;
 }
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 861531fe0e97..50cabf7656f3 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2871,6 +2871,7 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
 	tp->total_retrans += segs;
+	tp->bytes_retrans += skb->len;
 
 	/* make sure skb->data is aligned on arches that require it
 	 * and check if ack-trimming & collapsing extended the headroom
-- 
cgit v1.2.3


From 7e10b6554ff2ce7f86d5d3eec3af5db8db482caa Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 31 Jul 2018 17:46:23 -0700
Subject: tcp: add dsack blocks received stats

Introduce a new TCP stat to record the number of DSACK blocks received
(RFC4989 tcpEStatsStackDSACKDups) and expose it in both tcp_info
(TCP_INFO) and opt_stats (SOF_TIMESTAMPING_OPT_STATS).

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      | 3 +++
 include/uapi/linux/tcp.h | 2 ++
 net/ipv4/tcp.c           | 4 ++++
 net/ipv4/tcp_input.c     | 1 +
 4 files changed, 10 insertions(+)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index fb67f9a51b95..da6281c549a5 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -188,6 +188,9 @@ struct tcp_sock {
 				 * sum(delta(snd_una)), or how many bytes
 				 * were acked.
 				 */
+	u32	dsack_dups;	/* RFC4898 tcpEStatsStackDSACKDups
+				 * total number of DSACK blocks received
+				 */
  	u32	snd_una;	/* First byte we want an ack for	*/
  	u32	snd_sml;	/* Last byte of the most recently transmitted small packet */
 	u32	rcv_tstamp;	/* timestamp of last received ACK (for keepalives) */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index c31f5100b744..0e1c0aec0153 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -238,6 +238,7 @@ struct tcp_info {
 
 	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
 	__u64	tcpi_bytes_retrans;  /* RFC4898 tcpEStatsPerfOctetsRetrans */
+	__u32	tcpi_dsack_dups;     /* RFC4898 tcpEStatsStackDSACKDups */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -262,6 +263,7 @@ enum {
 	TCP_NLA_DELIVERED_CE,	/* Like above but only ones w/ CE marks */
 	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
 	TCP_NLA_BYTES_RETRANS,	/* Data bytes retransmitted */
+	TCP_NLA_DSACK_DUPS,	/* DSACK blocks received */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5ed1be88e922..d6232b598cae 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2596,6 +2596,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->compressed_ack = 0;
 	tp->bytes_sent = 0;
 	tp->bytes_retrans = 0;
+	tp->dsack_dups = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3205,6 +3206,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_delivered_ce = tp->delivered_ce;
 	info->tcpi_bytes_sent = tp->bytes_sent;
 	info->tcpi_bytes_retrans = tp->bytes_retrans;
+	info->tcpi_dsack_dups = tp->dsack_dups;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3231,6 +3233,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DELIVERED_CE */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */
 		0;
 }
 
@@ -3282,6 +3285,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 			  TCP_NLA_PAD);
 	nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
 			  TCP_NLA_PAD);
+	nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
 
 	return stats;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d51fa358b2b1..fbc85ff7d71d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -874,6 +874,7 @@ static void tcp_dsack_seen(struct tcp_sock *tp)
 {
 	tp->rx_opt.sack_ok |= TCP_DSACK_SEEN;
 	tp->rack.dsack_seen = 1;
+	tp->dsack_dups++;
 }
 
 /* It's reordering when higher sequence was delivered (i.e. sacked) before
-- 
cgit v1.2.3


From 7ec65372ca534217b53fd208500cf7aac223a383 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Tue, 31 Jul 2018 17:46:24 -0700
Subject: tcp: add stat of data packet reordering events

Introduce a new TCP stats to record the number of reordering events seen
and expose it in both tcp_info (TCP_INFO) and opt_stats
(SOF_TIMESTAMPING_OPT_STATS).
Application can use this stats to track the frequency of the reordering
events in addition to the existing reordering stats which tracks the
magnitude of the latest reordering event.

Note: this new stats tracks reordering events triggered by ACKs, which
could often be fewer than the actual number of packets being delivered
out-of-order.

Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Neal Cardwell <ncardwell@google.com>
Acked-by: Soheil Hassas Yeganeh <soheil@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/tcp.h      | 4 ++--
 include/uapi/linux/tcp.h | 2 ++
 net/ipv4/tcp.c           | 4 ++++
 net/ipv4/tcp_input.c     | 3 ++-
 net/ipv4/tcp_recovery.c  | 2 +-
 5 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index da6281c549a5..263e37271afd 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -220,8 +220,7 @@ struct tcp_sock {
 #define TCP_RACK_RECOVERY_THRESH 16
 		u8 reo_wnd_persist:5, /* No. of recovery since last adj */
 		   dsack_seen:1, /* Whether DSACK seen after last adj */
-		   advanced:1,	 /* mstamp advanced since last lost marking */
-		   reord:1;	 /* reordering detected */
+		   advanced:1;	 /* mstamp advanced since last lost marking */
 	} rack;
 	u16	advmss;		/* Advertised MSS			*/
 	u8	compressed_ack;
@@ -267,6 +266,7 @@ struct tcp_sock {
 	u8	ecn_flags;	/* ECN status bits.			*/
 	u8	keepalive_probes; /* num of allowed keep alive probes	*/
 	u32	reordering;	/* Packet reordering metric.		*/
+	u32	reord_seen;	/* number of data packet reordering events */
 	u32	snd_up;		/* Urgent pointer		*/
 
 /*
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 0e1c0aec0153..e02d31986ff9 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -239,6 +239,7 @@ struct tcp_info {
 	__u64	tcpi_bytes_sent;     /* RFC4898 tcpEStatsPerfHCDataOctetsOut */
 	__u64	tcpi_bytes_retrans;  /* RFC4898 tcpEStatsPerfOctetsRetrans */
 	__u32	tcpi_dsack_dups;     /* RFC4898 tcpEStatsStackDSACKDups */
+	__u32	tcpi_reord_seen;     /* reordering events seen */
 };
 
 /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */
@@ -264,6 +265,7 @@ enum {
 	TCP_NLA_BYTES_SENT,	/* Data bytes sent including retransmission */
 	TCP_NLA_BYTES_RETRANS,	/* Data bytes retransmitted */
 	TCP_NLA_DSACK_DUPS,	/* DSACK blocks received */
+	TCP_NLA_REORD_SEEN,	/* reordering events seen */
 };
 
 /* for TCP_MD5SIG socket option */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d6232b598cae..31fa1c080f28 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2597,6 +2597,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	tp->bytes_sent = 0;
 	tp->bytes_retrans = 0;
 	tp->dsack_dups = 0;
+	tp->reord_seen = 0;
 
 	/* Clean up fastopen related fields */
 	tcp_free_fastopen_req(tp);
@@ -3207,6 +3208,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_bytes_sent = tp->bytes_sent;
 	info->tcpi_bytes_retrans = tp->bytes_retrans;
 	info->tcpi_dsack_dups = tp->dsack_dups;
+	info->tcpi_reord_seen = tp->reord_seen;
 	unlock_sock_fast(sk, slow);
 }
 EXPORT_SYMBOL_GPL(tcp_get_info);
@@ -3234,6 +3236,7 @@ static size_t tcp_opt_stats_get_size(void)
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_SENT */
 		nla_total_size_64bit(sizeof(u64)) + /* TCP_NLA_BYTES_RETRANS */
 		nla_total_size(sizeof(u32)) + /* TCP_NLA_DSACK_DUPS */
+		nla_total_size(sizeof(u32)) + /* TCP_NLA_REORD_SEEN */
 		0;
 }
 
@@ -3286,6 +3289,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk)
 	nla_put_u64_64bit(stats, TCP_NLA_BYTES_RETRANS, tp->bytes_retrans,
 			  TCP_NLA_PAD);
 	nla_put_u32(stats, TCP_NLA_DSACK_DUPS, tp->dsack_dups);
+	nla_put_u32(stats, TCP_NLA_REORD_SEEN, tp->reord_seen);
 
 	return stats;
 }
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index fbc85ff7d71d..3d6156f07a8d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -906,8 +906,8 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
 				       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
 	}
 
-	tp->rack.reord = 1;
 	/* This exciting event is worth to be remembered. 8) */
+	tp->reord_seen++;
 	NET_INC_STATS(sock_net(sk),
 		      ts ? LINUX_MIB_TCPTSREORDER : LINUX_MIB_TCPSACKREORDER);
 }
@@ -1871,6 +1871,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
 
 	tp->reordering = min_t(u32, tp->packets_out + addend,
 			       sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+	tp->reord_seen++;
 	NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
 }
 
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 71593e4400ab..c81aadff769b 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -25,7 +25,7 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!tp->rack.reord) {
+	if (!tp->reord_seen) {
 		/* If reordering has not been observed, be aggressive during
 		 * the recovery or starting the recovery by DUPACK threshold.
 		 */
-- 
cgit v1.2.3


From 84b64de597bcc26549a7cbfe2fa8022bbc142daa Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Mon, 30 Jul 2018 07:07:03 +0000
Subject: thermal: armada: fix copy-paste error in armada_thermal_probe()

The return value from devm_kzalloc() is not checked correctly. The
test is done against a wrong variable. Fix it.

Fixes: e72f03ef2543 ("thermal: armada: use the resource managed registration helper alternative")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Reviewed-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Eduardo Valentin <edubezval@gmail.com>
---
 drivers/thermal/armada_thermal.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/armada_thermal.c b/drivers/thermal/armada_thermal.c
index 4164a5a4e480..2c2f6d93034e 100644
--- a/drivers/thermal/armada_thermal.c
+++ b/drivers/thermal/armada_thermal.c
@@ -611,7 +611,7 @@ static int armada_thermal_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	drvdata = devm_kzalloc(&pdev->dev, sizeof(*drvdata), GFP_KERNEL);
-	if (!priv)
+	if (!drvdata)
 		return -ENOMEM;
 
 	priv->dev = &pdev->dev;
-- 
cgit v1.2.3


From 13dde04f5c436f3b9f50ccfd0784db6db13401f3 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 1 Aug 2018 01:59:56 +0000
Subject: tcp: remove set but not used variable 'skb_size'

Fixes gcc '-Wunused-but-set-variable' warning:

net/ipv4/tcp_output.c: In function 'tcp_collapse_retrans':
net/ipv4/tcp_output.c:2700:6: warning:
 variable 'skb_size' set but not used [-Wunused-but-set-variable]
  int skb_size, next_skb_size;
      ^

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_output.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 50cabf7656f3..597dbd749f05 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2698,9 +2698,8 @@ static bool tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *next_skb = skb_rb_next(skb);
-	int skb_size, next_skb_size;
+	int next_skb_size;
 
-	skb_size = skb->len;
 	next_skb_size = next_skb->len;
 
 	BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1);
-- 
cgit v1.2.3


From ada953de4486a3e2a42c3b8146adb36d0dcbded2 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 19 Apr 2018 16:05:33 +0200
Subject: auxdisplay: simplify getting .drvdata

We should get drvdata from struct device directly. Going via
platform_device is an unneeded step back and forth.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Miguel Ojeda <miguel.ojeda.sandonis@gmail.com>
---
 drivers/auxdisplay/arm-charlcd.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/auxdisplay/arm-charlcd.c b/drivers/auxdisplay/arm-charlcd.c
index 296fb30dfa00..dea031484cc4 100644
--- a/drivers/auxdisplay/arm-charlcd.c
+++ b/drivers/auxdisplay/arm-charlcd.c
@@ -331,8 +331,7 @@ out_no_resource:
 
 static int charlcd_suspend(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct charlcd *lcd = platform_get_drvdata(pdev);
+	struct charlcd *lcd = dev_get_drvdata(dev);
 
 	/* Power the display off */
 	charlcd_4bit_command(lcd, HD_DISPCTRL);
@@ -341,8 +340,7 @@ static int charlcd_suspend(struct device *dev)
 
 static int charlcd_resume(struct device *dev)
 {
-	struct platform_device *pdev = to_platform_device(dev);
-	struct charlcd *lcd = platform_get_drvdata(pdev);
+	struct charlcd *lcd = dev_get_drvdata(dev);
 
 	/* Turn the display back on */
 	charlcd_4bit_command(lcd, HD_DISPCTRL | HD_DISPCTRL_ON);
-- 
cgit v1.2.3


From 1296ee8ffc74fea4350c756f722000211b38400d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 10:04:02 +0800
Subject: ip_gre: remove redundant variables t_hlen

After commit ffc2b6ee4174 ("ip_gre: fix IFLA_MTU ignored on NEWLINK")
variable t_hlen is assigned values that are never read,
hence they are redundant and can be removed.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_gre.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c8ca5d8f0f75..51a5d06085ac 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -985,7 +985,6 @@ static void ipgre_tunnel_setup(struct net_device *dev)
 static void __gre_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel;
-	int t_hlen;
 
 	tunnel = netdev_priv(dev);
 	tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags);
@@ -993,8 +992,6 @@ static void __gre_tunnel_init(struct net_device *dev)
 
 	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
 
-	t_hlen = tunnel->hlen + sizeof(struct iphdr);
-
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
 
@@ -1304,13 +1301,11 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 static int erspan_tunnel_init(struct net_device *dev)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
-	int t_hlen;
 
 	tunnel->tun_hlen = 8;
 	tunnel->parms.iph.protocol = IPPROTO_GRE;
 	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen +
 		       erspan_hdr_len(tunnel->erspan_ver);
-	t_hlen = tunnel->hlen + sizeof(struct iphdr);
 
 	dev->features		|= GRE_FEATURES;
 	dev->hw_features	|= GRE_FEATURES;
-- 
cgit v1.2.3


From bd707f17efc9e5dfc0fd05370cb89d2ee41d3558 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 15:10:37 +0800
Subject: strparser: remove redundant variable 'rd_desc'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Variable 'rd_desc' is being assigned but never used,
so can be removed.

fix this clang warning:
net/strparser/strparser.c:411:20: warning: variable ‘rd_desc’ set but not used [-Wunused-but-set-variable]

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/strparser/strparser.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/net/strparser/strparser.c b/net/strparser/strparser.c
index 3a512936eea9..da1a676860ca 100644
--- a/net/strparser/strparser.c
+++ b/net/strparser/strparser.c
@@ -408,8 +408,6 @@ EXPORT_SYMBOL_GPL(strp_data_ready);
 
 static void do_strp_work(struct strparser *strp)
 {
-	read_descriptor_t rd_desc;
-
 	/* We need the read lock to synchronize with strp_data_ready. We
 	 * need the socket lock for calling strp_read_sock.
 	 */
@@ -421,8 +419,6 @@ static void do_strp_work(struct strparser *strp)
 	if (strp->paused)
 		goto out;
 
-	rd_desc.arg.data = strp;
-
 	if (strp_read_sock(strp) == -ENOMEM)
 		queue_work(strp_wq, &strp->work);
 
-- 
cgit v1.2.3


From 87f70132b08eadc19e5a78e43b814366f9929399 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 15:14:07 +0800
Subject: rds: remove redundant variable 'rds_ibdev'
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Variable 'rds_ibdev' is being assigned but never used,
so can be removed.

fix this clang warning:
 net/rds/ib_send.c:762:24: warning: variable ‘rds_ibdev’ set but not used [-Wunused-but-set-variable]

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_send.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c
index c4cdfe491d96..c8dd3125d398 100644
--- a/net/rds/ib_send.c
+++ b/net/rds/ib_send.c
@@ -759,14 +759,11 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op)
 	struct rds_ib_connection *ic = conn->c_transport_data;
 	struct rds_ib_send_work *send = NULL;
 	struct ib_send_wr *failed_wr;
-	struct rds_ib_device *rds_ibdev;
 	u32 pos;
 	u32 work_alloc;
 	int ret;
 	int nr_sig = 0;
 
-	rds_ibdev = ib_get_client_data(ic->i_cm_id->device, &rds_ib_client);
-
 	work_alloc = rds_ib_ring_alloc(&ic->i_send_ring, 1, &pos);
 	if (work_alloc != 1) {
 		rds_ib_stats_inc(s_ib_tx_ring_full);
-- 
cgit v1.2.3


From 4a62e252e888f67cb87caf36f48338889b0b8a43 Mon Sep 17 00:00:00 2001
From: Huazhong Tan <tanhuazhong@huawei.com>
Date: Wed, 1 Aug 2018 18:27:03 +0800
Subject: net: hns3: fix return value error while hclge_cmd_csq_clean failed

While cleaning the command queue, the value of the HEAD register is not
in the range of next_to_clean and next_to_use, meaning that this value
is invalid. This also means that there is a hardware error and the
hardware will trigger a reset soon. At this time we should return an
error code instead of 0, and HCLGE_STATE_CMD_DISABLE needs to be set to
prevent sending command again.

Fixes: 3ff504908f95 ("net: hns3: fix a dead loop in hclge_cmd_csq_clean")
Signed-off-by: Huazhong Tan <tanhuazhong@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
index 165c3d5e1c4c..ac13cb2b168e 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c
@@ -147,7 +147,12 @@ static int hclge_cmd_csq_clean(struct hclge_hw *hw)
 	if (!is_valid_csq_clean_head(csq, head)) {
 		dev_warn(&hdev->pdev->dev, "wrong cmd head (%d, %d-%d)\n", head,
 			 csq->next_to_use, csq->next_to_clean);
-		return 0;
+		dev_warn(&hdev->pdev->dev,
+			 "Disabling any further commands to IMP firmware\n");
+		set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state);
+		dev_warn(&hdev->pdev->dev,
+			 "IMP firmware watchdog reset soon expected!\n");
+		return -EIO;
 	}
 
 	clean = (head - csq->next_to_clean + csq->desc_num) % csq->desc_num;
@@ -267,10 +272,11 @@ int hclge_cmd_send(struct hclge_hw *hw, struct hclge_desc *desc, int num)
 
 	/* Clean the command send queue */
 	handle = hclge_cmd_csq_clean(hw);
-	if (handle != num) {
+	if (handle < 0)
+		retval = handle;
+	else if (handle != num)
 		dev_warn(&hdev->pdev->dev,
 			 "cleaned %d, need to clean %d\n", handle, num);
-	}
 
 	spin_unlock_bh(&hw->cmq.csq.lock);
 
-- 
cgit v1.2.3


From 3d32f4c548bd8f3af58c59521bee9be127f3e87d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 1 Aug 2018 12:36:55 +0200
Subject: net: sched: change name of zombie chain to "held_by_acts_only"

As mentioned by Cong and Jakub during the review process, it is a bit
odd to sometimes (act flow) create a new chain which would be
immediately a "zombie". So just rename it to "held_by_acts_only".

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Suggested-by: Cong Wang <xiyou.wangcong@gmail.com>
Suggested-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e20aad1987b8..2f78341f2888 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -272,11 +272,10 @@ static void tcf_chain_release_by_act(struct tcf_chain *chain)
 	--chain->action_refcnt;
 }
 
-static bool tcf_chain_is_zombie(struct tcf_chain *chain)
+static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain)
 {
 	/* In case all the references are action references, this
-	 * chain is a zombie and should not be listed in the chain
-	 * dump list.
+	 * chain should not be shown to the user.
 	 */
 	return chain->refcnt == chain->action_refcnt;
 }
@@ -1838,10 +1837,9 @@ replay:
 	chain = tcf_chain_lookup(block, chain_index);
 	if (n->nlmsg_type == RTM_NEWCHAIN) {
 		if (chain) {
-			if (tcf_chain_is_zombie(chain)) {
+			if (tcf_chain_held_by_acts_only(chain)) {
 				/* The chain exists only because there is
-				 * some action referencing it, meaning it
-				 * is a zombie.
+				 * some action referencing it.
 				 */
 				tcf_chain_hold(chain);
 			} else {
@@ -1860,7 +1858,7 @@ replay:
 			}
 		}
 	} else {
-		if (!chain || tcf_chain_is_zombie(chain)) {
+		if (!chain || tcf_chain_held_by_acts_only(chain)) {
 			NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
 			return -EINVAL;
 		}
@@ -1988,7 +1986,7 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb)
 			index++;
 			continue;
 		}
-		if (tcf_chain_is_zombie(chain))
+		if (tcf_chain_held_by_acts_only(chain))
 			continue;
 		err = tc_chain_fill_node(chain, net, skb, block,
 					 NETLINK_CB(cb->skb).portid,
-- 
cgit v1.2.3


From 5368140730e4a67169303edd3a13e31fd9b9d355 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 1 Aug 2018 12:36:56 +0200
Subject: net: sched: fix notifications for action-held chains

Chains that only have action references serve as placeholders.
Until a non-action reference is created, user should not be aware
of the chain. Also he should not receive any notifications about it.
So send notifications for the new chain only in case the chain gets
the first non-action reference. Symmetrically to that, when
the last non-action reference is dropped, send the notification about
deleted chain.

Reported-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>

v1->v2:
- made __tcf_chain_{get,put}() static as suggested by Cong

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 71 ++++++++++++++++++++++++++++++++---------------------
 1 file changed, 43 insertions(+), 28 deletions(-)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 2f78341f2888..b194a5abfc6a 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -262,16 +262,6 @@ static void tcf_chain_hold(struct tcf_chain *chain)
 	++chain->refcnt;
 }
 
-static void tcf_chain_hold_by_act(struct tcf_chain *chain)
-{
-	++chain->action_refcnt;
-}
-
-static void tcf_chain_release_by_act(struct tcf_chain *chain)
-{
-	--chain->action_refcnt;
-}
-
 static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain)
 {
 	/* In case all the references are action references, this
@@ -295,52 +285,77 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block,
 static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb,
 			   u32 seq, u16 flags, int event, bool unicast);
 
-struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
-				bool create)
+static struct tcf_chain *__tcf_chain_get(struct tcf_block *block,
+					 u32 chain_index, bool create,
+					 bool by_act)
 {
 	struct tcf_chain *chain = tcf_chain_lookup(block, chain_index);
 
 	if (chain) {
 		tcf_chain_hold(chain);
-		return chain;
+	} else {
+		if (!create)
+			return NULL;
+		chain = tcf_chain_create(block, chain_index);
+		if (!chain)
+			return NULL;
 	}
 
-	if (!create)
-		return NULL;
-	chain = tcf_chain_create(block, chain_index);
-	if (!chain)
-		return NULL;
-	tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
-			RTM_NEWCHAIN, false);
+	if (by_act)
+		++chain->action_refcnt;
+
+	/* Send notification only in case we got the first
+	 * non-action reference. Until then, the chain acts only as
+	 * a placeholder for actions pointing to it and user ought
+	 * not know about them.
+	 */
+	if (chain->refcnt - chain->action_refcnt == 1 && !by_act)
+		tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL,
+				RTM_NEWCHAIN, false);
+
 	return chain;
 }
+
+struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
+				bool create)
+{
+	return __tcf_chain_get(block, chain_index, create, false);
+}
 EXPORT_SYMBOL(tcf_chain_get);
 
 struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index)
 {
-	struct tcf_chain *chain = tcf_chain_get(block, chain_index, true);
-
-	tcf_chain_hold_by_act(chain);
-	return chain;
+	return __tcf_chain_get(block, chain_index, true, true);
 }
 EXPORT_SYMBOL(tcf_chain_get_by_act);
 
 static void tc_chain_tmplt_del(struct tcf_chain *chain);
 
-void tcf_chain_put(struct tcf_chain *chain)
+static void __tcf_chain_put(struct tcf_chain *chain, bool by_act)
 {
-	if (--chain->refcnt == 0) {
+	if (by_act)
+		chain->action_refcnt--;
+	chain->refcnt--;
+
+	/* The last dropped non-action reference will trigger notification. */
+	if (chain->refcnt - chain->action_refcnt == 0 && !by_act)
 		tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false);
+
+	if (chain->refcnt == 0) {
 		tc_chain_tmplt_del(chain);
 		tcf_chain_destroy(chain);
 	}
 }
+
+void tcf_chain_put(struct tcf_chain *chain)
+{
+	__tcf_chain_put(chain, false);
+}
 EXPORT_SYMBOL(tcf_chain_put);
 
 void tcf_chain_put_by_act(struct tcf_chain *chain)
 {
-	tcf_chain_release_by_act(chain);
-	tcf_chain_put(chain);
+	__tcf_chain_put(chain, true);
 }
 EXPORT_SYMBOL(tcf_chain_put_by_act);
 
-- 
cgit v1.2.3


From 290b1c8b1a902c0902df9ec05577ab209296f345 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 1 Aug 2018 12:36:57 +0200
Subject: net: sched: make tcf_chain_{get,put}() static

These are no longer used outside of cls_api.c so make them static.
Move tcf_chain_flush() to avoid fwd declaration of tcf_chain_put().

Signed-off-by: Jiri Pirko <jiri@mellanox.com>

v1->v2:
- new patch

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/pkt_cls.h |  3 ---
 net/sched/cls_api.c   | 34 ++++++++++++++++------------------
 2 files changed, 16 insertions(+), 21 deletions(-)

diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
index 22bfc3a13c25..ef727f71336e 100644
--- a/include/net/pkt_cls.h
+++ b/include/net/pkt_cls.h
@@ -40,11 +40,8 @@ struct tcf_block_cb;
 bool tcf_queue_work(struct rcu_work *rwork, work_func_t func);
 
 #ifdef CONFIG_NET_CLS
-struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
-				bool create);
 struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block,
 				       u32 chain_index);
-void tcf_chain_put(struct tcf_chain *chain);
 void tcf_chain_put_by_act(struct tcf_chain *chain);
 void tcf_block_netif_keep_dst(struct tcf_block *block);
 int tcf_block_get(struct tcf_block **p_block,
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index b194a5abfc6a..e8b0bbd0883f 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -232,19 +232,6 @@ static void tcf_chain0_head_change(struct tcf_chain *chain,
 		tcf_chain_head_change_item(item, tp_head);
 }
 
-static void tcf_chain_flush(struct tcf_chain *chain)
-{
-	struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);
-
-	tcf_chain0_head_change(chain, NULL);
-	while (tp) {
-		RCU_INIT_POINTER(chain->filter_chain, tp->next);
-		tcf_proto_destroy(tp, NULL);
-		tp = rtnl_dereference(chain->filter_chain);
-		tcf_chain_put(chain);
-	}
-}
-
 static void tcf_chain_destroy(struct tcf_chain *chain)
 {
 	struct tcf_block *block = chain->block;
@@ -316,12 +303,11 @@ static struct tcf_chain *__tcf_chain_get(struct tcf_block *block,
 	return chain;
 }
 
-struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
-				bool create)
+static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index,
+				       bool create)
 {
 	return __tcf_chain_get(block, chain_index, create, false);
 }
-EXPORT_SYMBOL(tcf_chain_get);
 
 struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index)
 {
@@ -347,11 +333,10 @@ static void __tcf_chain_put(struct tcf_chain *chain, bool by_act)
 	}
 }
 
-void tcf_chain_put(struct tcf_chain *chain)
+static void tcf_chain_put(struct tcf_chain *chain)
 {
 	__tcf_chain_put(chain, false);
 }
-EXPORT_SYMBOL(tcf_chain_put);
 
 void tcf_chain_put_by_act(struct tcf_chain *chain)
 {
@@ -365,6 +350,19 @@ static void tcf_chain_put_explicitly_created(struct tcf_chain *chain)
 		tcf_chain_put(chain);
 }
 
+static void tcf_chain_flush(struct tcf_chain *chain)
+{
+	struct tcf_proto *tp = rtnl_dereference(chain->filter_chain);
+
+	tcf_chain0_head_change(chain, NULL);
+	while (tp) {
+		RCU_INIT_POINTER(chain->filter_chain, tp->next);
+		tcf_proto_destroy(tp, NULL);
+		tp = rtnl_dereference(chain->filter_chain);
+		tcf_chain_put(chain);
+	}
+}
+
 static bool tcf_block_offload_in_use(struct tcf_block *block)
 {
 	return block->offloadcnt;
-- 
cgit v1.2.3


From 90d4c5bb98bf66653333266917edf0e16ccd35f9 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Wed, 1 Aug 2018 18:15:32 +0530
Subject: cxgb4: fix endian to test F_FW_PORT_CMD_DCBXDIS32

For FW_PORT_ACTION_GET_PORT_INFO32 messages, the
u.info32.lstatus32_to_cbllen32 is 32-bit Big Endian.
We need to translate that to CPU Endian in order to
test F_FW_PORT_CMD_DCBXDIS32.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 40cf8dc9f163..674997d30cfd 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -554,10 +554,9 @@ static int fwevtq_handler(struct sge_rspq *q, const __be64 *rsp,
 
 			dev = q->adap->port[q->adap->chan_map[port]];
 			dcbxdis = (action == FW_PORT_ACTION_GET_PORT_INFO
-				   ? !!(pcmd->u.info.dcbxdis_pkd &
-					FW_PORT_CMD_DCBXDIS_F)
-				   : !!(pcmd->u.info32.lstatus32_to_cbllen32 &
-					FW_PORT_CMD_DCBXDIS32_F));
+			  ? !!(pcmd->u.info.dcbxdis_pkd & FW_PORT_CMD_DCBXDIS_F)
+			  : !!(be32_to_cpu(pcmd->u.info32.lstatus32_to_cbllen32)
+			       & FW_PORT_CMD_DCBXDIS32_F));
 			state_input = (dcbxdis
 				       ? CXGB4_DCB_INPUT_FW_DISABLED
 				       : CXGB4_DCB_INPUT_FW_ENABLED);
-- 
cgit v1.2.3


From d5e77fca87e636dda510710689b4c2ca93765598 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 11:14:16 -0500
Subject: ALSA: usb: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115084 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/pcm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/pcm.c b/sound/usb/pcm.c
index bbc7116c9543..382847154227 100644
--- a/sound/usb/pcm.c
+++ b/sound/usb/pcm.c
@@ -1694,6 +1694,7 @@ static int snd_usb_substream_playback_trigger(struct snd_pcm_substream *substrea
 	switch (cmd) {
 	case SNDRV_PCM_TRIGGER_START:
 		subs->trigger_tstamp_pending_update = true;
+		/* fall through */
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 		subs->data_endpoint->prepare_data_urb = prepare_playback_urb;
 		subs->data_endpoint->retire_data_urb = retire_playback_urb;
-- 
cgit v1.2.3


From b912885ab75c7c8aa841c615108afd755d0b97f8 Mon Sep 17 00:00:00 2001
From: Arnaldo Carvalho de Melo <acme@redhat.com>
Date: Wed, 1 Aug 2018 16:20:28 -0300
Subject: perf trace: Do not require --no-syscalls to suppress strace like
 output

So far the --syscalls option was the default, requiring explicit
--no-syscalls when wanting to process just some other event, invert that
and assume it only when no other event was specified, allowing its
explicit enablement when wanting to see all syscalls together with some
other event:

E.g:

The existing default is maintained for a single workload:

  # perf trace sleep 1
<SNIP>
     0.264 ( 0.003 ms): sleep/12762 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7f62cbf04000
     0.271 ( 0.001 ms): sleep/12762 close(fd: 3) = 0
     0.295 (1000.130 ms): sleep/12762 nanosleep(rqtp: 0x7ffd15194fd0) = 0
  1000.469 ( 0.006 ms): sleep/12762 close(fd: 1) = 0
  1000.480 ( 0.004 ms): sleep/12762 close(fd: 2) = 0
  1000.502 (         ): sleep/12762 exit_group()
  #

For a pid:

  # pidof ssh
  7826 3961 3226 2628 2493
  # perf trace -p 3961
         ? (         ):  ... [continued]: select()) = 1
     0.023 ( 0.005 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce870               ) = 0
     0.036 ( 0.009 ms): read(fd: 5</dev/pts/7>, buf: 0x7ffcc8fca7b0, count: 16384             ) = 3
     0.060 ( 0.004 ms): getpid(                                                               ) = 3961 (ssh)
     0.079 ( 0.004 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce8e0               ) = 0
     0.088 ( 0.003 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce7c0               ) = 0
<SNIP>

For system wide, threads, cgroups, user, etc when no event is specified,
the existing behaviour is maintained, i.e. --syscalls is selected.

When some event is specified, then --no-syscalls doesn't need to be
specified:

  # perf trace -e tcp:tcp_probe ssh localhost
     0.000 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=53 snd_nxt=0xb67ce8f7 snd_una=0xb67ce8f7 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43690
     0.010 tcp:tcp_probe:src=[::1]:39074 dest=[::1]:22 mark=0 length=32 snd_nxt=0xa8f9ef38 snd_una=0xa8f9ef23 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43690 srtt=31 rcv_wnd=43776
     4.525 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=1240 snd_nxt=0xb67ce90c snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43776
     7.242 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=80 snd_nxt=0xb67ced44 snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=174720
  The authenticity of host 'localhost (::1)' can't be established.
  ECDSA key fingerprint is SHA256:TKZS58923458203490asekfjaklskljmkjfgPMBfHzY.
  ECDSA key fingerprint is MD5:d8:29:54:40:71:fa:b8:44:89:52:64:8a:35:42:d0:e8.
  Are you sure you want to continue connecting (yes/no)?
^C
  #

To get the previous behaviour just use --syscalls and get all syscalls formatted
strace like + the specified extra events:

  # trace -e sched:*switch --syscalls sleep 1
  <SNIP>
     0.160 ( 0.003 ms): sleep/12877 mprotect(start: 0x7fdfe2361000, len: 4096, prot: READ) = 0
     0.164 ( 0.009 ms): sleep/12877 munmap(addr: 0x7fdfe2345000, len: 113155) = 0
     0.211 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce68e000
     0.212 ( 0.002 ms): sleep/12877 brk(brk: 0x55d3ce6af000) = 0x55d3ce6af000
     0.215 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce6af000
     0.219 ( 0.004 ms): sleep/12877 open(filename: 0xe1f07c00, flags: CLOEXEC) = 3
     0.225 ( 0.001 ms): sleep/12877 fstat(fd: 3, statbuf: 0x7fdfe2138aa0) = 0
     0.227 ( 0.003 ms): sleep/12877 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7fdfdb1b8000
     0.234 ( 0.001 ms): sleep/12877 close(fd: 3) = 0
     0.257 (         ): sleep/12877 nanosleep(rqtp: 0x7fffb36b6020) ...
     0.260 (         ): sched:sched_switch:prev_comm=sleep prev_pid=12877 prev_prio=120 prev_state=D ==> next_comm=swapper/3 next_pid=0 next_prio=120
     0.257 (1000.134 ms): sleep/12877  ... [continued]: nanosleep()) = 0
  1000.428 ( 0.006 ms): sleep/12877 close(fd: 1) = 0
  1000.440 ( 0.004 ms): sleep/12877 close(fd: 2) = 0
  1000.461 (         ): sleep/12877 exit_group()
  #

When specifiying just some syscalls, the behaviour doesn't change, i.e.:

  # trace -e nanosleep -e sched:*switch sleep 1
     0.000 (         ): sleep/14974 nanosleep(rqtp: 0x7ffc344ba9c0                                        ) ...
     0.007 (         ): sched:sched_switch:prev_comm=sleep prev_pid=14974 prev_prio=120 prev_state=D ==> next_comm=swapper/2 next_pid=0 next_prio=120
     0.000 (1000.139 ms): sleep/14974  ... [continued]: nanosleep()) = 0
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-om2fulll97ytnxv40ler8jkf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/builtin-trace.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 9aca65e6b9aa..88561eed7950 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -2992,6 +2992,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
 
 		if (trace__validate_ev_qualifier(trace))
 			goto out;
+		trace->trace_syscalls = true;
 	}
 
 	err = 0;
@@ -3047,7 +3048,7 @@ int cmd_trace(int argc, const char **argv)
 		},
 		.output = stderr,
 		.show_comm = true,
-		.trace_syscalls = true,
+		.trace_syscalls = false,
 		.kernel_syscallchains = false,
 		.max_stack = UINT_MAX,
 	};
@@ -3193,13 +3194,7 @@ int cmd_trace(int argc, const char **argv)
 
 	if (!trace.trace_syscalls && !trace.trace_pgfaults &&
 	    trace.evlist->nr_entries == 0 /* Was --events used? */) {
-		pr_err("Please specify something to trace.\n");
-		return -1;
-	}
-
-	if (!trace.trace_syscalls && trace.ev_qualifier) {
-		pr_err("The -e option can't be used with --no-syscalls.\n");
-		goto out;
+		trace.trace_syscalls = true;
 	}
 
 	if (output_name != NULL) {
-- 
cgit v1.2.3


From 96a68b14db358c310e1c5cc5229752845192c1fa Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Wed, 1 Aug 2018 13:12:42 -0700
Subject: MIPS: Remove nabi_no_regargs

Our sigreturn functions make use of a macro named nabi_no_regargs to
declare 8 dummy arguments to a function, forcing the compiler to expect
a pt_regs structure on the stack rather than in argument registers. This
is an ugly hack which unnecessarily causes these sigreturn functions to
need to care about the calling convention of the ABI the kernel is built
for. Although this is abstracted via nabi_no_regargs, it's still ugly &
unnecessary.

Remove nabi_no_regargs & the struct pt_regs argument from sigreturn
functions, and instead use current_pt_regs() to find the struct pt_regs
on the stack, which works cleanly regardless of ABI.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20106/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/sim.h   | 12 ------------
 arch/mips/kernel/signal.c     | 24 ++++++++++++++----------
 arch/mips/kernel/signal_n32.c | 12 +++++++-----
 arch/mips/kernel/signal_o32.c | 24 ++++++++++++++----------
 4 files changed, 35 insertions(+), 37 deletions(-)

diff --git a/arch/mips/include/asm/sim.h b/arch/mips/include/asm/sim.h
index 91831800c480..59f31a95facd 100644
--- a/arch/mips/include/asm/sim.h
+++ b/arch/mips/include/asm/sim.h
@@ -39,8 +39,6 @@ __asm__(								\
 	".end\t__" #symbol "\n\t"					\
 	".size\t__" #symbol",. - __" #symbol)
 
-#define nabi_no_regargs
-
 #endif /* CONFIG_32BIT */
 
 #ifdef CONFIG_64BIT
@@ -67,16 +65,6 @@ __asm__(								\
 	".end\t__" #symbol "\n\t"					\
 	".size\t__" #symbol",. - __" #symbol)
 
-#define nabi_no_regargs							\
-	unsigned long __dummy0,						\
-	unsigned long __dummy1,						\
-	unsigned long __dummy2,						\
-	unsigned long __dummy3,						\
-	unsigned long __dummy4,						\
-	unsigned long __dummy5,						\
-	unsigned long __dummy6,						\
-	unsigned long __dummy7,
-
 #endif /* CONFIG_64BIT */
 
 #endif /* _ASM_SIM_H */
diff --git a/arch/mips/kernel/signal.c b/arch/mips/kernel/signal.c
index 00f2535d2226..ed6023a74f77 100644
--- a/arch/mips/kernel/signal.c
+++ b/arch/mips/kernel/signal.c
@@ -592,13 +592,15 @@ SYSCALL_DEFINE3(sigaction, int, sig, const struct sigaction __user *, act,
 #endif
 
 #ifdef CONFIG_TRAD_SIGNALS
-asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_sigreturn(void)
 {
 	struct sigframe __user *frame;
+	struct pt_regs *regs;
 	sigset_t blocked;
 	int sig;
 
-	frame = (struct sigframe __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct sigframe __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&blocked, &frame->sf_mask, sizeof(blocked)))
@@ -606,7 +608,7 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&blocked);
 
-	sig = restore_sigcontext(&regs, &frame->sf_sc);
+	sig = restore_sigcontext(regs, &frame->sf_sc);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -618,8 +620,8 @@ asmlinkage void sys_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
@@ -627,13 +629,15 @@ badframe:
 }
 #endif /* CONFIG_TRAD_SIGNALS */
 
-asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys_rt_sigreturn(void)
 {
 	struct rt_sigframe __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_from_user(&set, &frame->rs_uc.uc_sigmask, sizeof(set)))
@@ -641,7 +645,7 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -656,8 +660,8 @@ asmlinkage void sys_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
diff --git a/arch/mips/kernel/signal_n32.c b/arch/mips/kernel/signal_n32.c
index b672cebb4a1a..8f65aaf9206d 100644
--- a/arch/mips/kernel/signal_n32.c
+++ b/arch/mips/kernel/signal_n32.c
@@ -64,13 +64,15 @@ struct rt_sigframe_n32 {
 	struct ucontextn32 rs_uc;
 };
 
-asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sysn32_rt_sigreturn(void)
 {
 	struct rt_sigframe_n32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe_n32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe_n32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
@@ -78,7 +80,7 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -93,8 +95,8 @@ asmlinkage void sysn32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
diff --git a/arch/mips/kernel/signal_o32.c b/arch/mips/kernel/signal_o32.c
index 2b3572fb5f1b..b6e3ddef48a0 100644
--- a/arch/mips/kernel/signal_o32.c
+++ b/arch/mips/kernel/signal_o32.c
@@ -151,13 +151,15 @@ static int setup_frame_32(void *sig_return, struct ksignal *ksig,
 	return 0;
 }
 
-asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_rt_sigreturn(void)
 {
 	struct rt_sigframe32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t set;
 	int sig;
 
-	frame = (struct rt_sigframe32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct rt_sigframe32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&set, &frame->rs_uc.uc_sigmask))
@@ -165,7 +167,7 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&set);
 
-	sig = restore_sigcontext32(&regs, &frame->rs_uc.uc_mcontext);
+	sig = restore_sigcontext32(regs, &frame->rs_uc.uc_mcontext);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -180,8 +182,8 @@ asmlinkage void sys32_rt_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
@@ -251,13 +253,15 @@ struct mips_abi mips_abi_32 = {
 };
 
 
-asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
+asmlinkage void sys32_sigreturn(void)
 {
 	struct sigframe32 __user *frame;
+	struct pt_regs *regs;
 	sigset_t blocked;
 	int sig;
 
-	frame = (struct sigframe32 __user *) regs.regs[29];
+	regs = current_pt_regs();
+	frame = (struct sigframe32 __user *)regs->regs[29];
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
 	if (__copy_conv_sigset_from_user(&blocked, &frame->sf_mask))
@@ -265,7 +269,7 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
 
 	set_current_blocked(&blocked);
 
-	sig = restore_sigcontext32(&regs, &frame->sf_sc);
+	sig = restore_sigcontext32(regs, &frame->sf_sc);
 	if (sig < 0)
 		goto badframe;
 	else if (sig)
@@ -277,8 +281,8 @@ asmlinkage void sys32_sigreturn(nabi_no_regargs struct pt_regs regs)
 	__asm__ __volatile__(
 		"move\t$29, %0\n\t"
 		"j\tsyscall_exit"
-		:/* no outputs */
-		:"r" (&regs));
+		: /* no outputs */
+		: "r" (regs));
 	/* Unreached */
 
 badframe:
-- 
cgit v1.2.3


From 3a1c0fc5927f001d2c70998c08cad42ee5f64849 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Wed, 1 Aug 2018 13:15:17 -0700
Subject: MIPS: Remove unused sys_32_mmap2

The sys_32_mmap2 function has been unused since we started using syscall
wrappers in commit dbda6ac08976 ("MIPS: CVE-2009-0029: Enable syscall
wrappers."), and is indeed identical to the sys_mips_mmap2 function that
replaced it in sys32_call_table.

Remove the dead code.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20107/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/kernel/linux32.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 318f1c05c5b3..d41855927996 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -61,16 +61,6 @@
 #define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL))
 #endif
 
-SYSCALL_DEFINE6(32_mmap2, unsigned long, addr, unsigned long, len,
-	unsigned long, prot, unsigned long, flags, unsigned long, fd,
-	unsigned long, pgoff)
-{
-	if (pgoff & (~PAGE_MASK >> 12))
-		return -EINVAL;
-	return ksys_mmap_pgoff(addr, len, prot, flags, fd,
-			       pgoff >> (PAGE_SHIFT-12));
-}
-
 #define RLIM_INFINITY32 0x7fffffff
 #define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x)
 
-- 
cgit v1.2.3


From 48ae93fdd133849cf8e0a46a525cb09229933c8b Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Wed, 1 Aug 2018 13:15:18 -0700
Subject: MIPS: Delete unused code in linux32.c

The A() & AA() macros have been unused since commit 05e4396651ca
("[MIPS] Use SYSVIPC_COMPAT to fix various problems on N32"), which
switched to the more standard compat_ptr().

RLIM_INFINITY32, RESOURCE32() & struct rlimit32 have been present but
unused since the beginning of the git era.

Remove the dead code.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20108/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/kernel/linux32.c | 19 -------------------
 1 file changed, 19 deletions(-)

diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index d41855927996..6b61be486303 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -43,17 +43,6 @@
 #include <asm/mmu_context.h>
 #include <asm/mman.h>
 
-/* Use this to get at 32-bit user passed pointers. */
-/* A() macro should be used for places where you e.g.
-   have some internal variable u32 and just want to get
-   rid of a compiler warning. AA() has to be used in
-   places where you want to convert a function argument
-   to 32bit pointer or when you e.g. access pt_regs
-   structure and want to consider 32bit registers only.
- */
-#define A(__x) ((unsigned long)(__x))
-#define AA(__x) ((unsigned long)((int)__x))
-
 #ifdef __MIPSEB__
 #define merge_64(r1, r2) ((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL))
 #endif
@@ -61,14 +50,6 @@
 #define merge_64(r1, r2) ((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL))
 #endif
 
-#define RLIM_INFINITY32 0x7fffffff
-#define RESOURCE32(x) ((x > RLIM_INFINITY32) ? RLIM_INFINITY32 : x)
-
-struct rlimit32 {
-	int	rlim_cur;
-	int	rlim_max;
-};
-
 SYSCALL_DEFINE4(32_truncate64, const char __user *, path,
 	unsigned long, __dummy, unsigned long, a2, unsigned long, a3)
 {
-- 
cgit v1.2.3


From db57dc7c7a5c42bb653425a01b6d73c49514b5db Mon Sep 17 00:00:00 2001
From: Vincent Bernat <vincent@bernat.im>
Date: Wed, 1 Aug 2018 22:05:10 +0200
Subject: net: don't declare IPv6 non-local bind helper if CONFIG_IPV6
 undefined

Fixes: 83ba4645152d ("net: add helpers checking if socket can be bound to nonlocal address")
Signed-off-by: Vincent Bernat <vincent@bernat.im>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/ipv6.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 82deb684ba73..ff33f498c137 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -766,13 +766,6 @@ static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6,
 	return hlimit;
 }
 
-static inline bool ipv6_can_nonlocal_bind(struct net *net,
-					  struct inet_sock *inet)
-{
-	return net->ipv6.sysctl.ip_nonlocal_bind ||
-		inet->freebind || inet->transparent;
-}
-
 /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store
  * Equivalent to :	flow->v6addrs.src = iph->saddr;
  *			flow->v6addrs.dst = iph->daddr;
@@ -789,6 +782,13 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow,
 
 #if IS_ENABLED(CONFIG_IPV6)
 
+static inline bool ipv6_can_nonlocal_bind(struct net *net,
+					  struct inet_sock *inet)
+{
+	return net->ipv6.sysctl.ip_nonlocal_bind ||
+		inet->freebind || inet->transparent;
+}
+
 /* Sysctl settings for net ipv6.auto_flowlabels */
 #define IP6_AUTO_FLOW_LABEL_OFF		0
 #define IP6_AUTO_FLOW_LABEL_OPTOUT	1
-- 
cgit v1.2.3


From ef965ad5a7697ff16e3be01954f5c57208e36c22 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 1 Aug 2018 14:38:18 +0200
Subject: ALSA: seq: Minor cleanup of MIDI event parser helpers

snd_midi_event_encode_byte() can never fail, and it can return rather
true/false.  Change the return type to bool, adjust the argument to
receive a MIDI byte as unsigned char, and adjust the comment
accordingly.  This allows callers to drop error checks, which
simplifies the code.

Meanwhile, snd_midi_event_encode() helper is used only in seq_midi.c,
and it can be better folded into it.  This will reduce the total
amount of lines in the end.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 include/sound/seq_midi_event.h    |  6 ++----
 sound/core/seq/oss/seq_oss_midi.c |  2 +-
 sound/core/seq/seq_midi.c         | 24 ++++++++++------------
 sound/core/seq/seq_midi_event.c   | 42 +++++++--------------------------------
 sound/core/seq/seq_virmidi.c      |  4 ++--
 5 files changed, 22 insertions(+), 56 deletions(-)

diff --git a/include/sound/seq_midi_event.h b/include/sound/seq_midi_event.h
index e40f43e6fc7b..2f135bccf457 100644
--- a/include/sound/seq_midi_event.h
+++ b/include/sound/seq_midi_event.h
@@ -43,10 +43,8 @@ void snd_midi_event_free(struct snd_midi_event *dev);
 void snd_midi_event_reset_encode(struct snd_midi_event *dev);
 void snd_midi_event_reset_decode(struct snd_midi_event *dev);
 void snd_midi_event_no_status(struct snd_midi_event *dev, int on);
-/* encode from byte stream - return number of written bytes if success */
-long snd_midi_event_encode(struct snd_midi_event *dev, unsigned char *buf, long count,
-			   struct snd_seq_event *ev);
-int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c, struct snd_seq_event *ev);
+bool snd_midi_event_encode_byte(struct snd_midi_event *dev, unsigned char c,
+				struct snd_seq_event *ev);
 /* decode from event to bytes - return number of written bytes if success */
 long snd_midi_event_decode(struct snd_midi_event *dev, unsigned char *buf, long count,
 			   struct snd_seq_event *ev);
diff --git a/sound/core/seq/oss/seq_oss_midi.c b/sound/core/seq/oss/seq_oss_midi.c
index 9debd1b8fd28..0d5f8b16d057 100644
--- a/sound/core/seq/oss/seq_oss_midi.c
+++ b/sound/core/seq/oss/seq_oss_midi.c
@@ -637,7 +637,7 @@ snd_seq_oss_midi_putc(struct seq_oss_devinfo *dp, int dev, unsigned char c, stru
 
 	if ((mdev = get_mididev(dp, dev)) == NULL)
 		return -ENODEV;
-	if (snd_midi_event_encode_byte(mdev->coder, c, ev) > 0) {
+	if (snd_midi_event_encode_byte(mdev->coder, c, ev)) {
 		snd_seq_oss_fill_addr(dp, ev, mdev->client, mdev->port);
 		snd_use_lock_free(&mdev->use_lock);
 		return 0;
diff --git a/sound/core/seq/seq_midi.c b/sound/core/seq/seq_midi.c
index 5dd0ee258359..9e0dabd3ce5f 100644
--- a/sound/core/seq/seq_midi.c
+++ b/sound/core/seq/seq_midi.c
@@ -78,7 +78,7 @@ static void snd_midi_input_event(struct snd_rawmidi_substream *substream)
 	struct seq_midisynth *msynth;
 	struct snd_seq_event ev;
 	char buf[16], *pbuf;
-	long res, count;
+	long res;
 
 	if (substream == NULL)
 		return;
@@ -94,19 +94,15 @@ static void snd_midi_input_event(struct snd_rawmidi_substream *substream)
 		if (msynth->parser == NULL)
 			continue;
 		pbuf = buf;
-		while (res > 0) {
-			count = snd_midi_event_encode(msynth->parser, pbuf, res, &ev);
-			if (count < 0)
-				break;
-			pbuf += count;
-			res -= count;
-			if (ev.type != SNDRV_SEQ_EVENT_NONE) {
-				ev.source.port = msynth->seq_port;
-				ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS;
-				snd_seq_kernel_client_dispatch(msynth->seq_client, &ev, 1, 0);
-				/* clear event and reset header */
-				memset(&ev, 0, sizeof(ev));
-			}
+		while (res-- > 0) {
+			if (!snd_midi_event_encode_byte(msynth->parser,
+							*pbuf++, &ev))
+				continue;
+			ev.source.port = msynth->seq_port;
+			ev.dest.client = SNDRV_SEQ_ADDRESS_SUBSCRIBERS;
+			snd_seq_kernel_client_dispatch(msynth->seq_client, &ev, 1, 0);
+			/* clear event and reset header */
+			memset(&ev, 0, sizeof(ev));
 		}
 	}
 }
diff --git a/sound/core/seq/seq_midi_event.c b/sound/core/seq/seq_midi_event.c
index 90bbbdbeba03..53c0dfab90d6 100644
--- a/sound/core/seq/seq_midi_event.c
+++ b/sound/core/seq/seq_midi_event.c
@@ -214,45 +214,17 @@ int snd_midi_event_resize_buffer(struct snd_midi_event *dev, int bufsize)
 }
 #endif  /*  0  */
 
-/*
- *  read bytes and encode to sequencer event if finished
- *  return the size of encoded bytes
- */
-long snd_midi_event_encode(struct snd_midi_event *dev, unsigned char *buf, long count,
-			   struct snd_seq_event *ev)
-{
-	long result = 0;
-	int rc;
-
-	ev->type = SNDRV_SEQ_EVENT_NONE;
-
-	while (count-- > 0) {
-		rc = snd_midi_event_encode_byte(dev, *buf++, ev);
-		result++;
-		if (rc < 0)
-			return rc;
-		else if (rc > 0)
-			return result;
-	}
-
-	return result;
-}
-EXPORT_SYMBOL(snd_midi_event_encode);
-
 /*
  *  read one byte and encode to sequencer event:
- *  return 1 if MIDI bytes are encoded to an event
- *         0 data is not finished
- *         negative for error
+ *  return true if MIDI bytes are encoded to an event
+ *         false data is not finished
  */
-int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c,
-			       struct snd_seq_event *ev)
+bool snd_midi_event_encode_byte(struct snd_midi_event *dev, unsigned char c,
+				struct snd_seq_event *ev)
 {
-	int rc = 0;
+	bool rc = false;
 	unsigned long flags;
 
-	c &= 0xff;
-
 	if (c >= MIDI_CMD_COMMON_CLOCK) {
 		/* real-time event */
 		ev->type = status_event[ST_SPECIAL + c - 0xf0].event;
@@ -293,7 +265,7 @@ int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c,
 			status_event[dev->type].encode(dev, ev);
 		if (dev->type >= ST_SPECIAL)
 			dev->type = ST_INVALID;
-		rc = 1;
+		rc = true;
 	} else 	if (dev->type == ST_SYSEX) {
 		if (c == MIDI_CMD_COMMON_SYSEX_END ||
 		    dev->read >= dev->bufsize) {
@@ -306,7 +278,7 @@ int snd_midi_event_encode_byte(struct snd_midi_event *dev, int c,
 				dev->read = 0; /* continue to parse */
 			else
 				reset_encode(dev); /* all parsed */
-			rc = 1;
+			rc = true;
 		}
 	}
 
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 03ac5e72dbe6..0c84926eb726 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -174,8 +174,8 @@ static void snd_vmidi_output_work(struct work_struct *work)
 	while (READ_ONCE(vmidi->trigger)) {
 		if (snd_rawmidi_transmit(substream, &input, 1) != 1)
 			break;
-		if (snd_midi_event_encode_byte(vmidi->parser, input,
-					       &vmidi->event) <= 0)
+		if (!snd_midi_event_encode_byte(vmidi->parser, input,
+						&vmidi->event))
 			continue;
 		if (vmidi->event.type != SNDRV_SEQ_EVENT_NONE) {
 			ret = snd_seq_kernel_client_dispatch(vmidi->client,
-- 
cgit v1.2.3


From fc4bfd9a35f3d9cbf5ad6a20faedca71d1d9ed52 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 1 Aug 2018 14:59:07 +0200
Subject: ALSA: seq: Remove dead codes

There are a few functions that have been commented out for ages.
And also there are functions that do nothing but placeholders.
Let's kill them.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq.c            |  7 -------
 sound/core/seq/seq_memory.c     | 12 -----------
 sound/core/seq/seq_memory.h     |  6 ------
 sound/core/seq/seq_midi_emul.c  | 12 -----------
 sound/core/seq/seq_midi_event.c | 45 -----------------------------------------
 sound/core/seq/seq_virmidi.c    | 33 ------------------------------
 6 files changed, 115 deletions(-)

diff --git a/sound/core/seq/seq.c b/sound/core/seq/seq.c
index 639544b4fb04..e685eccdc741 100644
--- a/sound/core/seq/seq.c
+++ b/sound/core/seq/seq.c
@@ -87,10 +87,6 @@ static int __init alsa_seq_init(void)
 	if ((err = client_init_data()) < 0)
 		goto error;
 
-	/* init memory, room for selected events */
-	if ((err = snd_sequencer_memory_init()) < 0)
-		goto error;
-
 	/* init event queues */
 	if ((err = snd_seq_queues_init()) < 0)
 		goto error;
@@ -126,9 +122,6 @@ static void __exit alsa_seq_exit(void)
 	/* unregister sequencer device */
 	snd_sequencer_device_done();
 
-	/* release event memory */
-	snd_sequencer_memory_done();
-
 	snd_seq_autoload_exit();
 }
 
diff --git a/sound/core/seq/seq_memory.c b/sound/core/seq/seq_memory.c
index a4c8543176b2..5b0388202bac 100644
--- a/sound/core/seq/seq_memory.c
+++ b/sound/core/seq/seq_memory.c
@@ -504,18 +504,6 @@ int snd_seq_pool_delete(struct snd_seq_pool **ppool)
 	return 0;
 }
 
-/* initialize sequencer memory */
-int __init snd_sequencer_memory_init(void)
-{
-	return 0;
-}
-
-/* release sequencer memory */
-void __exit snd_sequencer_memory_done(void)
-{
-}
-
-
 /* exported to seq_clientmgr.c */
 void snd_seq_info_pool(struct snd_info_buffer *buffer,
 		       struct snd_seq_pool *pool, char *space)
diff --git a/sound/core/seq/seq_memory.h b/sound/core/seq/seq_memory.h
index 3abe306c394a..1292fe91f02e 100644
--- a/sound/core/seq/seq_memory.h
+++ b/sound/core/seq/seq_memory.h
@@ -94,12 +94,6 @@ struct snd_seq_pool *snd_seq_pool_new(int poolsize);
 /* remove pool */
 int snd_seq_pool_delete(struct snd_seq_pool **pool);
 
-/* init memory */
-int snd_sequencer_memory_init(void);
-            
-/* release event memory */
-void snd_sequencer_memory_done(void);
-
 /* polling */
 int snd_seq_pool_poll_wait(struct snd_seq_pool *pool, struct file *file, poll_table *wait);
 
diff --git a/sound/core/seq/seq_midi_emul.c b/sound/core/seq/seq_midi_emul.c
index 288f839a554b..f9f21331aeea 100644
--- a/sound/core/seq/seq_midi_emul.c
+++ b/sound/core/seq/seq_midi_emul.c
@@ -728,15 +728,3 @@ void snd_midi_channel_free_set(struct snd_midi_channel_set *chset)
 	kfree(chset);
 }
 EXPORT_SYMBOL(snd_midi_channel_free_set);
-
-static int __init alsa_seq_midi_emul_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_seq_midi_emul_exit(void)
-{
-}
-
-module_init(alsa_seq_midi_emul_init)
-module_exit(alsa_seq_midi_emul_exit)
diff --git a/sound/core/seq/seq_midi_event.c b/sound/core/seq/seq_midi_event.c
index 53c0dfab90d6..b11419537062 100644
--- a/sound/core/seq/seq_midi_event.c
+++ b/sound/core/seq/seq_midi_event.c
@@ -175,45 +175,12 @@ void snd_midi_event_reset_decode(struct snd_midi_event *dev)
 }
 EXPORT_SYMBOL(snd_midi_event_reset_decode);
 
-#if 0
-void snd_midi_event_init(struct snd_midi_event *dev)
-{
-	snd_midi_event_reset_encode(dev);
-	snd_midi_event_reset_decode(dev);
-}
-#endif  /*  0  */
-
 void snd_midi_event_no_status(struct snd_midi_event *dev, int on)
 {
 	dev->nostat = on ? 1 : 0;
 }
 EXPORT_SYMBOL(snd_midi_event_no_status);
 
-/*
- * resize buffer
- */
-#if 0
-int snd_midi_event_resize_buffer(struct snd_midi_event *dev, int bufsize)
-{
-	unsigned char *new_buf, *old_buf;
-	unsigned long flags;
-
-	if (bufsize == dev->bufsize)
-		return 0;
-	new_buf = kmalloc(bufsize, GFP_KERNEL);
-	if (new_buf == NULL)
-		return -ENOMEM;
-	spin_lock_irqsave(&dev->lock, flags);
-	old_buf = dev->buf;
-	dev->buf = new_buf;
-	dev->bufsize = bufsize;
-	reset_encode(dev);
-	spin_unlock_irqrestore(&dev->lock, flags);
-	kfree(old_buf);
-	return 0;
-}
-#endif  /*  0  */
-
 /*
  *  read one byte and encode to sequencer event:
  *  return true if MIDI bytes are encoded to an event
@@ -503,15 +470,3 @@ static int extra_decode_xrpn(struct snd_midi_event *dev, unsigned char *buf,
 	}
 	return idx;
 }
-
-static int __init alsa_seq_midi_event_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_seq_midi_event_exit(void)
-{
-}
-
-module_init(alsa_seq_midi_event_init)
-module_exit(alsa_seq_midi_event_exit)
diff --git a/sound/core/seq/seq_virmidi.c b/sound/core/seq/seq_virmidi.c
index 0c84926eb726..a2f1c6b58693 100644
--- a/sound/core/seq/seq_virmidi.c
+++ b/sound/core/seq/seq_virmidi.c
@@ -109,23 +109,6 @@ static int snd_virmidi_dev_receive_event(struct snd_virmidi_dev *rdev,
 	return 0;
 }
 
-/*
- * receive an event from the remote virmidi port
- *
- * for rawmidi inputs, you can call this function from the event
- * handler of a remote port which is attached to the virmidi via
- * SNDRV_VIRMIDI_SEQ_ATTACH.
- */
-#if 0
-int snd_virmidi_receive(struct snd_rawmidi *rmidi, struct snd_seq_event *ev)
-{
-	struct snd_virmidi_dev *rdev;
-
-	rdev = rmidi->private_data;
-	return snd_virmidi_dev_receive_event(rdev, ev, true);
-}
-#endif  /*  0  */
-
 /*
  * event handler of virmidi port
  */
@@ -544,19 +527,3 @@ int snd_virmidi_new(struct snd_card *card, int device, struct snd_rawmidi **rrmi
 	return 0;
 }
 EXPORT_SYMBOL(snd_virmidi_new);
-
-/*
- *  ENTRY functions
- */
-
-static int __init alsa_virmidi_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_virmidi_exit(void)
-{
-}
-
-module_init(alsa_virmidi_init)
-module_exit(alsa_virmidi_exit)
-- 
cgit v1.2.3


From 00976ad5271999ba06d24319fd1031b178aff832 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 1 Aug 2018 16:37:02 +0200
Subject: ALSA: seq: Fix leftovers at probe error path

The sequencer core module doesn't call some destructors in the error
path of the init code, which may leave some resources.

This patch mainly fix these leaks by calling the destructors
appropriately at alsa_seq_init().  Also the patch brings a few
cleanups along with it, namely:

- Expand the old "if ((err = xxx) < 0)" coding style
- Get rid of empty seq_queue_init() and its caller
- Change snd_seq_info_done() to void

Last but not least, a couple of functions lose __exit annotation since
they are called also in alsa_seq_init().

No functional changes but minor code cleanups.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq.c           | 26 ++++++++++++++++----------
 sound/core/seq/seq_clientmgr.c |  2 +-
 sound/core/seq/seq_info.c      | 10 ++--------
 sound/core/seq/seq_info.h      |  6 +++---
 sound/core/seq/seq_queue.c     | 12 +-----------
 sound/core/seq/seq_queue.h     |  3 ---
 6 files changed, 23 insertions(+), 36 deletions(-)

diff --git a/sound/core/seq/seq.c b/sound/core/seq/seq.c
index e685eccdc741..7de98d71f2aa 100644
--- a/sound/core/seq/seq.c
+++ b/sound/core/seq/seq.c
@@ -84,26 +84,32 @@ static int __init alsa_seq_init(void)
 {
 	int err;
 
-	if ((err = client_init_data()) < 0)
-		goto error;
-
-	/* init event queues */
-	if ((err = snd_seq_queues_init()) < 0)
+	err = client_init_data();
+	if (err < 0)
 		goto error;
 
 	/* register sequencer device */
-	if ((err = snd_sequencer_device_init()) < 0)
+	err = snd_sequencer_device_init();
+	if (err < 0)
 		goto error;
 
 	/* register proc interface */
-	if ((err = snd_seq_info_init()) < 0)
-		goto error;
+	err = snd_seq_info_init();
+	if (err < 0)
+		goto error_device;
 
 	/* register our internal client */
-	if ((err = snd_seq_system_client_init()) < 0)
-		goto error;
+	err = snd_seq_system_client_init();
+	if (err < 0)
+		goto error_info;
 
 	snd_seq_autoload_init();
+	return 0;
+
+ error_info:
+	snd_seq_info_done();
+ error_device:
+	snd_sequencer_device_done();
  error:
 	return err;
 }
diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index 6fd4b074b206..a0b768e2f697 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -2543,7 +2543,7 @@ int __init snd_sequencer_device_init(void)
 /* 
  * unregister sequencer device 
  */
-void __exit snd_sequencer_device_done(void)
+void snd_sequencer_device_done(void)
 {
 	snd_unregister_device(&seq_dev);
 	put_device(&seq_dev);
diff --git a/sound/core/seq/seq_info.c b/sound/core/seq/seq_info.c
index 97015447b9b3..b27fedd435b6 100644
--- a/sound/core/seq/seq_info.c
+++ b/sound/core/seq/seq_info.c
@@ -50,7 +50,7 @@ create_info_entry(char *name, void (*read)(struct snd_info_entry *,
 	return entry;
 }
 
-static void free_info_entries(void)
+void snd_seq_info_done(void)
 {
 	snd_info_free_entry(queues_entry);
 	snd_info_free_entry(clients_entry);
@@ -70,12 +70,6 @@ int __init snd_seq_info_init(void)
 	return 0;
 
  error:
-	free_info_entries();
+	snd_seq_info_done();
 	return -ENOMEM;
 }
-
-int __exit snd_seq_info_done(void)
-{
-	free_info_entries();
-	return 0;
-}
diff --git a/sound/core/seq/seq_info.h b/sound/core/seq/seq_info.h
index f8549f81a645..2cdf8f6e63f5 100644
--- a/sound/core/seq/seq_info.h
+++ b/sound/core/seq/seq_info.h
@@ -30,11 +30,11 @@ void snd_seq_info_queues_read(struct snd_info_entry *entry, struct snd_info_buff
 
 
 #ifdef CONFIG_SND_PROC_FS
-int snd_seq_info_init( void );
-int snd_seq_info_done( void );
+int snd_seq_info_init(void);
+void snd_seq_info_done(void);
 #else
 static inline int snd_seq_info_init(void) { return 0; }
-static inline int snd_seq_info_done(void) { return 0; }
+static inline void snd_seq_info_done(void) {}
 #endif
 
 #endif
diff --git a/sound/core/seq/seq_queue.c b/sound/core/seq/seq_queue.c
index b377f5048352..3b3ac96f1f5f 100644
--- a/sound/core/seq/seq_queue.c
+++ b/sound/core/seq/seq_queue.c
@@ -159,18 +159,8 @@ static void queue_delete(struct snd_seq_queue *q)
 
 /*----------------------------------------------------------------*/
 
-/* setup queues */
-int __init snd_seq_queues_init(void)
-{
-	/*
-	memset(queue_list, 0, sizeof(queue_list));
-	num_queues = 0;
-	*/
-	return 0;
-}
-
 /* delete all existing queues */
-void __exit snd_seq_queues_delete(void)
+void snd_seq_queues_delete(void)
 {
 	int i;
 
diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h
index 719093489a2c..76db43b79a2b 100644
--- a/sound/core/seq/seq_queue.h
+++ b/sound/core/seq/seq_queue.h
@@ -63,9 +63,6 @@ struct snd_seq_queue {
 /* get the number of current queues */
 int snd_seq_queue_get_cur_queues(void);
 
-/* init queues structure */
-int snd_seq_queues_init(void);
-
 /* delete queues */ 
 void snd_seq_queues_delete(void);
 
-- 
cgit v1.2.3


From 04702e8d0092832eaeeacc6b1bfbf81a66f242c9 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 1 Aug 2018 16:42:29 +0200
Subject: ALSA: seq: Use no intrruptible mutex_lock

All usages of mutex in ALSA sequencer core would take too long, hence
we don't have to care about the user interruption that makes things
complicated.  Let's replace them with simpler mutex_lock().

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_clientmgr.c | 26 +++++++-------------------
 1 file changed, 7 insertions(+), 19 deletions(-)

diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index a0b768e2f697..92e6524a3a9d 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -311,10 +311,9 @@ static int snd_seq_open(struct inode *inode, struct file *file)
 	if (err < 0)
 		return err;
 
-	if (mutex_lock_interruptible(&register_mutex))
-		return -ERESTARTSYS;
+	mutex_lock(&register_mutex);
 	client = seq_create_client1(-1, SNDRV_SEQ_DEFAULT_EVENTS);
-	if (client == NULL) {
+	if (!client) {
 		mutex_unlock(&register_mutex);
 		return -ENOMEM;	/* failure code */
 	}
@@ -1704,10 +1703,7 @@ static int snd_seq_ioctl_get_queue_timer(struct snd_seq_client *client,
 	if (queue == NULL)
 		return -EINVAL;
 
-	if (mutex_lock_interruptible(&queue->timer_mutex)) {
-		queuefree(queue);
-		return -ERESTARTSYS;
-	}
+	mutex_lock(&queue->timer_mutex);
 	tmr = queue->timer;
 	memset(timer, 0, sizeof(*timer));
 	timer->queue = queue->queue;
@@ -1741,10 +1737,7 @@ static int snd_seq_ioctl_set_queue_timer(struct snd_seq_client *client,
 		q = queueptr(timer->queue);
 		if (q == NULL)
 			return -ENXIO;
-		if (mutex_lock_interruptible(&q->timer_mutex)) {
-			queuefree(q);
-			return -ERESTARTSYS;
-		}
+		mutex_lock(&q->timer_mutex);
 		tmr = q->timer;
 		snd_seq_queue_timer_close(timer->queue);
 		tmr->type = timer->type;
@@ -2180,8 +2173,7 @@ int snd_seq_create_kernel_client(struct snd_card *card, int client_index,
 	if (card == NULL && client_index >= SNDRV_SEQ_GLOBAL_CLIENTS)
 		return -EINVAL;
 
-	if (mutex_lock_interruptible(&register_mutex))
-		return -ERESTARTSYS;
+	mutex_lock(&register_mutex);
 
 	if (card) {
 		client_index += SNDRV_SEQ_GLOBAL_CLIENTS
@@ -2522,19 +2514,15 @@ int __init snd_sequencer_device_init(void)
 	snd_device_initialize(&seq_dev, NULL);
 	dev_set_name(&seq_dev, "seq");
 
-	if (mutex_lock_interruptible(&register_mutex))
-		return -ERESTARTSYS;
-
+	mutex_lock(&register_mutex);
 	err = snd_register_device(SNDRV_DEVICE_TYPE_SEQUENCER, NULL, 0,
 				  &snd_seq_f_ops, NULL, &seq_dev);
+	mutex_unlock(&register_mutex);
 	if (err < 0) {
-		mutex_unlock(&register_mutex);
 		put_device(&seq_dev);
 		return err;
 	}
 	
-	mutex_unlock(&register_mutex);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 93ce1b12966d9d60ee5583ffbde822a22909568e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Wed, 1 Aug 2018 16:43:56 +0200
Subject: ALSA: seq: Drop unused 64bit division macros

The old ugly macros remained in the code without usage.
Rip them off.

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_queue.h | 24 ------------------------
 1 file changed, 24 deletions(-)

diff --git a/sound/core/seq/seq_queue.h b/sound/core/seq/seq_queue.h
index 76db43b79a2b..e006fc8e3a36 100644
--- a/sound/core/seq/seq_queue.h
+++ b/sound/core/seq/seq_queue.h
@@ -109,28 +109,4 @@ int snd_seq_queue_is_used(int queueid, int client);
 
 int snd_seq_control_queue(struct snd_seq_event *ev, int atomic, int hop);
 
-/*
- * 64bit division - for sync stuff..
- */
-#if defined(i386) || defined(i486)
-
-#define udiv_qrnnd(q, r, n1, n0, d) \
-  __asm__ ("divl %4"		\
-	   : "=a" ((u32)(q)),	\
-	     "=d" ((u32)(r))	\
-	   : "0" ((u32)(n0)),	\
-	     "1" ((u32)(n1)),	\
-	     "rm" ((u32)(d)))
-
-#define u64_div(x,y,q) do {u32 __tmp; udiv_qrnnd(q, __tmp, (x)>>32, x, y);} while (0)
-#define u64_mod(x,y,r) do {u32 __tmp; udiv_qrnnd(__tmp, q, (x)>>32, x, y);} while (0)
-#define u64_divmod(x,y,q,r) udiv_qrnnd(q, r, (x)>>32, x, y)
-
-#else
-#define u64_div(x,y,q)	((q) = (u32)((u64)(x) / (u64)(y)))
-#define u64_mod(x,y,r)	((r) = (u32)((u64)(x) % (u64)(y)))
-#define u64_divmod(x,y,q,r) (u64_div(x,y,q), u64_mod(x,y,r))
-#endif
-
-
 #endif
-- 
cgit v1.2.3


From 19da44cd33a3a6ff7c97fff0189999ff15b241e4 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 13 Jul 2018 17:55:15 +0300
Subject: pinctrl: freescale: off by one in imx1_pinconf_group_dbg_show()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The info->groups[] array is allocated in imx1_pinctrl_parse_dt().  It
has info->ngroups elements.  Thus the > here should be >= to prevent
reading one element beyond the end of the array.

Cc: stable@vger.kernel.org
Fixes: 30612cd90005 ("pinctrl: imx1 core driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Uwe Kleine-König <u.kleine-könig@pengutronix.de>
Acked-by: Dong Aisheng <Aisheng.dong@nxp.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/freescale/pinctrl-imx1-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/freescale/pinctrl-imx1-core.c b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
index c3bdd90b1422..deb7870b3d1a 100644
--- a/drivers/pinctrl/freescale/pinctrl-imx1-core.c
+++ b/drivers/pinctrl/freescale/pinctrl-imx1-core.c
@@ -429,7 +429,7 @@ static void imx1_pinconf_group_dbg_show(struct pinctrl_dev *pctldev,
 	const char *name;
 	int i, ret;
 
-	if (group > info->ngroups)
+	if (group >= info->ngroups)
 		return;
 
 	seq_puts(s, "\n");
-- 
cgit v1.2.3


From fe710322b81343601ca1759a9f3d4b694ed72fca Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Wed, 1 Aug 2018 13:49:31 +0800
Subject: drm/ttm: fix missed conversion of set_pages_array_uc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch fixed the error when do not configure CONFIG_X86, otherwise, below
error will be encountered.

All errors (new ones prefixed by >>):

   drivers/gpu/drm/ttm/ttm_page_alloc_dma.c: In function 'ttm_set_pages_caching':
>> drivers/gpu/drm/ttm/ttm_page_alloc_dma.c:272:7: error: implicit declaration of function 'set_pages_array_uc'; did you mean
+'ttm_set_pages_array_uc'? [-Werror=implicit-function-declaration]
      r = set_pages_array_uc(pages, cpages);
          ^~~~~~~~~~~~~~~~~~
          ttm_set_pages_array_uc
   cc1: some warnings being treated as errors

Reported-by: kbuild test robot <lkp@intel.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_page_alloc_dma.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
index 8304917294a2..507be7ac1165 100644
--- a/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
+++ b/drivers/gpu/drm/ttm/ttm_page_alloc_dma.c
@@ -269,7 +269,7 @@ static int ttm_set_pages_caching(struct dma_pool *pool,
 	int r = 0;
 	/* Set page caching */
 	if (pool->type & IS_UC) {
-		r = set_pages_array_uc(pages, cpages);
+		r = ttm_set_pages_array_uc(pages, cpages);
 		if (r)
 			pr_err("%s: Failed to set %d pages to uc!\n",
 			       pool->dev_name, cpages);
-- 
cgit v1.2.3


From dceb219fc60766006bfe8e53afa62816b94fcb11 Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Wed, 1 Aug 2018 13:49:32 +0800
Subject: drm/ttm: Add ttm_set_pages_wc and ttm_set_pages_uc helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These two helpers will be used on set page caching.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 include/drm/ttm/ttm_set_memory.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/include/drm/ttm/ttm_set_memory.h b/include/drm/ttm/ttm_set_memory.h
index a70723cf208b..7c492b49e38c 100644
--- a/include/drm/ttm/ttm_set_memory.h
+++ b/include/drm/ttm/ttm_set_memory.h
@@ -57,6 +57,18 @@ static inline int ttm_set_pages_wb(struct page *page, int numpages)
 	return set_pages_wb(page, numpages);
 }
 
+static inline int ttm_set_pages_wc(struct page *page, int numpages)
+{
+	unsigned long addr = (unsigned long)page_address(page);
+
+	return set_memory_wc(addr, numpages);
+}
+
+static inline int ttm_set_pages_uc(struct page *page, int numpages)
+{
+	return set_pages_uc(page, numpages);
+}
+
 #else /* for CONFIG_X86 */
 
 #if IS_ENABLED(CONFIG_AGP)
@@ -123,6 +135,16 @@ static inline int ttm_set_pages_wb(struct page *page, int numpages)
 
 #endif /* for CONFIG_AGP */
 
+static inline int ttm_set_pages_wc(struct page *page, int numpages)
+{
+	return 0;
+}
+
+static inline int ttm_set_pages_uc(struct page *page, int numpages)
+{
+	return 0;
+}
+
 #endif /* for CONFIG_X86 */
 
 #endif
-- 
cgit v1.2.3


From df36b2fb8390d98453fff1aae3927095fe9ff36c Mon Sep 17 00:00:00 2001
From: Huang Rui <ray.huang@amd.com>
Date: Wed, 1 Aug 2018 13:49:33 +0800
Subject: drm/ttm: clean up non-x86 definitions on ttm_tt
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All non-x86 definitions are moved to ttm_set_memory header, so remove it from
ttm_tt.c.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Huang Rui <ray.huang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/ttm/ttm_tt.c | 25 +++++++------------------
 1 file changed, 7 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/drm/ttm/ttm_tt.c b/drivers/gpu/drm/ttm/ttm_tt.c
index a1e543972ca7..e3a0691582ff 100644
--- a/drivers/gpu/drm/ttm/ttm_tt.c
+++ b/drivers/gpu/drm/ttm/ttm_tt.c
@@ -38,9 +38,7 @@
 #include <drm/drm_cache.h>
 #include <drm/ttm/ttm_bo_driver.h>
 #include <drm/ttm/ttm_page_alloc.h>
-#ifdef CONFIG_X86
-#include <asm/set_memory.h>
-#endif
+#include <drm/ttm/ttm_set_memory.h>
 
 /**
  * Allocates a ttm structure for the given BO.
@@ -115,10 +113,9 @@ static int ttm_sg_tt_alloc_page_directory(struct ttm_dma_tt *ttm)
 	return 0;
 }
 
-#ifdef CONFIG_X86
-static inline int ttm_tt_set_page_caching(struct page *p,
-					  enum ttm_caching_state c_old,
-					  enum ttm_caching_state c_new)
+static int ttm_tt_set_page_caching(struct page *p,
+				   enum ttm_caching_state c_old,
+				   enum ttm_caching_state c_new)
 {
 	int ret = 0;
 
@@ -129,26 +126,18 @@ static inline int ttm_tt_set_page_caching(struct page *p,
 		/* p isn't in the default caching state, set it to
 		 * writeback first to free its current memtype. */
 
-		ret = set_pages_wb(p, 1);
+		ret = ttm_set_pages_wb(p, 1);
 		if (ret)
 			return ret;
 	}
 
 	if (c_new == tt_wc)
-		ret = set_memory_wc((unsigned long) page_address(p), 1);
+		ret = ttm_set_pages_wc(p, 1);
 	else if (c_new == tt_uncached)
-		ret = set_pages_uc(p, 1);
+		ret = ttm_set_pages_uc(p, 1);
 
 	return ret;
 }
-#else /* CONFIG_X86 */
-static inline int ttm_tt_set_page_caching(struct page *p,
-					  enum ttm_caching_state c_old,
-					  enum ttm_caching_state c_new)
-{
-	return 0;
-}
-#endif /* CONFIG_X86 */
 
 /*
  * Change caching policy for the linear kernel map
-- 
cgit v1.2.3


From 79b05c1f31e2ed3dbc4e1d098a29687f5c39c495 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:26 +0200
Subject: um: stop abusing KBUILD_KCONFIG

Instead create a arch/um/Kconfig file that just includes the actual
per-arch Kconfig file.  Note that we use HEADER_ARCH to find the
per-arch Kconfig file as that variable already includes the
normalization from i386 or x86_64 to x86.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/um/Kconfig     | 3 +++
 arch/um/Makefile    | 4 +---
 arch/x86/um/Kconfig | 5 -----
 3 files changed, 4 insertions(+), 8 deletions(-)
 create mode 100644 arch/um/Kconfig

diff --git a/arch/um/Kconfig b/arch/um/Kconfig
new file mode 100644
index 000000000000..76b4a32c9f42
--- /dev/null
+++ b/arch/um/Kconfig
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+source "arch/$(HEADER_ARCH)/um/Kconfig"
diff --git a/arch/um/Makefile b/arch/um/Makefile
index e54dda8a0363..d427bfc6948f 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -113,8 +113,6 @@ define archhelp
   echo '		   find in the kernel root.'
 endef
 
-KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig
-
 archheaders:
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \
 	            kbuild-file=$(HOST_DIR)/include/asm/Kbuild \
@@ -176,4 +174,4 @@ endef
 include/generated/user_constants.h: $(HOST_DIR)/um/user-offsets.s
 	$(call filechk,gen-asm-offsets)
 
-export SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS DEV_NULL_PATH
+export HEADER_ARCH SUBARCH USER_CFLAGS CFLAGS_NO_HARDENING OS DEV_NULL_PATH
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 9d529f22fd9d..7e509c83d80d 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -1,9 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-mainmenu "User Mode Linux/$(SUBARCH) $(KERNELVERSION) Kernel Configuration"
-
-comment "Compiler: $(CC_VERSION_TEXT)"
-
-source "scripts/Kconfig.include"
 
 source "arch/um/Kconfig.common"
 
-- 
cgit v1.2.3


From f163977d21a2b380ef83c25df2f83740577dc564 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:27 +0200
Subject: um: cleanup Kconfig files

We can handle all not architecture specific UM configuration directly in
the newly added arch/um/Kconfig.  Do so by merging the Kconfig.common,
Kconfig.rest and Kconfig.um files into arch/um/Kconfig, and move the main
UML menu as well.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/um/Kconfig        | 210 +++++++++++++++++++++++++++++++++++++++++++++++++
 arch/um/Kconfig.common |  60 --------------
 arch/um/Kconfig.rest   |  22 ------
 arch/um/Kconfig.um     | 124 -----------------------------
 arch/x86/um/Kconfig    |  10 ---
 5 files changed, 210 insertions(+), 216 deletions(-)
 delete mode 100644 arch/um/Kconfig.common
 delete mode 100644 arch/um/Kconfig.rest
 delete mode 100644 arch/um/Kconfig.um

diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 76b4a32c9f42..69fa01a4a81b 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -1,3 +1,213 @@
 # SPDX-License-Identifier: GPL-2.0
 
+menu "UML-specific options"
+
+config UML
+	bool
+	default y
+	select ARCH_HAS_KCOV
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_UID16
+	select HAVE_FUTEX_CMPXCHG if FUTEX
+	select HAVE_DEBUG_KMEMLEAK
+	select GENERIC_IRQ_SHOW
+	select GENERIC_CPU_DEVICES
+	select GENERIC_CLOCKEVENTS
+	select HAVE_GCC_PLUGINS
+	select TTY # Needed for line.c
+
+config MMU
+	bool
+	default y
+
+config NO_IOMEM
+	def_bool y
+
+config ISA
+	bool
+
+config SBUS
+	bool
+
+config PCI
+	bool
+
+config PCMCIA
+	bool
+
+config TRACE_IRQFLAGS_SUPPORT
+	bool
+	default y
+
+config LOCKDEP_SUPPORT
+	bool
+	default y
+
+config STACKTRACE_SUPPORT
+	bool
+	default y
+	select STACKTRACE
+
+config GENERIC_CALIBRATE_DELAY
+	bool
+	default y
+
+config HZ
+	int
+	default 100
+
+config NR_CPUS
+	int
+	range 1 1
+	default 1
+
 source "arch/$(HEADER_ARCH)/um/Kconfig"
+
+config STATIC_LINK
+	bool "Force a static link"
+	default n
+	help
+	  This option gives you the ability to force a static link of UML.
+	  Normally, UML is linked as a shared binary.  This is inconvenient for
+	  use in a chroot jail.  So, if you intend to run UML inside a chroot,
+	  you probably want to say Y here.
+	  Additionally, this option enables using higher memory spaces (up to
+	  2.75G) for UML.
+
+source "mm/Kconfig"
+
+config LD_SCRIPT_STATIC
+	bool
+	default y
+	depends on STATIC_LINK
+
+config LD_SCRIPT_DYN
+	bool
+	default y
+	depends on !LD_SCRIPT_STATIC
+        select MODULE_REL_CRCS if MODVERSIONS
+
+source "fs/Kconfig.binfmt"
+
+config HOSTFS
+	tristate "Host filesystem"
+	help
+          While the User-Mode Linux port uses its own root file system for
+          booting and normal file access, this module lets the UML user
+          access files stored on the host.  It does not require any
+          network connection between the Host and UML.  An example use of
+          this might be:
+
+          mount none /tmp/fromhost -t hostfs -o /tmp/umlshare
+
+          where /tmp/fromhost is an empty directory inside UML and
+          /tmp/umlshare is a directory on the host with files the UML user
+          wishes to access.
+
+          For more information, see
+          <http://user-mode-linux.sourceforge.net/hostfs.html>.
+
+          If you'd like to be able to work with files stored on the host,
+          say Y or M here; otherwise say N.
+
+config MCONSOLE
+	bool "Management console"
+	depends on PROC_FS
+	default y
+	help
+          The user mode linux management console is a low-level interface to
+          the kernel, somewhat like the i386 SysRq interface.  Since there is
+          a full-blown operating system running under every user mode linux
+          instance, there is much greater flexibility possible than with the
+          SysRq mechanism.
+
+          If you answer 'Y' to this option, to use this feature, you need the
+          mconsole client (called uml_mconsole) which is present in CVS in
+          2.4.5-9um and later (path /tools/mconsole), and is also in the
+          distribution RPM package in 2.4.6 and later.
+
+          It is safe to say 'Y' here.
+
+config MAGIC_SYSRQ
+	bool "Magic SysRq key"
+	depends on MCONSOLE
+	help
+	  If you say Y here, you will have some control over the system even
+	  if the system crashes for example during kernel debugging (e.g., you
+	  will be able to flush the buffer cache to disk, reboot the system
+	  immediately or dump some status information). A key for each of the
+	  possible requests is provided.
+
+	  This is the feature normally accomplished by pressing a key
+	  while holding SysRq (Alt+PrintScreen).
+
+	  On UML, this is accomplished by sending a "sysrq" command with
+	  mconsole, followed by the letter for the requested command.
+
+	  The keys are documented in <file:Documentation/admin-guide/sysrq.rst>. Don't say Y
+	  unless you really know what this hack does.
+
+config KERNEL_STACK_ORDER
+	int "Kernel stack size order"
+	default 1 if 64BIT
+	range 1 10 if 64BIT
+	default 0 if !64BIT
+	help
+	  This option determines the size of UML kernel stacks.  They will
+	  be 1 << order pages.  The default is OK unless you're running Valgrind
+	  on UML, in which case, set this to 3.
+
+config MMAPPER
+	tristate "iomem emulation driver"
+	help
+	  This driver allows a host file to be used as emulated IO memory inside
+	  UML.
+
+config NO_DMA
+	def_bool y
+
+config PGTABLE_LEVELS
+	int
+	default 3 if 3_LEVEL_PGTABLES
+	default 2
+
+config SECCOMP
+	def_bool y
+	prompt "Enable seccomp to safely compute untrusted bytecode"
+	---help---
+	  This kernel feature is useful for number crunching applications
+	  that may need to compute untrusted bytecode during their
+	  execution. By using pipes or other transports made available to
+	  the process as file descriptors supporting the read/write
+	  syscalls, it's possible to isolate those applications in
+	  their own address space using seccomp. Once seccomp is
+	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
+	  and the task is only allowed to execute a few safe syscalls
+	  defined by each seccomp mode.
+
+	  If unsure, say Y.
+
+endmenu
+
+source "init/Kconfig"
+
+source "kernel/Kconfig.freezer"
+
+source "arch/um/Kconfig.char"
+
+source "drivers/Kconfig"
+
+source "net/Kconfig"
+
+source "arch/um/Kconfig.net"
+
+source "fs/Kconfig"
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
+source "lib/Kconfig"
+
+source "arch/um/Kconfig.debug"
diff --git a/arch/um/Kconfig.common b/arch/um/Kconfig.common
deleted file mode 100644
index 07f84c842cc3..000000000000
--- a/arch/um/Kconfig.common
+++ /dev/null
@@ -1,60 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config UML
-	bool
-	default y
-	select ARCH_HAS_KCOV
-	select HAVE_ARCH_AUDITSYSCALL
-	select HAVE_ARCH_SECCOMP_FILTER
-	select HAVE_UID16
-	select HAVE_FUTEX_CMPXCHG if FUTEX
-	select HAVE_DEBUG_KMEMLEAK
-	select GENERIC_IRQ_SHOW
-	select GENERIC_CPU_DEVICES
-	select GENERIC_CLOCKEVENTS
-	select HAVE_GCC_PLUGINS
-	select TTY # Needed for line.c
-
-config MMU
-	bool
-	default y
-
-config NO_IOMEM
-	def_bool y
-
-config ISA
-	bool
-
-config SBUS
-	bool
-
-config PCI
-	bool
-
-config PCMCIA
-	bool
-
-config TRACE_IRQFLAGS_SUPPORT
-	bool
-	default y
-
-config LOCKDEP_SUPPORT
-	bool
-	default y
-
-config STACKTRACE_SUPPORT
-	bool
-	default y
-	select STACKTRACE
-
-config GENERIC_CALIBRATE_DELAY
-	bool
-	default y
-
-config HZ
-	int
-	default 100
-
-config NR_CPUS
-	int
-	range 1 1
-	default 1
diff --git a/arch/um/Kconfig.rest b/arch/um/Kconfig.rest
deleted file mode 100644
index 08327b9c0cbe..000000000000
--- a/arch/um/Kconfig.rest
+++ /dev/null
@@ -1,22 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
-source "arch/um/Kconfig.char"
-
-source "drivers/Kconfig"
-
-source "net/Kconfig"
-
-source "arch/um/Kconfig.net"
-
-source "fs/Kconfig"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
-source "arch/um/Kconfig.debug"
diff --git a/arch/um/Kconfig.um b/arch/um/Kconfig.um
deleted file mode 100644
index 20da5a8ca949..000000000000
--- a/arch/um/Kconfig.um
+++ /dev/null
@@ -1,124 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-config STATIC_LINK
-	bool "Force a static link"
-	default n
-	help
-	  This option gives you the ability to force a static link of UML.
-	  Normally, UML is linked as a shared binary.  This is inconvenient for
-	  use in a chroot jail.  So, if you intend to run UML inside a chroot,
-	  you probably want to say Y here.
-	  Additionally, this option enables using higher memory spaces (up to
-	  2.75G) for UML.
-
-source "mm/Kconfig"
-
-config LD_SCRIPT_STATIC
-	bool
-	default y
-	depends on STATIC_LINK
-
-config LD_SCRIPT_DYN
-	bool
-	default y
-	depends on !LD_SCRIPT_STATIC
-        select MODULE_REL_CRCS if MODVERSIONS
-
-source "fs/Kconfig.binfmt"
-
-config HOSTFS
-	tristate "Host filesystem"
-	help
-          While the User-Mode Linux port uses its own root file system for
-          booting and normal file access, this module lets the UML user
-          access files stored on the host.  It does not require any
-          network connection between the Host and UML.  An example use of
-          this might be:
-
-          mount none /tmp/fromhost -t hostfs -o /tmp/umlshare
-
-          where /tmp/fromhost is an empty directory inside UML and
-          /tmp/umlshare is a directory on the host with files the UML user
-          wishes to access.
-
-          For more information, see
-          <http://user-mode-linux.sourceforge.net/hostfs.html>.
-
-          If you'd like to be able to work with files stored on the host,
-          say Y or M here; otherwise say N.
-
-config MCONSOLE
-	bool "Management console"
-	depends on PROC_FS
-	default y
-	help
-          The user mode linux management console is a low-level interface to
-          the kernel, somewhat like the i386 SysRq interface.  Since there is
-          a full-blown operating system running under every user mode linux
-          instance, there is much greater flexibility possible than with the
-          SysRq mechanism.
-
-          If you answer 'Y' to this option, to use this feature, you need the
-          mconsole client (called uml_mconsole) which is present in CVS in
-          2.4.5-9um and later (path /tools/mconsole), and is also in the
-          distribution RPM package in 2.4.6 and later.
-
-          It is safe to say 'Y' here.
-
-config MAGIC_SYSRQ
-	bool "Magic SysRq key"
-	depends on MCONSOLE
-	help
-	  If you say Y here, you will have some control over the system even
-	  if the system crashes for example during kernel debugging (e.g., you
-	  will be able to flush the buffer cache to disk, reboot the system
-	  immediately or dump some status information). A key for each of the
-	  possible requests is provided.
-
-	  This is the feature normally accomplished by pressing a key
-	  while holding SysRq (Alt+PrintScreen).
-
-	  On UML, this is accomplished by sending a "sysrq" command with
-	  mconsole, followed by the letter for the requested command.
-
-	  The keys are documented in <file:Documentation/admin-guide/sysrq.rst>. Don't say Y
-	  unless you really know what this hack does.
-
-config KERNEL_STACK_ORDER
-	int "Kernel stack size order"
-	default 1 if 64BIT
-	range 1 10 if 64BIT
-	default 0 if !64BIT
-	help
-	  This option determines the size of UML kernel stacks.  They will
-	  be 1 << order pages.  The default is OK unless you're running Valgrind
-	  on UML, in which case, set this to 3.
-
-config MMAPPER
-	tristate "iomem emulation driver"
-	help
-	  This driver allows a host file to be used as emulated IO memory inside
-	  UML.
-
-config NO_DMA
-	def_bool y
-
-config PGTABLE_LEVELS
-	int
-	default 3 if 3_LEVEL_PGTABLES
-	default 2
-
-config SECCOMP
-	def_bool y
-	prompt "Enable seccomp to safely compute untrusted bytecode"
-	---help---
-	  This kernel feature is useful for number crunching applications
-	  that may need to compute untrusted bytecode during their
-	  execution. By using pipes or other transports made available to
-	  the process as file descriptors supporting the read/write
-	  syscalls, it's possible to isolate those applications in
-	  their own address space using seccomp. Once seccomp is
-	  enabled via prctl(PR_SET_SECCOMP), it cannot be disabled
-	  and the task is only allowed to execute a few safe syscalls
-	  defined by each seccomp mode.
-
-	  If unsure, say Y.
diff --git a/arch/x86/um/Kconfig b/arch/x86/um/Kconfig
index 7e509c83d80d..f518b4744ff8 100644
--- a/arch/x86/um/Kconfig
+++ b/arch/x86/um/Kconfig
@@ -1,9 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0
 
-source "arch/um/Kconfig.common"
-
-menu "UML-specific options"
-
 menu "Host processor type and features"
 
 source "arch/x86/Kconfig.cpu"
@@ -61,9 +57,3 @@ config ARCH_REUSE_HOST_VSYSCALL_AREA
 
 config GENERIC_HWEIGHT
 	def_bool y
-
-source "arch/um/Kconfig.um"
-
-endmenu
-
-source "arch/um/Kconfig.rest"
-- 
cgit v1.2.3


From 9bea18010f210dd24d2a4f2bd3df7b92132537ae Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:28 +0200
Subject: um: create a proper drivers Kconfig

Merge arch/um/Kconfig.char and arch/um/Kconfig.net into a new
arch/um/drivers/Kconfig.  This fits the way Kconfig files are placed
elsewhere in the kernel tree.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Richard Weinberger <richard@nod.at>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/um/Kconfig         |   4 +-
 arch/um/Kconfig.char    | 124 ------------------
 arch/um/Kconfig.net     | 214 ------------------------------
 arch/um/drivers/Kconfig | 337 ++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 338 insertions(+), 341 deletions(-)
 delete mode 100644 arch/um/Kconfig.char
 delete mode 100644 arch/um/Kconfig.net
 create mode 100644 arch/um/drivers/Kconfig

diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 69fa01a4a81b..ea35bf91fc0f 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -194,14 +194,12 @@ source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
 
-source "arch/um/Kconfig.char"
+source "arch/um/drivers/Kconfig"
 
 source "drivers/Kconfig"
 
 source "net/Kconfig"
 
-source "arch/um/Kconfig.net"
-
 source "fs/Kconfig"
 
 source "security/Kconfig"
diff --git a/arch/um/Kconfig.char b/arch/um/Kconfig.char
deleted file mode 100644
index f184bde7030e..000000000000
--- a/arch/um/Kconfig.char
+++ /dev/null
@@ -1,124 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-menu "UML Character Devices"
-
-config STDERR_CONSOLE
-	bool "stderr console"
-	default y
-	help
-	  console driver which dumps all printk messages to stderr.
-
-config SSL
-	bool "Virtual serial line"
-	help
-          The User-Mode Linux environment allows you to create virtual serial
-          lines on the UML that are usually made to show up on the host as
-          ttys or ptys.
-
-          See <http://user-mode-linux.sourceforge.net/old/input.html> for more
-          information and command line examples of how to use this facility.
-
-          Unless you have a specific reason for disabling this, say Y.
-
-config NULL_CHAN
-	bool "null channel support"
-	help
-          This option enables support for attaching UML consoles and serial
-          lines to a device similar to /dev/null.  Data written to it disappears
-          and there is never any data to be read.
-
-config PORT_CHAN
-	bool "port channel support"
-	help
-          This option enables support for attaching UML consoles and serial
-          lines to host portals.  They may be accessed with 'telnet <host>
-          <port number>'.  Any number of consoles and serial lines may be
-          attached to a single portal, although what UML device you get when
-          you telnet to that portal will be unpredictable.
-          It is safe to say 'Y' here.
-
-config PTY_CHAN
-	bool "pty channel support"
-	help
-          This option enables support for attaching UML consoles and serial
-          lines to host pseudo-terminals.  Access to both traditional
-          pseudo-terminals (/dev/pty*) and pts pseudo-terminals are controlled
-          with this option.  The assignment of UML devices to host devices
-          will be announced in the kernel message log.
-          It is safe to say 'Y' here.
-
-config TTY_CHAN
-	bool "tty channel support"
-	help
-          This option enables support for attaching UML consoles and serial
-          lines to host terminals.  Access to both virtual consoles
-          (/dev/tty*) and the slave side of pseudo-terminals (/dev/ttyp* and
-          /dev/pts/*) are controlled by this option.
-          It is safe to say 'Y' here.
-
-config XTERM_CHAN
-	bool "xterm channel support"
-	help
-          This option enables support for attaching UML consoles and serial
-          lines to xterms.  Each UML device so assigned will be brought up in
-          its own xterm.
-          It is safe to say 'Y' here.
-
-config NOCONFIG_CHAN
-	bool
-	default !(XTERM_CHAN && TTY_CHAN && PTY_CHAN && PORT_CHAN && NULL_CHAN)
-
-config CON_ZERO_CHAN
-	string "Default main console channel initialization"
-	default "fd:0,fd:1"
-	help
-          This is the string describing the channel to which the main console
-          will be attached by default.  This value can be overridden from the
-          command line.  The default value is "fd:0,fd:1", which attaches the
-          main console to stdin and stdout.
-          It is safe to leave this unchanged.
-
-config CON_CHAN
-	string "Default console channel initialization"
-	default "xterm"
-	help
-          This is the string describing the channel to which all consoles
-          except the main console will be attached by default.  This value can
-          be overridden from the command line.  The default value is "xterm",
-          which brings them up in xterms.
-          It is safe to leave this unchanged, although you may wish to change
-          this if you expect the UML that you build to be run in environments
-          which don't have X or xterm available.
-
-config SSL_CHAN
-	string "Default serial line channel initialization"
-	default "pty"
-	help
-          This is the string describing the channel to which the serial lines
-          will be attached by default.  This value can be overridden from the
-          command line.  The default value is "pty", which attaches them to
-          traditional pseudo-terminals.
-          It is safe to leave this unchanged, although you may wish to change
-          this if you expect the UML that you build to be run in environments
-          which don't have a set of /dev/pty* devices.
-
-config UML_SOUND
-	tristate "Sound support"
-	help
-          This option enables UML sound support.  If enabled, it will pull in
-          soundcore and the UML hostaudio relay, which acts as a intermediary
-          between the host's dsp and mixer devices and the UML sound system.
-          It is safe to say 'Y' here.
-
-config SOUND
-	tristate
-	default UML_SOUND
-
-config SOUND_OSS_CORE
-	bool
-	default UML_SOUND
-
-config HOSTAUDIO
-	tristate
-	default UML_SOUND
-
-endmenu
diff --git a/arch/um/Kconfig.net b/arch/um/Kconfig.net
deleted file mode 100644
index c390f3deb0dc..000000000000
--- a/arch/um/Kconfig.net
+++ /dev/null
@@ -1,214 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0
-
-menu "UML Network Devices"
-	depends on NET
-
-# UML virtual driver
-config UML_NET
-	bool "Virtual network device"
-	help
-        While the User-Mode port cannot directly talk to any physical
-        hardware devices, this choice and the following transport options
-        provide one or more virtual network devices through which the UML
-        kernels can talk to each other, the host, and with the host's help,
-        machines on the outside world.
-
-        For more information, including explanations of the networking and
-        sample configurations, see
-        <http://user-mode-linux.sourceforge.net/old/networking.html>.
-
-        If you'd like to be able to enable networking in the User-Mode
-        linux environment, say Y; otherwise say N.  Note that you must
-        enable at least one of the following transport options to actually
-        make use of UML networking.
-
-config UML_NET_ETHERTAP
-	bool "Ethertap transport"
-	depends on UML_NET
-	help
-        The Ethertap User-Mode Linux network transport allows a single
-        running UML to exchange packets with its host over one of the
-        host's Ethertap devices, such as /dev/tap0.  Additional running
-        UMLs can use additional Ethertap devices, one per running UML.
-        While the UML believes it's on a (multi-device, broadcast) virtual
-        Ethernet network, it's in fact communicating over a point-to-point
-        link with the host.
-
-        To use this, your host kernel must have support for Ethertap
-        devices.  Also, if your host kernel is 2.4.x, it must have
-        CONFIG_NETLINK_DEV configured as Y or M.
-
-        For more information, see
-        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-        has examples of the UML command line to use to enable Ethertap
-        networking.
-
-        If you'd like to set up an IP network with the host and/or the
-        outside world, say Y to this, the Daemon Transport and/or the
-        Slip Transport.  You'll need at least one of them, but may choose
-        more than one without conflict.  If you don't need UML networking,
-        say N.
-
-config UML_NET_TUNTAP
-	bool "TUN/TAP transport"
-	depends on UML_NET
-	help
-        The UML TUN/TAP network transport allows a UML instance to exchange
-        packets with the host over a TUN/TAP device.  This option will only
-        work with a 2.4 host, unless you've applied the TUN/TAP patch to
-        your 2.2 host kernel.
-
-        To use this transport, your host kernel must have support for TUN/TAP
-        devices, either built-in or as a module.
-
-config UML_NET_SLIP
-	bool "SLIP transport"
-	depends on UML_NET
-	help
-        The slip User-Mode Linux network transport allows a running UML to
-        network with its host over a point-to-point link.  Unlike Ethertap,
-        which can carry any Ethernet frame (and hence even non-IP packets),
-        the slip transport can only carry IP packets.
-
-        To use this, your host must support slip devices.
-
-        For more information, see
-        <http://user-mode-linux.sourceforge.net/old/networking.html>.
-        has examples of the UML command line to use to enable slip
-        networking, and details of a few quirks with it.
-
-        The Ethertap Transport is preferred over slip because of its
-        limitations.  If you prefer slip, however, say Y here.  Otherwise
-        choose the Multicast transport (to network multiple UMLs on
-        multiple hosts), Ethertap (to network with the host and the
-        outside world), and/or the Daemon transport (to network multiple
-        UMLs on a single host).  You may choose more than one without
-        conflict.  If you don't need UML networking, say N.
-
-config UML_NET_DAEMON
-	bool "Daemon transport"
-	depends on UML_NET
-	help
-        This User-Mode Linux network transport allows one or more running
-        UMLs on a single host to communicate with each other, but not to
-        the host.
-
-        To use this form of networking, you'll need to run the UML
-        networking daemon on the host.
-
-        For more information, see
-        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-        has examples of the UML command line to use to enable Daemon
-        networking.
-
-        If you'd like to set up a network with other UMLs on a single host,
-        say Y.  If you need a network between UMLs on multiple physical
-        hosts, choose the Multicast Transport.  To set up a network with
-        the host and/or other IP machines, say Y to the Ethertap or Slip
-        transports.  You'll need at least one of them, but may choose
-        more than one without conflict.  If you don't need UML networking,
-        say N.
-
-config UML_NET_VECTOR
-	bool "Vector I/O high performance network devices"
-	depends on UML_NET
-	help
-	This User-Mode Linux network driver uses multi-message send
-	and receive functions. The host running the UML guest must have
-	a linux kernel version above 3.0 and a libc version > 2.13.
-	This driver provides tap, raw, gre and l2tpv3 network transports
-	with up to 4 times higher network throughput than the UML network
-	drivers.
-
-config UML_NET_VDE
-	bool "VDE transport"
-	depends on UML_NET
-	help
-	This User-Mode Linux network transport allows one or more running
-	UMLs on a single host to communicate with each other and also
-	with the rest of the world using Virtual Distributed Ethernet,
-	an improved fork of uml_switch.
-
-	You must have libvdeplug installed in order to build the vde
-	transport into UML.
-
-	To use this form of networking, you will need to run vde_switch
-	on the host.
-
-	For more information, see <http://wiki.virtualsquare.org/>
-	That site has a good overview of what VDE is and also examples
-	of the UML command line to use to enable VDE networking.
-
-	If you need UML networking with VDE,
-	say Y.
-
-config UML_NET_MCAST
-	bool "Multicast transport"
-	depends on UML_NET
-	help
-        This Multicast User-Mode Linux network transport allows multiple
-        UMLs (even ones running on different host machines!) to talk to
-        each other over a virtual ethernet network.  However, it requires
-        at least one UML with one of the other transports to act as a
-        bridge if any of them need to be able to talk to their hosts or any
-        other IP machines.
-
-        To use this, your host kernel(s) must support IP Multicasting.
-
-        For more information, see
-        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-        has examples of the UML command line to use to enable Multicast
-        networking, and notes about the security of this approach.
-
-        If you need UMLs on multiple physical hosts to communicate as if
-        they shared an Ethernet network, say Y.  If you need to communicate
-        with other IP machines, make sure you select one of the other
-        transports (possibly in addition to Multicast; they're not
-        exclusive).  If you don't need to network UMLs say N to each of
-        the transports.
-
-config UML_NET_PCAP
-	bool "pcap transport"
-	depends on UML_NET
-	help
-	The pcap transport makes a pcap packet stream on the host look
-	like an ethernet device inside UML.  This is useful for making
-	UML act as a network monitor for the host.  You must have libcap
-	installed in order to build the pcap transport into UML.
-
-        For more information, see
-        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
-        has examples of the UML command line to use to enable this option.
-
-	If you intend to use UML as a network monitor for the host, say
-	Y here.  Otherwise, say N.
-
-config UML_NET_SLIRP
-	bool "SLiRP transport"
-	depends on UML_NET
-	help
-        The SLiRP User-Mode Linux network transport allows a running UML
-        to network by invoking a program that can handle SLIP encapsulated
-        packets.  This is commonly (but not limited to) the application
-        known as SLiRP, a program that can re-socket IP packets back onto
-        the host on which it is run.  Only IP packets are supported,
-        unlike other network transports that can handle all Ethernet
-        frames.  In general, slirp allows the UML the same IP connectivity
-        to the outside world that the host user is permitted, and unlike
-        other transports, SLiRP works without the need of root level
-        privleges, setuid binaries, or SLIP devices on the host.  This
-        also means not every type of connection is possible, but most
-        situations can be accommodated with carefully crafted slirp
-        commands that can be passed along as part of the network device's
-        setup string.  The effect of this transport on the UML is similar
-        that of a host behind a firewall that masquerades all network
-        connections passing through it (but is less secure).
-
-        To use this you should first have slirp compiled somewhere
-        accessible on the host, and have read its documentation.  If you
-        don't need UML networking, say N.
-
-        Startup example: "eth0=slirp,FE:FD:01:02:03:04,/usr/local/bin/slirp"
-
-endmenu
-
diff --git a/arch/um/drivers/Kconfig b/arch/um/drivers/Kconfig
new file mode 100644
index 000000000000..2b1aaf7755aa
--- /dev/null
+++ b/arch/um/drivers/Kconfig
@@ -0,0 +1,337 @@
+# SPDX-License-Identifier: GPL-2.0
+
+menu "UML Character Devices"
+
+config STDERR_CONSOLE
+	bool "stderr console"
+	default y
+	help
+	  console driver which dumps all printk messages to stderr.
+
+config SSL
+	bool "Virtual serial line"
+	help
+          The User-Mode Linux environment allows you to create virtual serial
+          lines on the UML that are usually made to show up on the host as
+          ttys or ptys.
+
+          See <http://user-mode-linux.sourceforge.net/old/input.html> for more
+          information and command line examples of how to use this facility.
+
+          Unless you have a specific reason for disabling this, say Y.
+
+config NULL_CHAN
+	bool "null channel support"
+	help
+          This option enables support for attaching UML consoles and serial
+          lines to a device similar to /dev/null.  Data written to it disappears
+          and there is never any data to be read.
+
+config PORT_CHAN
+	bool "port channel support"
+	help
+          This option enables support for attaching UML consoles and serial
+          lines to host portals.  They may be accessed with 'telnet <host>
+          <port number>'.  Any number of consoles and serial lines may be
+          attached to a single portal, although what UML device you get when
+          you telnet to that portal will be unpredictable.
+          It is safe to say 'Y' here.
+
+config PTY_CHAN
+	bool "pty channel support"
+	help
+          This option enables support for attaching UML consoles and serial
+          lines to host pseudo-terminals.  Access to both traditional
+          pseudo-terminals (/dev/pty*) and pts pseudo-terminals are controlled
+          with this option.  The assignment of UML devices to host devices
+          will be announced in the kernel message log.
+          It is safe to say 'Y' here.
+
+config TTY_CHAN
+	bool "tty channel support"
+	help
+          This option enables support for attaching UML consoles and serial
+          lines to host terminals.  Access to both virtual consoles
+          (/dev/tty*) and the slave side of pseudo-terminals (/dev/ttyp* and
+          /dev/pts/*) are controlled by this option.
+          It is safe to say 'Y' here.
+
+config XTERM_CHAN
+	bool "xterm channel support"
+	help
+          This option enables support for attaching UML consoles and serial
+          lines to xterms.  Each UML device so assigned will be brought up in
+          its own xterm.
+          It is safe to say 'Y' here.
+
+config NOCONFIG_CHAN
+	bool
+	default !(XTERM_CHAN && TTY_CHAN && PTY_CHAN && PORT_CHAN && NULL_CHAN)
+
+config CON_ZERO_CHAN
+	string "Default main console channel initialization"
+	default "fd:0,fd:1"
+	help
+          This is the string describing the channel to which the main console
+          will be attached by default.  This value can be overridden from the
+          command line.  The default value is "fd:0,fd:1", which attaches the
+          main console to stdin and stdout.
+          It is safe to leave this unchanged.
+
+config CON_CHAN
+	string "Default console channel initialization"
+	default "xterm"
+	help
+          This is the string describing the channel to which all consoles
+          except the main console will be attached by default.  This value can
+          be overridden from the command line.  The default value is "xterm",
+          which brings them up in xterms.
+          It is safe to leave this unchanged, although you may wish to change
+          this if you expect the UML that you build to be run in environments
+          which don't have X or xterm available.
+
+config SSL_CHAN
+	string "Default serial line channel initialization"
+	default "pty"
+	help
+          This is the string describing the channel to which the serial lines
+          will be attached by default.  This value can be overridden from the
+          command line.  The default value is "pty", which attaches them to
+          traditional pseudo-terminals.
+          It is safe to leave this unchanged, although you may wish to change
+          this if you expect the UML that you build to be run in environments
+          which don't have a set of /dev/pty* devices.
+
+config UML_SOUND
+	tristate "Sound support"
+	help
+          This option enables UML sound support.  If enabled, it will pull in
+          soundcore and the UML hostaudio relay, which acts as a intermediary
+          between the host's dsp and mixer devices and the UML sound system.
+          It is safe to say 'Y' here.
+
+config SOUND
+	tristate
+	default UML_SOUND
+
+config SOUND_OSS_CORE
+	bool
+	default UML_SOUND
+
+config HOSTAUDIO
+	tristate
+	default UML_SOUND
+
+endmenu
+
+menu "UML Network Devices"
+	depends on NET
+
+# UML virtual driver
+config UML_NET
+	bool "Virtual network device"
+	help
+        While the User-Mode port cannot directly talk to any physical
+        hardware devices, this choice and the following transport options
+        provide one or more virtual network devices through which the UML
+        kernels can talk to each other, the host, and with the host's help,
+        machines on the outside world.
+
+        For more information, including explanations of the networking and
+        sample configurations, see
+        <http://user-mode-linux.sourceforge.net/old/networking.html>.
+
+        If you'd like to be able to enable networking in the User-Mode
+        linux environment, say Y; otherwise say N.  Note that you must
+        enable at least one of the following transport options to actually
+        make use of UML networking.
+
+config UML_NET_ETHERTAP
+	bool "Ethertap transport"
+	depends on UML_NET
+	help
+        The Ethertap User-Mode Linux network transport allows a single
+        running UML to exchange packets with its host over one of the
+        host's Ethertap devices, such as /dev/tap0.  Additional running
+        UMLs can use additional Ethertap devices, one per running UML.
+        While the UML believes it's on a (multi-device, broadcast) virtual
+        Ethernet network, it's in fact communicating over a point-to-point
+        link with the host.
+
+        To use this, your host kernel must have support for Ethertap
+        devices.  Also, if your host kernel is 2.4.x, it must have
+        CONFIG_NETLINK_DEV configured as Y or M.
+
+        For more information, see
+        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
+        has examples of the UML command line to use to enable Ethertap
+        networking.
+
+        If you'd like to set up an IP network with the host and/or the
+        outside world, say Y to this, the Daemon Transport and/or the
+        Slip Transport.  You'll need at least one of them, but may choose
+        more than one without conflict.  If you don't need UML networking,
+        say N.
+
+config UML_NET_TUNTAP
+	bool "TUN/TAP transport"
+	depends on UML_NET
+	help
+        The UML TUN/TAP network transport allows a UML instance to exchange
+        packets with the host over a TUN/TAP device.  This option will only
+        work with a 2.4 host, unless you've applied the TUN/TAP patch to
+        your 2.2 host kernel.
+
+        To use this transport, your host kernel must have support for TUN/TAP
+        devices, either built-in or as a module.
+
+config UML_NET_SLIP
+	bool "SLIP transport"
+	depends on UML_NET
+	help
+        The slip User-Mode Linux network transport allows a running UML to
+        network with its host over a point-to-point link.  Unlike Ethertap,
+        which can carry any Ethernet frame (and hence even non-IP packets),
+        the slip transport can only carry IP packets.
+
+        To use this, your host must support slip devices.
+
+        For more information, see
+        <http://user-mode-linux.sourceforge.net/old/networking.html>.
+        has examples of the UML command line to use to enable slip
+        networking, and details of a few quirks with it.
+
+        The Ethertap Transport is preferred over slip because of its
+        limitations.  If you prefer slip, however, say Y here.  Otherwise
+        choose the Multicast transport (to network multiple UMLs on
+        multiple hosts), Ethertap (to network with the host and the
+        outside world), and/or the Daemon transport (to network multiple
+        UMLs on a single host).  You may choose more than one without
+        conflict.  If you don't need UML networking, say N.
+
+config UML_NET_DAEMON
+	bool "Daemon transport"
+	depends on UML_NET
+	help
+        This User-Mode Linux network transport allows one or more running
+        UMLs on a single host to communicate with each other, but not to
+        the host.
+
+        To use this form of networking, you'll need to run the UML
+        networking daemon on the host.
+
+        For more information, see
+        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
+        has examples of the UML command line to use to enable Daemon
+        networking.
+
+        If you'd like to set up a network with other UMLs on a single host,
+        say Y.  If you need a network between UMLs on multiple physical
+        hosts, choose the Multicast Transport.  To set up a network with
+        the host and/or other IP machines, say Y to the Ethertap or Slip
+        transports.  You'll need at least one of them, but may choose
+        more than one without conflict.  If you don't need UML networking,
+        say N.
+
+config UML_NET_VECTOR
+	bool "Vector I/O high performance network devices"
+	depends on UML_NET
+	help
+	This User-Mode Linux network driver uses multi-message send
+	and receive functions. The host running the UML guest must have
+	a linux kernel version above 3.0 and a libc version > 2.13.
+	This driver provides tap, raw, gre and l2tpv3 network transports
+	with up to 4 times higher network throughput than the UML network
+	drivers.
+
+config UML_NET_VDE
+	bool "VDE transport"
+	depends on UML_NET
+	help
+	This User-Mode Linux network transport allows one or more running
+	UMLs on a single host to communicate with each other and also
+	with the rest of the world using Virtual Distributed Ethernet,
+	an improved fork of uml_switch.
+
+	You must have libvdeplug installed in order to build the vde
+	transport into UML.
+
+	To use this form of networking, you will need to run vde_switch
+	on the host.
+
+	For more information, see <http://wiki.virtualsquare.org/>
+	That site has a good overview of what VDE is and also examples
+	of the UML command line to use to enable VDE networking.
+
+	If you need UML networking with VDE,
+	say Y.
+
+config UML_NET_MCAST
+	bool "Multicast transport"
+	depends on UML_NET
+	help
+        This Multicast User-Mode Linux network transport allows multiple
+        UMLs (even ones running on different host machines!) to talk to
+        each other over a virtual ethernet network.  However, it requires
+        at least one UML with one of the other transports to act as a
+        bridge if any of them need to be able to talk to their hosts or any
+        other IP machines.
+
+        To use this, your host kernel(s) must support IP Multicasting.
+
+        For more information, see
+        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
+        has examples of the UML command line to use to enable Multicast
+        networking, and notes about the security of this approach.
+
+        If you need UMLs on multiple physical hosts to communicate as if
+        they shared an Ethernet network, say Y.  If you need to communicate
+        with other IP machines, make sure you select one of the other
+        transports (possibly in addition to Multicast; they're not
+        exclusive).  If you don't need to network UMLs say N to each of
+        the transports.
+
+config UML_NET_PCAP
+	bool "pcap transport"
+	depends on UML_NET
+	help
+	The pcap transport makes a pcap packet stream on the host look
+	like an ethernet device inside UML.  This is useful for making
+	UML act as a network monitor for the host.  You must have libcap
+	installed in order to build the pcap transport into UML.
+
+        For more information, see
+        <http://user-mode-linux.sourceforge.net/old/networking.html>  That site
+        has examples of the UML command line to use to enable this option.
+
+	If you intend to use UML as a network monitor for the host, say
+	Y here.  Otherwise, say N.
+
+config UML_NET_SLIRP
+	bool "SLiRP transport"
+	depends on UML_NET
+	help
+        The SLiRP User-Mode Linux network transport allows a running UML
+        to network by invoking a program that can handle SLIP encapsulated
+        packets.  This is commonly (but not limited to) the application
+        known as SLiRP, a program that can re-socket IP packets back onto
+        the host on which it is run.  Only IP packets are supported,
+        unlike other network transports that can handle all Ethernet
+        frames.  In general, slirp allows the UML the same IP connectivity
+        to the outside world that the host user is permitted, and unlike
+        other transports, SLiRP works without the need of root level
+        privleges, setuid binaries, or SLIP devices on the host.  This
+        also means not every type of connection is possible, but most
+        situations can be accommodated with carefully crafted slirp
+        commands that can be passed along as part of the network device's
+        setup string.  The effect of this transport on the UML is similar
+        that of a host behind a firewall that masquerades all network
+        connections passing through it (but is less secure).
+
+        To use this you should first have slirp compiled somewhere
+        accessible on the host, and have read its documentation.  If you
+        don't need UML networking, say N.
+
+        Startup example: "eth0=slirp,FE:FD:01:02:03:04,/usr/local/bin/slirp"
+
+endmenu
-- 
cgit v1.2.3


From 17c46a6aff5c423f406adfb06eb832f771c06bd1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:29 +0200
Subject: kconfig: remove duplicate SWAP symbol defintions

microblaze and nios2 define their own always n SWAP symbols.  Remove those
and let the generic defintion do the right thing by adding a new symbol
to disable swap entirely.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/microblaze/Kconfig | 4 +---
 arch/nios2/Kconfig      | 4 +---
 init/Kconfig            | 9 ++++++++-
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index d14782100088..cc139d1b1284 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -1,5 +1,6 @@
 config MICROBLAZE
 	def_bool y
+	select ARCH_NO_SWAP
 	select ARCH_HAS_GCOV_PROFILE_ALL
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
@@ -52,9 +53,6 @@ config CPU_LITTLE_ENDIAN
 
 endchoice
 
-config SWAP
-	def_bool n
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 3d4ec88f1db1..3f9d4ef8b20f 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0
 config NIOS2
 	def_bool y
+	select ARCH_NO_SWAP
 	select TIMER_OF
 	select GENERIC_ATOMIC64
 	select GENERIC_CLOCKEVENTS
@@ -38,9 +39,6 @@ config HAS_DMA
 config FPU
 	def_bool n
 
-config SWAP
-	def_bool n
-
 config RWSEM_GENERIC_SPINLOCK
 	def_bool y
 
diff --git a/init/Kconfig b/init/Kconfig
index 041f3a022122..1e69f93b809e 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -218,9 +218,16 @@ config DEFAULT_HOSTNAME
 	  but you may wish to use a different default here to make a minimal
 	  system more usable with less configuration.
 
+#
+# For some reason microblaze and nios2 hard code SWAP=n.  Hopefully we can
+# add proper SWAP support to them, in which case this can be remove.
+#
+config ARCH_NO_SWAP
+	bool
+
 config SWAP
 	bool "Support for paging of anonymous memory (swap)"
-	depends on MMU && BLOCK
+	depends on MMU && BLOCK && !ARCH_NO_SWAP
 	default y
 	help
 	  This option allows you to choose whether you want to have support
-- 
cgit v1.2.3


From 1572497cb0e6d2016078bc9d5a95786bb878389f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:30 +0200
Subject: kconfig: include common Kconfig files from top-level Kconfig

Instead of duplicating the source statements in every architecture just
do it once in the toplevel Kconfig file.

Note that with this the inclusion of arch/$(SRCARCH/Kconfig moves out of
the top-level Kconfig into arch/Kconfig so that don't violate ordering
constraits while keeping a sensible menu structure.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Kconfig                 | 22 +++++++++++++++++++++-
 arch/Kconfig            |  6 ++++++
 arch/alpha/Kconfig      | 20 --------------------
 arch/arc/Kconfig        | 16 ----------------
 arch/arm/Kconfig        | 23 -----------------------
 arch/arm64/Kconfig      | 23 -----------------------
 arch/c6x/Kconfig        | 24 ------------------------
 arch/h8300/Kconfig      | 24 ------------------------
 arch/hexagon/Kconfig    | 16 ----------------
 arch/ia64/Kconfig       | 20 --------------------
 arch/m68k/Kconfig       | 24 ------------------------
 arch/microblaze/Kconfig | 24 ------------------------
 arch/mips/Kconfig       | 24 ------------------------
 arch/nds32/Kconfig      | 16 ----------------
 arch/nios2/Kconfig      | 24 ------------------------
 arch/openrisc/Kconfig   | 23 -----------------------
 arch/parisc/Kconfig     | 24 ------------------------
 arch/powerpc/Kconfig    | 19 -------------------
 arch/riscv/Kconfig      | 24 ------------------------
 arch/s390/Kconfig       | 24 ------------------------
 arch/sh/Kconfig         | 22 ----------------------
 arch/sh/mm/Kconfig      |  2 --
 arch/sparc/Kconfig      | 24 ------------------------
 arch/um/Kconfig         | 20 --------------------
 arch/unicore32/Kconfig  | 24 ------------------------
 arch/x86/Kconfig        | 22 +---------------------
 arch/xtensa/Kconfig     | 25 -------------------------
 init/Kconfig            |  4 ++--
 28 files changed, 30 insertions(+), 533 deletions(-)

diff --git a/Kconfig b/Kconfig
index a90d9f9e268b..1a5c0a5d4ea1 100644
--- a/Kconfig
+++ b/Kconfig
@@ -9,4 +9,24 @@ comment "Compiler: $(CC_VERSION_TEXT)"
 
 source "scripts/Kconfig.include"
 
-source "arch/$(SRCARCH)/Kconfig"
+source "init/Kconfig"
+
+source "kernel/Kconfig.freezer"
+
+menu "Executable file formats"
+source "fs/Kconfig.binfmt"
+endmenu
+
+source "mm/Kconfig"
+
+source "net/Kconfig"
+
+source "drivers/Kconfig"
+
+source "fs/Kconfig"
+
+source "security/Kconfig"
+
+source "crypto/Kconfig"
+
+source "lib/Kconfig"
diff --git a/arch/Kconfig b/arch/Kconfig
index 1aa59063f1fd..09a561a70168 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -3,6 +3,12 @@
 # General architecture dependent options
 #
 
+#
+# Note: arch/$(SRCARCH)/Kconfig needs to be included first so that it can
+# override the default values in this file.
+#
+source "arch/$(SRCARCH)/Kconfig"
+
 config CRASH_CORE
 	bool
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 04a4a138ed13..50676152babd 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -74,9 +74,6 @@ config PGTABLE_LEVELS
 	int
 	default 3
 
-source "init/Kconfig"
-source "kernel/Kconfig.freezer"
-
 config AUDIT_ARCH
 	bool
 
@@ -573,8 +570,6 @@ config ARCH_DISCONTIGMEM_ENABLE
 	  or have huge holes in the physical address space for other reasons.
 	  See <file:Documentation/vm/numa.rst> for more.
 
-source "mm/Kconfig"
-
 config NUMA
 	bool "NUMA Support (EXPERIMENTAL)"
 	depends on DISCONTIGMEM && BROKEN
@@ -713,16 +708,8 @@ config SRM_ENV
 	  This driver is also available as a module and will be called
 	  srm_env then.
 
-source "fs/Kconfig.binfmt"
-
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 source "arch/alpha/Kconfig.debug"
 
 # DUMMY_CONSOLE may be defined in drivers/video/console/Kconfig
@@ -731,10 +718,3 @@ config DUMMY_CONSOLE
 	bool
 	depends on VGA_HOSE
 	default y
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index e81bcd271be7..d4a28c45c406 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -94,9 +94,6 @@ config HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	def_bool y
 	depends on ARC_MMU_V4
 
-source "init/Kconfig"
-source "kernel/Kconfig.freezer"
-
 menu "ARC Architecture Configuration"
 
 menu "ARC Platform/SoC/Board"
@@ -550,22 +547,13 @@ config ARC_BUILTIN_DTB_NAME
 
 source "kernel/Kconfig.preempt"
 
-menu "Executable file formats"
-source "fs/Kconfig.binfmt"
-endmenu
-
 endmenu	 # "ARC Architecture Configuration"
 
-source "mm/Kconfig"
-
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	default "12" if ARC_HUGEPAGE_16M
 	default "11"
 
-source "net/Kconfig"
-source "drivers/Kconfig"
-
 menu "Bus Support"
 
 config PCI
@@ -586,9 +574,5 @@ source "drivers/pci/Kconfig"
 
 endmenu
 
-source "fs/Kconfig"
 source "arch/arc/Kconfig.debug"
-source "security/Kconfig"
-source "crypto/Kconfig"
-source "lib/Kconfig"
 source "kernel/power/Kconfig"
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 843edfd000be..46ee6669204b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -298,10 +298,6 @@ config PGTABLE_LEVELS
 	default 3 if ARM_LPAE
 	default 2
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 menu "System Type"
 
 config MMU
@@ -1721,8 +1717,6 @@ config ARM_MODULE_PLTS
 	  Disabling this is usually safe for small single-platform
 	  configurations. If unsure, say y.
 
-source "mm/Kconfig"
-
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	default "12" if SOC_AM33XX
@@ -2175,12 +2169,6 @@ config KERNEL_MODE_NEON
 
 endmenu
 
-menu "Userspace binary formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
 menu "Power management options"
 
 source "kernel/power/Kconfig"
@@ -2201,23 +2189,12 @@ config ARCH_HIBERNATION_POSSIBLE
 
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
 source "drivers/firmware/Kconfig"
 
-source "fs/Kconfig"
-
 source "arch/arm/Kconfig.debug"
 
-source "security/Kconfig"
-
-source "crypto/Kconfig"
 if CRYPTO
 source "arch/arm/crypto/Kconfig"
 endif
 
-source "lib/Kconfig"
-
 source "arch/arm/kvm/Kconfig"
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 42c090cf0292..fabd797c8645 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -267,10 +267,6 @@ config ARCH_PROC_KCORE_TEXT
 config MULTI_IRQ_HANDLER
 	def_bool y
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 source "arch/arm64/Kconfig.platforms"
 
 menu "Bus support"
@@ -791,8 +787,6 @@ config ARCH_WANT_HUGE_PMD_SHARE
 config ARCH_HAS_CACHE_LINE_SIZE
 	def_bool y
 
-source "mm/Kconfig"
-
 config SECCOMP
 	bool "Enable seccomp to safely compute untrusted bytecode"
 	---help---
@@ -1273,10 +1267,6 @@ config DMI
 
 endmenu
 
-menu "Userspace binary formats"
-
-source "fs/Kconfig.binfmt"
-
 config COMPAT
 	bool "Kernel support for 32-bit EL0"
 	depends on ARM64_4K_PAGES || EXPERT
@@ -1300,8 +1290,6 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
-endmenu
-
 menu "Power management options"
 
 source "kernel/power/Kconfig"
@@ -1327,25 +1315,14 @@ source "drivers/cpufreq/Kconfig"
 
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
 source "drivers/firmware/Kconfig"
 
 source "drivers/acpi/Kconfig"
 
-source "fs/Kconfig"
-
 source "arch/arm64/kvm/Kconfig"
 
 source "arch/arm64/Kconfig.debug"
 
-source "security/Kconfig"
-
-source "crypto/Kconfig"
 if CRYPTO
 source "arch/arm64/crypto/Kconfig"
 endif
-
-source "lib/Kconfig"
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index bf59855628ac..441bbe089b96 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -53,12 +53,8 @@ config C6X_BIG_KERNEL
 
 	  If unsure, say N.
 
-source "init/Kconfig"
-
 # Use the generic interrupt handling code in kernel/irq/
 
-source "kernel/Kconfig.freezer"
-
 config CMDLINE_BOOL
 	bool "Default bootloader kernel arguments"
 
@@ -114,32 +110,12 @@ config KERNEL_RAM_BASE_ADDRESS
 	default 0xe0000000 if SOC_TMS320C6472
 	default 0x80000000
 
-source "mm/Kconfig"
-
 source "kernel/Kconfig.preempt"
 
 source "kernel/Kconfig.hz"
 
 endmenu
 
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
 menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index 091d6d04b5e5..e23cd887f8f9 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -48,40 +48,16 @@ config NR_CPUS
 	int
 	default 1
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 source "arch/h8300/Kconfig.cpu"
 
 menu "Kernel Features"
 
 source "kernel/Kconfig.preempt"
 
-source "mm/Kconfig"
-
-endmenu
-
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
 endmenu
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index 37adb2003033..d2851f46a64b 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -146,26 +146,10 @@ config PAGE_SIZE_256KB
 
 endchoice
 
-source "mm/Kconfig"
-
 source "kernel/Kconfig.hz"
 
 endmenu
 
-source "init/Kconfig"
-source "kernel/Kconfig.freezer"
-source "drivers/Kconfig"
-source "fs/Kconfig"
-
-menu "Executable File Formats"
-source "fs/Kconfig.binfmt"
-endmenu
-
-source "net/Kconfig"
-source "security/Kconfig"
-source "crypto/Kconfig"
-source "lib/Kconfig"
-
 menu "Kernel hacking"
 source "lib/Kconfig.debug"
 endmenu
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index ff861420b8f5..6015d66fa521 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -4,10 +4,6 @@ config PGTABLE_LEVELS
 	range 3 4 if !IA64_PAGE_SIZE_64KB
 	default 3
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 menu "Processor type and features"
 
 config IA64
@@ -370,8 +366,6 @@ config FORCE_CPEI_RETARGET
 
 source "kernel/Kconfig.preempt"
 
-source "mm/Kconfig"
-
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 
@@ -532,8 +526,6 @@ config CRASH_DUMP
 
 source "drivers/firmware/Kconfig"
 
-source "fs/Kconfig.binfmt"
-
 endmenu
 
 menu "Power management and ACPI options"
@@ -574,10 +566,6 @@ endmenu
 
 endif
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
 source "arch/ia64/hp/sim/Kconfig"
 
 config MSPEC
@@ -589,12 +577,4 @@ config MSPEC
 	  operations support (formerly known as fetchop), say Y here,
 	  otherwise say N.
 
-source "fs/Kconfig"
-
 source "arch/ia64/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index 785612b576f7..f76fb7bb371f 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -75,10 +75,6 @@ config PGTABLE_LEVELS
 	default 2 if SUN3 || COLDFIRE
 	default 3
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 config MMU
 	bool "MMU-based Paged Memory Management Support"
 	default y
@@ -137,14 +133,6 @@ if COLDFIRE
 source "kernel/Kconfig.preempt"
 endif
 
-source "mm/Kconfig"
-
-endmenu
-
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
 endmenu
 
 if !MMU
@@ -158,18 +146,6 @@ config PM
 endmenu
 endif
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
 source "arch/m68k/Kconfig.devices"
 
-source "fs/Kconfig"
-
 source "arch/m68k/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index cc139d1b1284..fc31e047a43a 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -83,10 +83,6 @@ config STACKTRACE_SUPPORT
 config LOCKDEP_SUPPORT
 	def_bool y
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 source "arch/microblaze/Kconfig.platform"
 
 menu "Processor type and features"
@@ -266,14 +262,6 @@ config MICROBLAZE_64K_PAGES
 
 endchoice
 
-source "mm/Kconfig"
-
-endmenu
-
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
 endmenu
 
 menu "Bus Options"
@@ -298,16 +286,4 @@ source "drivers/pci/Kconfig"
 
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 source "arch/microblaze/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 08c10c518f83..f586a3259f7f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2641,8 +2641,6 @@ config HW_PERF_EVENTS
 	  Enable hardware performance counter support for perf events. If
 	  disabled, perf events will use software events only.
 
-source "mm/Kconfig"
-
 config SMP
 	bool "Multi-Processing support"
 	depends on SYS_SUPPORTS_SMP
@@ -2994,10 +2992,6 @@ config PGTABLE_LEVELS
 	default 3 if 64BIT && !PAGE_SIZE_64KB
 	default 2
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 menu "Bus options (PCI, PCMCIA, EISA, ISA, TC)"
 
 config HW_HAS_EISA
@@ -3127,10 +3121,6 @@ source "drivers/rapidio/Kconfig"
 
 endmenu
 
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
 config TRAD_SIGNALS
 	bool
 
@@ -3176,8 +3166,6 @@ config BINFMT_ELF32
 	default y if MIPS32_O32 || MIPS32_N32
 	select ELFCORE
 
-endmenu
-
 menu "Power management options"
 
 config ARCH_HIBERNATION_POSSIBLE
@@ -3205,20 +3193,8 @@ source "drivers/cpuidle/Kconfig"
 
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
 source "drivers/firmware/Kconfig"
 
-source "fs/Kconfig"
-
 source "arch/mips/Kconfig.debug"
 
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
 source "arch/mips/kvm/Kconfig"
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index 6aed974276d8..a9c6d25a14f0 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -71,8 +71,6 @@ config FIX_EARLYCON_MEM
 config PGTABLE_LEVELS
 	default 2
 
-source "init/Kconfig"
-
 menu "System Type"
 source "arch/nds32/Kconfig.cpu"
 config NR_CPUS
@@ -91,23 +89,9 @@ endmenu
 
 menu "Kernel Features"
 source "kernel/Kconfig.preempt"
-source "kernel/Kconfig.freezer"
-source "mm/Kconfig"
 source "kernel/Kconfig.hz"
 endmenu
 
-menu "Executable file formats"
-source "fs/Kconfig.binfmt"
-endmenu
-
-source "net/Kconfig"
-source "drivers/Kconfig"
-source "fs/Kconfig"
-
 menu "Kernel hacking"
 source "lib/Kconfig.debug"
 endmenu
-
-source "security/Kconfig"
-source "crypto/Kconfig"
-source "lib/Kconfig"
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 3f9d4ef8b20f..2d813dfdb8cb 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -45,18 +45,12 @@ config RWSEM_GENERIC_SPINLOCK
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool n
 
-source "init/Kconfig"
-
 menu "Kernel features"
 
 source "kernel/Kconfig.preempt"
 
-source "kernel/Kconfig.freezer"
-
 source "kernel/Kconfig.hz"
 
-source "mm/Kconfig"
-
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	range 9 20
@@ -194,22 +188,4 @@ config NIOS2_IO_REGION_BASE
 
 endmenu
 
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 source "arch/nios2/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 9ecad05bfc73..eb9f503c8972 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -72,10 +72,6 @@ config LOCKDEP_SUPPORT
 config MULTI_IRQ_HANDLER
 	def_bool y
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 menu "Processor type and features"
 
 choice
@@ -148,7 +144,6 @@ config SMP
 
 source kernel/Kconfig.hz
 source kernel/Kconfig.preempt
-source "mm/Kconfig"
 
 config OPENRISC_NO_SPR_SR_DSX
 	bool "use SPR_SR_DSX software emulation" if OR1K_1200
@@ -207,24 +202,6 @@ endmenu
 
 endmenu
 
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
 menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 17526bebcbd2..64b832a19bdf 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -129,10 +129,6 @@ config PGTABLE_LEVELS
 config SYS_SUPPORTS_HUGETLBFS
 	def_bool y if PA20
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 
 menu "Processor type and features"
 
@@ -329,7 +325,6 @@ config NODES_SHIFT
 
 source "kernel/Kconfig.preempt"
 source "kernel/Kconfig.hz"
-source "mm/Kconfig"
 
 config COMPAT
 	def_bool y
@@ -354,19 +349,6 @@ endmenu
 
 source "drivers/parisc/Kconfig"
 
-
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 source "arch/parisc/Kconfig.debug"
 
 config SECCOMP
@@ -384,9 +366,3 @@ config SECCOMP
 	  defined by each seccomp mode.
 
 	  If unsure, say Y. Only embedded should say N here.
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 9f2b75fe2c2d..131132f161e5 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -383,10 +383,6 @@ config PGTABLE_LEVELS
 	default 3 if PPC_64K_PAGES && !PPC_BOOK3S_64
 	default 4
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 source "arch/powerpc/sysdev/Kconfig"
 source "arch/powerpc/platforms/Kconfig"
 
@@ -398,7 +394,6 @@ config HIGHMEM
 
 source kernel/Kconfig.hz
 source kernel/Kconfig.preempt
-source "fs/Kconfig.binfmt"
 
 config HUGETLB_PAGE_SIZE_VARIABLE
 	bool
@@ -641,8 +636,6 @@ config ILLEGAL_POINTER_VALUE
 	default 0x5deadbeef0000000 if PPC64
 	default 0
 
-source "mm/Kconfig"
-
 config ARCH_MEMORY_PROBE
 	def_bool y
 	depends on MEMORY_HOTPLUG
@@ -1201,20 +1194,8 @@ endif
 config	ARCH_RANDOM
 	def_bool n
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
-source "lib/Kconfig"
-
 source "arch/powerpc/Kconfig.debug"
 
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
 config PPC_LIB_RHEAP
 	bool
 
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 4764fdeb4f1f..082486cddf31 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -212,8 +212,6 @@ endmenu
 
 menu "Kernel type"
 
-source "mm/Kconfig"
-
 source "kernel/Kconfig.preempt"
 
 source "kernel/Kconfig.hz"
@@ -242,28 +240,12 @@ source "drivers/pci/Kconfig"
 
 endmenu
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
 menu "Power management options"
 
 source kernel/power/Kconfig
 
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 menu "Kernel hacking"
 
 config CMDLINE_BOOL
@@ -308,9 +290,3 @@ source "lib/Kconfig.debug"
 config CMDLINE_BOOL
 	bool
 endmenu
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index e44bb2b2873e..a94667712337 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -184,10 +184,6 @@ config PGTABLE_LEVELS
 	int
 	default 5
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 source "kernel/livepatch/Kconfig"
 
 menu "Processor type and features"
@@ -627,8 +623,6 @@ config FORCE_MAX_ZONEORDER
 	int
 	default "9"
 
-source "mm/Kconfig"
-
 config MAX_PHYSMEM_BITS
 	int "Maximum size of supported physical memory in bits (42-53)"
 	range 42 53
@@ -798,10 +792,6 @@ config CRASH_DUMP
 
 endmenu
 
-menu "Executable file formats / Emulations"
-
-source "fs/Kconfig.binfmt"
-
 config SECCOMP
 	def_bool y
 	prompt "Enable seccomp to safely compute untrusted bytecode"
@@ -819,8 +809,6 @@ config SECCOMP
 
 	  If unsure, say Y.
 
-endmenu
-
 menu "Power Management"
 
 config ARCH_HIBERNATION_POSSIBLE
@@ -830,30 +818,18 @@ source "kernel/power/Kconfig"
 
 endmenu
 
-source "net/Kconfig"
-
 config PCMCIA
 	def_bool n
 
 config CCW
 	def_bool y
 
-source "drivers/Kconfig"
-
 config HAVE_PNETID
 	tristate
 	default (SMC || CCWGROUP)
 
-source "fs/Kconfig"
-
 source "arch/s390/Kconfig.debug"
 
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
 menu "Virtualization"
 
 config PFAULT
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index dd4f3d3e644f..f291d2568cd4 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -168,10 +168,6 @@ config PGTABLE_LEVELS
 	default 3 if X2TLB
 	default 2
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 menu "System type"
 
 #
@@ -882,12 +878,6 @@ source "drivers/pcmcia/Kconfig"
 
 endmenu
 
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
 menu "Power management options (EXPERIMENTAL)"
 
 source "kernel/power/Kconfig"
@@ -896,16 +886,4 @@ source "drivers/cpuidle/Kconfig"
 
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 source "arch/sh/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/sh/mm/Kconfig b/arch/sh/mm/Kconfig
index 50cdd1349015..02ed2df25a54 100644
--- a/arch/sh/mm/Kconfig
+++ b/arch/sh/mm/Kconfig
@@ -225,8 +225,6 @@ config HUGETLB_PAGE_SIZE_512MB
 
 endchoice
 
-source "mm/Kconfig"
-
 config SCHED_MC
 	bool "Multi-core scheduler support"
 	depends on SMP
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 0f535debf802..8a1e44d2e112 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -155,10 +155,6 @@ config PGTABLE_LEVELS
 config ARCH_SUPPORTS_UPROBES
 	def_bool y if SPARC64
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 menu "Processor type and features"
 
 config SMP
@@ -331,8 +327,6 @@ config FORCE_MAX_ZONEORDER
 	  This config option is actually maximum order plus one. For example,
 	  a value of 13 means that the largest free memory block is 2^12 pages.
 
-source "mm/Kconfig"
-
 if SPARC64
 source "kernel/power/Kconfig"
 endif
@@ -556,10 +550,6 @@ config SPARC64_PCI_MSI
 
 endmenu
 
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
 config COMPAT
 	bool
 	depends on SPARC64
@@ -574,20 +564,6 @@ config SYSVIPC_COMPAT
 	depends on COMPAT && SYSVIPC
 	default y
 
-endmenu
-
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
 source "drivers/sbus/char/Kconfig"
 
-source "fs/Kconfig"
-
 source "arch/sparc/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index ea35bf91fc0f..a5cc2b19a960 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -75,8 +75,6 @@ config STATIC_LINK
 	  Additionally, this option enables using higher memory spaces (up to
 	  2.75G) for UML.
 
-source "mm/Kconfig"
-
 config LD_SCRIPT_STATIC
 	bool
 	default y
@@ -88,8 +86,6 @@ config LD_SCRIPT_DYN
 	depends on !LD_SCRIPT_STATIC
         select MODULE_REL_CRCS if MODVERSIONS
 
-source "fs/Kconfig.binfmt"
-
 config HOSTFS
 	tristate "Host filesystem"
 	help
@@ -190,22 +186,6 @@ config SECCOMP
 
 endmenu
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 source "arch/um/drivers/Kconfig"
 
-source "drivers/Kconfig"
-
-source "net/Kconfig"
-
-source "fs/Kconfig"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
 source "arch/um/Kconfig.debug"
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 03f991e44288..7fa7e61eb19f 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -63,10 +63,6 @@ config ARCH_MAY_HAVE_PC_FDC
 config ZONE_DMA
 	def_bool y
 
-source "init/Kconfig"
-
-source "kernel/Kconfig.freezer"
-
 menu "System Type"
 
 config MMU
@@ -143,8 +139,6 @@ source "kernel/Kconfig.preempt"
 
 source "kernel/Kconfig.hz"
 
-source "mm/Kconfig"
-
 config LEDS
 	def_bool y
 	depends on GPIOLIB
@@ -181,12 +175,6 @@ config CMDLINE_FORCE
 
 endmenu
 
-menu "Userspace binary formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
 menu "Power management options"
 
 source "kernel/power/Kconfig"
@@ -201,8 +189,6 @@ config ARCH_HIBERNATION_POSSIBLE
 
 endmenu
 
-source "net/Kconfig"
-
 if ARCH_PUV3
 
 config PUV3_GPIO
@@ -237,14 +223,4 @@ endif
 
 endif
 
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 source "arch/unicore32/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index f1dbb4ee19d7..6faefd1c9f13 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -345,8 +345,6 @@ config PGTABLE_LEVELS
 	default 3 if X86_PAE
 	default 2
 
-source "init/Kconfig"
-
 config CC_HAS_SANE_STACKPROTECTOR
 	bool
 	default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC)) if 64BIT
@@ -355,8 +353,6 @@ config CC_HAS_SANE_STACKPROTECTOR
 	   We have to make sure stack protector is unconditionally disabled if
 	   the compiler produces broken code.
 
-source "kernel/Kconfig.freezer"
-
 menu "Processor type and features"
 
 config ZONE_DMA
@@ -1638,8 +1634,6 @@ config ILLEGAL_POINTER_VALUE
        default 0 if X86_32
        default 0xdead000000000000 if X86_64
 
-source "mm/Kconfig"
-
 config X86_PMEM_LEGACY_DEVICE
 	bool
 
@@ -2865,9 +2859,7 @@ config X86_SYSFB
 endmenu
 
 
-menu "Executable file formats / Emulations"
-
-source "fs/Kconfig.binfmt"
+menu "Binary Emulations"
 
 config IA32_EMULATION
 	bool "IA32 Emulation"
@@ -2937,20 +2929,8 @@ config X86_DMA_REMAP
 config HAVE_GENERIC_GUP
 	def_bool y
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
 source "drivers/firmware/Kconfig"
 
-source "fs/Kconfig"
-
 source "arch/x86/Kconfig.debug"
 
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
 source "arch/x86/kvm/Kconfig"
-
-source "lib/Kconfig"
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index d575e8701955..d8bac8be3a33 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -60,9 +60,6 @@ config HZ
 	int
 	default 100
 
-source "init/Kconfig"
-source "kernel/Kconfig.freezer"
-
 config LOCKDEP_SUPPORT
 	def_bool y
 
@@ -491,8 +488,6 @@ config SIMDISK1_FILENAME
 	  Another simulated disk in a host file for a buildroot-independent
 	  storage.
 
-source "mm/Kconfig"
-
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	default "11"
@@ -567,30 +562,10 @@ config XTFPGA_LCD_8BIT_ACCESS
 
 endmenu
 
-menu "Executable file formats"
-
-source "fs/Kconfig.binfmt"
-
-endmenu
-
 menu "Power management options"
 
 source "kernel/power/Kconfig"
 
 endmenu
 
-source "net/Kconfig"
-
-source "drivers/Kconfig"
-
-source "fs/Kconfig"
-
 source "arch/xtensa/Kconfig.debug"
-
-source "security/Kconfig"
-
-source "crypto/Kconfig"
-
-source "lib/Kconfig"
-
-
diff --git a/init/Kconfig b/init/Kconfig
index 1e69f93b809e..283f6bc796b1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1721,10 +1721,10 @@ config PROFILING
 config TRACEPOINTS
 	bool
 
-source "arch/Kconfig"
-
 endmenu		# General setup
 
+source "arch/Kconfig"
+
 config RT_MUTEXES
 	bool
 
-- 
cgit v1.2.3


From 06ec64b84c357693e9a5540de8eedfc775dbae12 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:31 +0200
Subject: Kconfig: consolidate the "Kernel hacking" menu

Move the source of lib/Kconfig.debug and arch/$(ARCH)/Kconfig.debug to
the top-level Kconfig.  For two architectures that means moving their
arch-specific symbols in that menu into a new arch Kconfig.debug file,
and for a few more creating a dummy file so that we can include it
unconditionally.

Also move the actual 'Kernel hacking' menu to lib/Kconfig.debug, where
it belongs.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Kconfig                       |  2 ++
 arch/alpha/Kconfig            |  2 --
 arch/alpha/Kconfig.debug      |  5 -----
 arch/arc/Kconfig              |  1 -
 arch/arc/Kconfig.debug        |  5 -----
 arch/arm/Kconfig              |  2 --
 arch/arm/Kconfig.debug        |  5 -----
 arch/arm64/Kconfig            |  2 --
 arch/arm64/Kconfig.debug      |  5 -----
 arch/c6x/Kconfig              | 15 ---------------
 arch/c6x/Kconfig.debug        | 10 ++++++++++
 arch/h8300/Kconfig            |  6 ------
 arch/h8300/Kconfig.debug      |  1 +
 arch/hexagon/Kconfig          |  4 ----
 arch/hexagon/Kconfig.debug    |  1 +
 arch/ia64/Kconfig             |  2 --
 arch/ia64/Kconfig.debug       |  5 -----
 arch/m68k/Kconfig             |  2 --
 arch/m68k/Kconfig.debug       |  5 -----
 arch/microblaze/Kconfig       |  2 --
 arch/microblaze/Kconfig.debug |  6 ------
 arch/mips/Kconfig             |  2 --
 arch/mips/Kconfig.debug       |  5 -----
 arch/nds32/Kconfig            |  4 ----
 arch/nds32/Kconfig.debug      |  1 +
 arch/nios2/Kconfig            |  2 --
 arch/nios2/Kconfig.debug      |  5 -----
 arch/openrisc/Kconfig         |  6 ------
 arch/openrisc/Kconfig.debug   |  1 +
 arch/parisc/Kconfig           |  2 --
 arch/parisc/Kconfig.debug     |  5 -----
 arch/powerpc/Kconfig          |  2 --
 arch/powerpc/Kconfig.debug    |  5 -----
 arch/riscv/Kconfig            | 45 -------------------------------------------
 arch/riscv/Kconfig.debug      | 37 +++++++++++++++++++++++++++++++++++
 arch/s390/Kconfig             |  2 --
 arch/s390/Kconfig.debug       |  5 -----
 arch/sh/Kconfig               |  2 --
 arch/sh/Kconfig.debug         |  5 -----
 arch/sparc/Kconfig            |  2 --
 arch/sparc/Kconfig.debug      |  5 -----
 arch/um/Kconfig               |  2 --
 arch/um/Kconfig.debug         |  5 -----
 arch/unicore32/Kconfig        |  2 --
 arch/unicore32/Kconfig.debug  |  5 -----
 arch/x86/Kconfig              |  2 --
 arch/x86/Kconfig.debug        |  5 -----
 arch/xtensa/Kconfig           |  2 --
 arch/xtensa/Kconfig.debug     |  5 -----
 lib/Kconfig.debug             |  6 ++++++
 50 files changed, 59 insertions(+), 206 deletions(-)
 create mode 100644 arch/c6x/Kconfig.debug
 create mode 100644 arch/h8300/Kconfig.debug
 create mode 100644 arch/hexagon/Kconfig.debug
 create mode 100644 arch/nds32/Kconfig.debug
 create mode 100644 arch/openrisc/Kconfig.debug
 create mode 100644 arch/riscv/Kconfig.debug

diff --git a/Kconfig b/Kconfig
index 1a5c0a5d4ea1..a5997d6c2029 100644
--- a/Kconfig
+++ b/Kconfig
@@ -30,3 +30,5 @@ source "security/Kconfig"
 source "crypto/Kconfig"
 
 source "lib/Kconfig"
+
+source "lib/Kconfig.debug"
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 50676152babd..e4334f017f8e 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -710,8 +710,6 @@ config SRM_ENV
 
 endmenu
 
-source "arch/alpha/Kconfig.debug"
-
 # DUMMY_CONSOLE may be defined in drivers/video/console/Kconfig
 # but we also need it if VGA_HOSE is set
 config DUMMY_CONSOLE
diff --git a/arch/alpha/Kconfig.debug b/arch/alpha/Kconfig.debug
index 5e93dffb818a..b88c7b641d72 100644
--- a/arch/alpha/Kconfig.debug
+++ b/arch/alpha/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config EARLY_PRINTK
 	bool
@@ -39,5 +36,3 @@ config MATHEMU
 	  This option is required for IEEE compliant floating point arithmetic
 	  on the Alpha. The only time you would ever not say Y is to say M in
 	  order to debug the code. Say Y unless you know what you are doing.
-
-endmenu
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index d4a28c45c406..5aab069eba17 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -574,5 +574,4 @@ source "drivers/pci/Kconfig"
 
 endmenu
 
-source "arch/arc/Kconfig.debug"
 source "kernel/power/Kconfig"
diff --git a/arch/arc/Kconfig.debug b/arch/arc/Kconfig.debug
index 03da1a6b3072..45add86decd5 100644
--- a/arch/arc/Kconfig.debug
+++ b/arch/arc/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config 16KSTACKS
 	bool "Use 16Kb for kernel stacks instead of 8Kb"
@@ -11,5 +8,3 @@ config 16KSTACKS
 	  This increases the resident kernel footprint and will cause less
 	  threads to run on the system and also increase the pressure
 	  on the VM subsystem for higher order allocations.
-
-endmenu
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 46ee6669204b..9aaa23c25374 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -2191,8 +2191,6 @@ endmenu
 
 source "drivers/firmware/Kconfig"
 
-source "arch/arm/Kconfig.debug"
-
 if CRYPTO
 source "arch/arm/crypto/Kconfig"
 endif
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 693f84392f1b..b48dc083d1b1 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config ARM_PTDUMP_CORE
 	def_bool n
@@ -1863,5 +1860,3 @@ config PID_IN_CONTEXTIDR
 	  are planning to use hardware trace tools with this kernel.
 
 source "drivers/hwtracing/coresight/Kconfig"
-
-endmenu
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fabd797c8645..07d457ec417a 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1321,8 +1321,6 @@ source "drivers/acpi/Kconfig"
 
 source "arch/arm64/kvm/Kconfig"
 
-source "arch/arm64/Kconfig.debug"
-
 if CRYPTO
 source "arch/arm64/crypto/Kconfig"
 endif
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index cc6bd559af85..69c9170bdd24 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -1,6 +1,3 @@
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config ARM64_PTDUMP_CORE
 	def_bool n
@@ -97,5 +94,3 @@ config ARM64_RELOC_TEST
 	tristate "Relocation testing module"
 
 source "drivers/hwtracing/coresight/Kconfig"
-
-endmenu
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 441bbe089b96..904b3375331e 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -115,18 +115,3 @@ source "kernel/Kconfig.preempt"
 source "kernel/Kconfig.hz"
 
 endmenu
-
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
-
-config ACCESS_CHECK
-	bool "Check the user pointer address"
-	default y
-	help
-	  Usually the pointer transfer from user space is checked to see if its
-	  address is in the kernel space.
-
-	  Say N here to disable that check to improve the performance.
-
-endmenu
diff --git a/arch/c6x/Kconfig.debug b/arch/c6x/Kconfig.debug
new file mode 100644
index 000000000000..c299e0d8eca3
--- /dev/null
+++ b/arch/c6x/Kconfig.debug
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+
+config ACCESS_CHECK
+	bool "Check the user pointer address"
+	default y
+	help
+	  Usually the pointer transfer from user space is checked to see if its
+	  address is in the kernel space.
+
+	  Say N here to disable that check to improve the performance.
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index e23cd887f8f9..c16e7cf732f7 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -55,9 +55,3 @@ menu "Kernel Features"
 source "kernel/Kconfig.preempt"
 
 endmenu
-
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
-
-endmenu
diff --git a/arch/h8300/Kconfig.debug b/arch/h8300/Kconfig.debug
new file mode 100644
index 000000000000..22a162cd99e8
--- /dev/null
+++ b/arch/h8300/Kconfig.debug
@@ -0,0 +1 @@
+# dummy file, do not delete
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index d2851f46a64b..fcdb6d9fcecc 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -149,7 +149,3 @@ endchoice
 source "kernel/Kconfig.hz"
 
 endmenu
-
-menu "Kernel hacking"
-source "lib/Kconfig.debug"
-endmenu
diff --git a/arch/hexagon/Kconfig.debug b/arch/hexagon/Kconfig.debug
new file mode 100644
index 000000000000..22a162cd99e8
--- /dev/null
+++ b/arch/hexagon/Kconfig.debug
@@ -0,0 +1 @@
+# dummy file, do not delete
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 6015d66fa521..34a8d24cffea 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -576,5 +576,3 @@ config MSPEC
 	  If you have an ia64 and you want to enable memory special
 	  operations support (formerly known as fetchop), say Y here,
 	  otherwise say N.
-
-source "arch/ia64/Kconfig.debug"
diff --git a/arch/ia64/Kconfig.debug b/arch/ia64/Kconfig.debug
index 677c409425df..1371efc9b005 100644
--- a/arch/ia64/Kconfig.debug
+++ b/arch/ia64/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 choice
 	prompt "Physical memory granularity"
@@ -56,5 +53,3 @@ config IA64_DEBUG_IRQ
 	  Selecting this option turns on bug checking for the IA-64 irq_save
 	  and restore instructions.  It's useful for tracking down spinlock
 	  problems, but slow!  If you're unsure, select N.
-
-endmenu
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index f76fb7bb371f..cf41ad45513f 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -147,5 +147,3 @@ endmenu
 endif
 
 source "arch/m68k/Kconfig.devices"
-
-source "arch/m68k/Kconfig.debug"
diff --git a/arch/m68k/Kconfig.debug b/arch/m68k/Kconfig.debug
index 04690b179a6e..f43643111eaf 100644
--- a/arch/m68k/Kconfig.debug
+++ b/arch/m68k/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config BOOTPARAM
 	bool 'Compiled-in Kernel Boot Parameter'
@@ -51,5 +48,3 @@ config BDM_DISABLE
 	  Disable the ColdFire CPU's BDM signals.
 
 endif
-
-endmenu
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index fc31e047a43a..f4492e9478fe 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -285,5 +285,3 @@ config PCI_XILINX
 source "drivers/pci/Kconfig"
 
 endmenu
-
-source "arch/microblaze/Kconfig.debug"
diff --git a/arch/microblaze/Kconfig.debug b/arch/microblaze/Kconfig.debug
index 93a737c8d1a6..dc2e3c45e8a2 100644
--- a/arch/microblaze/Kconfig.debug
+++ b/arch/microblaze/Kconfig.debug
@@ -1,11 +1,5 @@
 # For a description of the syntax of this configuration file,
 # see Documentation/kbuild/kconfig-language.txt.
 
-menu "Kernel hacking"
-
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
-
-source "lib/Kconfig.debug"
-
-endmenu
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index f586a3259f7f..ab02824c3976 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -3195,6 +3195,4 @@ endmenu
 
 source "drivers/firmware/Kconfig"
 
-source "arch/mips/Kconfig.debug"
-
 source "arch/mips/kvm/Kconfig"
diff --git a/arch/mips/Kconfig.debug b/arch/mips/Kconfig.debug
index 0749c3724543..0c86b2a2adfc 100644
--- a/arch/mips/Kconfig.debug
+++ b/arch/mips/Kconfig.debug
@@ -1,12 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
 
 config TRACE_IRQFLAGS_SUPPORT
 	bool
 	default y
 
-source "lib/Kconfig.debug"
-
 config EARLY_PRINTK
 	bool "Early printk" if EXPERT
 	depends on SYS_HAS_EARLY_PRINTK
@@ -155,5 +152,3 @@ config MIPS_CPS_NS16550_SHIFT
 	  adjacent ns16550 registers in the system.
 
 endif # MIPS_CPS_NS16550_BOOL
-
-endmenu
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index a9c6d25a14f0..c03d0e5a591b 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -91,7 +91,3 @@ menu "Kernel Features"
 source "kernel/Kconfig.preempt"
 source "kernel/Kconfig.hz"
 endmenu
-
-menu "Kernel hacking"
-source "lib/Kconfig.debug"
-endmenu
diff --git a/arch/nds32/Kconfig.debug b/arch/nds32/Kconfig.debug
new file mode 100644
index 000000000000..22a162cd99e8
--- /dev/null
+++ b/arch/nds32/Kconfig.debug
@@ -0,0 +1 @@
+# dummy file, do not delete
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 2d813dfdb8cb..22d19febcc92 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -187,5 +187,3 @@ config NIOS2_IO_REGION_BASE
 	default "0xe0000000"
 
 endmenu
-
-source "arch/nios2/Kconfig.debug"
diff --git a/arch/nios2/Kconfig.debug b/arch/nios2/Kconfig.debug
index edfeef049a51..7a49f0d28d14 100644
--- a/arch/nios2/Kconfig.debug
+++ b/arch/nios2/Kconfig.debug
@@ -1,11 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
 
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-source "lib/Kconfig.debug"
-
 config DEBUG_STACK_USAGE
 	bool "Enable stack utilization instrumentation"
 	depends on DEBUG_KERNEL
@@ -24,5 +21,3 @@ config EARLY_PRINTK
 	  This is useful for kernel debugging when your machine crashes very
 	  early before the console code is initialized.
 	  You should normally say N here, unless you want to debug such a crash.
-
-endmenu
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index eb9f503c8972..c52cecd94d62 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -201,9 +201,3 @@ config OPENRISC_ESR_EXCEPTION_BUG_CHECK
 endmenu
 
 endmenu
-
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
-
-endmenu
diff --git a/arch/openrisc/Kconfig.debug b/arch/openrisc/Kconfig.debug
new file mode 100644
index 000000000000..22a162cd99e8
--- /dev/null
+++ b/arch/openrisc/Kconfig.debug
@@ -0,0 +1 @@
+# dummy file, do not delete
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 64b832a19bdf..d1dd56ea297b 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -349,8 +349,6 @@ endmenu
 
 source "drivers/parisc/Kconfig"
 
-source "arch/parisc/Kconfig.debug"
-
 config SECCOMP
 	def_bool y
 	prompt "Enable seccomp to safely compute untrusted bytecode"
diff --git a/arch/parisc/Kconfig.debug b/arch/parisc/Kconfig.debug
index fb3507f9b14a..1478ded0e247 100644
--- a/arch/parisc/Kconfig.debug
+++ b/arch/parisc/Kconfig.debug
@@ -1,9 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
-
-endmenu
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 131132f161e5..c55e61302d57 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -1194,8 +1194,6 @@ endif
 config	ARCH_RANDOM
 	def_bool n
 
-source "arch/powerpc/Kconfig.debug"
-
 config PPC_LIB_RHEAP
 	bool
 
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index c45424c64e19..fd63cd914a74 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config PPC_DISABLE_WERROR
 	bool "Don't build arch/powerpc code with -Werror"
@@ -379,5 +376,3 @@ config PPC_FAST_ENDIAN_SWITCH
         depends on DEBUG_KERNEL && PPC_BOOK3S_64
         help
 	  If you're unsure what this is, say N.
-
-endmenu
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 082486cddf31..73c0e16793fa 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -245,48 +245,3 @@ menu "Power management options"
 source kernel/power/Kconfig
 
 endmenu
-
-menu "Kernel hacking"
-
-config CMDLINE_BOOL
-	bool "Built-in kernel command line"
-	help
-	  For most platforms, it is firmware or second stage bootloader
-	  that by default specifies the kernel command line options.
-	  However, it might be necessary or advantageous to either override
-	  the default kernel command line or add a few extra options to it.
-	  For such cases, this option allows hardcoding command line options
-	  directly into the kernel.
-
-	  For that, choose 'Y' here and fill in the extra boot parameters
-	  in CONFIG_CMDLINE.
-
-	  The built-in options will be concatenated to the default command
-	  line if CMDLINE_FORCE is set to 'N'. Otherwise, the default
-	  command line will be ignored and replaced by the built-in string.
-
-config CMDLINE
-	string "Built-in kernel command string"
-	depends on CMDLINE_BOOL
-	default ""
-	help
-	  Supply command-line options at build time by entering them here.
-
-config CMDLINE_FORCE
-	bool "Built-in command line overrides bootloader arguments"
-	depends on CMDLINE_BOOL
-	help
-	  Set this option to 'Y' to have the kernel ignore the bootloader
-	  or firmware command line.  Instead, the built-in command line
-	  will be used exclusively.
-
-	  If you don't know what to do here, say N.
-
-config EARLY_PRINTK
-	def_bool y
-
-source "lib/Kconfig.debug"
-
-config CMDLINE_BOOL
-	bool
-endmenu
diff --git a/arch/riscv/Kconfig.debug b/arch/riscv/Kconfig.debug
new file mode 100644
index 000000000000..3224ff6ecf6e
--- /dev/null
+++ b/arch/riscv/Kconfig.debug
@@ -0,0 +1,37 @@
+
+config CMDLINE_BOOL
+	bool "Built-in kernel command line"
+	help
+	  For most platforms, it is firmware or second stage bootloader
+	  that by default specifies the kernel command line options.
+	  However, it might be necessary or advantageous to either override
+	  the default kernel command line or add a few extra options to it.
+	  For such cases, this option allows hardcoding command line options
+	  directly into the kernel.
+
+	  For that, choose 'Y' here and fill in the extra boot parameters
+	  in CONFIG_CMDLINE.
+
+	  The built-in options will be concatenated to the default command
+	  line if CMDLINE_FORCE is set to 'N'. Otherwise, the default
+	  command line will be ignored and replaced by the built-in string.
+
+config CMDLINE
+	string "Built-in kernel command string"
+	depends on CMDLINE_BOOL
+	default ""
+	help
+	  Supply command-line options at build time by entering them here.
+
+config CMDLINE_FORCE
+	bool "Built-in command line overrides bootloader arguments"
+	depends on CMDLINE_BOOL
+	help
+	  Set this option to 'Y' to have the kernel ignore the bootloader
+	  or firmware command line.  Instead, the built-in command line
+	  will be used exclusively.
+
+	  If you don't know what to do here, say N.
+
+config EARLY_PRINTK
+	def_bool y
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a94667712337..ac8925766d0a 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -828,8 +828,6 @@ config HAVE_PNETID
 	tristate
 	default (SMC || CCWGROUP)
 
-source "arch/s390/Kconfig.debug"
-
 menu "Virtualization"
 
 config PFAULT
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index 2cfdfbf8d320..190527560b2c 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -1,11 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
 
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-source "lib/Kconfig.debug"
-
 config S390_PTDUMP
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
@@ -20,5 +17,3 @@ config S390_PTDUMP
 
 config EARLY_PRINTK
 	def_bool y
-
-endmenu
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index f291d2568cd4..c8460330eff7 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -885,5 +885,3 @@ source "kernel/power/Kconfig"
 source "drivers/cpuidle/Kconfig"
 
 endmenu
-
-source "arch/sh/Kconfig.debug"
diff --git a/arch/sh/Kconfig.debug b/arch/sh/Kconfig.debug
index d0767672640d..010b6c33bbba 100644
--- a/arch/sh/Kconfig.debug
+++ b/arch/sh/Kconfig.debug
@@ -1,11 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
 
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-source "lib/Kconfig.debug"
-
 config SH_STANDARD_BIOS
 	bool "Use LinuxSH standard BIOS"
 	depends on SUPERH32
@@ -88,5 +85,3 @@ config MCOUNT
 	def_bool y
 	depends on SUPERH32
 	depends on STACK_DEBUG || FUNCTION_TRACER
-
-endmenu
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 8a1e44d2e112..622695e8fa44 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -565,5 +565,3 @@ config SYSVIPC_COMPAT
 	default y
 
 source "drivers/sbus/char/Kconfig"
-
-source "arch/sparc/Kconfig.debug"
diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug
index 4aef29a11925..50a918d496c8 100644
--- a/arch/sparc/Kconfig.debug
+++ b/arch/sparc/Kconfig.debug
@@ -1,12 +1,9 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
 
 config TRACE_IRQFLAGS_SUPPORT
 	bool
 	default y
 
-source "lib/Kconfig.debug"
-
 config DEBUG_DCFLUSH
 	bool "D-cache flush debugging"
 	depends on SPARC64 && DEBUG_KERNEL
@@ -21,5 +18,3 @@ config FRAME_POINTER
 	bool
 	depends on MCOUNT
 	default y
-
-endmenu
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index a5cc2b19a960..3022d1bf9bf9 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -187,5 +187,3 @@ config SECCOMP
 endmenu
 
 source "arch/um/drivers/Kconfig"
-
-source "arch/um/Kconfig.debug"
diff --git a/arch/um/Kconfig.debug b/arch/um/Kconfig.debug
index 967d3109689f..2014597605ea 100644
--- a/arch/um/Kconfig.debug
+++ b/arch/um/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config GPROF
 	bool "Enable gprof support"
@@ -37,5 +34,3 @@ config EARLY_PRINTK
 
 	  This is useful for kernel debugging when your machine crashes very
 	  early before the console code is initialized.
-
-endmenu
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 7fa7e61eb19f..6bfaa4a910e1 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -222,5 +222,3 @@ endmenu
 endif
 
 endif
-
-source "arch/unicore32/Kconfig.debug"
diff --git a/arch/unicore32/Kconfig.debug b/arch/unicore32/Kconfig.debug
index de8dae3abc0a..ca0ff97657ef 100644
--- a/arch/unicore32/Kconfig.debug
+++ b/arch/unicore32/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config EARLY_PRINTK
 	def_bool DEBUG_OCD
@@ -30,5 +27,3 @@ config DEBUG_OCD
 	help
 	  Say Y here if you want the debug print routines to direct their
 	  output to the UniCore On-Chip-Debugger channel using CP #1.
-
-endmenu
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 6faefd1c9f13..41d28b430fef 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2931,6 +2931,4 @@ config HAVE_GENERIC_GUP
 
 source "drivers/firmware/Kconfig"
 
-source "arch/x86/Kconfig.debug"
-
 source "arch/x86/kvm/Kconfig"
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index c6dd1d980081..7d68f0c7cfb1 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -1,11 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
 
 config TRACE_IRQFLAGS_SUPPORT
 	def_bool y
 
-source "lib/Kconfig.debug"
-
 config EARLY_PRINTK_USB
 	bool
 
@@ -410,5 +407,3 @@ endchoice
 config FRAME_POINTER
 	depends on !UNWINDER_ORC && !UNWINDER_GUESS
 	bool
-
-endmenu
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index d8bac8be3a33..aae0e1800be7 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -567,5 +567,3 @@ menu "Power management options"
 source "kernel/power/Kconfig"
 
 endmenu
-
-source "arch/xtensa/Kconfig.debug"
diff --git a/arch/xtensa/Kconfig.debug b/arch/xtensa/Kconfig.debug
index f64c14adadb3..39de98e20018 100644
--- a/arch/xtensa/Kconfig.debug
+++ b/arch/xtensa/Kconfig.debug
@@ -1,7 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0
-menu "Kernel hacking"
-
-source "lib/Kconfig.debug"
 
 config DEBUG_TLB_SANITY
 	bool "Debug TLB sanity"
@@ -34,5 +31,3 @@ config S32C1I_SELFTEST
 	  It is easy to make wrong hardware configuration, this test should catch it early.
 
 	  Say 'N' on stable hardware.
-
-endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8838d1158d19..26d3ff7e3cf4 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1,3 +1,5 @@
+menu "Kernel hacking"
+
 menu "printk and dmesg options"
 
 config PRINTK_TIME
@@ -2034,3 +2036,7 @@ config IO_STRICT_DEVMEM
 	  if the driver using a given range cannot be disabled.
 
 	  If in doubt, say Y.
+
+source "arch/$(SRCARCH)/Kconfig.debug"
+
+endmenu # Kernel hacking
-- 
cgit v1.2.3


From 87a4c375995ed8eaa721b08825cf73d0b02b3145 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:32 +0200
Subject: kconfig: include kernel/Kconfig.preempt from init/Kconfig

Almost all architectures include it.  Add a ARCH_NO_PREEMPT symbol to
disable preempt support for alpha, hexagon, non-coldfire m68k and
user mode Linux.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/Kconfig            | 3 +++
 arch/alpha/Kconfig      | 1 +
 arch/arc/Kconfig        | 2 --
 arch/arm/Kconfig        | 2 --
 arch/arm64/Kconfig      | 1 -
 arch/c6x/Kconfig        | 2 --
 arch/h8300/Kconfig      | 6 ------
 arch/hexagon/Kconfig    | 1 +
 arch/ia64/Kconfig       | 2 --
 arch/m68k/Kconfig       | 5 +----
 arch/microblaze/Kconfig | 2 --
 arch/mips/Kconfig       | 2 --
 arch/nds32/Kconfig      | 1 -
 arch/nios2/Kconfig      | 2 --
 arch/openrisc/Kconfig   | 1 -
 arch/parisc/Kconfig     | 1 -
 arch/powerpc/Kconfig    | 1 -
 arch/riscv/Kconfig      | 2 --
 arch/s390/Kconfig       | 2 --
 arch/sh/Kconfig         | 2 --
 arch/sparc/Kconfig      | 2 --
 arch/um/Kconfig         | 1 +
 arch/unicore32/Kconfig  | 2 --
 arch/x86/Kconfig        | 2 --
 arch/xtensa/Kconfig     | 2 --
 init/Kconfig            | 1 +
 kernel/Kconfig.preempt  | 2 ++
 lib/Kconfig.debug       | 1 +
 28 files changed, 11 insertions(+), 43 deletions(-)

diff --git a/arch/Kconfig b/arch/Kconfig
index 09a561a70168..cddd0faae4cb 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -881,6 +881,9 @@ config COMPAT_32BIT_TIME
 config ARCH_NO_COHERENT_DMA_MMAP
 	bool
 
+config ARCH_NO_PREEMPT
+	bool
+
 config CPU_NO_EFFICIENT_FFS
 	def_bool n
 
diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index e4334f017f8e..5b4f88363453 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -4,6 +4,7 @@ config ALPHA
 	default y
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_NO_PREEMPT
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select HAVE_AOUT
 	select HAVE_IDE
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index 5aab069eba17..639ab1bed835 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -545,8 +545,6 @@ config ARC_BUILTIN_DTB_NAME
 	  Set the name of the DTB to embed in the vmlinux binary
 	  Leaving it blank selects the minimal "skeleton" dtb
 
-source "kernel/Kconfig.preempt"
-
 endmenu	 # "ARC Architecture Configuration"
 
 config FORCE_MAX_ZONEORDER
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 9aaa23c25374..1b1c21519039 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1481,8 +1481,6 @@ config ARCH_NR_GPIO
 
 	  If unsure, leave the default value.
 
-source kernel/Kconfig.preempt
-
 config HZ_FIXED
 	int
 	default 200 if ARCH_EBSA110
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 07d457ec417a..daf59d363dd3 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -752,7 +752,6 @@ config HOLES_IN_ZONE
 	def_bool y
 	depends on NUMA
 
-source kernel/Kconfig.preempt
 source kernel/Kconfig.hz
 
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig
index 904b3375331e..a641b0bf1611 100644
--- a/arch/c6x/Kconfig
+++ b/arch/c6x/Kconfig
@@ -110,8 +110,6 @@ config KERNEL_RAM_BASE_ADDRESS
 	default 0xe0000000 if SOC_TMS320C6472
 	default 0x80000000
 
-source "kernel/Kconfig.preempt"
-
 source "kernel/Kconfig.hz"
 
 endmenu
diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig
index c16e7cf732f7..5e89d40be8cd 100644
--- a/arch/h8300/Kconfig
+++ b/arch/h8300/Kconfig
@@ -49,9 +49,3 @@ config NR_CPUS
 	default 1
 
 source "arch/h8300/Kconfig.cpu"
-
-menu "Kernel Features"
-
-source "kernel/Kconfig.preempt"
-
-endmenu
diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig
index fcdb6d9fcecc..89a4b22f34d9 100644
--- a/arch/hexagon/Kconfig
+++ b/arch/hexagon/Kconfig
@@ -4,6 +4,7 @@ comment "Linux Kernel Configuration for Hexagon"
 
 config HEXAGON
 	def_bool y
+	select ARCH_NO_PREEMPT
 	select HAVE_OPROFILE
 	# Other pending projects/to-do items.
 	# select HAVE_REGS_AND_STACK_ACCESS_API
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 34a8d24cffea..86bd377bc7c0 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -364,8 +364,6 @@ config FORCE_CPEI_RETARGET
 	This option it useful to enable this feature on older BIOS's as well.
 	You can also enable this by using boot command line option force_cpei=1.
 
-source "kernel/Kconfig.preempt"
-
 config ARCH_SELECT_MEMORY_MODEL
 	def_bool y
 
diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig
index cf41ad45513f..3e47f8df6504 100644
--- a/arch/m68k/Kconfig
+++ b/arch/m68k/Kconfig
@@ -4,6 +4,7 @@ config M68K
 	default y
 	select ARCH_MIGHT_HAVE_PC_PARPORT if ISA
 	select ARCH_NO_COHERENT_DMA_MMAP if !MMU
+	select ARCH_NO_PREEMPT if !COLDFIRE
 	select HAVE_IDE
 	select HAVE_AOUT if MMU
 	select HAVE_DEBUG_BUGVERBOSE
@@ -129,10 +130,6 @@ endmenu
 
 menu "Kernel Features"
 
-if COLDFIRE
-source "kernel/Kconfig.preempt"
-endif
-
 endmenu
 
 if !MMU
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index f4492e9478fe..6163a39ddeb6 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -87,8 +87,6 @@ source "arch/microblaze/Kconfig.platform"
 
 menu "Processor type and features"
 
-source "kernel/Kconfig.preempt"
-
 source "kernel/Kconfig.hz"
 
 config MMU
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index ab02824c3976..06a633eb9777 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2818,8 +2818,6 @@ config HZ
 config SCHED_HRTICK
 	def_bool HIGH_RES_TIMERS
 
-source "kernel/Kconfig.preempt"
-
 config KEXEC
 	bool "Kexec system call"
 	select KEXEC_CORE
diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig
index c03d0e5a591b..541f16adfb06 100644
--- a/arch/nds32/Kconfig
+++ b/arch/nds32/Kconfig
@@ -88,6 +88,5 @@ config NDS32_BUILTIN_DTB
 endmenu
 
 menu "Kernel Features"
-source "kernel/Kconfig.preempt"
 source "kernel/Kconfig.hz"
 endmenu
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 22d19febcc92..cbe1844b0657 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -47,8 +47,6 @@ config TRACE_IRQFLAGS_SUPPORT
 
 menu "Kernel features"
 
-source "kernel/Kconfig.preempt"
-
 source "kernel/Kconfig.hz"
 
 config FORCE_MAX_ZONEORDER
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index c52cecd94d62..42e3a0f2afab 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -143,7 +143,6 @@ config SMP
 	  If you don't know what to do here, say N.
 
 source kernel/Kconfig.hz
-source kernel/Kconfig.preempt
 
 config OPENRISC_NO_SPR_SR_DSX
 	bool "use SPR_SR_DSX software emulation" if OR1K_1200
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index d1dd56ea297b..89496aa318da 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -323,7 +323,6 @@ config NODES_SHIFT
 	default "3"
 	depends on NEED_MULTIPLE_NODES
 
-source "kernel/Kconfig.preempt"
 source "kernel/Kconfig.hz"
 
 config COMPAT
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c55e61302d57..1c10ff0406f2 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -393,7 +393,6 @@ config HIGHMEM
 	depends on PPC32
 
 source kernel/Kconfig.hz
-source kernel/Kconfig.preempt
 
 config HUGETLB_PAGE_SIZE_VARIABLE
 	bool
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 73c0e16793fa..a344980287a5 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -212,8 +212,6 @@ endmenu
 
 menu "Kernel type"
 
-source "kernel/Kconfig.preempt"
-
 source "kernel/Kconfig.hz"
 
 endmenu
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index ac8925766d0a..8441bd8f7d70 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -511,8 +511,6 @@ config SCHED_TOPOLOGY
 	  making when dealing with machines that have multi-threading,
 	  multiple cores or multiple books.
 
-source kernel/Kconfig.preempt
-
 source kernel/Kconfig.hz
 
 config KEXEC
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index c8460330eff7..993f61a5961d 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -709,8 +709,6 @@ config HOTPLUG_CPU
 	  Say Y here to experiment with turning CPUs off and on.  CPUs
 	  can be controlled through /sys/devices/system/cpu.
 
-source "kernel/Kconfig.preempt"
-
 config GUSA
 	def_bool y
 	depends on !SMP && SUPERH32
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 622695e8fa44..2d58c26bff9a 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -349,8 +349,6 @@ config SCHED_MC
 	  making when dealing with multi-core CPU chips at a cost of slightly
 	  increased overhead in some places. If unsure say N here.
 
-source "kernel/Kconfig.preempt"
-
 config CMDLINE_BOOL
 	bool "Default bootloader kernel arguments"
 	depends on SPARC64
diff --git a/arch/um/Kconfig b/arch/um/Kconfig
index 3022d1bf9bf9..6b9938919f0b 100644
--- a/arch/um/Kconfig
+++ b/arch/um/Kconfig
@@ -6,6 +6,7 @@ config UML
 	bool
 	default y
 	select ARCH_HAS_KCOV
+	select ARCH_NO_PREEMPT
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_UID16
diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig
index 6bfaa4a910e1..60eae744d8fd 100644
--- a/arch/unicore32/Kconfig
+++ b/arch/unicore32/Kconfig
@@ -135,8 +135,6 @@ endmenu
 
 menu "Kernel Features"
 
-source "kernel/Kconfig.preempt"
-
 source "kernel/Kconfig.hz"
 
 config LEDS
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 41d28b430fef..98fd04cfa995 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1039,8 +1039,6 @@ config SCHED_MC_PRIO
 
 	  If unsure say Y here.
 
-source "kernel/Kconfig.preempt"
-
 config UP_LATE_INIT
        def_bool y
        depends on !SMP && X86_LOCAL_APIC
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index aae0e1800be7..801491e98890 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -173,8 +173,6 @@ config XTENSA_UNALIGNED_USER
 
 	  Say Y here to enable unaligned memory access in user space.
 
-source "kernel/Kconfig.preempt"
-
 config HAVE_SMP
 	bool "System Supports SMP (MX)"
 	depends on XTENSA_VARIANT_CUSTOM
diff --git a/init/Kconfig b/init/Kconfig
index 283f6bc796b1..29bbad9338d6 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -326,6 +326,7 @@ config AUDIT_TREE
 
 source "kernel/irq/Kconfig"
 source "kernel/time/Kconfig"
+source "kernel/Kconfig.preempt"
 
 menu "CPU/Task time and stats accounting"
 
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 3f9c97419f02..cd1655122ec0 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -18,6 +18,7 @@ config PREEMPT_NONE
 
 config PREEMPT_VOLUNTARY
 	bool "Voluntary Kernel Preemption (Desktop)"
+	depends on !ARCH_NO_PREEMPT
 	help
 	  This option reduces the latency of the kernel by adding more
 	  "explicit preemption points" to the kernel code. These new
@@ -35,6 +36,7 @@ config PREEMPT_VOLUNTARY
 
 config PREEMPT
 	bool "Preemptible Kernel (Low-Latency Desktop)"
+	depends on !ARCH_NO_PREEMPT
 	select PREEMPT_COUNT
 	select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK
 	help
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 26d3ff7e3cf4..373ce9fecd7e 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1195,6 +1195,7 @@ config DEBUG_ATOMIC_SLEEP
 	bool "Sleep inside atomic section checking"
 	select PREEMPT_COUNT
 	depends on DEBUG_KERNEL
+	depends on !ARCH_NO_PREEMPT
 	help
 	  If you say Y here, various routines which may sleep will become very
 	  noisy if they are called inside atomic sections: when a spinlock is
-- 
cgit v1.2.3


From 22471e1313f2b5ec698069206f3a310d6d35b1d4 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 31 Jul 2018 13:39:33 +0200
Subject: kconfig: use a menu in arch/Kconfig to reduce clutter

Put everything in arch/Kconfig into a General options menu
so that they don't clutter up the main/major/primary list of
menu options.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 arch/Kconfig | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/Kconfig b/arch/Kconfig
index cddd0faae4cb..6cf1b17a8df2 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -9,6 +9,8 @@
 #
 source "arch/$(SRCARCH)/Kconfig"
 
+menu "General architecture-dependent options"
+
 config CRASH_CORE
 	bool
 
@@ -981,3 +983,5 @@ config REFCOUNT_FULL
 	  security flaw exploits.
 
 source "kernel/gcov/Kconfig"
+
+endmenu
-- 
cgit v1.2.3


From 006477f40d2e79cd1ba655af94fbd9b2a585bfef Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:34 +0200
Subject: kconfig: move the "Executable file formats" menu to fs/Kconfig.binfmt

No need to have this in the top-level Kconfig.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 Kconfig           | 2 --
 fs/Kconfig.binfmt | 5 +++++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/Kconfig b/Kconfig
index a5997d6c2029..48a80beab685 100644
--- a/Kconfig
+++ b/Kconfig
@@ -13,9 +13,7 @@ source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
 
-menu "Executable file formats"
 source "fs/Kconfig.binfmt"
-endmenu
 
 source "mm/Kconfig"
 
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index 56df483de619..b795f8da81f3 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -1,3 +1,6 @@
+
+menu "Executable file formats"
+
 config BINFMT_ELF
 	bool "Kernel support for ELF binaries"
 	depends on MMU
@@ -187,3 +190,5 @@ config COREDUMP
 	  This option enables support for performing core dumps. You almost
 	  certainly want to say Y here. Not necessary on systems that never
 	  need debugging or only ever run flawless code.
+
+endmenu
-- 
cgit v1.2.3


From 59e0b520c75c8b4588395aea6170e551c4189fd8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 13:39:35 +0200
Subject: kconfig: add a Memory Management options" menu

This moves all the options under a proper menu.

Based on a patch from Randy Dunlap.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 mm/Kconfig | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/Kconfig b/mm/Kconfig
index ce95491abd6a..9ae1b6a8e30f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1,3 +1,6 @@
+
+menu "Memory Management options"
+
 config SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SELECT_MEMORY_MODEL
@@ -762,3 +765,5 @@ config GUP_BENCHMARK
 
 config ARCH_HAS_PTE_SPECIAL
 	bool
+
+endmenu
-- 
cgit v1.2.3


From c971e6a006175bd0f195c6346c4e8bc4089bec00 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 28 May 2018 18:27:19 -0400
Subject: kill d_instantiate_no_diralias()

The only user is fuse_create_new_entry(), and there it's used to
mitigate the same mkdir/open-by-handle race as in nfs_mkdir().
The same solution applies - unhash the mkdir argument, then
call d_splice_alias() and if that returns a reference to preexisting
alias, dput() and report success.  ->mkdir() argument left unhashed
negative with the preexisting alias moved in the right place is just
fine from the ->mkdir() callers point of view.

Cc: Miklos Szeredi <miklos@szeredi.hu>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 27 ---------------------------
 fs/fuse/dir.c          | 15 +++++++++++----
 include/linux/dcache.h |  1 -
 3 files changed, 11 insertions(+), 32 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 0e8e5de3c48a..a7d9e7a4c283 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1899,33 +1899,6 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode)
 }
 EXPORT_SYMBOL(d_instantiate_new);
 
-/**
- * d_instantiate_no_diralias - instantiate a non-aliased dentry
- * @entry: dentry to complete
- * @inode: inode to attach to this dentry
- *
- * Fill in inode information in the entry.  If a directory alias is found, then
- * return an error (and drop inode).  Together with d_materialise_unique() this
- * guarantees that a directory inode may never have more than one alias.
- */
-int d_instantiate_no_diralias(struct dentry *entry, struct inode *inode)
-{
-	BUG_ON(!hlist_unhashed(&entry->d_u.d_alias));
-
-	security_d_instantiate(entry, inode);
-	spin_lock(&inode->i_lock);
-	if (S_ISDIR(inode->i_mode) && !hlist_empty(&inode->i_dentry)) {
-		spin_unlock(&inode->i_lock);
-		iput(inode);
-		return -EBUSY;
-	}
-	__d_instantiate(entry, inode);
-	spin_unlock(&inode->i_lock);
-
-	return 0;
-}
-EXPORT_SYMBOL(d_instantiate_no_diralias);
-
 struct dentry *d_make_root(struct inode *root_inode)
 {
 	struct dentry *res = NULL;
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 56231b31f806..4bbae6ac75c3 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -539,6 +539,7 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
 {
 	struct fuse_entry_out outarg;
 	struct inode *inode;
+	struct dentry *d;
 	int err;
 	struct fuse_forget_link *forget;
 
@@ -570,11 +571,17 @@ static int create_new_entry(struct fuse_conn *fc, struct fuse_args *args,
 	}
 	kfree(forget);
 
-	err = d_instantiate_no_diralias(entry, inode);
-	if (err)
-		return err;
+	d_drop(entry);
+	d = d_splice_alias(inode, entry);
+	if (IS_ERR(d))
+		return PTR_ERR(d);
 
-	fuse_change_entry_timeout(entry, &outarg);
+	if (d) {
+		fuse_change_entry_timeout(d, &outarg);
+		dput(d);
+	} else {
+		fuse_change_entry_timeout(entry, &outarg);
+	}
 	fuse_invalidate_attr(dir);
 	return 0;
 
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 66c6e17e61e5..0b83629a3d8f 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -227,7 +227,6 @@ extern void d_instantiate(struct dentry *, struct inode *);
 extern void d_instantiate_new(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
 extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
-extern int d_instantiate_no_diralias(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
-- 
cgit v1.2.3


From 1a5d5e5d51e75a5bca67dadbcea8c841934b7b85 Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jcline@redhat.com>
Date: Thu, 2 Aug 2018 00:03:40 -0400
Subject: ext4: fix spectre gadget in ext4_mb_regular_allocator()

'ac->ac_g_ex.fe_len' is a user-controlled value which is used in the
derivation of 'ac->ac_2order'. 'ac->ac_2order', in turn, is used to
index arrays which makes it a potential spectre gadget. Fix this by
sanitizing the value assigned to 'ac->ac2_order'.  This covers the
following accesses found with the help of smatch:

* fs/ext4/mballoc.c:1896 ext4_mb_simple_scan_group() warn: potential
  spectre issue 'grp->bb_counters' [w] (local cap)

* fs/ext4/mballoc.c:445 mb_find_buddy() warn: potential spectre issue
  'EXT4_SB(e4b->bd_sb)->s_mb_offsets' [r] (local cap)

* fs/ext4/mballoc.c:446 mb_find_buddy() warn: potential spectre issue
  'EXT4_SB(e4b->bd_sb)->s_mb_maxs' [r] (local cap)

Suggested-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Jeremy Cline <jcline@redhat.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Cc: stable@vger.kernel.org
---
 fs/ext4/mballoc.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index f7ab34088162..8b24d3d42cb3 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -14,6 +14,7 @@
 #include <linux/log2.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/nospec.h>
 #include <linux/backing-dev.h>
 #include <trace/events/ext4.h>
 
@@ -2140,7 +2141,8 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 		 * This should tell if fe_len is exactly power of 2
 		 */
 		if ((ac->ac_g_ex.fe_len & (~(1 << (i - 1)))) == 0)
-			ac->ac_2order = i - 1;
+			ac->ac_2order = array_index_nospec(i - 1,
+							   sb->s_blocksize_bits + 2);
 	}
 
 	/* if stream allocation is enabled, use global goal */
-- 
cgit v1.2.3


From bc716523462f98ea6bfef3e1a5926daadbf32e9e Mon Sep 17 00:00:00 2001
From: Liu Song <liu.song11@zte.com.cn>
Date: Thu, 2 Aug 2018 00:11:16 -0400
Subject: ext4: improve code readability in ext4_iget()

Merge the duplicated complex conditions to improve code readability.

Signed-off-by: Liu Song <liu.song11@zte.com.cn>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
Reviewed-by: Jiang Biao <jiang.biao2@zte.com.cn>
---
 fs/ext4/inode.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 60432498acfb..8f6ad7667974 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -4982,17 +4982,14 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 		ret = -EFSCORRUPTED;
 		goto bad_inode;
 	} else if (!ext4_has_inline_data(inode)) {
-		if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
-			if ((S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-			    (S_ISLNK(inode->i_mode) &&
-			     !ext4_inode_is_fast_symlink(inode))))
-				/* Validate extent which is part of inode */
+		/* validate the block references in the inode */
+		if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		   (S_ISLNK(inode->i_mode) &&
+		    !ext4_inode_is_fast_symlink(inode))) {
+			if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
 				ret = ext4_ext_check_inode(inode);
-		} else if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-			   (S_ISLNK(inode->i_mode) &&
-			    !ext4_inode_is_fast_symlink(inode))) {
-			/* Validate block references which are part of inode */
-			ret = ext4_ind_check_inode(inode);
+			else
+				ret = ext4_ind_check_inode(inode);
 		}
 	}
 	if (ret)
-- 
cgit v1.2.3


From 11175556eec58b27a1398e80f8b1302314f2242c Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Thu, 2 Aug 2018 04:31:02 +0000
Subject: ALSA: usb-audio: Fix invalid use of sizeof in
 parse_uac_endpoint_attributes()

sizeof() when applied to a pointer typed expression gives the
size of the pointer, not that of the pointed data.

Fixes: 7edf3b5e6a45 ("ALSA: usb-audio: AudioStreaming Power Domain parsing")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/stream.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/stream.c b/sound/usb/stream.c
index 8fe3b0e00e45..67cf849aa16b 100644
--- a/sound/usb/stream.c
+++ b/sound/usb/stream.c
@@ -1037,7 +1037,7 @@ found_clock:
 		fp->rate_max = UAC3_BADD_SAMPLING_RATE;
 		fp->rates = SNDRV_PCM_RATE_CONTINUOUS;
 
-		pd = kzalloc(sizeof(pd), GFP_KERNEL);
+		pd = kzalloc(sizeof(*pd), GFP_KERNEL);
 		if (!pd) {
 			kfree(fp->rate_table);
 			kfree(fp);
-- 
cgit v1.2.3


From 789b7f43858f1c74a1c528e8b8f78c78624800d8 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Thu, 2 Aug 2018 07:40:19 +0200
Subject: ALSA: sb: Fix a typo

There was a typo of COPY_USER in the dead code (that is disabled
as default).

Fixes: 4b83eff81c81 ("ALSA: sb: Convert to the new PCM ops")
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/sb/emu8000_pcm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/isa/sb/emu8000_pcm.c b/sound/isa/sb/emu8000_pcm.c
index bc5af71d3bdb..f46f6ec3ea0c 100644
--- a/sound/isa/sb/emu8000_pcm.c
+++ b/sound/isa/sb/emu8000_pcm.c
@@ -470,7 +470,7 @@ static int emu8k_pcm_copy(struct snd_pcm_substream *subs,
 	/* convert to word unit */
 	pos = (pos << 1) + rec->loop_start[voice];
 	count <<= 1;
-	LOOP_WRITE(rec, pos, src, count, COPY_UESR);
+	LOOP_WRITE(rec, pos, src, count, COPY_USER);
 	return 0;
 }
 
-- 
cgit v1.2.3


From bfdbe1323253a3f829d59c2566bb3c9452b84651 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Thu, 26 Jul 2018 16:10:18 +0300
Subject: iwlwifi: pcie: add a bunch of PCI IDs for 22000 and 22560

Add some missing PCI IDs for 22000 and 22560 devices.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 0358b406be81..651975bc159b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -806,17 +806,32 @@ static const struct pci_device_id iwl_hw_card_ids[] = {
 	{IWL_PCI_DEVICE(0xA370, 0x42A4, iwl9462_2ac_cfg_soc)},
 
 /* 22000 Series */
-	{IWL_PCI_DEVICE(0x2720, 0x0A10, iwl22000_2ac_cfg_hr_cdb)},
-	{IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22000_2ac_cfg_jf)},
 	{IWL_PCI_DEVICE(0x2720, 0x0000, iwl22000_2ax_cfg_hr)},
-	{IWL_PCI_DEVICE(0x34F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x2720, 0x0040, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0078, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0070, iwl22000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x0030, iwl22000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x1080, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0x2720, 0x0090, iwl22000_2ac_cfg_hr_cdb)},
 	{IWL_PCI_DEVICE(0x2720, 0x0310, iwl22000_2ac_cfg_hr_cdb)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0040, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0078, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x34F0, 0x0310, iwl22000_2ac_cfg_jf)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0000, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0010, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40c0, 0x0090, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0310, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x40C0, 0x0A10, iwl22560_2ax_cfg_su_cdb)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0040, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0x43F0, 0x0078, iwl22000_2ax_cfg_hr)},
 	{IWL_PCI_DEVICE(0xA0F0, 0x0000, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0040, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0070, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0078, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x00B0, iwl22000_2ax_cfg_hr)},
+	{IWL_PCI_DEVICE(0xA0F0, 0x0A10, iwl22000_2ax_cfg_hr)},
 
 #endif /* CONFIG_IWLMVM */
 
-- 
cgit v1.2.3


From 0307c839613e17b052c53e2c80a6c76fd1cd0320 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Mon, 5 Feb 2018 12:01:36 +0200
Subject: iwlwifi: pcie: support rx structures for 22560 devices

The rfh for 22560 devices has changed so it supports now
the same arch of using used and free lists, but different
structures to support the last.
Use the new structures, hw dependent, to manage the lists.

bd, the free list, uses the iwl_rx_transfer_desc,
in which the vid is stored in the structs' rbid
field, and the page address in the addr field.

used_bd, the used list, uses the iwl_rx_completion_desc
struct, in which the vid is stored in the structs' rbid
field.

rb_stts, the hw "write" pointer of rx is stored in a
__le16 array, in which each entry represents the write
pointer per queue.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |  31 +++++-
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c       | 111 +++++++++++++++++----
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    |  12 ++-
 3 files changed, 128 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 11687dc4039d..90e8a47c8bda 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -72,6 +72,7 @@ struct iwl_host_cmd;
  * @page: driver's pointer to the rxb page
  * @invalid: rxb is in driver ownership - not owned by HW
  * @vid: index of this rxb in the global table
+ * @size: size used from the buffer
  */
 struct iwl_rx_mem_buffer {
 	dma_addr_t page_dma;
@@ -79,6 +80,7 @@ struct iwl_rx_mem_buffer {
 	u16 vid;
 	bool invalid;
 	struct list_head list;
+	u32 size;
 };
 
 /**
@@ -159,8 +161,10 @@ enum iwl_completion_desc_wifi_status {
 	IWL_CD_STTS_REPLAY_ERR,
 };
 
-#define IWL_RX_TD_TYPE		0xff000000
-#define IWL_RX_TD_SIZE		0x00ffffff
+#define IWL_RX_TD_TYPE_MSK	0xff000000
+#define IWL_RX_TD_SIZE_MSK	0x00ffffff
+#define IWL_RX_TD_SIZE_2K	BIT(11)
+#define IWL_RX_TD_TYPE		0
 
 /**
  * struct iwl_rx_transfer_desc - transfer descriptor
@@ -204,6 +208,7 @@ struct iwl_rx_completion_desc {
  * @id: queue index
  * @bd: driver's pointer to buffer of receive buffer descriptors (rbd).
  *	Address size is 32 bit in pre-9000 devices and 64 bit in 9000 devices.
+ *	In 22560 devices it is a pointer to a list of iwl_rx_transfer_desc's
  * @bd_dma: bus address of buffer of receive buffer descriptors (rbd)
  * @ubd: driver's pointer to buffer of used receive buffer descriptors (rbd)
  * @ubd_dma: physical address of buffer of used receive buffer descriptors (rbd)
@@ -230,7 +235,7 @@ struct iwl_rxq {
 	int id;
 	void *bd;
 	dma_addr_t bd_dma;
-	__le32 *used_bd;
+	void *used_bd;
 	dma_addr_t used_bd_dma;
 	__le16 *tr_tail;
 	dma_addr_t tr_tail_dma;
@@ -245,7 +250,7 @@ struct iwl_rxq {
 	struct list_head rx_free;
 	struct list_head rx_used;
 	bool need_update;
-	struct iwl_rb_status *rb_stts;
+	void *rb_stts;
 	dma_addr_t rb_stts_dma;
 	spinlock_t lock;
 	struct napi_struct napi;
@@ -289,6 +294,24 @@ static inline int iwl_queue_inc_wrap(struct iwl_trans *trans, int index)
 	return ++index & (trans->cfg->base_params->max_tfd_queue_size - 1);
 }
 
+/**
+ * iwl_get_closed_rb_stts - get closed rb stts from different structs
+ * @rxq - the rxq to get the rb stts from
+ */
+static inline __le16 iwl_get_closed_rb_stts(struct iwl_trans *trans,
+					    struct iwl_rxq *rxq)
+{
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		__le16 *rb_stts = rxq->rb_stts;
+
+		return READ_ONCE(*rb_stts);
+	} else {
+		struct iwl_rb_status *rb_stts = rxq->rb_stts;
+
+		return READ_ONCE(rb_stts->closed_rb_num);
+	}
+}
+
 /**
  * iwl_queue_dec_wrap - decrement queue index, wrap back to end
  * @index -- current index
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index f509e55f27b1..78e7e2d5d290 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -242,6 +242,25 @@ static void iwl_pcie_rxq_check_wrptr(struct iwl_trans *trans)
 	}
 }
 
+static void iwl_pcie_restock_bd(struct iwl_trans *trans,
+				struct iwl_rxq *rxq,
+				struct iwl_rx_mem_buffer *rxb)
+{
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		struct iwl_rx_transfer_desc *bd = rxq->bd;
+
+		bd[rxq->write].type_n_size =
+			cpu_to_le32((IWL_RX_TD_TYPE & IWL_RX_TD_TYPE_MSK) |
+			((IWL_RX_TD_SIZE_2K >> 8) & IWL_RX_TD_SIZE_MSK));
+		bd[rxq->write].addr = cpu_to_le64(rxb->page_dma);
+		bd[rxq->write].rbid = cpu_to_le16(rxb->vid);
+	} else {
+		__le64 *bd = rxq->bd;
+
+		bd[rxq->write] = cpu_to_le64(rxb->page_dma | rxb->vid);
+	}
+}
+
 /*
  * iwl_pcie_rxmq_restock - restock implementation for multi-queue rx
  */
@@ -263,8 +282,6 @@ static void iwl_pcie_rxmq_restock(struct iwl_trans *trans,
 
 	spin_lock(&rxq->lock);
 	while (rxq->free_count) {
-		__le64 *bd = (__le64 *)rxq->bd;
-
 		/* Get next free Rx buffer, remove from free list */
 		rxb = list_first_entry(&rxq->rx_free, struct iwl_rx_mem_buffer,
 				       list);
@@ -273,7 +290,7 @@ static void iwl_pcie_rxmq_restock(struct iwl_trans *trans,
 		/* 12 first bits are expected to be empty */
 		WARN_ON(rxb->page_dma & DMA_BIT_MASK(12));
 		/* Point to Rx buffer via next RBD in circular buffer */
-		bd[rxq->write] = cpu_to_le64(rxb->page_dma | rxb->vid);
+		iwl_pcie_restock_bd(trans, rxq, rxb);
 		rxq->write = (rxq->write + 1) & MQ_RX_TABLE_MASK;
 		rxq->free_count--;
 	}
@@ -617,28 +634,45 @@ void iwl_pcie_rx_allocator_work(struct work_struct *data)
 	iwl_pcie_rx_allocator(trans_pcie->trans);
 }
 
+static int iwl_pcie_free_bd_size(struct iwl_trans *trans, bool use_rx_td)
+{
+	struct iwl_rx_transfer_desc *rx_td;
+
+	if (use_rx_td)
+		return sizeof(*rx_td);
+	else
+		return trans->cfg->mq_rx_supported ? sizeof(__le64) :
+			sizeof(__le32);
+}
+
 static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans,
 				  struct iwl_rxq *rxq)
 {
 	struct device *dev = trans->dev;
-	int free_size = trans->cfg->mq_rx_supported ? sizeof(__le64) :
-						      sizeof(__le32);
+	struct iwl_rx_completion_desc *rx_cd;
+	bool use_rx_td = (trans->cfg->device_family >=
+			  IWL_DEVICE_FAMILY_22560);
+	int free_size = iwl_pcie_free_bd_size(trans, use_rx_td);
 
 	if (rxq->bd)
-		dma_free_coherent(dev, free_size * rxq->queue_size,
+		dma_free_coherent(trans->dev,
+				  free_size * rxq->queue_size,
 				  rxq->bd, rxq->bd_dma);
 	rxq->bd_dma = 0;
 	rxq->bd = NULL;
 
 	if (rxq->rb_stts)
 		dma_free_coherent(trans->dev,
+				  use_rx_td ? sizeof(__le16) :
 				  sizeof(struct iwl_rb_status),
 				  rxq->rb_stts, rxq->rb_stts_dma);
 	rxq->rb_stts_dma = 0;
 	rxq->rb_stts = NULL;
 
 	if (rxq->used_bd)
-		dma_free_coherent(dev, sizeof(__le32) * rxq->queue_size,
+		dma_free_coherent(trans->dev,
+				  (use_rx_td ? sizeof(*rx_cd) :
+				   sizeof(__le32)) * rxq->queue_size,
 				  rxq->used_bd, rxq->used_bd_dma);
 	rxq->used_bd_dma = 0;
 	rxq->used_bd = NULL;
@@ -664,9 +698,11 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct device *dev = trans->dev;
+	struct iwl_rx_completion_desc *rx_cd;
 	int i;
-	int free_size = trans->cfg->mq_rx_supported ? sizeof(__le64) :
-						      sizeof(__le32);
+	int free_size;
+	bool use_rx_td = (trans->cfg->device_family >=
+			  IWL_DEVICE_FAMILY_22560);
 
 	spin_lock_init(&rxq->lock);
 	if (trans->cfg->mq_rx_supported)
@@ -674,6 +710,8 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 	else
 		rxq->queue_size = RX_QUEUE_SIZE;
 
+	free_size = iwl_pcie_free_bd_size(trans, use_rx_td);
+
 	/*
 	 * Allocate the circular buffer of Read Buffer Descriptors
 	 * (RBDs)
@@ -686,7 +724,9 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 
 	if (trans->cfg->mq_rx_supported) {
 		rxq->used_bd = dma_zalloc_coherent(dev,
-						   sizeof(__le32) *
+						   (use_rx_td ?
+						   sizeof(*rx_cd) :
+						   sizeof(__le32)) *
 						   rxq->queue_size,
 						   &rxq->used_bd_dma,
 						   GFP_KERNEL);
@@ -695,13 +735,15 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 	}
 
 	/* Allocate the driver's pointer to receive buffer status */
-	rxq->rb_stts = dma_zalloc_coherent(dev, sizeof(*rxq->rb_stts),
+	rxq->rb_stts = dma_zalloc_coherent(dev, use_rx_td ?
+					   sizeof(__le16) :
+					   sizeof(struct iwl_rb_status),
 					   &rxq->rb_stts_dma,
 					   GFP_KERNEL);
 	if (!rxq->rb_stts)
 		goto err;
 
-	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
+	if (!use_rx_td)
 		return 0;
 
 	/* Allocate the driver's pointer to TR tail */
@@ -717,6 +759,11 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 					   GFP_KERNEL);
 	if (!rxq->cr_tail)
 		goto err;
+	/*
+	 * W/A 22560 device step Z0 must be non zero bug
+	 * TODO: remove this when stop supporting Z0
+	 */
+	*rxq->cr_tail = cpu_to_le16(500);
 
 	return 0;
 
@@ -1000,7 +1047,9 @@ static int _iwl_pcie_rx_init(struct iwl_trans *trans)
 		rxq->read = 0;
 		rxq->write = 0;
 		rxq->write_actual = 0;
-		memset(rxq->rb_stts, 0, sizeof(*rxq->rb_stts));
+		memset(rxq->rb_stts, 0,
+		       (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) ?
+		       sizeof(__le16) : sizeof(struct iwl_rb_status));
 
 		iwl_pcie_rx_init_rxb_lists(rxq);
 
@@ -1249,6 +1298,8 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		}
 
 		page_stolen |= rxcb._page_stolen;
+		if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			break;
 		offset += ALIGN(len, FH_RSCSR_FRAME_ALIGN);
 	}
 
@@ -1297,7 +1348,7 @@ restart:
 	spin_lock(&rxq->lock);
 	/* uCode's read index (stored in shared DRAM) indicates the last Rx
 	 * buffer that the driver may process (last buffer filled by ucode). */
-	r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF;
+	r = le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq)) & 0x0FFF;
 	i = rxq->read;
 
 	/* W/A 9000 device step A0 wrap-around bug */
@@ -1314,11 +1365,24 @@ restart:
 			emergency = true;
 
 		if (trans->cfg->mq_rx_supported) {
+			u16 vid;
 			/*
-			 * used_bd is a 32 bit but only 12 are used to retrieve
-			 * the vid
+			 * used_bd is a 32/16 bit but only 12 are used
+			 * to retrieve the vid
 			 */
-			u16 vid = le32_to_cpu(rxq->used_bd[i]) & 0x0FFF;
+			if (trans->cfg->device_family >=
+			    IWL_DEVICE_FAMILY_22560) {
+				struct iwl_rx_completion_desc *rx_cd =
+					&((struct iwl_rx_completion_desc *)
+					  rxq->used_bd)[i];
+
+				vid = le16_to_cpu(rx_cd->rbid) & 0x0FFF;
+			} else {
+				__le32 *used =
+					&((__le32 *)rxq->used_bd)[i];
+
+				vid = le32_to_cpu(*used) & 0x0FFF;
+			}
 
 			if (WARN(!vid ||
 				 vid > ARRAY_SIZE(trans_pcie->global_table),
@@ -1332,6 +1396,16 @@ restart:
 				iwl_force_nmi(trans);
 				goto out;
 			}
+			if (trans->cfg->device_family >=
+			    IWL_DEVICE_FAMILY_22560) {
+				struct iwl_rx_completion_desc *rx_cd =
+					&((struct iwl_rx_completion_desc *)
+					  rxq->used_bd)[i];
+
+				rxb->size = le32_to_cpu(rx_cd->size) &
+					IWL_RX_CD_SIZE;
+			}
+
 			rxb->invalid = true;
 		} else {
 			rxb = rxq->queue[i];
@@ -1378,6 +1452,9 @@ restart:
 out:
 	/* Backtrack one entry */
 	rxq->read = i;
+	/* update cr tail with the rxq read pointer */
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		*rxq->cr_tail = cpu_to_le16(r);
 	spin_unlock(&rxq->lock);
 
 	/*
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 9588b67110d1..64c781eab6a5 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2545,10 +2545,11 @@ static ssize_t iwl_dbgfs_rx_queue_read(struct file *file,
 		pos += scnprintf(buf + pos, bufsz - pos, "\tfree_count: %u\n",
 				 rxq->free_count);
 		if (rxq->rb_stts) {
+			u32 r =	__le16_to_cpu(iwl_get_closed_rb_stts(trans,
+								     rxq));
 			pos += scnprintf(buf + pos, bufsz - pos,
 					 "\tclosed_rb_num: %u\n",
-					 le16_to_cpu(rxq->rb_stts->closed_rb_num) &
-					 0x0FFF);
+					 r & 0x0FFF);
 		} else {
 			pos += scnprintf(buf + pos, bufsz - pos,
 					 "\tclosed_rb_num: Not Allocated\n");
@@ -2754,7 +2755,7 @@ static u32 iwl_trans_pcie_dump_rbs(struct iwl_trans *trans,
 
 	spin_lock(&rxq->lock);
 
-	r = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num)) & 0x0FFF;
+	r = le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq)) & 0x0FFF;
 
 	for (i = rxq->read, j = 0;
 	     i != r && j < allocated_rb_nums;
@@ -3039,8 +3040,9 @@ static struct iwl_trans_dump_data
 		/* Dump RBs is supported only for pre-9000 devices (1 queue) */
 		struct iwl_rxq *rxq = &trans_pcie->rxq[0];
 		/* RBs */
-		num_rbs = le16_to_cpu(READ_ONCE(rxq->rb_stts->closed_rb_num))
-				      & 0x0FFF;
+		num_rbs =
+			le16_to_cpu(iwl_get_closed_rb_stts(trans, rxq))
+			& 0x0FFF;
 		num_rbs = (num_rbs - rxq->read) & RX_QUEUE_MASK;
 		len += num_rbs * (sizeof(*data) +
 				  sizeof(struct iwl_fw_error_dump_rb) +
-- 
cgit v1.2.3


From 18ead597daa17a557249cf4b2f494361d836ed52 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Mon, 5 Feb 2018 12:54:36 +0200
Subject: iwlwifi: support new rx_mpdu_desc api

22560 devices use a new rx_mpdu_desc api.
Update the code to use the new api.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/rx.h   | 179 +++++++++++++++++------
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c |   8 +-
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c     |   9 +-
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c    |  95 +++++++++---
 4 files changed, 218 insertions(+), 73 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index 0daa09c94b0f..565343f7e61f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -377,78 +377,94 @@ enum iwl_rx_he_phy {
 };
 
 /**
- * struct iwl_rx_mpdu_desc - RX MPDU descriptor
+ * struct iwl_rx_mpdu_desc_v1 - RX MPDU descriptor
  */
-struct iwl_rx_mpdu_desc {
-	/* DW2 */
-	/**
-	 * @mpdu_len: MPDU length
-	 */
-	__le16 mpdu_len;
-	/**
-	 * @mac_flags1: &enum iwl_rx_mpdu_mac_flags1
-	 */
-	u8 mac_flags1;
-	/**
-	 * @mac_flags2: &enum iwl_rx_mpdu_mac_flags2
-	 */
-	u8 mac_flags2;
-	/* DW3 */
+struct iwl_rx_mpdu_desc_v1 {
+	/* DW7 - carries rss_hash only when rpa_en == 1 */
 	/**
-	 * @amsdu_info: &enum iwl_rx_mpdu_amsdu_info
+	 * @rss_hash: RSS hash value
 	 */
-	u8 amsdu_info;
+	__le32 rss_hash;
+	/* DW8 - carries filter_match only when rpa_en == 1 */
 	/**
-	 * @phy_info: &enum iwl_rx_mpdu_phy_info
+	 * @filter_match: filter match value
 	 */
-	__le16 phy_info;
+	__le32 filter_match;
+	/* DW9 */
 	/**
-	 * @mac_phy_idx: MAC/PHY index
+	 * @rate_n_flags: RX rate/flags encoding
 	 */
-	u8 mac_phy_idx;
-	/* DW4 - carries csum data only when rpa_en == 1 */
+	__le32 rate_n_flags;
+	/* DW10 */
 	/**
-	 * @raw_csum: raw checksum (alledgedly unreliable)
+	 * @energy_a: energy chain A
 	 */
-	__le16 raw_csum;
+	u8 energy_a;
 	/**
-	 * @l3l4_flags: &enum iwl_rx_l3l4_flags
+	 * @energy_b: energy chain B
 	 */
-	__le16 l3l4_flags;
-	/* DW5 */
+	u8 energy_b;
 	/**
-	 * @status: &enum iwl_rx_mpdu_status
+	 * @channel: channel number
 	 */
-	__le16 status;
+	u8 channel;
 	/**
-	 * @hash_filter: hash filter value
+	 * @mac_context: MAC context mask
 	 */
-	u8 hash_filter;
+	u8 mac_context;
+	/* DW11 */
 	/**
-	 * @sta_id_flags: &enum iwl_rx_mpdu_sta_id_flags
+	 * @gp2_on_air_rise: GP2 timer value on air rise (INA)
 	 */
-	u8 sta_id_flags;
-	/* DW6 */
+	__le32 gp2_on_air_rise;
+	/* DW12 & DW13 */
+	union {
+		/**
+		 * @tsf_on_air_rise:
+		 * TSF value on air rise (INA), only valid if
+		 * %IWL_RX_MPDU_PHY_TSF_OVERLOAD isn't set
+		 */
+		__le64 tsf_on_air_rise;
+		/**
+		 * @he_phy_data:
+		 * HE PHY data, see &enum iwl_rx_he_phy, valid
+		 * only if %IWL_RX_MPDU_PHY_TSF_OVERLOAD is set
+		 */
+		__le64 he_phy_data;
+	};
+} __packed;
+
+/**
+ * struct iwl_rx_mpdu_desc_v3 - RX MPDU descriptor
+ */
+struct iwl_rx_mpdu_desc_v3 {
+	/* DW7 - carries filter_match only when rpa_en == 1 */
 	/**
-	 * @reorder_data: &enum iwl_rx_mpdu_reorder_data
+	 * @filter_match: filter match value
 	 */
-	__le32 reorder_data;
-	/* DW7 - carries rss_hash only when rpa_en == 1 */
+	__le32 filter_match;
+	/* DW8 - carries rss_hash only when rpa_en == 1 */
 	/**
 	 * @rss_hash: RSS hash value
 	 */
 	__le32 rss_hash;
-	/* DW8 - carries filter_match only when rpa_en == 1 */
+	/* DW9 */
 	/**
-	 * @filter_match: filter match value
+	 * @partial_hash: 31:0 ip/tcp header hash
+	 *	w/o some fields (such as IP SRC addr)
 	 */
-	__le32 filter_match;
-	/* DW9 */
+	__le32 partial_hash;
+	/* DW10 */
+	/**
+	 * @raw_xsum: raw xsum value
+	 */
+	__le32 raw_xsum;
+	/* DW11 */
 	/**
 	 * @rate_n_flags: RX rate/flags encoding
 	 */
 	__le32 rate_n_flags;
-	/* DW10 */
+	/* DW12 */
 	/**
 	 * @energy_a: energy chain A
 	 */
@@ -465,12 +481,12 @@ struct iwl_rx_mpdu_desc {
 	 * @mac_context: MAC context mask
 	 */
 	u8 mac_context;
-	/* DW11 */
+	/* DW13 */
 	/**
 	 * @gp2_on_air_rise: GP2 timer value on air rise (INA)
 	 */
 	__le32 gp2_on_air_rise;
-	/* DW12 & DW13 */
+	/* DW14 & DW15 */
 	union {
 		/**
 		 * @tsf_on_air_rise:
@@ -485,7 +501,78 @@ struct iwl_rx_mpdu_desc {
 		 */
 		__le64 he_phy_data;
 	};
-} __packed;
+	/* DW16 & DW17 */
+	/**
+	 * @reserved: reserved
+	 */
+	__le32 reserved[2];
+} __packed; /* RX_MPDU_RES_START_API_S_VER_3 */
+
+/**
+ * struct iwl_rx_mpdu_desc - RX MPDU descriptor
+ */
+struct iwl_rx_mpdu_desc {
+	/* DW2 */
+	/**
+	 * @mpdu_len: MPDU length
+	 */
+	__le16 mpdu_len;
+	/**
+	 * @mac_flags1: &enum iwl_rx_mpdu_mac_flags1
+	 */
+	u8 mac_flags1;
+	/**
+	 * @mac_flags2: &enum iwl_rx_mpdu_mac_flags2
+	 */
+	u8 mac_flags2;
+	/* DW3 */
+	/**
+	 * @amsdu_info: &enum iwl_rx_mpdu_amsdu_info
+	 */
+	u8 amsdu_info;
+	/**
+	 * @phy_info: &enum iwl_rx_mpdu_phy_info
+	 */
+	__le16 phy_info;
+	/**
+	 * @mac_phy_idx: MAC/PHY index
+	 */
+	u8 mac_phy_idx;
+	/* DW4 - carries csum data only when rpa_en == 1 */
+	/**
+	 * @raw_csum: raw checksum (alledgedly unreliable)
+	 */
+	__le16 raw_csum;
+	/**
+	 * @l3l4_flags: &enum iwl_rx_l3l4_flags
+	 */
+	__le16 l3l4_flags;
+	/* DW5 */
+	/**
+	 * @status: &enum iwl_rx_mpdu_status
+	 */
+	__le16 status;
+	/**
+	 * @hash_filter: hash filter value
+	 */
+	u8 hash_filter;
+	/**
+	 * @sta_id_flags: &enum iwl_rx_mpdu_sta_id_flags
+	 */
+	u8 sta_id_flags;
+	/* DW6 */
+	/**
+	 * @reorder_data: &enum iwl_rx_mpdu_reorder_data
+	 */
+	__le32 reorder_data;
+
+	union {
+		struct iwl_rx_mpdu_desc_v1 v1;
+		struct iwl_rx_mpdu_desc_v3 v3;
+	};
+} __packed; /* RX_MPDU_RES_START_API_S_VER_3 */
+
+#define IWL_RX_DESC_SIZE_V1 offsetofend(struct iwl_rx_mpdu_desc, v1)
 
 struct iwl_frame_release {
 	u8 baid;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 1c4178f20441..05b77419953c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1150,6 +1150,10 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 	struct iwl_rx_mpdu_desc *desc;
 	int bin_len = count / 2;
 	int ret = -EINVAL;
+	size_t mpdu_cmd_hdr_size =
+		(mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) ?
+		sizeof(struct iwl_rx_mpdu_desc) :
+		IWL_RX_DESC_SIZE_V1;
 
 	if (!iwl_mvm_firmware_running(mvm))
 		return -EIO;
@@ -1168,7 +1172,7 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 		goto out;
 
 	/* avoid invalid memory access */
-	if (bin_len < sizeof(*pkt) + sizeof(*desc))
+	if (bin_len < sizeof(*pkt) + mpdu_cmd_hdr_size)
 		goto out;
 
 	/* check this is RX packet */
@@ -1179,7 +1183,7 @@ static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mvm *mvm,
 	/* check the length in metadata matches actual received length */
 	desc = (void *)pkt->data;
 	if (le16_to_cpu(desc->mpdu_len) !=
-	    (bin_len - sizeof(*desc) - sizeof(*pkt)))
+	    (bin_len - mpdu_cmd_hdr_size - sizeof(*pkt)))
 		goto out;
 
 	local_bh_disable();
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index d966262e0819..f5b117d8c354 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -621,7 +621,11 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	if (iwl_mvm_has_new_rx_api(mvm)) {
 		op_mode->ops = &iwl_mvm_ops_mq;
-		trans->rx_mpdu_cmd_hdr_size = sizeof(struct iwl_rx_mpdu_desc);
+		trans->rx_mpdu_cmd_hdr_size =
+			(trans->cfg->device_family >=
+			 IWL_DEVICE_FAMILY_22560) ?
+			sizeof(struct iwl_rx_mpdu_desc) :
+			IWL_RX_DESC_SIZE_V1;
 	} else {
 		op_mode->ops = &iwl_mvm_ops;
 		trans->rx_mpdu_cmd_hdr_size =
@@ -704,8 +708,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	}
 
 	/* the hardware splits the A-MSDU */
-	if (mvm->trans->cfg->device_family >=
-	    IWL_DEVICE_FAMILY_22560)
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
 		trans_cfg.rx_buf_size = IWL_AMSDU_2K;
 	else if (mvm->cfg->mq_rx_supported)
 		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index d82eeb7e0de7..b53148f972a4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -215,15 +215,14 @@ static void iwl_mvm_pass_packet_to_mac80211(struct iwl_mvm *mvm,
 }
 
 static void iwl_mvm_get_signal_strength(struct iwl_mvm *mvm,
-					struct iwl_rx_mpdu_desc *desc,
-					struct ieee80211_rx_status *rx_status)
+					struct ieee80211_rx_status *rx_status,
+					u32 rate_n_flags, int energy_a,
+					int energy_b)
 {
-	int energy_a, energy_b, max_energy;
-	u32 rate_flags = le32_to_cpu(desc->rate_n_flags);
+	int max_energy;
+	u32 rate_flags = rate_n_flags;
 
-	energy_a = desc->energy_a;
 	energy_a = energy_a ? -energy_a : S8_MIN;
-	energy_b = desc->energy_b;
 	energy_b = energy_b ? -energy_b : S8_MIN;
 	max_energy = max(energy_a, energy_b);
 
@@ -368,7 +367,8 @@ static bool iwl_mvm_is_dup(struct ieee80211_sta *sta, int queue,
 		tid = IWL_MAX_TID_COUNT;
 
 	/* If this wasn't a part of an A-MSDU the sub-frame index will be 0 */
-	sub_frame_idx = desc->amsdu_info & IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
+	sub_frame_idx = desc->amsdu_info &
+		IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
 
 	if (unlikely(ieee80211_has_retry(hdr->frame_control) &&
 		     dup_data->last_seq[tid] == hdr->seq_ctrl &&
@@ -862,23 +862,41 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 	struct ieee80211_rx_status *rx_status;
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
 	struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
-	struct ieee80211_hdr *hdr = (void *)(pkt->data + sizeof(*desc));
+	struct ieee80211_hdr *hdr;
 	u32 len = le16_to_cpu(desc->mpdu_len);
-	u32 rate_n_flags = le32_to_cpu(desc->rate_n_flags);
+	u32 rate_n_flags, gp2_on_air_rise;
 	u16 phy_info = le16_to_cpu(desc->phy_info);
 	struct ieee80211_sta *sta = NULL;
 	struct sk_buff *skb;
-	u8 crypt_len = 0;
+	u8 crypt_len = 0, channel, energy_a, energy_b;
 	struct ieee80211_radiotap_he *he = NULL;
 	struct ieee80211_radiotap_he_mu *he_mu = NULL;
 	u32 he_type = 0xffffffff;
 	/* this is invalid e.g. because puncture type doesn't allow 0b11 */
 #define HE_PHY_DATA_INVAL ((u64)-1)
 	u64 he_phy_data = HE_PHY_DATA_INVAL;
+	size_t desc_size;
 
 	if (unlikely(test_bit(IWL_MVM_STATUS_IN_HW_RESTART, &mvm->status)))
 		return;
 
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
+		rate_n_flags = le32_to_cpu(desc->v3.rate_n_flags);
+		channel = desc->v3.channel;
+		gp2_on_air_rise = le32_to_cpu(desc->v3.gp2_on_air_rise);
+		energy_a = desc->v3.energy_a;
+		energy_b = desc->v3.energy_b;
+		desc_size = sizeof(*desc);
+	} else {
+		rate_n_flags = le32_to_cpu(desc->v1.rate_n_flags);
+		channel = desc->v1.channel;
+		gp2_on_air_rise = le32_to_cpu(desc->v1.gp2_on_air_rise);
+		energy_a = desc->v1.energy_a;
+		energy_b = desc->v1.energy_b;
+		desc_size = IWL_RX_DESC_SIZE_V1;
+	}
+
+	hdr = (void *)(pkt->data + desc_size);
 	/* Dont use dev_alloc_skb(), we'll have enough headroom once
 	 * ieee80211_hdr pulled.
 	 */
@@ -925,8 +943,11 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
 
 		if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) {
-			he_phy_data =
-				le64_to_cpu(desc->he_phy_data);
+			if (mvm->trans->cfg->device_family >=
+			    IWL_DEVICE_FAMILY_22560)
+				he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+			else
+				he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
 
 			if (he_type == RATE_MCS_HE_TYPE_MU) {
 				he_mu = skb_put_data(skb, &mu_known,
@@ -940,6 +961,8 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		__skb_pull(skb, radiotap_len);
 	}
 
+	rx_status = IEEE80211_SKB_RXCB(skb);
+
 	if (iwl_mvm_rx_crypto(mvm, hdr, rx_status, phy_info, desc,
 			      le32_to_cpu(pkt->len_n_flags), queue,
 			      &crypt_len)) {
@@ -962,14 +985,28 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
 
 	if (likely(!(phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) {
-		rx_status->mactime = le64_to_cpu(desc->tsf_on_air_rise);
+		u64 tsf_on_air_rise;
+
+		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			tsf_on_air_rise = le64_to_cpu(desc->v3.tsf_on_air_rise);
+		else
+			tsf_on_air_rise = le64_to_cpu(desc->v1.tsf_on_air_rise);
+
+		rx_status->mactime = tsf_on_air_rise;
 		/* TSF as indicated by the firmware is at INA time */
 		rx_status->flag |= RX_FLAG_MACTIME_PLCP_START;
 	} else if (he_type == RATE_MCS_HE_TYPE_SU) {
+		u64 he_phy_data;
+
+		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+		else
+			he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
+
 		he->data1 |=
 			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN);
 		if (FIELD_GET(IWL_RX_HE_PHY_UPLINK,
-			      le64_to_cpu(desc->he_phy_data)))
+			      he_phy_data))
 			he->data3 |=
 				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
 
@@ -980,7 +1017,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
 			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
 			if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF,
-				      le64_to_cpu(desc->he_phy_data)))
+				      he_phy_data))
 				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
 		}
 	} else if (he_mu && he_phy_data != HE_PHY_DATA_INVAL) {
@@ -1005,16 +1042,23 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 						   he_phy_data),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW);
 	}
-	rx_status->device_timestamp = le32_to_cpu(desc->gp2_on_air_rise);
-	rx_status->band = desc->channel > 14 ? NL80211_BAND_5GHZ :
-					       NL80211_BAND_2GHZ;
-	rx_status->freq = ieee80211_channel_to_frequency(desc->channel,
+	rx_status->device_timestamp = gp2_on_air_rise;
+	rx_status->band = channel > 14 ? NL80211_BAND_5GHZ :
+		NL80211_BAND_2GHZ;
+	rx_status->freq = ieee80211_channel_to_frequency(channel,
 							 rx_status->band);
-	iwl_mvm_get_signal_strength(mvm, desc, rx_status);
+	iwl_mvm_get_signal_strength(mvm, rx_status, rate_n_flags, energy_a,
+				    energy_b);
 
 	/* update aggregation data for monitor sake on default queue */
 	if (!queue && (phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
 		bool toggle_bit = phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE;
+		u64 he_phy_data;
+
+		if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+			he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+		else
+			he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
 
 		rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
 		rx_status->ampdu_reference = mvm->ampdu_ref;
@@ -1027,7 +1071,7 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			    he_type == RATE_MCS_HE_TYPE_MU) {
 				rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
 				if (FIELD_GET(IWL_RX_HE_PHY_DELIM_EOF,
-					      le64_to_cpu(desc->he_phy_data)))
+					      he_phy_data))
 					rx_status->flag |=
 						RX_FLAG_AMPDU_EOF_BIT;
 			}
@@ -1327,12 +1371,19 @@ void iwl_mvm_rx_mpdu_mq(struct iwl_mvm *mvm, struct napi_struct *napi,
 			break;
 		case RATE_MCS_HE_TYPE_MU: {
 			u16 val;
+			u64 he_phy_data;
+
+			if (mvm->trans->cfg->device_family >=
+			    IWL_DEVICE_FAMILY_22560)
+				he_phy_data = le64_to_cpu(desc->v3.he_phy_data);
+			else
+				he_phy_data = le64_to_cpu(desc->v1.he_phy_data);
 
 			if (he_phy_data == HE_PHY_DATA_INVAL)
 				break;
 
 			val = FIELD_GET(IWL_RX_HE_PHY_HE_LTF_NUM_MASK,
-					le64_to_cpu(desc->he_phy_data));
+					he_phy_data);
 
 			he->data2 |=
 				cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
-- 
cgit v1.2.3


From b2a58c9712bb1b8744944c0cc54168be27e217f7 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Sun, 4 Mar 2018 13:09:01 +0200
Subject: iwlwifi: pcie: unionize used bd and completion descriptor

This allows less "dummy" declarations and casting.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h |  6 +++-
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c       | 32 ++++++----------------
 2 files changed, 13 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 90e8a47c8bda..f6726ccef819 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -235,7 +235,11 @@ struct iwl_rxq {
 	int id;
 	void *bd;
 	dma_addr_t bd_dma;
-	void *used_bd;
+	union {
+		void *used_bd;
+		__le32 *bd_32;
+		struct iwl_rx_completion_desc *cd;
+	};
 	dma_addr_t used_bd_dma;
 	__le16 *tr_tail;
 	dma_addr_t tr_tail_dma;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 78e7e2d5d290..284946653e27 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -649,7 +649,6 @@ static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans,
 				  struct iwl_rxq *rxq)
 {
 	struct device *dev = trans->dev;
-	struct iwl_rx_completion_desc *rx_cd;
 	bool use_rx_td = (trans->cfg->device_family >=
 			  IWL_DEVICE_FAMILY_22560);
 	int free_size = iwl_pcie_free_bd_size(trans, use_rx_td);
@@ -671,7 +670,7 @@ static void iwl_pcie_free_rxq_dma(struct iwl_trans *trans,
 
 	if (rxq->used_bd)
 		dma_free_coherent(trans->dev,
-				  (use_rx_td ? sizeof(*rx_cd) :
+				  (use_rx_td ? sizeof(*rxq->cd) :
 				   sizeof(__le32)) * rxq->queue_size,
 				  rxq->used_bd, rxq->used_bd_dma);
 	rxq->used_bd_dma = 0;
@@ -698,7 +697,6 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct device *dev = trans->dev;
-	struct iwl_rx_completion_desc *rx_cd;
 	int i;
 	int free_size;
 	bool use_rx_td = (trans->cfg->device_family >=
@@ -725,7 +723,7 @@ static int iwl_pcie_alloc_rxq_dma(struct iwl_trans *trans,
 	if (trans->cfg->mq_rx_supported) {
 		rxq->used_bd = dma_zalloc_coherent(dev,
 						   (use_rx_td ?
-						   sizeof(*rx_cd) :
+						   sizeof(*rxq->cd) :
 						   sizeof(__le32)) *
 						   rxq->queue_size,
 						   &rxq->used_bd_dma,
@@ -1371,18 +1369,10 @@ restart:
 			 * to retrieve the vid
 			 */
 			if (trans->cfg->device_family >=
-			    IWL_DEVICE_FAMILY_22560) {
-				struct iwl_rx_completion_desc *rx_cd =
-					&((struct iwl_rx_completion_desc *)
-					  rxq->used_bd)[i];
-
-				vid = le16_to_cpu(rx_cd->rbid) & 0x0FFF;
-			} else {
-				__le32 *used =
-					&((__le32 *)rxq->used_bd)[i];
-
-				vid = le32_to_cpu(*used) & 0x0FFF;
-			}
+			    IWL_DEVICE_FAMILY_22560)
+				vid = le16_to_cpu(rxq->cd[i].rbid) & 0x0FFF;
+			else
+				vid = le32_to_cpu(rxq->bd_32[i]) & 0x0FFF;
 
 			if (WARN(!vid ||
 				 vid > ARRAY_SIZE(trans_pcie->global_table),
@@ -1397,15 +1387,9 @@ restart:
 				goto out;
 			}
 			if (trans->cfg->device_family >=
-			    IWL_DEVICE_FAMILY_22560) {
-				struct iwl_rx_completion_desc *rx_cd =
-					&((struct iwl_rx_completion_desc *)
-					  rxq->used_bd)[i];
-
-				rxb->size = le32_to_cpu(rx_cd->size) &
+			    IWL_DEVICE_FAMILY_22560)
+				rxb->size = le32_to_cpu(rxq->cd[i].size) &
 					IWL_RX_CD_SIZE;
-			}
-
 			rxb->invalid = true;
 		} else {
 			rxb = rxq->queue[i];
-- 
cgit v1.2.3


From 1b4bbe8bf2eb631974c0688d7eeb350f86de25f8 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Sun, 4 Mar 2018 13:22:27 +0200
Subject: iwlwifi: pcie: move rxb retrieval to a helper function

This makes code less indented and more readable.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c | 75 ++++++++++++++++------------
 1 file changed, 42 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 284946653e27..59bedb461a8c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -1332,6 +1332,45 @@ static void iwl_pcie_rx_handle_rb(struct iwl_trans *trans,
 		iwl_pcie_rx_reuse_rbd(trans, rxb, rxq, emergency);
 }
 
+static struct iwl_rx_mem_buffer *iwl_pcie_get_rxb(struct iwl_trans *trans,
+						  struct iwl_rxq *rxq, int i)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+	struct iwl_rx_mem_buffer *rxb;
+	u16 vid;
+
+	if (!trans->cfg->mq_rx_supported) {
+		rxb = rxq->queue[i];
+		rxq->queue[i] = NULL;
+		return rxb;
+	}
+
+	/* used_bd is a 32/16 bit but only 12 are used to retrieve the vid */
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		vid = le16_to_cpu(rxq->cd[i].rbid) & 0x0FFF;
+	else
+		vid = le32_to_cpu(rxq->bd_32[i]) & 0x0FFF;
+
+	if (!vid || vid > ARRAY_SIZE(trans_pcie->global_table))
+		goto out_err;
+
+	rxb = trans_pcie->global_table[vid - 1];
+	if (rxb->invalid)
+		goto out_err;
+
+	if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+		rxb->size = le32_to_cpu(rxq->cd[i].size) & IWL_RX_CD_SIZE;
+
+	rxb->invalid = true;
+
+	return rxb;
+
+out_err:
+	WARN(1, "Invalid rxb from HW %u\n", (u32)vid);
+	iwl_force_nmi(trans);
+	return NULL;
+}
+
 /*
  * iwl_pcie_rx_handle - Main entry function for receiving responses from fw
  */
@@ -1362,39 +1401,9 @@ restart:
 		if (unlikely(rxq->used_count == rxq->queue_size / 2))
 			emergency = true;
 
-		if (trans->cfg->mq_rx_supported) {
-			u16 vid;
-			/*
-			 * used_bd is a 32/16 bit but only 12 are used
-			 * to retrieve the vid
-			 */
-			if (trans->cfg->device_family >=
-			    IWL_DEVICE_FAMILY_22560)
-				vid = le16_to_cpu(rxq->cd[i].rbid) & 0x0FFF;
-			else
-				vid = le32_to_cpu(rxq->bd_32[i]) & 0x0FFF;
-
-			if (WARN(!vid ||
-				 vid > ARRAY_SIZE(trans_pcie->global_table),
-				 "Invalid rxb index from HW %u\n", (u32)vid)) {
-				iwl_force_nmi(trans);
-				goto out;
-			}
-			rxb = trans_pcie->global_table[vid - 1];
-			if (WARN(rxb->invalid,
-				 "Invalid rxb from HW %u\n", (u32)vid)) {
-				iwl_force_nmi(trans);
-				goto out;
-			}
-			if (trans->cfg->device_family >=
-			    IWL_DEVICE_FAMILY_22560)
-				rxb->size = le32_to_cpu(rxq->cd[i].size) &
-					IWL_RX_CD_SIZE;
-			rxb->invalid = true;
-		} else {
-			rxb = rxq->queue[i];
-			rxq->queue[i] = NULL;
-		}
+		rxb = iwl_pcie_get_rxb(trans, rxq, i);
+		if (!rxb)
+			goto out;
 
 		IWL_DEBUG_RX(trans, "Q %d: HW = %d, SW = %d\n", rxq->id, r, i);
 		iwl_pcie_rx_handle_rb(trans, rxq, rxb, emergency);
-- 
cgit v1.2.3


From 92536c96159b62d73843af5702dd4e00d4bcffdf Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 5 Feb 2018 12:37:05 +0200
Subject: iwlwifi: trans: add a new op for getting DMA data

Op mode will need this data in order to feed FW with it.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h  | 26 +++++++++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 17 ++++++++++++++++
 2 files changed, 43 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 4229992073b6..9483f76476de 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -439,6 +439,20 @@ struct iwl_trans_txq_scd_cfg {
 	int frame_limit;
 };
 
+/**
+ * struct iwl_trans_rxq_dma_data - RX queue DMA data
+ * @fr_bd_cb: DMA address of free BD cyclic buffer
+ * @fr_bd_wid: Initial write index of the free BD cyclic buffer
+ * @urbd_stts_wrptr: DMA address of urbd_stts_wrptr
+ * @ur_bd_cb: DMA address of used BD cyclic buffer
+ */
+struct iwl_trans_rxq_dma_data {
+	u64 fr_bd_cb;
+	u32 fr_bd_wid;
+	u64 urbd_stts_wrptr;
+	u64 ur_bd_cb;
+};
+
 /**
  * struct iwl_trans_ops - transport specific operations
  *
@@ -559,6 +573,8 @@ struct iwl_trans_ops {
 			 int cmd_id, int size,
 			 unsigned int queue_wdg_timeout);
 	void (*txq_free)(struct iwl_trans *trans, int queue);
+	int (*rxq_dma_data)(struct iwl_trans *trans, int queue,
+			    struct iwl_trans_rxq_dma_data *data);
 
 	void (*txq_set_shared_mode)(struct iwl_trans *trans, u32 txq_id,
 				    bool shared);
@@ -947,6 +963,16 @@ iwl_trans_txq_enable_cfg(struct iwl_trans *trans, int queue, u16 ssn,
 				      cfg, queue_wdg_timeout);
 }
 
+static inline int
+iwl_trans_get_rxq_dma_data(struct iwl_trans *trans, int queue,
+			   struct iwl_trans_rxq_dma_data *data)
+{
+	if (WARN_ON_ONCE(!trans->ops->rxq_dma_data))
+		return -ENOTSUPP;
+
+	return trans->ops->rxq_dma_data(trans, queue, data);
+}
+
 static inline void
 iwl_trans_txq_free(struct iwl_trans *trans, int queue)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 64c781eab6a5..603458aa2923 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -2265,6 +2265,22 @@ void iwl_trans_pcie_log_scd_error(struct iwl_trans *trans, struct iwl_txq *txq)
 		iwl_read_direct32(trans, FH_TX_TRB_REG(fifo)));
 }
 
+static int iwl_trans_pcie_rxq_dma_data(struct iwl_trans *trans, int queue,
+				       struct iwl_trans_rxq_dma_data *data)
+{
+	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
+
+	if (queue >= trans->num_rx_queues || !trans_pcie->rxq)
+		return -EINVAL;
+
+	data->fr_bd_cb = trans_pcie->rxq[queue].bd_dma;
+	data->urbd_stts_wrptr = trans_pcie->rxq[queue].rb_stts_dma;
+	data->ur_bd_cb = trans_pcie->rxq[queue].used_bd_dma;
+	data->fr_bd_wid = 0;
+
+	return 0;
+}
+
 static int iwl_trans_pcie_wait_txq_empty(struct iwl_trans *trans, int txq_idx)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
@@ -3212,6 +3228,7 @@ static const struct iwl_trans_ops trans_ops_pcie_gen2 = {
 	.txq_alloc = iwl_trans_pcie_dyn_txq_alloc,
 	.txq_free = iwl_trans_pcie_dyn_txq_free,
 	.wait_txq_empty = iwl_trans_pcie_wait_txq_empty,
+	.rxq_dma_data = iwl_trans_pcie_rxq_dma_data,
 };
 
 struct iwl_trans *iwl_trans_pcie_alloc(struct pci_dev *pdev,
-- 
cgit v1.2.3


From 520f03eaaad7c4ede831f93995a0b0a916f369d8 Mon Sep 17 00:00:00 2001
From: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Date: Tue, 20 Feb 2018 17:20:32 +0200
Subject: iwlwifi: allow masking out memory areas from the fw dump

Reading and dumping memory areas takes time, and sometimes
dumping all of the areas isn't necessary.

Allow choosing the memory areas which should be dumped.

Signed-off-by: Shahar S Matityahu <shahar.s.matityahu@intel.com>
Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c     | 284 ++++++++++++++----------
 drivers/net/wireless/intel/iwlwifi/fw/file.h    |   3 +
 drivers/net/wireless/intel/iwlwifi/fw/img.h     |   1 +
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c    |  13 ++
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h  |   1 +
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c    |   1 +
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c |  98 ++++----
 7 files changed, 244 insertions(+), 157 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index fa283285fcbe..a31a42e673c4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -243,39 +243,47 @@ static void iwl_fw_dump_fifos(struct iwl_fw_runtime *fwrt,
 	if (!iwl_trans_grab_nic_access(fwrt->trans, &flags))
 		return;
 
-	/* Pull RXF1 */
-	iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->lmac[0].rxfifo1_size, 0, 0);
-	/* Pull RXF2 */
-	iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->rxfifo2_size,
-			  RXF_DIFF_FROM_PREV, 1);
-	/* Pull LMAC2 RXF1 */
-	if (fwrt->smem_cfg.num_lmacs > 1)
-		iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->lmac[1].rxfifo1_size,
-				  LMAC2_PRPH_OFFSET, 2);
-
-	/* Pull TXF data from LMAC1 */
-	for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries; i++) {
-		/* Mark the number of TXF we're pulling now */
-		iwl_trans_write_prph(fwrt->trans, TXF_LARC_NUM, i);
-		iwl_fwrt_dump_txf(fwrt, dump_data, cfg->lmac[0].txfifo_size[i],
-				  0, i);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RXF)) {
+		/* Pull RXF1 */
+		iwl_fwrt_dump_rxf(fwrt, dump_data,
+				  cfg->lmac[0].rxfifo1_size, 0, 0);
+		/* Pull RXF2 */
+		iwl_fwrt_dump_rxf(fwrt, dump_data, cfg->rxfifo2_size,
+				  RXF_DIFF_FROM_PREV, 1);
+		/* Pull LMAC2 RXF1 */
+		if (fwrt->smem_cfg.num_lmacs > 1)
+			iwl_fwrt_dump_rxf(fwrt, dump_data,
+					  cfg->lmac[1].rxfifo1_size,
+					  LMAC2_PRPH_OFFSET, 2);
 	}
 
-	/* Pull TXF data from LMAC2 */
-	if (fwrt->smem_cfg.num_lmacs > 1) {
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_TXF)) {
+		/* Pull TXF data from LMAC1 */
 		for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries; i++) {
 			/* Mark the number of TXF we're pulling now */
-			iwl_trans_write_prph(fwrt->trans,
-					     TXF_LARC_NUM + LMAC2_PRPH_OFFSET,
-					     i);
+			iwl_trans_write_prph(fwrt->trans, TXF_LARC_NUM, i);
 			iwl_fwrt_dump_txf(fwrt, dump_data,
-					  cfg->lmac[1].txfifo_size[i],
-					  LMAC2_PRPH_OFFSET,
-					  i + cfg->num_txfifo_entries);
+					  cfg->lmac[0].txfifo_size[i], 0, i);
+		}
+
+		/* Pull TXF data from LMAC2 */
+		if (fwrt->smem_cfg.num_lmacs > 1) {
+			for (i = 0; i < fwrt->smem_cfg.num_txfifo_entries;
+			     i++) {
+				/* Mark the number of TXF we're pulling now */
+				iwl_trans_write_prph(fwrt->trans,
+						     TXF_LARC_NUM +
+						     LMAC2_PRPH_OFFSET, i);
+				iwl_fwrt_dump_txf(fwrt, dump_data,
+						  cfg->lmac[1].txfifo_size[i],
+						  LMAC2_PRPH_OFFSET,
+						  i + cfg->num_txfifo_entries);
+			}
 		}
 	}
 
-	if (fw_has_capa(&fwrt->fw->ucode_capa,
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_INTERNAL_TXF) &&
+	    fw_has_capa(&fwrt->fw->ucode_capa,
 			IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
 		/* Pull UMAC internal TXF data from all TXFs */
 		for (i = 0;
@@ -600,42 +608,54 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status)) {
 		fifo_data_len = 0;
 
-		/* Count RXF2 size */
-		if (mem_cfg->rxfifo2_size) {
-			/* Add header info */
-			fifo_data_len += mem_cfg->rxfifo2_size +
-					 sizeof(*dump_data) +
-					 sizeof(struct iwl_fw_error_dump_fifo);
-		}
-
-		/* Count RXF1 sizes */
-		for (i = 0; i < mem_cfg->num_lmacs; i++) {
-			if (!mem_cfg->lmac[i].rxfifo1_size)
-				continue;
-
-			/* Add header info */
-			fifo_data_len += mem_cfg->lmac[i].rxfifo1_size +
-					 sizeof(*dump_data) +
-					 sizeof(struct iwl_fw_error_dump_fifo);
-		}
+		if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RXF)) {
 
-		/* Count TXF sizes */
-		for (i = 0; i < mem_cfg->num_lmacs; i++) {
-			int j;
+			/* Count RXF2 size */
+			if (mem_cfg->rxfifo2_size) {
+				/* Add header info */
+				fifo_data_len +=
+					mem_cfg->rxfifo2_size +
+					sizeof(*dump_data) +
+					sizeof(struct iwl_fw_error_dump_fifo);
+			}
 
-			for (j = 0; j < mem_cfg->num_txfifo_entries; j++) {
-				if (!mem_cfg->lmac[i].txfifo_size[j])
+			/* Count RXF1 sizes */
+			for (i = 0; i < mem_cfg->num_lmacs; i++) {
+				if (!mem_cfg->lmac[i].rxfifo1_size)
 					continue;
 
 				/* Add header info */
 				fifo_data_len +=
-					mem_cfg->lmac[i].txfifo_size[j] +
+					mem_cfg->lmac[i].rxfifo1_size +
 					sizeof(*dump_data) +
 					sizeof(struct iwl_fw_error_dump_fifo);
 			}
 		}
 
-		if (fw_has_capa(&fwrt->fw->ucode_capa,
+		if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_TXF)) {
+			size_t fifo_const_len = sizeof(*dump_data) +
+				sizeof(struct iwl_fw_error_dump_fifo);
+
+			/* Count TXF sizes */
+			for (i = 0; i < mem_cfg->num_lmacs; i++) {
+				int j;
+
+				for (j = 0; j < mem_cfg->num_txfifo_entries;
+				     j++) {
+					if (!mem_cfg->lmac[i].txfifo_size[j])
+						continue;
+
+					/* Add header info */
+					fifo_data_len +=
+						fifo_const_len +
+						mem_cfg->lmac[i].txfifo_size[j];
+				}
+			}
+		}
+
+		if ((fwrt->fw->dbg_dump_mask &
+		    BIT(IWL_FW_ERROR_DUMP_INTERNAL_TXF)) &&
+		    fw_has_capa(&fwrt->fw->ucode_capa,
 				IWL_UCODE_TLV_CAPA_EXTEND_SHARED_MEM_CFG)) {
 			for (i = 0;
 			     i < ARRAY_SIZE(mem_cfg->internal_txfifo_size);
@@ -652,7 +672,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		}
 
 		/* Make room for PRPH registers */
-		if (!fwrt->trans->cfg->gen2) {
+		if (!fwrt->trans->cfg->gen2 &&
+		    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PRPH)) {
 			for (i = 0; i < ARRAY_SIZE(iwl_prph_dump_addr_comm);
 			     i++) {
 				/* The range includes both boundaries */
@@ -667,7 +688,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		}
 
 		if (!fwrt->trans->cfg->gen2 &&
-		    fwrt->trans->cfg->mq_rx_supported) {
+		    fwrt->trans->cfg->mq_rx_supported &&
+		    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PRPH)) {
 			for (i = 0; i <
 				ARRAY_SIZE(iwl_prph_dump_addr_9000); i++) {
 				/* The range includes both boundaries */
@@ -681,34 +703,42 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			}
 		}
 
-		if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000)
+		if (fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000 &&
+		    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RADIO_REG))
 			radio_len = sizeof(*dump_data) + RADIO_REG_MAX_READ;
 	}
 
 	file_len = sizeof(*dump_file) +
-		   sizeof(*dump_data) * 3 +
-		   sizeof(*dump_smem_cfg) +
 		   fifo_data_len +
 		   prph_len +
-		   radio_len +
-		   sizeof(*dump_info);
-
-	/* Make room for the SMEM, if it exists */
-	if (smem_len)
-		file_len += sizeof(*dump_data) + sizeof(*dump_mem) + smem_len;
-
-	/* Make room for the secondary SRAM, if it exists */
-	if (sram2_len)
-		file_len += sizeof(*dump_data) + sizeof(*dump_mem) + sram2_len;
-
-	/* Make room for MEM segments */
-	for (i = 0; i < fwrt->fw->n_dbg_mem_tlv; i++) {
-		file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
-			    le32_to_cpu(fw_dbg_mem[i].len);
+		   radio_len;
+
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_DEV_FW_INFO))
+		file_len += sizeof(*dump_data) + sizeof(*dump_info);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM_CFG))
+		file_len += sizeof(*dump_data) + sizeof(*dump_smem_cfg);
+
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
+		/* Make room for the SMEM, if it exists */
+		if (smem_len)
+			file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
+				smem_len;
+
+		/* Make room for the secondary SRAM, if it exists */
+		if (sram2_len)
+			file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
+				sram2_len;
+
+		/* Make room for MEM segments */
+		for (i = 0; i < fwrt->fw->n_dbg_mem_tlv; i++) {
+			file_len += sizeof(*dump_data) + sizeof(*dump_mem) +
+				    le32_to_cpu(fw_dbg_mem[i].len);
+		}
 	}
 
 	/* Make room for fw's virtual image pages, if it exists */
-	if (!fwrt->trans->cfg->gen2 &&
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING) &&
+	    !fwrt->trans->cfg->gen2 &&
 	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 	    fwrt->fw_paging_db[0].fw_paging_block)
 		file_len += fwrt->num_of_paging_blk *
@@ -722,12 +752,14 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			   sizeof(*dump_info) + sizeof(*dump_smem_cfg);
 	}
 
-	if (fwrt->dump.desc)
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_ERROR_INFO) &&
+	    fwrt->dump.desc)
 		file_len += sizeof(*dump_data) + sizeof(*dump_trig) +
 			    fwrt->dump.desc->len;
 
-	if (!fwrt->fw->n_dbg_mem_tlv)
-		file_len += sram_len + sizeof(*dump_mem);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM) &&
+	    !fwrt->fw->n_dbg_mem_tlv)
+		file_len += sizeof(*dump_data) + sram_len + sizeof(*dump_mem);
 
 	dump_file = vzalloc(file_len);
 	if (!dump_file) {
@@ -740,48 +772,56 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	dump_file->barker = cpu_to_le32(IWL_FW_ERROR_DUMP_BARKER);
 	dump_data = (void *)dump_file->data;
 
-	dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_DEV_FW_INFO);
-	dump_data->len = cpu_to_le32(sizeof(*dump_info));
-	dump_info = (void *)dump_data->data;
-	dump_info->device_family =
-		fwrt->trans->cfg->device_family == IWL_DEVICE_FAMILY_7000 ?
-			cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_7) :
-			cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_8);
-	dump_info->hw_step = cpu_to_le32(CSR_HW_REV_STEP(fwrt->trans->hw_rev));
-	memcpy(dump_info->fw_human_readable, fwrt->fw->human_readable,
-	       sizeof(dump_info->fw_human_readable));
-	strncpy(dump_info->dev_human_readable, fwrt->trans->cfg->name,
-		sizeof(dump_info->dev_human_readable));
-	strncpy(dump_info->bus_human_readable, fwrt->dev->bus->name,
-		sizeof(dump_info->bus_human_readable));
-
-	dump_data = iwl_fw_error_next_data(dump_data);
-
-	/* Dump shared memory configuration */
-	dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM_CFG);
-	dump_data->len = cpu_to_le32(sizeof(*dump_smem_cfg));
-	dump_smem_cfg = (void *)dump_data->data;
-	dump_smem_cfg->num_lmacs = cpu_to_le32(mem_cfg->num_lmacs);
-	dump_smem_cfg->num_txfifo_entries =
-		cpu_to_le32(mem_cfg->num_txfifo_entries);
-	for (i = 0; i < MAX_NUM_LMAC; i++) {
-		int j;
-
-		for (j = 0; j < TX_FIFO_MAX_NUM; j++)
-			dump_smem_cfg->lmac[i].txfifo_size[j] =
-				cpu_to_le32(mem_cfg->lmac[i].txfifo_size[j]);
-		dump_smem_cfg->lmac[i].rxfifo1_size =
-			cpu_to_le32(mem_cfg->lmac[i].rxfifo1_size);
-	}
-	dump_smem_cfg->rxfifo2_size = cpu_to_le32(mem_cfg->rxfifo2_size);
-	dump_smem_cfg->internal_txfifo_addr =
-		cpu_to_le32(mem_cfg->internal_txfifo_addr);
-	for (i = 0; i < TX_FIFO_INTERNAL_MAX_NUM; i++) {
-		dump_smem_cfg->internal_txfifo_size[i] =
-			cpu_to_le32(mem_cfg->internal_txfifo_size[i]);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_DEV_FW_INFO)) {
+		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_DEV_FW_INFO);
+		dump_data->len = cpu_to_le32(sizeof(*dump_info));
+		dump_info = (void *)dump_data->data;
+		dump_info->device_family =
+			fwrt->trans->cfg->device_family ==
+			IWL_DEVICE_FAMILY_7000 ?
+				cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_7) :
+				cpu_to_le32(IWL_FW_ERROR_DUMP_FAMILY_8);
+		dump_info->hw_step =
+			cpu_to_le32(CSR_HW_REV_STEP(fwrt->trans->hw_rev));
+		memcpy(dump_info->fw_human_readable, fwrt->fw->human_readable,
+		       sizeof(dump_info->fw_human_readable));
+		strncpy(dump_info->dev_human_readable, fwrt->trans->cfg->name,
+			sizeof(dump_info->dev_human_readable) - 1);
+		strncpy(dump_info->bus_human_readable, fwrt->dev->bus->name,
+			sizeof(dump_info->bus_human_readable) - 1);
+
+		dump_data = iwl_fw_error_next_data(dump_data);
 	}
 
-	dump_data = iwl_fw_error_next_data(dump_data);
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM_CFG)) {
+		/* Dump shared memory configuration */
+		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM_CFG);
+		dump_data->len = cpu_to_le32(sizeof(*dump_smem_cfg));
+		dump_smem_cfg = (void *)dump_data->data;
+		dump_smem_cfg->num_lmacs = cpu_to_le32(mem_cfg->num_lmacs);
+		dump_smem_cfg->num_txfifo_entries =
+			cpu_to_le32(mem_cfg->num_txfifo_entries);
+		for (i = 0; i < MAX_NUM_LMAC; i++) {
+			int j;
+			u32 *txf_size = mem_cfg->lmac[i].txfifo_size;
+
+			for (j = 0; j < TX_FIFO_MAX_NUM; j++)
+				dump_smem_cfg->lmac[i].txfifo_size[j] =
+					cpu_to_le32(txf_size[j]);
+			dump_smem_cfg->lmac[i].rxfifo1_size =
+				cpu_to_le32(mem_cfg->lmac[i].rxfifo1_size);
+		}
+		dump_smem_cfg->rxfifo2_size =
+			cpu_to_le32(mem_cfg->rxfifo2_size);
+		dump_smem_cfg->internal_txfifo_addr =
+			cpu_to_le32(mem_cfg->internal_txfifo_addr);
+		for (i = 0; i < TX_FIFO_INTERNAL_MAX_NUM; i++) {
+			dump_smem_cfg->internal_txfifo_size[i] =
+				cpu_to_le32(mem_cfg->internal_txfifo_size[i]);
+		}
+
+		dump_data = iwl_fw_error_next_data(dump_data);
+	}
 
 	/* We only dump the FIFOs if the FW is in error state */
 	if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status)) {
@@ -790,7 +830,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			iwl_read_radio_regs(fwrt, &dump_data);
 	}
 
-	if (fwrt->dump.desc) {
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_ERROR_INFO) &&
+	    fwrt->dump.desc) {
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_ERROR_INFO);
 		dump_data->len = cpu_to_le32(sizeof(*dump_trig) +
 					     fwrt->dump.desc->len);
@@ -805,7 +846,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	if (monitor_dump_only)
 		goto dump_trans_data;
 
-	if (!fwrt->fw->n_dbg_mem_tlv) {
+	if (!fwrt->fw->n_dbg_mem_tlv &&
+	    fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(sram_len + sizeof(*dump_mem));
 		dump_mem = (void *)dump_data->data;
@@ -821,6 +863,9 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		u32 ofs = le32_to_cpu(fw_dbg_mem[i].ofs);
 		bool success;
 
+		if (!(fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)))
+			break;
+
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(len + sizeof(*dump_mem));
 		dump_mem = (void *)dump_data->data;
@@ -854,7 +899,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 			dump_data = iwl_fw_error_next_data(dump_data);
 	}
 
-	if (smem_len) {
+	if (smem_len && fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
 		IWL_DEBUG_INFO(fwrt, "WRT SMEM dump\n");
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(smem_len + sizeof(*dump_mem));
@@ -867,7 +912,7 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 		dump_data = iwl_fw_error_next_data(dump_data);
 	}
 
-	if (sram2_len) {
+	if (sram2_len && fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_MEM)) {
 		IWL_DEBUG_INFO(fwrt, "WRT SRAM dump\n");
 		dump_data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_MEM);
 		dump_data->len = cpu_to_le32(sram2_len + sizeof(*dump_mem));
@@ -881,7 +926,8 @@ void iwl_fw_error_dump(struct iwl_fw_runtime *fwrt)
 	}
 
 	/* Dump fw's virtual image */
-	if (!fwrt->trans->cfg->gen2 &&
+	if (fwrt->fw->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING) &&
+	    !fwrt->trans->cfg->gen2 &&
 	    fwrt->fw->img[fwrt->cur_fw_img].paging_mem_size &&
 	    fwrt->fw_paging_db[0].fw_paging_block) {
 		IWL_DEBUG_INFO(fwrt, "WRT paging dump\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index 9d939cbaf6c6..c967dfbeacaf 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -146,6 +146,9 @@ enum iwl_ucode_tlv_type {
 	IWL_UCODE_TLV_FW_GSCAN_CAPA	= 50,
 	IWL_UCODE_TLV_FW_MEM_SEG	= 51,
 	IWL_UCODE_TLV_IML		= 52,
+
+	/* TLVs 0x1000-0x2000 are for internal driver usage */
+	IWL_UCODE_TLV_FW_DBG_DUMP_LST	= 0x1000,
 };
 
 struct iwl_ucode_tlv {
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.h b/drivers/net/wireless/intel/iwlwifi/fw/img.h
index f4912382b6af..6c5de68b5244 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/img.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/img.h
@@ -299,6 +299,7 @@ struct iwl_fw {
 	size_t dbg_trigger_tlv_len[FW_DBG_TRIGGER_MAX];
 	u8 dbg_dest_reg_num;
 	struct iwl_gscan_capabilities gscan_capa;
+	u32 dbg_dump_mask;
 };
 
 static inline const char *get_fw_dbg_mode_string(int mode)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 38fcc6a9d421..370281e338b2 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1043,6 +1043,17 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 			pieces->dbg_trigger_tlv_len[trigger_id] = tlv_len;
 			break;
 			}
+		case IWL_UCODE_TLV_FW_DBG_DUMP_LST: {
+			if (tlv_len != sizeof(u32)) {
+				IWL_ERR(drv,
+					"dbg lst mask size incorrect, skip\n");
+				break;
+			}
+
+			drv->fw.dbg_dump_mask =
+				le32_to_cpup((__le32 *)tlv_data);
+			break;
+			}
 		case IWL_UCODE_TLV_SEC_RT_USNIFFER:
 			*usniffer_images = true;
 			iwl_store_ucode_sec(pieces, tlv_data,
@@ -1316,6 +1327,8 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 	fw->ucode_capa.standard_phy_calibration_size =
 			IWL_DEFAULT_STANDARD_PHY_CALIBRATE_TBL_SIZE;
 	fw->ucode_capa.n_scan_channels = IWL_DEFAULT_SCAN_CHANNELS;
+	/* dump all fw memory areas by default */
+	fw->dbg_dump_mask = 0xffffffff;
 
 	pieces = kzalloc(sizeof(*pieces), GFP_KERNEL);
 	if (!pieces)
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 9483f76476de..279dd7b7a3fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -771,6 +771,7 @@ struct iwl_trans {
 	const struct iwl_fw_dbg_dest_tlv_v1 *dbg_dest_tlv;
 	const struct iwl_fw_dbg_conf_tlv *dbg_conf_tlv[FW_DBG_CONF_MAX];
 	struct iwl_fw_dbg_trigger_tlv * const *dbg_trigger_tlv;
+	u32 dbg_dump_mask;
 	u8 dbg_dest_reg_num;
 
 	enum iwl_plat_pm_mode system_pm_mode;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index f5b117d8c354..99c086048aea 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -746,6 +746,7 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	memcpy(trans->dbg_conf_tlv, mvm->fw->dbg_conf_tlv,
 	       sizeof(trans->dbg_conf_tlv));
 	trans->dbg_trigger_tlv = mvm->fw->dbg_trigger_tlv;
+	trans->dbg_dump_mask = mvm->fw->dbg_dump_mask;
 
 	trans->iml = mvm->fw->iml;
 	trans->iml_len = mvm->fw->iml_len;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 603458aa2923..7928e8089f42 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -84,6 +84,7 @@
 #include "iwl-scd.h"
 #include "iwl-agn-hw.h"
 #include "fw/error-dump.h"
+#include "fw/dbg.h"
 #include "internal.h"
 #include "iwl-fh.h"
 
@@ -2978,7 +2979,8 @@ static struct iwl_trans_dump_data
 	u32 monitor_len;
 	int i, ptr;
 	bool dump_rbs = test_bit(STATUS_FW_ERROR, &trans->status) &&
-			!trans->cfg->mq_rx_supported;
+			!trans->cfg->mq_rx_supported &&
+			trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_RB);
 
 	/* transport dump header */
 	len = sizeof(*dump_data);
@@ -3030,6 +3032,10 @@ static struct iwl_trans_dump_data
 	}
 
 	if (trigger && (trigger->mode & IWL_FW_DBG_TRIGGER_MONITOR_ONLY)) {
+		if (!(trans->dbg_dump_mask &
+		      BIT(IWL_FW_ERROR_DUMP_FW_MONITOR)))
+			return NULL;
+
 		dump_data = vzalloc(len);
 		if (!dump_data)
 			return NULL;
@@ -3042,15 +3048,20 @@ static struct iwl_trans_dump_data
 	}
 
 	/* CSR registers */
-	len += sizeof(*data) + IWL_CSR_TO_DUMP;
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
+		len += sizeof(*data) + IWL_CSR_TO_DUMP;
 
 	/* FH registers */
-	if (trans->cfg->gen2)
-		len += sizeof(*data) +
-		       (FH_MEM_UPPER_BOUND_GEN2 - FH_MEM_LOWER_BOUND_GEN2);
-	else
-		len += sizeof(*data) +
-		       (FH_MEM_UPPER_BOUND - FH_MEM_LOWER_BOUND);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS)) {
+		if (trans->cfg->gen2)
+			len += sizeof(*data) +
+			       (FH_MEM_UPPER_BOUND_GEN2 -
+				FH_MEM_LOWER_BOUND_GEN2);
+		else
+			len += sizeof(*data) +
+			       (FH_MEM_UPPER_BOUND -
+				FH_MEM_LOWER_BOUND);
+	}
 
 	if (dump_rbs) {
 		/* Dump RBs is supported only for pre-9000 devices (1 queue) */
@@ -3066,7 +3077,8 @@ static struct iwl_trans_dump_data
 	}
 
 	/* Paged memory for gen2 HW */
-	if (trans->cfg->gen2)
+	if (trans->cfg->gen2 &&
+	    trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING))
 		for (i = 0; i < trans_pcie->init_dram.paging_cnt; i++)
 			len += sizeof(*data) +
 			       sizeof(struct iwl_fw_error_dump_paging) +
@@ -3078,41 +3090,51 @@ static struct iwl_trans_dump_data
 
 	len = 0;
 	data = (void *)dump_data->data;
-	data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD);
-	txcmd = (void *)data->data;
-	spin_lock_bh(&cmdq->lock);
-	ptr = cmdq->write_ptr;
-	for (i = 0; i < cmdq->n_window; i++) {
-		u8 idx = iwl_pcie_get_cmd_index(cmdq, ptr);
-		u32 caplen, cmdlen;
-
-		cmdlen = iwl_trans_pcie_get_cmdlen(trans, cmdq->tfds +
-						   trans_pcie->tfd_size * ptr);
-		caplen = min_t(u32, TFD_MAX_PAYLOAD_SIZE, cmdlen);
-
-		if (cmdlen) {
-			len += sizeof(*txcmd) + caplen;
-			txcmd->cmdlen = cpu_to_le32(cmdlen);
-			txcmd->caplen = cpu_to_le32(caplen);
-			memcpy(txcmd->data, cmdq->entries[idx].cmd, caplen);
-			txcmd = (void *)((u8 *)txcmd->data + caplen);
+
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD)) {
+		u16 tfd_size = trans_pcie->tfd_size;
+
+		data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD);
+		txcmd = (void *)data->data;
+		spin_lock_bh(&cmdq->lock);
+		ptr = cmdq->write_ptr;
+		for (i = 0; i < cmdq->n_window; i++) {
+			u8 idx = iwl_pcie_get_cmd_index(cmdq, ptr);
+			u32 caplen, cmdlen;
+
+			cmdlen = iwl_trans_pcie_get_cmdlen(trans,
+							   cmdq->tfds +
+							   tfd_size * ptr);
+			caplen = min_t(u32, TFD_MAX_PAYLOAD_SIZE, cmdlen);
+
+			if (cmdlen) {
+				len += sizeof(*txcmd) + caplen;
+				txcmd->cmdlen = cpu_to_le32(cmdlen);
+				txcmd->caplen = cpu_to_le32(caplen);
+				memcpy(txcmd->data, cmdq->entries[idx].cmd,
+				       caplen);
+				txcmd = (void *)((u8 *)txcmd->data + caplen);
+			}
+
+			ptr = iwl_queue_dec_wrap(trans, ptr);
 		}
+		spin_unlock_bh(&cmdq->lock);
 
-		ptr = iwl_queue_dec_wrap(trans, ptr);
+		data->len = cpu_to_le32(len);
+		len += sizeof(*data);
+		data = iwl_fw_error_next_data(data);
 	}
-	spin_unlock_bh(&cmdq->lock);
-
-	data->len = cpu_to_le32(len);
-	len += sizeof(*data);
-	data = iwl_fw_error_next_data(data);
 
-	len += iwl_trans_pcie_dump_csr(trans, &data);
-	len += iwl_trans_pcie_fh_regs_dump(trans, &data);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_CSR))
+		len += iwl_trans_pcie_dump_csr(trans, &data);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FH_REGS))
+		len += iwl_trans_pcie_fh_regs_dump(trans, &data);
 	if (dump_rbs)
 		len += iwl_trans_pcie_dump_rbs(trans, &data, num_rbs);
 
 	/* Paged memory for gen2 HW */
-	if (trans->cfg->gen2) {
+	if (trans->cfg->gen2 &&
+	    trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_PAGING)) {
 		for (i = 0; i < trans_pcie->init_dram.paging_cnt; i++) {
 			struct iwl_fw_error_dump_paging *paging;
 			dma_addr_t addr =
@@ -3132,8 +3154,8 @@ static struct iwl_trans_dump_data
 			len += sizeof(*data) + sizeof(*paging) + page_len;
 		}
 	}
-
-	len += iwl_trans_pcie_dump_monitor(trans, &data, monitor_len);
+	if (trans->dbg_dump_mask & BIT(IWL_FW_ERROR_DUMP_FW_MONITOR))
+		len += iwl_trans_pcie_dump_monitor(trans, &data, monitor_len);
 
 	dump_data->len = len;
 
-- 
cgit v1.2.3


From e8a583f9afa882cf9b2c6122ba16921c0d6a9cba Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Wed, 7 Mar 2018 18:46:01 +0200
Subject: iwlwifi: d3: disable dbg recording before entering D3

Currently the firmware does not stop recording debugging data when
entering D3 and this causes trouble (e.g. sporadic wake ups).

Fix that by stopping dbg recording when suspending.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 3fcf489f3120..79bdae994822 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -1037,6 +1037,13 @@ static int __iwl_mvm_suspend(struct ieee80211_hw *hw,
 			cpu_to_le32(IWL_WAKEUP_D3_CONFIG_FW_ERROR);
 #endif
 
+	/*
+	 * TODO: this is needed because the firmware is not stopping
+	 * the recording automatically before entering D3.  This can
+	 * be removed once the FW starts doing that.
+	 */
+	iwl_fw_dbg_stop_recording(&mvm->fwrt);
+
 	/* must be last -- this switches firmware state */
 	ret = iwl_mvm_send_cmd(mvm, &d3_cfg_cmd);
 	if (ret)
-- 
cgit v1.2.3


From 8edbfaa19835cf0bd2a9b3e5e328ba20a927d10b Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Mon, 5 Feb 2018 12:42:44 +0200
Subject: iwlwifi: mvm: configure multi RX queue

Currently multi-queue is disabled for 22000 devices.

This was since driver isn't supposed to write to prph
registers anymore, and FW needs to configure the RFH.

Now that FW added support for the API - use it and remove
the 22000 multi RX queue disablement.

Bump min API version to avoid compatibility issues.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c     |  2 +-
 .../net/wireless/intel/iwlwifi/fw/api/datapath.h   |  7 ++++
 drivers/net/wireless/intel/iwlwifi/fw/api/rx.h     | 32 +++++++++++++++
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c        | 48 ++++++++++++++++++++--
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c  |  7 ----
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       |  1 +
 6 files changed, 86 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index e5d5578f8b92..91ca77c7571c 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -59,7 +59,7 @@
 #define IWL_22000_UCODE_API_MAX	38
 
 /* Lowest firmware API version supported */
-#define IWL_22000_UCODE_API_MIN	24
+#define IWL_22000_UCODE_API_MIN	39
 
 /* NVM versions */
 #define IWL_22000_NVM_VERSION		0x0a1d
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
index c1bf3898f8b6..59b3c6e8f37b 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -87,6 +89,11 @@ enum iwl_data_path_subcmd_ids {
 	 */
 	STA_HE_CTXT_CMD = 0x7,
 
+	/**
+	 * @RFH_QUEUE_CONFIG_CMD: &struct iwl_rfh_queue_config
+	 */
+	RFH_QUEUE_CONFIG_CMD = 0xD,
+
 	/**
 	 * @TLC_MNG_CONFIG_CMD: &struct iwl_tlc_config_cmd
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
index 565343f7e61f..2f599353c885 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rx.h
@@ -715,4 +715,36 @@ struct iwl_ba_window_status_notif {
 	__le16 mpdu_rx_count[BA_WINDOW_STREAMS_MAX];
 } __packed; /* BA_WINDOW_STATUS_NTFY_API_S_VER_1 */
 
+/**
+ * struct iwl_rfh_queue_config - RX queue configuration
+ * @q_num: Q num
+ * @enable: enable queue
+ * @reserved: alignment
+ * @urbd_stts_wrptr: DMA address of urbd_stts_wrptr
+ * @fr_bd_cb: DMA address of freeRB table
+ * @ur_bd_cb: DMA address of used RB table
+ * @fr_bd_wid: Initial index of the free table
+ */
+struct iwl_rfh_queue_data {
+	u8 q_num;
+	u8 enable;
+	__le16 reserved;
+	__le64 urbd_stts_wrptr;
+	__le64 fr_bd_cb;
+	__le64 ur_bd_cb;
+	__le32 fr_bd_wid;
+} __packed; /* RFH_QUEUE_CONFIG_S_VER_1 */
+
+/**
+ * struct iwl_rfh_queue_config - RX queue configuration
+ * @num_queues: number of queues configured
+ * @reserved: alignment
+ * @data: DMA addresses per-queue
+ */
+struct iwl_rfh_queue_config {
+	u8 num_queues;
+	u8 reserved[3];
+	struct iwl_rfh_queue_data data[];
+} __packed; /* RFH_QUEUE_CONFIG_API_S_VER_1 */
+
 #endif /* __iwl_fw_api_rx_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 5fe2b460234b..6bb1a99a197a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -130,6 +130,41 @@ static int iwl_send_rss_cfg_cmd(struct iwl_mvm *mvm)
 	return iwl_mvm_send_cmd_pdu(mvm, RSS_CONFIG_CMD, 0, sizeof(cmd), &cmd);
 }
 
+static int iwl_configure_rxq(struct iwl_mvm *mvm)
+{
+	int i, num_queues, size;
+	struct iwl_rfh_queue_config *cmd;
+
+	/* Do not configure default queue, it is configured via context info */
+	num_queues = mvm->trans->num_rx_queues - 1;
+
+	size = sizeof(*cmd) + num_queues * sizeof(struct iwl_rfh_queue_data);
+
+	cmd = kzalloc(size, GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	cmd->num_queues = num_queues;
+
+	for (i = 0; i < num_queues; i++) {
+		struct iwl_trans_rxq_dma_data data;
+
+		cmd->data[i].q_num = i + 1;
+		iwl_trans_get_rxq_dma_data(mvm->trans, i + 1, &data);
+
+		cmd->data[i].fr_bd_cb = cpu_to_le64(data.fr_bd_cb);
+		cmd->data[i].urbd_stts_wrptr =
+			cpu_to_le64(data.urbd_stts_wrptr);
+		cmd->data[i].ur_bd_cb = cpu_to_le64(data.ur_bd_cb);
+		cmd->data[i].fr_bd_wid = cpu_to_le32(data.fr_bd_wid);
+	}
+
+	return iwl_mvm_send_cmd_pdu(mvm,
+				    WIDE_ID(DATA_PATH_GROUP,
+					    RFH_QUEUE_CONFIG_CMD),
+				    0, size, cmd);
+}
+
 static int iwl_mvm_send_dqa_cmd(struct iwl_mvm *mvm)
 {
 	struct iwl_dqa_enable_cmd dqa_cmd = {
@@ -1007,9 +1042,16 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 		goto error;
 
 	/* Init RSS configuration */
-	/* TODO - remove 22000 disablement when we have RXQ config API */
-	if (iwl_mvm_has_new_rx_api(mvm) &&
-	    mvm->trans->cfg->device_family < IWL_DEVICE_FAMILY_22000) {
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
+		ret = iwl_configure_rxq(mvm);
+		if (ret) {
+			IWL_ERR(mvm, "Failed to configure RX queues: %d\n",
+				ret);
+			goto error;
+		}
+	}
+
+	if (iwl_mvm_has_new_rx_api(mvm)) {
 		ret = iwl_send_rss_cfg_cmd(mvm);
 		if (ret) {
 			IWL_ERR(mvm, "Failed to configure RSS queues: %d\n",
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index a3b634ae3838..b15b0d84bb7e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4558,13 +4558,6 @@ void iwl_mvm_sync_rx_queues_internal(struct iwl_mvm *mvm,
 		atomic_set(&mvm->queue_sync_counter,
 			   mvm->trans->num_rx_queues);
 
-	/* TODO - remove this when we have RXQ config API */
-	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22000) {
-		qmask = BIT(0);
-		if (notif->sync)
-			atomic_set(&mvm->queue_sync_counter, 1);
-	}
-
 	ret = iwl_mvm_notify_rx_queue(mvm, qmask, (u8 *)notif, size);
 	if (ret) {
 		IWL_ERR(mvm, "Failed to trigger RX queues sync (%d)\n", ret);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 99c086048aea..06298356df6d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -449,6 +449,7 @@ static const struct iwl_hcmd_names iwl_mvm_data_path_names[] = {
 	HCMD_NAME(UPDATE_MU_GROUPS_CMD),
 	HCMD_NAME(TRIGGER_RX_QUEUES_NOTIF_CMD),
 	HCMD_NAME(STA_HE_CTXT_CMD),
+	HCMD_NAME(RFH_QUEUE_CONFIG_CMD),
 	HCMD_NAME(STA_PM_NOTIF),
 	HCMD_NAME(MU_GROUP_MGMT_NOTIF),
 	HCMD_NAME(RX_QUEUES_NOTIFICATION),
-- 
cgit v1.2.3


From f98ad635c097c29339b7a7d6947173000485893d Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 13 Mar 2018 14:12:40 +0200
Subject: iwlwifi: pcie: don't access periphery registers when not available

The periphery can't be accessed before we set the
INIT_DONE bit which initializes the device.

A previous patch added a reconfiguration of the MSI-X
tables upon resume, but at that point in the flow,
INIT_DONE wasn't set. Since the reconfiguration of the
MSI-X tables require periphery access, it failed.

The difference between WoWLAN and without WoWLAN is that
in WoWLAN, iwl_trans_pcie_d3_suspend clears the INIT_DONE
without clearing the STATUS_DEVICE_ENABLED bit in the
software status. Because of that, the resume code thinks
that the device is enabled, but the INIT_DONE bit has been
cleared.

To fix this, don't reconfigure the MSI-X tables in case
WoWLAN is enabled. It will be done in
iwl_trans_pcie_d3_resume anyway.

Fixes: 52848a79b9d2 ("iwlwifi: pcie: reconfigure MSI-X HW on resume")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c   |  4 ++++
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c | 24 ++++++++++++------------
 2 files changed, 16 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 651975bc159b..51a2e2deea9c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -994,6 +994,10 @@ static int iwl_pci_resume(struct device *device)
 	if (!trans->op_mode)
 		return 0;
 
+	/* In WOWLAN, let iwl_trans_pcie_d3_resume do the rest of the work */
+	if (test_bit(STATUS_DEVICE_ENABLED, &trans->status))
+		return 0;
+
 	/* reconfigure the MSI-X mapping to get the correct IRQ for rfkill */
 	iwl_pcie_conf_msix_hw(trans_pcie);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index 7928e8089f42..a54c2bc985ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1563,18 +1563,6 @@ static int iwl_trans_pcie_d3_resume(struct iwl_trans *trans,
 
 	iwl_pcie_enable_rx_wake(trans, true);
 
-	/*
-	 * Reconfigure IVAR table in case of MSIX or reset ict table in
-	 * MSI mode since HW reset erased it.
-	 * Also enables interrupts - none will happen as
-	 * the device doesn't know we're waking it up, only when
-	 * the opmode actually tells it after this call.
-	 */
-	iwl_pcie_conf_msix_hw(trans_pcie);
-	if (!trans_pcie->msix_enabled)
-		iwl_pcie_reset_ict(trans);
-	iwl_enable_interrupts(trans);
-
 	iwl_set_bit(trans, CSR_GP_CNTRL,
 		    BIT(trans->cfg->csr->flag_mac_access_req));
 	iwl_set_bit(trans, CSR_GP_CNTRL,
@@ -1592,6 +1580,18 @@ static int iwl_trans_pcie_d3_resume(struct iwl_trans *trans,
 		return ret;
 	}
 
+	/*
+	 * Reconfigure IVAR table in case of MSIX or reset ict table in
+	 * MSI mode since HW reset erased it.
+	 * Also enables interrupts - none will happen as
+	 * the device doesn't know we're waking it up, only when
+	 * the opmode actually tells it after this call.
+	 */
+	iwl_pcie_conf_msix_hw(trans_pcie);
+	if (!trans_pcie->msix_enabled)
+		iwl_pcie_reset_ict(trans);
+	iwl_enable_interrupts(trans);
+
 	iwl_pcie_set_pwr(trans, false);
 
 	if (!reset) {
-- 
cgit v1.2.3


From 07fb3299adc40b2e87bbe7047b7b1614deae0d05 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Tue, 13 Mar 2018 13:49:25 +0200
Subject: Revert "iwlwifi: implement fseq version mismatch warning"

This reverts commit f2e66c8df0d0f10c70ed7f5e14a939714e9ee6a9.

The firmware never implemented this, and they do not plan to.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/alive.h  | 18 +----
 .../net/wireless/intel/iwlwifi/fw/api/commands.h   |  7 --
 drivers/net/wireless/intel/iwlwifi/fw/common_rx.c  | 88 ----------------------
 drivers/net/wireless/intel/iwlwifi/fw/runtime.h    |  3 -
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c       |  4 +-
 5 files changed, 3 insertions(+), 117 deletions(-)
 delete mode 100644 drivers/net/wireless/intel/iwlwifi/fw/common_rx.c

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
index 007bfe7656a4..08d3d8a190f6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
@@ -8,6 +8,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
@@ -30,6 +31,7 @@
  * Copyright(c) 2012 - 2014 Intel Corporation. All rights reserved.
  * Copyright(c) 2013 - 2015 Intel Mobile Communications GmbH
  * Copyright(c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (C) 2018 Intel Corporation
  * All rights reserved.
  *
  * Redistribution and use in source and binary forms, with or without
@@ -187,20 +189,4 @@ struct iwl_card_state_notif {
 	__le32 flags;
 } __packed; /* CARD_STATE_NTFY_API_S_VER_1 */
 
-/**
- * struct iwl_fseq_ver_mismatch_nty - Notification about version
- *
- * This notification does not have a direct impact on the init flow.
- * It means that another core (not WiFi) has initiated the FSEQ flow
- * and updated the FSEQ version.  The driver only prints an error when
- * this occurs.
- *
- * @aux_read_fseq_ver: auxiliary read FSEQ version
- * @wifi_fseq_ver: FSEQ version (embedded in WiFi)
- */
-struct iwl_fseq_ver_mismatch_ntf {
-	__le32 aux_read_fseq_ver;
-	__le32 wifi_fseq_ver;
-} __packed; /* FSEQ_VER_MISMATCH_NTFY_API_S_VER_1 */
-
 #endif /* __iwl_fw_api_alive_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index d71a6a837ec5..6dad748e5cdc 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -647,13 +647,6 @@ enum iwl_system_subcmd_ids {
 	 * @INIT_EXTENDED_CFG_CMD: &struct iwl_init_extended_cfg_cmd
 	 */
 	INIT_EXTENDED_CFG_CMD = 0x03,
-
-	/**
-	 * @FSEQ_VER_MISMATCH_NTF: Notification about fseq version
-	 *	mismatch during init.  The format is specified in
-	 *	&struct iwl_fseq_ver_mismatch_ntf.
-	 */
-	FSEQ_VER_MISMATCH_NTF = 0xFF,
 };
 
 #endif /* __iwl_fw_api_commands_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/common_rx.c b/drivers/net/wireless/intel/iwlwifi/fw/common_rx.c
deleted file mode 100644
index 6f75985eea66..000000000000
--- a/drivers/net/wireless/intel/iwlwifi/fw/common_rx.c
+++ /dev/null
@@ -1,88 +0,0 @@
-/******************************************************************************
- *
- * This file is provided under a dual BSD/GPLv2 license.  When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2017 Intel Deutschland GmbH
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
- * The full GNU General Public License is included in this distribution
- * in the file called COPYING.
- *
- * Contact Information:
- *  Intel Linux Wireless <linuxwifi@intel.com>
- * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497
- *
- * BSD LICENSE
- *
- * Copyright(c) 2017 Intel Deutschland GmbH
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- *  * Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- *  * Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in
- *    the documentation and/or other materials provided with the
- *    distribution.
- *  * Neither the name Intel Corporation nor the names of its
- *    contributors may be used to endorse or promote products derived
- *    from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- *****************************************************************************/
-#include "iwl-drv.h"
-#include "runtime.h"
-#include "fw/api/commands.h"
-#include "fw/api/alive.h"
-
-static void iwl_fwrt_fseq_ver_mismatch(struct iwl_fw_runtime *fwrt,
-				       struct iwl_rx_cmd_buffer *rxb)
-{
-	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_fseq_ver_mismatch_ntf *fseq = (void *)pkt->data;
-
-	IWL_ERR(fwrt, "FSEQ version mismatch (aux: %d, wifi: %d)\n",
-		__le32_to_cpu(fseq->aux_read_fseq_ver),
-		__le32_to_cpu(fseq->wifi_fseq_ver));
-}
-
-void iwl_fwrt_handle_notification(struct iwl_fw_runtime *fwrt,
-				  struct iwl_rx_cmd_buffer *rxb)
-{
-	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	u32 cmd = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
-
-	switch (cmd) {
-	case WIDE_ID(SYSTEM_GROUP, FSEQ_VER_MISMATCH_NTF):
-		iwl_fwrt_fseq_ver_mismatch(fwrt, rxb);
-		break;
-	default:
-		break;
-	}
-}
-IWL_EXPORT_SYMBOL(iwl_fwrt_handle_notification);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index d8db1dd100b0..ed23367f7088 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -168,7 +168,4 @@ void iwl_free_fw_paging(struct iwl_fw_runtime *fwrt);
 
 void iwl_get_shared_mem_conf(struct iwl_fw_runtime *fwrt);
 
-void iwl_fwrt_handle_notification(struct iwl_fw_runtime *fwrt,
-				  struct iwl_rx_cmd_buffer *rxb);
-
 #endif /* __iwl_fw_runtime_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 06298356df6d..0efd2a36e6c4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1013,10 +1013,8 @@ static void iwl_mvm_rx_common(struct iwl_mvm *mvm,
 		list_add_tail(&entry->list, &mvm->async_handlers_list);
 		spin_unlock(&mvm->async_handlers_lock);
 		schedule_work(&mvm->async_handlers_wk);
-		return;
+		break;
 	}
-
-	iwl_fwrt_handle_notification(&mvm->fwrt, rxb);
 }
 
 static void iwl_mvm_rx(struct iwl_op_mode *op_mode,
-- 
cgit v1.2.3


From f137c0979b96be86c14692c8e4e1f32d93b250da Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Tue, 6 Mar 2018 14:29:11 +0200
Subject: iwlwifi: hard code power save mode to CAM for 22560 devices

Balanced power save mode isn't supported in the fw for 22560 devices
yet.  Configure the power save mode to CAM until it gets implemented.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 0efd2a36e6c4..0e26619fb330 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -709,10 +709,13 @@ iwl_op_mode_mvm_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	}
 
 	/* the hardware splits the A-MSDU */
-	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560)
+	if (mvm->trans->cfg->device_family >= IWL_DEVICE_FAMILY_22560) {
 		trans_cfg.rx_buf_size = IWL_AMSDU_2K;
-	else if (mvm->cfg->mq_rx_supported)
+		/* TODO: remove when balanced power mode is fw supported */
+		iwlmvm_mod_params.power_scheme = IWL_POWER_SCHEME_CAM;
+	} else if (mvm->cfg->mq_rx_supported) {
 		trans_cfg.rx_buf_size = IWL_AMSDU_4K;
+	}
 
 	trans->wide_cmd_header = true;
 	trans_cfg.bc_table_dword =
-- 
cgit v1.2.3


From 266ab689656bd640f85397eb49c16c2ec0a8ccff Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Fri, 27 Jul 2018 14:53:07 +0300
Subject: iwlwifi: mvm: remove dead gscan code

There was a bunch of code to support gscan which has never been used.
Remove it all to cleanup and get rid of a lot of dead code.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/Makefile  |  1 -
 drivers/net/wireless/intel/iwlwifi/fw/file.h | 37 +------------------
 drivers/net/wireless/intel/iwlwifi/fw/img.h  | 36 -------------------
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 54 +---------------------------
 4 files changed, 2 insertions(+), 126 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index d619995b8bc2..04e376cc898c 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -14,7 +14,6 @@ iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
 iwlwifi-objs		+= iwl-trans.o
 iwlwifi-objs		+= fw/notif-wait.o
 iwlwifi-$(CONFIG_IWLMVM) += fw/paging.o fw/smem.o fw/init.o fw/dbg.o
-iwlwifi-$(CONFIG_IWLMVM) += fw/common_rx.o
 iwlwifi-$(CONFIG_ACPI) += fw/acpi.o
 iwlwifi-$(CONFIG_IWLWIFI_DEBUGFS) += fw/debugfs.o
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/file.h b/drivers/net/wireless/intel/iwlwifi/fw/file.h
index c967dfbeacaf..bbf2b265a06a 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/file.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/file.h
@@ -321,7 +321,7 @@ typedef unsigned int __bitwise iwl_ucode_tlv_capa_t;
  *	IWL_UCODE_TLV_API_WIFI_MCC_UPDATE. When either is set, multi-source LAR
  *	is supported.
  * @IWL_UCODE_TLV_CAPA_BT_COEX_RRC: supports BT Coex RRC
- * @IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT: supports gscan
+ * @IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT: supports gscan (no longer used)
  * @IWL_UCODE_TLV_CAPA_STA_PM_NOTIF: firmware will send STA PM notification
  * @IWL_UCODE_TLV_CAPA_TLC_OFFLOAD: firmware implements rate scaling algorithm
  * @IWL_UCODE_TLV_CAPA_DYNAMIC_QUOTA: firmware implements quota related
@@ -892,39 +892,4 @@ struct iwl_fw_dbg_conf_tlv {
 	struct iwl_fw_dbg_conf_hcmd hcmd;
 } __packed;
 
-/**
- * struct iwl_fw_gscan_capabilities - gscan capabilities supported by FW
- * @max_scan_cache_size: total space allocated for scan results (in bytes).
- * @max_scan_buckets: maximum number of channel buckets.
- * @max_ap_cache_per_scan: maximum number of APs that can be stored per scan.
- * @max_rssi_sample_size: number of RSSI samples used for averaging RSSI.
- * @max_scan_reporting_threshold: max possible report threshold. in percentage.
- * @max_hotlist_aps: maximum number of entries for hotlist APs.
- * @max_significant_change_aps: maximum number of entries for significant
- *	change APs.
- * @max_bssid_history_entries: number of BSSID/RSSI entries that the device can
- *	hold.
- * @max_hotlist_ssids: maximum number of entries for hotlist SSIDs.
- * @max_number_epno_networks: max number of epno entries.
- * @max_number_epno_networks_by_ssid: max number of epno entries if ssid is
- *	specified.
- * @max_number_of_white_listed_ssid: max number of white listed SSIDs.
- * @max_number_of_black_listed_ssid: max number of black listed SSIDs.
- */
-struct iwl_fw_gscan_capabilities {
-	__le32 max_scan_cache_size;
-	__le32 max_scan_buckets;
-	__le32 max_ap_cache_per_scan;
-	__le32 max_rssi_sample_size;
-	__le32 max_scan_reporting_threshold;
-	__le32 max_hotlist_aps;
-	__le32 max_significant_change_aps;
-	__le32 max_bssid_history_entries;
-	__le32 max_hotlist_ssids;
-	__le32 max_number_epno_networks;
-	__le32 max_number_epno_networks_by_ssid;
-	__le32 max_number_of_white_listed_ssid;
-	__le32 max_number_of_black_listed_ssid;
-} __packed;
-
 #endif  /* __iwl_fw_file_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/img.h b/drivers/net/wireless/intel/iwlwifi/fw/img.h
index 6c5de68b5244..0861b97c4233 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/img.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/img.h
@@ -192,41 +192,6 @@ struct iwl_fw_cscheme_list {
 	struct iwl_fw_cipher_scheme cs[];
 } __packed;
 
-/**
- * struct iwl_gscan_capabilities - gscan capabilities supported by FW
- * @max_scan_cache_size: total space allocated for scan results (in bytes).
- * @max_scan_buckets: maximum number of channel buckets.
- * @max_ap_cache_per_scan: maximum number of APs that can be stored per scan.
- * @max_rssi_sample_size: number of RSSI samples used for averaging RSSI.
- * @max_scan_reporting_threshold: max possible report threshold. in percentage.
- * @max_hotlist_aps: maximum number of entries for hotlist APs.
- * @max_significant_change_aps: maximum number of entries for significant
- *	change APs.
- * @max_bssid_history_entries: number of BSSID/RSSI entries that the device can
- *	hold.
- * @max_hotlist_ssids: maximum number of entries for hotlist SSIDs.
- * @max_number_epno_networks: max number of epno entries.
- * @max_number_epno_networks_by_ssid: max number of epno entries if ssid is
- *	specified.
- * @max_number_of_white_listed_ssid: max number of white listed SSIDs.
- * @max_number_of_black_listed_ssid: max number of black listed SSIDs.
- */
-struct iwl_gscan_capabilities {
-	u32 max_scan_cache_size;
-	u32 max_scan_buckets;
-	u32 max_ap_cache_per_scan;
-	u32 max_rssi_sample_size;
-	u32 max_scan_reporting_threshold;
-	u32 max_hotlist_aps;
-	u32 max_significant_change_aps;
-	u32 max_bssid_history_entries;
-	u32 max_hotlist_ssids;
-	u32 max_number_epno_networks;
-	u32 max_number_epno_networks_by_ssid;
-	u32 max_number_of_white_listed_ssid;
-	u32 max_number_of_black_listed_ssid;
-};
-
 /**
  * enum iwl_fw_type - iwlwifi firmware type
  * @IWL_FW_DVM: DVM firmware
@@ -298,7 +263,6 @@ struct iwl_fw {
 	size_t n_dbg_mem_tlv;
 	size_t dbg_trigger_tlv_len[FW_DBG_TRIGGER_MAX];
 	u8 dbg_dest_reg_num;
-	struct iwl_gscan_capabilities gscan_capa;
 	u32 dbg_dump_mask;
 };
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 370281e338b2..c0631255aee7 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -402,35 +402,6 @@ static int iwl_store_cscheme(struct iwl_fw *fw, const u8 *data, const u32 len)
 	return 0;
 }
 
-static void iwl_store_gscan_capa(struct iwl_fw *fw, const u8 *data,
-				 const u32 len)
-{
-	struct iwl_fw_gscan_capabilities *fw_capa = (void *)data;
-	struct iwl_gscan_capabilities *capa = &fw->gscan_capa;
-
-	capa->max_scan_cache_size = le32_to_cpu(fw_capa->max_scan_cache_size);
-	capa->max_scan_buckets = le32_to_cpu(fw_capa->max_scan_buckets);
-	capa->max_ap_cache_per_scan =
-		le32_to_cpu(fw_capa->max_ap_cache_per_scan);
-	capa->max_rssi_sample_size = le32_to_cpu(fw_capa->max_rssi_sample_size);
-	capa->max_scan_reporting_threshold =
-		le32_to_cpu(fw_capa->max_scan_reporting_threshold);
-	capa->max_hotlist_aps = le32_to_cpu(fw_capa->max_hotlist_aps);
-	capa->max_significant_change_aps =
-		le32_to_cpu(fw_capa->max_significant_change_aps);
-	capa->max_bssid_history_entries =
-		le32_to_cpu(fw_capa->max_bssid_history_entries);
-	capa->max_hotlist_ssids = le32_to_cpu(fw_capa->max_hotlist_ssids);
-	capa->max_number_epno_networks =
-		le32_to_cpu(fw_capa->max_number_epno_networks);
-	capa->max_number_epno_networks_by_ssid =
-		le32_to_cpu(fw_capa->max_number_epno_networks_by_ssid);
-	capa->max_number_of_white_listed_ssid =
-		le32_to_cpu(fw_capa->max_number_of_white_listed_ssid);
-	capa->max_number_of_black_listed_ssid =
-		le32_to_cpu(fw_capa->max_number_of_black_listed_ssid);
-}
-
 /*
  * Gets uCode section from tlv.
  */
@@ -644,7 +615,6 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 	u32 build, paging_mem_size;
 	int num_of_cpus;
 	bool usniffer_req = false;
-	bool gscan_capa = false;
 
 	if (len < sizeof(*ucode)) {
 		IWL_ERR(drv, "uCode has invalid length: %zd\n", len);
@@ -1090,16 +1060,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 				paging_mem_size;
 			break;
 		case IWL_UCODE_TLV_FW_GSCAN_CAPA:
-			/*
-			 * Don't return an error in case of a shorter tlv_len
-			 * to enable loading of FW that has an old format
-			 * of GSCAN capabilities TLV.
-			 */
-			if (tlv_len < sizeof(struct iwl_fw_gscan_capabilities))
-				break;
-
-			iwl_store_gscan_capa(&drv->fw, tlv_data, tlv_len);
-			gscan_capa = true;
+			/* ignored */
 			break;
 		case IWL_UCODE_TLV_FW_MEM_SEG: {
 			struct iwl_fw_dbg_mem_seg_tlv *dbg_mem =
@@ -1164,19 +1125,6 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 		return -EINVAL;
 	}
 
-	/*
-	 * If ucode advertises that it supports GSCAN but GSCAN
-	 * capabilities TLV is not present, or if it has an old format,
-	 * warn and continue without GSCAN.
-	 */
-	if (fw_has_capa(capa, IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT) &&
-	    !gscan_capa) {
-		IWL_DEBUG_INFO(drv,
-			       "GSCAN is supported but capabilities TLV is unavailable\n");
-		__clear_bit((__force long)IWL_UCODE_TLV_CAPA_GSCAN_SUPPORT,
-			    capa->_capa);
-	}
-
 	return 0;
 
  invalid_tlv_len:
-- 
cgit v1.2.3


From f890269b29d71587bf223a99eb4939199a8fde40 Mon Sep 17 00:00:00 2001
From: Luca Coelho <luciano.coelho@intel.com>
Date: Wed, 14 Mar 2018 16:02:01 +0200
Subject: iwlwifi: pcie: include tcp.h implicitly

If CONFIG_IPV6 is not enabled in the kernel, tcp.h is not included
implicitly from other header files, causing compilation errors.  To
solve that, explicitly include it in tx-gen2.c.

Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index e3ae7f91206b..64db540ad605 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -52,6 +52,7 @@
  *****************************************************************************/
 #include <linux/pm_runtime.h>
 #include <net/tso.h>
+#include <linux/tcp.h>
 
 #include "iwl-debug.h"
 #include "iwl-csr.h"
-- 
cgit v1.2.3


From ff932f61ed2fd52752974831f46a601ce5864a27 Mon Sep 17 00:00:00 2001
From: Golan Ben Ami <golan.ben.ami@intel.com>
Date: Sun, 18 Feb 2018 18:20:09 +0200
Subject: iwlwifi: move some msix and rx functions to a common place

We would like to allow other utlities to init msix and rx.
Put their declarations in a place accessible to other utilities.

Signed-off-by: Golan Ben Ami <golan.ben.ami@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/internal.h | 43 ++++++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/pcie/rx.c       | 24 +++---------
 drivers/net/wireless/intel/iwlwifi/pcie/trans.c    | 23 ------------
 3 files changed, 48 insertions(+), 42 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index f6726ccef819..b63d44b7cd7c 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -45,6 +45,7 @@
 #include "iwl-debug.h"
 #include "iwl-io.h"
 #include "iwl-op-mode.h"
+#include "iwl-drv.h"
 
 /* We need 2 entries for the TX command and header, and another one might
  * be needed for potential data in the SKB's head. The remaining ones can
@@ -639,6 +640,20 @@ IWL_TRANS_GET_PCIE_TRANS(struct iwl_trans *trans)
 	return (void *)trans->trans_specific;
 }
 
+static inline void iwl_pcie_clear_irq(struct iwl_trans *trans,
+				      struct msix_entry *entry)
+{
+	/*
+	 * Before sending the interrupt the HW disables it to prevent
+	 * a nested interrupt. This is done by writing 1 to the corresponding
+	 * bit in the mask register. After handling the interrupt, it should be
+	 * re-enabled by clearing this bit. This register is defined as
+	 * write 1 clear (W1C) register, meaning that it's being clear
+	 * by writing 1 to the bit.
+	 */
+	iwl_write32(trans, CSR_MSIX_AUTOMASK_ST_AD, BIT(entry->entry));
+}
+
 static inline struct iwl_trans *
 iwl_trans_pcie_get_trans(struct iwl_trans_pcie *trans_pcie)
 {
@@ -666,6 +681,11 @@ irqreturn_t iwl_pcie_irq_msix_handler(int irq, void *dev_id);
 irqreturn_t iwl_pcie_irq_rx_msix_handler(int irq, void *dev_id);
 int iwl_pcie_rx_stop(struct iwl_trans *trans);
 void iwl_pcie_rx_free(struct iwl_trans *trans);
+void iwl_pcie_free_rbs_pool(struct iwl_trans *trans);
+void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq);
+int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget);
+void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
+			    struct iwl_rxq *rxq);
 
 /*****************************************************
 * ICT - interrupt handling
@@ -892,6 +912,29 @@ static inline void *iwl_pcie_get_tfd(struct iwl_trans *trans,
 	return txq->tfds + trans_pcie->tfd_size * idx;
 }
 
+static inline const char *queue_name(struct device *dev,
+				     struct iwl_trans_pcie *trans_p, int i)
+{
+	if (trans_p->shared_vec_mask) {
+		int vec = trans_p->shared_vec_mask &
+			  IWL_SHARED_IRQ_FIRST_RSS ? 1 : 0;
+
+		if (i == 0)
+			return DRV_NAME ": shared IRQ";
+
+		return devm_kasprintf(dev, GFP_KERNEL,
+				      DRV_NAME ": queue %d", i + vec);
+	}
+	if (i == 0)
+		return DRV_NAME ": default queue";
+
+	if (i == trans_p->alloc_vecs - 1)
+		return DRV_NAME ": exception";
+
+	return devm_kasprintf(dev, GFP_KERNEL,
+			      DRV_NAME  ": queue %d", i);
+}
+
 static inline void iwl_enable_rfkill_int(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
index 59bedb461a8c..d017aa2a0a8b 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/rx.c
@@ -417,8 +417,8 @@ static struct page *iwl_pcie_rx_alloc_page(struct iwl_trans *trans,
  * iwl_pcie_rxq_restock. The latter function will update the HW to use the newly
  * allocated buffers.
  */
-static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
-				   struct iwl_rxq *rxq)
+void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
+			    struct iwl_rxq *rxq)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	struct iwl_rx_mem_buffer *rxb;
@@ -474,7 +474,7 @@ static void iwl_pcie_rxq_alloc_rbs(struct iwl_trans *trans, gfp_t priority,
 	}
 }
 
-static void iwl_pcie_free_rbs_pool(struct iwl_trans *trans)
+void iwl_pcie_free_rbs_pool(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int i;
@@ -986,7 +986,7 @@ static void iwl_pcie_rx_mq_hw_init(struct iwl_trans *trans)
 	iwl_pcie_enable_rx_wake(trans, true);
 }
 
-static void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq)
+void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq)
 {
 	lockdep_assert_held(&rxq->lock);
 
@@ -996,7 +996,7 @@ static void iwl_pcie_rx_init_rxb_lists(struct iwl_rxq *rxq)
 	rxq->used_count = 0;
 }
 
-static int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget)
+int iwl_pcie_dummy_napi_poll(struct napi_struct *napi, int budget)
 {
 	WARN_ON(1);
 	return 0;
@@ -1479,20 +1479,6 @@ static struct iwl_trans_pcie *iwl_pcie_get_trans_pcie(struct msix_entry *entry)
 	return container_of(entries, struct iwl_trans_pcie, msix_entries[0]);
 }
 
-static inline void iwl_pcie_clear_irq(struct iwl_trans *trans,
-				      struct msix_entry *entry)
-{
-	/*
-	 * Before sending the interrupt the HW disables it to prevent
-	 * a nested interrupt. This is done by writing 1 to the corresponding
-	 * bit in the mask register. After handling the interrupt, it should be
-	 * re-enabled by clearing this bit. This register is defined as
-	 * write 1 clear (W1C) register, meaning that it's being clear
-	 * by writing 1 to the bit.
-	 */
-	iwl_write32(trans, CSR_MSIX_AUTOMASK_ST_AD, BIT(entry->entry));
-}
-
 /*
  * iwl_pcie_rx_msix_handle - Main entry function for receiving responses from fw
  * This interrupt handler should be used with RSS queue only.
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
index a54c2bc985ad..7d319b6863fe 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c
@@ -1709,29 +1709,6 @@ static void iwl_pcie_irq_set_affinity(struct iwl_trans *trans)
 	}
 }
 
-static const char *queue_name(struct device *dev,
-			      struct iwl_trans_pcie *trans_p, int i)
-{
-	if (trans_p->shared_vec_mask) {
-		int vec = trans_p->shared_vec_mask &
-			  IWL_SHARED_IRQ_FIRST_RSS ? 1 : 0;
-
-		if (i == 0)
-			return DRV_NAME ": shared IRQ";
-
-		return devm_kasprintf(dev, GFP_KERNEL,
-				      DRV_NAME ": queue %d", i + vec);
-	}
-	if (i == 0)
-		return DRV_NAME ": default queue";
-
-	if (i == trans_p->alloc_vecs - 1)
-		return DRV_NAME ": exception";
-
-	return devm_kasprintf(dev, GFP_KERNEL,
-			      DRV_NAME  ": queue %d", i);
-}
-
 static int iwl_pcie_init_msix_handler(struct pci_dev *pdev,
 				      struct iwl_trans_pcie *trans_pcie)
 {
-- 
cgit v1.2.3


From 45904e7edcd08730d1888cb79071654e344774a7 Mon Sep 17 00:00:00 2001
From: Sara Sharon <sara.sharon@intel.com>
Date: Wed, 14 Mar 2018 11:27:36 +0200
Subject: iwlwifi: pcie: split tx to amsdu and non amsdu

The code is different enough to justify a split.

Signed-off-by: Sara Sharon <sara.sharon@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 149 +++++++++++++++-------
 1 file changed, 100 insertions(+), 49 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 64db540ad605..b99f33ff9123 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -365,58 +365,89 @@ out_err:
 	return -EINVAL;
 }
 
-static
-struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
-					    struct iwl_txq *txq,
-					    struct iwl_device_cmd *dev_cmd,
-					    struct sk_buff *skb,
-					    struct iwl_cmd_meta *out_meta)
+static struct
+iwl_tfh_tfd *iwl_pcie_gen2_build_tx_amsdu(struct iwl_trans *trans,
+					  struct iwl_txq *txq,
+					  struct iwl_device_cmd *dev_cmd,
+					  struct sk_buff *skb,
+					  struct iwl_cmd_meta *out_meta,
+					  int hdr_len,
+					  int tx_cmd_len)
 {
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
 	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
 	dma_addr_t tb_phys;
-	bool amsdu;
-	int i, len, tb1_len, tb2_len, hdr_len;
+	int len;
 	void *tb1_addr;
 
-	memset(tfd, 0, sizeof(*tfd));
+	tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
 
-	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
-		(*ieee80211_get_qos_ctl(hdr) &
-		 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
+	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
+
+	/*
+	 * The second TB (tb1) points to the remainder of the TX command
+	 * and the 802.11 header - dword aligned size
+	 * (This calculation modifies the TX command, so do it before the
+	 * setup of the first TB)
+	 */
+	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
+	      IWL_FIRST_TB_SIZE;
+
+	/* do not align A-MSDU to dword as the subframe header aligns it */
+
+	/* map the data for TB1 */
+	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
+	tb_phys = dma_map_single(trans->dev, tb1_addr, len, DMA_TO_DEVICE);
+	if (unlikely(dma_mapping_error(trans->dev, tb_phys)))
+		goto out_err;
+	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, len);
+
+	if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd,
+				      len + IWL_FIRST_TB_SIZE,
+				      hdr_len, dev_cmd))
+		goto out_err;
+
+	/* building the A-MSDU might have changed this data, memcpy it now */
+	memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr, IWL_FIRST_TB_SIZE);
+	return tfd;
+
+out_err:
+	iwl_pcie_gen2_tfd_unmap(trans, out_meta, tfd);
+	return NULL;
+}
+
+static struct
+iwl_tfh_tfd *iwl_pcie_gen2_build_tx(struct iwl_trans *trans,
+				    struct iwl_txq *txq,
+				    struct iwl_device_cmd *dev_cmd,
+				    struct sk_buff *skb,
+				    struct iwl_cmd_meta *out_meta,
+				    int hdr_len,
+				    int tx_cmd_len)
+{
+	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
+	dma_addr_t tb_phys;
+	int i, len, tb1_len, tb2_len;
+	void *tb1_addr;
 
 	tb_phys = iwl_pcie_get_first_tb_dma(txq, idx);
+
 	/* The first TB points to bi-directional DMA data */
-	if (!amsdu)
-		memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr,
-		       IWL_FIRST_TB_SIZE);
+	memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr, IWL_FIRST_TB_SIZE);
 
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, IWL_FIRST_TB_SIZE);
 
-	/* there must be data left over for TB1 or this code must be changed */
-	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
-
 	/*
 	 * The second TB (tb1) points to the remainder of the TX command
 	 * and the 802.11 header - dword aligned size
 	 * (This calculation modifies the TX command, so do it before the
 	 * setup of the first TB)
 	 */
-	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
-		len = sizeof(struct iwl_tx_cmd_gen2);
-	else
-		len = sizeof(struct iwl_tx_cmd_gen3);
+	len = tx_cmd_len + sizeof(struct iwl_cmd_header) + hdr_len -
+	      IWL_FIRST_TB_SIZE;
 
-	len += sizeof(struct iwl_cmd_header) +
-		ieee80211_hdrlen(hdr->frame_control) -
-		IWL_FIRST_TB_SIZE;
-
-	/* do not align A-MSDU to dword as the subframe header aligns it */
-	if (amsdu)
-		tb1_len = len;
-	else
-		tb1_len = ALIGN(len, 4);
+	tb1_len = ALIGN(len, 4);
 
 	/* map the data for TB1 */
 	tb1_addr = ((u8 *)&dev_cmd->hdr) + IWL_FIRST_TB_SIZE;
@@ -425,23 +456,6 @@ struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
 		goto out_err;
 	iwl_pcie_gen2_set_tb(trans, tfd, tb_phys, tb1_len);
 
-	hdr_len = ieee80211_hdrlen(hdr->frame_control);
-
-	if (amsdu) {
-		if (iwl_pcie_gen2_build_amsdu(trans, skb, tfd,
-					      tb1_len + IWL_FIRST_TB_SIZE,
-					      hdr_len, dev_cmd))
-			goto out_err;
-
-		/*
-		 * building the A-MSDU might have changed this data, so memcpy
-		 * it now
-		 */
-		memcpy(&txq->first_tb_bufs[idx], &dev_cmd->hdr,
-		       IWL_FIRST_TB_SIZE);
-		return tfd;
-	}
-
 	/* set up TFD's third entry to point to remainder of skb's head */
 	tb2_len = skb_headlen(skb) - hdr_len;
 
@@ -483,6 +497,43 @@ out_err:
 	return NULL;
 }
 
+static
+struct iwl_tfh_tfd *iwl_pcie_gen2_build_tfd(struct iwl_trans *trans,
+					    struct iwl_txq *txq,
+					    struct iwl_device_cmd *dev_cmd,
+					    struct sk_buff *skb,
+					    struct iwl_cmd_meta *out_meta)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	int idx = iwl_pcie_get_cmd_index(txq, txq->write_ptr);
+	struct iwl_tfh_tfd *tfd = iwl_pcie_get_tfd(trans, txq, idx);
+	int len, hdr_len;
+	bool amsdu;
+
+	/* There must be data left over for TB1 or this code must be changed */
+	BUILD_BUG_ON(sizeof(struct iwl_tx_cmd_gen2) < IWL_FIRST_TB_SIZE);
+
+	memset(tfd, 0, sizeof(*tfd));
+
+	if (trans->cfg->device_family < IWL_DEVICE_FAMILY_22560)
+		len = sizeof(struct iwl_tx_cmd_gen2);
+	else
+		len = sizeof(struct iwl_tx_cmd_gen3);
+
+	amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
+			(*ieee80211_get_qos_ctl(hdr) &
+			 IEEE80211_QOS_CTL_A_MSDU_PRESENT);
+
+	hdr_len = ieee80211_hdrlen(hdr->frame_control);
+
+	if (amsdu)
+		return iwl_pcie_gen2_build_tx_amsdu(trans, txq, dev_cmd, skb,
+						    out_meta, hdr_len, len);
+
+	return iwl_pcie_gen2_build_tx(trans, txq, dev_cmd, skb, out_meta,
+				      hdr_len, len);
+}
+
 int iwl_trans_pcie_gen2_tx(struct iwl_trans *trans, struct sk_buff *skb,
 			   struct iwl_device_cmd *dev_cmd, int txq_id)
 {
-- 
cgit v1.2.3


From b1eb4f844f8c35e252eebfacacc438644d9f9ba8 Mon Sep 17 00:00:00 2001
From: Peter Rosin <peda@axentia.se>
Date: Thu, 2 Aug 2018 10:25:19 +0100
Subject: drm/i2c: tda998x: find the drm_device via the drm_connector

This prepares for being a drm_bridge which will not register the
encoder. That makes the connector the better choice.

Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 0038c976536a..c39f7c36ba24 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -762,7 +762,7 @@ static void tda998x_detect_work(struct work_struct *work)
 {
 	struct tda998x_priv *priv =
 		container_of(work, struct tda998x_priv, detect_work);
-	struct drm_device *dev = priv->encoder.dev;
+	struct drm_device *dev = priv->connector.dev;
 
 	if (dev)
 		drm_kms_helper_hotplug_event(dev);
-- 
cgit v1.2.3


From 2c6e758332a4fdf0d2b1c76adba10961afdabc8a Mon Sep 17 00:00:00 2001
From: Peter Rosin <peda@axentia.se>
Date: Thu, 2 Aug 2018 10:25:19 +0100
Subject: drm/i2c: tda998x: split tda998x_encoder_dpms into enable/disable

This fits better with the drm_bridge callbacks for when this
driver becomes a drm_bridge.

Suggested-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Peter Rosin <peda@axentia.se>
[edited by rmk to just split the tda998x_encoder_dpms() function
 and restore the double-disable protection we originally had,
 preserving original behaviour.]
Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index c39f7c36ba24..f9a9fb6b97d0 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1308,18 +1308,9 @@ static int tda998x_connector_init(struct tda998x_priv *priv,
 
 /* DRM encoder functions */
 
-static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
+static void tda998x_enable(struct tda998x_priv *priv)
 {
-	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
-	bool on;
-
-	/* we only care about on or off: */
-	on = mode == DRM_MODE_DPMS_ON;
-
-	if (on == priv->is_on)
-		return;
-
-	if (on) {
+	if (!priv->is_on) {
 		/* enable video ports, audio will be enabled later */
 		reg_write(priv, REG_ENA_VP_0, 0xff);
 		reg_write(priv, REG_ENA_VP_1, 0xff);
@@ -1330,7 +1321,12 @@ static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
 		reg_write(priv, REG_VIP_CNTRL_2, priv->vip_cntrl_2);
 
 		priv->is_on = true;
-	} else {
+	}
+}
+
+static void tda998x_disable(struct tda998x_priv *priv)
+{
+	if (priv->is_on) {
 		/* disable video ports */
 		reg_write(priv, REG_ENA_VP_0, 0x00);
 		reg_write(priv, REG_ENA_VP_1, 0x00);
@@ -1340,6 +1336,23 @@ static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
 	}
 }
 
+static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
+{
+	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
+	bool on;
+
+	/* we only care about on or off: */
+	on = mode == DRM_MODE_DPMS_ON;
+
+	if (on == priv->is_on)
+		return;
+
+	if (on)
+		tda998x_enable(priv);
+	else
+		tda998x_disable(priv);
+}
+
 static void
 tda998x_encoder_mode_set(struct drm_encoder *encoder,
 			 struct drm_display_mode *mode,
-- 
cgit v1.2.3


From 6c1187aaa2912fad40119140286160cfd9f4ac2f Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:25:19 +0100
Subject: drm/i2c: tda998x: move tda998x_set_config() into tda998x_create()

Move the non-DT configuration of the TDA998x into tda998x_create()
so that we do all setup in one place.

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 73 +++++++++++++++++++--------------------
 1 file changed, 35 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index f9a9fb6b97d0..c35b52a83001 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1630,6 +1630,25 @@ static int tda998x_get_audio_ports(struct tda998x_priv *priv,
 	return 0;
 }
 
+static void tda998x_set_config(struct tda998x_priv *priv,
+			       const struct tda998x_encoder_params *p)
+{
+	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(p->swap_a) |
+			    (p->mirr_a ? VIP_CNTRL_0_MIRR_A : 0) |
+			    VIP_CNTRL_0_SWAP_B(p->swap_b) |
+			    (p->mirr_b ? VIP_CNTRL_0_MIRR_B : 0);
+	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(p->swap_c) |
+			    (p->mirr_c ? VIP_CNTRL_1_MIRR_C : 0) |
+			    VIP_CNTRL_1_SWAP_D(p->swap_d) |
+			    (p->mirr_d ? VIP_CNTRL_1_MIRR_D : 0);
+	priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(p->swap_e) |
+			    (p->mirr_e ? VIP_CNTRL_2_MIRR_E : 0) |
+			    VIP_CNTRL_2_SWAP_F(p->swap_f) |
+			    (p->mirr_f ? VIP_CNTRL_2_MIRR_F : 0);
+
+	priv->audio_params = p->audio_params;
+}
+
 static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 {
 	struct device_node *np = client->dev.of_node;
@@ -1781,23 +1800,24 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	/* enable EDID read irq: */
 	reg_set(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
 
-	if (!np)
-		return 0;		/* non-DT */
+	if (np) {
+		/* get the device tree parameters */
+		ret = of_property_read_u32(np, "video-ports", &video);
+		if (ret == 0) {
+			priv->vip_cntrl_0 = video >> 16;
+			priv->vip_cntrl_1 = video >> 8;
+			priv->vip_cntrl_2 = video;
+		}
 
-	/* get the device tree parameters */
-	ret = of_property_read_u32(np, "video-ports", &video);
-	if (ret == 0) {
-		priv->vip_cntrl_0 = video >> 16;
-		priv->vip_cntrl_1 = video >> 8;
-		priv->vip_cntrl_2 = video;
-	}
+		ret = tda998x_get_audio_ports(priv, np);
+		if (ret)
+			goto fail;
 
-	ret = tda998x_get_audio_ports(priv, np);
-	if (ret)
-		goto fail;
-
-	if (priv->audio_port[0].format != AFMT_UNUSED)
-		tda998x_audio_codec_init(priv, &client->dev);
+		if (priv->audio_port[0].format != AFMT_UNUSED)
+			tda998x_audio_codec_init(priv, &client->dev);
+	} else if (client->dev.platform_data) {
+		tda998x_set_config(priv, client->dev.platform_data);
+	}
 
 	return 0;
 
@@ -1843,28 +1863,8 @@ static const struct drm_encoder_funcs tda998x_encoder_funcs = {
 	.destroy = tda998x_encoder_destroy,
 };
 
-static void tda998x_set_config(struct tda998x_priv *priv,
-			       const struct tda998x_encoder_params *p)
-{
-	priv->vip_cntrl_0 = VIP_CNTRL_0_SWAP_A(p->swap_a) |
-			    (p->mirr_a ? VIP_CNTRL_0_MIRR_A : 0) |
-			    VIP_CNTRL_0_SWAP_B(p->swap_b) |
-			    (p->mirr_b ? VIP_CNTRL_0_MIRR_B : 0);
-	priv->vip_cntrl_1 = VIP_CNTRL_1_SWAP_C(p->swap_c) |
-			    (p->mirr_c ? VIP_CNTRL_1_MIRR_C : 0) |
-			    VIP_CNTRL_1_SWAP_D(p->swap_d) |
-			    (p->mirr_d ? VIP_CNTRL_1_MIRR_D : 0);
-	priv->vip_cntrl_2 = VIP_CNTRL_2_SWAP_E(p->swap_e) |
-			    (p->mirr_e ? VIP_CNTRL_2_MIRR_E : 0) |
-			    VIP_CNTRL_2_SWAP_F(p->swap_f) |
-			    (p->mirr_f ? VIP_CNTRL_2_MIRR_F : 0);
-
-	priv->audio_params = p->audio_params;
-}
-
 static int tda998x_bind(struct device *dev, struct device *master, void *data)
 {
-	struct tda998x_encoder_params *params = dev->platform_data;
 	struct i2c_client *client = to_i2c_client(dev);
 	struct drm_device *drm = data;
 	struct tda998x_priv *priv;
@@ -1892,9 +1892,6 @@ static int tda998x_bind(struct device *dev, struct device *master, void *data)
 	if (ret)
 		return ret;
 
-	if (!dev->of_node && params)
-		tda998x_set_config(priv, params);
-
 	drm_encoder_helper_add(&priv->encoder, &tda998x_encoder_helper_funcs);
 	ret = drm_encoder_init(drm, &priv->encoder, &tda998x_encoder_funcs,
 			       DRM_MODE_ENCODER_TMDS, NULL);
-- 
cgit v1.2.3


From 5c41bb6071257ba668a2b8933a8654e69aea1cee Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 2 Aug 2018 10:40:33 +0200
Subject: gpu: ipu-v3: add support for XRGB32 and XBGR32 V4L2 pixel formats

These should be used instead of the ill-defined deprecated RGB32 and
BGR32 V4L2 pixel formats.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c        | 4 ++++
 drivers/gpu/ipu-v3/ipu-cpmem.c         | 8 ++++++++
 drivers/gpu/ipu-v3/ipu-image-convert.c | 6 ++++++
 3 files changed, 18 insertions(+)

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 48685cddbad1..66e9405faedc 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -122,6 +122,8 @@ enum ipu_color_space ipu_pixelformat_to_colorspace(u32 pixelformat)
 	case V4L2_PIX_FMT_NV16:
 	case V4L2_PIX_FMT_NV61:
 		return IPUV3_COLORSPACE_YUV;
+	case V4L2_PIX_FMT_XRGB32:
+	case V4L2_PIX_FMT_XBGR32:
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_BGR32:
 	case V4L2_PIX_FMT_RGB24:
@@ -190,6 +192,8 @@ int ipu_stride_to_bytes(u32 pixel_stride, u32 pixelformat)
 		return (24 * pixel_stride) >> 3;
 	case V4L2_PIX_FMT_BGR32:
 	case V4L2_PIX_FMT_RGB32:
+	case V4L2_PIX_FMT_XBGR32:
+	case V4L2_PIX_FMT_XRGB32:
 		return (32 * pixel_stride) >> 3;
 	default:
 		break;
diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 125721a7f8b6..0f1155ea0fbd 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -188,6 +188,12 @@ static int v4l2_pix_fmt_to_drm_fourcc(u32 pixelformat)
 	case V4L2_PIX_FMT_RGB32:
 		/* R G B A <=> [32:0] A:B:G:R */
 		return DRM_FORMAT_XBGR8888;
+	case V4L2_PIX_FMT_XBGR32:
+		/* B G R X <=> [32:0] X:R:G:B */
+		return DRM_FORMAT_XRGB8888;
+	case V4L2_PIX_FMT_XRGB32:
+		/* X R G B <=> [32:0] B:G:R:X */
+		return DRM_FORMAT_BGRX8888;
 	case V4L2_PIX_FMT_UYVY:
 		return DRM_FORMAT_UYVY;
 	case V4L2_PIX_FMT_YUYV:
@@ -787,6 +793,8 @@ int ipu_cpmem_set_image(struct ipuv3_channel *ch, struct ipu_image *image)
 		break;
 	case V4L2_PIX_FMT_RGB32:
 	case V4L2_PIX_FMT_BGR32:
+	case V4L2_PIX_FMT_XRGB32:
+	case V4L2_PIX_FMT_XBGR32:
 		offset = image->rect.left * 4 +
 			image->rect.top * pix->bytesperline;
 		break;
diff --git a/drivers/gpu/ipu-v3/ipu-image-convert.c b/drivers/gpu/ipu-v3/ipu-image-convert.c
index 524a717ab28e..f4081962784c 100644
--- a/drivers/gpu/ipu-v3/ipu-image-convert.c
+++ b/drivers/gpu/ipu-v3/ipu-image-convert.c
@@ -226,6 +226,12 @@ static const struct ipu_image_pixfmt image_convert_formats[] = {
 	}, {
 		.fourcc	= V4L2_PIX_FMT_BGR32,
 		.bpp    = 32,
+	}, {
+		.fourcc	= V4L2_PIX_FMT_XRGB32,
+		.bpp    = 32,
+	}, {
+		.fourcc	= V4L2_PIX_FMT_XBGR32,
+		.bpp    = 32,
 	}, {
 		.fourcc	= V4L2_PIX_FMT_YUYV,
 		.bpp    = 16,
-- 
cgit v1.2.3


From 9a73f6a235c2351adc07471519d4980e2fb33bbc Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:47:09 -0500
Subject: ASoC: wm8961: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1271173 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8961.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8961.c b/sound/soc/codecs/wm8961.c
index f70f563d59f3..68b4cadc308f 100644
--- a/sound/soc/codecs/wm8961.c
+++ b/sound/soc/codecs/wm8961.c
@@ -653,6 +653,7 @@ static int wm8961_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 
 	case SND_SOC_DAIFMT_DSP_B:
 		aif |= WM8961_LRP;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif |= 3;
 		switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
-- 
cgit v1.2.3


From 065dcc270af66acb4226b49f635b41a054b663d4 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:49:13 -0500
Subject: ASoC: rt5640: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1056547 ("Missing break in switch")
Addresses-Coverity-ID: 1056548 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5640.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index 8bf8d360c25f..27770143ae8f 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -1665,6 +1665,7 @@ static int get_sdp_info(struct snd_soc_component *component, int dai_id)
 			break;
 		case RT5640_IF_113:
 			ret |= RT5640_U_IF1;
+			/* fall through */
 		case RT5640_IF_312:
 		case RT5640_IF_213:
 			ret |= RT5640_U_IF2;
@@ -1680,6 +1681,7 @@ static int get_sdp_info(struct snd_soc_component *component, int dai_id)
 			break;
 		case RT5640_IF_223:
 			ret |= RT5640_U_IF1;
+			/* fall through */
 		case RT5640_IF_123:
 		case RT5640_IF_321:
 			ret |= RT5640_U_IF2;
-- 
cgit v1.2.3


From 43a26bd026dab09a8b28c40e94ba534a52375b20 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:50:20 -0500
Subject: ASoC: rt5677: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1271174 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5677.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 8a0181a2db08..922becfee59b 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -4417,6 +4417,7 @@ static int rt5677_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx_mask,
 		break;
 	case 25:
 		slot_width_25 = 0x8080;
+		/* fall through */
 	case 24:
 		val |= (2 << 8);
 		break;
-- 
cgit v1.2.3


From 85e7e77079f3201799467803f6c8533a9921e32d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:51:18 -0500
Subject: ASoC: wm8955: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115047 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8955.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c
index ba44e3d6c1e0..cd204f79647d 100644
--- a/sound/soc/codecs/wm8955.c
+++ b/sound/soc/codecs/wm8955.c
@@ -686,6 +686,7 @@ static int wm8955_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif |= WM8955_LRP;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif |= 0x3;
 		break;
-- 
cgit v1.2.3


From 3eb7dbc6d844d2033271434d02ff90ac9b19e393 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:51:59 -0500
Subject: ASoC: wm8960: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115041 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8960.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index c30f5aa392c6..8dc1f3d6a988 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -839,6 +839,7 @@ static int wm8960_hw_params(struct snd_pcm_substream *substream,
 			iface |= 0x000c;
 			break;
 		}
+		/* fall through */
 	default:
 		dev_err(component->dev, "unsupported width %d\n",
 			params_width(params));
-- 
cgit v1.2.3


From da41787b9f319a7a23fcc8cf65c6ad646803962e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:52:41 -0500
Subject: ASoC: wm8904: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115042 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8904.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index 9037a35b931d..1965635ec07c 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -1455,6 +1455,7 @@ static int wm8904_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif1 |= 0x3 | WM8904_AIF_LRCLK_INV;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif1 |= 0x3;
 		break;
-- 
cgit v1.2.3


From 42ef3c94ff6e8315377c04504f1bce50d1f21738 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:53:19 -0500
Subject: ASoC: wm8996: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 146354 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8996.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index d9d206046f8c..78a408236cfb 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -1858,6 +1858,7 @@ static int wm8996_set_sysclk(struct snd_soc_dai *dai,
 	case 24576000:
 		ratediv = WM8996_SYSCLK_DIV;
 		wm8996->sysclk /= 2;
+		/* fall through */
 	case 11289600:
 	case 12288000:
 		snd_soc_component_update_bits(component, WM8996_AIF_RATE,
-- 
cgit v1.2.3


From a9531ab151117e976544e0dc74a9bc8cbd01145f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:54:03 -0500
Subject: ASoC: wm8962: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115043 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8962.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index a11e9d6bf950..efd8910b1ff7 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2649,6 +2649,7 @@ static int wm8962_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif0 |= WM8962_LRCLK_INV | 3;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif0 |= 3;
 
-- 
cgit v1.2.3


From af5d1d5d4ba71164711025e077511ad48d5690e9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:54:45 -0500
Subject: ASoC: wm8995: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115045 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8995.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8995.c b/sound/soc/codecs/wm8995.c
index 60e227832331..68c99fe37097 100644
--- a/sound/soc/codecs/wm8995.c
+++ b/sound/soc/codecs/wm8995.c
@@ -1465,6 +1465,7 @@ static int wm8995_set_dai_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif |= WM8995_AIF1_LRCLK_INV;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif |= (0x3 << WM8995_AIF1_FMT_SHIFT);
 		break;
-- 
cgit v1.2.3


From 7a2235ef507822679ac89007a6a37b23f30eed56 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:55:26 -0500
Subject: ASoC: wm9081: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1357430 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm9081.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm9081.c b/sound/soc/codecs/wm9081.c
index 5a0ea7b3c149..399255d1f78a 100644
--- a/sound/soc/codecs/wm9081.c
+++ b/sound/soc/codecs/wm9081.c
@@ -933,6 +933,7 @@ static int wm9081_set_dai_fmt(struct snd_soc_dai *dai,
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_B:
 		aif2 |= WM9081_AIF_LRCLK_INV;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		aif2 |= 0x3;
 		break;
-- 
cgit v1.2.3


From 2cea1542859bc812f1ec51ea71c06e927e5b922e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 14:56:16 -0500
Subject: ASoC: wm8994: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115050 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8994.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 7fdfdf3f6e67..62f8c5b9ba92 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -2432,6 +2432,7 @@ static int wm8994_set_dai_sysclk(struct snd_soc_dai *dai,
 			snd_soc_component_update_bits(component, WM8994_POWER_MANAGEMENT_2,
 					    WM8994_OPCLK_ENA, 0);
 		}
+		/* fall through */
 
 	default:
 		return -EINVAL;
-- 
cgit v1.2.3


From 9f0ba3d92fe63fa72f88238d9dde47a38a7d8f40 Mon Sep 17 00:00:00 2001
From: Steve Longerbeam <slongerbeam@gmail.com>
Date: Wed, 1 Aug 2018 12:12:17 -0700
Subject: gpu: ipu-v3: Fix U/V offset macros for planar 4:2:0

The U and V offset macros for planar 4:2:0 (U_OFFSET, V_OFFSET, and
UV_OFFSET), are not correct. The height component to the offset was
calculated as:

(pix->width * y / 4)

But this does not produce correct offsets for odd values of y (luma
line #). The luma line # must be decimated by two to produce the
correct U/V line #, so the correct formula is:

(pix->width * (y / 2) / 2)

Signed-off-by: Steve Longerbeam <steve_longerbeam@mentor.com>
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-cpmem.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/ipu-v3/ipu-cpmem.c b/drivers/gpu/ipu-v3/ipu-cpmem.c
index 9f2d9ec42add..e68e4734f052 100644
--- a/drivers/gpu/ipu-v3/ipu-cpmem.c
+++ b/drivers/gpu/ipu-v3/ipu-cpmem.c
@@ -530,17 +530,17 @@ static const struct ipu_rgb def_bgra_16 = {
 
 #define Y_OFFSET(pix, x, y)	((x) + pix->width * (y))
 #define U_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
-				 (pix->width * (y) / 4) + (x) / 2)
+				 (pix->width * ((y) / 2) / 2) + (x) / 2)
 #define V_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
 				 (pix->width * pix->height / 4) +	\
-				 (pix->width * (y) / 4) + (x) / 2)
+				 (pix->width * ((y) / 2) / 2) + (x) / 2)
 #define U2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
 				 (pix->width * (y) / 2) + (x) / 2)
 #define V2_OFFSET(pix, x, y)	((pix->width * pix->height) +		\
 				 (pix->width * pix->height / 2) +	\
 				 (pix->width * (y) / 2) + (x) / 2)
 #define UV_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
-				 (pix->width * (y) / 2) + (x))
+				 (pix->width * ((y) / 2)) + (x))
 #define UV2_OFFSET(pix, x, y)	((pix->width * pix->height) +	\
 				 (pix->width * y) + (x))
 
-- 
cgit v1.2.3


From 73edbe42582207ff8f47168f05124376394aa643 Mon Sep 17 00:00:00 2001
From: Rohit kumar <rohitkr@codeaurora.org>
Date: Thu, 2 Aug 2018 12:32:59 +0530
Subject: ASoC: qcom: Fix unmet dependency warning for SND_SOC_SDM845

Add DEPENDS_ON QCOM_APR for SND_SOC_SDM845 to fix the
warning: unmet direct dependencies detected for
SND_SOC_QDSP6.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Rohit kumar <rohitkr@codeaurora.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 350730839c6f..5f03312ef007 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -93,6 +93,7 @@ config SND_SOC_MSM8996
 
 config SND_SOC_SDM845
 	tristate "SoC Machine driver for SDM845 boards"
+	depends on QCOM_APR
 	select SND_SOC_QDSP6
 	help
 	  To add support for audio on Qualcomm Technologies Inc.
-- 
cgit v1.2.3


From fdec79c18b08c68cfa079f2d3ee23c5a120a2eda Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Thu, 2 Aug 2018 01:47:30 +0000
Subject: ASoC: fsi: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/sh_fsi.h | 13 +++++--------
 1 file changed, 5 insertions(+), 8 deletions(-)

diff --git a/include/sound/sh_fsi.h b/include/sound/sh_fsi.h
index 7a9710b4b799..89eafe23ef88 100644
--- a/include/sound/sh_fsi.h
+++ b/include/sound/sh_fsi.h
@@ -1,16 +1,13 @@
-#ifndef __SOUND_FSI_H
-#define __SOUND_FSI_H
-
-/*
+/* SPDX-License-Identifier: GPL-2.0
+ *
  * Fifo-attached Serial Interface (FSI) support for SH7724
  *
  * Copyright (C) 2009 Renesas Solutions Corp.
  * Kuninori Morimoto <morimoto.kuninori@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
+#ifndef __SOUND_FSI_H
+#define __SOUND_FSI_H
+
 #include <linux/clk.h>
 #include <sound/soc.h>
 
-- 
cgit v1.2.3


From 83b15832ab91c9a4651decb6dc40075dd979d443 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Wed, 25 Jul 2018 12:38:10 -0400
Subject: media: doc-rst: Add packed Bayer raw14 pixel formats

These formats are compressed 14-bit raw bayer formats with four different
pixel orders. They are similar to 10-bit variants. The formats added by
this patch are

	V4L2_PIX_FMT_SBGGR14P
	V4L2_PIX_FMT_SGBRG14P
	V4L2_PIX_FMT_SGRBG14P
	V4L2_PIX_FMT_SRGGB14P

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Acked-by: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/pixfmt-rgb.rst      |   1 +
 Documentation/media/uapi/v4l/pixfmt-srggb14p.rst | 127 +++++++++++++++++++++++
 drivers/media/v4l2-core/v4l2-ioctl.c             |   4 +
 include/uapi/linux/videodev2.h                   |   5 +
 4 files changed, 137 insertions(+)
 create mode 100644 Documentation/media/uapi/v4l/pixfmt-srggb14p.rst

diff --git a/Documentation/media/uapi/v4l/pixfmt-rgb.rst b/Documentation/media/uapi/v4l/pixfmt-rgb.rst
index cf2ef7df9616..1f9a7e3a07c9 100644
--- a/Documentation/media/uapi/v4l/pixfmt-rgb.rst
+++ b/Documentation/media/uapi/v4l/pixfmt-rgb.rst
@@ -19,4 +19,5 @@ RGB Formats
     pixfmt-srggb10-ipu3
     pixfmt-srggb12
     pixfmt-srggb12p
+    pixfmt-srggb14p
     pixfmt-srggb16
diff --git a/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst b/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst
new file mode 100644
index 000000000000..88d20c0e4282
--- /dev/null
+++ b/Documentation/media/uapi/v4l/pixfmt-srggb14p.rst
@@ -0,0 +1,127 @@
+.. -*- coding: utf-8; mode: rst -*-
+
+.. _V4L2-PIX-FMT-SRGGB14P:
+.. _v4l2-pix-fmt-sbggr14p:
+.. _v4l2-pix-fmt-sgbrg14p:
+.. _v4l2-pix-fmt-sgrbg14p:
+
+*******************************************************************************************************************************
+V4L2_PIX_FMT_SRGGB14P ('pRCC'), V4L2_PIX_FMT_SGRBG14P ('pgCC'), V4L2_PIX_FMT_SGBRG14P ('pGCC'), V4L2_PIX_FMT_SBGGR14P ('pBCC'),
+*******************************************************************************************************************************
+
+*man V4L2_PIX_FMT_SRGGB14P(2)*
+
+V4L2_PIX_FMT_SGRBG14P
+V4L2_PIX_FMT_SGBRG14P
+V4L2_PIX_FMT_SBGGR14P
+14-bit packed Bayer formats
+
+
+Description
+===========
+
+These four pixel formats are packed raw sRGB / Bayer formats with 14
+bits per colour. Every four consecutive samples are packed into seven
+bytes. Each of the first four bytes contain the eight high order bits
+of the pixels, and the three following bytes contains the six least
+significants bits of each pixel, in the same order.
+
+Each n-pixel row contains n/2 green samples and n/2 blue or red samples,
+with alternating green-red and green-blue rows. They are conventionally
+described as GRGR... BGBG..., RGRG... GBGB..., etc. Below is an example
+of one of these formats:
+
+**Byte Order.**
+Each cell is one byte.
+
+
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths:       2 1 1 1 1 1 1 1
+
+
+    -  .. row 1
+
+       -  start + 0:
+
+       -  B\ :sub:`00high`
+
+       -  G\ :sub:`01high`
+
+       -  B\ :sub:`02high`
+
+       -  G\ :sub:`03high`
+
+       -  G\ :sub:`01low bits 1--0`\ (bits 7--6)
+	  B\ :sub:`00low bits 5--0`\ (bits 5--0)
+
+       -  R\ :sub:`02low bits 3--0`\ (bits 7--4)
+	  G\ :sub:`01low bits 5--2`\ (bits 3--0)
+
+       -  G\ :sub:`03low bits 5--0`\ (bits 7--2)
+	  R\ :sub:`02low bits 5--4`\ (bits 1--0)
+
+    -  .. row 2
+
+       -  start + 7:
+
+       -  G\ :sub:`00high`
+
+       -  R\ :sub:`01high`
+
+       -  G\ :sub:`02high`
+
+       -  R\ :sub:`03high`
+
+       -  R\ :sub:`01low bits 1--0`\ (bits 7--6)
+	  G\ :sub:`00low bits 5--0`\ (bits 5--0)
+
+       -  G\ :sub:`02low bits 3--0`\ (bits 7--4)
+	  R\ :sub:`01low bits 5--2`\ (bits 3--0)
+
+       -  R\ :sub:`03low bits 5--0`\ (bits 7--2)
+	  G\ :sub:`02low bits 5--4`\ (bits 1--0)
+
+    -  .. row 3
+
+       -  start + 14
+
+       -  B\ :sub:`20high`
+
+       -  G\ :sub:`21high`
+
+       -  B\ :sub:`22high`
+
+       -  G\ :sub:`23high`
+
+       -  G\ :sub:`21low bits 1--0`\ (bits 7--6)
+	  B\ :sub:`20low bits 5--0`\ (bits 5--0)
+
+       -  R\ :sub:`22low bits 3--0`\ (bits 7--4)
+	  G\ :sub:`21low bits 5--2`\ (bits 3--0)
+
+       -  G\ :sub:`23low bits 5--0`\ (bits 7--2)
+	  R\ :sub:`22low bits 5--4`\ (bits 1--0)
+
+    -  .. row 4
+
+       -  start + 21
+
+       -  G\ :sub:`30high`
+
+       -  R\ :sub:`31high`
+
+       -  G\ :sub:`32high`
+
+       -  R\ :sub:`33high`
+
+       -  R\ :sub:`31low bits 1--0`\ (bits 7--6)
+	  G\ :sub:`30low bits 5--0`\ (bits 5--0)
+
+       -  G\ :sub:`32low bits 3--0`\ (bits 7--4)
+	  R\ :sub:`31low bits 5--2`\ (bits 3--0)
+
+       -  R\ :sub:`33low bits 5--0`\ (bits 7--2)
+	  G\ :sub:`32low bits 5--4`\ (bits 1--0)
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 26d9702069fd..fd8d15f12307 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -1259,6 +1259,10 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_SGBRG12P:	descr = "12-bit Bayer GBGB/RGRG Packed"; break;
 	case V4L2_PIX_FMT_SGRBG12P:	descr = "12-bit Bayer GRGR/BGBG Packed"; break;
 	case V4L2_PIX_FMT_SRGGB12P:	descr = "12-bit Bayer RGRG/GBGB Packed"; break;
+	case V4L2_PIX_FMT_SBGGR14P:	descr = "14-bit Bayer BGBG/GRGR Packed"; break;
+	case V4L2_PIX_FMT_SGBRG14P:	descr = "14-bit Bayer GBGB/RGRG Packed"; break;
+	case V4L2_PIX_FMT_SGRBG14P:	descr = "14-bit Bayer GRGR/BGBG Packed"; break;
+	case V4L2_PIX_FMT_SRGGB14P:	descr = "14-bit Bayer RGRG/GBGB Packed"; break;
 	case V4L2_PIX_FMT_SBGGR16:	descr = "16-bit Bayer BGBG/GRGR"; break;
 	case V4L2_PIX_FMT_SGBRG16:	descr = "16-bit Bayer GBGB/RGRG"; break;
 	case V4L2_PIX_FMT_SGRBG16:	descr = "16-bit Bayer GRGR/BGBG"; break;
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index d8b33095abe0..2c20b6aa5335 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -609,6 +609,11 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_SGBRG12P v4l2_fourcc('p', 'G', 'C', 'C')
 #define V4L2_PIX_FMT_SGRBG12P v4l2_fourcc('p', 'g', 'C', 'C')
 #define V4L2_PIX_FMT_SRGGB12P v4l2_fourcc('p', 'R', 'C', 'C')
+	/* 14bit raw bayer packed, 7 bytes for every 4 pixels */
+#define V4L2_PIX_FMT_SBGGR14P v4l2_fourcc('p', 'B', 'E', 'E')
+#define V4L2_PIX_FMT_SGBRG14P v4l2_fourcc('p', 'G', 'E', 'E')
+#define V4L2_PIX_FMT_SGRBG14P v4l2_fourcc('p', 'g', 'E', 'E')
+#define V4L2_PIX_FMT_SRGGB14P v4l2_fourcc('p', 'R', 'E', 'E')
 #define V4L2_PIX_FMT_SBGGR16 v4l2_fourcc('B', 'Y', 'R', '2') /* 16  BGBG.. GRGR.. */
 #define V4L2_PIX_FMT_SGBRG16 v4l2_fourcc('G', 'B', '1', '6') /* 16  GBGB.. RGRG.. */
 #define V4L2_PIX_FMT_SGRBG16 v4l2_fourcc('G', 'R', '1', '6') /* 16  GRGR.. BGBG.. */
-- 
cgit v1.2.3


From 451af0bf04bd313bbaddd67a8be09d10210780bd Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:11 -0400
Subject: media: v4l: Add new 2X8 10-bit grayscale media bus code

The code will be called MEDIA_BUS_FMT_Y10_2X8_PADHI_LE.
It is similar to MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE
but MEDIA_BUS_FMT_Y10_2X8_PADHI_LE describes grayscale
data.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/subdev-formats.rst | 72 +++++++++++++++++++++++++
 include/uapi/linux/media-bus-format.h           |  3 +-
 2 files changed, 74 insertions(+), 1 deletion(-)

diff --git a/Documentation/media/uapi/v4l/subdev-formats.rst b/Documentation/media/uapi/v4l/subdev-formats.rst
index a4739f79d9c3..8e73fcfc6900 100644
--- a/Documentation/media/uapi/v4l/subdev-formats.rst
+++ b/Documentation/media/uapi/v4l/subdev-formats.rst
@@ -4318,6 +4318,78 @@ the following codes.
       - y\ :sub:`2`
       - y\ :sub:`1`
       - y\ :sub:`0`
+    * .. _MEDIA-BUS-FMT-Y10-2X8-PADHI_LE:
+
+      - MEDIA_BUS_FMT_Y10_2X8_PADHI_LE
+      - 0x202c
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      - y\ :sub:`7`
+      - y\ :sub:`6`
+      - y\ :sub:`5`
+      - y\ :sub:`4`
+      - y\ :sub:`3`
+      - y\ :sub:`2`
+      - y\ :sub:`1`
+      - y\ :sub:`0`
+    * -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      -
+      - 0
+      - 0
+      - 0
+      - 0
+      - 0
+      - 0
+      - y\ :sub:`9`
+      - y\ :sub:`8`
     * .. _MEDIA-BUS-FMT-UYVY10-2X10:
 
       - MEDIA_BUS_FMT_UYVY10_2X10
diff --git a/include/uapi/linux/media-bus-format.h b/include/uapi/linux/media-bus-format.h
index 9e3511742fdc..d6a5a3bfe6c4 100644
--- a/include/uapi/linux/media-bus-format.h
+++ b/include/uapi/linux/media-bus-format.h
@@ -62,7 +62,7 @@
 #define MEDIA_BUS_FMT_RGB121212_1X36		0x1019
 #define MEDIA_BUS_FMT_RGB161616_1X48		0x101a
 
-/* YUV (including grey) - next is	0x202c */
+/* YUV (including grey) - next is	0x202d */
 #define MEDIA_BUS_FMT_Y8_1X8			0x2001
 #define MEDIA_BUS_FMT_UV8_1X8			0x2015
 #define MEDIA_BUS_FMT_UYVY8_1_5X8		0x2002
@@ -74,6 +74,7 @@
 #define MEDIA_BUS_FMT_YUYV8_2X8			0x2008
 #define MEDIA_BUS_FMT_YVYU8_2X8			0x2009
 #define MEDIA_BUS_FMT_Y10_1X10			0x200a
+#define MEDIA_BUS_FMT_Y10_2X8_PADHI_LE		0x202c
 #define MEDIA_BUS_FMT_UYVY10_2X10		0x2018
 #define MEDIA_BUS_FMT_VYUY10_2X10		0x2019
 #define MEDIA_BUS_FMT_YUYV10_2X10		0x200b
-- 
cgit v1.2.3


From 6e15bec49f366511ec024a556505316222ef4ade Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:12 -0400
Subject: media: v4l: Add new 10-bit packed grayscale format

The new format will be called V4L2_PIX_FMT_Y10P.
It is similar to the V4L2_PIX_FMT_SBGGR10P family formats
but V4L2_PIX_FMT_Y10P is a grayscale format.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/uapi/v4l/pixfmt-y10p.rst | 33 ++++++++++++++++++++++++++++
 Documentation/media/uapi/v4l/yuv-formats.rst |  1 +
 drivers/media/v4l2-core/v4l2-ioctl.c         |  1 +
 include/uapi/linux/videodev2.h               |  1 +
 4 files changed, 36 insertions(+)
 create mode 100644 Documentation/media/uapi/v4l/pixfmt-y10p.rst

diff --git a/Documentation/media/uapi/v4l/pixfmt-y10p.rst b/Documentation/media/uapi/v4l/pixfmt-y10p.rst
new file mode 100644
index 000000000000..13b571306915
--- /dev/null
+++ b/Documentation/media/uapi/v4l/pixfmt-y10p.rst
@@ -0,0 +1,33 @@
+.. -*- coding: utf-8; mode: rst -*-
+
+.. _V4L2-PIX-FMT-Y10P:
+
+******************************
+V4L2_PIX_FMT_Y10P ('Y10P')
+******************************
+
+Grey-scale image as a MIPI RAW10 packed array
+
+
+Description
+===========
+
+This is a packed grey-scale image format with a depth of 10 bits per
+pixel. Every four consecutive pixels are packed into 5 bytes. Each of
+the first 4 bytes contain the 8 high order bits of the pixels, and
+the 5th byte contains the 2 least significants bits of each pixel,
+in the same order.
+
+**Bit-packed representation.**
+
+.. flat-table::
+    :header-rows:  0
+    :stub-columns: 0
+    :widths: 8 8 8 8 64
+
+    * - Y'\ :sub:`00[9:2]`
+      - Y'\ :sub:`01[9:2]`
+      - Y'\ :sub:`02[9:2]`
+      - Y'\ :sub:`03[9:2]`
+      - Y'\ :sub:`03[1:0]`\ (bits 7--6) Y'\ :sub:`02[1:0]`\ (bits 5--4)
+	Y'\ :sub:`01[1:0]`\ (bits 3--2) Y'\ :sub:`00[1:0]`\ (bits 1--0)
diff --git a/Documentation/media/uapi/v4l/yuv-formats.rst b/Documentation/media/uapi/v4l/yuv-formats.rst
index 3334ea445657..9ab0592d08da 100644
--- a/Documentation/media/uapi/v4l/yuv-formats.rst
+++ b/Documentation/media/uapi/v4l/yuv-formats.rst
@@ -29,6 +29,7 @@ to brightness information.
     pixfmt-y10
     pixfmt-y12
     pixfmt-y10b
+    pixfmt-y10p
     pixfmt-y16
     pixfmt-y16-be
     pixfmt-y8i
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index fd8d15f12307..54afc9c7ee6e 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -1184,6 +1184,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_Y16:		descr = "16-bit Greyscale"; break;
 	case V4L2_PIX_FMT_Y16_BE:	descr = "16-bit Greyscale BE"; break;
 	case V4L2_PIX_FMT_Y10BPACK:	descr = "10-bit Greyscale (Packed)"; break;
+	case V4L2_PIX_FMT_Y10P:		descr = "10-bit Greyscale (MIPI Packed)"; break;
 	case V4L2_PIX_FMT_Y8I:		descr = "Interleaved 8-bit Greyscale"; break;
 	case V4L2_PIX_FMT_Y12I:		descr = "Interleaved 12-bit Greyscale"; break;
 	case V4L2_PIX_FMT_Z16:		descr = "16-bit Depth"; break;
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 2c20b6aa5335..5d1a3685bea9 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -522,6 +522,7 @@ struct v4l2_pix_format {
 
 /* Grey bit-packed formats */
 #define V4L2_PIX_FMT_Y10BPACK    v4l2_fourcc('Y', '1', '0', 'B') /* 10  Greyscale bit-packed */
+#define V4L2_PIX_FMT_Y10P    v4l2_fourcc('Y', '1', '0', 'P') /* 10  Greyscale, MIPI RAW10 packed */
 
 /* Palette formats */
 #define V4L2_PIX_FMT_PAL8    v4l2_fourcc('P', 'A', 'L', '8') /*  8  8-bit palette */
-- 
cgit v1.2.3


From 07ebbbe458790d3c75f4a2f3634d8e04f66b389b Mon Sep 17 00:00:00 2001
From: Keiji Hayashibara <hayashibara.keiji@socionext.com>
Date: Thu, 2 Aug 2018 13:42:43 +0900
Subject: spi: uniphier: remove unnecessary include headers

This commit removed include headers of linux/of.h and linux/of_platform.h,
because they are not used.

Signed-off-by: Keiji Hayashibara <hayashibara.keiji@socionext.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-uniphier.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/spi/spi-uniphier.c b/drivers/spi/spi-uniphier.c
index 089985465890..5a6137fe172d 100644
--- a/drivers/spi/spi-uniphier.c
+++ b/drivers/spi/spi-uniphier.c
@@ -10,8 +10,6 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_platform.h>
 #include <linux/platform_device.h>
 #include <linux/spi/spi.h>
 
-- 
cgit v1.2.3


From ec6859b23f2212275fbd476df14d7a94839c2a35 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:13 -0400
Subject: media: Rename CAMSS driver path

Support for camera subsystem on QComm MSM8996/APQ8096 is to be added
so remove hardware version from CAMSS driver's path.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 MAINTAINERS                                        |    2 +-
 drivers/media/platform/Kconfig                     |    2 +-
 drivers/media/platform/Makefile                    |    2 +-
 drivers/media/platform/qcom/camss-8x16/Makefile    |   11 -
 .../media/platform/qcom/camss-8x16/camss-csid.c    | 1094 -------
 .../media/platform/qcom/camss-8x16/camss-csid.h    |   82 -
 .../media/platform/qcom/camss-8x16/camss-csiphy.c  |  893 ------
 .../media/platform/qcom/camss-8x16/camss-csiphy.h  |   77 -
 .../media/platform/qcom/camss-8x16/camss-ispif.c   | 1178 --------
 .../media/platform/qcom/camss-8x16/camss-ispif.h   |   85 -
 drivers/media/platform/qcom/camss-8x16/camss-vfe.c | 3093 --------------------
 drivers/media/platform/qcom/camss-8x16/camss-vfe.h |  123 -
 .../media/platform/qcom/camss-8x16/camss-video.c   |  859 ------
 .../media/platform/qcom/camss-8x16/camss-video.h   |   70 -
 drivers/media/platform/qcom/camss-8x16/camss.c     |  751 -----
 drivers/media/platform/qcom/camss-8x16/camss.h     |  106 -
 drivers/media/platform/qcom/camss/Makefile         |   11 +
 drivers/media/platform/qcom/camss/camss-csid.c     | 1094 +++++++
 drivers/media/platform/qcom/camss/camss-csid.h     |   82 +
 drivers/media/platform/qcom/camss/camss-csiphy.c   |  893 ++++++
 drivers/media/platform/qcom/camss/camss-csiphy.h   |   77 +
 drivers/media/platform/qcom/camss/camss-ispif.c    | 1178 ++++++++
 drivers/media/platform/qcom/camss/camss-ispif.h    |   85 +
 drivers/media/platform/qcom/camss/camss-vfe.c      | 3093 ++++++++++++++++++++
 drivers/media/platform/qcom/camss/camss-vfe.h      |  123 +
 drivers/media/platform/qcom/camss/camss-video.c    |  859 ++++++
 drivers/media/platform/qcom/camss/camss-video.h    |   70 +
 drivers/media/platform/qcom/camss/camss.c          |  751 +++++
 drivers/media/platform/qcom/camss/camss.h          |  106 +
 29 files changed, 8425 insertions(+), 8425 deletions(-)
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/Makefile
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-csid.c
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-csid.h
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-csiphy.c
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-csiphy.h
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-ispif.c
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-ispif.h
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-vfe.c
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-vfe.h
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-video.c
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss-video.h
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss.c
 delete mode 100644 drivers/media/platform/qcom/camss-8x16/camss.h
 create mode 100644 drivers/media/platform/qcom/camss/Makefile
 create mode 100644 drivers/media/platform/qcom/camss/camss-csid.c
 create mode 100644 drivers/media/platform/qcom/camss/camss-csid.h
 create mode 100644 drivers/media/platform/qcom/camss/camss-csiphy.c
 create mode 100644 drivers/media/platform/qcom/camss/camss-csiphy.h
 create mode 100644 drivers/media/platform/qcom/camss/camss-ispif.c
 create mode 100644 drivers/media/platform/qcom/camss/camss-ispif.h
 create mode 100644 drivers/media/platform/qcom/camss/camss-vfe.c
 create mode 100644 drivers/media/platform/qcom/camss/camss-vfe.h
 create mode 100644 drivers/media/platform/qcom/camss/camss-video.c
 create mode 100644 drivers/media/platform/qcom/camss/camss-video.h
 create mode 100644 drivers/media/platform/qcom/camss/camss.c
 create mode 100644 drivers/media/platform/qcom/camss/camss.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 3908908b1ec8..da68e6da9981 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11870,7 +11870,7 @@ L:	linux-media@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/media/qcom,camss.txt
 F:	Documentation/media/v4l-drivers/qcom_camss.rst
-F:	drivers/media/platform/qcom/camss-8x16/
+F:	drivers/media/platform/qcom/camss/
 
 QUALCOMM CPUFREQ DRIVER MSM8996/APQ8096
 M:  Ilia Lin <ilia.lin@gmail.com>
diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index 40bd3d96ca82..b25c8d3c1c31 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -90,7 +90,7 @@ config VIDEO_PXA27x
 	  This is a v4l2 driver for the PXA27x Quick Capture Interface
 
 config VIDEO_QCOM_CAMSS
-	tristate "Qualcomm 8x16 V4L2 Camera Subsystem driver"
+	tristate "Qualcomm V4L2 Camera Subsystem driver"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API
 	depends on (ARCH_QCOM && IOMMU_DMA) || COMPILE_TEST
 	select VIDEOBUF2_DMA_SG
diff --git a/drivers/media/platform/Makefile b/drivers/media/platform/Makefile
index 8e5f88eb7559..08640ba87fc2 100644
--- a/drivers/media/platform/Makefile
+++ b/drivers/media/platform/Makefile
@@ -89,7 +89,7 @@ obj-$(CONFIG_VIDEO_MEDIATEK_MDP)	+= mtk-mdp/
 
 obj-$(CONFIG_VIDEO_MEDIATEK_JPEG)	+= mtk-jpeg/
 
-obj-$(CONFIG_VIDEO_QCOM_CAMSS)		+= qcom/camss-8x16/
+obj-$(CONFIG_VIDEO_QCOM_CAMSS)		+= qcom/camss/
 
 obj-$(CONFIG_VIDEO_QCOM_VENUS)		+= qcom/venus/
 
diff --git a/drivers/media/platform/qcom/camss-8x16/Makefile b/drivers/media/platform/qcom/camss-8x16/Makefile
deleted file mode 100644
index 3c4024fbb768..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/Makefile
+++ /dev/null
@@ -1,11 +0,0 @@
-# Makefile for Qualcomm CAMSS driver
-
-qcom-camss-objs += \
-		camss.o \
-		camss-csid.o \
-		camss-csiphy.o \
-		camss-ispif.o \
-		camss-vfe.o \
-		camss-video.o \
-
-obj-$(CONFIG_VIDEO_QCOM_CAMSS) += qcom-camss.o
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csid.c b/drivers/media/platform/qcom/camss-8x16/camss-csid.c
deleted file mode 100644
index 226f36ef7419..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-csid.c
+++ /dev/null
@@ -1,1094 +0,0 @@
-/*
- * camss-csid.c
- *
- * Qualcomm MSM Camera Subsystem - CSID (CSI Decoder) Module
- *
- * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/clk.h>
-#include <linux/completion.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/regulator/consumer.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-
-#include "camss-csid.h"
-#include "camss.h"
-
-#define MSM_CSID_NAME "msm_csid"
-
-#define CAMSS_CSID_HW_VERSION		0x0
-#define CAMSS_CSID_CORE_CTRL_0		0x004
-#define CAMSS_CSID_CORE_CTRL_1		0x008
-#define CAMSS_CSID_RST_CMD		0x00c
-#define CAMSS_CSID_CID_LUT_VC_n(n)	(0x010 + 0x4 * (n))
-#define CAMSS_CSID_CID_n_CFG(n)		(0x020 + 0x4 * (n))
-#define CAMSS_CSID_IRQ_CLEAR_CMD	0x060
-#define CAMSS_CSID_IRQ_MASK		0x064
-#define CAMSS_CSID_IRQ_STATUS		0x068
-#define CAMSS_CSID_TG_CTRL		0x0a0
-#define CAMSS_CSID_TG_CTRL_DISABLE	0xa06436
-#define CAMSS_CSID_TG_CTRL_ENABLE	0xa06437
-#define CAMSS_CSID_TG_VC_CFG		0x0a4
-#define CAMSS_CSID_TG_VC_CFG_H_BLANKING		0x3ff
-#define CAMSS_CSID_TG_VC_CFG_V_BLANKING		0x7f
-#define CAMSS_CSID_TG_DT_n_CGG_0(n)	(0x0ac + 0xc * (n))
-#define CAMSS_CSID_TG_DT_n_CGG_1(n)	(0x0b0 + 0xc * (n))
-#define CAMSS_CSID_TG_DT_n_CGG_2(n)	(0x0b4 + 0xc * (n))
-
-#define DATA_TYPE_EMBEDDED_DATA_8BIT	0x12
-#define DATA_TYPE_YUV422_8BIT		0x1e
-#define DATA_TYPE_RAW_6BIT		0x28
-#define DATA_TYPE_RAW_8BIT		0x2a
-#define DATA_TYPE_RAW_10BIT		0x2b
-#define DATA_TYPE_RAW_12BIT		0x2c
-
-#define DECODE_FORMAT_UNCOMPRESSED_6_BIT	0x0
-#define DECODE_FORMAT_UNCOMPRESSED_8_BIT	0x1
-#define DECODE_FORMAT_UNCOMPRESSED_10_BIT	0x2
-#define DECODE_FORMAT_UNCOMPRESSED_12_BIT	0x3
-
-#define CSID_RESET_TIMEOUT_MS 500
-
-struct csid_fmts {
-	u32 code;
-	u8 data_type;
-	u8 decode_format;
-	u8 bpp;
-	u8 spp; /* bus samples per pixel */
-};
-
-static const struct csid_fmts csid_input_fmts[] = {
-	{
-		MEDIA_BUS_FMT_UYVY8_2X8,
-		DATA_TYPE_YUV422_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		2,
-	},
-	{
-		MEDIA_BUS_FMT_VYUY8_2X8,
-		DATA_TYPE_YUV422_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		2,
-	},
-	{
-		MEDIA_BUS_FMT_YUYV8_2X8,
-		DATA_TYPE_YUV422_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		2,
-	},
-	{
-		MEDIA_BUS_FMT_YVYU8_2X8,
-		DATA_TYPE_YUV422_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		2,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR8_1X8,
-		DATA_TYPE_RAW_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG8_1X8,
-		DATA_TYPE_RAW_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG8_1X8,
-		DATA_TYPE_RAW_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB8_1X8,
-		DATA_TYPE_RAW_8BIT,
-		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
-		8,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR10_1X10,
-		DATA_TYPE_RAW_10BIT,
-		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
-		10,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG10_1X10,
-		DATA_TYPE_RAW_10BIT,
-		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
-		10,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG10_1X10,
-		DATA_TYPE_RAW_10BIT,
-		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
-		10,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB10_1X10,
-		DATA_TYPE_RAW_10BIT,
-		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
-		10,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR12_1X12,
-		DATA_TYPE_RAW_12BIT,
-		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
-		12,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG12_1X12,
-		DATA_TYPE_RAW_12BIT,
-		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
-		12,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG12_1X12,
-		DATA_TYPE_RAW_12BIT,
-		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
-		12,
-		1,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB12_1X12,
-		DATA_TYPE_RAW_12BIT,
-		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
-		12,
-		1,
-	}
-};
-
-static const struct csid_fmts *csid_get_fmt_entry(u32 code)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-		if (code == csid_input_fmts[i].code)
-			return &csid_input_fmts[i];
-
-	WARN(1, "Unknown format\n");
-
-	return &csid_input_fmts[0];
-}
-
-/*
- * csid_isr - CSID module interrupt handler
- * @irq: Interrupt line
- * @dev: CSID device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t csid_isr(int irq, void *dev)
-{
-	struct csid_device *csid = dev;
-	u32 value;
-
-	value = readl_relaxed(csid->base + CAMSS_CSID_IRQ_STATUS);
-	writel_relaxed(value, csid->base + CAMSS_CSID_IRQ_CLEAR_CMD);
-
-	if ((value >> 11) & 0x1)
-		complete(&csid->reset_complete);
-
-	return IRQ_HANDLED;
-}
-
-/*
- * csid_set_clock_rates - Calculate and set clock rates on CSID module
- * @csiphy: CSID device
- */
-static int csid_set_clock_rates(struct csid_device *csid)
-{
-	struct device *dev = to_device_index(csid, csid->id);
-	u32 pixel_clock;
-	int i, j;
-	int ret;
-
-	ret = camss_get_pixel_clock(&csid->subdev.entity, &pixel_clock);
-	if (ret)
-		pixel_clock = 0;
-
-	for (i = 0; i < csid->nclocks; i++) {
-		struct camss_clock *clock = &csid->clock[i];
-
-		if (!strcmp(clock->name, "csi0") ||
-			!strcmp(clock->name, "csi1")) {
-			u8 bpp = csid_get_fmt_entry(
-				csid->fmt[MSM_CSIPHY_PAD_SINK].code)->bpp;
-			u8 num_lanes = csid->phy.lane_cnt;
-			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
-			long rate;
-
-			camss_add_clock_margin(&min_rate);
-
-			for (j = 0; j < clock->nfreqs; j++)
-				if (min_rate < clock->freq[j])
-					break;
-
-			if (j == clock->nfreqs) {
-				dev_err(dev,
-					"Pixel clock is too high for CSID\n");
-				return -EINVAL;
-			}
-
-			/* if sensor pixel clock is not available */
-			/* set highest possible CSID clock rate */
-			if (min_rate == 0)
-				j = clock->nfreqs - 1;
-
-			rate = clk_round_rate(clock->clk, clock->freq[j]);
-			if (rate < 0) {
-				dev_err(dev, "clk round rate failed: %ld\n",
-					rate);
-				return -EINVAL;
-			}
-
-			ret = clk_set_rate(clock->clk, rate);
-			if (ret < 0) {
-				dev_err(dev, "clk set rate failed: %d\n", ret);
-				return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
-/*
- * csid_reset - Trigger reset on CSID module and wait to complete
- * @csid: CSID device
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csid_reset(struct csid_device *csid)
-{
-	unsigned long time;
-
-	reinit_completion(&csid->reset_complete);
-
-	writel_relaxed(0x7fff, csid->base + CAMSS_CSID_RST_CMD);
-
-	time = wait_for_completion_timeout(&csid->reset_complete,
-		msecs_to_jiffies(CSID_RESET_TIMEOUT_MS));
-	if (!time) {
-		dev_err(to_device_index(csid, csid->id),
-			"CSID reset timeout\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/*
- * csid_set_power - Power on/off CSID module
- * @sd: CSID V4L2 subdevice
- * @on: Requested power state
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csid_set_power(struct v4l2_subdev *sd, int on)
-{
-	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct device *dev = to_device_index(csid, csid->id);
-	int ret;
-
-	if (on) {
-		u32 hw_version;
-
-		ret = regulator_enable(csid->vdda);
-		if (ret < 0)
-			return ret;
-
-		ret = csid_set_clock_rates(csid);
-		if (ret < 0) {
-			regulator_disable(csid->vdda);
-			return ret;
-		}
-
-		ret = camss_enable_clocks(csid->nclocks, csid->clock, dev);
-		if (ret < 0) {
-			regulator_disable(csid->vdda);
-			return ret;
-		}
-
-		enable_irq(csid->irq);
-
-		ret = csid_reset(csid);
-		if (ret < 0) {
-			disable_irq(csid->irq);
-			camss_disable_clocks(csid->nclocks, csid->clock);
-			regulator_disable(csid->vdda);
-			return ret;
-		}
-
-		hw_version = readl_relaxed(csid->base + CAMSS_CSID_HW_VERSION);
-		dev_dbg(dev, "CSID HW Version = 0x%08x\n", hw_version);
-	} else {
-		disable_irq(csid->irq);
-		camss_disable_clocks(csid->nclocks, csid->clock);
-		ret = regulator_disable(csid->vdda);
-	}
-
-	return ret;
-}
-
-/*
- * csid_set_stream - Enable/disable streaming on CSID module
- * @sd: CSID V4L2 subdevice
- * @enable: Requested streaming state
- *
- * Main configuration of CSID module is also done here.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csid_set_stream(struct v4l2_subdev *sd, int enable)
-{
-	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct csid_testgen_config *tg = &csid->testgen;
-	u32 val;
-
-	if (enable) {
-		u8 vc = 0; /* Virtual Channel 0 */
-		u8 cid = vc * 4; /* id of Virtual Channel and Data Type set */
-		u8 dt, dt_shift, df;
-		int ret;
-
-		ret = v4l2_ctrl_handler_setup(&csid->ctrls);
-		if (ret < 0) {
-			dev_err(to_device_index(csid, csid->id),
-				"could not sync v4l2 controls: %d\n", ret);
-			return ret;
-		}
-
-		if (!tg->enabled &&
-		    !media_entity_remote_pad(&csid->pads[MSM_CSID_PAD_SINK]))
-			return -ENOLINK;
-
-		dt = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SRC].code)->
-								data_type;
-
-		if (tg->enabled) {
-			/* Config Test Generator */
-			struct v4l2_mbus_framefmt *f =
-					&csid->fmt[MSM_CSID_PAD_SRC];
-			u8 bpp = csid_get_fmt_entry(f->code)->bpp;
-			u8 spp = csid_get_fmt_entry(f->code)->spp;
-			u32 num_bytes_per_line = f->width * bpp * spp / 8;
-			u32 num_lines = f->height;
-
-			/* 31:24 V blank, 23:13 H blank, 3:2 num of active DT */
-			/* 1:0 VC */
-			val = ((CAMSS_CSID_TG_VC_CFG_V_BLANKING & 0xff) << 24) |
-			      ((CAMSS_CSID_TG_VC_CFG_H_BLANKING & 0x7ff) << 13);
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_VC_CFG);
-
-			/* 28:16 bytes per lines, 12:0 num of lines */
-			val = ((num_bytes_per_line & 0x1fff) << 16) |
-			      (num_lines & 0x1fff);
-			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_0(0));
-
-			/* 5:0 data type */
-			val = dt;
-			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_1(0));
-
-			/* 2:0 output test pattern */
-			val = tg->payload_mode;
-			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_2(0));
-		} else {
-			struct csid_phy_config *phy = &csid->phy;
-
-			val = phy->lane_cnt - 1;
-			val |= phy->lane_assign << 4;
-
-			writel_relaxed(val,
-				       csid->base + CAMSS_CSID_CORE_CTRL_0);
-
-			val = phy->csiphy_id << 17;
-			val |= 0x9;
-
-			writel_relaxed(val,
-				       csid->base + CAMSS_CSID_CORE_CTRL_1);
-		}
-
-		/* Config LUT */
-
-		dt_shift = (cid % 4) * 8;
-		df = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SINK].code)->
-								decode_format;
-
-		val = readl_relaxed(csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
-		val &= ~(0xff << dt_shift);
-		val |= dt << dt_shift;
-		writel_relaxed(val, csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
-
-		val = (df << 4) | 0x3;
-		writel_relaxed(val, csid->base + CAMSS_CSID_CID_n_CFG(cid));
-
-		if (tg->enabled) {
-			val = CAMSS_CSID_TG_CTRL_ENABLE;
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
-		}
-	} else {
-		if (tg->enabled) {
-			val = CAMSS_CSID_TG_CTRL_DISABLE;
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
-		}
-	}
-
-	return 0;
-}
-
-/*
- * __csid_get_format - Get pointer to format structure
- * @csid: CSID device
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad from which format is requested
- * @which: TRY or ACTIVE format
- *
- * Return pointer to TRY or ACTIVE format structure
- */
-static struct v4l2_mbus_framefmt *
-__csid_get_format(struct csid_device *csid,
-		  struct v4l2_subdev_pad_config *cfg,
-		  unsigned int pad,
-		  enum v4l2_subdev_format_whence which)
-{
-	if (which == V4L2_SUBDEV_FORMAT_TRY)
-		return v4l2_subdev_get_try_format(&csid->subdev, cfg, pad);
-
-	return &csid->fmt[pad];
-}
-
-/*
- * csid_try_format - Handle try format by pad subdev method
- * @csid: CSID device
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad on which format is requested
- * @fmt: pointer to v4l2 format structure
- * @which: wanted subdev format
- */
-static void csid_try_format(struct csid_device *csid,
-			    struct v4l2_subdev_pad_config *cfg,
-			    unsigned int pad,
-			    struct v4l2_mbus_framefmt *fmt,
-			    enum v4l2_subdev_format_whence which)
-{
-	unsigned int i;
-
-	switch (pad) {
-	case MSM_CSID_PAD_SINK:
-		/* Set format on sink pad */
-
-		for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-			if (fmt->code == csid_input_fmts[i].code)
-				break;
-
-		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(csid_input_fmts))
-			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-
-		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
-		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
-
-		fmt->field = V4L2_FIELD_NONE;
-		fmt->colorspace = V4L2_COLORSPACE_SRGB;
-
-		break;
-
-	case MSM_CSID_PAD_SRC:
-		if (csid->testgen_mode->cur.val == 0) {
-			/* Test generator is disabled, keep pad formats */
-			/* in sync - set and return a format same as sink pad */
-			struct v4l2_mbus_framefmt format;
-
-			format = *__csid_get_format(csid, cfg,
-						    MSM_CSID_PAD_SINK, which);
-			*fmt = format;
-		} else {
-			/* Test generator is enabled, set format on source*/
-			/* pad to allow test generator usage */
-
-			for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-				if (csid_input_fmts[i].code == fmt->code)
-					break;
-
-			/* If not found, use UYVY as default */
-			if (i >= ARRAY_SIZE(csid_input_fmts))
-				fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-
-			fmt->width = clamp_t(u32, fmt->width, 1, 8191);
-			fmt->height = clamp_t(u32, fmt->height, 1, 8191);
-
-			fmt->field = V4L2_FIELD_NONE;
-		}
-		break;
-	}
-
-	fmt->colorspace = V4L2_COLORSPACE_SRGB;
-}
-
-/*
- * csid_enum_mbus_code - Handle pixel format enumeration
- * @sd: CSID V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @code: pointer to v4l2_subdev_mbus_code_enum structure
- * return -EINVAL or zero on success
- */
-static int csid_enum_mbus_code(struct v4l2_subdev *sd,
-			       struct v4l2_subdev_pad_config *cfg,
-			       struct v4l2_subdev_mbus_code_enum *code)
-{
-	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	if (code->pad == MSM_CSID_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(csid_input_fmts))
-			return -EINVAL;
-
-		code->code = csid_input_fmts[code->index].code;
-	} else {
-		if (csid->testgen_mode->cur.val == 0) {
-			if (code->index > 0)
-				return -EINVAL;
-
-			format = __csid_get_format(csid, cfg, MSM_CSID_PAD_SINK,
-						   code->which);
-
-			code->code = format->code;
-		} else {
-			if (code->index >= ARRAY_SIZE(csid_input_fmts))
-				return -EINVAL;
-
-			code->code = csid_input_fmts[code->index].code;
-		}
-	}
-
-	return 0;
-}
-
-/*
- * csid_enum_frame_size - Handle frame size enumeration
- * @sd: CSID V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fse: pointer to v4l2_subdev_frame_size_enum structure
- * return -EINVAL or zero on success
- */
-static int csid_enum_frame_size(struct v4l2_subdev *sd,
-				struct v4l2_subdev_pad_config *cfg,
-				struct v4l2_subdev_frame_size_enum *fse)
-{
-	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt format;
-
-	if (fse->index != 0)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = 1;
-	format.height = 1;
-	csid_try_format(csid, cfg, fse->pad, &format, fse->which);
-	fse->min_width = format.width;
-	fse->min_height = format.height;
-
-	if (format.code != fse->code)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = -1;
-	format.height = -1;
-	csid_try_format(csid, cfg, fse->pad, &format, fse->which);
-	fse->max_width = format.width;
-	fse->max_height = format.height;
-
-	return 0;
-}
-
-/*
- * csid_get_format - Handle get format by pads subdev method
- * @sd: CSID V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int csid_get_format(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_pad_config *cfg,
-			   struct v4l2_subdev_format *fmt)
-{
-	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __csid_get_format(csid, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	fmt->format = *format;
-
-	return 0;
-}
-
-/*
- * csid_set_format - Handle set format by pads subdev method
- * @sd: CSID V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int csid_set_format(struct v4l2_subdev *sd,
-			   struct v4l2_subdev_pad_config *cfg,
-			   struct v4l2_subdev_format *fmt)
-{
-	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __csid_get_format(csid, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	csid_try_format(csid, cfg, fmt->pad, &fmt->format, fmt->which);
-	*format = fmt->format;
-
-	/* Propagate the format from sink to source */
-	if (fmt->pad == MSM_CSID_PAD_SINK) {
-		format = __csid_get_format(csid, cfg, MSM_CSID_PAD_SRC,
-					   fmt->which);
-
-		*format = fmt->format;
-		csid_try_format(csid, cfg, MSM_CSID_PAD_SRC, format,
-				fmt->which);
-	}
-
-	return 0;
-}
-
-/*
- * csid_init_formats - Initialize formats on all pads
- * @sd: CSID V4L2 subdevice
- * @fh: V4L2 subdev file handle
- *
- * Initialize all pad formats with default values.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csid_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
-{
-	struct v4l2_subdev_format format = {
-		.pad = MSM_CSID_PAD_SINK,
-		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
-			      V4L2_SUBDEV_FORMAT_ACTIVE,
-		.format = {
-			.code = MEDIA_BUS_FMT_UYVY8_2X8,
-			.width = 1920,
-			.height = 1080
-		}
-	};
-
-	return csid_set_format(sd, fh ? fh->pad : NULL, &format);
-}
-
-static const char * const csid_test_pattern_menu[] = {
-	"Disabled",
-	"Incrementing",
-	"Alternating 0x55/0xAA",
-	"All Zeros 0x00",
-	"All Ones 0xFF",
-	"Pseudo-random Data",
-};
-
-/*
- * csid_set_test_pattern - Set test generator's pattern mode
- * @csid: CSID device
- * @value: desired test pattern mode
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csid_set_test_pattern(struct csid_device *csid, s32 value)
-{
-	struct csid_testgen_config *tg = &csid->testgen;
-
-	/* If CSID is linked to CSIPHY, do not allow to enable test generator */
-	if (value && media_entity_remote_pad(&csid->pads[MSM_CSID_PAD_SINK]))
-		return -EBUSY;
-
-	tg->enabled = !!value;
-
-	switch (value) {
-	case 1:
-		tg->payload_mode = CSID_PAYLOAD_MODE_INCREMENTING;
-		break;
-	case 2:
-		tg->payload_mode = CSID_PAYLOAD_MODE_ALTERNATING_55_AA;
-		break;
-	case 3:
-		tg->payload_mode = CSID_PAYLOAD_MODE_ALL_ZEROES;
-		break;
-	case 4:
-		tg->payload_mode = CSID_PAYLOAD_MODE_ALL_ONES;
-		break;
-	case 5:
-		tg->payload_mode = CSID_PAYLOAD_MODE_RANDOM;
-		break;
-	}
-
-	return 0;
-}
-
-/*
- * csid_s_ctrl - Handle set control subdev method
- * @ctrl: pointer to v4l2 control structure
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csid_s_ctrl(struct v4l2_ctrl *ctrl)
-{
-	struct csid_device *csid = container_of(ctrl->handler,
-						struct csid_device, ctrls);
-	int ret = -EINVAL;
-
-	switch (ctrl->id) {
-	case V4L2_CID_TEST_PATTERN:
-		ret = csid_set_test_pattern(csid, ctrl->val);
-		break;
-	}
-
-	return ret;
-}
-
-static const struct v4l2_ctrl_ops csid_ctrl_ops = {
-	.s_ctrl = csid_s_ctrl,
-};
-
-/*
- * msm_csid_subdev_init - Initialize CSID device structure and resources
- * @csid: CSID device
- * @res: CSID module resources table
- * @id: CSID module id
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_csid_subdev_init(struct csid_device *csid,
-			 const struct resources *res, u8 id)
-{
-	struct device *dev = to_device_index(csid, id);
-	struct platform_device *pdev = to_platform_device(dev);
-	struct resource *r;
-	int i, j;
-	int ret;
-
-	csid->id = id;
-
-	/* Memory */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
-	csid->base = devm_ioremap_resource(dev, r);
-	if (IS_ERR(csid->base)) {
-		dev_err(dev, "could not map memory\n");
-		return PTR_ERR(csid->base);
-	}
-
-	/* Interrupt */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ,
-					 res->interrupt[0]);
-	if (!r) {
-		dev_err(dev, "missing IRQ\n");
-		return -EINVAL;
-	}
-
-	csid->irq = r->start;
-	snprintf(csid->irq_name, sizeof(csid->irq_name), "%s_%s%d",
-		 dev_name(dev), MSM_CSID_NAME, csid->id);
-	ret = devm_request_irq(dev, csid->irq, csid_isr,
-		IRQF_TRIGGER_RISING, csid->irq_name, csid);
-	if (ret < 0) {
-		dev_err(dev, "request_irq failed: %d\n", ret);
-		return ret;
-	}
-
-	disable_irq(csid->irq);
-
-	/* Clocks */
-
-	csid->nclocks = 0;
-	while (res->clock[csid->nclocks])
-		csid->nclocks++;
-
-	csid->clock = devm_kcalloc(dev, csid->nclocks, sizeof(*csid->clock),
-				    GFP_KERNEL);
-	if (!csid->clock)
-		return -ENOMEM;
-
-	for (i = 0; i < csid->nclocks; i++) {
-		struct camss_clock *clock = &csid->clock[i];
-
-		clock->clk = devm_clk_get(dev, res->clock[i]);
-		if (IS_ERR(clock->clk))
-			return PTR_ERR(clock->clk);
-
-		clock->name = res->clock[i];
-
-		clock->nfreqs = 0;
-		while (res->clock_rate[i][clock->nfreqs])
-			clock->nfreqs++;
-
-		if (!clock->nfreqs) {
-			clock->freq = NULL;
-			continue;
-		}
-
-		clock->freq = devm_kcalloc(dev,
-					   clock->nfreqs,
-					   sizeof(*clock->freq),
-					   GFP_KERNEL);
-		if (!clock->freq)
-			return -ENOMEM;
-
-		for (j = 0; j < clock->nfreqs; j++)
-			clock->freq[j] = res->clock_rate[i][j];
-	}
-
-	/* Regulator */
-
-	csid->vdda = devm_regulator_get(dev, res->regulator[0]);
-	if (IS_ERR(csid->vdda)) {
-		dev_err(dev, "could not get regulator\n");
-		return PTR_ERR(csid->vdda);
-	}
-
-	init_completion(&csid->reset_complete);
-
-	return 0;
-}
-
-/*
- * msm_csid_get_csid_id - Get CSID HW module id
- * @entity: Pointer to CSID media entity structure
- * @id: Return CSID HW module id here
- */
-void msm_csid_get_csid_id(struct media_entity *entity, u8 *id)
-{
-	struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(entity);
-	struct csid_device *csid = v4l2_get_subdevdata(sd);
-
-	*id = csid->id;
-}
-
-/*
- * csid_get_lane_assign - Calculate CSI2 lane assign configuration parameter
- * @lane_cfg - CSI2 lane configuration
- *
- * Return lane assign
- */
-static u32 csid_get_lane_assign(struct csiphy_lanes_cfg *lane_cfg)
-{
-	u32 lane_assign = 0;
-	int i;
-
-	for (i = 0; i < lane_cfg->num_data; i++)
-		lane_assign |= lane_cfg->data[i].pos << (i * 4);
-
-	return lane_assign;
-}
-
-/*
- * csid_link_setup - Setup CSID connections
- * @entity: Pointer to media entity structure
- * @local: Pointer to local pad
- * @remote: Pointer to remote pad
- * @flags: Link flags
- *
- * Return 0 on success
- */
-static int csid_link_setup(struct media_entity *entity,
-			   const struct media_pad *local,
-			   const struct media_pad *remote, u32 flags)
-{
-	if (flags & MEDIA_LNK_FL_ENABLED)
-		if (media_entity_remote_pad(local))
-			return -EBUSY;
-
-	if ((local->flags & MEDIA_PAD_FL_SINK) &&
-	    (flags & MEDIA_LNK_FL_ENABLED)) {
-		struct v4l2_subdev *sd;
-		struct csid_device *csid;
-		struct csiphy_device *csiphy;
-		struct csiphy_lanes_cfg *lane_cfg;
-		struct v4l2_subdev_format format = { 0 };
-
-		sd = media_entity_to_v4l2_subdev(entity);
-		csid = v4l2_get_subdevdata(sd);
-
-		/* If test generator is enabled */
-		/* do not allow a link from CSIPHY to CSID */
-		if (csid->testgen_mode->cur.val != 0)
-			return -EBUSY;
-
-		sd = media_entity_to_v4l2_subdev(remote->entity);
-		csiphy = v4l2_get_subdevdata(sd);
-
-		/* If a sensor is not linked to CSIPHY */
-		/* do no allow a link from CSIPHY to CSID */
-		if (!csiphy->cfg.csi2)
-			return -EPERM;
-
-		csid->phy.csiphy_id = csiphy->id;
-
-		lane_cfg = &csiphy->cfg.csi2->lane_cfg;
-		csid->phy.lane_cnt = lane_cfg->num_data;
-		csid->phy.lane_assign = csid_get_lane_assign(lane_cfg);
-
-		/* Reset format on source pad to sink pad format */
-		format.pad = MSM_CSID_PAD_SRC;
-		format.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-		csid_set_format(&csid->subdev, NULL, &format);
-	}
-
-	return 0;
-}
-
-static const struct v4l2_subdev_core_ops csid_core_ops = {
-	.s_power = csid_set_power,
-};
-
-static const struct v4l2_subdev_video_ops csid_video_ops = {
-	.s_stream = csid_set_stream,
-};
-
-static const struct v4l2_subdev_pad_ops csid_pad_ops = {
-	.enum_mbus_code = csid_enum_mbus_code,
-	.enum_frame_size = csid_enum_frame_size,
-	.get_fmt = csid_get_format,
-	.set_fmt = csid_set_format,
-};
-
-static const struct v4l2_subdev_ops csid_v4l2_ops = {
-	.core = &csid_core_ops,
-	.video = &csid_video_ops,
-	.pad = &csid_pad_ops,
-};
-
-static const struct v4l2_subdev_internal_ops csid_v4l2_internal_ops = {
-	.open = csid_init_formats,
-};
-
-static const struct media_entity_operations csid_media_ops = {
-	.link_setup = csid_link_setup,
-	.link_validate = v4l2_subdev_link_validate,
-};
-
-/*
- * msm_csid_register_entity - Register subdev node for CSID module
- * @csid: CSID device
- * @v4l2_dev: V4L2 device
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_csid_register_entity(struct csid_device *csid,
-			     struct v4l2_device *v4l2_dev)
-{
-	struct v4l2_subdev *sd = &csid->subdev;
-	struct media_pad *pads = csid->pads;
-	struct device *dev = to_device_index(csid, csid->id);
-	int ret;
-
-	v4l2_subdev_init(sd, &csid_v4l2_ops);
-	sd->internal_ops = &csid_v4l2_internal_ops;
-	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-	snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
-		 MSM_CSID_NAME, csid->id);
-	v4l2_set_subdevdata(sd, csid);
-
-	ret = v4l2_ctrl_handler_init(&csid->ctrls, 1);
-	if (ret < 0) {
-		dev_err(dev, "Failed to init ctrl handler: %d\n", ret);
-		return ret;
-	}
-
-	csid->testgen_mode = v4l2_ctrl_new_std_menu_items(&csid->ctrls,
-				&csid_ctrl_ops, V4L2_CID_TEST_PATTERN,
-				ARRAY_SIZE(csid_test_pattern_menu) - 1, 0, 0,
-				csid_test_pattern_menu);
-
-	if (csid->ctrls.error) {
-		dev_err(dev, "Failed to init ctrl: %d\n", csid->ctrls.error);
-		ret = csid->ctrls.error;
-		goto free_ctrl;
-	}
-
-	csid->subdev.ctrl_handler = &csid->ctrls;
-
-	ret = csid_init_formats(sd, NULL);
-	if (ret < 0) {
-		dev_err(dev, "Failed to init format: %d\n", ret);
-		goto free_ctrl;
-	}
-
-	pads[MSM_CSID_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
-	pads[MSM_CSID_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
-
-	sd->entity.function = MEDIA_ENT_F_IO_V4L;
-	sd->entity.ops = &csid_media_ops;
-	ret = media_entity_pads_init(&sd->entity, MSM_CSID_PADS_NUM, pads);
-	if (ret < 0) {
-		dev_err(dev, "Failed to init media entity: %d\n", ret);
-		goto free_ctrl;
-	}
-
-	ret = v4l2_device_register_subdev(v4l2_dev, sd);
-	if (ret < 0) {
-		dev_err(dev, "Failed to register subdev: %d\n", ret);
-		goto media_cleanup;
-	}
-
-	return 0;
-
-media_cleanup:
-	media_entity_cleanup(&sd->entity);
-free_ctrl:
-	v4l2_ctrl_handler_free(&csid->ctrls);
-
-	return ret;
-}
-
-/*
- * msm_csid_unregister_entity - Unregister CSID module subdev node
- * @csid: CSID device
- */
-void msm_csid_unregister_entity(struct csid_device *csid)
-{
-	v4l2_device_unregister_subdev(&csid->subdev);
-	media_entity_cleanup(&csid->subdev.entity);
-	v4l2_ctrl_handler_free(&csid->ctrls);
-}
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csid.h b/drivers/media/platform/qcom/camss-8x16/camss-csid.h
deleted file mode 100644
index 8682d3081bc3..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-csid.h
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- * camss-csid.h
- *
- * Qualcomm MSM Camera Subsystem - CSID (CSI Decoder) Module
- *
- * Copyright (c) 2011-2014, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef QC_MSM_CAMSS_CSID_H
-#define QC_MSM_CAMSS_CSID_H
-
-#include <linux/clk.h>
-#include <media/media-entity.h>
-#include <media/v4l2-ctrls.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-mediabus.h>
-#include <media/v4l2-subdev.h>
-
-#define MSM_CSID_PAD_SINK 0
-#define MSM_CSID_PAD_SRC 1
-#define MSM_CSID_PADS_NUM 2
-
-enum csid_payload_mode {
-	CSID_PAYLOAD_MODE_INCREMENTING = 0,
-	CSID_PAYLOAD_MODE_ALTERNATING_55_AA = 1,
-	CSID_PAYLOAD_MODE_ALL_ZEROES = 2,
-	CSID_PAYLOAD_MODE_ALL_ONES = 3,
-	CSID_PAYLOAD_MODE_RANDOM = 4,
-	CSID_PAYLOAD_MODE_USER_SPECIFIED = 5,
-};
-
-struct csid_testgen_config {
-	u8 enabled;
-	enum csid_payload_mode payload_mode;
-};
-
-struct csid_phy_config {
-	u8 csiphy_id;
-	u8 lane_cnt;
-	u32 lane_assign;
-};
-
-struct csid_device {
-	u8 id;
-	struct v4l2_subdev subdev;
-	struct media_pad pads[MSM_CSID_PADS_NUM];
-	void __iomem *base;
-	u32 irq;
-	char irq_name[30];
-	struct camss_clock *clock;
-	int nclocks;
-	struct regulator *vdda;
-	struct completion reset_complete;
-	struct csid_testgen_config testgen;
-	struct csid_phy_config phy;
-	struct v4l2_mbus_framefmt fmt[MSM_CSID_PADS_NUM];
-	struct v4l2_ctrl_handler ctrls;
-	struct v4l2_ctrl *testgen_mode;
-};
-
-struct resources;
-
-int msm_csid_subdev_init(struct csid_device *csid,
-			 const struct resources *res, u8 id);
-
-int msm_csid_register_entity(struct csid_device *csid,
-			     struct v4l2_device *v4l2_dev);
-
-void msm_csid_unregister_entity(struct csid_device *csid);
-
-void msm_csid_get_csid_id(struct media_entity *entity, u8 *id);
-
-#endif /* QC_MSM_CAMSS_CSID_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.c b/drivers/media/platform/qcom/camss-8x16/camss-csiphy.c
deleted file mode 100644
index 7e61caba6a2d..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.c
+++ /dev/null
@@ -1,893 +0,0 @@
-/*
- * camss-csiphy.c
- *
- * Qualcomm MSM Camera Subsystem - CSIPHY Module
- *
- * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2016-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/clk.h>
-#include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-
-#include "camss-csiphy.h"
-#include "camss.h"
-
-#define MSM_CSIPHY_NAME "msm_csiphy"
-
-#define CAMSS_CSI_PHY_LNn_CFG2(n)		(0x004 + 0x40 * (n))
-#define CAMSS_CSI_PHY_LNn_CFG3(n)		(0x008 + 0x40 * (n))
-#define CAMSS_CSI_PHY_GLBL_RESET		0x140
-#define CAMSS_CSI_PHY_GLBL_PWR_CFG		0x144
-#define CAMSS_CSI_PHY_GLBL_IRQ_CMD		0x164
-#define CAMSS_CSI_PHY_HW_VERSION		0x188
-#define CAMSS_CSI_PHY_INTERRUPT_STATUSn(n)	(0x18c + 0x4 * (n))
-#define CAMSS_CSI_PHY_INTERRUPT_MASKn(n)	(0x1ac + 0x4 * (n))
-#define CAMSS_CSI_PHY_INTERRUPT_CLEARn(n)	(0x1cc + 0x4 * (n))
-#define CAMSS_CSI_PHY_GLBL_T_INIT_CFG0		0x1ec
-#define CAMSS_CSI_PHY_T_WAKEUP_CFG0		0x1f4
-
-static const struct {
-	u32 code;
-	u8 bpp;
-} csiphy_formats[] = {
-	{
-		MEDIA_BUS_FMT_UYVY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_VYUY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YUYV8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YVYU8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB12_1X12,
-		12,
-	}
-};
-
-/*
- * csiphy_get_bpp - map media bus format to bits per pixel
- * @code: media bus format code
- *
- * Return number of bits per pixel
- */
-static u8 csiphy_get_bpp(u32 code)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
-		if (code == csiphy_formats[i].code)
-			return csiphy_formats[i].bpp;
-
-	WARN(1, "Unknown format\n");
-
-	return csiphy_formats[0].bpp;
-}
-
-/*
- * csiphy_isr - CSIPHY module interrupt handler
- * @irq: Interrupt line
- * @dev: CSIPHY device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t csiphy_isr(int irq, void *dev)
-{
-	struct csiphy_device *csiphy = dev;
-	u8 i;
-
-	for (i = 0; i < 8; i++) {
-		u8 val = readl_relaxed(csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_STATUSn(i));
-		writel_relaxed(val, csiphy->base +
-			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-		writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
-		writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
-		writel_relaxed(0x0, csiphy->base +
-			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-	}
-
-	return IRQ_HANDLED;
-}
-
-/*
- * csiphy_set_clock_rates - Calculate and set clock rates on CSIPHY module
- * @csiphy: CSIPHY device
- */
-static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
-{
-	struct device *dev = to_device_index(csiphy, csiphy->id);
-	u32 pixel_clock;
-	int i, j;
-	int ret;
-
-	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
-	if (ret)
-		pixel_clock = 0;
-
-	for (i = 0; i < csiphy->nclocks; i++) {
-		struct camss_clock *clock = &csiphy->clock[i];
-
-		if (!strcmp(clock->name, "csiphy0_timer") ||
-			!strcmp(clock->name, "csiphy1_timer")) {
-			u8 bpp = csiphy_get_bpp(
-					csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
-			u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
-			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
-			long round_rate;
-
-			camss_add_clock_margin(&min_rate);
-
-			for (j = 0; j < clock->nfreqs; j++)
-				if (min_rate < clock->freq[j])
-					break;
-
-			if (j == clock->nfreqs) {
-				dev_err(dev,
-					"Pixel clock is too high for CSIPHY\n");
-				return -EINVAL;
-			}
-
-			/* if sensor pixel clock is not available */
-			/* set highest possible CSIPHY clock rate */
-			if (min_rate == 0)
-				j = clock->nfreqs - 1;
-
-			round_rate = clk_round_rate(clock->clk, clock->freq[j]);
-			if (round_rate < 0) {
-				dev_err(dev, "clk round rate failed: %ld\n",
-					round_rate);
-				return -EINVAL;
-			}
-
-			csiphy->timer_clk_rate = round_rate;
-
-			ret = clk_set_rate(clock->clk, csiphy->timer_clk_rate);
-			if (ret < 0) {
-				dev_err(dev, "clk set rate failed: %d\n", ret);
-				return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
-/*
- * csiphy_reset - Perform software reset on CSIPHY module
- * @csiphy: CSIPHY device
- */
-static void csiphy_reset(struct csiphy_device *csiphy)
-{
-	writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-	usleep_range(5000, 8000);
-	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-}
-
-/*
- * csiphy_set_power - Power on/off CSIPHY module
- * @sd: CSIPHY V4L2 subdevice
- * @on: Requested power state
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csiphy_set_power(struct v4l2_subdev *sd, int on)
-{
-	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	struct device *dev = to_device_index(csiphy, csiphy->id);
-
-	if (on) {
-		u8 hw_version;
-		int ret;
-
-		ret = csiphy_set_clock_rates(csiphy);
-		if (ret < 0)
-			return ret;
-
-		ret = camss_enable_clocks(csiphy->nclocks, csiphy->clock, dev);
-		if (ret < 0)
-			return ret;
-
-		enable_irq(csiphy->irq);
-
-		csiphy_reset(csiphy);
-
-		hw_version = readl_relaxed(csiphy->base +
-					   CAMSS_CSI_PHY_HW_VERSION);
-		dev_dbg(dev, "CSIPHY HW Version = 0x%02x\n", hw_version);
-	} else {
-		disable_irq(csiphy->irq);
-
-		camss_disable_clocks(csiphy->nclocks, csiphy->clock);
-	}
-
-	return 0;
-}
-
-/*
- * csiphy_get_lane_mask - Calculate CSI2 lane mask configuration parameter
- * @lane_cfg - CSI2 lane configuration
- *
- * Return lane mask
- */
-static u8 csiphy_get_lane_mask(struct csiphy_lanes_cfg *lane_cfg)
-{
-	u8 lane_mask;
-	int i;
-
-	lane_mask = 1 << lane_cfg->clk.pos;
-
-	for (i = 0; i < lane_cfg->num_data; i++)
-		lane_mask |= 1 << lane_cfg->data[i].pos;
-
-	return lane_mask;
-}
-
-/*
- * csiphy_settle_cnt_calc - Calculate settle count value
- * @csiphy: CSIPHY device
- *
- * Helper function to calculate settle count value. This is
- * based on the CSI2 T_hs_settle parameter which in turn
- * is calculated based on the CSI2 transmitter pixel clock
- * frequency.
- *
- * Return settle count value or 0 if the CSI2 pixel clock
- * frequency is not available
- */
-static u8 csiphy_settle_cnt_calc(struct csiphy_device *csiphy)
-{
-	u8 bpp = csiphy_get_bpp(
-			csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
-	u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
-	u32 pixel_clock; /* Hz */
-	u32 mipi_clock; /* Hz */
-	u32 ui; /* ps */
-	u32 timer_period; /* ps */
-	u32 t_hs_prepare_max; /* ps */
-	u32 t_hs_prepare_zero_min; /* ps */
-	u32 t_hs_settle; /* ps */
-	u8 settle_cnt;
-	int ret;
-
-	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
-	if (ret) {
-		dev_err(to_device_index(csiphy, csiphy->id),
-			"Cannot get CSI2 transmitter's pixel clock\n");
-		return 0;
-	}
-	if (!pixel_clock) {
-		dev_err(to_device_index(csiphy, csiphy->id),
-			"Got pixel clock == 0, cannot continue\n");
-		return 0;
-	}
-
-	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
-	ui = div_u64(1000000000000LL, mipi_clock);
-	ui /= 2;
-	t_hs_prepare_max = 85000 + 6 * ui;
-	t_hs_prepare_zero_min = 145000 + 10 * ui;
-	t_hs_settle = (t_hs_prepare_max + t_hs_prepare_zero_min) / 2;
-
-	timer_period = div_u64(1000000000000LL, csiphy->timer_clk_rate);
-	settle_cnt = t_hs_settle / timer_period;
-
-	return settle_cnt;
-}
-
-/*
- * csiphy_stream_on - Enable streaming on CSIPHY module
- * @csiphy: CSIPHY device
- *
- * Helper function to enable streaming on CSIPHY module.
- * Main configuration of CSIPHY module is also done here.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csiphy_stream_on(struct csiphy_device *csiphy)
-{
-	struct csiphy_config *cfg = &csiphy->cfg;
-	u8 lane_mask = csiphy_get_lane_mask(&cfg->csi2->lane_cfg);
-	u8 settle_cnt;
-	u8 val;
-	int i = 0;
-
-	settle_cnt = csiphy_settle_cnt_calc(csiphy);
-	if (!settle_cnt)
-		return -EINVAL;
-
-	val = readl_relaxed(csiphy->base_clk_mux);
-	if (cfg->combo_mode && (lane_mask & 0x18) == 0x18) {
-		val &= ~0xf0;
-		val |= cfg->csid_id << 4;
-	} else {
-		val &= ~0xf;
-		val |= cfg->csid_id;
-	}
-	writel_relaxed(val, csiphy->base_clk_mux);
-
-	writel_relaxed(0x1, csiphy->base +
-		       CAMSS_CSI_PHY_GLBL_T_INIT_CFG0);
-	writel_relaxed(0x1, csiphy->base +
-		       CAMSS_CSI_PHY_T_WAKEUP_CFG0);
-
-	val = 0x1;
-	val |= lane_mask << 1;
-	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
-
-	val = cfg->combo_mode << 4;
-	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-
-	while (lane_mask) {
-		if (lane_mask & 0x1) {
-			writel_relaxed(0x10, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
-			writel_relaxed(settle_cnt, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG3(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_MASKn(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-		}
-
-		lane_mask >>= 1;
-		i++;
-	}
-
-	return 0;
-}
-
-/*
- * csiphy_stream_off - Disable streaming on CSIPHY module
- * @csiphy: CSIPHY device
- *
- * Helper function to disable streaming on CSIPHY module
- */
-static void csiphy_stream_off(struct csiphy_device *csiphy)
-{
-	u8 lane_mask = csiphy_get_lane_mask(&csiphy->cfg.csi2->lane_cfg);
-	int i = 0;
-
-	while (lane_mask) {
-		if (lane_mask & 0x1)
-			writel_relaxed(0x0, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
-
-		lane_mask >>= 1;
-		i++;
-	}
-
-	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
-}
-
-
-/*
- * csiphy_set_stream - Enable/disable streaming on CSIPHY module
- * @sd: CSIPHY V4L2 subdevice
- * @enable: Requested streaming state
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csiphy_set_stream(struct v4l2_subdev *sd, int enable)
-{
-	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	int ret = 0;
-
-	if (enable)
-		ret = csiphy_stream_on(csiphy);
-	else
-		csiphy_stream_off(csiphy);
-
-	return ret;
-}
-
-/*
- * __csiphy_get_format - Get pointer to format structure
- * @csiphy: CSIPHY device
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad from which format is requested
- * @which: TRY or ACTIVE format
- *
- * Return pointer to TRY or ACTIVE format structure
- */
-static struct v4l2_mbus_framefmt *
-__csiphy_get_format(struct csiphy_device *csiphy,
-		    struct v4l2_subdev_pad_config *cfg,
-		    unsigned int pad,
-		    enum v4l2_subdev_format_whence which)
-{
-	if (which == V4L2_SUBDEV_FORMAT_TRY)
-		return v4l2_subdev_get_try_format(&csiphy->subdev, cfg, pad);
-
-	return &csiphy->fmt[pad];
-}
-
-/*
- * csiphy_try_format - Handle try format by pad subdev method
- * @csiphy: CSIPHY device
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad on which format is requested
- * @fmt: pointer to v4l2 format structure
- * @which: wanted subdev format
- */
-static void csiphy_try_format(struct csiphy_device *csiphy,
-			      struct v4l2_subdev_pad_config *cfg,
-			      unsigned int pad,
-			      struct v4l2_mbus_framefmt *fmt,
-			      enum v4l2_subdev_format_whence which)
-{
-	unsigned int i;
-
-	switch (pad) {
-	case MSM_CSIPHY_PAD_SINK:
-		/* Set format on sink pad */
-
-		for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
-			if (fmt->code == csiphy_formats[i].code)
-				break;
-
-		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(csiphy_formats))
-			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-
-		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
-		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
-
-		fmt->field = V4L2_FIELD_NONE;
-		fmt->colorspace = V4L2_COLORSPACE_SRGB;
-
-		break;
-
-	case MSM_CSIPHY_PAD_SRC:
-		/* Set and return a format same as sink pad */
-
-		*fmt = *__csiphy_get_format(csiphy, cfg, MSM_CSID_PAD_SINK,
-					    which);
-
-		break;
-	}
-}
-
-/*
- * csiphy_enum_mbus_code - Handle pixel format enumeration
- * @sd: CSIPHY V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @code: pointer to v4l2_subdev_mbus_code_enum structure
- * return -EINVAL or zero on success
- */
-static int csiphy_enum_mbus_code(struct v4l2_subdev *sd,
-				 struct v4l2_subdev_pad_config *cfg,
-				 struct v4l2_subdev_mbus_code_enum *code)
-{
-	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	if (code->pad == MSM_CSIPHY_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(csiphy_formats))
-			return -EINVAL;
-
-		code->code = csiphy_formats[code->index].code;
-	} else {
-		if (code->index > 0)
-			return -EINVAL;
-
-		format = __csiphy_get_format(csiphy, cfg, MSM_CSIPHY_PAD_SINK,
-					     code->which);
-
-		code->code = format->code;
-	}
-
-	return 0;
-}
-
-/*
- * csiphy_enum_frame_size - Handle frame size enumeration
- * @sd: CSIPHY V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fse: pointer to v4l2_subdev_frame_size_enum structure
- * return -EINVAL or zero on success
- */
-static int csiphy_enum_frame_size(struct v4l2_subdev *sd,
-				  struct v4l2_subdev_pad_config *cfg,
-				  struct v4l2_subdev_frame_size_enum *fse)
-{
-	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt format;
-
-	if (fse->index != 0)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = 1;
-	format.height = 1;
-	csiphy_try_format(csiphy, cfg, fse->pad, &format, fse->which);
-	fse->min_width = format.width;
-	fse->min_height = format.height;
-
-	if (format.code != fse->code)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = -1;
-	format.height = -1;
-	csiphy_try_format(csiphy, cfg, fse->pad, &format, fse->which);
-	fse->max_width = format.width;
-	fse->max_height = format.height;
-
-	return 0;
-}
-
-/*
- * csiphy_get_format - Handle get format by pads subdev method
- * @sd: CSIPHY V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int csiphy_get_format(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_pad_config *cfg,
-			     struct v4l2_subdev_format *fmt)
-{
-	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __csiphy_get_format(csiphy, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	fmt->format = *format;
-
-	return 0;
-}
-
-/*
- * csiphy_set_format - Handle set format by pads subdev method
- * @sd: CSIPHY V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int csiphy_set_format(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_pad_config *cfg,
-			     struct v4l2_subdev_format *fmt)
-{
-	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __csiphy_get_format(csiphy, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	csiphy_try_format(csiphy, cfg, fmt->pad, &fmt->format, fmt->which);
-	*format = fmt->format;
-
-	/* Propagate the format from sink to source */
-	if (fmt->pad == MSM_CSIPHY_PAD_SINK) {
-		format = __csiphy_get_format(csiphy, cfg, MSM_CSIPHY_PAD_SRC,
-					     fmt->which);
-
-		*format = fmt->format;
-		csiphy_try_format(csiphy, cfg, MSM_CSIPHY_PAD_SRC, format,
-				  fmt->which);
-	}
-
-	return 0;
-}
-
-/*
- * csiphy_init_formats - Initialize formats on all pads
- * @sd: CSIPHY V4L2 subdevice
- * @fh: V4L2 subdev file handle
- *
- * Initialize all pad formats with default values.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csiphy_init_formats(struct v4l2_subdev *sd,
-			       struct v4l2_subdev_fh *fh)
-{
-	struct v4l2_subdev_format format = {
-		.pad = MSM_CSIPHY_PAD_SINK,
-		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
-			      V4L2_SUBDEV_FORMAT_ACTIVE,
-		.format = {
-			.code = MEDIA_BUS_FMT_UYVY8_2X8,
-			.width = 1920,
-			.height = 1080
-		}
-	};
-
-	return csiphy_set_format(sd, fh ? fh->pad : NULL, &format);
-}
-
-/*
- * msm_csiphy_subdev_init - Initialize CSIPHY device structure and resources
- * @csiphy: CSIPHY device
- * @res: CSIPHY module resources table
- * @id: CSIPHY module id
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
-			   const struct resources *res, u8 id)
-{
-	struct device *dev = to_device_index(csiphy, id);
-	struct platform_device *pdev = to_platform_device(dev);
-	struct resource *r;
-	int i, j;
-	int ret;
-
-	csiphy->id = id;
-	csiphy->cfg.combo_mode = 0;
-
-	/* Memory */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
-	csiphy->base = devm_ioremap_resource(dev, r);
-	if (IS_ERR(csiphy->base)) {
-		dev_err(dev, "could not map memory\n");
-		return PTR_ERR(csiphy->base);
-	}
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[1]);
-	csiphy->base_clk_mux = devm_ioremap_resource(dev, r);
-	if (IS_ERR(csiphy->base_clk_mux)) {
-		dev_err(dev, "could not map memory\n");
-		return PTR_ERR(csiphy->base_clk_mux);
-	}
-
-	/* Interrupt */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ,
-					 res->interrupt[0]);
-	if (!r) {
-		dev_err(dev, "missing IRQ\n");
-		return -EINVAL;
-	}
-
-	csiphy->irq = r->start;
-	snprintf(csiphy->irq_name, sizeof(csiphy->irq_name), "%s_%s%d",
-		 dev_name(dev), MSM_CSIPHY_NAME, csiphy->id);
-	ret = devm_request_irq(dev, csiphy->irq, csiphy_isr,
-			       IRQF_TRIGGER_RISING, csiphy->irq_name, csiphy);
-	if (ret < 0) {
-		dev_err(dev, "request_irq failed: %d\n", ret);
-		return ret;
-	}
-
-	disable_irq(csiphy->irq);
-
-	/* Clocks */
-
-	csiphy->nclocks = 0;
-	while (res->clock[csiphy->nclocks])
-		csiphy->nclocks++;
-
-	csiphy->clock = devm_kcalloc(dev,
-				     csiphy->nclocks, sizeof(*csiphy->clock),
-				     GFP_KERNEL);
-	if (!csiphy->clock)
-		return -ENOMEM;
-
-	for (i = 0; i < csiphy->nclocks; i++) {
-		struct camss_clock *clock = &csiphy->clock[i];
-
-		clock->clk = devm_clk_get(dev, res->clock[i]);
-		if (IS_ERR(clock->clk))
-			return PTR_ERR(clock->clk);
-
-		clock->name = res->clock[i];
-
-		clock->nfreqs = 0;
-		while (res->clock_rate[i][clock->nfreqs])
-			clock->nfreqs++;
-
-		if (!clock->nfreqs) {
-			clock->freq = NULL;
-			continue;
-		}
-
-		clock->freq = devm_kcalloc(dev,
-					   clock->nfreqs,
-					   sizeof(*clock->freq),
-					   GFP_KERNEL);
-		if (!clock->freq)
-			return -ENOMEM;
-
-		for (j = 0; j < clock->nfreqs; j++)
-			clock->freq[j] = res->clock_rate[i][j];
-	}
-
-	return 0;
-}
-
-/*
- * csiphy_link_setup - Setup CSIPHY connections
- * @entity: Pointer to media entity structure
- * @local: Pointer to local pad
- * @remote: Pointer to remote pad
- * @flags: Link flags
- *
- * Rreturn 0 on success
- */
-static int csiphy_link_setup(struct media_entity *entity,
-			     const struct media_pad *local,
-			     const struct media_pad *remote, u32 flags)
-{
-	if ((local->flags & MEDIA_PAD_FL_SOURCE) &&
-	    (flags & MEDIA_LNK_FL_ENABLED)) {
-		struct v4l2_subdev *sd;
-		struct csiphy_device *csiphy;
-		struct csid_device *csid;
-
-		if (media_entity_remote_pad(local))
-			return -EBUSY;
-
-		sd = media_entity_to_v4l2_subdev(entity);
-		csiphy = v4l2_get_subdevdata(sd);
-
-		sd = media_entity_to_v4l2_subdev(remote->entity);
-		csid = v4l2_get_subdevdata(sd);
-
-		csiphy->cfg.csid_id = csid->id;
-	}
-
-	return 0;
-}
-
-static const struct v4l2_subdev_core_ops csiphy_core_ops = {
-	.s_power = csiphy_set_power,
-};
-
-static const struct v4l2_subdev_video_ops csiphy_video_ops = {
-	.s_stream = csiphy_set_stream,
-};
-
-static const struct v4l2_subdev_pad_ops csiphy_pad_ops = {
-	.enum_mbus_code = csiphy_enum_mbus_code,
-	.enum_frame_size = csiphy_enum_frame_size,
-	.get_fmt = csiphy_get_format,
-	.set_fmt = csiphy_set_format,
-};
-
-static const struct v4l2_subdev_ops csiphy_v4l2_ops = {
-	.core = &csiphy_core_ops,
-	.video = &csiphy_video_ops,
-	.pad = &csiphy_pad_ops,
-};
-
-static const struct v4l2_subdev_internal_ops csiphy_v4l2_internal_ops = {
-	.open = csiphy_init_formats,
-};
-
-static const struct media_entity_operations csiphy_media_ops = {
-	.link_setup = csiphy_link_setup,
-	.link_validate = v4l2_subdev_link_validate,
-};
-
-/*
- * msm_csiphy_register_entity - Register subdev node for CSIPHY module
- * @csiphy: CSIPHY device
- * @v4l2_dev: V4L2 device
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_csiphy_register_entity(struct csiphy_device *csiphy,
-			       struct v4l2_device *v4l2_dev)
-{
-	struct v4l2_subdev *sd = &csiphy->subdev;
-	struct media_pad *pads = csiphy->pads;
-	struct device *dev = to_device_index(csiphy, csiphy->id);
-	int ret;
-
-	v4l2_subdev_init(sd, &csiphy_v4l2_ops);
-	sd->internal_ops = &csiphy_v4l2_internal_ops;
-	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-	snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
-		 MSM_CSIPHY_NAME, csiphy->id);
-	v4l2_set_subdevdata(sd, csiphy);
-
-	ret = csiphy_init_formats(sd, NULL);
-	if (ret < 0) {
-		dev_err(dev, "Failed to init format: %d\n", ret);
-		return ret;
-	}
-
-	pads[MSM_CSIPHY_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
-	pads[MSM_CSIPHY_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
-
-	sd->entity.function = MEDIA_ENT_F_IO_V4L;
-	sd->entity.ops = &csiphy_media_ops;
-	ret = media_entity_pads_init(&sd->entity, MSM_CSIPHY_PADS_NUM, pads);
-	if (ret < 0) {
-		dev_err(dev, "Failed to init media entity: %d\n", ret);
-		return ret;
-	}
-
-	ret = v4l2_device_register_subdev(v4l2_dev, sd);
-	if (ret < 0) {
-		dev_err(dev, "Failed to register subdev: %d\n", ret);
-		media_entity_cleanup(&sd->entity);
-	}
-
-	return ret;
-}
-
-/*
- * msm_csiphy_unregister_entity - Unregister CSIPHY module subdev node
- * @csiphy: CSIPHY device
- */
-void msm_csiphy_unregister_entity(struct csiphy_device *csiphy)
-{
-	v4l2_device_unregister_subdev(&csiphy->subdev);
-	media_entity_cleanup(&csiphy->subdev.entity);
-}
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.h b/drivers/media/platform/qcom/camss-8x16/camss-csiphy.h
deleted file mode 100644
index ba8781122065..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-csiphy.h
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * camss-csiphy.h
- *
- * Qualcomm MSM Camera Subsystem - CSIPHY Module
- *
- * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2016-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef QC_MSM_CAMSS_CSIPHY_H
-#define QC_MSM_CAMSS_CSIPHY_H
-
-#include <linux/clk.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-mediabus.h>
-#include <media/v4l2-subdev.h>
-
-#define MSM_CSIPHY_PAD_SINK 0
-#define MSM_CSIPHY_PAD_SRC 1
-#define MSM_CSIPHY_PADS_NUM 2
-
-struct csiphy_lane {
-	u8 pos;
-	u8 pol;
-};
-
-struct csiphy_lanes_cfg {
-	int num_data;
-	struct csiphy_lane *data;
-	struct csiphy_lane clk;
-};
-
-struct csiphy_csi2_cfg {
-	struct csiphy_lanes_cfg lane_cfg;
-};
-
-struct csiphy_config {
-	u8 combo_mode;
-	u8 csid_id;
-	struct csiphy_csi2_cfg *csi2;
-};
-
-struct csiphy_device {
-	u8 id;
-	struct v4l2_subdev subdev;
-	struct media_pad pads[MSM_CSIPHY_PADS_NUM];
-	void __iomem *base;
-	void __iomem *base_clk_mux;
-	u32 irq;
-	char irq_name[30];
-	struct camss_clock *clock;
-	int nclocks;
-	u32 timer_clk_rate;
-	struct csiphy_config cfg;
-	struct v4l2_mbus_framefmt fmt[MSM_CSIPHY_PADS_NUM];
-};
-
-struct resources;
-
-int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
-			   const struct resources *res, u8 id);
-
-int msm_csiphy_register_entity(struct csiphy_device *csiphy,
-			       struct v4l2_device *v4l2_dev);
-
-void msm_csiphy_unregister_entity(struct csiphy_device *csiphy);
-
-#endif /* QC_MSM_CAMSS_CSIPHY_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-ispif.c b/drivers/media/platform/qcom/camss-8x16/camss-ispif.c
deleted file mode 100644
index 9d1af9353c1d..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-ispif.c
+++ /dev/null
@@ -1,1178 +0,0 @@
-/*
- * camss-ispif.c
- *
- * Qualcomm MSM Camera Subsystem - ISPIF (ISP Interface) Module
- *
- * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/clk.h>
-#include <linux/completion.h>
-#include <linux/interrupt.h>
-#include <linux/iopoll.h>
-#include <linux/kernel.h>
-#include <linux/mutex.h>
-#include <linux/platform_device.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-
-#include "camss-ispif.h"
-#include "camss.h"
-
-#define MSM_ISPIF_NAME "msm_ispif"
-
-#define ispif_line_array(ptr_line)	\
-	((const struct ispif_line (*)[]) &(ptr_line[-(ptr_line->id)]))
-
-#define to_ispif(ptr_line)	\
-	container_of(ispif_line_array(ptr_line), struct ispif_device, ptr_line)
-
-#define ISPIF_RST_CMD_0			0x008
-#define ISPIF_RST_CMD_0_STROBED_RST_EN		(1 << 0)
-#define ISPIF_RST_CMD_0_MISC_LOGIC_RST		(1 << 1)
-#define ISPIF_RST_CMD_0_SW_REG_RST		(1 << 2)
-#define ISPIF_RST_CMD_0_PIX_INTF_0_CSID_RST	(1 << 3)
-#define ISPIF_RST_CMD_0_PIX_INTF_0_VFE_RST	(1 << 4)
-#define ISPIF_RST_CMD_0_PIX_INTF_1_CSID_RST	(1 << 5)
-#define ISPIF_RST_CMD_0_PIX_INTF_1_VFE_RST	(1 << 6)
-#define ISPIF_RST_CMD_0_RDI_INTF_0_CSID_RST	(1 << 7)
-#define ISPIF_RST_CMD_0_RDI_INTF_0_VFE_RST	(1 << 8)
-#define ISPIF_RST_CMD_0_RDI_INTF_1_CSID_RST	(1 << 9)
-#define ISPIF_RST_CMD_0_RDI_INTF_1_VFE_RST	(1 << 10)
-#define ISPIF_RST_CMD_0_RDI_INTF_2_CSID_RST	(1 << 11)
-#define ISPIF_RST_CMD_0_RDI_INTF_2_VFE_RST	(1 << 12)
-#define ISPIF_RST_CMD_0_PIX_OUTPUT_0_MISR_RST	(1 << 16)
-#define ISPIF_RST_CMD_0_RDI_OUTPUT_0_MISR_RST	(1 << 17)
-#define ISPIF_RST_CMD_0_RDI_OUTPUT_1_MISR_RST	(1 << 18)
-#define ISPIF_RST_CMD_0_RDI_OUTPUT_2_MISR_RST	(1 << 19)
-#define ISPIF_IRQ_GLOBAL_CLEAR_CMD	0x01c
-#define ISPIF_VFE_m_CTRL_0(m)		(0x200 + 0x200 * (m))
-#define ISPIF_VFE_m_CTRL_0_PIX0_LINE_BUF_EN	(1 << 6)
-#define ISPIF_VFE_m_IRQ_MASK_0(m)	(0x208 + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_MASK_0_PIX0_ENABLE	0x00001249
-#define ISPIF_VFE_m_IRQ_MASK_0_PIX0_MASK	0x00001fff
-#define ISPIF_VFE_m_IRQ_MASK_0_RDI0_ENABLE	0x02492000
-#define ISPIF_VFE_m_IRQ_MASK_0_RDI0_MASK	0x03ffe000
-#define ISPIF_VFE_m_IRQ_MASK_1(m)	(0x20c + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_MASK_1_PIX1_ENABLE	0x00001249
-#define ISPIF_VFE_m_IRQ_MASK_1_PIX1_MASK	0x00001fff
-#define ISPIF_VFE_m_IRQ_MASK_1_RDI1_ENABLE	0x02492000
-#define ISPIF_VFE_m_IRQ_MASK_1_RDI1_MASK	0x03ffe000
-#define ISPIF_VFE_m_IRQ_MASK_2(m)	(0x210 + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_MASK_2_RDI2_ENABLE	0x00001249
-#define ISPIF_VFE_m_IRQ_MASK_2_RDI2_MASK	0x00001fff
-#define ISPIF_VFE_m_IRQ_STATUS_0(m)	(0x21c + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW	(1 << 12)
-#define ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW	(1 << 25)
-#define ISPIF_VFE_m_IRQ_STATUS_1(m)	(0x220 + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW	(1 << 12)
-#define ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW	(1 << 25)
-#define ISPIF_VFE_m_IRQ_STATUS_2(m)	(0x224 + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW	(1 << 12)
-#define ISPIF_VFE_m_IRQ_CLEAR_0(m)	(0x230 + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_CLEAR_1(m)	(0x234 + 0x200 * (m))
-#define ISPIF_VFE_m_IRQ_CLEAR_2(m)	(0x238 + 0x200 * (m))
-#define ISPIF_VFE_m_INTF_INPUT_SEL(m)	(0x244 + 0x200 * (m))
-#define ISPIF_VFE_m_INTF_CMD_0(m)	(0x248 + 0x200 * (m))
-#define ISPIF_VFE_m_INTF_CMD_1(m)	(0x24c + 0x200 * (m))
-#define ISPIF_VFE_m_PIX_INTF_n_CID_MASK(m, n)	\
-					(0x254 + 0x200 * (m) + 0x4 * (n))
-#define ISPIF_VFE_m_RDI_INTF_n_CID_MASK(m, n)	\
-					(0x264 + 0x200 * (m) + 0x4 * (n))
-#define ISPIF_VFE_m_PIX_INTF_n_STATUS(m, n)	\
-					(0x2c0 + 0x200 * (m) + 0x4 * (n))
-#define ISPIF_VFE_m_RDI_INTF_n_STATUS(m, n)	\
-					(0x2d0 + 0x200 * (m) + 0x4 * (n))
-
-#define CSI_PIX_CLK_MUX_SEL		0x000
-#define CSI_RDI_CLK_MUX_SEL		0x008
-
-#define ISPIF_TIMEOUT_SLEEP_US		1000
-#define ISPIF_TIMEOUT_ALL_US		1000000
-#define ISPIF_RESET_TIMEOUT_MS		500
-
-enum ispif_intf_cmd {
-	CMD_DISABLE_FRAME_BOUNDARY = 0x0,
-	CMD_ENABLE_FRAME_BOUNDARY = 0x1,
-	CMD_DISABLE_IMMEDIATELY = 0x2,
-	CMD_ALL_DISABLE_IMMEDIATELY = 0xaaaaaaaa,
-	CMD_ALL_NO_CHANGE = 0xffffffff,
-};
-
-static const u32 ispif_formats[] = {
-	MEDIA_BUS_FMT_UYVY8_2X8,
-	MEDIA_BUS_FMT_VYUY8_2X8,
-	MEDIA_BUS_FMT_YUYV8_2X8,
-	MEDIA_BUS_FMT_YVYU8_2X8,
-	MEDIA_BUS_FMT_SBGGR8_1X8,
-	MEDIA_BUS_FMT_SGBRG8_1X8,
-	MEDIA_BUS_FMT_SGRBG8_1X8,
-	MEDIA_BUS_FMT_SRGGB8_1X8,
-	MEDIA_BUS_FMT_SBGGR10_1X10,
-	MEDIA_BUS_FMT_SGBRG10_1X10,
-	MEDIA_BUS_FMT_SGRBG10_1X10,
-	MEDIA_BUS_FMT_SRGGB10_1X10,
-	MEDIA_BUS_FMT_SBGGR12_1X12,
-	MEDIA_BUS_FMT_SGBRG12_1X12,
-	MEDIA_BUS_FMT_SGRBG12_1X12,
-	MEDIA_BUS_FMT_SRGGB12_1X12,
-};
-
-/*
- * ispif_isr - ISPIF module interrupt handler
- * @irq: Interrupt line
- * @dev: ISPIF device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t ispif_isr(int irq, void *dev)
-{
-	struct ispif_device *ispif = dev;
-	u32 value0, value1, value2;
-
-	value0 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_0(0));
-	value1 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_1(0));
-	value2 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_2(0));
-
-	writel_relaxed(value0, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(0));
-	writel_relaxed(value1, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(0));
-	writel_relaxed(value2, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(0));
-
-	writel(0x1, ispif->base + ISPIF_IRQ_GLOBAL_CLEAR_CMD);
-
-	if ((value0 >> 27) & 0x1)
-		complete(&ispif->reset_complete);
-
-	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW))
-		dev_err_ratelimited(to_device(ispif), "VFE0 pix0 overflow\n");
-
-	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW))
-		dev_err_ratelimited(to_device(ispif), "VFE0 rdi0 overflow\n");
-
-	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW))
-		dev_err_ratelimited(to_device(ispif), "VFE0 pix1 overflow\n");
-
-	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW))
-		dev_err_ratelimited(to_device(ispif), "VFE0 rdi1 overflow\n");
-
-	if (unlikely(value2 & ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW))
-		dev_err_ratelimited(to_device(ispif), "VFE0 rdi2 overflow\n");
-
-	return IRQ_HANDLED;
-}
-
-/*
- * ispif_reset - Trigger reset on ISPIF module and wait to complete
- * @ispif: ISPIF device
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int ispif_reset(struct ispif_device *ispif)
-{
-	unsigned long time;
-	u32 val;
-	int ret;
-
-	ret = camss_enable_clocks(ispif->nclocks_for_reset,
-				  ispif->clock_for_reset,
-				  to_device(ispif));
-	if (ret < 0)
-		return ret;
-
-	reinit_completion(&ispif->reset_complete);
-
-	val = ISPIF_RST_CMD_0_STROBED_RST_EN |
-		ISPIF_RST_CMD_0_MISC_LOGIC_RST |
-		ISPIF_RST_CMD_0_SW_REG_RST |
-		ISPIF_RST_CMD_0_PIX_INTF_0_CSID_RST |
-		ISPIF_RST_CMD_0_PIX_INTF_0_VFE_RST |
-		ISPIF_RST_CMD_0_PIX_INTF_1_CSID_RST |
-		ISPIF_RST_CMD_0_PIX_INTF_1_VFE_RST |
-		ISPIF_RST_CMD_0_RDI_INTF_0_CSID_RST |
-		ISPIF_RST_CMD_0_RDI_INTF_0_VFE_RST |
-		ISPIF_RST_CMD_0_RDI_INTF_1_CSID_RST |
-		ISPIF_RST_CMD_0_RDI_INTF_1_VFE_RST |
-		ISPIF_RST_CMD_0_RDI_INTF_2_CSID_RST |
-		ISPIF_RST_CMD_0_RDI_INTF_2_VFE_RST |
-		ISPIF_RST_CMD_0_PIX_OUTPUT_0_MISR_RST |
-		ISPIF_RST_CMD_0_RDI_OUTPUT_0_MISR_RST |
-		ISPIF_RST_CMD_0_RDI_OUTPUT_1_MISR_RST |
-		ISPIF_RST_CMD_0_RDI_OUTPUT_2_MISR_RST;
-
-	writel_relaxed(val, ispif->base + ISPIF_RST_CMD_0);
-
-	time = wait_for_completion_timeout(&ispif->reset_complete,
-		msecs_to_jiffies(ISPIF_RESET_TIMEOUT_MS));
-	if (!time) {
-		dev_err(to_device(ispif), "ISPIF reset timeout\n");
-		return -EIO;
-	}
-
-	camss_disable_clocks(ispif->nclocks_for_reset, ispif->clock_for_reset);
-
-	return 0;
-}
-
-/*
- * ispif_set_power - Power on/off ISPIF module
- * @sd: ISPIF V4L2 subdevice
- * @on: Requested power state
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int ispif_set_power(struct v4l2_subdev *sd, int on)
-{
-	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct ispif_device *ispif = to_ispif(line);
-	struct device *dev = to_device(ispif);
-	int ret = 0;
-
-	mutex_lock(&ispif->power_lock);
-
-	if (on) {
-		if (ispif->power_count) {
-			/* Power is already on */
-			ispif->power_count++;
-			goto exit;
-		}
-
-		ret = camss_enable_clocks(ispif->nclocks, ispif->clock, dev);
-		if (ret < 0)
-			goto exit;
-
-		ret = ispif_reset(ispif);
-		if (ret < 0) {
-			camss_disable_clocks(ispif->nclocks, ispif->clock);
-			goto exit;
-		}
-
-		ispif->intf_cmd[line->vfe_id].cmd_0 = CMD_ALL_NO_CHANGE;
-		ispif->intf_cmd[line->vfe_id].cmd_1 = CMD_ALL_NO_CHANGE;
-
-		ispif->power_count++;
-	} else {
-		if (ispif->power_count == 0) {
-			dev_err(dev, "ispif power off on power_count == 0\n");
-			goto exit;
-		} else if (ispif->power_count == 1) {
-			camss_disable_clocks(ispif->nclocks, ispif->clock);
-		}
-
-		ispif->power_count--;
-	}
-
-exit:
-	mutex_unlock(&ispif->power_lock);
-
-	return ret;
-}
-
-/*
- * ispif_select_clk_mux - Select clock for PIX/RDI interface
- * @ispif: ISPIF device
- * @intf: VFE interface
- * @csid: CSID HW module id
- * @vfe: VFE HW module id
- * @enable: enable or disable the selected clock
- */
-static void ispif_select_clk_mux(struct ispif_device *ispif,
-				 enum ispif_intf intf, u8 csid,
-				 u8 vfe, u8 enable)
-{
-	u32 val;
-
-	switch (intf) {
-	case PIX0:
-		val = readl_relaxed(ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
-		val &= ~(0xf << (vfe * 8));
-		if (enable)
-			val |= (csid << (vfe * 8));
-		writel_relaxed(val, ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
-		break;
-
-	case RDI0:
-		val = readl_relaxed(ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
-		val &= ~(0xf << (vfe * 12));
-		if (enable)
-			val |= (csid << (vfe * 12));
-		writel_relaxed(val, ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
-		break;
-
-	case PIX1:
-		val = readl_relaxed(ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
-		val &= ~(0xf << (4 + (vfe * 8)));
-		if (enable)
-			val |= (csid << (4 + (vfe * 8)));
-		writel_relaxed(val, ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
-		break;
-
-	case RDI1:
-		val = readl_relaxed(ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
-		val &= ~(0xf << (4 + (vfe * 12)));
-		if (enable)
-			val |= (csid << (4 + (vfe * 12)));
-		writel_relaxed(val, ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
-		break;
-
-	case RDI2:
-		val = readl_relaxed(ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
-		val &= ~(0xf << (8 + (vfe * 12)));
-		if (enable)
-			val |= (csid << (8 + (vfe * 12)));
-		writel_relaxed(val, ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
-		break;
-	}
-
-	mb();
-}
-
-/*
- * ispif_validate_intf_status - Validate current status of PIX/RDI interface
- * @ispif: ISPIF device
- * @intf: VFE interface
- * @vfe: VFE HW module id
- *
- * Return 0 when interface is idle or -EBUSY otherwise
- */
-static int ispif_validate_intf_status(struct ispif_device *ispif,
-				      enum ispif_intf intf, u8 vfe)
-{
-	int ret = 0;
-	u32 val = 0;
-
-	switch (intf) {
-	case PIX0:
-		val = readl_relaxed(ispif->base +
-			ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 0));
-		break;
-	case RDI0:
-		val = readl_relaxed(ispif->base +
-			ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 0));
-		break;
-	case PIX1:
-		val = readl_relaxed(ispif->base +
-			ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 1));
-		break;
-	case RDI1:
-		val = readl_relaxed(ispif->base +
-			ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 1));
-		break;
-	case RDI2:
-		val = readl_relaxed(ispif->base +
-			ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 2));
-		break;
-	}
-
-	if ((val & 0xf) != 0xf) {
-		dev_err(to_device(ispif), "%s: ispif is busy: 0x%x\n",
-			__func__, val);
-		ret = -EBUSY;
-	}
-
-	return ret;
-}
-
-/*
- * ispif_wait_for_stop - Wait for PIX/RDI interface to stop
- * @ispif: ISPIF device
- * @intf: VFE interface
- * @vfe: VFE HW module id
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int ispif_wait_for_stop(struct ispif_device *ispif,
-			       enum ispif_intf intf, u8 vfe)
-{
-	u32 addr = 0;
-	u32 stop_flag = 0;
-	int ret;
-
-	switch (intf) {
-	case PIX0:
-		addr = ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 0);
-		break;
-	case RDI0:
-		addr = ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 0);
-		break;
-	case PIX1:
-		addr = ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 1);
-		break;
-	case RDI1:
-		addr = ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 1);
-		break;
-	case RDI2:
-		addr = ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 2);
-		break;
-	}
-
-	ret = readl_poll_timeout(ispif->base + addr,
-				 stop_flag,
-				 (stop_flag & 0xf) == 0xf,
-				 ISPIF_TIMEOUT_SLEEP_US,
-				 ISPIF_TIMEOUT_ALL_US);
-	if (ret < 0)
-		dev_err(to_device(ispif), "%s: ispif stop timeout\n",
-			__func__);
-
-	return ret;
-}
-
-/*
- * ispif_select_csid - Select CSID HW module for input from
- * @ispif: ISPIF device
- * @intf: VFE interface
- * @csid: CSID HW module id
- * @vfe: VFE HW module id
- * @enable: enable or disable the selected input
- */
-static void ispif_select_csid(struct ispif_device *ispif, enum ispif_intf intf,
-			      u8 csid, u8 vfe, u8 enable)
-{
-	u32 val;
-
-	val = readl_relaxed(ispif->base + ISPIF_VFE_m_INTF_INPUT_SEL(vfe));
-	switch (intf) {
-	case PIX0:
-		val &= ~(BIT(1) | BIT(0));
-		if (enable)
-			val |= csid;
-		break;
-	case RDI0:
-		val &= ~(BIT(5) | BIT(4));
-		if (enable)
-			val |= (csid << 4);
-		break;
-	case PIX1:
-		val &= ~(BIT(9) | BIT(8));
-		if (enable)
-			val |= (csid << 8);
-		break;
-	case RDI1:
-		val &= ~(BIT(13) | BIT(12));
-		if (enable)
-			val |= (csid << 12);
-		break;
-	case RDI2:
-		val &= ~(BIT(21) | BIT(20));
-		if (enable)
-			val |= (csid << 20);
-		break;
-	}
-
-	writel(val, ispif->base + ISPIF_VFE_m_INTF_INPUT_SEL(vfe));
-}
-
-/*
- * ispif_select_cid - Enable/disable desired CID
- * @ispif: ISPIF device
- * @intf: VFE interface
- * @cid: desired CID to enable/disable
- * @vfe: VFE HW module id
- * @enable: enable or disable the desired CID
- */
-static void ispif_select_cid(struct ispif_device *ispif, enum ispif_intf intf,
-			     u8 cid, u8 vfe, u8 enable)
-{
-	u32 cid_mask = 1 << cid;
-	u32 addr = 0;
-	u32 val;
-
-	switch (intf) {
-	case PIX0:
-		addr = ISPIF_VFE_m_PIX_INTF_n_CID_MASK(vfe, 0);
-		break;
-	case RDI0:
-		addr = ISPIF_VFE_m_RDI_INTF_n_CID_MASK(vfe, 0);
-		break;
-	case PIX1:
-		addr = ISPIF_VFE_m_PIX_INTF_n_CID_MASK(vfe, 1);
-		break;
-	case RDI1:
-		addr = ISPIF_VFE_m_RDI_INTF_n_CID_MASK(vfe, 1);
-		break;
-	case RDI2:
-		addr = ISPIF_VFE_m_RDI_INTF_n_CID_MASK(vfe, 2);
-		break;
-	}
-
-	val = readl_relaxed(ispif->base + addr);
-	if (enable)
-		val |= cid_mask;
-	else
-		val &= ~cid_mask;
-
-	writel(val, ispif->base + addr);
-}
-
-/*
- * ispif_config_irq - Enable/disable interrupts for PIX/RDI interface
- * @ispif: ISPIF device
- * @intf: VFE interface
- * @vfe: VFE HW module id
- * @enable: enable or disable
- */
-static void ispif_config_irq(struct ispif_device *ispif, enum ispif_intf intf,
-			     u8 vfe, u8 enable)
-{
-	u32 val;
-
-	switch (intf) {
-	case PIX0:
-		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
-		val &= ~ISPIF_VFE_m_IRQ_MASK_0_PIX0_MASK;
-		if (enable)
-			val |= ISPIF_VFE_m_IRQ_MASK_0_PIX0_ENABLE;
-		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
-		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_0_PIX0_ENABLE,
-			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(vfe));
-		break;
-	case RDI0:
-		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
-		val &= ~ISPIF_VFE_m_IRQ_MASK_0_RDI0_MASK;
-		if (enable)
-			val |= ISPIF_VFE_m_IRQ_MASK_0_RDI0_ENABLE;
-		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
-		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_0_RDI0_ENABLE,
-			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(vfe));
-		break;
-	case PIX1:
-		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
-		val &= ~ISPIF_VFE_m_IRQ_MASK_1_PIX1_MASK;
-		if (enable)
-			val |= ISPIF_VFE_m_IRQ_MASK_1_PIX1_ENABLE;
-		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
-		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_1_PIX1_ENABLE,
-			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(vfe));
-		break;
-	case RDI1:
-		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
-		val &= ~ISPIF_VFE_m_IRQ_MASK_1_RDI1_MASK;
-		if (enable)
-			val |= ISPIF_VFE_m_IRQ_MASK_1_RDI1_ENABLE;
-		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
-		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_1_RDI1_ENABLE,
-			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(vfe));
-		break;
-	case RDI2:
-		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_2(vfe));
-		val &= ~ISPIF_VFE_m_IRQ_MASK_2_RDI2_MASK;
-		if (enable)
-			val |= ISPIF_VFE_m_IRQ_MASK_2_RDI2_ENABLE;
-		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_2(vfe));
-		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_2_RDI2_ENABLE,
-			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(vfe));
-		break;
-	}
-
-	writel(0x1, ispif->base + ISPIF_IRQ_GLOBAL_CLEAR_CMD);
-}
-
-/*
- * ispif_set_intf_cmd - Set command to enable/disable interface
- * @ispif: ISPIF device
- * @cmd: interface command
- * @intf: VFE interface
- * @vfe: VFE HW module id
- * @vc: virtual channel
- */
-static void ispif_set_intf_cmd(struct ispif_device *ispif, u8 cmd,
-			       enum ispif_intf intf, u8 vfe, u8 vc)
-{
-	u32 *val;
-
-	if (intf == RDI2) {
-		val = &ispif->intf_cmd[vfe].cmd_1;
-		*val &= ~(0x3 << (vc * 2 + 8));
-		*val |= (cmd << (vc * 2 + 8));
-		wmb();
-		writel_relaxed(*val, ispif->base + ISPIF_VFE_m_INTF_CMD_1(vfe));
-		wmb();
-	} else {
-		val = &ispif->intf_cmd[vfe].cmd_0;
-		*val &= ~(0x3 << (vc * 2 + intf * 8));
-		*val |= (cmd << (vc * 2 + intf * 8));
-		wmb();
-		writel_relaxed(*val, ispif->base + ISPIF_VFE_m_INTF_CMD_0(vfe));
-		wmb();
-	}
-}
-
-/*
- * ispif_set_stream - Enable/disable streaming on ISPIF module
- * @sd: ISPIF V4L2 subdevice
- * @enable: Requested streaming state
- *
- * Main configuration of ISPIF module is also done here.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
-{
-	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct ispif_device *ispif = to_ispif(line);
-	enum ispif_intf intf = line->interface;
-	u8 csid = line->csid_id;
-	u8 vfe = line->vfe_id;
-	u8 vc = 0; /* Virtual Channel 0 */
-	u8 cid = vc * 4; /* id of Virtual Channel and Data Type set */
-	int ret;
-
-	if (enable) {
-		if (!media_entity_remote_pad(&line->pads[MSM_ISPIF_PAD_SINK]))
-			return -ENOLINK;
-
-		/* Config */
-
-		mutex_lock(&ispif->config_lock);
-		ispif_select_clk_mux(ispif, intf, csid, vfe, 1);
-
-		ret = ispif_validate_intf_status(ispif, intf, vfe);
-		if (ret < 0) {
-			mutex_unlock(&ispif->config_lock);
-			return ret;
-		}
-
-		ispif_select_csid(ispif, intf, csid, vfe, 1);
-		ispif_select_cid(ispif, intf, cid, vfe, 1);
-		ispif_config_irq(ispif, intf, vfe, 1);
-		ispif_set_intf_cmd(ispif, CMD_ENABLE_FRAME_BOUNDARY,
-				   intf, vfe, vc);
-	} else {
-		mutex_lock(&ispif->config_lock);
-		ispif_set_intf_cmd(ispif, CMD_DISABLE_FRAME_BOUNDARY,
-				   intf, vfe, vc);
-		mutex_unlock(&ispif->config_lock);
-
-		ret = ispif_wait_for_stop(ispif, intf, vfe);
-		if (ret < 0)
-			return ret;
-
-		mutex_lock(&ispif->config_lock);
-		ispif_config_irq(ispif, intf, vfe, 0);
-		ispif_select_cid(ispif, intf, cid, vfe, 0);
-		ispif_select_csid(ispif, intf, csid, vfe, 0);
-		ispif_select_clk_mux(ispif, intf, csid, vfe, 0);
-	}
-
-	mutex_unlock(&ispif->config_lock);
-
-	return 0;
-}
-
-/*
- * __ispif_get_format - Get pointer to format structure
- * @ispif: ISPIF line
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad from which format is requested
- * @which: TRY or ACTIVE format
- *
- * Return pointer to TRY or ACTIVE format structure
- */
-static struct v4l2_mbus_framefmt *
-__ispif_get_format(struct ispif_line *line,
-		   struct v4l2_subdev_pad_config *cfg,
-		   unsigned int pad,
-		   enum v4l2_subdev_format_whence which)
-{
-	if (which == V4L2_SUBDEV_FORMAT_TRY)
-		return v4l2_subdev_get_try_format(&line->subdev, cfg, pad);
-
-	return &line->fmt[pad];
-}
-
-/*
- * ispif_try_format - Handle try format by pad subdev method
- * @ispif: ISPIF line
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad on which format is requested
- * @fmt: pointer to v4l2 format structure
- * @which: wanted subdev format
- */
-static void ispif_try_format(struct ispif_line *line,
-			     struct v4l2_subdev_pad_config *cfg,
-			     unsigned int pad,
-			     struct v4l2_mbus_framefmt *fmt,
-			     enum v4l2_subdev_format_whence which)
-{
-	unsigned int i;
-
-	switch (pad) {
-	case MSM_ISPIF_PAD_SINK:
-		/* Set format on sink pad */
-
-		for (i = 0; i < ARRAY_SIZE(ispif_formats); i++)
-			if (fmt->code == ispif_formats[i])
-				break;
-
-		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(ispif_formats))
-			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-
-		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
-		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
-
-		fmt->field = V4L2_FIELD_NONE;
-		fmt->colorspace = V4L2_COLORSPACE_SRGB;
-
-		break;
-
-	case MSM_ISPIF_PAD_SRC:
-		/* Set and return a format same as sink pad */
-
-		*fmt = *__ispif_get_format(line, cfg, MSM_ISPIF_PAD_SINK,
-					   which);
-
-		break;
-	}
-
-	fmt->colorspace = V4L2_COLORSPACE_SRGB;
-}
-
-/*
- * ispif_enum_mbus_code - Handle pixel format enumeration
- * @sd: ISPIF V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @code: pointer to v4l2_subdev_mbus_code_enum structure
- * return -EINVAL or zero on success
- */
-static int ispif_enum_mbus_code(struct v4l2_subdev *sd,
-				struct v4l2_subdev_pad_config *cfg,
-				struct v4l2_subdev_mbus_code_enum *code)
-{
-	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	if (code->pad == MSM_ISPIF_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(ispif_formats))
-			return -EINVAL;
-
-		code->code = ispif_formats[code->index];
-	} else {
-		if (code->index > 0)
-			return -EINVAL;
-
-		format = __ispif_get_format(line, cfg, MSM_ISPIF_PAD_SINK,
-					    code->which);
-
-		code->code = format->code;
-	}
-
-	return 0;
-}
-
-/*
- * ispif_enum_frame_size - Handle frame size enumeration
- * @sd: ISPIF V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fse: pointer to v4l2_subdev_frame_size_enum structure
- * return -EINVAL or zero on success
- */
-static int ispif_enum_frame_size(struct v4l2_subdev *sd,
-				 struct v4l2_subdev_pad_config *cfg,
-				 struct v4l2_subdev_frame_size_enum *fse)
-{
-	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt format;
-
-	if (fse->index != 0)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = 1;
-	format.height = 1;
-	ispif_try_format(line, cfg, fse->pad, &format, fse->which);
-	fse->min_width = format.width;
-	fse->min_height = format.height;
-
-	if (format.code != fse->code)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = -1;
-	format.height = -1;
-	ispif_try_format(line, cfg, fse->pad, &format, fse->which);
-	fse->max_width = format.width;
-	fse->max_height = format.height;
-
-	return 0;
-}
-
-/*
- * ispif_get_format - Handle get format by pads subdev method
- * @sd: ISPIF V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int ispif_get_format(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_pad_config *cfg,
-			    struct v4l2_subdev_format *fmt)
-{
-	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __ispif_get_format(line, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	fmt->format = *format;
-
-	return 0;
-}
-
-/*
- * ispif_set_format - Handle set format by pads subdev method
- * @sd: ISPIF V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int ispif_set_format(struct v4l2_subdev *sd,
-			    struct v4l2_subdev_pad_config *cfg,
-			    struct v4l2_subdev_format *fmt)
-{
-	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __ispif_get_format(line, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	ispif_try_format(line, cfg, fmt->pad, &fmt->format, fmt->which);
-	*format = fmt->format;
-
-	/* Propagate the format from sink to source */
-	if (fmt->pad == MSM_ISPIF_PAD_SINK) {
-		format = __ispif_get_format(line, cfg, MSM_ISPIF_PAD_SRC,
-					    fmt->which);
-
-		*format = fmt->format;
-		ispif_try_format(line, cfg, MSM_ISPIF_PAD_SRC, format,
-				 fmt->which);
-	}
-
-	return 0;
-}
-
-/*
- * ispif_init_formats - Initialize formats on all pads
- * @sd: ISPIF V4L2 subdevice
- * @fh: V4L2 subdev file handle
- *
- * Initialize all pad formats with default values.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int ispif_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
-{
-	struct v4l2_subdev_format format = {
-		.pad = MSM_ISPIF_PAD_SINK,
-		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
-			      V4L2_SUBDEV_FORMAT_ACTIVE,
-		.format = {
-			.code = MEDIA_BUS_FMT_UYVY8_2X8,
-			.width = 1920,
-			.height = 1080
-		}
-	};
-
-	return ispif_set_format(sd, fh ? fh->pad : NULL, &format);
-}
-
-/*
- * msm_ispif_subdev_init - Initialize ISPIF device structure and resources
- * @ispif: ISPIF device
- * @res: ISPIF module resources table
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_ispif_subdev_init(struct ispif_device *ispif,
-			  const struct resources_ispif *res)
-{
-	struct device *dev = to_device(ispif);
-	struct platform_device *pdev = to_platform_device(dev);
-	struct resource *r;
-	int i;
-	int ret;
-
-	/* Memory */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
-	ispif->base = devm_ioremap_resource(dev, r);
-	if (IS_ERR(ispif->base)) {
-		dev_err(dev, "could not map memory\n");
-		return PTR_ERR(ispif->base);
-	}
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[1]);
-	ispif->base_clk_mux = devm_ioremap_resource(dev, r);
-	if (IS_ERR(ispif->base_clk_mux)) {
-		dev_err(dev, "could not map memory\n");
-		return PTR_ERR(ispif->base_clk_mux);
-	}
-
-	/* Interrupt */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, res->interrupt);
-
-	if (!r) {
-		dev_err(dev, "missing IRQ\n");
-		return -EINVAL;
-	}
-
-	ispif->irq = r->start;
-	snprintf(ispif->irq_name, sizeof(ispif->irq_name), "%s_%s",
-		 dev_name(dev), MSM_ISPIF_NAME);
-	ret = devm_request_irq(dev, ispif->irq, ispif_isr,
-			       IRQF_TRIGGER_RISING, ispif->irq_name, ispif);
-	if (ret < 0) {
-		dev_err(dev, "request_irq failed: %d\n", ret);
-		return ret;
-	}
-
-	/* Clocks */
-
-	ispif->nclocks = 0;
-	while (res->clock[ispif->nclocks])
-		ispif->nclocks++;
-
-	ispif->clock = devm_kcalloc(dev,
-				    ispif->nclocks, sizeof(*ispif->clock),
-				    GFP_KERNEL);
-	if (!ispif->clock)
-		return -ENOMEM;
-
-	for (i = 0; i < ispif->nclocks; i++) {
-		struct camss_clock *clock = &ispif->clock[i];
-
-		clock->clk = devm_clk_get(dev, res->clock[i]);
-		if (IS_ERR(clock->clk))
-			return PTR_ERR(clock->clk);
-
-		clock->freq = NULL;
-		clock->nfreqs = 0;
-	}
-
-	ispif->nclocks_for_reset = 0;
-	while (res->clock_for_reset[ispif->nclocks_for_reset])
-		ispif->nclocks_for_reset++;
-
-	ispif->clock_for_reset = devm_kcalloc(dev,
-					      ispif->nclocks_for_reset,
-					      sizeof(*ispif->clock_for_reset),
-					      GFP_KERNEL);
-	if (!ispif->clock_for_reset)
-		return -ENOMEM;
-
-	for (i = 0; i < ispif->nclocks_for_reset; i++) {
-		struct camss_clock *clock = &ispif->clock_for_reset[i];
-
-		clock->clk = devm_clk_get(dev, res->clock_for_reset[i]);
-		if (IS_ERR(clock->clk))
-			return PTR_ERR(clock->clk);
-
-		clock->freq = NULL;
-		clock->nfreqs = 0;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++)
-		ispif->line[i].id = i;
-
-	mutex_init(&ispif->power_lock);
-	ispif->power_count = 0;
-
-	mutex_init(&ispif->config_lock);
-
-	init_completion(&ispif->reset_complete);
-
-	return 0;
-}
-
-/*
- * ispif_get_intf - Get ISPIF interface to use by VFE line id
- * @line_id: VFE line id that the ISPIF line is connected to
- *
- * Return ISPIF interface to use
- */
-static enum ispif_intf ispif_get_intf(enum vfe_line_id line_id)
-{
-	switch (line_id) {
-	case (VFE_LINE_RDI0):
-		return RDI0;
-	case (VFE_LINE_RDI1):
-		return RDI1;
-	case (VFE_LINE_RDI2):
-		return RDI2;
-	case (VFE_LINE_PIX):
-		return PIX0;
-	default:
-		return RDI0;
-	}
-}
-
-/*
- * ispif_link_setup - Setup ISPIF connections
- * @entity: Pointer to media entity structure
- * @local: Pointer to local pad
- * @remote: Pointer to remote pad
- * @flags: Link flags
- *
- * Return 0 on success
- */
-static int ispif_link_setup(struct media_entity *entity,
-			    const struct media_pad *local,
-			    const struct media_pad *remote, u32 flags)
-{
-	if (flags & MEDIA_LNK_FL_ENABLED) {
-		if (media_entity_remote_pad(local))
-			return -EBUSY;
-
-		if (local->flags & MEDIA_PAD_FL_SINK) {
-			struct v4l2_subdev *sd;
-			struct ispif_line *line;
-
-			sd = media_entity_to_v4l2_subdev(entity);
-			line = v4l2_get_subdevdata(sd);
-
-			msm_csid_get_csid_id(remote->entity, &line->csid_id);
-		} else { /* MEDIA_PAD_FL_SOURCE */
-			struct v4l2_subdev *sd;
-			struct ispif_line *line;
-			enum vfe_line_id id;
-
-			sd = media_entity_to_v4l2_subdev(entity);
-			line = v4l2_get_subdevdata(sd);
-
-			msm_vfe_get_vfe_id(remote->entity, &line->vfe_id);
-			msm_vfe_get_vfe_line_id(remote->entity, &id);
-			line->interface = ispif_get_intf(id);
-		}
-	}
-
-	return 0;
-}
-
-static const struct v4l2_subdev_core_ops ispif_core_ops = {
-	.s_power = ispif_set_power,
-};
-
-static const struct v4l2_subdev_video_ops ispif_video_ops = {
-	.s_stream = ispif_set_stream,
-};
-
-static const struct v4l2_subdev_pad_ops ispif_pad_ops = {
-	.enum_mbus_code = ispif_enum_mbus_code,
-	.enum_frame_size = ispif_enum_frame_size,
-	.get_fmt = ispif_get_format,
-	.set_fmt = ispif_set_format,
-};
-
-static const struct v4l2_subdev_ops ispif_v4l2_ops = {
-	.core = &ispif_core_ops,
-	.video = &ispif_video_ops,
-	.pad = &ispif_pad_ops,
-};
-
-static const struct v4l2_subdev_internal_ops ispif_v4l2_internal_ops = {
-	.open = ispif_init_formats,
-};
-
-static const struct media_entity_operations ispif_media_ops = {
-	.link_setup = ispif_link_setup,
-	.link_validate = v4l2_subdev_link_validate,
-};
-
-/*
- * msm_ispif_register_entities - Register subdev node for ISPIF module
- * @ispif: ISPIF device
- * @v4l2_dev: V4L2 device
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_ispif_register_entities(struct ispif_device *ispif,
-				struct v4l2_device *v4l2_dev)
-{
-	struct device *dev = to_device(ispif);
-	int ret;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
-		struct v4l2_subdev *sd = &ispif->line[i].subdev;
-		struct media_pad *pads = ispif->line[i].pads;
-
-		v4l2_subdev_init(sd, &ispif_v4l2_ops);
-		sd->internal_ops = &ispif_v4l2_internal_ops;
-		sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-		snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
-			 MSM_ISPIF_NAME, i);
-		v4l2_set_subdevdata(sd, &ispif->line[i]);
-
-		ret = ispif_init_formats(sd, NULL);
-		if (ret < 0) {
-			dev_err(dev, "Failed to init format: %d\n", ret);
-			goto error;
-		}
-
-		pads[MSM_ISPIF_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
-		pads[MSM_ISPIF_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
-
-		sd->entity.function = MEDIA_ENT_F_IO_V4L;
-		sd->entity.ops = &ispif_media_ops;
-		ret = media_entity_pads_init(&sd->entity, MSM_ISPIF_PADS_NUM,
-					     pads);
-		if (ret < 0) {
-			dev_err(dev, "Failed to init media entity: %d\n", ret);
-			goto error;
-		}
-
-		ret = v4l2_device_register_subdev(v4l2_dev, sd);
-		if (ret < 0) {
-			dev_err(dev, "Failed to register subdev: %d\n", ret);
-			media_entity_cleanup(&sd->entity);
-			goto error;
-		}
-	}
-
-	return 0;
-
-error:
-	for (i--; i >= 0; i--) {
-		struct v4l2_subdev *sd = &ispif->line[i].subdev;
-
-		v4l2_device_unregister_subdev(sd);
-		media_entity_cleanup(&sd->entity);
-	}
-
-	return ret;
-}
-
-/*
- * msm_ispif_unregister_entities - Unregister ISPIF module subdev node
- * @ispif: ISPIF device
- */
-void msm_ispif_unregister_entities(struct ispif_device *ispif)
-{
-	int i;
-
-	mutex_destroy(&ispif->power_lock);
-	mutex_destroy(&ispif->config_lock);
-
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
-		struct v4l2_subdev *sd = &ispif->line[i].subdev;
-
-		v4l2_device_unregister_subdev(sd);
-		media_entity_cleanup(&sd->entity);
-	}
-}
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-ispif.h b/drivers/media/platform/qcom/camss-8x16/camss-ispif.h
deleted file mode 100644
index f668306020c3..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-ispif.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * camss-ispif.h
- *
- * Qualcomm MSM Camera Subsystem - ISPIF (ISP Interface) Module
- *
- * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef QC_MSM_CAMSS_ISPIF_H
-#define QC_MSM_CAMSS_ISPIF_H
-
-#include <linux/clk.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-
-/* Number of ISPIF lines - same as number of CSID hardware modules */
-#define MSM_ISPIF_LINE_NUM 2
-
-#define MSM_ISPIF_PAD_SINK 0
-#define MSM_ISPIF_PAD_SRC 1
-#define MSM_ISPIF_PADS_NUM 2
-
-#define MSM_ISPIF_VFE_NUM 1
-
-enum ispif_intf {
-	PIX0,
-	RDI0,
-	PIX1,
-	RDI1,
-	RDI2
-};
-
-struct ispif_intf_cmd_reg {
-	u32 cmd_0;
-	u32 cmd_1;
-};
-
-struct ispif_line {
-	u8 id;
-	u8 csid_id;
-	u8 vfe_id;
-	enum ispif_intf interface;
-	struct v4l2_subdev subdev;
-	struct media_pad pads[MSM_ISPIF_PADS_NUM];
-	struct v4l2_mbus_framefmt fmt[MSM_ISPIF_PADS_NUM];
-};
-
-struct ispif_device {
-	void __iomem *base;
-	void __iomem *base_clk_mux;
-	u32 irq;
-	char irq_name[30];
-	struct camss_clock *clock;
-	int nclocks;
-	struct camss_clock  *clock_for_reset;
-	int nclocks_for_reset;
-	struct completion reset_complete;
-	int power_count;
-	struct mutex power_lock;
-	struct ispif_intf_cmd_reg intf_cmd[MSM_ISPIF_VFE_NUM];
-	struct mutex config_lock;
-	struct ispif_line line[MSM_ISPIF_LINE_NUM];
-};
-
-struct resources_ispif;
-
-int msm_ispif_subdev_init(struct ispif_device *ispif,
-			  const struct resources_ispif *res);
-
-int msm_ispif_register_entities(struct ispif_device *ispif,
-				struct v4l2_device *v4l2_dev);
-
-void msm_ispif_unregister_entities(struct ispif_device *ispif);
-
-#endif /* QC_MSM_CAMSS_ISPIF_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c b/drivers/media/platform/qcom/camss-8x16/camss-vfe.c
deleted file mode 100644
index a6329a8a7c4a..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-vfe.c
+++ /dev/null
@@ -1,3093 +0,0 @@
-/*
- * camss-vfe.c
- *
- * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module
- *
- * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/clk.h>
-#include <linux/completion.h>
-#include <linux/interrupt.h>
-#include <linux/iommu.h>
-#include <linux/iopoll.h>
-#include <linux/mutex.h>
-#include <linux/of.h>
-#include <linux/platform_device.h>
-#include <linux/spinlock_types.h>
-#include <linux/spinlock.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-
-#include "camss-vfe.h"
-#include "camss.h"
-
-#define MSM_VFE_NAME "msm_vfe"
-
-#define vfe_line_array(ptr_line)	\
-	((const struct vfe_line (*)[]) &(ptr_line[-(ptr_line->id)]))
-
-#define to_vfe(ptr_line)	\
-	container_of(vfe_line_array(ptr_line), struct vfe_device, ptr_line)
-
-#define VFE_0_HW_VERSION		0x000
-
-#define VFE_0_GLOBAL_RESET_CMD		0x00c
-#define VFE_0_GLOBAL_RESET_CMD_CORE	(1 << 0)
-#define VFE_0_GLOBAL_RESET_CMD_CAMIF	(1 << 1)
-#define VFE_0_GLOBAL_RESET_CMD_BUS	(1 << 2)
-#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	(1 << 3)
-#define VFE_0_GLOBAL_RESET_CMD_REGISTER	(1 << 4)
-#define VFE_0_GLOBAL_RESET_CMD_TIMER	(1 << 5)
-#define VFE_0_GLOBAL_RESET_CMD_PM	(1 << 6)
-#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	(1 << 7)
-#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	(1 << 8)
-
-#define VFE_0_MODULE_CFG		0x018
-#define VFE_0_MODULE_CFG_DEMUX			(1 << 2)
-#define VFE_0_MODULE_CFG_CHROMA_UPSAMPLE	(1 << 3)
-#define VFE_0_MODULE_CFG_SCALE_ENC		(1 << 23)
-#define VFE_0_MODULE_CFG_CROP_ENC		(1 << 27)
-
-#define VFE_0_CORE_CFG			0x01c
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
-
-#define VFE_0_IRQ_CMD			0x024
-#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	(1 << 0)
-
-#define VFE_0_IRQ_MASK_0		0x028
-#define VFE_0_IRQ_MASK_0_CAMIF_SOF			(1 << 0)
-#define VFE_0_IRQ_MASK_0_CAMIF_EOF			(1 << 1)
-#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
-#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
-	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
-#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
-#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
-#define VFE_0_IRQ_MASK_0_RESET_ACK			(1 << 31)
-#define VFE_0_IRQ_MASK_1		0x02c
-#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			(1 << 0)
-#define VFE_0_IRQ_MASK_1_VIOLATION			(1 << 7)
-#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		(1 << 8)
-#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	(1 << ((n) + 9))
-#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			(1 << ((n) + 29))
-
-#define VFE_0_IRQ_CLEAR_0		0x030
-#define VFE_0_IRQ_CLEAR_1		0x034
-
-#define VFE_0_IRQ_STATUS_0		0x038
-#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			(1 << 0)
-#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
-#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
-	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
-#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
-#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
-#define VFE_0_IRQ_STATUS_0_RESET_ACK			(1 << 31)
-#define VFE_0_IRQ_STATUS_1		0x03c
-#define VFE_0_IRQ_STATUS_1_VIOLATION			(1 << 7)
-#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		(1 << 8)
-#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			(1 << ((n) + 29))
-
-#define VFE_0_IRQ_COMPOSITE_MASK_0	0x40
-#define VFE_0_VIOLATION_STATUS		0x48
-
-#define VFE_0_BUS_CMD			0x4c
-#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	(1 << (x))
-
-#define VFE_0_BUS_CFG			0x050
-
-#define VFE_0_BUS_XBAR_CFG_x(x)		(0x58 + 0x4 * ((x) / 2))
-#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			(1 << 1)
-#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	5
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	6
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	7
-
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x06c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT	1
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x070 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x074 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x078 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1F << 2)
-
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x07c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x080 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x084 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
-							(0x088 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
-							(0x08c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
-
-#define VFE_0_BUS_PING_PONG_STATUS	0x268
-
-#define VFE_0_BUS_BDG_CMD		0x2c0
-#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
-
-#define VFE_0_BUS_BDG_QOS_CFG_0		0x2c4
-#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa5aaa5
-#define VFE_0_BUS_BDG_QOS_CFG_1		0x2c8
-#define VFE_0_BUS_BDG_QOS_CFG_2		0x2cc
-#define VFE_0_BUS_BDG_QOS_CFG_3		0x2d0
-#define VFE_0_BUS_BDG_QOS_CFG_4		0x2d4
-#define VFE_0_BUS_BDG_QOS_CFG_5		0x2d8
-#define VFE_0_BUS_BDG_QOS_CFG_6		0x2dc
-#define VFE_0_BUS_BDG_QOS_CFG_7		0x2e0
-#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa5
-
-#define VFE_0_RDI_CFG_x(x)		(0x2e8 + (0x4 * (x)))
-#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
-#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
-#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
-#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
-#define VFE_0_RDI_CFG_x_RDI_EN_BIT		(1 << 2)
-#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
-#define VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(r)	(1 << (16 + (r)))
-
-#define VFE_0_CAMIF_CMD				0x2f4
-#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
-#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
-#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	(1 << 2)
-#define VFE_0_CAMIF_CFG				0x2f8
-#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		(1 << 6)
-#define VFE_0_CAMIF_FRAME_CFG			0x300
-#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x304
-#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x308
-#define VFE_0_CAMIF_SUBSAMPLE_CFG_0		0x30c
-#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x314
-#define VFE_0_CAMIF_STATUS			0x31c
-#define VFE_0_CAMIF_STATUS_HALT			(1 << 31)
-
-#define VFE_0_REG_UPDATE			0x378
-#define VFE_0_REG_UPDATE_RDIn(n)		(1 << (1 + (n)))
-#define VFE_0_REG_UPDATE_line_n(n)		\
-			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
-
-#define VFE_0_DEMUX_CFG				0x424
-#define VFE_0_DEMUX_CFG_PERIOD			0x3
-#define VFE_0_DEMUX_GAIN_0			0x428
-#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
-#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
-#define VFE_0_DEMUX_GAIN_1			0x42c
-#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
-#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
-#define VFE_0_DEMUX_EVEN_CFG			0x438
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
-#define VFE_0_DEMUX_ODD_CFG			0x43c
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
-
-#define VFE_0_SCALE_ENC_Y_CFG			0x75c
-#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x760
-#define VFE_0_SCALE_ENC_Y_H_PHASE		0x764
-#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x76c
-#define VFE_0_SCALE_ENC_Y_V_PHASE		0x770
-#define VFE_0_SCALE_ENC_CBCR_CFG		0x778
-#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x77c
-#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x780
-#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x790
-#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x794
-
-#define VFE_0_CROP_ENC_Y_WIDTH			0x854
-#define VFE_0_CROP_ENC_Y_HEIGHT			0x858
-#define VFE_0_CROP_ENC_CBCR_WIDTH		0x85c
-#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x860
-
-#define VFE_0_CLAMP_ENC_MAX_CFG			0x874
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
-#define VFE_0_CLAMP_ENC_MIN_CFG			0x878
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
-
-#define VFE_0_CGC_OVERRIDE_1			0x974
-#define VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(x)	(1 << (x))
-
-/* VFE reset timeout */
-#define VFE_RESET_TIMEOUT_MS 50
-/* VFE halt timeout */
-#define VFE_HALT_TIMEOUT_MS 100
-/* Max number of frame drop updates per frame */
-#define VFE_FRAME_DROP_UPDATES 5
-/* Frame drop value. NOTE: VAL + UPDATES should not exceed 31 */
-#define VFE_FRAME_DROP_VAL 20
-
-#define VFE_NEXT_SOF_MS 500
-
-#define CAMIF_TIMEOUT_SLEEP_US 1000
-#define CAMIF_TIMEOUT_ALL_US 1000000
-
-#define SCALER_RATIO_MAX 16
-
-static const struct {
-	u32 code;
-	u8 bpp;
-} vfe_formats[] = {
-	{
-		MEDIA_BUS_FMT_UYVY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_VYUY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YUYV8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YVYU8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB12_1X12,
-		12,
-	}
-};
-
-/*
- * vfe_get_bpp - map media bus format to bits per pixel
- * @code: media bus format code
- *
- * Return number of bits per pixel
- */
-static u8 vfe_get_bpp(u32 code)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
-		if (code == vfe_formats[i].code)
-			return vfe_formats[i].bpp;
-
-	WARN(1, "Unknown format\n");
-
-	return vfe_formats[0].bpp;
-}
-
-static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
-{
-	u32 bits = readl_relaxed(vfe->base + reg);
-
-	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
-}
-
-static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
-{
-	u32 bits = readl_relaxed(vfe->base + reg);
-
-	writel_relaxed(bits | set_bits, vfe->base + reg);
-}
-
-static void vfe_global_reset(struct vfe_device *vfe)
-{
-	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
-			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
-			 VFE_0_GLOBAL_RESET_CMD_PM		|
-			 VFE_0_GLOBAL_RESET_CMD_TIMER		|
-			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
-			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
-			 VFE_0_GLOBAL_RESET_CMD_BUS		|
-			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
-			 VFE_0_GLOBAL_RESET_CMD_CORE;
-
-	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
-}
-
-static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
-	else
-		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
-}
-
-static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
-	else
-		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
-}
-
-#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
-
-static int vfe_word_per_line(uint32_t format, uint32_t pixel_per_line)
-{
-	int val = 0;
-
-	switch (format) {
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		val = CALC_WORD(pixel_per_line, 1, 8);
-		break;
-	case V4L2_PIX_FMT_YUYV:
-	case V4L2_PIX_FMT_YVYU:
-	case V4L2_PIX_FMT_UYVY:
-	case V4L2_PIX_FMT_VYUY:
-		val = CALC_WORD(pixel_per_line, 2, 8);
-		break;
-	}
-
-	return val;
-}
-
-static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
-			     u16 *width, u16 *height, u16 *bytesperline)
-{
-	switch (pix->pixelformat) {
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-		*width = pix->width;
-		*height = pix->height;
-		*bytesperline = pix->plane_fmt[0].bytesperline;
-		if (plane == 1)
-			*height /= 2;
-		break;
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		*width = pix->width;
-		*height = pix->height;
-		*bytesperline = pix->plane_fmt[0].bytesperline;
-		break;
-	}
-}
-
-static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
-			      struct v4l2_pix_format_mplane *pix,
-			      u8 plane, u32 enable)
-{
-	u32 reg;
-
-	if (enable) {
-		u16 width = 0, height = 0, bytesperline = 0, wpl;
-
-		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
-
-		wpl = vfe_word_per_line(pix->pixelformat, width);
-
-		reg = height - 1;
-		reg |= ((wpl + 1) / 2 - 1) << 16;
-
-		writel_relaxed(reg, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
-
-		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
-
-		reg = 0x3;
-		reg |= (height - 1) << 4;
-		reg |= wpl << 16;
-
-		writel_relaxed(reg, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
-	} else {
-		writel_relaxed(0, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
-		writel_relaxed(0, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
-	}
-}
-
-static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
-{
-	u32 reg;
-
-	reg = readl_relaxed(vfe->base +
-			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
-
-	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
-
-	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
-		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
-
-	writel_relaxed(reg,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
-}
-
-static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
-					 u32 pattern)
-{
-	writel_relaxed(pattern,
-	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
-}
-
-static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm, u16 offset,
-			      u16 depth)
-{
-	u32 reg;
-
-	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
-		depth;
-	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
-}
-
-static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
-{
-	wmb();
-	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
-	wmb();
-}
-
-static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
-{
-	writel_relaxed(addr,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
-}
-
-static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
-{
-	writel_relaxed(addr,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
-}
-
-static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
-{
-	u32 reg;
-
-	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
-
-	return (reg >> wm) & 0x1;
-}
-
-static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
-{
-	if (enable)
-		writel_relaxed(0x10000009, vfe->base + VFE_0_BUS_CFG);
-	else
-		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
-}
-
-static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
-				      enum vfe_line_id id)
-{
-	u32 reg;
-
-	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
-	reg |= VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
-
-	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
-	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
-		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
-
-	switch (id) {
-	case VFE_LINE_RDI0:
-	default:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI1:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI2:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	}
-
-	if (wm % 2 == 1)
-		reg <<= 16;
-
-	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
-}
-
-static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
-{
-	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
-	       vfe->base +
-	       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
-}
-
-static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
-					   enum vfe_line_id id)
-{
-	u32 reg;
-
-	reg = VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(0), reg);
-
-	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
-
-	switch (id) {
-	case VFE_LINE_RDI0:
-	default:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI1:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI2:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	}
-
-	if (wm % 2 == 1)
-		reg <<= 16;
-
-	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
-}
-
-static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
-			     u8 enable)
-{
-	struct vfe_line *line = container_of(output, struct vfe_line, output);
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	unsigned int i;
-
-	for (i = 0; i < output->wm_num; i++) {
-		if (i == 0) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
-				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		} else if (i == 1) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
-			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
-				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
-		} else {
-			/* On current devices output->wm_num is always <= 2 */
-			break;
-		}
-
-		if (output->wm_idx[i] % 2 == 1)
-			reg <<= 16;
-
-		if (enable)
-			vfe_reg_set(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
-				    reg);
-		else
-			vfe_reg_clr(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
-				    reg);
-	}
-}
-
-static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
-{
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
-		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
-
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
-		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
-}
-
-static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
-{
-	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
-	wmb();
-	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
-	wmb();
-}
-
-static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
-				   enum vfe_line_id line_id, u8 enable)
-{
-	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
-		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
-	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
-		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
-
-	if (enable) {
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-	} else {
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-	}
-}
-
-static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
-				    enum vfe_line_id line_id, u8 enable)
-{
-	struct vfe_output *output = &vfe->line[line_id].output;
-	unsigned int i;
-	u32 irq_en0;
-	u32 irq_en1;
-	u32 comp_mask = 0;
-
-	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
-	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
-	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
-	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
-	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
-	for (i = 0; i < output->wm_num; i++) {
-		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
-							output->wm_idx[i]);
-		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
-	}
-
-	if (enable) {
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
-	} else {
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
-	}
-}
-
-static void vfe_enable_irq_common(struct vfe_device *vfe)
-{
-	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
-	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
-		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
-
-	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-}
-
-static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 val, even_cfg, odd_cfg;
-
-	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
-
-	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
-	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
-
-	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
-	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
-
-	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
-	case MEDIA_BUS_FMT_YUYV8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
-		break;
-	case MEDIA_BUS_FMT_YVYU8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
-		break;
-	case MEDIA_BUS_FMT_UYVY8_2X8:
-	default:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
-		break;
-	case MEDIA_BUS_FMT_VYUY8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
-		break;
-	}
-
-	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
-	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
-}
-
-static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
-{
-	if (input / output >= 16)
-		return 0;
-
-	if (input / output >= 8)
-		return 1;
-
-	if (input / output >= 4)
-		return 2;
-
-	return 3;
-}
-
-static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	u16 input, output;
-	u8 interp_reso;
-	u32 phase_mult;
-
-	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].width;
-	output = line->compose.width;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].height;
-	output = line->compose.height;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
-
-	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].width;
-	output = line->compose.width / 2;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].height;
-	output = line->compose.height;
-	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
-		output = line->compose.height / 2;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
-}
-
-static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	u16 first, last;
-
-	first = line->crop.left;
-	last = line->crop.left + line->crop.width - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
-
-	first = line->crop.top;
-	last = line->crop.top + line->crop.height - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
-
-	first = line->crop.left / 2;
-	last = line->crop.left / 2 + line->crop.width / 2 - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
-
-	first = line->crop.top;
-	last = line->crop.top + line->crop.height - 1;
-	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
-		first = line->crop.top / 2;
-		last = line->crop.top / 2 + line->crop.height / 2 - 1;
-	}
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
-}
-
-static void vfe_set_clamp_cfg(struct vfe_device *vfe)
-{
-	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
-		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
-		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
-
-	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
-
-	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
-		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
-		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
-
-	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
-}
-
-/*
- * vfe_reset - Trigger reset on VFE module and wait to complete
- * @vfe: VFE device
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_reset(struct vfe_device *vfe)
-{
-	unsigned long time;
-
-	reinit_completion(&vfe->reset_complete);
-
-	vfe_global_reset(vfe);
-
-	time = wait_for_completion_timeout(&vfe->reset_complete,
-		msecs_to_jiffies(VFE_RESET_TIMEOUT_MS));
-	if (!time) {
-		dev_err(to_device(vfe), "VFE reset timeout\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-/*
- * vfe_halt - Trigger halt on VFE module and wait to complete
- * @vfe: VFE device
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_halt(struct vfe_device *vfe)
-{
-	unsigned long time;
-
-	reinit_completion(&vfe->halt_complete);
-
-	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
-		       vfe->base + VFE_0_BUS_BDG_CMD);
-
-	time = wait_for_completion_timeout(&vfe->halt_complete,
-		msecs_to_jiffies(VFE_HALT_TIMEOUT_MS));
-	if (!time) {
-		dev_err(to_device(vfe), "VFE halt timeout\n");
-		return -EIO;
-	}
-
-	return 0;
-}
-
-static void vfe_init_outputs(struct vfe_device *vfe)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(vfe->line); i++) {
-		struct vfe_output *output = &vfe->line[i].output;
-
-		output->state = VFE_OUTPUT_OFF;
-		output->buf[0] = NULL;
-		output->buf[1] = NULL;
-		INIT_LIST_HEAD(&output->pending_bufs);
-
-		output->wm_num = 1;
-		if (vfe->line[i].id == VFE_LINE_PIX)
-			output->wm_num = 2;
-	}
-}
-
-static void vfe_reset_output_maps(struct vfe_device *vfe)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(vfe->wm_output_map); i++)
-		vfe->wm_output_map[i] = VFE_LINE_NONE;
-}
-
-static void vfe_set_qos(struct vfe_device *vfe)
-{
-	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
-	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
-
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
-	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
-}
-
-static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	u32 val = VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(wm);
-
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_CGC_OVERRIDE_1, val);
-	else
-		vfe_reg_clr(vfe, VFE_0_CGC_OVERRIDE_1, val);
-
-	wmb();
-}
-
-static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
-{
-	u32 val = VFE_0_MODULE_CFG_DEMUX |
-		  VFE_0_MODULE_CFG_CHROMA_UPSAMPLE |
-		  VFE_0_MODULE_CFG_SCALE_ENC |
-		  VFE_0_MODULE_CFG_CROP_ENC;
-
-	if (enable)
-		writel_relaxed(val, vfe->base + VFE_0_MODULE_CFG);
-	else
-		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_CFG);
-}
-
-static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 val;
-
-	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
-	case MEDIA_BUS_FMT_YUYV8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
-		break;
-	case MEDIA_BUS_FMT_YVYU8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
-		break;
-	case MEDIA_BUS_FMT_UYVY8_2X8:
-	default:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
-		break;
-	case MEDIA_BUS_FMT_VYUY8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
-		break;
-	}
-
-	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].width * 2;
-	val |= line->fmt[MSM_VFE_PAD_SINK].height << 16;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
-
-	val = 0xffffffff;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG_0);
-
-	val = 0xffffffff;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
-
-	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
-
-	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
-}
-
-static void vfe_set_camif_cmd(struct vfe_device *vfe, u32 cmd)
-{
-	writel_relaxed(VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS,
-		       vfe->base + VFE_0_CAMIF_CMD);
-
-	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
-}
-
-static int vfe_camif_wait_for_stop(struct vfe_device *vfe)
-{
-	u32 val;
-	int ret;
-
-	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
-				 val,
-				 (val & VFE_0_CAMIF_STATUS_HALT),
-				 CAMIF_TIMEOUT_SLEEP_US,
-				 CAMIF_TIMEOUT_ALL_US);
-	if (ret < 0)
-		dev_err(to_device(vfe), "%s: camif stop timeout\n", __func__);
-
-	return ret;
-}
-
-static void vfe_output_init_addrs(struct vfe_device *vfe,
-				  struct vfe_output *output, u8 sync)
-{
-	u32 ping_addr;
-	u32 pong_addr;
-	unsigned int i;
-
-	output->active_buf = 0;
-
-	for (i = 0; i < output->wm_num; i++) {
-		if (output->buf[0])
-			ping_addr = output->buf[0]->addr[i];
-		else
-			ping_addr = 0;
-
-		if (output->buf[1])
-			pong_addr = output->buf[1]->addr[i];
-		else
-			pong_addr = ping_addr;
-
-		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], ping_addr);
-		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], pong_addr);
-		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
-	}
-}
-
-static void vfe_output_update_ping_addr(struct vfe_device *vfe,
-					struct vfe_output *output, u8 sync)
-{
-	u32 addr;
-	unsigned int i;
-
-	for (i = 0; i < output->wm_num; i++) {
-		if (output->buf[0])
-			addr = output->buf[0]->addr[i];
-		else
-			addr = 0;
-
-		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], addr);
-		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
-	}
-}
-
-static void vfe_output_update_pong_addr(struct vfe_device *vfe,
-					struct vfe_output *output, u8 sync)
-{
-	u32 addr;
-	unsigned int i;
-
-	for (i = 0; i < output->wm_num; i++) {
-		if (output->buf[1])
-			addr = output->buf[1]->addr[i];
-		else
-			addr = 0;
-
-		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], addr);
-		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
-	}
-
-}
-
-static int vfe_reserve_wm(struct vfe_device *vfe, enum vfe_line_id line_id)
-{
-	int ret = -EBUSY;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(vfe->wm_output_map); i++) {
-		if (vfe->wm_output_map[i] == VFE_LINE_NONE) {
-			vfe->wm_output_map[i] = line_id;
-			ret = i;
-			break;
-		}
-	}
-
-	return ret;
-}
-
-static int vfe_release_wm(struct vfe_device *vfe, u8 wm)
-{
-	if (wm >= ARRAY_SIZE(vfe->wm_output_map))
-		return -EINVAL;
-
-	vfe->wm_output_map[wm] = VFE_LINE_NONE;
-
-	return 0;
-}
-
-static void vfe_output_frame_drop(struct vfe_device *vfe,
-				  struct vfe_output *output,
-				  u32 drop_pattern)
-{
-	u8 drop_period;
-	unsigned int i;
-
-	/* We need to toggle update period to be valid on next frame */
-	output->drop_update_idx++;
-	output->drop_update_idx %= VFE_FRAME_DROP_UPDATES;
-	drop_period = VFE_FRAME_DROP_VAL + output->drop_update_idx;
-
-	for (i = 0; i < output->wm_num; i++) {
-		vfe_wm_set_framedrop_period(vfe, output->wm_idx[i],
-					    drop_period);
-		vfe_wm_set_framedrop_pattern(vfe, output->wm_idx[i],
-					     drop_pattern);
-	}
-	vfe_reg_update(vfe, container_of(output, struct vfe_line, output)->id);
-}
-
-static struct camss_buffer *vfe_buf_get_pending(struct vfe_output *output)
-{
-	struct camss_buffer *buffer = NULL;
-
-	if (!list_empty(&output->pending_bufs)) {
-		buffer = list_first_entry(&output->pending_bufs,
-					  struct camss_buffer,
-					  queue);
-		list_del(&buffer->queue);
-	}
-
-	return buffer;
-}
-
-/*
- * vfe_buf_add_pending - Add output buffer to list of pending
- * @output: VFE output
- * @buffer: Video buffer
- */
-static void vfe_buf_add_pending(struct vfe_output *output,
-				struct camss_buffer *buffer)
-{
-	INIT_LIST_HEAD(&buffer->queue);
-	list_add_tail(&buffer->queue, &output->pending_bufs);
-}
-
-/*
- * vfe_buf_flush_pending - Flush all pending buffers.
- * @output: VFE output
- * @state: vb2 buffer state
- */
-static void vfe_buf_flush_pending(struct vfe_output *output,
-				  enum vb2_buffer_state state)
-{
-	struct camss_buffer *buf;
-	struct camss_buffer *t;
-
-	list_for_each_entry_safe(buf, t, &output->pending_bufs, queue) {
-		vb2_buffer_done(&buf->vb.vb2_buf, state);
-		list_del(&buf->queue);
-	}
-}
-
-static void vfe_buf_update_wm_on_next(struct vfe_device *vfe,
-				      struct vfe_output *output)
-{
-	switch (output->state) {
-	case VFE_OUTPUT_CONTINUOUS:
-		vfe_output_frame_drop(vfe, output, 3);
-		break;
-	case VFE_OUTPUT_SINGLE:
-	default:
-		dev_err_ratelimited(to_device(vfe),
-				    "Next buf in wrong state! %d\n",
-				    output->state);
-		break;
-	}
-}
-
-static void vfe_buf_update_wm_on_last(struct vfe_device *vfe,
-				      struct vfe_output *output)
-{
-	switch (output->state) {
-	case VFE_OUTPUT_CONTINUOUS:
-		output->state = VFE_OUTPUT_SINGLE;
-		vfe_output_frame_drop(vfe, output, 1);
-		break;
-	case VFE_OUTPUT_SINGLE:
-		output->state = VFE_OUTPUT_STOPPING;
-		vfe_output_frame_drop(vfe, output, 0);
-		break;
-	default:
-		dev_err_ratelimited(to_device(vfe),
-				    "Last buff in wrong state! %d\n",
-				    output->state);
-		break;
-	}
-}
-
-static void vfe_buf_update_wm_on_new(struct vfe_device *vfe,
-				     struct vfe_output *output,
-				     struct camss_buffer *new_buf)
-{
-	int inactive_idx;
-
-	switch (output->state) {
-	case VFE_OUTPUT_SINGLE:
-		inactive_idx = !output->active_buf;
-
-		if (!output->buf[inactive_idx]) {
-			output->buf[inactive_idx] = new_buf;
-
-			if (inactive_idx)
-				vfe_output_update_pong_addr(vfe, output, 0);
-			else
-				vfe_output_update_ping_addr(vfe, output, 0);
-
-			vfe_output_frame_drop(vfe, output, 3);
-			output->state = VFE_OUTPUT_CONTINUOUS;
-		} else {
-			vfe_buf_add_pending(output, new_buf);
-			dev_err_ratelimited(to_device(vfe),
-					    "Inactive buffer is busy\n");
-		}
-		break;
-
-	case VFE_OUTPUT_IDLE:
-		if (!output->buf[0]) {
-			output->buf[0] = new_buf;
-
-			vfe_output_init_addrs(vfe, output, 1);
-
-			vfe_output_frame_drop(vfe, output, 1);
-			output->state = VFE_OUTPUT_SINGLE;
-		} else {
-			vfe_buf_add_pending(output, new_buf);
-			dev_err_ratelimited(to_device(vfe),
-					    "Output idle with buffer set!\n");
-		}
-		break;
-
-	case VFE_OUTPUT_CONTINUOUS:
-	default:
-		vfe_buf_add_pending(output, new_buf);
-		break;
-	}
-}
-
-static int vfe_get_output(struct vfe_line *line)
-{
-	struct vfe_device *vfe = to_vfe(line);
-	struct vfe_output *output;
-	unsigned long flags;
-	int i;
-	int wm_idx;
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	output = &line->output;
-	if (output->state != VFE_OUTPUT_OFF) {
-		dev_err(to_device(vfe), "Output is running\n");
-		goto error;
-	}
-	output->state = VFE_OUTPUT_RESERVED;
-
-	output->active_buf = 0;
-
-	for (i = 0; i < output->wm_num; i++) {
-		wm_idx = vfe_reserve_wm(vfe, line->id);
-		if (wm_idx < 0) {
-			dev_err(to_device(vfe), "Can not reserve wm\n");
-			goto error_get_wm;
-		}
-		output->wm_idx[i] = wm_idx;
-	}
-
-	output->drop_update_idx = 0;
-
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	return 0;
-
-error_get_wm:
-	for (i--; i >= 0; i--)
-		vfe_release_wm(vfe, output->wm_idx[i]);
-	output->state = VFE_OUTPUT_OFF;
-error:
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	return -EINVAL;
-}
-
-static int vfe_put_output(struct vfe_line *line)
-{
-	struct vfe_device *vfe = to_vfe(line);
-	struct vfe_output *output = &line->output;
-	unsigned long flags;
-	unsigned int i;
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	for (i = 0; i < output->wm_num; i++)
-		vfe_release_wm(vfe, output->wm_idx[i]);
-
-	output->state = VFE_OUTPUT_OFF;
-
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-	return 0;
-}
-
-static int vfe_enable_output(struct vfe_line *line)
-{
-	struct vfe_device *vfe = to_vfe(line);
-	struct vfe_output *output = &line->output;
-	unsigned long flags;
-	unsigned int i;
-	u16 ub_size;
-
-	switch (vfe->id) {
-	case 0:
-		ub_size = MSM_VFE_VFE0_UB_SIZE_RDI;
-		break;
-	case 1:
-		ub_size = MSM_VFE_VFE1_UB_SIZE_RDI;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line->id);
-
-	if (output->state != VFE_OUTPUT_RESERVED) {
-		dev_err(to_device(vfe), "Output is not in reserved state %d\n",
-			output->state);
-		spin_unlock_irqrestore(&vfe->output_lock, flags);
-		return -EINVAL;
-	}
-	output->state = VFE_OUTPUT_IDLE;
-
-	output->buf[0] = vfe_buf_get_pending(output);
-	output->buf[1] = vfe_buf_get_pending(output);
-
-	if (!output->buf[0] && output->buf[1]) {
-		output->buf[0] = output->buf[1];
-		output->buf[1] = NULL;
-	}
-
-	if (output->buf[0])
-		output->state = VFE_OUTPUT_SINGLE;
-
-	if (output->buf[1])
-		output->state = VFE_OUTPUT_CONTINUOUS;
-
-	switch (output->state) {
-	case VFE_OUTPUT_SINGLE:
-		vfe_output_frame_drop(vfe, output, 1);
-		break;
-	case VFE_OUTPUT_CONTINUOUS:
-		vfe_output_frame_drop(vfe, output, 3);
-		break;
-	default:
-		vfe_output_frame_drop(vfe, output, 0);
-		break;
-	}
-
-	output->sequence = 0;
-	output->wait_sof = 0;
-	output->wait_reg_update = 0;
-	reinit_completion(&output->sof);
-	reinit_completion(&output->reg_update);
-
-	vfe_output_init_addrs(vfe, output, 0);
-
-	if (line->id != VFE_LINE_PIX) {
-		vfe_set_cgc_override(vfe, output->wm_idx[0], 1);
-		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 1);
-		vfe_bus_connect_wm_to_rdi(vfe, output->wm_idx[0], line->id);
-		vfe_wm_set_subsample(vfe, output->wm_idx[0]);
-		vfe_set_rdi_cid(vfe, line->id, 0);
-		vfe_wm_set_ub_cfg(vfe, output->wm_idx[0],
-				  (ub_size + 1) * output->wm_idx[0], ub_size);
-		vfe_wm_frame_based(vfe, output->wm_idx[0], 1);
-		vfe_wm_enable(vfe, output->wm_idx[0], 1);
-		vfe_bus_reload_wm(vfe, output->wm_idx[0]);
-	} else {
-		ub_size /= output->wm_num;
-		for (i = 0; i < output->wm_num; i++) {
-			vfe_set_cgc_override(vfe, output->wm_idx[i], 1);
-			vfe_wm_set_subsample(vfe, output->wm_idx[i]);
-			vfe_wm_set_ub_cfg(vfe, output->wm_idx[i],
-					  (ub_size + 1) * output->wm_idx[i],
-					  ub_size);
-			vfe_wm_line_based(vfe, output->wm_idx[i],
-					&line->video_out.active_fmt.fmt.pix_mp,
-					i, 1);
-			vfe_wm_enable(vfe, output->wm_idx[i], 1);
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
-		}
-		vfe_enable_irq_pix_line(vfe, 0, line->id, 1);
-		vfe_set_module_cfg(vfe, 1);
-		vfe_set_camif_cfg(vfe, line);
-		vfe_set_xbar_cfg(vfe, output, 1);
-		vfe_set_demux_cfg(vfe, line);
-		vfe_set_scale_cfg(vfe, line);
-		vfe_set_crop_cfg(vfe, line);
-		vfe_set_clamp_cfg(vfe);
-		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY);
-	}
-
-	vfe_reg_update(vfe, line->id);
-
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	return 0;
-}
-
-static int vfe_disable_output(struct vfe_line *line)
-{
-	struct vfe_device *vfe = to_vfe(line);
-	struct vfe_output *output = &line->output;
-	unsigned long flags;
-	unsigned long time;
-	unsigned int i;
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	output->wait_sof = 1;
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	time = wait_for_completion_timeout(&output->sof,
-					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
-	if (!time)
-		dev_err(to_device(vfe), "VFE sof timeout\n");
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-	for (i = 0; i < output->wm_num; i++)
-		vfe_wm_enable(vfe, output->wm_idx[i], 0);
-
-	vfe_reg_update(vfe, line->id);
-	output->wait_reg_update = 1;
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	time = wait_for_completion_timeout(&output->reg_update,
-					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
-	if (!time)
-		dev_err(to_device(vfe), "VFE reg update timeout\n");
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	if (line->id != VFE_LINE_PIX) {
-		vfe_wm_frame_based(vfe, output->wm_idx[0], 0);
-		vfe_bus_disconnect_wm_from_rdi(vfe, output->wm_idx[0], line->id);
-		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 0);
-		vfe_set_cgc_override(vfe, output->wm_idx[0], 0);
-		spin_unlock_irqrestore(&vfe->output_lock, flags);
-	} else {
-		for (i = 0; i < output->wm_num; i++) {
-			vfe_wm_line_based(vfe, output->wm_idx[i], NULL, i, 0);
-			vfe_set_cgc_override(vfe, output->wm_idx[i], 0);
-		}
-
-		vfe_enable_irq_pix_line(vfe, 0, line->id, 0);
-		vfe_set_module_cfg(vfe, 0);
-		vfe_set_xbar_cfg(vfe, output, 0);
-
-		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY);
-		spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-		vfe_camif_wait_for_stop(vfe);
-	}
-
-	return 0;
-}
-
-/*
- * vfe_enable - Enable streaming on VFE line
- * @line: VFE line
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_enable(struct vfe_line *line)
-{
-	struct vfe_device *vfe = to_vfe(line);
-	int ret;
-
-	mutex_lock(&vfe->stream_lock);
-
-	if (!vfe->stream_count) {
-		vfe_enable_irq_common(vfe);
-
-		vfe_bus_enable_wr_if(vfe, 1);
-
-		vfe_set_qos(vfe);
-	}
-
-	vfe->stream_count++;
-
-	mutex_unlock(&vfe->stream_lock);
-
-	ret = vfe_get_output(line);
-	if (ret < 0)
-		goto error_get_output;
-
-	ret = vfe_enable_output(line);
-	if (ret < 0)
-		goto error_enable_output;
-
-	vfe->was_streaming = 1;
-
-	return 0;
-
-
-error_enable_output:
-	vfe_put_output(line);
-
-error_get_output:
-	mutex_lock(&vfe->stream_lock);
-
-	if (vfe->stream_count == 1)
-		vfe_bus_enable_wr_if(vfe, 0);
-
-	vfe->stream_count--;
-
-	mutex_unlock(&vfe->stream_lock);
-
-	return ret;
-}
-
-/*
- * vfe_disable - Disable streaming on VFE line
- * @line: VFE line
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_disable(struct vfe_line *line)
-{
-	struct vfe_device *vfe = to_vfe(line);
-
-	vfe_disable_output(line);
-
-	vfe_put_output(line);
-
-	mutex_lock(&vfe->stream_lock);
-
-	if (vfe->stream_count == 1)
-		vfe_bus_enable_wr_if(vfe, 0);
-
-	vfe->stream_count--;
-
-	mutex_unlock(&vfe->stream_lock);
-
-	return 0;
-}
-
-/*
- * vfe_isr_sof - Process start of frame interrupt
- * @vfe: VFE Device
- * @line_id: VFE line
- */
-static void vfe_isr_sof(struct vfe_device *vfe, enum vfe_line_id line_id)
-{
-	struct vfe_output *output;
-	unsigned long flags;
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-	output = &vfe->line[line_id].output;
-	if (output->wait_sof) {
-		output->wait_sof = 0;
-		complete(&output->sof);
-	}
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-}
-
-/*
- * vfe_isr_reg_update - Process reg update interrupt
- * @vfe: VFE Device
- * @line_id: VFE line
- */
-static void vfe_isr_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
-{
-	struct vfe_output *output;
-	unsigned long flags;
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
-
-	output = &vfe->line[line_id].output;
-
-	if (output->wait_reg_update) {
-		output->wait_reg_update = 0;
-		complete(&output->reg_update);
-		spin_unlock_irqrestore(&vfe->output_lock, flags);
-		return;
-	}
-
-	if (output->state == VFE_OUTPUT_STOPPING) {
-		/* Release last buffer when hw is idle */
-		if (output->last_buffer) {
-			vb2_buffer_done(&output->last_buffer->vb.vb2_buf,
-					VB2_BUF_STATE_DONE);
-			output->last_buffer = NULL;
-		}
-		output->state = VFE_OUTPUT_IDLE;
-
-		/* Buffers received in stopping state are queued in */
-		/* dma pending queue, start next capture here */
-
-		output->buf[0] = vfe_buf_get_pending(output);
-		output->buf[1] = vfe_buf_get_pending(output);
-
-		if (!output->buf[0] && output->buf[1]) {
-			output->buf[0] = output->buf[1];
-			output->buf[1] = NULL;
-		}
-
-		if (output->buf[0])
-			output->state = VFE_OUTPUT_SINGLE;
-
-		if (output->buf[1])
-			output->state = VFE_OUTPUT_CONTINUOUS;
-
-		switch (output->state) {
-		case VFE_OUTPUT_SINGLE:
-			vfe_output_frame_drop(vfe, output, 2);
-			break;
-		case VFE_OUTPUT_CONTINUOUS:
-			vfe_output_frame_drop(vfe, output, 3);
-			break;
-		default:
-			vfe_output_frame_drop(vfe, output, 0);
-			break;
-		}
-
-		vfe_output_init_addrs(vfe, output, 1);
-	}
-
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-}
-
-/*
- * vfe_isr_wm_done - Process write master done interrupt
- * @vfe: VFE Device
- * @wm: Write master id
- */
-static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
-{
-	struct camss_buffer *ready_buf;
-	struct vfe_output *output;
-	dma_addr_t *new_addr;
-	unsigned long flags;
-	u32 active_index;
-	u64 ts = ktime_get_ns();
-	unsigned int i;
-
-	active_index = vfe_wm_get_ping_pong_status(vfe, wm);
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	if (vfe->wm_output_map[wm] == VFE_LINE_NONE) {
-		dev_err_ratelimited(to_device(vfe),
-				    "Received wm done for unmapped index\n");
-		goto out_unlock;
-	}
-	output = &vfe->line[vfe->wm_output_map[wm]].output;
-
-	if (output->active_buf == active_index) {
-		dev_err_ratelimited(to_device(vfe),
-				    "Active buffer mismatch!\n");
-		goto out_unlock;
-	}
-	output->active_buf = active_index;
-
-	ready_buf = output->buf[!active_index];
-	if (!ready_buf) {
-		dev_err_ratelimited(to_device(vfe),
-				    "Missing ready buf %d %d!\n",
-				    !active_index, output->state);
-		goto out_unlock;
-	}
-
-	ready_buf->vb.vb2_buf.timestamp = ts;
-	ready_buf->vb.sequence = output->sequence++;
-
-	/* Get next buffer */
-	output->buf[!active_index] = vfe_buf_get_pending(output);
-	if (!output->buf[!active_index]) {
-		/* No next buffer - set same address */
-		new_addr = ready_buf->addr;
-		vfe_buf_update_wm_on_last(vfe, output);
-	} else {
-		new_addr = output->buf[!active_index]->addr;
-		vfe_buf_update_wm_on_next(vfe, output);
-	}
-
-	if (active_index)
-		for (i = 0; i < output->wm_num; i++)
-			vfe_wm_set_ping_addr(vfe, output->wm_idx[i],
-					     new_addr[i]);
-	else
-		for (i = 0; i < output->wm_num; i++)
-			vfe_wm_set_pong_addr(vfe, output->wm_idx[i],
-					     new_addr[i]);
-
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	if (output->state == VFE_OUTPUT_STOPPING)
-		output->last_buffer = ready_buf;
-	else
-		vb2_buffer_done(&ready_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
-
-	return;
-
-out_unlock:
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-}
-
-/*
- * vfe_isr_wm_done - Process composite image done interrupt
- * @vfe: VFE Device
- * @comp: Composite image id
- */
-static void vfe_isr_comp_done(struct vfe_device *vfe, u8 comp)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(vfe->wm_output_map); i++)
-		if (vfe->wm_output_map[i] == VFE_LINE_PIX) {
-			vfe_isr_wm_done(vfe, i);
-			break;
-		}
-}
-
-/*
- * vfe_isr - ISPIF module interrupt handler
- * @irq: Interrupt line
- * @dev: VFE device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t vfe_isr(int irq, void *dev)
-{
-	struct vfe_device *vfe = dev;
-	u32 value0, value1;
-	u32 violation;
-	int i, j;
-
-	value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
-	value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
-
-	writel_relaxed(value0, vfe->base + VFE_0_IRQ_CLEAR_0);
-	writel_relaxed(value1, vfe->base + VFE_0_IRQ_CLEAR_1);
-
-	wmb();
-	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
-
-	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
-		complete(&vfe->reset_complete);
-
-	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION) {
-		violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
-		dev_err_ratelimited(to_device(vfe),
-				    "VFE: violation = 0x%08x\n", violation);
-	}
-
-	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK) {
-		complete(&vfe->halt_complete);
-		writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
-	}
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
-			vfe_isr_reg_update(vfe, i);
-
-	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
-		vfe_isr_sof(vfe, VFE_LINE_PIX);
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
-		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
-			vfe_isr_sof(vfe, i);
-
-	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
-			vfe_isr_comp_done(vfe, i);
-			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
-				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
-					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
-		}
-
-	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
-			vfe_isr_wm_done(vfe, i);
-
-	return IRQ_HANDLED;
-}
-
-/*
- * vfe_set_clock_rates - Calculate and set clock rates on VFE module
- * @vfe: VFE device
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_set_clock_rates(struct vfe_device *vfe)
-{
-	struct device *dev = to_device(vfe);
-	u32 pixel_clock[MSM_VFE_LINE_NUM];
-	int i, j;
-	int ret;
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
-		ret = camss_get_pixel_clock(&vfe->line[i].subdev.entity,
-					    &pixel_clock[i]);
-		if (ret)
-			pixel_clock[i] = 0;
-	}
-
-	for (i = 0; i < vfe->nclocks; i++) {
-		struct camss_clock *clock = &vfe->clock[i];
-
-		if (!strcmp(clock->name, "camss_vfe_vfe")) {
-			u64 min_rate = 0;
-			long rate;
-
-			for (j = VFE_LINE_RDI0; j <= VFE_LINE_PIX; j++) {
-				u32 tmp;
-				u8 bpp;
-
-				if (j == VFE_LINE_PIX) {
-					tmp = pixel_clock[j];
-				} else {
-					bpp = vfe_get_bpp(vfe->line[j].
-						fmt[MSM_VFE_PAD_SINK].code);
-					tmp = pixel_clock[j] * bpp / 64;
-				}
-
-				if (min_rate < tmp)
-					min_rate = tmp;
-			}
-
-			camss_add_clock_margin(&min_rate);
-
-			for (j = 0; j < clock->nfreqs; j++)
-				if (min_rate < clock->freq[j])
-					break;
-
-			if (j == clock->nfreqs) {
-				dev_err(dev,
-					"Pixel clock is too high for VFE");
-				return -EINVAL;
-			}
-
-			/* if sensor pixel clock is not available */
-			/* set highest possible VFE clock rate */
-			if (min_rate == 0)
-				j = clock->nfreqs - 1;
-
-			rate = clk_round_rate(clock->clk, clock->freq[j]);
-			if (rate < 0) {
-				dev_err(dev, "clk round rate failed: %ld\n",
-					rate);
-				return -EINVAL;
-			}
-
-			ret = clk_set_rate(clock->clk, rate);
-			if (ret < 0) {
-				dev_err(dev, "clk set rate failed: %d\n", ret);
-				return ret;
-			}
-		}
-	}
-
-	return 0;
-}
-
-/*
- * vfe_check_clock_rates - Check current clock rates on VFE module
- * @vfe: VFE device
- *
- * Return 0 if current clock rates are suitable for a new pipeline
- * or a negative error code otherwise
- */
-static int vfe_check_clock_rates(struct vfe_device *vfe)
-{
-	u32 pixel_clock[MSM_VFE_LINE_NUM];
-	int i, j;
-	int ret;
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
-		ret = camss_get_pixel_clock(&vfe->line[i].subdev.entity,
-					    &pixel_clock[i]);
-		if (ret)
-			pixel_clock[i] = 0;
-	}
-
-	for (i = 0; i < vfe->nclocks; i++) {
-		struct camss_clock *clock = &vfe->clock[i];
-
-		if (!strcmp(clock->name, "camss_vfe_vfe")) {
-			u64 min_rate = 0;
-			unsigned long rate;
-
-			for (j = VFE_LINE_RDI0; j <= VFE_LINE_PIX; j++) {
-				u32 tmp;
-				u8 bpp;
-
-				if (j == VFE_LINE_PIX) {
-					tmp = pixel_clock[j];
-				} else {
-					bpp = vfe_get_bpp(vfe->line[j].
-						fmt[MSM_VFE_PAD_SINK].code);
-					tmp = pixel_clock[j] * bpp / 64;
-				}
-
-				if (min_rate < tmp)
-					min_rate = tmp;
-			}
-
-			camss_add_clock_margin(&min_rate);
-
-			rate = clk_get_rate(clock->clk);
-			if (rate < min_rate)
-				return -EBUSY;
-		}
-	}
-
-	return 0;
-}
-
-/*
- * vfe_get - Power up and reset VFE module
- * @vfe: VFE Device
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_get(struct vfe_device *vfe)
-{
-	int ret;
-
-	mutex_lock(&vfe->power_lock);
-
-	if (vfe->power_count == 0) {
-		ret = vfe_set_clock_rates(vfe);
-		if (ret < 0)
-			goto error_clocks;
-
-		ret = camss_enable_clocks(vfe->nclocks, vfe->clock,
-					  to_device(vfe));
-		if (ret < 0)
-			goto error_clocks;
-
-		ret = vfe_reset(vfe);
-		if (ret < 0)
-			goto error_reset;
-
-		vfe_reset_output_maps(vfe);
-
-		vfe_init_outputs(vfe);
-	} else {
-		ret = vfe_check_clock_rates(vfe);
-		if (ret < 0)
-			goto error_clocks;
-	}
-	vfe->power_count++;
-
-	mutex_unlock(&vfe->power_lock);
-
-	return 0;
-
-error_reset:
-	camss_disable_clocks(vfe->nclocks, vfe->clock);
-
-error_clocks:
-	mutex_unlock(&vfe->power_lock);
-
-	return ret;
-}
-
-/*
- * vfe_put - Power down VFE module
- * @vfe: VFE Device
- */
-static void vfe_put(struct vfe_device *vfe)
-{
-	mutex_lock(&vfe->power_lock);
-
-	if (vfe->power_count == 0) {
-		dev_err(to_device(vfe), "vfe power off on power_count == 0\n");
-		goto exit;
-	} else if (vfe->power_count == 1) {
-		if (vfe->was_streaming) {
-			vfe->was_streaming = 0;
-			vfe_halt(vfe);
-		}
-		camss_disable_clocks(vfe->nclocks, vfe->clock);
-	}
-
-	vfe->power_count--;
-
-exit:
-	mutex_unlock(&vfe->power_lock);
-}
-
-/*
- * vfe_video_pad_to_line - Get pointer to VFE line by media pad
- * @pad: Media pad
- *
- * Return pointer to vfe line structure
- */
-static struct vfe_line *vfe_video_pad_to_line(struct media_pad *pad)
-{
-	struct media_pad *vfe_pad;
-	struct v4l2_subdev *subdev;
-
-	vfe_pad = media_entity_remote_pad(pad);
-	if (vfe_pad == NULL)
-		return NULL;
-
-	subdev = media_entity_to_v4l2_subdev(vfe_pad->entity);
-
-	return container_of(subdev, struct vfe_line, subdev);
-}
-
-/*
- * vfe_queue_buffer - Add empty buffer
- * @vid: Video device structure
- * @buf: Buffer to be enqueued
- *
- * Add an empty buffer - depending on the current number of buffers it will be
- * put in pending buffer queue or directly given to the hardware to be filled.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_queue_buffer(struct camss_video *vid,
-			    struct camss_buffer *buf)
-{
-	struct vfe_device *vfe = &vid->camss->vfe;
-	struct vfe_line *line;
-	struct vfe_output *output;
-	unsigned long flags;
-
-	line = vfe_video_pad_to_line(&vid->pad);
-	if (!line) {
-		dev_err(to_device(vfe), "Can not queue buffer\n");
-		return -1;
-	}
-	output = &line->output;
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	vfe_buf_update_wm_on_new(vfe, output, buf);
-
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	return 0;
-}
-
-/*
- * vfe_flush_buffers - Return all vb2 buffers
- * @vid: Video device structure
- * @state: vb2 buffer state of the returned buffers
- *
- * Return all buffers to vb2. This includes queued pending buffers (still
- * unused) and any buffers given to the hardware but again still not used.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_flush_buffers(struct camss_video *vid,
-			     enum vb2_buffer_state state)
-{
-	struct vfe_device *vfe = &vid->camss->vfe;
-	struct vfe_line *line;
-	struct vfe_output *output;
-	unsigned long flags;
-
-	line = vfe_video_pad_to_line(&vid->pad);
-	if (!line) {
-		dev_err(to_device(vfe),	"Can not flush buffers\n");
-		return -1;
-	}
-	output = &line->output;
-
-	spin_lock_irqsave(&vfe->output_lock, flags);
-
-	vfe_buf_flush_pending(output, state);
-
-	if (output->buf[0])
-		vb2_buffer_done(&output->buf[0]->vb.vb2_buf, state);
-
-	if (output->buf[1])
-		vb2_buffer_done(&output->buf[1]->vb.vb2_buf, state);
-
-	if (output->last_buffer) {
-		vb2_buffer_done(&output->last_buffer->vb.vb2_buf, state);
-		output->last_buffer = NULL;
-	}
-
-	spin_unlock_irqrestore(&vfe->output_lock, flags);
-
-	return 0;
-}
-
-/*
- * vfe_set_power - Power on/off VFE module
- * @sd: VFE V4L2 subdevice
- * @on: Requested power state
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_set_power(struct v4l2_subdev *sd, int on)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct vfe_device *vfe = to_vfe(line);
-	int ret;
-
-	if (on) {
-		u32 hw_version;
-
-		ret = vfe_get(vfe);
-		if (ret < 0)
-			return ret;
-
-		hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
-		dev_dbg(to_device(vfe),
-			"VFE HW Version = 0x%08x\n", hw_version);
-	} else {
-		vfe_put(vfe);
-	}
-
-	return 0;
-}
-
-/*
- * vfe_set_stream - Enable/disable streaming on VFE module
- * @sd: VFE V4L2 subdevice
- * @enable: Requested streaming state
- *
- * Main configuration of VFE module is triggered here.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_set_stream(struct v4l2_subdev *sd, int enable)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct vfe_device *vfe = to_vfe(line);
-	int ret;
-
-	if (enable) {
-		ret = vfe_enable(line);
-		if (ret < 0)
-			dev_err(to_device(vfe),
-				"Failed to enable vfe outputs\n");
-	} else {
-		ret = vfe_disable(line);
-		if (ret < 0)
-			dev_err(to_device(vfe),
-				"Failed to disable vfe outputs\n");
-	}
-
-	return ret;
-}
-
-/*
- * __vfe_get_format - Get pointer to format structure
- * @line: VFE line
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad from which format is requested
- * @which: TRY or ACTIVE format
- *
- * Return pointer to TRY or ACTIVE format structure
- */
-static struct v4l2_mbus_framefmt *
-__vfe_get_format(struct vfe_line *line,
-		 struct v4l2_subdev_pad_config *cfg,
-		 unsigned int pad,
-		 enum v4l2_subdev_format_whence which)
-{
-	if (which == V4L2_SUBDEV_FORMAT_TRY)
-		return v4l2_subdev_get_try_format(&line->subdev, cfg, pad);
-
-	return &line->fmt[pad];
-}
-
-/*
- * __vfe_get_compose - Get pointer to compose selection structure
- * @line: VFE line
- * @cfg: V4L2 subdev pad configuration
- * @which: TRY or ACTIVE format
- *
- * Return pointer to TRY or ACTIVE compose rectangle structure
- */
-static struct v4l2_rect *
-__vfe_get_compose(struct vfe_line *line,
-		  struct v4l2_subdev_pad_config *cfg,
-		  enum v4l2_subdev_format_whence which)
-{
-	if (which == V4L2_SUBDEV_FORMAT_TRY)
-		return v4l2_subdev_get_try_compose(&line->subdev, cfg,
-						   MSM_VFE_PAD_SINK);
-
-	return &line->compose;
-}
-
-/*
- * __vfe_get_crop - Get pointer to crop selection structure
- * @line: VFE line
- * @cfg: V4L2 subdev pad configuration
- * @which: TRY or ACTIVE format
- *
- * Return pointer to TRY or ACTIVE crop rectangle structure
- */
-static struct v4l2_rect *
-__vfe_get_crop(struct vfe_line *line,
-	       struct v4l2_subdev_pad_config *cfg,
-	       enum v4l2_subdev_format_whence which)
-{
-	if (which == V4L2_SUBDEV_FORMAT_TRY)
-		return v4l2_subdev_get_try_crop(&line->subdev, cfg,
-						MSM_VFE_PAD_SRC);
-
-	return &line->crop;
-}
-
-/*
- * vfe_try_format - Handle try format by pad subdev method
- * @line: VFE line
- * @cfg: V4L2 subdev pad configuration
- * @pad: pad on which format is requested
- * @fmt: pointer to v4l2 format structure
- * @which: wanted subdev format
- */
-static void vfe_try_format(struct vfe_line *line,
-			   struct v4l2_subdev_pad_config *cfg,
-			   unsigned int pad,
-			   struct v4l2_mbus_framefmt *fmt,
-			   enum v4l2_subdev_format_whence which)
-{
-	unsigned int i;
-	u32 code;
-
-	switch (pad) {
-	case MSM_VFE_PAD_SINK:
-		/* Set format on sink pad */
-
-		for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
-			if (fmt->code == vfe_formats[i].code)
-				break;
-
-		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(vfe_formats))
-			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-
-		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
-		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
-
-		fmt->field = V4L2_FIELD_NONE;
-		fmt->colorspace = V4L2_COLORSPACE_SRGB;
-
-		break;
-
-	case MSM_VFE_PAD_SRC:
-		/* Set and return a format same as sink pad */
-
-		code = fmt->code;
-
-		*fmt = *__vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
-					 which);
-
-		if (line->id == VFE_LINE_PIX) {
-			struct v4l2_rect *rect;
-
-			rect = __vfe_get_crop(line, cfg, which);
-
-			fmt->width = rect->width;
-			fmt->height = rect->height;
-
-			switch (fmt->code) {
-			case MEDIA_BUS_FMT_YUYV8_2X8:
-				if (code == MEDIA_BUS_FMT_YUYV8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_YUYV8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_YUYV8_2X8;
-				break;
-			case MEDIA_BUS_FMT_YVYU8_2X8:
-				if (code == MEDIA_BUS_FMT_YVYU8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_YVYU8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_YVYU8_2X8;
-				break;
-			case MEDIA_BUS_FMT_UYVY8_2X8:
-			default:
-				if (code == MEDIA_BUS_FMT_UYVY8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_UYVY8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-				break;
-			case MEDIA_BUS_FMT_VYUY8_2X8:
-				if (code == MEDIA_BUS_FMT_VYUY8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_VYUY8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_VYUY8_2X8;
-				break;
-			}
-		}
-
-		break;
-	}
-
-	fmt->colorspace = V4L2_COLORSPACE_SRGB;
-}
-
-/*
- * vfe_try_compose - Handle try compose selection by pad subdev method
- * @line: VFE line
- * @cfg: V4L2 subdev pad configuration
- * @rect: pointer to v4l2 rect structure
- * @which: wanted subdev format
- */
-static void vfe_try_compose(struct vfe_line *line,
-			    struct v4l2_subdev_pad_config *cfg,
-			    struct v4l2_rect *rect,
-			    enum v4l2_subdev_format_whence which)
-{
-	struct v4l2_mbus_framefmt *fmt;
-
-	fmt = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK, which);
-
-	if (rect->width > fmt->width)
-		rect->width = fmt->width;
-
-	if (rect->height > fmt->height)
-		rect->height = fmt->height;
-
-	if (fmt->width > rect->width * SCALER_RATIO_MAX)
-		rect->width = (fmt->width + SCALER_RATIO_MAX - 1) /
-							SCALER_RATIO_MAX;
-
-	rect->width &= ~0x1;
-
-	if (fmt->height > rect->height * SCALER_RATIO_MAX)
-		rect->height = (fmt->height + SCALER_RATIO_MAX - 1) /
-							SCALER_RATIO_MAX;
-
-	if (rect->width < 16)
-		rect->width = 16;
-
-	if (rect->height < 4)
-		rect->height = 4;
-}
-
-/*
- * vfe_try_crop - Handle try crop selection by pad subdev method
- * @line: VFE line
- * @cfg: V4L2 subdev pad configuration
- * @rect: pointer to v4l2 rect structure
- * @which: wanted subdev format
- */
-static void vfe_try_crop(struct vfe_line *line,
-			 struct v4l2_subdev_pad_config *cfg,
-			 struct v4l2_rect *rect,
-			 enum v4l2_subdev_format_whence which)
-{
-	struct v4l2_rect *compose;
-
-	compose = __vfe_get_compose(line, cfg, which);
-
-	if (rect->width > compose->width)
-		rect->width = compose->width;
-
-	if (rect->width + rect->left > compose->width)
-		rect->left = compose->width - rect->width;
-
-	if (rect->height > compose->height)
-		rect->height = compose->height;
-
-	if (rect->height + rect->top > compose->height)
-		rect->top = compose->height - rect->height;
-
-	/* wm in line based mode writes multiple of 16 horizontally */
-	rect->left += (rect->width & 0xf) >> 1;
-	rect->width &= ~0xf;
-
-	if (rect->width < 16) {
-		rect->left = 0;
-		rect->width = 16;
-	}
-
-	if (rect->height < 4) {
-		rect->top = 0;
-		rect->height = 4;
-	}
-}
-
-/*
- * vfe_enum_mbus_code - Handle pixel format enumeration
- * @sd: VFE V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @code: pointer to v4l2_subdev_mbus_code_enum structure
- *
- * return -EINVAL or zero on success
- */
-static int vfe_enum_mbus_code(struct v4l2_subdev *sd,
-			      struct v4l2_subdev_pad_config *cfg,
-			      struct v4l2_subdev_mbus_code_enum *code)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	if (code->pad == MSM_VFE_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(vfe_formats))
-			return -EINVAL;
-
-		code->code = vfe_formats[code->index].code;
-	} else {
-		if (code->index > 0)
-			return -EINVAL;
-
-		format = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
-					  code->which);
-
-		code->code = format->code;
-	}
-
-	return 0;
-}
-
-/*
- * vfe_enum_frame_size - Handle frame size enumeration
- * @sd: VFE V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fse: pointer to v4l2_subdev_frame_size_enum structure
- *
- * Return -EINVAL or zero on success
- */
-static int vfe_enum_frame_size(struct v4l2_subdev *sd,
-			       struct v4l2_subdev_pad_config *cfg,
-			       struct v4l2_subdev_frame_size_enum *fse)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt format;
-
-	if (fse->index != 0)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = 1;
-	format.height = 1;
-	vfe_try_format(line, cfg, fse->pad, &format, fse->which);
-	fse->min_width = format.width;
-	fse->min_height = format.height;
-
-	if (format.code != fse->code)
-		return -EINVAL;
-
-	format.code = fse->code;
-	format.width = -1;
-	format.height = -1;
-	vfe_try_format(line, cfg, fse->pad, &format, fse->which);
-	fse->max_width = format.width;
-	fse->max_height = format.height;
-
-	return 0;
-}
-
-/*
- * vfe_get_format - Handle get format by pads subdev method
- * @sd: VFE V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int vfe_get_format(struct v4l2_subdev *sd,
-			  struct v4l2_subdev_pad_config *cfg,
-			  struct v4l2_subdev_format *fmt)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __vfe_get_format(line, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	fmt->format = *format;
-
-	return 0;
-}
-
-static int vfe_set_selection(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_pad_config *cfg,
-			     struct v4l2_subdev_selection *sel);
-
-/*
- * vfe_set_format - Handle set format by pads subdev method
- * @sd: VFE V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @fmt: pointer to v4l2 subdev format structure
- *
- * Return -EINVAL or zero on success
- */
-static int vfe_set_format(struct v4l2_subdev *sd,
-			  struct v4l2_subdev_pad_config *cfg,
-			  struct v4l2_subdev_format *fmt)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
-
-	format = __vfe_get_format(line, cfg, fmt->pad, fmt->which);
-	if (format == NULL)
-		return -EINVAL;
-
-	vfe_try_format(line, cfg, fmt->pad, &fmt->format, fmt->which);
-	*format = fmt->format;
-
-	if (fmt->pad == MSM_VFE_PAD_SINK) {
-		struct v4l2_subdev_selection sel = { 0 };
-		int ret;
-
-		/* Propagate the format from sink to source */
-		format = __vfe_get_format(line, cfg, MSM_VFE_PAD_SRC,
-					  fmt->which);
-
-		*format = fmt->format;
-		vfe_try_format(line, cfg, MSM_VFE_PAD_SRC, format,
-			       fmt->which);
-
-		if (line->id != VFE_LINE_PIX)
-			return 0;
-
-		/* Reset sink pad compose selection */
-		sel.which = fmt->which;
-		sel.pad = MSM_VFE_PAD_SINK;
-		sel.target = V4L2_SEL_TGT_COMPOSE;
-		sel.r.width = fmt->format.width;
-		sel.r.height = fmt->format.height;
-		ret = vfe_set_selection(sd, cfg, &sel);
-		if (ret < 0)
-			return ret;
-	}
-
-	return 0;
-}
-
-/*
- * vfe_get_selection - Handle get selection by pads subdev method
- * @sd: VFE V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @sel: pointer to v4l2 subdev selection structure
- *
- * Return -EINVAL or zero on success
- */
-static int vfe_get_selection(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_pad_config *cfg,
-			     struct v4l2_subdev_selection *sel)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_subdev_format fmt = { 0 };
-	struct v4l2_rect *rect;
-	int ret;
-
-	if (line->id != VFE_LINE_PIX)
-		return -EINVAL;
-
-	if (sel->pad == MSM_VFE_PAD_SINK)
-		switch (sel->target) {
-		case V4L2_SEL_TGT_COMPOSE_BOUNDS:
-			fmt.pad = sel->pad;
-			fmt.which = sel->which;
-			ret = vfe_get_format(sd, cfg, &fmt);
-			if (ret < 0)
-				return ret;
-
-			sel->r.left = 0;
-			sel->r.top = 0;
-			sel->r.width = fmt.format.width;
-			sel->r.height = fmt.format.height;
-			break;
-		case V4L2_SEL_TGT_COMPOSE:
-			rect = __vfe_get_compose(line, cfg, sel->which);
-			if (rect == NULL)
-				return -EINVAL;
-
-			sel->r = *rect;
-			break;
-		default:
-			return -EINVAL;
-		}
-	else if (sel->pad == MSM_VFE_PAD_SRC)
-		switch (sel->target) {
-		case V4L2_SEL_TGT_CROP_BOUNDS:
-			rect = __vfe_get_compose(line, cfg, sel->which);
-			if (rect == NULL)
-				return -EINVAL;
-
-			sel->r.left = rect->left;
-			sel->r.top = rect->top;
-			sel->r.width = rect->width;
-			sel->r.height = rect->height;
-			break;
-		case V4L2_SEL_TGT_CROP:
-			rect = __vfe_get_crop(line, cfg, sel->which);
-			if (rect == NULL)
-				return -EINVAL;
-
-			sel->r = *rect;
-			break;
-		default:
-			return -EINVAL;
-		}
-
-	return 0;
-}
-
-/*
- * vfe_set_selection - Handle set selection by pads subdev method
- * @sd: VFE V4L2 subdevice
- * @cfg: V4L2 subdev pad configuration
- * @sel: pointer to v4l2 subdev selection structure
- *
- * Return -EINVAL or zero on success
- */
-static int vfe_set_selection(struct v4l2_subdev *sd,
-			     struct v4l2_subdev_pad_config *cfg,
-			     struct v4l2_subdev_selection *sel)
-{
-	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_rect *rect;
-	int ret;
-
-	if (line->id != VFE_LINE_PIX)
-		return -EINVAL;
-
-	if (sel->target == V4L2_SEL_TGT_COMPOSE &&
-		sel->pad == MSM_VFE_PAD_SINK) {
-		struct v4l2_subdev_selection crop = { 0 };
-
-		rect = __vfe_get_compose(line, cfg, sel->which);
-		if (rect == NULL)
-			return -EINVAL;
-
-		vfe_try_compose(line, cfg, &sel->r, sel->which);
-		*rect = sel->r;
-
-		/* Reset source crop selection */
-		crop.which = sel->which;
-		crop.pad = MSM_VFE_PAD_SRC;
-		crop.target = V4L2_SEL_TGT_CROP;
-		crop.r = *rect;
-		ret = vfe_set_selection(sd, cfg, &crop);
-	} else if (sel->target == V4L2_SEL_TGT_CROP &&
-		sel->pad == MSM_VFE_PAD_SRC) {
-		struct v4l2_subdev_format fmt = { 0 };
-
-		rect = __vfe_get_crop(line, cfg, sel->which);
-		if (rect == NULL)
-			return -EINVAL;
-
-		vfe_try_crop(line, cfg, &sel->r, sel->which);
-		*rect = sel->r;
-
-		/* Reset source pad format width and height */
-		fmt.which = sel->which;
-		fmt.pad = MSM_VFE_PAD_SRC;
-		ret = vfe_get_format(sd, cfg, &fmt);
-		if (ret < 0)
-			return ret;
-
-		fmt.format.width = rect->width;
-		fmt.format.height = rect->height;
-		ret = vfe_set_format(sd, cfg, &fmt);
-	} else {
-		ret = -EINVAL;
-	}
-
-	return ret;
-}
-
-/*
- * vfe_init_formats - Initialize formats on all pads
- * @sd: VFE V4L2 subdevice
- * @fh: V4L2 subdev file handle
- *
- * Initialize all pad formats with default values.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int vfe_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
-{
-	struct v4l2_subdev_format format = {
-		.pad = MSM_VFE_PAD_SINK,
-		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
-			      V4L2_SUBDEV_FORMAT_ACTIVE,
-		.format = {
-			.code = MEDIA_BUS_FMT_UYVY8_2X8,
-			.width = 1920,
-			.height = 1080
-		}
-	};
-
-	return vfe_set_format(sd, fh ? fh->pad : NULL, &format);
-}
-
-/*
- * msm_vfe_subdev_init - Initialize VFE device structure and resources
- * @vfe: VFE device
- * @res: VFE module resources table
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res)
-{
-	struct device *dev = to_device(vfe);
-	struct platform_device *pdev = to_platform_device(dev);
-	struct resource *r;
-	struct camss *camss = to_camss(vfe);
-	int i, j;
-	int ret;
-
-	/* Memory */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
-	vfe->base = devm_ioremap_resource(dev, r);
-	if (IS_ERR(vfe->base)) {
-		dev_err(dev, "could not map memory\n");
-		return PTR_ERR(vfe->base);
-	}
-
-	/* Interrupt */
-
-	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ,
-					 res->interrupt[0]);
-	if (!r) {
-		dev_err(dev, "missing IRQ\n");
-		return -EINVAL;
-	}
-
-	vfe->irq = r->start;
-	snprintf(vfe->irq_name, sizeof(vfe->irq_name), "%s_%s%d",
-		 dev_name(dev), MSM_VFE_NAME, vfe->id);
-	ret = devm_request_irq(dev, vfe->irq, vfe_isr,
-			       IRQF_TRIGGER_RISING, vfe->irq_name, vfe);
-	if (ret < 0) {
-		dev_err(dev, "request_irq failed: %d\n", ret);
-		return ret;
-	}
-
-	/* Clocks */
-
-	vfe->nclocks = 0;
-	while (res->clock[vfe->nclocks])
-		vfe->nclocks++;
-
-	vfe->clock = devm_kcalloc(dev, vfe->nclocks, sizeof(*vfe->clock),
-				  GFP_KERNEL);
-	if (!vfe->clock)
-		return -ENOMEM;
-
-	for (i = 0; i < vfe->nclocks; i++) {
-		struct camss_clock *clock = &vfe->clock[i];
-
-		clock->clk = devm_clk_get(dev, res->clock[i]);
-		if (IS_ERR(clock->clk))
-			return PTR_ERR(clock->clk);
-
-		clock->name = res->clock[i];
-
-		clock->nfreqs = 0;
-		while (res->clock_rate[i][clock->nfreqs])
-			clock->nfreqs++;
-
-		if (!clock->nfreqs) {
-			clock->freq = NULL;
-			continue;
-		}
-
-		clock->freq = devm_kcalloc(dev,
-					   clock->nfreqs,
-					   sizeof(*clock->freq),
-					   GFP_KERNEL);
-		if (!clock->freq)
-			return -ENOMEM;
-
-		for (j = 0; j < clock->nfreqs; j++)
-			clock->freq[j] = res->clock_rate[i][j];
-	}
-
-	mutex_init(&vfe->power_lock);
-	vfe->power_count = 0;
-
-	mutex_init(&vfe->stream_lock);
-	vfe->stream_count = 0;
-
-	spin_lock_init(&vfe->output_lock);
-
-	vfe->id = 0;
-	vfe->reg_update = 0;
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
-		vfe->line[i].video_out.type =
-					V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
-		vfe->line[i].video_out.camss = camss;
-		vfe->line[i].id = i;
-		init_completion(&vfe->line[i].output.sof);
-		init_completion(&vfe->line[i].output.reg_update);
-	}
-
-	init_completion(&vfe->reset_complete);
-	init_completion(&vfe->halt_complete);
-
-	return 0;
-}
-
-/*
- * msm_vfe_get_vfe_id - Get VFE HW module id
- * @entity: Pointer to VFE media entity structure
- * @id: Return CSID HW module id here
- */
-void msm_vfe_get_vfe_id(struct media_entity *entity, u8 *id)
-{
-	struct v4l2_subdev *sd;
-	struct vfe_line *line;
-	struct vfe_device *vfe;
-
-	sd = media_entity_to_v4l2_subdev(entity);
-	line = v4l2_get_subdevdata(sd);
-	vfe = to_vfe(line);
-
-	*id = vfe->id;
-}
-
-/*
- * msm_vfe_get_vfe_line_id - Get VFE line id by media entity
- * @entity: Pointer to VFE media entity structure
- * @id: Return VFE line id here
- */
-void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id)
-{
-	struct v4l2_subdev *sd;
-	struct vfe_line *line;
-
-	sd = media_entity_to_v4l2_subdev(entity);
-	line = v4l2_get_subdevdata(sd);
-
-	*id = line->id;
-}
-
-/*
- * vfe_link_setup - Setup VFE connections
- * @entity: Pointer to media entity structure
- * @local: Pointer to local pad
- * @remote: Pointer to remote pad
- * @flags: Link flags
- *
- * Return 0 on success
- */
-static int vfe_link_setup(struct media_entity *entity,
-			  const struct media_pad *local,
-			  const struct media_pad *remote, u32 flags)
-{
-	if (flags & MEDIA_LNK_FL_ENABLED)
-		if (media_entity_remote_pad(local))
-			return -EBUSY;
-
-	return 0;
-}
-
-static const struct v4l2_subdev_core_ops vfe_core_ops = {
-	.s_power = vfe_set_power,
-};
-
-static const struct v4l2_subdev_video_ops vfe_video_ops = {
-	.s_stream = vfe_set_stream,
-};
-
-static const struct v4l2_subdev_pad_ops vfe_pad_ops = {
-	.enum_mbus_code = vfe_enum_mbus_code,
-	.enum_frame_size = vfe_enum_frame_size,
-	.get_fmt = vfe_get_format,
-	.set_fmt = vfe_set_format,
-	.get_selection = vfe_get_selection,
-	.set_selection = vfe_set_selection,
-};
-
-static const struct v4l2_subdev_ops vfe_v4l2_ops = {
-	.core = &vfe_core_ops,
-	.video = &vfe_video_ops,
-	.pad = &vfe_pad_ops,
-};
-
-static const struct v4l2_subdev_internal_ops vfe_v4l2_internal_ops = {
-	.open = vfe_init_formats,
-};
-
-static const struct media_entity_operations vfe_media_ops = {
-	.link_setup = vfe_link_setup,
-	.link_validate = v4l2_subdev_link_validate,
-};
-
-static const struct camss_video_ops camss_vfe_video_ops = {
-	.queue_buffer = vfe_queue_buffer,
-	.flush_buffers = vfe_flush_buffers,
-};
-
-void msm_vfe_stop_streaming(struct vfe_device *vfe)
-{
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(vfe->line); i++)
-		msm_video_stop_streaming(&vfe->line[i].video_out);
-}
-
-/*
- * msm_vfe_register_entities - Register subdev node for VFE module
- * @vfe: VFE device
- * @v4l2_dev: V4L2 device
- *
- * Initialize and register a subdev node for the VFE module. Then
- * call msm_video_register() to register the video device node which
- * will be connected to this subdev node. Then actually create the
- * media link between them.
- *
- * Return 0 on success or a negative error code otherwise
- */
-int msm_vfe_register_entities(struct vfe_device *vfe,
-			      struct v4l2_device *v4l2_dev)
-{
-	struct device *dev = to_device(vfe);
-	struct v4l2_subdev *sd;
-	struct media_pad *pads;
-	struct camss_video *video_out;
-	int ret;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(vfe->line); i++) {
-		char name[32];
-
-		sd = &vfe->line[i].subdev;
-		pads = vfe->line[i].pads;
-		video_out = &vfe->line[i].video_out;
-
-		v4l2_subdev_init(sd, &vfe_v4l2_ops);
-		sd->internal_ops = &vfe_v4l2_internal_ops;
-		sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
-		if (i == VFE_LINE_PIX)
-			snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d_%s",
-				 MSM_VFE_NAME, vfe->id, "pix");
-		else
-			snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d_%s%d",
-				 MSM_VFE_NAME, vfe->id, "rdi", i);
-
-		v4l2_set_subdevdata(sd, &vfe->line[i]);
-
-		ret = vfe_init_formats(sd, NULL);
-		if (ret < 0) {
-			dev_err(dev, "Failed to init format: %d\n", ret);
-			goto error_init;
-		}
-
-		pads[MSM_VFE_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
-		pads[MSM_VFE_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
-
-		sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER;
-		sd->entity.ops = &vfe_media_ops;
-		ret = media_entity_pads_init(&sd->entity, MSM_VFE_PADS_NUM,
-					     pads);
-		if (ret < 0) {
-			dev_err(dev, "Failed to init media entity: %d\n", ret);
-			goto error_init;
-		}
-
-		ret = v4l2_device_register_subdev(v4l2_dev, sd);
-		if (ret < 0) {
-			dev_err(dev, "Failed to register subdev: %d\n", ret);
-			goto error_reg_subdev;
-		}
-
-		video_out->ops = &camss_vfe_video_ops;
-		video_out->bpl_alignment = 8;
-		video_out->line_based = 0;
-		if (i == VFE_LINE_PIX) {
-			video_out->bpl_alignment = 16;
-			video_out->line_based = 1;
-		}
-		snprintf(name, ARRAY_SIZE(name), "%s%d_%s%d",
-			 MSM_VFE_NAME, vfe->id, "video", i);
-		ret = msm_video_register(video_out, v4l2_dev, name,
-					 i == VFE_LINE_PIX ? 1 : 0);
-		if (ret < 0) {
-			dev_err(dev, "Failed to register video node: %d\n",
-				ret);
-			goto error_reg_video;
-		}
-
-		ret = media_create_pad_link(
-				&sd->entity, MSM_VFE_PAD_SRC,
-				&video_out->vdev.entity, 0,
-				MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
-		if (ret < 0) {
-			dev_err(dev, "Failed to link %s->%s entities: %d\n",
-				sd->entity.name, video_out->vdev.entity.name,
-				ret);
-			goto error_link;
-		}
-	}
-
-	return 0;
-
-error_link:
-	msm_video_unregister(video_out);
-
-error_reg_video:
-	v4l2_device_unregister_subdev(sd);
-
-error_reg_subdev:
-	media_entity_cleanup(&sd->entity);
-
-error_init:
-	for (i--; i >= 0; i--) {
-		sd = &vfe->line[i].subdev;
-		video_out = &vfe->line[i].video_out;
-
-		msm_video_unregister(video_out);
-		v4l2_device_unregister_subdev(sd);
-		media_entity_cleanup(&sd->entity);
-	}
-
-	return ret;
-}
-
-/*
- * msm_vfe_unregister_entities - Unregister VFE module subdev node
- * @vfe: VFE device
- */
-void msm_vfe_unregister_entities(struct vfe_device *vfe)
-{
-	int i;
-
-	mutex_destroy(&vfe->power_lock);
-	mutex_destroy(&vfe->stream_lock);
-
-	for (i = 0; i < ARRAY_SIZE(vfe->line); i++) {
-		struct v4l2_subdev *sd = &vfe->line[i].subdev;
-		struct camss_video *video_out = &vfe->line[i].video_out;
-
-		msm_video_unregister(video_out);
-		v4l2_device_unregister_subdev(sd);
-		media_entity_cleanup(&sd->entity);
-	}
-}
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-vfe.h b/drivers/media/platform/qcom/camss-8x16/camss-vfe.h
deleted file mode 100644
index 53d5b66a9dfb..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-vfe.h
+++ /dev/null
@@ -1,123 +0,0 @@
-/*
- * camss-vfe.h
- *
- * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module
- *
- * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef QC_MSM_CAMSS_VFE_H
-#define QC_MSM_CAMSS_VFE_H
-
-#include <linux/clk.h>
-#include <linux/spinlock_types.h>
-#include <media/media-entity.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-
-#include "camss-video.h"
-
-#define MSM_VFE_PAD_SINK 0
-#define MSM_VFE_PAD_SRC 1
-#define MSM_VFE_PADS_NUM 2
-
-#define MSM_VFE_LINE_NUM 4
-#define MSM_VFE_IMAGE_MASTERS_NUM 7
-#define MSM_VFE_COMPOSITE_IRQ_NUM 4
-
-#define MSM_VFE_VFE0_UB_SIZE 1023
-#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
-#define MSM_VFE_VFE1_UB_SIZE 1535
-#define MSM_VFE_VFE1_UB_SIZE_RDI (MSM_VFE_VFE1_UB_SIZE / 3)
-
-enum vfe_output_state {
-	VFE_OUTPUT_OFF,
-	VFE_OUTPUT_RESERVED,
-	VFE_OUTPUT_SINGLE,
-	VFE_OUTPUT_CONTINUOUS,
-	VFE_OUTPUT_IDLE,
-	VFE_OUTPUT_STOPPING
-};
-
-enum vfe_line_id {
-	VFE_LINE_NONE = -1,
-	VFE_LINE_RDI0 = 0,
-	VFE_LINE_RDI1 = 1,
-	VFE_LINE_RDI2 = 2,
-	VFE_LINE_PIX = 3
-};
-
-struct vfe_output {
-	u8 wm_num;
-	u8 wm_idx[3];
-
-	int active_buf;
-	struct camss_buffer *buf[2];
-	struct camss_buffer *last_buffer;
-	struct list_head pending_bufs;
-
-	unsigned int drop_update_idx;
-
-	enum vfe_output_state state;
-	unsigned int sequence;
-	int wait_sof;
-	int wait_reg_update;
-	struct completion sof;
-	struct completion reg_update;
-};
-
-struct vfe_line {
-	enum vfe_line_id id;
-	struct v4l2_subdev subdev;
-	struct media_pad pads[MSM_VFE_PADS_NUM];
-	struct v4l2_mbus_framefmt fmt[MSM_VFE_PADS_NUM];
-	struct v4l2_rect compose;
-	struct v4l2_rect crop;
-	struct camss_video video_out;
-	struct vfe_output output;
-};
-
-struct vfe_device {
-	u8 id;
-	void __iomem *base;
-	u32 irq;
-	char irq_name[30];
-	struct camss_clock *clock;
-	int nclocks;
-	struct completion reset_complete;
-	struct completion halt_complete;
-	struct mutex power_lock;
-	int power_count;
-	struct mutex stream_lock;
-	int stream_count;
-	spinlock_t output_lock;
-	enum vfe_line_id wm_output_map[MSM_VFE_IMAGE_MASTERS_NUM];
-	struct vfe_line line[MSM_VFE_LINE_NUM];
-	u32 reg_update;
-	u8 was_streaming;
-};
-
-struct resources;
-
-int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res);
-
-int msm_vfe_register_entities(struct vfe_device *vfe,
-			      struct v4l2_device *v4l2_dev);
-
-void msm_vfe_unregister_entities(struct vfe_device *vfe);
-
-void msm_vfe_get_vfe_id(struct media_entity *entity, u8 *id);
-void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id);
-
-void msm_vfe_stop_streaming(struct vfe_device *vfe);
-
-#endif /* QC_MSM_CAMSS_VFE_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-video.c b/drivers/media/platform/qcom/camss-8x16/camss-video.c
deleted file mode 100644
index ffaa2849e0c1..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-video.c
+++ /dev/null
@@ -1,859 +0,0 @@
-/*
- * camss-video.c
- *
- * Qualcomm MSM Camera Subsystem - V4L2 device node
- *
- * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/slab.h>
-#include <media/media-entity.h>
-#include <media/v4l2-dev.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-ioctl.h>
-#include <media/v4l2-mc.h>
-#include <media/videobuf2-dma-sg.h>
-
-#include "camss-video.h"
-#include "camss.h"
-
-struct fract {
-	u8 numerator;
-	u8 denominator;
-};
-
-/*
- * struct camss_format_info - ISP media bus format information
- * @code: V4L2 media bus format code
- * @pixelformat: V4L2 pixel format FCC identifier
- * @planes: Number of planes
- * @hsub: Horizontal subsampling (for each plane)
- * @vsub: Vertical subsampling (for each plane)
- * @bpp: Bits per pixel when stored in memory (for each plane)
- */
-struct camss_format_info {
-	u32 code;
-	u32 pixelformat;
-	u8 planes;
-	struct fract hsub[3];
-	struct fract vsub[3];
-	unsigned int bpp[3];
-};
-
-static const struct camss_format_info formats_rdi[] = {
-	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
-	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
-	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_YUYV, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
-	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_YVYU, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
-	{ MEDIA_BUS_FMT_SBGGR8_1X8, V4L2_PIX_FMT_SBGGR8, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
-	{ MEDIA_BUS_FMT_SGBRG8_1X8, V4L2_PIX_FMT_SGBRG8, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
-	{ MEDIA_BUS_FMT_SGRBG8_1X8, V4L2_PIX_FMT_SGRBG8, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
-	{ MEDIA_BUS_FMT_SRGGB8_1X8, V4L2_PIX_FMT_SRGGB8, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
-	{ MEDIA_BUS_FMT_SBGGR10_1X10, V4L2_PIX_FMT_SBGGR10P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
-	{ MEDIA_BUS_FMT_SGBRG10_1X10, V4L2_PIX_FMT_SGBRG10P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
-	{ MEDIA_BUS_FMT_SGRBG10_1X10, V4L2_PIX_FMT_SGRBG10P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
-	{ MEDIA_BUS_FMT_SRGGB10_1X10, V4L2_PIX_FMT_SRGGB10P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
-	{ MEDIA_BUS_FMT_SBGGR12_1X12, V4L2_PIX_FMT_SBGGR12P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
-	{ MEDIA_BUS_FMT_SGBRG12_1X12, V4L2_PIX_FMT_SGBRG12P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
-	{ MEDIA_BUS_FMT_SGRBG12_1X12, V4L2_PIX_FMT_SGRBG12P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
-	{ MEDIA_BUS_FMT_SRGGB12_1X12, V4L2_PIX_FMT_SRGGB12P, 1,
-	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
-};
-
-static const struct camss_format_info formats_pix[] = {
-	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV12, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV12, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV21, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV21, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
-	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
-	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV16, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV16, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV16, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV16, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV61, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV61, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV61, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV61, 1,
-	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
-};
-
-/* -----------------------------------------------------------------------------
- * Helper functions
- */
-
-static int video_find_format(u32 code, u32 pixelformat,
-			     const struct camss_format_info *formats,
-			     unsigned int nformats)
-{
-	int i;
-
-	for (i = 0; i < nformats; i++) {
-		if (formats[i].code == code &&
-		    formats[i].pixelformat == pixelformat)
-			return i;
-	}
-
-	for (i = 0; i < nformats; i++)
-		if (formats[i].code == code)
-			return i;
-
-	WARN_ON(1);
-
-	return -EINVAL;
-}
-
-/*
- * video_mbus_to_pix_mp - Convert v4l2_mbus_framefmt to v4l2_pix_format_mplane
- * @mbus: v4l2_mbus_framefmt format (input)
- * @pix: v4l2_pix_format_mplane format (output)
- * @f: a pointer to formats array element to be used for the conversion
- * @alignment: bytesperline alignment value
- *
- * Fill the output pix structure with information from the input mbus format.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int video_mbus_to_pix_mp(const struct v4l2_mbus_framefmt *mbus,
-				struct v4l2_pix_format_mplane *pix,
-				const struct camss_format_info *f,
-				unsigned int alignment)
-{
-	unsigned int i;
-	u32 bytesperline;
-
-	memset(pix, 0, sizeof(*pix));
-	v4l2_fill_pix_format_mplane(pix, mbus);
-	pix->pixelformat = f->pixelformat;
-	pix->num_planes = f->planes;
-	for (i = 0; i < pix->num_planes; i++) {
-		bytesperline = pix->width / f->hsub[i].numerator *
-			f->hsub[i].denominator * f->bpp[i] / 8;
-		bytesperline = ALIGN(bytesperline, alignment);
-		pix->plane_fmt[i].bytesperline = bytesperline;
-		pix->plane_fmt[i].sizeimage = pix->height /
-				f->vsub[i].numerator * f->vsub[i].denominator *
-				bytesperline;
-	}
-
-	return 0;
-}
-
-static struct v4l2_subdev *video_remote_subdev(struct camss_video *video,
-					       u32 *pad)
-{
-	struct media_pad *remote;
-
-	remote = media_entity_remote_pad(&video->pad);
-
-	if (!remote || !is_media_entity_v4l2_subdev(remote->entity))
-		return NULL;
-
-	if (pad)
-		*pad = remote->index;
-
-	return media_entity_to_v4l2_subdev(remote->entity);
-}
-
-static int video_get_subdev_format(struct camss_video *video,
-				   struct v4l2_format *format)
-{
-	struct v4l2_subdev_format fmt;
-	struct v4l2_subdev *subdev;
-	u32 pad;
-	int ret;
-
-	subdev = video_remote_subdev(video, &pad);
-	if (subdev == NULL)
-		return -EPIPE;
-
-	fmt.pad = pad;
-	fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
-
-	ret = v4l2_subdev_call(subdev, pad, get_fmt, NULL, &fmt);
-	if (ret)
-		return ret;
-
-	ret = video_find_format(fmt.format.code,
-				format->fmt.pix_mp.pixelformat,
-				video->formats, video->nformats);
-	if (ret < 0)
-		return ret;
-
-	format->type = video->type;
-
-	return video_mbus_to_pix_mp(&fmt.format, &format->fmt.pix_mp,
-				    &video->formats[ret], video->bpl_alignment);
-}
-
-/* -----------------------------------------------------------------------------
- * Video queue operations
- */
-
-static int video_queue_setup(struct vb2_queue *q,
-	unsigned int *num_buffers, unsigned int *num_planes,
-	unsigned int sizes[], struct device *alloc_devs[])
-{
-	struct camss_video *video = vb2_get_drv_priv(q);
-	const struct v4l2_pix_format_mplane *format =
-						&video->active_fmt.fmt.pix_mp;
-	unsigned int i;
-
-	if (*num_planes) {
-		if (*num_planes != format->num_planes)
-			return -EINVAL;
-
-		for (i = 0; i < *num_planes; i++)
-			if (sizes[i] < format->plane_fmt[i].sizeimage)
-				return -EINVAL;
-
-		return 0;
-	}
-
-	*num_planes = format->num_planes;
-
-	for (i = 0; i < *num_planes; i++)
-		sizes[i] = format->plane_fmt[i].sizeimage;
-
-	return 0;
-}
-
-static int video_buf_init(struct vb2_buffer *vb)
-{
-	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct camss_video *video = vb2_get_drv_priv(vb->vb2_queue);
-	struct camss_buffer *buffer = container_of(vbuf, struct camss_buffer,
-						   vb);
-	const struct v4l2_pix_format_mplane *format =
-						&video->active_fmt.fmt.pix_mp;
-	struct sg_table *sgt;
-	unsigned int i;
-
-	for (i = 0; i < format->num_planes; i++) {
-		sgt = vb2_dma_sg_plane_desc(vb, i);
-		if (!sgt)
-			return -EFAULT;
-
-		buffer->addr[i] = sg_dma_address(sgt->sgl);
-	}
-
-	if (format->pixelformat == V4L2_PIX_FMT_NV12 ||
-			format->pixelformat == V4L2_PIX_FMT_NV21 ||
-			format->pixelformat == V4L2_PIX_FMT_NV16 ||
-			format->pixelformat == V4L2_PIX_FMT_NV61)
-		buffer->addr[1] = buffer->addr[0] +
-				format->plane_fmt[0].bytesperline *
-				format->height;
-
-	return 0;
-}
-
-static int video_buf_prepare(struct vb2_buffer *vb)
-{
-	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct camss_video *video = vb2_get_drv_priv(vb->vb2_queue);
-	const struct v4l2_pix_format_mplane *format =
-						&video->active_fmt.fmt.pix_mp;
-	unsigned int i;
-
-	for (i = 0; i < format->num_planes; i++) {
-		if (format->plane_fmt[i].sizeimage > vb2_plane_size(vb, i))
-			return -EINVAL;
-
-		vb2_set_plane_payload(vb, i, format->plane_fmt[i].sizeimage);
-	}
-
-	vbuf->field = V4L2_FIELD_NONE;
-
-	return 0;
-}
-
-static void video_buf_queue(struct vb2_buffer *vb)
-{
-	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
-	struct camss_video *video = vb2_get_drv_priv(vb->vb2_queue);
-	struct camss_buffer *buffer = container_of(vbuf, struct camss_buffer,
-						   vb);
-
-	video->ops->queue_buffer(video, buffer);
-}
-
-static int video_check_format(struct camss_video *video)
-{
-	struct v4l2_pix_format_mplane *pix = &video->active_fmt.fmt.pix_mp;
-	struct v4l2_format format;
-	struct v4l2_pix_format_mplane *sd_pix = &format.fmt.pix_mp;
-	int ret;
-
-	sd_pix->pixelformat = pix->pixelformat;
-	ret = video_get_subdev_format(video, &format);
-	if (ret < 0)
-		return ret;
-
-	if (pix->pixelformat != sd_pix->pixelformat ||
-	    pix->height != sd_pix->height ||
-	    pix->width != sd_pix->width ||
-	    pix->num_planes != sd_pix->num_planes ||
-	    pix->field != format.fmt.pix_mp.field)
-		return -EPIPE;
-
-	return 0;
-}
-
-static int video_start_streaming(struct vb2_queue *q, unsigned int count)
-{
-	struct camss_video *video = vb2_get_drv_priv(q);
-	struct video_device *vdev = &video->vdev;
-	struct media_entity *entity;
-	struct media_pad *pad;
-	struct v4l2_subdev *subdev;
-	int ret;
-
-	ret = media_pipeline_start(&vdev->entity, &video->pipe);
-	if (ret < 0)
-		return ret;
-
-	ret = video_check_format(video);
-	if (ret < 0)
-		goto error;
-
-	entity = &vdev->entity;
-	while (1) {
-		pad = &entity->pads[0];
-		if (!(pad->flags & MEDIA_PAD_FL_SINK))
-			break;
-
-		pad = media_entity_remote_pad(pad);
-		if (!pad || !is_media_entity_v4l2_subdev(pad->entity))
-			break;
-
-		entity = pad->entity;
-		subdev = media_entity_to_v4l2_subdev(entity);
-
-		ret = v4l2_subdev_call(subdev, video, s_stream, 1);
-		if (ret < 0 && ret != -ENOIOCTLCMD)
-			goto error;
-	}
-
-	return 0;
-
-error:
-	media_pipeline_stop(&vdev->entity);
-
-	video->ops->flush_buffers(video, VB2_BUF_STATE_QUEUED);
-
-	return ret;
-}
-
-static void video_stop_streaming(struct vb2_queue *q)
-{
-	struct camss_video *video = vb2_get_drv_priv(q);
-	struct video_device *vdev = &video->vdev;
-	struct media_entity *entity;
-	struct media_pad *pad;
-	struct v4l2_subdev *subdev;
-
-	entity = &vdev->entity;
-	while (1) {
-		pad = &entity->pads[0];
-		if (!(pad->flags & MEDIA_PAD_FL_SINK))
-			break;
-
-		pad = media_entity_remote_pad(pad);
-		if (!pad || !is_media_entity_v4l2_subdev(pad->entity))
-			break;
-
-		entity = pad->entity;
-		subdev = media_entity_to_v4l2_subdev(entity);
-
-		v4l2_subdev_call(subdev, video, s_stream, 0);
-	}
-
-	media_pipeline_stop(&vdev->entity);
-
-	video->ops->flush_buffers(video, VB2_BUF_STATE_ERROR);
-}
-
-static const struct vb2_ops msm_video_vb2_q_ops = {
-	.queue_setup     = video_queue_setup,
-	.wait_prepare    = vb2_ops_wait_prepare,
-	.wait_finish     = vb2_ops_wait_finish,
-	.buf_init        = video_buf_init,
-	.buf_prepare     = video_buf_prepare,
-	.buf_queue       = video_buf_queue,
-	.start_streaming = video_start_streaming,
-	.stop_streaming  = video_stop_streaming,
-};
-
-/* -----------------------------------------------------------------------------
- * V4L2 ioctls
- */
-
-static int video_querycap(struct file *file, void *fh,
-			  struct v4l2_capability *cap)
-{
-	struct camss_video *video = video_drvdata(file);
-
-	strlcpy(cap->driver, "qcom-camss", sizeof(cap->driver));
-	strlcpy(cap->card, "Qualcomm Camera Subsystem", sizeof(cap->card));
-	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
-		 dev_name(video->camss->dev));
-
-	return 0;
-}
-
-static int video_enum_fmt(struct file *file, void *fh, struct v4l2_fmtdesc *f)
-{
-	struct camss_video *video = video_drvdata(file);
-	int i, j, k;
-
-	if (f->type != video->type)
-		return -EINVAL;
-
-	if (f->index >= video->nformats)
-		return -EINVAL;
-
-	/* find index "i" of "k"th unique pixelformat in formats array */
-	k = -1;
-	for (i = 0; i < video->nformats; i++) {
-		for (j = 0; j < i; j++) {
-			if (video->formats[i].pixelformat ==
-					video->formats[j].pixelformat)
-				break;
-		}
-
-		if (j == i)
-			k++;
-
-		if (k == f->index)
-			break;
-	}
-
-	if (k < f->index)
-		return -EINVAL;
-
-	f->pixelformat = video->formats[i].pixelformat;
-
-	return 0;
-}
-
-static int video_g_fmt(struct file *file, void *fh, struct v4l2_format *f)
-{
-	struct camss_video *video = video_drvdata(file);
-
-	*f = video->active_fmt;
-
-	return 0;
-}
-
-static int __video_try_fmt(struct camss_video *video, struct v4l2_format *f)
-{
-	struct v4l2_pix_format_mplane *pix_mp;
-	const struct camss_format_info *fi;
-	struct v4l2_plane_pix_format *p;
-	u32 bytesperline[3] = { 0 };
-	u32 sizeimage[3] = { 0 };
-	u32 width, height;
-	u32 bpl, lines;
-	int i, j;
-
-	pix_mp = &f->fmt.pix_mp;
-
-	if (video->line_based)
-		for (i = 0; i < pix_mp->num_planes && i < 3; i++) {
-			p = &pix_mp->plane_fmt[i];
-			bytesperline[i] = clamp_t(u32, p->bytesperline,
-						  1, 65528);
-			sizeimage[i] = clamp_t(u32, p->sizeimage,
-					       bytesperline[i],
-					       bytesperline[i] * 4096);
-		}
-
-	for (j = 0; j < video->nformats; j++)
-		if (pix_mp->pixelformat == video->formats[j].pixelformat)
-			break;
-
-	if (j == video->nformats)
-		j = 0; /* default format */
-
-	fi = &video->formats[j];
-	width = pix_mp->width;
-	height = pix_mp->height;
-
-	memset(pix_mp, 0, sizeof(*pix_mp));
-
-	pix_mp->pixelformat = fi->pixelformat;
-	pix_mp->width = clamp_t(u32, width, 1, 8191);
-	pix_mp->height = clamp_t(u32, height, 1, 8191);
-	pix_mp->num_planes = fi->planes;
-	for (i = 0; i < pix_mp->num_planes; i++) {
-		bpl = pix_mp->width / fi->hsub[i].numerator *
-			fi->hsub[i].denominator * fi->bpp[i] / 8;
-		bpl = ALIGN(bpl, video->bpl_alignment);
-		pix_mp->plane_fmt[i].bytesperline = bpl;
-		pix_mp->plane_fmt[i].sizeimage = pix_mp->height /
-			fi->vsub[i].numerator * fi->vsub[i].denominator * bpl;
-	}
-
-	pix_mp->field = V4L2_FIELD_NONE;
-	pix_mp->colorspace = V4L2_COLORSPACE_SRGB;
-	pix_mp->flags = 0;
-	pix_mp->ycbcr_enc = V4L2_MAP_YCBCR_ENC_DEFAULT(pix_mp->colorspace);
-	pix_mp->quantization = V4L2_MAP_QUANTIZATION_DEFAULT(true,
-					pix_mp->colorspace, pix_mp->ycbcr_enc);
-	pix_mp->xfer_func = V4L2_MAP_XFER_FUNC_DEFAULT(pix_mp->colorspace);
-
-	if (video->line_based)
-		for (i = 0; i < pix_mp->num_planes; i++) {
-			p = &pix_mp->plane_fmt[i];
-			p->bytesperline = clamp_t(u32, p->bytesperline,
-						  1, 65528);
-			p->sizeimage = clamp_t(u32, p->sizeimage,
-					       p->bytesperline,
-					       p->bytesperline * 4096);
-			lines = p->sizeimage / p->bytesperline;
-
-			if (p->bytesperline < bytesperline[i])
-				p->bytesperline = ALIGN(bytesperline[i], 8);
-
-			if (p->sizeimage < p->bytesperline * lines)
-				p->sizeimage = p->bytesperline * lines;
-
-			if (p->sizeimage < sizeimage[i])
-				p->sizeimage = sizeimage[i];
-		}
-
-	return 0;
-}
-
-static int video_try_fmt(struct file *file, void *fh, struct v4l2_format *f)
-{
-	struct camss_video *video = video_drvdata(file);
-
-	return __video_try_fmt(video, f);
-}
-
-static int video_s_fmt(struct file *file, void *fh, struct v4l2_format *f)
-{
-	struct camss_video *video = video_drvdata(file);
-	int ret;
-
-	if (vb2_is_busy(&video->vb2_q))
-		return -EBUSY;
-
-	ret = __video_try_fmt(video, f);
-	if (ret < 0)
-		return ret;
-
-	video->active_fmt = *f;
-
-	return 0;
-}
-
-static int video_enum_input(struct file *file, void *fh,
-			    struct v4l2_input *input)
-{
-	if (input->index > 0)
-		return -EINVAL;
-
-	strlcpy(input->name, "camera", sizeof(input->name));
-	input->type = V4L2_INPUT_TYPE_CAMERA;
-
-	return 0;
-}
-
-static int video_g_input(struct file *file, void *fh, unsigned int *input)
-{
-	*input = 0;
-
-	return 0;
-}
-
-static int video_s_input(struct file *file, void *fh, unsigned int input)
-{
-	return input == 0 ? 0 : -EINVAL;
-}
-
-static const struct v4l2_ioctl_ops msm_vid_ioctl_ops = {
-	.vidioc_querycap		= video_querycap,
-	.vidioc_enum_fmt_vid_cap_mplane	= video_enum_fmt,
-	.vidioc_g_fmt_vid_cap_mplane	= video_g_fmt,
-	.vidioc_s_fmt_vid_cap_mplane	= video_s_fmt,
-	.vidioc_try_fmt_vid_cap_mplane	= video_try_fmt,
-	.vidioc_reqbufs			= vb2_ioctl_reqbufs,
-	.vidioc_querybuf		= vb2_ioctl_querybuf,
-	.vidioc_qbuf			= vb2_ioctl_qbuf,
-	.vidioc_expbuf			= vb2_ioctl_expbuf,
-	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
-	.vidioc_create_bufs		= vb2_ioctl_create_bufs,
-	.vidioc_prepare_buf		= vb2_ioctl_prepare_buf,
-	.vidioc_streamon		= vb2_ioctl_streamon,
-	.vidioc_streamoff		= vb2_ioctl_streamoff,
-	.vidioc_enum_input		= video_enum_input,
-	.vidioc_g_input			= video_g_input,
-	.vidioc_s_input			= video_s_input,
-};
-
-/* -----------------------------------------------------------------------------
- * V4L2 file operations
- */
-
-static int video_open(struct file *file)
-{
-	struct video_device *vdev = video_devdata(file);
-	struct camss_video *video = video_drvdata(file);
-	struct v4l2_fh *vfh;
-	int ret;
-
-	mutex_lock(&video->lock);
-
-	vfh = kzalloc(sizeof(*vfh), GFP_KERNEL);
-	if (vfh == NULL) {
-		ret = -ENOMEM;
-		goto error_alloc;
-	}
-
-	v4l2_fh_init(vfh, vdev);
-	v4l2_fh_add(vfh);
-
-	file->private_data = vfh;
-
-	ret = v4l2_pipeline_pm_use(&vdev->entity, 1);
-	if (ret < 0) {
-		dev_err(video->camss->dev, "Failed to power up pipeline: %d\n",
-			ret);
-		goto error_pm_use;
-	}
-
-	mutex_unlock(&video->lock);
-
-	return 0;
-
-error_pm_use:
-	v4l2_fh_release(file);
-
-error_alloc:
-	mutex_unlock(&video->lock);
-
-	return ret;
-}
-
-static int video_release(struct file *file)
-{
-	struct video_device *vdev = video_devdata(file);
-
-	vb2_fop_release(file);
-
-	v4l2_pipeline_pm_use(&vdev->entity, 0);
-
-	file->private_data = NULL;
-
-	return 0;
-}
-
-static const struct v4l2_file_operations msm_vid_fops = {
-	.owner          = THIS_MODULE,
-	.unlocked_ioctl = video_ioctl2,
-	.open           = video_open,
-	.release        = video_release,
-	.poll           = vb2_fop_poll,
-	.mmap		= vb2_fop_mmap,
-	.read		= vb2_fop_read,
-};
-
-/* -----------------------------------------------------------------------------
- * CAMSS video core
- */
-
-static void msm_video_release(struct video_device *vdev)
-{
-	struct camss_video *video = video_get_drvdata(vdev);
-
-	media_entity_cleanup(&vdev->entity);
-
-	mutex_destroy(&video->q_lock);
-	mutex_destroy(&video->lock);
-
-	if (atomic_dec_and_test(&video->camss->ref_count))
-		camss_delete(video->camss);
-}
-
-/*
- * msm_video_init_format - Helper function to initialize format
- * @video: struct camss_video
- *
- * Initialize pad format with default value.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int msm_video_init_format(struct camss_video *video)
-{
-	int ret;
-	struct v4l2_format format = {
-		.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE,
-		.fmt.pix_mp = {
-			.width = 1920,
-			.height = 1080,
-			.pixelformat = video->formats[0].pixelformat,
-		},
-	};
-
-	ret = __video_try_fmt(video, &format);
-	if (ret < 0)
-		return ret;
-
-	video->active_fmt = format;
-
-	return 0;
-}
-
-/*
- * msm_video_register - Register a video device node
- * @video: struct camss_video
- * @v4l2_dev: V4L2 device
- * @name: name to be used for the video device node
- *
- * Initialize and register a video device node to a V4L2 device. Also
- * initialize the vb2 queue.
- *
- * Return 0 on success or a negative error code otherwise
- */
-
-int msm_video_register(struct camss_video *video, struct v4l2_device *v4l2_dev,
-		       const char *name, int is_pix)
-{
-	struct media_pad *pad = &video->pad;
-	struct video_device *vdev;
-	struct vb2_queue *q;
-	int ret;
-
-	vdev = &video->vdev;
-
-	mutex_init(&video->q_lock);
-
-	q = &video->vb2_q;
-	q->drv_priv = video;
-	q->mem_ops = &vb2_dma_sg_memops;
-	q->ops = &msm_video_vb2_q_ops;
-	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
-	q->io_modes = VB2_DMABUF | VB2_MMAP | VB2_READ;
-	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
-	q->buf_struct_size = sizeof(struct camss_buffer);
-	q->dev = video->camss->dev;
-	q->lock = &video->q_lock;
-	ret = vb2_queue_init(q);
-	if (ret < 0) {
-		dev_err(v4l2_dev->dev, "Failed to init vb2 queue: %d\n", ret);
-		goto error_vb2_init;
-	}
-
-	pad->flags = MEDIA_PAD_FL_SINK;
-	ret = media_entity_pads_init(&vdev->entity, 1, pad);
-	if (ret < 0) {
-		dev_err(v4l2_dev->dev, "Failed to init video entity: %d\n",
-			ret);
-		goto error_media_init;
-	}
-
-	mutex_init(&video->lock);
-
-	video->formats = formats_rdi;
-	video->nformats = ARRAY_SIZE(formats_rdi);
-	if (is_pix) {
-		video->formats = formats_pix;
-		video->nformats = ARRAY_SIZE(formats_pix);
-	}
-
-	ret = msm_video_init_format(video);
-	if (ret < 0) {
-		dev_err(v4l2_dev->dev, "Failed to init format: %d\n", ret);
-		goto error_video_register;
-	}
-
-	vdev->fops = &msm_vid_fops;
-	vdev->device_caps = V4L2_CAP_VIDEO_CAPTURE_MPLANE | V4L2_CAP_STREAMING |
-							V4L2_CAP_READWRITE;
-	vdev->ioctl_ops = &msm_vid_ioctl_ops;
-	vdev->release = msm_video_release;
-	vdev->v4l2_dev = v4l2_dev;
-	vdev->vfl_dir = VFL_DIR_RX;
-	vdev->queue = &video->vb2_q;
-	vdev->lock = &video->lock;
-	strlcpy(vdev->name, name, sizeof(vdev->name));
-
-	ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
-	if (ret < 0) {
-		dev_err(v4l2_dev->dev, "Failed to register video device: %d\n",
-			ret);
-		goto error_video_register;
-	}
-
-	video_set_drvdata(vdev, video);
-	atomic_inc(&video->camss->ref_count);
-
-	return 0;
-
-error_video_register:
-	media_entity_cleanup(&vdev->entity);
-	mutex_destroy(&video->lock);
-error_media_init:
-	vb2_queue_release(&video->vb2_q);
-error_vb2_init:
-	mutex_destroy(&video->q_lock);
-
-	return ret;
-}
-
-void msm_video_stop_streaming(struct camss_video *video)
-{
-	if (vb2_is_streaming(&video->vb2_q))
-		vb2_queue_release(&video->vb2_q);
-}
-
-void msm_video_unregister(struct camss_video *video)
-{
-	atomic_inc(&video->camss->ref_count);
-	video_unregister_device(&video->vdev);
-	atomic_dec(&video->camss->ref_count);
-}
diff --git a/drivers/media/platform/qcom/camss-8x16/camss-video.h b/drivers/media/platform/qcom/camss-8x16/camss-video.h
deleted file mode 100644
index 38bd1f2eec54..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss-video.h
+++ /dev/null
@@ -1,70 +0,0 @@
-/*
- * camss-video.h
- *
- * Qualcomm MSM Camera Subsystem - V4L2 device node
- *
- * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef QC_MSM_CAMSS_VIDEO_H
-#define QC_MSM_CAMSS_VIDEO_H
-
-#include <linux/mutex.h>
-#include <linux/videodev2.h>
-#include <media/media-entity.h>
-#include <media/v4l2-dev.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-fh.h>
-#include <media/v4l2-mediabus.h>
-#include <media/videobuf2-v4l2.h>
-
-struct camss_buffer {
-	struct vb2_v4l2_buffer vb;
-	dma_addr_t addr[3];
-	struct list_head queue;
-};
-
-struct camss_video;
-
-struct camss_video_ops {
-	int (*queue_buffer)(struct camss_video *vid, struct camss_buffer *buf);
-	int (*flush_buffers)(struct camss_video *vid,
-			     enum vb2_buffer_state state);
-};
-
-struct camss_format_info;
-
-struct camss_video {
-	struct camss *camss;
-	struct vb2_queue vb2_q;
-	struct video_device vdev;
-	struct media_pad pad;
-	struct v4l2_format active_fmt;
-	enum v4l2_buf_type type;
-	struct media_pipeline pipe;
-	const struct camss_video_ops *ops;
-	struct mutex lock;
-	struct mutex q_lock;
-	unsigned int bpl_alignment;
-	unsigned int line_based;
-	const struct camss_format_info *formats;
-	unsigned int nformats;
-};
-
-void msm_video_stop_streaming(struct camss_video *video);
-
-int msm_video_register(struct camss_video *video, struct v4l2_device *v4l2_dev,
-		       const char *name, int is_pix);
-
-void msm_video_unregister(struct camss_video *video);
-
-#endif /* QC_MSM_CAMSS_VIDEO_H */
diff --git a/drivers/media/platform/qcom/camss-8x16/camss.c b/drivers/media/platform/qcom/camss-8x16/camss.c
deleted file mode 100644
index 23fda6207a23..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss.c
+++ /dev/null
@@ -1,751 +0,0 @@
-/*
- * camss.c
- *
- * Qualcomm MSM Camera Subsystem - Core
- *
- * Copyright (c) 2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#include <linux/clk.h>
-#include <linux/media-bus-format.h>
-#include <linux/media.h>
-#include <linux/module.h>
-#include <linux/platform_device.h>
-#include <linux/of.h>
-#include <linux/of_graph.h>
-#include <linux/slab.h>
-#include <linux/videodev2.h>
-
-#include <media/media-device.h>
-#include <media/v4l2-async.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-mc.h>
-#include <media/v4l2-fwnode.h>
-
-#include "camss.h"
-
-#define CAMSS_CLOCK_MARGIN_NUMERATOR 105
-#define CAMSS_CLOCK_MARGIN_DENOMINATOR 100
-
-static const struct resources csiphy_res[] = {
-	/* CSIPHY0 */
-	{
-		.regulator = { NULL },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "camss_ahb", "csiphy0_timer" },
-		.clock_rate = { { 0 },
-				{ 0 },
-				{ 0 },
-				{ 100000000, 200000000 } },
-		.reg = { "csiphy0", "csiphy0_clk_mux" },
-		.interrupt = { "csiphy0" }
-	},
-
-	/* CSIPHY1 */
-	{
-		.regulator = { NULL },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "camss_ahb", "csiphy1_timer" },
-		.clock_rate = { { 0 },
-				{ 0 },
-				{ 0 },
-				{ 100000000, 200000000 } },
-		.reg = { "csiphy1", "csiphy1_clk_mux" },
-		.interrupt = { "csiphy1" }
-	}
-};
-
-static const struct resources csid_res[] = {
-	/* CSID0 */
-	{
-		.regulator = { "vdda" },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "csi0_ahb", "camss_ahb",
-			   "csi0", "csi0_phy", "csi0_pix", "csi0_rdi" },
-		.clock_rate = { { 0 },
-				{ 0 },
-				{ 0 },
-				{ 0 },
-				{ 100000000, 200000000 },
-				{ 0 },
-				{ 0 },
-				{ 0 } },
-		.reg = { "csid0" },
-		.interrupt = { "csid0" }
-	},
-
-	/* CSID1 */
-	{
-		.regulator = { "vdda" },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "csi1_ahb", "camss_ahb",
-			   "csi1", "csi1_phy", "csi1_pix", "csi1_rdi" },
-		.clock_rate = { { 0 },
-				{ 0 },
-				{ 0 },
-				{ 0 },
-				{ 100000000, 200000000 },
-				{ 0 },
-				{ 0 },
-				{ 0 } },
-		.reg = { "csid1" },
-		.interrupt = { "csid1" }
-	},
-};
-
-static const struct resources_ispif ispif_res = {
-	/* ISPIF */
-	.clock = { "camss_top_ahb", "camss_ahb", "ispif_ahb",
-		   "csi0", "csi0_pix", "csi0_rdi",
-		   "csi1", "csi1_pix", "csi1_rdi" },
-	.clock_for_reset = { "camss_vfe_vfe", "camss_csi_vfe" },
-	.reg = { "ispif", "csi_clk_mux" },
-	.interrupt = "ispif"
-
-};
-
-static const struct resources vfe_res = {
-	/* VFE0 */
-	.regulator = { NULL },
-	.clock = { "camss_top_ahb", "camss_vfe_vfe", "camss_csi_vfe",
-		   "iface", "bus", "camss_ahb" },
-	.clock_rate = { { 0 },
-			{ 50000000, 80000000, 100000000, 160000000,
-			  177780000, 200000000, 266670000, 320000000,
-			  400000000, 465000000 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 } },
-	.reg = { "vfe0" },
-	.interrupt = { "vfe0" }
-};
-
-/*
- * camss_add_clock_margin - Add margin to clock frequency rate
- * @rate: Clock frequency rate
- *
- * When making calculations with physical clock frequency values
- * some safety margin must be added. Add it.
- */
-inline void camss_add_clock_margin(u64 *rate)
-{
-	*rate *= CAMSS_CLOCK_MARGIN_NUMERATOR;
-	*rate = div_u64(*rate, CAMSS_CLOCK_MARGIN_DENOMINATOR);
-}
-
-/*
- * camss_enable_clocks - Enable multiple clocks
- * @nclocks: Number of clocks in clock array
- * @clock: Clock array
- * @dev: Device
- *
- * Return 0 on success or a negative error code otherwise
- */
-int camss_enable_clocks(int nclocks, struct camss_clock *clock,
-			struct device *dev)
-{
-	int ret;
-	int i;
-
-	for (i = 0; i < nclocks; i++) {
-		ret = clk_prepare_enable(clock[i].clk);
-		if (ret) {
-			dev_err(dev, "clock enable failed: %d\n", ret);
-			goto error;
-		}
-	}
-
-	return 0;
-
-error:
-	for (i--; i >= 0; i--)
-		clk_disable_unprepare(clock[i].clk);
-
-	return ret;
-}
-
-/*
- * camss_disable_clocks - Disable multiple clocks
- * @nclocks: Number of clocks in clock array
- * @clock: Clock array
- */
-void camss_disable_clocks(int nclocks, struct camss_clock *clock)
-{
-	int i;
-
-	for (i = nclocks - 1; i >= 0; i--)
-		clk_disable_unprepare(clock[i].clk);
-}
-
-/*
- * camss_find_sensor - Find a linked media entity which represents a sensor
- * @entity: Media entity to start searching from
- *
- * Return a pointer to sensor media entity or NULL if not found
- */
-static struct media_entity *camss_find_sensor(struct media_entity *entity)
-{
-	struct media_pad *pad;
-
-	while (1) {
-		pad = &entity->pads[0];
-		if (!(pad->flags & MEDIA_PAD_FL_SINK))
-			return NULL;
-
-		pad = media_entity_remote_pad(pad);
-		if (!pad || !is_media_entity_v4l2_subdev(pad->entity))
-			return NULL;
-
-		entity = pad->entity;
-
-		if (entity->function == MEDIA_ENT_F_CAM_SENSOR)
-			return entity;
-	}
-}
-
-/*
- * camss_get_pixel_clock - Get pixel clock rate from sensor
- * @entity: Media entity in the current pipeline
- * @pixel_clock: Received pixel clock value
- *
- * Return 0 on success or a negative error code otherwise
- */
-int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock)
-{
-	struct media_entity *sensor;
-	struct v4l2_subdev *subdev;
-	struct v4l2_ctrl *ctrl;
-
-	sensor = camss_find_sensor(entity);
-	if (!sensor)
-		return -ENODEV;
-
-	subdev = media_entity_to_v4l2_subdev(sensor);
-
-	ctrl = v4l2_ctrl_find(subdev->ctrl_handler, V4L2_CID_PIXEL_RATE);
-
-	if (!ctrl)
-		return -EINVAL;
-
-	*pixel_clock = v4l2_ctrl_g_ctrl_int64(ctrl);
-
-	return 0;
-}
-
-/*
- * camss_of_parse_endpoint_node - Parse port endpoint node
- * @dev: Device
- * @node: Device node to be parsed
- * @csd: Parsed data from port endpoint node
- *
- * Return 0 on success or a negative error code on failure
- */
-static int camss_of_parse_endpoint_node(struct device *dev,
-					struct device_node *node,
-					struct camss_async_subdev *csd)
-{
-	struct csiphy_lanes_cfg *lncfg = &csd->interface.csi2.lane_cfg;
-	struct v4l2_fwnode_bus_mipi_csi2 *mipi_csi2;
-	struct v4l2_fwnode_endpoint vep = { { 0 } };
-	unsigned int i;
-
-	v4l2_fwnode_endpoint_parse(of_fwnode_handle(node), &vep);
-
-	csd->interface.csiphy_id = vep.base.port;
-
-	mipi_csi2 = &vep.bus.mipi_csi2;
-	lncfg->clk.pos = mipi_csi2->clock_lane;
-	lncfg->clk.pol = mipi_csi2->lane_polarities[0];
-	lncfg->num_data = mipi_csi2->num_data_lanes;
-
-	lncfg->data = devm_kcalloc(dev,
-				   lncfg->num_data, sizeof(*lncfg->data),
-				   GFP_KERNEL);
-	if (!lncfg->data)
-		return -ENOMEM;
-
-	for (i = 0; i < lncfg->num_data; i++) {
-		lncfg->data[i].pos = mipi_csi2->data_lanes[i];
-		lncfg->data[i].pol = mipi_csi2->lane_polarities[i + 1];
-	}
-
-	return 0;
-}
-
-/*
- * camss_of_parse_ports - Parse ports node
- * @dev: Device
- * @notifier: v4l2_device notifier data
- *
- * Return number of "port" nodes found in "ports" node
- */
-static int camss_of_parse_ports(struct device *dev,
-				struct v4l2_async_notifier *notifier)
-{
-	struct device_node *node = NULL;
-	struct device_node *remote = NULL;
-	unsigned int size, i;
-	int ret;
-
-	while ((node = of_graph_get_next_endpoint(dev->of_node, node)))
-		if (of_device_is_available(node))
-			notifier->num_subdevs++;
-
-	size = sizeof(*notifier->subdevs) * notifier->num_subdevs;
-	notifier->subdevs = devm_kzalloc(dev, size, GFP_KERNEL);
-	if (!notifier->subdevs) {
-		dev_err(dev, "Failed to allocate memory\n");
-		return -ENOMEM;
-	}
-
-	i = 0;
-	while ((node = of_graph_get_next_endpoint(dev->of_node, node))) {
-		struct camss_async_subdev *csd;
-
-		if (!of_device_is_available(node))
-			continue;
-
-		csd = devm_kzalloc(dev, sizeof(*csd), GFP_KERNEL);
-		if (!csd) {
-			of_node_put(node);
-			dev_err(dev, "Failed to allocate memory\n");
-			return -ENOMEM;
-		}
-
-		notifier->subdevs[i++] = &csd->asd;
-
-		ret = camss_of_parse_endpoint_node(dev, node, csd);
-		if (ret < 0) {
-			of_node_put(node);
-			return ret;
-		}
-
-		remote = of_graph_get_remote_port_parent(node);
-		of_node_put(node);
-
-		if (!remote) {
-			dev_err(dev, "Cannot get remote parent\n");
-			return -EINVAL;
-		}
-
-		csd->asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
-		csd->asd.match.fwnode = of_fwnode_handle(remote);
-	}
-
-	return notifier->num_subdevs;
-}
-
-/*
- * camss_init_subdevices - Initialize subdev structures and resources
- * @camss: CAMSS device
- *
- * Return 0 on success or a negative error code on failure
- */
-static int camss_init_subdevices(struct camss *camss)
-{
-	unsigned int i;
-	int ret;
-
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
-		ret = msm_csiphy_subdev_init(&camss->csiphy[i],
-					     &csiphy_res[i], i);
-		if (ret < 0) {
-			dev_err(camss->dev,
-				"Failed to init csiphy%d sub-device: %d\n",
-				i, ret);
-			return ret;
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
-		ret = msm_csid_subdev_init(&camss->csid[i],
-					   &csid_res[i], i);
-		if (ret < 0) {
-			dev_err(camss->dev,
-				"Failed to init csid%d sub-device: %d\n",
-				i, ret);
-			return ret;
-		}
-	}
-
-	ret = msm_ispif_subdev_init(&camss->ispif, &ispif_res);
-	if (ret < 0) {
-		dev_err(camss->dev, "Failed to init ispif sub-device: %d\n",
-			ret);
-		return ret;
-	}
-
-	ret = msm_vfe_subdev_init(&camss->vfe, &vfe_res);
-	if (ret < 0) {
-		dev_err(camss->dev, "Fail to init vfe sub-device: %d\n", ret);
-		return ret;
-	}
-
-	return 0;
-}
-
-/*
- * camss_register_entities - Register subdev nodes and create links
- * @camss: CAMSS device
- *
- * Return 0 on success or a negative error code on failure
- */
-static int camss_register_entities(struct camss *camss)
-{
-	int i, j;
-	int ret;
-
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
-		ret = msm_csiphy_register_entity(&camss->csiphy[i],
-						 &camss->v4l2_dev);
-		if (ret < 0) {
-			dev_err(camss->dev,
-				"Failed to register csiphy%d entity: %d\n",
-				i, ret);
-			goto err_reg_csiphy;
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
-		ret = msm_csid_register_entity(&camss->csid[i],
-					       &camss->v4l2_dev);
-		if (ret < 0) {
-			dev_err(camss->dev,
-				"Failed to register csid%d entity: %d\n",
-				i, ret);
-			goto err_reg_csid;
-		}
-	}
-
-	ret = msm_ispif_register_entities(&camss->ispif, &camss->v4l2_dev);
-	if (ret < 0) {
-		dev_err(camss->dev, "Failed to register ispif entities: %d\n",
-			ret);
-		goto err_reg_ispif;
-	}
-
-	ret = msm_vfe_register_entities(&camss->vfe, &camss->v4l2_dev);
-	if (ret < 0) {
-		dev_err(camss->dev, "Failed to register vfe entities: %d\n",
-			ret);
-		goto err_reg_vfe;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->csid); j++) {
-			ret = media_create_pad_link(
-				&camss->csiphy[i].subdev.entity,
-				MSM_CSIPHY_PAD_SRC,
-				&camss->csid[j].subdev.entity,
-				MSM_CSID_PAD_SINK,
-				0);
-			if (ret < 0) {
-				dev_err(camss->dev,
-					"Failed to link %s->%s entities: %d\n",
-					camss->csiphy[i].subdev.entity.name,
-					camss->csid[j].subdev.entity.name,
-					ret);
-				goto err_link;
-			}
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->ispif.line); j++) {
-			ret = media_create_pad_link(
-				&camss->csid[i].subdev.entity,
-				MSM_CSID_PAD_SRC,
-				&camss->ispif.line[j].subdev.entity,
-				MSM_ISPIF_PAD_SINK,
-				0);
-			if (ret < 0) {
-				dev_err(camss->dev,
-					"Failed to link %s->%s entities: %d\n",
-					camss->csid[i].subdev.entity.name,
-					camss->ispif.line[j].subdev.entity.name,
-					ret);
-				goto err_link;
-			}
-		}
-	}
-
-	for (i = 0; i < ARRAY_SIZE(camss->ispif.line); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->vfe.line); j++) {
-			ret = media_create_pad_link(
-				&camss->ispif.line[i].subdev.entity,
-				MSM_ISPIF_PAD_SRC,
-				&camss->vfe.line[j].subdev.entity,
-				MSM_VFE_PAD_SINK,
-				0);
-			if (ret < 0) {
-				dev_err(camss->dev,
-					"Failed to link %s->%s entities: %d\n",
-					camss->ispif.line[i].subdev.entity.name,
-					camss->vfe.line[j].subdev.entity.name,
-					ret);
-				goto err_link;
-			}
-		}
-	}
-
-	return 0;
-
-err_link:
-	msm_vfe_unregister_entities(&camss->vfe);
-err_reg_vfe:
-	msm_ispif_unregister_entities(&camss->ispif);
-err_reg_ispif:
-
-	i = ARRAY_SIZE(camss->csid);
-err_reg_csid:
-	for (i--; i >= 0; i--)
-		msm_csid_unregister_entity(&camss->csid[i]);
-
-	i = ARRAY_SIZE(camss->csiphy);
-err_reg_csiphy:
-	for (i--; i >= 0; i--)
-		msm_csiphy_unregister_entity(&camss->csiphy[i]);
-
-	return ret;
-}
-
-/*
- * camss_unregister_entities - Unregister subdev nodes
- * @camss: CAMSS device
- *
- * Return 0 on success or a negative error code on failure
- */
-static void camss_unregister_entities(struct camss *camss)
-{
-	unsigned int i;
-
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++)
-		msm_csiphy_unregister_entity(&camss->csiphy[i]);
-
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++)
-		msm_csid_unregister_entity(&camss->csid[i]);
-
-	msm_ispif_unregister_entities(&camss->ispif);
-	msm_vfe_unregister_entities(&camss->vfe);
-}
-
-static int camss_subdev_notifier_bound(struct v4l2_async_notifier *async,
-				       struct v4l2_subdev *subdev,
-				       struct v4l2_async_subdev *asd)
-{
-	struct camss *camss = container_of(async, struct camss, notifier);
-	struct camss_async_subdev *csd =
-		container_of(asd, struct camss_async_subdev, asd);
-	u8 id = csd->interface.csiphy_id;
-	struct csiphy_device *csiphy = &camss->csiphy[id];
-
-	csiphy->cfg.csi2 = &csd->interface.csi2;
-	subdev->host_priv = csiphy;
-
-	return 0;
-}
-
-static int camss_subdev_notifier_complete(struct v4l2_async_notifier *async)
-{
-	struct camss *camss = container_of(async, struct camss, notifier);
-	struct v4l2_device *v4l2_dev = &camss->v4l2_dev;
-	struct v4l2_subdev *sd;
-	int ret;
-
-	list_for_each_entry(sd, &v4l2_dev->subdevs, list) {
-		if (sd->host_priv) {
-			struct media_entity *sensor = &sd->entity;
-			struct csiphy_device *csiphy =
-					(struct csiphy_device *) sd->host_priv;
-			struct media_entity *input = &csiphy->subdev.entity;
-			unsigned int i;
-
-			for (i = 0; i < sensor->num_pads; i++) {
-				if (sensor->pads[i].flags & MEDIA_PAD_FL_SOURCE)
-					break;
-			}
-			if (i == sensor->num_pads) {
-				dev_err(camss->dev,
-					"No source pad in external entity\n");
-				return -EINVAL;
-			}
-
-			ret = media_create_pad_link(sensor, i,
-				input, MSM_CSIPHY_PAD_SINK,
-				MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
-			if (ret < 0) {
-				dev_err(camss->dev,
-					"Failed to link %s->%s entities: %d\n",
-					sensor->name, input->name, ret);
-				return ret;
-			}
-		}
-	}
-
-	ret = v4l2_device_register_subdev_nodes(&camss->v4l2_dev);
-	if (ret < 0)
-		return ret;
-
-	return media_device_register(&camss->media_dev);
-}
-
-static const struct v4l2_async_notifier_operations camss_subdev_notifier_ops = {
-	.bound = camss_subdev_notifier_bound,
-	.complete = camss_subdev_notifier_complete,
-};
-
-static const struct media_device_ops camss_media_ops = {
-	.link_notify = v4l2_pipeline_link_notify,
-};
-
-/*
- * camss_probe - Probe CAMSS platform device
- * @pdev: Pointer to CAMSS platform device
- *
- * Return 0 on success or a negative error code on failure
- */
-static int camss_probe(struct platform_device *pdev)
-{
-	struct device *dev = &pdev->dev;
-	struct camss *camss;
-	int ret;
-
-	camss = kzalloc(sizeof(*camss), GFP_KERNEL);
-	if (!camss)
-		return -ENOMEM;
-
-	atomic_set(&camss->ref_count, 0);
-	camss->dev = dev;
-	platform_set_drvdata(pdev, camss);
-
-	ret = camss_of_parse_ports(dev, &camss->notifier);
-	if (ret < 0)
-		return ret;
-
-	ret = camss_init_subdevices(camss);
-	if (ret < 0)
-		return ret;
-
-	ret = dma_set_mask_and_coherent(dev, 0xffffffff);
-	if (ret)
-		return ret;
-
-	camss->media_dev.dev = camss->dev;
-	strlcpy(camss->media_dev.model, "Qualcomm Camera Subsystem",
-		sizeof(camss->media_dev.model));
-	camss->media_dev.ops = &camss_media_ops;
-	media_device_init(&camss->media_dev);
-
-	camss->v4l2_dev.mdev = &camss->media_dev;
-	ret = v4l2_device_register(camss->dev, &camss->v4l2_dev);
-	if (ret < 0) {
-		dev_err(dev, "Failed to register V4L2 device: %d\n", ret);
-		return ret;
-	}
-
-	ret = camss_register_entities(camss);
-	if (ret < 0)
-		goto err_register_entities;
-
-	if (camss->notifier.num_subdevs) {
-		camss->notifier.ops = &camss_subdev_notifier_ops;
-
-		ret = v4l2_async_notifier_register(&camss->v4l2_dev,
-						   &camss->notifier);
-		if (ret) {
-			dev_err(dev,
-				"Failed to register async subdev nodes: %d\n",
-				ret);
-			goto err_register_subdevs;
-		}
-	} else {
-		ret = v4l2_device_register_subdev_nodes(&camss->v4l2_dev);
-		if (ret < 0) {
-			dev_err(dev, "Failed to register subdev nodes: %d\n",
-				ret);
-			goto err_register_subdevs;
-		}
-
-		ret = media_device_register(&camss->media_dev);
-		if (ret < 0) {
-			dev_err(dev, "Failed to register media device: %d\n",
-				ret);
-			goto err_register_subdevs;
-		}
-	}
-
-	return 0;
-
-err_register_subdevs:
-	camss_unregister_entities(camss);
-err_register_entities:
-	v4l2_device_unregister(&camss->v4l2_dev);
-
-	return ret;
-}
-
-void camss_delete(struct camss *camss)
-{
-	v4l2_device_unregister(&camss->v4l2_dev);
-	media_device_unregister(&camss->media_dev);
-	media_device_cleanup(&camss->media_dev);
-
-	kfree(camss);
-}
-
-/*
- * camss_remove - Remove CAMSS platform device
- * @pdev: Pointer to CAMSS platform device
- *
- * Always returns 0.
- */
-static int camss_remove(struct platform_device *pdev)
-{
-	struct camss *camss = platform_get_drvdata(pdev);
-
-	msm_vfe_stop_streaming(&camss->vfe);
-
-	v4l2_async_notifier_unregister(&camss->notifier);
-	camss_unregister_entities(camss);
-
-	if (atomic_read(&camss->ref_count) == 0)
-		camss_delete(camss);
-
-	return 0;
-}
-
-static const struct of_device_id camss_dt_match[] = {
-	{ .compatible = "qcom,msm8916-camss" },
-	{ }
-};
-
-MODULE_DEVICE_TABLE(of, camss_dt_match);
-
-static struct platform_driver qcom_camss_driver = {
-	.probe = camss_probe,
-	.remove = camss_remove,
-	.driver = {
-		.name = "qcom-camss",
-		.of_match_table = camss_dt_match,
-	},
-};
-
-module_platform_driver(qcom_camss_driver);
-
-MODULE_ALIAS("platform:qcom-camss");
-MODULE_DESCRIPTION("Qualcomm Camera Subsystem driver");
-MODULE_AUTHOR("Todor Tomov <todor.tomov@linaro.org>");
-MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/platform/qcom/camss-8x16/camss.h b/drivers/media/platform/qcom/camss-8x16/camss.h
deleted file mode 100644
index 4ad223443e4b..000000000000
--- a/drivers/media/platform/qcom/camss-8x16/camss.h
+++ /dev/null
@@ -1,106 +0,0 @@
-/*
- * camss.h
- *
- * Qualcomm MSM Camera Subsystem - Core
- *
- * Copyright (c) 2015, The Linux Foundation. All rights reserved.
- * Copyright (C) 2015-2017 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
-#ifndef QC_MSM_CAMSS_H
-#define QC_MSM_CAMSS_H
-
-#include <linux/types.h>
-#include <media/v4l2-async.h>
-#include <media/v4l2-device.h>
-#include <media/v4l2-subdev.h>
-#include <media/media-device.h>
-#include <media/media-entity.h>
-#include <linux/device.h>
-
-#include "camss-csid.h"
-#include "camss-csiphy.h"
-#include "camss-ispif.h"
-#include "camss-vfe.h"
-
-#define CAMSS_CSID_NUM 2
-#define CAMSS_CSIPHY_NUM 2
-
-#define to_camss(ptr_module)	\
-	container_of(ptr_module, struct camss, ptr_module)
-
-#define to_device(ptr_module)	\
-	(to_camss(ptr_module)->dev)
-
-#define module_pointer(ptr_module, index)	\
-	((const struct ptr_module##_device (*)[]) &(ptr_module[-(index)]))
-
-#define to_camss_index(ptr_module, index)	\
-	container_of(module_pointer(ptr_module, index),	\
-		     struct camss, ptr_module)
-
-#define to_device_index(ptr_module, index)	\
-	(to_camss_index(ptr_module, index)->dev)
-
-#define CAMSS_RES_MAX 15
-
-struct resources {
-	char *regulator[CAMSS_RES_MAX];
-	char *clock[CAMSS_RES_MAX];
-	u32 clock_rate[CAMSS_RES_MAX][CAMSS_RES_MAX];
-	char *reg[CAMSS_RES_MAX];
-	char *interrupt[CAMSS_RES_MAX];
-};
-
-struct resources_ispif {
-	char *clock[CAMSS_RES_MAX];
-	char *clock_for_reset[CAMSS_RES_MAX];
-	char *reg[CAMSS_RES_MAX];
-	char *interrupt;
-};
-
-struct camss {
-	struct v4l2_device v4l2_dev;
-	struct v4l2_async_notifier notifier;
-	struct media_device media_dev;
-	struct device *dev;
-	struct csiphy_device csiphy[CAMSS_CSIPHY_NUM];
-	struct csid_device csid[CAMSS_CSID_NUM];
-	struct ispif_device ispif;
-	struct vfe_device vfe;
-	atomic_t ref_count;
-};
-
-struct camss_camera_interface {
-	u8 csiphy_id;
-	struct csiphy_csi2_cfg csi2;
-};
-
-struct camss_async_subdev {
-	struct camss_camera_interface interface;
-	struct v4l2_async_subdev asd;
-};
-
-struct camss_clock {
-	struct clk *clk;
-	const char *name;
-	u32 *freq;
-	u32 nfreqs;
-};
-
-void camss_add_clock_margin(u64 *rate);
-int camss_enable_clocks(int nclocks, struct camss_clock *clock,
-			struct device *dev);
-void camss_disable_clocks(int nclocks, struct camss_clock *clock);
-int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock);
-void camss_delete(struct camss *camss);
-
-#endif /* QC_MSM_CAMSS_H */
diff --git a/drivers/media/platform/qcom/camss/Makefile b/drivers/media/platform/qcom/camss/Makefile
new file mode 100644
index 000000000000..3c4024fbb768
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/Makefile
@@ -0,0 +1,11 @@
+# Makefile for Qualcomm CAMSS driver
+
+qcom-camss-objs += \
+		camss.o \
+		camss-csid.o \
+		camss-csiphy.o \
+		camss-ispif.o \
+		camss-vfe.o \
+		camss-video.o \
+
+obj-$(CONFIG_VIDEO_QCOM_CAMSS) += qcom-camss.o
diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
new file mode 100644
index 000000000000..39ea27b9da3b
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -0,0 +1,1094 @@
+/*
+ * camss-csid.c
+ *
+ * Qualcomm MSM Camera Subsystem - CSID (CSI Decoder) Module
+ *
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+#include "camss-csid.h"
+#include "camss.h"
+
+#define MSM_CSID_NAME "msm_csid"
+
+#define CAMSS_CSID_HW_VERSION		0x0
+#define CAMSS_CSID_CORE_CTRL_0		0x004
+#define CAMSS_CSID_CORE_CTRL_1		0x008
+#define CAMSS_CSID_RST_CMD		0x00c
+#define CAMSS_CSID_CID_LUT_VC_n(n)	(0x010 + 0x4 * (n))
+#define CAMSS_CSID_CID_n_CFG(n)		(0x020 + 0x4 * (n))
+#define CAMSS_CSID_IRQ_CLEAR_CMD	0x060
+#define CAMSS_CSID_IRQ_MASK		0x064
+#define CAMSS_CSID_IRQ_STATUS		0x068
+#define CAMSS_CSID_TG_CTRL		0x0a0
+#define CAMSS_CSID_TG_CTRL_DISABLE	0xa06436
+#define CAMSS_CSID_TG_CTRL_ENABLE	0xa06437
+#define CAMSS_CSID_TG_VC_CFG		0x0a4
+#define CAMSS_CSID_TG_VC_CFG_H_BLANKING		0x3ff
+#define CAMSS_CSID_TG_VC_CFG_V_BLANKING		0x7f
+#define CAMSS_CSID_TG_DT_n_CGG_0(n)	(0x0ac + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_1(n)	(0x0b0 + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_2(n)	(0x0b4 + 0xc * (n))
+
+#define DATA_TYPE_EMBEDDED_DATA_8BIT	0x12
+#define DATA_TYPE_YUV422_8BIT		0x1e
+#define DATA_TYPE_RAW_6BIT		0x28
+#define DATA_TYPE_RAW_8BIT		0x2a
+#define DATA_TYPE_RAW_10BIT		0x2b
+#define DATA_TYPE_RAW_12BIT		0x2c
+
+#define DECODE_FORMAT_UNCOMPRESSED_6_BIT	0x0
+#define DECODE_FORMAT_UNCOMPRESSED_8_BIT	0x1
+#define DECODE_FORMAT_UNCOMPRESSED_10_BIT	0x2
+#define DECODE_FORMAT_UNCOMPRESSED_12_BIT	0x3
+
+#define CSID_RESET_TIMEOUT_MS 500
+
+struct csid_fmts {
+	u32 code;
+	u8 data_type;
+	u8 decode_format;
+	u8 bpp;
+	u8 spp; /* bus samples per pixel */
+};
+
+static const struct csid_fmts csid_input_fmts[] = {
+	{
+		MEDIA_BUS_FMT_UYVY8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_VYUY8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_YUYV8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_YVYU8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	}
+};
+
+static const struct csid_fmts *csid_get_fmt_entry(u32 code)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
+		if (code == csid_input_fmts[i].code)
+			return &csid_input_fmts[i];
+
+	WARN(1, "Unknown format\n");
+
+	return &csid_input_fmts[0];
+}
+
+/*
+ * csid_isr - CSID module interrupt handler
+ * @irq: Interrupt line
+ * @dev: CSID device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t csid_isr(int irq, void *dev)
+{
+	struct csid_device *csid = dev;
+	u32 value;
+
+	value = readl_relaxed(csid->base + CAMSS_CSID_IRQ_STATUS);
+	writel_relaxed(value, csid->base + CAMSS_CSID_IRQ_CLEAR_CMD);
+
+	if ((value >> 11) & 0x1)
+		complete(&csid->reset_complete);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * csid_set_clock_rates - Calculate and set clock rates on CSID module
+ * @csiphy: CSID device
+ */
+static int csid_set_clock_rates(struct csid_device *csid)
+{
+	struct device *dev = to_device_index(csid, csid->id);
+	u32 pixel_clock;
+	int i, j;
+	int ret;
+
+	ret = camss_get_pixel_clock(&csid->subdev.entity, &pixel_clock);
+	if (ret)
+		pixel_clock = 0;
+
+	for (i = 0; i < csid->nclocks; i++) {
+		struct camss_clock *clock = &csid->clock[i];
+
+		if (!strcmp(clock->name, "csi0") ||
+			!strcmp(clock->name, "csi1")) {
+			u8 bpp = csid_get_fmt_entry(
+				csid->fmt[MSM_CSIPHY_PAD_SINK].code)->bpp;
+			u8 num_lanes = csid->phy.lane_cnt;
+			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
+			long rate;
+
+			camss_add_clock_margin(&min_rate);
+
+			for (j = 0; j < clock->nfreqs; j++)
+				if (min_rate < clock->freq[j])
+					break;
+
+			if (j == clock->nfreqs) {
+				dev_err(dev,
+					"Pixel clock is too high for CSID\n");
+				return -EINVAL;
+			}
+
+			/* if sensor pixel clock is not available */
+			/* set highest possible CSID clock rate */
+			if (min_rate == 0)
+				j = clock->nfreqs - 1;
+
+			rate = clk_round_rate(clock->clk, clock->freq[j]);
+			if (rate < 0) {
+				dev_err(dev, "clk round rate failed: %ld\n",
+					rate);
+				return -EINVAL;
+			}
+
+			ret = clk_set_rate(clock->clk, rate);
+			if (ret < 0) {
+				dev_err(dev, "clk set rate failed: %d\n", ret);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * csid_reset - Trigger reset on CSID module and wait to complete
+ * @csid: CSID device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csid_reset(struct csid_device *csid)
+{
+	unsigned long time;
+
+	reinit_completion(&csid->reset_complete);
+
+	writel_relaxed(0x7fff, csid->base + CAMSS_CSID_RST_CMD);
+
+	time = wait_for_completion_timeout(&csid->reset_complete,
+		msecs_to_jiffies(CSID_RESET_TIMEOUT_MS));
+	if (!time) {
+		dev_err(to_device_index(csid, csid->id),
+			"CSID reset timeout\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * csid_set_power - Power on/off CSID module
+ * @sd: CSID V4L2 subdevice
+ * @on: Requested power state
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csid_set_power(struct v4l2_subdev *sd, int on)
+{
+	struct csid_device *csid = v4l2_get_subdevdata(sd);
+	struct device *dev = to_device_index(csid, csid->id);
+	int ret;
+
+	if (on) {
+		u32 hw_version;
+
+		ret = regulator_enable(csid->vdda);
+		if (ret < 0)
+			return ret;
+
+		ret = csid_set_clock_rates(csid);
+		if (ret < 0) {
+			regulator_disable(csid->vdda);
+			return ret;
+		}
+
+		ret = camss_enable_clocks(csid->nclocks, csid->clock, dev);
+		if (ret < 0) {
+			regulator_disable(csid->vdda);
+			return ret;
+		}
+
+		enable_irq(csid->irq);
+
+		ret = csid_reset(csid);
+		if (ret < 0) {
+			disable_irq(csid->irq);
+			camss_disable_clocks(csid->nclocks, csid->clock);
+			regulator_disable(csid->vdda);
+			return ret;
+		}
+
+		hw_version = readl_relaxed(csid->base + CAMSS_CSID_HW_VERSION);
+		dev_dbg(dev, "CSID HW Version = 0x%08x\n", hw_version);
+	} else {
+		disable_irq(csid->irq);
+		camss_disable_clocks(csid->nclocks, csid->clock);
+		ret = regulator_disable(csid->vdda);
+	}
+
+	return ret;
+}
+
+/*
+ * csid_set_stream - Enable/disable streaming on CSID module
+ * @sd: CSID V4L2 subdevice
+ * @enable: Requested streaming state
+ *
+ * Main configuration of CSID module is also done here.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csid_set_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct csid_device *csid = v4l2_get_subdevdata(sd);
+	struct csid_testgen_config *tg = &csid->testgen;
+	u32 val;
+
+	if (enable) {
+		u8 vc = 0; /* Virtual Channel 0 */
+		u8 cid = vc * 4; /* id of Virtual Channel and Data Type set */
+		u8 dt, dt_shift, df;
+		int ret;
+
+		ret = v4l2_ctrl_handler_setup(&csid->ctrls);
+		if (ret < 0) {
+			dev_err(to_device_index(csid, csid->id),
+				"could not sync v4l2 controls: %d\n", ret);
+			return ret;
+		}
+
+		if (!tg->enabled &&
+		    !media_entity_remote_pad(&csid->pads[MSM_CSID_PAD_SINK]))
+			return -ENOLINK;
+
+		dt = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SRC].code)->
+								data_type;
+
+		if (tg->enabled) {
+			/* Config Test Generator */
+			struct v4l2_mbus_framefmt *f =
+					&csid->fmt[MSM_CSID_PAD_SRC];
+			u8 bpp = csid_get_fmt_entry(f->code)->bpp;
+			u8 spp = csid_get_fmt_entry(f->code)->spp;
+			u32 num_bytes_per_line = f->width * bpp * spp / 8;
+			u32 num_lines = f->height;
+
+			/* 31:24 V blank, 23:13 H blank, 3:2 num of active DT */
+			/* 1:0 VC */
+			val = ((CAMSS_CSID_TG_VC_CFG_V_BLANKING & 0xff) << 24) |
+			      ((CAMSS_CSID_TG_VC_CFG_H_BLANKING & 0x7ff) << 13);
+			writel_relaxed(val, csid->base + CAMSS_CSID_TG_VC_CFG);
+
+			/* 28:16 bytes per lines, 12:0 num of lines */
+			val = ((num_bytes_per_line & 0x1fff) << 16) |
+			      (num_lines & 0x1fff);
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_DT_n_CGG_0(0));
+
+			/* 5:0 data type */
+			val = dt;
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_DT_n_CGG_1(0));
+
+			/* 2:0 output test pattern */
+			val = tg->payload_mode;
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_DT_n_CGG_2(0));
+		} else {
+			struct csid_phy_config *phy = &csid->phy;
+
+			val = phy->lane_cnt - 1;
+			val |= phy->lane_assign << 4;
+
+			writel_relaxed(val,
+				       csid->base + CAMSS_CSID_CORE_CTRL_0);
+
+			val = phy->csiphy_id << 17;
+			val |= 0x9;
+
+			writel_relaxed(val,
+				       csid->base + CAMSS_CSID_CORE_CTRL_1);
+		}
+
+		/* Config LUT */
+
+		dt_shift = (cid % 4) * 8;
+		df = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SINK].code)->
+								decode_format;
+
+		val = readl_relaxed(csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
+		val &= ~(0xff << dt_shift);
+		val |= dt << dt_shift;
+		writel_relaxed(val, csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
+
+		val = (df << 4) | 0x3;
+		writel_relaxed(val, csid->base + CAMSS_CSID_CID_n_CFG(cid));
+
+		if (tg->enabled) {
+			val = CAMSS_CSID_TG_CTRL_ENABLE;
+			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
+		}
+	} else {
+		if (tg->enabled) {
+			val = CAMSS_CSID_TG_CTRL_DISABLE;
+			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * __csid_get_format - Get pointer to format structure
+ * @csid: CSID device
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad from which format is requested
+ * @which: TRY or ACTIVE format
+ *
+ * Return pointer to TRY or ACTIVE format structure
+ */
+static struct v4l2_mbus_framefmt *
+__csid_get_format(struct csid_device *csid,
+		  struct v4l2_subdev_pad_config *cfg,
+		  unsigned int pad,
+		  enum v4l2_subdev_format_whence which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_format(&csid->subdev, cfg, pad);
+
+	return &csid->fmt[pad];
+}
+
+/*
+ * csid_try_format - Handle try format by pad subdev method
+ * @csid: CSID device
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad on which format is requested
+ * @fmt: pointer to v4l2 format structure
+ * @which: wanted subdev format
+ */
+static void csid_try_format(struct csid_device *csid,
+			    struct v4l2_subdev_pad_config *cfg,
+			    unsigned int pad,
+			    struct v4l2_mbus_framefmt *fmt,
+			    enum v4l2_subdev_format_whence which)
+{
+	unsigned int i;
+
+	switch (pad) {
+	case MSM_CSID_PAD_SINK:
+		/* Set format on sink pad */
+
+		for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
+			if (fmt->code == csid_input_fmts[i].code)
+				break;
+
+		/* If not found, use UYVY as default */
+		if (i >= ARRAY_SIZE(csid_input_fmts))
+			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
+
+		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
+		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
+
+		fmt->field = V4L2_FIELD_NONE;
+		fmt->colorspace = V4L2_COLORSPACE_SRGB;
+
+		break;
+
+	case MSM_CSID_PAD_SRC:
+		if (csid->testgen_mode->cur.val == 0) {
+			/* Test generator is disabled, keep pad formats */
+			/* in sync - set and return a format same as sink pad */
+			struct v4l2_mbus_framefmt format;
+
+			format = *__csid_get_format(csid, cfg,
+						    MSM_CSID_PAD_SINK, which);
+			*fmt = format;
+		} else {
+			/* Test generator is enabled, set format on source*/
+			/* pad to allow test generator usage */
+
+			for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
+				if (csid_input_fmts[i].code == fmt->code)
+					break;
+
+			/* If not found, use UYVY as default */
+			if (i >= ARRAY_SIZE(csid_input_fmts))
+				fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
+
+			fmt->width = clamp_t(u32, fmt->width, 1, 8191);
+			fmt->height = clamp_t(u32, fmt->height, 1, 8191);
+
+			fmt->field = V4L2_FIELD_NONE;
+		}
+		break;
+	}
+
+	fmt->colorspace = V4L2_COLORSPACE_SRGB;
+}
+
+/*
+ * csid_enum_mbus_code - Handle pixel format enumeration
+ * @sd: CSID V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @code: pointer to v4l2_subdev_mbus_code_enum structure
+ * return -EINVAL or zero on success
+ */
+static int csid_enum_mbus_code(struct v4l2_subdev *sd,
+			       struct v4l2_subdev_pad_config *cfg,
+			       struct v4l2_subdev_mbus_code_enum *code)
+{
+	struct csid_device *csid = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	if (code->pad == MSM_CSID_PAD_SINK) {
+		if (code->index >= ARRAY_SIZE(csid_input_fmts))
+			return -EINVAL;
+
+		code->code = csid_input_fmts[code->index].code;
+	} else {
+		if (csid->testgen_mode->cur.val == 0) {
+			if (code->index > 0)
+				return -EINVAL;
+
+			format = __csid_get_format(csid, cfg, MSM_CSID_PAD_SINK,
+						   code->which);
+
+			code->code = format->code;
+		} else {
+			if (code->index >= ARRAY_SIZE(csid_input_fmts))
+				return -EINVAL;
+
+			code->code = csid_input_fmts[code->index].code;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * csid_enum_frame_size - Handle frame size enumeration
+ * @sd: CSID V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fse: pointer to v4l2_subdev_frame_size_enum structure
+ * return -EINVAL or zero on success
+ */
+static int csid_enum_frame_size(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_frame_size_enum *fse)
+{
+	struct csid_device *csid = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt format;
+
+	if (fse->index != 0)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = 1;
+	format.height = 1;
+	csid_try_format(csid, cfg, fse->pad, &format, fse->which);
+	fse->min_width = format.width;
+	fse->min_height = format.height;
+
+	if (format.code != fse->code)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = -1;
+	format.height = -1;
+	csid_try_format(csid, cfg, fse->pad, &format, fse->which);
+	fse->max_width = format.width;
+	fse->max_height = format.height;
+
+	return 0;
+}
+
+/*
+ * csid_get_format - Handle get format by pads subdev method
+ * @sd: CSID V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int csid_get_format(struct v4l2_subdev *sd,
+			   struct v4l2_subdev_pad_config *cfg,
+			   struct v4l2_subdev_format *fmt)
+{
+	struct csid_device *csid = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __csid_get_format(csid, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	fmt->format = *format;
+
+	return 0;
+}
+
+/*
+ * csid_set_format - Handle set format by pads subdev method
+ * @sd: CSID V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int csid_set_format(struct v4l2_subdev *sd,
+			   struct v4l2_subdev_pad_config *cfg,
+			   struct v4l2_subdev_format *fmt)
+{
+	struct csid_device *csid = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __csid_get_format(csid, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	csid_try_format(csid, cfg, fmt->pad, &fmt->format, fmt->which);
+	*format = fmt->format;
+
+	/* Propagate the format from sink to source */
+	if (fmt->pad == MSM_CSID_PAD_SINK) {
+		format = __csid_get_format(csid, cfg, MSM_CSID_PAD_SRC,
+					   fmt->which);
+
+		*format = fmt->format;
+		csid_try_format(csid, cfg, MSM_CSID_PAD_SRC, format,
+				fmt->which);
+	}
+
+	return 0;
+}
+
+/*
+ * csid_init_formats - Initialize formats on all pads
+ * @sd: CSID V4L2 subdevice
+ * @fh: V4L2 subdev file handle
+ *
+ * Initialize all pad formats with default values.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csid_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	struct v4l2_subdev_format format = {
+		.pad = MSM_CSID_PAD_SINK,
+		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
+			      V4L2_SUBDEV_FORMAT_ACTIVE,
+		.format = {
+			.code = MEDIA_BUS_FMT_UYVY8_2X8,
+			.width = 1920,
+			.height = 1080
+		}
+	};
+
+	return csid_set_format(sd, fh ? fh->pad : NULL, &format);
+}
+
+static const char * const csid_test_pattern_menu[] = {
+	"Disabled",
+	"Incrementing",
+	"Alternating 0x55/0xAA",
+	"All Zeros 0x00",
+	"All Ones 0xFF",
+	"Pseudo-random Data",
+};
+
+/*
+ * csid_set_test_pattern - Set test generator's pattern mode
+ * @csid: CSID device
+ * @value: desired test pattern mode
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csid_set_test_pattern(struct csid_device *csid, s32 value)
+{
+	struct csid_testgen_config *tg = &csid->testgen;
+
+	/* If CSID is linked to CSIPHY, do not allow to enable test generator */
+	if (value && media_entity_remote_pad(&csid->pads[MSM_CSID_PAD_SINK]))
+		return -EBUSY;
+
+	tg->enabled = !!value;
+
+	switch (value) {
+	case 1:
+		tg->payload_mode = CSID_PAYLOAD_MODE_INCREMENTING;
+		break;
+	case 2:
+		tg->payload_mode = CSID_PAYLOAD_MODE_ALTERNATING_55_AA;
+		break;
+	case 3:
+		tg->payload_mode = CSID_PAYLOAD_MODE_ALL_ZEROES;
+		break;
+	case 4:
+		tg->payload_mode = CSID_PAYLOAD_MODE_ALL_ONES;
+		break;
+	case 5:
+		tg->payload_mode = CSID_PAYLOAD_MODE_RANDOM;
+		break;
+	}
+
+	return 0;
+}
+
+/*
+ * csid_s_ctrl - Handle set control subdev method
+ * @ctrl: pointer to v4l2 control structure
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csid_s_ctrl(struct v4l2_ctrl *ctrl)
+{
+	struct csid_device *csid = container_of(ctrl->handler,
+						struct csid_device, ctrls);
+	int ret = -EINVAL;
+
+	switch (ctrl->id) {
+	case V4L2_CID_TEST_PATTERN:
+		ret = csid_set_test_pattern(csid, ctrl->val);
+		break;
+	}
+
+	return ret;
+}
+
+static const struct v4l2_ctrl_ops csid_ctrl_ops = {
+	.s_ctrl = csid_s_ctrl,
+};
+
+/*
+ * msm_csid_subdev_init - Initialize CSID device structure and resources
+ * @csid: CSID device
+ * @res: CSID module resources table
+ * @id: CSID module id
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_csid_subdev_init(struct csid_device *csid,
+			 const struct resources *res, u8 id)
+{
+	struct device *dev = to_device_index(csid, id);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct resource *r;
+	int i, j;
+	int ret;
+
+	csid->id = id;
+
+	/* Memory */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
+	csid->base = devm_ioremap_resource(dev, r);
+	if (IS_ERR(csid->base)) {
+		dev_err(dev, "could not map memory\n");
+		return PTR_ERR(csid->base);
+	}
+
+	/* Interrupt */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ,
+					 res->interrupt[0]);
+	if (!r) {
+		dev_err(dev, "missing IRQ\n");
+		return -EINVAL;
+	}
+
+	csid->irq = r->start;
+	snprintf(csid->irq_name, sizeof(csid->irq_name), "%s_%s%d",
+		 dev_name(dev), MSM_CSID_NAME, csid->id);
+	ret = devm_request_irq(dev, csid->irq, csid_isr,
+		IRQF_TRIGGER_RISING, csid->irq_name, csid);
+	if (ret < 0) {
+		dev_err(dev, "request_irq failed: %d\n", ret);
+		return ret;
+	}
+
+	disable_irq(csid->irq);
+
+	/* Clocks */
+
+	csid->nclocks = 0;
+	while (res->clock[csid->nclocks])
+		csid->nclocks++;
+
+	csid->clock = devm_kcalloc(dev, csid->nclocks, sizeof(*csid->clock),
+				    GFP_KERNEL);
+	if (!csid->clock)
+		return -ENOMEM;
+
+	for (i = 0; i < csid->nclocks; i++) {
+		struct camss_clock *clock = &csid->clock[i];
+
+		clock->clk = devm_clk_get(dev, res->clock[i]);
+		if (IS_ERR(clock->clk))
+			return PTR_ERR(clock->clk);
+
+		clock->name = res->clock[i];
+
+		clock->nfreqs = 0;
+		while (res->clock_rate[i][clock->nfreqs])
+			clock->nfreqs++;
+
+		if (!clock->nfreqs) {
+			clock->freq = NULL;
+			continue;
+		}
+
+		clock->freq = devm_kcalloc(dev,
+					   clock->nfreqs,
+					   sizeof(*clock->freq),
+					   GFP_KERNEL);
+		if (!clock->freq)
+			return -ENOMEM;
+
+		for (j = 0; j < clock->nfreqs; j++)
+			clock->freq[j] = res->clock_rate[i][j];
+	}
+
+	/* Regulator */
+
+	csid->vdda = devm_regulator_get(dev, res->regulator[0]);
+	if (IS_ERR(csid->vdda)) {
+		dev_err(dev, "could not get regulator\n");
+		return PTR_ERR(csid->vdda);
+	}
+
+	init_completion(&csid->reset_complete);
+
+	return 0;
+}
+
+/*
+ * msm_csid_get_csid_id - Get CSID HW module id
+ * @entity: Pointer to CSID media entity structure
+ * @id: Return CSID HW module id here
+ */
+void msm_csid_get_csid_id(struct media_entity *entity, u8 *id)
+{
+	struct v4l2_subdev *sd = media_entity_to_v4l2_subdev(entity);
+	struct csid_device *csid = v4l2_get_subdevdata(sd);
+
+	*id = csid->id;
+}
+
+/*
+ * csid_get_lane_assign - Calculate CSI2 lane assign configuration parameter
+ * @lane_cfg - CSI2 lane configuration
+ *
+ * Return lane assign
+ */
+static u32 csid_get_lane_assign(struct csiphy_lanes_cfg *lane_cfg)
+{
+	u32 lane_assign = 0;
+	int i;
+
+	for (i = 0; i < lane_cfg->num_data; i++)
+		lane_assign |= lane_cfg->data[i].pos << (i * 4);
+
+	return lane_assign;
+}
+
+/*
+ * csid_link_setup - Setup CSID connections
+ * @entity: Pointer to media entity structure
+ * @local: Pointer to local pad
+ * @remote: Pointer to remote pad
+ * @flags: Link flags
+ *
+ * Return 0 on success
+ */
+static int csid_link_setup(struct media_entity *entity,
+			   const struct media_pad *local,
+			   const struct media_pad *remote, u32 flags)
+{
+	if (flags & MEDIA_LNK_FL_ENABLED)
+		if (media_entity_remote_pad(local))
+			return -EBUSY;
+
+	if ((local->flags & MEDIA_PAD_FL_SINK) &&
+	    (flags & MEDIA_LNK_FL_ENABLED)) {
+		struct v4l2_subdev *sd;
+		struct csid_device *csid;
+		struct csiphy_device *csiphy;
+		struct csiphy_lanes_cfg *lane_cfg;
+		struct v4l2_subdev_format format = { 0 };
+
+		sd = media_entity_to_v4l2_subdev(entity);
+		csid = v4l2_get_subdevdata(sd);
+
+		/* If test generator is enabled */
+		/* do not allow a link from CSIPHY to CSID */
+		if (csid->testgen_mode->cur.val != 0)
+			return -EBUSY;
+
+		sd = media_entity_to_v4l2_subdev(remote->entity);
+		csiphy = v4l2_get_subdevdata(sd);
+
+		/* If a sensor is not linked to CSIPHY */
+		/* do no allow a link from CSIPHY to CSID */
+		if (!csiphy->cfg.csi2)
+			return -EPERM;
+
+		csid->phy.csiphy_id = csiphy->id;
+
+		lane_cfg = &csiphy->cfg.csi2->lane_cfg;
+		csid->phy.lane_cnt = lane_cfg->num_data;
+		csid->phy.lane_assign = csid_get_lane_assign(lane_cfg);
+
+		/* Reset format on source pad to sink pad format */
+		format.pad = MSM_CSID_PAD_SRC;
+		format.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+		csid_set_format(&csid->subdev, NULL, &format);
+	}
+
+	return 0;
+}
+
+static const struct v4l2_subdev_core_ops csid_core_ops = {
+	.s_power = csid_set_power,
+};
+
+static const struct v4l2_subdev_video_ops csid_video_ops = {
+	.s_stream = csid_set_stream,
+};
+
+static const struct v4l2_subdev_pad_ops csid_pad_ops = {
+	.enum_mbus_code = csid_enum_mbus_code,
+	.enum_frame_size = csid_enum_frame_size,
+	.get_fmt = csid_get_format,
+	.set_fmt = csid_set_format,
+};
+
+static const struct v4l2_subdev_ops csid_v4l2_ops = {
+	.core = &csid_core_ops,
+	.video = &csid_video_ops,
+	.pad = &csid_pad_ops,
+};
+
+static const struct v4l2_subdev_internal_ops csid_v4l2_internal_ops = {
+	.open = csid_init_formats,
+};
+
+static const struct media_entity_operations csid_media_ops = {
+	.link_setup = csid_link_setup,
+	.link_validate = v4l2_subdev_link_validate,
+};
+
+/*
+ * msm_csid_register_entity - Register subdev node for CSID module
+ * @csid: CSID device
+ * @v4l2_dev: V4L2 device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_csid_register_entity(struct csid_device *csid,
+			     struct v4l2_device *v4l2_dev)
+{
+	struct v4l2_subdev *sd = &csid->subdev;
+	struct media_pad *pads = csid->pads;
+	struct device *dev = to_device_index(csid, csid->id);
+	int ret;
+
+	v4l2_subdev_init(sd, &csid_v4l2_ops);
+	sd->internal_ops = &csid_v4l2_internal_ops;
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
+		 MSM_CSID_NAME, csid->id);
+	v4l2_set_subdevdata(sd, csid);
+
+	ret = v4l2_ctrl_handler_init(&csid->ctrls, 1);
+	if (ret < 0) {
+		dev_err(dev, "Failed to init ctrl handler: %d\n", ret);
+		return ret;
+	}
+
+	csid->testgen_mode = v4l2_ctrl_new_std_menu_items(&csid->ctrls,
+				&csid_ctrl_ops, V4L2_CID_TEST_PATTERN,
+				ARRAY_SIZE(csid_test_pattern_menu) - 1, 0, 0,
+				csid_test_pattern_menu);
+
+	if (csid->ctrls.error) {
+		dev_err(dev, "Failed to init ctrl: %d\n", csid->ctrls.error);
+		ret = csid->ctrls.error;
+		goto free_ctrl;
+	}
+
+	csid->subdev.ctrl_handler = &csid->ctrls;
+
+	ret = csid_init_formats(sd, NULL);
+	if (ret < 0) {
+		dev_err(dev, "Failed to init format: %d\n", ret);
+		goto free_ctrl;
+	}
+
+	pads[MSM_CSID_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
+	pads[MSM_CSID_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
+
+	sd->entity.function = MEDIA_ENT_F_IO_V4L;
+	sd->entity.ops = &csid_media_ops;
+	ret = media_entity_pads_init(&sd->entity, MSM_CSID_PADS_NUM, pads);
+	if (ret < 0) {
+		dev_err(dev, "Failed to init media entity: %d\n", ret);
+		goto free_ctrl;
+	}
+
+	ret = v4l2_device_register_subdev(v4l2_dev, sd);
+	if (ret < 0) {
+		dev_err(dev, "Failed to register subdev: %d\n", ret);
+		goto media_cleanup;
+	}
+
+	return 0;
+
+media_cleanup:
+	media_entity_cleanup(&sd->entity);
+free_ctrl:
+	v4l2_ctrl_handler_free(&csid->ctrls);
+
+	return ret;
+}
+
+/*
+ * msm_csid_unregister_entity - Unregister CSID module subdev node
+ * @csid: CSID device
+ */
+void msm_csid_unregister_entity(struct csid_device *csid)
+{
+	v4l2_device_unregister_subdev(&csid->subdev);
+	media_entity_cleanup(&csid->subdev.entity);
+	v4l2_ctrl_handler_free(&csid->ctrls);
+}
diff --git a/drivers/media/platform/qcom/camss/camss-csid.h b/drivers/media/platform/qcom/camss/camss-csid.h
new file mode 100644
index 000000000000..8012222b81ad
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csid.h
@@ -0,0 +1,82 @@
+/*
+ * camss-csid.h
+ *
+ * Qualcomm MSM Camera Subsystem - CSID (CSI Decoder) Module
+ *
+ * Copyright (c) 2011-2014, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef QC_MSM_CAMSS_CSID_H
+#define QC_MSM_CAMSS_CSID_H
+
+#include <linux/clk.h>
+#include <media/media-entity.h>
+#include <media/v4l2-ctrls.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-mediabus.h>
+#include <media/v4l2-subdev.h>
+
+#define MSM_CSID_PAD_SINK 0
+#define MSM_CSID_PAD_SRC 1
+#define MSM_CSID_PADS_NUM 2
+
+enum csid_payload_mode {
+	CSID_PAYLOAD_MODE_INCREMENTING = 0,
+	CSID_PAYLOAD_MODE_ALTERNATING_55_AA = 1,
+	CSID_PAYLOAD_MODE_ALL_ZEROES = 2,
+	CSID_PAYLOAD_MODE_ALL_ONES = 3,
+	CSID_PAYLOAD_MODE_RANDOM = 4,
+	CSID_PAYLOAD_MODE_USER_SPECIFIED = 5,
+};
+
+struct csid_testgen_config {
+	u8 enabled;
+	enum csid_payload_mode payload_mode;
+};
+
+struct csid_phy_config {
+	u8 csiphy_id;
+	u8 lane_cnt;
+	u32 lane_assign;
+};
+
+struct csid_device {
+	u8 id;
+	struct v4l2_subdev subdev;
+	struct media_pad pads[MSM_CSID_PADS_NUM];
+	void __iomem *base;
+	u32 irq;
+	char irq_name[30];
+	struct camss_clock *clock;
+	int nclocks;
+	struct regulator *vdda;
+	struct completion reset_complete;
+	struct csid_testgen_config testgen;
+	struct csid_phy_config phy;
+	struct v4l2_mbus_framefmt fmt[MSM_CSID_PADS_NUM];
+	struct v4l2_ctrl_handler ctrls;
+	struct v4l2_ctrl *testgen_mode;
+};
+
+struct resources;
+
+int msm_csid_subdev_init(struct csid_device *csid,
+			 const struct resources *res, u8 id);
+
+int msm_csid_register_entity(struct csid_device *csid,
+			     struct v4l2_device *v4l2_dev);
+
+void msm_csid_unregister_entity(struct csid_device *csid);
+
+void msm_csid_get_csid_id(struct media_entity *entity, u8 *id);
+
+#endif /* QC_MSM_CAMSS_CSID_H */
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
new file mode 100644
index 000000000000..642de259dc6b
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -0,0 +1,893 @@
+/*
+ * camss-csiphy.c
+ *
+ * Qualcomm MSM Camera Subsystem - CSIPHY Module
+ *
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2016-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+#include "camss-csiphy.h"
+#include "camss.h"
+
+#define MSM_CSIPHY_NAME "msm_csiphy"
+
+#define CAMSS_CSI_PHY_LNn_CFG2(n)		(0x004 + 0x40 * (n))
+#define CAMSS_CSI_PHY_LNn_CFG3(n)		(0x008 + 0x40 * (n))
+#define CAMSS_CSI_PHY_GLBL_RESET		0x140
+#define CAMSS_CSI_PHY_GLBL_PWR_CFG		0x144
+#define CAMSS_CSI_PHY_GLBL_IRQ_CMD		0x164
+#define CAMSS_CSI_PHY_HW_VERSION		0x188
+#define CAMSS_CSI_PHY_INTERRUPT_STATUSn(n)	(0x18c + 0x4 * (n))
+#define CAMSS_CSI_PHY_INTERRUPT_MASKn(n)	(0x1ac + 0x4 * (n))
+#define CAMSS_CSI_PHY_INTERRUPT_CLEARn(n)	(0x1cc + 0x4 * (n))
+#define CAMSS_CSI_PHY_GLBL_T_INIT_CFG0		0x1ec
+#define CAMSS_CSI_PHY_T_WAKEUP_CFG0		0x1f4
+
+static const struct {
+	u32 code;
+	u8 bpp;
+} csiphy_formats[] = {
+	{
+		MEDIA_BUS_FMT_UYVY8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_VYUY8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_YUYV8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_YVYU8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR12_1X12,
+		12,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG12_1X12,
+		12,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG12_1X12,
+		12,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB12_1X12,
+		12,
+	}
+};
+
+/*
+ * csiphy_get_bpp - map media bus format to bits per pixel
+ * @code: media bus format code
+ *
+ * Return number of bits per pixel
+ */
+static u8 csiphy_get_bpp(u32 code)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
+		if (code == csiphy_formats[i].code)
+			return csiphy_formats[i].bpp;
+
+	WARN(1, "Unknown format\n");
+
+	return csiphy_formats[0].bpp;
+}
+
+/*
+ * csiphy_isr - CSIPHY module interrupt handler
+ * @irq: Interrupt line
+ * @dev: CSIPHY device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t csiphy_isr(int irq, void *dev)
+{
+	struct csiphy_device *csiphy = dev;
+	u8 i;
+
+	for (i = 0; i < 8; i++) {
+		u8 val = readl_relaxed(csiphy->base +
+				       CAMSS_CSI_PHY_INTERRUPT_STATUSn(i));
+		writel_relaxed(val, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+		writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
+		writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
+		writel_relaxed(0x0, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+	}
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * csiphy_set_clock_rates - Calculate and set clock rates on CSIPHY module
+ * @csiphy: CSIPHY device
+ */
+static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
+{
+	struct device *dev = to_device_index(csiphy, csiphy->id);
+	u32 pixel_clock;
+	int i, j;
+	int ret;
+
+	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
+	if (ret)
+		pixel_clock = 0;
+
+	for (i = 0; i < csiphy->nclocks; i++) {
+		struct camss_clock *clock = &csiphy->clock[i];
+
+		if (!strcmp(clock->name, "csiphy0_timer") ||
+			!strcmp(clock->name, "csiphy1_timer")) {
+			u8 bpp = csiphy_get_bpp(
+					csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
+			u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
+			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
+			long round_rate;
+
+			camss_add_clock_margin(&min_rate);
+
+			for (j = 0; j < clock->nfreqs; j++)
+				if (min_rate < clock->freq[j])
+					break;
+
+			if (j == clock->nfreqs) {
+				dev_err(dev,
+					"Pixel clock is too high for CSIPHY\n");
+				return -EINVAL;
+			}
+
+			/* if sensor pixel clock is not available */
+			/* set highest possible CSIPHY clock rate */
+			if (min_rate == 0)
+				j = clock->nfreqs - 1;
+
+			round_rate = clk_round_rate(clock->clk, clock->freq[j]);
+			if (round_rate < 0) {
+				dev_err(dev, "clk round rate failed: %ld\n",
+					round_rate);
+				return -EINVAL;
+			}
+
+			csiphy->timer_clk_rate = round_rate;
+
+			ret = clk_set_rate(clock->clk, csiphy->timer_clk_rate);
+			if (ret < 0) {
+				dev_err(dev, "clk set rate failed: %d\n", ret);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * csiphy_reset - Perform software reset on CSIPHY module
+ * @csiphy: CSIPHY device
+ */
+static void csiphy_reset(struct csiphy_device *csiphy)
+{
+	writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+	usleep_range(5000, 8000);
+	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+}
+
+/*
+ * csiphy_set_power - Power on/off CSIPHY module
+ * @sd: CSIPHY V4L2 subdevice
+ * @on: Requested power state
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csiphy_set_power(struct v4l2_subdev *sd, int on)
+{
+	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
+	struct device *dev = to_device_index(csiphy, csiphy->id);
+
+	if (on) {
+		u8 hw_version;
+		int ret;
+
+		ret = csiphy_set_clock_rates(csiphy);
+		if (ret < 0)
+			return ret;
+
+		ret = camss_enable_clocks(csiphy->nclocks, csiphy->clock, dev);
+		if (ret < 0)
+			return ret;
+
+		enable_irq(csiphy->irq);
+
+		csiphy_reset(csiphy);
+
+		hw_version = readl_relaxed(csiphy->base +
+					   CAMSS_CSI_PHY_HW_VERSION);
+		dev_dbg(dev, "CSIPHY HW Version = 0x%02x\n", hw_version);
+	} else {
+		disable_irq(csiphy->irq);
+
+		camss_disable_clocks(csiphy->nclocks, csiphy->clock);
+	}
+
+	return 0;
+}
+
+/*
+ * csiphy_get_lane_mask - Calculate CSI2 lane mask configuration parameter
+ * @lane_cfg - CSI2 lane configuration
+ *
+ * Return lane mask
+ */
+static u8 csiphy_get_lane_mask(struct csiphy_lanes_cfg *lane_cfg)
+{
+	u8 lane_mask;
+	int i;
+
+	lane_mask = 1 << lane_cfg->clk.pos;
+
+	for (i = 0; i < lane_cfg->num_data; i++)
+		lane_mask |= 1 << lane_cfg->data[i].pos;
+
+	return lane_mask;
+}
+
+/*
+ * csiphy_settle_cnt_calc - Calculate settle count value
+ * @csiphy: CSIPHY device
+ *
+ * Helper function to calculate settle count value. This is
+ * based on the CSI2 T_hs_settle parameter which in turn
+ * is calculated based on the CSI2 transmitter pixel clock
+ * frequency.
+ *
+ * Return settle count value or 0 if the CSI2 pixel clock
+ * frequency is not available
+ */
+static u8 csiphy_settle_cnt_calc(struct csiphy_device *csiphy)
+{
+	u8 bpp = csiphy_get_bpp(
+			csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
+	u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
+	u32 pixel_clock; /* Hz */
+	u32 mipi_clock; /* Hz */
+	u32 ui; /* ps */
+	u32 timer_period; /* ps */
+	u32 t_hs_prepare_max; /* ps */
+	u32 t_hs_prepare_zero_min; /* ps */
+	u32 t_hs_settle; /* ps */
+	u8 settle_cnt;
+	int ret;
+
+	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
+	if (ret) {
+		dev_err(to_device_index(csiphy, csiphy->id),
+			"Cannot get CSI2 transmitter's pixel clock\n");
+		return 0;
+	}
+	if (!pixel_clock) {
+		dev_err(to_device_index(csiphy, csiphy->id),
+			"Got pixel clock == 0, cannot continue\n");
+		return 0;
+	}
+
+	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
+	ui = div_u64(1000000000000LL, mipi_clock);
+	ui /= 2;
+	t_hs_prepare_max = 85000 + 6 * ui;
+	t_hs_prepare_zero_min = 145000 + 10 * ui;
+	t_hs_settle = (t_hs_prepare_max + t_hs_prepare_zero_min) / 2;
+
+	timer_period = div_u64(1000000000000LL, csiphy->timer_clk_rate);
+	settle_cnt = t_hs_settle / timer_period;
+
+	return settle_cnt;
+}
+
+/*
+ * csiphy_stream_on - Enable streaming on CSIPHY module
+ * @csiphy: CSIPHY device
+ *
+ * Helper function to enable streaming on CSIPHY module.
+ * Main configuration of CSIPHY module is also done here.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csiphy_stream_on(struct csiphy_device *csiphy)
+{
+	struct csiphy_config *cfg = &csiphy->cfg;
+	u8 lane_mask = csiphy_get_lane_mask(&cfg->csi2->lane_cfg);
+	u8 settle_cnt;
+	u8 val;
+	int i = 0;
+
+	settle_cnt = csiphy_settle_cnt_calc(csiphy);
+	if (!settle_cnt)
+		return -EINVAL;
+
+	val = readl_relaxed(csiphy->base_clk_mux);
+	if (cfg->combo_mode && (lane_mask & 0x18) == 0x18) {
+		val &= ~0xf0;
+		val |= cfg->csid_id << 4;
+	} else {
+		val &= ~0xf;
+		val |= cfg->csid_id;
+	}
+	writel_relaxed(val, csiphy->base_clk_mux);
+
+	writel_relaxed(0x1, csiphy->base +
+		       CAMSS_CSI_PHY_GLBL_T_INIT_CFG0);
+	writel_relaxed(0x1, csiphy->base +
+		       CAMSS_CSI_PHY_T_WAKEUP_CFG0);
+
+	val = 0x1;
+	val |= lane_mask << 1;
+	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+
+	val = cfg->combo_mode << 4;
+	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+
+	while (lane_mask) {
+		if (lane_mask & 0x1) {
+			writel_relaxed(0x10, csiphy->base +
+				       CAMSS_CSI_PHY_LNn_CFG2(i));
+			writel_relaxed(settle_cnt, csiphy->base +
+				       CAMSS_CSI_PHY_LNn_CFG3(i));
+			writel_relaxed(0x3f, csiphy->base +
+				       CAMSS_CSI_PHY_INTERRUPT_MASKn(i));
+			writel_relaxed(0x3f, csiphy->base +
+				       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+		}
+
+		lane_mask >>= 1;
+		i++;
+	}
+
+	return 0;
+}
+
+/*
+ * csiphy_stream_off - Disable streaming on CSIPHY module
+ * @csiphy: CSIPHY device
+ *
+ * Helper function to disable streaming on CSIPHY module
+ */
+static void csiphy_stream_off(struct csiphy_device *csiphy)
+{
+	u8 lane_mask = csiphy_get_lane_mask(&csiphy->cfg.csi2->lane_cfg);
+	int i = 0;
+
+	while (lane_mask) {
+		if (lane_mask & 0x1)
+			writel_relaxed(0x0, csiphy->base +
+				       CAMSS_CSI_PHY_LNn_CFG2(i));
+
+		lane_mask >>= 1;
+		i++;
+	}
+
+	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+}
+
+
+/*
+ * csiphy_set_stream - Enable/disable streaming on CSIPHY module
+ * @sd: CSIPHY V4L2 subdevice
+ * @enable: Requested streaming state
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csiphy_set_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
+	int ret = 0;
+
+	if (enable)
+		ret = csiphy_stream_on(csiphy);
+	else
+		csiphy_stream_off(csiphy);
+
+	return ret;
+}
+
+/*
+ * __csiphy_get_format - Get pointer to format structure
+ * @csiphy: CSIPHY device
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad from which format is requested
+ * @which: TRY or ACTIVE format
+ *
+ * Return pointer to TRY or ACTIVE format structure
+ */
+static struct v4l2_mbus_framefmt *
+__csiphy_get_format(struct csiphy_device *csiphy,
+		    struct v4l2_subdev_pad_config *cfg,
+		    unsigned int pad,
+		    enum v4l2_subdev_format_whence which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_format(&csiphy->subdev, cfg, pad);
+
+	return &csiphy->fmt[pad];
+}
+
+/*
+ * csiphy_try_format - Handle try format by pad subdev method
+ * @csiphy: CSIPHY device
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad on which format is requested
+ * @fmt: pointer to v4l2 format structure
+ * @which: wanted subdev format
+ */
+static void csiphy_try_format(struct csiphy_device *csiphy,
+			      struct v4l2_subdev_pad_config *cfg,
+			      unsigned int pad,
+			      struct v4l2_mbus_framefmt *fmt,
+			      enum v4l2_subdev_format_whence which)
+{
+	unsigned int i;
+
+	switch (pad) {
+	case MSM_CSIPHY_PAD_SINK:
+		/* Set format on sink pad */
+
+		for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
+			if (fmt->code == csiphy_formats[i].code)
+				break;
+
+		/* If not found, use UYVY as default */
+		if (i >= ARRAY_SIZE(csiphy_formats))
+			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
+
+		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
+		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
+
+		fmt->field = V4L2_FIELD_NONE;
+		fmt->colorspace = V4L2_COLORSPACE_SRGB;
+
+		break;
+
+	case MSM_CSIPHY_PAD_SRC:
+		/* Set and return a format same as sink pad */
+
+		*fmt = *__csiphy_get_format(csiphy, cfg, MSM_CSID_PAD_SINK,
+					    which);
+
+		break;
+	}
+}
+
+/*
+ * csiphy_enum_mbus_code - Handle pixel format enumeration
+ * @sd: CSIPHY V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @code: pointer to v4l2_subdev_mbus_code_enum structure
+ * return -EINVAL or zero on success
+ */
+static int csiphy_enum_mbus_code(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_pad_config *cfg,
+				 struct v4l2_subdev_mbus_code_enum *code)
+{
+	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	if (code->pad == MSM_CSIPHY_PAD_SINK) {
+		if (code->index >= ARRAY_SIZE(csiphy_formats))
+			return -EINVAL;
+
+		code->code = csiphy_formats[code->index].code;
+	} else {
+		if (code->index > 0)
+			return -EINVAL;
+
+		format = __csiphy_get_format(csiphy, cfg, MSM_CSIPHY_PAD_SINK,
+					     code->which);
+
+		code->code = format->code;
+	}
+
+	return 0;
+}
+
+/*
+ * csiphy_enum_frame_size - Handle frame size enumeration
+ * @sd: CSIPHY V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fse: pointer to v4l2_subdev_frame_size_enum structure
+ * return -EINVAL or zero on success
+ */
+static int csiphy_enum_frame_size(struct v4l2_subdev *sd,
+				  struct v4l2_subdev_pad_config *cfg,
+				  struct v4l2_subdev_frame_size_enum *fse)
+{
+	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt format;
+
+	if (fse->index != 0)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = 1;
+	format.height = 1;
+	csiphy_try_format(csiphy, cfg, fse->pad, &format, fse->which);
+	fse->min_width = format.width;
+	fse->min_height = format.height;
+
+	if (format.code != fse->code)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = -1;
+	format.height = -1;
+	csiphy_try_format(csiphy, cfg, fse->pad, &format, fse->which);
+	fse->max_width = format.width;
+	fse->max_height = format.height;
+
+	return 0;
+}
+
+/*
+ * csiphy_get_format - Handle get format by pads subdev method
+ * @sd: CSIPHY V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int csiphy_get_format(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_pad_config *cfg,
+			     struct v4l2_subdev_format *fmt)
+{
+	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __csiphy_get_format(csiphy, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	fmt->format = *format;
+
+	return 0;
+}
+
+/*
+ * csiphy_set_format - Handle set format by pads subdev method
+ * @sd: CSIPHY V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int csiphy_set_format(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_pad_config *cfg,
+			     struct v4l2_subdev_format *fmt)
+{
+	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __csiphy_get_format(csiphy, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	csiphy_try_format(csiphy, cfg, fmt->pad, &fmt->format, fmt->which);
+	*format = fmt->format;
+
+	/* Propagate the format from sink to source */
+	if (fmt->pad == MSM_CSIPHY_PAD_SINK) {
+		format = __csiphy_get_format(csiphy, cfg, MSM_CSIPHY_PAD_SRC,
+					     fmt->which);
+
+		*format = fmt->format;
+		csiphy_try_format(csiphy, cfg, MSM_CSIPHY_PAD_SRC, format,
+				  fmt->which);
+	}
+
+	return 0;
+}
+
+/*
+ * csiphy_init_formats - Initialize formats on all pads
+ * @sd: CSIPHY V4L2 subdevice
+ * @fh: V4L2 subdev file handle
+ *
+ * Initialize all pad formats with default values.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int csiphy_init_formats(struct v4l2_subdev *sd,
+			       struct v4l2_subdev_fh *fh)
+{
+	struct v4l2_subdev_format format = {
+		.pad = MSM_CSIPHY_PAD_SINK,
+		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
+			      V4L2_SUBDEV_FORMAT_ACTIVE,
+		.format = {
+			.code = MEDIA_BUS_FMT_UYVY8_2X8,
+			.width = 1920,
+			.height = 1080
+		}
+	};
+
+	return csiphy_set_format(sd, fh ? fh->pad : NULL, &format);
+}
+
+/*
+ * msm_csiphy_subdev_init - Initialize CSIPHY device structure and resources
+ * @csiphy: CSIPHY device
+ * @res: CSIPHY module resources table
+ * @id: CSIPHY module id
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
+			   const struct resources *res, u8 id)
+{
+	struct device *dev = to_device_index(csiphy, id);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct resource *r;
+	int i, j;
+	int ret;
+
+	csiphy->id = id;
+	csiphy->cfg.combo_mode = 0;
+
+	/* Memory */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
+	csiphy->base = devm_ioremap_resource(dev, r);
+	if (IS_ERR(csiphy->base)) {
+		dev_err(dev, "could not map memory\n");
+		return PTR_ERR(csiphy->base);
+	}
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[1]);
+	csiphy->base_clk_mux = devm_ioremap_resource(dev, r);
+	if (IS_ERR(csiphy->base_clk_mux)) {
+		dev_err(dev, "could not map memory\n");
+		return PTR_ERR(csiphy->base_clk_mux);
+	}
+
+	/* Interrupt */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ,
+					 res->interrupt[0]);
+	if (!r) {
+		dev_err(dev, "missing IRQ\n");
+		return -EINVAL;
+	}
+
+	csiphy->irq = r->start;
+	snprintf(csiphy->irq_name, sizeof(csiphy->irq_name), "%s_%s%d",
+		 dev_name(dev), MSM_CSIPHY_NAME, csiphy->id);
+	ret = devm_request_irq(dev, csiphy->irq, csiphy_isr,
+			       IRQF_TRIGGER_RISING, csiphy->irq_name, csiphy);
+	if (ret < 0) {
+		dev_err(dev, "request_irq failed: %d\n", ret);
+		return ret;
+	}
+
+	disable_irq(csiphy->irq);
+
+	/* Clocks */
+
+	csiphy->nclocks = 0;
+	while (res->clock[csiphy->nclocks])
+		csiphy->nclocks++;
+
+	csiphy->clock = devm_kcalloc(dev,
+				     csiphy->nclocks, sizeof(*csiphy->clock),
+				     GFP_KERNEL);
+	if (!csiphy->clock)
+		return -ENOMEM;
+
+	for (i = 0; i < csiphy->nclocks; i++) {
+		struct camss_clock *clock = &csiphy->clock[i];
+
+		clock->clk = devm_clk_get(dev, res->clock[i]);
+		if (IS_ERR(clock->clk))
+			return PTR_ERR(clock->clk);
+
+		clock->name = res->clock[i];
+
+		clock->nfreqs = 0;
+		while (res->clock_rate[i][clock->nfreqs])
+			clock->nfreqs++;
+
+		if (!clock->nfreqs) {
+			clock->freq = NULL;
+			continue;
+		}
+
+		clock->freq = devm_kcalloc(dev,
+					   clock->nfreqs,
+					   sizeof(*clock->freq),
+					   GFP_KERNEL);
+		if (!clock->freq)
+			return -ENOMEM;
+
+		for (j = 0; j < clock->nfreqs; j++)
+			clock->freq[j] = res->clock_rate[i][j];
+	}
+
+	return 0;
+}
+
+/*
+ * csiphy_link_setup - Setup CSIPHY connections
+ * @entity: Pointer to media entity structure
+ * @local: Pointer to local pad
+ * @remote: Pointer to remote pad
+ * @flags: Link flags
+ *
+ * Rreturn 0 on success
+ */
+static int csiphy_link_setup(struct media_entity *entity,
+			     const struct media_pad *local,
+			     const struct media_pad *remote, u32 flags)
+{
+	if ((local->flags & MEDIA_PAD_FL_SOURCE) &&
+	    (flags & MEDIA_LNK_FL_ENABLED)) {
+		struct v4l2_subdev *sd;
+		struct csiphy_device *csiphy;
+		struct csid_device *csid;
+
+		if (media_entity_remote_pad(local))
+			return -EBUSY;
+
+		sd = media_entity_to_v4l2_subdev(entity);
+		csiphy = v4l2_get_subdevdata(sd);
+
+		sd = media_entity_to_v4l2_subdev(remote->entity);
+		csid = v4l2_get_subdevdata(sd);
+
+		csiphy->cfg.csid_id = csid->id;
+	}
+
+	return 0;
+}
+
+static const struct v4l2_subdev_core_ops csiphy_core_ops = {
+	.s_power = csiphy_set_power,
+};
+
+static const struct v4l2_subdev_video_ops csiphy_video_ops = {
+	.s_stream = csiphy_set_stream,
+};
+
+static const struct v4l2_subdev_pad_ops csiphy_pad_ops = {
+	.enum_mbus_code = csiphy_enum_mbus_code,
+	.enum_frame_size = csiphy_enum_frame_size,
+	.get_fmt = csiphy_get_format,
+	.set_fmt = csiphy_set_format,
+};
+
+static const struct v4l2_subdev_ops csiphy_v4l2_ops = {
+	.core = &csiphy_core_ops,
+	.video = &csiphy_video_ops,
+	.pad = &csiphy_pad_ops,
+};
+
+static const struct v4l2_subdev_internal_ops csiphy_v4l2_internal_ops = {
+	.open = csiphy_init_formats,
+};
+
+static const struct media_entity_operations csiphy_media_ops = {
+	.link_setup = csiphy_link_setup,
+	.link_validate = v4l2_subdev_link_validate,
+};
+
+/*
+ * msm_csiphy_register_entity - Register subdev node for CSIPHY module
+ * @csiphy: CSIPHY device
+ * @v4l2_dev: V4L2 device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_csiphy_register_entity(struct csiphy_device *csiphy,
+			       struct v4l2_device *v4l2_dev)
+{
+	struct v4l2_subdev *sd = &csiphy->subdev;
+	struct media_pad *pads = csiphy->pads;
+	struct device *dev = to_device_index(csiphy, csiphy->id);
+	int ret;
+
+	v4l2_subdev_init(sd, &csiphy_v4l2_ops);
+	sd->internal_ops = &csiphy_v4l2_internal_ops;
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
+		 MSM_CSIPHY_NAME, csiphy->id);
+	v4l2_set_subdevdata(sd, csiphy);
+
+	ret = csiphy_init_formats(sd, NULL);
+	if (ret < 0) {
+		dev_err(dev, "Failed to init format: %d\n", ret);
+		return ret;
+	}
+
+	pads[MSM_CSIPHY_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
+	pads[MSM_CSIPHY_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
+
+	sd->entity.function = MEDIA_ENT_F_IO_V4L;
+	sd->entity.ops = &csiphy_media_ops;
+	ret = media_entity_pads_init(&sd->entity, MSM_CSIPHY_PADS_NUM, pads);
+	if (ret < 0) {
+		dev_err(dev, "Failed to init media entity: %d\n", ret);
+		return ret;
+	}
+
+	ret = v4l2_device_register_subdev(v4l2_dev, sd);
+	if (ret < 0) {
+		dev_err(dev, "Failed to register subdev: %d\n", ret);
+		media_entity_cleanup(&sd->entity);
+	}
+
+	return ret;
+}
+
+/*
+ * msm_csiphy_unregister_entity - Unregister CSIPHY module subdev node
+ * @csiphy: CSIPHY device
+ */
+void msm_csiphy_unregister_entity(struct csiphy_device *csiphy)
+{
+	v4l2_device_unregister_subdev(&csiphy->subdev);
+	media_entity_cleanup(&csiphy->subdev.entity);
+}
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
new file mode 100644
index 000000000000..9a422095b773
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -0,0 +1,77 @@
+/*
+ * camss-csiphy.h
+ *
+ * Qualcomm MSM Camera Subsystem - CSIPHY Module
+ *
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2016-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef QC_MSM_CAMSS_CSIPHY_H
+#define QC_MSM_CAMSS_CSIPHY_H
+
+#include <linux/clk.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-mediabus.h>
+#include <media/v4l2-subdev.h>
+
+#define MSM_CSIPHY_PAD_SINK 0
+#define MSM_CSIPHY_PAD_SRC 1
+#define MSM_CSIPHY_PADS_NUM 2
+
+struct csiphy_lane {
+	u8 pos;
+	u8 pol;
+};
+
+struct csiphy_lanes_cfg {
+	int num_data;
+	struct csiphy_lane *data;
+	struct csiphy_lane clk;
+};
+
+struct csiphy_csi2_cfg {
+	struct csiphy_lanes_cfg lane_cfg;
+};
+
+struct csiphy_config {
+	u8 combo_mode;
+	u8 csid_id;
+	struct csiphy_csi2_cfg *csi2;
+};
+
+struct csiphy_device {
+	u8 id;
+	struct v4l2_subdev subdev;
+	struct media_pad pads[MSM_CSIPHY_PADS_NUM];
+	void __iomem *base;
+	void __iomem *base_clk_mux;
+	u32 irq;
+	char irq_name[30];
+	struct camss_clock *clock;
+	int nclocks;
+	u32 timer_clk_rate;
+	struct csiphy_config cfg;
+	struct v4l2_mbus_framefmt fmt[MSM_CSIPHY_PADS_NUM];
+};
+
+struct resources;
+
+int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
+			   const struct resources *res, u8 id);
+
+int msm_csiphy_register_entity(struct csiphy_device *csiphy,
+			       struct v4l2_device *v4l2_dev);
+
+void msm_csiphy_unregister_entity(struct csiphy_device *csiphy);
+
+#endif /* QC_MSM_CAMSS_CSIPHY_H */
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
new file mode 100644
index 000000000000..636d5e712037
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -0,0 +1,1178 @@
+/*
+ * camss-ispif.c
+ *
+ * Qualcomm MSM Camera Subsystem - ISPIF (ISP Interface) Module
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+#include "camss-ispif.h"
+#include "camss.h"
+
+#define MSM_ISPIF_NAME "msm_ispif"
+
+#define ispif_line_array(ptr_line)	\
+	((const struct ispif_line (*)[]) &(ptr_line[-(ptr_line->id)]))
+
+#define to_ispif(ptr_line)	\
+	container_of(ispif_line_array(ptr_line), struct ispif_device, ptr_line)
+
+#define ISPIF_RST_CMD_0			0x008
+#define ISPIF_RST_CMD_0_STROBED_RST_EN		(1 << 0)
+#define ISPIF_RST_CMD_0_MISC_LOGIC_RST		(1 << 1)
+#define ISPIF_RST_CMD_0_SW_REG_RST		(1 << 2)
+#define ISPIF_RST_CMD_0_PIX_INTF_0_CSID_RST	(1 << 3)
+#define ISPIF_RST_CMD_0_PIX_INTF_0_VFE_RST	(1 << 4)
+#define ISPIF_RST_CMD_0_PIX_INTF_1_CSID_RST	(1 << 5)
+#define ISPIF_RST_CMD_0_PIX_INTF_1_VFE_RST	(1 << 6)
+#define ISPIF_RST_CMD_0_RDI_INTF_0_CSID_RST	(1 << 7)
+#define ISPIF_RST_CMD_0_RDI_INTF_0_VFE_RST	(1 << 8)
+#define ISPIF_RST_CMD_0_RDI_INTF_1_CSID_RST	(1 << 9)
+#define ISPIF_RST_CMD_0_RDI_INTF_1_VFE_RST	(1 << 10)
+#define ISPIF_RST_CMD_0_RDI_INTF_2_CSID_RST	(1 << 11)
+#define ISPIF_RST_CMD_0_RDI_INTF_2_VFE_RST	(1 << 12)
+#define ISPIF_RST_CMD_0_PIX_OUTPUT_0_MISR_RST	(1 << 16)
+#define ISPIF_RST_CMD_0_RDI_OUTPUT_0_MISR_RST	(1 << 17)
+#define ISPIF_RST_CMD_0_RDI_OUTPUT_1_MISR_RST	(1 << 18)
+#define ISPIF_RST_CMD_0_RDI_OUTPUT_2_MISR_RST	(1 << 19)
+#define ISPIF_IRQ_GLOBAL_CLEAR_CMD	0x01c
+#define ISPIF_VFE_m_CTRL_0(m)		(0x200 + 0x200 * (m))
+#define ISPIF_VFE_m_CTRL_0_PIX0_LINE_BUF_EN	(1 << 6)
+#define ISPIF_VFE_m_IRQ_MASK_0(m)	(0x208 + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_MASK_0_PIX0_ENABLE	0x00001249
+#define ISPIF_VFE_m_IRQ_MASK_0_PIX0_MASK	0x00001fff
+#define ISPIF_VFE_m_IRQ_MASK_0_RDI0_ENABLE	0x02492000
+#define ISPIF_VFE_m_IRQ_MASK_0_RDI0_MASK	0x03ffe000
+#define ISPIF_VFE_m_IRQ_MASK_1(m)	(0x20c + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_MASK_1_PIX1_ENABLE	0x00001249
+#define ISPIF_VFE_m_IRQ_MASK_1_PIX1_MASK	0x00001fff
+#define ISPIF_VFE_m_IRQ_MASK_1_RDI1_ENABLE	0x02492000
+#define ISPIF_VFE_m_IRQ_MASK_1_RDI1_MASK	0x03ffe000
+#define ISPIF_VFE_m_IRQ_MASK_2(m)	(0x210 + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_MASK_2_RDI2_ENABLE	0x00001249
+#define ISPIF_VFE_m_IRQ_MASK_2_RDI2_MASK	0x00001fff
+#define ISPIF_VFE_m_IRQ_STATUS_0(m)	(0x21c + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW	(1 << 12)
+#define ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW	(1 << 25)
+#define ISPIF_VFE_m_IRQ_STATUS_1(m)	(0x220 + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW	(1 << 12)
+#define ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW	(1 << 25)
+#define ISPIF_VFE_m_IRQ_STATUS_2(m)	(0x224 + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW	(1 << 12)
+#define ISPIF_VFE_m_IRQ_CLEAR_0(m)	(0x230 + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_CLEAR_1(m)	(0x234 + 0x200 * (m))
+#define ISPIF_VFE_m_IRQ_CLEAR_2(m)	(0x238 + 0x200 * (m))
+#define ISPIF_VFE_m_INTF_INPUT_SEL(m)	(0x244 + 0x200 * (m))
+#define ISPIF_VFE_m_INTF_CMD_0(m)	(0x248 + 0x200 * (m))
+#define ISPIF_VFE_m_INTF_CMD_1(m)	(0x24c + 0x200 * (m))
+#define ISPIF_VFE_m_PIX_INTF_n_CID_MASK(m, n)	\
+					(0x254 + 0x200 * (m) + 0x4 * (n))
+#define ISPIF_VFE_m_RDI_INTF_n_CID_MASK(m, n)	\
+					(0x264 + 0x200 * (m) + 0x4 * (n))
+#define ISPIF_VFE_m_PIX_INTF_n_STATUS(m, n)	\
+					(0x2c0 + 0x200 * (m) + 0x4 * (n))
+#define ISPIF_VFE_m_RDI_INTF_n_STATUS(m, n)	\
+					(0x2d0 + 0x200 * (m) + 0x4 * (n))
+
+#define CSI_PIX_CLK_MUX_SEL		0x000
+#define CSI_RDI_CLK_MUX_SEL		0x008
+
+#define ISPIF_TIMEOUT_SLEEP_US		1000
+#define ISPIF_TIMEOUT_ALL_US		1000000
+#define ISPIF_RESET_TIMEOUT_MS		500
+
+enum ispif_intf_cmd {
+	CMD_DISABLE_FRAME_BOUNDARY = 0x0,
+	CMD_ENABLE_FRAME_BOUNDARY = 0x1,
+	CMD_DISABLE_IMMEDIATELY = 0x2,
+	CMD_ALL_DISABLE_IMMEDIATELY = 0xaaaaaaaa,
+	CMD_ALL_NO_CHANGE = 0xffffffff,
+};
+
+static const u32 ispif_formats[] = {
+	MEDIA_BUS_FMT_UYVY8_2X8,
+	MEDIA_BUS_FMT_VYUY8_2X8,
+	MEDIA_BUS_FMT_YUYV8_2X8,
+	MEDIA_BUS_FMT_YVYU8_2X8,
+	MEDIA_BUS_FMT_SBGGR8_1X8,
+	MEDIA_BUS_FMT_SGBRG8_1X8,
+	MEDIA_BUS_FMT_SGRBG8_1X8,
+	MEDIA_BUS_FMT_SRGGB8_1X8,
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+	MEDIA_BUS_FMT_SBGGR12_1X12,
+	MEDIA_BUS_FMT_SGBRG12_1X12,
+	MEDIA_BUS_FMT_SGRBG12_1X12,
+	MEDIA_BUS_FMT_SRGGB12_1X12,
+};
+
+/*
+ * ispif_isr - ISPIF module interrupt handler
+ * @irq: Interrupt line
+ * @dev: ISPIF device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t ispif_isr(int irq, void *dev)
+{
+	struct ispif_device *ispif = dev;
+	u32 value0, value1, value2;
+
+	value0 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_0(0));
+	value1 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_1(0));
+	value2 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_2(0));
+
+	writel_relaxed(value0, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(0));
+	writel_relaxed(value1, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(0));
+	writel_relaxed(value2, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(0));
+
+	writel(0x1, ispif->base + ISPIF_IRQ_GLOBAL_CLEAR_CMD);
+
+	if ((value0 >> 27) & 0x1)
+		complete(&ispif->reset_complete);
+
+	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 pix0 overflow\n");
+
+	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi0 overflow\n");
+
+	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 pix1 overflow\n");
+
+	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi1 overflow\n");
+
+	if (unlikely(value2 & ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi2 overflow\n");
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * ispif_reset - Trigger reset on ISPIF module and wait to complete
+ * @ispif: ISPIF device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int ispif_reset(struct ispif_device *ispif)
+{
+	unsigned long time;
+	u32 val;
+	int ret;
+
+	ret = camss_enable_clocks(ispif->nclocks_for_reset,
+				  ispif->clock_for_reset,
+				  to_device(ispif));
+	if (ret < 0)
+		return ret;
+
+	reinit_completion(&ispif->reset_complete);
+
+	val = ISPIF_RST_CMD_0_STROBED_RST_EN |
+		ISPIF_RST_CMD_0_MISC_LOGIC_RST |
+		ISPIF_RST_CMD_0_SW_REG_RST |
+		ISPIF_RST_CMD_0_PIX_INTF_0_CSID_RST |
+		ISPIF_RST_CMD_0_PIX_INTF_0_VFE_RST |
+		ISPIF_RST_CMD_0_PIX_INTF_1_CSID_RST |
+		ISPIF_RST_CMD_0_PIX_INTF_1_VFE_RST |
+		ISPIF_RST_CMD_0_RDI_INTF_0_CSID_RST |
+		ISPIF_RST_CMD_0_RDI_INTF_0_VFE_RST |
+		ISPIF_RST_CMD_0_RDI_INTF_1_CSID_RST |
+		ISPIF_RST_CMD_0_RDI_INTF_1_VFE_RST |
+		ISPIF_RST_CMD_0_RDI_INTF_2_CSID_RST |
+		ISPIF_RST_CMD_0_RDI_INTF_2_VFE_RST |
+		ISPIF_RST_CMD_0_PIX_OUTPUT_0_MISR_RST |
+		ISPIF_RST_CMD_0_RDI_OUTPUT_0_MISR_RST |
+		ISPIF_RST_CMD_0_RDI_OUTPUT_1_MISR_RST |
+		ISPIF_RST_CMD_0_RDI_OUTPUT_2_MISR_RST;
+
+	writel_relaxed(val, ispif->base + ISPIF_RST_CMD_0);
+
+	time = wait_for_completion_timeout(&ispif->reset_complete,
+		msecs_to_jiffies(ISPIF_RESET_TIMEOUT_MS));
+	if (!time) {
+		dev_err(to_device(ispif), "ISPIF reset timeout\n");
+		return -EIO;
+	}
+
+	camss_disable_clocks(ispif->nclocks_for_reset, ispif->clock_for_reset);
+
+	return 0;
+}
+
+/*
+ * ispif_set_power - Power on/off ISPIF module
+ * @sd: ISPIF V4L2 subdevice
+ * @on: Requested power state
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int ispif_set_power(struct v4l2_subdev *sd, int on)
+{
+	struct ispif_line *line = v4l2_get_subdevdata(sd);
+	struct ispif_device *ispif = to_ispif(line);
+	struct device *dev = to_device(ispif);
+	int ret = 0;
+
+	mutex_lock(&ispif->power_lock);
+
+	if (on) {
+		if (ispif->power_count) {
+			/* Power is already on */
+			ispif->power_count++;
+			goto exit;
+		}
+
+		ret = camss_enable_clocks(ispif->nclocks, ispif->clock, dev);
+		if (ret < 0)
+			goto exit;
+
+		ret = ispif_reset(ispif);
+		if (ret < 0) {
+			camss_disable_clocks(ispif->nclocks, ispif->clock);
+			goto exit;
+		}
+
+		ispif->intf_cmd[line->vfe_id].cmd_0 = CMD_ALL_NO_CHANGE;
+		ispif->intf_cmd[line->vfe_id].cmd_1 = CMD_ALL_NO_CHANGE;
+
+		ispif->power_count++;
+	} else {
+		if (ispif->power_count == 0) {
+			dev_err(dev, "ispif power off on power_count == 0\n");
+			goto exit;
+		} else if (ispif->power_count == 1) {
+			camss_disable_clocks(ispif->nclocks, ispif->clock);
+		}
+
+		ispif->power_count--;
+	}
+
+exit:
+	mutex_unlock(&ispif->power_lock);
+
+	return ret;
+}
+
+/*
+ * ispif_select_clk_mux - Select clock for PIX/RDI interface
+ * @ispif: ISPIF device
+ * @intf: VFE interface
+ * @csid: CSID HW module id
+ * @vfe: VFE HW module id
+ * @enable: enable or disable the selected clock
+ */
+static void ispif_select_clk_mux(struct ispif_device *ispif,
+				 enum ispif_intf intf, u8 csid,
+				 u8 vfe, u8 enable)
+{
+	u32 val;
+
+	switch (intf) {
+	case PIX0:
+		val = readl_relaxed(ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
+		val &= ~(0xf << (vfe * 8));
+		if (enable)
+			val |= (csid << (vfe * 8));
+		writel_relaxed(val, ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
+		break;
+
+	case RDI0:
+		val = readl_relaxed(ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
+		val &= ~(0xf << (vfe * 12));
+		if (enable)
+			val |= (csid << (vfe * 12));
+		writel_relaxed(val, ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
+		break;
+
+	case PIX1:
+		val = readl_relaxed(ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
+		val &= ~(0xf << (4 + (vfe * 8)));
+		if (enable)
+			val |= (csid << (4 + (vfe * 8)));
+		writel_relaxed(val, ispif->base_clk_mux + CSI_PIX_CLK_MUX_SEL);
+		break;
+
+	case RDI1:
+		val = readl_relaxed(ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
+		val &= ~(0xf << (4 + (vfe * 12)));
+		if (enable)
+			val |= (csid << (4 + (vfe * 12)));
+		writel_relaxed(val, ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
+		break;
+
+	case RDI2:
+		val = readl_relaxed(ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
+		val &= ~(0xf << (8 + (vfe * 12)));
+		if (enable)
+			val |= (csid << (8 + (vfe * 12)));
+		writel_relaxed(val, ispif->base_clk_mux + CSI_RDI_CLK_MUX_SEL);
+		break;
+	}
+
+	mb();
+}
+
+/*
+ * ispif_validate_intf_status - Validate current status of PIX/RDI interface
+ * @ispif: ISPIF device
+ * @intf: VFE interface
+ * @vfe: VFE HW module id
+ *
+ * Return 0 when interface is idle or -EBUSY otherwise
+ */
+static int ispif_validate_intf_status(struct ispif_device *ispif,
+				      enum ispif_intf intf, u8 vfe)
+{
+	int ret = 0;
+	u32 val = 0;
+
+	switch (intf) {
+	case PIX0:
+		val = readl_relaxed(ispif->base +
+			ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 0));
+		break;
+	case RDI0:
+		val = readl_relaxed(ispif->base +
+			ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 0));
+		break;
+	case PIX1:
+		val = readl_relaxed(ispif->base +
+			ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 1));
+		break;
+	case RDI1:
+		val = readl_relaxed(ispif->base +
+			ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 1));
+		break;
+	case RDI2:
+		val = readl_relaxed(ispif->base +
+			ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 2));
+		break;
+	}
+
+	if ((val & 0xf) != 0xf) {
+		dev_err(to_device(ispif), "%s: ispif is busy: 0x%x\n",
+			__func__, val);
+		ret = -EBUSY;
+	}
+
+	return ret;
+}
+
+/*
+ * ispif_wait_for_stop - Wait for PIX/RDI interface to stop
+ * @ispif: ISPIF device
+ * @intf: VFE interface
+ * @vfe: VFE HW module id
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int ispif_wait_for_stop(struct ispif_device *ispif,
+			       enum ispif_intf intf, u8 vfe)
+{
+	u32 addr = 0;
+	u32 stop_flag = 0;
+	int ret;
+
+	switch (intf) {
+	case PIX0:
+		addr = ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 0);
+		break;
+	case RDI0:
+		addr = ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 0);
+		break;
+	case PIX1:
+		addr = ISPIF_VFE_m_PIX_INTF_n_STATUS(vfe, 1);
+		break;
+	case RDI1:
+		addr = ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 1);
+		break;
+	case RDI2:
+		addr = ISPIF_VFE_m_RDI_INTF_n_STATUS(vfe, 2);
+		break;
+	}
+
+	ret = readl_poll_timeout(ispif->base + addr,
+				 stop_flag,
+				 (stop_flag & 0xf) == 0xf,
+				 ISPIF_TIMEOUT_SLEEP_US,
+				 ISPIF_TIMEOUT_ALL_US);
+	if (ret < 0)
+		dev_err(to_device(ispif), "%s: ispif stop timeout\n",
+			__func__);
+
+	return ret;
+}
+
+/*
+ * ispif_select_csid - Select CSID HW module for input from
+ * @ispif: ISPIF device
+ * @intf: VFE interface
+ * @csid: CSID HW module id
+ * @vfe: VFE HW module id
+ * @enable: enable or disable the selected input
+ */
+static void ispif_select_csid(struct ispif_device *ispif, enum ispif_intf intf,
+			      u8 csid, u8 vfe, u8 enable)
+{
+	u32 val;
+
+	val = readl_relaxed(ispif->base + ISPIF_VFE_m_INTF_INPUT_SEL(vfe));
+	switch (intf) {
+	case PIX0:
+		val &= ~(BIT(1) | BIT(0));
+		if (enable)
+			val |= csid;
+		break;
+	case RDI0:
+		val &= ~(BIT(5) | BIT(4));
+		if (enable)
+			val |= (csid << 4);
+		break;
+	case PIX1:
+		val &= ~(BIT(9) | BIT(8));
+		if (enable)
+			val |= (csid << 8);
+		break;
+	case RDI1:
+		val &= ~(BIT(13) | BIT(12));
+		if (enable)
+			val |= (csid << 12);
+		break;
+	case RDI2:
+		val &= ~(BIT(21) | BIT(20));
+		if (enable)
+			val |= (csid << 20);
+		break;
+	}
+
+	writel(val, ispif->base + ISPIF_VFE_m_INTF_INPUT_SEL(vfe));
+}
+
+/*
+ * ispif_select_cid - Enable/disable desired CID
+ * @ispif: ISPIF device
+ * @intf: VFE interface
+ * @cid: desired CID to enable/disable
+ * @vfe: VFE HW module id
+ * @enable: enable or disable the desired CID
+ */
+static void ispif_select_cid(struct ispif_device *ispif, enum ispif_intf intf,
+			     u8 cid, u8 vfe, u8 enable)
+{
+	u32 cid_mask = 1 << cid;
+	u32 addr = 0;
+	u32 val;
+
+	switch (intf) {
+	case PIX0:
+		addr = ISPIF_VFE_m_PIX_INTF_n_CID_MASK(vfe, 0);
+		break;
+	case RDI0:
+		addr = ISPIF_VFE_m_RDI_INTF_n_CID_MASK(vfe, 0);
+		break;
+	case PIX1:
+		addr = ISPIF_VFE_m_PIX_INTF_n_CID_MASK(vfe, 1);
+		break;
+	case RDI1:
+		addr = ISPIF_VFE_m_RDI_INTF_n_CID_MASK(vfe, 1);
+		break;
+	case RDI2:
+		addr = ISPIF_VFE_m_RDI_INTF_n_CID_MASK(vfe, 2);
+		break;
+	}
+
+	val = readl_relaxed(ispif->base + addr);
+	if (enable)
+		val |= cid_mask;
+	else
+		val &= ~cid_mask;
+
+	writel(val, ispif->base + addr);
+}
+
+/*
+ * ispif_config_irq - Enable/disable interrupts for PIX/RDI interface
+ * @ispif: ISPIF device
+ * @intf: VFE interface
+ * @vfe: VFE HW module id
+ * @enable: enable or disable
+ */
+static void ispif_config_irq(struct ispif_device *ispif, enum ispif_intf intf,
+			     u8 vfe, u8 enable)
+{
+	u32 val;
+
+	switch (intf) {
+	case PIX0:
+		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
+		val &= ~ISPIF_VFE_m_IRQ_MASK_0_PIX0_MASK;
+		if (enable)
+			val |= ISPIF_VFE_m_IRQ_MASK_0_PIX0_ENABLE;
+		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
+		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_0_PIX0_ENABLE,
+			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(vfe));
+		break;
+	case RDI0:
+		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
+		val &= ~ISPIF_VFE_m_IRQ_MASK_0_RDI0_MASK;
+		if (enable)
+			val |= ISPIF_VFE_m_IRQ_MASK_0_RDI0_ENABLE;
+		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_0(vfe));
+		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_0_RDI0_ENABLE,
+			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(vfe));
+		break;
+	case PIX1:
+		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
+		val &= ~ISPIF_VFE_m_IRQ_MASK_1_PIX1_MASK;
+		if (enable)
+			val |= ISPIF_VFE_m_IRQ_MASK_1_PIX1_ENABLE;
+		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
+		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_1_PIX1_ENABLE,
+			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(vfe));
+		break;
+	case RDI1:
+		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
+		val &= ~ISPIF_VFE_m_IRQ_MASK_1_RDI1_MASK;
+		if (enable)
+			val |= ISPIF_VFE_m_IRQ_MASK_1_RDI1_ENABLE;
+		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_1(vfe));
+		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_1_RDI1_ENABLE,
+			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(vfe));
+		break;
+	case RDI2:
+		val = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_MASK_2(vfe));
+		val &= ~ISPIF_VFE_m_IRQ_MASK_2_RDI2_MASK;
+		if (enable)
+			val |= ISPIF_VFE_m_IRQ_MASK_2_RDI2_ENABLE;
+		writel_relaxed(val, ispif->base + ISPIF_VFE_m_IRQ_MASK_2(vfe));
+		writel_relaxed(ISPIF_VFE_m_IRQ_MASK_2_RDI2_ENABLE,
+			       ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(vfe));
+		break;
+	}
+
+	writel(0x1, ispif->base + ISPIF_IRQ_GLOBAL_CLEAR_CMD);
+}
+
+/*
+ * ispif_set_intf_cmd - Set command to enable/disable interface
+ * @ispif: ISPIF device
+ * @cmd: interface command
+ * @intf: VFE interface
+ * @vfe: VFE HW module id
+ * @vc: virtual channel
+ */
+static void ispif_set_intf_cmd(struct ispif_device *ispif, u8 cmd,
+			       enum ispif_intf intf, u8 vfe, u8 vc)
+{
+	u32 *val;
+
+	if (intf == RDI2) {
+		val = &ispif->intf_cmd[vfe].cmd_1;
+		*val &= ~(0x3 << (vc * 2 + 8));
+		*val |= (cmd << (vc * 2 + 8));
+		wmb();
+		writel_relaxed(*val, ispif->base + ISPIF_VFE_m_INTF_CMD_1(vfe));
+		wmb();
+	} else {
+		val = &ispif->intf_cmd[vfe].cmd_0;
+		*val &= ~(0x3 << (vc * 2 + intf * 8));
+		*val |= (cmd << (vc * 2 + intf * 8));
+		wmb();
+		writel_relaxed(*val, ispif->base + ISPIF_VFE_m_INTF_CMD_0(vfe));
+		wmb();
+	}
+}
+
+/*
+ * ispif_set_stream - Enable/disable streaming on ISPIF module
+ * @sd: ISPIF V4L2 subdevice
+ * @enable: Requested streaming state
+ *
+ * Main configuration of ISPIF module is also done here.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct ispif_line *line = v4l2_get_subdevdata(sd);
+	struct ispif_device *ispif = to_ispif(line);
+	enum ispif_intf intf = line->interface;
+	u8 csid = line->csid_id;
+	u8 vfe = line->vfe_id;
+	u8 vc = 0; /* Virtual Channel 0 */
+	u8 cid = vc * 4; /* id of Virtual Channel and Data Type set */
+	int ret;
+
+	if (enable) {
+		if (!media_entity_remote_pad(&line->pads[MSM_ISPIF_PAD_SINK]))
+			return -ENOLINK;
+
+		/* Config */
+
+		mutex_lock(&ispif->config_lock);
+		ispif_select_clk_mux(ispif, intf, csid, vfe, 1);
+
+		ret = ispif_validate_intf_status(ispif, intf, vfe);
+		if (ret < 0) {
+			mutex_unlock(&ispif->config_lock);
+			return ret;
+		}
+
+		ispif_select_csid(ispif, intf, csid, vfe, 1);
+		ispif_select_cid(ispif, intf, cid, vfe, 1);
+		ispif_config_irq(ispif, intf, vfe, 1);
+		ispif_set_intf_cmd(ispif, CMD_ENABLE_FRAME_BOUNDARY,
+				   intf, vfe, vc);
+	} else {
+		mutex_lock(&ispif->config_lock);
+		ispif_set_intf_cmd(ispif, CMD_DISABLE_FRAME_BOUNDARY,
+				   intf, vfe, vc);
+		mutex_unlock(&ispif->config_lock);
+
+		ret = ispif_wait_for_stop(ispif, intf, vfe);
+		if (ret < 0)
+			return ret;
+
+		mutex_lock(&ispif->config_lock);
+		ispif_config_irq(ispif, intf, vfe, 0);
+		ispif_select_cid(ispif, intf, cid, vfe, 0);
+		ispif_select_csid(ispif, intf, csid, vfe, 0);
+		ispif_select_clk_mux(ispif, intf, csid, vfe, 0);
+	}
+
+	mutex_unlock(&ispif->config_lock);
+
+	return 0;
+}
+
+/*
+ * __ispif_get_format - Get pointer to format structure
+ * @ispif: ISPIF line
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad from which format is requested
+ * @which: TRY or ACTIVE format
+ *
+ * Return pointer to TRY or ACTIVE format structure
+ */
+static struct v4l2_mbus_framefmt *
+__ispif_get_format(struct ispif_line *line,
+		   struct v4l2_subdev_pad_config *cfg,
+		   unsigned int pad,
+		   enum v4l2_subdev_format_whence which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_format(&line->subdev, cfg, pad);
+
+	return &line->fmt[pad];
+}
+
+/*
+ * ispif_try_format - Handle try format by pad subdev method
+ * @ispif: ISPIF line
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad on which format is requested
+ * @fmt: pointer to v4l2 format structure
+ * @which: wanted subdev format
+ */
+static void ispif_try_format(struct ispif_line *line,
+			     struct v4l2_subdev_pad_config *cfg,
+			     unsigned int pad,
+			     struct v4l2_mbus_framefmt *fmt,
+			     enum v4l2_subdev_format_whence which)
+{
+	unsigned int i;
+
+	switch (pad) {
+	case MSM_ISPIF_PAD_SINK:
+		/* Set format on sink pad */
+
+		for (i = 0; i < ARRAY_SIZE(ispif_formats); i++)
+			if (fmt->code == ispif_formats[i])
+				break;
+
+		/* If not found, use UYVY as default */
+		if (i >= ARRAY_SIZE(ispif_formats))
+			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
+
+		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
+		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
+
+		fmt->field = V4L2_FIELD_NONE;
+		fmt->colorspace = V4L2_COLORSPACE_SRGB;
+
+		break;
+
+	case MSM_ISPIF_PAD_SRC:
+		/* Set and return a format same as sink pad */
+
+		*fmt = *__ispif_get_format(line, cfg, MSM_ISPIF_PAD_SINK,
+					   which);
+
+		break;
+	}
+
+	fmt->colorspace = V4L2_COLORSPACE_SRGB;
+}
+
+/*
+ * ispif_enum_mbus_code - Handle pixel format enumeration
+ * @sd: ISPIF V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @code: pointer to v4l2_subdev_mbus_code_enum structure
+ * return -EINVAL or zero on success
+ */
+static int ispif_enum_mbus_code(struct v4l2_subdev *sd,
+				struct v4l2_subdev_pad_config *cfg,
+				struct v4l2_subdev_mbus_code_enum *code)
+{
+	struct ispif_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	if (code->pad == MSM_ISPIF_PAD_SINK) {
+		if (code->index >= ARRAY_SIZE(ispif_formats))
+			return -EINVAL;
+
+		code->code = ispif_formats[code->index];
+	} else {
+		if (code->index > 0)
+			return -EINVAL;
+
+		format = __ispif_get_format(line, cfg, MSM_ISPIF_PAD_SINK,
+					    code->which);
+
+		code->code = format->code;
+	}
+
+	return 0;
+}
+
+/*
+ * ispif_enum_frame_size - Handle frame size enumeration
+ * @sd: ISPIF V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fse: pointer to v4l2_subdev_frame_size_enum structure
+ * return -EINVAL or zero on success
+ */
+static int ispif_enum_frame_size(struct v4l2_subdev *sd,
+				 struct v4l2_subdev_pad_config *cfg,
+				 struct v4l2_subdev_frame_size_enum *fse)
+{
+	struct ispif_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt format;
+
+	if (fse->index != 0)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = 1;
+	format.height = 1;
+	ispif_try_format(line, cfg, fse->pad, &format, fse->which);
+	fse->min_width = format.width;
+	fse->min_height = format.height;
+
+	if (format.code != fse->code)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = -1;
+	format.height = -1;
+	ispif_try_format(line, cfg, fse->pad, &format, fse->which);
+	fse->max_width = format.width;
+	fse->max_height = format.height;
+
+	return 0;
+}
+
+/*
+ * ispif_get_format - Handle get format by pads subdev method
+ * @sd: ISPIF V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int ispif_get_format(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_pad_config *cfg,
+			    struct v4l2_subdev_format *fmt)
+{
+	struct ispif_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __ispif_get_format(line, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	fmt->format = *format;
+
+	return 0;
+}
+
+/*
+ * ispif_set_format - Handle set format by pads subdev method
+ * @sd: ISPIF V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int ispif_set_format(struct v4l2_subdev *sd,
+			    struct v4l2_subdev_pad_config *cfg,
+			    struct v4l2_subdev_format *fmt)
+{
+	struct ispif_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __ispif_get_format(line, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	ispif_try_format(line, cfg, fmt->pad, &fmt->format, fmt->which);
+	*format = fmt->format;
+
+	/* Propagate the format from sink to source */
+	if (fmt->pad == MSM_ISPIF_PAD_SINK) {
+		format = __ispif_get_format(line, cfg, MSM_ISPIF_PAD_SRC,
+					    fmt->which);
+
+		*format = fmt->format;
+		ispif_try_format(line, cfg, MSM_ISPIF_PAD_SRC, format,
+				 fmt->which);
+	}
+
+	return 0;
+}
+
+/*
+ * ispif_init_formats - Initialize formats on all pads
+ * @sd: ISPIF V4L2 subdevice
+ * @fh: V4L2 subdev file handle
+ *
+ * Initialize all pad formats with default values.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int ispif_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	struct v4l2_subdev_format format = {
+		.pad = MSM_ISPIF_PAD_SINK,
+		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
+			      V4L2_SUBDEV_FORMAT_ACTIVE,
+		.format = {
+			.code = MEDIA_BUS_FMT_UYVY8_2X8,
+			.width = 1920,
+			.height = 1080
+		}
+	};
+
+	return ispif_set_format(sd, fh ? fh->pad : NULL, &format);
+}
+
+/*
+ * msm_ispif_subdev_init - Initialize ISPIF device structure and resources
+ * @ispif: ISPIF device
+ * @res: ISPIF module resources table
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_ispif_subdev_init(struct ispif_device *ispif,
+			  const struct resources_ispif *res)
+{
+	struct device *dev = to_device(ispif);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct resource *r;
+	int i;
+	int ret;
+
+	/* Memory */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
+	ispif->base = devm_ioremap_resource(dev, r);
+	if (IS_ERR(ispif->base)) {
+		dev_err(dev, "could not map memory\n");
+		return PTR_ERR(ispif->base);
+	}
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[1]);
+	ispif->base_clk_mux = devm_ioremap_resource(dev, r);
+	if (IS_ERR(ispif->base_clk_mux)) {
+		dev_err(dev, "could not map memory\n");
+		return PTR_ERR(ispif->base_clk_mux);
+	}
+
+	/* Interrupt */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ, res->interrupt);
+
+	if (!r) {
+		dev_err(dev, "missing IRQ\n");
+		return -EINVAL;
+	}
+
+	ispif->irq = r->start;
+	snprintf(ispif->irq_name, sizeof(ispif->irq_name), "%s_%s",
+		 dev_name(dev), MSM_ISPIF_NAME);
+	ret = devm_request_irq(dev, ispif->irq, ispif_isr,
+			       IRQF_TRIGGER_RISING, ispif->irq_name, ispif);
+	if (ret < 0) {
+		dev_err(dev, "request_irq failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Clocks */
+
+	ispif->nclocks = 0;
+	while (res->clock[ispif->nclocks])
+		ispif->nclocks++;
+
+	ispif->clock = devm_kcalloc(dev,
+				    ispif->nclocks, sizeof(*ispif->clock),
+				    GFP_KERNEL);
+	if (!ispif->clock)
+		return -ENOMEM;
+
+	for (i = 0; i < ispif->nclocks; i++) {
+		struct camss_clock *clock = &ispif->clock[i];
+
+		clock->clk = devm_clk_get(dev, res->clock[i]);
+		if (IS_ERR(clock->clk))
+			return PTR_ERR(clock->clk);
+
+		clock->freq = NULL;
+		clock->nfreqs = 0;
+	}
+
+	ispif->nclocks_for_reset = 0;
+	while (res->clock_for_reset[ispif->nclocks_for_reset])
+		ispif->nclocks_for_reset++;
+
+	ispif->clock_for_reset = devm_kcalloc(dev,
+					      ispif->nclocks_for_reset,
+					      sizeof(*ispif->clock_for_reset),
+					      GFP_KERNEL);
+	if (!ispif->clock_for_reset)
+		return -ENOMEM;
+
+	for (i = 0; i < ispif->nclocks_for_reset; i++) {
+		struct camss_clock *clock = &ispif->clock_for_reset[i];
+
+		clock->clk = devm_clk_get(dev, res->clock_for_reset[i]);
+		if (IS_ERR(clock->clk))
+			return PTR_ERR(clock->clk);
+
+		clock->freq = NULL;
+		clock->nfreqs = 0;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(ispif->line); i++)
+		ispif->line[i].id = i;
+
+	mutex_init(&ispif->power_lock);
+	ispif->power_count = 0;
+
+	mutex_init(&ispif->config_lock);
+
+	init_completion(&ispif->reset_complete);
+
+	return 0;
+}
+
+/*
+ * ispif_get_intf - Get ISPIF interface to use by VFE line id
+ * @line_id: VFE line id that the ISPIF line is connected to
+ *
+ * Return ISPIF interface to use
+ */
+static enum ispif_intf ispif_get_intf(enum vfe_line_id line_id)
+{
+	switch (line_id) {
+	case (VFE_LINE_RDI0):
+		return RDI0;
+	case (VFE_LINE_RDI1):
+		return RDI1;
+	case (VFE_LINE_RDI2):
+		return RDI2;
+	case (VFE_LINE_PIX):
+		return PIX0;
+	default:
+		return RDI0;
+	}
+}
+
+/*
+ * ispif_link_setup - Setup ISPIF connections
+ * @entity: Pointer to media entity structure
+ * @local: Pointer to local pad
+ * @remote: Pointer to remote pad
+ * @flags: Link flags
+ *
+ * Return 0 on success
+ */
+static int ispif_link_setup(struct media_entity *entity,
+			    const struct media_pad *local,
+			    const struct media_pad *remote, u32 flags)
+{
+	if (flags & MEDIA_LNK_FL_ENABLED) {
+		if (media_entity_remote_pad(local))
+			return -EBUSY;
+
+		if (local->flags & MEDIA_PAD_FL_SINK) {
+			struct v4l2_subdev *sd;
+			struct ispif_line *line;
+
+			sd = media_entity_to_v4l2_subdev(entity);
+			line = v4l2_get_subdevdata(sd);
+
+			msm_csid_get_csid_id(remote->entity, &line->csid_id);
+		} else { /* MEDIA_PAD_FL_SOURCE */
+			struct v4l2_subdev *sd;
+			struct ispif_line *line;
+			enum vfe_line_id id;
+
+			sd = media_entity_to_v4l2_subdev(entity);
+			line = v4l2_get_subdevdata(sd);
+
+			msm_vfe_get_vfe_id(remote->entity, &line->vfe_id);
+			msm_vfe_get_vfe_line_id(remote->entity, &id);
+			line->interface = ispif_get_intf(id);
+		}
+	}
+
+	return 0;
+}
+
+static const struct v4l2_subdev_core_ops ispif_core_ops = {
+	.s_power = ispif_set_power,
+};
+
+static const struct v4l2_subdev_video_ops ispif_video_ops = {
+	.s_stream = ispif_set_stream,
+};
+
+static const struct v4l2_subdev_pad_ops ispif_pad_ops = {
+	.enum_mbus_code = ispif_enum_mbus_code,
+	.enum_frame_size = ispif_enum_frame_size,
+	.get_fmt = ispif_get_format,
+	.set_fmt = ispif_set_format,
+};
+
+static const struct v4l2_subdev_ops ispif_v4l2_ops = {
+	.core = &ispif_core_ops,
+	.video = &ispif_video_ops,
+	.pad = &ispif_pad_ops,
+};
+
+static const struct v4l2_subdev_internal_ops ispif_v4l2_internal_ops = {
+	.open = ispif_init_formats,
+};
+
+static const struct media_entity_operations ispif_media_ops = {
+	.link_setup = ispif_link_setup,
+	.link_validate = v4l2_subdev_link_validate,
+};
+
+/*
+ * msm_ispif_register_entities - Register subdev node for ISPIF module
+ * @ispif: ISPIF device
+ * @v4l2_dev: V4L2 device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_ispif_register_entities(struct ispif_device *ispif,
+				struct v4l2_device *v4l2_dev)
+{
+	struct device *dev = to_device(ispif);
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
+		struct v4l2_subdev *sd = &ispif->line[i].subdev;
+		struct media_pad *pads = ispif->line[i].pads;
+
+		v4l2_subdev_init(sd, &ispif_v4l2_ops);
+		sd->internal_ops = &ispif_v4l2_internal_ops;
+		sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+		snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
+			 MSM_ISPIF_NAME, i);
+		v4l2_set_subdevdata(sd, &ispif->line[i]);
+
+		ret = ispif_init_formats(sd, NULL);
+		if (ret < 0) {
+			dev_err(dev, "Failed to init format: %d\n", ret);
+			goto error;
+		}
+
+		pads[MSM_ISPIF_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
+		pads[MSM_ISPIF_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
+
+		sd->entity.function = MEDIA_ENT_F_IO_V4L;
+		sd->entity.ops = &ispif_media_ops;
+		ret = media_entity_pads_init(&sd->entity, MSM_ISPIF_PADS_NUM,
+					     pads);
+		if (ret < 0) {
+			dev_err(dev, "Failed to init media entity: %d\n", ret);
+			goto error;
+		}
+
+		ret = v4l2_device_register_subdev(v4l2_dev, sd);
+		if (ret < 0) {
+			dev_err(dev, "Failed to register subdev: %d\n", ret);
+			media_entity_cleanup(&sd->entity);
+			goto error;
+		}
+	}
+
+	return 0;
+
+error:
+	for (i--; i >= 0; i--) {
+		struct v4l2_subdev *sd = &ispif->line[i].subdev;
+
+		v4l2_device_unregister_subdev(sd);
+		media_entity_cleanup(&sd->entity);
+	}
+
+	return ret;
+}
+
+/*
+ * msm_ispif_unregister_entities - Unregister ISPIF module subdev node
+ * @ispif: ISPIF device
+ */
+void msm_ispif_unregister_entities(struct ispif_device *ispif)
+{
+	int i;
+
+	mutex_destroy(&ispif->power_lock);
+	mutex_destroy(&ispif->config_lock);
+
+	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
+		struct v4l2_subdev *sd = &ispif->line[i].subdev;
+
+		v4l2_device_unregister_subdev(sd);
+		media_entity_cleanup(&sd->entity);
+	}
+}
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.h b/drivers/media/platform/qcom/camss/camss-ispif.h
new file mode 100644
index 000000000000..c90e1598943a
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-ispif.h
@@ -0,0 +1,85 @@
+/*
+ * camss-ispif.h
+ *
+ * Qualcomm MSM Camera Subsystem - ISPIF (ISP Interface) Module
+ *
+ * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef QC_MSM_CAMSS_ISPIF_H
+#define QC_MSM_CAMSS_ISPIF_H
+
+#include <linux/clk.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+/* Number of ISPIF lines - same as number of CSID hardware modules */
+#define MSM_ISPIF_LINE_NUM 2
+
+#define MSM_ISPIF_PAD_SINK 0
+#define MSM_ISPIF_PAD_SRC 1
+#define MSM_ISPIF_PADS_NUM 2
+
+#define MSM_ISPIF_VFE_NUM 1
+
+enum ispif_intf {
+	PIX0,
+	RDI0,
+	PIX1,
+	RDI1,
+	RDI2
+};
+
+struct ispif_intf_cmd_reg {
+	u32 cmd_0;
+	u32 cmd_1;
+};
+
+struct ispif_line {
+	u8 id;
+	u8 csid_id;
+	u8 vfe_id;
+	enum ispif_intf interface;
+	struct v4l2_subdev subdev;
+	struct media_pad pads[MSM_ISPIF_PADS_NUM];
+	struct v4l2_mbus_framefmt fmt[MSM_ISPIF_PADS_NUM];
+};
+
+struct ispif_device {
+	void __iomem *base;
+	void __iomem *base_clk_mux;
+	u32 irq;
+	char irq_name[30];
+	struct camss_clock *clock;
+	int nclocks;
+	struct camss_clock  *clock_for_reset;
+	int nclocks_for_reset;
+	struct completion reset_complete;
+	int power_count;
+	struct mutex power_lock;
+	struct ispif_intf_cmd_reg intf_cmd[MSM_ISPIF_VFE_NUM];
+	struct mutex config_lock;
+	struct ispif_line line[MSM_ISPIF_LINE_NUM];
+};
+
+struct resources_ispif;
+
+int msm_ispif_subdev_init(struct ispif_device *ispif,
+			  const struct resources_ispif *res);
+
+int msm_ispif_register_entities(struct ispif_device *ispif,
+				struct v4l2_device *v4l2_dev);
+
+void msm_ispif_unregister_entities(struct ispif_device *ispif);
+
+#endif /* QC_MSM_CAMSS_ISPIF_H */
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
new file mode 100644
index 000000000000..380b90bdd720
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -0,0 +1,3093 @@
+/*
+ * camss-vfe.c
+ *
+ * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/completion.h>
+#include <linux/interrupt.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/mutex.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/spinlock_types.h>
+#include <linux/spinlock.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+#include "camss-vfe.h"
+#include "camss.h"
+
+#define MSM_VFE_NAME "msm_vfe"
+
+#define vfe_line_array(ptr_line)	\
+	((const struct vfe_line (*)[]) &(ptr_line[-(ptr_line->id)]))
+
+#define to_vfe(ptr_line)	\
+	container_of(vfe_line_array(ptr_line), struct vfe_device, ptr_line)
+
+#define VFE_0_HW_VERSION		0x000
+
+#define VFE_0_GLOBAL_RESET_CMD		0x00c
+#define VFE_0_GLOBAL_RESET_CMD_CORE	(1 << 0)
+#define VFE_0_GLOBAL_RESET_CMD_CAMIF	(1 << 1)
+#define VFE_0_GLOBAL_RESET_CMD_BUS	(1 << 2)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	(1 << 3)
+#define VFE_0_GLOBAL_RESET_CMD_REGISTER	(1 << 4)
+#define VFE_0_GLOBAL_RESET_CMD_TIMER	(1 << 5)
+#define VFE_0_GLOBAL_RESET_CMD_PM	(1 << 6)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	(1 << 7)
+#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	(1 << 8)
+
+#define VFE_0_MODULE_CFG		0x018
+#define VFE_0_MODULE_CFG_DEMUX			(1 << 2)
+#define VFE_0_MODULE_CFG_CHROMA_UPSAMPLE	(1 << 3)
+#define VFE_0_MODULE_CFG_SCALE_ENC		(1 << 23)
+#define VFE_0_MODULE_CFG_CROP_ENC		(1 << 27)
+
+#define VFE_0_CORE_CFG			0x01c
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
+
+#define VFE_0_IRQ_CMD			0x024
+#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	(1 << 0)
+
+#define VFE_0_IRQ_MASK_0		0x028
+#define VFE_0_IRQ_MASK_0_CAMIF_SOF			(1 << 0)
+#define VFE_0_IRQ_MASK_0_CAMIF_EOF			(1 << 1)
+#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
+#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
+#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
+#define VFE_0_IRQ_MASK_0_RESET_ACK			(1 << 31)
+#define VFE_0_IRQ_MASK_1		0x02c
+#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			(1 << 0)
+#define VFE_0_IRQ_MASK_1_VIOLATION			(1 << 7)
+#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		(1 << 8)
+#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	(1 << ((n) + 9))
+#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			(1 << ((n) + 29))
+
+#define VFE_0_IRQ_CLEAR_0		0x030
+#define VFE_0_IRQ_CLEAR_1		0x034
+
+#define VFE_0_IRQ_STATUS_0		0x038
+#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			(1 << 0)
+#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
+#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
+#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
+#define VFE_0_IRQ_STATUS_0_RESET_ACK			(1 << 31)
+#define VFE_0_IRQ_STATUS_1		0x03c
+#define VFE_0_IRQ_STATUS_1_VIOLATION			(1 << 7)
+#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		(1 << 8)
+#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			(1 << ((n) + 29))
+
+#define VFE_0_IRQ_COMPOSITE_MASK_0	0x40
+#define VFE_0_VIOLATION_STATUS		0x48
+
+#define VFE_0_BUS_CMD			0x4c
+#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	(1 << (x))
+
+#define VFE_0_BUS_CFG			0x050
+
+#define VFE_0_BUS_XBAR_CFG_x(x)		(0x58 + 0x4 * ((x) / 2))
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			(1 << 1)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	5
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	6
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	7
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x06c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT	1
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x070 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x074 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x078 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1F << 2)
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x07c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x080 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x084 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
+							(0x088 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
+							(0x08c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
+
+#define VFE_0_BUS_PING_PONG_STATUS	0x268
+
+#define VFE_0_BUS_BDG_CMD		0x2c0
+#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
+
+#define VFE_0_BUS_BDG_QOS_CFG_0		0x2c4
+#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa5aaa5
+#define VFE_0_BUS_BDG_QOS_CFG_1		0x2c8
+#define VFE_0_BUS_BDG_QOS_CFG_2		0x2cc
+#define VFE_0_BUS_BDG_QOS_CFG_3		0x2d0
+#define VFE_0_BUS_BDG_QOS_CFG_4		0x2d4
+#define VFE_0_BUS_BDG_QOS_CFG_5		0x2d8
+#define VFE_0_BUS_BDG_QOS_CFG_6		0x2dc
+#define VFE_0_BUS_BDG_QOS_CFG_7		0x2e0
+#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa5
+
+#define VFE_0_RDI_CFG_x(x)		(0x2e8 + (0x4 * (x)))
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
+#define VFE_0_RDI_CFG_x_RDI_EN_BIT		(1 << 2)
+#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
+#define VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(r)	(1 << (16 + (r)))
+
+#define VFE_0_CAMIF_CMD				0x2f4
+#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
+#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
+#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	(1 << 2)
+#define VFE_0_CAMIF_CFG				0x2f8
+#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		(1 << 6)
+#define VFE_0_CAMIF_FRAME_CFG			0x300
+#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x304
+#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x308
+#define VFE_0_CAMIF_SUBSAMPLE_CFG_0		0x30c
+#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x314
+#define VFE_0_CAMIF_STATUS			0x31c
+#define VFE_0_CAMIF_STATUS_HALT			(1 << 31)
+
+#define VFE_0_REG_UPDATE			0x378
+#define VFE_0_REG_UPDATE_RDIn(n)		(1 << (1 + (n)))
+#define VFE_0_REG_UPDATE_line_n(n)		\
+			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
+
+#define VFE_0_DEMUX_CFG				0x424
+#define VFE_0_DEMUX_CFG_PERIOD			0x3
+#define VFE_0_DEMUX_GAIN_0			0x428
+#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
+#define VFE_0_DEMUX_GAIN_1			0x42c
+#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
+#define VFE_0_DEMUX_EVEN_CFG			0x438
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
+#define VFE_0_DEMUX_ODD_CFG			0x43c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
+
+#define VFE_0_SCALE_ENC_Y_CFG			0x75c
+#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x760
+#define VFE_0_SCALE_ENC_Y_H_PHASE		0x764
+#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x76c
+#define VFE_0_SCALE_ENC_Y_V_PHASE		0x770
+#define VFE_0_SCALE_ENC_CBCR_CFG		0x778
+#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x77c
+#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x780
+#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x790
+#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x794
+
+#define VFE_0_CROP_ENC_Y_WIDTH			0x854
+#define VFE_0_CROP_ENC_Y_HEIGHT			0x858
+#define VFE_0_CROP_ENC_CBCR_WIDTH		0x85c
+#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x860
+
+#define VFE_0_CLAMP_ENC_MAX_CFG			0x874
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
+#define VFE_0_CLAMP_ENC_MIN_CFG			0x878
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
+
+#define VFE_0_CGC_OVERRIDE_1			0x974
+#define VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(x)	(1 << (x))
+
+/* VFE reset timeout */
+#define VFE_RESET_TIMEOUT_MS 50
+/* VFE halt timeout */
+#define VFE_HALT_TIMEOUT_MS 100
+/* Max number of frame drop updates per frame */
+#define VFE_FRAME_DROP_UPDATES 5
+/* Frame drop value. NOTE: VAL + UPDATES should not exceed 31 */
+#define VFE_FRAME_DROP_VAL 20
+
+#define VFE_NEXT_SOF_MS 500
+
+#define CAMIF_TIMEOUT_SLEEP_US 1000
+#define CAMIF_TIMEOUT_ALL_US 1000000
+
+#define SCALER_RATIO_MAX 16
+
+static const struct {
+	u32 code;
+	u8 bpp;
+} vfe_formats[] = {
+	{
+		MEDIA_BUS_FMT_UYVY8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_VYUY8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_YUYV8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_YVYU8_2X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB8_1X8,
+		8,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB10_1X10,
+		10,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR12_1X12,
+		12,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG12_1X12,
+		12,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG12_1X12,
+		12,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB12_1X12,
+		12,
+	}
+};
+
+/*
+ * vfe_get_bpp - map media bus format to bits per pixel
+ * @code: media bus format code
+ *
+ * Return number of bits per pixel
+ */
+static u8 vfe_get_bpp(u32 code)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
+		if (code == vfe_formats[i].code)
+			return vfe_formats[i].bpp;
+
+	WARN(1, "Unknown format\n");
+
+	return vfe_formats[0].bpp;
+}
+
+static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
+}
+
+static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits | set_bits, vfe->base + reg);
+}
+
+static void vfe_global_reset(struct vfe_device *vfe)
+{
+	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
+			 VFE_0_GLOBAL_RESET_CMD_PM		|
+			 VFE_0_GLOBAL_RESET_CMD_TIMER		|
+			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS		|
+			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
+			 VFE_0_GLOBAL_RESET_CMD_CORE;
+
+	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
+}
+
+static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+}
+
+static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
+}
+
+#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
+
+static int vfe_word_per_line(uint32_t format, uint32_t pixel_per_line)
+{
+	int val = 0;
+
+	switch (format) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		val = CALC_WORD(pixel_per_line, 1, 8);
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_VYUY:
+		val = CALC_WORD(pixel_per_line, 2, 8);
+		break;
+	}
+
+	return val;
+}
+
+static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
+			     u16 *width, u16 *height, u16 *bytesperline)
+{
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		if (plane == 1)
+			*height /= 2;
+		break;
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		break;
+	}
+}
+
+static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
+			      struct v4l2_pix_format_mplane *pix,
+			      u8 plane, u32 enable)
+{
+	u32 reg;
+
+	if (enable) {
+		u16 width = 0, height = 0, bytesperline = 0, wpl;
+
+		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
+
+		wpl = vfe_word_per_line(pix->pixelformat, width);
+
+		reg = height - 1;
+		reg |= ((wpl + 1) / 2 - 1) << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+
+		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
+
+		reg = 0x3;
+		reg |= (height - 1) << 4;
+		reg |= wpl << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	} else {
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	}
+}
+
+static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base +
+			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+
+	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
+
+	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
+		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
+
+	writel_relaxed(reg,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+}
+
+static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
+					 u32 pattern)
+{
+	writel_relaxed(pattern,
+	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
+}
+
+static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm, u16 offset,
+			      u16 depth)
+{
+	u32 reg;
+
+	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
+		depth;
+	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
+}
+
+static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
+{
+	wmb();
+	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
+	wmb();
+}
+
+static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
+}
+
+static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
+}
+
+static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
+
+	return (reg >> wm) & 0x1;
+}
+
+static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
+{
+	if (enable)
+		writel_relaxed(0x10000009, vfe->base + VFE_0_BUS_CFG);
+	else
+		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
+}
+
+static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
+				      enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	reg |= VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
+		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
+{
+	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
+	       vfe->base +
+	       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
+}
+
+static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
+					   enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
+			     u8 enable)
+{
+	struct vfe_line *line = container_of(output, struct vfe_line, output);
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	unsigned int i;
+
+	for (i = 0; i < output->wm_num; i++) {
+		if (i == 0) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
+				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		} else if (i == 1) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
+				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+		} else {
+			/* On current devices output->wm_num is always <= 2 */
+			break;
+		}
+
+		if (output->wm_idx[i] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+	}
+}
+
+static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
+{
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
+		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
+
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
+		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
+}
+
+static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
+	wmb();
+	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
+	wmb();
+}
+
+static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
+				   enum vfe_line_id line_id, u8 enable)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
+		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
+		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	}
+}
+
+static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
+				    enum vfe_line_id line_id, u8 enable)
+{
+	struct vfe_output *output = &vfe->line[line_id].output;
+	unsigned int i;
+	u32 irq_en0;
+	u32 irq_en1;
+	u32 comp_mask = 0;
+
+	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
+	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
+	for (i = 0; i < output->wm_num; i++) {
+		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
+							output->wm_idx[i]);
+		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
+	}
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	}
+}
+
+static void vfe_enable_irq_common(struct vfe_device *vfe)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
+		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
+
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+}
+
+static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val, even_cfg, odd_cfg;
+
+	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
+
+	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
+
+	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
+		break;
+	}
+
+	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
+	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
+}
+
+static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
+{
+	if (input / output >= 16)
+		return 0;
+
+	if (input / output >= 8)
+		return 1;
+
+	if (input / output >= 4)
+		return 2;
+
+	return 3;
+}
+
+static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 input, output;
+	u8 interp_reso;
+	u32 phase_mult;
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width;
+	output = line->compose.width;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height;
+	output = line->compose.height;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width;
+	output = line->compose.width / 2;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height;
+	output = line->compose.height;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
+		output = line->compose.height / 2;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
+}
+
+static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 first, last;
+
+	first = line->crop.left;
+	last = line->crop.left + line->crop.width - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
+
+	first = line->crop.left / 2;
+	last = line->crop.left / 2 + line->crop.width / 2 - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
+		first = line->crop.top / 2;
+		last = line->crop.top / 2 + line->crop.height / 2 - 1;
+	}
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
+}
+
+static void vfe_set_clamp_cfg(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
+
+	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
+}
+
+/*
+ * vfe_reset - Trigger reset on VFE module and wait to complete
+ * @vfe: VFE device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_reset(struct vfe_device *vfe)
+{
+	unsigned long time;
+
+	reinit_completion(&vfe->reset_complete);
+
+	vfe_global_reset(vfe);
+
+	time = wait_for_completion_timeout(&vfe->reset_complete,
+		msecs_to_jiffies(VFE_RESET_TIMEOUT_MS));
+	if (!time) {
+		dev_err(to_device(vfe), "VFE reset timeout\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
+ * vfe_halt - Trigger halt on VFE module and wait to complete
+ * @vfe: VFE device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_halt(struct vfe_device *vfe)
+{
+	unsigned long time;
+
+	reinit_completion(&vfe->halt_complete);
+
+	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
+		       vfe->base + VFE_0_BUS_BDG_CMD);
+
+	time = wait_for_completion_timeout(&vfe->halt_complete,
+		msecs_to_jiffies(VFE_HALT_TIMEOUT_MS));
+	if (!time) {
+		dev_err(to_device(vfe), "VFE halt timeout\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void vfe_init_outputs(struct vfe_device *vfe)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfe->line); i++) {
+		struct vfe_output *output = &vfe->line[i].output;
+
+		output->state = VFE_OUTPUT_OFF;
+		output->buf[0] = NULL;
+		output->buf[1] = NULL;
+		INIT_LIST_HEAD(&output->pending_bufs);
+
+		output->wm_num = 1;
+		if (vfe->line[i].id == VFE_LINE_PIX)
+			output->wm_num = 2;
+	}
+}
+
+static void vfe_reset_output_maps(struct vfe_device *vfe)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfe->wm_output_map); i++)
+		vfe->wm_output_map[i] = VFE_LINE_NONE;
+}
+
+static void vfe_set_qos(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
+	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
+
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
+	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
+}
+
+static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	u32 val = VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(wm);
+
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_CGC_OVERRIDE_1, val);
+	else
+		vfe_reg_clr(vfe, VFE_0_CGC_OVERRIDE_1, val);
+
+	wmb();
+}
+
+static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
+{
+	u32 val = VFE_0_MODULE_CFG_DEMUX |
+		  VFE_0_MODULE_CFG_CHROMA_UPSAMPLE |
+		  VFE_0_MODULE_CFG_SCALE_ENC |
+		  VFE_0_MODULE_CFG_CROP_ENC;
+
+	if (enable)
+		writel_relaxed(val, vfe->base + VFE_0_MODULE_CFG);
+	else
+		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_CFG);
+}
+
+static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val;
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
+		break;
+	}
+
+	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2;
+	val |= line->fmt[MSM_VFE_PAD_SINK].height << 16;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG_0);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
+
+	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
+
+	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
+}
+
+static void vfe_set_camif_cmd(struct vfe_device *vfe, u32 cmd)
+{
+	writel_relaxed(VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS,
+		       vfe->base + VFE_0_CAMIF_CMD);
+
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+}
+
+static int vfe_camif_wait_for_stop(struct vfe_device *vfe)
+{
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
+				 val,
+				 (val & VFE_0_CAMIF_STATUS_HALT),
+				 CAMIF_TIMEOUT_SLEEP_US,
+				 CAMIF_TIMEOUT_ALL_US);
+	if (ret < 0)
+		dev_err(to_device(vfe), "%s: camif stop timeout\n", __func__);
+
+	return ret;
+}
+
+static void vfe_output_init_addrs(struct vfe_device *vfe,
+				  struct vfe_output *output, u8 sync)
+{
+	u32 ping_addr;
+	u32 pong_addr;
+	unsigned int i;
+
+	output->active_buf = 0;
+
+	for (i = 0; i < output->wm_num; i++) {
+		if (output->buf[0])
+			ping_addr = output->buf[0]->addr[i];
+		else
+			ping_addr = 0;
+
+		if (output->buf[1])
+			pong_addr = output->buf[1]->addr[i];
+		else
+			pong_addr = ping_addr;
+
+		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], ping_addr);
+		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], pong_addr);
+		if (sync)
+			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+	}
+}
+
+static void vfe_output_update_ping_addr(struct vfe_device *vfe,
+					struct vfe_output *output, u8 sync)
+{
+	u32 addr;
+	unsigned int i;
+
+	for (i = 0; i < output->wm_num; i++) {
+		if (output->buf[0])
+			addr = output->buf[0]->addr[i];
+		else
+			addr = 0;
+
+		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], addr);
+		if (sync)
+			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+	}
+}
+
+static void vfe_output_update_pong_addr(struct vfe_device *vfe,
+					struct vfe_output *output, u8 sync)
+{
+	u32 addr;
+	unsigned int i;
+
+	for (i = 0; i < output->wm_num; i++) {
+		if (output->buf[1])
+			addr = output->buf[1]->addr[i];
+		else
+			addr = 0;
+
+		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], addr);
+		if (sync)
+			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+	}
+
+}
+
+static int vfe_reserve_wm(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	int ret = -EBUSY;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfe->wm_output_map); i++) {
+		if (vfe->wm_output_map[i] == VFE_LINE_NONE) {
+			vfe->wm_output_map[i] = line_id;
+			ret = i;
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static int vfe_release_wm(struct vfe_device *vfe, u8 wm)
+{
+	if (wm >= ARRAY_SIZE(vfe->wm_output_map))
+		return -EINVAL;
+
+	vfe->wm_output_map[wm] = VFE_LINE_NONE;
+
+	return 0;
+}
+
+static void vfe_output_frame_drop(struct vfe_device *vfe,
+				  struct vfe_output *output,
+				  u32 drop_pattern)
+{
+	u8 drop_period;
+	unsigned int i;
+
+	/* We need to toggle update period to be valid on next frame */
+	output->drop_update_idx++;
+	output->drop_update_idx %= VFE_FRAME_DROP_UPDATES;
+	drop_period = VFE_FRAME_DROP_VAL + output->drop_update_idx;
+
+	for (i = 0; i < output->wm_num; i++) {
+		vfe_wm_set_framedrop_period(vfe, output->wm_idx[i],
+					    drop_period);
+		vfe_wm_set_framedrop_pattern(vfe, output->wm_idx[i],
+					     drop_pattern);
+	}
+	vfe_reg_update(vfe, container_of(output, struct vfe_line, output)->id);
+}
+
+static struct camss_buffer *vfe_buf_get_pending(struct vfe_output *output)
+{
+	struct camss_buffer *buffer = NULL;
+
+	if (!list_empty(&output->pending_bufs)) {
+		buffer = list_first_entry(&output->pending_bufs,
+					  struct camss_buffer,
+					  queue);
+		list_del(&buffer->queue);
+	}
+
+	return buffer;
+}
+
+/*
+ * vfe_buf_add_pending - Add output buffer to list of pending
+ * @output: VFE output
+ * @buffer: Video buffer
+ */
+static void vfe_buf_add_pending(struct vfe_output *output,
+				struct camss_buffer *buffer)
+{
+	INIT_LIST_HEAD(&buffer->queue);
+	list_add_tail(&buffer->queue, &output->pending_bufs);
+}
+
+/*
+ * vfe_buf_flush_pending - Flush all pending buffers.
+ * @output: VFE output
+ * @state: vb2 buffer state
+ */
+static void vfe_buf_flush_pending(struct vfe_output *output,
+				  enum vb2_buffer_state state)
+{
+	struct camss_buffer *buf;
+	struct camss_buffer *t;
+
+	list_for_each_entry_safe(buf, t, &output->pending_bufs, queue) {
+		vb2_buffer_done(&buf->vb.vb2_buf, state);
+		list_del(&buf->queue);
+	}
+}
+
+static void vfe_buf_update_wm_on_next(struct vfe_device *vfe,
+				      struct vfe_output *output)
+{
+	switch (output->state) {
+	case VFE_OUTPUT_CONTINUOUS:
+		vfe_output_frame_drop(vfe, output, 3);
+		break;
+	case VFE_OUTPUT_SINGLE:
+	default:
+		dev_err_ratelimited(to_device(vfe),
+				    "Next buf in wrong state! %d\n",
+				    output->state);
+		break;
+	}
+}
+
+static void vfe_buf_update_wm_on_last(struct vfe_device *vfe,
+				      struct vfe_output *output)
+{
+	switch (output->state) {
+	case VFE_OUTPUT_CONTINUOUS:
+		output->state = VFE_OUTPUT_SINGLE;
+		vfe_output_frame_drop(vfe, output, 1);
+		break;
+	case VFE_OUTPUT_SINGLE:
+		output->state = VFE_OUTPUT_STOPPING;
+		vfe_output_frame_drop(vfe, output, 0);
+		break;
+	default:
+		dev_err_ratelimited(to_device(vfe),
+				    "Last buff in wrong state! %d\n",
+				    output->state);
+		break;
+	}
+}
+
+static void vfe_buf_update_wm_on_new(struct vfe_device *vfe,
+				     struct vfe_output *output,
+				     struct camss_buffer *new_buf)
+{
+	int inactive_idx;
+
+	switch (output->state) {
+	case VFE_OUTPUT_SINGLE:
+		inactive_idx = !output->active_buf;
+
+		if (!output->buf[inactive_idx]) {
+			output->buf[inactive_idx] = new_buf;
+
+			if (inactive_idx)
+				vfe_output_update_pong_addr(vfe, output, 0);
+			else
+				vfe_output_update_ping_addr(vfe, output, 0);
+
+			vfe_output_frame_drop(vfe, output, 3);
+			output->state = VFE_OUTPUT_CONTINUOUS;
+		} else {
+			vfe_buf_add_pending(output, new_buf);
+			dev_err_ratelimited(to_device(vfe),
+					    "Inactive buffer is busy\n");
+		}
+		break;
+
+	case VFE_OUTPUT_IDLE:
+		if (!output->buf[0]) {
+			output->buf[0] = new_buf;
+
+			vfe_output_init_addrs(vfe, output, 1);
+
+			vfe_output_frame_drop(vfe, output, 1);
+			output->state = VFE_OUTPUT_SINGLE;
+		} else {
+			vfe_buf_add_pending(output, new_buf);
+			dev_err_ratelimited(to_device(vfe),
+					    "Output idle with buffer set!\n");
+		}
+		break;
+
+	case VFE_OUTPUT_CONTINUOUS:
+	default:
+		vfe_buf_add_pending(output, new_buf);
+		break;
+	}
+}
+
+static int vfe_get_output(struct vfe_line *line)
+{
+	struct vfe_device *vfe = to_vfe(line);
+	struct vfe_output *output;
+	unsigned long flags;
+	int i;
+	int wm_idx;
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	output = &line->output;
+	if (output->state != VFE_OUTPUT_OFF) {
+		dev_err(to_device(vfe), "Output is running\n");
+		goto error;
+	}
+	output->state = VFE_OUTPUT_RESERVED;
+
+	output->active_buf = 0;
+
+	for (i = 0; i < output->wm_num; i++) {
+		wm_idx = vfe_reserve_wm(vfe, line->id);
+		if (wm_idx < 0) {
+			dev_err(to_device(vfe), "Can not reserve wm\n");
+			goto error_get_wm;
+		}
+		output->wm_idx[i] = wm_idx;
+	}
+
+	output->drop_update_idx = 0;
+
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	return 0;
+
+error_get_wm:
+	for (i--; i >= 0; i--)
+		vfe_release_wm(vfe, output->wm_idx[i]);
+	output->state = VFE_OUTPUT_OFF;
+error:
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	return -EINVAL;
+}
+
+static int vfe_put_output(struct vfe_line *line)
+{
+	struct vfe_device *vfe = to_vfe(line);
+	struct vfe_output *output = &line->output;
+	unsigned long flags;
+	unsigned int i;
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	for (i = 0; i < output->wm_num; i++)
+		vfe_release_wm(vfe, output->wm_idx[i]);
+
+	output->state = VFE_OUTPUT_OFF;
+
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+	return 0;
+}
+
+static int vfe_enable_output(struct vfe_line *line)
+{
+	struct vfe_device *vfe = to_vfe(line);
+	struct vfe_output *output = &line->output;
+	unsigned long flags;
+	unsigned int i;
+	u16 ub_size;
+
+	switch (vfe->id) {
+	case 0:
+		ub_size = MSM_VFE_VFE0_UB_SIZE_RDI;
+		break;
+	case 1:
+		ub_size = MSM_VFE_VFE1_UB_SIZE_RDI;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line->id);
+
+	if (output->state != VFE_OUTPUT_RESERVED) {
+		dev_err(to_device(vfe), "Output is not in reserved state %d\n",
+			output->state);
+		spin_unlock_irqrestore(&vfe->output_lock, flags);
+		return -EINVAL;
+	}
+	output->state = VFE_OUTPUT_IDLE;
+
+	output->buf[0] = vfe_buf_get_pending(output);
+	output->buf[1] = vfe_buf_get_pending(output);
+
+	if (!output->buf[0] && output->buf[1]) {
+		output->buf[0] = output->buf[1];
+		output->buf[1] = NULL;
+	}
+
+	if (output->buf[0])
+		output->state = VFE_OUTPUT_SINGLE;
+
+	if (output->buf[1])
+		output->state = VFE_OUTPUT_CONTINUOUS;
+
+	switch (output->state) {
+	case VFE_OUTPUT_SINGLE:
+		vfe_output_frame_drop(vfe, output, 1);
+		break;
+	case VFE_OUTPUT_CONTINUOUS:
+		vfe_output_frame_drop(vfe, output, 3);
+		break;
+	default:
+		vfe_output_frame_drop(vfe, output, 0);
+		break;
+	}
+
+	output->sequence = 0;
+	output->wait_sof = 0;
+	output->wait_reg_update = 0;
+	reinit_completion(&output->sof);
+	reinit_completion(&output->reg_update);
+
+	vfe_output_init_addrs(vfe, output, 0);
+
+	if (line->id != VFE_LINE_PIX) {
+		vfe_set_cgc_override(vfe, output->wm_idx[0], 1);
+		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 1);
+		vfe_bus_connect_wm_to_rdi(vfe, output->wm_idx[0], line->id);
+		vfe_wm_set_subsample(vfe, output->wm_idx[0]);
+		vfe_set_rdi_cid(vfe, line->id, 0);
+		vfe_wm_set_ub_cfg(vfe, output->wm_idx[0],
+				  (ub_size + 1) * output->wm_idx[0], ub_size);
+		vfe_wm_frame_based(vfe, output->wm_idx[0], 1);
+		vfe_wm_enable(vfe, output->wm_idx[0], 1);
+		vfe_bus_reload_wm(vfe, output->wm_idx[0]);
+	} else {
+		ub_size /= output->wm_num;
+		for (i = 0; i < output->wm_num; i++) {
+			vfe_set_cgc_override(vfe, output->wm_idx[i], 1);
+			vfe_wm_set_subsample(vfe, output->wm_idx[i]);
+			vfe_wm_set_ub_cfg(vfe, output->wm_idx[i],
+					  (ub_size + 1) * output->wm_idx[i],
+					  ub_size);
+			vfe_wm_line_based(vfe, output->wm_idx[i],
+					&line->video_out.active_fmt.fmt.pix_mp,
+					i, 1);
+			vfe_wm_enable(vfe, output->wm_idx[i], 1);
+			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+		}
+		vfe_enable_irq_pix_line(vfe, 0, line->id, 1);
+		vfe_set_module_cfg(vfe, 1);
+		vfe_set_camif_cfg(vfe, line);
+		vfe_set_xbar_cfg(vfe, output, 1);
+		vfe_set_demux_cfg(vfe, line);
+		vfe_set_scale_cfg(vfe, line);
+		vfe_set_crop_cfg(vfe, line);
+		vfe_set_clamp_cfg(vfe);
+		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY);
+	}
+
+	vfe_reg_update(vfe, line->id);
+
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	return 0;
+}
+
+static int vfe_disable_output(struct vfe_line *line)
+{
+	struct vfe_device *vfe = to_vfe(line);
+	struct vfe_output *output = &line->output;
+	unsigned long flags;
+	unsigned long time;
+	unsigned int i;
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	output->wait_sof = 1;
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	time = wait_for_completion_timeout(&output->sof,
+					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
+	if (!time)
+		dev_err(to_device(vfe), "VFE sof timeout\n");
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+	for (i = 0; i < output->wm_num; i++)
+		vfe_wm_enable(vfe, output->wm_idx[i], 0);
+
+	vfe_reg_update(vfe, line->id);
+	output->wait_reg_update = 1;
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	time = wait_for_completion_timeout(&output->reg_update,
+					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
+	if (!time)
+		dev_err(to_device(vfe), "VFE reg update timeout\n");
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	if (line->id != VFE_LINE_PIX) {
+		vfe_wm_frame_based(vfe, output->wm_idx[0], 0);
+		vfe_bus_disconnect_wm_from_rdi(vfe, output->wm_idx[0], line->id);
+		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 0);
+		vfe_set_cgc_override(vfe, output->wm_idx[0], 0);
+		spin_unlock_irqrestore(&vfe->output_lock, flags);
+	} else {
+		for (i = 0; i < output->wm_num; i++) {
+			vfe_wm_line_based(vfe, output->wm_idx[i], NULL, i, 0);
+			vfe_set_cgc_override(vfe, output->wm_idx[i], 0);
+		}
+
+		vfe_enable_irq_pix_line(vfe, 0, line->id, 0);
+		vfe_set_module_cfg(vfe, 0);
+		vfe_set_xbar_cfg(vfe, output, 0);
+
+		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY);
+		spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+		vfe_camif_wait_for_stop(vfe);
+	}
+
+	return 0;
+}
+
+/*
+ * vfe_enable - Enable streaming on VFE line
+ * @line: VFE line
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_enable(struct vfe_line *line)
+{
+	struct vfe_device *vfe = to_vfe(line);
+	int ret;
+
+	mutex_lock(&vfe->stream_lock);
+
+	if (!vfe->stream_count) {
+		vfe_enable_irq_common(vfe);
+
+		vfe_bus_enable_wr_if(vfe, 1);
+
+		vfe_set_qos(vfe);
+	}
+
+	vfe->stream_count++;
+
+	mutex_unlock(&vfe->stream_lock);
+
+	ret = vfe_get_output(line);
+	if (ret < 0)
+		goto error_get_output;
+
+	ret = vfe_enable_output(line);
+	if (ret < 0)
+		goto error_enable_output;
+
+	vfe->was_streaming = 1;
+
+	return 0;
+
+
+error_enable_output:
+	vfe_put_output(line);
+
+error_get_output:
+	mutex_lock(&vfe->stream_lock);
+
+	if (vfe->stream_count == 1)
+		vfe_bus_enable_wr_if(vfe, 0);
+
+	vfe->stream_count--;
+
+	mutex_unlock(&vfe->stream_lock);
+
+	return ret;
+}
+
+/*
+ * vfe_disable - Disable streaming on VFE line
+ * @line: VFE line
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_disable(struct vfe_line *line)
+{
+	struct vfe_device *vfe = to_vfe(line);
+
+	vfe_disable_output(line);
+
+	vfe_put_output(line);
+
+	mutex_lock(&vfe->stream_lock);
+
+	if (vfe->stream_count == 1)
+		vfe_bus_enable_wr_if(vfe, 0);
+
+	vfe->stream_count--;
+
+	mutex_unlock(&vfe->stream_lock);
+
+	return 0;
+}
+
+/*
+ * vfe_isr_sof - Process start of frame interrupt
+ * @vfe: VFE Device
+ * @line_id: VFE line
+ */
+static void vfe_isr_sof(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	struct vfe_output *output;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+	output = &vfe->line[line_id].output;
+	if (output->wait_sof) {
+		output->wait_sof = 0;
+		complete(&output->sof);
+	}
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+}
+
+/*
+ * vfe_isr_reg_update - Process reg update interrupt
+ * @vfe: VFE Device
+ * @line_id: VFE line
+ */
+static void vfe_isr_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	struct vfe_output *output;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
+
+	output = &vfe->line[line_id].output;
+
+	if (output->wait_reg_update) {
+		output->wait_reg_update = 0;
+		complete(&output->reg_update);
+		spin_unlock_irqrestore(&vfe->output_lock, flags);
+		return;
+	}
+
+	if (output->state == VFE_OUTPUT_STOPPING) {
+		/* Release last buffer when hw is idle */
+		if (output->last_buffer) {
+			vb2_buffer_done(&output->last_buffer->vb.vb2_buf,
+					VB2_BUF_STATE_DONE);
+			output->last_buffer = NULL;
+		}
+		output->state = VFE_OUTPUT_IDLE;
+
+		/* Buffers received in stopping state are queued in */
+		/* dma pending queue, start next capture here */
+
+		output->buf[0] = vfe_buf_get_pending(output);
+		output->buf[1] = vfe_buf_get_pending(output);
+
+		if (!output->buf[0] && output->buf[1]) {
+			output->buf[0] = output->buf[1];
+			output->buf[1] = NULL;
+		}
+
+		if (output->buf[0])
+			output->state = VFE_OUTPUT_SINGLE;
+
+		if (output->buf[1])
+			output->state = VFE_OUTPUT_CONTINUOUS;
+
+		switch (output->state) {
+		case VFE_OUTPUT_SINGLE:
+			vfe_output_frame_drop(vfe, output, 2);
+			break;
+		case VFE_OUTPUT_CONTINUOUS:
+			vfe_output_frame_drop(vfe, output, 3);
+			break;
+		default:
+			vfe_output_frame_drop(vfe, output, 0);
+			break;
+		}
+
+		vfe_output_init_addrs(vfe, output, 1);
+	}
+
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+}
+
+/*
+ * vfe_isr_wm_done - Process write master done interrupt
+ * @vfe: VFE Device
+ * @wm: Write master id
+ */
+static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
+{
+	struct camss_buffer *ready_buf;
+	struct vfe_output *output;
+	dma_addr_t *new_addr;
+	unsigned long flags;
+	u32 active_index;
+	u64 ts = ktime_get_ns();
+	unsigned int i;
+
+	active_index = vfe_wm_get_ping_pong_status(vfe, wm);
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	if (vfe->wm_output_map[wm] == VFE_LINE_NONE) {
+		dev_err_ratelimited(to_device(vfe),
+				    "Received wm done for unmapped index\n");
+		goto out_unlock;
+	}
+	output = &vfe->line[vfe->wm_output_map[wm]].output;
+
+	if (output->active_buf == active_index) {
+		dev_err_ratelimited(to_device(vfe),
+				    "Active buffer mismatch!\n");
+		goto out_unlock;
+	}
+	output->active_buf = active_index;
+
+	ready_buf = output->buf[!active_index];
+	if (!ready_buf) {
+		dev_err_ratelimited(to_device(vfe),
+				    "Missing ready buf %d %d!\n",
+				    !active_index, output->state);
+		goto out_unlock;
+	}
+
+	ready_buf->vb.vb2_buf.timestamp = ts;
+	ready_buf->vb.sequence = output->sequence++;
+
+	/* Get next buffer */
+	output->buf[!active_index] = vfe_buf_get_pending(output);
+	if (!output->buf[!active_index]) {
+		/* No next buffer - set same address */
+		new_addr = ready_buf->addr;
+		vfe_buf_update_wm_on_last(vfe, output);
+	} else {
+		new_addr = output->buf[!active_index]->addr;
+		vfe_buf_update_wm_on_next(vfe, output);
+	}
+
+	if (active_index)
+		for (i = 0; i < output->wm_num; i++)
+			vfe_wm_set_ping_addr(vfe, output->wm_idx[i],
+					     new_addr[i]);
+	else
+		for (i = 0; i < output->wm_num; i++)
+			vfe_wm_set_pong_addr(vfe, output->wm_idx[i],
+					     new_addr[i]);
+
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	if (output->state == VFE_OUTPUT_STOPPING)
+		output->last_buffer = ready_buf;
+	else
+		vb2_buffer_done(&ready_buf->vb.vb2_buf, VB2_BUF_STATE_DONE);
+
+	return;
+
+out_unlock:
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+}
+
+/*
+ * vfe_isr_wm_done - Process composite image done interrupt
+ * @vfe: VFE Device
+ * @comp: Composite image id
+ */
+static void vfe_isr_comp_done(struct vfe_device *vfe, u8 comp)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfe->wm_output_map); i++)
+		if (vfe->wm_output_map[i] == VFE_LINE_PIX) {
+			vfe_isr_wm_done(vfe, i);
+			break;
+		}
+}
+
+/*
+ * vfe_isr - ISPIF module interrupt handler
+ * @irq: Interrupt line
+ * @dev: VFE device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t vfe_isr(int irq, void *dev)
+{
+	struct vfe_device *vfe = dev;
+	u32 value0, value1;
+	u32 violation;
+	int i, j;
+
+	value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
+	value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
+
+	writel_relaxed(value0, vfe->base + VFE_0_IRQ_CLEAR_0);
+	writel_relaxed(value1, vfe->base + VFE_0_IRQ_CLEAR_1);
+
+	wmb();
+	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
+		complete(&vfe->reset_complete);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION) {
+		violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
+		dev_err_ratelimited(to_device(vfe),
+				    "VFE: violation = 0x%08x\n", violation);
+	}
+
+	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK) {
+		complete(&vfe->halt_complete);
+		writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
+	}
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
+			vfe_isr_reg_update(vfe, i);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
+		vfe_isr_sof(vfe, VFE_LINE_PIX);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
+		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
+			vfe_isr_sof(vfe, i);
+
+	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
+			vfe_isr_comp_done(vfe, i);
+			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
+				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
+					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
+		}
+
+	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
+			vfe_isr_wm_done(vfe, i);
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * vfe_set_clock_rates - Calculate and set clock rates on VFE module
+ * @vfe: VFE device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_set_clock_rates(struct vfe_device *vfe)
+{
+	struct device *dev = to_device(vfe);
+	u32 pixel_clock[MSM_VFE_LINE_NUM];
+	int i, j;
+	int ret;
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
+		ret = camss_get_pixel_clock(&vfe->line[i].subdev.entity,
+					    &pixel_clock[i]);
+		if (ret)
+			pixel_clock[i] = 0;
+	}
+
+	for (i = 0; i < vfe->nclocks; i++) {
+		struct camss_clock *clock = &vfe->clock[i];
+
+		if (!strcmp(clock->name, "camss_vfe_vfe")) {
+			u64 min_rate = 0;
+			long rate;
+
+			for (j = VFE_LINE_RDI0; j <= VFE_LINE_PIX; j++) {
+				u32 tmp;
+				u8 bpp;
+
+				if (j == VFE_LINE_PIX) {
+					tmp = pixel_clock[j];
+				} else {
+					bpp = vfe_get_bpp(vfe->line[j].
+						fmt[MSM_VFE_PAD_SINK].code);
+					tmp = pixel_clock[j] * bpp / 64;
+				}
+
+				if (min_rate < tmp)
+					min_rate = tmp;
+			}
+
+			camss_add_clock_margin(&min_rate);
+
+			for (j = 0; j < clock->nfreqs; j++)
+				if (min_rate < clock->freq[j])
+					break;
+
+			if (j == clock->nfreqs) {
+				dev_err(dev,
+					"Pixel clock is too high for VFE");
+				return -EINVAL;
+			}
+
+			/* if sensor pixel clock is not available */
+			/* set highest possible VFE clock rate */
+			if (min_rate == 0)
+				j = clock->nfreqs - 1;
+
+			rate = clk_round_rate(clock->clk, clock->freq[j]);
+			if (rate < 0) {
+				dev_err(dev, "clk round rate failed: %ld\n",
+					rate);
+				return -EINVAL;
+			}
+
+			ret = clk_set_rate(clock->clk, rate);
+			if (ret < 0) {
+				dev_err(dev, "clk set rate failed: %d\n", ret);
+				return ret;
+			}
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * vfe_check_clock_rates - Check current clock rates on VFE module
+ * @vfe: VFE device
+ *
+ * Return 0 if current clock rates are suitable for a new pipeline
+ * or a negative error code otherwise
+ */
+static int vfe_check_clock_rates(struct vfe_device *vfe)
+{
+	u32 pixel_clock[MSM_VFE_LINE_NUM];
+	int i, j;
+	int ret;
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
+		ret = camss_get_pixel_clock(&vfe->line[i].subdev.entity,
+					    &pixel_clock[i]);
+		if (ret)
+			pixel_clock[i] = 0;
+	}
+
+	for (i = 0; i < vfe->nclocks; i++) {
+		struct camss_clock *clock = &vfe->clock[i];
+
+		if (!strcmp(clock->name, "camss_vfe_vfe")) {
+			u64 min_rate = 0;
+			unsigned long rate;
+
+			for (j = VFE_LINE_RDI0; j <= VFE_LINE_PIX; j++) {
+				u32 tmp;
+				u8 bpp;
+
+				if (j == VFE_LINE_PIX) {
+					tmp = pixel_clock[j];
+				} else {
+					bpp = vfe_get_bpp(vfe->line[j].
+						fmt[MSM_VFE_PAD_SINK].code);
+					tmp = pixel_clock[j] * bpp / 64;
+				}
+
+				if (min_rate < tmp)
+					min_rate = tmp;
+			}
+
+			camss_add_clock_margin(&min_rate);
+
+			rate = clk_get_rate(clock->clk);
+			if (rate < min_rate)
+				return -EBUSY;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * vfe_get - Power up and reset VFE module
+ * @vfe: VFE Device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_get(struct vfe_device *vfe)
+{
+	int ret;
+
+	mutex_lock(&vfe->power_lock);
+
+	if (vfe->power_count == 0) {
+		ret = vfe_set_clock_rates(vfe);
+		if (ret < 0)
+			goto error_clocks;
+
+		ret = camss_enable_clocks(vfe->nclocks, vfe->clock,
+					  to_device(vfe));
+		if (ret < 0)
+			goto error_clocks;
+
+		ret = vfe_reset(vfe);
+		if (ret < 0)
+			goto error_reset;
+
+		vfe_reset_output_maps(vfe);
+
+		vfe_init_outputs(vfe);
+	} else {
+		ret = vfe_check_clock_rates(vfe);
+		if (ret < 0)
+			goto error_clocks;
+	}
+	vfe->power_count++;
+
+	mutex_unlock(&vfe->power_lock);
+
+	return 0;
+
+error_reset:
+	camss_disable_clocks(vfe->nclocks, vfe->clock);
+
+error_clocks:
+	mutex_unlock(&vfe->power_lock);
+
+	return ret;
+}
+
+/*
+ * vfe_put - Power down VFE module
+ * @vfe: VFE Device
+ */
+static void vfe_put(struct vfe_device *vfe)
+{
+	mutex_lock(&vfe->power_lock);
+
+	if (vfe->power_count == 0) {
+		dev_err(to_device(vfe), "vfe power off on power_count == 0\n");
+		goto exit;
+	} else if (vfe->power_count == 1) {
+		if (vfe->was_streaming) {
+			vfe->was_streaming = 0;
+			vfe_halt(vfe);
+		}
+		camss_disable_clocks(vfe->nclocks, vfe->clock);
+	}
+
+	vfe->power_count--;
+
+exit:
+	mutex_unlock(&vfe->power_lock);
+}
+
+/*
+ * vfe_video_pad_to_line - Get pointer to VFE line by media pad
+ * @pad: Media pad
+ *
+ * Return pointer to vfe line structure
+ */
+static struct vfe_line *vfe_video_pad_to_line(struct media_pad *pad)
+{
+	struct media_pad *vfe_pad;
+	struct v4l2_subdev *subdev;
+
+	vfe_pad = media_entity_remote_pad(pad);
+	if (vfe_pad == NULL)
+		return NULL;
+
+	subdev = media_entity_to_v4l2_subdev(vfe_pad->entity);
+
+	return container_of(subdev, struct vfe_line, subdev);
+}
+
+/*
+ * vfe_queue_buffer - Add empty buffer
+ * @vid: Video device structure
+ * @buf: Buffer to be enqueued
+ *
+ * Add an empty buffer - depending on the current number of buffers it will be
+ * put in pending buffer queue or directly given to the hardware to be filled.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_queue_buffer(struct camss_video *vid,
+			    struct camss_buffer *buf)
+{
+	struct vfe_device *vfe = &vid->camss->vfe;
+	struct vfe_line *line;
+	struct vfe_output *output;
+	unsigned long flags;
+
+	line = vfe_video_pad_to_line(&vid->pad);
+	if (!line) {
+		dev_err(to_device(vfe), "Can not queue buffer\n");
+		return -1;
+	}
+	output = &line->output;
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	vfe_buf_update_wm_on_new(vfe, output, buf);
+
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	return 0;
+}
+
+/*
+ * vfe_flush_buffers - Return all vb2 buffers
+ * @vid: Video device structure
+ * @state: vb2 buffer state of the returned buffers
+ *
+ * Return all buffers to vb2. This includes queued pending buffers (still
+ * unused) and any buffers given to the hardware but again still not used.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_flush_buffers(struct camss_video *vid,
+			     enum vb2_buffer_state state)
+{
+	struct vfe_device *vfe = &vid->camss->vfe;
+	struct vfe_line *line;
+	struct vfe_output *output;
+	unsigned long flags;
+
+	line = vfe_video_pad_to_line(&vid->pad);
+	if (!line) {
+		dev_err(to_device(vfe),	"Can not flush buffers\n");
+		return -1;
+	}
+	output = &line->output;
+
+	spin_lock_irqsave(&vfe->output_lock, flags);
+
+	vfe_buf_flush_pending(output, state);
+
+	if (output->buf[0])
+		vb2_buffer_done(&output->buf[0]->vb.vb2_buf, state);
+
+	if (output->buf[1])
+		vb2_buffer_done(&output->buf[1]->vb.vb2_buf, state);
+
+	if (output->last_buffer) {
+		vb2_buffer_done(&output->last_buffer->vb.vb2_buf, state);
+		output->last_buffer = NULL;
+	}
+
+	spin_unlock_irqrestore(&vfe->output_lock, flags);
+
+	return 0;
+}
+
+/*
+ * vfe_set_power - Power on/off VFE module
+ * @sd: VFE V4L2 subdevice
+ * @on: Requested power state
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_set_power(struct v4l2_subdev *sd, int on)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct vfe_device *vfe = to_vfe(line);
+	int ret;
+
+	if (on) {
+		u32 hw_version;
+
+		ret = vfe_get(vfe);
+		if (ret < 0)
+			return ret;
+
+		hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
+		dev_dbg(to_device(vfe),
+			"VFE HW Version = 0x%08x\n", hw_version);
+	} else {
+		vfe_put(vfe);
+	}
+
+	return 0;
+}
+
+/*
+ * vfe_set_stream - Enable/disable streaming on VFE module
+ * @sd: VFE V4L2 subdevice
+ * @enable: Requested streaming state
+ *
+ * Main configuration of VFE module is triggered here.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_set_stream(struct v4l2_subdev *sd, int enable)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct vfe_device *vfe = to_vfe(line);
+	int ret;
+
+	if (enable) {
+		ret = vfe_enable(line);
+		if (ret < 0)
+			dev_err(to_device(vfe),
+				"Failed to enable vfe outputs\n");
+	} else {
+		ret = vfe_disable(line);
+		if (ret < 0)
+			dev_err(to_device(vfe),
+				"Failed to disable vfe outputs\n");
+	}
+
+	return ret;
+}
+
+/*
+ * __vfe_get_format - Get pointer to format structure
+ * @line: VFE line
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad from which format is requested
+ * @which: TRY or ACTIVE format
+ *
+ * Return pointer to TRY or ACTIVE format structure
+ */
+static struct v4l2_mbus_framefmt *
+__vfe_get_format(struct vfe_line *line,
+		 struct v4l2_subdev_pad_config *cfg,
+		 unsigned int pad,
+		 enum v4l2_subdev_format_whence which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_format(&line->subdev, cfg, pad);
+
+	return &line->fmt[pad];
+}
+
+/*
+ * __vfe_get_compose - Get pointer to compose selection structure
+ * @line: VFE line
+ * @cfg: V4L2 subdev pad configuration
+ * @which: TRY or ACTIVE format
+ *
+ * Return pointer to TRY or ACTIVE compose rectangle structure
+ */
+static struct v4l2_rect *
+__vfe_get_compose(struct vfe_line *line,
+		  struct v4l2_subdev_pad_config *cfg,
+		  enum v4l2_subdev_format_whence which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_compose(&line->subdev, cfg,
+						   MSM_VFE_PAD_SINK);
+
+	return &line->compose;
+}
+
+/*
+ * __vfe_get_crop - Get pointer to crop selection structure
+ * @line: VFE line
+ * @cfg: V4L2 subdev pad configuration
+ * @which: TRY or ACTIVE format
+ *
+ * Return pointer to TRY or ACTIVE crop rectangle structure
+ */
+static struct v4l2_rect *
+__vfe_get_crop(struct vfe_line *line,
+	       struct v4l2_subdev_pad_config *cfg,
+	       enum v4l2_subdev_format_whence which)
+{
+	if (which == V4L2_SUBDEV_FORMAT_TRY)
+		return v4l2_subdev_get_try_crop(&line->subdev, cfg,
+						MSM_VFE_PAD_SRC);
+
+	return &line->crop;
+}
+
+/*
+ * vfe_try_format - Handle try format by pad subdev method
+ * @line: VFE line
+ * @cfg: V4L2 subdev pad configuration
+ * @pad: pad on which format is requested
+ * @fmt: pointer to v4l2 format structure
+ * @which: wanted subdev format
+ */
+static void vfe_try_format(struct vfe_line *line,
+			   struct v4l2_subdev_pad_config *cfg,
+			   unsigned int pad,
+			   struct v4l2_mbus_framefmt *fmt,
+			   enum v4l2_subdev_format_whence which)
+{
+	unsigned int i;
+	u32 code;
+
+	switch (pad) {
+	case MSM_VFE_PAD_SINK:
+		/* Set format on sink pad */
+
+		for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
+			if (fmt->code == vfe_formats[i].code)
+				break;
+
+		/* If not found, use UYVY as default */
+		if (i >= ARRAY_SIZE(vfe_formats))
+			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
+
+		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
+		fmt->height = clamp_t(u32, fmt->height, 1, 8191);
+
+		fmt->field = V4L2_FIELD_NONE;
+		fmt->colorspace = V4L2_COLORSPACE_SRGB;
+
+		break;
+
+	case MSM_VFE_PAD_SRC:
+		/* Set and return a format same as sink pad */
+
+		code = fmt->code;
+
+		*fmt = *__vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
+					 which);
+
+		if (line->id == VFE_LINE_PIX) {
+			struct v4l2_rect *rect;
+
+			rect = __vfe_get_crop(line, cfg, which);
+
+			fmt->width = rect->width;
+			fmt->height = rect->height;
+
+			switch (fmt->code) {
+			case MEDIA_BUS_FMT_YUYV8_2X8:
+				if (code == MEDIA_BUS_FMT_YUYV8_1_5X8)
+					fmt->code = MEDIA_BUS_FMT_YUYV8_1_5X8;
+				else
+					fmt->code = MEDIA_BUS_FMT_YUYV8_2X8;
+				break;
+			case MEDIA_BUS_FMT_YVYU8_2X8:
+				if (code == MEDIA_BUS_FMT_YVYU8_1_5X8)
+					fmt->code = MEDIA_BUS_FMT_YVYU8_1_5X8;
+				else
+					fmt->code = MEDIA_BUS_FMT_YVYU8_2X8;
+				break;
+			case MEDIA_BUS_FMT_UYVY8_2X8:
+			default:
+				if (code == MEDIA_BUS_FMT_UYVY8_1_5X8)
+					fmt->code = MEDIA_BUS_FMT_UYVY8_1_5X8;
+				else
+					fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
+				break;
+			case MEDIA_BUS_FMT_VYUY8_2X8:
+				if (code == MEDIA_BUS_FMT_VYUY8_1_5X8)
+					fmt->code = MEDIA_BUS_FMT_VYUY8_1_5X8;
+				else
+					fmt->code = MEDIA_BUS_FMT_VYUY8_2X8;
+				break;
+			}
+		}
+
+		break;
+	}
+
+	fmt->colorspace = V4L2_COLORSPACE_SRGB;
+}
+
+/*
+ * vfe_try_compose - Handle try compose selection by pad subdev method
+ * @line: VFE line
+ * @cfg: V4L2 subdev pad configuration
+ * @rect: pointer to v4l2 rect structure
+ * @which: wanted subdev format
+ */
+static void vfe_try_compose(struct vfe_line *line,
+			    struct v4l2_subdev_pad_config *cfg,
+			    struct v4l2_rect *rect,
+			    enum v4l2_subdev_format_whence which)
+{
+	struct v4l2_mbus_framefmt *fmt;
+
+	fmt = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK, which);
+
+	if (rect->width > fmt->width)
+		rect->width = fmt->width;
+
+	if (rect->height > fmt->height)
+		rect->height = fmt->height;
+
+	if (fmt->width > rect->width * SCALER_RATIO_MAX)
+		rect->width = (fmt->width + SCALER_RATIO_MAX - 1) /
+							SCALER_RATIO_MAX;
+
+	rect->width &= ~0x1;
+
+	if (fmt->height > rect->height * SCALER_RATIO_MAX)
+		rect->height = (fmt->height + SCALER_RATIO_MAX - 1) /
+							SCALER_RATIO_MAX;
+
+	if (rect->width < 16)
+		rect->width = 16;
+
+	if (rect->height < 4)
+		rect->height = 4;
+}
+
+/*
+ * vfe_try_crop - Handle try crop selection by pad subdev method
+ * @line: VFE line
+ * @cfg: V4L2 subdev pad configuration
+ * @rect: pointer to v4l2 rect structure
+ * @which: wanted subdev format
+ */
+static void vfe_try_crop(struct vfe_line *line,
+			 struct v4l2_subdev_pad_config *cfg,
+			 struct v4l2_rect *rect,
+			 enum v4l2_subdev_format_whence which)
+{
+	struct v4l2_rect *compose;
+
+	compose = __vfe_get_compose(line, cfg, which);
+
+	if (rect->width > compose->width)
+		rect->width = compose->width;
+
+	if (rect->width + rect->left > compose->width)
+		rect->left = compose->width - rect->width;
+
+	if (rect->height > compose->height)
+		rect->height = compose->height;
+
+	if (rect->height + rect->top > compose->height)
+		rect->top = compose->height - rect->height;
+
+	/* wm in line based mode writes multiple of 16 horizontally */
+	rect->left += (rect->width & 0xf) >> 1;
+	rect->width &= ~0xf;
+
+	if (rect->width < 16) {
+		rect->left = 0;
+		rect->width = 16;
+	}
+
+	if (rect->height < 4) {
+		rect->top = 0;
+		rect->height = 4;
+	}
+}
+
+/*
+ * vfe_enum_mbus_code - Handle pixel format enumeration
+ * @sd: VFE V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @code: pointer to v4l2_subdev_mbus_code_enum structure
+ *
+ * return -EINVAL or zero on success
+ */
+static int vfe_enum_mbus_code(struct v4l2_subdev *sd,
+			      struct v4l2_subdev_pad_config *cfg,
+			      struct v4l2_subdev_mbus_code_enum *code)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	if (code->pad == MSM_VFE_PAD_SINK) {
+		if (code->index >= ARRAY_SIZE(vfe_formats))
+			return -EINVAL;
+
+		code->code = vfe_formats[code->index].code;
+	} else {
+		if (code->index > 0)
+			return -EINVAL;
+
+		format = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
+					  code->which);
+
+		code->code = format->code;
+	}
+
+	return 0;
+}
+
+/*
+ * vfe_enum_frame_size - Handle frame size enumeration
+ * @sd: VFE V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fse: pointer to v4l2_subdev_frame_size_enum structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int vfe_enum_frame_size(struct v4l2_subdev *sd,
+			       struct v4l2_subdev_pad_config *cfg,
+			       struct v4l2_subdev_frame_size_enum *fse)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt format;
+
+	if (fse->index != 0)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = 1;
+	format.height = 1;
+	vfe_try_format(line, cfg, fse->pad, &format, fse->which);
+	fse->min_width = format.width;
+	fse->min_height = format.height;
+
+	if (format.code != fse->code)
+		return -EINVAL;
+
+	format.code = fse->code;
+	format.width = -1;
+	format.height = -1;
+	vfe_try_format(line, cfg, fse->pad, &format, fse->which);
+	fse->max_width = format.width;
+	fse->max_height = format.height;
+
+	return 0;
+}
+
+/*
+ * vfe_get_format - Handle get format by pads subdev method
+ * @sd: VFE V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int vfe_get_format(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *fmt)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __vfe_get_format(line, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	fmt->format = *format;
+
+	return 0;
+}
+
+static int vfe_set_selection(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_pad_config *cfg,
+			     struct v4l2_subdev_selection *sel);
+
+/*
+ * vfe_set_format - Handle set format by pads subdev method
+ * @sd: VFE V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @fmt: pointer to v4l2 subdev format structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int vfe_set_format(struct v4l2_subdev *sd,
+			  struct v4l2_subdev_pad_config *cfg,
+			  struct v4l2_subdev_format *fmt)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_mbus_framefmt *format;
+
+	format = __vfe_get_format(line, cfg, fmt->pad, fmt->which);
+	if (format == NULL)
+		return -EINVAL;
+
+	vfe_try_format(line, cfg, fmt->pad, &fmt->format, fmt->which);
+	*format = fmt->format;
+
+	if (fmt->pad == MSM_VFE_PAD_SINK) {
+		struct v4l2_subdev_selection sel = { 0 };
+		int ret;
+
+		/* Propagate the format from sink to source */
+		format = __vfe_get_format(line, cfg, MSM_VFE_PAD_SRC,
+					  fmt->which);
+
+		*format = fmt->format;
+		vfe_try_format(line, cfg, MSM_VFE_PAD_SRC, format,
+			       fmt->which);
+
+		if (line->id != VFE_LINE_PIX)
+			return 0;
+
+		/* Reset sink pad compose selection */
+		sel.which = fmt->which;
+		sel.pad = MSM_VFE_PAD_SINK;
+		sel.target = V4L2_SEL_TGT_COMPOSE;
+		sel.r.width = fmt->format.width;
+		sel.r.height = fmt->format.height;
+		ret = vfe_set_selection(sd, cfg, &sel);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * vfe_get_selection - Handle get selection by pads subdev method
+ * @sd: VFE V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @sel: pointer to v4l2 subdev selection structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int vfe_get_selection(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_pad_config *cfg,
+			     struct v4l2_subdev_selection *sel)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_subdev_format fmt = { 0 };
+	struct v4l2_rect *rect;
+	int ret;
+
+	if (line->id != VFE_LINE_PIX)
+		return -EINVAL;
+
+	if (sel->pad == MSM_VFE_PAD_SINK)
+		switch (sel->target) {
+		case V4L2_SEL_TGT_COMPOSE_BOUNDS:
+			fmt.pad = sel->pad;
+			fmt.which = sel->which;
+			ret = vfe_get_format(sd, cfg, &fmt);
+			if (ret < 0)
+				return ret;
+
+			sel->r.left = 0;
+			sel->r.top = 0;
+			sel->r.width = fmt.format.width;
+			sel->r.height = fmt.format.height;
+			break;
+		case V4L2_SEL_TGT_COMPOSE:
+			rect = __vfe_get_compose(line, cfg, sel->which);
+			if (rect == NULL)
+				return -EINVAL;
+
+			sel->r = *rect;
+			break;
+		default:
+			return -EINVAL;
+		}
+	else if (sel->pad == MSM_VFE_PAD_SRC)
+		switch (sel->target) {
+		case V4L2_SEL_TGT_CROP_BOUNDS:
+			rect = __vfe_get_compose(line, cfg, sel->which);
+			if (rect == NULL)
+				return -EINVAL;
+
+			sel->r.left = rect->left;
+			sel->r.top = rect->top;
+			sel->r.width = rect->width;
+			sel->r.height = rect->height;
+			break;
+		case V4L2_SEL_TGT_CROP:
+			rect = __vfe_get_crop(line, cfg, sel->which);
+			if (rect == NULL)
+				return -EINVAL;
+
+			sel->r = *rect;
+			break;
+		default:
+			return -EINVAL;
+		}
+
+	return 0;
+}
+
+/*
+ * vfe_set_selection - Handle set selection by pads subdev method
+ * @sd: VFE V4L2 subdevice
+ * @cfg: V4L2 subdev pad configuration
+ * @sel: pointer to v4l2 subdev selection structure
+ *
+ * Return -EINVAL or zero on success
+ */
+static int vfe_set_selection(struct v4l2_subdev *sd,
+			     struct v4l2_subdev_pad_config *cfg,
+			     struct v4l2_subdev_selection *sel)
+{
+	struct vfe_line *line = v4l2_get_subdevdata(sd);
+	struct v4l2_rect *rect;
+	int ret;
+
+	if (line->id != VFE_LINE_PIX)
+		return -EINVAL;
+
+	if (sel->target == V4L2_SEL_TGT_COMPOSE &&
+		sel->pad == MSM_VFE_PAD_SINK) {
+		struct v4l2_subdev_selection crop = { 0 };
+
+		rect = __vfe_get_compose(line, cfg, sel->which);
+		if (rect == NULL)
+			return -EINVAL;
+
+		vfe_try_compose(line, cfg, &sel->r, sel->which);
+		*rect = sel->r;
+
+		/* Reset source crop selection */
+		crop.which = sel->which;
+		crop.pad = MSM_VFE_PAD_SRC;
+		crop.target = V4L2_SEL_TGT_CROP;
+		crop.r = *rect;
+		ret = vfe_set_selection(sd, cfg, &crop);
+	} else if (sel->target == V4L2_SEL_TGT_CROP &&
+		sel->pad == MSM_VFE_PAD_SRC) {
+		struct v4l2_subdev_format fmt = { 0 };
+
+		rect = __vfe_get_crop(line, cfg, sel->which);
+		if (rect == NULL)
+			return -EINVAL;
+
+		vfe_try_crop(line, cfg, &sel->r, sel->which);
+		*rect = sel->r;
+
+		/* Reset source pad format width and height */
+		fmt.which = sel->which;
+		fmt.pad = MSM_VFE_PAD_SRC;
+		ret = vfe_get_format(sd, cfg, &fmt);
+		if (ret < 0)
+			return ret;
+
+		fmt.format.width = rect->width;
+		fmt.format.height = rect->height;
+		ret = vfe_set_format(sd, cfg, &fmt);
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret;
+}
+
+/*
+ * vfe_init_formats - Initialize formats on all pads
+ * @sd: VFE V4L2 subdevice
+ * @fh: V4L2 subdev file handle
+ *
+ * Initialize all pad formats with default values.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int vfe_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
+{
+	struct v4l2_subdev_format format = {
+		.pad = MSM_VFE_PAD_SINK,
+		.which = fh ? V4L2_SUBDEV_FORMAT_TRY :
+			      V4L2_SUBDEV_FORMAT_ACTIVE,
+		.format = {
+			.code = MEDIA_BUS_FMT_UYVY8_2X8,
+			.width = 1920,
+			.height = 1080
+		}
+	};
+
+	return vfe_set_format(sd, fh ? fh->pad : NULL, &format);
+}
+
+/*
+ * msm_vfe_subdev_init - Initialize VFE device structure and resources
+ * @vfe: VFE device
+ * @res: VFE module resources table
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res)
+{
+	struct device *dev = to_device(vfe);
+	struct platform_device *pdev = to_platform_device(dev);
+	struct resource *r;
+	struct camss *camss = to_camss(vfe);
+	int i, j;
+	int ret;
+
+	/* Memory */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
+	vfe->base = devm_ioremap_resource(dev, r);
+	if (IS_ERR(vfe->base)) {
+		dev_err(dev, "could not map memory\n");
+		return PTR_ERR(vfe->base);
+	}
+
+	/* Interrupt */
+
+	r = platform_get_resource_byname(pdev, IORESOURCE_IRQ,
+					 res->interrupt[0]);
+	if (!r) {
+		dev_err(dev, "missing IRQ\n");
+		return -EINVAL;
+	}
+
+	vfe->irq = r->start;
+	snprintf(vfe->irq_name, sizeof(vfe->irq_name), "%s_%s%d",
+		 dev_name(dev), MSM_VFE_NAME, vfe->id);
+	ret = devm_request_irq(dev, vfe->irq, vfe_isr,
+			       IRQF_TRIGGER_RISING, vfe->irq_name, vfe);
+	if (ret < 0) {
+		dev_err(dev, "request_irq failed: %d\n", ret);
+		return ret;
+	}
+
+	/* Clocks */
+
+	vfe->nclocks = 0;
+	while (res->clock[vfe->nclocks])
+		vfe->nclocks++;
+
+	vfe->clock = devm_kcalloc(dev, vfe->nclocks, sizeof(*vfe->clock),
+				  GFP_KERNEL);
+	if (!vfe->clock)
+		return -ENOMEM;
+
+	for (i = 0; i < vfe->nclocks; i++) {
+		struct camss_clock *clock = &vfe->clock[i];
+
+		clock->clk = devm_clk_get(dev, res->clock[i]);
+		if (IS_ERR(clock->clk))
+			return PTR_ERR(clock->clk);
+
+		clock->name = res->clock[i];
+
+		clock->nfreqs = 0;
+		while (res->clock_rate[i][clock->nfreqs])
+			clock->nfreqs++;
+
+		if (!clock->nfreqs) {
+			clock->freq = NULL;
+			continue;
+		}
+
+		clock->freq = devm_kcalloc(dev,
+					   clock->nfreqs,
+					   sizeof(*clock->freq),
+					   GFP_KERNEL);
+		if (!clock->freq)
+			return -ENOMEM;
+
+		for (j = 0; j < clock->nfreqs; j++)
+			clock->freq[j] = res->clock_rate[i][j];
+	}
+
+	mutex_init(&vfe->power_lock);
+	vfe->power_count = 0;
+
+	mutex_init(&vfe->stream_lock);
+	vfe->stream_count = 0;
+
+	spin_lock_init(&vfe->output_lock);
+
+	vfe->id = 0;
+	vfe->reg_update = 0;
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
+		vfe->line[i].video_out.type =
+					V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+		vfe->line[i].video_out.camss = camss;
+		vfe->line[i].id = i;
+		init_completion(&vfe->line[i].output.sof);
+		init_completion(&vfe->line[i].output.reg_update);
+	}
+
+	init_completion(&vfe->reset_complete);
+	init_completion(&vfe->halt_complete);
+
+	return 0;
+}
+
+/*
+ * msm_vfe_get_vfe_id - Get VFE HW module id
+ * @entity: Pointer to VFE media entity structure
+ * @id: Return CSID HW module id here
+ */
+void msm_vfe_get_vfe_id(struct media_entity *entity, u8 *id)
+{
+	struct v4l2_subdev *sd;
+	struct vfe_line *line;
+	struct vfe_device *vfe;
+
+	sd = media_entity_to_v4l2_subdev(entity);
+	line = v4l2_get_subdevdata(sd);
+	vfe = to_vfe(line);
+
+	*id = vfe->id;
+}
+
+/*
+ * msm_vfe_get_vfe_line_id - Get VFE line id by media entity
+ * @entity: Pointer to VFE media entity structure
+ * @id: Return VFE line id here
+ */
+void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id)
+{
+	struct v4l2_subdev *sd;
+	struct vfe_line *line;
+
+	sd = media_entity_to_v4l2_subdev(entity);
+	line = v4l2_get_subdevdata(sd);
+
+	*id = line->id;
+}
+
+/*
+ * vfe_link_setup - Setup VFE connections
+ * @entity: Pointer to media entity structure
+ * @local: Pointer to local pad
+ * @remote: Pointer to remote pad
+ * @flags: Link flags
+ *
+ * Return 0 on success
+ */
+static int vfe_link_setup(struct media_entity *entity,
+			  const struct media_pad *local,
+			  const struct media_pad *remote, u32 flags)
+{
+	if (flags & MEDIA_LNK_FL_ENABLED)
+		if (media_entity_remote_pad(local))
+			return -EBUSY;
+
+	return 0;
+}
+
+static const struct v4l2_subdev_core_ops vfe_core_ops = {
+	.s_power = vfe_set_power,
+};
+
+static const struct v4l2_subdev_video_ops vfe_video_ops = {
+	.s_stream = vfe_set_stream,
+};
+
+static const struct v4l2_subdev_pad_ops vfe_pad_ops = {
+	.enum_mbus_code = vfe_enum_mbus_code,
+	.enum_frame_size = vfe_enum_frame_size,
+	.get_fmt = vfe_get_format,
+	.set_fmt = vfe_set_format,
+	.get_selection = vfe_get_selection,
+	.set_selection = vfe_set_selection,
+};
+
+static const struct v4l2_subdev_ops vfe_v4l2_ops = {
+	.core = &vfe_core_ops,
+	.video = &vfe_video_ops,
+	.pad = &vfe_pad_ops,
+};
+
+static const struct v4l2_subdev_internal_ops vfe_v4l2_internal_ops = {
+	.open = vfe_init_formats,
+};
+
+static const struct media_entity_operations vfe_media_ops = {
+	.link_setup = vfe_link_setup,
+	.link_validate = v4l2_subdev_link_validate,
+};
+
+static const struct camss_video_ops camss_vfe_video_ops = {
+	.queue_buffer = vfe_queue_buffer,
+	.flush_buffers = vfe_flush_buffers,
+};
+
+void msm_vfe_stop_streaming(struct vfe_device *vfe)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfe->line); i++)
+		msm_video_stop_streaming(&vfe->line[i].video_out);
+}
+
+/*
+ * msm_vfe_register_entities - Register subdev node for VFE module
+ * @vfe: VFE device
+ * @v4l2_dev: V4L2 device
+ *
+ * Initialize and register a subdev node for the VFE module. Then
+ * call msm_video_register() to register the video device node which
+ * will be connected to this subdev node. Then actually create the
+ * media link between them.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int msm_vfe_register_entities(struct vfe_device *vfe,
+			      struct v4l2_device *v4l2_dev)
+{
+	struct device *dev = to_device(vfe);
+	struct v4l2_subdev *sd;
+	struct media_pad *pads;
+	struct camss_video *video_out;
+	int ret;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(vfe->line); i++) {
+		char name[32];
+
+		sd = &vfe->line[i].subdev;
+		pads = vfe->line[i].pads;
+		video_out = &vfe->line[i].video_out;
+
+		v4l2_subdev_init(sd, &vfe_v4l2_ops);
+		sd->internal_ops = &vfe_v4l2_internal_ops;
+		sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+		if (i == VFE_LINE_PIX)
+			snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d_%s",
+				 MSM_VFE_NAME, vfe->id, "pix");
+		else
+			snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d_%s%d",
+				 MSM_VFE_NAME, vfe->id, "rdi", i);
+
+		v4l2_set_subdevdata(sd, &vfe->line[i]);
+
+		ret = vfe_init_formats(sd, NULL);
+		if (ret < 0) {
+			dev_err(dev, "Failed to init format: %d\n", ret);
+			goto error_init;
+		}
+
+		pads[MSM_VFE_PAD_SINK].flags = MEDIA_PAD_FL_SINK;
+		pads[MSM_VFE_PAD_SRC].flags = MEDIA_PAD_FL_SOURCE;
+
+		sd->entity.function = MEDIA_ENT_F_PROC_VIDEO_PIXEL_FORMATTER;
+		sd->entity.ops = &vfe_media_ops;
+		ret = media_entity_pads_init(&sd->entity, MSM_VFE_PADS_NUM,
+					     pads);
+		if (ret < 0) {
+			dev_err(dev, "Failed to init media entity: %d\n", ret);
+			goto error_init;
+		}
+
+		ret = v4l2_device_register_subdev(v4l2_dev, sd);
+		if (ret < 0) {
+			dev_err(dev, "Failed to register subdev: %d\n", ret);
+			goto error_reg_subdev;
+		}
+
+		video_out->ops = &camss_vfe_video_ops;
+		video_out->bpl_alignment = 8;
+		video_out->line_based = 0;
+		if (i == VFE_LINE_PIX) {
+			video_out->bpl_alignment = 16;
+			video_out->line_based = 1;
+		}
+		snprintf(name, ARRAY_SIZE(name), "%s%d_%s%d",
+			 MSM_VFE_NAME, vfe->id, "video", i);
+		ret = msm_video_register(video_out, v4l2_dev, name,
+					 i == VFE_LINE_PIX ? 1 : 0);
+		if (ret < 0) {
+			dev_err(dev, "Failed to register video node: %d\n",
+				ret);
+			goto error_reg_video;
+		}
+
+		ret = media_create_pad_link(
+				&sd->entity, MSM_VFE_PAD_SRC,
+				&video_out->vdev.entity, 0,
+				MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+		if (ret < 0) {
+			dev_err(dev, "Failed to link %s->%s entities: %d\n",
+				sd->entity.name, video_out->vdev.entity.name,
+				ret);
+			goto error_link;
+		}
+	}
+
+	return 0;
+
+error_link:
+	msm_video_unregister(video_out);
+
+error_reg_video:
+	v4l2_device_unregister_subdev(sd);
+
+error_reg_subdev:
+	media_entity_cleanup(&sd->entity);
+
+error_init:
+	for (i--; i >= 0; i--) {
+		sd = &vfe->line[i].subdev;
+		video_out = &vfe->line[i].video_out;
+
+		msm_video_unregister(video_out);
+		v4l2_device_unregister_subdev(sd);
+		media_entity_cleanup(&sd->entity);
+	}
+
+	return ret;
+}
+
+/*
+ * msm_vfe_unregister_entities - Unregister VFE module subdev node
+ * @vfe: VFE device
+ */
+void msm_vfe_unregister_entities(struct vfe_device *vfe)
+{
+	int i;
+
+	mutex_destroy(&vfe->power_lock);
+	mutex_destroy(&vfe->stream_lock);
+
+	for (i = 0; i < ARRAY_SIZE(vfe->line); i++) {
+		struct v4l2_subdev *sd = &vfe->line[i].subdev;
+		struct camss_video *video_out = &vfe->line[i].video_out;
+
+		msm_video_unregister(video_out);
+		v4l2_device_unregister_subdev(sd);
+		media_entity_cleanup(&sd->entity);
+	}
+}
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
new file mode 100644
index 000000000000..5aa740741de8
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -0,0 +1,123 @@
+/*
+ * camss-vfe.h
+ *
+ * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef QC_MSM_CAMSS_VFE_H
+#define QC_MSM_CAMSS_VFE_H
+
+#include <linux/clk.h>
+#include <linux/spinlock_types.h>
+#include <media/media-entity.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+
+#include "camss-video.h"
+
+#define MSM_VFE_PAD_SINK 0
+#define MSM_VFE_PAD_SRC 1
+#define MSM_VFE_PADS_NUM 2
+
+#define MSM_VFE_LINE_NUM 4
+#define MSM_VFE_IMAGE_MASTERS_NUM 7
+#define MSM_VFE_COMPOSITE_IRQ_NUM 4
+
+#define MSM_VFE_VFE0_UB_SIZE 1023
+#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
+#define MSM_VFE_VFE1_UB_SIZE 1535
+#define MSM_VFE_VFE1_UB_SIZE_RDI (MSM_VFE_VFE1_UB_SIZE / 3)
+
+enum vfe_output_state {
+	VFE_OUTPUT_OFF,
+	VFE_OUTPUT_RESERVED,
+	VFE_OUTPUT_SINGLE,
+	VFE_OUTPUT_CONTINUOUS,
+	VFE_OUTPUT_IDLE,
+	VFE_OUTPUT_STOPPING
+};
+
+enum vfe_line_id {
+	VFE_LINE_NONE = -1,
+	VFE_LINE_RDI0 = 0,
+	VFE_LINE_RDI1 = 1,
+	VFE_LINE_RDI2 = 2,
+	VFE_LINE_PIX = 3
+};
+
+struct vfe_output {
+	u8 wm_num;
+	u8 wm_idx[3];
+
+	int active_buf;
+	struct camss_buffer *buf[2];
+	struct camss_buffer *last_buffer;
+	struct list_head pending_bufs;
+
+	unsigned int drop_update_idx;
+
+	enum vfe_output_state state;
+	unsigned int sequence;
+	int wait_sof;
+	int wait_reg_update;
+	struct completion sof;
+	struct completion reg_update;
+};
+
+struct vfe_line {
+	enum vfe_line_id id;
+	struct v4l2_subdev subdev;
+	struct media_pad pads[MSM_VFE_PADS_NUM];
+	struct v4l2_mbus_framefmt fmt[MSM_VFE_PADS_NUM];
+	struct v4l2_rect compose;
+	struct v4l2_rect crop;
+	struct camss_video video_out;
+	struct vfe_output output;
+};
+
+struct vfe_device {
+	u8 id;
+	void __iomem *base;
+	u32 irq;
+	char irq_name[30];
+	struct camss_clock *clock;
+	int nclocks;
+	struct completion reset_complete;
+	struct completion halt_complete;
+	struct mutex power_lock;
+	int power_count;
+	struct mutex stream_lock;
+	int stream_count;
+	spinlock_t output_lock;
+	enum vfe_line_id wm_output_map[MSM_VFE_IMAGE_MASTERS_NUM];
+	struct vfe_line line[MSM_VFE_LINE_NUM];
+	u32 reg_update;
+	u8 was_streaming;
+};
+
+struct resources;
+
+int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res);
+
+int msm_vfe_register_entities(struct vfe_device *vfe,
+			      struct v4l2_device *v4l2_dev);
+
+void msm_vfe_unregister_entities(struct vfe_device *vfe);
+
+void msm_vfe_get_vfe_id(struct media_entity *entity, u8 *id);
+void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id);
+
+void msm_vfe_stop_streaming(struct vfe_device *vfe);
+
+#endif /* QC_MSM_CAMSS_VFE_H */
diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
new file mode 100644
index 000000000000..0e7b842854ec
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -0,0 +1,859 @@
+/*
+ * camss-video.c
+ *
+ * Qualcomm MSM Camera Subsystem - V4L2 device node
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/slab.h>
+#include <media/media-entity.h>
+#include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-ioctl.h>
+#include <media/v4l2-mc.h>
+#include <media/videobuf2-dma-sg.h>
+
+#include "camss-video.h"
+#include "camss.h"
+
+struct fract {
+	u8 numerator;
+	u8 denominator;
+};
+
+/*
+ * struct camss_format_info - ISP media bus format information
+ * @code: V4L2 media bus format code
+ * @pixelformat: V4L2 pixel format FCC identifier
+ * @planes: Number of planes
+ * @hsub: Horizontal subsampling (for each plane)
+ * @vsub: Vertical subsampling (for each plane)
+ * @bpp: Bits per pixel when stored in memory (for each plane)
+ */
+struct camss_format_info {
+	u32 code;
+	u32 pixelformat;
+	u8 planes;
+	struct fract hsub[3];
+	struct fract vsub[3];
+	unsigned int bpp[3];
+};
+
+static const struct camss_format_info formats_rdi[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_YUYV, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_YVYU, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, V4L2_PIX_FMT_SBGGR8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, V4L2_PIX_FMT_SGBRG8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, V4L2_PIX_FMT_SGRBG8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, V4L2_PIX_FMT_SRGGB8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, V4L2_PIX_FMT_SBGGR10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, V4L2_PIX_FMT_SGBRG10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, V4L2_PIX_FMT_SGRBG10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, V4L2_PIX_FMT_SRGGB10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, V4L2_PIX_FMT_SBGGR12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, V4L2_PIX_FMT_SGBRG12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, V4L2_PIX_FMT_SGRBG12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, V4L2_PIX_FMT_SRGGB12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+};
+
+static const struct camss_format_info formats_pix[] = {
+	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+};
+
+/* -----------------------------------------------------------------------------
+ * Helper functions
+ */
+
+static int video_find_format(u32 code, u32 pixelformat,
+			     const struct camss_format_info *formats,
+			     unsigned int nformats)
+{
+	int i;
+
+	for (i = 0; i < nformats; i++) {
+		if (formats[i].code == code &&
+		    formats[i].pixelformat == pixelformat)
+			return i;
+	}
+
+	for (i = 0; i < nformats; i++)
+		if (formats[i].code == code)
+			return i;
+
+	WARN_ON(1);
+
+	return -EINVAL;
+}
+
+/*
+ * video_mbus_to_pix_mp - Convert v4l2_mbus_framefmt to v4l2_pix_format_mplane
+ * @mbus: v4l2_mbus_framefmt format (input)
+ * @pix: v4l2_pix_format_mplane format (output)
+ * @f: a pointer to formats array element to be used for the conversion
+ * @alignment: bytesperline alignment value
+ *
+ * Fill the output pix structure with information from the input mbus format.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int video_mbus_to_pix_mp(const struct v4l2_mbus_framefmt *mbus,
+				struct v4l2_pix_format_mplane *pix,
+				const struct camss_format_info *f,
+				unsigned int alignment)
+{
+	unsigned int i;
+	u32 bytesperline;
+
+	memset(pix, 0, sizeof(*pix));
+	v4l2_fill_pix_format_mplane(pix, mbus);
+	pix->pixelformat = f->pixelformat;
+	pix->num_planes = f->planes;
+	for (i = 0; i < pix->num_planes; i++) {
+		bytesperline = pix->width / f->hsub[i].numerator *
+			f->hsub[i].denominator * f->bpp[i] / 8;
+		bytesperline = ALIGN(bytesperline, alignment);
+		pix->plane_fmt[i].bytesperline = bytesperline;
+		pix->plane_fmt[i].sizeimage = pix->height /
+				f->vsub[i].numerator * f->vsub[i].denominator *
+				bytesperline;
+	}
+
+	return 0;
+}
+
+static struct v4l2_subdev *video_remote_subdev(struct camss_video *video,
+					       u32 *pad)
+{
+	struct media_pad *remote;
+
+	remote = media_entity_remote_pad(&video->pad);
+
+	if (!remote || !is_media_entity_v4l2_subdev(remote->entity))
+		return NULL;
+
+	if (pad)
+		*pad = remote->index;
+
+	return media_entity_to_v4l2_subdev(remote->entity);
+}
+
+static int video_get_subdev_format(struct camss_video *video,
+				   struct v4l2_format *format)
+{
+	struct v4l2_subdev_format fmt;
+	struct v4l2_subdev *subdev;
+	u32 pad;
+	int ret;
+
+	subdev = video_remote_subdev(video, &pad);
+	if (subdev == NULL)
+		return -EPIPE;
+
+	fmt.pad = pad;
+	fmt.which = V4L2_SUBDEV_FORMAT_ACTIVE;
+
+	ret = v4l2_subdev_call(subdev, pad, get_fmt, NULL, &fmt);
+	if (ret)
+		return ret;
+
+	ret = video_find_format(fmt.format.code,
+				format->fmt.pix_mp.pixelformat,
+				video->formats, video->nformats);
+	if (ret < 0)
+		return ret;
+
+	format->type = video->type;
+
+	return video_mbus_to_pix_mp(&fmt.format, &format->fmt.pix_mp,
+				    &video->formats[ret], video->bpl_alignment);
+}
+
+/* -----------------------------------------------------------------------------
+ * Video queue operations
+ */
+
+static int video_queue_setup(struct vb2_queue *q,
+	unsigned int *num_buffers, unsigned int *num_planes,
+	unsigned int sizes[], struct device *alloc_devs[])
+{
+	struct camss_video *video = vb2_get_drv_priv(q);
+	const struct v4l2_pix_format_mplane *format =
+						&video->active_fmt.fmt.pix_mp;
+	unsigned int i;
+
+	if (*num_planes) {
+		if (*num_planes != format->num_planes)
+			return -EINVAL;
+
+		for (i = 0; i < *num_planes; i++)
+			if (sizes[i] < format->plane_fmt[i].sizeimage)
+				return -EINVAL;
+
+		return 0;
+	}
+
+	*num_planes = format->num_planes;
+
+	for (i = 0; i < *num_planes; i++)
+		sizes[i] = format->plane_fmt[i].sizeimage;
+
+	return 0;
+}
+
+static int video_buf_init(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct camss_video *video = vb2_get_drv_priv(vb->vb2_queue);
+	struct camss_buffer *buffer = container_of(vbuf, struct camss_buffer,
+						   vb);
+	const struct v4l2_pix_format_mplane *format =
+						&video->active_fmt.fmt.pix_mp;
+	struct sg_table *sgt;
+	unsigned int i;
+
+	for (i = 0; i < format->num_planes; i++) {
+		sgt = vb2_dma_sg_plane_desc(vb, i);
+		if (!sgt)
+			return -EFAULT;
+
+		buffer->addr[i] = sg_dma_address(sgt->sgl);
+	}
+
+	if (format->pixelformat == V4L2_PIX_FMT_NV12 ||
+			format->pixelformat == V4L2_PIX_FMT_NV21 ||
+			format->pixelformat == V4L2_PIX_FMT_NV16 ||
+			format->pixelformat == V4L2_PIX_FMT_NV61)
+		buffer->addr[1] = buffer->addr[0] +
+				format->plane_fmt[0].bytesperline *
+				format->height;
+
+	return 0;
+}
+
+static int video_buf_prepare(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct camss_video *video = vb2_get_drv_priv(vb->vb2_queue);
+	const struct v4l2_pix_format_mplane *format =
+						&video->active_fmt.fmt.pix_mp;
+	unsigned int i;
+
+	for (i = 0; i < format->num_planes; i++) {
+		if (format->plane_fmt[i].sizeimage > vb2_plane_size(vb, i))
+			return -EINVAL;
+
+		vb2_set_plane_payload(vb, i, format->plane_fmt[i].sizeimage);
+	}
+
+	vbuf->field = V4L2_FIELD_NONE;
+
+	return 0;
+}
+
+static void video_buf_queue(struct vb2_buffer *vb)
+{
+	struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+	struct camss_video *video = vb2_get_drv_priv(vb->vb2_queue);
+	struct camss_buffer *buffer = container_of(vbuf, struct camss_buffer,
+						   vb);
+
+	video->ops->queue_buffer(video, buffer);
+}
+
+static int video_check_format(struct camss_video *video)
+{
+	struct v4l2_pix_format_mplane *pix = &video->active_fmt.fmt.pix_mp;
+	struct v4l2_format format;
+	struct v4l2_pix_format_mplane *sd_pix = &format.fmt.pix_mp;
+	int ret;
+
+	sd_pix->pixelformat = pix->pixelformat;
+	ret = video_get_subdev_format(video, &format);
+	if (ret < 0)
+		return ret;
+
+	if (pix->pixelformat != sd_pix->pixelformat ||
+	    pix->height != sd_pix->height ||
+	    pix->width != sd_pix->width ||
+	    pix->num_planes != sd_pix->num_planes ||
+	    pix->field != format.fmt.pix_mp.field)
+		return -EPIPE;
+
+	return 0;
+}
+
+static int video_start_streaming(struct vb2_queue *q, unsigned int count)
+{
+	struct camss_video *video = vb2_get_drv_priv(q);
+	struct video_device *vdev = &video->vdev;
+	struct media_entity *entity;
+	struct media_pad *pad;
+	struct v4l2_subdev *subdev;
+	int ret;
+
+	ret = media_pipeline_start(&vdev->entity, &video->pipe);
+	if (ret < 0)
+		return ret;
+
+	ret = video_check_format(video);
+	if (ret < 0)
+		goto error;
+
+	entity = &vdev->entity;
+	while (1) {
+		pad = &entity->pads[0];
+		if (!(pad->flags & MEDIA_PAD_FL_SINK))
+			break;
+
+		pad = media_entity_remote_pad(pad);
+		if (!pad || !is_media_entity_v4l2_subdev(pad->entity))
+			break;
+
+		entity = pad->entity;
+		subdev = media_entity_to_v4l2_subdev(entity);
+
+		ret = v4l2_subdev_call(subdev, video, s_stream, 1);
+		if (ret < 0 && ret != -ENOIOCTLCMD)
+			goto error;
+	}
+
+	return 0;
+
+error:
+	media_pipeline_stop(&vdev->entity);
+
+	video->ops->flush_buffers(video, VB2_BUF_STATE_QUEUED);
+
+	return ret;
+}
+
+static void video_stop_streaming(struct vb2_queue *q)
+{
+	struct camss_video *video = vb2_get_drv_priv(q);
+	struct video_device *vdev = &video->vdev;
+	struct media_entity *entity;
+	struct media_pad *pad;
+	struct v4l2_subdev *subdev;
+
+	entity = &vdev->entity;
+	while (1) {
+		pad = &entity->pads[0];
+		if (!(pad->flags & MEDIA_PAD_FL_SINK))
+			break;
+
+		pad = media_entity_remote_pad(pad);
+		if (!pad || !is_media_entity_v4l2_subdev(pad->entity))
+			break;
+
+		entity = pad->entity;
+		subdev = media_entity_to_v4l2_subdev(entity);
+
+		v4l2_subdev_call(subdev, video, s_stream, 0);
+	}
+
+	media_pipeline_stop(&vdev->entity);
+
+	video->ops->flush_buffers(video, VB2_BUF_STATE_ERROR);
+}
+
+static const struct vb2_ops msm_video_vb2_q_ops = {
+	.queue_setup     = video_queue_setup,
+	.wait_prepare    = vb2_ops_wait_prepare,
+	.wait_finish     = vb2_ops_wait_finish,
+	.buf_init        = video_buf_init,
+	.buf_prepare     = video_buf_prepare,
+	.buf_queue       = video_buf_queue,
+	.start_streaming = video_start_streaming,
+	.stop_streaming  = video_stop_streaming,
+};
+
+/* -----------------------------------------------------------------------------
+ * V4L2 ioctls
+ */
+
+static int video_querycap(struct file *file, void *fh,
+			  struct v4l2_capability *cap)
+{
+	struct camss_video *video = video_drvdata(file);
+
+	strlcpy(cap->driver, "qcom-camss", sizeof(cap->driver));
+	strlcpy(cap->card, "Qualcomm Camera Subsystem", sizeof(cap->card));
+	snprintf(cap->bus_info, sizeof(cap->bus_info), "platform:%s",
+		 dev_name(video->camss->dev));
+
+	return 0;
+}
+
+static int video_enum_fmt(struct file *file, void *fh, struct v4l2_fmtdesc *f)
+{
+	struct camss_video *video = video_drvdata(file);
+	int i, j, k;
+
+	if (f->type != video->type)
+		return -EINVAL;
+
+	if (f->index >= video->nformats)
+		return -EINVAL;
+
+	/* find index "i" of "k"th unique pixelformat in formats array */
+	k = -1;
+	for (i = 0; i < video->nformats; i++) {
+		for (j = 0; j < i; j++) {
+			if (video->formats[i].pixelformat ==
+					video->formats[j].pixelformat)
+				break;
+		}
+
+		if (j == i)
+			k++;
+
+		if (k == f->index)
+			break;
+	}
+
+	if (k < f->index)
+		return -EINVAL;
+
+	f->pixelformat = video->formats[i].pixelformat;
+
+	return 0;
+}
+
+static int video_g_fmt(struct file *file, void *fh, struct v4l2_format *f)
+{
+	struct camss_video *video = video_drvdata(file);
+
+	*f = video->active_fmt;
+
+	return 0;
+}
+
+static int __video_try_fmt(struct camss_video *video, struct v4l2_format *f)
+{
+	struct v4l2_pix_format_mplane *pix_mp;
+	const struct camss_format_info *fi;
+	struct v4l2_plane_pix_format *p;
+	u32 bytesperline[3] = { 0 };
+	u32 sizeimage[3] = { 0 };
+	u32 width, height;
+	u32 bpl, lines;
+	int i, j;
+
+	pix_mp = &f->fmt.pix_mp;
+
+	if (video->line_based)
+		for (i = 0; i < pix_mp->num_planes && i < 3; i++) {
+			p = &pix_mp->plane_fmt[i];
+			bytesperline[i] = clamp_t(u32, p->bytesperline,
+						  1, 65528);
+			sizeimage[i] = clamp_t(u32, p->sizeimage,
+					       bytesperline[i],
+					       bytesperline[i] * 4096);
+		}
+
+	for (j = 0; j < video->nformats; j++)
+		if (pix_mp->pixelformat == video->formats[j].pixelformat)
+			break;
+
+	if (j == video->nformats)
+		j = 0; /* default format */
+
+	fi = &video->formats[j];
+	width = pix_mp->width;
+	height = pix_mp->height;
+
+	memset(pix_mp, 0, sizeof(*pix_mp));
+
+	pix_mp->pixelformat = fi->pixelformat;
+	pix_mp->width = clamp_t(u32, width, 1, 8191);
+	pix_mp->height = clamp_t(u32, height, 1, 8191);
+	pix_mp->num_planes = fi->planes;
+	for (i = 0; i < pix_mp->num_planes; i++) {
+		bpl = pix_mp->width / fi->hsub[i].numerator *
+			fi->hsub[i].denominator * fi->bpp[i] / 8;
+		bpl = ALIGN(bpl, video->bpl_alignment);
+		pix_mp->plane_fmt[i].bytesperline = bpl;
+		pix_mp->plane_fmt[i].sizeimage = pix_mp->height /
+			fi->vsub[i].numerator * fi->vsub[i].denominator * bpl;
+	}
+
+	pix_mp->field = V4L2_FIELD_NONE;
+	pix_mp->colorspace = V4L2_COLORSPACE_SRGB;
+	pix_mp->flags = 0;
+	pix_mp->ycbcr_enc = V4L2_MAP_YCBCR_ENC_DEFAULT(pix_mp->colorspace);
+	pix_mp->quantization = V4L2_MAP_QUANTIZATION_DEFAULT(true,
+					pix_mp->colorspace, pix_mp->ycbcr_enc);
+	pix_mp->xfer_func = V4L2_MAP_XFER_FUNC_DEFAULT(pix_mp->colorspace);
+
+	if (video->line_based)
+		for (i = 0; i < pix_mp->num_planes; i++) {
+			p = &pix_mp->plane_fmt[i];
+			p->bytesperline = clamp_t(u32, p->bytesperline,
+						  1, 65528);
+			p->sizeimage = clamp_t(u32, p->sizeimage,
+					       p->bytesperline,
+					       p->bytesperline * 4096);
+			lines = p->sizeimage / p->bytesperline;
+
+			if (p->bytesperline < bytesperline[i])
+				p->bytesperline = ALIGN(bytesperline[i], 8);
+
+			if (p->sizeimage < p->bytesperline * lines)
+				p->sizeimage = p->bytesperline * lines;
+
+			if (p->sizeimage < sizeimage[i])
+				p->sizeimage = sizeimage[i];
+		}
+
+	return 0;
+}
+
+static int video_try_fmt(struct file *file, void *fh, struct v4l2_format *f)
+{
+	struct camss_video *video = video_drvdata(file);
+
+	return __video_try_fmt(video, f);
+}
+
+static int video_s_fmt(struct file *file, void *fh, struct v4l2_format *f)
+{
+	struct camss_video *video = video_drvdata(file);
+	int ret;
+
+	if (vb2_is_busy(&video->vb2_q))
+		return -EBUSY;
+
+	ret = __video_try_fmt(video, f);
+	if (ret < 0)
+		return ret;
+
+	video->active_fmt = *f;
+
+	return 0;
+}
+
+static int video_enum_input(struct file *file, void *fh,
+			    struct v4l2_input *input)
+{
+	if (input->index > 0)
+		return -EINVAL;
+
+	strlcpy(input->name, "camera", sizeof(input->name));
+	input->type = V4L2_INPUT_TYPE_CAMERA;
+
+	return 0;
+}
+
+static int video_g_input(struct file *file, void *fh, unsigned int *input)
+{
+	*input = 0;
+
+	return 0;
+}
+
+static int video_s_input(struct file *file, void *fh, unsigned int input)
+{
+	return input == 0 ? 0 : -EINVAL;
+}
+
+static const struct v4l2_ioctl_ops msm_vid_ioctl_ops = {
+	.vidioc_querycap		= video_querycap,
+	.vidioc_enum_fmt_vid_cap_mplane	= video_enum_fmt,
+	.vidioc_g_fmt_vid_cap_mplane	= video_g_fmt,
+	.vidioc_s_fmt_vid_cap_mplane	= video_s_fmt,
+	.vidioc_try_fmt_vid_cap_mplane	= video_try_fmt,
+	.vidioc_reqbufs			= vb2_ioctl_reqbufs,
+	.vidioc_querybuf		= vb2_ioctl_querybuf,
+	.vidioc_qbuf			= vb2_ioctl_qbuf,
+	.vidioc_expbuf			= vb2_ioctl_expbuf,
+	.vidioc_dqbuf			= vb2_ioctl_dqbuf,
+	.vidioc_create_bufs		= vb2_ioctl_create_bufs,
+	.vidioc_prepare_buf		= vb2_ioctl_prepare_buf,
+	.vidioc_streamon		= vb2_ioctl_streamon,
+	.vidioc_streamoff		= vb2_ioctl_streamoff,
+	.vidioc_enum_input		= video_enum_input,
+	.vidioc_g_input			= video_g_input,
+	.vidioc_s_input			= video_s_input,
+};
+
+/* -----------------------------------------------------------------------------
+ * V4L2 file operations
+ */
+
+static int video_open(struct file *file)
+{
+	struct video_device *vdev = video_devdata(file);
+	struct camss_video *video = video_drvdata(file);
+	struct v4l2_fh *vfh;
+	int ret;
+
+	mutex_lock(&video->lock);
+
+	vfh = kzalloc(sizeof(*vfh), GFP_KERNEL);
+	if (vfh == NULL) {
+		ret = -ENOMEM;
+		goto error_alloc;
+	}
+
+	v4l2_fh_init(vfh, vdev);
+	v4l2_fh_add(vfh);
+
+	file->private_data = vfh;
+
+	ret = v4l2_pipeline_pm_use(&vdev->entity, 1);
+	if (ret < 0) {
+		dev_err(video->camss->dev, "Failed to power up pipeline: %d\n",
+			ret);
+		goto error_pm_use;
+	}
+
+	mutex_unlock(&video->lock);
+
+	return 0;
+
+error_pm_use:
+	v4l2_fh_release(file);
+
+error_alloc:
+	mutex_unlock(&video->lock);
+
+	return ret;
+}
+
+static int video_release(struct file *file)
+{
+	struct video_device *vdev = video_devdata(file);
+
+	vb2_fop_release(file);
+
+	v4l2_pipeline_pm_use(&vdev->entity, 0);
+
+	file->private_data = NULL;
+
+	return 0;
+}
+
+static const struct v4l2_file_operations msm_vid_fops = {
+	.owner          = THIS_MODULE,
+	.unlocked_ioctl = video_ioctl2,
+	.open           = video_open,
+	.release        = video_release,
+	.poll           = vb2_fop_poll,
+	.mmap		= vb2_fop_mmap,
+	.read		= vb2_fop_read,
+};
+
+/* -----------------------------------------------------------------------------
+ * CAMSS video core
+ */
+
+static void msm_video_release(struct video_device *vdev)
+{
+	struct camss_video *video = video_get_drvdata(vdev);
+
+	media_entity_cleanup(&vdev->entity);
+
+	mutex_destroy(&video->q_lock);
+	mutex_destroy(&video->lock);
+
+	if (atomic_dec_and_test(&video->camss->ref_count))
+		camss_delete(video->camss);
+}
+
+/*
+ * msm_video_init_format - Helper function to initialize format
+ * @video: struct camss_video
+ *
+ * Initialize pad format with default value.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+static int msm_video_init_format(struct camss_video *video)
+{
+	int ret;
+	struct v4l2_format format = {
+		.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE,
+		.fmt.pix_mp = {
+			.width = 1920,
+			.height = 1080,
+			.pixelformat = video->formats[0].pixelformat,
+		},
+	};
+
+	ret = __video_try_fmt(video, &format);
+	if (ret < 0)
+		return ret;
+
+	video->active_fmt = format;
+
+	return 0;
+}
+
+/*
+ * msm_video_register - Register a video device node
+ * @video: struct camss_video
+ * @v4l2_dev: V4L2 device
+ * @name: name to be used for the video device node
+ *
+ * Initialize and register a video device node to a V4L2 device. Also
+ * initialize the vb2 queue.
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+
+int msm_video_register(struct camss_video *video, struct v4l2_device *v4l2_dev,
+		       const char *name, int is_pix)
+{
+	struct media_pad *pad = &video->pad;
+	struct video_device *vdev;
+	struct vb2_queue *q;
+	int ret;
+
+	vdev = &video->vdev;
+
+	mutex_init(&video->q_lock);
+
+	q = &video->vb2_q;
+	q->drv_priv = video;
+	q->mem_ops = &vb2_dma_sg_memops;
+	q->ops = &msm_video_vb2_q_ops;
+	q->type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+	q->io_modes = VB2_DMABUF | VB2_MMAP | VB2_READ;
+	q->timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	q->buf_struct_size = sizeof(struct camss_buffer);
+	q->dev = video->camss->dev;
+	q->lock = &video->q_lock;
+	ret = vb2_queue_init(q);
+	if (ret < 0) {
+		dev_err(v4l2_dev->dev, "Failed to init vb2 queue: %d\n", ret);
+		goto error_vb2_init;
+	}
+
+	pad->flags = MEDIA_PAD_FL_SINK;
+	ret = media_entity_pads_init(&vdev->entity, 1, pad);
+	if (ret < 0) {
+		dev_err(v4l2_dev->dev, "Failed to init video entity: %d\n",
+			ret);
+		goto error_media_init;
+	}
+
+	mutex_init(&video->lock);
+
+	video->formats = formats_rdi;
+	video->nformats = ARRAY_SIZE(formats_rdi);
+	if (is_pix) {
+		video->formats = formats_pix;
+		video->nformats = ARRAY_SIZE(formats_pix);
+	}
+
+	ret = msm_video_init_format(video);
+	if (ret < 0) {
+		dev_err(v4l2_dev->dev, "Failed to init format: %d\n", ret);
+		goto error_video_register;
+	}
+
+	vdev->fops = &msm_vid_fops;
+	vdev->device_caps = V4L2_CAP_VIDEO_CAPTURE_MPLANE | V4L2_CAP_STREAMING |
+							V4L2_CAP_READWRITE;
+	vdev->ioctl_ops = &msm_vid_ioctl_ops;
+	vdev->release = msm_video_release;
+	vdev->v4l2_dev = v4l2_dev;
+	vdev->vfl_dir = VFL_DIR_RX;
+	vdev->queue = &video->vb2_q;
+	vdev->lock = &video->lock;
+	strlcpy(vdev->name, name, sizeof(vdev->name));
+
+	ret = video_register_device(vdev, VFL_TYPE_GRABBER, -1);
+	if (ret < 0) {
+		dev_err(v4l2_dev->dev, "Failed to register video device: %d\n",
+			ret);
+		goto error_video_register;
+	}
+
+	video_set_drvdata(vdev, video);
+	atomic_inc(&video->camss->ref_count);
+
+	return 0;
+
+error_video_register:
+	media_entity_cleanup(&vdev->entity);
+	mutex_destroy(&video->lock);
+error_media_init:
+	vb2_queue_release(&video->vb2_q);
+error_vb2_init:
+	mutex_destroy(&video->q_lock);
+
+	return ret;
+}
+
+void msm_video_stop_streaming(struct camss_video *video)
+{
+	if (vb2_is_streaming(&video->vb2_q))
+		vb2_queue_release(&video->vb2_q);
+}
+
+void msm_video_unregister(struct camss_video *video)
+{
+	atomic_inc(&video->camss->ref_count);
+	video_unregister_device(&video->vdev);
+	atomic_dec(&video->camss->ref_count);
+}
diff --git a/drivers/media/platform/qcom/camss/camss-video.h b/drivers/media/platform/qcom/camss/camss-video.h
new file mode 100644
index 000000000000..821c1ef6b5c7
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-video.h
@@ -0,0 +1,70 @@
+/*
+ * camss-video.h
+ *
+ * Qualcomm MSM Camera Subsystem - V4L2 device node
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef QC_MSM_CAMSS_VIDEO_H
+#define QC_MSM_CAMSS_VIDEO_H
+
+#include <linux/mutex.h>
+#include <linux/videodev2.h>
+#include <media/media-entity.h>
+#include <media/v4l2-dev.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-fh.h>
+#include <media/v4l2-mediabus.h>
+#include <media/videobuf2-v4l2.h>
+
+struct camss_buffer {
+	struct vb2_v4l2_buffer vb;
+	dma_addr_t addr[3];
+	struct list_head queue;
+};
+
+struct camss_video;
+
+struct camss_video_ops {
+	int (*queue_buffer)(struct camss_video *vid, struct camss_buffer *buf);
+	int (*flush_buffers)(struct camss_video *vid,
+			     enum vb2_buffer_state state);
+};
+
+struct camss_format_info;
+
+struct camss_video {
+	struct camss *camss;
+	struct vb2_queue vb2_q;
+	struct video_device vdev;
+	struct media_pad pad;
+	struct v4l2_format active_fmt;
+	enum v4l2_buf_type type;
+	struct media_pipeline pipe;
+	const struct camss_video_ops *ops;
+	struct mutex lock;
+	struct mutex q_lock;
+	unsigned int bpl_alignment;
+	unsigned int line_based;
+	const struct camss_format_info *formats;
+	unsigned int nformats;
+};
+
+void msm_video_stop_streaming(struct camss_video *video);
+
+int msm_video_register(struct camss_video *video, struct v4l2_device *v4l2_dev,
+		       const char *name, int is_pix);
+
+void msm_video_unregister(struct camss_video *video);
+
+#endif /* QC_MSM_CAMSS_VIDEO_H */
diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
new file mode 100644
index 000000000000..d1d27fca2958
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -0,0 +1,751 @@
+/*
+ * camss.c
+ *
+ * Qualcomm MSM Camera Subsystem - Core
+ *
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/clk.h>
+#include <linux/media-bus-format.h>
+#include <linux/media.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/of.h>
+#include <linux/of_graph.h>
+#include <linux/slab.h>
+#include <linux/videodev2.h>
+
+#include <media/media-device.h>
+#include <media/v4l2-async.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-mc.h>
+#include <media/v4l2-fwnode.h>
+
+#include "camss.h"
+
+#define CAMSS_CLOCK_MARGIN_NUMERATOR 105
+#define CAMSS_CLOCK_MARGIN_DENOMINATOR 100
+
+static const struct resources csiphy_res[] = {
+	/* CSIPHY0 */
+	{
+		.regulator = { NULL },
+		.clock = { "camss_top_ahb", "ispif_ahb",
+			   "camss_ahb", "csiphy0_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000 } },
+		.reg = { "csiphy0", "csiphy0_clk_mux" },
+		.interrupt = { "csiphy0" }
+	},
+
+	/* CSIPHY1 */
+	{
+		.regulator = { NULL },
+		.clock = { "camss_top_ahb", "ispif_ahb",
+			   "camss_ahb", "csiphy1_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000 } },
+		.reg = { "csiphy1", "csiphy1_clk_mux" },
+		.interrupt = { "csiphy1" }
+	}
+};
+
+static const struct resources csid_res[] = {
+	/* CSID0 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "camss_top_ahb", "ispif_ahb",
+			   "csi0_ahb", "camss_ahb",
+			   "csi0", "csi0_phy", "csi0_pix", "csi0_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid0" },
+		.interrupt = { "csid0" }
+	},
+
+	/* CSID1 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "camss_top_ahb", "ispif_ahb",
+			   "csi1_ahb", "camss_ahb",
+			   "csi1", "csi1_phy", "csi1_pix", "csi1_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid1" },
+		.interrupt = { "csid1" }
+	},
+};
+
+static const struct resources_ispif ispif_res = {
+	/* ISPIF */
+	.clock = { "camss_top_ahb", "camss_ahb", "ispif_ahb",
+		   "csi0", "csi0_pix", "csi0_rdi",
+		   "csi1", "csi1_pix", "csi1_rdi" },
+	.clock_for_reset = { "camss_vfe_vfe", "camss_csi_vfe" },
+	.reg = { "ispif", "csi_clk_mux" },
+	.interrupt = "ispif"
+
+};
+
+static const struct resources vfe_res = {
+	/* VFE0 */
+	.regulator = { NULL },
+	.clock = { "camss_top_ahb", "camss_vfe_vfe", "camss_csi_vfe",
+		   "iface", "bus", "camss_ahb" },
+	.clock_rate = { { 0 },
+			{ 50000000, 80000000, 100000000, 160000000,
+			  177780000, 200000000, 266670000, 320000000,
+			  400000000, 465000000 },
+			{ 0 },
+			{ 0 },
+			{ 0 },
+			{ 0 },
+			{ 0 },
+			{ 0 },
+			{ 0 } },
+	.reg = { "vfe0" },
+	.interrupt = { "vfe0" }
+};
+
+/*
+ * camss_add_clock_margin - Add margin to clock frequency rate
+ * @rate: Clock frequency rate
+ *
+ * When making calculations with physical clock frequency values
+ * some safety margin must be added. Add it.
+ */
+inline void camss_add_clock_margin(u64 *rate)
+{
+	*rate *= CAMSS_CLOCK_MARGIN_NUMERATOR;
+	*rate = div_u64(*rate, CAMSS_CLOCK_MARGIN_DENOMINATOR);
+}
+
+/*
+ * camss_enable_clocks - Enable multiple clocks
+ * @nclocks: Number of clocks in clock array
+ * @clock: Clock array
+ * @dev: Device
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int camss_enable_clocks(int nclocks, struct camss_clock *clock,
+			struct device *dev)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < nclocks; i++) {
+		ret = clk_prepare_enable(clock[i].clk);
+		if (ret) {
+			dev_err(dev, "clock enable failed: %d\n", ret);
+			goto error;
+		}
+	}
+
+	return 0;
+
+error:
+	for (i--; i >= 0; i--)
+		clk_disable_unprepare(clock[i].clk);
+
+	return ret;
+}
+
+/*
+ * camss_disable_clocks - Disable multiple clocks
+ * @nclocks: Number of clocks in clock array
+ * @clock: Clock array
+ */
+void camss_disable_clocks(int nclocks, struct camss_clock *clock)
+{
+	int i;
+
+	for (i = nclocks - 1; i >= 0; i--)
+		clk_disable_unprepare(clock[i].clk);
+}
+
+/*
+ * camss_find_sensor - Find a linked media entity which represents a sensor
+ * @entity: Media entity to start searching from
+ *
+ * Return a pointer to sensor media entity or NULL if not found
+ */
+static struct media_entity *camss_find_sensor(struct media_entity *entity)
+{
+	struct media_pad *pad;
+
+	while (1) {
+		pad = &entity->pads[0];
+		if (!(pad->flags & MEDIA_PAD_FL_SINK))
+			return NULL;
+
+		pad = media_entity_remote_pad(pad);
+		if (!pad || !is_media_entity_v4l2_subdev(pad->entity))
+			return NULL;
+
+		entity = pad->entity;
+
+		if (entity->function == MEDIA_ENT_F_CAM_SENSOR)
+			return entity;
+	}
+}
+
+/*
+ * camss_get_pixel_clock - Get pixel clock rate from sensor
+ * @entity: Media entity in the current pipeline
+ * @pixel_clock: Received pixel clock value
+ *
+ * Return 0 on success or a negative error code otherwise
+ */
+int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock)
+{
+	struct media_entity *sensor;
+	struct v4l2_subdev *subdev;
+	struct v4l2_ctrl *ctrl;
+
+	sensor = camss_find_sensor(entity);
+	if (!sensor)
+		return -ENODEV;
+
+	subdev = media_entity_to_v4l2_subdev(sensor);
+
+	ctrl = v4l2_ctrl_find(subdev->ctrl_handler, V4L2_CID_PIXEL_RATE);
+
+	if (!ctrl)
+		return -EINVAL;
+
+	*pixel_clock = v4l2_ctrl_g_ctrl_int64(ctrl);
+
+	return 0;
+}
+
+/*
+ * camss_of_parse_endpoint_node - Parse port endpoint node
+ * @dev: Device
+ * @node: Device node to be parsed
+ * @csd: Parsed data from port endpoint node
+ *
+ * Return 0 on success or a negative error code on failure
+ */
+static int camss_of_parse_endpoint_node(struct device *dev,
+					struct device_node *node,
+					struct camss_async_subdev *csd)
+{
+	struct csiphy_lanes_cfg *lncfg = &csd->interface.csi2.lane_cfg;
+	struct v4l2_fwnode_bus_mipi_csi2 *mipi_csi2;
+	struct v4l2_fwnode_endpoint vep = { { 0 } };
+	unsigned int i;
+
+	v4l2_fwnode_endpoint_parse(of_fwnode_handle(node), &vep);
+
+	csd->interface.csiphy_id = vep.base.port;
+
+	mipi_csi2 = &vep.bus.mipi_csi2;
+	lncfg->clk.pos = mipi_csi2->clock_lane;
+	lncfg->clk.pol = mipi_csi2->lane_polarities[0];
+	lncfg->num_data = mipi_csi2->num_data_lanes;
+
+	lncfg->data = devm_kcalloc(dev,
+				   lncfg->num_data, sizeof(*lncfg->data),
+				   GFP_KERNEL);
+	if (!lncfg->data)
+		return -ENOMEM;
+
+	for (i = 0; i < lncfg->num_data; i++) {
+		lncfg->data[i].pos = mipi_csi2->data_lanes[i];
+		lncfg->data[i].pol = mipi_csi2->lane_polarities[i + 1];
+	}
+
+	return 0;
+}
+
+/*
+ * camss_of_parse_ports - Parse ports node
+ * @dev: Device
+ * @notifier: v4l2_device notifier data
+ *
+ * Return number of "port" nodes found in "ports" node
+ */
+static int camss_of_parse_ports(struct device *dev,
+				struct v4l2_async_notifier *notifier)
+{
+	struct device_node *node = NULL;
+	struct device_node *remote = NULL;
+	unsigned int size, i;
+	int ret;
+
+	while ((node = of_graph_get_next_endpoint(dev->of_node, node)))
+		if (of_device_is_available(node))
+			notifier->num_subdevs++;
+
+	size = sizeof(*notifier->subdevs) * notifier->num_subdevs;
+	notifier->subdevs = devm_kzalloc(dev, size, GFP_KERNEL);
+	if (!notifier->subdevs) {
+		dev_err(dev, "Failed to allocate memory\n");
+		return -ENOMEM;
+	}
+
+	i = 0;
+	while ((node = of_graph_get_next_endpoint(dev->of_node, node))) {
+		struct camss_async_subdev *csd;
+
+		if (!of_device_is_available(node))
+			continue;
+
+		csd = devm_kzalloc(dev, sizeof(*csd), GFP_KERNEL);
+		if (!csd) {
+			of_node_put(node);
+			dev_err(dev, "Failed to allocate memory\n");
+			return -ENOMEM;
+		}
+
+		notifier->subdevs[i++] = &csd->asd;
+
+		ret = camss_of_parse_endpoint_node(dev, node, csd);
+		if (ret < 0) {
+			of_node_put(node);
+			return ret;
+		}
+
+		remote = of_graph_get_remote_port_parent(node);
+		of_node_put(node);
+
+		if (!remote) {
+			dev_err(dev, "Cannot get remote parent\n");
+			return -EINVAL;
+		}
+
+		csd->asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
+		csd->asd.match.fwnode = of_fwnode_handle(remote);
+	}
+
+	return notifier->num_subdevs;
+}
+
+/*
+ * camss_init_subdevices - Initialize subdev structures and resources
+ * @camss: CAMSS device
+ *
+ * Return 0 on success or a negative error code on failure
+ */
+static int camss_init_subdevices(struct camss *camss)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
+		ret = msm_csiphy_subdev_init(&camss->csiphy[i],
+					     &csiphy_res[i], i);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Failed to init csiphy%d sub-device: %d\n",
+				i, ret);
+			return ret;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
+		ret = msm_csid_subdev_init(&camss->csid[i],
+					   &csid_res[i], i);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Failed to init csid%d sub-device: %d\n",
+				i, ret);
+			return ret;
+		}
+	}
+
+	ret = msm_ispif_subdev_init(&camss->ispif, &ispif_res);
+	if (ret < 0) {
+		dev_err(camss->dev, "Failed to init ispif sub-device: %d\n",
+			ret);
+		return ret;
+	}
+
+	ret = msm_vfe_subdev_init(&camss->vfe, &vfe_res);
+	if (ret < 0) {
+		dev_err(camss->dev, "Fail to init vfe sub-device: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * camss_register_entities - Register subdev nodes and create links
+ * @camss: CAMSS device
+ *
+ * Return 0 on success or a negative error code on failure
+ */
+static int camss_register_entities(struct camss *camss)
+{
+	int i, j;
+	int ret;
+
+	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
+		ret = msm_csiphy_register_entity(&camss->csiphy[i],
+						 &camss->v4l2_dev);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Failed to register csiphy%d entity: %d\n",
+				i, ret);
+			goto err_reg_csiphy;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
+		ret = msm_csid_register_entity(&camss->csid[i],
+					       &camss->v4l2_dev);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Failed to register csid%d entity: %d\n",
+				i, ret);
+			goto err_reg_csid;
+		}
+	}
+
+	ret = msm_ispif_register_entities(&camss->ispif, &camss->v4l2_dev);
+	if (ret < 0) {
+		dev_err(camss->dev, "Failed to register ispif entities: %d\n",
+			ret);
+		goto err_reg_ispif;
+	}
+
+	ret = msm_vfe_register_entities(&camss->vfe, &camss->v4l2_dev);
+	if (ret < 0) {
+		dev_err(camss->dev, "Failed to register vfe entities: %d\n",
+			ret);
+		goto err_reg_vfe;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
+		for (j = 0; j < ARRAY_SIZE(camss->csid); j++) {
+			ret = media_create_pad_link(
+				&camss->csiphy[i].subdev.entity,
+				MSM_CSIPHY_PAD_SRC,
+				&camss->csid[j].subdev.entity,
+				MSM_CSID_PAD_SINK,
+				0);
+			if (ret < 0) {
+				dev_err(camss->dev,
+					"Failed to link %s->%s entities: %d\n",
+					camss->csiphy[i].subdev.entity.name,
+					camss->csid[j].subdev.entity.name,
+					ret);
+				goto err_link;
+			}
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
+		for (j = 0; j < ARRAY_SIZE(camss->ispif.line); j++) {
+			ret = media_create_pad_link(
+				&camss->csid[i].subdev.entity,
+				MSM_CSID_PAD_SRC,
+				&camss->ispif.line[j].subdev.entity,
+				MSM_ISPIF_PAD_SINK,
+				0);
+			if (ret < 0) {
+				dev_err(camss->dev,
+					"Failed to link %s->%s entities: %d\n",
+					camss->csid[i].subdev.entity.name,
+					camss->ispif.line[j].subdev.entity.name,
+					ret);
+				goto err_link;
+			}
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(camss->ispif.line); i++) {
+		for (j = 0; j < ARRAY_SIZE(camss->vfe.line); j++) {
+			ret = media_create_pad_link(
+				&camss->ispif.line[i].subdev.entity,
+				MSM_ISPIF_PAD_SRC,
+				&camss->vfe.line[j].subdev.entity,
+				MSM_VFE_PAD_SINK,
+				0);
+			if (ret < 0) {
+				dev_err(camss->dev,
+					"Failed to link %s->%s entities: %d\n",
+					camss->ispif.line[i].subdev.entity.name,
+					camss->vfe.line[j].subdev.entity.name,
+					ret);
+				goto err_link;
+			}
+		}
+	}
+
+	return 0;
+
+err_link:
+	msm_vfe_unregister_entities(&camss->vfe);
+err_reg_vfe:
+	msm_ispif_unregister_entities(&camss->ispif);
+err_reg_ispif:
+
+	i = ARRAY_SIZE(camss->csid);
+err_reg_csid:
+	for (i--; i >= 0; i--)
+		msm_csid_unregister_entity(&camss->csid[i]);
+
+	i = ARRAY_SIZE(camss->csiphy);
+err_reg_csiphy:
+	for (i--; i >= 0; i--)
+		msm_csiphy_unregister_entity(&camss->csiphy[i]);
+
+	return ret;
+}
+
+/*
+ * camss_unregister_entities - Unregister subdev nodes
+ * @camss: CAMSS device
+ *
+ * Return 0 on success or a negative error code on failure
+ */
+static void camss_unregister_entities(struct camss *camss)
+{
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++)
+		msm_csiphy_unregister_entity(&camss->csiphy[i]);
+
+	for (i = 0; i < ARRAY_SIZE(camss->csid); i++)
+		msm_csid_unregister_entity(&camss->csid[i]);
+
+	msm_ispif_unregister_entities(&camss->ispif);
+	msm_vfe_unregister_entities(&camss->vfe);
+}
+
+static int camss_subdev_notifier_bound(struct v4l2_async_notifier *async,
+				       struct v4l2_subdev *subdev,
+				       struct v4l2_async_subdev *asd)
+{
+	struct camss *camss = container_of(async, struct camss, notifier);
+	struct camss_async_subdev *csd =
+		container_of(asd, struct camss_async_subdev, asd);
+	u8 id = csd->interface.csiphy_id;
+	struct csiphy_device *csiphy = &camss->csiphy[id];
+
+	csiphy->cfg.csi2 = &csd->interface.csi2;
+	subdev->host_priv = csiphy;
+
+	return 0;
+}
+
+static int camss_subdev_notifier_complete(struct v4l2_async_notifier *async)
+{
+	struct camss *camss = container_of(async, struct camss, notifier);
+	struct v4l2_device *v4l2_dev = &camss->v4l2_dev;
+	struct v4l2_subdev *sd;
+	int ret;
+
+	list_for_each_entry(sd, &v4l2_dev->subdevs, list) {
+		if (sd->host_priv) {
+			struct media_entity *sensor = &sd->entity;
+			struct csiphy_device *csiphy =
+					(struct csiphy_device *) sd->host_priv;
+			struct media_entity *input = &csiphy->subdev.entity;
+			unsigned int i;
+
+			for (i = 0; i < sensor->num_pads; i++) {
+				if (sensor->pads[i].flags & MEDIA_PAD_FL_SOURCE)
+					break;
+			}
+			if (i == sensor->num_pads) {
+				dev_err(camss->dev,
+					"No source pad in external entity\n");
+				return -EINVAL;
+			}
+
+			ret = media_create_pad_link(sensor, i,
+				input, MSM_CSIPHY_PAD_SINK,
+				MEDIA_LNK_FL_IMMUTABLE | MEDIA_LNK_FL_ENABLED);
+			if (ret < 0) {
+				dev_err(camss->dev,
+					"Failed to link %s->%s entities: %d\n",
+					sensor->name, input->name, ret);
+				return ret;
+			}
+		}
+	}
+
+	ret = v4l2_device_register_subdev_nodes(&camss->v4l2_dev);
+	if (ret < 0)
+		return ret;
+
+	return media_device_register(&camss->media_dev);
+}
+
+static const struct v4l2_async_notifier_operations camss_subdev_notifier_ops = {
+	.bound = camss_subdev_notifier_bound,
+	.complete = camss_subdev_notifier_complete,
+};
+
+static const struct media_device_ops camss_media_ops = {
+	.link_notify = v4l2_pipeline_link_notify,
+};
+
+/*
+ * camss_probe - Probe CAMSS platform device
+ * @pdev: Pointer to CAMSS platform device
+ *
+ * Return 0 on success or a negative error code on failure
+ */
+static int camss_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct camss *camss;
+	int ret;
+
+	camss = kzalloc(sizeof(*camss), GFP_KERNEL);
+	if (!camss)
+		return -ENOMEM;
+
+	atomic_set(&camss->ref_count, 0);
+	camss->dev = dev;
+	platform_set_drvdata(pdev, camss);
+
+	ret = camss_of_parse_ports(dev, &camss->notifier);
+	if (ret < 0)
+		return ret;
+
+	ret = camss_init_subdevices(camss);
+	if (ret < 0)
+		return ret;
+
+	ret = dma_set_mask_and_coherent(dev, 0xffffffff);
+	if (ret)
+		return ret;
+
+	camss->media_dev.dev = camss->dev;
+	strlcpy(camss->media_dev.model, "Qualcomm Camera Subsystem",
+		sizeof(camss->media_dev.model));
+	camss->media_dev.ops = &camss_media_ops;
+	media_device_init(&camss->media_dev);
+
+	camss->v4l2_dev.mdev = &camss->media_dev;
+	ret = v4l2_device_register(camss->dev, &camss->v4l2_dev);
+	if (ret < 0) {
+		dev_err(dev, "Failed to register V4L2 device: %d\n", ret);
+		return ret;
+	}
+
+	ret = camss_register_entities(camss);
+	if (ret < 0)
+		goto err_register_entities;
+
+	if (camss->notifier.num_subdevs) {
+		camss->notifier.ops = &camss_subdev_notifier_ops;
+
+		ret = v4l2_async_notifier_register(&camss->v4l2_dev,
+						   &camss->notifier);
+		if (ret) {
+			dev_err(dev,
+				"Failed to register async subdev nodes: %d\n",
+				ret);
+			goto err_register_subdevs;
+		}
+	} else {
+		ret = v4l2_device_register_subdev_nodes(&camss->v4l2_dev);
+		if (ret < 0) {
+			dev_err(dev, "Failed to register subdev nodes: %d\n",
+				ret);
+			goto err_register_subdevs;
+		}
+
+		ret = media_device_register(&camss->media_dev);
+		if (ret < 0) {
+			dev_err(dev, "Failed to register media device: %d\n",
+				ret);
+			goto err_register_subdevs;
+		}
+	}
+
+	return 0;
+
+err_register_subdevs:
+	camss_unregister_entities(camss);
+err_register_entities:
+	v4l2_device_unregister(&camss->v4l2_dev);
+
+	return ret;
+}
+
+void camss_delete(struct camss *camss)
+{
+	v4l2_device_unregister(&camss->v4l2_dev);
+	media_device_unregister(&camss->media_dev);
+	media_device_cleanup(&camss->media_dev);
+
+	kfree(camss);
+}
+
+/*
+ * camss_remove - Remove CAMSS platform device
+ * @pdev: Pointer to CAMSS platform device
+ *
+ * Always returns 0.
+ */
+static int camss_remove(struct platform_device *pdev)
+{
+	struct camss *camss = platform_get_drvdata(pdev);
+
+	msm_vfe_stop_streaming(&camss->vfe);
+
+	v4l2_async_notifier_unregister(&camss->notifier);
+	camss_unregister_entities(camss);
+
+	if (atomic_read(&camss->ref_count) == 0)
+		camss_delete(camss);
+
+	return 0;
+}
+
+static const struct of_device_id camss_dt_match[] = {
+	{ .compatible = "qcom,msm8916-camss" },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(of, camss_dt_match);
+
+static struct platform_driver qcom_camss_driver = {
+	.probe = camss_probe,
+	.remove = camss_remove,
+	.driver = {
+		.name = "qcom-camss",
+		.of_match_table = camss_dt_match,
+	},
+};
+
+module_platform_driver(qcom_camss_driver);
+
+MODULE_ALIAS("platform:qcom-camss");
+MODULE_DESCRIPTION("Qualcomm Camera Subsystem driver");
+MODULE_AUTHOR("Todor Tomov <todor.tomov@linaro.org>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/platform/qcom/camss/camss.h b/drivers/media/platform/qcom/camss/camss.h
new file mode 100644
index 000000000000..0e7cfe6bfbe5
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss.h
@@ -0,0 +1,106 @@
+/*
+ * camss.h
+ *
+ * Qualcomm MSM Camera Subsystem - Core
+ *
+ * Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef QC_MSM_CAMSS_H
+#define QC_MSM_CAMSS_H
+
+#include <linux/types.h>
+#include <media/v4l2-async.h>
+#include <media/v4l2-device.h>
+#include <media/v4l2-subdev.h>
+#include <media/media-device.h>
+#include <media/media-entity.h>
+#include <linux/device.h>
+
+#include "camss-csid.h"
+#include "camss-csiphy.h"
+#include "camss-ispif.h"
+#include "camss-vfe.h"
+
+#define CAMSS_CSID_NUM 2
+#define CAMSS_CSIPHY_NUM 2
+
+#define to_camss(ptr_module)	\
+	container_of(ptr_module, struct camss, ptr_module)
+
+#define to_device(ptr_module)	\
+	(to_camss(ptr_module)->dev)
+
+#define module_pointer(ptr_module, index)	\
+	((const struct ptr_module##_device (*)[]) &(ptr_module[-(index)]))
+
+#define to_camss_index(ptr_module, index)	\
+	container_of(module_pointer(ptr_module, index),	\
+		     struct camss, ptr_module)
+
+#define to_device_index(ptr_module, index)	\
+	(to_camss_index(ptr_module, index)->dev)
+
+#define CAMSS_RES_MAX 15
+
+struct resources {
+	char *regulator[CAMSS_RES_MAX];
+	char *clock[CAMSS_RES_MAX];
+	u32 clock_rate[CAMSS_RES_MAX][CAMSS_RES_MAX];
+	char *reg[CAMSS_RES_MAX];
+	char *interrupt[CAMSS_RES_MAX];
+};
+
+struct resources_ispif {
+	char *clock[CAMSS_RES_MAX];
+	char *clock_for_reset[CAMSS_RES_MAX];
+	char *reg[CAMSS_RES_MAX];
+	char *interrupt;
+};
+
+struct camss {
+	struct v4l2_device v4l2_dev;
+	struct v4l2_async_notifier notifier;
+	struct media_device media_dev;
+	struct device *dev;
+	struct csiphy_device csiphy[CAMSS_CSIPHY_NUM];
+	struct csid_device csid[CAMSS_CSID_NUM];
+	struct ispif_device ispif;
+	struct vfe_device vfe;
+	atomic_t ref_count;
+};
+
+struct camss_camera_interface {
+	u8 csiphy_id;
+	struct csiphy_csi2_cfg csi2;
+};
+
+struct camss_async_subdev {
+	struct camss_camera_interface interface;
+	struct v4l2_async_subdev asd;
+};
+
+struct camss_clock {
+	struct clk *clk;
+	const char *name;
+	u32 *freq;
+	u32 nfreqs;
+};
+
+void camss_add_clock_margin(u64 *rate);
+int camss_enable_clocks(int nclocks, struct camss_clock *clock,
+			struct device *dev);
+void camss_disable_clocks(int nclocks, struct camss_clock *clock);
+int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock);
+void camss_delete(struct camss *camss);
+
+#endif /* QC_MSM_CAMSS_H */
-- 
cgit v1.2.3


From b873663bd85fff5e43bcedb5cc5360f2aa992e05 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:14 -0400
Subject: media: camss: Use SPDX license headers

Use SPDX license headers for all files of the Qualcomm CAMSS driver.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c   | 10 +---------
 drivers/media/platform/qcom/camss/camss-csid.h   | 10 +---------
 drivers/media/platform/qcom/camss/camss-csiphy.c | 10 +---------
 drivers/media/platform/qcom/camss/camss-csiphy.h | 10 +---------
 drivers/media/platform/qcom/camss/camss-ispif.c  | 10 +---------
 drivers/media/platform/qcom/camss/camss-ispif.h  | 10 +---------
 drivers/media/platform/qcom/camss/camss-vfe.c    | 10 +---------
 drivers/media/platform/qcom/camss/camss-vfe.h    | 10 +---------
 drivers/media/platform/qcom/camss/camss-video.c  | 10 +---------
 drivers/media/platform/qcom/camss/camss-video.h  | 10 +---------
 drivers/media/platform/qcom/camss/camss.c        | 10 +---------
 drivers/media/platform/qcom/camss/camss.h        | 10 +---------
 12 files changed, 12 insertions(+), 108 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 39ea27b9da3b..c0fef1787ad4 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-csid.c
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/clk.h>
 #include <linux/completion.h>
diff --git a/drivers/media/platform/qcom/camss/camss-csid.h b/drivers/media/platform/qcom/camss/camss-csid.h
index 8012222b81ad..ae1d045844fb 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.h
+++ b/drivers/media/platform/qcom/camss/camss-csid.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-csid.h
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2011-2014, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef QC_MSM_CAMSS_CSID_H
 #define QC_MSM_CAMSS_CSID_H
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 642de259dc6b..b37e69161712 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-csiphy.c
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2016-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/clk.h>
 #include <linux/delay.h>
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index 9a422095b773..76fa2395664c 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-csiphy.h
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2016-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef QC_MSM_CAMSS_CSIPHY_H
 #define QC_MSM_CAMSS_CSIPHY_H
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index 636d5e712037..5ad719d7e437 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-ispif.c
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/clk.h>
 #include <linux/completion.h>
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.h b/drivers/media/platform/qcom/camss/camss-ispif.h
index c90e1598943a..a5dfb4f27d0e 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.h
+++ b/drivers/media/platform/qcom/camss/camss-ispif.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-ispif.h
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2013-2014, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef QC_MSM_CAMSS_ISPIF_H
 #define QC_MSM_CAMSS_ISPIF_H
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 380b90bdd720..256dc2d42411 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-vfe.c
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/clk.h>
 #include <linux/completion.h>
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
index 5aa740741de8..6b4258d8761e 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.h
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-vfe.h
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef QC_MSM_CAMSS_VFE_H
 #define QC_MSM_CAMSS_VFE_H
diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
index 0e7b842854ec..16e74b2448fe 100644
--- a/drivers/media/platform/qcom/camss/camss-video.c
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss-video.c
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/slab.h>
 #include <media/media-entity.h>
diff --git a/drivers/media/platform/qcom/camss/camss-video.h b/drivers/media/platform/qcom/camss/camss-video.h
index 821c1ef6b5c7..aa35e8cc6fd5 100644
--- a/drivers/media/platform/qcom/camss/camss-video.h
+++ b/drivers/media/platform/qcom/camss/camss-video.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss-video.h
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef QC_MSM_CAMSS_VIDEO_H
 #define QC_MSM_CAMSS_VIDEO_H
diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
index d1d27fca2958..45285eb6842c 100644
--- a/drivers/media/platform/qcom/camss/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * camss.c
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #include <linux/clk.h>
 #include <linux/media-bus-format.h>
diff --git a/drivers/media/platform/qcom/camss/camss.h b/drivers/media/platform/qcom/camss/camss.h
index 0e7cfe6bfbe5..fb1c2f946e71 100644
--- a/drivers/media/platform/qcom/camss/camss.h
+++ b/drivers/media/platform/qcom/camss/camss.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * camss.h
  *
@@ -5,15 +6,6 @@
  *
  * Copyright (c) 2015, The Linux Foundation. All rights reserved.
  * Copyright (C) 2015-2018 Linaro Ltd.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
  */
 #ifndef QC_MSM_CAMSS_H
 #define QC_MSM_CAMSS_H
-- 
cgit v1.2.3


From 2d87e6c1b99c402360fdfe19ce4f579ab2f96adf Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Thu, 21 Jun 2018 21:13:38 +0200
Subject: gpu: ipu-v3: default to id 0 on missing OF alias

This is better than storing -ENODEV in the id number. This fixes SoCs
with only one IPU that don't specify an IPU alias in the device tree.

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/gpu/ipu-v3/ipu-common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 48685cddbad1..c73bd003f845 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -1401,6 +1401,8 @@ static int ipu_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	ipu->id = of_alias_get_id(np, "ipu");
+	if (ipu->id < 0)
+		ipu->id = 0;
 
 	if (of_device_is_compatible(np, "fsl,imx6qp-ipu") &&
 	    IS_ENABLED(CONFIG_DRM)) {
-- 
cgit v1.2.3


From 2004fc09b34128182ed26ec7b8f28190e5189061 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:15 -0400
Subject: media: camss: Fix OF node usage

of_graph_get_next_endpoint increases the refcount of the returned
node and decreases the refcount of the passed node. Take this into
account and use of_node_put properly.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
index 45285eb6842c..abf618489187 100644
--- a/drivers/media/platform/qcom/camss/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -296,6 +296,7 @@ static int camss_of_parse_ports(struct device *dev,
 		if (of_device_is_available(node))
 			notifier->num_subdevs++;
 
+	of_node_put(node);
 	size = sizeof(*notifier->subdevs) * notifier->num_subdevs;
 	notifier->subdevs = devm_kzalloc(dev, size, GFP_KERNEL);
 	if (!notifier->subdevs) {
@@ -326,16 +327,16 @@ static int camss_of_parse_ports(struct device *dev,
 		}
 
 		remote = of_graph_get_remote_port_parent(node);
-		of_node_put(node);
-
 		if (!remote) {
 			dev_err(dev, "Cannot get remote parent\n");
+			of_node_put(node);
 			return -EINVAL;
 		}
 
 		csd->asd.match_type = V4L2_ASYNC_MATCH_FWNODE;
 		csd->asd.match.fwnode = of_fwnode_handle(remote);
 	}
+	of_node_put(node);
 
 	return notifier->num_subdevs;
 }
-- 
cgit v1.2.3


From 5ba913b3fca8579d43c24d220d2f579cf3e992af Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:16 -0400
Subject: media: camss: csiphy: Ensure clock mux config is done before the rest

Add a write memory barier after clock mux config and before the rest
of the csiphy config.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csiphy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index b37e69161712..2a9adcd6ff3c 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -364,6 +364,7 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
 		val |= cfg->csid_id;
 	}
 	writel_relaxed(val, csiphy->base_clk_mux);
+	wmb();
 
 	writel_relaxed(0x1, csiphy->base +
 		       CAMSS_CSI_PHY_GLBL_T_INIT_CFG0);
-- 
cgit v1.2.3


From d9707ae2721da2867a81255cdfae812c5bb07d2a Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Tue, 31 Jul 2018 02:19:43 -0400
Subject: media: dt-bindings: media: qcom, camss: Unify the clock names

Use more logical clock names - similar to the names in documentation.
This will allow better handling of the clocks in the driver when support
for more hardware versions is added - equivalent clocks on different
hardware versions will have the same name.

Note: No dts is using this device (and clock names) yet.

CC: Rob Herring <robh+dt@kernel.org>
CC: Mark Rutland <mark.rutland@arm.com>
CC: devicetree@vger.kernel.org
Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../devicetree/bindings/media/qcom,camss.txt       | 24 +++++++++++-----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/qcom,camss.txt b/Documentation/devicetree/bindings/media/qcom,camss.txt
index cadecebc73f7..032e8ed81faa 100644
--- a/Documentation/devicetree/bindings/media/qcom,camss.txt
+++ b/Documentation/devicetree/bindings/media/qcom,camss.txt
@@ -53,7 +53,7 @@ Qualcomm Camera Subsystem
 	Usage: required
 	Value type: <stringlist>
 	Definition: Should contain the following entries:
-                - "camss_top_ahb"
+                - "top_ahb"
                 - "ispif_ahb"
                 - "csiphy0_timer"
                 - "csiphy1_timer"
@@ -67,11 +67,11 @@ Qualcomm Camera Subsystem
                 - "csi1_phy"
                 - "csi1_pix"
                 - "csi1_rdi"
-                - "camss_ahb"
-                - "camss_vfe_vfe"
-                - "camss_csi_vfe"
-                - "iface"
-                - "bus"
+                - "ahb"
+                - "vfe0"
+                - "csi_vfe0"
+                - "vfe_ahb"
+                - "vfe_axi"
 - vdda-supply:
 	Usage: required
 	Value type: <phandle>
@@ -161,7 +161,7 @@ Qualcomm Camera Subsystem
 			<&gcc GCC_CAMSS_CSI_VFE0_CLK>,
 			<&gcc GCC_CAMSS_VFE_AHB_CLK>,
 			<&gcc GCC_CAMSS_VFE_AXI_CLK>;
-                clock-names = "camss_top_ahb",
+                clock-names = "top_ahb",
                         "ispif_ahb",
                         "csiphy0_timer",
                         "csiphy1_timer",
@@ -175,11 +175,11 @@ Qualcomm Camera Subsystem
                         "csi1_phy",
                         "csi1_pix",
                         "csi1_rdi",
-                        "camss_ahb",
-                        "camss_vfe_vfe",
-                        "camss_csi_vfe",
-                        "iface",
-                        "bus";
+                        "ahb",
+                        "vfe0",
+                        "csi_vfe0",
+                        "vfe_ahb",
+                        "vfe_axi";
 		vdda-supply = <&pm8916_l2>;
 		iommus = <&apps_iommu 3>;
 		ports {
-- 
cgit v1.2.3


From 09a94865d4691726656909236b5d60b4e9dcc798 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:18 -0400
Subject: media: camss: Unify the clock names

Use more logical clock names - similar to the names in documentation.
This will allow better handling of the clocks in the driver when support
for more hardware versions is added - equivalent clocks on different
hardware versions will have the same name.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss.c | 20 ++++++++------------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
index abf618489187..0b663e009f8f 100644
--- a/drivers/media/platform/qcom/camss/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -32,8 +32,7 @@ static const struct resources csiphy_res[] = {
 	/* CSIPHY0 */
 	{
 		.regulator = { NULL },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "camss_ahb", "csiphy0_timer" },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy0_timer" },
 		.clock_rate = { { 0 },
 				{ 0 },
 				{ 0 },
@@ -45,8 +44,7 @@ static const struct resources csiphy_res[] = {
 	/* CSIPHY1 */
 	{
 		.regulator = { NULL },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "camss_ahb", "csiphy1_timer" },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy1_timer" },
 		.clock_rate = { { 0 },
 				{ 0 },
 				{ 0 },
@@ -60,8 +58,7 @@ static const struct resources csid_res[] = {
 	/* CSID0 */
 	{
 		.regulator = { "vdda" },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "csi0_ahb", "camss_ahb",
+		.clock = { "top_ahb", "ispif_ahb", "csi0_ahb", "ahb",
 			   "csi0", "csi0_phy", "csi0_pix", "csi0_rdi" },
 		.clock_rate = { { 0 },
 				{ 0 },
@@ -78,8 +75,7 @@ static const struct resources csid_res[] = {
 	/* CSID1 */
 	{
 		.regulator = { "vdda" },
-		.clock = { "camss_top_ahb", "ispif_ahb",
-			   "csi1_ahb", "camss_ahb",
+		.clock = { "top_ahb", "ispif_ahb", "csi1_ahb", "ahb",
 			   "csi1", "csi1_phy", "csi1_pix", "csi1_rdi" },
 		.clock_rate = { { 0 },
 				{ 0 },
@@ -96,10 +92,10 @@ static const struct resources csid_res[] = {
 
 static const struct resources_ispif ispif_res = {
 	/* ISPIF */
-	.clock = { "camss_top_ahb", "camss_ahb", "ispif_ahb",
+	.clock = { "top_ahb", "ahb", "ispif_ahb",
 		   "csi0", "csi0_pix", "csi0_rdi",
 		   "csi1", "csi1_pix", "csi1_rdi" },
-	.clock_for_reset = { "camss_vfe_vfe", "camss_csi_vfe" },
+	.clock_for_reset = { "vfe0", "csi_vfe0" },
 	.reg = { "ispif", "csi_clk_mux" },
 	.interrupt = "ispif"
 
@@ -108,8 +104,8 @@ static const struct resources_ispif ispif_res = {
 static const struct resources vfe_res = {
 	/* VFE0 */
 	.regulator = { NULL },
-	.clock = { "camss_top_ahb", "camss_vfe_vfe", "camss_csi_vfe",
-		   "iface", "bus", "camss_ahb" },
+	.clock = { "top_ahb", "vfe0", "csi_vfe0",
+		   "vfe_ahb", "vfe_axi", "ahb" },
 	.clock_rate = { { 0 },
 			{ 50000000, 80000000, 100000000, 160000000,
 			  177780000, 200000000, 266670000, 320000000,
-- 
cgit v1.2.3


From 7066647cdb4d3ea24fe6f34a9fc9812711eacba6 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:19 -0400
Subject: media: camss: csiphy: Update settle count calculation

Update settle count calculation as per specification.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csiphy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 2a9adcd6ff3c..6158ffd3b358 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -329,7 +329,7 @@ static u8 csiphy_settle_cnt_calc(struct csiphy_device *csiphy)
 	t_hs_settle = (t_hs_prepare_max + t_hs_prepare_zero_min) / 2;
 
 	timer_period = div_u64(1000000000000LL, csiphy->timer_clk_rate);
-	settle_cnt = t_hs_settle / timer_period;
+	settle_cnt = t_hs_settle / timer_period - 1;
 
 	return settle_cnt;
 }
-- 
cgit v1.2.3


From c628e78899ff8006b5f9d8206da54ed3bb994342 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:20 -0400
Subject: media: camss: csid: Configure data type and decode format properly

The CSID decodes the input data stream. When the input comes from
the Test Generator the format of the stream is set on the source
media pad. When the input comes from the CSIPHY the format is the
one on the sink media pad. Use the proper format for each case.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index c0fef1787ad4..3cde07e44af6 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -384,9 +384,6 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 		    !media_entity_remote_pad(&csid->pads[MSM_CSID_PAD_SINK]))
 			return -ENOLINK;
 
-		dt = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SRC].code)->
-								data_type;
-
 		if (tg->enabled) {
 			/* Config Test Generator */
 			struct v4l2_mbus_framefmt *f =
@@ -408,6 +405,9 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			writel_relaxed(val, csid->base +
 				       CAMSS_CSID_TG_DT_n_CGG_0(0));
 
+			dt = csid_get_fmt_entry(
+				csid->fmt[MSM_CSID_PAD_SRC].code)->data_type;
+
 			/* 5:0 data type */
 			val = dt;
 			writel_relaxed(val, csid->base +
@@ -417,6 +417,9 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			val = tg->payload_mode;
 			writel_relaxed(val, csid->base +
 				       CAMSS_CSID_TG_DT_n_CGG_2(0));
+
+			df = csid_get_fmt_entry(
+				csid->fmt[MSM_CSID_PAD_SRC].code)->decode_format;
 		} else {
 			struct csid_phy_config *phy = &csid->phy;
 
@@ -431,13 +434,16 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 
 			writel_relaxed(val,
 				       csid->base + CAMSS_CSID_CORE_CTRL_1);
+
+			dt = csid_get_fmt_entry(
+				csid->fmt[MSM_CSID_PAD_SINK].code)->data_type;
+			df = csid_get_fmt_entry(
+				csid->fmt[MSM_CSID_PAD_SINK].code)->decode_format;
 		}
 
 		/* Config LUT */
 
 		dt_shift = (cid % 4) * 8;
-		df = csid_get_fmt_entry(csid->fmt[MSM_CSID_PAD_SINK].code)->
-								decode_format;
 
 		val = readl_relaxed(csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
 		val &= ~(0xff << dt_shift);
-- 
cgit v1.2.3


From c9896b655177892cfaed2c0910fd55f44772ecad Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:21 -0400
Subject: media: camss: vfe: Fix to_vfe() macro member name

Use the member name which is "line" instead of the pointer argument.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-vfe.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 256dc2d42411..51ad3f8ce73d 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -30,7 +30,7 @@
 	((const struct vfe_line (*)[]) &(ptr_line[-(ptr_line->id)]))
 
 #define to_vfe(ptr_line)	\
-	container_of(vfe_line_array(ptr_line), struct vfe_device, ptr_line)
+	container_of(vfe_line_array(ptr_line), struct vfe_device, line)
 
 #define VFE_0_HW_VERSION		0x000
 
-- 
cgit v1.2.3


From a93e5f4fc8dfecd15df51ae176a77ce5b0db82b1 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:22 -0400
Subject: media: camss: vfe: Get line pointer as container of video_out

Simplify getting of the line pointer by using the container_of
macro instead of traversing media controller links.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-vfe.c | 38 +++------------------------
 1 file changed, 4 insertions(+), 34 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 51ad3f8ce73d..77167f11b655 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -2037,26 +2037,6 @@ exit:
 	mutex_unlock(&vfe->power_lock);
 }
 
-/*
- * vfe_video_pad_to_line - Get pointer to VFE line by media pad
- * @pad: Media pad
- *
- * Return pointer to vfe line structure
- */
-static struct vfe_line *vfe_video_pad_to_line(struct media_pad *pad)
-{
-	struct media_pad *vfe_pad;
-	struct v4l2_subdev *subdev;
-
-	vfe_pad = media_entity_remote_pad(pad);
-	if (vfe_pad == NULL)
-		return NULL;
-
-	subdev = media_entity_to_v4l2_subdev(vfe_pad->entity);
-
-	return container_of(subdev, struct vfe_line, subdev);
-}
-
 /*
  * vfe_queue_buffer - Add empty buffer
  * @vid: Video device structure
@@ -2070,16 +2050,11 @@ static struct vfe_line *vfe_video_pad_to_line(struct media_pad *pad)
 static int vfe_queue_buffer(struct camss_video *vid,
 			    struct camss_buffer *buf)
 {
-	struct vfe_device *vfe = &vid->camss->vfe;
-	struct vfe_line *line;
+	struct vfe_line *line = container_of(vid, struct vfe_line, video_out);
+	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output;
 	unsigned long flags;
 
-	line = vfe_video_pad_to_line(&vid->pad);
-	if (!line) {
-		dev_err(to_device(vfe), "Can not queue buffer\n");
-		return -1;
-	}
 	output = &line->output;
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
@@ -2104,16 +2079,11 @@ static int vfe_queue_buffer(struct camss_video *vid,
 static int vfe_flush_buffers(struct camss_video *vid,
 			     enum vb2_buffer_state state)
 {
-	struct vfe_device *vfe = &vid->camss->vfe;
-	struct vfe_line *line;
+	struct vfe_line *line = container_of(vid, struct vfe_line, video_out);
+	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output;
 	unsigned long flags;
 
-	line = vfe_video_pad_to_line(&vid->pad);
-	if (!line) {
-		dev_err(to_device(vfe),	"Can not flush buffers\n");
-		return -1;
-	}
 	output = &line->output;
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
-- 
cgit v1.2.3


From 06d690f092db28a7c83c9524010c42136e2bb37f Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:23 -0400
Subject: media: camss: vfe: Do not disable CAMIF when clearing its status

Use "no change" value when clearing CAMIF status and make sure
this is done before configuring the new command.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-vfe.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 77167f11b655..15a1a0100ba8 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -156,6 +156,7 @@
 #define VFE_0_CAMIF_CMD				0x2f4
 #define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
 #define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
+#define VFE_0_CAMIF_CMD_NO_CHANGE		3
 #define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	(1 << 2)
 #define VFE_0_CAMIF_CFG				0x2f8
 #define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		(1 << 6)
@@ -1021,8 +1022,10 @@ static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
 
 static void vfe_set_camif_cmd(struct vfe_device *vfe, u32 cmd)
 {
-	writel_relaxed(VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS,
+	writel_relaxed(VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS |
+		       VFE_0_CAMIF_CMD_NO_CHANGE,
 		       vfe->base + VFE_0_CAMIF_CMD);
+	wmb();
 
 	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
 }
-- 
cgit v1.2.3


From dc273f67b274499093e3da236e9749e4c33e78b6 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:24 -0400
Subject: media: dt-bindings: media: qcom,camss: Fix whitespaces

Use tabs.

CC: Rob Herring <robh+dt@kernel.org>
CC: Mark Rutland <mark.rutland@arm.com>
CC: devicetree@vger.kernel.org
Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../devicetree/bindings/media/qcom,camss.txt       | 92 +++++++++++-----------
 1 file changed, 46 insertions(+), 46 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/qcom,camss.txt b/Documentation/devicetree/bindings/media/qcom,camss.txt
index 032e8ed81faa..e938eb02274c 100644
--- a/Documentation/devicetree/bindings/media/qcom,camss.txt
+++ b/Documentation/devicetree/bindings/media/qcom,camss.txt
@@ -53,25 +53,25 @@ Qualcomm Camera Subsystem
 	Usage: required
 	Value type: <stringlist>
 	Definition: Should contain the following entries:
-                - "top_ahb"
-                - "ispif_ahb"
-                - "csiphy0_timer"
-                - "csiphy1_timer"
-                - "csi0_ahb"
-                - "csi0"
-                - "csi0_phy"
-                - "csi0_pix"
-                - "csi0_rdi"
-                - "csi1_ahb"
-                - "csi1"
-                - "csi1_phy"
-                - "csi1_pix"
-                - "csi1_rdi"
-                - "ahb"
-                - "vfe0"
-                - "csi_vfe0"
-                - "vfe_ahb"
-                - "vfe_axi"
+		- "top_ahb"
+		- "ispif_ahb"
+		- "csiphy0_timer"
+		- "csiphy1_timer"
+		- "csi0_ahb"
+		- "csi0"
+		- "csi0_phy"
+		- "csi0_pix"
+		- "csi0_rdi"
+		- "csi1_ahb"
+		- "csi1"
+		- "csi1_phy"
+		- "csi1_pix"
+		- "csi1_rdi"
+		- "ahb"
+		- "vfe0"
+		- "csi_vfe0"
+		- "vfe_ahb"
+		- "vfe_axi"
 - vdda-supply:
 	Usage: required
 	Value type: <phandle>
@@ -95,17 +95,17 @@ Qualcomm Camera Subsystem
 		- clock-lanes:
 			Usage: required
 			Value type: <u32>
-                        Definition: The physical clock lane index. The value
-                                    must always be <1> as the physical clock
-                                    lane is lane 1.
+			Definition: The physical clock lane index. The value
+				    must always be <1> as the physical clock
+				    lane is lane 1.
 		- data-lanes:
 			Usage: required
 			Value type: <prop-encoded-array>
-                        Definition: An array of physical data lanes indexes.
-                                    Position of an entry determines the logical
-                                    lane number, while the value of an entry
-                                    indicates physical lane index. Lane swapping
-                                    is supported.
+			Definition: An array of physical data lanes indexes.
+				    Position of an entry determines the logical
+				    lane number, while the value of an entry
+				    indicates physical lane index. Lane swapping
+				    is supported.
 
 * An Example
 
@@ -161,25 +161,25 @@ Qualcomm Camera Subsystem
 			<&gcc GCC_CAMSS_CSI_VFE0_CLK>,
 			<&gcc GCC_CAMSS_VFE_AHB_CLK>,
 			<&gcc GCC_CAMSS_VFE_AXI_CLK>;
-                clock-names = "top_ahb",
-                        "ispif_ahb",
-                        "csiphy0_timer",
-                        "csiphy1_timer",
-                        "csi0_ahb",
-                        "csi0",
-                        "csi0_phy",
-                        "csi0_pix",
-                        "csi0_rdi",
-                        "csi1_ahb",
-                        "csi1",
-                        "csi1_phy",
-                        "csi1_pix",
-                        "csi1_rdi",
-                        "ahb",
-                        "vfe0",
-                        "csi_vfe0",
-                        "vfe_ahb",
-                        "vfe_axi";
+		clock-names = "top_ahb",
+			"ispif_ahb",
+			"csiphy0_timer",
+			"csiphy1_timer",
+			"csi0_ahb",
+			"csi0",
+			"csi0_phy",
+			"csi0_pix",
+			"csi0_rdi",
+			"csi1_ahb",
+			"csi1",
+			"csi1_phy",
+			"csi1_pix",
+			"csi1_rdi",
+			"ahb",
+			"vfe0",
+			"csi_vfe0",
+			"vfe_ahb",
+			"vfe_axi";
 		vdda-supply = <&pm8916_l2>;
 		iommus = <&apps_iommu 3>;
 		ports {
-- 
cgit v1.2.3


From 21a3f6e531cc5e0fecd26f8e3f0835750426b7ad Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:25 -0400
Subject: media: dt-bindings: media: qcom,camss: Add 8996 bindings

Update binding document for MSM8996.

CC: Rob Herring <robh+dt@kernel.org>
CC: Mark Rutland <mark.rutland@arm.com>
CC: devicetree@vger.kernel.org
Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../devicetree/bindings/media/qcom,camss.txt       | 44 +++++++++++++++++++---
 1 file changed, 38 insertions(+), 6 deletions(-)

diff --git a/Documentation/devicetree/bindings/media/qcom,camss.txt b/Documentation/devicetree/bindings/media/qcom,camss.txt
index e938eb02274c..09eb6ed99114 100644
--- a/Documentation/devicetree/bindings/media/qcom,camss.txt
+++ b/Documentation/devicetree/bindings/media/qcom,camss.txt
@@ -5,8 +5,9 @@ Qualcomm Camera Subsystem
 - compatible:
 	Usage: required
 	Value type: <stringlist>
-	Definition: Should contain:
+	Definition: Should contain one of:
 		- "qcom,msm8916-camss"
+		- "qcom,msm8996-camss"
 - reg:
 	Usage: required
 	Value type: <prop-encoded-array>
@@ -19,11 +20,16 @@ Qualcomm Camera Subsystem
 		- "csiphy0_clk_mux"
 		- "csiphy1"
 		- "csiphy1_clk_mux"
+		- "csiphy2"		(8996 only)
+		- "csiphy2_clk_mux"	(8996 only)
 		- "csid0"
 		- "csid1"
+		- "csid2"		(8996 only)
+		- "csid3"		(8996 only)
 		- "ispif"
 		- "csi_clk_mux"
 		- "vfe0"
+		- "vfe1"		(8996 only)
 - interrupts:
 	Usage: required
 	Value type: <prop-encoded-array>
@@ -34,10 +40,14 @@ Qualcomm Camera Subsystem
 	Definition: Should contain the following entries:
 		- "csiphy0"
 		- "csiphy1"
+		- "csiphy2"		(8996 only)
 		- "csid0"
 		- "csid1"
+		- "csid2"		(8996 only)
+		- "csid3"		(8996 only)
 		- "ispif"
 		- "vfe0"
+		- "vfe1"		(8996 only)
 - power-domains:
 	Usage: required
 	Value type: <prop-encoded-array>
@@ -57,6 +67,7 @@ Qualcomm Camera Subsystem
 		- "ispif_ahb"
 		- "csiphy0_timer"
 		- "csiphy1_timer"
+		- "csiphy2_timer"	(8996 only)
 		- "csi0_ahb"
 		- "csi0"
 		- "csi0_phy"
@@ -67,9 +78,25 @@ Qualcomm Camera Subsystem
 		- "csi1_phy"
 		- "csi1_pix"
 		- "csi1_rdi"
+		- "csi2_ahb"		(8996 only)
+		- "csi2"		(8996 only)
+		- "csi2_phy"		(8996 only)
+		- "csi2_pix"		(8996 only)
+		- "csi2_rdi"		(8996 only)
+		- "csi3_ahb"		(8996 only)
+		- "csi3"		(8996 only)
+		- "csi3_phy"		(8996 only)
+		- "csi3_pix"		(8996 only)
+		- "csi3_rdi"		(8996 only)
 		- "ahb"
 		- "vfe0"
 		- "csi_vfe0"
+		- "vfe0_ahb",		(8996 only)
+		- "vfe0_stream",	(8996 only)
+		- "vfe1",		(8996 only)
+		- "csi_vfe1",		(8996 only)
+		- "vfe1_ahb",		(8996 only)
+		- "vfe1_stream",	(8996 only)
 		- "vfe_ahb"
 		- "vfe_axi"
 - vdda-supply:
@@ -90,14 +117,18 @@ Qualcomm Camera Subsystem
 		- reg:
 			Usage: required
 			Value type: <u32>
-			Definition: Selects CSI2 PHY interface - PHY0 or PHY1.
+			Definition: Selects CSI2 PHY interface - PHY0, PHY1
+				    or PHY2 (8996 only)
 	Endpoint node properties:
 		- clock-lanes:
 			Usage: required
 			Value type: <u32>
-			Definition: The physical clock lane index. The value
-				    must always be <1> as the physical clock
-				    lane is lane 1.
+			Definition: The physical clock lane index. On 8916
+				    the value must always be <1> as the physical
+				    clock lane is lane 1. On 8996 the value must
+				    always be <7> as the hardware supports D-PHY
+				    and C-PHY, indexes are in a common set and
+				    D-PHY physical clock lane is labeled as 7.
 		- data-lanes:
 			Usage: required
 			Value type: <prop-encoded-array>
@@ -105,7 +136,8 @@ Qualcomm Camera Subsystem
 				    Position of an entry determines the logical
 				    lane number, while the value of an entry
 				    indicates physical lane index. Lane swapping
-				    is supported.
+				    is supported. Physical lane indexes for
+				    8916: 0, 2, 3, 4; for 8996: 0, 1, 2, 3.
 
 * An Example
 
-- 
cgit v1.2.3


From 9c3e59de6041f84294fbead39c85b5541ac7b361 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:26 -0400
Subject: media: camss: Add 8x96 resources

Add structs with 8x96 resources. As the number of CSIPHY, CSID
and VFE hardware modules is different on 8x16 and 8x96 select
the number at runtime and allocate needed structures
dynamically.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c   |  20 +-
 drivers/media/platform/qcom/camss/camss-csid.h   |   3 +-
 drivers/media/platform/qcom/camss/camss-csiphy.c |  19 +-
 drivers/media/platform/qcom/camss/camss-csiphy.h |   4 +-
 drivers/media/platform/qcom/camss/camss-ispif.c  |  35 ++-
 drivers/media/platform/qcom/camss/camss-ispif.h  |   9 +-
 drivers/media/platform/qcom/camss/camss-vfe.c    |  61 ++--
 drivers/media/platform/qcom/camss/camss-vfe.h    |   4 +-
 drivers/media/platform/qcom/camss/camss.c        | 354 ++++++++++++++++++-----
 drivers/media/platform/qcom/camss/camss.h        |  20 +-
 10 files changed, 390 insertions(+), 139 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 3cde07e44af6..627ef44cf895 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -219,7 +219,7 @@ static irqreturn_t csid_isr(int irq, void *dev)
  */
 static int csid_set_clock_rates(struct csid_device *csid)
 {
-	struct device *dev = to_device_index(csid, csid->id);
+	struct device *dev = csid->camss->dev;
 	u32 pixel_clock;
 	int i, j;
 	int ret;
@@ -232,7 +232,9 @@ static int csid_set_clock_rates(struct csid_device *csid)
 		struct camss_clock *clock = &csid->clock[i];
 
 		if (!strcmp(clock->name, "csi0") ||
-			!strcmp(clock->name, "csi1")) {
+		    !strcmp(clock->name, "csi1") ||
+		    !strcmp(clock->name, "csi2") ||
+		    !strcmp(clock->name, "csi3")) {
 			u8 bpp = csid_get_fmt_entry(
 				csid->fmt[MSM_CSIPHY_PAD_SINK].code)->bpp;
 			u8 num_lanes = csid->phy.lane_cnt;
@@ -291,8 +293,7 @@ static int csid_reset(struct csid_device *csid)
 	time = wait_for_completion_timeout(&csid->reset_complete,
 		msecs_to_jiffies(CSID_RESET_TIMEOUT_MS));
 	if (!time) {
-		dev_err(to_device_index(csid, csid->id),
-			"CSID reset timeout\n");
+		dev_err(csid->camss->dev, "CSID reset timeout\n");
 		return -EIO;
 	}
 
@@ -309,7 +310,7 @@ static int csid_reset(struct csid_device *csid)
 static int csid_set_power(struct v4l2_subdev *sd, int on)
 {
 	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct device *dev = to_device_index(csid, csid->id);
+	struct device *dev = csid->camss->dev;
 	int ret;
 
 	if (on) {
@@ -375,7 +376,7 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 
 		ret = v4l2_ctrl_handler_setup(&csid->ctrls);
 		if (ret < 0) {
-			dev_err(to_device_index(csid, csid->id),
+			dev_err(csid->camss->dev,
 				"could not sync v4l2 controls: %d\n", ret);
 			return ret;
 		}
@@ -796,15 +797,16 @@ static const struct v4l2_ctrl_ops csid_ctrl_ops = {
  *
  * Return 0 on success or a negative error code otherwise
  */
-int msm_csid_subdev_init(struct csid_device *csid,
+int msm_csid_subdev_init(struct camss *camss, struct csid_device *csid,
 			 const struct resources *res, u8 id)
 {
-	struct device *dev = to_device_index(csid, id);
+	struct device *dev = camss->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *r;
 	int i, j;
 	int ret;
 
+	csid->camss = camss;
 	csid->id = id;
 
 	/* Memory */
@@ -1018,7 +1020,7 @@ int msm_csid_register_entity(struct csid_device *csid,
 {
 	struct v4l2_subdev *sd = &csid->subdev;
 	struct media_pad *pads = csid->pads;
-	struct device *dev = to_device_index(csid, csid->id);
+	struct device *dev = csid->camss->dev;
 	int ret;
 
 	v4l2_subdev_init(sd, &csid_v4l2_ops);
diff --git a/drivers/media/platform/qcom/camss/camss-csid.h b/drivers/media/platform/qcom/camss/camss-csid.h
index ae1d045844fb..ed605fd3bb87 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.h
+++ b/drivers/media/platform/qcom/camss/camss-csid.h
@@ -42,6 +42,7 @@ struct csid_phy_config {
 };
 
 struct csid_device {
+	struct camss *camss;
 	u8 id;
 	struct v4l2_subdev subdev;
 	struct media_pad pads[MSM_CSID_PADS_NUM];
@@ -61,7 +62,7 @@ struct csid_device {
 
 struct resources;
 
-int msm_csid_subdev_init(struct csid_device *csid,
+int msm_csid_subdev_init(struct camss *camss, struct csid_device *csid,
 			 const struct resources *res, u8 id);
 
 int msm_csid_register_entity(struct csid_device *csid,
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 6158ffd3b358..0383e94996a3 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -155,7 +155,7 @@ static irqreturn_t csiphy_isr(int irq, void *dev)
  */
 static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
 {
-	struct device *dev = to_device_index(csiphy, csiphy->id);
+	struct device *dev = csiphy->camss->dev;
 	u32 pixel_clock;
 	int i, j;
 	int ret;
@@ -168,7 +168,8 @@ static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
 		struct camss_clock *clock = &csiphy->clock[i];
 
 		if (!strcmp(clock->name, "csiphy0_timer") ||
-			!strcmp(clock->name, "csiphy1_timer")) {
+		    !strcmp(clock->name, "csiphy1_timer") ||
+		    !strcmp(clock->name, "csiphy2_timer")) {
 			u8 bpp = csiphy_get_bpp(
 					csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
 			u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
@@ -233,7 +234,7 @@ static void csiphy_reset(struct csiphy_device *csiphy)
 static int csiphy_set_power(struct v4l2_subdev *sd, int on)
 {
 	struct csiphy_device *csiphy = v4l2_get_subdevdata(sd);
-	struct device *dev = to_device_index(csiphy, csiphy->id);
+	struct device *dev = csiphy->camss->dev;
 
 	if (on) {
 		u8 hw_version;
@@ -311,12 +312,12 @@ static u8 csiphy_settle_cnt_calc(struct csiphy_device *csiphy)
 
 	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
 	if (ret) {
-		dev_err(to_device_index(csiphy, csiphy->id),
+		dev_err(csiphy->camss->dev,
 			"Cannot get CSI2 transmitter's pixel clock\n");
 		return 0;
 	}
 	if (!pixel_clock) {
-		dev_err(to_device_index(csiphy, csiphy->id),
+		dev_err(csiphy->camss->dev,
 			"Got pixel clock == 0, cannot continue\n");
 		return 0;
 	}
@@ -670,15 +671,17 @@ static int csiphy_init_formats(struct v4l2_subdev *sd,
  *
  * Return 0 on success or a negative error code otherwise
  */
-int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
+int msm_csiphy_subdev_init(struct camss *camss,
+			   struct csiphy_device *csiphy,
 			   const struct resources *res, u8 id)
 {
-	struct device *dev = to_device_index(csiphy, id);
+	struct device *dev = camss->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *r;
 	int i, j;
 	int ret;
 
+	csiphy->camss = camss;
 	csiphy->id = id;
 	csiphy->cfg.combo_mode = 0;
 
@@ -839,7 +842,7 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
 {
 	struct v4l2_subdev *sd = &csiphy->subdev;
 	struct media_pad *pads = csiphy->pads;
-	struct device *dev = to_device_index(csiphy, csiphy->id);
+	struct device *dev = csiphy->camss->dev;
 	int ret;
 
 	v4l2_subdev_init(sd, &csiphy_v4l2_ops);
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index 76fa2395664c..728dfef18676 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -42,6 +42,7 @@ struct csiphy_config {
 };
 
 struct csiphy_device {
+	struct camss *camss;
 	u8 id;
 	struct v4l2_subdev subdev;
 	struct media_pad pads[MSM_CSIPHY_PADS_NUM];
@@ -58,7 +59,8 @@ struct csiphy_device {
 
 struct resources;
 
-int msm_csiphy_subdev_init(struct csiphy_device *csiphy,
+int msm_csiphy_subdev_init(struct camss *camss,
+			   struct csiphy_device *csiphy,
 			   const struct resources *res, u8 id);
 
 int msm_csiphy_register_entity(struct csiphy_device *csiphy,
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index 5ad719d7e437..ed50cc55e3d5 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -23,12 +23,6 @@
 
 #define MSM_ISPIF_NAME "msm_ispif"
 
-#define ispif_line_array(ptr_line)	\
-	((const struct ispif_line (*)[]) &(ptr_line[-(ptr_line->id)]))
-
-#define to_ispif(ptr_line)	\
-	container_of(ispif_line_array(ptr_line), struct ispif_device, ptr_line)
-
 #define ISPIF_RST_CMD_0			0x008
 #define ISPIF_RST_CMD_0_STROBED_RST_EN		(1 << 0)
 #define ISPIF_RST_CMD_0_MISC_LOGIC_RST		(1 << 1)
@@ -225,7 +219,7 @@ static int ispif_reset(struct ispif_device *ispif)
 static int ispif_set_power(struct v4l2_subdev *sd, int on)
 {
 	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct ispif_device *ispif = to_ispif(line);
+	struct ispif_device *ispif = line->ispif;
 	struct device *dev = to_device(ispif);
 	int ret = 0;
 
@@ -611,7 +605,7 @@ static void ispif_set_intf_cmd(struct ispif_device *ispif, u8 cmd,
 static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct ispif_line *line = v4l2_get_subdevdata(sd);
-	struct ispif_device *ispif = to_ispif(line);
+	struct ispif_device *ispif = line->ispif;
 	enum ispif_intf intf = line->interface;
 	u8 csid = line->csid_id;
 	u8 vfe = line->vfe_id;
@@ -899,6 +893,24 @@ int msm_ispif_subdev_init(struct ispif_device *ispif,
 	int i;
 	int ret;
 
+	/* Number of ISPIF lines - same as number of CSID hardware modules */
+	if (to_camss(ispif)->version == CAMSS_8x16)
+		ispif->line_num = 2;
+	else if (to_camss(ispif)->version == CAMSS_8x96)
+		ispif->line_num = 4;
+	else
+		return -EINVAL;
+
+	ispif->line = kcalloc(ispif->line_num, sizeof(*ispif->line),
+			      GFP_KERNEL);
+	if (!ispif->line)
+		return -ENOMEM;
+
+	for (i = 0; i < ispif->line_num; i++) {
+		ispif->line[i].ispif = ispif;
+		ispif->line[i].id = i;
+	}
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
@@ -979,9 +991,6 @@ int msm_ispif_subdev_init(struct ispif_device *ispif,
 		clock->nfreqs = 0;
 	}
 
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++)
-		ispif->line[i].id = i;
-
 	mutex_init(&ispif->power_lock);
 	ispif->power_count = 0;
 
@@ -1100,7 +1109,7 @@ int msm_ispif_register_entities(struct ispif_device *ispif,
 	int ret;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
+	for (i = 0; i < ispif->line_num; i++) {
 		struct v4l2_subdev *sd = &ispif->line[i].subdev;
 		struct media_pad *pads = ispif->line[i].pads;
 
@@ -1161,7 +1170,7 @@ void msm_ispif_unregister_entities(struct ispif_device *ispif)
 	mutex_destroy(&ispif->power_lock);
 	mutex_destroy(&ispif->config_lock);
 
-	for (i = 0; i < ARRAY_SIZE(ispif->line); i++) {
+	for (i = 0; i < ispif->line_num; i++) {
 		struct v4l2_subdev *sd = &ispif->line[i].subdev;
 
 		v4l2_device_unregister_subdev(sd);
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.h b/drivers/media/platform/qcom/camss/camss-ispif.h
index a5dfb4f27d0e..9cd51dcb3ede 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.h
+++ b/drivers/media/platform/qcom/camss/camss-ispif.h
@@ -15,14 +15,11 @@
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
 
-/* Number of ISPIF lines - same as number of CSID hardware modules */
-#define MSM_ISPIF_LINE_NUM 2
-
 #define MSM_ISPIF_PAD_SINK 0
 #define MSM_ISPIF_PAD_SRC 1
 #define MSM_ISPIF_PADS_NUM 2
 
-#define MSM_ISPIF_VFE_NUM 1
+#define MSM_ISPIF_VFE_NUM 2
 
 enum ispif_intf {
 	PIX0,
@@ -38,6 +35,7 @@ struct ispif_intf_cmd_reg {
 };
 
 struct ispif_line {
+	struct ispif_device *ispif;
 	u8 id;
 	u8 csid_id;
 	u8 vfe_id;
@@ -61,7 +59,8 @@ struct ispif_device {
 	struct mutex power_lock;
 	struct ispif_intf_cmd_reg intf_cmd[MSM_ISPIF_VFE_NUM];
 	struct mutex config_lock;
-	struct ispif_line line[MSM_ISPIF_LINE_NUM];
+	unsigned int line_num;
+	struct ispif_line *line;
 };
 
 struct resources_ispif;
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 15a1a0100ba8..3f589c448cd2 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -877,7 +877,7 @@ static int vfe_reset(struct vfe_device *vfe)
 	time = wait_for_completion_timeout(&vfe->reset_complete,
 		msecs_to_jiffies(VFE_RESET_TIMEOUT_MS));
 	if (!time) {
-		dev_err(to_device(vfe), "VFE reset timeout\n");
+		dev_err(vfe->camss->dev, "VFE reset timeout\n");
 		return -EIO;
 	}
 
@@ -902,7 +902,7 @@ static int vfe_halt(struct vfe_device *vfe)
 	time = wait_for_completion_timeout(&vfe->halt_complete,
 		msecs_to_jiffies(VFE_HALT_TIMEOUT_MS));
 	if (!time) {
-		dev_err(to_device(vfe), "VFE halt timeout\n");
+		dev_err(vfe->camss->dev, "VFE halt timeout\n");
 		return -EIO;
 	}
 
@@ -1041,7 +1041,7 @@ static int vfe_camif_wait_for_stop(struct vfe_device *vfe)
 				 CAMIF_TIMEOUT_SLEEP_US,
 				 CAMIF_TIMEOUT_ALL_US);
 	if (ret < 0)
-		dev_err(to_device(vfe), "%s: camif stop timeout\n", __func__);
+		dev_err(vfe->camss->dev, "%s: camif stop timeout\n", __func__);
 
 	return ret;
 }
@@ -1209,7 +1209,7 @@ static void vfe_buf_update_wm_on_next(struct vfe_device *vfe,
 		break;
 	case VFE_OUTPUT_SINGLE:
 	default:
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Next buf in wrong state! %d\n",
 				    output->state);
 		break;
@@ -1229,7 +1229,7 @@ static void vfe_buf_update_wm_on_last(struct vfe_device *vfe,
 		vfe_output_frame_drop(vfe, output, 0);
 		break;
 	default:
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Last buff in wrong state! %d\n",
 				    output->state);
 		break;
@@ -1258,7 +1258,7 @@ static void vfe_buf_update_wm_on_new(struct vfe_device *vfe,
 			output->state = VFE_OUTPUT_CONTINUOUS;
 		} else {
 			vfe_buf_add_pending(output, new_buf);
-			dev_err_ratelimited(to_device(vfe),
+			dev_err_ratelimited(vfe->camss->dev,
 					    "Inactive buffer is busy\n");
 		}
 		break;
@@ -1273,7 +1273,7 @@ static void vfe_buf_update_wm_on_new(struct vfe_device *vfe,
 			output->state = VFE_OUTPUT_SINGLE;
 		} else {
 			vfe_buf_add_pending(output, new_buf);
-			dev_err_ratelimited(to_device(vfe),
+			dev_err_ratelimited(vfe->camss->dev,
 					    "Output idle with buffer set!\n");
 		}
 		break;
@@ -1297,7 +1297,7 @@ static int vfe_get_output(struct vfe_line *line)
 
 	output = &line->output;
 	if (output->state != VFE_OUTPUT_OFF) {
-		dev_err(to_device(vfe), "Output is running\n");
+		dev_err(vfe->camss->dev, "Output is running\n");
 		goto error;
 	}
 	output->state = VFE_OUTPUT_RESERVED;
@@ -1307,7 +1307,7 @@ static int vfe_get_output(struct vfe_line *line)
 	for (i = 0; i < output->wm_num; i++) {
 		wm_idx = vfe_reserve_wm(vfe, line->id);
 		if (wm_idx < 0) {
-			dev_err(to_device(vfe), "Can not reserve wm\n");
+			dev_err(vfe->camss->dev, "Can not reserve wm\n");
 			goto error_get_wm;
 		}
 		output->wm_idx[i] = wm_idx;
@@ -1371,7 +1371,7 @@ static int vfe_enable_output(struct vfe_line *line)
 	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line->id);
 
 	if (output->state != VFE_OUTPUT_RESERVED) {
-		dev_err(to_device(vfe), "Output is not in reserved state %d\n",
+		dev_err(vfe->camss->dev, "Output is not in reserved state %d\n",
 			output->state);
 		spin_unlock_irqrestore(&vfe->output_lock, flags);
 		return -EINVAL;
@@ -1471,7 +1471,7 @@ static int vfe_disable_output(struct vfe_line *line)
 	time = wait_for_completion_timeout(&output->sof,
 					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
 	if (!time)
-		dev_err(to_device(vfe), "VFE sof timeout\n");
+		dev_err(vfe->camss->dev, "VFE sof timeout\n");
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 	for (i = 0; i < output->wm_num; i++)
@@ -1484,7 +1484,7 @@ static int vfe_disable_output(struct vfe_line *line)
 	time = wait_for_completion_timeout(&output->reg_update,
 					   msecs_to_jiffies(VFE_NEXT_SOF_MS));
 	if (!time)
-		dev_err(to_device(vfe), "VFE reg update timeout\n");
+		dev_err(vfe->camss->dev, "VFE reg update timeout\n");
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
@@ -1698,14 +1698,14 @@ static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
 	if (vfe->wm_output_map[wm] == VFE_LINE_NONE) {
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Received wm done for unmapped index\n");
 		goto out_unlock;
 	}
 	output = &vfe->line[vfe->wm_output_map[wm]].output;
 
 	if (output->active_buf == active_index) {
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Active buffer mismatch!\n");
 		goto out_unlock;
 	}
@@ -1713,7 +1713,7 @@ static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
 
 	ready_buf = output->buf[!active_index];
 	if (!ready_buf) {
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "Missing ready buf %d %d!\n",
 				    !active_index, output->state);
 		goto out_unlock;
@@ -1799,7 +1799,7 @@ static irqreturn_t vfe_isr(int irq, void *dev)
 
 	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION) {
 		violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
-		dev_err_ratelimited(to_device(vfe),
+		dev_err_ratelimited(vfe->camss->dev,
 				    "VFE: violation = 0x%08x\n", violation);
 	}
 
@@ -1842,7 +1842,7 @@ static irqreturn_t vfe_isr(int irq, void *dev)
  */
 static int vfe_set_clock_rates(struct vfe_device *vfe)
 {
-	struct device *dev = to_device(vfe);
+	struct device *dev = vfe->camss->dev;
 	u32 pixel_clock[MSM_VFE_LINE_NUM];
 	int i, j;
 	int ret;
@@ -1857,7 +1857,8 @@ static int vfe_set_clock_rates(struct vfe_device *vfe)
 	for (i = 0; i < vfe->nclocks; i++) {
 		struct camss_clock *clock = &vfe->clock[i];
 
-		if (!strcmp(clock->name, "camss_vfe_vfe")) {
+		if (!strcmp(clock->name, "vfe0") ||
+		    !strcmp(clock->name, "vfe1")) {
 			u64 min_rate = 0;
 			long rate;
 
@@ -1935,7 +1936,8 @@ static int vfe_check_clock_rates(struct vfe_device *vfe)
 	for (i = 0; i < vfe->nclocks; i++) {
 		struct camss_clock *clock = &vfe->clock[i];
 
-		if (!strcmp(clock->name, "camss_vfe_vfe")) {
+		if (!strcmp(clock->name, "vfe0") ||
+		    !strcmp(clock->name, "vfe1")) {
 			u64 min_rate = 0;
 			unsigned long rate;
 
@@ -1984,7 +1986,7 @@ static int vfe_get(struct vfe_device *vfe)
 			goto error_clocks;
 
 		ret = camss_enable_clocks(vfe->nclocks, vfe->clock,
-					  to_device(vfe));
+					  vfe->camss->dev);
 		if (ret < 0)
 			goto error_clocks;
 
@@ -2024,7 +2026,7 @@ static void vfe_put(struct vfe_device *vfe)
 	mutex_lock(&vfe->power_lock);
 
 	if (vfe->power_count == 0) {
-		dev_err(to_device(vfe), "vfe power off on power_count == 0\n");
+		dev_err(vfe->camss->dev, "vfe power off on power_count == 0\n");
 		goto exit;
 	} else if (vfe->power_count == 1) {
 		if (vfe->was_streaming) {
@@ -2130,7 +2132,7 @@ static int vfe_set_power(struct v4l2_subdev *sd, int on)
 			return ret;
 
 		hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
-		dev_dbg(to_device(vfe),
+		dev_dbg(vfe->camss->dev,
 			"VFE HW Version = 0x%08x\n", hw_version);
 	} else {
 		vfe_put(vfe);
@@ -2157,12 +2159,12 @@ static int vfe_set_stream(struct v4l2_subdev *sd, int enable)
 	if (enable) {
 		ret = vfe_enable(line);
 		if (ret < 0)
-			dev_err(to_device(vfe),
+			dev_err(vfe->camss->dev,
 				"Failed to enable vfe outputs\n");
 	} else {
 		ret = vfe_disable(line);
 		if (ret < 0)
-			dev_err(to_device(vfe),
+			dev_err(vfe->camss->dev,
 				"Failed to disable vfe outputs\n");
 	}
 
@@ -2716,12 +2718,12 @@ static int vfe_init_formats(struct v4l2_subdev *sd, struct v4l2_subdev_fh *fh)
  *
  * Return 0 on success or a negative error code otherwise
  */
-int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res)
+int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
+			const struct resources *res, u8 id)
 {
-	struct device *dev = to_device(vfe);
+	struct device *dev = camss->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *r;
-	struct camss *camss = to_camss(vfe);
 	int i, j;
 	int ret;
 
@@ -2801,7 +2803,8 @@ int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res)
 
 	spin_lock_init(&vfe->output_lock);
 
-	vfe->id = 0;
+	vfe->camss = camss;
+	vfe->id = id;
 	vfe->reg_update = 0;
 
 	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
@@ -2933,7 +2936,7 @@ void msm_vfe_stop_streaming(struct vfe_device *vfe)
 int msm_vfe_register_entities(struct vfe_device *vfe,
 			      struct v4l2_device *v4l2_dev)
 {
-	struct device *dev = to_device(vfe);
+	struct device *dev = vfe->camss->dev;
 	struct v4l2_subdev *sd;
 	struct media_pad *pads;
 	struct camss_video *video_out;
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
index 6b4258d8761e..17d431e563da 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.h
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -79,6 +79,7 @@ struct vfe_line {
 };
 
 struct vfe_device {
+	struct camss *camss;
 	u8 id;
 	void __iomem *base;
 	u32 irq;
@@ -100,7 +101,8 @@ struct vfe_device {
 
 struct resources;
 
-int msm_vfe_subdev_init(struct vfe_device *vfe, const struct resources *res);
+int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
+			const struct resources *res, u8 id);
 
 int msm_vfe_register_entities(struct vfe_device *vfe,
 			      struct v4l2_device *v4l2_dev);
diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
index 0b663e009f8f..171e2c9d669e 100644
--- a/drivers/media/platform/qcom/camss/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -28,7 +28,7 @@
 #define CAMSS_CLOCK_MARGIN_NUMERATOR 105
 #define CAMSS_CLOCK_MARGIN_DENOMINATOR 100
 
-static const struct resources csiphy_res[] = {
+static const struct resources csiphy_res_8x16[] = {
 	/* CSIPHY0 */
 	{
 		.regulator = { NULL },
@@ -54,7 +54,7 @@ static const struct resources csiphy_res[] = {
 	}
 };
 
-static const struct resources csid_res[] = {
+static const struct resources csid_res_8x16[] = {
 	/* CSID0 */
 	{
 		.regulator = { "vdda" },
@@ -90,7 +90,7 @@ static const struct resources csid_res[] = {
 	},
 };
 
-static const struct resources_ispif ispif_res = {
+static const struct resources_ispif ispif_res_8x16 = {
 	/* ISPIF */
 	.clock = { "top_ahb", "ahb", "ispif_ahb",
 		   "csi0", "csi0_pix", "csi0_rdi",
@@ -101,24 +101,184 @@ static const struct resources_ispif ispif_res = {
 
 };
 
-static const struct resources vfe_res = {
+static const struct resources vfe_res_8x16[] = {
 	/* VFE0 */
-	.regulator = { NULL },
-	.clock = { "top_ahb", "vfe0", "csi_vfe0",
-		   "vfe_ahb", "vfe_axi", "ahb" },
-	.clock_rate = { { 0 },
-			{ 50000000, 80000000, 100000000, 160000000,
-			  177780000, 200000000, 266670000, 320000000,
-			  400000000, 465000000 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 },
-			{ 0 } },
-	.reg = { "vfe0" },
-	.interrupt = { "vfe0" }
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "vfe0", "csi_vfe0",
+			   "vfe_ahb", "vfe_axi", "ahb" },
+		.clock_rate = { { 0 },
+				{ 50000000, 80000000, 100000000, 160000000,
+				  177780000, 200000000, 266670000, 320000000,
+				  400000000, 465000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "vfe0" },
+		.interrupt = { "vfe0" }
+	}
+};
+
+static const struct resources csiphy_res_8x96[] = {
+	/* CSIPHY0 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy0_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 } },
+		.reg = { "csiphy0", "csiphy0_clk_mux" },
+		.interrupt = { "csiphy0" }
+	},
+
+	/* CSIPHY1 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy1_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 } },
+		.reg = { "csiphy1", "csiphy1_clk_mux" },
+		.interrupt = { "csiphy1" }
+	},
+
+	/* CSIPHY2 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ispif_ahb", "ahb", "csiphy2_timer" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 } },
+		.reg = { "csiphy2", "csiphy2_clk_mux" },
+		.interrupt = { "csiphy2" }
+	}
+};
+
+static const struct resources csid_res_8x96[] = {
+	/* CSID0 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi0_ahb", "ahb",
+			   "csi0", "csi0_phy", "csi0_pix", "csi0_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid0" },
+		.interrupt = { "csid0" }
+	},
+
+	/* CSID1 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi1_ahb", "ahb",
+			   "csi1", "csi1_phy", "csi1_pix", "csi1_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid1" },
+		.interrupt = { "csid1" }
+	},
+
+	/* CSID2 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi2_ahb", "ahb",
+			   "csi2", "csi2_phy", "csi2_pix", "csi2_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid2" },
+		.interrupt = { "csid2" }
+	},
+
+	/* CSID3 */
+	{
+		.regulator = { "vdda" },
+		.clock = { "top_ahb", "ispif_ahb", "csi3_ahb", "ahb",
+			   "csi3", "csi3_phy", "csi3_pix", "csi3_rdi" },
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 100000000, 200000000, 266666667 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "csid3" },
+		.interrupt = { "csid3" }
+	}
+};
+
+static const struct resources_ispif ispif_res_8x96 = {
+	/* ISPIF */
+	.clock = { "top_ahb", "ahb", "ispif_ahb",
+		   "csi0", "csi0_pix", "csi0_rdi",
+		   "csi1", "csi1_pix", "csi1_rdi",
+		   "csi2", "csi2_pix", "csi2_rdi",
+		   "csi3", "csi3_pix", "csi3_rdi" },
+	.clock_for_reset = { "vfe0", "csi_vfe0", "vfe1", "csi_vfe1" },
+	.reg = { "ispif", "csi_clk_mux" },
+	.interrupt = "ispif"
+};
+
+static const struct resources vfe_res_8x96[] = {
+	/* VFE0 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ahb", "vfe0", "csi_vfe0", "vfe_ahb",
+			   "vfe0_ahb", "vfe_axi", "vfe0_stream"},
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 75000000, 100000000, 300000000,
+				  320000000, 480000000, 600000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "vfe0" },
+		.interrupt = { "vfe0" }
+	},
+
+	/* VFE1 */
+	{
+		.regulator = { NULL },
+		.clock = { "top_ahb", "ahb", "vfe1", "csi_vfe1", "vfe_ahb",
+			   "vfe1_ahb", "vfe_axi", "vfe1_stream"},
+		.clock_rate = { { 0 },
+				{ 0 },
+				{ 75000000, 100000000, 300000000,
+				  320000000, 480000000, 600000000 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 },
+				{ 0 } },
+		.reg = { "vfe1" },
+		.interrupt = { "vfe1" }
+	}
 };
 
 /*
@@ -345,11 +505,29 @@ static int camss_of_parse_ports(struct device *dev,
  */
 static int camss_init_subdevices(struct camss *camss)
 {
+	const struct resources *csiphy_res;
+	const struct resources *csid_res;
+	const struct resources_ispif *ispif_res;
+	const struct resources *vfe_res;
 	unsigned int i;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
-		ret = msm_csiphy_subdev_init(&camss->csiphy[i],
+	if (camss->version == CAMSS_8x16) {
+		csiphy_res = csiphy_res_8x16;
+		csid_res = csid_res_8x16;
+		ispif_res = &ispif_res_8x16;
+		vfe_res = vfe_res_8x16;
+	} else if (camss->version == CAMSS_8x96) {
+		csiphy_res = csiphy_res_8x96;
+		csid_res = csid_res_8x96;
+		ispif_res = &ispif_res_8x96;
+		vfe_res = vfe_res_8x96;
+	} else {
+		return -EINVAL;
+	}
+
+	for (i = 0; i < camss->csiphy_num; i++) {
+		ret = msm_csiphy_subdev_init(camss, &camss->csiphy[i],
 					     &csiphy_res[i], i);
 		if (ret < 0) {
 			dev_err(camss->dev,
@@ -359,8 +537,8 @@ static int camss_init_subdevices(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
-		ret = msm_csid_subdev_init(&camss->csid[i],
+	for (i = 0; i < camss->csid_num; i++) {
+		ret = msm_csid_subdev_init(camss, &camss->csid[i],
 					   &csid_res[i], i);
 		if (ret < 0) {
 			dev_err(camss->dev,
@@ -370,17 +548,21 @@ static int camss_init_subdevices(struct camss *camss)
 		}
 	}
 
-	ret = msm_ispif_subdev_init(&camss->ispif, &ispif_res);
+	ret = msm_ispif_subdev_init(&camss->ispif, ispif_res);
 	if (ret < 0) {
 		dev_err(camss->dev, "Failed to init ispif sub-device: %d\n",
 			ret);
 		return ret;
 	}
 
-	ret = msm_vfe_subdev_init(&camss->vfe, &vfe_res);
-	if (ret < 0) {
-		dev_err(camss->dev, "Fail to init vfe sub-device: %d\n", ret);
-		return ret;
+	for (i = 0; i < camss->vfe_num; i++) {
+		ret = msm_vfe_subdev_init(camss, &camss->vfe[i],
+					  &vfe_res[i], i);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Fail to init vfe%d sub-device: %d\n", i, ret);
+			return ret;
+		}
 	}
 
 	return 0;
@@ -394,10 +576,10 @@ static int camss_init_subdevices(struct camss *camss)
  */
 static int camss_register_entities(struct camss *camss)
 {
-	int i, j;
+	int i, j, k;
 	int ret;
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
+	for (i = 0; i < camss->csiphy_num; i++) {
 		ret = msm_csiphy_register_entity(&camss->csiphy[i],
 						 &camss->v4l2_dev);
 		if (ret < 0) {
@@ -408,7 +590,7 @@ static int camss_register_entities(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
+	for (i = 0; i < camss->csid_num; i++) {
 		ret = msm_csid_register_entity(&camss->csid[i],
 					       &camss->v4l2_dev);
 		if (ret < 0) {
@@ -426,15 +608,19 @@ static int camss_register_entities(struct camss *camss)
 		goto err_reg_ispif;
 	}
 
-	ret = msm_vfe_register_entities(&camss->vfe, &camss->v4l2_dev);
-	if (ret < 0) {
-		dev_err(camss->dev, "Failed to register vfe entities: %d\n",
-			ret);
-		goto err_reg_vfe;
+	for (i = 0; i < camss->vfe_num; i++) {
+		ret = msm_vfe_register_entities(&camss->vfe[i],
+						&camss->v4l2_dev);
+		if (ret < 0) {
+			dev_err(camss->dev,
+				"Failed to register vfe%d entities: %d\n",
+				i, ret);
+			goto err_reg_vfe;
+		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->csid); j++) {
+	for (i = 0; i < camss->csiphy_num; i++) {
+		for (j = 0; j < camss->csid_num; j++) {
 			ret = media_create_pad_link(
 				&camss->csiphy[i].subdev.entity,
 				MSM_CSIPHY_PAD_SRC,
@@ -452,8 +638,8 @@ static int camss_register_entities(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->ispif.line); j++) {
+	for (i = 0; i < camss->csid_num; i++) {
+		for (j = 0; j < camss->ispif.line_num; j++) {
 			ret = media_create_pad_link(
 				&camss->csid[i].subdev.entity,
 				MSM_CSID_PAD_SRC,
@@ -471,39 +657,42 @@ static int camss_register_entities(struct camss *camss)
 		}
 	}
 
-	for (i = 0; i < ARRAY_SIZE(camss->ispif.line); i++) {
-		for (j = 0; j < ARRAY_SIZE(camss->vfe.line); j++) {
-			ret = media_create_pad_link(
-				&camss->ispif.line[i].subdev.entity,
-				MSM_ISPIF_PAD_SRC,
-				&camss->vfe.line[j].subdev.entity,
-				MSM_VFE_PAD_SINK,
-				0);
-			if (ret < 0) {
-				dev_err(camss->dev,
-					"Failed to link %s->%s entities: %d\n",
-					camss->ispif.line[i].subdev.entity.name,
-					camss->vfe.line[j].subdev.entity.name,
-					ret);
-				goto err_link;
+	for (i = 0; i < camss->ispif.line_num; i++)
+		for (k = 0; k < camss->vfe_num; k++)
+			for (j = 0; j < ARRAY_SIZE(camss->vfe[k].line); j++) {
+				ret = media_create_pad_link(
+					&camss->ispif.line[i].subdev.entity,
+					MSM_ISPIF_PAD_SRC,
+					&camss->vfe[k].line[j].subdev.entity,
+					MSM_VFE_PAD_SINK,
+					0);
+				if (ret < 0) {
+					dev_err(camss->dev,
+						"Failed to link %s->%s entities: %d\n",
+						camss->ispif.line[i].subdev.entity.name,
+						camss->vfe[k].line[j].subdev.entity.name,
+						ret);
+					goto err_link;
+				}
 			}
-		}
-	}
 
 	return 0;
 
 err_link:
-	msm_vfe_unregister_entities(&camss->vfe);
+	i = camss->vfe_num;
 err_reg_vfe:
+	for (i--; i >= 0; i--)
+		msm_vfe_unregister_entities(&camss->vfe[i]);
+
 	msm_ispif_unregister_entities(&camss->ispif);
 err_reg_ispif:
 
-	i = ARRAY_SIZE(camss->csid);
+	i = camss->csid_num;
 err_reg_csid:
 	for (i--; i >= 0; i--)
 		msm_csid_unregister_entity(&camss->csid[i]);
 
-	i = ARRAY_SIZE(camss->csiphy);
+	i = camss->csiphy_num;
 err_reg_csiphy:
 	for (i--; i >= 0; i--)
 		msm_csiphy_unregister_entity(&camss->csiphy[i]);
@@ -521,14 +710,16 @@ static void camss_unregister_entities(struct camss *camss)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(camss->csiphy); i++)
+	for (i = 0; i < camss->csiphy_num; i++)
 		msm_csiphy_unregister_entity(&camss->csiphy[i]);
 
-	for (i = 0; i < ARRAY_SIZE(camss->csid); i++)
+	for (i = 0; i < camss->csid_num; i++)
 		msm_csid_unregister_entity(&camss->csid[i]);
 
 	msm_ispif_unregister_entities(&camss->ispif);
-	msm_vfe_unregister_entities(&camss->vfe);
+
+	for (i = 0; i < camss->vfe_num; i++)
+		msm_vfe_unregister_entities(&camss->vfe[i]);
 }
 
 static int camss_subdev_notifier_bound(struct v4l2_async_notifier *async,
@@ -620,6 +811,35 @@ static int camss_probe(struct platform_device *pdev)
 	camss->dev = dev;
 	platform_set_drvdata(pdev, camss);
 
+	if (of_device_is_compatible(dev->of_node, "qcom,msm8916-camss")) {
+		camss->version = CAMSS_8x16;
+		camss->csiphy_num = 2;
+		camss->csid_num = 2;
+		camss->vfe_num = 1;
+	} else if (of_device_is_compatible(dev->of_node,
+					   "qcom,msm8996-camss")) {
+		camss->version = CAMSS_8x96;
+		camss->csiphy_num = 3;
+		camss->csid_num = 4;
+		camss->vfe_num = 2;
+	} else {
+		return -EINVAL;
+	}
+
+	camss->csiphy = kcalloc(camss->csiphy_num, sizeof(*camss->csiphy),
+				GFP_KERNEL);
+	if (!camss->csiphy)
+		return -ENOMEM;
+
+	camss->csid = kcalloc(camss->csid_num, sizeof(*camss->csid),
+			      GFP_KERNEL);
+	if (!camss->csid)
+		return -ENOMEM;
+
+	camss->vfe = kcalloc(camss->vfe_num, sizeof(*camss->vfe), GFP_KERNEL);
+	if (!camss->vfe)
+		return -ENOMEM;
+
 	ret = camss_of_parse_ports(dev, &camss->notifier);
 	if (ret < 0)
 		return ret;
@@ -703,9 +923,12 @@ void camss_delete(struct camss *camss)
  */
 static int camss_remove(struct platform_device *pdev)
 {
+	unsigned int i;
+
 	struct camss *camss = platform_get_drvdata(pdev);
 
-	msm_vfe_stop_streaming(&camss->vfe);
+	for (i = 0; i < camss->vfe_num; i++)
+		msm_vfe_stop_streaming(&camss->vfe[i]);
 
 	v4l2_async_notifier_unregister(&camss->notifier);
 	camss_unregister_entities(camss);
@@ -718,6 +941,7 @@ static int camss_remove(struct platform_device *pdev)
 
 static const struct of_device_id camss_dt_match[] = {
 	{ .compatible = "qcom,msm8916-camss" },
+	{ .compatible = "qcom,msm8996-camss" },
 	{ }
 };
 
diff --git a/drivers/media/platform/qcom/camss/camss.h b/drivers/media/platform/qcom/camss/camss.h
index fb1c2f946e71..dff1045a8a77 100644
--- a/drivers/media/platform/qcom/camss/camss.h
+++ b/drivers/media/platform/qcom/camss/camss.h
@@ -23,9 +23,6 @@
 #include "camss-ispif.h"
 #include "camss-vfe.h"
 
-#define CAMSS_CSID_NUM 2
-#define CAMSS_CSIPHY_NUM 2
-
 #define to_camss(ptr_module)	\
 	container_of(ptr_module, struct camss, ptr_module)
 
@@ -42,7 +39,7 @@
 #define to_device_index(ptr_module, index)	\
 	(to_camss_index(ptr_module, index)->dev)
 
-#define CAMSS_RES_MAX 15
+#define CAMSS_RES_MAX 17
 
 struct resources {
 	char *regulator[CAMSS_RES_MAX];
@@ -59,15 +56,24 @@ struct resources_ispif {
 	char *interrupt;
 };
 
+enum camss_version {
+	CAMSS_8x16,
+	CAMSS_8x96,
+};
+
 struct camss {
+	enum camss_version version;
 	struct v4l2_device v4l2_dev;
 	struct v4l2_async_notifier notifier;
 	struct media_device media_dev;
 	struct device *dev;
-	struct csiphy_device csiphy[CAMSS_CSIPHY_NUM];
-	struct csid_device csid[CAMSS_CSID_NUM];
+	int csiphy_num;
+	struct csiphy_device *csiphy;
+	int csid_num;
+	struct csid_device *csid;
 	struct ispif_device ispif;
-	struct vfe_device vfe;
+	int vfe_num;
+	struct vfe_device *vfe;
 	atomic_t ref_count;
 };
 
-- 
cgit v1.2.3


From 02afa816dbbf0bc648d22a8472f17236df886af5 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:27 -0400
Subject: media: camss: Add basic runtime PM support

There is a PM domain for each of the VFE hardware modules. Add
support for basic runtime PM support to be able to control the
PM domains. When a PM domain needs to be powered on - a device
link is created. When a PM domain needs to be powered off -
its device link is removed. This allows separate and
independent control of the PM domains.

Suspend/Resume is still not supported.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c   | 13 ++++-
 drivers/media/platform/qcom/camss/camss-csiphy.c | 15 +++++-
 drivers/media/platform/qcom/camss/camss-ispif.c  | 26 ++++++++--
 drivers/media/platform/qcom/camss/camss-vfe.c    | 17 +++++++
 drivers/media/platform/qcom/camss/camss.c        | 63 ++++++++++++++++++++++++
 drivers/media/platform/qcom/camss/camss.h        | 11 +++++
 6 files changed, 139 insertions(+), 6 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 627ef44cf895..3ba087fd95a1 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/regulator/consumer.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
@@ -316,19 +317,27 @@ static int csid_set_power(struct v4l2_subdev *sd, int on)
 	if (on) {
 		u32 hw_version;
 
-		ret = regulator_enable(csid->vdda);
+		ret = pm_runtime_get_sync(dev);
 		if (ret < 0)
 			return ret;
 
+		ret = regulator_enable(csid->vdda);
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
+			return ret;
+		}
+
 		ret = csid_set_clock_rates(csid);
 		if (ret < 0) {
 			regulator_disable(csid->vdda);
+			pm_runtime_put_sync(dev);
 			return ret;
 		}
 
 		ret = camss_enable_clocks(csid->nclocks, csid->clock, dev);
 		if (ret < 0) {
 			regulator_disable(csid->vdda);
+			pm_runtime_put_sync(dev);
 			return ret;
 		}
 
@@ -339,6 +348,7 @@ static int csid_set_power(struct v4l2_subdev *sd, int on)
 			disable_irq(csid->irq);
 			camss_disable_clocks(csid->nclocks, csid->clock);
 			regulator_disable(csid->vdda);
+			pm_runtime_put_sync(dev);
 			return ret;
 		}
 
@@ -348,6 +358,7 @@ static int csid_set_power(struct v4l2_subdev *sd, int on)
 		disable_irq(csid->irq);
 		camss_disable_clocks(csid->nclocks, csid->clock);
 		ret = regulator_disable(csid->vdda);
+		pm_runtime_put_sync(dev);
 	}
 
 	return ret;
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 0383e94996a3..4aeaedb69786 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
@@ -240,13 +241,21 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
 		u8 hw_version;
 		int ret;
 
-		ret = csiphy_set_clock_rates(csiphy);
+		ret = pm_runtime_get_sync(dev);
 		if (ret < 0)
 			return ret;
 
+		ret = csiphy_set_clock_rates(csiphy);
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
+			return ret;
+		}
+
 		ret = camss_enable_clocks(csiphy->nclocks, csiphy->clock, dev);
-		if (ret < 0)
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
 			return ret;
+		}
 
 		enable_irq(csiphy->irq);
 
@@ -259,6 +268,8 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
 		disable_irq(csiphy->irq);
 
 		camss_disable_clocks(csiphy->nclocks, csiphy->clock);
+
+		pm_runtime_put_sync(dev);
 	}
 
 	return 0;
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index ed50cc55e3d5..2c6c0d2d6acf 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -14,6 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/mutex.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-subdev.h>
@@ -169,6 +170,14 @@ static int ispif_reset(struct ispif_device *ispif)
 	u32 val;
 	int ret;
 
+	ret = camss_pm_domain_on(to_camss(ispif), PM_DOMAIN_VFE0);
+	if (ret < 0)
+		return ret;
+
+	ret = camss_pm_domain_on(to_camss(ispif), PM_DOMAIN_VFE1);
+	if (ret < 0)
+		return ret;
+
 	ret = camss_enable_clocks(ispif->nclocks_for_reset,
 				  ispif->clock_for_reset,
 				  to_device(ispif));
@@ -201,12 +210,15 @@ static int ispif_reset(struct ispif_device *ispif)
 		msecs_to_jiffies(ISPIF_RESET_TIMEOUT_MS));
 	if (!time) {
 		dev_err(to_device(ispif), "ISPIF reset timeout\n");
-		return -EIO;
+		ret = -EIO;
 	}
 
 	camss_disable_clocks(ispif->nclocks_for_reset, ispif->clock_for_reset);
 
-	return 0;
+	camss_pm_domain_off(to_camss(ispif), PM_DOMAIN_VFE0);
+	camss_pm_domain_off(to_camss(ispif), PM_DOMAIN_VFE1);
+
+	return ret;
 }
 
 /*
@@ -232,12 +244,19 @@ static int ispif_set_power(struct v4l2_subdev *sd, int on)
 			goto exit;
 		}
 
-		ret = camss_enable_clocks(ispif->nclocks, ispif->clock, dev);
+		ret = pm_runtime_get_sync(dev);
 		if (ret < 0)
 			goto exit;
 
+		ret = camss_enable_clocks(ispif->nclocks, ispif->clock, dev);
+		if (ret < 0) {
+			pm_runtime_put_sync(dev);
+			goto exit;
+		}
+
 		ret = ispif_reset(ispif);
 		if (ret < 0) {
+			pm_runtime_put_sync(dev);
 			camss_disable_clocks(ispif->nclocks, ispif->clock);
 			goto exit;
 		}
@@ -252,6 +271,7 @@ static int ispif_set_power(struct v4l2_subdev *sd, int on)
 			goto exit;
 		} else if (ispif->power_count == 1) {
 			camss_disable_clocks(ispif->nclocks, ispif->clock);
+			pm_runtime_put_sync(dev);
 		}
 
 		ispif->power_count--;
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 3f589c448cd2..474e1dd02891 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -15,6 +15,7 @@
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
 #include <linux/spinlock_types.h>
 #include <linux/spinlock.h>
 #include <media/media-entity.h>
@@ -1981,6 +1982,14 @@ static int vfe_get(struct vfe_device *vfe)
 	mutex_lock(&vfe->power_lock);
 
 	if (vfe->power_count == 0) {
+		ret = camss_pm_domain_on(vfe->camss, vfe->id);
+		if (ret < 0)
+			goto error_pm_domain;
+
+		ret = pm_runtime_get_sync(vfe->camss->dev);
+		if (ret < 0)
+			goto error_pm_runtime_get;
+
 		ret = vfe_set_clock_rates(vfe);
 		if (ret < 0)
 			goto error_clocks;
@@ -2012,6 +2021,12 @@ error_reset:
 	camss_disable_clocks(vfe->nclocks, vfe->clock);
 
 error_clocks:
+	pm_runtime_put_sync(vfe->camss->dev);
+
+error_pm_runtime_get:
+	camss_pm_domain_off(vfe->camss, vfe->id);
+
+error_pm_domain:
 	mutex_unlock(&vfe->power_lock);
 
 	return ret;
@@ -2034,6 +2049,8 @@ static void vfe_put(struct vfe_device *vfe)
 			vfe_halt(vfe);
 		}
 		camss_disable_clocks(vfe->nclocks, vfe->clock);
+		pm_runtime_put_sync(vfe->camss->dev);
+		camss_pm_domain_off(vfe->camss, vfe->id);
 	}
 
 	vfe->power_count--;
diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
index 171e2c9d669e..dcc0c30ef1b1 100644
--- a/drivers/media/platform/qcom/camss/camss.c
+++ b/drivers/media/platform/qcom/camss/camss.c
@@ -14,6 +14,8 @@
 #include <linux/platform_device.h>
 #include <linux/of.h>
 #include <linux/of_graph.h>
+#include <linux/pm_runtime.h>
+#include <linux/pm_domain.h>
 #include <linux/slab.h>
 #include <linux/videodev2.h>
 
@@ -393,6 +395,26 @@ int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock)
 	return 0;
 }
 
+int camss_pm_domain_on(struct camss *camss, int id)
+{
+	if (camss->version == CAMSS_8x96) {
+		camss->genpd_link[id] = device_link_add(camss->dev,
+				camss->genpd[id], DL_FLAG_STATELESS |
+				DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE);
+
+		if (!camss->genpd_link[id])
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+void camss_pm_domain_off(struct camss *camss, int id)
+{
+	if (camss->version == CAMSS_8x96)
+		device_link_del(camss->genpd_link[id]);
+}
+
 /*
  * camss_of_parse_endpoint_node - Parse port endpoint node
  * @dev: Device
@@ -896,6 +918,23 @@ static int camss_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (camss->version == CAMSS_8x96) {
+		camss->genpd[PM_DOMAIN_VFE0] = dev_pm_domain_attach_by_id(
+						camss->dev, PM_DOMAIN_VFE0);
+		if (IS_ERR(camss->genpd[PM_DOMAIN_VFE0]))
+			return PTR_ERR(camss->genpd[PM_DOMAIN_VFE0]);
+
+		camss->genpd[PM_DOMAIN_VFE1] = dev_pm_domain_attach_by_id(
+						camss->dev, PM_DOMAIN_VFE1);
+		if (IS_ERR(camss->genpd[PM_DOMAIN_VFE1])) {
+			dev_pm_domain_detach(camss->genpd[PM_DOMAIN_VFE0],
+					     true);
+			return PTR_ERR(camss->genpd[PM_DOMAIN_VFE1]);
+		}
+	}
+
+	pm_runtime_enable(dev);
+
 	return 0;
 
 err_register_subdevs:
@@ -912,6 +951,13 @@ void camss_delete(struct camss *camss)
 	media_device_unregister(&camss->media_dev);
 	media_device_cleanup(&camss->media_dev);
 
+	pm_runtime_disable(camss->dev);
+
+	if (camss->version == CAMSS_8x96) {
+		dev_pm_domain_detach(camss->genpd[PM_DOMAIN_VFE0], true);
+		dev_pm_domain_detach(camss->genpd[PM_DOMAIN_VFE1], true);
+	}
+
 	kfree(camss);
 }
 
@@ -947,12 +993,29 @@ static const struct of_device_id camss_dt_match[] = {
 
 MODULE_DEVICE_TABLE(of, camss_dt_match);
 
+static int camss_runtime_suspend(struct device *dev)
+{
+	return 0;
+}
+
+static int camss_runtime_resume(struct device *dev)
+{
+	return 0;
+}
+
+static const struct dev_pm_ops camss_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend,
+				pm_runtime_force_resume)
+	SET_RUNTIME_PM_OPS(camss_runtime_suspend, camss_runtime_resume, NULL)
+};
+
 static struct platform_driver qcom_camss_driver = {
 	.probe = camss_probe,
 	.remove = camss_remove,
 	.driver = {
 		.name = "qcom-camss",
 		.of_match_table = camss_dt_match,
+		.pm = &camss_pm_ops,
 	},
 };
 
diff --git a/drivers/media/platform/qcom/camss/camss.h b/drivers/media/platform/qcom/camss/camss.h
index dff1045a8a77..418996d8dad8 100644
--- a/drivers/media/platform/qcom/camss/camss.h
+++ b/drivers/media/platform/qcom/camss/camss.h
@@ -10,6 +10,7 @@
 #ifndef QC_MSM_CAMSS_H
 #define QC_MSM_CAMSS_H
 
+#include <linux/device.h>
 #include <linux/types.h>
 #include <media/v4l2-async.h>
 #include <media/v4l2-device.h>
@@ -56,6 +57,12 @@ struct resources_ispif {
 	char *interrupt;
 };
 
+enum pm_domain {
+	PM_DOMAIN_VFE0,
+	PM_DOMAIN_VFE1,
+	PM_DOMAIN_COUNT
+};
+
 enum camss_version {
 	CAMSS_8x16,
 	CAMSS_8x96,
@@ -75,6 +82,8 @@ struct camss {
 	int vfe_num;
 	struct vfe_device *vfe;
 	atomic_t ref_count;
+	struct device *genpd[PM_DOMAIN_COUNT];
+	struct device_link *genpd_link[PM_DOMAIN_COUNT];
 };
 
 struct camss_camera_interface {
@@ -99,6 +108,8 @@ int camss_enable_clocks(int nclocks, struct camss_clock *clock,
 			struct device *dev);
 void camss_disable_clocks(int nclocks, struct camss_clock *clock);
 int camss_get_pixel_clock(struct media_entity *entity, u32 *pixel_clock);
+int camss_pm_domain_on(struct camss *camss, int id);
+void camss_pm_domain_off(struct camss *camss, int id);
 void camss_delete(struct camss *camss);
 
 #endif /* QC_MSM_CAMSS_H */
-- 
cgit v1.2.3


From 516e8f0f8912b3779e4259c824953a23c4108fe8 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:28 -0400
Subject: media: camss: csiphy: Split to hardware dependent and independent
 parts

This will allow to add support for different hardware.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
[hans.verkuil@cisco.com: remove trailing empty line]
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/Makefile         |   1 +
 .../platform/qcom/camss/camss-csiphy-2ph-1-0.c     | 172 +++++++++++++++++++++
 drivers/media/platform/qcom/camss/camss-csiphy.c   | 171 +++-----------------
 drivers/media/platform/qcom/camss/camss-csiphy.h   |  17 ++
 4 files changed, 213 insertions(+), 148 deletions(-)
 create mode 100644 drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c

diff --git a/drivers/media/platform/qcom/camss/Makefile b/drivers/media/platform/qcom/camss/Makefile
index 3c4024fbb768..0446b242f7f8 100644
--- a/drivers/media/platform/qcom/camss/Makefile
+++ b/drivers/media/platform/qcom/camss/Makefile
@@ -3,6 +3,7 @@
 qcom-camss-objs += \
 		camss.o \
 		camss-csid.o \
+		camss-csiphy-2ph-1-0.o \
 		camss-csiphy.o \
 		camss-ispif.o \
 		camss-vfe.o \
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c
new file mode 100644
index 000000000000..5485d1fd31d7
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-csiphy-2ph-1-0.c
+ *
+ * Qualcomm MSM Camera Subsystem - CSIPHY Module 2phase v1.0
+ *
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2016-2018 Linaro Ltd.
+ */
+
+#include "camss-csiphy.h"
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+
+#define CAMSS_CSI_PHY_LNn_CFG2(n)		(0x004 + 0x40 * (n))
+#define CAMSS_CSI_PHY_LNn_CFG3(n)		(0x008 + 0x40 * (n))
+#define CAMSS_CSI_PHY_GLBL_RESET		0x140
+#define CAMSS_CSI_PHY_GLBL_PWR_CFG		0x144
+#define CAMSS_CSI_PHY_GLBL_IRQ_CMD		0x164
+#define CAMSS_CSI_PHY_HW_VERSION		0x188
+#define CAMSS_CSI_PHY_INTERRUPT_STATUSn(n)	(0x18c + 0x4 * (n))
+#define CAMSS_CSI_PHY_INTERRUPT_MASKn(n)	(0x1ac + 0x4 * (n))
+#define CAMSS_CSI_PHY_INTERRUPT_CLEARn(n)	(0x1cc + 0x4 * (n))
+#define CAMSS_CSI_PHY_GLBL_T_INIT_CFG0		0x1ec
+#define CAMSS_CSI_PHY_T_WAKEUP_CFG0		0x1f4
+
+static void csiphy_hw_version_read(struct csiphy_device *csiphy,
+				   struct device *dev)
+{
+	u8 hw_version = readl_relaxed(csiphy->base +
+				      CAMSS_CSI_PHY_HW_VERSION);
+
+	dev_dbg(dev, "CSIPHY HW Version = 0x%02x\n", hw_version);
+}
+
+/*
+ * csiphy_reset - Perform software reset on CSIPHY module
+ * @csiphy: CSIPHY device
+ */
+static void csiphy_reset(struct csiphy_device *csiphy)
+{
+	writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+	usleep_range(5000, 8000);
+	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+}
+
+/*
+ * csiphy_settle_cnt_calc - Calculate settle count value
+ *
+ * Helper function to calculate settle count value. This is
+ * based on the CSI2 T_hs_settle parameter which in turn
+ * is calculated based on the CSI2 transmitter pixel clock
+ * frequency.
+ *
+ * Return settle count value or 0 if the CSI2 pixel clock
+ * frequency is not available
+ */
+static u8 csiphy_settle_cnt_calc(u32 pixel_clock, u8 bpp, u8 num_lanes,
+				 u32 timer_clk_rate)
+{
+	u32 mipi_clock; /* Hz */
+	u32 ui; /* ps */
+	u32 timer_period; /* ps */
+	u32 t_hs_prepare_max; /* ps */
+	u32 t_hs_prepare_zero_min; /* ps */
+	u32 t_hs_settle; /* ps */
+	u8 settle_cnt;
+
+	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
+	ui = div_u64(1000000000000LL, mipi_clock);
+	ui /= 2;
+	t_hs_prepare_max = 85000 + 6 * ui;
+	t_hs_prepare_zero_min = 145000 + 10 * ui;
+	t_hs_settle = (t_hs_prepare_max + t_hs_prepare_zero_min) / 2;
+
+	timer_period = div_u64(1000000000000LL, timer_clk_rate);
+	settle_cnt = t_hs_settle / timer_period - 1;
+
+	return settle_cnt;
+}
+
+static void csiphy_lanes_enable(struct csiphy_device *csiphy,
+				struct csiphy_config *cfg,
+				u32 pixel_clock, u8 bpp, u8 lane_mask)
+{
+	struct csiphy_lanes_cfg *c = &cfg->csi2->lane_cfg;
+	u8 settle_cnt;
+	u8 val;
+	int i = 0;
+
+	settle_cnt = csiphy_settle_cnt_calc(pixel_clock, bpp, c->num_data,
+					    csiphy->timer_clk_rate);
+
+	writel_relaxed(0x1, csiphy->base +
+		       CAMSS_CSI_PHY_GLBL_T_INIT_CFG0);
+	writel_relaxed(0x1, csiphy->base +
+		       CAMSS_CSI_PHY_T_WAKEUP_CFG0);
+
+	val = 0x1;
+	val |= lane_mask << 1;
+	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+
+	val = cfg->combo_mode << 4;
+	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
+
+	while (lane_mask) {
+		if (lane_mask & 0x1) {
+			writel_relaxed(0x10, csiphy->base +
+				       CAMSS_CSI_PHY_LNn_CFG2(i));
+			writel_relaxed(settle_cnt, csiphy->base +
+				       CAMSS_CSI_PHY_LNn_CFG3(i));
+			writel_relaxed(0x3f, csiphy->base +
+				       CAMSS_CSI_PHY_INTERRUPT_MASKn(i));
+			writel_relaxed(0x3f, csiphy->base +
+				       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+		}
+
+		lane_mask >>= 1;
+		i++;
+	}
+}
+
+static void csiphy_lanes_disable(struct csiphy_device *csiphy, u8 lane_mask)
+{
+	int i = 0;
+
+	while (lane_mask) {
+		if (lane_mask & 0x1)
+			writel_relaxed(0x0, csiphy->base +
+				       CAMSS_CSI_PHY_LNn_CFG2(i));
+
+		lane_mask >>= 1;
+		i++;
+	}
+
+	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+}
+
+/*
+ * csiphy_isr - CSIPHY module interrupt handler
+ * @irq: Interrupt line
+ * @dev: CSIPHY device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t csiphy_isr(int irq, void *dev)
+{
+	struct csiphy_device *csiphy = dev;
+	u8 i;
+
+	for (i = 0; i < 8; i++) {
+		u8 val = readl_relaxed(csiphy->base +
+				       CAMSS_CSI_PHY_INTERRUPT_STATUSn(i));
+		writel_relaxed(val, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+		writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
+		writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
+		writel_relaxed(0x0, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
+	}
+
+	return IRQ_HANDLED;
+}
+
+const struct csiphy_hw_ops csiphy_ops_2ph_1_0 = {
+	.hw_version_read = csiphy_hw_version_read,
+	.reset = csiphy_reset,
+	.lanes_enable = csiphy_lanes_enable,
+	.lanes_disable = csiphy_lanes_disable,
+	.isr = csiphy_isr,
+};
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 4aeaedb69786..8d10e85eac62 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -23,18 +23,6 @@
 
 #define MSM_CSIPHY_NAME "msm_csiphy"
 
-#define CAMSS_CSI_PHY_LNn_CFG2(n)		(0x004 + 0x40 * (n))
-#define CAMSS_CSI_PHY_LNn_CFG3(n)		(0x008 + 0x40 * (n))
-#define CAMSS_CSI_PHY_GLBL_RESET		0x140
-#define CAMSS_CSI_PHY_GLBL_PWR_CFG		0x144
-#define CAMSS_CSI_PHY_GLBL_IRQ_CMD		0x164
-#define CAMSS_CSI_PHY_HW_VERSION		0x188
-#define CAMSS_CSI_PHY_INTERRUPT_STATUSn(n)	(0x18c + 0x4 * (n))
-#define CAMSS_CSI_PHY_INTERRUPT_MASKn(n)	(0x1ac + 0x4 * (n))
-#define CAMSS_CSI_PHY_INTERRUPT_CLEARn(n)	(0x1cc + 0x4 * (n))
-#define CAMSS_CSI_PHY_GLBL_T_INIT_CFG0		0x1ec
-#define CAMSS_CSI_PHY_T_WAKEUP_CFG0		0x1f4
-
 static const struct {
 	u32 code;
 	u8 bpp;
@@ -124,32 +112,6 @@ static u8 csiphy_get_bpp(u32 code)
 	return csiphy_formats[0].bpp;
 }
 
-/*
- * csiphy_isr - CSIPHY module interrupt handler
- * @irq: Interrupt line
- * @dev: CSIPHY device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t csiphy_isr(int irq, void *dev)
-{
-	struct csiphy_device *csiphy = dev;
-	u8 i;
-
-	for (i = 0; i < 8; i++) {
-		u8 val = readl_relaxed(csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_STATUSn(i));
-		writel_relaxed(val, csiphy->base +
-			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-		writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
-		writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_IRQ_CMD);
-		writel_relaxed(0x0, csiphy->base +
-			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-	}
-
-	return IRQ_HANDLED;
-}
-
 /*
  * csiphy_set_clock_rates - Calculate and set clock rates on CSIPHY module
  * @csiphy: CSIPHY device
@@ -214,17 +176,6 @@ static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
 	return 0;
 }
 
-/*
- * csiphy_reset - Perform software reset on CSIPHY module
- * @csiphy: CSIPHY device
- */
-static void csiphy_reset(struct csiphy_device *csiphy)
-{
-	writel_relaxed(0x1, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-	usleep_range(5000, 8000);
-	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-}
-
 /*
  * csiphy_set_power - Power on/off CSIPHY module
  * @sd: CSIPHY V4L2 subdevice
@@ -238,7 +189,6 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
 	struct device *dev = csiphy->camss->dev;
 
 	if (on) {
-		u8 hw_version;
 		int ret;
 
 		ret = pm_runtime_get_sync(dev);
@@ -259,11 +209,9 @@ static int csiphy_set_power(struct v4l2_subdev *sd, int on)
 
 		enable_irq(csiphy->irq);
 
-		csiphy_reset(csiphy);
+		csiphy->ops->reset(csiphy);
 
-		hw_version = readl_relaxed(csiphy->base +
-					   CAMSS_CSI_PHY_HW_VERSION);
-		dev_dbg(dev, "CSIPHY HW Version = 0x%02x\n", hw_version);
+		csiphy->ops->hw_version_read(csiphy, dev);
 	} else {
 		disable_irq(csiphy->irq);
 
@@ -295,77 +243,34 @@ static u8 csiphy_get_lane_mask(struct csiphy_lanes_cfg *lane_cfg)
 }
 
 /*
- * csiphy_settle_cnt_calc - Calculate settle count value
+ * csiphy_stream_on - Enable streaming on CSIPHY module
  * @csiphy: CSIPHY device
  *
- * Helper function to calculate settle count value. This is
- * based on the CSI2 T_hs_settle parameter which in turn
- * is calculated based on the CSI2 transmitter pixel clock
- * frequency.
+ * Helper function to enable streaming on CSIPHY module.
+ * Main configuration of CSIPHY module is also done here.
  *
- * Return settle count value or 0 if the CSI2 pixel clock
- * frequency is not available
+ * Return 0 on success or a negative error code otherwise
  */
-static u8 csiphy_settle_cnt_calc(struct csiphy_device *csiphy)
+static int csiphy_stream_on(struct csiphy_device *csiphy)
 {
-	u8 bpp = csiphy_get_bpp(
-			csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
-	u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
-	u32 pixel_clock; /* Hz */
-	u32 mipi_clock; /* Hz */
-	u32 ui; /* ps */
-	u32 timer_period; /* ps */
-	u32 t_hs_prepare_max; /* ps */
-	u32 t_hs_prepare_zero_min; /* ps */
-	u32 t_hs_settle; /* ps */
-	u8 settle_cnt;
+	struct csiphy_config *cfg = &csiphy->cfg;
+	u32 pixel_clock;
+	u8 lane_mask = csiphy_get_lane_mask(&cfg->csi2->lane_cfg);
+	u8 bpp = csiphy_get_bpp(csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
+	u8 val;
 	int ret;
 
 	ret = camss_get_pixel_clock(&csiphy->subdev.entity, &pixel_clock);
 	if (ret) {
 		dev_err(csiphy->camss->dev,
 			"Cannot get CSI2 transmitter's pixel clock\n");
-		return 0;
+		return -EINVAL;
 	}
 	if (!pixel_clock) {
 		dev_err(csiphy->camss->dev,
 			"Got pixel clock == 0, cannot continue\n");
-		return 0;
-	}
-
-	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
-	ui = div_u64(1000000000000LL, mipi_clock);
-	ui /= 2;
-	t_hs_prepare_max = 85000 + 6 * ui;
-	t_hs_prepare_zero_min = 145000 + 10 * ui;
-	t_hs_settle = (t_hs_prepare_max + t_hs_prepare_zero_min) / 2;
-
-	timer_period = div_u64(1000000000000LL, csiphy->timer_clk_rate);
-	settle_cnt = t_hs_settle / timer_period - 1;
-
-	return settle_cnt;
-}
-
-/*
- * csiphy_stream_on - Enable streaming on CSIPHY module
- * @csiphy: CSIPHY device
- *
- * Helper function to enable streaming on CSIPHY module.
- * Main configuration of CSIPHY module is also done here.
- *
- * Return 0 on success or a negative error code otherwise
- */
-static int csiphy_stream_on(struct csiphy_device *csiphy)
-{
-	struct csiphy_config *cfg = &csiphy->cfg;
-	u8 lane_mask = csiphy_get_lane_mask(&cfg->csi2->lane_cfg);
-	u8 settle_cnt;
-	u8 val;
-	int i = 0;
-
-	settle_cnt = csiphy_settle_cnt_calc(csiphy);
-	if (!settle_cnt)
 		return -EINVAL;
+	}
 
 	val = readl_relaxed(csiphy->base_clk_mux);
 	if (cfg->combo_mode && (lane_mask & 0x18) == 0x18) {
@@ -378,33 +283,7 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
 	writel_relaxed(val, csiphy->base_clk_mux);
 	wmb();
 
-	writel_relaxed(0x1, csiphy->base +
-		       CAMSS_CSI_PHY_GLBL_T_INIT_CFG0);
-	writel_relaxed(0x1, csiphy->base +
-		       CAMSS_CSI_PHY_T_WAKEUP_CFG0);
-
-	val = 0x1;
-	val |= lane_mask << 1;
-	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
-
-	val = cfg->combo_mode << 4;
-	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
-
-	while (lane_mask) {
-		if (lane_mask & 0x1) {
-			writel_relaxed(0x10, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
-			writel_relaxed(settle_cnt, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG3(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_MASKn(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-		}
-
-		lane_mask >>= 1;
-		i++;
-	}
+	csiphy->ops->lanes_enable(csiphy, cfg, pixel_clock, bpp, lane_mask);
 
 	return 0;
 }
@@ -418,18 +297,8 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
 static void csiphy_stream_off(struct csiphy_device *csiphy)
 {
 	u8 lane_mask = csiphy_get_lane_mask(&csiphy->cfg.csi2->lane_cfg);
-	int i = 0;
 
-	while (lane_mask) {
-		if (lane_mask & 0x1)
-			writel_relaxed(0x0, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
-
-		lane_mask >>= 1;
-		i++;
-	}
-
-	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
+	csiphy->ops->lanes_disable(csiphy, lane_mask);
 }
 
 
@@ -696,6 +565,11 @@ int msm_csiphy_subdev_init(struct camss *camss,
 	csiphy->id = id;
 	csiphy->cfg.combo_mode = 0;
 
+	if (camss->version == CAMSS_8x16)
+		csiphy->ops = &csiphy_ops_2ph_1_0;
+	else
+		return -EINVAL;
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
@@ -724,7 +598,8 @@ int msm_csiphy_subdev_init(struct camss *camss,
 	csiphy->irq = r->start;
 	snprintf(csiphy->irq_name, sizeof(csiphy->irq_name), "%s_%s%d",
 		 dev_name(dev), MSM_CSIPHY_NAME, csiphy->id);
-	ret = devm_request_irq(dev, csiphy->irq, csiphy_isr,
+
+	ret = devm_request_irq(dev, csiphy->irq, csiphy->ops->isr,
 			       IRQF_TRIGGER_RISING, csiphy->irq_name, csiphy);
 	if (ret < 0) {
 		dev_err(dev, "request_irq failed: %d\n", ret);
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index 728dfef18676..edad941d3bbe 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -11,6 +11,7 @@
 #define QC_MSM_CAMSS_CSIPHY_H
 
 #include <linux/clk.h>
+#include <linux/interrupt.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
 #include <media/v4l2-mediabus.h>
@@ -41,6 +42,19 @@ struct csiphy_config {
 	struct csiphy_csi2_cfg *csi2;
 };
 
+struct csiphy_device;
+
+struct csiphy_hw_ops {
+	void (*hw_version_read)(struct csiphy_device *csiphy,
+				struct device *dev);
+	void (*reset)(struct csiphy_device *csiphy);
+	void (*lanes_enable)(struct csiphy_device *csiphy,
+			     struct csiphy_config *cfg,
+			     u32 pixel_clock, u8 bpp, u8 lane_mask);
+	void (*lanes_disable)(struct csiphy_device *csiphy, u8 lane_mask);
+	irqreturn_t (*isr)(int irq, void *dev);
+};
+
 struct csiphy_device {
 	struct camss *camss;
 	u8 id;
@@ -55,6 +69,7 @@ struct csiphy_device {
 	u32 timer_clk_rate;
 	struct csiphy_config cfg;
 	struct v4l2_mbus_framefmt fmt[MSM_CSIPHY_PADS_NUM];
+	const struct csiphy_hw_ops *ops;
 };
 
 struct resources;
@@ -68,4 +83,6 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
 
 void msm_csiphy_unregister_entity(struct csiphy_device *csiphy);
 
+extern const struct csiphy_hw_ops csiphy_ops_2ph_1_0;
+
 #endif /* QC_MSM_CAMSS_CSIPHY_H */
-- 
cgit v1.2.3


From 369f81f350b5c03599d8f82e31f9a916d7bfe80a Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:29 -0400
Subject: media: camss: csiphy: Unify lane handling

Restructure lane configuration so it is simpler and will allow
similar (although not the same) handling for different hardware
versions.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 .../platform/qcom/camss/camss-csiphy-2ph-1-0.c     | 48 ++++++++++++----------
 drivers/media/platform/qcom/camss/camss-csiphy.c   |  4 +-
 drivers/media/platform/qcom/camss/camss-csiphy.h   |  3 +-
 3 files changed, 29 insertions(+), 26 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c
index 5485d1fd31d7..c832539397d7 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy-2ph-1-0.c
@@ -86,7 +86,7 @@ static void csiphy_lanes_enable(struct csiphy_device *csiphy,
 {
 	struct csiphy_lanes_cfg *c = &cfg->csi2->lane_cfg;
 	u8 settle_cnt;
-	u8 val;
+	u8 val, l = 0;
 	int i = 0;
 
 	settle_cnt = csiphy_settle_cnt_calc(pixel_clock, bpp, c->num_data,
@@ -104,34 +104,38 @@ static void csiphy_lanes_enable(struct csiphy_device *csiphy,
 	val = cfg->combo_mode << 4;
 	writel_relaxed(val, csiphy->base + CAMSS_CSI_PHY_GLBL_RESET);
 
-	while (lane_mask) {
-		if (lane_mask & 0x1) {
-			writel_relaxed(0x10, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
-			writel_relaxed(settle_cnt, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG3(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_MASKn(i));
-			writel_relaxed(0x3f, csiphy->base +
-				       CAMSS_CSI_PHY_INTERRUPT_CLEARn(i));
-		}
-
-		lane_mask >>= 1;
-		i++;
+	for (i = 0; i <= c->num_data; i++) {
+		if (i == c->num_data)
+			l = c->clk.pos;
+		else
+			l = c->data[i].pos;
+
+		writel_relaxed(0x10, csiphy->base +
+			       CAMSS_CSI_PHY_LNn_CFG2(l));
+		writel_relaxed(settle_cnt, csiphy->base +
+			       CAMSS_CSI_PHY_LNn_CFG3(l));
+		writel_relaxed(0x3f, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_MASKn(l));
+		writel_relaxed(0x3f, csiphy->base +
+			       CAMSS_CSI_PHY_INTERRUPT_CLEARn(l));
 	}
 }
 
-static void csiphy_lanes_disable(struct csiphy_device *csiphy, u8 lane_mask)
+static void csiphy_lanes_disable(struct csiphy_device *csiphy,
+				 struct csiphy_config *cfg)
 {
+	struct csiphy_lanes_cfg *c = &cfg->csi2->lane_cfg;
+	u8 l = 0;
 	int i = 0;
 
-	while (lane_mask) {
-		if (lane_mask & 0x1)
-			writel_relaxed(0x0, csiphy->base +
-				       CAMSS_CSI_PHY_LNn_CFG2(i));
+	for (i = 0; i <= c->num_data; i++) {
+		if (i == c->num_data)
+			l = c->clk.pos;
+		else
+			l = c->data[i].pos;
 
-		lane_mask >>= 1;
-		i++;
+		writel_relaxed(0x0, csiphy->base +
+			       CAMSS_CSI_PHY_LNn_CFG2(l));
 	}
 
 	writel_relaxed(0x0, csiphy->base + CAMSS_CSI_PHY_GLBL_PWR_CFG);
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 8d10e85eac62..d35eea03ebf8 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -296,9 +296,7 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
  */
 static void csiphy_stream_off(struct csiphy_device *csiphy)
 {
-	u8 lane_mask = csiphy_get_lane_mask(&csiphy->cfg.csi2->lane_cfg);
-
-	csiphy->ops->lanes_disable(csiphy, lane_mask);
+	csiphy->ops->lanes_disable(csiphy, &csiphy->cfg);
 }
 
 
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index edad941d3bbe..e3dd25702b01 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -51,7 +51,8 @@ struct csiphy_hw_ops {
 	void (*lanes_enable)(struct csiphy_device *csiphy,
 			     struct csiphy_config *cfg,
 			     u32 pixel_clock, u8 bpp, u8 lane_mask);
-	void (*lanes_disable)(struct csiphy_device *csiphy, u8 lane_mask);
+	void (*lanes_disable)(struct csiphy_device *csiphy,
+			      struct csiphy_config *cfg);
 	irqreturn_t (*isr)(int irq, void *dev);
 };
 
-- 
cgit v1.2.3


From 4138a88b6093e1f8bf1b8a95c653bec6c854f119 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:30 -0400
Subject: media: camss: csiphy: Add support for 8x96

Add CSIPHY hardware dependent part for 8x96.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/Makefile         |   1 +
 .../platform/qcom/camss/camss-csiphy-3ph-1-0.c     | 256 +++++++++++++++++++++
 drivers/media/platform/qcom/camss/camss-csiphy.c   |   2 +
 drivers/media/platform/qcom/camss/camss-csiphy.h   |   1 +
 4 files changed, 260 insertions(+)
 create mode 100644 drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c

diff --git a/drivers/media/platform/qcom/camss/Makefile b/drivers/media/platform/qcom/camss/Makefile
index 0446b242f7f8..36b9f7cc3340 100644
--- a/drivers/media/platform/qcom/camss/Makefile
+++ b/drivers/media/platform/qcom/camss/Makefile
@@ -4,6 +4,7 @@ qcom-camss-objs += \
 		camss.o \
 		camss-csid.o \
 		camss-csiphy-2ph-1-0.o \
+		camss-csiphy-3ph-1-0.o \
 		camss-csiphy.o \
 		camss-ispif.o \
 		camss-vfe.o \
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c
new file mode 100644
index 000000000000..bcd0dfd33618
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-csiphy-3ph-1-0.c
@@ -0,0 +1,256 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-csiphy-3ph-1-0.c
+ *
+ * Qualcomm MSM Camera Subsystem - CSIPHY Module 3phase v1.0
+ *
+ * Copyright (c) 2011-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2016-2018 Linaro Ltd.
+ */
+
+#include "camss-csiphy.h"
+
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+
+#define CSIPHY_3PH_LNn_CFG1(n)			(0x000 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG1_SWI_REC_DLY_PRG	(BIT(7) | BIT(6))
+#define CSIPHY_3PH_LNn_CFG2(n)			(0x004 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG2_LP_REC_EN_INT	BIT(3)
+#define CSIPHY_3PH_LNn_CFG3(n)			(0x008 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG4(n)			(0x00c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG4_T_HS_CLK_MISS	0xa4
+#define CSIPHY_3PH_LNn_CFG5(n)			(0x010 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG5_T_HS_DTERM		0x02
+#define CSIPHY_3PH_LNn_CFG5_HS_REC_EQ_FQ_INT	0x50
+#define CSIPHY_3PH_LNn_TEST_IMP(n)		(0x01c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_TEST_IMP_HS_TERM_IMP	0xa
+#define CSIPHY_3PH_LNn_MISC1(n)			(0x028 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_MISC1_IS_CLKLANE		BIT(2)
+#define CSIPHY_3PH_LNn_CFG6(n)			(0x02c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG6_SWI_FORCE_INIT_EXIT	BIT(0)
+#define CSIPHY_3PH_LNn_CFG7(n)			(0x030 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG7_SWI_T_INIT		0x2
+#define CSIPHY_3PH_LNn_CFG8(n)			(0x034 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG8_SWI_SKIP_WAKEUP	BIT(0)
+#define CSIPHY_3PH_LNn_CFG8_SKEW_FILTER_ENABLE	BIT(1)
+#define CSIPHY_3PH_LNn_CFG9(n)			(0x038 + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CFG9_SWI_T_WAKEUP	0x1
+#define CSIPHY_3PH_LNn_CSI_LANE_CTRL15(n)	(0x03c + 0x100 * (n))
+#define CSIPHY_3PH_LNn_CSI_LANE_CTRL15_SWI_SOT_SYMBOL	0xb8
+
+#define CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(n)	(0x800 + 0x4 * (n))
+#define CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_COMMON_PWRDN_B	BIT(0)
+#define CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_SHOW_REV_ID	BIT(1)
+#define CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(n)	(0x8b0 + 0x4 * (n))
+
+static void csiphy_hw_version_read(struct csiphy_device *csiphy,
+				   struct device *dev)
+{
+	u32 hw_version;
+
+	writel(CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_SHOW_REV_ID,
+	       csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(6));
+
+	hw_version = readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(12));
+	hw_version |= readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(13)) << 8;
+	hw_version |= readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(14)) << 16;
+	hw_version |= readl_relaxed(csiphy->base +
+				   CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(15)) << 24;
+
+	dev_err(dev, "CSIPHY 3PH HW Version = 0x%08x\n", hw_version);
+}
+
+/*
+ * csiphy_reset - Perform software reset on CSIPHY module
+ * @csiphy: CSIPHY device
+ */
+static void csiphy_reset(struct csiphy_device *csiphy)
+{
+	writel_relaxed(0x1, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(0));
+	usleep_range(5000, 8000);
+	writel_relaxed(0x0, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(0));
+}
+
+static irqreturn_t csiphy_isr(int irq, void *dev)
+{
+	struct csiphy_device *csiphy = dev;
+	int i;
+
+	for (i = 0; i < 11; i++) {
+		int c = i + 22;
+		u8 val = readl_relaxed(csiphy->base +
+				       CSIPHY_3PH_CMN_CSI_COMMON_STATUSn(i));
+
+		writel_relaxed(val, csiphy->base +
+				    CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(c));
+	}
+
+	writel_relaxed(0x1, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(10));
+	writel_relaxed(0x0, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(10));
+
+	for (i = 22; i < 33; i++)
+		writel_relaxed(0x0, csiphy->base +
+				    CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(i));
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * csiphy_settle_cnt_calc - Calculate settle count value
+ *
+ * Helper function to calculate settle count value. This is
+ * based on the CSI2 T_hs_settle parameter which in turn
+ * is calculated based on the CSI2 transmitter pixel clock
+ * frequency.
+ *
+ * Return settle count value or 0 if the CSI2 pixel clock
+ * frequency is not available
+ */
+static u8 csiphy_settle_cnt_calc(u32 pixel_clock, u8 bpp, u8 num_lanes,
+				 u32 timer_clk_rate)
+{
+	u32 mipi_clock; /* Hz */
+	u32 ui; /* ps */
+	u32 timer_period; /* ps */
+	u32 t_hs_prepare_max; /* ps */
+	u32 t_hs_settle; /* ps */
+	u8 settle_cnt;
+
+	mipi_clock = pixel_clock * bpp / (2 * num_lanes);
+	ui = div_u64(1000000000000LL, mipi_clock);
+	ui /= 2;
+	t_hs_prepare_max = 85000 + 6 * ui;
+	t_hs_settle = t_hs_prepare_max;
+
+	timer_period = div_u64(1000000000000LL, timer_clk_rate);
+	settle_cnt = t_hs_settle / timer_period - 6;
+
+	return settle_cnt;
+}
+
+static void csiphy_lanes_enable(struct csiphy_device *csiphy,
+				struct csiphy_config *cfg,
+				u32 pixel_clock, u8 bpp, u8 lane_mask)
+{
+	struct csiphy_lanes_cfg *c = &cfg->csi2->lane_cfg;
+	u8 settle_cnt;
+	u8 val, l = 0;
+	int i;
+
+	settle_cnt = csiphy_settle_cnt_calc(pixel_clock, bpp, c->num_data,
+					    csiphy->timer_clk_rate);
+
+	val = BIT(c->clk.pos);
+	for (i = 0; i < c->num_data; i++)
+		val |= BIT(c->data[i].pos * 2);
+
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(5));
+
+	val = CSIPHY_3PH_CMN_CSI_COMMON_CTRL6_COMMON_PWRDN_B;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(6));
+
+	for (i = 0; i <= c->num_data; i++) {
+		if (i == c->num_data)
+			l = 7;
+		else
+			l = c->data[i].pos * 2;
+
+		val = CSIPHY_3PH_LNn_CFG1_SWI_REC_DLY_PRG;
+		val |= 0x17;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG1(l));
+
+		val = CSIPHY_3PH_LNn_CFG2_LP_REC_EN_INT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG2(l));
+
+		val = settle_cnt;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG3(l));
+
+		val = CSIPHY_3PH_LNn_CFG5_T_HS_DTERM |
+			CSIPHY_3PH_LNn_CFG5_HS_REC_EQ_FQ_INT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG5(l));
+
+		val = CSIPHY_3PH_LNn_CFG6_SWI_FORCE_INIT_EXIT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG6(l));
+
+		val = CSIPHY_3PH_LNn_CFG7_SWI_T_INIT;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG7(l));
+
+		val = CSIPHY_3PH_LNn_CFG8_SWI_SKIP_WAKEUP |
+			CSIPHY_3PH_LNn_CFG8_SKEW_FILTER_ENABLE;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG8(l));
+
+		val = CSIPHY_3PH_LNn_CFG9_SWI_T_WAKEUP;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG9(l));
+
+		val = CSIPHY_3PH_LNn_TEST_IMP_HS_TERM_IMP;
+		writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_TEST_IMP(l));
+
+		val = CSIPHY_3PH_LNn_CSI_LANE_CTRL15_SWI_SOT_SYMBOL;
+		writel_relaxed(val, csiphy->base +
+				    CSIPHY_3PH_LNn_CSI_LANE_CTRL15(l));
+	}
+
+	val = CSIPHY_3PH_LNn_CFG1_SWI_REC_DLY_PRG;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG1(l));
+
+	val = CSIPHY_3PH_LNn_CFG4_T_HS_CLK_MISS;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_CFG4(l));
+
+	val = CSIPHY_3PH_LNn_MISC1_IS_CLKLANE;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_LNn_MISC1(l));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(11));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(12));
+
+	val = 0xfb;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(13));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(14));
+
+	val = 0x7f;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(15));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(16));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(17));
+
+	val = 0xef;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(18));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(19));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(20));
+
+	val = 0xff;
+	writel_relaxed(val, csiphy->base + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(21));
+}
+
+static void csiphy_lanes_disable(struct csiphy_device *csiphy,
+				 struct csiphy_config *cfg)
+{
+	writel_relaxed(0, csiphy->base +
+			  CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(5));
+
+	writel_relaxed(0, csiphy->base +
+			  CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(6));
+}
+
+const struct csiphy_hw_ops csiphy_ops_3ph_1_0 = {
+	.hw_version_read = csiphy_hw_version_read,
+	.reset = csiphy_reset,
+	.lanes_enable = csiphy_lanes_enable,
+	.lanes_disable = csiphy_lanes_disable,
+	.isr = csiphy_isr,
+};
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index d35eea03ebf8..7da705147966 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -565,6 +565,8 @@ int msm_csiphy_subdev_init(struct camss *camss,
 
 	if (camss->version == CAMSS_8x16)
 		csiphy->ops = &csiphy_ops_2ph_1_0;
+	else if (camss->version == CAMSS_8x96)
+		csiphy->ops = &csiphy_ops_3ph_1_0;
 	else
 		return -EINVAL;
 
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index e3dd25702b01..5debe46b6cf1 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -85,5 +85,6 @@ int msm_csiphy_register_entity(struct csiphy_device *csiphy,
 void msm_csiphy_unregister_entity(struct csiphy_device *csiphy);
 
 extern const struct csiphy_hw_ops csiphy_ops_2ph_1_0;
+extern const struct csiphy_hw_ops csiphy_ops_3ph_1_0;
 
 #endif /* QC_MSM_CAMSS_CSIPHY_H */
-- 
cgit v1.2.3


From 2a05493b5d549ee9a1ecea8772bcc7d9ec7f3d69 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:31 -0400
Subject: media: camss: csid: Add support for 8x96

CSID hardware modules on 8x16 and 8x96 are similar. There is no
need to duplicate the code by adding separate versions. Just
update the register macros to return the correct register
addresses.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c | 60 ++++++++++++++++----------
 1 file changed, 37 insertions(+), 23 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 3ba087fd95a1..915835ee3271 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -27,21 +27,26 @@
 #define CAMSS_CSID_HW_VERSION		0x0
 #define CAMSS_CSID_CORE_CTRL_0		0x004
 #define CAMSS_CSID_CORE_CTRL_1		0x008
-#define CAMSS_CSID_RST_CMD		0x00c
-#define CAMSS_CSID_CID_LUT_VC_n(n)	(0x010 + 0x4 * (n))
-#define CAMSS_CSID_CID_n_CFG(n)		(0x020 + 0x4 * (n))
-#define CAMSS_CSID_IRQ_CLEAR_CMD	0x060
-#define CAMSS_CSID_IRQ_MASK		0x064
-#define CAMSS_CSID_IRQ_STATUS		0x068
-#define CAMSS_CSID_TG_CTRL		0x0a0
+#define CAMSS_CSID_RST_CMD(v)		((v) == CAMSS_8x16 ? 0x00c : 0x010)
+#define CAMSS_CSID_CID_LUT_VC_n(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x010 : 0x014) + 0x4 * (n))
+#define CAMSS_CSID_CID_n_CFG(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x020 : 0x024) + 0x4 * (n))
+#define CAMSS_CSID_IRQ_CLEAR_CMD(v)	((v) == CAMSS_8x16 ? 0x060 : 0x064)
+#define CAMSS_CSID_IRQ_MASK(v)		((v) == CAMSS_8x16 ? 0x064 : 0x068)
+#define CAMSS_CSID_IRQ_STATUS(v)	((v) == CAMSS_8x16 ? 0x068 : 0x06c)
+#define CAMSS_CSID_TG_CTRL(v)		((v) == CAMSS_8x16 ? 0x0a0 : 0x0a8)
 #define CAMSS_CSID_TG_CTRL_DISABLE	0xa06436
 #define CAMSS_CSID_TG_CTRL_ENABLE	0xa06437
-#define CAMSS_CSID_TG_VC_CFG		0x0a4
+#define CAMSS_CSID_TG_VC_CFG(v)		((v) == CAMSS_8x16 ? 0x0a4 : 0x0ac)
 #define CAMSS_CSID_TG_VC_CFG_H_BLANKING		0x3ff
 #define CAMSS_CSID_TG_VC_CFG_V_BLANKING		0x7f
-#define CAMSS_CSID_TG_DT_n_CGG_0(n)	(0x0ac + 0xc * (n))
-#define CAMSS_CSID_TG_DT_n_CGG_1(n)	(0x0b0 + 0xc * (n))
-#define CAMSS_CSID_TG_DT_n_CGG_2(n)	(0x0b4 + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_0(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x0ac : 0x0b4) + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_1(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x0b0 : 0x0b8) + 0xc * (n))
+#define CAMSS_CSID_TG_DT_n_CGG_2(v, n)	\
+			(((v) == CAMSS_8x16 ? 0x0b4 : 0x0bc) + 0xc * (n))
 
 #define DATA_TYPE_EMBEDDED_DATA_8BIT	0x12
 #define DATA_TYPE_YUV422_8BIT		0x1e
@@ -203,10 +208,11 @@ static const struct csid_fmts *csid_get_fmt_entry(u32 code)
 static irqreturn_t csid_isr(int irq, void *dev)
 {
 	struct csid_device *csid = dev;
+	enum camss_version ver = csid->camss->version;
 	u32 value;
 
-	value = readl_relaxed(csid->base + CAMSS_CSID_IRQ_STATUS);
-	writel_relaxed(value, csid->base + CAMSS_CSID_IRQ_CLEAR_CMD);
+	value = readl_relaxed(csid->base + CAMSS_CSID_IRQ_STATUS(ver));
+	writel_relaxed(value, csid->base + CAMSS_CSID_IRQ_CLEAR_CMD(ver));
 
 	if ((value >> 11) & 0x1)
 		complete(&csid->reset_complete);
@@ -289,7 +295,8 @@ static int csid_reset(struct csid_device *csid)
 
 	reinit_completion(&csid->reset_complete);
 
-	writel_relaxed(0x7fff, csid->base + CAMSS_CSID_RST_CMD);
+	writel_relaxed(0x7fff, csid->base +
+		       CAMSS_CSID_RST_CMD(csid->camss->version));
 
 	time = wait_for_completion_timeout(&csid->reset_complete,
 		msecs_to_jiffies(CSID_RESET_TIMEOUT_MS));
@@ -377,6 +384,7 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 {
 	struct csid_device *csid = v4l2_get_subdevdata(sd);
 	struct csid_testgen_config *tg = &csid->testgen;
+	enum camss_version ver = csid->camss->version;
 	u32 val;
 
 	if (enable) {
@@ -409,13 +417,14 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			/* 1:0 VC */
 			val = ((CAMSS_CSID_TG_VC_CFG_V_BLANKING & 0xff) << 24) |
 			      ((CAMSS_CSID_TG_VC_CFG_H_BLANKING & 0x7ff) << 13);
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_VC_CFG);
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_VC_CFG(ver));
 
 			/* 28:16 bytes per lines, 12:0 num of lines */
 			val = ((num_bytes_per_line & 0x1fff) << 16) |
 			      (num_lines & 0x1fff);
 			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_0(0));
+				       CAMSS_CSID_TG_DT_n_CGG_0(ver, 0));
 
 			dt = csid_get_fmt_entry(
 				csid->fmt[MSM_CSID_PAD_SRC].code)->data_type;
@@ -423,12 +432,12 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			/* 5:0 data type */
 			val = dt;
 			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_1(0));
+				       CAMSS_CSID_TG_DT_n_CGG_1(ver, 0));
 
 			/* 2:0 output test pattern */
 			val = tg->payload_mode;
 			writel_relaxed(val, csid->base +
-				       CAMSS_CSID_TG_DT_n_CGG_2(0));
+				       CAMSS_CSID_TG_DT_n_CGG_2(ver, 0));
 
 			df = csid_get_fmt_entry(
 				csid->fmt[MSM_CSID_PAD_SRC].code)->decode_format;
@@ -457,22 +466,27 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 
 		dt_shift = (cid % 4) * 8;
 
-		val = readl_relaxed(csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
+		val = readl_relaxed(csid->base +
+				    CAMSS_CSID_CID_LUT_VC_n(ver, vc));
 		val &= ~(0xff << dt_shift);
 		val |= dt << dt_shift;
-		writel_relaxed(val, csid->base + CAMSS_CSID_CID_LUT_VC_n(vc));
+		writel_relaxed(val, csid->base +
+			       CAMSS_CSID_CID_LUT_VC_n(ver, vc));
 
 		val = (df << 4) | 0x3;
-		writel_relaxed(val, csid->base + CAMSS_CSID_CID_n_CFG(cid));
+		writel_relaxed(val, csid->base +
+			       CAMSS_CSID_CID_n_CFG(ver, cid));
 
 		if (tg->enabled) {
 			val = CAMSS_CSID_TG_CTRL_ENABLE;
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_CTRL(ver));
 		}
 	} else {
 		if (tg->enabled) {
 			val = CAMSS_CSID_TG_CTRL_DISABLE;
-			writel_relaxed(val, csid->base + CAMSS_CSID_TG_CTRL);
+			writel_relaxed(val, csid->base +
+				       CAMSS_CSID_TG_CTRL(ver));
 		}
 	}
 
-- 
cgit v1.2.3


From e08c7f8696200a22b7f5a05f139231ad202efdc7 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:32 -0400
Subject: media: camss: ispif: Add support for 8x96

ISPIF hardware modules on 8x16 and 8x96 are similar. However on
8x96 the ISPIF routes data to two VFE hardware modules. Add
separate interrupt handler for 8x96 to handle the additional
interrupts.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-ispif.c | 76 ++++++++++++++++++++++++-
 1 file changed, 73 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index 2c6c0d2d6acf..ae8073274624 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -116,13 +116,77 @@ static const u32 ispif_formats[] = {
 };
 
 /*
- * ispif_isr - ISPIF module interrupt handler
+ * ispif_isr_8x96 - ISPIF module interrupt handler for 8x96
  * @irq: Interrupt line
  * @dev: ISPIF device
  *
  * Return IRQ_HANDLED on success
  */
-static irqreturn_t ispif_isr(int irq, void *dev)
+static irqreturn_t ispif_isr_8x96(int irq, void *dev)
+{
+	struct ispif_device *ispif = dev;
+	u32 value0, value1, value2, value3, value4, value5;
+
+	value0 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_0(0));
+	value1 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_1(0));
+	value2 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_2(0));
+	value3 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_0(1));
+	value4 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_1(1));
+	value5 = readl_relaxed(ispif->base + ISPIF_VFE_m_IRQ_STATUS_2(1));
+
+	writel_relaxed(value0, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(0));
+	writel_relaxed(value1, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(0));
+	writel_relaxed(value2, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(0));
+	writel_relaxed(value3, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_0(1));
+	writel_relaxed(value4, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_1(1));
+	writel_relaxed(value5, ispif->base + ISPIF_VFE_m_IRQ_CLEAR_2(1));
+
+	writel(0x1, ispif->base + ISPIF_IRQ_GLOBAL_CLEAR_CMD);
+
+	if ((value0 >> 27) & 0x1)
+		complete(&ispif->reset_complete);
+
+	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 pix0 overflow\n");
+
+	if (unlikely(value0 & ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi0 overflow\n");
+
+	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 pix1 overflow\n");
+
+	if (unlikely(value1 & ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi1 overflow\n");
+
+	if (unlikely(value2 & ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE0 rdi2 overflow\n");
+
+	if (unlikely(value3 & ISPIF_VFE_m_IRQ_STATUS_0_PIX0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 pix0 overflow\n");
+
+	if (unlikely(value3 & ISPIF_VFE_m_IRQ_STATUS_0_RDI0_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 rdi0 overflow\n");
+
+	if (unlikely(value4 & ISPIF_VFE_m_IRQ_STATUS_1_PIX1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 pix1 overflow\n");
+
+	if (unlikely(value4 & ISPIF_VFE_m_IRQ_STATUS_1_RDI1_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 rdi1 overflow\n");
+
+	if (unlikely(value5 & ISPIF_VFE_m_IRQ_STATUS_2_RDI2_OVERFLOW))
+		dev_err_ratelimited(to_device(ispif), "VFE1 rdi2 overflow\n");
+
+	return IRQ_HANDLED;
+}
+
+/*
+ * ispif_isr_8x16 - ISPIF module interrupt handler for 8x16
+ * @irq: Interrupt line
+ * @dev: ISPIF device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t ispif_isr_8x16(int irq, void *dev)
 {
 	struct ispif_device *ispif = dev;
 	u32 value0, value1, value2;
@@ -959,8 +1023,14 @@ int msm_ispif_subdev_init(struct ispif_device *ispif,
 	ispif->irq = r->start;
 	snprintf(ispif->irq_name, sizeof(ispif->irq_name), "%s_%s",
 		 dev_name(dev), MSM_ISPIF_NAME);
-	ret = devm_request_irq(dev, ispif->irq, ispif_isr,
+	if (to_camss(ispif)->version == CAMSS_8x16)
+		ret = devm_request_irq(dev, ispif->irq, ispif_isr_8x16,
 			       IRQF_TRIGGER_RISING, ispif->irq_name, ispif);
+	else if (to_camss(ispif)->version == CAMSS_8x96)
+		ret = devm_request_irq(dev, ispif->irq, ispif_isr_8x96,
+			       IRQF_TRIGGER_RISING, ispif->irq_name, ispif);
+	else
+		ret = -EINVAL;
 	if (ret < 0) {
 		dev_err(dev, "request_irq failed: %d\n", ret);
 		return ret;
-- 
cgit v1.2.3


From 051a01ac9cf141f0d555488fd0c060949bd4e8b6 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:33 -0400
Subject: media: camss: vfe: Split to hardware dependent and independent parts

This will allow to add support for different hardware.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/Makefile        |    1 +
 drivers/media/platform/qcom/camss/camss-vfe-4-1.c | 1006 +++++++++++++++++++
 drivers/media/platform/qcom/camss/camss-vfe.c     | 1074 ++-------------------
 drivers/media/platform/qcom/camss/camss-vfe.h     |   73 +-
 4 files changed, 1169 insertions(+), 985 deletions(-)
 create mode 100644 drivers/media/platform/qcom/camss/camss-vfe-4-1.c

diff --git a/drivers/media/platform/qcom/camss/Makefile b/drivers/media/platform/qcom/camss/Makefile
index 36b9f7cc3340..38dc56e1630c 100644
--- a/drivers/media/platform/qcom/camss/Makefile
+++ b/drivers/media/platform/qcom/camss/Makefile
@@ -7,6 +7,7 @@ qcom-camss-objs += \
 		camss-csiphy-3ph-1-0.o \
 		camss-csiphy.o \
 		camss-ispif.o \
+		camss-vfe-4-1.o \
 		camss-vfe.o \
 		camss-video.o \
 
diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
new file mode 100644
index 000000000000..070c0c381f1b
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
@@ -0,0 +1,1006 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-vfe-4-1.c
+ *
+ * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module v4.1
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+
+#include "camss-vfe.h"
+
+#define VFE_0_HW_VERSION		0x000
+
+#define VFE_0_GLOBAL_RESET_CMD		0x00c
+#define VFE_0_GLOBAL_RESET_CMD_CORE	BIT(0)
+#define VFE_0_GLOBAL_RESET_CMD_CAMIF	BIT(1)
+#define VFE_0_GLOBAL_RESET_CMD_BUS	BIT(2)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	BIT(3)
+#define VFE_0_GLOBAL_RESET_CMD_REGISTER	BIT(4)
+#define VFE_0_GLOBAL_RESET_CMD_TIMER	BIT(5)
+#define VFE_0_GLOBAL_RESET_CMD_PM	BIT(6)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	BIT(7)
+#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	BIT(8)
+
+#define VFE_0_MODULE_CFG		0x018
+#define VFE_0_MODULE_CFG_DEMUX			BIT(2)
+#define VFE_0_MODULE_CFG_CHROMA_UPSAMPLE	BIT(3)
+#define VFE_0_MODULE_CFG_SCALE_ENC		BIT(23)
+#define VFE_0_MODULE_CFG_CROP_ENC		BIT(27)
+
+#define VFE_0_CORE_CFG			0x01c
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
+
+#define VFE_0_IRQ_CMD			0x024
+#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	BIT(0)
+
+#define VFE_0_IRQ_MASK_0		0x028
+#define VFE_0_IRQ_MASK_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_MASK_0_CAMIF_EOF			BIT(1)
+#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_MASK_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_MASK_1		0x02c
+#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			BIT(0)
+#define VFE_0_IRQ_MASK_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	BIT((n) + 9)
+#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_CLEAR_0		0x030
+#define VFE_0_IRQ_CLEAR_1		0x034
+
+#define VFE_0_IRQ_STATUS_0		0x038
+#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_STATUS_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_STATUS_1		0x03c
+#define VFE_0_IRQ_STATUS_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_COMPOSITE_MASK_0	0x40
+#define VFE_0_VIOLATION_STATUS		0x48
+
+#define VFE_0_BUS_CMD			0x4c
+#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	BIT(x)
+
+#define VFE_0_BUS_CFG			0x050
+
+#define VFE_0_BUS_XBAR_CFG_x(x)		(0x58 + 0x4 * ((x) / 2))
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			BIT(1)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	5
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	6
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	7
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x06c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT	1
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x070 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x074 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x078 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1f << 2)
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x07c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x080 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x084 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
+							(0x088 + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
+							(0x08c + 0x24 * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
+
+#define VFE_0_BUS_PING_PONG_STATUS	0x268
+
+#define VFE_0_BUS_BDG_CMD		0x2c0
+#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
+
+#define VFE_0_BUS_BDG_QOS_CFG_0		0x2c4
+#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa5aaa5
+#define VFE_0_BUS_BDG_QOS_CFG_1		0x2c8
+#define VFE_0_BUS_BDG_QOS_CFG_2		0x2cc
+#define VFE_0_BUS_BDG_QOS_CFG_3		0x2d0
+#define VFE_0_BUS_BDG_QOS_CFG_4		0x2d4
+#define VFE_0_BUS_BDG_QOS_CFG_5		0x2d8
+#define VFE_0_BUS_BDG_QOS_CFG_6		0x2dc
+#define VFE_0_BUS_BDG_QOS_CFG_7		0x2e0
+#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa5
+
+#define VFE_0_RDI_CFG_x(x)		(0x2e8 + (0x4 * (x)))
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
+#define VFE_0_RDI_CFG_x_RDI_EN_BIT		BIT(2)
+#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
+#define VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(r)	BIT(16 + (r))
+
+#define VFE_0_CAMIF_CMD				0x2f4
+#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
+#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
+#define VFE_0_CAMIF_CMD_NO_CHANGE		3
+#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	BIT(2)
+#define VFE_0_CAMIF_CFG				0x2f8
+#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		BIT(6)
+#define VFE_0_CAMIF_FRAME_CFG			0x300
+#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x304
+#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x308
+#define VFE_0_CAMIF_SUBSAMPLE_CFG_0		0x30c
+#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x314
+#define VFE_0_CAMIF_STATUS			0x31c
+#define VFE_0_CAMIF_STATUS_HALT			BIT(31)
+
+#define VFE_0_REG_UPDATE			0x378
+#define VFE_0_REG_UPDATE_RDIn(n)		BIT(1 + (n))
+#define VFE_0_REG_UPDATE_line_n(n)		\
+			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
+
+#define VFE_0_DEMUX_CFG				0x424
+#define VFE_0_DEMUX_CFG_PERIOD			0x3
+#define VFE_0_DEMUX_GAIN_0			0x428
+#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
+#define VFE_0_DEMUX_GAIN_1			0x42c
+#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
+#define VFE_0_DEMUX_EVEN_CFG			0x438
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
+#define VFE_0_DEMUX_ODD_CFG			0x43c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
+
+#define VFE_0_SCALE_ENC_Y_CFG			0x75c
+#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x760
+#define VFE_0_SCALE_ENC_Y_H_PHASE		0x764
+#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x76c
+#define VFE_0_SCALE_ENC_Y_V_PHASE		0x770
+#define VFE_0_SCALE_ENC_CBCR_CFG		0x778
+#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x77c
+#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x780
+#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x790
+#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x794
+
+#define VFE_0_CROP_ENC_Y_WIDTH			0x854
+#define VFE_0_CROP_ENC_Y_HEIGHT			0x858
+#define VFE_0_CROP_ENC_CBCR_WIDTH		0x85c
+#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x860
+
+#define VFE_0_CLAMP_ENC_MAX_CFG			0x874
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
+#define VFE_0_CLAMP_ENC_MIN_CFG			0x878
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
+
+#define VFE_0_CGC_OVERRIDE_1			0x974
+#define VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(x)	BIT(x)
+
+#define CAMIF_TIMEOUT_SLEEP_US 1000
+#define CAMIF_TIMEOUT_ALL_US 1000000
+
+#define MSM_VFE_VFE0_UB_SIZE 1023
+#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
+
+static void vfe_hw_version_read(struct vfe_device *vfe, struct device *dev)
+{
+	u32 hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
+
+	dev_dbg(dev, "VFE HW Version = 0x%08x\n", hw_version);
+}
+
+static u16 vfe_get_ub_size(u8 vfe_id)
+{
+	if (vfe_id == 0)
+		return MSM_VFE_VFE0_UB_SIZE_RDI;
+
+	return 0;
+}
+
+static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
+}
+
+static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits | set_bits, vfe->base + reg);
+}
+
+static void vfe_global_reset(struct vfe_device *vfe)
+{
+	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
+			 VFE_0_GLOBAL_RESET_CMD_PM		|
+			 VFE_0_GLOBAL_RESET_CMD_TIMER		|
+			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS		|
+			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
+			 VFE_0_GLOBAL_RESET_CMD_CORE;
+
+	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
+}
+
+static void vfe_halt_request(struct vfe_device *vfe)
+{
+	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
+		       vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_halt_clear(struct vfe_device *vfe)
+{
+	writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+}
+
+static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
+}
+
+#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
+
+static int vfe_word_per_line(u32 format, u32 pixel_per_line)
+{
+	int val = 0;
+
+	switch (format) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		val = CALC_WORD(pixel_per_line, 1, 8);
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_VYUY:
+		val = CALC_WORD(pixel_per_line, 2, 8);
+		break;
+	}
+
+	return val;
+}
+
+static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
+			     u16 *width, u16 *height, u16 *bytesperline)
+{
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		if (plane == 1)
+			*height /= 2;
+		break;
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		break;
+	}
+}
+
+static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
+			      struct v4l2_pix_format_mplane *pix,
+			      u8 plane, u32 enable)
+{
+	u32 reg;
+
+	if (enable) {
+		u16 width = 0, height = 0, bytesperline = 0, wpl;
+
+		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
+
+		wpl = vfe_word_per_line(pix->pixelformat, width);
+
+		reg = height - 1;
+		reg |= ((wpl + 1) / 2 - 1) << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+
+		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
+
+		reg = 0x3;
+		reg |= (height - 1) << 4;
+		reg |= wpl << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	} else {
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	}
+}
+
+static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base +
+			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+
+	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
+
+	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
+		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
+
+	writel_relaxed(reg,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+}
+
+static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
+					 u32 pattern)
+{
+	writel_relaxed(pattern,
+	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
+}
+
+static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm,
+			      u16 offset, u16 depth)
+{
+	u32 reg;
+
+	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
+		depth;
+	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
+}
+
+static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
+{
+	wmb();
+	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
+	wmb();
+}
+
+static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
+}
+
+static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
+}
+
+static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
+
+	return (reg >> wm) & 0x1;
+}
+
+static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
+{
+	if (enable)
+		writel_relaxed(0x10000009, vfe->base + VFE_0_BUS_CFG);
+	else
+		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
+}
+
+static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
+				      enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	reg |= VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
+		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
+{
+	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
+		       vfe->base +
+		       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
+}
+
+static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
+					   enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
+			     u8 enable)
+{
+	struct vfe_line *line = container_of(output, struct vfe_line, output);
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	unsigned int i;
+
+	for (i = 0; i < output->wm_num; i++) {
+		if (i == 0) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
+				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		} else if (i == 1) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
+				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+		} else {
+			/* On current devices output->wm_num is always <= 2 */
+			break;
+		}
+
+		if (output->wm_idx[i] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+	}
+}
+
+static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
+{
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
+		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
+
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
+		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
+}
+
+static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
+	wmb();
+	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
+	wmb();
+}
+
+static inline void vfe_reg_update_clear(struct vfe_device *vfe,
+					enum vfe_line_id line_id)
+{
+	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
+}
+
+static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
+				   enum vfe_line_id line_id, u8 enable)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
+		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
+		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	}
+}
+
+static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
+				    enum vfe_line_id line_id, u8 enable)
+{
+	struct vfe_output *output = &vfe->line[line_id].output;
+	unsigned int i;
+	u32 irq_en0;
+	u32 irq_en1;
+	u32 comp_mask = 0;
+
+	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
+	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
+	for (i = 0; i < output->wm_num; i++) {
+		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
+							output->wm_idx[i]);
+		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
+	}
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	}
+}
+
+static void vfe_enable_irq_common(struct vfe_device *vfe)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
+		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
+
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+}
+
+static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val, even_cfg, odd_cfg;
+
+	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
+
+	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
+
+	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
+		break;
+	}
+
+	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
+	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
+}
+
+static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
+{
+	if (input / output >= 16)
+		return 0;
+
+	if (input / output >= 8)
+		return 1;
+
+	if (input / output >= 4)
+		return 2;
+
+	return 3;
+}
+
+static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 input, output;
+	u8 interp_reso;
+	u32 phase_mult;
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width;
+	output = line->compose.width;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height;
+	output = line->compose.height;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width;
+	output = line->compose.width / 2;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height;
+	output = line->compose.height;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
+		output = line->compose.height / 2;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (13 + interp_reso)) / output;
+	reg = (interp_reso << 20) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
+}
+
+static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 first, last;
+
+	first = line->crop.left;
+	last = line->crop.left + line->crop.width - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
+
+	first = line->crop.left / 2;
+	last = line->crop.left / 2 + line->crop.width / 2 - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
+		first = line->crop.top / 2;
+		last = line->crop.top / 2 + line->crop.height / 2 - 1;
+	}
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
+}
+
+static void vfe_set_clamp_cfg(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
+
+	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
+}
+
+static void vfe_set_qos(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
+	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
+
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
+	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
+}
+
+static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	u32 val = VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(wm);
+
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_CGC_OVERRIDE_1, val);
+	else
+		vfe_reg_clr(vfe, VFE_0_CGC_OVERRIDE_1, val);
+
+	wmb();
+}
+
+static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val;
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
+		break;
+	}
+
+	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2;
+	val |= line->fmt[MSM_VFE_PAD_SINK].height << 16;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG_0);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
+
+	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
+
+	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
+}
+
+static void vfe_set_camif_cmd(struct vfe_device *vfe, u8 enable)
+{
+	u32 cmd;
+
+	cmd = VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS | VFE_0_CAMIF_CMD_NO_CHANGE;
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+	wmb();
+
+	if (enable)
+		cmd = VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY;
+	else
+		cmd = VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY;
+
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+}
+
+static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
+{
+	u32 val = VFE_0_MODULE_CFG_DEMUX |
+		  VFE_0_MODULE_CFG_CHROMA_UPSAMPLE |
+		  VFE_0_MODULE_CFG_SCALE_ENC |
+		  VFE_0_MODULE_CFG_CROP_ENC;
+
+	if (enable)
+		writel_relaxed(val, vfe->base + VFE_0_MODULE_CFG);
+	else
+		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_CFG);
+}
+
+static int vfe_camif_wait_for_stop(struct vfe_device *vfe, struct device *dev)
+{
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
+				 val,
+				 (val & VFE_0_CAMIF_STATUS_HALT),
+				 CAMIF_TIMEOUT_SLEEP_US,
+				 CAMIF_TIMEOUT_ALL_US);
+	if (ret < 0)
+		dev_err(dev, "%s: camif stop timeout\n", __func__);
+
+	return ret;
+}
+
+static void vfe_isr_read(struct vfe_device *vfe, u32 *value0, u32 *value1)
+{
+	*value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
+	*value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
+
+	writel_relaxed(*value0, vfe->base + VFE_0_IRQ_CLEAR_0);
+	writel_relaxed(*value1, vfe->base + VFE_0_IRQ_CLEAR_1);
+
+	wmb();
+	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
+}
+
+static void vfe_violation_read(struct vfe_device *vfe)
+{
+	u32 violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
+
+	pr_err_ratelimited("VFE: violation = 0x%08x\n", violation);
+}
+
+/*
+ * vfe_isr - ISPIF module interrupt handler
+ * @irq: Interrupt line
+ * @dev: VFE device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t vfe_isr(int irq, void *dev)
+{
+	struct vfe_device *vfe = dev;
+	u32 value0, value1;
+	int i, j;
+
+	vfe->ops->isr_read(vfe, &value0, &value1);
+
+	trace_printk("VFE: status0 = 0x%08x, status1 = 0x%08x\n",
+		     value0, value1);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
+		vfe->isr_ops.reset_ack(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION)
+		vfe->ops->violation_read(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK)
+		vfe->isr_ops.halt_ack(vfe);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
+			vfe->isr_ops.reg_update(vfe, i);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
+		vfe->isr_ops.sof(vfe, VFE_LINE_PIX);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
+		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
+			vfe->isr_ops.sof(vfe, i);
+
+	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
+			vfe->isr_ops.comp_done(vfe, i);
+			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
+				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
+					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
+		}
+
+	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
+			vfe->isr_ops.wm_done(vfe, i);
+
+	return IRQ_HANDLED;
+}
+
+const struct vfe_hw_ops vfe_ops_4_1 = {
+	.hw_version_read = vfe_hw_version_read,
+	.get_ub_size = vfe_get_ub_size,
+	.global_reset = vfe_global_reset,
+	.halt_request = vfe_halt_request,
+	.halt_clear = vfe_halt_clear,
+	.wm_enable = vfe_wm_enable,
+	.wm_frame_based = vfe_wm_frame_based,
+	.wm_line_based = vfe_wm_line_based,
+	.wm_set_framedrop_period = vfe_wm_set_framedrop_period,
+	.wm_set_framedrop_pattern = vfe_wm_set_framedrop_pattern,
+	.wm_set_ub_cfg = vfe_wm_set_ub_cfg,
+	.bus_reload_wm = vfe_bus_reload_wm,
+	.wm_set_ping_addr = vfe_wm_set_ping_addr,
+	.wm_set_pong_addr = vfe_wm_set_pong_addr,
+	.wm_get_ping_pong_status = vfe_wm_get_ping_pong_status,
+	.bus_enable_wr_if = vfe_bus_enable_wr_if,
+	.bus_connect_wm_to_rdi = vfe_bus_connect_wm_to_rdi,
+	.wm_set_subsample = vfe_wm_set_subsample,
+	.bus_disconnect_wm_from_rdi = vfe_bus_disconnect_wm_from_rdi,
+	.set_xbar_cfg = vfe_set_xbar_cfg,
+	.set_rdi_cid = vfe_set_rdi_cid,
+	.reg_update = vfe_reg_update,
+	.reg_update_clear = vfe_reg_update_clear,
+	.enable_irq_wm_line = vfe_enable_irq_wm_line,
+	.enable_irq_pix_line = vfe_enable_irq_pix_line,
+	.enable_irq_common = vfe_enable_irq_common,
+	.set_demux_cfg = vfe_set_demux_cfg,
+	.set_scale_cfg = vfe_set_scale_cfg,
+	.set_crop_cfg = vfe_set_crop_cfg,
+	.set_clamp_cfg = vfe_set_clamp_cfg,
+	.set_qos = vfe_set_qos,
+	.set_cgc_override = vfe_set_cgc_override,
+	.set_camif_cfg = vfe_set_camif_cfg,
+	.set_camif_cmd = vfe_set_camif_cmd,
+	.set_module_cfg = vfe_set_module_cfg,
+	.camif_wait_for_stop = vfe_camif_wait_for_stop,
+	.isr_read = vfe_isr_read,
+	.violation_read = vfe_violation_read,
+	.isr = vfe_isr,
+};
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 474e1dd02891..7f07a22c3e4b 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -11,7 +11,6 @@
 #include <linux/completion.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
-#include <linux/iopoll.h>
 #include <linux/mutex.h>
 #include <linux/of.h>
 #include <linux/platform_device.h>
@@ -33,194 +32,6 @@
 #define to_vfe(ptr_line)	\
 	container_of(vfe_line_array(ptr_line), struct vfe_device, line)
 
-#define VFE_0_HW_VERSION		0x000
-
-#define VFE_0_GLOBAL_RESET_CMD		0x00c
-#define VFE_0_GLOBAL_RESET_CMD_CORE	(1 << 0)
-#define VFE_0_GLOBAL_RESET_CMD_CAMIF	(1 << 1)
-#define VFE_0_GLOBAL_RESET_CMD_BUS	(1 << 2)
-#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	(1 << 3)
-#define VFE_0_GLOBAL_RESET_CMD_REGISTER	(1 << 4)
-#define VFE_0_GLOBAL_RESET_CMD_TIMER	(1 << 5)
-#define VFE_0_GLOBAL_RESET_CMD_PM	(1 << 6)
-#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	(1 << 7)
-#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	(1 << 8)
-
-#define VFE_0_MODULE_CFG		0x018
-#define VFE_0_MODULE_CFG_DEMUX			(1 << 2)
-#define VFE_0_MODULE_CFG_CHROMA_UPSAMPLE	(1 << 3)
-#define VFE_0_MODULE_CFG_SCALE_ENC		(1 << 23)
-#define VFE_0_MODULE_CFG_CROP_ENC		(1 << 27)
-
-#define VFE_0_CORE_CFG			0x01c
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
-#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
-
-#define VFE_0_IRQ_CMD			0x024
-#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	(1 << 0)
-
-#define VFE_0_IRQ_MASK_0		0x028
-#define VFE_0_IRQ_MASK_0_CAMIF_SOF			(1 << 0)
-#define VFE_0_IRQ_MASK_0_CAMIF_EOF			(1 << 1)
-#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
-#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
-	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
-#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
-#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
-#define VFE_0_IRQ_MASK_0_RESET_ACK			(1 << 31)
-#define VFE_0_IRQ_MASK_1		0x02c
-#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			(1 << 0)
-#define VFE_0_IRQ_MASK_1_VIOLATION			(1 << 7)
-#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		(1 << 8)
-#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	(1 << ((n) + 9))
-#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			(1 << ((n) + 29))
-
-#define VFE_0_IRQ_CLEAR_0		0x030
-#define VFE_0_IRQ_CLEAR_1		0x034
-
-#define VFE_0_IRQ_STATUS_0		0x038
-#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			(1 << 0)
-#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		(1 << ((n) + 5))
-#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
-	((n) == VFE_LINE_PIX ? (1 << 4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
-#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	(1 << ((n) + 8))
-#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	(1 << ((n) + 25))
-#define VFE_0_IRQ_STATUS_0_RESET_ACK			(1 << 31)
-#define VFE_0_IRQ_STATUS_1		0x03c
-#define VFE_0_IRQ_STATUS_1_VIOLATION			(1 << 7)
-#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		(1 << 8)
-#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			(1 << ((n) + 29))
-
-#define VFE_0_IRQ_COMPOSITE_MASK_0	0x40
-#define VFE_0_VIOLATION_STATUS		0x48
-
-#define VFE_0_BUS_CMD			0x4c
-#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	(1 << (x))
-
-#define VFE_0_BUS_CFG			0x050
-
-#define VFE_0_BUS_XBAR_CFG_x(x)		(0x58 + 0x4 * ((x) / 2))
-#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			(1 << 1)
-#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	5
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	6
-#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	7
-
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x06c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT	1
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x070 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x074 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x078 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1F << 2)
-
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x07c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x080 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x084 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
-							(0x088 + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
-							(0x08c + 0x24 * (n))
-#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
-
-#define VFE_0_BUS_PING_PONG_STATUS	0x268
-
-#define VFE_0_BUS_BDG_CMD		0x2c0
-#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
-
-#define VFE_0_BUS_BDG_QOS_CFG_0		0x2c4
-#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa5aaa5
-#define VFE_0_BUS_BDG_QOS_CFG_1		0x2c8
-#define VFE_0_BUS_BDG_QOS_CFG_2		0x2cc
-#define VFE_0_BUS_BDG_QOS_CFG_3		0x2d0
-#define VFE_0_BUS_BDG_QOS_CFG_4		0x2d4
-#define VFE_0_BUS_BDG_QOS_CFG_5		0x2d8
-#define VFE_0_BUS_BDG_QOS_CFG_6		0x2dc
-#define VFE_0_BUS_BDG_QOS_CFG_7		0x2e0
-#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa5
-
-#define VFE_0_RDI_CFG_x(x)		(0x2e8 + (0x4 * (x)))
-#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
-#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
-#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
-#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
-#define VFE_0_RDI_CFG_x_RDI_EN_BIT		(1 << 2)
-#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
-#define VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(r)	(1 << (16 + (r)))
-
-#define VFE_0_CAMIF_CMD				0x2f4
-#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
-#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
-#define VFE_0_CAMIF_CMD_NO_CHANGE		3
-#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	(1 << 2)
-#define VFE_0_CAMIF_CFG				0x2f8
-#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		(1 << 6)
-#define VFE_0_CAMIF_FRAME_CFG			0x300
-#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x304
-#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x308
-#define VFE_0_CAMIF_SUBSAMPLE_CFG_0		0x30c
-#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x314
-#define VFE_0_CAMIF_STATUS			0x31c
-#define VFE_0_CAMIF_STATUS_HALT			(1 << 31)
-
-#define VFE_0_REG_UPDATE			0x378
-#define VFE_0_REG_UPDATE_RDIn(n)		(1 << (1 + (n)))
-#define VFE_0_REG_UPDATE_line_n(n)		\
-			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
-
-#define VFE_0_DEMUX_CFG				0x424
-#define VFE_0_DEMUX_CFG_PERIOD			0x3
-#define VFE_0_DEMUX_GAIN_0			0x428
-#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
-#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
-#define VFE_0_DEMUX_GAIN_1			0x42c
-#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
-#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
-#define VFE_0_DEMUX_EVEN_CFG			0x438
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
-#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
-#define VFE_0_DEMUX_ODD_CFG			0x43c
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
-#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
-
-#define VFE_0_SCALE_ENC_Y_CFG			0x75c
-#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x760
-#define VFE_0_SCALE_ENC_Y_H_PHASE		0x764
-#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x76c
-#define VFE_0_SCALE_ENC_Y_V_PHASE		0x770
-#define VFE_0_SCALE_ENC_CBCR_CFG		0x778
-#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x77c
-#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x780
-#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x790
-#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x794
-
-#define VFE_0_CROP_ENC_Y_WIDTH			0x854
-#define VFE_0_CROP_ENC_Y_HEIGHT			0x858
-#define VFE_0_CROP_ENC_CBCR_WIDTH		0x85c
-#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x860
-
-#define VFE_0_CLAMP_ENC_MAX_CFG			0x874
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
-#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
-#define VFE_0_CLAMP_ENC_MIN_CFG			0x878
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
-#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
-
-#define VFE_0_CGC_OVERRIDE_1			0x974
-#define VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(x)	(1 << (x))
-
 /* VFE reset timeout */
 #define VFE_RESET_TIMEOUT_MS 50
 /* VFE halt timeout */
@@ -232,9 +43,6 @@
 
 #define VFE_NEXT_SOF_MS 500
 
-#define CAMIF_TIMEOUT_SLEEP_US 1000
-#define CAMIF_TIMEOUT_ALL_US 1000000
-
 #define SCALER_RATIO_MAX 16
 
 static const struct {
@@ -326,541 +134,6 @@ static u8 vfe_get_bpp(u32 code)
 	return vfe_formats[0].bpp;
 }
 
-static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
-{
-	u32 bits = readl_relaxed(vfe->base + reg);
-
-	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
-}
-
-static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
-{
-	u32 bits = readl_relaxed(vfe->base + reg);
-
-	writel_relaxed(bits | set_bits, vfe->base + reg);
-}
-
-static void vfe_global_reset(struct vfe_device *vfe)
-{
-	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
-			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
-			 VFE_0_GLOBAL_RESET_CMD_PM		|
-			 VFE_0_GLOBAL_RESET_CMD_TIMER		|
-			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
-			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
-			 VFE_0_GLOBAL_RESET_CMD_BUS		|
-			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
-			 VFE_0_GLOBAL_RESET_CMD_CORE;
-
-	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
-}
-
-static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
-	else
-		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
-}
-
-static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
-	else
-		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
-			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_FRM_BASED_SHIFT);
-}
-
-#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
-
-static int vfe_word_per_line(uint32_t format, uint32_t pixel_per_line)
-{
-	int val = 0;
-
-	switch (format) {
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		val = CALC_WORD(pixel_per_line, 1, 8);
-		break;
-	case V4L2_PIX_FMT_YUYV:
-	case V4L2_PIX_FMT_YVYU:
-	case V4L2_PIX_FMT_UYVY:
-	case V4L2_PIX_FMT_VYUY:
-		val = CALC_WORD(pixel_per_line, 2, 8);
-		break;
-	}
-
-	return val;
-}
-
-static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
-			     u16 *width, u16 *height, u16 *bytesperline)
-{
-	switch (pix->pixelformat) {
-	case V4L2_PIX_FMT_NV12:
-	case V4L2_PIX_FMT_NV21:
-		*width = pix->width;
-		*height = pix->height;
-		*bytesperline = pix->plane_fmt[0].bytesperline;
-		if (plane == 1)
-			*height /= 2;
-		break;
-	case V4L2_PIX_FMT_NV16:
-	case V4L2_PIX_FMT_NV61:
-		*width = pix->width;
-		*height = pix->height;
-		*bytesperline = pix->plane_fmt[0].bytesperline;
-		break;
-	}
-}
-
-static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
-			      struct v4l2_pix_format_mplane *pix,
-			      u8 plane, u32 enable)
-{
-	u32 reg;
-
-	if (enable) {
-		u16 width = 0, height = 0, bytesperline = 0, wpl;
-
-		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
-
-		wpl = vfe_word_per_line(pix->pixelformat, width);
-
-		reg = height - 1;
-		reg |= ((wpl + 1) / 2 - 1) << 16;
-
-		writel_relaxed(reg, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
-
-		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
-
-		reg = 0x3;
-		reg |= (height - 1) << 4;
-		reg |= wpl << 16;
-
-		writel_relaxed(reg, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
-	} else {
-		writel_relaxed(0, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
-		writel_relaxed(0, vfe->base +
-			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
-	}
-}
-
-static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
-{
-	u32 reg;
-
-	reg = readl_relaxed(vfe->base +
-			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
-
-	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
-
-	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
-		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
-
-	writel_relaxed(reg,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
-}
-
-static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
-					 u32 pattern)
-{
-	writel_relaxed(pattern,
-	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
-}
-
-static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm, u16 offset,
-			      u16 depth)
-{
-	u32 reg;
-
-	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
-		depth;
-	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
-}
-
-static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
-{
-	wmb();
-	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
-	wmb();
-}
-
-static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
-{
-	writel_relaxed(addr,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
-}
-
-static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
-{
-	writel_relaxed(addr,
-		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
-}
-
-static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
-{
-	u32 reg;
-
-	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
-
-	return (reg >> wm) & 0x1;
-}
-
-static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
-{
-	if (enable)
-		writel_relaxed(0x10000009, vfe->base + VFE_0_BUS_CFG);
-	else
-		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
-}
-
-static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
-				      enum vfe_line_id id)
-{
-	u32 reg;
-
-	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
-	reg |= VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
-
-	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
-	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
-		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
-
-	switch (id) {
-	case VFE_LINE_RDI0:
-	default:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI1:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI2:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	}
-
-	if (wm % 2 == 1)
-		reg <<= 16;
-
-	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
-}
-
-static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
-{
-	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
-	       vfe->base +
-	       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
-}
-
-static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
-					   enum vfe_line_id id)
-{
-	u32 reg;
-
-	reg = VFE_0_RDI_CFG_x_RDI_Mr_FRAME_BASED_EN(id);
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(0), reg);
-
-	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
-
-	switch (id) {
-	case VFE_LINE_RDI0:
-	default:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI1:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	case VFE_LINE_RDI2:
-		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
-		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		break;
-	}
-
-	if (wm % 2 == 1)
-		reg <<= 16;
-
-	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
-}
-
-static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
-			     u8 enable)
-{
-	struct vfe_line *line = container_of(output, struct vfe_line, output);
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	unsigned int i;
-
-	for (i = 0; i < output->wm_num; i++) {
-		if (i == 0) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
-				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		} else if (i == 1) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
-			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
-				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
-		} else {
-			/* On current devices output->wm_num is always <= 2 */
-			break;
-		}
-
-		if (output->wm_idx[i] % 2 == 1)
-			reg <<= 16;
-
-		if (enable)
-			vfe_reg_set(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
-				    reg);
-		else
-			vfe_reg_clr(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
-				    reg);
-	}
-}
-
-static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
-{
-	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
-		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
-
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
-		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
-}
-
-static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
-{
-	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
-	wmb();
-	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
-	wmb();
-}
-
-static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
-				   enum vfe_line_id line_id, u8 enable)
-{
-	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
-		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
-	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
-		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
-
-	if (enable) {
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-	} else {
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-	}
-}
-
-static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
-				    enum vfe_line_id line_id, u8 enable)
-{
-	struct vfe_output *output = &vfe->line[line_id].output;
-	unsigned int i;
-	u32 irq_en0;
-	u32 irq_en1;
-	u32 comp_mask = 0;
-
-	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
-	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
-	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
-	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
-	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
-	for (i = 0; i < output->wm_num; i++) {
-		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
-							output->wm_idx[i]);
-		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
-	}
-
-	if (enable) {
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
-	} else {
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
-	}
-}
-
-static void vfe_enable_irq_common(struct vfe_device *vfe)
-{
-	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
-	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
-		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
-
-	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
-	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
-}
-
-static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 val, even_cfg, odd_cfg;
-
-	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
-
-	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
-	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
-
-	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
-	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
-
-	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
-	case MEDIA_BUS_FMT_YUYV8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
-		break;
-	case MEDIA_BUS_FMT_YVYU8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
-		break;
-	case MEDIA_BUS_FMT_UYVY8_2X8:
-	default:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
-		break;
-	case MEDIA_BUS_FMT_VYUY8_2X8:
-		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
-		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
-		break;
-	}
-
-	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
-	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
-}
-
-static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
-{
-	if (input / output >= 16)
-		return 0;
-
-	if (input / output >= 8)
-		return 1;
-
-	if (input / output >= 4)
-		return 2;
-
-	return 3;
-}
-
-static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	u16 input, output;
-	u8 interp_reso;
-	u32 phase_mult;
-
-	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].width;
-	output = line->compose.width;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].height;
-	output = line->compose.height;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
-
-	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].width;
-	output = line->compose.width / 2;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
-
-	input = line->fmt[MSM_VFE_PAD_SINK].height;
-	output = line->compose.height;
-	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
-		output = line->compose.height / 2;
-	reg = (output << 16) | input;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
-
-	interp_reso = vfe_calc_interp_reso(input, output);
-	phase_mult = input * (1 << (13 + interp_reso)) / output;
-	reg = (interp_reso << 20) | phase_mult;
-	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
-}
-
-static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
-	u32 reg;
-	u16 first, last;
-
-	first = line->crop.left;
-	last = line->crop.left + line->crop.width - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
-
-	first = line->crop.top;
-	last = line->crop.top + line->crop.height - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
-
-	first = line->crop.left / 2;
-	last = line->crop.left / 2 + line->crop.width / 2 - 1;
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
-
-	first = line->crop.top;
-	last = line->crop.top + line->crop.height - 1;
-	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
-		first = line->crop.top / 2;
-		last = line->crop.top / 2 + line->crop.height / 2 - 1;
-	}
-	reg = (first << 16) | last;
-	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
-}
-
-static void vfe_set_clamp_cfg(struct vfe_device *vfe)
-{
-	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
-		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
-		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
-
-	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
-
-	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
-		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
-		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
-
-	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
-}
-
 /*
  * vfe_reset - Trigger reset on VFE module and wait to complete
  * @vfe: VFE device
@@ -873,7 +146,7 @@ static int vfe_reset(struct vfe_device *vfe)
 
 	reinit_completion(&vfe->reset_complete);
 
-	vfe_global_reset(vfe);
+	vfe->ops->global_reset(vfe);
 
 	time = wait_for_completion_timeout(&vfe->reset_complete,
 		msecs_to_jiffies(VFE_RESET_TIMEOUT_MS));
@@ -897,8 +170,7 @@ static int vfe_halt(struct vfe_device *vfe)
 
 	reinit_completion(&vfe->halt_complete);
 
-	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
-		       vfe->base + VFE_0_BUS_BDG_CMD);
+	vfe->ops->halt_request(vfe);
 
 	time = wait_for_completion_timeout(&vfe->halt_complete,
 		msecs_to_jiffies(VFE_HALT_TIMEOUT_MS));
@@ -936,117 +208,6 @@ static void vfe_reset_output_maps(struct vfe_device *vfe)
 		vfe->wm_output_map[i] = VFE_LINE_NONE;
 }
 
-static void vfe_set_qos(struct vfe_device *vfe)
-{
-	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
-	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
-
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
-	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
-	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
-}
-
-static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
-{
-	u32 val = VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(wm);
-
-	if (enable)
-		vfe_reg_set(vfe, VFE_0_CGC_OVERRIDE_1, val);
-	else
-		vfe_reg_clr(vfe, VFE_0_CGC_OVERRIDE_1, val);
-
-	wmb();
-}
-
-static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
-{
-	u32 val = VFE_0_MODULE_CFG_DEMUX |
-		  VFE_0_MODULE_CFG_CHROMA_UPSAMPLE |
-		  VFE_0_MODULE_CFG_SCALE_ENC |
-		  VFE_0_MODULE_CFG_CROP_ENC;
-
-	if (enable)
-		writel_relaxed(val, vfe->base + VFE_0_MODULE_CFG);
-	else
-		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_CFG);
-}
-
-static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
-{
-	u32 val;
-
-	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
-	case MEDIA_BUS_FMT_YUYV8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
-		break;
-	case MEDIA_BUS_FMT_YVYU8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
-		break;
-	case MEDIA_BUS_FMT_UYVY8_2X8:
-	default:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
-		break;
-	case MEDIA_BUS_FMT_VYUY8_2X8:
-		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
-		break;
-	}
-
-	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].width * 2;
-	val |= line->fmt[MSM_VFE_PAD_SINK].height << 16;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
-
-	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
-
-	val = 0xffffffff;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG_0);
-
-	val = 0xffffffff;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
-
-	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
-	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
-
-	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
-	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
-}
-
-static void vfe_set_camif_cmd(struct vfe_device *vfe, u32 cmd)
-{
-	writel_relaxed(VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS |
-		       VFE_0_CAMIF_CMD_NO_CHANGE,
-		       vfe->base + VFE_0_CAMIF_CMD);
-	wmb();
-
-	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
-}
-
-static int vfe_camif_wait_for_stop(struct vfe_device *vfe)
-{
-	u32 val;
-	int ret;
-
-	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
-				 val,
-				 (val & VFE_0_CAMIF_STATUS_HALT),
-				 CAMIF_TIMEOUT_SLEEP_US,
-				 CAMIF_TIMEOUT_ALL_US);
-	if (ret < 0)
-		dev_err(vfe->camss->dev, "%s: camif stop timeout\n", __func__);
-
-	return ret;
-}
-
 static void vfe_output_init_addrs(struct vfe_device *vfe,
 				  struct vfe_output *output, u8 sync)
 {
@@ -1067,10 +228,10 @@ static void vfe_output_init_addrs(struct vfe_device *vfe,
 		else
 			pong_addr = ping_addr;
 
-		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], ping_addr);
-		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], pong_addr);
+		vfe->ops->wm_set_ping_addr(vfe, output->wm_idx[i], ping_addr);
+		vfe->ops->wm_set_pong_addr(vfe, output->wm_idx[i], pong_addr);
 		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			vfe->ops->bus_reload_wm(vfe, output->wm_idx[i]);
 	}
 }
 
@@ -1086,9 +247,9 @@ static void vfe_output_update_ping_addr(struct vfe_device *vfe,
 		else
 			addr = 0;
 
-		vfe_wm_set_ping_addr(vfe, output->wm_idx[i], addr);
+		vfe->ops->wm_set_ping_addr(vfe, output->wm_idx[i], addr);
 		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			vfe->ops->bus_reload_wm(vfe, output->wm_idx[i]);
 	}
 }
 
@@ -1104,9 +265,9 @@ static void vfe_output_update_pong_addr(struct vfe_device *vfe,
 		else
 			addr = 0;
 
-		vfe_wm_set_pong_addr(vfe, output->wm_idx[i], addr);
+		vfe->ops->wm_set_pong_addr(vfe, output->wm_idx[i], addr);
 		if (sync)
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			vfe->ops->bus_reload_wm(vfe, output->wm_idx[i]);
 	}
 
 }
@@ -1150,12 +311,13 @@ static void vfe_output_frame_drop(struct vfe_device *vfe,
 	drop_period = VFE_FRAME_DROP_VAL + output->drop_update_idx;
 
 	for (i = 0; i < output->wm_num; i++) {
-		vfe_wm_set_framedrop_period(vfe, output->wm_idx[i],
-					    drop_period);
-		vfe_wm_set_framedrop_pattern(vfe, output->wm_idx[i],
-					     drop_pattern);
+		vfe->ops->wm_set_framedrop_period(vfe, output->wm_idx[i],
+						  drop_period);
+		vfe->ops->wm_set_framedrop_pattern(vfe, output->wm_idx[i],
+						   drop_pattern);
 	}
-	vfe_reg_update(vfe, container_of(output, struct vfe_line, output)->id);
+	vfe->ops->reg_update(vfe,
+			     container_of(output, struct vfe_line, output)->id);
 }
 
 static struct camss_buffer *vfe_buf_get_pending(struct vfe_output *output)
@@ -1352,24 +514,18 @@ static int vfe_enable_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output = &line->output;
+	const struct vfe_hw_ops *ops = vfe->ops;
 	unsigned long flags;
 	unsigned int i;
 	u16 ub_size;
 
-	switch (vfe->id) {
-	case 0:
-		ub_size = MSM_VFE_VFE0_UB_SIZE_RDI;
-		break;
-	case 1:
-		ub_size = MSM_VFE_VFE1_UB_SIZE_RDI;
-		break;
-	default:
+	ub_size = ops->get_ub_size(vfe->id);
+	if (!ub_size)
 		return -EINVAL;
-	}
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
-	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line->id);
+	ops->reg_update_clear(vfe, line->id);
 
 	if (output->state != VFE_OUTPUT_RESERVED) {
 		dev_err(vfe->camss->dev, "Output is not in reserved state %d\n",
@@ -1414,42 +570,42 @@ static int vfe_enable_output(struct vfe_line *line)
 	vfe_output_init_addrs(vfe, output, 0);
 
 	if (line->id != VFE_LINE_PIX) {
-		vfe_set_cgc_override(vfe, output->wm_idx[0], 1);
-		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 1);
-		vfe_bus_connect_wm_to_rdi(vfe, output->wm_idx[0], line->id);
-		vfe_wm_set_subsample(vfe, output->wm_idx[0]);
-		vfe_set_rdi_cid(vfe, line->id, 0);
-		vfe_wm_set_ub_cfg(vfe, output->wm_idx[0],
-				  (ub_size + 1) * output->wm_idx[0], ub_size);
-		vfe_wm_frame_based(vfe, output->wm_idx[0], 1);
-		vfe_wm_enable(vfe, output->wm_idx[0], 1);
-		vfe_bus_reload_wm(vfe, output->wm_idx[0]);
+		ops->set_cgc_override(vfe, output->wm_idx[0], 1);
+		ops->enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 1);
+		ops->bus_connect_wm_to_rdi(vfe, output->wm_idx[0], line->id);
+		ops->wm_set_subsample(vfe, output->wm_idx[0]);
+		ops->set_rdi_cid(vfe, line->id, 0);
+		ops->wm_set_ub_cfg(vfe, output->wm_idx[0],
+				   (ub_size + 1) * output->wm_idx[0], ub_size);
+		ops->wm_frame_based(vfe, output->wm_idx[0], 1);
+		ops->wm_enable(vfe, output->wm_idx[0], 1);
+		ops->bus_reload_wm(vfe, output->wm_idx[0]);
 	} else {
 		ub_size /= output->wm_num;
 		for (i = 0; i < output->wm_num; i++) {
-			vfe_set_cgc_override(vfe, output->wm_idx[i], 1);
-			vfe_wm_set_subsample(vfe, output->wm_idx[i]);
-			vfe_wm_set_ub_cfg(vfe, output->wm_idx[i],
-					  (ub_size + 1) * output->wm_idx[i],
-					  ub_size);
-			vfe_wm_line_based(vfe, output->wm_idx[i],
+			ops->set_cgc_override(vfe, output->wm_idx[i], 1);
+			ops->wm_set_subsample(vfe, output->wm_idx[i]);
+			ops->wm_set_ub_cfg(vfe, output->wm_idx[i],
+					   (ub_size + 1) * output->wm_idx[i],
+					   ub_size);
+			ops->wm_line_based(vfe, output->wm_idx[i],
 					&line->video_out.active_fmt.fmt.pix_mp,
 					i, 1);
-			vfe_wm_enable(vfe, output->wm_idx[i], 1);
-			vfe_bus_reload_wm(vfe, output->wm_idx[i]);
+			ops->wm_enable(vfe, output->wm_idx[i], 1);
+			ops->bus_reload_wm(vfe, output->wm_idx[i]);
 		}
-		vfe_enable_irq_pix_line(vfe, 0, line->id, 1);
-		vfe_set_module_cfg(vfe, 1);
-		vfe_set_camif_cfg(vfe, line);
-		vfe_set_xbar_cfg(vfe, output, 1);
-		vfe_set_demux_cfg(vfe, line);
-		vfe_set_scale_cfg(vfe, line);
-		vfe_set_crop_cfg(vfe, line);
-		vfe_set_clamp_cfg(vfe);
-		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY);
+		ops->enable_irq_pix_line(vfe, 0, line->id, 1);
+		ops->set_module_cfg(vfe, 1);
+		ops->set_camif_cfg(vfe, line);
+		ops->set_xbar_cfg(vfe, output, 1);
+		ops->set_demux_cfg(vfe, line);
+		ops->set_scale_cfg(vfe, line);
+		ops->set_crop_cfg(vfe, line);
+		ops->set_clamp_cfg(vfe);
+		ops->set_camif_cmd(vfe, 1);
 	}
 
-	vfe_reg_update(vfe, line->id);
+	ops->reg_update(vfe, line->id);
 
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
@@ -1460,6 +616,7 @@ static int vfe_disable_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output = &line->output;
+	const struct vfe_hw_ops *ops = vfe->ops;
 	unsigned long flags;
 	unsigned long time;
 	unsigned int i;
@@ -1476,9 +633,9 @@ static int vfe_disable_output(struct vfe_line *line)
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 	for (i = 0; i < output->wm_num; i++)
-		vfe_wm_enable(vfe, output->wm_idx[i], 0);
+		ops->wm_enable(vfe, output->wm_idx[i], 0);
 
-	vfe_reg_update(vfe, line->id);
+	ops->reg_update(vfe, line->id);
 	output->wait_reg_update = 1;
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
@@ -1490,25 +647,26 @@ static int vfe_disable_output(struct vfe_line *line)
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
 	if (line->id != VFE_LINE_PIX) {
-		vfe_wm_frame_based(vfe, output->wm_idx[0], 0);
-		vfe_bus_disconnect_wm_from_rdi(vfe, output->wm_idx[0], line->id);
-		vfe_enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 0);
-		vfe_set_cgc_override(vfe, output->wm_idx[0], 0);
+		ops->wm_frame_based(vfe, output->wm_idx[0], 0);
+		ops->bus_disconnect_wm_from_rdi(vfe, output->wm_idx[0],
+						line->id);
+		ops->enable_irq_wm_line(vfe, output->wm_idx[0], line->id, 0);
+		ops->set_cgc_override(vfe, output->wm_idx[0], 0);
 		spin_unlock_irqrestore(&vfe->output_lock, flags);
 	} else {
 		for (i = 0; i < output->wm_num; i++) {
-			vfe_wm_line_based(vfe, output->wm_idx[i], NULL, i, 0);
-			vfe_set_cgc_override(vfe, output->wm_idx[i], 0);
+			ops->wm_line_based(vfe, output->wm_idx[i], NULL, i, 0);
+			ops->set_cgc_override(vfe, output->wm_idx[i], 0);
 		}
 
-		vfe_enable_irq_pix_line(vfe, 0, line->id, 0);
-		vfe_set_module_cfg(vfe, 0);
-		vfe_set_xbar_cfg(vfe, output, 0);
+		ops->enable_irq_pix_line(vfe, 0, line->id, 0);
+		ops->set_module_cfg(vfe, 0);
+		ops->set_xbar_cfg(vfe, output, 0);
 
-		vfe_set_camif_cmd(vfe, VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY);
+		ops->set_camif_cmd(vfe, 0);
 		spin_unlock_irqrestore(&vfe->output_lock, flags);
 
-		vfe_camif_wait_for_stop(vfe);
+		ops->camif_wait_for_stop(vfe, vfe->camss->dev);
 	}
 
 	return 0;
@@ -1528,11 +686,11 @@ static int vfe_enable(struct vfe_line *line)
 	mutex_lock(&vfe->stream_lock);
 
 	if (!vfe->stream_count) {
-		vfe_enable_irq_common(vfe);
+		vfe->ops->enable_irq_common(vfe);
 
-		vfe_bus_enable_wr_if(vfe, 1);
+		vfe->ops->bus_enable_wr_if(vfe, 1);
 
-		vfe_set_qos(vfe);
+		vfe->ops->set_qos(vfe);
 	}
 
 	vfe->stream_count++;
@@ -1559,7 +717,7 @@ error_get_output:
 	mutex_lock(&vfe->stream_lock);
 
 	if (vfe->stream_count == 1)
-		vfe_bus_enable_wr_if(vfe, 0);
+		vfe->ops->bus_enable_wr_if(vfe, 0);
 
 	vfe->stream_count--;
 
@@ -1585,7 +743,7 @@ static int vfe_disable(struct vfe_line *line)
 	mutex_lock(&vfe->stream_lock);
 
 	if (vfe->stream_count == 1)
-		vfe_bus_enable_wr_if(vfe, 0);
+		vfe->ops->bus_enable_wr_if(vfe, 0);
 
 	vfe->stream_count--;
 
@@ -1624,7 +782,7 @@ static void vfe_isr_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
 	unsigned long flags;
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
-	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
+	vfe->ops->reg_update_clear(vfe, line_id);
 
 	output = &vfe->line[line_id].output;
 
@@ -1694,7 +852,7 @@ static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
 	u64 ts = ktime_get_ns();
 	unsigned int i;
 
-	active_index = vfe_wm_get_ping_pong_status(vfe, wm);
+	active_index = vfe->ops->wm_get_ping_pong_status(vfe, wm);
 
 	spin_lock_irqsave(&vfe->output_lock, flags);
 
@@ -1736,12 +894,12 @@ static void vfe_isr_wm_done(struct vfe_device *vfe, u8 wm)
 
 	if (active_index)
 		for (i = 0; i < output->wm_num; i++)
-			vfe_wm_set_ping_addr(vfe, output->wm_idx[i],
-					     new_addr[i]);
+			vfe->ops->wm_set_ping_addr(vfe, output->wm_idx[i],
+						   new_addr[i]);
 	else
 		for (i = 0; i < output->wm_num; i++)
-			vfe_wm_set_pong_addr(vfe, output->wm_idx[i],
-					     new_addr[i]);
+			vfe->ops->wm_set_pong_addr(vfe, output->wm_idx[i],
+						   new_addr[i]);
 
 	spin_unlock_irqrestore(&vfe->output_lock, flags);
 
@@ -1772,67 +930,15 @@ static void vfe_isr_comp_done(struct vfe_device *vfe, u8 comp)
 		}
 }
 
-/*
- * vfe_isr - ISPIF module interrupt handler
- * @irq: Interrupt line
- * @dev: VFE device
- *
- * Return IRQ_HANDLED on success
- */
-static irqreturn_t vfe_isr(int irq, void *dev)
+static inline void vfe_isr_reset_ack(struct vfe_device *vfe)
 {
-	struct vfe_device *vfe = dev;
-	u32 value0, value1;
-	u32 violation;
-	int i, j;
-
-	value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
-	value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
-
-	writel_relaxed(value0, vfe->base + VFE_0_IRQ_CLEAR_0);
-	writel_relaxed(value1, vfe->base + VFE_0_IRQ_CLEAR_1);
-
-	wmb();
-	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
-
-	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
-		complete(&vfe->reset_complete);
-
-	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION) {
-		violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
-		dev_err_ratelimited(vfe->camss->dev,
-				    "VFE: violation = 0x%08x\n", violation);
-	}
-
-	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK) {
-		complete(&vfe->halt_complete);
-		writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
-	}
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
-			vfe_isr_reg_update(vfe, i);
-
-	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
-		vfe_isr_sof(vfe, VFE_LINE_PIX);
-
-	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
-		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
-			vfe_isr_sof(vfe, i);
-
-	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
-			vfe_isr_comp_done(vfe, i);
-			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
-				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
-					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
-		}
-
-	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
-		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
-			vfe_isr_wm_done(vfe, i);
+	complete(&vfe->reset_complete);
+}
 
-	return IRQ_HANDLED;
+static inline void vfe_isr_halt_ack(struct vfe_device *vfe)
+{
+	complete(&vfe->halt_complete);
+	vfe->ops->halt_clear(vfe);
 }
 
 /*
@@ -2142,15 +1248,11 @@ static int vfe_set_power(struct v4l2_subdev *sd, int on)
 	int ret;
 
 	if (on) {
-		u32 hw_version;
-
 		ret = vfe_get(vfe);
 		if (ret < 0)
 			return ret;
 
-		hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
-		dev_dbg(vfe->camss->dev,
-			"VFE HW Version = 0x%08x\n", hw_version);
+		vfe->ops->hw_version_read(vfe, vfe->camss->dev);
 	} else {
 		vfe_put(vfe);
 	}
@@ -2744,6 +1846,18 @@ int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
 	int i, j;
 	int ret;
 
+	vfe->isr_ops.reset_ack = vfe_isr_reset_ack;
+	vfe->isr_ops.halt_ack = vfe_isr_halt_ack;
+	vfe->isr_ops.reg_update = vfe_isr_reg_update;
+	vfe->isr_ops.sof = vfe_isr_sof;
+	vfe->isr_ops.comp_done = vfe_isr_comp_done;
+	vfe->isr_ops.wm_done = vfe_isr_wm_done;
+
+	if (camss->version == CAMSS_8x16)
+		vfe->ops = &vfe_ops_4_1;
+	else
+		return -EINVAL;
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
@@ -2765,7 +1879,7 @@ int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
 	vfe->irq = r->start;
 	snprintf(vfe->irq_name, sizeof(vfe->irq_name), "%s_%s%d",
 		 dev_name(dev), MSM_VFE_NAME, vfe->id);
-	ret = devm_request_irq(dev, vfe->irq, vfe_isr,
+	ret = devm_request_irq(dev, vfe->irq, vfe->ops->isr,
 			       IRQF_TRIGGER_RISING, vfe->irq_name, vfe);
 	if (ret < 0) {
 		dev_err(dev, "request_irq failed: %d\n", ret);
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
index 17d431e563da..19041ba6644a 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.h
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -26,11 +26,6 @@
 #define MSM_VFE_IMAGE_MASTERS_NUM 7
 #define MSM_VFE_COMPOSITE_IRQ_NUM 4
 
-#define MSM_VFE_VFE0_UB_SIZE 1023
-#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
-#define MSM_VFE_VFE1_UB_SIZE 1535
-#define MSM_VFE_VFE1_UB_SIZE_RDI (MSM_VFE_VFE1_UB_SIZE / 3)
-
 enum vfe_output_state {
 	VFE_OUTPUT_OFF,
 	VFE_OUTPUT_RESERVED,
@@ -78,6 +73,70 @@ struct vfe_line {
 	struct vfe_output output;
 };
 
+struct vfe_device;
+
+struct vfe_hw_ops {
+	void (*hw_version_read)(struct vfe_device *vfe, struct device *dev);
+	u16 (*get_ub_size)(u8 vfe_id);
+	void (*global_reset)(struct vfe_device *vfe);
+	void (*halt_request)(struct vfe_device *vfe);
+	void (*halt_clear)(struct vfe_device *vfe);
+	void (*wm_enable)(struct vfe_device *vfe, u8 wm, u8 enable);
+	void (*wm_frame_based)(struct vfe_device *vfe, u8 wm, u8 enable);
+	void (*wm_line_based)(struct vfe_device *vfe, u32 wm,
+			      struct v4l2_pix_format_mplane *pix,
+			      u8 plane, u32 enable);
+	void (*wm_set_framedrop_period)(struct vfe_device *vfe, u8 wm, u8 per);
+	void (*wm_set_framedrop_pattern)(struct vfe_device *vfe, u8 wm,
+					 u32 pattern);
+	void (*wm_set_ub_cfg)(struct vfe_device *vfe, u8 wm, u16 offset,
+			      u16 depth);
+	void (*bus_reload_wm)(struct vfe_device *vfe, u8 wm);
+	void (*wm_set_ping_addr)(struct vfe_device *vfe, u8 wm, u32 addr);
+	void (*wm_set_pong_addr)(struct vfe_device *vfe, u8 wm, u32 addr);
+	int (*wm_get_ping_pong_status)(struct vfe_device *vfe, u8 wm);
+	void (*bus_enable_wr_if)(struct vfe_device *vfe, u8 enable);
+	void (*bus_connect_wm_to_rdi)(struct vfe_device *vfe, u8 wm,
+				      enum vfe_line_id id);
+	void (*wm_set_subsample)(struct vfe_device *vfe, u8 wm);
+	void (*bus_disconnect_wm_from_rdi)(struct vfe_device *vfe, u8 wm,
+					   enum vfe_line_id id);
+	void (*set_xbar_cfg)(struct vfe_device *vfe, struct vfe_output *output,
+			     u8 enable);
+	void (*set_rdi_cid)(struct vfe_device *vfe, enum vfe_line_id id,
+			    u8 cid);
+	void (*reg_update)(struct vfe_device *vfe, enum vfe_line_id line_id);
+	void (*reg_update_clear)(struct vfe_device *vfe,
+				 enum vfe_line_id line_id);
+	void (*enable_irq_wm_line)(struct vfe_device *vfe, u8 wm,
+				   enum vfe_line_id line_id, u8 enable);
+	void (*enable_irq_pix_line)(struct vfe_device *vfe, u8 comp,
+				    enum vfe_line_id line_id, u8 enable);
+	void (*enable_irq_common)(struct vfe_device *vfe);
+	void (*set_demux_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_scale_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_crop_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_clamp_cfg)(struct vfe_device *vfe);
+	void (*set_qos)(struct vfe_device *vfe);
+	void (*set_cgc_override)(struct vfe_device *vfe, u8 wm, u8 enable);
+	void (*set_camif_cfg)(struct vfe_device *vfe, struct vfe_line *line);
+	void (*set_camif_cmd)(struct vfe_device *vfe, u8 enable);
+	void (*set_module_cfg)(struct vfe_device *vfe, u8 enable);
+	int (*camif_wait_for_stop)(struct vfe_device *vfe, struct device *dev);
+	void (*isr_read)(struct vfe_device *vfe, u32 *value0, u32 *value1);
+	void (*violation_read)(struct vfe_device *vfe);
+	irqreturn_t (*isr)(int irq, void *dev);
+};
+
+struct vfe_isr_ops {
+	void (*reset_ack)(struct vfe_device *vfe);
+	void (*halt_ack)(struct vfe_device *vfe);
+	void (*reg_update)(struct vfe_device *vfe, enum vfe_line_id line_id);
+	void (*sof)(struct vfe_device *vfe, enum vfe_line_id line_id);
+	void (*comp_done)(struct vfe_device *vfe, u8 comp);
+	void (*wm_done)(struct vfe_device *vfe, u8 wm);
+};
+
 struct vfe_device {
 	struct camss *camss;
 	u8 id;
@@ -97,6 +156,8 @@ struct vfe_device {
 	struct vfe_line line[MSM_VFE_LINE_NUM];
 	u32 reg_update;
 	u8 was_streaming;
+	const struct vfe_hw_ops *ops;
+	struct vfe_isr_ops isr_ops;
 };
 
 struct resources;
@@ -114,4 +175,6 @@ void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id);
 
 void msm_vfe_stop_streaming(struct vfe_device *vfe);
 
+extern const struct vfe_hw_ops vfe_ops_4_1;
+
 #endif /* QC_MSM_CAMSS_VFE_H */
-- 
cgit v1.2.3


From 4e1abf66feba454b1dc3d4c7d86759346ec1f134 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:34 -0400
Subject: media: camss: vfe: Add support for 8x96

Add VFE hardware dependent part for 8x96.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/Makefile        |    1 +
 drivers/media/platform/qcom/camss/camss-vfe-4-1.c |    6 +
 drivers/media/platform/qcom/camss/camss-vfe-4-7.c | 1051 +++++++++++++++++++++
 drivers/media/platform/qcom/camss/camss-vfe.c     |    4 +
 drivers/media/platform/qcom/camss/camss-vfe.h     |    2 +
 5 files changed, 1064 insertions(+)
 create mode 100644 drivers/media/platform/qcom/camss/camss-vfe-4-7.c

diff --git a/drivers/media/platform/qcom/camss/Makefile b/drivers/media/platform/qcom/camss/Makefile
index 38dc56e1630c..f5e6e255f2a1 100644
--- a/drivers/media/platform/qcom/camss/Makefile
+++ b/drivers/media/platform/qcom/camss/Makefile
@@ -8,6 +8,7 @@ qcom-camss-objs += \
 		camss-csiphy.o \
 		camss-ispif.o \
 		camss-vfe-4-1.o \
+		camss-vfe-4-7.o \
 		camss-vfe.o \
 		camss-video.o \
 
diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
index 070c0c381f1b..41184dcc33ca 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
@@ -789,6 +789,11 @@ static void vfe_set_qos(struct vfe_device *vfe)
 	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
 }
 
+static void vfe_set_ds(struct vfe_device *vfe)
+{
+	/* empty */
+}
+
 static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
 {
 	u32 val = VFE_0_CGC_OVERRIDE_1_IMAGE_Mx_CGC_OVERRIDE(wm);
@@ -995,6 +1000,7 @@ const struct vfe_hw_ops vfe_ops_4_1 = {
 	.set_crop_cfg = vfe_set_crop_cfg,
 	.set_clamp_cfg = vfe_set_clamp_cfg,
 	.set_qos = vfe_set_qos,
+	.set_ds = vfe_set_ds,
 	.set_cgc_override = vfe_set_cgc_override,
 	.set_camif_cfg = vfe_set_camif_cfg,
 	.set_camif_cmd = vfe_set_camif_cmd,
diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-7.c b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c
new file mode 100644
index 000000000000..45e6711a346f
--- /dev/null
+++ b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c
@@ -0,0 +1,1051 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * camss-vfe-4-7.c
+ *
+ * Qualcomm MSM Camera Subsystem - VFE (Video Front End) Module v4.7
+ *
+ * Copyright (c) 2013-2015, The Linux Foundation. All rights reserved.
+ * Copyright (C) 2015-2018 Linaro Ltd.
+ */
+
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+
+#include "camss-vfe.h"
+
+#define VFE_0_HW_VERSION		0x000
+
+#define VFE_0_GLOBAL_RESET_CMD		0x018
+#define VFE_0_GLOBAL_RESET_CMD_CORE	BIT(0)
+#define VFE_0_GLOBAL_RESET_CMD_CAMIF	BIT(1)
+#define VFE_0_GLOBAL_RESET_CMD_BUS	BIT(2)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_BDG	BIT(3)
+#define VFE_0_GLOBAL_RESET_CMD_REGISTER	BIT(4)
+#define VFE_0_GLOBAL_RESET_CMD_PM	BIT(5)
+#define VFE_0_GLOBAL_RESET_CMD_BUS_MISR	BIT(6)
+#define VFE_0_GLOBAL_RESET_CMD_TESTGEN	BIT(7)
+#define VFE_0_GLOBAL_RESET_CMD_DSP	BIT(8)
+#define VFE_0_GLOBAL_RESET_CMD_IDLE_CGC	BIT(9)
+
+#define VFE_0_MODULE_LENS_EN		0x040
+#define VFE_0_MODULE_LENS_EN_DEMUX		BIT(2)
+#define VFE_0_MODULE_LENS_EN_CHROMA_UPSAMPLE	BIT(3)
+
+#define VFE_0_MODULE_ZOOM_EN		0x04c
+#define VFE_0_MODULE_ZOOM_EN_SCALE_ENC		BIT(1)
+#define VFE_0_MODULE_ZOOM_EN_CROP_ENC		BIT(2)
+
+#define VFE_0_CORE_CFG			0x050
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB	0x5
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY	0x6
+#define VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY	0x7
+#define VFE_0_CORE_CFG_COMPOSITE_REG_UPDATE_EN	BIT(4)
+
+#define VFE_0_IRQ_CMD			0x058
+#define VFE_0_IRQ_CMD_GLOBAL_CLEAR	BIT(0)
+
+#define VFE_0_IRQ_MASK_0		0x05c
+#define VFE_0_IRQ_MASK_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_MASK_0_CAMIF_EOF			BIT(1)
+#define VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_MASK_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_MASK_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_MASK_1		0x060
+#define VFE_0_IRQ_MASK_1_CAMIF_ERROR			BIT(0)
+#define VFE_0_IRQ_MASK_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(n)	BIT((n) + 9)
+#define VFE_0_IRQ_MASK_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_CLEAR_0		0x064
+#define VFE_0_IRQ_CLEAR_1		0x068
+
+#define VFE_0_IRQ_STATUS_0		0x06c
+#define VFE_0_IRQ_STATUS_0_CAMIF_SOF			BIT(0)
+#define VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n)		BIT((n) + 5)
+#define VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(n)		\
+	((n) == VFE_LINE_PIX ? BIT(4) : VFE_0_IRQ_STATUS_0_RDIn_REG_UPDATE(n))
+#define VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(n)	BIT((n) + 8)
+#define VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(n)	BIT((n) + 25)
+#define VFE_0_IRQ_STATUS_0_RESET_ACK			BIT(31)
+#define VFE_0_IRQ_STATUS_1		0x070
+#define VFE_0_IRQ_STATUS_1_VIOLATION			BIT(7)
+#define VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK		BIT(8)
+#define VFE_0_IRQ_STATUS_1_RDIn_SOF(n)			BIT((n) + 29)
+
+#define VFE_0_IRQ_COMPOSITE_MASK_0	0x074
+#define VFE_0_VIOLATION_STATUS		0x07c
+
+#define VFE_0_BUS_CMD			0x80
+#define VFE_0_BUS_CMD_Mx_RLD_CMD(x)	BIT(x)
+
+#define VFE_0_BUS_CFG			0x084
+
+#define VFE_0_BUS_XBAR_CFG_x(x)		(0x90 + 0x4 * ((x) / 2))
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			BIT(2)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0x0
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0	0xc
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1	0xd
+#define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2	0xe
+
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(n)		(0x0a0 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT	0
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(n)	(0x0a4 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(n)	(0x0ac + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(n)		(0x0b4 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_BASED_SHIFT	1
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT	2
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK	(0x1f << 2)
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(n)		(0x0b8 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT	16
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(n)	(0x0bc + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(n)	(0x0c0 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(n)	\
+							(0x0c4 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(n)	\
+							(0x0c8 + 0x2c * (n))
+#define VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF	0xffffffff
+
+#define VFE_0_BUS_PING_PONG_STATUS	0x338
+
+#define VFE_0_BUS_BDG_CMD		0x400
+#define VFE_0_BUS_BDG_CMD_HALT_REQ	1
+
+#define VFE_0_BUS_BDG_QOS_CFG_0		0x404
+#define VFE_0_BUS_BDG_QOS_CFG_0_CFG	0xaaa9aaa9
+#define VFE_0_BUS_BDG_QOS_CFG_1		0x408
+#define VFE_0_BUS_BDG_QOS_CFG_2		0x40c
+#define VFE_0_BUS_BDG_QOS_CFG_3		0x410
+#define VFE_0_BUS_BDG_QOS_CFG_4		0x414
+#define VFE_0_BUS_BDG_QOS_CFG_5		0x418
+#define VFE_0_BUS_BDG_QOS_CFG_6		0x41c
+#define VFE_0_BUS_BDG_QOS_CFG_7		0x420
+#define VFE_0_BUS_BDG_QOS_CFG_7_CFG	0x0001aaa9
+
+#define VFE_0_BUS_BDG_DS_CFG_0		0x424
+#define VFE_0_BUS_BDG_DS_CFG_0_CFG	0xcccc0011
+#define VFE_0_BUS_BDG_DS_CFG_1		0x428
+#define VFE_0_BUS_BDG_DS_CFG_2		0x42c
+#define VFE_0_BUS_BDG_DS_CFG_3		0x430
+#define VFE_0_BUS_BDG_DS_CFG_4		0x434
+#define VFE_0_BUS_BDG_DS_CFG_5		0x438
+#define VFE_0_BUS_BDG_DS_CFG_6		0x43c
+#define VFE_0_BUS_BDG_DS_CFG_7		0x440
+#define VFE_0_BUS_BDG_DS_CFG_8		0x444
+#define VFE_0_BUS_BDG_DS_CFG_9		0x448
+#define VFE_0_BUS_BDG_DS_CFG_10		0x44c
+#define VFE_0_BUS_BDG_DS_CFG_11		0x450
+#define VFE_0_BUS_BDG_DS_CFG_12		0x454
+#define VFE_0_BUS_BDG_DS_CFG_13		0x458
+#define VFE_0_BUS_BDG_DS_CFG_14		0x45c
+#define VFE_0_BUS_BDG_DS_CFG_15		0x460
+#define VFE_0_BUS_BDG_DS_CFG_16		0x464
+#define VFE_0_BUS_BDG_DS_CFG_16_CFG	0x40000103
+
+#define VFE_0_RDI_CFG_x(x)		(0x46c + (0x4 * (x)))
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT	28
+#define VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK	(0xf << 28)
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT	4
+#define VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK		(0xf << 4)
+#define VFE_0_RDI_CFG_x_RDI_EN_BIT		BIT(2)
+#define VFE_0_RDI_CFG_x_MIPI_EN_BITS		0x3
+
+#define VFE_0_CAMIF_CMD				0x478
+#define VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY	0
+#define VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY	1
+#define VFE_0_CAMIF_CMD_NO_CHANGE		3
+#define VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS	BIT(2)
+#define VFE_0_CAMIF_CFG				0x47c
+#define VFE_0_CAMIF_CFG_VFE_OUTPUT_EN		BIT(6)
+#define VFE_0_CAMIF_FRAME_CFG			0x484
+#define VFE_0_CAMIF_WINDOW_WIDTH_CFG		0x488
+#define VFE_0_CAMIF_WINDOW_HEIGHT_CFG		0x48c
+#define VFE_0_CAMIF_SUBSAMPLE_CFG		0x490
+#define VFE_0_CAMIF_IRQ_FRAMEDROP_PATTERN	0x498
+#define VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN	0x49c
+#define VFE_0_CAMIF_STATUS			0x4a4
+#define VFE_0_CAMIF_STATUS_HALT			BIT(31)
+
+#define VFE_0_REG_UPDATE		0x4ac
+#define VFE_0_REG_UPDATE_RDIn(n)		BIT(1 + (n))
+#define VFE_0_REG_UPDATE_line_n(n)		\
+			((n) == VFE_LINE_PIX ? 1 : VFE_0_REG_UPDATE_RDIn(n))
+
+#define VFE_0_DEMUX_CFG				0x560
+#define VFE_0_DEMUX_CFG_PERIOD			0x3
+#define VFE_0_DEMUX_GAIN_0			0x564
+#define VFE_0_DEMUX_GAIN_0_CH0_EVEN		(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_0_CH0_ODD		(0x80 << 16)
+#define VFE_0_DEMUX_GAIN_1			0x568
+#define VFE_0_DEMUX_GAIN_1_CH1			(0x80 << 0)
+#define VFE_0_DEMUX_GAIN_1_CH2			(0x80 << 16)
+#define VFE_0_DEMUX_EVEN_CFG			0x574
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY	0xcac9
+#define VFE_0_DEMUX_ODD_CFG			0x578
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV	0x9cac
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU	0xac9c
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY	0xc9ca
+#define VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY	0xcac9
+
+#define VFE_0_SCALE_ENC_Y_CFG			0x91c
+#define VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE		0x920
+#define VFE_0_SCALE_ENC_Y_H_PHASE		0x924
+#define VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE		0x934
+#define VFE_0_SCALE_ENC_Y_V_PHASE		0x938
+#define VFE_0_SCALE_ENC_CBCR_CFG		0x948
+#define VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE	0x94c
+#define VFE_0_SCALE_ENC_CBCR_H_PHASE		0x950
+#define VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE	0x960
+#define VFE_0_SCALE_ENC_CBCR_V_PHASE		0x964
+
+#define VFE_0_CROP_ENC_Y_WIDTH			0x974
+#define VFE_0_CROP_ENC_Y_HEIGHT			0x978
+#define VFE_0_CROP_ENC_CBCR_WIDTH		0x97c
+#define VFE_0_CROP_ENC_CBCR_HEIGHT		0x980
+
+#define VFE_0_CLAMP_ENC_MAX_CFG			0x984
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH0		(0xff << 0)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH1		(0xff << 8)
+#define VFE_0_CLAMP_ENC_MAX_CFG_CH2		(0xff << 16)
+#define VFE_0_CLAMP_ENC_MIN_CFG			0x988
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH0		(0x0 << 0)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
+#define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
+
+#define CAMIF_TIMEOUT_SLEEP_US 1000
+#define CAMIF_TIMEOUT_ALL_US 1000000
+
+#define MSM_VFE_VFE0_UB_SIZE 2047
+#define MSM_VFE_VFE0_UB_SIZE_RDI (MSM_VFE_VFE0_UB_SIZE / 3)
+#define MSM_VFE_VFE1_UB_SIZE 1535
+#define MSM_VFE_VFE1_UB_SIZE_RDI (MSM_VFE_VFE1_UB_SIZE / 3)
+
+static void vfe_hw_version_read(struct vfe_device *vfe, struct device *dev)
+{
+	u32 hw_version = readl_relaxed(vfe->base + VFE_0_HW_VERSION);
+
+	dev_err(dev, "VFE HW Version = 0x%08x\n", hw_version);
+}
+
+static u16 vfe_get_ub_size(u8 vfe_id)
+{
+	if (vfe_id == 0)
+		return MSM_VFE_VFE0_UB_SIZE_RDI;
+	else if (vfe_id == 1)
+		return MSM_VFE_VFE1_UB_SIZE_RDI;
+
+	return 0;
+}
+
+static inline void vfe_reg_clr(struct vfe_device *vfe, u32 reg, u32 clr_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits & ~clr_bits, vfe->base + reg);
+}
+
+static inline void vfe_reg_set(struct vfe_device *vfe, u32 reg, u32 set_bits)
+{
+	u32 bits = readl_relaxed(vfe->base + reg);
+
+	writel_relaxed(bits | set_bits, vfe->base + reg);
+}
+
+static void vfe_global_reset(struct vfe_device *vfe)
+{
+	u32 reset_bits = VFE_0_GLOBAL_RESET_CMD_IDLE_CGC	|
+			 VFE_0_GLOBAL_RESET_CMD_DSP		|
+			 VFE_0_GLOBAL_RESET_CMD_TESTGEN		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_MISR	|
+			 VFE_0_GLOBAL_RESET_CMD_PM		|
+			 VFE_0_GLOBAL_RESET_CMD_REGISTER	|
+			 VFE_0_GLOBAL_RESET_CMD_BUS_BDG		|
+			 VFE_0_GLOBAL_RESET_CMD_BUS		|
+			 VFE_0_GLOBAL_RESET_CMD_CAMIF		|
+			 VFE_0_GLOBAL_RESET_CMD_CORE;
+
+	writel_relaxed(BIT(31), vfe->base + VFE_0_IRQ_MASK_0);
+	wmb();
+	writel_relaxed(reset_bits, vfe->base + VFE_0_GLOBAL_RESET_CMD);
+}
+
+static void vfe_halt_request(struct vfe_device *vfe)
+{
+	writel_relaxed(VFE_0_BUS_BDG_CMD_HALT_REQ,
+		       vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_halt_clear(struct vfe_device *vfe)
+{
+	writel_relaxed(0x0, vfe->base + VFE_0_BUS_BDG_CMD);
+}
+
+static void vfe_wm_enable(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_CFG(wm),
+			    1 << VFE_0_BUS_IMAGE_MASTER_n_WR_CFG_WR_PATH_SHIFT);
+}
+
+static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	if (enable)
+		vfe_reg_set(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_BASED_SHIFT);
+	else
+		vfe_reg_clr(vfe, VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm),
+			1 << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_BASED_SHIFT);
+}
+
+#define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
+
+static int vfe_word_per_line(u32 format, u32 pixel_per_line)
+{
+	int val = 0;
+
+	switch (format) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		val = CALC_WORD(pixel_per_line, 1, 8);
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_UYVY:
+	case V4L2_PIX_FMT_VYUY:
+		val = CALC_WORD(pixel_per_line, 2, 8);
+		break;
+	}
+
+	return val;
+}
+
+static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
+			     u16 *width, u16 *height, u16 *bytesperline)
+{
+	switch (pix->pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		if (plane == 1)
+			*height /= 2;
+		break;
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[0].bytesperline;
+		break;
+	}
+}
+
+static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
+			      struct v4l2_pix_format_mplane *pix,
+			      u8 plane, u32 enable)
+{
+	u32 reg;
+
+	if (enable) {
+		u16 width = 0, height = 0, bytesperline = 0, wpl;
+
+		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
+
+		wpl = vfe_word_per_line(pix->pixelformat, width);
+
+		reg = height - 1;
+		reg |= ((wpl + 3) / 4 - 1) << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+
+		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
+
+		reg = 0x3;
+		reg |= (height - 1) << 2;
+		reg |= ((wpl + 1) / 2) << 16;
+
+		writel_relaxed(reg, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	} else {
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
+		writel_relaxed(0, vfe->base +
+			       VFE_0_BUS_IMAGE_MASTER_n_WR_BUFFER_CFG(wm));
+	}
+}
+
+static void vfe_wm_set_framedrop_period(struct vfe_device *vfe, u8 wm, u8 per)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base +
+			    VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+
+	reg &= ~(VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK);
+
+	reg |= (per << VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_SHIFT)
+		& VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG_FRM_DROP_PER_MASK;
+
+	writel_relaxed(reg,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_ADDR_CFG(wm));
+}
+
+static void vfe_wm_set_framedrop_pattern(struct vfe_device *vfe, u8 wm,
+					 u32 pattern)
+{
+	writel_relaxed(pattern,
+	       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_FRAMEDROP_PATTERN(wm));
+}
+
+static void vfe_wm_set_ub_cfg(struct vfe_device *vfe, u8 wm,
+			      u16 offset, u16 depth)
+{
+	u32 reg;
+
+	reg = (offset << VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG_OFFSET_SHIFT) |
+		depth;
+	writel_relaxed(reg, vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_UB_CFG(wm));
+}
+
+static void vfe_bus_reload_wm(struct vfe_device *vfe, u8 wm)
+{
+	wmb();
+	writel_relaxed(VFE_0_BUS_CMD_Mx_RLD_CMD(wm), vfe->base + VFE_0_BUS_CMD);
+	wmb();
+}
+
+static void vfe_wm_set_ping_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PING_ADDR(wm));
+}
+
+static void vfe_wm_set_pong_addr(struct vfe_device *vfe, u8 wm, u32 addr)
+{
+	writel_relaxed(addr,
+		       vfe->base + VFE_0_BUS_IMAGE_MASTER_n_WR_PONG_ADDR(wm));
+}
+
+static int vfe_wm_get_ping_pong_status(struct vfe_device *vfe, u8 wm)
+{
+	u32 reg;
+
+	reg = readl_relaxed(vfe->base + VFE_0_BUS_PING_PONG_STATUS);
+
+	return (reg >> wm) & 0x1;
+}
+
+static void vfe_bus_enable_wr_if(struct vfe_device *vfe, u8 enable)
+{
+	if (enable)
+		writel_relaxed(0x101, vfe->base + VFE_0_BUS_CFG);
+	else
+		writel_relaxed(0, vfe->base + VFE_0_BUS_CFG);
+}
+
+static void vfe_bus_connect_wm_to_rdi(struct vfe_device *vfe, u8 wm,
+				      enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), reg);
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	reg |= ((3 * id) << VFE_0_RDI_CFG_x_RDI_STREAM_SEL_SHIFT) &
+		VFE_0_RDI_CFG_x_RDI_STREAM_SEL_MASK;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_set(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_wm_set_subsample(struct vfe_device *vfe, u8 wm)
+{
+	writel_relaxed(VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN_DEF,
+	       vfe->base +
+	       VFE_0_BUS_IMAGE_MASTER_n_WR_IRQ_SUBSAMPLE_PATTERN(wm));
+}
+
+static void vfe_bus_disconnect_wm_from_rdi(struct vfe_device *vfe, u8 wm,
+					   enum vfe_line_id id)
+{
+	u32 reg;
+
+	reg = VFE_0_RDI_CFG_x_RDI_EN_BIT;
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id), reg);
+
+	switch (id) {
+	case VFE_LINE_RDI0:
+	default:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI0 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI1:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI1 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	case VFE_LINE_RDI2:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_VAL_RDI2 <<
+		      VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		break;
+	}
+
+	if (wm % 2 == 1)
+		reg <<= 16;
+
+	vfe_reg_clr(vfe, VFE_0_BUS_XBAR_CFG_x(wm), reg);
+}
+
+static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
+			     u8 enable)
+{
+	struct vfe_line *line = container_of(output, struct vfe_line, output);
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	unsigned int i;
+
+	for (i = 0; i < output->wm_num; i++) {
+		if (i == 0) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
+				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+		} else if (i == 1) {
+			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
+				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+		}
+
+		if (output->wm_idx[i] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    reg);
+	}
+}
+
+static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
+{
+	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
+		    VFE_0_RDI_CFG_x_RDI_M0_SEL_MASK);
+
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(id),
+		    cid << VFE_0_RDI_CFG_x_RDI_M0_SEL_SHIFT);
+}
+
+static void vfe_reg_update(struct vfe_device *vfe, enum vfe_line_id line_id)
+{
+	vfe->reg_update |= VFE_0_REG_UPDATE_line_n(line_id);
+	wmb();
+	writel_relaxed(vfe->reg_update, vfe->base + VFE_0_REG_UPDATE);
+	wmb();
+}
+
+static inline void vfe_reg_update_clear(struct vfe_device *vfe,
+					enum vfe_line_id line_id)
+{
+	vfe->reg_update &= ~VFE_0_REG_UPDATE_line_n(line_id);
+}
+
+static void vfe_enable_irq_wm_line(struct vfe_device *vfe, u8 wm,
+				   enum vfe_line_id line_id, u8 enable)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(wm) |
+		      VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(wm) |
+		      VFE_0_IRQ_MASK_1_RDIn_SOF(line_id);
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+	}
+}
+
+static void vfe_enable_irq_pix_line(struct vfe_device *vfe, u8 comp,
+				    enum vfe_line_id line_id, u8 enable)
+{
+	struct vfe_output *output = &vfe->line[line_id].output;
+	unsigned int i;
+	u32 irq_en0;
+	u32 irq_en1;
+	u32 comp_mask = 0;
+
+	irq_en0 = VFE_0_IRQ_MASK_0_CAMIF_SOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_CAMIF_EOF;
+	irq_en0 |= VFE_0_IRQ_MASK_0_IMAGE_COMPOSITE_DONE_n(comp);
+	irq_en0 |= VFE_0_IRQ_MASK_0_line_n_REG_UPDATE(line_id);
+	irq_en1 = VFE_0_IRQ_MASK_1_CAMIF_ERROR;
+	for (i = 0; i < output->wm_num; i++) {
+		irq_en1 |= VFE_0_IRQ_MASK_1_IMAGE_MASTER_n_BUS_OVERFLOW(
+							output->wm_idx[i]);
+		comp_mask |= (1 << output->wm_idx[i]) << comp * 8;
+	}
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_set(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+		vfe_reg_clr(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+		vfe_reg_clr(vfe, VFE_0_IRQ_COMPOSITE_MASK_0, comp_mask);
+	}
+}
+
+static void vfe_enable_irq_common(struct vfe_device *vfe)
+{
+	u32 irq_en0 = VFE_0_IRQ_MASK_0_RESET_ACK;
+	u32 irq_en1 = VFE_0_IRQ_MASK_1_VIOLATION |
+		      VFE_0_IRQ_MASK_1_BUS_BDG_HALT_ACK;
+
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_0, irq_en0);
+	vfe_reg_set(vfe, VFE_0_IRQ_MASK_1, irq_en1);
+}
+
+static void vfe_set_demux_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val, even_cfg, odd_cfg;
+
+	writel_relaxed(VFE_0_DEMUX_CFG_PERIOD, vfe->base + VFE_0_DEMUX_CFG);
+
+	val = VFE_0_DEMUX_GAIN_0_CH0_EVEN | VFE_0_DEMUX_GAIN_0_CH0_ODD;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_0);
+
+	val = VFE_0_DEMUX_GAIN_1_CH1 | VFE_0_DEMUX_GAIN_1_CH2;
+	writel_relaxed(val, vfe->base + VFE_0_DEMUX_GAIN_1);
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YUYV;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YUYV;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_YVYU;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_YVYU;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_UYVY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_UYVY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		even_cfg = VFE_0_DEMUX_EVEN_CFG_PATTERN_VYUY;
+		odd_cfg = VFE_0_DEMUX_ODD_CFG_PATTERN_VYUY;
+		break;
+	}
+
+	writel_relaxed(even_cfg, vfe->base + VFE_0_DEMUX_EVEN_CFG);
+	writel_relaxed(odd_cfg, vfe->base + VFE_0_DEMUX_ODD_CFG);
+}
+
+static inline u8 vfe_calc_interp_reso(u16 input, u16 output)
+{
+	if (input / output >= 16)
+		return 0;
+
+	if (input / output >= 8)
+		return 1;
+
+	if (input / output >= 4)
+		return 2;
+
+	return 3;
+}
+
+static void vfe_set_scale_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 input, output;
+	u8 interp_reso;
+	u32 phase_mult;
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_Y_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width - 1;
+	output = line->compose.width - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	output = line->compose.height - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_Y_V_PHASE);
+
+	writel_relaxed(0x3, vfe->base + VFE_0_SCALE_ENC_CBCR_CFG);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].width - 1;
+	output = line->compose.width / 2 - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_H_PHASE);
+
+	input = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	output = line->compose.height - 1;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21)
+		output = line->compose.height / 2 - 1;
+	reg = (output << 16) | input;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_IMAGE_SIZE);
+
+	interp_reso = vfe_calc_interp_reso(input, output);
+	phase_mult = input * (1 << (14 + interp_reso)) / output;
+	reg = (interp_reso << 28) | phase_mult;
+	writel_relaxed(reg, vfe->base + VFE_0_SCALE_ENC_CBCR_V_PHASE);
+}
+
+static void vfe_set_crop_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 reg;
+	u16 first, last;
+
+	first = line->crop.left;
+	last = line->crop.left + line->crop.width - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_Y_HEIGHT);
+
+	first = line->crop.left / 2;
+	last = line->crop.left / 2 + line->crop.width / 2 - 1;
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_WIDTH);
+
+	first = line->crop.top;
+	last = line->crop.top + line->crop.height - 1;
+	if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV21) {
+		first = line->crop.top / 2;
+		last = line->crop.top / 2 + line->crop.height / 2 - 1;
+	}
+	reg = (first << 16) | last;
+	writel_relaxed(reg, vfe->base + VFE_0_CROP_ENC_CBCR_HEIGHT);
+}
+
+static void vfe_set_clamp_cfg(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_CLAMP_ENC_MAX_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MAX_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MAX_CFG);
+
+	val = VFE_0_CLAMP_ENC_MIN_CFG_CH0 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH1 |
+		VFE_0_CLAMP_ENC_MIN_CFG_CH2;
+
+	writel_relaxed(val, vfe->base + VFE_0_CLAMP_ENC_MIN_CFG);
+}
+
+static void vfe_set_qos(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_BUS_BDG_QOS_CFG_0_CFG;
+	u32 val7 = VFE_0_BUS_BDG_QOS_CFG_7_CFG;
+
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_0);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_1);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_2);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_3);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_4);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_5);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_QOS_CFG_6);
+	writel_relaxed(val7, vfe->base + VFE_0_BUS_BDG_QOS_CFG_7);
+}
+
+static void vfe_set_ds(struct vfe_device *vfe)
+{
+	u32 val = VFE_0_BUS_BDG_DS_CFG_0_CFG;
+	u32 val16 = VFE_0_BUS_BDG_DS_CFG_16_CFG;
+
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_0);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_1);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_2);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_3);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_4);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_5);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_6);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_7);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_8);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_9);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_10);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_11);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_12);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_13);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_14);
+	writel_relaxed(val, vfe->base + VFE_0_BUS_BDG_DS_CFG_15);
+	writel_relaxed(val16, vfe->base + VFE_0_BUS_BDG_DS_CFG_16);
+}
+
+static void vfe_set_cgc_override(struct vfe_device *vfe, u8 wm, u8 enable)
+{
+	/* empty */
+}
+
+static void vfe_set_camif_cfg(struct vfe_device *vfe, struct vfe_line *line)
+{
+	u32 val;
+
+	switch (line->fmt[MSM_VFE_PAD_SINK].code) {
+	case MEDIA_BUS_FMT_YUYV8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR;
+		break;
+	case MEDIA_BUS_FMT_YVYU8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_YCRYCB;
+		break;
+	case MEDIA_BUS_FMT_UYVY8_2X8:
+	default:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CBYCRY;
+		break;
+	case MEDIA_BUS_FMT_VYUY8_2X8:
+		val = VFE_0_CORE_CFG_PIXEL_PATTERN_CRYCBY;
+		break;
+	}
+
+	val |= VFE_0_CORE_CFG_COMPOSITE_REG_UPDATE_EN;
+	writel_relaxed(val, vfe->base + VFE_0_CORE_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
+	val |= (line->fmt[MSM_VFE_PAD_SINK].height - 1) << 16;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_FRAME_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].width * 2 - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_WIDTH_CFG);
+
+	val = line->fmt[MSM_VFE_PAD_SINK].height - 1;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_WINDOW_HEIGHT_CFG);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_SUBSAMPLE_CFG);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_FRAMEDROP_PATTERN);
+
+	val = 0xffffffff;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_IRQ_SUBSAMPLE_PATTERN);
+
+	val = VFE_0_RDI_CFG_x_MIPI_EN_BITS;
+	vfe_reg_set(vfe, VFE_0_RDI_CFG_x(0), val);
+
+	val = VFE_0_CAMIF_CFG_VFE_OUTPUT_EN;
+	writel_relaxed(val, vfe->base + VFE_0_CAMIF_CFG);
+}
+
+static void vfe_set_camif_cmd(struct vfe_device *vfe, u8 enable)
+{
+	u32 cmd;
+
+	cmd = VFE_0_CAMIF_CMD_CLEAR_CAMIF_STATUS | VFE_0_CAMIF_CMD_NO_CHANGE;
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+	wmb();
+
+	if (enable)
+		cmd = VFE_0_CAMIF_CMD_ENABLE_FRAME_BOUNDARY;
+	else
+		cmd = VFE_0_CAMIF_CMD_DISABLE_FRAME_BOUNDARY;
+
+	writel_relaxed(cmd, vfe->base + VFE_0_CAMIF_CMD);
+}
+
+static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
+{
+	u32 val_lens = VFE_0_MODULE_LENS_EN_DEMUX |
+		       VFE_0_MODULE_LENS_EN_CHROMA_UPSAMPLE;
+	u32 val_zoom = VFE_0_MODULE_ZOOM_EN_SCALE_ENC |
+		       VFE_0_MODULE_ZOOM_EN_CROP_ENC;
+
+	if (enable) {
+		writel_relaxed(val_lens, vfe->base + VFE_0_MODULE_LENS_EN);
+		writel_relaxed(val_zoom, vfe->base + VFE_0_MODULE_ZOOM_EN);
+	} else {
+		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_LENS_EN);
+		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_ZOOM_EN);
+	}
+}
+
+static int vfe_camif_wait_for_stop(struct vfe_device *vfe, struct device *dev)
+{
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout(vfe->base + VFE_0_CAMIF_STATUS,
+				 val,
+				 (val & VFE_0_CAMIF_STATUS_HALT),
+				 CAMIF_TIMEOUT_SLEEP_US,
+				 CAMIF_TIMEOUT_ALL_US);
+	if (ret < 0)
+		dev_err(dev, "%s: camif stop timeout\n", __func__);
+
+	return ret;
+}
+
+static void vfe_isr_read(struct vfe_device *vfe, u32 *value0, u32 *value1)
+{
+	*value0 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_0);
+	*value1 = readl_relaxed(vfe->base + VFE_0_IRQ_STATUS_1);
+
+	writel_relaxed(*value0, vfe->base + VFE_0_IRQ_CLEAR_0);
+	writel_relaxed(*value1, vfe->base + VFE_0_IRQ_CLEAR_1);
+
+	wmb();
+	writel_relaxed(VFE_0_IRQ_CMD_GLOBAL_CLEAR, vfe->base + VFE_0_IRQ_CMD);
+}
+
+static void vfe_violation_read(struct vfe_device *vfe)
+{
+	u32 violation = readl_relaxed(vfe->base + VFE_0_VIOLATION_STATUS);
+
+	pr_err_ratelimited("VFE: violation = 0x%08x\n", violation);
+}
+
+/*
+ * vfe_isr - ISPIF module interrupt handler
+ * @irq: Interrupt line
+ * @dev: VFE device
+ *
+ * Return IRQ_HANDLED on success
+ */
+static irqreturn_t vfe_isr(int irq, void *dev)
+{
+	struct vfe_device *vfe = dev;
+	u32 value0, value1;
+	int i, j;
+
+	vfe->ops->isr_read(vfe, &value0, &value1);
+
+	trace_printk("VFE: status0 = 0x%08x, status1 = 0x%08x\n",
+		     value0, value1);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_RESET_ACK)
+		vfe->isr_ops.reset_ack(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_VIOLATION)
+		vfe->ops->violation_read(vfe);
+
+	if (value1 & VFE_0_IRQ_STATUS_1_BUS_BDG_HALT_ACK)
+		vfe->isr_ops.halt_ack(vfe);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_line_n_REG_UPDATE(i))
+			vfe->isr_ops.reg_update(vfe, i);
+
+	if (value0 & VFE_0_IRQ_STATUS_0_CAMIF_SOF)
+		vfe->isr_ops.sof(vfe, VFE_LINE_PIX);
+
+	for (i = VFE_LINE_RDI0; i <= VFE_LINE_RDI2; i++)
+		if (value1 & VFE_0_IRQ_STATUS_1_RDIn_SOF(i))
+			vfe->isr_ops.sof(vfe, i);
+
+	for (i = 0; i < MSM_VFE_COMPOSITE_IRQ_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_COMPOSITE_DONE_n(i)) {
+			vfe->isr_ops.comp_done(vfe, i);
+			for (j = 0; j < ARRAY_SIZE(vfe->wm_output_map); j++)
+				if (vfe->wm_output_map[j] == VFE_LINE_PIX)
+					value0 &= ~VFE_0_IRQ_MASK_0_IMAGE_MASTER_n_PING_PONG(j);
+		}
+
+	for (i = 0; i < MSM_VFE_IMAGE_MASTERS_NUM; i++)
+		if (value0 & VFE_0_IRQ_STATUS_0_IMAGE_MASTER_n_PING_PONG(i))
+			vfe->isr_ops.wm_done(vfe, i);
+
+	return IRQ_HANDLED;
+}
+
+const struct vfe_hw_ops vfe_ops_4_7 = {
+	.hw_version_read = vfe_hw_version_read,
+	.get_ub_size = vfe_get_ub_size,
+	.global_reset = vfe_global_reset,
+	.halt_request = vfe_halt_request,
+	.halt_clear = vfe_halt_clear,
+	.wm_enable = vfe_wm_enable,
+	.wm_frame_based = vfe_wm_frame_based,
+	.wm_line_based = vfe_wm_line_based,
+	.wm_set_framedrop_period = vfe_wm_set_framedrop_period,
+	.wm_set_framedrop_pattern = vfe_wm_set_framedrop_pattern,
+	.wm_set_ub_cfg = vfe_wm_set_ub_cfg,
+	.bus_reload_wm = vfe_bus_reload_wm,
+	.wm_set_ping_addr = vfe_wm_set_ping_addr,
+	.wm_set_pong_addr = vfe_wm_set_pong_addr,
+	.wm_get_ping_pong_status = vfe_wm_get_ping_pong_status,
+	.bus_enable_wr_if = vfe_bus_enable_wr_if,
+	.bus_connect_wm_to_rdi = vfe_bus_connect_wm_to_rdi,
+	.wm_set_subsample = vfe_wm_set_subsample,
+	.bus_disconnect_wm_from_rdi = vfe_bus_disconnect_wm_from_rdi,
+	.set_xbar_cfg = vfe_set_xbar_cfg,
+	.set_rdi_cid = vfe_set_rdi_cid,
+	.reg_update = vfe_reg_update,
+	.reg_update_clear = vfe_reg_update_clear,
+	.enable_irq_wm_line = vfe_enable_irq_wm_line,
+	.enable_irq_pix_line = vfe_enable_irq_pix_line,
+	.enable_irq_common = vfe_enable_irq_common,
+	.set_demux_cfg = vfe_set_demux_cfg,
+	.set_scale_cfg = vfe_set_scale_cfg,
+	.set_crop_cfg = vfe_set_crop_cfg,
+	.set_clamp_cfg = vfe_set_clamp_cfg,
+	.set_qos = vfe_set_qos,
+	.set_ds = vfe_set_ds,
+	.set_cgc_override = vfe_set_cgc_override,
+	.set_camif_cfg = vfe_set_camif_cfg,
+	.set_camif_cmd = vfe_set_camif_cmd,
+	.set_module_cfg = vfe_set_module_cfg,
+	.camif_wait_for_stop = vfe_camif_wait_for_stop,
+	.isr_read = vfe_isr_read,
+	.violation_read = vfe_violation_read,
+	.isr = vfe_isr,
+};
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 7f07a22c3e4b..e6f66cfad86d 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -691,6 +691,8 @@ static int vfe_enable(struct vfe_line *line)
 		vfe->ops->bus_enable_wr_if(vfe, 1);
 
 		vfe->ops->set_qos(vfe);
+
+		vfe->ops->set_ds(vfe);
 	}
 
 	vfe->stream_count++;
@@ -1855,6 +1857,8 @@ int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
 
 	if (camss->version == CAMSS_8x16)
 		vfe->ops = &vfe_ops_4_1;
+	else if (camss->version == CAMSS_8x96)
+		vfe->ops = &vfe_ops_4_7;
 	else
 		return -EINVAL;
 
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
index 19041ba6644a..eaebe833c143 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.h
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -118,6 +118,7 @@ struct vfe_hw_ops {
 	void (*set_crop_cfg)(struct vfe_device *vfe, struct vfe_line *line);
 	void (*set_clamp_cfg)(struct vfe_device *vfe);
 	void (*set_qos)(struct vfe_device *vfe);
+	void (*set_ds)(struct vfe_device *vfe);
 	void (*set_cgc_override)(struct vfe_device *vfe, u8 wm, u8 enable);
 	void (*set_camif_cfg)(struct vfe_device *vfe, struct vfe_line *line);
 	void (*set_camif_cmd)(struct vfe_device *vfe, u8 enable);
@@ -176,5 +177,6 @@ void msm_vfe_get_vfe_line_id(struct media_entity *entity, enum vfe_line_id *id);
 void msm_vfe_stop_streaming(struct vfe_device *vfe);
 
 extern const struct vfe_hw_ops vfe_ops_4_1;
+extern const struct vfe_hw_ops vfe_ops_4_7;
 
 #endif /* QC_MSM_CAMSS_VFE_H */
-- 
cgit v1.2.3


From cba3819d1e93fb77a9323554ccf7b564276c089b Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:35 -0400
Subject: media: camss: Format configuration per hardware version

As the 8x16 and 8x96 support different formats, separate the
arrays which contain the supported formats. For the VFE also
add separate arrays for RDI and PIX subdevices.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c   | 196 +++++++++++++++++++----
 drivers/media/platform/qcom/camss/camss-csid.h   |   2 +
 drivers/media/platform/qcom/camss/camss-csiphy.c | 145 ++++++++---------
 drivers/media/platform/qcom/camss/camss-csiphy.h |   2 +
 drivers/media/platform/qcom/camss/camss-ispif.c  |  43 ++++-
 drivers/media/platform/qcom/camss/camss-ispif.h  |   2 +
 drivers/media/platform/qcom/camss/camss-vfe.c    | 189 ++++++++++++----------
 drivers/media/platform/qcom/camss/camss-vfe.h    |   2 +
 drivers/media/platform/qcom/camss/camss-video.c  |  97 ++++++++++-
 9 files changed, 467 insertions(+), 211 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 915835ee3271..db960da560c9 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -62,7 +62,7 @@
 
 #define CSID_RESET_TIMEOUT_MS 500
 
-struct csid_fmts {
+struct csid_format {
 	u32 code;
 	u8 data_type;
 	u8 decode_format;
@@ -70,7 +70,7 @@ struct csid_fmts {
 	u8 spp; /* bus samples per pixel */
 };
 
-static const struct csid_fmts csid_input_fmts[] = {
+static const struct csid_format csid_formats_8x16[] = {
 	{
 		MEDIA_BUS_FMT_UYVY8_2X8,
 		DATA_TYPE_YUV422_8BIT,
@@ -185,17 +185,135 @@ static const struct csid_fmts csid_input_fmts[] = {
 	}
 };
 
-static const struct csid_fmts *csid_get_fmt_entry(u32 code)
+static const struct csid_format csid_formats_8x96[] = {
+	{
+		MEDIA_BUS_FMT_UYVY8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_VYUY8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_YUYV8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_YVYU8_2X8,
+		DATA_TYPE_YUV422_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		2,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB8_1X8,
+		DATA_TYPE_RAW_8BIT,
+		DECODE_FORMAT_UNCOMPRESSED_8_BIT,
+		8,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB12_1X12,
+		DATA_TYPE_RAW_12BIT,
+		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
+		12,
+		1,
+	}
+};
+
+static const struct csid_format *csid_get_fmt_entry(
+					const struct csid_format *formats,
+					unsigned int nformat,
+					u32 code)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-		if (code == csid_input_fmts[i].code)
-			return &csid_input_fmts[i];
+	for (i = 0; i < nformat; i++)
+		if (code == formats[i].code)
+			return &formats[i];
 
 	WARN(1, "Unknown format\n");
 
-	return &csid_input_fmts[0];
+	return &formats[0];
 }
 
 /*
@@ -242,10 +360,13 @@ static int csid_set_clock_rates(struct csid_device *csid)
 		    !strcmp(clock->name, "csi1") ||
 		    !strcmp(clock->name, "csi2") ||
 		    !strcmp(clock->name, "csi3")) {
-			u8 bpp = csid_get_fmt_entry(
-				csid->fmt[MSM_CSIPHY_PAD_SINK].code)->bpp;
+			const struct csid_format *f = csid_get_fmt_entry(
+				csid->formats,
+				csid->nformats,
+				csid->fmt[MSM_CSIPHY_PAD_SINK].code);
 			u8 num_lanes = csid->phy.lane_cnt;
-			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
+			u64 min_rate = pixel_clock * f->bpp /
+							(2 * num_lanes * 4);
 			long rate;
 
 			camss_add_clock_margin(&min_rate);
@@ -408,9 +529,10 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			/* Config Test Generator */
 			struct v4l2_mbus_framefmt *f =
 					&csid->fmt[MSM_CSID_PAD_SRC];
-			u8 bpp = csid_get_fmt_entry(f->code)->bpp;
-			u8 spp = csid_get_fmt_entry(f->code)->spp;
-			u32 num_bytes_per_line = f->width * bpp * spp / 8;
+			const struct csid_format *format = csid_get_fmt_entry(
+					csid->formats, csid->nformats, f->code);
+			u32 num_bytes_per_line =
+				f->width * format->bpp * format->spp / 8;
 			u32 num_lines = f->height;
 
 			/* 31:24 V blank, 23:13 H blank, 3:2 num of active DT */
@@ -426,8 +548,7 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			writel_relaxed(val, csid->base +
 				       CAMSS_CSID_TG_DT_n_CGG_0(ver, 0));
 
-			dt = csid_get_fmt_entry(
-				csid->fmt[MSM_CSID_PAD_SRC].code)->data_type;
+			dt = format->data_type;
 
 			/* 5:0 data type */
 			val = dt;
@@ -439,9 +560,12 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			writel_relaxed(val, csid->base +
 				       CAMSS_CSID_TG_DT_n_CGG_2(ver, 0));
 
-			df = csid_get_fmt_entry(
-				csid->fmt[MSM_CSID_PAD_SRC].code)->decode_format;
+			df = format->decode_format;
 		} else {
+			struct v4l2_mbus_framefmt *f =
+					&csid->fmt[MSM_CSID_PAD_SINK];
+			const struct csid_format *format = csid_get_fmt_entry(
+					csid->formats, csid->nformats, f->code);
 			struct csid_phy_config *phy = &csid->phy;
 
 			val = phy->lane_cnt - 1;
@@ -456,10 +580,8 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 			writel_relaxed(val,
 				       csid->base + CAMSS_CSID_CORE_CTRL_1);
 
-			dt = csid_get_fmt_entry(
-				csid->fmt[MSM_CSID_PAD_SINK].code)->data_type;
-			df = csid_get_fmt_entry(
-				csid->fmt[MSM_CSID_PAD_SINK].code)->decode_format;
+			dt = format->data_type;
+			df = format->decode_format;
 		}
 
 		/* Config LUT */
@@ -534,12 +656,12 @@ static void csid_try_format(struct csid_device *csid,
 	case MSM_CSID_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-			if (fmt->code == csid_input_fmts[i].code)
+		for (i = 0; i < csid->nformats; i++)
+			if (fmt->code == csid->formats[i].code)
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(csid_input_fmts))
+		if (i >= csid->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -563,12 +685,12 @@ static void csid_try_format(struct csid_device *csid,
 			/* Test generator is enabled, set format on source*/
 			/* pad to allow test generator usage */
 
-			for (i = 0; i < ARRAY_SIZE(csid_input_fmts); i++)
-				if (csid_input_fmts[i].code == fmt->code)
+			for (i = 0; i < csid->nformats; i++)
+				if (csid->formats[i].code == fmt->code)
 					break;
 
 			/* If not found, use UYVY as default */
-			if (i >= ARRAY_SIZE(csid_input_fmts))
+			if (i >= csid->nformats)
 				fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 			fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -597,10 +719,10 @@ static int csid_enum_mbus_code(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_CSID_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(csid_input_fmts))
+		if (code->index >= csid->nformats)
 			return -EINVAL;
 
-		code->code = csid_input_fmts[code->index].code;
+		code->code = csid->formats[code->index].code;
 	} else {
 		if (csid->testgen_mode->cur.val == 0) {
 			if (code->index > 0)
@@ -611,10 +733,10 @@ static int csid_enum_mbus_code(struct v4l2_subdev *sd,
 
 			code->code = format->code;
 		} else {
-			if (code->index >= ARRAY_SIZE(csid_input_fmts))
+			if (code->index >= csid->nformats)
 				return -EINVAL;
 
-			code->code = csid_input_fmts[code->index].code;
+			code->code = csid->formats[code->index].code;
 		}
 	}
 
@@ -834,6 +956,18 @@ int msm_csid_subdev_init(struct camss *camss, struct csid_device *csid,
 	csid->camss = camss;
 	csid->id = id;
 
+	if (camss->version == CAMSS_8x16) {
+		csid->formats = csid_formats_8x16;
+		csid->nformats =
+				ARRAY_SIZE(csid_formats_8x16);
+	} else if (camss->version == CAMSS_8x96) {
+		csid->formats = csid_formats_8x96;
+		csid->nformats =
+				ARRAY_SIZE(csid_formats_8x96);
+	} else {
+		return -EINVAL;
+	}
+
 	/* Memory */
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, res->reg[0]);
diff --git a/drivers/media/platform/qcom/camss/camss-csid.h b/drivers/media/platform/qcom/camss/camss-csid.h
index ed605fd3bb87..1824b3745e10 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.h
+++ b/drivers/media/platform/qcom/camss/camss-csid.h
@@ -58,6 +58,8 @@ struct csid_device {
 	struct v4l2_mbus_framefmt fmt[MSM_CSID_PADS_NUM];
 	struct v4l2_ctrl_handler ctrls;
 	struct v4l2_ctrl *testgen_mode;
+	const struct csid_format *formats;
+	unsigned int nformats;
 };
 
 struct resources;
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 7da705147966..3cdab59d24f9 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -23,93 +23,69 @@
 
 #define MSM_CSIPHY_NAME "msm_csiphy"
 
-static const struct {
+struct csiphy_format {
 	u32 code;
 	u8 bpp;
-} csiphy_formats[] = {
-	{
-		MEDIA_BUS_FMT_UYVY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_VYUY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YUYV8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YVYU8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB12_1X12,
-		12,
-	}
+};
+
+static const struct csiphy_format csiphy_formats_8x16[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+};
+
+static const struct csiphy_format csiphy_formats_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
 };
 
 /*
  * csiphy_get_bpp - map media bus format to bits per pixel
+ * @formats: supported media bus formats array
+ * @nformats: size of @formats array
  * @code: media bus format code
  *
  * Return number of bits per pixel
  */
-static u8 csiphy_get_bpp(u32 code)
+static u8 csiphy_get_bpp(const struct csiphy_format *formats,
+			 unsigned int nformats, u32 code)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
-		if (code == csiphy_formats[i].code)
-			return csiphy_formats[i].bpp;
+	for (i = 0; i < nformats; i++)
+		if (code == formats[i].code)
+			return formats[i].bpp;
 
 	WARN(1, "Unknown format\n");
 
-	return csiphy_formats[0].bpp;
+	return formats[0].bpp;
 }
 
 /*
@@ -133,7 +109,8 @@ static int csiphy_set_clock_rates(struct csiphy_device *csiphy)
 		if (!strcmp(clock->name, "csiphy0_timer") ||
 		    !strcmp(clock->name, "csiphy1_timer") ||
 		    !strcmp(clock->name, "csiphy2_timer")) {
-			u8 bpp = csiphy_get_bpp(
+			u8 bpp = csiphy_get_bpp(csiphy->formats,
+					csiphy->nformats,
 					csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
 			u8 num_lanes = csiphy->cfg.csi2->lane_cfg.num_data;
 			u64 min_rate = pixel_clock * bpp / (2 * num_lanes * 4);
@@ -256,7 +233,8 @@ static int csiphy_stream_on(struct csiphy_device *csiphy)
 	struct csiphy_config *cfg = &csiphy->cfg;
 	u32 pixel_clock;
 	u8 lane_mask = csiphy_get_lane_mask(&cfg->csi2->lane_cfg);
-	u8 bpp = csiphy_get_bpp(csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
+	u8 bpp = csiphy_get_bpp(csiphy->formats, csiphy->nformats,
+				csiphy->fmt[MSM_CSIPHY_PAD_SINK].code);
 	u8 val;
 	int ret;
 
@@ -361,12 +339,12 @@ static void csiphy_try_format(struct csiphy_device *csiphy,
 	case MSM_CSIPHY_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(csiphy_formats); i++)
-			if (fmt->code == csiphy_formats[i].code)
+		for (i = 0; i < csiphy->nformats; i++)
+			if (fmt->code == csiphy->formats[i].code)
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(csiphy_formats))
+		if (i >= csiphy->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -402,10 +380,10 @@ static int csiphy_enum_mbus_code(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_CSIPHY_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(csiphy_formats))
+		if (code->index >= csiphy->nformats)
 			return -EINVAL;
 
-		code->code = csiphy_formats[code->index].code;
+		code->code = csiphy->formats[code->index].code;
 	} else {
 		if (code->index > 0)
 			return -EINVAL;
@@ -563,12 +541,17 @@ int msm_csiphy_subdev_init(struct camss *camss,
 	csiphy->id = id;
 	csiphy->cfg.combo_mode = 0;
 
-	if (camss->version == CAMSS_8x16)
+	if (camss->version == CAMSS_8x16) {
 		csiphy->ops = &csiphy_ops_2ph_1_0;
-	else if (camss->version == CAMSS_8x96)
+		csiphy->formats = csiphy_formats_8x16;
+		csiphy->nformats = ARRAY_SIZE(csiphy_formats_8x16);
+	} else if (camss->version == CAMSS_8x96) {
 		csiphy->ops = &csiphy_ops_3ph_1_0;
-	else
+		csiphy->formats = csiphy_formats_8x96;
+		csiphy->nformats = ARRAY_SIZE(csiphy_formats_8x96);
+	} else {
 		return -EINVAL;
+	}
 
 	/* Memory */
 
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.h b/drivers/media/platform/qcom/camss/camss-csiphy.h
index 5debe46b6cf1..376f865ad383 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.h
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.h
@@ -71,6 +71,8 @@ struct csiphy_device {
 	struct csiphy_config cfg;
 	struct v4l2_mbus_framefmt fmt[MSM_CSIPHY_PADS_NUM];
 	const struct csiphy_hw_ops *ops;
+	const struct csiphy_format *formats;
+	unsigned int nformats;
 };
 
 struct resources;
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index ae8073274624..146d5d26b3c1 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -96,7 +96,26 @@ enum ispif_intf_cmd {
 	CMD_ALL_NO_CHANGE = 0xffffffff,
 };
 
-static const u32 ispif_formats[] = {
+static const u32 ispif_formats_8x16[] = {
+	MEDIA_BUS_FMT_UYVY8_2X8,
+	MEDIA_BUS_FMT_VYUY8_2X8,
+	MEDIA_BUS_FMT_YUYV8_2X8,
+	MEDIA_BUS_FMT_YVYU8_2X8,
+	MEDIA_BUS_FMT_SBGGR8_1X8,
+	MEDIA_BUS_FMT_SGBRG8_1X8,
+	MEDIA_BUS_FMT_SGRBG8_1X8,
+	MEDIA_BUS_FMT_SRGGB8_1X8,
+	MEDIA_BUS_FMT_SBGGR10_1X10,
+	MEDIA_BUS_FMT_SGBRG10_1X10,
+	MEDIA_BUS_FMT_SGRBG10_1X10,
+	MEDIA_BUS_FMT_SRGGB10_1X10,
+	MEDIA_BUS_FMT_SBGGR12_1X12,
+	MEDIA_BUS_FMT_SGBRG12_1X12,
+	MEDIA_BUS_FMT_SGRBG12_1X12,
+	MEDIA_BUS_FMT_SRGGB12_1X12,
+};
+
+static const u32 ispif_formats_8x96[] = {
 	MEDIA_BUS_FMT_UYVY8_2X8,
 	MEDIA_BUS_FMT_VYUY8_2X8,
 	MEDIA_BUS_FMT_YUYV8_2X8,
@@ -780,12 +799,12 @@ static void ispif_try_format(struct ispif_line *line,
 	case MSM_ISPIF_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(ispif_formats); i++)
-			if (fmt->code == ispif_formats[i])
+		for (i = 0; i < line->nformats; i++)
+			if (fmt->code == line->formats[i])
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(ispif_formats))
+		if (i >= line->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -823,10 +842,10 @@ static int ispif_enum_mbus_code(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_ISPIF_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(ispif_formats))
+		if (code->index >= line->nformats)
 			return -EINVAL;
 
-		code->code = ispif_formats[code->index];
+		code->code = line->formats[code->index];
 	} else {
 		if (code->index > 0)
 			return -EINVAL;
@@ -993,6 +1012,18 @@ int msm_ispif_subdev_init(struct ispif_device *ispif,
 	for (i = 0; i < ispif->line_num; i++) {
 		ispif->line[i].ispif = ispif;
 		ispif->line[i].id = i;
+
+		if (to_camss(ispif)->version == CAMSS_8x16) {
+			ispif->line[i].formats = ispif_formats_8x16;
+			ispif->line[i].nformats =
+					ARRAY_SIZE(ispif_formats_8x16);
+		} else if (to_camss(ispif)->version == CAMSS_8x96) {
+			ispif->line[i].formats = ispif_formats_8x96;
+			ispif->line[i].nformats =
+					ARRAY_SIZE(ispif_formats_8x96);
+		} else {
+			return -EINVAL;
+		}
 	}
 
 	/* Memory */
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.h b/drivers/media/platform/qcom/camss/camss-ispif.h
index 9cd51dcb3ede..1a5ba2425a42 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.h
+++ b/drivers/media/platform/qcom/camss/camss-ispif.h
@@ -43,6 +43,8 @@ struct ispif_line {
 	struct v4l2_subdev subdev;
 	struct media_pad pads[MSM_ISPIF_PADS_NUM];
 	struct v4l2_mbus_framefmt fmt[MSM_ISPIF_PADS_NUM];
+	const u32 *formats;
+	unsigned int nformats;
 };
 
 struct ispif_device {
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index e6f66cfad86d..c27097c440f2 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -45,93 +45,83 @@
 
 #define SCALER_RATIO_MAX 16
 
-static const struct {
+struct vfe_format {
 	u32 code;
 	u8 bpp;
-} vfe_formats[] = {
-	{
-		MEDIA_BUS_FMT_UYVY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_VYUY8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YUYV8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_YVYU8_2X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB8_1X8,
-		8,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB10_1X10,
-		10,
-	},
-	{
-		MEDIA_BUS_FMT_SBGGR12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGBRG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SGRBG12_1X12,
-		12,
-	},
-	{
-		MEDIA_BUS_FMT_SRGGB12_1X12,
-		12,
-	}
+};
+
+static const struct vfe_format formats_rdi_8x16[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+};
+
+static const struct vfe_format formats_pix_8x16[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+};
+
+static const struct vfe_format formats_rdi_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, 8 },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+};
+
+static const struct vfe_format formats_pix_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, 8 },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, 8 },
 };
 
 /*
  * vfe_get_bpp - map media bus format to bits per pixel
+ * @formats: supported media bus formats array
+ * @nformats: size of @formats array
  * @code: media bus format code
  *
  * Return number of bits per pixel
  */
-static u8 vfe_get_bpp(u32 code)
+static u8 vfe_get_bpp(const struct vfe_format *formats,
+		      unsigned int nformats, u32 code)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
-		if (code == vfe_formats[i].code)
-			return vfe_formats[i].bpp;
+	for (i = 0; i < nformats; i++)
+		if (code == formats[i].code)
+			return formats[i].bpp;
 
 	WARN(1, "Unknown format\n");
 
-	return vfe_formats[0].bpp;
+	return formats[0].bpp;
 }
 
 /*
@@ -978,8 +968,11 @@ static int vfe_set_clock_rates(struct vfe_device *vfe)
 				if (j == VFE_LINE_PIX) {
 					tmp = pixel_clock[j];
 				} else {
-					bpp = vfe_get_bpp(vfe->line[j].
-						fmt[MSM_VFE_PAD_SINK].code);
+					struct vfe_line *l = &vfe->line[j];
+
+					bpp = vfe_get_bpp(l->formats,
+						l->nformats,
+						l->fmt[MSM_VFE_PAD_SINK].code);
 					tmp = pixel_clock[j] * bpp / 64;
 				}
 
@@ -1057,8 +1050,11 @@ static int vfe_check_clock_rates(struct vfe_device *vfe)
 				if (j == VFE_LINE_PIX) {
 					tmp = pixel_clock[j];
 				} else {
-					bpp = vfe_get_bpp(vfe->line[j].
-						fmt[MSM_VFE_PAD_SINK].code);
+					struct vfe_line *l = &vfe->line[j];
+
+					bpp = vfe_get_bpp(l->formats,
+						l->nformats,
+						l->fmt[MSM_VFE_PAD_SINK].code);
 					tmp = pixel_clock[j] * bpp / 64;
 				}
 
@@ -1374,12 +1370,12 @@ static void vfe_try_format(struct vfe_line *line,
 	case MSM_VFE_PAD_SINK:
 		/* Set format on sink pad */
 
-		for (i = 0; i < ARRAY_SIZE(vfe_formats); i++)
-			if (fmt->code == vfe_formats[i].code)
+		for (i = 0; i < line->nformats; i++)
+			if (fmt->code == line->formats[i].code)
 				break;
 
 		/* If not found, use UYVY as default */
-		if (i >= ARRAY_SIZE(vfe_formats))
+		if (i >= line->nformats)
 			fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
 
 		fmt->width = clamp_t(u32, fmt->width, 1, 8191);
@@ -1539,10 +1535,10 @@ static int vfe_enum_mbus_code(struct v4l2_subdev *sd,
 	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_VFE_PAD_SINK) {
-		if (code->index >= ARRAY_SIZE(vfe_formats))
+		if (code->index >= line->nformats)
 			return -EINVAL;
 
-		code->code = vfe_formats[code->index].code;
+		code->code = line->formats[code->index].code;
 	} else {
 		if (code->index > 0)
 			return -EINVAL;
@@ -1943,12 +1939,33 @@ int msm_vfe_subdev_init(struct camss *camss, struct vfe_device *vfe,
 	vfe->reg_update = 0;
 
 	for (i = VFE_LINE_RDI0; i <= VFE_LINE_PIX; i++) {
-		vfe->line[i].video_out.type =
-					V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
-		vfe->line[i].video_out.camss = camss;
-		vfe->line[i].id = i;
-		init_completion(&vfe->line[i].output.sof);
-		init_completion(&vfe->line[i].output.reg_update);
+		struct vfe_line *l = &vfe->line[i];
+
+		l->video_out.type = V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE;
+		l->video_out.camss = camss;
+		l->id = i;
+		init_completion(&l->output.sof);
+		init_completion(&l->output.reg_update);
+
+		if (camss->version == CAMSS_8x16) {
+			if (i == VFE_LINE_PIX) {
+				l->formats = formats_pix_8x16;
+				l->nformats = ARRAY_SIZE(formats_pix_8x16);
+			} else {
+				l->formats = formats_rdi_8x16;
+				l->nformats = ARRAY_SIZE(formats_rdi_8x16);
+			}
+		} else if (camss->version == CAMSS_8x96) {
+			if (i == VFE_LINE_PIX) {
+				l->formats = formats_pix_8x96;
+				l->nformats = ARRAY_SIZE(formats_pix_8x96);
+			} else {
+				l->formats = formats_rdi_8x96;
+				l->nformats = ARRAY_SIZE(formats_rdi_8x96);
+			}
+		} else {
+			return -EINVAL;
+		}
 	}
 
 	init_completion(&vfe->reset_complete);
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
index eaebe833c143..71f6c97b266e 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.h
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -71,6 +71,8 @@ struct vfe_line {
 	struct v4l2_rect crop;
 	struct camss_video video_out;
 	struct vfe_output output;
+	const struct vfe_format *formats;
+	unsigned int nformats;
 };
 
 struct vfe_device;
diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
index 16e74b2448fe..ba7d0c45a8d9 100644
--- a/drivers/media/platform/qcom/camss/camss-video.c
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -41,7 +41,7 @@ struct camss_format_info {
 	unsigned int bpp[3];
 };
 
-static const struct camss_format_info formats_rdi[] = {
+static const struct camss_format_info formats_rdi_8x16[] = {
 	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
 	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
@@ -76,7 +76,77 @@ static const struct camss_format_info formats_rdi[] = {
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
 };
 
-static const struct camss_format_info formats_pix[] = {
+static const struct camss_format_info formats_rdi_8x96[] = {
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_YUYV, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_YVYU, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_SBGGR8_1X8, V4L2_PIX_FMT_SBGGR8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SGBRG8_1X8, V4L2_PIX_FMT_SGBRG8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SGRBG8_1X8, V4L2_PIX_FMT_SGRBG8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SRGGB8_1X8, V4L2_PIX_FMT_SRGGB8, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 8 } },
+	{ MEDIA_BUS_FMT_SBGGR10_1X10, V4L2_PIX_FMT_SBGGR10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SGBRG10_1X10, V4L2_PIX_FMT_SGBRG10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SGRBG10_1X10, V4L2_PIX_FMT_SGRBG10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SRGGB10_1X10, V4L2_PIX_FMT_SRGGB10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SBGGR12_1X12, V4L2_PIX_FMT_SBGGR12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SGBRG12_1X12, V4L2_PIX_FMT_SGBRG12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SGRBG12_1X12, V4L2_PIX_FMT_SGRBG12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SRGGB12_1X12, V4L2_PIX_FMT_SRGGB12P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+};
+
+static const struct camss_format_info formats_pix_8x16[] = {
+	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV12, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_1_5X8, V4L2_PIX_FMT_NV21, 1,
+	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV16, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV61, 1,
+	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+};
+
+static const struct camss_format_info formats_pix_8x96[] = {
 	{ MEDIA_BUS_FMT_YUYV8_1_5X8, V4L2_PIX_FMT_NV12, 1,
 	  { { 1, 1 } }, { { 2, 3 } }, { 8 } },
 	{ MEDIA_BUS_FMT_YVYU8_1_5X8, V4L2_PIX_FMT_NV12, 1,
@@ -790,11 +860,24 @@ int msm_video_register(struct camss_video *video, struct v4l2_device *v4l2_dev,
 
 	mutex_init(&video->lock);
 
-	video->formats = formats_rdi;
-	video->nformats = ARRAY_SIZE(formats_rdi);
-	if (is_pix) {
-		video->formats = formats_pix;
-		video->nformats = ARRAY_SIZE(formats_pix);
+	if (video->camss->version == CAMSS_8x16) {
+		if (is_pix) {
+			video->formats = formats_pix_8x16;
+			video->nformats = ARRAY_SIZE(formats_pix_8x16);
+		} else {
+			video->formats = formats_rdi_8x16;
+			video->nformats = ARRAY_SIZE(formats_rdi_8x16);
+		}
+	} else if (video->camss->version == CAMSS_8x96) {
+		if (is_pix) {
+			video->formats = formats_pix_8x96;
+			video->nformats = ARRAY_SIZE(formats_pix_8x96);
+		} else {
+			video->formats = formats_rdi_8x96;
+			video->nformats = ARRAY_SIZE(formats_rdi_8x96);
+		}
+	} else {
+		goto error_video_register;
 	}
 
 	ret = msm_video_init_format(video);
-- 
cgit v1.2.3


From 07eeb342a1385bbe07d6cb846af05e0add0bbbc2 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:36 -0400
Subject: media: camss: vfe: Different format support on source pad

Rework the format selection on the source pad. Make the format
on the source pad selectable amongst a list of formats. This
list can be different for each sink pad format.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-vfe.c | 172 ++++++++++++++++++++------
 1 file changed, 135 insertions(+), 37 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index c27097c440f2..dc353d624e95 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -124,6 +124,131 @@ static u8 vfe_get_bpp(const struct vfe_format *formats,
 	return formats[0].bpp;
 }
 
+static u32 vfe_find_code(u32 *code, unsigned int n_code,
+			 unsigned int index, u32 req_code)
+{
+	int i;
+
+	if (!req_code && (index >= n_code))
+		return 0;
+
+	for (i = 0; i < n_code; i++)
+		if (req_code) {
+			if (req_code == code[i])
+				return req_code;
+		} else {
+			if (i == index)
+				return code[i];
+		}
+
+	return code[0];
+}
+
+static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code,
+			    unsigned int index, u32 src_req_code)
+{
+	struct vfe_device *vfe = to_vfe(line);
+
+	if (vfe->camss->version == CAMSS_8x16)
+		switch (sink_code) {
+		case MEDIA_BUS_FMT_YUYV8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YUYV8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_YVYU8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_YVYU8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_UYVY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_UYVY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_VYUY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		default:
+			if (index > 0)
+				return 0;
+
+			return sink_code;
+		}
+	else if (vfe->camss->version == CAMSS_8x96)
+		switch (sink_code) {
+		case MEDIA_BUS_FMT_YUYV8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YUYV8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_YVYU8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_YVYU8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_UYVY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_UYVY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		case MEDIA_BUS_FMT_VYUY8_2X8:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_1_5X8,
+			};
+
+			return vfe_find_code(src_code, ARRAY_SIZE(src_code),
+					     index, src_req_code);
+		}
+		default:
+			if (index > 0)
+				return 0;
+
+			return sink_code;
+		}
+	else
+		return 0;
+}
+
 /*
  * vfe_reset - Trigger reset on VFE module and wait to complete
  * @vfe: VFE device
@@ -1388,11 +1513,11 @@ static void vfe_try_format(struct vfe_line *line,
 
 	case MSM_VFE_PAD_SRC:
 		/* Set and return a format same as sink pad */
-
 		code = fmt->code;
 
-		*fmt = *__vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
-					 which);
+		*fmt = *__vfe_get_format(line, cfg, MSM_VFE_PAD_SINK, which);
+
+		fmt->code = vfe_src_pad_code(line, fmt->code, 0, code);
 
 		if (line->id == VFE_LINE_PIX) {
 			struct v4l2_rect *rect;
@@ -1401,34 +1526,6 @@ static void vfe_try_format(struct vfe_line *line,
 
 			fmt->width = rect->width;
 			fmt->height = rect->height;
-
-			switch (fmt->code) {
-			case MEDIA_BUS_FMT_YUYV8_2X8:
-				if (code == MEDIA_BUS_FMT_YUYV8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_YUYV8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_YUYV8_2X8;
-				break;
-			case MEDIA_BUS_FMT_YVYU8_2X8:
-				if (code == MEDIA_BUS_FMT_YVYU8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_YVYU8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_YVYU8_2X8;
-				break;
-			case MEDIA_BUS_FMT_UYVY8_2X8:
-			default:
-				if (code == MEDIA_BUS_FMT_UYVY8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_UYVY8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_UYVY8_2X8;
-				break;
-			case MEDIA_BUS_FMT_VYUY8_2X8:
-				if (code == MEDIA_BUS_FMT_VYUY8_1_5X8)
-					fmt->code = MEDIA_BUS_FMT_VYUY8_1_5X8;
-				else
-					fmt->code = MEDIA_BUS_FMT_VYUY8_2X8;
-				break;
-			}
 		}
 
 		break;
@@ -1532,7 +1629,6 @@ static int vfe_enum_mbus_code(struct v4l2_subdev *sd,
 			      struct v4l2_subdev_mbus_code_enum *code)
 {
 	struct vfe_line *line = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_VFE_PAD_SINK) {
 		if (code->index >= line->nformats)
@@ -1540,13 +1636,15 @@ static int vfe_enum_mbus_code(struct v4l2_subdev *sd,
 
 		code->code = line->formats[code->index].code;
 	} else {
-		if (code->index > 0)
-			return -EINVAL;
+		struct v4l2_mbus_framefmt *sink_fmt;
 
-		format = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
-					  code->which);
+		sink_fmt = __vfe_get_format(line, cfg, MSM_VFE_PAD_SINK,
+					    code->which);
 
-		code->code = format->code;
+		code->code = vfe_src_pad_code(line, sink_fmt->code,
+					      code->index, 0);
+		if (!code->code)
+			return -EINVAL;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 312e1c858a0f05e27812cd7de87114801fced508 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:37 -0400
Subject: media: camss: vfe: Add support for UYVY output from VFE on 8x96

Add support to output UYVY formats from the VFE (via the PIX interface).
A configuration for the realign module in the VFE is added. As the
realign module is present on 8x96 but not on 8x16, this is supported
on 8x96 only.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-vfe-4-1.c |   6 +
 drivers/media/platform/qcom/camss/camss-vfe-4-7.c | 129 ++++++++++++++++++----
 drivers/media/platform/qcom/camss/camss-vfe.c     |  31 +++++-
 drivers/media/platform/qcom/camss/camss-vfe.h     |   2 +
 drivers/media/platform/qcom/camss/camss-video.c   |   8 ++
 5 files changed, 152 insertions(+), 24 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
index 41184dcc33ca..da3a9fed9f2d 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe-4-1.c
@@ -542,6 +542,11 @@ static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
 	}
 }
 
+static void vfe_set_realign_cfg(struct vfe_device *vfe, struct vfe_line *line,
+				u8 enable)
+{
+	/* empty */
+}
 static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
 {
 	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
@@ -989,6 +994,7 @@ const struct vfe_hw_ops vfe_ops_4_1 = {
 	.wm_set_subsample = vfe_wm_set_subsample,
 	.bus_disconnect_wm_from_rdi = vfe_bus_disconnect_wm_from_rdi,
 	.set_xbar_cfg = vfe_set_xbar_cfg,
+	.set_realign_cfg = vfe_set_realign_cfg,
 	.set_rdi_cid = vfe_set_rdi_cid,
 	.reg_update = vfe_reg_update,
 	.reg_update_clear = vfe_reg_update_clear,
diff --git a/drivers/media/platform/qcom/camss/camss-vfe-4-7.c b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c
index 45e6711a346f..4c584bffd179 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe-4-7.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe-4-7.c
@@ -34,6 +34,7 @@
 #define VFE_0_MODULE_ZOOM_EN		0x04c
 #define VFE_0_MODULE_ZOOM_EN_SCALE_ENC		BIT(1)
 #define VFE_0_MODULE_ZOOM_EN_CROP_ENC		BIT(2)
+#define VFE_0_MODULE_ZOOM_EN_REALIGN_BUF	BIT(9)
 
 #define VFE_0_CORE_CFG			0x050
 #define VFE_0_CORE_CFG_PIXEL_PATTERN_YCBYCR	0x4
@@ -87,6 +88,9 @@
 
 #define VFE_0_BUS_XBAR_CFG_x(x)		(0x90 + 0x4 * ((x) / 2))
 #define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN			BIT(2)
+#define VFE_0_BUS_XBAR_CFG_x_M_REALIGN_BUF_EN			BIT(3)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTRA		(0x1 << 4)
+#define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER		(0x2 << 4)
 #define VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA	(0x3 << 4)
 #define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT		8
 #define VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA		0x0
@@ -221,6 +225,11 @@
 #define VFE_0_CLAMP_ENC_MIN_CFG_CH1		(0x0 << 8)
 #define VFE_0_CLAMP_ENC_MIN_CFG_CH2		(0x0 << 16)
 
+#define VFE_0_REALIGN_BUF_CFG			0xaac
+#define VFE_0_REALIGN_BUF_CFG_CB_ODD_PIXEL     BIT(2)
+#define VFE_0_REALIGN_BUF_CFG_CR_ODD_PIXEL     BIT(3)
+#define VFE_0_REALIGN_BUF_CFG_HSUB_ENABLE      BIT(4)
+
 #define CAMIF_TIMEOUT_SLEEP_US 1000
 #define CAMIF_TIMEOUT_ALL_US 1000000
 
@@ -311,7 +320,7 @@ static void vfe_wm_frame_based(struct vfe_device *vfe, u8 wm, u8 enable)
 
 #define CALC_WORD(width, M, N) (((width) * (M) + (N) - 1) / (N))
 
-static int vfe_word_per_line(u32 format, u32 pixel_per_line)
+static int vfe_word_per_line_by_pixel(u32 format, u32 pixel_per_line)
 {
 	int val = 0;
 
@@ -333,6 +342,11 @@ static int vfe_word_per_line(u32 format, u32 pixel_per_line)
 	return val;
 }
 
+static int vfe_word_per_line_by_bytes(u32 bytes_per_line)
+{
+	return CALC_WORD(bytes_per_line, 1, 8);
+}
+
 static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
 			     u16 *width, u16 *height, u16 *bytesperline)
 {
@@ -351,6 +365,15 @@ static void vfe_get_wm_sizes(struct v4l2_pix_format_mplane *pix, u8 plane,
 		*height = pix->height;
 		*bytesperline = pix->plane_fmt[0].bytesperline;
 		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
+	case V4L2_PIX_FMT_UYVY:
+		*width = pix->width;
+		*height = pix->height;
+		*bytesperline = pix->plane_fmt[plane].bytesperline;
+		break;
+
 	}
 }
 
@@ -365,7 +388,7 @@ static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
 
 		vfe_get_wm_sizes(pix, plane, &width, &height, &bytesperline);
 
-		wpl = vfe_word_per_line(pix->pixelformat, width);
+		wpl = vfe_word_per_line_by_pixel(pix->pixelformat, width);
 
 		reg = height - 1;
 		reg |= ((wpl + 3) / 4 - 1) << 16;
@@ -373,7 +396,7 @@ static void vfe_wm_line_based(struct vfe_device *vfe, u32 wm,
 		writel_relaxed(reg, vfe->base +
 			       VFE_0_BUS_IMAGE_MASTER_n_WR_IMAGE_SIZE(wm));
 
-		wpl = vfe_word_per_line(pix->pixelformat, bytesperline);
+		wpl = vfe_word_per_line_by_bytes(bytesperline);
 
 		reg = 0x3;
 		reg |= (height - 1) << 2;
@@ -536,32 +559,97 @@ static void vfe_set_xbar_cfg(struct vfe_device *vfe, struct vfe_output *output,
 	struct vfe_line *line = container_of(output, struct vfe_line, output);
 	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
 	u32 reg;
-	unsigned int i;
 
-	for (i = 0; i < output->wm_num; i++) {
-		if (i == 0) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
-				VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
-		} else if (i == 1) {
-			reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
-			if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
-				reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
-		}
+	switch (p) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_LUMA <<
+			VFE_0_BUS_XBAR_CFG_x_M_SINGLE_STREAM_SEL_SHIFT;
+
+		if (output->wm_idx[0] % 2 == 1)
+			reg <<= 16;
+
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
+				    reg);
+
+		reg = VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+		if (p == V4L2_PIX_FMT_NV12 || p == V4L2_PIX_FMT_NV16)
+			reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+
+		if (output->wm_idx[1] % 2 == 1)
+			reg <<= 16;
 
-		if (output->wm_idx[i] % 2 == 1)
+		if (enable)
+			vfe_reg_set(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[1]),
+				    reg);
+		else
+			vfe_reg_clr(vfe,
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[1]),
+				    reg);
+		break;
+	case V4L2_PIX_FMT_YUYV:
+	case V4L2_PIX_FMT_YVYU:
+	case V4L2_PIX_FMT_VYUY:
+	case V4L2_PIX_FMT_UYVY:
+		reg = VFE_0_BUS_XBAR_CFG_x_M_REALIGN_BUF_EN;
+		reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_EN;
+
+		if (p == V4L2_PIX_FMT_YUYV || p == V4L2_PIX_FMT_YVYU)
+			reg |= VFE_0_BUS_XBAR_CFG_x_M_PAIR_STREAM_SWAP_INTER_INTRA;
+
+		if (output->wm_idx[0] % 2 == 1)
 			reg <<= 16;
 
 		if (enable)
 			vfe_reg_set(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
 				    reg);
 		else
 			vfe_reg_clr(vfe,
-				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[i]),
+				    VFE_0_BUS_XBAR_CFG_x(output->wm_idx[0]),
 				    reg);
+		break;
+	default:
+		break;
 	}
 }
 
+static void vfe_set_realign_cfg(struct vfe_device *vfe, struct vfe_line *line,
+				u8 enable)
+{
+	u32 p = line->video_out.active_fmt.fmt.pix_mp.pixelformat;
+	u32 val = VFE_0_MODULE_ZOOM_EN_REALIGN_BUF;
+
+	if (p != V4L2_PIX_FMT_YUYV && p != V4L2_PIX_FMT_YVYU &&
+			p != V4L2_PIX_FMT_VYUY && p != V4L2_PIX_FMT_UYVY)
+		return;
+
+	if (enable) {
+		vfe_reg_set(vfe, VFE_0_MODULE_ZOOM_EN, val);
+	} else {
+		vfe_reg_clr(vfe, VFE_0_MODULE_ZOOM_EN, val);
+		return;
+	}
+
+	val = VFE_0_REALIGN_BUF_CFG_HSUB_ENABLE;
+
+	if (p == V4L2_PIX_FMT_UYVY || p == V4L2_PIX_FMT_YUYV)
+		val |= VFE_0_REALIGN_BUF_CFG_CR_ODD_PIXEL;
+	else
+		val |= VFE_0_REALIGN_BUF_CFG_CB_ODD_PIXEL;
+
+	writel_relaxed(val, vfe->base + VFE_0_REALIGN_BUF_CFG);
+}
+
 static void vfe_set_rdi_cid(struct vfe_device *vfe, enum vfe_line_id id, u8 cid)
 {
 	vfe_reg_clr(vfe, VFE_0_RDI_CFG_x(id),
@@ -911,11 +999,11 @@ static void vfe_set_module_cfg(struct vfe_device *vfe, u8 enable)
 		       VFE_0_MODULE_ZOOM_EN_CROP_ENC;
 
 	if (enable) {
-		writel_relaxed(val_lens, vfe->base + VFE_0_MODULE_LENS_EN);
-		writel_relaxed(val_zoom, vfe->base + VFE_0_MODULE_ZOOM_EN);
+		vfe_reg_set(vfe, VFE_0_MODULE_LENS_EN, val_lens);
+		vfe_reg_set(vfe, VFE_0_MODULE_ZOOM_EN, val_zoom);
 	} else {
-		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_LENS_EN);
-		writel_relaxed(0x0, vfe->base + VFE_0_MODULE_ZOOM_EN);
+		vfe_reg_clr(vfe, VFE_0_MODULE_LENS_EN, val_lens);
+		vfe_reg_clr(vfe, VFE_0_MODULE_ZOOM_EN, val_zoom);
 	}
 }
 
@@ -1028,6 +1116,7 @@ const struct vfe_hw_ops vfe_ops_4_7 = {
 	.wm_set_subsample = vfe_wm_set_subsample,
 	.bus_disconnect_wm_from_rdi = vfe_bus_disconnect_wm_from_rdi,
 	.set_xbar_cfg = vfe_set_xbar_cfg,
+	.set_realign_cfg = vfe_set_realign_cfg,
 	.set_rdi_cid = vfe_set_rdi_cid,
 	.reg_update = vfe_reg_update,
 	.reg_update_clear = vfe_reg_update_clear,
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index dc353d624e95..d85d663101f5 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -203,6 +203,9 @@ static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code,
 		{
 			u32 src_code[] = {
 				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_2X8,
 				MEDIA_BUS_FMT_YUYV8_1_5X8,
 			};
 
@@ -213,6 +216,9 @@ static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code,
 		{
 			u32 src_code[] = {
 				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_VYUY8_2X8,
 				MEDIA_BUS_FMT_YVYU8_1_5X8,
 			};
 
@@ -223,6 +229,9 @@ static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code,
 		{
 			u32 src_code[] = {
 				MEDIA_BUS_FMT_UYVY8_2X8,
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_VYUY8_2X8,
 				MEDIA_BUS_FMT_UYVY8_1_5X8,
 			};
 
@@ -233,6 +242,9 @@ static u32 vfe_src_pad_code(struct vfe_line *line, u32 sink_code,
 		{
 			u32 src_code[] = {
 				MEDIA_BUS_FMT_VYUY8_2X8,
+				MEDIA_BUS_FMT_YUYV8_2X8,
+				MEDIA_BUS_FMT_YVYU8_2X8,
+				MEDIA_BUS_FMT_UYVY8_2X8,
 				MEDIA_BUS_FMT_VYUY8_1_5X8,
 			};
 
@@ -308,10 +320,6 @@ static void vfe_init_outputs(struct vfe_device *vfe)
 		output->buf[0] = NULL;
 		output->buf[1] = NULL;
 		INIT_LIST_HEAD(&output->pending_bufs);
-
-		output->wm_num = 1;
-		if (vfe->line[i].id == VFE_LINE_PIX)
-			output->wm_num = 2;
 	}
 }
 
@@ -567,6 +575,7 @@ static int vfe_get_output(struct vfe_line *line)
 {
 	struct vfe_device *vfe = to_vfe(line);
 	struct vfe_output *output;
+	struct v4l2_format *f = &line->video_out.active_fmt;
 	unsigned long flags;
 	int i;
 	int wm_idx;
@@ -582,6 +591,18 @@ static int vfe_get_output(struct vfe_line *line)
 
 	output->active_buf = 0;
 
+	switch (f->fmt.pix_mp.pixelformat) {
+	case V4L2_PIX_FMT_NV12:
+	case V4L2_PIX_FMT_NV21:
+	case V4L2_PIX_FMT_NV16:
+	case V4L2_PIX_FMT_NV61:
+		output->wm_num = 2;
+		break;
+	default:
+		output->wm_num = 1;
+		break;
+	}
+
 	for (i = 0; i < output->wm_num; i++) {
 		wm_idx = vfe_reserve_wm(vfe, line->id);
 		if (wm_idx < 0) {
@@ -712,6 +733,7 @@ static int vfe_enable_output(struct vfe_line *line)
 		ops->enable_irq_pix_line(vfe, 0, line->id, 1);
 		ops->set_module_cfg(vfe, 1);
 		ops->set_camif_cfg(vfe, line);
+		ops->set_realign_cfg(vfe, line, 1);
 		ops->set_xbar_cfg(vfe, output, 1);
 		ops->set_demux_cfg(vfe, line);
 		ops->set_scale_cfg(vfe, line);
@@ -776,6 +798,7 @@ static int vfe_disable_output(struct vfe_line *line)
 
 		ops->enable_irq_pix_line(vfe, 0, line->id, 0);
 		ops->set_module_cfg(vfe, 0);
+		ops->set_realign_cfg(vfe, line, 0);
 		ops->set_xbar_cfg(vfe, output, 0);
 
 		ops->set_camif_cmd(vfe, 0);
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.h b/drivers/media/platform/qcom/camss/camss-vfe.h
index 71f6c97b266e..0d10071ae881 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.h
+++ b/drivers/media/platform/qcom/camss/camss-vfe.h
@@ -107,6 +107,8 @@ struct vfe_hw_ops {
 			     u8 enable);
 	void (*set_rdi_cid)(struct vfe_device *vfe, enum vfe_line_id id,
 			    u8 cid);
+	void (*set_realign_cfg)(struct vfe_device *vfe, struct vfe_line *line,
+				u8 enable);
 	void (*reg_update)(struct vfe_device *vfe, enum vfe_line_id line_id);
 	void (*reg_update_clear)(struct vfe_device *vfe,
 				 enum vfe_line_id line_id);
diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
index ba7d0c45a8d9..e6e114a62355 100644
--- a/drivers/media/platform/qcom/camss/camss-video.c
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -179,6 +179,14 @@ static const struct camss_format_info formats_pix_8x96[] = {
 	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
 	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_NV61, 1,
 	  { { 1, 1 } }, { { 1, 2 } }, { 8 } },
+	{ MEDIA_BUS_FMT_UYVY8_2X8, V4L2_PIX_FMT_UYVY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_VYUY8_2X8, V4L2_PIX_FMT_VYUY, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YUYV8_2X8, V4L2_PIX_FMT_YUYV, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
+	{ MEDIA_BUS_FMT_YVYU8_2X8, V4L2_PIX_FMT_YVYU, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
 };
 
 /* -----------------------------------------------------------------------------
-- 
cgit v1.2.3


From 7e37f47f3ae7b73648768d652b669ea23161db5a Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:38 -0400
Subject: media: camss: csid: Different format support on source pad

Usually the format on the source pad is the same as on the sink pad.
However the CSID is able to do some format conversions. To support
this make the format on the source pad selectable amongst a list
of formats. This list can be different for each sink pad format.
This is still not used but will be when the format conversions
are implemented.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c | 69 +++++++++++++++++++++-----
 1 file changed, 56 insertions(+), 13 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index db960da560c9..cf543fa2c497 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -300,6 +300,47 @@ static const struct csid_format csid_formats_8x96[] = {
 	}
 };
 
+static u32 csid_find_code(u32 *code, unsigned int n_code,
+			  unsigned int index, u32 req_code)
+{
+	int i;
+
+	if (!req_code && (index >= n_code))
+		return 0;
+
+	for (i = 0; i < n_code; i++)
+		if (req_code) {
+			if (req_code == code[i])
+				return req_code;
+		} else {
+			if (i == index)
+				return code[i];
+		}
+
+	return code[0];
+}
+
+static u32 csid_src_pad_code(struct csid_device *csid, u32 sink_code,
+			     unsigned int index, u32 src_req_code)
+{
+	if (csid->camss->version == CAMSS_8x16) {
+		if (index > 0)
+			return 0;
+
+		return sink_code;
+	} else if (csid->camss->version == CAMSS_8x96) {
+		switch (sink_code) {
+		default:
+			if (index > 0)
+				return 0;
+
+			return sink_code;
+		}
+	} else {
+		return 0;
+	}
+}
+
 static const struct csid_format *csid_get_fmt_entry(
 					const struct csid_format *formats,
 					unsigned int nformat,
@@ -674,15 +715,15 @@ static void csid_try_format(struct csid_device *csid,
 
 	case MSM_CSID_PAD_SRC:
 		if (csid->testgen_mode->cur.val == 0) {
-			/* Test generator is disabled, keep pad formats */
-			/* in sync - set and return a format same as sink pad */
-			struct v4l2_mbus_framefmt format;
+			/* Test generator is disabled, */
+			/* keep pad formats in sync */
+			u32 code = fmt->code;
 
-			format = *__csid_get_format(csid, cfg,
-						    MSM_CSID_PAD_SINK, which);
-			*fmt = format;
+			*fmt = *__csid_get_format(csid, cfg,
+						      MSM_CSID_PAD_SINK, which);
+			fmt->code = csid_src_pad_code(csid, fmt->code, 0, code);
 		} else {
-			/* Test generator is enabled, set format on source*/
+			/* Test generator is enabled, set format on source */
 			/* pad to allow test generator usage */
 
 			for (i = 0; i < csid->nformats; i++)
@@ -716,7 +757,6 @@ static int csid_enum_mbus_code(struct v4l2_subdev *sd,
 			       struct v4l2_subdev_mbus_code_enum *code)
 {
 	struct csid_device *csid = v4l2_get_subdevdata(sd);
-	struct v4l2_mbus_framefmt *format;
 
 	if (code->pad == MSM_CSID_PAD_SINK) {
 		if (code->index >= csid->nformats)
@@ -725,13 +765,16 @@ static int csid_enum_mbus_code(struct v4l2_subdev *sd,
 		code->code = csid->formats[code->index].code;
 	} else {
 		if (csid->testgen_mode->cur.val == 0) {
-			if (code->index > 0)
-				return -EINVAL;
+			struct v4l2_mbus_framefmt *sink_fmt;
 
-			format = __csid_get_format(csid, cfg, MSM_CSID_PAD_SINK,
-						   code->which);
+			sink_fmt = __csid_get_format(csid, cfg,
+						     MSM_CSID_PAD_SINK,
+						     code->which);
 
-			code->code = format->code;
+			code->code = csid_src_pad_code(csid, sink_fmt->code,
+						       code->index, 0);
+			if (!code->code)
+				return -EINVAL;
 		} else {
 			if (code->index >= csid->nformats)
 				return -EINVAL;
-- 
cgit v1.2.3


From 5019d7c8209c539226f9e64c38eece7fce732e18 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:39 -0400
Subject: media: camss: csid: MIPI10 to Plain16 format conversion

Use the PRDI mode on 8x96 to allow to configure RAW MIPI10
to Plain16 format conversion.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c  | 33 ++++++++++++-
 drivers/media/platform/qcom/camss/camss-ispif.c | 64 +++++++++++++++++++++++++
 drivers/media/platform/qcom/camss/camss-vfe.c   |  1 +
 drivers/media/platform/qcom/camss/camss-video.c |  2 +
 4 files changed, 99 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index cf543fa2c497..0715a8e326b1 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -32,6 +32,15 @@
 			(((v) == CAMSS_8x16 ? 0x010 : 0x014) + 0x4 * (n))
 #define CAMSS_CSID_CID_n_CFG(v, n)	\
 			(((v) == CAMSS_8x16 ? 0x020 : 0x024) + 0x4 * (n))
+#define CAMSS_CSID_CID_n_CFG_ISPIF_EN	BIT(0)
+#define CAMSS_CSID_CID_n_CFG_RDI_EN	BIT(1)
+#define CAMSS_CSID_CID_n_CFG_DECODE_FORMAT_SHIFT	4
+#define CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_8		(0 << 8)
+#define CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_16		(1 << 8)
+#define CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_LSB	(0 << 9)
+#define CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_MSB	(1 << 9)
+#define CAMSS_CSID_CID_n_CFG_RDI_MODE_RAW_DUMP		(0 << 10)
+#define CAMSS_CSID_CID_n_CFG_RDI_MODE_PLAIN_PACKING	(1 << 10)
 #define CAMSS_CSID_IRQ_CLEAR_CMD(v)	((v) == CAMSS_8x16 ? 0x060 : 0x064)
 #define CAMSS_CSID_IRQ_MASK(v)		((v) == CAMSS_8x16 ? 0x064 : 0x068)
 #define CAMSS_CSID_IRQ_STATUS(v)	((v) == CAMSS_8x16 ? 0x068 : 0x06c)
@@ -330,6 +339,16 @@ static u32 csid_src_pad_code(struct csid_device *csid, u32 sink_code,
 		return sink_code;
 	} else if (csid->camss->version == CAMSS_8x96) {
 		switch (sink_code) {
+		case MEDIA_BUS_FMT_SBGGR10_1X10:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_SBGGR10_1X10,
+				MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE,
+			};
+
+			return csid_find_code(src_code, ARRAY_SIZE(src_code),
+					      index, src_req_code);
+		}
 		default:
 			if (index > 0)
 				return 0;
@@ -636,7 +655,19 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 		writel_relaxed(val, csid->base +
 			       CAMSS_CSID_CID_LUT_VC_n(ver, vc));
 
-		val = (df << 4) | 0x3;
+		val = CAMSS_CSID_CID_n_CFG_ISPIF_EN;
+		val |= CAMSS_CSID_CID_n_CFG_RDI_EN;
+		val |= df << CAMSS_CSID_CID_n_CFG_DECODE_FORMAT_SHIFT;
+		val |= CAMSS_CSID_CID_n_CFG_RDI_MODE_RAW_DUMP;
+		if (csid->camss->version == CAMSS_8x96 &&
+			csid->fmt[MSM_CSID_PAD_SINK].code ==
+					MEDIA_BUS_FMT_SBGGR10_1X10 &&
+			csid->fmt[MSM_CSID_PAD_SRC].code ==
+					MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE) {
+			val |= CAMSS_CSID_CID_n_CFG_RDI_MODE_PLAIN_PACKING;
+			val |= CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_16;
+			val |= CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_LSB;
+		}
 		writel_relaxed(val, csid->base +
 			       CAMSS_CSID_CID_n_CFG(ver, cid));
 
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index 146d5d26b3c1..81d6351c54c6 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -76,6 +76,13 @@
 					(0x254 + 0x200 * (m) + 0x4 * (n))
 #define ISPIF_VFE_m_RDI_INTF_n_CID_MASK(m, n)	\
 					(0x264 + 0x200 * (m) + 0x4 * (n))
+/* PACK_CFG registers are 8x96 only */
+#define ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(m, n)	\
+					(0x270 + 0x200 * (m) + 0x4 * (n))
+#define ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(m, n)	\
+					(0x27c + 0x200 * (m) + 0x4 * (n))
+#define ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0_CID_c_PLAIN(c)	\
+					(1 << ((cid % 8) * 4))
 #define ISPIF_VFE_m_PIX_INTF_n_STATUS(m, n)	\
 					(0x2c0 + 0x200 * (m) + 0x4 * (n))
 #define ISPIF_VFE_m_RDI_INTF_n_STATUS(m, n)	\
@@ -128,6 +135,7 @@ static const u32 ispif_formats_8x96[] = {
 	MEDIA_BUS_FMT_SGBRG10_1X10,
 	MEDIA_BUS_FMT_SGRBG10_1X10,
 	MEDIA_BUS_FMT_SRGGB10_1X10,
+	MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE,
 	MEDIA_BUS_FMT_SBGGR12_1X12,
 	MEDIA_BUS_FMT_SGBRG12_1X12,
 	MEDIA_BUS_FMT_SGRBG12_1X12,
@@ -666,6 +674,54 @@ static void ispif_config_irq(struct ispif_device *ispif, enum ispif_intf intf,
 	writel(0x1, ispif->base + ISPIF_IRQ_GLOBAL_CLEAR_CMD);
 }
 
+/*
+ * ispif_config_pack - Config packing for PRDI mode
+ * @ispif: ISPIF device
+ * @code: media bus format code
+ * @intf: VFE interface
+ * @cid: desired CID to handle
+ * @vfe: VFE HW module id
+ * @enable: enable or disable
+ */
+static void ispif_config_pack(struct ispif_device *ispif, u32 code,
+			      enum ispif_intf intf, u8 cid, u8 vfe, u8 enable)
+{
+	u32 addr, val;
+
+	if (code != MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE)
+		return;
+
+	switch (intf) {
+	case RDI0:
+		if (cid < 8)
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(vfe, 0);
+		else
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(vfe, 0);
+		break;
+	case RDI1:
+		if (cid < 8)
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(vfe, 1);
+		else
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(vfe, 1);
+		break;
+	case RDI2:
+		if (cid < 8)
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0(vfe, 2);
+		else
+			addr = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_1(vfe, 2);
+		break;
+	default:
+		return;
+	}
+
+	if (enable)
+		val = ISPIF_VFE_m_RDI_INTF_n_PACK_CFG_0_CID_c_PLAIN(cid);
+	else
+		val = 0;
+
+	writel_relaxed(val, ispif->base + addr);
+}
+
 /*
  * ispif_set_intf_cmd - Set command to enable/disable interface
  * @ispif: ISPIF device
@@ -734,6 +790,10 @@ static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
 		ispif_select_csid(ispif, intf, csid, vfe, 1);
 		ispif_select_cid(ispif, intf, cid, vfe, 1);
 		ispif_config_irq(ispif, intf, vfe, 1);
+		if (to_camss(ispif)->version == CAMSS_8x96)
+			ispif_config_pack(ispif,
+					  line->fmt[MSM_ISPIF_PAD_SINK].code,
+					  intf, cid, vfe, 1);
 		ispif_set_intf_cmd(ispif, CMD_ENABLE_FRAME_BOUNDARY,
 				   intf, vfe, vc);
 	} else {
@@ -747,6 +807,10 @@ static int ispif_set_stream(struct v4l2_subdev *sd, int enable)
 			return ret;
 
 		mutex_lock(&ispif->config_lock);
+		if (to_camss(ispif)->version == CAMSS_8x96)
+			ispif_config_pack(ispif,
+					  line->fmt[MSM_ISPIF_PAD_SINK].code,
+					  intf, cid, vfe, 0);
 		ispif_config_irq(ispif, intf, vfe, 0);
 		ispif_select_cid(ispif, intf, cid, vfe, 0);
 		ispif_select_csid(ispif, intf, csid, vfe, 0);
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index d85d663101f5..11d37b78c3cd 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -89,6 +89,7 @@ static const struct vfe_format formats_rdi_8x96[] = {
 	{ MEDIA_BUS_FMT_SGBRG10_1X10, 10 },
 	{ MEDIA_BUS_FMT_SGRBG10_1X10, 10 },
 	{ MEDIA_BUS_FMT_SRGGB10_1X10, 10 },
+	{ MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE, 16 },
 	{ MEDIA_BUS_FMT_SBGGR12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
index e6e114a62355..28d53bf4c784 100644
--- a/drivers/media/platform/qcom/camss/camss-video.c
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -101,6 +101,8 @@ static const struct camss_format_info formats_rdi_8x96[] = {
 	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
 	{ MEDIA_BUS_FMT_SRGGB10_1X10, V4L2_PIX_FMT_SRGGB10P, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE, V4L2_PIX_FMT_SBGGR10, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
 	{ MEDIA_BUS_FMT_SBGGR12_1X12, V4L2_PIX_FMT_SBGGR12P, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
 	{ MEDIA_BUS_FMT_SGBRG12_1X12, V4L2_PIX_FMT_SGBRG12P, 1,
-- 
cgit v1.2.3


From f476fb568f98bb6b2d2499ee7059504bf5203a91 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:40 -0400
Subject: media: camss: Add support for RAW MIPI14 on 8x96

Add support for RAW MIPI14 format for RDI mode on 8x96.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c   | 30 ++++++++++++++++++++++++
 drivers/media/platform/qcom/camss/camss-csiphy.c |  4 ++++
 drivers/media/platform/qcom/camss/camss-ispif.c  |  4 ++++
 drivers/media/platform/qcom/camss/camss-vfe.c    |  4 ++++
 drivers/media/platform/qcom/camss/camss-video.c  |  8 +++++++
 5 files changed, 50 insertions(+)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 0715a8e326b1..472884d1546e 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -63,11 +63,13 @@
 #define DATA_TYPE_RAW_8BIT		0x2a
 #define DATA_TYPE_RAW_10BIT		0x2b
 #define DATA_TYPE_RAW_12BIT		0x2c
+#define DATA_TYPE_RAW_14BIT		0x2d
 
 #define DECODE_FORMAT_UNCOMPRESSED_6_BIT	0x0
 #define DECODE_FORMAT_UNCOMPRESSED_8_BIT	0x1
 #define DECODE_FORMAT_UNCOMPRESSED_10_BIT	0x2
 #define DECODE_FORMAT_UNCOMPRESSED_12_BIT	0x3
+#define DECODE_FORMAT_UNCOMPRESSED_14_BIT	0x8
 
 #define CSID_RESET_TIMEOUT_MS 500
 
@@ -306,6 +308,34 @@ static const struct csid_format csid_formats_8x96[] = {
 		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
 		12,
 		1,
+	},
+	{
+		MEDIA_BUS_FMT_SBGGR14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGBRG14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SGRBG14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
+	},
+	{
+		MEDIA_BUS_FMT_SRGGB14_1X14,
+		DATA_TYPE_RAW_14BIT,
+		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
+		14,
+		1,
 	}
 };
 
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index 3cdab59d24f9..cae3e8b9ab37 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -64,6 +64,10 @@ static const struct csiphy_format csiphy_formats_8x96[] = {
 	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SBGGR14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGBRG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGRBG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SRGGB14_1X14, 14 },
 };
 
 /*
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index 81d6351c54c6..3e2f34148977 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -140,6 +140,10 @@ static const u32 ispif_formats_8x96[] = {
 	MEDIA_BUS_FMT_SGBRG12_1X12,
 	MEDIA_BUS_FMT_SGRBG12_1X12,
 	MEDIA_BUS_FMT_SRGGB12_1X12,
+	MEDIA_BUS_FMT_SBGGR14_1X14,
+	MEDIA_BUS_FMT_SGBRG14_1X14,
+	MEDIA_BUS_FMT_SGRBG14_1X14,
+	MEDIA_BUS_FMT_SRGGB14_1X14,
 };
 
 /*
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 11d37b78c3cd..96753090e072 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -94,6 +94,10 @@ static const struct vfe_format formats_rdi_8x96[] = {
 	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_SBGGR14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGBRG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SGRBG14_1X14, 14 },
+	{ MEDIA_BUS_FMT_SRGGB14_1X14, 14 },
 };
 
 static const struct vfe_format formats_pix_8x96[] = {
diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
index 28d53bf4c784..2e19bc8c4161 100644
--- a/drivers/media/platform/qcom/camss/camss-video.c
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -111,6 +111,14 @@ static const struct camss_format_info formats_rdi_8x96[] = {
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
 	{ MEDIA_BUS_FMT_SRGGB12_1X12, V4L2_PIX_FMT_SRGGB12P, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_SBGGR14_1X14, V4L2_PIX_FMT_SBGGR14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_SGBRG14_1X14, V4L2_PIX_FMT_SGBRG14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_SGRBG14_1X14, V4L2_PIX_FMT_SGRBG14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_SRGGB14_1X14, V4L2_PIX_FMT_SRGGB14P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
 };
 
 static const struct camss_format_info formats_pix_8x16[] = {
-- 
cgit v1.2.3


From 363e934d8811d799c88faffc5bfca782fd728334 Mon Sep 17 00:00:00 2001
From: Gaurav Kohli <gkohli@codeaurora.org>
Date: Thu, 2 Aug 2018 14:21:03 +0530
Subject: timers: Clear timer_base::must_forward_clk with timer_base::lock held

timer_base::must_forward_clock is indicating that the base clock might be
stale due to a long idle sleep.

The forwarding of the base clock takes place in the timer softirq or when a
timer is enqueued to a base which is idle. If the enqueue of timer to an
idle base happens from a remote CPU, then the following race can happen:

  CPU0					CPU1
  run_timer_softirq			mod_timer

					base = lock_timer_base(timer);
  base->must_forward_clk = false
					if (base->must_forward_clk)
				       	    forward(base); -> skipped

					enqueue_timer(base, timer, idx);
					-> idx is calculated high due to
					   stale base
					unlock_timer_base(timer);
  base = lock_timer_base(timer);
  forward(base);

The root cause is that timer_base::must_forward_clk is cleared outside the
timer_base::lock held region, so the remote queuing CPU observes it as
cleared, but the base clock is still stale. This can cause large
granularity values for timers, i.e. the accuracy of the expiry time
suffers.

Prevent this by clearing the flag with timer_base::lock held, so that the
forwarding takes place before the cleared flag is observable by a remote
CPU.

Signed-off-by: Gaurav Kohli <gkohli@codeaurora.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: john.stultz@linaro.org
Cc: sboyd@kernel.org
Cc: linux-arm-msm@vger.kernel.org
Link: https://lkml.kernel.org/r/1533199863-22748-1-git-send-email-gkohli@codeaurora.org
---
 kernel/time/timer.c | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/kernel/time/timer.c b/kernel/time/timer.c
index baa528a24a73..fa49cd753dea 100644
--- a/kernel/time/timer.c
+++ b/kernel/time/timer.c
@@ -1657,6 +1657,22 @@ static inline void __run_timers(struct timer_base *base)
 
 	raw_spin_lock_irq(&base->lock);
 
+	/*
+	 * timer_base::must_forward_clk must be cleared before running
+	 * timers so that any timer functions that call mod_timer() will
+	 * not try to forward the base. Idle tracking / clock forwarding
+	 * logic is only used with BASE_STD timers.
+	 *
+	 * The must_forward_clk flag is cleared unconditionally also for
+	 * the deferrable base. The deferrable base is not affected by idle
+	 * tracking and never forwarded, so clearing the flag is a NOOP.
+	 *
+	 * The fact that the deferrable base is never forwarded can cause
+	 * large variations in granularity for deferrable timers, but they
+	 * can be deferred for long periods due to idle anyway.
+	 */
+	base->must_forward_clk = false;
+
 	while (time_after_eq(jiffies, base->clk)) {
 
 		levels = collect_expired_timers(base, heads);
@@ -1676,19 +1692,6 @@ static __latent_entropy void run_timer_softirq(struct softirq_action *h)
 {
 	struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]);
 
-	/*
-	 * must_forward_clk must be cleared before running timers so that any
-	 * timer functions that call mod_timer will not try to forward the
-	 * base. idle trcking / clock forwarding logic is only used with
-	 * BASE_STD timers.
-	 *
-	 * The deferrable base does not do idle tracking at all, so we do
-	 * not forward it. This can result in very large variations in
-	 * granularity for deferrable timers, but they can be deferred for
-	 * long periods due to idle.
-	 */
-	base->must_forward_clk = false;
-
 	__run_timers(base);
 	if (IS_ENABLED(CONFIG_NO_HZ_COMMON))
 		__run_timers(this_cpu_ptr(&timer_bases[BASE_DEF]));
-- 
cgit v1.2.3


From c77aee71bbc67c4b0e56f4ce10406b85d4c929c1 Mon Sep 17 00:00:00 2001
From: Keerthy <j-keerthy@ti.com>
Date: Thu, 2 Aug 2018 12:05:16 +0530
Subject: clocksource: ti-32k: Remove CLOCK_SOURCE_SUSPEND_NONSTOP flag

Since commit 39232ed5a179 ("time: Introduce one suspend clocksource to
compensate the suspend time") suspend/resume fails on AM437x platforms as
the clocksource actually stops in suspend.

Hence remove the CLOCK_SOURCE_SUSPEND_NONSTOP flag.

Suggested-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Keerthy <j-keerthy@ti.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: <daniel.lezcano@linaro.org>
Cc: <linux-omap@vger.kernel.org>
Cc: <baolin.wang@linaro.org>
Cc: <d-gerlach@ti.com>
Cc: <tony@atomide.com>
Cc: <t-kristo@ti.com>
Link: https://lkml.kernel.org/r/1533191716-20476-1-git-send-email-j-keerthy@ti.com
---
 drivers/clocksource/timer-ti-32k.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/clocksource/timer-ti-32k.c b/drivers/clocksource/timer-ti-32k.c
index 880a861ab3c8..29e2e1a78a43 100644
--- a/drivers/clocksource/timer-ti-32k.c
+++ b/drivers/clocksource/timer-ti-32k.c
@@ -78,8 +78,7 @@ static struct ti_32k ti_32k_timer = {
 		.rating		= 250,
 		.read		= ti_32k_read_cycles,
 		.mask		= CLOCKSOURCE_MASK(32),
-		.flags		= CLOCK_SOURCE_IS_CONTINUOUS |
-				CLOCK_SOURCE_SUSPEND_NONSTOP,
+		.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 	},
 };
 
-- 
cgit v1.2.3


From 3ff4f80a74fd38398ae1bd8a458ba9c51aa0dd44 Mon Sep 17 00:00:00 2001
From: Zhong Jiang <zhongjiang@huawei.com>
Date: Wed, 1 Aug 2018 00:24:58 +0800
Subject: debugobjects: Remove redundant NULL pointer check

kmem_cache_destroy() has a built in NULL pointer check, so the one at the
call can be removed.

Signed-off-by: Zhong Jiang <zhongjiang@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: <longman@redhat.com>
Cc: <arnd@arndb.de>
Cc: <yang.shi@linux.alibaba.com>
Link: https://lkml.kernel.org/r/1533054298-35824-1-git-send-email-zhongjiang@huawei.com
---
 lib/debugobjects.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 24c1df0d7466..70935ed91125 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -1188,8 +1188,7 @@ void __init debug_objects_mem_init(void)
 
 	if (!obj_cache || debug_objects_replace_static_objects()) {
 		debug_objects_enabled = 0;
-		if (obj_cache)
-			kmem_cache_destroy(obj_cache);
+		kmem_cache_destroy(obj_cache);
 		pr_warn("out of memory.\n");
 	} else
 		debug_objects_selftest();
-- 
cgit v1.2.3


From b2fcb677d4dd2aac3202365719733452b5512719 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Apr 2018 17:26:38 +0200
Subject: sh: simplify get_arch_dma_ops

Remove the indirection through the dma_ops variable, and just return
nommu_dma_ops directly from get_arch_dma_ops.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Yoshinori Sato <ysato@users.sourceforge.jp>
---
 arch/sh/include/asm/dma-mapping.h |  5 ++---
 arch/sh/kernel/dma-nommu.c        |  8 +-------
 arch/sh/mm/consistent.c           |  3 ---
 arch/sh/mm/init.c                 | 10 ----------
 4 files changed, 3 insertions(+), 23 deletions(-)

diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
index 41167931e5d9..149e71f95be7 100644
--- a/arch/sh/include/asm/dma-mapping.h
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -2,12 +2,11 @@
 #ifndef __ASM_SH_DMA_MAPPING_H
 #define __ASM_SH_DMA_MAPPING_H
 
-extern const struct dma_map_ops *dma_ops;
-extern void no_iommu_init(void);
+extern const struct dma_map_ops nommu_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
-	return dma_ops;
+	return &nommu_dma_ops;
 }
 
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
index 3e3a32fc676e..79a9edafa5b0 100644
--- a/arch/sh/kernel/dma-nommu.c
+++ b/arch/sh/kernel/dma-nommu.c
@@ -79,10 +79,4 @@ const struct dma_map_ops nommu_dma_ops = {
 	.sync_sg_for_device	= nommu_sync_sg_for_device,
 #endif
 };
-
-void __init no_iommu_init(void)
-{
-	if (dma_ops)
-		return;
-	dma_ops = &nommu_dma_ops;
-}
+EXPORT_SYMBOL(nommu_dma_ops);
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index fceb2adfcac7..e9d422bd42a5 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -20,9 +20,6 @@
 #include <asm/cacheflush.h>
 #include <asm/addrspace.h>
 
-const struct dma_map_ops *dma_ops;
-EXPORT_SYMBOL(dma_ops);
-
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 				 dma_addr_t *dma_handle, gfp_t gfp,
 				 unsigned long attrs)
diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 4034035fbede..7713c084d040 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -339,22 +339,12 @@ void __init paging_init(void)
 	free_area_init_nodes(max_zone_pfns);
 }
 
-/*
- * Early initialization for any I/O MMUs we might have.
- */
-static void __init iommu_init(void)
-{
-	no_iommu_init();
-}
-
 unsigned int mem_init_done = 0;
 
 void __init mem_init(void)
 {
 	pg_data_t *pgdat;
 
-	iommu_init();
-
 	high_memory = NULL;
 	for_each_online_pgdat(pgdat)
 		high_memory = max_t(void *, high_memory,
-- 
cgit v1.2.3


From 47fcae0d2a5fc77123fc14b0db9fe0025a1a829a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 18 Apr 2018 08:53:46 +0200
Subject: sh: introduce a sh_cacheop_vaddr helper

And use it in the maple bus code to avoid a dma API dependency.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Yoshinori Sato <ysato@users.sourceforge.jp>
---
 arch/sh/include/asm/cacheflush.h | 7 +++++++
 arch/sh/mm/consistent.c          | 6 +-----
 drivers/sh/maple/maple.c         | 7 ++++---
 3 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/arch/sh/include/asm/cacheflush.h b/arch/sh/include/asm/cacheflush.h
index d103ab5a4e4b..b932e42ef028 100644
--- a/arch/sh/include/asm/cacheflush.h
+++ b/arch/sh/include/asm/cacheflush.h
@@ -101,5 +101,12 @@ void kunmap_coherent(void *kvaddr);
 
 void cpu_cache_init(void);
 
+static inline void *sh_cacheop_vaddr(void *vaddr)
+{
+	if (__in_29bit_mode())
+		vaddr = (void *)CAC_ADDR((unsigned long)vaddr);
+	return vaddr;
+}
+
 #endif /* __KERNEL__ */
 #endif /* __ASM_SH_CACHEFLUSH_H */
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index e9d422bd42a5..1622ae6b9dbd 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -74,10 +74,7 @@ void dma_generic_free_coherent(struct device *dev, size_t size,
 void sh_sync_dma_for_device(void *vaddr, size_t size,
 		    enum dma_data_direction direction)
 {
-	void *addr;
-
-	addr = __in_29bit_mode() ?
-	       (void *)CAC_ADDR((unsigned long)vaddr) : vaddr;
+	void *addr = sh_cacheop_vaddr(vaddr);
 
 	switch (direction) {
 	case DMA_FROM_DEVICE:		/* invalidate only */
@@ -93,7 +90,6 @@ void sh_sync_dma_for_device(void *vaddr, size_t size,
 		BUG();
 	}
 }
-EXPORT_SYMBOL(sh_sync_dma_for_device);
 
 static int __init memchunk_setup(char *str)
 {
diff --git a/drivers/sh/maple/maple.c b/drivers/sh/maple/maple.c
index 2e45988d1259..e5d7fb81ad66 100644
--- a/drivers/sh/maple/maple.c
+++ b/drivers/sh/maple/maple.c
@@ -300,8 +300,8 @@ static void maple_send(void)
 	mutex_unlock(&maple_wlist_lock);
 	if (maple_packets > 0) {
 		for (i = 0; i < (1 << MAPLE_DMA_PAGES); i++)
-			sh_sync_dma_for_device(maple_sendbuf + i * PAGE_SIZE,
-				       PAGE_SIZE, DMA_BIDIRECTIONAL);
+			__flush_purge_region(maple_sendbuf + i * PAGE_SIZE,
+					PAGE_SIZE);
 	}
 
 finish:
@@ -642,7 +642,8 @@ static void maple_dma_handler(struct work_struct *work)
 		list_for_each_entry_safe(mq, nmq, &maple_sentq, list) {
 			mdev = mq->dev;
 			recvbuf = mq->recvbuf->buf;
-			sh_sync_dma_for_device(recvbuf, 0x400, DMA_FROM_DEVICE);
+			__flush_invalidate_region(sh_cacheop_vaddr(recvbuf),
+					0x400);
 			code = recvbuf[0];
 			kfree(mq->sendbuf);
 			list_del_init(&mq->list);
-- 
cgit v1.2.3


From a602915f5d0d9eff96a1d85b6f81e4921b52edfe Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 17 Apr 2018 22:02:10 +0200
Subject: sh: use dma_direct_ops for the CONFIG_DMA_COHERENT case

This is a slight change in behavior as we avoid the detour through the
virtual mapping for the coherent allocator, but if this CPU really is
coherent that should be the right thing to do.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Yoshinori Sato <ysato@users.sourceforge.jp>
---
 arch/sh/Kconfig                   | 1 +
 arch/sh/include/asm/dma-mapping.h | 4 ++++
 arch/sh/kernel/Makefile           | 4 ++--
 arch/sh/kernel/dma-nommu.c        | 4 ----
 4 files changed, 7 insertions(+), 6 deletions(-)

diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index dd4f3d3e644f..c9993a0cdc7e 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -159,6 +159,7 @@ config SWAP_IO_SPACE
 	bool
 
 config DMA_COHERENT
+	select DMA_DIRECT_OPS
 	bool
 
 config DMA_NONCOHERENT
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
index 149e71f95be7..1ebc6a4eb1c5 100644
--- a/arch/sh/include/asm/dma-mapping.h
+++ b/arch/sh/include/asm/dma-mapping.h
@@ -6,7 +6,11 @@ extern const struct dma_map_ops nommu_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
 {
+#ifdef CONFIG_DMA_NONCOHERENT
 	return &nommu_dma_ops;
+#else
+	return &dma_direct_ops;
+#endif
 }
 
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index dc80041f7363..cb5f1bfb52de 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -12,7 +12,7 @@ endif
 
 CFLAGS_REMOVE_return_address.o = -pg
 
-obj-y	:= debugtraps.o dma-nommu.o dumpstack.o 		\
+obj-y	:= debugtraps.o dumpstack.o 		\
 	   idle.o io.o irq.o irq_$(BITS).o kdebugfs.o			\
 	   machvec.o nmi_debug.o process.o				\
 	   process_$(BITS).o ptrace.o ptrace_$(BITS).o			\
@@ -45,7 +45,7 @@ obj-$(CONFIG_DUMP_CODE)		+= disassemble.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o
 obj-$(CONFIG_DWARF_UNWINDER)	+= dwarf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_callchain.o
-
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-nommu.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)		+= hw_breakpoint.o
 
 ccflags-y := -Werror
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
index 79a9edafa5b0..d8689b1cb743 100644
--- a/arch/sh/kernel/dma-nommu.c
+++ b/arch/sh/kernel/dma-nommu.c
@@ -51,7 +51,6 @@ static int nommu_map_sg(struct device *dev, struct scatterlist *sg,
 	return nents;
 }
 
-#ifdef CONFIG_DMA_NONCOHERENT
 static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr,
 			      size_t size, enum dma_data_direction dir)
 {
@@ -67,16 +66,13 @@ static void nommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 	for_each_sg(sg, s, nelems, i)
 		sh_sync_dma_for_device(sg_virt(s), s->length, dir);
 }
-#endif
 
 const struct dma_map_ops nommu_dma_ops = {
 	.alloc			= dma_generic_alloc_coherent,
 	.free			= dma_generic_free_coherent,
 	.map_page		= nommu_map_page,
 	.map_sg			= nommu_map_sg,
-#ifdef CONFIG_DMA_NONCOHERENT
 	.sync_single_for_device	= nommu_sync_single_for_device,
 	.sync_sg_for_device	= nommu_sync_sg_for_device,
-#endif
 };
 EXPORT_SYMBOL(nommu_dma_ops);
-- 
cgit v1.2.3


From 46bcde94cd02283535cb719666399f1c4cfb8f22 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 18 Jul 2018 06:55:20 -0700
Subject: sh: split arch/sh/mm/consistent.c

Half of the file just contains platform device memory setup code which
is required for all builds, and half contains helpers for dma coherent
allocation, which is only needed if CONFIG_DMA_NONCOHERENT is enabled.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Yoshinori Sato <ysato@users.sourceforge.jp>
---
 arch/sh/kernel/Makefile       |  2 +-
 arch/sh/kernel/dma-coherent.c | 84 +++++++++++++++++++++++++++++++++++++++++++
 arch/sh/mm/consistent.c       | 80 -----------------------------------------
 3 files changed, 85 insertions(+), 81 deletions(-)
 create mode 100644 arch/sh/kernel/dma-coherent.c

diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index cb5f1bfb52de..d5ddb64bfffe 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -45,7 +45,7 @@ obj-$(CONFIG_DUMP_CODE)		+= disassemble.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o
 obj-$(CONFIG_DWARF_UNWINDER)	+= dwarf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_callchain.o
-obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-nommu.o
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-nommu.o dma-coherent.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)		+= hw_breakpoint.o
 
 ccflags-y := -Werror
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
new file mode 100644
index 000000000000..2518065d5d27
--- /dev/null
+++ b/arch/sh/kernel/dma-coherent.c
@@ -0,0 +1,84 @@
+/*
+ * Copyright (C) 2004 - 2007  Paul Mundt
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+#include <linux/mm.h>
+#include <linux/init.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
+#include <asm/cacheflush.h>
+#include <asm/addrspace.h>
+
+void *dma_generic_alloc_coherent(struct device *dev, size_t size,
+				 dma_addr_t *dma_handle, gfp_t gfp,
+				 unsigned long attrs)
+{
+	void *ret, *ret_nocache;
+	int order = get_order(size);
+
+	gfp |= __GFP_ZERO;
+
+	ret = (void *)__get_free_pages(gfp, order);
+	if (!ret)
+		return NULL;
+
+	/*
+	 * Pages from the page allocator may have data present in
+	 * cache. So flush the cache before using uncached memory.
+	 */
+	sh_sync_dma_for_device(ret, size, DMA_BIDIRECTIONAL);
+
+	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
+	if (!ret_nocache) {
+		free_pages((unsigned long)ret, order);
+		return NULL;
+	}
+
+	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
+
+	*dma_handle = virt_to_phys(ret);
+	if (!WARN_ON(!dev))
+		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
+
+	return ret_nocache;
+}
+
+void dma_generic_free_coherent(struct device *dev, size_t size,
+			       void *vaddr, dma_addr_t dma_handle,
+			       unsigned long attrs)
+{
+	int order = get_order(size);
+	unsigned long pfn = (dma_handle >> PAGE_SHIFT);
+	int k;
+
+	if (!WARN_ON(!dev))
+		pfn += dev->dma_pfn_offset;
+
+	for (k = 0; k < (1 << order); k++)
+		__free_pages(pfn_to_page(pfn + k), 0);
+
+	iounmap(vaddr);
+}
+
+void sh_sync_dma_for_device(void *vaddr, size_t size,
+		    enum dma_data_direction direction)
+{
+	void *addr = sh_cacheop_vaddr(vaddr);
+
+	switch (direction) {
+	case DMA_FROM_DEVICE:		/* invalidate only */
+		__flush_invalidate_region(addr, size);
+		break;
+	case DMA_TO_DEVICE:		/* writeback only */
+		__flush_wback_region(addr, size);
+		break;
+	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
+		__flush_purge_region(addr, size);
+		break;
+	default:
+		BUG();
+	}
+}
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 1622ae6b9dbd..792f36129062 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -1,10 +1,6 @@
 /*
- * arch/sh/mm/consistent.c
- *
  * Copyright (C) 2004 - 2007  Paul Mundt
  *
- * Declared coherent memory functions based on arch/x86/kernel/pci-dma_32.c
- *
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
  * for more details.
@@ -13,83 +9,7 @@
 #include <linux/init.h>
 #include <linux/platform_device.h>
 #include <linux/dma-mapping.h>
-#include <linux/dma-debug.h>
 #include <linux/io.h>
-#include <linux/module.h>
-#include <linux/gfp.h>
-#include <asm/cacheflush.h>
-#include <asm/addrspace.h>
-
-void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_handle, gfp_t gfp,
-				 unsigned long attrs)
-{
-	void *ret, *ret_nocache;
-	int order = get_order(size);
-
-	gfp |= __GFP_ZERO;
-
-	ret = (void *)__get_free_pages(gfp, order);
-	if (!ret)
-		return NULL;
-
-	/*
-	 * Pages from the page allocator may have data present in
-	 * cache. So flush the cache before using uncached memory.
-	 */
-	sh_sync_dma_for_device(ret, size, DMA_BIDIRECTIONAL);
-
-	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
-	if (!ret_nocache) {
-		free_pages((unsigned long)ret, order);
-		return NULL;
-	}
-
-	split_page(pfn_to_page(virt_to_phys(ret) >> PAGE_SHIFT), order);
-
-	*dma_handle = virt_to_phys(ret);
-	if (!WARN_ON(!dev))
-		*dma_handle -= PFN_PHYS(dev->dma_pfn_offset);
-
-	return ret_nocache;
-}
-
-void dma_generic_free_coherent(struct device *dev, size_t size,
-			       void *vaddr, dma_addr_t dma_handle,
-			       unsigned long attrs)
-{
-	int order = get_order(size);
-	unsigned long pfn = dma_handle >> PAGE_SHIFT;
-	int k;
-
-	if (!WARN_ON(!dev))
-		pfn += dev->dma_pfn_offset;
-
-	for (k = 0; k < (1 << order); k++)
-		__free_pages(pfn_to_page(pfn + k), 0);
-
-	iounmap(vaddr);
-}
-
-void sh_sync_dma_for_device(void *vaddr, size_t size,
-		    enum dma_data_direction direction)
-{
-	void *addr = sh_cacheop_vaddr(vaddr);
-
-	switch (direction) {
-	case DMA_FROM_DEVICE:		/* invalidate only */
-		__flush_invalidate_region(addr, size);
-		break;
-	case DMA_TO_DEVICE:		/* writeback only */
-		__flush_wback_region(addr, size);
-		break;
-	case DMA_BIDIRECTIONAL:		/* writeback and invalidate */
-		__flush_purge_region(addr, size);
-		break;
-	default:
-		BUG();
-	}
-}
 
 static int __init memchunk_setup(char *str)
 {
-- 
cgit v1.2.3


From 6fa1d28e38cfa0c90f8d64c0cab37769e5337b85 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 11 May 2018 08:36:53 +0200
Subject: sh: use generic dma_noncoherent_ops

Switch to the generic noncoherent direct mapping implementation.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Yoshinori Sato <ysato@users.sourceforge.jp>
---
 arch/sh/Kconfig                   |  3 +-
 arch/sh/include/asm/Kbuild        |  1 +
 arch/sh/include/asm/dma-mapping.h | 26 -------------
 arch/sh/kernel/Makefile           |  2 +-
 arch/sh/kernel/dma-coherent.c     | 23 ++++++------
 arch/sh/kernel/dma-nommu.c        | 78 ---------------------------------------
 6 files changed, 15 insertions(+), 118 deletions(-)
 delete mode 100644 arch/sh/include/asm/dma-mapping.h
 delete mode 100644 arch/sh/kernel/dma-nommu.c

diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index c9993a0cdc7e..da4db4b5359f 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -51,7 +51,6 @@ config SUPERH
 	select HAVE_ARCH_AUDITSYSCALL
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_NMI
-	select NEED_DMA_MAP_STATE
 	select NEED_SG_DMA_LENGTH
 
 	help
@@ -164,6 +163,8 @@ config DMA_COHERENT
 
 config DMA_NONCOHERENT
 	def_bool !DMA_COHERENT
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
 
 config PGTABLE_LEVELS
 	default 3 if X2TLB
diff --git a/arch/sh/include/asm/Kbuild b/arch/sh/include/asm/Kbuild
index 46dd82ab2c29..6a5609a55965 100644
--- a/arch/sh/include/asm/Kbuild
+++ b/arch/sh/include/asm/Kbuild
@@ -2,6 +2,7 @@ generic-y += compat.h
 generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
+generic-y += dma-mapping.h
 generic-y += emergency-restart.h
 generic-y += exec.h
 generic-y += irq_regs.h
diff --git a/arch/sh/include/asm/dma-mapping.h b/arch/sh/include/asm/dma-mapping.h
deleted file mode 100644
index 1ebc6a4eb1c5..000000000000
--- a/arch/sh/include/asm/dma-mapping.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __ASM_SH_DMA_MAPPING_H
-#define __ASM_SH_DMA_MAPPING_H
-
-extern const struct dma_map_ops nommu_dma_ops;
-
-static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
-{
-#ifdef CONFIG_DMA_NONCOHERENT
-	return &nommu_dma_ops;
-#else
-	return &dma_direct_ops;
-#endif
-}
-
-extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag,
-					unsigned long attrs);
-extern void dma_generic_free_coherent(struct device *dev, size_t size,
-				      void *vaddr, dma_addr_t dma_handle,
-				      unsigned long attrs);
-
-void sh_sync_dma_for_device(void *vaddr, size_t size,
-	    enum dma_data_direction dir);
-
-#endif /* __ASM_SH_DMA_MAPPING_H */
diff --git a/arch/sh/kernel/Makefile b/arch/sh/kernel/Makefile
index d5ddb64bfffe..59673f8a3379 100644
--- a/arch/sh/kernel/Makefile
+++ b/arch/sh/kernel/Makefile
@@ -45,7 +45,7 @@ obj-$(CONFIG_DUMP_CODE)		+= disassemble.o
 obj-$(CONFIG_HIBERNATION)	+= swsusp.o
 obj-$(CONFIG_DWARF_UNWINDER)	+= dwarf.o
 obj-$(CONFIG_PERF_EVENTS)	+= perf_event.o perf_callchain.o
-obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-nommu.o dma-coherent.o
+obj-$(CONFIG_DMA_NONCOHERENT)	+= dma-coherent.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT)		+= hw_breakpoint.o
 
 ccflags-y := -Werror
diff --git a/arch/sh/kernel/dma-coherent.c b/arch/sh/kernel/dma-coherent.c
index 2518065d5d27..a0021eef956b 100644
--- a/arch/sh/kernel/dma-coherent.c
+++ b/arch/sh/kernel/dma-coherent.c
@@ -7,14 +7,13 @@
  */
 #include <linux/mm.h>
 #include <linux/init.h>
-#include <linux/dma-mapping.h>
+#include <linux/dma-noncoherent.h>
 #include <linux/module.h>
 #include <asm/cacheflush.h>
 #include <asm/addrspace.h>
 
-void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_handle, gfp_t gfp,
-				 unsigned long attrs)
+void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, unsigned long attrs)
 {
 	void *ret, *ret_nocache;
 	int order = get_order(size);
@@ -29,7 +28,8 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 	 * Pages from the page allocator may have data present in
 	 * cache. So flush the cache before using uncached memory.
 	 */
-	sh_sync_dma_for_device(ret, size, DMA_BIDIRECTIONAL);
+	arch_sync_dma_for_device(dev, virt_to_phys(ret), size,
+			DMA_BIDIRECTIONAL);
 
 	ret_nocache = (void __force *)ioremap_nocache(virt_to_phys(ret), size);
 	if (!ret_nocache) {
@@ -46,9 +46,8 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size,
 	return ret_nocache;
 }
 
-void dma_generic_free_coherent(struct device *dev, size_t size,
-			       void *vaddr, dma_addr_t dma_handle,
-			       unsigned long attrs)
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
+		dma_addr_t dma_handle, unsigned long attrs)
 {
 	int order = get_order(size);
 	unsigned long pfn = (dma_handle >> PAGE_SHIFT);
@@ -63,12 +62,12 @@ void dma_generic_free_coherent(struct device *dev, size_t size,
 	iounmap(vaddr);
 }
 
-void sh_sync_dma_for_device(void *vaddr, size_t size,
-		    enum dma_data_direction direction)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	void *addr = sh_cacheop_vaddr(vaddr);
+	void *addr = sh_cacheop_vaddr(phys_to_virt(paddr));
 
-	switch (direction) {
+	switch (dir) {
 	case DMA_FROM_DEVICE:		/* invalidate only */
 		__flush_invalidate_region(addr, size);
 		break;
diff --git a/arch/sh/kernel/dma-nommu.c b/arch/sh/kernel/dma-nommu.c
deleted file mode 100644
index d8689b1cb743..000000000000
--- a/arch/sh/kernel/dma-nommu.c
+++ /dev/null
@@ -1,78 +0,0 @@
-/*
- * DMA mapping support for platforms lacking IOMMUs.
- *
- * Copyright (C) 2009  Paul Mundt
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-#include <linux/dma-mapping.h>
-#include <linux/io.h>
-#include <asm/cacheflush.h>
-
-static dma_addr_t nommu_map_page(struct device *dev, struct page *page,
-				 unsigned long offset, size_t size,
-				 enum dma_data_direction dir,
-				 unsigned long attrs)
-{
-	dma_addr_t addr = page_to_phys(page) + offset
-		- PFN_PHYS(dev->dma_pfn_offset);
-
-	WARN_ON(size == 0);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		sh_sync_dma_for_device(page_address(page) + offset, size, dir);
-
-	return addr;
-}
-
-static int nommu_map_sg(struct device *dev, struct scatterlist *sg,
-			int nents, enum dma_data_direction dir,
-			unsigned long attrs)
-{
-	struct scatterlist *s;
-	int i;
-
-	WARN_ON(nents == 0 || sg[0].length == 0);
-
-	for_each_sg(sg, s, nents, i) {
-		dma_addr_t offset = PFN_PHYS(dev->dma_pfn_offset);
-
-		BUG_ON(!sg_page(s));
-
-		if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-			sh_sync_dma_for_device(sg_virt(s), s->length, dir);
-
-		s->dma_address = sg_phys(s) - offset;
-		s->dma_length = s->length;
-	}
-
-	return nents;
-}
-
-static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr,
-			      size_t size, enum dma_data_direction dir)
-{
-	sh_sync_dma_for_device(phys_to_virt(addr), size, dir);
-}
-
-static void nommu_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-			  int nelems, enum dma_data_direction dir)
-{
-	struct scatterlist *s;
-	int i;
-
-	for_each_sg(sg, s, nelems, i)
-		sh_sync_dma_for_device(sg_virt(s), s->length, dir);
-}
-
-const struct dma_map_ops nommu_dma_ops = {
-	.alloc			= dma_generic_alloc_coherent,
-	.free			= dma_generic_free_coherent,
-	.map_page		= nommu_map_page,
-	.map_sg			= nommu_map_sg,
-	.sync_single_for_device	= nommu_sync_single_for_device,
-	.sync_sg_for_device	= nommu_sync_sg_for_device,
-};
-EXPORT_SYMBOL(nommu_dma_ops);
-- 
cgit v1.2.3


From 8e82a728792bf66b9f0a29c9d4c4b0630f7b9c79 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 2 Aug 2018 14:04:45 +0200
Subject: ALSA: hda: Correct Asrock B85M-ITX power_save blacklist entry

I added the subsys product-id for the HDMI HDA device rather then for
the PCH one, this commit fixes this.

BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=1525104
Cc: stable@vger.kernel.org
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 1ae1850b3bfd..647ae1a71e10 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2207,7 +2207,7 @@ out_free:
  */
 static struct snd_pci_quirk power_save_blacklist[] = {
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
-	SND_PCI_QUIRK(0x1849, 0x0c0c, "Asrock B85M-ITX", 0),
+	SND_PCI_QUIRK(0x1849, 0xc892, "Asrock B85M-ITX", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
 	SND_PCI_QUIRK(0x1849, 0x7662, "Asrock H81M-HDS", 0),
 	/* https://bugzilla.redhat.com/show_bug.cgi?id=1525104 */
-- 
cgit v1.2.3


From c7ba9f7cb55926605983187a68624999b93abb94 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 1 Aug 2018 00:08:06 +0800
Subject: x86/platform/olpc: Use PTR_ERR_OR_ZERO()

Replace the open coded equivalent with PTR_ERR_OR_ZERO().

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/1533053286-34990-1-git-send-email-zhongjiang@huawei.com
---
 arch/x86/platform/olpc/olpc.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/platform/olpc/olpc.c b/arch/x86/platform/olpc/olpc.c
index 7c3077e58fa0..f0e920fb98ad 100644
--- a/arch/x86/platform/olpc/olpc.c
+++ b/arch/x86/platform/olpc/olpc.c
@@ -311,10 +311,8 @@ static int __init add_xo1_platform_devices(void)
 		return PTR_ERR(pdev);
 
 	pdev = platform_device_register_simple("olpc-xo1", -1, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
 
-	return 0;
+	return PTR_ERR_OR_ZERO(pdev);
 }
 
 static int olpc_xo1_ec_probe(struct platform_device *pdev)
-- 
cgit v1.2.3


From d79d024820f2e522ab30b5e6662c245f887c752b Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 31 Jul 2018 10:09:38 +0100
Subject: x86/platform/UV: Remove redundant check of p == q

The check for p == q is dead code because the proceeding switch
statements jump to the end of the outer for-loop with continue
statements.  Remove the dead code.

Detected by CoverityScan, CID#145071 ("Structurally dead code")

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: kernel-janitors@vger.kernel.org
Link: https://lkml.kernel.org/r/20180731090938.11856-1-colin.king@canonical.com
---
 arch/x86/platform/uv/tlb_uv.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index ca446da48fd2..e26dfad507c8 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1607,8 +1607,6 @@ static int parse_tunables_write(struct bau_control *bcp, char *instr,
 				*tunables[cnt].tunp = val;
 			continue;
 		}
-		if (q == p)
-			break;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 765d28f136291f9639e3c031a1070fb76d6625c7 Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Tue, 12 Jun 2018 19:48:52 +0800
Subject: x86/mm: Remove redundant check for kmem_cache_create()

The flag 'SLAB_PANIC' implies panic on failure, So there is no need to
check the returned pointer for NULL.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: hpa@zytor.com
Link: https://lkml.kernel.org/r/1528804132-154948-1-git-send-email-cgxu519@gmx.com
---
 arch/x86/mm/pgtable.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index e3deefb891da..0f1683fcb196 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -329,9 +329,6 @@ static int __init pgd_cache_init(void)
 	 */
 	pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
 				      SLAB_PANIC, NULL);
-	if (!pgd_cache)
-		return -ENOMEM;
-
 	return 0;
 }
 core_initcall(pgd_cache_init);
-- 
cgit v1.2.3


From 216a37202f10b7d78f2f98e26a6681f367165f05 Mon Sep 17 00:00:00 2001
From: Uros Bizjak <ubizjak@gmail.com>
Date: Fri, 29 Jun 2018 16:28:44 +0200
Subject: x86/boot: Use CC_SET()/CC_OUT() instead of open coding it

Remove open-coded uses of set instructions with CC_SET()/CC_OUT().

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20180629142844.15200-1-ubizjak@gmail.com
---
 arch/x86/boot/bitops.h | 3 ++-
 arch/x86/boot/string.c | 5 +++--
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 0d41d68131cc..2e1382486e91 100644
--- a/arch/x86/boot/bitops.h
+++ b/arch/x86/boot/bitops.h
@@ -17,6 +17,7 @@
 #define _LINUX_BITOPS_H		/* Inhibit inclusion of <linux/bitops.h> */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 
 static inline bool constant_test_bit(int nr, const void *addr)
 {
@@ -28,7 +29,7 @@ static inline bool variable_test_bit(int nr, const void *addr)
 	bool v;
 	const u32 *p = (const u32 *)addr;
 
-	asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
+	asm("btl %2,%1" CC_SET(c) : CC_OUT(c) (v) : "m" (*p), "Ir" (nr));
 	return v;
 }
 
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 16f49123d747..c4428a176973 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -13,6 +13,7 @@
  */
 
 #include <linux/types.h>
+#include <asm/asm.h>
 #include "ctype.h"
 #include "string.h"
 
@@ -28,8 +29,8 @@
 int memcmp(const void *s1, const void *s2, size_t len)
 {
 	bool diff;
-	asm("repe; cmpsb; setnz %0"
-	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	asm("repe; cmpsb" CC_SET(nz)
+	    : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 
-- 
cgit v1.2.3


From 0b2c1aec49ddb2260894df6c69ae7b34142ff936 Mon Sep 17 00:00:00 2001
From: Zhong Jiang <zhongjiang@huawei.com>
Date: Sat, 21 Jul 2018 16:33:24 +0800
Subject: x86/iommu: Use NULL instead of 0

Fixes the following sparse warning:

arch/x86/kernel/pci-iommu_table.c:63:37: warning: Using plain integer as NULL pointer

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: <hpa@zytor.com>
Cc: <gregkh@linuxfoundation.org>
Link: https://lkml.kernel.org/r/1532162004-24670-1-git-send-email-zhongjiang@huawei.com
---
 arch/x86/kernel/pci-iommu_table.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/pci-iommu_table.c b/arch/x86/kernel/pci-iommu_table.c
index 4dfd90a75e63..2e9006c1e240 100644
--- a/arch/x86/kernel/pci-iommu_table.c
+++ b/arch/x86/kernel/pci-iommu_table.c
@@ -60,7 +60,7 @@ void __init check_iommu_entries(struct iommu_table_entry *start,
 			printk(KERN_ERR "CYCLIC DEPENDENCY FOUND! %pS depends on %pS and vice-versa. BREAKING IT.\n",
 			       p->detect, q->detect);
 			/* Heavy handed way..*/
-			x->depend = 0;
+			x->depend = NULL;
 		}
 	}
 
-- 
cgit v1.2.3


From cc8fe07398e390d2047c30849f3055d5074ee833 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:41 -0400
Subject: media: camss: Add support for 10-bit grayscale formats

Add support for 10-bit packed V4L2_PIX_FMT_Y10P (on 8x16 and 8x96)
and unpacked V4L2_PIX_FMT_Y10 (on 8x96 only) pixel formats.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c   | 50 +++++++++++++++++++-----
 drivers/media/platform/qcom/camss/camss-csiphy.c |  2 +
 drivers/media/platform/qcom/camss/camss-ispif.c  |  6 ++-
 drivers/media/platform/qcom/camss/camss-vfe.c    |  3 ++
 drivers/media/platform/qcom/camss/camss-video.c  |  6 +++
 5 files changed, 56 insertions(+), 11 deletions(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 472884d1546e..6e141af6b6df 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -193,7 +193,14 @@ static const struct csid_format csid_formats_8x16[] = {
 		DECODE_FORMAT_UNCOMPRESSED_12_BIT,
 		12,
 		1,
-	}
+	},
+	{
+		MEDIA_BUS_FMT_Y10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
 };
 
 static const struct csid_format csid_formats_8x96[] = {
@@ -336,7 +343,14 @@ static const struct csid_format csid_formats_8x96[] = {
 		DECODE_FORMAT_UNCOMPRESSED_14_BIT,
 		14,
 		1,
-	}
+	},
+	{
+		MEDIA_BUS_FMT_Y10_1X10,
+		DATA_TYPE_RAW_10BIT,
+		DECODE_FORMAT_UNCOMPRESSED_10_BIT,
+		10,
+		1,
+	},
 };
 
 static u32 csid_find_code(u32 *code, unsigned int n_code,
@@ -379,6 +393,16 @@ static u32 csid_src_pad_code(struct csid_device *csid, u32 sink_code,
 			return csid_find_code(src_code, ARRAY_SIZE(src_code),
 					      index, src_req_code);
 		}
+		case MEDIA_BUS_FMT_Y10_1X10:
+		{
+			u32 src_code[] = {
+				MEDIA_BUS_FMT_Y10_1X10,
+				MEDIA_BUS_FMT_Y10_2X8_PADHI_LE,
+			};
+
+			return csid_find_code(src_code, ARRAY_SIZE(src_code),
+					      index, src_req_code);
+		}
 		default:
 			if (index > 0)
 				return 0;
@@ -689,15 +713,21 @@ static int csid_set_stream(struct v4l2_subdev *sd, int enable)
 		val |= CAMSS_CSID_CID_n_CFG_RDI_EN;
 		val |= df << CAMSS_CSID_CID_n_CFG_DECODE_FORMAT_SHIFT;
 		val |= CAMSS_CSID_CID_n_CFG_RDI_MODE_RAW_DUMP;
-		if (csid->camss->version == CAMSS_8x96 &&
-			csid->fmt[MSM_CSID_PAD_SINK].code ==
-					MEDIA_BUS_FMT_SBGGR10_1X10 &&
-			csid->fmt[MSM_CSID_PAD_SRC].code ==
-					MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE) {
-			val |= CAMSS_CSID_CID_n_CFG_RDI_MODE_PLAIN_PACKING;
-			val |= CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_16;
-			val |= CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_LSB;
+
+		if (csid->camss->version == CAMSS_8x96) {
+			u32 sink_code = csid->fmt[MSM_CSID_PAD_SINK].code;
+			u32 src_code = csid->fmt[MSM_CSID_PAD_SRC].code;
+
+			if ((sink_code == MEDIA_BUS_FMT_SBGGR10_1X10 &&
+			     src_code == MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE) ||
+			    (sink_code == MEDIA_BUS_FMT_Y10_1X10 &&
+			     src_code == MEDIA_BUS_FMT_Y10_2X8_PADHI_LE)) {
+				val |= CAMSS_CSID_CID_n_CFG_RDI_MODE_PLAIN_PACKING;
+				val |= CAMSS_CSID_CID_n_CFG_PLAIN_FORMAT_16;
+				val |= CAMSS_CSID_CID_n_CFG_PLAIN_ALIGNMENT_LSB;
+			}
 		}
+
 		writel_relaxed(val, csid->base +
 			       CAMSS_CSID_CID_n_CFG(ver, cid));
 
diff --git a/drivers/media/platform/qcom/camss/camss-csiphy.c b/drivers/media/platform/qcom/camss/camss-csiphy.c
index cae3e8b9ab37..4559f3b1b38c 100644
--- a/drivers/media/platform/qcom/camss/camss-csiphy.c
+++ b/drivers/media/platform/qcom/camss/camss-csiphy.c
@@ -45,6 +45,7 @@ static const struct csiphy_format csiphy_formats_8x16[] = {
 	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
 };
 
 static const struct csiphy_format csiphy_formats_8x96[] = {
@@ -68,6 +69,7 @@ static const struct csiphy_format csiphy_formats_8x96[] = {
 	{ MEDIA_BUS_FMT_SGBRG14_1X14, 14 },
 	{ MEDIA_BUS_FMT_SGRBG14_1X14, 14 },
 	{ MEDIA_BUS_FMT_SRGGB14_1X14, 14 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
 };
 
 /*
diff --git a/drivers/media/platform/qcom/camss/camss-ispif.c b/drivers/media/platform/qcom/camss/camss-ispif.c
index 3e2f34148977..7f269021d08c 100644
--- a/drivers/media/platform/qcom/camss/camss-ispif.c
+++ b/drivers/media/platform/qcom/camss/camss-ispif.c
@@ -120,6 +120,7 @@ static const u32 ispif_formats_8x16[] = {
 	MEDIA_BUS_FMT_SGBRG12_1X12,
 	MEDIA_BUS_FMT_SGRBG12_1X12,
 	MEDIA_BUS_FMT_SRGGB12_1X12,
+	MEDIA_BUS_FMT_Y10_1X10,
 };
 
 static const u32 ispif_formats_8x96[] = {
@@ -144,6 +145,8 @@ static const u32 ispif_formats_8x96[] = {
 	MEDIA_BUS_FMT_SGBRG14_1X14,
 	MEDIA_BUS_FMT_SGRBG14_1X14,
 	MEDIA_BUS_FMT_SRGGB14_1X14,
+	MEDIA_BUS_FMT_Y10_1X10,
+	MEDIA_BUS_FMT_Y10_2X8_PADHI_LE,
 };
 
 /*
@@ -692,7 +695,8 @@ static void ispif_config_pack(struct ispif_device *ispif, u32 code,
 {
 	u32 addr, val;
 
-	if (code != MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE)
+	if (code != MEDIA_BUS_FMT_SBGGR10_2X8_PADHI_LE &&
+	    code != MEDIA_BUS_FMT_Y10_2X8_PADHI_LE)
 		return;
 
 	switch (intf) {
diff --git a/drivers/media/platform/qcom/camss/camss-vfe.c b/drivers/media/platform/qcom/camss/camss-vfe.c
index 96753090e072..ed6a557de65d 100644
--- a/drivers/media/platform/qcom/camss/camss-vfe.c
+++ b/drivers/media/platform/qcom/camss/camss-vfe.c
@@ -67,6 +67,7 @@ static const struct vfe_format formats_rdi_8x16[] = {
 	{ MEDIA_BUS_FMT_SGBRG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SGRBG12_1X12, 12 },
 	{ MEDIA_BUS_FMT_SRGGB12_1X12, 12 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
 };
 
 static const struct vfe_format formats_pix_8x16[] = {
@@ -98,6 +99,8 @@ static const struct vfe_format formats_rdi_8x96[] = {
 	{ MEDIA_BUS_FMT_SGBRG14_1X14, 14 },
 	{ MEDIA_BUS_FMT_SGRBG14_1X14, 14 },
 	{ MEDIA_BUS_FMT_SRGGB14_1X14, 14 },
+	{ MEDIA_BUS_FMT_Y10_1X10, 10 },
+	{ MEDIA_BUS_FMT_Y10_2X8_PADHI_LE, 16 },
 };
 
 static const struct vfe_format formats_pix_8x96[] = {
diff --git a/drivers/media/platform/qcom/camss/camss-video.c b/drivers/media/platform/qcom/camss/camss-video.c
index 2e19bc8c4161..c9bb0d023db4 100644
--- a/drivers/media/platform/qcom/camss/camss-video.c
+++ b/drivers/media/platform/qcom/camss/camss-video.c
@@ -74,6 +74,8 @@ static const struct camss_format_info formats_rdi_8x16[] = {
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
 	{ MEDIA_BUS_FMT_SRGGB12_1X12, V4L2_PIX_FMT_SRGGB12P, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 12 } },
+	{ MEDIA_BUS_FMT_Y10_1X10, V4L2_PIX_FMT_Y10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
 };
 
 static const struct camss_format_info formats_rdi_8x96[] = {
@@ -119,6 +121,10 @@ static const struct camss_format_info formats_rdi_8x96[] = {
 	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
 	{ MEDIA_BUS_FMT_SRGGB14_1X14, V4L2_PIX_FMT_SRGGB14P, 1,
 	  { { 1, 1 } }, { { 1, 1 } }, { 14 } },
+	{ MEDIA_BUS_FMT_Y10_1X10, V4L2_PIX_FMT_Y10P, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 10 } },
+	{ MEDIA_BUS_FMT_Y10_2X8_PADHI_LE, V4L2_PIX_FMT_Y10, 1,
+	  { { 1, 1 } }, { { 1, 1 } }, { 16 } },
 };
 
 static const struct camss_format_info formats_pix_8x16[] = {
-- 
cgit v1.2.3


From e1cf4b2f1724bbbb7174d9d8d477e9320ee4a82e Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:42 -0400
Subject: media: doc: media/v4l-drivers: Update Qualcomm CAMSS driver document
 for 8x96

Update the document to describe the support of Camera Subsystem
on MSM8996/APQ8096.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 Documentation/media/v4l-drivers/qcom_camss.rst     |  93 +++++++++++-------
 .../media/v4l-drivers/qcom_camss_8x96_graph.dot    | 104 +++++++++++++++++++++
 2 files changed, 164 insertions(+), 33 deletions(-)
 create mode 100644 Documentation/media/v4l-drivers/qcom_camss_8x96_graph.dot

diff --git a/Documentation/media/v4l-drivers/qcom_camss.rst b/Documentation/media/v4l-drivers/qcom_camss.rst
index 9e66b7b5770f..f27c8df20b2b 100644
--- a/Documentation/media/v4l-drivers/qcom_camss.rst
+++ b/Documentation/media/v4l-drivers/qcom_camss.rst
@@ -7,34 +7,34 @@ Introduction
 ------------
 
 This file documents the Qualcomm Camera Subsystem driver located under
-drivers/media/platform/qcom/camss-8x16.
+drivers/media/platform/qcom/camss.
 
 The current version of the driver supports the Camera Subsystem found on
-Qualcomm MSM8916 and APQ8016 processors.
+Qualcomm MSM8916/APQ8016 and MSM8996/APQ8096 processors.
 
 The driver implements V4L2, Media controller and V4L2 subdev interfaces.
 Camera sensor using V4L2 subdev interface in the kernel is supported.
 
 The driver is implemented using as a reference the Qualcomm Camera Subsystem
-driver for Android as found in Code Aurora [#f1]_.
+driver for Android as found in Code Aurora [#f1]_ [#f2]_.
 
 
 Qualcomm Camera Subsystem hardware
 ----------------------------------
 
-The Camera Subsystem hardware found on 8x16 processors and supported by the
-driver consists of:
+The Camera Subsystem hardware found on 8x16 / 8x96 processors and supported by
+the driver consists of:
 
-- 2 CSIPHY modules. They handle the Physical layer of the CSI2 receivers.
+- 2 / 3 CSIPHY modules. They handle the Physical layer of the CSI2 receivers.
   A separate camera sensor can be connected to each of the CSIPHY module;
-- 2 CSID (CSI Decoder) modules. They handle the Protocol and Application layer
-  of the CSI2 receivers. A CSID can decode data stream from any of the CSIPHY.
-  Each CSID also contains a TG (Test Generator) block which can generate
+- 2 / 4 CSID (CSI Decoder) modules. They handle the Protocol and Application
+  layer of the CSI2 receivers. A CSID can decode data stream from any of the
+  CSIPHY. Each CSID also contains a TG (Test Generator) block which can generate
   artificial input data for test purposes;
 - ISPIF (ISP Interface) module. Handles the routing of the data streams from
   the CSIDs to the inputs of the VFE;
-- VFE (Video Front End) module. Contains a pipeline of image processing hardware
-  blocks. The VFE has different input interfaces. The PIX (Pixel) input
+- 1 / 2 VFE (Video Front End) module(s). Contain a pipeline of image processing
+  hardware blocks. The VFE has different input interfaces. The PIX (Pixel) input
   interface feeds the input data to the image processing pipeline. The image
   processing pipeline contains also a scale and crop module at the end. Three
   RDI (Raw Dump Interface) input interfaces bypass the image processing
@@ -49,18 +49,33 @@ The current version of the driver supports:
 
 - Input from camera sensor via CSIPHY;
 - Generation of test input data by the TG in CSID;
-- RDI interface of VFE - raw dump of the input data to memory.
+- RDI interface of VFE
 
-  Supported formats:
+  - Raw dump of the input data to memory.
 
-  - YUYV/UYVY/YVYU/VYUY (packed YUV 4:2:2 - V4L2_PIX_FMT_YUYV /
-    V4L2_PIX_FMT_UYVY / V4L2_PIX_FMT_YVYU / V4L2_PIX_FMT_VYUY);
-  - MIPI RAW8 (8bit Bayer RAW - V4L2_PIX_FMT_SRGGB8 /
-    V4L2_PIX_FMT_SGRBG8 / V4L2_PIX_FMT_SGBRG8 / V4L2_PIX_FMT_SBGGR8);
-  - MIPI RAW10 (10bit packed Bayer RAW - V4L2_PIX_FMT_SBGGR10P /
-    V4L2_PIX_FMT_SGBRG10P / V4L2_PIX_FMT_SGRBG10P / V4L2_PIX_FMT_SRGGB10P);
-  - MIPI RAW12 (12bit packed Bayer RAW - V4L2_PIX_FMT_SRGGB12P /
-    V4L2_PIX_FMT_SGBRG12P / V4L2_PIX_FMT_SGRBG12P / V4L2_PIX_FMT_SRGGB12P).
+    Supported formats:
+
+    - YUYV/UYVY/YVYU/VYUY (packed YUV 4:2:2 - V4L2_PIX_FMT_YUYV /
+      V4L2_PIX_FMT_UYVY / V4L2_PIX_FMT_YVYU / V4L2_PIX_FMT_VYUY);
+    - MIPI RAW8 (8bit Bayer RAW - V4L2_PIX_FMT_SRGGB8 /
+      V4L2_PIX_FMT_SGRBG8 / V4L2_PIX_FMT_SGBRG8 / V4L2_PIX_FMT_SBGGR8);
+    - MIPI RAW10 (10bit packed Bayer RAW - V4L2_PIX_FMT_SBGGR10P /
+      V4L2_PIX_FMT_SGBRG10P / V4L2_PIX_FMT_SGRBG10P / V4L2_PIX_FMT_SRGGB10P /
+      V4L2_PIX_FMT_Y10P);
+    - MIPI RAW12 (12bit packed Bayer RAW - V4L2_PIX_FMT_SRGGB12P /
+      V4L2_PIX_FMT_SGBRG12P / V4L2_PIX_FMT_SGRBG12P / V4L2_PIX_FMT_SRGGB12P).
+    - (8x96 only) MIPI RAW14 (14bit packed Bayer RAW - V4L2_PIX_FMT_SRGGB14P /
+      V4L2_PIX_FMT_SGBRG14P / V4L2_PIX_FMT_SGRBG14P / V4L2_PIX_FMT_SRGGB14P).
+
+  - (8x96 only) Format conversion of the input data.
+
+    Supported input formats:
+
+    - MIPI RAW10 (10bit packed Bayer RAW - V4L2_PIX_FMT_SBGGR10P / V4L2_PIX_FMT_Y10P).
+
+    Supported output formats:
+
+    - Plain16 RAW10 (10bit unpacked Bayer RAW - V4L2_PIX_FMT_SBGGR10 / V4L2_PIX_FMT_Y10).
 
 - PIX interface of VFE
 
@@ -75,14 +90,16 @@ The current version of the driver supports:
 
     - NV12/NV21 (two plane YUV 4:2:0 - V4L2_PIX_FMT_NV12 / V4L2_PIX_FMT_NV21);
     - NV16/NV61 (two plane YUV 4:2:2 - V4L2_PIX_FMT_NV16 / V4L2_PIX_FMT_NV61).
+    - (8x96 only) YUYV/UYVY/YVYU/VYUY (packed YUV 4:2:2 - V4L2_PIX_FMT_YUYV /
+      V4L2_PIX_FMT_UYVY / V4L2_PIX_FMT_YVYU / V4L2_PIX_FMT_VYUY).
 
   - Scaling support. Configuration of the VFE Encoder Scale module
     for downscalling with ratio up to 16x.
 
   - Cropping support. Configuration of the VFE Encoder Crop module.
 
-- Concurrent and independent usage of two data inputs - could be camera sensors
-  and/or TG.
+- Concurrent and independent usage of two (8x96: three) data inputs -
+  could be camera sensors and/or TG.
 
 
 Driver Architecture and Design
@@ -90,14 +107,14 @@ Driver Architecture and Design
 
 The driver implements the V4L2 subdev interface. With the goal to model the
 hardware links between the modules and to expose a clean, logical and usable
-interface, the driver is split into V4L2 sub-devices as follows:
+interface, the driver is split into V4L2 sub-devices as follows (8x16 / 8x96):
 
-- 2 CSIPHY sub-devices - each CSIPHY is represented by a single sub-device;
-- 2 CSID sub-devices - each CSID is represented by a single sub-device;
-- 2 ISPIF sub-devices - ISPIF is represented by a number of sub-devices equal
-  to the number of CSID sub-devices;
-- 4 VFE sub-devices - VFE is represented by a number of sub-devices equal to
-  the number of the input interfaces (3 RDI and 1 PIX).
+- 2 / 3 CSIPHY sub-devices - each CSIPHY is represented by a single sub-device;
+- 2 / 4 CSID sub-devices - each CSID is represented by a single sub-device;
+- 2 / 4 ISPIF sub-devices - ISPIF is represented by a number of sub-devices
+  equal to the number of CSID sub-devices;
+- 4 / 8 VFE sub-devices - VFE is represented by a number of sub-devices equal to
+  the number of the input interfaces (3 RDI and 1 PIX for each VFE).
 
 The considerations to split the driver in this particular way are as follows:
 
@@ -115,8 +132,8 @@ The considerations to split the driver in this particular way are as follows:
 
 Each VFE sub-device is linked to a separate video device node.
 
-The media controller pipeline graph is as follows (with connected two OV5645
-camera sensors):
+The media controller pipeline graph is as follows (with connected two / three
+OV5645 camera sensors):
 
 .. _qcom_camss_graph:
 
@@ -124,7 +141,13 @@ camera sensors):
     :alt:   qcom_camss_graph.dot
     :align: center
 
-    Media pipeline graph
+    Media pipeline graph 8x16
+
+.. kernel-figure:: qcom_camss_8x96_graph.dot
+    :alt:   qcom_camss_8x96_graph.dot
+    :align: center
+
+    Media pipeline graph 8x96
 
 
 Implementation
@@ -149,8 +172,12 @@ APQ8016 Specification:
 https://developer.qualcomm.com/download/sd410/snapdragon-410-processor-device-specification.pdf
 Referenced 2016-11-24.
 
+APQ8096 Specification:
+https://developer.qualcomm.com/download/sd820e/qualcomm-snapdragon-820e-processor-apq8096sge-device-specification.pdf
+Referenced 2018-06-22.
 
 References
 ----------
 
 .. [#f1] https://source.codeaurora.org/quic/la/kernel/msm-3.10/
+.. [#f2] https://source.codeaurora.org/quic/la/kernel/msm-3.18/
diff --git a/Documentation/media/v4l-drivers/qcom_camss_8x96_graph.dot b/Documentation/media/v4l-drivers/qcom_camss_8x96_graph.dot
new file mode 100644
index 000000000000..de34f0a7afdc
--- /dev/null
+++ b/Documentation/media/v4l-drivers/qcom_camss_8x96_graph.dot
@@ -0,0 +1,104 @@
+digraph board {
+	rankdir=TB
+	n00000001 [label="{{<port0> 0} | msm_csiphy0\n/dev/v4l-subdev0 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000001:port1 -> n0000000a:port0 [style=dashed]
+	n00000001:port1 -> n0000000d:port0 [style=dashed]
+	n00000001:port1 -> n00000010:port0 [style=dashed]
+	n00000001:port1 -> n00000013:port0 [style=dashed]
+	n00000004 [label="{{<port0> 0} | msm_csiphy1\n/dev/v4l-subdev1 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000004:port1 -> n0000000a:port0 [style=dashed]
+	n00000004:port1 -> n0000000d:port0 [style=dashed]
+	n00000004:port1 -> n00000010:port0 [style=dashed]
+	n00000004:port1 -> n00000013:port0 [style=dashed]
+	n00000007 [label="{{<port0> 0} | msm_csiphy2\n/dev/v4l-subdev2 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000007:port1 -> n0000000a:port0 [style=dashed]
+	n00000007:port1 -> n0000000d:port0 [style=dashed]
+	n00000007:port1 -> n00000010:port0 [style=dashed]
+	n00000007:port1 -> n00000013:port0 [style=dashed]
+	n0000000a [label="{{<port0> 0} | msm_csid0\n/dev/v4l-subdev3 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n0000000a:port1 -> n00000016:port0 [style=dashed]
+	n0000000a:port1 -> n00000019:port0 [style=dashed]
+	n0000000a:port1 -> n0000001c:port0 [style=dashed]
+	n0000000a:port1 -> n0000001f:port0 [style=dashed]
+	n0000000d [label="{{<port0> 0} | msm_csid1\n/dev/v4l-subdev4 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n0000000d:port1 -> n00000016:port0 [style=dashed]
+	n0000000d:port1 -> n00000019:port0 [style=dashed]
+	n0000000d:port1 -> n0000001c:port0 [style=dashed]
+	n0000000d:port1 -> n0000001f:port0 [style=dashed]
+	n00000010 [label="{{<port0> 0} | msm_csid2\n/dev/v4l-subdev5 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000010:port1 -> n00000016:port0 [style=dashed]
+	n00000010:port1 -> n00000019:port0 [style=dashed]
+	n00000010:port1 -> n0000001c:port0 [style=dashed]
+	n00000010:port1 -> n0000001f:port0 [style=dashed]
+	n00000013 [label="{{<port0> 0} | msm_csid3\n/dev/v4l-subdev6 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000013:port1 -> n00000016:port0 [style=dashed]
+	n00000013:port1 -> n00000019:port0 [style=dashed]
+	n00000013:port1 -> n0000001c:port0 [style=dashed]
+	n00000013:port1 -> n0000001f:port0 [style=dashed]
+	n00000016 [label="{{<port0> 0} | msm_ispif0\n/dev/v4l-subdev7 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000016:port1 -> n00000022:port0 [style=dashed]
+	n00000016:port1 -> n0000002b:port0 [style=dashed]
+	n00000016:port1 -> n00000034:port0 [style=dashed]
+	n00000016:port1 -> n0000003d:port0 [style=dashed]
+	n00000016:port1 -> n00000046:port0 [style=dashed]
+	n00000016:port1 -> n0000004f:port0 [style=dashed]
+	n00000016:port1 -> n00000058:port0 [style=dashed]
+	n00000016:port1 -> n00000061:port0 [style=dashed]
+	n00000019 [label="{{<port0> 0} | msm_ispif1\n/dev/v4l-subdev8 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000019:port1 -> n00000022:port0 [style=dashed]
+	n00000019:port1 -> n0000002b:port0 [style=dashed]
+	n00000019:port1 -> n00000034:port0 [style=dashed]
+	n00000019:port1 -> n0000003d:port0 [style=dashed]
+	n00000019:port1 -> n00000046:port0 [style=dashed]
+	n00000019:port1 -> n0000004f:port0 [style=dashed]
+	n00000019:port1 -> n00000058:port0 [style=dashed]
+	n00000019:port1 -> n00000061:port0 [style=dashed]
+	n0000001c [label="{{<port0> 0} | msm_ispif2\n/dev/v4l-subdev9 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n0000001c:port1 -> n00000022:port0 [style=dashed]
+	n0000001c:port1 -> n0000002b:port0 [style=dashed]
+	n0000001c:port1 -> n00000034:port0 [style=dashed]
+	n0000001c:port1 -> n0000003d:port0 [style=dashed]
+	n0000001c:port1 -> n00000046:port0 [style=dashed]
+	n0000001c:port1 -> n0000004f:port0 [style=dashed]
+	n0000001c:port1 -> n00000058:port0 [style=dashed]
+	n0000001c:port1 -> n00000061:port0 [style=dashed]
+	n0000001f [label="{{<port0> 0} | msm_ispif3\n/dev/v4l-subdev10 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n0000001f:port1 -> n00000022:port0 [style=dashed]
+	n0000001f:port1 -> n0000002b:port0 [style=dashed]
+	n0000001f:port1 -> n00000034:port0 [style=dashed]
+	n0000001f:port1 -> n0000003d:port0 [style=dashed]
+	n0000001f:port1 -> n00000046:port0 [style=dashed]
+	n0000001f:port1 -> n0000004f:port0 [style=dashed]
+	n0000001f:port1 -> n00000058:port0 [style=dashed]
+	n0000001f:port1 -> n00000061:port0 [style=dashed]
+	n00000022 [label="{{<port0> 0} | msm_vfe0_rdi0\n/dev/v4l-subdev11 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000022:port1 -> n00000025 [style=bold]
+	n00000025 [label="msm_vfe0_video0\n/dev/video0", shape=box, style=filled, fillcolor=yellow]
+	n0000002b [label="{{<port0> 0} | msm_vfe0_rdi1\n/dev/v4l-subdev12 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n0000002b:port1 -> n0000002e [style=bold]
+	n0000002e [label="msm_vfe0_video1\n/dev/video1", shape=box, style=filled, fillcolor=yellow]
+	n00000034 [label="{{<port0> 0} | msm_vfe0_rdi2\n/dev/v4l-subdev13 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000034:port1 -> n00000037 [style=bold]
+	n00000037 [label="msm_vfe0_video2\n/dev/video2", shape=box, style=filled, fillcolor=yellow]
+	n0000003d [label="{{<port0> 0} | msm_vfe0_pix\n/dev/v4l-subdev14 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n0000003d:port1 -> n00000040 [style=bold]
+	n00000040 [label="msm_vfe0_video3\n/dev/video3", shape=box, style=filled, fillcolor=yellow]
+	n00000046 [label="{{<port0> 0} | msm_vfe1_rdi0\n/dev/v4l-subdev15 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000046:port1 -> n00000049 [style=bold]
+	n00000049 [label="msm_vfe1_video0\n/dev/video4", shape=box, style=filled, fillcolor=yellow]
+	n0000004f [label="{{<port0> 0} | msm_vfe1_rdi1\n/dev/v4l-subdev16 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n0000004f:port1 -> n00000052 [style=bold]
+	n00000052 [label="msm_vfe1_video1\n/dev/video5", shape=box, style=filled, fillcolor=yellow]
+	n00000058 [label="{{<port0> 0} | msm_vfe1_rdi2\n/dev/v4l-subdev17 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000058:port1 -> n0000005b [style=bold]
+	n0000005b [label="msm_vfe1_video2\n/dev/video6", shape=box, style=filled, fillcolor=yellow]
+	n00000061 [label="{{<port0> 0} | msm_vfe1_pix\n/dev/v4l-subdev18 | {<port1> 1}}", shape=Mrecord, style=filled, fillcolor=green]
+	n00000061:port1 -> n00000064 [style=bold]
+	n00000064 [label="msm_vfe1_video3\n/dev/video7", shape=box, style=filled, fillcolor=yellow]
+	n000000e2 [label="{{} | ov5645 3-0039\n/dev/v4l-subdev19 | {<port0> 0}}", shape=Mrecord, style=filled, fillcolor=green]
+	n000000e2:port0 -> n00000004:port0 [style=bold]
+	n000000e4 [label="{{} | ov5645 3-003a\n/dev/v4l-subdev20 | {<port0> 0}}", shape=Mrecord, style=filled, fillcolor=green]
+	n000000e4:port0 -> n00000007:port0 [style=bold]
+	n000000e6 [label="{{} | ov5645 3-003b\n/dev/v4l-subdev21 | {<port0> 0}}", shape=Mrecord, style=filled, fillcolor=green]
+	n000000e6:port0 -> n00000001:port0 [style=bold]
+}
-- 
cgit v1.2.3


From 988b3ae3e0e9374b6be3b4e58524cfa6f224d8d5 Mon Sep 17 00:00:00 2001
From: Todor Tomov <todor.tomov@linaro.org>
Date: Wed, 25 Jul 2018 12:38:43 -0400
Subject: media: camss: csid: Add support for events triggered by user controls

Changing a user control value can trigger an event to other
users. Add support for that.

Signed-off-by: Todor Tomov <todor.tomov@linaro.org>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Signed-off-by: Hans Verkuil <hansverk@cisco.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/qcom/camss/camss-csid.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/qcom/camss/camss-csid.c b/drivers/media/platform/qcom/camss/camss-csid.c
index 6e141af6b6df..729b31891466 100644
--- a/drivers/media/platform/qcom/camss/camss-csid.c
+++ b/drivers/media/platform/qcom/camss/camss-csid.c
@@ -17,6 +17,7 @@
 #include <linux/regulator/consumer.h>
 #include <media/media-entity.h>
 #include <media/v4l2-device.h>
+#include <media/v4l2-event.h>
 #include <media/v4l2-subdev.h>
 
 #include "camss-csid.h"
@@ -1273,6 +1274,8 @@ static int csid_link_setup(struct media_entity *entity,
 
 static const struct v4l2_subdev_core_ops csid_core_ops = {
 	.s_power = csid_set_power,
+	.subscribe_event = v4l2_ctrl_subdev_subscribe_event,
+	.unsubscribe_event = v4l2_event_subdev_unsubscribe,
 };
 
 static const struct v4l2_subdev_video_ops csid_video_ops = {
@@ -1318,7 +1321,8 @@ int msm_csid_register_entity(struct csid_device *csid,
 
 	v4l2_subdev_init(sd, &csid_v4l2_ops);
 	sd->internal_ops = &csid_v4l2_internal_ops;
-	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE;
+	sd->flags |= V4L2_SUBDEV_FL_HAS_DEVNODE |
+		     V4L2_SUBDEV_FL_HAS_EVENTS;
 	snprintf(sd->name, ARRAY_SIZE(sd->name), "%s%d",
 		 MSM_CSID_NAME, csid->id);
 	v4l2_set_subdevdata(sd, csid);
-- 
cgit v1.2.3


From 6777996d27dd4f0a569ed9593e78db68c6b659cd Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 2 Aug 2018 14:53:10 +0200
Subject: clocksource/drivers/arm_arch_timer: Fix bogus cpu_all_mask usage

Using cpu_all_mask as target mask for clockevents is wrong as it never can
actually target not possible CPUs. Use cpu_possible_mask instead

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Sudeep Holla <sudeep.holla@arm.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
---
 drivers/clocksource/arm_arch_timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 57cb2f00fc07..d8c7f5750cdb 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -735,7 +735,7 @@ static void __arch_timer_setup(unsigned type,
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
 		clk->rating = 400;
-		clk->cpumask = cpu_all_mask;
+		clk->cpumask = cpu_possible_mask;
 		if (arch_timer_mem_use_virtual) {
 			clk->set_state_shutdown = arch_timer_shutdown_virt_mem;
 			clk->set_state_oneshot_stopped = arch_timer_shutdown_virt_mem;
-- 
cgit v1.2.3


From 234b3840d73430564a03f53973a311b7a83a95a9 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 11 Jul 2018 12:24:23 +0100
Subject: tick/broadcast-hrtimer: Use cpu_possible_mask for
 ce_broadcast_hrtimer

This is the last instance of cpu_all_mask usage in the core framework.

Replace it with cpu_possible_mask like all other instances in the
clockevent drivers. This makes it possible to add a warning in the core
clockevents_register_device on usage of cpu_all_mask from any clockevent
drivers in the future.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lkml.kernel.org/r/1531308264-24220-2-git-send-email-sudeep.holla@arm.com
---
 kernel/time/tick-broadcast-hrtimer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c
index 58045eb976c3..a59641fb88b6 100644
--- a/kernel/time/tick-broadcast-hrtimer.c
+++ b/kernel/time/tick-broadcast-hrtimer.c
@@ -90,7 +90,7 @@ static struct clock_event_device ce_broadcast_hrtimer = {
 	.max_delta_ticks	= ULONG_MAX,
 	.mult			= 1,
 	.shift			= 0,
-	.cpumask		= cpu_all_mask,
+	.cpumask		= cpu_possible_mask,
 };
 
 static enum hrtimer_restart bc_handler(struct hrtimer *t)
-- 
cgit v1.2.3


From fbfa9260085b5b578a049a90135e5c51928c5f7f Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 11 Jul 2018 12:24:24 +0100
Subject: clockevents: Warn if cpu_all_mask is used as cpumask

Using cpu_all_mask in clockevents cpumask may result in issues while
comparing multiple clockevent devices to choose the preferred one.

On one of the platforms with 2 system (i.e. non per-CPU) timers with
different ratings, having cpu_all_mask for one of the device resulted in a
boot hang due to a endless loop in clockevents_notify_released() as both
were clocksources were selected as preferred.

In order to prevent such issues in the future, warn if any clockevent
driver sets cpu_all_mask as it's cpumask and just override it to use
cpu_possible_mask. All the existing occurrences of cpu_all_mask are already
replaced with cpu_possible_mask.

Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lkml.kernel.org/r/1531308264-24220-3-git-send-email-sudeep.holla@arm.com
---
 kernel/time/clockevents.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 16c027e9cc73..8c0e4092f661 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -463,6 +463,12 @@ void clockevents_register_device(struct clock_event_device *dev)
 		dev->cpumask = cpumask_of(smp_processor_id());
 	}
 
+	if (dev->cpumask == cpu_all_mask) {
+		WARN(1, "%s cpumask == cpu_all_mask, using cpu_possible_mask instead\n",
+		     dev->name);
+		dev->cpumask = cpu_possible_mask;
+	}
+
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
 	list_add(&dev->list, &clockevent_devices);
-- 
cgit v1.2.3


From b80a2bfce85e1051056d98d04ecb2d0b55cbbc1c Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 30 Jul 2018 13:21:40 +0200
Subject: stop_machine: Reflow cpu_stop_queue_two_works()

The code flow in cpu_stop_queue_two_works() is a little arcane; fix this by
lifting the preempt_disable() to the top to create more natural nesting wrt
the spinlocks and make the wake_up_q() and preempt_enable() unconditional
at the end.

Furthermore, enable preemption in the -EDEADLK case, such that we spin-wait
with preemption enabled.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: isaacm@codeaurora.org
Cc: matt@codeblueprint.co.uk
Cc: psodagud@codeaurora.org
Cc: gregkh@linuxfoundation.org
Cc: pkondeti@codeaurora.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180730112140.GH2494@hirez.programming.kicks-ass.net
---
 kernel/stop_machine.c | 41 +++++++++++++++++++++++------------------
 1 file changed, 23 insertions(+), 18 deletions(-)

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index e190d1ef3a23..34b6652e8677 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -236,13 +236,24 @@ static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1,
 	struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2);
 	DEFINE_WAKE_Q(wakeq);
 	int err;
+
 retry:
+	/*
+	 * The waking up of stopper threads has to happen in the same
+	 * scheduling context as the queueing.  Otherwise, there is a
+	 * possibility of one of the above stoppers being woken up by another
+	 * CPU, and preempting us. This will cause us to not wake up the other
+	 * stopper forever.
+	 */
+	preempt_disable();
 	raw_spin_lock_irq(&stopper1->lock);
 	raw_spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING);
 
-	err = -ENOENT;
-	if (!stopper1->enabled || !stopper2->enabled)
+	if (!stopper1->enabled || !stopper2->enabled) {
+		err = -ENOENT;
 		goto unlock;
+	}
+
 	/*
 	 * Ensure that if we race with __stop_cpus() the stoppers won't get
 	 * queued up in reverse order leading to system deadlock.
@@ -253,36 +264,30 @@ retry:
 	 * It can be falsely true but it is safe to spin until it is cleared,
 	 * queue_stop_cpus_work() does everything under preempt_disable().
 	 */
-	err = -EDEADLK;
-	if (unlikely(stop_cpus_in_progress))
-			goto unlock;
+	if (unlikely(stop_cpus_in_progress)) {
+		err = -EDEADLK;
+		goto unlock;
+	}
 
 	err = 0;
 	__cpu_stop_queue_work(stopper1, work1, &wakeq);
 	__cpu_stop_queue_work(stopper2, work2, &wakeq);
-	/*
-	 * The waking up of stopper threads has to happen
-	 * in the same scheduling context as the queueing.
-	 * Otherwise, there is a possibility of one of the
-	 * above stoppers being woken up by another CPU,
-	 * and preempting us. This will cause us to n ot
-	 * wake up the other stopper forever.
-	 */
-	preempt_disable();
+
 unlock:
 	raw_spin_unlock(&stopper2->lock);
 	raw_spin_unlock_irq(&stopper1->lock);
 
 	if (unlikely(err == -EDEADLK)) {
+		preempt_enable();
+
 		while (stop_cpus_in_progress)
 			cpu_relax();
+
 		goto retry;
 	}
 
-	if (!err) {
-		wake_up_q(&wakeq);
-		preempt_enable();
-	}
+	wake_up_q(&wakeq);
+	preempt_enable();
 
 	return err;
 }
-- 
cgit v1.2.3


From 06bcb5168d7d49aa3ed449ff13a6d13c30afc3f0 Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@exceet.de>
Date: Thu, 2 Aug 2018 14:53:52 +0200
Subject: spi: spi-mem: Fix a typo in the documentation of struct spi_mem

Fix a typo in the @drvpriv description.

Signed-off-by: Frieder Schrempf <frieder.schrempf@exceet.de>
Acked-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi-mem.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index bb4bd15ae1f6..951a2e949d5f 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -122,7 +122,7 @@ struct spi_mem_op {
 /**
  * struct spi_mem - describes a SPI memory device
  * @spi: the underlying SPI device
- * @drvpriv: spi_mem_drviver private data
+ * @drvpriv: spi_mem_driver private data
  *
  * Extra information that describe the SPI memory device and may be needed by
  * the controller to properly handle this device should be placed here.
-- 
cgit v1.2.3


From 5d27a9c8ea9e967d00b92a76d4bb242bf7692f2b Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@exceet.de>
Date: Thu, 2 Aug 2018 14:53:53 +0200
Subject: spi: spi-mem: Extend the SPI mem interface to set a custom memory
 name

When porting (Q)SPI controller drivers from the MTD layer to the SPI
layer, the naming scheme for the memory devices changes. To be able
to keep compatibility with the old drivers naming scheme, a name
field is added to struct spi_mem and a hook is added to let controller
drivers set a custom name for the memory device.

Example for the FSL QSPI driver:

Name with the old driver: 21e0000.qspi,
or with multiple devices: 21e0000.qspi-0, 21e0000.qspi-1, ...

Name with the new driver without spi_mem_get_name: spi4.0

Suggested-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Frieder Schrempf <frieder.schrempf@exceet.de>
Reviewed-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-mem.c       | 28 ++++++++++++++++++++++++++++
 include/linux/spi/spi-mem.h | 12 ++++++++++++
 2 files changed, 40 insertions(+)

diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index 990770dfa5cf..e43842c7a31a 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -310,6 +310,24 @@ int spi_mem_exec_op(struct spi_mem *mem, const struct spi_mem_op *op)
 }
 EXPORT_SYMBOL_GPL(spi_mem_exec_op);
 
+/**
+ * spi_mem_get_name() - Return the SPI mem device name to be used by the
+ *			upper layer if necessary
+ * @mem: the SPI memory
+ *
+ * This function allows SPI mem users to retrieve the SPI mem device name.
+ * It is useful if the upper layer needs to expose a custom name for
+ * compatibility reasons.
+ *
+ * Return: a string containing the name of the memory device to be used
+ *	   by the SPI mem user
+ */
+const char *spi_mem_get_name(struct spi_mem *mem)
+{
+	return mem->name;
+}
+EXPORT_SYMBOL_GPL(spi_mem_get_name);
+
 /**
  * spi_mem_adjust_op_size() - Adjust the data size of a SPI mem operation to
  *			      match controller limitations
@@ -344,6 +362,7 @@ static inline struct spi_mem_driver *to_spi_mem_drv(struct device_driver *drv)
 static int spi_mem_probe(struct spi_device *spi)
 {
 	struct spi_mem_driver *memdrv = to_spi_mem_drv(spi->dev.driver);
+	struct spi_controller *ctlr = spi->controller;
 	struct spi_mem *mem;
 
 	mem = devm_kzalloc(&spi->dev, sizeof(*mem), GFP_KERNEL);
@@ -351,6 +370,15 @@ static int spi_mem_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	mem->spi = spi;
+
+	if (ctlr->mem_ops && ctlr->mem_ops->get_name)
+		mem->name = ctlr->mem_ops->get_name(mem);
+	else
+		mem->name = dev_name(&spi->dev);
+
+	if (IS_ERR_OR_NULL(mem->name))
+		return PTR_ERR(mem->name);
+
 	spi_set_drvdata(spi, mem);
 
 	return memdrv->probe(mem);
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 951a2e949d5f..0d64ccc4e584 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -123,6 +123,7 @@ struct spi_mem_op {
  * struct spi_mem - describes a SPI memory device
  * @spi: the underlying SPI device
  * @drvpriv: spi_mem_driver private data
+ * @name: name of the SPI memory device
  *
  * Extra information that describe the SPI memory device and may be needed by
  * the controller to properly handle this device should be placed here.
@@ -133,6 +134,7 @@ struct spi_mem_op {
 struct spi_mem {
 	struct spi_device *spi;
 	void *drvpriv;
+	char *name;
 };
 
 /**
@@ -165,6 +167,13 @@ static inline void *spi_mem_get_drvdata(struct spi_mem *mem)
  *		    limitations)
  * @supports_op: check if an operation is supported by the controller
  * @exec_op: execute a SPI memory operation
+ * @get_name: get a custom name for the SPI mem device from the controller.
+ *	      This might be needed if the controller driver has been ported
+ *	      to use the SPI mem layer and a custom name is used to keep
+ *	      mtdparts compatible.
+ *	      Note that if the implementation of this function allocates memory
+ *	      dynamically, then it should do so with devm_xxx(), as we don't
+ *	      have a ->free_name() function.
  *
  * This interface should be implemented by SPI controllers providing an
  * high-level interface to execute SPI memory operation, which is usually the
@@ -176,6 +185,7 @@ struct spi_controller_mem_ops {
 			    const struct spi_mem_op *op);
 	int (*exec_op)(struct spi_mem *mem,
 		       const struct spi_mem_op *op);
+	const char *(*get_name)(struct spi_mem *mem);
 };
 
 /**
@@ -234,6 +244,8 @@ bool spi_mem_supports_op(struct spi_mem *mem,
 int spi_mem_exec_op(struct spi_mem *mem,
 		    const struct spi_mem_op *op);
 
+const char *spi_mem_get_name(struct spi_mem *mem);
+
 int spi_mem_driver_register_with_owner(struct spi_mem_driver *drv,
 				       struct module *owner);
 
-- 
cgit v1.2.3


From b02b17f55b2e789b9747cf4dd2eaaa110439a4cc Mon Sep 17 00:00:00 2001
From: Frieder Schrempf <frieder.schrempf@exceet.de>
Date: Thu, 2 Aug 2018 14:53:54 +0200
Subject: mtd: m25p80: Call spi_mem_get_name() to let controller set a custom
 name

By calling spi_mem_get_name(), the driver of the (Q)SPI controller can
set a custom name for the memory device if necessary.
This is useful to keep mtdparts compatible when controller drivers are
ported from the MTD to the SPI layer.

Suggested-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Frieder Schrempf <frieder.schrempf@exceet.de>
Acked-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/mtd/devices/m25p80.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/mtd/devices/m25p80.c b/drivers/mtd/devices/m25p80.c
index e84563d2067f..aac488008216 100644
--- a/drivers/mtd/devices/m25p80.c
+++ b/drivers/mtd/devices/m25p80.c
@@ -202,6 +202,9 @@ static int m25p_probe(struct spi_mem *spimem)
 	if (data && data->name)
 		nor->mtd.name = data->name;
 
+	if (!nor->mtd.name)
+		nor->mtd.name = spi_mem_get_name(spimem);
+
 	/* For some (historical?) reason many platforms provide two different
 	 * names in flash_platform_data: "name" and "type". Quite often name is
 	 * set to "m25p80" and then "type" provides a real chip name.
-- 
cgit v1.2.3


From b5cdca7361d083638dc7f422fe8e1ae77860f6a6 Mon Sep 17 00:00:00 2001
From: Dirk Gouders <dirk@gouders.net>
Date: Thu, 2 Aug 2018 15:47:08 +0200
Subject: Kbuild: Makefile.modbuiltin: include auto.conf and tristate.conf
 mandatory

The files auto.conf and tristate.conf are mandatory for building
modules.builtin files, therefore include them as such.

Usually, the top-level Makefile ensures that those files exist but we
want to make sure we get noticed if they are missing for whatever
reason.

Signed-off-by: Dirk Gouders <dirk@gouders.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/Makefile.modbuiltin | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/Makefile.modbuiltin b/scripts/Makefile.modbuiltin
index 40867a41615b..a072a4267746 100644
--- a/scripts/Makefile.modbuiltin
+++ b/scripts/Makefile.modbuiltin
@@ -8,10 +8,10 @@ src := $(obj)
 PHONY := __modbuiltin
 __modbuiltin:
 
--include include/config/auto.conf
+include include/config/auto.conf
 # tristate.conf sets tristate variables to uppercase 'Y' or 'M'
 # That way, we get the list of built-in modules in obj-Y
--include include/config/tristate.conf
+include include/config/tristate.conf
 
 include scripts/Kbuild.include
 
-- 
cgit v1.2.3


From c480bcf97b186a67ea6f0f6cab70ba430bcd5613 Mon Sep 17 00:00:00 2001
From: "Dennis Zhou (Facebook)" <dennisszhou@gmail.com>
Date: Wed, 1 Aug 2018 23:15:41 -0700
Subject: block: make iolatency avg_lat exponentially decay

Currently, avg_lat is calculated by accumulating the mean of every
window in a long running cumulative average. As time goes on, the metric
becomes less and less useful due to the accumulated history.

This patch reuses the same calculation done in load averages to make the
avg_lat metric more lively. Unlike load averages, the avg only advances
when a window elapses (due to an io). Idle periods extend the most
recent window. Bucketing is used to limit the history of avg_lat by
binding it to the window size. So, the window range for 1/exp (decay
rate) is [1 min, 2.5 min) when windows elapse immediately.

The current sample window size is exposed in the debug info to enable
calculation of the window range.

Signed-off-by: Dennis Zhou <dennisszhou@gmail.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/admin-guide/cgroup-v2.rst | 21 +++++++-----
 block/blk-iolatency.c                   | 60 ++++++++++++++++++++++++---------
 2 files changed, 57 insertions(+), 24 deletions(-)

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 3afe10fa82bc..1746131bc9cb 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1474,11 +1474,9 @@ So the ideal way to configure this is to set io.latency in groups A, B, and C.
 Generally you do not want to set a value lower than the latency your device
 supports.  Experiment to find the value that works best for your workload.
 Start at higher than the expected latency for your device and watch the
-total_lat_avg value in io.stat for your workload group to get an idea of the
-latency you see during normal operation.  Use this value as a basis for your
-real setting, setting at 10-15% higher than the value in io.stat.
-Experimentation is key here because total_lat_avg is a running total, so is the
-"statistics" portion of "lies, damned lies, and statistics."
+avg_lat value in io.stat for your workload group to get an idea of the
+latency you see during normal operation.  Use the avg_lat value as a basis for
+your real setting, setting at 10-15% higher than the value in io.stat.
 
 How IO Latency Throttling Works
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -1522,10 +1520,15 @@ IO Latency Interface Files
 		This is the current queue depth for the group.
 
 	  avg_lat
-		The running average IO latency for this group in microseconds.
-		Running average is generally flawed, but will give an
-		administrator a general idea of the overall latency they can
-		expect for their workload on the given disk.
+		This is an exponential moving average with a decay rate of 1/exp
+		bound by the sampling interval.  The decay rate interval can be
+		calculated by multiplying the win value in io.stat by the
+		corresponding number of samples based on the win value.
+
+	  win
+		The sampling window size in milliseconds.  This is the minimum
+		duration of time between evaluation events.  Windows only elapse
+		with IO activity.  Idle periods extend the most recent window.
 
 PID
 ---
diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c
index b0dc4fc64b3e..19923f8a029d 100644
--- a/block/blk-iolatency.c
+++ b/block/blk-iolatency.c
@@ -69,6 +69,7 @@
 #include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/memcontrol.h>
+#include <linux/sched/loadavg.h>
 #include <linux/sched/signal.h>
 #include <trace/events/block.h>
 #include "blk-rq-qos.h"
@@ -126,8 +127,7 @@ struct iolatency_grp {
 	u64 cur_win_nsec;
 
 	/* total running average of our io latency. */
-	u64 total_lat_avg;
-	u64 total_lat_nr;
+	u64 lat_avg;
 
 	/* Our current number of IO's for the last summation. */
 	u64 nr_samples;
@@ -135,6 +135,28 @@ struct iolatency_grp {
 	struct child_latency_info child_lat;
 };
 
+#define BLKIOLATENCY_MIN_WIN_SIZE (100 * NSEC_PER_MSEC)
+#define BLKIOLATENCY_MAX_WIN_SIZE NSEC_PER_SEC
+/*
+ * These are the constants used to fake the fixed-point moving average
+ * calculation just like load average.  The call to CALC_LOAD folds
+ * (FIXED_1 (2048) - exp_factor) * new_sample into lat_avg.  The sampling
+ * window size is bucketed to try to approximately calculate average
+ * latency such that 1/exp (decay rate) is [1 min, 2.5 min) when windows
+ * elapse immediately.  Note, windows only elapse with IO activity.  Idle
+ * periods extend the most recent window.
+ */
+#define BLKIOLATENCY_NR_EXP_FACTORS 5
+#define BLKIOLATENCY_EXP_BUCKET_SIZE (BLKIOLATENCY_MAX_WIN_SIZE / \
+				      (BLKIOLATENCY_NR_EXP_FACTORS - 1))
+static const u64 iolatency_exp_factors[BLKIOLATENCY_NR_EXP_FACTORS] = {
+	2045, // exp(1/600) - 600 samples
+	2039, // exp(1/240) - 240 samples
+	2031, // exp(1/120) - 120 samples
+	2023, // exp(1/80)  - 80 samples
+	2014, // exp(1/60)  - 60 samples
+};
+
 static inline struct iolatency_grp *pd_to_lat(struct blkg_policy_data *pd)
 {
 	return pd ? container_of(pd, struct iolatency_grp, pd) : NULL;
@@ -462,7 +484,7 @@ static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
 	struct child_latency_info *lat_info;
 	struct blk_rq_stat stat;
 	unsigned long flags;
-	int cpu;
+	int cpu, exp_idx;
 
 	blk_rq_stat_init(&stat);
 	preempt_disable();
@@ -480,11 +502,17 @@ static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
 
 	lat_info = &parent->child_lat;
 
-	iolat->total_lat_avg =
-		div64_u64((iolat->total_lat_avg * iolat->total_lat_nr) +
-			  stat.mean, iolat->total_lat_nr + 1);
-
-	iolat->total_lat_nr++;
+	/*
+	 * CALC_LOAD takes in a number stored in fixed point representation.
+	 * Because we are using this for IO time in ns, the values stored
+	 * are significantly larger than the FIXED_1 denominator (2048).
+	 * Therefore, rounding errors in the calculation are negligible and
+	 * can be ignored.
+	 */
+	exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1,
+			div64_u64(iolat->cur_win_nsec,
+				  BLKIOLATENCY_EXP_BUCKET_SIZE));
+	CALC_LOAD(iolat->lat_avg, iolatency_exp_factors[exp_idx], stat.mean);
 
 	/* Everything is ok and we don't need to adjust the scale. */
 	if (stat.mean <= iolat->min_lat_nsec &&
@@ -700,8 +728,9 @@ static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
 	u64 oldval = iolat->min_lat_nsec;
 
 	iolat->min_lat_nsec = val;
-	iolat->cur_win_nsec = max_t(u64, val << 4, 100 * NSEC_PER_MSEC);
-	iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec, NSEC_PER_SEC);
+	iolat->cur_win_nsec = max_t(u64, val << 4, BLKIOLATENCY_MIN_WIN_SIZE);
+	iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec,
+				    BLKIOLATENCY_MAX_WIN_SIZE);
 
 	if (!oldval && val)
 		atomic_inc(&blkiolat->enabled);
@@ -810,14 +839,15 @@ static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
 				size_t size)
 {
 	struct iolatency_grp *iolat = pd_to_lat(pd);
-	unsigned long long avg_lat = div64_u64(iolat->total_lat_avg, NSEC_PER_USEC);
+	unsigned long long avg_lat = div64_u64(iolat->lat_avg, NSEC_PER_USEC);
+	unsigned long long cur_win = div64_u64(iolat->cur_win_nsec, NSEC_PER_MSEC);
 
 	if (iolat->rq_depth.max_depth == UINT_MAX)
-		return scnprintf(buf, size, " depth=max avg_lat=%llu",
-				 avg_lat);
+		return scnprintf(buf, size, " depth=max avg_lat=%llu win=%llu",
+				 avg_lat, cur_win);
 
-	return scnprintf(buf, size, " depth=%u avg_lat=%llu",
-			 iolat->rq_depth.max_depth, avg_lat);
+	return scnprintf(buf, size, " depth=%u avg_lat=%llu win=%llu",
+			 iolat->rq_depth.max_depth, avg_lat, cur_win);
 }
 
 
-- 
cgit v1.2.3


From 99972f171bba19243999310154b7442198f0ab30 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 17:30:20 -0500
Subject: aoe: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114722 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/aoe/aoecmd.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 096882e54095..136dc507d020 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -1137,6 +1137,7 @@ noskb:		if (buf)
 			break;
 		}
 		bvcpy(skb, f->buf->bio, f->iter, n);
+		/* fall through */
 	case ATA_CMD_PIO_WRITE:
 	case ATA_CMD_PIO_WRITE_EXT:
 		spin_lock_irq(&d->lock);
-- 
cgit v1.2.3


From 1eb576881ff884dd6d10272b96cc336d156492c2 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Thu, 2 Aug 2018 16:03:36 +0100
Subject: ASoC: apq8096: remove auto rebinding

Remove auto rebinding support, as component framework can deadlock
in few usecases if we are trying to add new/remove component within
a bind/unbind callbacks.

Card rebinding is ASoC core feature so all the previous component
framework stuff in q6dsp remains removed.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/apq8096.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index 1e4a90d59228..6ee7e66cbaaa 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -48,7 +48,6 @@ static int apq8096_platform_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	card->dev = dev;
-	card->auto_bind = true;
 	dev_set_drvdata(dev, card);
 	ret = qcom_snd_parse_of(card);
 	if (ret) {
@@ -74,7 +73,6 @@ static int apq8096_platform_remove(struct platform_device *pdev)
 {
 	struct snd_soc_card *card = dev_get_drvdata(&pdev->dev);
 
-	card->auto_bind = false;
 	snd_soc_unregister_card(card);
 	kfree(card->dai_link);
 	kfree(card);
-- 
cgit v1.2.3


From 62121debfb31a8700e387bd2987779b3a98bc520 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Thu, 2 Aug 2018 16:03:37 +0100
Subject: ASoC: smd845: remove auto rebinding

Remove auto rebinding support, as component framework can deadlock
in few usecases if we are trying to add new/remove component within
a bind/unbind callbacks.

Card rebinding is ASoC core feature so all the previous component
framework stuff in q6dsp remains removed.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/sdm845.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index bf4ec4646906..be0cb1122036 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -226,7 +226,6 @@ static int sdm845_snd_platform_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	card->dev = dev;
-	card->auto_bind = true;
 	dev_set_drvdata(dev, card);
 	ret = qcom_snd_parse_of(card);
 	if (ret) {
@@ -258,7 +257,6 @@ static int sdm845_snd_platform_remove(struct platform_device *pdev)
 	struct snd_soc_card *card = dev_get_drvdata(&pdev->dev);
 	struct sdm845_snd_data *data = snd_soc_card_get_drvdata(card);
 
-	card->auto_bind = false;
 	snd_soc_unregister_card(card);
 	kfree(card->dai_link);
 	kfree(data);
-- 
cgit v1.2.3


From 611cbc8799b672f41b6ba7afed758ad9efb959a7 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Thu, 2 Aug 2018 16:03:38 +0100
Subject: ASoC: core: remove support for card rebind using component framework

DRM based audio components get registered inside the component framework
bind callback. However component framework has a big mutex lock taken for
every call to component_add, component_del and bind, unbind callbacks.

This can lead to deadlock situation if we are trying to add new/remove
component within a bind/unbind callbacks. Which is what was happening
with bcm2837 rpi 3.

Revert this change till we sort out the mutex issue.

Reported-by: Guillaume Tucker <guillaume.tucker@collabora.com>
Reported-by: Stefan Wahren <stefan.wahren@i2se.com>
Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h  |  7 ------
 sound/soc/soc-core.c | 62 ----------------------------------------------------
 2 files changed, 69 deletions(-)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index ace474e8649e..41cec42fb456 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -17,7 +17,6 @@
 #include <linux/workqueue.h>
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
-#include <linux/component.h>
 #include <linux/regmap.h>
 #include <linux/log2.h>
 #include <sound/core.h>
@@ -1091,12 +1090,6 @@ struct snd_soc_card {
 
 	struct work_struct deferred_resume_work;
 
-	/* component framework related */
-	bool components_added;
-	/* set in machine driver to enable/disable auto re-binding */
-	bool auto_bind;
-	struct component_match *match;
-
 	/* lists of probed devices belonging to this card */
 	struct list_head component_dev_list;
 
diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 81b27923303d..82eb3868be67 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -279,28 +279,11 @@ static inline void snd_soc_debugfs_exit(void)
 
 #endif
 
-static int snd_soc_card_comp_compare(struct device *dev, void *data)
-{
-	struct snd_soc_component *component;
-
-	lockdep_assert_held(&client_mutex);
-	list_for_each_entry(component, &component_list, list) {
-		if (dev == component->dev) {
-			if (!strcmp(component->name, data))
-				return 1;
-			break;
-		}
-	}
-
-	return 0;
-}
-
 static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd,
 			      struct snd_soc_component *component)
 {
 	struct snd_soc_rtdcom_list *rtdcom;
 	struct snd_soc_rtdcom_list *new_rtdcom;
-	char *cname;
 
 	for_each_rtdcom(rtd, rtdcom) {
 		/* already connected */
@@ -317,13 +300,6 @@ static int snd_soc_rtdcom_add(struct snd_soc_pcm_runtime *rtd,
 
 	list_add_tail(&new_rtdcom->list, &rtd->component_list);
 
-	if (rtd->card->auto_bind && !rtd->card->components_added) {
-		cname = devm_kasprintf(rtd->card->dev, GFP_KERNEL,
-				       "%s", component->name);
-		component_match_add(rtd->card->dev, &rtd->card->match,
-				    snd_soc_card_comp_compare, cname);
-	}
-
 	return 0;
 }
 
@@ -859,25 +835,6 @@ static bool soc_is_dai_link_bound(struct snd_soc_card *card,
 	return false;
 }
 
-static int snd_soc_card_comp_bind(struct device *dev)
-{
-	struct snd_soc_card *card = dev_get_drvdata(dev);
-
-	if (card->instantiated)
-		return 0;
-
-	return snd_soc_register_card(card);
-}
-
-static void snd_soc_card_comp_unbind(struct device *dev)
-{
-}
-
-static const struct component_master_ops snd_soc_card_comp_ops = {
-	.bind = snd_soc_card_comp_bind,
-	.unbind = snd_soc_card_comp_unbind,
-};
-
 static int soc_bind_dai_link(struct snd_soc_card *card,
 	struct snd_soc_dai_link *dai_link)
 {
@@ -2169,12 +2126,6 @@ static int snd_soc_instantiate_card(struct snd_soc_card *card)
 
 	card->instantiated = 1;
 	snd_soc_dapm_sync(&card->dapm);
-	if (card->auto_bind && !card->components_added) {
-		component_master_add_with_match(card->dev,
-						&snd_soc_card_comp_ops,
-						card->match);
-		card->components_added = true;
-	}
 	mutex_unlock(&card->mutex);
 	mutex_unlock(&client_mutex);
 
@@ -2820,9 +2771,6 @@ int snd_soc_unregister_card(struct snd_soc_card *card)
 		dev_dbg(card->dev, "ASoC: Unregistered card '%s'\n", card->name);
 	}
 
-	if (!card->auto_bind && card->components_added)
-		component_master_del(card->dev, &snd_soc_card_comp_ops);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(snd_soc_unregister_card);
@@ -3235,17 +3183,8 @@ int snd_soc_add_component(struct device *dev,
 
 	snd_soc_component_add(component);
 
-	ret = component_add(dev, NULL);
-	if (ret < 0) {
-		dev_err(dev, "ASoC: Failed to add Component: %d\n", ret);
-		goto err_comp;
-	}
-
 	return 0;
 
-err_comp:
-	soc_remove_component(component);
-	snd_soc_unregister_dais(component);
 err_cleanup:
 	snd_soc_component_cleanup(component);
 err_free:
@@ -3293,7 +3232,6 @@ static int __snd_soc_unregister_component(struct device *dev)
 	mutex_unlock(&client_mutex);
 
 	if (found) {
-		component_del(dev, NULL);
 		snd_soc_component_cleanup(component);
 	}
 
-- 
cgit v1.2.3


From b233f127042dba991229e3882c6217c80492f6ef Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 30 Jul 2018 20:02:19 +0800
Subject: block: really disable runtime-pm for blk-mq

Runtime PM isn't ready for blk-mq yet, and commit 765e40b675a9 ("block:
disable runtime-pm for blk-mq") tried to disable it. Unfortunately,
it can't take effect in that way since user space still can switch
it on via 'echo auto > /sys/block/sdN/device/power/control'.

This patch disables runtime-pm for blk-mq really by pm_runtime_disable()
and fixes all kinds of PM related kernel crash.

Cc: Tomas Janousek <tomi@nomi.cz>
Cc: Przemek Socha <soprwa@gmail.com>
Cc: Alan Stern <stern@rowland.harvard.edu>
Cc: <stable@vger.kernel.org>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Tested-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 23cd1b7770e7..f9ad73d8573c 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -3770,9 +3770,11 @@ EXPORT_SYMBOL(blk_finish_plug);
  */
 void blk_pm_runtime_init(struct request_queue *q, struct device *dev)
 {
-	/* not support for RQF_PM and ->rpm_status in blk-mq yet */
-	if (q->mq_ops)
+	/* Don't enable runtime PM for blk-mq until it is ready */
+	if (q->mq_ops) {
+		pm_runtime_disable(dev);
 		return;
+	}
 
 	q->dev = dev;
 	q->rpm_status = RPM_ACTIVE;
-- 
cgit v1.2.3


From 42019fc50dfadb219f9e6ddf4c354f3837057d80 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 9 Jul 2018 10:13:36 +0100
Subject: ARM: vfp: use __copy_from_user() when restoring VFP state

__get_user_error() is used as a fast accessor to make copying structure
members in the signal handling path as efficient as possible.  However,
with software PAN and the recent Spectre variant 1, the efficiency is
reduced as these are no longer fast accessors.

In the case of software PAN, it has to switch the domain register around
each access, and with Spectre variant 1, it would have to repeat the
access_ok() check for each access.

Use __copy_from_user() rather than __get_user_err() for individual
members when restoring VFP state.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/include/asm/thread_info.h |  4 ++--
 arch/arm/kernel/signal.c           | 20 ++++++++------------
 arch/arm/vfp/vfpmodule.c           | 17 +++++++----------
 3 files changed, 17 insertions(+), 24 deletions(-)

diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index e71cc35de163..9b37b6ab27fe 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -123,8 +123,8 @@ struct user_vfp_exc;
 
 extern int vfp_preserve_user_clear_hwstate(struct user_vfp __user *,
 					   struct user_vfp_exc __user *);
-extern int vfp_restore_user_hwstate(struct user_vfp __user *,
-				    struct user_vfp_exc __user *);
+extern int vfp_restore_user_hwstate(struct user_vfp *,
+				    struct user_vfp_exc *);
 #endif
 
 /*
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index 0ae74207e43e..db62c51250ad 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -150,22 +150,18 @@ static int preserve_vfp_context(struct vfp_sigframe __user *frame)
 
 static int restore_vfp_context(char __user **auxp)
 {
-	struct vfp_sigframe __user *frame =
-		(struct vfp_sigframe __user *)*auxp;
-	unsigned long magic;
-	unsigned long size;
-	int err = 0;
-
-	__get_user_error(magic, &frame->magic, err);
-	__get_user_error(size, &frame->size, err);
+	struct vfp_sigframe frame;
+	int err;
 
+	err = __copy_from_user(&frame, *auxp, sizeof(frame));
 	if (err)
-		return -EFAULT;
-	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
+		return err;
+
+	if (frame.magic != VFP_MAGIC || frame.size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	*auxp += size;
-	return vfp_restore_user_hwstate(&frame->ufp, &frame->ufp_exc);
+	*auxp += sizeof(frame);
+	return vfp_restore_user_hwstate(&frame.ufp, &frame.ufp_exc);
 }
 
 #endif
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 4c375e11ae95..859d50ea17d3 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -597,13 +597,11 @@ int vfp_preserve_user_clear_hwstate(struct user_vfp __user *ufp,
 }
 
 /* Sanitise and restore the current VFP state from the provided structures. */
-int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
-			     struct user_vfp_exc __user *ufp_exc)
+int vfp_restore_user_hwstate(struct user_vfp *ufp, struct user_vfp_exc *ufp_exc)
 {
 	struct thread_info *thread = current_thread_info();
 	struct vfp_hard_struct *hwstate = &thread->vfpstate.hard;
 	unsigned long fpexc;
-	int err = 0;
 
 	/* Disable VFP to avoid corrupting the new thread state. */
 	vfp_flush_hwstate(thread);
@@ -612,17 +610,16 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
 	 * Copy the floating point registers. There can be unused
 	 * registers see asm/hwcap.h for details.
 	 */
-	err |= __copy_from_user(&hwstate->fpregs, &ufp->fpregs,
-				sizeof(hwstate->fpregs));
+	memcpy(&hwstate->fpregs, &ufp->fpregs, sizeof(hwstate->fpregs));
 	/*
 	 * Copy the status and control register.
 	 */
-	__get_user_error(hwstate->fpscr, &ufp->fpscr, err);
+	hwstate->fpscr = ufp->fpscr;
 
 	/*
 	 * Sanitise and restore the exception registers.
 	 */
-	__get_user_error(fpexc, &ufp_exc->fpexc, err);
+	fpexc = ufp_exc->fpexc;
 
 	/* Ensure the VFP is enabled. */
 	fpexc |= FPEXC_EN;
@@ -631,10 +628,10 @@ int vfp_restore_user_hwstate(struct user_vfp __user *ufp,
 	fpexc &= ~(FPEXC_EX | FPEXC_FP2V);
 	hwstate->fpexc = fpexc;
 
-	__get_user_error(hwstate->fpinst, &ufp_exc->fpinst, err);
-	__get_user_error(hwstate->fpinst2, &ufp_exc->fpinst2, err);
+	hwstate->fpinst = ufp_exc->fpinst;
+	hwstate->fpinst2 = ufp_exc->fpinst2;
 
-	return err ? -EFAULT : 0;
+	return 0;
 }
 
 /*
-- 
cgit v1.2.3


From 8c8484a1c18e3231648f5ba7cc5ffb7fd70b3ca4 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 9 Jul 2018 10:20:06 +0100
Subject: ARM: oabi-compat: copy semops using __copy_from_user()

__get_user_error() is used as a fast accessor to make copying structure
members as efficient as possible.  However, with software PAN and the
recent Spectre variant 1, the efficiency is reduced as these are no
longer fast accessors.

In the case of software PAN, it has to switch the domain register around
each access, and with Spectre variant 1, it would have to repeat the
access_ok() check for each access.

Rather than using __get_user_error() to copy each semops element member,
copy each semops element in full using __copy_from_user().

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/kernel/sys_oabi-compat.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c
index b9786f491873..4abe4909417f 100644
--- a/arch/arm/kernel/sys_oabi-compat.c
+++ b/arch/arm/kernel/sys_oabi-compat.c
@@ -329,9 +329,11 @@ asmlinkage long sys_oabi_semtimedop(int semid,
 		return -ENOMEM;
 	err = 0;
 	for (i = 0; i < nsops; i++) {
-		__get_user_error(sops[i].sem_num, &tsops->sem_num, err);
-		__get_user_error(sops[i].sem_op,  &tsops->sem_op,  err);
-		__get_user_error(sops[i].sem_flg, &tsops->sem_flg, err);
+		struct oabi_sembuf osb;
+		err |= __copy_from_user(&osb, tsops, sizeof(osb));
+		sops[i].sem_num = osb.sem_num;
+		sops[i].sem_op = osb.sem_op;
+		sops[i].sem_flg = osb.sem_flg;
 		tsops++;
 	}
 	if (timeout) {
-- 
cgit v1.2.3


From d09fbb327d670737ab40fd8bbb0765ae06b8b739 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 9 Jul 2018 15:22:45 +0100
Subject: ARM: use __inttype() in get_user()

Borrow the x86 implementation of __inttype() to use in get_user() to
select an integer type suitable to temporarily hold the result value.
This is necessary to avoid propagating the volatile nature of the
result argument, which can cause the following warning:

lib/iov_iter.c:413:5: warning: optimization may eliminate reads and/or writes to register variables [-Wvolatile-register-var]

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/include/asm/uaccess.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 0bf2347495f1..29fa6f3ea25a 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -84,6 +84,13 @@ static inline void set_fs(mm_segment_t fs)
 		: "cc"); \
 	flag; })
 
+/*
+ * This is a type: either unsigned long, if the argument fits into
+ * that type, or otherwise unsigned long long.
+ */
+#define __inttype(x) \
+	__typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
+
 /*
  * Single-value transfer routines.  They automatically use the right
  * size if we just have the right pointer type.  Note that the functions
@@ -153,7 +160,7 @@ extern int __get_user_64t_4(void *);
 	({								\
 		unsigned long __limit = current_thread_info()->addr_limit - 1; \
 		register const typeof(*(p)) __user *__p asm("r0") = (p);\
-		register typeof(x) __r2 asm("r2");			\
+		register __inttype(x) __r2 asm("r2");			\
 		register unsigned long __l asm("r1") = __limit;		\
 		register int __e asm("r0");				\
 		unsigned int __ua_flags = uaccess_save_and_enable();	\
-- 
cgit v1.2.3


From b1cd0a14806321721aae45f5446ed83a3647c914 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 9 Jul 2018 10:28:12 +0100
Subject: ARM: spectre-v1: use get_user() for __get_user()

Fixing __get_user() for spectre variant 1 is not sane: we would have to
add address space bounds checking in order to validate that the location
should be accessed, and then zero the address if found to be invalid.

Since __get_user() is supposed to avoid the bounds check, and this is
exactly what get_user() does, there's no point having two different
implementations that are doing the same thing.  So, when the Spectre
workarounds are required, make __get_user() an alias of get_user().

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/include/asm/uaccess.h | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 29fa6f3ea25a..4140be431087 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -250,6 +250,16 @@ static inline void set_fs(mm_segment_t fs)
 #define user_addr_max() \
 	(uaccess_kernel() ? ~0UL : get_fs())
 
+#ifdef CONFIG_CPU_SPECTRE
+/*
+ * When mitigating Spectre variant 1, it is not worth fixing the non-
+ * verifying accessors, because we need to add verification of the
+ * address space there.  Force these to use the standard get_user()
+ * version instead.
+ */
+#define __get_user(x, ptr) get_user(x, ptr)
+#else
+
 /*
  * The "__xxx" versions of the user access functions do not verify the
  * address space - it must have been done previously with a separate
@@ -266,12 +276,6 @@ static inline void set_fs(mm_segment_t fs)
 	__gu_err;							\
 })
 
-#define __get_user_error(x, ptr, err)					\
-({									\
-	__get_user_err((x), (ptr), err);				\
-	(void) 0;							\
-})
-
 #define __get_user_err(x, ptr, err)					\
 do {									\
 	unsigned long __gu_addr = (unsigned long)(ptr);			\
@@ -331,6 +335,7 @@ do {									\
 
 #define __get_user_asm_word(x, addr, err)			\
 	__get_user_asm(x, addr, err, ldr)
+#endif
 
 
 #define __put_user_switch(x, ptr, __err, __fn)				\
-- 
cgit v1.2.3


From a3c0f84765bb429ba0fd23de1c57b5e1591c9389 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Mon, 14 May 2018 09:40:24 +0100
Subject: ARM: spectre-v1: mitigate user accesses

Spectre variant 1 attacks are about this sequence of pseudo-code:

	index = load(user-manipulated pointer);
	access(base + index * stride);

In order for the cache side-channel to work, the access() must me made
to memory which userspace can detect whether cache lines have been
loaded.  On 32-bit ARM, this must be either user accessible memory, or
a kernel mapping of that same user accessible memory.

The problem occurs when the load() speculatively loads privileged data,
and the subsequent access() is made to user accessible memory.

Any load() which makes use of a user-maniplated pointer is a potential
problem if the data it has loaded is used in a subsequent access.  This
also applies for the access() if the data loaded by that access is used
by a subsequent access.

Harden the get_user() accessors against Spectre attacks by forcing out
of bounds addresses to a NULL pointer.  This prevents get_user() being
used as the load() step above.  As a side effect, put_user() will also
be affected even though it isn't implicated.

Also harden copy_from_user() by redoing the bounds check within the
arm_copy_from_user() code, and NULLing the pointer if out of bounds.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 arch/arm/include/asm/assembler.h | 4 ++++
 arch/arm/lib/copy_from_user.S    | 9 +++++++++
 2 files changed, 13 insertions(+)

diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index ef1386b1af9b..f0515f60cff5 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -460,6 +460,10 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	adds	\tmp, \addr, #\size - 1
 	sbcccs	\tmp, \tmp, \limit
 	bcs	\bad
+#ifdef CONFIG_CPU_SPECTRE
+	movcs	\addr, #0
+	csdb
+#endif
 #endif
 	.endm
 
diff --git a/arch/arm/lib/copy_from_user.S b/arch/arm/lib/copy_from_user.S
index 7a4b06049001..a826df3d3814 100644
--- a/arch/arm/lib/copy_from_user.S
+++ b/arch/arm/lib/copy_from_user.S
@@ -90,6 +90,15 @@
 	.text
 
 ENTRY(arm_copy_from_user)
+#ifdef CONFIG_CPU_SPECTRE
+	get_thread_info r3
+	ldr	r3, [r3, #TI_ADDR_LIMIT]
+	adds	ip, r1, r2	@ ip=addr+size
+	sub	r3, r3, #1	@ addr_limit - 1
+	cmpcc	ip, r3		@ if (addr+size > addr_limit - 1)
+	movcs	r1, #0		@ addr = NULL
+	csdb
+#endif
 
 #include "copy_template.S"
 
-- 
cgit v1.2.3


From 770b26de1eca97142218de3b2829a790f2ff8803 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Thu, 2 Aug 2018 09:13:33 +0100
Subject: rxrpc: Remove set but not used variable 'nowj'

Fixes gcc '-Wunused-but-set-variable' warning:

net/rxrpc/proc.c: In function 'rxrpc_call_seq_show':
net/rxrpc/proc.c:66:29: warning:
 variable 'nowj' set but not used [-Wunused-but-set-variable]
  unsigned long timeout = 0, nowj;
                             ^

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/proc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c
index 163d05df339d..9805e3b85c36 100644
--- a/net/rxrpc/proc.c
+++ b/net/rxrpc/proc.c
@@ -63,7 +63,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 	struct rxrpc_peer *peer;
 	struct rxrpc_call *call;
 	struct rxrpc_net *rxnet = rxrpc_net(seq_file_net(seq));
-	unsigned long timeout = 0, nowj;
+	unsigned long timeout = 0;
 	rxrpc_seq_t tx_hard_ack, rx_hard_ack;
 	char lbuff[50], rbuff[50];
 
@@ -97,7 +97,6 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v)
 
 	if (call->state != RXRPC_CALL_SERVER_PREALLOC) {
 		timeout = READ_ONCE(call->expect_rx_by);
-		nowj = jiffies;
 		timeout -= jiffies;
 	}
 
-- 
cgit v1.2.3


From ca75e2fc7708c516e8e840eca29b326aae3819dd Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Thu, 2 Aug 2018 09:23:30 -0700
Subject: MIPS: generic: Remove input symbols from defconfig

generic_defconfig explicitly disables CONFIG_INPUT_MOUSEDEV,
CONFIG_INPUT_KEYBOARD & CONFIG_INPUT_MOUSE which results in warnings
when merging board config fragments if any of them require these
options. This is the case for the ranchu board, which means we've had
the following warning when configuring for generic platform targets
since commit f2d0b0d5c171 ("MIPS: ranchu: Add Ranchu as a new
generic-based board"):

  $ make ARCH=mips 32r2el_defconfig
  Using ./arch/mips/configs/generic_defconfig as base
  Merging arch/mips/configs/generic/32r2.config
  Merging arch/mips/configs/generic/el.config
  Merging ./arch/mips/configs/generic/board-sead-3.config
  Merging ./arch/mips/configs/generic/board-ranchu.config
  Value of CONFIG_INPUT_KEYBOARD is redefined by fragment ./arch/mips/configs/generic/board-ranchu.config:
  Previous value: # CONFIG_INPUT_KEYBOARD is not set
  New value: CONFIG_INPUT_KEYBOARD=y

  Merging ./arch/mips/configs/generic/board-ni169445.config
  Merging ./arch/mips/configs/generic/board-boston.config
  Merging ./arch/mips/configs/generic/board-ocelot.config
  Merging ./arch/mips/configs/generic/board-xilfpga.config
  scripts/kconfig/conf  --olddefconfig Kconfig
  #
  # configuration written to .config
  #

Resolve this by removing mention of the CONFIG_INPUT_* Kconfig symbols
from generic_defconfig, allowing them to take their default values &
allowing board config fragments to enable them without warnings.

This may be problematic if CONFIG_ARCH_MIGHT_HAVE_PC_SERIO is ever
enabled for CONFIG_MIPS_GENERIC=y configurations, but for now that isn't
the case so we can worry about that if & when it happens.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20109/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/configs/generic_defconfig | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/arch/mips/configs/generic_defconfig b/arch/mips/configs/generic_defconfig
index 26b1cd5ffbf5..684c9dcba126 100644
--- a/arch/mips/configs/generic_defconfig
+++ b/arch/mips/configs/generic_defconfig
@@ -43,9 +43,6 @@ CONFIG_NETFILTER=y
 CONFIG_DEVTMPFS=y
 CONFIG_DEVTMPFS_MOUNT=y
 CONFIG_SCSI=y
-# CONFIG_INPUT_MOUSEDEV is not set
-# CONFIG_INPUT_KEYBOARD is not set
-# CONFIG_INPUT_MOUSE is not set
 # CONFIG_SERIO is not set
 CONFIG_HW_RANDOM=y
 # CONFIG_HWMON is not set
-- 
cgit v1.2.3


From 453e9dc48be466afa2adc25d072aa4c5b8774f8d Mon Sep 17 00:00:00 2001
From: Stefan Agner <stefan@agner.ch>
Date: Thu, 2 Aug 2018 10:42:50 +0200
Subject: net: fec: check DMA addressing limitations

Check DMA addressing limitations as suggested by the DMA API
how-to. This does not fix a particular issue seen but is
considered good style.

Signed-off-by: Stefan Agner <stefan@agner.ch>
Acked-by: Fugang Duan <fugang.duan@nxp.com>
Reviewed-by: Robin Murphy <robin.murphy@arm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/freescale/fec_main.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 98ad34192255..76366c735831 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -3129,6 +3129,7 @@ static int fec_enet_init(struct net_device *ndev)
 	unsigned dsize = fep->bufdesc_ex ? sizeof(struct bufdesc_ex) :
 			sizeof(struct bufdesc);
 	unsigned dsize_log2 = __fls(dsize);
+	int ret;
 
 	WARN_ON(dsize != (1 << dsize_log2));
 #if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
@@ -3139,6 +3140,13 @@ static int fec_enet_init(struct net_device *ndev)
 	fep->tx_align = 0x3;
 #endif
 
+	/* Check mask of the streaming and coherent API */
+	ret = dma_set_mask_and_coherent(&fep->pdev->dev, DMA_BIT_MASK(32));
+	if (ret < 0) {
+		dev_warn(&fep->pdev->dev, "No suitable DMA available\n");
+		return ret;
+	}
+
 	fec_enet_alloc_queue(ndev);
 
 	bd_size = (fep->total_tx_ring_size + fep->total_rx_ring_size) * dsize;
-- 
cgit v1.2.3


From 9aba2f801eea5070f1d5588cd4052588437b9eea Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Thu, 2 Aug 2018 15:34:52 +0530
Subject: net: Fix coding style in skb_push()

Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 266b954f763e..51b0a9126e12 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1715,7 +1715,7 @@ void *skb_push(struct sk_buff *skb, unsigned int len)
 {
 	skb->data -= len;
 	skb->len  += len;
-	if (unlikely(skb->data<skb->head))
+	if (unlikely(skb->data < skb->head))
 		skb_under_panic(skb, len, __builtin_return_address(0));
 	return skb->data;
 }
-- 
cgit v1.2.3


From ffd7ce3cd9c294f1ff49ec02cdbd1bc7cb913db6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 2 Aug 2018 16:16:27 +0100
Subject: be2net: fix spelling mistake "seqence" -> "sequence"

Trivial fix to spelling mistake in dev_info message.

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 580cdec2d2ce..d0b9415d9ae7 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -1461,7 +1461,7 @@ static void be_tx_timeout(struct net_device *netdev)
 						 ntohs(tcphdr->source));
 					dev_info(dev, "TCP dest port %d\n",
 						 ntohs(tcphdr->dest));
-					dev_info(dev, "TCP seqence num %d\n",
+					dev_info(dev, "TCP sequence num %d\n",
 						 ntohs(tcphdr->seq));
 					dev_info(dev, "TCP ack_seq %d\n",
 						 ntohs(tcphdr->ack_seq));
-- 
cgit v1.2.3


From aa53bf0b03ae5e276c2714dc68e375d032bc9110 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 10 Jul 2018 12:18:29 -0400
Subject: media: cx231xx: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/cx231xx/cx231xx-audio.c | 10 ++++++----
 drivers/media/usb/cx231xx/cx231xx-core.c  | 10 ++++++----
 drivers/media/usb/cx231xx/cx231xx-vbi.c   |  5 +++--
 3 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c
index c4a84fb930b6..0025187c28e3 100644
--- a/drivers/media/usb/cx231xx/cx231xx-audio.c
+++ b/drivers/media/usb/cx231xx/cx231xx-audio.c
@@ -126,6 +126,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 		stride = runtime->frame_bits >> 3;
 
 		for (i = 0; i < urb->number_of_packets; i++) {
+			unsigned long flags;
 			int length = urb->iso_frame_desc[i].actual_length /
 				     stride;
 			cp = (unsigned char *)urb->transfer_buffer +
@@ -148,7 +149,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 				       length * stride);
 			}
 
-			snd_pcm_stream_lock(substream);
+			snd_pcm_stream_lock_irqsave(substream, flags);
 
 			dev->adev.hwptr_done_capture += length;
 			if (dev->adev.hwptr_done_capture >=
@@ -163,7 +164,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 						runtime->period_size;
 				period_elapsed = 1;
 			}
-			snd_pcm_stream_unlock(substream);
+			snd_pcm_stream_unlock_irqrestore(substream, flags);
 		}
 		if (period_elapsed)
 			snd_pcm_period_elapsed(substream);
@@ -216,6 +217,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 		stride = runtime->frame_bits >> 3;
 
 		if (1) {
+			unsigned long flags;
 			int length = urb->actual_length /
 				     stride;
 			cp = (unsigned char *)urb->transfer_buffer;
@@ -234,7 +236,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 				       length * stride);
 			}
 
-			snd_pcm_stream_lock(substream);
+			snd_pcm_stream_lock_irqsave(substream, flags);
 
 			dev->adev.hwptr_done_capture += length;
 			if (dev->adev.hwptr_done_capture >=
@@ -249,7 +251,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 						runtime->period_size;
 				period_elapsed = 1;
 			}
-			snd_pcm_stream_unlock(substream);
+			snd_pcm_stream_unlock_irqrestore(substream, flags);
 		}
 		if (period_elapsed)
 			snd_pcm_period_elapsed(substream);
diff --git a/drivers/media/usb/cx231xx/cx231xx-core.c b/drivers/media/usb/cx231xx/cx231xx-core.c
index 53d846dea3d2..493c2dca6244 100644
--- a/drivers/media/usb/cx231xx/cx231xx-core.c
+++ b/drivers/media/usb/cx231xx/cx231xx-core.c
@@ -799,6 +799,7 @@ static void cx231xx_isoc_irq_callback(struct urb *urb)
 	struct cx231xx_video_mode *vmode =
 	    container_of(dma_q, struct cx231xx_video_mode, vidq);
 	struct cx231xx *dev = container_of(vmode, struct cx231xx, video_mode);
+	unsigned long flags;
 	int i;
 
 	switch (urb->status) {
@@ -815,9 +816,9 @@ static void cx231xx_isoc_irq_callback(struct urb *urb)
 	}
 
 	/* Copy data from URB */
-	spin_lock(&dev->video_mode.slock);
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
 	dev->video_mode.isoc_ctl.isoc_copy(dev, urb);
-	spin_unlock(&dev->video_mode.slock);
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
 
 	/* Reset urb buffers */
 	for (i = 0; i < urb->number_of_packets; i++) {
@@ -844,6 +845,7 @@ static void cx231xx_bulk_irq_callback(struct urb *urb)
 	struct cx231xx_video_mode *vmode =
 	    container_of(dma_q, struct cx231xx_video_mode, vidq);
 	struct cx231xx *dev = container_of(vmode, struct cx231xx, video_mode);
+	unsigned long flags;
 
 	switch (urb->status) {
 	case 0:		/* success */
@@ -862,9 +864,9 @@ static void cx231xx_bulk_irq_callback(struct urb *urb)
 	}
 
 	/* Copy data from URB */
-	spin_lock(&dev->video_mode.slock);
+	spin_lock_irqsave(&dev->video_mode.slock, flags);
 	dev->video_mode.bulk_ctl.bulk_copy(dev, urb);
-	spin_unlock(&dev->video_mode.slock);
+	spin_unlock_irqrestore(&dev->video_mode.slock, flags);
 
 	/* Reset urb buffers */
 	urb->status = usb_submit_urb(urb, GFP_ATOMIC);
diff --git a/drivers/media/usb/cx231xx/cx231xx-vbi.c b/drivers/media/usb/cx231xx/cx231xx-vbi.c
index b621cf1aa96b..920417baf893 100644
--- a/drivers/media/usb/cx231xx/cx231xx-vbi.c
+++ b/drivers/media/usb/cx231xx/cx231xx-vbi.c
@@ -305,6 +305,7 @@ static void cx231xx_irq_vbi_callback(struct urb *urb)
 	struct cx231xx_video_mode *vmode =
 	    container_of(dma_q, struct cx231xx_video_mode, vidq);
 	struct cx231xx *dev = container_of(vmode, struct cx231xx, vbi_mode);
+	unsigned long flags;
 
 	switch (urb->status) {
 	case 0:		/* success */
@@ -321,9 +322,9 @@ static void cx231xx_irq_vbi_callback(struct urb *urb)
 	}
 
 	/* Copy data from URB */
-	spin_lock(&dev->vbi_mode.slock);
+	spin_lock_irqsave(&dev->vbi_mode.slock, flags);
 	dev->vbi_mode.bulk_ctl.bulk_copy(dev, urb);
-	spin_unlock(&dev->vbi_mode.slock);
+	spin_unlock_irqrestore(&dev->vbi_mode.slock, flags);
 
 	/* Reset status */
 	urb->status = 0;
-- 
cgit v1.2.3


From a4733b5248af10d5088ba06495e3faad9f7822b3 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 10 Jul 2018 12:18:31 -0400
Subject: media: go7007: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/go7007/go7007-driver.c |  9 +++++----
 drivers/media/usb/go7007/snd-go7007.c    | 11 ++++++-----
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/media/usb/go7007/go7007-driver.c b/drivers/media/usb/go7007/go7007-driver.c
index 05b1126f263e..62aeebcdd7f7 100644
--- a/drivers/media/usb/go7007/go7007-driver.c
+++ b/drivers/media/usb/go7007/go7007-driver.c
@@ -448,13 +448,14 @@ static struct go7007_buffer *frame_boundary(struct go7007 *go, struct go7007_buf
 {
 	u32 *bytesused;
 	struct go7007_buffer *vb_tmp = NULL;
+	unsigned long flags;
 
 	if (vb == NULL) {
-		spin_lock(&go->spinlock);
+		spin_lock_irqsave(&go->spinlock, flags);
 		if (!list_empty(&go->vidq_active))
 			vb = go->active_buf =
 				list_first_entry(&go->vidq_active, struct go7007_buffer, list);
-		spin_unlock(&go->spinlock);
+		spin_unlock_irqrestore(&go->spinlock, flags);
 		go->next_seq++;
 		return vb;
 	}
@@ -468,7 +469,7 @@ static struct go7007_buffer *frame_boundary(struct go7007 *go, struct go7007_buf
 
 	vb->vb.vb2_buf.timestamp = ktime_get_ns();
 	vb_tmp = vb;
-	spin_lock(&go->spinlock);
+	spin_lock_irqsave(&go->spinlock, flags);
 	list_del(&vb->list);
 	if (list_empty(&go->vidq_active))
 		vb = NULL;
@@ -476,7 +477,7 @@ static struct go7007_buffer *frame_boundary(struct go7007 *go, struct go7007_buf
 		vb = list_first_entry(&go->vidq_active,
 				struct go7007_buffer, list);
 	go->active_buf = vb;
-	spin_unlock(&go->spinlock);
+	spin_unlock_irqrestore(&go->spinlock, flags);
 	vb2_buffer_done(&vb_tmp->vb.vb2_buf, VB2_BUF_STATE_DONE);
 	return vb;
 }
diff --git a/drivers/media/usb/go7007/snd-go7007.c b/drivers/media/usb/go7007/snd-go7007.c
index f84a2130f033..137fc253b122 100644
--- a/drivers/media/usb/go7007/snd-go7007.c
+++ b/drivers/media/usb/go7007/snd-go7007.c
@@ -75,13 +75,14 @@ static void parse_audio_stream_data(struct go7007 *go, u8 *buf, int length)
 	struct go7007_snd *gosnd = go->snd_context;
 	struct snd_pcm_runtime *runtime = gosnd->substream->runtime;
 	int frames = bytes_to_frames(runtime, length);
+	unsigned long flags;
 
-	spin_lock(&gosnd->lock);
+	spin_lock_irqsave(&gosnd->lock, flags);
 	gosnd->hw_ptr += frames;
 	if (gosnd->hw_ptr >= runtime->buffer_size)
 		gosnd->hw_ptr -= runtime->buffer_size;
 	gosnd->avail += frames;
-	spin_unlock(&gosnd->lock);
+	spin_unlock_irqrestore(&gosnd->lock, flags);
 	if (gosnd->w_idx + length > runtime->dma_bytes) {
 		int cpy = runtime->dma_bytes - gosnd->w_idx;
 
@@ -92,13 +93,13 @@ static void parse_audio_stream_data(struct go7007 *go, u8 *buf, int length)
 	}
 	memcpy(runtime->dma_area + gosnd->w_idx, buf, length);
 	gosnd->w_idx += length;
-	spin_lock(&gosnd->lock);
+	spin_lock_irqsave(&gosnd->lock, flags);
 	if (gosnd->avail < runtime->period_size) {
-		spin_unlock(&gosnd->lock);
+		spin_unlock_irqrestore(&gosnd->lock, flags);
 		return;
 	}
 	gosnd->avail -= runtime->period_size;
-	spin_unlock(&gosnd->lock);
+	spin_unlock_irqrestore(&gosnd->lock, flags);
 	if (gosnd->capturing)
 		snd_pcm_period_elapsed(gosnd->substream);
 }
-- 
cgit v1.2.3


From 320905baa1dbddd3991c287432176d536e1d5b79 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 10 Jul 2018 12:18:33 -0400
Subject: media: usbtv: use irqsave() in USB's complete callback

The USB completion callback does not disable interrupts while acquiring
the lock. We want to remove the local_irq_disable() invocation from
__usb_hcd_giveback_urb() and therefore it is required for the callback
handler to disable the interrupts while acquiring the lock.
The callback may be invoked either in IRQ or BH context depending on the
USB host controller.
Use the _irqsave() variant of the locking primitives.

Cc: Hans Verkuil <hans.verkuil@cisco.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/usbtv/usbtv-audio.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/media/usb/usbtv/usbtv-audio.c b/drivers/media/usb/usbtv/usbtv-audio.c
index 2c2ca77fa01f..4ce38246ed64 100644
--- a/drivers/media/usb/usbtv/usbtv-audio.c
+++ b/drivers/media/usb/usbtv/usbtv-audio.c
@@ -126,6 +126,7 @@ static void usbtv_audio_urb_received(struct urb *urb)
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	size_t i, frame_bytes, chunk_length, buffer_pos, period_pos;
 	int period_elapsed;
+	unsigned long flags;
 	void *urb_current;
 
 	switch (urb->status) {
@@ -179,12 +180,12 @@ static void usbtv_audio_urb_received(struct urb *urb)
 		}
 	}
 
-	snd_pcm_stream_lock(substream);
+	snd_pcm_stream_lock_irqsave(substream, flags);
 
 	chip->snd_buffer_pos = buffer_pos;
 	chip->snd_period_pos = period_pos;
 
-	snd_pcm_stream_unlock(substream);
+	snd_pcm_stream_unlock_irqrestore(substream, flags);
 
 	if (period_elapsed)
 		snd_pcm_period_elapsed(substream);
-- 
cgit v1.2.3


From 04c450603fe4976e857099d15ba360b7cebb4e6d Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:54:56 +0300
Subject: mm/bootmem: drop duplicated kernel-doc comments

Parts of the bootmem interfaces are duplicated in nobootmem.c along with
the kernel-doc comments. There is no point to keep two copies of the
comments, so let's drop the bootmem.c copy.

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 mm/bootmem.c | 102 -----------------------------------------------------------
 1 file changed, 102 deletions(-)

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 9e197987b67d..42ab0da3a34a 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -143,15 +143,6 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 	return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages);
 }
 
-/*
- * free_bootmem_late - free bootmem pages directly to page allocator
- * @addr: starting physical address of the range
- * @size: size of the range in bytes
- *
- * This is only useful when the bootmem allocator has already been torn
- * down, but we are still initializing the system.  Pages are given directly
- * to the page allocator, no bootmem metadata is updated because it is gone.
- */
 void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 {
 	unsigned long cursor, end;
@@ -264,11 +255,6 @@ void __init reset_all_zones_managed_pages(void)
 	reset_managed_pages_done = 1;
 }
 
-/**
- * free_all_bootmem - release free pages to the buddy allocator
- *
- * Returns the number of pages actually released.
- */
 unsigned long __init free_all_bootmem(void)
 {
 	unsigned long total_pages = 0;
@@ -385,16 +371,6 @@ static int __init mark_bootmem(unsigned long start, unsigned long end,
 	BUG();
 }
 
-/**
- * free_bootmem_node - mark a page range as usable
- * @pgdat: node the range resides on
- * @physaddr: starting address of the range
- * @size: size of the range in bytes
- *
- * Partial pages will be considered reserved and left as they are.
- *
- * The range must reside completely on the specified node.
- */
 void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
@@ -408,15 +384,6 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 	mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
 }
 
-/**
- * free_bootmem - mark a page range as usable
- * @physaddr: starting physical address of the range
- * @size: size of the range in bytes
- *
- * Partial pages will be considered reserved and left as they are.
- *
- * The range must be contiguous but may span node boundaries.
- */
 void __init free_bootmem(unsigned long physaddr, unsigned long size)
 {
 	unsigned long start, end;
@@ -646,19 +613,6 @@ restart:
 	return NULL;
 }
 
-/**
- * __alloc_bootmem_nopanic - allocate boot memory without panicking
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * Returns NULL on failure.
- */
 void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 					unsigned long goal)
 {
@@ -682,19 +636,6 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
 	return NULL;
 }
 
-/**
- * __alloc_bootmem - allocate boot memory
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 			      unsigned long goal)
 {
@@ -754,21 +695,6 @@ void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 	return NULL;
 }
 
-/**
- * __alloc_bootmem_node - allocate boot memory from a specific node
- * @pgdat: node to allocate from
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may fall back to any node in the system if the specified node
- * can not hold the requested memory.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
 {
@@ -807,19 +733,6 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
 
 }
 
-/**
- * __alloc_bootmem_low - allocate low boot memory
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may happen on any node in the system.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 				  unsigned long goal)
 {
@@ -834,21 +747,6 @@ void * __init __alloc_bootmem_low_nopanic(unsigned long size,
 					ARCH_LOW_ADDRESS_LIMIT);
 }
 
-/**
- * __alloc_bootmem_low_node - allocate low boot memory from a specific node
- * @pgdat: node to allocate from
- * @size: size of the request in bytes
- * @align: alignment of the region
- * @goal: preferred starting address of the region
- *
- * The goal is dropped if it can not be satisfied and the allocation will
- * fall back to memory below @goal.
- *
- * Allocation may fall back to any node in the system if the specified node
- * can not hold the requested memory.
- *
- * The function panics if the request can not be satisfied.
- */
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
 {
-- 
cgit v1.2.3


From 8108ad51fe29d06da7bc963ab32e78ae6d882d5d Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:54:57 +0300
Subject: docs/mm: nobootmem: fixup kernel-doc comments

* add kernel-doc marking to free_bootmem_late() description
* add return value descriptions
* mention that address parameter of free_bootmem{_node} is a physical address

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 mm/nobootmem.c | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index 9b02fda0886b..c2cfa04f0231 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -72,7 +72,7 @@ again:
 	return ptr;
 }
 
-/*
+/**
  * free_bootmem_late - free bootmem pages directly to page allocator
  * @addr: starting address of the range
  * @size: size of the range in bytes
@@ -176,7 +176,7 @@ void __init reset_all_zones_managed_pages(void)
 /**
  * free_all_bootmem - release free pages to the buddy allocator
  *
- * Returns the number of pages actually released.
+ * Return: the number of pages actually released.
  */
 unsigned long __init free_all_bootmem(void)
 {
@@ -193,7 +193,7 @@ unsigned long __init free_all_bootmem(void)
 /**
  * free_bootmem_node - mark a page range as usable
  * @pgdat: node the range resides on
- * @physaddr: starting address of the range
+ * @physaddr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * Partial pages will be considered reserved and left as they are.
@@ -208,7 +208,7 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 /**
  * free_bootmem - mark a page range as usable
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * Partial pages will be considered reserved and left as they are.
@@ -256,7 +256,7 @@ restart:
  *
  * Allocation may happen on any node in the system.
  *
- * Returns NULL on failure.
+ * Return: address of the allocated region or %NULL on failure.
  */
 void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
 					unsigned long goal)
@@ -293,6 +293,8 @@ static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
  * Allocation may happen on any node in the system.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem(unsigned long size, unsigned long align,
 			      unsigned long goal)
@@ -367,6 +369,8 @@ static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
  * can not hold the requested memory.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
 				   unsigned long align, unsigned long goal)
@@ -396,6 +400,8 @@ void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
  * Allocation may happen on any node in the system.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
 				  unsigned long goal)
@@ -425,6 +431,8 @@ void * __init __alloc_bootmem_low_nopanic(unsigned long size,
  * can not hold the requested memory.
  *
  * The function panics if the request can not be satisfied.
+ *
+ * Return: address of the allocated region.
  */
 void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
 				       unsigned long align, unsigned long goal)
-- 
cgit v1.2.3


From 7c757207faf4526acfa18b25c6e9fe75a7e0d922 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:54:58 +0300
Subject: docs/mm: bootmem: fix kernel-doc warnings

Add descriptions of the return value where they were missing and fixup the
syntax for present ones.

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 mm/bootmem.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 42ab0da3a34a..76fc17eb78ae 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -62,6 +62,8 @@ static unsigned long __init bootmap_bytes(unsigned long pages)
 /**
  * bootmem_bootmap_pages - calculate bitmap size in pages
  * @pages: number of pages the bitmap has to represent
+ *
+ * Return: the number of pages needed to hold the bitmap.
  */
 unsigned long __init bootmem_bootmap_pages(unsigned long pages)
 {
@@ -121,7 +123,7 @@ static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
  * @startpfn: first pfn on the node
  * @endpfn: first pfn after the node
  *
- * Returns the number of bytes needed to hold the bitmap for this node.
+ * Return: the number of bytes needed to hold the bitmap for this node.
  */
 unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
 				unsigned long startpfn, unsigned long endpfn)
@@ -134,7 +136,7 @@ unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
  * @start: pfn where the bitmap is to be placed
  * @pages: number of available physical pages
  *
- * Returns the number of bytes needed to hold the bitmap.
+ * Return: the number of bytes needed to hold the bitmap.
  */
 unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 {
@@ -406,6 +408,8 @@ void __init free_bootmem(unsigned long physaddr, unsigned long size)
  * Partial pages will be reserved.
  *
  * The range must reside completely on the specified node.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 				 unsigned long size, int flags)
@@ -427,6 +431,8 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
  * Partial pages will be reserved.
  *
  * The range must be contiguous but may span node boundaries.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 int __init reserve_bootmem(unsigned long addr, unsigned long size,
 			    int flags)
-- 
cgit v1.2.3


From a83c0ea79d8b5705d09a39c73224332f9170a903 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:54:59 +0300
Subject: docs/mm: bootmem: add kernel-doc description of 'struct bootmem_data'

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/bootmem.h | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 7942a96b1a9d..42515195d7d8 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -27,9 +27,20 @@ extern unsigned long max_pfn;
 extern unsigned long long max_possible_pfn;
 
 #ifndef CONFIG_NO_BOOTMEM
-/*
- * node_bootmem_map is a map pointer - the bits represent all physical 
- * memory pages (including holes) on the node.
+/**
+ * struct bootmem_data - per-node information used by the bootmem allocator
+ * @node_min_pfn: the starting physical address of the node's memory
+ * @node_low_pfn: the end physical address of the directly addressable memory
+ * @node_bootmem_map: is a bitmap pointer - the bits represent all physical
+ *		      memory pages (including holes) on the node.
+ * @last_end_off: the offset within the page of the end of the last allocation;
+ *                if 0, the page used is full
+ * @hint_idx: the PFN of the page used with the last allocation;
+ *            together with using this with the @last_end_offset field,
+ *            a test can be made to see if allocations can be merged
+ *            with the page used for the last allocation rather than
+ *            using up a full new page.
+ * @list: list entry in the linked list ordered by the memory addresses
  */
 typedef struct bootmem_data {
 	unsigned long node_min_pfn;
-- 
cgit v1.2.3


From 58faef9328f7d66b377cb34a20331c4310cdbd5e Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:55:00 +0300
Subject: docs/mm: bootmem: add overview documentation

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 mm/bootmem.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 47 insertions(+)

diff --git a/mm/bootmem.c b/mm/bootmem.c
index 76fc17eb78ae..97db0e8e362b 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -21,6 +21,53 @@
 
 #include "internal.h"
 
+/**
+ * DOC: bootmem overview
+ *
+ * Bootmem is a boot-time physical memory allocator and configurator.
+ *
+ * It is used early in the boot process before the page allocator is
+ * set up.
+ *
+ * Bootmem is based on the most basic of allocators, a First Fit
+ * allocator which uses a bitmap to represent memory. If a bit is 1,
+ * the page is allocated and 0 if unallocated. To satisfy allocations
+ * of sizes smaller than a page, the allocator records the Page Frame
+ * Number (PFN) of the last allocation and the offset the allocation
+ * ended at. Subsequent small allocations are merged together and
+ * stored on the same page.
+ *
+ * The information used by the bootmem allocator is represented by
+ * :c:type:`struct bootmem_data`. An array to hold up to %MAX_NUMNODES
+ * such structures is statically allocated and then it is discarded
+ * when the system initialization completes. Each entry in this array
+ * corresponds to a node with memory. For UMA systems only entry 0 is
+ * used.
+ *
+ * The bootmem allocator is initialized during early architecture
+ * specific setup. Each architecture is required to supply a
+ * :c:func:`setup_arch` function which, among other tasks, is
+ * responsible for acquiring the necessary parameters to initialise
+ * the boot memory allocator. These parameters define limits of usable
+ * physical memory:
+ *
+ * * @min_low_pfn - the lowest PFN that is available in the system
+ * * @max_low_pfn - the highest PFN that may be addressed by low
+ *   memory (%ZONE_NORMAL)
+ * * @max_pfn - the last PFN available to the system.
+ *
+ * After those limits are determined, the :c:func:`init_bootmem` or
+ * :c:func:`init_bootmem_node` function should be called to initialize
+ * the bootmem allocator. The UMA case should use the `init_bootmem`
+ * function. It will initialize ``contig_page_data`` structure that
+ * represents the only memory node in the system. In the NUMA case the
+ * `init_bootmem_node` function should be called to initialize the
+ * bootmem allocator for each node.
+ *
+ * Once the allocator is set up, it is possible to use either single
+ * node or NUMA variant of the allocation APIs.
+ */
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 struct pglist_data __refdata contig_page_data = {
 	.bdata = &bootmem_node_data[0]
-- 
cgit v1.2.3


From e1720fee27246dfb84f7c433e35367170a2d4436 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:55:01 +0300
Subject: mm/memblock: add a name for memblock flags enumeration

Since kernel-doc does not like anonymous enums the name is required for
adding documentation. While on it, I've also updated all the function
declarations to use 'enum memblock_flags' instead of unsigned long.

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/memblock.h | 22 +++++++++++-----------
 mm/memblock.c            | 37 +++++++++++++++++++++----------------
 mm/nobootmem.c           |  2 +-
 3 files changed, 33 insertions(+), 28 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index ca59883c8364..8b8fbceffd4d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -21,7 +21,7 @@
 #define INIT_PHYSMEM_REGIONS	4
 
 /* Definition of memblock flags. */
-enum {
+enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
 	MEMBLOCK_HOTPLUG	= 0x1,	/* hotpluggable region */
 	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
@@ -31,7 +31,7 @@ enum {
 struct memblock_region {
 	phys_addr_t base;
 	phys_addr_t size;
-	unsigned long flags;
+	enum memblock_flags flags;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	int nid;
 #endif
@@ -72,7 +72,7 @@ void memblock_discard(void);
 
 phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
-					int nid, ulong flags);
+					int nid, enum memblock_flags flags);
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
 void memblock_allow_resize(void);
@@ -89,19 +89,19 @@ int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
 int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
-ulong choose_memblock_flags(void);
+enum memblock_flags choose_memblock_flags(void);
 
 /* Low level functions */
 int memblock_add_range(struct memblock_type *type,
 		       phys_addr_t base, phys_addr_t size,
-		       int nid, unsigned long flags);
+		       int nid, enum memblock_flags flags);
 
-void __next_mem_range(u64 *idx, int nid, ulong flags,
+void __next_mem_range(u64 *idx, int nid, enum memblock_flags flags,
 		      struct memblock_type *type_a,
 		      struct memblock_type *type_b, phys_addr_t *out_start,
 		      phys_addr_t *out_end, int *out_nid);
 
-void __next_mem_range_rev(u64 *idx, int nid, ulong flags,
+void __next_mem_range_rev(u64 *idx, int nid, enum memblock_flags flags,
 			  struct memblock_type *type_a,
 			  struct memblock_type *type_b, phys_addr_t *out_start,
 			  phys_addr_t *out_end, int *out_nid);
@@ -253,13 +253,13 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 			   NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL)
 
 static inline void memblock_set_region_flags(struct memblock_region *r,
-					     unsigned long flags)
+					     enum memblock_flags flags)
 {
 	r->flags |= flags;
 }
 
 static inline void memblock_clear_region_flags(struct memblock_region *r,
-					       unsigned long flags)
+					       enum memblock_flags flags)
 {
 	r->flags &= ~flags;
 }
@@ -317,10 +317,10 @@ static inline bool memblock_bottom_up(void)
 
 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
-					ulong flags);
+					enum memblock_flags flags);
 phys_addr_t memblock_alloc_base_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t max_addr,
-					int nid, ulong flags);
+					int nid, enum memblock_flags flags);
 phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
 				phys_addr_t max_addr);
 phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
diff --git a/mm/memblock.c b/mm/memblock.c
index 03d48d8835ba..20f48b49821a 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -60,7 +60,7 @@ static int memblock_can_resize __initdata_memblock;
 static int memblock_memory_in_slab __initdata_memblock = 0;
 static int memblock_reserved_in_slab __initdata_memblock = 0;
 
-ulong __init_memblock choose_memblock_flags(void)
+enum memblock_flags __init_memblock choose_memblock_flags(void)
 {
 	return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
 }
@@ -109,7 +109,7 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
 static phys_addr_t __init_memblock
 __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
 				phys_addr_t size, phys_addr_t align, int nid,
-				ulong flags)
+				enum memblock_flags flags)
 {
 	phys_addr_t this_start, this_end, cand;
 	u64 i;
@@ -143,7 +143,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
 static phys_addr_t __init_memblock
 __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
 			       phys_addr_t size, phys_addr_t align, int nid,
-			       ulong flags)
+			       enum memblock_flags flags)
 {
 	phys_addr_t this_start, this_end, cand;
 	u64 i;
@@ -188,7 +188,8 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  */
 phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
-					phys_addr_t end, int nid, ulong flags)
+					phys_addr_t end, int nid,
+					enum memblock_flags flags)
 {
 	phys_addr_t kernel_end, ret;
 
@@ -251,7 +252,7 @@ phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
 					phys_addr_t align)
 {
 	phys_addr_t ret;
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 
 again:
 	ret = memblock_find_in_range_node(size, align, start, end,
@@ -472,7 +473,8 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
 static void __init_memblock memblock_insert_region(struct memblock_type *type,
 						   int idx, phys_addr_t base,
 						   phys_addr_t size,
-						   int nid, unsigned long flags)
+						   int nid,
+						   enum memblock_flags flags)
 {
 	struct memblock_region *rgn = &type->regions[idx];
 
@@ -504,7 +506,7 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  */
 int __init_memblock memblock_add_range(struct memblock_type *type,
 				phys_addr_t base, phys_addr_t size,
-				int nid, unsigned long flags)
+				int nid, enum memblock_flags flags)
 {
 	bool insert = false;
 	phys_addr_t obase = base;
@@ -873,7 +875,8 @@ void __init_memblock __next_reserved_mem_region(u64 *idx,
  * As both region arrays are sorted, the function advances the two indices
  * in lockstep and returns each intersection.
  */
-void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
+void __init_memblock __next_mem_range(u64 *idx, int nid,
+				      enum memblock_flags flags,
 				      struct memblock_type *type_a,
 				      struct memblock_type *type_b,
 				      phys_addr_t *out_start,
@@ -982,7 +985,8 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
  *
  * Reverse of __next_mem_range().
  */
-void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
+void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
+					  enum memblock_flags flags,
 					  struct memblock_type *type_a,
 					  struct memblock_type *type_b,
 					  phys_addr_t *out_start,
@@ -1140,7 +1144,8 @@ int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
 
 static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t start,
-					phys_addr_t end, int nid, ulong flags)
+					phys_addr_t end, int nid,
+					enum memblock_flags flags)
 {
 	phys_addr_t found;
 
@@ -1162,7 +1167,7 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
 
 phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 					phys_addr_t start, phys_addr_t end,
-					ulong flags)
+					enum memblock_flags flags)
 {
 	return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE,
 					flags);
@@ -1170,14 +1175,14 @@ phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
 
 phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
 					phys_addr_t align, phys_addr_t max_addr,
-					int nid, ulong flags)
+					int nid, enum memblock_flags flags)
 {
 	return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags);
 }
 
 phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 	phys_addr_t ret;
 
 again:
@@ -1258,7 +1263,7 @@ static void * __init memblock_virt_alloc_internal(
 {
 	phys_addr_t alloc;
 	void *ptr;
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 
 	if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
 		nid = NUMA_NO_NODE;
@@ -1733,7 +1738,7 @@ phys_addr_t __init_memblock memblock_get_current_limit(void)
 static void __init_memblock memblock_dump(struct memblock_type *type)
 {
 	phys_addr_t base, end, size;
-	unsigned long flags;
+	enum memblock_flags flags;
 	int idx;
 	struct memblock_region *rgn;
 
@@ -1751,7 +1756,7 @@ static void __init_memblock memblock_dump(struct memblock_type *type)
 			snprintf(nid_buf, sizeof(nid_buf), " on node %d",
 				 memblock_get_region_node(rgn));
 #endif
-		pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#lx\n",
+		pr_info(" %s[%#x]\t[%pa-%pa], %pa bytes%s flags: %#x\n",
 			type->name, idx, &base, &end, &size, nid_buf, flags);
 	}
 }
diff --git a/mm/nobootmem.c b/mm/nobootmem.c
index c2cfa04f0231..439af3b765a7 100644
--- a/mm/nobootmem.c
+++ b/mm/nobootmem.c
@@ -42,7 +42,7 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 {
 	void *ptr;
 	u64 addr;
-	ulong flags = choose_memblock_flags();
+	enum memblock_flags flags = choose_memblock_flags();
 
 	if (limit > memblock.current_limit)
 		limit = memblock.current_limit;
-- 
cgit v1.2.3


From 47cec4432ab06c4ba90c241b142a016f878ac6da Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:55:02 +0300
Subject: docs/mm: memblock: update kernel-doc comments

* make memblock_discard description kernel-doc compatible
* add brief description for memblock_setclr_flag and describe its
  parameters
* fixup return value descriptions

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/memblock.h | 17 +++++++---
 mm/memblock.c            | 84 +++++++++++++++++++++++++++---------------------
 2 files changed, 59 insertions(+), 42 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8b8fbceffd4d..63704c64583a 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -239,7 +239,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 /**
  * for_each_resv_unavail_range - iterate through reserved and unavailable memory
  * @i: u64 used as loop variable
- * @flags: pick from blocks based on memory attributes
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  *
@@ -367,8 +366,10 @@ phys_addr_t memblock_get_current_limit(void);
  */
 
 /**
- * memblock_region_memory_base_pfn - Return the lowest pfn intersecting with the memory region
+ * memblock_region_memory_base_pfn - get the lowest pfn of the memory region
  * @reg: memblock_region structure
+ *
+ * Return: the lowest pfn intersecting with the memory region
  */
 static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg)
 {
@@ -376,8 +377,10 @@ static inline unsigned long memblock_region_memory_base_pfn(const struct membloc
 }
 
 /**
- * memblock_region_memory_end_pfn - Return the end_pfn this region
+ * memblock_region_memory_end_pfn - get the end pfn of the memory region
  * @reg: memblock_region structure
+ *
+ * Return: the end_pfn of the reserved region
  */
 static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg)
 {
@@ -385,8 +388,10 @@ static inline unsigned long memblock_region_memory_end_pfn(const struct memblock
 }
 
 /**
- * memblock_region_reserved_base_pfn - Return the lowest pfn intersecting with the reserved region
+ * memblock_region_reserved_base_pfn - get the lowest pfn of the reserved region
  * @reg: memblock_region structure
+ *
+ * Return: the lowest pfn intersecting with the reserved region
  */
 static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg)
 {
@@ -394,8 +399,10 @@ static inline unsigned long memblock_region_reserved_base_pfn(const struct membl
 }
 
 /**
- * memblock_region_reserved_end_pfn - Return the end_pfn this region
+ * memblock_region_reserved_end_pfn - get the end pfn of the reserved region
  * @reg: memblock_region structure
+ *
+ * Return: the end_pfn of the reserved region
  */
 static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg)
 {
diff --git a/mm/memblock.c b/mm/memblock.c
index 20f48b49821a..4b9dd76f6ae6 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -92,10 +92,11 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
 	return i < type->cnt;
 }
 
-/*
+/**
  * __memblock_find_range_bottom_up - find free area utility in bottom-up
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @size: size of free area to find
  * @align: alignment of free area to find
  * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
@@ -103,7 +104,7 @@ bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
  *
  * Utility called from memblock_find_in_range_node(), find free area bottom-up.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 static phys_addr_t __init_memblock
@@ -129,7 +130,8 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
 /**
  * __memblock_find_range_top_down - find free area utility, in top-down
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @size: size of free area to find
  * @align: alignment of free area to find
  * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
@@ -137,7 +139,7 @@ __memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
  *
  * Utility called from memblock_find_in_range_node(), find free area top-down.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 static phys_addr_t __init_memblock
@@ -169,7 +171,8 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  * @size: size of free area to find
  * @align: alignment of free area to find
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
  * @flags: pick from blocks based on memory attributes
  *
@@ -183,7 +186,7 @@ __memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
  *
  * If bottom-up allocation failed, will try to allocate memory top-down.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
@@ -238,13 +241,14 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
 /**
  * memblock_find_in_range - find free area in given range
  * @start: start of candidate range
- * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
+ * @end: end of candidate range, can be %MEMBLOCK_ALLOC_ANYWHERE or
+ *       %MEMBLOCK_ALLOC_ACCESSIBLE
  * @size: size of free area to find
  * @align: alignment of free area to find
  *
  * Find @size free area aligned to @align in the specified range.
  *
- * RETURNS:
+ * Return:
  * Found address on success, 0 on failure.
  */
 phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
@@ -288,7 +292,7 @@ static void __init_memblock memblock_remove_region(struct memblock_type *type, u
 
 #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
 /**
- * Discard memory and reserved arrays if they were allocated
+ * memblock_discard - discard memory and reserved arrays if they were allocated
  */
 void __init memblock_discard(void)
 {
@@ -318,11 +322,11 @@ void __init memblock_discard(void)
  *
  * Double the size of the @type regions array. If memblock is being used to
  * allocate memory for a new reserved regions array and there is a previously
- * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
+ * allocated memory range [@new_area_start, @new_area_start + @new_area_size]
  * waiting to be reserved, ensure the memory used by the new array does
  * not overlap.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -1 on failure.
  */
 static int __init_memblock memblock_double_array(struct memblock_type *type,
@@ -467,7 +471,7 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type)
  * @nid:	node id of the new region
  * @flags:	flags of the new region
  *
- * Insert new memblock region [@base,@base+@size) into @type at @idx.
+ * Insert new memblock region [@base, @base + @size) into @type at @idx.
  * @type must already have extra room to accommodate the new region.
  */
 static void __init_memblock memblock_insert_region(struct memblock_type *type,
@@ -496,12 +500,12 @@ static void __init_memblock memblock_insert_region(struct memblock_type *type,
  * @nid: nid of the new region
  * @flags: flags of the new region
  *
- * Add new memblock region [@base,@base+@size) into @type.  The new region
+ * Add new memblock region [@base, @base + @size) into @type.  The new region
  * is allowed to overlap with existing ones - overlaps don't affect already
  * existing regions.  @type is guaranteed to be minimal (all neighbouring
  * compatible regions are merged) after the addition.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -errno on failure.
  */
 int __init_memblock memblock_add_range(struct memblock_type *type,
@@ -615,11 +619,11 @@ int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
  * @end_rgn: out parameter for the end of isolated region
  *
  * Walk @type and ensure that regions don't cross the boundaries defined by
- * [@base,@base+@size).  Crossing regions are split at the boundaries,
+ * [@base, @base + @size).  Crossing regions are split at the boundaries,
  * which may create at most two more regions.  The index of the first
  * region inside the range is returned in *@start_rgn and end in *@end_rgn.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -errno on failure.
  */
 static int __init_memblock memblock_isolate_range(struct memblock_type *type,
@@ -730,10 +734,15 @@ int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 }
 
 /**
+ * memblock_setclr_flag - set or clear flag for a memory region
+ * @base: base address of the region
+ * @size: size of the region
+ * @set: set or clear the flag
+ * @flag: the flag to udpate
  *
  * This function isolates region [@base, @base + @size), and sets/clears flag
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 static int __init_memblock memblock_setclr_flag(phys_addr_t base,
 				phys_addr_t size, int set, int flag)
@@ -760,7 +769,7 @@ static int __init_memblock memblock_setclr_flag(phys_addr_t base,
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
 {
@@ -772,7 +781,7 @@ int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
 {
@@ -784,7 +793,7 @@ int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
 {
@@ -798,7 +807,7 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
 {
@@ -810,7 +819,7 @@ int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
  * @base: the base phys addr of the region
  * @size: the size of the region
  *
- * Return 0 on success, -errno on failure.
+ * Return: 0 on success, -errno on failure.
  */
 int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
 {
@@ -971,9 +980,6 @@ void __init_memblock __next_mem_range(u64 *idx, int nid,
 /**
  * __next_mem_range_rev - generic next function for for_each_*_range_rev()
  *
- * Finds the next range from type_a which is not marked as unsuitable
- * in type_b.
- *
  * @idx: pointer to u64 loop variable
  * @nid: node selector, %NUMA_NO_NODE for all nodes
  * @flags: pick from blocks based on memory attributes
@@ -983,6 +989,9 @@ void __init_memblock __next_mem_range(u64 *idx, int nid,
  * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @out_nid: ptr to int for nid of the range, can be %NULL
  *
+ * Finds the next range from type_a which is not marked as unsuitable
+ * in type_b.
+ *
  * Reverse of __next_mem_range().
  */
 void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
@@ -1118,10 +1127,10 @@ void __init_memblock __next_mem_pfn_range(int *idx, int nid,
  * @type: memblock type to set node ID for
  * @nid: node ID to set
  *
- * Set the nid of memblock @type regions in [@base,@base+@size) to @nid.
+ * Set the nid of memblock @type regions in [@base, @base + @size) to @nid.
  * Regions which cross the area boundaries are split as necessary.
  *
- * RETURNS:
+ * Return:
  * 0 on success, -errno on failure.
  */
 int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
@@ -1245,7 +1254,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
  * The allocation is performed from memory region limited by
  * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE.
  *
- * The memory block is aligned on SMP_CACHE_BYTES if @align == 0.
+ * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0.
  *
  * The phys address of allocated boot memory block is converted to virtual and
  * allocated memory is reset to 0.
@@ -1253,7 +1262,7 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i
  * In addition, function sets the min_count to 0 using kmemleak_alloc for
  * allocated boot memory block, so that it is never reported as leaks.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 static void * __init memblock_virt_alloc_internal(
@@ -1338,7 +1347,7 @@ done:
  * info), if enabled. Does not zero allocated memory, does not panic if request
  * cannot be satisfied.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 void * __init memblock_virt_alloc_try_nid_raw(
@@ -1375,7 +1384,7 @@ void * __init memblock_virt_alloc_try_nid_raw(
  * Public function, provides additional debug information (including caller
  * info), if enabled. This function zeroes the allocated memory.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 void * __init memblock_virt_alloc_try_nid_nopanic(
@@ -1411,7 +1420,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic(
  * which provides debug information (including caller info), if enabled,
  * and panics if the request can not be satisfied.
  *
- * RETURNS:
+ * Return:
  * Virtual address of allocated memory block on success, NULL on failure.
  */
 void * __init memblock_virt_alloc_try_nid(
@@ -1668,9 +1677,9 @@ int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
  * @base: base of region to check
  * @size: size of region to check
  *
- * Check if the region [@base, @base+@size) is a subset of a memory block.
+ * Check if the region [@base, @base + @size) is a subset of a memory block.
  *
- * RETURNS:
+ * Return:
  * 0 if false, non-zero if true
  */
 bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
@@ -1689,9 +1698,10 @@ bool __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t siz
  * @base: base of region to check
  * @size: size of region to check
  *
- * Check if the region [@base, @base+@size) intersects a reserved memory block.
+ * Check if the region [@base, @base + @size) intersects a reserved
+ * memory block.
  *
- * RETURNS:
+ * Return:
  * True if they intersect, false if not.
  */
 bool __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
-- 
cgit v1.2.3


From 48a833cc74ce90ec7937b96bfcbb3e43ec34cf05 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:55:03 +0300
Subject: docs/mm: memblock: add kernel-doc comments for memblock_add[_node]

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 mm/memblock.c | 27 +++++++++++++++++++++++++--
 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/mm/memblock.c b/mm/memblock.c
index 4b9dd76f6ae6..245263ad65fb 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -594,12 +594,35 @@ repeat:
 	}
 }
 
+/**
+ * memblock_add_node - add new memblock region within a NUMA node
+ * @base: base address of the new region
+ * @size: size of the new region
+ * @nid: nid of the new region
+ *
+ * Add new memblock region [@base, @base + @size) to the "memory"
+ * type. See memblock_add_range() description for mode details
+ *
+ * Return:
+ * 0 on success, -errno on failure.
+ */
 int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
 				       int nid)
 {
 	return memblock_add_range(&memblock.memory, base, size, nid, 0);
 }
 
+/**
+ * memblock_add - add new memblock region
+ * @base: base address of the new region
+ * @size: size of the new region
+ *
+ * Add new memblock region [@base, @base + @size) to the "memory"
+ * type. See memblock_add_range() description for mode details
+ *
+ * Return:
+ * 0 on success, -errno on failure.
+ */
 int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
 	phys_addr_t end = base + size - 1;
@@ -1463,9 +1486,9 @@ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size)
 	memblock_remove_range(&memblock.reserved, base, size);
 }
 
-/*
+/**
  * __memblock_free_late - free bootmem block pages directly to buddy allocator
- * @addr: phys starting address of the  boot memory block
+ * @base: phys starting address of the  boot memory block
  * @size: size of the boot memory block in bytes
  *
  * This is only useful when the bootmem allocator has already been torn
-- 
cgit v1.2.3


From 9a0de1bfe191220cb0437865261ab2f95cbb13ef Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:55:04 +0300
Subject: docs/mm: memblock: add kernel-doc description for memblock types

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 include/linux/memblock.h | 37 +++++++++++++++++++++++++++++++++----
 1 file changed, 33 insertions(+), 4 deletions(-)

diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 63704c64583a..516920549378 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -20,7 +20,13 @@
 #define INIT_MEMBLOCK_REGIONS	128
 #define INIT_PHYSMEM_REGIONS	4
 
-/* Definition of memblock flags. */
+/**
+ * enum memblock_flags - definition of memory region attributes
+ * @MEMBLOCK_NONE: no special request
+ * @MEMBLOCK_HOTPLUG: hotpluggable region
+ * @MEMBLOCK_MIRROR: mirrored region
+ * @MEMBLOCK_NOMAP: don't add to kernel direct mapping
+ */
 enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
 	MEMBLOCK_HOTPLUG	= 0x1,	/* hotpluggable region */
@@ -28,6 +34,13 @@ enum memblock_flags {
 	MEMBLOCK_NOMAP		= 0x4,	/* don't add to kernel direct mapping */
 };
 
+/**
+ * struct memblock_region - represents a memory region
+ * @base: physical address of the region
+ * @size: size of the region
+ * @flags: memory region attributes
+ * @nid: NUMA node id
+ */
 struct memblock_region {
 	phys_addr_t base;
 	phys_addr_t size;
@@ -37,14 +50,30 @@ struct memblock_region {
 #endif
 };
 
+/**
+ * struct memblock_type - collection of memory regions of certain type
+ * @cnt: number of regions
+ * @max: size of the allocated array
+ * @total_size: size of all regions
+ * @regions: array of regions
+ * @name: the memory type symbolic name
+ */
 struct memblock_type {
-	unsigned long cnt;	/* number of regions */
-	unsigned long max;	/* size of the allocated array */
-	phys_addr_t total_size;	/* size of all regions */
+	unsigned long cnt;
+	unsigned long max;
+	phys_addr_t total_size;
 	struct memblock_region *regions;
 	char *name;
 };
 
+/**
+ * struct memblock - memblock allocator metadata
+ * @bottom_up: is bottom up direction?
+ * @current_limit: physical address of the current allocation limit
+ * @memory: usabe memory regions
+ * @reserved: reserved memory regions
+ * @physmem: all physical memory
+ */
 struct memblock {
 	bool bottom_up;  /* is bottom up direction? */
 	phys_addr_t current_limit;
-- 
cgit v1.2.3


From 3e039c5c0a070050172e0382f2d3f5396c759019 Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:55:05 +0300
Subject: docs/mm: memblock: add overview documentation

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 mm/memblock.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/mm/memblock.c b/mm/memblock.c
index 245263ad65fb..1e1ea24e66ed 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -26,6 +26,61 @@
 
 #include "internal.h"
 
+/**
+ * DOC: memblock overview
+ *
+ * Memblock is a method of managing memory regions during the early
+ * boot period when the usual kernel memory allocators are not up and
+ * running.
+ *
+ * Memblock views the system memory as collections of contiguous
+ * regions. There are several types of these collections:
+ *
+ * * ``memory`` - describes the physical memory available to the
+ *   kernel; this may differ from the actual physical memory installed
+ *   in the system, for instance when the memory is restricted with
+ *   ``mem=`` command line parameter
+ * * ``reserved`` - describes the regions that were allocated
+ * * ``physmap`` - describes the actual physical memory regardless of
+ *   the possible restrictions; the ``physmap`` type is only available
+ *   on some architectures.
+ *
+ * Each region is represented by :c:type:`struct memblock_region` that
+ * defines the region extents, its attributes and NUMA node id on NUMA
+ * systems. Every memory type is described by the :c:type:`struct
+ * memblock_type` which contains an array of memory regions along with
+ * the allocator metadata. The memory types are nicely wrapped with
+ * :c:type:`struct memblock`. This structure is statically initialzed
+ * at build time. The region arrays for the "memory" and "reserved"
+ * types are initially sized to %INIT_MEMBLOCK_REGIONS and for the
+ * "physmap" type to %INIT_PHYSMEM_REGIONS.
+ * The :c:func:`memblock_allow_resize` enables automatic resizing of
+ * the region arrays during addition of new regions. This feature
+ * should be used with care so that memory allocated for the region
+ * array will not overlap with areas that should be reserved, for
+ * example initrd.
+ *
+ * The early architecture setup should tell memblock what the physical
+ * memory layout is by using :c:func:`memblock_add` or
+ * :c:func:`memblock_add_node` functions. The first function does not
+ * assign the region to a NUMA node and it is appropriate for UMA
+ * systems. Yet, it is possible to use it on NUMA systems as well and
+ * assign the region to a NUMA node later in the setup process using
+ * :c:func:`memblock_set_node`. The :c:func:`memblock_add_node`
+ * performs such an assignment directly.
+ *
+ * Once memblock is setup the memory can be allocated using either
+ * memblock or bootmem APIs.
+ *
+ * As the system boot progresses, the architecture specific
+ * :c:func:`mem_init` function frees all the memory to the buddy page
+ * allocator.
+ *
+ * If an architecure enables %CONFIG_ARCH_DISCARD_MEMBLOCK, the
+ * memblock data structures will be discarded after the system
+ * initialization compltes.
+ */
+
 static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
-- 
cgit v1.2.3


From 6706fe55af6fc2bcb069a77620ae38662bf09d1c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 4 Jul 2018 05:48:35 -0400
Subject: media: dvb_ca_en50221: off by one in dvb_ca_en50221_io_do_ioctl()

The > should be >= so we don't read one element beyond the end of the
ca->slot_info[] array.  The array is allocated in dvb_ca_en50221_init().

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Acked-by: Jasmin Jessich <jasmin@anw.at>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-core/dvb_ca_en50221.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/dvb-core/dvb_ca_en50221.c b/drivers/media/dvb-core/dvb_ca_en50221.c
index 1310526b0d49..4d371cea0d5d 100644
--- a/drivers/media/dvb-core/dvb_ca_en50221.c
+++ b/drivers/media/dvb-core/dvb_ca_en50221.c
@@ -1391,7 +1391,7 @@ static int dvb_ca_en50221_io_do_ioctl(struct file *file,
 		struct dvb_ca_slot *sl;
 
 		slot = info->num;
-		if ((slot > ca->slot_count) || (slot < 0)) {
+		if ((slot >= ca->slot_count) || (slot < 0)) {
 			err = -EINVAL;
 			goto out_unlock;
 		}
-- 
cgit v1.2.3


From d63e2fc804c46e50eee825c5d3a7228e07048b47 Mon Sep 17 00:00:00 2001
From: BingJing Chang <bingjingc@synology.com>
Date: Wed, 1 Aug 2018 17:08:36 +0800
Subject: md/raid5: fix data corruption of replacements after originals dropped

During raid5 replacement, the stripes can be marked with R5_NeedReplace
flag. Data can be read from being-replaced devices and written to
replacing spares without reading all other devices. (It's 'replace'
mode. s.replacing = 1) If a being-replaced device is dropped, the
replacement progress will be interrupted and resumed with pure recovery
mode. However, existing stripes before being interrupted cannot read
from the dropped device anymore. It prints lots of WARN_ON messages.
And it results in data corruption because existing stripes write
problematic data into its replacement device and update the progress.

\# Erase disks (1MB + 2GB)
dd if=/dev/zero of=/dev/sda bs=1MB count=2049
dd if=/dev/zero of=/dev/sdb bs=1MB count=2049
dd if=/dev/zero of=/dev/sdc bs=1MB count=2049
dd if=/dev/zero of=/dev/sdd bs=1MB count=2049
mdadm -C /dev/md0 -amd -R -l5 -n3 -x0 /dev/sd[abc] -z 2097152
\# Ensure array stores non-zero data
dd if=/root/data_4GB.iso of=/dev/md0 bs=1MB
\# Start replacement
mdadm /dev/md0 -a /dev/sdd
mdadm /dev/md0 --replace /dev/sda

Then, Hot-plug out /dev/sda during recovery, and wait for recovery done.
echo check > /sys/block/md0/md/sync_action
cat /sys/block/md0/md/mismatch_cnt # it will be greater than 0.

Soon after you hot-plug out /dev/sda, you will see many WARN_ON
messages. The replacement recovery will be interrupted shortly. After
the recovery finishes, it will result in data corruption.

Actually, it's just an unhandled case of replacement. In commit
<f94c0b6658c7> (md/raid5: fix interaction of 'replace' and 'recovery'.),
if a NeedReplace device is not UPTODATE then that is an error, the
commit just simply print WARN_ON but also mark these corrupted stripes
with R5_WantReplace. (it means it's ready for writes.)

To fix this case, we can leverage 'sync and replace' mode mentioned in
commit <9a3e1101b827> (md/raid5: detect and handle replacements during
recovery.). We can add logics to detect and use 'sync and replace' mode
for these stripes.

Reported-by: Alex Chen <alexchen@synology.com>
Reviewed-by: Alex Wu <alexwu@synology.com>
Reviewed-by: Chung-Chiang Cheng <cccheng@synology.com>
Signed-off-by: BingJing Chang <bingjingc@synology.com>
Signed-off-by: Shaohua Li <shli@fb.com>
---
 drivers/md/raid5.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index ca1dd0cb04c5..81eaa221216c 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -4519,6 +4519,12 @@ static void analyse_stripe(struct stripe_head *sh, struct stripe_head_state *s)
 			s->failed++;
 			if (rdev && !test_bit(Faulty, &rdev->flags))
 				do_recovery = 1;
+			else if (!rdev) {
+				rdev = rcu_dereference(
+				    conf->disks[i].replacement);
+				if (rdev && !test_bit(Faulty, &rdev->flags))
+					do_recovery = 1;
+			}
 		}
 
 		if (test_bit(R5_InJournal, &dev->flags))
-- 
cgit v1.2.3


From ae9d88454446a314f9cda785a072a0c77a81591b Mon Sep 17 00:00:00 2001
From: Mike Rapoport <rppt@linux.vnet.ibm.com>
Date: Sat, 30 Jun 2018 17:55:06 +0300
Subject: docs/mm: add description of boot time memory management

Both bootmem and memblock are have pretty good internal documentation
coverage. With addition of some overview we get a nice description of the
early memory management.

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/core-api/boot-time-mm.rst | 92 +++++++++++++++++++++++++++++++++
 Documentation/core-api/index.rst        |  1 +
 2 files changed, 93 insertions(+)
 create mode 100644 Documentation/core-api/boot-time-mm.rst

diff --git a/Documentation/core-api/boot-time-mm.rst b/Documentation/core-api/boot-time-mm.rst
new file mode 100644
index 000000000000..03cb1643f46f
--- /dev/null
+++ b/Documentation/core-api/boot-time-mm.rst
@@ -0,0 +1,92 @@
+===========================
+Boot time memory management
+===========================
+
+Early system initialization cannot use "normal" memory management
+simply because it is not set up yet. But there is still need to
+allocate memory for various data structures, for instance for the
+physical page allocator. To address this, a specialized allocator
+called the :ref:`Boot Memory Allocator <bootmem>`, or bootmem, was
+introduced. Several years later PowerPC developers added a "Logical
+Memory Blocks" allocator, which was later adopted by other
+architectures and renamed to :ref:`memblock <memblock>`. There is also
+a compatibility layer called `nobootmem` that translates bootmem
+allocation interfaces to memblock calls.
+
+The selection of the early allocator is done using
+``CONFIG_NO_BOOTMEM`` and ``CONFIG_HAVE_MEMBLOCK`` kernel
+configuration options. These options are enabled or disabled
+statically by the architectures' Kconfig files.
+
+* Architectures that rely only on bootmem select
+  ``CONFIG_NO_BOOTMEM=n && CONFIG_HAVE_MEMBLOCK=n``.
+* The users of memblock with the nobootmem compatibility layer set
+  ``CONFIG_NO_BOOTMEM=y && CONFIG_HAVE_MEMBLOCK=y``.
+* And for those that use both memblock and bootmem the configuration
+  includes ``CONFIG_NO_BOOTMEM=n && CONFIG_HAVE_MEMBLOCK=y``.
+
+Whichever allocator is used, it is the responsibility of the
+architecture specific initialization to set it up in
+:c:func:`setup_arch` and tear it down in :c:func:`mem_init` functions.
+
+Once the early memory management is available it offers a variety of
+functions and macros for memory allocations. The allocation request
+may be directed to the first (and probably the only) node or to a
+particular node in a NUMA system. There are API variants that panic
+when an allocation fails and those that don't. And more recent and
+advanced memblock even allows controlling its own behaviour.
+
+.. _bootmem:
+
+Bootmem
+=======
+
+(mostly stolen from Mel Gorman's "Understanding the Linux Virtual
+Memory Manager" `book`_)
+
+.. _book: https://www.kernel.org/doc/gorman/
+
+.. kernel-doc:: mm/bootmem.c
+   :doc: bootmem overview
+
+.. _memblock:
+
+Memblock
+========
+
+.. kernel-doc:: mm/memblock.c
+   :doc: memblock overview
+
+
+Functions and structures
+========================
+
+Common API
+----------
+
+The functions that are described in this section are available
+regardless of what early memory manager is enabled.
+
+.. kernel-doc:: mm/nobootmem.c
+
+Bootmem specific API
+--------------------
+
+These interfaces available only with bootmem, i.e when ``CONFIG_NO_BOOTMEM=n``
+
+.. kernel-doc:: include/linux/bootmem.h
+.. kernel-doc:: mm/bootmem.c
+   :nodocs:
+
+Memblock specific API
+---------------------
+
+Here is the description of memblock data structures, functions and
+macros. Some of them are actually internal, but since they are
+documented it would be silly to omit them. Besides, reading the
+descriptions for the internal functions can help to understand what
+really happens under the hood.
+
+.. kernel-doc:: include/linux/memblock.h
+.. kernel-doc:: mm/memblock.c
+   :nodocs:
diff --git a/Documentation/core-api/index.rst b/Documentation/core-api/index.rst
index f5a66b72f984..93d5a46122a1 100644
--- a/Documentation/core-api/index.rst
+++ b/Documentation/core-api/index.rst
@@ -28,6 +28,7 @@ Core utilities
    printk-formats
    circular-buffers
    gfp_mask-from-fs-io
+   boot-time-mm
 
 Interfaces for kernel debugging
 ===============================
-- 
cgit v1.2.3


From 66fc44b71c59165597afd751c5b2825a4d8e1456 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:02 +0200
Subject: mt76: move MT_TXD_INFO, MT_MCU_MSG and MT_RX_FCE_INFO defs in dma.h

Since MT_TXD_INFO, MT_MCU_MSG and MT_RX_FCE_INFO definitions are in
common between mt76x2u, mt76x2 and mt76x0u move them in dma.h in order
to reuse usb code supporting mt76x2u and mt76x0u based devices

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/dma.h        | 38 +++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2_dma.h | 38 -------------------------
 2 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h
index 1dad39697929..14cfb2dbca25 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.h
+++ b/drivers/net/wireless/mediatek/mt76/dma.h
@@ -25,6 +25,34 @@
 #define MT_DMA_CTL_LAST_SEC0		BIT(30)
 #define MT_DMA_CTL_DMA_DONE		BIT(31)
 
+#define MT_TXD_INFO_LEN			GENMASK(15, 0)
+#define MT_TXD_INFO_NEXT_VLD		BIT(16)
+#define MT_TXD_INFO_TX_BURST		BIT(17)
+#define MT_TXD_INFO_80211		BIT(19)
+#define MT_TXD_INFO_TSO			BIT(20)
+#define MT_TXD_INFO_CSO			BIT(21)
+#define MT_TXD_INFO_WIV			BIT(24)
+#define MT_TXD_INFO_QSEL		GENMASK(26, 25)
+#define MT_TXD_INFO_DPORT		GENMASK(29, 27)
+#define MT_TXD_INFO_TYPE		GENMASK(31, 30)
+
+#define MT_RX_FCE_INFO_LEN		GENMASK(13, 0)
+#define MT_RX_FCE_INFO_SELF_GEN		BIT(15)
+#define MT_RX_FCE_INFO_CMD_SEQ		GENMASK(19, 16)
+#define MT_RX_FCE_INFO_EVT_TYPE		GENMASK(23, 20)
+#define MT_RX_FCE_INFO_PCIE_INTR	BIT(24)
+#define MT_RX_FCE_INFO_QSEL		GENMASK(26, 25)
+#define MT_RX_FCE_INFO_D_PORT		GENMASK(29, 27)
+#define MT_RX_FCE_INFO_TYPE		GENMASK(31, 30)
+
+/* MCU request message header  */
+#define MT_MCU_MSG_LEN			GENMASK(15, 0)
+#define MT_MCU_MSG_CMD_SEQ		GENMASK(19, 16)
+#define MT_MCU_MSG_CMD_TYPE		GENMASK(26, 20)
+#define MT_MCU_MSG_PORT			GENMASK(29, 27)
+#define MT_MCU_MSG_TYPE			GENMASK(31, 30)
+#define MT_MCU_MSG_TYPE_CMD		BIT(30)
+
 struct mt76_desc {
 	__le32 buf0;
 	__le32 ctrl;
@@ -32,6 +60,16 @@ struct mt76_desc {
 	__le32 info;
 } __packed __aligned(4);
 
+enum dma_msg_port {
+	WLAN_PORT,
+	CPU_RX_PORT,
+	CPU_TX_PORT,
+	HOST_PORT,
+	VIRTUAL_CPU_RX_PORT,
+	VIRTUAL_CPU_TX_PORT,
+	DISCARD,
+};
+
 int mt76_dma_attach(struct mt76_dev *dev);
 void mt76_dma_cleanup(struct mt76_dev *dev);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h
index e9d426bbf91a..da294558c268 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.h
@@ -19,34 +19,6 @@
 
 #include "dma.h"
 
-#define MT_TXD_INFO_LEN			GENMASK(15, 0)
-#define MT_TXD_INFO_NEXT_VLD		BIT(16)
-#define MT_TXD_INFO_TX_BURST		BIT(17)
-#define MT_TXD_INFO_80211		BIT(19)
-#define MT_TXD_INFO_TSO			BIT(20)
-#define MT_TXD_INFO_CSO			BIT(21)
-#define MT_TXD_INFO_WIV			BIT(24)
-#define MT_TXD_INFO_QSEL		GENMASK(26, 25)
-#define MT_TXD_INFO_DPORT		GENMASK(29, 27)
-#define MT_TXD_INFO_TYPE		GENMASK(31, 30)
-
-#define MT_RX_FCE_INFO_LEN		GENMASK(13, 0)
-#define MT_RX_FCE_INFO_SELF_GEN		BIT(15)
-#define MT_RX_FCE_INFO_CMD_SEQ		GENMASK(19, 16)
-#define MT_RX_FCE_INFO_EVT_TYPE		GENMASK(23, 20)
-#define MT_RX_FCE_INFO_PCIE_INTR	BIT(24)
-#define MT_RX_FCE_INFO_QSEL		GENMASK(26, 25)
-#define MT_RX_FCE_INFO_D_PORT		GENMASK(29, 27)
-#define MT_RX_FCE_INFO_TYPE		GENMASK(31, 30)
-
-/* MCU request message header  */
-#define MT_MCU_MSG_LEN			GENMASK(15, 0)
-#define MT_MCU_MSG_CMD_SEQ		GENMASK(19, 16)
-#define MT_MCU_MSG_CMD_TYPE		GENMASK(26, 20)
-#define MT_MCU_MSG_PORT			GENMASK(29, 27)
-#define MT_MCU_MSG_TYPE			GENMASK(31, 30)
-#define MT_MCU_MSG_TYPE_CMD		BIT(30)
-
 enum mt76x2_qsel {
 	MT_QSEL_MGMT,
 	MT_QSEL_HCCA,
@@ -54,14 +26,4 @@ enum mt76x2_qsel {
 	MT_QSEL_EDCA_2,
 };
 
-enum dma_msg_port {
-	WLAN_PORT,
-	CPU_RX_PORT,
-	CPU_TX_PORT,
-	HOST_PORT,
-	VIRTUAL_CPU_RX_PORT,
-	VIRTUAL_CPU_TX_PORT,
-	DISCARD,
-};
-
 #endif
-- 
cgit v1.2.3


From 35ecee1f6755819f67c4360c2787cb4c27821886 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:03 +0200
Subject: mt76x2: move mt76x2_fw_header and mt76x2_patch_header definitions in
 mcu.h

move mt76x2_fw_header and mt76x2_patch_header definitions in mcu.h in
order to reuse them in mt76x2u mcu related code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c | 17 -----------------
 drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h | 17 +++++++++++++++++
 2 files changed, 17 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c
index dfd36d736b06..743da57760dc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.c
@@ -23,23 +23,6 @@
 #include "mt76x2_dma.h"
 #include "mt76x2_eeprom.h"
 
-struct mt76x2_fw_header {
-	__le32 ilm_len;
-	__le32 dlm_len;
-	__le16 build_ver;
-	__le16 fw_ver;
-	u8 pad[4];
-	char build_time[16];
-};
-
-struct mt76x2_patch_header {
-	char build_time[16];
-	char platform[4];
-	char hw_version[4];
-	char patch_version[4];
-	u8 pad[2];
-};
-
 static struct sk_buff *mt76x2_mcu_msg_alloc(const void *data, int len)
 {
 	struct sk_buff *skb;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h
index d7a7e83262ce..e40293f21417 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mcu.h
@@ -146,6 +146,23 @@ struct mt76x2_tssi_comp {
 	u8 offset1;
 } __packed __aligned(4);
 
+struct mt76x2_fw_header {
+	__le32 ilm_len;
+	__le32 dlm_len;
+	__le16 build_ver;
+	__le16 fw_ver;
+	u8 pad[4];
+	char build_time[16];
+};
+
+struct mt76x2_patch_header {
+	char build_time[16];
+	char platform[4];
+	char hw_version[4];
+	char patch_version[4];
+	u8 pad[2];
+};
+
 int mt76x2_mcu_calibrate(struct mt76x2_dev *dev, enum mcu_calibration type,
 			 u32 param);
 int mt76x2_mcu_tssi_comp(struct mt76x2_dev *dev, struct mt76x2_tssi_comp *tssi_data);
-- 
cgit v1.2.3


From 2edb2ae5e60a2520ce5dea19e4d967e5fdc366c5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:04 +0200
Subject: mt76x2: move utility routines in mt76x2.h

In order to reuse them supporting mt76x2u based devices, move
mt76x2_wait_for_mac, wait_for_wpdma and mt76x2_channel_silent in
mt76x2.h

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2.h      | 40 ++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2_init.c | 28 -----------------
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c  |  9 ------
 3 files changed, 40 insertions(+), 37 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 40e57073923e..e9d9e8228e89 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -159,6 +159,23 @@ struct mt76x2_sta {
 	int inactive_count;
 };
 
+static inline bool mt76x2_wait_for_mac(struct mt76x2_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < 500; i++) {
+		switch (mt76_rr(dev, MT_MAC_CSR0)) {
+		case 0:
+		case ~0:
+			break;
+		default:
+			return true;
+		}
+		usleep_range(5000, 10000);
+	}
+	return false;
+}
+
 static inline bool is_mt7612(struct mt76x2_dev *dev)
 {
 	return mt76_chip(&dev->mt76) == 0x7612;
@@ -166,6 +183,14 @@ static inline bool is_mt7612(struct mt76x2_dev *dev)
 
 void mt76x2_set_irq_mask(struct mt76x2_dev *dev, u32 clear, u32 set);
 
+static inline bool mt76x2_channel_silent(struct mt76x2_dev *dev)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+
+	return ((chan->flags & IEEE80211_CHAN_RADAR) &&
+		chan->dfs_state != NL80211_DFS_AVAILABLE);
+}
+
 static inline void mt76x2_irq_enable(struct mt76x2_dev *dev, u32 mask)
 {
 	mt76x2_set_irq_mask(dev, 0, mask);
@@ -176,6 +201,21 @@ static inline void mt76x2_irq_disable(struct mt76x2_dev *dev, u32 mask)
 	mt76x2_set_irq_mask(dev, mask, 0);
 }
 
+static inline bool mt76x2_wait_for_bbp(struct mt76x2_dev *dev)
+{
+	return mt76_poll_msec(dev, MT_MAC_STATUS,
+			      MT_MAC_STATUS_TX | MT_MAC_STATUS_RX,
+			      0, 100);
+}
+
+static inline bool wait_for_wpdma(struct mt76x2_dev *dev)
+{
+	return mt76_poll(dev, MT_WPDMA_GLO_CFG,
+			 MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+			 MT_WPDMA_GLO_CFG_RX_DMA_BUSY,
+			 0, 1000);
+}
+
 extern const struct ieee80211_ops mt76x2_ops;
 
 struct mt76x2_dev *mt76x2_alloc_device(struct device *pdev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
index 8ab9788464e8..347cccfc74bb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
@@ -24,34 +24,6 @@ struct mt76x2_reg_pair {
 	u32 value;
 };
 
-static bool
-mt76x2_wait_for_mac(struct mt76x2_dev *dev)
-{
-	int i;
-
-	for (i = 0; i < 500; i++) {
-		switch (mt76_rr(dev, MT_MAC_CSR0)) {
-		case 0:
-		case ~0:
-			break;
-		default:
-			return true;
-		}
-		usleep_range(5000, 10000);
-	}
-
-	return false;
-}
-
-static bool
-wait_for_wpdma(struct mt76x2_dev *dev)
-{
-	return mt76_poll(dev, MT_WPDMA_GLO_CFG,
-			 MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
-			 MT_WPDMA_GLO_CFG_RX_DMA_BUSY,
-			 0, 1000);
-}
-
 static void
 mt76x2_mac_pbf_init(struct mt76x2_dev *dev)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 20ffa6a40d39..9a7b50f0005d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -176,15 +176,6 @@ void mt76x2_phy_set_txpower(struct mt76x2_dev *dev)
 		mt76x2_tx_power_mask(t.ht[6], t.vht[8], t.vht[8], 0));
 }
 
-static bool
-mt76x2_channel_silent(struct mt76x2_dev *dev)
-{
-	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
-
-	return ((chan->flags & IEEE80211_CHAN_RADAR) &&
-		chan->dfs_state != NL80211_DFS_AVAILABLE);
-}
-
 static bool
 mt76x2_phy_tssi_init_cal(struct mt76x2_dev *dev)
 {
-- 
cgit v1.2.3


From 15fdb7a07bbe318320d2190e20bc87b66942114e Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:05 +0200
Subject: mt76x2: introduce mt76x2_init_device routine

Add mt76x2_init_device routine in order to reuse common pcie/usb mac80211
initialization code supporting mt76x2u based device

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2.h      |  1 +
 drivers/net/wireless/mediatek/mt76/mt76x2_init.c | 58 +++++++++++++-----------
 2 files changed, 33 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index e9d9e8228e89..896549c2fcbb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -221,6 +221,7 @@ extern const struct ieee80211_ops mt76x2_ops;
 struct mt76x2_dev *mt76x2_alloc_device(struct device *pdev);
 int mt76x2_register_device(struct mt76x2_dev *dev);
 void mt76x2_init_debugfs(struct mt76x2_dev *dev);
+void mt76x2_init_device(struct mt76x2_dev *dev);
 
 irqreturn_t mt76x2_irq_handler(int irq, void *dev_instance);
 void mt76x2_phy_power_on(struct mt76x2_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
index 347cccfc74bb..c3ecc1c206bd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
@@ -545,11 +545,6 @@ int mt76x2_init_hardware(struct mt76x2_dev *dev)
 	tasklet_init(&dev->pre_tbtt_tasklet, mt76x2_pre_tbtt_tasklet,
 		     (unsigned long) dev);
 
-	dev->chainmask = 0x202;
-	dev->global_wcid.idx = 255;
-	dev->global_wcid.hw_key_idx = -1;
-	dev->slottime = 9;
-
 	val = mt76_rr(dev, MT_WPDMA_GLO_CFG);
 	val &= MT_WPDMA_GLO_CFG_DMA_BURST_SIZE |
 	       MT_WPDMA_GLO_CFG_BIG_ENDIAN |
@@ -776,6 +771,34 @@ mt76x2_init_txpower(struct mt76x2_dev *dev,
 	}
 }
 
+void mt76x2_init_device(struct mt76x2_dev *dev)
+{
+	struct ieee80211_hw *hw = mt76_hw(dev);
+
+	hw->queues = 4;
+	hw->max_rates = 1;
+	hw->max_report_rates = 7;
+	hw->max_rate_tries = 1;
+	hw->extra_tx_headroom = 2;
+
+	hw->sta_data_size = sizeof(struct mt76x2_sta);
+	hw->vif_data_size = sizeof(struct mt76x2_vif);
+
+	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
+	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
+
+	dev->mt76.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
+	dev->mt76.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
+
+	dev->chainmask = 0x202;
+	dev->global_wcid.idx = 255;
+	dev->global_wcid.hw_key_idx = -1;
+	dev->slottime = 9;
+
+	/* init antenna configuration */
+	dev->mt76.antenna_mask = 3;
+}
+
 int mt76x2_register_device(struct mt76x2_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
@@ -790,20 +813,15 @@ int mt76x2_register_device(struct mt76x2_dev *dev)
 		return -ENOMEM;
 
 	kfifo_init(&dev->txstatus_fifo, status_fifo, fifo_size);
+	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x2_mac_work);
+
+	mt76x2_init_device(dev);
 
 	ret = mt76x2_init_hardware(dev);
 	if (ret)
 		return ret;
 
-	hw->queues = 4;
-	hw->max_rates = 1;
-	hw->max_report_rates = 7;
-	hw->max_rate_tries = 1;
-	hw->extra_tx_headroom = 2;
-
-	hw->sta_data_size = sizeof(struct mt76x2_sta);
-	hw->vif_data_size = sizeof(struct mt76x2_vif);
-
 	for (i = 0; i < ARRAY_SIZE(dev->macaddr_list); i++) {
 		u8 *addr = dev->macaddr_list[i].addr;
 
@@ -825,24 +843,12 @@ int mt76x2_register_device(struct mt76x2_dev *dev)
 
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
-	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
-	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
-
-	INIT_DELAYED_WORK(&dev->cal_work, mt76x2_phy_calibrate);
-	INIT_DELAYED_WORK(&dev->mac_work, mt76x2_mac_work);
-
-	dev->mt76.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
-	dev->mt76.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
-
 	mt76x2_dfs_init_detector(dev);
 
 	/* init led callbacks */
 	dev->mt76.led_cdev.brightness_set = mt76x2_led_set_brightness;
 	dev->mt76.led_cdev.blink_set = mt76x2_led_set_blink;
 
-	/* init antenna configuration */
-	dev->mt76.antenna_mask = 3;
-
 	ret = mt76_register_device(&dev->mt76, true, mt76x2_rates,
 				   ARRAY_SIZE(mt76x2_rates));
 	if (ret)
-- 
cgit v1.2.3


From 4681e0c79e4312c30a458ab87c8cea6b8f909b95 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:06 +0200
Subject: mt76x2: move interface_modes definition in mt76x2_init

Move  wiphy interface_modes definition in mt76x2_init in order to
reuse mt76_register_device routine supporting mt76x2u based chipsets
since mt76x2u currently supports just sta mode

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c    | 8 --------
 drivers/net/wireless/mediatek/mt76/mt76x2_init.c | 8 ++++++++
 2 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index d62e34e7eadf..6a0b6f4403a8 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -303,14 +303,6 @@ int mt76_register_device(struct mt76_dev *dev, bool vht,
 	SET_IEEE80211_DEV(hw, dev->dev);
 	SET_IEEE80211_PERM_ADDR(hw, dev->macaddr);
 
-	wiphy->interface_modes =
-		BIT(NL80211_IFTYPE_STATION) |
-		BIT(NL80211_IFTYPE_AP) |
-#ifdef CONFIG_MAC80211_MESH
-		BIT(NL80211_IFTYPE_MESH_POINT) |
-#endif
-		BIT(NL80211_IFTYPE_ADHOC);
-
 	wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
 
 	wiphy->available_antennas_tx = dev->antenna_mask;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
index c3ecc1c206bd..d3eedd9c59b7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
@@ -841,6 +841,14 @@ int mt76x2_register_device(struct mt76x2_dev *dev)
 
 	wiphy->reg_notifier = mt76x2_regd_notifier;
 
+	wiphy->interface_modes =
+		BIT(NL80211_IFTYPE_STATION) |
+		BIT(NL80211_IFTYPE_AP) |
+#ifdef CONFIG_MAC80211_MESH
+		BIT(NL80211_IFTYPE_MESH_POINT) |
+#endif
+		BIT(NL80211_IFTYPE_ADHOC);
+
 	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
 
 	mt76x2_dfs_init_detector(dev);
-- 
cgit v1.2.3


From d3c94b40460b8786d55380abf5dbd42fc3be7dfb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:07 +0200
Subject: mt76x2: introduce mt76x2_mac_load_tx_status routine

Add mt76x2_mac_load_tx_status routine since tx stats register map is
shared between usb and pci based devices but usb devices do not have a
tx stat irq line as pcie ones and it is necessary to load tx statistics
using a workqueue

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.c | 47 ++++++++++++++++---------
 1 file changed, 30 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
index e5e92f79f28a..bff0b7268467 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
@@ -532,11 +532,37 @@ out:
 	rcu_read_unlock();
 }
 
+static bool
+mt76x2_mac_load_tx_status(struct mt76x2_dev *dev,
+			  struct mt76x2_tx_status *stat)
+{
+	u32 stat1, stat2;
+
+	stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
+	stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
+
+	stat->valid = !!(stat1 & MT_TX_STAT_FIFO_VALID);
+	if (!stat->valid)
+		return false;
+
+	stat->success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
+	stat->aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
+	stat->ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
+	stat->wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
+	stat->rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
+
+	stat->retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
+	stat->pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
+
+	return true;
+}
+
 void mt76x2_mac_poll_tx_status(struct mt76x2_dev *dev, bool irq)
 {
 	struct mt76x2_tx_status stat = {};
 	unsigned long flags;
 	u8 update = 1;
+	bool ret;
 
 	if (!test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
 		return;
@@ -544,26 +570,13 @@ void mt76x2_mac_poll_tx_status(struct mt76x2_dev *dev, bool irq)
 	trace_mac_txstat_poll(dev);
 
 	while (!irq || !kfifo_is_full(&dev->txstatus_fifo)) {
-		u32 stat1, stat2;
-
 		spin_lock_irqsave(&dev->irq_lock, flags);
-		stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
-		stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
-		if (!(stat1 & MT_TX_STAT_FIFO_VALID)) {
-			spin_unlock_irqrestore(&dev->irq_lock, flags);
-			break;
-		}
-
+		ret = mt76x2_mac_load_tx_status(dev, &stat);
 		spin_unlock_irqrestore(&dev->irq_lock, flags);
 
-		stat.valid = 1;
-		stat.success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
-		stat.aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
-		stat.ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
-		stat.wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
-		stat.rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
-		stat.retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
-		stat.pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
+		if (!ret)
+			break;
+
 		trace_mac_txstat_fetch(dev, &stat);
 
 		if (!irq) {
-- 
cgit v1.2.3


From 81e850ef2625cb859d1ff8f0d81129bfb1e219fa Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:08 +0200
Subject: mt76x2: add napi struct to mt76_rx_poll_complete/mt76_rx_complete
 signatures

in order to reuse mt76_rx_complete routine supporting mt76x2u based
devices add napi struct to mt76_rx_poll_complete and mt76_rx_complete
routine signatures and do not fetch it according to the rx queue index

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/agg-rx.c   |  2 +-
 drivers/net/wireless/mediatek/mt76/dma.c      |  2 +-
 drivers/net/wireless/mediatek/mt76/mac80211.c | 12 +++++-------
 drivers/net/wireless/mediatek/mt76/mt76.h     |  5 +++--
 4 files changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/agg-rx.c b/drivers/net/wireless/mediatek/mt76/agg-rx.c
index 1e8cdce919d9..73c8b2805c97 100644
--- a/drivers/net/wireless/mediatek/mt76/agg-rx.c
+++ b/drivers/net/wireless/mediatek/mt76/agg-rx.c
@@ -113,7 +113,7 @@ mt76_rx_aggr_reorder_work(struct work_struct *work)
 	if (nframes)
 		ieee80211_queue_delayed_work(tid->dev->hw, &tid->reorder_work,
 					     REORDER_TIMEOUT);
-	mt76_rx_complete(dev, &frames, -1);
+	mt76_rx_complete(dev, &frames, NULL);
 
 	rcu_read_unlock();
 	local_bh_enable();
diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 3dbedcedc2c4..872b1c53e246 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -400,7 +400,7 @@ mt76_dma_rx_poll(struct napi_struct *napi, int budget)
 
 	do {
 		cur = mt76_dma_rx_process(dev, &dev->q_rx[qid], budget - done);
-		mt76_rx_poll_complete(dev, qid);
+		mt76_rx_poll_complete(dev, qid, napi);
 		done += cur;
 	} while (cur && done < budget);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 6a0b6f4403a8..029d54bce9e8 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -583,15 +583,11 @@ mt76_check_ps(struct mt76_dev *dev, struct sk_buff *skb)
 }
 
 void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
-		      int queue)
+		      struct napi_struct *napi)
 {
-	struct napi_struct *napi = NULL;
 	struct ieee80211_sta *sta;
 	struct sk_buff *skb;
 
-	if (queue >= 0)
-	    napi = &dev->napi[queue];
-
 	spin_lock(&dev->rx_lock);
 	while ((skb = __skb_dequeue(frames)) != NULL) {
 		if (mt76_check_ccmp_pn(skb)) {
@@ -605,7 +601,8 @@ void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
 	spin_unlock(&dev->rx_lock);
 }
 
-void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q)
+void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
+			   struct napi_struct *napi)
 {
 	struct sk_buff_head frames;
 	struct sk_buff *skb;
@@ -617,5 +614,6 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q)
 		mt76_rx_aggr_reorder(skb, &frames);
 	}
 
-	mt76_rx_complete(dev, &frames, q);
+	mt76_rx_complete(dev, &frames, napi);
 }
+EXPORT_SYMBOL_GPL(mt76_rx_poll_complete);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 96e9798bb8a0..eb0fd602b9cb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -456,8 +456,9 @@ void mt76_wcid_key_setup(struct mt76_dev *dev, struct mt76_wcid *wcid,
 void mt76_tx_free(struct mt76_dev *dev);
 void mt76_put_txwi(struct mt76_dev *dev, struct mt76_txwi_cache *t);
 void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
-		      int queue);
-void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q);
+		      struct napi_struct *napi);
+void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
+			   struct napi_struct *napi);
 void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames);
 
 #endif
-- 
cgit v1.2.3


From bbd89d948108217344556dc07beddca202fbd431 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:09 +0200
Subject: mt76x2: add buffer len to mt76x2_mac_write_txwi signature

Add frame length to mt76x2_mac_write_txwi routine signature and do not
fetch it from skb since txwi data structure is added at the beginning of
the skb for usb based devices and mt76x2_mac_write_txwi will be shared
between pci and usb related code

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.c | 6 +++---
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.h | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2_tx.c  | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
index bff0b7268467..010c1cbfcd6c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
@@ -167,7 +167,7 @@ void mt76x2_mac_wcid_set_rate(struct mt76x2_dev *dev, struct mt76_wcid *wcid,
 
 void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
-			   struct ieee80211_sta *sta)
+			   struct ieee80211_sta *sta, int len)
 {
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_tx_rate *rate = &info->control.rates[0];
@@ -254,7 +254,7 @@ void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
 		txwi_flags |= MT_TXWI_FLAGS_TS;
 
 	txwi->flags |= cpu_to_le16(txwi_flags);
-	txwi->len_ctl = cpu_to_le16(skb->len);
+	txwi->len_ctl = cpu_to_le16(len);
 }
 
 static void mt76x2_remove_hdr_pad(struct sk_buff *skb, int len)
@@ -732,7 +732,7 @@ mt76_write_beacon(struct mt76x2_dev *dev, int offset, struct sk_buff *skb)
 	if (WARN_ON_ONCE(beacon_len < skb->len + sizeof(struct mt76x2_txwi)))
 		return -ENOSPC;
 
-	mt76x2_mac_write_txwi(dev, &txwi, skb, NULL, NULL);
+	mt76x2_mac_write_txwi(dev, &txwi, skb, NULL, NULL, skb->len);
 
 	mt76_wr_copy(dev, offset, &txwi, sizeof(txwi));
 	offset += sizeof(txwi);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h
index c048cd06df6b..5af0107ba748 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.h
@@ -166,7 +166,7 @@ int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
 			  void *rxi);
 void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
-			   struct ieee80211_sta *sta);
+			   struct ieee80211_sta *sta, int len);
 void mt76x2_mac_wcid_setup(struct mt76x2_dev *dev, u8 idx, u8 vif_idx, u8 *mac);
 int mt76x2_mac_wcid_set_key(struct mt76x2_dev *dev, u8 idx,
 			    struct ieee80211_key_conf *key);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
index 560376dd1133..241a1513ec55 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
@@ -159,7 +159,7 @@ int mt76x2_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 	if (q == &dev->mt76.q_tx[MT_TXQ_PSD] && wcid && wcid->idx < 128)
 		mt76x2_mac_wcid_set_drop(dev, wcid->idx, false);
 
-	mt76x2_mac_write_txwi(dev, txwi, skb, wcid, sta);
+	mt76x2_mac_write_txwi(dev, txwi, skb, wcid, sta, skb->len);
 
 	ret = mt76x2_insert_hdr_pad(skb);
 	if (ret < 0)
-- 
cgit v1.2.3


From fcdd99ce7267f248980ae318af439a7ac1b111dc Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:10 +0200
Subject: mt76: rename mt76_tx_queue_skb in mt76_dma_tx_queue_skb

Move mt76_dma_tx_queue_skb routine in dma.c.
Remove static qualifier from mt76_get_txwi definition

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/dma.c       | 74 +++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76.h      |  7 ++-
 drivers/net/wireless/mediatek/mt76/mt76x2_tx.c |  3 +-
 drivers/net/wireless/mediatek/mt76/tx.c        | 84 ++------------------------
 4 files changed, 85 insertions(+), 83 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 872b1c53e246..6293f21856da 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -239,6 +239,80 @@ mt76_dma_kick_queue(struct mt76_dev *dev, struct mt76_queue *q)
 	iowrite32(q->head, &q->regs->cpu_idx);
 }
 
+int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
+			  struct sk_buff *skb, struct mt76_wcid *wcid,
+			  struct ieee80211_sta *sta)
+{
+	struct mt76_queue_entry e;
+	struct mt76_txwi_cache *t;
+	struct mt76_queue_buf buf[32];
+	struct sk_buff *iter;
+	dma_addr_t addr;
+	int len;
+	u32 tx_info = 0;
+	int n, ret;
+
+	t = mt76_get_txwi(dev);
+	if (!t) {
+		ieee80211_free_txskb(dev->hw, skb);
+		return -ENOMEM;
+	}
+
+	dma_sync_single_for_cpu(dev->dev, t->dma_addr, sizeof(t->txwi),
+				DMA_TO_DEVICE);
+	ret = dev->drv->tx_prepare_skb(dev, &t->txwi, skb, q, wcid, sta,
+				       &tx_info);
+	dma_sync_single_for_device(dev->dev, t->dma_addr, sizeof(t->txwi),
+				   DMA_TO_DEVICE);
+	if (ret < 0)
+		goto free;
+
+	len = skb->len - skb->data_len;
+	addr = dma_map_single(dev->dev, skb->data, len, DMA_TO_DEVICE);
+	if (dma_mapping_error(dev->dev, addr)) {
+		ret = -ENOMEM;
+		goto free;
+	}
+
+	n = 0;
+	buf[n].addr = t->dma_addr;
+	buf[n++].len = dev->drv->txwi_size;
+	buf[n].addr = addr;
+	buf[n++].len = len;
+
+	skb_walk_frags(skb, iter) {
+		if (n == ARRAY_SIZE(buf))
+			goto unmap;
+
+		addr = dma_map_single(dev->dev, iter->data, iter->len,
+				      DMA_TO_DEVICE);
+		if (dma_mapping_error(dev->dev, addr))
+			goto unmap;
+
+		buf[n].addr = addr;
+		buf[n++].len = iter->len;
+	}
+
+	if (q->queued + (n + 1) / 2 >= q->ndesc - 1)
+		goto unmap;
+
+	return dev->queue_ops->add_buf(dev, q, buf, n, tx_info, skb, t);
+
+unmap:
+	ret = -ENOMEM;
+	for (n--; n > 0; n--)
+		dma_unmap_single(dev->dev, buf[n].addr, buf[n].len,
+				 DMA_TO_DEVICE);
+
+free:
+	e.skb = skb;
+	e.txwi = t;
+	dev->drv->tx_complete_skb(dev, q, &e, true);
+	mt76_put_txwi(dev, t);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76_dma_tx_queue_skb);
+
 static int
 mt76_dma_rx_fill(struct mt76_dev *dev, struct mt76_queue *q, bool napi)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index eb0fd602b9cb..4d6660b9e451 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -421,9 +421,9 @@ wcid_to_sta(struct mt76_wcid *wcid)
 	return container_of(ptr, struct ieee80211_sta, drv_priv);
 }
 
-int mt76_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
-		      struct sk_buff *skb, struct mt76_wcid *wcid,
-		      struct ieee80211_sta *sta);
+int mt76_dma_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
+			  struct sk_buff *skb, struct mt76_wcid *wcid,
+			  struct ieee80211_sta *sta);
 
 void mt76_rx(struct mt76_dev *dev, enum mt76_rxq_id q, struct sk_buff *skb);
 void mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
@@ -454,6 +454,7 @@ void mt76_wcid_key_setup(struct mt76_dev *dev, struct mt76_wcid *wcid,
 
 /* internal */
 void mt76_tx_free(struct mt76_dev *dev);
+struct mt76_txwi_cache *mt76_get_txwi(struct mt76_dev *dev);
 void mt76_put_txwi(struct mt76_dev *dev, struct mt76_txwi_cache *t);
 void mt76_rx_complete(struct mt76_dev *dev, struct sk_buff_head *frames,
 		      struct napi_struct *napi);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
index 241a1513ec55..84a3448ca163 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
@@ -289,7 +289,8 @@ void mt76x2_pre_tbtt_tasklet(unsigned long arg)
 		struct ieee80211_vif *vif = info->control.vif;
 		struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
 
-		mt76_tx_queue_skb(&dev->mt76, q, skb, &mvif->group_wcid, NULL);
+		mt76_dma_tx_queue_skb(&dev->mt76, q, skb, &mvif->group_wcid,
+				      NULL);
 	}
 	spin_unlock_bh(&q->lock);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index e96956710fb2..f86501ecf31a 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -51,7 +51,7 @@ __mt76_get_txwi(struct mt76_dev *dev)
 	return t;
 }
 
-static struct mt76_txwi_cache *
+struct mt76_txwi_cache *
 mt76_get_txwi(struct mt76_dev *dev)
 {
 	struct mt76_txwi_cache *t = __mt76_get_txwi(dev);
@@ -91,80 +91,6 @@ mt76_txq_get_qid(struct ieee80211_txq *txq)
 	return txq->ac;
 }
 
-int mt76_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
-		      struct sk_buff *skb, struct mt76_wcid *wcid,
-		      struct ieee80211_sta *sta)
-{
-	struct mt76_queue_entry e;
-	struct mt76_txwi_cache *t;
-	struct mt76_queue_buf buf[32];
-	struct sk_buff *iter;
-	dma_addr_t addr;
-	int len;
-	u32 tx_info = 0;
-	int n, ret;
-
-	t = mt76_get_txwi(dev);
-	if (!t) {
-		ieee80211_free_txskb(dev->hw, skb);
-		return -ENOMEM;
-	}
-
-	dma_sync_single_for_cpu(dev->dev, t->dma_addr, sizeof(t->txwi),
-				DMA_TO_DEVICE);
-	ret = dev->drv->tx_prepare_skb(dev, &t->txwi, skb, q, wcid, sta,
-				       &tx_info);
-	dma_sync_single_for_device(dev->dev, t->dma_addr, sizeof(t->txwi),
-				   DMA_TO_DEVICE);
-	if (ret < 0)
-		goto free;
-
-	len = skb->len - skb->data_len;
-	addr = dma_map_single(dev->dev, skb->data, len, DMA_TO_DEVICE);
-	if (dma_mapping_error(dev->dev, addr)) {
-		ret = -ENOMEM;
-		goto free;
-	}
-
-	n = 0;
-	buf[n].addr = t->dma_addr;
-	buf[n++].len = dev->drv->txwi_size;
-	buf[n].addr = addr;
-	buf[n++].len = len;
-
-	skb_walk_frags(skb, iter) {
-		if (n == ARRAY_SIZE(buf))
-			goto unmap;
-
-		addr = dma_map_single(dev->dev, iter->data, iter->len,
-				      DMA_TO_DEVICE);
-		if (dma_mapping_error(dev->dev, addr))
-			goto unmap;
-
-		buf[n].addr = addr;
-		buf[n++].len = iter->len;
-	}
-
-	if (q->queued + (n + 1) / 2 >= q->ndesc - 1)
-		goto unmap;
-
-	return dev->queue_ops->add_buf(dev, q, buf, n, tx_info, skb, t);
-
-unmap:
-	ret = -ENOMEM;
-	for (n--; n > 0; n--)
-		dma_unmap_single(dev->dev, buf[n].addr, buf[n].len,
-				 DMA_TO_DEVICE);
-
-free:
-	e.skb = skb;
-	e.txwi = t;
-	dev->drv->tx_complete_skb(dev, q, &e, true);
-	mt76_put_txwi(dev, t);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(mt76_tx_queue_skb);
-
 void
 mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
 	struct mt76_wcid *wcid, struct sk_buff *skb)
@@ -185,7 +111,7 @@ mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
 	q = &dev->q_tx[qid];
 
 	spin_lock_bh(&q->lock);
-	mt76_tx_queue_skb(dev, q, skb, wcid, sta);
+	mt76_dma_tx_queue_skb(dev, q, skb, wcid, sta);
 	dev->queue_ops->kick(dev, q);
 
 	if (q->queued > q->ndesc - 8)
@@ -241,7 +167,7 @@ mt76_queue_ps_skb(struct mt76_dev *dev, struct ieee80211_sta *sta,
 		info->flags |= IEEE80211_TX_STATUS_EOSP;
 
 	mt76_skb_set_moredata(skb, !last);
-	mt76_tx_queue_skb(dev, hwq, skb, wcid, sta);
+	mt76_dma_tx_queue_skb(dev, hwq, skb, wcid, sta);
 }
 
 void
@@ -321,7 +247,7 @@ mt76_txq_send_burst(struct mt76_dev *dev, struct mt76_queue *hwq,
 	if (ampdu)
 		mt76_check_agg_ssn(mtxq, skb);
 
-	idx = mt76_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
+	idx = mt76_dma_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
 
 	if (idx < 0)
 		return idx;
@@ -356,7 +282,7 @@ mt76_txq_send_burst(struct mt76_dev *dev, struct mt76_queue *hwq,
 		if (cur_ampdu)
 			mt76_check_agg_ssn(mtxq, skb);
 
-		idx = mt76_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
+		idx = mt76_dma_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
 		if (idx < 0)
 			return idx;
 
-- 
cgit v1.2.3


From 469d48188625bbb5d1cf9bacdfeae8e8636f81d6 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:11 +0200
Subject: mt76: introduce tx_queue_skb function pointer in mt76_bus_ops

Add tx_queue_skb function pointer in mt76_bus_ops since mt76x2u based
devices do not map mt76x2_txwi on dma buffers and it is not possible
to reuse mt76_dma_tx_queue_skb() routine to enqueue tx frames to
hw buffers

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/dma.c  | 1 +
 drivers/net/wireless/mediatek/mt76/mt76.h | 5 +++++
 drivers/net/wireless/mediatek/mt76/tx.c   | 9 +++++----
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/dma.c b/drivers/net/wireless/mediatek/mt76/dma.c
index 6293f21856da..c51da2205b93 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/dma.c
@@ -510,6 +510,7 @@ static const struct mt76_queue_ops mt76_dma_ops = {
 	.init = mt76_dma_init,
 	.alloc = mt76_dma_alloc_queue,
 	.add_buf = mt76_dma_add_buf,
+	.tx_queue_skb = mt76_dma_tx_queue_skb,
 	.tx_cleanup = mt76_dma_tx_cleanup,
 	.rx_reset = mt76_dma_rx_reset,
 	.kick = mt76_dma_kick_queue,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 4d6660b9e451..ed40d6e66d44 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -30,6 +30,7 @@
 #define MT_RX_BUF_SIZE      2048
 
 struct mt76_dev;
+struct mt76_wcid;
 
 struct mt76_bus_ops {
 	u32 (*rr)(struct mt76_dev *dev, u32 offset);
@@ -110,6 +111,10 @@ struct mt76_queue_ops {
 		       struct mt76_queue_buf *buf, int nbufs, u32 info,
 		       struct sk_buff *skb, void *txwi);
 
+	int (*tx_queue_skb)(struct mt76_dev *dev, struct mt76_queue *q,
+			    struct sk_buff *skb, struct mt76_wcid *wcid,
+			    struct ieee80211_sta *sta);
+
 	void *(*dequeue)(struct mt76_dev *dev, struct mt76_queue *q, bool flush,
 			 int *len, u32 *info, bool *more);
 
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index f86501ecf31a..af48d43bb7dc 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -111,7 +111,7 @@ mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta,
 	q = &dev->q_tx[qid];
 
 	spin_lock_bh(&q->lock);
-	mt76_dma_tx_queue_skb(dev, q, skb, wcid, sta);
+	dev->queue_ops->tx_queue_skb(dev, q, skb, wcid, sta);
 	dev->queue_ops->kick(dev, q);
 
 	if (q->queued > q->ndesc - 8)
@@ -167,7 +167,7 @@ mt76_queue_ps_skb(struct mt76_dev *dev, struct ieee80211_sta *sta,
 		info->flags |= IEEE80211_TX_STATUS_EOSP;
 
 	mt76_skb_set_moredata(skb, !last);
-	mt76_dma_tx_queue_skb(dev, hwq, skb, wcid, sta);
+	dev->queue_ops->tx_queue_skb(dev, hwq, skb, wcid, sta);
 }
 
 void
@@ -247,7 +247,7 @@ mt76_txq_send_burst(struct mt76_dev *dev, struct mt76_queue *hwq,
 	if (ampdu)
 		mt76_check_agg_ssn(mtxq, skb);
 
-	idx = mt76_dma_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
+	idx = dev->queue_ops->tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
 
 	if (idx < 0)
 		return idx;
@@ -282,7 +282,8 @@ mt76_txq_send_burst(struct mt76_dev *dev, struct mt76_queue *hwq,
 		if (cur_ampdu)
 			mt76_check_agg_ssn(mtxq, skb);
 
-		idx = mt76_dma_tx_queue_skb(dev, hwq, skb, wcid, txq->sta);
+		idx = dev->queue_ops->tx_queue_skb(dev, hwq, skb, wcid,
+						   txq->sta);
 		if (idx < 0)
 			return idx;
 
-- 
cgit v1.2.3


From d20ad58169629f2337e6876dfc30855c5c297cef Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:12 +0200
Subject: mt76: introduce mt76x2-common module

In order to remove usb dependency from pcie code, add mt76x2-common as
a container of shared code between mt76x2 and mt76x2u. Add eeprom code
to mt76x2-common module

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Kconfig         |  5 +++++
 drivers/net/wireless/mediatek/mt76/Makefile        |  6 +++++-
 drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c | 13 +++++++++++--
 drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h |  1 +
 4 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index fc05d79c80d0..1e5c6af6afa2 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -1,9 +1,14 @@
 config MT76_CORE
 	tristate
 
+config MT76x2_COMMON
+	tristate
+	depends on MT76_CORE
+
 config MT76x2E
 	tristate "MediaTek MT76x2E (PCIe) support"
 	select MT76_CORE
+	select MT76x2_COMMON
 	depends on MAC80211
 	depends on PCI
 	---help---
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index a0156bc01dea..57feda501a51 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_MT76_CORE) += mt76.o
+obj-$(CONFIG_MT76x2_COMMON) += mt76x2-common.o
 obj-$(CONFIG_MT76x2E) += mt76x2e.o
 
 mt76-y := \
@@ -6,10 +7,13 @@ mt76-y := \
 
 CFLAGS_trace.o := -I$(src)
 
+mt76x2-common-y := \
+	mt76x2_eeprom.o
+
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
 	mt76x2_main.o mt76x2_init.o mt76x2_debugfs.o mt76x2_tx.o \
-	mt76x2_core.o mt76x2_mac.o mt76x2_eeprom.o mt76x2_mcu.o mt76x2_phy.o \
+	mt76x2_core.o mt76x2_mac.o mt76x2_mcu.o mt76x2_phy.o \
 	mt76x2_dfs.o mt76x2_trace.o
 
 CFLAGS_mt76x2_trace.o := -I$(src)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c
index 95d5f7d888f0..1753bcb36356 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.c
@@ -40,8 +40,7 @@ mt76x2_eeprom_get_macaddr(struct mt76x2_dev *dev)
 	return 0;
 }
 
-static void
-mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev)
+void mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev)
 {
 	u16 val = mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_0);
 
@@ -58,6 +57,7 @@ mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev)
 		break;
 	}
 }
+EXPORT_SYMBOL_GPL(mt76x2_eeprom_parse_hw_cap);
 
 static int
 mt76x2_efuse_read(struct mt76x2_dev *dev, u16 addr, u8 *data)
@@ -415,6 +415,7 @@ void mt76x2_read_rx_gain(struct mt76x2_dev *dev)
 
 	dev->cal.rx.lna_gain = mt76x2_sign_extend(lna, 8);
 }
+EXPORT_SYMBOL_GPL(mt76x2_read_rx_gain);
 
 static s8
 mt76x2_rate_power_val(u8 val)
@@ -482,6 +483,7 @@ void mt76x2_get_rate_power(struct mt76x2_dev *dev, struct mt76_rate_power *t,
 		val >>= 8;
 	t->vht[8] = t->vht[9] = mt76x2_rate_power_val(val >> 8);
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_rate_power);
 
 int mt76x2_get_max_rate_power(struct mt76_rate_power *r)
 {
@@ -493,6 +495,7 @@ int mt76x2_get_max_rate_power(struct mt76_rate_power *r)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_max_rate_power);
 
 static void
 mt76x2_get_power_info_2g(struct mt76x2_dev *dev, struct mt76x2_tx_power_info *t,
@@ -600,6 +603,7 @@ void mt76x2_get_power_info(struct mt76x2_dev *dev,
 	t->delta_bw40 = mt76x2_rate_power_val(bw40);
 	t->delta_bw80 = mt76x2_rate_power_val(bw80);
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_power_info);
 
 int mt76x2_get_temp_comp(struct mt76x2_dev *dev, struct mt76x2_temp_comp *t)
 {
@@ -632,6 +636,7 @@ int mt76x2_get_temp_comp(struct mt76x2_dev *dev, struct mt76x2_temp_comp *t)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt76x2_get_temp_comp);
 
 bool mt76x2_ext_pa_enabled(struct mt76x2_dev *dev, enum nl80211_band band)
 {
@@ -642,6 +647,7 @@ bool mt76x2_ext_pa_enabled(struct mt76x2_dev *dev, enum nl80211_band band)
 	else
 		return !(conf0 & MT_EE_NIC_CONF_0_PA_INT_2G);
 }
+EXPORT_SYMBOL_GPL(mt76x2_ext_pa_enabled);
 
 int mt76x2_eeprom_init(struct mt76x2_dev *dev)
 {
@@ -658,3 +664,6 @@ int mt76x2_eeprom_init(struct mt76x2_dev *dev)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mt76x2_eeprom_init);
+
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h
index aa0b0c040375..0f3e4d2f4fee 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_eeprom.h
@@ -155,6 +155,7 @@ void mt76x2_get_power_info(struct mt76x2_dev *dev,
 int mt76x2_get_temp_comp(struct mt76x2_dev *dev, struct mt76x2_temp_comp *t);
 bool mt76x2_ext_pa_enabled(struct mt76x2_dev *dev, enum nl80211_band band);
 void mt76x2_read_rx_gain(struct mt76x2_dev *dev);
+void mt76x2_eeprom_parse_hw_cap(struct mt76x2_dev *dev);
 
 static inline bool
 mt76x2_temp_tx_alc_enabled(struct mt76x2_dev *dev)
-- 
cgit v1.2.3


From 9367a9c7f956c02a696af111d46e155fb8f2412a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:13 +0200
Subject: mt76: add mt76x2_tx_common to mt76x2-common module

Move tx related code shared between mt76x2 and mt76x2u in mt76x2-common
module

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Makefile        |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2.h        |   2 +
 drivers/net/wireless/mediatek/mt76/mt76x2_tx.c     | 123 -----------------
 .../net/wireless/mediatek/mt76/mt76x2_tx_common.c  | 149 +++++++++++++++++++++
 4 files changed, 152 insertions(+), 124 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2_tx_common.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index 57feda501a51..e1226aae82fa 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -8,7 +8,7 @@ mt76-y := \
 CFLAGS_trace.o := -I$(src)
 
 mt76x2-common-y := \
-	mt76x2_eeprom.o
+	mt76x2_eeprom.o mt76x2_tx_common.o
 
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 896549c2fcbb..af9259cd6d42 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -280,4 +280,6 @@ s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev,
 s8 mt76x2_tx_get_txpwr_adj(struct mt76x2_dev *dev, s8 txpwr, s8 max_txpwr_adj);
 void mt76x2_tx_set_txpwr_auto(struct mt76x2_dev *dev, s8 txpwr);
 
+int mt76x2_insert_hdr_pad(struct sk_buff *skb);
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
index 84a3448ca163..4c907882e8b0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_tx.c
@@ -23,129 +23,6 @@ struct beacon_bc_data {
 	struct sk_buff *tail[8];
 };
 
-void mt76x2_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
-	     struct sk_buff *skb)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct mt76x2_dev *dev = hw->priv;
-	struct ieee80211_vif *vif = info->control.vif;
-	struct mt76_wcid *wcid = &dev->global_wcid;
-
-	if (control->sta) {
-		struct mt76x2_sta *msta;
-
-		msta = (struct mt76x2_sta *) control->sta->drv_priv;
-		wcid = &msta->wcid;
-		/* sw encrypted frames */
-		if (!info->control.hw_key && wcid->hw_key_idx != -1)
-			control->sta = NULL;
-	}
-
-	if (vif && !control->sta) {
-		struct mt76x2_vif *mvif;
-
-		mvif = (struct mt76x2_vif *) vif->drv_priv;
-		wcid = &mvif->group_wcid;
-	}
-
-	mt76_tx(&dev->mt76, control->sta, wcid, skb);
-}
-
-void mt76x2_tx_complete(struct mt76x2_dev *dev, struct sk_buff *skb)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-
-	if (info->flags & IEEE80211_TX_CTL_AMPDU) {
-		ieee80211_free_txskb(mt76_hw(dev), skb);
-	} else {
-		ieee80211_tx_info_clear_status(info);
-		info->status.rates[0].idx = -1;
-		info->flags |= IEEE80211_TX_STAT_ACK;
-		ieee80211_tx_status(mt76_hw(dev), skb);
-	}
-}
-
-s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev,
-			       const struct ieee80211_tx_rate *rate)
-{
-	s8 max_txpwr;
-
-	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
-		u8 mcs = ieee80211_rate_get_vht_mcs(rate);
-
-		if (mcs == 8 || mcs == 9) {
-			max_txpwr = dev->rate_power.vht[8];
-		} else {
-			u8 nss, idx;
-
-			nss = ieee80211_rate_get_vht_nss(rate);
-			idx = ((nss - 1) << 3) + mcs;
-			max_txpwr = dev->rate_power.ht[idx & 0xf];
-		}
-	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
-		max_txpwr = dev->rate_power.ht[rate->idx & 0xf];
-	} else {
-		enum nl80211_band band = dev->mt76.chandef.chan->band;
-
-		if (band == NL80211_BAND_2GHZ) {
-			const struct ieee80211_rate *r;
-			struct wiphy *wiphy = mt76_hw(dev)->wiphy;
-			struct mt76_rate_power *rp = &dev->rate_power;
-
-			r = &wiphy->bands[band]->bitrates[rate->idx];
-			if (r->flags & IEEE80211_RATE_SHORT_PREAMBLE)
-				max_txpwr = rp->cck[r->hw_value & 0x3];
-			else
-				max_txpwr = rp->ofdm[r->hw_value & 0x7];
-		} else {
-			max_txpwr = dev->rate_power.ofdm[rate->idx & 0x7];
-		}
-	}
-
-	return max_txpwr;
-}
-
-s8 mt76x2_tx_get_txpwr_adj(struct mt76x2_dev *dev, s8 txpwr, s8 max_txpwr_adj)
-{
-	txpwr = min_t(s8, txpwr, dev->txpower_conf);
-	txpwr -= (dev->target_power + dev->target_power_delta[0]);
-	txpwr = min_t(s8, txpwr, max_txpwr_adj);
-
-	if (!dev->enable_tpc)
-		return 0;
-	else if (txpwr >= 0)
-		return min_t(s8, txpwr, 7);
-	else
-		return (txpwr < -16) ? 8 : (txpwr + 32) / 2;
-}
-
-void mt76x2_tx_set_txpwr_auto(struct mt76x2_dev *dev, s8 txpwr)
-{
-	s8 txpwr_adj;
-
-	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, txpwr,
-					    dev->rate_power.ofdm[4]);
-	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
-		       MT_PROT_AUTO_TX_CFG_PROT_PADJ, txpwr_adj);
-	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
-		       MT_PROT_AUTO_TX_CFG_AUTO_PADJ, txpwr_adj);
-}
-
-static int mt76x2_insert_hdr_pad(struct sk_buff *skb)
-{
-	int len = ieee80211_get_hdrlen_from_skb(skb);
-
-	if (len % 4 == 0)
-		return 0;
-
-	skb_push(skb, 2);
-	memmove(skb->data, skb->data + 2, len);
-
-	skb->data[len] = 0;
-	skb->data[len + 1] = 0;
-	return 2;
-}
-
 int mt76x2_tx_prepare_skb(struct mt76_dev *mdev, void *txwi,
 			  struct sk_buff *skb, struct mt76_queue *q,
 			  struct mt76_wcid *wcid, struct ieee80211_sta *sta,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_tx_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_tx_common.c
new file mode 100644
index 000000000000..36afb166fa3f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_tx_common.c
@@ -0,0 +1,149 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+#include "mt76x2_dma.h"
+
+void mt76x2_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+	       struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76x2_dev *dev = hw->priv;
+	struct ieee80211_vif *vif = info->control.vif;
+	struct mt76_wcid *wcid = &dev->global_wcid;
+
+	if (control->sta) {
+		struct mt76x2_sta *msta;
+
+		msta = (struct mt76x2_sta *)control->sta->drv_priv;
+		wcid = &msta->wcid;
+		/* sw encrypted frames */
+		if (!info->control.hw_key && wcid->hw_key_idx != -1)
+			control->sta = NULL;
+	}
+
+	if (vif && !control->sta) {
+		struct mt76x2_vif *mvif;
+
+		mvif = (struct mt76x2_vif *)vif->drv_priv;
+		wcid = &mvif->group_wcid;
+	}
+
+	mt76_tx(&dev->mt76, control->sta, wcid, skb);
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx);
+
+int mt76x2_insert_hdr_pad(struct sk_buff *skb)
+{
+	int len = ieee80211_get_hdrlen_from_skb(skb);
+
+	if (len % 4 == 0)
+		return 0;
+
+	skb_push(skb, 2);
+	memmove(skb->data, skb->data + 2, len);
+
+	skb->data[len] = 0;
+	skb->data[len + 1] = 0;
+	return 2;
+}
+EXPORT_SYMBOL_GPL(mt76x2_insert_hdr_pad);
+
+s8 mt76x2_tx_get_max_txpwr_adj(struct mt76x2_dev *dev,
+			       const struct ieee80211_tx_rate *rate)
+{
+	s8 max_txpwr;
+
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		u8 mcs = ieee80211_rate_get_vht_mcs(rate);
+
+		if (mcs == 8 || mcs == 9) {
+			max_txpwr = dev->rate_power.vht[8];
+		} else {
+			u8 nss, idx;
+
+			nss = ieee80211_rate_get_vht_nss(rate);
+			idx = ((nss - 1) << 3) + mcs;
+			max_txpwr = dev->rate_power.ht[idx & 0xf];
+		}
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		max_txpwr = dev->rate_power.ht[rate->idx & 0xf];
+	} else {
+		enum nl80211_band band = dev->mt76.chandef.chan->band;
+
+		if (band == NL80211_BAND_2GHZ) {
+			const struct ieee80211_rate *r;
+			struct wiphy *wiphy = mt76_hw(dev)->wiphy;
+			struct mt76_rate_power *rp = &dev->rate_power;
+
+			r = &wiphy->bands[band]->bitrates[rate->idx];
+			if (r->flags & IEEE80211_RATE_SHORT_PREAMBLE)
+				max_txpwr = rp->cck[r->hw_value & 0x3];
+			else
+				max_txpwr = rp->ofdm[r->hw_value & 0x7];
+		} else {
+			max_txpwr = dev->rate_power.ofdm[rate->idx & 0x7];
+		}
+	}
+
+	return max_txpwr;
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_get_max_txpwr_adj);
+
+s8 mt76x2_tx_get_txpwr_adj(struct mt76x2_dev *dev, s8 txpwr, s8 max_txpwr_adj)
+{
+	txpwr = min_t(s8, txpwr, dev->txpower_conf);
+	txpwr -= (dev->target_power + dev->target_power_delta[0]);
+	txpwr = min_t(s8, txpwr, max_txpwr_adj);
+
+	if (!dev->enable_tpc)
+		return 0;
+	else if (txpwr >= 0)
+		return min_t(s8, txpwr, 7);
+	else
+		return (txpwr < -16) ? 8 : (txpwr + 32) / 2;
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_get_txpwr_adj);
+
+void mt76x2_tx_set_txpwr_auto(struct mt76x2_dev *dev, s8 txpwr)
+{
+	s8 txpwr_adj;
+
+	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, txpwr,
+					    dev->rate_power.ofdm[4]);
+	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
+		       MT_PROT_AUTO_TX_CFG_PROT_PADJ, txpwr_adj);
+	mt76_rmw_field(dev, MT_PROT_AUTO_TX_CFG,
+		       MT_PROT_AUTO_TX_CFG_AUTO_PADJ, txpwr_adj);
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_set_txpwr_auto);
+
+void mt76x2_tx_complete(struct mt76x2_dev *dev, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	if (info->flags & IEEE80211_TX_CTL_AMPDU) {
+		ieee80211_free_txskb(mt76_hw(dev), skb);
+	} else {
+		ieee80211_tx_info_clear_status(info);
+		info->status.rates[0].idx = -1;
+		info->flags |= IEEE80211_TX_STAT_ACK;
+		ieee80211_tx_status(mt76_hw(dev), skb);
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x2_tx_complete);
+
-- 
cgit v1.2.3


From b9c45e1c42b7d709ade99b6ae243065a832e87aa Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:14 +0200
Subject: mt76: add mt76x2_mac_common to mt76x2-common module

Move mac related code shared between mt76x2 and mt76x2u in
mt76x2-common module

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Makefile        |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2.h        |   7 +-
 drivers/net/wireless/mediatek/mt76/mt76x2_init.c   |  35 --
 drivers/net/wireless/mediatek/mt76/mt76x2_mac.c    | 627 ------------------
 .../net/wireless/mediatek/mt76/mt76x2_mac_common.c | 699 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c    |  10 -
 6 files changed, 706 insertions(+), 674 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2_mac_common.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index e1226aae82fa..bedb671200ea 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -8,7 +8,7 @@ mt76-y := \
 CFLAGS_trace.o := -I$(src)
 
 mt76x2-common-y := \
-	mt76x2_eeprom.o mt76x2_tx_common.o
+	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o
 
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index af9259cd6d42..6c5dd106057d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -235,7 +235,7 @@ void mt76x2_phy_set_antenna(struct mt76x2_dev *dev);
 int mt76x2_phy_start(struct mt76x2_dev *dev);
 int mt76x2_phy_set_channel(struct mt76x2_dev *dev,
 			 struct cfg80211_chan_def *chandef);
-int mt76x2_phy_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain);
+int mt76x2_mac_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain);
 void mt76x2_phy_calibrate(struct work_struct *work);
 void mt76x2_phy_set_txpower(struct mt76x2_dev *dev);
 
@@ -282,4 +282,9 @@ void mt76x2_tx_set_txpwr_auto(struct mt76x2_dev *dev, s8 txpwr);
 
 int mt76x2_insert_hdr_pad(struct sk_buff *skb);
 
+bool mt76x2_mac_load_tx_status(struct mt76x2_dev *dev,
+			       struct mt76x2_tx_status *stat);
+void mt76x2_send_tx_status(struct mt76x2_dev *dev,
+			   struct mt76x2_tx_status *stat, u8 *update);
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
index d3eedd9c59b7..309e55cf347c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
@@ -338,41 +338,6 @@ int mt76x2_mac_start(struct mt76x2_dev *dev)
 	return 0;
 }
 
-void mt76x2_mac_stop(struct mt76x2_dev *dev, bool force)
-{
-	bool stopped = false;
-	u32 rts_cfg;
-	int i;
-
-	mt76_wr(dev, MT_MAC_SYS_CTRL, 0);
-
-	rts_cfg = mt76_rr(dev, MT_TX_RTS_CFG);
-	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg & ~MT_TX_RTS_CFG_RETRY_LIMIT);
-
-	/* Wait for MAC to become idle */
-	for (i = 0; i < 300; i++) {
-		if ((mt76_rr(dev, MT_MAC_STATUS) &
-		     (MT_MAC_STATUS_RX | MT_MAC_STATUS_TX)) ||
-		    mt76_rr(dev, MT_BBP(IBI, 12))) {
-			udelay(1);
-			continue;
-		}
-
-		stopped = true;
-		break;
-	}
-
-	if (force && !stopped) {
-		mt76_set(dev, MT_BBP(CORE, 4), BIT(1));
-		mt76_clear(dev, MT_BBP(CORE, 4), BIT(1));
-
-		mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
-		mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
-	}
-
-	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg);
-}
-
 void mt76x2_mac_resume(struct mt76x2_dev *dev)
 {
 	mt76_wr(dev, MT_MAC_SYS_CTRL,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
index 010c1cbfcd6c..23cf437d14f9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac.c
@@ -28,535 +28,6 @@ void mt76x2_mac_set_bssid(struct mt76x2_dev *dev, u8 idx, const u8 *addr)
 		       get_unaligned_le16(addr + 4));
 }
 
-static int
-mt76x2_mac_process_rate(struct mt76_rx_status *status, u16 rate)
-{
-	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
-
-	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
-	case MT_PHY_TYPE_OFDM:
-		if (idx >= 8)
-			idx = 0;
-
-		if (status->band == NL80211_BAND_2GHZ)
-			idx += 4;
-
-		status->rate_idx = idx;
-		return 0;
-	case MT_PHY_TYPE_CCK:
-		if (idx >= 8) {
-			idx -= 8;
-			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
-		}
-
-		if (idx >= 4)
-			idx = 0;
-
-		status->rate_idx = idx;
-		return 0;
-	case MT_PHY_TYPE_HT_GF:
-		status->enc_flags |= RX_ENC_FLAG_HT_GF;
-		/* fall through */
-	case MT_PHY_TYPE_HT:
-		status->encoding = RX_ENC_HT;
-		status->rate_idx = idx;
-		break;
-	case MT_PHY_TYPE_VHT:
-		status->encoding = RX_ENC_VHT;
-		status->rate_idx = FIELD_GET(MT_RATE_INDEX_VHT_IDX, idx);
-		status->nss = FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (rate & MT_RXWI_RATE_LDPC)
-		status->enc_flags |= RX_ENC_FLAG_LDPC;
-
-	if (rate & MT_RXWI_RATE_SGI)
-		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
-
-	if (rate & MT_RXWI_RATE_STBC)
-		status->enc_flags |= 1 << RX_ENC_FLAG_STBC_SHIFT;
-
-	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
-	case MT_PHY_BW_20:
-		break;
-	case MT_PHY_BW_40:
-		status->bw = RATE_INFO_BW_40;
-		break;
-	case MT_PHY_BW_80:
-		status->bw = RATE_INFO_BW_80;
-		break;
-	default:
-		break;
-	}
-
-	return 0;
-}
-
-static __le16
-mt76x2_mac_tx_rate_val(struct mt76x2_dev *dev,
-		       const struct ieee80211_tx_rate *rate, u8 *nss_val)
-{
-	u16 rateval;
-	u8 phy, rate_idx;
-	u8 nss = 1;
-	u8 bw = 0;
-
-	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
-		rate_idx = rate->idx;
-		nss = 1 + (rate->idx >> 4);
-		phy = MT_PHY_TYPE_VHT;
-		if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
-			bw = 2;
-		else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			bw = 1;
-	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
-		rate_idx = rate->idx;
-		nss = 1 + (rate->idx >> 3);
-		phy = MT_PHY_TYPE_HT;
-		if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD)
-			phy = MT_PHY_TYPE_HT_GF;
-		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
-			bw = 1;
-	} else {
-		const struct ieee80211_rate *r;
-		int band = dev->mt76.chandef.chan->band;
-		u16 val;
-
-		r = &mt76_hw(dev)->wiphy->bands[band]->bitrates[rate->idx];
-		if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
-			val = r->hw_value_short;
-		else
-			val = r->hw_value;
-
-		phy = val >> 8;
-		rate_idx = val & 0xff;
-		bw = 0;
-	}
-
-	rateval = FIELD_PREP(MT_RXWI_RATE_INDEX, rate_idx);
-	rateval |= FIELD_PREP(MT_RXWI_RATE_PHY, phy);
-	rateval |= FIELD_PREP(MT_RXWI_RATE_BW, bw);
-	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
-		rateval |= MT_RXWI_RATE_SGI;
-
-	*nss_val = nss;
-	return cpu_to_le16(rateval);
-}
-
-void mt76x2_mac_wcid_set_drop(struct mt76x2_dev *dev, u8 idx, bool drop)
-{
-	u32 val = mt76_rr(dev, MT_WCID_DROP(idx));
-	u32 bit = MT_WCID_DROP_MASK(idx);
-
-	/* prevent unnecessary writes */
-	if ((val & bit) != (bit * drop))
-		mt76_wr(dev, MT_WCID_DROP(idx), (val & ~bit) | (bit * drop));
-}
-
-void mt76x2_mac_wcid_set_rate(struct mt76x2_dev *dev, struct mt76_wcid *wcid,
-			      const struct ieee80211_tx_rate *rate)
-{
-	spin_lock_bh(&dev->mt76.lock);
-	wcid->tx_rate = mt76x2_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
-	wcid->tx_rate_set = true;
-	spin_unlock_bh(&dev->mt76.lock);
-}
-
-void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
-			   struct sk_buff *skb, struct mt76_wcid *wcid,
-			   struct ieee80211_sta *sta, int len)
-{
-	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_tx_rate *rate = &info->control.rates[0];
-	struct ieee80211_key_conf *key = info->control.hw_key;
-	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	u16 rate_ht_mask = FIELD_PREP(MT_RXWI_RATE_PHY, BIT(1) | BIT(2));
-	u16 txwi_flags = 0;
-	u8 nss;
-	s8 txpwr_adj, max_txpwr_adj;
-	u8 ccmp_pn[8];
-
-	memset(txwi, 0, sizeof(*txwi));
-
-	if (wcid)
-		txwi->wcid = wcid->idx;
-	else
-		txwi->wcid = 0xff;
-
-	txwi->pktid = 1;
-
-	if (wcid && wcid->sw_iv && key) {
-		u64 pn = atomic64_inc_return(&key->tx_pn);
-		ccmp_pn[0] = pn;
-		ccmp_pn[1] = pn >> 8;
-		ccmp_pn[2] = 0;
-		ccmp_pn[3] = 0x20 | (key->keyidx << 6);
-		ccmp_pn[4] = pn >> 16;
-		ccmp_pn[5] = pn >> 24;
-		ccmp_pn[6] = pn >> 32;
-		ccmp_pn[7] = pn >> 40;
-		txwi->iv = *((__le32 *)&ccmp_pn[0]);
-		txwi->eiv = *((__le32 *)&ccmp_pn[1]);
-	}
-
-	spin_lock_bh(&dev->mt76.lock);
-	if (wcid && (rate->idx < 0 || !rate->count)) {
-		txwi->rate = wcid->tx_rate;
-		max_txpwr_adj = wcid->max_txpwr_adj;
-		nss = wcid->tx_rate_nss;
-	} else {
-		txwi->rate = mt76x2_mac_tx_rate_val(dev, rate, &nss);
-		max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, rate);
-	}
-	spin_unlock_bh(&dev->mt76.lock);
-
-	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, dev->txpower_conf,
-					    max_txpwr_adj);
-	txwi->ctl2 = FIELD_PREP(MT_TX_PWR_ADJ, txpwr_adj);
-
-	if (mt76xx_rev(dev) >= MT76XX_REV_E4)
-		txwi->txstream = 0x13;
-	else if (mt76xx_rev(dev) >= MT76XX_REV_E3 &&
-		 !(txwi->rate & cpu_to_le16(rate_ht_mask)))
-		txwi->txstream = 0x93;
-
-	if (info->flags & IEEE80211_TX_CTL_LDPC)
-		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_LDPC);
-	if ((info->flags & IEEE80211_TX_CTL_STBC) && nss == 1)
-		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_STBC);
-	if (nss > 1 && sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC)
-		txwi_flags |= MT_TXWI_FLAGS_MMPS;
-	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK))
-		txwi->ack_ctl |= MT_TXWI_ACK_CTL_REQ;
-	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
-		txwi->ack_ctl |= MT_TXWI_ACK_CTL_NSEQ;
-	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
-		txwi->pktid |= MT_TXWI_PKTID_PROBE;
-	if ((info->flags & IEEE80211_TX_CTL_AMPDU) && sta) {
-		u8 ba_size = IEEE80211_MIN_AMPDU_BUF;
-
-		ba_size <<= sta->ht_cap.ampdu_factor;
-		ba_size = min_t(int, 63, ba_size - 1);
-		if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
-			ba_size = 0;
-		txwi->ack_ctl |= FIELD_PREP(MT_TXWI_ACK_CTL_BA_WINDOW, ba_size);
-
-		txwi_flags |= MT_TXWI_FLAGS_AMPDU |
-			 FIELD_PREP(MT_TXWI_FLAGS_MPDU_DENSITY,
-				    sta->ht_cap.ampdu_density);
-	}
-
-	if (ieee80211_is_probe_resp(hdr->frame_control) ||
-	    ieee80211_is_beacon(hdr->frame_control))
-		txwi_flags |= MT_TXWI_FLAGS_TS;
-
-	txwi->flags |= cpu_to_le16(txwi_flags);
-	txwi->len_ctl = cpu_to_le16(len);
-}
-
-static void mt76x2_remove_hdr_pad(struct sk_buff *skb, int len)
-{
-	int hdrlen;
-
-	if (!len)
-		return;
-
-	hdrlen = ieee80211_get_hdrlen_from_skb(skb);
-	memmove(skb->data + len, skb->data, hdrlen);
-	skb_pull(skb, len);
-}
-
-static struct mt76x2_sta *
-mt76x2_rx_get_sta(struct mt76x2_dev *dev, u8 idx)
-{
-	struct mt76_wcid *wcid;
-
-	if (idx >= ARRAY_SIZE(dev->wcid))
-		return NULL;
-
-	wcid = rcu_dereference(dev->wcid[idx]);
-	if (!wcid)
-		return NULL;
-
-	return container_of(wcid, struct mt76x2_sta, wcid);
-}
-
-static struct mt76_wcid *
-mt76x2_rx_get_sta_wcid(struct mt76x2_dev *dev, struct mt76x2_sta *sta, bool unicast)
-{
-	if (!sta)
-		return NULL;
-
-	if (unicast)
-		return &sta->wcid;
-	else
-		return &sta->vif->group_wcid;
-}
-
-int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
-			  void *rxi)
-{
-	struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
-	struct mt76x2_rxwi *rxwi = rxi;
-	struct mt76x2_sta *sta;
-	u32 rxinfo = le32_to_cpu(rxwi->rxinfo);
-	u32 ctl = le32_to_cpu(rxwi->ctl);
-	u16 rate = le16_to_cpu(rxwi->rate);
-	u16 tid_sn = le16_to_cpu(rxwi->tid_sn);
-	bool unicast = rxwi->rxinfo & cpu_to_le32(MT_RXINFO_UNICAST);
-	int pad_len = 0;
-	u8 pn_len;
-	u8 wcid;
-	int len;
-
-	if (!test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
-		return -EINVAL;
-
-	if (rxinfo & MT_RXINFO_L2PAD)
-		pad_len += 2;
-
-	if (rxinfo & MT_RXINFO_DECRYPT) {
-		status->flag |= RX_FLAG_DECRYPTED;
-		status->flag |= RX_FLAG_MMIC_STRIPPED;
-		status->flag |= RX_FLAG_MIC_STRIPPED;
-		status->flag |= RX_FLAG_IV_STRIPPED;
-	}
-
-	wcid = FIELD_GET(MT_RXWI_CTL_WCID, ctl);
-	sta = mt76x2_rx_get_sta(dev, wcid);
-	status->wcid = mt76x2_rx_get_sta_wcid(dev, sta, unicast);
-
-	len = FIELD_GET(MT_RXWI_CTL_MPDU_LEN, ctl);
-	pn_len = FIELD_GET(MT_RXINFO_PN_LEN, rxinfo);
-	if (pn_len) {
-		int offset = ieee80211_get_hdrlen_from_skb(skb) + pad_len;
-		u8 *data = skb->data + offset;
-
-		status->iv[0] = data[7];
-		status->iv[1] = data[6];
-		status->iv[2] = data[5];
-		status->iv[3] = data[4];
-		status->iv[4] = data[1];
-		status->iv[5] = data[0];
-
-		/*
-		 * Driver CCMP validation can't deal with fragments.
-		 * Let mac80211 take care of it.
-		 */
-		if (rxinfo & MT_RXINFO_FRAG) {
-			status->flag &= ~RX_FLAG_IV_STRIPPED;
-		} else {
-			pad_len += pn_len << 2;
-			len -= pn_len << 2;
-		}
-	}
-
-	mt76x2_remove_hdr_pad(skb, pad_len);
-
-	if ((rxinfo & MT_RXINFO_BA) && !(rxinfo & MT_RXINFO_NULL))
-		status->aggr = true;
-
-	if (WARN_ON_ONCE(len > skb->len))
-		return -EINVAL;
-
-	pskb_trim(skb, len);
-	status->chains = BIT(0) | BIT(1);
-	status->chain_signal[0] = mt76x2_phy_get_rssi(dev, rxwi->rssi[0], 0);
-	status->chain_signal[1] = mt76x2_phy_get_rssi(dev, rxwi->rssi[1], 1);
-	status->signal = max(status->chain_signal[0], status->chain_signal[1]);
-	status->freq = dev->mt76.chandef.chan->center_freq;
-	status->band = dev->mt76.chandef.chan->band;
-
-	status->tid = FIELD_GET(MT_RXWI_TID, tid_sn);
-	status->seqno = FIELD_GET(MT_RXWI_SN, tid_sn);
-
-	if (sta) {
-		ewma_signal_add(&sta->rssi, status->signal);
-		sta->inactive_count = 0;
-	}
-
-	return mt76x2_mac_process_rate(status, rate);
-}
-
-static int
-mt76x2_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
-			   enum nl80211_band band)
-{
-	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
-
-	txrate->idx = 0;
-	txrate->flags = 0;
-	txrate->count = 1;
-
-	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
-	case MT_PHY_TYPE_OFDM:
-		if (band == NL80211_BAND_2GHZ)
-			idx += 4;
-
-		txrate->idx = idx;
-		return 0;
-	case MT_PHY_TYPE_CCK:
-		if (idx >= 8)
-			idx -= 8;
-
-		txrate->idx = idx;
-		return 0;
-	case MT_PHY_TYPE_HT_GF:
-		txrate->flags |= IEEE80211_TX_RC_GREEN_FIELD;
-		/* fall through */
-	case MT_PHY_TYPE_HT:
-		txrate->flags |= IEEE80211_TX_RC_MCS;
-		txrate->idx = idx;
-		break;
-	case MT_PHY_TYPE_VHT:
-		txrate->flags |= IEEE80211_TX_RC_VHT_MCS;
-		txrate->idx = idx;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
-	case MT_PHY_BW_20:
-		break;
-	case MT_PHY_BW_40:
-		txrate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
-		break;
-	case MT_PHY_BW_80:
-		txrate->flags |= IEEE80211_TX_RC_80_MHZ_WIDTH;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	if (rate & MT_RXWI_RATE_SGI)
-		txrate->flags |= IEEE80211_TX_RC_SHORT_GI;
-
-	return 0;
-}
-
-static void
-mt76x2_mac_fill_tx_status(struct mt76x2_dev *dev,
-			  struct ieee80211_tx_info *info,
-			  struct mt76x2_tx_status *st, int n_frames)
-{
-	struct ieee80211_tx_rate *rate = info->status.rates;
-	int cur_idx, last_rate;
-	int i;
-
-	if (!n_frames)
-		return;
-
-	last_rate = min_t(int, st->retry, IEEE80211_TX_MAX_RATES - 1);
-	mt76x2_mac_process_tx_rate(&rate[last_rate], st->rate,
-				 dev->mt76.chandef.chan->band);
-	if (last_rate < IEEE80211_TX_MAX_RATES - 1)
-		rate[last_rate + 1].idx = -1;
-
-	cur_idx = rate[last_rate].idx + last_rate;
-	for (i = 0; i <= last_rate; i++) {
-		rate[i].flags = rate[last_rate].flags;
-		rate[i].idx = max_t(int, 0, cur_idx - i);
-		rate[i].count = 1;
-	}
-	rate[last_rate].count = st->retry + 1 - last_rate;
-
-	info->status.ampdu_len = n_frames;
-	info->status.ampdu_ack_len = st->success ? n_frames : 0;
-
-	if (st->pktid & MT_TXWI_PKTID_PROBE)
-		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
-
-	if (st->aggr)
-		info->flags |= IEEE80211_TX_CTL_AMPDU |
-			       IEEE80211_TX_STAT_AMPDU;
-
-	if (!st->ack_req)
-		info->flags |= IEEE80211_TX_CTL_NO_ACK;
-	else if (st->success)
-		info->flags |= IEEE80211_TX_STAT_ACK;
-}
-
-static void
-mt76x2_send_tx_status(struct mt76x2_dev *dev, struct mt76x2_tx_status *stat,
-		      u8 *update)
-{
-	struct ieee80211_tx_info info = {};
-	struct ieee80211_sta *sta = NULL;
-	struct mt76_wcid *wcid = NULL;
-	struct mt76x2_sta *msta = NULL;
-
-	rcu_read_lock();
-	if (stat->wcid < ARRAY_SIZE(dev->wcid))
-		wcid = rcu_dereference(dev->wcid[stat->wcid]);
-
-	if (wcid) {
-		void *priv;
-
-		priv = msta = container_of(wcid, struct mt76x2_sta, wcid);
-		sta = container_of(priv, struct ieee80211_sta,
-				   drv_priv);
-	}
-
-	if (msta && stat->aggr) {
-		u32 stat_val, stat_cache;
-
-		stat_val = stat->rate;
-		stat_val |= ((u32) stat->retry) << 16;
-		stat_cache = msta->status.rate;
-		stat_cache |= ((u32) msta->status.retry) << 16;
-
-		if (*update == 0 && stat_val == stat_cache &&
-		    stat->wcid == msta->status.wcid && msta->n_frames < 32) {
-			msta->n_frames++;
-			goto out;
-		}
-
-		mt76x2_mac_fill_tx_status(dev, &info, &msta->status,
-					  msta->n_frames);
-
-		msta->status = *stat;
-		msta->n_frames = 1;
-		*update = 0;
-	} else {
-		mt76x2_mac_fill_tx_status(dev, &info, stat, 1);
-		*update = 1;
-	}
-
-	ieee80211_tx_status_noskb(mt76_hw(dev), sta, &info);
-
-out:
-	rcu_read_unlock();
-}
-
-static bool
-mt76x2_mac_load_tx_status(struct mt76x2_dev *dev,
-			  struct mt76x2_tx_status *stat)
-{
-	u32 stat1, stat2;
-
-	stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
-	stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
-
-	stat->valid = !!(stat1 & MT_TX_STAT_FIFO_VALID);
-	if (!stat->valid)
-		return false;
-
-	stat->success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
-	stat->aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
-	stat->ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
-	stat->wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
-	stat->rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
-
-	stat->retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
-	stat->pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
-
-	return true;
-}
-
 void mt76x2_mac_poll_tx_status(struct mt76x2_dev *dev, bool irq)
 {
 	struct mt76x2_tx_status stat = {};
@@ -625,104 +96,6 @@ void mt76x2_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
 		dev_kfree_skb_any(e->skb);
 }
 
-static enum mt76x2_cipher_type
-mt76x2_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
-{
-	memset(key_data, 0, 32);
-	if (!key)
-		return MT_CIPHER_NONE;
-
-	if (key->keylen > 32)
-		return MT_CIPHER_NONE;
-
-	memcpy(key_data, key->key, key->keylen);
-
-	switch (key->cipher) {
-	case WLAN_CIPHER_SUITE_WEP40:
-		return MT_CIPHER_WEP40;
-	case WLAN_CIPHER_SUITE_WEP104:
-		return MT_CIPHER_WEP104;
-	case WLAN_CIPHER_SUITE_TKIP:
-		return MT_CIPHER_TKIP;
-	case WLAN_CIPHER_SUITE_CCMP:
-		return MT_CIPHER_AES_CCMP;
-	default:
-		return MT_CIPHER_NONE;
-	}
-}
-
-void mt76x2_mac_wcid_setup(struct mt76x2_dev *dev, u8 idx, u8 vif_idx, u8 *mac)
-{
-	struct mt76_wcid_addr addr = {};
-	u32 attr;
-
-	attr = FIELD_PREP(MT_WCID_ATTR_BSS_IDX, vif_idx & 7) |
-	       FIELD_PREP(MT_WCID_ATTR_BSS_IDX_EXT, !!(vif_idx & 8));
-
-	mt76_wr(dev, MT_WCID_ATTR(idx), attr);
-
-	mt76_wr(dev, MT_WCID_TX_RATE(idx), 0);
-	mt76_wr(dev, MT_WCID_TX_RATE(idx) + 4, 0);
-
-	if (idx >= 128)
-		return;
-
-	if (mac)
-		memcpy(addr.macaddr, mac, ETH_ALEN);
-
-	mt76_wr_copy(dev, MT_WCID_ADDR(idx), &addr, sizeof(addr));
-}
-
-int mt76x2_mac_wcid_set_key(struct mt76x2_dev *dev, u8 idx,
-			    struct ieee80211_key_conf *key)
-{
-	enum mt76x2_cipher_type cipher;
-	u8 key_data[32];
-	u8 iv_data[8];
-
-	cipher = mt76x2_mac_get_key_info(key, key_data);
-	if (cipher == MT_CIPHER_NONE && key)
-		return -EOPNOTSUPP;
-
-	mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PKEY_MODE, cipher);
-	mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data));
-
-	memset(iv_data, 0, sizeof(iv_data));
-	if (key) {
-		mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PAIRWISE,
-			       !!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE));
-		iv_data[3] = key->keyidx << 6;
-		if (cipher >= MT_CIPHER_TKIP)
-			iv_data[3] |= 0x20;
-	}
-
-	mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data));
-
-	return 0;
-}
-
-int mt76x2_mac_shared_key_setup(struct mt76x2_dev *dev, u8 vif_idx, u8 key_idx,
-			      struct ieee80211_key_conf *key)
-{
-	enum mt76x2_cipher_type cipher;
-	u8 key_data[32];
-	u32 val;
-
-	cipher = mt76x2_mac_get_key_info(key, key_data);
-	if (cipher == MT_CIPHER_NONE && key)
-		return -EOPNOTSUPP;
-
-	val = mt76_rr(dev, MT_SKEY_MODE(vif_idx));
-	val &= ~(MT_SKEY_MODE_MASK << MT_SKEY_MODE_SHIFT(vif_idx, key_idx));
-	val |= cipher << MT_SKEY_MODE_SHIFT(vif_idx, key_idx);
-	mt76_wr(dev, MT_SKEY_MODE(vif_idx), val);
-
-	mt76_wr_copy(dev, MT_SKEY(vif_idx, key_idx), key_data,
-		     sizeof(key_data));
-
-	return 0;
-}
-
 static int
 mt76_write_beacon(struct mt76x2_dev *dev, int offset, struct sk_buff *skb)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_mac_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_mac_common.c
new file mode 100644
index 000000000000..6542644bc325
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_mac_common.c
@@ -0,0 +1,699 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+
+void mt76x2_mac_stop(struct mt76x2_dev *dev, bool force)
+{
+	bool stopped = false;
+	u32 rts_cfg;
+	int i;
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL, 0);
+
+	rts_cfg = mt76_rr(dev, MT_TX_RTS_CFG);
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg & ~MT_TX_RTS_CFG_RETRY_LIMIT);
+
+	/* Wait for MAC to become idle */
+	for (i = 0; i < 300; i++) {
+		if ((mt76_rr(dev, MT_MAC_STATUS) &
+		     (MT_MAC_STATUS_RX | MT_MAC_STATUS_TX)) ||
+		    mt76_rr(dev, MT_BBP(IBI, 12))) {
+			udelay(1);
+			continue;
+		}
+
+		stopped = true;
+		break;
+	}
+
+	if (force && !stopped) {
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(1));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(1));
+
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
+	}
+
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_stop);
+
+bool mt76x2_mac_load_tx_status(struct mt76x2_dev *dev,
+			       struct mt76x2_tx_status *stat)
+{
+	u32 stat1, stat2;
+
+	stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
+	stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
+
+	stat->valid = !!(stat1 & MT_TX_STAT_FIFO_VALID);
+	if (!stat->valid)
+		return false;
+
+	stat->success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
+	stat->aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
+	stat->ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
+	stat->wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
+	stat->rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
+
+	stat->retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
+	stat->pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_load_tx_status);
+
+static int
+mt76x2_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
+			   enum nl80211_band band)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	txrate->idx = 0;
+	txrate->flags = 0;
+	txrate->count = 1;
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		txrate->idx = idx;
+		return 0;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8)
+			idx -= 8;
+
+		txrate->idx = idx;
+		return 0;
+	case MT_PHY_TYPE_HT_GF:
+		txrate->flags |= IEEE80211_TX_RC_GREEN_FIELD;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		txrate->flags |= IEEE80211_TX_RC_MCS;
+		txrate->idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		txrate->flags |= IEEE80211_TX_RC_VHT_MCS;
+		txrate->idx = idx;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		txrate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
+		break;
+	case MT_PHY_BW_80:
+		txrate->flags |= IEEE80211_TX_RC_80_MHZ_WIDTH;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (rate & MT_RXWI_RATE_SGI)
+		txrate->flags |= IEEE80211_TX_RC_SHORT_GI;
+
+	return 0;
+}
+
+static void
+mt76x2_mac_fill_tx_status(struct mt76x2_dev *dev,
+			  struct ieee80211_tx_info *info,
+			  struct mt76x2_tx_status *st, int n_frames)
+{
+	struct ieee80211_tx_rate *rate = info->status.rates;
+	int cur_idx, last_rate;
+	int i;
+
+	if (!n_frames)
+		return;
+
+	last_rate = min_t(int, st->retry, IEEE80211_TX_MAX_RATES - 1);
+	mt76x2_mac_process_tx_rate(&rate[last_rate], st->rate,
+				 dev->mt76.chandef.chan->band);
+	if (last_rate < IEEE80211_TX_MAX_RATES - 1)
+		rate[last_rate + 1].idx = -1;
+
+	cur_idx = rate[last_rate].idx + last_rate;
+	for (i = 0; i <= last_rate; i++) {
+		rate[i].flags = rate[last_rate].flags;
+		rate[i].idx = max_t(int, 0, cur_idx - i);
+		rate[i].count = 1;
+	}
+	rate[last_rate].count = st->retry + 1 - last_rate;
+
+	info->status.ampdu_len = n_frames;
+	info->status.ampdu_ack_len = st->success ? n_frames : 0;
+
+	if (st->pktid & MT_TXWI_PKTID_PROBE)
+		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
+
+	if (st->aggr)
+		info->flags |= IEEE80211_TX_CTL_AMPDU |
+			       IEEE80211_TX_STAT_AMPDU;
+
+	if (!st->ack_req)
+		info->flags |= IEEE80211_TX_CTL_NO_ACK;
+	else if (st->success)
+		info->flags |= IEEE80211_TX_STAT_ACK;
+}
+
+void mt76x2_send_tx_status(struct mt76x2_dev *dev,
+			   struct mt76x2_tx_status *stat, u8 *update)
+{
+	struct ieee80211_tx_info info = {};
+	struct ieee80211_sta *sta = NULL;
+	struct mt76_wcid *wcid = NULL;
+	struct mt76x2_sta *msta = NULL;
+
+	rcu_read_lock();
+	if (stat->wcid < ARRAY_SIZE(dev->wcid))
+		wcid = rcu_dereference(dev->wcid[stat->wcid]);
+
+	if (wcid) {
+		void *priv;
+
+		priv = msta = container_of(wcid, struct mt76x2_sta, wcid);
+		sta = container_of(priv, struct ieee80211_sta,
+				   drv_priv);
+	}
+
+	if (msta && stat->aggr) {
+		u32 stat_val, stat_cache;
+
+		stat_val = stat->rate;
+		stat_val |= ((u32) stat->retry) << 16;
+		stat_cache = msta->status.rate;
+		stat_cache |= ((u32) msta->status.retry) << 16;
+
+		if (*update == 0 && stat_val == stat_cache &&
+		    stat->wcid == msta->status.wcid && msta->n_frames < 32) {
+			msta->n_frames++;
+			goto out;
+		}
+
+		mt76x2_mac_fill_tx_status(dev, &info, &msta->status,
+					  msta->n_frames);
+
+		msta->status = *stat;
+		msta->n_frames = 1;
+		*update = 0;
+	} else {
+		mt76x2_mac_fill_tx_status(dev, &info, stat, 1);
+		*update = 1;
+	}
+
+	ieee80211_tx_status_noskb(mt76_hw(dev), sta, &info);
+
+out:
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(mt76x2_send_tx_status);
+
+static enum mt76x2_cipher_type
+mt76x2_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
+{
+	memset(key_data, 0, 32);
+	if (!key)
+		return MT_CIPHER_NONE;
+
+	if (key->keylen > 32)
+		return MT_CIPHER_NONE;
+
+	memcpy(key_data, key->key, key->keylen);
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+		return MT_CIPHER_WEP40;
+	case WLAN_CIPHER_SUITE_WEP104:
+		return MT_CIPHER_WEP104;
+	case WLAN_CIPHER_SUITE_TKIP:
+		return MT_CIPHER_TKIP;
+	case WLAN_CIPHER_SUITE_CCMP:
+		return MT_CIPHER_AES_CCMP;
+	default:
+		return MT_CIPHER_NONE;
+	}
+}
+
+int mt76x2_mac_shared_key_setup(struct mt76x2_dev *dev, u8 vif_idx, u8 key_idx,
+				struct ieee80211_key_conf *key)
+{
+	enum mt76x2_cipher_type cipher;
+	u8 key_data[32];
+	u32 val;
+
+	cipher = mt76x2_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EOPNOTSUPP;
+
+	val = mt76_rr(dev, MT_SKEY_MODE(vif_idx));
+	val &= ~(MT_SKEY_MODE_MASK << MT_SKEY_MODE_SHIFT(vif_idx, key_idx));
+	val |= cipher << MT_SKEY_MODE_SHIFT(vif_idx, key_idx);
+	mt76_wr(dev, MT_SKEY_MODE(vif_idx), val);
+
+	mt76_wr_copy(dev, MT_SKEY(vif_idx, key_idx), key_data,
+		     sizeof(key_data));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_shared_key_setup);
+
+int mt76x2_mac_wcid_set_key(struct mt76x2_dev *dev, u8 idx,
+			    struct ieee80211_key_conf *key)
+{
+	enum mt76x2_cipher_type cipher;
+	u8 key_data[32];
+	u8 iv_data[8];
+
+	cipher = mt76x2_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EOPNOTSUPP;
+
+	mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PKEY_MODE, cipher);
+	mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data));
+
+	memset(iv_data, 0, sizeof(iv_data));
+	if (key) {
+		mt76_rmw_field(dev, MT_WCID_ATTR(idx), MT_WCID_ATTR_PAIRWISE,
+			       !!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE));
+		iv_data[3] = key->keyidx << 6;
+		if (cipher >= MT_CIPHER_TKIP)
+			iv_data[3] |= 0x20;
+	}
+
+	mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_set_key);
+
+static __le16
+mt76x2_mac_tx_rate_val(struct mt76x2_dev *dev,
+		       const struct ieee80211_tx_rate *rate, u8 *nss_val)
+{
+	u16 rateval;
+	u8 phy, rate_idx;
+	u8 nss = 1;
+	u8 bw = 0;
+
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 4);
+		phy = MT_PHY_TYPE_VHT;
+		if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+			bw = 2;
+		else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 3);
+		phy = MT_PHY_TYPE_HT;
+		if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD)
+			phy = MT_PHY_TYPE_HT_GF;
+		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else {
+		const struct ieee80211_rate *r;
+		int band = dev->mt76.chandef.chan->band;
+		u16 val;
+
+		r = &mt76_hw(dev)->wiphy->bands[band]->bitrates[rate->idx];
+		if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
+			val = r->hw_value_short;
+		else
+			val = r->hw_value;
+
+		phy = val >> 8;
+		rate_idx = val & 0xff;
+		bw = 0;
+	}
+
+	rateval = FIELD_PREP(MT_RXWI_RATE_INDEX, rate_idx);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_PHY, phy);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_BW, bw);
+	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+		rateval |= MT_RXWI_RATE_SGI;
+
+	*nss_val = nss;
+	return cpu_to_le16(rateval);
+}
+
+void mt76x2_mac_wcid_set_rate(struct mt76x2_dev *dev, struct mt76_wcid *wcid,
+			      const struct ieee80211_tx_rate *rate)
+{
+	spin_lock_bh(&dev->mt76.lock);
+	wcid->tx_rate = mt76x2_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
+	wcid->tx_rate_set = true;
+	spin_unlock_bh(&dev->mt76.lock);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_set_rate);
+
+void mt76x2_mac_write_txwi(struct mt76x2_dev *dev, struct mt76x2_txwi *txwi,
+			   struct sk_buff *skb, struct mt76_wcid *wcid,
+			   struct ieee80211_sta *sta, int len)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_rate *rate = &info->control.rates[0];
+	struct ieee80211_key_conf *key = info->control.hw_key;
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
+	u16 rate_ht_mask = FIELD_PREP(MT_RXWI_RATE_PHY, BIT(1) | BIT(2));
+	u16 txwi_flags = 0;
+	u8 nss;
+	s8 txpwr_adj, max_txpwr_adj;
+	u8 ccmp_pn[8];
+
+	memset(txwi, 0, sizeof(*txwi));
+
+	if (wcid)
+		txwi->wcid = wcid->idx;
+	else
+		txwi->wcid = 0xff;
+
+	txwi->pktid = 1;
+
+	if (wcid && wcid->sw_iv && key) {
+		u64 pn = atomic64_inc_return(&key->tx_pn);
+		ccmp_pn[0] = pn;
+		ccmp_pn[1] = pn >> 8;
+		ccmp_pn[2] = 0;
+		ccmp_pn[3] = 0x20 | (key->keyidx << 6);
+		ccmp_pn[4] = pn >> 16;
+		ccmp_pn[5] = pn >> 24;
+		ccmp_pn[6] = pn >> 32;
+		ccmp_pn[7] = pn >> 40;
+		txwi->iv = *((__le32 *)&ccmp_pn[0]);
+		txwi->eiv = *((__le32 *)&ccmp_pn[1]);
+	}
+
+	spin_lock_bh(&dev->mt76.lock);
+	if (wcid && (rate->idx < 0 || !rate->count)) {
+		txwi->rate = wcid->tx_rate;
+		max_txpwr_adj = wcid->max_txpwr_adj;
+		nss = wcid->tx_rate_nss;
+	} else {
+		txwi->rate = mt76x2_mac_tx_rate_val(dev, rate, &nss);
+		max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, rate);
+	}
+	spin_unlock_bh(&dev->mt76.lock);
+
+	txpwr_adj = mt76x2_tx_get_txpwr_adj(dev, dev->txpower_conf,
+					    max_txpwr_adj);
+	txwi->ctl2 = FIELD_PREP(MT_TX_PWR_ADJ, txpwr_adj);
+
+	if (mt76xx_rev(dev) >= MT76XX_REV_E4)
+		txwi->txstream = 0x13;
+	else if (mt76xx_rev(dev) >= MT76XX_REV_E3 &&
+		 !(txwi->rate & cpu_to_le16(rate_ht_mask)))
+		txwi->txstream = 0x93;
+
+	if (info->flags & IEEE80211_TX_CTL_LDPC)
+		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_LDPC);
+	if ((info->flags & IEEE80211_TX_CTL_STBC) && nss == 1)
+		txwi->rate |= cpu_to_le16(MT_RXWI_RATE_STBC);
+	if (nss > 1 && sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC)
+		txwi_flags |= MT_TXWI_FLAGS_MMPS;
+	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK))
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_REQ;
+	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_NSEQ;
+	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
+		txwi->pktid |= MT_TXWI_PKTID_PROBE;
+	if ((info->flags & IEEE80211_TX_CTL_AMPDU) && sta) {
+		u8 ba_size = IEEE80211_MIN_AMPDU_BUF;
+
+		ba_size <<= sta->ht_cap.ampdu_factor;
+		ba_size = min_t(int, 63, ba_size - 1);
+		if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
+			ba_size = 0;
+		txwi->ack_ctl |= FIELD_PREP(MT_TXWI_ACK_CTL_BA_WINDOW, ba_size);
+
+		txwi_flags |= MT_TXWI_FLAGS_AMPDU |
+			 FIELD_PREP(MT_TXWI_FLAGS_MPDU_DENSITY,
+				    sta->ht_cap.ampdu_density);
+	}
+
+	if (ieee80211_is_probe_resp(hdr->frame_control) ||
+	    ieee80211_is_beacon(hdr->frame_control))
+		txwi_flags |= MT_TXWI_FLAGS_TS;
+
+	txwi->flags |= cpu_to_le16(txwi_flags);
+	txwi->len_ctl = cpu_to_le16(len);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_write_txwi);
+
+void mt76x2_mac_wcid_set_drop(struct mt76x2_dev *dev, u8 idx, bool drop)
+{
+	u32 val = mt76_rr(dev, MT_WCID_DROP(idx));
+	u32 bit = MT_WCID_DROP_MASK(idx);
+
+	/* prevent unnecessary writes */
+	if ((val & bit) != (bit * drop))
+		mt76_wr(dev, MT_WCID_DROP(idx), (val & ~bit) | (bit * drop));
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_set_drop);
+
+void mt76x2_mac_wcid_setup(struct mt76x2_dev *dev, u8 idx, u8 vif_idx, u8 *mac)
+{
+	struct mt76_wcid_addr addr = {};
+	u32 attr;
+
+	attr = FIELD_PREP(MT_WCID_ATTR_BSS_IDX, vif_idx & 7) |
+	       FIELD_PREP(MT_WCID_ATTR_BSS_IDX_EXT, !!(vif_idx & 8));
+
+	mt76_wr(dev, MT_WCID_ATTR(idx), attr);
+
+	mt76_wr(dev, MT_WCID_TX_RATE(idx), 0);
+	mt76_wr(dev, MT_WCID_TX_RATE(idx) + 4, 0);
+
+	if (idx >= 128)
+		return;
+
+	if (mac)
+		memcpy(addr.macaddr, mac, ETH_ALEN);
+
+	mt76_wr_copy(dev, MT_WCID_ADDR(idx), &addr, sizeof(addr));
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_wcid_setup);
+
+static int
+mt76x2_mac_process_rate(struct mt76_rx_status *status, u16 rate)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (idx >= 8)
+			idx = 0;
+
+		if (status->band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		status->rate_idx = idx;
+		return 0;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8) {
+			idx -= 8;
+			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
+		}
+
+		if (idx >= 4)
+			idx = 0;
+
+		status->rate_idx = idx;
+		return 0;
+	case MT_PHY_TYPE_HT_GF:
+		status->enc_flags |= RX_ENC_FLAG_HT_GF;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		status->encoding = RX_ENC_HT;
+		status->rate_idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		status->encoding = RX_ENC_VHT;
+		status->rate_idx = FIELD_GET(MT_RATE_INDEX_VHT_IDX, idx);
+		status->nss = FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	if (rate & MT_RXWI_RATE_LDPC)
+		status->enc_flags |= RX_ENC_FLAG_LDPC;
+
+	if (rate & MT_RXWI_RATE_SGI)
+		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+	if (rate & MT_RXWI_RATE_STBC)
+		status->enc_flags |= 1 << RX_ENC_FLAG_STBC_SHIFT;
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		status->bw = RATE_INFO_BW_40;
+		break;
+	case MT_PHY_BW_80:
+		status->bw = RATE_INFO_BW_80;
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static void mt76x2_remove_hdr_pad(struct sk_buff *skb, int len)
+{
+	int hdrlen;
+
+	if (!len)
+		return;
+
+	hdrlen = ieee80211_get_hdrlen_from_skb(skb);
+	memmove(skb->data + len, skb->data, hdrlen);
+	skb_pull(skb, len);
+}
+
+int mt76x2_mac_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain)
+{
+	struct mt76x2_rx_freq_cal *cal = &dev->cal.rx;
+
+	rssi += cal->rssi_offset[chain];
+	rssi -= cal->lna_gain;
+
+	return rssi;
+}
+
+static struct mt76x2_sta *
+mt76x2_rx_get_sta(struct mt76x2_dev *dev, u8 idx)
+{
+	struct mt76_wcid *wcid;
+
+	if (idx >= ARRAY_SIZE(dev->wcid))
+		return NULL;
+
+	wcid = rcu_dereference(dev->wcid[idx]);
+	if (!wcid)
+		return NULL;
+
+	return container_of(wcid, struct mt76x2_sta, wcid);
+}
+
+static struct mt76_wcid *
+mt76x2_rx_get_sta_wcid(struct mt76x2_dev *dev, struct mt76x2_sta *sta,
+		       bool unicast)
+{
+	if (!sta)
+		return NULL;
+
+	if (unicast)
+		return &sta->wcid;
+	else
+		return &sta->vif->group_wcid;
+}
+
+int mt76x2_mac_process_rx(struct mt76x2_dev *dev, struct sk_buff *skb,
+			  void *rxi)
+{
+	struct mt76_rx_status *status = (struct mt76_rx_status *) skb->cb;
+	struct mt76x2_rxwi *rxwi = rxi;
+	struct mt76x2_sta *sta;
+	u32 rxinfo = le32_to_cpu(rxwi->rxinfo);
+	u32 ctl = le32_to_cpu(rxwi->ctl);
+	u16 rate = le16_to_cpu(rxwi->rate);
+	u16 tid_sn = le16_to_cpu(rxwi->tid_sn);
+	bool unicast = rxwi->rxinfo & cpu_to_le32(MT_RXINFO_UNICAST);
+	int pad_len = 0;
+	u8 pn_len;
+	u8 wcid;
+	int len;
+
+	if (!test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
+		return -EINVAL;
+
+	if (rxinfo & MT_RXINFO_L2PAD)
+		pad_len += 2;
+
+	if (rxinfo & MT_RXINFO_DECRYPT) {
+		status->flag |= RX_FLAG_DECRYPTED;
+		status->flag |= RX_FLAG_MMIC_STRIPPED;
+		status->flag |= RX_FLAG_MIC_STRIPPED;
+		status->flag |= RX_FLAG_IV_STRIPPED;
+	}
+
+	wcid = FIELD_GET(MT_RXWI_CTL_WCID, ctl);
+	sta = mt76x2_rx_get_sta(dev, wcid);
+	status->wcid = mt76x2_rx_get_sta_wcid(dev, sta, unicast);
+
+	len = FIELD_GET(MT_RXWI_CTL_MPDU_LEN, ctl);
+	pn_len = FIELD_GET(MT_RXINFO_PN_LEN, rxinfo);
+	if (pn_len) {
+		int offset = ieee80211_get_hdrlen_from_skb(skb) + pad_len;
+		u8 *data = skb->data + offset;
+
+		status->iv[0] = data[7];
+		status->iv[1] = data[6];
+		status->iv[2] = data[5];
+		status->iv[3] = data[4];
+		status->iv[4] = data[1];
+		status->iv[5] = data[0];
+
+		/*
+		 * Driver CCMP validation can't deal with fragments.
+		 * Let mac80211 take care of it.
+		 */
+		if (rxinfo & MT_RXINFO_FRAG) {
+			status->flag &= ~RX_FLAG_IV_STRIPPED;
+		} else {
+			pad_len += pn_len << 2;
+			len -= pn_len << 2;
+		}
+	}
+
+	mt76x2_remove_hdr_pad(skb, pad_len);
+
+	if ((rxinfo & MT_RXINFO_BA) && !(rxinfo & MT_RXINFO_NULL))
+		status->aggr = true;
+
+	if (WARN_ON_ONCE(len > skb->len))
+		return -EINVAL;
+
+	pskb_trim(skb, len);
+	status->chains = BIT(0) | BIT(1);
+	status->chain_signal[0] = mt76x2_mac_get_rssi(dev, rxwi->rssi[0], 0);
+	status->chain_signal[1] = mt76x2_mac_get_rssi(dev, rxwi->rssi[1], 1);
+	status->signal = max(status->chain_signal[0], status->chain_signal[1]);
+	status->freq = dev->mt76.chandef.chan->center_freq;
+	status->band = dev->mt76.chandef.chan->band;
+
+	status->tid = FIELD_GET(MT_RXWI_TID, tid_sn);
+	status->seqno = FIELD_GET(MT_RXWI_SN, tid_sn);
+
+	if (sta) {
+		ewma_signal_add(&sta->rssi, status->signal);
+		sta->inactive_count = 0;
+	}
+
+	return mt76x2_mac_process_rate(status, rate);
+}
+EXPORT_SYMBOL_GPL(mt76x2_mac_process_rx);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 9a7b50f0005d..962505bf8fbb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -63,16 +63,6 @@ mt76x2_tx_power_mask(u8 v1, u8 v2, u8 v3, u8 v4)
 	return val;
 }
 
-int mt76x2_phy_get_rssi(struct mt76x2_dev *dev, s8 rssi, int chain)
-{
-	struct mt76x2_rx_freq_cal *cal = &dev->cal.rx;
-
-	rssi += cal->rssi_offset[chain];
-	rssi -= cal->lna_gain;
-
-	return rssi;
-}
-
 static void
 mt76x2_add_rate_power_offset(struct mt76_rate_power *r, int offset)
 {
-- 
cgit v1.2.3


From 43930193a8741a0b7ddcf64c6da1ed4630dcfc51 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:15 +0200
Subject: mt76: add mt76x2_init_common to mt76x2-common module

Move init related code shared between mt76x2 and mt76x2u in
mt76x2-common module

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Makefile        |   3 +-
 drivers/net/wireless/mediatek/mt76/mt76x2.h        |   6 +
 drivers/net/wireless/mediatek/mt76/mt76x2_init.c   | 238 -------------------
 .../wireless/mediatek/mt76/mt76x2_init_common.c    | 259 +++++++++++++++++++++
 4 files changed, 267 insertions(+), 239 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2_init_common.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index bedb671200ea..8342b4d38220 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -8,7 +8,8 @@ mt76-y := \
 CFLAGS_trace.o := -I$(src)
 
 mt76x2-common-y := \
-	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o
+	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o \
+	mt76x2_init_common.o
 
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 6c5dd106057d..556a2961860b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -218,6 +218,8 @@ static inline bool wait_for_wpdma(struct mt76x2_dev *dev)
 
 extern const struct ieee80211_ops mt76x2_ops;
 
+extern struct ieee80211_rate mt76x2_rates[12];
+
 struct mt76x2_dev *mt76x2_alloc_device(struct device *pdev);
 int mt76x2_register_device(struct mt76x2_dev *dev);
 void mt76x2_init_debugfs(struct mt76x2_dev *dev);
@@ -286,5 +288,9 @@ bool mt76x2_mac_load_tx_status(struct mt76x2_dev *dev,
 			       struct mt76x2_tx_status *stat);
 void mt76x2_send_tx_status(struct mt76x2_dev *dev,
 			   struct mt76x2_tx_status *stat, u8 *update);
+void mt76x2_reset_wlan(struct mt76x2_dev *dev, bool enable);
+void mt76x2_init_txpower(struct mt76x2_dev *dev,
+			 struct ieee80211_supported_band *sband);
+void mt76_write_mac_initvals(struct mt76x2_dev *dev);
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
index 309e55cf347c..b814391f79ac 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init.c
@@ -19,11 +19,6 @@
 #include "mt76x2_eeprom.h"
 #include "mt76x2_mcu.h"
 
-struct mt76x2_reg_pair {
-	u32 reg;
-	u32 value;
-};
-
 static void
 mt76x2_mac_pbf_init(struct mt76x2_dev *dev)
 {
@@ -42,113 +37,6 @@ mt76x2_mac_pbf_init(struct mt76x2_dev *dev)
 	mt76_wr(dev, MT_PBF_RX_MAX_PCNT, 0xfebf);
 }
 
-static void
-mt76x2_write_reg_pairs(struct mt76x2_dev *dev,
-		       const struct mt76x2_reg_pair *data, int len)
-{
-	while (len > 0) {
-		mt76_wr(dev, data->reg, data->value);
-		len--;
-		data++;
-	}
-}
-
-static void
-mt76_write_mac_initvals(struct mt76x2_dev *dev)
-{
-#define DEFAULT_PROT_CFG_CCK				\
-	(FIELD_PREP(MT_PROT_CFG_RATE, 0x3) |		\
-	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |		\
-	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
-	 MT_PROT_CFG_RTS_THRESH)
-
-#define DEFAULT_PROT_CFG_OFDM				\
-	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
-	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
-	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
-	 MT_PROT_CFG_RTS_THRESH)
-
-#define DEFAULT_PROT_CFG_20				\
-	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
-	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
-	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
-	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x17))
-
-#define DEFAULT_PROT_CFG_40				\
-	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2084) |		\
-	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
-	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
-	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f))
-
-	static const struct mt76x2_reg_pair vals[] = {
-		/* Copied from MediaTek reference source */
-		{ MT_PBF_SYS_CTRL,		0x00080c00 },
-		{ MT_PBF_CFG,			0x1efebcff },
-		{ MT_FCE_PSE_CTRL,		0x00000001 },
-		{ MT_MAC_SYS_CTRL,		0x0000000c },
-		{ MT_MAX_LEN_CFG,		0x003e3f00 },
-		{ MT_AMPDU_MAX_LEN_20M1S,	0xaaa99887 },
-		{ MT_AMPDU_MAX_LEN_20M2S,	0x000000aa },
-		{ MT_XIFS_TIME_CFG,		0x33a40d0a },
-		{ MT_BKOFF_SLOT_CFG,		0x00000209 },
-		{ MT_TBTT_SYNC_CFG,		0x00422010 },
-		{ MT_PWR_PIN_CFG,		0x00000000 },
-		{ 0x1238,			0x001700c8 },
-		{ MT_TX_SW_CFG0,		0x00101001 },
-		{ MT_TX_SW_CFG1,		0x00010000 },
-		{ MT_TX_SW_CFG2,		0x00000000 },
-		{ MT_TXOP_CTRL_CFG,		0x0400583f },
-		{ MT_TX_RTS_CFG,		0x00100020 },
-		{ MT_TX_TIMEOUT_CFG,		0x000a2290 },
-		{ MT_TX_RETRY_CFG,		0x47f01f0f },
-		{ MT_EXP_ACK_TIME,		0x002c00dc },
-		{ MT_TX_PROT_CFG6,		0xe3f42004 },
-		{ MT_TX_PROT_CFG7,		0xe3f42084 },
-		{ MT_TX_PROT_CFG8,		0xe3f42104 },
-		{ MT_PIFS_TX_CFG,		0x00060fff },
-		{ MT_RX_FILTR_CFG,		0x00015f97 },
-		{ MT_LEGACY_BASIC_RATE,		0x0000017f },
-		{ MT_HT_BASIC_RATE,		0x00004003 },
-		{ MT_PN_PAD_MODE,		0x00000003 },
-		{ MT_TXOP_HLDR_ET,		0x00000002 },
-		{ 0xa44,			0x00000000 },
-		{ MT_HEADER_TRANS_CTRL_REG,	0x00000000 },
-		{ MT_TSO_CTRL,			0x00000000 },
-		{ MT_AUX_CLK_CFG,		0x00000000 },
-		{ MT_DACCLK_EN_DLY_CFG,		0x00000000 },
-		{ MT_TX_ALC_CFG_4,		0x00000000 },
-		{ MT_TX_ALC_VGA3,		0x00000000 },
-		{ MT_TX_PWR_CFG_0,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_1,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_2,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_3,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_4,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_7,		0x3a3a3a3a },
-		{ MT_TX_PWR_CFG_8,		0x0000003a },
-		{ MT_TX_PWR_CFG_9,		0x0000003a },
-		{ MT_EFUSE_CTRL,		0x0000d000 },
-		{ MT_PAUSE_ENABLE_CONTROL1,	0x0000000a },
-		{ MT_FCE_WLAN_FLOW_CONTROL1,	0x60401c18 },
-		{ MT_WPDMA_DELAY_INT_CFG,	0x94ff0000 },
-		{ MT_TX_SW_CFG3,		0x00000004 },
-		{ MT_HT_FBK_TO_LEGACY,		0x00001818 },
-		{ MT_VHT_HT_FBK_CFG1,		0xedcba980 },
-		{ MT_PROT_AUTO_TX_CFG,		0x00830083 },
-		{ MT_HT_CTRL_CFG,		0x000001ff },
-	};
-	struct mt76x2_reg_pair prot_vals[] = {
-		{ MT_CCK_PROT_CFG,		DEFAULT_PROT_CFG_CCK },
-		{ MT_OFDM_PROT_CFG,		DEFAULT_PROT_CFG_OFDM },
-		{ MT_MM20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
-		{ MT_MM40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
-		{ MT_GF20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
-		{ MT_GF40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
-	};
-
-	mt76x2_write_reg_pairs(dev, vals, ARRAY_SIZE(vals));
-	mt76x2_write_reg_pairs(dev, prot_vals, ARRAY_SIZE(prot_vals));
-}
-
 static void
 mt76x2_fixup_xtal(struct mt76x2_dev *dev)
 {
@@ -441,45 +329,6 @@ void mt76x2_set_tx_ackto(struct mt76x2_dev *dev)
 		       MT_TX_TIMEOUT_CFG_ACKTO, ackto);
 }
 
-static void
-mt76x2_set_wlan_state(struct mt76x2_dev *dev, bool enable)
-{
-	u32 val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
-
-	if (enable)
-		val |= (MT_WLAN_FUN_CTRL_WLAN_EN |
-			MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
-	else
-		val &= ~(MT_WLAN_FUN_CTRL_WLAN_EN |
-			 MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
-
-	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
-	udelay(20);
-}
-
-static void
-mt76x2_reset_wlan(struct mt76x2_dev *dev, bool enable)
-{
-	u32 val;
-
-	val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
-
-	val &= ~MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL;
-
-	if (val & MT_WLAN_FUN_CTRL_WLAN_EN) {
-		val |= MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
-		mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
-		udelay(20);
-
-		val &= ~MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
-	}
-
-	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
-	udelay(20);
-
-	mt76x2_set_wlan_state(dev, enable);
-}
-
 int mt76x2_init_hardware(struct mt76x2_dev *dev)
 {
 	static const u16 beacon_offsets[16] = {
@@ -601,34 +450,6 @@ static void mt76x2_regd_notifier(struct wiphy *wiphy,
 	mt76x2_dfs_set_domain(dev, request->dfs_region);
 }
 
-#define CCK_RATE(_idx, _rate) {					\
-	.bitrate = _rate,					\
-	.flags = IEEE80211_RATE_SHORT_PREAMBLE,			\
-	.hw_value = (MT_PHY_TYPE_CCK << 8) | _idx,		\
-	.hw_value_short = (MT_PHY_TYPE_CCK << 8) | (8 + _idx),	\
-}
-
-#define OFDM_RATE(_idx, _rate) {				\
-	.bitrate = _rate,					\
-	.hw_value = (MT_PHY_TYPE_OFDM << 8) | _idx,		\
-	.hw_value_short = (MT_PHY_TYPE_OFDM << 8) | _idx,	\
-}
-
-static struct ieee80211_rate mt76x2_rates[] = {
-	CCK_RATE(0, 10),
-	CCK_RATE(1, 20),
-	CCK_RATE(2, 55),
-	CCK_RATE(3, 110),
-	OFDM_RATE(0, 60),
-	OFDM_RATE(1, 90),
-	OFDM_RATE(2, 120),
-	OFDM_RATE(3, 180),
-	OFDM_RATE(4, 240),
-	OFDM_RATE(5, 360),
-	OFDM_RATE(6, 480),
-	OFDM_RATE(7, 540),
-};
-
 static const struct ieee80211_iface_limit if_limits[] = {
 	{
 		.max = 1,
@@ -705,65 +526,6 @@ static void mt76x2_led_set_brightness(struct led_classdev *led_cdev,
 		mt76x2_led_set_config(mt76, 0xff, 0);
 }
 
-static void
-mt76x2_init_txpower(struct mt76x2_dev *dev,
-		    struct ieee80211_supported_band *sband)
-{
-	struct ieee80211_channel *chan;
-	struct mt76x2_tx_power_info txp;
-	struct mt76_rate_power t = {};
-	int target_power;
-	int i;
-
-	for (i = 0; i < sband->n_channels; i++) {
-		chan = &sband->channels[i];
-
-		mt76x2_get_power_info(dev, &txp, chan);
-
-		target_power = max_t(int, (txp.chain[0].target_power +
-					   txp.chain[0].delta),
-					  (txp.chain[1].target_power +
-					   txp.chain[1].delta));
-
-		mt76x2_get_rate_power(dev, &t, chan);
-
-		chan->max_power = mt76x2_get_max_rate_power(&t) +
-				  target_power;
-		chan->max_power /= 2;
-
-		/* convert to combined output power on 2x2 devices */
-		chan->max_power += 3;
-	}
-}
-
-void mt76x2_init_device(struct mt76x2_dev *dev)
-{
-	struct ieee80211_hw *hw = mt76_hw(dev);
-
-	hw->queues = 4;
-	hw->max_rates = 1;
-	hw->max_report_rates = 7;
-	hw->max_rate_tries = 1;
-	hw->extra_tx_headroom = 2;
-
-	hw->sta_data_size = sizeof(struct mt76x2_sta);
-	hw->vif_data_size = sizeof(struct mt76x2_vif);
-
-	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
-	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
-
-	dev->mt76.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
-	dev->mt76.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
-
-	dev->chainmask = 0x202;
-	dev->global_wcid.idx = 255;
-	dev->global_wcid.hw_key_idx = -1;
-	dev->slottime = 9;
-
-	/* init antenna configuration */
-	dev->mt76.antenna_mask = 3;
-}
-
 int mt76x2_register_device(struct mt76x2_dev *dev)
 {
 	struct ieee80211_hw *hw = mt76_hw(dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_init_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_init_common.c
new file mode 100644
index 000000000000..324b2a4b8b67
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_init_common.c
@@ -0,0 +1,259 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+#include "mt76x2_eeprom.h"
+
+#define CCK_RATE(_idx, _rate) {					\
+	.bitrate = _rate,					\
+	.flags = IEEE80211_RATE_SHORT_PREAMBLE,			\
+	.hw_value = (MT_PHY_TYPE_CCK << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_CCK << 8) | (8 + _idx),	\
+}
+
+#define OFDM_RATE(_idx, _rate) {				\
+	.bitrate = _rate,					\
+	.hw_value = (MT_PHY_TYPE_OFDM << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_OFDM << 8) | _idx,	\
+}
+
+struct ieee80211_rate mt76x2_rates[] = {
+	CCK_RATE(0, 10),
+	CCK_RATE(1, 20),
+	CCK_RATE(2, 55),
+	CCK_RATE(3, 110),
+	OFDM_RATE(0, 60),
+	OFDM_RATE(1, 90),
+	OFDM_RATE(2, 120),
+	OFDM_RATE(3, 180),
+	OFDM_RATE(4, 240),
+	OFDM_RATE(5, 360),
+	OFDM_RATE(6, 480),
+	OFDM_RATE(7, 540),
+};
+EXPORT_SYMBOL_GPL(mt76x2_rates);
+
+struct mt76x2_reg_pair {
+	u32 reg;
+	u32 value;
+};
+
+static void
+mt76x2_set_wlan_state(struct mt76x2_dev *dev, bool enable)
+{
+	u32 val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
+
+	if (enable)
+		val |= (MT_WLAN_FUN_CTRL_WLAN_EN |
+			MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
+	else
+		val &= ~(MT_WLAN_FUN_CTRL_WLAN_EN |
+			 MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+}
+
+void mt76x2_reset_wlan(struct mt76x2_dev *dev, bool enable)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
+
+	val &= ~MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL;
+
+	if (val & MT_WLAN_FUN_CTRL_WLAN_EN) {
+		val |= MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
+		mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+		udelay(20);
+
+		val &= ~MT_WLAN_FUN_CTRL_WLAN_RESET_RF;
+	}
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+
+	mt76x2_set_wlan_state(dev, enable);
+}
+EXPORT_SYMBOL_GPL(mt76x2_reset_wlan);
+
+static void
+mt76x2_write_reg_pairs(struct mt76x2_dev *dev,
+		       const struct mt76x2_reg_pair *data, int len)
+{
+	while (len > 0) {
+		mt76_wr(dev, data->reg, data->value);
+		len--;
+		data++;
+	}
+}
+
+void mt76_write_mac_initvals(struct mt76x2_dev *dev)
+{
+#define DEFAULT_PROT_CFG_CCK				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x3) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |		\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
+	 MT_PROT_CFG_RTS_THRESH)
+
+#define DEFAULT_PROT_CFG_OFDM				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f) |	\
+	 MT_PROT_CFG_RTS_THRESH)
+
+#define DEFAULT_PROT_CFG_20				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2004) |		\
+	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x17))
+
+#define DEFAULT_PROT_CFG_40				\
+	(FIELD_PREP(MT_PROT_CFG_RATE, 0x2084) |		\
+	 FIELD_PREP(MT_PROT_CFG_CTRL, 1) |		\
+	 FIELD_PREP(MT_PROT_CFG_NAV, 1) |			\
+	 FIELD_PREP(MT_PROT_CFG_TXOP_ALLOW, 0x3f))
+
+	static const struct mt76x2_reg_pair vals[] = {
+		/* Copied from MediaTek reference source */
+		{ MT_PBF_SYS_CTRL,		0x00080c00 },
+		{ MT_PBF_CFG,			0x1efebcff },
+		{ MT_FCE_PSE_CTRL,		0x00000001 },
+		{ MT_MAC_SYS_CTRL,		0x0000000c },
+		{ MT_MAX_LEN_CFG,		0x003e3f00 },
+		{ MT_AMPDU_MAX_LEN_20M1S,	0xaaa99887 },
+		{ MT_AMPDU_MAX_LEN_20M2S,	0x000000aa },
+		{ MT_XIFS_TIME_CFG,		0x33a40d0a },
+		{ MT_BKOFF_SLOT_CFG,		0x00000209 },
+		{ MT_TBTT_SYNC_CFG,		0x00422010 },
+		{ MT_PWR_PIN_CFG,		0x00000000 },
+		{ 0x1238,			0x001700c8 },
+		{ MT_TX_SW_CFG0,		0x00101001 },
+		{ MT_TX_SW_CFG1,		0x00010000 },
+		{ MT_TX_SW_CFG2,		0x00000000 },
+		{ MT_TXOP_CTRL_CFG,		0x0400583f },
+		{ MT_TX_RTS_CFG,		0x00100020 },
+		{ MT_TX_TIMEOUT_CFG,		0x000a2290 },
+		{ MT_TX_RETRY_CFG,		0x47f01f0f },
+		{ MT_EXP_ACK_TIME,		0x002c00dc },
+		{ MT_TX_PROT_CFG6,		0xe3f42004 },
+		{ MT_TX_PROT_CFG7,		0xe3f42084 },
+		{ MT_TX_PROT_CFG8,		0xe3f42104 },
+		{ MT_PIFS_TX_CFG,		0x00060fff },
+		{ MT_RX_FILTR_CFG,		0x00015f97 },
+		{ MT_LEGACY_BASIC_RATE,		0x0000017f },
+		{ MT_HT_BASIC_RATE,		0x00004003 },
+		{ MT_PN_PAD_MODE,		0x00000003 },
+		{ MT_TXOP_HLDR_ET,		0x00000002 },
+		{ 0xa44,			0x00000000 },
+		{ MT_HEADER_TRANS_CTRL_REG,	0x00000000 },
+		{ MT_TSO_CTRL,			0x00000000 },
+		{ MT_AUX_CLK_CFG,		0x00000000 },
+		{ MT_DACCLK_EN_DLY_CFG,		0x00000000 },
+		{ MT_TX_ALC_CFG_4,		0x00000000 },
+		{ MT_TX_ALC_VGA3,		0x00000000 },
+		{ MT_TX_PWR_CFG_0,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_1,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_2,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_3,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_4,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_7,		0x3a3a3a3a },
+		{ MT_TX_PWR_CFG_8,		0x0000003a },
+		{ MT_TX_PWR_CFG_9,		0x0000003a },
+		{ MT_EFUSE_CTRL,		0x0000d000 },
+		{ MT_PAUSE_ENABLE_CONTROL1,	0x0000000a },
+		{ MT_FCE_WLAN_FLOW_CONTROL1,	0x60401c18 },
+		{ MT_WPDMA_DELAY_INT_CFG,	0x94ff0000 },
+		{ MT_TX_SW_CFG3,		0x00000004 },
+		{ MT_HT_FBK_TO_LEGACY,		0x00001818 },
+		{ MT_VHT_HT_FBK_CFG1,		0xedcba980 },
+		{ MT_PROT_AUTO_TX_CFG,		0x00830083 },
+		{ MT_HT_CTRL_CFG,		0x000001ff },
+	};
+	struct mt76x2_reg_pair prot_vals[] = {
+		{ MT_CCK_PROT_CFG,		DEFAULT_PROT_CFG_CCK },
+		{ MT_OFDM_PROT_CFG,		DEFAULT_PROT_CFG_OFDM },
+		{ MT_MM20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
+		{ MT_MM40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
+		{ MT_GF20_PROT_CFG,		DEFAULT_PROT_CFG_20 },
+		{ MT_GF40_PROT_CFG,		DEFAULT_PROT_CFG_40 },
+	};
+
+	mt76x2_write_reg_pairs(dev, vals, ARRAY_SIZE(vals));
+	mt76x2_write_reg_pairs(dev, prot_vals, ARRAY_SIZE(prot_vals));
+}
+EXPORT_SYMBOL_GPL(mt76_write_mac_initvals);
+
+void mt76x2_init_device(struct mt76x2_dev *dev)
+{
+	struct ieee80211_hw *hw = mt76_hw(dev);
+
+	hw->queues = 4;
+	hw->max_rates = 1;
+	hw->max_report_rates = 7;
+	hw->max_rate_tries = 1;
+	hw->extra_tx_headroom = 2;
+
+	hw->sta_data_size = sizeof(struct mt76x2_sta);
+	hw->vif_data_size = sizeof(struct mt76x2_vif);
+
+	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
+	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
+
+	dev->mt76.sband_2g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
+	dev->mt76.sband_5g.sband.ht_cap.cap |= IEEE80211_HT_CAP_LDPC_CODING;
+
+	dev->chainmask = 0x202;
+	dev->global_wcid.idx = 255;
+	dev->global_wcid.hw_key_idx = -1;
+	dev->slottime = 9;
+
+	/* init antenna configuration */
+	dev->mt76.antenna_mask = 3;
+}
+EXPORT_SYMBOL_GPL(mt76x2_init_device);
+
+void mt76x2_init_txpower(struct mt76x2_dev *dev,
+			 struct ieee80211_supported_band *sband)
+{
+	struct ieee80211_channel *chan;
+	struct mt76x2_tx_power_info txp;
+	struct mt76_rate_power t = {};
+	int target_power;
+	int i;
+
+	for (i = 0; i < sband->n_channels; i++) {
+		chan = &sband->channels[i];
+
+		mt76x2_get_power_info(dev, &txp, chan);
+
+		target_power = max_t(int, (txp.chain[0].target_power +
+					   txp.chain[0].delta),
+					  (txp.chain[1].target_power +
+					   txp.chain[1].delta));
+
+		mt76x2_get_rate_power(dev, &t, chan);
+
+		chan->max_power = mt76x2_get_max_rate_power(&t) +
+				  target_power;
+		chan->max_power /= 2;
+
+		/* convert to combined output power on 2x2 devices */
+		chan->max_power += 3;
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x2_init_txpower);
-- 
cgit v1.2.3


From 2de8c3eb7ed7a450e19b0edfa51f2acd6a81ec40 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:16 +0200
Subject: mt76: add mt76x2_common to mt76x2-common module

Move core related code shared between mt76x2 and mt76x2u in
mt76x2-common module

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Makefile        |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2.h        |  21 ++
 drivers/net/wireless/mediatek/mt76/mt76x2_common.c | 350 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2_dma.c    |  21 --
 drivers/net/wireless/mediatek/mt76/mt76x2_main.c   | 307 ------------------
 5 files changed, 372 insertions(+), 329 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2_common.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index 8342b4d38220..a184e16a5d54 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -9,7 +9,7 @@ CFLAGS_trace.o := -I$(src)
 
 mt76x2-common-y := \
 	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o \
-	mt76x2_init_common.o
+	mt76x2_init_common.o mt76x2_common.o
 
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 556a2961860b..0c129d6a9466 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -293,4 +293,25 @@ void mt76x2_init_txpower(struct mt76x2_dev *dev,
 			 struct ieee80211_supported_band *sband);
 void mt76_write_mac_initvals(struct mt76x2_dev *dev);
 
+int mt76x2_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			struct ieee80211_ampdu_params *params);
+int mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta);
+int mt76x2_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct ieee80211_sta *sta);
+void mt76x2_remove_interface(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif);
+int mt76x2_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
+		   struct ieee80211_vif *vif, struct ieee80211_sta *sta,
+		   struct ieee80211_key_conf *key);
+int mt76x2_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   u16 queue, const struct ieee80211_tx_queue_params *params);
+void mt76x2_configure_filter(struct ieee80211_hw *hw,
+			     unsigned int changed_flags,
+			     unsigned int *total_flags, u64 multicast);
+void mt76x2_txq_init(struct mt76x2_dev *dev, struct ieee80211_txq *txq);
+void mt76x2_sta_rate_tbl_update(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				struct ieee80211_sta *sta);
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_common.c
new file mode 100644
index 000000000000..a2338ba139b4
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_common.c
@@ -0,0 +1,350 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+
+void mt76x2_txq_init(struct mt76x2_dev *dev, struct ieee80211_txq *txq)
+{
+	struct mt76_txq *mtxq;
+
+	if (!txq)
+		return;
+
+	mtxq = (struct mt76_txq *) txq->drv_priv;
+	if (txq->sta) {
+		struct mt76x2_sta *sta;
+
+		sta = (struct mt76x2_sta *) txq->sta->drv_priv;
+		mtxq->wcid = &sta->wcid;
+	} else {
+		struct mt76x2_vif *mvif;
+
+		mvif = (struct mt76x2_vif *) txq->vif->drv_priv;
+		mtxq->wcid = &mvif->group_wcid;
+	}
+
+	mt76_txq_init(&dev->mt76, txq);
+}
+EXPORT_SYMBOL_GPL(mt76x2_txq_init);
+
+int mt76x2_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			struct ieee80211_ampdu_params *params)
+{
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	struct ieee80211_sta *sta = params->sta;
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	struct ieee80211_txq *txq = sta->txq[params->tid];
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	struct mt76_txq *mtxq;
+
+	if (!txq)
+		return -EINVAL;
+
+	mtxq = (struct mt76_txq *)txq->drv_priv;
+
+	switch (action) {
+	case IEEE80211_AMPDU_RX_START:
+		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, *ssn, params->buf_size);
+		mt76_set(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_RX_STOP:
+		mt76_rx_aggr_stop(&dev->mt76, &msta->wcid, tid);
+		mt76_clear(dev, MT_WCID_ADDR(msta->wcid.idx) + 4,
+			   BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_TX_OPERATIONAL:
+		mtxq->aggr = true;
+		mtxq->send_bar = false;
+		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_FLUSH:
+	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
+		mtxq->aggr = false;
+		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
+		break;
+	case IEEE80211_AMPDU_TX_START:
+		mtxq->agg_ssn = *ssn << 4;
+		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_CONT:
+		mtxq->aggr = false;
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_ampdu_action);
+
+int mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
+	int ret = 0;
+	int idx = 0;
+	int i;
+
+	mutex_lock(&dev->mutex);
+
+	idx = mt76_wcid_alloc(dev->wcid_mask, ARRAY_SIZE(dev->wcid));
+	if (idx < 0) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	msta->vif = mvif;
+	msta->wcid.sta = 1;
+	msta->wcid.idx = idx;
+	msta->wcid.hw_key_idx = -1;
+	mt76x2_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
+	mt76x2_mac_wcid_set_drop(dev, idx, false);
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		mt76x2_txq_init(dev, sta->txq[i]);
+
+	if (vif->type == NL80211_IFTYPE_AP)
+		set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
+
+	ewma_signal_init(&msta->rssi);
+
+	rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
+
+out:
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76x2_sta_add);
+
+int mt76x2_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct ieee80211_sta *sta)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	int idx = msta->wcid.idx;
+	int i;
+
+	mutex_lock(&dev->mutex);
+	rcu_assign_pointer(dev->wcid[idx], NULL);
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		mt76_txq_remove(&dev->mt76, sta->txq[i]);
+	mt76x2_mac_wcid_set_drop(dev, idx, true);
+	mt76_wcid_free(dev->wcid_mask, idx);
+	mt76x2_mac_wcid_setup(dev, idx, 0, NULL);
+	mutex_unlock(&dev->mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_sta_remove);
+
+void mt76x2_remove_interface(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	mt76_txq_remove(&dev->mt76, vif->txq);
+}
+EXPORT_SYMBOL_GPL(mt76x2_remove_interface);
+
+int mt76x2_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
+		   struct ieee80211_vif *vif, struct ieee80211_sta *sta,
+		   struct ieee80211_key_conf *key)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
+	struct mt76x2_sta *msta;
+	struct mt76_wcid *wcid;
+	int idx = key->keyidx;
+	int ret;
+
+	/* fall back to sw encryption for unsupported ciphers */
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+	case WLAN_CIPHER_SUITE_WEP104:
+	case WLAN_CIPHER_SUITE_TKIP:
+	case WLAN_CIPHER_SUITE_CCMP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	/*
+	 * The hardware does not support per-STA RX GTK, fall back
+	 * to software mode for these.
+	 */
+	if ((vif->type == NL80211_IFTYPE_ADHOC ||
+	     vif->type == NL80211_IFTYPE_MESH_POINT) &&
+	    (key->cipher == WLAN_CIPHER_SUITE_TKIP ||
+	     key->cipher == WLAN_CIPHER_SUITE_CCMP) &&
+	    !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE))
+		return -EOPNOTSUPP;
+
+	msta = sta ? (struct mt76x2_sta *) sta->drv_priv : NULL;
+	wcid = msta ? &msta->wcid : &mvif->group_wcid;
+
+	if (cmd == SET_KEY) {
+		key->hw_key_idx = wcid->idx;
+		wcid->hw_key_idx = idx;
+		if (key->flags & IEEE80211_KEY_FLAG_RX_MGMT) {
+			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
+			wcid->sw_iv = true;
+		}
+	} else {
+		if (idx == wcid->hw_key_idx) {
+			wcid->hw_key_idx = -1;
+			wcid->sw_iv = true;
+		}
+
+		key = NULL;
+	}
+	mt76_wcid_key_setup(&dev->mt76, wcid, key);
+
+	if (!msta) {
+		if (key || wcid->hw_key_idx == idx) {
+			ret = mt76x2_mac_wcid_set_key(dev, wcid->idx, key);
+			if (ret)
+				return ret;
+		}
+
+		return mt76x2_mac_shared_key_setup(dev, mvif->idx, idx, key);
+	}
+
+	return mt76x2_mac_wcid_set_key(dev, msta->wcid.idx, key);
+}
+EXPORT_SYMBOL_GPL(mt76x2_set_key);
+
+int mt76x2_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   u16 queue, const struct ieee80211_tx_queue_params *params)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	u8 cw_min = 5, cw_max = 10, qid;
+	u32 val;
+
+	qid = dev->mt76.q_tx[queue].hw_idx;
+
+	if (params->cw_min)
+		cw_min = fls(params->cw_min);
+	if (params->cw_max)
+		cw_max = fls(params->cw_max);
+
+	val = FIELD_PREP(MT_EDCA_CFG_TXOP, params->txop) |
+	      FIELD_PREP(MT_EDCA_CFG_AIFSN, params->aifs) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMIN, cw_min) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMAX, cw_max);
+	mt76_wr(dev, MT_EDCA_CFG_AC(qid), val);
+
+	val = mt76_rr(dev, MT_WMM_TXOP(qid));
+	val &= ~(MT_WMM_TXOP_MASK << MT_WMM_TXOP_SHIFT(qid));
+	val |= params->txop << MT_WMM_TXOP_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_TXOP(qid), val);
+
+	val = mt76_rr(dev, MT_WMM_AIFSN);
+	val &= ~(MT_WMM_AIFSN_MASK << MT_WMM_AIFSN_SHIFT(qid));
+	val |= params->aifs << MT_WMM_AIFSN_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_AIFSN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMIN);
+	val &= ~(MT_WMM_CWMIN_MASK << MT_WMM_CWMIN_SHIFT(qid));
+	val |= cw_min << MT_WMM_CWMIN_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_CWMIN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMAX);
+	val &= ~(MT_WMM_CWMAX_MASK << MT_WMM_CWMAX_SHIFT(qid));
+	val |= cw_max << MT_WMM_CWMAX_SHIFT(qid);
+	mt76_wr(dev, MT_WMM_CWMAX, val);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76x2_conf_tx);
+
+void mt76x2_configure_filter(struct ieee80211_hw *hw,
+			     unsigned int changed_flags,
+			     unsigned int *total_flags, u64 multicast)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	u32 flags = 0;
+
+#define MT76_FILTER(_flag, _hw) do { \
+		flags |= *total_flags & FIF_##_flag;			\
+		dev->rxfilter &= ~(_hw);				\
+		dev->rxfilter |= !(flags & FIF_##_flag) * (_hw);	\
+	} while (0)
+
+	mutex_lock(&dev->mutex);
+
+	dev->rxfilter &= ~MT_RX_FILTR_CFG_OTHER_BSS;
+
+	MT76_FILTER(FCSFAIL, MT_RX_FILTR_CFG_CRC_ERR);
+	MT76_FILTER(PLCPFAIL, MT_RX_FILTR_CFG_PHY_ERR);
+	MT76_FILTER(CONTROL, MT_RX_FILTR_CFG_ACK |
+			     MT_RX_FILTR_CFG_CTS |
+			     MT_RX_FILTR_CFG_CFEND |
+			     MT_RX_FILTR_CFG_CFACK |
+			     MT_RX_FILTR_CFG_BA |
+			     MT_RX_FILTR_CFG_CTRL_RSV);
+	MT76_FILTER(PSPOLL, MT_RX_FILTR_CFG_PSPOLL);
+
+	*total_flags = flags;
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mutex_unlock(&dev->mutex);
+}
+EXPORT_SYMBOL_GPL(mt76x2_configure_filter);
+
+void mt76x2_sta_rate_tbl_update(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				struct ieee80211_sta *sta)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
+	struct ieee80211_sta_rates *rates = rcu_dereference(sta->rates);
+	struct ieee80211_tx_rate rate = {};
+
+	if (!rates)
+		return;
+
+	rate.idx = rates->rate[0].idx;
+	rate.flags = rates->rate[0].flags;
+	mt76x2_mac_wcid_set_rate(dev, &msta->wcid, &rate);
+	msta->wcid.max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, &rate);
+}
+EXPORT_SYMBOL_GPL(mt76x2_sta_rate_tbl_update);
+
+void mt76x2_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
+			 struct sk_buff *skb)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+	void *rxwi = skb->data;
+
+	if (q == MT_RXQ_MCU) {
+		skb_queue_tail(&dev->mcu.res_q, skb);
+		wake_up(&dev->mcu.wait);
+		return;
+	}
+
+	skb_pull(skb, sizeof(struct mt76x2_rxwi));
+	if (mt76x2_mac_process_rx(dev, skb, rxwi)) {
+		dev_kfree_skb(skb);
+		return;
+	}
+
+	mt76_rx(&dev->mt76, q, skb);
+}
+EXPORT_SYMBOL_GPL(mt76x2_queue_rx_skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c
index fd1ec4743e0b..6720a6a1313f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_dma.c
@@ -66,27 +66,6 @@ mt76x2_init_tx_queue(struct mt76x2_dev *dev, struct mt76_queue *q,
 	return 0;
 }
 
-void mt76x2_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
-			 struct sk_buff *skb)
-{
-	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
-	void *rxwi = skb->data;
-
-	if (q == MT_RXQ_MCU) {
-		skb_queue_tail(&dev->mcu.res_q, skb);
-		wake_up(&dev->mcu.wait);
-		return;
-	}
-
-	skb_pull(skb, sizeof(struct mt76x2_rxwi));
-	if (mt76x2_mac_process_rx(dev, skb, rxwi)) {
-		dev_kfree_skb(skb);
-		return;
-	}
-
-	mt76_rx(&dev->mt76, q, skb);
-}
-
 static int
 mt76x2_init_rx_queue(struct mt76x2_dev *dev, struct mt76_queue *q,
 		     int idx, int n_desc, int bufsize)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
index 1f4d3e5ae64b..680a89f8aa87 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_main.c
@@ -53,30 +53,6 @@ mt76x2_stop(struct ieee80211_hw *hw)
 	mutex_unlock(&dev->mutex);
 }
 
-static void
-mt76x2_txq_init(struct mt76x2_dev *dev, struct ieee80211_txq *txq)
-{
-	struct mt76_txq *mtxq;
-
-	if (!txq)
-		return;
-
-	mtxq = (struct mt76_txq *) txq->drv_priv;
-	if (txq->sta) {
-		struct mt76x2_sta *sta;
-
-		sta = (struct mt76x2_sta *) txq->sta->drv_priv;
-		mtxq->wcid = &sta->wcid;
-	} else {
-		struct mt76x2_vif *mvif;
-
-		mvif = (struct mt76x2_vif *) txq->vif->drv_priv;
-		mtxq->wcid = &mvif->group_wcid;
-	}
-
-	mt76_txq_init(&dev->mt76, txq);
-}
-
 static int
 mt76x2_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 {
@@ -111,14 +87,6 @@ mt76x2_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	return 0;
 }
 
-static void
-mt76x2_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
-{
-	struct mt76x2_dev *dev = hw->priv;
-
-	mt76_txq_remove(&dev->mt76, vif->txq);
-}
-
 static int
 mt76x2_set_channel(struct mt76x2_dev *dev, struct cfg80211_chan_def *chandef)
 {
@@ -193,39 +161,6 @@ mt76x2_config(struct ieee80211_hw *hw, u32 changed)
 	return ret;
 }
 
-static void
-mt76x2_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags,
-			unsigned int *total_flags, u64 multicast)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	u32 flags = 0;
-
-#define MT76_FILTER(_flag, _hw) do { \
-		flags |= *total_flags & FIF_##_flag;			\
-		dev->rxfilter &= ~(_hw);				\
-		dev->rxfilter |= !(flags & FIF_##_flag) * (_hw);	\
-	} while (0)
-
-	mutex_lock(&dev->mutex);
-
-	dev->rxfilter &= ~MT_RX_FILTR_CFG_OTHER_BSS;
-
-	MT76_FILTER(FCSFAIL, MT_RX_FILTR_CFG_CRC_ERR);
-	MT76_FILTER(PLCPFAIL, MT_RX_FILTR_CFG_PHY_ERR);
-	MT76_FILTER(CONTROL, MT_RX_FILTR_CFG_ACK |
-			     MT_RX_FILTR_CFG_CTS |
-			     MT_RX_FILTR_CFG_CFEND |
-			     MT_RX_FILTR_CFG_CFACK |
-			     MT_RX_FILTR_CFG_BA |
-			     MT_RX_FILTR_CFG_CTRL_RSV);
-	MT76_FILTER(PSPOLL, MT_RX_FILTR_CFG_PSPOLL);
-
-	*total_flags = flags;
-	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
-
-	mutex_unlock(&dev->mutex);
-}
-
 static void
 mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			struct ieee80211_bss_conf *info, u32 changed)
@@ -263,68 +198,6 @@ mt76x2_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mutex_unlock(&dev->mutex);
 }
 
-static int
-mt76x2_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-	       struct ieee80211_sta *sta)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
-	int ret = 0;
-	int idx = 0;
-	int i;
-
-	mutex_lock(&dev->mutex);
-
-	idx = mt76_wcid_alloc(dev->wcid_mask, ARRAY_SIZE(dev->wcid));
-	if (idx < 0) {
-		ret = -ENOSPC;
-		goto out;
-	}
-
-	msta->vif = mvif;
-	msta->wcid.sta = 1;
-	msta->wcid.idx = idx;
-	msta->wcid.hw_key_idx = -1;
-	mt76x2_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
-	mt76x2_mac_wcid_set_drop(dev, idx, false);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		mt76x2_txq_init(dev, sta->txq[i]);
-
-	if (vif->type == NL80211_IFTYPE_AP)
-		set_bit(MT_WCID_FLAG_CHECK_PS, &msta->wcid.flags);
-
-	ewma_signal_init(&msta->rssi);
-
-	rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
-
-out:
-	mutex_unlock(&dev->mutex);
-
-	return ret;
-}
-
-static int
-mt76x2_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		  struct ieee80211_sta *sta)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	int idx = msta->wcid.idx;
-	int i;
-
-	mutex_lock(&dev->mutex);
-	rcu_assign_pointer(dev->wcid[idx], NULL);
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
-		mt76_txq_remove(&dev->mt76, sta->txq[i]);
-	mt76x2_mac_wcid_set_drop(dev, idx, true);
-	mt76_wcid_free(dev->wcid_mask, idx);
-	mt76x2_mac_wcid_setup(dev, idx, 0, NULL);
-	mutex_unlock(&dev->mutex);
-
-	return 0;
-}
-
 void
 mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
 {
@@ -336,117 +209,6 @@ mt76x2_sta_ps(struct mt76_dev *mdev, struct ieee80211_sta *sta, bool ps)
 	mt76x2_mac_wcid_set_drop(dev, idx, ps);
 }
 
-static int
-mt76x2_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
-	       struct ieee80211_vif *vif, struct ieee80211_sta *sta,
-	       struct ieee80211_key_conf *key)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_vif *mvif = (struct mt76x2_vif *) vif->drv_priv;
-	struct mt76x2_sta *msta;
-	struct mt76_wcid *wcid;
-	int idx = key->keyidx;
-	int ret;
-
-	/* fall back to sw encryption for unsupported ciphers */
-	switch (key->cipher) {
-	case WLAN_CIPHER_SUITE_WEP40:
-	case WLAN_CIPHER_SUITE_WEP104:
-	case WLAN_CIPHER_SUITE_TKIP:
-	case WLAN_CIPHER_SUITE_CCMP:
-		break;
-	default:
-		return -EOPNOTSUPP;
-	}
-
-	/*
-	 * The hardware does not support per-STA RX GTK, fall back
-	 * to software mode for these.
-	 */
-	if ((vif->type == NL80211_IFTYPE_ADHOC ||
-	     vif->type == NL80211_IFTYPE_MESH_POINT) &&
-	    (key->cipher == WLAN_CIPHER_SUITE_TKIP ||
-	     key->cipher == WLAN_CIPHER_SUITE_CCMP) &&
-	    !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE))
-		return -EOPNOTSUPP;
-
-	msta = sta ? (struct mt76x2_sta *) sta->drv_priv : NULL;
-	wcid = msta ? &msta->wcid : &mvif->group_wcid;
-
-	if (cmd == SET_KEY) {
-		key->hw_key_idx = wcid->idx;
-		wcid->hw_key_idx = idx;
-		if (key->flags & IEEE80211_KEY_FLAG_RX_MGMT) {
-			key->flags |= IEEE80211_KEY_FLAG_SW_MGMT_TX;
-			wcid->sw_iv = true;
-		}
-	} else {
-		if (idx == wcid->hw_key_idx) {
-			wcid->hw_key_idx = -1;
-			wcid->sw_iv = true;
-		}
-
-		key = NULL;
-	}
-	mt76_wcid_key_setup(&dev->mt76, wcid, key);
-
-	if (!msta) {
-		if (key || wcid->hw_key_idx == idx) {
-			ret = mt76x2_mac_wcid_set_key(dev, wcid->idx, key);
-			if (ret)
-				return ret;
-		}
-
-		return mt76x2_mac_shared_key_setup(dev, mvif->idx, idx, key);
-	}
-
-	return mt76x2_mac_wcid_set_key(dev, msta->wcid.idx, key);
-}
-
-static int
-mt76x2_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif, u16 queue,
-	       const struct ieee80211_tx_queue_params *params)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	u8 cw_min = 5, cw_max = 10, qid;
-	u32 val;
-
-	qid = dev->mt76.q_tx[queue].hw_idx;
-
-	if (params->cw_min)
-		cw_min = fls(params->cw_min);
-	if (params->cw_max)
-		cw_max = fls(params->cw_max);
-
-	val = FIELD_PREP(MT_EDCA_CFG_TXOP, params->txop) |
-	      FIELD_PREP(MT_EDCA_CFG_AIFSN, params->aifs) |
-	      FIELD_PREP(MT_EDCA_CFG_CWMIN, cw_min) |
-	      FIELD_PREP(MT_EDCA_CFG_CWMAX, cw_max);
-	mt76_wr(dev, MT_EDCA_CFG_AC(qid), val);
-
-	val = mt76_rr(dev, MT_WMM_TXOP(qid));
-	val &= ~(MT_WMM_TXOP_MASK << MT_WMM_TXOP_SHIFT(qid));
-	val |= params->txop << MT_WMM_TXOP_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_TXOP(qid), val);
-
-	val = mt76_rr(dev, MT_WMM_AIFSN);
-	val &= ~(MT_WMM_AIFSN_MASK << MT_WMM_AIFSN_SHIFT(qid));
-	val |= params->aifs << MT_WMM_AIFSN_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_AIFSN, val);
-
-	val = mt76_rr(dev, MT_WMM_CWMIN);
-	val &= ~(MT_WMM_CWMIN_MASK << MT_WMM_CWMIN_SHIFT(qid));
-	val |= cw_min << MT_WMM_CWMIN_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_CWMIN, val);
-
-	val = mt76_rr(dev, MT_WMM_CWMAX);
-	val &= ~(MT_WMM_CWMAX_MASK << MT_WMM_CWMAX_SHIFT(qid));
-	val |= cw_max << MT_WMM_CWMAX_SHIFT(qid);
-	mt76_wr(dev, MT_WMM_CWMAX, val);
-
-	return 0;
-}
-
 static void
 mt76x2_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	       const u8 *mac)
@@ -485,75 +247,6 @@ mt76x2_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif, int *dbm)
 	return 0;
 }
 
-static int
-mt76x2_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		    struct ieee80211_ampdu_params *params)
-{
-	enum ieee80211_ampdu_mlme_action action = params->action;
-	struct ieee80211_sta *sta = params->sta;
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	struct ieee80211_txq *txq = sta->txq[params->tid];
-	u16 tid = params->tid;
-	u16 *ssn = &params->ssn;
-	struct mt76_txq *mtxq;
-
-	if (!txq)
-		return -EINVAL;
-
-	mtxq = (struct mt76_txq *)txq->drv_priv;
-
-	switch (action) {
-	case IEEE80211_AMPDU_RX_START:
-		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, *ssn, params->buf_size);
-		mt76_set(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
-		break;
-	case IEEE80211_AMPDU_RX_STOP:
-		mt76_rx_aggr_stop(&dev->mt76, &msta->wcid, tid);
-		mt76_clear(dev, MT_WCID_ADDR(msta->wcid.idx) + 4,
-			   BIT(16 + tid));
-		break;
-	case IEEE80211_AMPDU_TX_OPERATIONAL:
-		mtxq->aggr = true;
-		mtxq->send_bar = false;
-		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
-		break;
-	case IEEE80211_AMPDU_TX_STOP_FLUSH:
-	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-		mtxq->aggr = false;
-		ieee80211_send_bar(vif, sta->addr, tid, mtxq->agg_ssn);
-		break;
-	case IEEE80211_AMPDU_TX_START:
-		mtxq->agg_ssn = *ssn << 4;
-		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
-		break;
-	case IEEE80211_AMPDU_TX_STOP_CONT:
-		mtxq->aggr = false;
-		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
-		break;
-	}
-
-	return 0;
-}
-
-static void
-mt76x2_sta_rate_tbl_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-			   struct ieee80211_sta *sta)
-{
-	struct mt76x2_dev *dev = hw->priv;
-	struct mt76x2_sta *msta = (struct mt76x2_sta *) sta->drv_priv;
-	struct ieee80211_sta_rates *rates = rcu_dereference(sta->rates);
-	struct ieee80211_tx_rate rate = {};
-
-	if (!rates)
-		return;
-
-	rate.idx = rates->rate[0].idx;
-	rate.flags = rates->rate[0].flags;
-	mt76x2_mac_wcid_set_rate(dev, &msta->wcid, &rate);
-	msta->wcid.max_txpwr_adj = mt76x2_tx_get_max_txpwr_adj(dev, &rate);
-}
-
 static void mt76x2_set_coverage_class(struct ieee80211_hw *hw,
 				      s16 coverage_class)
 {
-- 
cgit v1.2.3


From 5f0d10ceee47530bf6ae860e8aee158523ec402d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:17 +0200
Subject: mt76: add mt76x2_phy_common to mt76x2-common module

Move phy related code shared between mt76x2 and mt76x2u in
mt76x2-common module

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Makefile        |   2 +-
 drivers/net/wireless/mediatek/mt76/mt76x2.h        |   9 +
 drivers/net/wireless/mediatek/mt76/mt76x2_phy.c    | 328 -------------------
 .../net/wireless/mediatek/mt76/mt76x2_phy_common.c | 349 +++++++++++++++++++++
 4 files changed, 359 insertions(+), 329 deletions(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2_phy_common.c

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index a184e16a5d54..5a9f34b14ee4 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -9,7 +9,7 @@ CFLAGS_trace.o := -I$(src)
 
 mt76x2-common-y := \
 	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o \
-	mt76x2_init_common.o mt76x2_common.o
+	mt76x2_init_common.o mt76x2_common.o mt76x2_phy_common.o
 
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 0c129d6a9466..624ae804395a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -314,4 +314,13 @@ void mt76x2_sta_rate_tbl_update(struct ieee80211_hw *hw,
 				struct ieee80211_vif *vif,
 				struct ieee80211_sta *sta);
 
+void mt76x2_phy_set_txpower_regs(struct mt76x2_dev *dev,
+				 enum nl80211_band band);
+void mt76x2_configure_tx_delay(struct mt76x2_dev *dev,
+			       enum nl80211_band band, u8 bw);
+void mt76x2_phy_set_bw(struct mt76x2_dev *dev, int width, u8 ctrl);
+void mt76x2_phy_set_band(struct mt76x2_dev *dev, int band, bool primary_upper);
+int mt76x2_phy_get_min_avg_rssi(struct mt76x2_dev *dev);
+void mt76x2_apply_gain_adj(struct mt76x2_dev *dev);
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
index 962505bf8fbb..84c96c0415b6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy.c
@@ -19,153 +19,6 @@
 #include "mt76x2_mcu.h"
 #include "mt76x2_eeprom.h"
 
-static void
-mt76x2_adjust_high_lna_gain(struct mt76x2_dev *dev, int reg, s8 offset)
-{
-	s8 gain;
-
-	gain = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
-	gain -= offset / 2;
-	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_LNA_HIGH_GAIN, gain);
-}
-
-static void
-mt76x2_adjust_agc_gain(struct mt76x2_dev *dev, int reg, s8 offset)
-{
-	s8 gain;
-
-	gain = FIELD_GET(MT_BBP_AGC_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
-	gain += offset;
-	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_GAIN, gain);
-}
-
-static void
-mt76x2_apply_gain_adj(struct mt76x2_dev *dev)
-{
-	s8 *gain_adj = dev->cal.rx.high_gain;
-
-	mt76x2_adjust_high_lna_gain(dev, 4, gain_adj[0]);
-	mt76x2_adjust_high_lna_gain(dev, 5, gain_adj[1]);
-
-	mt76x2_adjust_agc_gain(dev, 8, gain_adj[0]);
-	mt76x2_adjust_agc_gain(dev, 9, gain_adj[1]);
-}
-
-static u32
-mt76x2_tx_power_mask(u8 v1, u8 v2, u8 v3, u8 v4)
-{
-	u32 val = 0;
-
-	val |= (v1 & (BIT(6) - 1)) << 0;
-	val |= (v2 & (BIT(6) - 1)) << 8;
-	val |= (v3 & (BIT(6) - 1)) << 16;
-	val |= (v4 & (BIT(6) - 1)) << 24;
-	return val;
-}
-
-static void
-mt76x2_add_rate_power_offset(struct mt76_rate_power *r, int offset)
-{
-	int i;
-
-	for (i = 0; i < sizeof(r->all); i++)
-		r->all[i] += offset;
-}
-
-static void
-mt76x2_limit_rate_power(struct mt76_rate_power *r, int limit)
-{
-	int i;
-
-	for (i = 0; i < sizeof(r->all); i++)
-		if (r->all[i] > limit)
-			r->all[i] = limit;
-}
-
-static int
-mt76x2_get_min_rate_power(struct mt76_rate_power *r)
-{
-	int i;
-	s8 ret = 0;
-
-	for (i = 0; i < sizeof(r->all); i++) {
-		if (!r->all[i])
-			continue;
-
-		if (ret)
-			ret = min(ret, r->all[i]);
-		else
-			ret = r->all[i];
-	}
-
-	return ret;
-}
-
-
-void mt76x2_phy_set_txpower(struct mt76x2_dev *dev)
-{
-	enum nl80211_chan_width width = dev->mt76.chandef.width;
-	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
-	struct mt76x2_tx_power_info txp;
-	int txp_0, txp_1, delta = 0;
-	struct mt76_rate_power t = {};
-	int base_power, gain;
-
-	mt76x2_get_power_info(dev, &txp, chan);
-
-	if (width == NL80211_CHAN_WIDTH_40)
-		delta = txp.delta_bw40;
-	else if (width == NL80211_CHAN_WIDTH_80)
-		delta = txp.delta_bw80;
-
-	mt76x2_get_rate_power(dev, &t, chan);
-	mt76x2_add_rate_power_offset(&t, txp.chain[0].target_power);
-	mt76x2_limit_rate_power(&t, dev->txpower_conf);
-	dev->txpower_cur = mt76x2_get_max_rate_power(&t);
-
-	base_power = mt76x2_get_min_rate_power(&t);
-	delta += base_power - txp.chain[0].target_power;
-	txp_0 = txp.chain[0].target_power + txp.chain[0].delta + delta;
-	txp_1 = txp.chain[1].target_power + txp.chain[1].delta + delta;
-
-	gain = min(txp_0, txp_1);
-	if (gain < 0) {
-		base_power -= gain;
-		txp_0 -= gain;
-		txp_1 -= gain;
-	} else if (gain > 0x2f) {
-		base_power -= gain - 0x2f;
-		txp_0 = 0x2f;
-		txp_1 = 0x2f;
-	}
-
-	mt76x2_add_rate_power_offset(&t, -base_power);
-	dev->target_power = txp.chain[0].target_power;
-	dev->target_power_delta[0] = txp_0 - txp.chain[0].target_power;
-	dev->target_power_delta[1] = txp_1 - txp.chain[0].target_power;
-	dev->rate_power = t;
-
-	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_0, txp_0);
-	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_1, txp_1);
-
-	mt76_wr(dev, MT_TX_PWR_CFG_0,
-		mt76x2_tx_power_mask(t.cck[0], t.cck[2], t.ofdm[0], t.ofdm[2]));
-	mt76_wr(dev, MT_TX_PWR_CFG_1,
-		mt76x2_tx_power_mask(t.ofdm[4], t.ofdm[6], t.ht[0], t.ht[2]));
-	mt76_wr(dev, MT_TX_PWR_CFG_2,
-		mt76x2_tx_power_mask(t.ht[4], t.ht[6], t.ht[8], t.ht[10]));
-	mt76_wr(dev, MT_TX_PWR_CFG_3,
-		mt76x2_tx_power_mask(t.ht[12], t.ht[14], t.ht[0], t.ht[2]));
-	mt76_wr(dev, MT_TX_PWR_CFG_4,
-		mt76x2_tx_power_mask(t.ht[4], t.ht[6], 0, 0));
-	mt76_wr(dev, MT_TX_PWR_CFG_7,
-		mt76x2_tx_power_mask(t.ofdm[6], t.vht[8], t.ht[6], t.vht[8]));
-	mt76_wr(dev, MT_TX_PWR_CFG_8,
-		mt76x2_tx_power_mask(t.ht[14], t.vht[8], t.vht[8], 0));
-	mt76_wr(dev, MT_TX_PWR_CFG_9,
-		mt76x2_tx_power_mask(t.ht[6], t.vht[8], t.vht[8], 0));
-}
-
 static bool
 mt76x2_phy_tssi_init_cal(struct mt76x2_dev *dev)
 {
@@ -224,140 +77,6 @@ mt76x2_phy_channel_calibrate(struct mt76x2_dev *dev, bool mac_stopped)
 	dev->cal.channel_cal_done = true;
 }
 
-static void
-mt76x2_phy_set_txpower_regs(struct mt76x2_dev *dev, enum nl80211_band band)
-{
-	u32 pa_mode[2];
-	u32 pa_mode_adj;
-
-	if (band == NL80211_BAND_2GHZ) {
-		pa_mode[0] = 0x010055ff;
-		pa_mode[1] = 0x00550055;
-
-		mt76_wr(dev, MT_TX_ALC_CFG_2, 0x35160a00);
-		mt76_wr(dev, MT_TX_ALC_CFG_3, 0x35160a06);
-
-		if (mt76x2_ext_pa_enabled(dev, band)) {
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0x0000ec00);
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0x0000ec00);
-		} else {
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0xf4000200);
-			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0xfa000200);
-		}
-	} else {
-		pa_mode[0] = 0x0000ffff;
-		pa_mode[1] = 0x00ff00ff;
-
-		if (mt76x2_ext_pa_enabled(dev, band)) {
-			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x2f0f0400);
-			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x2f0f0476);
-		} else {
-			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x1b0f0400);
-			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x1b0f0476);
-		}
-
-		if (mt76x2_ext_pa_enabled(dev, band))
-			pa_mode_adj = 0x04000000;
-		else
-			pa_mode_adj = 0;
-
-		mt76_wr(dev, MT_RF_PA_MODE_ADJ0, pa_mode_adj);
-		mt76_wr(dev, MT_RF_PA_MODE_ADJ1, pa_mode_adj);
-	}
-
-	mt76_wr(dev, MT_BB_PA_MODE_CFG0, pa_mode[0]);
-	mt76_wr(dev, MT_BB_PA_MODE_CFG1, pa_mode[1]);
-	mt76_wr(dev, MT_RF_PA_MODE_CFG0, pa_mode[0]);
-	mt76_wr(dev, MT_RF_PA_MODE_CFG1, pa_mode[1]);
-
-	if (mt76x2_ext_pa_enabled(dev, band)) {
-		u32 val;
-
-		if (band == NL80211_BAND_2GHZ)
-			val = 0x3c3c023c;
-		else
-			val = 0x363c023c;
-
-		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
-		mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
-		mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00001818);
-	} else {
-		if (band == NL80211_BAND_2GHZ) {
-			u32 val = 0x0f3c3c3c;
-
-			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
-			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
-			mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00000606);
-		} else {
-			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x383c023c);
-			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, 0x24282e28);
-			mt76_wr(dev, MT_TX_ALC_CFG_4, 0);
-		}
-	}
-}
-
-static void
-mt76x2_configure_tx_delay(struct mt76x2_dev *dev, enum nl80211_band band, u8 bw)
-{
-	u32 cfg0, cfg1;
-
-	if (mt76x2_ext_pa_enabled(dev, band)) {
-		cfg0 = bw ? 0x000b0c01 : 0x00101101;
-		cfg1 = 0x00011414;
-	} else {
-		cfg0 = bw ? 0x000b0b01 : 0x00101001;
-		cfg1 = 0x00021414;
-	}
-	mt76_wr(dev, MT_TX_SW_CFG0, cfg0);
-	mt76_wr(dev, MT_TX_SW_CFG1, cfg1);
-
-	mt76_rmw_field(dev, MT_XIFS_TIME_CFG, MT_XIFS_TIME_CFG_OFDM_SIFS, 15);
-}
-
-static void
-mt76x2_phy_set_bw(struct mt76x2_dev *dev, int width, u8 ctrl)
-{
-	int core_val, agc_val;
-
-	switch (width) {
-	case NL80211_CHAN_WIDTH_80:
-		core_val = 3;
-		agc_val = 7;
-		break;
-	case NL80211_CHAN_WIDTH_40:
-		core_val = 2;
-		agc_val = 3;
-		break;
-	default:
-		core_val = 0;
-		agc_val = 1;
-		break;
-	}
-
-	mt76_rmw_field(dev, MT_BBP(CORE, 1), MT_BBP_CORE_R1_BW, core_val);
-	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_BW, agc_val);
-	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_CTRL_CHAN, ctrl);
-	mt76_rmw_field(dev, MT_BBP(TXBE, 0), MT_BBP_TXBE_R0_CTRL_CHAN, ctrl);
-}
-
-static void
-mt76x2_phy_set_band(struct mt76x2_dev *dev, int band, bool primary_upper)
-{
-	switch (band) {
-	case NL80211_BAND_2GHZ:
-		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
-		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
-		break;
-	case NL80211_BAND_5GHZ:
-		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
-		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
-		break;
-	}
-
-	mt76_rmw_field(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_UPPER_40M,
-		       primary_upper);
-}
-
 void mt76x2_phy_set_antenna(struct mt76x2_dev *dev)
 {
 	u32 val;
@@ -481,53 +200,6 @@ mt76x2_phy_adjust_vga_gain(struct mt76x2_dev *dev)
 	mt76x2_phy_set_gain_val(dev);
 }
 
-static int
-mt76x2_phy_get_min_avg_rssi(struct mt76x2_dev *dev)
-{
-	struct mt76x2_sta *sta;
-	struct mt76_wcid *wcid;
-	int i, j, min_rssi = 0;
-	s8 cur_rssi;
-
-	local_bh_disable();
-	rcu_read_lock();
-
-	for (i = 0; i < ARRAY_SIZE(dev->wcid_mask); i++) {
-		unsigned long mask = dev->wcid_mask[i];
-
-		if (!mask)
-			continue;
-
-		for (j = i * BITS_PER_LONG; mask; j++, mask >>= 1) {
-			if (!(mask & 1))
-				continue;
-
-			wcid = rcu_dereference(dev->wcid[j]);
-			if (!wcid)
-				continue;
-
-			sta = container_of(wcid, struct mt76x2_sta, wcid);
-			spin_lock(&dev->mt76.rx_lock);
-			if (sta->inactive_count++ < 5)
-				cur_rssi = ewma_signal_read(&sta->rssi);
-			else
-				cur_rssi = 0;
-			spin_unlock(&dev->mt76.rx_lock);
-
-			if (cur_rssi < min_rssi)
-				min_rssi = cur_rssi;
-		}
-	}
-
-	rcu_read_unlock();
-	local_bh_enable();
-
-	if (!min_rssi)
-		return -75;
-
-	return min_rssi;
-}
-
 static void
 mt76x2_phy_update_channel_gain(struct mt76x2_dev *dev)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_phy_common.c b/drivers/net/wireless/mediatek/mt76/mt76x2_phy_common.c
new file mode 100644
index 000000000000..9fd6ab4cbb94
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_phy_common.c
@@ -0,0 +1,349 @@
+/*
+ * Copyright (C) 2016 Felix Fietkau <nbd@nbd.name>
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2.h"
+#include "mt76x2_eeprom.h"
+
+static void
+mt76x2_adjust_high_lna_gain(struct mt76x2_dev *dev, int reg, s8 offset)
+{
+	s8 gain;
+
+	gain = FIELD_GET(MT_BBP_AGC_LNA_HIGH_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
+	gain -= offset / 2;
+	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_LNA_HIGH_GAIN, gain);
+}
+
+static void
+mt76x2_adjust_agc_gain(struct mt76x2_dev *dev, int reg, s8 offset)
+{
+	s8 gain;
+
+	gain = FIELD_GET(MT_BBP_AGC_GAIN, mt76_rr(dev, MT_BBP(AGC, reg)));
+	gain += offset;
+	mt76_rmw_field(dev, MT_BBP(AGC, reg), MT_BBP_AGC_GAIN, gain);
+}
+
+void mt76x2_apply_gain_adj(struct mt76x2_dev *dev)
+{
+	s8 *gain_adj = dev->cal.rx.high_gain;
+
+	mt76x2_adjust_high_lna_gain(dev, 4, gain_adj[0]);
+	mt76x2_adjust_high_lna_gain(dev, 5, gain_adj[1]);
+
+	mt76x2_adjust_agc_gain(dev, 8, gain_adj[0]);
+	mt76x2_adjust_agc_gain(dev, 9, gain_adj[1]);
+}
+EXPORT_SYMBOL_GPL(mt76x2_apply_gain_adj);
+
+void mt76x2_phy_set_txpower_regs(struct mt76x2_dev *dev,
+				 enum nl80211_band band)
+{
+	u32 pa_mode[2];
+	u32 pa_mode_adj;
+
+	if (band == NL80211_BAND_2GHZ) {
+		pa_mode[0] = 0x010055ff;
+		pa_mode[1] = 0x00550055;
+
+		mt76_wr(dev, MT_TX_ALC_CFG_2, 0x35160a00);
+		mt76_wr(dev, MT_TX_ALC_CFG_3, 0x35160a06);
+
+		if (mt76x2_ext_pa_enabled(dev, band)) {
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0x0000ec00);
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0x0000ec00);
+		} else {
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ0, 0xf4000200);
+			mt76_wr(dev, MT_RF_PA_MODE_ADJ1, 0xfa000200);
+		}
+	} else {
+		pa_mode[0] = 0x0000ffff;
+		pa_mode[1] = 0x00ff00ff;
+
+		if (mt76x2_ext_pa_enabled(dev, band)) {
+			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x2f0f0400);
+			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x2f0f0476);
+		} else {
+			mt76_wr(dev, MT_TX_ALC_CFG_2, 0x1b0f0400);
+			mt76_wr(dev, MT_TX_ALC_CFG_3, 0x1b0f0476);
+		}
+
+		if (mt76x2_ext_pa_enabled(dev, band))
+			pa_mode_adj = 0x04000000;
+		else
+			pa_mode_adj = 0;
+
+		mt76_wr(dev, MT_RF_PA_MODE_ADJ0, pa_mode_adj);
+		mt76_wr(dev, MT_RF_PA_MODE_ADJ1, pa_mode_adj);
+	}
+
+	mt76_wr(dev, MT_BB_PA_MODE_CFG0, pa_mode[0]);
+	mt76_wr(dev, MT_BB_PA_MODE_CFG1, pa_mode[1]);
+	mt76_wr(dev, MT_RF_PA_MODE_CFG0, pa_mode[0]);
+	mt76_wr(dev, MT_RF_PA_MODE_CFG1, pa_mode[1]);
+
+	if (mt76x2_ext_pa_enabled(dev, band)) {
+		u32 val;
+
+		if (band == NL80211_BAND_2GHZ)
+			val = 0x3c3c023c;
+		else
+			val = 0x363c023c;
+
+		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
+		mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
+		mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00001818);
+	} else {
+		if (band == NL80211_BAND_2GHZ) {
+			u32 val = 0x0f3c3c3c;
+
+			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, val);
+			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, val);
+			mt76_wr(dev, MT_TX_ALC_CFG_4, 0x00000606);
+		} else {
+			mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x383c023c);
+			mt76_wr(dev, MT_TX1_RF_GAIN_CORR, 0x24282e28);
+			mt76_wr(dev, MT_TX_ALC_CFG_4, 0);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_txpower_regs);
+
+static void
+mt76x2_limit_rate_power(struct mt76_rate_power *r, int limit)
+{
+	int i;
+
+	for (i = 0; i < sizeof(r->all); i++)
+		if (r->all[i] > limit)
+			r->all[i] = limit;
+}
+
+static u32
+mt76x2_tx_power_mask(u8 v1, u8 v2, u8 v3, u8 v4)
+{
+	u32 val = 0;
+
+	val |= (v1 & (BIT(6) - 1)) << 0;
+	val |= (v2 & (BIT(6) - 1)) << 8;
+	val |= (v3 & (BIT(6) - 1)) << 16;
+	val |= (v4 & (BIT(6) - 1)) << 24;
+	return val;
+}
+
+static void
+mt76x2_add_rate_power_offset(struct mt76_rate_power *r, int offset)
+{
+	int i;
+
+	for (i = 0; i < sizeof(r->all); i++)
+		r->all[i] += offset;
+}
+
+static int
+mt76x2_get_min_rate_power(struct mt76_rate_power *r)
+{
+	int i;
+	s8 ret = 0;
+
+	for (i = 0; i < sizeof(r->all); i++) {
+		if (!r->all[i])
+			continue;
+
+		if (ret)
+			ret = min(ret, r->all[i]);
+		else
+			ret = r->all[i];
+	}
+
+	return ret;
+}
+
+void mt76x2_phy_set_txpower(struct mt76x2_dev *dev)
+{
+	enum nl80211_chan_width width = dev->mt76.chandef.width;
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	struct mt76x2_tx_power_info txp;
+	int txp_0, txp_1, delta = 0;
+	struct mt76_rate_power t = {};
+	int base_power, gain;
+
+	mt76x2_get_power_info(dev, &txp, chan);
+
+	if (width == NL80211_CHAN_WIDTH_40)
+		delta = txp.delta_bw40;
+	else if (width == NL80211_CHAN_WIDTH_80)
+		delta = txp.delta_bw80;
+
+	mt76x2_get_rate_power(dev, &t, chan);
+	mt76x2_add_rate_power_offset(&t, txp.chain[0].target_power);
+	mt76x2_limit_rate_power(&t, dev->txpower_conf);
+	dev->txpower_cur = mt76x2_get_max_rate_power(&t);
+
+	base_power = mt76x2_get_min_rate_power(&t);
+	delta += base_power - txp.chain[0].target_power;
+	txp_0 = txp.chain[0].target_power + txp.chain[0].delta + delta;
+	txp_1 = txp.chain[1].target_power + txp.chain[1].delta + delta;
+
+	gain = min(txp_0, txp_1);
+	if (gain < 0) {
+		base_power -= gain;
+		txp_0 -= gain;
+		txp_1 -= gain;
+	} else if (gain > 0x2f) {
+		base_power -= gain - 0x2f;
+		txp_0 = 0x2f;
+		txp_1 = 0x2f;
+	}
+
+	mt76x2_add_rate_power_offset(&t, -base_power);
+	dev->target_power = txp.chain[0].target_power;
+	dev->target_power_delta[0] = txp_0 - txp.chain[0].target_power;
+	dev->target_power_delta[1] = txp_1 - txp.chain[0].target_power;
+	dev->rate_power = t;
+
+	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_0, txp_0);
+	mt76_rmw_field(dev, MT_TX_ALC_CFG_0, MT_TX_ALC_CFG_0_CH_INIT_1, txp_1);
+
+	mt76_wr(dev, MT_TX_PWR_CFG_0,
+		mt76x2_tx_power_mask(t.cck[0], t.cck[2], t.ofdm[0], t.ofdm[2]));
+	mt76_wr(dev, MT_TX_PWR_CFG_1,
+		mt76x2_tx_power_mask(t.ofdm[4], t.ofdm[6], t.ht[0], t.ht[2]));
+	mt76_wr(dev, MT_TX_PWR_CFG_2,
+		mt76x2_tx_power_mask(t.ht[4], t.ht[6], t.ht[8], t.ht[10]));
+	mt76_wr(dev, MT_TX_PWR_CFG_3,
+		mt76x2_tx_power_mask(t.ht[12], t.ht[14], t.ht[0], t.ht[2]));
+	mt76_wr(dev, MT_TX_PWR_CFG_4,
+		mt76x2_tx_power_mask(t.ht[4], t.ht[6], 0, 0));
+	mt76_wr(dev, MT_TX_PWR_CFG_7,
+		mt76x2_tx_power_mask(t.ofdm[6], t.vht[8], t.ht[6], t.vht[8]));
+	mt76_wr(dev, MT_TX_PWR_CFG_8,
+		mt76x2_tx_power_mask(t.ht[14], t.vht[8], t.vht[8], 0));
+	mt76_wr(dev, MT_TX_PWR_CFG_9,
+		mt76x2_tx_power_mask(t.ht[6], t.vht[8], t.vht[8], 0));
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_txpower);
+
+void mt76x2_configure_tx_delay(struct mt76x2_dev *dev,
+			       enum nl80211_band band, u8 bw)
+{
+	u32 cfg0, cfg1;
+
+	if (mt76x2_ext_pa_enabled(dev, band)) {
+		cfg0 = bw ? 0x000b0c01 : 0x00101101;
+		cfg1 = 0x00011414;
+	} else {
+		cfg0 = bw ? 0x000b0b01 : 0x00101001;
+		cfg1 = 0x00021414;
+	}
+	mt76_wr(dev, MT_TX_SW_CFG0, cfg0);
+	mt76_wr(dev, MT_TX_SW_CFG1, cfg1);
+
+	mt76_rmw_field(dev, MT_XIFS_TIME_CFG, MT_XIFS_TIME_CFG_OFDM_SIFS, 15);
+}
+EXPORT_SYMBOL_GPL(mt76x2_configure_tx_delay);
+
+void mt76x2_phy_set_bw(struct mt76x2_dev *dev, int width, u8 ctrl)
+{
+	int core_val, agc_val;
+
+	switch (width) {
+	case NL80211_CHAN_WIDTH_80:
+		core_val = 3;
+		agc_val = 7;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		core_val = 2;
+		agc_val = 3;
+		break;
+	default:
+		core_val = 0;
+		agc_val = 1;
+		break;
+	}
+
+	mt76_rmw_field(dev, MT_BBP(CORE, 1), MT_BBP_CORE_R1_BW, core_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_BW, agc_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_CTRL_CHAN, ctrl);
+	mt76_rmw_field(dev, MT_BBP(TXBE, 0), MT_BBP_TXBE_R0_CTRL_CHAN, ctrl);
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_bw);
+
+void mt76x2_phy_set_band(struct mt76x2_dev *dev, int band, bool primary_upper)
+{
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+		break;
+	case NL80211_BAND_5GHZ:
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+		break;
+	}
+
+	mt76_rmw_field(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_UPPER_40M,
+		       primary_upper);
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_set_band);
+
+int mt76x2_phy_get_min_avg_rssi(struct mt76x2_dev *dev)
+{
+	struct mt76x2_sta *sta;
+	struct mt76_wcid *wcid;
+	int i, j, min_rssi = 0;
+	s8 cur_rssi;
+
+	local_bh_disable();
+	rcu_read_lock();
+
+	for (i = 0; i < ARRAY_SIZE(dev->wcid_mask); i++) {
+		unsigned long mask = dev->wcid_mask[i];
+
+		if (!mask)
+			continue;
+
+		for (j = i * BITS_PER_LONG; mask; j++, mask >>= 1) {
+			if (!(mask & 1))
+				continue;
+
+			wcid = rcu_dereference(dev->wcid[j]);
+			if (!wcid)
+				continue;
+
+			sta = container_of(wcid, struct mt76x2_sta, wcid);
+			spin_lock(&dev->mt76.rx_lock);
+			if (sta->inactive_count++ < 5)
+				cur_rssi = ewma_signal_read(&sta->rssi);
+			else
+				cur_rssi = 0;
+			spin_unlock(&dev->mt76.rx_lock);
+
+			if (cur_rssi < min_rssi)
+				min_rssi = cur_rssi;
+		}
+	}
+
+	rcu_read_unlock();
+	local_bh_enable();
+
+	if (!min_rssi)
+		return -75;
+
+	return min_rssi;
+}
+EXPORT_SYMBOL_GPL(mt76x2_phy_get_min_avg_rssi);
-- 
cgit v1.2.3


From 037804002b8a547a757bd0dd38a842186130385d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:18 +0200
Subject: mt76: move mt76x2_debugfs in mt76-common module

Move mt76x2_debugfs code in mt76-common module since it is shared
between mt76x2 and mt76x2u

Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Makefile         | 5 +++--
 drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c | 1 +
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index 5a9f34b14ee4..e1bc229e4aad 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -9,11 +9,12 @@ CFLAGS_trace.o := -I$(src)
 
 mt76x2-common-y := \
 	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o \
-	mt76x2_init_common.o mt76x2_common.o mt76x2_phy_common.o
+	mt76x2_init_common.o mt76x2_common.o mt76x2_phy_common.o \
+	mt76x2_debugfs.o
 
 mt76x2e-y := \
 	mt76x2_pci.o mt76x2_dma.o \
-	mt76x2_main.o mt76x2_init.o mt76x2_debugfs.o mt76x2_tx.o \
+	mt76x2_main.o mt76x2_init.o mt76x2_tx.o \
 	mt76x2_core.o mt76x2_mac.o mt76x2_mcu.o mt76x2_phy.o \
 	mt76x2_dfs.o mt76x2_trace.o
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
index 74725902e6dc..77b5ff1be05f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_debugfs.c
@@ -153,3 +153,4 @@ void mt76x2_init_debugfs(struct mt76x2_dev *dev)
 
 	debugfs_create_devm_seqfile(dev->mt76.dev, "agc", dir, read_agc);
 }
+EXPORT_SYMBOL_GPL(mt76x2_init_debugfs);
-- 
cgit v1.2.3


From b40b15e1521f7764ea8c68d5a00ecc971b673d21 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:19 +0200
Subject: mt76: add usb support to mt76 layer

This will be used by drivers for MT76x2u based devices

Tested-by: <cug_yangyuancong@hotmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Kconfig     |   4 +
 drivers/net/wireless/mediatek/mt76/Makefile    |   4 +
 drivers/net/wireless/mediatek/mt76/dma.h       |   5 +
 drivers/net/wireless/mediatek/mt76/mt76.h      | 143 ++++-
 drivers/net/wireless/mediatek/mt76/usb.c       | 845 +++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/usb_mcu.c   | 242 +++++++
 drivers/net/wireless/mediatek/mt76/usb_trace.c |  23 +
 drivers/net/wireless/mediatek/mt76/usb_trace.h |  71 +++
 8 files changed, 1336 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/wireless/mediatek/mt76/usb.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/usb_mcu.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/usb_trace.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/usb_trace.h

diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index 1e5c6af6afa2..ba17cdd46ea3 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -1,6 +1,10 @@
 config MT76_CORE
 	tristate
 
+config MT76_USB
+	tristate
+	depends on MT76_CORE
+
 config MT76x2_COMMON
 	tristate
 	depends on MT76_CORE
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index e1bc229e4aad..de0a4bc235d1 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -1,11 +1,15 @@
 obj-$(CONFIG_MT76_CORE) += mt76.o
+obj-$(CONFIG_MT76_USB) += mt76-usb.o
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2-common.o
 obj-$(CONFIG_MT76x2E) += mt76x2e.o
 
 mt76-y := \
 	mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o tx.o agg-rx.o
 
+mt76-usb-y := usb.o usb_trace.o usb_mcu.o
+
 CFLAGS_trace.o := -I$(src)
+CFLAGS_usb_trace.o := -I$(src)
 
 mt76x2-common-y := \
 	mt76x2_eeprom.o mt76x2_tx_common.o mt76x2_mac_common.o \
diff --git a/drivers/net/wireless/mediatek/mt76/dma.h b/drivers/net/wireless/mediatek/mt76/dma.h
index 14cfb2dbca25..27248e24a19b 100644
--- a/drivers/net/wireless/mediatek/mt76/dma.h
+++ b/drivers/net/wireless/mediatek/mt76/dma.h
@@ -53,6 +53,11 @@
 #define MT_MCU_MSG_TYPE			GENMASK(31, 30)
 #define MT_MCU_MSG_TYPE_CMD		BIT(30)
 
+#define MT_DMA_HDR_LEN			4
+#define MT_RX_INFO_LEN			4
+#define MT_FCE_INFO_LEN			4
+#define MT_RX_RXWI_LEN			32
+
 struct mt76_desc {
 	__le32 buf0;
 	__le32 ctrl;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index ed40d6e66d44..4bf1b35ec44c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -22,6 +22,7 @@
 #include <linux/spinlock.h>
 #include <linux/skbuff.h>
 #include <linux/leds.h>
+#include <linux/usb.h>
 #include <net/mac80211.h>
 #include "util.h"
 
@@ -63,12 +64,22 @@ struct mt76_queue_buf {
 	int len;
 };
 
+struct mt76u_buf {
+	struct mt76_dev *dev;
+	struct urb *urb;
+	size_t len;
+	bool done;
+};
+
 struct mt76_queue_entry {
 	union {
 		void *buf;
 		struct sk_buff *skb;
 	};
-	struct mt76_txwi_cache *txwi;
+	union {
+		struct mt76_txwi_cache *txwi;
+		struct mt76u_buf ubuf;
+	};
 	bool schedule;
 };
 
@@ -89,6 +100,7 @@ struct mt76_queue {
 	struct list_head swq;
 	int swq_queued;
 
+	u16 first;
 	u16 head;
 	u16 tail;
 	int ndesc;
@@ -195,6 +207,8 @@ enum {
 	MT76_SCANNING,
 	MT76_RESET,
 	MT76_OFFCHANNEL,
+	MT76_REMOVED,
+	MT76_READING_STATS,
 };
 
 struct mt76_hw_cap {
@@ -215,6 +229,8 @@ struct mt76_driver_ops {
 	void (*tx_complete_skb)(struct mt76_dev *dev, struct mt76_queue *q,
 				struct mt76_queue_entry *e, bool flush);
 
+	bool (*tx_status_data)(struct mt76_dev *dev, u8 *update);
+
 	void (*rx_skb)(struct mt76_dev *dev, enum mt76_rxq_id q,
 		       struct sk_buff *skb);
 
@@ -234,6 +250,64 @@ struct mt76_sband {
 	struct mt76_channel_state *chan;
 };
 
+/* addr req mask */
+#define MT_VEND_TYPE_EEPROM	BIT(31)
+#define MT_VEND_TYPE_CFG	BIT(30)
+#define MT_VEND_TYPE_MASK	(MT_VEND_TYPE_EEPROM | MT_VEND_TYPE_CFG)
+
+#define MT_VEND_ADDR(type, n)	(MT_VEND_TYPE_##type | (n))
+enum mt_vendor_req {
+	MT_VEND_DEV_MODE =	0x1,
+	MT_VEND_WRITE =		0x2,
+	MT_VEND_MULTI_WRITE =	0x6,
+	MT_VEND_MULTI_READ =	0x7,
+	MT_VEND_READ_EEPROM =	0x9,
+	MT_VEND_WRITE_FCE =	0x42,
+	MT_VEND_WRITE_CFG =	0x46,
+	MT_VEND_READ_CFG =	0x47,
+};
+
+enum mt76u_in_ep {
+	MT_EP_IN_PKT_RX,
+	MT_EP_IN_CMD_RESP,
+	__MT_EP_IN_MAX,
+};
+
+enum mt76u_out_ep {
+	MT_EP_OUT_INBAND_CMD,
+	MT_EP_OUT_AC_BK,
+	MT_EP_OUT_AC_BE,
+	MT_EP_OUT_AC_VI,
+	MT_EP_OUT_AC_VO,
+	MT_EP_OUT_HCCA,
+	__MT_EP_OUT_MAX,
+};
+
+#define MT_SG_MAX_SIZE		8
+#define MT_NUM_TX_ENTRIES	256
+#define MT_NUM_RX_ENTRIES	128
+#define MCU_RESP_URB_SIZE	1024
+struct mt76_usb {
+	struct mutex usb_ctrl_mtx;
+	u8 data[32];
+
+	struct tasklet_struct rx_tasklet;
+	struct tasklet_struct tx_tasklet;
+	struct delayed_work stat_work;
+
+	u8 out_ep[__MT_EP_OUT_MAX];
+	u16 out_max_packet;
+	u8 in_ep[__MT_EP_IN_MAX];
+	u16 in_max_packet;
+
+	struct mt76u_mcu {
+		struct mutex mutex;
+		struct completion cmpl;
+		struct mt76u_buf res;
+		u32 msg_seq;
+	} mcu;
+};
+
 struct mt76_dev {
 	struct ieee80211_hw *hw;
 	struct cfg80211_chan_def chandef;
@@ -276,6 +350,8 @@ struct mt76_dev {
 	char led_name[32];
 	bool led_al;
 	u8 led_pin;
+
+	struct mt76_usb usb;
 };
 
 enum mt76_phy_type {
@@ -407,6 +483,14 @@ static inline int mt76_decr(int val, int size)
 	return (val - 1) & (size - 1);
 }
 
+/* Hardware uses mirrored order of queues with Q3
+ * having the highest priority
+ */
+static inline u8 q2hwq(u8 q)
+{
+	return q ^ 0x3;
+}
+
 static inline struct ieee80211_txq *
 mtxq_to_txq(struct mt76_txq *mtxq)
 {
@@ -467,4 +551,61 @@ void mt76_rx_poll_complete(struct mt76_dev *dev, enum mt76_rxq_id q,
 			   struct napi_struct *napi);
 void mt76_rx_aggr_reorder(struct sk_buff *skb, struct sk_buff_head *frames);
 
+/* usb */
+static inline bool mt76u_urb_error(struct urb *urb)
+{
+	return urb->status &&
+	       urb->status != -ECONNRESET &&
+	       urb->status != -ESHUTDOWN &&
+	       urb->status != -ENOENT;
+}
+
+/* Map hardware queues to usb endpoints */
+static inline u8 q2ep(u8 qid)
+{
+	/* TODO: take management packets to queue 5 */
+	return qid + 1;
+}
+
+static inline bool mt76u_check_sg(struct mt76_dev *dev)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+
+	return (udev->bus->sg_tablesize > 0 &&
+		(udev->bus->no_sg_constraint ||
+		 udev->speed == USB_SPEED_WIRELESS));
+}
+
+int mt76u_vendor_request(struct mt76_dev *dev, u8 req,
+			 u8 req_type, u16 val, u16 offset,
+			 void *buf, size_t len);
+void mt76u_single_wr(struct mt76_dev *dev, const u8 req,
+		     const u16 offset, const u32 val);
+u32 mt76u_rr(struct mt76_dev *dev, u32 addr);
+void mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val);
+int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf);
+void mt76u_deinit(struct mt76_dev *dev);
+int mt76u_buf_alloc(struct mt76_dev *dev, struct mt76u_buf *buf,
+		    int nsgs, int len, int sglen, gfp_t gfp);
+void mt76u_buf_free(struct mt76u_buf *buf);
+int mt76u_submit_buf(struct mt76_dev *dev, int dir, int index,
+		     struct mt76u_buf *buf, gfp_t gfp,
+		     usb_complete_t complete_fn, void *context);
+int mt76u_submit_rx_buffers(struct mt76_dev *dev);
+int mt76u_alloc_queues(struct mt76_dev *dev);
+void mt76u_stop_queues(struct mt76_dev *dev);
+void mt76u_stop_stat_wk(struct mt76_dev *dev);
+void mt76u_queues_deinit(struct mt76_dev *dev);
+int mt76u_skb_dma_info(struct sk_buff *skb, int port, u32 flags);
+
+int mt76u_mcu_fw_send_data(struct mt76_dev *dev, const void *data,
+			   int data_len, u32 max_payload, u32 offset);
+void mt76u_mcu_complete_urb(struct urb *urb);
+struct sk_buff *mt76u_mcu_msg_alloc(const void *data, int len);
+int mt76u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
+		       int cmd, bool wait_resp);
+void mt76u_mcu_fw_reset(struct mt76_dev *dev);
+int mt76u_mcu_init_rx(struct mt76_dev *dev);
+
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
new file mode 100644
index 000000000000..7780b07543bb
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -0,0 +1,845 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76.h"
+#include "usb_trace.h"
+#include "dma.h"
+
+#define MT_VEND_REQ_MAX_RETRY	10
+#define MT_VEND_REQ_TOUT_MS	300
+
+/* should be called with usb_ctrl_mtx locked */
+static int __mt76u_vendor_request(struct mt76_dev *dev, u8 req,
+				  u8 req_type, u16 val, u16 offset,
+				  void *buf, size_t len)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	unsigned int pipe;
+	int i, ret;
+
+	pipe = (req_type & USB_DIR_IN) ? usb_rcvctrlpipe(udev, 0)
+				       : usb_sndctrlpipe(udev, 0);
+	for (i = 0; i < MT_VEND_REQ_MAX_RETRY; i++) {
+		if (test_bit(MT76_REMOVED, &dev->state))
+			return -EIO;
+
+		ret = usb_control_msg(udev, pipe, req, req_type, val,
+				      offset, buf, len, MT_VEND_REQ_TOUT_MS);
+		if (ret == -ENODEV)
+			set_bit(MT76_REMOVED, &dev->state);
+		if (ret >= 0 || ret == -ENODEV)
+			return ret;
+		usleep_range(5000, 10000);
+	}
+
+	dev_err(dev->dev, "vendor request req:%02x off:%04x failed:%d\n",
+		req, offset, ret);
+	return ret;
+}
+
+int mt76u_vendor_request(struct mt76_dev *dev, u8 req,
+			 u8 req_type, u16 val, u16 offset,
+			 void *buf, size_t len)
+{
+	int ret;
+
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	ret = __mt76u_vendor_request(dev, req, req_type,
+				     val, offset, buf, len);
+	trace_usb_reg_wr(dev, offset, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76u_vendor_request);
+
+/* should be called with usb_ctrl_mtx locked */
+static u32 __mt76u_rr(struct mt76_dev *dev, u32 addr)
+{
+	struct mt76_usb *usb = &dev->usb;
+	u32 data = ~0;
+	u16 offset;
+	int ret;
+	u8 req;
+
+	switch (addr & MT_VEND_TYPE_MASK) {
+	case MT_VEND_TYPE_EEPROM:
+		req = MT_VEND_READ_EEPROM;
+		break;
+	case MT_VEND_TYPE_CFG:
+		req = MT_VEND_READ_CFG;
+		break;
+	default:
+		req = MT_VEND_MULTI_READ;
+		break;
+	}
+	offset = addr & ~MT_VEND_TYPE_MASK;
+
+	ret = __mt76u_vendor_request(dev, req,
+				     USB_DIR_IN | USB_TYPE_VENDOR,
+				     0, offset, usb->data, sizeof(__le32));
+	if (ret == sizeof(__le32))
+		data = get_unaligned_le32(usb->data);
+	trace_usb_reg_rr(dev, addr, data);
+
+	return data;
+}
+
+u32 mt76u_rr(struct mt76_dev *dev, u32 addr)
+{
+	u32 ret;
+
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	ret = __mt76u_rr(dev, addr);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return ret;
+}
+
+/* should be called with usb_ctrl_mtx locked */
+static void __mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
+{
+	struct mt76_usb *usb = &dev->usb;
+	u16 offset;
+	u8 req;
+
+	switch (addr & MT_VEND_TYPE_MASK) {
+	case MT_VEND_TYPE_CFG:
+		req = MT_VEND_WRITE_CFG;
+		break;
+	default:
+		req = MT_VEND_MULTI_WRITE;
+		break;
+	}
+	offset = addr & ~MT_VEND_TYPE_MASK;
+
+	put_unaligned_le32(val, usb->data);
+	__mt76u_vendor_request(dev, req,
+			       USB_DIR_OUT | USB_TYPE_VENDOR, 0,
+			       offset, usb->data, sizeof(__le32));
+	trace_usb_reg_wr(dev, addr, val);
+}
+
+void mt76u_wr(struct mt76_dev *dev, u32 addr, u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	__mt76u_wr(dev, addr, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+}
+
+static u32 mt76u_rmw(struct mt76_dev *dev, u32 addr,
+		     u32 mask, u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	val |= __mt76u_rr(dev, addr) & ~mask;
+	__mt76u_wr(dev, addr, val);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+
+	return val;
+}
+
+static void mt76u_copy(struct mt76_dev *dev, u32 offset,
+		       const void *data, int len)
+{
+	struct mt76_usb *usb = &dev->usb;
+	const u32 *val = data;
+	int i, ret;
+
+	mutex_lock(&usb->usb_ctrl_mtx);
+	for (i = 0; i < (len / 4); i++) {
+		put_unaligned_le32(val[i], usb->data);
+		ret = __mt76u_vendor_request(dev, MT_VEND_MULTI_WRITE,
+					     USB_DIR_OUT | USB_TYPE_VENDOR,
+					     0, offset + i * 4, usb->data,
+					     sizeof(__le32));
+		if (ret < 0)
+			break;
+	}
+	mutex_unlock(&usb->usb_ctrl_mtx);
+}
+
+void mt76u_single_wr(struct mt76_dev *dev, const u8 req,
+		     const u16 offset, const u32 val)
+{
+	mutex_lock(&dev->usb.usb_ctrl_mtx);
+	__mt76u_vendor_request(dev, req,
+			       USB_DIR_OUT | USB_TYPE_VENDOR,
+			       val & 0xffff, offset, NULL, 0);
+	__mt76u_vendor_request(dev, req,
+			       USB_DIR_OUT | USB_TYPE_VENDOR,
+			       val >> 16, offset + 2, NULL, 0);
+	mutex_unlock(&dev->usb.usb_ctrl_mtx);
+}
+EXPORT_SYMBOL_GPL(mt76u_single_wr);
+
+static int
+mt76u_set_endpoints(struct usb_interface *intf,
+		    struct mt76_usb *usb)
+{
+	struct usb_host_interface *intf_desc = intf->cur_altsetting;
+	struct usb_endpoint_descriptor *ep_desc;
+	int i, in_ep = 0, out_ep = 0;
+
+	for (i = 0; i < intf_desc->desc.bNumEndpoints; i++) {
+		ep_desc = &intf_desc->endpoint[i].desc;
+
+		if (usb_endpoint_is_bulk_in(ep_desc) &&
+		    in_ep < __MT_EP_IN_MAX) {
+			usb->in_ep[in_ep] = usb_endpoint_num(ep_desc);
+			usb->in_max_packet = usb_endpoint_maxp(ep_desc);
+			in_ep++;
+		} else if (usb_endpoint_is_bulk_out(ep_desc) &&
+			   out_ep < __MT_EP_OUT_MAX) {
+			usb->out_ep[out_ep] = usb_endpoint_num(ep_desc);
+			usb->out_max_packet = usb_endpoint_maxp(ep_desc);
+			out_ep++;
+		}
+	}
+
+	if (in_ep != __MT_EP_IN_MAX || out_ep != __MT_EP_OUT_MAX)
+		return -EINVAL;
+	return 0;
+}
+
+static int
+mt76u_fill_rx_sg(struct mt76_dev *dev, struct mt76u_buf *buf,
+		 int nsgs, int len, int sglen)
+{
+	struct urb *urb = buf->urb;
+	int i;
+
+	for (i = 0; i < nsgs; i++) {
+		struct page *page;
+		void *data;
+		int offset;
+
+		data = netdev_alloc_frag(len);
+		if (!data)
+			break;
+
+		page = virt_to_head_page(data);
+		offset = data - page_address(page);
+		sg_set_page(&urb->sg[i], page, sglen, offset);
+	}
+
+	if (i < nsgs) {
+		int j;
+
+		for (j = nsgs; j < urb->num_sgs; j++)
+			skb_free_frag(sg_virt(&urb->sg[j]));
+		urb->num_sgs = i;
+	}
+
+	urb->num_sgs = max_t(int, i, urb->num_sgs);
+	buf->len = urb->num_sgs * sglen,
+	sg_init_marker(urb->sg, urb->num_sgs);
+
+	return i ? : -ENOMEM;
+}
+
+int mt76u_buf_alloc(struct mt76_dev *dev, struct mt76u_buf *buf,
+		    int nsgs, int len, int sglen, gfp_t gfp)
+{
+	buf->urb = usb_alloc_urb(0, gfp);
+	if (!buf->urb)
+		return -ENOMEM;
+
+	buf->urb->sg = devm_kzalloc(dev->dev, nsgs * sizeof(*buf->urb->sg),
+				    gfp);
+	if (!buf->urb->sg)
+		return -ENOMEM;
+
+	sg_init_table(buf->urb->sg, nsgs);
+	buf->dev = dev;
+
+	return mt76u_fill_rx_sg(dev, buf, nsgs, len, sglen);
+}
+EXPORT_SYMBOL_GPL(mt76u_buf_alloc);
+
+void mt76u_buf_free(struct mt76u_buf *buf)
+{
+	struct urb *urb = buf->urb;
+	int i;
+
+	for (i = 0; i < urb->num_sgs; i++)
+		skb_free_frag(sg_virt(&urb->sg[i]));
+	usb_free_urb(buf->urb);
+}
+EXPORT_SYMBOL_GPL(mt76u_buf_free);
+
+int mt76u_submit_buf(struct mt76_dev *dev, int dir, int index,
+		     struct mt76u_buf *buf, gfp_t gfp,
+		     usb_complete_t complete_fn, void *context)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	unsigned int pipe;
+
+	if (dir == USB_DIR_IN)
+		pipe = usb_rcvbulkpipe(udev, dev->usb.in_ep[index]);
+	else
+		pipe = usb_sndbulkpipe(udev, dev->usb.out_ep[index]);
+
+	usb_fill_bulk_urb(buf->urb, udev, pipe, NULL, buf->len,
+			  complete_fn, context);
+
+	return usb_submit_urb(buf->urb, gfp);
+}
+EXPORT_SYMBOL_GPL(mt76u_submit_buf);
+
+static inline struct mt76u_buf
+*mt76u_get_next_rx_entry(struct mt76_queue *q)
+{
+	struct mt76u_buf *buf = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (q->queued > 0) {
+		buf = &q->entry[q->head].ubuf;
+		q->head = (q->head + 1) % q->ndesc;
+		q->queued--;
+	}
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return buf;
+}
+
+static int mt76u_get_rx_entry_len(u8 *data, u32 data_len)
+{
+	u16 dma_len, min_len;
+
+	dma_len = get_unaligned_le16(data);
+	min_len = MT_DMA_HDR_LEN + MT_RX_RXWI_LEN +
+		  MT_FCE_INFO_LEN;
+
+	if (data_len < min_len || WARN_ON(!dma_len) ||
+	    WARN_ON(dma_len + MT_DMA_HDR_LEN > data_len) ||
+	    WARN_ON(dma_len & 0x3))
+		return -EINVAL;
+	return dma_len;
+}
+
+static int
+mt76u_process_rx_entry(struct mt76_dev *dev, struct urb *urb)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	u8 *data = sg_virt(&urb->sg[0]);
+	int data_len, len, nsgs = 1;
+	struct sk_buff *skb;
+
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->state))
+		return 0;
+
+	len = mt76u_get_rx_entry_len(data, urb->actual_length);
+	if (len < 0)
+		return 0;
+
+	skb = build_skb(data, q->buf_size);
+	if (!skb)
+		return 0;
+
+	data_len = min_t(int, len, urb->sg[0].length - MT_DMA_HDR_LEN);
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+	if (skb->tail + data_len > skb->end) {
+		dev_kfree_skb(skb);
+		return 1;
+	}
+
+	__skb_put(skb, data_len);
+	len -= data_len;
+
+	while (len > 0) {
+		data_len = min_t(int, len, urb->sg[nsgs].length);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				sg_page(&urb->sg[nsgs]),
+				urb->sg[nsgs].offset,
+				data_len, q->buf_size);
+		len -= data_len;
+		nsgs++;
+	}
+	dev->drv->rx_skb(dev, MT_RXQ_MAIN, skb);
+
+	return nsgs;
+}
+
+static void mt76u_complete_rx(struct urb *urb)
+{
+	struct mt76_dev *dev = urb->context;
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	unsigned long flags;
+
+	switch (urb->status) {
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+	case -ENOENT:
+		return;
+	default:
+		dev_err(dev->dev, "rx urb failed: %d\n", urb->status);
+		/* fall through */
+	case 0:
+		break;
+	}
+
+	spin_lock_irqsave(&q->lock, flags);
+	if (WARN_ONCE(q->entry[q->tail].ubuf.urb != urb, "rx urb mismatch"))
+		goto out;
+
+	q->tail = (q->tail + 1) % q->ndesc;
+	q->queued++;
+	tasklet_schedule(&dev->usb.rx_tasklet);
+out:
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+
+static void mt76u_rx_tasklet(unsigned long data)
+{
+	struct mt76_dev *dev = (struct mt76_dev *)data;
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int err, nsgs, buf_len = q->buf_size;
+	struct mt76u_buf *buf;
+
+	rcu_read_lock();
+
+	while (true) {
+		buf = mt76u_get_next_rx_entry(q);
+		if (!buf)
+			break;
+
+		nsgs = mt76u_process_rx_entry(dev, buf->urb);
+		if (nsgs > 0) {
+			err = mt76u_fill_rx_sg(dev, buf, nsgs,
+					       buf_len,
+					       SKB_WITH_OVERHEAD(buf_len));
+			if (err < 0)
+				break;
+		}
+		mt76u_submit_buf(dev, USB_DIR_IN, MT_EP_IN_PKT_RX,
+				 buf, GFP_ATOMIC,
+				 mt76u_complete_rx, dev);
+	}
+	mt76_rx_poll_complete(dev, MT_RXQ_MAIN, NULL);
+
+	rcu_read_unlock();
+}
+
+int mt76u_submit_rx_buffers(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	unsigned long flags;
+	int i, err = 0;
+
+	spin_lock_irqsave(&q->lock, flags);
+	for (i = 0; i < q->ndesc; i++) {
+		err = mt76u_submit_buf(dev, USB_DIR_IN, MT_EP_IN_PKT_RX,
+				       &q->entry[i].ubuf, GFP_ATOMIC,
+				       mt76u_complete_rx, dev);
+		if (err < 0)
+			break;
+	}
+	q->head = q->tail = 0;
+	q->queued = 0;
+	spin_unlock_irqrestore(&q->lock, flags);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_submit_rx_buffers);
+
+static int mt76u_alloc_rx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int i, err, nsgs;
+
+	spin_lock_init(&q->lock);
+	q->entry = devm_kzalloc(dev->dev,
+				MT_NUM_RX_ENTRIES * sizeof(*q->entry),
+				GFP_KERNEL);
+	if (!q->entry)
+		return -ENOMEM;
+
+	if (mt76u_check_sg(dev)) {
+		q->buf_size = MT_RX_BUF_SIZE;
+		nsgs = MT_SG_MAX_SIZE;
+	} else {
+		q->buf_size = PAGE_SIZE;
+		nsgs = 1;
+	}
+
+	for (i = 0; i < MT_NUM_RX_ENTRIES; i++) {
+		err = mt76u_buf_alloc(dev, &q->entry[i].ubuf,
+				      nsgs, q->buf_size,
+				      SKB_WITH_OVERHEAD(q->buf_size),
+				      GFP_KERNEL);
+		if (err < 0)
+			return err;
+	}
+	q->ndesc = MT_NUM_RX_ENTRIES;
+
+	return mt76u_submit_rx_buffers(dev);
+}
+
+static void mt76u_free_rx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int i;
+
+	for (i = 0; i < q->ndesc; i++)
+		mt76u_buf_free(&q->entry[i].ubuf);
+}
+
+static void mt76u_stop_rx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+	int i;
+
+	for (i = 0; i < q->ndesc; i++)
+		usb_kill_urb(q->entry[i].ubuf.urb);
+}
+
+int mt76u_skb_dma_info(struct sk_buff *skb, int port, u32 flags)
+{
+	struct sk_buff *iter, *last = skb;
+	u32 info, pad;
+
+	/* Buffer layout:
+	 *	|   4B   | xfer len |      pad       |  4B  |
+	 *	| TXINFO | pkt/cmd  | zero pad to 4B | zero |
+	 *
+	 * length field of TXINFO should be set to 'xfer len'.
+	 */
+	info = FIELD_PREP(MT_TXD_INFO_LEN, round_up(skb->len, 4)) |
+	       FIELD_PREP(MT_TXD_INFO_DPORT, port) | flags;
+	put_unaligned_le32(info, skb_push(skb, sizeof(info)));
+
+	pad = round_up(skb->len, 4) + 4 - skb->len;
+	skb_walk_frags(skb, iter) {
+		last = iter;
+		if (!iter->next) {
+			skb->data_len += pad;
+			skb->len += pad;
+			break;
+		}
+	}
+
+	if (unlikely(pad)) {
+		if (__skb_pad(last, pad, true))
+			return -ENOMEM;
+		__skb_put(last, pad);
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mt76u_skb_dma_info);
+
+static void mt76u_tx_tasklet(unsigned long data)
+{
+	struct mt76_dev *dev = (struct mt76_dev *)data;
+	struct mt76u_buf *buf;
+	struct mt76_queue *q;
+	bool wake;
+	int i;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+
+		spin_lock_bh(&q->lock);
+		while (true) {
+			buf = &q->entry[q->head].ubuf;
+			if (!buf->done || !q->queued)
+				break;
+
+			dev->drv->tx_complete_skb(dev, q,
+						  &q->entry[q->head],
+						  false);
+
+			if (q->entry[q->head].schedule) {
+				q->entry[q->head].schedule = false;
+				q->swq_queued--;
+			}
+
+			q->head = (q->head + 1) % q->ndesc;
+			q->queued--;
+		}
+		mt76_txq_schedule(dev, q);
+		wake = i < IEEE80211_NUM_ACS && q->queued < q->ndesc - 8;
+		if (!q->queued)
+			wake_up(&dev->tx_wait);
+
+		spin_unlock_bh(&q->lock);
+
+		if (!test_and_set_bit(MT76_READING_STATS, &dev->state))
+			ieee80211_queue_delayed_work(dev->hw,
+						     &dev->usb.stat_work,
+						     msecs_to_jiffies(10));
+
+		if (wake)
+			ieee80211_wake_queue(dev->hw, i);
+	}
+}
+
+static void mt76u_tx_status_data(struct work_struct *work)
+{
+	struct mt76_usb *usb;
+	struct mt76_dev *dev;
+	u8 update = 1;
+	u16 count = 0;
+
+	usb = container_of(work, struct mt76_usb, stat_work.work);
+	dev = container_of(usb, struct mt76_dev, usb);
+
+	while (true) {
+		if (test_bit(MT76_REMOVED, &dev->state))
+			break;
+
+		if (!dev->drv->tx_status_data(dev, &update))
+			break;
+		count++;
+	}
+
+	if (count && test_bit(MT76_STATE_RUNNING, &dev->state))
+		ieee80211_queue_delayed_work(dev->hw, &usb->stat_work,
+					     msecs_to_jiffies(10));
+	else
+		clear_bit(MT76_READING_STATS, &dev->state);
+}
+
+static void mt76u_complete_tx(struct urb *urb)
+{
+	struct mt76u_buf *buf = urb->context;
+	struct mt76_dev *dev = buf->dev;
+
+	if (mt76u_urb_error(urb))
+		dev_err(dev->dev, "tx urb failed: %d\n", urb->status);
+	buf->done = true;
+
+	tasklet_schedule(&dev->usb.tx_tasklet);
+}
+
+static int
+mt76u_tx_build_sg(struct sk_buff *skb, struct urb *urb)
+{
+	int nsgs = 1 + skb_shinfo(skb)->nr_frags;
+	struct sk_buff *iter;
+
+	skb_walk_frags(skb, iter)
+		nsgs += 1 + skb_shinfo(iter)->nr_frags;
+
+	memset(urb->sg, 0, sizeof(*urb->sg) * MT_SG_MAX_SIZE);
+
+	nsgs = min_t(int, MT_SG_MAX_SIZE, nsgs);
+	sg_init_marker(urb->sg, nsgs);
+	urb->num_sgs = nsgs;
+
+	return skb_to_sgvec_nomark(skb, urb->sg, 0, skb->len);
+}
+
+static int
+mt76u_tx_queue_skb(struct mt76_dev *dev, struct mt76_queue *q,
+		   struct sk_buff *skb, struct mt76_wcid *wcid,
+		   struct ieee80211_sta *sta)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	u8 ep = q2ep(q->hw_idx);
+	struct mt76u_buf *buf;
+	u16 idx = q->tail;
+	unsigned int pipe;
+	int err;
+
+	if (q->queued == q->ndesc)
+		return -ENOSPC;
+
+	err = dev->drv->tx_prepare_skb(dev, NULL, skb, q, wcid, sta, NULL);
+	if (err < 0)
+		return err;
+
+	buf = &q->entry[idx].ubuf;
+	buf->done = false;
+
+	err = mt76u_tx_build_sg(skb, buf->urb);
+	if (err < 0)
+		return err;
+
+	pipe = usb_sndbulkpipe(udev, dev->usb.out_ep[ep]);
+	usb_fill_bulk_urb(buf->urb, udev, pipe, NULL, skb->len,
+			  mt76u_complete_tx, buf);
+
+	q->tail = (q->tail + 1) % q->ndesc;
+	q->entry[idx].skb = skb;
+	q->queued++;
+
+	return idx;
+}
+
+static void mt76u_tx_kick(struct mt76_dev *dev, struct mt76_queue *q)
+{
+	struct mt76u_buf *buf;
+	int err;
+
+	while (q->first != q->tail) {
+		buf = &q->entry[q->first].ubuf;
+		err = usb_submit_urb(buf->urb, GFP_ATOMIC);
+		if (err < 0) {
+			if (err == -ENODEV)
+				set_bit(MT76_REMOVED, &dev->state);
+			else
+				dev_err(dev->dev, "tx urb submit failed:%d\n",
+					err);
+			break;
+		}
+		q->first = (q->first + 1) % q->ndesc;
+	}
+}
+
+static int mt76u_alloc_tx(struct mt76_dev *dev)
+{
+	struct mt76u_buf *buf;
+	struct mt76_queue *q;
+	size_t size;
+	int i, j;
+
+	size = MT_SG_MAX_SIZE * sizeof(struct scatterlist);
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+		spin_lock_init(&q->lock);
+		INIT_LIST_HEAD(&q->swq);
+		q->hw_idx = q2hwq(i);
+
+		q->entry = devm_kzalloc(dev->dev,
+					MT_NUM_TX_ENTRIES * sizeof(*q->entry),
+					GFP_KERNEL);
+		if (!q->entry)
+			return -ENOMEM;
+
+		q->ndesc = MT_NUM_TX_ENTRIES;
+		for (j = 0; j < q->ndesc; j++) {
+			buf = &q->entry[j].ubuf;
+			buf->dev = dev;
+
+			buf->urb = usb_alloc_urb(0, GFP_KERNEL);
+			if (!buf->urb)
+				return -ENOMEM;
+
+			buf->urb->sg = devm_kzalloc(dev->dev, size, GFP_KERNEL);
+			if (!buf->urb->sg)
+				return -ENOMEM;
+		}
+	}
+	return 0;
+}
+
+static void mt76u_free_tx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q;
+	int i, j;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+		for (j = 0; j < q->ndesc; j++)
+			usb_free_urb(q->entry[j].ubuf.urb);
+	}
+}
+
+static void mt76u_stop_tx(struct mt76_dev *dev)
+{
+	struct mt76_queue *q;
+	int i, j;
+
+	for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+		q = &dev->q_tx[i];
+		for (j = 0; j < q->ndesc; j++)
+			usb_kill_urb(q->entry[j].ubuf.urb);
+	}
+}
+
+void mt76u_stop_queues(struct mt76_dev *dev)
+{
+	tasklet_disable(&dev->usb.rx_tasklet);
+	tasklet_disable(&dev->usb.tx_tasklet);
+
+	mt76u_stop_rx(dev);
+	mt76u_stop_tx(dev);
+}
+EXPORT_SYMBOL_GPL(mt76u_stop_queues);
+
+void mt76u_stop_stat_wk(struct mt76_dev *dev)
+{
+	cancel_delayed_work_sync(&dev->usb.stat_work);
+	clear_bit(MT76_READING_STATS, &dev->state);
+}
+EXPORT_SYMBOL_GPL(mt76u_stop_stat_wk);
+
+void mt76u_queues_deinit(struct mt76_dev *dev)
+{
+	mt76u_stop_queues(dev);
+
+	mt76u_free_rx(dev);
+	mt76u_free_tx(dev);
+}
+EXPORT_SYMBOL_GPL(mt76u_queues_deinit);
+
+int mt76u_alloc_queues(struct mt76_dev *dev)
+{
+	int err;
+
+	err = mt76u_alloc_rx(dev);
+	if (err < 0)
+		goto err;
+
+	err = mt76u_alloc_tx(dev);
+	if (err < 0)
+		goto err;
+
+	return 0;
+err:
+	mt76u_queues_deinit(dev);
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_alloc_queues);
+
+static const struct mt76_queue_ops usb_queue_ops = {
+	.tx_queue_skb = mt76u_tx_queue_skb,
+	.kick = mt76u_tx_kick,
+};
+
+int mt76u_init(struct mt76_dev *dev,
+	       struct usb_interface *intf)
+{
+	static const struct mt76_bus_ops mt76u_ops = {
+		.rr = mt76u_rr,
+		.wr = mt76u_wr,
+		.rmw = mt76u_rmw,
+		.copy = mt76u_copy,
+	};
+	struct mt76_usb *usb = &dev->usb;
+
+	tasklet_init(&usb->rx_tasklet, mt76u_rx_tasklet, (unsigned long)dev);
+	tasklet_init(&usb->tx_tasklet, mt76u_tx_tasklet, (unsigned long)dev);
+	INIT_DELAYED_WORK(&usb->stat_work, mt76u_tx_status_data);
+	skb_queue_head_init(&dev->rx_skb[MT_RXQ_MAIN]);
+
+	init_completion(&usb->mcu.cmpl);
+	mutex_init(&usb->mcu.mutex);
+
+	mutex_init(&usb->usb_ctrl_mtx);
+	dev->bus = &mt76u_ops;
+	dev->queue_ops = &usb_queue_ops;
+
+	return mt76u_set_endpoints(intf, usb);
+}
+EXPORT_SYMBOL_GPL(mt76u_init);
+
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/usb_mcu.c b/drivers/net/wireless/mediatek/mt76/usb_mcu.c
new file mode 100644
index 000000000000..070be803d463
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb_mcu.c
@@ -0,0 +1,242 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/firmware.h>
+
+#include "mt76.h"
+#include "dma.h"
+
+#define MT_CMD_HDR_LEN			4
+
+#define MT_FCE_DMA_ADDR			0x0230
+#define MT_FCE_DMA_LEN			0x0234
+
+#define MT_TX_CPU_FROM_FCE_CPU_DESC_IDX	0x09a8
+
+struct sk_buff *mt76u_mcu_msg_alloc(const void *data, int len)
+{
+	struct sk_buff *skb;
+
+	skb = alloc_skb(MT_CMD_HDR_LEN + len + 8, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	skb_reserve(skb, MT_CMD_HDR_LEN);
+	skb_put_data(skb, data, len);
+
+	return skb;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_msg_alloc);
+
+void mt76u_mcu_complete_urb(struct urb *urb)
+{
+	struct completion *cmpl = urb->context;
+
+	complete(cmpl);
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_complete_urb);
+
+static int mt76u_mcu_wait_resp(struct mt76_dev *dev, u8 seq)
+{
+	struct mt76_usb *usb = &dev->usb;
+	struct mt76u_buf *buf = &usb->mcu.res;
+	int i, ret;
+	u32 rxfce;
+
+	for (i = 0; i < 5; i++) {
+		if (!wait_for_completion_timeout(&usb->mcu.cmpl,
+						 msecs_to_jiffies(300)))
+			continue;
+
+		if (buf->urb->status)
+			return -EIO;
+
+		rxfce = get_unaligned_le32(sg_virt(&buf->urb->sg[0]));
+		ret = mt76u_submit_buf(dev, USB_DIR_IN,
+				       MT_EP_IN_CMD_RESP,
+				       buf, GFP_KERNEL,
+				       mt76u_mcu_complete_urb,
+				       &usb->mcu.cmpl);
+		if (ret)
+			return ret;
+
+		if (seq == FIELD_GET(MT_RX_FCE_INFO_CMD_SEQ, rxfce))
+			return 0;
+
+		dev_err(dev->dev, "error: MCU resp evt:%lx seq:%hhx-%lx\n",
+			FIELD_GET(MT_RX_FCE_INFO_EVT_TYPE, rxfce),
+			seq, FIELD_GET(MT_RX_FCE_INFO_CMD_SEQ, rxfce));
+	}
+
+	dev_err(dev->dev, "error: %s timed out\n", __func__);
+	return -ETIMEDOUT;
+}
+
+int mt76u_mcu_send_msg(struct mt76_dev *dev, struct sk_buff *skb,
+		       int cmd, bool wait_resp)
+{
+	struct usb_interface *intf = to_usb_interface(dev->dev);
+	struct usb_device *udev = interface_to_usbdev(intf);
+	struct mt76_usb *usb = &dev->usb;
+	unsigned int pipe;
+	int ret, sent;
+	u8 seq = 0;
+	u32 info;
+
+	if (test_bit(MT76_REMOVED, &dev->state))
+		return 0;
+
+	mutex_lock(&usb->mcu.mutex);
+
+	pipe = usb_sndbulkpipe(udev, usb->out_ep[MT_EP_OUT_INBAND_CMD]);
+	if (wait_resp) {
+		seq = ++usb->mcu.msg_seq & 0xf;
+		if (!seq)
+			seq = ++usb->mcu.msg_seq & 0xf;
+	}
+
+	info = FIELD_PREP(MT_MCU_MSG_CMD_SEQ, seq) |
+	       FIELD_PREP(MT_MCU_MSG_CMD_TYPE, cmd) |
+	       MT_MCU_MSG_TYPE_CMD;
+	ret = mt76u_skb_dma_info(skb, CPU_TX_PORT, info);
+	if (ret)
+		goto out;
+
+	ret = usb_bulk_msg(udev, pipe, skb->data, skb->len, &sent, 500);
+	if (ret)
+		goto out;
+
+	if (wait_resp)
+		ret = mt76u_mcu_wait_resp(dev, seq);
+
+out:
+	mutex_unlock(&usb->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_send_msg);
+
+void mt76u_mcu_fw_reset(struct mt76_dev *dev)
+{
+	mt76u_vendor_request(dev, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR,
+			     0x1, 0, NULL, 0);
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_fw_reset);
+
+static int
+__mt76u_mcu_fw_send_data(struct mt76_dev *dev, struct mt76u_buf *buf,
+			 const void *fw_data, int len, u32 dst_addr)
+{
+	u8 *data = sg_virt(&buf->urb->sg[0]);
+	DECLARE_COMPLETION_ONSTACK(cmpl);
+	__le32 info;
+	u32 val;
+	int err;
+
+	info = cpu_to_le32(FIELD_PREP(MT_MCU_MSG_PORT, CPU_TX_PORT) |
+			   FIELD_PREP(MT_MCU_MSG_LEN, len) |
+			   MT_MCU_MSG_TYPE_CMD);
+
+	memcpy(data, &info, sizeof(info));
+	memcpy(data + sizeof(info), fw_data, len);
+	memset(data + sizeof(info) + len, 0, 4);
+
+	mt76u_single_wr(dev, MT_VEND_WRITE_FCE,
+			MT_FCE_DMA_ADDR, dst_addr);
+	len = roundup(len, 4);
+	mt76u_single_wr(dev, MT_VEND_WRITE_FCE,
+			MT_FCE_DMA_LEN, len << 16);
+
+	buf->len = MT_CMD_HDR_LEN + len + sizeof(info);
+	err = mt76u_submit_buf(dev, USB_DIR_OUT,
+			       MT_EP_OUT_INBAND_CMD,
+			       buf, GFP_KERNEL,
+			       mt76u_mcu_complete_urb, &cmpl);
+	if (err < 0)
+		return err;
+
+	if (!wait_for_completion_timeout(&cmpl,
+					 msecs_to_jiffies(1000))) {
+		dev_err(dev->dev, "firmware upload timed out\n");
+		usb_kill_urb(buf->urb);
+		return -ETIMEDOUT;
+	}
+
+	if (mt76u_urb_error(buf->urb)) {
+		dev_err(dev->dev, "firmware upload failed: %d\n",
+			buf->urb->status);
+		return buf->urb->status;
+	}
+
+	val = mt76u_rr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX);
+	val++;
+	mt76u_wr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX, val);
+
+	return 0;
+}
+
+int mt76u_mcu_fw_send_data(struct mt76_dev *dev, const void *data,
+			   int data_len, u32 max_payload, u32 offset)
+{
+	int err, len, pos = 0, max_len = max_payload - 8;
+	struct mt76u_buf buf;
+
+	err = mt76u_buf_alloc(dev, &buf, 1, max_payload, max_payload,
+			      GFP_KERNEL);
+	if (err < 0)
+		return err;
+
+	while (data_len > 0) {
+		len = min_t(int, data_len, max_len);
+		err = __mt76u_mcu_fw_send_data(dev, &buf, data + pos,
+					       len, offset + pos);
+		if (err < 0)
+			break;
+
+		data_len -= len;
+		pos += len;
+		usleep_range(5000, 10000);
+	}
+	mt76u_buf_free(&buf);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_fw_send_data);
+
+int mt76u_mcu_init_rx(struct mt76_dev *dev)
+{
+	struct mt76_usb *usb = &dev->usb;
+	int err;
+
+	err = mt76u_buf_alloc(dev, &usb->mcu.res, 1,
+			      MCU_RESP_URB_SIZE, MCU_RESP_URB_SIZE,
+			      GFP_KERNEL);
+	if (err < 0)
+		return err;
+
+	err = mt76u_submit_buf(dev, USB_DIR_IN, MT_EP_IN_CMD_RESP,
+			       &usb->mcu.res, GFP_KERNEL,
+			       mt76u_mcu_complete_urb,
+			       &usb->mcu.cmpl);
+	if (err < 0)
+		mt76u_buf_free(&usb->mcu.res);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mt76u_mcu_init_rx);
diff --git a/drivers/net/wireless/mediatek/mt76/usb_trace.c b/drivers/net/wireless/mediatek/mt76/usb_trace.c
new file mode 100644
index 000000000000..7e1f540f0b7a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb_trace.c
@@ -0,0 +1,23 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "usb_trace.h"
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/usb_trace.h b/drivers/net/wireless/mediatek/mt76/usb_trace.h
new file mode 100644
index 000000000000..52db7012304a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/usb_trace.h
@@ -0,0 +1,71 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#if !defined(__MT76_USB_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __MT76_USB_TRACE_H
+
+#include <linux/tracepoint.h>
+#include "mt76.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mt76_usb
+
+#define MAXNAME		32
+#define DEV_ENTRY   __array(char, wiphy_name, 32)
+#define DEV_ASSIGN  strlcpy(__entry->wiphy_name, wiphy_name(dev->hw->wiphy), MAXNAME)
+#define DEV_PR_FMT  "%s"
+#define DEV_PR_ARG  __entry->wiphy_name
+
+#define REG_ENTRY	__field(u32, reg) __field(u32, val)
+#define REG_ASSIGN	__entry->reg = reg; __entry->val = val
+#define REG_PR_FMT	" %04x=%08x"
+#define REG_PR_ARG	__entry->reg, __entry->val
+
+DECLARE_EVENT_CLASS(dev_reg_evt,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		REG_ENTRY
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		REG_ASSIGN;
+	),
+	TP_printk(
+		DEV_PR_FMT REG_PR_FMT,
+		DEV_PR_ARG, REG_PR_ARG
+	)
+);
+
+DEFINE_EVENT(dev_reg_evt, usb_reg_rr,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+DEFINE_EVENT(dev_reg_evt, usb_reg_wr,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE usb_trace
+
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From ee676cd5017c5f71b8aac1f2d1016ba0f6e4f348 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Date: Tue, 31 Jul 2018 10:09:20 +0200
Subject: mt76: add driver code for MT76x2u based devices

MT76x2u is a 2x2 USB 802.11ac chipset by MediaTek. This driver currently
support station mode

Tested-by: <cug_yangyuancong@hotmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo.bianconi@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Kconfig        |  10 +
 drivers/net/wireless/mediatek/mt76/Makefile       |   5 +
 drivers/net/wireless/mediatek/mt76/mt76x2.h       |   4 +
 drivers/net/wireless/mediatek/mt76/mt76x2_regs.h  |  30 ++
 drivers/net/wireless/mediatek/mt76/mt76x2_usb.c   | 142 +++++++
 drivers/net/wireless/mediatek/mt76/mt76x2u.h      |  83 ++++
 drivers/net/wireless/mediatek/mt76/mt76x2u_core.c | 108 +++++
 drivers/net/wireless/mediatek/mt76/mt76x2u_init.c | 318 +++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c  | 240 +++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2u_main.c | 185 +++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c  | 463 ++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c  | 303 ++++++++++++++
 12 files changed, 1891 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2_usb.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2u.h
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2u_core.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2u_init.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2u_main.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c

diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index ba17cdd46ea3..69906c733a1c 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -17,3 +17,13 @@ config MT76x2E
 	depends on PCI
 	---help---
 	  This adds support for MT7612/MT7602/MT7662-based wireless PCIe devices.
+
+config MT76x2U
+	tristate "MediaTek MT76x2U (USB) support"
+	select MT76_CORE
+	select MT76_USB
+	select MT76x2_COMMON
+	depends on MAC80211
+	depends on USB
+	help
+	  This adds support for MT7612U-based wireless USB dongles.
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index de0a4bc235d1..dfe1c1ba60db 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_MT76_CORE) += mt76.o
 obj-$(CONFIG_MT76_USB) += mt76-usb.o
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2-common.o
 obj-$(CONFIG_MT76x2E) += mt76x2e.o
+obj-$(CONFIG_MT76x2U) += mt76x2u.o
 
 mt76-y := \
 	mmio.o util.o trace.o dma.o mac80211.o debugfs.o eeprom.o tx.o agg-rx.o
@@ -22,4 +23,8 @@ mt76x2e-y := \
 	mt76x2_core.o mt76x2_mac.o mt76x2_mcu.o mt76x2_phy.o \
 	mt76x2_dfs.o mt76x2_trace.o
 
+mt76x2u-y := \
+	mt76x2_usb.o mt76x2u_init.o mt76x2u_main.o mt76x2u_mac.o \
+	mt76x2u_mcu.o mt76x2u_phy.o mt76x2u_core.o
+
 CFLAGS_mt76x2_trace.o := -I$(src)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2.h b/drivers/net/wireless/mediatek/mt76/mt76x2.h
index 624ae804395a..dca3209bf5f1 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2.h
@@ -33,6 +33,9 @@
 #define MT7662_ROM_PATCH	"mt7662_rom_patch.bin"
 #define MT7662_EEPROM_SIZE	512
 
+#define MT7662U_FIRMWARE	"mediatek/mt7662u.bin"
+#define MT7662U_ROM_PATCH	"mediatek/mt7662u_rom_patch.bin"
+
 #define MT76x2_RX_RING_SIZE	256
 #define MT_RX_HEADROOM		32
 
@@ -55,6 +58,7 @@ struct mt76x2_mcu {
 
 	wait_queue_head_t wait;
 	struct sk_buff_head res_q;
+	struct mt76u_buf res_u;
 
 	u32 msg_seq;
 };
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h b/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h
index b9c334d9e5b8..1551ea453180 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_regs.h
@@ -75,6 +75,21 @@
 
 #define MT_XO_CTRL7			0x011c
 
+#define MT_USB_U3DMA_CFG		0x9018
+#define MT_USB_DMA_CFG_RX_BULK_AGG_TOUT	GENMASK(7, 0)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_LMT	GENMASK(15, 8)
+#define MT_USB_DMA_CFG_UDMA_TX_WL_DROP	BIT(16)
+#define MT_USB_DMA_CFG_WAKE_UP_EN	BIT(17)
+#define MT_USB_DMA_CFG_RX_DROP_OR_PAD	BIT(18)
+#define MT_USB_DMA_CFG_TX_CLR		BIT(19)
+#define MT_USB_DMA_CFG_TXOP_HALT	BIT(20)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_EN	BIT(21)
+#define MT_USB_DMA_CFG_RX_BULK_EN	BIT(22)
+#define MT_USB_DMA_CFG_TX_BULK_EN	BIT(23)
+#define MT_USB_DMA_CFG_EP_OUT_VALID	GENMASK(29, 24)
+#define MT_USB_DMA_CFG_RX_BUSY		BIT(30)
+#define MT_USB_DMA_CFG_TX_BUSY		BIT(31)
+
 #define MT_WLAN_MTC_CTRL		0x10148
 #define MT_WLAN_MTC_CTRL_MTCMOS_PWR_UP	BIT(0)
 #define MT_WLAN_MTC_CTRL_PWR_ACK	BIT(12)
@@ -150,6 +165,9 @@
 #define MT_TX_HW_QUEUE_MCU		8
 #define MT_TX_HW_QUEUE_MGMT		9
 
+#define MT_US_CYC_CFG			0x02a4
+#define MT_US_CYC_CNT			GENMASK(7, 0)
+
 #define MT_PBF_SYS_CTRL			0x0400
 #define MT_PBF_SYS_CTRL_MCU_RESET	BIT(0)
 #define MT_PBF_SYS_CTRL_DMA_RESET	BIT(1)
@@ -202,6 +220,11 @@
 
 #define MT_FCE_WLAN_FLOW_CONTROL1	0x0824
 
+#define MT_TX_CPU_FROM_FCE_BASE_PTR	0x09a0
+#define MT_TX_CPU_FROM_FCE_MAX_COUNT	0x09a4
+#define MT_FCE_PDMA_GLOBAL_CONF		0x09c4
+#define MT_FCE_SKIP_FS			0x0a6c
+
 #define MT_PAUSE_ENABLE_CONTROL1	0x0a38
 
 #define MT_MAC_CSR0			0x1000
@@ -214,6 +237,7 @@
 
 #define MT_MAC_ADDR_DW0			0x1008
 #define MT_MAC_ADDR_DW1			0x100c
+#define MT_MAC_ADDR_DW1_U2ME_MASK	GENMASK(23, 16)
 
 #define MT_MAC_BSSID_DW0		0x1010
 #define MT_MAC_BSSID_DW1		0x1014
@@ -351,6 +375,7 @@
 #define MT_TX_TIMEOUT_CFG_ACKTO		GENMASK(15, 8)
 
 #define MT_TX_RETRY_CFG			0x134c
+#define MT_TX_LINK_CFG			0x1350
 #define MT_VHT_HT_FBK_CFG1		0x1358
 
 #define MT_PROT_CFG_RATE		GENMASK(15, 0)
@@ -425,6 +450,7 @@
 #define MT_RX_FILTR_CFG_BAR		BIT(15)
 #define MT_RX_FILTR_CFG_CTRL_RSV	BIT(16)
 
+#define MT_AUTO_RSP_CFG			0x1404
 #define MT_LEGACY_BASIC_RATE		0x1408
 #define MT_HT_BASIC_RATE		0x140c
 
@@ -460,6 +486,10 @@
 #define MT_RX_STAT_2_DUP_ERRORS		GENMASK(15, 0)
 #define MT_RX_STAT_2_OVERFLOW_ERRORS	GENMASK(31, 16)
 
+#define MT_TX_STA_0			0x170c
+#define MT_TX_STA_1			0x1710
+#define MT_TX_STA_2			0x1714
+
 #define MT_TX_STAT_FIFO			0x1718
 #define MT_TX_STAT_FIFO_VALID		BIT(0)
 #define MT_TX_STAT_FIFO_SUCCESS		BIT(5)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2_usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2_usb.c
new file mode 100644
index 000000000000..1428cfdee579
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2_usb.c
@@ -0,0 +1,142 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "mt76x2u.h"
+
+static const struct usb_device_id mt76x2u_device_table[] = {
+	{ USB_DEVICE(0x0b05, 0x1833) },	/* Asus USB-AC54 */
+	{ USB_DEVICE(0x0b05, 0x17eb) },	/* Asus USB-AC55 */
+	{ USB_DEVICE(0x0b05, 0x180b) },	/* Asus USB-N53 B1 */
+	{ USB_DEVICE(0x0e8d, 0x7612) },	/* Aukey USB-AC1200 */
+	{ USB_DEVICE(0x057c, 0x8503) },	/* Avm FRITZ!WLAN AC860 */
+	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax EW 7722 UAC */
+	{ USB_DEVICE(0x0846, 0x9053) },	/* Netgear A6210 */
+	{ USB_DEVICE(0x045e, 0x02e6) },	/* XBox One Wireless Adapter */
+	{ },
+};
+
+static int mt76x2u_probe(struct usb_interface *intf,
+			 const struct usb_device_id *id)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	struct mt76x2_dev *dev;
+	int err;
+
+	dev = mt76x2u_alloc_device(&intf->dev);
+	if (!dev)
+		return -ENOMEM;
+
+	udev = usb_get_dev(udev);
+	usb_reset_device(udev);
+
+	err = mt76u_init(&dev->mt76, intf);
+	if (err < 0)
+		goto err;
+
+	dev->mt76.rev = mt76_rr(dev, MT_ASIC_VERSION);
+	dev_info(dev->mt76.dev, "ASIC revision: %08x\n", dev->mt76.rev);
+
+	err = mt76x2u_register_device(dev);
+	if (err < 0)
+		goto err;
+
+	return 0;
+
+err:
+	ieee80211_free_hw(mt76_hw(dev));
+	usb_set_intfdata(intf, NULL);
+	usb_put_dev(udev);
+
+	return err;
+}
+
+static void mt76x2u_disconnect(struct usb_interface *intf)
+{
+	struct usb_device *udev = interface_to_usbdev(intf);
+	struct mt76x2_dev *dev = usb_get_intfdata(intf);
+	struct ieee80211_hw *hw = mt76_hw(dev);
+
+	set_bit(MT76_REMOVED, &dev->mt76.state);
+	ieee80211_unregister_hw(hw);
+	mt76x2u_cleanup(dev);
+
+	ieee80211_free_hw(hw);
+	usb_set_intfdata(intf, NULL);
+	usb_put_dev(udev);
+}
+
+static int __maybe_unused mt76x2u_suspend(struct usb_interface *intf,
+					  pm_message_t state)
+{
+	struct mt76x2_dev *dev = usb_get_intfdata(intf);
+	struct mt76_usb *usb = &dev->mt76.usb;
+
+	mt76u_stop_queues(&dev->mt76);
+	mt76x2u_stop_hw(dev);
+	usb_kill_urb(usb->mcu.res.urb);
+
+	return 0;
+}
+
+static int __maybe_unused mt76x2u_resume(struct usb_interface *intf)
+{
+	struct mt76x2_dev *dev = usb_get_intfdata(intf);
+	struct mt76_usb *usb = &dev->mt76.usb;
+	int err;
+
+	reinit_completion(&usb->mcu.cmpl);
+	err = mt76u_submit_buf(&dev->mt76, USB_DIR_IN,
+			       MT_EP_IN_CMD_RESP,
+			       &usb->mcu.res, GFP_KERNEL,
+			       mt76u_mcu_complete_urb,
+			       &usb->mcu.cmpl);
+	if (err < 0)
+		return err;
+
+	err = mt76u_submit_rx_buffers(&dev->mt76);
+	if (err < 0)
+		return err;
+
+	tasklet_enable(&usb->rx_tasklet);
+	tasklet_enable(&usb->tx_tasklet);
+
+	return mt76x2u_init_hardware(dev);
+}
+
+MODULE_DEVICE_TABLE(usb, mt76x2u_device_table);
+MODULE_FIRMWARE(MT7662U_FIRMWARE);
+MODULE_FIRMWARE(MT7662U_ROM_PATCH);
+
+static struct usb_driver mt76x2u_driver = {
+	.name		= KBUILD_MODNAME,
+	.id_table	= mt76x2u_device_table,
+	.probe		= mt76x2u_probe,
+	.disconnect	= mt76x2u_disconnect,
+#ifdef CONFIG_PM
+	.suspend	= mt76x2u_suspend,
+	.resume		= mt76x2u_resume,
+	.reset_resume	= mt76x2u_resume,
+#endif /* CONFIG_PM */
+	.soft_unbind	= 1,
+	.disable_hub_initiated_lpm = 1,
+};
+module_usb_driver(mt76x2u_driver);
+
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u.h b/drivers/net/wireless/mediatek/mt76/mt76x2u.h
new file mode 100644
index 000000000000..008092f0cd8a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u.h
@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#ifndef __MT76x2U_H
+#define __MT76x2U_H
+
+#include <linux/device.h>
+
+#include "mt76x2.h"
+#include "mt76x2_dma.h"
+#include "mt76x2_mcu.h"
+
+#define MT7612U_EEPROM_SIZE		512
+
+#define MT_USB_AGGR_SIZE_LIMIT		21 /* 1024B unit */
+#define MT_USB_AGGR_TIMEOUT		0x80 /* 33ns unit */
+
+extern const struct ieee80211_ops mt76x2u_ops;
+
+struct mt76x2_dev *mt76x2u_alloc_device(struct device *pdev);
+int mt76x2u_register_device(struct mt76x2_dev *dev);
+int mt76x2u_init_hardware(struct mt76x2_dev *dev);
+void mt76x2u_cleanup(struct mt76x2_dev *dev);
+void mt76x2u_stop_hw(struct mt76x2_dev *dev);
+
+void mt76x2u_mac_setaddr(struct mt76x2_dev *dev, u8 *addr);
+int mt76x2u_mac_reset(struct mt76x2_dev *dev);
+void mt76x2u_mac_resume(struct mt76x2_dev *dev);
+int mt76x2u_mac_start(struct mt76x2_dev *dev);
+int mt76x2u_mac_stop(struct mt76x2_dev *dev);
+
+int mt76x2u_phy_set_channel(struct mt76x2_dev *dev,
+			    struct cfg80211_chan_def *chandef);
+void mt76x2u_phy_calibrate(struct work_struct *work);
+void mt76x2u_phy_channel_calibrate(struct mt76x2_dev *dev);
+void mt76x2u_phy_set_txdac(struct mt76x2_dev *dev);
+void mt76x2u_phy_set_rxpath(struct mt76x2_dev *dev);
+
+void mt76x2u_mcu_complete_urb(struct urb *urb);
+int mt76x2u_mcu_set_channel(struct mt76x2_dev *dev, u8 channel, u8 bw,
+			    u8 bw_index, bool scan);
+int mt76x2u_mcu_calibrate(struct mt76x2_dev *dev, enum mcu_calibration type,
+			  u32 val);
+int mt76x2u_mcu_tssi_comp(struct mt76x2_dev *dev,
+			  struct mt76x2_tssi_comp *tssi_data);
+int mt76x2u_mcu_init_gain(struct mt76x2_dev *dev, u8 channel, u32 gain,
+			  bool force);
+int mt76x2u_mcu_set_dynamic_vga(struct mt76x2_dev *dev, u8 channel, bool ap,
+				bool ext, int rssi, u32 false_cca);
+int mt76x2u_mcu_set_radio_state(struct mt76x2_dev *dev, bool val);
+int mt76x2u_mcu_load_cr(struct mt76x2_dev *dev, u8 type,
+			u8 temp_level, u8 channel);
+int mt76x2u_mcu_init(struct mt76x2_dev *dev);
+int mt76x2u_mcu_fw_init(struct mt76x2_dev *dev);
+void mt76x2u_mcu_deinit(struct mt76x2_dev *dev);
+
+int mt76x2u_alloc_queues(struct mt76x2_dev *dev);
+void mt76x2u_queues_deinit(struct mt76x2_dev *dev);
+void mt76x2u_stop_queues(struct mt76x2_dev *dev);
+bool mt76x2u_tx_status_data(struct mt76_dev *mdev, u8 *update);
+int mt76x2u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
+			   struct sk_buff *skb, struct mt76_queue *q,
+			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
+			   u32 *tx_info);
+void mt76x2u_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
+			     struct mt76_queue_entry *e, bool flush);
+int mt76x2u_skb_dma_info(struct sk_buff *skb, enum dma_msg_port port,
+			 u32 flags);
+
+#endif /* __MT76x2U_H */
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_core.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_core.c
new file mode 100644
index 000000000000..1ca5dd05b265
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_core.c
@@ -0,0 +1,108 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+#include "dma.h"
+
+static void mt76x2u_remove_dma_hdr(struct sk_buff *skb)
+{
+	int hdr_len;
+
+	skb_pull(skb, sizeof(struct mt76x2_txwi) + MT_DMA_HDR_LEN);
+	hdr_len = ieee80211_get_hdrlen_from_skb(skb);
+	if (hdr_len % 4) {
+		memmove(skb->data + 2, skb->data, hdr_len);
+		skb_pull(skb, 2);
+	}
+}
+
+static int
+mt76x2u_check_skb_rooms(struct sk_buff *skb)
+{
+	int hdr_len = ieee80211_get_hdrlen_from_skb(skb);
+	u32 need_head;
+
+	need_head = sizeof(struct mt76x2_txwi) + MT_DMA_HDR_LEN;
+	if (hdr_len % 4)
+		need_head += 2;
+	return skb_cow(skb, need_head);
+}
+
+static int
+mt76x2u_set_txinfo(struct sk_buff *skb,
+		   struct mt76_wcid *wcid, u8 ep)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	enum mt76x2_qsel qsel;
+	u32 flags;
+
+	if ((info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) ||
+	    ep == MT_EP_OUT_HCCA)
+		qsel = MT_QSEL_MGMT;
+	else
+		qsel = MT_QSEL_EDCA;
+
+	flags = FIELD_PREP(MT_TXD_INFO_QSEL, qsel) |
+		MT_TXD_INFO_80211;
+	if (!wcid || wcid->hw_key_idx == 0xff || wcid->sw_iv)
+		flags |= MT_TXD_INFO_WIV;
+
+	return mt76u_skb_dma_info(skb, WLAN_PORT, flags);
+}
+
+bool mt76x2u_tx_status_data(struct mt76_dev *mdev, u8 *update)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+	struct mt76x2_tx_status stat;
+
+	if (!mt76x2_mac_load_tx_status(dev, &stat))
+		return false;
+
+	mt76x2_send_tx_status(dev, &stat, update);
+
+	return true;
+}
+
+int mt76x2u_tx_prepare_skb(struct mt76_dev *mdev, void *data,
+			   struct sk_buff *skb, struct mt76_queue *q,
+			   struct mt76_wcid *wcid, struct ieee80211_sta *sta,
+			   u32 *tx_info)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+	struct mt76x2_txwi *txwi;
+	int err, len = skb->len;
+
+	err = mt76x2u_check_skb_rooms(skb);
+	if (err < 0)
+		return -ENOMEM;
+
+	mt76x2_insert_hdr_pad(skb);
+
+	txwi = skb_push(skb, sizeof(struct mt76x2_txwi));
+	mt76x2_mac_write_txwi(dev, txwi, skb, wcid, sta, len);
+
+	return mt76x2u_set_txinfo(skb, wcid, q2ep(q->hw_idx));
+}
+
+void mt76x2u_tx_complete_skb(struct mt76_dev *mdev, struct mt76_queue *q,
+			     struct mt76_queue_entry *e, bool flush)
+{
+	struct mt76x2_dev *dev = container_of(mdev, struct mt76x2_dev, mt76);
+
+	mt76x2u_remove_dma_hdr(e->skb);
+	mt76x2_tx_complete(dev, e->skb);
+}
+
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_init.c
new file mode 100644
index 000000000000..9b81e7641c06
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_init.c
@@ -0,0 +1,318 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/delay.h>
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+static void mt76x2u_init_dma(struct mt76x2_dev *dev)
+{
+	u32 val = mt76_rr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG));
+
+	val |= MT_USB_DMA_CFG_RX_DROP_OR_PAD |
+	       MT_USB_DMA_CFG_RX_BULK_EN |
+	       MT_USB_DMA_CFG_TX_BULK_EN;
+
+	/* disable AGGR_BULK_RX in order to receive one
+	 * frame in each rx urb and avoid copies
+	 */
+	val &= ~MT_USB_DMA_CFG_RX_BULK_AGG_EN;
+	mt76_wr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG), val);
+}
+
+static void mt76x2u_power_on_rf_patch(struct mt76x2_dev *dev)
+{
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), BIT(0) | BIT(16));
+	udelay(1);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x1c), 0xff);
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x1c), 0x30);
+
+	mt76_wr(dev, MT_VEND_ADDR(CFG, 0x14), 0x484f);
+	udelay(1);
+
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), BIT(17));
+	usleep_range(150, 200);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x130), BIT(16));
+	usleep_range(50, 100);
+
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x14c), BIT(19) | BIT(20));
+}
+
+static void mt76x2u_power_on_rf(struct mt76x2_dev *dev, int unit)
+{
+	int shift = unit ? 8 : 0;
+	u32 val = (BIT(1) | BIT(3) | BIT(4) | BIT(5)) << shift;
+
+	/* Enable RF BG */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), BIT(0) << shift);
+	usleep_range(10, 20);
+
+	/* Enable RFDIG LDO/AFE/ABB/ADDA */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x130), val);
+	usleep_range(10, 20);
+
+	/* Switch RFDIG power to internal LDO */
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x130), BIT(2) << shift);
+	usleep_range(10, 20);
+
+	mt76x2u_power_on_rf_patch(dev);
+
+	mt76_set(dev, 0x530, 0xf);
+}
+
+static void mt76x2u_power_on(struct mt76x2_dev *dev)
+{
+	u32 val;
+
+	/* Turn on WL MTCMOS */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x148),
+		 MT_WLAN_MTC_CTRL_MTCMOS_PWR_UP);
+
+	val = MT_WLAN_MTC_CTRL_STATE_UP |
+	      MT_WLAN_MTC_CTRL_PWR_ACK |
+	      MT_WLAN_MTC_CTRL_PWR_ACK_S;
+
+	mt76_poll(dev, MT_VEND_ADDR(CFG, 0x148), val, val, 1000);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x148), 0x7f << 16);
+	usleep_range(10, 20);
+
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x148), 0xf << 24);
+	usleep_range(10, 20);
+
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x148), 0xf << 24);
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x148), 0xfff);
+
+	/* Turn on AD/DA power down */
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x1204), BIT(3));
+
+	/* WLAN function enable */
+	mt76_set(dev, MT_VEND_ADDR(CFG, 0x80), BIT(0));
+
+	/* Release BBP software reset */
+	mt76_clear(dev, MT_VEND_ADDR(CFG, 0x64), BIT(18));
+
+	mt76x2u_power_on_rf(dev, 0);
+	mt76x2u_power_on_rf(dev, 1);
+}
+
+static int mt76x2u_init_eeprom(struct mt76x2_dev *dev)
+{
+	u32 val, i;
+
+	dev->mt76.eeprom.data = devm_kzalloc(dev->mt76.dev,
+					     MT7612U_EEPROM_SIZE,
+					     GFP_KERNEL);
+	dev->mt76.eeprom.size = MT7612U_EEPROM_SIZE;
+	if (!dev->mt76.eeprom.data)
+		return -ENOMEM;
+
+	for (i = 0; i + 4 <= MT7612U_EEPROM_SIZE; i += 4) {
+		val = mt76_rr(dev, MT_VEND_ADDR(EEPROM, i));
+		put_unaligned_le32(val, dev->mt76.eeprom.data + i);
+	}
+
+	mt76x2_eeprom_parse_hw_cap(dev);
+	return 0;
+}
+
+struct mt76x2_dev *mt76x2u_alloc_device(struct device *pdev)
+{
+	static const struct mt76_driver_ops drv_ops = {
+		.tx_prepare_skb = mt76x2u_tx_prepare_skb,
+		.tx_complete_skb = mt76x2u_tx_complete_skb,
+		.tx_status_data = mt76x2u_tx_status_data,
+		.rx_skb = mt76x2_queue_rx_skb,
+	};
+	struct mt76x2_dev *dev;
+	struct mt76_dev *mdev;
+
+	mdev = mt76_alloc_device(sizeof(*dev), &mt76x2u_ops);
+	if (!mdev)
+		return NULL;
+
+	dev = container_of(mdev, struct mt76x2_dev, mt76);
+	mdev->dev = pdev;
+	mdev->drv = &drv_ops;
+
+	mutex_init(&dev->mutex);
+
+	return dev;
+}
+
+static void mt76x2u_init_beacon_offsets(struct mt76x2_dev *dev)
+{
+	mt76_wr(dev, MT_BCN_OFFSET(0), 0x18100800);
+	mt76_wr(dev, MT_BCN_OFFSET(1), 0x38302820);
+	mt76_wr(dev, MT_BCN_OFFSET(2), 0x58504840);
+	mt76_wr(dev, MT_BCN_OFFSET(3), 0x78706860);
+}
+
+int mt76x2u_init_hardware(struct mt76x2_dev *dev)
+{
+	static const u16 beacon_offsets[] = {
+		/* 512 byte per beacon */
+		0xc000, 0xc200, 0xc400, 0xc600,
+		0xc800, 0xca00, 0xcc00, 0xce00,
+		0xd000, 0xd200, 0xd400, 0xd600,
+		0xd800, 0xda00, 0xdc00, 0xde00
+	};
+	const struct mt76_wcid_addr addr = {
+		.macaddr = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff},
+		.ba_mask = 0,
+	};
+	int i, err;
+
+	dev->beacon_offsets = beacon_offsets;
+
+	mt76x2_reset_wlan(dev, true);
+	mt76x2u_power_on(dev);
+
+	if (!mt76x2_wait_for_mac(dev))
+		return -ETIMEDOUT;
+
+	err = mt76x2u_mcu_fw_init(dev);
+	if (err < 0)
+		return err;
+
+	if (!mt76_poll_msec(dev, MT_WPDMA_GLO_CFG,
+			    MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+			    MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 100))
+		return -EIO;
+
+	/* wait for asic ready after fw load. */
+	if (!mt76x2_wait_for_mac(dev))
+		return -ETIMEDOUT;
+
+	mt76_wr(dev, MT_HEADER_TRANS_CTRL_REG, 0);
+	mt76_wr(dev, MT_TSO_CTRL, 0);
+
+	mt76x2u_init_dma(dev);
+
+	err = mt76x2u_mcu_init(dev);
+	if (err < 0)
+		return err;
+
+	err = mt76x2u_mac_reset(dev);
+	if (err < 0)
+		return err;
+
+	mt76x2u_mac_setaddr(dev, dev->mt76.eeprom.data + MT_EE_MAC_ADDR);
+	dev->rxfilter = mt76_rr(dev, MT_RX_FILTR_CFG);
+
+	mt76x2u_init_beacon_offsets(dev);
+
+	if (!mt76x2_wait_for_bbp(dev))
+		return -ETIMEDOUT;
+
+	/* reset wcid table */
+	for (i = 0; i < 254; i++)
+		mt76_wr_copy(dev, MT_WCID_ADDR(i), &addr,
+			     sizeof(struct mt76_wcid_addr));
+
+	/* reset shared key table and pairwise key table */
+	for (i = 0; i < 4; i++)
+		mt76_wr(dev, MT_SKEY_MODE_BASE_0 + 4 * i, 0);
+	for (i = 0; i < 256; i++)
+		mt76_wr(dev, MT_WCID_ATTR(i), 1);
+
+	mt76_clear(dev, MT_BEACON_TIME_CFG,
+		   MT_BEACON_TIME_CFG_TIMER_EN |
+		   MT_BEACON_TIME_CFG_SYNC_MODE |
+		   MT_BEACON_TIME_CFG_TBTT_EN |
+		   MT_BEACON_TIME_CFG_BEACON_TX);
+
+	mt76_rmw(dev, MT_US_CYC_CFG, MT_US_CYC_CNT, 0x1e);
+	mt76_wr(dev, MT_TXOP_CTRL_CFG, 0x583f);
+
+	err = mt76x2u_mcu_load_cr(dev, MT_RF_BBP_CR, 0, 0);
+	if (err < 0)
+		return err;
+
+	mt76x2u_phy_set_rxpath(dev);
+	mt76x2u_phy_set_txdac(dev);
+
+	return mt76x2u_mac_stop(dev);
+}
+
+int mt76x2u_register_device(struct mt76x2_dev *dev)
+{
+	struct ieee80211_hw *hw = mt76_hw(dev);
+	struct wiphy *wiphy = hw->wiphy;
+	int err;
+
+	INIT_DELAYED_WORK(&dev->cal_work, mt76x2u_phy_calibrate);
+	mt76x2_init_device(dev);
+
+	err = mt76x2u_init_eeprom(dev);
+	if (err < 0)
+		return err;
+
+	err = mt76u_mcu_init_rx(&dev->mt76);
+	if (err < 0)
+		return err;
+
+	err = mt76u_alloc_queues(&dev->mt76);
+	if (err < 0)
+		goto fail;
+
+	err = mt76x2u_init_hardware(dev);
+	if (err < 0)
+		goto fail;
+
+	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
+
+	err = mt76_register_device(&dev->mt76, true, mt76x2_rates,
+				   ARRAY_SIZE(mt76x2_rates));
+	if (err)
+		goto fail;
+
+	/* check hw sg support in order to enable AMSDU */
+	if (mt76u_check_sg(&dev->mt76))
+		hw->max_tx_fragments = MT_SG_MAX_SIZE;
+	else
+		hw->max_tx_fragments = 1;
+
+	set_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	mt76x2_init_debugfs(dev);
+	mt76x2_init_txpower(dev, &dev->mt76.sband_2g.sband);
+	mt76x2_init_txpower(dev, &dev->mt76.sband_5g.sband);
+
+	return 0;
+
+fail:
+	mt76x2u_cleanup(dev);
+	return err;
+}
+
+void mt76x2u_stop_hw(struct mt76x2_dev *dev)
+{
+	mt76u_stop_stat_wk(&dev->mt76);
+	cancel_delayed_work_sync(&dev->cal_work);
+	mt76x2u_mac_stop(dev);
+}
+
+void mt76x2u_cleanup(struct mt76x2_dev *dev)
+{
+	mt76x2u_mcu_set_radio_state(dev, false);
+	mt76x2u_stop_hw(dev);
+	mt76u_queues_deinit(&dev->mt76);
+	mt76x2u_mcu_deinit(dev);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c
new file mode 100644
index 000000000000..eab7ab297aa6
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_mac.c
@@ -0,0 +1,240 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+static void mt76x2u_mac_reset_counters(struct mt76x2_dev *dev)
+{
+	mt76_rr(dev, MT_RX_STAT_0);
+	mt76_rr(dev, MT_RX_STAT_1);
+	mt76_rr(dev, MT_RX_STAT_2);
+	mt76_rr(dev, MT_TX_STA_0);
+	mt76_rr(dev, MT_TX_STA_1);
+	mt76_rr(dev, MT_TX_STA_2);
+}
+
+static void mt76x2u_mac_fixup_xtal(struct mt76x2_dev *dev)
+{
+	s8 offset = 0;
+	u16 eep_val;
+
+	eep_val = mt76x2_eeprom_get(dev, MT_EE_XTAL_TRIM_2);
+
+	offset = eep_val & 0x7f;
+	if ((eep_val & 0xff) == 0xff)
+		offset = 0;
+	else if (eep_val & 0x80)
+		offset = 0 - offset;
+
+	eep_val >>= 8;
+	if (eep_val == 0x00 || eep_val == 0xff) {
+		eep_val = mt76x2_eeprom_get(dev, MT_EE_XTAL_TRIM_1);
+		eep_val &= 0xff;
+
+		if (eep_val == 0x00 || eep_val == 0xff)
+			eep_val = 0x14;
+	}
+
+	eep_val &= 0x7f;
+	mt76_rmw_field(dev, MT_VEND_ADDR(CFG, MT_XO_CTRL5),
+		       MT_XO_CTRL5_C2_VAL, eep_val + offset);
+	mt76_set(dev, MT_VEND_ADDR(CFG, MT_XO_CTRL6), MT_XO_CTRL6_C2_CTRL);
+
+	mt76_wr(dev, 0x504, 0x06000000);
+	mt76_wr(dev, 0x50c, 0x08800000);
+	mdelay(5);
+	mt76_wr(dev, 0x504, 0x0);
+
+	/* decrease SIFS from 16us to 13us */
+	mt76_rmw_field(dev, MT_XIFS_TIME_CFG,
+		       MT_XIFS_TIME_CFG_OFDM_SIFS, 0xd);
+	mt76_rmw_field(dev, MT_BKOFF_SLOT_CFG, MT_BKOFF_SLOT_CFG_CC_DELAY, 1);
+
+	/* init fce */
+	mt76_clear(dev, MT_FCE_L2_STUFF, MT_FCE_L2_STUFF_WR_MPDU_LEN_EN);
+
+	eep_val = mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_2);
+	switch (FIELD_GET(MT_EE_NIC_CONF_2_XTAL_OPTION, eep_val)) {
+	case 0:
+		mt76_wr(dev, MT_XO_CTRL7, 0x5c1fee80);
+		break;
+	case 1:
+		mt76_wr(dev, MT_XO_CTRL7, 0x5c1feed0);
+		break;
+	default:
+		break;
+	}
+}
+
+int mt76x2u_mac_reset(struct mt76x2_dev *dev)
+{
+	mt76_wr(dev, MT_WPDMA_GLO_CFG, BIT(4) | BIT(5));
+
+	/* init pbf regs */
+	mt76_wr(dev, MT_PBF_TX_MAX_PCNT, 0xefef3f1f);
+	mt76_wr(dev, MT_PBF_RX_MAX_PCNT, 0xfebf);
+
+	mt76_write_mac_initvals(dev);
+
+	mt76_wr(dev, MT_TX_LINK_CFG, 0x1020);
+	mt76_wr(dev, MT_AUTO_RSP_CFG, 0x13);
+	mt76_wr(dev, MT_MAX_LEN_CFG, 0x2f00);
+	mt76_wr(dev, MT_TX_RTS_CFG, 0x92b20);
+
+	mt76_wr(dev, MT_WMM_AIFSN, 0x2273);
+	mt76_wr(dev, MT_WMM_CWMIN, 0x2344);
+	mt76_wr(dev, MT_WMM_CWMAX, 0x34aa);
+
+	mt76_clear(dev, MT_MAC_SYS_CTRL,
+		   MT_MAC_SYS_CTRL_RESET_CSR |
+		   MT_MAC_SYS_CTRL_RESET_BBP);
+
+	if (is_mt7612(dev))
+		mt76_clear(dev, MT_COEXCFG0, MT_COEXCFG0_COEX_EN);
+
+	mt76_set(dev, MT_EXT_CCA_CFG, 0xf000);
+	mt76_clear(dev, MT_TX_ALC_CFG_4, BIT(31));
+
+	mt76x2u_mac_fixup_xtal(dev);
+
+	return 0;
+}
+
+int mt76x2u_mac_start(struct mt76x2_dev *dev)
+{
+	mt76x2u_mac_reset_counters(dev);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_TX);
+	wait_for_wpdma(dev);
+	usleep_range(50, 100);
+
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL,
+		MT_MAC_SYS_CTRL_ENABLE_TX |
+		MT_MAC_SYS_CTRL_ENABLE_RX);
+
+	return 0;
+}
+
+int mt76x2u_mac_stop(struct mt76x2_dev *dev)
+{
+	int i, count = 0, val;
+	bool stopped = false;
+	u32 rts_cfg;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return -EIO;
+
+	rts_cfg = mt76_rr(dev, MT_TX_RTS_CFG);
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg & ~MT_TX_RTS_CFG_RETRY_LIMIT);
+
+	mt76_clear(dev, MT_TXOP_CTRL_CFG, BIT(20));
+	mt76_clear(dev, MT_TXOP_HLDR_ET, BIT(1));
+
+	/* wait tx dma to stop */
+	for (i = 0; i < 2000; i++) {
+		val = mt76_rr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG));
+		if (!(val & MT_USB_DMA_CFG_TX_BUSY) && i > 10)
+			break;
+		usleep_range(50, 100);
+	}
+
+	/* page count on TxQ */
+	for (i = 0; i < 200; i++) {
+		if (!(mt76_rr(dev, 0x0438) & 0xffffffff) &&
+		    !(mt76_rr(dev, 0x0a30) & 0x000000ff) &&
+		    !(mt76_rr(dev, 0x0a34) & 0xff00ff00))
+			break;
+		usleep_range(10, 20);
+	}
+
+	/* disable tx-rx */
+	mt76_clear(dev, MT_MAC_SYS_CTRL,
+		   MT_MAC_SYS_CTRL_ENABLE_RX |
+		   MT_MAC_SYS_CTRL_ENABLE_TX);
+
+	/* Wait for MAC to become idle */
+	for (i = 0; i < 1000; i++) {
+		if (!(mt76_rr(dev, MT_MAC_STATUS) & MT_MAC_STATUS_TX) &&
+		    !mt76_rr(dev, MT_BBP(IBI, 12))) {
+			stopped = true;
+			break;
+		}
+		usleep_range(10, 20);
+	}
+
+	if (!stopped) {
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(1));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(1));
+
+		mt76_set(dev, MT_BBP(CORE, 4), BIT(0));
+		mt76_clear(dev, MT_BBP(CORE, 4), BIT(0));
+	}
+
+	/* page count on RxQ */
+	for (i = 0; i < 200; i++) {
+		if (!(mt76_rr(dev, 0x0430) & 0x00ff0000) &&
+		    !(mt76_rr(dev, 0x0a30) & 0xffffffff) &&
+		    !(mt76_rr(dev, 0x0a34) & 0xffffffff) &&
+		    ++count > 10)
+			break;
+		msleep(50);
+	}
+
+	if (!mt76_poll(dev, MT_MAC_STATUS, MT_MAC_STATUS_RX, 0, 2000))
+		dev_warn(dev->mt76.dev, "MAC RX failed to stop\n");
+
+	/* wait rx dma to stop */
+	for (i = 0; i < 2000; i++) {
+		val = mt76_rr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG));
+		if (!(val & MT_USB_DMA_CFG_RX_BUSY) && i > 10)
+			break;
+		usleep_range(50, 100);
+	}
+
+	mt76_wr(dev, MT_TX_RTS_CFG, rts_cfg);
+
+	return 0;
+}
+
+void mt76x2u_mac_resume(struct mt76x2_dev *dev)
+{
+	mt76_wr(dev, MT_MAC_SYS_CTRL,
+		MT_MAC_SYS_CTRL_ENABLE_TX |
+		MT_MAC_SYS_CTRL_ENABLE_RX);
+	mt76_set(dev, MT_TXOP_CTRL_CFG, BIT(20));
+	mt76_set(dev, MT_TXOP_HLDR_ET, BIT(1));
+}
+
+void mt76x2u_mac_setaddr(struct mt76x2_dev *dev, u8 *addr)
+{
+	ether_addr_copy(dev->mt76.macaddr, addr);
+
+	if (!is_valid_ether_addr(dev->mt76.macaddr)) {
+		eth_random_addr(dev->mt76.macaddr);
+		dev_info(dev->mt76.dev,
+			 "Invalid MAC address, using random address %pM\n",
+			 dev->mt76.macaddr);
+	}
+
+	mt76_wr(dev, MT_MAC_ADDR_DW0, get_unaligned_le32(dev->mt76.macaddr));
+	mt76_wr(dev, MT_MAC_ADDR_DW1,
+		get_unaligned_le16(dev->mt76.macaddr + 4) |
+		FIELD_PREP(MT_MAC_ADDR_DW1_U2ME_MASK, 0xff));
+}
+
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_main.c
new file mode 100644
index 000000000000..7367ba111119
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_main.c
@@ -0,0 +1,185 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+
+static int mt76x2u_start(struct ieee80211_hw *hw)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	int ret;
+
+	mutex_lock(&dev->mutex);
+
+	ret = mt76x2u_mac_start(dev);
+	if (ret)
+		goto out;
+
+	set_bit(MT76_STATE_RUNNING, &dev->mt76.state);
+
+out:
+	mutex_unlock(&dev->mutex);
+	return ret;
+}
+
+static void mt76x2u_stop(struct ieee80211_hw *hw)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+	clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
+	mt76x2u_stop_hw(dev);
+	mutex_unlock(&dev->mutex);
+}
+
+static int mt76x2u_add_interface(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	struct mt76x2_vif *mvif = (struct mt76x2_vif *)vif->drv_priv;
+	unsigned int idx = 0;
+
+	if (!ether_addr_equal(dev->mt76.macaddr, vif->addr))
+		mt76x2u_mac_setaddr(dev, vif->addr);
+
+	mvif->idx = idx;
+	mvif->group_wcid.idx = MT_VIF_WCID(idx);
+	mvif->group_wcid.hw_key_idx = -1;
+	mt76x2_txq_init(dev, vif->txq);
+
+	return 0;
+}
+
+static int
+mt76x2u_set_channel(struct mt76x2_dev *dev,
+		    struct cfg80211_chan_def *chandef)
+{
+	int err;
+
+	cancel_delayed_work_sync(&dev->cal_work);
+	set_bit(MT76_RESET, &dev->mt76.state);
+
+	mt76_set_channel(&dev->mt76);
+
+	mt76_clear(dev, MT_TXOP_CTRL_CFG, BIT(20));
+	mt76_clear(dev, MT_TXOP_HLDR_ET, BIT(1));
+	mt76x2_mac_stop(dev, false);
+
+	err = mt76x2u_phy_set_channel(dev, chandef);
+
+	mt76x2u_mac_resume(dev);
+
+	clear_bit(MT76_RESET, &dev->mt76.state);
+	mt76_txq_schedule_all(&dev->mt76);
+
+	return err;
+}
+
+static void
+mt76x2u_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ieee80211_bss_conf *info, u32 changed)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & BSS_CHANGED_ASSOC) {
+		mt76x2u_phy_channel_calibrate(dev);
+		mt76x2_apply_gain_adj(dev);
+	}
+
+	if (changed & BSS_CHANGED_BSSID) {
+		mt76_wr(dev, MT_MAC_BSSID_DW0,
+			get_unaligned_le32(info->bssid));
+		mt76_wr(dev, MT_MAC_BSSID_DW1,
+			get_unaligned_le16(info->bssid + 4));
+	}
+
+	mutex_unlock(&dev->mutex);
+}
+
+static int
+mt76x2u_config(struct ieee80211_hw *hw, u32 changed)
+{
+	struct mt76x2_dev *dev = hw->priv;
+	int err = 0;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
+		if (!(hw->conf.flags & IEEE80211_CONF_MONITOR))
+			dev->rxfilter |= MT_RX_FILTR_CFG_PROMISC;
+		else
+			dev->rxfilter &= ~MT_RX_FILTR_CFG_PROMISC;
+		mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+	}
+
+	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
+		ieee80211_stop_queues(hw);
+		err = mt76x2u_set_channel(dev, &hw->conf.chandef);
+		ieee80211_wake_queues(hw);
+	}
+
+	if (changed & IEEE80211_CONF_CHANGE_POWER) {
+		dev->txpower_conf = hw->conf.power_level * 2;
+
+		/* convert to per-chain power for 2x2 devices */
+		dev->txpower_conf -= 6;
+
+		if (test_bit(MT76_STATE_RUNNING, &dev->mt76.state))
+			mt76x2_phy_set_txpower(dev);
+	}
+
+	mutex_unlock(&dev->mutex);
+
+	return err;
+}
+
+static void
+mt76x2u_sw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		const u8 *mac)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	set_bit(MT76_SCANNING, &dev->mt76.state);
+}
+
+static void
+mt76x2u_sw_scan_complete(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
+{
+	struct mt76x2_dev *dev = hw->priv;
+
+	clear_bit(MT76_SCANNING, &dev->mt76.state);
+}
+
+const struct ieee80211_ops mt76x2u_ops = {
+	.tx = mt76x2_tx,
+	.start = mt76x2u_start,
+	.stop = mt76x2u_stop,
+	.add_interface = mt76x2u_add_interface,
+	.remove_interface = mt76x2_remove_interface,
+	.sta_add = mt76x2_sta_add,
+	.sta_remove = mt76x2_sta_remove,
+	.set_key = mt76x2_set_key,
+	.ampdu_action = mt76x2_ampdu_action,
+	.config = mt76x2u_config,
+	.wake_tx_queue = mt76_wake_tx_queue,
+	.bss_info_changed = mt76x2u_bss_info_changed,
+	.configure_filter = mt76x2_configure_filter,
+	.conf_tx = mt76x2_conf_tx,
+	.sw_scan_start = mt76x2u_sw_scan,
+	.sw_scan_complete = mt76x2u_sw_scan_complete,
+	.sta_rate_tbl_update = mt76x2_sta_rate_tbl_update,
+};
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c
new file mode 100644
index 000000000000..22c16d638baa
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_mcu.c
@@ -0,0 +1,463 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include <linux/firmware.h>
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+#define MT_CMD_HDR_LEN			4
+#define MT_INBAND_PACKET_MAX_LEN	192
+#define MT_MCU_MEMMAP_WLAN		0x410000
+
+#define MCU_FW_URB_MAX_PAYLOAD		0x3900
+#define MCU_ROM_PATCH_MAX_PAYLOAD	2048
+
+#define MT76U_MCU_ILM_OFFSET		0x80000
+#define MT76U_MCU_DLM_OFFSET		0x110000
+#define MT76U_MCU_ROM_PATCH_OFFSET	0x90000
+
+static int
+mt76x2u_mcu_function_select(struct mt76x2_dev *dev, enum mcu_function func,
+			    u32 val)
+{
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(func),
+		.value = cpu_to_le32(val),
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_FUN_SET_OP,
+				  func != Q_SELECT);
+}
+
+int mt76x2u_mcu_set_radio_state(struct mt76x2_dev *dev, bool val)
+{
+	struct {
+		__le32 mode;
+		__le32 level;
+	} __packed __aligned(4) msg = {
+		.mode = cpu_to_le32(val ? RADIO_ON : RADIO_OFF),
+		.level = cpu_to_le32(0),
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_POWER_SAVING_OP,
+				  false);
+}
+
+int mt76x2u_mcu_load_cr(struct mt76x2_dev *dev, u8 type, u8 temp_level,
+			u8 channel)
+{
+	struct {
+		u8 cr_mode;
+		u8 temp;
+		u8 ch;
+		u8 _pad0;
+		__le32 cfg;
+	} __packed __aligned(4) msg = {
+		.cr_mode = type,
+		.temp = temp_level,
+		.ch = channel,
+	};
+	struct sk_buff *skb;
+	u32 val;
+
+	val = BIT(31);
+	val |= (mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_0) >> 8) & 0x00ff;
+	val |= (mt76x2_eeprom_get(dev, MT_EE_NIC_CONF_1) << 8) & 0xff00;
+	msg.cfg = cpu_to_le32(val);
+
+	/* first set the channel without the extension channel info */
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_LOAD_CR, true);
+}
+
+int mt76x2u_mcu_set_channel(struct mt76x2_dev *dev, u8 channel, u8 bw,
+			    u8 bw_index, bool scan)
+{
+	struct {
+		u8 idx;
+		u8 scan;
+		u8 bw;
+		u8 _pad0;
+
+		__le16 chainmask;
+		u8 ext_chan;
+		u8 _pad1;
+
+	} __packed __aligned(4) msg = {
+		.idx = channel,
+		.scan = scan,
+		.bw = bw,
+		.chainmask = cpu_to_le16(dev->chainmask),
+	};
+	struct sk_buff *skb;
+
+	/* first set the channel without the extension channel info */
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+
+	mt76u_mcu_send_msg(&dev->mt76, skb, CMD_SWITCH_CHANNEL_OP, true);
+
+	usleep_range(5000, 10000);
+
+	msg.ext_chan = 0xe0 + bw_index;
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_SWITCH_CHANNEL_OP, true);
+}
+
+int mt76x2u_mcu_calibrate(struct mt76x2_dev *dev, enum mcu_calibration type,
+			  u32 val)
+{
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(type),
+		.value = cpu_to_le32(val),
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_CALIBRATION_OP, true);
+}
+
+int mt76x2u_mcu_init_gain(struct mt76x2_dev *dev, u8 channel, u32 gain,
+			  bool force)
+{
+	struct {
+		__le32 channel;
+		__le32 gain_val;
+	} __packed __aligned(4) msg = {
+		.channel = cpu_to_le32(channel),
+		.gain_val = cpu_to_le32(gain),
+	};
+	struct sk_buff *skb;
+
+	if (force)
+		msg.channel |= cpu_to_le32(BIT(31));
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_INIT_GAIN_OP, true);
+}
+
+int mt76x2u_mcu_set_dynamic_vga(struct mt76x2_dev *dev, u8 channel, bool ap,
+				bool ext, int rssi, u32 false_cca)
+{
+	struct {
+		__le32 channel;
+		__le32 rssi_val;
+		__le32 false_cca_val;
+	} __packed __aligned(4) msg = {
+		.rssi_val = cpu_to_le32(rssi),
+		.false_cca_val = cpu_to_le32(false_cca),
+	};
+	struct sk_buff *skb;
+	u32 val = channel;
+
+	if (ap)
+		val |= BIT(31);
+	if (ext)
+		val |= BIT(30);
+	msg.channel = cpu_to_le32(val);
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_DYNC_VGA_OP, true);
+}
+
+int mt76x2u_mcu_tssi_comp(struct mt76x2_dev *dev,
+			  struct mt76x2_tssi_comp *tssi_data)
+{
+	struct {
+		__le32 id;
+		struct mt76x2_tssi_comp data;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(MCU_CAL_TSSI_COMP),
+		.data = *tssi_data,
+	};
+	struct sk_buff *skb;
+
+	skb = mt76u_mcu_msg_alloc(&msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76u_mcu_send_msg(&dev->mt76, skb, CMD_CALIBRATION_OP, true);
+}
+
+static void mt76x2u_mcu_load_ivb(struct mt76x2_dev *dev)
+{
+	mt76u_vendor_request(&dev->mt76, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_VENDOR,
+			     0x12, 0, NULL, 0);
+}
+
+static void mt76x2u_mcu_enable_patch(struct mt76x2_dev *dev)
+{
+	struct mt76_usb *usb = &dev->mt76.usb;
+	const u8 data[] = {
+		0x6f, 0xfc, 0x08, 0x01,
+		0x20, 0x04, 0x00, 0x00,
+		0x00, 0x09, 0x00,
+	};
+
+	memcpy(usb->data, data, sizeof(data));
+	mt76u_vendor_request(&dev->mt76, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_CLASS,
+			     0x12, 0, usb->data, sizeof(data));
+}
+
+static void mt76x2u_mcu_reset_wmt(struct mt76x2_dev *dev)
+{
+	struct mt76_usb *usb = &dev->mt76.usb;
+	u8 data[] = {
+		0x6f, 0xfc, 0x05, 0x01,
+		0x07, 0x01, 0x00, 0x04
+	};
+
+	memcpy(usb->data, data, sizeof(data));
+	mt76u_vendor_request(&dev->mt76, MT_VEND_DEV_MODE,
+			     USB_DIR_OUT | USB_TYPE_CLASS,
+			     0x12, 0, usb->data, sizeof(data));
+}
+
+static int mt76x2u_mcu_load_rom_patch(struct mt76x2_dev *dev)
+{
+	bool rom_protect = !is_mt7612(dev);
+	struct mt76x2_patch_header *hdr;
+	u32 val, patch_mask, patch_reg;
+	const struct firmware *fw;
+	int err;
+
+	if (rom_protect &&
+	    !mt76_poll_msec(dev, MT_MCU_SEMAPHORE_03, 1, 1, 600)) {
+		dev_err(dev->mt76.dev,
+			"could not get hardware semaphore for ROM PATCH\n");
+		return -ETIMEDOUT;
+	}
+
+	if (mt76xx_rev(dev) >= MT76XX_REV_E3) {
+		patch_mask = BIT(0);
+		patch_reg = MT_MCU_CLOCK_CTL;
+	} else {
+		patch_mask = BIT(1);
+		patch_reg = MT_MCU_COM_REG0;
+	}
+
+	if (rom_protect && (mt76_rr(dev, patch_reg) & patch_mask)) {
+		dev_info(dev->mt76.dev, "ROM patch already applied\n");
+		return 0;
+	}
+
+	err = request_firmware(&fw, MT7662U_ROM_PATCH, dev->mt76.dev);
+	if (err < 0)
+		return err;
+
+	if (!fw || !fw->data || fw->size <= sizeof(*hdr)) {
+		dev_err(dev->mt76.dev, "failed to load firmware\n");
+		err = -EIO;
+		goto out;
+	}
+
+	hdr = (struct mt76x2_patch_header *)fw->data;
+	dev_info(dev->mt76.dev, "ROM patch build: %.15s\n", hdr->build_time);
+
+	/* enable USB_DMA_CFG */
+	val = MT_USB_DMA_CFG_RX_BULK_EN |
+	      MT_USB_DMA_CFG_TX_BULK_EN |
+	      FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, 0x20);
+	mt76_wr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG), val);
+
+	/* vendor reset */
+	mt76u_mcu_fw_reset(&dev->mt76);
+	usleep_range(5000, 10000);
+
+	/* enable FCE to send in-band cmd */
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 0x1);
+	/* FCE tx_fs_base_ptr */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_BASE_PTR, 0x400230);
+	/* FCE tx_fs_max_cnt */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_MAX_COUNT, 0x1);
+	/* FCE pdma enable */
+	mt76_wr(dev, MT_FCE_PDMA_GLOBAL_CONF, 0x44);
+	/* FCE skip_fs_en */
+	mt76_wr(dev, MT_FCE_SKIP_FS, 0x3);
+
+	err = mt76u_mcu_fw_send_data(&dev->mt76, fw->data + sizeof(*hdr),
+				     fw->size - sizeof(*hdr),
+				     MCU_ROM_PATCH_MAX_PAYLOAD,
+				     MT76U_MCU_ROM_PATCH_OFFSET);
+	if (err < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	mt76x2u_mcu_enable_patch(dev);
+	mt76x2u_mcu_reset_wmt(dev);
+	mdelay(20);
+
+	if (!mt76_poll_msec(dev, patch_reg, patch_mask, patch_mask, 100)) {
+		dev_err(dev->mt76.dev, "failed to load ROM patch\n");
+		err = -ETIMEDOUT;
+	}
+
+out:
+	if (rom_protect)
+		mt76_wr(dev, MT_MCU_SEMAPHORE_03, 1);
+	release_firmware(fw);
+	return err;
+}
+
+static int mt76x2u_mcu_load_firmware(struct mt76x2_dev *dev)
+{
+	u32 val, dlm_offset = MT76U_MCU_DLM_OFFSET;
+	const struct mt76x2_fw_header *hdr;
+	int err, len, ilm_len, dlm_len;
+	const struct firmware *fw;
+
+	err = request_firmware(&fw, MT7662U_FIRMWARE, dev->mt76.dev);
+	if (err < 0)
+		return err;
+
+	if (!fw || !fw->data || fw->size < sizeof(*hdr)) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	hdr = (const struct mt76x2_fw_header *)fw->data;
+	ilm_len = le32_to_cpu(hdr->ilm_len);
+	dlm_len = le32_to_cpu(hdr->dlm_len);
+	len = sizeof(*hdr) + ilm_len + dlm_len;
+	if (fw->size != len) {
+		err = -EINVAL;
+		goto out;
+	}
+
+	val = le16_to_cpu(hdr->fw_ver);
+	dev_info(dev->mt76.dev, "Firmware Version: %d.%d.%02d\n",
+		 (val >> 12) & 0xf, (val >> 8) & 0xf, val & 0xf);
+
+	val = le16_to_cpu(hdr->build_ver);
+	dev_info(dev->mt76.dev, "Build: %x\n", val);
+	dev_info(dev->mt76.dev, "Build Time: %.16s\n", hdr->build_time);
+
+	/* vendor reset */
+	mt76u_mcu_fw_reset(&dev->mt76);
+	usleep_range(5000, 10000);
+
+	/* enable USB_DMA_CFG */
+	val = MT_USB_DMA_CFG_RX_BULK_EN |
+	      MT_USB_DMA_CFG_TX_BULK_EN |
+	      FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, 0x20);
+	mt76_wr(dev, MT_VEND_ADDR(CFG, MT_USB_U3DMA_CFG), val);
+	/* enable FCE to send in-band cmd */
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 0x1);
+	/* FCE tx_fs_base_ptr */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_BASE_PTR, 0x400230);
+	/* FCE tx_fs_max_cnt */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_MAX_COUNT, 0x1);
+	/* FCE pdma enable */
+	mt76_wr(dev, MT_FCE_PDMA_GLOBAL_CONF, 0x44);
+	/* FCE skip_fs_en */
+	mt76_wr(dev, MT_FCE_SKIP_FS, 0x3);
+
+	/* load ILM */
+	err = mt76u_mcu_fw_send_data(&dev->mt76, fw->data + sizeof(*hdr),
+				     ilm_len, MCU_FW_URB_MAX_PAYLOAD,
+				     MT76U_MCU_ILM_OFFSET);
+	if (err < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	/* load DLM */
+	if (mt76xx_rev(dev) >= MT76XX_REV_E3)
+		dlm_offset += 0x800;
+	err = mt76u_mcu_fw_send_data(&dev->mt76,
+				     fw->data + sizeof(*hdr) + ilm_len,
+				     dlm_len, MCU_FW_URB_MAX_PAYLOAD,
+				     dlm_offset);
+	if (err < 0) {
+		err = -EIO;
+		goto out;
+	}
+
+	mt76x2u_mcu_load_ivb(dev);
+	if (!mt76_poll_msec(dev, MT_MCU_COM_REG0, 1, 1, 100)) {
+		dev_err(dev->mt76.dev, "firmware failed to start\n");
+		err = -ETIMEDOUT;
+		goto out;
+	}
+
+	mt76_set(dev, MT_MCU_COM_REG0, BIT(1));
+	/* enable FCE to send in-band cmd */
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 0x1);
+	dev_dbg(dev->mt76.dev, "firmware running\n");
+
+out:
+	release_firmware(fw);
+	return err;
+}
+
+int mt76x2u_mcu_fw_init(struct mt76x2_dev *dev)
+{
+	int err;
+
+	err = mt76x2u_mcu_load_rom_patch(dev);
+	if (err < 0)
+		return err;
+
+	return mt76x2u_mcu_load_firmware(dev);
+}
+
+int mt76x2u_mcu_init(struct mt76x2_dev *dev)
+{
+	int err;
+
+	err = mt76x2u_mcu_function_select(dev, Q_SELECT, 1);
+	if (err < 0)
+		return err;
+
+	return mt76x2u_mcu_set_radio_state(dev, true);
+}
+
+void mt76x2u_mcu_deinit(struct mt76x2_dev *dev)
+{
+	struct mt76_usb *usb = &dev->mt76.usb;
+
+	usb_kill_urb(usb->mcu.res.urb);
+	mt76u_buf_free(&usb->mcu.res);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c b/drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c
new file mode 100644
index 000000000000..5158063d0c2e
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2u_phy.c
@@ -0,0 +1,303 @@
+/*
+ * Copyright (C) 2018 Lorenzo Bianconi <lorenzo.bianconi83@gmail.com>
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
+ * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+ * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
+ * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#include "mt76x2u.h"
+#include "mt76x2_eeprom.h"
+
+void mt76x2u_phy_set_rxpath(struct mt76x2_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_BBP(AGC, 0));
+	val &= ~BIT(4);
+
+	switch (dev->chainmask & 0xf) {
+	case 2:
+		val |= BIT(3);
+		break;
+	default:
+		val &= ~BIT(3);
+		break;
+	}
+	mt76_wr(dev, MT_BBP(AGC, 0), val);
+}
+
+void mt76x2u_phy_set_txdac(struct mt76x2_dev *dev)
+{
+	int txpath;
+
+	txpath = (dev->chainmask >> 8) & 0xf;
+	switch (txpath) {
+	case 2:
+		mt76_set(dev, MT_BBP(TXBE, 5), 0x3);
+		break;
+	default:
+		mt76_clear(dev, MT_BBP(TXBE, 5), 0x3);
+		break;
+	}
+}
+
+void mt76x2u_phy_channel_calibrate(struct mt76x2_dev *dev)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	bool is_5ghz = chan->band == NL80211_BAND_5GHZ;
+
+	if (mt76x2_channel_silent(dev))
+		return;
+
+	mt76x2u_mac_stop(dev);
+
+	if (is_5ghz)
+		mt76x2u_mcu_calibrate(dev, MCU_CAL_LC, 0);
+
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_TX_LOFT, is_5ghz);
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz);
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_RXIQC_FI, is_5ghz);
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_TEMP_SENSOR, 0);
+
+	mt76x2u_mac_resume(dev);
+}
+
+static void
+mt76x2u_phy_tssi_compensate(struct mt76x2_dev *dev)
+{
+	struct ieee80211_channel *chan = dev->mt76.chandef.chan;
+	struct mt76x2_tx_power_info txp;
+	struct mt76x2_tssi_comp t = {};
+
+	if (!dev->cal.tssi_cal_done)
+		return;
+
+	if (!dev->cal.tssi_comp_pending) {
+		/* TSSI trigger */
+		t.cal_mode = BIT(0);
+		mt76x2u_mcu_tssi_comp(dev, &t);
+		dev->cal.tssi_comp_pending = true;
+	} else {
+		if (mt76_rr(dev, MT_BBP(CORE, 34)) & BIT(4))
+			return;
+
+		dev->cal.tssi_comp_pending = false;
+		mt76x2_get_power_info(dev, &txp, chan);
+
+		if (mt76x2_ext_pa_enabled(dev, chan->band))
+			t.pa_mode = 1;
+
+		t.cal_mode = BIT(1);
+		t.slope0 = txp.chain[0].tssi_slope;
+		t.offset0 = txp.chain[0].tssi_offset;
+		t.slope1 = txp.chain[1].tssi_slope;
+		t.offset1 = txp.chain[1].tssi_offset;
+		mt76x2u_mcu_tssi_comp(dev, &t);
+
+		if (t.pa_mode || dev->cal.dpd_cal_done)
+			return;
+
+		usleep_range(10000, 20000);
+		mt76x2u_mcu_calibrate(dev, MCU_CAL_DPD, chan->hw_value);
+		dev->cal.dpd_cal_done = true;
+	}
+}
+
+static void
+mt76x2u_phy_update_channel_gain(struct mt76x2_dev *dev)
+{
+	u8 channel = dev->mt76.chandef.chan->hw_value;
+	int freq, freq1;
+	u32 false_cca;
+
+	freq = dev->mt76.chandef.chan->center_freq;
+	freq1 = dev->mt76.chandef.center_freq1;
+
+	switch (dev->mt76.chandef.width) {
+	case NL80211_CHAN_WIDTH_80: {
+		int ch_group_index;
+
+		ch_group_index = (freq - freq1 + 30) / 20;
+		if (WARN_ON(ch_group_index < 0 || ch_group_index > 3))
+			ch_group_index = 0;
+		channel += 6 - ch_group_index * 4;
+		break;
+	}
+	case NL80211_CHAN_WIDTH_40:
+		if (freq1 > freq)
+			channel += 2;
+		else
+			channel -= 2;
+		break;
+	default:
+		break;
+	}
+
+	dev->cal.avg_rssi_all = mt76x2_phy_get_min_avg_rssi(dev);
+	false_cca = FIELD_GET(MT_RX_STAT_1_CCA_ERRORS,
+			      mt76_rr(dev, MT_RX_STAT_1));
+
+	mt76x2u_mcu_set_dynamic_vga(dev, channel, false, false,
+				    dev->cal.avg_rssi_all, false_cca);
+}
+
+void mt76x2u_phy_calibrate(struct work_struct *work)
+{
+	struct mt76x2_dev *dev;
+
+	dev = container_of(work, struct mt76x2_dev, cal_work.work);
+	mt76x2u_phy_tssi_compensate(dev);
+	mt76x2u_phy_update_channel_gain(dev);
+
+	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+}
+
+int mt76x2u_phy_set_channel(struct mt76x2_dev *dev,
+			    struct cfg80211_chan_def *chandef)
+{
+	u32 ext_cca_chan[4] = {
+		[0] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(0)),
+		[1] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(1)),
+		[2] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(2)),
+		[3] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(3)),
+	};
+	bool scan = test_bit(MT76_SCANNING, &dev->mt76.state);
+	struct ieee80211_channel *chan = chandef->chan;
+	u8 channel = chan->hw_value, bw, bw_index;
+	int ch_group_index, freq, freq1, ret;
+
+	dev->cal.channel_cal_done = false;
+	freq = chandef->chan->center_freq;
+	freq1 = chandef->center_freq1;
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_40:
+		bw = 1;
+		if (freq1 > freq) {
+			bw_index = 1;
+			ch_group_index = 0;
+		} else {
+			bw_index = 3;
+			ch_group_index = 1;
+		}
+		channel += 2 - ch_group_index * 4;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		ch_group_index = (freq - freq1 + 30) / 20;
+		if (WARN_ON(ch_group_index < 0 || ch_group_index > 3))
+			ch_group_index = 0;
+		bw = 2;
+		bw_index = ch_group_index;
+		channel += 6 - ch_group_index * 4;
+		break;
+	default:
+		bw = 0;
+		bw_index = 0;
+		ch_group_index = 0;
+		break;
+	}
+
+	mt76x2_read_rx_gain(dev);
+	mt76x2_phy_set_txpower_regs(dev, chan->band);
+	mt76x2_configure_tx_delay(dev, chan->band, bw);
+	mt76x2_phy_set_txpower(dev);
+
+	mt76x2_phy_set_band(dev, chan->band, ch_group_index & 1);
+	mt76x2_phy_set_bw(dev, chandef->width, ch_group_index);
+
+	mt76_rmw(dev, MT_EXT_CCA_CFG,
+		 (MT_EXT_CCA_CFG_CCA0 |
+		  MT_EXT_CCA_CFG_CCA1 |
+		  MT_EXT_CCA_CFG_CCA2 |
+		  MT_EXT_CCA_CFG_CCA3 |
+		  MT_EXT_CCA_CFG_CCA_MASK),
+		 ext_cca_chan[ch_group_index]);
+
+	ret = mt76x2u_mcu_set_channel(dev, channel, bw, bw_index, scan);
+	if (ret)
+		return ret;
+
+	mt76x2u_mcu_init_gain(dev, channel, dev->cal.rx.mcu_gain, true);
+
+	/* Enable LDPC Rx */
+	if (mt76xx_rev(dev) >= MT76XX_REV_E3)
+		mt76_set(dev, MT_BBP(RXO, 13), BIT(10));
+
+	if (!dev->cal.init_cal_done) {
+		u8 val = mt76x2_eeprom_get(dev, MT_EE_BT_RCAL_RESULT);
+
+		if (val != 0xff)
+			mt76x2u_mcu_calibrate(dev, MCU_CAL_R, 0);
+	}
+
+	mt76x2u_mcu_calibrate(dev, MCU_CAL_RXDCOC, channel);
+
+	/* Rx LPF calibration */
+	if (!dev->cal.init_cal_done)
+		mt76x2u_mcu_calibrate(dev, MCU_CAL_RC, 0);
+	dev->cal.init_cal_done = true;
+
+	mt76_wr(dev, MT_BBP(AGC, 61), 0xff64a4e2);
+	mt76_wr(dev, MT_BBP(AGC, 7), 0x08081010);
+	mt76_wr(dev, MT_BBP(AGC, 11), 0x00000404);
+	mt76_wr(dev, MT_BBP(AGC, 2), 0x00007070);
+	mt76_wr(dev, MT_TXOP_CTRL_CFG, 0X04101b3f);
+
+	mt76_set(dev, MT_BBP(TXO, 4), BIT(25));
+	mt76_set(dev, MT_BBP(RXO, 13), BIT(8));
+
+	if (scan)
+		return 0;
+
+	if (mt76x2_tssi_enabled(dev)) {
+		/* init default values for temp compensation */
+		mt76_rmw_field(dev, MT_TX_ALC_CFG_1, MT_TX_ALC_CFG_1_TEMP_COMP,
+			       0x38);
+		mt76_rmw_field(dev, MT_TX_ALC_CFG_2, MT_TX_ALC_CFG_2_TEMP_COMP,
+			       0x38);
+
+		/* init tssi calibration */
+		if (!mt76x2_channel_silent(dev)) {
+			struct ieee80211_channel *chan;
+			u32 flag = 0;
+
+			chan = dev->mt76.chandef.chan;
+			if (chan->band == NL80211_BAND_5GHZ)
+				flag |= BIT(0);
+			if (mt76x2_ext_pa_enabled(dev, chan->band))
+				flag |= BIT(8);
+			mt76x2u_mcu_calibrate(dev, MCU_CAL_TSSI, flag);
+			dev->cal.tssi_cal_done = true;
+		}
+	}
+
+	ieee80211_queue_delayed_work(mt76_hw(dev), &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+	return 0;
+}
-- 
cgit v1.2.3


From 7b4859026ccd47fb1fb48394123fda08d4f30bd6 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:51 +0200
Subject: mt76x0: core files

Core files of mt76x0 driver.

mt76x0 driver adds support for Mediatek MT7610U based
USB Wi-Fi dongles.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/core.c   |  34 ++
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h | 335 +++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/regs.h   | 651 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/util.c   |  42 ++
 4 files changed, 1062 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/core.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/regs.h
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/util.c

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/core.c b/drivers/net/wireless/mediatek/mt76/mt76x0/core.c
new file mode 100644
index 000000000000..892803fce842
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/core.c
@@ -0,0 +1,34 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+
+int mt76x0_wait_asic_ready(struct mt76x0_dev *dev)
+{
+	int i = 100;
+	u32 val;
+
+	do {
+		if (test_bit(MT76_REMOVED, &dev->mt76.state))
+			return -EIO;
+
+		val = mt76_rr(dev, MT_MAC_CSR0);
+		if (val && ~val)
+			return 0;
+
+		udelay(10);
+	} while (i--);
+
+	return -EIO;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
new file mode 100644
index 000000000000..49b82a23533c
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -0,0 +1,335 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef MT76X0U_H
+#define MT76X0U_H
+
+#include <linux/bitfield.h>
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/mutex.h>
+#include <linux/usb.h>
+#include <linux/completion.h>
+#include <net/mac80211.h>
+#include <linux/debugfs.h>
+
+#include "../mt76.h"
+#include "regs.h"
+
+#define MT_CALIBRATE_INTERVAL		(4 * HZ)
+
+#define MT_FREQ_CAL_INIT_DELAY		(30 * HZ)
+#define MT_FREQ_CAL_CHECK_INTERVAL	(10 * HZ)
+#define MT_FREQ_CAL_ADJ_INTERVAL	(HZ / 2)
+
+#define MT_BBP_REG_VERSION		0x00
+
+#define MT_USB_AGGR_SIZE_LIMIT		21 /* * 1024B */
+#define MT_USB_AGGR_TIMEOUT		0x80 /* * 33ns */
+#define MT_RX_ORDER			3
+#define MT_RX_URB_SIZE			(PAGE_SIZE << MT_RX_ORDER)
+
+struct mt76x0_dma_buf {
+	struct urb *urb;
+	void *buf;
+	dma_addr_t dma;
+	size_t len;
+};
+
+struct mt76x0_mcu {
+	struct mutex mutex;
+
+	u8 msg_seq;
+
+	struct mt76x0_dma_buf resp;
+	struct completion resp_cmpl;
+
+	struct mt76_reg_pair *reg_pairs;
+	unsigned int reg_pairs_len;
+	u32 reg_base;
+	bool burst_read;
+};
+
+struct mac_stats {
+	u64 rx_stat[6];
+	u64 tx_stat[6];
+	u64 aggr_stat[2];
+	u64 aggr_n[32];
+	u64 zero_len_del[2];
+};
+
+#define N_RX_ENTRIES	16
+struct mt76x0_rx_queue {
+	struct mt76x0_dev *dev;
+
+	struct mt76x0_dma_buf_rx {
+		struct urb *urb;
+		struct page *p;
+	} e[N_RX_ENTRIES];
+
+	unsigned int start;
+	unsigned int end;
+	unsigned int entries;
+	unsigned int pending;
+};
+
+#define N_TX_ENTRIES	64
+
+struct mt76x0_tx_queue {
+	struct mt76x0_dev *dev;
+
+	struct mt76x0_dma_buf_tx {
+		struct urb *urb;
+		struct sk_buff *skb;
+	} e[N_TX_ENTRIES];
+
+	unsigned int start;
+	unsigned int end;
+	unsigned int entries;
+	unsigned int used;
+	unsigned int fifo_seq;
+};
+
+/* WCID allocation:
+ *     0: mcast wcid
+ *     1: bssid wcid
+ *  1...: STAs
+ * ...7e: group wcids
+ *    7f: reserved
+ */
+#define N_WCIDS		128
+#define GROUP_WCID(idx)	(254 - idx)
+
+struct mt76x0_eeprom_params;
+
+#define MT_EE_TEMPERATURE_SLOPE		39
+#define MT_FREQ_OFFSET_INVALID		-128
+
+/* addr req mask */
+#define MT_VEND_TYPE_EEPROM	BIT(31)
+#define MT_VEND_TYPE_CFG	BIT(30)
+#define MT_VEND_TYPE_MASK	(MT_VEND_TYPE_EEPROM | MT_VEND_TYPE_CFG)
+
+#define MT_VEND_ADDR(type, n)	(MT_VEND_TYPE_##type | (n))
+
+enum mt_temp_mode {
+	MT_TEMP_MODE_NORMAL,
+	MT_TEMP_MODE_HIGH,
+	MT_TEMP_MODE_LOW,
+};
+
+enum mt_bw {
+	MT_BW_20,
+	MT_BW_40,
+};
+
+/**
+ * struct mt76x0_dev - adapter structure
+ * @lock:		protects @wcid->tx_rate.
+ * @mac_lock:		locks out mac80211's tx status and rx paths.
+ * @tx_lock:		protects @tx_q and changes of MT76_STATE_*_STATS
+ *			flags in @state.
+ * @rx_lock:		protects @rx_q.
+ * @con_mon_lock:	protects @ap_bssid, @bcn_*, @avg_rssi.
+ * @mutex:		ensures exclusive access from mac80211 callbacks.
+ * @reg_atomic_mutex:	ensures atomicity of indirect register accesses
+ *			(accesses to RF and BBP).
+ * @hw_atomic_mutex:	ensures exclusive access to HW during critical
+ *			operations (power management, channel switch).
+ */
+struct mt76x0_dev {
+	struct mt76_dev mt76; /* must be first */
+
+	struct mutex mutex;
+
+	struct mutex usb_ctrl_mtx;
+	u8 data[32];
+
+	struct tasklet_struct rx_tasklet;
+	struct tasklet_struct tx_tasklet;
+
+	u8 out_ep[__MT_EP_OUT_MAX];
+	u16 out_max_packet;
+	u8 in_ep[__MT_EP_IN_MAX];
+	u16 in_max_packet;
+
+	unsigned long wcid_mask[DIV_ROUND_UP(N_WCIDS, BITS_PER_LONG)];
+	unsigned long vif_mask;
+
+	struct mt76x0_mcu mcu;
+
+	struct delayed_work cal_work;
+	struct delayed_work mac_work;
+
+	struct workqueue_struct *stat_wq;
+	struct delayed_work stat_work;
+
+	struct mt76_wcid *mon_wcid;
+	struct mt76_wcid __rcu *wcid[N_WCIDS];
+
+	spinlock_t mac_lock;
+
+	const u16 *beacon_offsets;
+
+	u8 macaddr[ETH_ALEN];
+	struct mt76x0_eeprom_params *ee;
+
+	struct mutex reg_atomic_mutex;
+	struct mutex hw_atomic_mutex;
+
+	u32 rxfilter;
+	u32 debugfs_reg;
+
+	/* TX */
+	spinlock_t tx_lock;
+	struct mt76x0_tx_queue *tx_q;
+	struct sk_buff_head tx_skb_done;
+
+	atomic_t avg_ampdu_len;
+
+	/* RX */
+	spinlock_t rx_lock;
+	struct mt76x0_rx_queue rx_q;
+
+	/* Connection monitoring things */
+	spinlock_t con_mon_lock;
+	u8 ap_bssid[ETH_ALEN];
+
+	s8 bcn_freq_off;
+	u8 bcn_phy_mode;
+
+	int avg_rssi; /* starts at 0 and converges */
+
+	u8 agc_save;
+	u16 chainmask;
+
+	struct mac_stats stats;
+};
+
+struct mt76x0_wcid {
+	u8 idx;
+	u8 hw_key_idx;
+
+	u16 tx_rate;
+	bool tx_rate_set;
+	u8 tx_rate_nss;
+};
+
+struct mt76_vif {
+	u8 idx;
+
+	struct mt76_wcid group_wcid;
+};
+
+struct mt76_tx_status {
+	u8 valid:1;
+	u8 success:1;
+	u8 aggr:1;
+	u8 ack_req:1;
+	u8 is_probe:1;
+	u8 wcid;
+	u8 pktid;
+	u8 retry;
+	u16 rate;
+} __packed __aligned(2);
+
+struct mt76_sta {
+	struct mt76_wcid wcid;
+	struct mt76_tx_status status;
+	int n_frames;
+	u16 agg_ssn[IEEE80211_NUM_TIDS];
+};
+
+struct mt76_reg_pair {
+	u32 reg;
+	u32 value;
+};
+
+struct mt76x0_rxwi;
+
+extern const struct ieee80211_ops mt76x0_ops;
+
+static inline bool is_mt7610e(struct mt76x0_dev *dev)
+{
+	/* TODO */
+	return false;
+}
+
+void mt76x0_init_debugfs(struct mt76x0_dev *dev);
+
+int mt76x0_wait_asic_ready(struct mt76x0_dev *dev);
+
+/* Compatibility with mt76 */
+#define mt76_rmw_field(_dev, _reg, _field, _val)	\
+	mt76_rmw(_dev, _reg, _field, FIELD_PREP(_field, _val))
+
+int mt76x0_write_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			    const struct mt76_reg_pair *data, int len);
+int mt76x0_read_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			  struct mt76_reg_pair *data, int len);
+int mt76x0_burst_write_regs(struct mt76x0_dev *dev, u32 offset,
+			     const u32 *data, int n);
+void mt76x0_addr_wr(struct mt76x0_dev *dev, const u32 offset, const u8 *addr);
+
+/* Init */
+struct mt76x0_dev *mt76x0_alloc_device(struct device *dev);
+int mt76x0_init_hardware(struct mt76x0_dev *dev);
+int mt76x0_register_device(struct mt76x0_dev *dev);
+void mt76x0_cleanup(struct mt76x0_dev *dev);
+
+int mt76x0_mac_start(struct mt76x0_dev *dev);
+void mt76x0_mac_stop(struct mt76x0_dev *dev);
+
+/* PHY */
+void mt76x0_phy_init(struct mt76x0_dev *dev);
+int mt76x0_wait_bbp_ready(struct mt76x0_dev *dev);
+void mt76x0_agc_save(struct mt76x0_dev *dev);
+void mt76x0_agc_restore(struct mt76x0_dev *dev);
+int mt76x0_phy_set_channel(struct mt76x0_dev *dev,
+			    struct cfg80211_chan_def *chandef);
+void mt76x0_phy_recalibrate_after_assoc(struct mt76x0_dev *dev);
+int mt76x0_phy_get_rssi(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi);
+void mt76x0_phy_con_cal_onoff(struct mt76x0_dev *dev,
+			       struct ieee80211_bss_conf *info);
+
+/* MAC */
+void mt76x0_mac_work(struct work_struct *work);
+void mt76x0_mac_set_protection(struct mt76x0_dev *dev, bool legacy_prot,
+				int ht_mode);
+void mt76x0_mac_set_short_preamble(struct mt76x0_dev *dev, bool short_preamb);
+void mt76x0_mac_config_tsf(struct mt76x0_dev *dev, bool enable, int interval);
+void
+mt76x0_mac_wcid_setup(struct mt76x0_dev *dev, u8 idx, u8 vif_idx, u8 *mac);
+void mt76x0_mac_set_ampdu_factor(struct mt76x0_dev *dev);
+
+/* TX */
+void mt76x0_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+		struct sk_buff *skb);
+int mt76x0_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		    u16 queue, const struct ieee80211_tx_queue_params *params);
+void mt76x0_tx_status(struct mt76x0_dev *dev, struct sk_buff *skb);
+void mt76x0_tx_stat(struct work_struct *work);
+
+/* util */
+void mt76_remove_hdr_pad(struct sk_buff *skb);
+int mt76_insert_hdr_pad(struct sk_buff *skb);
+
+int mt76x0_dma_init(struct mt76x0_dev *dev);
+void mt76x0_dma_cleanup(struct mt76x0_dev *dev);
+
+int mt76x0_dma_enqueue_tx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			   struct mt76_wcid *wcid, int hw_q);
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/regs.h b/drivers/net/wireless/mediatek/mt76/mt76x0/regs.h
new file mode 100644
index 000000000000..16bed4aaa242
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/regs.h
@@ -0,0 +1,651 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76_REGS_H
+#define __MT76_REGS_H
+
+#include <linux/bitops.h>
+
+#define MT_ASIC_VERSION			0x0000
+
+#define MT76XX_REV_E3		0x22
+#define MT76XX_REV_E4		0x33
+
+#define MT_CMB_CTRL			0x0020
+#define MT_CMB_CTRL_XTAL_RDY		BIT(22)
+#define MT_CMB_CTRL_PLL_LD		BIT(23)
+
+#define MT_EFUSE_CTRL			0x0024
+#define MT_EFUSE_CTRL_AOUT		GENMASK(5, 0)
+#define MT_EFUSE_CTRL_MODE		GENMASK(7, 6)
+#define MT_EFUSE_CTRL_LDO_OFF_TIME	GENMASK(13, 8)
+#define MT_EFUSE_CTRL_LDO_ON_TIME	GENMASK(15, 14)
+#define MT_EFUSE_CTRL_AIN		GENMASK(25, 16)
+#define MT_EFUSE_CTRL_KICK		BIT(30)
+#define MT_EFUSE_CTRL_SEL		BIT(31)
+
+#define MT_EFUSE_DATA_BASE		0x0028
+#define MT_EFUSE_DATA(_n)		(MT_EFUSE_DATA_BASE + ((_n) << 2))
+
+#define MT_COEXCFG0			0x0040
+#define MT_COEXCFG0_COEX_EN		BIT(0)
+
+#define MT_COEXCFG3			0x004c
+
+#define MT_LDO_CTRL_0			0x006c
+#define MT_LDO_CTRL_1			0x0070
+
+#define MT_WLAN_FUN_CTRL		0x0080
+#define MT_WLAN_FUN_CTRL_WLAN_EN	BIT(0)
+#define MT_WLAN_FUN_CTRL_WLAN_CLK_EN	BIT(1)
+#define MT_WLAN_FUN_CTRL_WLAN_RESET_RF	BIT(2)
+
+#define MT_WLAN_FUN_CTRL_WLAN_RESET	BIT(3) /* MT76x0 */
+#define MT_WLAN_FUN_CTRL_CSR_F20M_CKEN	BIT(3) /* MT76x2 */
+
+#define MT_WLAN_FUN_CTRL_PCIE_CLK_REQ	BIT(4)
+#define MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL	BIT(5)
+#define MT_WLAN_FUN_CTRL_INV_ANT_SEL	BIT(6)
+#define MT_WLAN_FUN_CTRL_WAKE_HOST	BIT(7)
+
+#define MT_WLAN_FUN_CTRL_THERM_RST	BIT(8) /* MT76x2 */
+#define MT_WLAN_FUN_CTRL_THERM_CKEN	BIT(9) /* MT76x2 */
+
+#define MT_WLAN_FUN_CTRL_GPIO_IN	GENMASK(15, 8) /* MT76x0 */
+#define MT_WLAN_FUN_CTRL_GPIO_OUT	GENMASK(23, 16) /* MT76x0 */
+#define MT_WLAN_FUN_CTRL_GPIO_OUT_EN	GENMASK(31, 24) /* MT76x0 */
+
+#define MT_XO_CTRL0			0x0100
+#define MT_XO_CTRL1			0x0104
+#define MT_XO_CTRL2			0x0108
+#define MT_XO_CTRL3			0x010c
+#define MT_XO_CTRL4			0x0110
+
+#define MT_XO_CTRL5			0x0114
+#define MT_XO_CTRL5_C2_VAL		GENMASK(14, 8)
+
+#define MT_XO_CTRL6			0x0118
+#define MT_XO_CTRL6_C2_CTRL		GENMASK(14, 8)
+
+#define MT_XO_CTRL7			0x011c
+
+#define MT_IOCFG_6			0x0124
+#define MT_WLAN_MTC_CTRL		0x10148
+#define MT_WLAN_MTC_CTRL_MTCMOS_PWR_UP	BIT(0)
+#define MT_WLAN_MTC_CTRL_PWR_ACK	BIT(12)
+#define MT_WLAN_MTC_CTRL_PWR_ACK_S	BIT(13)
+#define MT_WLAN_MTC_CTRL_BBP_MEM_PD	GENMASK(19, 16)
+#define MT_WLAN_MTC_CTRL_PBF_MEM_PD	BIT(20)
+#define MT_WLAN_MTC_CTRL_FCE_MEM_PD	BIT(21)
+#define MT_WLAN_MTC_CTRL_TSO_MEM_PD	BIT(22)
+#define MT_WLAN_MTC_CTRL_BBP_MEM_RB	BIT(24)
+#define MT_WLAN_MTC_CTRL_PBF_MEM_RB	BIT(25)
+#define MT_WLAN_MTC_CTRL_FCE_MEM_RB	BIT(26)
+#define MT_WLAN_MTC_CTRL_TSO_MEM_RB	BIT(27)
+#define MT_WLAN_MTC_CTRL_STATE_UP	BIT(28)
+
+#define MT_INT_SOURCE_CSR		0x0200
+#define MT_INT_MASK_CSR			0x0204
+
+#define MT_INT_RX_DONE(_n)		BIT(_n)
+#define MT_INT_RX_DONE_ALL		GENMASK(1, 0)
+#define MT_INT_TX_DONE_ALL		GENMASK(13, 4)
+#define MT_INT_TX_DONE(_n)		BIT(_n + 4)
+#define MT_INT_RX_COHERENT		BIT(16)
+#define MT_INT_TX_COHERENT		BIT(17)
+#define MT_INT_ANY_COHERENT		BIT(18)
+#define MT_INT_MCU_CMD			BIT(19)
+#define MT_INT_TBTT			BIT(20)
+#define MT_INT_PRE_TBTT			BIT(21)
+#define MT_INT_TX_STAT			BIT(22)
+#define MT_INT_AUTO_WAKEUP		BIT(23)
+#define MT_INT_GPTIMER			BIT(24)
+#define MT_INT_RXDELAYINT		BIT(26)
+#define MT_INT_TXDELAYINT		BIT(27)
+
+#define MT_WPDMA_GLO_CFG		0x0208
+#define MT_WPDMA_GLO_CFG_TX_DMA_EN	BIT(0)
+#define MT_WPDMA_GLO_CFG_TX_DMA_BUSY	BIT(1)
+#define MT_WPDMA_GLO_CFG_RX_DMA_EN	BIT(2)
+#define MT_WPDMA_GLO_CFG_RX_DMA_BUSY	BIT(3)
+#define MT_WPDMA_GLO_CFG_DMA_BURST_SIZE	GENMASK(5, 4)
+#define MT_WPDMA_GLO_CFG_TX_WRITEBACK_DONE	BIT(6)
+#define MT_WPDMA_GLO_CFG_BIG_ENDIAN	BIT(7)
+#define MT_WPDMA_GLO_CFG_HDR_SEG_LEN	GENMASK(15, 8)
+#define MT_WPDMA_GLO_CFG_CLK_GATE_DIS	BIT(30)
+#define MT_WPDMA_GLO_CFG_RX_2B_OFFSET	BIT(31)
+
+#define MT_WPDMA_RST_IDX		0x020c
+
+#define MT_WPDMA_DELAY_INT_CFG		0x0210
+
+#define MT_WMM_AIFSN		0x0214
+#define MT_WMM_AIFSN_MASK		GENMASK(3, 0)
+#define MT_WMM_AIFSN_SHIFT(_n)		((_n) * 4)
+
+#define MT_WMM_CWMIN		0x0218
+#define MT_WMM_CWMIN_MASK		GENMASK(3, 0)
+#define MT_WMM_CWMIN_SHIFT(_n)		((_n) * 4)
+
+#define MT_WMM_CWMAX		0x021c
+#define MT_WMM_CWMAX_MASK		GENMASK(3, 0)
+#define MT_WMM_CWMAX_SHIFT(_n)		((_n) * 4)
+
+#define MT_WMM_TXOP_BASE		0x0220
+#define MT_WMM_TXOP(_n)			(MT_WMM_TXOP_BASE + (((_n) / 2) << 2))
+#define MT_WMM_TXOP_SHIFT(_n)		((_n & 1) * 16)
+#define MT_WMM_TXOP_MASK		GENMASK(15, 0)
+
+#define MT_WMM_CTRL			0x0230 /* MT76x0 */
+
+#define MT_FCE_DMA_ADDR			0x0230
+#define MT_FCE_DMA_LEN			0x0234
+
+#define MT_USB_DMA_CFG			0x238
+#define MT_USB_DMA_CFG_RX_BULK_AGG_TOUT	GENMASK(7, 0)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_LMT	GENMASK(15, 8)
+#define MT_USB_DMA_CFG_TX_WL_DROP	BIT(16)
+#define MT_USB_DMA_CFG_WAKEUP_EN	BIT(17)
+#define MT_USB_DMA_CFG_RX_DROP_OR_PADDING	BIT(18)
+#define MT_USB_DMA_CFG_TX_CLR		BIT(19)
+#define MT_USB_DMA_CFG_WL_LPK_EN	BIT(20)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_EN	BIT(21)
+#define MT_USB_DMA_CFG_RX_BULK_EN	BIT(22)
+#define MT_USB_DMA_CFG_TX_BULK_EN	BIT(23)
+#define MT_USB_DMA_CFG_EP_OUT_VALID	GENMASK(29, 24)
+#define MT_USB_DMA_CFG_RX_BUSY		BIT(30)
+#define MT_USB_DMA_CFG_TX_BUSY		BIT(31)
+#if 0
+#define MT_USB_DMA_CFG_TX_CLR		BIT(19)
+#define MT_USB_DMA_CFG_TXOP_HALT	BIT(20)
+#define MT_USB_DMA_CFG_RX_BULK_AGG_EN	BIT(21)
+#define MT_USB_DMA_CFG_RX_BULK_EN	BIT(22)
+#define MT_USB_DMA_CFG_TX_BULK_EN	BIT(23)
+#define MT_USB_DMA_CFG_UDMA_RX_WL_DROP	BIT(25)
+#endif
+
+#define MT_TSO_CTRL			0x0250
+#define MT_HEADER_TRANS_CTRL_REG	0x0260
+
+#define MT_US_CYC_CFG			0x02a4
+#define MT_US_CYC_CNT			GENMASK(7, 0)
+
+#define MT_TX_RING_BASE			0x0300
+#define MT_RX_RING_BASE			0x03c0
+#define MT_RING_SIZE			0x10
+
+#define MT_TX_HW_QUEUE_MCU		8
+#define MT_TX_HW_QUEUE_MGMT		9
+
+#define MT_PBF_SYS_CTRL			0x0400
+#define MT_PBF_SYS_CTRL_MCU_RESET	BIT(0)
+#define MT_PBF_SYS_CTRL_DMA_RESET	BIT(1)
+#define MT_PBF_SYS_CTRL_MAC_RESET	BIT(2)
+#define MT_PBF_SYS_CTRL_PBF_RESET	BIT(3)
+#define MT_PBF_SYS_CTRL_ASY_RESET	BIT(4)
+
+#define MT_PBF_CFG			0x0404
+#define MT_PBF_CFG_TX0Q_EN		BIT(0)
+#define MT_PBF_CFG_TX1Q_EN		BIT(1)
+#define MT_PBF_CFG_TX2Q_EN		BIT(2)
+#define MT_PBF_CFG_TX3Q_EN		BIT(3)
+#define MT_PBF_CFG_RX0Q_EN		BIT(4)
+#define MT_PBF_CFG_RX_DROP_EN		BIT(8)
+
+#define MT_PBF_TX_MAX_PCNT		0x0408
+#define MT_PBF_RX_MAX_PCNT		0x040c
+
+#define MT_BCN_OFFSET_BASE		0x041c
+#define MT_BCN_OFFSET(_n)		(MT_BCN_OFFSET_BASE + ((_n) << 2))
+
+#define MT_RXQ_STA			0x0430
+#define MT_TXQ_STA			0x0434
+#define	MT_RF_CSR_CFG			0x0500
+#define MT_RF_CSR_CFG_DATA		GENMASK(7, 0)
+#define MT_RF_CSR_CFG_REG_ID		GENMASK(13, 8)
+#define MT_RF_CSR_CFG_REG_BANK		GENMASK(17, 14)
+#define MT_RF_CSR_CFG_WR		BIT(30)
+#define MT_RF_CSR_CFG_KICK		BIT(31)
+
+#define MT_RF_BYPASS_0			0x0504
+#define MT_RF_BYPASS_1			0x0508
+#define MT_RF_SETTING_0			0x050c
+
+#define MT_RF_MISC			0x0518
+#define MT_RF_DATA_WRITE		0x0524
+
+#define MT_RF_CTRL			0x0528
+#define MT_RF_CTRL_ADDR			GENMASK(11, 0)
+#define MT_RF_CTRL_WRITE		BIT(12)
+#define MT_RF_CTRL_BUSY			BIT(13)
+#define MT_RF_CTRL_IDX			BIT(16)
+
+#define MT_RF_DATA_READ			0x052c
+
+#define MT_COM_REG0			0x0730
+#define MT_COM_REG1			0x0734
+#define MT_COM_REG2			0x0738
+#define MT_COM_REG3			0x073C
+
+#define MT_FCE_PSE_CTRL			0x0800
+#define MT_FCE_PARAMETERS		0x0804
+#define MT_FCE_CSO			0x0808
+
+#define MT_FCE_L2_STUFF			0x080c
+#define MT_FCE_L2_STUFF_HT_L2_EN	BIT(0)
+#define MT_FCE_L2_STUFF_QOS_L2_EN	BIT(1)
+#define MT_FCE_L2_STUFF_RX_STUFF_EN	BIT(2)
+#define MT_FCE_L2_STUFF_TX_STUFF_EN	BIT(3)
+#define MT_FCE_L2_STUFF_WR_MPDU_LEN_EN	BIT(4)
+#define MT_FCE_L2_STUFF_MVINV_BSWAP	BIT(5)
+#define MT_FCE_L2_STUFF_TS_CMD_QSEL_EN	GENMASK(15, 8)
+#define MT_FCE_L2_STUFF_TS_LEN_EN	GENMASK(23, 16)
+#define MT_FCE_L2_STUFF_OTHER_PORT	GENMASK(25, 24)
+
+#define MT_FCE_WLAN_FLOW_CONTROL1	0x0824
+
+#define MT_TX_CPU_FROM_FCE_BASE_PTR	0x09a0
+#define MT_TX_CPU_FROM_FCE_MAX_COUNT	0x09a4
+#define MT_TX_CPU_FROM_FCE_CPU_DESC_IDX	0x09a8
+
+#define MT_FCE_PDMA_GLOBAL_CONF		0x09c4
+
+#define MT_PAUSE_ENABLE_CONTROL1	0x0a38
+
+#define MT_FCE_SKIP_FS			0x0a6c
+
+#define MT_MAC_CSR0			0x1000
+#define MT_MAC_SYS_CTRL			0x1004
+#define MT_MAC_SYS_CTRL_RESET_CSR	BIT(0)
+#define MT_MAC_SYS_CTRL_RESET_BBP	BIT(1)
+#define MT_MAC_SYS_CTRL_ENABLE_TX	BIT(2)
+#define MT_MAC_SYS_CTRL_ENABLE_RX	BIT(3)
+
+#define MT_MAC_ADDR_DW0			0x1008
+#define MT_MAC_ADDR_DW1			0x100c
+#define MT_MAC_ADDR_DW1_U2ME_MASK	GENMASK(23, 16)
+
+#define MT_MAC_BSSID_DW0		0x1010
+#define MT_MAC_BSSID_DW1		0x1014
+#define MT_MAC_BSSID_DW1_ADDR		GENMASK(15, 0)
+#define MT_MAC_BSSID_DW1_MBSS_MODE	GENMASK(17, 16)
+#define MT_MAC_BSSID_DW1_MBEACON_N	GENMASK(20, 18)
+#define MT_MAC_BSSID_DW1_MBSS_LOCAL_BIT	BIT(21)
+#define MT_MAC_BSSID_DW1_MBSS_MODE_B2	BIT(22)
+#define MT_MAC_BSSID_DW1_MBEACON_N_B3	BIT(23)
+#define MT_MAC_BSSID_DW1_MBSS_IDX_BYTE	GENMASK(26, 24)
+
+#define MT_MAX_LEN_CFG			0x1018
+#define MT_MAX_LEN_CFG_AMPDU		GENMASK(13, 12)
+
+#define MT_LED_CFG			0x102c
+
+#define MT_AMPDU_MAX_LEN_20M1S		0x1030
+#define MT_AMPDU_MAX_LEN_20M2S		0x1034
+#define MT_AMPDU_MAX_LEN_40M1S		0x1038
+#define MT_AMPDU_MAX_LEN_40M2S		0x103c
+#define MT_AMPDU_MAX_LEN		0x1040
+
+#define MT_WCID_DROP_BASE		0x106c
+#define MT_WCID_DROP(_n)		(MT_WCID_DROP_BASE + ((_n) >> 5) * 4)
+#define MT_WCID_DROP_MASK(_n)		BIT((_n) % 32)
+
+#define MT_BCN_BYPASS_MASK		0x108c
+
+#define MT_MAC_APC_BSSID_BASE		0x1090
+#define MT_MAC_APC_BSSID_L(_n)		(MT_MAC_APC_BSSID_BASE + ((_n) * 8))
+#define MT_MAC_APC_BSSID_H(_n)		(MT_MAC_APC_BSSID_BASE + ((_n) * 8 + 4))
+#define MT_MAC_APC_BSSID_H_ADDR		GENMASK(15, 0)
+#define MT_MAC_APC_BSSID0_H_EN		BIT(16)
+
+#define MT_XIFS_TIME_CFG		0x1100
+#define MT_XIFS_TIME_CFG_CCK_SIFS	GENMASK(7, 0)
+#define MT_XIFS_TIME_CFG_OFDM_SIFS	GENMASK(15, 8)
+#define MT_XIFS_TIME_CFG_OFDM_XIFS	GENMASK(19, 16)
+#define MT_XIFS_TIME_CFG_EIFS		GENMASK(28, 20)
+#define MT_XIFS_TIME_CFG_BB_RXEND_EN	BIT(29)
+
+#define MT_BKOFF_SLOT_CFG		0x1104
+#define MT_BKOFF_SLOT_CFG_SLOTTIME	GENMASK(7, 0)
+#define MT_BKOFF_SLOT_CFG_CC_DELAY	GENMASK(11, 8)
+
+#define MT_BEACON_TIME_CFG		0x1114
+#define MT_BEACON_TIME_CFG_INTVAL	GENMASK(15, 0)
+#define MT_BEACON_TIME_CFG_TIMER_EN	BIT(16)
+#define MT_BEACON_TIME_CFG_SYNC_MODE	GENMASK(18, 17)
+#define MT_BEACON_TIME_CFG_TBTT_EN	BIT(19)
+#define MT_BEACON_TIME_CFG_BEACON_TX	BIT(20)
+#define MT_BEACON_TIME_CFG_TSF_COMP	GENMASK(31, 24)
+
+#define MT_TBTT_SYNC_CFG		0x1118
+#define MT_TBTT_TIMER_CFG		0x1124
+
+#define MT_INT_TIMER_CFG		0x1128
+#define MT_INT_TIMER_CFG_PRE_TBTT	GENMASK(15, 0)
+#define MT_INT_TIMER_CFG_GP_TIMER	GENMASK(31, 16)
+
+#define MT_INT_TIMER_EN			0x112c
+#define MT_INT_TIMER_EN_PRE_TBTT_EN	BIT(0)
+#define MT_INT_TIMER_EN_GP_TIMER_EN	BIT(1)
+
+#define MT_MAC_STATUS			0x1200
+#define MT_MAC_STATUS_TX		BIT(0)
+#define MT_MAC_STATUS_RX		BIT(1)
+
+#define MT_PWR_PIN_CFG			0x1204
+#define MT_AUX_CLK_CFG			0x120c
+
+#define MT_BB_PA_MODE_CFG0		0x1214
+#define MT_BB_PA_MODE_CFG1		0x1218
+#define MT_RF_PA_MODE_CFG0		0x121c
+#define MT_RF_PA_MODE_CFG1		0x1220
+
+#define MT_RF_PA_MODE_ADJ0		0x1228
+#define MT_RF_PA_MODE_ADJ1		0x122c
+
+#define MT_DACCLK_EN_DLY_CFG		0x1264
+
+#define MT_EDCA_CFG_BASE		0x1300
+#define MT_EDCA_CFG_AC(_n)		(MT_EDCA_CFG_BASE + ((_n) << 2))
+#define MT_EDCA_CFG_TXOP		GENMASK(7, 0)
+#define MT_EDCA_CFG_AIFSN		GENMASK(11, 8)
+#define MT_EDCA_CFG_CWMIN		GENMASK(15, 12)
+#define MT_EDCA_CFG_CWMAX		GENMASK(19, 16)
+
+#define MT_TX_PWR_CFG_0			0x1314
+#define MT_TX_PWR_CFG_1			0x1318
+#define MT_TX_PWR_CFG_2			0x131c
+#define MT_TX_PWR_CFG_3			0x1320
+#define MT_TX_PWR_CFG_4			0x1324
+
+#define MT_TX_BAND_CFG			0x132c
+#define MT_TX_BAND_CFG_UPPER_40M	BIT(0)
+#define MT_TX_BAND_CFG_5G		BIT(1)
+#define MT_TX_BAND_CFG_2G		BIT(2)
+
+#define MT_HT_FBK_TO_LEGACY		0x1384
+#define MT_TX_MPDU_ADJ_INT		0x1388
+
+#define MT_TX_PWR_CFG_7			0x13d4
+#define MT_TX_PWR_CFG_8			0x13d8
+#define MT_TX_PWR_CFG_9			0x13dc
+
+#define MT_TX_SW_CFG0			0x1330
+#define MT_TX_SW_CFG1			0x1334
+#define MT_TX_SW_CFG2			0x1338
+
+#define MT_TXOP_CTRL_CFG		0x1340
+#define MT_TXOP_TRUN_EN			GENMASK(5, 0)
+#define MT_TXOP_EXT_CCA_DLY		GENMASK(15, 8)
+#define MT_TXOP_CTRL
+
+#define MT_TX_RTS_CFG			0x1344
+#define MT_TX_RTS_CFG_RETRY_LIMIT	GENMASK(7, 0)
+#define MT_TX_RTS_CFG_THRESH		GENMASK(23, 8)
+#define MT_TX_RTS_FALLBACK		BIT(24)
+
+#define MT_TX_TIMEOUT_CFG		0x1348
+#define MT_TX_RETRY_CFG			0x134c
+#define MT_TX_LINK_CFG			0x1350
+#define MT_HT_FBK_CFG0			0x1354
+#define MT_HT_FBK_CFG1			0x1358
+#define MT_LG_FBK_CFG0			0x135c
+#define MT_LG_FBK_CFG1			0x1360
+
+#define MT_CCK_PROT_CFG			0x1364
+#define MT_OFDM_PROT_CFG		0x1368
+#define MT_MM20_PROT_CFG		0x136c
+#define MT_MM40_PROT_CFG		0x1370
+#define MT_GF20_PROT_CFG		0x1374
+#define MT_GF40_PROT_CFG		0x1378
+
+#define MT_PROT_RATE			GENMASK(15, 0)
+#define MT_PROT_CTRL_RTS_CTS		BIT(16)
+#define MT_PROT_CTRL_CTS2SELF		BIT(17)
+#define MT_PROT_NAV_SHORT		BIT(18)
+#define MT_PROT_NAV_LONG		BIT(19)
+#define MT_PROT_TXOP_ALLOW_CCK		BIT(20)
+#define MT_PROT_TXOP_ALLOW_OFDM		BIT(21)
+#define MT_PROT_TXOP_ALLOW_MM20		BIT(22)
+#define MT_PROT_TXOP_ALLOW_MM40		BIT(23)
+#define MT_PROT_TXOP_ALLOW_GF20		BIT(24)
+#define MT_PROT_TXOP_ALLOW_GF40		BIT(25)
+#define MT_PROT_RTS_THR_EN		BIT(26)
+#define MT_PROT_RATE_CCK_11		0x0003
+#define MT_PROT_RATE_OFDM_6		0x4000
+#define MT_PROT_RATE_OFDM_24		0x4004
+#define MT_PROT_RATE_DUP_OFDM_24	0x4084
+#define MT_PROT_TXOP_ALLOW_ALL		GENMASK(25, 20)
+#define MT_PROT_TXOP_ALLOW_BW20		(MT_PROT_TXOP_ALLOW_ALL &	\
+					 ~MT_PROT_TXOP_ALLOW_MM40 &	\
+					 ~MT_PROT_TXOP_ALLOW_GF40)
+
+#define MT_EXP_ACK_TIME			0x1380
+
+#define MT_TX_PWR_CFG_0_EXT		0x1390
+#define MT_TX_PWR_CFG_1_EXT		0x1394
+
+#define MT_TX_FBK_LIMIT			0x1398
+#define MT_TX_FBK_LIMIT_MPDU_FBK	GENMASK(7, 0)
+#define MT_TX_FBK_LIMIT_AMPDU_FBK	GENMASK(15, 8)
+#define MT_TX_FBK_LIMIT_MPDU_UP_CLEAR	BIT(16)
+#define MT_TX_FBK_LIMIT_AMPDU_UP_CLEAR	BIT(17)
+#define MT_TX_FBK_LIMIT_RATE_LUT	BIT(18)
+
+#define MT_TX0_RF_GAIN_CORR		0x13a0
+#define MT_TX1_RF_GAIN_CORR		0x13a4
+#define MT_TX0_RF_GAIN_ATTEN		0x13a8
+
+#define MT_TX_ALC_CFG_0			0x13b0
+#define MT_TX_ALC_CFG_0_CH_INIT_0	GENMASK(5, 0)
+#define MT_TX_ALC_CFG_0_CH_INIT_1	GENMASK(13, 8)
+#define MT_TX_ALC_CFG_0_LIMIT_0		GENMASK(21, 16)
+#define MT_TX_ALC_CFG_0_LIMIT_1		GENMASK(29, 24)
+
+#define MT_TX_ALC_CFG_1			0x13b4
+#define MT_TX_ALC_CFG_1_TEMP_COMP	GENMASK(5, 0)
+
+#define MT_TX_ALC_CFG_2			0x13a8
+#define MT_TX_ALC_CFG_2_TEMP_COMP	GENMASK(5, 0)
+
+#define MT_TX0_BB_GAIN_ATTEN		0x13c0
+
+#define MT_TX_ALC_VGA3			0x13c8
+
+#define MT_TX_PROT_CFG6			0x13e0
+#define MT_TX_PROT_CFG7			0x13e4
+#define MT_TX_PROT_CFG8			0x13e8
+
+#define MT_PIFS_TX_CFG			0x13ec
+
+#define MT_RX_FILTR_CFG			0x1400
+
+#define MT_RX_FILTR_CFG_CRC_ERR		BIT(0)
+#define MT_RX_FILTR_CFG_PHY_ERR		BIT(1)
+#define MT_RX_FILTR_CFG_PROMISC		BIT(2)
+#define MT_RX_FILTR_CFG_OTHER_BSS	BIT(3)
+#define MT_RX_FILTR_CFG_VER_ERR		BIT(4)
+#define MT_RX_FILTR_CFG_MCAST		BIT(5)
+#define MT_RX_FILTR_CFG_BCAST		BIT(6)
+#define MT_RX_FILTR_CFG_DUP		BIT(7)
+#define MT_RX_FILTR_CFG_CFACK		BIT(8)
+#define MT_RX_FILTR_CFG_CFEND		BIT(9)
+#define MT_RX_FILTR_CFG_ACK		BIT(10)
+#define MT_RX_FILTR_CFG_CTS		BIT(11)
+#define MT_RX_FILTR_CFG_RTS		BIT(12)
+#define MT_RX_FILTR_CFG_PSPOLL		BIT(13)
+#define MT_RX_FILTR_CFG_BA		BIT(14)
+#define MT_RX_FILTR_CFG_BAR		BIT(15)
+#define MT_RX_FILTR_CFG_CTRL_RSV	BIT(16)
+
+#define MT_AUTO_RSP_CFG			0x1404
+
+#define MT_AUTO_RSP_PREAMB_SHORT	BIT(4)
+
+#define MT_LEGACY_BASIC_RATE		0x1408
+#define MT_HT_BASIC_RATE		0x140c
+#define MT_HT_CTRL_CFG			0x1410
+#define MT_RX_PARSER_CFG		0x1418
+#define MT_RX_PARSER_RX_SET_NAV_ALL	BIT(0)
+
+#define MT_EXT_CCA_CFG			0x141c
+#define MT_EXT_CCA_CFG_CCA0		GENMASK(1, 0)
+#define MT_EXT_CCA_CFG_CCA1		GENMASK(3, 2)
+#define MT_EXT_CCA_CFG_CCA2		GENMASK(5, 4)
+#define MT_EXT_CCA_CFG_CCA3		GENMASK(7, 6)
+#define MT_EXT_CCA_CFG_CCA_MASK		GENMASK(11, 8)
+#define MT_EXT_CCA_CFG_ED_CCA_MASK	GENMASK(15, 12)
+
+#define MT_TX_SW_CFG3			0x1478
+
+#define MT_PN_PAD_MODE			0x150c
+
+#define MT_TXOP_HLDR_ET			0x1608
+
+#define MT_PROT_AUTO_TX_CFG		0x1648
+
+#define MT_RX_STA_CNT0			0x1700
+#define MT_RX_STA_CNT1			0x1704
+#define MT_RX_STA_CNT2			0x1708
+#define MT_TX_STA_CNT0			0x170c
+#define MT_TX_STA_CNT1			0x1710
+#define MT_TX_STA_CNT2			0x1714
+
+/* Vendor driver defines content of the second word of STAT_FIFO as follows:
+ *	MT_TX_STAT_FIFO_RATE		GENMASK(26, 16)
+ *	MT_TX_STAT_FIFO_ETXBF		BIT(27)
+ *	MT_TX_STAT_FIFO_SND		BIT(28)
+ *	MT_TX_STAT_FIFO_ITXBF		BIT(29)
+ * However, tests show that b16-31 have the same layout as TXWI rate_ctl
+ * with rate set to rate at which frame was acked.
+ */
+#define MT_TX_STAT_FIFO			0x1718
+#define MT_TX_STAT_FIFO_VALID		BIT(0)
+#define MT_TX_STAT_FIFO_SUCCESS		BIT(5)
+#define MT_TX_STAT_FIFO_AGGR		BIT(6)
+#define MT_TX_STAT_FIFO_ACKREQ		BIT(7)
+#define MT_TX_STAT_FIFO_WCID		GENMASK(15, 8)
+#define MT_TX_STAT_FIFO_RATE		GENMASK(31, 16)
+
+#define MT_TX_AGG_STAT			0x171c
+
+#define MT_TX_AGG_CNT_BASE0		0x1720
+
+#define MT_MPDU_DENSITY_CNT		0x1740
+
+#define MT_TX_AGG_CNT_BASE1		0x174c
+
+#define MT_TX_AGG_CNT(_id)		((_id) < 8 ?			\
+					 MT_TX_AGG_CNT_BASE0 + ((_id) << 2) : \
+					 MT_TX_AGG_CNT_BASE1 + ((_id - 8) << 2))
+
+#define MT_TX_STAT_FIFO_EXT		0x1798
+#define MT_TX_STAT_FIFO_EXT_RETRY	GENMASK(7, 0)
+#define MT_TX_STAT_FIFO_EXT_PKTID	GENMASK(15, 8)
+
+#define MT_BBP_CORE_BASE		0x2000
+#define MT_BBP_IBI_BASE			0x2100
+#define MT_BBP_AGC_BASE			0x2300
+#define MT_BBP_TXC_BASE			0x2400
+#define MT_BBP_RXC_BASE			0x2500
+#define MT_BBP_TXO_BASE			0x2600
+#define MT_BBP_TXBE_BASE		0x2700
+#define MT_BBP_RXFE_BASE		0x2800
+#define MT_BBP_RXO_BASE			0x2900
+#define MT_BBP_DFS_BASE			0x2a00
+#define MT_BBP_TR_BASE			0x2b00
+#define MT_BBP_CAL_BASE			0x2c00
+#define MT_BBP_DSC_BASE			0x2e00
+#define MT_BBP_PFMU_BASE		0x2f00
+
+#define MT_BBP(_type, _n)		(MT_BBP_##_type##_BASE + ((_n) << 2))
+
+#define MT_BBP_CORE_R1_BW		GENMASK(4, 3)
+
+#define MT_BBP_AGC_R0_CTRL_CHAN		GENMASK(9, 8)
+#define MT_BBP_AGC_R0_BW		GENMASK(14, 12)
+
+/* AGC, R4/R5 */
+#define MT_BBP_AGC_LNA_GAIN		GENMASK(21, 16)
+
+/* AGC, R8/R9 */
+#define MT_BBP_AGC_GAIN			GENMASK(14, 8)
+
+#define MT_BBP_AGC20_RSSI0		GENMASK(7, 0)
+#define MT_BBP_AGC20_RSSI1		GENMASK(15, 8)
+
+#define MT_BBP_TXBE_R0_CTRL_CHAN	GENMASK(1, 0)
+
+#define MT_WCID_ADDR_BASE		0x1800
+#define MT_WCID_ADDR(_n)		(MT_WCID_ADDR_BASE + (_n) * 8)
+
+#define MT_SRAM_BASE			0x4000
+
+#define MT_WCID_KEY_BASE		0x8000
+#define MT_WCID_KEY(_n)			(MT_WCID_KEY_BASE + (_n) * 32)
+
+#define MT_WCID_IV_BASE			0xa000
+#define MT_WCID_IV(_n)			(MT_WCID_IV_BASE + (_n) * 8)
+
+#define MT_WCID_ATTR_BASE		0xa800
+#define MT_WCID_ATTR(_n)		(MT_WCID_ATTR_BASE + (_n) * 4)
+
+#define MT_WCID_ATTR_PAIRWISE		BIT(0)
+#define MT_WCID_ATTR_PKEY_MODE		GENMASK(3, 1)
+#define MT_WCID_ATTR_BSS_IDX		GENMASK(6, 4)
+#define MT_WCID_ATTR_RXWI_UDF		GENMASK(9, 7)
+#define MT_WCID_ATTR_PKEY_MODE_EXT	BIT(10)
+#define MT_WCID_ATTR_BSS_IDX_EXT	BIT(11)
+#define MT_WCID_ATTR_WAPI_MCBC		BIT(15)
+#define MT_WCID_ATTR_WAPI_KEYID		GENMASK(31, 24)
+
+#define MT_SKEY_BASE_0			0xac00
+#define MT_SKEY_BASE_1			0xb400
+#define MT_SKEY_0(_bss, _idx)		\
+	(MT_SKEY_BASE_0 + (4 * (_bss) + _idx) * 32)
+#define MT_SKEY_1(_bss, _idx)		\
+	(MT_SKEY_BASE_1 + (4 * ((_bss) & 7) + _idx) * 32)
+#define MT_SKEY(_bss, _idx)		\
+	((_bss & 8) ? MT_SKEY_1(_bss, _idx) : MT_SKEY_0(_bss, _idx))
+
+#define MT_SKEY_MODE_BASE_0		0xb000
+#define MT_SKEY_MODE_BASE_1		0xb3f0
+#define MT_SKEY_MODE_0(_bss)		\
+	(MT_SKEY_MODE_BASE_0 + ((_bss / 2) << 2))
+#define MT_SKEY_MODE_1(_bss)		\
+	(MT_SKEY_MODE_BASE_1 + ((((_bss) & 7) / 2) << 2))
+#define MT_SKEY_MODE(_bss)		\
+	((_bss & 8) ? MT_SKEY_MODE_1(_bss) : MT_SKEY_MODE_0(_bss))
+#define MT_SKEY_MODE_MASK		GENMASK(3, 0)
+#define MT_SKEY_MODE_SHIFT(_bss, _idx)	(4 * ((_idx) + 4 * (_bss & 1)))
+
+#define MT_BEACON_BASE			0xc000
+
+#define MT_TEMP_SENSOR			0x1d000
+#define MT_TEMP_SENSOR_VAL		GENMASK(6, 0)
+
+enum mt76_cipher_type {
+	MT_CIPHER_NONE,
+	MT_CIPHER_WEP40,
+	MT_CIPHER_WEP104,
+	MT_CIPHER_TKIP,
+	MT_CIPHER_AES_CCMP,
+	MT_CIPHER_CKIP40,
+	MT_CIPHER_CKIP104,
+	MT_CIPHER_CKIP128,
+	MT_CIPHER_WAPI,
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/util.c b/drivers/net/wireless/mediatek/mt76/mt76x0/util.c
new file mode 100644
index 000000000000..148be47d822f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/util.c
@@ -0,0 +1,42 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+
+void mt76_remove_hdr_pad(struct sk_buff *skb)
+{
+	int len = ieee80211_get_hdrlen_from_skb(skb);
+
+	memmove(skb->data + 2, skb->data, len);
+	skb_pull(skb, 2);
+}
+
+int mt76_insert_hdr_pad(struct sk_buff *skb)
+{
+	int len = ieee80211_get_hdrlen_from_skb(skb);
+	int ret;
+
+	if (len % 4 == 0)
+		return 0;
+
+	ret = skb_cow(skb, 2);
+	if (ret)
+		return ret;
+
+	skb_push(skb, 2);
+	memmove(skb->data, skb->data + 2, len);
+
+	skb->data[len] = 0;
+	skb->data[len + 1] = 0;
+	return 0;
+}
-- 
cgit v1.2.3


From a774434981372fc583dfdf39a4094b3f0e3c4677 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:52 +0200
Subject: mt76x0: mac files

Add mac files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c | 660 ++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.h | 154 ++++++
 2 files changed, 814 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/mac.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
new file mode 100644
index 000000000000..7b32777c06e9
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -0,0 +1,660 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "trace.h"
+#include <linux/etherdevice.h>
+
+static void
+mt76_mac_process_tx_rate(struct ieee80211_tx_rate *txrate, u16 rate,
+			 enum nl80211_band band)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	txrate->idx = 0;
+	txrate->flags = 0;
+	txrate->count = 1;
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		txrate->idx = idx;
+		return;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8)
+			idx -= 8;
+
+		txrate->idx = idx;
+		return;
+	case MT_PHY_TYPE_HT_GF:
+		txrate->flags |= IEEE80211_TX_RC_GREEN_FIELD;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		txrate->flags |= IEEE80211_TX_RC_MCS;
+		txrate->idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		txrate->flags |= IEEE80211_TX_RC_VHT_MCS;
+		txrate->idx = idx;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		txrate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
+		break;
+	case MT_PHY_BW_80:
+		txrate->flags |= IEEE80211_TX_RC_80_MHZ_WIDTH;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	if (rate & MT_RXWI_RATE_SGI)
+		txrate->flags |= IEEE80211_TX_RC_SHORT_GI;
+}
+
+static void
+mt76_mac_fill_tx_status(struct mt76x0_dev *dev, struct ieee80211_tx_info *info,
+			struct mt76_tx_status *st, int n_frames)
+{
+	struct ieee80211_tx_rate *rate = info->status.rates;
+	int cur_idx, last_rate;
+	int i;
+
+	if (!n_frames)
+		return;
+
+	last_rate = min_t(int, st->retry, IEEE80211_TX_MAX_RATES - 1);
+	mt76_mac_process_tx_rate(&rate[last_rate], st->rate,
+				 dev->mt76.chandef.chan->band);
+	if (last_rate < IEEE80211_TX_MAX_RATES - 1)
+		rate[last_rate + 1].idx = -1;
+
+	cur_idx = rate[last_rate].idx + last_rate;
+	for (i = 0; i <= last_rate; i++) {
+		rate[i].flags = rate[last_rate].flags;
+		rate[i].idx = max_t(int, 0, cur_idx - i);
+		rate[i].count = 1;
+	}
+
+	rate[last_rate - 1].count = st->retry + 1 - last_rate;
+
+	info->status.ampdu_len = n_frames;
+	info->status.ampdu_ack_len = st->success ? n_frames : 0;
+
+	if (st->pktid & MT_TXWI_PKTID_PROBE)
+		info->flags |= IEEE80211_TX_CTL_RATE_CTRL_PROBE;
+
+	if (st->aggr)
+		info->flags |= IEEE80211_TX_CTL_AMPDU |
+			       IEEE80211_TX_STAT_AMPDU;
+
+	if (!st->ack_req)
+		info->flags |= IEEE80211_TX_CTL_NO_ACK;
+	else if (st->success)
+		info->flags |= IEEE80211_TX_STAT_ACK;
+}
+
+u16 mt76_mac_tx_rate_val(struct mt76x0_dev *dev,
+			 const struct ieee80211_tx_rate *rate, u8 *nss_val)
+{
+	u16 rateval;
+	u8 phy, rate_idx;
+	u8 nss = 1;
+	u8 bw = 0;
+
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 4);
+		phy = MT_PHY_TYPE_VHT;
+		if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+			bw = 2;
+		else if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		rate_idx = rate->idx;
+		nss = 1 + (rate->idx >> 3);
+		phy = MT_PHY_TYPE_HT;
+		if (rate->flags & IEEE80211_TX_RC_GREEN_FIELD)
+			phy = MT_PHY_TYPE_HT_GF;
+		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			bw = 1;
+	} else {
+		const struct ieee80211_rate *r;
+		int band = dev->mt76.chandef.chan->band;
+		u16 val;
+
+		r = &dev->mt76.hw->wiphy->bands[band]->bitrates[rate->idx];
+		if (rate->flags & IEEE80211_TX_RC_USE_SHORT_PREAMBLE)
+			val = r->hw_value_short;
+		else
+			val = r->hw_value;
+
+		phy = val >> 8;
+		rate_idx = val & 0xff;
+		bw = 0;
+	}
+
+	rateval = FIELD_PREP(MT_RXWI_RATE_INDEX, rate_idx);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_PHY, phy);
+	rateval |= FIELD_PREP(MT_RXWI_RATE_BW, bw);
+	if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+		rateval |= MT_RXWI_RATE_SGI;
+
+	*nss_val = nss;
+	return cpu_to_le16(rateval);
+}
+
+void mt76_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
+			    const struct ieee80211_tx_rate *rate)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->mt76.lock, flags);
+	wcid->tx_rate = mt76_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
+	wcid->tx_rate_set = true;
+	spin_unlock_irqrestore(&dev->mt76.lock, flags);
+}
+
+struct mt76_tx_status mt76x0_mac_fetch_tx_status(struct mt76x0_dev *dev)
+{
+	struct mt76_tx_status stat = {};
+	u32 stat2, stat1;
+
+	stat2 = mt76_rr(dev, MT_TX_STAT_FIFO_EXT);
+	stat1 = mt76_rr(dev, MT_TX_STAT_FIFO);
+
+	stat.valid = !!(stat1 & MT_TX_STAT_FIFO_VALID);
+	stat.success = !!(stat1 & MT_TX_STAT_FIFO_SUCCESS);
+	stat.aggr = !!(stat1 & MT_TX_STAT_FIFO_AGGR);
+	stat.ack_req = !!(stat1 & MT_TX_STAT_FIFO_ACKREQ);
+	stat.wcid = FIELD_GET(MT_TX_STAT_FIFO_WCID, stat1);
+	stat.rate = FIELD_GET(MT_TX_STAT_FIFO_RATE, stat1);
+
+	stat.retry = FIELD_GET(MT_TX_STAT_FIFO_EXT_RETRY, stat2);
+	stat.pktid = FIELD_GET(MT_TX_STAT_FIFO_EXT_PKTID, stat2);
+
+	return stat;
+}
+
+void mt76_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update)
+{
+	struct ieee80211_tx_info info = {};
+	struct ieee80211_sta *sta = NULL;
+	struct mt76_wcid *wcid = NULL;
+	struct mt76_sta *msta = NULL;
+
+	rcu_read_lock();
+	if (stat->wcid < ARRAY_SIZE(dev->wcid))
+		wcid = rcu_dereference(dev->wcid[stat->wcid]);
+
+	if (wcid) {
+		void *priv;
+		priv = msta = container_of(wcid, struct mt76_sta, wcid);
+		sta = container_of(priv, struct ieee80211_sta, drv_priv);
+	}
+
+	if (msta && stat->aggr) {
+		u32 stat_val, stat_cache;
+
+		stat_val = stat->rate;
+		stat_val |= ((u32) stat->retry) << 16;
+		stat_cache = msta->status.rate;
+		stat_cache |= ((u32) msta->status.retry) << 16;
+
+		if (*update == 0 && stat_val == stat_cache &&
+		    stat->wcid == msta->status.wcid && msta->n_frames < 32) {
+			msta->n_frames++;
+			goto out;
+		}
+
+		mt76_mac_fill_tx_status(dev, &info, &msta->status,
+					msta->n_frames);
+		msta->status = *stat;
+		msta->n_frames = 1;
+		*update = 0;
+	} else {
+		mt76_mac_fill_tx_status(dev, &info, stat, 1);
+		*update = 1;
+	}
+
+	spin_lock_bh(&dev->mac_lock);
+	ieee80211_tx_status_noskb(dev->mt76.hw, sta, &info);
+	spin_unlock_bh(&dev->mac_lock);
+out:
+	rcu_read_unlock();
+}
+
+void mt76x0_mac_set_protection(struct mt76x0_dev *dev, bool legacy_prot,
+				int ht_mode)
+{
+	int mode = ht_mode & IEEE80211_HT_OP_MODE_PROTECTION;
+	bool non_gf = !!(ht_mode & IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT);
+	u32 prot[6];
+	bool ht_rts[4] = {};
+	int i;
+
+	prot[0] = MT_PROT_NAV_SHORT |
+		  MT_PROT_TXOP_ALLOW_ALL |
+		  MT_PROT_RTS_THR_EN;
+	prot[1] = prot[0];
+	if (legacy_prot)
+		prot[1] |= MT_PROT_CTRL_CTS2SELF;
+
+	prot[2] = prot[4] = MT_PROT_NAV_SHORT | MT_PROT_TXOP_ALLOW_BW20;
+	prot[3] = prot[5] = MT_PROT_NAV_SHORT | MT_PROT_TXOP_ALLOW_ALL;
+
+	if (legacy_prot) {
+		prot[2] |= MT_PROT_RATE_CCK_11;
+		prot[3] |= MT_PROT_RATE_CCK_11;
+		prot[4] |= MT_PROT_RATE_CCK_11;
+		prot[5] |= MT_PROT_RATE_CCK_11;
+	} else {
+		prot[2] |= MT_PROT_RATE_OFDM_24;
+		prot[3] |= MT_PROT_RATE_DUP_OFDM_24;
+		prot[4] |= MT_PROT_RATE_OFDM_24;
+		prot[5] |= MT_PROT_RATE_DUP_OFDM_24;
+	}
+
+	switch (mode) {
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
+		break;
+
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
+		ht_rts[0] = ht_rts[1] = ht_rts[2] = ht_rts[3] = true;
+		break;
+
+	case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
+		ht_rts[1] = ht_rts[3] = true;
+		break;
+
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
+		ht_rts[0] = ht_rts[1] = ht_rts[2] = ht_rts[3] = true;
+		break;
+	}
+
+	if (non_gf)
+		ht_rts[2] = ht_rts[3] = true;
+
+	for (i = 0; i < 4; i++)
+		if (ht_rts[i])
+			prot[i + 2] |= MT_PROT_CTRL_RTS_CTS;
+
+	for (i = 0; i < 6; i++)
+		mt76_wr(dev, MT_CCK_PROT_CFG + i * 4, prot[i]);
+}
+
+void mt76x0_mac_set_short_preamble(struct mt76x0_dev *dev, bool short_preamb)
+{
+	if (short_preamb)
+		mt76_set(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
+	else
+		mt76_clear(dev, MT_AUTO_RSP_CFG, MT_AUTO_RSP_PREAMB_SHORT);
+}
+
+void mt76x0_mac_config_tsf(struct mt76x0_dev *dev, bool enable, int interval)
+{
+	u32 val = mt76_rr(dev, MT_BEACON_TIME_CFG);
+
+	val &= ~(MT_BEACON_TIME_CFG_TIMER_EN |
+		 MT_BEACON_TIME_CFG_SYNC_MODE |
+		 MT_BEACON_TIME_CFG_TBTT_EN);
+
+	if (!enable) {
+		mt76_wr(dev, MT_BEACON_TIME_CFG, val);
+		return;
+	}
+
+	val &= ~MT_BEACON_TIME_CFG_INTVAL;
+	val |= FIELD_PREP(MT_BEACON_TIME_CFG_INTVAL, interval << 4) |
+		MT_BEACON_TIME_CFG_TIMER_EN |
+		MT_BEACON_TIME_CFG_SYNC_MODE |
+		MT_BEACON_TIME_CFG_TBTT_EN;
+}
+
+static void mt76x0_check_mac_err(struct mt76x0_dev *dev)
+{
+	u32 val = mt76_rr(dev, 0x10f4);
+
+	if (!(val & BIT(29)) || !(val & (BIT(7) | BIT(5))))
+		return;
+
+	dev_err(dev->mt76.dev, "Error: MAC specific condition occurred\n");
+
+	mt76_set(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR);
+	udelay(10);
+	mt76_clear(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR);
+}
+void mt76x0_mac_work(struct work_struct *work)
+{
+	struct mt76x0_dev *dev = container_of(work, struct mt76x0_dev,
+					       mac_work.work);
+	struct {
+		u32 addr_base;
+		u32 span;
+		u64 *stat_base;
+	} spans[] = {
+		{ MT_RX_STA_CNT0,	3,	dev->stats.rx_stat },
+		{ MT_TX_STA_CNT0,	3,	dev->stats.tx_stat },
+		{ MT_TX_AGG_STAT,	1,	dev->stats.aggr_stat },
+		{ MT_MPDU_DENSITY_CNT,	1,	dev->stats.zero_len_del },
+		{ MT_TX_AGG_CNT_BASE0,	8,	&dev->stats.aggr_n[0] },
+		{ MT_TX_AGG_CNT_BASE1,	8,	&dev->stats.aggr_n[16] },
+	};
+	u32 sum, n;
+	int i, j, k;
+
+	/* Note: using MCU_RANDOM_READ is actually slower then reading all the
+	 *	 registers by hand.  MCU takes ca. 20ms to complete read of 24
+	 *	 registers while reading them one by one will takes roughly
+	 *	 24*200us =~ 5ms.
+	 */
+
+	k = 0;
+	n = 0;
+	sum = 0;
+	for (i = 0; i < ARRAY_SIZE(spans); i++)
+		for (j = 0; j < spans[i].span; j++) {
+			u32 val = mt76_rr(dev, spans[i].addr_base + j * 4);
+
+			spans[i].stat_base[j * 2] += val & 0xffff;
+			spans[i].stat_base[j * 2 + 1] += val >> 16;
+
+			/* Calculate average AMPDU length */
+			if (spans[i].addr_base != MT_TX_AGG_CNT_BASE0 &&
+			    spans[i].addr_base != MT_TX_AGG_CNT_BASE1)
+				continue;
+
+			n += (val >> 16) + (val & 0xffff);
+			sum += (val & 0xffff) * (1 + k * 2) +
+				(val >> 16) * (2 + k * 2);
+			k++;
+		}
+
+	atomic_set(&dev->avg_ampdu_len, n ? DIV_ROUND_CLOSEST(sum, n) : 1);
+
+	mt76x0_check_mac_err(dev);
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->mac_work, 10 * HZ);
+}
+
+void
+mt76x0_mac_wcid_setup(struct mt76x0_dev *dev, u8 idx, u8 vif_idx, u8 *mac)
+{
+	u8 zmac[ETH_ALEN] = {};
+	u32 attr;
+
+	attr = FIELD_PREP(MT_WCID_ATTR_BSS_IDX, vif_idx & 7) |
+	       FIELD_PREP(MT_WCID_ATTR_BSS_IDX_EXT, !!(vif_idx & 8));
+
+	mt76_wr(dev, MT_WCID_ATTR(idx), attr);
+
+	if (mac)
+		memcpy(zmac, mac, sizeof(zmac));
+
+	mt76x0_addr_wr(dev, MT_WCID_ADDR(idx), zmac);
+}
+
+void mt76x0_mac_set_ampdu_factor(struct mt76x0_dev *dev)
+{
+	struct ieee80211_sta *sta;
+	struct mt76_wcid *wcid;
+	void *msta;
+	u8 min_factor = 3;
+	int i;
+
+	return;
+
+	rcu_read_lock();
+	for (i = 0; i < ARRAY_SIZE(dev->wcid); i++) {
+		wcid = rcu_dereference(dev->wcid[i]);
+		if (!wcid)
+			continue;
+
+		msta = container_of(wcid, struct mt76_sta, wcid);
+		sta = container_of(msta, struct ieee80211_sta, drv_priv);
+
+		min_factor = min(min_factor, sta->ht_cap.ampdu_factor);
+	}
+	rcu_read_unlock();
+
+	mt76_wr(dev, MT_MAX_LEN_CFG, 0xa0fff |
+		   FIELD_PREP(MT_MAX_LEN_CFG_AMPDU, min_factor));
+}
+
+static void
+mt76_mac_process_rate(struct ieee80211_rx_status *status, u16 rate)
+{
+	u8 idx = FIELD_GET(MT_RXWI_RATE_INDEX, rate);
+
+	switch (FIELD_GET(MT_RXWI_RATE_PHY, rate)) {
+	case MT_PHY_TYPE_OFDM:
+		if (idx >= 8)
+			idx = 0;
+
+		if (status->band == NL80211_BAND_2GHZ)
+			idx += 4;
+
+		status->rate_idx = idx;
+		return;
+	case MT_PHY_TYPE_CCK:
+		if (idx >= 8) {
+			idx -= 8;
+			status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
+		}
+
+		if (idx >= 4)
+			idx = 0;
+
+		status->rate_idx = idx;
+		return;
+	case MT_PHY_TYPE_HT_GF:
+		status->enc_flags |= RX_ENC_FLAG_HT_GF;
+		/* fall through */
+	case MT_PHY_TYPE_HT:
+		status->encoding = RX_ENC_HT;
+		status->rate_idx = idx;
+		break;
+	case MT_PHY_TYPE_VHT:
+		status->encoding = RX_ENC_VHT;
+		status->rate_idx = FIELD_GET(MT_RATE_INDEX_VHT_IDX, idx);
+		status->nss = FIELD_GET(MT_RATE_INDEX_VHT_NSS, idx) + 1;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	if (rate & MT_RXWI_RATE_LDPC)
+		status->enc_flags |= RX_ENC_FLAG_LDPC;
+
+	if (rate & MT_RXWI_RATE_SGI)
+		status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+	if (rate & MT_RXWI_RATE_STBC)
+		status->enc_flags |= 1 << RX_ENC_FLAG_STBC_SHIFT;
+
+	switch (FIELD_GET(MT_RXWI_RATE_BW, rate)) {
+	case MT_PHY_BW_20:
+		break;
+	case MT_PHY_BW_40:
+		status->bw = RATE_INFO_BW_40;
+		break;
+	case MT_PHY_BW_80:
+		status->bw = RATE_INFO_BW_80;
+		break;
+	default:
+		WARN_ON(1);
+		break;
+	}
+}
+
+static void
+mt76x0_rx_monitor_beacon(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi,
+			  u16 rate, int rssi)
+{
+	dev->bcn_phy_mode = FIELD_GET(MT_RXWI_RATE_PHY, rate);
+	dev->avg_rssi = ((dev->avg_rssi * 15) / 16 + (rssi << 8)) / 256;
+}
+
+static int
+mt76x0_rx_is_our_beacon(struct mt76x0_dev *dev, u8 *data)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)data;
+
+	return ieee80211_is_beacon(hdr->frame_control) &&
+		ether_addr_equal(hdr->addr2, dev->ap_bssid);
+}
+
+u32 mt76_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			u8 *data, void *rxi)
+{
+	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
+	struct mt76x0_rxwi *rxwi = rxi;
+	u32 len, ctl = le32_to_cpu(rxwi->ctl);
+	u16 rate = le16_to_cpu(rxwi->rate);
+	int rssi;
+
+	len = FIELD_GET(MT_RXWI_CTL_MPDU_LEN, ctl);
+	if (WARN_ON(len < 10))
+		return 0;
+
+	if (rxwi->rxinfo & cpu_to_le32(MT_RXINFO_DECRYPT)) {
+		status->flag |= RX_FLAG_DECRYPTED;
+		status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED;
+	}
+
+	status->chains = BIT(0);
+	rssi = mt76x0_phy_get_rssi(dev, rxwi);
+	status->chain_signal[0] = status->signal = rssi;
+	status->freq = dev->mt76.chandef.chan->center_freq;
+	status->band = dev->mt76.chandef.chan->band;
+
+	mt76_mac_process_rate(status, rate);
+
+	spin_lock_bh(&dev->con_mon_lock);
+	if (mt76x0_rx_is_our_beacon(dev, data)) {
+		mt76x0_rx_monitor_beacon(dev, rxwi, rate, rssi);
+	} else if (rxwi->rxinfo & cpu_to_le32(MT_RXINFO_U2M)) {
+		if (dev->avg_rssi == 0)
+			dev->avg_rssi = rssi;
+		else
+			dev->avg_rssi = (dev->avg_rssi * 15) / 16 + rssi / 16;
+
+	}
+	spin_unlock_bh(&dev->con_mon_lock);
+
+	return len;
+}
+
+static enum mt76_cipher_type
+mt76_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
+{
+	memset(key_data, 0, 32);
+	if (!key)
+		return MT_CIPHER_NONE;
+
+	if (key->keylen > 32)
+		return MT_CIPHER_NONE;
+
+	memcpy(key_data, key->key, key->keylen);
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+		return MT_CIPHER_WEP40;
+	case WLAN_CIPHER_SUITE_WEP104:
+		return MT_CIPHER_WEP104;
+	case WLAN_CIPHER_SUITE_TKIP:
+		return MT_CIPHER_TKIP;
+	case WLAN_CIPHER_SUITE_CCMP:
+		return MT_CIPHER_AES_CCMP;
+	default:
+		return MT_CIPHER_NONE;
+	}
+}
+
+int mt76_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
+			  struct ieee80211_key_conf *key)
+{
+	enum mt76_cipher_type cipher;
+	u8 key_data[32];
+	u8 iv_data[8];
+	u32 val;
+
+	cipher = mt76_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EINVAL;
+
+	trace_set_key(&dev->mt76, idx);
+
+	mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data));
+
+	memset(iv_data, 0, sizeof(iv_data));
+	if (key) {
+		iv_data[3] = key->keyidx << 6;
+		if (cipher >= MT_CIPHER_TKIP) {
+			/* Note: start with 1 to comply with spec,
+			 *	 (see comment on common/cmm_wpa.c:4291).
+			 */
+			iv_data[0] |= 1;
+			iv_data[3] |= 0x20;
+		}
+	}
+	mt76_wr_copy(dev, MT_WCID_IV(idx), iv_data, sizeof(iv_data));
+
+	val = mt76_rr(dev, MT_WCID_ATTR(idx));
+	val &= ~MT_WCID_ATTR_PKEY_MODE & ~MT_WCID_ATTR_PKEY_MODE_EXT;
+	val |= FIELD_PREP(MT_WCID_ATTR_PKEY_MODE, cipher & 7) |
+	       FIELD_PREP(MT_WCID_ATTR_PKEY_MODE_EXT, cipher >> 3);
+	val &= ~MT_WCID_ATTR_PAIRWISE;
+	val |= MT_WCID_ATTR_PAIRWISE *
+		!!(key && key->flags & IEEE80211_KEY_FLAG_PAIRWISE);
+	mt76_wr(dev, MT_WCID_ATTR(idx), val);
+
+	return 0;
+}
+
+int mt76_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
+			      struct ieee80211_key_conf *key)
+{
+	enum mt76_cipher_type cipher;
+	u8 key_data[32];
+	u32 val;
+
+	cipher = mt76_mac_get_key_info(key, key_data);
+	if (cipher == MT_CIPHER_NONE && key)
+		return -EINVAL;
+
+	trace_set_shared_key(&dev->mt76, vif_idx, key_idx);
+
+	mt76_wr_copy(dev, MT_SKEY(vif_idx, key_idx),
+			key_data, sizeof(key_data));
+
+	val = mt76_rr(dev, MT_SKEY_MODE(vif_idx));
+	val &= ~(MT_SKEY_MODE_MASK << MT_SKEY_MODE_SHIFT(vif_idx, key_idx));
+	val |= cipher << MT_SKEY_MODE_SHIFT(vif_idx, key_idx);
+	mt76_wr(dev, MT_SKEY_MODE(vif_idx), val);
+
+	return 0;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h
new file mode 100644
index 000000000000..947eba253553
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h
@@ -0,0 +1,154 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76_MAC_H
+#define __MT76_MAC_H
+
+/* Note: values in original "RSSI" and "SNR" fields are not actually what they
+ *	 are called for MT76X0U, names used by this driver are educated guesses
+ *	 (see vendor mac/ral_omac.c).
+ */
+struct mt76x0_rxwi {
+	__le32 rxinfo;
+
+	__le32 ctl;
+
+	__le16 tid_sn;
+	__le16 rate;
+
+	s8 rssi[4];
+
+	__le32 bbp_rxinfo[4];
+} __packed __aligned(4);
+
+#define MT_RXINFO_BA			BIT(0)
+#define MT_RXINFO_DATA			BIT(1)
+#define MT_RXINFO_NULL			BIT(2)
+#define MT_RXINFO_FRAG			BIT(3)
+#define MT_RXINFO_U2M			BIT(4)
+#define MT_RXINFO_MULTICAST		BIT(5)
+#define MT_RXINFO_BROADCAST		BIT(6)
+#define MT_RXINFO_MYBSS			BIT(7)
+#define MT_RXINFO_CRCERR		BIT(8)
+#define MT_RXINFO_ICVERR		BIT(9)
+#define MT_RXINFO_MICERR		BIT(10)
+#define MT_RXINFO_AMSDU			BIT(11)
+#define MT_RXINFO_HTC			BIT(12)
+#define MT_RXINFO_RSSI			BIT(13)
+#define MT_RXINFO_L2PAD			BIT(14)
+#define MT_RXINFO_AMPDU			BIT(15)
+#define MT_RXINFO_DECRYPT		BIT(16)
+#define MT_RXINFO_BSSIDX3		BIT(17)
+#define MT_RXINFO_WAPI_KEY		BIT(18)
+#define MT_RXINFO_PN_LEN		GENMASK(21, 19)
+#define MT_RXINFO_SW_PKT_80211		BIT(22)
+#define MT_RXINFO_TCP_SUM_BYPASS	BIT(28)
+#define MT_RXINFO_IP_SUM_BYPASS		BIT(29)
+#define MT_RXINFO_TCP_SUM_ERR		BIT(30)
+#define MT_RXINFO_IP_SUM_ERR		BIT(31)
+
+#define MT_RXWI_CTL_WCID		GENMASK(7, 0)
+#define MT_RXWI_CTL_KEY_IDX		GENMASK(9, 8)
+#define MT_RXWI_CTL_BSS_IDX		GENMASK(12, 10)
+#define MT_RXWI_CTL_UDF			GENMASK(15, 13)
+#define MT_RXWI_CTL_MPDU_LEN		GENMASK(27, 16)
+#define MT_RXWI_CTL_TID			GENMASK(31, 28)
+
+#define MT_RXWI_FRAG			GENMASK(3, 0)
+#define MT_RXWI_SN			GENMASK(15, 4)
+
+#define MT_RXWI_RATE_INDEX		GENMASK(5, 0)
+#define MT_RXWI_RATE_LDPC		BIT(6)
+#define MT_RXWI_RATE_BW			GENMASK(8, 7)
+#define MT_RXWI_RATE_SGI		BIT(9)
+#define MT_RXWI_RATE_STBC		BIT(10)
+#define MT_RXWI_RATE_LDPC_ETXBF		BIT(11)
+#define MT_RXWI_RATE_SND		BIT(12)
+#define MT_RXWI_RATE_PHY		GENMASK(15, 13)
+
+#define MT_RATE_INDEX_VHT_IDX		GENMASK(3, 0)
+#define MT_RATE_INDEX_VHT_NSS		GENMASK(5, 4)
+
+#define MT_RXWI_GAIN_RSSI_VAL		GENMASK(5, 0)
+#define MT_RXWI_GAIN_RSSI_LNA_ID	GENMASK(7, 6)
+#define MT_RXWI_ANT_AUX_LNA		BIT(7)
+
+#define MT_RXWI_EANT_ENC_ANT_ID		GENMASK(7, 0)
+
+enum mt76_phy_bandwidth {
+	MT_PHY_BW_20,
+	MT_PHY_BW_40,
+	MT_PHY_BW_80,
+};
+
+struct mt76_txwi {
+	__le16 flags;
+	__le16 rate_ctl;
+	u8 ack_ctl;
+	u8 wcid;
+	__le16 len_ctl;
+	__le32 iv;
+	__le32 eiv;
+	u8 aid;
+	u8 txstream;
+	u8 ctl2;
+	u8 pktid;
+} __packed __aligned(4);
+
+#define MT_TXWI_FLAGS_FRAG		BIT(0)
+#define MT_TXWI_FLAGS_MMPS		BIT(1)
+#define MT_TXWI_FLAGS_CFACK		BIT(2)
+#define MT_TXWI_FLAGS_TS		BIT(3)
+#define MT_TXWI_FLAGS_AMPDU		BIT(4)
+#define MT_TXWI_FLAGS_MPDU_DENSITY	GENMASK(7, 5)
+#define MT_TXWI_FLAGS_TXOP		GENMASK(9, 8)
+#define MT_TXWI_FLAGS_CWMIN		GENMASK(12, 10)
+#define MT_TXWI_FLAGS_NO_RATE_FALLBACK	BIT(13)
+#define MT_TXWI_FLAGS_TX_RPT		BIT(14)
+#define MT_TXWI_FLAGS_TX_RATE_LUT	BIT(15)
+
+#define MT_TXWI_RATE_MCS		GENMASK(6, 0)
+#define MT_TXWI_RATE_BW			BIT(7)
+#define MT_TXWI_RATE_SGI		BIT(8)
+#define MT_TXWI_RATE_STBC		GENMASK(10, 9)
+#define MT_TXWI_RATE_PHY_MODE		GENMASK(15, 14)
+
+#define MT_TXWI_ACK_CTL_REQ		BIT(0)
+#define MT_TXWI_ACK_CTL_NSEQ		BIT(1)
+#define MT_TXWI_ACK_CTL_BA_WINDOW	GENMASK(7, 2)
+
+#define MT_TXWI_LEN_BYTE_CNT		GENMASK(11, 0)
+
+#define MT_TXWI_CTL_TX_POWER_ADJ	GENMASK(3, 0)
+#define MT_TXWI_CTL_CHAN_CHECK_PKT	BIT(4)
+#define MT_TXWI_CTL_PIFS_REV		BIT(6)
+
+#define MT_TXWI_PKTID_PROBE             BIT(7)
+
+u32 mt76_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			u8 *data, void *rxi);
+int mt76_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
+			  struct ieee80211_key_conf *key);
+void mt76_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
+			    const struct ieee80211_tx_rate *rate);
+
+int mt76_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
+			      struct ieee80211_key_conf *key);
+u16 mt76_mac_tx_rate_val(struct mt76x0_dev *dev,
+			 const struct ieee80211_tx_rate *rate, u8 *nss_val);
+struct mt76_tx_status
+mt76x0_mac_fetch_tx_status(struct mt76x0_dev *dev);
+void mt76_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update);
+
+#endif
-- 
cgit v1.2.3


From ff69c75ee5392320ab3a8dd01db46d3cd097eb46 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:53 +0200
Subject: mt76x0: usb files

Add usb files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c | 377 ++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.h |  61 ++++
 2 files changed, 438 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/usb.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
new file mode 100644
index 000000000000..0871fdef59c3
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -0,0 +1,377 @@
+/*
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/usb.h>
+
+#include "mt76x0.h"
+#include "usb.h"
+#include "trace.h"
+
+static struct usb_device_id mt76x0_device_table[] = {
+	{ USB_DEVICE(0x148F, 0x7610) },	/* MT7610U */
+	{ USB_DEVICE(0x13B1, 0x003E) },	/* Linksys AE6000 */
+	{ USB_DEVICE(0x0E8D, 0x7610) },	/* Sabrent NTWLAC */
+	{ USB_DEVICE(0x7392, 0xa711) },	/* Edimax 7711mac */
+	{ USB_DEVICE(0x7392, 0xb711) },	/* Edimax / Elecom  */
+	{ USB_DEVICE(0x148f, 0x761a) },	/* TP-Link TL-WDN5200 */
+	{ USB_DEVICE(0x148f, 0x760a) },	/* TP-Link unknown */
+	{ USB_DEVICE(0x0b05, 0x17d1) },	/* Asus USB-AC51 */
+	{ USB_DEVICE(0x0b05, 0x17db) },	/* Asus USB-AC50 */
+	{ USB_DEVICE(0x0df6, 0x0075) },	/* Sitecom WLA-3100 */
+	{ USB_DEVICE(0x2019, 0xab31) },	/* Planex GW-450D */
+	{ USB_DEVICE(0x2001, 0x3d02) },	/* D-LINK DWA-171 rev B1 */
+	{ USB_DEVICE(0x0586, 0x3425) },	/* Zyxel NWD6505 */
+	{ USB_DEVICE(0x07b8, 0x7610) },	/* AboCom AU7212 */
+	{ USB_DEVICE(0x04bb, 0x0951) },	/* I-O DATA WN-AC433UK */
+	{ USB_DEVICE(0x057c, 0x8502) },	/* AVM FRITZ!WLAN USB Stick AC 430 */
+	{ USB_DEVICE(0x293c, 0x5702) },	/* Comcast Xfinity KXW02AAA  */
+	{ USB_DEVICE(0x20f4, 0x806b) },	/* TRENDnet TEW-806UBH  */
+	{ USB_DEVICE(0x7392, 0xc711) }, /* Devolo Wifi ac Stick */
+	{ USB_DEVICE(0x0df6, 0x0079) }, /* Sitecom Europe B.V. ac  Stick */
+	{ USB_DEVICE(0x2357, 0x0105) }, /* TP-LINK Archer T1U */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0E8D, 0x7630, 0xff, 0x2, 0xff)}, /* MT7630U */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0E8D, 0x7650, 0xff, 0x2, 0xff)}, /* MT7650U */
+	{ 0, }
+};
+
+bool mt76x0_usb_alloc_buf(struct mt76x0_dev *dev, size_t len,
+			   struct mt76x0_dma_buf *buf)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+
+	buf->len = len;
+	buf->urb = usb_alloc_urb(0, GFP_KERNEL);
+	buf->buf = usb_alloc_coherent(usb_dev, buf->len, GFP_KERNEL, &buf->dma);
+
+	return !buf->urb || !buf->buf;
+}
+
+void mt76x0_usb_free_buf(struct mt76x0_dev *dev, struct mt76x0_dma_buf *buf)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+
+	usb_free_coherent(usb_dev, buf->len, buf->buf, buf->dma);
+	usb_free_urb(buf->urb);
+}
+
+int mt76x0_usb_submit_buf(struct mt76x0_dev *dev, int dir, int ep_idx,
+			   struct mt76x0_dma_buf *buf, gfp_t gfp,
+			   usb_complete_t complete_fn, void *context)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	unsigned pipe;
+	int ret;
+
+	if (dir == USB_DIR_IN)
+		pipe = usb_rcvbulkpipe(usb_dev, dev->in_ep[ep_idx]);
+	else
+		pipe = usb_sndbulkpipe(usb_dev, dev->out_ep[ep_idx]);
+
+	usb_fill_bulk_urb(buf->urb, usb_dev, pipe, buf->buf, buf->len,
+			  complete_fn, context);
+	buf->urb->transfer_dma = buf->dma;
+	buf->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
+
+	trace_mt_submit_urb(&dev->mt76, buf->urb);
+	ret = usb_submit_urb(buf->urb, gfp);
+	if (ret)
+		dev_err(dev->mt76.dev, "Error: submit URB dir:%d ep:%d failed:%d\n",
+			dir, ep_idx, ret);
+	return ret;
+}
+
+void mt76x0_complete_urb(struct urb *urb)
+{
+	struct completion *cmpl = urb->context;
+
+	complete(cmpl);
+}
+
+int mt76x0_vendor_request(struct mt76x0_dev *dev, const u8 req,
+			   const u8 direction, const u16 val, const u16 offset,
+			   void *buf, const size_t buflen)
+{
+	int i, ret;
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	const u8 req_type = direction | USB_TYPE_VENDOR | USB_RECIP_DEVICE;
+	const unsigned int pipe = (direction == USB_DIR_IN) ?
+		usb_rcvctrlpipe(usb_dev, 0) : usb_sndctrlpipe(usb_dev, 0);
+
+	for (i = 0; i < MT_VEND_REQ_MAX_RETRY; i++) {
+		ret = usb_control_msg(usb_dev, pipe, req, req_type,
+				      val, offset, buf, buflen,
+				      MT_VEND_REQ_TOUT_MS);
+		trace_mt_vend_req(&dev->mt76, pipe, req, req_type, val, offset,
+				  buf, buflen, ret);
+
+		if (ret == -ENODEV)
+			set_bit(MT76_REMOVED, &dev->mt76.state);
+		if (ret >= 0 || ret == -ENODEV)
+			return ret;
+
+		msleep(5);
+	}
+
+	dev_err(dev->mt76.dev, "Vendor request req:%02x off:%04x failed:%d\n",
+		req, offset, ret);
+
+	return ret;
+}
+
+void mt76x0_vendor_reset(struct mt76x0_dev *dev)
+{
+	mt76x0_vendor_request(dev, MT_VEND_DEV_MODE, USB_DIR_OUT,
+			      MT_VEND_DEV_MODE_RESET, 0, NULL, 0);
+}
+
+static u32 mt76x0_rr(struct mt76_dev *dev, u32 offset)
+{
+	struct mt76x0_dev *mdev = (struct mt76x0_dev *) dev;
+	int ret;
+	u32 val = ~0;
+
+	WARN_ONCE(offset > USHRT_MAX, "read high off:%08x", offset);
+
+	mutex_lock(&mdev->usb_ctrl_mtx);
+
+	ret = mt76x0_vendor_request((struct mt76x0_dev *)dev, MT_VEND_MULTI_READ, USB_DIR_IN,
+				    0, offset, mdev->data, MT_VEND_BUF);
+	if (ret == MT_VEND_BUF)
+		val = get_unaligned_le32(mdev->data);
+	else if (ret > 0)
+		dev_err(dev->dev, "Error: wrong size read:%d off:%08x\n",
+			ret, offset);
+
+	mutex_unlock(&mdev->usb_ctrl_mtx);
+
+	trace_reg_read(dev, offset, val);
+	return val;
+}
+
+int mt76x0_vendor_single_wr(struct mt76x0_dev *dev, const u8 req,
+			     const u16 offset, const u32 val)
+{
+	struct mt76x0_dev *mdev = dev;
+	int ret;
+
+	mutex_lock(&mdev->usb_ctrl_mtx);
+
+	ret = mt76x0_vendor_request(dev, req, USB_DIR_OUT,
+				    val & 0xffff, offset, NULL, 0);
+	if (!ret)
+		ret = mt76x0_vendor_request(dev, req, USB_DIR_OUT,
+					    val >> 16, offset + 2, NULL, 0);
+
+	mutex_unlock(&mdev->usb_ctrl_mtx);
+
+	return ret;
+}
+
+static void mt76x0_wr(struct mt76_dev *dev, u32 offset, u32 val)
+{
+	struct mt76x0_dev *mdev = (struct mt76x0_dev *) dev;
+	int ret;
+
+	WARN_ONCE(offset > USHRT_MAX, "write high off:%08x", offset);
+
+	mutex_lock(&mdev->usb_ctrl_mtx);
+
+	put_unaligned_le32(val, mdev->data);
+	ret = mt76x0_vendor_request(mdev, MT_VEND_MULTI_WRITE, USB_DIR_OUT,
+				    0, offset, mdev->data, MT_VEND_BUF);
+	trace_reg_write(dev, offset, val);
+
+	mutex_unlock(&mdev->usb_ctrl_mtx);
+}
+
+static u32 mt76x0_rmw(struct mt76_dev *dev, u32 offset, u32 mask, u32 val)
+{
+	val |= mt76x0_rr(dev, offset) & ~mask;
+	mt76x0_wr(dev, offset, val);
+	return val;
+}
+
+static void mt76x0_wr_copy(struct mt76_dev *dev, u32 offset,
+			   const void *data, int len)
+{
+	WARN_ONCE(offset & 3, "unaligned write copy off:%08x", offset);
+	WARN_ONCE(len & 3, "short write copy off:%08x", offset);
+
+	mt76x0_burst_write_regs((struct mt76x0_dev *) dev, offset, data, len / 4);
+}
+
+void mt76x0_addr_wr(struct mt76x0_dev *dev, const u32 offset, const u8 *addr)
+{
+	mt76_wr(dev, offset, get_unaligned_le32(addr));
+	mt76_wr(dev, offset + 4, addr[4] | addr[5] << 8);
+}
+
+static int mt76x0_assign_pipes(struct usb_interface *usb_intf,
+				struct mt76x0_dev *dev)
+{
+	struct usb_endpoint_descriptor *ep_desc;
+	struct usb_host_interface *intf_desc = usb_intf->cur_altsetting;
+	unsigned i, ep_i = 0, ep_o = 0;
+
+	BUILD_BUG_ON(sizeof(dev->in_ep) < __MT_EP_IN_MAX);
+	BUILD_BUG_ON(sizeof(dev->out_ep) < __MT_EP_OUT_MAX);
+
+	for (i = 0; i < intf_desc->desc.bNumEndpoints; i++) {
+		ep_desc = &intf_desc->endpoint[i].desc;
+
+		if (usb_endpoint_is_bulk_in(ep_desc) &&
+		    ep_i++ < __MT_EP_IN_MAX) {
+			dev->in_ep[ep_i - 1] = usb_endpoint_num(ep_desc);
+			dev->in_max_packet = usb_endpoint_maxp(ep_desc);
+			/* Note: this is ignored by usb sub-system but vendor
+			 *	 code does it. We can drop this at some point.
+			 */
+			dev->in_ep[ep_i - 1] |= USB_DIR_IN;
+		} else if (usb_endpoint_is_bulk_out(ep_desc) &&
+			   ep_o++ < __MT_EP_OUT_MAX) {
+			dev->out_ep[ep_o - 1] = usb_endpoint_num(ep_desc);
+			dev->out_max_packet = usb_endpoint_maxp(ep_desc);
+		}
+	}
+
+	if (ep_i != __MT_EP_IN_MAX || ep_o != __MT_EP_OUT_MAX) {
+		dev_err(dev->mt76.dev, "Error: wrong pipe number in:%d out:%d\n",
+			ep_i, ep_o);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int mt76x0_probe(struct usb_interface *usb_intf,
+			 const struct usb_device_id *id)
+{
+	struct usb_device *usb_dev = interface_to_usbdev(usb_intf);
+	struct mt76x0_dev *dev;
+	u32 asic_rev, mac_rev;
+	int ret;
+	static const struct mt76_bus_ops usb_ops = {
+		.rr = mt76x0_rr,
+		.wr = mt76x0_wr,
+		.rmw = mt76x0_rmw,
+		.copy = mt76x0_wr_copy,
+	};
+
+	dev = mt76x0_alloc_device(&usb_intf->dev);
+	if (!dev)
+		return -ENOMEM;
+
+	usb_dev = usb_get_dev(usb_dev);
+	usb_reset_device(usb_dev);
+
+	usb_set_intfdata(usb_intf, dev);
+
+	dev->mt76.bus = &usb_ops;
+
+	ret = mt76x0_assign_pipes(usb_intf, dev);
+	if (ret)
+		goto err;
+	ret = mt76x0_wait_asic_ready(dev);
+	if (ret)
+		goto err;
+
+	asic_rev = mt76_rr(dev, MT_ASIC_VERSION);
+	mac_rev = mt76_rr(dev, MT_MAC_CSR0);
+	dev_info(dev->mt76.dev, "ASIC revision: %08x MAC revision: %08x\n",
+		 asic_rev, mac_rev);
+
+	/* Note: vendor driver skips this check for MT76X0U */
+	if (!(mt76_rr(dev, MT_EFUSE_CTRL) & MT_EFUSE_CTRL_SEL))
+		dev_warn(dev->mt76.dev, "Warning: eFUSE not present\n");
+
+	ret = mt76x0_init_hardware(dev);
+	if (ret)
+		goto err;
+
+	ret = mt76x0_register_device(dev);
+	if (ret)
+		goto err_hw;
+
+	set_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	return 0;
+err_hw:
+	mt76x0_cleanup(dev);
+err:
+	usb_set_intfdata(usb_intf, NULL);
+	usb_put_dev(interface_to_usbdev(usb_intf));
+
+	destroy_workqueue(dev->stat_wq);
+	ieee80211_free_hw(dev->mt76.hw);
+	return ret;
+}
+
+static void mt76x0_disconnect(struct usb_interface *usb_intf)
+{
+	struct mt76x0_dev *dev = usb_get_intfdata(usb_intf);
+	bool initalized = test_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	if (!initalized)
+		return;
+
+	ieee80211_unregister_hw(dev->mt76.hw);
+	mt76x0_cleanup(dev);
+
+	usb_set_intfdata(usb_intf, NULL);
+	usb_put_dev(interface_to_usbdev(usb_intf));
+
+	destroy_workqueue(dev->stat_wq);
+	ieee80211_free_hw(dev->mt76.hw);
+}
+
+static int mt76x0_suspend(struct usb_interface *usb_intf, pm_message_t state)
+{
+	struct mt76x0_dev *dev = usb_get_intfdata(usb_intf);
+
+	mt76x0_cleanup(dev);
+
+	return 0;
+}
+
+static int mt76x0_resume(struct usb_interface *usb_intf)
+{
+	struct mt76x0_dev *dev = usb_get_intfdata(usb_intf);
+	int ret;
+
+	ret = mt76x0_init_hardware(dev);
+	if (ret)
+		return ret;
+
+	set_bit(MT76_STATE_INITIALIZED, &dev->mt76.state);
+
+	return 0;
+}
+
+MODULE_DEVICE_TABLE(usb, mt76x0_device_table);
+MODULE_FIRMWARE(MT7610_FIRMWARE);
+MODULE_LICENSE("GPL");
+
+static struct usb_driver mt76x0_driver = {
+	.name		= KBUILD_MODNAME,
+	.id_table	= mt76x0_device_table,
+	.probe		= mt76x0_probe,
+	.disconnect	= mt76x0_disconnect,
+	.suspend	= mt76x0_suspend,
+	.resume		= mt76x0_resume,
+	.reset_resume	= mt76x0_resume,
+	.soft_unbind	= 1,
+	.disable_hub_initiated_lpm = 1,
+};
+module_usb_driver(mt76x0_driver);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h
new file mode 100644
index 000000000000..9e42dfa665de
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h
@@ -0,0 +1,61 @@
+/*
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_USB_H
+#define __MT76X0U_USB_H
+
+#include "mt76x0.h"
+
+#define MT7610_FIRMWARE	"mt7610.bin"
+
+#define MT_VEND_REQ_MAX_RETRY	10
+#define MT_VEND_REQ_TOUT_MS	300
+
+#define MT_VEND_DEV_MODE_RESET	1
+
+#define MT_VEND_BUF		sizeof(__le32)
+
+static inline struct usb_device *mt76x0_to_usb_dev(struct mt76x0_dev *mt76x0)
+{
+	return interface_to_usbdev(to_usb_interface(mt76x0->mt76.dev));
+}
+
+static inline struct usb_device *mt76_to_usb_dev(struct mt76_dev *mt76)
+{
+	return interface_to_usbdev(to_usb_interface(mt76->dev));
+}
+
+static inline bool mt76x0_urb_has_error(struct urb *urb)
+{
+	return urb->status &&
+		urb->status != -ENOENT &&
+		urb->status != -ECONNRESET &&
+		urb->status != -ESHUTDOWN;
+}
+
+bool mt76x0_usb_alloc_buf(struct mt76x0_dev *dev, size_t len,
+			   struct mt76x0_dma_buf *buf);
+void mt76x0_usb_free_buf(struct mt76x0_dev *dev, struct mt76x0_dma_buf *buf);
+int mt76x0_usb_submit_buf(struct mt76x0_dev *dev, int dir, int ep_idx,
+			   struct mt76x0_dma_buf *buf, gfp_t gfp,
+			   usb_complete_t complete_fn, void *context);
+void mt76x0_complete_urb(struct urb *urb);
+
+int mt76x0_vendor_request(struct mt76x0_dev *dev, const u8 req,
+			   const u8 direction, const u16 val, const u16 offset,
+			   void *buf, const size_t buflen);
+void mt76x0_vendor_reset(struct mt76x0_dev *dev);
+int mt76x0_vendor_single_wr(struct mt76x0_dev *dev, const u8 req,
+			     const u16 offset, const u32 val);
+
+#endif
-- 
cgit v1.2.3


From 55b13a04744594a7ba7f36ff95352d7d20fcff8c Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:54 +0200
Subject: mt76x0: mcu files

Add mcu files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c | 656 ++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h | 101 ++++
 2 files changed, 757 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
new file mode 100644
index 000000000000..979ba519e54f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
@@ -0,0 +1,656 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/firmware.h>
+#include <linux/delay.h>
+#include <linux/usb.h>
+#include <linux/skbuff.h>
+
+#include "mt76x0.h"
+#include "dma.h"
+#include "mcu.h"
+#include "usb.h"
+#include "trace.h"
+
+#define MCU_FW_URB_MAX_PAYLOAD		0x38f8
+#define MCU_FW_URB_SIZE			(MCU_FW_URB_MAX_PAYLOAD + 12)
+#define MCU_RESP_URB_SIZE		1024
+
+static inline int firmware_running(struct mt76x0_dev *dev)
+{
+	return mt76_rr(dev, MT_MCU_COM_REG0) == 1;
+}
+
+static inline void skb_put_le32(struct sk_buff *skb, u32 val)
+{
+	put_unaligned_le32(val, skb_put(skb, 4));
+}
+
+static inline void mt76x0_dma_skb_wrap_cmd(struct sk_buff *skb,
+					    u8 seq, enum mcu_cmd cmd)
+{
+	WARN_ON(mt76x0_dma_skb_wrap(skb, CPU_TX_PORT, DMA_COMMAND,
+				     FIELD_PREP(MT_TXD_CMD_SEQ, seq) |
+				     FIELD_PREP(MT_TXD_CMD_TYPE, cmd)));
+}
+
+static inline void trace_mt_mcu_msg_send_cs(struct mt76_dev *dev,
+					    struct sk_buff *skb, bool need_resp)
+{
+	u32 i, csum = 0;
+
+	for (i = 0; i < skb->len / 4; i++)
+		csum ^= get_unaligned_le32(skb->data + i * 4);
+
+	trace_mt_mcu_msg_send(dev, skb, csum, need_resp);
+}
+
+static struct sk_buff *
+mt76x0_mcu_msg_alloc(struct mt76x0_dev *dev, const void *data, int len)
+{
+	struct sk_buff *skb;
+
+	WARN_ON(len % 4); /* if length is not divisible by 4 we need to pad */
+
+	skb = alloc_skb(len + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (skb) {
+		skb_reserve(skb, MT_DMA_HDR_LEN);
+		memcpy(skb_put(skb, len), data, len);
+	}
+	return skb;
+}
+
+static void mt76x0_read_resp_regs(struct mt76x0_dev *dev, int len)
+{
+	int i;
+	int n = dev->mcu.reg_pairs_len;
+	u8 *buf = dev->mcu.resp.buf;
+
+	buf += 4;
+	len -= 8;
+
+	if (dev->mcu.burst_read) {
+		u32 reg = dev->mcu.reg_pairs[0].reg - dev->mcu.reg_base;
+
+		WARN_ON_ONCE(len/4 != n);
+		for (i = 0; i < n; i++) {
+			u32 val = get_unaligned_le32(buf + 4*i);
+
+			dev->mcu.reg_pairs[i].reg = reg++;
+			dev->mcu.reg_pairs[i].value = val;
+		}
+	} else {
+		WARN_ON_ONCE(len/8 != n);
+		for (i = 0; i < n; i++) {
+			u32 reg = get_unaligned_le32(buf + 8*i) - dev->mcu.reg_base;
+			u32 val = get_unaligned_le32(buf + 8*i + 4);
+
+			WARN_ON_ONCE(dev->mcu.reg_pairs[i].reg != reg);
+			dev->mcu.reg_pairs[i].value = val;
+		}
+	}
+}
+
+static int mt76x0_mcu_wait_resp(struct mt76x0_dev *dev, u8 seq)
+{
+	struct urb *urb = dev->mcu.resp.urb;
+	u32 rxfce;
+	int urb_status, ret, try = 5;
+
+	while (try--) {
+		if (!wait_for_completion_timeout(&dev->mcu.resp_cmpl,
+						 msecs_to_jiffies(300))) {
+			dev_warn(dev->mt76.dev, "Warning: %s retrying\n", __func__);
+			continue;
+		}
+
+		/* Make copies of important data before reusing the urb */
+		rxfce = get_unaligned_le32(dev->mcu.resp.buf);
+		urb_status = urb->status * mt76x0_urb_has_error(urb);
+
+		if (urb_status == 0 && dev->mcu.reg_pairs)
+			mt76x0_read_resp_regs(dev, urb->actual_length);
+
+		ret = mt76x0_usb_submit_buf(dev, USB_DIR_IN, MT_EP_IN_CMD_RESP,
+					     &dev->mcu.resp, GFP_KERNEL,
+					     mt76x0_complete_urb,
+					     &dev->mcu.resp_cmpl);
+		if (ret)
+			return ret;
+
+		if (urb_status)
+			dev_err(dev->mt76.dev, "Error: MCU resp urb failed:%d\n",
+				urb_status);
+
+		if (FIELD_GET(MT_RXD_CMD_INFO_CMD_SEQ, rxfce) == seq &&
+		    FIELD_GET(MT_RXD_CMD_INFO_EVT_TYPE, rxfce) == CMD_DONE)
+			return 0;
+
+		dev_err(dev->mt76.dev, "Error: MCU resp evt:%lx seq:%hhx-%lx!\n",
+			FIELD_GET(MT_RXD_CMD_INFO_EVT_TYPE, rxfce),
+			seq, FIELD_GET(MT_RXD_CMD_INFO_CMD_SEQ, rxfce));
+	}
+
+	dev_err(dev->mt76.dev, "Error: %s timed out\n", __func__);
+	return -ETIMEDOUT;
+}
+
+static int
+__mt76x0_mcu_msg_send(struct mt76x0_dev *dev, struct sk_buff *skb,
+		      enum mcu_cmd cmd, bool wait_resp)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	unsigned cmd_pipe = usb_sndbulkpipe(usb_dev,
+					    dev->out_ep[MT_EP_OUT_INBAND_CMD]);
+	int sent, ret;
+	u8 seq = 0;
+
+	if (wait_resp)
+		while (!seq)
+			seq = ++dev->mcu.msg_seq & 0xf;
+
+	mt76x0_dma_skb_wrap_cmd(skb, seq, cmd);
+
+	if (dev->mcu.resp_cmpl.done)
+		dev_err(dev->mt76.dev, "Error: MCU response pre-completed!\n");
+
+	trace_mt_mcu_msg_send_cs(&dev->mt76, skb, wait_resp);
+	trace_mt_submit_urb_sync(&dev->mt76, cmd_pipe, skb->len);
+
+	ret = usb_bulk_msg(usb_dev, cmd_pipe, skb->data, skb->len, &sent, 500);
+	if (ret) {
+		dev_err(dev->mt76.dev, "Error: send MCU cmd failed:%d\n", ret);
+		goto out;
+	}
+	if (sent != skb->len)
+		dev_err(dev->mt76.dev, "Error: %s sent != skb->len\n", __func__);
+
+	if (wait_resp)
+		ret = mt76x0_mcu_wait_resp(dev, seq);
+
+out:
+	return ret;
+}
+
+static int
+mt76x0_mcu_msg_send(struct mt76x0_dev *dev, struct sk_buff *skb,
+		     enum mcu_cmd cmd, bool wait_resp)
+{
+	int ret;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return 0;
+
+	mutex_lock(&dev->mcu.mutex);
+	ret = __mt76x0_mcu_msg_send(dev, skb, cmd, wait_resp);
+	mutex_unlock(&dev->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+}
+
+int mt76x0_mcu_function_select(struct mt76x0_dev *dev,
+			       enum mcu_function func, u32 val)
+{
+	struct sk_buff *skb;
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(func),
+		.value = cpu_to_le32(val),
+	};
+
+	skb = mt76x0_mcu_msg_alloc(dev, &msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76x0_mcu_msg_send(dev, skb, CMD_FUN_SET_OP, func == 5);
+}
+
+int
+mt76x0_mcu_calibrate(struct mt76x0_dev *dev, enum mcu_calibrate cal, u32 val)
+{
+	struct sk_buff *skb;
+	struct {
+		__le32 id;
+		__le32 value;
+	} __packed __aligned(4) msg = {
+		.id = cpu_to_le32(cal),
+		.value = cpu_to_le32(val),
+	};
+
+	skb = mt76x0_mcu_msg_alloc(dev, &msg, sizeof(msg));
+	if (!skb)
+		return -ENOMEM;
+	return mt76x0_mcu_msg_send(dev, skb, CMD_CALIBRATION_OP, true);
+}
+
+int mt76x0_write_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			   const struct mt76_reg_pair *data, int n)
+{
+	const int max_vals_per_cmd = INBAND_PACKET_MAX_LEN / 8;
+	struct sk_buff *skb;
+	int cnt, i, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_vals_per_cmd, n);
+
+	skb = alloc_skb(cnt * 8 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	for (i = 0; i < cnt; i++) {
+		skb_put_le32(skb, base + data[i].reg);
+		skb_put_le32(skb, data[i].value);
+	}
+
+	ret = mt76x0_mcu_msg_send(dev, skb, CMD_RANDOM_WRITE, cnt == n);
+	if (ret)
+		return ret;
+
+	return mt76x0_write_reg_pairs(dev, base, data + cnt, n - cnt);
+}
+
+int mt76x0_read_reg_pairs(struct mt76x0_dev *dev, u32 base,
+			  struct mt76_reg_pair *data, int n)
+{
+	const int max_vals_per_cmd = INBAND_PACKET_MAX_LEN / 8;
+	struct sk_buff *skb;
+	int cnt, i, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_vals_per_cmd, n);
+	if (cnt != n)
+		return -EINVAL;
+
+	skb = alloc_skb(cnt * 8 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	for (i = 0; i < cnt; i++) {
+		skb_put_le32(skb, base + data[i].reg);
+		skb_put_le32(skb, data[i].value);
+	}
+
+	mutex_lock(&dev->mcu.mutex);
+
+	dev->mcu.reg_pairs = data;
+	dev->mcu.reg_pairs_len = n;
+	dev->mcu.reg_base = base;
+	dev->mcu.burst_read = false;
+
+	ret = __mt76x0_mcu_msg_send(dev, skb, CMD_RANDOM_READ, true);
+
+	dev->mcu.reg_pairs = NULL;
+
+	mutex_unlock(&dev->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+
+}
+
+int mt76x0_burst_write_regs(struct mt76x0_dev *dev, u32 offset,
+			     const u32 *data, int n)
+{
+	const int max_regs_per_cmd = INBAND_PACKET_MAX_LEN / 4 - 1;
+	struct sk_buff *skb;
+	int cnt, i, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_regs_per_cmd, n);
+
+	skb = alloc_skb(cnt * 4 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	skb_put_le32(skb, MT_MCU_MEMMAP_WLAN + offset);
+	for (i = 0; i < cnt; i++)
+		skb_put_le32(skb, data[i]);
+
+	ret = mt76x0_mcu_msg_send(dev, skb, CMD_BURST_WRITE, cnt == n);
+	if (ret)
+		return ret;
+
+	return mt76x0_burst_write_regs(dev, offset + cnt * 4,
+					data + cnt, n - cnt);
+}
+
+#if 0
+static int mt76x0_burst_read_regs(struct mt76x0_dev *dev, u32 base,
+				  struct mt76_reg_pair *data, int n)
+{
+	const int max_vals_per_cmd = INBAND_PACKET_MAX_LEN / 4 - 1;
+	struct sk_buff *skb;
+	int cnt, ret;
+
+	if (!n)
+		return 0;
+
+	cnt = min(max_vals_per_cmd, n);
+	if (cnt != n)
+		return -EINVAL;
+
+	skb = alloc_skb(cnt * 4 + MT_DMA_HDR_LEN + 4, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+	skb_reserve(skb, MT_DMA_HDR_LEN);
+
+	skb_put_le32(skb, base + data[0].reg);
+	skb_put_le32(skb, n);
+
+	mutex_lock(&dev->mcu.mutex);
+
+	dev->mcu.reg_pairs = data;
+	dev->mcu.reg_pairs_len = n;
+	dev->mcu.reg_base = base;
+	dev->mcu.burst_read = true;
+
+	ret = __mt76x0_mcu_msg_send(dev, skb, CMD_BURST_READ, true);
+
+	dev->mcu.reg_pairs = NULL;
+
+	mutex_unlock(&dev->mcu.mutex);
+
+	consume_skb(skb);
+
+	return ret;
+}
+#endif
+
+struct mt76_fw_header {
+	__le32 ilm_len;
+	__le32 dlm_len;
+	__le16 build_ver;
+	__le16 fw_ver;
+	u8 pad[4];
+	char build_time[16];
+};
+
+struct mt76_fw {
+	struct mt76_fw_header hdr;
+	u8 ivb[MT_MCU_IVB_SIZE];
+	u8 ilm[];
+};
+
+static int __mt76x0_dma_fw(struct mt76x0_dev *dev,
+			    const struct mt76x0_dma_buf *dma_buf,
+			    const void *data, u32 len, u32 dst_addr)
+{
+	DECLARE_COMPLETION_ONSTACK(cmpl);
+	struct mt76x0_dma_buf buf = *dma_buf; /* we need to fake length */
+	__le32 reg;
+	u32 val;
+	int ret;
+
+	reg = cpu_to_le32(FIELD_PREP(MT_TXD_INFO_TYPE, DMA_COMMAND) |
+			  FIELD_PREP(MT_TXD_INFO_D_PORT, CPU_TX_PORT) |
+			  FIELD_PREP(MT_TXD_INFO_LEN, len));
+	memcpy(buf.buf, &reg, sizeof(reg));
+	memcpy(buf.buf + sizeof(reg), data, len);
+	memset(buf.buf + sizeof(reg) + len, 0, 8);
+
+	ret = mt76x0_vendor_single_wr(dev, MT_VEND_WRITE_FCE,
+				       MT_FCE_DMA_ADDR, dst_addr);
+	if (ret)
+		return ret;
+	len = roundup(len, 4);
+	ret = mt76x0_vendor_single_wr(dev, MT_VEND_WRITE_FCE,
+				       MT_FCE_DMA_LEN, len << 16);
+	if (ret)
+		return ret;
+
+	buf.len = MT_DMA_HDR_LEN + len + 4;
+	ret = mt76x0_usb_submit_buf(dev, USB_DIR_OUT, MT_EP_OUT_INBAND_CMD,
+				     &buf, GFP_KERNEL,
+				     mt76x0_complete_urb, &cmpl);
+	if (ret)
+		return ret;
+
+	if (!wait_for_completion_timeout(&cmpl, msecs_to_jiffies(1000))) {
+		dev_err(dev->mt76.dev, "Error: firmware upload timed out\n");
+		usb_kill_urb(buf.urb);
+		return -ETIMEDOUT;
+	}
+	if (mt76x0_urb_has_error(buf.urb)) {
+		dev_err(dev->mt76.dev, "Error: firmware upload urb failed:%d\n",
+			buf.urb->status);
+		return buf.urb->status;
+	}
+
+	val = mt76_rr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX);
+	val++;
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_CPU_DESC_IDX, val);
+
+	msleep(5);
+
+	return 0;
+}
+
+static int
+mt76x0_dma_fw(struct mt76x0_dev *dev, struct mt76x0_dma_buf *dma_buf,
+	       const void *data, int len, u32 dst_addr)
+{
+	int n, ret;
+
+	if (len == 0)
+		return 0;
+
+	n = min(MCU_FW_URB_MAX_PAYLOAD, len);
+	ret = __mt76x0_dma_fw(dev, dma_buf, data, n, dst_addr);
+	if (ret)
+		return ret;
+
+#if 0
+	if (!mt76_poll_msec(dev, MT_MCU_COM_REG1, BIT(31), BIT(31), 500))
+		return -ETIMEDOUT;
+#endif
+
+	return mt76x0_dma_fw(dev, dma_buf, data + n, len - n, dst_addr + n);
+}
+
+static int
+mt76x0_upload_firmware(struct mt76x0_dev *dev, const struct mt76_fw *fw)
+{
+	struct mt76x0_dma_buf dma_buf;
+	void *ivb;
+	u32 ilm_len, dlm_len;
+	int i, ret;
+
+	ivb = kmemdup(fw->ivb, sizeof(fw->ivb), GFP_KERNEL);
+	if (!ivb)
+		return -ENOMEM;
+	if (mt76x0_usb_alloc_buf(dev, MCU_FW_URB_SIZE, &dma_buf)) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	ilm_len = le32_to_cpu(fw->hdr.ilm_len) - sizeof(fw->ivb);
+	dev_dbg(dev->mt76.dev, "loading FW - ILM %u + IVB %zu\n",
+		ilm_len, sizeof(fw->ivb));
+	ret = mt76x0_dma_fw(dev, &dma_buf, fw->ilm, ilm_len, sizeof(fw->ivb));
+	if (ret)
+		goto error;
+
+	dlm_len = le32_to_cpu(fw->hdr.dlm_len);
+	dev_dbg(dev->mt76.dev, "loading FW - DLM %u\n", dlm_len);
+	ret = mt76x0_dma_fw(dev, &dma_buf, fw->ilm + ilm_len,
+			     dlm_len, MT_MCU_DLM_OFFSET);
+	if (ret)
+		goto error;
+
+	ret = mt76x0_vendor_request(dev, MT_VEND_DEV_MODE, USB_DIR_OUT,
+				     0x12, 0, ivb, sizeof(fw->ivb));
+	if (ret < 0)
+		goto error;
+	ret = 0;
+
+	for (i = 100; i && !firmware_running(dev); i--)
+		msleep(10);
+	if (!i) {
+		ret = -ETIMEDOUT;
+		goto error;
+	}
+
+	dev_dbg(dev->mt76.dev, "Firmware running!\n");
+error:
+	kfree(ivb);
+	mt76x0_usb_free_buf(dev, &dma_buf);
+
+	return ret;
+}
+
+static int mt76x0_load_firmware(struct mt76x0_dev *dev)
+{
+	const struct firmware *fw;
+	const struct mt76_fw_header *hdr;
+	int len, ret;
+	u32 val;
+
+	mt76_wr(dev, MT_USB_DMA_CFG, (MT_USB_DMA_CFG_RX_BULK_EN |
+					 MT_USB_DMA_CFG_TX_BULK_EN));
+
+	if (firmware_running(dev))
+		return 0;
+
+	ret = request_firmware(&fw, MT7610_FIRMWARE, dev->mt76.dev);
+	if (ret)
+		return ret;
+
+	if (!fw || !fw->data || fw->size < sizeof(*hdr))
+		goto err_inv_fw;
+
+	hdr = (const struct mt76_fw_header *) fw->data;
+
+	if (le32_to_cpu(hdr->ilm_len) <= MT_MCU_IVB_SIZE)
+		goto err_inv_fw;
+
+	len = sizeof(*hdr);
+	len += le32_to_cpu(hdr->ilm_len);
+	len += le32_to_cpu(hdr->dlm_len);
+
+	if (fw->size != len)
+		goto err_inv_fw;
+
+	val = le16_to_cpu(hdr->fw_ver);
+	dev_dbg(dev->mt76.dev,
+		 "Firmware Version: %d.%d.%02d Build: %x Build time: %.16s\n",
+		 (val >> 12) & 0xf, (val >> 8) & 0xf, val & 0xf,
+		 le16_to_cpu(hdr->build_ver), hdr->build_time);
+
+	len = le32_to_cpu(hdr->ilm_len);
+
+	mt76_wr(dev, 0x1004, 0x2c);
+
+	mt76_set(dev, MT_USB_DMA_CFG, (MT_USB_DMA_CFG_RX_BULK_EN |
+				       MT_USB_DMA_CFG_TX_BULK_EN) |
+				       FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, 0x20));
+	mt76x0_vendor_reset(dev);
+	msleep(5);
+/*
+	mt76x0_rmw(dev, MT_PBF_CFG, 0, (MT_PBF_CFG_TX0Q_EN |
+					 MT_PBF_CFG_TX1Q_EN |
+					 MT_PBF_CFG_TX2Q_EN |
+					 MT_PBF_CFG_TX3Q_EN));
+*/
+
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 1);
+
+	/* FCE tx_fs_base_ptr */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_BASE_PTR, 0x400230);
+	/* FCE tx_fs_max_cnt */
+	mt76_wr(dev, MT_TX_CPU_FROM_FCE_MAX_COUNT, 1);
+	/* FCE pdma enable */
+	mt76_wr(dev, MT_FCE_PDMA_GLOBAL_CONF, 0x44);
+	/* FCE skip_fs_en */
+	mt76_wr(dev, MT_FCE_SKIP_FS, 3);
+
+	val = mt76_rr(dev, MT_USB_DMA_CFG);
+	val |= MT_USB_DMA_CFG_TX_WL_DROP;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+	val &= ~MT_USB_DMA_CFG_TX_WL_DROP;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+
+	ret = mt76x0_upload_firmware(dev, (const struct mt76_fw *)fw->data);
+	release_firmware(fw);
+
+	mt76_wr(dev, MT_FCE_PSE_CTRL, 1);
+
+	return ret;
+
+err_inv_fw:
+	dev_err(dev->mt76.dev, "Invalid firmware image\n");
+	release_firmware(fw);
+	return -ENOENT;
+}
+
+int mt76x0_mcu_init(struct mt76x0_dev *dev)
+{
+	int ret;
+
+	mutex_init(&dev->mcu.mutex);
+
+	ret = mt76x0_load_firmware(dev);
+	if (ret)
+		return ret;
+
+	set_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state);
+
+	return 0;
+}
+
+int mt76x0_mcu_cmd_init(struct mt76x0_dev *dev)
+{
+	int ret;
+
+	ret = mt76x0_mcu_function_select(dev, Q_SELECT, 1);
+	if (ret)
+		return ret;
+
+	init_completion(&dev->mcu.resp_cmpl);
+	if (mt76x0_usb_alloc_buf(dev, MCU_RESP_URB_SIZE, &dev->mcu.resp)) {
+		mt76x0_usb_free_buf(dev, &dev->mcu.resp);
+		return -ENOMEM;
+	}
+
+	ret = mt76x0_usb_submit_buf(dev, USB_DIR_IN, MT_EP_IN_CMD_RESP,
+				     &dev->mcu.resp, GFP_KERNEL,
+				     mt76x0_complete_urb, &dev->mcu.resp_cmpl);
+	if (ret) {
+		mt76x0_usb_free_buf(dev, &dev->mcu.resp);
+		return ret;
+	}
+
+	return 0;
+}
+
+void mt76x0_mcu_cmd_deinit(struct mt76x0_dev *dev)
+{
+	usb_kill_urb(dev->mcu.resp.urb);
+	mt76x0_usb_free_buf(dev, &dev->mcu.resp);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h
new file mode 100644
index 000000000000..8c2f77f4c3f5
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.h
@@ -0,0 +1,101 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_MCU_H
+#define __MT76X0U_MCU_H
+
+struct mt76x0_dev;
+
+/* Register definitions */
+#define MT_MCU_RESET_CTL		0x070C
+#define MT_MCU_INT_LEVEL		0x0718
+#define MT_MCU_COM_REG0			0x0730
+#define MT_MCU_COM_REG1			0x0734
+#define MT_MCU_COM_REG2			0x0738
+#define MT_MCU_COM_REG3			0x073C
+
+#define MT_MCU_IVB_SIZE			0x40
+#define MT_MCU_DLM_OFFSET		0x80000
+
+#define MT_MCU_MEMMAP_WLAN		0x00410000
+/* We use same space for BBP as for MAC regs
+ * #define MT_MCU_MEMMAP_BBP		0x40000000
+ */
+#define MT_MCU_MEMMAP_RF		0x80000000
+
+#define INBAND_PACKET_MAX_LEN		192
+
+enum mcu_cmd {
+	CMD_FUN_SET_OP = 1,
+	CMD_LOAD_CR = 2,
+	CMD_INIT_GAIN_OP = 3,
+	CMD_DYNC_VGA_OP = 6,
+	CMD_TDLS_CH_SW = 7,
+	CMD_BURST_WRITE = 8,
+	CMD_READ_MODIFY_WRITE = 9,
+	CMD_RANDOM_READ = 10,
+	CMD_BURST_READ = 11,
+	CMD_RANDOM_WRITE = 12,
+	CMD_LED_MODE_OP = 16,
+	CMD_POWER_SAVING_OP = 20,
+	CMD_WOW_CONFIG = 21,
+	CMD_WOW_QUERY = 22,
+	CMD_WOW_FEATURE = 24,
+	CMD_CARRIER_DETECT_OP = 28,
+	CMD_RADOR_DETECT_OP = 29,
+	CMD_SWITCH_CHANNEL_OP = 30,
+	CMD_CALIBRATION_OP = 31,
+	CMD_BEACON_OP = 32,
+	CMD_ANTENNA_OP = 33,
+};
+
+enum mcu_function {
+	Q_SELECT = 1,
+	BW_SETTING = 2,
+	ATOMIC_TSSI_SETTING = 5,
+};
+
+enum mcu_power_mode {
+	RADIO_OFF = 0x30,
+	RADIO_ON = 0x31,
+	RADIO_OFF_AUTO_WAKEUP = 0x32,
+	RADIO_OFF_ADVANCE = 0x33,
+	RADIO_ON_ADVANCE = 0x34,
+};
+
+enum mcu_calibrate {
+	MCU_CAL_R = 1,
+	MCU_CAL_RXDCOC,
+	MCU_CAL_LC,
+	MCU_CAL_LOFT,
+	MCU_CAL_TXIQ,
+	MCU_CAL_BW,
+	MCU_CAL_DPD,
+	MCU_CAL_RXIQ,
+	MCU_CAL_TXDCOC,
+	MCU_CAL_RX_GROUP_DELAY,
+	MCU_CAL_TX_GROUP_DELAY,
+};
+
+int mt76x0_mcu_init(struct mt76x0_dev *dev);
+int mt76x0_mcu_cmd_init(struct mt76x0_dev *dev);
+void mt76x0_mcu_cmd_deinit(struct mt76x0_dev *dev);
+
+int
+mt76x0_mcu_calibrate(struct mt76x0_dev *dev, enum mcu_calibrate cal, u32 val);
+
+int
+mt76x0_mcu_function_select(struct mt76x0_dev *dev, enum mcu_function func, u32 val);
+
+#endif
-- 
cgit v1.2.3


From 10de7a8b4ab992cf2348d97409109c9f4c7a565d Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:55 +0200
Subject: mt76x0: phy files

Add phy files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../wireless/mediatek/mt76/mt76x0/initvals_phy.h   |  772 +++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    | 1008 ++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.h    |   81 ++
 3 files changed, 1861 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/phy.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
new file mode 100644
index 000000000000..95d43efc1f3d
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals_phy.h
@@ -0,0 +1,772 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_PHY_INITVALS_H
+#define __MT76X0U_PHY_INITVALS_H
+
+#define RF_REG_PAIR(bank, reg, value)				\
+	{ (bank) << 16 | (reg), value }
+
+
+static const struct mt76_reg_pair mt76x0_rf_central_tab[] = {
+/*
+	Bank 0 - For central blocks: BG, PLL, XTAL, LO, ADC/DAC
+*/
+	{ MT_RF(0, 1), 0x01},
+	{ MT_RF(0, 2), 0x11},
+
+	/*
+		R3 ~ R7: VCO Cal.
+	*/
+	{ MT_RF(0, 3), 0x73}, /* VCO Freq Cal - No Bypass, VCO Amp Cal - No Bypass */
+	{ MT_RF(0, 4), 0x30}, /* R4 b<7>=1, VCO cal */
+	{ MT_RF(0, 5), 0x00},
+	{ MT_RF(0, 6), 0x41}, /* Set the open loop amplitude to middle since bypassing amplitude calibration */
+	{ MT_RF(0, 7), 0x00},
+
+	/*
+		XO
+	*/
+	{ MT_RF(0,  8), 0x00},
+	{ MT_RF(0,  9), 0x00},
+	{ MT_RF(0, 10), 0x0C},
+	{ MT_RF(0, 11), 0x00},
+	{ MT_RF(0, 12), 0x00},
+
+	/*
+		BG
+	*/
+	{ MT_RF(0, 13), 0x00},
+	{ MT_RF(0, 14), 0x00},
+	{ MT_RF(0, 15), 0x00},
+
+	/*
+		LDO
+	*/
+	{ MT_RF(0, 19), 0x20},
+	/*
+		XO
+	*/
+	{ MT_RF(0, 20), 0x22},
+	{ MT_RF(0, 21), 0x12},
+	{ MT_RF(0, 23), 0x00},
+	{ MT_RF(0, 24), 0x33}, /* See band selection for R24<1:0> */
+	{ MT_RF(0, 25), 0x00},
+
+	/*
+		PLL, See Freq Selection
+	*/
+	{ MT_RF(0, 26), 0x00},
+	{ MT_RF(0, 27), 0x00},
+	{ MT_RF(0, 28), 0x00},
+	{ MT_RF(0, 29), 0x00},
+	{ MT_RF(0, 30), 0x00},
+	{ MT_RF(0, 31), 0x00},
+	{ MT_RF(0, 32), 0x00},
+	{ MT_RF(0, 33), 0x00},
+	{ MT_RF(0, 34), 0x00},
+	{ MT_RF(0, 35), 0x00},
+	{ MT_RF(0, 36), 0x00},
+	{ MT_RF(0, 37), 0x00},
+
+	/*
+		LO Buffer
+	*/
+	{ MT_RF(0, 38), 0x2F},
+
+	/*
+		Test Ports
+	*/
+	{ MT_RF(0, 64), 0x00},
+	{ MT_RF(0, 65), 0x80},
+	{ MT_RF(0, 66), 0x01},
+	{ MT_RF(0, 67), 0x04},
+
+	/*
+		ADC/DAC
+	*/
+	{ MT_RF(0, 68), 0x00},
+	{ MT_RF(0, 69), 0x08},
+	{ MT_RF(0, 70), 0x08},
+	{ MT_RF(0, 71), 0x40},
+	{ MT_RF(0, 72), 0xD0},
+	{ MT_RF(0, 73), 0x93},
+};
+
+static const struct mt76_reg_pair mt76x0_rf_2g_channel_0_tab[] = {
+/*
+	Bank 5 - Channel 0 2G RF registers
+*/
+	/*
+		RX logic operation
+	*/
+	/* RF_R00 Change in SelectBand6590 */
+
+	{ MT_RF(5, 2), 0x0C}, /* 5G+2G (MT7610U) */
+	{ MT_RF(5, 3), 0x00},
+
+	/*
+		TX logic operation
+	*/
+	{ MT_RF(5, 4), 0x00},
+	{ MT_RF(5, 5), 0x84},
+	{ MT_RF(5, 6), 0x02},
+
+	/*
+		LDO
+	*/
+	{ MT_RF(5, 7), 0x00},
+	{ MT_RF(5, 8), 0x00},
+	{ MT_RF(5, 9), 0x00},
+
+	/*
+		RX
+	*/
+	{ MT_RF(5, 10), 0x51},
+	{ MT_RF(5, 11), 0x22},
+	{ MT_RF(5, 12), 0x22},
+	{ MT_RF(5, 13), 0x0F},
+	{ MT_RF(5, 14), 0x47}, /* Increase mixer current for more gain */
+	{ MT_RF(5, 15), 0x25},
+	{ MT_RF(5, 16), 0xC7}, /* Tune LNA2 tank */
+	{ MT_RF(5, 17), 0x00},
+	{ MT_RF(5, 18), 0x00},
+	{ MT_RF(5, 19), 0x30}, /* Improve max Pin */
+	{ MT_RF(5, 20), 0x33},
+	{ MT_RF(5, 21), 0x02},
+	{ MT_RF(5, 22), 0x32}, /* Tune LNA1 tank */
+	{ MT_RF(5, 23), 0x00},
+	{ MT_RF(5, 24), 0x25},
+	{ MT_RF(5, 26), 0x00},
+	{ MT_RF(5, 27), 0x12},
+	{ MT_RF(5, 28), 0x0F},
+	{ MT_RF(5, 29), 0x00},
+
+	/*
+		LOGEN
+	*/
+	{ MT_RF(5, 30), 0x51}, /* Tune LOGEN tank */
+	{ MT_RF(5, 31), 0x35},
+	{ MT_RF(5, 32), 0x31},
+	{ MT_RF(5, 33), 0x31},
+	{ MT_RF(5, 34), 0x34},
+	{ MT_RF(5, 35), 0x03},
+	{ MT_RF(5, 36), 0x00},
+
+	/*
+		TX
+	*/
+	{ MT_RF(5, 37), 0xDD}, /* Improve 3.2GHz spur */
+	{ MT_RF(5, 38), 0xB3},
+	{ MT_RF(5, 39), 0x33},
+	{ MT_RF(5, 40), 0xB1},
+	{ MT_RF(5, 41), 0x71},
+	{ MT_RF(5, 42), 0xF2},
+	{ MT_RF(5, 43), 0x47},
+	{ MT_RF(5, 44), 0x77},
+	{ MT_RF(5, 45), 0x0E},
+	{ MT_RF(5, 46), 0x10},
+	{ MT_RF(5, 47), 0x00},
+	{ MT_RF(5, 48), 0x53},
+	{ MT_RF(5, 49), 0x03},
+	{ MT_RF(5, 50), 0xEF},
+	{ MT_RF(5, 51), 0xC7},
+	{ MT_RF(5, 52), 0x62},
+	{ MT_RF(5, 53), 0x62},
+	{ MT_RF(5, 54), 0x00},
+	{ MT_RF(5, 55), 0x00},
+	{ MT_RF(5, 56), 0x0F},
+	{ MT_RF(5, 57), 0x0F},
+	{ MT_RF(5, 58), 0x16},
+	{ MT_RF(5, 59), 0x16},
+	{ MT_RF(5, 60), 0x10},
+	{ MT_RF(5, 61), 0x10},
+	{ MT_RF(5, 62), 0xD0},
+	{ MT_RF(5, 63), 0x6C},
+	{ MT_RF(5, 64), 0x58},
+	{ MT_RF(5, 65), 0x58},
+	{ MT_RF(5, 66), 0xF2},
+	{ MT_RF(5, 67), 0xE8},
+	{ MT_RF(5, 68), 0xF0},
+	{ MT_RF(5, 69), 0xF0},
+	{ MT_RF(5, 127), 0x04},
+};
+
+static const struct mt76_reg_pair mt76x0_rf_5g_channel_0_tab[] = {
+/*
+	Bank 6 - Channel 0 5G RF registers
+*/
+	/*
+		RX logic operation
+	*/
+	/* RF_R00 Change in SelectBandmt76x0 */
+
+	{ MT_RF(6, 2), 0x0C},
+	{ MT_RF(6, 3), 0x00},
+
+	/*
+		TX logic operation
+	*/
+	{ MT_RF(6, 4), 0x00},
+	{ MT_RF(6, 5), 0x84},
+	{ MT_RF(6, 6), 0x02},
+
+	/*
+		LDO
+	*/
+	{ MT_RF(6, 7), 0x00},
+	{ MT_RF(6, 8), 0x00},
+	{ MT_RF(6, 9), 0x00},
+
+	/*
+		RX
+	*/
+	{ MT_RF(6, 10), 0x00},
+	{ MT_RF(6, 11), 0x01},
+
+	{ MT_RF(6, 13), 0x23},
+	{ MT_RF(6, 14), 0x00},
+	{ MT_RF(6, 15), 0x04},
+	{ MT_RF(6, 16), 0x22},
+
+	{ MT_RF(6, 18), 0x08},
+	{ MT_RF(6, 19), 0x00},
+	{ MT_RF(6, 20), 0x00},
+	{ MT_RF(6, 21), 0x00},
+	{ MT_RF(6, 22), 0xFB},
+
+	/*
+		LOGEN5G
+	*/
+	{ MT_RF(6, 25), 0x76},
+	{ MT_RF(6, 26), 0x24},
+	{ MT_RF(6, 27), 0x04},
+	{ MT_RF(6, 28), 0x00},
+	{ MT_RF(6, 29), 0x00},
+
+	/*
+		TX
+	*/
+	{ MT_RF(6, 37), 0xBB},
+	{ MT_RF(6, 38), 0xB3},
+
+	{ MT_RF(6, 40), 0x33},
+	{ MT_RF(6, 41), 0x33},
+
+	{ MT_RF(6, 43), 0x03},
+	{ MT_RF(6, 44), 0xB3},
+
+	{ MT_RF(6, 46), 0x17},
+	{ MT_RF(6, 47), 0x0E},
+	{ MT_RF(6, 48), 0x10},
+	{ MT_RF(6, 49), 0x07},
+
+	{ MT_RF(6, 62), 0x00},
+	{ MT_RF(6, 63), 0x00},
+	{ MT_RF(6, 64), 0xF1},
+	{ MT_RF(6, 65), 0x0F},
+};
+
+static const struct mt76_reg_pair mt76x0_rf_vga_channel_0_tab[] = {
+/*
+	Bank 7 - Channel 0 VGA RF registers
+*/
+	/* E3 CR */
+	{ MT_RF(7, 0), 0x47}, /* Allow BBP/MAC to do calibration */
+	{ MT_RF(7, 1), 0x00},
+	{ MT_RF(7, 2), 0x00},
+	{ MT_RF(7, 3), 0x00},
+	{ MT_RF(7, 4), 0x00},
+
+	{ MT_RF(7, 10), 0x13},
+	{ MT_RF(7, 11), 0x0F},
+	{ MT_RF(7, 12), 0x13}, /* For dcoc */
+	{ MT_RF(7, 13), 0x13}, /* For dcoc */
+	{ MT_RF(7, 14), 0x13}, /* For dcoc */
+	{ MT_RF(7, 15), 0x20}, /* For dcoc */
+	{ MT_RF(7, 16), 0x22}, /* For dcoc */
+
+	{ MT_RF(7, 17), 0x7C},
+
+	{ MT_RF(7, 18), 0x00},
+	{ MT_RF(7, 19), 0x00},
+	{ MT_RF(7, 20), 0x00},
+	{ MT_RF(7, 21), 0xF1},
+	{ MT_RF(7, 22), 0x11},
+	{ MT_RF(7, 23), 0xC2},
+	{ MT_RF(7, 24), 0x41},
+	{ MT_RF(7, 25), 0x20},
+	{ MT_RF(7, 26), 0x40},
+	{ MT_RF(7, 27), 0xD7},
+	{ MT_RF(7, 28), 0xA2},
+	{ MT_RF(7, 29), 0x60},
+	{ MT_RF(7, 30), 0x49},
+	{ MT_RF(7, 31), 0x20},
+	{ MT_RF(7, 32), 0x44},
+	{ MT_RF(7, 33), 0xC1},
+	{ MT_RF(7, 34), 0x60},
+	{ MT_RF(7, 35), 0xC0},
+
+	{ MT_RF(7, 61), 0x01},
+
+	{ MT_RF(7, 72), 0x3C},
+	{ MT_RF(7, 73), 0x34},
+	{ MT_RF(7, 74), 0x00},
+};
+
+static const struct mt76x0_rf_switch_item mt76x0_rf_bw_switch_tab[] = {
+	/*   Bank, 		Register,	Bw/Band, 	Value */
+	{ MT_RF(0, 17),		RF_G_BAND | RF_BW_20,	0x00},
+	{ MT_RF(0, 17),		RF_G_BAND | RF_BW_40,	0x00},
+	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_20,	0x00},
+	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_40,	0x00},
+	{ MT_RF(0, 17),		RF_A_BAND | RF_BW_80,	0x00},
+
+	/* TODO: need to check B7.R6 & B7.R7 setting for 2.4G again @20121112 */
+	{ MT_RF(7,  6),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  6),		RF_G_BAND | RF_BW_40,	0x1C},
+	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_40,	0x20},
+	{ MT_RF(7,  6),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7,  7),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  7),		RF_G_BAND | RF_BW_40,	0x20},
+	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_40,	0x20},
+	{ MT_RF(7,  7),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7,  8),		RF_G_BAND | RF_BW_20,	0x03},
+	{ MT_RF(7,  8),		RF_G_BAND | RF_BW_40,	0x01},
+	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_20,	0x03},
+	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_40,	0x01},
+	{ MT_RF(7,  8),		RF_A_BAND | RF_BW_80,	0x00},
+
+	/* TODO: need to check B7.R58 & B7.R59 setting for 2.4G again @20121112 */
+	{ MT_RF(7, 58),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 58),		RF_G_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 58),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7, 59),		RF_G_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 59),		RF_G_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_20,	0x40},
+	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_40,	0x40},
+	{ MT_RF(7, 59),		RF_A_BAND | RF_BW_80,	0x10},
+
+	{ MT_RF(7, 60),		RF_G_BAND | RF_BW_20,	0xAA},
+	{ MT_RF(7, 60),		RF_G_BAND | RF_BW_40,	0xAA},
+	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_20,	0xAA},
+	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_40,	0xAA},
+	{ MT_RF(7, 60),		RF_A_BAND | RF_BW_80,	0xAA},
+
+	{ MT_RF(7, 76),		RF_BW_20,	0x40},
+	{ MT_RF(7, 76),		RF_BW_40,	0x40},
+	{ MT_RF(7, 76),		RF_BW_80,	0x10},
+
+	{ MT_RF(7, 77),		RF_BW_20,	0x40},
+	{ MT_RF(7, 77),		RF_BW_40,	0x40},
+	{ MT_RF(7, 77),		RF_BW_80,	0x10},
+};
+
+static const struct mt76x0_rf_switch_item mt76x0_rf_band_switch_tab[] = {
+	/*   Bank, 		Register,	Bw/Band, 		Value */
+	{ MT_RF(0, 16),		RF_G_BAND,		0x20},
+	{ MT_RF(0, 16),		RF_A_BAND,		0x20},
+
+	{ MT_RF(0, 18),		RF_G_BAND,		0x00},
+	{ MT_RF(0, 18),		RF_A_BAND,		0x00},
+
+	{ MT_RF(0, 39),		RF_G_BAND,		0x36},
+	{ MT_RF(0, 39),		RF_A_BAND_LB,	0x34},
+	{ MT_RF(0, 39),		RF_A_BAND_MB,	0x33},
+	{ MT_RF(0, 39),		RF_A_BAND_HB,	0x31},
+	{ MT_RF(0, 39),		RF_A_BAND_11J,	0x36},
+
+	{ MT_RF(6, 12),		RF_A_BAND_LB,	0x44},
+	{ MT_RF(6, 12),		RF_A_BAND_MB,	0x44},
+	{ MT_RF(6, 12),		RF_A_BAND_HB,	0x55},
+	{ MT_RF(6, 12),		RF_A_BAND_11J,	0x44},
+
+	{ MT_RF(6, 17),		RF_A_BAND_LB,	0x02},
+	{ MT_RF(6, 17),		RF_A_BAND_MB,	0x00},
+	{ MT_RF(6, 17),		RF_A_BAND_HB,	0x00},
+	{ MT_RF(6, 17),		RF_A_BAND_11J,	0x05},
+
+	{ MT_RF(6, 24),		RF_A_BAND_LB,	0xA1},
+	{ MT_RF(6, 24),		RF_A_BAND_MB,	0x41},
+	{ MT_RF(6, 24),		RF_A_BAND_HB,	0x21},
+	{ MT_RF(6, 24),		RF_A_BAND_11J,	0xE1},
+
+	{ MT_RF(6, 39),		RF_A_BAND_LB,	0x36},
+	{ MT_RF(6, 39),		RF_A_BAND_MB,	0x34},
+	{ MT_RF(6, 39),		RF_A_BAND_HB,	0x32},
+	{ MT_RF(6, 39),		RF_A_BAND_11J,	0x37},
+
+	{ MT_RF(6, 42),		RF_A_BAND_LB,	0xFB},
+	{ MT_RF(6, 42),		RF_A_BAND_MB,	0xF3},
+	{ MT_RF(6, 42),		RF_A_BAND_HB,	0xEB},
+	{ MT_RF(6, 42),		RF_A_BAND_11J,	0xEB},
+
+	/* Move R6-R45, R50~R59 to mt76x0_RF_INT_PA_5G_Channel_0_RegTb/mt76x0_RF_EXT_PA_5G_Channel_0_RegTb */
+
+	{ MT_RF(6, 127),	RF_G_BAND,		0x84},
+	{ MT_RF(6, 127),	RF_A_BAND,		0x04},
+
+	{ MT_RF(7, 5),		RF_G_BAND,		0x40},
+	{ MT_RF(7, 5),		RF_A_BAND,		0x00},
+
+	{ MT_RF(7, 9),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 9),		RF_A_BAND,		0x00},
+
+	{ MT_RF(7, 70),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 70),		RF_A_BAND,		0x6D},
+
+	{ MT_RF(7, 71),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 71),		RF_A_BAND,		0xB0},
+
+	{ MT_RF(7, 78),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 78),		RF_A_BAND,		0x55},
+
+	{ MT_RF(7, 79),		RF_G_BAND,		0x00},
+	{ MT_RF(7, 79),		RF_A_BAND,		0x55},
+};
+
+static const struct mt76x0_freq_item mt76x0_frequency_plan[] = {
+	{1,	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2412 */
+	{2, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xE4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA1, 0, 0x30, 0, 0, 0x1}, /* Freq 2417 */
+	{3, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xE2, 0x40, 0x07, 0x40, 0x0B, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0}, /* Freq 2422 */
+	{4, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x50, 0, 0x30, 0, 0, 0x0}, /* Freq 2427 */
+	{5, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1}, /* Freq 2432 */
+	{6, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA2, 0, 0x30, 0, 0, 0x1}, /* Freq 2437 */
+	{7, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xE2, 0x40, 0x02, 0x40, 0x07, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2442 */
+	{8, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA3, 0, 0x30, 0, 0, 0x1}, /* Freq 2447 */
+	{9, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xF2, 0x40, 0x07, 0x40, 0x0D, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 2452 */
+	{10, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xD4, 0x40, 0x02, 0x40, 0x09, 0, 0, 1, 0x51, 0, 0x30, 0, 0, 0x0}, /* Freq 2457 */
+	{11, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x02, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1}, /* Freq 2462 */
+	{12, 	RF_G_BAND,	0x02, 0x3F, 0x3C, 0xDD, 0xD4, 0x40, 0x07, 0x40, 0x07, 0, 0, 1, 0xA4, 0, 0x30, 0, 0, 0x1}, /* Freq 2467 */
+	{13, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 2472 */
+	{14, 	RF_G_BAND,	0x02, 0x3F, 0x28, 0xDD, 0xF2, 0x40, 0x02, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 2484 */
+
+	{183, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x28, 0, 0x30, 0, 0, 0x3}, /* Freq 4915 */
+	{184, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x00, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4920 */
+	{185, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4925 */
+	{187, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4935 */
+	{188, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4940 */
+	{189, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4945 */
+	{192, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4960 */
+	{196, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x29, 0, 0x30, 0, 0, 0x3}, /* Freq 4980 */
+
+	{36, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5180 */
+	{37, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5185 */
+	{38, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5190 */
+	{39, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5195 */
+	{40, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5200 */
+	{41, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5205 */
+	{42, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5210 */
+	{43, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5215 */
+	{44, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5220 */
+	{45, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5225 */
+	{46, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5230 */
+	{47, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5235 */
+	{48, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5240 */
+	{49, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5245 */
+	{50, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5250 */
+	{51, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5255 */
+	{52, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5260 */
+	{53, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5265 */
+	{54, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5270 */
+	{55, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2B, 0, 0x30, 0, 0, 0x3}, /* Freq 5275 */
+	{56, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5280 */
+	{57, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5285 */
+	{58, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5290 */
+	{59, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5295 */
+	{60, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5300 */
+	{61, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5305 */
+	{62, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5310 */
+	{63, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5315 */
+	{64, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2C, 0, 0x30, 0, 0, 0x3}, /* Freq 5320 */
+
+	{100, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5500 */
+	{101, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5505 */
+	{102, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5510 */
+	{103, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2D, 0, 0x30, 0, 0, 0x3}, /* Freq 5515 */
+	{104, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5520 */
+	{105, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5525 */
+	{106, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5530 */
+	{107, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5535 */
+	{108, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5540 */
+	{109, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5545 */
+	{110, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5550 */
+	{111, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5555 */
+	{112, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5560 */
+	{113, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5565 */
+	{114, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5570 */
+	{115, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5575 */
+	{116, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5580 */
+	{117, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5585 */
+	{118, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5590 */
+	{119, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5595 */
+	{120, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5600 */
+	{121, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5605 */
+	{122, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5610 */
+	{123, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5615 */
+	{124, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5620 */
+	{125, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5625 */
+	{126, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5630 */
+	{127, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2E, 0, 0x30, 0, 0, 0x3}, /* Freq 5635 */
+	{128, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5640 */
+	{129, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5645 */
+	{130, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5650 */
+	{131, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5655 */
+	{132, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5660 */
+	{133, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5665 */
+	{134, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5670 */
+	{135, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5675 */
+	{136, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5680 */
+
+	{137, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5685 */
+	{138, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5690 */
+	{139, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5695 */
+	{140, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5700 */
+	{141, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5705 */
+	{142, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5710 */
+	{143, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5715 */
+	{144, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5720 */
+	{145, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5725 */
+	{146, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5730 */
+	{147, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5735 */
+	{148, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5740 */
+	{149, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5745 */
+	{150, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x0B, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5750 */
+	{151, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x70, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x17, 0, 0, 1, 0x2F, 0, 0x30, 0, 0, 0x3}, /* Freq 5755 */
+	{152, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x00, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5760 */
+	{153, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5765 */
+	{154, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x01, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5770 */
+	{155, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5775 */
+	{156, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x02, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5780 */
+	{157, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5785 */
+	{158, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x03, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5790 */
+	{159, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5795 */
+	{160, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x04, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5800 */
+	{161, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5805 */
+	{162, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x05, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5810 */
+	{163, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0B, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5815 */
+	{164, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x06, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5820 */
+	{165, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0D, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5825 */
+	{166, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0xDD, 0xD2, 0x40, 0x04, 0x40, 0x07, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5830 */
+	{167, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x0F, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5835 */
+	{168, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x08, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5840 */
+	{169, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x11, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5845 */
+	{170, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x09, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5850 */
+	{171, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x13, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5855 */
+	{172, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x30, 0x97, 0xD2, 0x40, 0x04, 0x40, 0x0A, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5860 */
+	{173, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x68, 0xDD, 0xD2, 0x40, 0x10, 0x40, 0x15, 0, 0, 1, 0x30, 0, 0x30, 0, 0, 0x3}, /* Freq 5865 */
+};
+
+static const struct mt76x0_freq_item mt76x0_sdm_frequency_plan[] = {
+	{1,	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0xCCCC,  0x3}, /* Freq 2412 */
+	{2, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x12222, 0x3}, /* Freq 2417 */
+	{3, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x17777, 0x3}, /* Freq 2422 */
+	{4, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x1CCCC, 0x3}, /* Freq 2427 */
+	{5, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x22222, 0x3}, /* Freq 2432 */
+	{6, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x27777, 0x3}, /* Freq 2437 */
+	{7, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x2CCCC, 0x3}, /* Freq 2442 */
+	{8, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x32222, 0x3}, /* Freq 2447 */
+	{9, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x37777, 0x3}, /* Freq 2452 */
+	{10, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x3CCCC, 0x3}, /* Freq 2457 */
+	{11, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x2222, 0x3}, /* Freq 2462 */
+	{12, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x7777, 0x3}, /* Freq 2467 */
+	{13, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xCCCC, 0x3}, /* Freq 2472 */
+	{14, 	RF_G_BAND,	0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x19999, 0x3}, /* Freq 2484 */
+
+	{183, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x28, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 4915 */
+	{184, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x0,     0x3}, /* Freq 4920 */
+	{185, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x2AAA,  0x3}, /* Freq 4925 */
+	{187, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x8000,  0x3}, /* Freq 4935 */
+	{188, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xAAAA,  0x3}, /* Freq 4940 */
+	{189, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0xD555,  0x3}, /* Freq 4945 */
+	{192, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 4960 */
+	{196, 	(RF_A_BAND | RF_A_BAND_11J), 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x29, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 4980 */
+
+	{36, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0xAAAA,  0x3}, /* Freq 5180 */
+	{37, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0xD555,  0x3}, /* Freq 5185 */
+	{38, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5190 */
+	{39, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5195 */
+	{40, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5200 */
+	{41, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5205 */
+	{42, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5210 */
+	{43, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5215 */
+	{44, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5220 */
+	{45, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5225 */
+	{46, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5230 */
+	{47, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5235 */
+	{48, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5240 */
+	{49, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5245 */
+	{50, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5250 */
+	{51, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5255 */
+	{52, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5260 */
+	{53, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5265 */
+	{54, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5270 */
+	{55, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2B, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5275 */
+	{56, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5280 */
+	{57, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5285 */
+	{58, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5290 */
+	{59, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5295 */
+	{60, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5300 */
+	{61, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5305 */
+	{62, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5310 */
+	{63, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5315 */
+	{64, 	(RF_A_BAND | RF_A_BAND_LB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2C, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5320 */
+
+	{100, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5500 */
+	{101, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5505 */
+	{102, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5510 */
+	{103, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2D, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5515 */
+	{104, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5520 */
+	{105, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5525 */
+	{106, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5530 */
+	{107, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5535 */
+	{108, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5540 */
+	{109, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5545 */
+	{110, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5550 */
+	{111, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5555 */
+	{112, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5560 */
+	{113, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5565 */
+	{114, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5570 */
+	{115, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5575 */
+	{116, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5580 */
+	{117, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5585 */
+	{118, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5590 */
+	{119, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5595 */
+	{120, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5600 */
+	{121, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5605 */
+	{122, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5610 */
+	{123, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5615 */
+	{124, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5620 */
+	{125, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5625 */
+	{126, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5630 */
+	{127, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2E, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5635 */
+	{128, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5640 */
+	{129, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5645 */
+	{130, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5650 */
+	{131, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5655 */
+	{132, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5660 */
+	{133, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5665 */
+	{134, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5670 */
+	{135, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5675 */
+	{136, 	(RF_A_BAND | RF_A_BAND_MB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5680 */
+
+	{137, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5685 */
+	{138, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5690 */
+	{139, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5695 */
+	{140, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5700 */
+	{141, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5705 */
+	{142, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5710 */
+	{143, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5715 */
+	{144, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5720 */
+	{145, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5725 */
+	{146, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5730 */
+	{147, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5735 */
+	{148, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5740 */
+	{149, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5745 */
+	{150, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3AAAA, 0x3}, /* Freq 5750 */
+	{151, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x2F, 0, 0x0, 0x8, 0x3D555, 0x3}, /* Freq 5755 */
+	{152, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x00000, 0x3}, /* Freq 5760 */
+	{153, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x02AAA, 0x3}, /* Freq 5765 */
+	{154, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x05555, 0x3}, /* Freq 5770 */
+	{155, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x08000, 0x3}, /* Freq 5775 */
+	{156, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x0AAAA, 0x3}, /* Freq 5780 */
+	{157, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x0D555, 0x3}, /* Freq 5785 */
+	{158, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x10000, 0x3}, /* Freq 5790 */
+	{159, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x12AAA, 0x3}, /* Freq 5795 */
+	{160, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x15555, 0x3}, /* Freq 5800 */
+	{161, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x18000, 0x3}, /* Freq 5805 */
+	{162, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x1AAAA, 0x3}, /* Freq 5810 */
+	{163, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x1D555, 0x3}, /* Freq 5815 */
+	{164, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x20000, 0x3}, /* Freq 5820 */
+	{165, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x22AAA, 0x3}, /* Freq 5825 */
+	{166, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x25555, 0x3}, /* Freq 5830 */
+	{167, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x28000, 0x3}, /* Freq 5835 */
+	{168, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x2AAAA, 0x3}, /* Freq 5840 */
+	{169, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x2D555, 0x3}, /* Freq 5845 */
+	{170, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x30000, 0x3}, /* Freq 5850 */
+	{171, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x32AAA, 0x3}, /* Freq 5855 */
+	{172, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x35555, 0x3}, /* Freq 5860 */
+	{173, 	(RF_A_BAND | RF_A_BAND_HB),	 0x02, 0x3F, 0x7F, 0xDD, 0xC3, 0x40, 0x0, 0x80, 0x0, 0/*0 -> 1*/, 0, 0, 0x30, 0, 0x0, 0x8, 0x38000, 0x3}, /* Freq 5865 */
+};
+
+static const u8 mt76x0_sdm_channel[] = {
+	183, 185, 43, 45, 54, 55, 57, 58, 102, 103, 105, 106, 115, 117, 126, 127, 129, 130, 139, 141, 150, 151, 153, 154, 163, 165
+};
+
+static const struct mt76x0_rf_switch_item mt76x0_rf_ext_pa_tab[] = {
+	{ MT_RF(6, 45),		RF_A_BAND_LB,	0x63},
+	{ MT_RF(6, 45),		RF_A_BAND_MB,	0x43},
+	{ MT_RF(6, 45),		RF_A_BAND_HB,	0x33},
+	{ MT_RF(6, 45),		RF_A_BAND_11J,	0x73},
+
+	{ MT_RF(6, 50),		RF_A_BAND_LB,	0x02},
+	{ MT_RF(6, 50),		RF_A_BAND_MB,	0x02},
+	{ MT_RF(6, 50),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 50),		RF_A_BAND_11J,	0x02},
+
+	{ MT_RF(6, 51),		RF_A_BAND_LB,	0x02},
+	{ MT_RF(6, 51),		RF_A_BAND_MB,	0x02},
+	{ MT_RF(6, 51),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 51),		RF_A_BAND_11J,	0x02},
+
+	{ MT_RF(6, 52),		RF_A_BAND_LB,	0x08},
+	{ MT_RF(6, 52),		RF_A_BAND_MB,	0x08},
+	{ MT_RF(6, 52),		RF_A_BAND_HB,	0x08},
+	{ MT_RF(6, 52),		RF_A_BAND_11J,	0x08},
+
+	{ MT_RF(6, 53),		RF_A_BAND_LB,	0x08},
+	{ MT_RF(6, 53),		RF_A_BAND_MB,	0x08},
+	{ MT_RF(6, 53),		RF_A_BAND_HB,	0x08},
+	{ MT_RF(6, 53),		RF_A_BAND_11J,	0x08},
+
+	{ MT_RF(6, 54),		RF_A_BAND_LB,	0x0A},
+	{ MT_RF(6, 54),		RF_A_BAND_MB,	0x0A},
+	{ MT_RF(6, 54),		RF_A_BAND_HB,	0x0A},
+	{ MT_RF(6, 54),		RF_A_BAND_11J,	0x0A},
+
+	{ MT_RF(6, 55),		RF_A_BAND_LB,	0x0A},
+	{ MT_RF(6, 55),		RF_A_BAND_MB,	0x0A},
+	{ MT_RF(6, 55),		RF_A_BAND_HB,	0x0A},
+	{ MT_RF(6, 55),		RF_A_BAND_11J,	0x0A},
+
+	{ MT_RF(6, 56),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 56),		RF_A_BAND_MB,	0x05},
+	{ MT_RF(6, 56),		RF_A_BAND_HB,	0x05},
+	{ MT_RF(6, 56),		RF_A_BAND_11J,	0x05},
+
+	{ MT_RF(6, 57),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 57),		RF_A_BAND_MB,	0x05},
+	{ MT_RF(6, 57),		RF_A_BAND_HB,	0x05},
+	{ MT_RF(6, 57),		RF_A_BAND_11J,	0x05},
+
+	{ MT_RF(6, 58),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 58),		RF_A_BAND_MB,	0x03},
+	{ MT_RF(6, 58),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 58),		RF_A_BAND_11J,	0x07},
+
+	{ MT_RF(6, 59),		RF_A_BAND_LB,	0x05},
+	{ MT_RF(6, 59),		RF_A_BAND_MB,	0x03},
+	{ MT_RF(6, 59),		RF_A_BAND_HB,	0x02},
+	{ MT_RF(6, 59),		RF_A_BAND_11J,	0x07},
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
new file mode 100644
index 000000000000..e52a50661b1a
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -0,0 +1,1008 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "mcu.h"
+#include "eeprom.h"
+#include "trace.h"
+#include "phy.h"
+#include "initvals.h"
+#include "initvals_phy.h"
+
+#include <linux/etherdevice.h>
+
+static int
+mt76x0_rf_csr_wr(struct mt76x0_dev *dev, u32 offset, u8 value)
+{
+	int ret = 0;
+	u8 bank, reg;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return -ENODEV;
+
+	bank = MT_RF_BANK(offset);
+	reg = MT_RF_REG(offset);
+
+	if (WARN_ON_ONCE(reg > 64) || WARN_ON_ONCE(bank) > 8)
+		return -EINVAL;
+
+	mutex_lock(&dev->reg_atomic_mutex);
+
+	if (!mt76_poll(dev, MT_RF_CSR_CFG, MT_RF_CSR_CFG_KICK, 0, 100)) {
+		ret = -ETIMEDOUT;
+		goto out;
+	}
+
+	mt76_wr(dev, MT_RF_CSR_CFG,
+		   FIELD_PREP(MT_RF_CSR_CFG_DATA, value) |
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
+		   MT_RF_CSR_CFG_WR |
+		   MT_RF_CSR_CFG_KICK);
+	trace_rf_write(&dev->mt76, bank, offset, value);
+out:
+	mutex_unlock(&dev->reg_atomic_mutex);
+
+	if (ret < 0)
+		dev_err(dev->mt76.dev, "Error: RF write %d:%d failed:%d!!\n",
+			bank, reg, ret);
+
+	return ret;
+}
+
+static int
+mt76x0_rf_csr_rr(struct mt76x0_dev *dev, u32 offset)
+{
+	int ret = -ETIMEDOUT;
+	u32 val;
+	u8 bank, reg;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return -ENODEV;
+
+	bank = MT_RF_BANK(offset);
+	reg = MT_RF_REG(offset);
+
+	if (WARN_ON_ONCE(reg > 64) || WARN_ON_ONCE(bank) > 8)
+		return -EINVAL;
+
+	mutex_lock(&dev->reg_atomic_mutex);
+
+	if (!mt76_poll(dev, MT_RF_CSR_CFG, MT_RF_CSR_CFG_KICK, 0, 100))
+		goto out;
+
+	mt76_wr(dev, MT_RF_CSR_CFG,
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_BANK, bank) |
+		   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
+		   MT_RF_CSR_CFG_KICK);
+
+	if (!mt76_poll(dev, MT_RF_CSR_CFG, MT_RF_CSR_CFG_KICK, 0, 100))
+		goto out;
+
+	val = mt76_rr(dev, MT_RF_CSR_CFG);
+	if (FIELD_GET(MT_RF_CSR_CFG_REG_ID, val) == reg &&
+	    FIELD_GET(MT_RF_CSR_CFG_REG_BANK, val) == bank) {
+		ret = FIELD_GET(MT_RF_CSR_CFG_DATA, val);
+		trace_rf_read(&dev->mt76, bank, offset, ret);
+	}
+out:
+	mutex_unlock(&dev->reg_atomic_mutex);
+
+	if (ret < 0)
+		dev_err(dev->mt76.dev, "Error: RF read %d:%d failed:%d!!\n",
+			bank, reg, ret);
+
+	return ret;
+}
+
+static int
+rf_wr(struct mt76x0_dev *dev, u32 offset, u8 val)
+{
+	if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state)) {
+		struct mt76_reg_pair pair = {
+			.reg = offset,
+			.value = val,
+		};
+
+		return mt76x0_write_reg_pairs(dev, MT_MCU_MEMMAP_RF, &pair, 1);
+	} else {
+		WARN_ON_ONCE(1);
+		return mt76x0_rf_csr_wr(dev, offset, val);
+	}
+}
+
+static int
+rf_rr(struct mt76x0_dev *dev, u32 offset)
+{
+	int ret;
+	u32 val;
+
+	if (test_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state)) {
+		struct mt76_reg_pair pair = {
+			.reg = offset,
+		};
+
+		ret = mt76x0_read_reg_pairs(dev, MT_MCU_MEMMAP_RF, &pair, 1);
+		val = pair.value;
+	} else {
+		WARN_ON_ONCE(1);
+		ret = val = mt76x0_rf_csr_rr(dev, offset);
+	}
+
+	return (ret < 0) ? ret : val;
+}
+
+static int
+rf_rmw(struct mt76x0_dev *dev, u32 offset, u8 mask, u8 val)
+{
+	int ret;
+
+	ret = rf_rr(dev, offset);
+	if (ret < 0)
+		return ret;
+	val |= ret & ~mask;
+	ret = rf_wr(dev, offset, val);
+	if (ret)
+		return ret;
+
+	return val;
+}
+
+static int
+rf_set(struct mt76x0_dev *dev, u32 offset, u8 val)
+{
+	return rf_rmw(dev, offset, 0, val);
+}
+
+#if 0
+static int
+rf_clear(struct mt76x0_dev *dev, u32 offset, u8 mask)
+{
+	return rf_rmw(dev, offset, mask, 0);
+}
+#endif
+
+#define RF_RANDOM_WRITE(dev, tab) \
+	mt76x0_write_reg_pairs(dev, MT_MCU_MEMMAP_RF, tab, ARRAY_SIZE(tab));
+
+int mt76x0_wait_bbp_ready(struct mt76x0_dev *dev)
+{
+	int i = 20;
+	u32 val;
+
+	do {
+		val = mt76_rr(dev, MT_BBP(CORE, 0));
+		printk("BBP version %08x\n", val);
+		if (val && ~val)
+			break;
+	} while (--i);
+
+	if (!i) {
+		dev_err(dev->mt76.dev, "Error: BBP is not ready\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+static void
+mt76x0_bbp_set_ctrlch(struct mt76x0_dev *dev, enum nl80211_chan_width width,
+		      u8 ctrl)
+{
+	int core_val, agc_val;
+
+	switch (width) {
+	case NL80211_CHAN_WIDTH_80:
+		core_val = 3;
+		agc_val = 7;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		core_val = 2;
+		agc_val = 3;
+		break;
+	default:
+		core_val = 0;
+		agc_val = 1;
+		break;
+	}
+
+	mt76_rmw_field(dev, MT_BBP(CORE, 1), MT_BBP_CORE_R1_BW, core_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_BW, agc_val);
+	mt76_rmw_field(dev, MT_BBP(AGC, 0), MT_BBP_AGC_R0_CTRL_CHAN, ctrl);
+	mt76_rmw_field(dev, MT_BBP(TXBE, 0), MT_BBP_TXBE_R0_CTRL_CHAN, ctrl);
+}
+
+int mt76x0_phy_get_rssi(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi)
+{
+	s8 lna_gain, rssi_offset;
+	int val;
+
+	if (dev->mt76.chandef.chan->band == NL80211_BAND_2GHZ) {
+		lna_gain = dev->ee->lna_gain_2ghz;
+		rssi_offset = dev->ee->rssi_offset_2ghz[0];
+	} else {
+		lna_gain = dev->ee->lna_gain_5ghz[0];
+		rssi_offset = dev->ee->rssi_offset_5ghz[0];
+	}
+
+	val = rxwi->rssi[0] + rssi_offset - lna_gain;
+
+	return val;
+}
+
+static void mt76x0_vco_cal(struct mt76x0_dev *dev, u8 channel)
+{
+	u8 val;
+
+	val = rf_rr(dev, MT_RF(0, 4));
+	if ((val & 0x70) != 0x30)
+		return;
+
+	/*
+	 * Calibration Mode - Open loop, closed loop, and amplitude:
+	 * B0.R06.[0]: 1
+	 * B0.R06.[3:1] bp_close_code: 100
+	 * B0.R05.[7:0] bp_open_code: 0x0
+	 * B0.R04.[2:0] cal_bits: 000
+	 * B0.R03.[2:0] startup_time: 011
+	 * B0.R03.[6:4] settle_time:
+	 *  80MHz channel: 110
+	 *  40MHz channel: 101
+	 *  20MHz channel: 100
+	 */
+	val = rf_rr(dev, MT_RF(0, 6));
+	val &= ~0xf;
+	val |= 0x09;
+	rf_wr(dev, MT_RF(0, 6), val);
+
+	val = rf_rr(dev, MT_RF(0, 5));
+	if (val != 0)
+		rf_wr(dev, MT_RF(0, 5), 0x0);
+
+	val = rf_rr(dev, MT_RF(0, 4));
+	val &= ~0x07;
+	rf_wr(dev, MT_RF(0, 4), val);
+
+	val = rf_rr(dev, MT_RF(0, 3));
+	val &= ~0x77;
+	if (channel == 1 || channel == 7 || channel == 9 || channel >= 13) {
+		val |= 0x63;
+	} else if (channel == 3 || channel == 4 || channel == 10) {
+		val |= 0x53;
+	} else if (channel == 2 || channel == 5 || channel == 6 ||
+		   channel == 8 || channel == 11 || channel == 12) {
+		val |= 0x43;
+	} else {
+		WARN(1, "Unknown channel %u\n", channel);
+		return;
+	}
+	rf_wr(dev, MT_RF(0, 3), val);
+
+	/* TODO replace by mt76x0_rf_set(dev, MT_RF(0, 4), BIT(7)); */
+	val = rf_rr(dev, MT_RF(0, 4));
+	val = ((val & ~(0x80)) | 0x80);
+	rf_wr(dev, MT_RF(0, 4), val);
+
+	msleep(2);
+}
+
+static void
+mt76x0_mac_set_ctrlch(struct mt76x0_dev *dev, bool primary_upper)
+{
+	mt76_rmw_field(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_UPPER_40M,
+		       primary_upper);
+}
+
+static void
+mt76x0_phy_set_band(struct mt76x0_dev *dev, enum nl80211_band band)
+{
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		RF_RANDOM_WRITE(dev, mt76x0_rf_2g_channel_0_tab);
+
+		rf_wr(dev, MT_RF(5, 0), 0x45);
+		rf_wr(dev, MT_RF(6, 0), 0x44);
+
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+
+		mt76_wr(dev, MT_TX_ALC_VGA3, 0x00050007);
+		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x003E0002);
+		break;
+	case NL80211_BAND_5GHZ:
+		RF_RANDOM_WRITE(dev, mt76x0_rf_5g_channel_0_tab);
+
+		rf_wr(dev, MT_RF(5, 0), 0x44);
+		rf_wr(dev, MT_RF(6, 0), 0x45);
+
+		mt76_clear(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_2G);
+		mt76_set(dev, MT_TX_BAND_CFG, MT_TX_BAND_CFG_5G);
+
+		mt76_wr(dev, MT_TX_ALC_VGA3, 0x00000005);
+		mt76_wr(dev, MT_TX0_RF_GAIN_CORR, 0x01010102);
+		break;
+	default:
+		break;
+	}
+}
+
+#define EXT_PA_2G_5G            0x0
+#define EXT_PA_5G_ONLY          0x1
+#define EXT_PA_2G_ONLY          0x2
+#define INT_PA_2G_5G            0x3
+
+static void
+mt76x0_phy_set_chan_rf_params(struct mt76x0_dev *dev, u8 channel, u16 rf_bw_band)
+{
+	u16 rf_band = rf_bw_band & 0xff00;
+	u16 rf_bw = rf_bw_band & 0x00ff;
+	u32 mac_reg;
+	u8 rf_val;
+	int i;
+	bool bSDM = false;
+	const struct mt76x0_freq_item *freq_item;
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_sdm_channel); i++) {
+		if (channel == mt76x0_sdm_channel[i]) {
+			bSDM = true;
+			break;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_frequency_plan); i++) {
+		if (channel == mt76x0_frequency_plan[i].channel) {
+			rf_band = mt76x0_frequency_plan[i].band;
+
+			if (bSDM)
+				freq_item = &(mt76x0_sdm_frequency_plan[i]);
+			else
+				freq_item = &(mt76x0_frequency_plan[i]);
+
+			rf_wr(dev, MT_RF(0, 37), freq_item->pllR37);
+			rf_wr(dev, MT_RF(0, 36), freq_item->pllR36);
+			rf_wr(dev, MT_RF(0, 35), freq_item->pllR35);
+			rf_wr(dev, MT_RF(0, 34), freq_item->pllR34);
+			rf_wr(dev, MT_RF(0, 33), freq_item->pllR33);
+
+			rf_val = rf_rr(dev, MT_RF(0, 32));
+			rf_val &= ~0xE0;
+			rf_val |= freq_item->pllR32_b7b5;
+			rf_wr(dev, MT_RF(0, 32), rf_val);
+
+			/* R32<4:0> pll_den: (Denomina - 8) */
+			rf_val = rf_rr(dev, MT_RF(0, 32));
+			rf_val &= ~0x1F;
+			rf_val |= freq_item->pllR32_b4b0;
+			rf_wr(dev, MT_RF(0, 32), rf_val);
+
+			/* R31<7:5> */
+			rf_val = rf_rr(dev, MT_RF(0, 31));
+			rf_val &= ~0xE0;
+			rf_val |= freq_item->pllR31_b7b5;
+			rf_wr(dev, MT_RF(0, 31), rf_val);
+
+			/* R31<4:0> pll_k(Nominator) */
+			rf_val = rf_rr(dev, MT_RF(0, 31));
+			rf_val &= ~0x1F;
+			rf_val |= freq_item->pllR31_b4b0;
+			rf_wr(dev, MT_RF(0, 31), rf_val);
+
+			/* R30<7> sdm_reset_n */
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x80;
+			if (bSDM) {
+				rf_wr(dev, MT_RF(0, 30), rf_val);
+				rf_val |= 0x80;
+				rf_wr(dev, MT_RF(0, 30), rf_val);
+			} else {
+				rf_val |= freq_item->pllR30_b7;
+				rf_wr(dev, MT_RF(0, 30), rf_val);
+			}
+
+			/* R30<6:2> sdmmash_prbs,sin */
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x7C;
+			rf_val |= freq_item->pllR30_b6b2;
+			rf_wr(dev, MT_RF(0, 30), rf_val);
+
+			/* R30<1> sdm_bp */
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x02;
+			rf_val |= (freq_item->pllR30_b1 << 1);
+			rf_wr(dev, MT_RF(0, 30), rf_val);
+
+			/* R30<0> R29<7:0> (hex) pll_n */
+			rf_val = freq_item->pll_n & 0x00FF;
+			rf_wr(dev, MT_RF(0, 29), rf_val);
+
+			rf_val = rf_rr(dev, MT_RF(0, 30));
+			rf_val &= ~0x1;
+			rf_val |= ((freq_item->pll_n >> 8) & 0x0001);
+			rf_wr(dev, MT_RF(0, 30), rf_val);
+
+			/* R28<7:6> isi_iso */
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0xC0;
+			rf_val |= freq_item->pllR28_b7b6;
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R28<5:4> pfd_dly */
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0x30;
+			rf_val |= freq_item->pllR28_b5b4;
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R28<3:2> clksel option */
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0x0C;
+			rf_val |= freq_item->pllR28_b3b2;
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R28<1:0> R27<7:0> R26<7:0> (hex) sdm_k */
+			rf_val = freq_item->pll_sdm_k & 0x000000FF;
+			rf_wr(dev, MT_RF(0, 26), rf_val);
+
+			rf_val = ((freq_item->pll_sdm_k >> 8) & 0x000000FF);
+			rf_wr(dev, MT_RF(0, 27), rf_val);
+
+			rf_val = rf_rr(dev, MT_RF(0, 28));
+			rf_val &= ~0x3;
+			rf_val |= ((freq_item->pll_sdm_k >> 16) & 0x0003);
+			rf_wr(dev, MT_RF(0, 28), rf_val);
+
+			/* R24<1:0> xo_div */
+			rf_val = rf_rr(dev, MT_RF(0, 24));
+			rf_val &= ~0x3;
+			rf_val |= freq_item->pllR24_b1b0;
+			rf_wr(dev, MT_RF(0, 24), rf_val);
+
+			break;
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_bw_switch_tab); i++) {
+		if (rf_bw == mt76x0_rf_bw_switch_tab[i].bw_band) {
+			rf_wr(dev, mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
+				   mt76x0_rf_bw_switch_tab[i].value);
+		} else if ((rf_bw == (mt76x0_rf_bw_switch_tab[i].bw_band & 0xFF)) &&
+			   (rf_band & mt76x0_rf_bw_switch_tab[i].bw_band)) {
+			rf_wr(dev, mt76x0_rf_bw_switch_tab[i].rf_bank_reg,
+				   mt76x0_rf_bw_switch_tab[i].value);
+		}
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_band_switch_tab); i++) {
+		if (mt76x0_rf_band_switch_tab[i].bw_band & rf_band) {
+			rf_wr(dev, mt76x0_rf_band_switch_tab[i].rf_bank_reg,
+				   mt76x0_rf_band_switch_tab[i].value);
+		}
+	}
+
+	mac_reg = mt76_rr(dev, MT_RF_MISC);
+	mac_reg &= ~0xC; /* Clear 0x518[3:2] */
+	mt76_wr(dev, MT_RF_MISC, mac_reg);
+
+	if (dev->ee->pa_type == INT_PA_2G_5G ||
+	    (dev->ee->pa_type == EXT_PA_5G_ONLY && (rf_band & RF_G_BAND)) ||
+	    (dev->ee->pa_type == EXT_PA_2G_ONLY && (rf_band & RF_A_BAND))) {
+		; /* Internal PA - nothing to do. */
+	} else {
+		/*
+			MT_RF_MISC (offset: 0x0518)
+			[2]1'b1: enable external A band PA, 1'b0: disable external A band PA
+			[3]1'b1: enable external G band PA, 1'b0: disable external G band PA
+		*/
+		if (rf_band & RF_A_BAND) {
+			mac_reg = mt76_rr(dev, MT_RF_MISC);
+			mac_reg |= 0x4;
+			mt76_wr(dev, MT_RF_MISC, mac_reg);
+		} else {
+			mac_reg = mt76_rr(dev, MT_RF_MISC);
+			mac_reg |= 0x8;
+			mt76_wr(dev, MT_RF_MISC, mac_reg);
+		}
+
+		/* External PA */
+		for (i = 0; i < ARRAY_SIZE(mt76x0_rf_ext_pa_tab); i++)
+			if (mt76x0_rf_ext_pa_tab[i].bw_band & rf_band)
+				rf_wr(dev, mt76x0_rf_ext_pa_tab[i].rf_bank_reg,
+					   mt76x0_rf_ext_pa_tab[i].value);
+	}
+
+	if (rf_band & RF_G_BAND) {
+		mt76_wr(dev, MT_TX0_RF_GAIN_ATTEN, 0x63707400);
+		/* Set Atten mode = 2 For G band, Disable Tx Inc dcoc. */
+		mac_reg = mt76_rr(dev, MT_TX_ALC_CFG_1);
+		mac_reg &= 0x896400FF;
+		mt76_wr(dev, MT_TX_ALC_CFG_1, mac_reg);
+	} else {
+		mt76_wr(dev, MT_TX0_RF_GAIN_ATTEN, 0x686A7800);
+		/* Set Atten mode = 0 For Ext A band, Disable Tx Inc dcoc Cal. */
+		mac_reg = mt76_rr(dev, MT_TX_ALC_CFG_1);
+		mac_reg &= 0x890400FF;
+		mt76_wr(dev, MT_TX_ALC_CFG_1, mac_reg);
+	}
+}
+
+static void
+mt76x0_phy_set_chan_bbp_params(struct mt76x0_dev *dev, u8 channel, u16 rf_bw_band)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_bbp_switch_tab); i++) {
+		const struct mt76x0_bbp_switch_item *item = &mt76x0_bbp_switch_tab[i];
+		const struct mt76_reg_pair *pair = &item->reg_pair;
+
+		if ((rf_bw_band & item->bw_band) != rf_bw_band)
+			continue;
+
+		if (pair->reg == MT_BBP(AGC, 8)) {
+			u32 val = pair->value;
+			u8 gain = FIELD_GET(MT_BBP_AGC_GAIN, val);
+
+			if (channel > 14) {
+				if (channel < 100)
+					gain -= dev->ee->lna_gain_5ghz[0]*2;
+				else if (channel < 137)
+					gain -= dev->ee->lna_gain_5ghz[1]*2;
+				else
+					gain -= dev->ee->lna_gain_5ghz[2]*2;
+
+			} else {
+				gain -= dev->ee->lna_gain_2ghz*2;
+			}
+
+			val &= ~MT_BBP_AGC_GAIN;
+			val |= FIELD_PREP(MT_BBP_AGC_GAIN, gain);
+			mt76_wr(dev, pair->reg, val);
+		} else {
+			mt76_wr(dev, pair->reg, pair->value);
+		}
+	}
+}
+
+#if 0
+static void
+mt76x0_extra_power_over_mac(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = ((mt76_rr(dev, MT_TX_PWR_CFG_1) & 0x00003f00) >> 8);
+	val |= ((mt76_rr(dev, MT_TX_PWR_CFG_2) & 0x00003f00) << 8);
+	mt76_wr(dev, MT_TX_PWR_CFG_7, val);
+
+	/* TODO: fix VHT */
+	val = ((mt76_rr(dev, MT_TX_PWR_CFG_3) & 0x0000ff00) >> 8);
+	mt76_wr(dev, MT_TX_PWR_CFG_8, val);
+
+	val = ((mt76_rr(dev, MT_TX_PWR_CFG_4) & 0x0000ff00) >> 8);
+	mt76_wr(dev, MT_TX_PWR_CFG_9, val);
+}
+
+static void
+mt76x0_phy_set_tx_power(struct mt76x0_dev *dev, u8 channel, u8 rf_bw_band)
+{
+	u32 val;
+	int i;
+	int bw = (rf_bw_band & RF_BW_20) ? 0 : 1;
+
+	for (i = 0; i < 4; i++) {
+		if (channel <= 14)
+			val = dev->ee->tx_pwr_cfg_2g[i][bw];
+		else
+			val = dev->ee->tx_pwr_cfg_5g[i][bw];
+
+		mt76_wr(dev, MT_TX_PWR_CFG_0 + 4*i, val);
+	}
+
+	mt76x0_extra_power_over_mac(dev);
+}
+#endif
+
+static void
+mt76x0_bbp_set_bw(struct mt76x0_dev *dev, enum nl80211_chan_width width)
+{
+	enum { BW_20 = 0, BW_40 = 1, BW_80 = 2, BW_10 = 4};
+	int bw;
+
+	switch (width) {
+	default:
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+		bw = BW_20;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		bw = BW_40;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		bw = BW_80;
+		break;
+	case NL80211_CHAN_WIDTH_10:
+		bw = BW_10;
+		break;
+	case NL80211_CHAN_WIDTH_80P80:
+	case NL80211_CHAN_WIDTH_160:
+	case NL80211_CHAN_WIDTH_5:
+		/* TODO error */
+		return ;
+	}
+
+	mt76x0_mcu_function_select(dev, BW_SETTING, bw);
+}
+
+static void
+mt76x0_phy_set_chan_pwr(struct mt76x0_dev *dev, u8 channel)
+{
+	static const int mt76x0_tx_pwr_ch_list[] = {
+		1,2,3,4,5,6,7,8,9,10,11,12,13,14,
+		36,38,40,44,46,48,52,54,56,60,62,64,
+		100,102,104,108,110,112,116,118,120,124,126,128,132,134,136,140,
+		149,151,153,157,159,161,165,167,169,171,173,
+		42,58,106,122,155
+	};
+	int i;
+	u32 val;
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_tx_pwr_ch_list); i++)
+		if (mt76x0_tx_pwr_ch_list[i] == channel)
+			break;
+
+	if (WARN_ON(i == ARRAY_SIZE(mt76x0_tx_pwr_ch_list)))
+		return;
+
+	val = mt76_rr(dev, MT_TX_ALC_CFG_0);
+	val &= ~0x3f3f;
+	val |= dev->ee->tx_pwr_per_chan[i];
+	val |= 0x2f2f << 16;
+	mt76_wr(dev, MT_TX_ALC_CFG_0, val);
+}
+
+static int
+__mt76x0_phy_set_channel(struct mt76x0_dev *dev,
+		       struct cfg80211_chan_def *chandef)
+{
+	u32 ext_cca_chan[4] = {
+		[0] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(0)),
+		[1] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(1)),
+		[2] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(2)),
+		[3] = FIELD_PREP(MT_EXT_CCA_CFG_CCA0, 3) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA1, 2) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA2, 1) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA3, 0) |
+		      FIELD_PREP(MT_EXT_CCA_CFG_CCA_MASK, BIT(3)),
+	};
+	bool scan = test_bit(MT76_SCANNING, &dev->mt76.state);
+	int ch_group_index, freq, freq1;
+	u8 channel;
+	u32 val;
+	u16 rf_bw_band;
+
+	freq = chandef->chan->center_freq;
+	freq1 = chandef->center_freq1;
+	channel = chandef->chan->hw_value;
+	rf_bw_band = (channel <= 14) ? RF_G_BAND : RF_A_BAND;
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_40:
+		if (freq1 > freq)
+			ch_group_index = 0;
+		else
+			ch_group_index = 1;
+		channel += 2 - ch_group_index * 4;
+		rf_bw_band |= RF_BW_40;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		ch_group_index = (freq - freq1 + 30) / 20;
+		if (WARN_ON(ch_group_index < 0 || ch_group_index > 3))
+			ch_group_index = 0;
+		channel += 6 - ch_group_index * 4;
+		rf_bw_band |= RF_BW_80;
+		break;
+	default:
+		ch_group_index = 0;
+		rf_bw_band |= RF_BW_20;
+		break;
+	}
+
+	mt76x0_bbp_set_bw(dev, chandef->width);
+	mt76x0_bbp_set_ctrlch(dev, chandef->width, ch_group_index);
+	mt76x0_mac_set_ctrlch(dev, ch_group_index & 1);
+
+	mt76_rmw(dev, MT_EXT_CCA_CFG,
+		 (MT_EXT_CCA_CFG_CCA0 |
+		  MT_EXT_CCA_CFG_CCA1 |
+		  MT_EXT_CCA_CFG_CCA2 |
+		  MT_EXT_CCA_CFG_CCA3 |
+		  MT_EXT_CCA_CFG_CCA_MASK),
+		 ext_cca_chan[ch_group_index]);
+
+	mt76x0_phy_set_band(dev, chandef->chan->band);
+	mt76x0_phy_set_chan_rf_params(dev, channel, rf_bw_band);
+
+	/* set Japan Tx filter at channel 14 */
+	val = mt76_rr(dev, MT_BBP(CORE, 1));
+	if (channel == 14)
+		val |= 0x20;
+	else
+		val &= ~0x20;
+	mt76_wr(dev, MT_BBP(CORE, 1), val);
+
+	mt76x0_phy_set_chan_bbp_params(dev, channel, rf_bw_band);
+
+	/* Vendor driver don't do it */
+	/* mt76x0_phy_set_tx_power(dev, channel, rf_bw_band); */
+
+	if (scan)
+		mt76x0_vco_cal(dev, channel);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1);
+	mt76x0_phy_set_chan_pwr(dev, channel);
+
+	dev->mt76.chandef = *chandef;
+	return 0;
+}
+
+int mt76x0_phy_set_channel(struct mt76x0_dev *dev,
+			   struct cfg80211_chan_def *chandef)
+{
+	int ret;
+
+	mutex_lock(&dev->hw_atomic_mutex);
+	ret = __mt76x0_phy_set_channel(dev, chandef);
+	mutex_unlock(&dev->hw_atomic_mutex);
+
+	return ret;
+}
+
+void mt76x0_phy_recalibrate_after_assoc(struct mt76x0_dev *dev)
+{
+	u32 tx_alc, reg_val;
+	u8 channel = dev->mt76.chandef.chan->hw_value;
+	int is_5ghz = (dev->mt76.chandef.chan->band == NL80211_BAND_5GHZ) ? 1 : 0;
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_R, 0);
+
+	mt76x0_vco_cal(dev, channel);
+
+	tx_alc = mt76_rr(dev, MT_TX_ALC_CFG_0);
+	mt76_wr(dev, MT_TX_ALC_CFG_0, 0);
+	usleep_range(500, 700);
+
+	reg_val = mt76_rr(dev, 0x2124);
+	reg_val &= 0xffffff7e;
+	mt76_wr(dev, 0x2124, reg_val);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXDCOC, 0);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_LC, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_LOFT, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_TXIQ, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_TX_GROUP_DELAY, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXIQ, is_5ghz);
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RX_GROUP_DELAY, is_5ghz);
+
+	mt76_wr(dev, 0x2124, reg_val);
+	mt76_wr(dev, MT_TX_ALC_CFG_0, tx_alc);
+	msleep(100);
+
+	mt76x0_mcu_calibrate(dev, MCU_CAL_RXDCOC, 1);
+}
+
+void mt76x0_agc_save(struct mt76x0_dev *dev)
+{
+	/* Only one RX path */
+	dev->agc_save = FIELD_GET(MT_BBP_AGC_GAIN, mt76_rr(dev, MT_BBP(AGC, 8)));
+}
+
+void mt76x0_agc_restore(struct mt76x0_dev *dev)
+{
+	mt76_rmw_field(dev, MT_BBP(AGC, 8), MT_BBP_AGC_GAIN, dev->agc_save);
+}
+
+static void mt76x0_temp_sensor(struct mt76x0_dev *dev)
+{
+	u8 rf_b7_73, rf_b0_66, rf_b0_67;
+	int cycle, temp;
+	u32 val;
+	s32 sval;
+
+	rf_b7_73 = rf_rr(dev, MT_RF(7, 73));
+	rf_b0_66 = rf_rr(dev, MT_RF(0, 66));
+	rf_b0_67 = rf_rr(dev, MT_RF(0, 73));
+
+	rf_wr(dev, MT_RF(7, 73), 0x02);
+	rf_wr(dev, MT_RF(0, 66), 0x23);
+	rf_wr(dev, MT_RF(0, 73), 0x01);
+
+	mt76_wr(dev, MT_BBP(CORE, 34), 0x00080055);
+
+	for (cycle = 0; cycle < 2000; cycle++) {
+		val = mt76_rr(dev, MT_BBP(CORE, 34));
+		if (!(val & 0x10))
+			break;
+		udelay(3);
+	}
+
+	if (cycle >= 2000) {
+		val &= 0x10;
+		mt76_wr(dev, MT_BBP(CORE, 34), val);
+		goto done;
+	}
+
+	sval = mt76_rr(dev, MT_BBP(CORE, 35)) & 0xff;
+	if (!(sval & 0x80))
+		sval &= 0x7f; /* Positive */
+	else
+		sval |= 0xffffff00; /* Negative */
+
+	temp = (35 * (sval - dev->ee->temp_off))/ 10 + 25;
+
+done:
+	rf_wr(dev, MT_RF(7, 73), rf_b7_73);
+	rf_wr(dev, MT_RF(0, 66), rf_b0_66);
+	rf_wr(dev, MT_RF(0, 73), rf_b0_67);
+}
+
+static void mt76x0_dynamic_vga_tuning(struct mt76x0_dev *dev)
+{
+	u32 val, init_vga;
+
+	init_vga = (dev->mt76.chandef.chan->band == NL80211_BAND_5GHZ) ? 0x54 : 0x4E;
+	if (dev->avg_rssi > -60)
+		init_vga -= 0x20;
+	else if (dev->avg_rssi > -70)
+		init_vga -= 0x10;
+
+	val = mt76_rr(dev, MT_BBP(AGC, 8));
+	val &= 0xFFFF80FF;
+	val |= init_vga << 8;
+	mt76_wr(dev, MT_BBP(AGC,8), val);
+}
+
+static void mt76x0_phy_calibrate(struct work_struct *work)
+{
+	struct mt76x0_dev *dev = container_of(work, struct mt76x0_dev,
+					    cal_work.work);
+
+	mt76x0_dynamic_vga_tuning(dev);
+	mt76x0_temp_sensor(dev);
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+}
+
+void mt76x0_phy_con_cal_onoff(struct mt76x0_dev *dev,
+			       struct ieee80211_bss_conf *info)
+{
+	/* Start/stop collecting beacon data */
+	spin_lock_bh(&dev->con_mon_lock);
+	ether_addr_copy(dev->ap_bssid, info->bssid);
+	dev->avg_rssi = 0;
+	dev->bcn_freq_off = MT_FREQ_OFFSET_INVALID;
+	spin_unlock_bh(&dev->con_mon_lock);
+}
+
+static void
+mt76x0_set_rx_chains(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_BBP(AGC, 0));
+	val &= ~(BIT(3) | BIT(4));
+
+	if (dev->chainmask & BIT(1))
+		val |= BIT(3);
+
+	mt76_wr(dev, MT_BBP(AGC, 0), val);
+
+	mb();
+	val = mt76_rr(dev, MT_BBP(AGC, 0));
+}
+
+static void
+mt76x0_set_tx_dac(struct mt76x0_dev *dev)
+{
+	if (dev->chainmask & BIT(1))
+		mt76_set(dev, MT_BBP(TXBE, 5), 3);
+	else
+		mt76_clear(dev, MT_BBP(TXBE, 5), 3);
+}
+
+static void
+mt76x0_rf_init(struct mt76x0_dev *dev)
+{
+	int i;
+	u8 val;
+
+	RF_RANDOM_WRITE(dev, mt76x0_rf_central_tab);
+	RF_RANDOM_WRITE(dev, mt76x0_rf_2g_channel_0_tab);
+	RF_RANDOM_WRITE(dev, mt76x0_rf_5g_channel_0_tab);
+	RF_RANDOM_WRITE(dev, mt76x0_rf_vga_channel_0_tab);
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_bw_switch_tab); i++) {
+		const struct mt76x0_rf_switch_item *item = &mt76x0_rf_bw_switch_tab[i];
+
+		if (item->bw_band == RF_BW_20)
+			rf_wr(dev, item->rf_bank_reg, item->value);
+		else if (((RF_G_BAND | RF_BW_20) & item->bw_band) == (RF_G_BAND | RF_BW_20))
+			rf_wr(dev, item->rf_bank_reg, item->value);
+	}
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_rf_band_switch_tab); i++) {
+		if (mt76x0_rf_band_switch_tab[i].bw_band & RF_G_BAND) {
+			rf_wr(dev,
+			      mt76x0_rf_band_switch_tab[i].rf_bank_reg,
+			      mt76x0_rf_band_switch_tab[i].value);
+		}
+	}
+
+	/*
+	   Frequency calibration
+	   E1: B0.R22<6:0>: xo_cxo<6:0>
+	   E2: B0.R21<0>: xo_cxo<0>, B0.R22<7:0>: xo_cxo<8:1>
+	 */
+	rf_wr(dev, MT_RF(0, 22), min_t(u8, dev->ee->rf_freq_off, 0xBF));
+	val = rf_rr(dev, MT_RF(0, 22));
+
+	/*
+	   Reset the DAC (Set B0.R73<7>=1, then set B0.R73<7>=0, and then set B0.R73<7>) during power up.
+	 */
+	val = rf_rr(dev, MT_RF(0, 73));
+	val |= 0x80;
+	rf_wr(dev, MT_RF(0, 73), val);
+	val &= ~0x80;
+	rf_wr(dev, MT_RF(0, 73), val);
+	val |= 0x80;
+	rf_wr(dev, MT_RF(0, 73), val);
+
+	/*
+	   vcocal_en (initiate VCO calibration (reset after completion)) - It should be at the end of RF configuration.
+	 */
+	rf_set(dev, MT_RF(0, 4), 0x80);
+}
+
+static void mt76x0_ant_select(struct mt76x0_dev *dev)
+{
+	/* Single antenna mode. */
+	mt76_rmw(dev, MT_WLAN_FUN_CTRL, BIT(5), BIT(6));
+	mt76_clear(dev, MT_CMB_CTRL, BIT(14) | BIT(12));
+	mt76_clear(dev, MT_COEXCFG0, BIT(2));
+	mt76_rmw(dev, MT_COEXCFG3, BIT(5) | BIT(4) | BIT(3) | BIT(2), BIT(1));
+}
+
+void mt76x0_phy_init(struct mt76x0_dev *dev)
+{
+	INIT_DELAYED_WORK(&dev->cal_work, mt76x0_phy_calibrate);
+
+	mt76x0_ant_select(dev);
+
+	mt76x0_rf_init(dev);
+
+	mt76x0_set_rx_chains(dev);
+	mt76x0_set_tx_dac(dev);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h
new file mode 100644
index 000000000000..2880a43c3cb0
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.h
@@ -0,0 +1,81 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#ifndef _MT76X0_PHY_H_
+#define _MT76X0_PHY_H_
+
+#define RF_G_BAND 	0x0100
+#define RF_A_BAND 	0x0200
+#define RF_A_BAND_LB	0x0400
+#define RF_A_BAND_MB	0x0800
+#define RF_A_BAND_HB	0x1000
+#define RF_A_BAND_11J	0x2000
+
+#define RF_BW_20        1
+#define RF_BW_40        2
+#define RF_BW_10        4
+#define RF_BW_80        8
+
+#define MT_RF(bank, reg) ((bank) << 16 | (reg))
+#define MT_RF_BANK(offset) (offset >> 16)
+#define MT_RF_REG(offset) (offset & 0xff)
+
+struct mt76x0_bbp_switch_item {
+	u16 bw_band;
+	struct mt76_reg_pair reg_pair;
+};
+
+struct mt76x0_rf_switch_item {
+	u32 rf_bank_reg;
+	u16 bw_band;
+	u8 value;
+};
+
+struct mt76x0_freq_item {
+	u8 channel;
+	u32 band;
+	u8 pllR37;
+	u8 pllR36;
+	u8 pllR35;
+	u8 pllR34;
+	u8 pllR33;
+	u8 pllR32_b7b5;
+	u8 pllR32_b4b0; /* PLL_DEN (Denomina - 8) */
+	u8 pllR31_b7b5;
+	u8 pllR31_b4b0; /* PLL_K (Nominator *)*/
+	u8 pllR30_b7;	/* sdm_reset_n */
+	u8 pllR30_b6b2; /* sdmmash_prbs,sin */
+	u8 pllR30_b1;	/* sdm_bp */
+	u16 pll_n;	/* R30<0>, R29<7:0> (hex) */
+	u8 pllR28_b7b6; /* isi,iso */
+	u8 pllR28_b5b4;	/* pfd_dly */
+	u8 pllR28_b3b2;	/* clksel option */
+	u32 pll_sdm_k;	/* R28<1:0>, R27<7:0>, R26<7:0> (hex) SDM_k */
+	u8 pllR24_b1b0;	/* xo_div */
+};
+
+struct mt76x0_rate_pwr_item {
+	s8 mcs_power;
+	u8 rf_pa_mode;
+};
+
+struct mt76x0_rate_pwr_tab {
+	struct mt76x0_rate_pwr_item cck[4];
+	struct mt76x0_rate_pwr_item ofdm[8];
+	struct mt76x0_rate_pwr_item ht[8];
+	struct mt76x0_rate_pwr_item vht[10];
+	struct mt76x0_rate_pwr_item stbc[8];
+	struct mt76x0_rate_pwr_item mcs32;
+};
+
+#endif /* _MT76X0_PHY_H_ */
-- 
cgit v1.2.3


From 134b2d0d1fcf8c228cdaa3bd959025518e5cf1c8 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:56 +0200
Subject: mt76x0: init files

Add init files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   | 720 +++++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt76x0/initvals.h   | 282 ++++++++
 2 files changed, 1002 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/init.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
new file mode 100644
index 000000000000..b65b76d80906
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -0,0 +1,720 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "eeprom.h"
+#include "trace.h"
+#include "mcu.h"
+#include "usb.h"
+
+#include "initvals.h"
+
+static void
+mt76x0_set_wlan_state(struct mt76x0_dev *dev, u32 val, bool enable)
+{
+	int i;
+
+	/* Note: we don't turn off WLAN_CLK because that makes the device
+	 *	 not respond properly on the probe path.
+	 *	 In case anyone (PSM?) wants to use this function we can
+	 *	 bring the clock stuff back and fixup the probe path.
+	 */
+
+	if (enable)
+		val |= (MT_WLAN_FUN_CTRL_WLAN_EN |
+			MT_WLAN_FUN_CTRL_WLAN_CLK_EN);
+	else
+		val &= ~(MT_WLAN_FUN_CTRL_WLAN_EN);
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+
+	if (!enable)
+		return;
+
+	for (i = 200; i; i--) {
+		val = mt76_rr(dev, MT_CMB_CTRL);
+
+		if (val & MT_CMB_CTRL_XTAL_RDY && val & MT_CMB_CTRL_PLL_LD)
+			break;
+
+		udelay(20);
+	}
+
+	/* Note: vendor driver tries to disable/enable wlan here and retry
+	 *       but the code which does it is so buggy it must have never
+	 *       triggered, so don't bother.
+	 */
+	if (!i)
+		dev_err(dev->mt76.dev, "Error: PLL and XTAL check failed!\n");
+}
+
+static void mt76x0_chip_onoff(struct mt76x0_dev *dev, bool enable, bool reset)
+{
+	u32 val;
+
+	mutex_lock(&dev->hw_atomic_mutex);
+
+	val = mt76_rr(dev, MT_WLAN_FUN_CTRL);
+
+	if (reset) {
+		val |= MT_WLAN_FUN_CTRL_GPIO_OUT_EN;
+		val &= ~MT_WLAN_FUN_CTRL_FRC_WL_ANT_SEL;
+
+		if (val & MT_WLAN_FUN_CTRL_WLAN_EN) {
+			val |= (MT_WLAN_FUN_CTRL_WLAN_RESET |
+				MT_WLAN_FUN_CTRL_WLAN_RESET_RF);
+			mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+			udelay(20);
+
+			val &= ~(MT_WLAN_FUN_CTRL_WLAN_RESET |
+				 MT_WLAN_FUN_CTRL_WLAN_RESET_RF);
+		}
+	}
+
+	mt76_wr(dev, MT_WLAN_FUN_CTRL, val);
+	udelay(20);
+
+	mt76x0_set_wlan_state(dev, val, enable);
+
+	mutex_unlock(&dev->hw_atomic_mutex);
+}
+
+static void mt76x0_reset_csr_bbp(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_PBF_SYS_CTRL);
+	val &= ~0x2000;
+	mt76_wr(dev, MT_PBF_SYS_CTRL, val);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_RESET_CSR |
+					 MT_MAC_SYS_CTRL_RESET_BBP);
+
+	msleep(200);
+}
+
+static void mt76x0_init_usb_dma(struct mt76x0_dev *dev)
+{
+	u32 val;
+
+	val = mt76_rr(dev, MT_USB_DMA_CFG);
+
+	val |= FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_TOUT, MT_USB_AGGR_TIMEOUT) |
+	       FIELD_PREP(MT_USB_DMA_CFG_RX_BULK_AGG_LMT, MT_USB_AGGR_SIZE_LIMIT) |
+	       MT_USB_DMA_CFG_RX_BULK_EN |
+	       MT_USB_DMA_CFG_TX_BULK_EN;
+	if (dev->in_max_packet == 512)
+		val |= MT_USB_DMA_CFG_RX_BULK_AGG_EN;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+
+	val = mt76_rr(dev, MT_COM_REG0);
+	if (val & 1)
+		dev_dbg(dev->mt76.dev, "MCU not ready\n");
+
+	val = mt76_rr(dev, MT_USB_DMA_CFG);
+
+	val |= MT_USB_DMA_CFG_RX_DROP_OR_PADDING;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+	val &= ~MT_USB_DMA_CFG_RX_DROP_OR_PADDING;
+	mt76_wr(dev, MT_USB_DMA_CFG, val);
+}
+
+#define RANDOM_WRITE(dev, tab) \
+	mt76x0_write_reg_pairs(dev, MT_MCU_MEMMAP_WLAN, tab, ARRAY_SIZE(tab));
+
+static int mt76x0_init_bbp(struct mt76x0_dev *dev)
+{
+	int ret, i;
+
+	ret = mt76x0_wait_bbp_ready(dev);
+	if (ret)
+		return ret;
+
+	RANDOM_WRITE(dev, mt76x0_bbp_init_tab);
+
+	for (i = 0; i < ARRAY_SIZE(mt76x0_bbp_switch_tab); i++) {
+		const struct mt76x0_bbp_switch_item *item = &mt76x0_bbp_switch_tab[i];
+		const struct mt76_reg_pair *pair = &item->reg_pair;
+
+		if (((RF_G_BAND | RF_BW_20) & item->bw_band) == (RF_G_BAND | RF_BW_20))
+			mt76_wr(dev, pair->reg, pair->value);
+	}
+
+	RANDOM_WRITE(dev, mt76x0_dcoc_tab);
+
+	return 0;
+}
+
+static void
+mt76_init_beacon_offsets(struct mt76x0_dev *dev)
+{
+	u16 base = MT_BEACON_BASE;
+	u32 regs[4] = {};
+	int i;
+
+	for (i = 0; i < 16; i++) {
+		u16 addr = dev->beacon_offsets[i];
+
+		regs[i / 4] |= ((addr - base) / 64) << (8 * (i % 4));
+	}
+
+	for (i = 0; i < 4; i++)
+		mt76_wr(dev, MT_BCN_OFFSET(i), regs[i]);
+}
+
+static void mt76x0_init_mac_registers(struct mt76x0_dev *dev)
+{
+	u32 reg;
+
+	RANDOM_WRITE(dev, common_mac_reg_table);
+
+	mt76_init_beacon_offsets(dev);
+
+	/* Enable PBF and MAC clock SYS_CTRL[11:10] = 0x3 */
+	RANDOM_WRITE(dev, mt76x0_mac_reg_table);
+
+	/* Release BBP and MAC reset MAC_SYS_CTRL[1:0] = 0x0 */
+	reg = mt76_rr(dev, MT_MAC_SYS_CTRL);
+	reg &= ~0x3;
+	mt76_wr(dev, MT_MAC_SYS_CTRL, reg);
+
+	if (is_mt7610e(dev)) {
+		/* Disable COEX_EN */
+		reg = mt76_rr(dev, MT_COEXCFG0);
+		reg &= 0xFFFFFFFE;
+		mt76_wr(dev, MT_COEXCFG0, reg);
+	}
+
+	/* Set 0x141C[15:12]=0xF */
+	reg = mt76_rr(dev, MT_EXT_CCA_CFG);
+	reg |= 0x0000F000;
+	mt76_wr(dev, MT_EXT_CCA_CFG, reg);
+
+	mt76_clear(dev, MT_FCE_L2_STUFF, MT_FCE_L2_STUFF_WR_MPDU_LEN_EN);
+
+	/*
+		TxRing 9 is for Mgmt frame.
+		TxRing 8 is for In-band command frame.
+		WMM_RG0_TXQMA: This register setting is for FCE to define the rule of TxRing 9.
+		WMM_RG1_TXQMA: This register setting is for FCE to define the rule of TxRing 8.
+	*/
+	reg = mt76_rr(dev, MT_WMM_CTRL);
+	reg &= ~0x000003FF;
+	reg |= 0x00000201;
+	mt76_wr(dev, MT_WMM_CTRL, reg);
+
+	/* TODO: Probably not needed */
+	mt76_wr(dev, 0x7028, 0);
+	mt76_wr(dev, 0x7010, 0);
+	mt76_wr(dev, 0x7024, 0);
+	msleep(10);
+}
+
+static int mt76x0_init_wcid_mem(struct mt76x0_dev *dev)
+{
+	u32 *vals;
+	int i, ret;
+
+	vals = kmalloc(sizeof(*vals) * N_WCIDS * 2, GFP_KERNEL);
+	if (!vals)
+		return -ENOMEM;
+
+	for (i = 0; i < N_WCIDS; i++)  {
+		vals[i * 2] = 0xffffffff;
+		vals[i * 2 + 1] = 0x00ffffff;
+	}
+
+	ret = mt76x0_burst_write_regs(dev, MT_WCID_ADDR_BASE,
+				      vals, N_WCIDS * 2);
+	kfree(vals);
+
+	return ret;
+}
+
+static int mt76x0_init_key_mem(struct mt76x0_dev *dev)
+{
+	u32 vals[4] = {};
+
+	return mt76x0_burst_write_regs(dev, MT_SKEY_MODE_BASE_0,
+					vals, ARRAY_SIZE(vals));
+}
+
+static int mt76x0_init_wcid_attr_mem(struct mt76x0_dev *dev)
+{
+	u32 *vals;
+	int i, ret;
+
+	vals = kmalloc(sizeof(*vals) * N_WCIDS * 2, GFP_KERNEL);
+	if (!vals)
+		return -ENOMEM;
+
+	for (i = 0; i < N_WCIDS * 2; i++)
+		vals[i] = 1;
+
+	ret = mt76x0_burst_write_regs(dev, MT_WCID_ATTR_BASE,
+				      vals, N_WCIDS * 2);
+	kfree(vals);
+
+	return ret;
+}
+
+static void mt76x0_reset_counters(struct mt76x0_dev *dev)
+{
+	mt76_rr(dev, MT_RX_STA_CNT0);
+	mt76_rr(dev, MT_RX_STA_CNT1);
+	mt76_rr(dev, MT_RX_STA_CNT2);
+	mt76_rr(dev, MT_TX_STA_CNT0);
+	mt76_rr(dev, MT_TX_STA_CNT1);
+	mt76_rr(dev, MT_TX_STA_CNT2);
+}
+
+int mt76x0_mac_start(struct mt76x0_dev *dev)
+{
+	mt76_wr(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_TX);
+
+	if (!mt76_poll(dev, MT_WPDMA_GLO_CFG, MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+		       MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 200000))
+		return -ETIMEDOUT;
+
+	dev->rxfilter = MT_RX_FILTR_CFG_CRC_ERR |
+		MT_RX_FILTR_CFG_PHY_ERR | MT_RX_FILTR_CFG_PROMISC |
+		MT_RX_FILTR_CFG_VER_ERR | MT_RX_FILTR_CFG_DUP |
+		MT_RX_FILTR_CFG_CFACK | MT_RX_FILTR_CFG_CFEND |
+		MT_RX_FILTR_CFG_ACK | MT_RX_FILTR_CFG_CTS |
+		MT_RX_FILTR_CFG_RTS | MT_RX_FILTR_CFG_PSPOLL |
+		MT_RX_FILTR_CFG_BA | MT_RX_FILTR_CFG_CTRL_RSV;
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mt76_wr(dev, MT_MAC_SYS_CTRL,
+		   MT_MAC_SYS_CTRL_ENABLE_TX | MT_MAC_SYS_CTRL_ENABLE_RX);
+
+	if (!mt76_poll(dev, MT_WPDMA_GLO_CFG, MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+		       MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 50))
+		return -ETIMEDOUT;
+
+	return 0;
+}
+
+static void mt76x0_mac_stop_hw(struct mt76x0_dev *dev)
+{
+	int i, ok;
+
+	if (test_bit(MT76_REMOVED, &dev->mt76.state))
+		return;
+
+	mt76_clear(dev, MT_BEACON_TIME_CFG, MT_BEACON_TIME_CFG_TIMER_EN |
+		   MT_BEACON_TIME_CFG_SYNC_MODE | MT_BEACON_TIME_CFG_TBTT_EN |
+		   MT_BEACON_TIME_CFG_BEACON_TX);
+
+	if (!mt76_poll(dev, MT_USB_DMA_CFG, MT_USB_DMA_CFG_TX_BUSY, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: TX DMA did not stop!\n");
+
+	/* Page count on TxQ */
+	i = 200;
+	while (i-- && ((mt76_rr(dev, 0x0438) & 0xffffffff) ||
+		       (mt76_rr(dev, 0x0a30) & 0x000000ff) ||
+		       (mt76_rr(dev, 0x0a34) & 0x00ff00ff)))
+		msleep(10);
+
+	if (!mt76_poll(dev, MT_MAC_STATUS, MT_MAC_STATUS_TX, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: MAC TX did not stop!\n");
+
+	mt76_clear(dev, MT_MAC_SYS_CTRL, MT_MAC_SYS_CTRL_ENABLE_RX |
+					 MT_MAC_SYS_CTRL_ENABLE_TX);
+
+	/* Page count on RxQ */
+	ok = 0;
+	i = 200;
+	while (i--) {
+		if (!(mt76_rr(dev, MT_RXQ_STA) & 0x00ff0000) &&
+		    !mt76_rr(dev, 0x0a30) &&
+		    !mt76_rr(dev, 0x0a34)) {
+			if (ok++ > 5)
+				break;
+			continue;
+		}
+		msleep(1);
+	}
+
+	if (!mt76_poll(dev, MT_MAC_STATUS, MT_MAC_STATUS_RX, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: MAC RX did not stop!\n");
+
+	if (!mt76_poll(dev, MT_USB_DMA_CFG, MT_USB_DMA_CFG_RX_BUSY, 0, 1000))
+		dev_warn(dev->mt76.dev, "Warning: RX DMA did not stop!\n");
+}
+
+void mt76x0_mac_stop(struct mt76x0_dev *dev)
+{
+	mt76x0_mac_stop_hw(dev);
+	flush_delayed_work(&dev->stat_work);
+	cancel_delayed_work_sync(&dev->stat_work);
+}
+
+static void mt76x0_stop_hardware(struct mt76x0_dev *dev)
+{
+	mt76x0_chip_onoff(dev, false, false);
+}
+
+int mt76x0_init_hardware(struct mt76x0_dev *dev)
+{
+	static const u16 beacon_offsets[16] = {
+		/* 512 byte per beacon */
+		0xc000,	0xc200,	0xc400,	0xc600,
+		0xc800,	0xca00,	0xcc00,	0xce00,
+		0xd000,	0xd200,	0xd400,	0xd600,
+		0xd800,	0xda00,	0xdc00,	0xde00
+	};
+	int ret;
+
+	dev->beacon_offsets = beacon_offsets;
+
+	mt76x0_chip_onoff(dev, true, true);
+
+	ret = mt76x0_wait_asic_ready(dev);
+	if (ret)
+		goto err;
+	ret = mt76x0_mcu_init(dev);
+	if (ret)
+		goto err;
+
+	if (!mt76_poll_msec(dev, MT_WPDMA_GLO_CFG,
+			    MT_WPDMA_GLO_CFG_TX_DMA_BUSY |
+			    MT_WPDMA_GLO_CFG_RX_DMA_BUSY, 0, 100)) {
+		ret = -EIO;
+		goto err;
+	}
+
+	/* Wait for ASIC ready after FW load. */
+	ret = mt76x0_wait_asic_ready(dev);
+	if (ret)
+		goto err;
+
+	mt76x0_reset_csr_bbp(dev);
+	mt76x0_init_usb_dma(dev);
+
+	mt76_wr(dev, MT_HEADER_TRANS_CTRL_REG, 0x0);
+	mt76_wr(dev, MT_TSO_CTRL, 0x0);
+
+	ret = mt76x0_mcu_cmd_init(dev);
+	if (ret)
+		goto err;
+	ret = mt76x0_dma_init(dev);
+	if (ret)
+		goto err_mcu;
+
+	mt76x0_init_mac_registers(dev);
+
+	if (!mt76_poll_msec(dev, MT_MAC_STATUS,
+			    MT_MAC_STATUS_TX | MT_MAC_STATUS_RX, 0, 1000)) {
+		ret = -EIO;
+		goto err_rx;
+	}
+
+	ret = mt76x0_init_bbp(dev);
+	if (ret)
+		goto err_rx;
+
+	ret = mt76x0_init_wcid_mem(dev);
+	if (ret)
+		goto err_rx;
+	ret = mt76x0_init_key_mem(dev);
+	if (ret)
+		goto err_rx;
+	ret = mt76x0_init_wcid_attr_mem(dev);
+	if (ret)
+		goto err_rx;
+
+	mt76_clear(dev, MT_BEACON_TIME_CFG, (MT_BEACON_TIME_CFG_TIMER_EN |
+					     MT_BEACON_TIME_CFG_SYNC_MODE |
+					     MT_BEACON_TIME_CFG_TBTT_EN |
+					     MT_BEACON_TIME_CFG_BEACON_TX));
+
+	mt76x0_reset_counters(dev);
+
+	mt76_rmw(dev, MT_US_CYC_CFG, MT_US_CYC_CNT, 0x1e);
+
+	mt76_wr(dev, MT_TXOP_CTRL_CFG,
+		   FIELD_PREP(MT_TXOP_TRUN_EN, 0x3f) |
+		   FIELD_PREP(MT_TXOP_EXT_CCA_DLY, 0x58));
+
+	ret = mt76x0_eeprom_init(dev);
+	if (ret)
+		goto err_rx;
+
+	mt76x0_phy_init(dev);
+	return 0;
+
+err_rx:
+	mt76x0_dma_cleanup(dev);
+err_mcu:
+	mt76x0_mcu_cmd_deinit(dev);
+err:
+	mt76x0_chip_onoff(dev, false, false);
+	return ret;
+}
+
+void mt76x0_cleanup(struct mt76x0_dev *dev)
+{
+	if (!test_and_clear_bit(MT76_STATE_INITIALIZED, &dev->mt76.state))
+		return;
+
+	mt76x0_stop_hardware(dev);
+	mt76x0_dma_cleanup(dev);
+	mt76x0_mcu_cmd_deinit(dev);
+}
+
+struct mt76x0_dev *mt76x0_alloc_device(struct device *pdev)
+{
+	struct ieee80211_hw *hw;
+	struct mt76x0_dev *dev;
+
+	hw = ieee80211_alloc_hw(sizeof(*dev), &mt76x0_ops);
+	if (!hw)
+		return NULL;
+
+	dev = hw->priv;
+	dev->mt76.dev = pdev;
+	dev->mt76.hw = hw;
+	mutex_init(&dev->usb_ctrl_mtx);
+	mutex_init(&dev->reg_atomic_mutex);
+	mutex_init(&dev->hw_atomic_mutex);
+	mutex_init(&dev->mutex);
+	spin_lock_init(&dev->tx_lock);
+	spin_lock_init(&dev->rx_lock);
+	spin_lock_init(&dev->mt76.lock);
+	spin_lock_init(&dev->mac_lock);
+	spin_lock_init(&dev->con_mon_lock);
+	atomic_set(&dev->avg_ampdu_len, 1);
+	skb_queue_head_init(&dev->tx_skb_done);
+
+	dev->stat_wq = alloc_workqueue("mt76x0", WQ_UNBOUND, 0);
+	if (!dev->stat_wq) {
+		ieee80211_free_hw(hw);
+		return NULL;
+	}
+
+	return dev;
+}
+
+#define CHAN2G(_idx, _freq) {			\
+	.band = NL80211_BAND_2GHZ,		\
+	.center_freq = (_freq),			\
+	.hw_value = (_idx),			\
+	.max_power = 30,			\
+}
+
+static const struct ieee80211_channel mt76_channels_2ghz[] = {
+	CHAN2G(1, 2412),
+	CHAN2G(2, 2417),
+	CHAN2G(3, 2422),
+	CHAN2G(4, 2427),
+	CHAN2G(5, 2432),
+	CHAN2G(6, 2437),
+	CHAN2G(7, 2442),
+	CHAN2G(8, 2447),
+	CHAN2G(9, 2452),
+	CHAN2G(10, 2457),
+	CHAN2G(11, 2462),
+	CHAN2G(12, 2467),
+	CHAN2G(13, 2472),
+	CHAN2G(14, 2484),
+};
+
+#define CHAN5G(_idx, _freq) {			\
+	.band = NL80211_BAND_5GHZ,		\
+	.center_freq = (_freq),			\
+	.hw_value = (_idx),			\
+	.max_power = 30,			\
+}
+
+static const struct ieee80211_channel mt76_channels_5ghz[] = {
+	CHAN5G(36, 5180),
+	CHAN5G(40, 5200),
+	CHAN5G(44, 5220),
+	CHAN5G(46, 5230),
+	CHAN5G(48, 5240),
+	CHAN5G(52, 5260),
+	CHAN5G(56, 5280),
+	CHAN5G(60, 5300),
+	CHAN5G(64, 5320),
+
+	CHAN5G(100, 5500),
+	CHAN5G(104, 5520),
+	CHAN5G(108, 5540),
+	CHAN5G(112, 5560),
+	CHAN5G(116, 5580),
+	CHAN5G(120, 5600),
+	CHAN5G(124, 5620),
+	CHAN5G(128, 5640),
+	CHAN5G(132, 5660),
+	CHAN5G(136, 5680),
+	CHAN5G(140, 5700),
+};
+
+#define CCK_RATE(_idx, _rate) {					\
+	.bitrate = _rate,					\
+	.flags = IEEE80211_RATE_SHORT_PREAMBLE,			\
+	.hw_value = (MT_PHY_TYPE_CCK << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_CCK << 8) | (8 + _idx),	\
+}
+
+#define OFDM_RATE(_idx, _rate) {				\
+	.bitrate = _rate,					\
+	.hw_value = (MT_PHY_TYPE_OFDM << 8) | _idx,		\
+	.hw_value_short = (MT_PHY_TYPE_OFDM << 8) | _idx,	\
+}
+
+static struct ieee80211_rate mt76_rates[] = {
+	CCK_RATE(0, 10),
+	CCK_RATE(1, 20),
+	CCK_RATE(2, 55),
+	CCK_RATE(3, 110),
+	OFDM_RATE(0, 60),
+	OFDM_RATE(1, 90),
+	OFDM_RATE(2, 120),
+	OFDM_RATE(3, 180),
+	OFDM_RATE(4, 240),
+	OFDM_RATE(5, 360),
+	OFDM_RATE(6, 480),
+	OFDM_RATE(7, 540),
+};
+
+static int
+mt76_init_sband(struct mt76x0_dev *dev, struct ieee80211_supported_band *sband,
+		const struct ieee80211_channel *chan, int n_chan,
+		struct ieee80211_rate *rates, int n_rates)
+{
+	struct ieee80211_sta_ht_cap *ht_cap;
+	void *chanlist;
+	int size;
+
+	size = n_chan * sizeof(*chan);
+	chanlist = devm_kmemdup(dev->mt76.dev, chan, size, GFP_KERNEL);
+	if (!chanlist)
+		return -ENOMEM;
+
+	sband->channels = chanlist;
+	sband->n_channels = n_chan;
+	sband->bitrates = rates;
+	sband->n_bitrates = n_rates;
+
+	ht_cap = &sband->ht_cap;
+	ht_cap->ht_supported = true;
+	ht_cap->cap = IEEE80211_HT_CAP_SUP_WIDTH_20_40 |
+		      IEEE80211_HT_CAP_GRN_FLD |
+		      IEEE80211_HT_CAP_SGI_20 |
+		      IEEE80211_HT_CAP_SGI_40 |
+		      (1 << IEEE80211_HT_CAP_RX_STBC_SHIFT);
+
+	ht_cap->mcs.rx_mask[0] = 0xff;
+	ht_cap->mcs.rx_mask[4] = 0x1;
+	ht_cap->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
+	ht_cap->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
+	ht_cap->ampdu_density = IEEE80211_HT_MPDU_DENSITY_2;
+
+	return 0;
+}
+
+static int
+mt76_init_sband_2g(struct mt76x0_dev *dev)
+{
+	dev->mt76.hw->wiphy->bands[NL80211_BAND_2GHZ] = &dev->mt76.sband_2g.sband;
+
+	WARN_ON(dev->ee->reg.start - 1 + dev->ee->reg.num >
+		ARRAY_SIZE(mt76_channels_2ghz));
+
+
+	return mt76_init_sband(dev, &dev->mt76.sband_2g.sband,
+			       mt76_channels_2ghz, ARRAY_SIZE(mt76_channels_2ghz),
+			       mt76_rates, ARRAY_SIZE(mt76_rates));
+}
+
+static int
+mt76_init_sband_5g(struct mt76x0_dev *dev)
+{
+	dev->mt76.hw->wiphy->bands[NL80211_BAND_5GHZ] = &dev->mt76.sband_5g.sband;
+
+	return mt76_init_sband(dev, &dev->mt76.sband_5g.sband,
+			       mt76_channels_5ghz, ARRAY_SIZE(mt76_channels_5ghz),
+			       mt76_rates + 4, ARRAY_SIZE(mt76_rates) - 4);
+}
+
+
+int mt76x0_register_device(struct mt76x0_dev *dev)
+{
+	struct ieee80211_hw *hw = dev->mt76.hw;
+	struct wiphy *wiphy = hw->wiphy;
+	int ret;
+
+	/* Reserve WCID 0 for mcast - thanks to this APs WCID will go to
+	 * entry no. 1 like it does in the vendor driver.
+	 */
+	dev->wcid_mask[0] |= 1;
+
+	/* init fake wcid for monitor interfaces */
+	dev->mon_wcid = devm_kmalloc(dev->mt76.dev, sizeof(*dev->mon_wcid),
+				     GFP_KERNEL);
+	if (!dev->mon_wcid)
+		return -ENOMEM;
+	dev->mon_wcid->idx = 0xff;
+	dev->mon_wcid->hw_key_idx = -1;
+
+	SET_IEEE80211_DEV(hw, dev->mt76.dev);
+
+	hw->queues = 4;
+	ieee80211_hw_set(hw, SIGNAL_DBM);
+	ieee80211_hw_set(hw, PS_NULLFUNC_STACK);
+	ieee80211_hw_set(hw, SUPPORTS_HT_CCK_RATES);
+	ieee80211_hw_set(hw, AMPDU_AGGREGATION);
+	ieee80211_hw_set(hw, SUPPORTS_RC_TABLE);
+	hw->max_rates = 1;
+	hw->max_report_rates = 7;
+	hw->max_rate_tries = 1;
+
+	hw->sta_data_size = sizeof(struct mt76_sta);
+	hw->vif_data_size = sizeof(struct mt76_vif);
+
+	SET_IEEE80211_PERM_ADDR(hw, dev->macaddr);
+
+	wiphy->features |= NL80211_FEATURE_ACTIVE_MONITOR;
+	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION);
+
+	if (dev->ee->has_2ghz) {
+		ret = mt76_init_sband_2g(dev);
+		if (ret)
+			return ret;
+	}
+
+	if (dev->ee->has_5ghz) {
+		ret = mt76_init_sband_5g(dev);
+		if (ret)
+			return ret;
+	}
+
+	dev->mt76.chandef.chan = &dev->mt76.sband_2g.sband.channels[0];
+
+	INIT_DELAYED_WORK(&dev->mac_work, mt76x0_mac_work);
+	INIT_DELAYED_WORK(&dev->stat_work, mt76x0_tx_stat);
+
+	ret = ieee80211_register_hw(hw);
+	if (ret)
+		return ret;
+
+	mt76x0_init_debugfs(dev);
+
+	return 0;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
new file mode 100644
index 000000000000..24afcfd94b4e
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/initvals.h
@@ -0,0 +1,282 @@
+/*
+ * (c) Copyright 2002-2010, Ralink Technology, Inc.
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_INITVALS_H
+#define __MT76X0U_INITVALS_H
+
+#include "phy.h"
+
+static const struct mt76_reg_pair common_mac_reg_table[] = {
+#if 1
+	{MT_BCN_OFFSET(0),			0xf8f0e8e0}, /* 0x3800(e0), 0x3A00(e8), 0x3C00(f0), 0x3E00(f8), 512B for each beacon */
+	{MT_BCN_OFFSET(1),			0x6f77d0c8}, /* 0x3200(c8), 0x3400(d0), 0x1DC0(77), 0x1BC0(6f), 512B for each beacon */
+#endif
+
+	{MT_LEGACY_BASIC_RATE,		0x0000013f}, /*  Basic rate set bitmap*/
+	{MT_HT_BASIC_RATE,		0x00008003}, /* Basic HT rate set , 20M, MCS=3, MM. Format is the same as in TXWI.*/
+	{MT_MAC_SYS_CTRL,		0x00}, /* 0x1004, , default Disable RX*/
+	{MT_RX_FILTR_CFG,		0x17f97}, /*0x1400  , RX filter control,  */
+	{MT_BKOFF_SLOT_CFG,	0x209}, /* default set short slot time, CC_DELAY_TIME should be 2	 */
+	/*{TX_SW_CFG0,		0x40a06},  Gary,2006-08-23 */
+	{MT_TX_SW_CFG0,		0x0}, 		/* Gary,2008-05-21 for CWC test */
+	{MT_TX_SW_CFG1,		0x80606}, /* Gary,2006-08-23 */
+	{MT_TX_LINK_CFG,		0x1020},		/* Gary,2006-08-23 */
+	/*{TX_TIMEOUT_CFG,	0x00182090},	 CCK has some problem. So increase timieout value. 2006-10-09 MArvek RT*/
+	{MT_TX_TIMEOUT_CFG,	0x000a2090},	/* CCK has some problem. So increase timieout value. 2006-10-09 MArvek RT , Modify for 2860E ,2007-08-01*/
+	{MT_MAX_LEN_CFG,		0xa0fff | 0x00001000},	/* 0x3018, MAX frame length. Max PSDU = 16kbytes.*/
+	{MT_LED_CFG,		0x7f031e46}, /* Gary, 2006-08-23*/
+
+	{MT_PBF_TX_MAX_PCNT,		0x1fbf1f1f /*0xbfbf3f1f*/},
+	{MT_PBF_RX_MAX_PCNT,		0x9f},
+
+	/*{TX_RTY_CFG,			0x6bb80408},	 Jan, 2006/11/16*/
+/* WMM_ACM_SUPPORT */
+/*	{TX_RTY_CFG,			0x6bb80101},	 sample*/
+	{MT_TX_RETRY_CFG,			0x47d01f0f},	/* Jan, 2006/11/16, Set TxWI->ACK =0 in Probe Rsp Modify for 2860E ,2007-08-03*/
+
+	{MT_AUTO_RSP_CFG,			0x00000013},	/* Initial Auto_Responder, because QA will turn off Auto-Responder*/
+	{MT_CCK_PROT_CFG,			0x05740003 /*0x01740003*/},	/* Initial Auto_Responder, because QA will turn off Auto-Responder. And RTS threshold is enabled. */
+	{MT_OFDM_PROT_CFG,			0x05740003 /*0x01740003*/},	/* Initial Auto_Responder, because QA will turn off Auto-Responder. And RTS threshold is enabled. */
+	{MT_PBF_CFG, 				0xf40006}, 		/* Only enable Queue 2*/
+	{MT_MM40_PROT_CFG,			0x3F44084},		/* Initial Auto_Responder, because QA will turn off Auto-Responder*/
+	{MT_WPDMA_GLO_CFG,			0x00000030},
+	{MT_GF20_PROT_CFG,			0x01744004},    /* set 19:18 --> Short NAV for MIMO PS*/
+	{MT_GF40_PROT_CFG,			0x03F44084},
+	{MT_MM20_PROT_CFG,			0x01744004},
+	{MT_TXOP_CTRL_CFG,			0x0000583f, /*0x0000243f*/ /*0x000024bf*/},	/*Extension channel backoff.*/
+	{MT_TX_RTS_CFG,			0x00092b20},
+
+	{MT_EXP_ACK_TIME,			0x002400ca},	/* default value */
+	{MT_TXOP_HLDR_ET, 			0x00000002},
+
+	/* Jerry comments 2008/01/16: we use SIFS = 10us in CCK defaultly, but it seems that 10us
+		is too small for INTEL 2200bg card, so in MBSS mode, the delta time between beacon0
+		and beacon1 is SIFS (10us), so if INTEL 2200bg card connects to BSS0, the ping
+		will always lost. So we change the SIFS of CCK from 10us to 16us. */
+	{MT_XIFS_TIME_CFG,			0x33a41010},
+	{MT_PWR_PIN_CFG,			0x00000000},
+};
+
+static const struct mt76_reg_pair mt76x0_mac_reg_table[] = {
+	/* {MT_IOCFG_6,		0xA0040080 }, */
+	{MT_PBF_SYS_CTRL,	0x00080c00 },
+	{MT_PBF_CFG,		0x77723c1f },
+	{MT_FCE_PSE_CTRL,	0x00000001 },
+
+	{MT_AMPDU_MAX_LEN_20M1S,	0xBAA99887 },
+
+	/* Delay bb_tx_pe for proper tx_mcs_pwr update */
+	{MT_TX_SW_CFG0,		0x00000601 },
+
+	/* Set rf_tx_pe deassert time to 1us by Chee's comment @MT7650_CR_setting_1018.xlsx */
+	{MT_TX_SW_CFG1,		0x00040000 },
+	{MT_TX_SW_CFG2,		0x00000000 },
+
+	/* disable Tx info report */
+	{0xa44,		0x0000000 },
+
+	{MT_HEADER_TRANS_CTRL_REG, 0x0},
+	{MT_TSO_CTRL,		0x0},
+
+	/* BB_PA_MODE_CFG0(0x1214) Keep default value @20120903 */
+	{MT_BB_PA_MODE_CFG1,	0x00500055},
+
+	/* RF_PA_MODE_CFG0(0x121C) Keep default value @20120903 */
+	{MT_RF_PA_MODE_CFG1,	0x00500055},
+
+	{MT_TX_ALC_CFG_0,	0x2F2F000C},
+	{MT_TX0_BB_GAIN_ATTEN,  0x00000000}, /* set BBP atten gain = 0 */
+
+	{MT_TX_PWR_CFG_0, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_1, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_2, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_3, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_4, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_7, 0x3A3A3A3A},
+	{MT_TX_PWR_CFG_8, 0x3A},
+	{MT_TX_PWR_CFG_9, 0x3A},
+	/* Enable Tx length > 4095 byte */
+	{0x150C,		0x00000002},
+
+	/* Disable bt_abort_tx_en(0x1238[21] = 0) which is not used at MT7650 */
+	{0x1238, 		0x001700C8},
+	/* PMU_OCLEVEL<5:1> from default <5'b10010> to <5'b11011> for normal driver */
+	/* {MT_LDO_CTRL_0,		0x00A647B6}, */
+
+	/* Default LDO_DIG supply 1.26V, change to 1.2V */
+	{MT_LDO_CTRL_1,		0x6B006464 },
+/*
+	{MT_HT_BASIC_RATE,	0x00004003 },
+	{MT_HT_CTRL_CFG,	0x000001FF },
+*/
+};
+
+
+static const struct mt76_reg_pair mt76x0_bbp_init_tab[] = {
+	{MT_BBP(CORE, 1), 0x00000002},
+	{MT_BBP(CORE, 4), 0x00000000},
+	{MT_BBP(CORE, 24), 0x00000000},
+	{MT_BBP(CORE, 32), 0x4003000a},
+	{MT_BBP(CORE, 42), 0x00000000},
+	{MT_BBP(CORE, 44), 0x00000000},
+
+	{MT_BBP(IBI, 11), 0x00000080},
+
+	/*
+		0x2300[5] Default Antenna:
+		0 for WIFI main antenna
+		1 for WIFI aux  antenna
+
+	*/
+	{MT_BBP(AGC, 0), 0x00021400},
+	{MT_BBP(AGC, 1), 0x00000003},
+	{MT_BBP(AGC, 2), 0x003A6464},
+	{MT_BBP(AGC, 15), 0x88A28CB8},
+	{MT_BBP(AGC, 22), 0x00001E21},
+	{MT_BBP(AGC, 23), 0x0000272C},
+	{MT_BBP(AGC, 24), 0x00002F3A},
+	{MT_BBP(AGC, 25), 0x8000005A},
+	{MT_BBP(AGC, 26), 0x007C2005},
+	{MT_BBP(AGC, 34), 0x000A0C0C},
+	{MT_BBP(AGC, 37), 0x2121262C},
+	{MT_BBP(AGC, 41), 0x38383E45},
+	{MT_BBP(AGC, 57), 0x00001010},
+	{MT_BBP(AGC, 59), 0xBAA20E96},
+	{MT_BBP(AGC, 63), 0x00000001},
+
+	{MT_BBP(TXC, 0), 0x00280403},
+	{MT_BBP(TXC, 1), 0x00000000},
+
+	{MT_BBP(RXC, 1), 0x00000012},
+	{MT_BBP(RXC, 2), 0x00000011},
+	{MT_BBP(RXC, 3), 0x00000005},
+	{MT_BBP(RXC, 4), 0x00000000},
+	{MT_BBP(RXC, 5), 0xF977C4EC},
+	{MT_BBP(RXC, 7), 0x00000090},
+
+	{MT_BBP(TXO, 8), 0x00000000},
+
+	{MT_BBP(TXBE, 0), 0x00000000},
+	{MT_BBP(TXBE, 4), 0x00000004},
+	{MT_BBP(TXBE, 6), 0x00000000},
+	{MT_BBP(TXBE, 8), 0x00000014},
+	{MT_BBP(TXBE, 9), 0x20000000},
+	{MT_BBP(TXBE, 10), 0x00000000},
+	{MT_BBP(TXBE, 12), 0x00000000},
+	{MT_BBP(TXBE, 13), 0x00000000},
+	{MT_BBP(TXBE, 14), 0x00000000},
+	{MT_BBP(TXBE, 15), 0x00000000},
+	{MT_BBP(TXBE, 16), 0x00000000},
+	{MT_BBP(TXBE, 17), 0x00000000},
+
+	{MT_BBP(RXFE, 1), 0x00008800}, /* Add for E3 */
+	{MT_BBP(RXFE, 3), 0x00000000},
+	{MT_BBP(RXFE, 4), 0x00000000},
+
+	{MT_BBP(RXO, 13), 0x00000092},
+	{MT_BBP(RXO, 14), 0x00060612},
+	{MT_BBP(RXO, 15), 0xC8321B18},
+	{MT_BBP(RXO, 16), 0x0000001E},
+	{MT_BBP(RXO, 17), 0x00000000},
+	{MT_BBP(RXO, 18), 0xCC00A993},
+	{MT_BBP(RXO, 19), 0xB9CB9CB9},
+	{MT_BBP(RXO, 20), 0x26c00057},
+	{MT_BBP(RXO, 21), 0x00000001},
+	{MT_BBP(RXO, 24), 0x00000006},
+};
+
+static const struct mt76x0_bbp_switch_item mt76x0_bbp_switch_tab[] = {
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 8), 0x0E344EF0}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 8), 0x122C54F2}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 14), 0x310F2E39}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 14), 0x310F2A3F}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 32), 0x00003230}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 32), 0x0000181C}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 33), 0x00003240}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 33), 0x00003218}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 35), 0x11112016}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 35), 0x11112016}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(RXO, 28), 0x0000008A}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(RXO, 28), 0x0000008A}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 4), 0x1FEDA049}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 4), 0x1FECA054}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 6), 0x00000045}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 6), 0x0000000A}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 12), 0x05052879}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 12), 0x050528F9}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 12), 0x050528F9}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 13), 0x35050004}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 13), 0x2C3A0406}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 27), 0x000000E1}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 27), 0x000000EC}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 28), 0x00060806}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 28), 0x00050806}},
+	{RF_A_BAND | RF_BW_40,				{MT_BBP(AGC, 28), 0x00060801}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_80,		{MT_BBP(AGC, 28), 0x00060806}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 31), 0x00000F23}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 31), 0x00000F13}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 39), 0x2A2A3036}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 39), 0x2A2A2C36}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 39), 0x2A2A3036}},
+	{RF_A_BAND | RF_BW_80,				{MT_BBP(AGC, 39), 0x2A2A2A36}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 43), 0x27273438}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 43), 0x27272D38}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 43), 0x27272B30}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 51), 0x17171C1C}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 51), 0xFFFFFFFF}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 53), 0x26262A2F}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 53), 0x2626322F}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 53), 0xFFFFFFFF}},
+
+	{RF_G_BAND | RF_BW_20,				{MT_BBP(AGC, 55), 0x40404E58}},
+	{RF_G_BAND | RF_BW_40,				{MT_BBP(AGC, 55), 0x40405858}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 55), 0xFFFFFFFF}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(AGC, 58), 0x00001010}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(AGC, 58), 0x00000000}},
+
+	{RF_G_BAND | RF_BW_20 | RF_BW_40,		{MT_BBP(RXFE, 0), 0x3D5000E0}},
+	{RF_A_BAND | RF_BW_20 | RF_BW_40 | RF_BW_80,	{MT_BBP(RXFE, 0), 0x895000E0}},
+};
+
+static const struct mt76_reg_pair mt76x0_dcoc_tab[] = {
+	{MT_BBP(CAL, 47), 0x000010F0 },
+	{MT_BBP(CAL, 48), 0x00008080 },
+	{MT_BBP(CAL, 49), 0x00000F07 },
+	{MT_BBP(CAL, 50), 0x00000040 },
+	{MT_BBP(CAL, 51), 0x00000404 },
+	{MT_BBP(CAL, 52), 0x00080803 },
+	{MT_BBP(CAL, 53), 0x00000704 },
+	{MT_BBP(CAL, 54), 0x00002828 },
+	{MT_BBP(CAL, 55), 0x00005050 },
+};
+
+#endif
-- 
cgit v1.2.3


From e87b5039511a7780f3483a7202b4e67a8493c181 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:57 +0200
Subject: mt76x0: eeprom files

Add eeprom files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c | 445 +++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h | 149 +++++++
 2 files changed, 594 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
new file mode 100644
index 000000000000..1ecd018f12b8
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -0,0 +1,445 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/of.h>
+#include <linux/mtd/mtd.h>
+#include <linux/mtd/partitions.h>
+#include <linux/etherdevice.h>
+#include <asm/unaligned.h>
+#include "mt76x0.h"
+#include "eeprom.h"
+
+static bool
+field_valid(u8 val)
+{
+	return val != 0xff;
+}
+
+static s8
+field_validate(u8 val)
+{
+	if (!field_valid(val))
+		return 0;
+
+	return val;
+}
+
+static inline int
+sign_extend(u32 val, unsigned int size)
+{
+	bool sign = val & BIT(size - 1);
+
+	val &= BIT(size - 1) - 1;
+
+	return sign ? val : -val;
+}
+
+static int
+mt76x0_efuse_read(struct mt76x0_dev *dev, u16 addr, u8 *data,
+		   enum mt76x0_eeprom_access_modes mode)
+{
+	u32 val;
+	int i;
+
+	val = mt76_rr(dev, MT_EFUSE_CTRL);
+	val &= ~(MT_EFUSE_CTRL_AIN |
+		 MT_EFUSE_CTRL_MODE);
+	val |= FIELD_PREP(MT_EFUSE_CTRL_AIN, addr & ~0xf) |
+	       FIELD_PREP(MT_EFUSE_CTRL_MODE, mode) |
+	       MT_EFUSE_CTRL_KICK;
+	mt76_wr(dev, MT_EFUSE_CTRL, val);
+
+	if (!mt76_poll(dev, MT_EFUSE_CTRL, MT_EFUSE_CTRL_KICK, 0, 1000))
+		return -ETIMEDOUT;
+
+	val = mt76_rr(dev, MT_EFUSE_CTRL);
+	if ((val & MT_EFUSE_CTRL_AOUT) == MT_EFUSE_CTRL_AOUT) {
+		/* Parts of eeprom not in the usage map (0x80-0xc0,0xf0)
+		 * will not return valid data but it's ok.
+		 */
+		memset(data, 0xff, 16);
+		return 0;
+	}
+
+	for (i = 0; i < 4; i++) {
+		val = mt76_rr(dev, MT_EFUSE_DATA(i));
+		put_unaligned_le32(val, data + 4 * i);
+	}
+
+	return 0;
+}
+
+static int
+mt76x0_efuse_physical_size_check(struct mt76x0_dev *dev)
+{
+	const int map_reads = DIV_ROUND_UP(MT_EFUSE_USAGE_MAP_SIZE, 16);
+	u8 data[map_reads * 16];
+	int ret, i;
+	u32 start = 0, end = 0, cnt_free;
+
+	for (i = 0; i < map_reads; i++) {
+		ret = mt76x0_efuse_read(dev, MT_EE_USAGE_MAP_START + i * 16,
+					 data + i * 16, MT_EE_PHYSICAL_READ);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < MT_EFUSE_USAGE_MAP_SIZE; i++)
+		if (!data[i]) {
+			if (!start)
+				start = MT_EE_USAGE_MAP_START + i;
+			end = MT_EE_USAGE_MAP_START + i;
+		}
+	cnt_free = end - start + 1;
+
+	if (MT_EFUSE_USAGE_MAP_SIZE - cnt_free < 5) {
+		dev_err(dev->mt76.dev, "Error: your device needs default EEPROM file and this driver doesn't support it!\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void
+mt76x0_set_chip_cap(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	enum mt76x2_board_type { BOARD_TYPE_2GHZ = 1, BOARD_TYPE_5GHZ = 2 };
+	u16 nic_conf0 = get_unaligned_le16(eeprom + MT_EE_NIC_CONF_0);
+	u16 nic_conf1 = get_unaligned_le16(eeprom + MT_EE_NIC_CONF_1);
+
+	dev_dbg(dev->mt76.dev, "NIC_CONF0: %04x NIC_CONF1: %04x\n", nic_conf0, nic_conf1);
+
+	switch (FIELD_GET(MT_EE_NIC_CONF_0_BOARD_TYPE, nic_conf0)) {
+	case BOARD_TYPE_5GHZ:
+		dev->ee->has_5ghz = true;
+		break;
+	case BOARD_TYPE_2GHZ:
+		dev->ee->has_2ghz = true;
+		break;
+	default:
+		dev->ee->has_2ghz = true;
+		dev->ee->has_5ghz = true;
+		break;
+	}
+
+	dev_dbg(dev->mt76.dev, "Has 2GHZ %d 5GHZ %d\n", dev->ee->has_2ghz, dev->ee->has_5ghz);
+
+	if (!field_valid(nic_conf1 & 0xff))
+		nic_conf1 &= 0xff00;
+
+	if (nic_conf1 & MT_EE_NIC_CONF_1_HW_RF_CTRL)
+		dev_err(dev->mt76.dev,
+			"Error: this driver does not support HW RF ctrl\n");
+
+	if (!field_valid(nic_conf0 >> 8))
+		return;
+
+	if (FIELD_GET(MT_EE_NIC_CONF_0_RX_PATH, nic_conf0) > 1 ||
+	    FIELD_GET(MT_EE_NIC_CONF_0_TX_PATH, nic_conf0) > 1)
+		dev_err(dev->mt76.dev,
+			"Error: device has more than 1 RX/TX stream!\n");
+
+	dev->ee->pa_type = FIELD_GET(MT_EE_NIC_CONF_0_PA_TYPE, nic_conf0);
+	dev_dbg(dev->mt76.dev, "PA Type %d\n", dev->ee->pa_type);
+}
+
+static int
+mt76x0_set_macaddr(struct mt76x0_dev *dev, const u8 *eeprom)
+{
+	const void *src = eeprom + MT_EE_MAC_ADDR;
+
+	ether_addr_copy(dev->macaddr, src);
+
+	if (!is_valid_ether_addr(dev->macaddr)) {
+		eth_random_addr(dev->macaddr);
+		dev_info(dev->mt76.dev,
+			 "Invalid MAC address, using random address %pM\n",
+			 dev->macaddr);
+	}
+
+	mt76_wr(dev, MT_MAC_ADDR_DW0, get_unaligned_le32(dev->macaddr));
+	mt76_wr(dev, MT_MAC_ADDR_DW1, get_unaligned_le16(dev->macaddr + 4) |
+		FIELD_PREP(MT_MAC_ADDR_DW1_U2ME_MASK, 0xff));
+
+	return 0;
+}
+
+static void
+mt76x0_set_temp_offset(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	u8 temp = eeprom[MT_EE_TEMP_OFFSET];
+
+	if (field_valid(temp))
+		dev->ee->temp_off = sign_extend(temp, 8);
+	else
+		dev->ee->temp_off = -10;
+}
+
+static void
+mt76x0_set_country_reg(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	/* Note: - region 31 is not valid for mt76x0 (see rtmp_init.c)
+	 *	 - comments in rtmp_def.h are incorrect (see rt_channel.c)
+	 */
+	static const struct reg_channel_bounds chan_bounds[] = {
+		/* EEPROM country regions 0 - 7 */
+		{  1, 11 },	{  1, 13 },	{ 10,  2 },	{ 10,  4 },
+		{ 14,  1 },	{  1, 14 },	{  3,  7 },	{  5,  9 },
+		/* EEPROM country regions 32 - 33 */
+		{  1, 11 },	{  1, 14 }
+	};
+	u8 val = eeprom[MT_EE_COUNTRY_REGION_2GHZ];
+	int idx = -1;
+
+	dev_dbg(dev->mt76.dev, "REG 2GHZ %u REG 5GHZ %u\n", val, eeprom[MT_EE_COUNTRY_REGION_5GHZ]);
+	if (val < 8)
+		idx = val;
+	if (val > 31 && val < 33)
+		idx = val - 32 + 8;
+
+	if (idx != -1)
+		dev_info(dev->mt76.dev,
+			 "EEPROM country region %02hhx (channels %hhd-%hhd)\n",
+			 val, chan_bounds[idx].start,
+			 chan_bounds[idx].start + chan_bounds[idx].num - 1);
+	else
+		idx = 5; /* channels 1 - 14 */
+
+	dev->ee->reg = chan_bounds[idx];
+
+	/* TODO: country region 33 is special - phy should be set to B-mode
+	 *	 before entering channel 14 (see sta/connect.c)
+	 */
+}
+
+static void
+mt76x0_set_rf_freq_off(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	u8 comp;
+
+	dev->ee->rf_freq_off = field_validate(eeprom[MT_EE_FREQ_OFFSET]);
+	comp = field_validate(eeprom[MT_EE_FREQ_OFFSET_COMPENSATION]);
+
+	if (comp & BIT(7))
+		dev->ee->rf_freq_off -= comp & 0x7f;
+	else
+		dev->ee->rf_freq_off += comp;
+}
+
+static void
+mt76x0_set_lna_gain(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	s8 gain;
+
+	dev->ee->lna_gain_2ghz = eeprom[MT_EE_LNA_GAIN_2GHZ];
+	dev->ee->lna_gain_5ghz[0] = eeprom[MT_EE_LNA_GAIN_5GHZ_0];
+
+	gain = eeprom[MT_EE_LNA_GAIN_5GHZ_1];
+	if (gain == 0xff || gain == 0)
+		dev->ee->lna_gain_5ghz[1] = dev->ee->lna_gain_5ghz[0];
+	else
+		dev->ee->lna_gain_5ghz[1] = gain;
+
+	gain = eeprom[MT_EE_LNA_GAIN_5GHZ_2];
+	if (gain == 0xff || gain == 0)
+		dev->ee->lna_gain_5ghz[2] = dev->ee->lna_gain_5ghz[0];
+	else
+		dev->ee->lna_gain_5ghz[2] = gain;
+}
+
+static void
+mt76x0_set_rssi_offset(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	int i;
+	s8 *rssi_offset = dev->ee->rssi_offset_2ghz;
+
+	for (i = 0; i < 2; i++) {
+		rssi_offset[i] = eeprom[MT_EE_RSSI_OFFSET + i];
+
+		if (rssi_offset[i] < -10 || rssi_offset[i] > 10) {
+			dev_warn(dev->mt76.dev,
+				 "Warning: EEPROM RSSI is invalid %02hhx\n",
+				 rssi_offset[i]);
+			rssi_offset[i] = 0;
+		}
+	}
+
+	rssi_offset = dev->ee->rssi_offset_5ghz;
+
+	for (i = 0; i < 3; i++) {
+		rssi_offset[i] = eeprom[MT_EE_RSSI_OFFSET_5GHZ + i];
+
+		if (rssi_offset[i] < -10 || rssi_offset[i] > 10) {
+			dev_warn(dev->mt76.dev,
+				 "Warning: EEPROM RSSI is invalid %02hhx\n",
+				 rssi_offset[i]);
+			rssi_offset[i] = 0;
+		}
+	}
+}
+
+static u32
+calc_bw40_power_rate(u32 value, int delta)
+{
+	u32 ret = 0;
+	int i, tmp;
+
+	for (i = 0; i < 4; i++) {
+		tmp = s6_to_int((value >> i*8) & 0xff) + delta;
+		ret |= (u32)(int_to_s6(tmp)) << i*8;
+	}
+
+	return ret;
+}
+
+static s8
+get_delta(u8 val)
+{
+	s8 ret;
+
+	if (!field_valid(val) || !(val & BIT(7)))
+		return 0;
+
+	ret = val & 0x1f;
+	if (ret > 8)
+		ret = 8;
+	if (val & BIT(6))
+		ret = -ret;
+
+	return ret;
+}
+
+static void
+mt76x0_set_tx_power_per_rate(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	s8 bw40_delta_2g, bw40_delta_5g;
+	u32 val;
+	int i;
+
+	bw40_delta_2g = get_delta(eeprom[MT_EE_TX_POWER_DELTA_BW40]);
+	bw40_delta_5g = get_delta(eeprom[MT_EE_TX_POWER_DELTA_BW40 + 1]);
+
+	for (i = 0; i < 5; i++) {
+		val = get_unaligned_le32(eeprom + MT_EE_TX_POWER_BYRATE(i));
+
+		/* Skip last 16 bits. */
+		if (i == 4)
+			val &= 0x0000ffff;
+
+		dev->ee->tx_pwr_cfg_2g[i][0] = val;
+		dev->ee->tx_pwr_cfg_2g[i][1] = calc_bw40_power_rate(val, bw40_delta_2g);
+	}
+
+	/* Reading per rate tx power for 5 GHz band is a bit more complex. Note
+	 * we mix 16 bit and 32 bit reads and sometimes do shifts.
+	 */
+	val = get_unaligned_le16(eeprom + 0x120);
+	val <<= 16;
+	dev->ee->tx_pwr_cfg_5g[0][0] = val;
+	dev->ee->tx_pwr_cfg_5g[0][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le32(eeprom + 0x122);
+	dev->ee->tx_pwr_cfg_5g[1][0] = val;
+	dev->ee->tx_pwr_cfg_5g[1][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le16(eeprom + 0x126);
+	dev->ee->tx_pwr_cfg_5g[2][0] = val;
+	dev->ee->tx_pwr_cfg_5g[2][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le16(eeprom + 0xec);
+	val <<= 16;
+	dev->ee->tx_pwr_cfg_5g[3][0] = val;
+	dev->ee->tx_pwr_cfg_5g[3][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+
+	val = get_unaligned_le16(eeprom + 0xee);
+	dev->ee->tx_pwr_cfg_5g[4][0] = val;
+	dev->ee->tx_pwr_cfg_5g[4][1] = calc_bw40_power_rate(val, bw40_delta_5g);
+}
+
+static void
+mt76x0_set_tx_power_per_chan(struct mt76x0_dev *dev, u8 *eeprom)
+{
+	int i;
+	u8 tx_pwr;
+
+	for (i = 0; i < 14; i++) {
+		tx_pwr = eeprom[MT_EE_TX_POWER_OFFSET_2GHZ + i];
+		if (tx_pwr <= 0x3f && tx_pwr > 0)
+			dev->ee->tx_pwr_per_chan[i] = tx_pwr;
+		else
+			dev->ee->tx_pwr_per_chan[i] = 5;
+	}
+
+	for (i = 0; i < 40; i++) {
+		tx_pwr = eeprom[MT_EE_TX_POWER_OFFSET_5GHZ + i];
+		if (tx_pwr <= 0x3f && tx_pwr > 0)
+			dev->ee->tx_pwr_per_chan[14 + i] = tx_pwr;
+		else
+			dev->ee->tx_pwr_per_chan[14 + i] = 5;
+	}
+
+	dev->ee->tx_pwr_per_chan[54] = dev->ee->tx_pwr_per_chan[22];
+	dev->ee->tx_pwr_per_chan[55] = dev->ee->tx_pwr_per_chan[28];
+	dev->ee->tx_pwr_per_chan[56] = dev->ee->tx_pwr_per_chan[34];
+	dev->ee->tx_pwr_per_chan[57] = dev->ee->tx_pwr_per_chan[44];
+}
+
+int
+mt76x0_eeprom_init(struct mt76x0_dev *dev)
+{
+	u8 *eeprom;
+	int i, ret;
+
+	ret = mt76x0_efuse_physical_size_check(dev);
+	if (ret)
+		return ret;
+
+	dev->ee = devm_kzalloc(dev->mt76.dev, sizeof(*dev->ee), GFP_KERNEL);
+	if (!dev->ee)
+		return -ENOMEM;
+
+	eeprom = kmalloc(MT76X0_EEPROM_SIZE, GFP_KERNEL);
+	if (!eeprom)
+		return -ENOMEM;
+
+	for (i = 0; i + 16 <= MT76X0_EEPROM_SIZE; i += 16) {
+		ret = mt76x0_efuse_read(dev, i, eeprom + i, MT_EE_READ);
+		if (ret)
+			goto out;
+	}
+
+	if (eeprom[MT_EE_VERSION_EE] > MT76X0U_EE_MAX_VER)
+		dev_warn(dev->mt76.dev,
+			 "Warning: unsupported EEPROM version %02hhx\n",
+			 eeprom[MT_EE_VERSION_EE]);
+	dev_info(dev->mt76.dev, "EEPROM ver:%02hhx fae:%02hhx\n",
+		 eeprom[MT_EE_VERSION_EE], eeprom[MT_EE_VERSION_FAE]);
+
+	mt76x0_set_macaddr(dev, eeprom);
+	mt76x0_set_chip_cap(dev, eeprom);
+	mt76x0_set_country_reg(dev, eeprom);
+	mt76x0_set_rf_freq_off(dev, eeprom);
+	mt76x0_set_temp_offset(dev, eeprom);
+	mt76x0_set_lna_gain(dev, eeprom);
+	mt76x0_set_rssi_offset(dev, eeprom);
+	dev->chainmask = 0x0101;
+
+	mt76x0_set_tx_power_per_rate(dev, eeprom);
+	mt76x0_set_tx_power_per_chan(dev, eeprom);
+
+out:
+	kfree(eeprom);
+	return ret;
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h
new file mode 100644
index 000000000000..e37b573aed7b
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.h
@@ -0,0 +1,149 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_EEPROM_H
+#define __MT76X0U_EEPROM_H
+
+struct mt76x0_dev;
+
+#define MT76X0U_EE_MAX_VER			0x0c
+#define MT76X0_EEPROM_SIZE			512
+
+#define MT76X0U_DEFAULT_TX_POWER		6
+
+enum mt76_eeprom_field {
+	MT_EE_CHIP_ID =				0x00,
+	MT_EE_VERSION_FAE =			0x02,
+	MT_EE_VERSION_EE =			0x03,
+	MT_EE_MAC_ADDR =			0x04,
+	MT_EE_NIC_CONF_0 =			0x34,
+	MT_EE_NIC_CONF_1 =			0x36,
+	MT_EE_COUNTRY_REGION_5GHZ =		0x38,
+	MT_EE_COUNTRY_REGION_2GHZ =		0x39,
+	MT_EE_FREQ_OFFSET =			0x3a,
+	MT_EE_NIC_CONF_2 =			0x42,
+
+	MT_EE_LNA_GAIN_2GHZ =			0x44,
+	MT_EE_LNA_GAIN_5GHZ_0 =			0x45,
+	MT_EE_RSSI_OFFSET =			0x46,
+	MT_EE_RSSI_OFFSET_5GHZ =		0x4a,
+	MT_EE_LNA_GAIN_5GHZ_1 =			0x49,
+	MT_EE_LNA_GAIN_5GHZ_2 =			0x4d,
+
+	MT_EE_TX_POWER_DELTA_BW40 =		0x50,
+
+	MT_EE_TX_POWER_OFFSET_2GHZ =		0x52,
+
+	MT_EE_TX_TSSI_SLOPE =			0x6e,
+	MT_EE_TX_TSSI_OFFSET_GROUP =		0x6f,
+	MT_EE_TX_TSSI_OFFSET =			0x76,
+
+	MT_EE_TX_POWER_OFFSET_5GHZ =		0x78,
+
+	MT_EE_TEMP_OFFSET =			0xd1,
+	MT_EE_FREQ_OFFSET_COMPENSATION =	0xdb,
+	MT_EE_TX_POWER_BYRATE_BASE =		0xde,
+
+	MT_EE_TX_POWER_BYRATE_BASE_5GHZ =	0x120,
+
+	MT_EE_USAGE_MAP_START =			0x1e0,
+	MT_EE_USAGE_MAP_END =			0x1fc,
+};
+
+#define MT_EE_NIC_CONF_0_RX_PATH		GENMASK(3, 0)
+#define MT_EE_NIC_CONF_0_TX_PATH		GENMASK(7, 4)
+#define MT_EE_NIC_CONF_0_PA_TYPE		GENMASK(9, 8)
+#define MT_EE_NIC_CONF_0_BOARD_TYPE		GENMASK(13, 12)
+
+#define MT_EE_NIC_CONF_1_HW_RF_CTRL		BIT(0)
+#define MT_EE_NIC_CONF_1_TEMP_TX_ALC		BIT(1)
+#define MT_EE_NIC_CONF_1_LNA_EXT_2G		BIT(2)
+#define MT_EE_NIC_CONF_1_LNA_EXT_5G		BIT(3)
+#define MT_EE_NIC_CONF_1_TX_ALC_EN		BIT(13)
+
+#define MT_EE_NIC_CONF_2_RX_STREAM		GENMASK(3, 0)
+#define MT_EE_NIC_CONF_2_TX_STREAM		GENMASK(7, 4)
+#define MT_EE_NIC_CONF_2_HW_ANTDIV		BIT(8)
+#define MT_EE_NIC_CONF_2_XTAL_OPTION		GENMASK(10, 9)
+#define MT_EE_NIC_CONF_2_TEMP_DISABLE		BIT(11)
+#define MT_EE_NIC_CONF_2_COEX_METHOD		GENMASK(15, 13)
+
+#define MT_EE_TX_POWER_BYRATE(i)		(MT_EE_TX_POWER_BYRATE_BASE + \
+						 (i) * 4)
+
+#define MT_EFUSE_USAGE_MAP_SIZE			(MT_EE_USAGE_MAP_END -	\
+						 MT_EE_USAGE_MAP_START + 1)
+
+enum mt76x0_eeprom_access_modes {
+	MT_EE_READ = 0,
+	MT_EE_PHYSICAL_READ = 1,
+};
+
+struct reg_channel_bounds {
+	u8 start;
+	u8 num;
+};
+
+struct mt76x0_eeprom_params {
+	u8 rf_freq_off;
+	s16 temp_off;
+	s8 rssi_offset_2ghz[2];
+	s8 rssi_offset_5ghz[3];
+	s8 lna_gain_2ghz;
+	s8 lna_gain_5ghz[3];
+	u8 pa_type;
+
+	/* TX_PWR_CFG_* values from EEPROM for 20 and 40 Mhz bandwidths. */
+	u32 tx_pwr_cfg_2g[5][2];
+	u32 tx_pwr_cfg_5g[5][2];
+
+	u8 tx_pwr_per_chan[58];
+
+	struct reg_channel_bounds reg;
+
+	bool has_2ghz;
+	bool has_5ghz;
+};
+
+int mt76x0_eeprom_init(struct mt76x0_dev *dev);
+
+static inline u32 s6_validate(u32 reg)
+{
+	WARN_ON(reg & ~GENMASK(5, 0));
+	return reg & GENMASK(5, 0);
+}
+
+static inline int s6_to_int(u32 reg)
+{
+	int s6;
+
+	s6 = s6_validate(reg);
+	if (s6 & BIT(5))
+		s6 -= BIT(6);
+
+	return s6;
+}
+
+static inline u32 int_to_s6(int val)
+{
+	if (val < -0x20)
+		return 0x20;
+	if (val > 0x1f)
+		return 0x1f;
+
+	return val & 0x3f;
+}
+
+#endif
-- 
cgit v1.2.3


From a79e4638152f315aa24627da062b91f60665cf3b Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:58 +0200
Subject: mt76x0: trace and debugfs files

Add trace and debugfs files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../net/wireless/mediatek/mt76/mt76x0/debugfs.c    | 166 ++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/trace.c  |  21 ++
 drivers/net/wireless/mediatek/mt76/mt76x0/trace.h  | 366 +++++++++++++++++++++
 3 files changed, 553 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/trace.h

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c
new file mode 100644
index 000000000000..e7a77a886068
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/debugfs.c
@@ -0,0 +1,166 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/debugfs.h>
+
+#include "mt76x0.h"
+#include "eeprom.h"
+
+static int
+mt76_reg_set(void *data, u64 val)
+{
+	struct mt76x0_dev *dev = data;
+
+	mt76_wr(dev, dev->debugfs_reg, val);
+	return 0;
+}
+
+static int
+mt76_reg_get(void *data, u64 *val)
+{
+	struct mt76x0_dev *dev = data;
+
+	*val = mt76_rr(dev, dev->debugfs_reg);
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_regval, mt76_reg_get, mt76_reg_set, "0x%08llx\n");
+
+static int
+mt76x0_ampdu_stat_read(struct seq_file *file, void *data)
+{
+	struct mt76x0_dev *dev = file->private;
+	int i, j;
+
+#define stat_printf(grp, off, name)					\
+	seq_printf(file, #name ":\t%llu\n", dev->stats.grp[off])
+
+	stat_printf(rx_stat, 0, rx_crc_err);
+	stat_printf(rx_stat, 1, rx_phy_err);
+	stat_printf(rx_stat, 2, rx_false_cca);
+	stat_printf(rx_stat, 3, rx_plcp_err);
+	stat_printf(rx_stat, 4, rx_fifo_overflow);
+	stat_printf(rx_stat, 5, rx_duplicate);
+
+	stat_printf(tx_stat, 0, tx_fail_cnt);
+	stat_printf(tx_stat, 1, tx_bcn_cnt);
+	stat_printf(tx_stat, 2, tx_success);
+	stat_printf(tx_stat, 3, tx_retransmit);
+	stat_printf(tx_stat, 4, tx_zero_len);
+	stat_printf(tx_stat, 5, tx_underflow);
+
+	stat_printf(aggr_stat, 0, non_aggr_tx);
+	stat_printf(aggr_stat, 1, aggr_tx);
+
+	stat_printf(zero_len_del, 0, tx_zero_len_del);
+	stat_printf(zero_len_del, 1, rx_zero_len_del);
+#undef stat_printf
+
+	seq_puts(file, "Aggregations stats:\n");
+	for (i = 0; i < 4; i++) {
+		for (j = 0; j < 8; j++)
+			seq_printf(file, "%08llx ",
+				   dev->stats.aggr_n[i * 8 + j]);
+		seq_putc(file, '\n');
+	}
+
+	seq_printf(file, "recent average AMPDU len: %d\n",
+		   atomic_read(&dev->avg_ampdu_len));
+
+	return 0;
+}
+
+static int
+mt76x0_ampdu_stat_open(struct inode *inode, struct file *f)
+{
+	return single_open(f, mt76x0_ampdu_stat_read, inode->i_private);
+}
+
+static const struct file_operations fops_ampdu_stat = {
+	.open = mt76x0_ampdu_stat_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int
+mt76x0_eeprom_param_read(struct seq_file *file, void *data)
+{
+	struct mt76x0_dev *dev = file->private;
+	int i;
+
+	seq_printf(file, "RF freq offset: %hhx\n", dev->ee->rf_freq_off);
+	seq_printf(file, "RSSI offset 2GHz: %hhx %hhx\n",
+		   dev->ee->rssi_offset_2ghz[0], dev->ee->rssi_offset_2ghz[1]);
+	seq_printf(file, "RSSI offset 5GHz: %hhx %hhx %hhx\n",
+		   dev->ee->rssi_offset_5ghz[0], dev->ee->rssi_offset_5ghz[1],
+		   dev->ee->rssi_offset_5ghz[2]);
+	seq_printf(file, "Temperature offset: %hhx\n", dev->ee->temp_off);
+	seq_printf(file, "LNA gain 2Ghz: %hhx\n", dev->ee->lna_gain_2ghz);
+	seq_printf(file, "LNA gain 5Ghz: %hhx %hhx %hhx\n",
+		   dev->ee->lna_gain_5ghz[0], dev->ee->lna_gain_5ghz[1],
+		   dev->ee->lna_gain_5ghz[2]);
+	seq_printf(file, "Power Amplifier type %hhx\n", dev->ee->pa_type);
+	seq_printf(file, "Reg channels: %hhu-%hhu\n", dev->ee->reg.start,
+		   dev->ee->reg.start + dev->ee->reg.num - 1);
+
+	seq_puts(file, "Per channel power:\n");
+	for (i = 0; i < 58; i++)
+		seq_printf(file, "\t%d chan:%d pwr:%d\n", i, i,
+			   dev->ee->tx_pwr_per_chan[i]);
+
+	seq_puts(file, "Per rate power 2GHz:\n");
+	for (i = 0; i < 5; i++)
+		seq_printf(file, "\t %d bw20:%d bw40:%d\n",
+			   i, dev->ee->tx_pwr_cfg_2g[i][0],
+			      dev->ee->tx_pwr_cfg_5g[i][1]);
+
+	seq_puts(file, "Per rate power 5GHz:\n");
+	for (i = 0; i < 5; i++)
+		seq_printf(file, "\t %d bw20:%d bw40:%d\n",
+			   i, dev->ee->tx_pwr_cfg_5g[i][0],
+			      dev->ee->tx_pwr_cfg_5g[i][1]);
+
+	return 0;
+}
+
+static int
+mt76x0_eeprom_param_open(struct inode *inode, struct file *f)
+{
+	return single_open(f, mt76x0_eeprom_param_read, inode->i_private);
+}
+
+static const struct file_operations fops_eeprom_param = {
+	.open = mt76x0_eeprom_param_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+void mt76x0_init_debugfs(struct mt76x0_dev *dev)
+{
+	struct dentry *dir;
+
+	dir = debugfs_create_dir("mt76x0", dev->mt76.hw->wiphy->debugfsdir);
+	if (!dir)
+		return;
+
+	debugfs_create_u32("regidx", S_IRUSR | S_IWUSR, dir, &dev->debugfs_reg);
+	debugfs_create_file("regval", S_IRUSR | S_IWUSR, dir, dev,
+			    &fops_regval);
+	debugfs_create_file("ampdu_stat", S_IRUSR, dir, dev, &fops_ampdu_stat);
+	debugfs_create_file("eeprom_param", S_IRUSR, dir, dev,
+			    &fops_eeprom_param);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
new file mode 100644
index 000000000000..8abdd3cd546d
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.c
@@ -0,0 +1,21 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/module.h>
+
+#ifndef __CHECKER__
+#define CREATE_TRACE_POINTS
+#include "trace.h"
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
new file mode 100644
index 000000000000..cdf53e5442d8
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
@@ -0,0 +1,366 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#if !defined(__MT76X0U_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __MT76X0U_TRACE_H
+
+#include <linux/tracepoint.h>
+#include "mt76x0.h"
+#include "mac.h"
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mt76x0
+
+#define MAXNAME		32
+#define DEV_ENTRY	__array(char, wiphy_name, 32)
+#define DEV_ASSIGN	strlcpy(__entry->wiphy_name,			\
+				wiphy_name(dev->hw->wiphy), MAXNAME)
+#define DEV_PR_FMT	"%s "
+#define DEV_PR_ARG	__entry->wiphy_name
+
+#define REG_ENTRY	__field(u32, reg) __field(u32, val)
+#define REG_ASSIGN	__entry->reg = reg; __entry->val = val
+#define REG_PR_FMT	"%04x=%08x"
+#define REG_PR_ARG	__entry->reg, __entry->val
+
+DECLARE_EVENT_CLASS(dev_reg_evt,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		REG_ENTRY
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		REG_ASSIGN;
+	),
+	TP_printk(
+		DEV_PR_FMT REG_PR_FMT,
+		DEV_PR_ARG, REG_PR_ARG
+	)
+);
+
+DEFINE_EVENT(dev_reg_evt, reg_read,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+DEFINE_EVENT(dev_reg_evt, reg_write,
+	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
+	TP_ARGS(dev, reg, val)
+);
+
+TRACE_EVENT(mt_submit_urb,
+	TP_PROTO(struct mt76_dev *dev, struct urb *u),
+	TP_ARGS(dev, u),
+	TP_STRUCT__entry(
+		DEV_ENTRY __field(unsigned, pipe) __field(u32, len)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->pipe = u->pipe;
+		__entry->len = u->transfer_buffer_length;
+	),
+	TP_printk(DEV_PR_FMT "p:%08x len:%u",
+		  DEV_PR_ARG, __entry->pipe, __entry->len)
+);
+
+#define trace_mt_submit_urb_sync(__dev, __pipe, __len) ({	\
+	struct urb u;					\
+	u.pipe = __pipe;				\
+	u.transfer_buffer_length = __len;		\
+	trace_mt_submit_urb(__dev, &u);			\
+})
+
+TRACE_EVENT(mt_mcu_msg_send,
+	TP_PROTO(struct mt76_dev *dev,
+		 struct sk_buff *skb, u32 csum, bool resp),
+	TP_ARGS(dev, skb, csum, resp),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u32, info)
+		__field(u32, csum)
+		__field(bool, resp)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->info = *(u32 *)skb->data;
+		__entry->csum = csum;
+		__entry->resp = resp;
+	),
+	TP_printk(DEV_PR_FMT "i:%08x c:%08x r:%d",
+		  DEV_PR_ARG, __entry->info, __entry->csum, __entry->resp)
+);
+
+TRACE_EVENT(mt_vend_req,
+	TP_PROTO(struct mt76_dev *dev, unsigned pipe, u8 req, u8 req_type,
+		 u16 val, u16 offset, void *buf, size_t buflen, int ret),
+	TP_ARGS(dev, pipe, req, req_type, val, offset, buf, buflen, ret),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(unsigned, pipe) __field(u8, req) __field(u8, req_type)
+		__field(u16, val) __field(u16, offset) __field(void*, buf)
+		__field(int, buflen) __field(int, ret)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->pipe = pipe;
+		__entry->req = req;
+		__entry->req_type = req_type;
+		__entry->val = val;
+		__entry->offset = offset;
+		__entry->buf = buf;
+		__entry->buflen = buflen;
+		__entry->ret = ret;
+	),
+	TP_printk(DEV_PR_FMT
+		  "%d p:%08x req:%02hhx %02hhx val:%04hx %04hx buf:%d %d",
+		  DEV_PR_ARG, __entry->ret, __entry->pipe, __entry->req,
+		  __entry->req_type, __entry->val, __entry->offset,
+		  !!__entry->buf, __entry->buflen)
+);
+
+TRACE_EVENT(ee_read,
+	TP_PROTO(struct mt76_dev *dev, int offset, u16 val),
+	TP_ARGS(dev, offset, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(int, o) __field(u16, v)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->o = offset;
+		__entry->v = val;
+	),
+	TP_printk(DEV_PR_FMT "%04x=%04x", DEV_PR_ARG, __entry->o, __entry->v)
+);
+
+DECLARE_EVENT_CLASS(dev_rf_reg_evt,
+	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
+	TP_ARGS(dev, bank, reg, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, bank)
+		__field(u8, reg)
+		__field(u8, val)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		REG_ASSIGN;
+		__entry->bank = bank;
+	),
+	TP_printk(
+		DEV_PR_FMT "%02hhx:%02hhx=%02hhx",
+		DEV_PR_ARG, __entry->bank, __entry->reg, __entry->val
+	)
+);
+
+DEFINE_EVENT(dev_rf_reg_evt, rf_read,
+	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
+	TP_ARGS(dev, bank, reg, val)
+);
+
+DEFINE_EVENT(dev_rf_reg_evt, rf_write,
+	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
+	TP_ARGS(dev, bank, reg, val)
+);
+
+DECLARE_EVENT_CLASS(dev_bbp_reg_evt,
+	TP_PROTO(struct mt76_dev *dev, u8 reg, u8 val),
+	TP_ARGS(dev, reg, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, reg)
+		__field(u8, val)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		REG_ASSIGN;
+	),
+	TP_printk(
+		DEV_PR_FMT "%02hhx=%02hhx",
+		DEV_PR_ARG, __entry->reg, __entry->val
+	)
+);
+
+DEFINE_EVENT(dev_bbp_reg_evt, bbp_read,
+	TP_PROTO(struct mt76_dev *dev, u8 reg, u8 val),
+	TP_ARGS(dev, reg, val)
+);
+
+DEFINE_EVENT(dev_bbp_reg_evt, bbp_write,
+	TP_PROTO(struct mt76_dev *dev, u8 reg, u8 val),
+	TP_ARGS(dev, reg, val)
+);
+
+DECLARE_EVENT_CLASS(dev_simple_evt,
+	TP_PROTO(struct mt76_dev *dev, u8 val),
+	TP_ARGS(dev, val),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, val)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->val = val;
+	),
+	TP_printk(
+		DEV_PR_FMT "%02hhx", DEV_PR_ARG, __entry->val
+	)
+);
+
+DEFINE_EVENT(dev_simple_evt, temp_mode,
+	TP_PROTO(struct mt76_dev *dev, u8 val),
+	TP_ARGS(dev, val)
+);
+
+DEFINE_EVENT(dev_simple_evt, read_temp,
+	TP_PROTO(struct mt76_dev *dev, u8 val),
+	TP_ARGS(dev, val)
+);
+
+TRACE_EVENT(mt_rx,
+	TP_PROTO(struct mt76_dev *dev, struct mt76x0_rxwi *rxwi, u32 f),
+	TP_ARGS(dev, rxwi, f),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field_struct(struct mt76x0_rxwi, rxwi)
+		__field(u32, fce_info)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->rxwi = *rxwi;
+		__entry->fce_info = f;
+	),
+	TP_printk(DEV_PR_FMT "rxi:%08x ctl:%08x", DEV_PR_ARG,
+		  le32_to_cpu(__entry->rxwi.rxinfo),
+		  le32_to_cpu(__entry->rxwi.ctl))
+);
+
+TRACE_EVENT(mt_tx,
+	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb,
+		 struct mt76_sta *sta, struct mt76_txwi *h),
+	TP_ARGS(dev, skb, sta, h),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field_struct(struct mt76_txwi, h)
+		__field(struct sk_buff *, skb)
+		__field(struct mt76_sta *, sta)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->h = *h;
+		__entry->skb = skb;
+		__entry->sta = sta;
+	),
+	TP_printk(DEV_PR_FMT "skb:%p sta:%p  flg:%04hx rate_ctl:%04hx "
+		  "ack:%02hhx wcid:%02hhx len_ctl:%05hx", DEV_PR_ARG,
+		  __entry->skb, __entry->sta,
+		  le16_to_cpu(__entry->h.flags),
+		  le16_to_cpu(__entry->h.rate_ctl),
+		  __entry->h.ack_ctl, __entry->h.wcid,
+		  le16_to_cpu(__entry->h.len_ctl))
+);
+
+TRACE_EVENT(mt_tx_dma_done,
+	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb),
+	TP_ARGS(dev, skb),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(struct sk_buff *, skb)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->skb = skb;
+	),
+	TP_printk(DEV_PR_FMT "%p", DEV_PR_ARG, __entry->skb)
+);
+
+TRACE_EVENT(mt_tx_status_cleaned,
+	TP_PROTO(struct mt76_dev *dev, int cleaned),
+	TP_ARGS(dev, cleaned),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(int, cleaned)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->cleaned = cleaned;
+	),
+	TP_printk(DEV_PR_FMT "%d", DEV_PR_ARG, __entry->cleaned)
+);
+
+TRACE_EVENT(mt_tx_status,
+	TP_PROTO(struct mt76_dev *dev, u32 stat1, u32 stat2),
+	TP_ARGS(dev, stat1, stat2),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u32, stat1)	__field(u32, stat2)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->stat1 = stat1;
+		__entry->stat2 = stat2;
+	),
+	TP_printk(DEV_PR_FMT "%08x %08x",
+		  DEV_PR_ARG, __entry->stat1, __entry->stat2)
+);
+
+TRACE_EVENT(mt_rx_dma_aggr,
+	TP_PROTO(struct mt76_dev *dev, int cnt, bool paged),
+	TP_ARGS(dev, cnt, paged),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, cnt)
+		__field(bool, paged)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->cnt = cnt;
+		__entry->paged = paged;
+	),
+	TP_printk(DEV_PR_FMT "cnt:%d paged:%d",
+		  DEV_PR_ARG, __entry->cnt, __entry->paged)
+);
+
+DEFINE_EVENT(dev_simple_evt, set_key,
+	TP_PROTO(struct mt76_dev *dev, u8 val),
+	TP_ARGS(dev, val)
+);
+
+TRACE_EVENT(set_shared_key,
+	TP_PROTO(struct mt76_dev *dev, u8 vid, u8 key),
+	TP_ARGS(dev, vid, key),
+	TP_STRUCT__entry(
+		DEV_ENTRY
+		__field(u8, vid)
+		__field(u8, key)
+	),
+	TP_fast_assign(
+		DEV_ASSIGN;
+		__entry->vid = vid;
+		__entry->key = key;
+	),
+	TP_printk(DEV_PR_FMT "phy:%02hhx off:%02hhx",
+		  DEV_PR_ARG, __entry->vid, __entry->key)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH .
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE trace
+
+#include <trace/define_trace.h>
-- 
cgit v1.2.3


From b4d4d0644331f431bd9d3c28c26529c77b9dc452 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:40:59 +0200
Subject: mt76x0: dma and tx files

Add dma and tx files of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/dma.c | 522 ++++++++++++++++++++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/dma.h | 126 ++++++
 drivers/net/wireless/mediatek/mt76/mt76x0/tx.c  | 270 ++++++++++++
 3 files changed, 918 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/dma.h
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/tx.c

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
new file mode 100644
index 000000000000..2cf71283de3f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
@@ -0,0 +1,522 @@
+/*
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "dma.h"
+#include "usb.h"
+#include "trace.h"
+
+static int mt76x0_submit_rx_buf(struct mt76x0_dev *dev,
+				 struct mt76x0_dma_buf_rx *e, gfp_t gfp);
+
+static unsigned int ieee80211_get_hdrlen_from_buf(const u8 *data, unsigned len)
+{
+	const struct ieee80211_hdr *hdr = (const struct ieee80211_hdr *)data;
+	unsigned int hdrlen;
+
+	if (unlikely(len < 10))
+		return 0;
+	hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	if (unlikely(hdrlen > len))
+		return 0;
+	return hdrlen;
+}
+
+static struct sk_buff *
+mt76x0_rx_skb_from_seg(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi,
+			void *data, u32 seg_len, u32 truesize, struct page *p)
+{
+	struct sk_buff *skb;
+	u32 true_len, hdr_len = 0, copy, frag;
+
+	skb = alloc_skb(p ? 128 : seg_len, GFP_ATOMIC);
+	if (!skb)
+		return NULL;
+
+	true_len = mt76_mac_process_rx(dev, skb, data, rxwi);
+	if (!true_len || true_len > seg_len)
+		goto bad_frame;
+
+	hdr_len = ieee80211_get_hdrlen_from_buf(data, true_len);
+	if (!hdr_len)
+		goto bad_frame;
+
+	if (rxwi->rxinfo & cpu_to_le32(MT_RXINFO_L2PAD)) {
+		memcpy(skb_put(skb, hdr_len), data, hdr_len);
+
+		data += hdr_len + 2;
+		true_len -= hdr_len;
+		hdr_len = 0;
+	}
+
+	/* If not doing paged RX allocated skb will always have enough space */
+	copy = (true_len <= skb_tailroom(skb)) ? true_len : hdr_len + 8;
+	frag = true_len - copy;
+
+	memcpy(skb_put(skb, copy), data, copy);
+	data += copy;
+
+	if (frag) {
+		skb_add_rx_frag(skb, 0, p, data - page_address(p),
+				frag, truesize);
+		get_page(p);
+	}
+
+	return skb;
+
+bad_frame:
+	dev_err_ratelimited(dev->mt76.dev, "Error: incorrect frame len:%u hdr:%u\n",
+			    true_len, hdr_len);
+	dev_kfree_skb(skb);
+	return NULL;
+}
+
+static void mt76x0_rx_process_seg(struct mt76x0_dev *dev, u8 *data,
+				   u32 seg_len, struct page *p)
+{
+	struct sk_buff *skb;
+	struct mt76x0_rxwi *rxwi;
+	u32 fce_info, truesize = seg_len;
+
+	/* DMA_INFO field at the beginning of the segment contains only some of
+	 * the information, we need to read the FCE descriptor from the end.
+	 */
+	fce_info = get_unaligned_le32(data + seg_len - MT_FCE_INFO_LEN);
+	seg_len -= MT_FCE_INFO_LEN;
+
+	data += MT_DMA_HDR_LEN;
+	seg_len -= MT_DMA_HDR_LEN;
+
+	rxwi = (struct mt76x0_rxwi *) data;
+	data += sizeof(struct mt76x0_rxwi);
+	seg_len -= sizeof(struct mt76x0_rxwi);
+
+	if (unlikely(FIELD_GET(MT_RXD_INFO_TYPE, fce_info)))
+		dev_err_once(dev->mt76.dev, "Error: RX path seen a non-pkt urb\n");
+
+	trace_mt_rx(&dev->mt76, rxwi, fce_info);
+
+	skb = mt76x0_rx_skb_from_seg(dev, rxwi, data, seg_len, truesize, p);
+	if (!skb)
+		return;
+
+	spin_lock(&dev->mac_lock);
+	ieee80211_rx(dev->mt76.hw, skb);
+	spin_unlock(&dev->mac_lock);
+}
+
+static u16 mt76x0_rx_next_seg_len(u8 *data, u32 data_len)
+{
+	u32 min_seg_len = MT_DMA_HDR_LEN + MT_RX_INFO_LEN +
+		sizeof(struct mt76x0_rxwi) + MT_FCE_INFO_LEN;
+	u16 dma_len = get_unaligned_le16(data);
+
+	if (data_len < min_seg_len ||
+	    WARN_ON(!dma_len) ||
+	    WARN_ON(dma_len + MT_DMA_HDRS > data_len) ||
+	    WARN_ON(dma_len & 0x3))
+		return 0;
+
+	return MT_DMA_HDRS + dma_len;
+}
+
+static void
+mt76x0_rx_process_entry(struct mt76x0_dev *dev, struct mt76x0_dma_buf_rx *e)
+{
+	u32 seg_len, data_len = e->urb->actual_length;
+	u8 *data = page_address(e->p);
+	struct page *new_p = NULL;
+	int cnt = 0;
+
+	if (!test_bit(MT76_STATE_INITIALIZED, &dev->mt76.state))
+		return;
+
+	/* Copy if there is very little data in the buffer. */
+	if (data_len > 512)
+		new_p = dev_alloc_pages(MT_RX_ORDER);
+
+	while ((seg_len = mt76x0_rx_next_seg_len(data, data_len))) {
+		mt76x0_rx_process_seg(dev, data, seg_len, new_p ? e->p : NULL);
+
+		data_len -= seg_len;
+		data += seg_len;
+		cnt++;
+	}
+
+	if (cnt > 1)
+		trace_mt_rx_dma_aggr(&dev->mt76, cnt, !!new_p);
+
+	if (new_p) {
+		/* we have one extra ref from the allocator */
+		__free_pages(e->p, MT_RX_ORDER);
+
+		e->p = new_p;
+	}
+}
+
+static struct mt76x0_dma_buf_rx *
+mt76x0_rx_get_pending_entry(struct mt76x0_dev *dev)
+{
+	struct mt76x0_rx_queue *q = &dev->rx_q;
+	struct mt76x0_dma_buf_rx *buf = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->rx_lock, flags);
+
+	if (!q->pending)
+		goto out;
+
+	buf = &q->e[q->start];
+	q->pending--;
+	q->start = (q->start + 1) % q->entries;
+out:
+	spin_unlock_irqrestore(&dev->rx_lock, flags);
+
+	return buf;
+}
+
+static void mt76x0_complete_rx(struct urb *urb)
+{
+	struct mt76x0_dev *dev = urb->context;
+	struct mt76x0_rx_queue *q = &dev->rx_q;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->rx_lock, flags);
+
+	if (mt76x0_urb_has_error(urb))
+		dev_err(dev->mt76.dev, "Error: RX urb failed:%d\n", urb->status);
+	if (WARN_ONCE(q->e[q->end].urb != urb, "RX urb mismatch"))
+		goto out;
+
+	q->end = (q->end + 1) % q->entries;
+	q->pending++;
+	tasklet_schedule(&dev->rx_tasklet);
+out:
+	spin_unlock_irqrestore(&dev->rx_lock, flags);
+}
+
+static void mt76x0_rx_tasklet(unsigned long data)
+{
+	struct mt76x0_dev *dev = (struct mt76x0_dev *) data;
+	struct mt76x0_dma_buf_rx *e;
+
+	while ((e = mt76x0_rx_get_pending_entry(dev))) {
+		if (e->urb->status)
+			continue;
+
+		mt76x0_rx_process_entry(dev, e);
+		mt76x0_submit_rx_buf(dev, e, GFP_ATOMIC);
+	}
+}
+
+static void mt76x0_complete_tx(struct urb *urb)
+{
+	struct mt76x0_tx_queue *q = urb->context;
+	struct mt76x0_dev *dev = q->dev;
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+
+	if (mt76x0_urb_has_error(urb))
+		dev_err(dev->mt76.dev, "Error: TX urb failed:%d\n", urb->status);
+	if (WARN_ONCE(q->e[q->start].urb != urb, "TX urb mismatch"))
+		goto out;
+
+	skb = q->e[q->start].skb;
+	trace_mt_tx_dma_done(&dev->mt76, skb);
+
+	__skb_queue_tail(&dev->tx_skb_done, skb);
+	tasklet_schedule(&dev->tx_tasklet);
+
+	if (q->used == q->entries - q->entries / 8)
+		ieee80211_wake_queue(dev->mt76.hw, skb_get_queue_mapping(skb));
+
+	q->start = (q->start + 1) % q->entries;
+	q->used--;
+out:
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+}
+
+static void mt76x0_tx_tasklet(unsigned long data)
+{
+	struct mt76x0_dev *dev = (struct mt76x0_dev *) data;
+	struct sk_buff_head skbs;
+	unsigned long flags;
+
+	__skb_queue_head_init(&skbs);
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+
+	set_bit(MT76_MORE_STATS, &dev->mt76.state);
+	if (!test_and_set_bit(MT76_READING_STATS, &dev->mt76.state))
+		queue_delayed_work(dev->stat_wq, &dev->stat_work,
+				   msecs_to_jiffies(10));
+
+	skb_queue_splice_init(&dev->tx_skb_done, &skbs);
+
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+
+	while (!skb_queue_empty(&skbs)) {
+		struct sk_buff *skb = __skb_dequeue(&skbs);
+
+		mt76x0_tx_status(dev, skb);
+	}
+}
+
+static int mt76x0_dma_submit_tx(struct mt76x0_dev *dev,
+				 struct sk_buff *skb, u8 ep)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	unsigned snd_pipe = usb_sndbulkpipe(usb_dev, dev->out_ep[ep]);
+	struct mt76x0_dma_buf_tx *e;
+	struct mt76x0_tx_queue *q = &dev->tx_q[ep];
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+
+	if (WARN_ON_ONCE(q->entries <= q->used)) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	e = &q->e[q->end];
+	e->skb = skb;
+	usb_fill_bulk_urb(e->urb, usb_dev, snd_pipe, skb->data, skb->len,
+			  mt76x0_complete_tx, q);
+	ret = usb_submit_urb(e->urb, GFP_ATOMIC);
+	if (ret) {
+		/* Special-handle ENODEV from TX urb submission because it will
+		 * often be the first ENODEV we see after device is removed.
+		 */
+		if (ret == -ENODEV)
+			set_bit(MT76_REMOVED, &dev->mt76.state);
+		else
+			dev_err(dev->mt76.dev, "Error: TX urb submit failed:%d\n",
+				ret);
+		goto out;
+	}
+
+	q->end = (q->end + 1) % q->entries;
+	q->used++;
+
+	if (q->used >= q->entries)
+		ieee80211_stop_queue(dev->mt76.hw, skb_get_queue_mapping(skb));
+out:
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+
+	return ret;
+}
+
+/* Map USB endpoint number to Q id in the DMA engine */
+static enum mt76_qsel ep2dmaq(u8 ep)
+{
+	if (ep == 5)
+		return MT_QSEL_MGMT;
+	return MT_QSEL_EDCA;
+}
+
+int mt76x0_dma_enqueue_tx(struct mt76x0_dev *dev, struct sk_buff *skb,
+			   struct mt76_wcid *wcid, int hw_q)
+{
+	u8 ep = q2ep(hw_q);
+	u32 dma_flags;
+	int ret;
+
+	dma_flags = MT_TXD_PKT_INFO_80211;
+	if (wcid->hw_key_idx == 0xff)
+		dma_flags |= MT_TXD_PKT_INFO_WIV;
+
+	ret = mt76x0_dma_skb_wrap_pkt(skb, ep2dmaq(ep), dma_flags);
+	if (ret)
+		return ret;
+
+	ret = mt76x0_dma_submit_tx(dev, skb, ep);
+
+	if (ret) {
+		ieee80211_free_txskb(dev->mt76.hw, skb);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void mt76x0_kill_rx(struct mt76x0_dev *dev)
+{
+	int i;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->rx_lock, flags);
+
+	for (i = 0; i < dev->rx_q.entries; i++) {
+		int next = dev->rx_q.end;
+
+		spin_unlock_irqrestore(&dev->rx_lock, flags);
+		usb_poison_urb(dev->rx_q.e[next].urb);
+		spin_lock_irqsave(&dev->rx_lock, flags);
+	}
+
+	spin_unlock_irqrestore(&dev->rx_lock, flags);
+}
+
+static int mt76x0_submit_rx_buf(struct mt76x0_dev *dev,
+				 struct mt76x0_dma_buf_rx *e, gfp_t gfp)
+{
+	struct usb_device *usb_dev = mt76x0_to_usb_dev(dev);
+	u8 *buf = page_address(e->p);
+	unsigned pipe;
+	int ret;
+
+	pipe = usb_rcvbulkpipe(usb_dev, dev->in_ep[MT_EP_IN_PKT_RX]);
+
+	usb_fill_bulk_urb(e->urb, usb_dev, pipe, buf, MT_RX_URB_SIZE,
+			  mt76x0_complete_rx, dev);
+
+	trace_mt_submit_urb(&dev->mt76, e->urb);
+	ret = usb_submit_urb(e->urb, gfp);
+	if (ret)
+		dev_err(dev->mt76.dev, "Error: submit RX URB failed:%d\n", ret);
+
+	return ret;
+}
+
+static int mt76x0_submit_rx(struct mt76x0_dev *dev)
+{
+	int i, ret;
+
+	for (i = 0; i < dev->rx_q.entries; i++) {
+		ret = mt76x0_submit_rx_buf(dev, &dev->rx_q.e[i], GFP_KERNEL);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void mt76x0_free_rx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < dev->rx_q.entries; i++) {
+		__free_pages(dev->rx_q.e[i].p, MT_RX_ORDER);
+		usb_free_urb(dev->rx_q.e[i].urb);
+	}
+}
+
+static int mt76x0_alloc_rx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	memset(&dev->rx_q, 0, sizeof(dev->rx_q));
+	dev->rx_q.dev = dev;
+	dev->rx_q.entries = N_RX_ENTRIES;
+
+	for (i = 0; i < N_RX_ENTRIES; i++) {
+		dev->rx_q.e[i].urb = usb_alloc_urb(0, GFP_KERNEL);
+		dev->rx_q.e[i].p = dev_alloc_pages(MT_RX_ORDER);
+
+		if (!dev->rx_q.e[i].urb || !dev->rx_q.e[i].p)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void mt76x0_free_tx_queue(struct mt76x0_tx_queue *q)
+{
+	int i;
+
+	WARN_ON(q->used);
+
+	for (i = 0; i < q->entries; i++)  {
+		usb_poison_urb(q->e[i].urb);
+		usb_free_urb(q->e[i].urb);
+	}
+}
+
+static void mt76x0_free_tx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	for (i = 0; i < __MT_EP_OUT_MAX; i++)
+		mt76x0_free_tx_queue(&dev->tx_q[i]);
+}
+
+static int mt76x0_alloc_tx_queue(struct mt76x0_dev *dev,
+				  struct mt76x0_tx_queue *q)
+{
+	int i;
+
+	q->dev = dev;
+	q->entries = N_TX_ENTRIES;
+
+	for (i = 0; i < N_TX_ENTRIES; i++) {
+		q->e[i].urb = usb_alloc_urb(0, GFP_KERNEL);
+		if (!q->e[i].urb)
+			return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int mt76x0_alloc_tx(struct mt76x0_dev *dev)
+{
+	int i;
+
+	dev->tx_q = devm_kcalloc(dev->mt76.dev, __MT_EP_OUT_MAX,
+				 sizeof(*dev->tx_q), GFP_KERNEL);
+
+	for (i = 0; i < __MT_EP_OUT_MAX; i++)
+		if (mt76x0_alloc_tx_queue(dev, &dev->tx_q[i]))
+			return -ENOMEM;
+
+	return 0;
+}
+
+int mt76x0_dma_init(struct mt76x0_dev *dev)
+{
+	int ret = -ENOMEM;
+
+	tasklet_init(&dev->tx_tasklet, mt76x0_tx_tasklet, (unsigned long) dev);
+	tasklet_init(&dev->rx_tasklet, mt76x0_rx_tasklet, (unsigned long) dev);
+
+	ret = mt76x0_alloc_tx(dev);
+	if (ret)
+		goto err;
+	ret = mt76x0_alloc_rx(dev);
+	if (ret)
+		goto err;
+
+	ret = mt76x0_submit_rx(dev);
+	if (ret)
+		goto err;
+
+	return 0;
+err:
+	mt76x0_dma_cleanup(dev);
+	return ret;
+}
+
+void mt76x0_dma_cleanup(struct mt76x0_dev *dev)
+{
+	mt76x0_kill_rx(dev);
+
+	tasklet_kill(&dev->rx_tasklet);
+
+	mt76x0_free_rx(dev);
+	mt76x0_free_tx(dev);
+
+	tasklet_kill(&dev->tx_tasklet);
+}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.h b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.h
new file mode 100644
index 000000000000..891ce1c3461f
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.h
@@ -0,0 +1,126 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#ifndef __MT76X0U_DMA_H
+#define __MT76X0U_DMA_H
+
+#include <asm/unaligned.h>
+#include <linux/skbuff.h>
+
+#define MT_DMA_HDR_LEN			4
+#define MT_RX_INFO_LEN			4
+#define MT_FCE_INFO_LEN			4
+#define MT_DMA_HDRS			(MT_DMA_HDR_LEN + MT_RX_INFO_LEN)
+
+/* Common Tx DMA descriptor fields */
+#define MT_TXD_INFO_LEN		GENMASK(15, 0)
+#define MT_TXD_INFO_D_PORT	GENMASK(29, 27)
+#define MT_TXD_INFO_TYPE	GENMASK(31, 30)
+
+/* Tx DMA MCU command specific flags */
+#define MT_TXD_CMD_SEQ		GENMASK(19, 16)
+#define MT_TXD_CMD_TYPE		GENMASK(26, 20)
+
+enum mt76_msg_port {
+	WLAN_PORT,
+	CPU_RX_PORT,
+	CPU_TX_PORT,
+	HOST_PORT,
+	VIRTUAL_CPU_RX_PORT,
+	VIRTUAL_CPU_TX_PORT,
+	DISCARD,
+};
+
+enum mt76_info_type {
+	DMA_PACKET,
+	DMA_COMMAND,
+};
+
+/* Tx DMA packet specific flags */
+#define MT_TXD_PKT_INFO_NEXT_VLD	BIT(16)
+#define MT_TXD_PKT_INFO_TX_BURST	BIT(17)
+#define MT_TXD_PKT_INFO_80211		BIT(19)
+#define MT_TXD_PKT_INFO_TSO		BIT(20)
+#define MT_TXD_PKT_INFO_CSO		BIT(21)
+#define MT_TXD_PKT_INFO_WIV		BIT(24)
+#define MT_TXD_PKT_INFO_QSEL		GENMASK(26, 25)
+
+enum mt76_qsel {
+	MT_QSEL_MGMT,
+	MT_QSEL_HCCA,
+	MT_QSEL_EDCA,
+	MT_QSEL_EDCA_2,
+};
+
+
+static inline int mt76x0_dma_skb_wrap(struct sk_buff *skb,
+				       enum mt76_msg_port d_port,
+				       enum mt76_info_type type, u32 flags)
+{
+	u32 info;
+
+	/* Buffer layout:
+	 *	|   4B   | xfer len |      pad       |  4B  |
+	 *	| TXINFO | pkt/cmd  | zero pad to 4B | zero |
+	 *
+	 * length field of TXINFO should be set to 'xfer len'.
+	 */
+
+	info = flags |
+		FIELD_PREP(MT_TXD_INFO_LEN, round_up(skb->len, 4)) |
+		FIELD_PREP(MT_TXD_INFO_D_PORT, d_port) |
+		FIELD_PREP(MT_TXD_INFO_TYPE, type);
+
+	put_unaligned_le32(info, skb_push(skb, sizeof(info)));
+	return skb_put_padto(skb, round_up(skb->len, 4) + 4);
+}
+
+static inline int
+mt76x0_dma_skb_wrap_pkt(struct sk_buff *skb, enum mt76_qsel qsel, u32 flags)
+{
+	flags |= FIELD_PREP(MT_TXD_PKT_INFO_QSEL, qsel);
+	return mt76x0_dma_skb_wrap(skb, WLAN_PORT, DMA_PACKET, flags);
+}
+
+/* Common Rx DMA descriptor fields */
+#define MT_RXD_INFO_LEN			GENMASK(13, 0)
+#define MT_RXD_INFO_PCIE_INTR		BIT(24)
+#define MT_RXD_INFO_QSEL		GENMASK(26, 25)
+#define MT_RXD_INFO_PORT		GENMASK(29, 27)
+#define MT_RXD_INFO_TYPE		GENMASK(31, 30)
+
+/* Rx DMA packet specific flags */
+#define MT_RXD_PKT_INFO_UDP_ERR		BIT(16)
+#define MT_RXD_PKT_INFO_TCP_ERR		BIT(17)
+#define MT_RXD_PKT_INFO_IP_ERR		BIT(18)
+#define MT_RXD_PKT_INFO_PKT_80211	BIT(19)
+#define MT_RXD_PKT_INFO_L3L4_DONE	BIT(20)
+#define MT_RXD_PKT_INFO_MAC_LEN		GENMASK(23, 21)
+
+/* Rx DMA MCU command specific flags */
+#define MT_RXD_CMD_INFO_SELF_GEN	BIT(15)
+#define MT_RXD_CMD_INFO_CMD_SEQ		GENMASK(19, 16)
+#define MT_RXD_CMD_INFO_EVT_TYPE	GENMASK(23, 20)
+
+enum mt76_evt_type {
+	CMD_DONE,
+	CMD_ERROR,
+	CMD_RETRY,
+	EVENT_PWR_RSP,
+	EVENT_WOW_RSP,
+	EVENT_CARRIER_DETECT_RSP,
+	EVENT_DFS_DETECT_RSP,
+};
+
+#endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
new file mode 100644
index 000000000000..28b8e1508016
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
@@ -0,0 +1,270 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "trace.h"
+
+/* Take mac80211 Q id from the skb and translate it to hardware Q id */
+static u8 skb2q(struct sk_buff *skb)
+{
+	int qid = skb_get_queue_mapping(skb);
+
+	if (WARN_ON(qid >= MT_TXQ_PSD)) {
+		qid = MT_TXQ_BE;
+		skb_set_queue_mapping(skb, qid);
+	}
+
+	return q2hwq(qid);
+}
+
+static void mt76x0_tx_skb_remove_dma_overhead(struct sk_buff *skb,
+					       struct ieee80211_tx_info *info)
+{
+	int pkt_len = (unsigned long)info->status.status_driver_data[0];
+
+	skb_pull(skb, sizeof(struct mt76_txwi) + 4);
+	if (ieee80211_get_hdrlen_from_skb(skb) % 4)
+		mt76_remove_hdr_pad(skb);
+
+	skb_trim(skb, pkt_len);
+}
+
+void mt76x0_tx_status(struct mt76x0_dev *dev, struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	mt76x0_tx_skb_remove_dma_overhead(skb, info);
+
+	ieee80211_tx_info_clear_status(info);
+	info->status.rates[0].idx = -1;
+	info->flags |= IEEE80211_TX_STAT_ACK;
+
+	spin_lock(&dev->mac_lock);
+	ieee80211_tx_status(dev->mt76.hw, skb);
+	spin_unlock(&dev->mac_lock);
+}
+
+static int mt76x0_skb_rooms(struct mt76x0_dev *dev, struct sk_buff *skb)
+{
+	int hdr_len = ieee80211_get_hdrlen_from_skb(skb);
+	u32 need_head;
+
+	need_head = sizeof(struct mt76_txwi) + 4;
+	if (hdr_len % 4)
+		need_head += 2;
+
+	return skb_cow(skb, need_head);
+}
+
+static struct mt76_txwi *
+mt76x0_push_txwi(struct mt76x0_dev *dev, struct sk_buff *skb,
+		  struct ieee80211_sta *sta, struct mt76_wcid *wcid,
+		  int pkt_len)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_tx_rate *rate = &info->control.rates[0];
+	struct mt76_txwi *txwi;
+	unsigned long flags;
+	u16 txwi_flags = 0;
+	u32 pkt_id;
+	u16 rate_ctl;
+	u8 nss;
+
+	txwi = (struct mt76_txwi *)skb_push(skb, sizeof(struct mt76_txwi));
+	memset(txwi, 0, sizeof(*txwi));
+
+	if (!wcid->tx_rate_set)
+		ieee80211_get_tx_rates(info->control.vif, sta, skb,
+				       info->control.rates, 1);
+
+	spin_lock_irqsave(&dev->mt76.lock, flags);
+	if (rate->idx < 0 || !rate->count) {
+		rate_ctl = wcid->tx_rate;
+		nss = wcid->tx_rate_nss;
+	} else {
+		rate_ctl = mt76_mac_tx_rate_val(dev, rate, &nss);
+	}
+	spin_unlock_irqrestore(&dev->mt76.lock, flags);
+
+	txwi->rate_ctl = cpu_to_le16(rate_ctl);
+
+	if (info->flags & IEEE80211_TX_CTL_LDPC)
+		txwi->rate_ctl |= cpu_to_le16(MT_RXWI_RATE_LDPC);
+	if ((info->flags & IEEE80211_TX_CTL_STBC) && nss == 1)
+		txwi->rate_ctl |= cpu_to_le16(MT_RXWI_RATE_STBC);
+	if (nss > 1 && sta && sta->smps_mode == IEEE80211_SMPS_DYNAMIC)
+		txwi_flags |= MT_TXWI_FLAGS_MMPS;
+
+	if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_REQ;
+		pkt_id = 1;
+	} else {
+		pkt_id = 0;
+	}
+
+	if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE)
+		pkt_id |= MT_TXWI_PKTID_PROBE;
+
+	if (info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)
+		txwi->ack_ctl |= MT_TXWI_ACK_CTL_NSEQ;
+
+	if ((info->flags & IEEE80211_TX_CTL_AMPDU) && sta) {
+		u8 ba_size = IEEE80211_MIN_AMPDU_BUF;
+
+		ba_size <<= sta->ht_cap.ampdu_factor;
+		ba_size = min_t(int, 7, ba_size - 1);
+		if (info->flags & IEEE80211_TX_CTL_RATE_CTRL_PROBE) {
+			ba_size = 0;
+		} else {
+			txwi_flags |= MT_TXWI_FLAGS_AMPDU;
+			txwi_flags |= FIELD_PREP(MT_TXWI_FLAGS_MPDU_DENSITY,
+						 sta->ht_cap.ampdu_density);
+		}
+		txwi->ack_ctl |= FIELD_PREP(MT_TXWI_ACK_CTL_BA_WINDOW, ba_size);
+	}
+
+	txwi->wcid = wcid->idx;
+	txwi->flags |= cpu_to_le16(txwi_flags);
+	txwi->len_ctl = cpu_to_le16(pkt_len);
+	txwi->pktid = pkt_id;
+
+	return txwi;
+}
+
+void mt76x0_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
+		struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct mt76x0_dev *dev = hw->priv;
+	struct ieee80211_vif *vif = info->control.vif;
+	struct ieee80211_sta *sta = control->sta;
+	struct mt76_sta *msta = NULL;
+	struct mt76_wcid *wcid = dev->mon_wcid;
+	struct mt76_txwi *txwi;
+	int pkt_len = skb->len;
+	int hw_q = skb2q(skb);
+
+	BUILD_BUG_ON(ARRAY_SIZE(info->status.status_driver_data) < 1);
+	info->status.status_driver_data[0] = (void *)(unsigned long)pkt_len;
+
+	if (mt76x0_skb_rooms(dev, skb) || mt76_insert_hdr_pad(skb)) {
+		ieee80211_free_txskb(dev->mt76.hw, skb);
+		return;
+	}
+
+	if (sta) {
+		msta = (struct mt76_sta *) sta->drv_priv;
+		wcid = &msta->wcid;
+	} else if (vif && (!info->control.hw_key && wcid->hw_key_idx != -1)) {
+		struct mt76_vif *mvif = (struct mt76_vif *)vif->drv_priv;
+
+		wcid = &mvif->group_wcid;
+	}
+
+	txwi = mt76x0_push_txwi(dev, skb, sta, wcid, pkt_len);
+
+	if (mt76x0_dma_enqueue_tx(dev, skb, wcid, hw_q))
+		return;
+
+	trace_mt_tx(&dev->mt76, skb, msta, txwi);
+}
+
+void mt76x0_tx_stat(struct work_struct *work)
+{
+	struct mt76x0_dev *dev = container_of(work, struct mt76x0_dev,
+					       stat_work.work);
+	struct mt76_tx_status stat;
+	unsigned long flags;
+	int cleaned = 0;
+	u8 update = 1;
+
+	while (!test_bit(MT76_REMOVED, &dev->mt76.state)) {
+		stat = mt76x0_mac_fetch_tx_status(dev);
+		if (!stat.valid)
+			break;
+
+		mt76_send_tx_status(dev, &stat, &update);
+
+		cleaned++;
+	}
+	trace_mt_tx_status_cleaned(&dev->mt76, cleaned);
+
+	spin_lock_irqsave(&dev->tx_lock, flags);
+	if (cleaned)
+		queue_delayed_work(dev->stat_wq, &dev->stat_work,
+				   msecs_to_jiffies(10));
+	else if (test_and_clear_bit(MT76_MORE_STATS, &dev->mt76.state))
+		queue_delayed_work(dev->stat_wq, &dev->stat_work,
+				   msecs_to_jiffies(20));
+	else
+		clear_bit(MT76_READING_STATS, &dev->mt76.state);
+	spin_unlock_irqrestore(&dev->tx_lock, flags);
+}
+
+int mt76x0_conf_tx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		    u16 queue, const struct ieee80211_tx_queue_params *params)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	u8 cw_min = 5, cw_max = 10, hw_q = q2hwq(queue);
+	u32 val;
+
+	/* TODO: should we do funny things with the parameters?
+	 *	 See what mt76x0_set_default_edca() used to do in init.c.
+	 */
+
+	if (params->cw_min)
+		cw_min = fls(params->cw_min);
+	if (params->cw_max)
+		cw_max = fls(params->cw_max);
+
+	WARN_ON(params->txop > 0xff);
+	WARN_ON(params->aifs > 0xf);
+	WARN_ON(cw_min > 0xf);
+	WARN_ON(cw_max > 0xf);
+
+	val = FIELD_PREP(MT_EDCA_CFG_AIFSN, params->aifs) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMIN, cw_min) |
+	      FIELD_PREP(MT_EDCA_CFG_CWMAX, cw_max);
+	/* TODO: based on user-controlled EnableTxBurst var vendor drv sets
+	 *	 a really long txop on AC0 (see connect.c:2009) but only on
+	 *	 connect? When not connected should be 0.
+	 */
+	if (!hw_q)
+		val |= 0x60;
+	else
+		val |= FIELD_PREP(MT_EDCA_CFG_TXOP, params->txop);
+	mt76_wr(dev, MT_EDCA_CFG_AC(hw_q), val);
+
+	val = mt76_rr(dev, MT_WMM_TXOP(hw_q));
+	val &= ~(MT_WMM_TXOP_MASK << MT_WMM_TXOP_SHIFT(hw_q));
+	val |= params->txop << MT_WMM_TXOP_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_TXOP(hw_q), val);
+
+	val = mt76_rr(dev, MT_WMM_AIFSN);
+	val &= ~(MT_WMM_AIFSN_MASK << MT_WMM_AIFSN_SHIFT(hw_q));
+	val |= params->aifs << MT_WMM_AIFSN_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_AIFSN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMIN);
+	val &= ~(MT_WMM_CWMIN_MASK << MT_WMM_CWMIN_SHIFT(hw_q));
+	val |= cw_min << MT_WMM_CWMIN_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_CWMIN, val);
+
+	val = mt76_rr(dev, MT_WMM_CWMAX);
+	val &= ~(MT_WMM_CWMAX_MASK << MT_WMM_CWMAX_SHIFT(hw_q));
+	val |= cw_max << MT_WMM_CWMAX_SHIFT(hw_q);
+	mt76_wr(dev, MT_WMM_CWMAX, val);
+
+	return 0;
+}
-- 
cgit v1.2.3


From 95e444098a7b9d42dee36c80b75fe4500e7cf1e5 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:41:00 +0200
Subject: mt76x0: main file

Add main file of mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c | 403 +++++++++++++++++++++++
 1 file changed, 403 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/main.c

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
new file mode 100644
index 000000000000..0c521f3485c9
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -0,0 +1,403 @@
+/*
+ * Copyright (C) 2014 Felix Fietkau <nbd@openwrt.org>
+ * Copyright (C) 2015 Jakub Kicinski <kubakici@wp.pl>
+ * Copyright (C) 2018 Stanislaw Gruszka <stf_xl@wp.pl>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include "mt76x0.h"
+#include "mac.h"
+#include <linux/etherdevice.h>
+
+static int mt76x0_start(struct ieee80211_hw *hw)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	int ret;
+
+	mutex_lock(&dev->mutex);
+
+	ret = mt76x0_mac_start(dev);
+	if (ret)
+		goto out;
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->mac_work,
+				     MT_CALIBRATE_INTERVAL);
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+out:
+	mutex_unlock(&dev->mutex);
+	return ret;
+}
+
+static void mt76x0_stop(struct ieee80211_hw *hw)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+
+	cancel_delayed_work_sync(&dev->cal_work);
+	cancel_delayed_work_sync(&dev->mac_work);
+	mt76x0_mac_stop(dev);
+
+	mutex_unlock(&dev->mutex);
+}
+
+
+static int mt76x0_add_interface(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	unsigned int idx;
+
+	idx = ffs(~dev->vif_mask);
+	if (!idx || idx > 8)
+		return -ENOSPC;
+
+	idx--;
+	dev->vif_mask |= BIT(idx);
+
+	mvif->idx = idx;
+	mvif->group_wcid.idx = GROUP_WCID(idx);
+	mvif->group_wcid.hw_key_idx = -1;
+
+	return 0;
+}
+
+static void mt76x0_remove_interface(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	unsigned int wcid = mvif->group_wcid.idx;
+
+	dev->wcid_mask[wcid / BITS_PER_LONG] &= ~BIT(wcid % BITS_PER_LONG);
+}
+
+static int mt76x0_config(struct ieee80211_hw *hw, u32 changed)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	int ret = 0;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & IEEE80211_CONF_CHANGE_MONITOR) {
+		if (!(hw->conf.flags & IEEE80211_CONF_MONITOR))
+			dev->rxfilter |= MT_RX_FILTR_CFG_PROMISC;
+		else
+			dev->rxfilter &= ~MT_RX_FILTR_CFG_PROMISC;
+
+		mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+	}
+
+	if (changed & IEEE80211_CONF_CHANGE_CHANNEL) {
+		ieee80211_stop_queues(hw);
+		ret = mt76x0_phy_set_channel(dev, &hw->conf.chandef);
+		ieee80211_wake_queues(hw);
+	}
+
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+
+static void
+mt76_configure_filter(struct ieee80211_hw *hw, unsigned int changed_flags,
+		      unsigned int *total_flags, u64 multicast)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	u32 flags = 0;
+
+#define MT76_FILTER(_flag, _hw) do { \
+		flags |= *total_flags & FIF_##_flag;			\
+		dev->rxfilter &= ~(_hw);				\
+		dev->rxfilter |= !(flags & FIF_##_flag) * (_hw);	\
+	} while (0)
+
+	mutex_lock(&dev->mutex);
+
+	dev->rxfilter &= ~MT_RX_FILTR_CFG_OTHER_BSS;
+
+	MT76_FILTER(FCSFAIL, MT_RX_FILTR_CFG_CRC_ERR);
+	MT76_FILTER(PLCPFAIL, MT_RX_FILTR_CFG_PHY_ERR);
+	MT76_FILTER(CONTROL, MT_RX_FILTR_CFG_ACK |
+			     MT_RX_FILTR_CFG_CTS |
+			     MT_RX_FILTR_CFG_CFEND |
+			     MT_RX_FILTR_CFG_CFACK |
+			     MT_RX_FILTR_CFG_BA |
+			     MT_RX_FILTR_CFG_CTRL_RSV);
+	MT76_FILTER(PSPOLL, MT_RX_FILTR_CFG_PSPOLL);
+
+	*total_flags = flags;
+	mt76_wr(dev, MT_RX_FILTR_CFG, dev->rxfilter);
+
+	mutex_unlock(&dev->mutex);
+}
+
+static void
+mt76x0_bss_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ieee80211_bss_conf *info, u32 changed)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mutex_lock(&dev->mutex);
+
+	if (changed & BSS_CHANGED_ASSOC)
+		mt76x0_phy_con_cal_onoff(dev, info);
+
+	if (changed & BSS_CHANGED_BSSID) {
+		mt76x0_addr_wr(dev, MT_MAC_BSSID_DW0, info->bssid);
+
+		/* Note: this is a hack because beacon_int is not changed
+		 *	 on leave nor is any more appropriate event generated.
+		 *	 rt2x00 doesn't seem to be bothered though.
+		 */
+		if (is_zero_ether_addr(info->bssid))
+			mt76x0_mac_config_tsf(dev, false, 0);
+	}
+
+	if (changed & BSS_CHANGED_BASIC_RATES) {
+		mt76_wr(dev, MT_LEGACY_BASIC_RATE, info->basic_rates);
+		mt76_wr(dev, MT_HT_FBK_CFG0, 0x65432100);
+		mt76_wr(dev, MT_HT_FBK_CFG1, 0xedcba980);
+		mt76_wr(dev, MT_LG_FBK_CFG0, 0xedcba988);
+		mt76_wr(dev, MT_LG_FBK_CFG1, 0x00002100);
+	}
+
+	if (changed & BSS_CHANGED_BEACON_INT)
+		mt76x0_mac_config_tsf(dev, true, info->beacon_int);
+
+	if (changed & BSS_CHANGED_HT || changed & BSS_CHANGED_ERP_CTS_PROT)
+		mt76x0_mac_set_protection(dev, info->use_cts_prot,
+					   info->ht_operation_mode);
+
+	if (changed & BSS_CHANGED_ERP_PREAMBLE)
+		mt76x0_mac_set_short_preamble(dev, info->use_short_preamble);
+
+	if (changed & BSS_CHANGED_ERP_SLOT) {
+		int slottime = info->use_short_slot ? 9 : 20;
+
+		mt76_rmw_field(dev, MT_BKOFF_SLOT_CFG,
+			       MT_BKOFF_SLOT_CFG_SLOTTIME, slottime);
+	}
+
+	if (changed & BSS_CHANGED_ASSOC)
+		mt76x0_phy_recalibrate_after_assoc(dev);
+
+	mutex_unlock(&dev->mutex);
+}
+
+static int
+mt76x0_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		struct ieee80211_sta *sta)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	int ret = 0;
+	int idx = 0;
+
+	mutex_lock(&dev->mutex);
+
+	idx = mt76_wcid_alloc(dev->wcid_mask, ARRAY_SIZE(dev->wcid));
+	if (idx < 0) {
+		ret = -ENOSPC;
+		goto out;
+	}
+
+	msta->wcid.idx = idx;
+	msta->wcid.hw_key_idx = -1;
+	mt76x0_mac_wcid_setup(dev, idx, mvif->idx, sta->addr);
+	mt76_clear(dev, MT_WCID_DROP(idx), MT_WCID_DROP_MASK(idx));
+	rcu_assign_pointer(dev->wcid[idx], &msta->wcid);
+	mt76x0_mac_set_ampdu_factor(dev);
+
+out:
+	mutex_unlock(&dev->mutex);
+
+	return ret;
+}
+
+static int
+mt76x0_sta_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+	int idx = msta->wcid.idx;
+
+	mutex_lock(&dev->mutex);
+	rcu_assign_pointer(dev->wcid[idx], NULL);
+	mt76_set(dev, MT_WCID_DROP(idx), MT_WCID_DROP_MASK(idx));
+	dev->wcid_mask[idx / BITS_PER_LONG] &= ~BIT(idx % BITS_PER_LONG);
+	mt76x0_mac_wcid_setup(dev, idx, 0, NULL);
+	mt76x0_mac_set_ampdu_factor(dev);
+	mutex_unlock(&dev->mutex);
+
+	return 0;
+}
+
+static void
+mt76x0_sta_notify(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   enum sta_notify_cmd cmd, struct ieee80211_sta *sta)
+{
+}
+
+static void
+mt76x0_sw_scan(struct ieee80211_hw *hw,
+		struct ieee80211_vif *vif,
+		const u8 *mac_addr)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	cancel_delayed_work_sync(&dev->cal_work);
+	mt76x0_agc_save(dev);
+	set_bit(MT76_SCANNING, &dev->mt76.state);
+}
+
+static void
+mt76x0_sw_scan_complete(struct ieee80211_hw *hw,
+			 struct ieee80211_vif *vif)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mt76x0_agc_restore(dev);
+	clear_bit(MT76_SCANNING, &dev->mt76.state);
+
+	ieee80211_queue_delayed_work(dev->mt76.hw, &dev->cal_work,
+				     MT_CALIBRATE_INTERVAL);
+}
+
+static int
+mt76x0_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
+		struct ieee80211_vif *vif, struct ieee80211_sta *sta,
+		struct ieee80211_key_conf *key)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_vif *mvif = (struct mt76_vif *) vif->drv_priv;
+	struct mt76_sta *msta = sta ? (struct mt76_sta *) sta->drv_priv : NULL;
+	struct mt76_wcid *wcid = msta ? &msta->wcid : &mvif->group_wcid;
+	int idx = key->keyidx;
+	int ret;
+
+	if (cmd == SET_KEY) {
+		key->hw_key_idx = wcid->idx;
+		wcid->hw_key_idx = idx;
+	} else {
+		if (idx == wcid->hw_key_idx)
+			wcid->hw_key_idx = -1;
+
+		key = NULL;
+	}
+
+	if (!msta) {
+		if (key || wcid->hw_key_idx == idx) {
+			ret = mt76_mac_wcid_set_key(dev, wcid->idx, key);
+			if (ret)
+				return ret;
+		}
+
+		return mt76_mac_shared_key_setup(dev, mvif->idx, idx, key);
+	}
+
+	return mt76_mac_wcid_set_key(dev, msta->wcid.idx, key);
+}
+
+static int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
+{
+	struct mt76x0_dev *dev = hw->priv;
+
+	mt76_rmw_field(dev, MT_TX_RTS_CFG, MT_TX_RTS_CFG_THRESH, value);
+
+	return 0;
+}
+
+static int
+mt76_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  struct ieee80211_ampdu_params *params)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 *ssn = &params->ssn;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+
+	WARN_ON(msta->wcid.idx > N_WCIDS);
+
+	switch (action) {
+	case IEEE80211_AMPDU_RX_START:
+		mt76_set(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_RX_STOP:
+		mt76_clear(dev, MT_WCID_ADDR(msta->wcid.idx) + 4, BIT(16 + tid));
+		break;
+	case IEEE80211_AMPDU_TX_OPERATIONAL:
+		ieee80211_send_bar(vif, sta->addr, tid, msta->agg_ssn[tid]);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_FLUSH:
+	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
+		break;
+	case IEEE80211_AMPDU_TX_START:
+		msta->agg_ssn[tid] = *ssn << 4;
+		ieee80211_start_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	case IEEE80211_AMPDU_TX_STOP_CONT:
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+		break;
+	}
+
+	return 0;
+}
+
+static void
+mt76_sta_rate_tbl_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta)
+{
+	struct mt76x0_dev *dev = hw->priv;
+	struct mt76_sta *msta = (struct mt76_sta *) sta->drv_priv;
+	struct ieee80211_sta_rates *rates;
+	struct ieee80211_tx_rate rate = {};
+
+	rcu_read_lock();
+	rates = rcu_dereference(sta->rates);
+
+	if (!rates)
+		goto out;
+
+	rate.idx = rates->rate[0].idx;
+	rate.flags = rates->rate[0].flags;
+	mt76_mac_wcid_set_rate(dev, &msta->wcid, &rate);
+
+out:
+	rcu_read_unlock();
+}
+
+const struct ieee80211_ops mt76x0_ops = {
+	.tx = mt76x0_tx,
+	.start = mt76x0_start,
+	.stop = mt76x0_stop,
+	.add_interface = mt76x0_add_interface,
+	.remove_interface = mt76x0_remove_interface,
+	.config = mt76x0_config,
+	.configure_filter = mt76_configure_filter,
+	.bss_info_changed = mt76x0_bss_info_changed,
+	.sta_add = mt76x0_sta_add,
+	.sta_remove = mt76x0_sta_remove,
+	.sta_notify = mt76x0_sta_notify,
+	.set_key = mt76x0_set_key,
+	.conf_tx = mt76x0_conf_tx,
+	.sw_scan_start = mt76x0_sw_scan,
+	.sw_scan_complete = mt76x0_sw_scan_complete,
+	.ampdu_action = mt76_ampdu_action,
+	.sta_rate_tbl_update = mt76_sta_rate_tbl_update,
+	.set_rts_threshold = mt76x0_set_rts_threshold,
+};
-- 
cgit v1.2.3


From 87e022de330a26ad792056ec8d2602c13481e4a2 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:41:01 +0200
Subject: mt76: add more states

Add states needed for mt76x0 driver.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 4bf1b35ec44c..2eab35879163 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -204,11 +204,13 @@ struct mt76_rx_tid {
 enum {
 	MT76_STATE_INITIALIZED,
 	MT76_STATE_RUNNING,
+	MT76_STATE_MCU_RUNNING,
 	MT76_SCANNING,
 	MT76_RESET,
 	MT76_OFFCHANNEL,
 	MT76_REMOVED,
 	MT76_READING_STATS,
+	MT76_MORE_STATS,
 };
 
 struct mt76_hw_cap {
-- 
cgit v1.2.3


From 52abb142baa0f35291ac2f12b56e56fa071b95d8 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:41:02 +0200
Subject: mt76: Kconfig and Makefile for mt76x0 driver

Add Kconfig and Makefiles for mt76x0 driver. Now the driver
can be build.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Kconfig         | 7 +++++++
 drivers/net/wireless/mediatek/mt76/Makefile        | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/Makefile | 7 +++++++
 3 files changed, 15 insertions(+)
 create mode 100644 drivers/net/wireless/mediatek/mt76/mt76x0/Makefile

diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index 69906c733a1c..850611ad347a 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -9,6 +9,13 @@ config MT76x2_COMMON
 	tristate
 	depends on MT76_CORE
 
+config MT76x0U
+	tristate "MediaTek MT76x0U (USB) support"
+	depends on MAC80211
+	depends on USB
+	help
+	  This adds support for MT7610U-based wireless USB dongles.
+
 config MT76x2E
 	tristate "MediaTek MT76x2E (PCIe) support"
 	select MT76_CORE
diff --git a/drivers/net/wireless/mediatek/mt76/Makefile b/drivers/net/wireless/mediatek/mt76/Makefile
index dfe1c1ba60db..158d10d2716c 100644
--- a/drivers/net/wireless/mediatek/mt76/Makefile
+++ b/drivers/net/wireless/mediatek/mt76/Makefile
@@ -1,5 +1,6 @@
 obj-$(CONFIG_MT76_CORE) += mt76.o
 obj-$(CONFIG_MT76_USB) += mt76-usb.o
+obj-$(CONFIG_MT76x0U) += mt76x0/
 obj-$(CONFIG_MT76x2_COMMON) += mt76x2-common.o
 obj-$(CONFIG_MT76x2E) += mt76x2e.o
 obj-$(CONFIG_MT76x2U) += mt76x2u.o
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
new file mode 100644
index 000000000000..7843908261ba
--- /dev/null
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_MT76x0U)    += mt76x0.o
+
+mt76x0-objs	= \
+	usb.o init.o main.o mcu.o trace.o dma.o eeprom.o phy.o \
+	mac.o util.o debugfs.o tx.o core.o
+# ccflags-y := -DDEBUG
+CFLAGS_trace.o := -I$(src)
-- 
cgit v1.2.3


From 369bbecdbb2def6265c06512c44e1fbe6ad8e556 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:41:03 +0200
Subject: mt76x0: disable HW before probe

Disable HW before probe, otherwise after reboot we will fail
to initialize MCU.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/init.c   | 2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    | 4 ++++
 3 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
index b65b76d80906..7cdb3e740522 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/init.c
@@ -62,7 +62,7 @@ mt76x0_set_wlan_state(struct mt76x0_dev *dev, u32 val, bool enable)
 		dev_err(dev->mt76.dev, "Error: PLL and XTAL check failed!\n");
 }
 
-static void mt76x0_chip_onoff(struct mt76x0_dev *dev, bool enable, bool reset)
+void mt76x0_chip_onoff(struct mt76x0_dev *dev, bool enable, bool reset)
 {
 	u32 val;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 49b82a23533c..9e60fcb14687 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -288,6 +288,7 @@ struct mt76x0_dev *mt76x0_alloc_device(struct device *dev);
 int mt76x0_init_hardware(struct mt76x0_dev *dev);
 int mt76x0_register_device(struct mt76x0_dev *dev);
 void mt76x0_cleanup(struct mt76x0_dev *dev);
+void mt76x0_chip_onoff(struct mt76x0_dev *dev, bool enable, bool reset);
 
 int mt76x0_mac_start(struct mt76x0_dev *dev);
 void mt76x0_mac_stop(struct mt76x0_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 0871fdef59c3..7a635cdcbae0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -283,6 +283,10 @@ static int mt76x0_probe(struct usb_interface *usb_intf,
 	ret = mt76x0_assign_pipes(usb_intf, dev);
 	if (ret)
 		goto err;
+
+	/* Disable the HW, otherwise MCU fail to initalize on hot reboot */
+	mt76x0_chip_onoff(dev, false, false);
+
 	ret = mt76x0_wait_asic_ready(dev);
 	if (ret)
 		goto err;
-- 
cgit v1.2.3


From a33ce21e2afcdc29b749f74a5ec489595c417907 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 31 Jul 2018 14:41:04 +0200
Subject: mt76x0: load firmware from mediatek subdir

Firmware blob will be located in mediatek subdirectory. Add "u" suffix
to indicate this is USB device firmware.

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h
index 9e42dfa665de..492e431390a8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.h
@@ -16,7 +16,7 @@
 
 #include "mt76x0.h"
 
-#define MT7610_FIRMWARE	"mt7610.bin"
+#define MT7610_FIRMWARE	"mediatek/mt7610u.bin"
 
 #define MT_VEND_REQ_MAX_RETRY	10
 #define MT_VEND_REQ_TOUT_MS	300
-- 
cgit v1.2.3


From 28b9188483908b2579fc4bbb2ec07e9ffdca69f7 Mon Sep 17 00:00:00 2001
From: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Date: Thu, 2 Aug 2018 13:40:43 +0300
Subject: qtnfmac: implement basic WoWLAN support

This patch implements basic WoWLAN support in qtnfmac driver, including
processing of WoWLAN features reported by firmware and implementation
of cfg80211 suspend/resume/wakeup callbacks. Currently the following
WoWLAN triggers are supported: disconnect, magic packet,
custom pattern packet.

Signed-off-by: Sergey Matyukevich <sergey.matyukevich.os@quantenna.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/quantenna/qtnfmac/cfg80211.c |  76 +++++++++++++++
 drivers/net/wireless/quantenna/qtnfmac/commands.c | 112 ++++++++++++++++++++++
 drivers/net/wireless/quantenna/qtnfmac/commands.h |   2 +
 drivers/net/wireless/quantenna/qtnfmac/core.c     |   1 +
 drivers/net/wireless/quantenna/qtnfmac/core.h     |   1 +
 drivers/net/wireless/quantenna/qtnfmac/qlink.h    |  56 +++++++++++
 6 files changed, 248 insertions(+)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
index 0032fa9fdddd..4aa332f4646b 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/cfg80211.c
@@ -859,6 +859,72 @@ static int qtnf_set_power_mgmt(struct wiphy *wiphy, struct net_device *dev,
 	return ret;
 }
 
+#ifdef CONFIG_PM
+static int qtnf_suspend(struct wiphy *wiphy, struct cfg80211_wowlan *wowlan)
+{
+	struct qtnf_wmac *mac = wiphy_priv(wiphy);
+	struct qtnf_vif *vif;
+	int ret = 0;
+
+	vif = qtnf_mac_get_base_vif(mac);
+	if (!vif) {
+		pr_err("MAC%u: primary VIF is not configured\n", mac->macid);
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	if (!wowlan) {
+		pr_debug("WoWLAN triggers are not enabled\n");
+		qtnf_virtual_intf_cleanup(vif->netdev);
+		goto exit;
+	}
+
+	qtnf_scan_done(vif->mac, true);
+
+	ret = qtnf_cmd_send_wowlan_set(vif, wowlan);
+	if (ret) {
+		pr_err("MAC%u: failed to set WoWLAN triggers\n",
+		       mac->macid);
+		goto exit;
+	}
+
+exit:
+	return ret;
+}
+
+static int qtnf_resume(struct wiphy *wiphy)
+{
+	struct qtnf_wmac *mac = wiphy_priv(wiphy);
+	struct qtnf_vif *vif;
+	int ret = 0;
+
+	vif = qtnf_mac_get_base_vif(mac);
+	if (!vif) {
+		pr_err("MAC%u: primary VIF is not configured\n", mac->macid);
+		ret = -EFAULT;
+		goto exit;
+	}
+
+	ret = qtnf_cmd_send_wowlan_set(vif, NULL);
+	if (ret) {
+		pr_err("MAC%u: failed to reset WoWLAN triggers\n",
+		       mac->macid);
+		goto exit;
+	}
+
+exit:
+	return ret;
+}
+
+static void qtnf_set_wakeup(struct wiphy *wiphy, bool enabled)
+{
+	struct qtnf_wmac *mac = wiphy_priv(wiphy);
+	struct qtnf_bus *bus = mac->bus;
+
+	device_set_wakeup_enable(bus->dev, enabled);
+}
+#endif
+
 static struct cfg80211_ops qtn_cfg80211_ops = {
 	.add_virtual_intf	= qtnf_add_virtual_intf,
 	.change_virtual_intf	= qtnf_change_virtual_intf,
@@ -886,6 +952,11 @@ static struct cfg80211_ops qtn_cfg80211_ops = {
 	.start_radar_detection	= qtnf_start_radar_detection,
 	.set_mac_acl		= qtnf_set_mac_acl,
 	.set_power_mgmt		= qtnf_set_power_mgmt,
+#ifdef CONFIG_PM
+	.suspend		= qtnf_suspend,
+	.resume			= qtnf_resume,
+	.set_wakeup		= qtnf_set_wakeup,
+#endif
 };
 
 static void qtnf_cfg80211_reg_notifier(struct wiphy *wiphy_in,
@@ -1038,6 +1109,11 @@ int qtnf_wiphy_register(struct qtnf_hw_info *hw_info, struct qtnf_wmac *mac)
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_SCAN_RANDOM_MAC_ADDR)
 		wiphy->features |= NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR;
 
+#ifdef CONFIG_PM
+	if (macinfo->wowlan)
+		wiphy->wowlan = macinfo->wowlan;
+#endif
+
 	if (hw_info->hw_capab & QLINK_HW_CAPAB_REG_UPDATE) {
 		wiphy->regulatory_flags |= REGULATORY_STRICT_REG |
 			REGULATORY_CUSTOM_REG;
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.c b/drivers/net/wireless/quantenna/qtnfmac/commands.c
index 7942261961d6..ae9e77300533 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.c
@@ -1138,6 +1138,37 @@ qtnf_cmd_resp_proc_hw_info(struct qtnf_bus *bus,
 	return 0;
 }
 
+static void
+qtnf_parse_wowlan_info(struct qtnf_wmac *mac,
+		       const struct qlink_wowlan_capab_data *wowlan)
+{
+	struct qtnf_mac_info *mac_info = &mac->macinfo;
+	const struct qlink_wowlan_support *data1;
+	struct wiphy_wowlan_support *supp;
+
+	supp = kzalloc(sizeof(*supp), GFP_KERNEL);
+	if (!supp)
+		return;
+
+	switch (le16_to_cpu(wowlan->version)) {
+	case 0x1:
+		data1 = (struct qlink_wowlan_support *)wowlan->data;
+
+		supp->flags = WIPHY_WOWLAN_MAGIC_PKT | WIPHY_WOWLAN_DISCONNECT;
+		supp->n_patterns = le32_to_cpu(data1->n_patterns);
+		supp->pattern_max_len = le32_to_cpu(data1->pattern_max_len);
+		supp->pattern_min_len = le32_to_cpu(data1->pattern_min_len);
+
+		mac_info->wowlan = supp;
+		break;
+	default:
+		pr_warn("MAC%u: unsupported WoWLAN version 0x%x\n",
+			mac->macid, le16_to_cpu(wowlan->version));
+		kfree(supp);
+		break;
+	}
+}
+
 static int qtnf_parse_variable_mac_info(struct qtnf_wmac *mac,
 					const u8 *tlv_buf, size_t tlv_buf_size)
 {
@@ -1147,6 +1178,7 @@ static int qtnf_parse_variable_mac_info(struct qtnf_wmac *mac,
 	const struct qlink_iface_comb_num *comb_num;
 	const struct qlink_iface_limit_record *rec;
 	const struct qlink_iface_limit *lim;
+	const struct qlink_wowlan_capab_data *wowlan;
 	u16 rec_len;
 	u16 tlv_type;
 	u16 tlv_value_len;
@@ -1255,7 +1287,31 @@ static int qtnf_parse_variable_mac_info(struct qtnf_wmac *mac,
 			ext_capa_mask = (u8 *)tlv->val;
 			ext_capa_mask_len = tlv_value_len;
 			break;
+		case QTN_TLV_ID_WOWLAN_CAPAB:
+			if (tlv_value_len < sizeof(*wowlan))
+				return -EINVAL;
+
+			wowlan = (void *)tlv->val;
+			if (!le16_to_cpu(wowlan->len)) {
+				pr_warn("MAC%u: skip empty WoWLAN data\n",
+					mac->macid);
+				break;
+			}
+
+			rec_len = sizeof(*wowlan) + le16_to_cpu(wowlan->len);
+			if (unlikely(tlv_value_len != rec_len)) {
+				pr_warn("MAC%u: WoWLAN data size mismatch\n",
+					mac->macid);
+				return -EINVAL;
+			}
+
+			kfree(mac->macinfo.wowlan);
+			mac->macinfo.wowlan = NULL;
+			qtnf_parse_wowlan_info(mac, wowlan);
+			break;
 		default:
+			pr_warn("MAC%u: unknown TLV type %u\n",
+				mac->macid, tlv_type);
 			break;
 		}
 
@@ -2831,3 +2887,59 @@ out:
 	qtnf_bus_unlock(bus);
 	return ret;
 }
+
+int qtnf_cmd_send_wowlan_set(const struct qtnf_vif *vif,
+			     const struct cfg80211_wowlan *wowl)
+{
+	struct qtnf_bus *bus = vif->mac->bus;
+	struct sk_buff *cmd_skb;
+	u16 res_code = QLINK_CMD_RESULT_OK;
+	struct qlink_cmd_wowlan_set *cmd;
+	u32 triggers = 0;
+	int count = 0;
+	int ret = 0;
+
+	cmd_skb = qtnf_cmd_alloc_new_cmdskb(vif->mac->macid, vif->vifid,
+					    QLINK_CMD_WOWLAN_SET, sizeof(*cmd));
+	if (!cmd_skb)
+		return -ENOMEM;
+
+	qtnf_bus_lock(bus);
+
+	cmd = (struct qlink_cmd_wowlan_set *)cmd_skb->data;
+
+	if (wowl) {
+		if (wowl->disconnect)
+			triggers |=  QLINK_WOWLAN_TRIG_DISCONNECT;
+
+		if (wowl->magic_pkt)
+			triggers |= QLINK_WOWLAN_TRIG_MAGIC_PKT;
+
+		if (wowl->n_patterns && wowl->patterns) {
+			triggers |= QLINK_WOWLAN_TRIG_PATTERN_PKT;
+			while (count < wowl->n_patterns) {
+				qtnf_cmd_skb_put_tlv_arr(cmd_skb,
+					QTN_TLV_ID_WOWLAN_PATTERN,
+					wowl->patterns[count].pattern,
+					wowl->patterns[count].pattern_len);
+				count++;
+			}
+		}
+	}
+
+	cmd->triggers = cpu_to_le32(triggers);
+
+	ret = qtnf_cmd_send(bus, cmd_skb, &res_code);
+
+	if (unlikely(ret))
+		goto out;
+
+	if (unlikely(res_code != QLINK_CMD_RESULT_OK)) {
+		pr_err("cmd exec failed: 0x%.4X\n", res_code);
+		ret = -EFAULT;
+	}
+
+out:
+	qtnf_bus_unlock(bus);
+	return ret;
+}
diff --git a/drivers/net/wireless/quantenna/qtnfmac/commands.h b/drivers/net/wireless/quantenna/qtnfmac/commands.h
index 03a57e37a665..1ac41156c192 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/commands.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/commands.h
@@ -77,5 +77,7 @@ int qtnf_cmd_start_cac(const struct qtnf_vif *vif,
 int qtnf_cmd_set_mac_acl(const struct qtnf_vif *vif,
 			 const struct cfg80211_acl_data *params);
 int qtnf_cmd_send_pm_set(const struct qtnf_vif *vif, u8 pm_mode, int timeout);
+int qtnf_cmd_send_wowlan_set(const struct qtnf_vif *vif,
+			     const struct cfg80211_wowlan *wowl);
 
 #endif /* QLINK_COMMANDS_H_ */
diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.c b/drivers/net/wireless/quantenna/qtnfmac/core.c
index c318340e1bd5..19abbc4e23e0 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.c
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.c
@@ -495,6 +495,7 @@ static void qtnf_core_mac_detach(struct qtnf_bus *bus, unsigned int macid)
 	qtnf_mac_iface_comb_free(mac);
 	kfree(mac->macinfo.extended_capabilities);
 	kfree(mac->macinfo.extended_capabilities_mask);
+	kfree(mac->macinfo.wowlan);
 	wiphy_free(wiphy);
 	bus->mac[macid] = NULL;
 }
diff --git a/drivers/net/wireless/quantenna/qtnfmac/core.h b/drivers/net/wireless/quantenna/qtnfmac/core.h
index c4808f1ba8b0..a1e338a1f055 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/core.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/core.h
@@ -110,6 +110,7 @@ struct qtnf_mac_info {
 	u8 *extended_capabilities;
 	u8 *extended_capabilities_mask;
 	u8 extended_capabilities_len;
+	struct wiphy_wowlan_support *wowlan;
 };
 
 struct qtnf_chan_stats {
diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
index 8fbef67fbbb8..99d37e3efba6 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
@@ -258,6 +258,7 @@ enum qlink_cmd_type {
 	QLINK_CMD_CONNECT		= 0x0060,
 	QLINK_CMD_DISCONNECT		= 0x0061,
 	QLINK_CMD_PM_SET		= 0x0062,
+	QLINK_CMD_WOWLAN_SET		= 0x0063,
 };
 
 /**
@@ -694,6 +695,30 @@ struct qlink_cmd_pm_set {
 	u8 pm_mode;
 } __packed;
 
+/**
+ * enum qlink_wowlan_trigger
+ *
+ * @QLINK_WOWLAN_TRIG_DISCONNECT: wakeup on disconnect
+ * @QLINK_WOWLAN_TRIG_MAGIC_PKT: wakeup on magic packet
+ * @QLINK_WOWLAN_TRIG_PATTERN_PKT: wakeup on user-defined packet
+ */
+enum qlink_wowlan_trigger {
+	QLINK_WOWLAN_TRIG_DISCONNECT	= BIT(0),
+	QLINK_WOWLAN_TRIG_MAGIC_PKT	= BIT(1),
+	QLINK_WOWLAN_TRIG_PATTERN_PKT	= BIT(2),
+};
+
+/**
+ * struct qlink_cmd_wowlan_set - data for QLINK_CMD_WOWLAN_SET command
+ *
+ * @triggers: requested bitmask of WoWLAN triggers
+ */
+struct qlink_cmd_wowlan_set {
+	struct qlink_cmd chdr;
+	__le32 triggers;
+	u8 data[0];
+} __packed;
+
 /* QLINK Command Responses messages related definitions
  */
 
@@ -1122,6 +1147,8 @@ enum qlink_tlv_id {
 	QTN_TLV_ID_UBOOT_VER		= 0x0407,
 	QTN_TLV_ID_RANDOM_MAC_ADDR	= 0x0408,
 	QTN_TLV_ID_MAX_SCAN_SSIDS	= 0x0409,
+	QTN_TLV_ID_WOWLAN_CAPAB		= 0x0410,
+	QTN_TLV_ID_WOWLAN_PATTERN	= 0x0411,
 };
 
 struct qlink_tlv_hdr {
@@ -1409,4 +1436,33 @@ struct qlink_random_mac_addr {
 	u8 mac_addr_mask[ETH_ALEN];
 } __packed;
 
+/**
+ * struct qlink_wowlan_capab_data - data for QTN_TLV_ID_WOWLAN_CAPAB TLV
+ *
+ * WoWLAN capabilities supported by cards.
+ *
+ * @version: version of WoWLAN data structure, to ensure backward
+ *	compatibility for firmwares with limited WoWLAN support
+ * @len: Total length of WoWLAN data
+ * @data: supported WoWLAN features
+ */
+struct qlink_wowlan_capab_data {
+	__le16 version;
+	__le16 len;
+	u8 data[0];
+} __packed;
+
+/**
+ * struct qlink_wowlan_support - supported WoWLAN capabilities
+ *
+ * @n_patterns: number of supported wakeup patterns
+ * @pattern_max_len: maximum length of each pattern
+ * @pattern_min_len: minimum length of each pattern
+ */
+struct qlink_wowlan_support {
+	__le32 n_patterns;
+	__le32 pattern_max_len;
+	__le32 pattern_min_len;
+} __packed;
+
 #endif /* _QTN_QLINK_H_ */
-- 
cgit v1.2.3


From 6a64f6e1591322beb8ce16e952a53582caf2a15c Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:20 -0500
Subject: scsi: target: fix __transport_register_session locking

When __transport_register_session is called from transport_register_session
irqs will already have been disabled, so we do not want the unlock irq call
to enable them until the higher level has done the final
spin_unlock_irqrestore/ spin_unlock_irq.

This has __transport_register_session use the save/restore call.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 7261561e87cc..b419d4f8cb96 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -347,6 +347,7 @@ void __transport_register_session(
 {
 	const struct target_core_fabric_ops *tfo = se_tpg->se_tpg_tfo;
 	unsigned char buf[PR_REG_ISID_LEN];
+	unsigned long flags;
 
 	se_sess->se_tpg = se_tpg;
 	se_sess->fabric_sess_ptr = fabric_sess_ptr;
@@ -383,7 +384,7 @@ void __transport_register_session(
 			se_sess->sess_bin_isid = get_unaligned_be64(&buf[0]);
 		}
 
-		spin_lock_irq(&se_nacl->nacl_sess_lock);
+		spin_lock_irqsave(&se_nacl->nacl_sess_lock, flags);
 		/*
 		 * The se_nacl->nacl_sess pointer will be set to the
 		 * last active I_T Nexus for each struct se_node_acl.
@@ -392,7 +393,7 @@ void __transport_register_session(
 
 		list_add_tail(&se_sess->sess_acl_list,
 			      &se_nacl->acl_sess_list);
-		spin_unlock_irq(&se_nacl->nacl_sess_lock);
+		spin_unlock_irqrestore(&se_nacl->nacl_sess_lock, flags);
 	}
 	list_add_tail(&se_sess->sess_list, &se_tpg->tpg_sess_list);
 
-- 
cgit v1.2.3


From aeb502794b75f201d1df05f2f351346e0eb2eb83 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:21 -0500
Subject: scsi: iscsi target: have iscsit_start_nopin_timer call
 __iscsit_start_nopin_timer

Just have iscsit_start_nopin_timer grab the lock and call
__iscsit_start_nopin_timer.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/iscsi/iscsi_target_util.c | 20 +-------------------
 1 file changed, 1 insertion(+), 19 deletions(-)

diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c
index 8cfcf9033507..49be1e41290c 100644
--- a/drivers/target/iscsi/iscsi_target_util.c
+++ b/drivers/target/iscsi/iscsi_target_util.c
@@ -1053,26 +1053,8 @@ void __iscsit_start_nopin_timer(struct iscsi_conn *conn)
 
 void iscsit_start_nopin_timer(struct iscsi_conn *conn)
 {
-	struct iscsi_session *sess = conn->sess;
-	struct iscsi_node_attrib *na = iscsit_tpg_get_node_attrib(sess);
-	/*
-	 * NOPIN timeout is disabled..
-	 */
-	if (!na->nopin_timeout)
-		return;
-
 	spin_lock_bh(&conn->nopin_timer_lock);
-	if (conn->nopin_timer_flags & ISCSI_TF_RUNNING) {
-		spin_unlock_bh(&conn->nopin_timer_lock);
-		return;
-	}
-
-	conn->nopin_timer_flags &= ~ISCSI_TF_STOP;
-	conn->nopin_timer_flags |= ISCSI_TF_RUNNING;
-	mod_timer(&conn->nopin_timer, jiffies + na->nopin_timeout * HZ);
-
-	pr_debug("Started NOPIN Timer on CID: %d at %u second"
-			" interval\n", conn->cid, na->nopin_timeout);
+	__iscsit_start_nopin_timer(conn);
 	spin_unlock_bh(&conn->nopin_timer_lock);
 }
 
-- 
cgit v1.2.3


From 3cd14285a1bb58eaa98c44aec0db4d914fdc8c13 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:22 -0500
Subject: scsi: target: make transport_init_session_tags static

transport_init_session_tags is only called from target_core_transport.c so
make it static.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 7 +++----
 include/target/target_core_fabric.h    | 2 --
 2 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index b419d4f8cb96..8044b8115dbf 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -304,9 +304,9 @@ EXPORT_SYMBOL(transport_alloc_session_tags);
  *	      each command.
  * @sup_prot_ops: bitmask that defines which T10-PI modes are supported.
  */
-struct se_session *transport_init_session_tags(unsigned int tag_num,
-					       unsigned int tag_size,
-					       enum target_prot_op sup_prot_ops)
+static struct se_session *
+transport_init_session_tags(unsigned int tag_num, unsigned int tag_size,
+			    enum target_prot_op sup_prot_ops)
 {
 	struct se_session *se_sess;
 	int rc;
@@ -334,7 +334,6 @@ struct se_session *transport_init_session_tags(unsigned int tag_num,
 
 	return se_sess;
 }
-EXPORT_SYMBOL(transport_init_session_tags);
 
 /*
  * Called with spin_lock_irqsave(&struct se_portal_group->session_lock called.
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index f61aa716cfe1..d0d064212bfc 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -119,8 +119,6 @@ void transport_init_session(struct se_session *);
 struct se_session *transport_alloc_session(enum target_prot_op);
 int transport_alloc_session_tags(struct se_session *, unsigned int,
 		unsigned int);
-struct se_session *transport_init_session_tags(unsigned int, unsigned int,
-		enum target_prot_op);
 void	__transport_register_session(struct se_portal_group *,
 		struct se_node_acl *, struct se_session *, void *);
 void	transport_register_session(struct se_portal_group *,
-- 
cgit v1.2.3


From fa834287300ba6a89e0a590f520a3398527eb541 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:23 -0500
Subject: scsi: target: rename target_alloc_session

Rename target_alloc_session to target_setup_session to avoid confusion with
the other transport session allocation function that only allocates the
session and because the target_alloc_session does so much more. It
allocates the session, sets up the nacl and registers the session.

The next patch will then add a remove function to match the setup in this
one, so it should make sense for all drivers, except iscsi, to just call
those 2 functions to setup and remove a session.

iscsi will continue to be the odd driver.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Chris Boot <bootc@bootc.net>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: <qla2xxx-upstream@qlogic.com>
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/infiniband/ulp/srpt/ib_srpt.c    | 6 +++---
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 2 +-
 drivers/scsi/qla2xxx/tcm_qla2xxx.c       | 2 +-
 drivers/target/loopback/tcm_loop.c       | 2 +-
 drivers/target/sbp/sbp_target.c          | 2 +-
 drivers/target/target_core_transport.c   | 4 ++--
 drivers/target/tcm_fc/tfc_sess.c         | 2 +-
 drivers/usb/gadget/function/f_tcm.c      | 2 +-
 drivers/vhost/scsi.c                     | 2 +-
 drivers/xen/xen-scsiback.c               | 2 +-
 include/target/target_core_fabric.h      | 2 +-
 11 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 07b3e1c583bd..21435a73771a 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2221,16 +2221,16 @@ static int srpt_cm_req_recv(struct srpt_device *const sdev,
 	pr_debug("registering session %s\n", ch->sess_name);
 
 	if (sport->port_guid_tpg.se_tpg_wwn)
-		ch->sess = target_alloc_session(&sport->port_guid_tpg, 0, 0,
+		ch->sess = target_setup_session(&sport->port_guid_tpg, 0, 0,
 						TARGET_PROT_NORMAL,
 						ch->sess_name, ch, NULL);
 	if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess))
-		ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0,
+		ch->sess = target_setup_session(&sport->port_gid_tpg, 0, 0,
 					TARGET_PROT_NORMAL, i_port_id, ch,
 					NULL);
 	/* Retry without leading "0x" */
 	if (sport->port_gid_tpg.se_tpg_wwn && IS_ERR_OR_NULL(ch->sess))
-		ch->sess = target_alloc_session(&sport->port_gid_tpg, 0, 0,
+		ch->sess = target_setup_session(&sport->port_gid_tpg, 0, 0,
 						TARGET_PROT_NORMAL,
 						i_port_id + 2, ch, NULL);
 	if (IS_ERR_OR_NULL(ch->sess)) {
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index fdda04e5cf94..1bdf9379c4ce 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -2233,7 +2233,7 @@ static int ibmvscsis_make_nexus(struct ibmvscsis_tport *tport)
 		return -ENOMEM;
 	}
 
-	nexus->se_sess = target_alloc_session(&tport->se_tpg, 0, 0,
+	nexus->se_sess = target_setup_session(&tport->se_tpg, 0, 0,
 					      TARGET_PROT_NORMAL, name, nexus,
 					      NULL);
 	if (IS_ERR(nexus->se_sess)) {
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index cfb5d6067f9f..b9ce4e7e1c3e 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1539,7 +1539,7 @@ static int tcm_qla2xxx_check_initiator_node_acl(
 	 * Locate our struct se_node_acl either from an explict NodeACL created
 	 * via ConfigFS, or via running in TPG demo mode.
 	 */
-	se_sess = target_alloc_session(&tpg->se_tpg, num_tags,
+	se_sess = target_setup_session(&tpg->se_tpg, num_tags,
 				       sizeof(struct qla_tgt_cmd),
 				       TARGET_PROT_ALL, port_name,
 				       qlat_sess, tcm_qla2xxx_session_cb);
diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index b2e7ff50ff61..54b5b94dad37 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -765,7 +765,7 @@ static int tcm_loop_make_nexus(
 	if (!tl_nexus)
 		return -ENOMEM;
 
-	tl_nexus->se_sess = target_alloc_session(&tl_tpg->tl_se_tpg, 0, 0,
+	tl_nexus->se_sess = target_setup_session(&tl_tpg->tl_se_tpg, 0, 0,
 					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
 					name, tl_nexus, tcm_loop_alloc_sess_cb);
 	if (IS_ERR(tl_nexus->se_sess)) {
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index b61b79ac98ff..c4369b52a3fb 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -209,7 +209,7 @@ static struct sbp_session *sbp_session_create(
 	INIT_DELAYED_WORK(&sess->maint_work, session_maintenance_work);
 	sess->guid = guid;
 
-	sess->se_sess = target_alloc_session(&tpg->se_tpg, 128,
+	sess->se_sess = target_setup_session(&tpg->se_tpg, 128,
 					     sizeof(struct sbp_target_request),
 					     TARGET_PROT_NORMAL, guid_str,
 					     sess, NULL);
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 8044b8115dbf..57fadec2d1ae 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -416,7 +416,7 @@ void transport_register_session(
 EXPORT_SYMBOL(transport_register_session);
 
 struct se_session *
-target_alloc_session(struct se_portal_group *tpg,
+target_setup_session(struct se_portal_group *tpg,
 		     unsigned int tag_num, unsigned int tag_size,
 		     enum target_prot_op prot_op,
 		     const char *initiatorname, void *private,
@@ -458,7 +458,7 @@ target_alloc_session(struct se_portal_group *tpg,
 	transport_register_session(tpg, sess->se_node_acl, sess, private);
 	return sess;
 }
-EXPORT_SYMBOL(target_alloc_session);
+EXPORT_SYMBOL(target_setup_session);
 
 ssize_t target_show_dynamic_sessions(struct se_portal_group *se_tpg, char *page)
 {
diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index c91979c1463d..efd7d5e5bfc4 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -239,7 +239,7 @@ static struct ft_sess *ft_sess_create(struct ft_tport *tport, u32 port_id,
 	sess->tport = tport;
 	sess->port_id = port_id;
 
-	sess->se_sess = target_alloc_session(se_tpg, TCM_FC_DEFAULT_TAGS,
+	sess->se_sess = target_setup_session(se_tpg, TCM_FC_DEFAULT_TAGS,
 					     sizeof(struct ft_cmd),
 					     TARGET_PROT_NORMAL, &initiatorname[0],
 					     sess, ft_sess_alloc_cb);
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index 4f183176b0b4..ba7c5f68d38a 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1592,7 +1592,7 @@ static int tcm_usbg_make_nexus(struct usbg_tpg *tpg, char *name)
 		goto out_unlock;
 	}
 
-	tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg,
+	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
 						     USB_G_DEFAULT_SESSION_TAGS,
 						     sizeof(struct usbg_cmd),
 						     TARGET_PROT_NORMAL, name,
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index c84a6edd4c25..e9368842c63f 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1738,7 +1738,7 @@ static int vhost_scsi_make_nexus(struct vhost_scsi_tpg *tpg,
 	 * struct se_node_acl for the vhost_scsi struct se_portal_group with
 	 * the SCSI Initiator port name of the passed configfs group 'name'.
 	 */
-	tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg,
+	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
 					VHOST_SCSI_DEFAULT_TAGS,
 					sizeof(struct vhost_scsi_cmd),
 					TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS,
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index fd77ccfc7d6e..2ffc7ed944d8 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1521,7 +1521,7 @@ static int scsiback_make_nexus(struct scsiback_tpg *tpg,
 		goto out_unlock;
 	}
 
-	tv_nexus->tvn_se_sess = target_alloc_session(&tpg->se_tpg,
+	tv_nexus->tvn_se_sess = target_setup_session(&tpg->se_tpg,
 						     VSCSI_DEFAULT_SESSION_TAGS,
 						     sizeof(struct vscsibk_pend),
 						     TARGET_PROT_NORMAL, name,
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index d0d064212bfc..fbcc9a4025b9 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -109,7 +109,7 @@ void target_unregister_template(const struct target_core_fabric_ops *fo);
 int target_depend_item(struct config_item *item);
 void target_undepend_item(struct config_item *item);
 
-struct se_session *target_alloc_session(struct se_portal_group *,
+struct se_session *target_setup_session(struct se_portal_group *,
 		unsigned int, unsigned int, enum target_prot_op prot_op,
 		const char *, void *,
 		int (*callback)(struct se_portal_group *,
-- 
cgit v1.2.3


From fb7c70f2d750a462c5a9757555bc23bf35360cec Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:24 -0500
Subject: scsi: target: add session removal function

This adds a function to remove a session which should be used by drivers
that use target_setup_session. The next patches will convert the target
drivers to use this new function.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Chris Boot <bootc@bootc.net>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: <qla2xxx-upstream@qlogic.com>
Cc: Johannes Thumshirn <jth@kernel.org>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/target_core_transport.c | 7 +++++++
 include/target/target_core_fabric.h    | 1 +
 2 files changed, 8 insertions(+)

diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index 57fadec2d1ae..86c0156e6c88 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -616,6 +616,13 @@ void transport_deregister_session(struct se_session *se_sess)
 }
 EXPORT_SYMBOL(transport_deregister_session);
 
+void target_remove_session(struct se_session *se_sess)
+{
+	transport_deregister_session_configfs(se_sess);
+	transport_deregister_session(se_sess);
+}
+EXPORT_SYMBOL(target_remove_session);
+
 static void target_remove_from_state_list(struct se_cmd *cmd)
 {
 	struct se_device *dev = cmd->se_dev;
diff --git a/include/target/target_core_fabric.h b/include/target/target_core_fabric.h
index fbcc9a4025b9..f4147b398431 100644
--- a/include/target/target_core_fabric.h
+++ b/include/target/target_core_fabric.h
@@ -114,6 +114,7 @@ struct se_session *target_setup_session(struct se_portal_group *,
 		const char *, void *,
 		int (*callback)(struct se_portal_group *,
 				struct se_session *, void *));
+void target_remove_session(struct se_session *);
 
 void transport_init_session(struct se_session *);
 struct se_session *transport_alloc_session(enum target_prot_op);
-- 
cgit v1.2.3


From b287e3517ed5c76ad48afdfc4f11fadb58a0707e Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:25 -0500
Subject: scsi: target: srp, vscsi, sbp, qla: use target_remove_session

This converts the drivers that called transport_deregister_session_configfs
and then immediately called transport_deregister_session to use
target_remove_session.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Chris Boot <bootc@bootc.net>
Cc: Bryant G. Ly <bryantly@linux.vnet.ibm.com>
Cc: Michael Cyr <mikecyr@linux.vnet.ibm.com>
Cc: <qla2xxx-upstream@qlogic.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/infiniband/ulp/srpt/ib_srpt.c    | 3 +--
 drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c | 3 +--
 drivers/scsi/qla2xxx/tcm_qla2xxx.c       | 3 +--
 drivers/target/sbp/sbp_target.c          | 3 +--
 4 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 21435a73771a..1ae638b58b63 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -2029,8 +2029,7 @@ static void srpt_release_channel_work(struct work_struct *w)
 	target_sess_cmd_list_set_waiting(se_sess);
 	target_wait_for_sess_cmds(se_sess);
 
-	transport_deregister_session_configfs(se_sess);
-	transport_deregister_session(se_sess);
+	target_remove_session(se_sess);
 	ch->sess = NULL;
 
 	if (ch->using_rdma_cm)
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 1bdf9379c4ce..fac377320158 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -2267,8 +2267,7 @@ static int ibmvscsis_drop_nexus(struct ibmvscsis_tport *tport)
 	 * Release the SCSI I_T Nexus to the emulated ibmvscsis Target Port
 	 */
 	target_wait_for_sess_cmds(se_sess);
-	transport_deregister_session_configfs(se_sess);
-	transport_deregister_session(se_sess);
+	target_remove_session(se_sess);
 	tport->ibmv_nexus = NULL;
 	kfree(nexus);
 
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index b9ce4e7e1c3e..f71ec94acc3b 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1461,8 +1461,7 @@ static void tcm_qla2xxx_free_session(struct fc_port *sess)
 	}
 	target_wait_for_sess_cmds(se_sess);
 
-	transport_deregister_session_configfs(sess->se_sess);
-	transport_deregister_session(sess->se_sess);
+	target_remove_session(se_sess);
 }
 
 static int tcm_qla2xxx_session_cb(struct se_portal_group *se_tpg,
diff --git a/drivers/target/sbp/sbp_target.c b/drivers/target/sbp/sbp_target.c
index c4369b52a3fb..3d10189ecedc 100644
--- a/drivers/target/sbp/sbp_target.c
+++ b/drivers/target/sbp/sbp_target.c
@@ -235,8 +235,7 @@ static void sbp_session_release(struct sbp_session *sess, bool cancel_work)
 	if (cancel_work)
 		cancel_delayed_work_sync(&sess->maint_work);
 
-	transport_deregister_session_configfs(sess->se_sess);
-	transport_deregister_session(sess->se_sess);
+	target_remove_session(sess->se_sess);
 
 	if (sess->card)
 		fw_card_put(sess->card);
-- 
cgit v1.2.3


From 60daca10065a13a133e88b738fdc5a40b3654575 Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:26 -0500
Subject: scsi: tcm_fc: use target_remove_session

This converts tcm_fc to use target_remove_session

tcm_fc was calling transport_deregister_session_configfs then calling
transport_deregister_session when commands have completed. It should be ok
for it to call transport_deregister_session_configfs later via
target_remove_session because transport_deregister_session_configfs only
prevents access from configfs via tpg removal and its call to the
close_session callback for that driver, and this is already protected by
the ft_lport_lock and its port lookup handling.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Johannes Thumshirn <jth@kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/tcm_fc/tfc_sess.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/target/tcm_fc/tfc_sess.c b/drivers/target/tcm_fc/tfc_sess.c
index efd7d5e5bfc4..6d4adf5ec26c 100644
--- a/drivers/target/tcm_fc/tfc_sess.c
+++ b/drivers/target/tcm_fc/tfc_sess.c
@@ -287,7 +287,6 @@ static struct ft_sess *ft_sess_delete(struct ft_tport *tport, u32 port_id)
 
 static void ft_close_sess(struct ft_sess *sess)
 {
-	transport_deregister_session_configfs(sess->se_sess);
 	target_sess_cmd_list_set_waiting(sess->se_sess);
 	target_wait_for_sess_cmds(sess->se_sess);
 	ft_sess_put(sess);
@@ -448,7 +447,7 @@ static void ft_sess_free(struct kref *kref)
 {
 	struct ft_sess *sess = container_of(kref, struct ft_sess, kref);
 
-	transport_deregister_session(sess->se_sess);
+	target_remove_session(sess->se_sess);
 	kfree_rcu(sess, rcu);
 }
 
-- 
cgit v1.2.3


From 25b88550b7d57c6ae91b0e5f4b1be2aaa73a60df Mon Sep 17 00:00:00 2001
From: Mike Christie <mchristi@redhat.com>
Date: Thu, 2 Aug 2018 12:12:27 -0500
Subject: scsi: target: loop, usb, vhost, xen: use target_remove_session

This converts drivers that were only calling transport_deregister_session
to use target_remove_session. The calling of
transport_deregister_session_configfs via target_remove_session for these
types of drivers is ok, because they were not exporting info from fields
like sess_acl_list, sess->se_tpg and sess->fabric_sess_ptr from configfs
accessible functions, so they will see no difference.

Signed-off-by: Mike Christie <mchristi@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Felipe Balbi <balbi@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Andrzej Pietrasiewicz <andrzej.p@samsung.com>
Cc: Michael S. Tsirkin <mst@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/target/loopback/tcm_loop.c  | 2 +-
 drivers/usb/gadget/function/f_tcm.c | 2 +-
 drivers/vhost/scsi.c                | 2 +-
 drivers/xen/xen-scsiback.c          | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/target/loopback/tcm_loop.c b/drivers/target/loopback/tcm_loop.c
index 54b5b94dad37..bc8918f382e4 100644
--- a/drivers/target/loopback/tcm_loop.c
+++ b/drivers/target/loopback/tcm_loop.c
@@ -805,7 +805,7 @@ static int tcm_loop_drop_nexus(
 	/*
 	 * Release the SCSI I_T Nexus to the emulated Target Port
 	 */
-	transport_deregister_session(tl_nexus->se_sess);
+	target_remove_session(se_sess);
 	tpg->tl_nexus = NULL;
 	kfree(tl_nexus);
 	return 0;
diff --git a/drivers/usb/gadget/function/f_tcm.c b/drivers/usb/gadget/function/f_tcm.c
index ba7c5f68d38a..106988a6661a 100644
--- a/drivers/usb/gadget/function/f_tcm.c
+++ b/drivers/usb/gadget/function/f_tcm.c
@@ -1638,7 +1638,7 @@ static int tcm_usbg_drop_nexus(struct usbg_tpg *tpg)
 	/*
 	 * Release the SCSI I_T Nexus to the emulated vHost Target Port
 	 */
-	transport_deregister_session(tv_nexus->tvn_se_sess);
+	target_remove_session(se_sess);
 	tpg->tpg_nexus = NULL;
 
 	kfree(tv_nexus);
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index e9368842c63f..76f8d649147b 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -1797,7 +1797,7 @@ static int vhost_scsi_drop_nexus(struct vhost_scsi_tpg *tpg)
 	/*
 	 * Release the SCSI I_T Nexus to the emulated vhost Target Port
 	 */
-	transport_deregister_session(tv_nexus->tvn_se_sess);
+	target_remove_session(se_sess);
 	tpg->tpg_nexus = NULL;
 	mutex_unlock(&tpg->tv_tpg_mutex);
 
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 2ffc7ed944d8..2aadabd053c2 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -1576,7 +1576,7 @@ static int scsiback_drop_nexus(struct scsiback_tpg *tpg)
 	/*
 	 * Release the SCSI I_T Nexus to the emulated xen-pvscsi Target Port
 	 */
-	transport_deregister_session(tv_nexus->tvn_se_sess);
+	target_remove_session(se_sess);
 	tpg->tpg_nexus = NULL;
 	mutex_unlock(&tpg->tv_tpg_mutex);
 
-- 
cgit v1.2.3


From faa832e97a0c0d79838c3a6521a473d870217053 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:18 -0700
Subject: scsi: lpfc: Fix ELS abort on SLI-3 adapters

For ABORT_XRI_CN command, firmware identifies XRI to abort by IOTAG and RPI
combination. For ELS aborts, driver specifies IOTAG correctly but RPI is
not specified.

Fix by setting RPI in WQE.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_nportdisc.c |  3 +++
 drivers/scsi/lpfc/lpfc_sli.c       | 16 ++++++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 1f0a7d7dbc54..843e765db86d 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -1062,6 +1062,9 @@ lpfc_rcv_logo_plogi_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 {
 	struct lpfc_iocbq *cmdiocb = (struct lpfc_iocbq *) arg;
 
+	/* Retrieve RPI from LOGO IOCB. RPI is used for CMD_ABORT_XRI_CN */
+	if (vport->phba->sli_rev == LPFC_SLI_REV3)
+		ndlp->nlp_rpi = cmdiocb->iocb.ulpIoTag;
 				/* software abort outstanding PLOGI */
 	lpfc_els_abort(vport->phba, ndlp);
 
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 72500dcb13a9..9830bdb6e072 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -10703,6 +10703,12 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 		spin_lock_irq(&phba->hbalock);
 		if (phba->sli_rev < LPFC_SLI_REV4) {
+			if (irsp->ulpCommand == CMD_ABORT_XRI_CX &&
+			    irsp->ulpStatus == IOSTAT_LOCAL_REJECT &&
+			    irsp->un.ulpWord[4] == IOERR_ABORT_REQUESTED) {
+				spin_unlock_irq(&phba->hbalock);
+				goto release_iocb;
+			}
 			if (abort_iotag != 0 &&
 				abort_iotag <= phba->sli.last_iotag)
 				abort_iocb =
@@ -10724,6 +10730,7 @@ lpfc_sli_abort_els_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *cmdiocb,
 
 		spin_unlock_irq(&phba->hbalock);
 	}
+release_iocb:
 	lpfc_sli_release_iocbq(phba, cmdiocb);
 	return;
 }
@@ -10780,6 +10787,7 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	IOCB_t *iabt = NULL;
 	int retval;
 	unsigned long iflags;
+	struct lpfc_nodelist *ndlp;
 
 	lockdep_assert_held(&phba->hbalock);
 
@@ -10810,9 +10818,13 @@ lpfc_sli_abort_iotag_issue(struct lpfc_hba *phba, struct lpfc_sli_ring *pring,
 	if (phba->sli_rev == LPFC_SLI_REV4) {
 		iabt->un.acxri.abortIoTag = cmdiocb->sli4_xritag;
 		iabt->un.acxri.abortContextTag = cmdiocb->iotag;
-	}
-	else
+	} else {
 		iabt->un.acxri.abortIoTag = icmd->ulpIoTag;
+		if (pring->ringno == LPFC_ELS_RING) {
+			ndlp = (struct lpfc_nodelist *)(cmdiocb->context1);
+			iabt->un.acxri.abortContextTag = ndlp->nlp_rpi;
+		}
+	}
 	iabt->ulpLe = 1;
 	iabt->ulpClass = icmd->ulpClass;
 
-- 
cgit v1.2.3


From b615a20adf04cf3c8e9293851da3aac54792fb07 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:19 -0700
Subject: scsi: lpfc: Fix sysfs Speed value on CNA ports

CNA ports were showing speed as "unknown" even if the link is up.

Add speed decoding for FCOE-based adapters.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_attr.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 23a5a298d60e..514513f837a8 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -5927,6 +5927,24 @@ lpfc_get_host_speed(struct Scsi_Host *shost)
 			fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
 			break;
 		}
+	} else if (lpfc_is_link_up(phba) && (phba->hba_flag & HBA_FCOE_MODE)) {
+		switch (phba->fc_linkspeed) {
+		case LPFC_ASYNC_LINK_SPEED_10GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_10GBIT;
+			break;
+		case LPFC_ASYNC_LINK_SPEED_25GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_25GBIT;
+			break;
+		case LPFC_ASYNC_LINK_SPEED_40GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_40GBIT;
+			break;
+		case LPFC_ASYNC_LINK_SPEED_100GBPS:
+			fc_host_speed(shost) = FC_PORTSPEED_100GBIT;
+			break;
+		default:
+			fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
+			break;
+		}
 	} else
 		fc_host_speed(shost) = FC_PORTSPEED_UNKNOWN;
 
-- 
cgit v1.2.3


From 8931c73bee077f5bc5710afebc0136363970cb2b Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:20 -0700
Subject: scsi: lpfc: Fix list corruption on the completion queue.

Enabling list_debug showed the drivers txcmplq was suffering list
corruption. The systems will eventually crash because the iocb free list
gets crossed linked with the prings txcmplq.  Most systems will run for a
while after the corruption, but will eventually crash when a scsi eh reset
occurs and the txcmplq is attempted to be flushed. The flush gets stuck in
an endless loop.

The problem is the abort handler does not hold the sli4 ring lock while
validating the IO so the IO could complete while the driver is still
preping the abort.  The erroneously generated abort, when it completes, has
pointers to the original IO that has already completed, and the IO
manipulation (for the second time) corrupts the list.

Correct by taking the ring lock early in the abort handler so the erroneous
abort won't be sent if the io has/is completing.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_scsi.c | 44 +++++++++++++++++++++++++++++++++++--------
 1 file changed, 36 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 25ef2b6ccc34..51ce244cf10a 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -4727,7 +4727,7 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	struct lpfc_scsi_buf *lpfc_cmd;
 	IOCB_t *cmd, *icmd;
 	int ret = SUCCESS, status = 0;
-	struct lpfc_sli_ring *pring_s4;
+	struct lpfc_sli_ring *pring_s4 = NULL;
 	int ret_val;
 	unsigned long flags;
 	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(waitq);
@@ -4757,8 +4757,25 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	}
 
 	iocb = &lpfc_cmd->cur_iocbq;
+	if (phba->sli_rev == LPFC_SLI_REV4) {
+		if (!(phba->cfg_fof) ||
+		    (!(iocb->iocb_flag & LPFC_IO_FOF))) {
+			pring_s4 =
+				phba->sli4_hba.fcp_wq[iocb->hba_wqidx]->pring;
+		} else {
+			iocb->hba_wqidx = 0;
+			pring_s4 = phba->sli4_hba.oas_wq->pring;
+		}
+		if (!pring_s4) {
+			ret = FAILED;
+			goto out_unlock;
+		}
+		spin_lock(&pring_s4->ring_lock);
+	}
 	/* the command is in process of being cancelled */
 	if (!(iocb->iocb_flag & LPFC_IO_ON_TXCMPLQ)) {
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			"3169 SCSI Layer abort requested I/O has been "
@@ -4772,6 +4789,8 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	 * see the completion before the eh fired. Just return SUCCESS.
 	 */
 	if (lpfc_cmd->pCmd != cmnd) {
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			"3170 SCSI Layer abort requested I/O has been "
 			"completed by LLD.\n");
@@ -4784,6 +4803,8 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	if (iocb->iocb_flag & LPFC_DRIVER_ABORTED) {
 		lpfc_printf_vlog(vport, KERN_WARNING, LOG_FCP,
 			 "3389 SCSI Layer I/O Abort Request is pending\n");
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		spin_unlock_irqrestore(&phba->hbalock, flags);
 		goto wait_for_cmpl;
 	}
@@ -4791,6 +4812,8 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 	abtsiocb = __lpfc_sli_get_iocbq(phba);
 	if (abtsiocb == NULL) {
 		ret = FAILED;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock(&pring_s4->ring_lock);
 		goto out_unlock;
 	}
 
@@ -4828,14 +4851,9 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 	abtsiocb->iocb_cmpl = lpfc_sli_abort_fcp_cmpl;
 	abtsiocb->vport = vport;
+	lpfc_cmd->waitq = &waitq;
 	if (phba->sli_rev == LPFC_SLI_REV4) {
-		pring_s4 = lpfc_sli4_calc_ring(phba, abtsiocb);
-		if (pring_s4 == NULL) {
-			ret = FAILED;
-			goto out_unlock;
-		}
 		/* Note: both hbalock and ring_lock must be set here */
-		spin_lock(&pring_s4->ring_lock);
 		ret_val = __lpfc_sli_issue_iocb(phba, pring_s4->ringno,
 						abtsiocb, 0);
 		spin_unlock(&pring_s4->ring_lock);
@@ -4848,6 +4866,17 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 
 
 	if (ret_val == IOCB_ERROR) {
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_lock_irqsave(&pring_s4->ring_lock, flags);
+		else
+			spin_lock_irqsave(&phba->hbalock, flags);
+		/* Indicate the IO is not being aborted by the driver. */
+		iocb->iocb_flag &= ~LPFC_DRIVER_ABORTED;
+		lpfc_cmd->waitq = NULL;
+		if (phba->sli_rev == LPFC_SLI_REV4)
+			spin_unlock_irqrestore(&pring_s4->ring_lock, flags);
+		else
+			spin_unlock_irqrestore(&phba->hbalock, flags);
 		lpfc_sli_release_iocbq(phba, abtsiocb);
 		ret = FAILED;
 		goto out;
@@ -4858,7 +4887,6 @@ lpfc_abort_handler(struct scsi_cmnd *cmnd)
 			&phba->sli.sli3_ring[LPFC_FCP_RING], HA_R0RE_REQ);
 
 wait_for_cmpl:
-	lpfc_cmd->waitq = &waitq;
 	/* Wait for abort to complete */
 	wait_event_timeout(waitq,
 			  (lpfc_cmd->pCmd != cmnd),
-- 
cgit v1.2.3


From 93a3922da428ec0752e8b2ab00c42dadbbf805a9 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:21 -0700
Subject: scsi: lpfc: Fix driver crash when re-registering NVME rports.

During remote port loss fault testing, the driver crashed with the
following trace:

general protection fault: 0000 [#1] SMP
RIP: ... lpfc_nvme_register_port+0x250/0x480 [lpfc]
Call Trace:
 lpfc_nlp_state_cleanup+0x1b3/0x7a0 [lpfc]
 lpfc_nlp_set_state+0xa6/0x1d0 [lpfc]
 lpfc_cmpl_prli_prli_issue+0x213/0x440
 lpfc_disc_state_machine+0x7e/0x1e0 [lpfc]
 lpfc_cmpl_els_prli+0x18a/0x200 [lpfc]
 lpfc_sli_sp_handle_rspiocb+0x3b5/0x6f0 [lpfc]
 lpfc_sli_handle_slow_ring_event_s4+0x161/0x240 [lpfc]
 lpfc_work_done+0x948/0x14c0 [lpfc]
 lpfc_do_work+0x16f/0x180 [lpfc]
 kthread+0xc9/0xe0
 ret_from_fork+0x55/0x80

After registering a new remoteport, the driver is pulling an ndlp pointer
from the lpfc rport associated with the private area of a newly registered
remoteport. The private area is uninitialized, so it's garbage.

Correct by pulling the the lpfc rport pointer from the entering ndlp point,
then ndlp value from at rport. Note the entering ndlp may be replacing by
the rport->ndlp due to an address change swap.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_nvme.c | 22 ++++++++++++++--------
 1 file changed, 14 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 4cc6783b6a9f..32053424d546 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -2687,7 +2687,7 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 	struct lpfc_nvme_rport *oldrport;
 	struct nvme_fc_remote_port *remote_port;
 	struct nvme_fc_port_info rpinfo;
-	struct lpfc_nodelist *prev_ndlp;
+	struct lpfc_nodelist *prev_ndlp = NULL;
 
 	lpfc_printf_vlog(ndlp->vport, KERN_INFO, LOG_NVME_DISC,
 			 "6006 Register NVME PORT. DID x%06x nlptype x%x\n",
@@ -2736,23 +2736,29 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		spin_unlock_irq(&vport->phba->hbalock);
 		rport = remote_port->private;
 		if (oldrport) {
+			/* New remoteport record does not guarantee valid
+			 * host private memory area.
+			 */
+			prev_ndlp = oldrport->ndlp;
 			if (oldrport == remote_port->private) {
-				/* Same remoteport.  Just reuse. */
+				/* Same remoteport - ndlp should match.
+				 * Just reuse.
+				 */
 				lpfc_printf_vlog(ndlp->vport, KERN_INFO,
 						 LOG_NVME_DISC,
 						 "6014 Rebinding lport to "
 						 "remoteport %p wwpn 0x%llx, "
-						 "Data: x%x x%x %p x%x x%06x\n",
+						 "Data: x%x x%x %p %p x%x x%06x\n",
 						 remote_port,
 						 remote_port->port_name,
 						 remote_port->port_id,
 						 remote_port->port_role,
+						 prev_ndlp,
 						 ndlp,
 						 ndlp->nlp_type,
 						 ndlp->nlp_DID);
 				return 0;
 			}
-			prev_ndlp = rport->ndlp;
 
 			/* Sever the ndlp<->rport association
 			 * before dropping the ndlp ref from
@@ -2786,13 +2792,13 @@ lpfc_nvme_register_port(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp)
 		lpfc_printf_vlog(vport, KERN_INFO,
 				 LOG_NVME_DISC | LOG_NODE,
 				 "6022 Binding new rport to "
-				 "lport %p Remoteport %p  WWNN 0x%llx, "
+				 "lport %p Remoteport %p rport %p WWNN 0x%llx, "
 				 "Rport WWPN 0x%llx DID "
-				 "x%06x Role x%x, ndlp %p\n",
-				 lport, remote_port,
+				 "x%06x Role x%x, ndlp %p prev_ndlp %p\n",
+				 lport, remote_port, rport,
 				 rpinfo.node_name, rpinfo.port_name,
 				 rpinfo.port_id, rpinfo.port_role,
-				 ndlp);
+				 ndlp, prev_ndlp);
 	} else {
 		lpfc_printf_vlog(vport, KERN_ERR,
 				 LOG_NVME_DISC | LOG_NODE,
-- 
cgit v1.2.3


From 2a5b7d626ed2256fd0ef0e799ebc6ef47b7bd283 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:22 -0700
Subject: scsi: lpfc: Limit tracking of tgt queue depth in fast path

Performance is affected when target queue depth is tracked.  An atomic
counter is incremented on the submission path which competes with it being
decremented on the completion path.  In addition, multiple CPUs can
simultaniously be manipulating this counter for the same ndlp.

Reduce the overhead by only performing the target increment/decrement when
the target queue depth is less than the overall adapter depth, thus is
actually meaningful.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_disc.h      |  3 ++
 drivers/scsi/lpfc/lpfc_nportdisc.c |  6 ----
 drivers/scsi/lpfc/lpfc_nvme.c      | 41 ++++++++++++---------
 drivers/scsi/lpfc/lpfc_nvme.h      |  1 +
 drivers/scsi/lpfc/lpfc_scsi.c      | 74 ++++++++++++++++++++++----------------
 drivers/scsi/lpfc/lpfc_scsi.h      |  2 ++
 6 files changed, 74 insertions(+), 53 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_disc.h b/drivers/scsi/lpfc/lpfc_disc.h
index 376f02819f20..28e2b60fc5c0 100644
--- a/drivers/scsi/lpfc/lpfc_disc.h
+++ b/drivers/scsi/lpfc/lpfc_disc.h
@@ -150,6 +150,9 @@ struct lpfc_node_rrq {
 	unsigned long rrq_stop_time;
 };
 
+#define lpfc_ndlp_check_qdepth(phba, ndlp) \
+	(ndlp->cmd_qdepth < phba->sli4_hba.max_cfg_param.max_xri)
+
 /* Defines for nlp_flag (uint32) */
 #define NLP_IGNR_REG_CMPL  0x00000001 /* Rcvd rscn before we cmpl reg login */
 #define NLP_REG_LOGIN_SEND 0x00000002   /* sent reglogin to adapter */
diff --git a/drivers/scsi/lpfc/lpfc_nportdisc.c b/drivers/scsi/lpfc/lpfc_nportdisc.c
index 843e765db86d..bd9bce9d9974 100644
--- a/drivers/scsi/lpfc/lpfc_nportdisc.c
+++ b/drivers/scsi/lpfc/lpfc_nportdisc.c
@@ -1985,12 +1985,6 @@ lpfc_cmpl_prli_prli_issue(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp,
 			if (bf_get_be32(prli_disc, nvpr))
 				ndlp->nlp_type |= NLP_NVME_DISCOVERY;
 
-			/* This node is an NVME target.  Adjust the command
-			 * queue depth on this node to not exceed the available
-			 * xris.
-			 */
-			ndlp->cmd_qdepth = phba->sli4_hba.nvme_xri_max;
-
 			/*
 			 * If prli_fba is set, the Target supports FirstBurst.
 			 * If prli_fb_sz is 0, the FirstBurst size is unlimited,
diff --git a/drivers/scsi/lpfc/lpfc_nvme.c b/drivers/scsi/lpfc/lpfc_nvme.c
index 32053424d546..028462e5994d 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.c
+++ b/drivers/scsi/lpfc/lpfc_nvme.c
@@ -1135,9 +1135,6 @@ out_err:
 	else
 		lpfc_ncmd->flags &= ~LPFC_SBUF_XBUSY;
 
-	if (ndlp && NLP_CHK_NODE_ACT(ndlp))
-		atomic_dec(&ndlp->cmd_pending);
-
 	/* Update stats and complete the IO.  There is
 	 * no need for dma unprep because the nvme_transport
 	 * owns the dma address.
@@ -1546,17 +1543,19 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	/* The node is shared with FCP IO, make sure the IO pending count does
 	 * not exceed the programmed depth.
 	 */
-	if ((atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) &&
-	    !expedite) {
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
-				 "6174 Fail IO, ndlp qdepth exceeded: "
-				 "idx %d DID %x pend %d qdepth %d\n",
-				 lpfc_queue_info->index, ndlp->nlp_DID,
-				 atomic_read(&ndlp->cmd_pending),
-				 ndlp->cmd_qdepth);
-		atomic_inc(&lport->xmt_fcp_qdepth);
-		ret = -EBUSY;
-		goto out_fail;
+	if (lpfc_ndlp_check_qdepth(phba, ndlp)) {
+		if ((atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) &&
+		    !expedite) {
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
+					 "6174 Fail IO, ndlp qdepth exceeded: "
+					 "idx %d DID %x pend %d qdepth %d\n",
+					 lpfc_queue_info->index, ndlp->nlp_DID,
+					 atomic_read(&ndlp->cmd_pending),
+					 ndlp->cmd_qdepth);
+			atomic_inc(&lport->xmt_fcp_qdepth);
+			ret = -EBUSY;
+			goto out_fail;
+		}
 	}
 
 	lpfc_ncmd = lpfc_get_nvme_buf(phba, ndlp, expedite);
@@ -1614,8 +1613,6 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 		goto out_free_nvme_buf;
 	}
 
-	atomic_inc(&ndlp->cmd_pending);
-
 	lpfc_nvmeio_data(phba, "NVME FCP XMIT: xri x%x idx %d to %06x\n",
 			 lpfc_ncmd->cur_iocbq.sli4_xritag,
 			 lpfc_queue_info->index, ndlp->nlp_DID);
@@ -1623,7 +1620,6 @@ lpfc_nvme_fcp_io_submit(struct nvme_fc_local_port *pnvme_lport,
 	ret = lpfc_sli4_issue_wqe(phba, LPFC_FCP_RING, &lpfc_ncmd->cur_iocbq);
 	if (ret) {
 		atomic_inc(&lport->xmt_fcp_wqerr);
-		atomic_dec(&ndlp->cmd_pending);
 		lpfc_printf_vlog(vport, KERN_INFO, LOG_NVME_IOERR,
 				 "6113 Fail IO, Could not issue WQE err %x "
 				 "sid: x%x did: x%x oxid: x%x\n",
@@ -2378,6 +2374,11 @@ lpfc_get_nvme_buf(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp,
 			lpfc_ncmd = lpfc_nvme_buf(phba);
 	}
 	spin_unlock_irqrestore(&phba->nvme_buf_list_get_lock, iflag);
+
+	if (lpfc_ndlp_check_qdepth(phba, ndlp) && lpfc_ncmd) {
+		atomic_inc(&ndlp->cmd_pending);
+		lpfc_ncmd->flags |= LPFC_BUMP_QDEPTH;
+	}
 	return  lpfc_ncmd;
 }
 
@@ -2396,7 +2397,13 @@ lpfc_release_nvme_buf(struct lpfc_hba *phba, struct lpfc_nvme_buf *lpfc_ncmd)
 {
 	unsigned long iflag = 0;
 
+	if ((lpfc_ncmd->flags & LPFC_BUMP_QDEPTH) && lpfc_ncmd->ndlp)
+		atomic_dec(&lpfc_ncmd->ndlp->cmd_pending);
+
 	lpfc_ncmd->nonsg_phys = 0;
+	lpfc_ncmd->ndlp = NULL;
+	lpfc_ncmd->flags &= ~LPFC_BUMP_QDEPTH;
+
 	if (lpfc_ncmd->flags & LPFC_SBUF_XBUSY) {
 		lpfc_printf_log(phba, KERN_INFO, LOG_NVME_ABTS,
 				"6310 XB release deferred for "
diff --git a/drivers/scsi/lpfc/lpfc_nvme.h b/drivers/scsi/lpfc/lpfc_nvme.h
index 04bd463dd043..cfd4719be25c 100644
--- a/drivers/scsi/lpfc/lpfc_nvme.h
+++ b/drivers/scsi/lpfc/lpfc_nvme.h
@@ -86,6 +86,7 @@ struct lpfc_nvme_buf {
 
 	uint16_t flags;  /* TBD convert exch_busy to flags */
 #define LPFC_SBUF_XBUSY         0x1     /* SLI4 hba reported XB on WCQE cmpl */
+#define LPFC_BUMP_QDEPTH	0x2	/* bumped queue depth counter */
 	uint16_t exch_busy;     /* SLI4 hba reported XB on complete WCQE */
 	uint16_t status;	/* From IOCB Word 7- ulpStatus */
 	uint16_t cpu;
diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
index 51ce244cf10a..5c7858e735c9 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.c
+++ b/drivers/scsi/lpfc/lpfc_scsi.c
@@ -995,6 +995,11 @@ lpfc_get_scsi_buf_s3(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 		spin_unlock(&phba->scsi_buf_list_put_lock);
 	}
 	spin_unlock_irqrestore(&phba->scsi_buf_list_get_lock, iflag);
+
+	if (lpfc_ndlp_check_qdepth(phba, ndlp) && lpfc_cmd) {
+		atomic_inc(&ndlp->cmd_pending);
+		lpfc_cmd->flags |= LPFC_SBUF_BUMP_QDEPTH;
+	}
 	return  lpfc_cmd;
 }
 /**
@@ -1044,6 +1049,11 @@ lpfc_get_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_nodelist *ndlp)
 	spin_unlock_irqrestore(&phba->scsi_buf_list_get_lock, iflag);
 	if (!found)
 		return NULL;
+
+	if (lpfc_ndlp_check_qdepth(phba, ndlp) && lpfc_cmd) {
+		atomic_inc(&ndlp->cmd_pending);
+		lpfc_cmd->flags |= LPFC_SBUF_BUMP_QDEPTH;
+	}
 	return  lpfc_cmd;
 }
 /**
@@ -1134,7 +1144,10 @@ lpfc_release_scsi_buf_s4(struct lpfc_hba *phba, struct lpfc_scsi_buf *psb)
 static void
 lpfc_release_scsi_buf(struct lpfc_hba *phba, struct lpfc_scsi_buf *psb)
 {
+	if ((psb->flags & LPFC_SBUF_BUMP_QDEPTH) && psb->ndlp)
+		atomic_dec(&psb->ndlp->cmd_pending);
 
+	psb->flags &= ~LPFC_SBUF_BUMP_QDEPTH;
 	phba->lpfc_release_scsi_buf(phba, psb);
 }
 
@@ -4130,7 +4143,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 		msecs_to_jiffies(vport->cfg_max_scsicmpl_time))) {
 		spin_lock_irqsave(shost->host_lock, flags);
 		if (pnode && NLP_CHK_NODE_ACT(pnode)) {
-			atomic_dec(&pnode->cmd_pending);
 			if (pnode->cmd_qdepth >
 				atomic_read(&pnode->cmd_pending) &&
 				(atomic_read(&pnode->cmd_pending) >
@@ -4143,8 +4155,6 @@ lpfc_scsi_cmd_iocb_cmpl(struct lpfc_hba *phba, struct lpfc_iocbq *pIocbIn,
 			pnode->last_change_time = jiffies;
 		}
 		spin_unlock_irqrestore(shost->host_lock, flags);
-	} else if (pnode && NLP_CHK_NODE_ACT(pnode)) {
-		atomic_dec(&pnode->cmd_pending);
 	}
 	lpfc_scsi_unprep_dma_buf(phba, lpfc_cmd);
 
@@ -4568,33 +4578,36 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	 */
 	if (!ndlp || !NLP_CHK_NODE_ACT(ndlp))
 		goto out_tgt_busy;
-	if (atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) {
-		lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP_ERROR,
-				 "3377 Target Queue Full, scsi Id:%d Qdepth:%d"
-				 " Pending command:%d"
-				 " WWNN:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x, "
-				 " WWPN:%02x:%02x:%02x:%02x:%02x:%02x:%02x:%02x",
-				 ndlp->nlp_sid, ndlp->cmd_qdepth,
-				 atomic_read(&ndlp->cmd_pending),
-				 ndlp->nlp_nodename.u.wwn[0],
-				 ndlp->nlp_nodename.u.wwn[1],
-				 ndlp->nlp_nodename.u.wwn[2],
-				 ndlp->nlp_nodename.u.wwn[3],
-				 ndlp->nlp_nodename.u.wwn[4],
-				 ndlp->nlp_nodename.u.wwn[5],
-				 ndlp->nlp_nodename.u.wwn[6],
-				 ndlp->nlp_nodename.u.wwn[7],
-				 ndlp->nlp_portname.u.wwn[0],
-				 ndlp->nlp_portname.u.wwn[1],
-				 ndlp->nlp_portname.u.wwn[2],
-				 ndlp->nlp_portname.u.wwn[3],
-				 ndlp->nlp_portname.u.wwn[4],
-				 ndlp->nlp_portname.u.wwn[5],
-				 ndlp->nlp_portname.u.wwn[6],
-				 ndlp->nlp_portname.u.wwn[7]);
-		goto out_tgt_busy;
+	if (lpfc_ndlp_check_qdepth(phba, ndlp)) {
+		if (atomic_read(&ndlp->cmd_pending) >= ndlp->cmd_qdepth) {
+			lpfc_printf_vlog(vport, KERN_INFO, LOG_FCP_ERROR,
+					 "3377 Target Queue Full, scsi Id:%d "
+					 "Qdepth:%d Pending command:%d"
+					 " WWNN:%02x:%02x:%02x:%02x:"
+					 "%02x:%02x:%02x:%02x, "
+					 " WWPN:%02x:%02x:%02x:%02x:"
+					 "%02x:%02x:%02x:%02x",
+					 ndlp->nlp_sid, ndlp->cmd_qdepth,
+					 atomic_read(&ndlp->cmd_pending),
+					 ndlp->nlp_nodename.u.wwn[0],
+					 ndlp->nlp_nodename.u.wwn[1],
+					 ndlp->nlp_nodename.u.wwn[2],
+					 ndlp->nlp_nodename.u.wwn[3],
+					 ndlp->nlp_nodename.u.wwn[4],
+					 ndlp->nlp_nodename.u.wwn[5],
+					 ndlp->nlp_nodename.u.wwn[6],
+					 ndlp->nlp_nodename.u.wwn[7],
+					 ndlp->nlp_portname.u.wwn[0],
+					 ndlp->nlp_portname.u.wwn[1],
+					 ndlp->nlp_portname.u.wwn[2],
+					 ndlp->nlp_portname.u.wwn[3],
+					 ndlp->nlp_portname.u.wwn[4],
+					 ndlp->nlp_portname.u.wwn[5],
+					 ndlp->nlp_portname.u.wwn[6],
+					 ndlp->nlp_portname.u.wwn[7]);
+			goto out_tgt_busy;
+		}
 	}
-	atomic_inc(&ndlp->cmd_pending);
 
 	lpfc_cmd = lpfc_get_scsi_buf(phba, ndlp);
 	if (lpfc_cmd == NULL) {
@@ -4612,6 +4625,7 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	 */
 	lpfc_cmd->pCmd  = cmnd;
 	lpfc_cmd->rdata = rdata;
+	lpfc_cmd->ndlp = ndlp;
 	lpfc_cmd->timeout = 0;
 	lpfc_cmd->start_time = jiffies;
 	cmnd->host_scribble = (unsigned char *)lpfc_cmd;
@@ -4694,7 +4708,6 @@ lpfc_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *cmnd)
 	lpfc_scsi_unprep_dma_buf(phba, lpfc_cmd);
 	lpfc_release_scsi_buf(phba, lpfc_cmd);
  out_host_busy:
-	atomic_dec(&ndlp->cmd_pending);
 	return SCSI_MLQUEUE_HOST_BUSY;
 
  out_tgt_busy:
@@ -5047,6 +5060,7 @@ lpfc_send_taskmgmt(struct lpfc_vport *vport, struct scsi_cmnd *cmnd,
 	lpfc_cmd->timeout = phba->cfg_task_mgmt_tmo;
 	lpfc_cmd->rdata = rdata;
 	lpfc_cmd->pCmd = cmnd;
+	lpfc_cmd->ndlp = pnode;
 
 	status = lpfc_scsi_prep_task_mgmt_cmd(vport, lpfc_cmd, lun_id,
 					   task_mgmt_cmd);
diff --git a/drivers/scsi/lpfc/lpfc_scsi.h b/drivers/scsi/lpfc/lpfc_scsi.h
index c38e4da71f5f..cc99859774ff 100644
--- a/drivers/scsi/lpfc/lpfc_scsi.h
+++ b/drivers/scsi/lpfc/lpfc_scsi.h
@@ -134,11 +134,13 @@ struct lpfc_scsi_buf {
 	struct list_head list;
 	struct scsi_cmnd *pCmd;
 	struct lpfc_rport_data *rdata;
+	struct lpfc_nodelist *ndlp;
 
 	uint32_t timeout;
 
 	uint16_t flags;  /* TBD convert exch_busy to flags */
 #define LPFC_SBUF_XBUSY         0x1     /* SLI4 hba reported XB on WCQE cmpl */
+#define LPFC_SBUF_BUMP_QDEPTH	0x8	/* bumped queue depth counter */
 	uint16_t exch_busy;     /* SLI4 hba reported XB on complete WCQE */
 	uint16_t status;	/* From IOCB Word 7- ulpStatus */
 	uint32_t result;	/* From IOCB Word 4. */
-- 
cgit v1.2.3


From 24bc3119424ac163c2f67e072c956f50e153d034 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:23 -0700
Subject: scsi: lpfc: Correct LCB ACCept payload

After memory allocation for the LCB response frame, the memory wasn't zero
initialized, and not all fields are set. Thus garbage shows up in the
payload.

Fix by zeroing the memory at allocation.  Also properly set the Capability
field based on duration support.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_els.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
index df655f1284d0..4dda969e947c 100644
--- a/drivers/scsi/lpfc/lpfc_els.c
+++ b/drivers/scsi/lpfc/lpfc_els.c
@@ -5662,6 +5662,7 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	lcb_res = (struct fc_lcb_res_frame *)
 		(((struct lpfc_dmabuf *)elsiocb->context2)->virt);
 
+	memset(lcb_res, 0, sizeof(struct fc_lcb_res_frame));
 	icmd = &elsiocb->iocb;
 	icmd->ulpContext = lcb_context->rx_id;
 	icmd->unsli3.rcvsli3.ox_id = lcb_context->ox_id;
@@ -5670,6 +5671,7 @@ lpfc_els_lcb_rsp(struct lpfc_hba *phba, LPFC_MBOXQ_t *pmb)
 	*((uint32_t *)(pcmd)) = ELS_CMD_ACC;
 	lcb_res->lcb_sub_command = lcb_context->sub_command;
 	lcb_res->lcb_type = lcb_context->type;
+	lcb_res->capability = lcb_context->capability;
 	lcb_res->lcb_frequency = lcb_context->frequency;
 	lcb_res->lcb_duration = lcb_context->duration;
 	elsiocb->iocb_cmpl = lpfc_cmpl_els_rsp;
-- 
cgit v1.2.3


From 06b6fa38155ea3709f4d612ae71c201c3f179164 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:24 -0700
Subject: scsi: lpfc: Remove lpfc_enable_pbde as module parameter

Enablement of the PBDE optimization brought out some incompatible behaviors
under error scenarios.

Best to disable and remove the PBDE optimization.

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_attr.c | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
index 514513f837a8..5a25553415f8 100644
--- a/drivers/scsi/lpfc/lpfc_attr.c
+++ b/drivers/scsi/lpfc/lpfc_attr.c
@@ -5387,14 +5387,6 @@ LPFC_BBCR_ATTR_RW(enable_bbcr, 1, 0, 1, "Enable BBC Recovery");
  */
 LPFC_ATTR_RW(enable_dpp, 1, 0, 1, "Enable Direct Packet Push");
 
-/*
- * lpfc_enable_pbde: Enable PBDE on PRISM - G7
- *       0  = PBDE on G7 disabled
- *       1  = PBDE on G7 enabled (default)
- * Value range is [0,1]. Default value is 1
- */
-LPFC_ATTR_R(enable_pbde, 1, 0, 1, "Enable PBDE support on PRISM");
-
 struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_nvme_info,
 	&dev_attr_bg_info,
@@ -5506,7 +5498,6 @@ struct device_attribute *lpfc_hba_attrs[] = {
 	&dev_attr_lpfc_enable_mds_diags,
 	&dev_attr_lpfc_enable_bbcr,
 	&dev_attr_lpfc_enable_dpp,
-	&dev_attr_lpfc_enable_pbde,
 	NULL,
 };
 
@@ -6541,7 +6532,6 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 	lpfc_nvme_io_channel_init(phba, lpfc_nvme_io_channel);
 	lpfc_enable_bbcr_init(phba, lpfc_enable_bbcr);
 	lpfc_enable_dpp_init(phba, lpfc_enable_dpp);
-	lpfc_enable_pbde_init(phba, lpfc_enable_pbde);
 
 	if (phba->sli_rev != LPFC_SLI_REV4) {
 		/* NVME only supported on SLI4 */
@@ -6558,6 +6548,8 @@ lpfc_get_cfgparam(struct lpfc_hba *phba)
 		phba->cfg_auto_imax = 0;
 	phba->initial_imax = phba->cfg_fcp_imax;
 
+	phba->cfg_enable_pbde = 0;
+
 	/* A value of 0 means use the number of CPUs found in the system */
 	if (phba->cfg_fcp_io_channel == 0)
 		phba->cfg_fcp_io_channel = phba->sli4_hba.num_present_cpu;
-- 
cgit v1.2.3


From 7fa8512330ab7cbb394b3e42ee092f4ad2e8f906 Mon Sep 17 00:00:00 2001
From: James Smart <jsmart2021@gmail.com>
Date: Tue, 31 Jul 2018 17:23:25 -0700
Subject: scsi: lpfc: update driver version to 12.0.0.6

Update the driver version to 12.0.0.6

Signed-off-by: Dick Kennedy <dick.kennedy@broadcom.com>
Signed-off-by: James Smart <james.smart@broadcom.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/lpfc/lpfc_version.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/lpfc/lpfc_version.h b/drivers/scsi/lpfc/lpfc_version.h
index a669af45fce7..501249509af4 100644
--- a/drivers/scsi/lpfc/lpfc_version.h
+++ b/drivers/scsi/lpfc/lpfc_version.h
@@ -20,7 +20,7 @@
  * included with this package.                                     *
  *******************************************************************/
 
-#define LPFC_DRIVER_VERSION "12.0.0.5"
+#define LPFC_DRIVER_VERSION "12.0.0.6"
 #define LPFC_DRIVER_NAME		"lpfc"
 
 /* Used for SLI 2/3 */
-- 
cgit v1.2.3


From 2afc9166f79b8f6da5f347f48515215ceee4ae37 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 2 Aug 2018 10:51:40 -0700
Subject: scsi: sysfs: Introduce sysfs_{un,}break_active_protection()

Introduce these two functions and export them such that the next patch
can add calls to these functions from the SCSI core.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 fs/sysfs/file.c       | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/sysfs.h | 14 ++++++++++++++
 2 files changed, 58 insertions(+)

diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index 5c13f29bfcdb..118fa197a35f 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -405,6 +405,50 @@ int sysfs_chmod_file(struct kobject *kobj, const struct attribute *attr,
 }
 EXPORT_SYMBOL_GPL(sysfs_chmod_file);
 
+/**
+ * sysfs_break_active_protection - break "active" protection
+ * @kobj: The kernel object @attr is associated with.
+ * @attr: The attribute to break the "active" protection for.
+ *
+ * With sysfs, just like kernfs, deletion of an attribute is postponed until
+ * all active .show() and .store() callbacks have finished unless this function
+ * is called. Hence this function is useful in methods that implement self
+ * deletion.
+ */
+struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj,
+						  const struct attribute *attr)
+{
+	struct kernfs_node *kn;
+
+	kobject_get(kobj);
+	kn = kernfs_find_and_get(kobj->sd, attr->name);
+	if (kn)
+		kernfs_break_active_protection(kn);
+	return kn;
+}
+EXPORT_SYMBOL_GPL(sysfs_break_active_protection);
+
+/**
+ * sysfs_unbreak_active_protection - restore "active" protection
+ * @kn: Pointer returned by sysfs_break_active_protection().
+ *
+ * Undo the effects of sysfs_break_active_protection(). Since this function
+ * calls kernfs_put() on the kernfs node that corresponds to the 'attr'
+ * argument passed to sysfs_break_active_protection() that attribute may have
+ * been removed between the sysfs_break_active_protection() and
+ * sysfs_unbreak_active_protection() calls, it is not safe to access @kn after
+ * this function has returned.
+ */
+void sysfs_unbreak_active_protection(struct kernfs_node *kn)
+{
+	struct kobject *kobj = kn->parent->priv;
+
+	kernfs_unbreak_active_protection(kn);
+	kernfs_put(kn);
+	kobject_put(kobj);
+}
+EXPORT_SYMBOL_GPL(sysfs_unbreak_active_protection);
+
 /**
  * sysfs_remove_file_ns - remove an object attribute with a custom ns tag
  * @kobj: object we're acting for
diff --git a/include/linux/sysfs.h b/include/linux/sysfs.h
index b8bfdc173ec0..3c12198c0103 100644
--- a/include/linux/sysfs.h
+++ b/include/linux/sysfs.h
@@ -237,6 +237,9 @@ int __must_check sysfs_create_files(struct kobject *kobj,
 				   const struct attribute **attr);
 int __must_check sysfs_chmod_file(struct kobject *kobj,
 				  const struct attribute *attr, umode_t mode);
+struct kernfs_node *sysfs_break_active_protection(struct kobject *kobj,
+						  const struct attribute *attr);
+void sysfs_unbreak_active_protection(struct kernfs_node *kn);
 void sysfs_remove_file_ns(struct kobject *kobj, const struct attribute *attr,
 			  const void *ns);
 bool sysfs_remove_file_self(struct kobject *kobj, const struct attribute *attr);
@@ -350,6 +353,17 @@ static inline int sysfs_chmod_file(struct kobject *kobj,
 	return 0;
 }
 
+static inline struct kernfs_node *
+sysfs_break_active_protection(struct kobject *kobj,
+			      const struct attribute *attr)
+{
+	return NULL;
+}
+
+static inline void sysfs_unbreak_active_protection(struct kernfs_node *kn)
+{
+}
+
 static inline void sysfs_remove_file_ns(struct kobject *kobj,
 					const struct attribute *attr,
 					const void *ns)
-- 
cgit v1.2.3


From 0ee223b2e1f67cb2de9c0e3247c510d846e74d63 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 2 Aug 2018 10:51:41 -0700
Subject: scsi: core: Avoid that SCSI device removal through sysfs triggers a
 deadlock

A long time ago the unfortunate decision was taken to add a self-deletion
attribute to the sysfs SCSI device directory. That decision was unfortunate
because self-deletion is really tricky. We can't drop that attribute
because widely used user space software depends on it, namely the
rescan-scsi-bus.sh script. Hence this patch that avoids that writing into
that attribute triggers a deadlock. See also commit 7973cbd9fbd9 ("[PATCH]
add sysfs attributes to scan and delete scsi_devices").

This patch avoids that self-removal triggers the following deadlock:

======================================================
WARNING: possible circular locking dependency detected
4.18.0-rc2-dbg+ #5 Not tainted
------------------------------------------------------
modprobe/6539 is trying to acquire lock:
000000008323c4cd (kn->count#202){++++}, at: kernfs_remove_by_name_ns+0x45/0x90

but task is already holding lock:
00000000a6ec2c69 (&shost->scan_mutex){+.+.}, at: scsi_remove_host+0x21/0x150 [scsi_mod]

which lock already depends on the new lock.

the existing dependency chain (in reverse order) is:

-> #1 (&shost->scan_mutex){+.+.}:
       __mutex_lock+0xfe/0xc70
       mutex_lock_nested+0x1b/0x20
       scsi_remove_device+0x26/0x40 [scsi_mod]
       sdev_store_delete+0x27/0x30 [scsi_mod]
       dev_attr_store+0x3e/0x50
       sysfs_kf_write+0x87/0xa0
       kernfs_fop_write+0x190/0x230
       __vfs_write+0xd2/0x3b0
       vfs_write+0x101/0x270
       ksys_write+0xab/0x120
       __x64_sys_write+0x43/0x50
       do_syscall_64+0x77/0x230
       entry_SYSCALL_64_after_hwframe+0x49/0xbe

-> #0 (kn->count#202){++++}:
       lock_acquire+0xd2/0x260
       __kernfs_remove+0x424/0x4a0
       kernfs_remove_by_name_ns+0x45/0x90
       remove_files.isra.1+0x3a/0x90
       sysfs_remove_group+0x5c/0xc0
       sysfs_remove_groups+0x39/0x60
       device_remove_attrs+0x82/0xb0
       device_del+0x251/0x580
       __scsi_remove_device+0x19f/0x1d0 [scsi_mod]
       scsi_forget_host+0x37/0xb0 [scsi_mod]
       scsi_remove_host+0x9b/0x150 [scsi_mod]
       sdebug_driver_remove+0x4b/0x150 [scsi_debug]
       device_release_driver_internal+0x241/0x360
       device_release_driver+0x12/0x20
       bus_remove_device+0x1bc/0x290
       device_del+0x259/0x580
       device_unregister+0x1a/0x70
       sdebug_remove_adapter+0x8b/0xf0 [scsi_debug]
       scsi_debug_exit+0x76/0xe8 [scsi_debug]
       __x64_sys_delete_module+0x1c1/0x280
       do_syscall_64+0x77/0x230
       entry_SYSCALL_64_after_hwframe+0x49/0xbe

other info that might help us debug this:

 Possible unsafe locking scenario:

       CPU0                    CPU1
       ----                    ----
  lock(&shost->scan_mutex);
                               lock(kn->count#202);
                               lock(&shost->scan_mutex);
  lock(kn->count#202);

 *** DEADLOCK ***

2 locks held by modprobe/6539:
 #0: 00000000efaf9298 (&dev->mutex){....}, at: device_release_driver_internal+0x68/0x360
 #1: 00000000a6ec2c69 (&shost->scan_mutex){+.+.}, at: scsi_remove_host+0x21/0x150 [scsi_mod]

stack backtrace:
CPU: 10 PID: 6539 Comm: modprobe Not tainted 4.18.0-rc2-dbg+ #5
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
Call Trace:
 dump_stack+0xa4/0xf5
 print_circular_bug.isra.34+0x213/0x221
 __lock_acquire+0x1a7e/0x1b50
 lock_acquire+0xd2/0x260
 __kernfs_remove+0x424/0x4a0
 kernfs_remove_by_name_ns+0x45/0x90
 remove_files.isra.1+0x3a/0x90
 sysfs_remove_group+0x5c/0xc0
 sysfs_remove_groups+0x39/0x60
 device_remove_attrs+0x82/0xb0
 device_del+0x251/0x580
 __scsi_remove_device+0x19f/0x1d0 [scsi_mod]
 scsi_forget_host+0x37/0xb0 [scsi_mod]
 scsi_remove_host+0x9b/0x150 [scsi_mod]
 sdebug_driver_remove+0x4b/0x150 [scsi_debug]
 device_release_driver_internal+0x241/0x360
 device_release_driver+0x12/0x20
 bus_remove_device+0x1bc/0x290
 device_del+0x259/0x580
 device_unregister+0x1a/0x70
 sdebug_remove_adapter+0x8b/0xf0 [scsi_debug]
 scsi_debug_exit+0x76/0xe8 [scsi_debug]
 __x64_sys_delete_module+0x1c1/0x280
 do_syscall_64+0x77/0x230
 entry_SYSCALL_64_after_hwframe+0x49/0xbe

See also https://www.mail-archive.com/linux-scsi@vger.kernel.org/msg54525.html.

Fixes: ac0ece9174ac ("scsi: use device_remove_file_self() instead of device_schedule_callback()")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Acked-by: Tejun Heo <tj@kernel.org>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: <stable@vger.kernel.org>

Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_sysfs.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index de122354d09a..3aee9464a7bf 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -722,8 +722,24 @@ static ssize_t
 sdev_store_delete(struct device *dev, struct device_attribute *attr,
 		  const char *buf, size_t count)
 {
-	if (device_remove_file_self(dev, attr))
-		scsi_remove_device(to_scsi_device(dev));
+	struct kernfs_node *kn;
+
+	kn = sysfs_break_active_protection(&dev->kobj, &attr->attr);
+	WARN_ON_ONCE(!kn);
+	/*
+	 * Concurrent writes into the "delete" sysfs attribute may trigger
+	 * concurrent calls to device_remove_file() and scsi_remove_device().
+	 * device_remove_file() handles concurrent removal calls by
+	 * serializing these and by ignoring the second and later removal
+	 * attempts.  Concurrent calls of scsi_remove_device() are
+	 * serialized. The second and later calls of scsi_remove_device() are
+	 * ignored because the first call of that function changes the device
+	 * state into SDEV_DEL.
+	 */
+	device_remove_file(dev, attr);
+	scsi_remove_device(to_scsi_device(dev));
+	if (kn)
+		sysfs_unbreak_active_protection(kn);
 	return count;
 };
 static DEVICE_ATTR(delete, S_IWUSR, NULL, sdev_store_delete);
-- 
cgit v1.2.3


From a3f90c75b833caeff123499e13e0e31cbecf7d5b Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Thu, 5 Jul 2018 18:59:35 -0400
Subject: media: dvb: convert tuner_info frequencies to Hz
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Right now, satellite tuner drivers specify frequencies in kHz,
while terrestrial/cable ones specify in Hz. That's confusing
for developers.

However, the main problem is that universal tuners capable
of handling both satellite and non-satelite delivery systems
are appearing. We end by needing to hack the drivers in
order to support such hybrid tuners.

So, convert everything to specify tuner frequencies in Hz.

Plese notice that a similar patch is also needed for frontends.

Tested-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Acked-by: Michael Büsch <m@bues.ch>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-core/dvb_frontend.c         | 25 +++++++++++++++++++++----
 drivers/media/dvb-frontends/ascot2e.c         |  6 +++---
 drivers/media/dvb-frontends/cx24113.c         |  8 ++++----
 drivers/media/dvb-frontends/dib0070.c         |  8 ++++----
 drivers/media/dvb-frontends/dib0090.c         | 12 ++++++------
 drivers/media/dvb-frontends/dvb-pll.c         | 16 ++++++++++++++--
 drivers/media/dvb-frontends/helene.c          | 12 ++++++------
 drivers/media/dvb-frontends/horus3a.c         |  6 +++---
 drivers/media/dvb-frontends/itd1000.c         |  8 ++++----
 drivers/media/dvb-frontends/ix2505v.c         |  4 ++--
 drivers/media/dvb-frontends/stb6000.c         |  4 ++--
 drivers/media/dvb-frontends/stb6100.c         |  5 ++---
 drivers/media/dvb-frontends/stv6110.c         |  6 +++---
 drivers/media/dvb-frontends/stv6110x.c        |  7 +++----
 drivers/media/dvb-frontends/stv6111.c         |  5 ++---
 drivers/media/dvb-frontends/tda18271c2dd.c    |  6 +++---
 drivers/media/dvb-frontends/tda665x.c         |  6 +++---
 drivers/media/dvb-frontends/tda8261.c         |  9 ++++-----
 drivers/media/dvb-frontends/tda826x.c         |  4 ++--
 drivers/media/dvb-frontends/ts2020.c          |  4 ++--
 drivers/media/dvb-frontends/tua6100.c         |  6 +++---
 drivers/media/dvb-frontends/zl10036.c         |  4 ++--
 drivers/media/tuners/e4000.c                  |  6 +++---
 drivers/media/tuners/fc0011.c                 |  6 +++---
 drivers/media/tuners/fc0012.c                 |  7 +++----
 drivers/media/tuners/fc0013.c                 |  7 +++----
 drivers/media/tuners/fc2580.c                 |  6 +++---
 drivers/media/tuners/it913x.c                 |  6 +++---
 drivers/media/tuners/m88rs6000t.c             |  6 +++---
 drivers/media/tuners/max2165.c                |  8 ++++----
 drivers/media/tuners/mc44s803.c               |  8 ++++----
 drivers/media/tuners/mt2060.c                 |  8 ++++----
 drivers/media/tuners/mt2063.c                 |  7 +++----
 drivers/media/tuners/mt2131.c                 |  8 ++++----
 drivers/media/tuners/mt2266.c                 |  8 ++++----
 drivers/media/tuners/mxl301rf.c               |  4 ++--
 drivers/media/tuners/mxl5005s.c               |  8 ++++----
 drivers/media/tuners/qm1d1b0004.c             |  4 ++--
 drivers/media/tuners/qm1d1c0042.c             |  4 ++--
 drivers/media/tuners/qt1010.c                 |  8 ++++----
 drivers/media/tuners/qt1010_priv.h            | 14 ++++++++------
 drivers/media/tuners/r820t.c                  |  6 +++---
 drivers/media/tuners/si2157.c                 |  6 +++---
 drivers/media/tuners/tda18212.c               |  8 ++++----
 drivers/media/tuners/tda18218.c               |  8 ++++----
 drivers/media/tuners/tda18250.c               |  6 +++---
 drivers/media/tuners/tda18271-fe.c            |  6 +++---
 drivers/media/tuners/tda827x.c                | 12 ++++++------
 drivers/media/tuners/tua9001.c                |  6 +++---
 drivers/media/tuners/tuner-xc2028.c           |  6 +++---
 drivers/media/tuners/xc4000.c                 | 12 ++++++------
 drivers/media/tuners/xc5000.c                 | 12 ++++++------
 drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c |  6 +++---
 include/media/dvb_frontend.h                  | 19 ++++++++++---------
 54 files changed, 221 insertions(+), 196 deletions(-)

diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index ce25aef39008..75e95b56f8b3 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -896,14 +896,31 @@ static int dvb_frontend_start(struct dvb_frontend *fe)
 static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe,
 					      u32 *freq_min, u32 *freq_max)
 {
-	*freq_min = max(fe->ops.info.frequency_min, fe->ops.tuner_ops.info.frequency_min);
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	__u32 tuner_min = fe->ops.tuner_ops.info.frequency_min_hz;
+	__u32 tuner_max = fe->ops.tuner_ops.info.frequency_max_hz;
+
+	/* If the standard is for satellite, convert frequencies to kHz */
+	switch (c->delivery_system) {
+	case SYS_DVBS:
+	case SYS_DVBS2:
+	case SYS_TURBO:
+	case SYS_ISDBS:
+		tuner_max /= kHz;
+		tuner_min /= kHz;
+		break;
+	default:
+		break;
+	}
+
+	*freq_min = max(fe->ops.info.frequency_min, tuner_min);
 
 	if (fe->ops.info.frequency_max == 0)
-		*freq_max = fe->ops.tuner_ops.info.frequency_max;
-	else if (fe->ops.tuner_ops.info.frequency_max == 0)
+		*freq_max = tuner_max;
+	else if (tuner_max == 0)
 		*freq_max = fe->ops.info.frequency_max;
 	else
-		*freq_max = min(fe->ops.info.frequency_max, fe->ops.tuner_ops.info.frequency_max);
+		*freq_max = min(fe->ops.info.frequency_max, tuner_max);
 
 	if (*freq_min == 0 || *freq_max == 0)
 		dev_warn(fe->dvb->device,
diff --git a/drivers/media/dvb-frontends/ascot2e.c b/drivers/media/dvb-frontends/ascot2e.c
index 9746c6dd7fb8..52ce0e6e2a15 100644
--- a/drivers/media/dvb-frontends/ascot2e.c
+++ b/drivers/media/dvb-frontends/ascot2e.c
@@ -468,9 +468,9 @@ static int ascot2e_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops ascot2e_tuner_ops = {
 	.info = {
 		.name = "Sony ASCOT2E",
-		.frequency_min = 1000000,
-		.frequency_max = 1200000000,
-		.frequency_step = 25000,
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1200 * MHz,
+		.frequency_step_hz =   25 * kHz,
 	},
 	.init = ascot2e_init,
 	.release = ascot2e_release,
diff --git a/drivers/media/dvb-frontends/cx24113.c b/drivers/media/dvb-frontends/cx24113.c
index 037db3e9d2dd..91a5033b6bd7 100644
--- a/drivers/media/dvb-frontends/cx24113.c
+++ b/drivers/media/dvb-frontends/cx24113.c
@@ -533,10 +533,10 @@ static void cx24113_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops cx24113_tuner_ops = {
 	.info = {
-		.name           = "Conexant CX24113",
-		.frequency_min  = 950000,
-		.frequency_max  = 2150000,
-		.frequency_step = 125,
+		.name              = "Conexant CX24113",
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =  125 * kHz,
 	},
 
 	.release       = cx24113_release,
diff --git a/drivers/media/dvb-frontends/dib0070.c b/drivers/media/dvb-frontends/dib0070.c
index 932d235118e2..37ebd5af8fd4 100644
--- a/drivers/media/dvb-frontends/dib0070.c
+++ b/drivers/media/dvb-frontends/dib0070.c
@@ -726,10 +726,10 @@ static void dib0070_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops dib0070_ops = {
 	.info = {
-		.name           = "DiBcom DiB0070",
-		.frequency_min  =  45000000,
-		.frequency_max  = 860000000,
-		.frequency_step =      1000,
+		.name              = "DiBcom DiB0070",
+		.frequency_min_hz  =  45 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =   1 * kHz,
 	},
 	.release       = dib0070_release,
 
diff --git a/drivers/media/dvb-frontends/dib0090.c b/drivers/media/dvb-frontends/dib0090.c
index ee7af34979ed..44a074261e69 100644
--- a/drivers/media/dvb-frontends/dib0090.c
+++ b/drivers/media/dvb-frontends/dib0090.c
@@ -2578,9 +2578,9 @@ static int dib0090_set_params(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops dib0090_ops = {
 	.info = {
 		 .name = "DiBcom DiB0090",
-		 .frequency_min = 45000000,
-		 .frequency_max = 860000000,
-		 .frequency_step = 1000,
+		 .frequency_min_hz  =  45 * MHz,
+		 .frequency_max_hz  = 860 * MHz,
+		 .frequency_step_hz =   1 * kHz,
 		 },
 	.release = dib0090_release,
 
@@ -2593,9 +2593,9 @@ static const struct dvb_tuner_ops dib0090_ops = {
 static const struct dvb_tuner_ops dib0090_fw_ops = {
 	.info = {
 		 .name = "DiBcom DiB0090",
-		 .frequency_min = 45000000,
-		 .frequency_max = 860000000,
-		 .frequency_step = 1000,
+		 .frequency_min_hz  =  45 * MHz,
+		 .frequency_max_hz  = 860 * MHz,
+		 .frequency_step_hz =   1 * kHz,
 		 },
 	.release = dib0090_release,
 
diff --git a/drivers/media/dvb-frontends/dvb-pll.c b/drivers/media/dvb-frontends/dvb-pll.c
index 4a663420190e..6d4b2eec67b4 100644
--- a/drivers/media/dvb-frontends/dvb-pll.c
+++ b/drivers/media/dvb-frontends/dvb-pll.c
@@ -799,6 +799,7 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr,
 	struct dvb_pll_priv *priv = NULL;
 	int ret;
 	const struct dvb_pll_desc *desc;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
 
 	b1 = kmalloc(1, GFP_KERNEL);
 	if (!b1)
@@ -844,8 +845,19 @@ struct dvb_frontend *dvb_pll_attach(struct dvb_frontend *fe, int pll_addr,
 
 	strncpy(fe->ops.tuner_ops.info.name, desc->name,
 		sizeof(fe->ops.tuner_ops.info.name));
-	fe->ops.tuner_ops.info.frequency_min = desc->min;
-	fe->ops.tuner_ops.info.frequency_max = desc->max;
+	switch (c->delivery_system) {
+	case SYS_DVBS:
+	case SYS_DVBS2:
+	case SYS_TURBO:
+	case SYS_ISDBS:
+		fe->ops.tuner_ops.info.frequency_min_hz = desc->min * kHz;
+		fe->ops.tuner_ops.info.frequency_max_hz = desc->max * kHz;
+		break;
+	default:
+		fe->ops.tuner_ops.info.frequency_min_hz = desc->min;
+		fe->ops.tuner_ops.info.frequency_max_hz = desc->max;
+	}
+
 	if (!desc->initdata)
 		fe->ops.tuner_ops.init = NULL;
 	if (!desc->sleepdata)
diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c
index a5de65dcf784..dc70fb684681 100644
--- a/drivers/media/dvb-frontends/helene.c
+++ b/drivers/media/dvb-frontends/helene.c
@@ -846,9 +846,9 @@ static int helene_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops helene_tuner_ops = {
 	.info = {
 		.name = "Sony HELENE Ter tuner",
-		.frequency_min = 1000000,
-		.frequency_max = 1200000000,
-		.frequency_step = 25000,
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1200 * MHz,
+		.frequency_step_hz =   25 * kHz,
 	},
 	.init = helene_init,
 	.release = helene_release,
@@ -860,9 +860,9 @@ static const struct dvb_tuner_ops helene_tuner_ops = {
 static const struct dvb_tuner_ops helene_tuner_ops_s = {
 	.info = {
 		.name = "Sony HELENE Sat tuner",
-		.frequency_min = 500000,
-		.frequency_max = 2500000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  500 * MHz,
+		.frequency_max_hz  = 2500 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.init = helene_init,
 	.release = helene_release,
diff --git a/drivers/media/dvb-frontends/horus3a.c b/drivers/media/dvb-frontends/horus3a.c
index 5e7e265a52e6..02bc08081971 100644
--- a/drivers/media/dvb-frontends/horus3a.c
+++ b/drivers/media/dvb-frontends/horus3a.c
@@ -330,9 +330,9 @@ static int horus3a_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops horus3a_tuner_ops = {
 	.info = {
 		.name = "Sony Horus3a",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.init = horus3a_init,
 	.release = horus3a_release,
diff --git a/drivers/media/dvb-frontends/itd1000.c b/drivers/media/dvb-frontends/itd1000.c
index 04f7f6854f73..c3a6e81ae87f 100644
--- a/drivers/media/dvb-frontends/itd1000.c
+++ b/drivers/media/dvb-frontends/itd1000.c
@@ -353,10 +353,10 @@ static void itd1000_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops itd1000_tuner_ops = {
 	.info = {
-		.name           = "Integrant ITD1000",
-		.frequency_min  = 950000,
-		.frequency_max  = 2150000,
-		.frequency_step = 125,     /* kHz for QPSK frontends */
+		.name              = "Integrant ITD1000",
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =  125 * kHz,
 	},
 
 	.release       = itd1000_release,
diff --git a/drivers/media/dvb-frontends/ix2505v.c b/drivers/media/dvb-frontends/ix2505v.c
index 965012ad5c59..9c055f72c416 100644
--- a/drivers/media/dvb-frontends/ix2505v.c
+++ b/drivers/media/dvb-frontends/ix2505v.c
@@ -256,8 +256,8 @@ static int ix2505v_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops ix2505v_tuner_ops = {
 	.info = {
 		.name = "Sharp IX2505V (B0017)",
-		.frequency_min = 950000,
-		.frequency_max = 2175000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2175 * MHz
 	},
 	.release = ix2505v_release,
 	.set_params = ix2505v_set_params,
diff --git a/drivers/media/dvb-frontends/stb6000.c b/drivers/media/dvb-frontends/stb6000.c
index 69c03892f2da..786b9eccde00 100644
--- a/drivers/media/dvb-frontends/stb6000.c
+++ b/drivers/media/dvb-frontends/stb6000.c
@@ -188,8 +188,8 @@ static int stb6000_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops stb6000_tuner_ops = {
 	.info = {
 		.name = "ST STB6000",
-		.frequency_min = 950000,
-		.frequency_max = 2150000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz
 	},
 	.release = stb6000_release,
 	.sleep = stb6000_sleep,
diff --git a/drivers/media/dvb-frontends/stb6100.c b/drivers/media/dvb-frontends/stb6100.c
index 3a851f524b16..30ac584dfab3 100644
--- a/drivers/media/dvb-frontends/stb6100.c
+++ b/drivers/media/dvb-frontends/stb6100.c
@@ -527,9 +527,8 @@ static int stb6100_set_params(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops stb6100_ops = {
 	.info = {
 		.name			= "STB6100 Silicon Tuner",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_step		= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 	},
 
 	.init		= stb6100_init,
diff --git a/drivers/media/dvb-frontends/stv6110.c b/drivers/media/dvb-frontends/stv6110.c
index 6aad0efa3174..7db9a5bceccc 100644
--- a/drivers/media/dvb-frontends/stv6110.c
+++ b/drivers/media/dvb-frontends/stv6110.c
@@ -371,9 +371,9 @@ static int stv6110_get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth)
 static const struct dvb_tuner_ops stv6110_tuner_ops = {
 	.info = {
 		.name = "ST STV6110",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.init = stv6110_init,
 	.release = stv6110_release,
diff --git a/drivers/media/dvb-frontends/stv6110x.c b/drivers/media/dvb-frontends/stv6110x.c
index d8950028d021..82c002d3833a 100644
--- a/drivers/media/dvb-frontends/stv6110x.c
+++ b/drivers/media/dvb-frontends/stv6110x.c
@@ -347,10 +347,9 @@ static void stv6110x_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops stv6110x_ops = {
 	.info = {
-		.name		= "STV6110(A) Silicon Tuner",
-		.frequency_min	=  950000,
-		.frequency_max	= 2150000,
-		.frequency_step	= 0,
+		.name		  = "STV6110(A) Silicon Tuner",
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 	.release		= stv6110x_release
 };
diff --git a/drivers/media/dvb-frontends/stv6111.c b/drivers/media/dvb-frontends/stv6111.c
index 9b715b6fe152..0cf460111acb 100644
--- a/drivers/media/dvb-frontends/stv6111.c
+++ b/drivers/media/dvb-frontends/stv6111.c
@@ -646,9 +646,8 @@ static int get_rf_strength(struct dvb_frontend *fe, u16 *st)
 static const struct dvb_tuner_ops tuner_ops = {
 	.info = {
 		.name		= "ST STV6111",
-		.frequency_min	= 950000,
-		.frequency_max	= 2150000,
-		.frequency_step	= 0
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 	.set_params		= set_params,
 	.release		= release,
diff --git a/drivers/media/dvb-frontends/tda18271c2dd.c b/drivers/media/dvb-frontends/tda18271c2dd.c
index fcffc7b4acf7..5ce58612315d 100644
--- a/drivers/media/dvb-frontends/tda18271c2dd.c
+++ b/drivers/media/dvb-frontends/tda18271c2dd.c
@@ -1215,9 +1215,9 @@ static int get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth)
 static const struct dvb_tuner_ops tuner_ops = {
 	.info = {
 		.name = "NXP TDA18271C2D",
-		.frequency_min  =  47125000,
-		.frequency_max  = 865000000,
-		.frequency_step =     62500
+		.frequency_min_hz  =  47125 * kHz,
+		.frequency_max_hz  =    865 * MHz,
+		.frequency_step_hz =  62500
 	},
 	.init              = init,
 	.sleep             = sleep,
diff --git a/drivers/media/dvb-frontends/tda665x.c b/drivers/media/dvb-frontends/tda665x.c
index 3ef7140ed7f3..8766c9ff6680 100644
--- a/drivers/media/dvb-frontends/tda665x.c
+++ b/drivers/media/dvb-frontends/tda665x.c
@@ -231,9 +231,9 @@ struct dvb_frontend *tda665x_attach(struct dvb_frontend *fe,
 	info			 = &fe->ops.tuner_ops.info;
 
 	memcpy(info->name, config->name, sizeof(config->name));
-	info->frequency_min	= config->frequency_min;
-	info->frequency_max	= config->frequency_max;
-	info->frequency_step	= config->frequency_offst;
+	info->frequency_min_hz	= config->frequency_min;
+	info->frequency_max_hz	= config->frequency_max;
+	info->frequency_step_hz	= config->frequency_offst;
 
 	printk(KERN_DEBUG "%s: Attaching TDA665x (%s) tuner\n", __func__, info->name);
 
diff --git a/drivers/media/dvb-frontends/tda8261.c b/drivers/media/dvb-frontends/tda8261.c
index f72a54e7eb23..500f50b81b66 100644
--- a/drivers/media/dvb-frontends/tda8261.c
+++ b/drivers/media/dvb-frontends/tda8261.c
@@ -163,10 +163,9 @@ static void tda8261_release(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops tda8261_ops = {
 
 	.info = {
-		.name		= "TDA8261",
-		.frequency_min	=  950000,
-		.frequency_max	= 2150000,
-		.frequency_step = 0
+		.name		   = "TDA8261",
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
 	},
 
 	.set_params	= tda8261_set_params,
@@ -190,7 +189,7 @@ struct dvb_frontend *tda8261_attach(struct dvb_frontend *fe,
 	fe->tuner_priv		= state;
 	fe->ops.tuner_ops	= tda8261_ops;
 
-	fe->ops.tuner_ops.info.frequency_step = div_tab[config->step_size];
+	fe->ops.tuner_ops.info.frequency_step_hz = div_tab[config->step_size] * kHz;
 
 	pr_info("%s: Attaching TDA8261 8PSK/QPSK tuner\n", __func__);
 
diff --git a/drivers/media/dvb-frontends/tda826x.c b/drivers/media/dvb-frontends/tda826x.c
index da427b4c2aaa..100da5d5fdc5 100644
--- a/drivers/media/dvb-frontends/tda826x.c
+++ b/drivers/media/dvb-frontends/tda826x.c
@@ -131,8 +131,8 @@ static int tda826x_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops tda826x_tuner_ops = {
 	.info = {
 		.name = "Philips TDA826X",
-		.frequency_min = 950000,
-		.frequency_max = 2175000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2175 * MHz
 	},
 	.release = tda826x_release,
 	.sleep = tda826x_sleep,
diff --git a/drivers/media/dvb-frontends/ts2020.c b/drivers/media/dvb-frontends/ts2020.c
index c55882a8da06..3e3e40878633 100644
--- a/drivers/media/dvb-frontends/ts2020.c
+++ b/drivers/media/dvb-frontends/ts2020.c
@@ -498,8 +498,8 @@ static int ts2020_read_signal_strength(struct dvb_frontend *fe,
 static const struct dvb_tuner_ops ts2020_tuner_ops = {
 	.info = {
 		.name = "TS2020",
-		.frequency_min = 950000,
-		.frequency_max = 2150000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz
 	},
 	.init = ts2020_init,
 	.release = ts2020_release,
diff --git a/drivers/media/dvb-frontends/tua6100.c b/drivers/media/dvb-frontends/tua6100.c
index 1d41abd47f04..b233b7be0b84 100644
--- a/drivers/media/dvb-frontends/tua6100.c
+++ b/drivers/media/dvb-frontends/tua6100.c
@@ -155,9 +155,9 @@ static int tua6100_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 static const struct dvb_tuner_ops tua6100_tuner_ops = {
 	.info = {
 		.name = "Infineon TUA6100",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_step = 1000,
+		.frequency_min_hz  =  950 * MHz,
+		.frequency_max_hz  = 2150 * MHz,
+		.frequency_step_hz =    1 * MHz,
 	},
 	.release = tua6100_release,
 	.sleep = tua6100_sleep,
diff --git a/drivers/media/dvb-frontends/zl10036.c b/drivers/media/dvb-frontends/zl10036.c
index 89dd65ae88ad..e5a432fd84c3 100644
--- a/drivers/media/dvb-frontends/zl10036.c
+++ b/drivers/media/dvb-frontends/zl10036.c
@@ -443,8 +443,8 @@ static int zl10036_init(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops zl10036_tuner_ops = {
 	.info = {
 		.name = "Zarlink ZL10036",
-		.frequency_min = 950000,
-		.frequency_max = 2175000
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2175 * MHz
 	},
 	.init = zl10036_init,
 	.release = zl10036_release,
diff --git a/drivers/media/tuners/e4000.c b/drivers/media/tuners/e4000.c
index b5b9d87ba75c..fbec1a13dc6a 100644
--- a/drivers/media/tuners/e4000.c
+++ b/drivers/media/tuners/e4000.c
@@ -610,9 +610,9 @@ static int e4000_dvb_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops e4000_dvb_tuner_ops = {
 	.info = {
-		.name           = "Elonics E4000",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
+		.name              = "Elonics E4000",
+		.frequency_min_hz  = 174 * MHz,
+		.frequency_max_hz  = 862 * MHz,
 	},
 
 	.init = e4000_dvb_init,
diff --git a/drivers/media/tuners/fc0011.c b/drivers/media/tuners/fc0011.c
index 145407dee3db..a983899c6b0b 100644
--- a/drivers/media/tuners/fc0011.c
+++ b/drivers/media/tuners/fc0011.c
@@ -472,10 +472,10 @@ static int fc0011_get_bandwidth(struct dvb_frontend *fe, u32 *bandwidth)
 
 static const struct dvb_tuner_ops fc0011_tuner_ops = {
 	.info = {
-		.name		= "Fitipower FC0011",
+		.name		  = "Fitipower FC0011",
 
-		.frequency_min	= 45000000,
-		.frequency_max	= 1000000000,
+		.frequency_min_hz =   45 * MHz,
+		.frequency_max_hz = 1000 * MHz,
 	},
 
 	.release		= fc0011_release,
diff --git a/drivers/media/tuners/fc0012.c b/drivers/media/tuners/fc0012.c
index 625ac6f51c39..e992b98ae5bc 100644
--- a/drivers/media/tuners/fc0012.c
+++ b/drivers/media/tuners/fc0012.c
@@ -415,11 +415,10 @@ exit:
 
 static const struct dvb_tuner_ops fc0012_tuner_ops = {
 	.info = {
-		.name           = "Fitipower FC0012",
+		.name              = "Fitipower FC0012",
 
-		.frequency_min  = 37000000,	/* estimate */
-		.frequency_max  = 862000000,	/* estimate */
-		.frequency_step = 0,
+		.frequency_min_hz  =  37 * MHz,	/* estimate */
+		.frequency_max_hz  = 862 * MHz,	/* estimate */
 	},
 
 	.release	= fc0012_release,
diff --git a/drivers/media/tuners/fc0013.c b/drivers/media/tuners/fc0013.c
index e606118d1a9b..fc62afb1450d 100644
--- a/drivers/media/tuners/fc0013.c
+++ b/drivers/media/tuners/fc0013.c
@@ -574,11 +574,10 @@ exit:
 
 static const struct dvb_tuner_ops fc0013_tuner_ops = {
 	.info = {
-		.name		= "Fitipower FC0013",
+		.name		  = "Fitipower FC0013",
 
-		.frequency_min	= 37000000,	/* estimate */
-		.frequency_max	= 1680000000,	/* CHECK */
-		.frequency_step	= 0,
+		.frequency_min_hz =   37 * MHz,	/* estimate */
+		.frequency_max_hz = 1680 * MHz,	/* CHECK */
 	},
 
 	.release	= fc0013_release,
diff --git a/drivers/media/tuners/fc2580.c b/drivers/media/tuners/fc2580.c
index 743184ae0d26..db26892aac84 100644
--- a/drivers/media/tuners/fc2580.c
+++ b/drivers/media/tuners/fc2580.c
@@ -355,9 +355,9 @@ static int fc2580_dvb_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops fc2580_dvb_tuner_ops = {
 	.info = {
-		.name           = "FCI FC2580",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
+		.name             = "FCI FC2580",
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
 	},
 
 	.init = fc2580_dvb_init,
diff --git a/drivers/media/tuners/it913x.c b/drivers/media/tuners/it913x.c
index 27e5bc1c3cb5..b5eb39921e95 100644
--- a/drivers/media/tuners/it913x.c
+++ b/drivers/media/tuners/it913x.c
@@ -375,9 +375,9 @@ err:
 
 static const struct dvb_tuner_ops it913x_tuner_ops = {
 	.info = {
-		.name           = "ITE IT913X",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
+		.name             = "ITE IT913X",
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
 	},
 
 	.init = it913x_init,
diff --git a/drivers/media/tuners/m88rs6000t.c b/drivers/media/tuners/m88rs6000t.c
index 9f3e0fd4cad9..3df2f23a40be 100644
--- a/drivers/media/tuners/m88rs6000t.c
+++ b/drivers/media/tuners/m88rs6000t.c
@@ -569,9 +569,9 @@ err:
 
 static const struct dvb_tuner_ops m88rs6000t_tuner_ops = {
 	.info = {
-		.name          = "Montage M88RS6000 Internal Tuner",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
+		.name             = "Montage M88RS6000 Internal Tuner",
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 
 	.init = m88rs6000t_init,
diff --git a/drivers/media/tuners/max2165.c b/drivers/media/tuners/max2165.c
index 20ceb72e530b..721d8f722efb 100644
--- a/drivers/media/tuners/max2165.c
+++ b/drivers/media/tuners/max2165.c
@@ -377,10 +377,10 @@ static void max2165_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops max2165_tuner_ops = {
 	.info = {
-		.name           = "Maxim MAX2165",
-		.frequency_min  = 470000000,
-		.frequency_max  = 862000000,
-		.frequency_step =     50000,
+		.name              = "Maxim MAX2165",
+		.frequency_min_hz  = 470 * MHz,
+		.frequency_max_hz  = 862 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release	   = max2165_release,
diff --git a/drivers/media/tuners/mc44s803.c b/drivers/media/tuners/mc44s803.c
index 403c6b2aa53b..2023e081d9ad 100644
--- a/drivers/media/tuners/mc44s803.c
+++ b/drivers/media/tuners/mc44s803.c
@@ -300,10 +300,10 @@ static int mc44s803_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops mc44s803_tuner_ops = {
 	.info = {
-		.name           = "Freescale MC44S803",
-		.frequency_min  =   48000000,
-		.frequency_max  = 1000000000,
-		.frequency_step =     100000,
+		.name              = "Freescale MC44S803",
+		.frequency_min_hz  =   48 * MHz,
+		.frequency_max_hz  = 1000 * MHz,
+		.frequency_step_hz =  100 * kHz,
 	},
 
 	.release       = mc44s803_release,
diff --git a/drivers/media/tuners/mt2060.c b/drivers/media/tuners/mt2060.c
index 3d3c6815b6a7..4ace77cfe285 100644
--- a/drivers/media/tuners/mt2060.c
+++ b/drivers/media/tuners/mt2060.c
@@ -395,10 +395,10 @@ static void mt2060_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mt2060_tuner_ops = {
 	.info = {
-		.name           = "Microtune MT2060",
-		.frequency_min  =  48000000,
-		.frequency_max  = 860000000,
-		.frequency_step =     50000,
+		.name              = "Microtune MT2060",
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release       = mt2060_release,
diff --git a/drivers/media/tuners/mt2063.c b/drivers/media/tuners/mt2063.c
index 80dc3e241b4a..f4c8a7293ebb 100644
--- a/drivers/media/tuners/mt2063.c
+++ b/drivers/media/tuners/mt2063.c
@@ -2200,10 +2200,9 @@ static int mt2063_get_bandwidth(struct dvb_frontend *fe, u32 *bw)
 static const struct dvb_tuner_ops mt2063_ops = {
 	.info = {
 		 .name = "MT2063 Silicon Tuner",
-		 .frequency_min = 45000000,
-		 .frequency_max = 865000000,
-		 .frequency_step = 0,
-		 },
+		 .frequency_min_hz  =  45 * MHz,
+		 .frequency_max_hz  = 865 * MHz,
+	 },
 
 	.init = mt2063_init,
 	.sleep = MT2063_Sleep,
diff --git a/drivers/media/tuners/mt2131.c b/drivers/media/tuners/mt2131.c
index 659bf19dc434..086a7b7cf634 100644
--- a/drivers/media/tuners/mt2131.c
+++ b/drivers/media/tuners/mt2131.c
@@ -235,10 +235,10 @@ static void mt2131_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mt2131_tuner_ops = {
 	.info = {
-		.name           = "Microtune MT2131",
-		.frequency_min  =  48000000,
-		.frequency_max  = 860000000,
-		.frequency_step =     50000,
+		.name              = "Microtune MT2131",
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release       = mt2131_release,
diff --git a/drivers/media/tuners/mt2266.c b/drivers/media/tuners/mt2266.c
index f4545b7f5da2..e6cc78720de4 100644
--- a/drivers/media/tuners/mt2266.c
+++ b/drivers/media/tuners/mt2266.c
@@ -304,10 +304,10 @@ static void mt2266_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mt2266_tuner_ops = {
 	.info = {
-		.name           = "Microtune MT2266",
-		.frequency_min  = 174000000,
-		.frequency_max  = 862000000,
-		.frequency_step =     50000,
+		.name              = "Microtune MT2266",
+		.frequency_min_hz  = 174 * MHz,
+		.frequency_max_hz  = 862 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 	.release       = mt2266_release,
 	.init          = mt2266_init,
diff --git a/drivers/media/tuners/mxl301rf.c b/drivers/media/tuners/mxl301rf.c
index 57b0e4862aaf..c628435a1b06 100644
--- a/drivers/media/tuners/mxl301rf.c
+++ b/drivers/media/tuners/mxl301rf.c
@@ -271,8 +271,8 @@ static const struct dvb_tuner_ops mxl301rf_ops = {
 	.info = {
 		.name = "MaxLinear MxL301RF",
 
-		.frequency_min =  93000000,
-		.frequency_max = 803142857,
+		.frequency_min_hz =  93 * MHz,
+		.frequency_max_hz = 803 * MHz + 142857,
 	},
 
 	.init = mxl301rf_init,
diff --git a/drivers/media/tuners/mxl5005s.c b/drivers/media/tuners/mxl5005s.c
index 355ef2959b7d..ec584316c812 100644
--- a/drivers/media/tuners/mxl5005s.c
+++ b/drivers/media/tuners/mxl5005s.c
@@ -4075,10 +4075,10 @@ static void mxl5005s_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops mxl5005s_tuner_ops = {
 	.info = {
-		.name           = "MaxLinear MXL5005S",
-		.frequency_min  =  48000000,
-		.frequency_max  = 860000000,
-		.frequency_step =     50000,
+		.name              = "MaxLinear MXL5005S",
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz =  50 * kHz,
 	},
 
 	.release       = mxl5005s_release,
diff --git a/drivers/media/tuners/qm1d1b0004.c b/drivers/media/tuners/qm1d1b0004.c
index b4495cc1626b..008ad870c00f 100644
--- a/drivers/media/tuners/qm1d1b0004.c
+++ b/drivers/media/tuners/qm1d1b0004.c
@@ -186,8 +186,8 @@ static const struct dvb_tuner_ops qm1d1b0004_ops = {
 	.info = {
 		.name = "Sharp qm1d1b0004",
 
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 
 	.init = qm1d1b0004_init,
diff --git a/drivers/media/tuners/qm1d1c0042.c b/drivers/media/tuners/qm1d1c0042.c
index 642a065b9a07..83ca5dc047ea 100644
--- a/drivers/media/tuners/qm1d1c0042.c
+++ b/drivers/media/tuners/qm1d1c0042.c
@@ -388,8 +388,8 @@ static const struct dvb_tuner_ops qm1d1c0042_ops = {
 	.info = {
 		.name = "Sharp QM1D1C0042",
 
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 	},
 
 	.init = qm1d1c0042_init,
diff --git a/drivers/media/tuners/qt1010.c b/drivers/media/tuners/qt1010.c
index b92be882ab3c..4565c06b1617 100644
--- a/drivers/media/tuners/qt1010.c
+++ b/drivers/media/tuners/qt1010.c
@@ -394,10 +394,10 @@ static int qt1010_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops qt1010_tuner_ops = {
 	.info = {
-		.name           = "Quantek QT1010",
-		.frequency_min  = QT1010_MIN_FREQ,
-		.frequency_max  = QT1010_MAX_FREQ,
-		.frequency_step = QT1010_STEP,
+		.name              = "Quantek QT1010",
+		.frequency_min_hz  = QT1010_MIN_FREQ,
+		.frequency_max_hz  = QT1010_MAX_FREQ,
+		.frequency_step_hz = QT1010_STEP,
 	},
 
 	.release       = qt1010_release,
diff --git a/drivers/media/tuners/qt1010_priv.h b/drivers/media/tuners/qt1010_priv.h
index 4cb78ecc8985..f25324c63067 100644
--- a/drivers/media/tuners/qt1010_priv.h
+++ b/drivers/media/tuners/qt1010_priv.h
@@ -71,12 +71,14 @@ reg def meaning
 2f  00  ? not used?
 */
 
-#define QT1010_STEP         125000 /*  125 kHz used by Windows drivers,
-				      hw could be more precise but we don't
-				      know how to use */
-#define QT1010_MIN_FREQ   48000000 /*   48 MHz */
-#define QT1010_MAX_FREQ  860000000 /*  860 MHz */
-#define QT1010_OFFSET   1246000000 /* 1246 MHz */
+#define QT1010_STEP         (125 * kHz) /*
+					 * used by Windows drivers,
+				         * hw could be more precise but we don't
+				         * know how to use
+					 */
+#define QT1010_MIN_FREQ   (48 * MHz)
+#define QT1010_MAX_FREQ  (860 * MHz)
+#define QT1010_OFFSET   (1246 * MHz)
 
 #define QT1010_WR 0
 #define QT1010_RD 1
diff --git a/drivers/media/tuners/r820t.c b/drivers/media/tuners/r820t.c
index 3e14b9e2e763..ba4be08a8551 100644
--- a/drivers/media/tuners/r820t.c
+++ b/drivers/media/tuners/r820t.c
@@ -2297,9 +2297,9 @@ static void r820t_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops r820t_tuner_ops = {
 	.info = {
-		.name           = "Rafael Micro R820T",
-		.frequency_min  =   42000000,
-		.frequency_max  = 1002000000,
+		.name             = "Rafael Micro R820T",
+		.frequency_min_hz =   42 * MHz,
+		.frequency_max_hz = 1002 * MHz,
 	},
 	.init = r820t_init,
 	.release = r820t_release,
diff --git a/drivers/media/tuners/si2157.c b/drivers/media/tuners/si2157.c
index 9e34d31d724d..a08d8fe2bb1b 100644
--- a/drivers/media/tuners/si2157.c
+++ b/drivers/media/tuners/si2157.c
@@ -387,9 +387,9 @@ static int si2157_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops si2157_ops = {
 	.info = {
-		.name           = "Silicon Labs Si2141/Si2146/2147/2148/2157/2158",
-		.frequency_min  = 42000000,
-		.frequency_max  = 870000000,
+		.name             = "Silicon Labs Si2141/Si2146/2147/2148/2157/2158",
+		.frequency_min_hz =  42 * MHz,
+		.frequency_max_hz = 870 * MHz,
 	},
 
 	.init = si2157_init,
diff --git a/drivers/media/tuners/tda18212.c b/drivers/media/tuners/tda18212.c
index 7b8068354fea..8326106ec2e3 100644
--- a/drivers/media/tuners/tda18212.c
+++ b/drivers/media/tuners/tda18212.c
@@ -175,11 +175,11 @@ static int tda18212_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops tda18212_tuner_ops = {
 	.info = {
-		.name           = "NXP TDA18212",
+		.name              = "NXP TDA18212",
 
-		.frequency_min  =  48000000,
-		.frequency_max  = 864000000,
-		.frequency_step =      1000,
+		.frequency_min_hz  =  48 * MHz,
+		.frequency_max_hz  = 864 * MHz,
+		.frequency_step_hz =   1 * kHz,
 	},
 
 	.set_params    = tda18212_set_params,
diff --git a/drivers/media/tuners/tda18218.c b/drivers/media/tuners/tda18218.c
index c56fcf5d48e3..cbbd4d5e15da 100644
--- a/drivers/media/tuners/tda18218.c
+++ b/drivers/media/tuners/tda18218.c
@@ -269,11 +269,11 @@ static void tda18218_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops tda18218_tuner_ops = {
 	.info = {
-		.name           = "NXP TDA18218",
+		.name              = "NXP TDA18218",
 
-		.frequency_min  = 174000000,
-		.frequency_max  = 864000000,
-		.frequency_step =      1000,
+		.frequency_min_hz  = 174 * MHz,
+		.frequency_max_hz  = 864 * MHz,
+		.frequency_step_hz =   1 * kHz,
 	},
 
 	.release       = tda18218_release,
diff --git a/drivers/media/tuners/tda18250.c b/drivers/media/tuners/tda18250.c
index 20d12b063380..20d10ef45ab6 100644
--- a/drivers/media/tuners/tda18250.c
+++ b/drivers/media/tuners/tda18250.c
@@ -740,9 +740,9 @@ static int tda18250_sleep(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops tda18250_ops = {
 	.info = {
-		.name           = "NXP TDA18250",
-		.frequency_min  = 42000000,
-		.frequency_max  = 870000000,
+		.name              = "NXP TDA18250",
+		.frequency_min_hz  =  42 * MHz,
+		.frequency_max_hz  = 870 * MHz,
 	},
 
 	.init = tda18250_init,
diff --git a/drivers/media/tuners/tda18271-fe.c b/drivers/media/tuners/tda18271-fe.c
index 147155553648..4d69029229e4 100644
--- a/drivers/media/tuners/tda18271-fe.c
+++ b/drivers/media/tuners/tda18271-fe.c
@@ -1240,9 +1240,9 @@ static int tda18271_set_config(struct dvb_frontend *fe, void *priv_cfg)
 static const struct dvb_tuner_ops tda18271_tuner_ops = {
 	.info = {
 		.name = "NXP TDA18271HD",
-		.frequency_min  =  45000000,
-		.frequency_max  = 864000000,
-		.frequency_step =     62500
+		.frequency_min_hz  =  45 * MHz,
+		.frequency_max_hz  = 864 * MHz,
+		.frequency_step_hz = 62500
 	},
 	.init              = tda18271_init,
 	.sleep             = tda18271_sleep,
diff --git a/drivers/media/tuners/tda827x.c b/drivers/media/tuners/tda827x.c
index 8400808f8f7f..4391dabba510 100644
--- a/drivers/media/tuners/tda827x.c
+++ b/drivers/media/tuners/tda827x.c
@@ -816,9 +816,9 @@ static int tda827x_initial_sleep(struct dvb_frontend *fe)
 static const struct dvb_tuner_ops tda827xo_tuner_ops = {
 	.info = {
 		.name = "Philips TDA827X",
-		.frequency_min  =  55000000,
-		.frequency_max  = 860000000,
-		.frequency_step =    250000
+		.frequency_min_hz  =  55 * MHz,
+		.frequency_max_hz  = 860 * MHz,
+		.frequency_step_hz = 250 * kHz
 	},
 	.release = tda827x_release,
 	.init = tda827x_initial_init,
@@ -832,9 +832,9 @@ static const struct dvb_tuner_ops tda827xo_tuner_ops = {
 static const struct dvb_tuner_ops tda827xa_tuner_ops = {
 	.info = {
 		.name = "Philips TDA827XA",
-		.frequency_min  =  44000000,
-		.frequency_max  = 906000000,
-		.frequency_step =     62500
+		.frequency_min_hz  =  44 * MHz,
+		.frequency_max_hz  = 906 * MHz,
+		.frequency_step_hz = 62500
 	},
 	.release = tda827x_release,
 	.init = tda827x_init,
diff --git a/drivers/media/tuners/tua9001.c b/drivers/media/tuners/tua9001.c
index 9d70378fe2d3..5c89a130b47d 100644
--- a/drivers/media/tuners/tua9001.c
+++ b/drivers/media/tuners/tua9001.c
@@ -164,9 +164,9 @@ static int tua9001_get_if_frequency(struct dvb_frontend *fe, u32 *frequency)
 
 static const struct dvb_tuner_ops tua9001_tuner_ops = {
 	.info = {
-		.name           = "Infineon TUA9001",
-		.frequency_min  = 170000000,
-		.frequency_max  = 862000000,
+		.name             = "Infineon TUA9001",
+		.frequency_min_hz = 170 * MHz,
+		.frequency_max_hz = 862 * MHz,
 	},
 
 	.init = tua9001_init,
diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 84744e138982..222b93ef31c0 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -1440,9 +1440,9 @@ unlock:
 static const struct dvb_tuner_ops xc2028_dvb_tuner_ops = {
 	.info = {
 		 .name = "Xceive XC3028",
-		 .frequency_min = 42000000,
-		 .frequency_max = 864000000,
-		 .frequency_step = 50000,
+		 .frequency_min_hz  =  42 * MHz,
+		 .frequency_max_hz  = 864 * MHz,
+		 .frequency_step_hz =  50 * kHz,
 		 },
 
 	.set_config	   = xc2028_set_config,
diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index f0fa8da08afa..76b3f37f24a8 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -398,8 +398,8 @@ static int xc_set_rf_frequency(struct xc4000_priv *priv, u32 freq_hz)
 
 	dprintk(1, "%s(%u)\n", __func__, freq_hz);
 
-	if ((freq_hz > xc4000_tuner_ops.info.frequency_max) ||
-	    (freq_hz < xc4000_tuner_ops.info.frequency_min))
+	if ((freq_hz > xc4000_tuner_ops.info.frequency_max_hz) ||
+	    (freq_hz < xc4000_tuner_ops.info.frequency_min_hz))
 		return -EINVAL;
 
 	freq_code = (u16)(freq_hz / 15625);
@@ -1635,10 +1635,10 @@ static void xc4000_release(struct dvb_frontend *fe)
 
 static const struct dvb_tuner_ops xc4000_tuner_ops = {
 	.info = {
-		.name           = "Xceive XC4000",
-		.frequency_min  =    1000000,
-		.frequency_max  = 1023000000,
-		.frequency_step =      50000,
+		.name              = "Xceive XC4000",
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1023 * MHz,
+		.frequency_step_hz =   50 * kHz,
 	},
 
 	.release	   = xc4000_release,
diff --git a/drivers/media/tuners/xc5000.c b/drivers/media/tuners/xc5000.c
index f7a8d05d1758..f6b65278e502 100644
--- a/drivers/media/tuners/xc5000.c
+++ b/drivers/media/tuners/xc5000.c
@@ -460,8 +460,8 @@ static int xc_set_rf_frequency(struct xc5000_priv *priv, u32 freq_hz)
 
 	dprintk(1, "%s(%u)\n", __func__, freq_hz);
 
-	if ((freq_hz > xc5000_tuner_ops.info.frequency_max) ||
-		(freq_hz < xc5000_tuner_ops.info.frequency_min))
+	if ((freq_hz > xc5000_tuner_ops.info.frequency_max_hz) ||
+		(freq_hz < xc5000_tuner_ops.info.frequency_min_hz))
 		return -EINVAL;
 
 	freq_code = (u16)(freq_hz / 15625);
@@ -1350,10 +1350,10 @@ static int xc5000_set_config(struct dvb_frontend *fe, void *priv_cfg)
 
 static const struct dvb_tuner_ops xc5000_tuner_ops = {
 	.info = {
-		.name           = "Xceive XC5000",
-		.frequency_min  =    1000000,
-		.frequency_max  = 1023000000,
-		.frequency_step =      50000,
+		.name              = "Xceive XC5000",
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 1023 * MHz,
+		.frequency_step_hz =   50 * kHz,
 	},
 
 	.release	   = xc5000_release,
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
index 240d736bf1bb..92b3b9221a21 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-tuner.c
@@ -465,9 +465,9 @@ static const struct dvb_tuner_ops mxl111sf_tuner_tuner_ops = {
 	.info = {
 		.name = "MaxLinear MxL111SF",
 #if 0
-		.frequency_min  = ,
-		.frequency_max  = ,
-		.frequency_step = ,
+		.frequency_min_hz  = ,
+		.frequency_max_hz  = ,
+		.frequency_step_hz = ,
 #endif
 	},
 #if 0
diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h
index 331c8269c00e..aebaec2dc725 100644
--- a/include/media/dvb_frontend.h
+++ b/include/media/dvb_frontend.h
@@ -52,6 +52,10 @@
  */
 #define MAX_DELSYS	8
 
+/* Helper definitions to be used at frontend drivers */
+#define kHz 1000UL
+#define MHz 1000000UL
+
 /**
  * struct dvb_frontend_tune_settings - parameters to adjust frontend tuning
  *
@@ -73,22 +77,19 @@ struct dvb_frontend;
  * struct dvb_tuner_info - Frontend name and min/max ranges/bandwidths
  *
  * @name:		name of the Frontend
- * @frequency_min:	minimal frequency supported
- * @frequency_max:	maximum frequency supported
- * @frequency_step:	frequency step
+ * @frequency_min_hz:	minimal frequency supported in Hz
+ * @frequency_max_hz:	maximum frequency supported in Hz
+ * @frequency_step_hz:	frequency step in Hz
  * @bandwidth_min:	minimal frontend bandwidth supported
  * @bandwidth_max:	maximum frontend bandwidth supported
  * @bandwidth_step:	frontend bandwidth step
- *
- * NOTE: frequency parameters are in Hz, for terrestrial/cable or kHz for
- * satellite.
  */
 struct dvb_tuner_info {
 	char name[128];
 
-	u32 frequency_min;
-	u32 frequency_max;
-	u32 frequency_step;
+	u32 frequency_min_hz;
+	u32 frequency_max_hz;
+	u32 frequency_step_hz;
 
 	u32 bandwidth_min;
 	u32 bandwidth_max;
-- 
cgit v1.2.3


From 46a75118d6fb93863abfa3723ea6a7ca921c928b Mon Sep 17 00:00:00 2001
From: Arjun Vynipadath <arjun@chelsio.com>
Date: Wed, 1 Aug 2018 17:17:12 +0530
Subject: scsi: csiostor: update csio_get_flash_params()

- Updates csio_get_flash_params() to take care of ISSI, Macronix and
  Winbond FLASH parts.

- Assume flash part size to be 4MB if it cannot be identified

Signed-off-by: Arjun Vynipadath <arjun@chelsio.com>
Signed-off-by: Varun Prakash <varun@chelsio.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/csiostor/csio_hw.c | 115 +++++++++++++++++++++++++++++++++++-----
 1 file changed, 102 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/csiostor/csio_hw.c b/drivers/scsi/csiostor/csio_hw.c
index a10cf25ee7f9..23d07e9f87d0 100644
--- a/drivers/scsi/csiostor/csio_hw.c
+++ b/drivers/scsi/csiostor/csio_hw.c
@@ -761,27 +761,116 @@ out:
 static int
 csio_hw_get_flash_params(struct csio_hw *hw)
 {
+	/* Table for non-Numonix supported flash parts.  Numonix parts are left
+	 * to the preexisting code.  All flash parts have 64KB sectors.
+	 */
+	static struct flash_desc {
+		u32 vendor_and_model_id;
+		u32 size_mb;
+	} supported_flash[] = {
+		{ 0x150201, 4 << 20 },       /* Spansion 4MB S25FL032P */
+	};
+
+	u32 part, manufacturer;
+	u32 density, size = 0;
+	u32 flashid = 0;
 	int ret;
-	uint32_t info = 0;
 
 	ret = csio_hw_sf1_write(hw, 1, 1, 0, SF_RD_ID);
 	if (!ret)
-		ret = csio_hw_sf1_read(hw, 3, 0, 1, &info);
+		ret = csio_hw_sf1_read(hw, 3, 0, 1, &flashid);
 	csio_wr_reg32(hw, 0, SF_OP_A);    /* unlock SF */
-	if (ret != 0)
+	if (ret)
 		return ret;
 
-	if ((info & 0xff) != 0x20)		/* not a Numonix flash */
-		return -EINVAL;
-	info >>= 16;				/* log2 of size */
-	if (info >= 0x14 && info < 0x18)
-		hw->params.sf_nsec = 1 << (info - 16);
-	else if (info == 0x18)
-		hw->params.sf_nsec = 64;
-	else
-		return -EINVAL;
-	hw->params.sf_size = 1 << info;
+	/* Check to see if it's one of our non-standard supported Flash parts.
+	 */
+	for (part = 0; part < ARRAY_SIZE(supported_flash); part++)
+		if (supported_flash[part].vendor_and_model_id == flashid) {
+			hw->params.sf_size = supported_flash[part].size_mb;
+			hw->params.sf_nsec =
+				hw->params.sf_size / SF_SEC_SIZE;
+			goto found;
+		}
+
+	/* Decode Flash part size.  The code below looks repetative with
+	 * common encodings, but that's not guaranteed in the JEDEC
+	 * specification for the Read JADEC ID command.  The only thing that
+	 * we're guaranteed by the JADEC specification is where the
+	 * Manufacturer ID is in the returned result.  After that each
+	 * Manufacturer ~could~ encode things completely differently.
+	 * Note, all Flash parts must have 64KB sectors.
+	 */
+	manufacturer = flashid & 0xff;
+	switch (manufacturer) {
+	case 0x20: { /* Micron/Numonix */
+		/* This Density -> Size decoding table is taken from Micron
+		 * Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x14 ... 0x19: /* 1MB - 32MB */
+			size = 1 << density;
+			break;
+		case 0x20: /* 64MB */
+			size = 1 << 26;
+			break;
+		case 0x21: /* 128MB */
+			size = 1 << 27;
+			break;
+		case 0x22: /* 256MB */
+			size = 1 << 28;
+		}
+		break;
+	}
+	case 0x9d: { /* ISSI -- Integrated Silicon Solution, Inc. */
+		/* This Density -> Size decoding table is taken from ISSI
+		 * Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x16: /* 32 MB */
+			size = 1 << 25;
+			break;
+		case 0x17: /* 64MB */
+			size = 1 << 26;
+		}
+		break;
+	}
+	case 0xc2: /* Macronix */
+	case 0xef: /* Winbond */ {
+		/* This Density -> Size decoding table is taken from
+		 * Macronix and Winbond Data Sheets.
+		 */
+		density = (flashid >> 16) & 0xff;
+		switch (density) {
+		case 0x17: /* 8MB */
+		case 0x18: /* 16MB */
+			size = 1 << density;
+		}
+	}
+	}
+
+	/* If we didn't recognize the FLASH part, that's no real issue: the
+	 * Hardware/Software contract says that Hardware will _*ALWAYS*_
+	 * use a FLASH part which is at least 4MB in size and has 64KB
+	 * sectors.  The unrecognized FLASH part is likely to be much larger
+	 * than 4MB, but that's all we really need.
+	 */
+	if (size == 0) {
+		csio_warn(hw, "Unknown Flash Part, ID = %#x, assuming 4MB\n",
+			  flashid);
+		size = 1 << 22;
+	}
+
+	/* Store decoded Flash size */
+	hw->params.sf_size = size;
+	hw->params.sf_nsec = size / SF_SEC_SIZE;
 
+found:
+	if (hw->params.sf_size < FLASH_MIN_SIZE)
+		csio_warn(hw, "WARNING: Flash Part ID %#x, size %#x < %#x\n",
+			  flashid, hw->params.sf_size, FLASH_MIN_SIZE);
 	return 0;
 }
 
-- 
cgit v1.2.3


From a89f4f1e5f56a3e595c1a87f43df68e22fabf479 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 15:58:41 +0100
Subject: scsi: sym53c8xx: remove some redundant variables

Variables scriptb0 and dp_sgmin are being assigned but are never used
hence they are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'scriptb0' set but not used [-Wunused-but-set-variable]
warning: variable 'dp_sgmin' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/sym53c8xx_2/sym_fw.c   | 4 ----
 drivers/scsi/sym53c8xx_2/sym_hipd.c | 3 +--
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/scsi/sym53c8xx_2/sym_fw.c b/drivers/scsi/sym53c8xx_2/sym_fw.c
index 190770bdc194..91db17727963 100644
--- a/drivers/scsi/sym53c8xx_2/sym_fw.c
+++ b/drivers/scsi/sym53c8xx_2/sym_fw.c
@@ -295,10 +295,8 @@ static void
 sym_fw1_setup(struct sym_hcb *np, struct sym_fw *fw)
 {
 	struct sym_fw1a_scr *scripta0;
-	struct sym_fw1b_scr *scriptb0;
 
 	scripta0 = (struct sym_fw1a_scr *) np->scripta0;
-	scriptb0 = (struct sym_fw1b_scr *) np->scriptb0;
 
 	/*
 	 *  Fill variable parts in scripts.
@@ -319,10 +317,8 @@ static void
 sym_fw2_setup(struct sym_hcb *np, struct sym_fw *fw)
 {
 	struct sym_fw2a_scr *scripta0;
-	struct sym_fw2b_scr *scriptb0;
 
 	scripta0 = (struct sym_fw2a_scr *) np->scripta0;
-	scriptb0 = (struct sym_fw2b_scr *) np->scriptb0;
 
 	/*
 	 *  Fill variable parts in scripts.
diff --git a/drivers/scsi/sym53c8xx_2/sym_hipd.c b/drivers/scsi/sym53c8xx_2/sym_hipd.c
index 378af306fda1..bd3f6e2d6834 100644
--- a/drivers/scsi/sym53c8xx_2/sym_hipd.c
+++ b/drivers/scsi/sym53c8xx_2/sym_hipd.c
@@ -3855,7 +3855,7 @@ out_reject:
 
 int sym_compute_residual(struct sym_hcb *np, struct sym_ccb *cp)
 {
-	int dp_sg, dp_sgmin, resid = 0;
+	int dp_sg, resid = 0;
 	int dp_ofs = 0;
 
 	/*
@@ -3902,7 +3902,6 @@ int sym_compute_residual(struct sym_hcb *np, struct sym_ccb *cp)
 	 *  We are now full comfortable in the computation 
 	 *  of the data residual (2's complement).
 	 */
-	dp_sgmin = SYM_CONF_MAX_SG - cp->segments;
 	resid = -cp->ext_ofs;
 	for (dp_sg = cp->ext_sg; dp_sg < SYM_CONF_MAX_SG; ++dp_sg) {
 		u_int tmp = scr_to_cpu(cp->phys.data[dp_sg].size);
-- 
cgit v1.2.3


From 75d6e175fc511e95ae3eb8f708680133bc211ed3 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Thu, 2 Aug 2018 18:23:26 +0800
Subject: blk-mq: fix updating tags depth

The passed 'nr' from userspace represents the total depth, meantime
inside 'struct blk_mq_tags', 'nr_tags' stores the total tag depth,
and 'nr_reserved_tags' stores the reserved part.

There are two issues in blk_mq_tag_update_depth() now:

1) for growing tags, we should have used the passed 'nr', and keep the
number of reserved tags not changed.

2) the passed 'nr' should have been used for checking against
'tags->nr_tags', instead of number of the normal part.

This patch fixes the above two cases, and avoids kernel crash caused
by wrong resizing sbitmap queue.

Cc: "Ewan D. Milne" <emilne@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Bart Van Assche <bart.vanassche@sandisk.com>
Cc: Omar Sandoval <osandov@fb.com>
Tested by: Marco Patalano <mpatalan@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index 09b2ee6694fb..c43b3398d7b4 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -399,8 +399,6 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 	if (tdepth <= tags->nr_reserved_tags)
 		return -EINVAL;
 
-	tdepth -= tags->nr_reserved_tags;
-
 	/*
 	 * If we are allowed to grow beyond the original size, allocate
 	 * a new set of tags before freeing the old one.
@@ -420,7 +418,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 		if (tdepth > 16 * BLKDEV_MAX_RQ)
 			return -EINVAL;
 
-		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth, 0);
+		new = blk_mq_alloc_rq_map(set, hctx->queue_num, tdepth,
+				tags->nr_reserved_tags);
 		if (!new)
 			return -ENOMEM;
 		ret = blk_mq_alloc_rqs(set, new, hctx->queue_num, tdepth);
@@ -437,7 +436,8 @@ int blk_mq_tag_update_depth(struct blk_mq_hw_ctx *hctx,
 		 * Don't need (or can't) update reserved tags here, they
 		 * remain static and should never need resizing.
 		 */
-		sbitmap_queue_resize(&tags->bitmap_tags, tdepth);
+		sbitmap_queue_resize(&tags->bitmap_tags,
+				tdepth - tags->nr_reserved_tags);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 7a8655e19bdb3be43f6a3b4768c9b0928a2585fc Mon Sep 17 00:00:00 2001
From: Amit Daniel Kachhap <amit.kachhap@arm.com>
Date: Tue, 31 Jul 2018 11:25:55 +0530
Subject: clk: scmi: Fix the rounding of clock rate

This fix rounds the clock rate properly by using quotient and not
remainder in the calculation. This issue was found while testing HDMI
in the Juno platform.

Fixes: 6d6a1d82eaef7 ("clk: add support for clocks provided by SCMI")
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-scmi.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/clk/clk-scmi.c b/drivers/clk/clk-scmi.c
index bb2a6f2f5516..a985bf5e1ac6 100644
--- a/drivers/clk/clk-scmi.c
+++ b/drivers/clk/clk-scmi.c
@@ -38,7 +38,6 @@ static unsigned long scmi_clk_recalc_rate(struct clk_hw *hw,
 static long scmi_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 				unsigned long *parent_rate)
 {
-	int step;
 	u64 fmin, fmax, ftmp;
 	struct scmi_clk *clk = to_scmi_clk(hw);
 
@@ -60,9 +59,9 @@ static long scmi_clk_round_rate(struct clk_hw *hw, unsigned long rate,
 
 	ftmp = rate - fmin;
 	ftmp += clk->info->range.step_size - 1; /* to round up */
-	step = do_div(ftmp, clk->info->range.step_size);
+	do_div(ftmp, clk->info->range.step_size);
 
-	return step * clk->info->range.step_size + fmin;
+	return ftmp * clk->info->range.step_size + fmin;
 }
 
 static int scmi_clk_set_rate(struct clk_hw *hw, unsigned long rate,
-- 
cgit v1.2.3


From 67075b3cb8d509642ff09ef3134a3b2d30c45a32 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Mon, 30 Jul 2018 07:49:55 +0000
Subject: clk: cs2000-cp: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk-cs2000-cp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/clk/clk-cs2000-cp.c b/drivers/clk/clk-cs2000-cp.c
index a2f8c42e527a..92bc4aca0f95 100644
--- a/drivers/clk/clk-cs2000-cp.c
+++ b/drivers/clk/clk-cs2000-cp.c
@@ -1,12 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * CS2000  --  CIRRUS LOGIC Fractional-N Clock Synthesizer & Clock Multiplier
  *
  * Copyright (C) 2015 Renesas Electronics Corporation
  * Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 #include <linux/clk-provider.h>
 #include <linux/delay.h>
-- 
cgit v1.2.3


From 4ae5716b4188d20178fdcaa39561fa50f6e6b513 Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <himanshu.madhani@cavium.com>
Date: Thu, 2 Aug 2018 13:16:43 -0700
Subject: scsi: qla2xxx: Cleanup for N2N code

Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 112 ----------------------------------------
 drivers/scsi/qla2xxx/qla_iocb.c |  25 ---------
 2 files changed, 137 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 7b675243bd16..1de78697dc0d 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4686,110 +4686,6 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 	return (rval);
 }
 
-/*
- * N2N Login
- *	Updates Fibre Channel Device Database with local loop devices.
- *
- * Input:
- *	ha = adapter block pointer.
- *
- * Returns:
- */
-static int qla24xx_n2n_handle_login(struct scsi_qla_host *vha,
-				    fc_port_t *fcport)
-{
-	struct qla_hw_data *ha = vha->hw;
-	int	res = QLA_SUCCESS, rval;
-	int	greater_wwpn = 0;
-	int	logged_in = 0;
-
-	if (ha->current_topology != ISP_CFG_N)
-		return res;
-
-	if (wwn_to_u64(vha->port_name) >
-	    wwn_to_u64(vha->n2n_port_name)) {
-		ql_dbg(ql_dbg_disc, vha, 0x2002,
-		    "HBA WWPN is greater %llx > target %llx\n",
-		    wwn_to_u64(vha->port_name),
-		    wwn_to_u64(vha->n2n_port_name));
-		greater_wwpn = 1;
-		fcport->d_id.b24 = vha->n2n_id;
-	}
-
-	fcport->loop_id = vha->loop_id;
-	fcport->fc4f_nvme = 0;
-	fcport->query = 1;
-
-	ql_dbg(ql_dbg_disc, vha, 0x4001,
-	    "Initiate N2N login handler: HBA port_id=%06x loopid=%d\n",
-	    fcport->d_id.b24, vha->loop_id);
-
-	/* Fill in member data. */
-	if (!greater_wwpn) {
-		rval = qla2x00_get_port_database(vha, fcport, 0);
-		ql_dbg(ql_dbg_disc, vha, 0x1051,
-		    "Remote login-state (%x/%x) port_id=%06x loop_id=%x, rval=%d\n",
-		    fcport->current_login_state, fcport->last_login_state,
-		    fcport->d_id.b24, fcport->loop_id, rval);
-
-		if (((fcport->current_login_state & 0xf) == 0x4) ||
-		    ((fcport->current_login_state & 0xf) == 0x6))
-			logged_in = 1;
-	}
-
-	if (logged_in || greater_wwpn) {
-		if (!vha->nvme_local_port && vha->flags.nvme_enabled)
-			qla_nvme_register_hba(vha);
-
-		/* Set connected N_Port d_id */
-		if (vha->flags.nvme_enabled)
-			fcport->fc4f_nvme = 1;
-
-		fcport->scan_state = QLA_FCPORT_FOUND;
-		fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
-		fcport->disc_state = DSC_GNL;
-		fcport->n2n_flag = 1;
-		fcport->flags = 3;
-		vha->hw->flags.gpsc_supported = 0;
-
-		if (greater_wwpn) {
-			ql_dbg(ql_dbg_disc, vha, 0x20e5,
-			    "%s %d PLOGI ELS %8phC\n",
-			    __func__, __LINE__, fcport->port_name);
-
-			res = qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI,
-			    fcport, fcport->d_id);
-		}
-
-		if (res != QLA_SUCCESS) {
-			ql_log(ql_log_info, vha, 0xd04d,
-			    "PLOGI Failed: portid=%06x - retrying\n",
-			    fcport->d_id.b24);
-			res = QLA_SUCCESS;
-		} else {
-			/* State 0x6 means FCP PRLI complete */
-			if ((fcport->current_login_state & 0xf) == 0x6) {
-				ql_dbg(ql_dbg_disc, vha, 0x2118,
-				    "%s %d %8phC post GPDB work\n",
-				    __func__, __LINE__, fcport->port_name);
-				fcport->chip_reset =
-				    vha->hw->base_qpair->chip_reset;
-				qla24xx_post_gpdb_work(vha, fcport, 0);
-			} else {
-				ql_dbg(ql_dbg_disc, vha, 0x2118,
-				    "%s %d %8phC post NVMe PRLI\n",
-				    __func__, __LINE__, fcport->port_name);
-				qla24xx_post_prli_work(vha, fcport);
-			}
-		}
-	} else {
-		/* Wait for next database change */
-		set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags);
-	}
-
-	return res;
-}
-
 /*
  * qla2x00_configure_local_loop
  *	Updates Fibre Channel Device Database with local loop devices.
@@ -4847,14 +4743,6 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 	}
 	new_fcport->flags &= ~FCF_FABRIC_DEVICE;
 
-	/* Inititae N2N login. */
-	if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) {
-		rval = qla24xx_n2n_handle_login(vha, new_fcport);
-		if (rval != QLA_SUCCESS)
-			goto cleanup_allocation;
-		return QLA_SUCCESS;
-	}
-
 	/* Add devices to port list. */
 	id_iter = (char *)ha->gid_list;
 	for (index = 0; index < entries; index++) {
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index a91cca52b5d5..b349e9b94c08 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2567,26 +2567,6 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 	sp->vha->qla_stats.control_requests++;
 }
 
-static void
-qla2x00_els_dcmd2_sp_free(void *data)
-{
-	srb_t *sp = data;
-	struct srb_iocb *elsio = &sp->u.iocb_cmd;
-
-	if (elsio->u.els_plogi.els_plogi_pyld)
-		dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
-		    elsio->u.els_plogi.els_plogi_pyld,
-		    elsio->u.els_plogi.els_plogi_pyld_dma);
-
-	if (elsio->u.els_plogi.els_resp_pyld)
-		dma_free_coherent(&sp->vha->hw->pdev->dev, DMA_POOL_SIZE,
-		    elsio->u.els_plogi.els_resp_pyld,
-		    elsio->u.els_plogi.els_resp_pyld_dma);
-
-	del_timer(&elsio->timer);
-	qla2x00_rel_sp(sp);
-}
-
 static void
 qla2x00_els_dcmd2_iocb_timeout(void *data)
 {
@@ -2648,10 +2628,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 	}
 
 	elsio = &sp->u.iocb_cmd;
-	fcport->d_id.b.domain = remote_did.b.domain;
-	fcport->d_id.b.area = remote_did.b.area;
-	fcport->d_id.b.al_pa = remote_did.b.al_pa;
-
 	ql_dbg(ql_dbg_io, vha, 0x3073,
 	    "Enter: PLOGI portid=%06x\n", fcport->d_id.b24);
 
@@ -2664,7 +2640,6 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 	qla2x00_init_timer(sp, ELS_DCMD_TIMEOUT);
 
 	sp->done = qla2x00_els_dcmd2_sp_done;
-	sp->free = qla2x00_els_dcmd2_sp_free;
 
 	ptr = elsio->u.els_plogi.els_plogi_pyld =
 	    dma_alloc_coherent(&ha->pdev->dev, DMA_POOL_SIZE,
-- 
cgit v1.2.3


From 48acad099074984f6b0b6e4da011856ba25d12ba Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:44 -0700
Subject: scsi: qla2xxx: Fix N2N link re-connect

In case of N2N connect, sg_reset for bus/device/host was causing driver and
firmware state to go out of sync.  This patch fixes this link instablity
when reconnect is attempted after link flap.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h    |   3 +-
 drivers/scsi/qla2xxx/qla_init.c   | 227 +++++++++++++++++++++++++-------------
 drivers/scsi/qla2xxx/qla_iocb.c   |  15 ++-
 drivers/scsi/qla2xxx/qla_isr.c    |   3 +-
 drivers/scsi/qla2xxx/qla_mbx.c    |  27 +----
 drivers/scsi/qla2xxx/qla_os.c     |   5 +
 drivers/scsi/qla2xxx/qla_target.c |   9 ++
 7 files changed, 181 insertions(+), 108 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 9442e18aef6f..ee4d1f4fdf95 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -377,6 +377,7 @@ struct srb_iocb {
 #define SRB_LOGIN_COND_PLOGI	BIT_1
 #define SRB_LOGIN_SKIP_PRLI	BIT_2
 #define SRB_LOGIN_NVME_PRLI	BIT_3
+#define SRB_LOGIN_PRLI_ONLY	BIT_4
 			uint16_t data[2];
 			u32 iop[2];
 		} logio;
@@ -4236,7 +4237,7 @@ typedef struct scsi_qla_host {
 #define FCOE_CTX_RESET_NEEDED	18	/* Initiate FCoE context reset */
 #define MPI_RESET_NEEDED	19	/* Initiate MPI FW reset */
 #define ISP_QUIESCE_NEEDED	20	/* Driver need some quiescence */
-#define FREE_BIT 21
+#define N2N_LINK_RESET		21
 #define PORT_UPDATE_NEEDED	22
 #define FX00_RESET_RECOVERY	23
 #define FX00_TARGET_SCAN	24
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 1de78697dc0d..52e163553e90 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -160,6 +160,22 @@ qla2x00_async_login_sp_done(void *ptr, int res)
 	sp->free(sp);
 }
 
+static inline bool
+fcport_is_smaller(fc_port_t *fcport)
+{
+	if (wwn_to_u64(fcport->port_name) <
+	    wwn_to_u64(fcport->vha->port_name))
+		return true;
+	else
+		return false;
+}
+
+static inline bool
+fcport_is_bigger(fc_port_t *fcport)
+{
+	return !fcport_is_smaller(fcport);
+}
+
 int
 qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
@@ -189,13 +205,18 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
 
 	sp->done = qla2x00_async_login_sp_done;
-	lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI;
+	if (N2N_TOPO(fcport->vha->hw) && fcport_is_bigger(fcport)) {
+		lio->u.logio.flags |= SRB_LOGIN_PRLI_ONLY;
+	} else {
+		lio->u.logio.flags |= SRB_LOGIN_COND_PLOGI;
 
-	if (fcport->fc4f_nvme)
-		lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI;
+		if (fcport->fc4f_nvme)
+			lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI;
+
+		if (data[1] & QLA_LOGIO_LOGIN_RETRIED)
+			lio->u.logio.flags |= SRB_LOGIN_RETRIED;
+	}
 
-	if (data[1] & QLA_LOGIO_LOGIN_RETRIED)
-		lio->u.logio.flags |= SRB_LOGIN_RETRIED;
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
 		fcport->flags |= FCF_LOGIN_NEEDED;
@@ -497,15 +518,18 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 	for (i = 0; i < n; i++) {
 		e = &vha->gnl.l[i];
 		wwn = wwn_to_u64(e->port_name);
+		id.b.domain = e->port_id[2];
+		id.b.area = e->port_id[1];
+		id.b.al_pa = e->port_id[0];
+		id.b.rsvd_1 = 0;
 
 		if (memcmp((u8 *)&wwn, fcport->port_name, WWN_SIZE))
 			continue;
 
+		if (IS_SW_RESV_ADDR(id))
+			continue;
+
 		found = 1;
-		id.b.domain = e->port_id[2];
-		id.b.area = e->port_id[1];
-		id.b.al_pa = e->port_id[0];
-		id.b.rsvd_1 = 0;
 
 		loop_id = le16_to_cpu(e->nport_handle);
 		loop_id = (loop_id & 0x7fff);
@@ -518,14 +542,18 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 		    fcport->d_id.b.domain, fcport->d_id.b.area,
 		    fcport->d_id.b.al_pa, loop_id, fcport->loop_id);
 
-		if ((id.b24 != fcport->d_id.b24) ||
-		    ((fcport->loop_id != FC_NO_LOOP_ID) &&
-			(fcport->loop_id != loop_id))) {
-			ql_dbg(ql_dbg_disc, vha, 0x20e3,
-			    "%s %d %8phC post del sess\n",
-			    __func__, __LINE__, fcport->port_name);
-			qlt_schedule_sess_for_deletion(fcport);
-			return;
+		switch (fcport->disc_state) {
+		case DSC_DELETE_PEND:
+		case DSC_DELETED:
+			break;
+		default:
+			if ((id.b24 != fcport->d_id.b24) ||
+			    ((fcport->loop_id != FC_NO_LOOP_ID) &&
+				(fcport->loop_id != loop_id))) {
+				qlt_schedule_sess_for_deletion(fcport);
+				return;
+			}
+			break;
 		}
 
 		fcport->loop_id = loop_id;
@@ -544,66 +572,122 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 			fcport->login_pause = 1;
 		}
 
-		if  (fcport->fc4f_nvme)
+		if (fcport->fc4f_nvme)
 			current_login_state = e->current_login_state >> 4;
 		else
 			current_login_state = e->current_login_state & 0xf;
 
-		switch (current_login_state) {
-		case DSC_LS_PRLI_COMP:
-			ql_dbg(ql_dbg_disc, vha, 0x20e4,
-			    "%s %d %8phC post gpdb\n",
-			    __func__, __LINE__, fcport->port_name);
+		switch (vha->hw->current_topology) {
+		default:
+			switch (current_login_state) {
+			case DSC_LS_PRLI_COMP:
+				ql_dbg(ql_dbg_disc + ql_dbg_verbose,
+				    vha, 0x20e4, "%s %d %8phC post gpdb\n",
+				    __func__, __LINE__, fcport->port_name);
 
-			if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
-				fcport->port_type = FCT_INITIATOR;
-			else
-				fcport->port_type = FCT_TARGET;
+				if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
+					fcport->port_type = FCT_INITIATOR;
+				else
+					fcport->port_type = FCT_TARGET;
+				data[0] = data[1] = 0;
+				qla2x00_post_async_adisc_work(vha, fcport,
+				    data);
+				break;
+			case DSC_LS_PORT_UNAVAIL:
+			default:
+				if (fcport->loop_id != FC_NO_LOOP_ID)
+					qla2x00_clear_loop_id(fcport);
 
-			data[0] = data[1] = 0;
-			qla2x00_post_async_adisc_work(vha, fcport, data);
-			break;
-		case DSC_LS_PORT_UNAVAIL:
-		default:
-			if (fcport->loop_id == FC_NO_LOOP_ID) {
-				qla2x00_find_new_loop_id(vha, fcport);
+				fcport->loop_id = loop_id;
 				fcport->fw_login_state = DSC_LS_PORT_UNAVAIL;
+				qla24xx_fcport_handle_login(vha, fcport);
+				break;
 			}
-			ql_dbg(ql_dbg_disc, vha, 0x20e5,
-			    "%s %d %8phC\n",
-			    __func__, __LINE__, fcport->port_name);
-			qla24xx_fcport_handle_login(vha, fcport);
 			break;
-		}
+		case ISP_CFG_N:
+			switch (current_login_state) {
+			case DSC_LS_PRLI_COMP:
+				if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
+					fcport->port_type = FCT_INITIATOR;
+				else
+					fcport->port_type = FCT_TARGET;
+
+				data[0] = data[1] = 0;
+				qla2x00_post_async_adisc_work(vha, fcport,
+				    data);
+				break;
+			case DSC_LS_PLOGI_COMP:
+				if (fcport_is_bigger(fcport)) {
+					/* local adapter is smaller */
+					if (fcport->loop_id != FC_NO_LOOP_ID)
+						qla2x00_clear_loop_id(fcport);
+
+					fcport->loop_id = loop_id;
+					qla24xx_fcport_handle_login(vha,
+					    fcport);
+					break;
+				}
+				/* drop through */
+			default:
+				if (fcport_is_smaller(fcport)) {
+					/* local adapter is bigger */
+					if (fcport->loop_id != FC_NO_LOOP_ID)
+						qla2x00_clear_loop_id(fcport);
+
+					fcport->loop_id = loop_id;
+					qla24xx_fcport_handle_login(vha,
+					    fcport);
+				}
+				break;
+			}
+			break;
+		} /* switch (ha->current_topology) */
 	}
 
 	if (!found) {
-		/* fw has no record of this port */
-		for (i = 0; i < n; i++) {
-			e = &vha->gnl.l[i];
-			id.b.domain = e->port_id[0];
-			id.b.area = e->port_id[1];
-			id.b.al_pa = e->port_id[2];
-			id.b.rsvd_1 = 0;
-			loop_id = le16_to_cpu(e->nport_handle);
-
-			if (fcport->d_id.b24 == id.b24) {
-				conflict_fcport =
-					qla2x00_find_fcport_by_wwpn(vha,
-					    e->port_name, 0);
-				ql_dbg(ql_dbg_disc, vha, 0x20e6,
-				    "%s %d %8phC post del sess\n",
-				    __func__, __LINE__,
-				    conflict_fcport->port_name);
-				qlt_schedule_sess_for_deletion
-					(conflict_fcport);
+		switch (vha->hw->current_topology) {
+		case ISP_CFG_F:
+		case ISP_CFG_FL:
+			for (i = 0; i < n; i++) {
+				e = &vha->gnl.l[i];
+				id.b.domain = e->port_id[0];
+				id.b.area = e->port_id[1];
+				id.b.al_pa = e->port_id[2];
+				id.b.rsvd_1 = 0;
+				loop_id = le16_to_cpu(e->nport_handle);
+
+				if (fcport->d_id.b24 == id.b24) {
+					conflict_fcport =
+					    qla2x00_find_fcport_by_wwpn(vha,
+						e->port_name, 0);
+					ql_dbg(ql_dbg_disc + ql_dbg_verbose,
+					    vha, 0x20e5,
+					    "%s %d %8phC post del sess\n",
+					    __func__, __LINE__,
+					    conflict_fcport->port_name);
+					qlt_schedule_sess_for_deletion
+						(conflict_fcport);
+				}
+				/*
+				 * FW already picked this loop id for
+				 * another fcport
+				 */
+				if (fcport->loop_id == loop_id)
+					fcport->loop_id = FC_NO_LOOP_ID;
 			}
-
-			/* FW already picked this loop id for another fcport */
-			if (fcport->loop_id == loop_id)
-				fcport->loop_id = FC_NO_LOOP_ID;
+			qla24xx_fcport_handle_login(vha, fcport);
+			break;
+		case ISP_CFG_N:
+			/*
+			 * FW handles the initial login for n2n.
+			 * Do link reinit to trigger this auto login.
+			 */
+			set_bit(N2N_LINK_RESET, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+			break;
+		default:
+			break;
 		}
-		qla24xx_fcport_handle_login(vha, fcport);
 	}
 } /* gnl_event */
 
@@ -4590,20 +4674,10 @@ qla2x00_configure_loop(scsi_qla_host_t *vha)
 
 	} else if (ha->current_topology == ISP_CFG_N) {
 		clear_bit(RSCN_UPDATE, &flags);
-		if (ha->flags.rida_fmt2) {
-			/* With Rida Format 2, the login is already triggered.
-			 * We know who is on the other side of the wire.
-			 * No need to login to do login to find out or drop into
-			 * qla2x00_configure_local_loop().
-			 */
+		if (qla_tgt_mode_enabled(vha)) {
+			/* allow the other side to start the login */
 			clear_bit(LOCAL_LOOP_UPDATE, &flags);
 			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		} else {
-			if (qla_tgt_mode_enabled(vha)) {
-				/* allow the other side to start the login */
-				clear_bit(LOCAL_LOOP_UPDATE, &flags);
-				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-			}
 		}
 	} else if (ha->current_topology == ISP_CFG_NL) {
 		clear_bit(RSCN_UPDATE, &flags);
@@ -7929,8 +8003,7 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 	}
 
 	 /* enable RIDA Format2 */
-	if (qla_tgt_mode_enabled(vha) || qla_dual_mode_enabled(vha))
-		icb->firmware_options_3 |= BIT_0;
+	icb->firmware_options_3 |= BIT_0;
 
 	if (IS_QLA27XX(ha)) {
 		icb->firmware_options_3 |= BIT_8;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index b349e9b94c08..e1ff2e27e59f 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2240,12 +2240,15 @@ qla24xx_login_iocb(srb_t *sp, struct logio_entry_24xx *logio)
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
-	logio->control_flags = cpu_to_le16(LCF_COMMAND_PLOGI);
-
-	if (lio->u.logio.flags & SRB_LOGIN_COND_PLOGI)
-		logio->control_flags |= cpu_to_le16(LCF_COND_PLOGI);
-	if (lio->u.logio.flags & SRB_LOGIN_SKIP_PRLI)
-		logio->control_flags |= cpu_to_le16(LCF_SKIP_PRLI);
+	if (lio->u.logio.flags & SRB_LOGIN_PRLI_ONLY) {
+		logio->control_flags = cpu_to_le16(LCF_COMMAND_PRLI);
+	} else {
+		logio->control_flags = cpu_to_le16(LCF_COMMAND_PLOGI);
+		if (lio->u.logio.flags & SRB_LOGIN_COND_PLOGI)
+			logio->control_flags |= cpu_to_le16(LCF_COND_PLOGI);
+		if (lio->u.logio.flags & SRB_LOGIN_SKIP_PRLI)
+			logio->control_flags |= cpu_to_le16(LCF_SKIP_PRLI);
+	}
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
diff --git a/drivers/scsi/qla2xxx/qla_isr.c b/drivers/scsi/qla2xxx/qla_isr.c
index 9fa5a2557f2c..e90fb17d2121 100644
--- a/drivers/scsi/qla2xxx/qla_isr.c
+++ b/drivers/scsi/qla2xxx/qla_isr.c
@@ -908,7 +908,8 @@ skip_rio:
 			if (!atomic_read(&vha->loop_down_timer))
 				atomic_set(&vha->loop_down_timer,
 				    LOOP_DOWN_TIME);
-			qla2x00_mark_all_devices_lost(vha, 1);
+			if (!N2N_TOPO(ha))
+				qla2x00_mark_all_devices_lost(vha, 1);
 		}
 
 		if (vha->vp_idx) {
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 7e875f575229..4e42ce057a37 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -2177,7 +2177,10 @@ qla2x00_lip_reset(scsi_qla_host_t *vha)
 		mcp->out_mb = MBX_2|MBX_1|MBX_0;
 	} else if (IS_FWI2_CAPABLE(vha->hw)) {
 		mcp->mb[0] = MBC_LIP_FULL_LOGIN;
-		mcp->mb[1] = BIT_6;
+		if (N2N_TOPO(vha->hw))
+			mcp->mb[1] = BIT_4; /* re-init */
+		else
+			mcp->mb[1] = BIT_6; /* LIP */
 		mcp->mb[2] = 0;
 		mcp->mb[3] = vha->hw->loop_reset_delay;
 		mcp->out_mb = MBX_3|MBX_2|MBX_1|MBX_0;
@@ -3911,28 +3914,6 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		if (fcport) {
 			fcport->plogi_nack_done_deadline = jiffies + HZ;
 			fcport->scan_state = QLA_FCPORT_FOUND;
-			switch (fcport->disc_state) {
-			case DSC_DELETED:
-				ql_dbg(ql_dbg_disc, vha, 0x210d,
-				    "%s %d %8phC login\n",
-				    __func__, __LINE__, fcport->port_name);
-				qla24xx_fcport_handle_login(vha, fcport);
-				break;
-			case DSC_DELETE_PEND:
-				break;
-			default:
-				qlt_schedule_sess_for_deletion(fcport);
-				break;
-			}
-		} else {
-			id.b.al_pa  = rptid_entry->u.f2.remote_nport_id[0];
-			id.b.area   = rptid_entry->u.f2.remote_nport_id[1];
-			id.b.domain = rptid_entry->u.f2.remote_nport_id[2];
-			qla24xx_post_newsess_work(vha, &id,
-			    rptid_entry->u.f2.port_name,
-			    rptid_entry->u.f2.node_name,
-			    NULL,
-			    FC4_TYPE_UNKNOWN);
 		}
 	}
 }
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index e881fce7477a..eb804e2feedf 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -6186,6 +6186,11 @@ intr_on_check:
 		if (!IS_QLAFX00(ha))
 			qla2x00_do_dpc_all_vps(base_vha);
 
+		if (test_and_clear_bit(N2N_LINK_RESET,
+			&base_vha->dpc_flags)) {
+			qla2x00_lip_reset(base_vha);
+		}
+
 		ha->dpc_active = 0;
 end_loop:
 		set_current_state(TASK_INTERRUPTIBLE);
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 3de11153d1d3..9d10989ed027 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -805,6 +805,10 @@ qlt_plogi_ack_find_add(struct scsi_qla_host *vha, port_id_t *id,
 
 	list_for_each_entry(pla, &vha->plogi_ack_list, list) {
 		if (pla->id.b24 == id->b24) {
+			ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x210d,
+			    "%s %d %8phC Term INOT due to new INOT",
+			    __func__, __LINE__,
+			    pla->iocb.u.isp24.port_name);
 			qlt_send_term_imm_notif(vha, &pla->iocb, 1);
 			memcpy(&pla->iocb, iocb, sizeof(pla->iocb));
 			return pla;
@@ -1073,6 +1077,7 @@ void qlt_free_session_done(struct work_struct *work)
 		struct qlt_plogi_ack_t *con =
 		    sess->plogi_link[QLT_PLOGI_LINK_CONFLICT];
 		struct imm_ntfy_from_isp *iocb;
+		own = sess->plogi_link[QLT_PLOGI_LINK_SAME_WWN];
 
 		if (con) {
 			iocb = &con->iocb;
@@ -4716,6 +4721,10 @@ static int qlt_handle_login(struct scsi_qla_host *vha,
 
 	pla = qlt_plogi_ack_find_add(vha, &port_id, iocb);
 	if (!pla) {
+		ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
+		    "%s %d %8phC Term INOT due to mem alloc fail",
+		    __func__, __LINE__,
+		    iocb->u.isp24.port_name);
 		qlt_send_term_imm_notif(vha, iocb, 1);
 		goto out;
 	}
-- 
cgit v1.2.3


From 23dd98a6555897f65306c6937b428c8742fef610 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:45 -0700
Subject: scsi: qla2xxx: Fix login retry count

Login retry count was not properly decrementing which lead to endless
retry.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_gs.c     | 16 +++++++
 drivers/scsi/qla2xxx/qla_init.c   | 23 +++-------
 drivers/scsi/qla2xxx/qla_mbx.c    |  1 +
 drivers/scsi/qla2xxx/qla_os.c     | 90 ++++++++++++++++++++-------------------
 drivers/scsi/qla2xxx/qla_target.c |  3 +-
 5 files changed, 70 insertions(+), 63 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 4bc2b66b299f..5139a3577bb3 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -3475,6 +3475,14 @@ void qla24xx_handle_gpnid_event(scsi_qla_host_t *vha, struct event_arg *ea)
 			fcport->rscn_gen++;
 			fcport->scan_state = QLA_FCPORT_FOUND;
 			fcport->flags |= FCF_FABRIC_DEVICE;
+			if (fcport->login_retry == 0) {
+				fcport->login_retry =
+					vha->hw->login_retry_count;
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "Port login retry %8phN, lid 0x%04x cnt=%d.\n",
+				    fcport->port_name, fcport->loop_id,
+				    fcport->login_retry);
+			}
 			switch (fcport->disc_state) {
 			case DSC_LOGIN_COMPLETE:
 				/* recheck session is still intact. */
@@ -3967,6 +3975,14 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
 		} else {
 			if (fcport->rscn_rcvd ||
 			    fcport->disc_state != DSC_LOGIN_COMPLETE) {
+				if (fcport->login_retry == 0) {
+					fcport->login_retry =
+						vha->hw->login_retry_count;
+					ql_dbg(ql_dbg_disc, vha, 0x20a3,
+					    "Port login retry %8phN, lid 0x%04x retry cnt=%d.\n",
+					    fcport->port_name, fcport->loop_id,
+					    fcport->login_retry);
+				}
 				fcport->rscn_rcvd = 0;
 				qla24xx_fcport_handle_login(vha, fcport);
 			}
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 52e163553e90..aea264100673 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -213,8 +213,6 @@ qla2x00_async_login(struct scsi_qla_host *vha, fc_port_t *fcport,
 		if (fcport->fc4f_nvme)
 			lio->u.logio.flags |= SRB_LOGIN_SKIP_PRLI;
 
-		if (data[1] & QLA_LOGIO_LOGIN_RETRIED)
-			lio->u.logio.flags |= SRB_LOGIN_RETRIED;
 	}
 
 	rval = qla2x00_start_sp(sp);
@@ -485,7 +483,6 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 
 	if (ea->rc) { /* rval */
 		if (fcport->login_retry == 0) {
-			fcport->login_retry = vha->hw->login_retry_count;
 			ql_dbg(ql_dbg_disc, vha, 0x20de,
 			    "GNL failed Port login retry %8phN, retry cnt=%d.\n",
 			    fcport->port_name, fcport->login_retry);
@@ -1256,11 +1253,10 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 		return 0;
 	}
 
-	if (fcport->login_retry > 0)
-		fcport->login_retry--;
 
 	switch (fcport->disc_state) {
 	case DSC_DELETED:
+		fcport->login_retry--;
 		wwn = wwn_to_u64(fcport->node_name);
 		if (wwn == 0) {
 			ql_dbg(ql_dbg_disc, vha, 0xffff,
@@ -1273,6 +1269,7 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 			    __func__, __LINE__, fcport->port_name);
 			qla24xx_post_gnl_work(vha, fcport);
 		} else {
+			fcport->login_retry--;
 			qla_chk_n2n_b4_login(vha, fcport);
 		}
 		break;
@@ -1289,6 +1286,7 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 		break;
 
 	case DSC_LOGIN_FAILED:
+		fcport->login_retry--;
 		ql_dbg(ql_dbg_disc, vha, 0x20d0,
 		    "%s %d %8phC post gidpn\n",
 		    __func__, __LINE__, fcport->port_name);
@@ -1303,6 +1301,7 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 		ql_dbg(ql_dbg_disc, vha, 0x20d1,
 		    "%s %d %8phC post adisc\n",
 		    __func__, __LINE__, fcport->port_name);
+		fcport->login_retry--;
 		data[0] = data[1] = 0;
 		qla2x00_post_async_adisc_work(vha, fcport, data);
 		break;
@@ -1386,17 +1385,6 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
 		}
 	}
 
-	if (fcport->flags & FCF_ASYNC_SENT) {
-		fcport->login_retry++;
-		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-		return;
-	}
-
-	if (fcport->disc_state == DSC_DELETE_PEND) {
-		fcport->login_retry++;
-		return;
-	}
-
 	if (fcport->last_rscn_gen != fcport->rscn_gen) {
 		ql_dbg(ql_dbg_disc, vha, 0x20e9, "%s %d %8phC post gidpn\n",
 		    __func__, __LINE__, fcport->port_name);
@@ -1882,7 +1870,6 @@ void
 qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
-	qla2x00_mark_device_lost(vha, fcport, 1, 0);
 	qlt_logo_completion_handler(fcport, data[0]);
 	fcport->login_gen++;
 	fcport->flags &= ~FCF_ASYNC_ACTIVE;
@@ -5076,11 +5063,11 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	if (IS_QLAFX00(vha->hw)) {
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	} else {
-		fcport->login_retry = 0;
 		fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
 		fcport->disc_state = DSC_LOGIN_COMPLETE;
 		fcport->deleted = 0;
 		fcport->logout_on_delete = 1;
+		fcport->login_retry = vha->hw->login_retry_count;
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	}
 
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 4e42ce057a37..17537f0b3b54 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -3912,6 +3912,7 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		    rptid_entry->u.f2.port_name, 1);
 
 		if (fcport) {
+			fcport->login_retry = vha->hw->login_retry_count;
 			fcport->plogi_nack_done_deadline = jiffies + HZ;
 			fcport->scan_state = QLA_FCPORT_FOUND;
 		}
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index eb804e2feedf..e218d68de532 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3838,14 +3838,6 @@ void qla2x00_mark_device_lost(scsi_qla_host_t *vha, fc_port_t *fcport,
 		return;
 
 	set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-
-	if (fcport->login_retry == 0) {
-		fcport->login_retry = vha->hw->login_retry_count;
-
-		ql_dbg(ql_dbg_disc, vha, 0x20a3,
-		    "Port login retry %8phN, lid 0x%04x retry cnt=%d.\n",
-		    fcport->port_name, fcport->loop_id, fcport->login_retry);
-	}
 }
 
 /*
@@ -5098,7 +5090,7 @@ int qla24xx_post_relogin_work(struct scsi_qla_host *vha)
 void qla2x00_relogin(struct scsi_qla_host *vha)
 {
 	fc_port_t       *fcport;
-	int status;
+	int status, relogin_needed = 0;
 	struct event_arg ea;
 
 	list_for_each_entry(fcport, &vha->vp_fcports, list) {
@@ -5107,47 +5099,59 @@ void qla2x00_relogin(struct scsi_qla_host *vha)
 		 * to it if we haven't run out of retries.
 		 */
 		if (atomic_read(&fcport->state) != FCS_ONLINE &&
-		    fcport->login_retry &&
-		    !(fcport->flags & (FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE))) {
-			if (vha->hw->current_topology != ISP_CFG_NL) {
-				ql_dbg(ql_dbg_disc, fcport->vha, 0x2108,
-				    "%s %8phC DS %d LS %d\n", __func__,
-				    fcport->port_name, fcport->disc_state,
-				    fcport->fw_login_state);
-				memset(&ea, 0, sizeof(ea));
-				ea.event = FCME_RELOGIN;
-				ea.fcport = fcport;
-				qla2x00_fcport_event_handler(vha, &ea);
-			} else if (vha->hw->current_topology == ISP_CFG_NL) {
-				fcport->login_retry--;
-				status = qla2x00_local_device_login(vha,
-								fcport);
-				if (status == QLA_SUCCESS) {
-					fcport->old_loop_id = fcport->loop_id;
-					ql_dbg(ql_dbg_disc, vha, 0x2003,
-					    "Port login OK: logged in ID 0x%x.\n",
-					    fcport->loop_id);
-					qla2x00_update_fcport(vha, fcport);
-				} else if (status == 1) {
-					set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
-					/* retry the login again */
-					ql_dbg(ql_dbg_disc, vha, 0x2007,
-					    "Retrying %d login again loop_id 0x%x.\n",
-					    fcport->login_retry,
-					    fcport->loop_id);
-				} else {
-					fcport->login_retry = 0;
-				}
+		    fcport->login_retry) {
+			if (fcport->scan_state != QLA_FCPORT_FOUND ||
+			    fcport->disc_state == DSC_LOGIN_COMPLETE)
+				continue;
 
-				if (fcport->login_retry == 0 &&
-				    status != QLA_SUCCESS)
-					qla2x00_clear_loop_id(fcport);
+			if (fcport->flags & (FCF_ASYNC_SENT|FCF_ASYNC_ACTIVE) ||
+				fcport->disc_state == DSC_DELETE_PEND) {
+				relogin_needed = 1;
+			} else {
+				if (vha->hw->current_topology != ISP_CFG_NL) {
+					memset(&ea, 0, sizeof(ea));
+					ea.event = FCME_RELOGIN;
+					ea.fcport = fcport;
+					qla2x00_fcport_event_handler(vha, &ea);
+				} else if (vha->hw->current_topology ==
+				    ISP_CFG_NL) {
+					fcport->login_retry--;
+					status =
+					    qla2x00_local_device_login(vha,
+						fcport);
+					if (status == QLA_SUCCESS) {
+						fcport->old_loop_id =
+						    fcport->loop_id;
+						ql_dbg(ql_dbg_disc, vha, 0x2003,
+						    "Port login OK: logged in ID 0x%x.\n",
+						    fcport->loop_id);
+						qla2x00_update_fcport
+							(vha, fcport);
+					} else if (status == 1) {
+						set_bit(RELOGIN_NEEDED,
+						    &vha->dpc_flags);
+						/* retry the login again */
+						ql_dbg(ql_dbg_disc, vha, 0x2007,
+						    "Retrying %d login again loop_id 0x%x.\n",
+						    fcport->login_retry,
+						    fcport->loop_id);
+					} else {
+						fcport->login_retry = 0;
+					}
+
+					if (fcport->login_retry == 0 &&
+					    status != QLA_SUCCESS)
+						qla2x00_clear_loop_id(fcport);
+				}
 			}
 		}
 		if (test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
 			break;
 	}
 
+	if (relogin_needed)
+		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+
 	ql_dbg(ql_dbg_disc, vha, 0x400e,
 	    "Relogin end.\n");
 }
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 9d10989ed027..4f9c315813df 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -1057,7 +1057,6 @@ void qlt_free_session_done(struct work_struct *work)
 	sess->disc_state = DSC_DELETED;
 	sess->fw_login_state = DSC_LS_PORT_UNAVAIL;
 	sess->deleted = QLA_SESS_DELETED;
-	sess->login_retry = vha->hw->login_retry_count;
 
 	if (sess->login_succ && !IS_SW_RESV_ADDR(sess->d_id)) {
 		vha->fcport_count--;
@@ -1161,7 +1160,7 @@ void qlt_unreg_sess(struct fc_port *sess)
 	if (sess->se_sess)
 		vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
-	qla2x00_mark_device_lost(vha, sess, 1, 1);
+	qla2x00_mark_device_lost(vha, sess, 0, 0);
 
 	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 	sess->disc_state = DSC_DELETE_PEND;
-- 
cgit v1.2.3


From 7e84766c9bceb4fc687f483a4cc2bff06f89a563 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:46 -0700
Subject: scsi: qla2xxx: Add longer window for chip reset

qla2x00_reset_active only covers the window of turning the chip off. Add
check to cover turning chip on.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_dbg.c  | 3 +++
 drivers/scsi/qla2xxx/qla_tmpl.c | 4 +++-
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 5fd44c50bbac..c7533fa7f46e 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -1130,6 +1130,7 @@ qla24xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 		    ha->fw_dump);
 		goto qla24xx_fw_dump_failed;
 	}
+	QLA_FW_STOPPED(ha);
 	fw = &ha->fw_dump->isp.isp24;
 	qla2xxx_prep_dump(ha, ha->fw_dump);
 
@@ -1384,6 +1385,7 @@ qla25xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 		    ha->fw_dump);
 		goto qla25xx_fw_dump_failed;
 	}
+	QLA_FW_STOPPED(ha);
 	fw = &ha->fw_dump->isp.isp25;
 	qla2xxx_prep_dump(ha, ha->fw_dump);
 	ha->fw_dump->version = htonl(2);
@@ -2036,6 +2038,7 @@ qla83xx_fw_dump(scsi_qla_host_t *vha, int hardware_locked)
 		    "request...\n", ha->fw_dump);
 		goto qla83xx_fw_dump_failed;
 	}
+	QLA_FW_STOPPED(ha);
 	fw = &ha->fw_dump->isp.isp83;
 	qla2xxx_prep_dump(ha, ha->fw_dump);
 
diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index 731ca0d8520a..b170eb54aab5 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -1028,8 +1028,10 @@ qla27xx_fwdump(scsi_qla_host_t *vha, int hardware_locked)
 		ql_log(ql_log_warn, vha, 0xd300,
 		    "Firmware has been previously dumped (%p),"
 		    " -- ignoring request\n", vha->hw->fw_dump);
-	else
+	else {
+		QLA_FW_STOPPED(vha->hw);
 		qla27xx_execute_fwdt_template(vha);
+	}
 
 #ifndef __CHECKER__
 	if (!hardware_locked)
-- 
cgit v1.2.3


From 22ebde16f141a5602a5e7c090aac7d50eb05f475 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:47 -0700
Subject: scsi: qla2xxx: Prevent sysfs access when chip is down

Prevent user from sending commands through sysfs while firmware is not
running or reset is in progress.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_attr.c   | 33 +++++++++++++++++++++++++++------
 drivers/scsi/qla2xxx/qla_init.c   |  2 +-
 drivers/scsi/qla2xxx/qla_inline.h |  6 ++++++
 3 files changed, 34 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 89a4999fa631..cc04caf83bd3 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -518,6 +518,9 @@ qla2x00_sysfs_write_vpd(struct file *filp, struct kobject *kobj,
 	if (unlikely(pci_channel_offline(ha->pdev)))
 		return 0;
 
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	if (!capable(CAP_SYS_ADMIN) || off != 0 || count != ha->vpd_size ||
 	    !ha->isp_ops->write_nvram)
 		return 0;
@@ -570,7 +573,7 @@ qla2x00_sysfs_read_sfp(struct file *filp, struct kobject *kobj,
 	if (!capable(CAP_SYS_ADMIN) || off != 0 || count < SFP_DEV_SIZE)
 		return 0;
 
-	if (qla2x00_reset_active(vha))
+	if (qla2x00_chip_is_down(vha))
 		return 0;
 
 	rval = qla2x00_read_sfp_dev(vha, buf, count);
@@ -733,6 +736,15 @@ qla2x00_issue_logo(struct file *filp, struct kobject *kobj,
 	int type;
 	port_id_t did;
 
+	if (!capable(CAP_SYS_ADMIN))
+		return 0;
+
+	if (unlikely(pci_channel_offline(vha->hw->pdev)))
+		return 0;
+
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	type = simple_strtol(buf, NULL, 10);
 
 	did.b.domain = (type & 0x00ff0000) >> 16;
@@ -771,6 +783,12 @@ qla2x00_sysfs_read_xgmac_stats(struct file *filp, struct kobject *kobj,
 	if (!capable(CAP_SYS_ADMIN) || off != 0 || count > XGMAC_DATA_SIZE)
 		return 0;
 
+	if (unlikely(pci_channel_offline(ha->pdev)))
+		return 0;
+
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	if (ha->xgmac_data)
 		goto do_read;
 
@@ -825,6 +843,9 @@ qla2x00_sysfs_read_dcbx_tlv(struct file *filp, struct kobject *kobj,
 	if (ha->dcbx_tlv)
 		goto do_read;
 
+	if (qla2x00_chip_is_down(vha))
+		return 0;
+
 	ha->dcbx_tlv = dma_alloc_coherent(&ha->pdev->dev, DCBX_TLV_DATA_SIZE,
 	    &ha->dcbx_tlv_dma, GFP_KERNEL);
 	if (!ha->dcbx_tlv) {
@@ -1036,7 +1057,7 @@ qla2x00_link_state_show(struct device *dev, struct device_attribute *attr,
 	    vha->device_flags & DFLG_NO_CABLE)
 		len = scnprintf(buf, PAGE_SIZE, "Link Down\n");
 	else if (atomic_read(&vha->loop_state) != LOOP_READY ||
-	    qla2x00_reset_active(vha))
+	    qla2x00_chip_is_down(vha))
 		len = scnprintf(buf, PAGE_SIZE, "Unknown Link State\n");
 	else {
 		len = scnprintf(buf, PAGE_SIZE, "Link Up - ");
@@ -1163,7 +1184,7 @@ qla2x00_beacon_store(struct device *dev, struct device_attribute *attr,
 	if (IS_QLA2100(ha) || IS_QLA2200(ha))
 		return -EPERM;
 
-	if (test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags)) {
+	if (qla2x00_chip_is_down(vha)) {
 		ql_log(ql_log_warn, vha, 0x707a,
 		    "Abort ISP active -- ignoring beacon request.\n");
 		return -EBUSY;
@@ -1350,7 +1371,7 @@ qla2x00_thermal_temp_show(struct device *dev,
 	scsi_qla_host_t *vha = shost_priv(class_to_shost(dev));
 	uint16_t temp = 0;
 
-	if (qla2x00_reset_active(vha)) {
+	if (qla2x00_chip_is_down(vha)) {
 		ql_log(ql_log_warn, vha, 0x70dc, "ISP reset active.\n");
 		goto done;
 	}
@@ -1381,7 +1402,7 @@ qla2x00_fw_state_show(struct device *dev, struct device_attribute *attr,
 		return scnprintf(buf, PAGE_SIZE, "0x%x\n", pstate);
 	}
 
-	if (qla2x00_reset_active(vha))
+	if (qla2x00_chip_is_down(vha))
 		ql_log(ql_log_warn, vha, 0x707c,
 		    "ISP reset active.\n");
 	else if (!vha->hw->flags.eeh_busy)
@@ -1840,7 +1861,7 @@ qla2x00_get_fc_host_stats(struct Scsi_Host *shost)
 	if (unlikely(pci_channel_offline(ha->pdev)))
 		goto done;
 
-	if (qla2x00_reset_active(vha))
+	if (qla2x00_chip_is_down(vha))
 		goto done;
 
 	stats = dma_zalloc_coherent(&ha->pdev->dev, sizeof(*stats),
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index aea264100673..740403510779 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -7017,7 +7017,7 @@ check_valid_image:
 			ha->active_image = QLA27XX_SECONDARY_IMAGE;
 	}
 
-	ql_dbg(ql_dbg_init, vha, 0x018f, "%s image\n",
+	ql_dbg(ql_dbg_init + ql_dbg_verbose, vha, 0x018f, "%s image\n",
 	    ha->active_image == 0 ? "default bootld and fw" :
 	    ha->active_image == 1 ? "primary" :
 	    ha->active_image == 2 ? "secondary" :
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index bcbdf28bd7b9..acf6511e8ef7 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -202,6 +202,12 @@ qla2x00_reset_active(scsi_qla_host_t *vha)
 	    test_bit(ABORT_ISP_ACTIVE, &vha->dpc_flags);
 }
 
+static inline int
+qla2x00_chip_is_down(scsi_qla_host_t *vha)
+{
+	return (qla2x00_reset_active(vha) || !vha->hw->flags.fw_started);
+}
+
 static inline srb_t *
 qla2xxx_get_qpair_sp(struct qla_qpair *qpair, fc_port_t *fcport, gfp_t flag)
 {
-- 
cgit v1.2.3


From 3f915271b12e11183c606bed1c3dfff0983662d3 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:48 -0700
Subject: scsi: qla2xxx: Silent erroneous message

Driver uses shadow pointer instead of Mirror pointer for firmware dump
collection. Skip those entries for Mirror pointers for Request/Response
queue from firmware dump template reading.

Following messages are printed in log messages:

 qla27xx_fwdt_entry_t268: unknown buffer 4
 qla27xx_fwdt_entry_t268: unknown buffer 5

This patch fixes these error messages by adding skip_entry() to not read
them from template.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_tmpl.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/scsi/qla2xxx/qla_tmpl.c b/drivers/scsi/qla2xxx/qla_tmpl.c
index b170eb54aab5..0ccd06f11f12 100644
--- a/drivers/scsi/qla2xxx/qla_tmpl.c
+++ b/drivers/scsi/qla2xxx/qla_tmpl.c
@@ -571,6 +571,15 @@ qla27xx_fwdt_entry_t268(struct scsi_qla_host *vha,
 		}
 		break;
 
+	case T268_BUF_TYPE_REQ_MIRROR:
+	case T268_BUF_TYPE_RSP_MIRROR:
+		/*
+		 * Mirror pointers are not implemented in the
+		 * driver, instead shadow pointers are used by
+		 * the drier. Skip these entries.
+		 */
+		qla27xx_skip_entry(ent, buf);
+		break;
 	default:
 		ql_dbg(ql_dbg_async, vha, 0xd02b,
 		    "%s: unknown buffer %x\n", __func__, ent->t268.buf_type);
-- 
cgit v1.2.3


From b63d8b895a1038e5ff762e19b46e9fe9fa3a19a2 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:49 -0700
Subject: scsi: qla2xxx: Fix redundant fc_rport registration

Prevent multiple registrations with transport layer for the same remote
port.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 740403510779..df55fd4e1716 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -5002,6 +5002,9 @@ qla2x00_reg_remote_port(scsi_qla_host_t *vha, fc_port_t *fcport)
 	struct fc_rport *rport;
 	unsigned long flags;
 
+	if (atomic_read(&fcport->state) == FCS_ONLINE)
+		return;
+
 	rport_ids.node_name = wwn_to_u64(fcport->node_name);
 	rport_ids.port_name = wwn_to_u64(fcport->port_name);
 	rport_ids.port_id = fcport->d_id.b.domain << 16 |
@@ -5057,25 +5060,18 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	if (IS_SW_RESV_ADDR(fcport->d_id))
 		return;
 
-	ql_dbg(ql_dbg_disc, vha, 0x20ef, "%s %8phC\n",
-	    __func__, fcport->port_name);
-
-	if (IS_QLAFX00(vha->hw)) {
-		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-	} else {
-		fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
-		fcport->disc_state = DSC_LOGIN_COMPLETE;
-		fcport->deleted = 0;
-		fcport->logout_on_delete = 1;
-		fcport->login_retry = vha->hw->login_retry_count;
-		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-	}
+	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
+	fcport->disc_state = DSC_LOGIN_COMPLETE;
+	fcport->deleted = 0;
+	fcport->logout_on_delete = 1;
+	fcport->login_retry = vha->hw->login_retry_count;
 
-	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	qla2x00_iidma_fcport(vha, fcport);
 
 	if (fcport->fc4f_nvme) {
 		qla_nvme_register_remote(vha, fcport);
+		fcport->disc_state = DSC_LOGIN_COMPLETE;
+		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 		return;
 	}
 
@@ -5116,6 +5112,7 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 			qla24xx_post_gpsc_work(vha, fcport);
 		}
 	}
+	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 }
 
 /*
-- 
cgit v1.2.3


From 8fde6977ac478c00eeb2beccfdd4a6ad44219f6c Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:50 -0700
Subject: scsi: qla2xxx: Fix session state stuck in Get Port DB

This patch sets discovery state back to GNL (Get Name List) when session is
stuck at GPDB (Get Port DataBase). This will allow state machine to retry
login and move session state ahead in discovery.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index df55fd4e1716..bb565f556c2f 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -1153,9 +1153,12 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	case PDS_PLOGI_COMPLETE:
 	case PDS_PRLI_PENDING:
 	case PDS_PRLI2_PENDING:
-		ql_dbg(ql_dbg_disc, vha, 0x20d5, "%s %d %8phC relogin needed\n",
-		    __func__, __LINE__, fcport->port_name);
-		set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		/* Set discovery state back to GNL to Relogin attempt */
+		if (qla_dual_mode_enabled(vha) ||
+		    qla_ini_mode_enabled(vha)) {
+			fcport->disc_state = DSC_GNL;
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		}
 		return;
 	case PDS_LOGO_PENDING:
 	case PDS_PORT_UNAVAILABLE:
-- 
cgit v1.2.3


From cb97f2c2e8d9f8c71ddbf04ad57e163ee6d86474 Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:51 -0700
Subject: scsi: qla2xxx: Fix unintended Logout

During normal IO, FW can return IO with 'port unavailble' status.  Driver
would send a LOGO to remote port for session resync.  On an off chance, a
PLOGI could arrive before sending the LOGO.  This patch will skip sendiing
LOGO if a PLOGI just came in.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_target.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index 4f9c315813df..f9036004f179 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -986,8 +986,9 @@ void qlt_free_session_done(struct work_struct *work)
 
 			logo.id = sess->d_id;
 			logo.cmd_count = 0;
+			if (!own)
+				qlt_send_first_logo(vha, &logo);
 			sess->send_els_logo = 0;
-			qlt_send_first_logo(vha, &logo);
 		}
 
 		if (sess->logout_on_delete && sess->loop_id != FC_NO_LOOP_ID) {
-- 
cgit v1.2.3


From b2000805a9759d315f56eecaca7779aa9197a72f Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:52 -0700
Subject: scsi: qla2xxx: Flush mailbox commands on chip reset

Flush pending mailbox commands on chip reset.  Wake up command that's
waiting for an interrupt and wait for mailbox counters to go to zero.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h  |  5 +++++
 drivers/scsi/qla2xxx/qla_init.c | 21 ++++++++++++++++-
 drivers/scsi/qla2xxx/qla_mbx.c  | 50 +++++++++++++++++++++++++++++++++++++----
 drivers/scsi/qla2xxx/qla_os.c   |  3 +++
 4 files changed, 74 insertions(+), 5 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index ee4d1f4fdf95..40bcf938cf4f 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3598,6 +3598,7 @@ struct qla_hw_data {
 		uint32_t	detected_lr_sfp:1;
 		uint32_t	using_lr_setting:1;
 		uint32_t	rida_fmt2:1;
+		uint32_t	purge_mbox:1;
 	} flags;
 
 	uint16_t max_exchg;
@@ -3843,6 +3844,9 @@ struct qla_hw_data {
 	int		port_down_retry_count;
 	uint8_t		mbx_count;
 	uint8_t		aen_mbx_count;
+	atomic_t	num_pend_mbx_stage1;
+	atomic_t	num_pend_mbx_stage2;
+	atomic_t	num_pend_mbx_stage3;
 
 	uint32_t	login_retry_count;
 	/* SNS command interfaces. */
@@ -4156,6 +4160,7 @@ struct qla_hw_data {
 	struct work_struct board_disable;
 
 	struct mr_data_fx00 mr;
+	uint32_t chip_reset;
 
 	struct qlt_hw_data tgt;
 	int	allow_cna_fw_dump;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index bb565f556c2f..a10a8bb895e9 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -6283,6 +6283,7 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	ql_log(ql_log_info, vha, 0x00af,
 	    "Performing ISP error recovery - ha=%p.\n", ha);
 
+	ha->flags.purge_mbox = 1;
 	/* For ISP82XX, reset_chip is just disabling interrupts.
 	 * Driver waits for the completion of the commands.
 	 * the interrupts need to be enabled.
@@ -6297,13 +6298,31 @@ qla2x00_abort_isp_cleanup(scsi_qla_host_t *vha)
 	ha->current_topology = 0;
 	ha->flags.fw_started = 0;
 	ha->flags.fw_init_done = 0;
-	ha->base_qpair->chip_reset++;
+	ha->chip_reset++;
+	ha->base_qpair->chip_reset = ha->chip_reset;
 	for (i = 0; i < ha->max_qpairs; i++) {
 		if (ha->queue_pair_map[i])
 			ha->queue_pair_map[i]->chip_reset =
 				ha->base_qpair->chip_reset;
 	}
 
+	/* purge MBox commands */
+	if (atomic_read(&ha->num_pend_mbx_stage3)) {
+		clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
+		complete(&ha->mbx_intr_comp);
+	}
+
+	i = 0;
+	while (atomic_read(&ha->num_pend_mbx_stage3) ||
+	    atomic_read(&ha->num_pend_mbx_stage2) ||
+	    atomic_read(&ha->num_pend_mbx_stage1)) {
+		msleep(20);
+		i++;
+		if (i > 50)
+			break;
+	}
+	ha->flags.purge_mbox = 0;
+
 	atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
 	if (atomic_read(&vha->loop_state) != LOOP_DOWN) {
 		atomic_set(&vha->loop_state, LOOP_DOWN);
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 17537f0b3b54..10847cdca093 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -110,6 +110,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 	unsigned long	wait_time;
 	struct qla_hw_data *ha = vha->hw;
 	scsi_qla_host_t *base_vha = pci_get_drvdata(ha->pdev);
+	u32 chip_reset;
 
 
 	ql_dbg(ql_dbg_mbx, vha, 0x1000, "Entered %s.\n", __func__);
@@ -140,7 +141,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 
 	rval = QLA_SUCCESS;
 	abort_active = test_bit(ABORT_ISP_ACTIVE, &base_vha->dpc_flags);
-
+	chip_reset = ha->chip_reset;
 
 	if (ha->flags.pci_channel_io_perm_failure) {
 		ql_log(ql_log_warn, vha, 0x1003,
@@ -167,6 +168,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		return QLA_FUNCTION_TIMEOUT;
 	}
 
+	atomic_inc(&ha->num_pend_mbx_stage1);
 	/*
 	 * Wait for active mailbox commands to finish by waiting at most tov
 	 * seconds. This is to serialize actual issuing of mailbox cmds during
@@ -177,8 +179,14 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		ql_log(ql_log_warn, vha, 0xd035,
 		    "Cmd access timeout, cmd=0x%x, Exiting.\n",
 		    mcp->mb[0]);
+		atomic_dec(&ha->num_pend_mbx_stage1);
 		return QLA_FUNCTION_TIMEOUT;
 	}
+	atomic_dec(&ha->num_pend_mbx_stage1);
+	if (ha->flags.purge_mbox || chip_reset != ha->chip_reset) {
+		rval = QLA_ABORTED;
+		goto premature_exit;
+	}
 
 	ha->flags.mbox_busy = 1;
 	/* Save mailbox command for debug */
@@ -189,6 +197,13 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
+	if (ha->flags.purge_mbox || chip_reset != ha->chip_reset) {
+		rval = QLA_ABORTED;
+		ha->flags.mbox_busy = 0;
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		goto premature_exit;
+	}
+
 	/* Load mailbox registers. */
 	if (IS_P3P_TYPE(ha))
 		optr = (uint16_t __iomem *)&reg->isp82.mailbox_in[0];
@@ -231,7 +246,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 	    "jiffies=%lx.\n", jiffies);
 
 	/* Wait for mbx cmd completion until timeout */
-
+	atomic_inc(&ha->num_pend_mbx_stage2);
 	if ((!abort_active && io_lock_on) || IS_NOPOLLING_TYPE(ha)) {
 		set_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 
@@ -241,6 +256,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 				spin_unlock_irqrestore(&ha->hardware_lock,
 					flags);
 				ha->flags.mbox_busy = 0;
+				atomic_dec(&ha->num_pend_mbx_stage2);
 				ql_dbg(ql_dbg_mbx, vha, 0x1010,
 				    "Pending mailbox timeout, exiting.\n");
 				rval = QLA_FUNCTION_TIMEOUT;
@@ -254,6 +270,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 		wait_time = jiffies;
+		atomic_inc(&ha->num_pend_mbx_stage3);
 		if (!wait_for_completion_timeout(&ha->mbx_intr_comp,
 		    mcp->tov * HZ)) {
 			ql_dbg(ql_dbg_mbx, vha, 0x117a,
@@ -261,7 +278,17 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 			spin_lock_irqsave(&ha->hardware_lock, flags);
 			clear_bit(MBX_INTR_WAIT, &ha->mbx_cmd_flags);
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
+		} else if (ha->flags.purge_mbox ||
+		    chip_reset != ha->chip_reset) {
+			ha->flags.mbox_busy = 0;
+			atomic_dec(&ha->num_pend_mbx_stage2);
+			atomic_dec(&ha->num_pend_mbx_stage3);
+			rval = QLA_ABORTED;
+			goto premature_exit;
 		}
+		atomic_dec(&ha->num_pend_mbx_stage3);
+
 		if (time_after(jiffies, wait_time + 5 * HZ))
 			ql_log(ql_log_warn, vha, 0x1015, "cmd=0x%x, waited %d msecs\n",
 			    command, jiffies_to_msecs(jiffies - wait_time));
@@ -275,6 +302,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 				spin_unlock_irqrestore(&ha->hardware_lock,
 					flags);
 				ha->flags.mbox_busy = 0;
+				atomic_dec(&ha->num_pend_mbx_stage2);
 				ql_dbg(ql_dbg_mbx, vha, 0x1012,
 				    "Pending mailbox timeout, exiting.\n");
 				rval = QLA_FUNCTION_TIMEOUT;
@@ -289,6 +317,14 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 
 		wait_time = jiffies + mcp->tov * HZ; /* wait at most tov secs */
 		while (!ha->flags.mbox_int) {
+			if (ha->flags.purge_mbox ||
+			    chip_reset != ha->chip_reset) {
+				ha->flags.mbox_busy = 0;
+				atomic_dec(&ha->num_pend_mbx_stage2);
+				rval = QLA_ABORTED;
+				goto premature_exit;
+			}
+
 			if (time_after(jiffies, wait_time))
 				break;
 
@@ -312,6 +348,7 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		    "Waited %d sec.\n",
 		    (uint)((jiffies - (wait_time - (mcp->tov * HZ)))/HZ));
 	}
+	atomic_dec(&ha->num_pend_mbx_stage2);
 
 	/* Check whether we timed out */
 	if (ha->flags.mbox_int) {
@@ -390,7 +427,8 @@ qla2x00_mailbox_command(scsi_qla_host_t *vha, mbx_cmd_t *mcp)
 		/* Capture FW dump only, if PCI device active */
 		if (!pci_channel_offline(vha->hw->pdev)) {
 			pci_read_config_word(ha->pdev, PCI_VENDOR_ID, &w);
-			if (w == 0xffff || ictrl == 0xffffffff) {
+			if (w == 0xffff || ictrl == 0xffffffff ||
+			    (chip_reset != ha->chip_reset)) {
 				/* This is special case if there is unload
 				 * of driver happening and if PCI device go
 				 * into bad state due to PCI error condition
@@ -497,7 +535,11 @@ premature_exit:
 	complete(&ha->mbx_cmd_comp);
 
 mbx_done:
-	if (rval) {
+	if (rval == QLA_ABORTED) {
+		ql_log(ql_log_info, vha, 0xd035,
+		    "Chip Reset in progress. Purging Mbox cmd=0x%x.\n",
+		    mcp->mb[0]);
+	} else if (rval) {
 		if (ql2xextended_error_logging & (ql_dbg_disc|ql_dbg_mbx)) {
 			pr_warn("%s [%s]-%04x:%ld: **** Failed", QL_MSGHDR,
 			    dev_name(&ha->pdev->dev), 0x1020+0x800,
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index e218d68de532..04e0c7f51e68 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2815,6 +2815,9 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	ha->link_data_rate = PORT_SPEED_UNKNOWN;
 	ha->optrom_size = OPTROM_SIZE_2300;
 	ha->max_exchg = FW_MAX_EXCHANGES_CNT;
+	atomic_set(&ha->num_pend_mbx_stage1, 0);
+	atomic_set(&ha->num_pend_mbx_stage2, 0);
+	atomic_set(&ha->num_pend_mbx_stage3, 0);
 
 	/* Assign ISP specific operations. */
 	if (IS_QLA2100(ha)) {
-- 
cgit v1.2.3


From f6602f3befbb9979cdb031e32211358dd008d05e Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:53 -0700
Subject: scsi: qla2xxx: Fix Management Server NPort handle reservation logic

After selecting the NPort handle/loop_id, set a bit in the loop_id_map to
prevent others from selecting the same NPort handle.

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_gbl.h  |  1 +
 drivers/scsi/qla2xxx/qla_init.c | 28 ++++++++++++++++++++++++++++
 drivers/scsi/qla2xxx/qla_mid.c  |  2 +-
 drivers/scsi/qla2xxx/qla_os.c   |  3 ++-
 4 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index f68eb6096559..00fbd49a9a7a 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -118,6 +118,7 @@ extern int qla2x00_post_async_prlo_done_work(struct scsi_qla_host *,
     fc_port_t *, uint16_t *);
 int qla_post_iidma_work(struct scsi_qla_host *vha, fc_port_t *fcport);
 void qla_do_iidma_work(struct scsi_qla_host *vha, fc_port_t *fcport);
+int qla2x00_reserve_mgmt_server_loop_id(scsi_qla_host_t *);
 /*
  * Global Data in qla_os.c source file.
  */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index a10a8bb895e9..9d1a8b2c41a9 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -5616,6 +5616,34 @@ qla2x00_find_new_loop_id(scsi_qla_host_t *vha, fc_port_t *dev)
 }
 
 
+/* FW does not set aside Loop id for MGMT Server/FFFFFAh */
+int
+qla2x00_reserve_mgmt_server_loop_id(scsi_qla_host_t *vha)
+{
+	int loop_id = FC_NO_LOOP_ID;
+	int lid = NPH_MGMT_SERVER - vha->vp_idx;
+	unsigned long flags;
+	struct qla_hw_data *ha = vha->hw;
+
+	if (vha->vp_idx == 0) {
+		set_bit(NPH_MGMT_SERVER, ha->loop_id_map);
+		return NPH_MGMT_SERVER;
+	}
+
+	/* pick id from high and work down to low */
+	spin_lock_irqsave(&ha->vport_slock, flags);
+	for (; lid > 0; lid--) {
+		if (!test_bit(lid, vha->hw->loop_id_map)) {
+			set_bit(lid, vha->hw->loop_id_map);
+			loop_id = lid;
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&ha->vport_slock, flags);
+
+	return loop_id;
+}
+
 /*
  * qla2x00_fabric_login
  *	Issue fabric login command.
diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
index f6f0a759a7c2..14bc88bc4a5a 100644
--- a/drivers/scsi/qla2xxx/qla_mid.c
+++ b/drivers/scsi/qla2xxx/qla_mid.c
@@ -485,7 +485,7 @@ qla24xx_create_vhost(struct fc_vport *fc_vport)
 		    "Couldn't allocate vp_id.\n");
 		goto create_vhost_failed;
 	}
-	vha->mgmt_svr_loop_id = NPH_MGMT_SERVER;
+	vha->mgmt_svr_loop_id = qla2x00_reserve_mgmt_server_loop_id(vha);
 
 	vha->dpc_flags = 0L;
 
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 04e0c7f51e68..48d1003c8178 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -3048,7 +3048,8 @@ qla2x00_probe_one(struct pci_dev *pdev, const struct pci_device_id *id)
 	host = base_vha->host;
 	base_vha->req = req;
 	if (IS_QLA2XXX_MIDTYPE(ha))
-		base_vha->mgmt_svr_loop_id = NPH_MGMT_SERVER;
+		base_vha->mgmt_svr_loop_id =
+			qla2x00_reserve_mgmt_server_loop_id(base_vha);
 	else
 		base_vha->mgmt_svr_loop_id = MANAGEMENT_SERVER +
 						base_vha->vp_idx;
-- 
cgit v1.2.3


From f6145e86d21fccd59bbb87bc1e1eb076658fd79a Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:54 -0700
Subject: scsi: qla2xxx: Fix race between switch cmd completion and timeout

Fix race condition between switch cmd completion and timeout timer. Timer
has popped triggers command free. On IOCB completion, stale sp point was
reused. Instead, an abort will be sent to FW to nudge the command out of FW
where the normal completion will take place.

RIP: 0010:qla2x00_chk_ms_status+0xf3/0x1b0 [qla2xxx]
Call Trace:
<IRQ>
qla24xx_els_ct_entry.isra.15+0x1d4/0x2b0 [qla2xxx]
 qla24xx_msix_rsp_q+0x39/0xf0 [qla2xxx]
qla24xx_process_response_queue+0xbc/0x2b0 [qla2xxx]
qla24xx_msix_rsp_q+0x8a/0xf0 [qla2xxx]
__handle_irq_event_percpu+0xa0/0x1f0

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h  |  1 +
 drivers/scsi/qla2xxx/qla_gbl.h  |  2 +-
 drivers/scsi/qla2xxx/qla_init.c | 75 ++++++++++++++++++++++++++++++-----------
 3 files changed, 58 insertions(+), 20 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 40bcf938cf4f..0fc563572fad 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -313,6 +313,7 @@ struct srb_cmd {
 #define SRB_CRC_CTX_DMA_VALID		BIT_2	/* DIF: context DMA valid */
 #define SRB_CRC_PROT_DMA_VALID		BIT_4	/* DIF: prot DMA valid */
 #define SRB_CRC_CTX_DSD_VALID		BIT_5	/* DIF: dsd_list valid */
+#define SRB_WAKEUP_ON_COMP		BIT_6
 
 /* To identify if a srb is of T10-CRC type. @sp => srb_t pointer */
 #define IS_PROT_IO(sp)	(sp->flags & SRB_CRC_CTX_DSD_VALID)
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 00fbd49a9a7a..6f2a37220a55 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -213,7 +213,7 @@ extern int qla24xx_post_upd_fcport_work(struct scsi_qla_host *, fc_port_t *);
 void qla2x00_handle_login_done_event(struct scsi_qla_host *, fc_port_t *,
 	uint16_t *);
 int qla24xx_post_gnl_work(struct scsi_qla_host *, fc_port_t *);
-int qla24xx_async_abort_cmd(srb_t *);
+int qla24xx_async_abort_cmd(srb_t *, bool);
 int qla24xx_post_relogin_work(struct scsi_qla_host *vha);
 
 /*
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 9d1a8b2c41a9..75538383de5b 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -50,16 +50,15 @@ qla2x00_sp_timeout(struct timer_list *t)
 {
 	srb_t *sp = from_timer(sp, t, u.iocb_cmd.timer);
 	struct srb_iocb *iocb;
-	scsi_qla_host_t *vha = sp->vha;
 	struct req_que *req;
 	unsigned long flags;
 
-	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
-	req = vha->hw->req_q_map[0];
+	spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+	req = sp->qpair->req;
 	req->outstanding_cmds[sp->handle] = NULL;
 	iocb = &sp->u.iocb_cmd;
+	spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
 	iocb->timeout(sp);
-	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 }
 
 void
@@ -100,6 +99,8 @@ qla2x00_async_iocb_timeout(void *data)
 	srb_t *sp = data;
 	fc_port_t *fcport = sp->fcport;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
+	int rc, h;
+	unsigned long flags;
 
 	if (fcport) {
 		ql_dbg(ql_dbg_disc, fcport->vha, 0x2071,
@@ -114,11 +115,26 @@ qla2x00_async_iocb_timeout(void *data)
 
 	switch (sp->type) {
 	case SRB_LOGIN_CMD:
-		/* Retry as needed. */
-		lio->u.logio.data[0] = MBS_COMMAND_ERROR;
-		lio->u.logio.data[1] = lio->u.logio.flags & SRB_LOGIN_RETRIED ?
-			QLA_LOGIO_LOGIN_RETRIED : 0;
-		sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		rc = qla24xx_async_abort_cmd(sp, false);
+		if (rc) {
+			/* Retry as needed. */
+			lio->u.logio.data[0] = MBS_COMMAND_ERROR;
+			lio->u.logio.data[1] =
+				lio->u.logio.flags & SRB_LOGIN_RETRIED ?
+				QLA_LOGIO_LOGIN_RETRIED : 0;
+			spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+			for (h = 1; h < sp->qpair->req->num_outstanding_cmds;
+			    h++) {
+				if (sp->qpair->req->outstanding_cmds[h] ==
+				    sp) {
+					sp->qpair->req->outstanding_cmds[h] =
+					    NULL;
+					break;
+				}
+			}
+			spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
+			sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		}
 		break;
 	case SRB_LOGOUT_CMD:
 	case SRB_CT_PTHRU_CMD:
@@ -127,7 +143,21 @@ qla2x00_async_iocb_timeout(void *data)
 	case SRB_NACK_PRLI:
 	case SRB_NACK_LOGO:
 	case SRB_CTRL_VP:
-		sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		rc = qla24xx_async_abort_cmd(sp, false);
+		if (rc) {
+			spin_lock_irqsave(sp->qpair->qp_lock_ptr, flags);
+			for (h = 1; h < sp->qpair->req->num_outstanding_cmds;
+			    h++) {
+				if (sp->qpair->req->outstanding_cmds[h] ==
+				    sp) {
+					sp->qpair->req->outstanding_cmds[h] =
+					    NULL;
+					break;
+				}
+			}
+			spin_unlock_irqrestore(sp->qpair->qp_lock_ptr, flags);
+			sp->done(sp, QLA_FUNCTION_TIMEOUT);
+		}
 		break;
 	}
 }
@@ -1594,7 +1624,7 @@ qla24xx_abort_iocb_timeout(void *data)
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
 	abt->u.abt.comp_status = CS_TIMEOUT;
-	complete(&abt->u.abt.comp);
+	sp->done(sp, QLA_FUNCTION_TIMEOUT);
 }
 
 static void
@@ -1603,12 +1633,16 @@ qla24xx_abort_sp_done(void *ptr, int res)
 	srb_t *sp = ptr;
 	struct srb_iocb *abt = &sp->u.iocb_cmd;
 
-	if (del_timer(&sp->u.iocb_cmd.timer))
-		complete(&abt->u.abt.comp);
+	if (del_timer(&sp->u.iocb_cmd.timer)) {
+		if (sp->flags & SRB_WAKEUP_ON_COMP)
+			complete(&abt->u.abt.comp);
+		else
+			sp->free(sp);
+	}
 }
 
 int
-qla24xx_async_abort_cmd(srb_t *cmd_sp)
+qla24xx_async_abort_cmd(srb_t *cmd_sp, bool wait)
 {
 	scsi_qla_host_t *vha = cmd_sp->vha;
 	fc_port_t *fcport = cmd_sp->fcport;
@@ -1623,6 +1657,8 @@ qla24xx_async_abort_cmd(srb_t *cmd_sp)
 	abt_iocb = &sp->u.iocb_cmd;
 	sp->type = SRB_ABT_CMD;
 	sp->name = "abort";
+	if (wait)
+		sp->flags = SRB_WAKEUP_ON_COMP;
 
 	abt_iocb->timeout = qla24xx_abort_iocb_timeout;
 	init_completion(&abt_iocb->u.abt.comp);
@@ -1646,10 +1682,11 @@ qla24xx_async_abort_cmd(srb_t *cmd_sp)
 	    "Abort command issued - hdl=%x, target_id=%x\n",
 	    cmd_sp->handle, fcport->tgt_id);
 
-	wait_for_completion(&abt_iocb->u.abt.comp);
-
-	rval = abt_iocb->u.abt.comp_status == CS_COMPLETE ?
-	    QLA_SUCCESS : QLA_FUNCTION_FAILED;
+	if (wait) {
+		wait_for_completion(&abt_iocb->u.abt.comp);
+		rval = abt_iocb->u.abt.comp_status == CS_COMPLETE ?
+			QLA_SUCCESS : QLA_FUNCTION_FAILED;
+	}
 
 done_free_sp:
 	sp->free(sp);
@@ -1685,7 +1722,7 @@ qla24xx_async_abort_command(srb_t *sp)
 		return qlafx00_fx_disc(vha, &vha->hw->mr.fcport,
 		    FXDISC_ABORT_IOCTL);
 
-	return qla24xx_async_abort_cmd(sp);
+	return qla24xx_async_abort_cmd(sp, true);
 }
 
 static void
-- 
cgit v1.2.3


From 15b6c3c9568765f0717b2dd3aa67a5f7eadd9734 Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <himanshu.madhani@cavium.com>
Date: Thu, 2 Aug 2018 13:16:55 -0700
Subject: scsi: qla2xxx: Fix stalled relogin

This patch sets and clears FCF_ASYNC_{SENT|ACTIVE} flags to prevent
stalling of relogin attempt. Once flag are correctly set/cleared, relogin
timer can retry relogin attempt for driver to continue login.

Fixes: fa83e65885b9 ("scsi: qla2xxx: ensure async flags are reset correctly")
Cc: stable@vger.kernel.org #4.17
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_init.c | 2 +-
 drivers/scsi/qla2xxx/qla_iocb.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 75538383de5b..c3c7aa1cb86e 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -431,7 +431,7 @@ qla2x00_async_adisc_sp_done(void *ptr, int res)
 	    "Async done-%s res %x %8phC\n",
 	    sp->name, res, sp->fcport->port_name);
 
-	sp->fcport->flags &= ~FCF_ASYNC_SENT;
+	sp->fcport->flags &= ~(FCF_ASYNC_SENT | FCF_ASYNC_ACTIVE);
 
 	memset(&ea, 0, sizeof(ea));
 	ea.event = FCME_ADISC_DONE;
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index e1ff2e27e59f..ba14db8d0b8d 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2634,6 +2634,7 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 	ql_dbg(ql_dbg_io, vha, 0x3073,
 	    "Enter: PLOGI portid=%06x\n", fcport->d_id.b24);
 
+	fcport->flags |= FCF_ASYNC_SENT;
 	sp->type = SRB_ELS_DCMD;
 	sp->name = "ELS_DCMD";
 	sp->fcport = fcport;
-- 
cgit v1.2.3


From 0eaaca4c1bd6349fff3a47228c4db8e9e5cf7cdf Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:56 -0700
Subject: scsi: qla2xxx: Save frame payload size from ICB

Save frame payload size from init control block.  This field/data is used
to register with switch database.  This allows the init control block temp
buf to be reused.

[mkp: remove unused variable]

Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h  | 1 +
 drivers/scsi/qla2xxx/qla_gs.c   | 5 +----
 drivers/scsi/qla2xxx/qla_init.c | 6 +++---
 3 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index 0fc563572fad..d1ff1b8f1ae5 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -3848,6 +3848,7 @@ struct qla_hw_data {
 	atomic_t	num_pend_mbx_stage1;
 	atomic_t	num_pend_mbx_stage2;
 	atomic_t	num_pend_mbx_stage3;
+	uint16_t	frame_payload_size;
 
 	uint32_t	login_retry_count;
 	/* SNS command interfaces. */
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index 5139a3577bb3..cf70c59c2523 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -1954,7 +1954,6 @@ qla2x00_fdmiv2_rhba(scsi_qla_host_t *vha)
 	void *entries;
 	struct ct_fdmiv2_hba_attr *eiter;
 	struct qla_hw_data *ha = vha->hw;
-	struct init_cb_24xx *icb24 = (struct init_cb_24xx *)ha->init_cb;
 	struct new_utsname *p_sysid = NULL;
 
 	/* Issue RHBA */
@@ -2134,9 +2133,7 @@ qla2x00_fdmiv2_rhba(scsi_qla_host_t *vha)
 	/* MAX CT Payload Length */
 	eiter = entries + size;
 	eiter->type = cpu_to_be16(FDMI_HBA_MAXIMUM_CT_PAYLOAD_LENGTH);
-	eiter->a.max_ct_len = IS_FWI2_CAPABLE(ha) ?
-	    le16_to_cpu(icb24->frame_payload_size) :
-	    le16_to_cpu(ha->init_cb->frame_payload_size);
+	eiter->a.max_ct_len = cpu_to_be32(ha->frame_payload_size);
 	eiter->a.max_ct_len = cpu_to_be32(eiter->a.max_ct_len);
 	eiter->len = cpu_to_be16(4 + 4);
 	size += 4 + 4;
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index c3c7aa1cb86e..471322c29db6 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -4418,7 +4418,7 @@ qla2x00_nvram_config(scsi_qla_host_t *vha)
 	cnt = (uint8_t *)icb->reserved_3 - (uint8_t *)icb->add_firmware_options;
 	while (cnt--)
 		*dptr1++ = *dptr2++;
-
+	ha->frame_payload_size = le16_to_cpu(icb->frame_payload_size);
 	/* Use alternate WWN? */
 	if (nv->host_p[1] & BIT_7) {
 		memcpy(icb->node_name, nv->alternate_node_name, WWN_SIZE);
@@ -6893,7 +6893,7 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 	    (uint8_t *)&icb->interrupt_delay_timer;
 	while (cnt--)
 		*dptr1++ = *dptr2++;
-
+	ha->frame_payload_size = le16_to_cpu(icb->frame_payload_size);
 	/*
 	 * Setup driver NVRAM options.
 	 */
@@ -7949,7 +7949,7 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 
 	/* Use extended-initialization control block. */
 	memcpy(ha->ex_init_cb, &nv->ex_version, sizeof(*ha->ex_init_cb));
-
+	ha->frame_payload_size = le16_to_cpu(icb->frame_payload_size);
 	/*
 	 * Setup driver NVRAM options.
 	 */
-- 
cgit v1.2.3


From 8777e4314d397c4e3615dc02fe8537e571e3922f Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Thu, 2 Aug 2018 13:16:57 -0700
Subject: scsi: qla2xxx: Migrate NVME N2N handling into state machine

This patch fixes regression introduced for the N2N support for FC-NVMe. For
FC-NVMe with N2N connection, instead of FW initiating the Login, Driver
starts Login process.  This patch migrates that new process from a
standalone path into existing session management state machine. With this
state change now driver will not wait for pull NPort ID from FW.

Fixes: edd05de197592 ("scsi: qla2xxx: Changes to support N2N logins")
Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_def.h     |  12 +-
 drivers/scsi/qla2xxx/qla_fw.h      |   5 +
 drivers/scsi/qla2xxx/qla_gbl.h     |   3 +-
 drivers/scsi/qla2xxx/qla_gs.c      |  47 +++++---
 drivers/scsi/qla2xxx/qla_init.c    | 229 ++++++++++++++++++++++++++++++-------
 drivers/scsi/qla2xxx/qla_inline.h  |   2 -
 drivers/scsi/qla2xxx/qla_iocb.c    | 112 +++++++++++++-----
 drivers/scsi/qla2xxx/qla_mbx.c     |  77 ++++++++++---
 drivers/scsi/qla2xxx/qla_nvme.c    |  15 ++-
 drivers/scsi/qla2xxx/qla_nvme.h    |   2 +-
 drivers/scsi/qla2xxx/qla_os.c      |  32 ++++--
 drivers/scsi/qla2xxx/tcm_qla2xxx.c |   3 -
 12 files changed, 413 insertions(+), 126 deletions(-)

diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index d1ff1b8f1ae5..a03e12797f30 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -398,6 +398,8 @@ struct srb_iocb {
 			struct completion comp;
 			struct els_plogi_payload *els_plogi_pyld;
 			struct els_plogi_payload *els_resp_pyld;
+			u32 tx_size;
+			u32 rx_size;
 			dma_addr_t els_plogi_pyld_dma;
 			dma_addr_t els_resp_pyld_dma;
 			uint32_t	fw_status[3];
@@ -2312,6 +2314,7 @@ enum fcport_mgt_event {
 	FCME_ADISC_DONE,
 	FCME_GNNID_DONE,
 	FCME_GFPNID_DONE,
+	FCME_ELS_PLOGI_DONE,
 };
 
 enum rscn_addr_format {
@@ -2408,6 +2411,7 @@ typedef struct fc_port {
 	struct ct_sns_desc ct_desc;
 	enum discovery_state disc_state;
 	enum login_state fw_login_state;
+	unsigned long dm_login_expire;
 	unsigned long plogi_nack_done_deadline;
 
 	u32 login_gen, last_login_gen;
@@ -2418,7 +2422,8 @@ typedef struct fc_port {
 	u8 iocb[IOCB_SIZE];
 	u8 current_login_state;
 	u8 last_login_state;
-	struct completion n2n_done;
+	u16 n2n_link_reset_cnt;
+	u16 n2n_chip_reset;
 } fc_port_t;
 
 #define QLA_FCPORT_SCAN		1
@@ -3228,6 +3233,7 @@ enum qla_work_type {
 	QLA_EVT_GFPNID,
 	QLA_EVT_SP_RETRY,
 	QLA_EVT_IIDMA,
+	QLA_EVT_ELS_PLOGI,
 };
 
 
@@ -3600,6 +3606,7 @@ struct qla_hw_data {
 		uint32_t	using_lr_setting:1;
 		uint32_t	rida_fmt2:1;
 		uint32_t	purge_mbox:1;
+		uint32_t        n2n_bigger:1;
 	} flags;
 
 	uint16_t max_exchg;
@@ -3908,6 +3915,9 @@ struct qla_hw_data {
 	int		exchoffld_size;
 	int 		exchoffld_count;
 
+	/* n2n */
+	struct els_plogi_payload plogi_els_payld;
+
 	void            *swl;
 
 	/* These are used by mailbox operations. */
diff --git a/drivers/scsi/qla2xxx/qla_fw.h b/drivers/scsi/qla2xxx/qla_fw.h
index 5d8688e5bc7c..50c1e6c62e31 100644
--- a/drivers/scsi/qla2xxx/qla_fw.h
+++ b/drivers/scsi/qla2xxx/qla_fw.h
@@ -1366,6 +1366,11 @@ struct vp_rpt_id_entry_24xx {
 			/* format 1 fabric */
 			uint8_t vpstat1_subcode; /* vp_status=1 subcode */
 			uint8_t flags;
+#define TOPO_MASK  0xE
+#define TOPO_FL    0x2
+#define TOPO_N2N   0x4
+#define TOPO_F     0x6
+
 			uint16_t fip_flags;
 			uint8_t rsv2[12];
 
diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
index 6f2a37220a55..035ab18bd534 100644
--- a/drivers/scsi/qla2xxx/qla_gbl.h
+++ b/drivers/scsi/qla2xxx/qla_gbl.h
@@ -45,8 +45,7 @@ extern int qla2x00_fabric_login(scsi_qla_host_t *, fc_port_t *, uint16_t *);
 extern int qla2x00_local_device_login(scsi_qla_host_t *, fc_port_t *);
 
 extern int qla24xx_els_dcmd_iocb(scsi_qla_host_t *, int, port_id_t);
-extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *,
-				  port_id_t);
+extern int qla24xx_els_dcmd2_iocb(scsi_qla_host_t *, int, fc_port_t *, bool);
 
 extern void qla2x00_update_fcports(scsi_qla_host_t *);
 
diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
index cf70c59c2523..407eb705f1be 100644
--- a/drivers/scsi/qla2xxx/qla_gs.c
+++ b/drivers/scsi/qla2xxx/qla_gs.c
@@ -3383,19 +3383,40 @@ int qla24xx_post_gpnid_work(struct scsi_qla_host *vha, port_id_t *id)
 
 void qla24xx_sp_unmap(scsi_qla_host_t *vha, srb_t *sp)
 {
-	if (sp->u.iocb_cmd.u.ctarg.req) {
-		dma_free_coherent(&vha->hw->pdev->dev,
-			sizeof(struct ct_sns_pkt),
-			sp->u.iocb_cmd.u.ctarg.req,
-			sp->u.iocb_cmd.u.ctarg.req_dma);
-		sp->u.iocb_cmd.u.ctarg.req = NULL;
-	}
-	if (sp->u.iocb_cmd.u.ctarg.rsp) {
-		dma_free_coherent(&vha->hw->pdev->dev,
-			sizeof(struct ct_sns_pkt),
-			sp->u.iocb_cmd.u.ctarg.rsp,
-			sp->u.iocb_cmd.u.ctarg.rsp_dma);
-		sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+	struct srb_iocb *c = &sp->u.iocb_cmd;
+
+	switch (sp->type) {
+	case SRB_ELS_DCMD:
+		if (c->u.els_plogi.els_plogi_pyld)
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    c->u.els_plogi.tx_size,
+			    c->u.els_plogi.els_plogi_pyld,
+			    c->u.els_plogi.els_plogi_pyld_dma);
+
+		if (c->u.els_plogi.els_resp_pyld)
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    c->u.els_plogi.rx_size,
+			    c->u.els_plogi.els_resp_pyld,
+			    c->u.els_plogi.els_resp_pyld_dma);
+		break;
+	case SRB_CT_PTHRU_CMD:
+	default:
+		if (sp->u.iocb_cmd.u.ctarg.req) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.req,
+			    sp->u.iocb_cmd.u.ctarg.req_dma);
+			sp->u.iocb_cmd.u.ctarg.req = NULL;
+		}
+
+		if (sp->u.iocb_cmd.u.ctarg.rsp) {
+			dma_free_coherent(&vha->hw->pdev->dev,
+			    sizeof(struct ct_sns_pkt),
+			    sp->u.iocb_cmd.u.ctarg.rsp,
+			    sp->u.iocb_cmd.u.ctarg.rsp_dma);
+			sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+		}
+		break;
 	}
 
 	sp->free(sp);
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 471322c29db6..f52c68b4da44 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -419,6 +419,19 @@ void qla24xx_handle_adisc_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	__qla24xx_handle_gpdb_event(vha, ea);
 }
 
+int qla_post_els_plogi_work(struct scsi_qla_host *vha, fc_port_t *fcport)
+{
+	struct qla_work_evt *e;
+
+	e = qla2x00_alloc_work(vha, QLA_EVT_ELS_PLOGI);
+	if (!e)
+		return QLA_FUNCTION_FAILED;
+
+	e->u.fcport.fcport = fcport;
+	fcport->flags |= FCF_ASYNC_ACTIVE;
+	return qla2x00_post_work(vha, e);
+}
+
 static void
 qla2x00_async_adisc_sp_done(void *ptr, int res)
 {
@@ -467,6 +480,8 @@ qla2x00_async_adisc(struct scsi_qla_host *vha, fc_port_t *fcport,
 
 	lio = &sp->u.iocb_cmd;
 	lio->timeout = qla2x00_async_iocb_timeout;
+	sp->gen1 = fcport->rscn_gen;
+	sp->gen2 = fcport->login_gen;
 	qla2x00_init_timer(sp, qla2x00_get_async_timeout(vha) + 2);
 
 	sp->done = qla2x00_async_adisc_sp_done;
@@ -560,12 +575,17 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 
 		loop_id = le16_to_cpu(e->nport_handle);
 		loop_id = (loop_id & 0x7fff);
+		if  (fcport->fc4f_nvme)
+			current_login_state = e->current_login_state >> 4;
+		else
+			current_login_state = e->current_login_state & 0xf;
+
 
 		ql_dbg(ql_dbg_disc, vha, 0x20e2,
-		    "%s found %8phC CLS [%d|%d] ID[%02x%02x%02x|%02x%02x%02x] lid[%d|%d]\n",
+		    "%s found %8phC CLS [%x|%x] nvme %d ID[%02x%02x%02x|%02x%02x%02x] lid[%d|%d]\n",
 		    __func__, fcport->port_name,
 		    e->current_login_state, fcport->fw_login_state,
-		    id.b.domain, id.b.area, id.b.al_pa,
+		    fcport->fc4f_nvme, id.b.domain, id.b.area, id.b.al_pa,
 		    fcport->d_id.b.domain, fcport->d_id.b.area,
 		    fcport->d_id.b.al_pa, loop_id, fcport->loop_id);
 
@@ -574,9 +594,13 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 		case DSC_DELETED:
 			break;
 		default:
-			if ((id.b24 != fcport->d_id.b24) ||
-			    ((fcport->loop_id != FC_NO_LOOP_ID) &&
-				(fcport->loop_id != loop_id))) {
+			if ((id.b24 != fcport->d_id.b24 &&
+			    fcport->d_id.b24) ||
+			    (fcport->loop_id != FC_NO_LOOP_ID &&
+				fcport->loop_id != loop_id)) {
+				ql_dbg(ql_dbg_disc, vha, 0x20e3,
+				    "%s %d %8phC post del sess\n",
+				    __func__, __LINE__, fcport->port_name);
 				qlt_schedule_sess_for_deletion(fcport);
 				return;
 			}
@@ -599,11 +623,6 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 			fcport->login_pause = 1;
 		}
 
-		if (fcport->fc4f_nvme)
-			current_login_state = e->current_login_state >> 4;
-		else
-			current_login_state = e->current_login_state & 0xf;
-
 		switch (vha->hw->current_topology) {
 		default:
 			switch (current_login_state) {
@@ -632,6 +651,8 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 			}
 			break;
 		case ISP_CFG_N:
+			fcport->fw_login_state = current_login_state;
+			fcport->d_id = id;
 			switch (current_login_state) {
 			case DSC_LS_PRLI_COMP:
 				if ((e->prli_svc_param_word_3[0] & BIT_4) == 0)
@@ -705,12 +726,39 @@ static void qla24xx_handle_gnl_done_event(scsi_qla_host_t *vha,
 			qla24xx_fcport_handle_login(vha, fcport);
 			break;
 		case ISP_CFG_N:
-			/*
-			 * FW handles the initial login for n2n.
-			 * Do link reinit to trigger this auto login.
-			 */
-			set_bit(N2N_LINK_RESET, &vha->dpc_flags);
-			qla2xxx_wake_dpc(vha);
+			fcport->disc_state = DSC_DELETED;
+			if (time_after_eq(jiffies, fcport->dm_login_expire)) {
+				if (fcport->n2n_link_reset_cnt < 2) {
+					fcport->n2n_link_reset_cnt++;
+					/*
+					 * remote port is not sending PLOGI.
+					 * Reset link to kick start his state
+					 * machine
+					 */
+					set_bit(N2N_LINK_RESET,
+					    &vha->dpc_flags);
+				} else {
+					if (fcport->n2n_chip_reset < 1) {
+						ql_log(ql_log_info, vha, 0x705d,
+						    "Chip reset to bring laser down");
+						set_bit(ISP_ABORT_NEEDED,
+						    &vha->dpc_flags);
+						fcport->n2n_chip_reset++;
+					} else {
+						ql_log(ql_log_info, vha, 0x705d,
+						    "Remote port %8ph is not coming back\n",
+						    fcport->port_name);
+						fcport->scan_state = 0;
+					}
+				}
+				qla2xxx_wake_dpc(vha);
+			} else {
+				/*
+				 * report port suppose to do PLOGI. Give him
+				 * more time. FW will catch it.
+				 */
+				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+			}
 			break;
 		default:
 			break;
@@ -1020,9 +1068,9 @@ qla24xx_async_prli(struct scsi_qla_host *vha, fc_port_t *fcport)
 	}
 
 	ql_dbg(ql_dbg_disc, vha, 0x211b,
-	    "Async-prli - %8phC hdl=%x, loopid=%x portid=%06x retries=%d.\n",
-	    fcport->port_name, sp->handle, fcport->loop_id,
-	    fcport->d_id.b24, fcport->login_retry);
+	    "Async-prli - %8phC hdl=%x, loopid=%x portid=%06x retries=%d %s.\n",
+	    fcport->port_name, sp->handle, fcport->loop_id, fcport->d_id.b24,
+	    fcport->login_retry, fcport->fc4f_nvme ? "nvme" : "fc");
 
 	return rval;
 
@@ -1164,8 +1212,9 @@ void qla24xx_handle_gpdb_event(scsi_qla_host_t *vha, struct event_arg *ea)
 	fcport->flags &= ~FCF_ASYNC_SENT;
 
 	ql_dbg(ql_dbg_disc, vha, 0x20d2,
-	    "%s %8phC DS %d LS %d rc %d\n", __func__, fcport->port_name,
-	    fcport->disc_state, pd->current_login_state, ea->rc);
+	    "%s %8phC DS %d LS %d nvme %x rc %d\n", __func__, fcport->port_name,
+	    fcport->disc_state, pd->current_login_state, fcport->fc4f_nvme,
+	    ea->rc);
 
 	if (fcport->disc_state == DSC_DELETE_PEND)
 		return;
@@ -1286,36 +1335,76 @@ int qla24xx_fcport_handle_login(struct scsi_qla_host *vha, fc_port_t *fcport)
 		return 0;
 	}
 
-
 	switch (fcport->disc_state) {
 	case DSC_DELETED:
-		fcport->login_retry--;
 		wwn = wwn_to_u64(fcport->node_name);
-		if (wwn == 0) {
-			ql_dbg(ql_dbg_disc, vha, 0xffff,
-			    "%s %d %8phC post GNNID\n",
-			    __func__, __LINE__, fcport->port_name);
-			qla24xx_post_gnnid_work(vha, fcport);
-		} else if (fcport->loop_id == FC_NO_LOOP_ID) {
-			ql_dbg(ql_dbg_disc, vha, 0x20bd,
-			    "%s %d %8phC post gnl\n",
-			    __func__, __LINE__, fcport->port_name);
-			qla24xx_post_gnl_work(vha, fcport);
-		} else {
-			fcport->login_retry--;
-			qla_chk_n2n_b4_login(vha, fcport);
+		switch (vha->hw->current_topology) {
+		case ISP_CFG_N:
+			if (fcport_is_smaller(fcport)) {
+				/* this adapter is bigger */
+				if (fcport->login_retry) {
+					if (fcport->loop_id == FC_NO_LOOP_ID) {
+						qla2x00_find_new_loop_id(vha,
+						    fcport);
+						fcport->fw_login_state =
+						    DSC_LS_PORT_UNAVAIL;
+					}
+					fcport->login_retry--;
+					qla_post_els_plogi_work(vha, fcport);
+				} else {
+					ql_log(ql_log_info, vha, 0x705d,
+					    "Unable to reach remote port %8phC",
+					    fcport->port_name);
+				}
+			} else {
+				qla24xx_post_gnl_work(vha, fcport);
+			}
+			break;
+		default:
+			if (wwn == 0)    {
+				ql_dbg(ql_dbg_disc, vha, 0xffff,
+				    "%s %d %8phC post GNNID\n",
+				    __func__, __LINE__, fcport->port_name);
+				qla24xx_post_gnnid_work(vha, fcport);
+			} else if (fcport->loop_id == FC_NO_LOOP_ID) {
+				ql_dbg(ql_dbg_disc, vha, 0x20bd,
+				    "%s %d %8phC post gnl\n",
+				    __func__, __LINE__, fcport->port_name);
+				qla24xx_post_gnl_work(vha, fcport);
+			} else {
+				qla_chk_n2n_b4_login(vha, fcport);
+			}
+			break;
 		}
 		break;
 
 	case DSC_GNL:
-		if (fcport->login_pause) {
-			fcport->last_rscn_gen = fcport->rscn_gen;
-			fcport->last_login_gen = fcport->login_gen;
-			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		switch (vha->hw->current_topology) {
+		case ISP_CFG_N:
+			if ((fcport->current_login_state & 0xf) == 0x6) {
+				ql_dbg(ql_dbg_disc, vha, 0x2118,
+				    "%s %d %8phC post GPDB work\n",
+				    __func__, __LINE__, fcport->port_name);
+				fcport->chip_reset =
+					vha->hw->base_qpair->chip_reset;
+				qla24xx_post_gpdb_work(vha, fcport, 0);
+			}  else {
+				ql_dbg(ql_dbg_disc, vha, 0x2118,
+				    "%s %d %8phC post NVMe PRLI\n",
+				    __func__, __LINE__, fcport->port_name);
+				qla24xx_post_prli_work(vha, fcport);
+			}
+			break;
+		default:
+			if (fcport->login_pause) {
+				fcport->last_rscn_gen = fcport->rscn_gen;
+				fcport->last_login_gen = fcport->login_gen;
+				set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+				break;
+			}
+			qla_chk_n2n_b4_login(vha, fcport);
 			break;
 		}
-
-		qla_chk_n2n_b4_login(vha, fcport);
 		break;
 
 	case DSC_LOGIN_FAILED:
@@ -1429,6 +1518,15 @@ void qla24xx_handle_relogin_event(scsi_qla_host_t *vha,
 	qla24xx_fcport_handle_login(vha, fcport);
 }
 
+
+void qla_handle_els_plogi_done(scsi_qla_host_t *vha, struct event_arg *ea)
+{
+	ql_dbg(ql_dbg_disc, vha, 0x2118,
+	    "%s %d %8phC post PRLI\n",
+	    __func__, __LINE__, ea->fcport->port_name);
+	qla24xx_post_prli_work(vha, ea->fcport);
+}
+
 void qla2x00_fcport_event_handler(scsi_qla_host_t *vha, struct event_arg *ea)
 {
 	fc_port_t *f, *tf;
@@ -1530,6 +1628,9 @@ void qla2x00_fcport_event_handler(scsi_qla_host_t *vha, struct event_arg *ea)
 	case FCME_GFPNID_DONE:
 		qla24xx_handle_gfpnid_event(vha, ea);
 		break;
+	case FCME_ELS_PLOGI_DONE:
+		qla_handle_els_plogi_done(vha, ea);
+		break;
 	default:
 		BUG_ON(1);
 		break;
@@ -4160,7 +4261,8 @@ qla2x00_configure_hba(scsi_qla_host_t *vha)
 	id.b.al_pa = al_pa;
 	id.b.rsvd_1 = 0;
 	spin_lock_irqsave(&ha->hardware_lock, flags);
-	qlt_update_host_map(vha, id);
+	if (!(topo == 2 && ha->flags.n2n_bigger))
+		qlt_update_host_map(vha, id);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	if (!vha->flags.init_done)
@@ -4813,6 +4915,31 @@ qla2x00_configure_local_loop(scsi_qla_host_t *vha)
 	struct qla_hw_data *ha = vha->hw;
 	unsigned long flags;
 
+	/* Inititae N2N login. */
+	if (test_and_clear_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags)) {
+		/* borrowing */
+		u32 *bp, i, sz;
+
+		memset(ha->init_cb, 0, ha->init_cb_size);
+		sz = min_t(int, sizeof(struct els_plogi_payload),
+		    ha->init_cb_size);
+		rval = qla24xx_get_port_login_templ(vha, ha->init_cb_dma,
+		    (void *)ha->init_cb, sz);
+		if (rval == QLA_SUCCESS) {
+			bp = (uint32_t *)ha->init_cb;
+			for (i = 0; i < sz/4 ; i++, bp++)
+				*bp = cpu_to_be32(*bp);
+
+			memcpy(&ha->plogi_els_payld.data, (void *)ha->init_cb,
+			    sizeof(ha->plogi_els_payld.data));
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		} else {
+			ql_dbg(ql_dbg_init, vha, 0x00d1,
+			    "PLOGI ELS param read fail.\n");
+		}
+		return QLA_SUCCESS;
+	}
+
 	found_devs = 0;
 	new_fcport = NULL;
 	entries = MAX_FIBRE_DEVICES_LOOP;
@@ -5105,9 +5232,19 @@ qla2x00_update_fcport(scsi_qla_host_t *vha, fc_port_t *fcport)
 	fcport->deleted = 0;
 	fcport->logout_on_delete = 1;
 	fcport->login_retry = vha->hw->login_retry_count;
+	fcport->n2n_chip_reset = fcport->n2n_link_reset_cnt = 0;
 
 	qla2x00_iidma_fcport(vha, fcport);
 
+	switch (vha->hw->current_topology) {
+	case ISP_CFG_N:
+	case ISP_CFG_NL:
+		fcport->keep_nport_handle = 1;
+		break;
+	default:
+		break;
+	}
+
 	if (fcport->fc4f_nvme) {
 		qla_nvme_register_remote(vha, fcport);
 		fcport->disc_state = DSC_LOGIN_COMPLETE;
@@ -6992,6 +7129,9 @@ qla24xx_nvram_config(scsi_qla_host_t *vha)
 	if (ql2xloginretrycount)
 		ha->login_retry_count = ql2xloginretrycount;
 
+	/* N2N: driver will initiate Login instead of FW */
+	icb->firmware_options_3 |= BIT_8;
+
 	/* Enable ZIO. */
 	if (!vha->flags.init_done) {
 		ha->zio_mode = le32_to_cpu(icb->firmware_options_2) &
@@ -8076,6 +8216,9 @@ qla81xx_nvram_config(scsi_qla_host_t *vha)
 	 /* enable RIDA Format2 */
 	icb->firmware_options_3 |= BIT_0;
 
+	/* N2N: driver will initiate Login instead of FW */
+	icb->firmware_options_3 |= BIT_8;
+
 	if (IS_QLA27XX(ha)) {
 		icb->firmware_options_3 |= BIT_8;
 		ql_dbg(ql_log_info, vha, 0x0075,
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index acf6511e8ef7..a29f8898c687 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -280,8 +280,6 @@ qla2x00_init_timer(srb_t *sp, unsigned long tmo)
 	init_completion(&sp->comp);
 	if (IS_QLAFX00(sp->vha->hw) && (sp->type == SRB_FXIOCB_DCMD))
 		init_completion(&sp->u.iocb_cmd.u.fxiocb.fxiocb_comp);
-	if (sp->type == SRB_ELS_DCMD)
-		init_completion(&sp->u.iocb_cmd.u.els_logo.comp);
 	add_timer(&sp->u.iocb_cmd.timer);
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index ba14db8d0b8d..059f2c9dc192 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2465,6 +2465,7 @@ qla24xx_els_dcmd_iocb(scsi_qla_host_t *vha, int els_opcode,
 	sp->fcport = fcport;
 	elsio->timeout = qla2x00_els_dcmd_iocb_timeout;
 	qla2x00_init_timer(sp, ELS_DCMD_TIMEOUT);
+	init_completion(&sp->u.iocb_cmd.u.els_logo.comp);
 	sp->done = qla2x00_els_dcmd_sp_done;
 	sp->free = qla2x00_els_dcmd_sp_free;
 
@@ -2512,7 +2513,6 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 {
 	scsi_qla_host_t *vha = sp->vha;
 	struct srb_iocb *elsio = &sp->u.iocb_cmd;
-	uint32_t	dsd_len = 24;
 
 	els_iocb->entry_type = ELS_IOCB_TYPE;
 	els_iocb->entry_count = 1;
@@ -2535,20 +2535,21 @@ qla24xx_els_logo_iocb(srb_t *sp, struct els_entry_24xx *els_iocb)
 	els_iocb->control_flags = 0;
 
 	if (elsio->u.els_logo.els_cmd == ELS_DCMD_PLOGI) {
-		els_iocb->tx_byte_count = sizeof(struct els_plogi_payload);
+		els_iocb->tx_byte_count = els_iocb->tx_len =
+			sizeof(struct els_plogi_payload);
 		els_iocb->tx_address[0] =
 			cpu_to_le32(LSD(elsio->u.els_plogi.els_plogi_pyld_dma));
 		els_iocb->tx_address[1] =
 			cpu_to_le32(MSD(elsio->u.els_plogi.els_plogi_pyld_dma));
-		els_iocb->tx_len = dsd_len;
 
 		els_iocb->rx_dsd_count = 1;
-		els_iocb->rx_byte_count = sizeof(struct els_plogi_payload);
+		els_iocb->rx_byte_count = els_iocb->rx_len =
+			sizeof(struct els_plogi_payload);
 		els_iocb->rx_address[0] =
 			cpu_to_le32(LSD(elsio->u.els_plogi.els_resp_pyld_dma));
 		els_iocb->rx_address[1] =
 			cpu_to_le32(MSD(elsio->u.els_plogi.els_resp_pyld_dma));
-		els_iocb->rx_len = dsd_len;
+
 		ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073,
 		    "PLOGI ELS IOCB:\n");
 		ql_dump_buffer(ql_log_info, vha, 0x0109,
@@ -2577,7 +2578,6 @@ qla2x00_els_dcmd2_iocb_timeout(void *data)
 	fc_port_t *fcport = sp->fcport;
 	struct scsi_qla_host *vha = sp->vha;
 	struct qla_hw_data *ha = vha->hw;
-	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	unsigned long flags = 0;
 	int res;
 
@@ -2593,7 +2593,7 @@ qla2x00_els_dcmd2_iocb_timeout(void *data)
 	    (res == QLA_SUCCESS) ? "successful" : "failed");
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
-	complete(&lio->u.els_plogi.comp);
+	sp->done(sp, QLA_FUNCTION_TIMEOUT);
 }
 
 static void
@@ -2603,17 +2603,54 @@ qla2x00_els_dcmd2_sp_done(void *ptr, int res)
 	fc_port_t *fcport = sp->fcport;
 	struct srb_iocb *lio = &sp->u.iocb_cmd;
 	struct scsi_qla_host *vha = sp->vha;
+	struct event_arg ea;
+	struct qla_work_evt *e;
+
+	ql_dbg(ql_dbg_disc, vha, 0x3072,
+	    "%s ELS done rc %d hdl=%x, portid=%06x %8phC\n",
+	    sp->name, res, sp->handle, fcport->d_id.b24, fcport->port_name);
 
-	ql_dbg(ql_dbg_io + ql_dbg_disc, vha, 0x3072,
-	    "%s ELS hdl=%x, portid=%06x done %8phC\n",
-	    sp->name, sp->handle, fcport->d_id.b24, fcport->port_name);
+	fcport->flags &= ~(FCF_ASYNC_SENT|FCF_ASYNC_ACTIVE);
+	del_timer(&sp->u.iocb_cmd.timer);
 
-	complete(&lio->u.els_plogi.comp);
+	if (sp->flags & SRB_WAKEUP_ON_COMP)
+		complete(&lio->u.els_plogi.comp);
+	else {
+		if (res) {
+			set_bit(RELOGIN_NEEDED, &vha->dpc_flags);
+		} else {
+			memset(&ea, 0, sizeof(ea));
+			ea.fcport = fcport;
+			ea.rc = res;
+			ea.event = FCME_ELS_PLOGI_DONE;
+			qla2x00_fcport_event_handler(vha, &ea);
+		}
+
+		e = qla2x00_alloc_work(vha, QLA_EVT_UNMAP);
+		if (!e) {
+			struct srb_iocb *elsio = &sp->u.iocb_cmd;
+
+			if (elsio->u.els_plogi.els_plogi_pyld)
+				dma_free_coherent(&sp->vha->hw->pdev->dev,
+				    elsio->u.els_plogi.tx_size,
+				    elsio->u.els_plogi.els_plogi_pyld,
+				    elsio->u.els_plogi.els_plogi_pyld_dma);
+
+			if (elsio->u.els_plogi.els_resp_pyld)
+				dma_free_coherent(&sp->vha->hw->pdev->dev,
+				    elsio->u.els_plogi.rx_size,
+				    elsio->u.els_plogi.els_resp_pyld,
+				    elsio->u.els_plogi.els_resp_pyld_dma);
+			sp->free(sp);
+		}
+		e->u.iosb.sp = sp;
+		qla2x00_post_work(vha, e);
+	}
 }
 
 int
 qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
-		       fc_port_t *fcport, port_id_t remote_did)
+    fc_port_t *fcport, bool wait)
 {
 	srb_t *sp;
 	struct srb_iocb *elsio = NULL;
@@ -2641,9 +2678,13 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 
 	elsio->timeout = qla2x00_els_dcmd2_iocb_timeout;
 	init_completion(&elsio->u.els_plogi.comp);
-	qla2x00_init_timer(sp, ELS_DCMD_TIMEOUT);
+	if (wait)
+		sp->flags = SRB_WAKEUP_ON_COMP;
+
+	qla2x00_init_timer(sp, ELS_DCMD_TIMEOUT + 2);
 
 	sp->done = qla2x00_els_dcmd2_sp_done;
+	elsio->u.els_plogi.tx_size = elsio->u.els_plogi.rx_size = DMA_POOL_SIZE;
 
 	ptr = elsio->u.els_plogi.els_plogi_pyld =
 	    dma_alloc_coherent(&ha->pdev->dev, DMA_POOL_SIZE,
@@ -2668,33 +2709,52 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode,
 
 	memset(ptr, 0, sizeof(struct els_plogi_payload));
 	memset(resp_ptr, 0, sizeof(struct els_plogi_payload));
+	memcpy(elsio->u.els_plogi.els_plogi_pyld->data,
+	    &ha->plogi_els_payld.data,
+	    sizeof(elsio->u.els_plogi.els_plogi_pyld->data));
+
 	elsio->u.els_plogi.els_cmd = els_opcode;
 	elsio->u.els_plogi.els_plogi_pyld->opcode = els_opcode;
-	qla24xx_get_port_login_templ(vha, ptr_dma + 4,
-		&elsio->u.els_plogi.els_plogi_pyld->data[0],
-		sizeof(struct els_plogi_payload));
 
-	ql_dbg(ql_dbg_io + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n");
-	ql_dump_buffer(ql_dbg_io + ql_dbg_buffer, vha, 0x0109,
+	ql_dbg(ql_dbg_disc + ql_dbg_buffer, vha, 0x3073, "PLOGI buffer:\n");
+	ql_dump_buffer(ql_dbg_disc + ql_dbg_buffer, vha, 0x0109,
 	    (uint8_t *)elsio->u.els_plogi.els_plogi_pyld, 0x70);
 
 	rval = qla2x00_start_sp(sp);
 	if (rval != QLA_SUCCESS) {
 		rval = QLA_FUNCTION_FAILED;
-		goto out;
+	} else {
+		ql_dbg(ql_dbg_disc, vha, 0x3074,
+		    "%s PLOGI sent, hdl=%x, loopid=%x, to port_id %06x from port_id %06x\n",
+		    sp->name, sp->handle, fcport->loop_id,
+		    fcport->d_id.b24, vha->d_id.b24);
 	}
 
-	ql_dbg(ql_dbg_io, vha, 0x3074,
-	    "%s PLOGI sent, hdl=%x, loopid=%x, portid=%06x\n",
-	    sp->name, sp->handle, fcport->loop_id, fcport->d_id.b24);
-
-	wait_for_completion(&elsio->u.els_plogi.comp);
+	if (wait) {
+		wait_for_completion(&elsio->u.els_plogi.comp);
 
-	if (elsio->u.els_plogi.comp_status != CS_COMPLETE)
-		rval = QLA_FUNCTION_FAILED;
+		if (elsio->u.els_plogi.comp_status != CS_COMPLETE)
+			rval = QLA_FUNCTION_FAILED;
+	} else {
+		goto done;
+	}
 
 out:
+	fcport->flags &= ~(FCF_ASYNC_SENT);
+	if (elsio->u.els_plogi.els_plogi_pyld)
+		dma_free_coherent(&sp->vha->hw->pdev->dev,
+		    elsio->u.els_plogi.tx_size,
+		    elsio->u.els_plogi.els_plogi_pyld,
+		    elsio->u.els_plogi.els_plogi_pyld_dma);
+
+	if (elsio->u.els_plogi.els_resp_pyld)
+		dma_free_coherent(&sp->vha->hw->pdev->dev,
+		    elsio->u.els_plogi.rx_size,
+		    elsio->u.els_plogi.els_resp_pyld,
+		    elsio->u.els_plogi.els_resp_pyld_dma);
+
 	sp->free(sp);
+done:
 	return rval;
 }
 
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 10847cdca093..7c07a939cf15 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -59,6 +59,7 @@ static struct rom_cmd {
 	{ MBC_IOCB_COMMAND_A64 },
 	{ MBC_GET_ADAPTER_LOOP_ID },
 	{ MBC_READ_SFP },
+	{ MBC_GET_RNID_PARAMS },
 };
 
 static int is_rom_cmd(uint16_t cmd)
@@ -3842,30 +3843,68 @@ qla24xx_report_id_acquisition(scsi_qla_host_t *vha,
 		   "Format 1: WWPN %8phC.\n",
 		   vha->port_name);
 
-		/* N2N.  direct connect */
-		if (IS_QLA27XX(ha) &&
-		    ((rptid_entry->u.f1.flags>>1) & 0x7) == 2) {
-			/* if our portname is higher then initiate N2N login */
-			if (wwn_to_u64(vha->port_name) >
-			    wwn_to_u64(rptid_entry->u.f1.port_name)) {
-				// ??? qlt_update_host_map(vha, id);
-				vha->n2n_id = 0x1;
-				ql_dbg(ql_dbg_async, vha, 0x5075,
-				    "Format 1: Setting n2n_update_needed for id %d\n",
-				    vha->n2n_id);
+		switch (rptid_entry->u.f1.flags & TOPO_MASK) {
+		case TOPO_N2N:
+			ha->current_topology = ISP_CFG_N;
+			spin_lock_irqsave(&vha->hw->tgt.sess_lock, flags);
+			fcport = qla2x00_find_fcport_by_wwpn(vha,
+			    rptid_entry->u.f1.port_name, 1);
+			spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
+
+			if (fcport) {
+				fcport->plogi_nack_done_deadline = jiffies + HZ;
+				fcport->dm_login_expire = jiffies + 3*HZ;
+				fcport->scan_state = QLA_FCPORT_FOUND;
+				switch (fcport->disc_state) {
+				case DSC_DELETED:
+					set_bit(RELOGIN_NEEDED,
+					    &vha->dpc_flags);
+					break;
+				case DSC_DELETE_PEND:
+					break;
+				default:
+					qlt_schedule_sess_for_deletion(fcport);
+					break;
+				}
 			} else {
-				ql_dbg(ql_dbg_async, vha, 0x5075,
-				    "Format 1: Remote login - Waiting for WWPN %8phC.\n",
-				    rptid_entry->u.f1.port_name);
+				id.b24 = 0;
+				if (wwn_to_u64(vha->port_name) >
+				    wwn_to_u64(rptid_entry->u.f1.port_name)) {
+					vha->d_id.b24 = 0;
+					vha->d_id.b.al_pa = 1;
+					ha->flags.n2n_bigger = 1;
+
+					id.b.al_pa = 2;
+					ql_dbg(ql_dbg_async, vha, 0x5075,
+					    "Format 1: assign local id %x remote id %x\n",
+					    vha->d_id.b24, id.b24);
+				} else {
+					ql_dbg(ql_dbg_async, vha, 0x5075,
+					    "Format 1: Remote login - Waiting for WWPN %8phC.\n",
+					    rptid_entry->u.f1.port_name);
+					ha->flags.n2n_bigger = 0;
+				}
+				qla24xx_post_newsess_work(vha, &id,
+				    rptid_entry->u.f1.port_name,
+				    rptid_entry->u.f1.node_name,
+				    NULL,
+				    FC4_TYPE_UNKNOWN);
 			}
 
-			memcpy(vha->n2n_port_name, rptid_entry->u.f1.port_name,
-			    WWN_SIZE);
+			/* if our portname is higher then initiate N2N login */
+
 			set_bit(N2N_LOGIN_NEEDED, &vha->dpc_flags);
-			set_bit(REGISTER_FC4_NEEDED, &vha->dpc_flags);
-			set_bit(REGISTER_FDMI_NEEDED, &vha->dpc_flags);
 			ha->flags.n2n_ae = 1;
 			return;
+			break;
+		case TOPO_FL:
+			ha->current_topology = ISP_CFG_FL;
+			break;
+		case TOPO_F:
+			ha->current_topology = ISP_CFG_F;
+			break;
+		default:
+			break;
 		}
 
 		ha->flags.gpsc_supported = 1;
@@ -4681,7 +4720,7 @@ qla24xx_get_port_login_templ(scsi_qla_host_t *vha, dma_addr_t buf_dma,
 		    "Done %s.\n", __func__);
 		bp = (uint32_t *) buf;
 		for (i = 0; i < (bufsiz-4)/4; i++, bp++)
-			*bp = cpu_to_be32(*bp);
+			*bp = le32_to_cpu(*bp);
 	}
 
 	return rval;
diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
index c5a963c2c86e..20d9dc39f0fb 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.c
+++ b/drivers/scsi/qla2xxx/qla_nvme.c
@@ -30,6 +30,9 @@ int qla_nvme_register_remote(struct scsi_qla_host *vha, struct fc_port *fcport)
 		return 0;
 	}
 
+	if (!vha->nvme_local_port && qla_nvme_register_hba(vha))
+		return 0;
+
 	if (!(fcport->nvme_prli_service_param &
 	    (NVME_PRLI_SP_TARGET | NVME_PRLI_SP_DISCOVERY)) ||
 		(fcport->nvme_flag & NVME_FLAG_REGISTERED))
@@ -676,15 +679,15 @@ void qla_nvme_delete(struct scsi_qla_host *vha)
 	}
 }
 
-void qla_nvme_register_hba(struct scsi_qla_host *vha)
+int qla_nvme_register_hba(struct scsi_qla_host *vha)
 {
 	struct nvme_fc_port_template *tmpl;
 	struct qla_hw_data *ha;
 	struct nvme_fc_port_info pinfo;
-	int ret;
+	int ret = EINVAL;
 
 	if (!IS_ENABLED(CONFIG_NVME_FC))
-		return;
+		return ret;
 
 	ha = vha->hw;
 	tmpl = &qla_nvme_fc_transport;
@@ -711,7 +714,9 @@ void qla_nvme_register_hba(struct scsi_qla_host *vha)
 	if (ret) {
 		ql_log(ql_log_warn, vha, 0xffff,
 		    "register_localport failed: ret=%x\n", ret);
-		return;
+	} else {
+		vha->nvme_local_port->private = vha;
 	}
-	vha->nvme_local_port->private = vha;
+
+	return ret;
 }
diff --git a/drivers/scsi/qla2xxx/qla_nvme.h b/drivers/scsi/qla2xxx/qla_nvme.h
index 816854ada654..4941d107fb1c 100644
--- a/drivers/scsi/qla2xxx/qla_nvme.h
+++ b/drivers/scsi/qla2xxx/qla_nvme.h
@@ -142,7 +142,7 @@ struct pt_ls4_rx_unsol {
 /*
  * Global functions prototype in qla_nvme.c source file.
  */
-void qla_nvme_register_hba(struct scsi_qla_host *);
+int qla_nvme_register_hba(struct scsi_qla_host *);
 int  qla_nvme_register_remote(struct scsi_qla_host *, struct fc_port *);
 void qla_nvme_delete(struct scsi_qla_host *);
 void qla_nvme_abort(struct qla_hw_data *, struct srb *sp, int res);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index 48d1003c8178..15b63136961c 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -4789,7 +4789,6 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 	struct qlt_plogi_ack_t *pla =
 	    (struct qlt_plogi_ack_t *)e->u.new_sess.pla;
 	uint8_t free_fcport = 0;
-	u64 wwn;
 
 	ql_dbg(ql_dbg_disc, vha, 0xffff,
 	    "%s %d %8phC enter\n",
@@ -4817,10 +4816,10 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 			fcport->d_id = e->u.new_sess.id;
 			fcport->flags |= FCF_FABRIC_DEVICE;
 			fcport->fw_login_state = DSC_LS_PLOGI_PEND;
-			if (e->u.new_sess.fc4_type & FS_FC4TYPE_FCP)
+			if (e->u.new_sess.fc4_type == FS_FC4TYPE_FCP)
 				fcport->fc4_type = FC4_TYPE_FCP_SCSI;
 
-			if (e->u.new_sess.fc4_type & FS_FC4TYPE_NVME) {
+			if (e->u.new_sess.fc4_type == FS_FC4TYPE_NVME) {
 				fcport->fc4_type = FC4_TYPE_OTHER;
 				fcport->fc4f_nvme = FC4_TYPE_NVME;
 			}
@@ -4862,9 +4861,6 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 	spin_unlock_irqrestore(&vha->hw->tgt.sess_lock, flags);
 
 	if (fcport) {
-		if (N2N_TOPO(vha->hw))
-			fcport->flags &= ~FCF_FABRIC_DEVICE;
-
 		fcport->id_changed = 1;
 		fcport->scan_state = QLA_FCPORT_FOUND;
 		memcpy(fcport->node_name, e->u.new_sess.node_name, WWN_SIZE);
@@ -4925,12 +4921,22 @@ void qla24xx_create_new_sess(struct scsi_qla_host *vha, struct qla_work_evt *e)
 			if (dfcp)
 				qlt_schedule_sess_for_deletion(tfcp);
 
-			wwn = wwn_to_u64(fcport->node_name);
 
-			if (!wwn)
-				qla24xx_async_gnnid(vha, fcport);
-			else
-				qla24xx_async_gnl(vha, fcport);
+			if (N2N_TOPO(vha->hw))
+				fcport->flags &= ~FCF_FABRIC_DEVICE;
+
+			if (N2N_TOPO(vha->hw)) {
+				if (vha->flags.nvme_enabled) {
+					fcport->fc4f_nvme = 1;
+					fcport->n2n_flag = 1;
+				}
+				fcport->fw_login_state = 0;
+				/*
+				 * wait link init done before sending login
+				 */
+			} else {
+				qla24xx_fcport_handle_login(vha, fcport);
+			}
 		}
 	}
 
@@ -5065,6 +5071,10 @@ qla2x00_do_work(struct scsi_qla_host *vha)
 		case QLA_EVT_IIDMA:
 			qla_do_iidma_work(vha, e->u.fcport.fcport);
 			break;
+		case QLA_EVT_ELS_PLOGI:
+			qla24xx_els_dcmd2_iocb(vha, ELS_DCMD_PLOGI,
+			    e->u.fcport.fcport, false);
+			break;
 		}
 		if (e->flags & QLA_EVT_FLAG_FREE)
 			kfree(e);
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index f71ec94acc3b..e03d12a5f986 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -1619,9 +1619,6 @@ static void tcm_qla2xxx_update_sess(struct fc_port *sess, port_id_t s_id,
 
 	sess->conf_compl_supported = conf_compl_supported;
 
-	/* Reset logout parameters to default */
-	sess->logout_on_delete = 1;
-	sess->keep_nport_handle = 0;
 }
 
 /*
-- 
cgit v1.2.3


From dc0aa99258813b1e8b567e20bb50ed4a931a848a Mon Sep 17 00:00:00 2001
From: Himanshu Madhani <himanshu.madhani@cavium.com>
Date: Thu, 2 Aug 2018 13:16:58 -0700
Subject: scsi: qla2xxx: Update driver version to 10.00.00.08-k

Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_version.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/qla2xxx/qla_version.h b/drivers/scsi/qla2xxx/qla_version.h
index 1ad7582220c3..3850b28518e5 100644
--- a/drivers/scsi/qla2xxx/qla_version.h
+++ b/drivers/scsi/qla2xxx/qla_version.h
@@ -7,7 +7,7 @@
 /*
  * Driver version
  */
-#define QLA2XXX_VERSION      "10.00.00.07-k"
+#define QLA2XXX_VERSION      "10.00.00.08-k"
 
 #define QLA_DRIVER_MAJOR_VER	10
 #define QLA_DRIVER_MINOR_VER	0
-- 
cgit v1.2.3


From 54f8a7ae7c210382a3037887a9831462741ae0db Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 31 Jul 2018 12:51:46 -0700
Subject: ide-cd: Drop unused sense buffers

This drops unused sense buffers from:

	cdrom_eject()
	cdrom_read_capacity()
	cdrom_read_tocentry()
	ide_cd_lockdoor()
	ide_cd_read_toc()

Acked-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ide/ide-cd.c       | 36 +++++++++++++++---------------------
 drivers/ide/ide-cd.h       |  2 +-
 drivers/ide/ide-cd_ioctl.c | 34 ++++++++++++----------------------
 3 files changed, 28 insertions(+), 44 deletions(-)

diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index 5f178384876f..a37dd381d307 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -890,8 +890,7 @@ int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
 }
 
 static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
-			       unsigned long *sectors_per_frame,
-			       struct request_sense *sense)
+			       unsigned long *sectors_per_frame)
 {
 	struct {
 		__be32 lba;
@@ -908,7 +907,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 	memset(cmd, 0, BLK_MAX_CDB);
 	cmd[0] = GPCMD_READ_CDVD_CAPACITY;
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, sense, 0,
+	stat = ide_cd_queue_pc(drive, cmd, 0, &capbuf, &len, NULL, 0,
 			       RQF_QUIET);
 	if (stat)
 		return stat;
@@ -944,8 +943,7 @@ static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
 }
 
 static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
-				int format, char *buf, int buflen,
-				struct request_sense *sense)
+				int format, char *buf, int buflen)
 {
 	unsigned char cmd[BLK_MAX_CDB];
 
@@ -962,11 +960,11 @@ static int cdrom_read_tocentry(ide_drive_t *drive, int trackno, int msf_flag,
 	if (msf_flag)
 		cmd[1] = 2;
 
-	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, buf, &buflen, NULL, 0, RQF_QUIET);
 }
 
 /* Try to read the entire TOC for the disk into our internal buffer. */
-int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
+int ide_cd_read_toc(ide_drive_t *drive)
 {
 	int stat, ntracks, i;
 	struct cdrom_info *info = drive->driver_data;
@@ -996,14 +994,13 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	 * Check to see if the existing data is still valid. If it is,
 	 * just return.
 	 */
-	(void) cdrom_check_status(drive, sense);
+	(void) cdrom_check_status(drive, NULL);
 
 	if (drive->atapi_flags & IDE_AFLAG_TOC_VALID)
 		return 0;
 
 	/* try to get the total cdrom capacity and sector size */
-	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame,
-				   sense);
+	stat = cdrom_read_capacity(drive, &toc->capacity, &sectors_per_frame);
 	if (stat)
 		toc->capacity = 0x1fffff;
 
@@ -1016,7 +1013,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 
 	/* first read just the header, so we know how long the TOC is */
 	stat = cdrom_read_tocentry(drive, 0, 1, 0, (char *) &toc->hdr,
-				    sizeof(struct atapi_toc_header), sense);
+				    sizeof(struct atapi_toc_header));
 	if (stat)
 		return stat;
 
@@ -1036,7 +1033,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 				  (char *)&toc->hdr,
 				   sizeof(struct atapi_toc_header) +
 				   (ntracks + 1) *
-				   sizeof(struct atapi_toc_entry), sense);
+				   sizeof(struct atapi_toc_entry));
 
 	if (stat && toc->hdr.first_track > 1) {
 		/*
@@ -1056,8 +1053,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 					   (char *)&toc->hdr,
 					   sizeof(struct atapi_toc_header) +
 					   (ntracks + 1) *
-					   sizeof(struct atapi_toc_entry),
-					   sense);
+					   sizeof(struct atapi_toc_entry));
 		if (stat)
 			return stat;
 
@@ -1094,7 +1090,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (toc->hdr.first_track != CDROM_LEADOUT) {
 		/* read the multisession information */
 		stat = cdrom_read_tocentry(drive, 0, 0, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1108,7 +1104,7 @@ int ide_cd_read_toc(ide_drive_t *drive, struct request_sense *sense)
 	if (drive->atapi_flags & IDE_AFLAG_TOCADDR_AS_BCD) {
 		/* re-read multisession information using MSF format */
 		stat = cdrom_read_tocentry(drive, 0, 1, 1, (char *)&ms_tmp,
-					   sizeof(ms_tmp), sense);
+					   sizeof(ms_tmp));
 		if (stat)
 			return stat;
 
@@ -1412,7 +1408,7 @@ static sector_t ide_cdrom_capacity(ide_drive_t *drive)
 {
 	unsigned long capacity, sectors_per_frame;
 
-	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame, NULL))
+	if (cdrom_read_capacity(drive, &capacity, &sectors_per_frame))
 		return 0;
 
 	return capacity * sectors_per_frame;
@@ -1710,9 +1706,8 @@ static unsigned int idecd_check_events(struct gendisk *disk,
 static int idecd_revalidate_disk(struct gendisk *disk)
 {
 	struct cdrom_info *info = ide_drv_g(disk, cdrom_info);
-	struct request_sense sense;
 
-	ide_cd_read_toc(info->drive, &sense);
+	ide_cd_read_toc(info->drive);
 
 	return  0;
 }
@@ -1736,7 +1731,6 @@ static int ide_cd_probe(ide_drive_t *drive)
 {
 	struct cdrom_info *info;
 	struct gendisk *g;
-	struct request_sense sense;
 
 	ide_debug_log(IDE_DBG_PROBE, "driver_req: %s, media: 0x%x",
 				     drive->driver_req, drive->media);
@@ -1785,7 +1779,7 @@ static int ide_cd_probe(ide_drive_t *drive)
 		goto failed;
 	}
 
-	ide_cd_read_toc(drive, &sense);
+	ide_cd_read_toc(drive);
 	g->fops = &idecd_ops;
 	g->flags |= GENHD_FL_REMOVABLE | GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE;
 	device_add_disk(&drive->gendev, g);
diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h
index 04f0f310a856..fc162fbb6629 100644
--- a/drivers/ide/ide-cd.h
+++ b/drivers/ide/ide-cd.h
@@ -99,7 +99,7 @@ void ide_cd_log_error(const char *, struct request *, struct request_sense *);
 /* ide-cd.c functions used by ide-cd_ioctl.c */
 int ide_cd_queue_pc(ide_drive_t *, const unsigned char *, int, void *,
 		    unsigned *, struct request_sense *, int, req_flags_t);
-int ide_cd_read_toc(ide_drive_t *, struct request_sense *);
+int ide_cd_read_toc(ide_drive_t *);
 int ide_cdrom_get_capabilities(ide_drive_t *, u8 *);
 void ide_cdrom_update_speed(ide_drive_t *, u8 *);
 int cdrom_check_status(ide_drive_t *, struct request_sense *);
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index b1322400887b..14540544413c 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -105,8 +105,7 @@ unsigned int ide_cdrom_check_events_real(struct cdrom_device_info *cdi,
 /* Eject the disk if EJECTFLAG is 0.
    If EJECTFLAG is 1, try to reload the disk. */
 static
-int cdrom_eject(ide_drive_t *drive, int ejectflag,
-		struct request_sense *sense)
+int cdrom_eject(ide_drive_t *drive, int ejectflag)
 {
 	struct cdrom_info *cd = drive->driver_data;
 	struct cdrom_device_info *cdi = &cd->devinfo;
@@ -129,20 +128,16 @@ int cdrom_eject(ide_drive_t *drive, int ejectflag,
 	cmd[0] = GPCMD_START_STOP_UNIT;
 	cmd[4] = loej | (ejectflag != 0);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 /* Lock the door if LOCKFLAG is nonzero; unlock it otherwise. */
 static
-int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
-		    struct request_sense *sense)
+int ide_cd_lockdoor(ide_drive_t *drive, int lockflag)
 {
-	struct request_sense my_sense;
+	struct request_sense my_sense, *sense = &my_sense;
 	int stat;
 
-	if (sense == NULL)
-		sense = &my_sense;
-
 	/* If the drive cannot lock the door, just pretend. */
 	if ((drive->dev_flags & IDE_DFLAG_DOORLOCKING) == 0) {
 		stat = 0;
@@ -186,23 +181,22 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag,
 int ide_cdrom_tray_move(struct cdrom_device_info *cdi, int position)
 {
 	ide_drive_t *drive = cdi->handle;
-	struct request_sense sense;
 
 	if (position) {
-		int stat = ide_cd_lockdoor(drive, 0, &sense);
+		int stat = ide_cd_lockdoor(drive, 0);
 
 		if (stat)
 			return stat;
 	}
 
-	return cdrom_eject(drive, !position, &sense);
+	return cdrom_eject(drive, !position);
 }
 
 int ide_cdrom_lock_door(struct cdrom_device_info *cdi, int lock)
 {
 	ide_drive_t *drive = cdi->handle;
 
-	return ide_cd_lockdoor(drive, lock, NULL);
+	return ide_cd_lockdoor(drive, lock);
 }
 
 /*
@@ -213,7 +207,6 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	u8 buf[ATAPI_CAPABILITIES_PAGE_SIZE];
 	int stat;
 	unsigned char cmd[BLK_MAX_CDB];
@@ -236,7 +229,7 @@ int ide_cdrom_select_speed(struct cdrom_device_info *cdi, int speed)
 		cmd[5] = speed & 0xff;
 	}
 
-	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 
 	if (!ide_cdrom_get_capabilities(drive, buf)) {
 		ide_cdrom_update_speed(drive, buf);
@@ -252,11 +245,10 @@ int ide_cdrom_get_last_session(struct cdrom_device_info *cdi,
 	struct atapi_toc *toc;
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *info = drive->driver_data;
-	struct request_sense sense;
 	int ret;
 
 	if ((drive->atapi_flags & IDE_AFLAG_TOC_VALID) == 0 || !info->toc) {
-		ret = ide_cd_read_toc(drive, &sense);
+		ret = ide_cd_read_toc(drive);
 		if (ret)
 			return ret;
 	}
@@ -300,7 +292,6 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct cdrom_info *cd = drive->driver_data;
-	struct request_sense sense;
 	struct request *rq;
 	int ret;
 
@@ -315,7 +306,7 @@ int ide_cdrom_reset(struct cdrom_device_info *cdi)
 	 * lock it again.
 	 */
 	if (drive->atapi_flags & IDE_AFLAG_DOOR_LOCKED)
-		(void)ide_cd_lockdoor(drive, 1, &sense);
+		(void)ide_cd_lockdoor(drive, 1);
 
 	return ret;
 }
@@ -355,7 +346,6 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	struct atapi_toc_entry *first_toc, *last_toc;
 	unsigned long lba_start, lba_end;
 	int stat;
-	struct request_sense sense;
 	unsigned char cmd[BLK_MAX_CDB];
 
 	stat = ide_cd_get_toc_entry(drive, ti->cdti_trk0, &first_toc);
@@ -380,7 +370,7 @@ static int ide_cd_fake_play_trkind(ide_drive_t *drive, void *arg)
 	lba_to_msf(lba_start,   &cmd[3], &cmd[4], &cmd[5]);
 	lba_to_msf(lba_end - 1, &cmd[6], &cmd[7], &cmd[8]);
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, &sense, 0, 0);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, NULL, 0, 0);
 }
 
 static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
@@ -391,7 +381,7 @@ static int ide_cd_read_tochdr(ide_drive_t *drive, void *arg)
 	int stat;
 
 	/* Make sure our saved TOC is valid. */
-	stat = ide_cd_read_toc(drive, NULL);
+	stat = ide_cd_read_toc(drive);
 	if (stat)
 		return stat;
 
-- 
cgit v1.2.3


From 1fd89e4ddcec0c8cae15ddd19980cb944b2baf5d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 31 Jul 2018 12:51:47 -0700
Subject: scsi: cxlflash: Drop unused sense buffers

This removes the unused sense buffer in read_cap16() and write_same16().

Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/scsi/cxlflash/superpipe.c | 8 ++------
 drivers/scsi/cxlflash/vlun.c      | 7 ++-----
 2 files changed, 4 insertions(+), 11 deletions(-)

diff --git a/drivers/scsi/cxlflash/superpipe.c b/drivers/scsi/cxlflash/superpipe.c
index e489d89cbb45..379890c4500b 100644
--- a/drivers/scsi/cxlflash/superpipe.c
+++ b/drivers/scsi/cxlflash/superpipe.c
@@ -339,7 +339,6 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 	struct scsi_sense_hdr sshdr;
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	int retry_cnt = 0;
@@ -348,8 +347,7 @@ static int read_cap16(struct scsi_device *sdev, struct llun_info *lli)
 retry:
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -364,7 +362,7 @@ retry:
 	/* Drop the ioctl read semahpore across lengthy call */
 	up_read(&cfg->ioctl_rwsem);
 	result = scsi_execute(sdev, scsi_cmd, DMA_FROM_DEVICE, cmd_buf,
-			      CMD_BUFSIZE, sense_buf, &sshdr, to, CMD_RETRIES,
+			      CMD_BUFSIZE, NULL, &sshdr, to, CMD_RETRIES,
 			      0, 0, NULL);
 	down_read(&cfg->ioctl_rwsem);
 	rc = check_state(cfg);
@@ -395,7 +393,6 @@ retry:
 					if (retry_cnt++ < 1) {
 						kfree(cmd_buf);
 						kfree(scsi_cmd);
-						kfree(sense_buf);
 						goto retry;
 					}
 				}
@@ -426,7 +423,6 @@ retry:
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 
 	dev_dbg(dev, "%s: maxlba=%lld blklen=%d rc=%d\n",
 		__func__, gli->max_lba, gli->blk_len, rc);
diff --git a/drivers/scsi/cxlflash/vlun.c b/drivers/scsi/cxlflash/vlun.c
index 66e445a17d6c..2c904bf16b65 100644
--- a/drivers/scsi/cxlflash/vlun.c
+++ b/drivers/scsi/cxlflash/vlun.c
@@ -426,7 +426,6 @@ static int write_same16(struct scsi_device *sdev,
 {
 	u8 *cmd_buf = NULL;
 	u8 *scsi_cmd = NULL;
-	u8 *sense_buf = NULL;
 	int rc = 0;
 	int result = 0;
 	u64 offset = lba;
@@ -440,8 +439,7 @@ static int write_same16(struct scsi_device *sdev,
 
 	cmd_buf = kzalloc(CMD_BUFSIZE, GFP_KERNEL);
 	scsi_cmd = kzalloc(MAX_COMMAND_SIZE, GFP_KERNEL);
-	sense_buf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_KERNEL);
-	if (unlikely(!cmd_buf || !scsi_cmd || !sense_buf)) {
+	if (unlikely(!cmd_buf || !scsi_cmd)) {
 		rc = -ENOMEM;
 		goto out;
 	}
@@ -457,7 +455,7 @@ static int write_same16(struct scsi_device *sdev,
 		/* Drop the ioctl read semahpore across lengthy call */
 		up_read(&cfg->ioctl_rwsem);
 		result = scsi_execute(sdev, scsi_cmd, DMA_TO_DEVICE, cmd_buf,
-				      CMD_BUFSIZE, sense_buf, NULL, to,
+				      CMD_BUFSIZE, NULL, NULL, to,
 				      CMD_RETRIES, 0, 0, NULL);
 		down_read(&cfg->ioctl_rwsem);
 		rc = check_state(cfg);
@@ -482,7 +480,6 @@ static int write_same16(struct scsi_device *sdev,
 out:
 	kfree(cmd_buf);
 	kfree(scsi_cmd);
-	kfree(sense_buf);
 	dev_dbg(dev, "%s: returning rc=%d\n", __func__, rc);
 	return rc;
 }
-- 
cgit v1.2.3


From ad80f9703a3de62c48c012af62899b754af087f1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 12:51:48 -0700
Subject: scsi: build scsi_common.o for all scsi passthrough request users

Split scsi_common.o out of SCSI so that non-SCSI users can pull it in
easily for future sense buffer helper usage.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/Makefile      | 2 +-
 drivers/scsi/Makefile | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/Makefile b/drivers/Makefile
index 24cd47014657..a6abd7a856c6 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -76,7 +76,7 @@ obj-$(CONFIG_DMA_SHARED_BUFFER) += dma-buf/
 obj-$(CONFIG_NUBUS)		+= nubus/
 obj-y				+= macintosh/
 obj-$(CONFIG_IDE)		+= ide/
-obj-$(CONFIG_SCSI)		+= scsi/
+obj-y				+= scsi/
 obj-y				+= nvme/
 obj-$(CONFIG_ATA)		+= ata/
 obj-$(CONFIG_TARGET_CORE)	+= target/
diff --git a/drivers/scsi/Makefile b/drivers/scsi/Makefile
index 80aca2456353..768953881c9e 100644
--- a/drivers/scsi/Makefile
+++ b/drivers/scsi/Makefile
@@ -21,6 +21,7 @@ CFLAGS_gdth.o    = # -DDEBUG_GDTH=2 -D__SERIAL__ -D__COM2__ -DGDTH_STATISTICS
 obj-$(CONFIG_PCMCIA)		+= pcmcia/
 
 obj-$(CONFIG_SCSI)		+= scsi_mod.o
+obj-$(CONFIG_BLK_SCSI_REQUEST)	+= scsi_common.o
 
 obj-$(CONFIG_RAID_ATTRS)	+= raid_class.o
 
@@ -156,7 +157,6 @@ obj-$(CONFIG_SCSI_HISI_SAS) += hisi_sas/
 obj-$(CONFIG_SCSI_DEBUG)	+= scsi_debug.o
 scsi_mod-y			+= scsi.o hosts.o scsi_ioctl.o \
 				   scsicam.o scsi_error.o scsi_lib.o
-scsi_mod-y			+= scsi_common.o
 scsi_mod-$(CONFIG_SCSI_CONSTANTS) += constants.o
 scsi_mod-$(CONFIG_SCSI_DMA)	+= scsi_lib_dma.o
 scsi_mod-y			+= scsi_scan.o scsi_sysfs.o scsi_devinfo.o
-- 
cgit v1.2.3


From 8a39a0478355e9dfdd2f35038d07c4ebe3192441 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 31 Jul 2018 12:51:49 -0700
Subject: target: don't depend on SCSI

The core target code only needs code from scsi_common.c, which is now
separately selectable.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/target/Kconfig | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/target/Kconfig b/drivers/target/Kconfig
index 4c44d7bed01a..cb6f32ce7de8 100644
--- a/drivers/target/Kconfig
+++ b/drivers/target/Kconfig
@@ -1,10 +1,10 @@
 
 menuconfig TARGET_CORE
 	tristate "Generic Target Core Mod (TCM) and ConfigFS Infrastructure"
-	depends on SCSI && BLOCK
+	depends on BLOCK
 	select CONFIGFS_FS
 	select CRC_T10DIF
-	select BLK_SCSI_REQUEST # only for scsi_command_size_tbl..
+	select BLK_SCSI_REQUEST
 	select SGL_ALLOC
 	default n
 	help
@@ -29,6 +29,7 @@ config TCM_FILEIO
 
 config TCM_PSCSI
 	tristate "TCM/pSCSI Subsystem Plugin for Linux/SCSI"
+	depends on SCSI
 	help
 	Say Y here to enable the TCM/pSCSI subsystem plugin for non-buffered
 	passthrough access to Linux/SCSI device
-- 
cgit v1.2.3


From e7d0748dd71695b94f3a35c8bdc05226a7f3d919 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Thu, 2 Aug 2018 15:22:13 -0600
Subject: block: Switch struct packet_command to use struct scsi_sense_hdr

There is a lot of needless struct request_sense usage in the CDROM
code. These can all be struct scsi_sense_hdr instead, to avoid any
confusion over their respective structure sizes. This patch is a lot
of noise changing "sense" to "sshdr", but the final code is more
readable to distinguish between "sense" meaning "struct request_sense"
and "sshdr" meaning "struct scsi_sense_hdr".

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/pktcdvd.c    | 36 ++++++++++++++++++------------------
 drivers/cdrom/cdrom.c      | 22 +++++++++++-----------
 drivers/ide/ide-cd.c       | 11 ++++++-----
 drivers/ide/ide-cd.h       |  4 ++--
 drivers/ide/ide-cd_ioctl.c | 30 +++++++++++++++---------------
 drivers/scsi/sr_ioctl.c    | 22 +++++++++-------------
 include/linux/cdrom.h      |  3 ++-
 7 files changed, 63 insertions(+), 65 deletions(-)

diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
index 9bb7721c26fc..e285413d4a75 100644
--- a/drivers/block/pktcdvd.c
+++ b/drivers/block/pktcdvd.c
@@ -748,13 +748,13 @@ static const char *sense_key_string(__u8 index)
 static void pkt_dump_sense(struct pktcdvd_device *pd,
 			   struct packet_command *cgc)
 {
-	struct request_sense *sense = cgc->sense;
+	struct scsi_sense_hdr *sshdr = cgc->sshdr;
 
-	if (sense)
+	if (sshdr)
 		pkt_err(pd, "%*ph - sense %02x.%02x.%02x (%s)\n",
 			CDROM_PACKET_SIZE, cgc->cmd,
-			sense->sense_key, sense->asc, sense->ascq,
-			sense_key_string(sense->sense_key));
+			sshdr->sense_key, sshdr->asc, sshdr->ascq,
+			sense_key_string(sshdr->sense_key));
 	else
 		pkt_err(pd, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
 }
@@ -787,11 +787,11 @@ static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
 				unsigned write_speed, unsigned read_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_SET_SPEED;
 	cgc.cmd[2] = (read_speed >> 8) & 0xff;
 	cgc.cmd[3] = read_speed & 0xff;
@@ -1651,7 +1651,7 @@ static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	write_param_page *wp;
 	char buffer[128];
 	int ret, size;
@@ -1662,7 +1662,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 
 	memset(buffer, 0, sizeof(buffer));
 	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
 	if (ret) {
 		pkt_dump_sense(pd, &cgc);
@@ -1678,7 +1678,7 @@ static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
 	 * now get it all
 	 */
 	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
 	if (ret) {
 		pkt_dump_sense(pd, &cgc);
@@ -1916,12 +1916,12 @@ static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd,
 						int set)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	int ret;
 
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.buflen = pd->mode_offset + 12;
 
 	/*
@@ -1962,14 +1962,14 @@ static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
 						unsigned *write_speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[256+18];
 	unsigned char *cap_buf;
 	int ret, offset;
 
 	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
 	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 
 	ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
 	if (ret) {
@@ -2023,13 +2023,13 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 						unsigned *speed)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	unsigned char buf[64];
 	unsigned int size, st, sp;
 	int ret;
 
 	init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4; /* READ ATIP */
@@ -2044,7 +2044,7 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 		size = sizeof(buf);
 
 	init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
 	cgc.cmd[1] = 2;
 	cgc.cmd[2] = 4;
@@ -2095,13 +2095,13 @@ static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
 static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
 {
 	struct packet_command cgc;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int ret;
 
 	pkt_dbg(2, pd, "Performing OPC\n");
 
 	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sense = &sense;
+	cgc.sshdr = &sshdr;
 	cgc.timeout = 60*HZ;
 	cgc.cmd[0] = GPCMD_SEND_OPC;
 	cgc.cmd[1] = 1;
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index a78b8e7085e9..86619472d916 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -345,10 +345,10 @@ static LIST_HEAD(cdrom_list);
 int cdrom_dummy_generic_packet(struct cdrom_device_info *cdi,
 			       struct packet_command *cgc)
 {
-	if (cgc->sense) {
-		cgc->sense->sense_key = 0x05;
-		cgc->sense->asc = 0x20;
-		cgc->sense->ascq = 0x00;
+	if (cgc->sshdr) {
+		cgc->sshdr->sense_key = 0x05;
+		cgc->sshdr->asc = 0x20;
+		cgc->sshdr->ascq = 0x00;
 	}
 
 	cgc->stat = -EIO;
@@ -2943,7 +2943,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 					      struct packet_command *cgc,
 					      int cmd)
 {
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	struct cdrom_msf msf;
 	int blocksize = 0, format = 0, lba;
 	int ret;
@@ -2971,13 +2971,13 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 	if (cgc->buffer == NULL)
 		return -ENOMEM;
 
-	memset(&sense, 0, sizeof(sense));
-	cgc->sense = &sense;
+	memset(&sshdr, 0, sizeof(sshdr));
+	cgc->sshdr = &sshdr;
 	cgc->data_direction = CGC_DATA_READ;
 	ret = cdrom_read_block(cdi, cgc, lba, 1, format, blocksize);
-	if (ret && sense.sense_key == 0x05 &&
-	    sense.asc == 0x20 &&
-	    sense.ascq == 0x00) {
+	if (ret && sshdr.sense_key == 0x05 &&
+	    sshdr.asc == 0x20 &&
+	    sshdr.ascq == 0x00) {
 		/*
 		 * SCSI-II devices are not required to support
 		 * READ_CD, so let's try switching block size
@@ -2986,7 +2986,7 @@ static noinline int mmc_ioctl_cdrom_read_data(struct cdrom_device_info *cdi,
 		ret = cdrom_switch_blocksize(cdi, blocksize);
 		if (ret)
 			goto out;
-		cgc->sense = NULL;
+		cgc->sshdr = NULL;
 		ret = cdrom_read_cd(cdi, cgc, lba, blocksize, 1);
 		ret |= cdrom_switch_blocksize(cdi, blocksize);
 	}
diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index a37dd381d307..a24cdff01865 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -419,7 +419,7 @@ static void ide_cd_request_sense_fixup(ide_drive_t *drive, struct ide_cmd *cmd)
 
 int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		    int write, void *buffer, unsigned *bufflen,
-		    struct request_sense *sense, int timeout,
+		    struct scsi_sense_hdr *sshdr, int timeout,
 		    req_flags_t rq_flags)
 {
 	struct cdrom_info *info = drive->driver_data;
@@ -456,8 +456,9 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 
 		if (buffer)
 			*bufflen = scsi_req(rq)->resid_len;
-		if (sense)
-			memcpy(sense, scsi_req(rq)->sense, sizeof(*sense));
+		if (sshdr)
+			scsi_normalize_sense(scsi_req(rq)->sense,
+					     scsi_req(rq)->sense_len, sshdr);
 
 		/*
 		 * FIXME: we should probably abort/retry or something in case of
@@ -864,7 +865,7 @@ static void msf_from_bcd(struct atapi_msf *msf)
 	msf->frame  = bcd2bin(msf->frame);
 }
 
-int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
+int cdrom_check_status(ide_drive_t *drive, struct scsi_sense_hdr *sshdr)
 {
 	struct cdrom_info *info = drive->driver_data;
 	struct cdrom_device_info *cdi;
@@ -886,7 +887,7 @@ int cdrom_check_status(ide_drive_t *drive, struct request_sense *sense)
 	 */
 	cmd[7] = cdi->sanyo_slot % 3;
 
-	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sense, 0, RQF_QUIET);
+	return ide_cd_queue_pc(drive, cmd, 0, NULL, NULL, sshdr, 0, RQF_QUIET);
 }
 
 static int cdrom_read_capacity(ide_drive_t *drive, unsigned long *capacity,
diff --git a/drivers/ide/ide-cd.h b/drivers/ide/ide-cd.h
index fc162fbb6629..a69dc7f61c4d 100644
--- a/drivers/ide/ide-cd.h
+++ b/drivers/ide/ide-cd.h
@@ -98,11 +98,11 @@ void ide_cd_log_error(const char *, struct request *, struct request_sense *);
 
 /* ide-cd.c functions used by ide-cd_ioctl.c */
 int ide_cd_queue_pc(ide_drive_t *, const unsigned char *, int, void *,
-		    unsigned *, struct request_sense *, int, req_flags_t);
+		    unsigned *, struct scsi_sense_hdr *, int, req_flags_t);
 int ide_cd_read_toc(ide_drive_t *);
 int ide_cdrom_get_capabilities(ide_drive_t *, u8 *);
 void ide_cdrom_update_speed(ide_drive_t *, u8 *);
-int cdrom_check_status(ide_drive_t *, struct request_sense *);
+int cdrom_check_status(ide_drive_t *, struct scsi_sense_hdr *);
 
 /* ide-cd_ioctl.c */
 int ide_cdrom_open_real(struct cdrom_device_info *, int);
diff --git a/drivers/ide/ide-cd_ioctl.c b/drivers/ide/ide-cd_ioctl.c
index 14540544413c..4a6e1a413ead 100644
--- a/drivers/ide/ide-cd_ioctl.c
+++ b/drivers/ide/ide-cd_ioctl.c
@@ -43,14 +43,14 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 {
 	ide_drive_t *drive = cdi->handle;
 	struct media_event_desc med;
-	struct request_sense sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
 	if (slot_nr != CDSL_CURRENT)
 		return -EINVAL;
 
-	stat = cdrom_check_status(drive, &sense);
-	if (!stat || sense.sense_key == UNIT_ATTENTION)
+	stat = cdrom_check_status(drive, &sshdr);
+	if (!stat || sshdr.sense_key == UNIT_ATTENTION)
 		return CDS_DISC_OK;
 
 	if (!cdrom_get_media_event(cdi, &med)) {
@@ -62,8 +62,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 			return CDS_NO_DISC;
 	}
 
-	if (sense.sense_key == NOT_READY && sense.asc == 0x04
-			&& sense.ascq == 0x04)
+	if (sshdr.sense_key == NOT_READY && sshdr.asc == 0x04
+			&& sshdr.ascq == 0x04)
 		return CDS_DISC_OK;
 
 	/*
@@ -71,8 +71,8 @@ int ide_cdrom_drive_status(struct cdrom_device_info *cdi, int slot_nr)
 	 * just return TRAY_OPEN since ATAPI doesn't provide
 	 * any other way to detect this...
 	 */
-	if (sense.sense_key == NOT_READY) {
-		if (sense.asc == 0x3a && sense.ascq == 1)
+	if (sshdr.sense_key == NOT_READY) {
+		if (sshdr.asc == 0x3a && sshdr.ascq == 1)
 			return CDS_NO_DISC;
 		else
 			return CDS_TRAY_OPEN;
@@ -135,7 +135,7 @@ int cdrom_eject(ide_drive_t *drive, int ejectflag)
 static
 int ide_cd_lockdoor(ide_drive_t *drive, int lockflag)
 {
-	struct request_sense my_sense, *sense = &my_sense;
+	struct scsi_sense_hdr sshdr;
 	int stat;
 
 	/* If the drive cannot lock the door, just pretend. */
@@ -150,14 +150,14 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag)
 		cmd[4] = lockflag ? 1 : 0;
 
 		stat = ide_cd_queue_pc(drive, cmd, 0, NULL, NULL,
-				       sense, 0, 0);
+				       &sshdr, 0, 0);
 	}
 
 	/* If we got an illegal field error, the drive
 	   probably cannot lock the door. */
 	if (stat != 0 &&
-	    sense->sense_key == ILLEGAL_REQUEST &&
-	    (sense->asc == 0x24 || sense->asc == 0x20)) {
+	    sshdr.sense_key == ILLEGAL_REQUEST &&
+	    (sshdr.asc == 0x24 || sshdr.asc == 0x20)) {
 		printk(KERN_ERR "%s: door locking not supported\n",
 			drive->name);
 		drive->dev_flags &= ~IDE_DFLAG_DOORLOCKING;
@@ -165,7 +165,7 @@ int ide_cd_lockdoor(ide_drive_t *drive, int lockflag)
 	}
 
 	/* no medium, that's alright. */
-	if (stat != 0 && sense->sense_key == NOT_READY && sense->asc == 0x3a)
+	if (stat != 0 && sshdr.sense_key == NOT_READY && sshdr.asc == 0x3a)
 		stat = 0;
 
 	if (stat == 0) {
@@ -451,8 +451,8 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	   layer. the packet must be complete, as we do not
 	   touch it at all. */
 
-	if (cgc->sense)
-		memset(cgc->sense, 0, sizeof(struct request_sense));
+	if (cgc->sshdr)
+		memset(cgc->sshdr, 0, sizeof(*cgc->sshdr));
 
 	if (cgc->quiet)
 		flags |= RQF_QUIET;
@@ -460,7 +460,7 @@ int ide_cdrom_packet(struct cdrom_device_info *cdi,
 	cgc->stat = ide_cd_queue_pc(drive, cgc->cmd,
 				    cgc->data_direction == CGC_DATA_WRITE,
 				    cgc->buffer, &len,
-				    cgc->sense, cgc->timeout, flags);
+				    cgc->sshdr, cgc->timeout, flags);
 	if (!cgc->stat)
 		cgc->buflen -= len;
 	return cgc->stat;
diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
index 35fab1e18adc..ffcf902da390 100644
--- a/drivers/scsi/sr_ioctl.c
+++ b/drivers/scsi/sr_ioctl.c
@@ -186,14 +186,13 @@ static int sr_play_trkind(struct cdrom_device_info *cdi,
 int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 {
 	struct scsi_device *SDev;
-	struct scsi_sense_hdr sshdr;
+	struct scsi_sense_hdr local_sshdr, *sshdr = &local_sshdr;
 	int result, err = 0, retries = 0;
-	unsigned char sense_buffer[SCSI_SENSE_BUFFERSIZE], *senseptr = NULL;
 
 	SDev = cd->device;
 
-	if (cgc->sense)
-		senseptr = sense_buffer;
+	if (cgc->sshdr)
+		sshdr = cgc->sshdr;
 
       retry:
 	if (!scsi_block_when_processing_errors(SDev)) {
@@ -202,15 +201,12 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 	}
 
 	result = scsi_execute(SDev, cgc->cmd, cgc->data_direction,
-			      cgc->buffer, cgc->buflen, senseptr, &sshdr,
+			      cgc->buffer, cgc->buflen, NULL, sshdr,
 			      cgc->timeout, IOCTL_RETRIES, 0, 0, NULL);
 
-	if (cgc->sense)
-		memcpy(cgc->sense, sense_buffer, sizeof(*cgc->sense));
-
 	/* Minimal error checking.  Ignore cases we know about, and report the rest. */
 	if (driver_byte(result) != 0) {
-		switch (sshdr.sense_key) {
+		switch (sshdr->sense_key) {
 		case UNIT_ATTENTION:
 			SDev->changed = 1;
 			if (!cgc->quiet)
@@ -221,8 +217,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			err = -ENOMEDIUM;
 			break;
 		case NOT_READY:	/* This happens if there is no disc in drive */
-			if (sshdr.asc == 0x04 &&
-			    sshdr.ascq == 0x01) {
+			if (sshdr->asc == 0x04 &&
+			    sshdr->ascq == 0x01) {
 				/* sense: Logical unit is in process of becoming ready */
 				if (!cgc->quiet)
 					sr_printk(KERN_INFO, cd,
@@ -245,8 +241,8 @@ int sr_do_ioctl(Scsi_CD *cd, struct packet_command *cgc)
 			break;
 		case ILLEGAL_REQUEST:
 			err = -EIO;
-			if (sshdr.asc == 0x20 &&
-			    sshdr.ascq == 0x00)
+			if (sshdr->asc == 0x20 &&
+			    sshdr->ascq == 0x00)
 				/* sense: Invalid command operation code */
 				err = -EDRIVE_CANT_DO_THIS;
 			break;
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index e75dfd1f1dec..528271c60018 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>		/* not really needed, later.. */
 #include <linux/list.h>
+#include <scsi/scsi_common.h>
 #include <uapi/linux/cdrom.h>
 
 struct packet_command
@@ -21,7 +22,7 @@ struct packet_command
 	unsigned char 		*buffer;
 	unsigned int 		buflen;
 	int			stat;
-	struct request_sense	*sense;
+	struct scsi_sense_hdr	*sshdr;
 	unsigned char		data_direction;
 	int			quiet;
 	int			timeout;
-- 
cgit v1.2.3


From 7a6873be1b11517a0c55ab4534e4de54b3e228a3 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 31 Jul 2018 12:51:51 -0700
Subject: ide-cd: Remove redundant sense buffer

This is already able to process the sense buffer, so remove the redundant
parsing during the failure path. This also fixes any possible stale values
since the prior code did not check the sense length.

Acked-by: David S. Miller <davem@davemloft.net>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ide/ide-cd.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/ide/ide-cd.c b/drivers/ide/ide-cd.c
index a24cdff01865..44a7a255ef74 100644
--- a/drivers/ide/ide-cd.c
+++ b/drivers/ide/ide-cd.c
@@ -423,6 +423,7 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 		    req_flags_t rq_flags)
 {
 	struct cdrom_info *info = drive->driver_data;
+	struct scsi_sense_hdr local_sshdr;
 	int retries = 10;
 	bool failed;
 
@@ -430,6 +431,9 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 				  "rq_flags: 0x%x",
 				  cmd[0], write, timeout, rq_flags);
 
+	if (!sshdr)
+		sshdr = &local_sshdr;
+
 	/* start of retry loop */
 	do {
 		struct request *rq;
@@ -456,9 +460,8 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 
 		if (buffer)
 			*bufflen = scsi_req(rq)->resid_len;
-		if (sshdr)
-			scsi_normalize_sense(scsi_req(rq)->sense,
-					     scsi_req(rq)->sense_len, sshdr);
+		scsi_normalize_sense(scsi_req(rq)->sense,
+				     scsi_req(rq)->sense_len, sshdr);
 
 		/*
 		 * FIXME: we should probably abort/retry or something in case of
@@ -470,12 +473,10 @@ int ide_cd_queue_pc(ide_drive_t *drive, const unsigned char *cmd,
 			 * The request failed.  Retry if it was due to a unit
 			 * attention status (usually means media was changed).
 			 */
-			struct request_sense *reqbuf = scsi_req(rq)->sense;
-
-			if (reqbuf->sense_key == UNIT_ATTENTION)
+			if (sshdr->sense_key == UNIT_ATTENTION)
 				cdrom_saw_media_change(drive);
-			else if (reqbuf->sense_key == NOT_READY &&
-				 reqbuf->asc == 4 && reqbuf->ascq != 4) {
+			else if (sshdr->sense_key == NOT_READY &&
+				 sshdr->asc == 4 && sshdr->ascq != 4) {
 				/*
 				 * The drive is in the process of loading
 				 * a disk.  Retry, but wait a little to give
-- 
cgit v1.2.3


From 4e178c17cac07d58df7d31ef6fe10036cfa3883d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 31 Jul 2018 12:51:52 -0700
Subject: cdrom: Use struct scsi_sense_hdr internally

This removes more casts of struct request_sense and uses the standard
struct scsi_sense_hdr instead. This also fixes any possible stale values
since the prior code did not check the sense length.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/Kconfig | 2 +-
 drivers/cdrom/cdrom.c | 8 ++++++--
 2 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index ad9b687a236a..d4913516823f 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -74,12 +74,12 @@ config AMIGA_Z2RAM
 
 config CDROM
 	tristate
+	select BLK_SCSI_REQUEST
 
 config GDROM
 	tristate "SEGA Dreamcast GD-ROM drive"
 	depends on SH_DREAMCAST
 	select CDROM
-	select BLK_SCSI_REQUEST # only for the generic cdrom code
 	help
 	  A standard SEGA Dreamcast comes with a modified CD ROM drive called a
 	  "GD-ROM" by SEGA to signify it is capable of reading special disks
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 86619472d916..113fc6edb2b0 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -282,6 +282,7 @@
 #include <linux/blkdev.h>
 #include <linux/times.h>
 #include <linux/uaccess.h>
+#include <scsi/scsi_common.h>
 #include <scsi/scsi_request.h>
 
 /* used to tell the module to turn on full debugging messages */
@@ -2222,9 +2223,12 @@ static int cdrom_read_cdda_bpc(struct cdrom_device_info *cdi, __u8 __user *ubuf,
 
 		blk_execute_rq(q, cdi->disk, rq, 0);
 		if (scsi_req(rq)->result) {
-			struct request_sense *s = req->sense;
+			struct scsi_sense_hdr sshdr;
+
 			ret = -EIO;
-			cdi->last_sense = s->sense_key;
+			scsi_normalize_sense(req->sense, req->sense_len,
+					     &sshdr);
+			cdi->last_sense = sshdr.sense_key;
 		}
 
 		if (blk_rq_unmap_user(bio))
-- 
cgit v1.2.3


From 429296cc51c4cf145b240a78c8d68545e4d67e4c Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 31 Jul 2018 12:51:53 -0700
Subject: libata-scsi: Move sense buffers onto stack

To support future compile-time sizeof() checks that will be able to
validate the length of sense buffers, this removes the only dynamically
allocated sense buffers in the tree by putting the 96 byte sense buffers
on the stack.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/ata/libata-scsi.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index 6a91d04351d9..d46863e9e300 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -597,8 +597,9 @@ static int ata_get_identity(struct ata_port *ap, struct scsi_device *sdev,
 int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[4], *argbuf = NULL, *sensebuf = NULL;
+	u8 args[4], *argbuf = NULL;
 	int argsize = 0;
 	enum dma_data_direction data_dir;
 	struct scsi_sense_hdr sshdr;
@@ -610,10 +611,7 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 
 	if (args[3]) {
@@ -685,7 +683,6 @@ int ata_cmd_ioctl(struct scsi_device *scsidev, void __user *arg)
 	 && copy_to_user(arg + sizeof(args), argbuf, argsize))
 		rc = -EFAULT;
 error:
-	kfree(sensebuf);
 	kfree(argbuf);
 	return rc;
 }
@@ -704,8 +701,9 @@ error:
 int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 {
 	int rc = 0;
+	u8 sensebuf[SCSI_SENSE_BUFFERSIZE];
 	u8 scsi_cmd[MAX_COMMAND_SIZE];
-	u8 args[7], *sensebuf = NULL;
+	u8 args[7];
 	struct scsi_sense_hdr sshdr;
 	int cmd_result;
 
@@ -715,10 +713,7 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	if (copy_from_user(args, arg, sizeof(args)))
 		return -EFAULT;
 
-	sensebuf = kzalloc(SCSI_SENSE_BUFFERSIZE, GFP_NOIO);
-	if (!sensebuf)
-		return -ENOMEM;
-
+	memset(sensebuf, 0, sizeof(sensebuf));
 	memset(scsi_cmd, 0, sizeof(scsi_cmd));
 	scsi_cmd[0]  = ATA_16;
 	scsi_cmd[1]  = (3 << 1); /* Non-data */
@@ -769,7 +764,6 @@ int ata_task_ioctl(struct scsi_device *scsidev, void __user *arg)
 	}
 
  error:
-	kfree(sensebuf);
 	return rc;
 }
 
-- 
cgit v1.2.3


From 704f83928c8e7da6e06144569efb15dec73278e8 Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 31 Jul 2018 12:51:54 -0700
Subject: scsi: Check sense buffer size at build time

To avoid introducing problems like those fixed in commit f7068114d45e
("sr: pass down correctly sized SCSI sense buffer"), this creates a macro
wrapper for scsi_execute() that verifies the size of the sense buffer
similar to what was done for command string sizes in commit 3756f6401c30
("exec: avoid gcc-8 warning for get_task_comm").

Another solution could be to add a length argument to scsi_execute(),
but this function already takes a lot of arguments and Jens was not fond
of that approach.

Additionally, this moves the SCSI_SENSE_BUFFERSIZE definition into
scsi_device.h, and removes a redundant include for scsi_device.h from
scsi_cmnd.h.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Kees Cook <keescook@chromium.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/scsi/scsi_lib.c    |  6 +++---
 include/scsi/scsi_cmnd.h   |  6 ++----
 include/scsi/scsi_device.h | 14 +++++++++++++-
 3 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 41e9ac9fc138..9cb9a166fa0c 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -238,7 +238,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
 
 
 /**
- * scsi_execute - insert request and wait for the result
+ * __scsi_execute - insert request and wait for the result
  * @sdev:	scsi device
  * @cmd:	scsi command
  * @data_direction: data direction
@@ -255,7 +255,7 @@ void scsi_queue_insert(struct scsi_cmnd *cmd, int reason)
  * Returns the scsi_cmnd result field if a command was executed, or a negative
  * Linux error code if we didn't get that far.
  */
-int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 		 int data_direction, void *buffer, unsigned bufflen,
 		 unsigned char *sense, struct scsi_sense_hdr *sshdr,
 		 int timeout, int retries, u64 flags, req_flags_t rq_flags,
@@ -309,7 +309,7 @@ int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 
 	return ret;
 }
-EXPORT_SYMBOL(scsi_execute);
+EXPORT_SYMBOL(__scsi_execute);
 
 /*
  * Function:    scsi_init_cmd_errh()
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index cae229b5395c..c891ada3c5c2 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -15,8 +15,6 @@
 struct Scsi_Host;
 struct scsi_driver;
 
-#include <scsi/scsi_device.h>
-
 /*
  * MAX_COMMAND_SIZE is:
  * The longest fixed-length SCSI CDB as per the SCSI standard.
@@ -121,11 +119,11 @@ struct scsi_cmnd {
 	struct request *request;	/* The command we are
 				   	   working on */
 
-#define SCSI_SENSE_BUFFERSIZE 	96
 	unsigned char *sense_buffer;
 				/* obtained by REQUEST SENSE when
 				 * CHECK CONDITION is received on original
-				 * command (auto-sense) */
+				 * command (auto-sense). Length must be
+				 * SCSI_SENSE_BUFFERSIZE bytes. */
 
 	/* Low-level done function - can be used by low-level driver to point
 	 *        to completion function.  Not used by mid/upper level code. */
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 4c36af6edd79..202f4d6a4342 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -17,6 +17,8 @@ struct scsi_sense_hdr;
 
 typedef __u64 __bitwise blist_flags_t;
 
+#define SCSI_SENSE_BUFFERSIZE	96
+
 struct scsi_mode_data {
 	__u32	length;
 	__u16	block_descriptor_length;
@@ -426,11 +428,21 @@ extern const char *scsi_device_state_name(enum scsi_device_state);
 extern int scsi_is_sdev_device(const struct device *);
 extern int scsi_is_target_device(const struct device *);
 extern void scsi_sanitize_inquiry_string(unsigned char *s, int len);
-extern int scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
+extern int __scsi_execute(struct scsi_device *sdev, const unsigned char *cmd,
 			int data_direction, void *buffer, unsigned bufflen,
 			unsigned char *sense, struct scsi_sense_hdr *sshdr,
 			int timeout, int retries, u64 flags,
 			req_flags_t rq_flags, int *resid);
+/* Make sure any sense buffer is the correct size. */
+#define scsi_execute(sdev, cmd, data_direction, buffer, bufflen, sense,	\
+		     sshdr, timeout, retries, flags, rq_flags, resid)	\
+({									\
+	BUILD_BUG_ON((sense) != NULL &&					\
+		     sizeof(sense) != SCSI_SENSE_BUFFERSIZE);		\
+	__scsi_execute(sdev, cmd, data_direction, buffer, bufflen,	\
+		       sense, sshdr, timeout, retries, flags, rq_flags,	\
+		       resid);						\
+})
 static inline int scsi_execute_req(struct scsi_device *sdev,
 	const unsigned char *cmd, int data_direction, void *buffer,
 	unsigned bufflen, struct scsi_sense_hdr *sshdr, int timeout,
-- 
cgit v1.2.3


From ae61bac9c470cf546558ea525e7cf6b636f04046 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 1 Aug 2018 01:40:31 +0000
Subject: gpio: pxa: remove set but not used variable 'gpio_offset'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/gpio/gpio-pxa.c: In function "pxa_gpio_probe":
drivers/gpio/gpio-pxa.c:629:35: warning:
 variable "gpio_offset" set but not used [-Wunused-but-set-variable]
  int irq0 = 0, irq1 = 0, irq_mux, gpio_offset = 0;
                                   ^
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Acked-by: Robert Jarzmik <robert.jarzmik@free.fr>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-pxa.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index 99070e2ac3cd..c18712dabf93 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -626,7 +626,7 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	struct pxa_gpio_platform_data *info;
 	void __iomem *gpio_reg_base;
 	int gpio, ret;
-	int irq0 = 0, irq1 = 0, irq_mux, gpio_offset = 0;
+	int irq0 = 0, irq1 = 0, irq_mux;
 
 	pchip = devm_kzalloc(&pdev->dev, sizeof(*pchip), GFP_KERNEL);
 	if (!pchip)
@@ -672,9 +672,6 @@ static int pxa_gpio_probe(struct platform_device *pdev)
 	if (!gpio_reg_base)
 		return -EINVAL;
 
-	if (irq0 > 0)
-		gpio_offset = 2;
-
 	clk = clk_get(&pdev->dev, NULL);
 	if (IS_ERR(clk)) {
 		dev_err(&pdev->dev, "Error %ld to get gpio clock\n",
-- 
cgit v1.2.3


From 9a47249d444d344051c7c0e909fad0e88515a5c2 Mon Sep 17 00:00:00 2001
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
Date: Tue, 31 Jul 2018 21:11:00 +0200
Subject: random: Make crng state queryable

It is very useful to be able to know whether or not get_random_bytes_wait
/ wait_for_random_bytes is going to block or not, or whether plain
get_random_bytes is going to return good randomness or bad randomness.

The particular use case is for mitigating certain attacks in WireGuard.
A handshake packet arrives and is queued up. Elsewhere a worker thread
takes items from the queue and processes them. In replying to these
items, it needs to use some random data, and it has to be good random
data. If we simply block until we can have good randomness, then it's
possible for an attacker to fill the queue up with packets waiting to be
processed. Upon realizing the queue is full, WireGuard will detect that
it's under a denial of service attack, and behave accordingly. A better
approach is just to drop incoming handshake packets if the crng is not
yet initialized.

This patch, therefore, makes that information directly accessible.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 drivers/char/random.c  | 15 +++++++++++++++
 include/linux/random.h |  1 +
 2 files changed, 16 insertions(+)

diff --git a/drivers/char/random.c b/drivers/char/random.c
index 561082d46a82..bf5f99fc36f1 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1663,6 +1663,21 @@ int wait_for_random_bytes(void)
 }
 EXPORT_SYMBOL(wait_for_random_bytes);
 
+/*
+ * Returns whether or not the urandom pool has been seeded and thus guaranteed
+ * to supply cryptographically secure random numbers. This applies to: the
+ * /dev/urandom device, the get_random_bytes function, and the get_random_{u32,
+ * ,u64,int,long} family of functions.
+ *
+ * Returns: true if the urandom pool has been seeded.
+ *          false if the urandom pool has not been seeded.
+ */
+bool rng_is_initialized(void)
+{
+	return crng_ready();
+}
+EXPORT_SYMBOL(rng_is_initialized);
+
 /*
  * Add a callback function that will be invoked when the nonblocking
  * pool is initialised.
diff --git a/include/linux/random.h b/include/linux/random.h
index f1c9bc5cd231..445a0ea4ff49 100644
--- a/include/linux/random.h
+++ b/include/linux/random.h
@@ -36,6 +36,7 @@ extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy;
 
 extern void get_random_bytes(void *buf, int nbytes);
 extern int wait_for_random_bytes(void);
+extern bool rng_is_initialized(void);
 extern int add_random_ready_callback(struct random_ready_callback *rdy);
 extern void del_random_ready_callback(struct random_ready_callback *rdy);
 extern int __must_check get_random_bytes_arch(void *buf, int nbytes);
-- 
cgit v1.2.3


From 9b1dd818095fdec6e4952b8ff5c5da20553c4e09 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:46 -0700
Subject: dt-bindings: net: Fix Broadcom iProc mdio mux driver base address

Modify the base address of the Broadcom iProc MDIO mux driver to
point to the start of the block's register address space.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
index dfe287a5d6f2..dc8aa68dbc60 100644
--- a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
+++ b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
@@ -18,9 +18,9 @@ at- Documentation/devicetree/bindings/net/mdio-mux.txt
 
 
 for example:
-		mdio_mux_iproc: mdio-mux@6602023c {
+		mdio_mux_iproc: mdio-mux@66020000 {
 			compatible = "brcm,mdio-mux-iproc";
-			reg = <0x6602023c 0x14>;
+			reg = <0x66020000 0x250>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-- 
cgit v1.2.3


From 77fefa93bfebe4df44f154f2aa5938e32630d0bf Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:47 -0700
Subject: net: phy: Fix the register offsets in Broadcom iProc mdio mux driver

Modify the register offsets in the Broadcom iProc mdio mux to start
from the top of the register address space.

Earlier, the base address pointed to the end of the block's register
space. The base address will now point to the start of the mdio's
address space. The offsets have been fixed to match this.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 0c5b68e7da51..9b3167054843 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -22,7 +22,7 @@
 #include <linux/mdio-mux.h>
 #include <linux/delay.h>
 
-#define MDIO_PARAM_OFFSET		0x00
+#define MDIO_PARAM_OFFSET		0x23c
 #define MDIO_PARAM_MIIM_CYCLE		29
 #define MDIO_PARAM_INTERNAL_SEL		25
 #define MDIO_PARAM_BUS_ID		22
@@ -30,20 +30,22 @@
 #define MDIO_PARAM_PHY_ID		16
 #define MDIO_PARAM_PHY_DATA		0
 
-#define MDIO_READ_OFFSET		0x04
+#define MDIO_READ_OFFSET		0x240
 #define MDIO_READ_DATA_MASK		0xffff
-#define MDIO_ADDR_OFFSET		0x08
+#define MDIO_ADDR_OFFSET		0x244
 
-#define MDIO_CTRL_OFFSET		0x0C
+#define MDIO_CTRL_OFFSET		0x248
 #define MDIO_CTRL_WRITE_OP		0x1
 #define MDIO_CTRL_READ_OP		0x2
 
-#define MDIO_STAT_OFFSET		0x10
+#define MDIO_STAT_OFFSET		0x24c
 #define MDIO_STAT_DONE			1
 
 #define BUS_MAX_ADDR			32
 #define EXT_BUS_START_ADDR		16
 
+#define MDIO_REG_ADDR_SPACE_SIZE	0x250
+
 struct iproc_mdiomux_desc {
 	void *mux_handle;
 	void __iomem *base;
@@ -169,6 +171,14 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 	md->dev = &pdev->dev;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (res->start & 0xfff) {
+		/* For backward compatibility in case the
+		 * base address is specified with an offset.
+		 */
+		dev_info(&pdev->dev, "fix base address in dt-blob\n");
+		res->start &= ~0xfff;
+		res->end = res->start + MDIO_REG_ADDR_SPACE_SIZE - 1;
+	}
 	md->base = devm_ioremap_resource(&pdev->dev, res);
 	if (IS_ERR(md->base)) {
 		dev_err(&pdev->dev, "failed to ioremap register\n");
-- 
cgit v1.2.3


From 18b872d854dc7256863755ece26828aa1856c13f Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:48 -0700
Subject: arm64: dts: Fix the base address of the Broadcom iProc mdio mux

Modify the base address of the mdio mux driver to point to the
start of the mdio mux block's register address space.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi    | 4 ++--
 arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
index 4057197048dc..1a406a76c86a 100644
--- a/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
+++ b/arch/arm64/boot/dts/broadcom/northstar2/ns2.dtsi
@@ -482,9 +482,9 @@
 			status = "disabled";
 		};
 
-		mdio_mux_iproc: mdio-mux@6602023c {
+		mdio_mux_iproc: mdio-mux@66020000 {
 			compatible = "brcm,mdio-mux-iproc";
-			reg = <0x6602023c 0x14>;
+			reg = <0x66020000 0x250>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 
diff --git a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
index b203152ad67c..a70e8ddbd66f 100644
--- a/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
+++ b/arch/arm64/boot/dts/broadcom/stingray/stingray.dtsi
@@ -278,9 +278,9 @@
 
 		#include "stingray-pinctrl.dtsi"
 
-		mdio_mux_iproc: mdio-mux@2023c {
+		mdio_mux_iproc: mdio-mux@20000 {
 			compatible = "brcm,mdio-mux-iproc";
-			reg = <0x0002023c 0x14>;
+			reg = <0x00020000 0x250>;
 			#address-cells = <1>;
 			#size-cells = <0>;
 
-- 
cgit v1.2.3


From 5634cb2b376cef882435c3acce57d4f429405254 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:49 -0700
Subject: net: phy: Disable external master access in bcm mdio mux driver

Configure the scan control register in the Broadcom iProc
mdio mux driver to disable access to external master.

In some SoC's, the scan control register defaults to an incorrect
value.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 9b3167054843..4a253c28edbc 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -22,6 +22,9 @@
 #include <linux/mdio-mux.h>
 #include <linux/delay.h>
 
+#define MDIO_SCAN_CTRL_OFFSET		0x008
+#define MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR	28
+
 #define MDIO_PARAM_OFFSET		0x23c
 #define MDIO_PARAM_MIIM_CYCLE		29
 #define MDIO_PARAM_INTERNAL_SEL		25
@@ -53,6 +56,16 @@ struct iproc_mdiomux_desc {
 	struct mii_bus *mii_bus;
 };
 
+static void mdio_mux_iproc_config(struct iproc_mdiomux_desc *md)
+{
+	u32 val;
+
+	/* Disable external mdio master access */
+	val = readl(md->base + MDIO_SCAN_CTRL_OFFSET);
+	val |= BIT(MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR);
+	writel(val, md->base + MDIO_SCAN_CTRL_OFFSET);
+}
+
 static int iproc_mdio_wait_for_idle(void __iomem *base, bool result)
 {
 	unsigned int timeout = 1000; /* loop for 1s */
@@ -216,6 +229,8 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 		goto out_register;
 	}
 
+	mdio_mux_iproc_config(md);
+
 	dev_info(md->dev, "iProc mdiomux registered\n");
 	return 0;
 
-- 
cgit v1.2.3


From 0fe2cd564c35ce322830967e24693a36bf30cc7f Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:50 -0700
Subject: net: phy: Use devm api for mdio bus allocation in bcm iproc mdio mux

Use devm_mdiobus_alloc() instead of mdiobus_alloc() in the Broadcom
iProc mdio mux driver.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index 4a253c28edbc..e6146b439b45 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -198,7 +198,7 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 		return PTR_ERR(md->base);
 	}
 
-	md->mii_bus = mdiobus_alloc();
+	md->mii_bus = devm_mdiobus_alloc(&pdev->dev);
 	if (!md->mii_bus) {
 		dev_err(&pdev->dev, "mdiomux bus alloc failed\n");
 		return -ENOMEM;
@@ -217,7 +217,7 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 	rc = mdiobus_register(bus);
 	if (rc) {
 		dev_err(&pdev->dev, "mdiomux registration failed\n");
-		goto out;
+		return rc;
 	}
 
 	platform_set_drvdata(pdev, md);
@@ -236,8 +236,6 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 
 out_register:
 	mdiobus_unregister(bus);
-out:
-	mdiobus_free(bus);
 	return rc;
 }
 
@@ -247,7 +245,6 @@ static int mdio_mux_iproc_remove(struct platform_device *pdev)
 
 	mdio_mux_uninit(md->mux_handle);
 	mdiobus_unregister(md->mii_bus);
-	mdiobus_free(md->mii_bus);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 0d5204abe527b28bd708d503c8116a0b627845b4 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:51 -0700
Subject: dt-bindings: net: Add clock handle to Broadcom iProc mdio mux

Add clock phandle, of the core clock driving the mdio block, as an
optional property to the Broadcom iProc mdio mux.

The clock, when specified, will be used to setup the rate adjust registers
in the mdio to derrive the mdio's operating frequency.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
index dc8aa68dbc60..b58843f29591 100644
--- a/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
+++ b/Documentation/devicetree/bindings/net/brcm,mdio-mux-iproc.txt
@@ -13,6 +13,9 @@ MDIO multiplexer node:
 Every non-ethernet PHY requires a compatible so that it could be probed based
 on this compatible string.
 
+Optional properties:
+- clocks: phandle of the core clock which drives the mdio block.
+
 Additional information regarding generic multiplexer properties can be found
 at- Documentation/devicetree/bindings/net/mdio-mux.txt
 
-- 
cgit v1.2.3


From 56aea577c8c08c9888d805a5ad81def62f89da55 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:52 -0700
Subject: net: phy: Add support to configure clock in Broadcom iProc mdio mux

Add support to configure the internal rate adjust register based on the
core clock supplied through device tree in the Broadcom iProc mdio mux.

The operating frequency of the mdio mux block is 11MHz. This is derrived
by dividing the clock to the mdio mux with the rate adjust register.

In some SoC's the default values of the rate adjust register do not yield
11MHz. These SoC's are required to specify the clock via the device tree
for proper operation.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 41 ++++++++++++++++++++++++++++++++++--
 1 file changed, 39 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index e6146b439b45..c5aae5e3f20f 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -13,7 +13,7 @@
  * You should have received a copy of the GNU General Public License
  * version 2 (GPLv2) along with this source code.
  */
-
+#include <linux/clk.h>
 #include <linux/platform_device.h>
 #include <linux/device.h>
 #include <linux/of_mdio.h>
@@ -22,6 +22,10 @@
 #include <linux/mdio-mux.h>
 #include <linux/delay.h>
 
+#define MDIO_RATE_ADJ_EXT_OFFSET	0x000
+#define MDIO_RATE_ADJ_INT_OFFSET	0x004
+#define MDIO_RATE_ADJ_DIVIDENT_SHIFT	16
+
 #define MDIO_SCAN_CTRL_OFFSET		0x008
 #define MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR	28
 
@@ -49,21 +53,38 @@
 
 #define MDIO_REG_ADDR_SPACE_SIZE	0x250
 
+#define MDIO_OPERATING_FREQUENCY	11000000
+#define MDIO_RATE_ADJ_DIVIDENT		1
+
 struct iproc_mdiomux_desc {
 	void *mux_handle;
 	void __iomem *base;
 	struct device *dev;
 	struct mii_bus *mii_bus;
+	struct clk *core_clk;
 };
 
 static void mdio_mux_iproc_config(struct iproc_mdiomux_desc *md)
 {
+	u32 divisor;
 	u32 val;
 
 	/* Disable external mdio master access */
 	val = readl(md->base + MDIO_SCAN_CTRL_OFFSET);
 	val |= BIT(MDIO_SCAN_CTRL_OVRIDE_EXT_MSTR);
 	writel(val, md->base + MDIO_SCAN_CTRL_OFFSET);
+
+	if (md->core_clk) {
+		/* use rate adjust regs to derrive the mdio's operating
+		 * frequency from the specified core clock
+		 */
+		divisor = clk_get_rate(md->core_clk) / MDIO_OPERATING_FREQUENCY;
+		divisor = divisor / (MDIO_RATE_ADJ_DIVIDENT + 1);
+		val = divisor;
+		val |= MDIO_RATE_ADJ_DIVIDENT << MDIO_RATE_ADJ_DIVIDENT_SHIFT;
+		writel(val, md->base + MDIO_RATE_ADJ_EXT_OFFSET);
+		writel(val, md->base + MDIO_RATE_ADJ_INT_OFFSET);
+	}
 }
 
 static int iproc_mdio_wait_for_idle(void __iomem *base, bool result)
@@ -204,6 +225,19 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	md->core_clk = devm_clk_get(&pdev->dev, NULL);
+	if (md->core_clk == ERR_PTR(-ENOENT) ||
+	    md->core_clk == ERR_PTR(-EINVAL))
+		md->core_clk = NULL;
+	else if (IS_ERR(md->core_clk))
+		return PTR_ERR(md->core_clk);
+
+	rc = clk_prepare_enable(md->core_clk);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to enable core clk\n");
+		return rc;
+	}
+
 	bus = md->mii_bus;
 	bus->priv = md;
 	bus->name = "iProc MDIO mux bus";
@@ -217,7 +251,7 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 	rc = mdiobus_register(bus);
 	if (rc) {
 		dev_err(&pdev->dev, "mdiomux registration failed\n");
-		return rc;
+		goto out_clk;
 	}
 
 	platform_set_drvdata(pdev, md);
@@ -236,6 +270,8 @@ static int mdio_mux_iproc_probe(struct platform_device *pdev)
 
 out_register:
 	mdiobus_unregister(bus);
+out_clk:
+	clk_disable_unprepare(md->core_clk);
 	return rc;
 }
 
@@ -245,6 +281,7 @@ static int mdio_mux_iproc_remove(struct platform_device *pdev)
 
 	mdio_mux_uninit(md->mux_handle);
 	mdiobus_unregister(md->mii_bus);
+	clk_disable_unprepare(md->core_clk);
 
 	return 0;
 }
-- 
cgit v1.2.3


From 2c7230446bc90bc883890007e2a5da60c399e88a Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Wed, 1 Aug 2018 17:53:53 -0700
Subject: net: phy: Add pm support to Broadcom iProc mdio mux driver

Add support for suspend and resume to the Broadcom iProc mdio
mux driver.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/mdio-mux-bcm-iproc.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/net/phy/mdio-mux-bcm-iproc.c b/drivers/net/phy/mdio-mux-bcm-iproc.c
index c5aae5e3f20f..c017486e9b86 100644
--- a/drivers/net/phy/mdio-mux-bcm-iproc.c
+++ b/drivers/net/phy/mdio-mux-bcm-iproc.c
@@ -286,6 +286,32 @@ static int mdio_mux_iproc_remove(struct platform_device *pdev)
 	return 0;
 }
 
+#ifdef CONFIG_PM_SLEEP
+static int mdio_mux_iproc_suspend(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
+
+	clk_disable_unprepare(md->core_clk);
+
+	return 0;
+}
+
+static int mdio_mux_iproc_resume(struct device *dev)
+{
+	struct platform_device *pdev = to_platform_device(dev);
+	struct iproc_mdiomux_desc *md = platform_get_drvdata(pdev);
+
+	clk_prepare_enable(md->core_clk);
+	mdio_mux_iproc_config(md);
+
+	return 0;
+}
+#endif
+
+static SIMPLE_DEV_PM_OPS(mdio_mux_iproc_pm_ops,
+			 mdio_mux_iproc_suspend, mdio_mux_iproc_resume);
+
 static const struct of_device_id mdio_mux_iproc_match[] = {
 	{
 		.compatible = "brcm,mdio-mux-iproc",
@@ -298,6 +324,7 @@ static struct platform_driver mdiomux_iproc_driver = {
 	.driver = {
 		.name		= "mdio-mux-iproc",
 		.of_match_table = mdio_mux_iproc_match,
+		.pm		= &mdio_mux_iproc_pm_ops,
 	},
 	.probe		= mdio_mux_iproc_probe,
 	.remove		= mdio_mux_iproc_remove,
-- 
cgit v1.2.3


From bd34389d4fdb4fe85a4c4a663dcf29c97ea2111a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 18:16:47 +0800
Subject: net: hns: remove redundant variables 'max_frm' and 'tmp_mac_key'

Variables 'max_frm' and 'tmp_mac_key' are being assigned,
but are never used,hence they are redundant and can be removed.

fix fllowing warning:

drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c:461:6: warning: variable 'max_frm' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:1685:31: warning: variable 'tmp_mac_key' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c:1855:41: warning: variable 'tmp_mac_key' set but not used [-Wunused-but-set-variable]

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c  |  5 -----
 drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c | 10 +---------
 2 files changed, 1 insertion(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
index 6e5107d428c7..3545a5d0bc95 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_mac.c
@@ -458,11 +458,6 @@ int hns_mac_set_mtu(struct hns_mac_cb *mac_cb, u32 new_mtu, u32 buf_size)
 {
 	struct mac_driver *drv = hns_mac_get_drv(mac_cb);
 	u32 new_frm = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
-	u32 max_frm = AE_IS_VER1(mac_cb->dsaf_dev->dsaf_ver) ?
-			MAC_MAX_MTU : MAC_MAX_MTU_V2;
-
-	if (mac_cb->mac_type == HNAE_PORT_DEBUG)
-		max_frm = MAC_MAX_MTU_DBG;
 
 	if (new_frm > HNS_RCB_RING_MAX_BD_PER_PKT * buf_size)
 		return -EINVAL;
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
index 619e6ce465c2..ca50c2553a9c 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c
@@ -1683,7 +1683,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 	struct dsaf_tbl_tcam_mcast_cfg mac_data;
 	struct dsaf_drv_priv *priv = hns_dsaf_dev_priv(dsaf_dev);
 	struct dsaf_drv_soft_mac_tbl *soft_mac_entry = priv->soft_mac_tbl;
-	struct dsaf_drv_tbl_tcam_key tmp_mac_key;
 	struct dsaf_tbl_tcam_data tcam_data;
 	u8 mc_addr[ETH_ALEN];
 	int mskid;
@@ -1740,10 +1739,6 @@ int hns_dsaf_add_mac_mc_port(struct dsaf_device *dsaf_dev,
 		/* if exist, add in */
 		hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data,
 				     &mac_data);
-
-		tmp_mac_key.high.val =
-			le32_to_cpu(tcam_data.tbl_tcam_data_high);
-		tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
 	}
 
 	/* config hardware entry */
@@ -1853,7 +1848,7 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 	struct dsaf_tbl_tcam_data tcam_data;
 	int mskid;
 	const u8 empty_msk[sizeof(mac_data.tbl_mcast_port_msk)] = {0};
-	struct dsaf_drv_tbl_tcam_key mask_key, tmp_mac_key;
+	struct dsaf_drv_tbl_tcam_key mask_key;
 	struct dsaf_tbl_tcam_data *pmask_key = NULL;
 	u8 mc_addr[ETH_ALEN];
 
@@ -1916,9 +1911,6 @@ int hns_dsaf_del_mac_mc_port(struct dsaf_device *dsaf_dev,
 	/* read entry */
 	hns_dsaf_tcam_mc_get(dsaf_dev, entry_index, &tcam_data, &mac_data);
 
-	tmp_mac_key.high.val = le32_to_cpu(tcam_data.tbl_tcam_data_high);
-	tmp_mac_key.low.val = le32_to_cpu(tcam_data.tbl_tcam_data_low);
-
 	/*del the port*/
 	if (mac_entry->port_num < DSAF_SERVICE_NW_NUM) {
 		mskid = mac_entry->port_num;
-- 
cgit v1.2.3


From d3e2a25bcd0b24f0905554ef0762eb77cbca7ad5 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 19:31:01 -0500
Subject: xen-netback: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This issue was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Wei Liu <wei.liu2@citrix.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netback/netback.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index a27daa23c9dc..3621e05a7494 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -1603,9 +1603,9 @@ static void xenvif_ctrl_action(struct xenvif *vif)
 static bool xenvif_ctrl_work_todo(struct xenvif *vif)
 {
 	if (likely(RING_HAS_UNCONSUMED_REQUESTS(&vif->ctrl)))
-		return 1;
+		return true;
 
-	return 0;
+	return false;
 }
 
 irqreturn_t xenvif_ctrl_irq_fn(int irq, void *data)
-- 
cgit v1.2.3


From e9340c9205c3b1cea8f1b799b5f8e034d6e3e000 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 31 Jul 2018 17:37:16 +0300
Subject: MAINTAINERS: Replace Heikki as maintainer of Intel pinctrl

Heikki has another priorities and no time to maintain Intel pinctrl
driver. As we decided off line I'm going to replace him.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 9d5eeff51b5f..6fcf510e77a1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11249,7 +11249,7 @@ F:	Documentation/devicetree/bindings/pinctrl/fsl,*
 
 PIN CONTROLLER - INTEL
 M:	Mika Westerberg <mika.westerberg@linux.intel.com>
-M:	Heikki Krogerus <heikki.krogerus@linux.intel.com>
+M:	Andy Shevchenko <andriy.shevchenko@linux.intel.com>
 S:	Maintained
 F:	drivers/pinctrl/intel/
 
-- 
cgit v1.2.3


From 6b431d50d2a8acd1c418b998b856a055252ebc3a Mon Sep 17 00:00:00 2001
From: Matthieu Baerts <matthieu.baerts@tessares.net>
Date: Thu, 2 Aug 2018 18:14:33 +0200
Subject: net/socket: remove duplicated init code

This refactoring work has been started by David Howells in cdfbabfb2f0c
(net: Work around lockdep limitation in sockets that use sockets) but
the exact same day in 581319c58600 (net/socket: use per af lockdep
classes for sk queues), Paolo Abeni added new classes.

This reduces the amount of (nearly) duplicated code and eases the
addition of new socket types.

Signed-off-by: Matthieu Baerts <matthieu.baerts@tessares.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock.c | 51 +++------------------------------------------------
 1 file changed, 3 insertions(+), 48 deletions(-)

diff --git a/net/core/sock.c b/net/core/sock.c
index 9c6ebbdfebf3..e31233f5ba39 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -250,58 +250,13 @@ static const char *const af_family_kern_clock_key_strings[AF_MAX+1] = {
 	_sock_locks("k-clock-")
 };
 static const char *const af_family_rlock_key_strings[AF_MAX+1] = {
-  "rlock-AF_UNSPEC", "rlock-AF_UNIX"     , "rlock-AF_INET"     ,
-  "rlock-AF_AX25"  , "rlock-AF_IPX"      , "rlock-AF_APPLETALK",
-  "rlock-AF_NETROM", "rlock-AF_BRIDGE"   , "rlock-AF_ATMPVC"   ,
-  "rlock-AF_X25"   , "rlock-AF_INET6"    , "rlock-AF_ROSE"     ,
-  "rlock-AF_DECnet", "rlock-AF_NETBEUI"  , "rlock-AF_SECURITY" ,
-  "rlock-AF_KEY"   , "rlock-AF_NETLINK"  , "rlock-AF_PACKET"   ,
-  "rlock-AF_ASH"   , "rlock-AF_ECONET"   , "rlock-AF_ATMSVC"   ,
-  "rlock-AF_RDS"   , "rlock-AF_SNA"      , "rlock-AF_IRDA"     ,
-  "rlock-AF_PPPOX" , "rlock-AF_WANPIPE"  , "rlock-AF_LLC"      ,
-  "rlock-27"       , "rlock-28"          , "rlock-AF_CAN"      ,
-  "rlock-AF_TIPC"  , "rlock-AF_BLUETOOTH", "rlock-AF_IUCV"     ,
-  "rlock-AF_RXRPC" , "rlock-AF_ISDN"     , "rlock-AF_PHONET"   ,
-  "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG"      ,
-  "rlock-AF_NFC"   , "rlock-AF_VSOCK"    , "rlock-AF_KCM"      ,
-  "rlock-AF_QIPCRTR", "rlock-AF_SMC"     , "rlock-AF_XDP"      ,
-  "rlock-AF_MAX"
+	_sock_locks("rlock-")
 };
 static const char *const af_family_wlock_key_strings[AF_MAX+1] = {
-  "wlock-AF_UNSPEC", "wlock-AF_UNIX"     , "wlock-AF_INET"     ,
-  "wlock-AF_AX25"  , "wlock-AF_IPX"      , "wlock-AF_APPLETALK",
-  "wlock-AF_NETROM", "wlock-AF_BRIDGE"   , "wlock-AF_ATMPVC"   ,
-  "wlock-AF_X25"   , "wlock-AF_INET6"    , "wlock-AF_ROSE"     ,
-  "wlock-AF_DECnet", "wlock-AF_NETBEUI"  , "wlock-AF_SECURITY" ,
-  "wlock-AF_KEY"   , "wlock-AF_NETLINK"  , "wlock-AF_PACKET"   ,
-  "wlock-AF_ASH"   , "wlock-AF_ECONET"   , "wlock-AF_ATMSVC"   ,
-  "wlock-AF_RDS"   , "wlock-AF_SNA"      , "wlock-AF_IRDA"     ,
-  "wlock-AF_PPPOX" , "wlock-AF_WANPIPE"  , "wlock-AF_LLC"      ,
-  "wlock-27"       , "wlock-28"          , "wlock-AF_CAN"      ,
-  "wlock-AF_TIPC"  , "wlock-AF_BLUETOOTH", "wlock-AF_IUCV"     ,
-  "wlock-AF_RXRPC" , "wlock-AF_ISDN"     , "wlock-AF_PHONET"   ,
-  "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG"      ,
-  "wlock-AF_NFC"   , "wlock-AF_VSOCK"    , "wlock-AF_KCM"      ,
-  "wlock-AF_QIPCRTR", "wlock-AF_SMC"     , "wlock-AF_XDP"      ,
-  "wlock-AF_MAX"
+	_sock_locks("wlock-")
 };
 static const char *const af_family_elock_key_strings[AF_MAX+1] = {
-  "elock-AF_UNSPEC", "elock-AF_UNIX"     , "elock-AF_INET"     ,
-  "elock-AF_AX25"  , "elock-AF_IPX"      , "elock-AF_APPLETALK",
-  "elock-AF_NETROM", "elock-AF_BRIDGE"   , "elock-AF_ATMPVC"   ,
-  "elock-AF_X25"   , "elock-AF_INET6"    , "elock-AF_ROSE"     ,
-  "elock-AF_DECnet", "elock-AF_NETBEUI"  , "elock-AF_SECURITY" ,
-  "elock-AF_KEY"   , "elock-AF_NETLINK"  , "elock-AF_PACKET"   ,
-  "elock-AF_ASH"   , "elock-AF_ECONET"   , "elock-AF_ATMSVC"   ,
-  "elock-AF_RDS"   , "elock-AF_SNA"      , "elock-AF_IRDA"     ,
-  "elock-AF_PPPOX" , "elock-AF_WANPIPE"  , "elock-AF_LLC"      ,
-  "elock-27"       , "elock-28"          , "elock-AF_CAN"      ,
-  "elock-AF_TIPC"  , "elock-AF_BLUETOOTH", "elock-AF_IUCV"     ,
-  "elock-AF_RXRPC" , "elock-AF_ISDN"     , "elock-AF_PHONET"   ,
-  "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG"      ,
-  "elock-AF_NFC"   , "elock-AF_VSOCK"    , "elock-AF_KCM"      ,
-  "elock-AF_QIPCRTR", "elock-AF_SMC"     , "elock-AF_XDP"      ,
-  "elock-AF_MAX"
+	_sock_locks("elock-")
 };
 
 /*
-- 
cgit v1.2.3


From f1b1eabff0eb3fc46b06668de8174c0f23b271fd Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Thu, 5 Jul 2018 18:59:36 -0400
Subject: media: dvb: represent min/max/step/tolerance freqs in Hz

Right now, satellite frontend drivers specify frequencies in kHz,
while terrestrial/cable ones specify in Hz. That's confusing
for developers.

However, the main problem is that universal frontends capable
of handling both satellite and non-satelite delivery systems
are appearing. We end by needing to hack the drivers in
order to support such hybrid frontends.

So, convert everything to specify frontend frequencies in Hz.

Tested-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/common/siano/smsdvb-main.c          |  6 +-
 drivers/media/dvb-core/dvb_frontend.c             | 84 ++++++++++++++++-------
 drivers/media/dvb-frontends/af9013.c              |  7 +-
 drivers/media/dvb-frontends/af9033.c              |  7 +-
 drivers/media/dvb-frontends/as102_fe.c            |  6 +-
 drivers/media/dvb-frontends/atbm8830.c            |  6 +-
 drivers/media/dvb-frontends/au8522_dig.c          |  6 +-
 drivers/media/dvb-frontends/bcm3510.c             |  6 +-
 drivers/media/dvb-frontends/cx22700.c             |  6 +-
 drivers/media/dvb-frontends/cx22702.c             |  6 +-
 drivers/media/dvb-frontends/cx24110.c             |  8 +--
 drivers/media/dvb-frontends/cx24116.c             |  8 +--
 drivers/media/dvb-frontends/cx24117.c             |  8 +--
 drivers/media/dvb-frontends/cx24120.c             |  8 +--
 drivers/media/dvb-frontends/cx24123.c             |  8 +--
 drivers/media/dvb-frontends/cxd2820r_t.c          |  4 +-
 drivers/media/dvb-frontends/cxd2820r_t2.c         |  4 +-
 drivers/media/dvb-frontends/cxd2841er.c           |  9 ++-
 drivers/media/dvb-frontends/cxd2880/cxd2880_top.c |  6 +-
 drivers/media/dvb-frontends/dib3000mb.c           |  6 +-
 drivers/media/dvb-frontends/dib3000mc.c           |  6 +-
 drivers/media/dvb-frontends/dib7000m.c            |  6 +-
 drivers/media/dvb-frontends/dib7000p.c            |  6 +-
 drivers/media/dvb-frontends/dib8000.c             |  6 +-
 drivers/media/dvb-frontends/dib9000.c             |  6 +-
 drivers/media/dvb-frontends/drx39xyj/drxj.c       |  6 +-
 drivers/media/dvb-frontends/drxd_hard.c           |  7 +-
 drivers/media/dvb-frontends/drxk_hard.c           |  8 +--
 drivers/media/dvb-frontends/ds3000.c              |  8 +--
 drivers/media/dvb-frontends/dvb_dummy_fe.c        | 24 +++----
 drivers/media/dvb-frontends/gp8psk-fe.c           |  6 +-
 drivers/media/dvb-frontends/ix2505v.c             |  4 +-
 drivers/media/dvb-frontends/l64781.c              |  7 +-
 drivers/media/dvb-frontends/lg2160.c              | 12 ++--
 drivers/media/dvb-frontends/lgdt3305.c            | 12 ++--
 drivers/media/dvb-frontends/lgdt3306a.c           |  6 +-
 drivers/media/dvb-frontends/lgdt330x.c            | 12 ++--
 drivers/media/dvb-frontends/lgs8gl5.c             |  7 +-
 drivers/media/dvb-frontends/lgs8gxx.c             |  6 +-
 drivers/media/dvb-frontends/m88ds3103.c           |  6 +-
 drivers/media/dvb-frontends/m88rs2000.c           |  8 +--
 drivers/media/dvb-frontends/mb86a16.c             |  7 +-
 drivers/media/dvb-frontends/mb86a20s.c            |  6 +-
 drivers/media/dvb-frontends/mt312.c               | 10 +--
 drivers/media/dvb-frontends/mt352.c               |  7 +-
 drivers/media/dvb-frontends/mxl5xx.c              |  6 +-
 drivers/media/dvb-frontends/nxt200x.c             |  6 +-
 drivers/media/dvb-frontends/nxt6000.c             |  6 +-
 drivers/media/dvb-frontends/or51132.c             |  6 +-
 drivers/media/dvb-frontends/or51211.c             |  8 +--
 drivers/media/dvb-frontends/rtl2830.c             |  4 +-
 drivers/media/dvb-frontends/rtl2832.c             | 10 +--
 drivers/media/dvb-frontends/s5h1409.c             |  6 +-
 drivers/media/dvb-frontends/s5h1411.c             |  6 +-
 drivers/media/dvb-frontends/s5h1420.c             |  8 +--
 drivers/media/dvb-frontends/s5h1432.c             |  6 +-
 drivers/media/dvb-frontends/s921.c                |  7 +-
 drivers/media/dvb-frontends/si2165.c              |  2 +-
 drivers/media/dvb-frontends/si21xx.c              |  7 +-
 drivers/media/dvb-frontends/sp8870.c              |  6 +-
 drivers/media/dvb-frontends/sp887x.c              |  6 +-
 drivers/media/dvb-frontends/stb0899_drv.c         |  6 +-
 drivers/media/dvb-frontends/stv0288.c             |  7 +-
 drivers/media/dvb-frontends/stv0297.c             |  6 +-
 drivers/media/dvb-frontends/stv0299.c             |  7 +-
 drivers/media/dvb-frontends/stv0367.c             | 20 +++---
 drivers/media/dvb-frontends/stv0900_core.c        |  7 +-
 drivers/media/dvb-frontends/stv090x.c             |  6 +-
 drivers/media/dvb-frontends/stv0910.c             |  6 +-
 drivers/media/dvb-frontends/tc90522.c             | 10 +--
 drivers/media/dvb-frontends/tda10021.c            | 10 +--
 drivers/media/dvb-frontends/tda10023.c            |  6 +-
 drivers/media/dvb-frontends/tda10048.c            |  6 +-
 drivers/media/dvb-frontends/tda1004x.c            | 12 ++--
 drivers/media/dvb-frontends/tda10071.c            | 10 +--
 drivers/media/dvb-frontends/tda10086.c            |  6 +-
 drivers/media/dvb-frontends/tda8083.c             |  7 +-
 drivers/media/dvb-frontends/ves1820.c             |  6 +-
 drivers/media/dvb-frontends/ves1x93.c             |  8 +--
 drivers/media/dvb-frontends/zl10036.c             |  4 +-
 drivers/media/dvb-frontends/zl10353.c             |  7 +-
 drivers/media/firewire/firedtv-fe.c               | 26 +++----
 drivers/media/pci/bt8xx/dst.c                     | 26 +++----
 drivers/media/pci/bt8xx/dvb-bt8xx.c               |  8 +--
 drivers/media/pci/ddbridge/ddbridge-sx8.c         |  6 +-
 drivers/media/pci/mantis/mantis_vp3030.c          |  4 +-
 drivers/media/tuners/mxl5007t.c                   |  2 -
 drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c     |  6 +-
 drivers/media/usb/dvb-usb/af9005-fe.c             |  6 +-
 drivers/media/usb/dvb-usb/cinergyT2-fe.c          |  6 +-
 drivers/media/usb/dvb-usb/dtt200u-fe.c            |  6 +-
 drivers/media/usb/dvb-usb/friio-fe.c              | 11 ++-
 drivers/media/usb/dvb-usb/vp702x-fe.c             |  7 +-
 drivers/media/usb/dvb-usb/vp7045-fe.c             |  6 +-
 drivers/media/usb/ttusb-dec/ttusbdecfe.c          | 12 ++--
 include/media/dvb_frontend.h                      | 30 +++++++-
 96 files changed, 428 insertions(+), 399 deletions(-)

diff --git a/drivers/media/common/siano/smsdvb-main.c b/drivers/media/common/siano/smsdvb-main.c
index c0faad1ba428..43cfd1dbda01 100644
--- a/drivers/media/common/siano/smsdvb-main.c
+++ b/drivers/media/common/siano/smsdvb-main.c
@@ -1047,9 +1047,9 @@ static void smsdvb_release(struct dvb_frontend *fe)
 static const struct dvb_frontend_ops smsdvb_fe_ops = {
 	.info = {
 		.name			= "Siano Mobile Digital MDTV Receiver",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 250000,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	=    250 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index 75e95b56f8b3..fe0fae482ba4 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -894,11 +894,28 @@ static int dvb_frontend_start(struct dvb_frontend *fe)
 }
 
 static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe,
-					      u32 *freq_min, u32 *freq_max)
+					      u32 *freq_min, u32 *freq_max,
+					      u32 *tolerance)
 {
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	__u32 tuner_min = fe->ops.tuner_ops.info.frequency_min_hz;
-	__u32 tuner_max = fe->ops.tuner_ops.info.frequency_max_hz;
+	u32 tuner_min = fe->ops.tuner_ops.info.frequency_min_hz;
+	u32 tuner_max = fe->ops.tuner_ops.info.frequency_max_hz;
+	u32 frontend_min = fe->ops.info.frequency_min_hz;
+	u32 frontend_max = fe->ops.info.frequency_max_hz;
+
+	*freq_min = max(frontend_min, tuner_min);
+
+	if (frontend_max == 0)
+		*freq_max = tuner_max;
+	else if (tuner_max == 0)
+		*freq_max = frontend_max;
+	else
+		*freq_max = min(frontend_max, tuner_max);
+
+	if (*freq_min == 0 || *freq_max == 0)
+		dev_warn(fe->dvb->device,
+			 "DVB: adapter %i frontend %u frequency limits undefined - fix the driver\n",
+			 fe->dvb->num, fe->id);
 
 	/* If the standard is for satellite, convert frequencies to kHz */
 	switch (c->delivery_system) {
@@ -906,26 +923,35 @@ static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe,
 	case SYS_DVBS2:
 	case SYS_TURBO:
 	case SYS_ISDBS:
-		tuner_max /= kHz;
-		tuner_min /= kHz;
+		*freq_min /= kHz;
+		*freq_max /= kHz;
+		if (tolerance)
+			*tolerance = fe->ops.info.frequency_tolerance_hz / kHz;
+
 		break;
 	default:
+		if (tolerance)
+			*tolerance = fe->ops.info.frequency_tolerance_hz;
 		break;
 	}
+}
 
-	*freq_min = max(fe->ops.info.frequency_min, tuner_min);
-
-	if (fe->ops.info.frequency_max == 0)
-		*freq_max = tuner_max;
-	else if (tuner_max == 0)
-		*freq_max = fe->ops.info.frequency_max;
-	else
-		*freq_max = min(fe->ops.info.frequency_max, tuner_max);
+static u32 dvb_frontend_get_stepsize(struct dvb_frontend *fe)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	u32 step = fe->ops.info.frequency_stepsize_hz;
+	switch (c->delivery_system) {
+	case SYS_DVBS:
+	case SYS_DVBS2:
+	case SYS_TURBO:
+	case SYS_ISDBS:
+		step /= kHz;
+		break;
+	default:
+		break;
+	}
 
-	if (*freq_min == 0 || *freq_max == 0)
-		dev_warn(fe->dvb->device,
-			 "DVB: adapter %i frontend %u frequency limits undefined - fix the driver\n",
-			 fe->dvb->num, fe->id);
+	return step;
 }
 
 static int dvb_frontend_check_parameters(struct dvb_frontend *fe)
@@ -935,7 +961,7 @@ static int dvb_frontend_check_parameters(struct dvb_frontend *fe)
 	u32 freq_max;
 
 	/* range check: frequency */
-	dvb_frontend_get_frequency_limits(fe, &freq_min, &freq_max);
+	dvb_frontend_get_frequency_limits(fe, &freq_min, &freq_max, NULL);
 	if ((freq_min && c->frequency < freq_min) ||
 	    (freq_max && c->frequency > freq_max)) {
 		dev_warn(fe->dvb->device, "DVB: adapter %i frontend %i frequency %u out of range (%u..%u)\n",
@@ -2261,8 +2287,8 @@ static int dtv_set_frontend(struct dvb_frontend *fe)
 		case SYS_ISDBT:
 		case SYS_DTMB:
 			fepriv->min_delay = HZ / 20;
-			fepriv->step_size = fe->ops.info.frequency_stepsize * 2;
-			fepriv->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+			fepriv->step_size = dvb_frontend_get_stepsize(fe) * 2;
+			fepriv->max_drift = (dvb_frontend_get_stepsize(fe) * 2) + 1;
 			break;
 		default:
 			/*
@@ -2391,9 +2417,17 @@ static int dvb_frontend_handle_ioctl(struct file *file,
 
 	case FE_GET_INFO: {
 		struct dvb_frontend_info *info = parg;
-
-		memcpy(info, &fe->ops.info, sizeof(struct dvb_frontend_info));
-		dvb_frontend_get_frequency_limits(fe, &info->frequency_min, &info->frequency_max);
+		memset(info, 0, sizeof(*info));
+
+		strcpy(info->name, fe->ops.info.name);
+		info->symbol_rate_min = fe->ops.info.symbol_rate_min;
+		info->symbol_rate_max = fe->ops.info.symbol_rate_max;
+		info->symbol_rate_tolerance = fe->ops.info.symbol_rate_tolerance;
+		info->caps = fe->ops.info.caps;
+		info->frequency_stepsize = dvb_frontend_get_stepsize(fe);
+		dvb_frontend_get_frequency_limits(fe, &info->frequency_min,
+						  &info->frequency_max,
+						  &info->frequency_tolerance);
 
 		/*
 		 * Associate the 4 delivery systems supported by DVBv3
@@ -2423,10 +2457,10 @@ static int dvb_frontend_handle_ioctl(struct file *file,
 			dev_err(fe->dvb->device,
 				"%s: doesn't know how to handle a DVBv3 call to delivery system %i\n",
 				__func__, c->delivery_system);
-			fe->ops.info.type = FE_OFDM;
+			info->type = FE_OFDM;
 		}
 		dev_dbg(fe->dvb->device, "%s: current delivery system on cache: %d, V3 type: %d\n",
-			__func__, c->delivery_system, fe->ops.info.type);
+			__func__, c->delivery_system, info->type);
 
 		/* Set CAN_INVERSION_AUTO bit on in other than oneshot mode */
 		if (!(fepriv->tune_mode_flags & FE_TUNE_MODE_ONESHOT))
diff --git a/drivers/media/dvb-frontends/af9013.c b/drivers/media/dvb-frontends/af9013.c
index 482bce49819a..f3acbb57d48c 100644
--- a/drivers/media/dvb-frontends/af9013.c
+++ b/drivers/media/dvb-frontends/af9013.c
@@ -1136,10 +1136,9 @@ static const struct dvb_frontend_ops af9013_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Afatech AF9013",
-		.frequency_min = 174000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 250000,
-		.frequency_tolerance = 0,
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 250 * kHz,
 		.caps =	FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/af9033.c b/drivers/media/dvb-frontends/af9033.c
index aaed7cfe5f66..0cd57013ea25 100644
--- a/drivers/media/dvb-frontends/af9033.c
+++ b/drivers/media/dvb-frontends/af9033.c
@@ -1020,10 +1020,9 @@ static const struct dvb_frontend_ops af9033_ops = {
 	.delsys = {SYS_DVBT},
 	.info = {
 		.name = "Afatech AF9033 (DVB-T)",
-		.frequency_min = 174000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 250000,
-		.frequency_tolerance = 0,
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 250 * kHz,
 		.caps =	FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/as102_fe.c b/drivers/media/dvb-frontends/as102_fe.c
index 9b2f2da1d989..f59a102b0a64 100644
--- a/drivers/media/dvb-frontends/as102_fe.c
+++ b/drivers/media/dvb-frontends/as102_fe.c
@@ -419,9 +419,9 @@ static const struct dvb_frontend_ops as102_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Abilis AS102 DVB-T",
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_INVERSION_AUTO
 			| FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4
 			| FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO
diff --git a/drivers/media/dvb-frontends/atbm8830.c b/drivers/media/dvb-frontends/atbm8830.c
index 7b0f3239dbba..cbcc65dc9d54 100644
--- a/drivers/media/dvb-frontends/atbm8830.c
+++ b/drivers/media/dvb-frontends/atbm8830.c
@@ -428,9 +428,9 @@ static const struct dvb_frontend_ops atbm8830_ops = {
 	.delsys = { SYS_DTMB },
 	.info = {
 		.name = "AltoBeam ATBM8830/8831 DMB-TH",
-		.frequency_min = 474000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 10000,
+		.frequency_min_hz = 474 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 10 * kHz,
 		.caps =
 			FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/au8522_dig.c b/drivers/media/dvb-frontends/au8522_dig.c
index 8f659bd1c79e..076f737aa8c0 100644
--- a/drivers/media/dvb-frontends/au8522_dig.c
+++ b/drivers/media/dvb-frontends/au8522_dig.c
@@ -897,9 +897,9 @@ static const struct dvb_frontend_ops au8522_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Auvitek AU8522 QAM/8VSB Frontend",
-		.frequency_min		= 54000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  54 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/bcm3510.c b/drivers/media/dvb-frontends/bcm3510.c
index 05df133dc5be..e92542b92d34 100644
--- a/drivers/media/dvb-frontends/bcm3510.c
+++ b/drivers/media/dvb-frontends/bcm3510.c
@@ -840,10 +840,8 @@ static const struct dvb_frontend_ops bcm3510_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "Broadcom BCM3510 VSB/QAM frontend",
-		.frequency_min =  54000000,
-		.frequency_max = 803000000,
-		/* stepsize is just a guess */
-		.frequency_stepsize = 0,
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 803 * MHz,
 		.caps =
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/cx22700.c b/drivers/media/dvb-frontends/cx22700.c
index 9ffd2c7ac74a..961380162cdd 100644
--- a/drivers/media/dvb-frontends/cx22700.c
+++ b/drivers/media/dvb-frontends/cx22700.c
@@ -412,9 +412,9 @@ static const struct dvb_frontend_ops cx22700_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Conexant CX22700 DVB-T",
-		.frequency_min		= 470000000,
-		.frequency_max		= 860000000,
-		.frequency_stepsize	= 166667,
+		.frequency_min_hz	= 470 * MHz,
+		.frequency_max_hz	= 860 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		      FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		      FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/cx22702.c b/drivers/media/dvb-frontends/cx22702.c
index e8b1e6b7e7e5..ab9b2924bcca 100644
--- a/drivers/media/dvb-frontends/cx22702.c
+++ b/drivers/media/dvb-frontends/cx22702.c
@@ -622,9 +622,9 @@ static const struct dvb_frontend_ops cx22702_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Conexant CX22702 DVB-T",
-		.frequency_min		= 177000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	= 177 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24110.c b/drivers/media/dvb-frontends/cx24110.c
index 2f3a1c237489..9441bdc73097 100644
--- a/drivers/media/dvb-frontends/cx24110.c
+++ b/drivers/media/dvb-frontends/cx24110.c
@@ -629,10 +629,10 @@ static const struct dvb_frontend_ops cx24110_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "Conexant CX24110 DVB-S",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011,  /* kHz for QPSK frontends */
-		.frequency_tolerance = 29500,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 29500 * kHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24116.c b/drivers/media/dvb-frontends/cx24116.c
index 2dbc7349d870..220f26663647 100644
--- a/drivers/media/dvb-frontends/cx24116.c
+++ b/drivers/media/dvb-frontends/cx24116.c
@@ -1465,10 +1465,10 @@ static const struct dvb_frontend_ops cx24116_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Conexant CX24116/CX24118",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz = 950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24117.c b/drivers/media/dvb-frontends/cx24117.c
index ba55d75d916c..667bc8be848d 100644
--- a/drivers/media/dvb-frontends/cx24117.c
+++ b/drivers/media/dvb-frontends/cx24117.c
@@ -1622,10 +1622,10 @@ static const struct dvb_frontend_ops cx24117_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Conexant CX24117/CX24132",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24120.c b/drivers/media/dvb-frontends/cx24120.c
index ccbabdae6a69..dd3ec316e7c2 100644
--- a/drivers/media/dvb-frontends/cx24120.c
+++ b/drivers/media/dvb-frontends/cx24120.c
@@ -1555,10 +1555,10 @@ static const struct dvb_frontend_ops cx24120_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Conexant CX24120/CX24118",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps =	FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cx24123.c b/drivers/media/dvb-frontends/cx24123.c
index bf33e7390aaf..e49215020a93 100644
--- a/drivers/media/dvb-frontends/cx24123.c
+++ b/drivers/media/dvb-frontends/cx24123.c
@@ -1111,10 +1111,10 @@ static const struct dvb_frontend_ops cx24123_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "Conexant CX24123/CX24109",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/cxd2820r_t.c b/drivers/media/dvb-frontends/cxd2820r_t.c
index c2e7caf9b010..eb1d7478fa8d 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t.c
@@ -431,8 +431,8 @@ int cxd2820r_get_tune_settings_t(struct dvb_frontend *fe,
 	struct dvb_frontend_tune_settings *s)
 {
 	s->min_delay_ms = 500;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/cxd2820r_t2.c b/drivers/media/dvb-frontends/cxd2820r_t2.c
index e641fde75379..f330ec1710b4 100644
--- a/drivers/media/dvb-frontends/cxd2820r_t2.c
+++ b/drivers/media/dvb-frontends/cxd2820r_t2.c
@@ -426,8 +426,8 @@ int cxd2820r_get_tune_settings_t2(struct dvb_frontend *fe,
 	struct dvb_frontend_tune_settings *s)
 {
 	s->min_delay_ms = 1500;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/cxd2841er.c b/drivers/media/dvb-frontends/cxd2841er.c
index 85905d3503ff..c98093ed3dd7 100644
--- a/drivers/media/dvb-frontends/cxd2841er.c
+++ b/drivers/media/dvb-frontends/cxd2841er.c
@@ -3942,9 +3942,8 @@ static const struct dvb_frontend_ops cxd2841er_dvbs_s2_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name		= "Sony CXD2841ER DVB-S/S2 demodulator",
-		.frequency_min	= 500000,
-		.frequency_max	= 2500000,
-		.frequency_stepsize	= 0,
+		.frequency_min_hz	=  500 * MHz,
+		.frequency_max_hz	= 2500 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.symbol_rate_tolerance = 500,
@@ -3988,8 +3987,8 @@ static struct dvb_frontend_ops cxd2841er_t_c_ops = {
 			FE_CAN_HIERARCHY_AUTO |
 			FE_CAN_MUTE_TS |
 			FE_CAN_2G_MODULATION,
-		.frequency_min = 42000000,
-		.frequency_max = 1002000000,
+		.frequency_min_hz =   42 * MHz,
+		.frequency_max_hz = 1002 * MHz,
 		.symbol_rate_min = 870000,
 		.symbol_rate_max = 11700000
 	},
diff --git a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
index bd9101e246d5..f87e27481ea7 100644
--- a/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
+++ b/drivers/media/dvb-frontends/cxd2880/cxd2880_top.c
@@ -1833,9 +1833,9 @@ static enum dvbfe_algo cxd2880_get_frontend_algo(struct dvb_frontend *fe)
 static struct dvb_frontend_ops cxd2880_dvbt_t2_ops = {
 	.info = {
 		.name = "Sony CXD2880",
-		.frequency_min =  174000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 1000,
+		.frequency_min_hz = 174 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 1 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 |
 				FE_CAN_FEC_2_3 |
diff --git a/drivers/media/dvb-frontends/dib3000mb.c b/drivers/media/dvb-frontends/dib3000mb.c
index 5861f346db49..bbbd53280477 100644
--- a/drivers/media/dvb-frontends/dib3000mb.c
+++ b/drivers/media/dvb-frontends/dib3000mb.c
@@ -786,9 +786,9 @@ static const struct dvb_frontend_ops dib3000mb_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "DiBcom 3000M-B DVB-T",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib3000mc.c b/drivers/media/dvb-frontends/dib3000mc.c
index 7e5d474806a5..c9e1db251723 100644
--- a/drivers/media/dvb-frontends/dib3000mc.c
+++ b/drivers/media/dvb-frontends/dib3000mc.c
@@ -944,9 +944,9 @@ static const struct dvb_frontend_ops dib3000mc_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "DiBcom 3000MC/P",
-		.frequency_min      = 44250000,
-		.frequency_max      = 867250000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  44250 * kHz,
+		.frequency_max_hz      = 867250 * kHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib7000m.c b/drivers/media/dvb-frontends/dib7000m.c
index 6a1d357d0c7c..b79358d09de6 100644
--- a/drivers/media/dvb-frontends/dib7000m.c
+++ b/drivers/media/dvb-frontends/dib7000m.c
@@ -1443,9 +1443,9 @@ static const struct dvb_frontend_ops dib7000m_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "DiBcom 7000MA/MB/PA/PB/MC",
-		.frequency_min      = 44250000,
-		.frequency_max      = 867250000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  44250 * kHz,
+		.frequency_max_hz      = 867250 * kHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib7000p.c b/drivers/media/dvb-frontends/dib7000p.c
index 5a8dbc0b25fb..58387860b62d 100644
--- a/drivers/media/dvb-frontends/dib7000p.c
+++ b/drivers/media/dvb-frontends/dib7000p.c
@@ -2824,9 +2824,9 @@ static const struct dvb_frontend_ops dib7000p_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "DiBcom 7000PC",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz =  44250 * kHz,
+		 .frequency_max_hz = 867250 * kHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib8000.c b/drivers/media/dvb-frontends/dib8000.c
index 22eec8f65485..3c3f8cb14845 100644
--- a/drivers/media/dvb-frontends/dib8000.c
+++ b/drivers/media/dvb-frontends/dib8000.c
@@ -4390,9 +4390,9 @@ static const struct dvb_frontend_ops dib8000_ops = {
 	.delsys = { SYS_ISDBT },
 	.info = {
 		 .name = "DiBcom 8000 ISDB-T",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz =  44250 * kHz,
+		 .frequency_max_hz = 867250 * kHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/dib9000.c b/drivers/media/dvb-frontends/dib9000.c
index b8edb55696bb..0183fb1346ef 100644
--- a/drivers/media/dvb-frontends/dib9000.c
+++ b/drivers/media/dvb-frontends/dib9000.c
@@ -2553,9 +2553,9 @@ static const struct dvb_frontend_ops dib9000_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "DiBcom 9000",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz =  44250 * kHz,
+		 .frequency_max_hz = 867250 * kHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 5706898e84cc..2ddb7d218ace 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -12374,9 +12374,9 @@ static const struct dvb_frontend_ops drx39xxj_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		 .name = "Micronas DRX39xxj family Frontend",
-		 .frequency_stepsize = 62500,
-		 .frequency_min = 51000000,
-		 .frequency_max = 858000000,
+		 .frequency_min_hz =  51 * MHz,
+		 .frequency_max_hz = 858 * MHz,
+		 .frequency_stepsize_hz = 62500,
 		 .caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c
index 3b7d31a22d82..11fc259e4383 100644
--- a/drivers/media/dvb-frontends/drxd_hard.c
+++ b/drivers/media/dvb-frontends/drxd_hard.c
@@ -2912,10 +2912,9 @@ static const struct dvb_frontend_ops drxd_ops = {
 	.delsys = { SYS_DVBT},
 	.info = {
 		 .name = "Micronas DRXD DVB-T",
-		 .frequency_min = 47125000,
-		 .frequency_max = 855250000,
-		 .frequency_stepsize = 166667,
-		 .frequency_tolerance = 0,
+		 .frequency_min_hz =  47125 * kHz,
+		 .frequency_max_hz = 855250 * kHz,
+		 .frequency_stepsize_hz = 166667,
 		 .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 		 FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 		 FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c
index 5a26ad93be10..ac10781d3550 100644
--- a/drivers/media/dvb-frontends/drxk_hard.c
+++ b/drivers/media/dvb-frontends/drxk_hard.c
@@ -6744,13 +6744,13 @@ static const struct dvb_frontend_ops drxk_ops = {
 	/* .delsys will be filled dynamically */
 	.info = {
 		.name = "DRXK",
-		.frequency_min = 47000000,
-		.frequency_max = 865000000,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 865 * MHz,
 		 /* For DVB-C */
-		.symbol_rate_min = 870000,
+		.symbol_rate_min =   870000,
 		.symbol_rate_max = 11700000,
 		/* For DVB-T */
-		.frequency_stepsize = 166667,
+		.frequency_stepsize_hz = 166667,
 
 		.caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 |
 			FE_CAN_QAM_128 | FE_CAN_QAM_256 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/ds3000.c b/drivers/media/dvb-frontends/ds3000.c
index 2ff90e5eabce..46a55146cb07 100644
--- a/drivers/media/dvb-frontends/ds3000.c
+++ b/drivers/media/dvb-frontends/ds3000.c
@@ -1100,10 +1100,10 @@ static const struct dvb_frontend_ops ds3000_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "Montage Technology DS3000",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1011, /* kHz for QPSK frontends */
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_stepsize_hz = 1011 * kHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/dvb_dummy_fe.c b/drivers/media/dvb-frontends/dvb_dummy_fe.c
index 6650d4f61ef2..a4cbcae7967d 100644
--- a/drivers/media/dvb-frontends/dvb_dummy_fe.c
+++ b/drivers/media/dvb-frontends/dvb_dummy_fe.c
@@ -170,9 +170,9 @@ static const struct dvb_frontend_ops dvb_dummy_fe_ofdm_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Dummy DVB-T",
-		.frequency_min		= 0,
-		.frequency_max		= 863250000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	= 0,
+		.frequency_max_hz	= 863250 * kHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_4_5 | FE_CAN_FEC_5_6 | FE_CAN_FEC_6_7 |
 				FE_CAN_FEC_7_8 | FE_CAN_FEC_8_9 | FE_CAN_FEC_AUTO |
@@ -201,11 +201,11 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qam_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name			= "Dummy DVB-C",
-		.frequency_stepsize	= 62500,
-		.frequency_min		= 51000000,
-		.frequency_max		= 858000000,
-		.symbol_rate_min	= (57840000/2)/64,     /* SACLK/64 == (XIN/2)/64 */
-		.symbol_rate_max	= (57840000/2)/4,      /* SACLK/4 */
+		.frequency_min_hz	=  51 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
+		.symbol_rate_min	= (57840000 / 2) / 64,  /* SACLK/64 == (XIN/2)/64 */
+		.symbol_rate_max	= (57840000 / 2) / 4,   /* SACLK/4 */
 		.caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 |
 			FE_CAN_QAM_128 | FE_CAN_QAM_256 |
 			FE_CAN_FEC_AUTO | FE_CAN_INVERSION_AUTO
@@ -230,10 +230,10 @@ static const struct dvb_frontend_ops dvb_dummy_fe_qpsk_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Dummy DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 250,           /* kHz for QPSK frontends */
-		.frequency_tolerance	= 29500,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	= 250 * kHz,
+		.frequency_tolerance_hz	= 29500 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/gp8psk-fe.c b/drivers/media/dvb-frontends/gp8psk-fe.c
index a772ef8bfe1c..238f09aa72f2 100644
--- a/drivers/media/dvb-frontends/gp8psk-fe.c
+++ b/drivers/media/dvb-frontends/gp8psk-fe.c
@@ -355,9 +355,9 @@ static const struct dvb_frontend_ops gp8psk_fe_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Genpix DVB-S",
-		.frequency_min		= 800000,
-		.frequency_max		= 2250000,
-		.frequency_stepsize	= 100,
+		.frequency_min_hz	=  800 * MHz,
+		.frequency_max_hz	= 2250 * MHz,
+		.frequency_stepsize_hz	=  100 * kHz,
 		.symbol_rate_min        = 1000000,
 		.symbol_rate_max        = 45000000,
 		.symbol_rate_tolerance  = 500,  /* ppm */
diff --git a/drivers/media/dvb-frontends/ix2505v.c b/drivers/media/dvb-frontends/ix2505v.c
index 9c055f72c416..a30707b61b1f 100644
--- a/drivers/media/dvb-frontends/ix2505v.c
+++ b/drivers/media/dvb-frontends/ix2505v.c
@@ -135,8 +135,8 @@ static int ix2505v_set_params(struct dvb_frontend *fe)
 	u8 gain, cc, ref, psc, local_osc, lpf;
 	u8 data[4] = {0};
 
-	if ((frequency < fe->ops.info.frequency_min)
-	||  (frequency > fe->ops.info.frequency_max))
+	if ((frequency < fe->ops.info.frequency_min_hz / kHz)
+	||  (frequency > fe->ops.info.frequency_max_hz / kHz))
 		return -EINVAL;
 
 	if (state->config->tuner_gain)
diff --git a/drivers/media/dvb-frontends/l64781.c b/drivers/media/dvb-frontends/l64781.c
index 249c18761e6e..9afb5bf6424b 100644
--- a/drivers/media/dvb-frontends/l64781.c
+++ b/drivers/media/dvb-frontends/l64781.c
@@ -575,10 +575,9 @@ static const struct dvb_frontend_ops l64781_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "LSI L64781 DVB-T",
-	/*	.frequency_min = ???,*/
-	/*	.frequency_max = ???,*/
-		.frequency_stepsize = 166666,
-	/*      .frequency_tolerance = ???,*/
+	/*	.frequency_min_hz = ???,*/
+	/*	.frequency_max_hz = ???,*/
+		.frequency_stepsize_hz = 166666,
 	/*      .symbol_rate_tolerance = ???,*/
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		      FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
diff --git a/drivers/media/dvb-frontends/lg2160.c b/drivers/media/dvb-frontends/lg2160.c
index 9854096839ae..408151e33fa7 100644
--- a/drivers/media/dvb-frontends/lg2160.c
+++ b/drivers/media/dvb-frontends/lg2160.c
@@ -1349,9 +1349,9 @@ static const struct dvb_frontend_ops lg2160_ops = {
 	.delsys = { SYS_ATSCMH },
 	.info = {
 		.name = "LG Electronics LG2160 ATSC/MH Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 	},
 	.i2c_gate_ctrl        = lg216x_i2c_gate_ctrl,
 #if 0
@@ -1375,9 +1375,9 @@ static const struct dvb_frontend_ops lg2161_ops = {
 	.delsys = { SYS_ATSCMH },
 	.info = {
 		.name = "LG Electronics LG2161 ATSC/MH Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 	},
 	.i2c_gate_ctrl        = lg216x_i2c_gate_ctrl,
 #if 0
diff --git a/drivers/media/dvb-frontends/lgdt3305.c b/drivers/media/dvb-frontends/lgdt3305.c
index 735d73060265..857e9b4d69b4 100644
--- a/drivers/media/dvb-frontends/lgdt3305.c
+++ b/drivers/media/dvb-frontends/lgdt3305.c
@@ -1164,9 +1164,9 @@ static const struct dvb_frontend_ops lgdt3304_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3304 VSB/QAM Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 	.i2c_gate_ctrl        = lgdt3305_i2c_gate_ctrl,
@@ -1187,9 +1187,9 @@ static const struct dvb_frontend_ops lgdt3305_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3305 VSB/QAM Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 	.i2c_gate_ctrl        = lgdt3305_i2c_gate_ctrl,
diff --git a/drivers/media/dvb-frontends/lgdt3306a.c b/drivers/media/dvb-frontends/lgdt3306a.c
index 32de824476db..0e1f5daaf20c 100644
--- a/drivers/media/dvb-frontends/lgdt3306a.c
+++ b/drivers/media/dvb-frontends/lgdt3306a.c
@@ -2157,9 +2157,9 @@ static const struct dvb_frontend_ops lgdt3306a_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3306A VSB/QAM Frontend",
-		.frequency_min      = 54000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz      =  54 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_AUTO | FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 	.i2c_gate_ctrl        = lgdt3306a_i2c_gate_ctrl,
diff --git a/drivers/media/dvb-frontends/lgdt330x.c b/drivers/media/dvb-frontends/lgdt330x.c
index f6731738b073..10d584ce538d 100644
--- a/drivers/media/dvb-frontends/lgdt330x.c
+++ b/drivers/media/dvb-frontends/lgdt330x.c
@@ -944,9 +944,9 @@ static const struct dvb_frontend_ops lgdt3302_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3302 VSB/QAM Frontend",
-		.frequency_min = 54000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min    = 5056941,	/* QAM 64 */
 		.symbol_rate_max    = 10762000,	/* VSB 8  */
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
@@ -966,9 +966,9 @@ static const struct dvb_frontend_ops lgdt3303_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "LG Electronics LGDT3303 VSB/QAM Frontend",
-		.frequency_min = 54000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min    = 5056941,	/* QAM 64 */
 		.symbol_rate_max    = 10762000,	/* VSB 8  */
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
diff --git a/drivers/media/dvb-frontends/lgs8gl5.c b/drivers/media/dvb-frontends/lgs8gl5.c
index f47e5a1af16d..07e5bcee9c1e 100644
--- a/drivers/media/dvb-frontends/lgs8gl5.c
+++ b/drivers/media/dvb-frontends/lgs8gl5.c
@@ -416,10 +416,9 @@ static const struct dvb_frontend_ops lgs8gl5_ops = {
 	.delsys = { SYS_DTMB },
 	.info = {
 		.name			= "Legend Silicon LGS-8GL5 DMB-TH",
-		.frequency_min		= 474000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 10000,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 474 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	=  10 * kHz,
 		.caps = FE_CAN_FEC_AUTO |
 			FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_32 |
 			FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/lgs8gxx.c b/drivers/media/dvb-frontends/lgs8gxx.c
index 84af8a12f26a..a6bcf1571d10 100644
--- a/drivers/media/dvb-frontends/lgs8gxx.c
+++ b/drivers/media/dvb-frontends/lgs8gxx.c
@@ -985,9 +985,9 @@ static const struct dvb_frontend_ops lgs8gxx_ops = {
 	.delsys = { SYS_DTMB },
 	.info = {
 		.name = "Legend Silicon LGS8913/LGS8GXX DMB-TH",
-		.frequency_min = 474000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 10000,
+		.frequency_min_hz = 474 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 10 * kHz,
 		.caps =
 			FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/m88ds3103.c b/drivers/media/dvb-frontends/m88ds3103.c
index 65d157fe76d1..dffd2d4bf1c8 100644
--- a/drivers/media/dvb-frontends/m88ds3103.c
+++ b/drivers/media/dvb-frontends/m88ds3103.c
@@ -1300,9 +1300,9 @@ static const struct dvb_frontend_ops m88ds3103_ops = {
 	.delsys = {SYS_DVBS, SYS_DVBS2},
 	.info = {
 		.name = "Montage Technology M88DS3103",
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
-		.frequency_tolerance = 5000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min =  1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/m88rs2000.c b/drivers/media/dvb-frontends/m88rs2000.c
index 496ce27fa63a..d5bc85501f9e 100644
--- a/drivers/media/dvb-frontends/m88rs2000.c
+++ b/drivers/media/dvb-frontends/m88rs2000.c
@@ -759,10 +759,10 @@ static const struct dvb_frontend_ops m88rs2000_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "M88RS2000 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 1000,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 5000,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	= 1 * MHz,
+		.frequency_tolerance_hz	= 5 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/mb86a16.c b/drivers/media/dvb-frontends/mb86a16.c
index 377cd984b069..da505a5d035f 100644
--- a/drivers/media/dvb-frontends/mb86a16.c
+++ b/drivers/media/dvb-frontends/mb86a16.c
@@ -1808,10 +1808,9 @@ static const struct dvb_frontend_ops mb86a16_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Fujitsu MB86A16 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 3000,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=    3 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,
diff --git a/drivers/media/dvb-frontends/mb86a20s.c b/drivers/media/dvb-frontends/mb86a20s.c
index c3b1b88e2e7a..66fc77db0e75 100644
--- a/drivers/media/dvb-frontends/mb86a20s.c
+++ b/drivers/media/dvb-frontends/mb86a20s.c
@@ -2111,9 +2111,9 @@ static const struct dvb_frontend_ops mb86a20s_ops = {
 			FE_CAN_TRANSMISSION_MODE_AUTO | FE_CAN_QAM_AUTO |
 			FE_CAN_GUARD_INTERVAL_AUTO    | FE_CAN_HIERARCHY_AUTO,
 		/* Actually, those values depend on the used tuner */
-		.frequency_min = 45000000,
-		.frequency_max = 864000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  45 * MHz,
+		.frequency_max_hz = 864 * MHz,
+		.frequency_stepsize_hz = 62500,
 	},
 
 	.release = mb86a20s_release,
diff --git a/drivers/media/dvb-frontends/mt312.c b/drivers/media/dvb-frontends/mt312.c
index e2a3fc521620..aad07adda37d 100644
--- a/drivers/media/dvb-frontends/mt312.c
+++ b/drivers/media/dvb-frontends/mt312.c
@@ -559,8 +559,8 @@ static int mt312_set_frontend(struct dvb_frontend *fe)
 
 	dprintk("%s: Freq %d\n", __func__, p->frequency);
 
-	if ((p->frequency < fe->ops.info.frequency_min)
-	    || (p->frequency > fe->ops.info.frequency_max))
+	if ((p->frequency < fe->ops.info.frequency_min_hz / kHz)
+	    || (p->frequency > fe->ops.info.frequency_max_hz / kHz))
 		return -EINVAL;
 
 	if (((int)p->inversion < INVERSION_OFF)
@@ -755,10 +755,10 @@ static const struct dvb_frontend_ops mt312_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "Zarlink ???? DVB-S",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 		/* FIXME: adjust freq to real used xtal */
-		.frequency_stepsize = (MT312_PLL_CLK / 1000) / 128,
+		.frequency_stepsize_hz = MT312_PLL_CLK / 128,
 		.symbol_rate_min = MT312_SYS_CLK / 128, /* FIXME as above */
 		.symbol_rate_max = MT312_SYS_CLK / 2,
 		.caps =
diff --git a/drivers/media/dvb-frontends/mt352.c b/drivers/media/dvb-frontends/mt352.c
index a440b76444d3..da3e466d50e2 100644
--- a/drivers/media/dvb-frontends/mt352.c
+++ b/drivers/media/dvb-frontends/mt352.c
@@ -567,10 +567,9 @@ static const struct dvb_frontend_ops mt352_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Zarlink MT352 DVB-T",
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 			FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/mxl5xx.c b/drivers/media/dvb-frontends/mxl5xx.c
index 274d8fca0763..295f37d5f10e 100644
--- a/drivers/media/dvb-frontends/mxl5xx.c
+++ b/drivers/media/dvb-frontends/mxl5xx.c
@@ -784,10 +784,8 @@ static struct dvb_frontend_ops mxl_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "MaxLinear MxL5xx DVB-S/S2 tuner-demodulator",
-		.frequency_min		= 300000,
-		.frequency_max		= 2350000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  300 * MHz,
+		.frequency_max_hz	= 2350 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.caps			= FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/nxt200x.c b/drivers/media/dvb-frontends/nxt200x.c
index a6cc4952eb74..0961e686ff68 100644
--- a/drivers/media/dvb-frontends/nxt200x.c
+++ b/drivers/media/dvb-frontends/nxt200x.c
@@ -1212,9 +1212,9 @@ static const struct dvb_frontend_ops nxt200x_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name = "Nextwave NXT200X VSB/QAM frontend",
-		.frequency_min =  54000000,
-		.frequency_max = 860000000,
-		.frequency_stepsize = 166666,	/* stepsize is just a guess */
+		.frequency_min_hz =  54 * MHz,
+		.frequency_max_hz = 860 * MHz,
+		.frequency_stepsize_hz = 166666,	/* stepsize is just a guess */
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_8VSB | FE_CAN_QAM_64 | FE_CAN_QAM_256
diff --git a/drivers/media/dvb-frontends/nxt6000.c b/drivers/media/dvb-frontends/nxt6000.c
index 109a635d166a..72e447e8ba64 100644
--- a/drivers/media/dvb-frontends/nxt6000.c
+++ b/drivers/media/dvb-frontends/nxt6000.c
@@ -596,9 +596,9 @@ static const struct dvb_frontend_ops nxt6000_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "NxtWave NXT6000 DVB-T",
-		.frequency_min = 0,
-		.frequency_max = 863250000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz = 0,
+		.frequency_max_hz = 863250 * kHz,
+		.frequency_stepsize_hz = 62500,
 		/*.frequency_tolerance = *//* FIXME: 12% of SR */
 		.symbol_rate_min = 0,	/* FIXME */
 		.symbol_rate_max = 9360000,	/* FIXME */
diff --git a/drivers/media/dvb-frontends/or51132.c b/drivers/media/dvb-frontends/or51132.c
index b4c9aadcb552..fc35f37eb3c0 100644
--- a/drivers/media/dvb-frontends/or51132.c
+++ b/drivers/media/dvb-frontends/or51132.c
@@ -583,9 +583,9 @@ static const struct dvb_frontend_ops or51132_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Oren OR51132 VSB/QAM Frontend",
-		.frequency_min		= 44000000,
-		.frequency_max		= 958000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	=  44 * MHz,
+		.frequency_max_hz	= 958 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/or51211.c b/drivers/media/dvb-frontends/or51211.c
index b65ba34fd00a..a39bbd8ff1f0 100644
--- a/drivers/media/dvb-frontends/or51211.c
+++ b/drivers/media/dvb-frontends/or51211.c
@@ -530,10 +530,10 @@ struct dvb_frontend* or51211_attach(const struct or51211_config* config,
 static const struct dvb_frontend_ops or51211_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
-		.name               = "Oren OR51211 VSB Frontend",
-		.frequency_min      = 44000000,
-		.frequency_max      = 958000000,
-		.frequency_stepsize = 166666,
+		.name                  = "Oren OR51211 VSB Frontend",
+		.frequency_min_hz      =  44 * MHz,
+		.frequency_max_hz      = 958 * MHz,
+		.frequency_stepsize_hz = 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_8VSB
diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c
index 7bbfe11d11ed..adc9046d5a90 100644
--- a/drivers/media/dvb-frontends/rtl2830.c
+++ b/drivers/media/dvb-frontends/rtl2830.c
@@ -159,8 +159,8 @@ static int rtl2830_get_tune_settings(struct dvb_frontend *fe,
 				     struct dvb_frontend_tune_settings *s)
 {
 	s->min_delay_ms = 500;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 
 	return 0;
 }
diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
index fa3b8169c1a5..2f1f5cbaf03c 100644
--- a/drivers/media/dvb-frontends/rtl2832.c
+++ b/drivers/media/dvb-frontends/rtl2832.c
@@ -408,8 +408,8 @@ static int rtl2832_get_tune_settings(struct dvb_frontend *fe,
 
 	dev_dbg(&client->dev, "\n");
 	s->min_delay_ms = 1000;
-	s->step_size = fe->ops.info.frequency_stepsize * 2;
-	s->max_drift = (fe->ops.info.frequency_stepsize * 2) + 1;
+	s->step_size = fe->ops.info.frequency_stepsize_hz * 2;
+	s->max_drift = (fe->ops.info.frequency_stepsize_hz * 2) + 1;
 	return 0;
 }
 
@@ -841,9 +841,9 @@ static const struct dvb_frontend_ops rtl2832_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Realtek RTL2832 (DVB-T)",
-		.frequency_min	  = 174000000,
-		.frequency_max	  = 862000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/s5h1409.c b/drivers/media/dvb-frontends/s5h1409.c
index a23ba8727218..ceeb0c3551ce 100644
--- a/drivers/media/dvb-frontends/s5h1409.c
+++ b/drivers/media/dvb-frontends/s5h1409.c
@@ -999,9 +999,9 @@ static const struct dvb_frontend_ops s5h1409_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Samsung S5H1409 QAM/8VSB Frontend",
-		.frequency_min		= 54000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  54 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/s5h1411.c b/drivers/media/dvb-frontends/s5h1411.c
index af5962807f2c..98aeed1d2284 100644
--- a/drivers/media/dvb-frontends/s5h1411.c
+++ b/drivers/media/dvb-frontends/s5h1411.c
@@ -918,9 +918,9 @@ static const struct dvb_frontend_ops s5h1411_ops = {
 	.delsys = { SYS_ATSC, SYS_DVBC_ANNEX_B },
 	.info = {
 		.name			= "Samsung S5H1411 QAM/8VSB Frontend",
-		.frequency_min		= 54000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  54 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps = FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
 	},
 
diff --git a/drivers/media/dvb-frontends/s5h1420.c b/drivers/media/dvb-frontends/s5h1420.c
index 8b2222530227..a65cdf8e8cd9 100644
--- a/drivers/media/dvb-frontends/s5h1420.c
+++ b/drivers/media/dvb-frontends/s5h1420.c
@@ -934,10 +934,10 @@ static const struct dvb_frontend_ops s5h1420_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name     = "Samsung S5H1420/PnpNetwork PN1010 DVB-S",
-		.frequency_min    = 950000,
-		.frequency_max    = 2150000,
-		.frequency_stepsize = 125,     /* kHz for QPSK frontends */
-		.frequency_tolerance  = 29500,
+		.frequency_min_hz    =  950 * MHz,
+		.frequency_max_hz    = 2150 * MHz,
+		.frequency_stepsize_hz = 125 * kHz,
+		.frequency_tolerance_hz  = 29500 * kHz,
 		.symbol_rate_min  = 1000000,
 		.symbol_rate_max  = 45000000,
 		/*  .symbol_rate_tolerance  = ???,*/
diff --git a/drivers/media/dvb-frontends/s5h1432.c b/drivers/media/dvb-frontends/s5h1432.c
index 740a60df0455..4dc3febc0e12 100644
--- a/drivers/media/dvb-frontends/s5h1432.c
+++ b/drivers/media/dvb-frontends/s5h1432.c
@@ -370,9 +370,9 @@ static const struct dvb_frontend_ops s5h1432_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "Samsung s5h1432 DVB-T Frontend",
-		 .frequency_min = 177000000,
-		 .frequency_max = 858000000,
-		 .frequency_stepsize = 166666,
+		 .frequency_min_hz = 177 * MHz,
+		 .frequency_max_hz = 858 * MHz,
+		 .frequency_stepsize_hz = 166666,
 		 .caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		 FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/s921.c b/drivers/media/dvb-frontends/s921.c
index 6c9015236655..79276871112a 100644
--- a/drivers/media/dvb-frontends/s921.c
+++ b/drivers/media/dvb-frontends/s921.c
@@ -510,15 +510,14 @@ static const struct dvb_frontend_ops s921_ops = {
 	/* Use dib8000 values per default */
 	.info = {
 		.name = "Sharp S921",
-		.frequency_min = 470000000,
+		.frequency_min_hz = 470 * MHz,
 		/*
 		 * Max should be 770MHz instead, according with Sharp docs,
 		 * but Leadership doc says it works up to 806 MHz. This is
 		 * required to get channel 69, used in Brazil
 		 */
-		.frequency_max = 806000000,
-		.frequency_tolerance = 0,
-		 .caps = FE_CAN_INVERSION_AUTO |
+		.frequency_max_hz = 806 * MHz,
+		.caps =  FE_CAN_INVERSION_AUTO |
 			 FE_CAN_FEC_1_2  | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			 FE_CAN_FEC_5_6  | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			 FE_CAN_QPSK     | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/si2165.c b/drivers/media/dvb-frontends/si2165.c
index 2dd336f95cbf..feacd8da421d 100644
--- a/drivers/media/dvb-frontends/si2165.c
+++ b/drivers/media/dvb-frontends/si2165.c
@@ -1120,7 +1120,7 @@ static const struct dvb_frontend_ops si2165_ops = {
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 7200000,
 		/* For DVB-T */
-		.frequency_stepsize = 166667,
+		.frequency_stepsize_hz = 166667,
 		.caps = FE_CAN_FEC_1_2 |
 			FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 |
diff --git a/drivers/media/dvb-frontends/si21xx.c b/drivers/media/dvb-frontends/si21xx.c
index 9b32a1b3205e..8546a236d452 100644
--- a/drivers/media/dvb-frontends/si21xx.c
+++ b/drivers/media/dvb-frontends/si21xx.c
@@ -870,10 +870,9 @@ static const struct dvb_frontend_ops si21xx_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "SL SI21XX DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/sp8870.c b/drivers/media/dvb-frontends/sp8870.c
index 1d57a20093fc..8d31cf3f4f07 100644
--- a/drivers/media/dvb-frontends/sp8870.c
+++ b/drivers/media/dvb-frontends/sp8870.c
@@ -584,9 +584,9 @@ static const struct dvb_frontend_ops sp8870_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Spase SP8870 DVB-T",
-		.frequency_min		= 470000000,
-		.frequency_max		= 860000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	= 470 * MHz,
+		.frequency_max_hz	= 860 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps			= FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 					  FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 |
 					  FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/sp887x.c b/drivers/media/dvb-frontends/sp887x.c
index 57a0d0ae2b48..c02f50995df4 100644
--- a/drivers/media/dvb-frontends/sp887x.c
+++ b/drivers/media/dvb-frontends/sp887x.c
@@ -594,9 +594,9 @@ static const struct dvb_frontend_ops sp887x_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Spase SP887x DVB-T",
-		.frequency_min =  50500000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166666,
+		.frequency_min_hz =  50500 * kHz,
+		.frequency_max_hz = 858000 * kHz,
+		.frequency_stepsize_hz = 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/stb0899_drv.c b/drivers/media/dvb-frontends/stb0899_drv.c
index 3c654ae16e78..874e9c9125d6 100644
--- a/drivers/media/dvb-frontends/stb0899_drv.c
+++ b/drivers/media/dvb-frontends/stb0899_drv.c
@@ -1584,10 +1584,8 @@ static const struct dvb_frontend_ops stb0899_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "STB0899 Multistandard",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 		.symbol_rate_min	=  5000000,
 		.symbol_rate_max	= 45000000,
 
diff --git a/drivers/media/dvb-frontends/stv0288.c b/drivers/media/dvb-frontends/stv0288.c
index f947ed947aae..c9a9fa4e2c1b 100644
--- a/drivers/media/dvb-frontends/stv0288.c
+++ b/drivers/media/dvb-frontends/stv0288.c
@@ -533,10 +533,9 @@ static const struct dvb_frontend_ops stv0288_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "ST STV0288 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 1000,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=    1 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/stv0297.c b/drivers/media/dvb-frontends/stv0297.c
index b823c04e24d3..9a9915f71483 100644
--- a/drivers/media/dvb-frontends/stv0297.c
+++ b/drivers/media/dvb-frontends/stv0297.c
@@ -694,9 +694,9 @@ static const struct dvb_frontend_ops stv0297_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		 .name = "ST STV0297 DVB-C",
-		 .frequency_min = 47000000,
-		 .frequency_max = 862000000,
-		 .frequency_stepsize = 62500,
+		 .frequency_min_hz = 470 * MHz,
+		 .frequency_max_hz = 862 * MHz,
+		 .frequency_stepsize_hz = 62500,
 		 .symbol_rate_min = 870000,
 		 .symbol_rate_max = 11700000,
 		 .caps = FE_CAN_QAM_16 | FE_CAN_QAM_32 | FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/stv0299.c b/drivers/media/dvb-frontends/stv0299.c
index 633b90e6fe86..4f466394a16c 100644
--- a/drivers/media/dvb-frontends/stv0299.c
+++ b/drivers/media/dvb-frontends/stv0299.c
@@ -717,10 +717,9 @@ static const struct dvb_frontend_ops stv0299_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "ST STV0299 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,	 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,	/* ppm */
diff --git a/drivers/media/dvb-frontends/stv0367.c b/drivers/media/dvb-frontends/stv0367.c
index 5435c908e298..5b91e740e135 100644
--- a/drivers/media/dvb-frontends/stv0367.c
+++ b/drivers/media/dvb-frontends/stv0367.c
@@ -1693,10 +1693,9 @@ static const struct dvb_frontend_ops stv0367ter_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "ST STV0367 DVB-T",
-		.frequency_min		= 47000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 15625,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  47 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 15625,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 			FE_CAN_FEC_AUTO |
@@ -2867,9 +2866,9 @@ static const struct dvb_frontend_ops stv0367cab_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name = "ST STV0367 DVB-C",
-		.frequency_min = 47000000,
-		.frequency_max = 862000000,
-		.frequency_stepsize = 62500,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 870000,
 		.symbol_rate_max = 11700000,
 		.caps = 0x400 |/* FE_CAN_QAM_4 */
@@ -3273,10 +3272,9 @@ static const struct dvb_frontend_ops stv0367ddb_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A, SYS_DVBT },
 	.info = {
 		.name			= "ST STV0367 DDB DVB-C/T",
-		.frequency_min		= 47000000,
-		.frequency_max		= 865000000,
-		.frequency_stepsize	= 166667,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  47 * MHz,
+		.frequency_max_hz	= 865 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.symbol_rate_min	= 870000,
 		.symbol_rate_max	= 11700000,
 		.caps = /* DVB-C */
diff --git a/drivers/media/dvb-frontends/stv0900_core.c b/drivers/media/dvb-frontends/stv0900_core.c
index 72f17b97ca04..254618a06140 100644
--- a/drivers/media/dvb-frontends/stv0900_core.c
+++ b/drivers/media/dvb-frontends/stv0900_core.c
@@ -1875,10 +1875,9 @@ static const struct dvb_frontend_ops stv0900_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "STV0900 frontend",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.symbol_rate_tolerance	= 500,
diff --git a/drivers/media/dvb-frontends/stv090x.c b/drivers/media/dvb-frontends/stv090x.c
index 9133f65d4623..a0622bb71803 100644
--- a/drivers/media/dvb-frontends/stv090x.c
+++ b/drivers/media/dvb-frontends/stv090x.c
@@ -4905,10 +4905,8 @@ static const struct dvb_frontend_ops stv090x_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "STV090x Multistandard",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 		.caps			= FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/stv0910.c b/drivers/media/dvb-frontends/stv0910.c
index 91b21eb59531..4c86073f1a8d 100644
--- a/drivers/media/dvb-frontends/stv0910.c
+++ b/drivers/media/dvb-frontends/stv0910.c
@@ -1724,10 +1724,8 @@ static const struct dvb_frontend_ops stv0910_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2, SYS_DSS },
 	.info = {
 		.name			= "ST STV0910",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 		.symbol_rate_min	= 100000,
 		.symbol_rate_max	= 70000000,
 		.caps			= FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/tc90522.c b/drivers/media/dvb-frontends/tc90522.c
index 7abf6b0916ed..2ad81a438d6a 100644
--- a/drivers/media/dvb-frontends/tc90522.c
+++ b/drivers/media/dvb-frontends/tc90522.c
@@ -714,8 +714,8 @@ static const struct dvb_frontend_ops tc90522_ops_sat = {
 	.delsys = { SYS_ISDBS },
 	.info = {
 		.name = "Toshiba TC90522 ISDB-S module",
-		.frequency_min =  950000,
-		.frequency_max = 2150000,
+		.frequency_min_hz =  950 * MHz,
+		.frequency_max_hz = 2150 * MHz,
 		.caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_AUTO | FE_CAN_TRANSMISSION_MODE_AUTO |
 			FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_HIERARCHY_AUTO,
@@ -734,9 +734,9 @@ static const struct dvb_frontend_ops tc90522_ops_ter = {
 	.delsys = { SYS_ISDBT },
 	.info = {
 		.name = "Toshiba TC90522 ISDB-T module",
-		.frequency_min = 470000000,
-		.frequency_max = 770000000,
-		.frequency_stepsize = 142857,
+		.frequency_min_hz = 470 * MHz,
+		.frequency_max_hz = 770 * MHz,
+		.frequency_stepsize_hz = 142857,
 		.caps = FE_CAN_INVERSION_AUTO |
 			FE_CAN_FEC_1_2  | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6  | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/tda10021.c b/drivers/media/dvb-frontends/tda10021.c
index 4f588ebde39d..5cd885d4ea04 100644
--- a/drivers/media/dvb-frontends/tda10021.c
+++ b/drivers/media/dvb-frontends/tda10021.c
@@ -487,11 +487,11 @@ static const struct dvb_frontend_ops tda10021_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A, SYS_DVBC_ANNEX_C },
 	.info = {
 		.name = "Philips TDA10021 DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min = 47000000,
-		.frequency_max = 862000000,
-		.symbol_rate_min = (XIN/2)/64,     /* SACLK/64 == (XIN/2)/64 */
-		.symbol_rate_max = (XIN/2)/4,      /* SACLK/4 */
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
+		.symbol_rate_min = (XIN / 2) / 64,     /* SACLK/64 == (XIN/2)/64 */
+		.symbol_rate_max = (XIN / 2) / 4,      /* SACLK/4 */
 	#if 0
 		.frequency_tolerance = ???,
 		.symbol_rate_tolerance = ???,  /* ppm */  /* == 8% (spec p. 5) */
diff --git a/drivers/media/dvb-frontends/tda10023.c b/drivers/media/dvb-frontends/tda10023.c
index 6c84916234e3..0a9a54563ebe 100644
--- a/drivers/media/dvb-frontends/tda10023.c
+++ b/drivers/media/dvb-frontends/tda10023.c
@@ -575,9 +575,9 @@ static const struct dvb_frontend_ops tda10023_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A, SYS_DVBC_ANNEX_C },
 	.info = {
 		.name = "Philips TDA10023 DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min =  47000000,
-		.frequency_max = 862000000,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 0,  /* set in tda10023_attach */
 		.symbol_rate_max = 0,  /* set in tda10023_attach */
 		.caps = 0x400 | //FE_CAN_QAM_4
diff --git a/drivers/media/dvb-frontends/tda10048.c b/drivers/media/dvb-frontends/tda10048.c
index de82a2558e15..c01d60a88af2 100644
--- a/drivers/media/dvb-frontends/tda10048.c
+++ b/drivers/media/dvb-frontends/tda10048.c
@@ -1156,9 +1156,9 @@ static const struct dvb_frontend_ops tda10048_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "NXP TDA10048HN DVB-T",
-		.frequency_min		= 177000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 166666,
+		.frequency_min_hz	= 177 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 		FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
diff --git a/drivers/media/dvb-frontends/tda1004x.c b/drivers/media/dvb-frontends/tda1004x.c
index 7dcfb4a4b2d0..d402e4b722ca 100644
--- a/drivers/media/dvb-frontends/tda1004x.c
+++ b/drivers/media/dvb-frontends/tda1004x.c
@@ -1249,9 +1249,9 @@ static const struct dvb_frontend_ops tda10045_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Philips TDA10045H DVB-T",
-		.frequency_min = 51000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz =  51 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 166667,
 		.caps =
 		    FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		    FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
@@ -1319,9 +1319,9 @@ static const struct dvb_frontend_ops tda10046_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "Philips TDA10046H DVB-T",
-		.frequency_min = 51000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz =  51 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 166667,
 		.caps =
 		    FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		    FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c
index 1ed67c08e699..097c42d3f8c2 100644
--- a/drivers/media/dvb-frontends/tda10071.c
+++ b/drivers/media/dvb-frontends/tda10071.c
@@ -681,8 +681,8 @@ static int tda10071_set_frontend(struct dvb_frontend *fe)
 	cmd.args[5] = (c->frequency >>  0) & 0xff;
 	cmd.args[6] = ((c->symbol_rate / 1000) >> 8) & 0xff;
 	cmd.args[7] = ((c->symbol_rate / 1000) >> 0) & 0xff;
-	cmd.args[8] = (tda10071_ops.info.frequency_tolerance >> 8) & 0xff;
-	cmd.args[9] = (tda10071_ops.info.frequency_tolerance >> 0) & 0xff;
+	cmd.args[8] = ((tda10071_ops.info.frequency_tolerance_hz / 1000) >> 8) & 0xff;
+	cmd.args[9] = ((tda10071_ops.info.frequency_tolerance_hz / 1000) >> 0) & 0xff;
 	cmd.args[10] = rolloff;
 	cmd.args[11] = inversion;
 	cmd.args[12] = pilot;
@@ -1106,9 +1106,9 @@ static const struct dvb_frontend_ops tda10071_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name = "NXP TDA10071",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_tolerance = 5000,
+		.frequency_min_hz    =  950 * MHz,
+		.frequency_max_hz    = 2150 * MHz,
+		.frequency_tolerance_hz = 5 * MHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/tda10086.c b/drivers/media/dvb-frontends/tda10086.c
index 1a95c521e97f..8323e4e53d66 100644
--- a/drivers/media/dvb-frontends/tda10086.c
+++ b/drivers/media/dvb-frontends/tda10086.c
@@ -710,9 +710,9 @@ static const struct dvb_frontend_ops tda10086_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name     = "Philips TDA10086 DVB-S",
-		.frequency_min    = 950000,
-		.frequency_max    = 2150000,
-		.frequency_stepsize = 125,     /* kHz for QPSK frontends */
+		.frequency_min_hz      =  950 * MHz,
+		.frequency_max_hz      = 2150 * MHz,
+		.frequency_stepsize_hz =  125 * kHz,
 		.symbol_rate_min  = 1000000,
 		.symbol_rate_max  = 45000000,
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/dvb-frontends/tda8083.c b/drivers/media/dvb-frontends/tda8083.c
index 29b4f64c030c..53b26060db7e 100644
--- a/drivers/media/dvb-frontends/tda8083.c
+++ b/drivers/media/dvb-frontends/tda8083.c
@@ -453,10 +453,9 @@ static const struct dvb_frontend_ops tda8083_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "Philips TDA8083 DVB-S",
-		.frequency_min		= 920000,     /* TDA8060 */
-		.frequency_max		= 2200000,    /* TDA8060 */
-		.frequency_stepsize	= 125,   /* kHz for QPSK frontends */
-	/*      .frequency_tolerance	= ???,*/
+		.frequency_min_hz	=  920 * MHz,     /* TDA8060 */
+		.frequency_max_hz	= 2200 * MHz,    /* TDA8060 */
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min	= 12000000,
 		.symbol_rate_max	= 30000000,
 	/*      .symbol_rate_tolerance	= ???,*/
diff --git a/drivers/media/dvb-frontends/ves1820.c b/drivers/media/dvb-frontends/ves1820.c
index 17600989f121..eb1249d81310 100644
--- a/drivers/media/dvb-frontends/ves1820.c
+++ b/drivers/media/dvb-frontends/ves1820.c
@@ -412,9 +412,9 @@ static const struct dvb_frontend_ops ves1820_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name = "VLSI VES1820 DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min = 47000000,
-		.frequency_max = 862000000,
+		.frequency_min_hz =  47 * MHz,
+		.frequency_max_hz = 862 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.caps = FE_CAN_QAM_16 |
 			FE_CAN_QAM_32 |
 			FE_CAN_QAM_64 |
diff --git a/drivers/media/dvb-frontends/ves1x93.c b/drivers/media/dvb-frontends/ves1x93.c
index 0c7b3286b04d..ddc5bfd84cd5 100644
--- a/drivers/media/dvb-frontends/ves1x93.c
+++ b/drivers/media/dvb-frontends/ves1x93.c
@@ -516,10 +516,10 @@ static const struct dvb_frontend_ops ves1x93_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "VLSI VES1x93 DVB-S",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,		 /* kHz for QPSK frontends */
-		.frequency_tolerance	= 29500,
+		.frequency_min_hz	=   950 * MHz,
+		.frequency_max_hz	=  2150 * MHz,
+		.frequency_stepsize_hz	=   125 * kHz,
+		.frequency_tolerance_hz	= 29500 * kHz,
 		.symbol_rate_min	= 1000000,
 		.symbol_rate_max	= 45000000,
 	/*	.symbol_rate_tolerance	=	???,*/
diff --git a/drivers/media/dvb-frontends/zl10036.c b/drivers/media/dvb-frontends/zl10036.c
index e5a432fd84c3..f1c92338015d 100644
--- a/drivers/media/dvb-frontends/zl10036.c
+++ b/drivers/media/dvb-frontends/zl10036.c
@@ -311,8 +311,8 @@ static int zl10036_set_params(struct dvb_frontend *fe)
 
 	/* ensure correct values
 	 * maybe redundant as core already checks this */
-	if ((frequency < fe->ops.info.frequency_min)
-	||  (frequency > fe->ops.info.frequency_max))
+	if ((frequency < fe->ops.info.frequency_min_hz / kHz)
+	||  (frequency > fe->ops.info.frequency_max_hz / kHz))
 		return -EINVAL;
 
 	/*
diff --git a/drivers/media/dvb-frontends/zl10353.c b/drivers/media/dvb-frontends/zl10353.c
index c9901f45deb7..42e63a3fa121 100644
--- a/drivers/media/dvb-frontends/zl10353.c
+++ b/drivers/media/dvb-frontends/zl10353.c
@@ -635,10 +635,9 @@ static const struct dvb_frontend_ops zl10353_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Zarlink ZL10353 DVB-T",
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 |
 			FE_CAN_FEC_3_4 | FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 |
 			FE_CAN_FEC_AUTO |
diff --git a/drivers/media/firewire/firedtv-fe.c b/drivers/media/firewire/firedtv-fe.c
index a2ef4ede8ebe..69087ae6c1d0 100644
--- a/drivers/media/firewire/firedtv-fe.c
+++ b/drivers/media/firewire/firedtv-fe.c
@@ -152,7 +152,7 @@ static int fdtv_set_frontend(struct dvb_frontend *fe)
 void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 {
 	struct dvb_frontend_ops *ops = &fdtv->fe.ops;
-	struct dvb_frontend_info *fi = &ops->info;
+	struct dvb_frontend_internal_info *fi = &ops->info;
 
 	ops->init			= fdtv_dvb_init;
 	ops->sleep			= fdtv_sleep;
@@ -174,9 +174,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 	case FIREDTV_DVB_S:
 		ops->delsys[0]		= SYS_DVBS;
 
-		fi->frequency_min	= 950000;
-		fi->frequency_max	= 2150000;
-		fi->frequency_stepsize	= 125;
+		fi->frequency_min_hz	=   950 * MHz;
+		fi->frequency_max_hz	=  2150 * MHz;
+		fi->frequency_stepsize_hz = 125 * kHz;
 		fi->symbol_rate_min	= 1000000;
 		fi->symbol_rate_max	= 40000000;
 
@@ -194,9 +194,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 		ops->delsys[0]		= SYS_DVBS;
 		ops->delsys[1]		= SYS_DVBS2;
 
-		fi->frequency_min	= 950000;
-		fi->frequency_max	= 2150000;
-		fi->frequency_stepsize	= 125;
+		fi->frequency_min_hz	=   950 * MHz;
+		fi->frequency_max_hz	=  2150 * MHz;
+		fi->frequency_stepsize_hz = 125 * kHz;
 		fi->symbol_rate_min	= 1000000;
 		fi->symbol_rate_max	= 40000000;
 
@@ -214,9 +214,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 	case FIREDTV_DVB_C:
 		ops->delsys[0]		= SYS_DVBC_ANNEX_A;
 
-		fi->frequency_min	= 47000000;
-		fi->frequency_max	= 866000000;
-		fi->frequency_stepsize	= 62500;
+		fi->frequency_min_hz	=      47 * MHz;
+		fi->frequency_max_hz	=     866 * MHz;
+		fi->frequency_stepsize_hz = 62500;
 		fi->symbol_rate_min	= 870000;
 		fi->symbol_rate_max	= 6900000;
 
@@ -232,9 +232,9 @@ void fdtv_frontend_init(struct firedtv *fdtv, const char *name)
 	case FIREDTV_DVB_T:
 		ops->delsys[0]		= SYS_DVBT;
 
-		fi->frequency_min	= 49000000;
-		fi->frequency_max	= 861000000;
-		fi->frequency_stepsize	= 62500;
+		fi->frequency_min_hz	=  49 * MHz;
+		fi->frequency_max_hz	= 861 * MHz;
+		fi->frequency_stepsize_hz = 62500;
 
 		fi->caps		= FE_CAN_INVERSION_AUTO		|
 					  FE_CAN_FEC_2_3		|
diff --git a/drivers/media/pci/bt8xx/dst.c b/drivers/media/pci/bt8xx/dst.c
index 2e33b7236672..b98de2a22f78 100644
--- a/drivers/media/pci/bt8xx/dst.c
+++ b/drivers/media/pci/bt8xx/dst.c
@@ -1739,9 +1739,9 @@ static const struct dvb_frontend_ops dst_dvbt_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name = "DST DVB-T",
-		.frequency_min = 137000000,
-		.frequency_max = 858000000,
-		.frequency_stepsize = 166667,
+		.frequency_min_hz = 137 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 166667,
 		.caps = FE_CAN_FEC_AUTO			|
 			FE_CAN_QAM_AUTO			|
 			FE_CAN_QAM_16			|
@@ -1768,10 +1768,10 @@ static const struct dvb_frontend_ops dst_dvbs_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name = "DST DVB-S",
-		.frequency_min = 950000,
-		.frequency_max = 2150000,
-		.frequency_stepsize = 1000,	/* kHz for QPSK frontends */
-		.frequency_tolerance = 29500,
+		.frequency_min_hz   =  950 * MHz,
+		.frequency_max_hz   = 2150 * MHz,
+		.frequency_stepsize_hz = 1 * MHz,
+		.frequency_tolerance_hz = 29500 * kHz,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 	/*     . symbol_rate_tolerance	=	???,*/
@@ -1797,9 +1797,9 @@ static const struct dvb_frontend_ops dst_dvbc_ops = {
 	.delsys = { SYS_DVBC_ANNEX_A },
 	.info = {
 		.name = "DST DVB-C",
-		.frequency_stepsize = 62500,
-		.frequency_min = 51000000,
-		.frequency_max = 858000000,
+		.frequency_min_hz =  51 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_FEC_AUTO |
@@ -1826,9 +1826,9 @@ static const struct dvb_frontend_ops dst_atsc_ops = {
 	.delsys = { SYS_ATSC },
 	.info = {
 		.name = "DST ATSC",
-		.frequency_stepsize = 62500,
-		.frequency_min = 510000000,
-		.frequency_max = 858000000,
+		.frequency_min_hz = 510 * MHz,
+		.frequency_max_hz = 858 * MHz,
+		.frequency_stepsize_hz = 62500,
 		.symbol_rate_min = 1000000,
 		.symbol_rate_max = 45000000,
 		.caps = FE_CAN_FEC_AUTO | FE_CAN_QAM_AUTO | FE_CAN_QAM_64 | FE_CAN_QAM_256 | FE_CAN_8VSB
diff --git a/drivers/media/pci/bt8xx/dvb-bt8xx.c b/drivers/media/pci/bt8xx/dvb-bt8xx.c
index 6b2a9e6eb6a8..2f810b7130e6 100644
--- a/drivers/media/pci/bt8xx/dvb-bt8xx.c
+++ b/drivers/media/pci/bt8xx/dvb-bt8xx.c
@@ -602,8 +602,8 @@ static void frontend_init(struct dvb_bt8xx_card *card, u32 type)
 
 		if (card->fe != NULL) {
 			card->fe->ops.tuner_ops.calc_regs = thomson_dtt7579_tuner_calc_regs;
-			card->fe->ops.info.frequency_min = 174000000;
-			card->fe->ops.info.frequency_max = 862000000;
+			card->fe->ops.info.frequency_min_hz = 174 * MHz;
+			card->fe->ops.info.frequency_max_hz = 862 * MHz;
 		}
 		break;
 
@@ -655,8 +655,8 @@ static void frontend_init(struct dvb_bt8xx_card *card, u32 type)
 		card->fe = dvb_attach(mt352_attach, &advbt771_samsung_tdtc9251dh0_config, card->i2c_adapter);
 		if (card->fe != NULL) {
 			card->fe->ops.tuner_ops.calc_regs = advbt771_samsung_tdtc9251dh0_tuner_calc_regs;
-			card->fe->ops.info.frequency_min = 174000000;
-			card->fe->ops.info.frequency_max = 862000000;
+			card->fe->ops.info.frequency_min_hz = 174 * MHz;
+			card->fe->ops.info.frequency_max_hz = 862 * MHz;
 		}
 		break;
 
diff --git a/drivers/media/pci/ddbridge/ddbridge-sx8.c b/drivers/media/pci/ddbridge/ddbridge-sx8.c
index 4418604258d1..64f05f5ee039 100644
--- a/drivers/media/pci/ddbridge/ddbridge-sx8.c
+++ b/drivers/media/pci/ddbridge/ddbridge-sx8.c
@@ -454,10 +454,8 @@ static struct dvb_frontend_ops sx8_ops = {
 	.delsys = { SYS_DVBS, SYS_DVBS2 },
 	.info = {
 		.name			= "Digital Devices MaxSX8 MCI DVB-S/S2/S2X",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 0,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
 		.symbol_rate_min	= 100000,
 		.symbol_rate_max	= 100000000,
 		.caps			= FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/pci/mantis/mantis_vp3030.c b/drivers/media/pci/mantis/mantis_vp3030.c
index 14f6e153000c..9797c9fd8259 100644
--- a/drivers/media/pci/mantis/mantis_vp3030.c
+++ b/drivers/media/pci/mantis/mantis_vp3030.c
@@ -42,8 +42,8 @@ static struct zl10353_config mantis_vp3030_config = {
 static struct tda665x_config env57h12d5_config = {
 	.name			= "ENV57H12D5 (ET-50DT)",
 	.addr			= 0x60,
-	.frequency_min		=  47000000,
-	.frequency_max		= 862000000,
+	.frequency_min		=  47 * MHz,
+	.frequency_max		= 862 * MHz,
 	.frequency_offst	=   3616667,
 	.ref_multiplier		= 6, /* 1/6 MHz */
 	.ref_divider		= 100000, /* 1/6 MHz */
diff --git a/drivers/media/tuners/mxl5007t.c b/drivers/media/tuners/mxl5007t.c
index 4081fd97c3b2..54d9226aaff7 100644
--- a/drivers/media/tuners/mxl5007t.c
+++ b/drivers/media/tuners/mxl5007t.c
@@ -59,8 +59,6 @@ MODULE_PARM_DESC(debug, "set debug level");
 
 /* ------------------------------------------------------------------------- */
 
-#define MHz 1000000
-
 enum mxl5007t_mode {
 	MxL_MODE_ISDBT     =    0,
 	MxL_MODE_DVBT      =    1,
diff --git a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
index 221cf46b4140..9f74453799a2 100644
--- a/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
+++ b/drivers/media/usb/dvb-usb-v2/mxl111sf-demod.c
@@ -554,9 +554,9 @@ static const struct dvb_frontend_ops mxl111sf_demod_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name               = "MaxLinear MxL111SF DVB-T demodulator",
-		.frequency_min      = 177000000,
-		.frequency_max      = 858000000,
-		.frequency_stepsize = 166666,
+		.frequency_min_hz      = 177 * MHz,
+		.frequency_max_hz      = 858 * MHz,
+		.frequency_stepsize_hz = 166666,
 		.caps = FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QPSK | FE_CAN_QAM_16 | FE_CAN_QAM_64 |
diff --git a/drivers/media/usb/dvb-usb/af9005-fe.c b/drivers/media/usb/dvb-usb/af9005-fe.c
index 7fbbc954da16..09cc3a21af65 100644
--- a/drivers/media/usb/dvb-usb/af9005-fe.c
+++ b/drivers/media/usb/dvb-usb/af9005-fe.c
@@ -1455,9 +1455,9 @@ static const struct dvb_frontend_ops af9005_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		 .name = "AF9005 USB DVB-T",
-		 .frequency_min = 44250000,
-		 .frequency_max = 867250000,
-		 .frequency_stepsize = 250000,
+		 .frequency_min_hz =    44250 * kHz,
+		 .frequency_max_hz =   867250 * kHz,
+		 .frequency_stepsize_hz = 250 * kHz,
 		 .caps = FE_CAN_INVERSION_AUTO |
 		 FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 		 FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/usb/dvb-usb/cinergyT2-fe.c b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
index 5a2f81311fb7..df71df7ed524 100644
--- a/drivers/media/usb/dvb-usb/cinergyT2-fe.c
+++ b/drivers/media/usb/dvb-usb/cinergyT2-fe.c
@@ -295,9 +295,9 @@ static const struct dvb_frontend_ops cinergyt2_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= DRIVER_NAME,
-		.frequency_min		= 174000000,
-		.frequency_max		= 862000000,
-		.frequency_stepsize	= 166667,
+		.frequency_min_hz	= 174 * MHz,
+		.frequency_max_hz	= 862 * MHz,
+		.frequency_stepsize_hz	= 166667,
 		.caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_1_2
 			| FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4
 			| FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8
diff --git a/drivers/media/usb/dvb-usb/dtt200u-fe.c b/drivers/media/usb/dvb-usb/dtt200u-fe.c
index 7e75aae34fb8..1ca3a51b2ae3 100644
--- a/drivers/media/usb/dvb-usb/dtt200u-fe.c
+++ b/drivers/media/usb/dvb-usb/dtt200u-fe.c
@@ -230,9 +230,9 @@ static const struct dvb_frontend_ops dtt200u_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "WideView USB DVB-T",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 250000,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	=    250 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/usb/dvb-usb/friio-fe.c b/drivers/media/usb/dvb-usb/friio-fe.c
index 932f262452eb..e6bd0ed8d789 100644
--- a/drivers/media/usb/dvb-usb/friio-fe.c
+++ b/drivers/media/usb/dvb-usb/friio-fe.c
@@ -133,10 +133,10 @@ static int jdvbt90502_pll_set_freq(struct jdvbt90502_state *state, u32 freq)
 	u32 f;
 
 	deb_fe("%s: freq=%d, step=%d\n", __func__, freq,
-	       state->frontend.ops.info.frequency_stepsize);
+	       state->frontend.ops.info.frequency_stepsize_hz);
 	/* freq -> oscilator frequency conversion. */
 	/* freq: 473,000,000 + n*6,000,000 [+ 142857 (center freq. shift)] */
-	f = freq / state->frontend.ops.info.frequency_stepsize;
+	f = freq / state->frontend.ops.info.frequency_stepsize_hz;
 	/* add 399[1/7 MHZ] = 57MHz for the IF  */
 	f += 399;
 	/* add center frequency shift if necessary */
@@ -413,10 +413,9 @@ static const struct dvb_frontend_ops jdvbt90502_ops = {
 	.delsys = { SYS_ISDBT },
 	.info = {
 		.name			= "Comtech JDVBT90502 ISDB-T",
-		.frequency_min		= 473000000, /* UHF 13ch, center */
-		.frequency_max		= 767142857, /* UHF 62ch, center */
-		.frequency_stepsize	= JDVBT90502_PLL_CLK / JDVBT90502_PLL_DIVIDER,
-		.frequency_tolerance	= 0,
+		.frequency_min_hz	= 473000000, /* UHF 13ch, center */
+		.frequency_max_hz	= 767142857, /* UHF 62ch, center */
+		.frequency_stepsize_hz	= JDVBT90502_PLL_CLK / JDVBT90502_PLL_DIVIDER,
 
 		/* NOTE: this driver ignores all parameters but frequency. */
 		.caps = FE_CAN_INVERSION_AUTO |
diff --git a/drivers/media/usb/dvb-usb/vp702x-fe.c b/drivers/media/usb/dvb-usb/vp702x-fe.c
index ae48146e005c..9eb811452f2e 100644
--- a/drivers/media/usb/dvb-usb/vp702x-fe.c
+++ b/drivers/media/usb/dvb-usb/vp702x-fe.c
@@ -349,10 +349,9 @@ static const struct dvb_frontend_ops vp702x_fe_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name           = "Twinhan DST-like frontend (VP7021/VP7020) DVB-S",
-		.frequency_min       = 950000,
-		.frequency_max       = 2150000,
-		.frequency_stepsize  = 1000,   /* kHz for QPSK frontends */
-		.frequency_tolerance = 0,
+		.frequency_min_hz       =  950 * MHz,
+		.frequency_max_hz       = 2150 * MHz,
+		.frequency_stepsize_hz  =    1 * MHz,
 		.symbol_rate_min     = 1000000,
 		.symbol_rate_max     = 45000000,
 		.symbol_rate_tolerance = 500,  /* ppm */
diff --git a/drivers/media/usb/dvb-usb/vp7045-fe.c b/drivers/media/usb/dvb-usb/vp7045-fe.c
index f86040173b8d..1173ae29885b 100644
--- a/drivers/media/usb/dvb-usb/vp7045-fe.c
+++ b/drivers/media/usb/dvb-usb/vp7045-fe.c
@@ -162,9 +162,9 @@ static const struct dvb_frontend_ops vp7045_fe_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "Twinhan VP7045/46 USB DVB-T",
-		.frequency_min		= 44250000,
-		.frequency_max		= 867250000,
-		.frequency_stepsize	= 1000,
+		.frequency_min_hz	=  44250 * kHz,
+		.frequency_max_hz	= 867250 * kHz,
+		.frequency_stepsize_hz	=      1 * kHz,
 		.caps = FE_CAN_INVERSION_AUTO |
 				FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 				FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
diff --git a/drivers/media/usb/ttusb-dec/ttusbdecfe.c b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
index 6ea05d909024..278bf6c5855b 100644
--- a/drivers/media/usb/ttusb-dec/ttusbdecfe.c
+++ b/drivers/media/usb/ttusb-dec/ttusbdecfe.c
@@ -247,9 +247,9 @@ static const struct dvb_frontend_ops ttusbdecfe_dvbt_ops = {
 	.delsys = { SYS_DVBT },
 	.info = {
 		.name			= "TechnoTrend/Hauppauge DEC2000-t Frontend",
-		.frequency_min		= 51000000,
-		.frequency_max		= 858000000,
-		.frequency_stepsize	= 62500,
+		.frequency_min_hz	=  51 * MHz,
+		.frequency_max_hz	= 858 * MHz,
+		.frequency_stepsize_hz	= 62500,
 		.caps =	FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
 			FE_CAN_FEC_5_6 | FE_CAN_FEC_7_8 | FE_CAN_FEC_AUTO |
 			FE_CAN_QAM_16 | FE_CAN_QAM_64 | FE_CAN_QAM_AUTO |
@@ -270,9 +270,9 @@ static const struct dvb_frontend_ops ttusbdecfe_dvbs_ops = {
 	.delsys = { SYS_DVBS },
 	.info = {
 		.name			= "TechnoTrend/Hauppauge DEC3000-s Frontend",
-		.frequency_min		= 950000,
-		.frequency_max		= 2150000,
-		.frequency_stepsize	= 125,
+		.frequency_min_hz	=  950 * MHz,
+		.frequency_max_hz	= 2150 * MHz,
+		.frequency_stepsize_hz	=  125 * kHz,
 		.symbol_rate_min        = 1000000,  /* guessed */
 		.symbol_rate_max        = 45000000, /* guessed */
 		.caps =	FE_CAN_FEC_1_2 | FE_CAN_FEC_2_3 | FE_CAN_FEC_3_4 |
diff --git a/include/media/dvb_frontend.h b/include/media/dvb_frontend.h
index aebaec2dc725..6f7a85ab3541 100644
--- a/include/media/dvb_frontend.h
+++ b/include/media/dvb_frontend.h
@@ -317,6 +317,34 @@ struct analog_demod_ops {
 
 struct dtv_frontend_properties;
 
+/**
+ * struct dvb_frontend_internal_info - Frontend properties and capabilities
+ *
+ * @name:			Name of the frontend
+ * @frequency_min_hz:		Minimal frequency supported by the frontend.
+ * @frequency_max_hz:		Minimal frequency supported by the frontend.
+ * @frequency_stepsize_hz:	All frequencies are multiple of this value.
+ * @frequency_tolerance_hz:	Frequency tolerance.
+ * @symbol_rate_min:		Minimal symbol rate, in bauds
+ *				(for Cable/Satellite systems).
+ * @symbol_rate_max:		Maximal symbol rate, in bauds
+ *				(for Cable/Satellite systems).
+ * @symbol_rate_tolerance:	Maximal symbol rate tolerance, in ppm
+ *				(for Cable/Satellite systems).
+ * @caps:			Capabilities supported by the frontend,
+ *				as specified in &enum fe_caps.
+ */
+struct dvb_frontend_internal_info {
+	char	name[128];
+	u32	frequency_min_hz;
+	u32	frequency_max_hz;
+	u32	frequency_stepsize_hz;
+	u32	frequency_tolerance_hz;
+	u32	symbol_rate_min;
+	u32	symbol_rate_max;
+	u32	symbol_rate_tolerance;
+	enum fe_caps caps;
+};
 
 /**
  * struct dvb_frontend_ops - Demodulation information and callbacks for
@@ -404,7 +432,7 @@ struct dtv_frontend_properties;
  * @analog_ops:		pointer to &struct analog_demod_ops
  */
 struct dvb_frontend_ops {
-	struct dvb_frontend_info info;
+	struct dvb_frontend_internal_info info;
 
 	u8 delsys[MAX_DELSYS];
 
-- 
cgit v1.2.3


From 6a2a1ca34ca68025df793a1bedfba658be2b1952 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Thu, 5 Jul 2018 18:59:37 -0400
Subject: media: dvb_frontend: ensure that the step is ok for both FE and tuner

The frequency step should take into account the tuner step,
as, if tuner step is bigger than frontend step, the zigzag
algorithm won't be doing the right thing, as it will be
tuning multiple times at the same frequency.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-core/dvb_frontend.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/media/dvb-core/dvb_frontend.c b/drivers/media/dvb-core/dvb_frontend.c
index fe0fae482ba4..c4e7ebfe4d29 100644
--- a/drivers/media/dvb-core/dvb_frontend.c
+++ b/drivers/media/dvb-core/dvb_frontend.c
@@ -939,7 +939,10 @@ static void dvb_frontend_get_frequency_limits(struct dvb_frontend *fe,
 static u32 dvb_frontend_get_stepsize(struct dvb_frontend *fe)
 {
 	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
-	u32 step = fe->ops.info.frequency_stepsize_hz;
+	u32 fe_step = fe->ops.info.frequency_stepsize_hz;
+	u32 tuner_step = fe->ops.tuner_ops.info.frequency_step_hz;
+	u32 step = max(fe_step, tuner_step);
+
 	switch (c->delivery_system) {
 	case SYS_DVBS:
 	case SYS_DVBS2:
-- 
cgit v1.2.3


From 1b7369acc465ddf3d9c7604af3971753b9a548f2 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 9 Jul 2018 11:19:02 -0400
Subject: media: headers: fix linux/mod_devicetable.h inclusions

A couple of drivers produced build errors after the mod_devicetable.h
header was split out from the platform_device one, e.g.

drivers/media/platform/davinci/vpbe_osd.c:42:40: error: array type has incomplete element type 'struct platform_device_id'
drivers/media/platform/davinci/vpbe_venc.c:42:40: error: array type has incomplete element type 'struct platform_device_id'

This adds the inclusion where needed.

Fixes: ac3167257b9f ("headers: separate linux/mod_devicetable.h from linux/platform_device.h")

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Lad, Prabhakar <prabhakar.csengg@gmail.com>
Acked-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/firmware/qemu_fw_cfg.c             | 1 +
 drivers/media/platform/davinci/vpbe_osd.c  | 1 +
 drivers/media/platform/davinci/vpbe_venc.c | 1 +
 drivers/media/platform/qcom/venus/vdec.c   | 1 +
 drivers/media/platform/qcom/venus/venc.c   | 1 +
 drivers/media/platform/sti/hva/hva-v4l2.c  | 1 +
 drivers/platform/x86/intel_punit_ipc.c     | 1 +
 7 files changed, 7 insertions(+)

diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 14fedbeca724..039e0f91dba8 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
diff --git a/drivers/media/platform/davinci/vpbe_osd.c b/drivers/media/platform/davinci/vpbe_osd.c
index 7f610320426d..c551a25d90d9 100644
--- a/drivers/media/platform/davinci/vpbe_osd.c
+++ b/drivers/media/platform/davinci/vpbe_osd.c
@@ -18,6 +18,7 @@
  *
  */
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/kernel.h>
 #include <linux/interrupt.h>
 #include <linux/platform_device.h>
diff --git a/drivers/media/platform/davinci/vpbe_venc.c b/drivers/media/platform/davinci/vpbe_venc.c
index ba157827192c..ddcad7b3e76c 100644
--- a/drivers/media/platform/davinci/vpbe_venc.c
+++ b/drivers/media/platform/davinci/vpbe_venc.c
@@ -11,6 +11,7 @@
  * GNU General Public License for more details.
  */
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/ctype.h>
diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
index 0d043c33cd83..dfbbbf0f746f 100644
--- a/drivers/media/platform/qcom/venus/vdec.c
+++ b/drivers/media/platform/qcom/venus/vdec.c
@@ -14,6 +14,7 @@
  */
 #include <linux/clk.h>
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
diff --git a/drivers/media/platform/qcom/venus/venc.c b/drivers/media/platform/qcom/venus/venc.c
index 20d7246a3ef9..41249d1443fa 100644
--- a/drivers/media/platform/qcom/venus/venc.c
+++ b/drivers/media/platform/qcom/venus/venc.c
@@ -14,6 +14,7 @@
  */
 #include <linux/clk.h>
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
diff --git a/drivers/media/platform/sti/hva/hva-v4l2.c b/drivers/media/platform/sti/hva/hva-v4l2.c
index 15080cb00fa7..5a807c7c5e79 100644
--- a/drivers/media/platform/sti/hva/hva-v4l2.c
+++ b/drivers/media/platform/sti/hva/hva-v4l2.c
@@ -6,6 +6,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <media/v4l2-event.h>
diff --git a/drivers/platform/x86/intel_punit_ipc.c b/drivers/platform/x86/intel_punit_ipc.c
index b5b890127479..f1afc0ebbc68 100644
--- a/drivers/platform/x86/intel_punit_ipc.c
+++ b/drivers/platform/x86/intel_punit_ipc.c
@@ -12,6 +12,7 @@
  */
 
 #include <linux/module.h>
+#include <linux/mod_devicetable.h>
 #include <linux/acpi.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
-- 
cgit v1.2.3


From 0a4c58f5702858822621fa1177c7d3475f181ccb Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:17 -0700
Subject: bpf: add ability to charge bpf maps memory dynamically

This commits extends existing bpf maps memory charging API
to support dynamic charging/uncharging.

This is required to account memory used by maps,
if all entries are created dynamically after
the map initialization.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h  |  2 ++
 kernel/bpf/syscall.c | 58 ++++++++++++++++++++++++++++++++++++++--------------
 2 files changed, 45 insertions(+), 15 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5b5ad95cf339..5a4a256473c3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -435,6 +435,8 @@ struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_precharge_memlock(u32 pages);
+int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
+void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
 void *bpf_map_area_alloc(size_t size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index a31a1ba0f8ea..7958252a4d29 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -181,32 +181,60 @@ int bpf_map_precharge_memlock(u32 pages)
 	return 0;
 }
 
-static int bpf_map_charge_memlock(struct bpf_map *map)
+static int bpf_charge_memlock(struct user_struct *user, u32 pages)
 {
-	struct user_struct *user = get_current_user();
-	unsigned long memlock_limit;
+	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
 
-	memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+	if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {
+		atomic_long_sub(pages, &user->locked_vm);
+		return -EPERM;
+	}
+	return 0;
+}
 
-	atomic_long_add(map->pages, &user->locked_vm);
+static void bpf_uncharge_memlock(struct user_struct *user, u32 pages)
+{
+	atomic_long_sub(pages, &user->locked_vm);
+}
+
+static int bpf_map_init_memlock(struct bpf_map *map)
+{
+	struct user_struct *user = get_current_user();
+	int ret;
 
-	if (atomic_long_read(&user->locked_vm) > memlock_limit) {
-		atomic_long_sub(map->pages, &user->locked_vm);
+	ret = bpf_charge_memlock(user, map->pages);
+	if (ret) {
 		free_uid(user);
-		return -EPERM;
+		return ret;
 	}
 	map->user = user;
-	return 0;
+	return ret;
 }
 
-static void bpf_map_uncharge_memlock(struct bpf_map *map)
+static void bpf_map_release_memlock(struct bpf_map *map)
 {
 	struct user_struct *user = map->user;
-
-	atomic_long_sub(map->pages, &user->locked_vm);
+	bpf_uncharge_memlock(user, map->pages);
 	free_uid(user);
 }
 
+int bpf_map_charge_memlock(struct bpf_map *map, u32 pages)
+{
+	int ret;
+
+	ret = bpf_charge_memlock(map->user, pages);
+	if (ret)
+		return ret;
+	map->pages += pages;
+	return ret;
+}
+
+void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages)
+{
+	bpf_uncharge_memlock(map->user, pages);
+	map->pages -= pages;
+}
+
 static int bpf_map_alloc_id(struct bpf_map *map)
 {
 	int id;
@@ -256,7 +284,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 {
 	struct bpf_map *map = container_of(work, struct bpf_map, work);
 
-	bpf_map_uncharge_memlock(map);
+	bpf_map_release_memlock(map);
 	security_bpf_map_free(map);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
@@ -492,7 +520,7 @@ static int map_create(union bpf_attr *attr)
 	if (err)
 		goto free_map_nouncharge;
 
-	err = bpf_map_charge_memlock(map);
+	err = bpf_map_init_memlock(map);
 	if (err)
 		goto free_map_sec;
 
@@ -515,7 +543,7 @@ static int map_create(union bpf_attr *attr)
 	return err;
 
 free_map:
-	bpf_map_uncharge_memlock(map);
+	bpf_map_release_memlock(map);
 free_map_sec:
 	security_bpf_map_free(map);
 free_map_nouncharge:
-- 
cgit v1.2.3


From de9cbbaadba5adf88a19e46df61f7054000838f6 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:18 -0700
Subject: bpf: introduce cgroup storage maps

This commit introduces BPF_MAP_TYPE_CGROUP_STORAGE maps:
a special type of maps which are implementing the cgroup storage.

>From the userspace point of view it's almost a generic
hash map with the (cgroup inode id, attachment type) pair
used as a key.

The only difference is that some operations are restricted:
  1) a user can't create new entries,
  2) a user can't remove existing entries.

The lookup from userspace is o(log(n)).

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf-cgroup.h |  38 +++++
 include/linux/bpf.h        |   1 +
 include/linux/bpf_types.h  |   3 +
 include/uapi/linux/bpf.h   |   6 +
 kernel/bpf/Makefile        |   1 +
 kernel/bpf/local_storage.c | 376 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c       |   3 +
 kernel/bpf/verifier.c      |  12 ++
 8 files changed, 440 insertions(+)
 create mode 100644 kernel/bpf/local_storage.c

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index d50c2f0a655a..7d00d58869ed 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -4,19 +4,39 @@
 
 #include <linux/errno.h>
 #include <linux/jump_label.h>
+#include <linux/rbtree.h>
 #include <uapi/linux/bpf.h>
 
 struct sock;
 struct sockaddr;
 struct cgroup;
 struct sk_buff;
+struct bpf_map;
+struct bpf_prog;
 struct bpf_sock_ops_kern;
+struct bpf_cgroup_storage;
 
 #ifdef CONFIG_CGROUP_BPF
 
 extern struct static_key_false cgroup_bpf_enabled_key;
 #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
 
+struct bpf_cgroup_storage_map;
+
+struct bpf_storage_buffer {
+	struct rcu_head rcu;
+	char data[0];
+};
+
+struct bpf_cgroup_storage {
+	struct bpf_storage_buffer *buf;
+	struct bpf_cgroup_storage_map *map;
+	struct bpf_cgroup_storage_key key;
+	struct list_head list;
+	struct rb_node node;
+	struct rcu_head rcu;
+};
+
 struct bpf_prog_list {
 	struct list_head node;
 	struct bpf_prog *prog;
@@ -77,6 +97,15 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum bpf_attach_type type);
 
+struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog);
+void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage);
+void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
+			     struct cgroup *cgroup,
+			     enum bpf_attach_type type);
+void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage);
+int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *map);
+void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *map);
+
 /* Wrappers for __cgroup_bpf_run_filter_skb() guarded by cgroup_bpf_enabled. */
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb)			      \
 ({									      \
@@ -221,6 +250,15 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
+static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog,
+					    struct bpf_map *map) { return 0; }
+static inline void bpf_cgroup_storage_release(struct bpf_prog *prog,
+					      struct bpf_map *map) {}
+static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
+	struct bpf_prog *prog) { return 0; }
+static inline void bpf_cgroup_storage_free(
+	struct bpf_cgroup_storage *storage) {}
+
 #define cgroup_bpf_enabled (0)
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5a4a256473c3..9d1e4727495e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -282,6 +282,7 @@ struct bpf_prog_aux {
 	struct bpf_prog *prog;
 	struct user_struct *user;
 	u64 load_time; /* ns since boottime */
+	struct bpf_map *cgroup_storage;
 	char name[BPF_OBJ_NAME_LEN];
 #ifdef CONFIG_SECURITY
 	void *security;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index c5700c2d5549..add08be53b6f 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -37,6 +37,9 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_PERF_EVENT_ARRAY, perf_event_array_map_ops)
 #ifdef CONFIG_CGROUPS
 BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_ARRAY, cgroup_array_map_ops)
 #endif
+#ifdef CONFIG_CGROUP_BPF
+BPF_MAP_TYPE(BPF_MAP_TYPE_CGROUP_STORAGE, cgroup_storage_map_ops)
+#endif
 BPF_MAP_TYPE(BPF_MAP_TYPE_HASH, htab_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_HASH, htab_percpu_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_LRU_HASH, htab_lru_map_ops)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0ebaaf7f3568..b10118ee5afe 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
 	__u8	data[0];	/* Arbitrary size */
 };
 
+struct bpf_cgroup_storage_key {
+	__u64	cgroup_inode_id;	/* cgroup inode id */
+	__u32	attach_type;		/* program attach type */
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
 	BPF_MAP_CREATE,
@@ -120,6 +125,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
+	BPF_MAP_TYPE_CGROUP_STORAGE,
 };
 
 enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index f27f5496d6fe..e8906cbad81f 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -3,6 +3,7 @@ obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
new file mode 100644
index 000000000000..f23d3fdeba23
--- /dev/null
+++ b/kernel/bpf/local_storage.c
@@ -0,0 +1,376 @@
+//SPDX-License-Identifier: GPL-2.0
+#include <linux/bpf-cgroup.h>
+#include <linux/bpf.h>
+#include <linux/bug.h>
+#include <linux/filter.h>
+#include <linux/mm.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+
+#ifdef CONFIG_CGROUP_BPF
+
+#define LOCAL_STORAGE_CREATE_FLAG_MASK					\
+	(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)
+
+struct bpf_cgroup_storage_map {
+	struct bpf_map map;
+
+	spinlock_t lock;
+	struct bpf_prog *prog;
+	struct rb_root root;
+	struct list_head list;
+};
+
+static struct bpf_cgroup_storage_map *map_to_storage(struct bpf_map *map)
+{
+	return container_of(map, struct bpf_cgroup_storage_map, map);
+}
+
+static int bpf_cgroup_storage_key_cmp(
+	const struct bpf_cgroup_storage_key *key1,
+	const struct bpf_cgroup_storage_key *key2)
+{
+	if (key1->cgroup_inode_id < key2->cgroup_inode_id)
+		return -1;
+	else if (key1->cgroup_inode_id > key2->cgroup_inode_id)
+		return 1;
+	else if (key1->attach_type < key2->attach_type)
+		return -1;
+	else if (key1->attach_type > key2->attach_type)
+		return 1;
+	return 0;
+}
+
+static struct bpf_cgroup_storage *cgroup_storage_lookup(
+	struct bpf_cgroup_storage_map *map, struct bpf_cgroup_storage_key *key,
+	bool locked)
+{
+	struct rb_root *root = &map->root;
+	struct rb_node *node;
+
+	if (!locked)
+		spin_lock_bh(&map->lock);
+
+	node = root->rb_node;
+	while (node) {
+		struct bpf_cgroup_storage *storage;
+
+		storage = container_of(node, struct bpf_cgroup_storage, node);
+
+		switch (bpf_cgroup_storage_key_cmp(key, &storage->key)) {
+		case -1:
+			node = node->rb_left;
+			break;
+		case 1:
+			node = node->rb_right;
+			break;
+		default:
+			if (!locked)
+				spin_unlock_bh(&map->lock);
+			return storage;
+		}
+	}
+
+	if (!locked)
+		spin_unlock_bh(&map->lock);
+
+	return NULL;
+}
+
+static int cgroup_storage_insert(struct bpf_cgroup_storage_map *map,
+				 struct bpf_cgroup_storage *storage)
+{
+	struct rb_root *root = &map->root;
+	struct rb_node **new = &(root->rb_node), *parent = NULL;
+
+	while (*new) {
+		struct bpf_cgroup_storage *this;
+
+		this = container_of(*new, struct bpf_cgroup_storage, node);
+
+		parent = *new;
+		switch (bpf_cgroup_storage_key_cmp(&storage->key, &this->key)) {
+		case -1:
+			new = &((*new)->rb_left);
+			break;
+		case 1:
+			new = &((*new)->rb_right);
+			break;
+		default:
+			return -EEXIST;
+		}
+	}
+
+	rb_link_node(&storage->node, parent, new);
+	rb_insert_color(&storage->node, root);
+
+	return 0;
+}
+
+static void *cgroup_storage_lookup_elem(struct bpf_map *_map, void *_key)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage *storage;
+
+	storage = cgroup_storage_lookup(map, key, false);
+	if (!storage)
+		return NULL;
+
+	return &READ_ONCE(storage->buf)->data[0];
+}
+
+static int cgroup_storage_update_elem(struct bpf_map *map, void *_key,
+				      void *value, u64 flags)
+{
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage *storage;
+	struct bpf_storage_buffer *new;
+
+	if (flags & BPF_NOEXIST)
+		return -EINVAL;
+
+	storage = cgroup_storage_lookup((struct bpf_cgroup_storage_map *)map,
+					key, false);
+	if (!storage)
+		return -ENOENT;
+
+	new = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+			   map->value_size, __GFP_ZERO | GFP_USER,
+			   map->numa_node);
+	if (!new)
+		return -ENOMEM;
+
+	memcpy(&new->data[0], value, map->value_size);
+
+	new = xchg(&storage->buf, new);
+	kfree_rcu(new, rcu);
+
+	return 0;
+}
+
+static int cgroup_storage_get_next_key(struct bpf_map *_map, void *_key,
+				       void *_next_key)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	struct bpf_cgroup_storage_key *key = _key;
+	struct bpf_cgroup_storage_key *next = _next_key;
+	struct bpf_cgroup_storage *storage;
+
+	spin_lock_bh(&map->lock);
+
+	if (list_empty(&map->list))
+		goto enoent;
+
+	if (key) {
+		storage = cgroup_storage_lookup(map, key, true);
+		if (!storage)
+			goto enoent;
+
+		storage = list_next_entry(storage, list);
+		if (!storage)
+			goto enoent;
+	} else {
+		storage = list_first_entry(&map->list,
+					 struct bpf_cgroup_storage, list);
+	}
+
+	spin_unlock_bh(&map->lock);
+	next->attach_type = storage->key.attach_type;
+	next->cgroup_inode_id = storage->key.cgroup_inode_id;
+	return 0;
+
+enoent:
+	spin_unlock_bh(&map->lock);
+	return -ENOENT;
+}
+
+static struct bpf_map *cgroup_storage_map_alloc(union bpf_attr *attr)
+{
+	int numa_node = bpf_map_attr_numa_node(attr);
+	struct bpf_cgroup_storage_map *map;
+
+	if (attr->key_size != sizeof(struct bpf_cgroup_storage_key))
+		return ERR_PTR(-EINVAL);
+
+	if (attr->value_size > PAGE_SIZE)
+		return ERR_PTR(-E2BIG);
+
+	if (attr->map_flags & ~LOCAL_STORAGE_CREATE_FLAG_MASK)
+		/* reserved bits should not be used */
+		return ERR_PTR(-EINVAL);
+
+	if (attr->max_entries)
+		/* max_entries is not used and enforced to be 0 */
+		return ERR_PTR(-EINVAL);
+
+	map = kmalloc_node(sizeof(struct bpf_cgroup_storage_map),
+			   __GFP_ZERO | GFP_USER, numa_node);
+	if (!map)
+		return ERR_PTR(-ENOMEM);
+
+	map->map.pages = round_up(sizeof(struct bpf_cgroup_storage_map),
+				  PAGE_SIZE) >> PAGE_SHIFT;
+
+	/* copy mandatory map attributes */
+	bpf_map_init_from_attr(&map->map, attr);
+
+	spin_lock_init(&map->lock);
+	map->root = RB_ROOT;
+	INIT_LIST_HEAD(&map->list);
+
+	return &map->map;
+}
+
+static void cgroup_storage_map_free(struct bpf_map *_map)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+	WARN_ON(!RB_EMPTY_ROOT(&map->root));
+	WARN_ON(!list_empty(&map->list));
+
+	kfree(map);
+}
+
+static int cgroup_storage_delete_elem(struct bpf_map *map, void *key)
+{
+	return -EINVAL;
+}
+
+const struct bpf_map_ops cgroup_storage_map_ops = {
+	.map_alloc = cgroup_storage_map_alloc,
+	.map_free = cgroup_storage_map_free,
+	.map_get_next_key = cgroup_storage_get_next_key,
+	.map_lookup_elem = cgroup_storage_lookup_elem,
+	.map_update_elem = cgroup_storage_update_elem,
+	.map_delete_elem = cgroup_storage_delete_elem,
+};
+
+int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+	int ret = -EBUSY;
+
+	spin_lock_bh(&map->lock);
+
+	if (map->prog && map->prog != prog)
+		goto unlock;
+	if (prog->aux->cgroup_storage && prog->aux->cgroup_storage != _map)
+		goto unlock;
+
+	map->prog = prog;
+	prog->aux->cgroup_storage = _map;
+	ret = 0;
+unlock:
+	spin_unlock_bh(&map->lock);
+
+	return ret;
+}
+
+void bpf_cgroup_storage_release(struct bpf_prog *prog, struct bpf_map *_map)
+{
+	struct bpf_cgroup_storage_map *map = map_to_storage(_map);
+
+	spin_lock_bh(&map->lock);
+	if (map->prog == prog) {
+		WARN_ON(prog->aux->cgroup_storage != _map);
+		map->prog = NULL;
+		prog->aux->cgroup_storage = NULL;
+	}
+	spin_unlock_bh(&map->lock);
+}
+
+struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog)
+{
+	struct bpf_cgroup_storage *storage;
+	struct bpf_map *map;
+	u32 pages;
+
+	map = prog->aux->cgroup_storage;
+	if (!map)
+		return NULL;
+
+	pages = round_up(sizeof(struct bpf_cgroup_storage) +
+			 sizeof(struct bpf_storage_buffer) +
+			 map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+	if (bpf_map_charge_memlock(map, pages))
+		return ERR_PTR(-EPERM);
+
+	storage = kmalloc_node(sizeof(struct bpf_cgroup_storage),
+			       __GFP_ZERO | GFP_USER, map->numa_node);
+	if (!storage) {
+		bpf_map_uncharge_memlock(map, pages);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	storage->buf = kmalloc_node(sizeof(struct bpf_storage_buffer) +
+				    map->value_size, __GFP_ZERO | GFP_USER,
+				    map->numa_node);
+	if (!storage->buf) {
+		bpf_map_uncharge_memlock(map, pages);
+		kfree(storage);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	storage->map = (struct bpf_cgroup_storage_map *)map;
+
+	return storage;
+}
+
+void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage)
+{
+	u32 pages;
+	struct bpf_map *map;
+
+	if (!storage)
+		return;
+
+	map = &storage->map->map;
+	pages = round_up(sizeof(struct bpf_cgroup_storage) +
+			 sizeof(struct bpf_storage_buffer) +
+			 map->value_size, PAGE_SIZE) >> PAGE_SHIFT;
+	bpf_map_uncharge_memlock(map, pages);
+
+	kfree_rcu(storage->buf, rcu);
+	kfree_rcu(storage, rcu);
+}
+
+void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
+			     struct cgroup *cgroup,
+			     enum bpf_attach_type type)
+{
+	struct bpf_cgroup_storage_map *map;
+
+	if (!storage)
+		return;
+
+	storage->key.attach_type = type;
+	storage->key.cgroup_inode_id = cgroup->kn->id.id;
+
+	map = storage->map;
+
+	spin_lock_bh(&map->lock);
+	WARN_ON(cgroup_storage_insert(map, storage));
+	list_add(&storage->list, &map->list);
+	spin_unlock_bh(&map->lock);
+}
+
+void bpf_cgroup_storage_unlink(struct bpf_cgroup_storage *storage)
+{
+	struct bpf_cgroup_storage_map *map;
+	struct rb_root *root;
+
+	if (!storage)
+		return;
+
+	map = storage->map;
+
+	spin_lock_bh(&map->lock);
+	root = &map->root;
+	rb_erase(&storage->node, root);
+
+	list_del(&storage->list);
+	spin_unlock_bh(&map->lock);
+}
+
+#endif
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7958252a4d29..5af4e9e2722d 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -957,6 +957,9 @@ static void free_used_maps(struct bpf_prog_aux *aux)
 {
 	int i;
 
+	if (aux->cgroup_storage)
+		bpf_cgroup_storage_release(aux->prog, aux->cgroup_storage);
+
 	for (i = 0; i < aux->used_map_cnt; i++)
 		bpf_map_put(aux->used_maps[i]);
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index e948303a0ea8..7e75434a9e54 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5154,6 +5154,14 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env)
 			}
 			env->used_maps[env->used_map_cnt++] = map;
 
+			if (map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE &&
+			    bpf_cgroup_storage_assign(env->prog, map)) {
+				verbose(env,
+					"only one cgroup storage is allowed\n");
+				fdput(f);
+				return -EBUSY;
+			}
+
 			fdput(f);
 next_insn:
 			insn++;
@@ -5180,6 +5188,10 @@ static void release_maps(struct bpf_verifier_env *env)
 {
 	int i;
 
+	if (env->prog->aux->cgroup_storage)
+		bpf_cgroup_storage_release(env->prog,
+					   env->prog->aux->cgroup_storage);
+
 	for (i = 0; i < env->used_map_cnt; i++)
 		bpf_map_put(env->used_maps[i]);
 }
-- 
cgit v1.2.3


From aa0ad5b0391e268bdecf6cda31268388844f8afd Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:19 -0700
Subject: bpf: pass a pointer to a cgroup storage using pcpu variable

This commit introduces the bpf_cgroup_storage_set() helper,
which will be used to pass a pointer to a cgroup storage
to the bpf helper.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf-cgroup.h | 15 +++++++++++++++
 kernel/bpf/local_storage.c |  2 ++
 2 files changed, 17 insertions(+)

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 7d00d58869ed..9a144ddbbc8f 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -4,6 +4,7 @@
 
 #include <linux/errno.h>
 #include <linux/jump_label.h>
+#include <linux/percpu.h>
 #include <linux/rbtree.h>
 #include <uapi/linux/bpf.h>
 
@@ -21,6 +22,8 @@ struct bpf_cgroup_storage;
 extern struct static_key_false cgroup_bpf_enabled_key;
 #define cgroup_bpf_enabled static_branch_unlikely(&cgroup_bpf_enabled_key)
 
+DECLARE_PER_CPU(void*, bpf_cgroup_storage);
+
 struct bpf_cgroup_storage_map;
 
 struct bpf_storage_buffer {
@@ -97,6 +100,17 @@ int __cgroup_bpf_run_filter_sock_ops(struct sock *sk,
 int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum bpf_attach_type type);
 
+static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage)
+{
+	struct bpf_storage_buffer *buf;
+
+	if (!storage)
+		return;
+
+	buf = READ_ONCE(storage->buf);
+	this_cpu_write(bpf_cgroup_storage, &buf->data[0]);
+}
+
 struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(struct bpf_prog *prog);
 void bpf_cgroup_storage_free(struct bpf_cgroup_storage *storage);
 void bpf_cgroup_storage_link(struct bpf_cgroup_storage *storage,
@@ -250,6 +264,7 @@ static inline int cgroup_bpf_prog_query(const union bpf_attr *attr,
 	return -EINVAL;
 }
 
+static inline void bpf_cgroup_storage_set(struct bpf_cgroup_storage *storage) {}
 static inline int bpf_cgroup_storage_assign(struct bpf_prog *prog,
 					    struct bpf_map *map) { return 0; }
 static inline void bpf_cgroup_storage_release(struct bpf_prog *prog,
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index f23d3fdeba23..fc4e37f68f2a 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -7,6 +7,8 @@
 #include <linux/rbtree.h>
 #include <linux/slab.h>
 
+DEFINE_PER_CPU(void*, bpf_cgroup_storage);
+
 #ifdef CONFIG_CGROUP_BPF
 
 #define LOCAL_STORAGE_CREATE_FLAG_MASK					\
-- 
cgit v1.2.3


From d7bf2c10af053191e931b58704cd862fccb7f9de Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:20 -0700
Subject: bpf: allocate cgroup storage entries on attaching bpf programs

If a bpf program is using cgroup local storage, allocate
a bpf_cgroup_storage structure automatically on attaching the program
to a cgroup and save the pointer into the corresponding bpf_prog_list
entry.
Analogically, release the cgroup local storage on detaching
of the bpf program.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf-cgroup.h |  1 +
 kernel/bpf/cgroup.c        | 35 +++++++++++++++++++++++++++++++----
 2 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 9a144ddbbc8f..f91b0f8ff3a9 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -43,6 +43,7 @@ struct bpf_cgroup_storage {
 struct bpf_prog_list {
 	struct list_head node;
 	struct bpf_prog *prog;
+	struct bpf_cgroup_storage *storage;
 };
 
 struct bpf_prog_array;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index badabb0b435c..935274c86bfe 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -34,6 +34,8 @@ void cgroup_bpf_put(struct cgroup *cgrp)
 		list_for_each_entry_safe(pl, tmp, progs, node) {
 			list_del(&pl->node);
 			bpf_prog_put(pl->prog);
+			bpf_cgroup_storage_unlink(pl->storage);
+			bpf_cgroup_storage_free(pl->storage);
 			kfree(pl);
 			static_branch_dec(&cgroup_bpf_enabled_key);
 		}
@@ -188,6 +190,7 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 {
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
+	struct bpf_cgroup_storage *storage, *old_storage = NULL;
 	struct cgroup_subsys_state *css;
 	struct bpf_prog_list *pl;
 	bool pl_was_allocated;
@@ -210,31 +213,47 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	if (prog_list_length(progs) >= BPF_CGROUP_MAX_PROGS)
 		return -E2BIG;
 
+	storage = bpf_cgroup_storage_alloc(prog);
+	if (IS_ERR(storage))
+		return -ENOMEM;
+
 	if (flags & BPF_F_ALLOW_MULTI) {
-		list_for_each_entry(pl, progs, node)
-			if (pl->prog == prog)
+		list_for_each_entry(pl, progs, node) {
+			if (pl->prog == prog) {
 				/* disallow attaching the same prog twice */
+				bpf_cgroup_storage_free(storage);
 				return -EINVAL;
+			}
+		}
 
 		pl = kmalloc(sizeof(*pl), GFP_KERNEL);
-		if (!pl)
+		if (!pl) {
+			bpf_cgroup_storage_free(storage);
 			return -ENOMEM;
+		}
+
 		pl_was_allocated = true;
 		pl->prog = prog;
+		pl->storage = storage;
 		list_add_tail(&pl->node, progs);
 	} else {
 		if (list_empty(progs)) {
 			pl = kmalloc(sizeof(*pl), GFP_KERNEL);
-			if (!pl)
+			if (!pl) {
+				bpf_cgroup_storage_free(storage);
 				return -ENOMEM;
+			}
 			pl_was_allocated = true;
 			list_add_tail(&pl->node, progs);
 		} else {
 			pl = list_first_entry(progs, typeof(*pl), node);
 			old_prog = pl->prog;
+			old_storage = pl->storage;
+			bpf_cgroup_storage_unlink(old_storage);
 			pl_was_allocated = false;
 		}
 		pl->prog = prog;
+		pl->storage = storage;
 	}
 
 	cgrp->bpf.flags[type] = flags;
@@ -257,10 +276,13 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	}
 
 	static_branch_inc(&cgroup_bpf_enabled_key);
+	if (old_storage)
+		bpf_cgroup_storage_free(old_storage);
 	if (old_prog) {
 		bpf_prog_put(old_prog);
 		static_branch_dec(&cgroup_bpf_enabled_key);
 	}
+	bpf_cgroup_storage_link(storage, cgrp, type);
 	return 0;
 
 cleanup:
@@ -276,6 +298,9 @@ cleanup:
 
 	/* and cleanup the prog list */
 	pl->prog = old_prog;
+	bpf_cgroup_storage_free(pl->storage);
+	pl->storage = old_storage;
+	bpf_cgroup_storage_link(old_storage, cgrp, type);
 	if (pl_was_allocated) {
 		list_del(&pl->node);
 		kfree(pl);
@@ -356,6 +381,8 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 
 	/* now can actually delete it from this cgroup list */
 	list_del(&pl->node);
+	bpf_cgroup_storage_unlink(pl->storage);
+	bpf_cgroup_storage_free(pl->storage);
 	kfree(pl);
 	if (list_empty(progs))
 		/* last program was detached, reset flags to zero */
-- 
cgit v1.2.3


From 394e40a29788820c9c0526b1c3497c9e0ec2a126 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:21 -0700
Subject: bpf: extend bpf_prog_array to store pointers to the cgroup storage

This patch converts bpf_prog_array from an array of prog pointers
to the array of struct bpf_prog_array_item elements.

This allows to save a cgroup storage pointer for each bpf program
efficiently attached to a cgroup.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/media/rc/bpf-lirc.c | 10 +++---
 include/linux/bpf.h         | 19 ++++++++----
 kernel/bpf/cgroup.c         | 21 +++++++------
 kernel/bpf/core.c           | 76 +++++++++++++++++++++++----------------------
 4 files changed, 70 insertions(+), 56 deletions(-)

diff --git a/drivers/media/rc/bpf-lirc.c b/drivers/media/rc/bpf-lirc.c
index fcfab6635f9c..8c26df9b96c1 100644
--- a/drivers/media/rc/bpf-lirc.c
+++ b/drivers/media/rc/bpf-lirc.c
@@ -195,14 +195,16 @@ void lirc_bpf_run(struct rc_dev *rcdev, u32 sample)
  */
 void lirc_bpf_free(struct rc_dev *rcdev)
 {
-	struct bpf_prog **progs;
+	struct bpf_prog_array_item *item;
 
 	if (!rcdev->raw->progs)
 		return;
 
-	progs = rcu_dereference(rcdev->raw->progs)->progs;
-	while (*progs)
-		bpf_prog_put(*progs++);
+	item = rcu_dereference(rcdev->raw->progs)->items;
+	while (item->prog) {
+		bpf_prog_put(item->prog);
+		item++;
+	}
 
 	bpf_prog_array_free(rcdev->raw->progs);
 }
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 9d1e4727495e..16be67888c30 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -349,9 +349,14 @@ int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
  * The 'struct bpf_prog_array *' should only be replaced with xchg()
  * since other cpus are walking the array of pointers in parallel.
  */
+struct bpf_prog_array_item {
+	struct bpf_prog *prog;
+	struct bpf_cgroup_storage *cgroup_storage;
+};
+
 struct bpf_prog_array {
 	struct rcu_head rcu;
-	struct bpf_prog *progs[0];
+	struct bpf_prog_array_item items[0];
 };
 
 struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
@@ -372,7 +377,8 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 
 #define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null)	\
 	({						\
-		struct bpf_prog **_prog, *__prog;	\
+		struct bpf_prog_array_item *_item;	\
+		struct bpf_prog *_prog;			\
 		struct bpf_prog_array *_array;		\
 		u32 _ret = 1;				\
 		preempt_disable();			\
@@ -380,10 +386,11 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 		_array = rcu_dereference(array);	\
 		if (unlikely(check_non_null && !_array))\
 			goto _out;			\
-		_prog = _array->progs;			\
-		while ((__prog = READ_ONCE(*_prog))) {	\
-			_ret &= func(__prog, ctx);	\
-			_prog++;			\
+		_item = &_array->items[0];		\
+		while ((_prog = READ_ONCE(_item->prog))) {		\
+			bpf_cgroup_storage_set(_item->cgroup_storage);	\
+			_ret &= func(_prog, ctx);	\
+			_item++;			\
 		}					\
 _out:							\
 		rcu_read_unlock();			\
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 935274c86bfe..ddfa6cc13e57 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -117,15 +117,18 @@ static int compute_effective_progs(struct cgroup *cgrp,
 	cnt = 0;
 	p = cgrp;
 	do {
-		if (cnt == 0 || (p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
-			list_for_each_entry(pl,
-					    &p->bpf.progs[type], node) {
-				if (!pl->prog)
-					continue;
-				progs->progs[cnt++] = pl->prog;
-			}
-		p = cgroup_parent(p);
-	} while (p);
+		if (cnt > 0 && !(p->bpf.flags[type] & BPF_F_ALLOW_MULTI))
+			continue;
+
+		list_for_each_entry(pl, &p->bpf.progs[type], node) {
+			if (!pl->prog)
+				continue;
+
+			progs->items[cnt].prog = pl->prog;
+			progs->items[cnt].cgroup_storage = pl->storage;
+			cnt++;
+		}
+	} while ((p = cgroup_parent(p)));
 
 	rcu_assign_pointer(*array, progs);
 	return 0;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 253aa8e79c7b..9abcf25ebf9f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1542,7 +1542,8 @@ struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags)
 {
 	if (prog_cnt)
 		return kzalloc(sizeof(struct bpf_prog_array) +
-			       sizeof(struct bpf_prog *) * (prog_cnt + 1),
+			       sizeof(struct bpf_prog_array_item) *
+			       (prog_cnt + 1),
 			       flags);
 
 	return &empty_prog_array.hdr;
@@ -1556,43 +1557,45 @@ void bpf_prog_array_free(struct bpf_prog_array __rcu *progs)
 	kfree_rcu(progs, rcu);
 }
 
-int bpf_prog_array_length(struct bpf_prog_array __rcu *progs)
+int bpf_prog_array_length(struct bpf_prog_array __rcu *array)
 {
-	struct bpf_prog **prog;
+	struct bpf_prog_array_item *item;
 	u32 cnt = 0;
 
 	rcu_read_lock();
-	prog = rcu_dereference(progs)->progs;
-	for (; *prog; prog++)
-		if (*prog != &dummy_bpf_prog.prog)
+	item = rcu_dereference(array)->items;
+	for (; item->prog; item++)
+		if (item->prog != &dummy_bpf_prog.prog)
 			cnt++;
 	rcu_read_unlock();
 	return cnt;
 }
 
-static bool bpf_prog_array_copy_core(struct bpf_prog **prog,
+
+static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array,
 				     u32 *prog_ids,
 				     u32 request_cnt)
 {
+	struct bpf_prog_array_item *item;
 	int i = 0;
 
-	for (; *prog; prog++) {
-		if (*prog == &dummy_bpf_prog.prog)
+	item = rcu_dereference(array)->items;
+	for (; item->prog; item++) {
+		if (item->prog == &dummy_bpf_prog.prog)
 			continue;
-		prog_ids[i] = (*prog)->aux->id;
+		prog_ids[i] = item->prog->aux->id;
 		if (++i == request_cnt) {
-			prog++;
+			item++;
 			break;
 		}
 	}
 
-	return !!(*prog);
+	return !!(item->prog);
 }
 
-int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
+int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array,
 				__u32 __user *prog_ids, u32 cnt)
 {
-	struct bpf_prog **prog;
 	unsigned long err = 0;
 	bool nospc;
 	u32 *ids;
@@ -1611,8 +1614,7 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 	if (!ids)
 		return -ENOMEM;
 	rcu_read_lock();
-	prog = rcu_dereference(progs)->progs;
-	nospc = bpf_prog_array_copy_core(prog, ids, cnt);
+	nospc = bpf_prog_array_copy_core(array, ids, cnt);
 	rcu_read_unlock();
 	err = copy_to_user(prog_ids, ids, cnt * sizeof(u32));
 	kfree(ids);
@@ -1623,14 +1625,14 @@ int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs,
 	return 0;
 }
 
-void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs,
+void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array,
 				struct bpf_prog *old_prog)
 {
-	struct bpf_prog **prog = progs->progs;
+	struct bpf_prog_array_item *item = array->items;
 
-	for (; *prog; prog++)
-		if (*prog == old_prog) {
-			WRITE_ONCE(*prog, &dummy_bpf_prog.prog);
+	for (; item->prog; item++)
+		if (item->prog == old_prog) {
+			WRITE_ONCE(item->prog, &dummy_bpf_prog.prog);
 			break;
 		}
 }
@@ -1641,7 +1643,7 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 			struct bpf_prog_array **new_array)
 {
 	int new_prog_cnt, carry_prog_cnt = 0;
-	struct bpf_prog **existing_prog;
+	struct bpf_prog_array_item *existing;
 	struct bpf_prog_array *array;
 	bool found_exclude = false;
 	int new_prog_idx = 0;
@@ -1650,15 +1652,15 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 	 * the new array.
 	 */
 	if (old_array) {
-		existing_prog = old_array->progs;
-		for (; *existing_prog; existing_prog++) {
-			if (*existing_prog == exclude_prog) {
+		existing = old_array->items;
+		for (; existing->prog; existing++) {
+			if (existing->prog == exclude_prog) {
 				found_exclude = true;
 				continue;
 			}
-			if (*existing_prog != &dummy_bpf_prog.prog)
+			if (existing->prog != &dummy_bpf_prog.prog)
 				carry_prog_cnt++;
-			if (*existing_prog == include_prog)
+			if (existing->prog == include_prog)
 				return -EEXIST;
 		}
 	}
@@ -1684,15 +1686,17 @@ int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array,
 
 	/* Fill in the new prog array */
 	if (carry_prog_cnt) {
-		existing_prog = old_array->progs;
-		for (; *existing_prog; existing_prog++)
-			if (*existing_prog != exclude_prog &&
-			    *existing_prog != &dummy_bpf_prog.prog)
-				array->progs[new_prog_idx++] = *existing_prog;
+		existing = old_array->items;
+		for (; existing->prog; existing++)
+			if (existing->prog != exclude_prog &&
+			    existing->prog != &dummy_bpf_prog.prog) {
+				array->items[new_prog_idx++].prog =
+					existing->prog;
+			}
 	}
 	if (include_prog)
-		array->progs[new_prog_idx++] = include_prog;
-	array->progs[new_prog_idx] = NULL;
+		array->items[new_prog_idx++].prog = include_prog;
+	array->items[new_prog_idx].prog = NULL;
 	*new_array = array;
 	return 0;
 }
@@ -1701,7 +1705,6 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
 			     u32 *prog_ids, u32 request_cnt,
 			     u32 *prog_cnt)
 {
-	struct bpf_prog **prog;
 	u32 cnt = 0;
 
 	if (array)
@@ -1714,8 +1717,7 @@ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
 		return 0;
 
 	/* this function is called under trace/bpf_trace.c: bpf_event_mutex */
-	prog = rcu_dereference_check(array, 1)->progs;
-	return bpf_prog_array_copy_core(prog, prog_ids, request_cnt) ? -ENOSPC
+	return bpf_prog_array_copy_core(array, prog_ids, request_cnt) ? -ENOSPC
 								     : 0;
 }
 
-- 
cgit v1.2.3


From 3e6a4b3e0289dc9540a2c1d8a20657f4707fbabb Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:22 -0700
Subject: bpf/verifier: introduce BPF_PTR_TO_MAP_VALUE

BPF_MAP_TYPE_CGROUP_STORAGE maps are special in a way
that the access from the bpf program side is lookup-free.
That means the result is guaranteed to be a valid
pointer to the cgroup storage; no NULL-check is required.

This patch introduces BPF_PTR_TO_MAP_VALUE return type,
which is required to cause the verifier accept programs,
which are not checking the map value pointer for being NULL.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h   | 1 +
 kernel/bpf/verifier.c | 8 ++++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 16be67888c30..ca4ac2a39def 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -155,6 +155,7 @@ enum bpf_arg_type {
 enum bpf_return_type {
 	RET_INTEGER,			/* function returns integer */
 	RET_VOID,			/* function doesn't return anything */
+	RET_PTR_TO_MAP_VALUE,		/* returns a pointer to map elem value */
 	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
 };
 
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7e75434a9e54..1ede16c8bb40 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2545,8 +2545,12 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		mark_reg_unknown(env, regs, BPF_REG_0);
 	} else if (fn->ret_type == RET_VOID) {
 		regs[BPF_REG_0].type = NOT_INIT;
-	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL) {
-		regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
+	} else if (fn->ret_type == RET_PTR_TO_MAP_VALUE_OR_NULL ||
+		   fn->ret_type == RET_PTR_TO_MAP_VALUE) {
+		if (fn->ret_type == RET_PTR_TO_MAP_VALUE)
+			regs[BPF_REG_0].type = PTR_TO_MAP_VALUE;
+		else
+			regs[BPF_REG_0].type = PTR_TO_MAP_VALUE_OR_NULL;
 		/* There is no offset yet applied, variable or fixed */
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].off = 0;
-- 
cgit v1.2.3


From 7b5dd2bde72cd33313b63cf3ba1de6a9e443a65d Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:23 -0700
Subject: bpf: don't allow create maps of cgroup local storages

As there is one-to-one relation between a bpf program
and cgroup local storage map, there is no sense in
creating a map of cgroup local storage maps.

Forbid it explicitly to avoid possible side effects.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/map_in_map.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/map_in_map.c b/kernel/bpf/map_in_map.c
index 1da574612bea..3bfbf4464416 100644
--- a/kernel/bpf/map_in_map.c
+++ b/kernel/bpf/map_in_map.c
@@ -23,7 +23,8 @@ struct bpf_map *bpf_map_meta_alloc(int inner_map_ufd)
 	 * is a runtime binding.  Doing static check alone
 	 * in the verifier is not enough.
 	 */
-	if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {
+	if (inner_map->map_type == BPF_MAP_TYPE_PROG_ARRAY ||
+	    inner_map->map_type == BPF_MAP_TYPE_CGROUP_STORAGE) {
 		fdput(f);
 		return ERR_PTR(-ENOTSUPP);
 	}
-- 
cgit v1.2.3


From cd3394317653837e2eb5c5d0904a8996102af9fc Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:24 -0700
Subject: bpf: introduce the bpf_get_local_storage() helper function

The bpf_get_local_storage() helper function is used
to get a pointer to the bpf local storage from a bpf program.

It takes a pointer to a storage map and flags as arguments.
Right now it accepts only cgroup storage maps, and flags
argument has to be 0. Further it can be extended to support
other types of local storage: e.g. thread local storage etc.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h      |  2 ++
 include/uapi/linux/bpf.h | 21 ++++++++++++++++++++-
 kernel/bpf/cgroup.c      |  2 ++
 kernel/bpf/core.c        |  1 +
 kernel/bpf/helpers.c     | 20 ++++++++++++++++++++
 kernel/bpf/verifier.c    | 18 ++++++++++++++++++
 net/core/filter.c        | 23 ++++++++++++++++++++++-
 7 files changed, 85 insertions(+), 2 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index ca4ac2a39def..cd8790d2c6ed 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -788,6 +788,8 @@ extern const struct bpf_func_proto bpf_sock_map_update_proto;
 extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
 
+extern const struct bpf_func_proto bpf_get_local_storage_proto;
+
 /* Shared helpers among cBPF and eBPF. */
 void bpf_user_rnd_init_once(void);
 u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index b10118ee5afe..dd5758dc35d3 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2095,6 +2095,24 @@ union bpf_attr {
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ *	Description
+ *		Get the pointer to the local storage area.
+ *		The type and the size of the local storage is defined
+ *		by the *map* argument.
+ *		The *flags* meaning is specific for each map type,
+ *		and has to be 0 for cgroup local storage.
+ *
+ *		Depending on the bpf program type, a local storage area
+ *		can be shared between multiple instances of the bpf program,
+ *		running simultaneously.
+ *
+ *		A user should care about the synchronization by himself.
+ *		For example, by using the BPF_STX_XADD instruction to alter
+ *		the shared data.
+ *	Return
+ *		Pointer to the local storage area.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2177,7 +2195,8 @@ union bpf_attr {
 	FN(rc_repeat),			\
 	FN(rc_keydown),			\
 	FN(skb_cgroup_id),		\
-	FN(get_current_cgroup_id),
+	FN(get_current_cgroup_id),	\
+	FN(get_local_storage),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index ddfa6cc13e57..0a4fe5a7dc91 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -684,6 +684,8 @@ cgroup_dev_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_map_delete_elem_proto;
 	case BPF_FUNC_get_current_uid_gid:
 		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
 	case BPF_FUNC_trace_printk:
 		if (capable(CAP_SYS_ADMIN))
 			return bpf_get_trace_printk_proto();
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9abcf25ebf9f..4d09e610777f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1795,6 +1795,7 @@ const struct bpf_func_proto bpf_get_current_comm_proto __weak;
 const struct bpf_func_proto bpf_sock_map_update_proto __weak;
 const struct bpf_func_proto bpf_sock_hash_update_proto __weak;
 const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
+const struct bpf_func_proto bpf_get_local_storage_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 73065e2d23c2..1991466b8327 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -193,4 +193,24 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 };
+
+DECLARE_PER_CPU(void*, bpf_cgroup_storage);
+
+BPF_CALL_2(bpf_get_local_storage, struct bpf_map *, map, u64, flags)
+{
+	/* map and flags arguments are not used now,
+	 * but provide an ability to extend the API
+	 * for other types of local storages.
+	 * verifier checks that their values are correct.
+	 */
+	return (unsigned long) this_cpu_read(bpf_cgroup_storage);
+}
+
+const struct bpf_func_proto bpf_get_local_storage_proto = {
+	.func		= bpf_get_local_storage,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_MAP_VALUE,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+};
 #endif
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 1ede16c8bb40..587468a9c37d 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2127,6 +2127,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_current_task_under_cgroup)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_CGROUP_STORAGE:
+		if (func_id != BPF_FUNC_get_local_storage)
+			goto error;
+		break;
 	/* devmap returns a pointer to a live net_device ifindex that we cannot
 	 * allow to be modified from bpf side. So do not allow lookup elements
 	 * for now.
@@ -2209,6 +2213,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (map->map_type != BPF_MAP_TYPE_SOCKHASH)
 			goto error;
 		break;
+	case BPF_FUNC_get_local_storage:
+		if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -2533,6 +2541,16 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	}
 
 	regs = cur_regs(env);
+
+	/* check that flags argument in get_local_storage(map, flags) is 0,
+	 * this is required because get_local_storage() can't return an error.
+	 */
+	if (func_id == BPF_FUNC_get_local_storage &&
+	    !register_is_null(&regs[BPF_REG_2])) {
+		verbose(env, "get_local_storage() doesn't support non-zero flags\n");
+		return -EINVAL;
+	}
+
 	/* reset caller saved regs */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);
diff --git a/net/core/filter.c b/net/core/filter.c
index 9bb9a4488e25..9f73aae2f089 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4820,6 +4820,8 @@ sock_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	 */
 	case BPF_FUNC_get_current_uid_gid:
 		return &bpf_get_current_uid_gid_proto;
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -4844,6 +4846,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		}
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_addr_proto;
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -4866,6 +4870,17 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	}
 }
 
+static const struct bpf_func_proto *
+cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
+	default:
+		return sk_filter_func_proto(func_id, prog);
+	}
+}
+
 static const struct bpf_func_proto *
 tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -4988,6 +5003,8 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_hash_update_proto;
 	case BPF_FUNC_get_socket_cookie:
 		return &bpf_get_socket_cookie_sock_ops_proto;
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5007,6 +5024,8 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_msg_cork_bytes_proto;
 	case BPF_FUNC_msg_pull_data:
 		return &bpf_msg_pull_data_proto;
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -5034,6 +5053,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_redirect_map_proto;
 	case BPF_FUNC_sk_redirect_hash:
 		return &bpf_sk_redirect_hash_proto;
+	case BPF_FUNC_get_local_storage:
+		return &bpf_get_local_storage_proto;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -6838,7 +6859,7 @@ const struct bpf_prog_ops xdp_prog_ops = {
 };
 
 const struct bpf_verifier_ops cg_skb_verifier_ops = {
-	.get_func_proto		= sk_filter_func_proto,
+	.get_func_proto		= cg_skb_func_proto,
 	.is_valid_access	= sk_filter_is_valid_access,
 	.convert_ctx_access	= bpf_convert_ctx_access,
 };
-- 
cgit v1.2.3


From c419cf52da77d0f0f01d4b75a75ae89406f0923f Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:25 -0700
Subject: bpf: sync bpf.h to tools/

Sync cgroup storage related changes:
1) new BPF_MAP_TYPE_CGROUP_STORAGE map type
2) struct bpf_cgroup_sotrage_key definition
3) get_local_storage() helper

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 27 ++++++++++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0ebaaf7f3568..dd5758dc35d3 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -75,6 +75,11 @@ struct bpf_lpm_trie_key {
 	__u8	data[0];	/* Arbitrary size */
 };
 
+struct bpf_cgroup_storage_key {
+	__u64	cgroup_inode_id;	/* cgroup inode id */
+	__u32	attach_type;		/* program attach type */
+};
+
 /* BPF syscall commands, see bpf(2) man-page for details. */
 enum bpf_cmd {
 	BPF_MAP_CREATE,
@@ -120,6 +125,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CPUMAP,
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
+	BPF_MAP_TYPE_CGROUP_STORAGE,
 };
 
 enum bpf_prog_type {
@@ -2089,6 +2095,24 @@ union bpf_attr {
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
  * 		on the cgroup within which the current task is running.
+ *
+ * void* get_local_storage(void *map, u64 flags)
+ *	Description
+ *		Get the pointer to the local storage area.
+ *		The type and the size of the local storage is defined
+ *		by the *map* argument.
+ *		The *flags* meaning is specific for each map type,
+ *		and has to be 0 for cgroup local storage.
+ *
+ *		Depending on the bpf program type, a local storage area
+ *		can be shared between multiple instances of the bpf program,
+ *		running simultaneously.
+ *
+ *		A user should care about the synchronization by himself.
+ *		For example, by using the BPF_STX_XADD instruction to alter
+ *		the shared data.
+ *	Return
+ *		Pointer to the local storage area.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2171,7 +2195,8 @@ union bpf_attr {
 	FN(rc_repeat),			\
 	FN(rc_keydown),			\
 	FN(skb_cgroup_id),		\
-	FN(get_current_cgroup_id),
+	FN(get_current_cgroup_id),	\
+	FN(get_local_storage),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 34a6bbb8131b75daeb3e9be026d39d6463762baf Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:26 -0700
Subject: bpftool: add support for CGROUP_STORAGE maps

Add BPF_MAP_TYPE_CGROUP_STORAGE maps to the list
of maps types which bpftool recognizes.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/bpf/bpftool/map.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index 0ee3ba479d87..2dd1f8d9cc2d 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -68,6 +68,7 @@ static const char * const map_type_name[] = {
 	[BPF_MAP_TYPE_SOCKMAP]		= "sockmap",
 	[BPF_MAP_TYPE_CPUMAP]		= "cpumap",
 	[BPF_MAP_TYPE_SOCKHASH]		= "sockhash",
+	[BPF_MAP_TYPE_CGROUP_STORAGE]	= "cgroup_storage",
 };
 
 static bool map_is_per_cpu(__u32 type)
-- 
cgit v1.2.3


From f42ee093be2980f2689ea7a170d580364820f48b Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:27 -0700
Subject: bpf/test_run: support cgroup local storage

Allocate a temporary cgroup storage to use for bpf program test runs.

Because the test program is not actually attached to a cgroup,
the storage is allocated manually just for the execution
of the bpf program.

If the program is executed multiple times, the storage is not zeroed
on each run, emulating multiple runs of the program, attached to
a real cgroup.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/bpf/test_run.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 22a78eedf4b1..f4078830ea50 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -11,12 +11,14 @@
 #include <linux/filter.h>
 #include <linux/sched/signal.h>
 
-static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx)
+static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx,
+					    struct bpf_cgroup_storage *storage)
 {
 	u32 ret;
 
 	preempt_disable();
 	rcu_read_lock();
+	bpf_cgroup_storage_set(storage);
 	ret = BPF_PROG_RUN(prog, ctx);
 	rcu_read_unlock();
 	preempt_enable();
@@ -26,14 +28,19 @@ static __always_inline u32 bpf_test_run_one(struct bpf_prog *prog, void *ctx)
 
 static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
 {
+	struct bpf_cgroup_storage *storage = NULL;
 	u64 time_start, time_spent = 0;
 	u32 ret = 0, i;
 
+	storage = bpf_cgroup_storage_alloc(prog);
+	if (IS_ERR(storage))
+		return PTR_ERR(storage);
+
 	if (!repeat)
 		repeat = 1;
 	time_start = ktime_get_ns();
 	for (i = 0; i < repeat; i++) {
-		ret = bpf_test_run_one(prog, ctx);
+		ret = bpf_test_run_one(prog, ctx, storage);
 		if (need_resched()) {
 			if (signal_pending(current))
 				break;
@@ -46,6 +53,8 @@ static u32 bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat, u32 *time)
 	do_div(time_spent, repeat);
 	*time = time_spent > U32_MAX ? U32_MAX : (u32)time_spent;
 
+	bpf_cgroup_storage_free(storage);
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From d4c9f573537506530019c505c8b6097a7d7a5fab Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:28 -0700
Subject: selftests/bpf: add verifier cgroup storage tests

Add the following verifier tests to cover the cgroup storage
functionality:
1) valid access to the cgroup storage
2) invalid access: use regular hashmap instead of cgroup storage map
3) invalid access: use invalid map fd
4) invalid access: try access memory after the cgroup storage
5) invalid access: try access memory before the cgroup storage
6) invalid access: call get_local_storage() with non-zero flags

For tests 2)-6) check returned error strings.

Expected output:
  $ ./test_verifier
  #0/u add+sub+mul OK
  #0/p add+sub+mul OK
  #1/u DIV32 by 0, zero check 1 OK
  ...
  #280/p valid cgroup storage access OK
  #281/p invalid cgroup storage access 1 OK
  #282/p invalid cgroup storage access 2 OK
  #283/p invalid per-cgroup storage access 3 OK
  #284/p invalid cgroup storage access 4 OK
  #285/p invalid cgroup storage access 5 OK
  ...
  #649/p pass modified ctx pointer to helper, 2 OK
  #650/p pass modified ctx pointer to helper, 3 OK
  Summary: 901 PASSED, 0 SKIPPED, 0 FAILED

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/bpf_helpers.h   |   2 +
 tools/testing/selftests/bpf/test_verifier.c | 140 +++++++++++++++++++++++++++-
 2 files changed, 141 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 19a424483f6e..cb9fcfbc9307 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -135,6 +135,8 @@ static int (*bpf_rc_keydown)(void *ctx, unsigned int protocol,
 	(void *) BPF_FUNC_rc_keydown;
 static unsigned long long (*bpf_get_current_cgroup_id)(void) =
 	(void *) BPF_FUNC_get_current_cgroup_id;
+static void *(*bpf_get_local_storage)(void *map, unsigned long long flags) =
+	(void *) BPF_FUNC_get_local_storage;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c582afba9d1f..4b5e03c25204 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -50,7 +50,7 @@
 
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
-#define MAX_NR_MAPS	7
+#define MAX_NR_MAPS	8
 #define POINTER_VALUE	0xcafe4all
 #define TEST_DATA_LEN	64
 
@@ -70,6 +70,7 @@ struct bpf_test {
 	int fixup_prog1[MAX_FIXUPS];
 	int fixup_prog2[MAX_FIXUPS];
 	int fixup_map_in_map[MAX_FIXUPS];
+	int fixup_cgroup_storage[MAX_FIXUPS];
 	const char *errstr;
 	const char *errstr_unpriv;
 	uint32_t retval;
@@ -4630,6 +4631,121 @@ static struct bpf_test tests[] = {
 		.result = REJECT,
 		.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
 	},
+	{
+		"valid cgroup storage access",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = ACCEPT,
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid cgroup storage access 1",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_map1 = { 1 },
+		.result = REJECT,
+		.errstr = "cannot pass map_type 1 into func bpf_get_local_storage",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid cgroup storage access 2",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 1),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = REJECT,
+		.errstr = "fd 1 is not pointing to valid bpf_map",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid per-cgroup storage access 3",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 256),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=256 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid cgroup storage access 4",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 0),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, -2),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "invalid access to map value, value_size=64 off=-2 size=4",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid cgroup storage access 5",
+		.insns = {
+			BPF_MOV64_IMM(BPF_REG_2, 7),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
+	{
+		"invalid cgroup storage access 6",
+		.insns = {
+			BPF_MOV64_REG(BPF_REG_2, BPF_REG_1),
+			BPF_LD_MAP_FD(BPF_REG_1, 0),
+			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+				     BPF_FUNC_get_local_storage),
+			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+			BPF_ALU64_IMM(BPF_AND, BPF_REG_0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.fixup_cgroup_storage = { 1 },
+		.result = REJECT,
+		.errstr = "get_local_storage() doesn't support non-zero flags",
+		.prog_type = BPF_PROG_TYPE_CGROUP_SKB,
+	},
 	{
 		"multiple registers share map_lookup_elem result",
 		.insns = {
@@ -12462,6 +12578,19 @@ static int create_map_in_map(void)
 	return outer_map_fd;
 }
 
+static int create_cgroup_storage(void)
+{
+	int fd;
+
+	fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+			    sizeof(struct bpf_cgroup_storage_key),
+			    TEST_DATA_LEN, 0, 0);
+	if (fd < 0)
+		printf("Failed to create array '%s'!\n", strerror(errno));
+
+	return fd;
+}
+
 static char bpf_vlog[UINT_MAX >> 8];
 
 static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
@@ -12474,6 +12603,7 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 	int *fixup_prog1 = test->fixup_prog1;
 	int *fixup_prog2 = test->fixup_prog2;
 	int *fixup_map_in_map = test->fixup_map_in_map;
+	int *fixup_cgroup_storage = test->fixup_cgroup_storage;
 
 	if (test->fill_helper)
 		test->fill_helper(test);
@@ -12541,6 +12671,14 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog,
 			fixup_map_in_map++;
 		} while (*fixup_map_in_map);
 	}
+
+	if (*fixup_cgroup_storage) {
+		map_fds[7] = create_cgroup_storage();
+		do {
+			prog[*fixup_cgroup_storage].imm = map_fds[7];
+			fixup_cgroup_storage++;
+		} while (*fixup_cgroup_storage);
+	}
 }
 
 static void do_test_single(struct bpf_test *test, bool unpriv,
-- 
cgit v1.2.3


From 68cfa3ac6b8db2782300ad0d699da27aaa2ac9fb Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:29 -0700
Subject: selftests/bpf: add a cgroup storage test

Implement a test to cover the cgroup storage functionality.
The test implements a bpf program which drops every second packet
by using the cgroup storage as a persistent storage.

The test also use the userspace API to check the data
in the cgroup storage, alter it, and check that the loaded
and attached bpf program sees the update.

Expected output:
  $ ./test_cgroup_storage
  test_cgroup_storage:PASS

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile              |   3 +-
 tools/testing/selftests/bpf/test_cgroup_storage.c | 130 ++++++++++++++++++++++
 2 files changed, 132 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/bpf/test_cgroup_storage.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 1b28277998e2..ad241ddba350 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,7 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
-	test_socket_cookie
+	test_socket_cookie test_cgroup_storage
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
@@ -66,6 +66,7 @@ $(OUTPUT)/test_sockmap: cgroup_helpers.c
 $(OUTPUT)/test_tcpbpf_user: cgroup_helpers.c
 $(OUTPUT)/test_progs: trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
+$(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
 
 .PHONY: force
 
diff --git a/tools/testing/selftests/bpf/test_cgroup_storage.c b/tools/testing/selftests/bpf/test_cgroup_storage.c
new file mode 100644
index 000000000000..dc83fb2d3f27
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_cgroup_storage.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <assert.h>
+#include <bpf/bpf.h>
+#include <linux/filter.h>
+#include <stdio.h>
+#include <stdlib.h>
+
+#include "cgroup_helpers.h"
+
+char bpf_log_buf[BPF_LOG_BUF_SIZE];
+
+#define TEST_CGROUP "/test-bpf-cgroup-storage-buf/"
+
+int main(int argc, char **argv)
+{
+	struct bpf_insn prog[] = {
+		BPF_LD_MAP_FD(BPF_REG_1, 0), /* map fd */
+		BPF_MOV64_IMM(BPF_REG_2, 0), /* flags, not used */
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+			     BPF_FUNC_get_local_storage),
+		BPF_MOV64_IMM(BPF_REG_1, 1),
+		BPF_STX_XADD(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+		BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_0, 0),
+		BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0x1),
+		BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+		BPF_EXIT_INSN(),
+	};
+	size_t insns_cnt = sizeof(prog) / sizeof(struct bpf_insn);
+	int error = EXIT_FAILURE;
+	int map_fd, prog_fd, cgroup_fd;
+	struct bpf_cgroup_storage_key key;
+	unsigned long long value;
+
+	map_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE, sizeof(key),
+				sizeof(value), 0, 0);
+	if (map_fd < 0) {
+		printf("Failed to create map: %s\n", strerror(errno));
+		goto out;
+	}
+
+	prog[0].imm = map_fd;
+	prog_fd = bpf_load_program(BPF_PROG_TYPE_CGROUP_SKB,
+				   prog, insns_cnt, "GPL", 0,
+				   bpf_log_buf, BPF_LOG_BUF_SIZE);
+	if (prog_fd < 0) {
+		printf("Failed to load bpf program: %s\n", bpf_log_buf);
+		goto out;
+	}
+
+	if (setup_cgroup_environment()) {
+		printf("Failed to setup cgroup environment\n");
+		goto err;
+	}
+
+	/* Create a cgroup, get fd, and join it */
+	cgroup_fd = create_and_get_cgroup(TEST_CGROUP);
+	if (!cgroup_fd) {
+		printf("Failed to create test cgroup\n");
+		goto err;
+	}
+
+	if (join_cgroup(TEST_CGROUP)) {
+		printf("Failed to join cgroup\n");
+		goto err;
+	}
+
+	/* Attach the bpf program */
+	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
+		printf("Failed to attach bpf program\n");
+		goto err;
+	}
+
+	if (bpf_map_get_next_key(map_fd, NULL, &key)) {
+		printf("Failed to get the first key in cgroup storage\n");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+		printf("Failed to lookup cgroup storage\n");
+		goto err;
+	}
+
+	/* Every second packet should be dropped */
+	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+	assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
+	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+
+	/* Check the counter in the cgroup local storage */
+	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+		printf("Failed to lookup cgroup storage\n");
+		goto err;
+	}
+
+	if (value != 3) {
+		printf("Unexpected data in the cgroup storage: %llu\n", value);
+		goto err;
+	}
+
+	/* Bump the counter in the cgroup local storage */
+	value++;
+	if (bpf_map_update_elem(map_fd, &key, &value, 0)) {
+		printf("Failed to update the data in the cgroup storage\n");
+		goto err;
+	}
+
+	/* Every second packet should be dropped */
+	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+	assert(system("ping localhost -c 1 -W 1 -q > /dev/null"));
+	assert(system("ping localhost -c 1 -W 1 -q > /dev/null") == 0);
+
+	/* Check the final value of the counter in the cgroup local storage */
+	if (bpf_map_lookup_elem(map_fd, &key, &value)) {
+		printf("Failed to lookup the cgroup storage\n");
+		goto err;
+	}
+
+	if (value != 7) {
+		printf("Unexpected data in the cgroup storage: %llu\n", value);
+		goto err;
+	}
+
+	error = 0;
+	printf("test_cgroup_storage:PASS\n");
+
+err:
+	cleanup_cgroup_environment();
+
+out:
+	return error;
+}
-- 
cgit v1.2.3


From 28ba068760a7e136a7fe2783bca74e3f43affb9b Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 14:27:30 -0700
Subject: samples/bpf: extend test_cgrp2_attach2 test to use cgroup storage

The test_cgrp2_attach test covers bpf cgroup attachment code well,
so let's re-use it for testing allocation/releasing of cgroup storage.

The extension is pretty straightforward: the bpf program will use
the cgroup storage to save the number of transmitted bytes.

Expected output:
  $ ./test_cgrp2_attach2
  Attached DROP prog. This ping in cgroup /foo should fail...
  ping: sendmsg: Operation not permitted
  Attached DROP prog. This ping in cgroup /foo/bar should fail...
  ping: sendmsg: Operation not permitted
  Attached PASS prog. This ping in cgroup /foo/bar should pass...
  Detached PASS from /foo/bar while DROP is attached to /foo.
  This ping in cgroup /foo/bar should fail...
  ping: sendmsg: Operation not permitted
  Attached PASS from /foo/bar and detached DROP from /foo.
  This ping in cgroup /foo/bar should pass...
  ### override:PASS
  ### multi:PASS

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/test_cgrp2_attach2.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/samples/bpf/test_cgrp2_attach2.c b/samples/bpf/test_cgrp2_attach2.c
index b453e6a161be..180f9d813bca 100644
--- a/samples/bpf/test_cgrp2_attach2.c
+++ b/samples/bpf/test_cgrp2_attach2.c
@@ -8,7 +8,8 @@
  *   information. The number of invocations of the program, which maps
  *   to the number of packets received, is stored to key 0. Key 1 is
  *   incremented on each iteration by the number of bytes stored in
- *   the skb.
+ *   the skb. The program also stores the number of received bytes
+ *   in the cgroup storage.
  *
  * - Attaches the new program to a cgroup using BPF_PROG_ATTACH
  *
@@ -21,12 +22,15 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <assert.h>
+#include <sys/resource.h>
+#include <sys/time.h>
 #include <unistd.h>
 
 #include <linux/bpf.h>
 #include <bpf/bpf.h>
 
 #include "bpf_insn.h"
+#include "bpf_rlimit.h"
 #include "cgroup_helpers.h"
 
 #define FOO		"/foo"
@@ -205,6 +209,8 @@ static int map_fd = -1;
 
 static int prog_load_cnt(int verdict, int val)
 {
+	int cgroup_storage_fd;
+
 	if (map_fd < 0)
 		map_fd = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 8, 1, 0);
 	if (map_fd < 0) {
@@ -212,6 +218,13 @@ static int prog_load_cnt(int verdict, int val)
 		return -1;
 	}
 
+	cgroup_storage_fd = bpf_create_map(BPF_MAP_TYPE_CGROUP_STORAGE,
+				sizeof(struct bpf_cgroup_storage_key), 8, 0, 0);
+	if (cgroup_storage_fd < 0) {
+		printf("failed to create map '%s'\n", strerror(errno));
+		return -1;
+	}
+
 	struct bpf_insn prog[] = {
 		BPF_MOV32_IMM(BPF_REG_0, 0),
 		BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
@@ -222,6 +235,11 @@ static int prog_load_cnt(int verdict, int val)
 		BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
 		BPF_MOV64_IMM(BPF_REG_1, val), /* r1 = 1 */
 		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+		BPF_LD_MAP_FD(BPF_REG_1, cgroup_storage_fd),
+		BPF_MOV64_IMM(BPF_REG_2, 0),
+		BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_local_storage),
+		BPF_MOV64_IMM(BPF_REG_1, val),
+		BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_W, BPF_REG_0, BPF_REG_1, 0, 0),
 		BPF_MOV64_IMM(BPF_REG_0, verdict), /* r0 = verdict */
 		BPF_EXIT_INSN(),
 	};
@@ -237,6 +255,7 @@ static int prog_load_cnt(int verdict, int val)
 		printf("Output from verifier:\n%s\n-------\n", bpf_log_buf);
 		return 0;
 	}
+	close(cgroup_storage_fd);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 299c7007e93645067e1d2743f4e50156de78c4ff Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Mon, 23 Jul 2018 13:04:54 -0400
Subject: media: dw2102: Fix memleak on sequence of probes

Each call to dw2102_probe() allocates memory by kmemdup for structures
p1100, s660, p7500 and s421, but there is no their deallocation.
dvb_usb_device_init() copies the corresponding structure into
dvb_usb_device->props, so there is no use of original structure after
dvb_usb_device_init().

The patch moves structures from global scope to local and adds their
deallocation.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb/dw2102.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/media/usb/dvb-usb/dw2102.c b/drivers/media/usb/dvb-usb/dw2102.c
index 0d4fdd34a710..9ce8b4d79d1f 100644
--- a/drivers/media/usb/dvb-usb/dw2102.c
+++ b/drivers/media/usb/dvb-usb/dw2102.c
@@ -2101,14 +2101,12 @@ static struct dvb_usb_device_properties s6x0_properties = {
 	}
 };
 
-static struct dvb_usb_device_properties *p1100;
 static const struct dvb_usb_device_description d1100 = {
 	"Prof 1100 USB ",
 	{&dw2102_table[PROF_1100], NULL},
 	{NULL},
 };
 
-static struct dvb_usb_device_properties *s660;
 static const struct dvb_usb_device_description d660 = {
 	"TeVii S660 USB",
 	{&dw2102_table[TEVII_S660], NULL},
@@ -2127,14 +2125,12 @@ static const struct dvb_usb_device_description d480_2 = {
 	{NULL},
 };
 
-static struct dvb_usb_device_properties *p7500;
 static const struct dvb_usb_device_description d7500 = {
 	"Prof 7500 USB DVB-S2",
 	{&dw2102_table[PROF_7500], NULL},
 	{NULL},
 };
 
-static struct dvb_usb_device_properties *s421;
 static const struct dvb_usb_device_description d421 = {
 	"TeVii S421 PCI",
 	{&dw2102_table[TEVII_S421], NULL},
@@ -2334,6 +2330,11 @@ static int dw2102_probe(struct usb_interface *intf,
 		const struct usb_device_id *id)
 {
 	int retval = -ENOMEM;
+	struct dvb_usb_device_properties *p1100;
+	struct dvb_usb_device_properties *s660;
+	struct dvb_usb_device_properties *p7500;
+	struct dvb_usb_device_properties *s421;
+
 	p1100 = kmemdup(&s6x0_properties,
 			sizeof(struct dvb_usb_device_properties), GFP_KERNEL);
 	if (!p1100)
@@ -2402,8 +2403,16 @@ static int dw2102_probe(struct usb_interface *intf,
 	    0 == dvb_usb_device_init(intf, &t220_properties,
 			 THIS_MODULE, NULL, adapter_nr) ||
 	    0 == dvb_usb_device_init(intf, &tt_s2_4600_properties,
-			 THIS_MODULE, NULL, adapter_nr))
+			 THIS_MODULE, NULL, adapter_nr)) {
+
+		/* clean up copied properties */
+		kfree(s421);
+		kfree(p7500);
+		kfree(s660);
+		kfree(p1100);
+
 		return 0;
+	}
 
 	retval = -ENODEV;
 	kfree(s421);
-- 
cgit v1.2.3


From 817dc4b579d897d3f645c11dc255f21642aa99df Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Tue, 17 Jul 2018 21:06:42 -0400
Subject: media: helene: add I2C device probe function

This patch adds I2C probe function to use dvb_module_probe() with
this driver. And also support multiple delivery systems at the
same device.

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/helene.c | 88 ++++++++++++++++++++++++++++++++++--
 drivers/media/dvb-frontends/helene.h |  3 ++
 2 files changed, 87 insertions(+), 4 deletions(-)

diff --git a/drivers/media/dvb-frontends/helene.c b/drivers/media/dvb-frontends/helene.c
index dc70fb684681..d7790cb98a0c 100644
--- a/drivers/media/dvb-frontends/helene.c
+++ b/drivers/media/dvb-frontends/helene.c
@@ -666,7 +666,7 @@ static int helene_set_params_s(struct dvb_frontend *fe)
 	return 0;
 }
 
-static int helene_set_params(struct dvb_frontend *fe)
+static int helene_set_params_t(struct dvb_frontend *fe)
 {
 	u8 data[MAX_WRITE_REGSIZE];
 	u32 frequency;
@@ -835,6 +835,19 @@ static int helene_set_params(struct dvb_frontend *fe)
 	return 0;
 }
 
+static int helene_set_params(struct dvb_frontend *fe)
+{
+	struct dtv_frontend_properties *p = &fe->dtv_property_cache;
+
+	if (p->delivery_system == SYS_DVBT ||
+	    p->delivery_system == SYS_DVBT2 ||
+	    p->delivery_system == SYS_ISDBT ||
+	    p->delivery_system == SYS_DVBC_ANNEX_A)
+		return helene_set_params_t(fe);
+
+	return helene_set_params_s(fe);
+}
+
 static int helene_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 {
 	struct helene_priv *priv = fe->tuner_priv;
@@ -843,7 +856,7 @@ static int helene_get_frequency(struct dvb_frontend *fe, u32 *frequency)
 	return 0;
 }
 
-static const struct dvb_tuner_ops helene_tuner_ops = {
+static const struct dvb_tuner_ops helene_tuner_ops_t = {
 	.info = {
 		.name = "Sony HELENE Ter tuner",
 		.frequency_min_hz  =    1 * MHz,
@@ -853,7 +866,7 @@ static const struct dvb_tuner_ops helene_tuner_ops = {
 	.init = helene_init,
 	.release = helene_release,
 	.sleep = helene_sleep,
-	.set_params = helene_set_params,
+	.set_params = helene_set_params_t,
 	.get_frequency = helene_get_frequency,
 };
 
@@ -871,6 +884,20 @@ static const struct dvb_tuner_ops helene_tuner_ops_s = {
 	.get_frequency = helene_get_frequency,
 };
 
+static const struct dvb_tuner_ops helene_tuner_ops = {
+	.info = {
+		.name = "Sony HELENE Sat/Ter tuner",
+		.frequency_min_hz  =    1 * MHz,
+		.frequency_max_hz  = 2500 * MHz,
+		.frequency_step_hz =   25 * kHz,
+	},
+	.init = helene_init,
+	.release = helene_release,
+	.sleep = helene_sleep,
+	.set_params = helene_set_params,
+	.get_frequency = helene_get_frequency,
+};
+
 /* power-on tuner
  * call once after reset
  */
@@ -1035,7 +1062,7 @@ struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
 	if (fe->ops.i2c_gate_ctrl)
 		fe->ops.i2c_gate_ctrl(fe, 0);
 
-	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops,
+	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops_t,
 			sizeof(struct dvb_tuner_ops));
 	fe->tuner_priv = priv;
 	dev_info(&priv->i2c->dev,
@@ -1045,6 +1072,59 @@ struct dvb_frontend *helene_attach(struct dvb_frontend *fe,
 }
 EXPORT_SYMBOL(helene_attach);
 
+static int helene_probe(struct i2c_client *client,
+			const struct i2c_device_id *id)
+{
+	struct helene_config *config = client->dev.platform_data;
+	struct dvb_frontend *fe = config->fe;
+	struct device *dev = &client->dev;
+	struct helene_priv *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->i2c_address = client->addr;
+	priv->i2c = client->adapter;
+	priv->set_tuner_data = config->set_tuner_priv;
+	priv->set_tuner = config->set_tuner_callback;
+	priv->xtal = config->xtal;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 1);
+
+	if (helene_x_pon(priv) != 0)
+		return -EINVAL;
+
+	if (fe->ops.i2c_gate_ctrl)
+		fe->ops.i2c_gate_ctrl(fe, 0);
+
+	memcpy(&fe->ops.tuner_ops, &helene_tuner_ops,
+	       sizeof(struct dvb_tuner_ops));
+	fe->tuner_priv = priv;
+	i2c_set_clientdata(client, priv);
+
+	dev_info(dev, "Sony HELENE attached on addr=%x at I2C adapter %p\n",
+		 priv->i2c_address, priv->i2c);
+
+	return 0;
+}
+
+static const struct i2c_device_id helene_id[] = {
+	{ "helene", },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, helene_id);
+
+static struct i2c_driver helene_driver = {
+	.driver = {
+		.name = "helene",
+	},
+	.probe    = helene_probe,
+	.id_table = helene_id,
+};
+module_i2c_driver(helene_driver);
+
 MODULE_DESCRIPTION("Sony HELENE Sat/Ter tuner driver");
 MODULE_AUTHOR("Abylay Ospan <aospan@netup.ru>");
 MODULE_LICENSE("GPL");
diff --git a/drivers/media/dvb-frontends/helene.h b/drivers/media/dvb-frontends/helene.h
index c9fc81c7e4e7..8562d01bc93e 100644
--- a/drivers/media/dvb-frontends/helene.h
+++ b/drivers/media/dvb-frontends/helene.h
@@ -39,6 +39,7 @@ enum helene_xtal {
  * @set_tuner_callback:	Callback function that notifies the parent driver
  *			which tuner is active now
  * @xtal: Cristal frequency as described by &enum helene_xtal
+ * @fe: Frontend for which connects this tuner
  */
 struct helene_config {
 	u8	i2c_address;
@@ -46,6 +47,8 @@ struct helene_config {
 	void	*set_tuner_priv;
 	int	(*set_tuner_callback)(void *, int);
 	enum helene_xtal xtal;
+
+	struct dvb_frontend *fe;
 };
 
 #if IS_REACHABLE(CONFIG_DVB_HELENE)
-- 
cgit v1.2.3


From 65b40a986fc68cb3b362bb855303b73a2b8538c2 Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Wed, 18 Jul 2018 10:13:56 -0400
Subject: media: dm1105: Limit number of cards to avoid buffer over read

dm1105_probe() counts number of cards at dm1105_devcount,
but missed bounds check before dereference a card array.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/dm1105/dm1105.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/media/pci/dm1105/dm1105.c b/drivers/media/pci/dm1105/dm1105.c
index c9db108751a7..1ddb0576fb7b 100644
--- a/drivers/media/pci/dm1105/dm1105.c
+++ b/drivers/media/pci/dm1105/dm1105.c
@@ -986,6 +986,9 @@ static int dm1105_probe(struct pci_dev *pdev,
 	int ret = -ENOMEM;
 	int i;
 
+	if (dm1105_devcount >= ARRAY_SIZE(card))
+		return -ENODEV;
+
 	dev = kzalloc(sizeof(struct dm1105_dev), GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
-- 
cgit v1.2.3


From 0f408ce8941fcb1b6e8431272cfc9337a0407d73 Mon Sep 17 00:00:00 2001
From: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Date: Mon, 23 Jul 2018 04:51:50 -0400
Subject: media: dvb-frontends: add Socionext MN88443x ISDB-S/T demodulator
 driver

This patch adds a frontend driver for the Socionext/Panasonic
MN884434 and MN884433 ISDB-S/T demodulators.

The maximum and minimum frequency of MN88443x comes from
ISDB-S and ISDB-T so frequency range is the following:
  - ISDB-S (BS/CS110 IF frequency, Local freq 10.678GHz)
    - Min: BS-1: 1032MHz
    - Max: ND24: 2070MHz
  - ISDB-T
    - Min: ch13: 470MHz
    - Max: ch62: 770MHz

Signed-off-by: Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/Kconfig    |  10 +
 drivers/media/dvb-frontends/Makefile   |   1 +
 drivers/media/dvb-frontends/mn88443x.c | 802 +++++++++++++++++++++++++++++++++
 drivers/media/dvb-frontends/mn88443x.h |  27 ++
 4 files changed, 840 insertions(+)
 create mode 100644 drivers/media/dvb-frontends/mn88443x.c
 create mode 100644 drivers/media/dvb-frontends/mn88443x.h

diff --git a/drivers/media/dvb-frontends/Kconfig b/drivers/media/dvb-frontends/Kconfig
index 9ecaa9d0744a..048285134cdf 100644
--- a/drivers/media/dvb-frontends/Kconfig
+++ b/drivers/media/dvb-frontends/Kconfig
@@ -739,6 +739,16 @@ config DVB_TC90522
 	  Toshiba TC90522 2xISDB-S 8PSK + 2xISDB-T OFDM demodulator.
 	  Say Y when you want to support this frontend.
 
+config DVB_MN88443X
+	tristate "Socionext MN88443x"
+	depends on DVB_CORE && I2C
+	select REGMAP_I2C
+	default m if !MEDIA_SUBDRV_AUTOSELECT
+	help
+	  A driver for Socionext/Panasonic MN884433 and MN884434
+	  ISDB-S + ISDB-T demodulator.
+	  Say Y when you want to support this frontend.
+
 comment "Digital terrestrial only tuners/PLL"
 	depends on DVB_CORE
 
diff --git a/drivers/media/dvb-frontends/Makefile b/drivers/media/dvb-frontends/Makefile
index 67a783fd5ed0..779dfd027b24 100644
--- a/drivers/media/dvb-frontends/Makefile
+++ b/drivers/media/dvb-frontends/Makefile
@@ -125,6 +125,7 @@ obj-$(CONFIG_DVB_AF9033) += af9033.o
 obj-$(CONFIG_DVB_AS102_FE) += as102_fe.o
 obj-$(CONFIG_DVB_GP8PSK_FE) += gp8psk-fe.o
 obj-$(CONFIG_DVB_TC90522) += tc90522.o
+obj-$(CONFIG_DVB_MN88443X) += mn88443x.o
 obj-$(CONFIG_DVB_HORUS3A) += horus3a.o
 obj-$(CONFIG_DVB_ASCOT2E) += ascot2e.o
 obj-$(CONFIG_DVB_HELENE) += helene.o
diff --git a/drivers/media/dvb-frontends/mn88443x.c b/drivers/media/dvb-frontends/mn88443x.c
new file mode 100644
index 000000000000..9ec1aeef03d5
--- /dev/null
+++ b/drivers/media/dvb-frontends/mn88443x.c
@@ -0,0 +1,802 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Socionext MN88443x series demodulator driver for ISDB-S/ISDB-T.
+//
+// Copyright (c) 2018 Socionext Inc.
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_device.h>
+#include <linux/regmap.h>
+#include <media/dvb_math.h>
+
+#include "mn88443x.h"
+
+/* ISDB-S registers */
+#define ATSIDU_S                                    0x2f
+#define ATSIDL_S                                    0x30
+#define TSSET_S                                     0x31
+#define AGCREAD_S                                   0x5a
+#define CPMON1_S                                    0x5e
+#define   CPMON1_S_FSYNC                              BIT(5)
+#define   CPMON1_S_ERRMON                             BIT(4)
+#define   CPMON1_S_SIGOFF                             BIT(3)
+#define   CPMON1_S_W2LOCK                             BIT(2)
+#define   CPMON1_S_W1LOCK                             BIT(1)
+#define   CPMON1_S_DW1LOCK                            BIT(0)
+#define TRMON_S                                     0x60
+#define BERCNFLG_S                                  0x68
+#define   BERCNFLG_S_BERVRDY                          BIT(5)
+#define   BERCNFLG_S_BERVCHK                          BIT(4)
+#define   BERCNFLG_S_BERDRDY                          BIT(3)
+#define   BERCNFLG_S_BERDCHK                          BIT(2)
+#define CNRDXU_S                                    0x69
+#define CNRDXL_S                                    0x6a
+#define CNRDYU_S                                    0x6b
+#define CNRDYL_S                                    0x6c
+#define BERVRDU_S                                   0x71
+#define BERVRDL_S                                   0x72
+#define DOSET1_S                                    0x73
+
+/* Primary ISDB-T */
+#define PLLASET1                                    0x00
+#define PLLASET2                                    0x01
+#define PLLBSET1                                    0x02
+#define PLLBSET2                                    0x03
+#define PLLSET                                      0x04
+#define OUTCSET                                     0x08
+#define   OUTCSET_CHDRV_8MA                           0xff
+#define   OUTCSET_CHDRV_4MA                           0x00
+#define PLDWSET                                     0x09
+#define   PLDWSET_NORMAL                             0x00
+#define   PLDWSET_PULLDOWN                           0xff
+#define HIZSET1                                     0x0a
+#define HIZSET2                                     0x0b
+
+/* Secondary ISDB-T (for MN884434 only) */
+#define RCVSET                                      0x00
+#define TSSET1_M                                    0x01
+#define TSSET2_M                                    0x02
+#define TSSET3_M                                    0x03
+#define INTACSET                                    0x08
+#define HIZSET3                                     0x0b
+
+/* ISDB-T registers */
+#define TSSET1                                      0x05
+#define   TSSET1_TSASEL_MASK                          GENMASK(4, 3)
+#define   TSSET1_TSASEL_ISDBT                         (0x0 << 3)
+#define   TSSET1_TSASEL_ISDBS                         (0x1 << 3)
+#define   TSSET1_TSASEL_NONE                          (0x2 << 3)
+#define   TSSET1_TSBSEL_MASK                          GENMASK(2, 1)
+#define   TSSET1_TSBSEL_ISDBS                         (0x0 << 1)
+#define   TSSET1_TSBSEL_ISDBT                         (0x1 << 1)
+#define   TSSET1_TSBSEL_NONE                          (0x2 << 1)
+#define TSSET2                                      0x06
+#define TSSET3                                      0x07
+#define   TSSET3_INTASEL_MASK                         GENMASK(7, 6)
+#define   TSSET3_INTASEL_T                            (0x0 << 6)
+#define   TSSET3_INTASEL_S                            (0x1 << 6)
+#define   TSSET3_INTASEL_NONE                         (0x2 << 6)
+#define   TSSET3_INTBSEL_MASK                         GENMASK(5, 4)
+#define   TSSET3_INTBSEL_S                            (0x0 << 4)
+#define   TSSET3_INTBSEL_T                            (0x1 << 4)
+#define   TSSET3_INTBSEL_NONE                         (0x2 << 4)
+#define OUTSET2                                     0x0d
+#define PWDSET                                      0x0f
+#define   PWDSET_OFDMPD_MASK                          GENMASK(3, 2)
+#define   PWDSET_OFDMPD_DOWN                          BIT(3)
+#define   PWDSET_PSKPD_MASK                           GENMASK(1, 0)
+#define   PWDSET_PSKPD_DOWN                           BIT(1)
+#define CLKSET1_T                                   0x11
+#define MDSET_T                                     0x13
+#define   MDSET_T_MDAUTO_MASK                         GENMASK(7, 4)
+#define   MDSET_T_MDAUTO_AUTO                         (0xf << 4)
+#define   MDSET_T_MDAUTO_MANUAL                       (0x0 << 4)
+#define   MDSET_T_FFTS_MASK                           GENMASK(3, 2)
+#define   MDSET_T_FFTS_MODE1                          (0x0 << 2)
+#define   MDSET_T_FFTS_MODE2                          (0x1 << 2)
+#define   MDSET_T_FFTS_MODE3                          (0x2 << 2)
+#define   MDSET_T_GI_MASK                             GENMASK(1, 0)
+#define   MDSET_T_GI_1_32                             (0x0 << 0)
+#define   MDSET_T_GI_1_16                             (0x1 << 0)
+#define   MDSET_T_GI_1_8                              (0x2 << 0)
+#define   MDSET_T_GI_1_4                              (0x3 << 0)
+#define MDASET_T                                    0x14
+#define ADCSET1_T                                   0x20
+#define   ADCSET1_T_REFSEL_MASK                       GENMASK(1, 0)
+#define   ADCSET1_T_REFSEL_2V                         (0x3 << 0)
+#define   ADCSET1_T_REFSEL_1_5V                       (0x2 << 0)
+#define   ADCSET1_T_REFSEL_1V                         (0x1 << 0)
+#define NCOFREQU_T                                  0x24
+#define NCOFREQM_T                                  0x25
+#define NCOFREQL_T                                  0x26
+#define FADU_T                                      0x27
+#define FADM_T                                      0x28
+#define FADL_T                                      0x29
+#define AGCSET2_T                                   0x2c
+#define   AGCSET2_T_IFPOLINV_INC                      BIT(0)
+#define   AGCSET2_T_RFPOLINV_INC                      BIT(1)
+#define AGCV3_T                                     0x3e
+#define MDRD_T                                      0xa2
+#define   MDRD_T_SEGID_MASK                           GENMASK(5, 4)
+#define   MDRD_T_SEGID_13                             (0x0 << 4)
+#define   MDRD_T_SEGID_1                              (0x1 << 4)
+#define   MDRD_T_SEGID_3                              (0x2 << 4)
+#define   MDRD_T_FFTS_MASK                            GENMASK(3, 2)
+#define   MDRD_T_FFTS_MODE1                           (0x0 << 2)
+#define   MDRD_T_FFTS_MODE2                           (0x1 << 2)
+#define   MDRD_T_FFTS_MODE3                           (0x2 << 2)
+#define   MDRD_T_GI_MASK                              GENMASK(1, 0)
+#define   MDRD_T_GI_1_32                              (0x0 << 0)
+#define   MDRD_T_GI_1_16                              (0x1 << 0)
+#define   MDRD_T_GI_1_8                               (0x2 << 0)
+#define   MDRD_T_GI_1_4                               (0x3 << 0)
+#define SSEQRD_T                                    0xa3
+#define   SSEQRD_T_SSEQSTRD_MASK                      GENMASK(3, 0)
+#define   SSEQRD_T_SSEQSTRD_RESET                     (0x0 << 0)
+#define   SSEQRD_T_SSEQSTRD_TUNING                    (0x1 << 0)
+#define   SSEQRD_T_SSEQSTRD_AGC                       (0x2 << 0)
+#define   SSEQRD_T_SSEQSTRD_SEARCH                    (0x3 << 0)
+#define   SSEQRD_T_SSEQSTRD_CLOCK_SYNC                (0x4 << 0)
+#define   SSEQRD_T_SSEQSTRD_FREQ_SYNC                 (0x8 << 0)
+#define   SSEQRD_T_SSEQSTRD_FRAME_SYNC                (0x9 << 0)
+#define   SSEQRD_T_SSEQSTRD_SYNC                      (0xa << 0)
+#define   SSEQRD_T_SSEQSTRD_LOCK                      (0xb << 0)
+#define AGCRDU_T                                    0xa8
+#define AGCRDL_T                                    0xa9
+#define CNRDU_T                                     0xbe
+#define CNRDL_T                                     0xbf
+#define BERFLG_T                                    0xc0
+#define   BERFLG_T_BERDRDY                            BIT(7)
+#define   BERFLG_T_BERDCHK                            BIT(6)
+#define   BERFLG_T_BERVRDYA                           BIT(5)
+#define   BERFLG_T_BERVCHKA                           BIT(4)
+#define   BERFLG_T_BERVRDYB                           BIT(3)
+#define   BERFLG_T_BERVCHKB                           BIT(2)
+#define   BERFLG_T_BERVRDYC                           BIT(1)
+#define   BERFLG_T_BERVCHKC                           BIT(0)
+#define BERRDU_T                                    0xc1
+#define BERRDM_T                                    0xc2
+#define BERRDL_T                                    0xc3
+#define BERLENRDU_T                                 0xc4
+#define BERLENRDL_T                                 0xc5
+#define ERRFLG_T                                    0xc6
+#define   ERRFLG_T_BERDOVF                            BIT(7)
+#define   ERRFLG_T_BERVOVFA                           BIT(6)
+#define   ERRFLG_T_BERVOVFB                           BIT(5)
+#define   ERRFLG_T_BERVOVFC                           BIT(4)
+#define   ERRFLG_T_NERRFA                             BIT(3)
+#define   ERRFLG_T_NERRFB                             BIT(2)
+#define   ERRFLG_T_NERRFC                             BIT(1)
+#define   ERRFLG_T_NERRF                              BIT(0)
+#define DOSET1_T                                    0xcf
+
+#define CLK_LOW            4000000
+#define CLK_DIRECT         20200000
+#define CLK_MAX            25410000
+
+#define S_T_FREQ           8126984 /* 512 / 63 MHz */
+
+struct mn88443x_spec {
+	bool primary;
+};
+
+struct mn88443x_priv {
+	const struct mn88443x_spec *spec;
+
+	struct dvb_frontend fe;
+	struct clk *mclk;
+	struct gpio_desc *reset_gpio;
+	u32 clk_freq;
+	u32 if_freq;
+
+	/* Common */
+	bool use_clkbuf;
+
+	/* ISDB-S */
+	struct i2c_client *client_s;
+	struct regmap *regmap_s;
+
+	/* ISDB-T */
+	struct i2c_client *client_t;
+	struct regmap *regmap_t;
+};
+
+static void mn88443x_cmn_power_on(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	clk_prepare_enable(chip->mclk);
+
+	gpiod_set_value_cansleep(chip->reset_gpio, 1);
+	usleep_range(100, 1000);
+	gpiod_set_value_cansleep(chip->reset_gpio, 0);
+
+	if (chip->spec->primary) {
+		regmap_write(r_t, OUTCSET, OUTCSET_CHDRV_8MA);
+		regmap_write(r_t, PLDWSET, PLDWSET_NORMAL);
+		regmap_write(r_t, HIZSET1, 0x80);
+		regmap_write(r_t, HIZSET2, 0xe0);
+	} else {
+		regmap_write(r_t, HIZSET3, 0x8f);
+	}
+}
+
+static void mn88443x_cmn_power_off(struct mn88443x_priv *chip)
+{
+	gpiod_set_value_cansleep(chip->reset_gpio, 1);
+
+	clk_disable_unprepare(chip->mclk);
+}
+
+static void mn88443x_s_sleep(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_PSKPD_MASK,
+			   PWDSET_PSKPD_DOWN);
+}
+
+static void mn88443x_s_wake(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_PSKPD_MASK, 0);
+}
+
+static void mn88443x_s_tune(struct mn88443x_priv *chip,
+			    struct dtv_frontend_properties *c)
+{
+	struct regmap *r_s = chip->regmap_s;
+
+	regmap_write(r_s, ATSIDU_S, c->stream_id >> 8);
+	regmap_write(r_s, ATSIDL_S, c->stream_id);
+	regmap_write(r_s, TSSET_S, 0);
+}
+
+static int mn88443x_s_read_status(struct mn88443x_priv *chip,
+				  struct dtv_frontend_properties *c,
+				  enum fe_status *status)
+{
+	struct regmap *r_s = chip->regmap_s;
+	u32 cpmon, tmpu, tmpl, flg;
+	u64 tmp;
+
+	/* Sync detection */
+	regmap_read(r_s, CPMON1_S, &cpmon);
+
+	*status = 0;
+	if (cpmon & CPMON1_S_FSYNC)
+		*status |= FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+	if (cpmon & CPMON1_S_W2LOCK)
+		*status |= FE_HAS_SIGNAL | FE_HAS_CARRIER;
+
+	/* Signal strength */
+	c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_SIGNAL) {
+		u32 agc;
+
+		regmap_read(r_s, AGCREAD_S, &tmpu);
+		agc = tmpu << 8;
+
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_RELATIVE;
+		c->strength.stat[0].uvalue = agc;
+	}
+
+	/* C/N rate */
+	c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_VITERBI) {
+		u32 cnr = 0, x, y, d;
+		u64 d_3 = 0;
+
+		regmap_read(r_s, CNRDXU_S, &tmpu);
+		regmap_read(r_s, CNRDXL_S, &tmpl);
+		x = (tmpu << 8) | tmpl;
+		regmap_read(r_s, CNRDYU_S, &tmpu);
+		regmap_read(r_s, CNRDYL_S, &tmpl);
+		y = (tmpu << 8) | tmpl;
+
+		/* CNR[dB]: 10 * log10(D) - 30.74 / D^3 - 3 */
+		/*   D = x^2 / (2^15 * y - x^2) */
+		d = (y << 15) - x * x;
+		if (d > 0) {
+			/* (2^4 * D)^3 = 2^12 * D^3 */
+			/* 3.074 * 2^(12 + 24) = 211243671486 */
+			d_3 = div_u64(16 * x * x, d);
+			d_3 = d_3 * d_3 * d_3;
+			if (d_3)
+				d_3 = div_u64(211243671486ULL, d_3);
+		}
+
+		if (d_3) {
+			/* 0.3 * 2^24 = 5033164 */
+			tmp = (s64)2 * intlog10(x) - intlog10(abs(d)) - d_3
+				- 5033164;
+			cnr = div_u64(tmp * 10000, 1 << 24);
+		}
+
+		if (cnr) {
+			c->cnr.len = 1;
+			c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+			c->cnr.stat[0].uvalue = cnr;
+		}
+	}
+
+	/* BER */
+	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	regmap_read(r_s, BERCNFLG_S, &flg);
+
+	if ((*status & FE_HAS_VITERBI) && (flg & BERCNFLG_S_BERVRDY)) {
+		u32 bit_err, bit_cnt;
+
+		regmap_read(r_s, BERVRDU_S, &tmpu);
+		regmap_read(r_s, BERVRDL_S, &tmpl);
+		bit_err = (tmpu << 8) | tmpl;
+		bit_cnt = (1 << 13) * 204;
+
+		if (bit_cnt) {
+			c->post_bit_error.len = 1;
+			c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_error.stat[0].uvalue = bit_err;
+			c->post_bit_count.len = 1;
+			c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_count.stat[0].uvalue = bit_cnt;
+		}
+	}
+
+	return 0;
+}
+
+static void mn88443x_t_sleep(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_OFDMPD_MASK,
+			   PWDSET_OFDMPD_DOWN);
+}
+
+static void mn88443x_t_wake(struct mn88443x_priv *chip)
+{
+	struct regmap *r_t = chip->regmap_t;
+
+	regmap_update_bits(r_t, PWDSET, PWDSET_OFDMPD_MASK, 0);
+}
+
+static bool mn88443x_t_is_valid_clk(u32 adckt, u32 if_freq)
+{
+	if (if_freq == DIRECT_IF_57MHZ) {
+		if (adckt >= CLK_DIRECT && adckt <= 21000000)
+			return true;
+		if (adckt >= 25300000 && adckt <= CLK_MAX)
+			return true;
+	} else if (if_freq == DIRECT_IF_44MHZ) {
+		if (adckt >= 25000000 && adckt <= CLK_MAX)
+			return true;
+	} else if (if_freq >= LOW_IF_4MHZ && if_freq < DIRECT_IF_44MHZ) {
+		if (adckt >= CLK_DIRECT && adckt <= CLK_MAX)
+			return true;
+	}
+
+	return false;
+}
+
+static int mn88443x_t_set_freq(struct mn88443x_priv *chip)
+{
+	struct device *dev = &chip->client_s->dev;
+	struct regmap *r_t = chip->regmap_t;
+	s64 adckt, nco, ad_t;
+	u32 m, v;
+
+	/* Clock buffer (but not supported) or XTAL */
+	if (chip->clk_freq >= CLK_LOW && chip->clk_freq < CLK_DIRECT) {
+		chip->use_clkbuf = true;
+		regmap_write(r_t, CLKSET1_T, 0x07);
+
+		adckt = 0;
+	} else {
+		chip->use_clkbuf = false;
+		regmap_write(r_t, CLKSET1_T, 0x00);
+
+		adckt = chip->clk_freq;
+	}
+	if (!mn88443x_t_is_valid_clk(adckt, chip->if_freq)) {
+		dev_err(dev, "Invalid clock, CLK:%d, ADCKT:%lld, IF:%d\n",
+			chip->clk_freq, adckt, chip->if_freq);
+		return -EINVAL;
+	}
+
+	/* Direct IF or Low IF */
+	if (chip->if_freq == DIRECT_IF_57MHZ ||
+	    chip->if_freq == DIRECT_IF_44MHZ)
+		nco = adckt * 2 - chip->if_freq;
+	else
+		nco = -((s64)chip->if_freq);
+	nco = div_s64(nco << 24, adckt);
+	ad_t = div_s64(adckt << 22, S_T_FREQ);
+
+	regmap_write(r_t, NCOFREQU_T, nco >> 16);
+	regmap_write(r_t, NCOFREQM_T, nco >> 8);
+	regmap_write(r_t, NCOFREQL_T, nco);
+	regmap_write(r_t, FADU_T, ad_t >> 16);
+	regmap_write(r_t, FADM_T, ad_t >> 8);
+	regmap_write(r_t, FADL_T, ad_t);
+
+	/* Level of IF */
+	m = ADCSET1_T_REFSEL_MASK;
+	v = ADCSET1_T_REFSEL_1_5V;
+	regmap_update_bits(r_t, ADCSET1_T, m, v);
+
+	/* Polarity of AGC */
+	v = AGCSET2_T_IFPOLINV_INC | AGCSET2_T_RFPOLINV_INC;
+	regmap_update_bits(r_t, AGCSET2_T, v, v);
+
+	/* Lower output level of AGC */
+	regmap_write(r_t, AGCV3_T, 0x00);
+
+	regmap_write(r_t, MDSET_T, 0xfa);
+
+	return 0;
+}
+
+static void mn88443x_t_tune(struct mn88443x_priv *chip,
+			    struct dtv_frontend_properties *c)
+{
+	struct regmap *r_t = chip->regmap_t;
+	u32 m, v;
+
+	m = MDSET_T_MDAUTO_MASK | MDSET_T_FFTS_MASK | MDSET_T_GI_MASK;
+	v = MDSET_T_MDAUTO_AUTO | MDSET_T_FFTS_MODE3 | MDSET_T_GI_1_8;
+	regmap_update_bits(r_t, MDSET_T, m, v);
+
+	regmap_write(r_t, MDASET_T, 0);
+}
+
+static int mn88443x_t_read_status(struct mn88443x_priv *chip,
+				  struct dtv_frontend_properties *c,
+				  enum fe_status *status)
+{
+	struct regmap *r_t = chip->regmap_t;
+	u32 seqrd, st, flg, tmpu, tmpm, tmpl;
+	u64 tmp;
+
+	/* Sync detection */
+	regmap_read(r_t, SSEQRD_T, &seqrd);
+	st = seqrd & SSEQRD_T_SSEQSTRD_MASK;
+
+	*status = 0;
+	if (st >= SSEQRD_T_SSEQSTRD_SYNC)
+		*status |= FE_HAS_VITERBI | FE_HAS_SYNC | FE_HAS_LOCK;
+	if (st >= SSEQRD_T_SSEQSTRD_FRAME_SYNC)
+		*status |= FE_HAS_SIGNAL | FE_HAS_CARRIER;
+
+	/* Signal strength */
+	c->strength.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_SIGNAL) {
+		u32 agc;
+
+		regmap_read(r_t, AGCRDU_T, &tmpu);
+		regmap_read(r_t, AGCRDL_T, &tmpl);
+		agc = (tmpu << 8) | tmpl;
+
+		c->strength.len = 1;
+		c->strength.stat[0].scale = FE_SCALE_RELATIVE;
+		c->strength.stat[0].uvalue = agc;
+	}
+
+	/* C/N rate */
+	c->cnr.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	if (*status & FE_HAS_VITERBI) {
+		u32 cnr;
+
+		regmap_read(r_t, CNRDU_T, &tmpu);
+		regmap_read(r_t, CNRDL_T, &tmpl);
+
+		if (tmpu || tmpl) {
+			/* CNR[dB]: 10 * (log10(65536 / value) + 0.2) */
+			/* intlog10(65536) = 80807124, 0.2 * 2^24 = 3355443 */
+			tmp = (u64)80807124 - intlog10((tmpu << 8) | tmpl)
+				+ 3355443;
+			cnr = div_u64(tmp * 10000, 1 << 24);
+		} else {
+			cnr = 0;
+		}
+
+		c->cnr.len = 1;
+		c->cnr.stat[0].scale = FE_SCALE_DECIBEL;
+		c->cnr.stat[0].uvalue = cnr;
+	}
+
+	/* BER */
+	c->post_bit_error.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+	c->post_bit_count.stat[0].scale = FE_SCALE_NOT_AVAILABLE;
+
+	regmap_read(r_t, BERFLG_T, &flg);
+
+	if ((*status & FE_HAS_VITERBI) && (flg & BERFLG_T_BERVRDYA)) {
+		u32 bit_err, bit_cnt;
+
+		regmap_read(r_t, BERRDU_T, &tmpu);
+		regmap_read(r_t, BERRDM_T, &tmpm);
+		regmap_read(r_t, BERRDL_T, &tmpl);
+		bit_err = (tmpu << 16) | (tmpm << 8) | tmpl;
+
+		regmap_read(r_t, BERLENRDU_T, &tmpu);
+		regmap_read(r_t, BERLENRDL_T, &tmpl);
+		bit_cnt = ((tmpu << 8) | tmpl) * 203 * 8;
+
+		if (bit_cnt) {
+			c->post_bit_error.len = 1;
+			c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_error.stat[0].uvalue = bit_err;
+			c->post_bit_count.len = 1;
+			c->post_bit_count.stat[0].scale = FE_SCALE_COUNTER;
+			c->post_bit_count.stat[0].uvalue = bit_cnt;
+		}
+	}
+
+	return 0;
+}
+
+static int mn88443x_sleep(struct dvb_frontend *fe)
+{
+	struct mn88443x_priv *chip = fe->demodulator_priv;
+
+	mn88443x_s_sleep(chip);
+	mn88443x_t_sleep(chip);
+
+	return 0;
+}
+
+static int mn88443x_set_frontend(struct dvb_frontend *fe)
+{
+	struct mn88443x_priv *chip = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+	struct regmap *r_s = chip->regmap_s;
+	struct regmap *r_t = chip->regmap_t;
+	u8 tssel = 0, intsel = 0;
+
+	if (c->delivery_system == SYS_ISDBS) {
+		mn88443x_s_wake(chip);
+		mn88443x_t_sleep(chip);
+
+		tssel = TSSET1_TSASEL_ISDBS;
+		intsel = TSSET3_INTASEL_S;
+	} else if (c->delivery_system == SYS_ISDBT) {
+		mn88443x_s_sleep(chip);
+		mn88443x_t_wake(chip);
+
+		mn88443x_t_set_freq(chip);
+
+		tssel = TSSET1_TSASEL_ISDBT;
+		intsel = TSSET3_INTASEL_T;
+	}
+
+	regmap_update_bits(r_t, TSSET1,
+			   TSSET1_TSASEL_MASK | TSSET1_TSBSEL_MASK,
+			   tssel | TSSET1_TSBSEL_NONE);
+	regmap_write(r_t, TSSET2, 0);
+	regmap_update_bits(r_t, TSSET3,
+			   TSSET3_INTASEL_MASK | TSSET3_INTBSEL_MASK,
+			   intsel | TSSET3_INTBSEL_NONE);
+
+	regmap_write(r_t, DOSET1_T, 0x95);
+	regmap_write(r_s, DOSET1_S, 0x80);
+
+	if (c->delivery_system == SYS_ISDBS)
+		mn88443x_s_tune(chip, c);
+	else if (c->delivery_system == SYS_ISDBT)
+		mn88443x_t_tune(chip, c);
+
+	if (fe->ops.tuner_ops.set_params) {
+		if (fe->ops.i2c_gate_ctrl)
+			fe->ops.i2c_gate_ctrl(fe, 1);
+		fe->ops.tuner_ops.set_params(fe);
+		if (fe->ops.i2c_gate_ctrl)
+			fe->ops.i2c_gate_ctrl(fe, 0);
+	}
+
+	return 0;
+}
+
+static int mn88443x_get_tune_settings(struct dvb_frontend *fe,
+				      struct dvb_frontend_tune_settings *s)
+{
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	s->min_delay_ms = 850;
+
+	if (c->delivery_system == SYS_ISDBS) {
+		s->max_drift = 30000 * 2 + 1;
+		s->step_size = 30000;
+	} else if (c->delivery_system == SYS_ISDBT) {
+		s->max_drift = 142857 * 2 + 1;
+		s->step_size = 142857 * 2;
+	}
+
+	return 0;
+}
+
+static int mn88443x_read_status(struct dvb_frontend *fe, enum fe_status *status)
+{
+	struct mn88443x_priv *chip = fe->demodulator_priv;
+	struct dtv_frontend_properties *c = &fe->dtv_property_cache;
+
+	if (c->delivery_system == SYS_ISDBS)
+		return mn88443x_s_read_status(chip, c, status);
+
+	if (c->delivery_system == SYS_ISDBT)
+		return mn88443x_t_read_status(chip, c, status);
+
+	return -EINVAL;
+}
+
+static const struct dvb_frontend_ops mn88443x_ops = {
+	.delsys = { SYS_ISDBS, SYS_ISDBT },
+	.info = {
+		.name = "Socionext MN88443x",
+		.frequency_min_hz =  470 * MHz,
+		.frequency_max_hz = 2071 * MHz,
+		.symbol_rate_min  = 28860000,
+		.symbol_rate_max  = 28860000,
+		.caps = FE_CAN_INVERSION_AUTO | FE_CAN_FEC_AUTO |
+			FE_CAN_QAM_AUTO | FE_CAN_TRANSMISSION_MODE_AUTO |
+			FE_CAN_GUARD_INTERVAL_AUTO | FE_CAN_HIERARCHY_AUTO,
+	},
+
+	.sleep                   = mn88443x_sleep,
+	.set_frontend            = mn88443x_set_frontend,
+	.get_tune_settings       = mn88443x_get_tune_settings,
+	.read_status             = mn88443x_read_status,
+};
+
+static const struct regmap_config regmap_config = {
+	.reg_bits   = 8,
+	.val_bits   = 8,
+	.cache_type = REGCACHE_NONE,
+};
+
+static int mn88443x_probe(struct i2c_client *client,
+			  const struct i2c_device_id *id)
+{
+	struct mn88443x_config *conf = client->dev.platform_data;
+	struct mn88443x_priv *chip;
+	struct device *dev = &client->dev;
+	int ret;
+
+	chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+	if (!chip)
+		return -ENOMEM;
+
+	if (dev->of_node)
+		chip->spec = of_device_get_match_data(dev);
+	else
+		chip->spec = (struct mn88443x_spec *)id->driver_data;
+	if (!chip->spec)
+		return -EINVAL;
+
+	chip->mclk = devm_clk_get(dev, "mclk");
+	if (IS_ERR(chip->mclk) && !conf) {
+		dev_err(dev, "Failed to request mclk: %ld\n",
+			PTR_ERR(chip->mclk));
+		return PTR_ERR(chip->mclk);
+	}
+
+	ret = of_property_read_u32(dev->of_node, "if-frequency",
+				   &chip->if_freq);
+	if (ret && !conf) {
+		dev_err(dev, "Failed to load IF frequency: %d.\n", ret);
+		return ret;
+	}
+
+	chip->reset_gpio = devm_gpiod_get_optional(dev, "reset",
+						   GPIOD_OUT_HIGH);
+	if (IS_ERR(chip->reset_gpio)) {
+		dev_err(dev, "Failed to request reset_gpio: %ld\n",
+			PTR_ERR(chip->reset_gpio));
+		return PTR_ERR(chip->reset_gpio);
+	}
+
+	if (conf) {
+		chip->mclk = conf->mclk;
+		chip->if_freq = conf->if_freq;
+		chip->reset_gpio = conf->reset_gpio;
+
+		*conf->fe = &chip->fe;
+	}
+
+	chip->client_s = client;
+	chip->regmap_s = devm_regmap_init_i2c(chip->client_s, &regmap_config);
+	if (IS_ERR(chip->regmap_s))
+		return PTR_ERR(chip->regmap_s);
+
+	/*
+	 * Chip has two I2C addresses for each satellite/terrestrial system.
+	 * ISDB-T uses address ISDB-S + 4, so we register a dummy client.
+	 */
+	chip->client_t = i2c_new_dummy(client->adapter, client->addr + 4);
+	if (!chip->client_t)
+		return -ENODEV;
+
+	chip->regmap_t = devm_regmap_init_i2c(chip->client_t, &regmap_config);
+	if (IS_ERR(chip->regmap_t)) {
+		ret = PTR_ERR(chip->regmap_t);
+		goto err_i2c_t;
+	}
+
+	chip->clk_freq = clk_get_rate(chip->mclk);
+
+	memcpy(&chip->fe.ops, &mn88443x_ops, sizeof(mn88443x_ops));
+	chip->fe.demodulator_priv = chip;
+	i2c_set_clientdata(client, chip);
+
+	mn88443x_cmn_power_on(chip);
+	mn88443x_s_sleep(chip);
+	mn88443x_t_sleep(chip);
+
+	return 0;
+
+err_i2c_t:
+	i2c_unregister_device(chip->client_t);
+
+	return ret;
+}
+
+static int mn88443x_remove(struct i2c_client *client)
+{
+	struct mn88443x_priv *chip = i2c_get_clientdata(client);
+
+	mn88443x_cmn_power_off(chip);
+
+	i2c_unregister_device(chip->client_t);
+
+	return 0;
+}
+
+static const struct mn88443x_spec mn88443x_spec_pri = {
+	.primary = true,
+};
+
+static const struct mn88443x_spec mn88443x_spec_sec = {
+	.primary = false,
+};
+
+static const struct of_device_id mn88443x_of_match[] = {
+	{ .compatible = "socionext,mn884433",   .data = &mn88443x_spec_pri, },
+	{ .compatible = "socionext,mn884434-0", .data = &mn88443x_spec_pri, },
+	{ .compatible = "socionext,mn884434-1", .data = &mn88443x_spec_sec, },
+	{}
+};
+MODULE_DEVICE_TABLE(of, mn88443x_of_match);
+
+static const struct i2c_device_id mn88443x_i2c_id[] = {
+	{ "mn884433",   (kernel_ulong_t)&mn88443x_spec_pri },
+	{ "mn884434-0", (kernel_ulong_t)&mn88443x_spec_pri },
+	{ "mn884434-1", (kernel_ulong_t)&mn88443x_spec_sec },
+	{}
+};
+MODULE_DEVICE_TABLE(i2c, mn88443x_i2c_id);
+
+static struct i2c_driver mn88443x_driver = {
+	.driver = {
+		.name = "mn88443x",
+		.of_match_table = of_match_ptr(mn88443x_of_match),
+	},
+	.probe    = mn88443x_probe,
+	.remove   = mn88443x_remove,
+	.id_table = mn88443x_i2c_id,
+};
+
+module_i2c_driver(mn88443x_driver);
+
+MODULE_AUTHOR("Katsuhiro Suzuki <suzuki.katsuhiro@socionext.com>");
+MODULE_DESCRIPTION("Socionext MN88443x series demodulator driver.");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/media/dvb-frontends/mn88443x.h b/drivers/media/dvb-frontends/mn88443x.h
new file mode 100644
index 000000000000..b19aaf6a1ea3
--- /dev/null
+++ b/drivers/media/dvb-frontends/mn88443x.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Socionext MN88443x series demodulator driver for ISDB-S/ISDB-T.
+ *
+ * Copyright (c) 2018 Socionext Inc.
+ */
+
+#ifndef MN88443X_H
+#define MN88443X_H
+
+#include <media/dvb_frontend.h>
+
+/* ISDB-T IF frequency */
+#define DIRECT_IF_57MHZ    57000000
+#define DIRECT_IF_44MHZ    44000000
+#define LOW_IF_4MHZ        4000000
+
+struct mn88443x_config {
+	struct clk *mclk;
+	u32 if_freq;
+	struct gpio_desc *reset_gpio;
+
+	/* Everything after that is returned by the driver. */
+	struct dvb_frontend **fe;
+};
+
+#endif /* MN88443X_H */
-- 
cgit v1.2.3


From ad1363c05a7d65ce6d4c5dca1fdec823b58d6e8b Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Wed, 25 Jul 2018 13:57:00 -0400
Subject: media: omap2: omapfb: fix ifnullfree.cocci warnings

drivers/video/fbdev/omap2/omapfb/dss/core.c:141:2-26: WARNING: NULL check before some freeing functions is not needed.

 NULL check before some freeing functions is not needed.

 Based on checkpatch warning
 "kfree(NULL) is safe this check is probably not required"
 and kfreeaddr.cocci by Julia Lawall.

Generated by: scripts/coccinelle/free/ifnullfree.cocci

Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/video/fbdev/omap2/omapfb/dss/core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/omap2/omapfb/dss/core.c b/drivers/video/fbdev/omap2/omapfb/dss/core.c
index 09e5bb013d28..a5e58a829ea0 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/core.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/core.c
@@ -137,8 +137,7 @@ static int dss_initialize_debugfs(void)
 
 static void dss_uninitialize_debugfs(void)
 {
-	if (dss_debugfs_dir)
-		debugfs_remove_recursive(dss_debugfs_dir);
+	debugfs_remove_recursive(dss_debugfs_dir);
 }
 
 int dss_debugfs_create_file(const char *name, void (*write)(struct seq_file *))
-- 
cgit v1.2.3


From 73fc60aa6386ecb4201908be42241dcbd790d556 Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Wed, 25 Jul 2018 13:57:00 -0400
Subject: media: omap2: omapfb: fix boolreturn.cocci warnings

drivers/video/fbdev/omap2/omapfb/omapfb-main.c:290:9-10: WARNING: return of 0/1 in function 'cmp_var_to_colormode' with return type bool

 Return statements in functions returning bool should use
 true/false instead of 1/0.
Generated by: scripts/coccinelle/misc/boolreturn.cocci

Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/video/fbdev/omap2/omapfb/omapfb-main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
index e08e5664e330..3e7887c53d7c 100644
--- a/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
+++ b/drivers/video/fbdev/omap2/omapfb/omapfb-main.c
@@ -287,7 +287,7 @@ static bool cmp_var_to_colormode(struct fb_var_screeninfo *var,
 			var->red.length == 0 ||
 			var->blue.length == 0 ||
 			var->green.length == 0)
-		return 0;
+		return false;
 
 	return var->bits_per_pixel == color->bits_per_pixel &&
 		cmp_component(&var->red, &color->red) &&
-- 
cgit v1.2.3


From f46bdacdc06a2256187f98d7d063d1bd5c318b12 Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Wed, 25 Jul 2018 13:57:00 -0400
Subject: media: omap2: omapfb: fix bugon.cocci warnings

drivers/video/fbdev/omap2/omapfb/dss/dss_features.c:895:2-5: WARNING: Use BUG_ON instead of if condition followed by BUG.
Please make sure the condition has no side effects (see conditional BUG_ON definition in include/asm-generic/bug.h)

 Use BUG_ON instead of a if condition followed by BUG.

Semantic patch information:
 This makes an effort to find cases where BUG() follows an if
 condition on an expression and replaces the if condition and BUG()
 with a BUG_ON having the conditional expression of the if statement
 as argument.

Generated by: scripts/coccinelle/misc/bugon.cocci

Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/video/fbdev/omap2/omapfb/dss/dss_features.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c b/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
index 8fc843b56b26..e8d428bc47e3 100644
--- a/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
+++ b/drivers/video/fbdev/omap2/omapfb/dss/dss_features.c
@@ -891,8 +891,7 @@ bool dss_has_feature(enum dss_feat_id id)
 
 void dss_feat_get_reg_field(enum dss_feat_reg_field id, u8 *start, u8 *end)
 {
-	if (id >= omap_current_dss_features->num_reg_fields)
-		BUG();
+	BUG_ON(id >= omap_current_dss_features->num_reg_fields);
 
 	*start = omap_current_dss_features->reg_fields[id].start;
 	*end = omap_current_dss_features->reg_fields[id].end;
-- 
cgit v1.2.3


From 730129e9ba4dd668452371eba900e6e46f63b778 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Thu, 26 Jul 2018 22:52:49 -0400
Subject: media: dvb-frontends: rtl2832_sdr: Replace GFP_ATOMIC with GFP_KERNEL

rtl2832_sdr_submit_urbs(), rtl2832_sdr_alloc_stream_bufs(), and
rtl2832_sdr_alloc_urbs() are never called in atomic context.
They call usb_submit_urb(), usb_alloc_coherent() and usb_alloc_urb()
with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/rtl2832_sdr.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/dvb-frontends/rtl2832_sdr.c b/drivers/media/dvb-frontends/rtl2832_sdr.c
index c6e78d870ccd..d448d9d4879c 100644
--- a/drivers/media/dvb-frontends/rtl2832_sdr.c
+++ b/drivers/media/dvb-frontends/rtl2832_sdr.c
@@ -301,7 +301,7 @@ static int rtl2832_sdr_submit_urbs(struct rtl2832_sdr_dev *dev)
 
 	for (i = 0; i < dev->urbs_initialized; i++) {
 		dev_dbg(&pdev->dev, "submit urb=%d\n", i);
-		ret = usb_submit_urb(dev->urb_list[i], GFP_ATOMIC);
+		ret = usb_submit_urb(dev->urb_list[i], GFP_KERNEL);
 		if (ret) {
 			dev_err(&pdev->dev,
 				"Could not submit urb no. %d - get them all back\n",
@@ -345,7 +345,7 @@ static int rtl2832_sdr_alloc_stream_bufs(struct rtl2832_sdr_dev *dev)
 
 	for (dev->buf_num = 0; dev->buf_num < MAX_BULK_BUFS; dev->buf_num++) {
 		dev->buf_list[dev->buf_num] = usb_alloc_coherent(dev->udev,
-				BULK_BUFFER_SIZE, GFP_ATOMIC,
+				BULK_BUFFER_SIZE, GFP_KERNEL,
 				&dev->dma_addr[dev->buf_num]);
 		if (!dev->buf_list[dev->buf_num]) {
 			dev_dbg(&pdev->dev, "alloc buf=%d failed\n",
@@ -390,7 +390,7 @@ static int rtl2832_sdr_alloc_urbs(struct rtl2832_sdr_dev *dev)
 	/* allocate the URBs */
 	for (i = 0; i < MAX_BULK_BUFS; i++) {
 		dev_dbg(&pdev->dev, "alloc urb=%d\n", i);
-		dev->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC);
+		dev->urb_list[i] = usb_alloc_urb(0, GFP_KERNEL);
 		if (!dev->urb_list[i]) {
 			for (j = 0; j < i; j++)
 				usb_free_urb(dev->urb_list[j]);
-- 
cgit v1.2.3


From b9f0f653ea2c214933b16884bd40baf26ff61895 Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Fri, 27 Jul 2018 07:47:59 -0400
Subject: media: vimc: Remove redundant free

Commit 4a29b7090749 ("[media] vimc: Subdevices as modules") removes
vimc allocation from vimc_probe(), so corresponding deallocation
on the error path tries to free static memory.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Acked-by: Helen Koike <helen.koike@collabora.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vimc/vimc-core.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/media/platform/vimc/vimc-core.c b/drivers/media/platform/vimc/vimc-core.c
index fe088a953860..9246f265de31 100644
--- a/drivers/media/platform/vimc/vimc-core.c
+++ b/drivers/media/platform/vimc/vimc-core.c
@@ -328,7 +328,6 @@ static int vimc_probe(struct platform_device *pdev)
 	if (ret) {
 		media_device_cleanup(&vimc->mdev);
 		vimc_rm_subdevs(vimc);
-		kfree(vimc);
 		return ret;
 	}
 
-- 
cgit v1.2.3


From 61e641f36ed81ae473177c085f0bfd83ad3b55ed Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Fri, 27 Jul 2018 07:52:20 -0400
Subject: media: davinci: vpif_display: Mix memory leak on probe error path

If vpif_probe() fails on v4l2_device_register() then memory allocated
at initialize_vpif() for global vpif_obj.dev[i] become unreleased.

The patch adds deallocation of vpif_obj.dev[i] on the error path and
removes duplicated check on platform_data presence.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/davinci/vpif_display.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/drivers/media/platform/davinci/vpif_display.c b/drivers/media/platform/davinci/vpif_display.c
index 7be636237acf..0f324055cc9f 100644
--- a/drivers/media/platform/davinci/vpif_display.c
+++ b/drivers/media/platform/davinci/vpif_display.c
@@ -1114,6 +1114,14 @@ vpif_init_free_channel_objects:
 	return err;
 }
 
+static void free_vpif_objs(void)
+{
+	int i;
+
+	for (i = 0; i < VPIF_DISPLAY_MAX_DEVICES; i++)
+		kfree(vpif_obj.dev[i]);
+}
+
 static int vpif_async_bound(struct v4l2_async_notifier *notifier,
 			    struct v4l2_subdev *subdev,
 			    struct v4l2_async_subdev *asd)
@@ -1255,11 +1263,6 @@ static __init int vpif_probe(struct platform_device *pdev)
 		return -EINVAL;
 	}
 
-	if (!pdev->dev.platform_data) {
-		dev_warn(&pdev->dev, "Missing platform data.  Giving up.\n");
-		return -EINVAL;
-	}
-
 	vpif_dev = &pdev->dev;
 	err = initialize_vpif();
 
@@ -1271,7 +1274,7 @@ static __init int vpif_probe(struct platform_device *pdev)
 	err = v4l2_device_register(vpif_dev, &vpif_obj.v4l2_dev);
 	if (err) {
 		v4l2_err(vpif_dev->driver, "Error registering v4l2 device\n");
-		return err;
+		goto vpif_free;
 	}
 
 	while ((res = platform_get_resource(pdev, IORESOURCE_IRQ, res_idx))) {
@@ -1314,7 +1317,10 @@ static __init int vpif_probe(struct platform_device *pdev)
 			if (vpif_obj.sd[i])
 				vpif_obj.sd[i]->grp_id = 1 << i;
 		}
-		vpif_probe_complete();
+		err = vpif_probe_complete();
+		if (err) {
+			goto probe_subdev_out;
+		}
 	} else {
 		vpif_obj.notifier.subdevs = vpif_obj.config->asd;
 		vpif_obj.notifier.num_subdevs = vpif_obj.config->asd_sizes[0];
@@ -1334,6 +1340,8 @@ probe_subdev_out:
 	kfree(vpif_obj.sd);
 vpif_unregister:
 	v4l2_device_unregister(&vpif_obj.v4l2_dev);
+vpif_free:
+	free_vpif_objs();
 
 	return err;
 }
@@ -1355,8 +1363,8 @@ static int vpif_remove(struct platform_device *device)
 		ch = vpif_obj.dev[i];
 		/* Unregister video device */
 		video_unregister_device(&ch->video_dev);
-		kfree(vpif_obj.dev[i]);
 	}
+	free_vpif_objs();
 
 	return 0;
 }
-- 
cgit v1.2.3


From 2453e60702e1a4d22720e3b6aac543e1a96fcd6b Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 30 Jul 2018 05:25:07 -0400
Subject: media: usb: em28xx: Replace GFP_ATOMIC with GFP_KERNEL in
 em28xx_init_usb_xfer()

em28xx_init_usb_xfer() is never called in atomic context.
It calls usb_submit_urb() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/em28xx/em28xx-core.c b/drivers/media/usb/em28xx/em28xx-core.c
index 45b24776a695..5657f8710ca6 100644
--- a/drivers/media/usb/em28xx/em28xx-core.c
+++ b/drivers/media/usb/em28xx/em28xx-core.c
@@ -1053,7 +1053,7 @@ int em28xx_init_usb_xfer(struct em28xx *dev, enum em28xx_mode mode,
 
 	/* submit urbs and enables IRQ */
 	for (i = 0; i < usb_bufs->num_bufs; i++) {
-		rc = usb_submit_urb(usb_bufs->urb[i], GFP_ATOMIC);
+		rc = usb_submit_urb(usb_bufs->urb[i], GFP_KERNEL);
 		if (rc) {
 			dev_err(&dev->intf->dev,
 				"submit of urb %i failed (error=%i)\n", i, rc);
-- 
cgit v1.2.3


From 7a3369e8a78538e813e96294b8c7fce9feb76e0f Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 30 Jul 2018 05:24:59 -0400
Subject: media: usb: em28xx: Replace mdelay() with msleep() in
 em28xx_pre_card_setup()

em28xx_pre_card_setup() is never called in atomic context.
It calls mdelay() to busily wait, which is not necessary.
mdelay() can be replaced with msleep().

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/em28xx/em28xx-cards.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/media/usb/em28xx/em28xx-cards.c b/drivers/media/usb/em28xx/em28xx-cards.c
index 98a428769baa..71c829f31d3b 100644
--- a/drivers/media/usb/em28xx/em28xx-cards.c
+++ b/drivers/media/usb/em28xx/em28xx-cards.c
@@ -2852,13 +2852,13 @@ static void em28xx_pre_card_setup(struct em28xx *dev)
 		em28xx_write_reg(dev, EM2880_R04_GPO, 0x01);
 		usleep_range(10000, 11000);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfd);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfc);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xdc);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfc);
-		mdelay(70);
+		msleep(70);
 		break;
 	case EM2870_BOARD_TERRATEC_XS_MT2060:
 		/*
@@ -2866,11 +2866,11 @@ static void em28xx_pre_card_setup(struct em28xx *dev)
 		 * demod work
 		 */
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xde);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		break;
 	case EM2870_BOARD_PINNACLE_PCTV_DVB:
 		/*
@@ -2878,11 +2878,11 @@ static void em28xx_pre_card_setup(struct em28xx *dev)
 		 * DVB-T demod work
 		 */
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xde);
-		mdelay(70);
+		msleep(70);
 		em28xx_write_reg(dev, EM2820_R08_GPIO_CTRL, 0xfe);
-		mdelay(70);
+		msleep(70);
 		break;
 	case EM2820_BOARD_GADMEI_UTV310:
 	case EM2820_BOARD_MSI_VOX_USB_2:
-- 
cgit v1.2.3


From 2c3449fb95c318920ca8dc645d918d408db219ac Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 30 Jul 2018 05:33:20 -0400
Subject: media: usb: hackrf: Replace GFP_ATOMIC with GFP_KERNEL

hackrf_submit_urbs(), hackrf_alloc_stream_bufs() and hackrf_alloc_urbs()
are never called in atomic context.
They call usb_submit_urb(), usb_alloc_coherent() and usb_alloc_urb()
with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/hackrf/hackrf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/usb/hackrf/hackrf.c b/drivers/media/usb/hackrf/hackrf.c
index 6d692fb3e8dd..34085a0b15a1 100644
--- a/drivers/media/usb/hackrf/hackrf.c
+++ b/drivers/media/usb/hackrf/hackrf.c
@@ -597,7 +597,7 @@ static int hackrf_submit_urbs(struct hackrf_dev *dev)
 
 	for (i = 0; i < dev->urbs_initialized; i++) {
 		dev_dbg(dev->dev, "submit urb=%d\n", i);
-		ret = usb_submit_urb(dev->urb_list[i], GFP_ATOMIC);
+		ret = usb_submit_urb(dev->urb_list[i], GFP_KERNEL);
 		if (ret) {
 			dev_err(dev->dev, "Could not submit URB no. %d - get them all back\n",
 					i);
@@ -636,7 +636,7 @@ static int hackrf_alloc_stream_bufs(struct hackrf_dev *dev)
 
 	for (dev->buf_num = 0; dev->buf_num < MAX_BULK_BUFS; dev->buf_num++) {
 		dev->buf_list[dev->buf_num] = usb_alloc_coherent(dev->udev,
-				BULK_BUFFER_SIZE, GFP_ATOMIC,
+				BULK_BUFFER_SIZE, GFP_KERNEL,
 				&dev->dma_addr[dev->buf_num]);
 		if (!dev->buf_list[dev->buf_num]) {
 			dev_dbg(dev->dev, "alloc buf=%d failed\n",
@@ -689,7 +689,7 @@ static int hackrf_alloc_urbs(struct hackrf_dev *dev, bool rcv)
 	/* allocate the URBs */
 	for (i = 0; i < MAX_BULK_BUFS; i++) {
 		dev_dbg(dev->dev, "alloc urb=%d\n", i);
-		dev->urb_list[i] = usb_alloc_urb(0, GFP_ATOMIC);
+		dev->urb_list[i] = usb_alloc_urb(0, GFP_KERNEL);
 		if (!dev->urb_list[i]) {
 			for (j = 0; j < i; j++)
 				usb_free_urb(dev->urb_list[j]);
-- 
cgit v1.2.3


From 6534770d6f176093b50896961107b2d545ef38f0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Thu, 2 Aug 2018 19:30:27 -0700
Subject: tools: bpf: fix BTF code added twice to different trees

commit 38d5d3b3d5db ("bpf: Introduce BPF_ANNOTATE_KV_PAIR")

added to the bpf and net trees what

commit 92b57121ca79 ("bpf: btf: export btf types and name by offset from lib")

has already added to bpf-next/net-next, but in slightly different
location.  Remove the duplicates (to fix build of libbpf).

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/lib/bpf/btf.c | 17 -----------------
 tools/lib/bpf/btf.h |  1 -
 2 files changed, 18 deletions(-)

diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index 1622a309f169..09ecf8162f7a 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -37,14 +37,6 @@ struct btf {
 	int fd;
 };
 
-static const char *btf_name_by_offset(const struct btf *btf, __u32 offset)
-{
-	if (offset < btf->hdr->str_len)
-		return &btf->strings[offset];
-	else
-		return NULL;
-}
-
 static int btf_add_type(struct btf *btf, struct btf_type *t)
 {
 	if (btf->types_size - btf->nr_types < 2) {
@@ -401,12 +393,3 @@ const char *btf__name_by_offset(const struct btf *btf, __u32 offset)
 	else
 		return NULL;
 }
-
-const struct btf_type *btf__type_by_id(const struct btf *btf,
-				       __u32 type_id)
-{
-	if (type_id > btf->nr_types)
-		return NULL;
-
-	return btf->types[type_id];
-}
diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h
index dd8a86eab8ca..43c658ccfc2b 100644
--- a/tools/lib/bpf/btf.h
+++ b/tools/lib/bpf/btf.h
@@ -22,6 +22,5 @@ __s64 btf__resolve_size(const struct btf *btf, __u32 type_id);
 int btf__resolve_type(const struct btf *btf, __u32 type_id);
 int btf__fd(const struct btf *btf);
 const char *btf__name_by_offset(const struct btf *btf, __u32 offset);
-const struct btf_type *btf__type_by_id(const struct btf *btf, __u32 type_id);
 
 #endif
-- 
cgit v1.2.3


From 98719051e75ccf9eca18bd2b569de4ea637b4479 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:29 -0700
Subject: xfs: refactor internal dfops initialization

The current transaction allocation code conditionally initializes
the ->t_dfops indirection pointer. Transaction commit/cancel check
the validity of the pointer to determine whether to finish/cancel
the internal dfops.

This disallows the ability to use the internal dfops list as a
temporary container (via xfs_trans_alloc_empty()). Refactor
transaction allocation to always initialize ->t_dfops and check
permanent reservation state on transaction commit/cancel.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_trans.c | 19 +++++++++----------
 1 file changed, 9 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 7bf5c1202719..12b6ad1558e6 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -281,13 +281,7 @@ xfs_trans_alloc(
 	INIT_LIST_HEAD(&tp->t_items);
 	INIT_LIST_HEAD(&tp->t_busy);
 	tp->t_firstblock = NULLFSBLOCK;
-	/*
-	 * We only roll transactions with permanent log reservation. Don't init
-	 * ->t_dfops to skip attempts to finish or cancel an empty dfops with a
-	 * non-permanent res.
-	 */
-	if (resp->tr_logflags & XFS_TRANS_PERM_LOG_RES)
-		xfs_defer_init(tp, &tp->t_dfops_internal);
+	xfs_defer_init(tp, &tp->t_dfops_internal);
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error) {
@@ -931,8 +925,13 @@ __xfs_trans_commit(
 
 	trace_xfs_trans_commit(tp, _RET_IP_);
 
-	/* finish deferred items on final commit */
-	if (!regrant && tp->t_dfops) {
+	/*
+	 * Finish deferred items on final commit. Only permanent transactions
+	 * should ever have deferred ops.
+	 */
+	WARN_ON_ONCE(xfs_defer_has_unfinished_work(tp->t_dfops) &&
+		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
+	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
 		error = xfs_defer_finish_noroll(&tp);
 		if (error) {
 			xfs_defer_cancel(tp);
@@ -1029,7 +1028,7 @@ xfs_trans_cancel(
 
 	trace_xfs_trans_cancel(tp, _RET_IP_);
 
-	if (tp->t_dfops)
+	if (tp->t_flags & XFS_TRANS_PERM_LOG_RES)
 		xfs_defer_cancel(tp);
 
 	/*
-- 
cgit v1.2.3


From fbfa977d25dc8db92dbf5fcafb0e03fae0005be5 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:29 -0700
Subject: xfs: use transaction for intent recovery instead of raw dfops

Log intent recovery is the last user of an external (on-stack)
dfops. The pattern exists because the dfops is used to collect
additional deferred operations queued during the whole recovery
sequence. The dfops is finished with a new transaction after intent
recovery completes.

We already have a mechanism to create an empty, container-like
transaction to support the scrub infrastructure. We can reuse that
mechanism here to drop the final user of external dfops. This
facilitates folding dfops state (i.e., dop_low) into the
transaction, the elimination of now unused external dfops support
and also eliminates the only caller of __xfs_defer_cancel().

Replace the on-stack dfops with an empty transaction and pass it
around to the various helpers that queue and finish deferred
operations during intent recovery.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_bmap_item.c     | 12 +++++------
 fs/xfs/xfs_bmap_item.h     |  3 +--
 fs/xfs/xfs_log_recover.c   | 51 ++++++++++++++++++++++++++--------------------
 fs/xfs/xfs_refcount_item.c | 12 +++++------
 fs/xfs/xfs_refcount_item.h |  3 +--
 5 files changed, 43 insertions(+), 38 deletions(-)

diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index e1d6c127b07d..57429055e608 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -375,9 +375,8 @@ xfs_bud_init(
  */
 int
 xfs_bui_recover(
-	struct xfs_mount		*mp,
-	struct xfs_bui_log_item		*buip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_trans		*parent_tp,
+	struct xfs_bui_log_item		*buip)
 {
 	int				error = 0;
 	unsigned int			bui_type;
@@ -393,6 +392,7 @@ xfs_bui_recover(
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_bmbt_irec		irec;
+	struct xfs_mount		*mp = parent_tp->t_mountp;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
 
@@ -446,7 +446,7 @@ xfs_bui_recover(
 	 * finishes them on completion. Transfer current dfops state to this
 	 * transaction and transfer the result back before we return.
 	 */
-	xfs_defer_move(tp->t_dfops, dfops);
+	xfs_defer_move(tp->t_dfops, parent_tp->t_dfops);
 	budp = xfs_trans_get_bud(tp, buip);
 
 	/* Grab the inode. */
@@ -494,7 +494,7 @@ xfs_bui_recover(
 	}
 
 	set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
-	xfs_defer_move(dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	xfs_irele(ip);
@@ -502,7 +502,7 @@ xfs_bui_recover(
 	return error;
 
 err_inode:
-	xfs_defer_move(dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
 	xfs_trans_cancel(tp);
 	if (ip) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_bmap_item.h b/fs/xfs/xfs_bmap_item.h
index fd1a1b13df51..89e043a88bb8 100644
--- a/fs/xfs/xfs_bmap_item.h
+++ b/fs/xfs/xfs_bmap_item.h
@@ -79,7 +79,6 @@ struct xfs_bud_log_item *xfs_bud_init(struct xfs_mount *,
 		struct xfs_bui_log_item *);
 void xfs_bui_item_free(struct xfs_bui_log_item *);
 void xfs_bui_release(struct xfs_bui_log_item *);
-int xfs_bui_recover(struct xfs_mount *mp, struct xfs_bui_log_item *buip,
-		struct xfs_defer_ops *dfops);
+int xfs_bui_recover(struct xfs_trans *parent_tp, struct xfs_bui_log_item *buip);
 
 #endif	/* __XFS_BMAP_ITEM_H__ */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 7776fde9430c..fc1ce9a644e3 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4733,10 +4733,9 @@ xlog_recover_cancel_rui(
 /* Recover the CUI if necessary. */
 STATIC int
 xlog_recover_process_cui(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*parent_tp,
 	struct xfs_ail			*ailp,
-	struct xfs_log_item		*lip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_log_item		*lip)
 {
 	struct xfs_cui_log_item		*cuip;
 	int				error;
@@ -4749,7 +4748,7 @@ xlog_recover_process_cui(
 		return 0;
 
 	spin_unlock(&ailp->ail_lock);
-	error = xfs_cui_recover(mp, cuip, dfops);
+	error = xfs_cui_recover(parent_tp, cuip);
 	spin_lock(&ailp->ail_lock);
 
 	return error;
@@ -4774,10 +4773,9 @@ xlog_recover_cancel_cui(
 /* Recover the BUI if necessary. */
 STATIC int
 xlog_recover_process_bui(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*parent_tp,
 	struct xfs_ail			*ailp,
-	struct xfs_log_item		*lip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_log_item		*lip)
 {
 	struct xfs_bui_log_item		*buip;
 	int				error;
@@ -4790,7 +4788,7 @@ xlog_recover_process_bui(
 		return 0;
 
 	spin_unlock(&ailp->ail_lock);
-	error = xfs_bui_recover(mp, buip, dfops);
+	error = xfs_bui_recover(parent_tp, buip);
 	spin_lock(&ailp->ail_lock);
 
 	return error;
@@ -4829,9 +4827,9 @@ static inline bool xlog_item_is_intent(struct xfs_log_item *lip)
 /* Take all the collected deferred ops and finish them in order. */
 static int
 xlog_finish_defer_ops(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops)
+	struct xfs_trans	*parent_tp)
 {
+	struct xfs_mount	*mp = parent_tp->t_mountp;
 	struct xfs_trans	*tp;
 	int64_t			freeblks;
 	uint			resblks;
@@ -4855,7 +4853,7 @@ xlog_finish_defer_ops(
 	if (error)
 		return error;
 	/* transfer all collected dfops to this transaction */
-	xfs_defer_move(tp->t_dfops, dfops);
+	xfs_defer_move(tp->t_dfops, parent_tp->t_dfops);
 
 	return xfs_trans_commit(tp);
 }
@@ -4880,22 +4878,34 @@ STATIC int
 xlog_recover_process_intents(
 	struct xlog		*log)
 {
-	struct xfs_defer_ops	dfops;
+	struct xfs_trans	*parent_tp;
 	struct xfs_ail_cursor	cur;
 	struct xfs_log_item	*lip;
 	struct xfs_ail		*ailp;
-	int			error = 0;
+	int			error;
 #if defined(DEBUG) || defined(XFS_WARN)
 	xfs_lsn_t		last_lsn;
 #endif
 
+	/*
+	 * The intent recovery handlers commit transactions to complete recovery
+	 * for individual intents, but any new deferred operations that are
+	 * queued during that process are held off until the very end. The
+	 * purpose of this transaction is to serve as a container for deferred
+	 * operations. Each intent recovery handler must transfer dfops here
+	 * before its local transaction commits, and we'll finish the entire
+	 * list below.
+	 */
+	error = xfs_trans_alloc_empty(log->l_mp, &parent_tp);
+	if (error)
+		return error;
+
 	ailp = log->l_ailp;
 	spin_lock(&ailp->ail_lock);
 	lip = xfs_trans_ail_cursor_first(ailp, &cur, 0);
 #if defined(DEBUG) || defined(XFS_WARN)
 	last_lsn = xlog_assign_lsn(log->l_curr_cycle, log->l_curr_block);
 #endif
-	xfs_defer_init(NULL, &dfops);
 	while (lip != NULL) {
 		/*
 		 * We're done when we see something other than an intent.
@@ -4930,12 +4940,10 @@ xlog_recover_process_intents(
 			error = xlog_recover_process_rui(log->l_mp, ailp, lip);
 			break;
 		case XFS_LI_CUI:
-			error = xlog_recover_process_cui(log->l_mp, ailp, lip,
-					&dfops);
+			error = xlog_recover_process_cui(parent_tp, ailp, lip);
 			break;
 		case XFS_LI_BUI:
-			error = xlog_recover_process_bui(log->l_mp, ailp, lip,
-					&dfops);
+			error = xlog_recover_process_bui(parent_tp, ailp, lip);
 			break;
 		}
 		if (error)
@@ -4945,10 +4953,9 @@ xlog_recover_process_intents(
 out:
 	xfs_trans_ail_cursor_done(&cur);
 	spin_unlock(&ailp->ail_lock);
-	if (error)
-		__xfs_defer_cancel(&dfops);
-	else
-		error = xlog_finish_defer_ops(log->l_mp, &dfops);
+	if (!error)
+		error = xlog_finish_defer_ops(parent_tp);
+	xfs_trans_cancel(parent_tp);
 
 	return error;
 }
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index d3582a06626f..011e1d0640fb 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -380,9 +380,8 @@ xfs_cud_init(
  */
 int
 xfs_cui_recover(
-	struct xfs_mount		*mp,
-	struct xfs_cui_log_item		*cuip,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_trans		*parent_tp,
+	struct xfs_cui_log_item		*cuip)
 {
 	int				i;
 	int				error = 0;
@@ -398,6 +397,7 @@ xfs_cui_recover(
 	xfs_extlen_t			new_len;
 	struct xfs_bmbt_irec		irec;
 	bool				requeue_only = false;
+	struct xfs_mount		*mp = parent_tp->t_mountp;
 
 	ASSERT(!test_bit(XFS_CUI_RECOVERED, &cuip->cui_flags));
 
@@ -457,7 +457,7 @@ xfs_cui_recover(
 	 * finishes them on completion. Transfer current dfops state to this
 	 * transaction and transfer the result back before we return.
 	 */
-	xfs_defer_move(tp->t_dfops, dfops);
+	xfs_defer_move(tp->t_dfops, parent_tp->t_dfops);
 	cudp = xfs_trans_get_cud(tp, cuip);
 
 	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
@@ -522,13 +522,13 @@ xfs_cui_recover(
 
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
-	xfs_defer_move(dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
-	xfs_defer_move(dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
 	xfs_trans_cancel(tp);
 	return error;
 }
diff --git a/fs/xfs/xfs_refcount_item.h b/fs/xfs/xfs_refcount_item.h
index dd830b69cd1e..3896dcc2368f 100644
--- a/fs/xfs/xfs_refcount_item.h
+++ b/fs/xfs/xfs_refcount_item.h
@@ -82,7 +82,6 @@ struct xfs_cud_log_item *xfs_cud_init(struct xfs_mount *,
 		struct xfs_cui_log_item *);
 void xfs_cui_item_free(struct xfs_cui_log_item *);
 void xfs_cui_release(struct xfs_cui_log_item *);
-int xfs_cui_recover(struct xfs_mount *mp, struct xfs_cui_log_item *cuip,
-		struct xfs_defer_ops *dfops);
+int xfs_cui_recover(struct xfs_trans *parent_tp, struct xfs_cui_log_item *cuip);
 
 #endif	/* __XFS_REFCOUNT_ITEM_H__ */
-- 
cgit v1.2.3


From 7279aa13b8fb954f50073a672f912898198efd14 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:30 -0700
Subject: xfs: remove unused __xfs_defer_cancel() internal helper

With no more external dfops users, there is no need for an
xfs_defer_ops cancel wrapper.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 5 +++--
 fs/xfs/libxfs/xfs_defer.h | 2 +-
 fs/xfs/xfs_trans.c        | 7 -------
 fs/xfs/xfs_trans.h        | 3 ---
 4 files changed, 4 insertions(+), 13 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index a5f7dc18a62f..ebead781613f 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -465,9 +465,10 @@ xfs_defer_finish(
  * Free up any items left in the list.
  */
 void
-__xfs_defer_cancel(
-	struct xfs_defer_ops		*dop)
+xfs_defer_cancel(
+	struct xfs_trans		*tp)
 {
+	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct xfs_defer_pending	*dfp;
 	struct xfs_defer_pending	*pli;
 	struct list_head		*pwi;
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 85c41fe4dbae..da145fc04ae1 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -50,7 +50,7 @@ void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
 		struct list_head *h);
 int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
-void __xfs_defer_cancel(struct xfs_defer_ops *dop);
+void xfs_defer_cancel(struct xfs_trans *);
 void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 12b6ad1558e6..0d07cdcc5c7d 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -1110,10 +1110,3 @@ xfs_trans_roll(
 	tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
 	return xfs_trans_reserve(*tpp, &tres, 0, 0);
 }
-
-void
-xfs_defer_cancel(
-	struct xfs_trans	*tp)
-{
-	__xfs_defer_cancel(tp->t_dfops);
-}
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 5170e89bec02..dc79e3c1d3e8 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -214,9 +214,6 @@ xfs_trans_read_buf(
 				      flags, bpp, ops);
 }
 
-/* cancel dfops associated with a transaction */
-void xfs_defer_cancel(struct xfs_trans *);
-
 struct xfs_buf	*xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int);
 
 void		xfs_trans_brelse(xfs_trans_t *, struct xfs_buf *);
-- 
cgit v1.2.3


From ce356d64772f920f26cd6c1b02878a737a275638 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:30 -0700
Subject: xfs: pass transaction to dfops reset/move helpers

All callers pass ->t_dfops of the associated transactions. Refactor
the helpers to receive the transactions and facilitate further
cleanups between xfs_defer_ops and xfs_trans.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c  | 15 ++++++++++-----
 fs/xfs/libxfs/xfs_defer.h  |  2 +-
 fs/xfs/xfs_bmap_item.c     |  6 +++---
 fs/xfs/xfs_log_recover.c   |  2 +-
 fs/xfs/xfs_refcount_item.c |  6 +++---
 fs/xfs/xfs_trans.c         |  2 +-
 6 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index ebead781613f..e3517a53c525 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -324,9 +324,12 @@ xfs_defer_bjoin(
  */
 static void
 xfs_defer_reset(
-	struct xfs_defer_ops	*dop)
+	struct xfs_trans	*tp)
 {
+	struct xfs_defer_ops	*dop = tp->t_dfops;
+
 	ASSERT(!xfs_defer_has_unfinished_work(dop));
+
 	dop->dop_low = false;
 	memset(dop->dop_inodes, 0, sizeof(dop->dop_inodes));
 	memset(dop->dop_bufs, 0, sizeof(dop->dop_bufs));
@@ -457,7 +460,7 @@ xfs_defer_finish(
 		if (error)
 			return error;
 	}
-	xfs_defer_reset((*tp)->t_dfops);
+	xfs_defer_reset(*tp);
 	return 0;
 }
 
@@ -575,9 +578,11 @@ xfs_defer_init(
  */
 void
 xfs_defer_move(
-	struct xfs_defer_ops	*dst,
-	struct xfs_defer_ops	*src)
+	struct xfs_trans	*dtp,
+	struct xfs_trans	*stp)
 {
+	struct xfs_defer_ops	*dst = dtp->t_dfops;
+	struct xfs_defer_ops	*src = stp->t_dfops;
 	ASSERT(dst != src);
 
 	list_splice_init(&src->dop_intake, &dst->dop_intake);
@@ -587,5 +592,5 @@ xfs_defer_move(
 	memcpy(dst->dop_bufs, src->dop_bufs, sizeof(dst->dop_bufs));
 	dst->dop_low = src->dop_low;
 
-	xfs_defer_reset(src);
+	xfs_defer_reset(stp);
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index da145fc04ae1..d60c50498fdf 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -55,7 +55,7 @@ void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
 int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
-void xfs_defer_move(struct xfs_defer_ops *dst, struct xfs_defer_ops *src);
+void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
 struct xfs_defer_op_type {
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 57429055e608..b8a6be036cd7 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -446,7 +446,7 @@ xfs_bui_recover(
 	 * finishes them on completion. Transfer current dfops state to this
 	 * transaction and transfer the result back before we return.
 	 */
-	xfs_defer_move(tp->t_dfops, parent_tp->t_dfops);
+	xfs_defer_move(tp, parent_tp);
 	budp = xfs_trans_get_bud(tp, buip);
 
 	/* Grab the inode. */
@@ -494,7 +494,7 @@ xfs_bui_recover(
 	}
 
 	set_bit(XFS_BUI_RECOVERED, &buip->bui_flags);
-	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp, tp);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	xfs_irele(ip);
@@ -502,7 +502,7 @@ xfs_bui_recover(
 	return error;
 
 err_inode:
-	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp, tp);
 	xfs_trans_cancel(tp);
 	if (ip) {
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index fc1ce9a644e3..a21dc61ec09e 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -4853,7 +4853,7 @@ xlog_finish_defer_ops(
 	if (error)
 		return error;
 	/* transfer all collected dfops to this transaction */
-	xfs_defer_move(tp->t_dfops, parent_tp->t_dfops);
+	xfs_defer_move(tp, parent_tp);
 
 	return xfs_trans_commit(tp);
 }
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 011e1d0640fb..4a417daae781 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -457,7 +457,7 @@ xfs_cui_recover(
 	 * finishes them on completion. Transfer current dfops state to this
 	 * transaction and transfer the result back before we return.
 	 */
-	xfs_defer_move(tp->t_dfops, parent_tp->t_dfops);
+	xfs_defer_move(tp, parent_tp);
 	cudp = xfs_trans_get_cud(tp, cuip);
 
 	for (i = 0; i < cuip->cui_format.cui_nextents; i++) {
@@ -522,13 +522,13 @@ xfs_cui_recover(
 
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
 	set_bit(XFS_CUI_RECOVERED, &cuip->cui_flags);
-	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp, tp);
 	error = xfs_trans_commit(tp);
 	return error;
 
 abort_error:
 	xfs_refcount_finish_one_cleanup(tp, rcur, error);
-	xfs_defer_move(parent_tp->t_dfops, tp->t_dfops);
+	xfs_defer_move(parent_tp, tp);
 	xfs_trans_cancel(tp);
 	return error;
 }
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 0d07cdcc5c7d..ae3c875a14e5 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -125,7 +125,7 @@ xfs_trans_dup(
 	if (tp->t_dfops != &tp->t_dfops_internal)
 		ntp->t_dfops = tp->t_dfops;
 	else
-		xfs_defer_move(ntp->t_dfops, tp->t_dfops);
+		xfs_defer_move(ntp, tp);
 
 	xfs_trans_dup_dqinfo(tp, ntp);
 
-- 
cgit v1.2.3


From 1214f1cf663b0939fbb8f1bccdc74c1d1e452d53 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:31 -0700
Subject: xfs: replace dop_low with transaction flag

The dop_low field enables the low free space allocation mode when a
previous allocation has detected difficulty allocating blocks. It
has historically been part of the xfs_defer_ops structure, which
means if enabled, it remains enabled across a set of transactions
until the deferred operations have completed and the dfops is reset.

Now that the dfops is embedded in the transaction, we can save a bit
more space by using a transaction flag rather than a standalone
boolean. Drop the ->dop_low field and replace it with a transaction
flag that is set at the same points, carried across rolling
transactions and cleared on completion of deferred operations. This
essentially emulates the behavior of ->dop_low and so should not
change behavior.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c       |  8 ++++----
 fs/xfs/libxfs/xfs_bmap_btree.c |  4 ++--
 fs/xfs/libxfs/xfs_defer.c      | 16 ++++++++++++++--
 fs/xfs/libxfs/xfs_defer.h      | 11 -----------
 fs/xfs/libxfs/xfs_shared.h     | 12 ++++++++++++
 fs/xfs/xfs_filestream.c        |  3 ++-
 fs/xfs/xfs_trace.h             | 10 ++--------
 fs/xfs/xfs_trans.h             |  2 --
 8 files changed, 36 insertions(+), 30 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index a85c0445b38f..8edf7522aaff 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -700,7 +700,7 @@ xfs_bmap_extents_to_btree(
 	if (tp->t_firstblock == NULLFSBLOCK) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
-	} else if (tp->t_dfops->dop_low) {
+	} else if (tp->t_flags & XFS_TRANS_LOWMODE) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = tp->t_firstblock;
 	} else {
@@ -3449,7 +3449,7 @@ xfs_bmap_btalloc(
 			error = xfs_bmap_btalloc_nullfb(ap, &args, &blen);
 		if (error)
 			return error;
-	} else if (ap->tp->t_dfops->dop_low) {
+	} else if (ap->tp->t_flags & XFS_TRANS_LOWMODE) {
 		if (xfs_inode_is_filestream(ap->ip))
 			args.type = XFS_ALLOCTYPE_FIRST_AG;
 		else
@@ -3484,7 +3484,7 @@ xfs_bmap_btalloc(
 	 * is >= the stripe unit and the allocation offset is
 	 * at the end of file.
 	 */
-	if (!ap->tp->t_dfops->dop_low && ap->aeof) {
+	if (!(ap->tp->t_flags & XFS_TRANS_LOWMODE) && ap->aeof) {
 		if (!ap->offset) {
 			args.alignment = stripe_align;
 			atype = args.type;
@@ -3576,7 +3576,7 @@ xfs_bmap_btalloc(
 		args.total = ap->minlen;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
-		ap->tp->t_dfops->dop_low = true;
+		ap->tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 	if (args.fsbno != NULLFSBLOCK) {
 		/*
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 01489714a253..955e29de8cae 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -226,7 +226,7 @@ xfs_bmbt_alloc_block(
 		 * block allocation here and corrupt the filesystem.
 		 */
 		args.minleft = args.tp->t_blk_res;
-	} else if (cur->bc_tp->t_dfops->dop_low) {
+	} else if (cur->bc_tp->t_flags & XFS_TRANS_LOWMODE) {
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -253,7 +253,7 @@ xfs_bmbt_alloc_block(
 		error = xfs_alloc_vextent(&args);
 		if (error)
 			goto error0;
-		cur->bc_tp->t_dfops->dop_low = true;
+		cur->bc_tp->t_flags |= XFS_TRANS_LOWMODE;
 	}
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		*stat = 0;
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index e3517a53c525..64e1abc60edc 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -330,9 +330,14 @@ xfs_defer_reset(
 
 	ASSERT(!xfs_defer_has_unfinished_work(dop));
 
-	dop->dop_low = false;
 	memset(dop->dop_inodes, 0, sizeof(dop->dop_inodes));
 	memset(dop->dop_bufs, 0, sizeof(dop->dop_bufs));
+
+	/*
+	 * Low mode state transfers across transaction rolls to mirror dfops
+	 * lifetime. Clear it now that dfops is reset.
+	 */
+	tp->t_flags &= ~XFS_TRANS_LOWMODE;
 }
 
 /*
@@ -590,7 +595,14 @@ xfs_defer_move(
 
 	memcpy(dst->dop_inodes, src->dop_inodes, sizeof(dst->dop_inodes));
 	memcpy(dst->dop_bufs, src->dop_bufs, sizeof(dst->dop_bufs));
-	dst->dop_low = src->dop_low;
+
+	/*
+	 * Low free space mode was historically controlled by a dfops field.
+	 * This meant that low mode state potentially carried across multiple
+	 * transaction rolls. Transfer low mode on a dfops move to preserve
+	 * that behavior.
+	 */
+	dtp->t_flags |= (stp->t_flags & XFS_TRANS_LOWMODE);
 
 	xfs_defer_reset(stp);
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index d60c50498fdf..8908a2716774 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -25,17 +25,6 @@ struct xfs_defer_pending {
 
 /*
  * Header for deferred operation list.
- *
- * dop_low is used by the allocator to activate the lowspace algorithm -
- * when free space is running low the extent allocator may choose to
- * allocate an extent from an AG without leaving sufficient space for
- * a btree split when inserting the new extent.  In this case the allocator
- * will enable the lowspace algorithm which is supposed to allow further
- * allocations (such as btree splits and newroots) to allocate from
- * sequential AGs.  In order to avoid locking AGs out of order the lowspace
- * algorithm will start searching for free space from AG 0.  If the correct
- * transaction reservations have been made then this algorithm will eventually
- * find all the space it needs.
  */
 enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_BMAP,
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 22089f1c880a..1c5debe748f0 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -64,6 +64,18 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 #define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
 #define XFS_TRANS_NO_WRITECOUNT 0x40	/* do not elevate SB writecount */
 #define XFS_TRANS_NOFS		0x80	/* pass KM_NOFS to kmem_alloc */
+/*
+ * LOWMODE is used by the allocator to activate the lowspace algorithm - when
+ * free space is running low the extent allocator may choose to allocate an
+ * extent from an AG without leaving sufficient space for a btree split when
+ * inserting the new extent. In this case the allocator will enable the
+ * lowspace algorithm which is supposed to allow further allocations (such as
+ * btree splits and newroots) to allocate from sequential AGs. In order to
+ * avoid locking AGs out of order the lowspace algorithm will start searching
+ * for free space from AG 0. If the correct transaction reservations have been
+ * made then this algorithm will eventually find all the space it needs.
+ */
+#define XFS_TRANS_LOWMODE	0x100	/* allocate in low space mode */
 
 /*
  * Field values for xfs_trans_mod_sb.
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index 212173c62588..182501373af2 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -20,6 +20,7 @@
 #include "xfs_trace.h"
 #include "xfs_ag_resv.h"
 #include "xfs_trans.h"
+#include "xfs_shared.h"
 
 struct xfs_fstrm_item {
 	struct xfs_mru_cache_elem	mru;
@@ -378,7 +379,7 @@ xfs_filestream_new_ag(
 
 	if (xfs_alloc_is_userdata(ap->datatype))
 		flags |= XFS_PICK_USERDATA;
-	if (ap->tp->t_dfops->dop_low)
+	if (ap->tp->t_flags & XFS_TRANS_LOWMODE)
 		flags |= XFS_PICK_LOWSPACE;
 
 	err = xfs_filestream_pick_ag(pip, startag, agp, flags, minlen);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index cc6995cfce66..8807f1bb814a 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2223,19 +2223,16 @@ DECLARE_EVENT_CLASS(xfs_defer_class,
 		__field(dev_t, dev)
 		__field(void *, dop)
 		__field(char, committed)
-		__field(char, low)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
 		__entry->dop = dop;
-		__entry->low = dop->dop_low;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ops %p low %d, caller %pS",
+	TP_printk("dev %d:%d ops %p caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dop,
-		  __entry->low,
 		  (char *)__entry->caller_ip)
 )
 #define DEFINE_DEFER_EVENT(name) \
@@ -2251,19 +2248,16 @@ DECLARE_EVENT_CLASS(xfs_defer_error_class,
 		__field(dev_t, dev)
 		__field(void *, dop)
 		__field(char, committed)
-		__field(char, low)
 		__field(int, error)
 	),
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
 		__entry->dop = dop;
-		__entry->low = dop->dop_low;
 		__entry->error = error;
 	),
-	TP_printk("dev %d:%d ops %p low %d err %d",
+	TP_printk("dev %d:%d ops %p err %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dop,
-		  __entry->low,
 		  __entry->error)
 )
 #define DEFINE_DEFER_ERROR_EVENT(name) \
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index dc79e3c1d3e8..7e493221160e 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -101,8 +101,6 @@ struct xfs_defer_ops {
 	/* relog these with each roll */
 	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
 	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
-
-	bool			dop_low;	/* alloc in low mode */
 };
 
 /*
-- 
cgit v1.2.3


From 488c919a5bec3be4b8613898de6958043edbb8d9 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:31 -0700
Subject: xfs: add missing defer ijoins for held inodes

Log items that require relogging during deferred operations
processing are explicitly joined to the associated dfops via the
xfs_defer_*join() helpers. These calls imply that the associated
object is "held" by the transaction such that when rolled, the item
can be immediately joined to a follow up transaction. For buffers,
this means the buffer remains locked and held after each roll. For
inodes, this means that the inode remains locked.

Failure to join a held item to the dfops structure means the
associated object pins the tail of the log while dfops processing
completes, because the item never relogs and is not unlocked or
released until deferred processing completes.

Currently, all buffers that are held in transactions (XFS_BLI_HOLD)
with deferred operations are explicitly joined to the dfops. This is
not the case for inodes, however, as various contexts defer
operations to transactions with held inodes without explicit joins
to the associated dfops (and thus not relogging).

While this is not a catastrophic problem, it is not ideal. Given
that we want to eventually relog such items automatically during
dfops processing, start by explicitly adding these missing
xfs_defer_ijoin() calls. A call is added everywhere an inode is
joined to a transaction without transferring lock ownership and
said transaction runs deferred operations.

All xfs_defer_ijoin() calls will eventually be replaced by automatic
dfops inode relogging. This patch essentially implements the
behavior change that would otherwise occur due to automatic inode
dfops relogging.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 1 +
 fs/xfs/xfs_bmap_util.c   | 1 +
 fs/xfs/xfs_inode.c       | 1 +
 fs/xfs/xfs_iomap.c       | 3 +++
 fs/xfs/xfs_reflink.c     | 1 +
 5 files changed, 7 insertions(+)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 8edf7522aaff..71687d805f79 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1119,6 +1119,7 @@ xfs_bmap_add_attrfork(
 			xfs_log_sb(tp);
 	}
 
+	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 412dc58ae54d..0c58a66b39e5 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -979,6 +979,7 @@ xfs_alloc_file_space(
 		/*
 		 * Complete the transaction
 		 */
+		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5fc1815c2b62..441c8593cfd7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1810,6 +1810,7 @@ xfs_inactive_ifree(
 	 * Just ignore errors at this point.  There is nothing we can do except
 	 * to try to keep going. Make sure it's not a silent error.
 	 */
+	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	if (error)
 		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 3282575e2df4..8093a01fcf9e 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -261,6 +261,7 @@ xfs_iomap_write_direct(
 	/*
 	 * Complete the transaction
 	 */
+	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;
@@ -763,6 +764,7 @@ xfs_iomap_write_allocate(
 			if (error)
 				goto trans_cancel;
 
+			xfs_defer_ijoin(tp->t_dfops, ip);
 			error = xfs_trans_commit(tp);
 			if (error)
 				goto error0;
@@ -882,6 +884,7 @@ xfs_iomap_write_unwritten(
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
+		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 9a0a56526266..e986fcf928e5 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -435,6 +435,7 @@ retry:
 	xfs_inode_set_cowblocks_tag(ip);
 
 	/* Finish up. */
+	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	if (error)
 		return error;
-- 
cgit v1.2.3


From 82ff27bc52a88cb5cc400bfa64e210d3ec8dfebd Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:32 -0700
Subject: xfs: automatic dfops buffer relogging

Buffers that are held across deferred operations are explicitly
joined to the dfops structure to ensure appropriate relogging.
While buffers are currently joined explicitly, we can detect the
conditions that require relogging at dfops finish time by inspecting
the transaction item list for held buffers.

Replace the xfs_defer_bjoin() infrastructure with such detection and
automatic relogging of held buffers. This eliminates the need for
the per-dfops buffer list, replaced by an on-stack variant in
xfs_defer_trans_roll().

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c  |  1 -
 fs/xfs/libxfs/xfs_defer.c | 58 +++++++++++++++++++++--------------------------
 fs/xfs/libxfs/xfs_defer.h |  1 -
 fs/xfs/xfs_dquot.c        |  1 -
 fs/xfs/xfs_trans.h        |  1 -
 5 files changed, 26 insertions(+), 36 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 3deb5cdadf08..227887bee00d 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -320,7 +320,6 @@ xfs_attr_set(
 		 * buffer and run into problems with the write verifier.
 		 */
 		xfs_trans_bhold(args.trans, leaf_bp);
-		xfs_defer_bjoin(args.trans->t_dfops, leaf_bp);
 		xfs_defer_ijoin(args.trans->t_dfops, dp);
 		error = xfs_defer_finish(&args.trans);
 		if (error)
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 64e1abc60edc..e9b7671d289a 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -14,6 +14,7 @@
 #include "xfs_mount.h"
 #include "xfs_defer.h"
 #include "xfs_trans.h"
+#include "xfs_buf_item.h"
 #include "xfs_trace.h"
 
 /*
@@ -228,6 +229,10 @@ xfs_defer_trans_roll(
 	struct xfs_trans		**tp)
 {
 	struct xfs_defer_ops		*dop = (*tp)->t_dfops;
+	struct xfs_buf_log_item		*bli;
+	struct xfs_log_item		*lip;
+	struct xfs_buf			*bplist[XFS_DEFER_OPS_NR_BUFS];
+	int				bpcount = 0;
 	int				i;
 	int				error;
 
@@ -235,9 +240,24 @@ xfs_defer_trans_roll(
 	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
 		xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE);
 
-	/* Hold the (previously bjoin'd) buffer locked across the roll. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++)
-		xfs_trans_dirty_buf(*tp, dop->dop_bufs[i]);
+	list_for_each_entry(lip, &(*tp)->t_items, li_trans) {
+		switch (lip->li_type) {
+		case XFS_LI_BUF:
+			bli = container_of(lip, struct xfs_buf_log_item,
+					   bli_item);
+			if (bli->bli_flags & XFS_BLI_HOLD) {
+				if (bpcount >= XFS_DEFER_OPS_NR_BUFS) {
+					ASSERT(0);
+					return -EFSCORRUPTED;
+				}
+				xfs_trans_dirty_buf(*tp, bli->bli_buf);
+				bplist[bpcount++] = bli->bli_buf;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	trace_xfs_defer_trans_roll((*tp)->t_mountp, dop, _RET_IP_);
 
@@ -255,9 +275,9 @@ xfs_defer_trans_roll(
 		xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0);
 
 	/* Rejoin the buffers and dirty them so the log moves forward. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS && dop->dop_bufs[i]; i++) {
-		xfs_trans_bjoin(*tp, dop->dop_bufs[i]);
-		xfs_trans_bhold(*tp, dop->dop_bufs[i]);
+	for (i = 0; i < bpcount; i++) {
+		xfs_trans_bjoin(*tp, bplist[i]);
+		xfs_trans_bhold(*tp, bplist[i]);
 	}
 
 	return error;
@@ -295,30 +315,6 @@ xfs_defer_ijoin(
 	return -EFSCORRUPTED;
 }
 
-/*
- * Add this buffer to the deferred op.  Each joined buffer is relogged
- * each time we roll the transaction.
- */
-int
-xfs_defer_bjoin(
-	struct xfs_defer_ops		*dop,
-	struct xfs_buf			*bp)
-{
-	int				i;
-
-	for (i = 0; i < XFS_DEFER_OPS_NR_BUFS; i++) {
-		if (dop->dop_bufs[i] == bp)
-			return 0;
-		else if (dop->dop_bufs[i] == NULL) {
-			dop->dop_bufs[i] = bp;
-			return 0;
-		}
-	}
-
-	ASSERT(0);
-	return -EFSCORRUPTED;
-}
-
 /*
  * Reset an already used dfops after finish.
  */
@@ -331,7 +327,6 @@ xfs_defer_reset(
 	ASSERT(!xfs_defer_has_unfinished_work(dop));
 
 	memset(dop->dop_inodes, 0, sizeof(dop->dop_inodes));
-	memset(dop->dop_bufs, 0, sizeof(dop->dop_bufs));
 
 	/*
 	 * Low mode state transfers across transaction rolls to mirror dfops
@@ -594,7 +589,6 @@ xfs_defer_move(
 	list_splice_init(&src->dop_pending, &dst->dop_pending);
 
 	memcpy(dst->dop_inodes, src->dop_inodes, sizeof(dst->dop_inodes));
-	memcpy(dst->dop_bufs, src->dop_bufs, sizeof(dst->dop_bufs));
 
 	/*
 	 * Low free space mode was historically controlled by a dfops field.
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 8908a2716774..4a8bb838adf2 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -43,7 +43,6 @@ void xfs_defer_cancel(struct xfs_trans *);
 void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
 int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
-int xfs_defer_bjoin(struct xfs_defer_ops *dop, struct xfs_buf *bp);
 void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index da5c55cec966..e1196854dbcd 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -362,7 +362,6 @@ xfs_dquot_disk_alloc(
 	 * manually or by committing the transaction.
 	 */
 	xfs_trans_bhold(tp, bp);
-	error = xfs_defer_bjoin(tp->t_dfops, bp);
 	if (error) {
 		xfs_trans_bhold_release(tp, bp);
 		xfs_trans_brelse(tp, bp);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 7e493221160e..581456c79197 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -100,7 +100,6 @@ struct xfs_defer_ops {
 
 	/* relog these with each roll */
 	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
-	struct xfs_buf		*dop_bufs[XFS_DEFER_OPS_NR_BUFS];
 };
 
 /*
-- 
cgit v1.2.3


From a8198666fb755e129c2fe92819774256ec26c79c Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:32 -0700
Subject: xfs: automatic dfops inode relogging

Inodes that are held across deferred operations are explicitly
joined to the dfops structure to ensure appropriate relogging.
While inodes are currently joined explicitly, we can detect the
conditions that require relogging at dfops finish time by inspecting
the transaction item list for inodes with ili_lock_flags == 0.

Replace the xfs_defer_ijoin() infrastructure with such detection and
automatic relogging of held inodes. This eliminates the need for the
per-dfops inode list, replaced by an on-stack variant in
xfs_defer_trans_roll().

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        |  9 -------
 fs/xfs/libxfs/xfs_attr_remote.c |  2 --
 fs/xfs/libxfs/xfs_bmap.c        |  8 ------
 fs/xfs/libxfs/xfs_defer.c       | 59 +++++++++++++++--------------------------
 fs/xfs/libxfs/xfs_defer.h       |  1 -
 fs/xfs/xfs_bmap_util.c          |  4 ---
 fs/xfs/xfs_inode.c              |  2 --
 fs/xfs/xfs_iomap.c              |  3 ---
 fs/xfs/xfs_reflink.c            |  4 ---
 fs/xfs/xfs_symlink.c            |  1 -
 fs/xfs/xfs_trans.h              |  3 ---
 11 files changed, 21 insertions(+), 75 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 227887bee00d..3190dfc21b60 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -320,7 +320,6 @@ xfs_attr_set(
 		 * buffer and run into problems with the write verifier.
 		 */
 		xfs_trans_bhold(args.trans, leaf_bp);
-		xfs_defer_ijoin(args.trans->t_dfops, dp);
 		error = xfs_defer_finish(&args.trans);
 		if (error)
 			goto out;
@@ -589,7 +588,6 @@ xfs_attr_leaf_addname(
 		error = xfs_attr3_leaf_to_node(args);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->trans->t_dfops, dp);
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
@@ -678,7 +676,6 @@ xfs_attr_leaf_addname(
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->trans->t_dfops, dp);
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
@@ -742,7 +739,6 @@ xfs_attr_leaf_removename(
 		/* bp is gone due to xfs_da_shrink_inode */
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->trans->t_dfops, dp);
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
@@ -869,7 +865,6 @@ restart:
 			error = xfs_attr3_leaf_to_node(args);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->trans->t_dfops, dp);
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
@@ -894,7 +889,6 @@ restart:
 		error = xfs_da3_split(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->trans->t_dfops, dp);
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
@@ -991,7 +985,6 @@ restart:
 			error = xfs_da3_join(state);
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->trans->t_dfops, dp);
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
@@ -1115,7 +1108,6 @@ xfs_attr_node_removename(
 		error = xfs_da3_join(state);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->trans->t_dfops, dp);
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
@@ -1147,7 +1139,6 @@ xfs_attr_node_removename(
 			/* bp is gone due to xfs_da_shrink_inode */
 			if (error)
 				goto out_defer_cancel;
-			xfs_defer_ijoin(args->trans->t_dfops, dp);
 			error = xfs_defer_finish(&args->trans);
 			if (error)
 				goto out_defer_cancel;
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 77ca38586913..f52552313773 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -486,7 +486,6 @@ xfs_attr_rmtval_set(
 				  &nmap);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->trans->t_dfops, dp);
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
@@ -627,7 +626,6 @@ xfs_attr_rmtval_remove(
 				    XFS_BMAPI_ATTRFORK, 1, &done);
 		if (error)
 			goto out_defer_cancel;
-		xfs_defer_ijoin(args->trans->t_dfops, args->dp);
 		error = xfs_defer_finish(&args->trans);
 		if (error)
 			goto out_defer_cancel;
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 71687d805f79..5cd490dc891a 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -1119,7 +1119,6 @@ xfs_bmap_add_attrfork(
 			xfs_log_sb(tp);
 	}
 
-	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -5987,7 +5986,6 @@ __xfs_bmap_add(
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
-	int				error;
 	struct xfs_bmap_intent		*bi;
 
 	trace_xfs_bmap_defer(mp,
@@ -6006,12 +6004,6 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
-	error = xfs_defer_ijoin(dfops, bi->bi_owner);
-	if (error) {
-		kmem_free(bi);
-		return error;
-	}
-
 	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
 	return 0;
 }
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index e9b7671d289a..1e7073252a5e 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -15,6 +15,8 @@
 #include "xfs_defer.h"
 #include "xfs_trans.h"
 #include "xfs_buf_item.h"
+#include "xfs_inode.h"
+#include "xfs_inode_item.h"
 #include "xfs_trace.h"
 
 /*
@@ -230,16 +232,14 @@ xfs_defer_trans_roll(
 {
 	struct xfs_defer_ops		*dop = (*tp)->t_dfops;
 	struct xfs_buf_log_item		*bli;
+	struct xfs_inode_log_item	*ili;
 	struct xfs_log_item		*lip;
 	struct xfs_buf			*bplist[XFS_DEFER_OPS_NR_BUFS];
-	int				bpcount = 0;
+	struct xfs_inode		*iplist[XFS_DEFER_OPS_NR_INODES];
+	int				bpcount = 0, ipcount = 0;
 	int				i;
 	int				error;
 
-	/* Log all the joined inodes. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
-		xfs_trans_log_inode(*tp, dop->dop_inodes[i], XFS_ILOG_CORE);
-
 	list_for_each_entry(lip, &(*tp)->t_items, li_trans) {
 		switch (lip->li_type) {
 		case XFS_LI_BUF:
@@ -254,6 +254,19 @@ xfs_defer_trans_roll(
 				bplist[bpcount++] = bli->bli_buf;
 			}
 			break;
+		case XFS_LI_INODE:
+			ili = container_of(lip, struct xfs_inode_log_item,
+					   ili_item);
+			if (ili->ili_lock_flags == 0) {
+				if (ipcount >= XFS_DEFER_OPS_NR_INODES) {
+					ASSERT(0);
+					return -EFSCORRUPTED;
+				}
+				xfs_trans_log_inode(*tp, ili->ili_inode,
+						    XFS_ILOG_CORE);
+				iplist[ipcount++] = ili->ili_inode;
+			}
+			break;
 		default:
 			break;
 		}
@@ -271,8 +284,8 @@ xfs_defer_trans_roll(
 	}
 
 	/* Rejoin the joined inodes. */
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES && dop->dop_inodes[i]; i++)
-		xfs_trans_ijoin(*tp, dop->dop_inodes[i], 0);
+	for (i = 0; i < ipcount; i++)
+		xfs_trans_ijoin(*tp, iplist[i], 0);
 
 	/* Rejoin the buffers and dirty them so the log moves forward. */
 	for (i = 0; i < bpcount; i++) {
@@ -291,30 +304,6 @@ xfs_defer_has_unfinished_work(
 	return !list_empty(&dop->dop_pending) || !list_empty(&dop->dop_intake);
 }
 
-/*
- * Add this inode to the deferred op.  Each joined inode is relogged
- * each time we roll the transaction.
- */
-int
-xfs_defer_ijoin(
-	struct xfs_defer_ops		*dop,
-	struct xfs_inode		*ip)
-{
-	int				i;
-
-	for (i = 0; i < XFS_DEFER_OPS_NR_INODES; i++) {
-		if (dop->dop_inodes[i] == ip)
-			return 0;
-		else if (dop->dop_inodes[i] == NULL) {
-			dop->dop_inodes[i] = ip;
-			return 0;
-		}
-	}
-
-	ASSERT(0);
-	return -EFSCORRUPTED;
-}
-
 /*
  * Reset an already used dfops after finish.
  */
@@ -322,11 +311,7 @@ static void
 xfs_defer_reset(
 	struct xfs_trans	*tp)
 {
-	struct xfs_defer_ops	*dop = tp->t_dfops;
-
-	ASSERT(!xfs_defer_has_unfinished_work(dop));
-
-	memset(dop->dop_inodes, 0, sizeof(dop->dop_inodes));
+	ASSERT(!xfs_defer_has_unfinished_work(tp->t_dfops));
 
 	/*
 	 * Low mode state transfers across transaction rolls to mirror dfops
@@ -588,8 +573,6 @@ xfs_defer_move(
 	list_splice_init(&src->dop_intake, &dst->dop_intake);
 	list_splice_init(&src->dop_pending, &dst->dop_pending);
 
-	memcpy(dst->dop_inodes, src->dop_inodes, sizeof(dst->dop_inodes));
-
 	/*
 	 * Low free space mode was historically controlled by a dfops field.
 	 * This meant that low mode state potentially carried across multiple
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 4a8bb838adf2..bf1e9f78561e 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -42,7 +42,6 @@ int xfs_defer_finish(struct xfs_trans **tp);
 void xfs_defer_cancel(struct xfs_trans *);
 void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
-int xfs_defer_ijoin(struct xfs_defer_ops *dop, struct xfs_inode *ip);
 void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 0c58a66b39e5..30ac1300dc49 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -979,7 +979,6 @@ xfs_alloc_file_space(
 		/*
 		 * Complete the transaction
 		 */
-		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
@@ -1037,8 +1036,6 @@ xfs_unmap_extent(
 	if (error)
 		goto out_trans_cancel;
 
-	xfs_defer_ijoin(tp->t_dfops, ip);
-
 	error = xfs_trans_commit(tp);
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -1624,7 +1621,6 @@ xfs_swap_extent_rmap(
 			if (error)
 				goto out_defer;
 
-			xfs_defer_ijoin(tp->t_dfops, ip);
 			error = xfs_defer_finish(tpp);
 			tp = *tpp;
 			if (error)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 441c8593cfd7..7bb46a0eecfc 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1569,7 +1569,6 @@ xfs_itruncate_extents_flags(
 		 * Duplicate the transaction that has the permanent
 		 * reservation and commit the old transaction.
 		 */
-		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_bmap_cancel;
@@ -1810,7 +1809,6 @@ xfs_inactive_ifree(
 	 * Just ignore errors at this point.  There is nothing we can do except
 	 * to try to keep going. Make sure it's not a silent error.
 	 */
-	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	if (error)
 		xfs_notice(mp, "%s: xfs_trans_commit returned error %d",
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 8093a01fcf9e..3282575e2df4 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -261,7 +261,6 @@ xfs_iomap_write_direct(
 	/*
 	 * Complete the transaction
 	 */
-	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;
@@ -764,7 +763,6 @@ xfs_iomap_write_allocate(
 			if (error)
 				goto trans_cancel;
 
-			xfs_defer_ijoin(tp->t_dfops, ip);
 			error = xfs_trans_commit(tp);
 			if (error)
 				goto error0;
@@ -884,7 +882,6 @@ xfs_iomap_write_unwritten(
 			xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 		}
 
-		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_trans_commit(tp);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index e986fcf928e5..dce8ba8ab681 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -435,7 +435,6 @@ retry:
 	xfs_inode_set_cowblocks_tag(ip);
 
 	/* Finish up. */
-	xfs_defer_ijoin(tp->t_dfops, ip);
 	error = xfs_trans_commit(tp);
 	if (error)
 		return error;
@@ -518,7 +517,6 @@ xfs_reflink_cancel_cow_blocks(
 					NULL);
 
 			/* Roll the transaction */
-			xfs_defer_ijoin((*tpp)->t_dfops, ip);
 			error = xfs_defer_finish(tpp);
 			if (error) {
 				xfs_defer_cancel(*tpp);
@@ -716,7 +714,6 @@ xfs_reflink_end_cow(
 		/* Remove the mapping from the CoW fork. */
 		xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
 
-		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_cancel;
@@ -1077,7 +1074,6 @@ xfs_reflink_remap_extent(
 
 next_extent:
 		/* Process all the deferred stuff. */
-		xfs_defer_ijoin(tp->t_dfops, ip);
 		error = xfs_defer_finish(&tp);
 		if (error)
 			goto out_cancel;
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index 2bfe7fbbedb2..a3e98c64b6e3 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -454,7 +454,6 @@ xfs_inactive_symlink_rmt(
 	 * Commit the transaction. This first logs the EFI and the inode, then
 	 * rolls and commits the transaction that frees the extents.
 	 */
-	xfs_defer_ijoin(tp->t_dfops, ip);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 	error = xfs_trans_commit(tp);
 	if (error) {
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 581456c79197..8665d45b82c6 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -97,9 +97,6 @@ void	xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
 struct xfs_defer_ops {
 	struct list_head	dop_intake;	/* unlogged pending work */
 	struct list_head	dop_pending;	/* logged pending work */
-
-	/* relog these with each roll */
-	struct xfs_inode	*dop_inodes[XFS_DEFER_OPS_NR_INODES];
 };
 
 /*
-- 
cgit v1.2.3


From 7dbddbaccd189e63c39c9e22c728c4548b9893bb Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:32 -0700
Subject: xfs: drop dop param from xfs_defer_op_type ->finish_item() callback

The dfops infrastructure ->finish_item() callback passes the
transaction and dfops as separate parameters. Since dfops is always
part of a transaction, the latter parameter is no longer necessary.
Remove it from the various callbacks.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c     |  2 --
 fs/xfs/libxfs/xfs_bmap.h     |  6 +++---
 fs/xfs/libxfs/xfs_defer.c    |  2 +-
 fs/xfs/libxfs/xfs_defer.h    |  4 ++--
 fs/xfs/libxfs/xfs_refcount.c |  2 +-
 fs/xfs/libxfs/xfs_refcount.h |  7 +++----
 fs/xfs/xfs_bmap_item.c       |  5 ++---
 fs/xfs/xfs_refcount_item.c   |  4 ++--
 fs/xfs/xfs_trans.h           | 10 +++++-----
 fs/xfs/xfs_trans_bmap.c      |  6 ++----
 fs/xfs/xfs_trans_extfree.c   |  2 --
 fs/xfs/xfs_trans_refcount.c  |  6 ++----
 fs/xfs/xfs_trans_rmap.c      |  1 -
 13 files changed, 23 insertions(+), 34 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 5cd490dc891a..d20f541b7061 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -6045,7 +6045,6 @@ xfs_bmap_unmap_extent(
 int
 xfs_bmap_finish_one(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dfops,
 	struct xfs_inode		*ip,
 	enum xfs_bmap_intent_type	type,
 	int				whichfork,
@@ -6072,7 +6071,6 @@ xfs_bmap_finish_one(
 
 	switch (type) {
 	case XFS_BMAP_MAP:
-		ASSERT(dfops == tp->t_dfops);
 		error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
 				startblock, 0);
 		*blockcount = 0;
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 2e8555c1229a..9165a878edcd 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -252,9 +252,9 @@ struct xfs_bmap_intent {
 	struct xfs_bmbt_irec			bi_bmap;
 };
 
-int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, enum xfs_bmap_intent_type type,
-		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
+int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_inode *ip,
+		enum xfs_bmap_intent_type type, int whichfork,
+		xfs_fileoff_t startoff, xfs_fsblock_t startblock,
 		xfs_filblks_t *blockcount, xfs_exntst_t state);
 int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 1e7073252a5e..66ef9341813b 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -371,7 +371,7 @@ xfs_defer_finish_noroll(
 		list_for_each_safe(li, n, &dfp->dfp_work) {
 			list_del(li);
 			dfp->dfp_count--;
-			error = dfp->dfp_type->finish_item(*tp, dop, li,
+			error = dfp->dfp_type->finish_item(*tp, li,
 					dfp->dfp_done, &state);
 			if (error == -EAGAIN) {
 				/*
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index bf1e9f78561e..0de7504e5651 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -50,8 +50,8 @@ struct xfs_defer_op_type {
 	unsigned int		max_items;
 	void (*abort_intent)(void *);
 	void *(*create_done)(struct xfs_trans *, void *, unsigned int);
-	int (*finish_item)(struct xfs_trans *, struct xfs_defer_ops *,
-			struct list_head *, void *, void **);
+	int (*finish_item)(struct xfs_trans *, struct list_head *, void *,
+			void **);
 	void (*finish_cleanup)(struct xfs_trans *, void *, int);
 	void (*cancel_item)(struct list_head *);
 	int (*diff_items)(void *, struct list_head *, struct list_head *);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 4cbc2efb099e..86f297ca90cd 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -1082,7 +1082,6 @@ xfs_refcount_finish_one_cleanup(
 int
 xfs_refcount_finish_one(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dfops,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount,
@@ -1091,6 +1090,7 @@ xfs_refcount_finish_one(
 	struct xfs_btree_cur		**pcur)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_defer_ops		*dfops = tp->t_dfops;
 	struct xfs_btree_cur		*rcur;
 	struct xfs_buf			*agbp = NULL;
 	int				error = 0;
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 5fef74412727..3b72c6dbf6ad 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -37,10 +37,9 @@ extern int xfs_refcount_decrease_extent(struct xfs_mount *mp,
 extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
 extern int xfs_refcount_finish_one(struct xfs_trans *tp,
-		struct xfs_defer_ops *dfops, enum xfs_refcount_intent_type type,
-		xfs_fsblock_t startblock, xfs_extlen_t blockcount,
-		xfs_fsblock_t *new_fsb, xfs_extlen_t *new_len,
-		struct xfs_btree_cur **pcur);
+		enum xfs_refcount_intent_type type, xfs_fsblock_t startblock,
+		xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb,
+		xfs_extlen_t *new_len, struct xfs_btree_cur **pcur);
 
 extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur,
 		xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno,
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index b8a6be036cd7..e828e0b51814 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -475,9 +475,8 @@ xfs_bui_recover(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	count = bmap->me_len;
-	error = xfs_trans_log_finish_bmap_update(tp, budp, tp->t_dfops, type,
-			ip, whichfork, bmap->me_startoff,
-			bmap->me_startblock, &count, state);
+	error = xfs_trans_log_finish_bmap_update(tp, budp, type, ip, whichfork,
+			bmap->me_startoff, bmap->me_startblock, &count, state);
 	if (error)
 		goto err_inode;
 
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 4a417daae781..43c4ac374cba 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -479,8 +479,8 @@ xfs_cui_recover(
 			new_len = refc->pe_len;
 		} else
 			error = xfs_trans_log_finish_refcount_update(tp, cudp,
-				tp->t_dfops, type, refc->pe_startblock,
-				refc->pe_len, &new_fsb, &new_len, &rcur);
+				type, refc->pe_startblock, refc->pe_len,
+				&new_fsb, &new_len, &rcur);
 		if (error)
 			goto abort_error;
 
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 8665d45b82c6..299656dbf324 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -268,7 +268,7 @@ void xfs_refcount_update_init_defer_op(void);
 struct xfs_cud_log_item *xfs_trans_get_cud(struct xfs_trans *tp,
 		struct xfs_cui_log_item *cuip);
 int xfs_trans_log_finish_refcount_update(struct xfs_trans *tp,
-		struct xfs_cud_log_item *cudp, struct xfs_defer_ops *dfops,
+		struct xfs_cud_log_item *cudp,
 		enum xfs_refcount_intent_type type, xfs_fsblock_t startblock,
 		xfs_extlen_t blockcount, xfs_fsblock_t *new_fsb,
 		xfs_extlen_t *new_len, struct xfs_btree_cur **pcur);
@@ -280,9 +280,9 @@ void xfs_bmap_update_init_defer_op(void);
 struct xfs_bud_log_item *xfs_trans_get_bud(struct xfs_trans *tp,
 		struct xfs_bui_log_item *buip);
 int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp,
-		struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops,
-		enum xfs_bmap_intent_type type, struct xfs_inode *ip,
-		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t *blockcount, xfs_exntst_t state);
+		struct xfs_bud_log_item *rudp, enum xfs_bmap_intent_type type,
+		struct xfs_inode *ip, int whichfork, xfs_fileoff_t startoff,
+		xfs_fsblock_t startblock, xfs_filblks_t *blockcount,
+		xfs_exntst_t state);
 
 #endif	/* __XFS_TRANS_H__ */
diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c
index a15a5cd867f9..741c558b2179 100644
--- a/fs/xfs/xfs_trans_bmap.c
+++ b/fs/xfs/xfs_trans_bmap.c
@@ -43,7 +43,6 @@ int
 xfs_trans_log_finish_bmap_update(
 	struct xfs_trans		*tp,
 	struct xfs_bud_log_item		*budp,
-	struct xfs_defer_ops		*dop,
 	enum xfs_bmap_intent_type	type,
 	struct xfs_inode		*ip,
 	int				whichfork,
@@ -54,7 +53,7 @@ xfs_trans_log_finish_bmap_update(
 {
 	int				error;
 
-	error = xfs_bmap_finish_one(tp, dop, ip, type, whichfork, startoff,
+	error = xfs_bmap_finish_one(tp, ip, type, whichfork, startoff,
 			startblock, blockcount, state);
 
 	/*
@@ -176,7 +175,6 @@ xfs_bmap_update_create_done(
 STATIC int
 xfs_bmap_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -187,7 +185,7 @@ xfs_bmap_update_finish_item(
 
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
 	count = bmap->bi_bmap.br_blockcount;
-	error = xfs_trans_log_finish_bmap_update(tp, done_item, dop,
+	error = xfs_trans_log_finish_bmap_update(tp, done_item,
 			bmap->bi_type,
 			bmap->bi_owner, bmap->bi_whichfork,
 			bmap->bi_bmap.br_startoff,
diff --git a/fs/xfs/xfs_trans_extfree.c b/fs/xfs/xfs_trans_extfree.c
index bd66c76f55e6..855c0b651fd4 100644
--- a/fs/xfs/xfs_trans_extfree.c
+++ b/fs/xfs/xfs_trans_extfree.c
@@ -171,7 +171,6 @@ xfs_extent_free_create_done(
 STATIC int
 xfs_extent_free_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -226,7 +225,6 @@ static const struct xfs_defer_op_type xfs_extent_free_defer_type = {
 STATIC int
 xfs_agfl_free_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
diff --git a/fs/xfs/xfs_trans_refcount.c b/fs/xfs/xfs_trans_refcount.c
index 46dd4fca8aa7..523c55663954 100644
--- a/fs/xfs/xfs_trans_refcount.c
+++ b/fs/xfs/xfs_trans_refcount.c
@@ -42,7 +42,6 @@ int
 xfs_trans_log_finish_refcount_update(
 	struct xfs_trans		*tp,
 	struct xfs_cud_log_item		*cudp,
-	struct xfs_defer_ops		*dop,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount,
@@ -52,7 +51,7 @@ xfs_trans_log_finish_refcount_update(
 {
 	int				error;
 
-	error = xfs_refcount_finish_one(tp, dop, type, startblock,
+	error = xfs_refcount_finish_one(tp, type, startblock,
 			blockcount, new_fsb, new_len, pcur);
 
 	/*
@@ -169,7 +168,6 @@ xfs_refcount_update_create_done(
 STATIC int
 xfs_refcount_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
@@ -180,7 +178,7 @@ xfs_refcount_update_finish_item(
 	int				error;
 
 	refc = container_of(item, struct xfs_refcount_intent, ri_list);
-	error = xfs_trans_log_finish_refcount_update(tp, done_item, dop,
+	error = xfs_trans_log_finish_refcount_update(tp, done_item,
 			refc->ri_type,
 			refc->ri_startblock,
 			refc->ri_blockcount,
diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c
index 726d8e2c0558..05b00e40251f 100644
--- a/fs/xfs/xfs_trans_rmap.c
+++ b/fs/xfs/xfs_trans_rmap.c
@@ -193,7 +193,6 @@ xfs_rmap_update_create_done(
 STATIC int
 xfs_rmap_update_finish_item(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	struct list_head		*item,
 	void				*done_item,
 	void				**state)
-- 
cgit v1.2.3


From 60f31a609ed3d28791acb2bc24188cb7e2259176 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:33 -0700
Subject: xfs: clean out superfluous dfops dop params/vars

The dfops code still passes around the xfs_defer_ops pointer
superfluously in a few places. Clean this up wherever the
transaction will suffice.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 43 +++++++++++++++++++++----------------------
 fs/xfs/libxfs/xfs_defer.h |  2 +-
 fs/xfs/xfs_trans.c        |  2 +-
 3 files changed, 23 insertions(+), 24 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 66ef9341813b..7079f534c735 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -181,9 +181,9 @@ static const struct xfs_defer_op_type *defer_op_types[XFS_DEFER_OPS_TYPE_MAX];
  */
 STATIC void
 xfs_defer_intake_work(
-	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop)
+	struct xfs_trans		*tp)
 {
+	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct list_head		*li;
 	struct xfs_defer_pending	*dfp;
 
@@ -204,9 +204,9 @@ xfs_defer_intake_work(
 STATIC void
 xfs_defer_trans_abort(
 	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop,
 	int				error)
 {
+	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct xfs_defer_pending	*dfp;
 
 	trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);
@@ -230,7 +230,6 @@ STATIC int
 xfs_defer_trans_roll(
 	struct xfs_trans		**tp)
 {
-	struct xfs_defer_ops		*dop = (*tp)->t_dfops;
 	struct xfs_buf_log_item		*bli;
 	struct xfs_inode_log_item	*ili;
 	struct xfs_log_item		*lip;
@@ -272,14 +271,14 @@ xfs_defer_trans_roll(
 		}
 	}
 
-	trace_xfs_defer_trans_roll((*tp)->t_mountp, dop, _RET_IP_);
+	trace_xfs_defer_trans_roll((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);
 
 	/* Roll the transaction. */
 	error = xfs_trans_roll(tp);
-	dop = (*tp)->t_dfops;
 	if (error) {
-		trace_xfs_defer_trans_roll_error((*tp)->t_mountp, dop, error);
-		xfs_defer_trans_abort(*tp, dop, error);
+		trace_xfs_defer_trans_roll_error((*tp)->t_mountp,
+						 (*tp)->t_dfops, error);
+		xfs_defer_trans_abort(*tp,  error);
 		return error;
 	}
 
@@ -299,9 +298,10 @@ xfs_defer_trans_roll(
 /* Do we have any work items to finish? */
 bool
 xfs_defer_has_unfinished_work(
-	struct xfs_defer_ops		*dop)
+	struct xfs_trans		*tp)
 {
-	return !list_empty(&dop->dop_pending) || !list_empty(&dop->dop_intake);
+	return !list_empty(&tp->t_dfops->dop_pending) ||
+		!list_empty(&tp->t_dfops->dop_intake);
 }
 
 /*
@@ -311,7 +311,7 @@ static void
 xfs_defer_reset(
 	struct xfs_trans	*tp)
 {
-	ASSERT(!xfs_defer_has_unfinished_work(tp->t_dfops));
+	ASSERT(!xfs_defer_has_unfinished_work(tp));
 
 	/*
 	 * Low mode state transfers across transaction rolls to mirror dfops
@@ -332,7 +332,6 @@ int
 xfs_defer_finish_noroll(
 	struct xfs_trans		**tp)
 {
-	struct xfs_defer_ops		*dop = (*tp)->t_dfops;
 	struct xfs_defer_pending	*dfp;
 	struct list_head		*li;
 	struct list_head		*n;
@@ -342,24 +341,22 @@ xfs_defer_finish_noroll(
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
-	trace_xfs_defer_finish((*tp)->t_mountp, dop, _RET_IP_);
+	trace_xfs_defer_finish((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);
 
 	/* Until we run out of pending work to finish... */
-	while (xfs_defer_has_unfinished_work(dop)) {
+	while (xfs_defer_has_unfinished_work(*tp)) {
 		/* Log intents for work items sitting in the intake. */
-		xfs_defer_intake_work(*tp, dop);
+		xfs_defer_intake_work(*tp);
 
 		/*
-		 * Roll the transaction and update dop in case dfops was
-		 * embedded in the transaction.
+		 * Roll the transaction.
 		 */
 		error = xfs_defer_trans_roll(tp);
 		if (error)
 			goto out;
-		dop = (*tp)->t_dfops;
 
 		/* Log an intent-done item for the first pending item. */
-		dfp = list_first_entry(&dop->dop_pending,
+		dfp = list_first_entry(&(*tp)->t_dfops->dop_pending,
 				struct xfs_defer_pending, dfp_list);
 		trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp);
 		dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent,
@@ -390,7 +387,7 @@ xfs_defer_finish_noroll(
 				 */
 				if (cleanup_fn)
 					cleanup_fn(*tp, state, error);
-				xfs_defer_trans_abort(*tp, dop, error);
+				xfs_defer_trans_abort(*tp, error);
 				goto out;
 			}
 		}
@@ -420,9 +417,11 @@ xfs_defer_finish_noroll(
 
 out:
 	if (error)
-		trace_xfs_defer_finish_error((*tp)->t_mountp, dop, error);
+		trace_xfs_defer_finish_error((*tp)->t_mountp, (*tp)->t_dfops,
+					     error);
 	 else
-		trace_xfs_defer_finish_done((*tp)->t_mountp, dop, _RET_IP_);
+		trace_xfs_defer_finish_done((*tp)->t_mountp, (*tp)->t_dfops,
+					    _RET_IP_);
 
 	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index 0de7504e5651..f051c8056141 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -41,7 +41,7 @@ int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
 void xfs_defer_cancel(struct xfs_trans *);
 void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
-bool xfs_defer_has_unfinished_work(struct xfs_defer_ops *dop);
+bool xfs_defer_has_unfinished_work(struct xfs_trans *tp);
 void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index ae3c875a14e5..b0130b21f4de 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -929,7 +929,7 @@ __xfs_trans_commit(
 	 * Finish deferred items on final commit. Only permanent transactions
 	 * should ever have deferred ops.
 	 */
-	WARN_ON_ONCE(xfs_defer_has_unfinished_work(tp->t_dfops) &&
+	WARN_ON_ONCE(xfs_defer_has_unfinished_work(tp) &&
 		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
 	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
 		error = xfs_defer_finish_noroll(&tp);
-- 
cgit v1.2.3


From 9b1f4e9831df29776031e86e112e68784f1fc079 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:33 -0700
Subject: xfs: cancel dfops on xfs_defer_finish() error

The current semantics of xfs_defer_finish() require the caller to
call xfs_defer_cancel() on error. This is slightly inconsistent with
transaction commit error handling where a failed commit cleans up
the transaction before returning.

More significantly, the only requirement for exposure of
->dop_pending outside of xfs_defer_finish() is so that
xfs_defer_cancel() can drain it on error. Since the only recourse of
xfs_defer_finish() errors is cancellation, mirror the transaction
logic and cancel remaining dfops before returning from
xfs_defer_finish() with an error.

Beside simplifying xfs_defer_finish() semantics, this ensures that
xfs_defer_finish() always returns with an empty ->dop_pending and
thus facilitates removal of the list from xfs_defer_ops.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_attr.c        | 16 ++++++++--------
 fs/xfs/libxfs/xfs_attr_remote.c |  4 ++--
 fs/xfs/libxfs/xfs_defer.c       | 11 ++++++-----
 fs/xfs/xfs_bmap_util.c          |  2 +-
 fs/xfs/xfs_dquot.c              |  2 +-
 fs/xfs/xfs_inode.c              |  2 +-
 fs/xfs/xfs_reflink.c            |  4 +---
 fs/xfs/xfs_trans.c              |  4 +---
 8 files changed, 21 insertions(+), 24 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 3190dfc21b60..1e671d4eb6fa 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -590,7 +590,7 @@ xfs_attr_leaf_addname(
 			goto out_defer_cancel;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		/*
 		 * Commit the current trans (including the inode) and start
@@ -678,7 +678,7 @@ xfs_attr_leaf_addname(
 				goto out_defer_cancel;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				return error;
 		}
 
 		/*
@@ -741,7 +741,7 @@ xfs_attr_leaf_removename(
 			goto out_defer_cancel;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 	}
 	return 0;
 out_defer_cancel:
@@ -867,7 +867,7 @@ restart:
 				goto out_defer_cancel;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 
 			/*
 			 * Commit the node conversion and start the next
@@ -891,7 +891,7 @@ restart:
 			goto out_defer_cancel;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 	} else {
 		/*
 		 * Addition succeeded, update Btree hashvals.
@@ -987,7 +987,7 @@ restart:
 				goto out_defer_cancel;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 		}
 
 		/*
@@ -1110,7 +1110,7 @@ xfs_attr_node_removename(
 			goto out_defer_cancel;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			goto out;
 		/*
 		 * Commit the Btree join operation and start a new trans.
 		 */
@@ -1141,7 +1141,7 @@ xfs_attr_node_removename(
 				goto out_defer_cancel;
 			error = xfs_defer_finish(&args->trans);
 			if (error)
-				goto out_defer_cancel;
+				goto out;
 		} else
 			xfs_trans_brelse(args->trans, bp);
 	}
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index f52552313773..af094063e402 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -488,7 +488,7 @@ xfs_attr_rmtval_set(
 			goto out_defer_cancel;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		ASSERT(nmap == 1);
 		ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
@@ -628,7 +628,7 @@ xfs_attr_rmtval_remove(
 			goto out_defer_cancel;
 		error = xfs_defer_finish(&args->trans);
 		if (error)
-			goto out_defer_cancel;
+			return error;
 
 		/*
 		 * Close out trans and start the next one in the chain.
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 7079f534c735..b656a399cd71 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -416,14 +416,15 @@ xfs_defer_finish_noroll(
 	}
 
 out:
-	if (error)
+	if (error) {
 		trace_xfs_defer_finish_error((*tp)->t_mountp, (*tp)->t_dfops,
 					     error);
-	 else
-		trace_xfs_defer_finish_done((*tp)->t_mountp, (*tp)->t_dfops,
-					    _RET_IP_);
+		xfs_defer_cancel(*tp);
+		return error;
+	}
 
-	return error;
+	trace_xfs_defer_finish_done((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);
+	return 0;
 }
 
 int
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 30ac1300dc49..d9dad399440a 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1624,7 +1624,7 @@ xfs_swap_extent_rmap(
 			error = xfs_defer_finish(tpp);
 			tp = *tpp;
 			if (error)
-				goto out_defer;
+				goto out;
 
 			tirec.br_startoff += rlen;
 			if (tirec.br_startblock != HOLESTARTBLOCK &&
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index e1196854dbcd..70a76ac41f01 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -371,7 +371,7 @@ xfs_dquot_disk_alloc(
 	tp = *tpp;
 	if (error) {
 		xfs_buf_relse(bp);
-		goto error1;
+		goto error0;
 	}
 	*bpp = bp;
 	return 0;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 7bb46a0eecfc..d957a46dc1cb 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1571,7 +1571,7 @@ xfs_itruncate_extents_flags(
 		 */
 		error = xfs_defer_finish(&tp);
 		if (error)
-			goto out_bmap_cancel;
+			goto out;
 
 		error = xfs_trans_roll_inode(&tp, ip);
 		if (error)
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index dce8ba8ab681..2ec562d75494 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -518,10 +518,8 @@ xfs_reflink_cancel_cow_blocks(
 
 			/* Roll the transaction */
 			error = xfs_defer_finish(tpp);
-			if (error) {
-				xfs_defer_cancel(*tpp);
+			if (error)
 				break;
-			}
 
 			/* Remove the mapping from the CoW fork. */
 			xfs_bmap_del_extent_cow(ip, &icur, &got, &del);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index b0130b21f4de..b050663c2a70 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -933,10 +933,8 @@ __xfs_trans_commit(
 		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
 	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
 		error = xfs_defer_finish_noroll(&tp);
-		if (error) {
-			xfs_defer_cancel(tp);
+		if (error)
 			goto out_unreserve;
-		}
 	}
 
 	/*
-- 
cgit v1.2.3


From 1ae093cbea3d1ef04e1344b9e3996a9e1763a91b Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:34 -0700
Subject: xfs: replace xfs_defer_ops ->dop_pending with on-stack list

The xfs_defer_ops ->dop_pending list is used to track active
deferred operations once intents are logged. These items must be
aborted in the event of an error. The list is populated as intents
are logged and items are removed as they complete (or are aborted).

Now that xfs_defer_finish() cancels on error, there is no need to
ever access ->dop_pending outside of xfs_defer_finish(). The list is
only ever populated after xfs_defer_finish() begins and is either
completed or cancelled before it returns.

Remove ->dop_pending from xfs_defer_ops and replace it with a local
list in the xfs_defer_finish() path. Pass the local list to the
various helpers now that it is not accessible via dfops. Note that
we have to check for NULL in the abort case as the final tx roll
occurs outside of the scope of the new local list (once the dfops
has completed and thus drained the list).

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_defer.c | 146 +++++++++++++++++++++-------------------------
 fs/xfs/libxfs/xfs_defer.h |   1 -
 fs/xfs/xfs_trace.h        |   5 +-
 fs/xfs/xfs_trans.c        |   2 +-
 fs/xfs/xfs_trans.h        |   1 -
 5 files changed, 71 insertions(+), 84 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index b656a399cd71..1cbddcf539da 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -180,7 +180,7 @@ static const struct xfs_defer_op_type *defer_op_types[XFS_DEFER_OPS_TYPE_MAX];
  * the pending list.
  */
 STATIC void
-xfs_defer_intake_work(
+xfs_defer_create_intents(
 	struct xfs_trans		*tp)
 {
 	struct xfs_defer_ops		*dop = tp->t_dfops;
@@ -190,21 +190,19 @@ xfs_defer_intake_work(
 	list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
 		dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
 				dfp->dfp_count);
-		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
+		trace_xfs_defer_create_intent(tp->t_mountp, dfp);
 		list_sort(tp->t_mountp, &dfp->dfp_work,
 				dfp->dfp_type->diff_items);
 		list_for_each(li, &dfp->dfp_work)
 			dfp->dfp_type->log_item(tp, dfp->dfp_intent, li);
 	}
-
-	list_splice_tail_init(&dop->dop_intake, &dop->dop_pending);
 }
 
 /* Abort all the intents that were committed. */
 STATIC void
 xfs_defer_trans_abort(
 	struct xfs_trans		*tp,
-	int				error)
+	struct list_head		*dop_pending)
 {
 	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct xfs_defer_pending	*dfp;
@@ -212,24 +210,21 @@ xfs_defer_trans_abort(
 	trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);
 
 	/* Abort intent items that don't have a done item. */
-	list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
+	list_for_each_entry(dfp, dop_pending, dfp_list) {
 		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
 		if (dfp->dfp_intent && !dfp->dfp_done) {
 			dfp->dfp_type->abort_intent(dfp->dfp_intent);
 			dfp->dfp_intent = NULL;
 		}
 	}
-
-	/* Shut down FS. */
-	xfs_force_shutdown(tp->t_mountp, (error == -EFSCORRUPTED) ?
-			SHUTDOWN_CORRUPT_INCORE : SHUTDOWN_META_IO_ERROR);
 }
 
 /* Roll a transaction so we can do some deferred op processing. */
 STATIC int
 xfs_defer_trans_roll(
-	struct xfs_trans		**tp)
+	struct xfs_trans		**tpp)
 {
+	struct xfs_trans		*tp = *tpp;
 	struct xfs_buf_log_item		*bli;
 	struct xfs_inode_log_item	*ili;
 	struct xfs_log_item		*lip;
@@ -239,7 +234,7 @@ xfs_defer_trans_roll(
 	int				i;
 	int				error;
 
-	list_for_each_entry(lip, &(*tp)->t_items, li_trans) {
+	list_for_each_entry(lip, &tp->t_items, li_trans) {
 		switch (lip->li_type) {
 		case XFS_LI_BUF:
 			bli = container_of(lip, struct xfs_buf_log_item,
@@ -249,7 +244,7 @@ xfs_defer_trans_roll(
 					ASSERT(0);
 					return -EFSCORRUPTED;
 				}
-				xfs_trans_dirty_buf(*tp, bli->bli_buf);
+				xfs_trans_dirty_buf(tp, bli->bli_buf);
 				bplist[bpcount++] = bli->bli_buf;
 			}
 			break;
@@ -261,7 +256,7 @@ xfs_defer_trans_roll(
 					ASSERT(0);
 					return -EFSCORRUPTED;
 				}
-				xfs_trans_log_inode(*tp, ili->ili_inode,
+				xfs_trans_log_inode(tp, ili->ili_inode,
 						    XFS_ILOG_CORE);
 				iplist[ipcount++] = ili->ili_inode;
 			}
@@ -271,39 +266,30 @@ xfs_defer_trans_roll(
 		}
 	}
 
-	trace_xfs_defer_trans_roll((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);
+	trace_xfs_defer_trans_roll(tp->t_mountp, tp->t_dfops, _RET_IP_);
 
 	/* Roll the transaction. */
-	error = xfs_trans_roll(tp);
+	error = xfs_trans_roll(tpp);
+	tp = *tpp;
 	if (error) {
-		trace_xfs_defer_trans_roll_error((*tp)->t_mountp,
-						 (*tp)->t_dfops, error);
-		xfs_defer_trans_abort(*tp,  error);
+		trace_xfs_defer_trans_roll_error(tp->t_mountp,
+						 tp->t_dfops, error);
 		return error;
 	}
 
 	/* Rejoin the joined inodes. */
 	for (i = 0; i < ipcount; i++)
-		xfs_trans_ijoin(*tp, iplist[i], 0);
+		xfs_trans_ijoin(tp, iplist[i], 0);
 
 	/* Rejoin the buffers and dirty them so the log moves forward. */
 	for (i = 0; i < bpcount; i++) {
-		xfs_trans_bjoin(*tp, bplist[i]);
-		xfs_trans_bhold(*tp, bplist[i]);
+		xfs_trans_bjoin(tp, bplist[i]);
+		xfs_trans_bhold(tp, bplist[i]);
 	}
 
 	return error;
 }
 
-/* Do we have any work items to finish? */
-bool
-xfs_defer_has_unfinished_work(
-	struct xfs_trans		*tp)
-{
-	return !list_empty(&tp->t_dfops->dop_pending) ||
-		!list_empty(&tp->t_dfops->dop_intake);
-}
-
 /*
  * Reset an already used dfops after finish.
  */
@@ -311,7 +297,7 @@ static void
 xfs_defer_reset(
 	struct xfs_trans	*tp)
 {
-	ASSERT(!xfs_defer_has_unfinished_work(tp));
+	ASSERT(list_empty(&tp->t_dfops->dop_intake));
 
 	/*
 	 * Low mode state transfers across transaction rolls to mirror dfops
@@ -320,6 +306,36 @@ xfs_defer_reset(
 	tp->t_flags &= ~XFS_TRANS_LOWMODE;
 }
 
+/*
+ * Free up any items left in the list.
+ */
+static void
+xfs_defer_cancel_list(
+	struct xfs_mount		*mp,
+	struct list_head		*dop_list)
+{
+	struct xfs_defer_pending	*dfp;
+	struct xfs_defer_pending	*pli;
+	struct list_head		*pwi;
+	struct list_head		*n;
+
+	/*
+	 * Free the pending items.  Caller should already have arranged
+	 * for the intent items to be released.
+	 */
+	list_for_each_entry_safe(dfp, pli, dop_list, dfp_list) {
+		trace_xfs_defer_cancel_list(mp, dfp);
+		list_del(&dfp->dfp_list);
+		list_for_each_safe(pwi, n, &dfp->dfp_work) {
+			list_del(pwi);
+			dfp->dfp_count--;
+			dfp->dfp_type->cancel_item(pwi);
+		}
+		ASSERT(dfp->dfp_count == 0);
+		kmem_free(dfp);
+	}
+}
+
 /*
  * Finish all the pending work.  This involves logging intent items for
  * any work items that wandered in since the last transaction roll (if
@@ -338,15 +354,19 @@ xfs_defer_finish_noroll(
 	void				*state;
 	int				error = 0;
 	void				(*cleanup_fn)(struct xfs_trans *, void *, int);
+	LIST_HEAD(dop_pending);
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
 	trace_xfs_defer_finish((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);
 
 	/* Until we run out of pending work to finish... */
-	while (xfs_defer_has_unfinished_work(*tp)) {
-		/* Log intents for work items sitting in the intake. */
-		xfs_defer_intake_work(*tp);
+	while (!list_empty(&dop_pending) ||
+	       !list_empty(&(*tp)->t_dfops->dop_intake)) {
+		/* log intents and pull in intake items */
+		xfs_defer_create_intents(*tp);
+		list_splice_tail_init(&(*tp)->t_dfops->dop_intake,
+				      &dop_pending);
 
 		/*
 		 * Roll the transaction.
@@ -356,8 +376,8 @@ xfs_defer_finish_noroll(
 			goto out;
 
 		/* Log an intent-done item for the first pending item. */
-		dfp = list_first_entry(&(*tp)->t_dfops->dop_pending,
-				struct xfs_defer_pending, dfp_list);
+		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
+				       dfp_list);
 		trace_xfs_defer_pending_finish((*tp)->t_mountp, dfp);
 		dfp->dfp_done = dfp->dfp_type->create_done(*tp, dfp->dfp_intent,
 				dfp->dfp_count);
@@ -387,7 +407,6 @@ xfs_defer_finish_noroll(
 				 */
 				if (cleanup_fn)
 					cleanup_fn(*tp, state, error);
-				xfs_defer_trans_abort(*tp, error);
 				goto out;
 			}
 		}
@@ -417,8 +436,11 @@ xfs_defer_finish_noroll(
 
 out:
 	if (error) {
+		xfs_defer_trans_abort(*tp, &dop_pending);
+		xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
 		trace_xfs_defer_finish_error((*tp)->t_mountp, (*tp)->t_dfops,
 					     error);
+		xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending);
 		xfs_defer_cancel(*tp);
 		return error;
 	}
@@ -442,54 +464,24 @@ xfs_defer_finish(
 		return error;
 	if ((*tp)->t_flags & XFS_TRANS_DIRTY) {
 		error = xfs_defer_trans_roll(tp);
-		if (error)
+		if (error) {
+			xfs_force_shutdown((*tp)->t_mountp,
+					   SHUTDOWN_CORRUPT_INCORE);
 			return error;
+		}
 	}
 	xfs_defer_reset(*tp);
 	return 0;
 }
 
-/*
- * Free up any items left in the list.
- */
 void
 xfs_defer_cancel(
-	struct xfs_trans		*tp)
+	struct xfs_trans	*tp)
 {
-	struct xfs_defer_ops		*dop = tp->t_dfops;
-	struct xfs_defer_pending	*dfp;
-	struct xfs_defer_pending	*pli;
-	struct list_head		*pwi;
-	struct list_head		*n;
+	struct xfs_mount	*mp = tp->t_mountp;
 
-	trace_xfs_defer_cancel(NULL, dop, _RET_IP_);
-
-	/*
-	 * Free the pending items.  Caller should already have arranged
-	 * for the intent items to be released.
-	 */
-	list_for_each_entry_safe(dfp, pli, &dop->dop_intake, dfp_list) {
-		trace_xfs_defer_intake_cancel(NULL, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			dfp->dfp_type->cancel_item(pwi);
-		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_free(dfp);
-	}
-	list_for_each_entry_safe(dfp, pli, &dop->dop_pending, dfp_list) {
-		trace_xfs_defer_pending_cancel(NULL, dfp);
-		list_del(&dfp->dfp_list);
-		list_for_each_safe(pwi, n, &dfp->dfp_work) {
-			list_del(pwi);
-			dfp->dfp_count--;
-			dfp->dfp_type->cancel_item(pwi);
-		}
-		ASSERT(dfp->dfp_count == 0);
-		kmem_free(dfp);
-	}
+	trace_xfs_defer_cancel(mp, tp->t_dfops, _RET_IP_);
+	xfs_defer_cancel_list(mp, &tp->t_dfops->dop_intake);
 }
 
 /* Add an item for later deferred processing. */
@@ -547,7 +539,6 @@ xfs_defer_init(
 
 	memset(dop, 0, sizeof(struct xfs_defer_ops));
 	INIT_LIST_HEAD(&dop->dop_intake);
-	INIT_LIST_HEAD(&dop->dop_pending);
 	if (tp) {
 		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		tp->t_dfops = dop;
@@ -571,7 +562,6 @@ xfs_defer_move(
 	ASSERT(dst != src);
 
 	list_splice_init(&src->dop_intake, &dst->dop_intake);
-	list_splice_init(&src->dop_pending, &dst->dop_pending);
 
 	/*
 	 * Low free space mode was historically controlled by a dfops field.
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index f051c8056141..f091bf3abeaf 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -41,7 +41,6 @@ int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
 void xfs_defer_cancel(struct xfs_trans *);
 void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
-bool xfs_defer_has_unfinished_work(struct xfs_trans *tp);
 void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 8807f1bb814a..fec9cfe3dfb4 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2392,9 +2392,8 @@ DEFINE_DEFER_EVENT(xfs_defer_finish_done);
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_trans_roll_error);
 DEFINE_DEFER_ERROR_EVENT(xfs_defer_finish_error);
 
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_intake_work);
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_intake_cancel);
-DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_cancel);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_create_intent);
+DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish);
 DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort);
 
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index b050663c2a70..413e4138357f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -929,7 +929,7 @@ __xfs_trans_commit(
 	 * Finish deferred items on final commit. Only permanent transactions
 	 * should ever have deferred ops.
 	 */
-	WARN_ON_ONCE(xfs_defer_has_unfinished_work(tp) &&
+	WARN_ON_ONCE(!list_empty(&tp->t_dfops->dop_intake) &&
 		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
 	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
 		error = xfs_defer_finish_noroll(&tp);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 299656dbf324..1cdc7c0ebeac 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -96,7 +96,6 @@ void	xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
 #define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
 struct xfs_defer_ops {
 	struct list_head	dop_intake;	/* unlogged pending work */
-	struct list_head	dop_pending;	/* logged pending work */
 };
 
 /*
-- 
cgit v1.2.3


From 0f37d1780c3d864599fb377dcb47ad1aa0686b4e Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:34 -0700
Subject: xfs: pass transaction to xfs_defer_add()

The majority of remaining references to struct xfs_defer_ops in XFS
are associated with xfs_defer_add(). At this point, there are no
more external xfs_defer_ops users left. All instances of
xfs_defer_ops are embedded in the transaction, which means we can
safely pass the transaction down to the dfops add interface.

Update xfs_defer_add() to receive the transaction as a parameter.
Various subsystems implement wrappers to allocate and construct the
context specific data structures for the associated deferred
operation type. Update these to also carry the transaction down as
needed and clean up unused dfops parameters along the way.

This removes most of the remaining references to struct
xfs_defer_ops throughout the code and facilitates removal of the
structure.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
[darrick: fix unused variable warnings with ftrace disabled]
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c      |  9 ++---
 fs/xfs/libxfs/xfs_bmap.c       | 89 +++++++++++++++++++-----------------------
 fs/xfs/libxfs/xfs_bmap.h       | 19 +++++----
 fs/xfs/libxfs/xfs_bmap_btree.c |  2 +-
 fs/xfs/libxfs/xfs_defer.c      |  5 ++-
 fs/xfs/libxfs/xfs_defer.h      |  2 +-
 fs/xfs/libxfs/xfs_ialloc.c     | 25 ++++++------
 fs/xfs/libxfs/xfs_refcount.c   | 80 ++++++++++++++++---------------------
 fs/xfs/libxfs/xfs_refcount.h   | 18 ++++-----
 fs/xfs/libxfs/xfs_rmap.c       | 57 +++++++++++++--------------
 fs/xfs/libxfs/xfs_rmap.h       | 22 +++++------
 fs/xfs/xfs_bmap_item.c         |  3 +-
 fs/xfs/xfs_bmap_util.c         | 13 ++----
 fs/xfs/xfs_refcount_item.c     | 14 ++-----
 fs/xfs/xfs_reflink.c           | 21 +++++-----
 15 files changed, 169 insertions(+), 210 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 9847c1632712..5580b6e23bb3 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2198,12 +2198,12 @@ xfs_agfl_reset(
  */
 STATIC void
 xfs_defer_agfl_block(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
 	xfs_fsblock_t			agbno,
 	struct xfs_owner_info		*oinfo)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_extent_free_item	*new;		/* new element */
 
 	ASSERT(xfs_bmap_free_item_zone != NULL);
@@ -2216,7 +2216,7 @@ xfs_defer_agfl_block(
 
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &new->xefi_list);
 }
 
 /*
@@ -2325,8 +2325,7 @@ xfs_alloc_fix_freelist(
 
 		/* defer agfl frees if dfops is provided */
 		if (tp->t_dfops) {
-			xfs_defer_agfl_block(mp, tp->t_dfops, args->agno,
-					     bno, &targs.oinfo);
+			xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
 		} else {
 			error = xfs_free_agfl_block(tp, args->agno, bno, agbp,
 						    &targs.oinfo);
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index d20f541b7061..c9fec0443f38 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -533,8 +533,7 @@ xfs_bmap_validate_ret(
  */
 void
 __xfs_bmap_add_free(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	struct xfs_owner_info		*oinfo,
@@ -542,8 +541,9 @@ __xfs_bmap_add_free(
 {
 	struct xfs_extent_free_item	*new;		/* new element */
 #ifdef DEBUG
-	xfs_agnumber_t		agno;
-	xfs_agblock_t		agbno;
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
 
 	ASSERT(bno != NULLFSBLOCK);
 	ASSERT(len > 0);
@@ -566,9 +566,10 @@ __xfs_bmap_add_free(
 	else
 		xfs_rmap_skip_owner_update(&new->xefi_oinfo);
 	new->xefi_skip_discard = skip_discard;
-	trace_xfs_bmap_free_defer(mp, XFS_FSB_TO_AGNO(mp, bno), 0,
-			XFS_FSB_TO_AGBNO(mp, bno), len);
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
+	trace_xfs_bmap_free_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &new->xefi_list);
 }
 
 /*
@@ -624,7 +625,7 @@ xfs_bmap_btree_to_extents(
 	if ((error = xfs_btree_check_block(cur, cblock, 0, cbp)))
 		return error;
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
-	xfs_bmap_add_free(mp, cur->bc_tp->t_dfops, cbno, 1, &oinfo);
+	xfs_bmap_add_free(cur->bc_tp, cbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
 	xfs_trans_binval(tp, cbp);
@@ -1961,8 +1962,7 @@ xfs_bmap_add_extent_delay_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(bma->flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, bma->tp->t_dfops, bma->ip,
-				whichfork, new);
+		error = xfs_rmap_map_extent(bma->tp, bma->ip, whichfork, new);
 		if (error)
 			goto done;
 	}
@@ -2026,7 +2026,6 @@ xfs_bmap_add_extent_unwritten_real(
 	int			state = xfs_bmap_fork_to_state(whichfork);
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_bmbt_irec	old;
-	struct xfs_defer_ops	*dfops = tp ? tp->t_dfops : NULL;
 
 	*logflagsp = 0;
 
@@ -2445,7 +2444,7 @@ xfs_bmap_add_extent_unwritten_real(
 	}
 
 	/* update reverse mappings */
-	error = xfs_rmap_convert_extent(mp, dfops, ip, whichfork, new);
+	error = xfs_rmap_convert_extent(mp, tp, ip, whichfork, new);
 	if (error)
 		goto done;
 
@@ -2806,8 +2805,7 @@ xfs_bmap_add_extent_hole_real(
 
 	/* add reverse mapping unless caller opted out */
 	if (!(flags & XFS_BMAPI_NORMAP)) {
-		error = xfs_rmap_map_extent(mp, tp->t_dfops, ip, whichfork,
-				new);
+		error = xfs_rmap_map_extent(tp, ip, whichfork, new);
 		if (error)
 			goto done;
 	}
@@ -4364,9 +4362,8 @@ xfs_bmapi_write(
 			 * the refcount btree for orphan recovery.
 			 */
 			if (whichfork == XFS_COW_FORK) {
-				error = xfs_refcount_alloc_cow_extent(mp,
-						tp->t_dfops, bma.blkno,
-						bma.length);
+				error = xfs_refcount_alloc_cow_extent(tp,
+						bma.blkno, bma.length);
 				if (error)
 					goto error0;
 			}
@@ -4852,7 +4849,6 @@ xfs_bmap_del_extent_real(
 	uint			qfield;	/* quota field to update */
 	int			state = xfs_bmap_fork_to_state(whichfork);
 	struct xfs_bmbt_irec	old;
-	struct xfs_defer_ops	*dfops = tp ? tp->t_dfops : NULL;
 
 	mp = ip->i_mount;
 	XFS_STATS_INC(mp, xs_del_exlist);
@@ -5036,7 +5032,7 @@ xfs_bmap_del_extent_real(
 	}
 
 	/* remove reverse mapping */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, del);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, del);
 	if (error)
 		goto done;
 
@@ -5045,11 +5041,11 @@ xfs_bmap_del_extent_real(
 	 */
 	if (do_fx && !(bflags & XFS_BMAPI_REMAP)) {
 		if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) {
-			error = xfs_refcount_decrease_extent(mp, dfops, del);
+			error = xfs_refcount_decrease_extent(tp, del);
 			if (error)
 				goto done;
 		} else {
-			__xfs_bmap_add_free(mp, dfops, del->br_startblock,
+			__xfs_bmap_add_free(tp, del->br_startblock,
 					del->br_blockcount, NULL,
 					(bflags & XFS_BMAPI_NODISCARD) ||
 					del->br_state == XFS_EXT_UNWRITTEN);
@@ -5489,6 +5485,7 @@ xfs_bmse_can_merge(
  */
 STATIC int
 xfs_bmse_merge(
+	struct xfs_trans		*tp,
 	struct xfs_inode		*ip,
 	int				whichfork,
 	xfs_fileoff_t			shift,		/* shift fsb */
@@ -5496,8 +5493,7 @@ xfs_bmse_merge(
 	struct xfs_bmbt_irec		*got,		/* extent to shift */
 	struct xfs_bmbt_irec		*left,		/* preceding extent */
 	struct xfs_btree_cur		*cur,
-	int				*logflags,	/* output */
-	struct xfs_defer_ops		*dfops)
+	int				*logflags)	/* output */
 {
 	struct xfs_bmbt_irec		new;
 	xfs_filblks_t			blockcount;
@@ -5553,23 +5549,23 @@ done:
 			&new);
 
 	/* update reverse mapping. rmap functions merge the rmaps for us */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, got);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, got);
 	if (error)
 		return error;
 	memcpy(&new, got, sizeof(new));
 	new.br_startoff = left->br_startoff + left->br_blockcount;
-	return xfs_rmap_map_extent(mp, dfops, ip, whichfork, &new);
+	return xfs_rmap_map_extent(tp, ip, whichfork, &new);
 }
 
 static int
 xfs_bmap_shift_update_extent(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_iext_cursor	*icur,
 	struct xfs_bmbt_irec	*got,
 	struct xfs_btree_cur	*cur,
 	int			*logflags,
-	struct xfs_defer_ops	*dfops,
 	xfs_fileoff_t		startoff)
 {
 	struct xfs_mount	*mp = ip->i_mount;
@@ -5597,10 +5593,10 @@ xfs_bmap_shift_update_extent(
 			got);
 
 	/* update reverse mapping */
-	error = xfs_rmap_unmap_extent(mp, dfops, ip, whichfork, &prev);
+	error = xfs_rmap_unmap_extent(tp, ip, whichfork, &prev);
 	if (error)
 		return error;
-	return xfs_rmap_map_extent(mp, dfops, ip, whichfork, got);
+	return xfs_rmap_map_extent(tp, ip, whichfork, got);
 }
 
 int
@@ -5660,9 +5656,9 @@ xfs_bmap_collapse_extents(
 		}
 
 		if (xfs_bmse_can_merge(&prev, &got, offset_shift_fsb)) {
-			error = xfs_bmse_merge(ip, whichfork, offset_shift_fsb,
-					&icur, &got, &prev, cur, &logflags,
-					tp->t_dfops);
+			error = xfs_bmse_merge(tp, ip, whichfork,
+					offset_shift_fsb, &icur, &got, &prev,
+					cur, &logflags);
 			if (error)
 				goto del_cursor;
 			goto done;
@@ -5674,8 +5670,8 @@ xfs_bmap_collapse_extents(
 		}
 	}
 
-	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, tp->t_dfops, new_startoff);
+	error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got,
+			cur, &logflags, new_startoff);
 	if (error)
 		goto del_cursor;
 
@@ -5801,8 +5797,8 @@ xfs_bmap_insert_extents(
 			WARN_ON_ONCE(1);
 	}
 
-	error = xfs_bmap_shift_update_extent(ip, whichfork, &icur, &got, cur,
-			&logflags, tp->t_dfops, new_startoff);
+	error = xfs_bmap_shift_update_extent(tp, ip, whichfork, &icur, &got,
+			cur, &logflags, new_startoff);
 	if (error)
 		goto del_cursor;
 
@@ -5979,8 +5975,7 @@ xfs_bmap_is_update_needed(
 /* Record a bmap intent. */
 static int
 __xfs_bmap_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_bmap_intent_type	type,
 	struct xfs_inode		*ip,
 	int				whichfork,
@@ -5988,10 +5983,10 @@ __xfs_bmap_add(
 {
 	struct xfs_bmap_intent		*bi;
 
-	trace_xfs_bmap_defer(mp,
-			XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
+	trace_xfs_bmap_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
 			type,
-			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
 			ip->i_ino, whichfork,
 			bmap->br_startoff,
 			bmap->br_blockcount,
@@ -6004,38 +5999,34 @@ __xfs_bmap_add(
 	bi->bi_whichfork = whichfork;
 	bi->bi_bmap = *bmap;
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list);
 	return 0;
 }
 
 /* Map an extent into a file. */
 int
 xfs_bmap_map_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*PREV)
 {
 	if (!xfs_bmap_is_update_needed(PREV))
 		return 0;
 
-	return __xfs_bmap_add(mp, dfops, XFS_BMAP_MAP, ip,
-			XFS_DATA_FORK, PREV);
+	return __xfs_bmap_add(tp, XFS_BMAP_MAP, ip, XFS_DATA_FORK, PREV);
 }
 
 /* Unmap an extent out of a file. */
 int
 xfs_bmap_unmap_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	struct xfs_bmbt_irec	*PREV)
 {
 	if (!xfs_bmap_is_update_needed(PREV))
 		return 0;
 
-	return __xfs_bmap_add(mp, dfops, XFS_BMAP_UNMAP, ip,
-			XFS_DATA_FORK, PREV);
+	return __xfs_bmap_add(tp, XFS_BMAP_UNMAP, ip, XFS_DATA_FORK, PREV);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 9165a878edcd..b6e9b639e731 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -184,9 +184,9 @@ void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
 void	xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
-void	__xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-			  xfs_fsblock_t bno, xfs_filblks_t len,
-			  struct xfs_owner_info *oinfo, bool skip_discard);
+void	__xfs_bmap_add_free(struct xfs_trans *tp, xfs_fsblock_t bno,
+		xfs_filblks_t len, struct xfs_owner_info *oinfo,
+		bool skip_discard);
 void	xfs_bmap_compute_maxlevels(struct xfs_mount *mp, int whichfork);
 int	xfs_bmap_first_unused(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extlen_t len, xfs_fileoff_t *unused, int whichfork);
@@ -230,13 +230,12 @@ int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
 
 static inline void
 xfs_bmap_add_free(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			bno,
 	xfs_filblks_t			len,
 	struct xfs_owner_info		*oinfo)
 {
-	__xfs_bmap_add_free(mp, dfops, bno, len, oinfo, false);
+	__xfs_bmap_add_free(tp, bno, len, oinfo, false);
 }
 
 enum xfs_bmap_intent_type {
@@ -256,10 +255,10 @@ int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_inode *ip,
 		enum xfs_bmap_intent_type type, int whichfork,
 		xfs_fileoff_t startoff, xfs_fsblock_t startblock,
 		xfs_filblks_t *blockcount, xfs_exntst_t state);
-int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
-int	xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
+int	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap);
+int	xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap);
 
 static inline int xfs_bmap_fork_to_state(int whichfork)
 {
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index 955e29de8cae..cdb74d2e2a43 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -289,7 +289,7 @@ xfs_bmbt_free_block(
 	struct xfs_owner_info	oinfo;
 
 	xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_private.b.whichfork);
-	xfs_bmap_add_free(mp, cur->bc_tp->t_dfops, fsbno, 1, &oinfo);
+	xfs_bmap_add_free(cur->bc_tp, fsbno, 1, &oinfo);
 	ip->i_d.di_nblocks--;
 
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 1cbddcf539da..ce2286763531 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -487,12 +487,15 @@ xfs_defer_cancel(
 /* Add an item for later deferred processing. */
 void
 xfs_defer_add(
-	struct xfs_defer_ops		*dop,
+	struct xfs_trans		*tp,
 	enum xfs_defer_ops_type		type,
 	struct list_head		*li)
 {
+	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct xfs_defer_pending	*dfp = NULL;
 
+	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
+
 	/*
 	 * Add the item to a pending item at the end of the intake list.
 	 * If the last pending item has the same type, reuse it.  Else,
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index f091bf3abeaf..b2675f1ca909 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -35,7 +35,7 @@ enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_MAX,
 };
 
-void xfs_defer_add(struct xfs_defer_ops *dop, enum xfs_defer_ops_type type,
+void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
 		struct list_head *h);
 int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 295304ad1bc1..a8f6db735d5d 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1838,23 +1838,24 @@ out_error:
  */
 STATIC void
 xfs_difree_inode_chunk(
-	struct xfs_mount		*mp,
+	struct xfs_trans		*tp,
 	xfs_agnumber_t			agno,
-	struct xfs_inobt_rec_incore	*rec,
-	struct xfs_defer_ops		*dfops)
+	struct xfs_inobt_rec_incore	*rec)
 {
-	xfs_agblock_t	sagbno = XFS_AGINO_TO_AGBNO(mp, rec->ir_startino);
-	int		startidx, endidx;
-	int		nextbit;
-	xfs_agblock_t	agbno;
-	int		contigblk;
-	struct xfs_owner_info	oinfo;
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_agblock_t			sagbno = XFS_AGINO_TO_AGBNO(mp,
+							rec->ir_startino);
+	int				startidx, endidx;
+	int				nextbit;
+	xfs_agblock_t			agbno;
+	int				contigblk;
+	struct xfs_owner_info		oinfo;
 	DECLARE_BITMAP(holemask, XFS_INOBT_HOLEMASK_BITS);
 	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_INODES);
 
 	if (!xfs_inobt_issparse(rec->ir_holemask)) {
 		/* not sparse, calculate extent info directly */
-		xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, sagbno),
+		xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, sagbno),
 				  mp->m_ialloc_blks, &oinfo);
 		return;
 	}
@@ -1898,7 +1899,7 @@ xfs_difree_inode_chunk(
 
 		ASSERT(agbno % mp->m_sb.sb_spino_align == 0);
 		ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
-		xfs_bmap_add_free(mp, dfops, XFS_AGB_TO_FSB(mp, agno, agbno),
+		xfs_bmap_add_free(tp, XFS_AGB_TO_FSB(mp, agno, agbno),
 				  contigblk, &oinfo);
 
 		/* reset range to current bit and carry on... */
@@ -2002,7 +2003,7 @@ xfs_difree_inobt(
 			goto error0;
 		}
 
-		xfs_difree_inode_chunk(mp, agno, &rec, tp->t_dfops);
+		xfs_difree_inode_chunk(tp, agno, &rec);
 	} else {
 		xic->deleted = false;
 
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 86f297ca90cd..542aa1475b5f 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -34,11 +34,9 @@ enum xfs_refc_adjust_op {
 };
 
 STATIC int __xfs_refcount_cow_alloc(struct xfs_btree_cur *rcur,
-		xfs_agblock_t agbno, xfs_extlen_t aglen,
-		struct xfs_defer_ops *dfops);
+		xfs_agblock_t agbno, xfs_extlen_t aglen);
 STATIC int __xfs_refcount_cow_free(struct xfs_btree_cur *rcur,
-		xfs_agblock_t agbno, xfs_extlen_t aglen,
-		struct xfs_defer_ops *dfops);
+		xfs_agblock_t agbno, xfs_extlen_t aglen);
 
 /*
  * Look up the first record less than or equal to [bno, len] in the btree
@@ -870,7 +868,6 @@ xfs_refcount_adjust_extents(
 	xfs_agblock_t		*agbno,
 	xfs_extlen_t		*aglen,
 	enum xfs_refc_adjust_op	adj,
-	struct xfs_defer_ops	*dfops,
 	struct xfs_owner_info	*oinfo)
 {
 	struct xfs_refcount_irec	ext, tmp;
@@ -925,8 +922,8 @@ xfs_refcount_adjust_extents(
 				fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 						cur->bc_private.a.agno,
 						tmp.rc_startblock);
-				xfs_bmap_add_free(cur->bc_mp, dfops, fsbno,
-						tmp.rc_blockcount, oinfo);
+				xfs_bmap_add_free(cur->bc_tp, fsbno,
+						  tmp.rc_blockcount, oinfo);
 			}
 
 			(*agbno) += tmp.rc_blockcount;
@@ -968,8 +965,8 @@ xfs_refcount_adjust_extents(
 			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 					cur->bc_private.a.agno,
 					ext.rc_startblock);
-			xfs_bmap_add_free(cur->bc_mp, dfops, fsbno,
-					ext.rc_blockcount, oinfo);
+			xfs_bmap_add_free(cur->bc_tp, fsbno, ext.rc_blockcount,
+					  oinfo);
 		}
 
 skip:
@@ -998,7 +995,6 @@ xfs_refcount_adjust(
 	xfs_agblock_t		*new_agbno,
 	xfs_extlen_t		*new_aglen,
 	enum xfs_refc_adjust_op	adj,
-	struct xfs_defer_ops	*dfops,
 	struct xfs_owner_info	*oinfo)
 {
 	bool			shape_changed;
@@ -1043,7 +1039,7 @@ xfs_refcount_adjust(
 
 	/* Now that we've taken care of the ends, adjust the middle extents */
 	error = xfs_refcount_adjust_extents(cur, new_agbno, new_aglen,
-			adj, dfops, oinfo);
+			adj, oinfo);
 	if (error)
 		goto out_error;
 
@@ -1090,7 +1086,6 @@ xfs_refcount_finish_one(
 	struct xfs_btree_cur		**pcur)
 {
 	struct xfs_mount		*mp = tp->t_mountp;
-	struct xfs_defer_ops		*dfops = tp->t_dfops;
 	struct xfs_btree_cur		*rcur;
 	struct xfs_buf			*agbp = NULL;
 	int				error = 0;
@@ -1145,23 +1140,23 @@ xfs_refcount_finish_one(
 	switch (type) {
 	case XFS_REFCOUNT_INCREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
-			new_len, XFS_REFCOUNT_ADJUST_INCREASE, dfops, NULL);
+			new_len, XFS_REFCOUNT_ADJUST_INCREASE, NULL);
 		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
 		break;
 	case XFS_REFCOUNT_DECREASE:
 		error = xfs_refcount_adjust(rcur, bno, blockcount, &new_agbno,
-			new_len, XFS_REFCOUNT_ADJUST_DECREASE, dfops, NULL);
+			new_len, XFS_REFCOUNT_ADJUST_DECREASE, NULL);
 		*new_fsb = XFS_AGB_TO_FSB(mp, agno, new_agbno);
 		break;
 	case XFS_REFCOUNT_ALLOC_COW:
 		*new_fsb = startblock + blockcount;
 		*new_len = 0;
-		error = __xfs_refcount_cow_alloc(rcur, bno, blockcount, dfops);
+		error = __xfs_refcount_cow_alloc(rcur, bno, blockcount);
 		break;
 	case XFS_REFCOUNT_FREE_COW:
 		*new_fsb = startblock + blockcount;
 		*new_len = 0;
-		error = __xfs_refcount_cow_free(rcur, bno, blockcount, dfops);
+		error = __xfs_refcount_cow_free(rcur, bno, blockcount);
 		break;
 	default:
 		ASSERT(0);
@@ -1183,16 +1178,16 @@ out_cur:
  */
 static int
 __xfs_refcount_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_refcount_intent_type	type,
 	xfs_fsblock_t			startblock,
 	xfs_extlen_t			blockcount)
 {
 	struct xfs_refcount_intent	*ri;
 
-	trace_xfs_refcount_defer(mp, XFS_FSB_TO_AGNO(mp, startblock),
-			type, XFS_FSB_TO_AGBNO(mp, startblock),
+	trace_xfs_refcount_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, startblock),
+			type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
 			blockcount);
 
 	ri = kmem_alloc(sizeof(struct xfs_refcount_intent),
@@ -1202,7 +1197,7 @@ __xfs_refcount_add(
 	ri->ri_startblock = startblock;
 	ri->ri_blockcount = blockcount;
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_REFCOUNT, &ri->ri_list);
 	return 0;
 }
 
@@ -1211,14 +1206,13 @@ __xfs_refcount_add(
  */
 int
 xfs_refcount_increase_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	struct xfs_bmbt_irec		*PREV)
 {
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
 		return 0;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_INCREASE,
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_INCREASE,
 			PREV->br_startblock, PREV->br_blockcount);
 }
 
@@ -1227,14 +1221,13 @@ xfs_refcount_increase_extent(
  */
 int
 xfs_refcount_decrease_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	struct xfs_bmbt_irec		*PREV)
 {
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+	if (!xfs_sb_version_hasreflink(&tp->t_mountp->m_sb))
 		return 0;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_DECREASE,
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_DECREASE,
 			PREV->br_startblock, PREV->br_blockcount);
 }
 
@@ -1522,8 +1515,7 @@ STATIC int
 __xfs_refcount_cow_alloc(
 	struct xfs_btree_cur	*rcur,
 	xfs_agblock_t		agbno,
-	xfs_extlen_t		aglen,
-	struct xfs_defer_ops	*dfops)
+	xfs_extlen_t		aglen)
 {
 	trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
@@ -1540,8 +1532,7 @@ STATIC int
 __xfs_refcount_cow_free(
 	struct xfs_btree_cur	*rcur,
 	xfs_agblock_t		agbno,
-	xfs_extlen_t		aglen,
-	struct xfs_defer_ops	*dfops)
+	xfs_extlen_t		aglen)
 {
 	trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_private.a.agno,
 			agbno, aglen);
@@ -1554,47 +1545,45 @@ __xfs_refcount_cow_free(
 /* Record a CoW staging extent in the refcount btree. */
 int
 xfs_refcount_alloc_cow_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	int				error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
-	error = __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_ALLOC_COW,
-			fsb, len);
+	error = __xfs_refcount_add(tp, XFS_REFCOUNT_ALLOC_COW, fsb, len);
 	if (error)
 		return error;
 
 	/* Add rmap entry */
-	return xfs_rmap_alloc_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+	return xfs_rmap_alloc_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
 }
 
 /* Forget a CoW staging event in the refcount btree. */
 int
 xfs_refcount_free_cow_extent(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	xfs_fsblock_t			fsb,
 	xfs_extlen_t			len)
 {
+	struct xfs_mount		*mp = tp->t_mountp;
 	int				error;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return 0;
 
 	/* Remove rmap entry */
-	error = xfs_rmap_free_extent(mp, dfops, XFS_FSB_TO_AGNO(mp, fsb),
+	error = xfs_rmap_free_extent(tp, XFS_FSB_TO_AGNO(mp, fsb),
 			XFS_FSB_TO_AGBNO(mp, fsb), len, XFS_RMAP_OWN_COW);
 	if (error)
 		return error;
 
-	return __xfs_refcount_add(mp, dfops, XFS_REFCOUNT_FREE_COW,
-			fsb, len);
+	return __xfs_refcount_add(tp, XFS_REFCOUNT_FREE_COW, fsb, len);
 }
 
 struct xfs_refcount_recovery {
@@ -1692,14 +1681,13 @@ xfs_refcount_recover_cow_leftovers(
 		/* Free the orphan record */
 		agbno = rr->rr_rrec.rc_startblock - XFS_REFC_COW_START;
 		fsb = XFS_AGB_TO_FSB(mp, agno, agbno);
-		error = xfs_refcount_free_cow_extent(mp, tp->t_dfops, fsb,
+		error = xfs_refcount_free_cow_extent(tp, fsb,
 				rr->rr_rrec.rc_blockcount);
 		if (error)
 			goto out_trans;
 
 		/* Free the block. */
-		xfs_bmap_add_free(mp, tp->t_dfops, fsb,
-				rr->rr_rrec.rc_blockcount, NULL);
+		xfs_bmap_add_free(tp, fsb, rr->rr_rrec.rc_blockcount, NULL);
 
 		error = xfs_trans_commit(tp);
 		if (error)
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 3b72c6dbf6ad..1d9c518575e7 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -29,10 +29,10 @@ struct xfs_refcount_intent {
 	xfs_extlen_t				ri_blockcount;
 };
 
-extern int xfs_refcount_increase_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec);
-extern int xfs_refcount_decrease_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, struct xfs_bmbt_irec *irec);
+extern int xfs_refcount_increase_extent(struct xfs_trans *tp,
+		struct xfs_bmbt_irec *irec);
+extern int xfs_refcount_decrease_extent(struct xfs_trans *tp,
+		struct xfs_bmbt_irec *irec);
 
 extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
@@ -45,12 +45,10 @@ extern int xfs_refcount_find_shared(struct xfs_btree_cur *cur,
 		xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno,
 		xfs_extlen_t *flen, bool find_end_of_shared);
 
-extern int xfs_refcount_alloc_cow_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, xfs_fsblock_t fsb,
-		xfs_extlen_t len);
-extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp,
-		struct xfs_defer_ops *dfops, xfs_fsblock_t fsb,
-		xfs_extlen_t len);
+extern int xfs_refcount_alloc_cow_extent(struct xfs_trans *tp,
+		xfs_fsblock_t fsb, xfs_extlen_t len);
+extern int xfs_refcount_free_cow_extent(struct xfs_trans *tp,
+		xfs_fsblock_t fsb, xfs_extlen_t len);
 extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 		xfs_agnumber_t agno);
 
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index fb266fa2cc45..245af452840e 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -2277,18 +2277,18 @@ xfs_rmap_update_is_needed(
  */
 static int
 __xfs_rmap_add(
-	struct xfs_mount		*mp,
-	struct xfs_defer_ops		*dfops,
+	struct xfs_trans		*tp,
 	enum xfs_rmap_intent_type	type,
 	uint64_t			owner,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
-	struct xfs_rmap_intent	*ri;
+	struct xfs_rmap_intent		*ri;
 
-	trace_xfs_rmap_defer(mp, XFS_FSB_TO_AGNO(mp, bmap->br_startblock),
+	trace_xfs_rmap_defer(tp->t_mountp,
+			XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
 			type,
-			XFS_FSB_TO_AGBNO(mp, bmap->br_startblock),
+			XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
 			owner, whichfork,
 			bmap->br_startoff,
 			bmap->br_blockcount,
@@ -2301,23 +2301,22 @@ __xfs_rmap_add(
 	ri->ri_whichfork = whichfork;
 	ri->ri_bmap = *bmap;
 
-	xfs_defer_add(dfops, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
+	xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_RMAP, &ri->ri_list);
 	return 0;
 }
 
 /* Map an extent into a file. */
 int
 xfs_rmap_map_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_rmap_update_is_needed(mp, whichfork))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_MAP_SHARED : XFS_RMAP_MAP, ip->i_ino,
 			whichfork, PREV);
 }
@@ -2325,25 +2324,29 @@ xfs_rmap_map_extent(
 /* Unmap an extent out of a file. */
 int
 xfs_rmap_unmap_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
 {
-	if (!xfs_rmap_update_is_needed(mp, whichfork))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_UNMAP_SHARED : XFS_RMAP_UNMAP, ip->i_ino,
 			whichfork, PREV);
 }
 
-/* Convert a data fork extent from unwritten to real or vice versa. */
+/*
+ * Convert a data fork extent from unwritten to real or vice versa.
+ *
+ * Note that tp can be NULL here as no transaction is used for COW fork
+ * unwritten conversion.
+ */
 int
 xfs_rmap_convert_extent(
 	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	int			whichfork,
 	struct xfs_bmbt_irec	*PREV)
@@ -2351,7 +2354,7 @@ xfs_rmap_convert_extent(
 	if (!xfs_rmap_update_is_needed(mp, whichfork))
 		return 0;
 
-	return __xfs_rmap_add(mp, dfops, xfs_is_reflink_inode(ip) ?
+	return __xfs_rmap_add(tp, xfs_is_reflink_inode(ip) ?
 			XFS_RMAP_CONVERT_SHARED : XFS_RMAP_CONVERT, ip->i_ino,
 			whichfork, PREV);
 }
@@ -2359,8 +2362,7 @@ xfs_rmap_convert_extent(
 /* Schedule the creation of an rmap for non-file data. */
 int
 xfs_rmap_alloc_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
@@ -2368,23 +2370,21 @@ xfs_rmap_alloc_extent(
 {
 	struct xfs_bmbt_irec	bmap;
 
-	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return 0;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
+	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	return __xfs_rmap_add(mp, dfops, XFS_RMAP_ALLOC, owner,
-			XFS_DATA_FORK, &bmap);
+	return __xfs_rmap_add(tp, XFS_RMAP_ALLOC, owner, XFS_DATA_FORK, &bmap);
 }
 
 /* Schedule the deletion of an rmap for non-file data. */
 int
 xfs_rmap_free_extent(
-	struct xfs_mount	*mp,
-	struct xfs_defer_ops	*dfops,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
@@ -2392,16 +2392,15 @@ xfs_rmap_free_extent(
 {
 	struct xfs_bmbt_irec	bmap;
 
-	if (!xfs_rmap_update_is_needed(mp, XFS_DATA_FORK))
+	if (!xfs_rmap_update_is_needed(tp->t_mountp, XFS_DATA_FORK))
 		return 0;
 
-	bmap.br_startblock = XFS_AGB_TO_FSB(mp, agno, bno);
+	bmap.br_startblock = XFS_AGB_TO_FSB(tp->t_mountp, agno, bno);
 	bmap.br_blockcount = len;
 	bmap.br_startoff = 0;
 	bmap.br_state = XFS_EXT_NORM;
 
-	return __xfs_rmap_add(mp, dfops, XFS_RMAP_FREE, owner,
-			XFS_DATA_FORK, &bmap);
+	return __xfs_rmap_add(tp, XFS_RMAP_FREE, owner, XFS_DATA_FORK, &bmap);
 }
 
 /* Compare rmap records.  Returns -1 if a < b, 1 if a > b, and 0 if equal. */
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 9f19454768b2..157dc722ad35 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -185,21 +185,17 @@ struct xfs_rmap_intent {
 };
 
 /* functions for updating the rmapbt based on bmbt map/unmap operations */
-int xfs_rmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
+int xfs_rmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		int whichfork, struct xfs_bmbt_irec *imap);
+int xfs_rmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
+		int whichfork, struct xfs_bmbt_irec *imap);
+int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_trans *tp,
 		struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *imap);
-int xfs_rmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, int whichfork,
-		struct xfs_bmbt_irec *imap);
-int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		struct xfs_inode *ip, int whichfork,
-		struct xfs_bmbt_irec *imap);
-int xfs_rmap_alloc_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		uint64_t owner);
-int xfs_rmap_free_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
-		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		uint64_t owner);
+int xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
+		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
+int xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
+		xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
 
 void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index e828e0b51814..ce45f066995e 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -486,8 +486,7 @@ xfs_bui_recover(
 		irec.br_blockcount = count;
 		irec.br_startoff = bmap->me_startoff;
 		irec.br_state = state;
-		error = xfs_bmap_unmap_extent(tp->t_mountp, tp->t_dfops, ip,
-					      &irec);
+		error = xfs_bmap_unmap_extent(tp, ip, &irec);
 		if (error)
 			goto err_inode;
 	}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index d9dad399440a..addbd74ecd8e 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1534,7 +1534,6 @@ xfs_swap_extent_rmap(
 	struct xfs_inode		*tip)
 {
 	struct xfs_trans		*tp = *tpp;
-	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_bmbt_irec		irec;
 	struct xfs_bmbt_irec		uirec;
 	struct xfs_bmbt_irec		tirec;
@@ -1598,26 +1597,22 @@ xfs_swap_extent_rmap(
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
 
 			/* Remove the mapping from the donor file. */
-			error = xfs_bmap_unmap_extent(mp, tp->t_dfops, tip,
-					&uirec);
+			error = xfs_bmap_unmap_extent(tp, tip, &uirec);
 			if (error)
 				goto out_defer;
 
 			/* Remove the mapping from the source file. */
-			error = xfs_bmap_unmap_extent(mp, tp->t_dfops, ip,
-					&irec);
+			error = xfs_bmap_unmap_extent(tp, ip, &irec);
 			if (error)
 				goto out_defer;
 
 			/* Map the donor file's blocks into the source file. */
-			error = xfs_bmap_map_extent(mp, tp->t_dfops, ip,
-					&uirec);
+			error = xfs_bmap_map_extent(tp, ip, &uirec);
 			if (error)
 				goto out_defer;
 
 			/* Map the source file's blocks into the donor file. */
-			error = xfs_bmap_map_extent(mp, tp->t_dfops, tip,
-					&irec);
+			error = xfs_bmap_map_extent(tp, tip, &irec);
 			if (error)
 				goto out_defer;
 
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 43c4ac374cba..fce38b56b962 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -490,24 +490,18 @@ xfs_cui_recover(
 			irec.br_blockcount = new_len;
 			switch (type) {
 			case XFS_REFCOUNT_INCREASE:
-				error = xfs_refcount_increase_extent(
-						tp->t_mountp, tp->t_dfops,
-						&irec);
+				error = xfs_refcount_increase_extent(tp, &irec);
 				break;
 			case XFS_REFCOUNT_DECREASE:
-				error = xfs_refcount_decrease_extent(
-						tp->t_mountp, tp->t_dfops,
-						&irec);
+				error = xfs_refcount_decrease_extent(tp, &irec);
 				break;
 			case XFS_REFCOUNT_ALLOC_COW:
-				error = xfs_refcount_alloc_cow_extent(
-						tp->t_mountp, tp->t_dfops,
+				error = xfs_refcount_alloc_cow_extent(tp,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
 			case XFS_REFCOUNT_FREE_COW:
-				error = xfs_refcount_free_cow_extent(
-						tp->t_mountp, tp->t_dfops,
+				error = xfs_refcount_free_cow_extent(tp,
 						irec.br_startblock,
 						irec.br_blockcount);
 				break;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 2ec562d75494..cbceb320a2e7 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -506,15 +506,13 @@ xfs_reflink_cancel_cow_blocks(
 			ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
 
 			/* Free the CoW orphan record. */
-			error = xfs_refcount_free_cow_extent(ip->i_mount,
-					(*tpp)->t_dfops, del.br_startblock,
-					del.br_blockcount);
+			error = xfs_refcount_free_cow_extent(*tpp,
+					del.br_startblock, del.br_blockcount);
 			if (error)
 				break;
 
-			xfs_bmap_add_free(ip->i_mount, (*tpp)->t_dfops,
-					del.br_startblock, del.br_blockcount,
-					NULL);
+			xfs_bmap_add_free(*tpp, del.br_startblock,
+					  del.br_blockcount, NULL);
 
 			/* Roll the transaction */
 			error = xfs_defer_finish(tpp);
@@ -694,14 +692,13 @@ xfs_reflink_end_cow(
 		trace_xfs_reflink_cow_remap(ip, &del);
 
 		/* Free the CoW orphan record. */
-		error = xfs_refcount_free_cow_extent(tp->t_mountp, tp->t_dfops,
-				del.br_startblock, del.br_blockcount);
+		error = xfs_refcount_free_cow_extent(tp, del.br_startblock,
+				del.br_blockcount);
 		if (error)
 			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(tp->t_mountp, tp->t_dfops, ip,
-					    &del);
+		error = xfs_bmap_map_extent(tp, ip, &del);
 		if (error)
 			goto out_cancel;
 
@@ -1046,12 +1043,12 @@ xfs_reflink_remap_extent(
 				uirec.br_blockcount, uirec.br_startblock);
 
 		/* Update the refcount tree */
-		error = xfs_refcount_increase_extent(mp, tp->t_dfops, &uirec);
+		error = xfs_refcount_increase_extent(tp, &uirec);
 		if (error)
 			goto out_cancel;
 
 		/* Map the new blocks into the data fork. */
-		error = xfs_bmap_map_extent(mp, tp->t_dfops, ip, &uirec);
+		error = xfs_bmap_map_extent(tp, ip, &uirec);
 		if (error)
 			goto out_cancel;
 
-- 
cgit v1.2.3


From c03edc9e49b6a3c1f4b27f505a04093ab333b245 Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:35 -0700
Subject: xfs: always defer agfl block frees

The AGFL fixup code conditionally defers block frees from the free
list based on whether the current transaction has an associated
xfs_defer_ops structure. Now that dfops is embedded in the
transaction and the internal dfops is used unconditionally, this
invariant is always true.

Remove the now dead logic to check for ->t_dfops in
xfs_alloc_fix_freelist() and unconditionally defer AGFL block frees.

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_alloc.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 5580b6e23bb3..e1c0c0d2f1b0 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2323,15 +2323,8 @@ xfs_alloc_fix_freelist(
 		if (error)
 			goto out_agbp_relse;
 
-		/* defer agfl frees if dfops is provided */
-		if (tp->t_dfops) {
-			xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
-		} else {
-			error = xfs_free_agfl_block(tp, args->agno, bno, agbp,
-						    &targs.oinfo);
-			if (error)
-				goto out_agbp_relse;
-		}
+		/* defer agfl frees */
+		xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
 	}
 
 	targs.tp = tp;
-- 
cgit v1.2.3


From 9d9e6233859706875c392707efd6d516cfb764fb Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Wed, 1 Aug 2018 07:20:35 -0700
Subject: xfs: fold dfops into the transaction

struct xfs_defer_ops has now been reduced to a single list_head. The
external dfops mechanism is unused and thus everywhere a (permanent)
transaction is accessible the associated dfops structure is as well.

Remove the xfs_defer_ops structure and fold the list_head into the
transaction. Also remove the last remnant of external dfops in
xfs_trans_dup().

Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c     |  1 -
 fs/xfs/libxfs/xfs_btree.h    |  1 -
 fs/xfs/libxfs/xfs_da_btree.h |  1 -
 fs/xfs/libxfs/xfs_defer.c    | 67 +++++++++++++-------------------------------
 fs/xfs/libxfs/xfs_defer.h    |  2 --
 fs/xfs/libxfs/xfs_dir2.c     |  2 --
 fs/xfs/libxfs/xfs_dir2.h     |  1 -
 fs/xfs/xfs_inode.h           |  1 -
 fs/xfs/xfs_reflink.c         |  5 ++--
 fs/xfs/xfs_trace.h           | 40 ++++++++++++--------------
 fs/xfs/xfs_trans.c           | 13 ++++-----
 fs/xfs/xfs_trans.h           |  8 ++----
 12 files changed, 46 insertions(+), 96 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index c9fec0443f38..5648a177e0ac 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4286,7 +4286,6 @@ xfs_bmapi_write(
 	bma.ip = ip;
 	bma.total = total;
 	bma.datatype = 0;
-	ASSERT(!tp || tp->t_dfops);
 
 	while (bno < end && n < *nmap) {
 		bool			need_alloc = false, wasdelay = false;
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index 503615f4d729..e3b3e9dce5da 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -7,7 +7,6 @@
 #define	__XFS_BTREE_H__
 
 struct xfs_buf;
-struct xfs_defer_ops;
 struct xfs_inode;
 struct xfs_mount;
 struct xfs_trans;
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 59e290ef334f..84dd865b6c3d 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -7,7 +7,6 @@
 #ifndef __XFS_DA_BTREE_H__
 #define	__XFS_DA_BTREE_H__
 
-struct xfs_defer_ops;
 struct xfs_inode;
 struct xfs_trans;
 struct zone;
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index ce2286763531..e792b167150a 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -183,11 +183,10 @@ STATIC void
 xfs_defer_create_intents(
 	struct xfs_trans		*tp)
 {
-	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct list_head		*li;
 	struct xfs_defer_pending	*dfp;
 
-	list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
+	list_for_each_entry(dfp, &tp->t_dfops, dfp_list) {
 		dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
 				dfp->dfp_count);
 		trace_xfs_defer_create_intent(tp->t_mountp, dfp);
@@ -204,10 +203,9 @@ xfs_defer_trans_abort(
 	struct xfs_trans		*tp,
 	struct list_head		*dop_pending)
 {
-	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct xfs_defer_pending	*dfp;
 
-	trace_xfs_defer_trans_abort(tp->t_mountp, dop, _RET_IP_);
+	trace_xfs_defer_trans_abort(tp, _RET_IP_);
 
 	/* Abort intent items that don't have a done item. */
 	list_for_each_entry(dfp, dop_pending, dfp_list) {
@@ -266,14 +264,13 @@ xfs_defer_trans_roll(
 		}
 	}
 
-	trace_xfs_defer_trans_roll(tp->t_mountp, tp->t_dfops, _RET_IP_);
+	trace_xfs_defer_trans_roll(tp, _RET_IP_);
 
 	/* Roll the transaction. */
 	error = xfs_trans_roll(tpp);
 	tp = *tpp;
 	if (error) {
-		trace_xfs_defer_trans_roll_error(tp->t_mountp,
-						 tp->t_dfops, error);
+		trace_xfs_defer_trans_roll_error(tp, error);
 		return error;
 	}
 
@@ -297,7 +294,7 @@ static void
 xfs_defer_reset(
 	struct xfs_trans	*tp)
 {
-	ASSERT(list_empty(&tp->t_dfops->dop_intake));
+	ASSERT(list_empty(&tp->t_dfops));
 
 	/*
 	 * Low mode state transfers across transaction rolls to mirror dfops
@@ -358,15 +355,13 @@ xfs_defer_finish_noroll(
 
 	ASSERT((*tp)->t_flags & XFS_TRANS_PERM_LOG_RES);
 
-	trace_xfs_defer_finish((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);
+	trace_xfs_defer_finish(*tp, _RET_IP_);
 
 	/* Until we run out of pending work to finish... */
-	while (!list_empty(&dop_pending) ||
-	       !list_empty(&(*tp)->t_dfops->dop_intake)) {
+	while (!list_empty(&dop_pending) || !list_empty(&(*tp)->t_dfops)) {
 		/* log intents and pull in intake items */
 		xfs_defer_create_intents(*tp);
-		list_splice_tail_init(&(*tp)->t_dfops->dop_intake,
-				      &dop_pending);
+		list_splice_tail_init(&(*tp)->t_dfops, &dop_pending);
 
 		/*
 		 * Roll the transaction.
@@ -438,14 +433,13 @@ out:
 	if (error) {
 		xfs_defer_trans_abort(*tp, &dop_pending);
 		xfs_force_shutdown((*tp)->t_mountp, SHUTDOWN_CORRUPT_INCORE);
-		trace_xfs_defer_finish_error((*tp)->t_mountp, (*tp)->t_dfops,
-					     error);
+		trace_xfs_defer_finish_error(*tp, error);
 		xfs_defer_cancel_list((*tp)->t_mountp, &dop_pending);
 		xfs_defer_cancel(*tp);
 		return error;
 	}
 
-	trace_xfs_defer_finish_done((*tp)->t_mountp, (*tp)->t_dfops, _RET_IP_);
+	trace_xfs_defer_finish_done(*tp, _RET_IP_);
 	return 0;
 }
 
@@ -480,8 +474,8 @@ xfs_defer_cancel(
 {
 	struct xfs_mount	*mp = tp->t_mountp;
 
-	trace_xfs_defer_cancel(mp, tp->t_dfops, _RET_IP_);
-	xfs_defer_cancel_list(mp, &tp->t_dfops->dop_intake);
+	trace_xfs_defer_cancel(tp, _RET_IP_);
+	xfs_defer_cancel_list(mp, &tp->t_dfops);
 }
 
 /* Add an item for later deferred processing. */
@@ -491,7 +485,6 @@ xfs_defer_add(
 	enum xfs_defer_ops_type		type,
 	struct list_head		*li)
 {
-	struct xfs_defer_ops		*dop = tp->t_dfops;
 	struct xfs_defer_pending	*dfp = NULL;
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
@@ -501,8 +494,8 @@ xfs_defer_add(
 	 * If the last pending item has the same type, reuse it.  Else,
 	 * create a new pending item at the end of the intake list.
 	 */
-	if (!list_empty(&dop->dop_intake)) {
-		dfp = list_last_entry(&dop->dop_intake,
+	if (!list_empty(&tp->t_dfops)) {
+		dfp = list_last_entry(&tp->t_dfops,
 				struct xfs_defer_pending, dfp_list);
 		if (dfp->dfp_type->type != type ||
 		    (dfp->dfp_type->max_items &&
@@ -517,7 +510,7 @@ xfs_defer_add(
 		dfp->dfp_done = NULL;
 		dfp->dfp_count = 0;
 		INIT_LIST_HEAD(&dfp->dfp_work);
-		list_add_tail(&dfp->dfp_list, &dop->dop_intake);
+		list_add_tail(&dfp->dfp_list, &tp->t_dfops);
 	}
 
 	list_add_tail(li, &dfp->dfp_work);
@@ -532,39 +525,17 @@ xfs_defer_init_op_type(
 	defer_op_types[type->type] = type;
 }
 
-/* Initialize a deferred operation. */
-void
-xfs_defer_init(
-	struct xfs_trans		*tp,
-	struct xfs_defer_ops		*dop)
-{
-	struct xfs_mount		*mp = NULL;
-
-	memset(dop, 0, sizeof(struct xfs_defer_ops));
-	INIT_LIST_HEAD(&dop->dop_intake);
-	if (tp) {
-		ASSERT(tp->t_firstblock == NULLFSBLOCK);
-		tp->t_dfops = dop;
-		mp = tp->t_mountp;
-	}
-	trace_xfs_defer_init(mp, dop, _RET_IP_);
-}
-
 /*
- * Move state from one xfs_defer_ops to another and reset the source to initial
- * state. This is primarily used to carry state forward across transaction rolls
- * with internal dfops.
+ * Move deferred ops from one transaction to another and reset the source to
+ * initial state. This is primarily used to carry state forward across
+ * transaction rolls with pending dfops.
  */
 void
 xfs_defer_move(
 	struct xfs_trans	*dtp,
 	struct xfs_trans	*stp)
 {
-	struct xfs_defer_ops	*dst = dtp->t_dfops;
-	struct xfs_defer_ops	*src = stp->t_dfops;
-	ASSERT(dst != src);
-
-	list_splice_init(&src->dop_intake, &dst->dop_intake);
+	list_splice_init(&stp->t_dfops, &dtp->t_dfops);
 
 	/*
 	 * Low free space mode was historically controlled by a dfops field.
diff --git a/fs/xfs/libxfs/xfs_defer.h b/fs/xfs/libxfs/xfs_defer.h
index b2675f1ca909..2584a5b95b0d 100644
--- a/fs/xfs/libxfs/xfs_defer.h
+++ b/fs/xfs/libxfs/xfs_defer.h
@@ -7,7 +7,6 @@
 #define	__XFS_DEFER_H__
 
 struct xfs_defer_op_type;
-struct xfs_defer_ops;
 
 /*
  * Save a log intent item and a list of extents, so that we can replay
@@ -40,7 +39,6 @@ void xfs_defer_add(struct xfs_trans *tp, enum xfs_defer_ops_type type,
 int xfs_defer_finish_noroll(struct xfs_trans **tp);
 int xfs_defer_finish(struct xfs_trans **tp);
 void xfs_defer_cancel(struct xfs_trans *);
-void xfs_defer_init(struct xfs_trans *tp, struct xfs_defer_ops *dop);
 void xfs_defer_move(struct xfs_trans *dtp, struct xfs_trans *stp);
 
 /* Description of a deferred type. */
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 4ea1fddb126f..229152cd1a24 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -424,7 +424,6 @@ xfs_dir_removename(
 	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
-	ASSERT(tp->t_dfops);
 	XFS_STATS_INC(dp->i_mount, xs_dir_remove);
 
 	args = kmem_zalloc(sizeof(*args), KM_SLEEP | KM_NOFS);
@@ -483,7 +482,6 @@ xfs_dir_replace(
 	int			v;		/* type-checking value */
 
 	ASSERT(S_ISDIR(VFS_I(dp)->i_mode));
-	ASSERT(tp->t_dfops);
 
 	rval = xfs_dir_ino_validate(tp->t_mountp, inum);
 	if (rval)
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index ba5acd03de94..c3e3f6b813d8 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -9,7 +9,6 @@
 #include "xfs_da_format.h"
 #include "xfs_da_btree.h"
 
-struct xfs_defer_ops;
 struct xfs_da_args;
 struct xfs_inode;
 struct xfs_mount;
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 79a3e61a6991..be2014520155 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -15,7 +15,6 @@
 struct xfs_dinode;
 struct xfs_inode;
 struct xfs_buf;
-struct xfs_defer_ops;
 struct xfs_bmbt_irec;
 struct xfs_inode_log_item;
 struct xfs_mount;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index cbceb320a2e7..38f405415b88 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -502,7 +502,6 @@ xfs_reflink_cancel_cow_blocks(
 			if (error)
 				break;
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
-			ASSERT((*tpp)->t_dfops);
 			ASSERT((*tpp)->t_firstblock == NULLFSBLOCK);
 
 			/* Free the CoW orphan record. */
@@ -678,7 +677,7 @@ xfs_reflink_end_cow(
 			goto prev_extent;
 
 		/* Unmap the old blocks in the data fork. */
-		ASSERT(tp->t_dfops && tp->t_firstblock == NULLFSBLOCK);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		rlen = del.br_blockcount;
 		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1);
 		if (error)
@@ -1021,7 +1020,7 @@ xfs_reflink_remap_extent(
 	/* Unmap the old blocks in the data fork. */
 	rlen = unmap_len;
 	while (rlen) {
-		ASSERT(tp->t_dfops && tp->t_firstblock == NULLFSBLOCK);
+		ASSERT(tp->t_firstblock == NULLFSBLOCK);
 		error = __xfs_bunmapi(tp, ip, destoff, &rlen, 0, 1);
 		if (error)
 			goto out_cancel;
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index fec9cfe3dfb4..ad315e83bc02 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2213,57 +2213,54 @@ DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range);
 
 /* deferred ops */
 struct xfs_defer_pending;
-struct xfs_defer_ops;
 
 DECLARE_EVENT_CLASS(xfs_defer_class,
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop,
-		 unsigned long caller_ip),
-	TP_ARGS(mp, dop, caller_ip),
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip),
+	TP_ARGS(tp, caller_ip),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(void *, dop)
+		__field(struct xfs_trans *, tp)
 		__field(char, committed)
 		__field(unsigned long, caller_ip)
 	),
 	TP_fast_assign(
-		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->dop = dop;
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->tp = tp;
 		__entry->caller_ip = caller_ip;
 	),
-	TP_printk("dev %d:%d ops %p caller %pS",
+	TP_printk("dev %d:%d tp %p caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->dop,
+		  __entry->tp,
 		  (char *)__entry->caller_ip)
 )
 #define DEFINE_DEFER_EVENT(name) \
 DEFINE_EVENT(xfs_defer_class, name, \
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, \
-		 unsigned long caller_ip), \
-	TP_ARGS(mp, dop, caller_ip))
+	TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), \
+	TP_ARGS(tp, caller_ip))
 
 DECLARE_EVENT_CLASS(xfs_defer_error_class,
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error),
-	TP_ARGS(mp, dop, error),
+	TP_PROTO(struct xfs_trans *tp, int error),
+	TP_ARGS(tp, error),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(void *, dop)
+		__field(struct xfs_trans *, tp)
 		__field(char, committed)
 		__field(int, error)
 	),
 	TP_fast_assign(
-		__entry->dev = mp ? mp->m_super->s_dev : 0;
-		__entry->dop = dop;
+		__entry->dev = tp->t_mountp->m_super->s_dev;
+		__entry->tp = tp;
 		__entry->error = error;
 	),
-	TP_printk("dev %d:%d ops %p err %d",
+	TP_printk("dev %d:%d tp %p err %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->dop,
+		  __entry->tp,
 		  __entry->error)
 )
 #define DEFINE_DEFER_ERROR_EVENT(name) \
 DEFINE_EVENT(xfs_defer_error_class, name, \
-	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_ops *dop, int error), \
-	TP_ARGS(mp, dop, error))
+	TP_PROTO(struct xfs_trans *tp, int error), \
+	TP_ARGS(tp, error))
 
 DECLARE_EVENT_CLASS(xfs_defer_pending_class,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp),
@@ -2382,7 +2379,6 @@ DEFINE_EVENT(xfs_map_extent_deferred_class, name, \
 		 xfs_exntst_t state), \
 	TP_ARGS(mp, agno, op, agbno, ino, whichfork, offset, len, state))
 
-DEFINE_DEFER_EVENT(xfs_defer_init);
 DEFINE_DEFER_EVENT(xfs_defer_cancel);
 DEFINE_DEFER_EVENT(xfs_defer_trans_roll);
 DEFINE_DEFER_EVENT(xfs_defer_trans_abort);
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 413e4138357f..bedc5a5133a5 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -100,6 +100,7 @@ xfs_trans_dup(
 	ntp->t_mountp = tp->t_mountp;
 	INIT_LIST_HEAD(&ntp->t_items);
 	INIT_LIST_HEAD(&ntp->t_busy);
+	INIT_LIST_HEAD(&ntp->t_dfops);
 	ntp->t_firstblock = NULLFSBLOCK;
 
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
@@ -120,12 +121,8 @@ xfs_trans_dup(
 	tp->t_rtx_res = tp->t_rtx_res_used;
 	ntp->t_pflags = tp->t_pflags;
 
-	/* copy the dfops pointer if it's external, otherwise move it */
-	xfs_defer_init(ntp, &ntp->t_dfops_internal);
-	if (tp->t_dfops != &tp->t_dfops_internal)
-		ntp->t_dfops = tp->t_dfops;
-	else
-		xfs_defer_move(ntp, tp);
+	/* move deferred ops over to the new tp */
+	xfs_defer_move(ntp, tp);
 
 	xfs_trans_dup_dqinfo(tp, ntp);
 
@@ -280,8 +277,8 @@ xfs_trans_alloc(
 	tp->t_mountp = mp;
 	INIT_LIST_HEAD(&tp->t_items);
 	INIT_LIST_HEAD(&tp->t_busy);
+	INIT_LIST_HEAD(&tp->t_dfops);
 	tp->t_firstblock = NULLFSBLOCK;
-	xfs_defer_init(tp, &tp->t_dfops_internal);
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
 	if (error) {
@@ -929,7 +926,7 @@ __xfs_trans_commit(
 	 * Finish deferred items on final commit. Only permanent transactions
 	 * should ever have deferred ops.
 	 */
-	WARN_ON_ONCE(!list_empty(&tp->t_dfops->dop_intake) &&
+	WARN_ON_ONCE(!list_empty(&tp->t_dfops) &&
 		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
 	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
 		error = xfs_defer_finish_noroll(&tp);
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 1cdc7c0ebeac..c3d278e96ad1 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -90,13 +90,10 @@ void	xfs_log_item_init(struct xfs_mount *mp, struct xfs_log_item *item,
 #define XFS_ITEM_FLUSHING	3
 
 /*
- * Deferred operations tracking structure.
+ * Deferred operation item relogging limits.
  */
 #define XFS_DEFER_OPS_NR_INODES	2	/* join up to two inodes */
 #define XFS_DEFER_OPS_NR_BUFS	2	/* join up to two buffers */
-struct xfs_defer_ops {
-	struct list_head	dop_intake;	/* unlogged pending work */
-};
 
 /*
  * This is the structure maintained for every active transaction.
@@ -114,7 +111,6 @@ typedef struct xfs_trans {
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
-	struct xfs_defer_ops	*t_dfops;	/* dfops reference */
 	int64_t			t_icount_delta;	/* superblock icount change */
 	int64_t			t_ifree_delta;	/* superblock ifree change */
 	int64_t			t_fdblocks_delta; /* superblock fdblocks chg */
@@ -136,8 +132,8 @@ typedef struct xfs_trans {
 	int64_t			t_rextslog_delta;/* superblocks rextslog chg */
 	struct list_head	t_items;	/* log item descriptors */
 	struct list_head	t_busy;		/* list of busy extents */
+	struct list_head	t_dfops;	/* deferred operations */
 	unsigned long		t_pflags;	/* saved process flags state */
-	struct xfs_defer_ops	t_dfops_internal;
 } xfs_trans_t;
 
 /*
-- 
cgit v1.2.3


From c2b6e1591b6b15e1dcd9c1596b0371b6abc48fed Mon Sep 17 00:00:00 2001
From: Thomas Bianchi <thomas.bianchi8@gmail.com>
Date: Wed, 1 Aug 2018 12:58:34 -0700
Subject: xfs: substitute spaces with tabs

Inside xfs_attr_shortform_list removes spaces at the beginnig of the line
and replaces with tabs.
Issue found by checkpatch.

ERROR: code indent should use tabs where possible

Signed-off-by: Thomas Bianchi <thomas.bianchi8@gmail.com>
Reviewed-by: Bill O'Donnell <billodo@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_attr_list.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index f9ca80154c9c..a58034049995 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -87,7 +87,7 @@ xfs_attr_shortform_list(xfs_attr_list_context_t *context)
 	 */
 	if (context->bufsize == 0 ||
 	    (XFS_ISRESET_CURSOR(cursor) &&
-             (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
+	     (dp->i_afp->if_bytes + sf->hdr.count * 16) < context->bufsize)) {
 		for (i = 0, sfe = &sf->list[0]; i < sf->hdr.count; i++) {
 			context->put_listent(context,
 					     sfe->flags,
-- 
cgit v1.2.3


From 0069fb854364da79fd99236ea620affc8e1152d5 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Thu, 2 Aug 2018 15:47:10 -0700
Subject: selftests/bpf: fix a typo in map in map test

Commit fbeb1603bf4e ("bpf: verifier: MOV64 don't mark dst reg unbounded")
revealed a typo in commit fb30d4b71214 ("bpf: Add tests for map-in-map"):
BPF_MOV64_REG(BPF_REG_0, 0) was used instead of
BPF_MOV64_IMM(BPF_REG_0, 0).

I've noticed the problem by running bpf kselftests.

Fixes: fb30d4b71214 ("bpf: Add tests for map-in-map")
Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Arthur Fabre <afabre@cloudflare.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Alexei Starovoitov <ast@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_verifier.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 4b5e03c25204..ac281ee771dd 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -7113,7 +7113,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 				     BPF_FUNC_map_lookup_elem),
-			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map_in_map = { 3 },
@@ -7136,7 +7136,7 @@ static struct bpf_test tests[] = {
 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 				     BPF_FUNC_map_lookup_elem),
-			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map_in_map = { 3 },
@@ -7158,7 +7158,7 @@ static struct bpf_test tests[] = {
 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
 				     BPF_FUNC_map_lookup_elem),
-			BPF_MOV64_REG(BPF_REG_0, 0),
+			BPF_MOV64_IMM(BPF_REG_0, 0),
 			BPF_EXIT_INSN(),
 		},
 		.fixup_map_in_map = { 3 },
-- 
cgit v1.2.3


From 1313bccf00f6dfef99724d58e4416281b71e7189 Mon Sep 17 00:00:00 2001
From: Amit K Bag <amit.k.bag@intel.com>
Date: Fri, 3 Aug 2018 12:43:20 +0530
Subject: Bluetooth: btusb: Release RF resource on BT shutdown

Issue description: Intel 7265 shares the same RF with Wifi and BT.
In the shutdown scenario turn off BT, followed by turn WiFi off
and on causing error in RF calibration in WiFi Module

Solution: before shutdown BT ensure any RF activity to clear by
HCI reset command.

Reference Logs:
ERR kernel: [ 386.193284] iwlwifi 0000:01:00.0: Failed to run INIT calibrations: -5
ERR kernel: [ 386.193298] iwlwifi 0000:01:00.0: Failed to run INIT ucode: -5
ERR kernel: [ 386.193309] iwlwifi 0000:01:00.0: Failed to start RT ucode: -5

Signed-off-by: Amit K Bag <amit.k.bag@intel.com>
Singed-off-by: Chethan T N <chethan.tumkur.narayan@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btusb.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 572fd75fbcf6..f99fc6bfd1da 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2369,6 +2369,22 @@ static int btusb_shutdown_intel(struct hci_dev *hdev)
 	struct sk_buff *skb;
 	long ret;
 
+	/* In the shutdown sequence where Bluetooth is turned off followed
+	 * by WiFi being turned off, turning WiFi back on causes issue with
+	 * the RF calibration.
+	 *
+	 * To ensure that any RF activity has been stopped, issue HCI Reset
+	 * command to clear all ongoing activity including advertising,
+	 * scanning etc.
+	 */
+	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		bt_dev_err(hdev, "HCI reset during shutdown failed");
+		return ret;
+	}
+	kfree_skb(skb);
+
 	/* Some platforms have an issue with BT LED when the interface is
 	 * down or BT radio is turned off, which takes 5 seconds to BT LED
 	 * goes off. This command turns off the BT LED immediately.
-- 
cgit v1.2.3


From 26a6dce8ef99b0199e7682d1c203cf7d0b5fd5b0 Mon Sep 17 00:00:00 2001
From: Yong Zhi <yong.zhi@intel.com>
Date: Thu, 2 Aug 2018 18:21:31 -0500
Subject: ASoC: Intel: bxt: Use refcap device for mono recording

The refcap capture device supports mono recording only, this patch
adds the channel constraints.

Signed-off-by: Yong Zhi <yong.zhi@intel.com>
Reviewed-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/bxt_da7219_max98357a.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/sound/soc/intel/boards/bxt_da7219_max98357a.c b/sound/soc/intel/boards/bxt_da7219_max98357a.c
index be6e4b40bf03..6f052fc8d1e2 100644
--- a/sound/soc/intel/boards/bxt_da7219_max98357a.c
+++ b/sound/soc/intel/boards/bxt_da7219_max98357a.c
@@ -324,8 +324,22 @@ static const struct snd_pcm_hw_constraint_list constraints_16000 = {
 	.list  = rates_16000,
 };
 
+static const unsigned int ch_mono[] = {
+	1,
+};
+
+static const struct snd_pcm_hw_constraint_list constraints_refcap = {
+	.count = ARRAY_SIZE(ch_mono),
+	.list  = ch_mono,
+};
+
 static int broxton_refcap_startup(struct snd_pcm_substream *substream)
 {
+	substream->runtime->hw.channels_max = 1;
+	snd_pcm_hw_constraint_list(substream->runtime, 0,
+				   SNDRV_PCM_HW_PARAM_CHANNELS,
+				   &constraints_refcap);
+
 	return snd_pcm_hw_constraint_list(substream->runtime, 0,
 			SNDRV_PCM_HW_PARAM_RATE,
 			&constraints_16000);
-- 
cgit v1.2.3


From 401c0d7712eb3189023efc9c0708a2ac984ed62e Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Fri, 3 Aug 2018 11:50:39 +0200
Subject: spi: spi-mem: Constify spi_mem->name

There is no reason to make spi_mem->name modifiable. Moreover,
spi_mem_ops->get_name() returns a const char *, which generates a gcc
warning when assigning the value returned by spi_mem_ops->get_name()
to spi_mem->name.

Fixes: 5d27a9c8ea9e ("spi: spi-mem: Extend the SPI mem interface to set a custom memory name")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi-mem.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index 0d64ccc4e584..62722fb7472d 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -134,7 +134,7 @@ struct spi_mem_op {
 struct spi_mem {
 	struct spi_device *spi;
 	void *drvpriv;
-	char *name;
+	const char *name;
 };
 
 /**
-- 
cgit v1.2.3


From 43490e8046b5d273eb82710b04290c5997138adc Mon Sep 17 00:00:00 2001
From: Stephan Müller <smueller@chronox.de>
Date: Fri, 20 Jul 2018 19:42:01 +0200
Subject: crypto: drbg - in-place cipher operation for CTR

The cipher implementations of the kernel crypto API favor in-place
cipher operations. Thus, switch the CTR cipher operation in the DRBG to
perform in-place operations. This is implemented by using the output
buffer as input buffer and zeroizing it before the cipher operation to
implement a CTR encryption of a NULL buffer.

The speed improvement is quite visibile with the following comparison
using the LRNG implementation.

Without the patch set:

      16 bytes|           12.267661 MB/s|    61338304 bytes |  5000000213 ns
      32 bytes|           23.603770 MB/s|   118018848 bytes |  5000000073 ns
      64 bytes|           46.732262 MB/s|   233661312 bytes |  5000000241 ns
     128 bytes|           90.038042 MB/s|   450190208 bytes |  5000000244 ns
     256 bytes|          160.399616 MB/s|   801998080 bytes |  5000000393 ns
     512 bytes|          259.878400 MB/s|  1299392000 bytes |  5000001675 ns
    1024 bytes|          386.050662 MB/s|  1930253312 bytes |  5000001661 ns
    2048 bytes|          493.641728 MB/s|  2468208640 bytes |  5000001598 ns
    4096 bytes|          581.835981 MB/s|  2909179904 bytes |  5000003426 ns

With the patch set:

      16 bytes |         17.051142 MB/s |     85255712 bytes |  5000000854 ns
      32 bytes |         32.695898 MB/s |    163479488 bytes |  5000000544 ns
      64 bytes |         64.490739 MB/s |    322453696 bytes |  5000000954 ns
     128 bytes |        123.285043 MB/s |    616425216 bytes |  5000000201 ns
     256 bytes |        233.434573 MB/s |   1167172864 bytes |  5000000573 ns
     512 bytes |        384.405197 MB/s |   1922025984 bytes |  5000000671 ns
    1024 bytes |        566.313370 MB/s |   2831566848 bytes |  5000001080 ns
    2048 bytes |        744.518042 MB/s |   3722590208 bytes |  5000000926 ns
    4096 bytes |        867.501670 MB/s |   4337508352 bytes |  5000002181 ns

Signed-off-by: Stephan Mueller <smueller@chronox.de>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/drbg.c         | 34 ++++++++++++++--------------------
 include/crypto/drbg.h |  2 --
 2 files changed, 14 insertions(+), 22 deletions(-)

diff --git a/crypto/drbg.c b/crypto/drbg.c
index ee302fd229ad..bc52d9562611 100644
--- a/crypto/drbg.c
+++ b/crypto/drbg.c
@@ -261,8 +261,7 @@ static int drbg_fini_sym_kernel(struct drbg_state *drbg);
 static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 			      u8 *inbuf, u32 inbuflen,
 			      u8 *outbuf, u32 outlen);
-#define DRBG_CTR_NULL_LEN 128
-#define DRBG_OUTSCRATCHLEN DRBG_CTR_NULL_LEN
+#define DRBG_OUTSCRATCHLEN 256
 
 /* BCC function for CTR DRBG as defined in 10.4.3 */
 static int drbg_ctr_bcc(struct drbg_state *drbg,
@@ -555,8 +554,7 @@ static int drbg_ctr_generate(struct drbg_state *drbg,
 	}
 
 	/* 10.2.1.5.2 step 4.1 */
-	ret = drbg_kcapi_sym_ctr(drbg, drbg->ctr_null_value, DRBG_CTR_NULL_LEN,
-				 buf, len);
+	ret = drbg_kcapi_sym_ctr(drbg, NULL, 0, buf, len);
 	if (ret)
 		return ret;
 
@@ -1644,9 +1642,6 @@ static int drbg_fini_sym_kernel(struct drbg_state *drbg)
 		skcipher_request_free(drbg->ctr_req);
 	drbg->ctr_req = NULL;
 
-	kfree(drbg->ctr_null_value_buf);
-	drbg->ctr_null_value = NULL;
-
 	kfree(drbg->outscratchpadbuf);
 	drbg->outscratchpadbuf = NULL;
 
@@ -1697,15 +1692,6 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg)
 					crypto_req_done, &drbg->ctr_wait);
 
 	alignmask = crypto_skcipher_alignmask(sk_tfm);
-	drbg->ctr_null_value_buf = kzalloc(DRBG_CTR_NULL_LEN + alignmask,
-					   GFP_KERNEL);
-	if (!drbg->ctr_null_value_buf) {
-		drbg_fini_sym_kernel(drbg);
-		return -ENOMEM;
-	}
-	drbg->ctr_null_value = (u8 *)PTR_ALIGN(drbg->ctr_null_value_buf,
-					       alignmask + 1);
-
 	drbg->outscratchpadbuf = kmalloc(DRBG_OUTSCRATCHLEN + alignmask,
 					 GFP_KERNEL);
 	if (!drbg->outscratchpadbuf) {
@@ -1716,7 +1702,7 @@ static int drbg_init_sym_kernel(struct drbg_state *drbg)
 					      alignmask + 1);
 
 	sg_init_table(&drbg->sg_in, 1);
-	sg_init_table(&drbg->sg_out, 1);
+	sg_init_one(&drbg->sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN);
 
 	return alignmask;
 }
@@ -1747,10 +1733,18 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 			      u8 *outbuf, u32 outlen)
 {
 	struct scatterlist *sg_in = &drbg->sg_in, *sg_out = &drbg->sg_out;
+	u32 scratchpad_use = min_t(u32, outlen, DRBG_OUTSCRATCHLEN);
 	int ret;
 
-	sg_set_buf(sg_in, inbuf, inlen);
-	sg_set_buf(sg_out, drbg->outscratchpad, DRBG_OUTSCRATCHLEN);
+	if (inbuf) {
+		/* Use caller-provided input buffer */
+		sg_set_buf(sg_in, inbuf, inlen);
+	} else {
+		/* Use scratchpad for in-place operation */
+		inlen = scratchpad_use;
+		memset(drbg->outscratchpad, 0, scratchpad_use);
+		sg_set_buf(sg_in, drbg->outscratchpad, scratchpad_use);
+	}
 
 	while (outlen) {
 		u32 cryptlen = min3(inlen, outlen, (u32)DRBG_OUTSCRATCHLEN);
@@ -1766,6 +1760,7 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 		crypto_init_wait(&drbg->ctr_wait);
 
 		memcpy(outbuf, drbg->outscratchpad, cryptlen);
+		memzero_explicit(drbg->outscratchpad, cryptlen);
 
 		outlen -= cryptlen;
 		outbuf += cryptlen;
@@ -1773,7 +1768,6 @@ static int drbg_kcapi_sym_ctr(struct drbg_state *drbg,
 	ret = 0;
 
 out:
-	memzero_explicit(drbg->outscratchpad, DRBG_OUTSCRATCHLEN);
 	return ret;
 }
 #endif /* CONFIG_CRYPTO_DRBG_CTR */
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 54b9f5d375f5..3fb581bf3b87 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -122,8 +122,6 @@ struct drbg_state {
 
 	struct crypto_skcipher *ctr_handle;	/* CTR mode cipher handle */
 	struct skcipher_request *ctr_req;	/* CTR mode request handle */
-	__u8 *ctr_null_value_buf;		/* CTR mode unaligned buffer */
-	__u8 *ctr_null_value;			/* CTR mode aligned zero buf */
 	__u8 *outscratchpadbuf;			/* CTR mode output scratchpad */
         __u8 *outscratchpad;			/* CTR mode aligned outbuf */
 	struct crypto_wait ctr_wait;		/* CTR mode async wait obj */
-- 
cgit v1.2.3


From 1c96dde100987149f42bd6dd97013f7c421f27c7 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 16:14:26 +0800
Subject: crypto: cavium/nitrox - Replace GFP_ATOMIC with GFP_KERNEL in
 crypto_alloc_context()

crypto_alloc_context() is only called by nitrox_skcipher_init(), which is
never called in atomic context.

crypto_alloc_context() calls dma_pool_alloc() with GFP_ATOMIC,
which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/cavium/nitrox/nitrox_lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/cavium/nitrox/nitrox_lib.c b/drivers/crypto/cavium/nitrox/nitrox_lib.c
index 4fdc921ba611..ebe267379ac9 100644
--- a/drivers/crypto/cavium/nitrox/nitrox_lib.c
+++ b/drivers/crypto/cavium/nitrox/nitrox_lib.c
@@ -148,7 +148,7 @@ void *crypto_alloc_context(struct nitrox_device *ndev)
 	void *vaddr;
 	dma_addr_t dma;
 
-	vaddr = dma_pool_alloc(ndev->ctx_pool, (GFP_ATOMIC | __GFP_ZERO), &dma);
+	vaddr = dma_pool_alloc(ndev->ctx_pool, (GFP_KERNEL | __GFP_ZERO), &dma);
 	if (!vaddr)
 		return NULL;
 
-- 
cgit v1.2.3


From 8e8c0386b1fdd495173f085c8f58926d2a181c1c Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 16:27:44 +0800
Subject: crypto: qat/adf_aer - Replace GFP_ATOMIC with GFP_KERNEL in
 adf_dev_aer_schedule_reset()

adf_dev_aer_schedule_reset() is never called in atomic context, as it
calls wait_for_completion_timeout().

adf_dev_aer_schedule_reset() calls kzalloc() with GFP_ATOMIC,
which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/qat/qat_common/adf_aer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index da8a2d3b5e9a..9225d060e18f 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -163,7 +163,7 @@ static int adf_dev_aer_schedule_reset(struct adf_accel_dev *accel_dev,
 		return 0;
 
 	set_bit(ADF_STATUS_RESTARTING, &accel_dev->status);
-	reset_data = kzalloc(sizeof(*reset_data), GFP_ATOMIC);
+	reset_data = kzalloc(sizeof(*reset_data), GFP_KERNEL);
 	if (!reset_data)
 		return -ENOMEM;
 	reset_data->accel_dev = accel_dev;
-- 
cgit v1.2.3


From f6adeef77e0724b695fa2b4a655936bb04df075c Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Mon, 23 Jul 2018 16:43:46 +0800
Subject: crypto: virtio - Replace GFP_ATOMIC with GFP_KERNEL in
 __virtio_crypto_ablkcipher_do_req()

__virtio_crypto_ablkcipher_do_req() is never called in atomic context.

__virtio_crypto_ablkcipher_do_req() is only called by
virtio_crypto_ablkcipher_crypt_req(), which is only called by
virtcrypto_find_vqs() that is never called in atomic context.

__virtio_crypto_ablkcipher_do_req() calls kzalloc_node() with GFP_ATOMIC,
which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.
I also manually check the kernel code before reporting it.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/virtio/virtio_crypto_algs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/virtio/virtio_crypto_algs.c b/drivers/crypto/virtio/virtio_crypto_algs.c
index 7a104f636f11..2c573d1aaa64 100644
--- a/drivers/crypto/virtio/virtio_crypto_algs.c
+++ b/drivers/crypto/virtio/virtio_crypto_algs.c
@@ -383,12 +383,12 @@ __virtio_crypto_ablkcipher_do_req(struct virtio_crypto_sym_request *vc_sym_req,
 
 	/* Why 3?  outhdr + iv + inhdr */
 	sg_total = src_nents + dst_nents + 3;
-	sgs = kcalloc_node(sg_total, sizeof(*sgs), GFP_ATOMIC,
+	sgs = kcalloc_node(sg_total, sizeof(*sgs), GFP_KERNEL,
 				dev_to_node(&vcrypto->vdev->dev));
 	if (!sgs)
 		return -ENOMEM;
 
-	req_data = kzalloc_node(sizeof(*req_data), GFP_ATOMIC,
+	req_data = kzalloc_node(sizeof(*req_data), GFP_KERNEL,
 				dev_to_node(&vcrypto->vdev->dev));
 	if (!req_data) {
 		kfree(sgs);
-- 
cgit v1.2.3


From 2af632996b898687d382f2b52e820141aba72d63 Mon Sep 17 00:00:00 2001
From: Horia Geantă <horia.geanta@nxp.com>
Date: Mon, 23 Jul 2018 17:18:48 +0300
Subject: crypto: tcrypt - reschedule during speed tests
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Avoid RCU stalls in the case of non-preemptible kernel and lengthy
speed tests by rescheduling when advancing from one block size
to another.

Signed-off-by: Horia Geantă <horia.geanta@nxp.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/tcrypt.c | 36 ++++++++++++++++++++++++------------
 1 file changed, 24 insertions(+), 12 deletions(-)

diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 078ec36007bf..bdde95e8d369 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -415,12 +415,14 @@ static void test_mb_aead_speed(const char *algo, int enc, int secs,
 
 			}
 
-			if (secs)
+			if (secs) {
 				ret = test_mb_aead_jiffies(data, enc, *b_size,
 							   secs, num_mb);
-			else
+				cond_resched();
+			} else {
 				ret = test_mb_aead_cycles(data, enc, *b_size,
 							  num_mb);
+			}
 
 			if (ret) {
 				pr_err("%s() failed return code=%d\n", e, ret);
@@ -660,11 +662,13 @@ static void test_aead_speed(const char *algo, int enc, unsigned int secs,
 					       *b_size + (enc ? 0 : authsize),
 					       iv);
 
-			if (secs)
+			if (secs) {
 				ret = test_aead_jiffies(req, enc, *b_size,
 							secs);
-			else
+				cond_resched();
+			} else {
 				ret = test_aead_cycles(req, enc, *b_size);
+			}
 
 			if (ret) {
 				pr_err("%s() failed return code=%d\n", e, ret);
@@ -876,11 +880,13 @@ static void test_mb_ahash_speed(const char *algo, unsigned int secs,
 			i, speed[i].blen, speed[i].plen,
 			speed[i].blen / speed[i].plen);
 
-		if (secs)
+		if (secs) {
 			ret = test_mb_ahash_jiffies(data, speed[i].blen, secs,
 						    num_mb);
-		else
+			cond_resched();
+		} else {
 			ret = test_mb_ahash_cycles(data, speed[i].blen, num_mb);
+		}
 
 
 		if (ret) {
@@ -1103,12 +1109,14 @@ static void test_ahash_speed_common(const char *algo, unsigned int secs,
 
 		ahash_request_set_crypt(req, sg, output, speed[i].plen);
 
-		if (secs)
+		if (secs) {
 			ret = test_ahash_jiffies(req, speed[i].blen,
 						 speed[i].plen, output, secs);
-		else
+			cond_resched();
+		} else {
 			ret = test_ahash_cycles(req, speed[i].blen,
 						speed[i].plen, output);
+		}
 
 		if (ret) {
 			pr_err("hashing failed ret=%d\n", ret);
@@ -1367,13 +1375,15 @@ static void test_mb_skcipher_speed(const char *algo, int enc, int secs,
 							   iv);
 			}
 
-			if (secs)
+			if (secs) {
 				ret = test_mb_acipher_jiffies(data, enc,
 							      *b_size, secs,
 							      num_mb);
-			else
+				cond_resched();
+			} else {
 				ret = test_mb_acipher_cycles(data, enc,
 							     *b_size, num_mb);
+			}
 
 			if (ret) {
 				pr_err("%s() failed flags=%x\n", e,
@@ -1581,12 +1591,14 @@ static void test_skcipher_speed(const char *algo, int enc, unsigned int secs,
 
 			skcipher_request_set_crypt(req, sg, sg, *b_size, iv);
 
-			if (secs)
+			if (secs) {
 				ret = test_acipher_jiffies(req, enc,
 							   *b_size, secs);
-			else
+				cond_resched();
+			} else {
 				ret = test_acipher_cycles(req, enc,
 							  *b_size);
+			}
 
 			if (ret) {
 				pr_err("%s() failed flags=%x\n", e,
-- 
cgit v1.2.3


From 778bd9924dba13d4816cbf73f9ae1519fe445a25 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Mon, 23 Jul 2018 16:49:53 +0100
Subject: dt-bindings: Add bindings for Hisilicon SEC crypto accelerators.

The hip06 and hip07 SoCs contain a number of these crypto units which
accelerate AES and DES operations.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 .../bindings/crypto/hisilicon,hip07-sec.txt        | 67 ++++++++++++++++++++++
 1 file changed, 67 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/crypto/hisilicon,hip07-sec.txt

diff --git a/Documentation/devicetree/bindings/crypto/hisilicon,hip07-sec.txt b/Documentation/devicetree/bindings/crypto/hisilicon,hip07-sec.txt
new file mode 100644
index 000000000000..78d2db9d4de5
--- /dev/null
+++ b/Documentation/devicetree/bindings/crypto/hisilicon,hip07-sec.txt
@@ -0,0 +1,67 @@
+* Hisilicon hip07 Security Accelerator (SEC)
+
+Required properties:
+- compatible: Must contain one of
+  - "hisilicon,hip06-sec"
+  - "hisilicon,hip07-sec"
+- reg: Memory addresses and lengths of the memory regions through which
+  this device is controlled.
+  Region 0 has registers to control the backend processing engines.
+  Region 1 has registers for functionality common to all queues.
+  Regions 2-18 have registers for the 16 individual queues which are isolated
+  both in hardware and within the driver.
+- interrupts: Interrupt specifiers.
+  Refer to interrupt-controller/interrupts.txt for generic interrupt client node
+  bindings.
+  Interrupt 0 is for the SEC unit error queue.
+  Interrupt 2N + 1 is the completion interrupt for queue N.
+  Interrupt 2N + 2 is the error interrupt for queue N.
+- dma-coherent:  The driver assumes coherent dma is possible.
+
+Optional properties:
+- iommus: The SEC units are behind smmu-v3 iommus.
+  Refer to iommu/arm,smmu-v3.txt for more information.
+
+Example:
+
+p1_sec_a: crypto@400,d2000000 {
+	compatible = "hisilicon,hip07-sec";
+	reg = <0x400 0xd0000000 0x0 0x10000
+	       0x400 0xd2000000 0x0 0x10000
+	       0x400 0xd2010000 0x0 0x10000
+	       0x400 0xd2020000 0x0 0x10000
+	       0x400 0xd2030000 0x0 0x10000
+	       0x400 0xd2040000 0x0 0x10000
+	       0x400 0xd2050000 0x0 0x10000
+	       0x400 0xd2060000 0x0 0x10000
+	       0x400 0xd2070000 0x0 0x10000
+	       0x400 0xd2080000 0x0 0x10000
+	       0x400 0xd2090000 0x0 0x10000
+	       0x400 0xd20a0000 0x0 0x10000
+	       0x400 0xd20b0000 0x0 0x10000
+	       0x400 0xd20c0000 0x0 0x10000
+	       0x400 0xd20d0000 0x0 0x10000
+	       0x400 0xd20e0000 0x0 0x10000
+	       0x400 0xd20f0000 0x0 0x10000
+	       0x400 0xd2100000 0x0 0x10000>;
+	interrupt-parent = <&p1_mbigen_sec_a>;
+	iommus = <&p1_smmu_alg_a 0x600>;
+	dma-coherent;
+	interrupts = <576 4>,
+		     <577 1>, <578 4>,
+		     <579 1>, <580 4>,
+		     <581 1>, <582 4>,
+		     <583 1>, <584 4>,
+		     <585 1>, <586 4>,
+		     <587 1>, <588 4>,
+		     <589 1>, <590 4>,
+		     <591 1>, <592 4>,
+		     <593 1>, <594 4>,
+		     <595 1>, <596 4>,
+		     <597 1>, <598 4>,
+		     <599 1>, <600 4>,
+		     <601 1>, <602 4>,
+		     <603 1>, <604 4>,
+		     <605 1>, <606 4>,
+		     <607 1>, <608 4>;
+};
-- 
cgit v1.2.3


From 915e4e8413dacc086efcef4de04fdfdca57e8b1c Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Mon, 23 Jul 2018 16:49:54 +0100
Subject: crypto: hisilicon - SEC security accelerator driver

This accelerator is found inside hisilicon hip06 and hip07 SoCs.
Each instance provides a number of queues which feed a different number of
backend acceleration units.

The queues are operating in an out of order mode in the interests of
throughput. The silicon does not do tracking of dependencies between
multiple 'messages' or update of the IVs as appropriate for training.
Hence where relevant we need to do this in software.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/Kconfig                  |    2 +
 drivers/crypto/Makefile                 |    1 +
 drivers/crypto/hisilicon/Kconfig        |   14 +
 drivers/crypto/hisilicon/Makefile       |    2 +
 drivers/crypto/hisilicon/sec/Makefile   |    3 +
 drivers/crypto/hisilicon/sec/sec_algs.c | 1122 ++++++++++++++++++++++++++
 drivers/crypto/hisilicon/sec/sec_drv.c  | 1323 +++++++++++++++++++++++++++++++
 drivers/crypto/hisilicon/sec/sec_drv.h  |  428 ++++++++++
 8 files changed, 2895 insertions(+)
 create mode 100644 drivers/crypto/hisilicon/Kconfig
 create mode 100644 drivers/crypto/hisilicon/Makefile
 create mode 100644 drivers/crypto/hisilicon/sec/Makefile
 create mode 100644 drivers/crypto/hisilicon/sec/sec_algs.c
 create mode 100644 drivers/crypto/hisilicon/sec/sec_drv.c
 create mode 100644 drivers/crypto/hisilicon/sec/sec_drv.h

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 2bf799ba7674..a8c4ce07fc9d 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -759,4 +759,6 @@ config CRYPTO_DEV_CCREE
 	  cryptographic operations on the system REE.
 	  If unsure say Y.
 
+source "drivers/crypto/hisilicon/Kconfig"
+
 endif # CRYPTO_HW
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 3602875c4f80..c23396f32c8a 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -46,3 +46,4 @@ obj-$(CONFIG_CRYPTO_DEV_VMX) += vmx/
 obj-$(CONFIG_CRYPTO_DEV_BCM_SPU) += bcm/
 obj-$(CONFIG_CRYPTO_DEV_SAFEXCEL) += inside-secure/
 obj-$(CONFIG_CRYPTO_DEV_ARTPEC6) += axis/
+obj-y += hisilicon/
diff --git a/drivers/crypto/hisilicon/Kconfig b/drivers/crypto/hisilicon/Kconfig
new file mode 100644
index 000000000000..8ca9c503bcb0
--- /dev/null
+++ b/drivers/crypto/hisilicon/Kconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+
+config CRYPTO_DEV_HISI_SEC
+	tristate "Support for Hisilicon SEC crypto block cipher accelerator"
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_ALGAPI
+	select SG_SPLIT
+	depends on ARM64 || COMPILE_TEST
+	depends on HAS_IOMEM
+	help
+	  Support for Hisilicon SEC Engine in Hip06 and Hip07
+
+	  To compile this as a module, choose M here: the module
+	  will be called hisi_sec.
diff --git a/drivers/crypto/hisilicon/Makefile b/drivers/crypto/hisilicon/Makefile
new file mode 100644
index 000000000000..463f46ace182
--- /dev/null
+++ b/drivers/crypto/hisilicon/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += sec/
diff --git a/drivers/crypto/hisilicon/sec/Makefile b/drivers/crypto/hisilicon/sec/Makefile
new file mode 100644
index 000000000000..a55b698e0c27
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_CRYPTO_DEV_HISI_SEC) += hisi_sec.o
+hisi_sec-y = sec_algs.o sec_drv.o
diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c
new file mode 100644
index 000000000000..d69d3ce358b0
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/sec_algs.c
@@ -0,0 +1,1122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2016-2017 Hisilicon Limited. */
+#include <linux/crypto.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/slab.h>
+
+#include <crypto/aes.h>
+#include <crypto/algapi.h>
+#include <crypto/des.h>
+#include <crypto/skcipher.h>
+#include <crypto/xts.h>
+#include <crypto/internal/skcipher.h>
+
+#include "sec_drv.h"
+
+#define SEC_MAX_CIPHER_KEY		64
+#define SEC_REQ_LIMIT SZ_32M
+
+struct sec_c_alg_cfg {
+	unsigned c_alg		: 3;
+	unsigned c_mode		: 3;
+	unsigned key_len	: 2;
+	unsigned c_width	: 2;
+};
+
+static const struct sec_c_alg_cfg sec_c_alg_cfgs[] =  {
+	[SEC_C_DES_ECB_64] = {
+		.c_alg = SEC_C_ALG_DES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_DES,
+	},
+	[SEC_C_DES_CBC_64] = {
+		.c_alg = SEC_C_ALG_DES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_DES,
+	},
+	[SEC_C_3DES_ECB_192_3KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_3DES_3_KEY,
+	},
+	[SEC_C_3DES_ECB_192_2KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_3DES_2_KEY,
+	},
+	[SEC_C_3DES_CBC_192_3KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_3DES_3_KEY,
+	},
+	[SEC_C_3DES_CBC_192_2KEY] = {
+		.c_alg = SEC_C_ALG_3DES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_3DES_2_KEY,
+	},
+	[SEC_C_AES_ECB_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_ECB_192] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_AES_192,
+	},
+	[SEC_C_AES_ECB_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_ECB,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_AES_CBC_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_CBC_192] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_AES_192,
+	},
+	[SEC_C_AES_CBC_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CBC,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_AES_CTR_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CTR,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_CTR_192] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CTR,
+		.key_len = SEC_KEY_LEN_AES_192,
+	},
+	[SEC_C_AES_CTR_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_CTR,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_AES_XTS_128] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_XTS,
+		.key_len = SEC_KEY_LEN_AES_128,
+	},
+	[SEC_C_AES_XTS_256] = {
+		.c_alg = SEC_C_ALG_AES,
+		.c_mode = SEC_C_MODE_XTS,
+		.key_len = SEC_KEY_LEN_AES_256,
+	},
+	[SEC_C_NULL] = {
+	},
+};
+
+/*
+ * Mutex used to ensure safe operation of reference count of
+ * alg providers
+ */
+static DEFINE_MUTEX(algs_lock);
+static unsigned int active_devs;
+
+static void sec_alg_skcipher_init_template(struct sec_alg_tfm_ctx *ctx,
+					   struct sec_bd_info *req,
+					   enum sec_cipher_alg alg)
+{
+	const struct sec_c_alg_cfg *cfg = &sec_c_alg_cfgs[alg];
+
+	memset(req, 0, sizeof(*req));
+	req->w0 |= cfg->c_mode << SEC_BD_W0_C_MODE_S;
+	req->w1 |= cfg->c_alg << SEC_BD_W1_C_ALG_S;
+	req->w3 |= cfg->key_len << SEC_BD_W3_C_KEY_LEN_S;
+	req->w0 |= cfg->c_width << SEC_BD_W0_C_WIDTH_S;
+
+	req->cipher_key_addr_lo = lower_32_bits(ctx->pkey);
+	req->cipher_key_addr_hi = upper_32_bits(ctx->pkey);
+}
+
+static void sec_alg_skcipher_init_context(struct crypto_skcipher *atfm,
+					  const u8 *key,
+					  unsigned int keylen,
+					  enum sec_cipher_alg alg)
+{
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(atfm);
+	struct sec_alg_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	ctx->cipher_alg = alg;
+	memcpy(ctx->key, key, keylen);
+	sec_alg_skcipher_init_template(ctx, &ctx->req_template,
+				       ctx->cipher_alg);
+}
+
+static int sec_alloc_and_fill_hw_sgl(struct sec_hw_sgl **sec_sgl,
+				     dma_addr_t *psec_sgl,
+				     struct scatterlist *sgl,
+				     int count,
+				     struct sec_dev_info *info)
+{
+	struct sec_hw_sgl *sgl_current = NULL;
+	struct sec_hw_sgl *sgl_next;
+	dma_addr_t sgl_next_dma;
+	struct scatterlist *sg;
+	int ret, sge_index, i;
+
+	if (!count)
+		return -EINVAL;
+
+	for_each_sg(sgl, sg, count, i) {
+		sge_index = i % SEC_MAX_SGE_NUM;
+		if (sge_index == 0) {
+			sgl_next = dma_pool_zalloc(info->hw_sgl_pool,
+						   GFP_KERNEL, &sgl_next_dma);
+			if (!sgl_next) {
+				ret = -ENOMEM;
+				goto err_free_hw_sgls;
+			}
+
+			if (!sgl_current) { /* First one */
+				*psec_sgl = sgl_next_dma;
+				*sec_sgl = sgl_next;
+			} else { /* Chained */
+				sgl_current->entry_sum_in_sgl = SEC_MAX_SGE_NUM;
+				sgl_current->next_sgl = sgl_next_dma;
+				sgl_current->next = sgl_next;
+			}
+			sgl_current = sgl_next;
+		}
+		sgl_current->sge_entries[sge_index].buf = sg_dma_address(sg);
+		sgl_current->sge_entries[sge_index].len = sg_dma_len(sg);
+		sgl_current->data_bytes_in_sgl += sg_dma_len(sg);
+	}
+	sgl_current->entry_sum_in_sgl = count % SEC_MAX_SGE_NUM;
+	sgl_current->next_sgl = 0;
+	(*sec_sgl)->entry_sum_in_chain = count;
+
+	return 0;
+
+err_free_hw_sgls:
+	sgl_current = *sec_sgl;
+	while (sgl_current) {
+		sgl_next = sgl_current->next;
+		dma_pool_free(info->hw_sgl_pool, sgl_current,
+			      sgl_current->next_sgl);
+		sgl_current = sgl_next;
+	}
+	*psec_sgl = 0;
+
+	return ret;
+}
+
+static void sec_free_hw_sgl(struct sec_hw_sgl *hw_sgl,
+			    dma_addr_t psec_sgl, struct sec_dev_info *info)
+{
+	struct sec_hw_sgl *sgl_current, *sgl_next;
+
+	if (!hw_sgl)
+		return;
+	sgl_current = hw_sgl;
+	while (sgl_current->next) {
+		sgl_next = sgl_current->next;
+		dma_pool_free(info->hw_sgl_pool, sgl_current,
+			      sgl_current->next_sgl);
+		sgl_current = sgl_next;
+	}
+	dma_pool_free(info->hw_sgl_pool, hw_sgl, psec_sgl);
+}
+
+static int sec_alg_skcipher_setkey(struct crypto_skcipher *tfm,
+				   const u8 *key, unsigned int keylen,
+				   enum sec_cipher_alg alg)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct device *dev = ctx->queue->dev_info->dev;
+
+	mutex_lock(&ctx->lock);
+	if (ctx->key) {
+		/* rekeying */
+		memset(ctx->key, 0, SEC_MAX_CIPHER_KEY);
+	} else {
+		/* new key */
+		ctx->key = dma_zalloc_coherent(dev, SEC_MAX_CIPHER_KEY,
+					       &ctx->pkey, GFP_KERNEL);
+		if (!ctx->key) {
+			mutex_unlock(&ctx->lock);
+			return -ENOMEM;
+		}
+	}
+	mutex_unlock(&ctx->lock);
+	sec_alg_skcipher_init_context(tfm, key, keylen, alg);
+
+	return 0;
+}
+
+static int sec_alg_skcipher_setkey_aes_ecb(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		alg = SEC_C_AES_ECB_128;
+		break;
+	case AES_KEYSIZE_192:
+		alg = SEC_C_AES_ECB_192;
+		break;
+	case AES_KEYSIZE_256:
+		alg = SEC_C_AES_ECB_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_aes_cbc(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		alg = SEC_C_AES_CBC_128;
+		break;
+	case AES_KEYSIZE_192:
+		alg = SEC_C_AES_CBC_192;
+		break;
+	case AES_KEYSIZE_256:
+		alg = SEC_C_AES_CBC_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_aes_ctr(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128:
+		alg = SEC_C_AES_CTR_128;
+		break;
+	case AES_KEYSIZE_192:
+		alg = SEC_C_AES_CTR_192;
+		break;
+	case AES_KEYSIZE_256:
+		alg = SEC_C_AES_CTR_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_aes_xts(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	enum sec_cipher_alg alg;
+	int ret;
+
+	ret = xts_verify_key(tfm, key, keylen);
+	if (ret)
+		return ret;
+
+	switch (keylen) {
+	case AES_KEYSIZE_128 * 2:
+		alg = SEC_C_AES_XTS_128;
+		break;
+	case AES_KEYSIZE_256 * 2:
+		alg = SEC_C_AES_XTS_256;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, alg);
+}
+
+static int sec_alg_skcipher_setkey_des_ecb(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES_KEY_SIZE)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_ECB_64);
+}
+
+static int sec_alg_skcipher_setkey_des_cbc(struct crypto_skcipher *tfm,
+					   const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES_KEY_SIZE)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen, SEC_C_DES_CBC_64);
+}
+
+static int sec_alg_skcipher_setkey_3des_ecb(struct crypto_skcipher *tfm,
+					    const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES_KEY_SIZE * 3)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen,
+				       SEC_C_3DES_ECB_192_3KEY);
+}
+
+static int sec_alg_skcipher_setkey_3des_cbc(struct crypto_skcipher *tfm,
+					    const u8 *key, unsigned int keylen)
+{
+	if (keylen != DES3_EDE_KEY_SIZE)
+		return -EINVAL;
+
+	return sec_alg_skcipher_setkey(tfm, key, keylen,
+				       SEC_C_3DES_CBC_192_3KEY);
+}
+
+static void sec_alg_free_el(struct sec_request_el *el,
+			    struct sec_dev_info *info)
+{
+	sec_free_hw_sgl(el->out, el->dma_out, info);
+	sec_free_hw_sgl(el->in, el->dma_in, info);
+	kfree(el->sgl_in);
+	kfree(el->sgl_out);
+	kfree(el);
+}
+
+/* queuelock must be held */
+int sec_send_request(struct sec_request *sec_req, struct sec_queue *queue)
+{
+	struct sec_request_el *el, *temp;
+	int ret = 0;
+
+	mutex_lock(&sec_req->lock);
+	list_for_each_entry_safe(el, temp, &sec_req->elements, head) {
+		/*
+		 * Add to hardware queue only under following circumstances
+		 * 1) Software and hardware queue empty so no chain dependencies
+		 * 2) No dependencies as new IV - (check software queue empty
+		 *    to maintain order)
+		 * 3) No dependencies because the mode does no chaining.
+		 *
+		 * In other cases first insert onto the software queue which
+		 * is then emptied as requests complete
+		 */
+		if (!queue->havesoftqueue ||
+		    (kfifo_is_empty(&queue->softqueue) &&
+		     sec_queue_empty(queue))) {
+			ret = sec_queue_send(queue, &el->req, sec_req);
+			if (ret == -EAGAIN) {
+				/* Wait unti we can send then try again */
+				/* DEAD if here - should not happen */
+				ret = -EBUSY;
+				goto err_unlock;
+			}
+		} else {
+			kfifo_put(&queue->softqueue, el);
+		}
+	}
+err_unlock:
+	mutex_unlock(&sec_req->lock);
+
+	return ret;
+}
+
+static void sec_skcipher_alg_callback(struct sec_bd_info *sec_resp,
+				      struct crypto_async_request *req_base)
+{
+	struct skcipher_request *skreq = container_of(req_base,
+						      struct skcipher_request,
+						      base);
+	struct sec_request *sec_req = skcipher_request_ctx(skreq);
+	struct sec_request *backlog_req;
+	struct sec_request_el *sec_req_el, *nextrequest;
+	struct sec_alg_tfm_ctx *ctx = sec_req->tfm_ctx;
+	struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(skreq);
+	struct device *dev = ctx->queue->dev_info->dev;
+	int icv_or_skey_en, ret;
+	bool done;
+
+	sec_req_el = list_first_entry(&sec_req->elements, struct sec_request_el,
+				      head);
+	icv_or_skey_en = (sec_resp->w0 & SEC_BD_W0_ICV_OR_SKEY_EN_M) >>
+		SEC_BD_W0_ICV_OR_SKEY_EN_S;
+	if (sec_resp->w1 & SEC_BD_W1_BD_INVALID || icv_or_skey_en == 3) {
+		dev_err(dev, "Got an invalid answer %lu %d\n",
+			sec_resp->w1 & SEC_BD_W1_BD_INVALID,
+			icv_or_skey_en);
+		sec_req->err = -EINVAL;
+		/*
+		 * We need to muddle on to avoid getting stuck with elements
+		 * on the queue. Error will be reported so requester so
+		 * it should be able to handle appropriately.
+		 */
+	}
+
+	mutex_lock(&ctx->queue->queuelock);
+	/* Put the IV in place for chained cases */
+	switch (ctx->cipher_alg) {
+	case SEC_C_AES_CBC_128:
+	case SEC_C_AES_CBC_192:
+	case SEC_C_AES_CBC_256:
+		if (sec_req_el->req.w0 & SEC_BD_W0_DE)
+			sg_pcopy_to_buffer(sec_req_el->sgl_out,
+					   sg_nents(sec_req_el->sgl_out),
+					   skreq->iv,
+					   crypto_skcipher_ivsize(atfm),
+					   sec_req_el->el_length -
+					   crypto_skcipher_ivsize(atfm));
+		else
+			sg_pcopy_to_buffer(sec_req_el->sgl_in,
+					   sg_nents(sec_req_el->sgl_in),
+					   skreq->iv,
+					   crypto_skcipher_ivsize(atfm),
+					   sec_req_el->el_length -
+					   crypto_skcipher_ivsize(atfm));
+		/* No need to sync to the device as coherent DMA */
+		break;
+	case SEC_C_AES_CTR_128:
+	case SEC_C_AES_CTR_192:
+	case SEC_C_AES_CTR_256:
+		crypto_inc(skreq->iv, 16);
+		break;
+	default:
+		/* Do not update */
+		break;
+	}
+
+	if (ctx->queue->havesoftqueue &&
+	    !kfifo_is_empty(&ctx->queue->softqueue) &&
+	    sec_queue_empty(ctx->queue)) {
+		ret = kfifo_get(&ctx->queue->softqueue, &nextrequest);
+		if (ret <= 0)
+			dev_err(dev,
+				"Error getting next element from kfifo %d\n",
+				ret);
+		else
+			/* We know there is space so this cannot fail */
+			sec_queue_send(ctx->queue, &nextrequest->req,
+				       nextrequest->sec_req);
+	} else if (!list_empty(&ctx->backlog)) {
+		/* Need to verify there is room first */
+		backlog_req = list_first_entry(&ctx->backlog,
+					       typeof(*backlog_req),
+					       backlog_head);
+		if (sec_queue_can_enqueue(ctx->queue,
+		    backlog_req->num_elements) ||
+		    (ctx->queue->havesoftqueue &&
+		     kfifo_avail(&ctx->queue->softqueue) >
+		     backlog_req->num_elements)) {
+			sec_send_request(backlog_req, ctx->queue);
+			backlog_req->req_base->complete(backlog_req->req_base,
+							-EINPROGRESS);
+			list_del(&backlog_req->backlog_head);
+		}
+	}
+	mutex_unlock(&ctx->queue->queuelock);
+
+	mutex_lock(&sec_req->lock);
+	list_del(&sec_req_el->head);
+	mutex_unlock(&sec_req->lock);
+	sec_alg_free_el(sec_req_el, ctx->queue->dev_info);
+
+	/*
+	 * Request is done.
+	 * The dance is needed as the lock is freed in the completion
+	 */
+	mutex_lock(&sec_req->lock);
+	done = list_empty(&sec_req->elements);
+	mutex_unlock(&sec_req->lock);
+	if (done) {
+		if (crypto_skcipher_ivsize(atfm)) {
+			dma_unmap_single(dev, sec_req->dma_iv,
+					 crypto_skcipher_ivsize(atfm),
+					 DMA_TO_DEVICE);
+		}
+		dma_unmap_sg(dev, skreq->src, sec_req->len_in,
+			     DMA_BIDIRECTIONAL);
+		if (skreq->src != skreq->dst)
+			dma_unmap_sg(dev, skreq->dst, sec_req->len_out,
+				     DMA_BIDIRECTIONAL);
+		skreq->base.complete(&skreq->base, sec_req->err);
+	}
+}
+
+void sec_alg_callback(struct sec_bd_info *resp, void *shadow)
+{
+	struct sec_request *sec_req = shadow;
+
+	sec_req->cb(resp, sec_req->req_base);
+}
+
+static int sec_alg_alloc_and_calc_split_sizes(int length, size_t **split_sizes,
+					      int *steps)
+{
+	size_t *sizes;
+	int i;
+
+	/* Split into suitable sized blocks */
+	*steps = roundup(length, SEC_REQ_LIMIT) / SEC_REQ_LIMIT;
+	sizes = kcalloc(*steps, sizeof(*sizes), GFP_KERNEL);
+	if (!sizes)
+		return -ENOMEM;
+
+	for (i = 0; i < *steps - 1; i++)
+		sizes[i] = SEC_REQ_LIMIT;
+	sizes[*steps - 1] = length - SEC_REQ_LIMIT * (*steps - 1);
+	*split_sizes = sizes;
+
+	return 0;
+}
+
+static int sec_map_and_split_sg(struct scatterlist *sgl, size_t *split_sizes,
+				int steps, struct scatterlist ***splits,
+				int **splits_nents,
+				int sgl_len_in,
+				struct device *dev)
+{
+	int ret, count;
+
+	count = dma_map_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL);
+	if (!count)
+		return -EINVAL;
+
+	*splits = kcalloc(steps, sizeof(struct scatterlist *), GFP_KERNEL);
+	if (!*splits) {
+		ret = -ENOMEM;
+		goto err_unmap_sg;
+	}
+	*splits_nents = kcalloc(steps, sizeof(int), GFP_KERNEL);
+	if (!*splits_nents) {
+		ret = -ENOMEM;
+		goto err_free_splits;
+	}
+
+	/* output the scatter list before and after this */
+	ret = sg_split(sgl, count, 0, steps, split_sizes,
+		       *splits, *splits_nents, GFP_KERNEL);
+	if (ret) {
+		ret = -ENOMEM;
+		goto err_free_splits_nents;
+	}
+
+	return 0;
+
+err_free_splits_nents:
+	kfree(*splits_nents);
+err_free_splits:
+	kfree(*splits);
+err_unmap_sg:
+	dma_unmap_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL);
+
+	return ret;
+}
+
+/*
+ * Reverses the sec_map_and_split_sg call for messages not yet added to
+ * the queues.
+ */
+static void sec_unmap_sg_on_err(struct scatterlist *sgl, int steps,
+				struct scatterlist **splits, int *splits_nents,
+				int sgl_len_in, struct device *dev)
+{
+	int i;
+
+	for (i = 0; i < steps; i++)
+		kfree(splits[i]);
+	kfree(splits_nents);
+	kfree(splits);
+
+	dma_unmap_sg(dev, sgl, sgl_len_in, DMA_BIDIRECTIONAL);
+}
+
+static struct sec_request_el
+*sec_alg_alloc_and_fill_el(struct sec_bd_info *template, int encrypt,
+			   int el_size, bool different_dest,
+			   struct scatterlist *sgl_in, int n_ents_in,
+			   struct scatterlist *sgl_out, int n_ents_out,
+			   struct sec_dev_info *info)
+{
+	struct sec_request_el *el;
+	struct sec_bd_info *req;
+	int ret;
+
+	el = kzalloc(sizeof(*el), GFP_KERNEL);
+	if (!el)
+		return ERR_PTR(-ENOMEM);
+	el->el_length = el_size;
+	req = &el->req;
+	memcpy(req, template, sizeof(*req));
+
+	req->w0 &= ~SEC_BD_W0_CIPHER_M;
+	if (encrypt)
+		req->w0 |= SEC_CIPHER_ENCRYPT << SEC_BD_W0_CIPHER_S;
+	else
+		req->w0 |= SEC_CIPHER_DECRYPT << SEC_BD_W0_CIPHER_S;
+
+	req->w0 &= ~SEC_BD_W0_C_GRAN_SIZE_19_16_M;
+	req->w0 |= ((el_size >> 16) << SEC_BD_W0_C_GRAN_SIZE_19_16_S) &
+		SEC_BD_W0_C_GRAN_SIZE_19_16_M;
+
+	req->w0 &= ~SEC_BD_W0_C_GRAN_SIZE_21_20_M;
+	req->w0 |= ((el_size >> 20) << SEC_BD_W0_C_GRAN_SIZE_21_20_S) &
+		SEC_BD_W0_C_GRAN_SIZE_21_20_M;
+
+	/* Writing whole u32 so no need to take care of masking */
+	req->w2 = ((1 << SEC_BD_W2_GRAN_NUM_S) & SEC_BD_W2_GRAN_NUM_M) |
+		((el_size << SEC_BD_W2_C_GRAN_SIZE_15_0_S) &
+		 SEC_BD_W2_C_GRAN_SIZE_15_0_M);
+
+	req->w3 &= ~SEC_BD_W3_CIPHER_LEN_OFFSET_M;
+	req->w1 |= SEC_BD_W1_ADDR_TYPE;
+
+	el->sgl_in = sgl_in;
+
+	ret = sec_alloc_and_fill_hw_sgl(&el->in, &el->dma_in, el->sgl_in,
+					n_ents_in, info);
+	if (ret)
+		goto err_free_el;
+
+	req->data_addr_lo = lower_32_bits(el->dma_in);
+	req->data_addr_hi = upper_32_bits(el->dma_in);
+
+	if (different_dest) {
+		el->sgl_out = sgl_out;
+		ret = sec_alloc_and_fill_hw_sgl(&el->out, &el->dma_out,
+						el->sgl_out,
+						n_ents_out, info);
+		if (ret)
+			goto err_free_hw_sgl_in;
+
+		req->w0 |= SEC_BD_W0_DE;
+		req->cipher_destin_addr_lo = lower_32_bits(el->dma_out);
+		req->cipher_destin_addr_hi = upper_32_bits(el->dma_out);
+
+	} else {
+		req->w0 &= ~SEC_BD_W0_DE;
+		req->cipher_destin_addr_lo = lower_32_bits(el->dma_in);
+		req->cipher_destin_addr_hi = upper_32_bits(el->dma_in);
+	}
+
+	return el;
+
+err_free_hw_sgl_in:
+	sec_free_hw_sgl(el->in, el->dma_in, info);
+err_free_el:
+	kfree(el);
+
+	return ERR_PTR(ret);
+}
+
+static int sec_alg_skcipher_crypto(struct skcipher_request *skreq,
+				   bool encrypt)
+{
+	struct crypto_skcipher *atfm = crypto_skcipher_reqtfm(skreq);
+	struct crypto_tfm *tfm = crypto_skcipher_tfm(atfm);
+	struct sec_alg_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct sec_queue *queue = ctx->queue;
+	struct sec_request *sec_req = skcipher_request_ctx(skreq);
+	struct sec_dev_info *info = queue->dev_info;
+	int i, ret, steps;
+	size_t *split_sizes;
+	struct scatterlist **splits_in;
+	struct scatterlist **splits_out = NULL;
+	int *splits_in_nents;
+	int *splits_out_nents = NULL;
+	struct sec_request_el *el, *temp;
+
+	mutex_init(&sec_req->lock);
+	sec_req->req_base = &skreq->base;
+	sec_req->err = 0;
+	/* SGL mapping out here to allow us to break it up as necessary */
+	sec_req->len_in = sg_nents(skreq->src);
+
+	ret = sec_alg_alloc_and_calc_split_sizes(skreq->cryptlen, &split_sizes,
+						 &steps);
+	if (ret)
+		return ret;
+	sec_req->num_elements = steps;
+	ret = sec_map_and_split_sg(skreq->src, split_sizes, steps, &splits_in,
+				   &splits_in_nents, sec_req->len_in,
+				   info->dev);
+	if (ret)
+		goto err_free_split_sizes;
+
+	if (skreq->src != skreq->dst) {
+		sec_req->len_out = sg_nents(skreq->dst);
+		ret = sec_map_and_split_sg(skreq->dst, split_sizes, steps,
+					   &splits_out, &splits_out_nents,
+					   sec_req->len_out, info->dev);
+		if (ret)
+			goto err_unmap_in_sg;
+	}
+	/* Shared info stored in seq_req - applies to all BDs */
+	sec_req->tfm_ctx = ctx;
+	sec_req->cb = sec_skcipher_alg_callback;
+	INIT_LIST_HEAD(&sec_req->elements);
+
+	/*
+	 * Future optimization.
+	 * In the chaining case we can't use a dma pool bounce buffer
+	 * but in the case where we know there is no chaining we can
+	 */
+	if (crypto_skcipher_ivsize(atfm)) {
+		sec_req->dma_iv = dma_map_single(info->dev, skreq->iv,
+						 crypto_skcipher_ivsize(atfm),
+						 DMA_TO_DEVICE);
+		if (dma_mapping_error(info->dev, sec_req->dma_iv)) {
+			ret = -ENOMEM;
+			goto err_unmap_out_sg;
+		}
+	}
+
+	/* Set them all up then queue - cleaner error handling. */
+	for (i = 0; i < steps; i++) {
+		el = sec_alg_alloc_and_fill_el(&ctx->req_template,
+					       encrypt ? 1 : 0,
+					       split_sizes[i],
+					       skreq->src != skreq->dst,
+					       splits_in[i], splits_in_nents[i],
+					       splits_out[i],
+					       splits_out_nents[i], info);
+		if (IS_ERR(el)) {
+			ret = PTR_ERR(el);
+			goto err_free_elements;
+		}
+		el->req.cipher_iv_addr_lo = lower_32_bits(sec_req->dma_iv);
+		el->req.cipher_iv_addr_hi = upper_32_bits(sec_req->dma_iv);
+		el->sec_req = sec_req;
+		list_add_tail(&el->head, &sec_req->elements);
+	}
+
+	/*
+	 * Only attempt to queue if the whole lot can fit in the queue -
+	 * we can't successfully cleanup after a partial queing so this
+	 * must succeed or fail atomically.
+	 *
+	 * Big hammer test of both software and hardware queues - could be
+	 * more refined but this is unlikely to happen so no need.
+	 */
+
+	/* Cleanup - all elements in pointer arrays have been coppied */
+	kfree(splits_in_nents);
+	kfree(splits_in);
+	kfree(splits_out_nents);
+	kfree(splits_out);
+	kfree(split_sizes);
+
+	/* Grab a big lock for a long time to avoid concurrency issues */
+	mutex_lock(&queue->queuelock);
+
+	/*
+	 * Can go on to queue if we have space in either:
+	 * 1) The hardware queue and no software queue
+	 * 2) The software queue
+	 * AND there is nothing in the backlog.  If there is backlog we
+	 * have to only queue to the backlog queue and return busy.
+	 */
+	if ((!sec_queue_can_enqueue(queue, steps) &&
+	     (!queue->havesoftqueue ||
+	      kfifo_avail(&queue->softqueue) > steps)) ||
+	    !list_empty(&ctx->backlog)) {
+		if ((skreq->base.flags & CRYPTO_TFM_REQ_MAY_BACKLOG)) {
+			list_add_tail(&sec_req->backlog_head, &ctx->backlog);
+			mutex_unlock(&queue->queuelock);
+			return -EBUSY;
+		}
+
+		ret = -EBUSY;
+		mutex_unlock(&queue->queuelock);
+		goto err_free_elements;
+	}
+	ret = sec_send_request(sec_req, queue);
+	mutex_unlock(&queue->queuelock);
+	if (ret)
+		goto err_free_elements;
+
+	return -EINPROGRESS;
+
+err_free_elements:
+	list_for_each_entry_safe(el, temp, &sec_req->elements, head) {
+		list_del(&el->head);
+		sec_alg_free_el(el, info);
+	}
+	if (crypto_skcipher_ivsize(atfm))
+		dma_unmap_single(info->dev, sec_req->dma_iv,
+				 crypto_skcipher_ivsize(atfm),
+				 DMA_BIDIRECTIONAL);
+err_unmap_out_sg:
+	if (skreq->src != skreq->dst)
+		sec_unmap_sg_on_err(skreq->dst, steps, splits_out,
+				    splits_out_nents, sec_req->len_out,
+				    info->dev);
+err_unmap_in_sg:
+	sec_unmap_sg_on_err(skreq->src, steps, splits_in, splits_in_nents,
+			    sec_req->len_in, info->dev);
+err_free_split_sizes:
+	kfree(split_sizes);
+
+	return ret;
+}
+
+static int sec_alg_skcipher_encrypt(struct skcipher_request *req)
+{
+	return sec_alg_skcipher_crypto(req, true);
+}
+
+static int sec_alg_skcipher_decrypt(struct skcipher_request *req)
+{
+	return sec_alg_skcipher_crypto(req, false);
+}
+
+static int sec_alg_skcipher_init(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	mutex_init(&ctx->lock);
+	INIT_LIST_HEAD(&ctx->backlog);
+	crypto_skcipher_set_reqsize(tfm, sizeof(struct sec_request));
+
+	ctx->queue = sec_queue_alloc_start_safe();
+	if (IS_ERR(ctx->queue))
+		return PTR_ERR(ctx->queue);
+
+	mutex_init(&ctx->queue->queuelock);
+	ctx->queue->havesoftqueue = false;
+
+	return 0;
+}
+
+static void sec_alg_skcipher_exit(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	struct device *dev = ctx->queue->dev_info->dev;
+
+	if (ctx->key) {
+		memzero_explicit(ctx->key, SEC_MAX_CIPHER_KEY);
+		dma_free_coherent(dev, SEC_MAX_CIPHER_KEY, ctx->key,
+				  ctx->pkey);
+	}
+	sec_queue_stop_release(ctx->queue);
+}
+
+static int sec_alg_skcipher_init_with_queue(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+	int ret;
+
+	ret = sec_alg_skcipher_init(tfm);
+	if (ret)
+		return ret;
+
+	INIT_KFIFO(ctx->queue->softqueue);
+	ret = kfifo_alloc(&ctx->queue->softqueue, 512, GFP_KERNEL);
+	if (ret) {
+		sec_alg_skcipher_exit(tfm);
+		return ret;
+	}
+	ctx->queue->havesoftqueue = true;
+
+	return 0;
+}
+
+static void sec_alg_skcipher_exit_with_queue(struct crypto_skcipher *tfm)
+{
+	struct sec_alg_tfm_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+	kfifo_free(&ctx->queue->softqueue);
+	sec_alg_skcipher_exit(tfm);
+}
+
+static struct skcipher_alg sec_algs[] = {
+	{
+		.base = {
+			.cra_name = "ecb(aes)",
+			.cra_driver_name = "hisi_sec_aes_ecb",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_aes_ecb,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize = 0,
+	}, {
+		.base = {
+			.cra_name = "cbc(aes)",
+			.cra_driver_name = "hisi_sec_aes_cbc",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_aes_cbc,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize = AES_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "ctr(aes)",
+			.cra_driver_name = "hisi_sec_aes_ctr",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_aes_ctr,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = AES_MIN_KEY_SIZE,
+		.max_keysize = AES_MAX_KEY_SIZE,
+		.ivsize = AES_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "xts(aes)",
+			.cra_driver_name = "hisi_sec_aes_xts",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = AES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_aes_xts,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = 2 * AES_MIN_KEY_SIZE,
+		.max_keysize = 2 * AES_MAX_KEY_SIZE,
+		.ivsize = AES_BLOCK_SIZE,
+	}, {
+	/* Unable to find any test vectors so untested */
+		.base = {
+			.cra_name = "ecb(des)",
+			.cra_driver_name = "hisi_sec_des_ecb",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_des_ecb,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = 0,
+	}, {
+		.base = {
+			.cra_name = "cbc(des)",
+			.cra_driver_name = "hisi_sec_des_cbc",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_des_cbc,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES_KEY_SIZE,
+		.max_keysize = DES_KEY_SIZE,
+		.ivsize = DES_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "cbc(des3_ede)",
+			.cra_driver_name = "hisi_sec_3des_cbc",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init_with_queue,
+		.exit = sec_alg_skcipher_exit_with_queue,
+		.setkey = sec_alg_skcipher_setkey_3des_cbc,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = DES3_EDE_BLOCK_SIZE,
+	}, {
+		.base = {
+			.cra_name = "ecb(des3_ede)",
+			.cra_driver_name = "hisi_sec_3des_ecb",
+			.cra_priority = 4001,
+			.cra_flags = CRYPTO_ALG_ASYNC,
+			.cra_blocksize = DES3_EDE_BLOCK_SIZE,
+			.cra_ctxsize = sizeof(struct sec_alg_tfm_ctx),
+			.cra_alignmask = 0,
+			.cra_module = THIS_MODULE,
+		},
+		.init = sec_alg_skcipher_init,
+		.exit = sec_alg_skcipher_exit,
+		.setkey = sec_alg_skcipher_setkey_3des_ecb,
+		.decrypt = sec_alg_skcipher_decrypt,
+		.encrypt = sec_alg_skcipher_encrypt,
+		.min_keysize = DES3_EDE_KEY_SIZE,
+		.max_keysize = DES3_EDE_KEY_SIZE,
+		.ivsize = 0,
+	}
+};
+
+int sec_algs_register(void)
+{
+	int ret = 0;
+
+	mutex_lock(&algs_lock);
+	if (++active_devs != 1)
+		goto unlock;
+
+	ret = crypto_register_skciphers(sec_algs, ARRAY_SIZE(sec_algs));
+	if (ret)
+		--active_devs;
+unlock:
+	mutex_unlock(&algs_lock);
+
+	return ret;
+}
+
+void sec_algs_unregister(void)
+{
+	mutex_lock(&algs_lock);
+	if (--active_devs != 0)
+		goto unlock;
+	crypto_unregister_skciphers(sec_algs, ARRAY_SIZE(sec_algs));
+
+unlock:
+	mutex_unlock(&algs_lock);
+}
diff --git a/drivers/crypto/hisilicon/sec/sec_drv.c b/drivers/crypto/hisilicon/sec/sec_drv.c
new file mode 100644
index 000000000000..c1ee4e7bf996
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/sec_drv.c
@@ -0,0 +1,1323 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for the Hisilicon SEC units found on Hip06 Hip07
+ *
+ * Copyright (c) 2016-2017 Hisilicon Limited.
+ */
+#include <linux/acpi.h>
+#include <linux/atomic.h>
+#include <linux/delay.h>
+#include <linux/dma-direction.h>
+#include <linux/dma-mapping.h>
+#include <linux/dmapool.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqreturn.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+
+#include "sec_drv.h"
+
+#define SEC_QUEUE_AR_FROCE_ALLOC			0
+#define SEC_QUEUE_AR_FROCE_NOALLOC			1
+#define SEC_QUEUE_AR_FROCE_DIS				2
+
+#define SEC_QUEUE_AW_FROCE_ALLOC			0
+#define SEC_QUEUE_AW_FROCE_NOALLOC			1
+#define SEC_QUEUE_AW_FROCE_DIS				2
+
+/* SEC_ALGSUB registers */
+#define SEC_ALGSUB_CLK_EN_REG				0x03b8
+#define SEC_ALGSUB_CLK_DIS_REG				0x03bc
+#define SEC_ALGSUB_CLK_ST_REG				0x535c
+#define SEC_ALGSUB_RST_REQ_REG				0x0aa8
+#define SEC_ALGSUB_RST_DREQ_REG				0x0aac
+#define SEC_ALGSUB_RST_ST_REG				0x5a54
+#define   SEC_ALGSUB_RST_ST_IS_RST			BIT(0)
+
+#define SEC_ALGSUB_BUILD_RST_REQ_REG			0x0ab8
+#define SEC_ALGSUB_BUILD_RST_DREQ_REG			0x0abc
+#define SEC_ALGSUB_BUILD_RST_ST_REG			0x5a5c
+#define   SEC_ALGSUB_BUILD_RST_ST_IS_RST		BIT(0)
+
+#define SEC_SAA_BASE					0x00001000UL
+
+/* SEC_SAA registers */
+#define SEC_SAA_CTRL_REG(x)	((x) * SEC_SAA_ADDR_SIZE)
+#define   SEC_SAA_CTRL_GET_QM_EN			BIT(0)
+
+#define SEC_ST_INTMSK1_REG				0x0200
+#define SEC_ST_RINT1_REG				0x0400
+#define SEC_ST_INTSTS1_REG				0x0600
+#define SEC_BD_MNG_STAT_REG				0x0800
+#define SEC_PARSING_STAT_REG				0x0804
+#define SEC_LOAD_TIME_OUT_CNT_REG			0x0808
+#define SEC_CORE_WORK_TIME_OUT_CNT_REG			0x080c
+#define SEC_BACK_TIME_OUT_CNT_REG			0x0810
+#define SEC_BD1_PARSING_RD_TIME_OUT_CNT_REG		0x0814
+#define SEC_BD1_PARSING_WR_TIME_OUT_CNT_REG		0x0818
+#define SEC_BD2_PARSING_RD_TIME_OUT_CNT_REG		0x081c
+#define SEC_BD2_PARSING_WR_TIME_OUT_CNT_REG		0x0820
+#define SEC_SAA_ACC_REG					0x083c
+#define SEC_BD_NUM_CNT_IN_SEC_REG			0x0858
+#define SEC_LOAD_WORK_TIME_CNT_REG			0x0860
+#define SEC_CORE_WORK_WORK_TIME_CNT_REG			0x0864
+#define SEC_BACK_WORK_TIME_CNT_REG			0x0868
+#define SEC_SAA_IDLE_TIME_CNT_REG			0x086c
+#define SEC_SAA_CLK_CNT_REG				0x0870
+
+/* SEC_COMMON registers */
+#define SEC_CLK_EN_REG					0x0000
+#define SEC_CTRL_REG					0x0004
+
+#define SEC_COMMON_CNT_CLR_CE_REG			0x0008
+#define   SEC_COMMON_CNT_CLR_CE_CLEAR			BIT(0)
+#define   SEC_COMMON_CNT_CLR_CE_SNAP_EN			BIT(1)
+
+#define SEC_SECURE_CTRL_REG				0x000c
+#define SEC_AXI_CACHE_CFG_REG				0x0010
+#define SEC_AXI_QOS_CFG_REG				0x0014
+#define SEC_IPV4_MASK_TABLE_REG				0x0020
+#define SEC_IPV6_MASK_TABLE_X_REG(x)	(0x0024 + (x) * 4)
+#define SEC_FSM_MAX_CNT_REG				0x0064
+
+#define SEC_CTRL2_REG					0x0068
+#define   SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M		GENMASK(3, 0)
+#define   SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_S		0
+#define   SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M		GENMASK(6, 4)
+#define   SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_S		4
+#define   SEC_CTRL2_CLK_GATE_EN				BIT(7)
+#define   SEC_CTRL2_ENDIAN_BD				BIT(8)
+#define   SEC_CTRL2_ENDIAN_BD_TYPE			BIT(9)
+
+#define SEC_CNT_PRECISION_CFG_REG			0x006c
+#define SEC_DEBUG_BD_CFG_REG				0x0070
+#define   SEC_DEBUG_BD_CFG_WB_NORMAL			BIT(0)
+#define   SEC_DEBUG_BD_CFG_WB_EN			BIT(1)
+
+#define SEC_Q_SIGHT_SEL					0x0074
+#define SEC_Q_SIGHT_HIS_CLR				0x0078
+#define SEC_Q_VMID_CFG_REG(q)		(0x0100 + (q) * 4)
+#define SEC_Q_WEIGHT_CFG_REG(q)		(0x200 + (q) * 4)
+#define SEC_STAT_CLR_REG				0x0a00
+#define SEC_SAA_IDLE_CNT_CLR_REG			0x0a04
+#define SEC_QM_CPL_Q_IDBUF_DFX_CFG_REG			0x0b00
+#define SEC_QM_CPL_Q_IDBUF_DFX_RESULT_REG		0x0b04
+#define SEC_QM_BD_DFX_CFG_REG				0x0b08
+#define SEC_QM_BD_DFX_RESULT_REG			0x0b0c
+#define SEC_QM_BDID_DFX_RESULT_REG			0x0b10
+#define SEC_QM_BD_DFIFO_STATUS_REG			0x0b14
+#define SEC_QM_BD_DFX_CFG2_REG				0x0b1c
+#define SEC_QM_BD_DFX_RESULT2_REG			0x0b20
+#define SEC_QM_BD_IDFIFO_STATUS_REG			0x0b18
+#define SEC_QM_BD_DFIFO_STATUS2_REG			0x0b28
+#define SEC_QM_BD_IDFIFO_STATUS2_REG			0x0b2c
+
+#define SEC_HASH_IPV4_MASK				0xfff00000
+#define SEC_MAX_SAA_NUM					0xa
+#define SEC_SAA_ADDR_SIZE				0x1000
+
+#define SEC_Q_INIT_REG					0x0
+#define   SEC_Q_INIT_WO_STAT_CLEAR			0x2
+#define   SEC_Q_INIT_AND_STAT_CLEAR			0x3
+
+#define SEC_Q_CFG_REG					0x8
+#define   SEC_Q_CFG_REORDER				BIT(0)
+
+#define SEC_Q_PROC_NUM_CFG_REG				0x10
+#define SEC_QUEUE_ENB_REG				0x18
+
+#define SEC_Q_DEPTH_CFG_REG				0x50
+#define   SEC_Q_DEPTH_CFG_DEPTH_M			GENMASK(11, 0)
+#define   SEC_Q_DEPTH_CFG_DEPTH_S			0
+
+#define SEC_Q_BASE_HADDR_REG				0x54
+#define SEC_Q_BASE_LADDR_REG				0x58
+#define SEC_Q_WR_PTR_REG				0x5c
+#define SEC_Q_OUTORDER_BASE_HADDR_REG			0x60
+#define SEC_Q_OUTORDER_BASE_LADDR_REG			0x64
+#define SEC_Q_OUTORDER_RD_PTR_REG			0x68
+#define SEC_Q_OT_TH_REG					0x6c
+
+#define SEC_Q_ARUSER_CFG_REG				0x70
+#define   SEC_Q_ARUSER_CFG_FA				BIT(0)
+#define   SEC_Q_ARUSER_CFG_FNA				BIT(1)
+#define   SEC_Q_ARUSER_CFG_RINVLD			BIT(2)
+#define   SEC_Q_ARUSER_CFG_PKG				BIT(3)
+
+#define SEC_Q_AWUSER_CFG_REG				0x74
+#define   SEC_Q_AWUSER_CFG_FA				BIT(0)
+#define   SEC_Q_AWUSER_CFG_FNA				BIT(1)
+#define   SEC_Q_AWUSER_CFG_PKG				BIT(2)
+
+#define SEC_Q_ERR_BASE_HADDR_REG			0x7c
+#define SEC_Q_ERR_BASE_LADDR_REG			0x80
+#define SEC_Q_CFG_VF_NUM_REG				0x84
+#define SEC_Q_SOFT_PROC_PTR_REG				0x88
+#define SEC_Q_FAIL_INT_MSK_REG				0x300
+#define SEC_Q_FLOW_INT_MKS_REG				0x304
+#define SEC_Q_FAIL_RINT_REG				0x400
+#define SEC_Q_FLOW_RINT_REG				0x404
+#define SEC_Q_FAIL_INT_STATUS_REG			0x500
+#define SEC_Q_FLOW_INT_STATUS_REG			0x504
+#define SEC_Q_STATUS_REG				0x600
+#define SEC_Q_RD_PTR_REG				0x604
+#define SEC_Q_PRO_PTR_REG				0x608
+#define SEC_Q_OUTORDER_WR_PTR_REG			0x60c
+#define SEC_Q_OT_CNT_STATUS_REG				0x610
+#define SEC_Q_INORDER_BD_NUM_ST_REG			0x650
+#define SEC_Q_INORDER_GET_FLAG_ST_REG			0x654
+#define SEC_Q_INORDER_ADD_FLAG_ST_REG			0x658
+#define SEC_Q_INORDER_TASK_INT_NUM_LEFT_ST_REG		0x65c
+#define SEC_Q_RD_DONE_PTR_REG				0x660
+#define SEC_Q_CPL_Q_BD_NUM_ST_REG			0x700
+#define SEC_Q_CPL_Q_PTR_ST_REG				0x704
+#define SEC_Q_CPL_Q_H_ADDR_ST_REG			0x708
+#define SEC_Q_CPL_Q_L_ADDR_ST_REG			0x70c
+#define SEC_Q_CPL_TASK_INT_NUM_LEFT_ST_REG		0x710
+#define SEC_Q_WRR_ID_CHECK_REG				0x714
+#define SEC_Q_CPLQ_FULL_CHECK_REG			0x718
+#define SEC_Q_SUCCESS_BD_CNT_REG			0x800
+#define SEC_Q_FAIL_BD_CNT_REG				0x804
+#define SEC_Q_GET_BD_CNT_REG				0x808
+#define SEC_Q_IVLD_CNT_REG				0x80c
+#define SEC_Q_BD_PROC_GET_CNT_REG			0x810
+#define SEC_Q_BD_PROC_DONE_CNT_REG			0x814
+#define SEC_Q_LAT_CLR_REG				0x850
+#define SEC_Q_PKT_LAT_MAX_REG				0x854
+#define SEC_Q_PKT_LAT_AVG_REG				0x858
+#define SEC_Q_PKT_LAT_MIN_REG				0x85c
+#define SEC_Q_ID_CLR_CFG_REG				0x900
+#define SEC_Q_1ST_BD_ERR_ID_REG				0x904
+#define SEC_Q_1ST_AUTH_FAIL_ID_REG			0x908
+#define SEC_Q_1ST_RD_ERR_ID_REG				0x90c
+#define SEC_Q_1ST_ECC2_ERR_ID_REG			0x910
+#define SEC_Q_1ST_IVLD_ID_REG				0x914
+#define SEC_Q_1ST_BD_WR_ERR_ID_REG			0x918
+#define SEC_Q_1ST_ERR_BD_WR_ERR_ID_REG			0x91c
+#define SEC_Q_1ST_BD_MAC_WR_ERR_ID_REG			0x920
+
+struct sec_debug_bd_info {
+#define SEC_DEBUG_BD_INFO_SOFT_ERR_CHECK_M	GENMASK(22, 0)
+	u32 soft_err_check;
+#define SEC_DEBUG_BD_INFO_HARD_ERR_CHECK_M	GENMASK(9, 0)
+	u32 hard_err_check;
+	u32 icv_mac1st_word;
+#define SEC_DEBUG_BD_INFO_GET_ID_M		GENMASK(19, 0)
+	u32 sec_get_id;
+	/* W4---W15 */
+	u32 reserv_left[12];
+};
+
+struct sec_out_bd_info	{
+#define SEC_OUT_BD_INFO_Q_ID_M			GENMASK(11, 0)
+#define SEC_OUT_BD_INFO_ECC_2BIT_ERR		BIT(14)
+	u16 data;
+};
+
+#define SEC_MAX_DEVICES				8
+static struct sec_dev_info *sec_devices[SEC_MAX_DEVICES];
+static DEFINE_MUTEX(sec_id_lock);
+
+static int sec_queue_map_io(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+	struct resource *res;
+
+	res = platform_get_resource(to_platform_device(dev),
+				    IORESOURCE_MEM,
+				    2 + queue->queue_id);
+	if (!res) {
+		dev_err(dev, "Failed to get queue %d memory resource\n",
+			queue->queue_id);
+		return -ENOMEM;
+	}
+	queue->regs = ioremap(res->start, resource_size(res));
+	if (!queue->regs)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void sec_queue_unmap_io(struct sec_queue *queue)
+{
+	 iounmap(queue->regs);
+}
+
+static int sec_queue_ar_pkgattr(struct sec_queue *queue, u32 ar_pkg)
+{
+	void __iomem *addr = queue->regs +  SEC_Q_ARUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (ar_pkg)
+		regval |= SEC_Q_ARUSER_CFG_PKG;
+	else
+		regval &= ~SEC_Q_ARUSER_CFG_PKG;
+	writel_relaxed(regval, addr);
+
+	return 0;
+}
+
+static int sec_queue_aw_pkgattr(struct sec_queue *queue, u32 aw_pkg)
+{
+	void __iomem *addr = queue->regs + SEC_Q_AWUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval |= SEC_Q_AWUSER_CFG_PKG;
+	writel_relaxed(regval, addr);
+
+	return 0;
+}
+
+static int sec_clk_en(struct sec_dev_info *info)
+{
+	void __iomem *base = info->regs[SEC_COMMON];
+	u32 i = 0;
+
+	writel_relaxed(0x7, base + SEC_ALGSUB_CLK_EN_REG);
+	do {
+		usleep_range(1000, 10000);
+		if ((readl_relaxed(base + SEC_ALGSUB_CLK_ST_REG) & 0x7) == 0x7)
+			return 0;
+		i++;
+	} while (i < 10);
+	dev_err(info->dev, "sec clock enable fail!\n");
+
+	return -EIO;
+}
+
+static int sec_clk_dis(struct sec_dev_info *info)
+{
+	void __iomem *base = info->regs[SEC_COMMON];
+	u32 i = 0;
+
+	writel_relaxed(0x7, base + SEC_ALGSUB_CLK_DIS_REG);
+	do {
+		usleep_range(1000, 10000);
+		if ((readl_relaxed(base + SEC_ALGSUB_CLK_ST_REG) & 0x7) == 0)
+			return 0;
+		i++;
+	} while (i < 10);
+	dev_err(info->dev, "sec clock disable fail!\n");
+
+	return -EIO;
+}
+
+static int sec_reset_whole_module(struct sec_dev_info *info)
+{
+	void __iomem *base = info->regs[SEC_COMMON];
+	bool is_reset, b_is_reset;
+	u32 i = 0;
+
+	writel_relaxed(1, base + SEC_ALGSUB_RST_REQ_REG);
+	writel_relaxed(1, base + SEC_ALGSUB_BUILD_RST_REQ_REG);
+	while (1) {
+		usleep_range(1000, 10000);
+		is_reset = readl_relaxed(base + SEC_ALGSUB_RST_ST_REG) &
+			SEC_ALGSUB_RST_ST_IS_RST;
+		b_is_reset = readl_relaxed(base + SEC_ALGSUB_BUILD_RST_ST_REG) &
+			SEC_ALGSUB_BUILD_RST_ST_IS_RST;
+		if (is_reset && b_is_reset)
+			break;
+		i++;
+		if (i > 10) {
+			dev_err(info->dev, "Reset req failed\n");
+			return -EIO;
+		}
+	}
+
+	i = 0;
+	writel_relaxed(1, base + SEC_ALGSUB_RST_DREQ_REG);
+	writel_relaxed(1, base + SEC_ALGSUB_BUILD_RST_DREQ_REG);
+	while (1) {
+		usleep_range(1000, 10000);
+		is_reset = readl_relaxed(base + SEC_ALGSUB_RST_ST_REG) &
+			SEC_ALGSUB_RST_ST_IS_RST;
+		b_is_reset = readl_relaxed(base + SEC_ALGSUB_BUILD_RST_ST_REG) &
+			SEC_ALGSUB_BUILD_RST_ST_IS_RST;
+		if (!is_reset && !b_is_reset)
+			break;
+
+		i++;
+		if (i > 10) {
+			dev_err(info->dev, "Reset dreq failed\n");
+			return -EIO;
+		}
+	}
+
+	return 0;
+}
+
+static void sec_bd_endian_little(struct sec_dev_info *info)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~(SEC_CTRL2_ENDIAN_BD | SEC_CTRL2_ENDIAN_BD_TYPE);
+	writel_relaxed(regval, addr);
+}
+
+/*
+ * sec_cache_config - configure optimum cache placement
+ */
+static void sec_cache_config(struct sec_dev_info *info)
+{
+	struct iommu_domain *domain;
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL_REG;
+
+	domain = iommu_get_domain_for_dev(info->dev);
+
+	/* Check that translation is occurring */
+	if (domain && (domain->type & __IOMMU_DOMAIN_PAGING))
+		writel_relaxed(0x44cf9e, addr);
+	else
+		writel_relaxed(0x4cfd9, addr);
+}
+
+static void sec_data_axiwr_otsd_cfg(struct sec_dev_info *info, u32 cfg)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M;
+	regval |= (cfg << SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_S) &
+		SEC_CTRL2_DATA_AXI_WR_OTSD_CFG_M;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_data_axird_otsd_cfg(struct sec_dev_info *info, u32 cfg)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M;
+	regval |= (cfg << SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_S) &
+		SEC_CTRL2_DATA_AXI_RD_OTSD_CFG_M;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_clk_gate_en(struct sec_dev_info *info, bool clkgate)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_CTRL2_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (clkgate)
+		regval |= SEC_CTRL2_CLK_GATE_EN;
+	else
+		regval &= ~SEC_CTRL2_CLK_GATE_EN;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_comm_cnt_cfg(struct sec_dev_info *info, bool clr_ce)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_COMMON_CNT_CLR_CE_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (clr_ce)
+		regval |= SEC_COMMON_CNT_CLR_CE_CLEAR;
+	else
+		regval &= ~SEC_COMMON_CNT_CLR_CE_CLEAR;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_commsnap_en(struct sec_dev_info *info, bool snap_en)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_COMMON_CNT_CLR_CE_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (snap_en)
+		regval |= SEC_COMMON_CNT_CLR_CE_SNAP_EN;
+	else
+		regval &= ~SEC_COMMON_CNT_CLR_CE_SNAP_EN;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_ipv6_hashmask(struct sec_dev_info *info, u32 hash_mask[])
+{
+	void __iomem *base = info->regs[SEC_SAA];
+	int i;
+
+	for (i = 0; i < 10; i++)
+		writel_relaxed(hash_mask[0],
+			       base + SEC_IPV6_MASK_TABLE_X_REG(i));
+}
+
+static int sec_ipv4_hashmask(struct sec_dev_info *info, u32 hash_mask)
+{
+	if (hash_mask & SEC_HASH_IPV4_MASK) {
+		dev_err(info->dev, "Sec Ipv4 Hash Mask Input Error!\n ");
+		return -EINVAL;
+	}
+
+	writel_relaxed(hash_mask,
+		       info->regs[SEC_SAA] + SEC_IPV4_MASK_TABLE_REG);
+
+	return 0;
+}
+
+static void sec_set_dbg_bd_cfg(struct sec_dev_info *info, u32 cfg)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_DEBUG_BD_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	/* Always disable write back of normal bd */
+	regval &= ~SEC_DEBUG_BD_CFG_WB_NORMAL;
+
+	if (cfg)
+		regval &= ~SEC_DEBUG_BD_CFG_WB_EN;
+	else
+		regval |= SEC_DEBUG_BD_CFG_WB_EN;
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_saa_getqm_en(struct sec_dev_info *info, u32 saa_indx, u32 en)
+{
+	void __iomem *addr = info->regs[SEC_SAA] + SEC_SAA_BASE +
+		SEC_SAA_CTRL_REG(saa_indx);
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (en)
+		regval |= SEC_SAA_CTRL_GET_QM_EN;
+	else
+		regval &= ~SEC_SAA_CTRL_GET_QM_EN;
+	writel_relaxed(regval, addr);
+}
+
+static void sec_saa_int_mask(struct sec_dev_info *info, u32 saa_indx,
+			     u32 saa_int_mask)
+{
+	writel_relaxed(saa_int_mask,
+		       info->regs[SEC_SAA] + SEC_SAA_BASE + SEC_ST_INTMSK1_REG +
+		       saa_indx * SEC_SAA_ADDR_SIZE);
+}
+
+static void sec_streamid(struct sec_dev_info *info, int i)
+{
+	#define SEC_SID 0x600
+	#define SEC_VMID 0
+
+	writel_relaxed((SEC_VMID | ((SEC_SID & 0xffff) << 8)),
+		       info->regs[SEC_SAA] + SEC_Q_VMID_CFG_REG(i));
+}
+
+static void sec_queue_ar_alloc(struct sec_queue *queue, u32 alloc)
+{
+	void __iomem *addr = queue->regs + SEC_Q_ARUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (alloc == SEC_QUEUE_AR_FROCE_ALLOC) {
+		regval |= SEC_Q_ARUSER_CFG_FA;
+		regval &= ~SEC_Q_ARUSER_CFG_FNA;
+	} else {
+		regval &= ~SEC_Q_ARUSER_CFG_FA;
+		regval |= SEC_Q_ARUSER_CFG_FNA;
+	}
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_queue_aw_alloc(struct sec_queue *queue, u32 alloc)
+{
+	void __iomem *addr = queue->regs + SEC_Q_AWUSER_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	if (alloc == SEC_QUEUE_AW_FROCE_ALLOC) {
+		regval |= SEC_Q_AWUSER_CFG_FA;
+		regval &= ~SEC_Q_AWUSER_CFG_FNA;
+	} else {
+		regval &= ~SEC_Q_AWUSER_CFG_FA;
+		regval |= SEC_Q_AWUSER_CFG_FNA;
+	}
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_queue_reorder(struct sec_queue *queue, bool reorder)
+{
+	void __iomem *base = queue->regs;
+	u32 regval;
+
+	regval = readl_relaxed(base + SEC_Q_CFG_REG);
+	if (reorder)
+		regval |= SEC_Q_CFG_REORDER;
+	else
+		regval &= ~SEC_Q_CFG_REORDER;
+	writel_relaxed(regval, base + SEC_Q_CFG_REG);
+}
+
+static void sec_queue_depth(struct sec_queue *queue, u32 depth)
+{
+	void __iomem *addr = queue->regs + SEC_Q_DEPTH_CFG_REG;
+	u32 regval;
+
+	regval = readl_relaxed(addr);
+	regval &= ~SEC_Q_DEPTH_CFG_DEPTH_M;
+	regval |= (depth << SEC_Q_DEPTH_CFG_DEPTH_S) & SEC_Q_DEPTH_CFG_DEPTH_M;
+
+	writel_relaxed(regval, addr);
+}
+
+static void sec_queue_cmdbase_addr(struct sec_queue *queue, u64 addr)
+{
+	writel_relaxed(upper_32_bits(addr), queue->regs + SEC_Q_BASE_HADDR_REG);
+	writel_relaxed(lower_32_bits(addr), queue->regs + SEC_Q_BASE_LADDR_REG);
+}
+
+static void sec_queue_outorder_addr(struct sec_queue *queue, u64 addr)
+{
+	writel_relaxed(upper_32_bits(addr),
+		       queue->regs + SEC_Q_OUTORDER_BASE_HADDR_REG);
+	writel_relaxed(lower_32_bits(addr),
+		       queue->regs + SEC_Q_OUTORDER_BASE_LADDR_REG);
+}
+
+static void sec_queue_errbase_addr(struct sec_queue *queue, u64 addr)
+{
+	writel_relaxed(upper_32_bits(addr),
+		       queue->regs + SEC_Q_ERR_BASE_HADDR_REG);
+	writel_relaxed(lower_32_bits(addr),
+		       queue->regs + SEC_Q_ERR_BASE_LADDR_REG);
+}
+
+static void sec_queue_irq_disable(struct sec_queue *queue)
+{
+	writel_relaxed((u32)~0, queue->regs + SEC_Q_FLOW_INT_MKS_REG);
+}
+
+static void sec_queue_irq_enable(struct sec_queue *queue)
+{
+	writel_relaxed(0, queue->regs + SEC_Q_FLOW_INT_MKS_REG);
+}
+
+static void sec_queue_abn_irq_disable(struct sec_queue *queue)
+{
+	writel_relaxed((u32)~0, queue->regs + SEC_Q_FAIL_INT_MSK_REG);
+}
+
+static void sec_queue_stop(struct sec_queue *queue)
+{
+	disable_irq(queue->task_irq);
+	sec_queue_irq_disable(queue);
+	writel_relaxed(0x0, queue->regs + SEC_QUEUE_ENB_REG);
+}
+
+static void sec_queue_start(struct sec_queue *queue)
+{
+	sec_queue_irq_enable(queue);
+	enable_irq(queue->task_irq);
+	queue->expected = 0;
+	writel_relaxed(SEC_Q_INIT_AND_STAT_CLEAR, queue->regs + SEC_Q_INIT_REG);
+	writel_relaxed(0x1, queue->regs + SEC_QUEUE_ENB_REG);
+}
+
+static struct sec_queue *sec_alloc_queue(struct sec_dev_info *info)
+{
+	int i;
+
+	mutex_lock(&info->dev_lock);
+
+	/* Get the first idle queue in SEC device */
+	for (i = 0; i < SEC_Q_NUM; i++)
+		if (!info->queues[i].in_use) {
+			info->queues[i].in_use = true;
+			info->queues_in_use++;
+			mutex_unlock(&info->dev_lock);
+
+			return &info->queues[i];
+		}
+	mutex_unlock(&info->dev_lock);
+
+	return ERR_PTR(-ENODEV);
+}
+
+static int sec_queue_free(struct sec_queue *queue)
+{
+	struct sec_dev_info *info = queue->dev_info;
+
+	if (queue->queue_id >= SEC_Q_NUM) {
+		dev_err(info->dev, "No queue %d\n", queue->queue_id);
+		return -ENODEV;
+	}
+
+	if (!queue->in_use) {
+		dev_err(info->dev, "Queue %d is idle\n", queue->queue_id);
+		return -ENODEV;
+	}
+
+	mutex_lock(&info->dev_lock);
+	queue->in_use = false;
+	info->queues_in_use--;
+	mutex_unlock(&info->dev_lock);
+
+	return 0;
+}
+
+static irqreturn_t sec_isr_handle_th(int irq, void *q)
+{
+	sec_queue_irq_disable(q);
+	return IRQ_WAKE_THREAD;
+}
+
+static irqreturn_t sec_isr_handle(int irq, void *q)
+{
+	struct sec_queue *queue = q;
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+	struct sec_queue_ring_cq *cq_ring = &queue->ring_cq;
+	struct sec_out_bd_info *outorder_msg;
+	struct sec_bd_info *msg;
+	u32 ooo_read, ooo_write;
+	void __iomem *base = queue->regs;
+	int q_id;
+
+	ooo_read = readl(base + SEC_Q_OUTORDER_RD_PTR_REG);
+	ooo_write = readl(base + SEC_Q_OUTORDER_WR_PTR_REG);
+	outorder_msg = cq_ring->vaddr + ooo_read;
+	q_id = outorder_msg->data & SEC_OUT_BD_INFO_Q_ID_M;
+	msg = msg_ring->vaddr + q_id;
+
+	while ((ooo_write != ooo_read) && msg->w0 & SEC_BD_W0_DONE) {
+		/*
+		 * Must be before callback otherwise blocks adding other chained
+		 * elements
+		 */
+		set_bit(q_id, queue->unprocessed);
+		if (q_id == queue->expected)
+			while (test_bit(queue->expected, queue->unprocessed)) {
+				clear_bit(queue->expected, queue->unprocessed);
+				msg = msg_ring->vaddr + queue->expected;
+				msg->w0 &= ~SEC_BD_W0_DONE;
+				msg_ring->callback(msg,
+						queue->shadow[queue->expected]);
+				queue->shadow[queue->expected] = NULL;
+				queue->expected = (queue->expected + 1) %
+					SEC_QUEUE_LEN;
+				atomic_dec(&msg_ring->used);
+			}
+
+		ooo_read = (ooo_read + 1) % SEC_QUEUE_LEN;
+		writel(ooo_read, base + SEC_Q_OUTORDER_RD_PTR_REG);
+		ooo_write = readl(base + SEC_Q_OUTORDER_WR_PTR_REG);
+		outorder_msg = cq_ring->vaddr + ooo_read;
+		q_id = outorder_msg->data & SEC_OUT_BD_INFO_Q_ID_M;
+		msg = msg_ring->vaddr + q_id;
+	}
+
+	sec_queue_irq_enable(queue);
+
+	return IRQ_HANDLED;
+}
+
+static int sec_queue_irq_init(struct sec_queue *queue)
+{
+	struct sec_dev_info *info = queue->dev_info;
+	int irq = queue->task_irq;
+	int ret;
+
+	ret = request_threaded_irq(irq, sec_isr_handle_th, sec_isr_handle,
+				   IRQF_TRIGGER_RISING, queue->name, queue);
+	if (ret) {
+		dev_err(info->dev, "request irq(%d) failed %d\n", irq, ret);
+		return ret;
+	}
+	disable_irq(irq);
+
+	return 0;
+}
+
+static int sec_queue_irq_uninit(struct sec_queue *queue)
+{
+	free_irq(queue->task_irq, queue);
+
+	return 0;
+}
+
+static struct sec_dev_info *sec_device_get(void)
+{
+	struct sec_dev_info *sec_dev = NULL;
+	struct sec_dev_info *this_sec_dev;
+	int least_busy_n = SEC_Q_NUM + 1;
+	int i;
+
+	/* Find which one is least busy and use that first */
+	for (i = 0; i < SEC_MAX_DEVICES; i++) {
+		this_sec_dev = sec_devices[i];
+		if (this_sec_dev &&
+		    this_sec_dev->queues_in_use < least_busy_n) {
+			least_busy_n = this_sec_dev->queues_in_use;
+			sec_dev = this_sec_dev;
+		}
+	}
+
+	return sec_dev;
+}
+
+static struct sec_queue *sec_queue_alloc_start(struct sec_dev_info *info)
+{
+	struct sec_queue *queue;
+
+	queue = sec_alloc_queue(info);
+	if (IS_ERR(queue)) {
+		dev_err(info->dev, "alloc sec queue failed! %ld\n",
+			PTR_ERR(queue));
+		return queue;
+	}
+
+	sec_queue_start(queue);
+
+	return queue;
+}
+
+/**
+ * sec_queue_alloc_start_safe - get a hw queue from appropriate instance
+ *
+ * This function does extremely simplistic load balancing. It does not take into
+ * account NUMA locality of the accelerator, or which cpu has requested the
+ * queue.  Future work may focus on optimizing this in order to improve full
+ * machine throughput.
+ */
+struct sec_queue *sec_queue_alloc_start_safe(void)
+{
+	struct sec_dev_info *info;
+	struct sec_queue *queue = ERR_PTR(-ENODEV);
+
+	mutex_lock(&sec_id_lock);
+	info = sec_device_get();
+	if (!info)
+		goto unlock;
+
+	queue = sec_queue_alloc_start(info);
+
+unlock:
+	mutex_unlock(&sec_id_lock);
+
+	return queue;
+}
+
+/**
+ * sec_queue_stop_release() - free up a hw queue for reuse
+ * @queue: The queue we are done with.
+ *
+ * This will stop the current queue, terminanting any transactions
+ * that are inflight an return it to the pool of available hw queuess
+ */
+int sec_queue_stop_release(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+	int ret;
+
+	sec_queue_stop(queue);
+
+	ret = sec_queue_free(queue);
+	if (ret)
+		dev_err(dev, "Releasing queue failed %d\n", ret);
+
+	return ret;
+}
+
+/**
+ * sec_queue_empty() - Is this hardware queue currently empty.
+ *
+ * We need to know if we have an empty queue for some of the chaining modes
+ * as if it is not empty we may need to hold the message in a software queue
+ * until the hw queue is drained.
+ */
+bool sec_queue_empty(struct sec_queue *queue)
+{
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+
+	return !atomic_read(&msg_ring->used);
+}
+
+/**
+ * sec_queue_send() - queue up a single operation in the hw queue
+ * @queue: The queue in which to put the message
+ * @msg: The message
+ * @ctx: Context to be put in the shadow array and passed back to cb on result.
+ *
+ * This function will return -EAGAIN if the queue is currently full.
+ */
+int sec_queue_send(struct sec_queue *queue, struct sec_bd_info *msg, void *ctx)
+{
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+	void __iomem *base = queue->regs;
+	u32 write, read;
+
+	mutex_lock(&msg_ring->lock);
+	read = readl(base + SEC_Q_RD_PTR_REG);
+	write = readl(base + SEC_Q_WR_PTR_REG);
+	if (write == read && atomic_read(&msg_ring->used) == SEC_QUEUE_LEN) {
+		mutex_unlock(&msg_ring->lock);
+		return -EAGAIN;
+	}
+	memcpy(msg_ring->vaddr + write, msg, sizeof(*msg));
+	queue->shadow[write] = ctx;
+	write = (write + 1) % SEC_QUEUE_LEN;
+
+	/* Ensure content updated before queue advance */
+	wmb();
+	writel(write, base + SEC_Q_WR_PTR_REG);
+
+	atomic_inc(&msg_ring->used);
+	mutex_unlock(&msg_ring->lock);
+
+	return 0;
+}
+
+bool sec_queue_can_enqueue(struct sec_queue *queue, int num)
+{
+	struct sec_queue_ring_cmd *msg_ring = &queue->ring_cmd;
+
+	return SEC_QUEUE_LEN - atomic_read(&msg_ring->used) >= num;
+}
+
+static void sec_queue_hw_init(struct sec_queue *queue)
+{
+	sec_queue_ar_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC);
+	sec_queue_aw_alloc(queue, SEC_QUEUE_AR_FROCE_NOALLOC);
+	sec_queue_ar_pkgattr(queue, 1);
+	sec_queue_aw_pkgattr(queue, 1);
+
+	/* Enable out of order queue */
+	sec_queue_reorder(queue, true);
+
+	/* Interrupt after a single complete element */
+	writel_relaxed(1, queue->regs + SEC_Q_PROC_NUM_CFG_REG);
+
+	sec_queue_depth(queue, SEC_QUEUE_LEN - 1);
+
+	sec_queue_cmdbase_addr(queue, queue->ring_cmd.paddr);
+
+	sec_queue_outorder_addr(queue, queue->ring_cq.paddr);
+
+	sec_queue_errbase_addr(queue, queue->ring_db.paddr);
+
+	writel_relaxed(0x100, queue->regs + SEC_Q_OT_TH_REG);
+
+	sec_queue_abn_irq_disable(queue);
+	sec_queue_irq_disable(queue);
+	writel_relaxed(SEC_Q_INIT_AND_STAT_CLEAR, queue->regs + SEC_Q_INIT_REG);
+}
+
+static int sec_hw_init(struct sec_dev_info *info)
+{
+	struct iommu_domain *domain;
+	u32 sec_ipv4_mask = 0;
+	u32 sec_ipv6_mask[10] = {};
+	u32 i, ret;
+
+	domain = iommu_get_domain_for_dev(info->dev);
+
+	/*
+	 * Enable all available processing unit clocks.
+	 * Only the first cluster is usable with translations.
+	 */
+	if (domain && (domain->type & __IOMMU_DOMAIN_PAGING))
+		info->num_saas = 5;
+
+	else
+		info->num_saas = 10;
+
+	writel_relaxed(GENMASK(info->num_saas - 1, 0),
+		       info->regs[SEC_SAA] + SEC_CLK_EN_REG);
+
+	/* 32 bit little endian */
+	sec_bd_endian_little(info);
+
+	sec_cache_config(info);
+
+	/* Data axi port write and read outstanding config as per datasheet */
+	sec_data_axiwr_otsd_cfg(info, 0x7);
+	sec_data_axird_otsd_cfg(info, 0x7);
+
+	/* Enable clock gating */
+	sec_clk_gate_en(info, true);
+
+	/* Set CNT_CYC register not read clear */
+	sec_comm_cnt_cfg(info, false);
+
+	/* Enable CNT_CYC */
+	sec_commsnap_en(info, false);
+
+	writel_relaxed((u32)~0, info->regs[SEC_SAA] + SEC_FSM_MAX_CNT_REG);
+
+	ret = sec_ipv4_hashmask(info, sec_ipv4_mask);
+	if (ret) {
+		dev_err(info->dev, "Failed to set ipv4 hashmask %d\n", ret);
+		return -EIO;
+	}
+
+	sec_ipv6_hashmask(info, sec_ipv6_mask);
+
+	/*  do not use debug bd */
+	sec_set_dbg_bd_cfg(info, 0);
+
+	if (domain && (domain->type & __IOMMU_DOMAIN_PAGING)) {
+		for (i = 0; i < SEC_Q_NUM; i++) {
+			sec_streamid(info, i);
+			/* Same QoS for all queues */
+			writel_relaxed(0x3f,
+				       info->regs[SEC_SAA] +
+				       SEC_Q_WEIGHT_CFG_REG(i));
+		}
+	}
+
+	for (i = 0; i < info->num_saas; i++) {
+		sec_saa_getqm_en(info, i, 1);
+		sec_saa_int_mask(info, i, 0);
+	}
+
+	return 0;
+}
+
+static void sec_hw_exit(struct sec_dev_info *info)
+{
+	int i;
+
+	for (i = 0; i < SEC_MAX_SAA_NUM; i++) {
+		sec_saa_int_mask(info, i, (u32)~0);
+		sec_saa_getqm_en(info, i, 0);
+	}
+}
+
+static void sec_queue_base_init(struct sec_dev_info *info,
+				struct sec_queue *queue, int queue_id)
+{
+	queue->dev_info = info;
+	queue->queue_id = queue_id;
+	snprintf(queue->name, sizeof(queue->name),
+		 "%s_%d", dev_name(info->dev), queue->queue_id);
+}
+
+static int sec_map_io(struct sec_dev_info *info, struct platform_device *pdev)
+{
+	struct resource *res;
+	int i;
+
+	for (i = 0; i < SEC_NUM_ADDR_REGIONS; i++) {
+		res = platform_get_resource(pdev, IORESOURCE_MEM, i);
+
+		if (!res) {
+			dev_err(info->dev, "Memory resource %d not found\n", i);
+			return -EINVAL;
+		}
+
+		info->regs[i] = devm_ioremap(info->dev, res->start,
+					     resource_size(res));
+		if (!info->regs[i]) {
+			dev_err(info->dev,
+				"Memory resource %d could not be remapped\n",
+				i);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static int sec_base_init(struct sec_dev_info *info,
+			 struct platform_device *pdev)
+{
+	int ret;
+
+	ret = sec_map_io(info, pdev);
+	if (ret)
+		return ret;
+
+	ret = sec_clk_en(info);
+	if (ret)
+		return ret;
+
+	ret = sec_reset_whole_module(info);
+	if (ret)
+		goto sec_clk_disable;
+
+	ret = sec_hw_init(info);
+	if (ret)
+		goto sec_clk_disable;
+
+	return 0;
+
+sec_clk_disable:
+	sec_clk_dis(info);
+
+	return ret;
+}
+
+static void sec_base_exit(struct sec_dev_info *info)
+{
+	sec_hw_exit(info);
+	sec_clk_dis(info);
+}
+
+#define SEC_Q_CMD_SIZE \
+	round_up(SEC_QUEUE_LEN * sizeof(struct sec_bd_info), PAGE_SIZE)
+#define SEC_Q_CQ_SIZE \
+	round_up(SEC_QUEUE_LEN * sizeof(struct sec_out_bd_info), PAGE_SIZE)
+#define SEC_Q_DB_SIZE \
+	round_up(SEC_QUEUE_LEN * sizeof(struct sec_debug_bd_info), PAGE_SIZE)
+
+static int sec_queue_res_cfg(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+	struct sec_queue_ring_cmd *ring_cmd = &queue->ring_cmd;
+	struct sec_queue_ring_cq *ring_cq = &queue->ring_cq;
+	struct sec_queue_ring_db *ring_db = &queue->ring_db;
+	int ret;
+
+	ring_cmd->vaddr = dma_zalloc_coherent(dev, SEC_Q_CMD_SIZE,
+					      &ring_cmd->paddr,
+					      GFP_KERNEL);
+	if (!ring_cmd->vaddr)
+		return -ENOMEM;
+
+	atomic_set(&ring_cmd->used, 0);
+	mutex_init(&ring_cmd->lock);
+	ring_cmd->callback = sec_alg_callback;
+
+	ring_cq->vaddr = dma_zalloc_coherent(dev, SEC_Q_CQ_SIZE,
+					     &ring_cq->paddr,
+					     GFP_KERNEL);
+	if (!ring_cq->vaddr) {
+		ret = -ENOMEM;
+		goto err_free_ring_cmd;
+	}
+
+	ring_db->vaddr = dma_zalloc_coherent(dev, SEC_Q_DB_SIZE,
+					     &ring_db->paddr,
+					     GFP_KERNEL);
+	if (!ring_db->vaddr) {
+		ret = -ENOMEM;
+		goto err_free_ring_cq;
+	}
+	queue->task_irq = platform_get_irq(to_platform_device(dev),
+					   queue->queue_id * 2 + 1);
+	if (queue->task_irq <= 0) {
+		ret = -EINVAL;
+		goto err_free_ring_db;
+	}
+
+	return 0;
+
+err_free_ring_db:
+	dma_free_coherent(dev, SEC_Q_DB_SIZE, queue->ring_db.vaddr,
+			  queue->ring_db.paddr);
+err_free_ring_cq:
+	dma_free_coherent(dev, SEC_Q_CQ_SIZE, queue->ring_cq.vaddr,
+			  queue->ring_cq.paddr);
+err_free_ring_cmd:
+	dma_free_coherent(dev, SEC_Q_CMD_SIZE, queue->ring_cmd.vaddr,
+			  queue->ring_cmd.paddr);
+
+	return ret;
+}
+
+static void sec_queue_free_ring_pages(struct sec_queue *queue)
+{
+	struct device *dev = queue->dev_info->dev;
+
+	dma_free_coherent(dev, SEC_Q_DB_SIZE, queue->ring_db.vaddr,
+			  queue->ring_db.paddr);
+	dma_free_coherent(dev, SEC_Q_CQ_SIZE, queue->ring_cq.vaddr,
+			  queue->ring_cq.paddr);
+	dma_free_coherent(dev, SEC_Q_CMD_SIZE, queue->ring_cmd.vaddr,
+			  queue->ring_cmd.paddr);
+}
+
+static int sec_queue_config(struct sec_dev_info *info, struct sec_queue *queue,
+			    int queue_id)
+{
+	int ret;
+
+	sec_queue_base_init(info, queue, queue_id);
+
+	ret = sec_queue_res_cfg(queue);
+	if (ret)
+		return ret;
+
+	ret = sec_queue_map_io(queue);
+	if (ret) {
+		dev_err(info->dev, "Queue map failed %d\n", ret);
+		sec_queue_free_ring_pages(queue);
+		return ret;
+	}
+
+	sec_queue_hw_init(queue);
+
+	return 0;
+}
+
+static void sec_queue_unconfig(struct sec_dev_info *info,
+			       struct sec_queue *queue)
+{
+	sec_queue_unmap_io(queue);
+	sec_queue_free_ring_pages(queue);
+}
+
+static int sec_id_alloc(struct sec_dev_info *info)
+{
+	int ret = 0;
+	int i;
+
+	mutex_lock(&sec_id_lock);
+
+	for (i = 0; i < SEC_MAX_DEVICES; i++)
+		if (!sec_devices[i])
+			break;
+	if (i == SEC_MAX_DEVICES) {
+		ret = -ENOMEM;
+		goto unlock;
+	}
+	info->sec_id = i;
+	sec_devices[info->sec_id] = info;
+
+unlock:
+	mutex_unlock(&sec_id_lock);
+
+	return ret;
+}
+
+static void sec_id_free(struct sec_dev_info *info)
+{
+	mutex_lock(&sec_id_lock);
+	sec_devices[info->sec_id] = NULL;
+	mutex_unlock(&sec_id_lock);
+}
+
+static int sec_probe(struct platform_device *pdev)
+{
+	struct sec_dev_info *info;
+	struct device *dev = &pdev->dev;
+	int i, j;
+	int ret;
+
+	ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+	if (ret) {
+		dev_err(dev, "Failed to set 64 bit dma mask %d", ret);
+		return -ENODEV;
+	}
+
+	info = devm_kzalloc(dev, (sizeof(*info)), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->dev = dev;
+	mutex_init(&info->dev_lock);
+
+	info->hw_sgl_pool = dmam_pool_create("sgl", dev,
+					     sizeof(struct sec_hw_sgl), 64, 0);
+	if (!info->hw_sgl_pool) {
+		dev_err(dev, "Failed to create sec sgl dma pool\n");
+		return -ENOMEM;
+	}
+
+	ret = sec_base_init(info, pdev);
+	if (ret) {
+		dev_err(dev, "Base initialization fail! %d\n", ret);
+		return ret;
+	}
+
+	for (i = 0; i < SEC_Q_NUM; i++) {
+		ret = sec_queue_config(info, &info->queues[i], i);
+		if (ret)
+			goto queues_unconfig;
+
+		ret = sec_queue_irq_init(&info->queues[i]);
+		if (ret) {
+			sec_queue_unconfig(info, &info->queues[i]);
+			goto queues_unconfig;
+		}
+	}
+
+	ret = sec_algs_register();
+	if (ret) {
+		dev_err(dev, "Failed to register algorithms with crypto %d\n",
+			ret);
+		goto queues_unconfig;
+	}
+
+	platform_set_drvdata(pdev, info);
+
+	ret = sec_id_alloc(info);
+	if (ret)
+		goto algs_unregister;
+
+	return 0;
+
+algs_unregister:
+	sec_algs_unregister();
+queues_unconfig:
+	for (j = i - 1; j >= 0; j--) {
+		sec_queue_irq_uninit(&info->queues[j]);
+		sec_queue_unconfig(info, &info->queues[j]);
+	}
+	sec_base_exit(info);
+
+	return ret;
+}
+
+static int sec_remove(struct platform_device *pdev)
+{
+	struct sec_dev_info *info = platform_get_drvdata(pdev);
+	int i;
+
+	/* Unexpose as soon as possible, reuse during remove is fine */
+	sec_id_free(info);
+
+	sec_algs_unregister();
+
+	for (i = 0; i < SEC_Q_NUM; i++) {
+		sec_queue_irq_uninit(&info->queues[i]);
+		sec_queue_unconfig(info, &info->queues[i]);
+	}
+
+	sec_base_exit(info);
+
+	return 0;
+}
+
+static const __maybe_unused struct of_device_id sec_match[] = {
+	{ .compatible = "hisilicon,hip06-sec" },
+	{ .compatible = "hisilicon,hip07-sec" },
+	{}
+};
+MODULE_DEVICE_TABLE(of, sec_match);
+
+static const __maybe_unused struct acpi_device_id sec_acpi_match[] = {
+	{ "HISI02C1", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, sec_acpi_match);
+
+static struct platform_driver sec_driver = {
+	.probe = sec_probe,
+	.remove = sec_remove,
+	.driver = {
+		.name = "hisi_sec_platform_driver",
+		.of_match_table = sec_match,
+		.acpi_match_table = ACPI_PTR(sec_acpi_match),
+	},
+};
+module_platform_driver(sec_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Hisilicon Security Accelerators");
+MODULE_AUTHOR("Zaibo Xu <xuzaibo@huawei.com");
+MODULE_AUTHOR("Jonathan Cameron <jonathan.cameron@huawei.com>");
diff --git a/drivers/crypto/hisilicon/sec/sec_drv.h b/drivers/crypto/hisilicon/sec/sec_drv.h
new file mode 100644
index 000000000000..2d2f186674ba
--- /dev/null
+++ b/drivers/crypto/hisilicon/sec/sec_drv.h
@@ -0,0 +1,428 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2016-2017 Hisilicon Limited. */
+
+#ifndef _SEC_DRV_H_
+#define _SEC_DRV_H_
+
+#include <crypto/algapi.h>
+#include <linux/kfifo.h>
+
+#define SEC_MAX_SGE_NUM			64
+#define SEC_HW_RING_NUM			3
+
+#define SEC_CMD_RING			0
+#define SEC_OUTORDER_RING		1
+#define SEC_DBG_RING			2
+
+/* A reasonable length to balance memory use against flexibility */
+#define SEC_QUEUE_LEN			512
+
+#define SEC_MAX_SGE_NUM   64
+
+struct sec_bd_info {
+#define SEC_BD_W0_T_LEN_M			GENMASK(4, 0)
+#define SEC_BD_W0_T_LEN_S			0
+
+#define SEC_BD_W0_C_WIDTH_M			GENMASK(6, 5)
+#define SEC_BD_W0_C_WIDTH_S			5
+#define   SEC_C_WIDTH_AES_128BIT		0
+#define   SEC_C_WIDTH_AES_8BIT		1
+#define   SEC_C_WIDTH_AES_1BIT		2
+#define   SEC_C_WIDTH_DES_64BIT		0
+#define   SEC_C_WIDTH_DES_8BIT		1
+#define   SEC_C_WIDTH_DES_1BIT		2
+
+#define SEC_BD_W0_C_MODE_M			GENMASK(9, 7)
+#define SEC_BD_W0_C_MODE_S			7
+#define   SEC_C_MODE_ECB			0
+#define   SEC_C_MODE_CBC			1
+#define   SEC_C_MODE_CTR			4
+#define   SEC_C_MODE_CCM			5
+#define   SEC_C_MODE_GCM			6
+#define   SEC_C_MODE_XTS			7
+
+#define SEC_BD_W0_SEQ				BIT(10)
+#define SEC_BD_W0_DE				BIT(11)
+#define SEC_BD_W0_DAT_SKIP_M			GENMASK(13, 12)
+#define SEC_BD_W0_DAT_SKIP_S			12
+#define SEC_BD_W0_C_GRAN_SIZE_19_16_M		GENMASK(17, 14)
+#define SEC_BD_W0_C_GRAN_SIZE_19_16_S		14
+
+#define SEC_BD_W0_CIPHER_M			GENMASK(19, 18)
+#define SEC_BD_W0_CIPHER_S			18
+#define   SEC_CIPHER_NULL			0
+#define   SEC_CIPHER_ENCRYPT			1
+#define   SEC_CIPHER_DECRYPT			2
+
+#define SEC_BD_W0_AUTH_M			GENMASK(21, 20)
+#define SEC_BD_W0_AUTH_S			20
+#define   SEC_AUTH_NULL				0
+#define   SEC_AUTH_MAC				1
+#define   SEC_AUTH_VERIF			2
+
+#define SEC_BD_W0_AI_GEN			BIT(22)
+#define SEC_BD_W0_CI_GEN			BIT(23)
+#define SEC_BD_W0_NO_HPAD			BIT(24)
+#define SEC_BD_W0_HM_M				GENMASK(26, 25)
+#define SEC_BD_W0_HM_S				25
+#define SEC_BD_W0_ICV_OR_SKEY_EN_M		GENMASK(28, 27)
+#define SEC_BD_W0_ICV_OR_SKEY_EN_S		27
+
+/* Multi purpose field - gran size bits for send, flag for recv */
+#define SEC_BD_W0_FLAG_M			GENMASK(30, 29)
+#define SEC_BD_W0_C_GRAN_SIZE_21_20_M		GENMASK(30, 29)
+#define SEC_BD_W0_FLAG_S			29
+#define SEC_BD_W0_C_GRAN_SIZE_21_20_S		29
+
+#define SEC_BD_W0_DONE				BIT(31)
+	u32 w0;
+
+#define SEC_BD_W1_AUTH_GRAN_SIZE_M		GENMASK(21, 0)
+#define SEC_BD_W1_AUTH_GRAN_SIZE_S		0
+#define SEC_BD_W1_M_KEY_EN			BIT(22)
+#define SEC_BD_W1_BD_INVALID			BIT(23)
+#define SEC_BD_W1_ADDR_TYPE			BIT(24)
+
+#define SEC_BD_W1_A_ALG_M			GENMASK(28, 25)
+#define SEC_BD_W1_A_ALG_S			25
+#define   SEC_A_ALG_SHA1			0
+#define   SEC_A_ALG_SHA256			1
+#define   SEC_A_ALG_MD5				2
+#define   SEC_A_ALG_SHA224			3
+#define   SEC_A_ALG_HMAC_SHA1			8
+#define   SEC_A_ALG_HMAC_SHA224			10
+#define   SEC_A_ALG_HMAC_SHA256			11
+#define   SEC_A_ALG_HMAC_MD5			12
+#define   SEC_A_ALG_AES_XCBC			13
+#define   SEC_A_ALG_AES_CMAC			14
+
+#define SEC_BD_W1_C_ALG_M			GENMASK(31, 29)
+#define SEC_BD_W1_C_ALG_S			29
+#define   SEC_C_ALG_DES				0
+#define   SEC_C_ALG_3DES			1
+#define   SEC_C_ALG_AES				2
+
+	u32 w1;
+
+#define SEC_BD_W2_C_GRAN_SIZE_15_0_M		GENMASK(15, 0)
+#define SEC_BD_W2_C_GRAN_SIZE_15_0_S		0
+#define SEC_BD_W2_GRAN_NUM_M			GENMASK(31, 16)
+#define SEC_BD_W2_GRAN_NUM_S			16
+	u32 w2;
+
+#define SEC_BD_W3_AUTH_LEN_OFFSET_M		GENMASK(9, 0)
+#define SEC_BD_W3_AUTH_LEN_OFFSET_S		0
+#define SEC_BD_W3_CIPHER_LEN_OFFSET_M		GENMASK(19, 10)
+#define SEC_BD_W3_CIPHER_LEN_OFFSET_S		10
+#define SEC_BD_W3_MAC_LEN_M			GENMASK(24, 20)
+#define SEC_BD_W3_MAC_LEN_S			20
+#define SEC_BD_W3_A_KEY_LEN_M			GENMASK(29, 25)
+#define SEC_BD_W3_A_KEY_LEN_S			25
+#define SEC_BD_W3_C_KEY_LEN_M			GENMASK(31, 30)
+#define SEC_BD_W3_C_KEY_LEN_S			30
+#define   SEC_KEY_LEN_AES_128			0
+#define   SEC_KEY_LEN_AES_192			1
+#define   SEC_KEY_LEN_AES_256			2
+#define   SEC_KEY_LEN_DES			1
+#define   SEC_KEY_LEN_3DES_3_KEY		1
+#define   SEC_KEY_LEN_3DES_2_KEY		3
+	u32 w3;
+
+	/* W4,5 */
+	union {
+		u32 authkey_addr_lo;
+		u32 authiv_addr_lo;
+	};
+	union {
+		u32 authkey_addr_hi;
+		u32 authiv_addr_hi;
+	};
+
+	/* W6,7 */
+	u32 cipher_key_addr_lo;
+	u32 cipher_key_addr_hi;
+
+	/* W8,9 */
+	u32 cipher_iv_addr_lo;
+	u32 cipher_iv_addr_hi;
+
+	/* W10,11 */
+	u32 data_addr_lo;
+	u32 data_addr_hi;
+
+	/* W12,13 */
+	u32 mac_addr_lo;
+	u32 mac_addr_hi;
+
+	/* W14,15 */
+	u32 cipher_destin_addr_lo;
+	u32 cipher_destin_addr_hi;
+};
+
+enum sec_mem_region {
+	SEC_COMMON = 0,
+	SEC_SAA,
+	SEC_NUM_ADDR_REGIONS
+};
+
+#define SEC_NAME_SIZE				64
+#define SEC_Q_NUM				16
+
+
+/**
+ * struct sec_queue_ring_cmd - store information about a SEC HW cmd ring
+ * @used: Local counter used to cheaply establish if the ring is empty.
+ * @lock: Protect against simultaneous adjusting of the read and write pointers.
+ * @vaddr: Virtual address for the ram pages used for the ring.
+ * @paddr: Physical address of the dma mapped region of ram used for the ring.
+ * @callback: Callback function called on a ring element completing.
+ */
+struct sec_queue_ring_cmd {
+	atomic_t used;
+	struct mutex lock;
+	struct sec_bd_info *vaddr;
+	dma_addr_t paddr;
+	void (*callback)(struct sec_bd_info *resp, void *ctx);
+};
+
+struct sec_debug_bd_info;
+struct sec_queue_ring_db {
+	struct sec_debug_bd_info *vaddr;
+	dma_addr_t paddr;
+};
+
+struct sec_out_bd_info;
+struct sec_queue_ring_cq {
+	struct sec_out_bd_info *vaddr;
+	dma_addr_t paddr;
+};
+
+struct sec_dev_info;
+
+enum sec_cipher_alg {
+	SEC_C_DES_ECB_64,
+	SEC_C_DES_CBC_64,
+
+	SEC_C_3DES_ECB_192_3KEY,
+	SEC_C_3DES_ECB_192_2KEY,
+
+	SEC_C_3DES_CBC_192_3KEY,
+	SEC_C_3DES_CBC_192_2KEY,
+
+	SEC_C_AES_ECB_128,
+	SEC_C_AES_ECB_192,
+	SEC_C_AES_ECB_256,
+
+	SEC_C_AES_CBC_128,
+	SEC_C_AES_CBC_192,
+	SEC_C_AES_CBC_256,
+
+	SEC_C_AES_CTR_128,
+	SEC_C_AES_CTR_192,
+	SEC_C_AES_CTR_256,
+
+	SEC_C_AES_XTS_128,
+	SEC_C_AES_XTS_256,
+
+	SEC_C_NULL,
+};
+
+/**
+ * struct sec_alg_tfm_ctx - hardware specific tranformation context
+ * @cipher_alg: Cipher algorithm enabled include encryption mode.
+ * @key: Key storage if required.
+ * @pkey: DMA address for the key storage.
+ * @req_template: Request template to save time on setup.
+ * @queue: The hardware queue associated with this tfm context.
+ * @lock: Protect key and pkey to ensure they are consistent
+ * @auth_buf: Current context buffer for auth operations.
+ * @backlog: The backlog queue used for cases where our buffers aren't
+ * large enough.
+ */
+struct sec_alg_tfm_ctx {
+	enum sec_cipher_alg cipher_alg;
+	u8 *key;
+	dma_addr_t pkey;
+	struct sec_bd_info req_template;
+	struct sec_queue *queue;
+	struct mutex lock;
+	u8 *auth_buf;
+	struct list_head backlog;
+};
+
+/**
+ * struct sec_request - data associate with a single crypto request
+ * @elements: List of subparts of this request (hardware size restriction)
+ * @num_elements: The number of subparts (used as an optimization)
+ * @lock: Protect elements of this structure against concurrent change.
+ * @tfm_ctx: hardware specific context.
+ * @len_in: length of in sgl from upper layers
+ * @len_out: length of out sgl from upper layers
+ * @dma_iv: initialization vector - phsyical address
+ * @err: store used to track errors across subelements of this request.
+ * @req_base: pointer to base element of associate crypto context.
+ * This is needed to allow shared handling skcipher, ahash etc.
+ * @cb: completion callback.
+ * @backlog_head: list head to allow backlog maintenance.
+ *
+ * The hardware is limited in the maximum size of data that it can
+ * process from a single BD.  Typically this is fairly large (32MB)
+ * but still requires the complexity of splitting the incoming
+ * skreq up into a number of elements complete with appropriate
+ * iv chaining.
+ */
+struct sec_request {
+	struct list_head elements;
+	int num_elements;
+	struct mutex lock;
+	struct sec_alg_tfm_ctx *tfm_ctx;
+	int len_in;
+	int len_out;
+	dma_addr_t dma_iv;
+	int err;
+	struct crypto_async_request *req_base;
+	void (*cb)(struct sec_bd_info *resp, struct crypto_async_request *req);
+	struct list_head backlog_head;
+};
+
+/**
+ * struct sec_request_el - A subpart of a request.
+ * @head: allow us to attach this to the list in the sec_request
+ * @req: hardware block descriptor corresponding to this request subpart
+ * @in: hardware sgl for input - virtual address
+ * @dma_in: hardware sgl for input - physical address
+ * @sgl_in: scatterlist for this request subpart
+ * @out: hardware sgl for output - virtual address
+ * @dma_out: hardware sgl for output - physical address
+ * @sgl_out: scatterlist for this request subpart
+ * @sec_req: The request which this subpart forms a part of
+ * @el_length: Number of bytes in this subpart. Needed to locate
+ * last ivsize chunk for iv chaining.
+ */
+struct sec_request_el {
+	struct list_head head;
+	struct sec_bd_info req;
+	struct sec_hw_sgl *in;
+	dma_addr_t dma_in;
+	struct scatterlist *sgl_in;
+	struct sec_hw_sgl *out;
+	dma_addr_t dma_out;
+	struct scatterlist *sgl_out;
+	struct sec_request *sec_req;
+	size_t el_length;
+};
+
+/**
+ * struct sec_queue - All the information about a HW queue
+ * @dev_info: The parent SEC device to which this queue belongs.
+ * @task_irq: Completion interrupt for the queue.
+ * @name: Human readable queue description also used as irq name.
+ * @ring: The several HW rings associated with one queue.
+ * @regs: The iomapped device registers
+ * @queue_id: Index of the queue used for naming and resource selection.
+ * @in_use: Flag to say if the queue is in use.
+ * @expected: The next expected element to finish assuming we were in order.
+ * @uprocessed: A bitmap to track which OoO elements are done but not handled.
+ * @softqueue: A software queue used when chaining requirements prevent direct
+ *   use of the hardware queues.
+ * @havesoftqueue: A flag to say we have a queues - as we may need one for the
+ *   current mode.
+ * @queuelock: Protect the soft queue from concurrent changes to avoid some
+ *   potential loss of data races.
+ * @shadow: Pointers back to the shadow copy of the hardware ring element
+ *   need because we can't store any context reference in the bd element.
+ */
+struct sec_queue {
+	struct sec_dev_info *dev_info;
+	int task_irq;
+	char name[SEC_NAME_SIZE];
+	struct sec_queue_ring_cmd ring_cmd;
+	struct sec_queue_ring_cq ring_cq;
+	struct sec_queue_ring_db ring_db;
+	void __iomem *regs;
+	u32 queue_id;
+	bool in_use;
+	int expected;
+
+	DECLARE_BITMAP(unprocessed, SEC_QUEUE_LEN);
+	DECLARE_KFIFO_PTR(softqueue, typeof(struct sec_request_el *));
+	bool havesoftqueue;
+	struct mutex queuelock;
+	void *shadow[SEC_QUEUE_LEN];
+};
+
+/**
+ * struct sec_hw_sge: Track each of the 64 element SEC HW SGL entries
+ * @buf: The IOV dma address for this entry.
+ * @len: Length of this IOV.
+ * @pad: Reserved space.
+ */
+struct sec_hw_sge {
+	dma_addr_t buf;
+	unsigned int len;
+	unsigned int pad;
+};
+
+/**
+ * struct sec_hw_sgl: One hardware SGL entry.
+ * @next_sgl: The next entry if we need to chain dma address. Null if last.
+ * @entry_sum_in_chain: The full count of SGEs - only matters for first SGL.
+ * @entry_sum_in_sgl: The number of SGEs in this SGL element.
+ * @flag: Unused in skciphers.
+ * @serial_num: Unsued in skciphers.
+ * @cpuid: Currently unused.
+ * @data_bytes_in_sgl: Count of bytes from all SGEs in this SGL.
+ * @next: Virtual address used to stash the next sgl - useful in completion.
+ * @reserved: A reserved field not currently used.
+ * @sge_entries: The (up to) 64 Scatter Gather Entries, representing IOVs.
+ * @node: Currently unused.
+ */
+struct sec_hw_sgl {
+	dma_addr_t next_sgl;
+	u16 entry_sum_in_chain;
+	u16 entry_sum_in_sgl;
+	u32 flag;
+	u64 serial_num;
+	u32 cpuid;
+	u32 data_bytes_in_sgl;
+	struct sec_hw_sgl *next;
+	u64 reserved;
+	struct sec_hw_sge  sge_entries[SEC_MAX_SGE_NUM];
+	u8 node[16];
+};
+
+struct dma_pool;
+
+/**
+ * struct sec_dev_info: The full SEC unit comprising queues and processors.
+ * @sec_id: Index used to track which SEC this is when more than one is present.
+ * @num_saas: The number of backed processors enabled.
+ * @regs: iomapped register regions shared by whole SEC unit.
+ * @dev_lock: Protects concurrent queue allocation / freeing for the SEC.
+ * @queues: The 16 queues that this SEC instance provides.
+ * @dev: Device pointer.
+ * @hw_sgl_pool: DMA pool used to mimise mapping for the scatter gather lists.
+ */
+struct sec_dev_info {
+	int sec_id;
+	int num_saas;
+	void __iomem *regs[SEC_NUM_ADDR_REGIONS];
+	struct mutex dev_lock;
+	int queues_in_use;
+	struct sec_queue queues[SEC_Q_NUM];
+	struct device *dev;
+	struct dma_pool *hw_sgl_pool;
+};
+
+int sec_queue_send(struct sec_queue *queue, struct sec_bd_info *msg, void *ctx);
+bool sec_queue_can_enqueue(struct sec_queue *queue, int num);
+int sec_queue_stop_release(struct sec_queue *queue);
+struct sec_queue *sec_queue_alloc_start_safe(void);
+bool sec_queue_empty(struct sec_queue *queue);
+
+/* Algorithm specific elements from sec_algs.c */
+void sec_alg_callback(struct sec_bd_info *resp, void *ctx);
+int sec_algs_register(void);
+void sec_algs_unregister(void);
+
+#endif /* _SEC_DRV_H_ */
-- 
cgit v1.2.3


From e4a1f7858ab834b2cdddfc51be2f5debae782029 Mon Sep 17 00:00:00 2001
From: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Date: Mon, 23 Jul 2018 16:49:55 +0100
Subject: arm64: dts: hisi: add SEC crypto accelerator nodes for hip07 SoC

Enable all 4 SEC units available on d05 boards.

Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm64/boot/dts/hisilicon/hip07.dtsi | 284 +++++++++++++++++++++++++++++++
 1 file changed, 284 insertions(+)

diff --git a/arch/arm64/boot/dts/hisilicon/hip07.dtsi b/arch/arm64/boot/dts/hisilicon/hip07.dtsi
index 9c10030a07f8..c33adefc3061 100644
--- a/arch/arm64/boot/dts/hisilicon/hip07.dtsi
+++ b/arch/arm64/boot/dts/hisilicon/hip07.dtsi
@@ -1049,7 +1049,74 @@
 			num-pins = <2>;
 		};
 	};
+	p0_mbigen_alg_a:interrupt-controller@d0080000 {
+		compatible = "hisilicon,mbigen-v2";
+		reg = <0x0 0xd0080000 0x0 0x10000>;
 
+		p0_mbigen_sec_a: intc_sec {
+			msi-parent = <&p0_its_dsa_a 0x40400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <33>;
+		};
+		p0_mbigen_smmu_alg_a: intc_smmu_alg {
+			msi-parent = <&p0_its_dsa_a 0x40b1b>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <3>;
+		};
+	};
+	p0_mbigen_alg_b:interrupt-controller@8,d0080000 {
+		compatible = "hisilicon,mbigen-v2";
+		reg = <0x8 0xd0080000 0x0 0x10000>;
+
+		p0_mbigen_sec_b: intc_sec {
+			msi-parent = <&p0_its_dsa_b 0x42400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <33>;
+		};
+		p0_mbigen_smmu_alg_b: intc_smmu_alg {
+			msi-parent = <&p0_its_dsa_b 0x42b1b>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <3>;
+		};
+	};
+	p1_mbigen_alg_a:interrupt-controller@400,d0080000 {
+		compatible = "hisilicon,mbigen-v2";
+		reg = <0x400 0xd0080000 0x0 0x10000>;
+
+		p1_mbigen_sec_a: intc_sec {
+			msi-parent = <&p1_its_dsa_a 0x44400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <33>;
+		};
+		p1_mbigen_smmu_alg_a: intc_smmu_alg {
+			msi-parent = <&p1_its_dsa_a 0x44b1b>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <3>;
+		};
+	};
+	p1_mbigen_alg_b:interrupt-controller@408,d0080000 {
+		compatible = "hisilicon,mbigen-v2";
+		reg = <0x408 0xd0080000 0x0 0x10000>;
+
+		p1_mbigen_sec_b: intc_sec {
+			msi-parent = <&p1_its_dsa_b 0x46400>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <33>;
+		};
+		p1_mbigen_smmu_alg_b: intc_smmu_alg {
+			msi-parent = <&p1_its_dsa_b 0x46b1b>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+			num-pins = <3>;
+		};
+	};
 	p0_mbigen_dsa_a: interrupt-controller@c0080000 {
 		compatible = "hisilicon,mbigen-v2";
 		reg = <0x0 0xc0080000 0x0 0x10000>;
@@ -1107,6 +1174,58 @@
 		hisilicon,broken-prefetch-cmd;
 		status = "disabled";
 	};
+	p0_smmu_alg_a: smmu_alg@d0040000 {
+		compatible = "arm,smmu-v3";
+		reg = <0x0 0xd0040000 0x0 0x20000>;
+		interrupt-parent = <&p0_mbigen_smmu_alg_a>;
+		interrupts = <733 1>,
+		<734 1>,
+		<735 1>;
+		interrupt-names = "eventq", "gerror", "priq";
+		#iommu-cells = <1>;
+		dma-coherent;
+		hisilicon,broken-prefetch-cmd;
+		/* smmu-cb-memtype = <0x0 0x1>;*/
+	};
+	p0_smmu_alg_b: smmu_alg@8,d0040000 {
+		compatible = "arm,smmu-v3";
+		reg = <0x8 0xd0040000 0x0 0x20000>;
+		interrupt-parent = <&p0_mbigen_smmu_alg_b>;
+		interrupts = <733 1>,
+		<734 1>,
+		<735 1>;
+		interrupt-names = "eventq", "gerror", "priq";
+		#iommu-cells = <1>;
+		dma-coherent;
+		hisilicon,broken-prefetch-cmd;
+		/* smmu-cb-memtype = <0x0 0x1>;*/
+	};
+	p1_smmu_alg_a: smmu_alg@400,d0040000 {
+		compatible = "arm,smmu-v3";
+		reg = <0x400 0xd0040000 0x0 0x20000>;
+		interrupt-parent = <&p1_mbigen_smmu_alg_a>;
+		interrupts = <733 1>,
+		<734 1>,
+		<735 1>;
+		interrupt-names = "eventq", "gerror", "priq";
+		#iommu-cells = <1>;
+		dma-coherent;
+		hisilicon,broken-prefetch-cmd;
+		/* smmu-cb-memtype = <0x0 0x1>;*/
+	};
+	p1_smmu_alg_b: smmu_alg@408,d0040000 {
+		compatible = "arm,smmu-v3";
+		reg = <0x408 0xd0040000 0x0 0x20000>;
+		interrupt-parent = <&p1_mbigen_smmu_alg_b>;
+		interrupts = <733 1>,
+		<734 1>,
+		<735 1>;
+		interrupt-names = "eventq", "gerror", "priq";
+		#iommu-cells = <1>;
+		dma-coherent;
+		hisilicon,broken-prefetch-cmd;
+		/* smmu-cb-memtype = <0x0 0x1>;*/
+	};
 
 	soc {
 		compatible = "simple-bus";
@@ -1603,5 +1722,170 @@
 					 0x0 0 0 4 &mbigen_pcie2_a 671 4>;
 			status = "disabled";
 		};
+		p0_sec_a: crypto@d2000000 {
+			compatible = "hisilicon,hip07-sec";
+			reg = <0x0 0xd0000000 0x0 0x10000
+			       0x0 0xd2000000 0x0 0x10000
+			       0x0 0xd2010000 0x0 0x10000
+			       0x0 0xd2020000 0x0 0x10000
+			       0x0 0xd2030000 0x0 0x10000
+			       0x0 0xd2040000 0x0 0x10000
+			       0x0 0xd2050000 0x0 0x10000
+			       0x0 0xd2060000 0x0 0x10000
+			       0x0 0xd2070000 0x0 0x10000
+			       0x0 0xd2080000 0x0 0x10000
+			       0x0 0xd2090000 0x0 0x10000
+			       0x0 0xd20a0000 0x0 0x10000
+			       0x0 0xd20b0000 0x0 0x10000
+			       0x0 0xd20c0000 0x0 0x10000
+			       0x0 0xd20d0000 0x0 0x10000
+			       0x0 0xd20e0000 0x0 0x10000
+			       0x0 0xd20f0000 0x0 0x10000
+			       0x0 0xd2100000 0x0 0x10000>;
+			interrupt-parent = <&p0_mbigen_sec_a>;
+			iommus = <&p0_smmu_alg_a 0x600>;
+			dma-coherent;
+			interrupts = <576 4>,
+				     <577 1>, <578 4>,
+				     <579 1>, <580 4>,
+				     <581 1>, <582 4>,
+				     <583 1>, <584 4>,
+				     <585 1>, <586 4>,
+				     <587 1>, <588 4>,
+				     <589 1>, <590 4>,
+				     <591 1>, <592 4>,
+				     <593 1>, <594 4>,
+				     <595 1>, <596 4>,
+				     <597 1>, <598 4>,
+				     <599 1>, <600 4>,
+				     <601 1>, <602 4>,
+				     <603 1>, <604 4>,
+				     <605 1>, <606 4>,
+				     <607 1>, <608 4>;
+		};
+		p0_sec_b: crypto@8,d2000000 {
+			compatible = "hisilicon,hip07-sec";
+			reg = <0x8 0xd0000000 0x0 0x10000
+			       0x8 0xd2000000 0x0 0x10000
+			       0x8 0xd2010000 0x0 0x10000
+			       0x8 0xd2020000 0x0 0x10000
+			       0x8 0xd2030000 0x0 0x10000
+			       0x8 0xd2040000 0x0 0x10000
+			       0x8 0xd2050000 0x0 0x10000
+			       0x8 0xd2060000 0x0 0x10000
+			       0x8 0xd2070000 0x0 0x10000
+			       0x8 0xd2080000 0x0 0x10000
+			       0x8 0xd2090000 0x0 0x10000
+			       0x8 0xd20a0000 0x0 0x10000
+			       0x8 0xd20b0000 0x0 0x10000
+			       0x8 0xd20c0000 0x0 0x10000
+			       0x8 0xd20d0000 0x0 0x10000
+			       0x8 0xd20e0000 0x0 0x10000
+			       0x8 0xd20f0000 0x0 0x10000
+			       0x8 0xd2100000 0x0 0x10000>;
+			interrupt-parent = <&p0_mbigen_sec_b>;
+			iommus = <&p0_smmu_alg_b 0x600>;
+			dma-coherent;
+			interrupts = <576 4>,
+				     <577 1>, <578 4>,
+				     <579 1>, <580 4>,
+				     <581 1>, <582 4>,
+				     <583 1>, <584 4>,
+				     <585 1>, <586 4>,
+				     <587 1>, <588 4>,
+				     <589 1>, <590 4>,
+				     <591 1>, <592 4>,
+				     <593 1>, <594 4>,
+				     <595 1>, <596 4>,
+				     <597 1>, <598 4>,
+				     <599 1>, <600 4>,
+				     <601 1>, <602 4>,
+				     <603 1>, <604 4>,
+				     <605 1>, <606 4>,
+				     <607 1>, <608 4>;
+		};
+		p1_sec_a: crypto@400,d2000000 {
+			compatible = "hisilicon,hip07-sec";
+			reg = <0x400 0xd0000000 0x0 0x10000
+			       0x400 0xd2000000 0x0 0x10000
+			       0x400 0xd2010000 0x0 0x10000
+			       0x400 0xd2020000 0x0 0x10000
+			       0x400 0xd2030000 0x0 0x10000
+			       0x400 0xd2040000 0x0 0x10000
+			       0x400 0xd2050000 0x0 0x10000
+			       0x400 0xd2060000 0x0 0x10000
+			       0x400 0xd2070000 0x0 0x10000
+			       0x400 0xd2080000 0x0 0x10000
+			       0x400 0xd2090000 0x0 0x10000
+			       0x400 0xd20a0000 0x0 0x10000
+			       0x400 0xd20b0000 0x0 0x10000
+			       0x400 0xd20c0000 0x0 0x10000
+			       0x400 0xd20d0000 0x0 0x10000
+			       0x400 0xd20e0000 0x0 0x10000
+			       0x400 0xd20f0000 0x0 0x10000
+			       0x400 0xd2100000 0x0 0x10000>;
+			interrupt-parent = <&p1_mbigen_sec_a>;
+			iommus = <&p1_smmu_alg_a 0x600>;
+			dma-coherent;
+			interrupts = <576 4>,
+				     <577 1>, <578 4>,
+				     <579 1>, <580 4>,
+				     <581 1>, <582 4>,
+				     <583 1>, <584 4>,
+				     <585 1>, <586 4>,
+				     <587 1>, <588 4>,
+				     <589 1>, <590 4>,
+				     <591 1>, <592 4>,
+				     <593 1>, <594 4>,
+				     <595 1>, <596 4>,
+				     <597 1>, <598 4>,
+				     <599 1>, <600 4>,
+				     <601 1>, <602 4>,
+				     <603 1>, <604 4>,
+				     <605 1>, <606 4>,
+				     <607 1>, <608 4>;
+		};
+		p1_sec_b: crypto@408,d2000000 {
+			compatible = "hisilicon,hip07-sec";
+			reg = <0x408 0xd0000000 0x0 0x10000
+			       0x408 0xd2000000 0x0 0x10000
+			       0x408 0xd2010000 0x0 0x10000
+			       0x408 0xd2020000 0x0 0x10000
+			       0x408 0xd2030000 0x0 0x10000
+			       0x408 0xd2040000 0x0 0x10000
+			       0x408 0xd2050000 0x0 0x10000
+			       0x408 0xd2060000 0x0 0x10000
+			       0x408 0xd2070000 0x0 0x10000
+			       0x408 0xd2080000 0x0 0x10000
+			       0x408 0xd2090000 0x0 0x10000
+			       0x408 0xd20a0000 0x0 0x10000
+			       0x408 0xd20b0000 0x0 0x10000
+			       0x408 0xd20c0000 0x0 0x10000
+			       0x408 0xd20d0000 0x0 0x10000
+			       0x408 0xd20e0000 0x0 0x10000
+			       0x408 0xd20f0000 0x0 0x10000
+			       0x408 0xd2100000 0x0 0x10000>;
+			interrupt-parent = <&p1_mbigen_sec_b>;
+			iommus = <&p1_smmu_alg_b 0x600>;
+			dma-coherent;
+			interrupts = <576 4>,
+				     <577 1>, <578 4>,
+				     <579 1>, <580 4>,
+				     <581 1>, <582 4>,
+				     <583 1>, <584 4>,
+				     <585 1>, <586 4>,
+				     <587 1>, <588 4>,
+				     <589 1>, <590 4>,
+				     <591 1>, <592 4>,
+				     <593 1>, <594 4>,
+				     <595 1>, <596 4>,
+				     <597 1>, <598 4>,
+				     <599 1>, <600 4>,
+				     <601 1>, <602 4>,
+				     <603 1>, <604 4>,
+				     <605 1>, <606 4>,
+				     <607 1>, <608 4>;
+		};
+
 	};
 };
-- 
cgit v1.2.3


From 0567fc9e90b9b1c8dbce8a5468758e6206744d4a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 23 Jul 2018 09:57:50 -0700
Subject: crypto: skcipher - fix aligning block size in skcipher_copy_iv()

The ALIGN() macro needs to be passed the alignment, not the alignmask
(which is the alignment minus 1).

Fixes: b286d8b1a690 ("crypto: skcipher - Add skcipher walk interface")
Cc: <stable@vger.kernel.org> # v4.10+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/skcipher.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 7d6a49fe3047..4f6b8dadaceb 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -398,7 +398,7 @@ static int skcipher_copy_iv(struct skcipher_walk *walk)
 	unsigned size;
 	u8 *iv;
 
-	aligned_bs = ALIGN(bs, alignmask);
+	aligned_bs = ALIGN(bs, alignmask + 1);
 
 	/* Minimum size to align buffer by alignmask. */
 	size = alignmask & ~a;
-- 
cgit v1.2.3


From 8c30fbe63e4eff1b221f8db70ae5c48a9331eae0 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 23 Jul 2018 10:01:33 -0700
Subject: crypto: scatterwalk - remove 'chain' argument from
 scatterwalk_crypto_chain()

All callers pass chain=0 to scatterwalk_crypto_chain().

Remove this unneeded parameter.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/lrw.c                  | 4 ++--
 crypto/scatterwalk.c          | 2 +-
 crypto/xts.c                  | 4 ++--
 include/crypto/scatterwalk.h  | 8 +-------
 net/tls/tls_device_fallback.c | 2 +-
 5 files changed, 7 insertions(+), 13 deletions(-)

diff --git a/crypto/lrw.c b/crypto/lrw.c
index 954a7064a179..393a782679c7 100644
--- a/crypto/lrw.c
+++ b/crypto/lrw.c
@@ -188,7 +188,7 @@ static int post_crypt(struct skcipher_request *req)
 	if (rctx->dst != sg) {
 		rctx->dst[0] = *sg;
 		sg_unmark_end(rctx->dst);
-		scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 0, 2);
+		scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 2);
 	}
 	rctx->dst[0].length -= offset - sg->offset;
 	rctx->dst[0].offset = offset;
@@ -265,7 +265,7 @@ static int pre_crypt(struct skcipher_request *req)
 	if (rctx->src != sg) {
 		rctx->src[0] = *sg;
 		sg_unmark_end(rctx->src);
-		scatterwalk_crypto_chain(rctx->src, sg_next(sg), 0, 2);
+		scatterwalk_crypto_chain(rctx->src, sg_next(sg), 2);
 	}
 	rctx->src[0].length -= offset - sg->offset;
 	rctx->src[0].offset = offset;
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index c16c94f88733..d0b92c1cd6e9 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -91,7 +91,7 @@ struct scatterlist *scatterwalk_ffwd(struct scatterlist dst[2],
 
 	sg_init_table(dst, 2);
 	sg_set_page(dst, sg_page(src), src->length - len, src->offset + len);
-	scatterwalk_crypto_chain(dst, sg_next(src), 0, 2);
+	scatterwalk_crypto_chain(dst, sg_next(src), 2);
 
 	return dst;
 }
diff --git a/crypto/xts.c b/crypto/xts.c
index 12284183bd20..ccf55fbb8bc2 100644
--- a/crypto/xts.c
+++ b/crypto/xts.c
@@ -138,7 +138,7 @@ static int post_crypt(struct skcipher_request *req)
 	if (rctx->dst != sg) {
 		rctx->dst[0] = *sg;
 		sg_unmark_end(rctx->dst);
-		scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 0, 2);
+		scatterwalk_crypto_chain(rctx->dst, sg_next(sg), 2);
 	}
 	rctx->dst[0].length -= offset - sg->offset;
 	rctx->dst[0].offset = offset;
@@ -204,7 +204,7 @@ static int pre_crypt(struct skcipher_request *req)
 	if (rctx->src != sg) {
 		rctx->src[0] = *sg;
 		sg_unmark_end(rctx->src);
-		scatterwalk_crypto_chain(rctx->src, sg_next(sg), 0, 2);
+		scatterwalk_crypto_chain(rctx->src, sg_next(sg), 2);
 	}
 	rctx->src[0].length -= offset - sg->offset;
 	rctx->src[0].offset = offset;
diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index 880e6be9e95e..eac72840a7d2 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -22,14 +22,8 @@
 #include <linux/scatterlist.h>
 
 static inline void scatterwalk_crypto_chain(struct scatterlist *head,
-					    struct scatterlist *sg,
-					    int chain, int num)
+					    struct scatterlist *sg, int num)
 {
-	if (chain) {
-		head->length += sg->length;
-		sg = sg_next(sg);
-	}
-
 	if (sg)
 		sg_chain(head, num, sg);
 	else
diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c
index 748914abdb60..4e1ec12bc0fb 100644
--- a/net/tls/tls_device_fallback.c
+++ b/net/tls/tls_device_fallback.c
@@ -42,7 +42,7 @@ static void chain_to_walk(struct scatterlist *sg, struct scatter_walk *walk)
 	sg_set_page(sg, sg_page(src),
 		    src->length - diff, walk->offset);
 
-	scatterwalk_crypto_chain(sg, sg_next(src), 0, 2);
+	scatterwalk_crypto_chain(sg, sg_next(src), 2);
 }
 
 static int tls_enc_record(struct aead_request *aead_req,
-- 
cgit v1.2.3


From 3dd8cc00c34ab9cde4bcc808ebc607e7b9861280 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 23 Jul 2018 10:04:28 -0700
Subject: crypto: scatterwalk - remove scatterwalk_samebuf()

scatterwalk_samebuf() is never used.  Remove it.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/crypto/scatterwalk.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/include/crypto/scatterwalk.h b/include/crypto/scatterwalk.h
index eac72840a7d2..a66c127a20ed 100644
--- a/include/crypto/scatterwalk.h
+++ b/include/crypto/scatterwalk.h
@@ -30,13 +30,6 @@ static inline void scatterwalk_crypto_chain(struct scatterlist *head,
 		sg_mark_end(head);
 }
 
-static inline unsigned long scatterwalk_samebuf(struct scatter_walk *walk_in,
-						struct scatter_walk *walk_out)
-{
-	return !(((sg_page(walk_in->sg) - sg_page(walk_out->sg)) << PAGE_SHIFT) +
-		 (int)(walk_in->offset - walk_out->offset));
-}
-
 static inline unsigned int scatterwalk_pagelen(struct scatter_walk *walk)
 {
 	unsigned int len = walk->sg->offset + walk->sg->length - walk->offset;
-- 
cgit v1.2.3


From 2a57c0be225f8c7140f8791819f5afbb6fb34c5a Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 23 Jul 2018 10:21:29 -0700
Subject: crypto: skcipher - remove unnecessary setting of walk->nbytes

Setting 'walk->nbytes = walk->total' in skcipher_walk_first() doesn't
make sense because actually walk->nbytes needs to be set to the length
of the first step in the walk, which may be less than walk->total.  This
is done by skcipher_walk_next() which is called immediately afterwards.
Also walk->nbytes was already set to 0 in skcipher_walk_skcipher(),
which is a better default value in case it's forgotten to be set later.

Therefore, remove the unnecessary assignment to walk->nbytes.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/skcipher.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 4f6b8dadaceb..835e5d36ad59 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -436,7 +436,6 @@ static int skcipher_walk_first(struct skcipher_walk *walk)
 	}
 
 	walk->page = NULL;
-	walk->nbytes = walk->total;
 
 	return skcipher_walk_next(walk);
 }
-- 
cgit v1.2.3


From 8088d3dd4d7c6933a65aa169393b5d88d8065672 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 23 Jul 2018 10:54:56 -0700
Subject: crypto: skcipher - fix crash flushing dcache in error path

scatterwalk_done() is only meant to be called after a nonzero number of
bytes have been processed, since scatterwalk_pagedone() will flush the
dcache of the *previous* page.  But in the error case of
skcipher_walk_done(), e.g. if the input wasn't an integer number of
blocks, scatterwalk_done() was actually called after advancing 0 bytes.
This caused a crash ("BUG: unable to handle kernel paging request")
during '!PageSlab(page)' on architectures like arm and arm64 that define
ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE, provided that the input was
page-aligned as in that case walk->offset == 0.

Fix it by reorganizing skcipher_walk_done() to skip the
scatterwalk_advance() and scatterwalk_done() if an error has occurred.

This bug was found by syzkaller fuzzing.

Reproducer, assuming ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE:

	#include <linux/if_alg.h>
	#include <sys/socket.h>
	#include <unistd.h>

	int main()
	{
		struct sockaddr_alg addr = {
			.salg_type = "skcipher",
			.salg_name = "cbc(aes-generic)",
		};
		char buffer[4096] __attribute__((aligned(4096))) = { 0 };
		int fd;

		fd = socket(AF_ALG, SOCK_SEQPACKET, 0);
		bind(fd, (void *)&addr, sizeof(addr));
		setsockopt(fd, SOL_ALG, ALG_SET_KEY, buffer, 16);
		fd = accept(fd, NULL, NULL);
		write(fd, buffer, 15);
		read(fd, buffer, 15);
	}

Reported-by: Liu Chao <liuchao741@huawei.com>
Fixes: b286d8b1a690 ("crypto: skcipher - Add skcipher walk interface")
Cc: <stable@vger.kernel.org> # v4.10+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/skcipher.c | 53 +++++++++++++++++++++++++++--------------------------
 1 file changed, 27 insertions(+), 26 deletions(-)

diff --git a/crypto/skcipher.c b/crypto/skcipher.c
index 835e5d36ad59..0bd8c6caa498 100644
--- a/crypto/skcipher.c
+++ b/crypto/skcipher.c
@@ -95,7 +95,7 @@ static inline u8 *skcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static int skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize)
+static void skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize)
 {
 	u8 *addr;
 
@@ -103,23 +103,24 @@ static int skcipher_done_slow(struct skcipher_walk *walk, unsigned int bsize)
 	addr = skcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize,
 			       (walk->flags & SKCIPHER_WALK_PHYS) ? 2 : 1);
-	return 0;
 }
 
 int skcipher_walk_done(struct skcipher_walk *walk, int err)
 {
-	unsigned int n = walk->nbytes - err;
-	unsigned int nbytes;
-
-	nbytes = walk->total - n;
-
-	if (unlikely(err < 0)) {
-		nbytes = 0;
-		n = 0;
-	} else if (likely(!(walk->flags & (SKCIPHER_WALK_PHYS |
-					   SKCIPHER_WALK_SLOW |
-					   SKCIPHER_WALK_COPY |
-					   SKCIPHER_WALK_DIFF)))) {
+	unsigned int n; /* bytes processed */
+	bool more;
+
+	if (unlikely(err < 0))
+		goto finish;
+
+	n = walk->nbytes - err;
+	walk->total -= n;
+	more = (walk->total != 0);
+
+	if (likely(!(walk->flags & (SKCIPHER_WALK_PHYS |
+				    SKCIPHER_WALK_SLOW |
+				    SKCIPHER_WALK_COPY |
+				    SKCIPHER_WALK_DIFF)))) {
 unmap_src:
 		skcipher_unmap_src(walk);
 	} else if (walk->flags & SKCIPHER_WALK_DIFF) {
@@ -131,28 +132,28 @@ unmap_src:
 		skcipher_unmap_dst(walk);
 	} else if (unlikely(walk->flags & SKCIPHER_WALK_SLOW)) {
 		if (WARN_ON(err)) {
+			/* unexpected case; didn't process all bytes */
 			err = -EINVAL;
-			nbytes = 0;
-		} else
-			n = skcipher_done_slow(walk, n);
+			goto finish;
+		}
+		skcipher_done_slow(walk, n);
+		goto already_advanced;
 	}
 
-	if (err > 0)
-		err = 0;
-
-	walk->total = nbytes;
-	walk->nbytes = nbytes;
-
 	scatterwalk_advance(&walk->in, n);
 	scatterwalk_advance(&walk->out, n);
-	scatterwalk_done(&walk->in, 0, nbytes);
-	scatterwalk_done(&walk->out, 1, nbytes);
+already_advanced:
+	scatterwalk_done(&walk->in, 0, more);
+	scatterwalk_done(&walk->out, 1, more);
 
-	if (nbytes) {
+	if (more) {
 		crypto_yield(walk->flags & SKCIPHER_WALK_SLEEP ?
 			     CRYPTO_TFM_REQ_MAY_SLEEP : 0);
 		return skcipher_walk_next(walk);
 	}
+	err = 0;
+finish:
+	walk->nbytes = 0;
 
 	/* Short-circuit for the common/fast path. */
 	if (!((unsigned long)walk->buffer | (unsigned long)walk->page))
-- 
cgit v1.2.3


From 0868def3e4100591e7a1fdbf3eed1439cc8f7ca3 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 23 Jul 2018 10:54:57 -0700
Subject: crypto: blkcipher - fix crash flushing dcache in error path

Like the skcipher_walk case:

scatterwalk_done() is only meant to be called after a nonzero number of
bytes have been processed, since scatterwalk_pagedone() will flush the
dcache of the *previous* page.  But in the error case of
blkcipher_walk_done(), e.g. if the input wasn't an integer number of
blocks, scatterwalk_done() was actually called after advancing 0 bytes.
This caused a crash ("BUG: unable to handle kernel paging request")
during '!PageSlab(page)' on architectures like arm and arm64 that define
ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE, provided that the input was
page-aligned as in that case walk->offset == 0.

Fix it by reorganizing blkcipher_walk_done() to skip the
scatterwalk_advance() and scatterwalk_done() if an error has occurred.

This bug was found by syzkaller fuzzing.

Reproducer, assuming ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE:

	#include <linux/if_alg.h>
	#include <sys/socket.h>
	#include <unistd.h>

	int main()
	{
		struct sockaddr_alg addr = {
			.salg_type = "skcipher",
			.salg_name = "ecb(aes-generic)",
		};
		char buffer[4096] __attribute__((aligned(4096))) = { 0 };
		int fd;

		fd = socket(AF_ALG, SOCK_SEQPACKET, 0);
		bind(fd, (void *)&addr, sizeof(addr));
		setsockopt(fd, SOL_ALG, ALG_SET_KEY, buffer, 16);
		fd = accept(fd, NULL, NULL);
		write(fd, buffer, 15);
		read(fd, buffer, 15);
	}

Reported-by: Liu Chao <liuchao741@huawei.com>
Fixes: 5cde0af2a982 ("[CRYPTO] cipher: Added block cipher type")
Cc: <stable@vger.kernel.org> # v2.6.19+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/blkcipher.c | 54 ++++++++++++++++++++++++++----------------------------
 1 file changed, 26 insertions(+), 28 deletions(-)

diff --git a/crypto/blkcipher.c b/crypto/blkcipher.c
index dd4dcab3766a..f93abf13b5d4 100644
--- a/crypto/blkcipher.c
+++ b/crypto/blkcipher.c
@@ -70,19 +70,18 @@ static inline u8 *blkcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static inline unsigned int blkcipher_done_slow(struct blkcipher_walk *walk,
-					       unsigned int bsize)
+static inline void blkcipher_done_slow(struct blkcipher_walk *walk,
+				       unsigned int bsize)
 {
 	u8 *addr;
 
 	addr = (u8 *)ALIGN((unsigned long)walk->buffer, walk->alignmask + 1);
 	addr = blkcipher_get_spot(addr, bsize);
 	scatterwalk_copychunks(addr, &walk->out, bsize, 1);
-	return bsize;
 }
 
-static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk,
-					       unsigned int n)
+static inline void blkcipher_done_fast(struct blkcipher_walk *walk,
+				       unsigned int n)
 {
 	if (walk->flags & BLKCIPHER_WALK_COPY) {
 		blkcipher_map_dst(walk);
@@ -96,49 +95,48 @@ static inline unsigned int blkcipher_done_fast(struct blkcipher_walk *walk,
 
 	scatterwalk_advance(&walk->in, n);
 	scatterwalk_advance(&walk->out, n);
-
-	return n;
 }
 
 int blkcipher_walk_done(struct blkcipher_desc *desc,
 			struct blkcipher_walk *walk, int err)
 {
-	unsigned int nbytes = 0;
+	unsigned int n; /* bytes processed */
+	bool more;
 
-	if (likely(err >= 0)) {
-		unsigned int n = walk->nbytes - err;
+	if (unlikely(err < 0))
+		goto finish;
 
-		if (likely(!(walk->flags & BLKCIPHER_WALK_SLOW)))
-			n = blkcipher_done_fast(walk, n);
-		else if (WARN_ON(err)) {
-			err = -EINVAL;
-			goto err;
-		} else
-			n = blkcipher_done_slow(walk, n);
+	n = walk->nbytes - err;
+	walk->total -= n;
+	more = (walk->total != 0);
 
-		nbytes = walk->total - n;
-		err = 0;
+	if (likely(!(walk->flags & BLKCIPHER_WALK_SLOW))) {
+		blkcipher_done_fast(walk, n);
+	} else {
+		if (WARN_ON(err)) {
+			/* unexpected case; didn't process all bytes */
+			err = -EINVAL;
+			goto finish;
+		}
+		blkcipher_done_slow(walk, n);
 	}
 
-	scatterwalk_done(&walk->in, 0, nbytes);
-	scatterwalk_done(&walk->out, 1, nbytes);
+	scatterwalk_done(&walk->in, 0, more);
+	scatterwalk_done(&walk->out, 1, more);
 
-err:
-	walk->total = nbytes;
-	walk->nbytes = nbytes;
-
-	if (nbytes) {
+	if (more) {
 		crypto_yield(desc->flags);
 		return blkcipher_walk_next(desc, walk);
 	}
-
+	err = 0;
+finish:
+	walk->nbytes = 0;
 	if (walk->iv != desc->info)
 		memcpy(desc->info, walk->iv, walk->ivsize);
 	if (walk->buffer != walk->page)
 		kfree(walk->buffer);
 	if (walk->page)
 		free_page((unsigned long)walk->page);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(blkcipher_walk_done);
-- 
cgit v1.2.3


From 318abdfbe708aaaa652c79fb500e9bd60521f9dc Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Mon, 23 Jul 2018 10:54:58 -0700
Subject: crypto: ablkcipher - fix crash flushing dcache in error path

Like the skcipher_walk and blkcipher_walk cases:

scatterwalk_done() is only meant to be called after a nonzero number of
bytes have been processed, since scatterwalk_pagedone() will flush the
dcache of the *previous* page.  But in the error case of
ablkcipher_walk_done(), e.g. if the input wasn't an integer number of
blocks, scatterwalk_done() was actually called after advancing 0 bytes.
This caused a crash ("BUG: unable to handle kernel paging request")
during '!PageSlab(page)' on architectures like arm and arm64 that define
ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE, provided that the input was
page-aligned as in that case walk->offset == 0.

Fix it by reorganizing ablkcipher_walk_done() to skip the
scatterwalk_advance() and scatterwalk_done() if an error has occurred.

Reported-by: Liu Chao <liuchao741@huawei.com>
Fixes: bf06099db18a ("crypto: skcipher - Add ablkcipher_walk interfaces")
Cc: <stable@vger.kernel.org> # v2.6.35+
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/ablkcipher.c | 57 ++++++++++++++++++++++++-----------------------------
 1 file changed, 26 insertions(+), 31 deletions(-)

diff --git a/crypto/ablkcipher.c b/crypto/ablkcipher.c
index 1edb5000d783..8882e90e868e 100644
--- a/crypto/ablkcipher.c
+++ b/crypto/ablkcipher.c
@@ -71,11 +71,9 @@ static inline u8 *ablkcipher_get_spot(u8 *start, unsigned int len)
 	return max(start, end_page);
 }
 
-static inline unsigned int ablkcipher_done_slow(struct ablkcipher_walk *walk,
-						unsigned int bsize)
+static inline void ablkcipher_done_slow(struct ablkcipher_walk *walk,
+					unsigned int n)
 {
-	unsigned int n = bsize;
-
 	for (;;) {
 		unsigned int len_this_page = scatterwalk_pagelen(&walk->out);
 
@@ -87,17 +85,13 @@ static inline unsigned int ablkcipher_done_slow(struct ablkcipher_walk *walk,
 		n -= len_this_page;
 		scatterwalk_start(&walk->out, sg_next(walk->out.sg));
 	}
-
-	return bsize;
 }
 
-static inline unsigned int ablkcipher_done_fast(struct ablkcipher_walk *walk,
-						unsigned int n)
+static inline void ablkcipher_done_fast(struct ablkcipher_walk *walk,
+					unsigned int n)
 {
 	scatterwalk_advance(&walk->in, n);
 	scatterwalk_advance(&walk->out, n);
-
-	return n;
 }
 
 static int ablkcipher_walk_next(struct ablkcipher_request *req,
@@ -107,39 +101,40 @@ int ablkcipher_walk_done(struct ablkcipher_request *req,
 			 struct ablkcipher_walk *walk, int err)
 {
 	struct crypto_tfm *tfm = req->base.tfm;
-	unsigned int nbytes = 0;
+	unsigned int n; /* bytes processed */
+	bool more;
 
-	if (likely(err >= 0)) {
-		unsigned int n = walk->nbytes - err;
+	if (unlikely(err < 0))
+		goto finish;
 
-		if (likely(!(walk->flags & ABLKCIPHER_WALK_SLOW)))
-			n = ablkcipher_done_fast(walk, n);
-		else if (WARN_ON(err)) {
-			err = -EINVAL;
-			goto err;
-		} else
-			n = ablkcipher_done_slow(walk, n);
+	n = walk->nbytes - err;
+	walk->total -= n;
+	more = (walk->total != 0);
 
-		nbytes = walk->total - n;
-		err = 0;
+	if (likely(!(walk->flags & ABLKCIPHER_WALK_SLOW))) {
+		ablkcipher_done_fast(walk, n);
+	} else {
+		if (WARN_ON(err)) {
+			/* unexpected case; didn't process all bytes */
+			err = -EINVAL;
+			goto finish;
+		}
+		ablkcipher_done_slow(walk, n);
 	}
 
-	scatterwalk_done(&walk->in, 0, nbytes);
-	scatterwalk_done(&walk->out, 1, nbytes);
-
-err:
-	walk->total = nbytes;
-	walk->nbytes = nbytes;
+	scatterwalk_done(&walk->in, 0, more);
+	scatterwalk_done(&walk->out, 1, more);
 
-	if (nbytes) {
+	if (more) {
 		crypto_yield(req->base.flags);
 		return ablkcipher_walk_next(req, walk);
 	}
-
+	err = 0;
+finish:
+	walk->nbytes = 0;
 	if (walk->iv != req->info)
 		memcpy(req->info, walk->iv, tfm->crt_ablkcipher.ivsize);
 	kfree(walk->iv_buffer);
-
 	return err;
 }
 EXPORT_SYMBOL_GPL(ablkcipher_walk_done);
-- 
cgit v1.2.3


From 76c9e53e633c8584f752effc4412d395ccf90547 Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Tue, 24 Jul 2018 15:12:43 +0100
Subject: crypto: ccree - drop useless type flag during reg

Drop the explicit setting of CRYPTO_ALG_TYPE_AEAD or
CRYPTO_ALG_TYPE_SKCIPHER flags during alg registration as they are
set anyway by the framework.

Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_aead.c   | 16 +---------------
 drivers/crypto/ccree/cc_cipher.c | 14 --------------
 drivers/crypto/ccree/cc_driver.h |  1 -
 3 files changed, 1 insertion(+), 30 deletions(-)

diff --git a/drivers/crypto/ccree/cc_aead.c b/drivers/crypto/ccree/cc_aead.c
index 03f4b9fce556..01b82b82f8b8 100644
--- a/drivers/crypto/ccree/cc_aead.c
+++ b/drivers/crypto/ccree/cc_aead.c
@@ -2344,7 +2344,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha1),cbc(aes))",
 		.driver_name = "authenc-hmac-sha1-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2364,7 +2363,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha1),cbc(des3_ede))",
 		.driver_name = "authenc-hmac-sha1-cbc-des3-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2384,7 +2382,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha256),cbc(aes))",
 		.driver_name = "authenc-hmac-sha256-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2404,7 +2401,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha256),cbc(des3_ede))",
 		.driver_name = "authenc-hmac-sha256-cbc-des3-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2424,7 +2420,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(xcbc(aes),cbc(aes))",
 		.driver_name = "authenc-xcbc-aes-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2444,7 +2439,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha1),rfc3686(ctr(aes)))",
 		.driver_name = "authenc-hmac-sha1-rfc3686-ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2464,7 +2458,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(hmac(sha256),rfc3686(ctr(aes)))",
 		.driver_name = "authenc-hmac-sha256-rfc3686-ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2484,7 +2477,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "authenc(xcbc(aes),rfc3686(ctr(aes)))",
 		.driver_name = "authenc-xcbc-aes-rfc3686-ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_aead_setauthsize,
@@ -2504,7 +2496,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "ccm(aes)",
 		.driver_name = "ccm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_ccm_setauthsize,
@@ -2524,7 +2515,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "rfc4309(ccm(aes))",
 		.driver_name = "rfc4309-ccm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_rfc4309_ccm_setkey,
 			.setauthsize = cc_rfc4309_ccm_setauthsize,
@@ -2544,7 +2534,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "gcm(aes)",
 		.driver_name = "gcm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_aead_setkey,
 			.setauthsize = cc_gcm_setauthsize,
@@ -2564,7 +2553,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "rfc4106(gcm(aes))",
 		.driver_name = "rfc4106-gcm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_rfc4106_gcm_setkey,
 			.setauthsize = cc_rfc4106_gcm_setauthsize,
@@ -2584,7 +2572,6 @@ static struct cc_alg_template aead_algs[] = {
 		.name = "rfc4543(gcm(aes))",
 		.driver_name = "rfc4543-gcm-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_AEAD,
 		.template_aead = {
 			.setkey = cc_rfc4543_gcm_setkey,
 			.setauthsize = cc_rfc4543_gcm_setauthsize,
@@ -2621,8 +2608,7 @@ static struct cc_crypto_alg *cc_create_aead_alg(struct cc_alg_template *tmpl,
 	alg->base.cra_priority = CC_CRA_PRIO;
 
 	alg->base.cra_ctxsize = sizeof(struct cc_aead_ctx);
-	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY |
-			 tmpl->type;
+	alg->base.cra_flags = CRYPTO_ALG_ASYNC | CRYPTO_ALG_KERN_DRIVER_ONLY;
 	alg->init = cc_aead_init;
 	alg->exit = cc_aead_exit;
 
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index 1100185215ac..eb99633570b5 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -968,7 +968,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(paes)",
 		.driver_name = "ecb-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -985,7 +984,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(paes)",
 		.driver_name = "cbc-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1002,7 +1000,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ofb(paes)",
 		.driver_name = "ofb-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1019,7 +1016,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cts(cbc(paes))",
 		.driver_name = "cts-cbc-paes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1036,7 +1032,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ctr(paes)",
 		.driver_name = "ctr-paes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_sethkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1203,7 +1198,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(aes)",
 		.driver_name = "ecb-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1220,7 +1214,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(aes)",
 		.driver_name = "cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1237,7 +1230,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ofb(aes)",
 		.driver_name = "ofb-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1254,7 +1246,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cts(cbc(aes))",
 		.driver_name = "cts-cbc-aes-ccree",
 		.blocksize = AES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1271,7 +1262,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ctr(aes)",
 		.driver_name = "ctr-aes-ccree",
 		.blocksize = 1,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1288,7 +1278,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(des3_ede)",
 		.driver_name = "cbc-3des-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1305,7 +1294,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(des3_ede)",
 		.driver_name = "ecb-3des-ccree",
 		.blocksize = DES3_EDE_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1322,7 +1310,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "cbc(des)",
 		.driver_name = "cbc-des-ccree",
 		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
@@ -1339,7 +1326,6 @@ static const struct cc_alg_template skcipher_algs[] = {
 		.name = "ecb(des)",
 		.driver_name = "ecb-des-ccree",
 		.blocksize = DES_BLOCK_SIZE,
-		.type = CRYPTO_ALG_TYPE_ABLKCIPHER,
 		.template_skcipher = {
 			.setkey = cc_cipher_setkey,
 			.encrypt = cc_cipher_encrypt,
diff --git a/drivers/crypto/ccree/cc_driver.h b/drivers/crypto/ccree/cc_driver.h
index 95f82b2d1e70..d608a4faf662 100644
--- a/drivers/crypto/ccree/cc_driver.h
+++ b/drivers/crypto/ccree/cc_driver.h
@@ -148,7 +148,6 @@ struct cc_alg_template {
 	char name[CRYPTO_MAX_ALG_NAME];
 	char driver_name[CRYPTO_MAX_ALG_NAME];
 	unsigned int blocksize;
-	u32 type;
 	union {
 		struct skcipher_alg skcipher;
 		struct aead_alg aead;
-- 
cgit v1.2.3


From f5c19df90ae7fc21d3dcf50af9d6b456aa6b3351 Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Tue, 24 Jul 2018 15:12:44 +0100
Subject: crypto: ccree - remove cipher ivgen left overs

IV generation is not available via the skcipher interface.
Remove the left over support of it from the ablkcipher days.

Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_buffer_mgr.c |  8 ++------
 drivers/crypto/ccree/cc_cipher.c     | 11 -----------
 drivers/crypto/ccree/cc_cipher.h     |  1 -
 3 files changed, 2 insertions(+), 18 deletions(-)

diff --git a/drivers/crypto/ccree/cc_buffer_mgr.c b/drivers/crypto/ccree/cc_buffer_mgr.c
index b32577477b4c..dd948e1df9e5 100644
--- a/drivers/crypto/ccree/cc_buffer_mgr.c
+++ b/drivers/crypto/ccree/cc_buffer_mgr.c
@@ -454,9 +454,7 @@ void cc_unmap_cipher_request(struct device *dev, void *ctx,
 		dev_dbg(dev, "Unmapped iv: iv_dma_addr=%pad iv_size=%u\n",
 			&req_ctx->gen_ctx.iv_dma_addr, ivsize);
 		dma_unmap_single(dev, req_ctx->gen_ctx.iv_dma_addr,
-				 ivsize,
-				 req_ctx->is_giv ? DMA_BIDIRECTIONAL :
-				 DMA_TO_DEVICE);
+				 ivsize, DMA_TO_DEVICE);
 	}
 	/* Release pool */
 	if (req_ctx->dma_buf_type == CC_DMA_BUF_MLLI &&
@@ -498,9 +496,7 @@ int cc_map_cipher_request(struct cc_drvdata *drvdata, void *ctx,
 		dump_byte_array("iv", (u8 *)info, ivsize);
 		req_ctx->gen_ctx.iv_dma_addr =
 			dma_map_single(dev, (void *)info,
-				       ivsize,
-				       req_ctx->is_giv ? DMA_BIDIRECTIONAL :
-				       DMA_TO_DEVICE);
+				       ivsize, DMA_TO_DEVICE);
 		if (dma_mapping_error(dev, req_ctx->gen_ctx.iv_dma_addr)) {
 			dev_err(dev, "Mapping iv %u B at va=%pK for DMA failed\n",
 				ivsize, info);
diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index eb99633570b5..64740dd6f5f1 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -743,14 +743,6 @@ static int cc_cipher_process(struct skcipher_request *req,
 	cc_setup_cipher_data(tfm, req_ctx, dst, src, nbytes, req, desc,
 			     &seq_len);
 
-	/* do we need to generate IV? */
-	if (req_ctx->is_giv) {
-		cc_req.ivgen_dma_addr[0] = req_ctx->gen_ctx.iv_dma_addr;
-		cc_req.ivgen_dma_addr_len = 1;
-		/* set the IV size (8/16 B long)*/
-		cc_req.ivgen_size = ivsize;
-	}
-
 	/* STAT_PHASE_3: Lock HW and push sequence */
 
 	rc = cc_send_request(ctx_p->drvdata, &cc_req, desc, seq_len,
@@ -775,7 +767,6 @@ static int cc_cipher_encrypt(struct skcipher_request *req)
 {
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
 
-	req_ctx->is_giv = false;
 	req_ctx->backup_info = NULL;
 
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
@@ -807,8 +798,6 @@ static int cc_cipher_decrypt(struct skcipher_request *req)
 		req_ctx->backup_info = NULL;
 	}
 
-	req_ctx->is_giv = false;
-
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_DECRYPT);
 }
 
diff --git a/drivers/crypto/ccree/cc_cipher.h b/drivers/crypto/ccree/cc_cipher.h
index 68444cfa936b..4dbc0a1e6d5c 100644
--- a/drivers/crypto/ccree/cc_cipher.h
+++ b/drivers/crypto/ccree/cc_cipher.h
@@ -22,7 +22,6 @@ struct cipher_req_ctx {
 	u32 out_mlli_nents;
 	u8 *backup_info; /*store iv for generated IV flow*/
 	u8 *iv;
-	bool is_giv;
 	struct mlli_params mlli_params;
 };
 
-- 
cgit v1.2.3


From e30368f3f3ee72e20aa4b1fdb6ec2c5ddcd7e2d1 Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Tue, 24 Jul 2018 15:12:45 +0100
Subject: crypto: ccree - zero all of request ctx before use

In certain error path req_ctx->iv was being freed despite
not being allocated because it was not initialized to NULL.
Rather than play whack a mole with the structure various
field, zero it before use.

This fixes a kernel panic that may occur if an invalid
buffer size was requested triggering the bug above.

Fixes: 63ee04c8b491 ("crypto: ccree - add skcipher support")
Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_cipher.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index 64740dd6f5f1..9da0ecce5411 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -767,7 +767,7 @@ static int cc_cipher_encrypt(struct skcipher_request *req)
 {
 	struct cipher_req_ctx *req_ctx = skcipher_request_ctx(req);
 
-	req_ctx->backup_info = NULL;
+	memset(req_ctx, 0, sizeof(*req_ctx));
 
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_ENCRYPT);
 }
@@ -782,6 +782,8 @@ static int cc_cipher_decrypt(struct skcipher_request *req)
 	gfp_t flags = cc_gfp_flags(&req->base);
 	unsigned int len;
 
+	memset(req_ctx, 0, sizeof(*req_ctx));
+
 	if (ctx_p->cipher_mode == DRV_CIPHER_CBC) {
 
 		/* Allocate and save the last IV sized bytes of the source,
@@ -794,8 +796,6 @@ static int cc_cipher_decrypt(struct skcipher_request *req)
 		len = req->cryptlen - ivsize;
 		scatterwalk_map_and_copy(req_ctx->backup_info, req->src, len,
 					 ivsize, 0);
-	} else {
-		req_ctx->backup_info = NULL;
 	}
 
 	return cc_cipher_process(req, DRV_CRYPTO_DIRECTION_DECRYPT);
-- 
cgit v1.2.3


From f53ad3e1b35a558528f6d0041568016d1f623a9d Mon Sep 17 00:00:00 2001
From: Gilad Ben-Yossef <gilad@benyossef.com>
Date: Tue, 24 Jul 2018 15:12:46 +0100
Subject: crypto: ccree - allow bigger than sector XTS op

The ccree driver had a sanity check that we are not asked
to encrypt an XTS buffer bigger than a sane sector size
since XTS IV needs to include the sector number in the IV
so this is not expected in any real use case.

Unfortunately, this breaks cryptsetup benchmark test which
has a synthetic performance test using 64k buffer of data
with the same IV.

Remove the sanity check and allow the user to hang themselves
and/or run benchmarks if they so wish.

Reported-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccree/cc_cipher.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/crypto/ccree/cc_cipher.c b/drivers/crypto/ccree/cc_cipher.c
index 9da0ecce5411..7623b29911af 100644
--- a/drivers/crypto/ccree/cc_cipher.c
+++ b/drivers/crypto/ccree/cc_cipher.c
@@ -19,8 +19,6 @@
 
 #define template_skcipher	template_u.skcipher
 
-#define CC_MIN_AES_XTS_SIZE 0x10
-#define CC_MAX_AES_XTS_SIZE 0x2000
 struct cc_cipher_handle {
 	struct list_head alg_list;
 };
@@ -98,8 +96,7 @@ static int validate_data_size(struct cc_cipher_ctx *ctx_p,
 	case S_DIN_to_AES:
 		switch (ctx_p->cipher_mode) {
 		case DRV_CIPHER_XTS:
-			if (size >= CC_MIN_AES_XTS_SIZE &&
-			    size <= CC_MAX_AES_XTS_SIZE &&
+			if (size >= AES_BLOCK_SIZE &&
 			    IS_ALIGNED(size, AES_BLOCK_SIZE))
 				return 0;
 			break;
-- 
cgit v1.2.3


From 4e34e51f48ab7f77a4022aa810a786daa3eb3e22 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Tue, 24 Jul 2018 18:29:07 -0700
Subject: crypto: arm/chacha20 - always use vrev for 16-bit rotates

The 4-way ChaCha20 NEON code implements 16-bit rotates with vrev32.16,
but the one-way code (used on remainder blocks) implements it with
vshl + vsri, which is slower.  Switch the one-way code to vrev32.16 too.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Acked-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm/crypto/chacha20-neon-core.S | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/arch/arm/crypto/chacha20-neon-core.S b/arch/arm/crypto/chacha20-neon-core.S
index 3fecb2124c35..451a849ad518 100644
--- a/arch/arm/crypto/chacha20-neon-core.S
+++ b/arch/arm/crypto/chacha20-neon-core.S
@@ -51,9 +51,8 @@ ENTRY(chacha20_block_xor_neon)
 .Ldoubleround:
 	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
 	vadd.i32	q0, q0, q1
-	veor		q4, q3, q0
-	vshl.u32	q3, q4, #16
-	vsri.u32	q3, q4, #16
+	veor		q3, q3, q0
+	vrev32.16	q3, q3
 
 	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
 	vadd.i32	q2, q2, q3
@@ -82,9 +81,8 @@ ENTRY(chacha20_block_xor_neon)
 
 	// x0 += x1, x3 = rotl32(x3 ^ x0, 16)
 	vadd.i32	q0, q0, q1
-	veor		q4, q3, q0
-	vshl.u32	q3, q4, #16
-	vsri.u32	q3, q4, #16
+	veor		q3, q3, q0
+	vrev32.16	q3, q3
 
 	// x2 += x3, x1 = rotl32(x1 ^ x2, 12)
 	vadd.i32	q2, q2, q3
-- 
cgit v1.2.3


From afb31cd2d1a1bc3ca055fb2519ec4e9ab969ffe0 Mon Sep 17 00:00:00 2001
From: Tom Lendacky <thomas.lendacky@amd.com>
Date: Thu, 26 Jul 2018 09:37:59 -0500
Subject: crypto: ccp - Check for NULL PSP pointer at module unload

Should the PSP initialization fail, the PSP data structure will be
freed and the value contained in the sp_device struct set to NULL.
At module unload, psp_dev_destroy() does not check if the pointer
value is NULL and will end up dereferencing a NULL pointer.

Add a pointer check of the psp_data field in the sp_device struct
in psp_dev_destroy() and return immediately if it is NULL.

Cc: <stable@vger.kernel.org> # 4.16.x-
Fixes: 2a6170dfe755 ("crypto: ccp: Add Platform Security Processor (PSP) device support")
Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
Acked-by: Gary R Hook <gary.hook@amd.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/ccp/psp-dev.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/crypto/ccp/psp-dev.c b/drivers/crypto/ccp/psp-dev.c
index 9b596387a09f..218739b961fe 100644
--- a/drivers/crypto/ccp/psp-dev.c
+++ b/drivers/crypto/ccp/psp-dev.c
@@ -858,6 +858,9 @@ void psp_dev_destroy(struct sp_device *sp)
 {
 	struct psp_device *psp = sp->psp_data;
 
+	if (!psp)
+		return;
+
 	if (psp->sev_misc)
 		kref_put(&misc_dev->refcount, sev_exit);
 
-- 
cgit v1.2.3


From 35f7d5225ffcbf1b759f641aec1735e3a89b1914 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 27 Jul 2018 15:36:10 -0700
Subject: crypto: dh - fix calculating encoded key size

It was forgotten to increase DH_KPP_SECRET_MIN_SIZE to include 'q_size',
causing an out-of-bounds write of 4 bytes in crypto_dh_encode_key(), and
an out-of-bounds read of 4 bytes in crypto_dh_decode_key().  Fix it, and
fix the lengths of the test vectors to match this.

Reported-by: syzbot+6d38d558c25b53b8f4ed@syzkaller.appspotmail.com
Fixes: e3fe0ae12962 ("crypto: dh - add public key verification test")
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/dh_helper.c |  2 +-
 crypto/testmgr.h   | 12 ++++++------
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/crypto/dh_helper.c b/crypto/dh_helper.c
index a7de3d9ce5ac..db9b2d9c58f0 100644
--- a/crypto/dh_helper.c
+++ b/crypto/dh_helper.c
@@ -14,7 +14,7 @@
 #include <crypto/dh.h>
 #include <crypto/kpp.h>
 
-#define DH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 3 * sizeof(int))
+#define DH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 4 * sizeof(int))
 
 static inline u8 *dh_pack_data(void *dst, const void *src, size_t size)
 {
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 759462d65f41..173111c70746 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -641,14 +641,14 @@ static const struct kpp_testvec dh_tv_template[] = {
 	.secret =
 #ifdef __LITTLE_ENDIAN
 	"\x01\x00" /* type */
-	"\x11\x02" /* len */
+	"\x15\x02" /* len */
 	"\x00\x01\x00\x00" /* key_size */
 	"\x00\x01\x00\x00" /* p_size */
 	"\x00\x00\x00\x00" /* q_size */
 	"\x01\x00\x00\x00" /* g_size */
 #else
 	"\x00\x01" /* type */
-	"\x02\x11" /* len */
+	"\x02\x15" /* len */
 	"\x00\x00\x01\x00" /* key_size */
 	"\x00\x00\x01\x00" /* p_size */
 	"\x00\x00\x00\x00" /* q_size */
@@ -741,7 +741,7 @@ static const struct kpp_testvec dh_tv_template[] = {
 	"\xd3\x34\x49\xad\x64\xa6\xb1\xc0\x59\x28\x75\x60\xa7\x8a\xb0\x11"
 	"\x56\x89\x42\x74\x11\xf5\xf6\x5e\x6f\x16\x54\x6a\xb1\x76\x4d\x50"
 	"\x8a\x68\xc1\x5b\x82\xb9\x0d\x00\x32\x50\xed\x88\x87\x48\x92\x17",
-	.secret_size = 529,
+	.secret_size = 533,
 	.b_public_size = 256,
 	.expected_a_public_size = 256,
 	.expected_ss_size = 256,
@@ -750,14 +750,14 @@ static const struct kpp_testvec dh_tv_template[] = {
 	.secret =
 #ifdef __LITTLE_ENDIAN
 	"\x01\x00" /* type */
-	"\x11\x02" /* len */
+	"\x15\x02" /* len */
 	"\x00\x01\x00\x00" /* key_size */
 	"\x00\x01\x00\x00" /* p_size */
 	"\x00\x00\x00\x00" /* q_size */
 	"\x01\x00\x00\x00" /* g_size */
 #else
 	"\x00\x01" /* type */
-	"\x02\x11" /* len */
+	"\x02\x15" /* len */
 	"\x00\x00\x01\x00" /* key_size */
 	"\x00\x00\x01\x00" /* p_size */
 	"\x00\x00\x00\x00" /* q_size */
@@ -850,7 +850,7 @@ static const struct kpp_testvec dh_tv_template[] = {
 	"\x5e\x5a\x64\xbd\xf6\x85\x04\xe8\x28\x6a\xac\xef\xce\x19\x8e\x9a"
 	"\xfe\x75\xc0\x27\x69\xe3\xb3\x7b\x21\xa7\xb1\x16\xa4\x85\x23\xee"
 	"\xb0\x1b\x04\x6e\xbd\xab\x16\xde\xfd\x86\x6b\xa9\x95\xd7\x0b\xfd",
-	.secret_size = 529,
+	.secret_size = 533,
 	.b_public_size = 256,
 	.expected_a_public_size = 256,
 	.expected_ss_size = 256,
-- 
cgit v1.2.3


From d6e43798b3d9cb8c59e1fccfaeec7cb396dc0699 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Fri, 27 Jul 2018 15:36:11 -0700
Subject: crypto: dh - make crypto_dh_encode_key() make robust

Make it return -EINVAL if crypto_dh_key_len() is incorrect rather than
overflowing the buffer.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 crypto/dh_helper.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/crypto/dh_helper.c b/crypto/dh_helper.c
index db9b2d9c58f0..edacda5f6a4d 100644
--- a/crypto/dh_helper.c
+++ b/crypto/dh_helper.c
@@ -16,8 +16,10 @@
 
 #define DH_KPP_SECRET_MIN_SIZE (sizeof(struct kpp_secret) + 4 * sizeof(int))
 
-static inline u8 *dh_pack_data(void *dst, const void *src, size_t size)
+static inline u8 *dh_pack_data(u8 *dst, u8 *end, const void *src, size_t size)
 {
+	if (!dst || size > end - dst)
+		return NULL;
 	memcpy(dst, src, size);
 	return dst + size;
 }
@@ -42,27 +44,27 @@ EXPORT_SYMBOL_GPL(crypto_dh_key_len);
 int crypto_dh_encode_key(char *buf, unsigned int len, const struct dh *params)
 {
 	u8 *ptr = buf;
+	u8 * const end = ptr + len;
 	struct kpp_secret secret = {
 		.type = CRYPTO_KPP_SECRET_TYPE_DH,
 		.len = len
 	};
 
-	if (unlikely(!buf))
+	if (unlikely(!len))
 		return -EINVAL;
 
-	if (len != crypto_dh_key_len(params))
+	ptr = dh_pack_data(ptr, end, &secret, sizeof(secret));
+	ptr = dh_pack_data(ptr, end, &params->key_size,
+			   sizeof(params->key_size));
+	ptr = dh_pack_data(ptr, end, &params->p_size, sizeof(params->p_size));
+	ptr = dh_pack_data(ptr, end, &params->q_size, sizeof(params->q_size));
+	ptr = dh_pack_data(ptr, end, &params->g_size, sizeof(params->g_size));
+	ptr = dh_pack_data(ptr, end, params->key, params->key_size);
+	ptr = dh_pack_data(ptr, end, params->p, params->p_size);
+	ptr = dh_pack_data(ptr, end, params->q, params->q_size);
+	ptr = dh_pack_data(ptr, end, params->g, params->g_size);
+	if (ptr != end)
 		return -EINVAL;
-
-	ptr = dh_pack_data(ptr, &secret, sizeof(secret));
-	ptr = dh_pack_data(ptr, &params->key_size, sizeof(params->key_size));
-	ptr = dh_pack_data(ptr, &params->p_size, sizeof(params->p_size));
-	ptr = dh_pack_data(ptr, &params->q_size, sizeof(params->q_size));
-	ptr = dh_pack_data(ptr, &params->g_size, sizeof(params->g_size));
-	ptr = dh_pack_data(ptr, params->key, params->key_size);
-	ptr = dh_pack_data(ptr, params->p, params->p_size);
-	ptr = dh_pack_data(ptr, params->q, params->q_size);
-	dh_pack_data(ptr, params->g, params->g_size);
-
 	return 0;
 }
 EXPORT_SYMBOL_GPL(crypto_dh_encode_key);
-- 
cgit v1.2.3


From 08fb550cb3f8e1efff5586b938eeedddb3ba0506 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@sifive.com>
Date: Fri, 22 Jun 2018 10:01:22 -0700
Subject: irqchip: Port the ARM IRQ drivers to GENERIC_IRQ_MULTI_HANDLER

GENERIC_IRQ_MULTI_HANDLER is incompatible with MULTI_IRQ_HANDLER because
they define the same symbols.  Multiple generic irqchip drivers select
MULTI_IRQ_HANDLER, which is now defined on all architectures that
provide set_handle_irq().

To solve this select GENERIC_IRQ_MULTI_HANDLER for all drivers that used to
select MULTI_IRQ_HANDLER, but only when MULTI_IRQ_HANDLER doesn't exist.

After that every architecture can be converted over from MULTI_IRQ_HANDLER
to GENERIC_IRQ_MULTI_HANDLER before removing the extra MULTI_IRQ_HANDLER
scaffolding.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux@armlinux.org.uk
Cc: catalin.marinas@arm.com
Cc: Will Deacon <will.deacon@arm.com>
Cc: jonas@southpole.se
Cc: stefan.kristiansson@saunalahti.fi
Cc: shorne@gmail.com
Cc: jason@lakedaemon.net
Cc: marc.zyngier@arm.com
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: nicolas.pitre@linaro.org
Cc: vladimir.murzin@arm.com
Cc: keescook@chromium.org
Cc: jinb.park7@gmail.com
Cc: yamada.masahiro@socionext.com
Cc: alexandre.belloni@bootlin.com
Cc: pombredanne@nexb.com
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: kstewart@linuxfoundation.org
Cc: jhogan@kernel.org
Cc: mark.rutland@arm.com
Cc: ard.biesheuvel@linaro.org
Cc: james.morse@arm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: openrisc@lists.librecores.org
Cc: Shea Levy <shea@shealevy.com>
Link: https://lkml.kernel.org/r/20180622170126.6308-2-palmer@sifive.com
---
 drivers/irqchip/Kconfig | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index e9233db16e03..7527f6a9adae 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -9,6 +9,7 @@ config ARM_GIC
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config ARM_GIC_PM
@@ -35,6 +36,7 @@ config ARM_GIC_V3
 	bool
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 	select IRQ_DOMAIN_HIERARCHY
 	select PARTITION_PERCPU
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -67,6 +69,7 @@ config ARM_VIC
 	bool
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 
 config ARM_VIC_NR
 	int
@@ -94,6 +97,7 @@ config ATMEL_AIC_IRQ
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 
 config ATMEL_AIC5_IRQ
@@ -101,6 +105,7 @@ config ATMEL_AIC5_IRQ
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 
 config I8259
@@ -138,6 +143,7 @@ config FARADAY_FTINTC010
 	bool
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 
 config HISILICON_IRQ_MBIGEN
@@ -163,6 +169,7 @@ config CLPS711X_IRQCHIP
 	depends on ARCH_CLPS711X
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 	default y
 
@@ -182,6 +189,7 @@ config ORION_IRQCHIP
 	bool
 	select IRQ_DOMAIN
 	select MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
 
 config PIC32_EVIC
 	bool
-- 
cgit v1.2.3


From 4c301f9b6a94bb383089bc847083e287e9bfc96e Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@sifive.com>
Date: Fri, 22 Jun 2018 10:01:23 -0700
Subject: ARM: Convert to GENERIC_IRQ_MULTI_HANDLER

Converts the ARM interrupt code to use the recently added
GENERIC_IRQ_MULTI_HANDLER, which is essentially just a copy of ARM's
existhing MULTI_IRQ_HANDLER.  The only changes are:

* handle_arch_irq is now defined in a generic C file instead of an
  arm-specific assembly file.

* handle_arch_irq is now marked as __ro_after_init.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux@armlinux.org.uk
Cc: catalin.marinas@arm.com
Cc: Will Deacon <will.deacon@arm.com>
Cc: jonas@southpole.se
Cc: stefan.kristiansson@saunalahti.fi
Cc: shorne@gmail.com
Cc: jason@lakedaemon.net
Cc: marc.zyngier@arm.com
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: nicolas.pitre@linaro.org
Cc: vladimir.murzin@arm.com
Cc: keescook@chromium.org
Cc: jinb.park7@gmail.com
Cc: yamada.masahiro@socionext.com
Cc: alexandre.belloni@bootlin.com
Cc: pombredanne@nexb.com
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: kstewart@linuxfoundation.org
Cc: jhogan@kernel.org
Cc: mark.rutland@arm.com
Cc: ard.biesheuvel@linaro.org
Cc: james.morse@arm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: openrisc@lists.librecores.org
Link: https://lkml.kernel.org/r/20180622170126.6308-3-palmer@sifive.com
---
 arch/arm/Kconfig                 | 19 +++++++------------
 arch/arm/include/asm/irq.h       |  5 -----
 arch/arm/include/asm/mach/arch.h |  2 +-
 arch/arm/kernel/entry-armv.S     | 10 ++--------
 arch/arm/kernel/irq.c            | 10 ----------
 arch/arm/kernel/setup.c          |  2 +-
 6 files changed, 11 insertions(+), 37 deletions(-)

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 54eeb8d00bc6..b6be2b1be75d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -337,8 +337,8 @@ config ARCH_MULTIPLATFORM
 	select TIMER_OF
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select PCI_DOMAINS if PCI
 	select SPARSE_IRQ
 	select USE_OF
@@ -465,9 +465,9 @@ config ARCH_DOVE
 	bool "Marvell Dove"
 	select CPU_PJ4
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select MIGHT_HAVE_PCI
-	select MULTI_IRQ_HANDLER
 	select MVEBU_MBUS
 	select PINCTRL
 	select PINCTRL_DOVE
@@ -512,8 +512,8 @@ config ARCH_LPC32XX
 	select COMMON_CLK
 	select CPU_ARM926T
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
-	select MULTI_IRQ_HANDLER
 	select SPARSE_IRQ
 	select USE_OF
 	help
@@ -532,11 +532,11 @@ config ARCH_PXA
 	select TIMER_OF
 	select CPU_XSCALE if !CPU_XSC3
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIO_PXA
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select PLAT_PXA
 	select SPARSE_IRQ
 	help
@@ -572,11 +572,11 @@ config ARCH_SA1100
 	select CPU_FREQ
 	select CPU_SA1100
 	select GENERIC_CLOCKEVENTS
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
 	select ISA
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
 	help
@@ -590,10 +590,10 @@ config ARCH_S3C24XX
 	select GENERIC_CLOCKEVENTS
 	select GPIO_SAMSUNG
 	select GPIOLIB
+	select GENERIC_IRQ_MULTI_HANDLER
 	select HAVE_S3C2410_I2C if I2C
 	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select HAVE_S3C_RTC if RTC_CLASS
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H
 	select SAMSUNG_ATAGS
 	select USE_OF
@@ -627,10 +627,10 @@ config ARCH_OMAP1
 	select CLKSRC_MMIO
 	select GENERIC_CLOCKEVENTS
 	select GENERIC_IRQ_CHIP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_IDE
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
 	select NEED_MACH_IO_H if PCCARD
 	select NEED_MACH_MEMORY_H
 	select SPARSE_IRQ
@@ -921,11 +921,6 @@ config IWMMXT
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.
 
-config MULTI_IRQ_HANDLER
-	bool
-	help
-	  Allow each machine to specify it's own IRQ handler at run time.
-
 if !MMU
 source "arch/arm/Kconfig-nommu"
 endif
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index b6f319606e30..c883fcbe93b6 100644
--- a/arch/arm/include/asm/irq.h
+++ b/arch/arm/include/asm/irq.h
@@ -31,11 +31,6 @@ extern void asm_do_IRQ(unsigned int, struct pt_regs *);
 void handle_IRQ(unsigned int, struct pt_regs *);
 void init_IRQ(void);
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-extern void (*handle_arch_irq)(struct pt_regs *);
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-#endif
-
 #ifdef CONFIG_SMP
 extern void arch_trigger_cpumask_backtrace(const cpumask_t *mask,
 					   bool exclude_self);
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 5c1ad11aa392..bb8851208e17 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -59,7 +59,7 @@ struct machine_desc {
 	void			(*init_time)(void);
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	void			(*handle_irq)(struct pt_regs *);
 #endif
 	void			(*restart)(enum reboot_mode, const char *);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 179a9f6bd1e3..e85a3af9ddeb 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -22,7 +22,7 @@
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
 #include <asm/vfpmacros.h>
-#ifndef CONFIG_MULTI_IRQ_HANDLER
+#ifndef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 #include <mach/entry-macro.S>
 #endif
 #include <asm/thread_notify.h>
@@ -39,7 +39,7 @@
  * Interrupt handling.
  */
 	.macro	irq_handler
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	ldr	r1, =handle_arch_irq
 	mov	r0, sp
 	badr	lr, 9997f
@@ -1226,9 +1226,3 @@ vector_addrexcptn:
 	.globl	cr_alignment
 cr_alignment:
 	.space	4
-
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-	.globl	handle_arch_irq
-handle_arch_irq:
-	.space	4
-#endif
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index ece04a457486..9908dacf9229 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -102,16 +102,6 @@ void __init init_IRQ(void)
 	uniphier_cache_init();
 }
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-#endif
-
 #ifdef CONFIG_SPARSE_IRQ
 int __init arch_probe_nr_irqs(void)
 {
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 35ca494c028c..4c249cb261f3 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1145,7 +1145,7 @@ void __init setup_arch(char **cmdline_p)
 
 	reserve_crashkernel();
 
-#ifdef CONFIG_MULTI_IRQ_HANDLER
+#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	handle_arch_irq = mdesc->handle_irq;
 #endif
 
-- 
cgit v1.2.3


From 78ae2e1cd845480caaa2f181fee64e51f679f5aa Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@sifive.com>
Date: Fri, 22 Jun 2018 10:01:24 -0700
Subject: arm64: Use the new GENERIC_IRQ_MULTI_HANDLER

It appears arm64 copied arm's GENERIC_IRQ_MULTI_HANDLER code, but made
it unconditional.

Converts the arm64 code to use the new generic code, which simply consists
of deleting the arm64 code and setting MULTI_IRQ_HANDLER instead.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: linux@armlinux.org.uk
Cc: catalin.marinas@arm.com
Cc: Will Deacon <will.deacon@arm.com>
Cc: jonas@southpole.se
Cc: stefan.kristiansson@saunalahti.fi
Cc: shorne@gmail.com
Cc: jason@lakedaemon.net
Cc: marc.zyngier@arm.com
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: nicolas.pitre@linaro.org
Cc: vladimir.murzin@arm.com
Cc: keescook@chromium.org
Cc: jinb.park7@gmail.com
Cc: yamada.masahiro@socionext.com
Cc: alexandre.belloni@bootlin.com
Cc: pombredanne@nexb.com
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: kstewart@linuxfoundation.org
Cc: jhogan@kernel.org
Cc: mark.rutland@arm.com
Cc: ard.biesheuvel@linaro.org
Cc: james.morse@arm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: openrisc@lists.librecores.org
Link: https://lkml.kernel.org/r/20180622170126.6308-4-palmer@sifive.com
---
 arch/arm64/Kconfig           |  4 +---
 arch/arm64/include/asm/irq.h |  2 --
 arch/arm64/kernel/irq.c      | 10 ----------
 3 files changed, 1 insertion(+), 15 deletions(-)

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 42c090cf0292..3d1011957823 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -74,6 +74,7 @@ config ARM64
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
@@ -264,9 +265,6 @@ config ARCH_SUPPORTS_UPROBES
 config ARCH_PROC_KCORE_TEXT
 	def_bool y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/arm64/include/asm/irq.h b/arch/arm64/include/asm/irq.h
index a0fee6985e6a..b2b0c6405eb0 100644
--- a/arch/arm64/include/asm/irq.h
+++ b/arch/arm64/include/asm/irq.h
@@ -8,8 +8,6 @@
 
 struct pt_regs;
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 static inline int nr_legacy_irqs(void)
 {
 	return 0;
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 60e5fc661f74..780a12f59a8f 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -42,16 +42,6 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-void (*handle_arch_irq)(struct pt_regs *) = NULL;
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	if (handle_arch_irq)
-		return;
-
-	handle_arch_irq = handle_irq;
-}
-
 #ifdef CONFIG_VMAP_STACK
 static void init_irq_stacks(void)
 {
-- 
cgit v1.2.3


From c5ca4560de0f04a3c872bdd17ae3378762c66bd2 Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@sifive.com>
Date: Fri, 22 Jun 2018 10:01:25 -0700
Subject: openrisc: Use the new GENERIC_IRQ_MULTI_HANDLER

It appears that openrisc copied arm64's GENERIC_IRQ_MULTI_HANDLER code
(which came from arm).  Cnvert it to use the generic version.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Stafford Horne <shorne@gmail.com>
Cc: linux@armlinux.org.uk
Cc: catalin.marinas@arm.com
Cc: Will Deacon <will.deacon@arm.com>
Cc: jonas@southpole.se
Cc: stefan.kristiansson@saunalahti.fi
Cc: jason@lakedaemon.net
Cc: marc.zyngier@arm.com
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: nicolas.pitre@linaro.org
Cc: vladimir.murzin@arm.com
Cc: keescook@chromium.org
Cc: jinb.park7@gmail.com
Cc: yamada.masahiro@socionext.com
Cc: alexandre.belloni@bootlin.com
Cc: pombredanne@nexb.com
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: kstewart@linuxfoundation.org
Cc: jhogan@kernel.org
Cc: mark.rutland@arm.com
Cc: ard.biesheuvel@linaro.org
Cc: james.morse@arm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: openrisc@lists.librecores.org
Link: https://lkml.kernel.org/r/20180622170126.6308-5-palmer@sifive.com
---
 arch/openrisc/Kconfig           | 5 +----
 arch/openrisc/include/asm/irq.h | 2 --
 arch/openrisc/kernel/irq.c      | 7 -------
 3 files changed, 1 insertion(+), 13 deletions(-)

diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index 9ecad05bfc73..dfb6a79ba7ff 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -27,7 +27,6 @@ config OPENRISC
 	select GENERIC_STRNLEN_USER
 	select GENERIC_SMP_IDLE_THREAD
 	select MODULES_USE_ELF_RELA
-	select MULTI_IRQ_HANDLER
 	select HAVE_DEBUG_STACKOVERFLOW
 	select OR1K_PIC
 	select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1
@@ -36,6 +35,7 @@ config OPENRISC
 	select ARCH_USE_QUEUED_RWLOCKS
 	select OMPIC if SMP
 	select ARCH_WANT_FRAME_POINTERS
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config CPU_BIG_ENDIAN
 	def_bool y
@@ -69,9 +69,6 @@ config STACKTRACE_SUPPORT
 config LOCKDEP_SUPPORT
 	def_bool  y
 
-config MULTI_IRQ_HANDLER
-	def_bool y
-
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
diff --git a/arch/openrisc/include/asm/irq.h b/arch/openrisc/include/asm/irq.h
index d9eee0a2b7b4..eb612b1865d2 100644
--- a/arch/openrisc/include/asm/irq.h
+++ b/arch/openrisc/include/asm/irq.h
@@ -24,6 +24,4 @@
 
 #define NO_IRQ		(-1)
 
-extern void set_handle_irq(void (*handle_irq)(struct pt_regs *));
-
 #endif /* __ASM_OPENRISC_IRQ_H__ */
diff --git a/arch/openrisc/kernel/irq.c b/arch/openrisc/kernel/irq.c
index 35e478a93116..5f9445effaf8 100644
--- a/arch/openrisc/kernel/irq.c
+++ b/arch/openrisc/kernel/irq.c
@@ -41,13 +41,6 @@ void __init init_IRQ(void)
 	irqchip_init();
 }
 
-static void (*handle_arch_irq)(struct pt_regs *);
-
-void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
-{
-	handle_arch_irq = handle_irq;
-}
-
 void __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	handle_arch_irq(regs);
-- 
cgit v1.2.3


From 4f7799d96e6621ce584df60739e1480a6fd89f0a Mon Sep 17 00:00:00 2001
From: Palmer Dabbelt <palmer@sifive.com>
Date: Fri, 22 Jun 2018 10:01:26 -0700
Subject: genirq/irqchip: Remove MULTI_IRQ_HANDLER as it's now obselete

Now that every user of MULTI_IRQ_HANDLER has been convereted over to use
GENERIC_IRQ_MULTI_HANDLER remove the references to MULTI_IRQ_HANDLER.

Signed-off-by: Palmer Dabbelt <palmer@sifive.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux@armlinux.org.uk
Cc: catalin.marinas@arm.com
Cc: Will Deacon <will.deacon@arm.com>
Cc: jonas@southpole.se
Cc: stefan.kristiansson@saunalahti.fi
Cc: shorne@gmail.com
Cc: jason@lakedaemon.net
Cc: marc.zyngier@arm.com
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: nicolas.pitre@linaro.org
Cc: vladimir.murzin@arm.com
Cc: keescook@chromium.org
Cc: jinb.park7@gmail.com
Cc: yamada.masahiro@socionext.com
Cc: alexandre.belloni@bootlin.com
Cc: pombredanne@nexb.com
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: kstewart@linuxfoundation.org
Cc: jhogan@kernel.org
Cc: mark.rutland@arm.com
Cc: ard.biesheuvel@linaro.org
Cc: james.morse@arm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: openrisc@lists.librecores.org
Link: https://lkml.kernel.org/r/20180622170126.6308-6-palmer@sifive.com
---
 drivers/irqchip/Kconfig | 24 ++++++++----------------
 kernel/irq/Kconfig      |  1 -
 2 files changed, 8 insertions(+), 17 deletions(-)

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 7527f6a9adae..d564d21245c5 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -8,8 +8,7 @@ config ARM_GIC
 	bool
 	select IRQ_DOMAIN
 	select IRQ_DOMAIN_HIERARCHY
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
 
 config ARM_GIC_PM
@@ -35,8 +34,7 @@ config GIC_NON_BANKED
 config ARM_GIC_V3
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select IRQ_DOMAIN_HIERARCHY
 	select PARTITION_PERCPU
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -68,8 +66,7 @@ config ARM_NVIC
 config ARM_VIC
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config ARM_VIC_NR
 	int
@@ -96,16 +93,14 @@ config ATMEL_AIC_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config ATMEL_AIC5_IRQ
 	bool
 	select GENERIC_IRQ_CHIP
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config I8259
@@ -142,8 +137,7 @@ config DW_APB_ICTL
 config FARADAY_FTINTC010
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 
 config HISILICON_IRQ_MBIGEN
@@ -168,8 +162,7 @@ config CLPS711X_IRQCHIP
 	bool
 	depends on ARCH_CLPS711X
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 	select SPARSE_IRQ
 	default y
 
@@ -188,8 +181,7 @@ config OMAP_IRQCHIP
 config ORION_IRQCHIP
 	bool
 	select IRQ_DOMAIN
-	select MULTI_IRQ_HANDLER
-	select GENERIC_IRQ_MULTI_HANDLER if !MULTI_IRQ_HANDLER
+	select GENERIC_IRQ_MULTI_HANDLER
 
 config PIC32_EVIC
 	bool
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index c6766f326072..5f3e2baefca9 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -134,7 +134,6 @@ config GENERIC_IRQ_DEBUGFS
 endmenu
 
 config GENERIC_IRQ_MULTI_HANDLER
-	depends on !MULTI_IRQ_HANDLER
 	bool
 	help
 	  Allow to specify the low level IRQ handler at run time.
-- 
cgit v1.2.3


From 1b6266ebe3da8198e9a02fbad77bbb56e2f7ce2e Mon Sep 17 00:00:00 2001
From: Sinan Kaya <okaya@kernel.org>
Date: Thu, 2 Aug 2018 23:09:41 -0700
Subject: watchdog: Reduce message verbosity

Code is emitting the following error message during boot on systems
without PMU hardware support while probing NMI capability.

 NMI watchdog: Perf event create on CPU 0 failed with -2

This error is emitted as the perf subsystem returns -ENOENT due to lack of
PMUs in the system.

It is followed by the warning that NMI watchdog is disabled:

  NMI watchdog: Perf NMI watchdog permanently disabled

While NMI disabled information is useful for ordinary users, seeing a PERF
event create failed with error code -2 is not.

Reduce the message severity to debug so that if debugging is still possible
in case the error code returned by perf is required for analysis.

Signed-off-by: Sinan Kaya <okaya@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Don Zickus <dzickus@redhat.com>
Cc: Kate Stewart <kstewart@linuxfoundation.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=599368
Link: https://lkml.kernel.org/r/20180803060943.2643-1-okaya@kernel.org
---
 kernel/watchdog_hld.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index e449a23e9d59..1f7020d65d0a 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -175,8 +175,8 @@ static int hardlockup_detector_event_create(void)
 	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
 					       watchdog_overflow_callback, NULL);
 	if (IS_ERR(evt)) {
-		pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
-			PTR_ERR(evt));
+		pr_debug("Perf event create on CPU %d failed with %ld\n", cpu,
+			 PTR_ERR(evt));
 		return PTR_ERR(evt);
 	}
 	this_cpu_write(watchdog_ev, evt);
-- 
cgit v1.2.3


From a9fe47e5e96be6401738f6c1e087edbcff6a5ceb Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 2 Aug 2018 15:40:37 -0500
Subject: ALSA: galaxy: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1468367 ("Missing break in switch")
Addresses-Coverity-ID: 115037 ("Missing break in switch")
Addresses-Coverity-ID: 115038 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/galaxy/galaxy.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/isa/galaxy/galaxy.c b/sound/isa/galaxy/galaxy.c
index b9994cc9f5fb..af9eea41379f 100644
--- a/sound/isa/galaxy/galaxy.c
+++ b/sound/isa/galaxy/galaxy.c
@@ -260,6 +260,7 @@ static int snd_galaxy_match(struct device *dev, unsigned int n)
 		break;
 	case 2:
 		irq[n] = 9;
+		/* Fall through */
 	case 9:
 		wss_config[n] |= WSS_CONFIG_IRQ_9;
 		break;
@@ -304,6 +305,7 @@ static int snd_galaxy_match(struct device *dev, unsigned int n)
 	case 1:
 		if (dma1[n] == 0)
 			break;
+		/* Fall through */
 	default:
 		dev_err(dev, "invalid capture DMA %d\n", dma2[n]);
 		return 0;
@@ -333,6 +335,7 @@ mpu:
 		break;
 	case 2:
 		mpu_irq[n] = 9;
+		/* Fall through */
 	case 9:
 		config[n] |= GALAXY_CONFIG_MPUIRQ_2;
 		break;
-- 
cgit v1.2.3


From 3e313f34720ea1bb876636263e30a779ff65836e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 2 Aug 2018 15:41:21 -0500
Subject: ALSA: opti92x: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1165394 ("Missing break in switch")
Addresses-Coverity-ID: 1167851 ("Missing break in switch")
Addresses-Coverity-ID: 402015 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/opti9xx/opti92x-ad1848.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/isa/opti9xx/opti92x-ad1848.c b/sound/isa/opti9xx/opti92x-ad1848.c
index 505cd81e19fa..ac0ab6eb40f0 100644
--- a/sound/isa/opti9xx/opti92x-ad1848.c
+++ b/sound/isa/opti9xx/opti92x-ad1848.c
@@ -261,6 +261,7 @@ static unsigned char snd_opti9xx_read(struct snd_opti9xx *chip,
 			retval = inb(chip->mc_base + 9);
 			break;
 		}
+		/* Fall through */
 
 	case OPTi9XX_HW_82C928:
 	case OPTi9XX_HW_82C929:
@@ -303,6 +304,7 @@ static void snd_opti9xx_write(struct snd_opti9xx *chip, unsigned char reg,
 			outb(value, chip->mc_base + 9);
 			break;
 		}
+		/* Fall through */
 
 	case OPTi9XX_HW_82C928:
 	case OPTi9XX_HW_82C929:
@@ -350,6 +352,7 @@ static int snd_opti9xx_configure(struct snd_opti9xx *chip,
 		snd_opti9xx_write_mask(chip, OPTi9XX_MC_REG(4), 0xf0, 0xfc);
 		/* enable wave audio */
 		snd_opti9xx_write_mask(chip, OPTi9XX_MC_REG(6), 0x02, 0x02);
+		/* Fall through */
 
 	case OPTi9XX_HW_82C925:
 		/* enable WSS mode */
-- 
cgit v1.2.3


From 734be97b967c7e2bab72b34da87534ccd854c72d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 2 Aug 2018 15:41:55 -0500
Subject: ALSA: opti9xx: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 402016 ("Missing break in switch")
Addresses-Coverity-ID: 1056542 ("Missing break in switch")
Addresses-Coverity-ID: 1339579 ("Missing break in switch")
Addresses-Coverity-ID: 1369526 ("Missing break in switch")
Addresses-Coverity-ID: 1369529 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/opti9xx/miro.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/sound/isa/opti9xx/miro.c b/sound/isa/opti9xx/miro.c
index 8894c7c18ad6..c6136c6b0214 100644
--- a/sound/isa/opti9xx/miro.c
+++ b/sound/isa/opti9xx/miro.c
@@ -176,10 +176,13 @@ static int aci_busy_wait(struct snd_miro_aci *aci)
 			switch (timeout-ACI_MINTIME) {
 			case 0 ... 9:
 				out /= 10;
+				/* fall through */
 			case 10 ... 19:
 				out /= 10;
+				/* fall through */
 			case 20 ... 30:
 				out /= 10;
+				/* fall through */
 			default:
 				set_current_state(TASK_UNINTERRUPTIBLE);
 				schedule_timeout(out);
@@ -834,6 +837,7 @@ static unsigned char snd_miro_read(struct snd_miro *chip,
 			retval = inb(chip->mc_base + 9);
 			break;
 		}
+		/* fall through */
 
 	case OPTi9XX_HW_82C929:
 		retval = inb(chip->mc_base + reg);
@@ -863,6 +867,7 @@ static void snd_miro_write(struct snd_miro *chip, unsigned char reg,
 			outb(value, chip->mc_base + 9);
 			break;
 		}
+		/* fall through */
 
 	case OPTi9XX_HW_82C929:
 		outb(value, chip->mc_base + reg);
-- 
cgit v1.2.3


From 13a01635823c409a0911304ee50987cb851317da Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 2 Aug 2018 15:42:39 -0500
Subject: ALSA: es18xx: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115075 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/es18xx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/isa/es18xx.c b/sound/isa/es18xx.c
index 2a6960c3e2a4..0d103d6f805e 100644
--- a/sound/isa/es18xx.c
+++ b/sound/isa/es18xx.c
@@ -1024,6 +1024,7 @@ static int snd_es18xx_put_mux(struct snd_kcontrol *kcontrol, struct snd_ctl_elem
 			val = 3;
 		} else
 			retVal = snd_es18xx_mixer_bits(chip, 0x7a, 0x08, 0x00) != 0x00;
+		/* fall through */
  /* 4 source chips */
 	case 0x1868:
 	case 0x1878:
-- 
cgit v1.2.3


From 301d328a6f8b53bb86c5ecf72db7bc178bcf1999 Mon Sep 17 00:00:00 2001
From: Peter Feiner <pfeiner@google.com>
Date: Wed, 1 Aug 2018 11:06:57 -0700
Subject: x86/cpufeatures: Add EPT_AD feature bit

Some Intel processors have an EPT feature whereby the accessed & dirty bits
in EPT entries can be updated by HW. MSR IA32_VMX_EPT_VPID_CAP exposes the
presence of this capability.

There is no point in trying to use that new feature bit in the VMX code as
VMX needs to read the MSR anyway to access other bits, but having the
feature bit for EPT_AD in place helps virtualization management as it
exposes "ept_ad" in /proc/cpuinfo/$proc/flags if the feature is present.

[ tglx: Amended changelog ]

Signed-off-by: Peter Feiner <pfeiner@google.com>
Signed-off-by: Peter Shier <pshier@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Jim Mattson <jmattson@google.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lkml.kernel.org/r/20180801180657.138051-1-pshier@google.com
---
 arch/x86/include/asm/cpufeatures.h |  2 +-
 arch/x86/kernel/cpu/intel.c        | 10 +++++++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..7fff98fa5855 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -229,7 +229,7 @@
 
 #define X86_FEATURE_VMMCALL		( 8*32+15) /* Prefer VMMCALL to VMCALL */
 #define X86_FEATURE_XENPV		( 8*32+16) /* "" Xen paravirtual guest */
-
+#define X86_FEATURE_EPT_AD		( 8*32+17) /* Intel Extended Page Table access-dirty bit */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (EBX), word 9 */
 #define X86_FEATURE_FSGSBASE		( 9*32+ 0) /* RDFSBASE, WRFSBASE, RDGSBASE, WRGSBASE instructions*/
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index eb75564f2d25..c050cd6066af 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -465,14 +465,17 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 #define X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC	0x00000001
 #define X86_VMX_FEATURE_PROC_CTLS2_EPT		0x00000002
 #define X86_VMX_FEATURE_PROC_CTLS2_VPID		0x00000020
+#define x86_VMX_FEATURE_EPT_CAP_AD		0x00200000
 
 	u32 vmx_msr_low, vmx_msr_high, msr_ctl, msr_ctl2;
+	u32 msr_vpid_cap, msr_ept_cap;
 
 	clear_cpu_cap(c, X86_FEATURE_TPR_SHADOW);
 	clear_cpu_cap(c, X86_FEATURE_VNMI);
 	clear_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
 	clear_cpu_cap(c, X86_FEATURE_EPT);
 	clear_cpu_cap(c, X86_FEATURE_VPID);
+	clear_cpu_cap(c, X86_FEATURE_EPT_AD);
 
 	rdmsr(MSR_IA32_VMX_PROCBASED_CTLS, vmx_msr_low, vmx_msr_high);
 	msr_ctl = vmx_msr_high | vmx_msr_low;
@@ -487,8 +490,13 @@ static void detect_vmx_virtcap(struct cpuinfo_x86 *c)
 		if ((msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VIRT_APIC) &&
 		    (msr_ctl & X86_VMX_FEATURE_PROC_CTLS_TPR_SHADOW))
 			set_cpu_cap(c, X86_FEATURE_FLEXPRIORITY);
-		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT)
+		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_EPT) {
 			set_cpu_cap(c, X86_FEATURE_EPT);
+			rdmsr(MSR_IA32_VMX_EPT_VPID_CAP,
+			      msr_ept_cap, msr_vpid_cap);
+			if (msr_ept_cap & x86_VMX_FEATURE_EPT_CAP_AD)
+				set_cpu_cap(c, X86_FEATURE_EPT_AD);
+		}
 		if (msr_ctl2 & X86_VMX_FEATURE_PROC_CTLS2_VPID)
 			set_cpu_cap(c, X86_FEATURE_VPID);
 	}
-- 
cgit v1.2.3


From 706d51681d636a0c4a5ef53395ec3b803e45ed4d Mon Sep 17 00:00:00 2001
From: Sai Praneeth <sai.praneeth.prakhya@intel.com>
Date: Wed, 1 Aug 2018 11:42:25 -0700
Subject: x86/speculation: Support Enhanced IBRS on future CPUs

Future Intel processors will support "Enhanced IBRS" which is an "always
on" mode i.e. IBRS bit in SPEC_CTRL MSR is enabled once and never
disabled.

From the specification [1]:

 "With enhanced IBRS, the predicted targets of indirect branches
  executed cannot be controlled by software that was executed in a less
  privileged predictor mode or on another logical processor. As a
  result, software operating on a processor with enhanced IBRS need not
  use WRMSR to set IA32_SPEC_CTRL.IBRS after every transition to a more
  privileged predictor mode. Software can isolate predictor modes
  effectively simply by setting the bit once. Software need not disable
  enhanced IBRS prior to entering a sleep state such as MWAIT or HLT."

If Enhanced IBRS is supported by the processor then use it as the
preferred spectre v2 mitigation mechanism instead of Retpoline. Intel's
Retpoline white paper [2] states:

 "Retpoline is known to be an effective branch target injection (Spectre
  variant 2) mitigation on Intel processors belonging to family 6
  (enumerated by the CPUID instruction) that do not have support for
  enhanced IBRS. On processors that support enhanced IBRS, it should be
  used for mitigation instead of retpoline."

The reason why Enhanced IBRS is the recommended mitigation on processors
which support it is that these processors also support CET which
provides a defense against ROP attacks. Retpoline is very similar to ROP
techniques and might trigger false positives in the CET defense.

If Enhanced IBRS is selected as the mitigation technique for spectre v2,
the IBRS bit in SPEC_CTRL MSR is set once at boot time and never
cleared. Kernel also has to make sure that IBRS bit remains set after
VMEXIT because the guest might have cleared the bit. This is already
covered by the existing x86_spec_ctrl_set_guest() and
x86_spec_ctrl_restore_host() speculation control functions.

Enhanced IBRS still requires IBPB for full mitigation.

[1] Speculative-Execution-Side-Channel-Mitigations.pdf
[2] Retpoline-A-Branch-Target-Injection-Mitigation.pdf
Both documents are available at:
https://bugzilla.kernel.org/show_bug.cgi?id=199511

Originally-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Sai Praneeth Prakhya <sai.praneeth.prakhya@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Tim C Chen <tim.c.chen@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ravi Shankar <ravi.v.shankar@intel.com>
Link: https://lkml.kernel.org/r/1533148945-24095-1-git-send-email-sai.praneeth.prakhya@intel.com
---
 arch/x86/include/asm/cpufeatures.h   |  1 +
 arch/x86/include/asm/nospec-branch.h |  1 +
 arch/x86/kernel/cpu/bugs.c           | 20 ++++++++++++++++++--
 arch/x86/kernel/cpu/common.c         |  3 +++
 4 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..2687cd8e8d58 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,7 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_IBRS_ENHANCED	( 7*32+29) /* Enhanced IBRS */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index c99082e2ef13..fd2a8c1b88bc 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -214,6 +214,7 @@ enum spectre_v2_mitigation {
 	SPECTRE_V2_RETPOLINE_MINIMAL_AMD,
 	SPECTRE_V2_RETPOLINE_GENERIC,
 	SPECTRE_V2_RETPOLINE_AMD,
+	SPECTRE_V2_IBRS_ENHANCED,
 };
 
 /* The Speculative Store Bypass disable variants */
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index bc8c43b22460..405a9a61bb89 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -130,6 +130,7 @@ static const char *spectre_v2_strings[] = {
 	[SPECTRE_V2_RETPOLINE_MINIMAL_AMD]	= "Vulnerable: Minimal AMD ASM retpoline",
 	[SPECTRE_V2_RETPOLINE_GENERIC]		= "Mitigation: Full generic retpoline",
 	[SPECTRE_V2_RETPOLINE_AMD]		= "Mitigation: Full AMD retpoline",
+	[SPECTRE_V2_IBRS_ENHANCED]		= "Mitigation: Enhanced IBRS",
 };
 
 #undef pr_fmt
@@ -332,6 +333,13 @@ static void __init spectre_v2_select_mitigation(void)
 
 	case SPECTRE_V2_CMD_FORCE:
 	case SPECTRE_V2_CMD_AUTO:
+		if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
+			mode = SPECTRE_V2_IBRS_ENHANCED;
+			/* Force it so VMEXIT will restore correctly */
+			x86_spec_ctrl_base |= SPEC_CTRL_IBRS;
+			wrmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+			goto specv2_set_mode;
+		}
 		if (IS_ENABLED(CONFIG_RETPOLINE))
 			goto retpoline_auto;
 		break;
@@ -369,6 +377,7 @@ retpoline_auto:
 		setup_force_cpu_cap(X86_FEATURE_RETPOLINE);
 	}
 
+specv2_set_mode:
 	spectre_v2_enabled = mode;
 	pr_info("%s\n", spectre_v2_strings[mode]);
 
@@ -391,9 +400,16 @@ retpoline_auto:
 
 	/*
 	 * Retpoline means the kernel is safe because it has no indirect
-	 * branches. But firmware isn't, so use IBRS to protect that.
+	 * branches. Enhanced IBRS protects firmware too, so, enable restricted
+	 * speculation around firmware calls only when Enhanced IBRS isn't
+	 * supported.
+	 *
+	 * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
+	 * the user might select retpoline on the kernel command line and if
+	 * the CPU supports Enhanced IBRS, kernel might un-intentionally not
+	 * enable IBRS around firmware calls.
 	 */
-	if (boot_cpu_has(X86_FEATURE_IBRS)) {
+	if (boot_cpu_has(X86_FEATURE_IBRS) && mode != SPECTRE_V2_IBRS_ENHANCED) {
 		setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
 		pr_info("Enabling Restricted Speculation for firmware calls\n");
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 43a927eb9c09..df28e931d732 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1005,6 +1005,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 	   !cpu_has(c, X86_FEATURE_AMD_SSB_NO))
 		setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS);
 
+	if (ia32_cap & ARCH_CAP_IBRS_ALL)
+		setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED);
+
 	if (x86_match_cpu(cpu_no_meltdown))
 		return;
 
-- 
cgit v1.2.3


From 4a7a54a55e7237386cacc73f173e74329773ac93 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Fri, 3 Aug 2018 13:06:35 +0200
Subject: x86/intel_rdt: Disable PMU access

Peter is objecting to the direct PMU access in RDT. Right now the PMU usage
is broken anyway as it is not coordinated with perf.

Until this discussion settled, disable the PMU mechanics by simply
rejecting the type '2' measurement in the resctrl file.

Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Reinette Chatre <reinette.chatre@intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: fenghua.yu@intel.com
Cc: tony.luck@intel.com
Cc: vikas.shivappa@linux.intel.com
CC: gavin.hindman@intel.com
Cc: jithu.joseph@intel.com
Cc: hpa@zytor.com
---
 arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
index f80c58f8adc3..40f3903ae5d9 100644
--- a/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
+++ b/arch/x86/kernel/cpu/intel_rdt_pseudo_lock.c
@@ -1171,7 +1171,7 @@ static ssize_t pseudo_lock_measure_trigger(struct file *file,
 	buf[buf_size] = '\0';
 	ret = kstrtoint(buf, 10, &sel);
 	if (ret == 0) {
-		if (sel != 1 && sel != 2)
+		if (sel != 1)
 			return -EINVAL;
 		ret = debugfs_file_get(file->f_path.dentry);
 		if (ret)
-- 
cgit v1.2.3


From 85418feff6faa96b6f3cee29235821d9afd8a592 Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Fri, 3 Aug 2018 11:20:49 +0200
Subject: Bluetooth: btusb: Use bt_dev_err for Intel firmware loading errors

Replace the BT_ERR functions with bt_dev_err to get a consistent error
printout that always prefixes the HCI device identifier.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 drivers/bluetooth/btusb.c | 77 +++++++++++++++++++++++------------------------
 1 file changed, 37 insertions(+), 40 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index f99fc6bfd1da..cd2e5cf14ea5 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -1598,13 +1598,13 @@ static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev,
 	ret = request_firmware(&fw, fwname, &hdev->dev);
 	if (ret < 0) {
 		if (ret == -EINVAL) {
-			BT_ERR("%s Intel firmware file request failed (%d)",
-			       hdev->name, ret);
+			bt_dev_err(hdev, "Intel firmware file request failed (%d)",
+				   ret);
 			return NULL;
 		}
 
-		BT_ERR("%s failed to open Intel firmware file: %s(%d)",
-		       hdev->name, fwname, ret);
+		bt_dev_err(hdev, "failed to open Intel firmware file: %s (%d)",
+			   fwname, ret);
 
 		/* If the correct firmware patch file is not found, use the
 		 * default firmware patch file instead
@@ -1612,8 +1612,8 @@ static const struct firmware *btusb_setup_intel_get_fw(struct hci_dev *hdev,
 		snprintf(fwname, sizeof(fwname), "intel/ibt-hw-%x.%x.bseq",
 			 ver->hw_platform, ver->hw_variant);
 		if (request_firmware(&fw, fwname, &hdev->dev) < 0) {
-			BT_ERR("%s failed to open default Intel fw file: %s",
-			       hdev->name, fwname);
+			bt_dev_err(hdev, "failed to open default fw file: %s",
+				   fwname);
 			return NULL;
 		}
 	}
@@ -1642,7 +1642,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * process.
 	 */
 	if (remain > HCI_COMMAND_HDR_SIZE && *fw_ptr[0] != 0x01) {
-		BT_ERR("%s Intel fw corrupted: invalid cmd read", hdev->name);
+		bt_dev_err(hdev, "Intel fw corrupted: invalid cmd read");
 		return -EINVAL;
 	}
 	(*fw_ptr)++;
@@ -1656,7 +1656,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * of command parameter. If not, the firmware file is corrupted.
 	 */
 	if (remain < cmd->plen) {
-		BT_ERR("%s Intel fw corrupted: invalid cmd len", hdev->name);
+		bt_dev_err(hdev, "Intel fw corrupted: invalid cmd len");
 		return -EFAULT;
 	}
 
@@ -1689,8 +1689,7 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 		remain -= sizeof(*evt);
 
 		if (remain < evt->plen) {
-			BT_ERR("%s Intel fw corrupted: invalid evt len",
-			       hdev->name);
+			bt_dev_err(hdev, "Intel fw corrupted: invalid evt len");
 			return -EFAULT;
 		}
 
@@ -1704,15 +1703,15 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * file is corrupted.
 	 */
 	if (!evt || !evt_param || remain < 0) {
-		BT_ERR("%s Intel fw corrupted: invalid evt read", hdev->name);
+		bt_dev_err(hdev, "Intel fw corrupted: invalid evt read");
 		return -EFAULT;
 	}
 
 	skb = __hci_cmd_sync_ev(hdev, le16_to_cpu(cmd->opcode), cmd->plen,
 				cmd_param, evt->evt, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s sending Intel patch command (0x%4.4x) failed (%ld)",
-		       hdev->name, cmd->opcode, PTR_ERR(skb));
+		bt_dev_err(hdev, "sending Intel patch command (0x%4.4x) failed (%ld)",
+			   cmd->opcode, PTR_ERR(skb));
 		return PTR_ERR(skb);
 	}
 
@@ -1721,15 +1720,15 @@ static int btusb_setup_intel_patching(struct hci_dev *hdev,
 	 * the contents of the event.
 	 */
 	if (skb->len != evt->plen) {
-		BT_ERR("%s mismatch event length (opcode 0x%4.4x)", hdev->name,
-		       le16_to_cpu(cmd->opcode));
+		bt_dev_err(hdev, "mismatch event length (opcode 0x%4.4x)",
+			   le16_to_cpu(cmd->opcode));
 		kfree_skb(skb);
 		return -EFAULT;
 	}
 
 	if (memcmp(skb->data, evt_param, evt->plen)) {
-		BT_ERR("%s mismatch event parameter (opcode 0x%4.4x)",
-		       hdev->name, le16_to_cpu(cmd->opcode));
+		bt_dev_err(hdev, "mismatch event parameter (opcode 0x%4.4x)",
+			   le16_to_cpu(cmd->opcode));
 		kfree_skb(skb);
 		return -EFAULT;
 	}
@@ -1758,8 +1757,8 @@ static int btusb_setup_intel(struct hci_dev *hdev)
 	 */
 	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s sending initial HCI reset command failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		bt_dev_err(hdev, "sending initial HCI reset command failed (%ld)",
+			   PTR_ERR(skb));
 		return PTR_ERR(skb);
 	}
 	kfree_skb(skb);
@@ -2089,8 +2088,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * for now only accept this single value.
 	 */
 	if (ver.hw_platform != 0x37) {
-		BT_ERR("%s: Unsupported Intel hardware platform (%u)",
-		       hdev->name, ver.hw_platform);
+		bt_dev_err(hdev, "Unsupported Intel hardware platform (%u)",
+			   ver.hw_platform);
 		return -EINVAL;
 	}
 
@@ -2109,8 +2108,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	case 0x14:	/* QnJ, IcP */
 		break;
 	default:
-		BT_ERR("%s: Unsupported Intel hardware variant (%u)",
-		       hdev->name, ver.hw_variant);
+		bt_dev_err(hdev, "Unsupported Intel hardware variant (%u)",
+			   ver.hw_variant);
 		return -EINVAL;
 	}
 
@@ -2139,8 +2138,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * choice is to return an error and abort the device initialization.
 	 */
 	if (ver.fw_variant != 0x06) {
-		BT_ERR("%s: Unsupported Intel firmware variant (%u)",
-		       hdev->name, ver.fw_variant);
+		bt_dev_err(hdev, "Unsupported Intel firmware variant (%u)",
+			   ver.fw_variant);
 		return -ENODEV;
 	}
 
@@ -2156,8 +2155,8 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 	 * that this bootloader does not send them, then abort the setup.
 	 */
 	if (params.limited_cce != 0x00) {
-		BT_ERR("%s: Unsupported Intel firmware loading method (%u)",
-		       hdev->name, params.limited_cce);
+		bt_dev_err(hdev, "Unsupported Intel firmware loading method (%u)",
+			   params.limited_cce);
 		return -EINVAL;
 	}
 
@@ -2207,14 +2206,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 			 le16_to_cpu(ver.fw_revision));
 		break;
 	default:
-		BT_ERR("%s: Unsupported Intel firmware naming", hdev->name);
+		bt_dev_err(hdev, "Unsupported Intel firmware naming");
 		return -EINVAL;
 	}
 
 	err = request_firmware(&fw, fwname, &hdev->dev);
 	if (err < 0) {
-		BT_ERR("%s: Failed to load Intel firmware file (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "Failed to load Intel firmware file (%d)", err);
 		return err;
 	}
 
@@ -2240,13 +2238,13 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 			 le16_to_cpu(ver.fw_revision));
 		break;
 	default:
-		BT_ERR("%s: Unsupported Intel firmware naming", hdev->name);
+		bt_dev_err(hdev, "Unsupported Intel firmware naming");
 		return -EINVAL;
 	}
 
 	if (fw->size < 644) {
-		BT_ERR("%s: Invalid size of firmware file (%zu)",
-		       hdev->name, fw->size);
+		bt_dev_err(hdev, "Invalid size of firmware file (%zu)",
+			   fw->size);
 		err = -EBADF;
 		goto done;
 	}
@@ -2277,18 +2275,18 @@ static int btusb_setup_intel_new(struct hci_dev *hdev)
 				  TASK_INTERRUPTIBLE,
 				  msecs_to_jiffies(5000));
 	if (err == -EINTR) {
-		BT_ERR("%s: Firmware loading interrupted", hdev->name);
+		bt_dev_err(hdev, "Firmware loading interrupted");
 		goto done;
 	}
 
 	if (err) {
-		BT_ERR("%s: Firmware loading timeout", hdev->name);
+		bt_dev_err(hdev, "Firmware loading timeout");
 		err = -ETIMEDOUT;
 		goto done;
 	}
 
 	if (test_bit(BTUSB_FIRMWARE_FAILED, &data->flags)) {
-		BT_ERR("%s: Firmware loading failed", hdev->name);
+		bt_dev_err(hdev, "Firmware loading failed");
 		err = -ENOEXEC;
 		goto done;
 	}
@@ -2327,12 +2325,12 @@ done:
 				  msecs_to_jiffies(1000));
 
 	if (err == -EINTR) {
-		BT_ERR("%s: Device boot interrupted", hdev->name);
+		bt_dev_err(hdev, "Device boot interrupted");
 		return -EINTR;
 	}
 
 	if (err) {
-		BT_ERR("%s: Device boot timeout", hdev->name);
+		bt_dev_err(hdev, "Device boot timeout");
 		return -ETIMEDOUT;
 	}
 
@@ -2392,8 +2390,7 @@ static int btusb_shutdown_intel(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, 0xfc3f, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		ret = PTR_ERR(skb);
-		BT_ERR("%s: turning off Intel device LED failed (%ld)",
-		       hdev->name, ret);
+		bt_dev_err(hdev, "turning off Intel device LED failed");
 		return ret;
 	}
 	kfree_skb(skb);
-- 
cgit v1.2.3


From f96dbd322a8f1368dc663c48c7dc3c66a086ec9f Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 2 Aug 2018 16:57:12 +0200
Subject: Bluetooth: btrtl: add MODULE_FIRMWARE declarations

This makes the firmware names show up in modinfo.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Jeremy Cline <jeremy@jcline.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btrtl.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 437f080deaab..c08f63e3bc14 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -528,3 +528,12 @@ MODULE_AUTHOR("Daniel Drake <drake@endlessm.com>");
 MODULE_DESCRIPTION("Bluetooth support for Realtek devices ver " VERSION);
 MODULE_VERSION(VERSION);
 MODULE_LICENSE("GPL");
+MODULE_FIRMWARE("rtl_bt/rtl8723a_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723b_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723b_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8761a_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8761a_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8821a_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8821a_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8822b_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8822b_config.bin");
-- 
cgit v1.2.3


From 26503ad25de8c7c93a2037f919c2e49a62cf65f1 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 2 Aug 2018 16:57:13 +0200
Subject: Bluetooth: btrtl: split the device initialization into smaller parts

This prepares the btrtl code so it can be used to initialize Bluetooth
modules connected via UART (these are found for example on the RTL8723BS
and RTL8723DS SDIO chips, which come with an embedded UART Bluetooth
module).

The Realtek "rtl8723bs_bt" and "rtl8723ds_bt" userspace Bluetooth UART
initialization tools (rtk_hciattach) use the following sequence:
1) send H5 sync pattern (already supported by hci_h5)
2) get LMP version (already supported by btrtl)
3) get ROM version (already supported by btrtl)
4) load the firmware and config for the current chipset (already
   supported by btrtl)
5) read UART settings from the config blob (currently not supported)
6) send UART settings via a vendor command to the device (which changes
   the baudrate of the device and enables or disables flow control
   depending on the config)
7) change the baudrate and flow control settings on the host
8) send the firmware and config blob to the device (already supported by
   btrtl)

The main reason why the initialization has to be split is step #7. This
requires changes to the underlying "bus", which should be kept outside
of the "generic" btrtl driver.
The idea for this split is borrowed from the btbcm driver but adjusted
where needed (the btrtl driver for example needs two blobs: firmware and
config, while the btbcm only needs one).

This also prepares the code for step #5 (parsing the config blob) by
centralizing the code which loads the firmware and config blobs and
storing the result in the new struct btrtl_device_info.

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Jeremy Cline <jeremy@jcline.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btrtl.c | 279 ++++++++++++++++++++++++++++------------------
 drivers/bluetooth/btrtl.h |  26 +++++
 2 files changed, 199 insertions(+), 106 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index c08f63e3bc14..bb6c138b47cc 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -47,48 +47,96 @@ struct id_table {
 	__u16 lmp_subver;
 	__u16 hci_rev;
 	bool config_needed;
+	bool has_rom_version;
 	char *fw_name;
 	char *cfg_name;
 };
 
+struct btrtl_device_info {
+	const struct id_table *ic_info;
+	u8 rom_version;
+	u8 *fw_data;
+	int fw_len;
+	u8 *cfg_data;
+	int cfg_len;
+};
+
 static const struct id_table ic_id_table[] = {
+	{ IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8723A, 0x0,
+	  .config_needed = false,
+	  .has_rom_version = false,
+	  .fw_name = "rtl_bt/rtl8723a_fw.bin",
+	  .cfg_name = NULL },
+
+	{ IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_3499, 0x0,
+	  .config_needed = false,
+	  .has_rom_version = false,
+	  .fw_name = "rtl_bt/rtl8723a_fw.bin",
+	  .cfg_name = NULL },
+
 	/* 8723B */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb),
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723b_fw.bin",
 	  .cfg_name = "rtl_bt/rtl8723b_config.bin" },
 
 	/* 8723D */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xd),
 	  .config_needed = true,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723d_fw.bin",
 	  .cfg_name = "rtl_bt/rtl8723d_config.bin" },
 
 	/* 8821A */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xa),
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8821a_fw.bin",
 	  .cfg_name = "rtl_bt/rtl8821a_config.bin" },
 
 	/* 8821C */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xc),
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8821c_fw.bin",
 	  .cfg_name = "rtl_bt/rtl8821c_config.bin" },
 
 	/* 8761A */
 	{ IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8761A, 0x0,
 	  .config_needed = false,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8761a_fw.bin",
 	  .cfg_name = "rtl_bt/rtl8761a_config.bin" },
 
 	/* 8822B */
 	{ IC_INFO(RTL_ROM_LMP_8822B, 0xb),
 	  .config_needed = true,
+	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8822b_fw.bin",
 	  .cfg_name = "rtl_bt/rtl8822b_config.bin" },
 	};
 
+static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) {
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) &&
+		    (ic_id_table[i].lmp_subver != lmp_subver))
+			continue;
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) &&
+		    (ic_id_table[i].hci_rev != hci_rev))
+			continue;
+
+		break;
+	}
+	if (i >= ARRAY_SIZE(ic_id_table))
+		return NULL;
+
+	return &ic_id_table[i];
+}
+
 static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
 {
 	struct rtl_rom_version_evt *rom_version;
@@ -118,16 +166,16 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
 	return 0;
 }
 
-static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
-				const struct firmware *fw,
+static int rtlbt_parse_firmware(struct hci_dev *hdev,
+				struct btrtl_device_info *btrtl_dev,
 				unsigned char **_buf)
 {
 	const u8 extension_sig[] = { 0x51, 0x04, 0xfd, 0x77 };
 	struct rtl_epatch_header *epatch_info;
 	unsigned char *buf;
-	int i, ret, len;
+	int i, len;
 	size_t min_size;
-	u8 opcode, length, data, rom_version = 0;
+	u8 opcode, length, data;
 	int project_id = -1;
 	const unsigned char *fwptr, *chip_id_base;
 	const unsigned char *patch_length_base, *patch_offset_base;
@@ -146,15 +194,11 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 		{ RTL_ROM_LMP_8821A, 10 },	/* 8821C */
 	};
 
-	ret = rtl_read_rom_version(hdev, &rom_version);
-	if (ret)
-		return ret;
-
 	min_size = sizeof(struct rtl_epatch_header) + sizeof(extension_sig) + 3;
-	if (fw->size < min_size)
+	if (btrtl_dev->fw_len < min_size)
 		return -EINVAL;
 
-	fwptr = fw->data + fw->size - sizeof(extension_sig);
+	fwptr = btrtl_dev->fw_data + btrtl_dev->fw_len - sizeof(extension_sig);
 	if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) {
 		BT_ERR("%s: extension section signature mismatch", hdev->name);
 		return -EINVAL;
@@ -166,7 +210,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 	 * Once we have that, we double-check that that project_id is suitable
 	 * for the hardware we are working with.
 	 */
-	while (fwptr >= fw->data + (sizeof(struct rtl_epatch_header) + 3)) {
+	while (fwptr >= btrtl_dev->fw_data + (sizeof(*epatch_info) + 3)) {
 		opcode = *--fwptr;
 		length = *--fwptr;
 		data = *--fwptr;
@@ -206,13 +250,15 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 		return -EINVAL;
 	}
 
-	if (lmp_subver != project_id_to_lmp_subver[i].lmp_subver) {
+	if (btrtl_dev->ic_info->lmp_subver !=
+				project_id_to_lmp_subver[i].lmp_subver) {
 		BT_ERR("%s: firmware is for %x but this is a %x", hdev->name,
-		       project_id_to_lmp_subver[i].lmp_subver, lmp_subver);
+		       project_id_to_lmp_subver[i].lmp_subver,
+		       btrtl_dev->ic_info->lmp_subver);
 		return -EINVAL;
 	}
 
-	epatch_info = (struct rtl_epatch_header *)fw->data;
+	epatch_info = (struct rtl_epatch_header *)btrtl_dev->fw_data;
 	if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) {
 		BT_ERR("%s: bad EPATCH signature", hdev->name);
 		return -EINVAL;
@@ -229,16 +275,16 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 	 * Find the right patch for this chip.
 	 */
 	min_size += 8 * num_patches;
-	if (fw->size < min_size)
+	if (btrtl_dev->fw_len < min_size)
 		return -EINVAL;
 
-	chip_id_base = fw->data + sizeof(struct rtl_epatch_header);
+	chip_id_base = btrtl_dev->fw_data + sizeof(struct rtl_epatch_header);
 	patch_length_base = chip_id_base + (sizeof(u16) * num_patches);
 	patch_offset_base = patch_length_base + (sizeof(u16) * num_patches);
 	for (i = 0; i < num_patches; i++) {
 		u16 chip_id = get_unaligned_le16(chip_id_base +
 						 (i * sizeof(u16)));
-		if (chip_id == rom_version + 1) {
+		if (chip_id == btrtl_dev->rom_version + 1) {
 			patch_length = get_unaligned_le16(patch_length_base +
 							  (i * sizeof(u16)));
 			patch_offset = get_unaligned_le32(patch_offset_base +
@@ -249,20 +295,21 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, u16 lmp_subver,
 
 	if (!patch_offset) {
 		BT_ERR("%s: didn't find patch for chip id %d",
-		       hdev->name, rom_version);
+		       hdev->name, btrtl_dev->rom_version);
 		return -EINVAL;
 	}
 
 	BT_DBG("length=%x offset=%x index %d", patch_length, patch_offset, i);
 	min_size = patch_offset + patch_length;
-	if (fw->size < min_size)
+	if (btrtl_dev->fw_len < min_size)
 		return -EINVAL;
 
 	/* Copy the firmware into a new buffer and write the version at
 	 * the end.
 	 */
 	len = patch_length;
-	buf = kmemdup(fw->data + patch_offset, patch_length, GFP_KERNEL);
+	buf = kmemdup(btrtl_dev->fw_data + patch_offset, patch_length,
+		      GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
@@ -324,7 +371,7 @@ out:
 	return ret;
 }
 
-static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff)
+static int rtl_load_file(struct hci_dev *hdev, const char *name, u8 **buff)
 {
 	const struct firmware *fw;
 	int ret;
@@ -343,96 +390,37 @@ static int rtl_load_config(struct hci_dev *hdev, const char *name, u8 **buff)
 	return ret;
 }
 
-static int btrtl_setup_rtl8723a(struct hci_dev *hdev)
+static int btrtl_setup_rtl8723a(struct hci_dev *hdev,
+				struct btrtl_device_info *btrtl_dev)
 {
-	const struct firmware *fw;
-	int ret;
-
-	bt_dev_info(hdev, "rtl: loading rtl_bt/rtl8723a_fw.bin");
-	ret = request_firmware(&fw, "rtl_bt/rtl8723a_fw.bin", &hdev->dev);
-	if (ret < 0) {
-		BT_ERR("%s: Failed to load rtl_bt/rtl8723a_fw.bin", hdev->name);
-		return ret;
-	}
-
-	if (fw->size < 8) {
-		ret = -EINVAL;
-		goto out;
-	}
+	if (btrtl_dev->fw_len < 8)
+		return -EINVAL;
 
 	/* Check that the firmware doesn't have the epatch signature
 	 * (which is only for RTL8723B and newer).
 	 */
-	if (!memcmp(fw->data, RTL_EPATCH_SIGNATURE, 8)) {
+	if (!memcmp(btrtl_dev->fw_data, RTL_EPATCH_SIGNATURE, 8)) {
 		BT_ERR("%s: unexpected EPATCH signature!", hdev->name);
-		ret = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
-	ret = rtl_download_firmware(hdev, fw->data, fw->size);
-
-out:
-	release_firmware(fw);
-	return ret;
+	return rtl_download_firmware(hdev, btrtl_dev->fw_data,
+				     btrtl_dev->fw_len);
 }
 
-static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev,
-				u16 lmp_subver)
+static int btrtl_setup_rtl8723b(struct hci_dev *hdev,
+				struct btrtl_device_info *btrtl_dev)
 {
 	unsigned char *fw_data = NULL;
-	const struct firmware *fw;
 	int ret;
-	int cfg_sz;
-	u8 *cfg_buff = NULL;
 	u8 *tbuff;
-	char *cfg_name = NULL;
-	char *fw_name = NULL;
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(ic_id_table); i++) {
-		if ((ic_id_table[i].match_flags & IC_MATCH_FL_LMPSUBV) &&
-		    (ic_id_table[i].lmp_subver != lmp_subver))
-			continue;
-		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) &&
-		    (ic_id_table[i].hci_rev != hci_rev))
-			continue;
-
-		break;
-	}
-
-	if (i >= ARRAY_SIZE(ic_id_table)) {
-		BT_ERR("%s: unknown IC info, lmp subver %04x, hci rev %04x",
-		       hdev->name, lmp_subver, hci_rev);
-		return -EINVAL;
-	}
-
-	cfg_name = ic_id_table[i].cfg_name;
-
-	if (cfg_name) {
-		cfg_sz = rtl_load_config(hdev, cfg_name, &cfg_buff);
-		if (cfg_sz < 0) {
-			cfg_sz = 0;
-			if (ic_id_table[i].config_needed)
-				BT_ERR("Necessary config file %s not found\n",
-				       cfg_name);
-		}
-	} else
-		cfg_sz = 0;
-
-	fw_name = ic_id_table[i].fw_name;
-	bt_dev_info(hdev, "rtl: loading %s", fw_name);
-	ret = request_firmware(&fw, fw_name, &hdev->dev);
-	if (ret < 0) {
-		BT_ERR("%s: Failed to load %s", hdev->name, fw_name);
-		goto err_req_fw;
-	}
 
-	ret = rtlbt_parse_firmware(hdev, lmp_subver, fw, &fw_data);
+	ret = rtlbt_parse_firmware(hdev, btrtl_dev, &fw_data);
 	if (ret < 0)
 		goto out;
 
-	if (cfg_sz) {
-		tbuff = kzalloc(ret + cfg_sz, GFP_KERNEL);
+	if (btrtl_dev->cfg_len > 0) {
+		tbuff = kzalloc(ret + btrtl_dev->cfg_len, GFP_KERNEL);
 		if (!tbuff) {
 			ret = -ENOMEM;
 			goto out;
@@ -441,22 +429,18 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, u16 hci_rev,
 		memcpy(tbuff, fw_data, ret);
 		kfree(fw_data);
 
-		memcpy(tbuff + ret, cfg_buff, cfg_sz);
-		ret += cfg_sz;
+		memcpy(tbuff + ret, btrtl_dev->cfg_data, btrtl_dev->cfg_len);
+		ret += btrtl_dev->cfg_len;
 
 		fw_data = tbuff;
 	}
 
-	bt_dev_info(hdev, "cfg_sz %d, total size %d", cfg_sz, ret);
+	rtl_dev_info(hdev, "cfg_sz %d, total sz %d\n", btrtl_dev->cfg_len, ret);
 
 	ret = rtl_download_firmware(hdev, fw_data, ret);
 
 out:
-	release_firmware(fw);
 	kfree(fw_data);
-err_req_fw:
-	if (cfg_sz)
-		kfree(cfg_buff);
 	return ret;
 }
 
@@ -482,15 +466,33 @@ static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev)
 	return skb;
 }
 
-int btrtl_setup_realtek(struct hci_dev *hdev)
+void btrtl_free(struct btrtl_device_info *btrtl_dev)
+{
+	kfree(btrtl_dev->fw_data);
+	kfree(btrtl_dev->cfg_data);
+	kfree(btrtl_dev);
+}
+EXPORT_SYMBOL_GPL(btrtl_free);
+
+struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
 {
+	struct btrtl_device_info *btrtl_dev;
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *resp;
 	u16 hci_rev, lmp_subver;
+	int ret;
+
+	btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL);
+	if (!btrtl_dev) {
+		ret = -ENOMEM;
+		goto err_alloc;
+	}
 
 	skb = btrtl_read_local_version(hdev);
-	if (IS_ERR(skb))
-		return -PTR_ERR(skb);
+	if (IS_ERR(skb)) {
+		ret = PTR_ERR(skb);
+		goto err_free;
+	}
 
 	resp = (struct hci_rp_read_local_version *)skb->data;
 	bt_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x "
@@ -502,26 +504,91 @@ int btrtl_setup_realtek(struct hci_dev *hdev)
 	lmp_subver = le16_to_cpu(resp->lmp_subver);
 	kfree_skb(skb);
 
+	btrtl_dev->ic_info = btrtl_match_ic(lmp_subver, hci_rev);
+	if (!btrtl_dev->ic_info) {
+		rtl_dev_err(hdev, "unknown IC info, lmp subver %04x, hci rev %04x\n",
+			    lmp_subver, hci_rev);
+		ret = -EINVAL;
+		goto err_free;
+	}
+
+	if (btrtl_dev->ic_info->has_rom_version) {
+		ret = rtl_read_rom_version(hdev, &btrtl_dev->rom_version);
+		if (ret)
+			goto err_free;
+	}
+
+	btrtl_dev->fw_len = rtl_load_file(hdev, btrtl_dev->ic_info->fw_name,
+					  &btrtl_dev->fw_data);
+	if (btrtl_dev->fw_len < 0) {
+		rtl_dev_err(hdev, "firmware file %s not found\n",
+			    btrtl_dev->ic_info->fw_name);
+		ret = btrtl_dev->fw_len;
+		goto err_free;
+	}
+
+	if (btrtl_dev->ic_info->cfg_name) {
+		btrtl_dev->cfg_len = rtl_load_file(hdev,
+						   btrtl_dev->ic_info->cfg_name,
+						   &btrtl_dev->cfg_data);
+		if (btrtl_dev->ic_info->config_needed &&
+		    btrtl_dev->cfg_len <= 0) {
+			rtl_dev_err(hdev, "mandatory config file %s not found\n",
+				    btrtl_dev->ic_info->cfg_name);
+			ret = btrtl_dev->cfg_len;
+			goto err_free;
+		}
+	}
+
+	return btrtl_dev;
+
+err_free:
+	btrtl_free(btrtl_dev);
+err_alloc:
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(btrtl_initialize);
+
+int btrtl_download_firmware(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev)
+{
 	/* Match a set of subver values that correspond to stock firmware,
 	 * which is not compatible with standard btusb.
 	 * If matched, upload an alternative firmware that does conform to
 	 * standard btusb. Once that firmware is uploaded, the subver changes
 	 * to a different value.
 	 */
-	switch (lmp_subver) {
+	switch (btrtl_dev->ic_info->lmp_subver) {
 	case RTL_ROM_LMP_8723A:
 	case RTL_ROM_LMP_3499:
-		return btrtl_setup_rtl8723a(hdev);
+		return btrtl_setup_rtl8723a(hdev, btrtl_dev);
 	case RTL_ROM_LMP_8723B:
 	case RTL_ROM_LMP_8821A:
 	case RTL_ROM_LMP_8761A:
 	case RTL_ROM_LMP_8822B:
-		return btrtl_setup_rtl8723b(hdev, hci_rev, lmp_subver);
+		return btrtl_setup_rtl8723b(hdev, btrtl_dev);
 	default:
 		bt_dev_info(hdev, "rtl: assuming no firmware upload needed");
 		return 0;
 	}
 }
+EXPORT_SYMBOL_GPL(btrtl_download_firmware);
+
+int btrtl_setup_realtek(struct hci_dev *hdev)
+{
+	struct btrtl_device_info *btrtl_dev;
+	int ret;
+
+	btrtl_dev = btrtl_initialize(hdev);
+	if (IS_ERR(btrtl_dev))
+		return PTR_ERR(btrtl_dev);
+
+	ret = btrtl_download_firmware(hdev, btrtl_dev);
+
+	btrtl_free(btrtl_dev);
+
+	return ret;
+}
 EXPORT_SYMBOL_GPL(btrtl_setup_realtek);
 
 MODULE_AUTHOR("Daniel Drake <drake@endlessm.com>");
diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h
index 38ffe4890cd1..e41974f8af40 100644
--- a/drivers/bluetooth/btrtl.h
+++ b/drivers/bluetooth/btrtl.h
@@ -17,6 +17,13 @@
 
 #define RTL_FRAG_LEN 252
 
+#define rtl_dev_err(dev, fmt, ...) bt_dev_err(dev, "RTL: " fmt, ##__VA_ARGS__)
+#define rtl_dev_warn(dev, fmt, ...) bt_dev_warn(dev, "RTL: " fmt, ##__VA_ARGS__)
+#define rtl_dev_info(dev, fmt, ...) bt_dev_info(dev, "RTL: " fmt, ##__VA_ARGS__)
+#define rtl_dev_dbg(dev, fmt, ...) bt_dev_dbg(dev, "RTL: " fmt, ##__VA_ARGS__)
+
+struct btrtl_device_info;
+
 struct rtl_download_cmd {
 	__u8 index;
 	__u8 data[RTL_FRAG_LEN];
@@ -40,10 +47,29 @@ struct rtl_epatch_header {
 
 #if IS_ENABLED(CONFIG_BT_RTL)
 
+struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev);
+void btrtl_free(struct btrtl_device_info *btrtl_dev);
+int btrtl_download_firmware(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev);
 int btrtl_setup_realtek(struct hci_dev *hdev);
 
 #else
 
+static inline struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void btrtl_free(struct btrtl_device_info *btrtl_dev)
+{
+}
+
+static inline int btrtl_download_firmware(struct hci_dev *hdev,
+					  struct btrtl_device_info *btrtl_dev)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int btrtl_setup_realtek(struct hci_dev *hdev)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From a5c76e67ca82f12b6ba6d2cbc0d3ff5dc89c45af Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 2 Aug 2018 16:57:14 +0200
Subject: Bluetooth: btrtl: Use rtl_dev_err and rtl_dev_info

Consistently use rtl_dev_err and rtl_dev_info everywhere for messages.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btrtl.c | 58 ++++++++++++++++++++++-------------------------
 1 file changed, 27 insertions(+), 31 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index bb6c138b47cc..0500b598691e 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -145,20 +145,20 @@ static int rtl_read_rom_version(struct hci_dev *hdev, u8 *version)
 	/* Read RTL ROM version command */
 	skb = __hci_cmd_sync(hdev, 0xfc6d, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: Read ROM version failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		rtl_dev_err(hdev, "Read ROM version failed (%ld)\n",
+			    PTR_ERR(skb));
 		return PTR_ERR(skb);
 	}
 
 	if (skb->len != sizeof(*rom_version)) {
-		BT_ERR("%s: RTL version event length mismatch", hdev->name);
+		rtl_dev_err(hdev, "RTL version event length mismatch\n");
 		kfree_skb(skb);
 		return -EIO;
 	}
 
 	rom_version = (struct rtl_rom_version_evt *)skb->data;
-	bt_dev_info(hdev, "rom_version status=%x version=%x",
-		    rom_version->status, rom_version->version);
+	rtl_dev_info(hdev, "rom_version status=%x version=%x\n",
+		     rom_version->status, rom_version->version);
 
 	*version = rom_version->version;
 
@@ -200,7 +200,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 
 	fwptr = btrtl_dev->fw_data + btrtl_dev->fw_len - sizeof(extension_sig);
 	if (memcmp(fwptr, extension_sig, sizeof(extension_sig)) != 0) {
-		BT_ERR("%s: extension section signature mismatch", hdev->name);
+		rtl_dev_err(hdev, "extension section signature mismatch\n");
 		return -EINVAL;
 	}
 
@@ -221,8 +221,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 			break;
 
 		if (length == 0) {
-			BT_ERR("%s: found instruction with length 0",
-			       hdev->name);
+			rtl_dev_err(hdev, "found instruction with length 0\n");
 			return -EINVAL;
 		}
 
@@ -235,7 +234,7 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 	}
 
 	if (project_id < 0) {
-		BT_ERR("%s: failed to find version instruction", hdev->name);
+		rtl_dev_err(hdev, "failed to find version instruction\n");
 		return -EINVAL;
 	}
 
@@ -246,21 +245,21 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 	}
 
 	if (i >= ARRAY_SIZE(project_id_to_lmp_subver)) {
-		BT_ERR("%s: unknown project id %d", hdev->name, project_id);
+		rtl_dev_err(hdev, "unknown project id %d\n", project_id);
 		return -EINVAL;
 	}
 
 	if (btrtl_dev->ic_info->lmp_subver !=
 				project_id_to_lmp_subver[i].lmp_subver) {
-		BT_ERR("%s: firmware is for %x but this is a %x", hdev->name,
-		       project_id_to_lmp_subver[i].lmp_subver,
-		       btrtl_dev->ic_info->lmp_subver);
+		rtl_dev_err(hdev, "firmware is for %x but this is a %x\n",
+			    project_id_to_lmp_subver[i].lmp_subver,
+			    btrtl_dev->ic_info->lmp_subver);
 		return -EINVAL;
 	}
 
 	epatch_info = (struct rtl_epatch_header *)btrtl_dev->fw_data;
 	if (memcmp(epatch_info->signature, RTL_EPATCH_SIGNATURE, 8) != 0) {
-		BT_ERR("%s: bad EPATCH signature", hdev->name);
+		rtl_dev_err(hdev, "bad EPATCH signature\n");
 		return -EINVAL;
 	}
 
@@ -294,8 +293,8 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev,
 	}
 
 	if (!patch_offset) {
-		BT_ERR("%s: didn't find patch for chip id %d",
-		       hdev->name, btrtl_dev->rom_version);
+		rtl_dev_err(hdev, "didn't find patch for chip id %d",
+			    btrtl_dev->rom_version);
 		return -EINVAL;
 	}
 
@@ -348,15 +347,14 @@ static int rtl_download_firmware(struct hci_dev *hdev,
 		skb = __hci_cmd_sync(hdev, 0xfc20, frag_len + 1, dl_cmd,
 				     HCI_INIT_TIMEOUT);
 		if (IS_ERR(skb)) {
-			BT_ERR("%s: download fw command failed (%ld)",
-			       hdev->name, PTR_ERR(skb));
+			rtl_dev_err(hdev, "download fw command failed (%ld)\n",
+				    PTR_ERR(skb));
 			ret = -PTR_ERR(skb);
 			goto out;
 		}
 
 		if (skb->len != sizeof(struct rtl_download_response)) {
-			BT_ERR("%s: download fw event length mismatch",
-			       hdev->name);
+			rtl_dev_err(hdev, "download fw event length mismatch\n");
 			kfree_skb(skb);
 			ret = -EIO;
 			goto out;
@@ -376,7 +374,7 @@ static int rtl_load_file(struct hci_dev *hdev, const char *name, u8 **buff)
 	const struct firmware *fw;
 	int ret;
 
-	bt_dev_info(hdev, "rtl: loading %s", name);
+	rtl_dev_info(hdev, "rtl: loading %s\n", name);
 	ret = request_firmware(&fw, name, &hdev->dev);
 	if (ret < 0)
 		return ret;
@@ -400,7 +398,7 @@ static int btrtl_setup_rtl8723a(struct hci_dev *hdev,
 	 * (which is only for RTL8723B and newer).
 	 */
 	if (!memcmp(btrtl_dev->fw_data, RTL_EPATCH_SIGNATURE, 8)) {
-		BT_ERR("%s: unexpected EPATCH signature!", hdev->name);
+		rtl_dev_err(hdev, "unexpected EPATCH signature!\n");
 		return -EINVAL;
 	}
 
@@ -451,14 +449,13 @@ static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev)
 	skb = __hci_cmd_sync(hdev, HCI_OP_READ_LOCAL_VERSION, 0, NULL,
 			     HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
-		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION failed (%ld)",
-		       hdev->name, PTR_ERR(skb));
+		rtl_dev_err(hdev, "HCI_OP_READ_LOCAL_VERSION failed (%ld)\n",
+			    PTR_ERR(skb));
 		return skb;
 	}
 
 	if (skb->len != sizeof(struct hci_rp_read_local_version)) {
-		BT_ERR("%s: HCI_OP_READ_LOCAL_VERSION event length mismatch",
-		       hdev->name);
+		rtl_dev_err(hdev, "HCI_OP_READ_LOCAL_VERSION event length mismatch\n");
 		kfree_skb(skb);
 		return ERR_PTR(-EIO);
 	}
@@ -495,10 +492,9 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
 	}
 
 	resp = (struct hci_rp_read_local_version *)skb->data;
-	bt_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x "
-		    "lmp_ver=%02x lmp_subver=%04x",
-		    resp->hci_ver, resp->hci_rev,
-		    resp->lmp_ver, resp->lmp_subver);
+	rtl_dev_info(hdev, "rtl: examining hci_ver=%02x hci_rev=%04x lmp_ver=%02x lmp_subver=%04x\n",
+		     resp->hci_ver, resp->hci_rev,
+		     resp->lmp_ver, resp->lmp_subver);
 
 	hci_rev = le16_to_cpu(resp->hci_rev);
 	lmp_subver = le16_to_cpu(resp->lmp_subver);
@@ -568,7 +564,7 @@ int btrtl_download_firmware(struct hci_dev *hdev,
 	case RTL_ROM_LMP_8822B:
 		return btrtl_setup_rtl8723b(hdev, btrtl_dev);
 	default:
-		bt_dev_info(hdev, "rtl: assuming no firmware upload needed");
+		rtl_dev_info(hdev, "rtl: assuming no firmware upload needed\n");
 		return 0;
 	}
 }
-- 
cgit v1.2.3


From b85b0ee1001b112a3dd4c4718d80b0c40551a2bb Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 2 Aug 2018 16:57:15 +0200
Subject: Bluetooth: btrtl: add support for retrieving the UART settings

The UART settings are embedded in the config blob. This has to be parsed
to successfully initialize the Bluetooth part of the RTL8723BS (which is
an SDIO chip, but the Bluetooth part is connected via UART).

The Realtek "rtl8723bs_bt" and "rtl8723ds_bt" userspace Bluetooth UART
initialization tools (rtk_hciattach) use the following sequence:
- send H5 sync pattern (already supported by hci_h5)
- get LMP version (already supported by btrtl)
- get ROM version (already supported by btrtl)
- load the firmware and config for the current chipset (already
  supported by btrtl)
- read UART settings from the config blob (part of this patch)
- send UART settings via a vendor command to the device (which changes
  the baudrate of the device and enables or disables flow control
  depending on the config)
- change the baudrate and flow control settings on the host
- send the firmware and config blob to the device (already supported by
  btrtl)

Sending the last firmware and config blob download command
(rtl_download_cmd) fails if the UART settings are not updated
beforehand. This is presumably because the device applies the config
right after the firmware and config blob download - which means that at
this point the host is using different UART settings than the device
(which will obviously result in non-working communication).

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Jeremy Cline <jeremy@jcline.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btrtl.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++
 drivers/bluetooth/btrtl.h |  25 +++++++++++
 2 files changed, 134 insertions(+)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 0500b598691e..75d6acb3ee82 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -34,6 +34,7 @@
 #define RTL_ROM_LMP_8821A	0x8821
 #define RTL_ROM_LMP_8761A	0x8761
 #define RTL_ROM_LMP_8822B	0x8822
+#define RTL_CONFIG_MAGIC	0x8723ab55
 
 #define IC_MATCH_FL_LMPSUBV	(1 << 0)
 #define IC_MATCH_FL_HCIREV	(1 << 1)
@@ -587,6 +588,114 @@ int btrtl_setup_realtek(struct hci_dev *hdev)
 }
 EXPORT_SYMBOL_GPL(btrtl_setup_realtek);
 
+static unsigned int btrtl_convert_baudrate(u32 device_baudrate)
+{
+	switch (device_baudrate) {
+	case 0x0252a00a:
+		return 230400;
+
+	case 0x05f75004:
+		return 921600;
+
+	case 0x00005004:
+		return 1000000;
+
+	case 0x04928002:
+	case 0x01128002:
+		return 1500000;
+
+	case 0x00005002:
+		return 2000000;
+
+	case 0x0000b001:
+		return 2500000;
+
+	case 0x04928001:
+		return 3000000;
+
+	case 0x052a6001:
+		return 3500000;
+
+	case 0x00005001:
+		return 4000000;
+
+	case 0x0252c014:
+	default:
+		return 115200;
+	}
+}
+
+int btrtl_get_uart_settings(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev,
+			    unsigned int *controller_baudrate,
+			    u32 *device_baudrate, bool *flow_control)
+{
+	struct rtl_vendor_config *config;
+	struct rtl_vendor_config_entry *entry;
+	int i, total_data_len;
+	bool found = false;
+
+	total_data_len = btrtl_dev->cfg_len - sizeof(*config);
+	if (total_data_len <= 0) {
+		rtl_dev_warn(hdev, "no config loaded\n");
+		return -EINVAL;
+	}
+
+	config = (struct rtl_vendor_config *)btrtl_dev->cfg_data;
+	if (le32_to_cpu(config->signature) != RTL_CONFIG_MAGIC) {
+		rtl_dev_err(hdev, "invalid config magic\n");
+		return -EINVAL;
+	}
+
+	if (total_data_len < le16_to_cpu(config->total_len)) {
+		rtl_dev_err(hdev, "config is too short\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < total_data_len; ) {
+		entry = ((void *)config->entry) + i;
+
+		switch (le16_to_cpu(entry->offset)) {
+		case 0xc:
+			if (entry->len < sizeof(*device_baudrate)) {
+				rtl_dev_err(hdev, "invalid UART config entry\n");
+				return -EINVAL;
+			}
+
+			*device_baudrate = get_unaligned_le32(entry->data);
+			*controller_baudrate = btrtl_convert_baudrate(
+							*device_baudrate);
+
+			if (entry->len >= 13)
+				*flow_control = !!(entry->data[12] & BIT(2));
+			else
+				*flow_control = false;
+
+			found = true;
+			break;
+
+		default:
+			rtl_dev_dbg(hdev, "skipping config entry 0x%x (len %u)\n",
+				   le16_to_cpu(entry->offset), entry->len);
+			break;
+		};
+
+		i += sizeof(*entry) + entry->len;
+	}
+
+	if (!found) {
+		rtl_dev_err(hdev, "no UART config entry found\n");
+		return -ENOENT;
+	}
+
+	rtl_dev_dbg(hdev, "device baudrate = 0x%08x\n", *device_baudrate);
+	rtl_dev_dbg(hdev, "controller baudrate = %u\n", *controller_baudrate);
+	rtl_dev_dbg(hdev, "flow control %d\n", *flow_control);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(btrtl_get_uart_settings);
+
 MODULE_AUTHOR("Daniel Drake <drake@endlessm.com>");
 MODULE_DESCRIPTION("Bluetooth support for Realtek devices ver " VERSION);
 MODULE_VERSION(VERSION);
diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h
index e41974f8af40..9249ad1e9a1d 100644
--- a/drivers/bluetooth/btrtl.h
+++ b/drivers/bluetooth/btrtl.h
@@ -45,6 +45,18 @@ struct rtl_epatch_header {
 	__le16 num_patches;
 } __packed;
 
+struct rtl_vendor_config_entry {
+	__le16 offset;
+	__u8 len;
+	__u8 data[0];
+} __packed;
+
+struct rtl_vendor_config {
+	__le32 signature;
+	__le16 total_len;
+	struct rtl_vendor_config_entry entry[0];
+} __packed;
+
 #if IS_ENABLED(CONFIG_BT_RTL)
 
 struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev);
@@ -52,6 +64,10 @@ void btrtl_free(struct btrtl_device_info *btrtl_dev);
 int btrtl_download_firmware(struct hci_dev *hdev,
 			    struct btrtl_device_info *btrtl_dev);
 int btrtl_setup_realtek(struct hci_dev *hdev);
+int btrtl_get_uart_settings(struct hci_dev *hdev,
+			    struct btrtl_device_info *btrtl_dev,
+			    unsigned int *controller_baudrate,
+			    u32 *device_baudrate, bool *flow_control);
 
 #else
 
@@ -75,4 +91,13 @@ static inline int btrtl_setup_realtek(struct hci_dev *hdev)
 	return -EOPNOTSUPP;
 }
 
+static inline int btrtl_get_uart_settings(struct hci_dev *hdev,
+					  struct btrtl_device_info *btrtl_dev,
+					  unsigned int *controller_baudrate,
+					  u32 *device_baudrate,
+					  bool *flow_control)
+{
+	return -ENOENT;
+}
+
 #endif
-- 
cgit v1.2.3


From c50903e3ee1b55d0d8a43eebed0c159e91986496 Mon Sep 17 00:00:00 2001
From: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Date: Thu, 2 Aug 2018 16:57:16 +0200
Subject: Bluetooth: btrtl: add support for the RTL8723BS and RTL8723DS chips

The Realtek RTL8723BS and RTL8723DS chipsets are SDIO wifi chips. They
also contain a Bluetooth module which is connected via UART to the host.

Realtek's userspace initialization tool (rtk_hciattach) differentiates
these two via the HCI version and revision returned by the
HCI_OP_READ_LOCAL_VERSION command.
Additionally we apply these checks only the for UART devices. Everything
else is assumed to be a "RTL8723B" which was originally supported by the
driver (communicating via USB).

Signed-off-by: Martin Blumenstingl <martin.blumenstingl@googlemail.com>
Signed-off-by: Jeremy Cline <jeremy@jcline.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btrtl.c | 51 +++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 47 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index 75d6acb3ee82..fa9fd60e93aa 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -38,6 +38,8 @@
 
 #define IC_MATCH_FL_LMPSUBV	(1 << 0)
 #define IC_MATCH_FL_HCIREV	(1 << 1)
+#define IC_MATCH_FL_HCIVER	(1 << 2)
+#define IC_MATCH_FL_HCIBUS	(1 << 3)
 #define IC_INFO(lmps, hcir) \
 	.match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV, \
 	.lmp_subver = (lmps), \
@@ -47,6 +49,8 @@ struct id_table {
 	__u16 match_flags;
 	__u16 lmp_subver;
 	__u16 hci_rev;
+	__u8 hci_ver;
+	__u8 hci_bus;
 	bool config_needed;
 	bool has_rom_version;
 	char *fw_name;
@@ -75,6 +79,18 @@ static const struct id_table ic_id_table[] = {
 	  .fw_name = "rtl_bt/rtl8723a_fw.bin",
 	  .cfg_name = NULL },
 
+	/* 8723BS */
+	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV |
+			 IC_MATCH_FL_HCIVER | IC_MATCH_FL_HCIBUS,
+	  .lmp_subver = RTL_ROM_LMP_8723B,
+	  .hci_rev = 0xb,
+	  .hci_ver = 6,
+	  .hci_bus = HCI_UART,
+	  .config_needed = true,
+	  .has_rom_version = true,
+	  .fw_name  = "rtl_bt/rtl8723bs_fw.bin",
+	  .cfg_name = "rtl_bt/rtl8723bs_config.bin" },
+
 	/* 8723B */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb),
 	  .config_needed = false,
@@ -89,6 +105,18 @@ static const struct id_table ic_id_table[] = {
 	  .fw_name  = "rtl_bt/rtl8723d_fw.bin",
 	  .cfg_name = "rtl_bt/rtl8723d_config.bin" },
 
+	/* 8723DS */
+	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV |
+			 IC_MATCH_FL_HCIVER | IC_MATCH_FL_HCIBUS,
+	  .lmp_subver = RTL_ROM_LMP_8723B,
+	  .hci_rev = 0xd,
+	  .hci_ver = 8,
+	  .hci_bus = HCI_UART,
+	  .config_needed = true,
+	  .has_rom_version = true,
+	  .fw_name  = "rtl_bt/rtl8723ds_fw.bin",
+	  .cfg_name = "rtl_bt/rtl8723ds_config.bin" },
+
 	/* 8821A */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xa),
 	  .config_needed = false,
@@ -118,7 +146,8 @@ static const struct id_table ic_id_table[] = {
 	  .cfg_name = "rtl_bt/rtl8822b_config.bin" },
 	};
 
-static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev)
+static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev,
+					     u8 hci_ver, u8 hci_bus)
 {
 	int i;
 
@@ -129,6 +158,12 @@ static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev)
 		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIREV) &&
 		    (ic_id_table[i].hci_rev != hci_rev))
 			continue;
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIVER) &&
+		    (ic_id_table[i].hci_ver != hci_ver))
+			continue;
+		if ((ic_id_table[i].match_flags & IC_MATCH_FL_HCIBUS) &&
+		    (ic_id_table[i].hci_bus != hci_bus))
+			continue;
 
 		break;
 	}
@@ -478,6 +513,7 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *resp;
 	u16 hci_rev, lmp_subver;
+	u8 hci_ver;
 	int ret;
 
 	btrtl_dev = kzalloc(sizeof(*btrtl_dev), GFP_KERNEL);
@@ -497,14 +533,17 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
 		     resp->hci_ver, resp->hci_rev,
 		     resp->lmp_ver, resp->lmp_subver);
 
+	hci_ver = resp->hci_ver;
 	hci_rev = le16_to_cpu(resp->hci_rev);
 	lmp_subver = le16_to_cpu(resp->lmp_subver);
 	kfree_skb(skb);
 
-	btrtl_dev->ic_info = btrtl_match_ic(lmp_subver, hci_rev);
+	btrtl_dev->ic_info = btrtl_match_ic(lmp_subver, hci_rev, hci_ver,
+					    hdev->bus);
+
 	if (!btrtl_dev->ic_info) {
-		rtl_dev_err(hdev, "unknown IC info, lmp subver %04x, hci rev %04x\n",
-			    lmp_subver, hci_rev);
+		rtl_dev_err(hdev, "rtl: unknown IC info, lmp subver %04x, hci rev %04x, hci ver %04x",
+			    lmp_subver, hci_rev, hci_ver);
 		ret = -EINVAL;
 		goto err_free;
 	}
@@ -703,6 +742,10 @@ MODULE_LICENSE("GPL");
 MODULE_FIRMWARE("rtl_bt/rtl8723a_fw.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8723b_fw.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8723b_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723bs_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723bs_config.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723ds_fw.bin");
+MODULE_FIRMWARE("rtl_bt/rtl8723ds_config.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8761a_fw.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8761a_config.bin");
 MODULE_FIRMWARE("rtl_bt/rtl8821a_fw.bin");
-- 
cgit v1.2.3


From 1cc194caaffbe07b8e08d464d8c309bc8e824618 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 2 Aug 2018 16:57:17 +0200
Subject: Bluetooth: btrtl: Add support for a config filename postfix

The contents of the rtl_bt/rtlXXXX_config.bin file may be board specific
allow the caller of btrtl_initialize to specify a postfix identifying
the board, which if specified will make btrtl_initialize look for
rtl_bt/rtlXXXX_config-<postfix>.bin instead.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btrtl.c | 32 ++++++++++++++++++++------------
 drivers/bluetooth/btrtl.h |  6 ++++--
 2 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index fa9fd60e93aa..7f9ea8e4c1b2 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -89,21 +89,21 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723bs_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723bs_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8723bs_config" },
 
 	/* 8723B */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xb),
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723b_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723b_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8723b_config" },
 
 	/* 8723D */
 	{ IC_INFO(RTL_ROM_LMP_8723B, 0xd),
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723d_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723d_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8723d_config" },
 
 	/* 8723DS */
 	{ .match_flags = IC_MATCH_FL_LMPSUBV | IC_MATCH_FL_HCIREV |
@@ -115,35 +115,35 @@ static const struct id_table ic_id_table[] = {
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8723ds_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8723ds_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8723ds_config" },
 
 	/* 8821A */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xa),
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8821a_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8821a_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8821a_config" },
 
 	/* 8821C */
 	{ IC_INFO(RTL_ROM_LMP_8821A, 0xc),
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8821c_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8821c_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8821c_config" },
 
 	/* 8761A */
 	{ IC_MATCH_FL_LMPSUBV, RTL_ROM_LMP_8761A, 0x0,
 	  .config_needed = false,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8761a_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8761a_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8761a_config" },
 
 	/* 8822B */
 	{ IC_INFO(RTL_ROM_LMP_8822B, 0xb),
 	  .config_needed = true,
 	  .has_rom_version = true,
 	  .fw_name  = "rtl_bt/rtl8822b_fw.bin",
-	  .cfg_name = "rtl_bt/rtl8822b_config.bin" },
+	  .cfg_name = "rtl_bt/rtl8822b_config" },
 	};
 
 static const struct id_table *btrtl_match_ic(u16 lmp_subver, u16 hci_rev,
@@ -507,11 +507,13 @@ void btrtl_free(struct btrtl_device_info *btrtl_dev)
 }
 EXPORT_SYMBOL_GPL(btrtl_free);
 
-struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
+struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
+					   const char *postfix)
 {
 	struct btrtl_device_info *btrtl_dev;
 	struct sk_buff *skb;
 	struct hci_rp_read_local_version *resp;
+	char cfg_name[40];
 	u16 hci_rev, lmp_subver;
 	u8 hci_ver;
 	int ret;
@@ -564,8 +566,14 @@ struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
 	}
 
 	if (btrtl_dev->ic_info->cfg_name) {
-		btrtl_dev->cfg_len = rtl_load_file(hdev,
-						   btrtl_dev->ic_info->cfg_name,
+		if (postfix) {
+			snprintf(cfg_name, sizeof(cfg_name), "%s-%s.bin",
+				 btrtl_dev->ic_info->cfg_name, postfix);
+		} else {
+			snprintf(cfg_name, sizeof(cfg_name), "%s.bin",
+				 btrtl_dev->ic_info->cfg_name);
+		}
+		btrtl_dev->cfg_len = rtl_load_file(hdev, cfg_name,
 						   &btrtl_dev->cfg_data);
 		if (btrtl_dev->ic_info->config_needed &&
 		    btrtl_dev->cfg_len <= 0) {
@@ -615,7 +623,7 @@ int btrtl_setup_realtek(struct hci_dev *hdev)
 	struct btrtl_device_info *btrtl_dev;
 	int ret;
 
-	btrtl_dev = btrtl_initialize(hdev);
+	btrtl_dev = btrtl_initialize(hdev, NULL);
 	if (IS_ERR(btrtl_dev))
 		return PTR_ERR(btrtl_dev);
 
diff --git a/drivers/bluetooth/btrtl.h b/drivers/bluetooth/btrtl.h
index 9249ad1e9a1d..f5e36f3993a8 100644
--- a/drivers/bluetooth/btrtl.h
+++ b/drivers/bluetooth/btrtl.h
@@ -59,7 +59,8 @@ struct rtl_vendor_config {
 
 #if IS_ENABLED(CONFIG_BT_RTL)
 
-struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev);
+struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
+					   const char *postfix);
 void btrtl_free(struct btrtl_device_info *btrtl_dev);
 int btrtl_download_firmware(struct hci_dev *hdev,
 			    struct btrtl_device_info *btrtl_dev);
@@ -71,7 +72,8 @@ int btrtl_get_uart_settings(struct hci_dev *hdev,
 
 #else
 
-static inline struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev)
+static inline struct btrtl_device_info *btrtl_initialize(struct hci_dev *hdev,
+							 const char *postfix)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-- 
cgit v1.2.3


From ce945552fde4a09f0bd4c0a33b8694b8515e2bd9 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 2 Aug 2018 16:57:18 +0200
Subject: Bluetooth: hci_h5: Add support for serdev enumerated devices

Add basic support for serdev enumerated devices, note sine this does
not (yet) declare any of / ACPI ids to bind to atm this is a nop.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_h5.c | 52 ++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 48 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 6a8d0d06aba7..672f63623bf7 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -23,6 +23,7 @@
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
+#include <linux/serdev.h>
 #include <linux/skbuff.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -65,6 +66,9 @@ enum {
 };
 
 struct h5 {
+	/* Must be the first member, hci_serdev.c expects this. */
+	struct hci_uart		serdev_hu;
+
 	struct sk_buff_head	unack;		/* Unack'ed packets queue */
 	struct sk_buff_head	rel;		/* Reliable packets queue */
 	struct sk_buff_head	unrel;		/* Unreliable packets queue */
@@ -193,9 +197,13 @@ static int h5_open(struct hci_uart *hu)
 
 	BT_DBG("hu %p", hu);
 
-	h5 = kzalloc(sizeof(*h5), GFP_KERNEL);
-	if (!h5)
-		return -ENOMEM;
+	if (hu->serdev) {
+		h5 = serdev_device_get_drvdata(hu->serdev);
+	} else {
+		h5 = kzalloc(sizeof(*h5), GFP_KERNEL);
+		if (!h5)
+			return -ENOMEM;
+	}
 
 	hu->priv = h5;
 	h5->hu = hu;
@@ -229,7 +237,8 @@ static int h5_close(struct hci_uart *hu)
 	skb_queue_purge(&h5->rel);
 	skb_queue_purge(&h5->unrel);
 
-	kfree(h5);
+	if (!hu->serdev)
+		kfree(h5);
 
 	return 0;
 }
@@ -750,12 +759,47 @@ static const struct hci_uart_proto h5p = {
 	.flush		= h5_flush,
 };
 
+static int h5_serdev_probe(struct serdev_device *serdev)
+{
+	struct device *dev = &serdev->dev;
+	struct h5 *h5;
+
+	h5 = devm_kzalloc(dev, sizeof(*h5), GFP_KERNEL);
+	if (!h5)
+		return -ENOMEM;
+
+	set_bit(HCI_UART_RESET_ON_INIT, &h5->serdev_hu.flags);
+
+	h5->hu = &h5->serdev_hu;
+	h5->serdev_hu.serdev = serdev;
+	serdev_device_set_drvdata(serdev, h5);
+
+	return hci_uart_register_device(&h5->serdev_hu, &h5p);
+}
+
+static void h5_serdev_remove(struct serdev_device *serdev)
+{
+	struct h5 *h5 = serdev_device_get_drvdata(serdev);
+
+	hci_uart_unregister_device(&h5->serdev_hu);
+}
+
+static struct serdev_device_driver h5_serdev_driver = {
+	.probe = h5_serdev_probe,
+	.remove = h5_serdev_remove,
+	.driver = {
+		.name = "hci_uart_h5",
+	},
+};
+
 int __init h5_init(void)
 {
+	serdev_device_driver_register(&h5_serdev_driver);
 	return hci_uart_register_proto(&h5p);
 }
 
 int __exit h5_deinit(void)
 {
+	serdev_device_driver_unregister(&h5_serdev_driver);
 	return hci_uart_unregister_proto(&h5p);
 }
-- 
cgit v1.2.3


From 4eb3cbc4c4dbd3185c9e7595e38ed01a87bba80f Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jeremy@jcline.org>
Date: Thu, 2 Aug 2018 16:57:19 +0200
Subject: Bluetooth: hci_h5: Add vendor setup, open, and close callbacks

Allow vendor-specific setup, open, and close functions to be defined.

Signed-off-by: Jeremy Cline <jeremy@jcline.org>
[hdegoede@redhat.com: Port from bt3wire.c to hci_h5.c, drop dt support]
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_h5.c | 40 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 39 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 672f63623bf7..b3f762291e7f 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -21,8 +21,10 @@
  *
  */
 
-#include <linux/kernel.h>
+#include <linux/acpi.h>
 #include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/mod_devicetable.h>
 #include <linux/serdev.h>
 #include <linux/skbuff.h>
 
@@ -99,6 +101,15 @@ struct h5 {
 		H5_SLEEPING,
 		H5_WAKING_UP,
 	} sleep;
+
+	const struct h5_vnd *vnd;
+	const char *id;
+};
+
+struct h5_vnd {
+	int (*setup)(struct h5 *h5);
+	void (*open)(struct h5 *h5);
+	void (*close)(struct h5 *h5);
 };
 
 static void h5_reset_rx(struct h5 *h5);
@@ -218,6 +229,9 @@ static int h5_open(struct hci_uart *hu)
 
 	h5->tx_win = H5_TX_WIN_MAX;
 
+	if (h5->vnd && h5->vnd->open)
+		h5->vnd->open(h5);
+
 	set_bit(HCI_UART_INIT_PENDING, &hu->hdev_flags);
 
 	/* Send initial sync request */
@@ -237,12 +251,25 @@ static int h5_close(struct hci_uart *hu)
 	skb_queue_purge(&h5->rel);
 	skb_queue_purge(&h5->unrel);
 
+	if (h5->vnd && h5->vnd->close)
+		h5->vnd->close(h5);
+
 	if (!hu->serdev)
 		kfree(h5);
 
 	return 0;
 }
 
+static int h5_setup(struct hci_uart *hu)
+{
+	struct h5 *h5 = hu->priv;
+
+	if (h5->vnd && h5->vnd->setup)
+		return h5->vnd->setup(h5);
+
+	return 0;
+}
+
 static void h5_pkt_cull(struct h5 *h5)
 {
 	struct sk_buff *skb, *tmp;
@@ -753,6 +780,7 @@ static const struct hci_uart_proto h5p = {
 	.name		= "Three-wire (H5)",
 	.open		= h5_open,
 	.close		= h5_close,
+	.setup		= h5_setup,
 	.recv		= h5_recv,
 	.enqueue	= h5_enqueue,
 	.dequeue	= h5_dequeue,
@@ -761,6 +789,7 @@ static const struct hci_uart_proto h5p = {
 
 static int h5_serdev_probe(struct serdev_device *serdev)
 {
+	const struct acpi_device_id *match;
 	struct device *dev = &serdev->dev;
 	struct h5 *h5;
 
@@ -774,6 +803,15 @@ static int h5_serdev_probe(struct serdev_device *serdev)
 	h5->serdev_hu.serdev = serdev;
 	serdev_device_set_drvdata(serdev, h5);
 
+	if (has_acpi_companion(dev)) {
+		match = acpi_match_device(dev->driver->acpi_match_table, dev);
+		if (!match)
+			return -ENODEV;
+
+		h5->vnd = (const struct h5_vnd *)match->driver_data;
+		h5->id  = (char *)match->id;
+	}
+
 	return hci_uart_register_device(&h5->serdev_hu, &h5p);
 }
 
-- 
cgit v1.2.3


From b825d7c4052643a9b8a10d1c83213394f795c806 Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jeremy@jcline.org>
Date: Thu, 2 Aug 2018 16:57:20 +0200
Subject: Bluetooth: hci_h5: Add support for the RTL8723BS

Implement support for the RTL8723BS chip.

Signed-off-by: Jeremy Cline <jeremy@jcline.org>
[hdegoede@redhat.com: Port from bt3wire.c to hci_h5.c, drop broken GPIO code]
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_h5.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 69 insertions(+)

diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index b3f762291e7f..3513dad43f3c 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -31,6 +31,7 @@
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
 
+#include "btrtl.h"
 #include "hci_uart.h"
 
 #define HCI_3WIRE_ACK_PKT	0
@@ -822,11 +823,79 @@ static void h5_serdev_remove(struct serdev_device *serdev)
 	hci_uart_unregister_device(&h5->serdev_hu);
 }
 
+static int h5_btrtl_setup(struct h5 *h5)
+{
+	struct btrtl_device_info *btrtl_dev;
+	struct sk_buff *skb;
+	__le32 baudrate_data;
+	u32 device_baudrate;
+	unsigned int controller_baudrate;
+	bool flow_control;
+	int err;
+
+	btrtl_dev = btrtl_initialize(h5->hu->hdev, h5->id);
+	if (IS_ERR(btrtl_dev))
+		return PTR_ERR(btrtl_dev);
+
+	err = btrtl_get_uart_settings(h5->hu->hdev, btrtl_dev,
+				      &controller_baudrate, &device_baudrate,
+				      &flow_control);
+	if (err)
+		goto out_free;
+
+	baudrate_data = cpu_to_le32(device_baudrate);
+	skb = __hci_cmd_sync(h5->hu->hdev, 0xfc17, sizeof(baudrate_data),
+			     &baudrate_data, HCI_INIT_TIMEOUT);
+	if (IS_ERR(skb)) {
+		rtl_dev_err(h5->hu->hdev, "set baud rate command failed\n");
+		err = PTR_ERR(skb);
+		goto out_free;
+	} else {
+		kfree_skb(skb);
+	}
+	/* Give the device some time to set up the new baudrate. */
+	usleep_range(10000, 20000);
+
+	serdev_device_set_baudrate(h5->hu->serdev, controller_baudrate);
+	serdev_device_set_flow_control(h5->hu->serdev, flow_control);
+
+	err = btrtl_download_firmware(h5->hu->hdev, btrtl_dev);
+	/* Give the device some time before the hci-core sends it a reset */
+	usleep_range(10000, 20000);
+
+out_free:
+	btrtl_free(btrtl_dev);
+
+	return err;
+}
+
+static void h5_btrtl_open(struct h5 *h5)
+{
+	/* Devices always start with these fixed parameters */
+	serdev_device_set_flow_control(h5->hu->serdev, false);
+	serdev_device_set_parity(h5->hu->serdev, SERDEV_PARITY_EVEN);
+	serdev_device_set_baudrate(h5->hu->serdev, 115200);
+}
+
+static struct h5_vnd rtl_vnd = {
+	.setup		= h5_btrtl_setup,
+	.open		= h5_btrtl_open,
+};
+
+#ifdef CONFIG_ACPI
+static const struct acpi_device_id h5_acpi_match[] = {
+	{ "OBDA8723", (kernel_ulong_t)&rtl_vnd },
+	{ },
+};
+MODULE_DEVICE_TABLE(acpi, h5_acpi_match);
+#endif
+
 static struct serdev_device_driver h5_serdev_driver = {
 	.probe = h5_serdev_probe,
 	.remove = h5_serdev_remove,
 	.driver = {
 		.name = "hci_uart_h5",
+		.acpi_match_table = ACPI_PTR(h5_acpi_match),
 	},
 };
 
-- 
cgit v1.2.3


From 4c79148970fbb3cfe078d4ad31a2c7a7722196a8 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 2 Aug 2018 16:57:21 +0200
Subject: Bluetooth: hci_h5: Add support for enable and device-wake GPIOs

Add support for the enable and device-wake GPIOs used on ACPI enumerated
RTL8723BS devices.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_h5.c | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 3513dad43f3c..63c0dcbc4914 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -23,6 +23,7 @@
 
 #include <linux/acpi.h>
 #include <linux/errno.h>
+#include <linux/gpio/consumer.h>
 #include <linux/kernel.h>
 #include <linux/mod_devicetable.h>
 #include <linux/serdev.h>
@@ -105,12 +106,16 @@ struct h5 {
 
 	const struct h5_vnd *vnd;
 	const char *id;
+
+	struct gpio_desc *enable_gpio;
+	struct gpio_desc *device_wake_gpio;
 };
 
 struct h5_vnd {
 	int (*setup)(struct h5 *h5);
 	void (*open)(struct h5 *h5);
 	void (*close)(struct h5 *h5);
+	const struct acpi_gpio_mapping *acpi_gpio_map;
 };
 
 static void h5_reset_rx(struct h5 *h5);
@@ -811,8 +816,21 @@ static int h5_serdev_probe(struct serdev_device *serdev)
 
 		h5->vnd = (const struct h5_vnd *)match->driver_data;
 		h5->id  = (char *)match->id;
+
+		if (h5->vnd->acpi_gpio_map)
+			devm_acpi_dev_add_driver_gpios(dev,
+						       h5->vnd->acpi_gpio_map);
 	}
 
+	h5->enable_gpio = devm_gpiod_get_optional(dev, "enable", GPIOD_OUT_LOW);
+	if (IS_ERR(h5->enable_gpio))
+		return PTR_ERR(h5->enable_gpio);
+
+	h5->device_wake_gpio = devm_gpiod_get_optional(dev, "device-wake",
+						       GPIOD_OUT_LOW);
+	if (IS_ERR(h5->device_wake_gpio))
+		return PTR_ERR(h5->device_wake_gpio);
+
 	return hci_uart_register_device(&h5->serdev_hu, &h5p);
 }
 
@@ -875,11 +893,34 @@ static void h5_btrtl_open(struct h5 *h5)
 	serdev_device_set_flow_control(h5->hu->serdev, false);
 	serdev_device_set_parity(h5->hu->serdev, SERDEV_PARITY_EVEN);
 	serdev_device_set_baudrate(h5->hu->serdev, 115200);
+
+	/* The controller needs up to 500ms to wakeup */
+	gpiod_set_value_cansleep(h5->enable_gpio, 1);
+	gpiod_set_value_cansleep(h5->device_wake_gpio, 1);
+	msleep(500);
 }
 
+static void h5_btrtl_close(struct h5 *h5)
+{
+	gpiod_set_value_cansleep(h5->device_wake_gpio, 0);
+	gpiod_set_value_cansleep(h5->enable_gpio, 0);
+}
+
+static const struct acpi_gpio_params btrtl_device_wake_gpios = { 0, 0, false };
+static const struct acpi_gpio_params btrtl_enable_gpios = { 1, 0, false };
+static const struct acpi_gpio_params btrtl_host_wake_gpios = { 2, 0, false };
+static const struct acpi_gpio_mapping acpi_btrtl_gpios[] = {
+	{ "device-wake-gpios", &btrtl_device_wake_gpios, 1 },
+	{ "enable-gpios", &btrtl_enable_gpios, 1 },
+	{ "host-wake-gpios", &btrtl_host_wake_gpios, 1 },
+	{},
+};
+
 static struct h5_vnd rtl_vnd = {
 	.setup		= h5_btrtl_setup,
 	.open		= h5_btrtl_open,
+	.close		= h5_btrtl_close,
+	.acpi_gpio_map	= acpi_btrtl_gpios,
 };
 
 #ifdef CONFIG_ACPI
-- 
cgit v1.2.3


From 21e2156f3c4b2ad8b780a6d02342ca0e028a8acd Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 3 Aug 2018 10:57:52 +0100
Subject: gfs2: Get rid of gfs2_ea_strlen

Function gfs2_ea_strlen is only called from ea_list_i, so inline it
there.  Remove the duplicate switch statement and the creative use of
memcpy to set a null byte.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Andrew Price <anprice@redhat.com>
Reviewed-by: Bob Peterson <rpeterso@redhat.com>
---
 fs/gfs2/xattr.c | 59 +++++++++++++++++++++------------------------------------
 1 file changed, 22 insertions(+), 37 deletions(-)

diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index f2bce1e0f6fb..38515988aaf7 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -343,60 +343,45 @@ struct ea_list {
 	unsigned int ei_size;
 };
 
-static inline unsigned int gfs2_ea_strlen(struct gfs2_ea_header *ea)
-{
-	switch (ea->ea_type) {
-	case GFS2_EATYPE_USR:
-		return 5 + ea->ea_name_len + 1;
-	case GFS2_EATYPE_SYS:
-		return 7 + ea->ea_name_len + 1;
-	case GFS2_EATYPE_SECURITY:
-		return 9 + ea->ea_name_len + 1;
-	default:
-		return 0;
-	}
-}
-
 static int ea_list_i(struct gfs2_inode *ip, struct buffer_head *bh,
 		     struct gfs2_ea_header *ea, struct gfs2_ea_header *prev,
 		     void *private)
 {
 	struct ea_list *ei = private;
 	struct gfs2_ea_request *er = ei->ei_er;
-	unsigned int ea_size = gfs2_ea_strlen(ea);
+	unsigned int ea_size;
+	char *prefix;
+	unsigned int l;
 
 	if (ea->ea_type == GFS2_EATYPE_UNUSED)
 		return 0;
 
-	if (er->er_data_len) {
-		char *prefix = NULL;
-		unsigned int l = 0;
-		char c = 0;
+	switch (ea->ea_type) {
+	case GFS2_EATYPE_USR:
+		prefix = "user.";
+		l = 5;
+		break;
+	case GFS2_EATYPE_SYS:
+		prefix = "system.";
+		l = 7;
+		break;
+	case GFS2_EATYPE_SECURITY:
+		prefix = "security.";
+		l = 9;
+		break;
+	default:
+		BUG();
+	}
 
+	ea_size = l + ea->ea_name_len + 1;
+	if (er->er_data_len) {
 		if (ei->ei_size + ea_size > er->er_data_len)
 			return -ERANGE;
 
-		switch (ea->ea_type) {
-		case GFS2_EATYPE_USR:
-			prefix = "user.";
-			l = 5;
-			break;
-		case GFS2_EATYPE_SYS:
-			prefix = "system.";
-			l = 7;
-			break;
-		case GFS2_EATYPE_SECURITY:
-			prefix = "security.";
-			l = 9;
-			break;
-		}
-
-		BUG_ON(l == 0);
-
 		memcpy(er->er_data + ei->ei_size, prefix, l);
 		memcpy(er->er_data + ei->ei_size + l, GFS2_EA2NAME(ea),
 		       ea->ea_name_len);
-		memcpy(er->er_data + ei->ei_size + ea_size - 1, &c, 1);
+		er->er_data[ei->ei_size + ea_size - 1] = 0;
 	}
 
 	ei->ei_size += ea_size;
-- 
cgit v1.2.3


From 505013555a47c8dfed11bd124d2f4ea71988c21e Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Fri, 3 Aug 2018 17:46:26 +0530
Subject: dt-bindings: net: bluetooth: Add device tree bindings for QTI chip
 wcn3990

This patch enables regulators for the Qualcomm Bluetooth wcn3990
controller.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Stephen Boyd <swboyd@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 .../devicetree/bindings/net/qualcomm-bluetooth.txt | 29 ++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt
index 0ea18a53cc29..824c0e23c544 100644
--- a/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt
+++ b/Documentation/devicetree/bindings/net/qualcomm-bluetooth.txt
@@ -10,12 +10,25 @@ device the slave device is attached to.
 Required properties:
  - compatible: should contain one of the following:
    * "qcom,qca6174-bt"
+   * "qcom,wcn3990-bt"
+
+Optional properties for compatible string qcom,qca6174-bt:
 
-Optional properties:
  - enable-gpios: gpio specifier used to enable chip
  - clocks: clock provided to the controller (SUSCLK_32KHZ)
 
-Example:
+Required properties for compatible string qcom,wcn3990-bt:
+
+ - vddio-supply: VDD_IO supply regulator handle.
+ - vddxo-supply: VDD_XO supply regulator handle.
+ - vddrf-supply: VDD_RF supply regulator handle.
+ - vddch0-supply: VDD_CH0 supply regulator handle.
+
+Optional properties for compatible string qcom,wcn3990-bt:
+
+ - max-speed: see Documentation/devicetree/bindings/serial/slave-device.txt
+
+Examples:
 
 serial@7570000 {
 	label = "BT-UART";
@@ -28,3 +41,15 @@ serial@7570000 {
 		clocks = <&divclk4>;
 	};
 };
+
+serial@898000 {
+	bluetooth {
+		compatible = "qcom,wcn3990-bt";
+
+		vddio-supply = <&vreg_s4a_1p8>;
+		vddxo-supply = <&vreg_l7a_1p8>;
+		vddrf-supply = <&vreg_l17a_1p3>;
+		vddch0-supply = <&vreg_l25a_3p3>;
+		max-speed = <3200000>;
+	};
+};
-- 
cgit v1.2.3


From ba493d4fbcb84bd14842c61cc077ffb5b3f7ecb1 Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Fri, 3 Aug 2018 17:46:27 +0530
Subject: Bluetooth: btqca: Rename ROME specific functions to generic functions

Some of the QCA BTSoC ROME functions, are used for different versions
or different make of BTSoC's. Instead of duplicating the same functions
for new chip, update names of the functions that are used for both
chips to keep this generic and would help in future when we would have
new BT SoC. To have generic text in logs updated from ROME to QCA where
ever possible. This avoids confusion to user, when using the future
Qualcomm Bluetooth SoC's. Updated BT_DBG, BT_ERR and BT_INFO with
bt_dev_dbg, bt_dev_err and bt_dev_info where ever applicable.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btqca.c   | 85 ++++++++++++++++++++++-----------------------
 drivers/bluetooth/btqca.h   | 10 ++++--
 drivers/bluetooth/hci_qca.c |  2 +-
 3 files changed, 51 insertions(+), 46 deletions(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 8219816c54a0..c5cf9cab438a 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -27,7 +27,7 @@
 
 #define VERSION "0.1"
 
-static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version)
+int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version)
 {
 	struct sk_buff *skb;
 	struct edl_event_hdr *edl;
@@ -35,36 +35,35 @@ static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version)
 	char cmd;
 	int err = 0;
 
-	BT_DBG("%s: ROME Patch Version Request", hdev->name);
+	bt_dev_dbg(hdev, "QCA Version Request");
 
 	cmd = EDL_PATCH_VER_REQ_CMD;
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN,
 				&cmd, HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Failed to read version of ROME (%d)", hdev->name,
-		       err);
+		bt_dev_err(hdev, "Reading QCA version information failed (%d)",
+			   err);
 		return err;
 	}
 
 	if (skb->len != sizeof(*edl) + sizeof(*ver)) {
-		BT_ERR("%s: Version size mismatch len %d", hdev->name,
-		       skb->len);
+		bt_dev_err(hdev, "QCA Version size mismatch len %d", skb->len);
 		err = -EILSEQ;
 		goto out;
 	}
 
 	edl = (struct edl_event_hdr *)(skb->data);
 	if (!edl) {
-		BT_ERR("%s: TLV with no header", hdev->name);
+		bt_dev_err(hdev, "QCA TLV with no header");
 		err = -EILSEQ;
 		goto out;
 	}
 
 	if (edl->cresp != EDL_CMD_REQ_RES_EVT ||
 	    edl->rtype != EDL_APP_VER_RES_EVT) {
-		BT_ERR("%s: Wrong packet received %d %d", hdev->name,
-		       edl->cresp, edl->rtype);
+		bt_dev_err(hdev, "QCA Wrong packet received %d %d", edl->cresp,
+			   edl->rtype);
 		err = -EIO;
 		goto out;
 	}
@@ -76,11 +75,11 @@ static int rome_patch_ver_req(struct hci_dev *hdev, u32 *rome_version)
 	BT_DBG("%s: ROM    :0x%08x", hdev->name, le16_to_cpu(ver->rome_ver));
 	BT_DBG("%s: SOC    :0x%08x", hdev->name, le32_to_cpu(ver->soc_id));
 
-	/* ROME chipset version can be decided by patch and SoC
+	/* QCA chipset version can be decided by patch and SoC
 	 * version, combination with upper 2 bytes from SoC
 	 * and lower 2 bytes from patch will be used.
 	 */
-	*rome_version = (le32_to_cpu(ver->soc_id) << 16) |
+	*soc_version = (le32_to_cpu(ver->soc_id) << 16) |
 			(le16_to_cpu(ver->rome_ver) & 0x0000ffff);
 
 out:
@@ -88,18 +87,19 @@ out:
 
 	return err;
 }
+EXPORT_SYMBOL_GPL(qca_read_soc_version);
 
-static int rome_reset(struct hci_dev *hdev)
+static int qca_send_reset(struct hci_dev *hdev)
 {
 	struct sk_buff *skb;
 	int err;
 
-	BT_DBG("%s: ROME HCI_RESET", hdev->name);
+	bt_dev_dbg(hdev, "QCA HCI_RESET");
 
 	skb = __hci_cmd_sync(hdev, HCI_OP_RESET, 0, NULL, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Reset failed (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Reset failed (%d)", err);
 		return err;
 	}
 
@@ -108,7 +108,7 @@ static int rome_reset(struct hci_dev *hdev)
 	return 0;
 }
 
-static void rome_tlv_check_data(struct rome_config *config,
+static void qca_tlv_check_data(struct rome_config *config,
 				const struct firmware *fw)
 {
 	const u8 *data;
@@ -207,7 +207,7 @@ static void rome_tlv_check_data(struct rome_config *config,
 	}
 }
 
-static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size,
+static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size,
 				 const u8 *data, enum rome_tlv_dnld_mode mode)
 {
 	struct sk_buff *skb;
@@ -228,19 +228,19 @@ static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size,
 				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Failed to send TLV segment (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to send TLV segment (%d)", err);
 		return err;
 	}
 
 	if (skb->len != sizeof(*edl) + sizeof(*tlv_resp)) {
-		BT_ERR("%s: TLV response size mismatch", hdev->name);
+		bt_dev_err(hdev, "QCA TLV response size mismatch");
 		err = -EILSEQ;
 		goto out;
 	}
 
 	edl = (struct edl_event_hdr *)(skb->data);
 	if (!edl) {
-		BT_ERR("%s: TLV with no header", hdev->name);
+		bt_dev_err(hdev, "TLV with no header");
 		err = -EILSEQ;
 		goto out;
 	}
@@ -249,8 +249,8 @@ static int rome_tlv_send_segment(struct hci_dev *hdev, int seg_size,
 
 	if (edl->cresp != EDL_CMD_REQ_RES_EVT ||
 	    edl->rtype != EDL_TVL_DNLD_RES_EVT || tlv_resp->result != 0x00) {
-		BT_ERR("%s: TLV with error stat 0x%x rtype 0x%x (0x%x)",
-		       hdev->name, edl->cresp, edl->rtype, tlv_resp->result);
+		bt_dev_err(hdev, "QCA TLV with error stat 0x%x rtype 0x%x (0x%x)",
+			   edl->cresp, edl->rtype, tlv_resp->result);
 		err = -EIO;
 	}
 
@@ -260,23 +260,23 @@ out:
 	return err;
 }
 
-static int rome_download_firmware(struct hci_dev *hdev,
+static int qca_download_firmware(struct hci_dev *hdev,
 				  struct rome_config *config)
 {
 	const struct firmware *fw;
 	const u8 *segment;
 	int ret, remain, i = 0;
 
-	bt_dev_info(hdev, "ROME Downloading %s", config->fwname);
+	bt_dev_info(hdev, "QCA Downloading %s", config->fwname);
 
 	ret = request_firmware(&fw, config->fwname, &hdev->dev);
 	if (ret) {
-		BT_ERR("%s: Failed to request file: %s (%d)", hdev->name,
-		       config->fwname, ret);
+		bt_dev_err(hdev, "QCA Failed to request file: %s (%d)",
+			   config->fwname, ret);
 		return ret;
 	}
 
-	rome_tlv_check_data(config, fw);
+	qca_tlv_check_data(config, fw);
 
 	segment = fw->data;
 	remain = fw->size;
@@ -290,7 +290,7 @@ static int rome_download_firmware(struct hci_dev *hdev,
 		if (!remain || segsize < MAX_SIZE_PER_TLV_SEGMENT)
 			config->dnld_mode = ROME_SKIP_EVT_NONE;
 
-		ret = rome_tlv_send_segment(hdev, segsize, segment,
+		ret = qca_tlv_send_segment(hdev, segsize, segment,
 					    config->dnld_mode);
 		if (ret)
 			break;
@@ -317,8 +317,7 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
-		BT_ERR("%s: Change address command failed (%d)",
-		       hdev->name, err);
+		bt_dev_err(hdev, "QCA Change address command failed (%d)", err);
 		return err;
 	}
 
@@ -328,32 +327,32 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 }
 EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome);
 
-int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate)
+int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate)
 {
 	u32 rome_ver = 0;
 	struct rome_config config;
 	int err;
 
-	BT_DBG("%s: ROME setup on UART", hdev->name);
+	bt_dev_dbg(hdev, "QCA setup on UART");
 
 	config.user_baud_rate = baudrate;
 
-	/* Get ROME version information */
-	err = rome_patch_ver_req(hdev, &rome_ver);
+	/* Get QCA version information */
+	err = qca_read_soc_version(hdev, &rome_ver);
 	if (err < 0 || rome_ver == 0) {
-		BT_ERR("%s: Failed to get version 0x%x", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to get version %d", err);
 		return err;
 	}
 
-	bt_dev_info(hdev, "ROME controller version 0x%08x", rome_ver);
+	bt_dev_info(hdev, "QCA controller version 0x%08x", rome_ver);
 
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
 	snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin",
 		 rome_ver);
-	err = rome_download_firmware(hdev, &config);
+	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
-		BT_ERR("%s: Failed to download patch (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to download patch (%d)", err);
 		return err;
 	}
 
@@ -361,24 +360,24 @@ int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate)
 	config.type = TLV_TYPE_NVM;
 	snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin",
 		 rome_ver);
-	err = rome_download_firmware(hdev, &config);
+	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
-		BT_ERR("%s: Failed to download NVM (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to download NVM (%d)", err);
 		return err;
 	}
 
 	/* Perform HCI reset */
-	err = rome_reset(hdev);
+	err = qca_send_reset(hdev);
 	if (err < 0) {
-		BT_ERR("%s: Failed to run HCI_RESET (%d)", hdev->name, err);
+		bt_dev_err(hdev, "QCA Failed to run HCI_RESET (%d)", err);
 		return err;
 	}
 
-	bt_dev_info(hdev, "ROME setup on UART is completed");
+	bt_dev_info(hdev, "QCA setup on UART is completed");
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(qca_uart_setup_rome);
+EXPORT_SYMBOL_GPL(qca_uart_setup);
 
 MODULE_AUTHOR("Ben Young Tae Kim <ytkim@qca.qualcomm.com>");
 MODULE_DESCRIPTION("Bluetooth support for Qualcomm Atheros family ver " VERSION);
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index 13d77fd873b6..5c9851b11838 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -127,7 +127,8 @@ struct tlv_type_hdr {
 #if IS_ENABLED(CONFIG_BT_QCA)
 
 int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr);
-int qca_uart_setup_rome(struct hci_dev *hdev, uint8_t baudrate);
+int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate);
+int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version);
 
 #else
 
@@ -136,7 +137,12 @@ static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdad
 	return -EOPNOTSUPP;
 }
 
-static inline int qca_uart_setup_rome(struct hci_dev *hdev, int speed)
+static inline int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 8431be3a837f..59d9953011a5 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -966,7 +966,7 @@ static int qca_setup(struct hci_uart *hu)
 	}
 
 	/* Setup patch / NVM configurations */
-	ret = qca_uart_setup_rome(hdev, qca_baudrate);
+	ret = qca_uart_setup(hdev, qca_baudrate);
 	if (!ret) {
 		set_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 		qca_debugfs_init(hdev);
-- 
cgit v1.2.3


From aadebac4639d84ee51a12f2a1706fea1e4760b81 Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Fri, 3 Aug 2018 17:46:28 +0530
Subject: Bluetooth: btqca: Redefine qca_uart_setup() to generic function.

Redefinition of qca_uart_setup will help future Qualcomm Bluetooth
SoC, to use the same function instead of duplicating the function.
Added new arguments soc_type and soc_ver to the functions.

These arguments will help to decide type of firmware files
to be loaded into Bluetooth chip.
soc_type holds the Bluetooth chip connected to APPS processor.
soc_ver holds the Bluetooth chip version.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btqca.c   | 21 ++++++++-------------
 drivers/bluetooth/btqca.h   | 13 +++++++++++--
 drivers/bluetooth/hci_qca.c | 10 +++++++++-
 3 files changed, 28 insertions(+), 16 deletions(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index c5cf9cab438a..479179c54dcf 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -81,9 +81,13 @@ int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version)
 	 */
 	*soc_version = (le32_to_cpu(ver->soc_id) << 16) |
 			(le16_to_cpu(ver->rome_ver) & 0x0000ffff);
+	if (*soc_version == 0)
+		err = -EILSEQ;
 
 out:
 	kfree_skb(skb);
+	if (err)
+		bt_dev_err(hdev, "QCA Failed to get version (%d)", err);
 
 	return err;
 }
@@ -327,9 +331,9 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 }
 EXPORT_SYMBOL_GPL(qca_set_bdaddr_rome);
 
-int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate)
+int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
+		   enum qca_btsoc_type soc_type, u32 soc_ver)
 {
-	u32 rome_ver = 0;
 	struct rome_config config;
 	int err;
 
@@ -337,19 +341,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate)
 
 	config.user_baud_rate = baudrate;
 
-	/* Get QCA version information */
-	err = qca_read_soc_version(hdev, &rome_ver);
-	if (err < 0 || rome_ver == 0) {
-		bt_dev_err(hdev, "QCA Failed to get version %d", err);
-		return err;
-	}
-
-	bt_dev_info(hdev, "QCA controller version 0x%08x", rome_ver);
-
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
 	snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin",
-		 rome_ver);
+		 soc_ver);
 	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
 		bt_dev_err(hdev, "QCA Failed to download patch (%d)", err);
@@ -359,7 +354,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate)
 	/* Download NVM configuration */
 	config.type = TLV_TYPE_NVM;
 	snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin",
-		 rome_ver);
+		 soc_ver);
 	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
 		bt_dev_err(hdev, "QCA Failed to download NVM (%d)", err);
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index 5c9851b11838..a9c2779f3e07 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -124,10 +124,18 @@ struct tlv_type_hdr {
 	__u8   data[0];
 } __packed;
 
+enum qca_btsoc_type {
+	QCA_INVALID = -1,
+	QCA_AR3002,
+	QCA_ROME,
+	QCA_WCN3990
+};
+
 #if IS_ENABLED(CONFIG_BT_QCA)
 
 int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr);
-int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate);
+int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
+		   enum qca_btsoc_type soc_type, u32 soc_ver);
 int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version);
 
 #else
@@ -137,7 +145,8 @@ static inline int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdad
 	return -EOPNOTSUPP;
 }
 
-static inline int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate)
+static inline int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
+				 enum qca_btsoc_type soc_type, u32 soc_ver)
 {
 	return -EOPNOTSUPP;
 }
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 59d9953011a5..6bc8cfb982a9 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -929,6 +929,7 @@ static int qca_setup(struct hci_uart *hu)
 	struct qca_data *qca = hu->priv;
 	unsigned int speed, qca_baudrate = QCA_BAUDRATE_115200;
 	int ret;
+	int soc_ver = 0;
 
 	bt_dev_info(hdev, "ROME setup");
 
@@ -965,8 +966,15 @@ static int qca_setup(struct hci_uart *hu)
 		host_set_baudrate(hu, speed);
 	}
 
+	/* Get QCA version information */
+	ret = qca_read_soc_version(hdev, &soc_ver);
+	if (ret)
+		return ret;
+
+	bt_dev_info(hdev, "QCA controller version 0x%08x", soc_ver);
+
 	/* Setup patch / NVM configurations */
-	ret = qca_uart_setup(hdev, qca_baudrate);
+	ret = qca_uart_setup(hdev, qca_baudrate, QCA_ROME, soc_ver);
 	if (!ret) {
 		set_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 		qca_debugfs_init(hdev);
-- 
cgit v1.2.3


From 83d9c5e56687a75cd75e537f97fb35009e9ba232 Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Fri, 3 Aug 2018 17:46:29 +0530
Subject: Bluetooth: hci_qca: Add wrapper functions for setting UART speed

In function qca_setup, we set initial and operating speeds for Qualcomm
Bluetooth SoC's. This block of code is common across different
Qualcomm Bluetooth SoC's. Instead of duplicating the code, created
a wrapper function to set the speeds. So that future coming SoC's
can use these wrapper functions to set speeds.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_qca.c | 93 ++++++++++++++++++++++++++++++++++-----------
 1 file changed, 70 insertions(+), 23 deletions(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 6bc8cfb982a9..41278c5852e4 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -119,6 +119,11 @@ struct qca_data {
 	u64 votes_off;
 };
 
+enum qca_speed_type {
+	QCA_INIT_SPEED = 1,
+	QCA_OPER_SPEED
+};
+
 struct qca_serdev {
 	struct hci_uart	 serdev_hu;
 	struct gpio_desc *bt_en;
@@ -923,6 +928,61 @@ static inline void host_set_baudrate(struct hci_uart *hu, unsigned int speed)
 		hci_uart_set_baudrate(hu, speed);
 }
 
+static unsigned int qca_get_speed(struct hci_uart *hu,
+				  enum qca_speed_type speed_type)
+{
+	unsigned int speed = 0;
+
+	if (speed_type == QCA_INIT_SPEED) {
+		if (hu->init_speed)
+			speed = hu->init_speed;
+		else if (hu->proto->init_speed)
+			speed = hu->proto->init_speed;
+	} else {
+		if (hu->oper_speed)
+			speed = hu->oper_speed;
+		else if (hu->proto->oper_speed)
+			speed = hu->proto->oper_speed;
+	}
+
+	return speed;
+}
+
+static int qca_check_speeds(struct hci_uart *hu)
+{
+	if (!qca_get_speed(hu, QCA_INIT_SPEED) ||
+	    !qca_get_speed(hu, QCA_OPER_SPEED))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
+{
+	unsigned int speed, qca_baudrate;
+	int ret;
+
+	if (speed_type == QCA_INIT_SPEED) {
+		speed = qca_get_speed(hu, QCA_INIT_SPEED);
+		if (speed)
+			host_set_baudrate(hu, speed);
+	} else {
+		speed = qca_get_speed(hu, QCA_OPER_SPEED);
+		if (!speed)
+			return 0;
+
+		qca_baudrate = qca_get_baudrate_value(speed);
+		bt_dev_info(hu->hdev, "Set UART speed to %d", speed);
+		ret = qca_set_baudrate(hu->hdev, qca_baudrate);
+		if (ret)
+			return ret;
+
+		host_set_baudrate(hu, speed);
+	}
+
+	return 0;
+}
+
 static int qca_setup(struct hci_uart *hu)
 {
 	struct hci_dev *hdev = hu->hdev;
@@ -933,37 +993,24 @@ static int qca_setup(struct hci_uart *hu)
 
 	bt_dev_info(hdev, "ROME setup");
 
+	ret = qca_check_speeds(hu);
+	if (ret)
+		return ret;
+
 	/* Patch downloading has to be done without IBS mode */
 	clear_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 
 	/* Setup initial baudrate */
-	speed = 0;
-	if (hu->init_speed)
-		speed = hu->init_speed;
-	else if (hu->proto->init_speed)
-		speed = hu->proto->init_speed;
-
-	if (speed)
-		host_set_baudrate(hu, speed);
+	qca_set_speed(hu, QCA_INIT_SPEED);
 
 	/* Setup user speed if needed */
-	speed = 0;
-	if (hu->oper_speed)
-		speed = hu->oper_speed;
-	else if (hu->proto->oper_speed)
-		speed = hu->proto->oper_speed;
-
+	speed = qca_get_speed(hu, QCA_OPER_SPEED);
 	if (speed) {
-		qca_baudrate = qca_get_baudrate_value(speed);
-
-		bt_dev_info(hdev, "Set UART speed to %d", speed);
-		ret = qca_set_baudrate(hdev, qca_baudrate);
-		if (ret) {
-			bt_dev_err(hdev, "Failed to change the baud rate (%d)",
-				   ret);
+		ret = qca_set_speed(hu, QCA_OPER_SPEED);
+		if (ret)
 			return ret;
-		}
-		host_set_baudrate(hu, speed);
+
+		qca_baudrate = qca_get_baudrate_value(speed);
 	}
 
 	/* Get QCA version information */
-- 
cgit v1.2.3


From be93a497fa7fea2302e0d35ad08dbed30e5791d3 Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Fri, 3 Aug 2018 17:46:30 +0530
Subject: Bluetooth: hci_qca: Enable 3.2 Mbps operating speed.

Enable Qualcomm chips to operate at 3.2Mbps.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/hci_qca.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 41278c5852e4..29adb95f0957 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -877,6 +877,8 @@ static uint8_t qca_get_baudrate_value(int speed)
 		return QCA_BAUDRATE_2000000;
 	case 3000000:
 		return QCA_BAUDRATE_3000000;
+	case 3200000:
+		return QCA_BAUDRATE_3200000;
 	case 3500000:
 		return QCA_BAUDRATE_3500000;
 	default:
@@ -891,7 +893,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 	struct sk_buff *skb;
 	u8 cmd[] = { 0x01, 0x48, 0xFC, 0x01, 0x00 };
 
-	if (baudrate > QCA_BAUDRATE_3000000)
+	if (baudrate > QCA_BAUDRATE_3200000)
 		return -EINVAL;
 
 	cmd[4] = baudrate;
-- 
cgit v1.2.3


From 4219d4686875fdd83df3da00fda5ff0551e0a2d7 Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Fri, 3 Aug 2018 17:46:31 +0530
Subject: Bluetooth: btqca: Add wcn3990 firmware download support.

This patch enables the RAM and NV patch download for wcn3990.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btqca.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 479179c54dcf..488f5e7521dd 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -336,6 +336,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 {
 	struct rome_config config;
 	int err;
+	u8 rom_ver;
 
 	bt_dev_dbg(hdev, "QCA setup on UART");
 
@@ -343,8 +344,19 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 
 	/* Download rampatch file */
 	config.type = TLV_TYPE_PATCH;
-	snprintf(config.fwname, sizeof(config.fwname), "qca/rampatch_%08x.bin",
-		 soc_ver);
+	if (soc_type == QCA_WCN3990) {
+		/* Firmware files to download are based on ROM version.
+		 * ROM version is derived from last two bytes of soc_ver.
+		 */
+		rom_ver = ((soc_ver & 0x00000f00) >> 0x04) |
+			    (soc_ver & 0x0000000f);
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/crbtfw%02x.tlv", rom_ver);
+	} else {
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/rampatch_%08x.bin", soc_ver);
+	}
+
 	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
 		bt_dev_err(hdev, "QCA Failed to download patch (%d)", err);
@@ -353,8 +365,13 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 
 	/* Download NVM configuration */
 	config.type = TLV_TYPE_NVM;
-	snprintf(config.fwname, sizeof(config.fwname), "qca/nvm_%08x.bin",
-		 soc_ver);
+	if (soc_type == QCA_WCN3990)
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/crnv%02x.bin", rom_ver);
+	else
+		snprintf(config.fwname, sizeof(config.fwname),
+			 "qca/nvm_%08x.bin", soc_ver);
+
 	err = qca_download_firmware(hdev, &config);
 	if (err < 0) {
 		bt_dev_err(hdev, "QCA Failed to download NVM (%d)", err);
-- 
cgit v1.2.3


From fa9ad876b8e0ebd2b4367ef1580f89be64ebd5d3 Mon Sep 17 00:00:00 2001
From: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Date: Fri, 3 Aug 2018 17:46:32 +0530
Subject: Bluetooth: hci_qca: Add support for Qualcomm Bluetooth chip wcn3990

Add support to set voltage/current of various regulators
to power up/down Bluetooth chip wcn3990.

Signed-off-by: Balakrishna Godavarthi <bgodavar@codeaurora.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btqca.h   |   3 +
 drivers/bluetooth/hci_qca.c | 407 +++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 363 insertions(+), 47 deletions(-)

diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index a9c2779f3e07..0c01f375fe83 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -37,6 +37,9 @@
 #define EDL_TAG_ID_HCI			(17)
 #define EDL_TAG_ID_DEEP_SLEEP		(27)
 
+#define QCA_WCN3990_POWERON_PULSE	0xFC
+#define QCA_WCN3990_POWEROFF_PULSE	0xC0
+
 enum qca_bardrate {
 	QCA_BAUDRATE_115200 	= 0,
 	QCA_BAUDRATE_57600,
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 29adb95f0957..e182f6019f68 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -5,7 +5,7 @@
  *  protocol extension to H4.
  *
  *  Copyright (C) 2007 Texas Instruments, Inc.
- *  Copyright (c) 2010, 2012 The Linux Foundation. All rights reserved.
+ *  Copyright (c) 2010, 2012, 2018 The Linux Foundation. All rights reserved.
  *
  *  Acknowledgements:
  *  This file is based on hci_ll.c, which was...
@@ -31,9 +31,14 @@
 #include <linux/kernel.h>
 #include <linux/clk.h>
 #include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/device.h>
 #include <linux/gpio/consumer.h>
 #include <linux/mod_devicetable.h>
 #include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
 #include <linux/serdev.h>
 
 #include <net/bluetooth/bluetooth.h>
@@ -124,12 +129,46 @@ enum qca_speed_type {
 	QCA_OPER_SPEED
 };
 
+/*
+ * Voltage regulator information required for configuring the
+ * QCA Bluetooth chipset
+ */
+struct qca_vreg {
+	const char *name;
+	unsigned int min_uV;
+	unsigned int max_uV;
+	unsigned int load_uA;
+};
+
+struct qca_vreg_data {
+	enum qca_btsoc_type soc_type;
+	struct qca_vreg *vregs;
+	size_t num_vregs;
+};
+
+/*
+ * Platform data for the QCA Bluetooth power driver.
+ */
+struct qca_power {
+	struct device *dev;
+	const struct qca_vreg_data *vreg_data;
+	struct regulator_bulk_data *vreg_bulk;
+	bool vregs_on;
+};
+
 struct qca_serdev {
 	struct hci_uart	 serdev_hu;
 	struct gpio_desc *bt_en;
 	struct clk	 *susclk;
+	enum qca_btsoc_type btsoc_type;
+	struct qca_power *bt_power;
+	u32 init_speed;
+	u32 oper_speed;
 };
 
+static int qca_power_setup(struct hci_uart *hu, bool on);
+static void qca_power_shutdown(struct hci_dev *hdev);
+
 static void __serial_clock_on(struct tty_struct *tty)
 {
 	/* TODO: Some chipset requires to enable UART clock on client
@@ -407,6 +446,7 @@ static int qca_open(struct hci_uart *hu)
 {
 	struct qca_serdev *qcadev;
 	struct qca_data *qca;
+	int ret;
 
 	BT_DBG("hu %p qca_open", hu);
 
@@ -458,19 +498,32 @@ static int qca_open(struct hci_uart *hu)
 
 	hu->priv = qca;
 
-	timer_setup(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout, 0);
-	qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS;
-
-	timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0);
-	qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS;
-
 	if (hu->serdev) {
 		serdev_device_open(hu->serdev);
 
 		qcadev = serdev_device_get_drvdata(hu->serdev);
-		gpiod_set_value_cansleep(qcadev->bt_en, 1);
+		if (qcadev->btsoc_type != QCA_WCN3990) {
+			gpiod_set_value_cansleep(qcadev->bt_en, 1);
+		} else {
+			hu->init_speed = qcadev->init_speed;
+			hu->oper_speed = qcadev->oper_speed;
+			ret = qca_power_setup(hu, true);
+			if (ret) {
+				destroy_workqueue(qca->workqueue);
+				kfree_skb(qca->rx_skb);
+				hu->priv = NULL;
+				kfree(qca);
+				return ret;
+			}
+		}
 	}
 
+	timer_setup(&qca->wake_retrans_timer, hci_ibs_wake_retrans_timeout, 0);
+	qca->wake_retrans = IBS_WAKE_RETRANS_TIMEOUT_MS;
+
+	timer_setup(&qca->tx_idle_timer, hci_ibs_tx_idle_timeout, 0);
+	qca->tx_idle_delay = IBS_TX_IDLE_TIMEOUT_MS;
+
 	BT_DBG("HCI_UART_QCA open, tx_idle_delay=%u, wake_retrans=%u",
 	       qca->tx_idle_delay, qca->wake_retrans);
 
@@ -554,10 +607,13 @@ static int qca_close(struct hci_uart *hu)
 	qca->hu = NULL;
 
 	if (hu->serdev) {
-		serdev_device_close(hu->serdev);
-
 		qcadev = serdev_device_get_drvdata(hu->serdev);
-		gpiod_set_value_cansleep(qcadev->bt_en, 0);
+		if (qcadev->btsoc_type == QCA_WCN3990)
+			qca_power_shutdown(hu->hdev);
+		else
+			gpiod_set_value_cansleep(qcadev->bt_en, 0);
+
+		serdev_device_close(hu->serdev);
 	}
 
 	kfree_skb(qca->rx_skb);
@@ -891,6 +947,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 	struct hci_uart *hu = hci_get_drvdata(hdev);
 	struct qca_data *qca = hu->priv;
 	struct sk_buff *skb;
+	struct qca_serdev *qcadev;
 	u8 cmd[] = { 0x01, 0x48, 0xFC, 0x01, 0x00 };
 
 	if (baudrate > QCA_BAUDRATE_3200000)
@@ -904,6 +961,13 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 		return -ENOMEM;
 	}
 
+	/* Disabling hardware flow control is mandatory while
+	 * sending change baudrate request to wcn3990 SoC.
+	 */
+	qcadev = serdev_device_get_drvdata(hu->serdev);
+	if (qcadev->btsoc_type == QCA_WCN3990)
+		hci_uart_set_flow_control(hu, true);
+
 	/* Assign commands to change baudrate and packet type. */
 	skb_put_data(skb, cmd, sizeof(cmd));
 	hci_skb_pkt_type(skb) = HCI_COMMAND_PKT;
@@ -919,6 +983,9 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 	schedule_timeout(msecs_to_jiffies(BAUDRATE_SETTLE_TIMEOUT_MS));
 	set_current_state(TASK_RUNNING);
 
+	if (qcadev->btsoc_type == QCA_WCN3990)
+		hci_uart_set_flow_control(hu, false);
+
 	return 0;
 }
 
@@ -930,6 +997,43 @@ static inline void host_set_baudrate(struct hci_uart *hu, unsigned int speed)
 		hci_uart_set_baudrate(hu, speed);
 }
 
+static int qca_send_power_pulse(struct hci_dev *hdev, u8 cmd)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+	struct qca_data *qca = hu->priv;
+	struct sk_buff *skb;
+
+	/* These power pulses are single byte command which are sent
+	 * at required baudrate to wcn3990. On wcn3990, we have an external
+	 * circuit at Tx pin which decodes the pulse sent at specific baudrate.
+	 * For example, wcn3990 supports RF COEX antenna for both Wi-Fi/BT
+	 * and also we use the same power inputs to turn on and off for
+	 * Wi-Fi/BT. Powering up the power sources will not enable BT, until
+	 * we send a power on pulse at 115200 bps. This algorithm will help to
+	 * save power. Disabling hardware flow control is mandatory while
+	 * sending power pulses to SoC.
+	 */
+	bt_dev_dbg(hdev, "sending power pulse %02x to SoC", cmd);
+
+	skb = bt_skb_alloc(sizeof(cmd), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	hci_uart_set_flow_control(hu, true);
+
+	skb_put_u8(skb, cmd);
+	hci_skb_pkt_type(skb) = HCI_COMMAND_PKT;
+
+	skb_queue_tail(&qca->txq, skb);
+	hci_uart_tx_wakeup(hu);
+
+	/* Wait for 100 uS for SoC to settle down */
+	usleep_range(100, 200);
+	hci_uart_set_flow_control(hu, false);
+
+	return 0;
+}
+
 static unsigned int qca_get_speed(struct hci_uart *hu,
 				  enum qca_speed_type speed_type)
 {
@@ -952,9 +1056,18 @@ static unsigned int qca_get_speed(struct hci_uart *hu,
 
 static int qca_check_speeds(struct hci_uart *hu)
 {
-	if (!qca_get_speed(hu, QCA_INIT_SPEED) ||
-	    !qca_get_speed(hu, QCA_OPER_SPEED))
-		return -EINVAL;
+	struct qca_serdev *qcadev;
+
+	qcadev = serdev_device_get_drvdata(hu->serdev);
+	if (qcadev->btsoc_type == QCA_WCN3990) {
+		if (!qca_get_speed(hu, QCA_INIT_SPEED) &&
+		    !qca_get_speed(hu, QCA_OPER_SPEED))
+			return -EINVAL;
+	} else {
+		if (!qca_get_speed(hu, QCA_INIT_SPEED) ||
+		    !qca_get_speed(hu, QCA_OPER_SPEED))
+			return -EINVAL;
+	}
 
 	return 0;
 }
@@ -974,7 +1087,7 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 			return 0;
 
 		qca_baudrate = qca_get_baudrate_value(speed);
-		bt_dev_info(hu->hdev, "Set UART speed to %d", speed);
+		bt_dev_dbg(hu->hdev, "Set UART speed to %d", speed);
 		ret = qca_set_baudrate(hu->hdev, qca_baudrate);
 		if (ret)
 			return ret;
@@ -985,15 +1098,52 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 	return 0;
 }
 
+static int qca_wcn3990_init(struct hci_uart *hu)
+{
+	struct hci_dev *hdev = hu->hdev;
+	int ret;
+
+	/* Forcefully enable wcn3990 to enter in to boot mode. */
+	host_set_baudrate(hu, 2400);
+	ret = qca_send_power_pulse(hdev, QCA_WCN3990_POWEROFF_PULSE);
+	if (ret)
+		return ret;
+
+	qca_set_speed(hu, QCA_INIT_SPEED);
+	ret = qca_send_power_pulse(hdev, QCA_WCN3990_POWERON_PULSE);
+	if (ret)
+		return ret;
+
+	/* Wait for 100 ms for SoC to boot */
+	msleep(100);
+
+	/* Now the device is in ready state to communicate with host.
+	 * To sync host with device we need to reopen port.
+	 * Without this, we will have RTS and CTS synchronization
+	 * issues.
+	 */
+	serdev_device_close(hu->serdev);
+	ret = serdev_device_open(hu->serdev);
+	if (ret) {
+		bt_dev_err(hu->hdev, "failed to open port");
+		return ret;
+	}
+
+	hci_uart_set_flow_control(hu, false);
+
+	return 0;
+}
+
 static int qca_setup(struct hci_uart *hu)
 {
 	struct hci_dev *hdev = hu->hdev;
 	struct qca_data *qca = hu->priv;
 	unsigned int speed, qca_baudrate = QCA_BAUDRATE_115200;
+	struct qca_serdev *qcadev;
 	int ret;
 	int soc_ver = 0;
 
-	bt_dev_info(hdev, "ROME setup");
+	qcadev = serdev_device_get_drvdata(hu->serdev);
 
 	ret = qca_check_speeds(hu);
 	if (ret)
@@ -1002,8 +1152,19 @@ static int qca_setup(struct hci_uart *hu)
 	/* Patch downloading has to be done without IBS mode */
 	clear_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 
-	/* Setup initial baudrate */
-	qca_set_speed(hu, QCA_INIT_SPEED);
+	if (qcadev->btsoc_type == QCA_WCN3990) {
+		bt_dev_info(hdev, "setting up wcn3990");
+		ret = qca_wcn3990_init(hu);
+		if (ret)
+			return ret;
+
+		ret = qca_read_soc_version(hdev, &soc_ver);
+		if (ret)
+			return ret;
+	} else {
+		bt_dev_info(hdev, "ROME setup");
+		qca_set_speed(hu, QCA_INIT_SPEED);
+	}
 
 	/* Setup user speed if needed */
 	speed = qca_get_speed(hu, QCA_OPER_SPEED);
@@ -1015,15 +1176,16 @@ static int qca_setup(struct hci_uart *hu)
 		qca_baudrate = qca_get_baudrate_value(speed);
 	}
 
-	/* Get QCA version information */
-	ret = qca_read_soc_version(hdev, &soc_ver);
-	if (ret)
-		return ret;
+	if (qcadev->btsoc_type != QCA_WCN3990) {
+		/* Get QCA version information */
+		ret = qca_read_soc_version(hdev, &soc_ver);
+		if (ret)
+			return ret;
+	}
 
 	bt_dev_info(hdev, "QCA controller version 0x%08x", soc_ver);
-
 	/* Setup patch / NVM configurations */
-	ret = qca_uart_setup(hdev, qca_baudrate, QCA_ROME, soc_ver);
+	ret = qca_uart_setup(hdev, qca_baudrate, qcadev->btsoc_type, soc_ver);
 	if (!ret) {
 		set_bit(STATE_IN_BAND_SLEEP_ENABLED, &qca->flags);
 		qca_debugfs_init(hdev);
@@ -1059,9 +1221,123 @@ static struct hci_uart_proto qca_proto = {
 	.dequeue	= qca_dequeue,
 };
 
+static const struct qca_vreg_data qca_soc_data = {
+	.soc_type = QCA_WCN3990,
+	.vregs = (struct qca_vreg []) {
+		{ "vddio",   1800000, 1900000,  15000  },
+		{ "vddxo",   1800000, 1900000,  80000  },
+		{ "vddrf",   1300000, 1350000,  300000 },
+		{ "vddch0",  3300000, 3400000,  450000 },
+	},
+	.num_vregs = 4,
+};
+
+static void qca_power_shutdown(struct hci_dev *hdev)
+{
+	struct hci_uart *hu = hci_get_drvdata(hdev);
+
+	host_set_baudrate(hu, 2400);
+	qca_send_power_pulse(hdev, QCA_WCN3990_POWEROFF_PULSE);
+	qca_power_setup(hu, false);
+}
+
+static int qca_enable_regulator(struct qca_vreg vregs,
+				struct regulator *regulator)
+{
+	int ret;
+
+	ret = regulator_set_voltage(regulator, vregs.min_uV,
+				    vregs.max_uV);
+	if (ret)
+		return ret;
+
+	if (vregs.load_uA)
+		ret = regulator_set_load(regulator,
+					 vregs.load_uA);
+
+	if (ret)
+		return ret;
+
+	return regulator_enable(regulator);
+
+}
+
+static void qca_disable_regulator(struct qca_vreg vregs,
+				  struct regulator *regulator)
+{
+	regulator_disable(regulator);
+	regulator_set_voltage(regulator, 0, vregs.max_uV);
+	if (vregs.load_uA)
+		regulator_set_load(regulator, 0);
+
+}
+
+static int qca_power_setup(struct hci_uart *hu, bool on)
+{
+	struct qca_vreg *vregs;
+	struct regulator_bulk_data *vreg_bulk;
+	struct qca_serdev *qcadev;
+	int i, num_vregs, ret = 0;
+
+	qcadev = serdev_device_get_drvdata(hu->serdev);
+	if (!qcadev || !qcadev->bt_power || !qcadev->bt_power->vreg_data ||
+	    !qcadev->bt_power->vreg_bulk)
+		return -EINVAL;
+
+	vregs = qcadev->bt_power->vreg_data->vregs;
+	vreg_bulk = qcadev->bt_power->vreg_bulk;
+	num_vregs = qcadev->bt_power->vreg_data->num_vregs;
+	BT_DBG("on: %d", on);
+	if (on && !qcadev->bt_power->vregs_on) {
+		for (i = 0; i < num_vregs; i++) {
+			ret = qca_enable_regulator(vregs[i],
+						   vreg_bulk[i].consumer);
+			if (ret)
+				break;
+		}
+
+		if (ret) {
+			BT_ERR("failed to enable regulator:%s", vregs[i].name);
+			/* turn off regulators which are enabled */
+			for (i = i - 1; i >= 0; i--)
+				qca_disable_regulator(vregs[i],
+						      vreg_bulk[i].consumer);
+		} else {
+			qcadev->bt_power->vregs_on = true;
+		}
+	} else if (!on && qcadev->bt_power->vregs_on) {
+		/* turn off regulator in reverse order */
+		i = qcadev->bt_power->vreg_data->num_vregs - 1;
+		for ( ; i >= 0; i--)
+			qca_disable_regulator(vregs[i], vreg_bulk[i].consumer);
+
+		qcadev->bt_power->vregs_on = false;
+	}
+
+	return ret;
+}
+
+static int qca_init_regulators(struct qca_power *qca,
+				const struct qca_vreg *vregs, size_t num_vregs)
+{
+	int i;
+
+	qca->vreg_bulk = devm_kzalloc(qca->dev, num_vregs *
+				      sizeof(struct regulator_bulk_data),
+				      GFP_KERNEL);
+	if (!qca->vreg_bulk)
+		return -ENOMEM;
+
+	for (i = 0; i < num_vregs; i++)
+		qca->vreg_bulk[i].supply = vregs[i].name;
+
+	return devm_regulator_bulk_get(qca->dev, num_vregs, qca->vreg_bulk);
+}
+
 static int qca_serdev_probe(struct serdev_device *serdev)
 {
 	struct qca_serdev *qcadev;
+	const struct qca_vreg_data *data;
 	int err;
 
 	qcadev = devm_kzalloc(&serdev->dev, sizeof(*qcadev), GFP_KERNEL);
@@ -1069,47 +1345,84 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 		return -ENOMEM;
 
 	qcadev->serdev_hu.serdev = serdev;
+	data = of_device_get_match_data(&serdev->dev);
 	serdev_device_set_drvdata(serdev, qcadev);
+	if (data && data->soc_type == QCA_WCN3990) {
+		qcadev->btsoc_type = QCA_WCN3990;
+		qcadev->bt_power = devm_kzalloc(&serdev->dev,
+						sizeof(struct qca_power),
+						GFP_KERNEL);
+		if (!qcadev->bt_power)
+			return -ENOMEM;
+
+		qcadev->bt_power->dev = &serdev->dev;
+		qcadev->bt_power->vreg_data = data;
+		err = qca_init_regulators(qcadev->bt_power, data->vregs,
+					  data->num_vregs);
+		if (err) {
+			BT_ERR("Failed to init regulators:%d", err);
+			goto out;
+		}
 
-	qcadev->bt_en = devm_gpiod_get(&serdev->dev, "enable",
-				       GPIOD_OUT_LOW);
-	if (IS_ERR(qcadev->bt_en)) {
-		dev_err(&serdev->dev, "failed to acquire enable gpio\n");
-		return PTR_ERR(qcadev->bt_en);
-	}
+		qcadev->bt_power->vregs_on = false;
 
-	qcadev->susclk = devm_clk_get(&serdev->dev, NULL);
-	if (IS_ERR(qcadev->susclk)) {
-		dev_err(&serdev->dev, "failed to acquire clk\n");
-		return PTR_ERR(qcadev->susclk);
-	}
+		device_property_read_u32(&serdev->dev, "max-speed",
+					 &qcadev->oper_speed);
+		if (!qcadev->oper_speed)
+			BT_DBG("UART will pick default operating speed");
 
-	err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ);
-	if (err)
-		return err;
+		err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
+		if (err) {
+			BT_ERR("wcn3990 serdev registration failed");
+			goto out;
+		}
+	} else {
+		qcadev->btsoc_type = QCA_ROME;
+		qcadev->bt_en = devm_gpiod_get(&serdev->dev, "enable",
+					       GPIOD_OUT_LOW);
+		if (IS_ERR(qcadev->bt_en)) {
+			dev_err(&serdev->dev, "failed to acquire enable gpio\n");
+			return PTR_ERR(qcadev->bt_en);
+		}
 
-	err = clk_prepare_enable(qcadev->susclk);
-	if (err)
-		return err;
+		qcadev->susclk = devm_clk_get(&serdev->dev, NULL);
+		if (IS_ERR(qcadev->susclk)) {
+			dev_err(&serdev->dev, "failed to acquire clk\n");
+			return PTR_ERR(qcadev->susclk);
+		}
 
-	err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
-	if (err)
-		clk_disable_unprepare(qcadev->susclk);
+		err = clk_set_rate(qcadev->susclk, SUSCLK_RATE_32KHZ);
+		if (err)
+			return err;
+
+		err = clk_prepare_enable(qcadev->susclk);
+		if (err)
+			return err;
+
+		err = hci_uart_register_device(&qcadev->serdev_hu, &qca_proto);
+		if (err)
+			clk_disable_unprepare(qcadev->susclk);
+	}
+
+out:	return err;
 
-	return err;
 }
 
 static void qca_serdev_remove(struct serdev_device *serdev)
 {
 	struct qca_serdev *qcadev = serdev_device_get_drvdata(serdev);
 
-	hci_uart_unregister_device(&qcadev->serdev_hu);
+	if (qcadev->btsoc_type == QCA_WCN3990)
+		qca_power_shutdown(qcadev->serdev_hu.hdev);
+	else
+		clk_disable_unprepare(qcadev->susclk);
 
-	clk_disable_unprepare(qcadev->susclk);
+	hci_uart_unregister_device(&qcadev->serdev_hu);
 }
 
 static const struct of_device_id qca_bluetooth_of_match[] = {
 	{ .compatible = "qcom,qca6174-bt" },
+	{ .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, qca_bluetooth_of_match);
-- 
cgit v1.2.3


From 3512a18cbd8d09e22a790540cb9624c3c49827ba Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 26 Jul 2018 12:11:39 -0500
Subject: mailbox: xgene-slimpro: Fix potential NULL pointer dereference

There is a potential execution path in which function
platform_get_resource() returns NULL. If this happens,
we will end up having a NULL pointer dereference.

Fix this by replacing devm_ioremap with devm_ioremap_resource,
which has the NULL check and the memory region request.

This code was detected with the help of Coccinelle.

Cc: stable@vger.kernel.org
Fixes: f700e84f417b ("mailbox: Add support for APM X-Gene platform mailbox driver")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mailbox-xgene-slimpro.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/mailbox/mailbox-xgene-slimpro.c b/drivers/mailbox/mailbox-xgene-slimpro.c
index a7040163dd43..b8b2b3533f46 100644
--- a/drivers/mailbox/mailbox-xgene-slimpro.c
+++ b/drivers/mailbox/mailbox-xgene-slimpro.c
@@ -195,9 +195,9 @@ static int slimpro_mbox_probe(struct platform_device *pdev)
 	platform_set_drvdata(pdev, ctx);
 
 	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mb_base = devm_ioremap(&pdev->dev, regs->start, resource_size(regs));
-	if (!mb_base)
-		return -ENOMEM;
+	mb_base = devm_ioremap_resource(&pdev->dev, regs);
+	if (IS_ERR(mb_base))
+		return PTR_ERR(mb_base);
 
 	/* Setup mailbox links */
 	for (i = 0; i < MBOX_CNT; i++) {
-- 
cgit v1.2.3


From 2ad5157650b446f14a719280ba3670303bc4f439 Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Wed, 11 Jul 2018 18:42:11 -0500
Subject: mailbox/omap: switch to SPDX license identifier

Use the appropriate SPDX license identifier in the OMAP Mailbox
driver source files and drop the previous boilerplate license text.

Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/omap-mailbox.c | 10 +---------
 include/linux/omap-mailbox.h   |  5 +----
 2 files changed, 2 insertions(+), 13 deletions(-)

diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c
index e1e2c085e68e..97c7d9b7f46f 100644
--- a/drivers/mailbox/omap-mailbox.c
+++ b/drivers/mailbox/omap-mailbox.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * OMAP mailbox driver
  *
@@ -6,15 +7,6 @@
  *
  * Contact: Hiroshi DOYU <Hiroshi.DOYU@nokia.com>
  *          Suman Anna <s-anna@ti.com>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
  */
 
 #include <linux/interrupt.h>
diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h
index c726bd833761..6dbcd2da0332 100644
--- a/include/linux/omap-mailbox.h
+++ b/include/linux/omap-mailbox.h
@@ -1,9 +1,6 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * omap-mailbox: interprocessor communication module for OMAP
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #ifndef OMAP_MAILBOX_H
-- 
cgit v1.2.3


From ea2ec1e80f78e5f1d6bd04315a2a0bf0646d8548 Mon Sep 17 00:00:00 2001
From: Suman Anna <s-anna@ti.com>
Date: Wed, 11 Jul 2018 18:42:12 -0500
Subject: mailbox/omap: use of_device_get_match_data() to get match data

The OMAP Mailbox driver is directly using an integer value as
match data for distinguishing the interrupt register layout
between OMAP2 and OMAP4+ SoCs. Introduce a dedicated structure
for storing this match data, and simplify the probe function by
using the of_device_get_match_data() function. This allows the
driver to scale for 64-bit platforms by eliminating the unnecessary
type-casting between a u32 and a void pointer types.

Signed-off-by: Suman Anna <s-anna@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/omap-mailbox.c | 21 ++++++++++++++-------
 1 file changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c
index 97c7d9b7f46f..db66e952a871 100644
--- a/drivers/mailbox/omap-mailbox.c
+++ b/drivers/mailbox/omap-mailbox.c
@@ -69,6 +69,10 @@ struct omap_mbox_queue {
 	bool full;
 };
 
+struct omap_mbox_match_data {
+	u32 intr_type;
+};
+
 struct omap_mbox_device {
 	struct device *dev;
 	struct mutex cfg_lock;
@@ -638,18 +642,21 @@ static const struct dev_pm_ops omap_mbox_pm_ops = {
 	SET_SYSTEM_SLEEP_PM_OPS(omap_mbox_suspend, omap_mbox_resume)
 };
 
+static const struct omap_mbox_match_data omap2_data = { MBOX_INTR_CFG_TYPE1 };
+static const struct omap_mbox_match_data omap4_data = { MBOX_INTR_CFG_TYPE2 };
+
 static const struct of_device_id omap_mailbox_of_match[] = {
 	{
 		.compatible	= "ti,omap2-mailbox",
-		.data		= (void *)MBOX_INTR_CFG_TYPE1,
+		.data		= &omap2_data,
 	},
 	{
 		.compatible	= "ti,omap3-mailbox",
-		.data		= (void *)MBOX_INTR_CFG_TYPE1,
+		.data		= &omap2_data,
 	},
 	{
 		.compatible	= "ti,omap4-mailbox",
-		.data		= (void *)MBOX_INTR_CFG_TYPE2,
+		.data		= &omap4_data,
 	},
 	{
 		/* end */
@@ -692,7 +699,7 @@ static int omap_mbox_probe(struct platform_device *pdev)
 	struct omap_mbox_fifo *fifo;
 	struct device_node *node = pdev->dev.of_node;
 	struct device_node *child;
-	const struct of_device_id *match;
+	const struct omap_mbox_match_data *match_data;
 	u32 intr_type, info_count;
 	u32 num_users, num_fifos;
 	u32 tmp[3];
@@ -704,10 +711,10 @@ static int omap_mbox_probe(struct platform_device *pdev)
 		return -ENODEV;
 	}
 
-	match = of_match_device(omap_mailbox_of_match, &pdev->dev);
-	if (!match)
+	match_data = of_device_get_match_data(&pdev->dev);
+	if (!match_data)
 		return -ENODEV;
-	intr_type = (u32)match->data;
+	intr_type = match_data->intr_type;
 
 	if (of_property_read_u32(node, "ti,mbox-num-users", &num_users))
 		return -ENODEV;
-- 
cgit v1.2.3


From e7474ca1005768bddde2aad6fdd920245357377e Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Mon, 16 Jul 2018 13:06:02 -0500
Subject: mailbox: ti-msgmgr: Get rid of unused structure members

Though q_proxies and q_slices do describe the hardware configuration,
they are not necessary for operation given that the values are
always default. Hence drop the same.

Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/ti-msgmgr.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c
index 5d04738c3c8a..5fe6ce200264 100644
--- a/drivers/mailbox/ti-msgmgr.c
+++ b/drivers/mailbox/ti-msgmgr.c
@@ -42,8 +42,6 @@ struct ti_msgmgr_valid_queue_desc {
  * @queue_count:	Number of Queues
  * @max_message_size:	Message size in bytes
  * @max_messages:	Number of messages
- * @q_slices:		Number of queue engines
- * @q_proxies:		Number of queue proxies per page
  * @data_first_reg:	First data register for proxy data region
  * @data_last_reg:	Last data register for proxy data region
  * @tx_polled:		Do I need to use polled mechanism for tx
@@ -58,8 +56,6 @@ struct ti_msgmgr_desc {
 	u8 queue_count;
 	u8 max_message_size;
 	u8 max_messages;
-	u8 q_slices;
-	u8 q_proxies;
 	u8 data_first_reg;
 	u8 data_last_reg;
 	bool tx_polled;
@@ -494,8 +490,6 @@ static const struct ti_msgmgr_desc k2g_desc = {
 	.queue_count = 64,
 	.max_message_size = 64,
 	.max_messages = 128,
-	.q_slices = 1,
-	.q_proxies = 1,
 	.data_first_reg = 16,
 	.data_last_reg = 31,
 	.tx_polled = false,
-- 
cgit v1.2.3


From 5ab935e1942bdf8cab192478ac668b1589c47059 Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Mon, 16 Jul 2018 13:06:03 -0500
Subject: mailbox: ti-msgmgr: Allocate Rx channel resources only on request

In a much bigger system SoCs, the number of Rx channels can be
many and mostly unused based on the system of choice, and not all
Rx channels need IRQs and allocating all memory at probe will be
inefficient. Some SoCs could have total threads in the 100s and usage
would be just 1 Rx thread.

Thus, request and map the IRQs and allocate memory only when needed.

Since these channels are requested by client drivers on need, our
utilization will be optimal.

Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/ti-msgmgr.c | 91 ++++++++++++++++++++++++++++++---------------
 1 file changed, 61 insertions(+), 30 deletions(-)

diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c
index 5fe6ce200264..91c955979008 100644
--- a/drivers/mailbox/ti-msgmgr.c
+++ b/drivers/mailbox/ti-msgmgr.c
@@ -310,6 +310,51 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data)
 	return 0;
 }
 
+/**
+ *  ti_msgmgr_queue_rx_irq_req() - RX IRQ request
+ *  @dev:	device pointer
+ *  @qinst:	Queue instance
+ *  @chan:	Channel pointer
+ */
+static int ti_msgmgr_queue_rx_irq_req(struct device *dev,
+				      struct ti_queue_inst *qinst,
+				      struct mbox_chan *chan)
+{
+	int ret = 0;
+	char of_rx_irq_name[7];
+	struct device_node *np;
+
+	snprintf(of_rx_irq_name, sizeof(of_rx_irq_name),
+		 "rx_%03d", qinst->queue_id);
+
+	/* Get the IRQ if not found */
+	if (qinst->irq < 0) {
+		np = of_node_get(dev->of_node);
+		if (!np)
+			return -ENODATA;
+		qinst->irq = of_irq_get_byname(np, of_rx_irq_name);
+		of_node_put(np);
+
+		if (qinst->irq < 0) {
+			dev_err(dev,
+				"QID %d PID %d:No IRQ[%s]: %d\n",
+				qinst->queue_id, qinst->proxy_id,
+				of_rx_irq_name, qinst->irq);
+			return qinst->irq;
+		}
+	}
+
+	/* With the expectation that the IRQ might be shared in SoC */
+	ret = request_irq(qinst->irq, ti_msgmgr_queue_rx_interrupt,
+			  IRQF_SHARED, qinst->name, chan);
+	if (ret) {
+		dev_err(dev, "Unable to get IRQ %d on %s(res=%d)\n",
+			qinst->irq, qinst->name, ret);
+	}
+
+	return ret;
+}
+
 /**
  * ti_msgmgr_queue_startup() - Startup queue
  * @chan:	Channel pointer
@@ -318,19 +363,21 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data)
  */
 static int ti_msgmgr_queue_startup(struct mbox_chan *chan)
 {
-	struct ti_queue_inst *qinst = chan->con_priv;
 	struct device *dev = chan->mbox->dev;
+	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
+	struct ti_queue_inst *qinst = chan->con_priv;
+	const struct ti_msgmgr_desc *d = inst->desc;
 	int ret;
 
 	if (!qinst->is_tx) {
-		/*
-		 * With the expectation that the IRQ might be shared in SoC
-		 */
-		ret = request_irq(qinst->irq, ti_msgmgr_queue_rx_interrupt,
-				  IRQF_SHARED, qinst->name, chan);
+		/* Allocate usage buffer for rx */
+		qinst->rx_buff = kzalloc(d->max_message_size, GFP_KERNEL);
+		if (!qinst->rx_buff)
+			return -ENOMEM;
+		/* Request IRQ */
+		ret = ti_msgmgr_queue_rx_irq_req(dev, qinst, chan);
 		if (ret) {
-			dev_err(dev, "Unable to get IRQ %d on %s(res=%d)\n",
-				qinst->irq, qinst->name, ret);
+			kfree(qinst->rx_buff);
 			return ret;
 		}
 	}
@@ -346,8 +393,10 @@ static void ti_msgmgr_queue_shutdown(struct mbox_chan *chan)
 {
 	struct ti_queue_inst *qinst = chan->con_priv;
 
-	if (!qinst->is_tx)
+	if (!qinst->is_tx) {
 		free_irq(qinst->irq, chan);
+		kfree(qinst->rx_buff);
+	}
 }
 
 /**
@@ -425,27 +474,6 @@ static int ti_msgmgr_queue_setup(int idx, struct device *dev,
 		 dev_name(dev), qinst->is_tx ? "tx" : "rx", qinst->queue_id,
 		 qinst->proxy_id);
 
-	if (!qinst->is_tx) {
-		char of_rx_irq_name[7];
-
-		snprintf(of_rx_irq_name, sizeof(of_rx_irq_name),
-			 "rx_%03d", qinst->queue_id);
-
-		qinst->irq = of_irq_get_byname(np, of_rx_irq_name);
-		if (qinst->irq < 0) {
-			dev_crit(dev,
-				 "[%d]QID %d PID %d:No IRQ[%s]: %d\n",
-				 idx, qinst->queue_id, qinst->proxy_id,
-				 of_rx_irq_name, qinst->irq);
-			return qinst->irq;
-		}
-		/* Allocate usage buffer for rx */
-		qinst->rx_buff = devm_kzalloc(dev,
-					      d->max_message_size, GFP_KERNEL);
-		if (!qinst->rx_buff)
-			return -ENOMEM;
-	}
-
 	qinst->queue_buff_start = inst->queue_proxy_region +
 	    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id, d->data_first_reg);
 	qinst->queue_buff_end = inst->queue_proxy_region +
@@ -454,6 +482,9 @@ static int ti_msgmgr_queue_setup(int idx, struct device *dev,
 	    Q_STATE_OFFSET(qinst->queue_id);
 	qinst->chan = chan;
 
+	/* Setup an error value for IRQ - Lazy allocation */
+	qinst->irq = -EINVAL;
+
 	chan->con_priv = qinst;
 
 	dev_dbg(dev, "[%d] qidx=%d pidx=%d irq=%d q_s=%p q_e = %p\n",
-- 
cgit v1.2.3


From 8e56086292094290600edd7c526841df14b201ca Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Mon, 16 Jul 2018 13:06:04 -0500
Subject: mailbox: ti-msgmgr: Change message count mask to be descriptor based

Change mask used to extract the message count to be descriptor based.

This is to support changes for count location for various SoC
solutions.

Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/ti-msgmgr.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c
index 91c955979008..7d2eb4b359ba 100644
--- a/drivers/mailbox/ti-msgmgr.c
+++ b/drivers/mailbox/ti-msgmgr.c
@@ -44,6 +44,7 @@ struct ti_msgmgr_valid_queue_desc {
  * @max_messages:	Number of messages
  * @data_first_reg:	First data register for proxy data region
  * @data_last_reg:	Last data register for proxy data region
+ * @status_cnt_mask:	Mask for getting the status value
  * @tx_polled:		Do I need to use polled mechanism for tx
  * @tx_poll_timeout_ms: Timeout in ms if polled
  * @valid_queues:	List of Valid queues that the processor can access
@@ -58,6 +59,7 @@ struct ti_msgmgr_desc {
 	u8 max_messages;
 	u8 data_first_reg;
 	u8 data_last_reg;
+	u32 status_cnt_mask;
 	bool tx_polled;
 	int tx_poll_timeout_ms;
 	const struct ti_msgmgr_valid_queue_desc *valid_queues;
@@ -116,20 +118,24 @@ struct ti_msgmgr_inst {
 
 /**
  * ti_msgmgr_queue_get_num_messages() - Get the number of pending messages
+ * @d:		Description of message manager
  * @qinst:	Queue instance for which we check the number of pending messages
  *
  * Return: number of messages pending in the queue (0 == no pending messages)
  */
-static inline int ti_msgmgr_queue_get_num_messages(struct ti_queue_inst *qinst)
+static inline int
+ti_msgmgr_queue_get_num_messages(const struct ti_msgmgr_desc *d,
+				 struct ti_queue_inst *qinst)
 {
 	u32 val;
+	u32 status_cnt_mask = d->status_cnt_mask;
 
 	/*
 	 * We cannot use relaxed operation here - update may happen
 	 * real-time.
 	 */
-	val = readl(qinst->queue_state) & Q_STATE_ENTRY_COUNT_MASK;
-	val >>= __ffs(Q_STATE_ENTRY_COUNT_MASK);
+	val = readl(qinst->queue_state) & status_cnt_mask;
+	val >>= __ffs(status_cnt_mask);
 
 	return val;
 }
@@ -167,8 +173,9 @@ static irqreturn_t ti_msgmgr_queue_rx_interrupt(int irq, void *p)
 		return IRQ_NONE;
 	}
 
+	desc = inst->desc;
 	/* Do I actually have messages to read? */
-	msg_count = ti_msgmgr_queue_get_num_messages(qinst);
+	msg_count = ti_msgmgr_queue_get_num_messages(desc, qinst);
 	if (!msg_count) {
 		/* Shared IRQ? */
 		dev_dbg(dev, "Spurious event - 0 pending data!\n");
@@ -181,7 +188,6 @@ static irqreturn_t ti_msgmgr_queue_rx_interrupt(int irq, void *p)
 	 * of how many bytes I should be reading. Let the client figure this
 	 * out.. I just read the full message and pass it on..
 	 */
-	desc = inst->desc;
 	message.len = desc->max_message_size;
 	message.buf = (u8 *)qinst->rx_buff;
 
@@ -224,12 +230,14 @@ static irqreturn_t ti_msgmgr_queue_rx_interrupt(int irq, void *p)
 static bool ti_msgmgr_queue_peek_data(struct mbox_chan *chan)
 {
 	struct ti_queue_inst *qinst = chan->con_priv;
+	struct device *dev = chan->mbox->dev;
+	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
 	int msg_count;
 
 	if (qinst->is_tx)
 		return false;
 
-	msg_count = ti_msgmgr_queue_get_num_messages(qinst);
+	msg_count = ti_msgmgr_queue_get_num_messages(inst->desc, qinst);
 
 	return msg_count ? true : false;
 }
@@ -243,12 +251,14 @@ static bool ti_msgmgr_queue_peek_data(struct mbox_chan *chan)
 static bool ti_msgmgr_last_tx_done(struct mbox_chan *chan)
 {
 	struct ti_queue_inst *qinst = chan->con_priv;
+	struct device *dev = chan->mbox->dev;
+	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
 	int msg_count;
 
 	if (!qinst->is_tx)
 		return false;
 
-	msg_count = ti_msgmgr_queue_get_num_messages(qinst);
+	msg_count = ti_msgmgr_queue_get_num_messages(inst->desc, qinst);
 
 	/* if we have any messages pending.. */
 	return msg_count ? false : true;
@@ -523,6 +533,7 @@ static const struct ti_msgmgr_desc k2g_desc = {
 	.max_messages = 128,
 	.data_first_reg = 16,
 	.data_last_reg = 31,
+	.status_cnt_mask = Q_STATE_ENTRY_COUNT_MASK,
 	.tx_polled = false,
 	.valid_queues = k2g_valid_queues,
 	.num_valid_queues = ARRAY_SIZE(k2g_valid_queues),
-- 
cgit v1.2.3


From 89c976c2f3fc02b95ae0a4a35dc3373ec8bfbdcb Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Mon, 16 Jul 2018 13:06:05 -0500
Subject: mailbox: ti-msgmgr: Move the memory region name to descriptor

For newer generation of the hardware, the naming of the region is
decided at integration level and there could be additional regions
as well. Hence move the region naming to be described from compatible
descriptor.

Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/ti-msgmgr.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c
index 7d2eb4b359ba..7167cc708f44 100644
--- a/drivers/mailbox/ti-msgmgr.c
+++ b/drivers/mailbox/ti-msgmgr.c
@@ -48,6 +48,8 @@ struct ti_msgmgr_valid_queue_desc {
  * @tx_polled:		Do I need to use polled mechanism for tx
  * @tx_poll_timeout_ms: Timeout in ms if polled
  * @valid_queues:	List of Valid queues that the processor can access
+ * @data_region_name:	Name of the proxy data region
+ * @status_region_name:	Name of the proxy status region
  * @num_valid_queues:	Number of valid queues
  *
  * This structure is used in of match data to describe how integration
@@ -63,6 +65,8 @@ struct ti_msgmgr_desc {
 	bool tx_polled;
 	int tx_poll_timeout_ms;
 	const struct ti_msgmgr_valid_queue_desc *valid_queues;
+	const char *data_region_name;
+	const char *status_region_name;
 	int num_valid_queues;
 };
 
@@ -531,6 +535,8 @@ static const struct ti_msgmgr_desc k2g_desc = {
 	.queue_count = 64,
 	.max_message_size = 64,
 	.max_messages = 128,
+	.data_region_name = "queue_proxy_region",
+	.status_region_name = "queue_state_debug_region",
 	.data_first_reg = 16,
 	.data_last_reg = 31,
 	.status_cnt_mask = Q_STATE_ENTRY_COUNT_MASK,
@@ -582,13 +588,13 @@ static int ti_msgmgr_probe(struct platform_device *pdev)
 	inst->desc = desc;
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-					   "queue_proxy_region");
+					   desc->data_region_name);
 	inst->queue_proxy_region = devm_ioremap_resource(dev, res);
 	if (IS_ERR(inst->queue_proxy_region))
 		return PTR_ERR(inst->queue_proxy_region);
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-					   "queue_state_debug_region");
+					   desc->status_region_name);
 	inst->queue_state_debug_region = devm_ioremap_resource(dev, res);
 	if (IS_ERR(inst->queue_state_debug_region))
 		return PTR_ERR(inst->queue_state_debug_region);
-- 
cgit v1.2.3


From 0f23a179746c10de8f8fe6ecc4767a0d6c824fa9 Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Mon, 16 Jul 2018 13:06:06 -0500
Subject: dt-bindings: mailbox: Add support for secure proxy threads

Secure Proxy is another communication scheme in Texas Instrument's
devices intended to provide an unique communication path from various
processors in the System on Chip(SoC) to a central System Controller.

Secure proxy is, in effect, an evolution of current generation Message
Manager hardware block found in K2G devices. However the following
changes have taken place:

Secure Proxy instance exposes "threads" or "proxies" which is
primary representation of "a" communication channel. Each thread is
preconfigured by System controller configuration based on SoC usage
requirements. Secure proxy by itself represents a single "queue" of
communication but allows the proxies to be independently operated.

Each Secure proxy thread can uniquely have their own error and threshold
interrupts allowing for more fine control of IRQ handling.

Provide an hardware description of the same for device tree
representation.

See AM65x Technical Reference Manual (SPRUID7, April 2018)
for further details: http://www.ti.com/lit/pdf/spruid7

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../bindings/mailbox/ti,secure-proxy.txt           | 50 ++++++++++++++++++++++
 1 file changed, 50 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mailbox/ti,secure-proxy.txt

diff --git a/Documentation/devicetree/bindings/mailbox/ti,secure-proxy.txt b/Documentation/devicetree/bindings/mailbox/ti,secure-proxy.txt
new file mode 100644
index 000000000000..6c9c7daf0f5c
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/ti,secure-proxy.txt
@@ -0,0 +1,50 @@
+Texas Instruments' Secure Proxy
+========================================
+
+The Texas Instruments' secure proxy is a mailbox controller that has
+configurable queues selectable at SoC(System on Chip) integration. The
+Message manager is broken up into different address regions that are
+called "threads" or "proxies" - each instance is unidirectional and is
+instantiated at SoC integration level by system controller to indicate
+receive or transmit path.
+
+Message Manager Device Node:
+===========================
+Required properties:
+--------------------
+- compatible:		Shall be "ti,am654-secure-proxy"
+- reg-names 		target_data - Map the proxy data region
+			rt - Map the realtime status region
+			scfg - Map the configuration region
+- reg:			Contains the register map per reg-names.
+- #mbox-cells		Shall be 1 and shall refer to the transfer path
+			called thread.
+- interrupt-names:	Contains interrupt names matching the rx transfer path
+			for a given SoC. Receive interrupts shall be of the
+			format: "rx_<PID>".
+- interrupts:		Contains the interrupt information corresponding to
+			interrupt-names property.
+
+Example(AM654):
+------------
+
+	secure_proxy: mailbox@32c00000 {
+		compatible = "ti,am654-secure-proxy";
+		#mbox-cells = <1>;
+		reg-names = "target_data", "rt", "scfg";
+		reg = <0x0 0x32c00000 0x0 0x100000>,
+		      <0x0 0x32400000 0x0 0x100000>,
+		      <0x0 0x32800000 0x0 0x100000>;
+		interrupt-names = "rx_011";
+		interrupts = <GIC_SPI 32 IRQ_TYPE_LEVEL_HIGH>;
+	};
+
+	dmsc: dmsc {
+		[...]
+		mbox-names = "rx", "tx";
+		# RX Thread ID is 11
+		# TX Thread ID is 13
+		mboxes= <&secure_proxy 11>,
+			<&secure_proxy 13>;
+		[...]
+	};
-- 
cgit v1.2.3


From a2b79838b891718dd4f0caf86dfa193af789245d Mon Sep 17 00:00:00 2001
From: Nishanth Menon <nm@ti.com>
Date: Mon, 16 Jul 2018 13:06:07 -0500
Subject: mailbox: ti-msgmgr: Add support for Secure Proxy

Secure Proxy is another communication scheme in Texas Instrument's
devices intended to provide an unique communication path from various
processors in the System on Chip(SoC) to a central System Controller.

Secure proxy is, in effect, an evolution of current generation Message
Manager hardware block found in K2G devices. However the following
changes have taken place:

Secure Proxy instance exposes "threads" or "proxies" which is
primary representation of "a" communication channel. Each thread is
preconfigured by System controller configuration based on SoC usage
requirements. Secure proxy by itself represents a single "queue" of
communication but allows the proxies to be independently operated.

Each Secure proxy thread can uniquely have their own error and threshold
interrupts allowing for more fine control of IRQ handling.

Provide the driver support for Secure Proxy and thread instances.

NOTE: Secure proxy configuration is only done by System Controller,
hence these are assumed to be pre-configured instances.

See AM65x Technical Reference Manual (SPRUID7, April 2018)
for further details: http://www.ti.com/lit/pdf/spruid7

Signed-off-by: Nishanth Menon <nm@ti.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/ti-msgmgr.c | 233 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 205 insertions(+), 28 deletions(-)

diff --git a/drivers/mailbox/ti-msgmgr.c b/drivers/mailbox/ti-msgmgr.c
index 7167cc708f44..5bceafbf6699 100644
--- a/drivers/mailbox/ti-msgmgr.c
+++ b/drivers/mailbox/ti-msgmgr.c
@@ -25,6 +25,17 @@
 #define Q_STATE_OFFSET(queue)			((queue) * 0x4)
 #define Q_STATE_ENTRY_COUNT_MASK		(0xFFF000)
 
+#define SPROXY_THREAD_OFFSET(tid) (0x1000 * (tid))
+#define SPROXY_THREAD_DATA_OFFSET(tid, reg) \
+	(SPROXY_THREAD_OFFSET(tid) + ((reg) * 0x4) + 0x4)
+
+#define SPROXY_THREAD_STATUS_OFFSET(tid) (SPROXY_THREAD_OFFSET(tid))
+
+#define SPROXY_THREAD_STATUS_COUNT_MASK (0xFF)
+
+#define SPROXY_THREAD_CTRL_OFFSET(tid) (0x1000 + SPROXY_THREAD_OFFSET(tid))
+#define SPROXY_THREAD_CTRL_DIR_MASK (0x1 << 31)
+
 /**
  * struct ti_msgmgr_valid_queue_desc - SoC valid queues meant for this processor
  * @queue_id:	Queue Number for this path
@@ -45,12 +56,15 @@ struct ti_msgmgr_valid_queue_desc {
  * @data_first_reg:	First data register for proxy data region
  * @data_last_reg:	Last data register for proxy data region
  * @status_cnt_mask:	Mask for getting the status value
+ * @status_err_mask:	Mask for getting the error value, if applicable
  * @tx_polled:		Do I need to use polled mechanism for tx
  * @tx_poll_timeout_ms: Timeout in ms if polled
  * @valid_queues:	List of Valid queues that the processor can access
  * @data_region_name:	Name of the proxy data region
  * @status_region_name:	Name of the proxy status region
+ * @ctrl_region_name:	Name of the proxy control region
  * @num_valid_queues:	Number of valid queues
+ * @is_sproxy:		Is this an Secure Proxy instance?
  *
  * This structure is used in of match data to describe how integration
  * for a specific compatible SoC is done.
@@ -62,12 +76,15 @@ struct ti_msgmgr_desc {
 	u8 data_first_reg;
 	u8 data_last_reg;
 	u32 status_cnt_mask;
+	u32 status_err_mask;
 	bool tx_polled;
 	int tx_poll_timeout_ms;
 	const struct ti_msgmgr_valid_queue_desc *valid_queues;
 	const char *data_region_name;
 	const char *status_region_name;
+	const char *ctrl_region_name;
 	int num_valid_queues;
+	bool is_sproxy;
 };
 
 /**
@@ -80,6 +97,7 @@ struct ti_msgmgr_desc {
  * @queue_buff_start: First register of Data Buffer
  * @queue_buff_end: Last (or confirmation) register of Data buffer
  * @queue_state: Queue status register
+ * @queue_ctrl: Queue Control register
  * @chan:	Mailbox channel
  * @rx_buff:	Receive buffer pointer allocated at probe, max_message_size
  */
@@ -92,6 +110,7 @@ struct ti_queue_inst {
 	void __iomem *queue_buff_start;
 	void __iomem *queue_buff_end;
 	void __iomem *queue_state;
+	void __iomem *queue_ctrl;
 	struct mbox_chan *chan;
 	u32 *rx_buff;
 };
@@ -102,6 +121,7 @@ struct ti_queue_inst {
  * @desc:	Description of the SoC integration
  * @queue_proxy_region:	Queue proxy region where queue buffers are located
  * @queue_state_debug_region:	Queue status register regions
+ * @queue_ctrl_region:	Queue Control register regions
  * @num_valid_queues:	Number of valid queues defined for the processor
  *		Note: other queues are probably reserved for other processors
  *		in the SoC.
@@ -114,6 +134,7 @@ struct ti_msgmgr_inst {
 	const struct ti_msgmgr_desc *desc;
 	void __iomem *queue_proxy_region;
 	void __iomem *queue_state_debug_region;
+	void __iomem *queue_ctrl_region;
 	u8 num_valid_queues;
 	struct ti_queue_inst *qinsts;
 	struct mbox_controller mbox;
@@ -144,6 +165,31 @@ ti_msgmgr_queue_get_num_messages(const struct ti_msgmgr_desc *d,
 	return val;
 }
 
+/**
+ * ti_msgmgr_queue_is_error() - Check to see if there is queue error
+ * @d:		Description of message manager
+ * @qinst:	Queue instance for which we check the number of pending messages
+ *
+ * Return: true if error, else false
+ */
+static inline bool ti_msgmgr_queue_is_error(const struct ti_msgmgr_desc *d,
+					    struct ti_queue_inst *qinst)
+{
+	u32 val;
+
+	/* Msgmgr has no error detection */
+	if (!d->is_sproxy)
+		return false;
+
+	/*
+	 * We cannot use relaxed operation here - update may happen
+	 * real-time.
+	 */
+	val = readl(qinst->queue_state) & d->status_err_mask;
+
+	return val ? true : false;
+}
+
 /**
  * ti_msgmgr_queue_rx_interrupt() - Interrupt handler for receive Queue
  * @irq:	Interrupt number
@@ -178,6 +224,11 @@ static irqreturn_t ti_msgmgr_queue_rx_interrupt(int irq, void *p)
 	}
 
 	desc = inst->desc;
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on Rx channel %s\n", qinst->name);
+		return IRQ_NONE;
+	}
+
 	/* Do I actually have messages to read? */
 	msg_count = ti_msgmgr_queue_get_num_messages(desc, qinst);
 	if (!msg_count) {
@@ -236,12 +287,18 @@ static bool ti_msgmgr_queue_peek_data(struct mbox_chan *chan)
 	struct ti_queue_inst *qinst = chan->con_priv;
 	struct device *dev = chan->mbox->dev;
 	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
+	const struct ti_msgmgr_desc *desc = inst->desc;
 	int msg_count;
 
 	if (qinst->is_tx)
 		return false;
 
-	msg_count = ti_msgmgr_queue_get_num_messages(inst->desc, qinst);
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on channel %s\n", qinst->name);
+		return false;
+	}
+
+	msg_count = ti_msgmgr_queue_get_num_messages(desc, qinst);
 
 	return msg_count ? true : false;
 }
@@ -257,12 +314,23 @@ static bool ti_msgmgr_last_tx_done(struct mbox_chan *chan)
 	struct ti_queue_inst *qinst = chan->con_priv;
 	struct device *dev = chan->mbox->dev;
 	struct ti_msgmgr_inst *inst = dev_get_drvdata(dev);
+	const struct ti_msgmgr_desc *desc = inst->desc;
 	int msg_count;
 
 	if (!qinst->is_tx)
 		return false;
 
-	msg_count = ti_msgmgr_queue_get_num_messages(inst->desc, qinst);
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on channel %s\n", qinst->name);
+		return false;
+	}
+
+	msg_count = ti_msgmgr_queue_get_num_messages(desc, qinst);
+
+	if (desc->is_sproxy) {
+		/* In secure proxy, msg_count indicates how many we can send */
+		return msg_count ? true : false;
+	}
 
 	/* if we have any messages pending.. */
 	return msg_count ? false : true;
@@ -292,6 +360,11 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data)
 	}
 	desc = inst->desc;
 
+	if (ti_msgmgr_queue_is_error(desc, qinst)) {
+		dev_err(dev, "Error on channel %s\n", qinst->name);
+		return false;
+	}
+
 	if (desc->max_message_size < message->len) {
 		dev_err(dev, "Queue %s message length %zu > max %d\n",
 			qinst->name, message->len, desc->max_message_size);
@@ -327,10 +400,12 @@ static int ti_msgmgr_send_data(struct mbox_chan *chan, void *data)
 /**
  *  ti_msgmgr_queue_rx_irq_req() - RX IRQ request
  *  @dev:	device pointer
+ *  @d:		descriptor for ti_msgmgr
  *  @qinst:	Queue instance
  *  @chan:	Channel pointer
  */
 static int ti_msgmgr_queue_rx_irq_req(struct device *dev,
+				      const struct ti_msgmgr_desc *d,
 				      struct ti_queue_inst *qinst,
 				      struct mbox_chan *chan)
 {
@@ -339,7 +414,7 @@ static int ti_msgmgr_queue_rx_irq_req(struct device *dev,
 	struct device_node *np;
 
 	snprintf(of_rx_irq_name, sizeof(of_rx_irq_name),
-		 "rx_%03d", qinst->queue_id);
+		 "rx_%03d", d->is_sproxy ? qinst->proxy_id : qinst->queue_id);
 
 	/* Get the IRQ if not found */
 	if (qinst->irq < 0) {
@@ -382,6 +457,24 @@ static int ti_msgmgr_queue_startup(struct mbox_chan *chan)
 	struct ti_queue_inst *qinst = chan->con_priv;
 	const struct ti_msgmgr_desc *d = inst->desc;
 	int ret;
+	int msg_count;
+
+	/*
+	 * If sproxy is starting and can send messages, we are a Tx thread,
+	 * else Rx
+	 */
+	if (d->is_sproxy) {
+		qinst->is_tx = (readl(qinst->queue_ctrl) &
+				SPROXY_THREAD_CTRL_DIR_MASK) ? false : true;
+
+		msg_count = ti_msgmgr_queue_get_num_messages(d, qinst);
+
+		if (!msg_count && qinst->is_tx) {
+			dev_err(dev, "%s: Cannot transmit with 0 credits!\n",
+				qinst->name);
+			return -EINVAL;
+		}
+	}
 
 	if (!qinst->is_tx) {
 		/* Allocate usage buffer for rx */
@@ -389,7 +482,7 @@ static int ti_msgmgr_queue_startup(struct mbox_chan *chan)
 		if (!qinst->rx_buff)
 			return -ENOMEM;
 		/* Request IRQ */
-		ret = ti_msgmgr_queue_rx_irq_req(dev, qinst, chan);
+		ret = ti_msgmgr_queue_rx_irq_req(dev, d, qinst, chan);
 		if (ret) {
 			kfree(qinst->rx_buff);
 			return ret;
@@ -427,20 +520,38 @@ static struct mbox_chan *ti_msgmgr_of_xlate(struct mbox_controller *mbox,
 	struct ti_msgmgr_inst *inst;
 	int req_qid, req_pid;
 	struct ti_queue_inst *qinst;
-	int i;
+	const struct ti_msgmgr_desc *d;
+	int i, ncells;
 
 	inst = container_of(mbox, struct ti_msgmgr_inst, mbox);
 	if (WARN_ON(!inst))
 		return ERR_PTR(-EINVAL);
 
-	/* #mbox-cells is 2 */
-	if (p->args_count != 2) {
-		dev_err(inst->dev, "Invalid arguments in dt[%d] instead of 2\n",
-			p->args_count);
+	d = inst->desc;
+
+	if (d->is_sproxy)
+		ncells = 1;
+	else
+		ncells = 2;
+	if (p->args_count != ncells) {
+		dev_err(inst->dev, "Invalid arguments in dt[%d]. Must be %d\n",
+			p->args_count, ncells);
 		return ERR_PTR(-EINVAL);
 	}
-	req_qid = p->args[0];
-	req_pid = p->args[1];
+	if (ncells == 1) {
+		req_qid = 0;
+		req_pid = p->args[0];
+	} else {
+		req_qid = p->args[0];
+		req_pid = p->args[1];
+	}
+
+	if (d->is_sproxy) {
+		if (req_pid > d->num_valid_queues)
+			goto err;
+		qinst = &inst->qinsts[req_pid];
+		return qinst->chan;
+	}
 
 	for (qinst = inst->qinsts, i = 0; i < inst->num_valid_queues;
 	     i++, qinst++) {
@@ -448,6 +559,7 @@ static struct mbox_chan *ti_msgmgr_of_xlate(struct mbox_controller *mbox,
 			return qinst->chan;
 	}
 
+err:
 	dev_err(inst->dev, "Queue ID %d, Proxy ID %d is wrong on %s\n",
 		req_qid, req_pid, p->np->name);
 	return ERR_PTR(-ENOENT);
@@ -474,6 +586,8 @@ static int ti_msgmgr_queue_setup(int idx, struct device *dev,
 				 struct ti_queue_inst *qinst,
 				 struct mbox_chan *chan)
 {
+	char *dir;
+
 	qinst->proxy_id = qd->proxy_id;
 	qinst->queue_id = qd->queue_id;
 
@@ -483,17 +597,38 @@ static int ti_msgmgr_queue_setup(int idx, struct device *dev,
 		return -ERANGE;
 	}
 
-	qinst->is_tx = qd->is_tx;
-	snprintf(qinst->name, sizeof(qinst->name), "%s %s_%03d_%03d",
-		 dev_name(dev), qinst->is_tx ? "tx" : "rx", qinst->queue_id,
-		 qinst->proxy_id);
-
-	qinst->queue_buff_start = inst->queue_proxy_region +
-	    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id, d->data_first_reg);
-	qinst->queue_buff_end = inst->queue_proxy_region +
-	    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id, d->data_last_reg);
-	qinst->queue_state = inst->queue_state_debug_region +
-	    Q_STATE_OFFSET(qinst->queue_id);
+	if (d->is_sproxy) {
+		qinst->queue_buff_start = inst->queue_proxy_region +
+		    SPROXY_THREAD_DATA_OFFSET(qinst->proxy_id,
+					      d->data_first_reg);
+		qinst->queue_buff_end = inst->queue_proxy_region +
+		    SPROXY_THREAD_DATA_OFFSET(qinst->proxy_id,
+					      d->data_last_reg);
+		qinst->queue_state = inst->queue_state_debug_region +
+		    SPROXY_THREAD_STATUS_OFFSET(qinst->proxy_id);
+		qinst->queue_ctrl = inst->queue_ctrl_region +
+		    SPROXY_THREAD_CTRL_OFFSET(qinst->proxy_id);
+
+		/* XXX: DONOT read registers here!.. Some may be unusable */
+		dir = "thr";
+		snprintf(qinst->name, sizeof(qinst->name), "%s %s_%03d",
+			 dev_name(dev), dir, qinst->proxy_id);
+	} else {
+		qinst->queue_buff_start = inst->queue_proxy_region +
+		    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id,
+				  d->data_first_reg);
+		qinst->queue_buff_end = inst->queue_proxy_region +
+		    Q_DATA_OFFSET(qinst->proxy_id, qinst->queue_id,
+				  d->data_last_reg);
+		qinst->queue_state =
+		    inst->queue_state_debug_region +
+		    Q_STATE_OFFSET(qinst->queue_id);
+		qinst->is_tx = qd->is_tx;
+		dir = qinst->is_tx ? "tx" : "rx";
+		snprintf(qinst->name, sizeof(qinst->name), "%s %s_%03d_%03d",
+			 dev_name(dev), dir, qinst->queue_id, qinst->proxy_id);
+	}
+
 	qinst->chan = chan;
 
 	/* Setup an error value for IRQ - Lazy allocation */
@@ -543,12 +678,29 @@ static const struct ti_msgmgr_desc k2g_desc = {
 	.tx_polled = false,
 	.valid_queues = k2g_valid_queues,
 	.num_valid_queues = ARRAY_SIZE(k2g_valid_queues),
+	.is_sproxy = false,
+};
+
+static const struct ti_msgmgr_desc am654_desc = {
+	.queue_count = 190,
+	.num_valid_queues = 190,
+	.max_message_size = 60,
+	.data_region_name = "target_data",
+	.status_region_name = "rt",
+	.ctrl_region_name = "scfg",
+	.data_first_reg = 0,
+	.data_last_reg = 14,
+	.status_cnt_mask = SPROXY_THREAD_STATUS_COUNT_MASK,
+	.tx_polled = false,
+	.is_sproxy = true,
 };
 
 static const struct of_device_id ti_msgmgr_of_match[] = {
 	{.compatible = "ti,k2g-message-manager", .data = &k2g_desc},
+	{.compatible = "ti,am654-secure-proxy", .data = &am654_desc},
 	{ /* Sentinel */ }
 };
+
 MODULE_DEVICE_TABLE(of, ti_msgmgr_of_match);
 
 static int ti_msgmgr_probe(struct platform_device *pdev)
@@ -599,6 +751,14 @@ static int ti_msgmgr_probe(struct platform_device *pdev)
 	if (IS_ERR(inst->queue_state_debug_region))
 		return PTR_ERR(inst->queue_state_debug_region);
 
+	if (desc->is_sproxy) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   desc->ctrl_region_name);
+		inst->queue_ctrl_region = devm_ioremap_resource(dev, res);
+		if (IS_ERR(inst->queue_ctrl_region))
+			return PTR_ERR(inst->queue_ctrl_region);
+	}
+
 	dev_dbg(dev, "proxy region=%p, queue_state=%p\n",
 		inst->queue_proxy_region, inst->queue_state_debug_region);
 
@@ -620,12 +780,29 @@ static int ti_msgmgr_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	inst->chans = chans;
 
-	for (i = 0, queue_desc = desc->valid_queues;
-	     i < queue_count; i++, qinst++, chans++, queue_desc++) {
-		ret = ti_msgmgr_queue_setup(i, dev, np, inst,
-					    desc, queue_desc, qinst, chans);
-		if (ret)
-			return ret;
+	if (desc->is_sproxy) {
+		struct ti_msgmgr_valid_queue_desc sproxy_desc;
+
+		/* All proxies may be valid in Secure Proxy instance */
+		for (i = 0; i < queue_count; i++, qinst++, chans++) {
+			sproxy_desc.queue_id = 0;
+			sproxy_desc.proxy_id = i;
+			ret = ti_msgmgr_queue_setup(i, dev, np, inst,
+						    desc, &sproxy_desc, qinst,
+						    chans);
+			if (ret)
+				return ret;
+		}
+	} else {
+		/* Only Some proxies are valid in Message Manager */
+		for (i = 0, queue_desc = desc->valid_queues;
+		     i < queue_count; i++, qinst++, chans++, queue_desc++) {
+			ret = ti_msgmgr_queue_setup(i, dev, np, inst,
+						    desc, queue_desc, qinst,
+						    chans);
+			if (ret)
+				return ret;
+		}
 	}
 
 	mbox = &inst->mbox;
-- 
cgit v1.2.3


From 9038820cef3c3824cdd846d69894746a73c053db Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 14:47:56 +0100
Subject: ALSA: gus: fix spelling mistake "acumulator" -> "accumulator"

Trivial spelling mistake fix in debug message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/gus/gus_io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/isa/gus/gus_io.c b/sound/isa/gus/gus_io.c
index ca79878d8d8c..2fd32ef22c30 100644
--- a/sound/isa/gus/gus_io.c
+++ b/sound/isa/gus/gus_io.c
@@ -461,7 +461,7 @@ void snd_gf1_print_voice_registers(struct snd_gus_card * gus)
 			printk(KERN_INFO " -%i- GFA1 effect address         = 0x%x\n", voice, snd_gf1_i_read_addr(gus, 0x11, ctrl & 4));
 			printk(KERN_INFO " -%i- GFA1 effect volume          = 0x%x\n", voice, snd_gf1_i_read16(gus, 0x16));
 			printk(KERN_INFO " -%i- GFA1 effect volume final    = 0x%x\n", voice, snd_gf1_i_read16(gus, 0x1d));
-			printk(KERN_INFO " -%i- GFA1 effect acumulator      = 0x%x\n", voice, snd_gf1_i_read8(gus, 0x14));
+			printk(KERN_INFO " -%i- GFA1 effect accumulator     = 0x%x\n", voice, snd_gf1_i_read8(gus, 0x14));
 		}
 		if (mode & 0x20) {
 			printk(KERN_INFO " -%i- GFA1 left offset            = 0x%x (%i)\n", voice, snd_gf1_i_read16(gus, 0x13), snd_gf1_i_read16(gus, 0x13) >> 4);
-- 
cgit v1.2.3


From a6403299893982a2c0b0a6f43261976c43e1598e Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 3 Aug 2018 15:40:25 +0200
Subject: ALSA: compress: Remove empty init and exit

For a sake of code simplification, remove the init and the exit
entries that do nothing.

Notes for readers: actually it's OK to remove *both* init and exit,
but not OK to remove the exit entry.  By removing only the exit while
keeping init, the module becomes permanently loaded; i.e. you cannot
unload it any longer!

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/compress_offload.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/sound/core/compress_offload.c b/sound/core/compress_offload.c
index 4b01a37c836e..26b5e245b074 100644
--- a/sound/core/compress_offload.c
+++ b/sound/core/compress_offload.c
@@ -1160,18 +1160,6 @@ int snd_compress_deregister(struct snd_compr *device)
 }
 EXPORT_SYMBOL_GPL(snd_compress_deregister);
 
-static int __init snd_compress_init(void)
-{
-	return 0;
-}
-
-static void __exit snd_compress_exit(void)
-{
-}
-
-module_init(snd_compress_init);
-module_exit(snd_compress_exit);
-
 MODULE_DESCRIPTION("ALSA Compressed offload framework");
 MODULE_AUTHOR("Vinod Koul <vinod.koul@linux.intel.com>");
 MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 969686ee0e0ff62ece428e8e02b07f81ac88a84d Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 3 Aug 2018 15:42:46 +0200
Subject: ALSA: drivers: Remove empty init and exit

For a sake of code simplification, remove the init and the exit
entries that do nothing.

Notes for readers: actually it's OK to remove *both* init and exit,
but not OK to remove the exit entry.  By removing only the exit while
keeping init, the module becomes permanently loaded; i.e. you cannot
unload it any longer!

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/drivers/mpu401/mpu401_uart.c | 16 ----------------
 sound/drivers/opl3/opl3_lib.c      | 16 ----------------
 sound/drivers/opl4/opl4_lib.c      | 12 ------------
 sound/drivers/vx/vx_core.c         | 15 ---------------
 4 files changed, 59 deletions(-)

diff --git a/sound/drivers/mpu401/mpu401_uart.c b/sound/drivers/mpu401/mpu401_uart.c
index 3e745f47dd2f..dae26e856b26 100644
--- a/sound/drivers/mpu401/mpu401_uart.c
+++ b/sound/drivers/mpu401/mpu401_uart.c
@@ -617,19 +617,3 @@ free_device:
 }
 
 EXPORT_SYMBOL(snd_mpu401_uart_new);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_mpu401_uart_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_mpu401_uart_exit(void)
-{
-}
-
-module_init(alsa_mpu401_uart_init)
-module_exit(alsa_mpu401_uart_exit)
diff --git a/sound/drivers/opl3/opl3_lib.c b/sound/drivers/opl3/opl3_lib.c
index 1a5355b747ec..cf86c36c7c3b 100644
--- a/sound/drivers/opl3/opl3_lib.c
+++ b/sound/drivers/opl3/opl3_lib.c
@@ -538,19 +538,3 @@ int snd_opl3_hwdep_new(struct snd_opl3 * opl3,
 }
 
 EXPORT_SYMBOL(snd_opl3_hwdep_new);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_opl3_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_opl3_exit(void)
-{
-}
-
-module_init(alsa_opl3_init)
-module_exit(alsa_opl3_exit)
diff --git a/sound/drivers/opl4/opl4_lib.c b/sound/drivers/opl4/opl4_lib.c
index db76a5bf2bd2..819d2dce2a19 100644
--- a/sound/drivers/opl4/opl4_lib.c
+++ b/sound/drivers/opl4/opl4_lib.c
@@ -263,15 +263,3 @@ int snd_opl4_create(struct snd_card *card,
 }
 
 EXPORT_SYMBOL(snd_opl4_create);
-
-static int __init alsa_opl4_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_opl4_exit(void)
-{
-}
-
-module_init(alsa_opl4_init)
-module_exit(alsa_opl4_exit)
diff --git a/sound/drivers/vx/vx_core.c b/sound/drivers/vx/vx_core.c
index 121357397a6d..04368dd59a4c 100644
--- a/sound/drivers/vx/vx_core.c
+++ b/sound/drivers/vx/vx_core.c
@@ -815,18 +815,3 @@ struct vx_core *snd_vx_create(struct snd_card *card, struct snd_vx_hardware *hw,
 }
 
 EXPORT_SYMBOL(snd_vx_create);
-
-/*
- * module entries
- */
-static int __init alsa_vx_core_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_vx_core_exit(void)
-{
-}
-
-module_init(alsa_vx_core_init)
-module_exit(alsa_vx_core_exit)
-- 
cgit v1.2.3


From 498aaa9152eef3e101ec897f9c9b51662f700830 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 3 Aug 2018 15:44:15 +0200
Subject: ALSA: isa: Remove empty init and exit

For a sake of code simplification, remove the init and the exit
entries that do nothing.

Notes for readers: actually it's OK to remove *both* init and exit,
but not OK to remove the exit entry.  By removing only the exit while
keeping init, the module becomes permanently loaded; i.e. you cannot
unload it any longer!

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/isa/es1688/es1688_lib.c | 16 ----------------
 sound/isa/gus/gus_main.c      | 16 ----------------
 sound/isa/sb/sb16_csp.c       | 16 ----------------
 sound/isa/sb/sb16_main.c      | 16 ----------------
 sound/isa/sb/sb8_main.c       | 16 ----------------
 sound/isa/sb/sb_common.c      | 16 ----------------
 sound/isa/wss/wss_lib.c       | 16 ----------------
 7 files changed, 112 deletions(-)

diff --git a/sound/isa/es1688/es1688_lib.c b/sound/isa/es1688/es1688_lib.c
index f9c0662e9a22..50cdce0e8946 100644
--- a/sound/isa/es1688/es1688_lib.c
+++ b/sound/isa/es1688/es1688_lib.c
@@ -1029,19 +1029,3 @@ EXPORT_SYMBOL(snd_es1688_mixer_write);
 EXPORT_SYMBOL(snd_es1688_create);
 EXPORT_SYMBOL(snd_es1688_pcm);
 EXPORT_SYMBOL(snd_es1688_mixer);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_es1688_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_es1688_exit(void)
-{
-}
-
-module_init(alsa_es1688_init)
-module_exit(alsa_es1688_exit)
diff --git a/sound/isa/gus/gus_main.c b/sound/isa/gus/gus_main.c
index 3cf9b13c780a..3b8a0c880db5 100644
--- a/sound/isa/gus/gus_main.c
+++ b/sound/isa/gus/gus_main.c
@@ -465,19 +465,3 @@ EXPORT_SYMBOL(snd_gf1_mem_alloc);
 EXPORT_SYMBOL(snd_gf1_mem_xfree);
 EXPORT_SYMBOL(snd_gf1_mem_free);
 EXPORT_SYMBOL(snd_gf1_mem_lock);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_gus_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_gus_exit(void)
-{
-}
-
-module_init(alsa_gus_init)
-module_exit(alsa_gus_exit)
diff --git a/sound/isa/sb/sb16_csp.c b/sound/isa/sb/sb16_csp.c
index b9d67a7065cd..bf3db0d2ea12 100644
--- a/sound/isa/sb/sb16_csp.c
+++ b/sound/isa/sb/sb16_csp.c
@@ -1185,19 +1185,3 @@ static void info_read(struct snd_info_entry *entry, struct snd_info_buffer *buff
 /* */
 
 EXPORT_SYMBOL(snd_sb_csp_new);
-
-/*
- * INIT part
- */
-
-static int __init alsa_sb_csp_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb_csp_exit(void)
-{
-}
-
-module_init(alsa_sb_csp_init)
-module_exit(alsa_sb_csp_exit)
diff --git a/sound/isa/sb/sb16_main.c b/sound/isa/sb/sb16_main.c
index 11ed4a6e5bf1..37e6ce7b0b13 100644
--- a/sound/isa/sb/sb16_main.c
+++ b/sound/isa/sb/sb16_main.c
@@ -900,19 +900,3 @@ EXPORT_SYMBOL(snd_sb16dsp_pcm);
 EXPORT_SYMBOL(snd_sb16dsp_get_pcm_ops);
 EXPORT_SYMBOL(snd_sb16dsp_configure);
 EXPORT_SYMBOL(snd_sb16dsp_interrupt);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_sb16_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb16_exit(void)
-{
-}
-
-module_init(alsa_sb16_init)
-module_exit(alsa_sb16_exit)
diff --git a/sound/isa/sb/sb8_main.c b/sound/isa/sb/sb8_main.c
index 80e7dcaa551f..481797744b3c 100644
--- a/sound/isa/sb/sb8_main.c
+++ b/sound/isa/sb/sb8_main.c
@@ -621,19 +621,3 @@ EXPORT_SYMBOL(snd_sb8dsp_interrupt);
   /* sb8_midi.c */
 EXPORT_SYMBOL(snd_sb8dsp_midi_interrupt);
 EXPORT_SYMBOL(snd_sb8dsp_midi);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_sb8_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb8_exit(void)
-{
-}
-
-module_init(alsa_sb8_init)
-module_exit(alsa_sb8_exit)
diff --git a/sound/isa/sb/sb_common.c b/sound/isa/sb/sb_common.c
index 787a4ade4afd..90b254aaef74 100644
--- a/sound/isa/sb/sb_common.c
+++ b/sound/isa/sb/sb_common.c
@@ -305,19 +305,3 @@ EXPORT_SYMBOL(snd_sbmixer_add_ctl);
 EXPORT_SYMBOL(snd_sbmixer_suspend);
 EXPORT_SYMBOL(snd_sbmixer_resume);
 #endif
-
-/*
- *  INIT part
- */
-
-static int __init alsa_sb_common_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_sb_common_exit(void)
-{
-}
-
-module_init(alsa_sb_common_init)
-module_exit(alsa_sb_common_exit)
diff --git a/sound/isa/wss/wss_lib.c b/sound/isa/wss/wss_lib.c
index d23cc8abe1ef..32453f81b95a 100644
--- a/sound/isa/wss/wss_lib.c
+++ b/sound/isa/wss/wss_lib.c
@@ -2279,19 +2279,3 @@ const struct snd_pcm_ops *snd_wss_get_pcm_ops(int direction)
 		&snd_wss_playback_ops : &snd_wss_capture_ops;
 }
 EXPORT_SYMBOL(snd_wss_get_pcm_ops);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_wss_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_wss_exit(void)
-{
-}
-
-module_init(alsa_wss_init);
-module_exit(alsa_wss_exit);
-- 
cgit v1.2.3


From 3b23dc52da90c340c51273414f4e2d13e07e594c Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 3 Aug 2018 15:48:26 +0200
Subject: ALSA: i2c: Remove empty init and exit

For a sake of code simplification, remove the init and the exit
entries that do nothing.

Notes for readers: actually it's OK to remove *both* init and exit,
but not OK to remove the exit entry.  By removing only the exit while
keeping init, the module becomes permanently loaded; i.e. you cannot
unload it any longer!

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/i2c/cs8427.c            | 12 ------------
 sound/i2c/i2c.c               | 13 -------------
 sound/i2c/other/ak4xxx-adda.c | 12 ------------
 sound/i2c/tea6330t.c          | 16 ----------------
 4 files changed, 53 deletions(-)

diff --git a/sound/i2c/cs8427.c b/sound/i2c/cs8427.c
index 7e21621e492a..2647309bc675 100644
--- a/sound/i2c/cs8427.c
+++ b/sound/i2c/cs8427.c
@@ -621,15 +621,3 @@ int snd_cs8427_iec958_pcm(struct snd_i2c_device *cs8427, unsigned int rate)
 }
 
 EXPORT_SYMBOL(snd_cs8427_iec958_pcm);
-
-static int __init alsa_cs8427_module_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_cs8427_module_exit(void)
-{
-}
-
-module_init(alsa_cs8427_module_init)
-module_exit(alsa_cs8427_module_exit)
diff --git a/sound/i2c/i2c.c b/sound/i2c/i2c.c
index ef2a9afe9e19..c4a232f18a79 100644
--- a/sound/i2c/i2c.c
+++ b/sound/i2c/i2c.c
@@ -338,16 +338,3 @@ static int snd_i2c_bit_probeaddr(struct snd_i2c_bus *bus, unsigned short addr)
 	snd_i2c_bit_stop(bus);
 	return err;
 }
-
-
-static int __init alsa_i2c_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_i2c_exit(void)
-{
-}
-
-module_init(alsa_i2c_init)
-module_exit(alsa_i2c_exit)
diff --git a/sound/i2c/other/ak4xxx-adda.c b/sound/i2c/other/ak4xxx-adda.c
index bf377dc192aa..7f2761a2e7c8 100644
--- a/sound/i2c/other/ak4xxx-adda.c
+++ b/sound/i2c/other/ak4xxx-adda.c
@@ -911,15 +911,3 @@ int snd_akm4xxx_build_controls(struct snd_akm4xxx *ak)
 	return 0;
 }
 EXPORT_SYMBOL(snd_akm4xxx_build_controls);
-
-static int __init alsa_akm4xxx_module_init(void)
-{
-	return 0;
-}
-        
-static void __exit alsa_akm4xxx_module_exit(void)
-{
-}
-        
-module_init(alsa_akm4xxx_module_init)
-module_exit(alsa_akm4xxx_module_exit)
diff --git a/sound/i2c/tea6330t.c b/sound/i2c/tea6330t.c
index 2d22310dce05..239c4822427f 100644
--- a/sound/i2c/tea6330t.c
+++ b/sound/i2c/tea6330t.c
@@ -368,19 +368,3 @@ int snd_tea6330t_update_mixer(struct snd_card *card,
 
 EXPORT_SYMBOL(snd_tea6330t_detect);
 EXPORT_SYMBOL(snd_tea6330t_update_mixer);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_tea6330t_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_tea6330t_exit(void)
-{
-}
-
-module_init(alsa_tea6330t_init)
-module_exit(alsa_tea6330t_exit)
-- 
cgit v1.2.3


From a7da09fecf35cc1b328f0229c019757f6582f6bb Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 3 Aug 2018 15:48:41 +0200
Subject: ALSA: pci: Remove empty init and exit

For a sake of code simplification, remove the init and the exit
entries that do nothing.

Notes for readers: actually it's OK to remove *both* init and exit,
but not OK to remove the exit entry.  By removing only the exit while
keeping init, the module becomes permanently loaded; i.e. you cannot
unload it any longer!

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/ac97/ac97_codec.c | 16 ----------------
 sound/pci/ice1712/ak4xxx.c  | 12 ------------
 2 files changed, 28 deletions(-)

diff --git a/sound/pci/ac97/ac97_codec.c b/sound/pci/ac97/ac97_codec.c
index 1ef7cdf1d3e8..f4459d1a9d67 100644
--- a/sound/pci/ac97/ac97_codec.c
+++ b/sound/pci/ac97/ac97_codec.c
@@ -2941,19 +2941,3 @@ int snd_ac97_tune_hardware(struct snd_ac97 *ac97,
 }
 
 EXPORT_SYMBOL(snd_ac97_tune_hardware);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_ac97_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_ac97_exit(void)
-{
-}
-
-module_init(alsa_ac97_init)
-module_exit(alsa_ac97_exit)
diff --git a/sound/pci/ice1712/ak4xxx.c b/sound/pci/ice1712/ak4xxx.c
index 179ef7a5f0d1..a553897a4c4f 100644
--- a/sound/pci/ice1712/ak4xxx.c
+++ b/sound/pci/ice1712/ak4xxx.c
@@ -179,18 +179,6 @@ int snd_ice1712_akm4xxx_build_controls(struct snd_ice1712 *ice)
 	return 0;
 }
 
-static int __init alsa_ice1712_akm4xxx_module_init(void)
-{
-	return 0;
-}
-        
-static void __exit alsa_ice1712_akm4xxx_module_exit(void)
-{
-}
-        
-module_init(alsa_ice1712_akm4xxx_module_init)
-module_exit(alsa_ice1712_akm4xxx_module_exit)
-
 EXPORT_SYMBOL(snd_ice1712_akm4xxx_init);
 EXPORT_SYMBOL(snd_ice1712_akm4xxx_free);
 EXPORT_SYMBOL(snd_ice1712_akm4xxx_build_controls);
-- 
cgit v1.2.3


From c000c4f1d96534885bc7a8ef5185fd8c0de5e827 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Fri, 3 Aug 2018 15:48:54 +0200
Subject: ALSA: synth: Remove empty init and exit

For a sake of code simplification, remove the init and the exit
entries that do nothing.

Notes for readers: actually it's OK to remove *both* init and exit,
but not OK to remove the exit entry.  By removing only the exit while
keeping init, the module becomes permanently loaded; i.e. you cannot
unload it any longer!

Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/synth/emux/emux.c | 17 -----------------
 sound/synth/util_mem.c  | 16 ----------------
 2 files changed, 33 deletions(-)

diff --git a/sound/synth/emux/emux.c b/sound/synth/emux/emux.c
index b840ff2dcfbb..64f3141a3e1b 100644
--- a/sound/synth/emux/emux.c
+++ b/sound/synth/emux/emux.c
@@ -163,20 +163,3 @@ int snd_emux_free(struct snd_emux *emu)
 }
 
 EXPORT_SYMBOL(snd_emux_free);
-
-
-/*
- *  INIT part
- */
-
-static int __init alsa_emux_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_emux_exit(void)
-{
-}
-
-module_init(alsa_emux_init)
-module_exit(alsa_emux_exit)
diff --git a/sound/synth/util_mem.c b/sound/synth/util_mem.c
index 8e34bc4e07ec..4bd1e98200d2 100644
--- a/sound/synth/util_mem.c
+++ b/sound/synth/util_mem.c
@@ -193,19 +193,3 @@ EXPORT_SYMBOL(snd_util_mem_avail);
 EXPORT_SYMBOL(__snd_util_mem_alloc);
 EXPORT_SYMBOL(__snd_util_mem_free);
 EXPORT_SYMBOL(__snd_util_memblk_new);
-
-/*
- *  INIT part
- */
-
-static int __init alsa_util_mem_init(void)
-{
-	return 0;
-}
-
-static void __exit alsa_util_mem_exit(void)
-{
-}
-
-module_init(alsa_util_mem_init)
-module_exit(alsa_util_mem_exit)
-- 
cgit v1.2.3


From 1c82407aa302774b24bf619e56973aa97cbf25bd Mon Sep 17 00:00:00 2001
From: Houlong Wei <houlong.wei@mediatek.com>
Date: Wed, 25 Jul 2018 09:26:39 +0800
Subject: dt-bindings: soc: Add documentation for the MediaTek GCE unit

This adds documentation for the MediaTek Global Command Engine (GCE) unit
found in MT8173 SoCs.

Signed-off-by: Houlong Wei <houlong.wei@mediatek.com>
Signed-off-by: HS Liao <hs.liao@mediatek.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../devicetree/bindings/mailbox/mtk-gce.txt        | 57 ++++++++++++++++++++++
 include/dt-bindings/gce/mt8173-gce.h               | 44 +++++++++++++++++
 2 files changed, 101 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mailbox/mtk-gce.txt
 create mode 100644 include/dt-bindings/gce/mt8173-gce.h

diff --git a/Documentation/devicetree/bindings/mailbox/mtk-gce.txt b/Documentation/devicetree/bindings/mailbox/mtk-gce.txt
new file mode 100644
index 000000000000..7d72b21c9e94
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/mtk-gce.txt
@@ -0,0 +1,57 @@
+MediaTek GCE
+===============
+
+The Global Command Engine (GCE) is used to help read/write registers with
+critical time limitation, such as updating display configuration during the
+vblank. The GCE can be used to implement the Command Queue (CMDQ) driver.
+
+CMDQ driver uses mailbox framework for communication. Please refer to
+mailbox.txt for generic information about mailbox device-tree bindings.
+
+Required properties:
+- compatible: Must be "mediatek,mt8173-gce"
+- reg: Address range of the GCE unit
+- interrupts: The interrupt signal from the GCE block
+- clock: Clocks according to the common clock binding
+- clock-names: Must be "gce" to stand for GCE clock
+- #mbox-cells: Should be 3.
+	<&phandle channel priority atomic_exec>
+	phandle: Label name of a gce node.
+	channel: Channel of mailbox. Be equal to the thread id of GCE.
+	priority: Priority of GCE thread.
+	atomic_exec: GCE processing continuous packets of commands in atomic
+		way.
+
+Required properties for a client device:
+- mboxes: Client use mailbox to communicate with GCE, it should have this
+  property and list of phandle, mailbox specifiers.
+- mediatek,gce-subsys: u32, specify the sub-system id which is corresponding
+  to the register address.
+
+Some vaules of properties are defined in 'dt-bindings/gce/mt8173-gce.h'. Such as
+sub-system ids, thread priority, event ids.
+
+Example:
+
+	gce: gce@10212000 {
+		compatible = "mediatek,mt8173-gce";
+		reg = <0 0x10212000 0 0x1000>;
+		interrupts = <GIC_SPI 135 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&infracfg CLK_INFRA_GCE>;
+		clock-names = "gce";
+		thread-num = CMDQ_THR_MAX_COUNT;
+		#mbox-cells = <3>;
+	};
+
+Example for a client device:
+
+	mmsys: clock-controller@14000000 {
+		compatible = "mediatek,mt8173-mmsys";
+		mboxes = <&gce 0 CMDQ_THR_PRIO_LOWEST 1>,
+			 <&gce 1 CMDQ_THR_PRIO_LOWEST 1>;
+		mediatek,gce-subsys = <SUBSYS_1400XXXX>;
+		mutex-event-eof = <CMDQ_EVENT_MUTEX0_STREAM_EOF
+				CMDQ_EVENT_MUTEX1_STREAM_EOF>;
+
+		...
+	};
diff --git a/include/dt-bindings/gce/mt8173-gce.h b/include/dt-bindings/gce/mt8173-gce.h
new file mode 100644
index 000000000000..ffcf94ba96c6
--- /dev/null
+++ b/include/dt-bindings/gce/mt8173-gce.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 MediaTek Inc.
+ * Author: Houlong Wei <houlong.wei@mediatek.com>
+ *
+ */
+
+#ifndef _DT_BINDINGS_GCE_MT8173_H
+#define _DT_BINDINGS_GCE_MT8173_H
+
+/* GCE HW thread priority */
+#define CMDQ_THR_PRIO_LOWEST	0
+#define CMDQ_THR_PRIO_HIGHEST	1
+
+/* GCE SUBSYS */
+#define SUBSYS_1400XXXX		1
+#define SUBSYS_1401XXXX		2
+#define SUBSYS_1402XXXX		3
+
+/* GCE HW EVENT */
+#define CMDQ_EVENT_DISP_OVL0_SOF		11
+#define CMDQ_EVENT_DISP_OVL1_SOF		12
+#define CMDQ_EVENT_DISP_RDMA0_SOF		13
+#define CMDQ_EVENT_DISP_RDMA1_SOF		14
+#define CMDQ_EVENT_DISP_RDMA2_SOF		15
+#define CMDQ_EVENT_DISP_WDMA0_SOF		16
+#define CMDQ_EVENT_DISP_WDMA1_SOF		17
+#define CMDQ_EVENT_DISP_OVL0_EOF		39
+#define CMDQ_EVENT_DISP_OVL1_EOF		40
+#define CMDQ_EVENT_DISP_RDMA0_EOF		41
+#define CMDQ_EVENT_DISP_RDMA1_EOF		42
+#define CMDQ_EVENT_DISP_RDMA2_EOF		43
+#define CMDQ_EVENT_DISP_WDMA0_EOF		44
+#define CMDQ_EVENT_DISP_WDMA1_EOF		45
+#define CMDQ_EVENT_MUTEX0_STREAM_EOF		53
+#define CMDQ_EVENT_MUTEX1_STREAM_EOF		54
+#define CMDQ_EVENT_MUTEX2_STREAM_EOF		55
+#define CMDQ_EVENT_MUTEX3_STREAM_EOF		56
+#define CMDQ_EVENT_MUTEX4_STREAM_EOF		57
+#define CMDQ_EVENT_DISP_RDMA0_UNDERRUN		63
+#define CMDQ_EVENT_DISP_RDMA1_UNDERRUN		64
+#define CMDQ_EVENT_DISP_RDMA2_UNDERRUN		65
+
+#endif
-- 
cgit v1.2.3


From 623a6143a845bd485b00ba684f0ccef11835edab Mon Sep 17 00:00:00 2001
From: Houlong Wei <houlong.wei@mediatek.com>
Date: Wed, 25 Jul 2018 09:26:40 +0800
Subject: mailbox: mediatek: Add Mediatek CMDQ driver

This patch is first version of Mediatek Command Queue(CMDQ) driver. The
CMDQ is used to help write registers with critical time limitation,
such as updating display configuration during the vblank. It controls
Global Command Engine (GCE) hardware to achieve this requirement.
Currently, CMDQ only supports display related hardwares, but we expect
it can be extended to other hardwares for future requirements.

Signed-off-by: Houlong Wei <houlong.wei@mediatek.com>
Signed-off-by: HS Liao <hs.liao@mediatek.com>
Signed-off-by: CK Hu <ck.hu@mediatek.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/Kconfig                  |  10 +
 drivers/mailbox/Makefile                 |   2 +
 drivers/mailbox/mtk-cmdq-mailbox.c       | 569 +++++++++++++++++++++++++++++++
 include/linux/mailbox/mtk-cmdq-mailbox.h |  77 +++++
 4 files changed, 658 insertions(+)
 create mode 100644 drivers/mailbox/mtk-cmdq-mailbox.c
 create mode 100644 include/linux/mailbox/mtk-cmdq-mailbox.h

diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index e63d29a95e76..2bbabc907add 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -189,4 +189,14 @@ config STM32_IPCC
 	  Mailbox implementation for STMicroelectonics STM32 family chips
 	  with hardware for Inter-Processor Communication Controller (IPCC)
 	  between processors. Say Y here if you want to have this support.
+
+config MTK_CMDQ_MBOX
+	tristate "MediaTek CMDQ Mailbox Support"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	select MTK_INFRACFG
+	help
+	  Say yes here to add support for the MediaTek Command Queue (CMDQ)
+	  mailbox driver. The CMDQ is used to help read/write registers with
+	  critical time limitation, such as updating display configuration
+	  during the vblank.
 endif
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 4d501bea7863..4b0080480661 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -40,3 +40,5 @@ obj-$(CONFIG_QCOM_APCS_IPC)	+= qcom-apcs-ipc-mailbox.o
 obj-$(CONFIG_TEGRA_HSP_MBOX)	+= tegra-hsp.o
 
 obj-$(CONFIG_STM32_IPCC) 	+= stm32-ipcc.o
+
+obj-$(CONFIG_MTK_CMDQ_MBOX)	+= mtk-cmdq-mailbox.o
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
new file mode 100644
index 000000000000..6f92c5ee12f7
--- /dev/null
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -0,0 +1,569 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2018 MediaTek Inc.
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/dma-mapping.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/mailbox_controller.h>
+#include <linux/mailbox/mtk-cmdq-mailbox.h>
+#include <linux/of_device.h>
+
+#define CMDQ_OP_CODE_MASK		(0xff << CMDQ_OP_CODE_SHIFT)
+#define CMDQ_IRQ_MASK			0xffff
+#define CMDQ_NUM_CMD(t)			(t->cmd_buf_size / CMDQ_INST_SIZE)
+
+#define CMDQ_CURR_IRQ_STATUS		0x10
+#define CMDQ_THR_SLOT_CYCLES		0x30
+#define CMDQ_THR_BASE			0x100
+#define CMDQ_THR_SIZE			0x80
+#define CMDQ_THR_WARM_RESET		0x00
+#define CMDQ_THR_ENABLE_TASK		0x04
+#define CMDQ_THR_SUSPEND_TASK		0x08
+#define CMDQ_THR_CURR_STATUS		0x0c
+#define CMDQ_THR_IRQ_STATUS		0x10
+#define CMDQ_THR_IRQ_ENABLE		0x14
+#define CMDQ_THR_CURR_ADDR		0x20
+#define CMDQ_THR_END_ADDR		0x24
+#define CMDQ_THR_WAIT_TOKEN		0x30
+#define CMDQ_THR_PRIORITY		0x40
+
+#define CMDQ_THR_ACTIVE_SLOT_CYCLES	0x3200
+#define CMDQ_THR_ENABLED		0x1
+#define CMDQ_THR_DISABLED		0x0
+#define CMDQ_THR_SUSPEND		0x1
+#define CMDQ_THR_RESUME			0x0
+#define CMDQ_THR_STATUS_SUSPENDED	BIT(1)
+#define CMDQ_THR_DO_WARM_RESET		BIT(0)
+#define CMDQ_THR_IRQ_DONE		0x1
+#define CMDQ_THR_IRQ_ERROR		0x12
+#define CMDQ_THR_IRQ_EN			(CMDQ_THR_IRQ_ERROR | CMDQ_THR_IRQ_DONE)
+#define CMDQ_THR_IS_WAITING		BIT(31)
+
+#define CMDQ_JUMP_BY_OFFSET		0x10000000
+#define CMDQ_JUMP_BY_PA			0x10000001
+
+struct cmdq_thread {
+	struct mbox_chan	*chan;
+	void __iomem		*base;
+	struct list_head	task_busy_list;
+	u32			priority;
+	bool			atomic_exec;
+};
+
+struct cmdq_task {
+	struct cmdq		*cmdq;
+	struct list_head	list_entry;
+	dma_addr_t		pa_base;
+	struct cmdq_thread	*thread;
+	struct cmdq_pkt		*pkt; /* the packet sent from mailbox client */
+};
+
+struct cmdq {
+	struct mbox_controller	mbox;
+	void __iomem		*base;
+	u32			irq;
+	u32			thread_nr;
+	struct cmdq_thread	*thread;
+	struct clk		*clock;
+	bool			suspended;
+};
+
+static int cmdq_thread_suspend(struct cmdq *cmdq, struct cmdq_thread *thread)
+{
+	u32 status;
+
+	writel(CMDQ_THR_SUSPEND, thread->base + CMDQ_THR_SUSPEND_TASK);
+
+	/* If already disabled, treat as suspended successful. */
+	if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED))
+		return 0;
+
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_STATUS,
+			status, status & CMDQ_THR_STATUS_SUSPENDED, 0, 10)) {
+		dev_err(cmdq->mbox.dev, "suspend GCE thread 0x%x failed\n",
+			(u32)(thread->base - cmdq->base));
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static void cmdq_thread_resume(struct cmdq_thread *thread)
+{
+	writel(CMDQ_THR_RESUME, thread->base + CMDQ_THR_SUSPEND_TASK);
+}
+
+static void cmdq_init(struct cmdq *cmdq)
+{
+	WARN_ON(clk_enable(cmdq->clock) < 0);
+	writel(CMDQ_THR_ACTIVE_SLOT_CYCLES, cmdq->base + CMDQ_THR_SLOT_CYCLES);
+	clk_disable(cmdq->clock);
+}
+
+static int cmdq_thread_reset(struct cmdq *cmdq, struct cmdq_thread *thread)
+{
+	u32 warm_reset;
+
+	writel(CMDQ_THR_DO_WARM_RESET, thread->base + CMDQ_THR_WARM_RESET);
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_WARM_RESET,
+			warm_reset, !(warm_reset & CMDQ_THR_DO_WARM_RESET),
+			0, 10)) {
+		dev_err(cmdq->mbox.dev, "reset GCE thread 0x%x failed\n",
+			(u32)(thread->base - cmdq->base));
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+static void cmdq_thread_disable(struct cmdq *cmdq, struct cmdq_thread *thread)
+{
+	cmdq_thread_reset(cmdq, thread);
+	writel(CMDQ_THR_DISABLED, thread->base + CMDQ_THR_ENABLE_TASK);
+}
+
+/* notify GCE to re-fetch commands by setting GCE thread PC */
+static void cmdq_thread_invalidate_fetched_data(struct cmdq_thread *thread)
+{
+	writel(readl(thread->base + CMDQ_THR_CURR_ADDR),
+	       thread->base + CMDQ_THR_CURR_ADDR);
+}
+
+static void cmdq_task_insert_into_thread(struct cmdq_task *task)
+{
+	struct device *dev = task->cmdq->mbox.dev;
+	struct cmdq_thread *thread = task->thread;
+	struct cmdq_task *prev_task = list_last_entry(
+			&thread->task_busy_list, typeof(*task), list_entry);
+	u64 *prev_task_base = prev_task->pkt->va_base;
+
+	/* let previous task jump to this task */
+	dma_sync_single_for_cpu(dev, prev_task->pa_base,
+				prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE);
+	prev_task_base[CMDQ_NUM_CMD(prev_task->pkt) - 1] =
+		(u64)CMDQ_JUMP_BY_PA << 32 | task->pa_base;
+	dma_sync_single_for_device(dev, prev_task->pa_base,
+				   prev_task->pkt->cmd_buf_size, DMA_TO_DEVICE);
+
+	cmdq_thread_invalidate_fetched_data(thread);
+}
+
+static bool cmdq_command_is_wfe(u64 cmd)
+{
+	u64 wfe_option = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE;
+	u64 wfe_op = (u64)(CMDQ_CODE_WFE << CMDQ_OP_CODE_SHIFT) << 32;
+	u64 wfe_mask = (u64)CMDQ_OP_CODE_MASK << 32 | 0xffffffff;
+
+	return ((cmd & wfe_mask) == (wfe_op | wfe_option));
+}
+
+/* we assume tasks in the same display GCE thread are waiting the same event. */
+static void cmdq_task_remove_wfe(struct cmdq_task *task)
+{
+	struct device *dev = task->cmdq->mbox.dev;
+	u64 *base = task->pkt->va_base;
+	int i;
+
+	dma_sync_single_for_cpu(dev, task->pa_base, task->pkt->cmd_buf_size,
+				DMA_TO_DEVICE);
+	for (i = 0; i < CMDQ_NUM_CMD(task->pkt); i++)
+		if (cmdq_command_is_wfe(base[i]))
+			base[i] = (u64)CMDQ_JUMP_BY_OFFSET << 32 |
+				  CMDQ_JUMP_PASS;
+	dma_sync_single_for_device(dev, task->pa_base, task->pkt->cmd_buf_size,
+				   DMA_TO_DEVICE);
+}
+
+static bool cmdq_thread_is_in_wfe(struct cmdq_thread *thread)
+{
+	return readl(thread->base + CMDQ_THR_WAIT_TOKEN) & CMDQ_THR_IS_WAITING;
+}
+
+static void cmdq_thread_wait_end(struct cmdq_thread *thread,
+				 unsigned long end_pa)
+{
+	struct device *dev = thread->chan->mbox->dev;
+	unsigned long curr_pa;
+
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_ADDR,
+			curr_pa, curr_pa == end_pa, 1, 20))
+		dev_err(dev, "GCE thread cannot run to end.\n");
+}
+
+static void cmdq_task_exec_done(struct cmdq_task *task, enum cmdq_cb_status sta)
+{
+	struct cmdq_task_cb *cb = &task->pkt->async_cb;
+	struct cmdq_cb_data data;
+
+	WARN_ON(cb->cb == (cmdq_async_flush_cb)NULL);
+	data.sta = sta;
+	data.data = cb->data;
+	cb->cb(data);
+
+	list_del(&task->list_entry);
+}
+
+static void cmdq_task_handle_error(struct cmdq_task *task)
+{
+	struct cmdq_thread *thread = task->thread;
+	struct cmdq_task *next_task;
+
+	dev_err(task->cmdq->mbox.dev, "task 0x%p error\n", task);
+	WARN_ON(cmdq_thread_suspend(task->cmdq, thread) < 0);
+	next_task = list_first_entry_or_null(&thread->task_busy_list,
+			struct cmdq_task, list_entry);
+	if (next_task)
+		writel(next_task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
+	cmdq_thread_resume(thread);
+}
+
+static void cmdq_thread_irq_handler(struct cmdq *cmdq,
+				    struct cmdq_thread *thread)
+{
+	struct cmdq_task *task, *tmp, *curr_task = NULL;
+	u32 curr_pa, irq_flag, task_end_pa;
+	bool err;
+
+	irq_flag = readl(thread->base + CMDQ_THR_IRQ_STATUS);
+	writel(~irq_flag, thread->base + CMDQ_THR_IRQ_STATUS);
+
+	/*
+	 * When ISR call this function, another CPU core could run
+	 * "release task" right before we acquire the spin lock, and thus
+	 * reset / disable this GCE thread, so we need to check the enable
+	 * bit of this GCE thread.
+	 */
+	if (!(readl(thread->base + CMDQ_THR_ENABLE_TASK) & CMDQ_THR_ENABLED))
+		return;
+
+	if (irq_flag & CMDQ_THR_IRQ_ERROR)
+		err = true;
+	else if (irq_flag & CMDQ_THR_IRQ_DONE)
+		err = false;
+	else
+		return;
+
+	curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
+
+	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
+				 list_entry) {
+		task_end_pa = task->pa_base + task->pkt->cmd_buf_size;
+		if (curr_pa >= task->pa_base && curr_pa < task_end_pa)
+			curr_task = task;
+
+		if (!curr_task || curr_pa == task_end_pa - CMDQ_INST_SIZE) {
+			cmdq_task_exec_done(task, CMDQ_CB_NORMAL);
+			kfree(task);
+		} else if (err) {
+			cmdq_task_exec_done(task, CMDQ_CB_ERROR);
+			cmdq_task_handle_error(curr_task);
+			kfree(task);
+		}
+
+		if (curr_task)
+			break;
+	}
+
+	if (list_empty(&thread->task_busy_list)) {
+		cmdq_thread_disable(cmdq, thread);
+		clk_disable(cmdq->clock);
+	}
+}
+
+static irqreturn_t cmdq_irq_handler(int irq, void *dev)
+{
+	struct cmdq *cmdq = dev;
+	unsigned long irq_status, flags = 0L;
+	int bit;
+
+	irq_status = readl(cmdq->base + CMDQ_CURR_IRQ_STATUS) & CMDQ_IRQ_MASK;
+	if (!(irq_status ^ CMDQ_IRQ_MASK))
+		return IRQ_NONE;
+
+	for_each_clear_bit(bit, &irq_status, fls(CMDQ_IRQ_MASK)) {
+		struct cmdq_thread *thread = &cmdq->thread[bit];
+
+		spin_lock_irqsave(&thread->chan->lock, flags);
+		cmdq_thread_irq_handler(cmdq, thread);
+		spin_unlock_irqrestore(&thread->chan->lock, flags);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int cmdq_suspend(struct device *dev)
+{
+	struct cmdq *cmdq = dev_get_drvdata(dev);
+	struct cmdq_thread *thread;
+	int i;
+	bool task_running = false;
+
+	cmdq->suspended = true;
+
+	for (i = 0; i < cmdq->thread_nr; i++) {
+		thread = &cmdq->thread[i];
+		if (!list_empty(&thread->task_busy_list)) {
+			task_running = true;
+			break;
+		}
+	}
+
+	if (task_running)
+		dev_warn(dev, "exist running task(s) in suspend\n");
+
+	clk_unprepare(cmdq->clock);
+
+	return 0;
+}
+
+static int cmdq_resume(struct device *dev)
+{
+	struct cmdq *cmdq = dev_get_drvdata(dev);
+
+	WARN_ON(clk_prepare(cmdq->clock) < 0);
+	cmdq->suspended = false;
+	return 0;
+}
+
+static int cmdq_remove(struct platform_device *pdev)
+{
+	struct cmdq *cmdq = platform_get_drvdata(pdev);
+
+	mbox_controller_unregister(&cmdq->mbox);
+	clk_unprepare(cmdq->clock);
+
+	if (cmdq->mbox.chans)
+		devm_kfree(&pdev->dev, cmdq->mbox.chans);
+
+	if (cmdq->thread)
+		devm_kfree(&pdev->dev, cmdq->thread);
+
+	devm_kfree(&pdev->dev, cmdq);
+
+	return 0;
+}
+
+static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
+{
+	struct cmdq_pkt *pkt = (struct cmdq_pkt *)data;
+	struct cmdq_thread *thread = (struct cmdq_thread *)chan->con_priv;
+	struct cmdq *cmdq = dev_get_drvdata(chan->mbox->dev);
+	struct cmdq_task *task;
+	unsigned long curr_pa, end_pa;
+
+	/* Client should not flush new tasks if suspended. */
+	WARN_ON(cmdq->suspended);
+
+	task = kzalloc(sizeof(*task), GFP_ATOMIC);
+	task->cmdq = cmdq;
+	INIT_LIST_HEAD(&task->list_entry);
+	task->pa_base = pkt->pa_base;
+	task->thread = thread;
+	task->pkt = pkt;
+
+	if (list_empty(&thread->task_busy_list)) {
+		WARN_ON(clk_enable(cmdq->clock) < 0);
+		WARN_ON(cmdq_thread_reset(cmdq, thread) < 0);
+
+		writel(task->pa_base, thread->base + CMDQ_THR_CURR_ADDR);
+		writel(task->pa_base + pkt->cmd_buf_size,
+		       thread->base + CMDQ_THR_END_ADDR);
+		writel(thread->priority, thread->base + CMDQ_THR_PRIORITY);
+		writel(CMDQ_THR_IRQ_EN, thread->base + CMDQ_THR_IRQ_ENABLE);
+		writel(CMDQ_THR_ENABLED, thread->base + CMDQ_THR_ENABLE_TASK);
+	} else {
+		WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
+		curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
+		end_pa = readl(thread->base + CMDQ_THR_END_ADDR);
+
+		/*
+		 * Atomic execution should remove the following wfe, i.e. only
+		 * wait event at first task, and prevent to pause when running.
+		 */
+		if (thread->atomic_exec) {
+			/* GCE is executing if command is not WFE */
+			if (!cmdq_thread_is_in_wfe(thread)) {
+				cmdq_thread_resume(thread);
+				cmdq_thread_wait_end(thread, end_pa);
+				WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
+				/* set to this task directly */
+				writel(task->pa_base,
+				       thread->base + CMDQ_THR_CURR_ADDR);
+			} else {
+				cmdq_task_insert_into_thread(task);
+				cmdq_task_remove_wfe(task);
+				smp_mb(); /* modify jump before enable thread */
+			}
+		} else {
+			/* check boundary */
+			if (curr_pa == end_pa - CMDQ_INST_SIZE ||
+			    curr_pa == end_pa) {
+				/* set to this task directly */
+				writel(task->pa_base,
+				       thread->base + CMDQ_THR_CURR_ADDR);
+			} else {
+				cmdq_task_insert_into_thread(task);
+				smp_mb(); /* modify jump before enable thread */
+			}
+		}
+		writel(task->pa_base + pkt->cmd_buf_size,
+		       thread->base + CMDQ_THR_END_ADDR);
+		cmdq_thread_resume(thread);
+	}
+	list_move_tail(&task->list_entry, &thread->task_busy_list);
+
+	return 0;
+}
+
+static int cmdq_mbox_startup(struct mbox_chan *chan)
+{
+	return 0;
+}
+
+static void cmdq_mbox_shutdown(struct mbox_chan *chan)
+{
+}
+
+static const struct mbox_chan_ops cmdq_mbox_chan_ops = {
+	.send_data = cmdq_mbox_send_data,
+	.startup = cmdq_mbox_startup,
+	.shutdown = cmdq_mbox_shutdown,
+};
+
+static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
+		const struct of_phandle_args *sp)
+{
+	int ind = sp->args[0];
+	struct cmdq_thread *thread;
+
+	if (ind >= mbox->num_chans)
+		return ERR_PTR(-EINVAL);
+
+	thread = (struct cmdq_thread *)mbox->chans[ind].con_priv;
+	thread->priority = sp->args[1];
+	thread->atomic_exec = (sp->args[2] != 0);
+	thread->chan = &mbox->chans[ind];
+
+	return &mbox->chans[ind];
+}
+
+static int cmdq_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *res;
+	struct cmdq *cmdq;
+	int err, i;
+
+	cmdq = devm_kzalloc(dev, sizeof(*cmdq), GFP_KERNEL);
+	if (!cmdq)
+		return -ENOMEM;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	cmdq->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(cmdq->base)) {
+		dev_err(dev, "failed to ioremap gce\n");
+		return PTR_ERR(cmdq->base);
+	}
+
+	cmdq->irq = platform_get_irq(pdev, 0);
+	if (!cmdq->irq) {
+		dev_err(dev, "failed to get irq\n");
+		return -EINVAL;
+	}
+	err = devm_request_irq(dev, cmdq->irq, cmdq_irq_handler, IRQF_SHARED,
+			       "mtk_cmdq", cmdq);
+	if (err < 0) {
+		dev_err(dev, "failed to register ISR (%d)\n", err);
+		return err;
+	}
+
+	dev_dbg(dev, "cmdq device: addr:0x%p, va:0x%p, irq:%d\n",
+		dev, cmdq->base, cmdq->irq);
+
+	cmdq->clock = devm_clk_get(dev, "gce");
+	if (IS_ERR(cmdq->clock)) {
+		dev_err(dev, "failed to get gce clk\n");
+		return PTR_ERR(cmdq->clock);
+	}
+
+	cmdq->thread_nr = (u32)(unsigned long)of_device_get_match_data(dev);
+	cmdq->mbox.dev = dev;
+	cmdq->mbox.chans = devm_kcalloc(dev, cmdq->thread_nr,
+					sizeof(*cmdq->mbox.chans), GFP_KERNEL);
+	if (!cmdq->mbox.chans)
+		return -ENOMEM;
+
+	cmdq->mbox.num_chans = cmdq->thread_nr;
+	cmdq->mbox.ops = &cmdq_mbox_chan_ops;
+	cmdq->mbox.of_xlate = cmdq_xlate;
+
+	/* make use of TXDONE_BY_ACK */
+	cmdq->mbox.txdone_irq = false;
+	cmdq->mbox.txdone_poll = false;
+
+	cmdq->thread = devm_kcalloc(dev, cmdq->thread_nr,
+					sizeof(*cmdq->thread), GFP_KERNEL);
+	if (!cmdq->thread)
+		return -ENOMEM;
+
+	for (i = 0; i < cmdq->thread_nr; i++) {
+		cmdq->thread[i].base = cmdq->base + CMDQ_THR_BASE +
+				CMDQ_THR_SIZE * i;
+		INIT_LIST_HEAD(&cmdq->thread[i].task_busy_list);
+		cmdq->mbox.chans[i].con_priv = (void *)&cmdq->thread[i];
+	}
+
+	err = mbox_controller_register(&cmdq->mbox);
+	if (err < 0) {
+		dev_err(dev, "failed to register mailbox: %d\n", err);
+		return err;
+	}
+
+	platform_set_drvdata(pdev, cmdq);
+	WARN_ON(clk_prepare(cmdq->clock) < 0);
+
+	cmdq_init(cmdq);
+
+	return 0;
+}
+
+static const struct dev_pm_ops cmdq_pm_ops = {
+	.suspend = cmdq_suspend,
+	.resume = cmdq_resume,
+};
+
+static const struct of_device_id cmdq_of_ids[] = {
+	{.compatible = "mediatek,mt8173-gce", .data = (void *)16},
+	{}
+};
+
+static struct platform_driver cmdq_drv = {
+	.probe = cmdq_probe,
+	.remove = cmdq_remove,
+	.driver = {
+		.name = "mtk_cmdq",
+		.pm = &cmdq_pm_ops,
+		.of_match_table = cmdq_of_ids,
+	}
+};
+
+static int __init cmdq_drv_init(void)
+{
+	return platform_driver_register(&cmdq_drv);
+}
+
+static void __exit cmdq_drv_exit(void)
+{
+	platform_driver_unregister(&cmdq_drv);
+}
+
+subsys_initcall(cmdq_drv_init);
+module_exit(cmdq_drv_exit);
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
new file mode 100644
index 000000000000..ccb73422c2fa
--- /dev/null
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2018 MediaTek Inc.
+ *
+ */
+
+#ifndef __MTK_CMDQ_MAILBOX_H__
+#define __MTK_CMDQ_MAILBOX_H__
+
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#define CMDQ_INST_SIZE			8 /* instruction is 64-bit */
+#define CMDQ_SUBSYS_SHIFT		16
+#define CMDQ_OP_CODE_SHIFT		24
+#define CMDQ_JUMP_PASS			CMDQ_INST_SIZE
+
+#define CMDQ_WFE_UPDATE			BIT(31)
+#define CMDQ_WFE_WAIT			BIT(15)
+#define CMDQ_WFE_WAIT_VALUE		0x1
+
+/*
+ * CMDQ_CODE_MASK:
+ *   set write mask
+ *   format: op mask
+ * CMDQ_CODE_WRITE:
+ *   write value into target register
+ *   format: op subsys address value
+ * CMDQ_CODE_JUMP:
+ *   jump by offset
+ *   format: op offset
+ * CMDQ_CODE_WFE:
+ *   wait for event and clear
+ *   it is just clear if no wait
+ *   format: [wait]  op event update:1 to_wait:1 wait:1
+ *           [clear] op event update:1 to_wait:0 wait:0
+ * CMDQ_CODE_EOC:
+ *   end of command
+ *   format: op irq_flag
+ */
+enum cmdq_code {
+	CMDQ_CODE_MASK = 0x02,
+	CMDQ_CODE_WRITE = 0x04,
+	CMDQ_CODE_JUMP = 0x10,
+	CMDQ_CODE_WFE = 0x20,
+	CMDQ_CODE_EOC = 0x40,
+};
+
+enum cmdq_cb_status {
+	CMDQ_CB_NORMAL = 0,
+	CMDQ_CB_ERROR
+};
+
+struct cmdq_cb_data {
+	enum cmdq_cb_status	sta;
+	void			*data;
+};
+
+typedef void (*cmdq_async_flush_cb)(struct cmdq_cb_data data);
+
+struct cmdq_task_cb {
+	cmdq_async_flush_cb	cb;
+	void			*data;
+};
+
+struct cmdq_pkt {
+	void			*va_base;
+	dma_addr_t		pa_base;
+	size_t			cmd_buf_size; /* command occupied size */
+	size_t			buf_size; /* real buffer size */
+	struct cmdq_task_cb	cb;
+	struct cmdq_task_cb	async_cb;
+	void			*cl;
+};
+
+#endif /* __MTK_CMDQ_MAILBOX_H__ */
-- 
cgit v1.2.3


From 8530ebf1079ccc84ffa32d970cdcae168b2f3684 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 08:42:11 -0500
Subject: ASoC: smd845: fix memory leak

In case memory resources for *card* were allocated, release them before
return.

Addresses-Coverity-ID: 1472244 ("Resource leak")
Fixes: 6b1687bf76ef ("ASoC: qcom: add sdm845 sound card support")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/sdm845.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index be0cb1122036..c1adb77230eb 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -222,8 +222,10 @@ static int sdm845_snd_platform_probe(struct platform_device *pdev)
 
 	/* Allocate the private data */
 	data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return -ENOMEM;
+	if (!data) {
+		ret = -ENOMEM;
+		goto data_alloc_fail;
+	}
 
 	card->dev = dev;
 	dev_set_drvdata(dev, card);
@@ -248,6 +250,7 @@ register_card_fail:
 	kfree(card->dai_link);
 parse_dt_fail:
 	kfree(data);
+data_alloc_fail:
 	kfree(card);
 	return ret;
 }
-- 
cgit v1.2.3


From 01dc285d5cd89b77686d8baef8482c58d7dc3ead Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Wed, 1 Aug 2018 10:48:23 -0400
Subject: drm/amd/display: Report non-DP display as disconnected without EDID

[Why]
Some boards seem to have a problem where HPD is high on HDMI even though
no display is connected. We don't want to report these as connected. DP
spec still requires us to report DP displays as connected when HPD is
high but we can't read the EDID in order to go to fail-safe mode.

[How]
If connector_signal is not DP abort detection if we can't retrieve the
EDID.

v2: Add Bugzilla and stable

Bugzilla: https://bugs.freedesktop.org/107390
Bugzilla: https://bugs.freedesktop.org/106846
Cc: stable@vger.kernel.org
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 966d2f9c8c99..31cebb645fca 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -744,6 +744,17 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 			break;
 		case EDID_NO_RESPONSE:
 			DC_LOG_ERROR("No EDID read.\n");
+
+			/*
+			 * Abort detection for non-DP connectors if we have
+			 * no EDID
+			 *
+			 * DP needs to report as connected if HDP is high
+			 * even if we have no EDID in order to go to
+			 * fail-safe mode
+			 */
+			if (!dc_is_dp_signal(link->connector_signal))
+				return false;
 		default:
 			break;
 		}
-- 
cgit v1.2.3


From 16196776185cb19bb8c2318ebd1dbbefb5350d6a Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Thu, 2 Aug 2018 15:32:01 -0400
Subject: drm/amd/display: Only require EDID read for HDMI and DVI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

[Why]
VGA sometimes has trouble retrieving the EDID on very long cables, KVM
switches, or old displays.

[How]
Only require EDID read for HDMI and DVI and exempt other types (DP,
VGA). We currently don't support VGA but if anyone adds support in the
future this might get overlooked.

Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Suggested-by: Michel Dänzer <michel@daenzer.net>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 31cebb645fca..89d7c1e99168 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -753,7 +753,8 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 			 * even if we have no EDID in order to go to
 			 * fail-safe mode
 			 */
-			if (!dc_is_dp_signal(link->connector_signal))
+			if (dc_is_hdmi_signal(link->connector_signal) ||
+			    dc_is_dvi_signal(link->connector_signal))
 				return false;
 		default:
 			break;
-- 
cgit v1.2.3


From 1f31c98d650ca342e2f54cb17c4554ad110c5a11 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Wed, 1 Aug 2018 15:50:27 -0700
Subject: xfs: only validate summary counts on primary superblock

Skip the summary counter checks for secondary superblocks and inprogress
primary superblocks because mkfs has always written those out with
zeroed summary counters.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
---
 fs/xfs/libxfs/xfs_sb.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index ca1b3a7a9171..081f46e30556 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -148,6 +148,7 @@ xfs_validate_sb_read(
 STATIC int
 xfs_validate_sb_write(
 	struct xfs_mount	*mp,
+	struct xfs_buf		*bp,
 	struct xfs_sb		*sbp)
 {
 	/*
@@ -155,10 +156,15 @@ xfs_validate_sb_write(
 	 * the superblock.  We skip this in the read validator because there
 	 * could be newer superblocks in the log and if the values are garbage
 	 * even after replay we'll recalculate them at the end of log mount.
+	 *
+	 * mkfs has traditionally written zeroed counters to inprogress and
+	 * secondary superblocks, so allow this usage to continue because
+	 * we never read counters from such superblocks.
 	 */
-	if (sbp->sb_fdblocks > sbp->sb_dblocks ||
-	    !xfs_verify_icount(mp, sbp->sb_icount) ||
-	    sbp->sb_ifree > sbp->sb_icount) {
+	if (XFS_BUF_ADDR(bp) == XFS_SB_DADDR && !sbp->sb_inprogress &&
+	    (sbp->sb_fdblocks > sbp->sb_dblocks ||
+	     !xfs_verify_icount(mp, sbp->sb_icount) ||
+	     sbp->sb_ifree > sbp->sb_icount)) {
 		xfs_warn(mp, "SB summary counter sanity check failed");
 		return -EFSCORRUPTED;
 	}
@@ -756,7 +762,7 @@ xfs_sb_write_verify(
 	error = xfs_validate_sb_common(mp, bp, &sb);
 	if (error)
 		goto out_error;
-	error = xfs_validate_sb_write(mp, &sb);
+	error = xfs_validate_sb_write(mp, bp, &sb);
 	if (error)
 		goto out_error;
 
-- 
cgit v1.2.3


From a0e336ba3e3d1c7ec0f738a2e2e203434c00b08e Mon Sep 17 00:00:00 2001
From: Huang Chong <huang.chong@zte.com.cn>
Date: Fri, 3 Aug 2018 08:17:54 -0700
Subject: xfs: fix a comment in xfs_log_reserve

Fix the comment in xfs_log_reserve to avoid confusing.

Signed-of-by: Huang Chong <huang.chong@zte.com.cn>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_log.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 00df4f39093a..c3b610b687d1 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -410,7 +410,7 @@ out_error:
 }
 
 /*
- * Reserve log space and return a ticket corresponding the reservation.
+ * Reserve log space and return a ticket corresponding to the reservation.
  *
  * Each reservation is going to reserve extra space for a log record header.
  * When writes happen to the on-disk log, we don't subtract the length of the
-- 
cgit v1.2.3


From 285189c78eeb6f684a024b86fb5997d10c6aa564 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Wed, 25 Jul 2018 15:52:13 +0800
Subject: netfilter: use kvmalloc_array to allocate memory for hashtable

nf_ct_alloc_hashtable is used to allocate memory for conntrack,
NAT bysrc and expectation hashtable. Assuming 64k bucket size,
which means 7th order page allocation, __get_free_pages, called
by nf_ct_alloc_hashtable, will trigger the direct memory reclaim
and stall for a long time, when system has lots of memory stress

so replace combination of __get_free_pages and vzalloc with
kvmalloc_array, which provides a overflow check and a fallback
if no high order memory is available, and do not retry to reclaim
memory, reduce stall

and remove nf_ct_free_hashtable, since it is just a kvfree

Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Wang Li <wangli39@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack.h |  2 --
 net/netfilter/nf_conntrack_core.c    | 29 ++++++-----------------------
 net/netfilter/nf_conntrack_expect.c  |  2 +-
 net/netfilter/nf_conntrack_helper.c  |  4 ++--
 net/netfilter/nf_nat_core.c          |  4 ++--
 5 files changed, 11 insertions(+), 30 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index a2b0ed025908..7e012312cd61 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -176,8 +176,6 @@ void nf_ct_netns_put(struct net *net, u8 nfproto);
  */
 void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls);
 
-void nf_ct_free_hashtable(void *hash, unsigned int size);
-
 int nf_conntrack_hash_check_insert(struct nf_conn *ct);
 bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report);
 
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 8a113ca1eea2..a676d5f76bdc 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2022,16 +2022,6 @@ static int kill_all(struct nf_conn *i, void *data)
 	return net_eq(nf_ct_net(i), data);
 }
 
-void nf_ct_free_hashtable(void *hash, unsigned int size)
-{
-	if (is_vmalloc_addr(hash))
-		vfree(hash);
-	else
-		free_pages((unsigned long)hash,
-			   get_order(sizeof(struct hlist_head) * size));
-}
-EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
-
 void nf_conntrack_cleanup_start(void)
 {
 	conntrack_gc_work.exiting = true;
@@ -2042,7 +2032,7 @@ void nf_conntrack_cleanup_end(void)
 {
 	RCU_INIT_POINTER(nf_ct_hook, NULL);
 	cancel_delayed_work_sync(&conntrack_gc_work.dwork);
-	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
+	kvfree(nf_conntrack_hash);
 
 	nf_conntrack_proto_fini();
 	nf_conntrack_seqadj_fini();
@@ -2108,7 +2098,6 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
 {
 	struct hlist_nulls_head *hash;
 	unsigned int nr_slots, i;
-	size_t sz;
 
 	if (*sizep > (UINT_MAX / sizeof(struct hlist_nulls_head)))
 		return NULL;
@@ -2116,14 +2105,8 @@ void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)
 	BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head));
 	nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head));
 
-	if (nr_slots > (UINT_MAX / sizeof(struct hlist_nulls_head)))
-		return NULL;
-
-	sz = nr_slots * sizeof(struct hlist_nulls_head);
-	hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO,
-					get_order(sz));
-	if (!hash)
-		hash = vzalloc(sz);
+	hash = kvmalloc_array(nr_slots, sizeof(struct hlist_nulls_head),
+			      GFP_KERNEL | __GFP_ZERO);
 
 	if (hash && nulls)
 		for (i = 0; i < nr_slots; i++)
@@ -2150,7 +2133,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize)
 
 	old_size = nf_conntrack_htable_size;
 	if (old_size == hashsize) {
-		nf_ct_free_hashtable(hash, hashsize);
+		kvfree(hash);
 		return 0;
 	}
 
@@ -2186,7 +2169,7 @@ int nf_conntrack_hash_resize(unsigned int hashsize)
 	local_bh_enable();
 
 	synchronize_net();
-	nf_ct_free_hashtable(old_hash, old_size);
+	kvfree(old_hash);
 	return 0;
 }
 
@@ -2350,7 +2333,7 @@ err_acct:
 err_expect:
 	kmem_cache_destroy(nf_conntrack_cachep);
 err_cachep:
-	nf_ct_free_hashtable(nf_conntrack_hash, nf_conntrack_htable_size);
+	kvfree(nf_conntrack_hash);
 	return ret;
 }
 
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 3f586ba23d92..27b84231db10 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -712,5 +712,5 @@ void nf_conntrack_expect_fini(void)
 {
 	rcu_barrier(); /* Wait for call_rcu() before destroy */
 	kmem_cache_destroy(nf_ct_expect_cachep);
-	nf_ct_free_hashtable(nf_ct_expect_hash, nf_ct_expect_hsize);
+	kvfree(nf_ct_expect_hash);
 }
diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c
index d557a425289d..e24b762ffa1d 100644
--- a/net/netfilter/nf_conntrack_helper.c
+++ b/net/netfilter/nf_conntrack_helper.c
@@ -562,12 +562,12 @@ int nf_conntrack_helper_init(void)
 
 	return 0;
 out_extend:
-	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize);
+	kvfree(nf_ct_helper_hash);
 	return ret;
 }
 
 void nf_conntrack_helper_fini(void)
 {
 	nf_ct_extend_unregister(&helper_extend);
-	nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize);
+	kvfree(nf_ct_helper_hash);
 }
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 6366f0c0b8c1..e2b196054dfc 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -1056,7 +1056,7 @@ static int __init nf_nat_init(void)
 
 	ret = nf_ct_extend_register(&nat_extend);
 	if (ret < 0) {
-		nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
+		kvfree(nf_nat_bysource);
 		pr_err("Unable to register extension\n");
 		return ret;
 	}
@@ -1094,7 +1094,7 @@ static void __exit nf_nat_cleanup(void)
 	for (i = 0; i < NFPROTO_NUMPROTO; i++)
 		kfree(nf_nat_l4protos[i]);
 	synchronize_net();
-	nf_ct_free_hashtable(nf_nat_bysource, nf_nat_htable_size);
+	kvfree(nf_nat_bysource);
 	unregister_pernet_subsys(&nat_net_ops);
 }
 
-- 
cgit v1.2.3


From 7cca1ed0bb248b8d5768d17f5afe297a832d66c0 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Tue, 31 Jul 2018 20:25:00 +0200
Subject: netfilter: nf_osf: move nf_osf_fingers to non-uapi header file

All warnings (new ones prefixed by >>):

>> ./usr/include/linux/netfilter/nf_osf.h:73: userspace cannot reference function or variable defined in the kernel

Fixes: f9324952088f ("netfilter: nfnetlink_osf: extract nfnetlink_subsystem code from xt_osf.c")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_osf.h      | 2 ++
 include/uapi/linux/netfilter/nf_osf.h | 2 --
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h
index aee460fcbd31..3e455d6f94d5 100644
--- a/include/linux/netfilter/nf_osf.h
+++ b/include/linux/netfilter/nf_osf.h
@@ -25,6 +25,8 @@ enum osf_fmatch_states {
 	FMATCH_OPT_WRONG,
 };
 
+extern struct list_head nf_osf_fingers[2];
+
 struct nf_osf_finger {
 	struct rcu_head			rcu_head;
 	struct list_head		finger_entry;
diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h
index cc2487ff74f6..3b93fbb9fc24 100644
--- a/include/uapi/linux/netfilter/nf_osf.h
+++ b/include/uapi/linux/netfilter/nf_osf.h
@@ -70,8 +70,6 @@ struct nf_osf_nlmsg {
 	struct tcphdr			tcp;
 };
 
-extern struct list_head nf_osf_fingers[2];
-
 /* Defines for IANA option kinds */
 enum iana_options {
 	OSFOPT_EOL = 0,		/* End of options */
-- 
cgit v1.2.3


From ddba40be59c9be4059288464f8e6f38fbba27495 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Tue, 31 Jul 2018 20:25:01 +0200
Subject: netfilter: nfnetlink_osf: rename nf_osf header file to nfnetlink_osf

The first client of the nf_osf.h userspace header is nft_osf, coming in
this batch, rename it to nfnetlink_osf.h as there are no userspace
clients for this yet, hence this looks consistent with other nfnetlink
subsystem.

Suggested-by: Jan Engelhardt <jengelh@inai.de>
Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nf_osf.h             |  44 -----------
 include/linux/netfilter/nfnetlink_osf.h      |  44 +++++++++++
 include/uapi/linux/netfilter/nf_osf.h        | 106 ---------------------------
 include/uapi/linux/netfilter/nfnetlink_osf.h | 106 +++++++++++++++++++++++++++
 include/uapi/linux/netfilter/xt_osf.h        |   2 +-
 net/netfilter/nfnetlink_osf.c                |   2 +-
 net/netfilter/nft_osf.c                      |   2 +-
 7 files changed, 153 insertions(+), 153 deletions(-)
 delete mode 100644 include/linux/netfilter/nf_osf.h
 create mode 100644 include/linux/netfilter/nfnetlink_osf.h
 delete mode 100644 include/uapi/linux/netfilter/nf_osf.h
 create mode 100644 include/uapi/linux/netfilter/nfnetlink_osf.h

diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h
deleted file mode 100644
index 3e455d6f94d5..000000000000
--- a/include/linux/netfilter/nf_osf.h
+++ /dev/null
@@ -1,44 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NFOSF_H
-#define _NFOSF_H
-
-#include <uapi/linux/netfilter/nf_osf.h>
-
-/* Initial window size option state machine: multiple of mss, mtu or
- * plain numeric value. Can also be made as plain numeric value which
- * is not a multiple of specified value.
- */
-enum nf_osf_window_size_options {
-	OSF_WSS_PLAIN   = 0,
-	OSF_WSS_MSS,
-	OSF_WSS_MTU,
-	OSF_WSS_MODULO,
-	OSF_WSS_MAX,
-};
-
-enum osf_fmatch_states {
-	/* Packet does not match the fingerprint */
-	FMATCH_WRONG = 0,
-	/* Packet matches the fingerprint */
-	FMATCH_OK,
-	/* Options do not match the fingerprint, but header does */
-	FMATCH_OPT_WRONG,
-};
-
-extern struct list_head nf_osf_fingers[2];
-
-struct nf_osf_finger {
-	struct rcu_head			rcu_head;
-	struct list_head		finger_entry;
-	struct nf_osf_user_finger	finger;
-};
-
-bool nf_osf_match(const struct sk_buff *skb, u_int8_t family,
-		  int hooknum, struct net_device *in, struct net_device *out,
-		  const struct nf_osf_info *info, struct net *net,
-		  const struct list_head *nf_osf_fingers);
-
-const char *nf_osf_find(const struct sk_buff *skb,
-                        const struct list_head *nf_osf_fingers);
-
-#endif /* _NFOSF_H */
diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h
new file mode 100644
index 000000000000..a7311bc03d3a
--- /dev/null
+++ b/include/linux/netfilter/nfnetlink_osf.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NFOSF_H
+#define _NFOSF_H
+
+#include <uapi/linux/netfilter/nfnetlink_osf.h>
+
+/* Initial window size option state machine: multiple of mss, mtu or
+ * plain numeric value. Can also be made as plain numeric value which
+ * is not a multiple of specified value.
+ */
+enum nf_osf_window_size_options {
+	OSF_WSS_PLAIN   = 0,
+	OSF_WSS_MSS,
+	OSF_WSS_MTU,
+	OSF_WSS_MODULO,
+	OSF_WSS_MAX,
+};
+
+enum osf_fmatch_states {
+	/* Packet does not match the fingerprint */
+	FMATCH_WRONG = 0,
+	/* Packet matches the fingerprint */
+	FMATCH_OK,
+	/* Options do not match the fingerprint, but header does */
+	FMATCH_OPT_WRONG,
+};
+
+extern struct list_head nf_osf_fingers[2];
+
+struct nf_osf_finger {
+	struct rcu_head			rcu_head;
+	struct list_head		finger_entry;
+	struct nf_osf_user_finger	finger;
+};
+
+bool nf_osf_match(const struct sk_buff *skb, u_int8_t family,
+		  int hooknum, struct net_device *in, struct net_device *out,
+		  const struct nf_osf_info *info, struct net *net,
+		  const struct list_head *nf_osf_fingers);
+
+const char *nf_osf_find(const struct sk_buff *skb,
+                        const struct list_head *nf_osf_fingers);
+
+#endif /* _NFOSF_H */
diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h
deleted file mode 100644
index 3b93fbb9fc24..000000000000
--- a/include/uapi/linux/netfilter/nf_osf.h
+++ /dev/null
@@ -1,106 +0,0 @@
-#ifndef _NF_OSF_H
-#define _NF_OSF_H
-
-#include <linux/types.h>
-
-#define MAXGENRELEN	32
-
-#define NF_OSF_GENRE	(1 << 0)
-#define NF_OSF_TTL	(1 << 1)
-#define NF_OSF_LOG	(1 << 2)
-#define NF_OSF_INVERT	(1 << 3)
-
-#define NF_OSF_LOGLEVEL_ALL		0	/* log all matched fingerprints */
-#define NF_OSF_LOGLEVEL_FIRST		1	/* log only the first matced fingerprint */
-#define NF_OSF_LOGLEVEL_ALL_KNOWN	2	/* do not log unknown packets */
-
-#define NF_OSF_TTL_TRUE			0	/* True ip and fingerprint TTL comparison */
-
-/* Check if ip TTL is less than fingerprint one */
-#define NF_OSF_TTL_LESS			1
-
-/* Do not compare ip and fingerprint TTL at all */
-#define NF_OSF_TTL_NOCHECK		2
-
-#define NF_OSF_FLAGMASK		(NF_OSF_GENRE | NF_OSF_TTL | \
-				 NF_OSF_LOG | NF_OSF_INVERT)
-/* Wildcard MSS (kind of).
- * It is used to implement a state machine for the different wildcard values
- * of the MSS and window sizes.
- */
-struct nf_osf_wc {
-	__u32	wc;
-	__u32	val;
-};
-
-/* This struct represents IANA options
- * http://www.iana.org/assignments/tcp-parameters
- */
-struct nf_osf_opt {
-	__u16			kind, length;
-	struct nf_osf_wc	wc;
-};
-
-struct nf_osf_info {
-	char	genre[MAXGENRELEN];
-	__u32	len;
-	__u32	flags;
-	__u32	loglevel;
-	__u32	ttl;
-};
-
-struct nf_osf_user_finger {
-	struct nf_osf_wc	wss;
-
-	__u8	ttl, df;
-	__u16	ss, mss;
-	__u16	opt_num;
-
-	char	genre[MAXGENRELEN];
-	char	version[MAXGENRELEN];
-	char	subtype[MAXGENRELEN];
-
-	/* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */
-	struct nf_osf_opt	opt[MAX_IPOPTLEN];
-};
-
-struct nf_osf_nlmsg {
-	struct nf_osf_user_finger	f;
-	struct iphdr			ip;
-	struct tcphdr			tcp;
-};
-
-/* Defines for IANA option kinds */
-enum iana_options {
-	OSFOPT_EOL = 0,		/* End of options */
-	OSFOPT_NOP,		/* NOP */
-	OSFOPT_MSS,		/* Maximum segment size */
-	OSFOPT_WSO,		/* Window scale option */
-	OSFOPT_SACKP,		/* SACK permitted */
-	OSFOPT_SACK,		/* SACK */
-	OSFOPT_ECHO,
-	OSFOPT_ECHOREPLY,
-	OSFOPT_TS,		/* Timestamp option */
-	OSFOPT_POCP,		/* Partial Order Connection Permitted */
-	OSFOPT_POSP,		/* Partial Order Service Profile */
-
-	/* Others are not used in the current OSF */
-	OSFOPT_EMPTY = 255,
-};
-
-enum nf_osf_attr_type {
-	OSF_ATTR_UNSPEC,
-	OSF_ATTR_FINGER,
-	OSF_ATTR_MAX,
-};
-
-/*
- * Add/remove fingerprint from the kernel.
- */
-enum nf_osf_msg_types {
-	OSF_MSG_ADD,
-	OSF_MSG_REMOVE,
-	OSF_MSG_MAX,
-};
-
-#endif /* _NF_OSF_H */
diff --git a/include/uapi/linux/netfilter/nfnetlink_osf.h b/include/uapi/linux/netfilter/nfnetlink_osf.h
new file mode 100644
index 000000000000..3b93fbb9fc24
--- /dev/null
+++ b/include/uapi/linux/netfilter/nfnetlink_osf.h
@@ -0,0 +1,106 @@
+#ifndef _NF_OSF_H
+#define _NF_OSF_H
+
+#include <linux/types.h>
+
+#define MAXGENRELEN	32
+
+#define NF_OSF_GENRE	(1 << 0)
+#define NF_OSF_TTL	(1 << 1)
+#define NF_OSF_LOG	(1 << 2)
+#define NF_OSF_INVERT	(1 << 3)
+
+#define NF_OSF_LOGLEVEL_ALL		0	/* log all matched fingerprints */
+#define NF_OSF_LOGLEVEL_FIRST		1	/* log only the first matced fingerprint */
+#define NF_OSF_LOGLEVEL_ALL_KNOWN	2	/* do not log unknown packets */
+
+#define NF_OSF_TTL_TRUE			0	/* True ip and fingerprint TTL comparison */
+
+/* Check if ip TTL is less than fingerprint one */
+#define NF_OSF_TTL_LESS			1
+
+/* Do not compare ip and fingerprint TTL at all */
+#define NF_OSF_TTL_NOCHECK		2
+
+#define NF_OSF_FLAGMASK		(NF_OSF_GENRE | NF_OSF_TTL | \
+				 NF_OSF_LOG | NF_OSF_INVERT)
+/* Wildcard MSS (kind of).
+ * It is used to implement a state machine for the different wildcard values
+ * of the MSS and window sizes.
+ */
+struct nf_osf_wc {
+	__u32	wc;
+	__u32	val;
+};
+
+/* This struct represents IANA options
+ * http://www.iana.org/assignments/tcp-parameters
+ */
+struct nf_osf_opt {
+	__u16			kind, length;
+	struct nf_osf_wc	wc;
+};
+
+struct nf_osf_info {
+	char	genre[MAXGENRELEN];
+	__u32	len;
+	__u32	flags;
+	__u32	loglevel;
+	__u32	ttl;
+};
+
+struct nf_osf_user_finger {
+	struct nf_osf_wc	wss;
+
+	__u8	ttl, df;
+	__u16	ss, mss;
+	__u16	opt_num;
+
+	char	genre[MAXGENRELEN];
+	char	version[MAXGENRELEN];
+	char	subtype[MAXGENRELEN];
+
+	/* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */
+	struct nf_osf_opt	opt[MAX_IPOPTLEN];
+};
+
+struct nf_osf_nlmsg {
+	struct nf_osf_user_finger	f;
+	struct iphdr			ip;
+	struct tcphdr			tcp;
+};
+
+/* Defines for IANA option kinds */
+enum iana_options {
+	OSFOPT_EOL = 0,		/* End of options */
+	OSFOPT_NOP,		/* NOP */
+	OSFOPT_MSS,		/* Maximum segment size */
+	OSFOPT_WSO,		/* Window scale option */
+	OSFOPT_SACKP,		/* SACK permitted */
+	OSFOPT_SACK,		/* SACK */
+	OSFOPT_ECHO,
+	OSFOPT_ECHOREPLY,
+	OSFOPT_TS,		/* Timestamp option */
+	OSFOPT_POCP,		/* Partial Order Connection Permitted */
+	OSFOPT_POSP,		/* Partial Order Service Profile */
+
+	/* Others are not used in the current OSF */
+	OSFOPT_EMPTY = 255,
+};
+
+enum nf_osf_attr_type {
+	OSF_ATTR_UNSPEC,
+	OSF_ATTR_FINGER,
+	OSF_ATTR_MAX,
+};
+
+/*
+ * Add/remove fingerprint from the kernel.
+ */
+enum nf_osf_msg_types {
+	OSF_MSG_ADD,
+	OSF_MSG_REMOVE,
+	OSF_MSG_MAX,
+};
+
+#endif /* _NF_OSF_H */
diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h
index a90e90c27cef..c56c59605c2b 100644
--- a/include/uapi/linux/netfilter/xt_osf.h
+++ b/include/uapi/linux/netfilter/xt_osf.h
@@ -23,7 +23,7 @@
 #include <linux/types.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
-#include <linux/netfilter/nf_osf.h>
+#include <linux/netfilter/nfnetlink_osf.h>
 
 #define XT_OSF_GENRE		NF_OSF_GENRE
 #define XT_OSF_INVERT		NF_OSF_INVERT
diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index ba0fa11869ce..f9dba62c450f 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -18,7 +18,7 @@
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/x_tables.h>
 #include <net/netfilter/nf_log.h>
-#include <linux/netfilter/nf_osf.h>
+#include <linux/netfilter/nfnetlink_osf.h>
 
 /*
  * Indexed by dont-fragment bit.
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index bdacc4cffba4..9b2f3de7be4f 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -2,7 +2,7 @@
 #include <net/tcp.h>
 
 #include <net/netfilter/nf_tables.h>
-#include <linux/netfilter/nf_osf.h>
+#include <linux/netfilter/nfnetlink_osf.h>
 
 #define OSF_GENRE_SIZE		32
 
-- 
cgit v1.2.3


From 9e619d87b277bbcc4e0b64cc5963520c1cd99f18 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 31 Jul 2018 17:24:45 +0200
Subject: netfilter: nf_tables: flow event notifier must use transaction mutex

Fixes: f102d66b335a4 ("netfilter: nf_tables: use dedicated mutex to guard transactions")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f18085639807..06d6af067619 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -5940,13 +5940,13 @@ static int nf_tables_flowtable_event(struct notifier_block *this,
 	if (!net)
 		return 0;
 
-	nfnl_lock(NFNL_SUBSYS_NFTABLES);
+	mutex_lock(&net->nft.commit_mutex);
 	list_for_each_entry(table, &net->nft.tables, list) {
 		list_for_each_entry(flowtable, &table->flowtables, list) {
 			nft_flowtable_event(event, dev, flowtable);
 		}
 	}
-	nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+	mutex_unlock(&net->nft.commit_mutex);
 	put_net(net);
 	return NOTIFY_DONE;
 }
-- 
cgit v1.2.3


From 6fd544c897d98bc6f185da215f1585dc144218cc Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 3 Aug 2018 16:48:56 +0800
Subject: bnxt_en: combine 'else if' and 'else' into single branch

The else-if branch and else branch set mac_ok to true similarly,
so combine the two into single else branch.

Also add comments to explain the two conditions, which
from Michael Chan and Vasundhara Volam.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index a64910892c25..f560845c5a9d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -956,9 +956,13 @@ static int bnxt_vf_validate_set_mac(struct bnxt *bp, struct bnxt_vf_info *vf)
 	} else if (is_valid_ether_addr(vf->vf_mac_addr)) {
 		if (ether_addr_equal((const u8 *)req->l2_addr, vf->vf_mac_addr))
 			mac_ok = true;
-	} else if (bp->hwrm_spec_code < 0x10202) {
-		mac_ok = true;
 	} else {
+		/* There are two cases:
+		 * 1.If firmware spec < 0x10202,VF MAC address is not forwarded
+		 *   to the PF and so it doesn't have to match
+		 * 2.Allow VF to modify it's own MAC when PF has not assigned a
+		 *   valid MAC address and firmware spec >= 0x10202
+		 */
 		mac_ok = true;
 	}
 	if (mac_ok)
-- 
cgit v1.2.3


From 3b7c88fcc2873eba64f9e8cef34c4af0cba20887 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 11:28:24 -0500
Subject: ASoC: davinci-i2s: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1364478 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/davinci/davinci-i2s.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/davinci/davinci-i2s.c b/sound/soc/davinci/davinci-i2s.c
index 807040bb3921..a3206e65e5e5 100644
--- a/sound/soc/davinci/davinci-i2s.c
+++ b/sound/soc/davinci/davinci-i2s.c
@@ -340,6 +340,7 @@ static int davinci_i2s_set_dai_fmt(struct snd_soc_dai *cpu_dai,
 		 * rate is lowered.
 		 */
 		inv_fs = true;
+		/* fall through */
 	case SND_SOC_DAIFMT_DSP_A:
 		dev->mode = MOD_DSP_A;
 		break;
-- 
cgit v1.2.3


From 85c81941d5033fc8a68646823d3157840c9de8b3 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 11:32:52 -0500
Subject: ASoC: omap-mcpdm: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1369526 ("Missing break in switch")
Addresses-Coverity-ID: 1369529 ("Missing break in switch")
Addresses-Coverity-ID: 1451415 ("Missing break in switch")
Addresses-Coverity-ID: 115103 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/omap/omap-mcpdm.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/soc/omap/omap-mcpdm.c b/sound/soc/omap/omap-mcpdm.c
index 0e97360f9890..4c1be36c2207 100644
--- a/sound/soc/omap/omap-mcpdm.c
+++ b/sound/soc/omap/omap-mcpdm.c
@@ -310,15 +310,19 @@ static int omap_mcpdm_dai_hw_params(struct snd_pcm_substream *substream,
 			/* up to 3 channels for capture */
 			return -EINVAL;
 		link_mask |= 1 << 4;
+		/* fall through */
 	case 4:
 		if (stream == SNDRV_PCM_STREAM_CAPTURE)
 			/* up to 3 channels for capture */
 			return -EINVAL;
 		link_mask |= 1 << 3;
+		/* fall through */
 	case 3:
 		link_mask |= 1 << 2;
+		/* fall through */
 	case 2:
 		link_mask |= 1 << 1;
+		/* fall through */
 	case 1:
 		link_mask |= 1 << 0;
 		break;
-- 
cgit v1.2.3


From 1a12d5dc7dd1ffd985503f9770b736fb03db2e3f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 11:34:30 -0500
Subject: ASoC: core: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 146568 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/soc-core.c b/sound/soc/soc-core.c
index 82eb3868be67..9cfe10d8040c 100644
--- a/sound/soc/soc-core.c
+++ b/sound/soc/soc-core.c
@@ -528,6 +528,7 @@ int snd_soc_suspend(struct device *dev)
 						"ASoC: idle_bias_off CODEC on over suspend\n");
 					break;
 				}
+				/* fall through */
 
 			case SND_SOC_BIAS_OFF:
 				if (component->driver->suspend)
-- 
cgit v1.2.3


From 5ca8a25c144dbb04511147601943691baab0aaca Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Fri, 3 Aug 2018 11:08:47 +0200
Subject: net: sched: fix flush on non-existing chain

User was able to perform filter flush on chain 0 even if it didn't have
any filters in it. With the patch that avoided implicit chain 0
creation, this changed. So in case user wants filter flush on chain
which does not exist, just return success. There's no reason for non-0
chains to behave differently than chain 0, so do the same for them.

Reported-by: Ido Schimmel <idosch@mellanox.com>
Fixes: f71e0ca4db18 ("net: sched: Avoid implicit chain 0 creation")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index e8b0bbd0883f..194c2e0b2737 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -1389,6 +1389,13 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
 	}
 	chain = tcf_chain_get(block, chain_index, false);
 	if (!chain) {
+		/* User requested flush on non-existent chain. Nothing to do,
+		 * so just return success.
+		 */
+		if (prio == 0) {
+			err = 0;
+			goto errout;
+		}
 		NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
 		err = -EINVAL;
 		goto errout;
-- 
cgit v1.2.3


From 54424d3891967b83d707c9300a3509c2ae8f42ee Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 3 Aug 2018 10:15:25 +0100
Subject: rxrpc: Reuse SKCIPHER_REQUEST_ON_STACK buffer

The use of SKCIPHER_REQUEST_ON_STACK() will trigger FRAME_WARN warnings
(when less than 2048) once the VLA is no longer hidden from the check:

net/rxrpc/rxkad.c:398:1: warning: the frame size of 1152 bytes is larger than 1024 bytes [-Wframe-larger-than=]
net/rxrpc/rxkad.c:242:1: warning: the frame size of 1152 bytes is larger than 1024 bytes [-Wframe-larger-than=]

This passes the initial SKCIPHER_REQUEST_ON_STACK allocation to the leaf
functions for reuse. Two requests allocated on the stack is not needed
when only one is used at a time.

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/rxkad.c | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c
index 6988073ae842..eaf8f4f446b0 100644
--- a/net/rxrpc/rxkad.c
+++ b/net/rxrpc/rxkad.c
@@ -146,10 +146,10 @@ static int rxkad_prime_packet_security(struct rxrpc_connection *conn)
 static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 				    struct sk_buff *skb,
 				    u32 data_size,
-				    void *sechdr)
+				    void *sechdr,
+				    struct skcipher_request *req)
 {
 	struct rxrpc_skb_priv *sp = rxrpc_skb(skb);
-	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxkad_level1_hdr hdr;
 	struct rxrpc_crypt iv;
 	struct scatterlist sg;
@@ -183,12 +183,12 @@ static int rxkad_secure_packet_auth(const struct rxrpc_call *call,
 static int rxkad_secure_packet_encrypt(const struct rxrpc_call *call,
 				       struct sk_buff *skb,
 				       u32 data_size,
-				       void *sechdr)
+				       void *sechdr,
+				       struct skcipher_request *req)
 {
 	const struct rxrpc_key_token *token;
 	struct rxkad_level2_hdr rxkhdr;
 	struct rxrpc_skb_priv *sp;
-	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[16];
 	struct sk_buff *trailer;
@@ -296,11 +296,12 @@ static int rxkad_secure_packet(struct rxrpc_call *call,
 		ret = 0;
 		break;
 	case RXRPC_SECURITY_AUTH:
-		ret = rxkad_secure_packet_auth(call, skb, data_size, sechdr);
+		ret = rxkad_secure_packet_auth(call, skb, data_size, sechdr,
+					       req);
 		break;
 	case RXRPC_SECURITY_ENCRYPT:
 		ret = rxkad_secure_packet_encrypt(call, skb, data_size,
-						  sechdr);
+						  sechdr, req);
 		break;
 	default:
 		ret = -EPERM;
@@ -316,10 +317,10 @@ static int rxkad_secure_packet(struct rxrpc_call *call,
  */
 static int rxkad_verify_packet_1(struct rxrpc_call *call, struct sk_buff *skb,
 				 unsigned int offset, unsigned int len,
-				 rxrpc_seq_t seq)
+				 rxrpc_seq_t seq,
+				 struct skcipher_request *req)
 {
 	struct rxkad_level1_hdr sechdr;
-	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist sg[16];
 	struct sk_buff *trailer;
@@ -402,11 +403,11 @@ nomem:
  */
 static int rxkad_verify_packet_2(struct rxrpc_call *call, struct sk_buff *skb,
 				 unsigned int offset, unsigned int len,
-				 rxrpc_seq_t seq)
+				 rxrpc_seq_t seq,
+				 struct skcipher_request *req)
 {
 	const struct rxrpc_key_token *token;
 	struct rxkad_level2_hdr sechdr;
-	SKCIPHER_REQUEST_ON_STACK(req, call->conn->cipher);
 	struct rxrpc_crypt iv;
 	struct scatterlist _sg[4], *sg;
 	struct sk_buff *trailer;
@@ -549,9 +550,9 @@ static int rxkad_verify_packet(struct rxrpc_call *call, struct sk_buff *skb,
 	case RXRPC_SECURITY_PLAIN:
 		return 0;
 	case RXRPC_SECURITY_AUTH:
-		return rxkad_verify_packet_1(call, skb, offset, len, seq);
+		return rxkad_verify_packet_1(call, skb, offset, len, seq, req);
 	case RXRPC_SECURITY_ENCRYPT:
-		return rxkad_verify_packet_2(call, skb, offset, len, seq);
+		return rxkad_verify_packet_2(call, skb, offset, len, seq, req);
 	default:
 		return -ENOANO;
 	}
-- 
cgit v1.2.3


From 1974d2453fa7bfea5574d09332df3cc7fb0d909a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 10:14:00 +0800
Subject: netfilter: nf_tables: remove unused variable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Variable 'ext' is being assigned but are never used hence they are
unused and can be removed.

Cleans up clang warnings:
net/netfilter/nf_tables_api.c:4032:28: warning: variable ‘ext’ set but not used [-Wunused-but-set-variable]

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 06d6af067619..debc1680607c 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4029,7 +4029,6 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 			    const struct nlattr *attr)
 {
 	struct nlattr *nla[NFTA_SET_ELEM_MAX + 1];
-	const struct nft_set_ext *ext;
 	struct nft_data_desc desc;
 	struct nft_set_elem elem;
 	struct sk_buff *skb;
@@ -4063,7 +4062,6 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 		return PTR_ERR(priv);
 
 	elem.priv = priv;
-	ext = nft_set_elem_ext(set, &elem);
 
 	err = -ENOMEM;
 	skb = nlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC);
-- 
cgit v1.2.3


From c75303269009667cc2b7ddee274bc9e96e840f57 Mon Sep 17 00:00:00 2001
From: Harsha Sharma <harshasharmaiitr@gmail.com>
Date: Thu, 2 Aug 2018 09:26:24 +0530
Subject: netfilter: cttimeout: Make NF_CT_NETLINK_TIMEOUT depend on
 NF_CONNTRACK_TIMEOUT

With this, remove ifdef for CONFIG_NF_CONNTRACK_TIMEOUT in
nfnetlink_cttimeout. This is also required for moving ctnl_untimeout
from nfnetlink_cttimeout to nf_conntrack_timeout.

Signed-off-by: Harsha Sharma <harshasharmaiitr@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/Kconfig               | 1 +
 net/netfilter/nfnetlink_cttimeout.c | 6 ------
 2 files changed, 1 insertion(+), 6 deletions(-)

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 0febf3e21f91..55e399d5af10 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -365,6 +365,7 @@ config NF_CT_NETLINK_TIMEOUT
 	tristate  'Connection tracking timeout tuning via Netlink'
 	select NETFILTER_NETLINK
 	depends on NETFILTER_ADVANCED
+	depends on NF_CONNTRACK_TIMEOUT
 	help
 	  This option enables support for connection tracking timeout
 	  fine-grain tuning. This allows you to attach specific timeout
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index d9d952fad3e0..4199e5300575 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -503,7 +503,6 @@ err:
 	return err;
 }
 
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 static struct ctnl_timeout *
 ctnl_timeout_find_get(struct net *net, const char *name)
 {
@@ -534,7 +533,6 @@ static void ctnl_timeout_put(struct ctnl_timeout *timeout)
 
 	module_put(THIS_MODULE);
 }
-#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
 static const struct nfnl_callback cttimeout_cb[IPCTNL_MSG_TIMEOUT_MAX] = {
 	[IPCTNL_MSG_TIMEOUT_NEW]	= { .call = cttimeout_new_timeout,
@@ -605,10 +603,8 @@ static int __init cttimeout_init(void)
 			"nfnetlink.\n");
 		goto err_out;
 	}
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, ctnl_timeout_find_get);
 	RCU_INIT_POINTER(nf_ct_timeout_put_hook, ctnl_timeout_put);
-#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 	return 0;
 
 err_out:
@@ -621,11 +617,9 @@ static void __exit cttimeout_exit(void)
 	nfnetlink_subsys_unregister(&cttimeout_subsys);
 
 	unregister_pernet_subsys(&cttimeout_ops);
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	RCU_INIT_POINTER(nf_ct_timeout_find_get_hook, NULL);
 	RCU_INIT_POINTER(nf_ct_timeout_put_hook, NULL);
 	synchronize_rcu();
-#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 }
 
 module_init(cttimeout_init);
-- 
cgit v1.2.3


From 07acf909ee33983fe22334446dd5c2adf0fdca26 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 3 Aug 2018 10:56:30 +0100
Subject: net: hns3: Fix MSIX allocation issue for VF

The msix number for vf is different, depends on the max vf number.
Futherly if the vf supports roce, the offset of msix is not fixed.
It's incorrect to fix the msix number to 33. This patch fixes it by
querying the msix number from firmware, and adjusting it with roce
support.

Fixes: e2cb1dec9779 ("net: hns3: Add HNS3 VF HCL(Hardware Compatibility Layer) Support")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c    |  3 +-
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h   | 14 ++++
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c  | 80 ++++++++++++++++++----
 .../ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h  |  4 +-
 4 files changed, 85 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index 6c9e5d62455b..bd031af38a96 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -50,7 +50,8 @@ static const struct pci_device_id hns3_pci_tbl[] = {
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_MACSEC),
 	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_VF), 0},
-	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF), 0},
+	{PCI_VDEVICE(HUAWEI, HNAE3_DEV_ID_100G_RDMA_DCB_PFC_VF),
+	 HNAE3_DEV_SUPPORT_ROCE_DCB_BITS},
 	/* required last entry */
 	{0, }
 };
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
index 621c6cbacf76..19b32860309c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h
@@ -82,6 +82,7 @@ struct hclgevf_cmq {
 enum hclgevf_opcode_type {
 	/* Generic command */
 	HCLGEVF_OPC_QUERY_FW_VER	= 0x0001,
+	HCLGEVF_OPC_QUERY_VF_RSRC	= 0x0024,
 	/* TQP command */
 	HCLGEVF_OPC_QUERY_TX_STATUS	= 0x0B03,
 	HCLGEVF_OPC_QUERY_RX_STATUS	= 0x0B13,
@@ -134,6 +135,19 @@ struct hclgevf_query_version_cmd {
 	__le32 firmware_rsv[5];
 };
 
+#define HCLGEVF_MSIX_OFT_ROCEE_S       0
+#define HCLGEVF_MSIX_OFT_ROCEE_M       (0xffff << HCLGEVF_MSIX_OFT_ROCEE_S)
+#define HCLGEVF_VEC_NUM_S              0
+#define HCLGEVF_VEC_NUM_M              (0xff << HCLGEVF_VEC_NUM_S)
+struct hclgevf_query_res_cmd {
+	__le16 tqp_num;
+	__le16 reserved;
+	__le16 msixcap_localid_ba_nic;
+	__le16 msixcap_localid_ba_rocee;
+	__le16 vf_intr_vector_number;
+	__le16 rsv[7];
+};
+
 #define HCLGEVF_RSS_HASH_KEY_OFFSET	4
 #define HCLGEVF_RSS_HASH_KEY_NUM	16
 struct hclgevf_rss_config_cmd {
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
index d1f16f0c1646..9c0091f2addf 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
@@ -1370,14 +1370,13 @@ static int hclgevf_init_roce_base_info(struct hclgevf_dev *hdev)
 	struct hnae3_handle *roce = &hdev->roce;
 	struct hnae3_handle *nic = &hdev->nic;
 
-	roce->rinfo.num_vectors = HCLGEVF_ROCEE_VECTOR_NUM;
+	roce->rinfo.num_vectors = hdev->num_roce_msix;
 
 	if (hdev->num_msi_left < roce->rinfo.num_vectors ||
 	    hdev->num_msi_left == 0)
 		return -EINVAL;
 
-	roce->rinfo.base_vector =
-		hdev->vector_status[hdev->num_msi_used];
+	roce->rinfo.base_vector = hdev->roce_base_vector;
 
 	roce->rinfo.netdev = nic->kinfo.netdev;
 	roce->rinfo.roce_io_base = hdev->hw.io_base;
@@ -1520,10 +1519,15 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	if (hclgevf_dev_ongoing_reset(hdev))
 		return 0;
 
-	hdev->num_msi = HCLGEVF_MAX_VF_VECTOR_NUM;
+	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B))
+		vectors = pci_alloc_irq_vectors(pdev,
+						hdev->roce_base_msix_offset + 1,
+						hdev->num_msi,
+						PCI_IRQ_MSIX);
+	else
+		vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
+						PCI_IRQ_MSI | PCI_IRQ_MSIX);
 
-	vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi,
-					PCI_IRQ_MSI | PCI_IRQ_MSIX);
 	if (vectors < 0) {
 		dev_err(&pdev->dev,
 			"failed(%d) to allocate MSI/MSI-X vectors\n",
@@ -1538,6 +1542,7 @@ static int hclgevf_init_msi(struct hclgevf_dev *hdev)
 	hdev->num_msi = vectors;
 	hdev->num_msi_left = vectors;
 	hdev->base_msi_vector = pdev->irq;
+	hdev->roce_base_vector = pdev->irq + hdev->roce_base_msix_offset;
 
 	hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi,
 					   sizeof(u16), GFP_KERNEL);
@@ -1733,6 +1738,45 @@ static void hclgevf_pci_uninit(struct hclgevf_dev *hdev)
 	pci_disable_device(pdev);
 }
 
+static int hclgevf_query_vf_resource(struct hclgevf_dev *hdev)
+{
+	struct hclgevf_query_res_cmd *req;
+	struct hclgevf_desc desc;
+	int ret;
+
+	hclgevf_cmd_setup_basic_desc(&desc, HCLGEVF_OPC_QUERY_VF_RSRC, true);
+	ret = hclgevf_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"query vf resource failed, ret = %d.\n", ret);
+		return ret;
+	}
+
+	req = (struct hclgevf_query_res_cmd *)desc.data;
+
+	if (hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B)) {
+		hdev->roce_base_msix_offset =
+		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
+				HCLGEVF_MSIX_OFT_ROCEE_M,
+				HCLGEVF_MSIX_OFT_ROCEE_S);
+		hdev->num_roce_msix =
+		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
+				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
+
+		/* VF should have NIC vectors and Roce vectors, NIC vectors
+		 * are queued before Roce vectors. The offset is fixed to 64.
+		 */
+		hdev->num_msi = hdev->num_roce_msix +
+				hdev->roce_base_msix_offset;
+	} else {
+		hdev->num_msi =
+		hnae3_get_field(__le16_to_cpu(req->vf_intr_vector_number),
+				HCLGEVF_VEC_NUM_M, HCLGEVF_VEC_NUM_S);
+	}
+
+	return 0;
+}
+
 static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 {
 	struct pci_dev *pdev = hdev->pdev;
@@ -1750,18 +1794,26 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 		return ret;
 	}
 
+	ret = hclgevf_cmd_init(hdev);
+	if (ret)
+		goto err_cmd_init;
+
+	/* Get vf resource */
+	ret = hclgevf_query_vf_resource(hdev);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"Query vf status error, ret = %d.\n", ret);
+		goto err_query_vf;
+	}
+
 	ret = hclgevf_init_msi(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to init MSI/MSI-X\n", ret);
-		goto err_irq_init;
+		goto err_query_vf;
 	}
 
 	hclgevf_state_init(hdev);
 
-	ret = hclgevf_cmd_init(hdev);
-	if (ret)
-		goto err_cmd_init;
-
 	ret = hclgevf_misc_irq_init(hdev);
 	if (ret) {
 		dev_err(&pdev->dev, "failed(%d) to init Misc IRQ(vector0)\n",
@@ -1817,11 +1869,11 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev)
 err_config:
 	hclgevf_misc_irq_uninit(hdev);
 err_misc_irq_init:
-	hclgevf_cmd_uninit(hdev);
-err_cmd_init:
 	hclgevf_state_uninit(hdev);
 	hclgevf_uninit_msi(hdev);
-err_irq_init:
+err_query_vf:
+	hclgevf_cmd_uninit(hdev);
+err_cmd_init:
 	hclgevf_pci_uninit(hdev);
 	return ret;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
index 0656e8e5c5f0..b23ba171473c 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h
@@ -12,7 +12,6 @@
 #define HCLGEVF_MOD_VERSION "1.0"
 #define HCLGEVF_DRIVER_NAME "hclgevf"
 
-#define HCLGEVF_ROCEE_VECTOR_NUM	0
 #define HCLGEVF_MISC_VECTOR_NUM		0
 
 #define HCLGEVF_INVALID_VPORT		0xffff
@@ -150,6 +149,9 @@ struct hclgevf_dev {
 	u16 num_msi;
 	u16 num_msi_left;
 	u16 num_msi_used;
+	u16 num_roce_msix;	/* Num of roce vectors for this VF */
+	u16 roce_base_msix_offset;
+	int roce_base_vector;
 	u32 base_msi_vector;
 	u16 *vector_status;
 	int *vector_irq;
-- 
cgit v1.2.3


From 375dd5e432128ee071227e3ab0071ca11d01ac8c Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 3 Aug 2018 10:56:31 +0100
Subject: net: hns3: Refine the MSIX allocation for PF

The offset of msix number for roce is different between different
revision id. We should get it from firmware, instead of a fix value.
This patch refines the msix allocation, make it compatible.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h  | 2 ++
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 8 ++++++--
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h | 3 +--
 3 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index 5cd22f9bbdec..cd0a4f228470 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -358,6 +358,8 @@ struct hclge_pf_res_cmd {
 	__le16 buf_size;
 	__le16 msixcap_localid_ba_nic;
 	__le16 msixcap_localid_ba_rocee;
+#define HCLGE_MSIX_OFT_ROCEE_S		0
+#define HCLGE_MSIX_OFT_ROCEE_M		GENMASK(15, 0)
 #define HCLGE_PF_VEC_NUM_S		0
 #define HCLGE_PF_VEC_NUM_M		GENMASK(7, 0)
 	__le16 pf_intr_vector_number;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index a9b888f1544a..fc813b7f20e8 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -932,6 +932,9 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 	hdev->pkt_buf_size = __le16_to_cpu(req->buf_size) << HCLGE_BUF_UNIT_S;
 
 	if (hnae3_dev_roce_supported(hdev)) {
+		hdev->roce_base_msix_offset =
+		hnae3_get_field(__le16_to_cpu(req->msixcap_localid_ba_rocee),
+				HCLGE_MSIX_OFT_ROCEE_M, HCLGE_MSIX_OFT_ROCEE_S);
 		hdev->num_roce_msi =
 		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
 				HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);
@@ -939,7 +942,8 @@ static int hclge_query_pf_resource(struct hclge_dev *hdev)
 		/* PF should have NIC vectors and Roce vectors,
 		 * NIC vectors are queued before Roce vectors.
 		 */
-		hdev->num_msi = hdev->num_roce_msi  + HCLGE_ROCE_VECTOR_OFFSET;
+		hdev->num_msi = hdev->num_roce_msi  +
+				hdev->roce_base_msix_offset;
 	} else {
 		hdev->num_msi =
 		hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number),
@@ -2037,7 +2041,7 @@ static int hclge_init_msi(struct hclge_dev *hdev)
 	hdev->num_msi_left = vectors;
 	hdev->base_msi_vector = pdev->irq;
 	hdev->roce_base_vector = hdev->base_msi_vector +
-				HCLGE_ROCE_VECTOR_OFFSET;
+				hdev->roce_base_msix_offset;
 
 	hdev->vector_status = devm_kcalloc(&pdev->dev, hdev->num_msi,
 					   sizeof(u16), GFP_KERNEL);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
index dfa5c9456d22..1528fb3fa6be 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h
@@ -16,8 +16,6 @@
 
 #define HCLGE_INVALID_VPORT 0xffff
 
-#define HCLGE_ROCE_VECTOR_OFFSET	96
-
 #define HCLGE_PF_CFG_BLOCK_SIZE		32
 #define HCLGE_PF_CFG_DESC_NUM \
 	(HCLGE_PF_CFG_BLOCK_SIZE / HCLGE_CFG_RD_LEN_BYTES)
@@ -509,6 +507,7 @@ struct hclge_dev {
 	u16 num_msi;
 	u16 num_msi_left;
 	u16 num_msi_used;
+	u16 roce_base_msix_offset;
 	u32 base_msi_vector;
 	u16 *vector_status;
 	int *vector_irq;
-- 
cgit v1.2.3


From 16bbeb2b43c3f5d69e1348477e75a24ae6d55d5a Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 11:29:53 -0500
Subject: ASoC: fsl_esai: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1222121 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_esai.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/fsl/fsl_esai.c b/sound/soc/fsl/fsl_esai.c
index 8f43110373b8..c1d1d06783e5 100644
--- a/sound/soc/fsl/fsl_esai.c
+++ b/sound/soc/fsl/fsl_esai.c
@@ -249,6 +249,7 @@ static int fsl_esai_set_dai_sysclk(struct snd_soc_dai *dai, int clk_id,
 		break;
 	case ESAI_HCKT_EXTAL:
 		ecr |= ESAI_ECR_ETI;
+		/* fall through */
 	case ESAI_HCKR_EXTAL:
 		ecr |= ESAI_ECR_ERI;
 		break;
-- 
cgit v1.2.3


From a773c3b6be185d171e2755ac715e8b1ea099ebbc Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 11:31:48 -0500
Subject: ASoC: omap-dmic: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1468847 ("Missing break in switch")
Addresses-Coverity-ID: 1468849 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/omap/omap-dmic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/soc/omap/omap-dmic.c b/sound/soc/omap/omap-dmic.c
index 51dd7c65096b..fe966272bd0c 100644
--- a/sound/soc/omap/omap-dmic.c
+++ b/sound/soc/omap/omap-dmic.c
@@ -213,8 +213,10 @@ static int omap_dmic_dai_hw_params(struct snd_pcm_substream *substream,
 	switch (channels) {
 	case 6:
 		dmic->ch_enabled |= OMAP_DMIC_UP3_ENABLE;
+		/* fall through */
 	case 4:
 		dmic->ch_enabled |= OMAP_DMIC_UP2_ENABLE;
+		/* fall through */
 	case 2:
 		dmic->ch_enabled |= OMAP_DMIC_UP1_ENABLE;
 		break;
-- 
cgit v1.2.3


From 5019027a566de4986a7f66017cf0d6d794fc155f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 11:33:57 -0500
Subject: ASoC: samsung: i2s: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1381093 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/samsung/i2s.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/samsung/i2s.c b/sound/soc/samsung/i2s.c
index f914ed45db7d..d6c62aa13041 100644
--- a/sound/soc/samsung/i2s.c
+++ b/sound/soc/samsung/i2s.c
@@ -710,6 +710,7 @@ static int i2s_hw_params(struct snd_pcm_substream *substream,
 	switch (params_channels(params)) {
 	case 6:
 		val |= MOD_DC2_EN;
+		/* fall through */
 	case 4:
 		val |= MOD_DC1_EN;
 		break;
-- 
cgit v1.2.3


From 1f5cd2a0107d4ed95cbd9118e6a5f7ccd3d4d12a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 3 Aug 2018 12:38:34 +0200
Subject: l2tp: define l2tp_tunnel_dst_mtu()

Consolidate retrieval of tunnel's socket mtu in order to simplify
l2tp_eth and l2tp_ppp a bit.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.h | 18 ++++++++++++++++++
 net/l2tp/l2tp_eth.c  | 14 ++++----------
 net/l2tp/l2tp_ppp.c  | 15 ++++-----------
 3 files changed, 26 insertions(+), 21 deletions(-)

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index fa5ae9432d38..1ca39629031b 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -12,6 +12,9 @@
 #ifndef _L2TP_CORE_H_
 #define _L2TP_CORE_H_
 
+#include <net/dst.h>
+#include <net/sock.h>
+
 /* Just some random numbers */
 #define L2TP_TUNNEL_MAGIC	0x42114DDA
 #define L2TP_SESSION_MAGIC	0x0C04EB7D
@@ -268,6 +271,21 @@ static inline int l2tp_get_l2specific_len(struct l2tp_session *session)
 	}
 }
 
+static inline u32 l2tp_tunnel_dst_mtu(const struct l2tp_tunnel *tunnel)
+{
+	struct dst_entry *dst;
+	u32 mtu;
+
+	dst = sk_dst_get(tunnel->sock);
+	if (!dst)
+		return 0;
+
+	mtu = dst_mtu(dst);
+	dst_release(dst);
+
+	return mtu;
+}
+
 #define l2tp_printk(ptr, type, func, fmt, ...)				\
 do {									\
 	if (((ptr)->debug) & (type))					\
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 5c366ecfa1cb..cfca5e63ae31 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -226,8 +226,8 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
 				struct net_device *dev)
 {
 	unsigned int overhead = 0;
-	struct dst_entry *dst;
 	u32 l3_overhead = 0;
+	u32 mtu;
 
 	/* if the encap is UDP, account for UDP header size */
 	if (tunnel->encap == L2TP_ENCAPTYPE_UDP) {
@@ -256,15 +256,9 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
 	overhead += session->hdr_len + ETH_HLEN + l3_overhead;
 
 	/* If PMTU discovery was enabled, use discovered MTU on L2TP device */
-	dst = sk_dst_get(tunnel->sock);
-	if (dst) {
-		/* dst_mtu will use PMTU if found, else fallback to intf MTU */
-		u32 pmtu = dst_mtu(dst);
-
-		if (pmtu != 0)
-			dev->mtu = pmtu;
-		dst_release(dst);
-	}
+	mtu = l2tp_tunnel_dst_mtu(tunnel);
+	if (mtu)
+		dev->mtu = mtu;
 	session->mtu = dev->mtu - overhead;
 	dev->mtu = session->mtu;
 	dev->needed_headroom += session->hdr_len;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 44cac66284a5..1c6da02f976a 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -93,7 +93,6 @@
 #include <linux/nsproxy.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
-#include <net/dst.h>
 #include <net/ip.h>
 #include <net/udp.h>
 #include <net/xfrm.h>
@@ -554,7 +553,7 @@ static void pppol2tp_show(struct seq_file *m, void *arg)
 static void pppol2tp_session_init(struct l2tp_session *session)
 {
 	struct pppol2tp_session *ps;
-	struct dst_entry *dst;
+	u32 mtu;
 
 	session->recv_skb = pppol2tp_recv;
 #if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
@@ -566,15 +565,9 @@ static void pppol2tp_session_init(struct l2tp_session *session)
 	ps->owner = current->pid;
 
 	/* If PMTU discovery was enabled, use the MTU that was discovered */
-	dst = sk_dst_get(session->tunnel->sock);
-	if (dst) {
-		u32 pmtu = dst_mtu(dst);
-
-		if (pmtu)
-			session->mtu = pmtu - PPPOL2TP_HEADER_OVERHEAD;
-
-		dst_release(dst);
-	}
+	mtu = l2tp_tunnel_dst_mtu(session->tunnel);
+	if (mtu)
+		session->mtu = mtu - PPPOL2TP_HEADER_OVERHEAD;
 }
 
 struct l2tp_connect_info {
-- 
cgit v1.2.3


From 789141b215fc509defdd0f0978e4bf1bb5b31fc2 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 3 Aug 2018 12:38:37 +0200
Subject: l2tp: simplify MTU handling in l2tp_ppp

The value of the session's .mtu field, as defined by
pppol2tp_connect() or pppol2tp_session_create(), is later overwritten
by pppol2tp_session_init() (unless getting the tunnel's socket PMTU
fails). This field is then only used when setting the PPP channel's MTU
in pppol2tp_connect().
Furthermore, the SIOC[GS]IFMTU ioctls only act on the session's .mtu
without propagating this value to the PPP channel, making them useless.

This patch initialises the PPP channel's MTU directly and ignores the
session's .mtu entirely. MTU is still computed by subtracting the
PPPOL2TP_HEADER_OVERHEAD constant. It is not optimal, but that doesn't
really matter: po->chan.mtu is only used when the channel is part of a
multilink PPP bundle. Running multilink PPP over packet switched
networks is certainly not going to be efficient, so not picking the
best MTU does not harm (in the worst case, packets will just be
fragmented by the underlay).

The SIOC[GS]IFMTU ioctls are removed entirely (as opposed to simply
ignored), because these ioctls commands are part of the requests that
should be handled generically by the socket layer. PX_PROTO_OL2TP was
the only socket type abusing these ioctls.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 67 ++++++++++++++---------------------------------------
 1 file changed, 18 insertions(+), 49 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 1c6da02f976a..b403728e2757 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -553,7 +553,6 @@ static void pppol2tp_show(struct seq_file *m, void *arg)
 static void pppol2tp_session_init(struct l2tp_session *session)
 {
 	struct pppol2tp_session *ps;
-	u32 mtu;
 
 	session->recv_skb = pppol2tp_recv;
 #if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
@@ -563,11 +562,6 @@ static void pppol2tp_session_init(struct l2tp_session *session)
 	ps = l2tp_session_priv(session);
 	mutex_init(&ps->sk_lock);
 	ps->owner = current->pid;
-
-	/* If PMTU discovery was enabled, use the MTU that was discovered */
-	mtu = l2tp_tunnel_dst_mtu(session->tunnel);
-	if (mtu)
-		session->mtu = mtu - PPPOL2TP_HEADER_OVERHEAD;
 }
 
 struct l2tp_connect_info {
@@ -654,6 +648,22 @@ static int pppol2tp_sockaddr_get_info(const void *sa, int sa_len,
 	return 0;
 }
 
+/* Rough estimation of the maximum payload size a tunnel can transmit without
+ * fragmenting at the lower IP layer. Assumes L2TPv2 with sequence
+ * numbers and no IP option. Not quite accurate, but the result is mostly
+ * unused anyway.
+ */
+static int pppol2tp_tunnel_mtu(const struct l2tp_tunnel *tunnel)
+{
+	int mtu;
+
+	mtu = l2tp_tunnel_dst_mtu(tunnel);
+	if (mtu <= PPPOL2TP_HEADER_OVERHEAD)
+		return 1500 - PPPOL2TP_HEADER_OVERHEAD;
+
+	return mtu - PPPOL2TP_HEADER_OVERHEAD;
+}
+
 /* connect() handler. Attach a PPPoX socket to a tunnel UDP socket
  */
 static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
@@ -771,8 +781,6 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 			goto end;
 		}
 	} else {
-		/* Default MTU must allow space for UDP/L2TP/PPP headers */
-		cfg.mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
 		cfg.pw_type = L2TP_PWTYPE_PPP;
 
 		session = l2tp_session_create(sizeof(struct pppol2tp_session),
@@ -817,7 +825,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 
 	po->chan.private = sk;
 	po->chan.ops	 = &pppol2tp_chan_ops;
-	po->chan.mtu	 = session->mtu;
+	po->chan.mtu	 = pppol2tp_tunnel_mtu(tunnel);
 
 	error = ppp_register_net_channel(sock_net(sk), &po->chan);
 	if (error) {
@@ -873,10 +881,6 @@ static int pppol2tp_session_create(struct net *net, struct l2tp_tunnel *tunnel,
 		goto err;
 	}
 
-	/* Default MTU values. */
-	if (cfg->mtu == 0)
-		cfg->mtu = 1500 - PPPOL2TP_HEADER_OVERHEAD;
-
 	/* Allocate and initialize a new session context. */
 	session = l2tp_session_create(sizeof(struct pppol2tp_session),
 				      tunnel, session_id,
@@ -1040,7 +1044,6 @@ static void pppol2tp_copy_stats(struct pppol2tp_ioc_stats *dest,
 static int pppol2tp_session_ioctl(struct l2tp_session *session,
 				  unsigned int cmd, unsigned long arg)
 {
-	struct ifreq ifr;
 	int err = 0;
 	struct sock *sk;
 	int val = (int) arg;
@@ -1056,39 +1059,6 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 		return -EBADR;
 
 	switch (cmd) {
-	case SIOCGIFMTU:
-		err = -ENXIO;
-		if (!(sk->sk_state & PPPOX_CONNECTED))
-			break;
-
-		err = -EFAULT;
-		if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
-			break;
-		ifr.ifr_mtu = session->mtu;
-		if (copy_to_user((void __user *) arg, &ifr, sizeof(struct ifreq)))
-			break;
-
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: get mtu=%d\n",
-			  session->name, session->mtu);
-		err = 0;
-		break;
-
-	case SIOCSIFMTU:
-		err = -ENXIO;
-		if (!(sk->sk_state & PPPOX_CONNECTED))
-			break;
-
-		err = -EFAULT;
-		if (copy_from_user(&ifr, (void __user *) arg, sizeof(struct ifreq)))
-			break;
-
-		session->mtu = ifr.ifr_mtu;
-
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: set mtu=%d\n",
-			  session->name, session->mtu);
-		err = 0;
-		break;
-
 	case PPPIOCGMRU:
 	case PPPIOCGFLAGS:
 		err = -EFAULT;
@@ -1685,8 +1655,7 @@ static void pppol2tp_seq_session_show(struct seq_file *m, void *v)
 		   tunnel->peer_tunnel_id,
 		   session->peer_session_id,
 		   state, user_data_ok);
-	seq_printf(m, "   %d/0/%c/%c/%s %08x %u\n",
-		   session->mtu,
+	seq_printf(m, "   0/0/%c/%c/%s %08x %u\n",
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
-- 
cgit v1.2.3


From e9697e2effad50c0081b3c72002d3975f8ab4347 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 3 Aug 2018 12:38:39 +0200
Subject: l2tp: ignore L2TP_ATTR_MTU

This attribute's handling is broken. It can only be used when creating
Ethernet pseudo-wires, in which case its value can be used as the
initial MTU for the l2tpeth device.
However, when handling update requests, L2TP_ATTR_MTU only modifies
session->mtu. This value is never propagated to the l2tpeth device.
Dump requests also return the value of session->mtu, which is not
synchronised anymore with the device MTU.

The same problem occurs if the device MTU is properly updated using the
generic IFLA_MTU attribute. In this case, session->mtu is not updated,
and L2TP_ATTR_MTU will report an invalid value again when dumping the
session.

It does not seem worthwhile to complexify l2tp_eth.c to synchronise
session->mtu with the device MTU. Even the ip-l2tp manpage advises to
use 'ip link' to initialise the MTU of l2tpeth devices (iproute2 does
not handle L2TP_ATTR_MTU at all anyway). So let's just ignore it
entirely.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/l2tp.h |  2 +-
 net/l2tp/l2tp_core.c      |  1 -
 net/l2tp/l2tp_core.h      |  2 --
 net/l2tp/l2tp_debugfs.c   |  3 +--
 net/l2tp/l2tp_eth.c       | 17 +++++++----------
 net/l2tp/l2tp_netlink.c   |  9 +--------
 6 files changed, 10 insertions(+), 24 deletions(-)

diff --git a/include/uapi/linux/l2tp.h b/include/uapi/linux/l2tp.h
index 8bb8c7cfabe5..61158f5a1a5b 100644
--- a/include/uapi/linux/l2tp.h
+++ b/include/uapi/linux/l2tp.h
@@ -119,7 +119,7 @@ enum {
 	L2TP_ATTR_IP_DADDR,		/* u32 */
 	L2TP_ATTR_UDP_SPORT,		/* u16 */
 	L2TP_ATTR_UDP_DPORT,		/* u16 */
-	L2TP_ATTR_MTU,			/* u16 */
+	L2TP_ATTR_MTU,			/* u16 (not used) */
 	L2TP_ATTR_MRU,			/* u16 (not used) */
 	L2TP_ATTR_STATS,		/* nested */
 	L2TP_ATTR_IP6_SADDR,		/* struct in6_addr */
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index c61a467fd9b8..ac6a00bcec71 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1674,7 +1674,6 @@ struct l2tp_session *l2tp_session_create(int priv_size, struct l2tp_tunnel *tunn
 		if (cfg) {
 			session->pwtype = cfg->pw_type;
 			session->debug = cfg->debug;
-			session->mtu = cfg->mtu;
 			session->send_seq = cfg->send_seq;
 			session->recv_seq = cfg->recv_seq;
 			session->lns_mode = cfg->lns_mode;
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 1ca39629031b..5804065dfbfb 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -64,7 +64,6 @@ struct l2tp_session_cfg {
 	int			peer_cookie_len; /* 0, 4 or 8 bytes */
 	int			reorder_timeout; /* configured reorder timeout
 						  * (in jiffies) */
-	int			mtu;
 	char			*ifname;
 };
 
@@ -108,7 +107,6 @@ struct l2tp_session {
 	int			reorder_timeout; /* configured reorder timeout
 						  * (in jiffies) */
 	int			reorder_skip;	/* set if skip to next nr */
-	int			mtu;
 	enum l2tp_pwtype	pwtype;
 	struct l2tp_stats	stats;
 	struct hlist_node	global_hlist;	/* Global hash list node */
diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c
index aee271741f5b..9821a1458555 100644
--- a/net/l2tp/l2tp_debugfs.c
+++ b/net/l2tp/l2tp_debugfs.c
@@ -191,8 +191,7 @@ static void l2tp_dfs_seq_session_show(struct seq_file *m, void *v)
 	if (session->send_seq || session->recv_seq)
 		seq_printf(m, "   nr %hu, ns %hu\n", session->nr, session->ns);
 	seq_printf(m, "   refcnt %d\n", refcount_read(&session->ref_count));
-	seq_printf(m, "   config %d/0/%c/%c/-/%s %08x %u\n",
-		   session->mtu,
+	seq_printf(m, "   config 0/0/%c/%c/-/%s %08x %u\n",
 		   session->recv_seq ? 'R' : '-',
 		   session->send_seq ? 'S' : '-',
 		   session->lns_mode ? "LNS" : "LAC",
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index cfca5e63ae31..3728986ec885 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -234,14 +234,11 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
 		overhead += sizeof(struct udphdr);
 		dev->needed_headroom += sizeof(struct udphdr);
 	}
-	if (session->mtu != 0) {
-		dev->mtu = session->mtu;
-		dev->needed_headroom += session->hdr_len;
-		return;
-	}
+
 	lock_sock(tunnel->sock);
 	l3_overhead = kernel_sock_ip_overhead(tunnel->sock);
 	release_sock(tunnel->sock);
+
 	if (l3_overhead == 0) {
 		/* L3 Overhead couldn't be identified, this could be
 		 * because tunnel->sock was NULL or the socket's
@@ -255,12 +252,12 @@ static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
 	 */
 	overhead += session->hdr_len + ETH_HLEN + l3_overhead;
 
-	/* If PMTU discovery was enabled, use discovered MTU on L2TP device */
-	mtu = l2tp_tunnel_dst_mtu(tunnel);
-	if (mtu)
+	mtu = l2tp_tunnel_dst_mtu(tunnel) - overhead;
+	if (mtu < dev->min_mtu || mtu > dev->max_mtu)
+		dev->mtu = ETH_DATA_LEN - overhead;
+	else
 		dev->mtu = mtu;
-	session->mtu = dev->mtu - overhead;
-	dev->mtu = session->mtu;
+
 	dev->needed_headroom += session->hdr_len;
 }
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index a7c409215336..2e1e92651545 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -608,9 +608,6 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_RECV_TIMEOUT])
 		cfg.reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]);
 
-	if (info->attrs[L2TP_ATTR_MTU])
-		cfg.mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]);
-
 #ifdef CONFIG_MODULES
 	if (l2tp_nl_cmd_ops[cfg.pw_type] == NULL) {
 		genl_unlock();
@@ -698,9 +695,6 @@ static int l2tp_nl_cmd_session_modify(struct sk_buff *skb, struct genl_info *inf
 	if (info->attrs[L2TP_ATTR_RECV_TIMEOUT])
 		session->reorder_timeout = nla_get_msecs(info->attrs[L2TP_ATTR_RECV_TIMEOUT]);
 
-	if (info->attrs[L2TP_ATTR_MTU])
-		session->mtu = nla_get_u16(info->attrs[L2TP_ATTR_MTU]);
-
 	ret = l2tp_session_notify(&l2tp_nl_family, info,
 				  session, L2TP_CMD_SESSION_MODIFY);
 
@@ -730,8 +724,7 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	    nla_put_u32(skb, L2TP_ATTR_PEER_SESSION_ID,
 			session->peer_session_id) ||
 	    nla_put_u32(skb, L2TP_ATTR_DEBUG, session->debug) ||
-	    nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype) ||
-	    nla_put_u16(skb, L2TP_ATTR_MTU, session->mtu))
+	    nla_put_u16(skb, L2TP_ATTR_PW_TYPE, session->pwtype))
 		goto nla_put_failure;
 
 	if ((session->ifname[0] &&
-- 
cgit v1.2.3


From 973232e2a327cbf30b50b678af081426ca403088 Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@systec-electronic.com>
Date: Thu, 2 Aug 2018 12:53:18 +0200
Subject: pinctrl: baytrail: actually print the apparently misconfigured pin

For further investigation the actual result in interrupt status register
is needed.

Signed-off-by: Alexander Stein <alexander.stein@systec-electronic.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/pinctrl-baytrail.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 003ad48a607f..f38d596efa05 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1685,7 +1685,8 @@ static void byt_gpio_irq_init_hw(struct byt_gpio *vg)
 		value = readl(reg);
 		if (value)
 			dev_err(&vg->pdev->dev,
-				"GPIO interrupt error, pins misconfigured\n");
+				"GPIO interrupt error, pins misconfigured. INT_STAT%u: 0x%08x\n",
+				base / 32, value);
 	}
 }
 
-- 
cgit v1.2.3


From 1e0813ee5599932c856bda64a568895ed7a33d3a Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Thu, 2 Aug 2018 14:11:43 +0300
Subject: pinctrl: tegra: Move drivers registration to arch_init level

There is a bug in regards to deferred probing within the drivers core
that causes GPIO-driver to suspend after its users. The bug appears if
GPIO-driver probe is getting deferred, which happens after introducing
dependency on PINCTRL-driver for the GPIO-driver by defining "gpio-ranges"
property in device-tree. The bug in the drivers core is old (more than 4
years now) and is well known, unfortunately there is no easy fix for it.
The good news is that we can workaround the deferred probe issue by
changing GPIO / PINCTRL drivers registration order and hence by moving
PINCTRL driver registration to the arch_init level and GPIO to the
subsys_init.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Acked-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/tegra/pinctrl-tegra114.c | 7 ++++++-
 drivers/pinctrl/tegra/pinctrl-tegra124.c | 7 ++++++-
 drivers/pinctrl/tegra/pinctrl-tegra20.c  | 7 ++++++-
 drivers/pinctrl/tegra/pinctrl-tegra210.c | 7 ++++++-
 drivers/pinctrl/tegra/pinctrl-tegra30.c  | 7 ++++++-
 5 files changed, 30 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/tegra/pinctrl-tegra114.c b/drivers/pinctrl/tegra/pinctrl-tegra114.c
index 511a8774fd8d..d43c209e9c30 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra114.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra114.c
@@ -1868,4 +1868,9 @@ static struct platform_driver tegra114_pinctrl_driver = {
 	},
 	.probe = tegra114_pinctrl_probe,
 };
-builtin_platform_driver(tegra114_pinctrl_driver);
+
+static int __init tegra114_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra114_pinctrl_driver);
+}
+arch_initcall(tegra114_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra124.c b/drivers/pinctrl/tegra/pinctrl-tegra124.c
index 57e3cdcf4503..5b07a5834d15 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra124.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra124.c
@@ -2080,4 +2080,9 @@ static struct platform_driver tegra124_pinctrl_driver = {
 	},
 	.probe = tegra124_pinctrl_probe,
 };
-builtin_platform_driver(tegra124_pinctrl_driver);
+
+static int __init tegra124_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra124_pinctrl_driver);
+}
+arch_initcall(tegra124_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra20.c b/drivers/pinctrl/tegra/pinctrl-tegra20.c
index 624889ed3a9d..1fc82a9576e0 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra20.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra20.c
@@ -2277,4 +2277,9 @@ static struct platform_driver tegra20_pinctrl_driver = {
 	},
 	.probe = tegra20_pinctrl_probe,
 };
-builtin_platform_driver(tegra20_pinctrl_driver);
+
+static int __init tegra20_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra20_pinctrl_driver);
+}
+arch_initcall(tegra20_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra210.c b/drivers/pinctrl/tegra/pinctrl-tegra210.c
index 0956a1c73391..3e77f5474dd8 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra210.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra210.c
@@ -1582,4 +1582,9 @@ static struct platform_driver tegra210_pinctrl_driver = {
 	},
 	.probe = tegra210_pinctrl_probe,
 };
-builtin_platform_driver(tegra210_pinctrl_driver);
+
+static int __init tegra210_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra210_pinctrl_driver);
+}
+arch_initcall(tegra210_pinctrl_init);
diff --git a/drivers/pinctrl/tegra/pinctrl-tegra30.c b/drivers/pinctrl/tegra/pinctrl-tegra30.c
index c923ad58af84..10e617003e9c 100644
--- a/drivers/pinctrl/tegra/pinctrl-tegra30.c
+++ b/drivers/pinctrl/tegra/pinctrl-tegra30.c
@@ -2503,4 +2503,9 @@ static struct platform_driver tegra30_pinctrl_driver = {
 	},
 	.probe = tegra30_pinctrl_probe,
 };
-builtin_platform_driver(tegra30_pinctrl_driver);
+
+static int __init tegra30_pinctrl_init(void)
+{
+	return platform_driver_register(&tegra30_pinctrl_driver);
+}
+arch_initcall(tegra30_pinctrl_init);
-- 
cgit v1.2.3


From 40b25bce0adbe641a744d1291bc0e51fb7f3c3d8 Mon Sep 17 00:00:00 2001
From: Dmitry Osipenko <digetx@gmail.com>
Date: Thu, 2 Aug 2018 14:11:44 +0300
Subject: gpio: tegra: Move driver registration to subsys_init level

There is a bug in regards to deferred probing within the drivers core
that causes GPIO-driver to suspend after its users. The bug appears if
GPIO-driver probe is getting deferred, which happens after introducing
dependency on PINCTRL-driver for the GPIO-driver by defining "gpio-ranges"
property in device-tree. The bug in the drivers core is old (more than 4
years now) and is well known, unfortunately there is no easy fix for it.
The good news is that we can workaround the deferred probe issue by
changing GPIO / PINCTRL drivers registration order and hence by moving
PINCTRL driver registration to the arch_init level and GPIO to the
subsys_init.

Signed-off-by: Dmitry Osipenko <digetx@gmail.com>
Acked-by: Stefan Agner <stefan@agner.ch>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tegra.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 94396caaca75..d5d79727c55d 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -720,4 +720,4 @@ static int __init tegra_gpio_init(void)
 {
 	return platform_driver_register(&tegra_gpio_driver);
 }
-postcore_initcall(tegra_gpio_init);
+subsys_initcall(tegra_gpio_init);
-- 
cgit v1.2.3


From b5031b7db77dc47f474f0efc2b2552c32b7bb59d Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 1 Aug 2018 13:10:49 +0800
Subject: pinctrl: berlin: fix 'pctrl->functions' allocation in
 berlin_pinctrl_build_state

fixes following Smatch static check warning:

 drivers/pinctrl/berlin/berlin.c:237 berlin_pinctrl_build_state()
 warn: passing devm_ allocated variable to kfree. 'pctrl->functions'

As we will be calling krealloc() on pointer 'pctrl->functions', which means
kfree() will be called in there, devm_kzalloc() shouldn't be used with
the allocation in the first place.  Fix the warning by calling kcalloc()
and managing the free procedure in error path on our own.

Fixes: 3de68d331c24 ("pinctrl: berlin: add the core pinctrl driver for Marvell Berlin SoCs")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/berlin/berlin.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/berlin/berlin.c b/drivers/pinctrl/berlin/berlin.c
index d6d183e9db17..b5903fffb3d0 100644
--- a/drivers/pinctrl/berlin/berlin.c
+++ b/drivers/pinctrl/berlin/berlin.c
@@ -216,10 +216,8 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 	}
 
 	/* we will reallocate later */
-	pctrl->functions = devm_kcalloc(&pdev->dev,
-					max_functions,
-					sizeof(*pctrl->functions),
-					GFP_KERNEL);
+	pctrl->functions = kcalloc(max_functions,
+				   sizeof(*pctrl->functions), GFP_KERNEL);
 	if (!pctrl->functions)
 		return -ENOMEM;
 
@@ -257,8 +255,10 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 				function++;
 			}
 
-			if (!found)
+			if (!found) {
+				kfree(pctrl->functions);
 				return -EINVAL;
+			}
 
 			if (!function->groups) {
 				function->groups =
@@ -267,8 +267,10 @@ static int berlin_pinctrl_build_state(struct platform_device *pdev)
 						     sizeof(char *),
 						     GFP_KERNEL);
 
-				if (!function->groups)
+				if (!function->groups) {
+					kfree(pctrl->functions);
 					return -ENOMEM;
+				}
 			}
 
 			groups = function->groups;
-- 
cgit v1.2.3


From cb85d2b04b408ba8328eb5fa1e184cc538ba8c6a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:30 +0300
Subject: pinctrl: intel: Don't shadow error code of gpiochip_lock_as_irq()

gpiochip_lock_as_irq() may return a few error codes,
do not shadow them by -EINVAL and let caller to decide.

No functional change intended.

Cc: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/intel/pinctrl-intel.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index d023b64825d0..62b009b27eda 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -877,13 +877,15 @@ static int intel_gpio_irq_reqres(struct irq_data *d)
 	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
 	struct intel_pinctrl *pctrl = gpiochip_get_data(gc);
 	int pin;
+	int ret;
 
 	pin = intel_gpio_to_pin(pctrl, irqd_to_hwirq(d), NULL, NULL);
 	if (pin >= 0) {
-		if (gpiochip_lock_as_irq(gc, pin)) {
+		ret = gpiochip_lock_as_irq(gc, pin);
+		if (ret) {
 			dev_err(pctrl->dev, "unable to lock HW IRQ %d for IRQ\n",
 				pin);
-			return -EINVAL;
+			return ret;
 		}
 	}
 	return 0;
-- 
cgit v1.2.3


From 033eab53fff7acc0f5718dee6fda641734b94416 Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Thu, 2 Aug 2018 21:18:31 +0200
Subject: netfilter: nft_tproxy: Add missing config check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A config check was missing form the code when using
nf_defrag_ipv6_enable with NFT_TPROXY != n and NF_DEFRAG_IPV6 = n and
this caused the following error:

../net/netfilter/nft_tproxy.c: In function 'nft_tproxy_init':
../net/netfilter/nft_tproxy.c:237:3: error: implicit declaration of function
+'nf_defrag_ipv6_enable' [-Werror=implicit-function-declaration]
   err = nf_defrag_ipv6_enable(ctx->net);

This patch adds a check for NF_TABLES_IPV6 when NF_DEFRAG_IPV6 is
selected by Kconfig.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Fixes: 4ed8eb6570a4 ("netfilter: nf_tables: Add native tproxy support")
Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_tproxy.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c
index c6845f7baa08..eff99dffc842 100644
--- a/net/netfilter/nft_tproxy.c
+++ b/net/netfilter/nft_tproxy.c
@@ -234,9 +234,11 @@ static int nft_tproxy_init(const struct nft_ctx *ctx,
 		err = nf_defrag_ipv4_enable(ctx->net);
 		if (err)
 			return err;
+#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
 		err = nf_defrag_ipv6_enable(ctx->net);
 		if (err)
 			return err;
+#endif
 		break;
 	default:
 		return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 2104bc0ab0eee8a4768dd80df8ed42eb591543bc Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 3 Aug 2018 11:08:41 -0700
Subject: net: dsa: bcm_sf2: Allow targeting CPU ports for CFP rules

ds->enabled_port_mask only contains a bitmask of user-facing enabled
ports, we also need to allow programming CFP rules that target CPU ports
(e.g: ports 5 and 8).

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index b89acaee12d4..1e37b65aab93 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -755,7 +755,8 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	port_num = fs->ring_cookie / SF2_NUM_EGRESS_QUEUES;
 
 	if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
-	    !dsa_is_user_port(ds, port_num) ||
+	    !(dsa_is_user_port(ds, port_num) ||
+	      dsa_is_cpu_port(ds, port_num)) ||
 	    port_num >= priv->hw_params.num_ports)
 		return -EINVAL;
 	/*
-- 
cgit v1.2.3


From c0e6820b7e4175171f302df6cc4706b818f4a691 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 3 Aug 2018 11:08:42 -0700
Subject: net: dsa: bcm_sf2: Disable learning while in WoL

When we are in Wake-on-LAN, we operate with the host sofware not running
a network stack, so we want to the switch to flood packets in order to
cause a system wake-up when matching specific filters (unicast or
multicast). This was not necessary before since we supported Magic
Packet which are targeting a broadcast MAC address which the switch
already floods.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2.c      | 12 +++++++++++-
 drivers/net/dsa/bcm_sf2_regs.h |  2 ++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
index ac96ff40d37e..e0066adcd2f3 100644
--- a/drivers/net/dsa/bcm_sf2.c
+++ b/drivers/net/dsa/bcm_sf2.c
@@ -166,6 +166,11 @@ static int bcm_sf2_port_setup(struct dsa_switch *ds, int port,
 	reg &= ~P_TXQ_PSM_VDD(port);
 	core_writel(priv, reg, CORE_MEM_PSM_VDD_CTRL);
 
+	/* Enable learning */
+	reg = core_readl(priv, CORE_DIS_LEARN);
+	reg &= ~BIT(port);
+	core_writel(priv, reg, CORE_DIS_LEARN);
+
 	/* Enable Broadcom tags for that port if requested */
 	if (priv->brcm_tag_mask & BIT(port))
 		b53_brcm_hdr_setup(ds, port);
@@ -222,8 +227,13 @@ static void bcm_sf2_port_disable(struct dsa_switch *ds, int port,
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	u32 reg;
 
-	if (priv->wol_ports_mask & (1 << port))
+	/* Disable learning while in WoL mode */
+	if (priv->wol_ports_mask & (1 << port)) {
+		reg = core_readl(priv, CORE_DIS_LEARN);
+		reg |= BIT(port);
+		core_writel(priv, reg, CORE_DIS_LEARN);
 		return;
+	}
 
 	if (port == priv->moca_port)
 		bcm_sf2_port_intr_disable(priv, port);
diff --git a/drivers/net/dsa/bcm_sf2_regs.h b/drivers/net/dsa/bcm_sf2_regs.h
index 3ccd5a865dcb..0a1e530d52b7 100644
--- a/drivers/net/dsa/bcm_sf2_regs.h
+++ b/drivers/net/dsa/bcm_sf2_regs.h
@@ -168,6 +168,8 @@ enum bcm_sf2_reg_offs {
 #define CORE_SWITCH_CTRL		0x00088
 #define  MII_DUMB_FWDG_EN		(1 << 6)
 
+#define CORE_DIS_LEARN			0x000f0
+
 #define CORE_SFT_LRN_CTRL		0x000f8
 #define  SW_LEARN_CNTL(x)		(1 << (x))
 
-- 
cgit v1.2.3


From 9e85e22713d6fed4873057493d6307c08b1d86a6 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 3 Aug 2018 11:08:43 -0700
Subject: net: systemport: Do not re-configure upon WoL interrupt

We already properly resume from Wake-on-LAN whether such a condition
occured or not, no need to process the WoL interrupt for functional
changes since that could race with other settings.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 631617d95769..7faad9e1a6f9 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1102,10 +1102,8 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
 	if (priv->irq0_stat & INTRL2_0_TX_RING_FULL)
 		bcm_sysport_tx_reclaim_all(priv);
 
-	if (priv->irq0_stat & INTRL2_0_MPD) {
+	if (priv->irq0_stat & INTRL2_0_MPD)
 		netdev_info(priv->netdev, "Wake-on-LAN interrupt!\n");
-		bcm_sysport_resume_from_wol(priv);
-	}
 
 	if (!priv->is_lite)
 		goto out;
-- 
cgit v1.2.3


From 54226116add4dcfe6391ffb810225f78c9c3d245 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Fri, 3 Aug 2018 11:08:44 -0700
Subject: net: systemport: Create helper to set MPD

Create a helper function to turn on/off MPD, this will be used to avoid
duplicating code as we are going to add additional types of wake-up
types.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 7faad9e1a6f9..284581c9680e 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -1041,17 +1041,25 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
+static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable)
 {
 	u32 reg;
 
+	reg = umac_readl(priv, UMAC_MPD_CTRL);
+	if (enable)
+		reg |= MPD_EN;
+	else
+		reg &= ~MPD_EN;
+	umac_writel(priv, reg, UMAC_MPD_CTRL);
+}
+
+static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
+{
 	/* Stop monitoring MPD interrupt */
 	intrl2_0_mask_set(priv, INTRL2_0_MPD);
 
 	/* Clear the MagicPacket detection logic */
-	reg = umac_readl(priv, UMAC_MPD_CTRL);
-	reg &= ~MPD_EN;
-	umac_writel(priv, reg, UMAC_MPD_CTRL);
+	mpd_enable_set(priv, false);
 
 	netif_dbg(priv, wol, priv->netdev, "resumed from WOL\n");
 }
@@ -2447,9 +2455,7 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 
 	/* Do not leave the UniMAC RBUF matching only MPD packets */
 	if (!timeout) {
-		reg = umac_readl(priv, UMAC_MPD_CTRL);
-		reg &= ~MPD_EN;
-		umac_writel(priv, reg, UMAC_MPD_CTRL);
+		mpd_enable_set(priv, false);
 		netif_err(priv, wol, ndev, "failed to enter WOL mode\n");
 		return -ETIMEDOUT;
 	}
-- 
cgit v1.2.3


From af308b94a2a4a5a27bec9028354c4df444a7c8ba Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 2 Aug 2018 20:51:39 +0200
Subject: netfilter: nf_tables: add tunnel support

This patch implements the tunnel object type that can be used to
configure tunnels via metadata template through the existing lightweight
API from the ingress path.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  69 ++++-
 net/core/dst.c                           |   1 +
 net/netfilter/Kconfig                    |   6 +
 net/netfilter/Makefile                   |   1 +
 net/netfilter/nft_tunnel.c               | 458 +++++++++++++++++++++++++++++++
 5 files changed, 534 insertions(+), 1 deletion(-)
 create mode 100644 net/netfilter/nft_tunnel.c

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index f112ea52dc1a..3ee1198eeac1 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1416,7 +1416,8 @@ enum nft_ct_helper_attributes {
 #define NFT_OBJECT_CT_HELPER	3
 #define NFT_OBJECT_LIMIT	4
 #define NFT_OBJECT_CONNLIMIT	5
-#define __NFT_OBJECT_MAX	6
+#define NFT_OBJECT_TUNNEL	6
+#define __NFT_OBJECT_MAX	7
 #define NFT_OBJECT_MAX		(__NFT_OBJECT_MAX - 1)
 
 /**
@@ -1580,4 +1581,70 @@ enum nft_ng_types {
 };
 #define NFT_NG_MAX	(__NFT_NG_MAX - 1)
 
+enum nft_tunnel_key_ip_attributes {
+	NFTA_TUNNEL_KEY_IP_UNSPEC,
+	NFTA_TUNNEL_KEY_IP_SRC,
+	NFTA_TUNNEL_KEY_IP_DST,
+	__NFTA_TUNNEL_KEY_IP_MAX
+};
+#define NFTA_TUNNEL_KEY_IP_MAX	(__NFTA_TUNNEL_KEY_IP_MAX - 1)
+
+enum nft_tunnel_ip6_attributes {
+	NFTA_TUNNEL_KEY_IP6_UNSPEC,
+	NFTA_TUNNEL_KEY_IP6_SRC,
+	NFTA_TUNNEL_KEY_IP6_DST,
+	NFTA_TUNNEL_KEY_IP6_FLOWLABEL,
+	__NFTA_TUNNEL_KEY_IP6_MAX
+};
+#define NFTA_TUNNEL_KEY_IP6_MAX	(__NFTA_TUNNEL_KEY_IP6_MAX - 1)
+
+enum nft_tunnel_opts_attributes {
+	NFTA_TUNNEL_KEY_OPTS_UNSPEC,
+	NFTA_TUNNEL_KEY_OPTS_VXLAN,
+	NFTA_TUNNEL_KEY_OPTS_ERSPAN,
+	__NFTA_TUNNEL_KEY_OPTS_MAX
+};
+#define NFTA_TUNNEL_KEY_OPTS_MAX	(__NFTA_TUNNEL_KEY_OPTS_MAX - 1)
+
+enum nft_tunnel_opts_vxlan_attributes {
+	NFTA_TUNNEL_KEY_VXLAN_UNSPEC,
+	NFTA_TUNNEL_KEY_VXLAN_GBP,
+	__NFTA_TUNNEL_KEY_VXLAN_MAX
+};
+#define NFTA_TUNNEL_KEY_VXLAN_MAX	(__NFTA_TUNNEL_KEY_VXLAN_MAX - 1)
+
+enum nft_tunnel_opts_erspan_attributes {
+	NFTA_TUNNEL_KEY_ERSPAN_UNSPEC,
+	NFTA_TUNNEL_KEY_ERSPAN_VERSION,
+	NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX,
+	NFTA_TUNNEL_KEY_ERSPAN_V2_HWID,
+	NFTA_TUNNEL_KEY_ERSPAN_V2_DIR,
+	__NFTA_TUNNEL_KEY_ERSPAN_MAX
+};
+#define NFTA_TUNNEL_KEY_ERSPAN_MAX	(__NFTA_TUNNEL_KEY_ERSPAN_MAX - 1)
+
+enum nft_tunnel_flags {
+	NFT_TUNNEL_F_ZERO_CSUM_TX	= (1 << 0),
+	NFT_TUNNEL_F_DONT_FRAGMENT	= (1 << 1),
+	NFT_TUNNEL_F_SEQ_NUMBER		= (1 << 2),
+};
+#define NFT_TUNNEL_F_MASK	(NFT_TUNNEL_F_ZERO_CSUM_TX | \
+				 NFT_TUNNEL_F_DONT_FRAGMENT | \
+				 NFT_TUNNEL_F_SEQ_NUMBER)
+
+enum nft_tunnel_key_attributes {
+	NFTA_TUNNEL_KEY_UNSPEC,
+	NFTA_TUNNEL_KEY_ID,
+	NFTA_TUNNEL_KEY_IP,
+	NFTA_TUNNEL_KEY_IP6,
+	NFTA_TUNNEL_KEY_FLAGS,
+	NFTA_TUNNEL_KEY_TOS,
+	NFTA_TUNNEL_KEY_TTL,
+	NFTA_TUNNEL_KEY_SPORT,
+	NFTA_TUNNEL_KEY_DPORT,
+	NFTA_TUNNEL_KEY_OPTS,
+	__NFTA_TUNNEL_KEY_MAX
+};
+#define NFTA_TUNNEL_KEY_MAX	(__NFTA_TUNNEL_KEY_MAX - 1)
+
 #endif /* _LINUX_NF_TABLES_H */
diff --git a/net/core/dst.c b/net/core/dst.c
index 2d9b37f8944a..81ccf20e2826 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -307,6 +307,7 @@ void metadata_dst_free(struct metadata_dst *md_dst)
 #endif
 	kfree(md_dst);
 }
+EXPORT_SYMBOL_GPL(metadata_dst_free);
 
 struct metadata_dst __percpu *
 metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 55e399d5af10..654588088676 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -559,6 +559,12 @@ config NFT_NAT
 	  This option adds the "nat" expression that you can use to perform
 	  typical Network Address Translation (NAT) packet transformations.
 
+config NFT_TUNNEL
+	tristate "Netfilter nf_tables tunnel module"
+	help
+	  This option adds the "tunnel" expression that you can use to set
+	  tunneling policies.
+
 config NFT_OBJREF
 	tristate "Netfilter nf_tables stateful object reference module"
 	help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index cf61615cc529..16895e045b66 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -101,6 +101,7 @@ obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
 obj-$(CONFIG_NFT_QUOTA)		+= nft_quota.o
 obj-$(CONFIG_NFT_REJECT) 	+= nft_reject.o
 obj-$(CONFIG_NFT_REJECT_INET)	+= nft_reject_inet.o
+obj-$(CONFIG_NFT_TUNNEL)	+= nft_tunnel.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o
 obj-$(CONFIG_NFT_LOG)		+= nft_log.o
 obj-$(CONFIG_NFT_MASQ)		+= nft_masq.o
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
new file mode 100644
index 000000000000..715613d99c20
--- /dev/null
+++ b/net/netfilter/nft_tunnel.c
@@ -0,0 +1,458 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/seqlock.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/dst_metadata.h>
+#include <net/ip_tunnels.h>
+#include <net/vxlan.h>
+#include <net/erspan.h>
+
+struct nft_tunnel_opts {
+	union {
+		struct vxlan_metadata	vxlan;
+		struct erspan_metadata	erspan;
+	} u;
+	u32	len;
+	u32	flags;
+};
+
+struct nft_tunnel_obj {
+	struct metadata_dst	*md;
+	struct nft_tunnel_opts	opts;
+};
+
+static const struct nla_policy nft_tunnel_ip_policy[NFTA_TUNNEL_KEY_IP_MAX + 1] = {
+	[NFTA_TUNNEL_KEY_IP_SRC]	= { .type = NLA_U32 },
+	[NFTA_TUNNEL_KEY_IP_DST]	= { .type = NLA_U32 },
+};
+
+static int nft_tunnel_obj_ip_init(const struct nft_ctx *ctx,
+				  const struct nlattr *attr,
+				  struct ip_tunnel_info *info)
+{
+	struct nlattr *tb[NFTA_TUNNEL_KEY_IP_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP_MAX, attr,
+			       nft_tunnel_ip_policy, NULL);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFTA_TUNNEL_KEY_IP_DST])
+		return -EINVAL;
+
+	if (tb[NFTA_TUNNEL_KEY_IP_SRC])
+		info->key.u.ipv4.src = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_SRC]);
+	if (tb[NFTA_TUNNEL_KEY_IP_DST])
+		info->key.u.ipv4.dst = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP_DST]);
+
+	return 0;
+}
+
+static const struct nla_policy nft_tunnel_ip6_policy[NFTA_TUNNEL_KEY_IP6_MAX + 1] = {
+	[NFTA_TUNNEL_KEY_IP6_SRC]	= { .len = sizeof(struct in6_addr), },
+	[NFTA_TUNNEL_KEY_IP6_DST]	= { .len = sizeof(struct in6_addr), },
+	[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]	= { .type = NLA_U32, }
+};
+
+static int nft_tunnel_obj_ip6_init(const struct nft_ctx *ctx,
+				   const struct nlattr *attr,
+				   struct ip_tunnel_info *info)
+{
+	struct nlattr *tb[NFTA_TUNNEL_KEY_IP6_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_IP6_MAX, attr,
+			       nft_tunnel_ip6_policy, NULL);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFTA_TUNNEL_KEY_IP6_DST])
+		return -EINVAL;
+
+	if (tb[NFTA_TUNNEL_KEY_IP6_SRC]) {
+		memcpy(&info->key.u.ipv6.src,
+		       nla_data(tb[NFTA_TUNNEL_KEY_IP6_SRC]),
+		       sizeof(struct in6_addr));
+	}
+	if (tb[NFTA_TUNNEL_KEY_IP6_DST]) {
+		memcpy(&info->key.u.ipv6.dst,
+		       nla_data(tb[NFTA_TUNNEL_KEY_IP6_DST]),
+		       sizeof(struct in6_addr));
+	}
+	if (tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL])
+		info->key.label = nla_get_be32(tb[NFTA_TUNNEL_KEY_IP6_FLOWLABEL]);
+
+	info->mode |= IP_TUNNEL_INFO_IPV6;
+
+	return 0;
+}
+
+static const struct nla_policy nft_tunnel_opts_vxlan_policy[NFTA_TUNNEL_KEY_VXLAN_MAX + 1] = {
+	[NFTA_TUNNEL_KEY_VXLAN_GBP]	= { .type = NLA_U32 },
+};
+
+static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr,
+				     struct nft_tunnel_opts *opts)
+{
+	struct nlattr *tb[NFTA_TUNNEL_KEY_VXLAN_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_VXLAN_MAX, attr,
+			       nft_tunnel_opts_vxlan_policy, NULL);
+	if (err < 0)
+		return err;
+
+	if (!tb[NFTA_TUNNEL_KEY_VXLAN_GBP])
+		return -EINVAL;
+
+	opts->u.vxlan.gbp = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_VXLAN_GBP]));
+
+	opts->len	= sizeof(struct vxlan_metadata);
+	opts->flags	= TUNNEL_VXLAN_OPT;
+
+	return 0;
+}
+
+static const struct nla_policy nft_tunnel_opts_erspan_policy[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1] = {
+	[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]	= { .type = NLA_U32 },
+	[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR]	= { .type = NLA_U8 },
+	[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]	= { .type = NLA_U8 },
+};
+
+static int nft_tunnel_obj_erspan_init(const struct nlattr *attr,
+				      struct nft_tunnel_opts *opts)
+{
+	struct nlattr *tb[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1];
+	uint8_t hwid, dir;
+	int err, version;
+
+	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_ERSPAN_MAX, attr,
+			       nft_tunnel_opts_erspan_policy, NULL);
+	if (err < 0)
+		return err;
+
+	version = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION]));
+	switch (version) {
+	case ERSPAN_VERSION:
+		if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX])
+			return -EINVAL;
+
+		opts->u.erspan.u.index =
+			nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX]);
+		break;
+	case ERSPAN_VERSION2:
+		if (!tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] ||
+		    !tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID])
+			return -EINVAL;
+
+		hwid = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_HWID]);
+		dir = nla_get_u8(tb[NFTA_TUNNEL_KEY_ERSPAN_V2_DIR]);
+
+		set_hwid(&opts->u.erspan.u.md2, hwid);
+		opts->u.erspan.u.md2.dir = dir;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+	opts->u.erspan.version = version;
+
+	opts->len	= sizeof(struct erspan_metadata);
+	opts->flags	= TUNNEL_ERSPAN_OPT;
+
+	return 0;
+}
+
+static const struct nla_policy nft_tunnel_opts_policy[NFTA_TUNNEL_KEY_OPTS_MAX + 1] = {
+	[NFTA_TUNNEL_KEY_OPTS_VXLAN]	= { .type = NLA_NESTED, },
+	[NFTA_TUNNEL_KEY_OPTS_ERSPAN]	= { .type = NLA_NESTED, },
+};
+
+static int nft_tunnel_obj_opts_init(const struct nft_ctx *ctx,
+				    const struct nlattr *attr,
+				    struct ip_tunnel_info *info,
+				    struct nft_tunnel_opts *opts)
+{
+	struct nlattr *tb[NFTA_TUNNEL_KEY_OPTS_MAX + 1];
+	int err;
+
+	err = nla_parse_nested(tb, NFTA_TUNNEL_KEY_OPTS_MAX, attr,
+			       nft_tunnel_opts_policy, NULL);
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_TUNNEL_KEY_OPTS_VXLAN]) {
+		err = nft_tunnel_obj_vxlan_init(tb[NFTA_TUNNEL_KEY_OPTS_VXLAN],
+						opts);
+	} else if (tb[NFTA_TUNNEL_KEY_OPTS_ERSPAN]) {
+		err = nft_tunnel_obj_erspan_init(tb[NFTA_TUNNEL_KEY_OPTS_ERSPAN],
+						 opts);
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	return err;
+}
+
+static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] = {
+	[NFTA_TUNNEL_KEY_IP]	= { .type = NLA_NESTED, },
+	[NFTA_TUNNEL_KEY_IP6]	= { .type = NLA_NESTED, },
+	[NFTA_TUNNEL_KEY_ID]	= { .type = NLA_U32, },
+	[NFTA_TUNNEL_KEY_FLAGS]	= { .type = NLA_U32, },
+	[NFTA_TUNNEL_KEY_TOS]	= { .type = NLA_U8, },
+	[NFTA_TUNNEL_KEY_TTL]	= { .type = NLA_U8, },
+	[NFTA_TUNNEL_KEY_OPTS]	= { .type = NLA_NESTED, },
+};
+
+static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
+			       const struct nlattr * const tb[],
+			       struct nft_object *obj)
+{
+	struct nft_tunnel_obj *priv = nft_obj_data(obj);
+	struct ip_tunnel_info info;
+	struct metadata_dst *md;
+	int err;
+
+	if (!tb[NFTA_TUNNEL_KEY_ID])
+		return -EINVAL;
+
+	memset(&info, 0, sizeof(info));
+	info.mode		= IP_TUNNEL_INFO_TX;
+	info.key.tun_id		= key32_to_tunnel_id(nla_get_be32(tb[NFTA_TUNNEL_KEY_ID]));
+	info.key.tun_flags	= TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_NOCACHE;
+
+	if (tb[NFTA_TUNNEL_KEY_IP]) {
+		err = nft_tunnel_obj_ip_init(ctx, tb[NFTA_TUNNEL_KEY_IP], &info);
+		if (err < 0)
+			return err;
+	} else if (tb[NFTA_TUNNEL_KEY_IP6]) {
+		err = nft_tunnel_obj_ip6_init(ctx, tb[NFTA_TUNNEL_KEY_IP6], &info);
+		if (err < 0)
+			return err;
+	} else {
+		return -EINVAL;
+	}
+
+	if (tb[NFTA_TUNNEL_KEY_SPORT]) {
+		info.key.tp_src =
+			ntohs(nla_get_be16(tb[NFTA_TUNNEL_KEY_SPORT]));
+	}
+	if (tb[NFTA_TUNNEL_KEY_DPORT]) {
+		info.key.tp_dst =
+			ntohs(nla_get_be16(tb[NFTA_TUNNEL_KEY_DPORT]));
+	}
+
+	if (tb[NFTA_TUNNEL_KEY_FLAGS]) {
+		u32 tun_flags;
+
+		tun_flags = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_FLAGS]));
+		if (tun_flags & ~NFT_TUNNEL_F_MASK)
+			return -EOPNOTSUPP;
+
+		if (tun_flags & NFT_TUNNEL_F_ZERO_CSUM_TX)
+			info.key.tun_flags &= ~TUNNEL_CSUM;
+		if (tun_flags & NFT_TUNNEL_F_DONT_FRAGMENT)
+			info.key.tun_flags |= TUNNEL_DONT_FRAGMENT;
+		if (tun_flags & NFT_TUNNEL_F_SEQ_NUMBER)
+			info.key.tun_flags |= TUNNEL_SEQ;
+	}
+	if (tb[NFTA_TUNNEL_KEY_TOS])
+		info.key.tos = nla_get_u8(tb[NFTA_TUNNEL_KEY_TOS]);
+	if (tb[NFTA_TUNNEL_KEY_TTL])
+		info.key.ttl = nla_get_u8(tb[NFTA_TUNNEL_KEY_TTL]);
+	else
+		info.key.ttl = U8_MAX;
+
+	if (tb[NFTA_TUNNEL_KEY_OPTS]) {
+		err = nft_tunnel_obj_opts_init(ctx, tb[NFTA_TUNNEL_KEY_OPTS],
+					       &info, &priv->opts);
+		if (err < 0)
+			return err;
+	}
+
+	md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL);
+	if (!md)
+		return -ENOMEM;
+
+	memcpy(&md->u.tun_info, &info, sizeof(info));
+	ip_tunnel_info_opts_set(&md->u.tun_info, &priv->opts.u, priv->opts.len,
+				priv->opts.flags);
+	priv->md = md;
+
+	return 0;
+}
+
+static inline void nft_tunnel_obj_eval(struct nft_object *obj,
+				       struct nft_regs *regs,
+				       const struct nft_pktinfo *pkt)
+{
+	struct nft_tunnel_obj *priv = nft_obj_data(obj);
+	struct sk_buff *skb = pkt->skb;
+
+	skb_dst_drop(skb);
+	dst_hold((struct dst_entry *) priv->md);
+	skb_dst_set(skb, (struct dst_entry *) priv->md);
+}
+
+static int nft_tunnel_ip_dump(struct sk_buff *skb, struct ip_tunnel_info *info)
+{
+	struct nlattr *nest;
+
+	if (info->mode & IP_TUNNEL_INFO_IPV6) {
+		nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP6);
+		if (!nest)
+			return -1;
+
+		if (nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_SRC, &info->key.u.ipv6.src) < 0 ||
+		    nla_put_in6_addr(skb, NFTA_TUNNEL_KEY_IP6_DST, &info->key.u.ipv6.dst) < 0 ||
+		    nla_put_be32(skb, NFTA_TUNNEL_KEY_IP6_FLOWLABEL, info->key.label))
+			return -1;
+
+		nla_nest_end(skb, nest);
+	} else {
+		nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_IP);
+		if (!nest)
+			return -1;
+
+		if (nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_SRC, info->key.u.ipv4.src) < 0 ||
+		    nla_put_in_addr(skb, NFTA_TUNNEL_KEY_IP_DST, info->key.u.ipv4.dst) < 0)
+			return -1;
+
+		nla_nest_end(skb, nest);
+	}
+
+	return 0;
+}
+
+static int nft_tunnel_opts_dump(struct sk_buff *skb,
+				struct nft_tunnel_obj *priv)
+{
+	struct nft_tunnel_opts *opts = &priv->opts;
+	struct nlattr *nest;
+
+	nest = nla_nest_start(skb, NFTA_TUNNEL_KEY_OPTS);
+	if (!nest)
+		return -1;
+
+	if (opts->flags & TUNNEL_VXLAN_OPT) {
+		if (nla_put_be32(skb, NFTA_TUNNEL_KEY_VXLAN_GBP,
+				 htonl(opts->u.vxlan.gbp)))
+			return -1;
+	} else if (opts->flags & TUNNEL_ERSPAN_OPT) {
+		switch (opts->u.erspan.version) {
+		case ERSPAN_VERSION:
+			if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX,
+					 opts->u.erspan.u.index))
+				return -1;
+			break;
+		case ERSPAN_VERSION2:
+			if (nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_HWID,
+				       get_hwid(&opts->u.erspan.u.md2)) ||
+			    nla_put_u8(skb, NFTA_TUNNEL_KEY_ERSPAN_V2_DIR,
+				       opts->u.erspan.u.md2.dir))
+				return -1;
+			break;
+		}
+	}
+	nla_nest_end(skb, nest);
+
+	return 0;
+}
+
+static int nft_tunnel_ports_dump(struct sk_buff *skb,
+				 struct ip_tunnel_info *info)
+{
+	if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, htons(info->key.tp_src)) < 0 ||
+	    nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, htons(info->key.tp_dst)) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int nft_tunnel_flags_dump(struct sk_buff *skb,
+				 struct ip_tunnel_info *info)
+{
+	u32 flags = 0;
+
+	if (info->key.tun_flags & TUNNEL_DONT_FRAGMENT)
+		flags |= NFT_TUNNEL_F_DONT_FRAGMENT;
+	if (!(info->key.tun_flags & TUNNEL_CSUM))
+		flags |= NFT_TUNNEL_F_ZERO_CSUM_TX;
+	if (info->key.tun_flags & TUNNEL_SEQ)
+		flags |= NFT_TUNNEL_F_SEQ_NUMBER;
+
+	if (nla_put_be32(skb, NFTA_TUNNEL_KEY_FLAGS, htonl(flags)) < 0)
+		return -1;
+
+	return 0;
+}
+
+static int nft_tunnel_obj_dump(struct sk_buff *skb,
+			       struct nft_object *obj, bool reset)
+{
+	struct nft_tunnel_obj *priv = nft_obj_data(obj);
+	struct ip_tunnel_info *info = &priv->md->u.tun_info;
+
+	if (nla_put_be32(skb, NFTA_TUNNEL_KEY_ID,
+			 tunnel_id_to_key32(info->key.tun_id)) ||
+	    nft_tunnel_ip_dump(skb, info) < 0 ||
+	    nft_tunnel_ports_dump(skb, info) < 0 ||
+	    nft_tunnel_flags_dump(skb, info) < 0 ||
+	    nla_put_u8(skb, NFTA_TUNNEL_KEY_TOS, info->key.tos) ||
+	    nla_put_u8(skb, NFTA_TUNNEL_KEY_TTL, info->key.ttl) ||
+	    nft_tunnel_opts_dump(skb, priv) < 0)
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static void nft_tunnel_obj_destroy(const struct nft_ctx *ctx,
+				   struct nft_object *obj)
+{
+	struct nft_tunnel_obj *priv = nft_obj_data(obj);
+
+	metadata_dst_free(priv->md);
+}
+
+static struct nft_object_type nft_tunnel_obj_type;
+static const struct nft_object_ops nft_tunnel_obj_ops = {
+	.type		= &nft_tunnel_obj_type,
+	.size		= sizeof(struct nft_tunnel_obj),
+	.eval		= nft_tunnel_obj_eval,
+	.init		= nft_tunnel_obj_init,
+	.destroy	= nft_tunnel_obj_destroy,
+	.dump		= nft_tunnel_obj_dump,
+};
+
+static struct nft_object_type nft_tunnel_obj_type __read_mostly = {
+	.type		= NFT_OBJECT_TUNNEL,
+	.ops		= &nft_tunnel_obj_ops,
+	.maxattr	= NFTA_TUNNEL_KEY_MAX,
+	.policy		= nft_tunnel_key_policy,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_tunnel_module_init(void)
+{
+	return nft_register_obj(&nft_tunnel_obj_type);
+}
+
+static void __exit nft_tunnel_module_exit(void)
+{
+	nft_unregister_obj(&nft_tunnel_obj_type);
+}
+
+module_init(nft_tunnel_module_init);
+module_exit(nft_tunnel_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL);
-- 
cgit v1.2.3


From aaecfdb5c5dd8bac2dfd112166844a9f2d5711f0 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 2 Aug 2018 20:51:46 +0200
Subject: netfilter: nf_tables: match on tunnel metadata

This patch allows us to match on the tunnel metadata that is available
of the packet. We can use this to validate if the packet comes from/goes
to tunnel and the corresponding tunnel ID.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  15 +++++
 net/netfilter/nft_tunnel.c               | 112 ++++++++++++++++++++++++++++++-
 2 files changed, 126 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 3ee1198eeac1..357862d948de 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -1647,4 +1647,19 @@ enum nft_tunnel_key_attributes {
 };
 #define NFTA_TUNNEL_KEY_MAX	(__NFTA_TUNNEL_KEY_MAX - 1)
 
+enum nft_tunnel_keys {
+	NFT_TUNNEL_PATH,
+	NFT_TUNNEL_ID,
+	__NFT_TUNNEL_MAX
+};
+#define NFT_TUNNEL_MAX	(__NFT_TUNNEL_MAX - 1)
+
+enum nft_tunnel_attributes {
+	NFTA_TUNNEL_UNSPEC,
+	NFTA_TUNNEL_KEY,
+	NFTA_TUNNEL_DREG,
+	__NFTA_TUNNEL_MAX
+};
+#define NFTA_TUNNEL_MAX	(__NFTA_TUNNEL_MAX - 1)
+
 #endif /* _LINUX_NF_TABLES_H */
diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 715613d99c20..9332d7933dd5 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -12,6 +12,104 @@
 #include <net/vxlan.h>
 #include <net/erspan.h>
 
+struct nft_tunnel {
+	enum nft_tunnel_keys	key:8;
+	enum nft_registers	dreg:8;
+};
+
+static void nft_tunnel_get_eval(const struct nft_expr *expr,
+				struct nft_regs *regs,
+				const struct nft_pktinfo *pkt)
+{
+	const struct nft_tunnel *priv = nft_expr_priv(expr);
+	u32 *dest = &regs->data[priv->dreg];
+	struct ip_tunnel_info *tun_info;
+
+	tun_info = skb_tunnel_info(pkt->skb);
+
+	switch (priv->key) {
+	case NFT_TUNNEL_PATH:
+		nft_reg_store8(dest, !!tun_info);
+		break;
+	case NFT_TUNNEL_ID:
+		if (!tun_info) {
+			regs->verdict.code = NFT_BREAK;
+			return;
+		}
+		*dest = ntohl(tunnel_id_to_key32(tun_info->key.tun_id));
+		break;
+	default:
+		WARN_ON(1);
+		regs->verdict.code = NFT_BREAK;
+	}
+}
+
+static const struct nla_policy nft_tunnel_policy[NFTA_TUNNEL_MAX + 1] = {
+	[NFTA_TUNNEL_KEY]	= { .type = NLA_U32 },
+	[NFTA_TUNNEL_DREG]	= { .type = NLA_U32 },
+};
+
+static int nft_tunnel_get_init(const struct nft_ctx *ctx,
+			       const struct nft_expr *expr,
+			       const struct nlattr * const tb[])
+{
+	struct nft_tunnel *priv = nft_expr_priv(expr);
+	u32 len;
+
+	if (!tb[NFTA_TUNNEL_KEY] &&
+	    !tb[NFTA_TUNNEL_DREG])
+		return -EINVAL;
+
+	priv->key = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY]));
+	switch (priv->key) {
+	case NFT_TUNNEL_PATH:
+		len = sizeof(u8);
+		break;
+	case NFT_TUNNEL_ID:
+		len = sizeof(u32);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	priv->dreg = nft_parse_register(tb[NFTA_TUNNEL_DREG]);
+
+	return nft_validate_register_store(ctx, priv->dreg, NULL,
+					   NFT_DATA_VALUE, len);
+}
+
+static int nft_tunnel_get_dump(struct sk_buff *skb,
+			       const struct nft_expr *expr)
+{
+	const struct nft_tunnel *priv = nft_expr_priv(expr);
+
+	if (nla_put_be32(skb, NFTA_TUNNEL_KEY, htonl(priv->key)))
+		goto nla_put_failure;
+	if (nft_dump_register(skb, NFTA_TUNNEL_DREG, priv->dreg))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_tunnel_type;
+static const struct nft_expr_ops nft_tunnel_get_ops = {
+	.type		= &nft_tunnel_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_tunnel)),
+	.eval		= nft_tunnel_get_eval,
+	.init		= nft_tunnel_get_init,
+	.dump		= nft_tunnel_get_dump,
+};
+
+static struct nft_expr_type nft_tunnel_type __read_mostly = {
+	.name		= "tunnel",
+	.ops		= &nft_tunnel_get_ops,
+	.policy		= nft_tunnel_policy,
+	.maxattr	= NFTA_TUNNEL_MAX,
+	.owner		= THIS_MODULE,
+};
+
 struct nft_tunnel_opts {
 	union {
 		struct vxlan_metadata	vxlan;
@@ -442,12 +540,23 @@ static struct nft_object_type nft_tunnel_obj_type __read_mostly = {
 
 static int __init nft_tunnel_module_init(void)
 {
-	return nft_register_obj(&nft_tunnel_obj_type);
+	int err;
+
+	err = nft_register_expr(&nft_tunnel_type);
+	if (err < 0)
+		return err;
+
+	err = nft_register_obj(&nft_tunnel_obj_type);
+	if (err < 0)
+		nft_unregister_expr(&nft_tunnel_type);
+
+	return err;
 }
 
 static void __exit nft_tunnel_module_exit(void)
 {
 	nft_unregister_obj(&nft_tunnel_obj_type);
+	nft_unregister_expr(&nft_tunnel_type);
 }
 
 module_init(nft_tunnel_module_init);
@@ -455,4 +564,5 @@ module_exit(nft_tunnel_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NFT_EXPR("tunnel");
 MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_TUNNEL);
-- 
cgit v1.2.3


From 94276fa8a2a4c08ccb2e9d55e88b95dc972ccea3 Mon Sep 17 00:00:00 2001
From: Máté Eckl <ecklm94@gmail.com>
Date: Fri, 3 Aug 2018 13:36:13 +0200
Subject: netfilter: bridge: Expose nf_tables bridge hook priorities through
 uapi
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Netfilter exposes standard hook priorities in case of ipv4, ipv6 and
arp but not in case of bridge.

This patch exposes the hook priority values of the bridge family (which are
different from the formerly mentioned) via uapi so that they can be used by
user-space applications just like the others.

Signed-off-by: Máté Eckl <ecklm94@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter_bridge.h      | 11 -----------
 include/uapi/linux/netfilter_bridge.h | 11 +++++++++++
 net/bridge/br_netfilter_hooks.c       |  1 +
 net/bridge/netfilter/ebtable_filter.c |  1 +
 net/bridge/netfilter/ebtable_nat.c    |  1 +
 5 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index b671fdfd212b..fa0686500970 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -5,17 +5,6 @@
 #include <uapi/linux/netfilter_bridge.h>
 #include <linux/skbuff.h>
 
-enum nf_br_hook_priorities {
-	NF_BR_PRI_FIRST = INT_MIN,
-	NF_BR_PRI_NAT_DST_BRIDGED = -300,
-	NF_BR_PRI_FILTER_BRIDGED = -200,
-	NF_BR_PRI_BRNF = 0,
-	NF_BR_PRI_NAT_DST_OTHER = 100,
-	NF_BR_PRI_FILTER_OTHER = 200,
-	NF_BR_PRI_NAT_SRC = 300,
-	NF_BR_PRI_LAST = INT_MAX,
-};
-
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 
 int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb);
diff --git a/include/uapi/linux/netfilter_bridge.h b/include/uapi/linux/netfilter_bridge.h
index 12fb77633f83..156ccd089df1 100644
--- a/include/uapi/linux/netfilter_bridge.h
+++ b/include/uapi/linux/netfilter_bridge.h
@@ -26,4 +26,15 @@
 #define NF_BR_BROUTING		5
 #define NF_BR_NUMHOOKS		6
 
+enum nf_br_hook_priorities {
+	NF_BR_PRI_FIRST = INT_MIN,
+	NF_BR_PRI_NAT_DST_BRIDGED = -300,
+	NF_BR_PRI_FILTER_BRIDGED = -200,
+	NF_BR_PRI_BRNF = 0,
+	NF_BR_PRI_NAT_DST_OTHER = 100,
+	NF_BR_PRI_FILTER_OTHER = 200,
+	NF_BR_PRI_NAT_SRC = 300,
+	NF_BR_PRI_LAST = INT_MAX,
+};
+
 #endif /* _UAPI__LINUX_BRIDGE_NETFILTER_H */
diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 9b16eaf33819..6e0dc6bcd32a 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -26,6 +26,7 @@
 #include <linux/if_pppox.h>
 #include <linux/ppp_defs.h>
 #include <linux/netfilter_bridge.h>
+#include <uapi/linux/netfilter_bridge.h>
 #include <linux/netfilter_ipv4.h>
 #include <linux/netfilter_ipv6.h>
 #include <linux/netfilter_arp.h>
diff --git a/net/bridge/netfilter/ebtable_filter.c b/net/bridge/netfilter/ebtable_filter.c
index c41da5fac84f..550324c516ee 100644
--- a/net/bridge/netfilter/ebtable_filter.c
+++ b/net/bridge/netfilter/ebtable_filter.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/netfilter_bridge/ebtables.h>
+#include <uapi/linux/netfilter_bridge.h>
 #include <linux/module.h>
 
 #define FILTER_VALID_HOOKS ((1 << NF_BR_LOCAL_IN) | (1 << NF_BR_FORWARD) | \
diff --git a/net/bridge/netfilter/ebtable_nat.c b/net/bridge/netfilter/ebtable_nat.c
index 08df7406ecb3..c0fb3ca518af 100644
--- a/net/bridge/netfilter/ebtable_nat.c
+++ b/net/bridge/netfilter/ebtable_nat.c
@@ -9,6 +9,7 @@
  */
 
 #include <linux/netfilter_bridge/ebtables.h>
+#include <uapi/linux/netfilter_bridge.h>
 #include <linux/module.h>
 
 #define NAT_VALID_HOOKS ((1 << NF_BR_PRE_ROUTING) | (1 << NF_BR_LOCAL_OUT) | \
-- 
cgit v1.2.3


From 445509eb9b00278b31c92f16b05260176a41c27f Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Fri, 3 Aug 2018 13:35:36 +0200
Subject: netfilter: nf_tables: simplify NLM_F_CREATE handling

* From nf_tables_newchain(), codepath provides context that allows us to
  infer if we are updating a chain (in that case, no module autoload is
  required) or adding a new one (then, module autoload is indeed
  needed).
* We only need it in one single spot in nf_tables_newrule().
* Not needed for nf_tables_newset() at all.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_api.c | 29 ++++++++++-------------------
 1 file changed, 10 insertions(+), 19 deletions(-)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index debc1680607c..67cdd5c4f4f5 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1442,7 +1442,7 @@ struct nft_chain_hook {
 static int nft_chain_parse_hook(struct net *net,
 				const struct nlattr * const nla[],
 				struct nft_chain_hook *hook, u8 family,
-				bool create)
+				bool autoload)
 {
 	struct nlattr *ha[NFTA_HOOK_MAX + 1];
 	const struct nft_chain_type *type;
@@ -1467,7 +1467,7 @@ static int nft_chain_parse_hook(struct net *net,
 	type = chain_type[family][NFT_CHAIN_T_DEFAULT];
 	if (nla[NFTA_CHAIN_TYPE]) {
 		type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE],
-						   family, create);
+						   family, autoload);
 		if (IS_ERR(type))
 			return PTR_ERR(type);
 	}
@@ -1534,7 +1534,7 @@ static struct nft_rule **nf_tables_chain_alloc_rules(const struct nft_chain *cha
 }
 
 static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
-			      u8 policy, bool create)
+			      u8 policy)
 {
 	const struct nlattr * const *nla = ctx->nla;
 	struct nft_table *table = ctx->table;
@@ -1552,7 +1552,7 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask,
 		struct nft_chain_hook hook;
 		struct nf_hook_ops *ops;
 
-		err = nft_chain_parse_hook(net, nla, &hook, family, create);
+		err = nft_chain_parse_hook(net, nla, &hook, family, true);
 		if (err < 0)
 			return err;
 
@@ -1643,8 +1643,7 @@ err1:
 	return err;
 }
 
-static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
-			      bool create)
+static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy)
 {
 	const struct nlattr * const *nla = ctx->nla;
 	struct nft_table *table = ctx->table;
@@ -1661,7 +1660,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy,
 			return -EBUSY;
 
 		err = nft_chain_parse_hook(ctx->net, nla, &hook, ctx->family,
-					   create);
+					   false);
 		if (err < 0)
 			return err;
 
@@ -1761,9 +1760,6 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 	u8 policy = NF_ACCEPT;
 	struct nft_ctx ctx;
 	u64 handle = 0;
-	bool create;
-
-	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
 
 	lockdep_assert_held(&net->nft.commit_mutex);
 
@@ -1828,10 +1824,10 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk,
 		if (nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		return nf_tables_updchain(&ctx, genmask, policy, create);
+		return nf_tables_updchain(&ctx, genmask, policy);
 	}
 
-	return nf_tables_addchain(&ctx, family, genmask, policy, create);
+	return nf_tables_addchain(&ctx, family, genmask, policy);
 }
 
 static int nf_tables_delchain(struct net *net, struct sock *nlsk,
@@ -2529,13 +2525,10 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 	struct nlattr *tmp;
 	unsigned int size, i, n, ulen = 0, usize = 0;
 	int err, rem;
-	bool create;
 	u64 handle, pos_handle;
 
 	lockdep_assert_held(&net->nft.commit_mutex);
 
-	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
-
 	table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask);
 	if (IS_ERR(table)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]);
@@ -2565,7 +2558,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk,
 		else
 			return -EOPNOTSUPP;
 	} else {
-		if (!create || nlh->nlmsg_flags & NLM_F_REPLACE)
+		if (!(nlh->nlmsg_flags & NLM_F_CREATE) ||
+		    nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EINVAL;
 		handle = nf_tables_alloc_handle(table);
 
@@ -3361,7 +3355,6 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 	struct nft_ctx ctx;
 	char *name;
 	unsigned int size;
-	bool create;
 	u64 timeout;
 	u32 ktype, dtype, flags, policy, gc_int, objtype;
 	struct nft_set_desc desc;
@@ -3462,8 +3455,6 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk,
 			return err;
 	}
 
-	create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false;
-
 	table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask);
 	if (IS_ERR(table)) {
 		NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]);
-- 
cgit v1.2.3


From 7bdfcea875ad42b6fd00413882fbc657c751f13a Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 3 Aug 2018 17:56:12 +0200
Subject: netfilter: kconfig: remove ct zone/label dependencies

connection tracking zones currently depend on the xtables CT target.
The reasoning was that it makes no sense to support zones if they can't
be configured (which needed CT target).

Nowadays zones can also be used by OVS and configured via nftables,
so remove the dependency.

connection tracking labels are handled via hidden dependency that gets
auto-selected by the connlabel match.
Make it a visible knob, as labels can be attached via ctnetlink
or via nftables rules (nft_ct expression) too.

This allows to use conntrack labels and zones with nftables-only build.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/Kconfig | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 654588088676..71709c104081 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -106,7 +106,6 @@ config NF_CONNTRACK_SECMARK
 config NF_CONNTRACK_ZONES
 	bool  'Connection tracking zones'
 	depends on NETFILTER_ADVANCED
-	depends on NETFILTER_XT_TARGET_CT
 	help
 	  This option enables support for connection tracking zones.
 	  Normally, each connection needs to have a unique system wide
@@ -158,10 +157,11 @@ config NF_CONNTRACK_TIMESTAMP
 	  If unsure, say `N'.
 
 config NF_CONNTRACK_LABELS
-	bool
+	bool "Connection tracking labels"
 	help
 	  This option enables support for assigning user-defined flag bits
-	  to connection tracking entries.  It selected by the connlabel match.
+	  to connection tracking entries.  It can be used with xtables connlabel
+	  match and the nftables ct expression.
 
 config NF_CT_PROTO_DCCP
 	bool 'DCCP protocol connection tracking support'
-- 
cgit v1.2.3


From 020f6cc5f75511c5974cfd454f224365bc0c2df4 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 3 Aug 2018 18:40:21 +0200
Subject: netfilter: conntrack: avoid use-after free on rmmod

When the conntrack module is removed, we call nf_ct_iterate_destroy via
nf_ct_l4proto_unregister().

Problem is that nf_conntrack_proto_fini() gets called after the
conntrack hash table has already been freed.

Just remove the l4proto unregister call, its unecessary as the
nf_ct_protos[] array gets free'd right after anyway.

v2: add comment wrt. missing unreg call.

Fixes: a0ae2562c6c4b2 ("netfilter: conntrack: remove l3proto abstraction")
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_proto.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 803607a90102..30070732ee50 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -940,14 +940,13 @@ void nf_conntrack_proto_fini(void)
 {
 	unsigned int i;
 
-	nf_ct_l4proto_unregister(builtin_l4proto,
-				 ARRAY_SIZE(builtin_l4proto));
 	nf_unregister_sockopt(&so_getorigdst);
 #if IS_ENABLED(CONFIG_IPV6)
 	nf_unregister_sockopt(&so_getorigdst6);
 #endif
-
-	/* free l3proto protocol tables */
+	/* No need to call nf_ct_l4proto_unregister(), the register
+	 * tables are free'd here anyway.
+	 */
 	for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++)
 		kfree(nf_ct_protos[i]);
 }
-- 
cgit v1.2.3


From eb9950eb31f56e57582a61c92073336d04a26542 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Fri, 3 Aug 2018 17:06:56 +0100
Subject: rxrpc: Push iov_iter up from rxrpc_kernel_recv_data() to caller

Push iov_iter up from rxrpc_kernel_recv_data() to its caller to allow
non-contiguous iovs to be passed down, thereby permitting file reading to
be simplified in the AFS filesystem in a future patch.

Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 fs/afs/rxrpc.c         | 28 +++++++++++++++++-----------
 include/net/af_rxrpc.h |  2 +-
 net/rxrpc/recvmsg.c    | 33 +++++++++++----------------------
 3 files changed, 29 insertions(+), 34 deletions(-)

diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index a1b18082991b..19db5f672a9d 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -346,7 +346,6 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call,
 	struct rxrpc_call *rxcall;
 	struct msghdr msg;
 	struct kvec iov[1];
-	size_t offset;
 	s64 tx_total_len;
 	int ret;
 
@@ -433,10 +432,10 @@ error_do_abort:
 		rxrpc_kernel_abort_call(call->net->socket, rxcall,
 					RX_USER_ABORT, ret, "KSD");
 	} else {
-		offset = 0;
-		rxrpc_kernel_recv_data(call->net->socket, rxcall, NULL,
-				       0, &offset, false, &call->abort_code,
-				       &call->service_id);
+		iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, NULL, 0, 0);
+		rxrpc_kernel_recv_data(call->net->socket, rxcall,
+				       &msg.msg_iter, false,
+				       &call->abort_code, &call->service_id);
 		ac->abort_code = call->abort_code;
 		ac->responded = true;
 	}
@@ -467,13 +466,14 @@ static void afs_deliver_to_call(struct afs_call *call)
 	       state == AFS_CALL_SV_AWAIT_ACK
 	       ) {
 		if (state == AFS_CALL_SV_AWAIT_ACK) {
-			size_t offset = 0;
+			struct iov_iter iter;
+
+			iov_iter_kvec(&iter, READ | ITER_KVEC, NULL, 0, 0);
 			ret = rxrpc_kernel_recv_data(call->net->socket,
-						     call->rxcall,
-						     NULL, 0, &offset, false,
+						     call->rxcall, &iter, false,
 						     &remote_abort,
 						     &call->service_id);
-			trace_afs_recv_data(call, 0, offset, false, ret);
+			trace_afs_recv_data(call, 0, 0, false, ret);
 
 			if (ret == -EINPROGRESS || ret == -EAGAIN)
 				return;
@@ -894,6 +894,8 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count,
 		     bool want_more)
 {
 	struct afs_net *net = call->net;
+	struct iov_iter iter;
+	struct kvec iov;
 	enum afs_call_state state;
 	u32 remote_abort = 0;
 	int ret;
@@ -903,10 +905,14 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count,
 
 	ASSERTCMP(call->offset, <=, count);
 
-	ret = rxrpc_kernel_recv_data(net->socket, call->rxcall,
-				     buf, count, &call->offset,
+	iov.iov_base = buf + call->offset;
+	iov.iov_len = count - call->offset;
+	iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, count - call->offset);
+
+	ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, &iter,
 				     want_more, &remote_abort,
 				     &call->service_id);
+	call->offset += (count - call->offset) - iov_iter_count(&iter);
 	trace_afs_recv_data(call, count, call->offset, want_more, ret);
 	if (ret == 0 || ret == -EAGAIN)
 		return ret;
diff --git a/include/net/af_rxrpc.h b/include/net/af_rxrpc.h
index 8ae8ee004258..f53edb3754bc 100644
--- a/include/net/af_rxrpc.h
+++ b/include/net/af_rxrpc.h
@@ -61,7 +61,7 @@ int rxrpc_kernel_send_data(struct socket *, struct rxrpc_call *,
 			   struct msghdr *, size_t,
 			   rxrpc_notify_end_tx_t);
 int rxrpc_kernel_recv_data(struct socket *, struct rxrpc_call *,
-			   void *, size_t, size_t *, bool, u32 *, u16 *);
+			   struct iov_iter *, bool, u32 *, u16 *);
 bool rxrpc_kernel_abort_call(struct socket *, struct rxrpc_call *,
 			     u32, int, const char *);
 void rxrpc_kernel_end_call(struct socket *, struct rxrpc_call *);
diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c
index a57ea96c84ea..816b19a78809 100644
--- a/net/rxrpc/recvmsg.c
+++ b/net/rxrpc/recvmsg.c
@@ -611,9 +611,7 @@ wait_error:
  * rxrpc_kernel_recv_data - Allow a kernel service to receive data/info
  * @sock: The socket that the call exists on
  * @call: The call to send data through
- * @buf: The buffer to receive into
- * @size: The size of the buffer, including data already read
- * @_offset: The running offset into the buffer.
+ * @iter: The buffer to receive into
  * @want_more: True if more data is expected to be read
  * @_abort: Where the abort code is stored if -ECONNABORTED is returned
  * @_service: Where to store the actual service ID (may be upgraded)
@@ -626,39 +624,30 @@ wait_error:
  * Note that we may return -EAGAIN to drain empty packets at the end of the
  * data, even if we've already copied over the requested data.
  *
- * This function adds the amount it transfers to *_offset, so this should be
- * precleared as appropriate.  Note that the amount remaining in the buffer is
- * taken to be size - *_offset.
- *
  * *_abort should also be initialised to 0.
  */
 int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
-			   void *buf, size_t size, size_t *_offset,
+			   struct iov_iter *iter,
 			   bool want_more, u32 *_abort, u16 *_service)
 {
-	struct iov_iter iter;
-	struct kvec iov;
+	size_t offset = 0;
 	int ret;
 
-	_enter("{%d,%s},%zu/%zu,%d",
+	_enter("{%d,%s},%zu,%d",
 	       call->debug_id, rxrpc_call_states[call->state],
-	       *_offset, size, want_more);
+	       iov_iter_count(iter), want_more);
 
-	ASSERTCMP(*_offset, <=, size);
 	ASSERTCMP(call->state, !=, RXRPC_CALL_SERVER_ACCEPTING);
 
-	iov.iov_base = buf + *_offset;
-	iov.iov_len = size - *_offset;
-	iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, size - *_offset);
-
 	mutex_lock(&call->user_mutex);
 
 	switch (READ_ONCE(call->state)) {
 	case RXRPC_CALL_CLIENT_RECV_REPLY:
 	case RXRPC_CALL_SERVER_RECV_REQUEST:
 	case RXRPC_CALL_SERVER_ACK_REQUEST:
-		ret = rxrpc_recvmsg_data(sock, call, NULL, &iter, size, 0,
-					 _offset);
+		ret = rxrpc_recvmsg_data(sock, call, NULL, iter,
+					 iov_iter_count(iter), 0,
+					 &offset);
 		if (ret < 0)
 			goto out;
 
@@ -667,7 +656,7 @@ int rxrpc_kernel_recv_data(struct socket *sock, struct rxrpc_call *call,
 		 * full buffer or have been given -EAGAIN.
 		 */
 		if (ret == 1) {
-			if (*_offset < size)
+			if (iov_iter_count(iter) > 0)
 				goto short_data;
 			if (!want_more)
 				goto read_phase_complete;
@@ -704,7 +693,7 @@ out:
 	if (_service)
 		*_service = call->service_id;
 	mutex_unlock(&call->user_mutex);
-	_leave(" = %d [%zu,%d]", ret, *_offset, *_abort);
+	_leave(" = %d [%zu,%d]", ret, iov_iter_count(iter), *_abort);
 	return ret;
 
 short_data:
@@ -720,7 +709,7 @@ call_complete:
 	ret = call->error;
 	if (call->completion == RXRPC_CALL_SUCCEEDED) {
 		ret = 1;
-		if (size > 0)
+		if (iov_iter_count(iter) > 0)
 			ret = -ECONNRESET;
 	}
 	goto out;
-- 
cgit v1.2.3


From 3c56b2cccbd1d66ab394ca73f4de48d8c98d923d Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:20 -0400
Subject: media: vsp1: drm: Fix minor grammar error

The pixel format is 'unsupported'. Fix the small debug message which
incorrectly declares this.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_drm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index edb35a5c57ea..a16856856789 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -806,7 +806,7 @@ int vsp1_du_atomic_update(struct device *dev, unsigned int pipe_index,
 	 */
 	fmtinfo = vsp1_get_format_info(vsp1, cfg->pixelformat);
 	if (!fmtinfo) {
-		dev_dbg(vsp1->dev, "Unsupport pixel format %08x for RPF\n",
+		dev_dbg(vsp1->dev, "Unsupported pixel format %08x for RPF\n",
 			cfg->pixelformat);
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From a394b3af206c211b80b02e47c19aab763fd33b3d Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Fri, 3 Aug 2018 09:37:45 -0700
Subject: ppp: mppe: Remove VLA usage

In the quest to remove all stack VLA usage from the kernel[1], this
removes the discouraged use of AHASH_REQUEST_ON_STACK (and associated
VLA) by switching to shash directly and keeping the associated descriptor
allocated with the regular state on the heap.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ppp/ppp_mppe.c | 56 +++++++++++++++++++++++++---------------------
 1 file changed, 30 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ppp/ppp_mppe.c b/drivers/net/ppp/ppp_mppe.c
index 6c7fd98cb00a..a205750b431b 100644
--- a/drivers/net/ppp/ppp_mppe.c
+++ b/drivers/net/ppp/ppp_mppe.c
@@ -96,7 +96,7 @@ static inline void sha_pad_init(struct sha_pad *shapad)
  */
 struct ppp_mppe_state {
 	struct crypto_skcipher *arc4;
-	struct crypto_ahash *sha1;
+	struct shash_desc *sha1;
 	unsigned char *sha1_digest;
 	unsigned char master_key[MPPE_MAX_KEY_LEN];
 	unsigned char session_key[MPPE_MAX_KEY_LEN];
@@ -136,25 +136,16 @@ struct ppp_mppe_state {
  */
 static void get_new_key_from_sha(struct ppp_mppe_state * state)
 {
-	AHASH_REQUEST_ON_STACK(req, state->sha1);
-	struct scatterlist sg[4];
-	unsigned int nbytes;
-
-	sg_init_table(sg, 4);
-
-	nbytes = setup_sg(&sg[0], state->master_key, state->keylen);
-	nbytes += setup_sg(&sg[1], sha_pad->sha_pad1,
-			   sizeof(sha_pad->sha_pad1));
-	nbytes += setup_sg(&sg[2], state->session_key, state->keylen);
-	nbytes += setup_sg(&sg[3], sha_pad->sha_pad2,
-			   sizeof(sha_pad->sha_pad2));
-
-	ahash_request_set_tfm(req, state->sha1);
-	ahash_request_set_callback(req, 0, NULL, NULL);
-	ahash_request_set_crypt(req, sg, state->sha1_digest, nbytes);
-
-	crypto_ahash_digest(req);
-	ahash_request_zero(req);
+	crypto_shash_init(state->sha1);
+	crypto_shash_update(state->sha1, state->master_key,
+			    state->keylen);
+	crypto_shash_update(state->sha1, sha_pad->sha_pad1,
+			    sizeof(sha_pad->sha_pad1));
+	crypto_shash_update(state->sha1, state->session_key,
+			    state->keylen);
+	crypto_shash_update(state->sha1, sha_pad->sha_pad2,
+			    sizeof(sha_pad->sha_pad2));
+	crypto_shash_final(state->sha1, state->sha1_digest);
 }
 
 /*
@@ -200,6 +191,7 @@ static void mppe_rekey(struct ppp_mppe_state * state, int initial_key)
 static void *mppe_alloc(unsigned char *options, int optlen)
 {
 	struct ppp_mppe_state *state;
+	struct crypto_shash *shash;
 	unsigned int digestsize;
 
 	if (optlen != CILEN_MPPE + sizeof(state->master_key) ||
@@ -217,13 +209,21 @@ static void *mppe_alloc(unsigned char *options, int optlen)
 		goto out_free;
 	}
 
-	state->sha1 = crypto_alloc_ahash("sha1", 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(state->sha1)) {
-		state->sha1 = NULL;
+	shash = crypto_alloc_shash("sha1", 0, 0);
+	if (IS_ERR(shash))
+		goto out_free;
+
+	state->sha1 = kmalloc(sizeof(*state->sha1) +
+				     crypto_shash_descsize(shash),
+			      GFP_KERNEL);
+	if (!state->sha1) {
+		crypto_free_shash(shash);
 		goto out_free;
 	}
+	state->sha1->tfm = shash;
+	state->sha1->flags = 0;
 
-	digestsize = crypto_ahash_digestsize(state->sha1);
+	digestsize = crypto_shash_digestsize(shash);
 	if (digestsize < MPPE_MAX_KEY_LEN)
 		goto out_free;
 
@@ -246,7 +246,10 @@ static void *mppe_alloc(unsigned char *options, int optlen)
 
 out_free:
 	kfree(state->sha1_digest);
-	crypto_free_ahash(state->sha1);
+	if (state->sha1) {
+		crypto_free_shash(state->sha1->tfm);
+		kzfree(state->sha1);
+	}
 	crypto_free_skcipher(state->arc4);
 	kfree(state);
 out:
@@ -261,7 +264,8 @@ static void mppe_free(void *arg)
 	struct ppp_mppe_state *state = (struct ppp_mppe_state *) arg;
 	if (state) {
 		kfree(state->sha1_digest);
-		crypto_free_ahash(state->sha1);
+		crypto_free_shash(state->sha1->tfm);
+		kzfree(state->sha1);
 		crypto_free_skcipher(state->arc4);
 		kfree(state);
 	}
-- 
cgit v1.2.3


From c2b6d621c4ffe9936adf7a55c8b1c769672c306f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 28 Jun 2018 15:53:17 -0400
Subject: new primitive: discard_new_inode()

	We don't want open-by-handle picking half-set-up in-core
struct inode from e.g. mkdir() having failed halfway through.
In other words, we don't want such inodes returned by iget_locked()
on their way to extinction.  However, we can't just have them
unhashed - otherwise open-by-handle immediately *after* that would've
ended up creating a new in-core inode over the on-disk one that
is in process of being freed right under us.

	Solution: new flag (I_CREATING) set by insert_inode_locked() and
removed by unlock_new_inode() and a new primitive (discard_new_inode())
to be used by such halfway-through-setup failure exits instead of
unlock_new_inode() / iput() combinations.  That primitive unlocks new
inode, but leaves I_CREATING in place.

	iget_locked() treats finding an I_CREATING inode as failure
(-ESTALE, once we sort out the error propagation).
	insert_inode_locked() treats the same as instant -EBUSY.
	ilookup() treats those as icache miss.

[Fix by Dan Carpenter <dan.carpenter@oracle.com> folded in]

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c        |  2 +-
 fs/inode.c         | 45 +++++++++++++++++++++++++++++++++++++++++----
 include/linux/fs.h |  6 +++++-
 3 files changed, 47 insertions(+), 6 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index a7d9e7a4c283..11b753d29409 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1892,7 +1892,7 @@ void d_instantiate_new(struct dentry *entry, struct inode *inode)
 	spin_lock(&inode->i_lock);
 	__d_instantiate(entry, inode);
 	WARN_ON(!(inode->i_state & I_NEW));
-	inode->i_state &= ~I_NEW;
+	inode->i_state &= ~I_NEW & ~I_CREATING;
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_NEW);
 	spin_unlock(&inode->i_lock);
diff --git a/fs/inode.c b/fs/inode.c
index 2c300e981796..6cd2e7ba9f4d 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -804,6 +804,10 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
+		if (unlikely(inode->i_state & I_CREATING)) {
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-ESTALE);
+		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
 		return inode;
@@ -831,6 +835,10 @@ repeat:
 			__wait_on_freeing_inode(inode);
 			goto repeat;
 		}
+		if (unlikely(inode->i_state & I_CREATING)) {
+			spin_unlock(&inode->i_lock);
+			return ERR_PTR(-ESTALE);
+		}
 		__iget(inode);
 		spin_unlock(&inode->i_lock);
 		return inode;
@@ -961,13 +969,26 @@ void unlock_new_inode(struct inode *inode)
 	lockdep_annotate_inode_mutex_key(inode);
 	spin_lock(&inode->i_lock);
 	WARN_ON(!(inode->i_state & I_NEW));
-	inode->i_state &= ~I_NEW;
+	inode->i_state &= ~I_NEW & ~I_CREATING;
 	smp_mb();
 	wake_up_bit(&inode->i_state, __I_NEW);
 	spin_unlock(&inode->i_lock);
 }
 EXPORT_SYMBOL(unlock_new_inode);
 
+void discard_new_inode(struct inode *inode)
+{
+	lockdep_annotate_inode_mutex_key(inode);
+	spin_lock(&inode->i_lock);
+	WARN_ON(!(inode->i_state & I_NEW));
+	inode->i_state &= ~I_NEW;
+	smp_mb();
+	wake_up_bit(&inode->i_state, __I_NEW);
+	spin_unlock(&inode->i_lock);
+	iput(inode);
+}
+EXPORT_SYMBOL(discard_new_inode);
+
 /**
  * lock_two_nondirectories - take two i_mutexes on non-directory objects
  *
@@ -1039,6 +1060,8 @@ again:
 		 * Use the old inode instead of the preallocated one.
 		 */
 		spin_unlock(&inode_hash_lock);
+		if (IS_ERR(old))
+			return NULL;
 		wait_on_inode(old);
 		if (unlikely(inode_unhashed(old))) {
 			iput(old);
@@ -1128,6 +1151,8 @@ again:
 	inode = find_inode_fast(sb, head, ino);
 	spin_unlock(&inode_hash_lock);
 	if (inode) {
+		if (IS_ERR(inode))
+			return NULL;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
 			iput(inode);
@@ -1165,6 +1190,8 @@ again:
 		 */
 		spin_unlock(&inode_hash_lock);
 		destroy_inode(inode);
+		if (IS_ERR(old))
+			return NULL;
 		inode = old;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
@@ -1282,7 +1309,7 @@ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval,
 	inode = find_inode(sb, head, test, data);
 	spin_unlock(&inode_hash_lock);
 
-	return inode;
+	return IS_ERR(inode) ? NULL : inode;
 }
 EXPORT_SYMBOL(ilookup5_nowait);
 
@@ -1338,6 +1365,8 @@ again:
 	spin_unlock(&inode_hash_lock);
 
 	if (inode) {
+		if (IS_ERR(inode))
+			return NULL;
 		wait_on_inode(inode);
 		if (unlikely(inode_unhashed(inode))) {
 			iput(inode);
@@ -1421,12 +1450,17 @@ int insert_inode_locked(struct inode *inode)
 		}
 		if (likely(!old)) {
 			spin_lock(&inode->i_lock);
-			inode->i_state |= I_NEW;
+			inode->i_state |= I_NEW | I_CREATING;
 			hlist_add_head(&inode->i_hash, head);
 			spin_unlock(&inode->i_lock);
 			spin_unlock(&inode_hash_lock);
 			return 0;
 		}
+		if (unlikely(old->i_state & I_CREATING)) {
+			spin_unlock(&old->i_lock);
+			spin_unlock(&inode_hash_lock);
+			return -EBUSY;
+		}
 		__iget(old);
 		spin_unlock(&old->i_lock);
 		spin_unlock(&inode_hash_lock);
@@ -1443,7 +1477,10 @@ EXPORT_SYMBOL(insert_inode_locked);
 int insert_inode_locked4(struct inode *inode, unsigned long hashval,
 		int (*test)(struct inode *, void *), void *data)
 {
-	struct inode *old = inode_insert5(inode, hashval, test, NULL, data);
+	struct inode *old;
+
+	inode->i_state |= I_CREATING;
+	old = inode_insert5(inode, hashval, test, NULL, data);
 
 	if (old != inode) {
 		iput(old);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 5c91108846db..a42600565925 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2016,6 +2016,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
  * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
  *			and work dirs among overlayfs mounts.
  *
+ * I_CREATING		New object's inode in the middle of setting up.
+ *
  * Q: What is the difference between I_WILL_FREE and I_FREEING?
  */
 #define I_DIRTY_SYNC		(1 << 0)
@@ -2036,7 +2038,8 @@ static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
 #define __I_DIRTY_TIME_EXPIRED	12
 #define I_DIRTY_TIME_EXPIRED	(1 << __I_DIRTY_TIME_EXPIRED)
 #define I_WB_SWITCH		(1 << 13)
-#define I_OVL_INUSE			(1 << 14)
+#define I_OVL_INUSE		(1 << 14)
+#define I_CREATING		(1 << 15)
 
 #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
 #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
@@ -2919,6 +2922,7 @@ extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
 static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
 #endif
 extern void unlock_new_inode(struct inode *);
+extern void discard_new_inode(struct inode *);
 extern unsigned int get_next_ino(void);
 extern void evict_inodes(struct super_block *sb);
 
-- 
cgit v1.2.3


From 3e737e394329564b70ceff8eb0c5f587904aa396 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:21 -0400
Subject: media: vsp1: use kernel __packed for structures

The kernel provides a __packed definition to abstract away from the
compiler specific attributes tag.

Convert all packed structures in VSP1 to use it.

The GCC documentation [0] describes this attribute as "the structure or
union is placed to minimize the memory required".

The Keil compiler documentation at [1] warns that the use of this
attribute can cause a performance penalty in the event that the compiler
can not deduce the allignment of each field.

Careful examination of the object code generated both with and without
this attribute shows that these structures are accessed identically and
are not affected by any performance penalty. The structures are
correctly aligned and padded to match the needs of the hardware already.

This patch does not serve to make a decision as to the use of the
attribute, but purely to clean up the code to use the kernel defined
abstraction as per [2].

[0] https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-packed-type-attribute
[1] http://www.keil.com/support/man/docs/armcc/armcc_chr1359124230195.htm
[2] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/linux/compiler-gcc.h?h=v4.16-rc5#n92

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 10a24bde2299..e4aae334f047 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -25,19 +25,19 @@
 struct vsp1_dl_header_list {
 	u32 num_bytes;
 	u32 addr;
-} __attribute__((__packed__));
+} __packed;
 
 struct vsp1_dl_header {
 	u32 num_lists;
 	struct vsp1_dl_header_list lists[8];
 	u32 next_header;
 	u32 flags;
-} __attribute__((__packed__));
+} __packed;
 
 struct vsp1_dl_entry {
 	u32 addr;
 	u32 data;
-} __attribute__((__packed__));
+} __packed;
 
 /**
  * struct vsp1_dl_body - Display list body
-- 
cgit v1.2.3


From 2ca72570b934e820f9a5b645cfb9b5df93e3c139 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:22 -0400
Subject: media: vsp1: Rename dl_child to dl_next

Both vsp1_dl_list_commit() and __vsp1_dl_list_put() walk the display
list chain referencing the nodes as children, when in reality they are
siblings.

Update the terminology to 'dl_next' to be consistent with the
vsp1_video_pipeline_run() usage.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index e4aae334f047..202bc0c6e484 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -399,7 +399,7 @@ struct vsp1_dl_list *vsp1_dl_list_get(struct vsp1_dl_manager *dlm)
 /* This function must be called with the display list manager lock held.*/
 static void __vsp1_dl_list_put(struct vsp1_dl_list *dl)
 {
-	struct vsp1_dl_list *dl_child;
+	struct vsp1_dl_list *dl_next;
 
 	if (!dl)
 		return;
@@ -409,8 +409,8 @@ static void __vsp1_dl_list_put(struct vsp1_dl_list *dl)
 	 * hardware operation.
 	 */
 	if (dl->has_chain) {
-		list_for_each_entry(dl_child, &dl->chain, chain)
-			__vsp1_dl_list_put(dl_child);
+		list_for_each_entry(dl_next, &dl->chain, chain)
+			__vsp1_dl_list_put(dl_next);
 	}
 
 	dl->has_chain = false;
@@ -674,17 +674,17 @@ static void vsp1_dl_list_commit_singleshot(struct vsp1_dl_list *dl)
 void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
 {
 	struct vsp1_dl_manager *dlm = dl->dlm;
-	struct vsp1_dl_list *dl_child;
+	struct vsp1_dl_list *dl_next;
 	unsigned long flags;
 
 	if (dlm->mode == VSP1_DL_MODE_HEADER) {
 		/* Fill the header for the head and chained display lists. */
 		vsp1_dl_list_fill_header(dl, list_empty(&dl->chain));
 
-		list_for_each_entry(dl_child, &dl->chain, chain) {
-			bool last = list_is_last(&dl_child->chain, &dl->chain);
+		list_for_each_entry(dl_next, &dl->chain, chain) {
+			bool last = list_is_last(&dl_next->chain, &dl->chain);
 
-			vsp1_dl_list_fill_header(dl_child, last);
+			vsp1_dl_list_fill_header(dl_next, last);
 		}
 	}
 
-- 
cgit v1.2.3


From b6ee44d1ea189cf0872b48e4fa56d648dec10fa2 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:23 -0400
Subject: media: vsp1: Remove unused display list structure field

The vsp1 reference in the vsp1_dl_body structure is not used.
Remove it.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 202bc0c6e484..199843a73df1 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -45,7 +45,6 @@ struct vsp1_dl_entry {
  * @free: entry in the pool free body list
  * @refcnt: reference tracking for the body
  * @pool: pool to which this body belongs
- * @vsp1: the VSP1 device
  * @entries: array of entries
  * @dma: DMA address of the entries
  * @size: size of the DMA memory in bytes
@@ -59,7 +58,6 @@ struct vsp1_dl_body {
 	refcount_t refcnt;
 
 	struct vsp1_dl_body_pool *pool;
-	struct vsp1_device *vsp1;
 
 	struct vsp1_dl_entry *entries;
 	dma_addr_t dma;
-- 
cgit v1.2.3


From 8a3a0797dedd39a6ee7a52c3749d31f8104aafa7 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:24 -0400
Subject: media: vsp1: Clean up DLM objects on error

If there is an error allocating a display list within a DLM object
the existing display lists are not free'd, and neither is the DL body
pool.

Use the existing vsp1_dlm_destroy() function to clean up on error.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 199843a73df1..64e5b25d1123 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -858,8 +858,10 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 		struct vsp1_dl_list *dl;
 
 		dl = vsp1_dl_list_alloc(dlm);
-		if (!dl)
+		if (!dl) {
+			vsp1_dlm_destroy(dlm);
 			return NULL;
+		}
 
 		list_add_tail(&dl->list, &dlm->free);
 	}
-- 
cgit v1.2.3


From 177fb098b89644b1f1143482a87587a6ed7de578 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:25 -0400
Subject: media: vsp1: Provide VSP1 feature helper macro

The VSP1 devices define their specific capabilities through features
marked in their device info structure. Various parts of the code read
this info structure to infer if the features are available.

Wrap this into a more readable vsp1_feature(vsp1, f) macro to ensure
that usage is consistent throughout the driver.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1.h     |  2 ++
 drivers/media/platform/vsp1/vsp1_drv.c | 16 ++++++++--------
 drivers/media/platform/vsp1/vsp1_wpf.c |  6 +++---
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1.h b/drivers/media/platform/vsp1/vsp1.h
index 33f632331474..f0d21cc8e9ab 100644
--- a/drivers/media/platform/vsp1/vsp1.h
+++ b/drivers/media/platform/vsp1/vsp1.h
@@ -68,6 +68,8 @@ struct vsp1_device_info {
 	bool uapi;
 };
 
+#define vsp1_feature(vsp1, f) ((vsp1)->info->features & (f))
+
 struct vsp1_device {
 	struct device *dev;
 	const struct vsp1_device_info *info;
diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c
index 5d82f6ee56ea..3367c2ba990d 100644
--- a/drivers/media/platform/vsp1/vsp1_drv.c
+++ b/drivers/media/platform/vsp1/vsp1_drv.c
@@ -265,7 +265,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 	}
 
 	/* Instantiate all the entities. */
-	if (vsp1->info->features & VSP1_HAS_BRS) {
+	if (vsp1_feature(vsp1, VSP1_HAS_BRS)) {
 		vsp1->brs = vsp1_brx_create(vsp1, VSP1_ENTITY_BRS);
 		if (IS_ERR(vsp1->brs)) {
 			ret = PTR_ERR(vsp1->brs);
@@ -275,7 +275,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->brs->entity.list_dev, &vsp1->entities);
 	}
 
-	if (vsp1->info->features & VSP1_HAS_BRU) {
+	if (vsp1_feature(vsp1, VSP1_HAS_BRU)) {
 		vsp1->bru = vsp1_brx_create(vsp1, VSP1_ENTITY_BRU);
 		if (IS_ERR(vsp1->bru)) {
 			ret = PTR_ERR(vsp1->bru);
@@ -285,7 +285,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		list_add_tail(&vsp1->bru->entity.list_dev, &vsp1->entities);
 	}
 
-	if (vsp1->info->features & VSP1_HAS_CLU) {
+	if (vsp1_feature(vsp1, VSP1_HAS_CLU)) {
 		vsp1->clu = vsp1_clu_create(vsp1);
 		if (IS_ERR(vsp1->clu)) {
 			ret = PTR_ERR(vsp1->clu);
@@ -311,7 +311,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 
 	list_add_tail(&vsp1->hst->entity.list_dev, &vsp1->entities);
 
-	if (vsp1->info->features & VSP1_HAS_HGO && vsp1->info->uapi) {
+	if (vsp1_feature(vsp1, VSP1_HAS_HGO) && vsp1->info->uapi) {
 		vsp1->hgo = vsp1_hgo_create(vsp1);
 		if (IS_ERR(vsp1->hgo)) {
 			ret = PTR_ERR(vsp1->hgo);
@@ -322,7 +322,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 			      &vsp1->entities);
 	}
 
-	if (vsp1->info->features & VSP1_HAS_HGT && vsp1->info->uapi) {
+	if (vsp1_feature(vsp1, VSP1_HAS_HGT) && vsp1->info->uapi) {
 		vsp1->hgt = vsp1_hgt_create(vsp1);
 		if (IS_ERR(vsp1->hgt)) {
 			ret = PTR_ERR(vsp1->hgt);
@@ -353,7 +353,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		}
 	}
 
-	if (vsp1->info->features & VSP1_HAS_LUT) {
+	if (vsp1_feature(vsp1, VSP1_HAS_LUT)) {
 		vsp1->lut = vsp1_lut_create(vsp1);
 		if (IS_ERR(vsp1->lut)) {
 			ret = PTR_ERR(vsp1->lut);
@@ -387,7 +387,7 @@ static int vsp1_create_entities(struct vsp1_device *vsp1)
 		}
 	}
 
-	if (vsp1->info->features & VSP1_HAS_SRU) {
+	if (vsp1_feature(vsp1, VSP1_HAS_SRU)) {
 		vsp1->sru = vsp1_sru_create(vsp1);
 		if (IS_ERR(vsp1->sru)) {
 			ret = PTR_ERR(vsp1->sru);
@@ -537,7 +537,7 @@ static int vsp1_device_init(struct vsp1_device *vsp1)
 	vsp1_write(vsp1, VI6_DPR_HSI_ROUTE, VI6_DPR_NODE_UNUSED);
 	vsp1_write(vsp1, VI6_DPR_BRU_ROUTE, VI6_DPR_NODE_UNUSED);
 
-	if (vsp1->info->features & VSP1_HAS_BRS)
+	if (vsp1_feature(vsp1, VSP1_HAS_BRS))
 		vsp1_write(vsp1, VI6_DPR_ILV_BRS_ROUTE, VI6_DPR_NODE_UNUSED);
 
 	vsp1_write(vsp1, VI6_DPR_HGO_SMPPT, (7 << VI6_DPR_SMPPT_TGW_SHIFT) |
diff --git a/drivers/media/platform/vsp1/vsp1_wpf.c b/drivers/media/platform/vsp1/vsp1_wpf.c
index 23c8f706b3f2..c2a1a7f97e26 100644
--- a/drivers/media/platform/vsp1/vsp1_wpf.c
+++ b/drivers/media/platform/vsp1/vsp1_wpf.c
@@ -141,13 +141,13 @@ static int wpf_init_controls(struct vsp1_rwpf *wpf)
 	if (wpf->entity.index != 0) {
 		/* Only WPF0 supports flipping. */
 		num_flip_ctrls = 0;
-	} else if (vsp1->info->features & VSP1_HAS_WPF_HFLIP) {
+	} else if (vsp1_feature(vsp1, VSP1_HAS_WPF_HFLIP)) {
 		/*
 		 * When horizontal flip is supported the WPF implements three
 		 * controls (horizontal flip, vertical flip and rotation).
 		 */
 		num_flip_ctrls = 3;
-	} else if (vsp1->info->features & VSP1_HAS_WPF_VFLIP) {
+	} else if (vsp1_feature(vsp1, VSP1_HAS_WPF_VFLIP)) {
 		/*
 		 * When only vertical flip is supported the WPF implements a
 		 * single control (vertical flip).
@@ -276,7 +276,7 @@ static void wpf_configure_stream(struct vsp1_entity *entity,
 
 		vsp1_wpf_write(wpf, dlb, VI6_WPF_DSWAP, fmtinfo->swap);
 
-		if (vsp1->info->features & VSP1_HAS_WPF_HFLIP &&
+		if (vsp1_feature(vsp1, VSP1_HAS_WPF_HFLIP) &&
 		    wpf->entity.index == 0)
 			vsp1_wpf_write(wpf, dlb, VI6_WPF_ROT_CTRL,
 				       VI6_WPF_ROT_CTRL_LN16 |
-- 
cgit v1.2.3


From 08e41f6219c717d16bb22b53010ee7401c27fb11 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:26 -0400
Subject: media: vsp1: Use header display lists for all WPF outputs linked to
 the DU

Header mode display lists are now supported on all WPF outputs. To
support extended headers and auto-fld capabilities for interlaced mode
handling only header mode display lists can be used.

Disable the headerless display list configuration, and remove the dead
code.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 108 +++++++++-------------------------
 1 file changed, 27 insertions(+), 81 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 64e5b25d1123..e535fee13d54 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -95,7 +95,7 @@ struct vsp1_dl_body_pool {
  * struct vsp1_dl_list - Display list
  * @list: entry in the display list manager lists
  * @dlm: the display list manager
- * @header: display list header, NULL for headerless lists
+ * @header: display list header
  * @dma: DMA address for the header
  * @body0: first display list body
  * @bodies: list of extra display list bodies
@@ -119,15 +119,9 @@ struct vsp1_dl_list {
 	bool internal;
 };
 
-enum vsp1_dl_mode {
-	VSP1_DL_MODE_HEADER,
-	VSP1_DL_MODE_HEADERLESS,
-};
-
 /**
  * struct vsp1_dl_manager - Display List manager
  * @index: index of the related WPF
- * @mode: display list operation mode (header or headerless)
  * @singleshot: execute the display list in single-shot mode
  * @vsp1: the VSP1 device
  * @lock: protects the free, active, queued, and pending lists
@@ -139,7 +133,6 @@ enum vsp1_dl_mode {
  */
 struct vsp1_dl_manager {
 	unsigned int index;
-	enum vsp1_dl_mode mode;
 	bool singleshot;
 	struct vsp1_device *vsp1;
 
@@ -319,6 +312,7 @@ void vsp1_dl_body_write(struct vsp1_dl_body *dlb, u32 reg, u32 data)
 static struct vsp1_dl_list *vsp1_dl_list_alloc(struct vsp1_dl_manager *dlm)
 {
 	struct vsp1_dl_list *dl;
+	size_t header_offset;
 
 	dl = kzalloc(sizeof(*dl), GFP_KERNEL);
 	if (!dl)
@@ -331,16 +325,14 @@ static struct vsp1_dl_list *vsp1_dl_list_alloc(struct vsp1_dl_manager *dlm)
 	dl->body0 = vsp1_dl_body_get(dlm->pool);
 	if (!dl->body0)
 		return NULL;
-	if (dlm->mode == VSP1_DL_MODE_HEADER) {
-		size_t header_offset = dl->body0->max_entries
-				     * sizeof(*dl->body0->entries);
 
-		dl->header = ((void *)dl->body0->entries) + header_offset;
-		dl->dma = dl->body0->dma + header_offset;
+	header_offset = dl->body0->max_entries * sizeof(*dl->body0->entries);
 
-		memset(dl->header, 0, sizeof(*dl->header));
-		dl->header->lists[0].addr = dl->body0->dma;
-	}
+	dl->header = ((void *)dl->body0->entries) + header_offset;
+	dl->dma = dl->body0->dma + header_offset;
+
+	memset(dl->header, 0, sizeof(*dl->header));
+	dl->header->lists[0].addr = dl->body0->dma;
 
 	return dl;
 }
@@ -472,16 +464,9 @@ struct vsp1_dl_body *vsp1_dl_list_get_body0(struct vsp1_dl_list *dl)
  *
  * The reference must be explicitly released by a call to vsp1_dl_body_put()
  * when the body isn't needed anymore.
- *
- * Additional bodies are only usable for display lists in header mode.
- * Attempting to add a body to a header-less display list will return an error.
  */
 int vsp1_dl_list_add_body(struct vsp1_dl_list *dl, struct vsp1_dl_body *dlb)
 {
-	/* Multi-body lists are only available in header mode. */
-	if (dl->dlm->mode != VSP1_DL_MODE_HEADER)
-		return -EINVAL;
-
 	refcount_inc(&dlb->refcnt);
 
 	list_add_tail(&dlb->list, &dl->bodies);
@@ -502,17 +487,10 @@ int vsp1_dl_list_add_body(struct vsp1_dl_list *dl, struct vsp1_dl_body *dlb)
  * Adding a display list to a chain passes ownership of the display list to
  * the head display list item. The chain is released when the head dl item is
  * put back with __vsp1_dl_list_put().
- *
- * Chained display lists are only usable in header mode. Attempts to add a
- * display list to a chain in header-less mode will return an error.
  */
 int vsp1_dl_list_add_chain(struct vsp1_dl_list *head,
 			   struct vsp1_dl_list *dl)
 {
-	/* Chained lists are only available in header mode. */
-	if (head->dlm->mode != VSP1_DL_MODE_HEADER)
-		return -EINVAL;
-
 	head->has_chain = true;
 	list_add_tail(&dl->chain, &head->chain);
 	return 0;
@@ -580,17 +558,10 @@ static bool vsp1_dl_list_hw_update_pending(struct vsp1_dl_manager *dlm)
 		return false;
 
 	/*
-	 * Check whether the VSP1 has taken the update. In headerless mode the
-	 * hardware indicates this by clearing the UPD bit in the DL_BODY_SIZE
-	 * register, and in header mode by clearing the UPDHDR bit in the CMD
-	 * register.
+	 * Check whether the VSP1 has taken the update. The hardware indicates
+	 * this by clearing the UPDHDR bit in the CMD register.
 	 */
-	if (dlm->mode == VSP1_DL_MODE_HEADERLESS)
-		return !!(vsp1_read(vsp1, VI6_DL_BODY_SIZE)
-			  & VI6_DL_BODY_SIZE_UPD);
-	else
-		return !!(vsp1_read(vsp1, VI6_CMD(dlm->index))
-			  & VI6_CMD_UPDHDR);
+	return !!(vsp1_read(vsp1, VI6_CMD(dlm->index)) & VI6_CMD_UPDHDR);
 }
 
 static void vsp1_dl_list_hw_enqueue(struct vsp1_dl_list *dl)
@@ -598,26 +569,14 @@ static void vsp1_dl_list_hw_enqueue(struct vsp1_dl_list *dl)
 	struct vsp1_dl_manager *dlm = dl->dlm;
 	struct vsp1_device *vsp1 = dlm->vsp1;
 
-	if (dlm->mode == VSP1_DL_MODE_HEADERLESS) {
-		/*
-		 * In headerless mode, program the hardware directly with the
-		 * display list body address and size and set the UPD bit. The
-		 * bit will be cleared by the hardware when the display list
-		 * processing starts.
-		 */
-		vsp1_write(vsp1, VI6_DL_HDR_ADDR(0), dl->body0->dma);
-		vsp1_write(vsp1, VI6_DL_BODY_SIZE, VI6_DL_BODY_SIZE_UPD |
-			(dl->body0->num_entries * sizeof(*dl->header->lists)));
-	} else {
-		/*
-		 * In header mode, program the display list header address. If
-		 * the hardware is idle (single-shot mode or first frame in
-		 * continuous mode) it will then be started independently. If
-		 * the hardware is operating, the VI6_DL_HDR_REF_ADDR register
-		 * will be updated with the display list address.
-		 */
-		vsp1_write(vsp1, VI6_DL_HDR_ADDR(dlm->index), dl->dma);
-	}
+	/*
+	 * Program the display list header address. If the hardware is idle
+	 * (single-shot mode or first frame in continuous mode) it will then be
+	 * started independently. If the hardware is operating, the
+	 * VI6_DL_HDR_REF_ADDR register will be updated with the display list
+	 * address.
+	 */
+	vsp1_write(vsp1, VI6_DL_HDR_ADDR(dlm->index), dl->dma);
 }
 
 static void vsp1_dl_list_commit_continuous(struct vsp1_dl_list *dl)
@@ -675,15 +634,13 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
 	struct vsp1_dl_list *dl_next;
 	unsigned long flags;
 
-	if (dlm->mode == VSP1_DL_MODE_HEADER) {
-		/* Fill the header for the head and chained display lists. */
-		vsp1_dl_list_fill_header(dl, list_empty(&dl->chain));
+	/* Fill the header for the head and chained display lists. */
+	vsp1_dl_list_fill_header(dl, list_empty(&dl->chain));
 
-		list_for_each_entry(dl_next, &dl->chain, chain) {
-			bool last = list_is_last(&dl_next->chain, &dl->chain);
+	list_for_each_entry(dl_next, &dl->chain, chain) {
+		bool last = list_is_last(&dl_next->chain, &dl->chain);
 
-			vsp1_dl_list_fill_header(dl_next, last);
-		}
+		vsp1_dl_list_fill_header(dl_next, last);
 	}
 
 	dl->internal = internal;
@@ -712,7 +669,7 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
  * has completed at frame end. If the flag is not returned display list
  * completion has been delayed by one frame because the display list commit
  * raced with the frame end interrupt. The function always returns with the flag
- * set in header mode as display list processing is then not continuous and
+ * set in single-shot mode as display list processing is then not continuous and
  * races never occur.
  *
  * The VSP1_DL_FRAME_END_INTERNAL flag indicates that the previous display list
@@ -784,13 +741,6 @@ void vsp1_dlm_setup(struct vsp1_device *vsp1)
 		 | VI6_DL_CTRL_DC2 | VI6_DL_CTRL_DC1 | VI6_DL_CTRL_DC0
 		 | VI6_DL_CTRL_DLE;
 
-	/*
-	 * The DRM pipeline operates with display lists in Continuous Frame
-	 * Mode, all other pipelines use manual start.
-	 */
-	if (vsp1->drm)
-		ctrl |= VI6_DL_CTRL_CFM0 | VI6_DL_CTRL_NH0;
-
 	vsp1_write(vsp1, VI6_DL_CTRL, ctrl);
 	vsp1_write(vsp1, VI6_DL_SWAP, VI6_DL_SWAP_LWS);
 }
@@ -830,8 +780,6 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 		return NULL;
 
 	dlm->index = index;
-	dlm->mode = index == 0 && !vsp1->info->uapi
-		  ? VSP1_DL_MODE_HEADERLESS : VSP1_DL_MODE_HEADER;
 	dlm->singleshot = vsp1->info->uapi;
 	dlm->vsp1 = vsp1;
 
@@ -840,14 +788,12 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 
 	/*
 	 * Initialize the display list body and allocate DMA memory for the body
-	 * and the optional header. Both are allocated together to avoid memory
+	 * and the header. Both are allocated together to avoid memory
 	 * fragmentation, with the header located right after the body in
 	 * memory. An extra body is allocated on top of the prealloc to account
 	 * for the cached body used by the vsp1_pipeline object.
 	 */
-	header_size = dlm->mode == VSP1_DL_MODE_HEADER
-		    ? ALIGN(sizeof(struct vsp1_dl_header), 8)
-		    : 0;
+	header_size = ALIGN(sizeof(struct vsp1_dl_header), 8);
 
 	dlm->pool = vsp1_dl_body_pool_create(vsp1, prealloc + 1,
 					     VSP1_DL_NUM_ENTRIES, header_size);
-- 
cgit v1.2.3


From 7d630c4924d82c4679e2df4bf55c2fd94e668e91 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:27 -0400
Subject: media: vsp1: Add support for extended display list headers

Extended display list headers allow pre and post command lists to be
executed by the VSP pipeline. This provides the base support for
features such as AUTO_FLD (for interlaced support) and AUTO_DISP (for
supporting continuous camera preview pipelines.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1.h      |   1 +
 drivers/media/platform/vsp1/vsp1_dl.c   | 105 +++++++++++++++++++++++++++++++-
 drivers/media/platform/vsp1/vsp1_dl.h   |  25 ++++++++
 drivers/media/platform/vsp1/vsp1_drv.c  |   4 +-
 drivers/media/platform/vsp1/vsp1_regs.h |   2 +-
 5 files changed, 133 insertions(+), 4 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1.h b/drivers/media/platform/vsp1/vsp1.h
index f0d21cc8e9ab..56c62122a81a 100644
--- a/drivers/media/platform/vsp1/vsp1.h
+++ b/drivers/media/platform/vsp1/vsp1.h
@@ -53,6 +53,7 @@ struct vsp1_uif;
 #define VSP1_HAS_HGO		(1 << 7)
 #define VSP1_HAS_HGT		(1 << 8)
 #define VSP1_HAS_BRS		(1 << 9)
+#define VSP1_HAS_EXT_DL		(1 << 10)
 
 struct vsp1_device_info {
 	u32 version;
diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index e535fee13d54..309ac4a38586 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -22,6 +22,9 @@
 #define VSP1_DLH_INT_ENABLE		(1 << 1)
 #define VSP1_DLH_AUTO_START		(1 << 0)
 
+#define VSP1_DLH_EXT_PRE_CMD_EXEC	(1 << 9)
+#define VSP1_DLH_EXT_POST_CMD_EXEC	(1 << 8)
+
 struct vsp1_dl_header_list {
 	u32 num_bytes;
 	u32 addr;
@@ -34,11 +37,58 @@ struct vsp1_dl_header {
 	u32 flags;
 } __packed;
 
+/**
+ * struct vsp1_dl_ext_header - Extended display list header
+ * @padding: padding zero bytes for alignment
+ * @pre_ext_dl_num_cmd: number of pre-extended command bodies to parse
+ * @flags: enables or disables execution of the pre and post command
+ * @pre_ext_dl_plist: start address of pre-extended display list bodies
+ * @post_ext_dl_num_cmd: number of post-extended command bodies to parse
+ * @post_ext_dl_plist: start address of post-extended display list bodies
+ */
+struct vsp1_dl_ext_header {
+	u32 padding;
+
+	/*
+	 * The datasheet represents flags as stored before pre_ext_dl_num_cmd,
+	 * expecting 32-bit accesses. The flags are appropriate to the whole
+	 * header, not just the pre_ext command, and thus warrant being
+	 * separated out. Due to byte ordering, and representing as 16 bit
+	 * values here, the flags must be positioned after the
+	 * pre_ext_dl_num_cmd.
+	 */
+	u16 pre_ext_dl_num_cmd;
+	u16 flags;
+	u32 pre_ext_dl_plist;
+
+	u32 post_ext_dl_num_cmd;
+	u32 post_ext_dl_plist;
+} __packed;
+
+struct vsp1_dl_header_extended {
+	struct vsp1_dl_header header;
+	struct vsp1_dl_ext_header ext;
+} __packed;
+
 struct vsp1_dl_entry {
 	u32 addr;
 	u32 data;
 } __packed;
 
+/**
+ * struct vsp1_pre_ext_dl_body - Pre Extended Display List Body
+ * @opcode: Extended display list command operation code
+ * @flags: Pre-extended command flags. These are specific to each command
+ * @address_set: Source address set pointer. Must have 16-byte alignment
+ * @reserved: Zero bits for alignment.
+ */
+struct vsp1_pre_ext_dl_body {
+	u32 opcode;
+	u32 flags;
+	u32 address_set;
+	u32 reserved;
+} __packed;
+
 /**
  * struct vsp1_dl_body - Display list body
  * @list: entry in the display list list of bodies
@@ -96,9 +146,12 @@ struct vsp1_dl_body_pool {
  * @list: entry in the display list manager lists
  * @dlm: the display list manager
  * @header: display list header
+ * @extension: extended display list header. NULL for normal lists
  * @dma: DMA address for the header
  * @body0: first display list body
  * @bodies: list of extra display list bodies
+ * @pre_cmd: pre command to be issued through extended dl header
+ * @post_cmd: post command to be issued through extended dl header
  * @has_chain: if true, indicates that there's a partition chain
  * @chain: entry in the display list partition chain
  * @internal: whether the display list is used for internal purpose
@@ -108,11 +161,15 @@ struct vsp1_dl_list {
 	struct vsp1_dl_manager *dlm;
 
 	struct vsp1_dl_header *header;
+	struct vsp1_dl_ext_header *extension;
 	dma_addr_t dma;
 
 	struct vsp1_dl_body *body0;
 	struct list_head bodies;
 
+	struct vsp1_dl_ext_cmd *pre_cmd;
+	struct vsp1_dl_ext_cmd *post_cmd;
+
 	bool has_chain;
 	struct list_head chain;
 
@@ -496,6 +553,14 @@ int vsp1_dl_list_add_chain(struct vsp1_dl_list *head,
 	return 0;
 }
 
+static void vsp1_dl_ext_cmd_fill_header(struct vsp1_dl_ext_cmd *cmd)
+{
+	cmd->cmds[0].opcode = cmd->opcode;
+	cmd->cmds[0].flags = cmd->flags;
+	cmd->cmds[0].address_set = cmd->data_dma;
+	cmd->cmds[0].reserved = 0;
+}
+
 static void vsp1_dl_list_fill_header(struct vsp1_dl_list *dl, bool is_last)
 {
 	struct vsp1_dl_manager *dlm = dl->dlm;
@@ -548,6 +613,27 @@ static void vsp1_dl_list_fill_header(struct vsp1_dl_list *dl, bool is_last)
 		 */
 		dl->header->flags = VSP1_DLH_INT_ENABLE;
 	}
+
+	if (!dl->extension)
+		return;
+
+	dl->extension->flags = 0;
+
+	if (dl->pre_cmd) {
+		dl->extension->pre_ext_dl_plist = dl->pre_cmd->cmd_dma;
+		dl->extension->pre_ext_dl_num_cmd = dl->pre_cmd->num_cmds;
+		dl->extension->flags |= VSP1_DLH_EXT_PRE_CMD_EXEC;
+
+		vsp1_dl_ext_cmd_fill_header(dl->pre_cmd);
+	}
+
+	if (dl->post_cmd) {
+		dl->extension->post_ext_dl_plist = dl->post_cmd->cmd_dma;
+		dl->extension->post_ext_dl_num_cmd = dl->post_cmd->num_cmds;
+		dl->extension->flags |= VSP1_DLH_EXT_POST_CMD_EXEC;
+
+		vsp1_dl_ext_cmd_fill_header(dl->post_cmd);
+	}
 }
 
 static bool vsp1_dl_list_hw_update_pending(struct vsp1_dl_manager *dlm)
@@ -737,9 +823,17 @@ done:
 /* Hardware Setup */
 void vsp1_dlm_setup(struct vsp1_device *vsp1)
 {
+	unsigned int i;
 	u32 ctrl = (256 << VI6_DL_CTRL_AR_WAIT_SHIFT)
 		 | VI6_DL_CTRL_DC2 | VI6_DL_CTRL_DC1 | VI6_DL_CTRL_DC0
 		 | VI6_DL_CTRL_DLE;
+	u32 ext_dl = (0x02 << VI6_DL_EXT_CTRL_POLINT_SHIFT)
+		   | VI6_DL_EXT_CTRL_DLPRI | VI6_DL_EXT_CTRL_EXT;
+
+	if (vsp1_feature(vsp1, VSP1_HAS_EXT_DL)) {
+		for (i = 0; i < vsp1->info->wpf_count; ++i)
+			vsp1_write(vsp1, VI6_DL_EXT_CTRL(i), ext_dl);
+	}
 
 	vsp1_write(vsp1, VI6_DL_CTRL, ctrl);
 	vsp1_write(vsp1, VI6_DL_SWAP, VI6_DL_SWAP_LWS);
@@ -793,7 +887,11 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 	 * memory. An extra body is allocated on top of the prealloc to account
 	 * for the cached body used by the vsp1_pipeline object.
 	 */
-	header_size = ALIGN(sizeof(struct vsp1_dl_header), 8);
+	header_size = vsp1_feature(vsp1, VSP1_HAS_EXT_DL) ?
+			sizeof(struct vsp1_dl_header_extended) :
+			sizeof(struct vsp1_dl_header);
+
+	header_size = ALIGN(header_size, 8);
 
 	dlm->pool = vsp1_dl_body_pool_create(vsp1, prealloc + 1,
 					     VSP1_DL_NUM_ENTRIES, header_size);
@@ -809,6 +907,11 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 			return NULL;
 		}
 
+		/* The extended header immediately follows the header. */
+		if (vsp1_feature(vsp1, VSP1_HAS_EXT_DL))
+			dl->extension = (void *)dl->header
+				      + sizeof(*dl->header);
+
 		list_add_tail(&dl->list, &dlm->free);
 	}
 
diff --git a/drivers/media/platform/vsp1/vsp1_dl.h b/drivers/media/platform/vsp1/vsp1_dl.h
index 7dba0469c92e..afefd5bfa136 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.h
+++ b/drivers/media/platform/vsp1/vsp1_dl.h
@@ -20,6 +20,31 @@ struct vsp1_dl_manager;
 #define VSP1_DL_FRAME_END_COMPLETED		BIT(0)
 #define VSP1_DL_FRAME_END_INTERNAL		BIT(1)
 
+/**
+ * struct vsp1_dl_ext_cmd - Extended Display command
+ * @free: entry in the pool of free commands list
+ * @opcode: command type opcode
+ * @flags: flags used by the command
+ * @cmds: array of command bodies for this extended cmd
+ * @num_cmds: quantity of commands in @cmds array
+ * @cmd_dma: DMA address of the command body
+ * @data: memory allocation for command-specific data
+ * @data_dma: DMA address for command-specific data
+ */
+struct vsp1_dl_ext_cmd {
+	struct list_head free;
+
+	u8 opcode;
+	u32 flags;
+
+	struct vsp1_pre_ext_dl_body *cmds;
+	unsigned int num_cmds;
+	dma_addr_t cmd_dma;
+
+	void *data;
+	dma_addr_t data_dma;
+};
+
 void vsp1_dlm_setup(struct vsp1_device *vsp1);
 
 struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
diff --git a/drivers/media/platform/vsp1/vsp1_drv.c b/drivers/media/platform/vsp1/vsp1_drv.c
index 3367c2ba990d..b6619c9c18bb 100644
--- a/drivers/media/platform/vsp1/vsp1_drv.c
+++ b/drivers/media/platform/vsp1/vsp1_drv.c
@@ -754,7 +754,7 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 		.version = VI6_IP_VERSION_MODEL_VSPD_GEN3,
 		.model = "VSP2-D",
 		.gen = 3,
-		.features = VSP1_HAS_BRU | VSP1_HAS_WPF_VFLIP,
+		.features = VSP1_HAS_BRU | VSP1_HAS_WPF_VFLIP | VSP1_HAS_EXT_DL,
 		.lif_count = 1,
 		.rpf_count = 5,
 		.uif_count = 1,
@@ -774,7 +774,7 @@ static const struct vsp1_device_info vsp1_device_infos[] = {
 		.version = VI6_IP_VERSION_MODEL_VSPDL_GEN3,
 		.model = "VSP2-DL",
 		.gen = 3,
-		.features = VSP1_HAS_BRS | VSP1_HAS_BRU,
+		.features = VSP1_HAS_BRS | VSP1_HAS_BRU | VSP1_HAS_EXT_DL,
 		.lif_count = 2,
 		.rpf_count = 5,
 		.uif_count = 2,
diff --git a/drivers/media/platform/vsp1/vsp1_regs.h b/drivers/media/platform/vsp1/vsp1_regs.h
index 0d249ff9f564..5ea9f9070cf3 100644
--- a/drivers/media/platform/vsp1/vsp1_regs.h
+++ b/drivers/media/platform/vsp1/vsp1_regs.h
@@ -72,7 +72,7 @@
 #define VI6_DL_SWAP_WDS			(1 << 1)
 #define VI6_DL_SWAP_BTS			(1 << 0)
 
-#define VI6_DL_EXT_CTRL			0x011c
+#define VI6_DL_EXT_CTRL(n)		(0x011c + (n) * 36)
 #define VI6_DL_EXT_CTRL_NWE		(1 << 16)
 #define VI6_DL_EXT_CTRL_POLINT_MASK	(0x3f << 8)
 #define VI6_DL_EXT_CTRL_POLINT_SHIFT	8
-- 
cgit v1.2.3


From f3b98e3c4d2e16bb7c99fc75d652559bd591070f Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:28 -0400
Subject: media: vsp1: Provide support for extended command pools

VSPD and VSP-DL devices can provide extended display lists supporting
extended command display list objects.

These extended commands require their own dma memory areas for a header
and body specific to the command type.

Implement a command pool to allocate all necessary memory in a single
DMA allocation to reduce pressure on the TLB, and provide convenient
re-usable command objects for the entities to utilise.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 193 ++++++++++++++++++++++++++++++++++
 drivers/media/platform/vsp1/vsp1_dl.h |   3 +
 2 files changed, 196 insertions(+)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 309ac4a38586..6021c43c53b4 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -141,6 +141,30 @@ struct vsp1_dl_body_pool {
 	struct vsp1_device *vsp1;
 };
 
+/**
+ * struct vsp1_cmd_pool - Display List commands pool
+ * @dma: DMA address of the entries
+ * @size: size of the full DMA memory pool in bytes
+ * @mem: CPU memory pointer for the pool
+ * @cmds: Array of command structures for the pool
+ * @free: Free pool entries
+ * @lock: Protects the free list
+ * @vsp1: the VSP1 device
+ */
+struct vsp1_dl_cmd_pool {
+	/* DMA allocation */
+	dma_addr_t dma;
+	size_t size;
+	void *mem;
+
+	struct vsp1_dl_ext_cmd *cmds;
+	struct list_head free;
+
+	spinlock_t lock;
+
+	struct vsp1_device *vsp1;
+};
+
 /**
  * struct vsp1_dl_list - Display list
  * @list: entry in the display list manager lists
@@ -187,6 +211,7 @@ struct vsp1_dl_list {
  * @queued: list queued to the hardware (written to the DL registers)
  * @pending: list waiting to be queued to the hardware
  * @pool: body pool for the display list bodies
+ * @autofld_cmds: command pool to support auto-fld interlaced mode
  */
 struct vsp1_dl_manager {
 	unsigned int index;
@@ -200,6 +225,7 @@ struct vsp1_dl_manager {
 	struct vsp1_dl_list *pending;
 
 	struct vsp1_dl_body_pool *pool;
+	struct vsp1_dl_cmd_pool *cmdpool;
 };
 
 /* -----------------------------------------------------------------------------
@@ -363,6 +389,157 @@ void vsp1_dl_body_write(struct vsp1_dl_body *dlb, u32 reg, u32 data)
 }
 
 /* -----------------------------------------------------------------------------
+ * Display List Extended Command Management
+ */
+
+enum vsp1_extcmd_type {
+	VSP1_EXTCMD_AUTODISP,
+	VSP1_EXTCMD_AUTOFLD,
+};
+
+struct vsp1_extended_command_info {
+	u16 opcode;
+	size_t body_size;
+};
+
+static const struct vsp1_extended_command_info vsp1_extended_commands[] = {
+	[VSP1_EXTCMD_AUTODISP] = { 0x02, 96 },
+	[VSP1_EXTCMD_AUTOFLD]  = { 0x03, 160 },
+};
+
+/**
+ * vsp1_dl_cmd_pool_create - Create a pool of commands from a single allocation
+ * @vsp1: The VSP1 device
+ * @type: The command pool type
+ * @num_cmds: The number of commands to allocate
+ *
+ * Allocate a pool of commands each with enough memory to contain the private
+ * data of each command. The allocation sizes are dependent upon the command
+ * type.
+ *
+ * Return a pointer to the pool on success or NULL if memory can't be allocated.
+ */
+static struct vsp1_dl_cmd_pool *
+vsp1_dl_cmd_pool_create(struct vsp1_device *vsp1, enum vsp1_extcmd_type type,
+			unsigned int num_cmds)
+{
+	struct vsp1_dl_cmd_pool *pool;
+	unsigned int i;
+	size_t cmd_size;
+
+	pool = kzalloc(sizeof(*pool), GFP_KERNEL);
+	if (!pool)
+		return NULL;
+
+	spin_lock_init(&pool->lock);
+	INIT_LIST_HEAD(&pool->free);
+
+	pool->cmds = kcalloc(num_cmds, sizeof(*pool->cmds), GFP_KERNEL);
+	if (!pool->cmds) {
+		kfree(pool);
+		return NULL;
+	}
+
+	cmd_size = sizeof(struct vsp1_pre_ext_dl_body) +
+		   vsp1_extended_commands[type].body_size;
+	cmd_size = ALIGN(cmd_size, 16);
+
+	pool->size = cmd_size * num_cmds;
+	pool->mem = dma_alloc_wc(vsp1->bus_master, pool->size, &pool->dma,
+				 GFP_KERNEL);
+	if (!pool->mem) {
+		kfree(pool->cmds);
+		kfree(pool);
+		return NULL;
+	}
+
+	for (i = 0; i < num_cmds; ++i) {
+		struct vsp1_dl_ext_cmd *cmd = &pool->cmds[i];
+		size_t cmd_offset = i * cmd_size;
+		/* data_offset must be 16 byte aligned for DMA. */
+		size_t data_offset = sizeof(struct vsp1_pre_ext_dl_body) +
+				     cmd_offset;
+
+		cmd->pool = pool;
+		cmd->opcode = vsp1_extended_commands[type].opcode;
+
+		/*
+		 * TODO: Auto-disp can utilise more than one extended body
+		 * command per cmd.
+		 */
+		cmd->num_cmds = 1;
+		cmd->cmds = pool->mem + cmd_offset;
+		cmd->cmd_dma = pool->dma + cmd_offset;
+
+		cmd->data = pool->mem + data_offset;
+		cmd->data_dma = pool->dma + data_offset;
+
+		list_add_tail(&cmd->free, &pool->free);
+	}
+
+	return pool;
+}
+
+static
+struct vsp1_dl_ext_cmd *vsp1_dl_ext_cmd_get(struct vsp1_dl_cmd_pool *pool)
+{
+	struct vsp1_dl_ext_cmd *cmd = NULL;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pool->lock, flags);
+
+	if (!list_empty(&pool->free)) {
+		cmd = list_first_entry(&pool->free, struct vsp1_dl_ext_cmd,
+				       free);
+		list_del(&cmd->free);
+	}
+
+	spin_unlock_irqrestore(&pool->lock, flags);
+
+	return cmd;
+}
+
+static void vsp1_dl_ext_cmd_put(struct vsp1_dl_ext_cmd *cmd)
+{
+	unsigned long flags;
+
+	if (!cmd)
+		return;
+
+	/* Reset flags, these mark data usage. */
+	cmd->flags = 0;
+
+	spin_lock_irqsave(&cmd->pool->lock, flags);
+	list_add_tail(&cmd->free, &cmd->pool->free);
+	spin_unlock_irqrestore(&cmd->pool->lock, flags);
+}
+
+static void vsp1_dl_ext_cmd_pool_destroy(struct vsp1_dl_cmd_pool *pool)
+{
+	if (!pool)
+		return;
+
+	if (pool->mem)
+		dma_free_wc(pool->vsp1->bus_master, pool->size, pool->mem,
+			    pool->dma);
+
+	kfree(pool->cmds);
+	kfree(pool);
+}
+
+struct vsp1_dl_ext_cmd *vsp1_dl_get_pre_cmd(struct vsp1_dl_list *dl)
+{
+	struct vsp1_dl_manager *dlm = dl->dlm;
+
+	if (dl->pre_cmd)
+		return dl->pre_cmd;
+
+	dl->pre_cmd = vsp1_dl_ext_cmd_get(dlm->cmdpool);
+
+	return dl->pre_cmd;
+}
+
+/* ----------------------------------------------------------------------------
  * Display List Transaction Management
  */
 
@@ -464,6 +641,12 @@ static void __vsp1_dl_list_put(struct vsp1_dl_list *dl)
 
 	vsp1_dl_list_bodies_put(dl);
 
+	vsp1_dl_ext_cmd_put(dl->pre_cmd);
+	vsp1_dl_ext_cmd_put(dl->post_cmd);
+
+	dl->pre_cmd = NULL;
+	dl->post_cmd = NULL;
+
 	/*
 	 * body0 is reused as as an optimisation as presently every display list
 	 * has at least one body, thus we reinitialise the entries list.
@@ -915,6 +1098,15 @@ struct vsp1_dl_manager *vsp1_dlm_create(struct vsp1_device *vsp1,
 		list_add_tail(&dl->list, &dlm->free);
 	}
 
+	if (vsp1_feature(vsp1, VSP1_HAS_EXT_DL)) {
+		dlm->cmdpool = vsp1_dl_cmd_pool_create(vsp1,
+					VSP1_EXTCMD_AUTOFLD, prealloc);
+		if (!dlm->cmdpool) {
+			vsp1_dlm_destroy(dlm);
+			return NULL;
+		}
+	}
+
 	return dlm;
 }
 
@@ -931,4 +1123,5 @@ void vsp1_dlm_destroy(struct vsp1_dl_manager *dlm)
 	}
 
 	vsp1_dl_body_pool_destroy(dlm->pool);
+	vsp1_dl_ext_cmd_pool_destroy(dlm->cmdpool);
 }
diff --git a/drivers/media/platform/vsp1/vsp1_dl.h b/drivers/media/platform/vsp1/vsp1_dl.h
index afefd5bfa136..125750dc8b5c 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.h
+++ b/drivers/media/platform/vsp1/vsp1_dl.h
@@ -22,6 +22,7 @@ struct vsp1_dl_manager;
 
 /**
  * struct vsp1_dl_ext_cmd - Extended Display command
+ * @pool: pool to which this command belongs
  * @free: entry in the pool of free commands list
  * @opcode: command type opcode
  * @flags: flags used by the command
@@ -32,6 +33,7 @@ struct vsp1_dl_manager;
  * @data_dma: DMA address for command-specific data
  */
 struct vsp1_dl_ext_cmd {
+	struct vsp1_dl_cmd_pool *pool;
 	struct list_head free;
 
 	u8 opcode;
@@ -58,6 +60,7 @@ struct vsp1_dl_body *vsp1_dlm_dl_body_get(struct vsp1_dl_manager *dlm);
 struct vsp1_dl_list *vsp1_dl_list_get(struct vsp1_dl_manager *dlm);
 void vsp1_dl_list_put(struct vsp1_dl_list *dl);
 struct vsp1_dl_body *vsp1_dl_list_get_body0(struct vsp1_dl_list *dl);
+struct vsp1_dl_ext_cmd *vsp1_dl_get_pre_cmd(struct vsp1_dl_list *dl);
 void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal);
 
 struct vsp1_dl_body_pool *
-- 
cgit v1.2.3


From e90561d40f830f1266d9531ae95eae8252dd8fa1 Mon Sep 17 00:00:00 2001
From: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Date: Fri, 3 Aug 2018 07:37:29 -0400
Subject: media: vsp1: Support Interlaced display pipelines

Calculate the top and bottom fields for the interlaced frames and
utilise the extended display list command feature to implement the
auto-field operations. This allows the DU to update the VSP2 registers
dynamically based upon the currently processing field.

Signed-off-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c   | 10 +++++
 drivers/media/platform/vsp1/vsp1_drm.c  |  6 ++-
 drivers/media/platform/vsp1/vsp1_pipe.h |  2 +
 drivers/media/platform/vsp1/vsp1_regs.h |  3 ++
 drivers/media/platform/vsp1/vsp1_rpf.c  | 72 +++++++++++++++++++++++++++++++--
 include/media/vsp1.h                    |  2 +
 6 files changed, 90 insertions(+), 5 deletions(-)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 6021c43c53b4..9255b5ee2cb8 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -947,6 +947,8 @@ void vsp1_dl_list_commit(struct vsp1_dl_list *dl, bool internal)
  */
 unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm)
 {
+	struct vsp1_device *vsp1 = dlm->vsp1;
+	u32 status = vsp1_read(vsp1, VI6_STATUS);
 	unsigned int flags = 0;
 
 	spin_lock(&dlm->lock);
@@ -971,6 +973,14 @@ unsigned int vsp1_dlm_irq_frame_end(struct vsp1_dl_manager *dlm)
 	if (vsp1_dl_list_hw_update_pending(dlm))
 		goto done;
 
+	/*
+	 * Progressive streams report only TOP fields. If we have a BOTTOM
+	 * field, we are interlaced, and expect the frame to complete on the
+	 * next frame end interrupt.
+	 */
+	if (status & VI6_STATUS_FLD_STD(dlm->index))
+		goto done;
+
 	/*
 	 * The device starts processing the queued display list right after the
 	 * frame end interrupt. The display list thus becomes active.
diff --git a/drivers/media/platform/vsp1/vsp1_drm.c b/drivers/media/platform/vsp1/vsp1_drm.c
index a16856856789..87dc3ddbe2d3 100644
--- a/drivers/media/platform/vsp1/vsp1_drm.c
+++ b/drivers/media/platform/vsp1/vsp1_drm.c
@@ -670,9 +670,11 @@ int vsp1_du_setup_lif(struct device *dev, unsigned int pipe_index,
 
 	drm_pipe->width = cfg->width;
 	drm_pipe->height = cfg->height;
+	pipe->interlaced = cfg->interlaced;
 
-	dev_dbg(vsp1->dev, "%s: configuring LIF%u with format %ux%u\n",
-		__func__, pipe_index, cfg->width, cfg->height);
+	dev_dbg(vsp1->dev, "%s: configuring LIF%u with format %ux%u%s\n",
+		__func__, pipe_index, cfg->width, cfg->height,
+		pipe->interlaced ? "i" : "");
 
 	mutex_lock(&vsp1->drm->lock);
 
diff --git a/drivers/media/platform/vsp1/vsp1_pipe.h b/drivers/media/platform/vsp1/vsp1_pipe.h
index 743d8f0db45c..ae646c9ef337 100644
--- a/drivers/media/platform/vsp1/vsp1_pipe.h
+++ b/drivers/media/platform/vsp1/vsp1_pipe.h
@@ -104,6 +104,7 @@ struct vsp1_partition {
  * @entities: list of entities in the pipeline
  * @stream_config: cached stream configuration for video pipelines
  * @configured: when false the @stream_config shall be written to the hardware
+ * @interlaced: True when the pipeline is configured in interlaced mode
  * @partitions: The number of partitions used to process one frame
  * @partition: The current partition for configuration to process
  * @part_table: The pre-calculated partitions used by the pipeline
@@ -142,6 +143,7 @@ struct vsp1_pipeline {
 
 	struct vsp1_dl_body *stream_config;
 	bool configured;
+	bool interlaced;
 
 	unsigned int partitions;
 	struct vsp1_partition *partition;
diff --git a/drivers/media/platform/vsp1/vsp1_regs.h b/drivers/media/platform/vsp1/vsp1_regs.h
index 5ea9f9070cf3..3738ff2f7b85 100644
--- a/drivers/media/platform/vsp1/vsp1_regs.h
+++ b/drivers/media/platform/vsp1/vsp1_regs.h
@@ -28,6 +28,7 @@
 #define VI6_SRESET_SRTS(n)		(1 << (n))
 
 #define VI6_STATUS			0x0038
+#define VI6_STATUS_FLD_STD(n)		(1 << ((n) + 28))
 #define VI6_STATUS_SYS_ACT(n)		(1 << ((n) + 8))
 
 #define VI6_WPF_IRQ_ENB(n)		(0x0048 + (n) * 12)
@@ -80,6 +81,8 @@
 #define VI6_DL_EXT_CTRL_EXPRI		(1 << 4)
 #define VI6_DL_EXT_CTRL_EXT		(1 << 0)
 
+#define VI6_DL_EXT_AUTOFLD_INT		BIT(0)
+
 #define VI6_DL_BODY_SIZE		0x0120
 #define VI6_DL_BODY_SIZE_UPD		(1 << 24)
 #define VI6_DL_BODY_SIZE_BS_MASK	(0x1ffff << 0)
diff --git a/drivers/media/platform/vsp1/vsp1_rpf.c b/drivers/media/platform/vsp1/vsp1_rpf.c
index 69e5fe6e6b50..f8005b60b9d2 100644
--- a/drivers/media/platform/vsp1/vsp1_rpf.c
+++ b/drivers/media/platform/vsp1/vsp1_rpf.c
@@ -20,6 +20,18 @@
 #define RPF_MAX_WIDTH				8190
 #define RPF_MAX_HEIGHT				8190
 
+/* Pre extended display list command data structure. */
+struct vsp1_extcmd_auto_fld_body {
+	u32 top_y0;
+	u32 bottom_y0;
+	u32 top_c0;
+	u32 bottom_c0;
+	u32 top_c1;
+	u32 bottom_c1;
+	u32 reserved0;
+	u32 reserved1;
+} __packed;
+
 /* -----------------------------------------------------------------------------
  * Device Access
  */
@@ -64,6 +76,14 @@ static void rpf_configure_stream(struct vsp1_entity *entity,
 		pstride |= format->plane_fmt[1].bytesperline
 			<< VI6_RPF_SRCM_PSTRIDE_C_SHIFT;
 
+	/*
+	 * pstride has both STRIDE_Y and STRIDE_C, but multiplying the whole
+	 * of pstride by 2 is conveniently OK here as we are multiplying both
+	 * values.
+	 */
+	if (pipe->interlaced)
+		pstride *= 2;
+
 	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_PSTRIDE, pstride);
 
 	/* Format */
@@ -100,6 +120,9 @@ static void rpf_configure_stream(struct vsp1_entity *entity,
 		top = compose->top;
 	}
 
+	if (pipe->interlaced)
+		top /= 2;
+
 	vsp1_rpf_write(rpf, dlb, VI6_RPF_LOC,
 		       (left << VI6_RPF_LOC_HCOORD_SHIFT) |
 		       (top << VI6_RPF_LOC_VCOORD_SHIFT));
@@ -169,6 +192,36 @@ static void rpf_configure_stream(struct vsp1_entity *entity,
 
 }
 
+static void vsp1_rpf_configure_autofld(struct vsp1_rwpf *rpf,
+				       struct vsp1_dl_list *dl)
+{
+	const struct v4l2_pix_format_mplane *format = &rpf->format;
+	struct vsp1_dl_ext_cmd *cmd;
+	struct vsp1_extcmd_auto_fld_body *auto_fld;
+	u32 offset_y, offset_c;
+
+	cmd = vsp1_dl_get_pre_cmd(dl);
+	if (WARN_ONCE(!cmd, "Failed to obtain an autofld cmd"))
+		return;
+
+	/* Re-index our auto_fld to match the current RPF. */
+	auto_fld = cmd->data;
+	auto_fld = &auto_fld[rpf->entity.index];
+
+	auto_fld->top_y0 = rpf->mem.addr[0];
+	auto_fld->top_c0 = rpf->mem.addr[1];
+	auto_fld->top_c1 = rpf->mem.addr[2];
+
+	offset_y = format->plane_fmt[0].bytesperline;
+	offset_c = format->plane_fmt[1].bytesperline;
+
+	auto_fld->bottom_y0 = rpf->mem.addr[0] + offset_y;
+	auto_fld->bottom_c0 = rpf->mem.addr[1] + offset_c;
+	auto_fld->bottom_c1 = rpf->mem.addr[2] + offset_c;
+
+	cmd->flags |= VI6_DL_EXT_AUTOFLD_INT | BIT(16 + rpf->entity.index);
+}
+
 static void rpf_configure_frame(struct vsp1_entity *entity,
 				struct vsp1_pipeline *pipe,
 				struct vsp1_dl_list *dl,
@@ -221,6 +274,11 @@ static void rpf_configure_partition(struct vsp1_entity *entity,
 		crop.left += pipe->partition->rpf.left;
 	}
 
+	if (pipe->interlaced) {
+		crop.height = round_down(crop.height / 2, fmtinfo->vsub);
+		crop.top = round_down(crop.top / 2, fmtinfo->vsub);
+	}
+
 	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRC_BSIZE,
 		       (crop.width << VI6_RPF_SRC_BSIZE_BHSIZE_SHIFT) |
 		       (crop.height << VI6_RPF_SRC_BSIZE_BVSIZE_SHIFT));
@@ -249,9 +307,17 @@ static void rpf_configure_partition(struct vsp1_entity *entity,
 	    fmtinfo->swap_uv)
 		swap(mem.addr[1], mem.addr[2]);
 
-	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_Y, mem.addr[0]);
-	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C0, mem.addr[1]);
-	vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C1, mem.addr[2]);
+	/*
+	 * Interlaced pipelines will use the extended pre-cmd to process
+	 * SRCM_ADDR_{Y,C0,C1}
+	 */
+	if (pipe->interlaced) {
+		vsp1_rpf_configure_autofld(rpf, dl);
+	} else {
+		vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_Y, mem.addr[0]);
+		vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C0, mem.addr[1]);
+		vsp1_rpf_write(rpf, dlb, VI6_RPF_SRCM_ADDR_C1, mem.addr[2]);
+	}
 }
 
 static void rpf_partition(struct vsp1_entity *entity,
diff --git a/include/media/vsp1.h b/include/media/vsp1.h
index 678c24de1ac6..3093b9cb9067 100644
--- a/include/media/vsp1.h
+++ b/include/media/vsp1.h
@@ -25,6 +25,7 @@ int vsp1_du_init(struct device *dev);
  * struct vsp1_du_lif_config - VSP LIF configuration
  * @width: output frame width
  * @height: output frame height
+ * @interlaced: true for interlaced pipelines
  * @callback: frame completion callback function (optional). When a callback
  *	      is provided, the VSP driver guarantees that it will be called once
  *	      and only once for each vsp1_du_atomic_flush() call.
@@ -33,6 +34,7 @@ int vsp1_du_init(struct device *dev);
 struct vsp1_du_lif_config {
 	unsigned int width;
 	unsigned int height;
+	bool interlaced;
 
 	void (*callback)(void *data, bool completed, u32 crc);
 	void *callback_data;
-- 
cgit v1.2.3


From 4679b79f217550f2f4c83101eb8149c5e552a93a Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:34:42 -0400
Subject: media: soc_camera_platform: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/soc_camera/soc_camera_platform.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/media/platform/soc_camera/soc_camera_platform.c b/drivers/media/platform/soc_camera/soc_camera_platform.c
index ce00e90d4e3c..6745a6e3f464 100644
--- a/drivers/media/platform/soc_camera/soc_camera_platform.c
+++ b/drivers/media/platform/soc_camera/soc_camera_platform.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Generic Platform Camera Driver
  *
  * Copyright (C) 2008 Magnus Damm
  * Based on mt9m001 driver,
  * Copyright (C) 2008, Guennadi Liakhovetski <kernel@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/init.h>
-- 
cgit v1.2.3


From 32955c5422a8a5460bbefe2a6fc51eadcafff4c9 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 May 2018 12:20:05 -0400
Subject: btrfs: switch to discard_new_inode()

Make sure that no partially set up inodes can be returned by
open-by-handle.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/btrfs/inode.c | 106 ++++++++++++++++++++-----------------------------------
 1 file changed, 39 insertions(+), 67 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index e9482f0db9d0..9382e0881900 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6335,8 +6335,10 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	location->type = BTRFS_INODE_ITEM_KEY;
 
 	ret = btrfs_insert_inode_locked(inode);
-	if (ret < 0)
+	if (ret < 0) {
+		iput(inode);
 		goto fail;
+	}
 
 	path->leave_spinning = 1;
 	ret = btrfs_insert_empty_items(trans, root, path, key, sizes, nitems);
@@ -6395,12 +6397,11 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	return inode;
 
 fail_unlock:
-	unlock_new_inode(inode);
+	discard_new_inode(inode);
 fail:
 	if (dir && name)
 		BTRFS_I(dir)->index_cnt--;
 	btrfs_free_path(path);
-	iput(inode);
 	return ERR_PTR(ret);
 }
 
@@ -6505,7 +6506,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = NULL;
 	int err;
-	int drop_inode = 0;
 	u64 objectid;
 	u64 index = 0;
 
@@ -6527,6 +6527,7 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
 
@@ -6541,31 +6542,24 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
 			0, index);
-	if (err) {
-		goto out_unlock_inode;
-	} else {
-		btrfs_update_inode(trans, root, inode);
-		d_instantiate_new(dentry, inode);
-	}
+	if (err)
+		goto out_unlock;
+
+	btrfs_update_inode(trans, root, inode);
+	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
-	if (drop_inode) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	return err;
-
-out_unlock_inode:
-	drop_inode = 1;
-	unlock_new_inode(inode);
-	goto out_unlock;
-
 }
 
 static int btrfs_create(struct inode *dir, struct dentry *dentry,
@@ -6575,7 +6569,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	struct btrfs_trans_handle *trans;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct inode *inode = NULL;
-	int drop_inode_on_err = 0;
 	int err;
 	u64 objectid;
 	u64 index = 0;
@@ -6598,9 +6591,9 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
-	drop_inode_on_err = 1;
 	/*
 	* If the active LSM wants to access the inode during
 	* d_instantiate it needs these. Smack checks to see
@@ -6613,33 +6606,28 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
 			0, index);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
 	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
-	if (err && drop_inode_on_err) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_unlock_inode:
-	unlock_new_inode(inode);
-	goto out_unlock;
-
 }
 
 static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
@@ -6748,6 +6736,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 			S_IFDIR | mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_fail;
 	}
 
@@ -6758,34 +6747,30 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	btrfs_i_size_write(BTRFS_I(inode), 0);
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
 			dentry->d_name.name,
 			dentry->d_name.len, 0, index);
 	if (err)
-		goto out_fail_inode;
+		goto out_fail;
 
 	d_instantiate_new(dentry, inode);
 	drop_on_err = 0;
 
 out_fail:
 	btrfs_end_transaction(trans);
-	if (drop_on_err) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_fail_inode:
-	unlock_new_inode(inode);
-	goto out_fail;
 }
 
 static noinline int uncompress_inline(struct btrfs_path *path,
@@ -10112,7 +10097,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	struct btrfs_key key;
 	struct inode *inode = NULL;
 	int err;
-	int drop_inode = 0;
 	u64 objectid;
 	u64 index = 0;
 	int name_len;
@@ -10145,6 +10129,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				objectid, S_IFLNK|S_IRWXUGO, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
+		inode = NULL;
 		goto out_unlock;
 	}
 
@@ -10161,12 +10146,12 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 
 	err = btrfs_init_inode_security(trans, inode, dir, &dentry->d_name);
 	if (err)
-		goto out_unlock_inode;
+		goto out_unlock;
 
 	path = btrfs_alloc_path();
 	if (!path) {
 		err = -ENOMEM;
-		goto out_unlock_inode;
+		goto out_unlock;
 	}
 	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.offset = 0;
@@ -10176,7 +10161,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 				      datasize);
 	if (err) {
 		btrfs_free_path(path);
-		goto out_unlock_inode;
+		goto out_unlock;
 	}
 	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -10208,26 +10193,19 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	if (!err)
 		err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
 				BTRFS_I(inode), 0, index);
-	if (err) {
-		drop_inode = 1;
-		goto out_unlock_inode;
-	}
+	if (err)
+		goto out_unlock;
 
 	d_instantiate_new(dentry, inode);
 
 out_unlock:
 	btrfs_end_transaction(trans);
-	if (drop_inode) {
+	if (err && inode) {
 		inode_dec_link_count(inode);
-		iput(inode);
+		discard_new_inode(inode);
 	}
 	btrfs_btree_balance_dirty(fs_info);
 	return err;
-
-out_unlock_inode:
-	drop_inode = 1;
-	unlock_new_inode(inode);
-	goto out_unlock;
 }
 
 static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
@@ -10436,14 +10414,14 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	ret = btrfs_init_inode_security(trans, inode, dir, NULL);
 	if (ret)
-		goto out_inode;
+		goto out;
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret)
-		goto out_inode;
+		goto out;
 	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 	if (ret)
-		goto out_inode;
+		goto out;
 
 	/*
 	 * We set number of links to 0 in btrfs_new_inode(), and here we set
@@ -10453,21 +10431,15 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	 *    d_tmpfile() -> inode_dec_link_count() -> drop_nlink()
 	 */
 	set_nlink(inode, 1);
-	unlock_new_inode(inode);
 	d_tmpfile(dentry, inode);
+	unlock_new_inode(inode);
 	mark_inode_dirty(inode);
-
 out:
 	btrfs_end_transaction(trans);
-	if (ret)
-		iput(inode);
+	if (ret && inode)
+		discard_new_inode(inode);
 	btrfs_btree_balance_dirty(fs_info);
 	return ret;
-
-out_inode:
-	unlock_new_inode(inode);
-	goto out;
-
 }
 
 __attribute__((const))
-- 
cgit v1.2.3


From dd54992776ebb44519ba4cd69145c4f19d166ddb Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 May 2018 12:22:50 -0400
Subject: ufs: switch to discard_new_inode()

we don't want open-by-handle to pick an in-core inode that
has failed setup halfway through.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ufs/ialloc.c | 3 +--
 fs/ufs/namei.c  | 9 +++------
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index e1ef0f0a1353..02c0a4be4212 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -343,8 +343,7 @@ cg_found:
 fail_remove_inode:
 	mutex_unlock(&sbi->s_lock);
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	UFSD("EXIT (FAILED): err %d\n", err);
 	return ERR_PTR(err);
 failed:
diff --git a/fs/ufs/namei.c b/fs/ufs/namei.c
index d5f43ba76c59..9ef40f100415 100644
--- a/fs/ufs/namei.c
+++ b/fs/ufs/namei.c
@@ -43,8 +43,7 @@ static inline int ufs_add_nondir(struct dentry *dentry, struct inode *inode)
 		return 0;
 	}
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -142,8 +141,7 @@ static int ufs_symlink (struct inode * dir, struct dentry * dentry,
 
 out_fail:
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -198,8 +196,7 @@ static int ufs_mkdir(struct inode * dir, struct dentry * dentry, umode_t mode)
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput (inode);
+	discard_new_inode(inode);
 out_dir:
 	inode_dec_link_count(dir);
 	return err;
-- 
cgit v1.2.3


From 5c1a68a358f94b9ac2e33183327bc04f207feed2 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 May 2018 12:25:39 -0400
Subject: udf: switch to discard_new_inode()

we don't want open-by-handle to pick an in-core inode that
has failed setup halfway through.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/udf/namei.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index c586026508db..061d049c2620 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -608,8 +608,7 @@ static int udf_add_nondir(struct dentry *dentry, struct inode *inode)
 	fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err);
 	if (unlikely(!fi)) {
 		inode_dec_link_count(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		return err;
 	}
 	cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
@@ -700,8 +699,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	fi = udf_add_entry(inode, NULL, &fibh, &cfi, &err);
 	if (!fi) {
 		inode_dec_link_count(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		goto out;
 	}
 	set_nlink(inode, 2);
@@ -719,8 +717,7 @@ static int udf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (!fi) {
 		clear_nlink(inode);
 		mark_inode_dirty(inode);
-		unlock_new_inode(inode);
-		iput(inode);
+		discard_new_inode(inode);
 		goto out;
 	}
 	cfi.icb.extLength = cpu_to_le32(inode->i_sb->s_blocksize);
@@ -1047,8 +1044,7 @@ out:
 out_no_entry:
 	up_write(&iinfo->i_data_sem);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	goto out;
 }
 
-- 
cgit v1.2.3


From 2e5afe54e0cd6fce79b51ca547caf08a990ad56d Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 16 May 2018 18:29:56 -0400
Subject: ext2: make sure that partially set up inodes won't be returned by
 ext2_iget()

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/ext2/ialloc.c | 3 +--
 fs/ext2/namei.c  | 9 +++------
 2 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c
index 6484199b35d1..5c3d7b7e4975 100644
--- a/fs/ext2/ialloc.c
+++ b/fs/ext2/ialloc.c
@@ -611,8 +611,7 @@ fail_drop:
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
 	clear_nlink(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return ERR_PTR(err);
 
 fail:
diff --git a/fs/ext2/namei.c b/fs/ext2/namei.c
index 152453a91877..0c26dcc5d850 100644
--- a/fs/ext2/namei.c
+++ b/fs/ext2/namei.c
@@ -45,8 +45,7 @@ static inline int ext2_add_nondir(struct dentry *dentry, struct inode *inode)
 		return 0;
 	}
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 	return err;
 }
 
@@ -192,8 +191,7 @@ out:
 
 out_fail:
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput (inode);
+	discard_new_inode(inode);
 	goto out;
 }
 
@@ -261,8 +259,7 @@ out:
 out_fail:
 	inode_dec_link_count(inode);
 	inode_dec_link_count(inode);
-	unlock_new_inode(inode);
-	iput(inode);
+	discard_new_inode(inode);
 out_dir:
 	inode_dec_link_count(dir);
 	goto out;
-- 
cgit v1.2.3


From a6cbedfa8783b42b9272c05297865bdb501005cb Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 29 Jun 2018 11:59:37 -0400
Subject: jfs: switch to discard_new_inode()

we don't want open-by-handle to pick an in-core inode that
has failed setup halfway through.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/jfs/jfs_inode.c |  8 ++++----
 fs/jfs/namei.c     | 12 ++++--------
 2 files changed, 8 insertions(+), 12 deletions(-)

diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 5e9b7bb3aabf..96732c24b054 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -61,8 +61,7 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 	inode = new_inode(sb);
 	if (!inode) {
 		jfs_warn("ialloc: new_inode returned NULL!");
-		rc = -ENOMEM;
-		goto fail;
+		return ERR_PTR(-ENOMEM);
 	}
 
 	jfs_inode = JFS_IP(inode);
@@ -141,9 +140,10 @@ fail_drop:
 	dquot_drop(inode);
 	inode->i_flags |= S_NOQUOTA;
 	clear_nlink(inode);
-	unlock_new_inode(inode);
+	discard_new_inode(inode);
+	return ERR_PTR(rc);
+
 fail_put:
 	iput(inode);
-fail:
 	return ERR_PTR(rc);
 }
diff --git a/fs/jfs/namei.c b/fs/jfs/namei.c
index 56c3fcbfe80e..14528c0ffe63 100644
--- a/fs/jfs/namei.c
+++ b/fs/jfs/namei.c
@@ -175,8 +175,7 @@ static int jfs_create(struct inode *dip, struct dentry *dentry, umode_t mode,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -309,8 +308,7 @@ static int jfs_mkdir(struct inode *dip, struct dentry *dentry, umode_t mode)
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -1054,8 +1052,7 @@ static int jfs_symlink(struct inode *dip, struct dentry *dentry,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
@@ -1441,8 +1438,7 @@ static int jfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (rc) {
 		free_ea_wmap(ip);
 		clear_nlink(ip);
-		unlock_new_inode(ip);
-		iput(ip);
+		discard_new_inode(ip);
 	} else {
 		d_instantiate_new(dentry, ip);
 	}
-- 
cgit v1.2.3


From e950564b97fd0f541b02eb207685d0746f5ecf29 Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Tue, 24 Jul 2018 15:01:55 +0200
Subject: vfs: don't evict uninitialized inode

iput() ends up calling ->evict() on new inode, which is not yet initialized
by owning fs.  So use destroy_inode() instead.

Add to sb->s_inodes list only if inode is not in I_CREATING state (meaning
that it wasn't allocated with new_inode(), which already does the
insertion).

Reported-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Fixes: 80ea09a002bf ("vfs: factor out inode_insert5()")
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/inode.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/inode.c b/fs/inode.c
index 6cd2e7ba9f4d..e44a97584158 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1050,6 +1050,7 @@ struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 {
 	struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval);
 	struct inode *old;
+	bool creating = inode->i_state & I_CREATING;
 
 again:
 	spin_lock(&inode_hash_lock);
@@ -1083,6 +1084,8 @@ again:
 	inode->i_state |= I_NEW;
 	hlist_add_head(&inode->i_hash, head);
 	spin_unlock(&inode->i_lock);
+	if (!creating)
+		inode_sb_list_add(inode);
 unlock:
 	spin_unlock(&inode_hash_lock);
 
@@ -1117,12 +1120,13 @@ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval,
 	struct inode *inode = ilookup5(sb, hashval, test, data);
 
 	if (!inode) {
-		struct inode *new = new_inode(sb);
+		struct inode *new = alloc_inode(sb);
 
 		if (new) {
+			new->i_state = 0;
 			inode = inode_insert5(new, hashval, test, set, data);
 			if (unlikely(inode != new))
-				iput(new);
+				destroy_inode(new);
 		}
 	}
 	return inode;
-- 
cgit v1.2.3


From 5bef915104f32c9d0bb5df6e86a98e31cb524e9a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 29 Jun 2018 19:36:57 -0400
Subject: new helper: inode_fake_hash()

open-coded in a quite a few places...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/hfs/inode.c     |  2 +-
 fs/jfs/jfs_imap.c  |  8 +-------
 fs/jfs/super.c     |  2 +-
 fs/xfs/xfs_iops.c  |  2 +-
 include/linux/fs.h | 11 +++++++++++
 5 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index 2a16111d312f..a2dfa1b2a89c 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -541,7 +541,7 @@ static struct dentry *hfs_file_lookup(struct inode *dir, struct dentry *dentry,
 	HFS_I(inode)->rsrc_inode = dir;
 	HFS_I(dir)->rsrc_inode = inode;
 	igrab(dir);
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 	mark_inode_dirty(inode);
 	dont_mount(dentry);
 out:
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index f36ef68905a7..93e8c590ff5c 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -491,13 +491,7 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary)
 	/* release the page */
 	release_metapage(mp);
 
-	/*
-	 * __mark_inode_dirty expects inodes to be hashed.  Since we don't
-	 * want special inodes in the fileset inode space, we make them
-	 * appear hashed, but do not put on any lists.  hlist_del()
-	 * will work fine and require no locking.
-	 */
-	hlist_add_fake(&ip->i_hash);
+	inode_fake_hash(ip);
 
 	return (ip);
 }
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 1b9264fd54b6..5403ece57dba 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -581,7 +581,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	inode->i_ino = 0;
 	inode->i_size = i_size_read(sb->s_bdev->bd_inode);
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	sbi->direct_inode = inode;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 0fa29f39d658..3a75de777843 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -1253,7 +1253,7 @@ xfs_setup_inode(
 
 	inode_sb_list_add(inode);
 	/* make the inode look hashed for the writeback code */
-	hlist_add_fake(&inode->i_hash);
+	inode_fake_hash(inode);
 
 	inode->i_uid    = xfs_uid_to_kuid(ip->i_d.di_uid);
 	inode->i_gid    = xfs_gid_to_kgid(ip->i_d.di_gid);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index a42600565925..43941e230e2b 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -684,6 +684,17 @@ static inline int inode_unhashed(struct inode *inode)
 	return hlist_unhashed(&inode->i_hash);
 }
 
+/*
+ * __mark_inode_dirty expects inodes to be hashed.  Since we don't
+ * want special inodes in the fileset inode space, we make them
+ * appear hashed, but do not put on any lists.  hlist_del()
+ * will work fine and require no locking.
+ */
+static inline void inode_fake_hash(struct inode *inode)
+{
+	hlist_add_fake(&inode->i_hash);
+}
+
 /*
  * inode->i_mutex nesting subclasses for the lock validator:
  *
-- 
cgit v1.2.3


From d8e78da8682028ad53d040339a2b9d6fb6092d63 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 30 Jun 2018 03:15:49 -0400
Subject: adfs: don't put inodes into icache

We never look them up in there; inode_fake_hash() will make them appear
hashed for mark_inode_dirty() purposes.  And don't leave them around
until memory pressure kicks them out - we never look them up again.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/adfs/inode.c | 2 +-
 fs/adfs/super.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index c836c425ca94..e91028d4340a 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -287,7 +287,7 @@ adfs_iget(struct super_block *sb, struct object_info *obj)
 		ADFS_I(inode)->mmu_private = inode->i_size;
 	}
 
-	insert_inode_hash(inode);
+	inode_fake_hash(inode);
 
 out:
 	return inode;
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 71fa525d63a0..7e099a7a4eb1 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -291,6 +291,7 @@ static void destroy_inodecache(void)
 static const struct super_operations adfs_sops = {
 	.alloc_inode	= adfs_alloc_inode,
 	.destroy_inode	= adfs_destroy_inode,
+	.drop_inode	= generic_delete_inode,
 	.write_inode	= adfs_write_inode,
 	.put_super	= adfs_put_super,
 	.statfs		= adfs_statfs,
-- 
cgit v1.2.3


From c7b15a8657da7f8d11269c7cc3d8beef10d26b43 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 30 Jun 2018 14:32:04 -0400
Subject: jfs: don't bother with make_bad_inode() in ialloc()

We hit that when inumber allocation has failed.  In that case
the in-core inode is not hashed and since its ->i_nlink is 1
the only place where jfs checks is_bad_inode() won't be reached.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/jfs/jfs_inode.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 96732c24b054..4572b7cf183d 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -69,8 +69,6 @@ struct inode *ialloc(struct inode *parent, umode_t mode)
 	rc = diAlloc(parent, S_ISDIR(mode), inode);
 	if (rc) {
 		jfs_warn("ialloc: diAlloc returned %d!", rc);
-		if (rc == -EIO)
-			make_bad_inode(inode);
 		goto fail_put;
 	}
 
-- 
cgit v1.2.3


From aa7b827878f06876c32b050d1737c3a1a3816af1 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:35:06 -0400
Subject: media: rcar-vin: convert to SPDX identifiers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Kconfig and Makefile doesn't have license line, thus,
these are GPL-2.0 as default.
All ohter files are GPL-2.0+ as original license.

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-vin/Kconfig     | 1 +
 drivers/media/platform/rcar-vin/Makefile    | 1 +
 drivers/media/platform/rcar-vin/rcar-core.c | 8 ++------
 drivers/media/platform/rcar-vin/rcar-dma.c  | 6 +-----
 drivers/media/platform/rcar-vin/rcar-v4l2.c | 6 +-----
 drivers/media/platform/rcar-vin/rcar-vin.h  | 6 +-----
 6 files changed, 7 insertions(+), 21 deletions(-)

diff --git a/drivers/media/platform/rcar-vin/Kconfig b/drivers/media/platform/rcar-vin/Kconfig
index baf4eafff6e3..e3eb8fee2536 100644
--- a/drivers/media/platform/rcar-vin/Kconfig
+++ b/drivers/media/platform/rcar-vin/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 config VIDEO_RCAR_CSI2
 	tristate "R-Car MIPI CSI-2 Receiver"
 	depends on VIDEO_V4L2 && VIDEO_V4L2_SUBDEV_API && OF
diff --git a/drivers/media/platform/rcar-vin/Makefile b/drivers/media/platform/rcar-vin/Makefile
index 5ab803d3e7c1..00d809f5d2c1 100644
--- a/drivers/media/platform/rcar-vin/Makefile
+++ b/drivers/media/platform/rcar-vin/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
 rcar-vin-objs = rcar-core.o rcar-dma.o rcar-v4l2.o
 
 obj-$(CONFIG_VIDEO_RCAR_CSI2) += rcar-csi2.o
diff --git a/drivers/media/platform/rcar-vin/rcar-core.c b/drivers/media/platform/rcar-vin/rcar-core.c
index 8843367cd339..ce09799976ef 100644
--- a/drivers/media/platform/rcar-vin/rcar-core.c
+++ b/drivers/media/platform/rcar-vin/rcar-core.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/module.h>
@@ -1275,4 +1271,4 @@ module_platform_driver(rcar_vin_driver);
 
 MODULE_AUTHOR("Niklas Söderlund <niklas.soderlund@ragnatech.se>");
 MODULE_DESCRIPTION("Renesas R-Car VIN camera host driver");
-MODULE_LICENSE("GPL v2");
+MODULE_LICENSE("GPL");
diff --git a/drivers/media/platform/rcar-vin/rcar-dma.c b/drivers/media/platform/rcar-vin/rcar-dma.c
index 9146f63430c2..92323310f735 100644
--- a/drivers/media/platform/rcar-vin/rcar-dma.c
+++ b/drivers/media/platform/rcar-vin/rcar-dma.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/delay.h>
diff --git a/drivers/media/platform/rcar-vin/rcar-v4l2.c b/drivers/media/platform/rcar-vin/rcar-v4l2.c
index 87a718b1c2e6..5a54779cfc27 100644
--- a/drivers/media/platform/rcar-vin/rcar-v4l2.c
+++ b/drivers/media/platform/rcar-vin/rcar-v4l2.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #include <linux/pm_runtime.h>
diff --git a/drivers/media/platform/rcar-vin/rcar-vin.h b/drivers/media/platform/rcar-vin/rcar-vin.h
index df2a47e4be31..0b13b34d03e3 100644
--- a/drivers/media/platform/rcar-vin/rcar-vin.h
+++ b/drivers/media/platform/rcar-vin/rcar-vin.h
@@ -1,3 +1,4 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
 /*
  * Driver for Renesas R-Car VIN
  *
@@ -7,11 +8,6 @@
  * Copyright (C) 2008 Magnus Damm
  *
  * Based on the soc-camera rcar_vin driver
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
  */
 
 #ifndef __RCAR_VIN__
-- 
cgit v1.2.3


From 58c708f64aee6a0adf4e7ca00589c0bf1dd69fe6 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:35:23 -0400
Subject: media: rcar-fcp: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar-fcp.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/media/platform/rcar-fcp.c b/drivers/media/platform/rcar-fcp.c
index 2988031d285d..b47af8eb145a 100644
--- a/drivers/media/platform/rcar-fcp.c
+++ b/drivers/media/platform/rcar-fcp.c
@@ -1,14 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * rcar-fcp.c  --  R-Car Frame Compression Processor Driver
  *
  * Copyright (C) 2016 Renesas Electronics Corporation
  *
  * Contact: Laurent Pinchart (laurent.pinchart@ideasonboard.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/device.h>
-- 
cgit v1.2.3


From adeb6970568256e4208b1b131f710f544c58d5c8 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:35:49 -0400
Subject: media: rcar_drif: convert to SPDX identifiers

As original license mentioned, it is GPL-2.0+ in SPDX.
Then, MODULE_LICENSE() should be "GPL" instead of "GPL v2".
See ${LINUX}/include/linux/module.h

	"GPL"		[GNU Public License v2 or later]
	"GPL v2"	[GNU Public License v2]

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Acked-by: Ramesh Shanmugasundaram <ramesh.shanmugasundaram@bp.renesas.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar_drif.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/media/platform/rcar_drif.c b/drivers/media/platform/rcar_drif.c
index dc7e280c91b4..81413ab52475 100644
--- a/drivers/media/platform/rcar_drif.c
+++ b/drivers/media/platform/rcar_drif.c
@@ -1,13 +1,9 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * R-Car Gen3 Digital Radio Interface (DRIF) driver
  *
  * Copyright (C) 2017 Renesas Electronics Corporation
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
  * This program is distributed in the hope that it will be useful,
  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
@@ -1499,5 +1495,5 @@ module_platform_driver(rcar_drif_driver);
 
 MODULE_DESCRIPTION("Renesas R-Car Gen3 DRIF driver");
 MODULE_ALIAS("platform:" RCAR_DRIF_DRV_NAME);
-MODULE_LICENSE("GPL v2");
+MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Ramesh Shanmugasundaram <ramesh.shanmugasundaram@bp.renesas.com>");
-- 
cgit v1.2.3


From 7c1d62e455ab934ab3fdf86e03bc2a1fa550aa23 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:36:04 -0400
Subject: media: rcar_fdp1: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Acked-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar_fdp1.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/media/platform/rcar_fdp1.c b/drivers/media/platform/rcar_fdp1.c
index b13dec3081e5..2a15b7cca338 100644
--- a/drivers/media/platform/rcar_fdp1.c
+++ b/drivers/media/platform/rcar_fdp1.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * Renesas R-Car Fine Display Processor
  *
@@ -8,11 +9,6 @@
  *
  * This code is developed and inspired from the vim2m, rcar_jpu,
  * m2m-deinterlace, and vsp1 drivers.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by the
- * Free Software Foundation; either version 2 of the
- * License, or (at your option) any later version
  */
 
 #include <linux/clk.h>
-- 
cgit v1.2.3


From 88352b163c839277be367ddcf13ef5971ce9df2a Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:36:21 -0400
Subject: media: rcar_jpu: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/rcar_jpu.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/media/platform/rcar_jpu.c b/drivers/media/platform/rcar_jpu.c
index a808258a4180..e5c882423f57 100644
--- a/drivers/media/platform/rcar_jpu.c
+++ b/drivers/media/platform/rcar_jpu.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * Author: Mikhail Ulyanov
  * Copyright (C) 2014-2015 Cogent Embedded, Inc.  <source@cogentembedded.com>
@@ -11,10 +12,6 @@
  *      1) Rotation
  *      2) Cropping
  *      3) V4L2_CID_JPEG_ACTIVE_MARKER
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <asm/unaligned.h>
-- 
cgit v1.2.3


From d81469d2b77553b281b9b59eadd995309728f506 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:36:36 -0400
Subject: media: sh_veu: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/sh_veu.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/media/platform/sh_veu.c b/drivers/media/platform/sh_veu.c
index 1a0cde017fdf..1d274c64de09 100644
--- a/drivers/media/platform/sh_veu.c
+++ b/drivers/media/platform/sh_veu.c
@@ -1,13 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * sh-mobile VEU mem2mem driver
  *
  * Copyright (C) 2012 Renesas Electronics Corporation
  * Author: Guennadi Liakhovetski, <g.liakhovetski@gmx.de>
  * Copyright (C) 2008 Magnus Damm
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the version 2 of the GNU General Public License as
- * published by the Free Software Foundation
  */
 
 #include <linux/err.h>
-- 
cgit v1.2.3


From 7b381978c8563672e19d90db00119d74ed2221b3 Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:36:55 -0400
Subject: media: sh_vou: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/sh_vou.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/media/platform/sh_vou.c b/drivers/media/platform/sh_vou.c
index 4dccf29e9d78..6135e13e24d4 100644
--- a/drivers/media/platform/sh_vou.c
+++ b/drivers/media/platform/sh_vou.c
@@ -1,11 +1,8 @@
+// SPDX-License-Identifier: GPL-2.0
 /*
  * SuperH Video Output Unit (VOU) driver
  *
  * Copyright (C) 2010, Guennadi Liakhovetski <g.liakhovetski@gmx.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 #include <linux/dma-mapping.h>
-- 
cgit v1.2.3


From 12f336c88090fb8004736fd4329184326a49673b Mon Sep 17 00:00:00 2001
From: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Date: Wed, 25 Jul 2018 22:37:11 -0400
Subject: media: sh_mobile_ceu: convert to SPDX identifiers

Signed-off-by: Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
Signed-off-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Reviewed-by: Simon Horman <horms+renesas@verge.net.au>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
index 9897213f2618..0a2c0daaffef 100644
--- a/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
+++ b/drivers/media/platform/soc_camera/sh_mobile_ceu_camera.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * V4L2 Driver for SuperH Mobile CEU interface
  *
@@ -7,11 +8,6 @@
  *
  * Copyright (C) 2006, Sascha Hauer, Pengutronix
  * Copyright (C) 2008, Guennadi Liakhovetski <kernel@pengutronix.de>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
  */
 
 #include <linux/init.h>
-- 
cgit v1.2.3


From 16200248f48dded48f7c79a0d20d18b8c6b02605 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 10:36:01 -0400
Subject: media: dvb-usb: fix spelling mistake: "completition" -> "completion"

Trivial fix to spelling mistake in debug and error messages

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb/usb-urb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/usb/dvb-usb/usb-urb.c b/drivers/media/usb/dvb-usb/usb-urb.c
index 5e05963f4220..9771f0954c69 100644
--- a/drivers/media/usb/dvb-usb/usb-urb.c
+++ b/drivers/media/usb/dvb-usb/usb-urb.c
@@ -33,7 +33,7 @@ static void usb_urb_complete(struct urb *urb)
 		case -ESHUTDOWN:
 			return;
 		default:        /* error */
-			deb_ts("urb completition error %d.\n", urb->status);
+			deb_ts("urb completion error %d.\n", urb->status);
 			break;
 	}
 
@@ -57,7 +57,7 @@ static void usb_urb_complete(struct urb *urb)
 				stream->complete(stream, b, urb->actual_length);
 			break;
 		default:
-			err("unknown endpoint type in completition handler.");
+			err("unknown endpoint type in completion handler.");
 			return;
 	}
 	usb_submit_urb(urb,GFP_ATOMIC);
-- 
cgit v1.2.3


From 3c8496e5d0595cec6e463b35b7ad87eefabc531f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 10:36:00 -0400
Subject: media: dvb-usb-v2: fix spelling mistake: "completition" ->
 "completion"

Trivial fix to spelling mistake in dev_dbg and dev_err messages

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb-v2/usb_urb.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/usb/dvb-usb-v2/usb_urb.c b/drivers/media/usb/dvb-usb-v2/usb_urb.c
index b0499f95ec45..024c751eb165 100644
--- a/drivers/media/usb/dvb-usb-v2/usb_urb.c
+++ b/drivers/media/usb/dvb-usb-v2/usb_urb.c
@@ -40,7 +40,7 @@ static void usb_urb_complete(struct urb *urb)
 		return;
 	default:        /* error */
 		dev_dbg_ratelimited(&stream->udev->dev,
-				"%s: urb completition failed=%d\n",
+				"%s: urb completion failed=%d\n",
 				__func__, urb->status);
 		break;
 	}
@@ -69,7 +69,7 @@ static void usb_urb_complete(struct urb *urb)
 		break;
 	default:
 		dev_err(&stream->udev->dev,
-				"%s: unknown endpoint type in completition handler\n",
+				"%s: unknown endpoint type in completion handler\n",
 				KBUILD_MODNAME);
 		return;
 	}
-- 
cgit v1.2.3


From 854bb4ec126320046afd2e299c8dd070946d2410 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 10:35:59 -0400
Subject: media: cx231xx: fix spelling mistake: "completition" -> "completion"

Trivial fix to spelling mistake in dev_dbg debug messages

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/cx231xx/cx231xx-audio.c | 4 ++--
 drivers/media/usb/cx231xx/cx231xx-vbi.c   | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/usb/cx231xx/cx231xx-audio.c b/drivers/media/usb/cx231xx/cx231xx-audio.c
index 0025187c28e3..32ee7b3f21c9 100644
--- a/drivers/media/usb/cx231xx/cx231xx-audio.c
+++ b/drivers/media/usb/cx231xx/cx231xx-audio.c
@@ -112,7 +112,7 @@ static void cx231xx_audio_isocirq(struct urb *urb)
 	case -ESHUTDOWN:
 		return;
 	default:		/* error */
-		dev_dbg(dev->dev, "urb completition error %d.\n",
+		dev_dbg(dev->dev, "urb completion error %d.\n",
 			urb->status);
 		break;
 	}
@@ -203,7 +203,7 @@ static void cx231xx_audio_bulkirq(struct urb *urb)
 	case -ESHUTDOWN:
 		return;
 	default:		/* error */
-		dev_dbg(dev->dev, "urb completition error %d.\n",
+		dev_dbg(dev->dev, "urb completion error %d.\n",
 			urb->status);
 		break;
 	}
diff --git a/drivers/media/usb/cx231xx/cx231xx-vbi.c b/drivers/media/usb/cx231xx/cx231xx-vbi.c
index 920417baf893..10b2eb7338ad 100644
--- a/drivers/media/usb/cx231xx/cx231xx-vbi.c
+++ b/drivers/media/usb/cx231xx/cx231xx-vbi.c
@@ -317,7 +317,7 @@ static void cx231xx_irq_vbi_callback(struct urb *urb)
 		return;
 	default:		/* error */
 		dev_err(dev->dev,
-			"urb completition error %d.\n",	urb->status);
+			"urb completion error %d.\n", urb->status);
 		break;
 	}
 
-- 
cgit v1.2.3


From 1e506464a4d5c5d7482fda1f745b9ec79e44ad4f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 10:35:58 -0400
Subject: media: au0828: fix spelling mistake: "completition" -> "completion"

Trivial fix to spelling mistake in au0828_isocdbg debug message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/au0828/au0828-video.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/au0828/au0828-video.c b/drivers/media/usb/au0828/au0828-video.c
index 70e187971590..62b45062b1e6 100644
--- a/drivers/media/usb/au0828/au0828-video.c
+++ b/drivers/media/usb/au0828/au0828-video.c
@@ -133,7 +133,7 @@ static void au0828_irq_callback(struct urb *urb)
 		au0828_isocdbg("au0828_irq_callback called: status kill\n");
 		return;
 	default:            /* unknown error */
-		au0828_isocdbg("urb completition error %d.\n", urb->status);
+		au0828_isocdbg("urb completion error %d.\n", urb->status);
 		break;
 	}
 
-- 
cgit v1.2.3


From 483f3fdcc70b3c3a1f314235ab0066f3dbd4cfbe Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Sat, 4 Aug 2018 00:31:48 +0200
Subject: netfilter: nft_tunnel: fix sparse errors

[...]
net/netfilter/nft_tunnel.c:117:25:    expected unsigned int [unsigned] [usertype] flags
net/netfilter/nft_tunnel.c:117:25:    got restricted __be16 [usertype] <noident>
[...]
net/netfilter/nft_tunnel.c:246:33:    expected restricted __be16 [addressable] [assigned] [usertype] tp_dst
net/netfilter/nft_tunnel.c:246:33:    got int

Fixes: af308b94a2a4 ("netfilter: nf_tables: add tunnel support")
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_tunnel.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index 9332d7933dd5..3a15f219e4e7 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -116,7 +116,7 @@ struct nft_tunnel_opts {
 		struct erspan_metadata	erspan;
 	} u;
 	u32	len;
-	u32	flags;
+	__be16	flags;
 };
 
 struct nft_tunnel_obj {
@@ -337,12 +337,10 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
 	}
 
 	if (tb[NFTA_TUNNEL_KEY_SPORT]) {
-		info.key.tp_src =
-			ntohs(nla_get_be16(tb[NFTA_TUNNEL_KEY_SPORT]));
+		info.key.tp_src = nla_get_be16(tb[NFTA_TUNNEL_KEY_SPORT]);
 	}
 	if (tb[NFTA_TUNNEL_KEY_DPORT]) {
-		info.key.tp_dst =
-			ntohs(nla_get_be16(tb[NFTA_TUNNEL_KEY_DPORT]));
+		info.key.tp_dst = nla_get_be16(tb[NFTA_TUNNEL_KEY_DPORT]);
 	}
 
 	if (tb[NFTA_TUNNEL_KEY_FLAGS]) {
-- 
cgit v1.2.3


From 51f7e95187f127d5eadf50541943813ff57f12ba Mon Sep 17 00:00:00 2001
From: Jason Baron <jbaron@akamai.com>
Date: Fri, 3 Aug 2018 17:24:53 -0400
Subject: af_unix: ensure POLLOUT on remote close() for connected dgram socket

Applications use -ECONNREFUSED as returned from write() in order to
determine that a socket should be closed. However, when using connected
dgram unix sockets in a poll/write loop, a final POLLOUT event can be
missed when the remote end closes. Thus, the poll is stuck forever:

          thread 1 (client)                   thread 2 (server)

connect() to server
write() returns -EAGAIN
unix_dgram_poll()
 -> unix_recvq_full() is true
                                       close()
                                        ->unix_release_sock()
                                         ->wake_up_interruptible_all()
unix_dgram_poll() (due to the
     wake_up_interruptible_all)
 -> unix_recvq_full() still is true
                                         ->free all skbs

Now thread 1 is stuck and will not receive anymore wakeups. In this
case, when thread 1 gets the -EAGAIN, it has not queued any skbs
otherwise the 'free all skbs' step would in fact cause a wakeup and
a POLLOUT return. So the race here is probably fairly rare because
it means there are no skbs that thread 1 queued and that thread 1
schedules before the 'free all skbs' step.

This issue was reported as a hang when /dev/log is closed.

The fix is to signal POLLOUT if the socket is marked as SOCK_DEAD, which
means a subsequent write() will get -ECONNREFUSED.

Reported-by: Ian Lance Taylor <iant@golang.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Rainer Weikusat <rweikusat@mobileactivedefense.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Jason Baron <jbaron@akamai.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/unix/af_unix.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 1772a0e32665..d1edfa3cad61 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -430,7 +430,12 @@ static int unix_dgram_peer_wake_me(struct sock *sk, struct sock *other)
 
 	connected = unix_dgram_peer_wake_connect(sk, other);
 
-	if (unix_recvq_full(other))
+	/* If other is SOCK_DEAD, we want to make sure we signal
+	 * POLLOUT, such that a subsequent write() can get a
+	 * -ECONNREFUSED. Otherwise, if we haven't queued any skbs
+	 * to other and its full, we will hang waiting for POLLOUT.
+	 */
+	if (unix_recvq_full(other) && !sock_flag(other, SOCK_DEAD))
 		return 1;
 
 	if (connected)
-- 
cgit v1.2.3


From a01512b14d4faa9f6f7501201d7033216d2e563a Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 3 Aug 2018 16:28:48 +0800
Subject: tcp: remove unneeded variable 'err'

variable 'err' is unmodified after initalization,
so simply cleans up it and returns 0.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 31fa1c080f28..b8af2fec5ad5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2531,7 +2531,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 	struct inet_sock *inet = inet_sk(sk);
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	int err = 0;
 	int old_state = sk->sk_state;
 
 	if (old_state != TCP_CLOSE)
@@ -2612,7 +2611,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	}
 
 	sk->sk_error_report(sk);
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL(tcp_disconnect);
 
-- 
cgit v1.2.3


From 1021bcf44d0e876b10f8739594ad7e6e9c746026 Mon Sep 17 00:00:00 2001
From: Geliang Tang <geliangtang@gmail.com>
Date: Wed, 1 Aug 2018 19:23:37 +0800
Subject: pstore: add zstd compression support

This patch added the 6th compression algorithm support for pstore: zstd.

Signed-off-by: Geliang Tang <geliangtang@gmail.com>
Signed-off-by: Kees Cook <keescook@chromium.org>
---
 fs/pstore/Kconfig    | 17 ++++++++++++++---
 fs/pstore/platform.c | 16 ++++++++++++++++
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig
index 09c19ef91526..503086f7f7c1 100644
--- a/fs/pstore/Kconfig
+++ b/fs/pstore/Kconfig
@@ -50,12 +50,19 @@ config PSTORE_842_COMPRESS
 	help
 	  This option enables 842 compression algorithm support.
 
+config PSTORE_ZSTD_COMPRESS
+	bool "zstd compression"
+	depends on PSTORE
+	select CRYPTO_ZSTD
+	help
+	  This option enables zstd compression algorithm support.
+
 config PSTORE_COMPRESS
 	def_bool y
 	depends on PSTORE
 	depends on PSTORE_DEFLATE_COMPRESS || PSTORE_LZO_COMPRESS ||	\
 		   PSTORE_LZ4_COMPRESS || PSTORE_LZ4HC_COMPRESS ||	\
-		   PSTORE_842_COMPRESS
+		   PSTORE_842_COMPRESS || PSTORE_ZSTD_COMPRESS
 
 choice
 	prompt "Default pstore compression algorithm"
@@ -65,8 +72,8 @@ choice
 	  This change be changed at boot with "pstore.compress=..." on
 	  the kernel command line.
 
-	  Currently, pstore has support for 5 compression algorithms:
-	  deflate, lzo, lz4, lz4hc and 842.
+	  Currently, pstore has support for 6 compression algorithms:
+	  deflate, lzo, lz4, lz4hc, 842 and zstd.
 
 	  The default compression algorithm is deflate.
 
@@ -85,6 +92,9 @@ choice
 	config PSTORE_842_COMPRESS_DEFAULT
 		bool "842" if PSTORE_842_COMPRESS
 
+	config PSTORE_ZSTD_COMPRESS_DEFAULT
+		bool "zstd" if PSTORE_ZSTD_COMPRESS
+
 endchoice
 
 config PSTORE_COMPRESS_DEFAULT
@@ -95,6 +105,7 @@ config PSTORE_COMPRESS_DEFAULT
 	default "lz4" if PSTORE_LZ4_COMPRESS_DEFAULT
 	default "lz4hc" if PSTORE_LZ4HC_COMPRESS_DEFAULT
 	default "842" if PSTORE_842_COMPRESS_DEFAULT
+	default "zstd" if PSTORE_ZSTD_COMPRESS_DEFAULT
 
 config PSTORE_CONSOLE
 	bool "Log kernel console messages"
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index c238ab8ba31d..15e99d5a681d 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -34,6 +34,9 @@
 #if IS_ENABLED(CONFIG_PSTORE_LZ4_COMPRESS) || IS_ENABLED(CONFIG_PSTORE_LZ4HC_COMPRESS)
 #include <linux/lz4.h>
 #endif
+#if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS)
+#include <linux/zstd.h>
+#endif
 #include <linux/crypto.h>
 #include <linux/string.h>
 #include <linux/timer.h>
@@ -192,6 +195,13 @@ static int zbufsize_842(size_t size)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS)
+static int zbufsize_zstd(size_t size)
+{
+	return ZSTD_compressBound(size);
+}
+#endif
+
 static const struct pstore_zbackend *zbackend __ro_after_init;
 
 static const struct pstore_zbackend zbackends[] = {
@@ -224,6 +234,12 @@ static const struct pstore_zbackend zbackends[] = {
 		.zbufsize	= zbufsize_842,
 		.name		= "842",
 	},
+#endif
+#if IS_ENABLED(CONFIG_PSTORE_ZSTD_COMPRESS)
+	{
+		.zbufsize	= zbufsize_zstd,
+		.name		= "zstd",
+	},
 #endif
 	{ }
 };
-- 
cgit v1.2.3


From 909da6e4b577be65432ba4bcede3e036db2d1dc8 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Fri, 3 Aug 2018 13:44:39 +0200
Subject: mt76x0: rename mt76_* functions

mt76_* functions conflicts with mt7601u driver what prevents to build
those drivers in the kernel or use both drivers modules at once.

Patch fixes build errors like this:
ld: drivers/net/wireless/mediatek/mt76/mt76x0/mac.o:(.opd+0x30): multiple definition of `mt76_mac_tx_rate_val'; drivers/net/wireless/mediatek/mt7601u/mac.o:(.opd+0x30): first defined here

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 7b4859026ccd ("mt76x0: core files")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/dma.c    |  2 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    | 14 +++++++-------
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.h    | 12 ++++++------
 drivers/net/wireless/mediatek/mt76/mt76x0/main.c   |  8 ++++----
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt76x0/tx.c     |  8 ++++----
 drivers/net/wireless/mediatek/mt76/mt76x0/util.c   |  4 ++--
 7 files changed, 26 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
index 2cf71283de3f..d91b1bb8fcc7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
@@ -44,7 +44,7 @@ mt76x0_rx_skb_from_seg(struct mt76x0_dev *dev, struct mt76x0_rxwi *rxwi,
 	if (!skb)
 		return NULL;
 
-	true_len = mt76_mac_process_rx(dev, skb, data, rxwi);
+	true_len = mt76x0_mac_process_rx(dev, skb, data, rxwi);
 	if (!true_len || true_len > seg_len)
 		goto bad_frame;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 7b32777c06e9..5f12724eeb62 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -116,7 +116,7 @@ mt76_mac_fill_tx_status(struct mt76x0_dev *dev, struct ieee80211_tx_info *info,
 		info->flags |= IEEE80211_TX_STAT_ACK;
 }
 
-u16 mt76_mac_tx_rate_val(struct mt76x0_dev *dev,
+u16 mt76x0_mac_tx_rate_val(struct mt76x0_dev *dev,
 			 const struct ieee80211_tx_rate *rate, u8 *nss_val)
 {
 	u16 rateval;
@@ -166,13 +166,13 @@ u16 mt76_mac_tx_rate_val(struct mt76x0_dev *dev,
 	return cpu_to_le16(rateval);
 }
 
-void mt76_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
+void mt76x0_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
 			    const struct ieee80211_tx_rate *rate)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&dev->mt76.lock, flags);
-	wcid->tx_rate = mt76_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
+	wcid->tx_rate = mt76x0_mac_tx_rate_val(dev, rate, &wcid->tx_rate_nss);
 	wcid->tx_rate_set = true;
 	spin_unlock_irqrestore(&dev->mt76.lock, flags);
 }
@@ -198,7 +198,7 @@ struct mt76_tx_status mt76x0_mac_fetch_tx_status(struct mt76x0_dev *dev)
 	return stat;
 }
 
-void mt76_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update)
+void mt76x0_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update)
 {
 	struct ieee80211_tx_info info = {};
 	struct ieee80211_sta *sta = NULL;
@@ -527,7 +527,7 @@ mt76x0_rx_is_our_beacon(struct mt76x0_dev *dev, u8 *data)
 		ether_addr_equal(hdr->addr2, dev->ap_bssid);
 }
 
-u32 mt76_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
+u32 mt76x0_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
 			u8 *data, void *rxi)
 {
 	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
@@ -594,7 +594,7 @@ mt76_mac_get_key_info(struct ieee80211_key_conf *key, u8 *key_data)
 	}
 }
 
-int mt76_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
+int mt76x0_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
 			  struct ieee80211_key_conf *key)
 {
 	enum mt76_cipher_type cipher;
@@ -635,7 +635,7 @@ int mt76_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
 	return 0;
 }
 
-int mt76_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
+int mt76x0_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
 			      struct ieee80211_key_conf *key)
 {
 	enum mt76_cipher_type cipher;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h
index 947eba253553..bea067b71c13 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.h
@@ -136,19 +136,19 @@ struct mt76_txwi {
 
 #define MT_TXWI_PKTID_PROBE             BIT(7)
 
-u32 mt76_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
+u32 mt76x0_mac_process_rx(struct mt76x0_dev *dev, struct sk_buff *skb,
 			u8 *data, void *rxi);
-int mt76_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
+int mt76x0_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
 			  struct ieee80211_key_conf *key);
-void mt76_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
+void mt76x0_mac_wcid_set_rate(struct mt76x0_dev *dev, struct mt76_wcid *wcid,
 			    const struct ieee80211_tx_rate *rate);
 
-int mt76_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
+int mt76x0_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
 			      struct ieee80211_key_conf *key);
-u16 mt76_mac_tx_rate_val(struct mt76x0_dev *dev,
+u16 mt76x0_mac_tx_rate_val(struct mt76x0_dev *dev,
 			 const struct ieee80211_tx_rate *rate, u8 *nss_val);
 struct mt76_tx_status
 mt76x0_mac_fetch_tx_status(struct mt76x0_dev *dev);
-void mt76_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update);
+void mt76x0_send_tx_status(struct mt76x0_dev *dev, struct mt76_tx_status *stat, u8 *update);
 
 #endif
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
index 0c521f3485c9..cf6ffb1ba4a2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/main.c
@@ -300,15 +300,15 @@ mt76x0_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 	if (!msta) {
 		if (key || wcid->hw_key_idx == idx) {
-			ret = mt76_mac_wcid_set_key(dev, wcid->idx, key);
+			ret = mt76x0_mac_wcid_set_key(dev, wcid->idx, key);
 			if (ret)
 				return ret;
 		}
 
-		return mt76_mac_shared_key_setup(dev, mvif->idx, idx, key);
+		return mt76x0_mac_shared_key_setup(dev, mvif->idx, idx, key);
 	}
 
-	return mt76_mac_wcid_set_key(dev, msta->wcid.idx, key);
+	return mt76x0_mac_wcid_set_key(dev, msta->wcid.idx, key);
 }
 
 static int mt76x0_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
@@ -375,7 +375,7 @@ mt76_sta_rate_tbl_update(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	rate.idx = rates->rate[0].idx;
 	rate.flags = rates->rate[0].flags;
-	mt76_mac_wcid_set_rate(dev, &msta->wcid, &rate);
+	mt76x0_mac_wcid_set_rate(dev, &msta->wcid, &rate);
 
 out:
 	rcu_read_unlock();
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index 9e60fcb14687..c1feca3ea016 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -324,8 +324,8 @@ void mt76x0_tx_status(struct mt76x0_dev *dev, struct sk_buff *skb);
 void mt76x0_tx_stat(struct work_struct *work);
 
 /* util */
-void mt76_remove_hdr_pad(struct sk_buff *skb);
-int mt76_insert_hdr_pad(struct sk_buff *skb);
+void mt76x0_remove_hdr_pad(struct sk_buff *skb);
+int mt76x0_insert_hdr_pad(struct sk_buff *skb);
 
 int mt76x0_dma_init(struct mt76x0_dev *dev);
 void mt76x0_dma_cleanup(struct mt76x0_dev *dev);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
index 28b8e1508016..976d3ee91f67 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
@@ -35,7 +35,7 @@ static void mt76x0_tx_skb_remove_dma_overhead(struct sk_buff *skb,
 
 	skb_pull(skb, sizeof(struct mt76_txwi) + 4);
 	if (ieee80211_get_hdrlen_from_skb(skb) % 4)
-		mt76_remove_hdr_pad(skb);
+		mt76x0_remove_hdr_pad(skb);
 
 	skb_trim(skb, pkt_len);
 }
@@ -93,7 +93,7 @@ mt76x0_push_txwi(struct mt76x0_dev *dev, struct sk_buff *skb,
 		rate_ctl = wcid->tx_rate;
 		nss = wcid->tx_rate_nss;
 	} else {
-		rate_ctl = mt76_mac_tx_rate_val(dev, rate, &nss);
+		rate_ctl = mt76x0_mac_tx_rate_val(dev, rate, &nss);
 	}
 	spin_unlock_irqrestore(&dev->mt76.lock, flags);
 
@@ -158,7 +158,7 @@ void mt76x0_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
 	BUILD_BUG_ON(ARRAY_SIZE(info->status.status_driver_data) < 1);
 	info->status.status_driver_data[0] = (void *)(unsigned long)pkt_len;
 
-	if (mt76x0_skb_rooms(dev, skb) || mt76_insert_hdr_pad(skb)) {
+	if (mt76x0_skb_rooms(dev, skb) || mt76x0_insert_hdr_pad(skb)) {
 		ieee80211_free_txskb(dev->mt76.hw, skb);
 		return;
 	}
@@ -194,7 +194,7 @@ void mt76x0_tx_stat(struct work_struct *work)
 		if (!stat.valid)
 			break;
 
-		mt76_send_tx_status(dev, &stat, &update);
+		mt76x0_send_tx_status(dev, &stat, &update);
 
 		cleaned++;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/util.c b/drivers/net/wireless/mediatek/mt76/mt76x0/util.c
index 148be47d822f..7856dd760419 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/util.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/util.c
@@ -13,7 +13,7 @@
 
 #include "mt76x0.h"
 
-void mt76_remove_hdr_pad(struct sk_buff *skb)
+void mt76x0_remove_hdr_pad(struct sk_buff *skb)
 {
 	int len = ieee80211_get_hdrlen_from_skb(skb);
 
@@ -21,7 +21,7 @@ void mt76_remove_hdr_pad(struct sk_buff *skb)
 	skb_pull(skb, 2);
 }
 
-int mt76_insert_hdr_pad(struct sk_buff *skb)
+int mt76x0_insert_hdr_pad(struct sk_buff *skb)
 {
 	int len = ieee80211_get_hdrlen_from_skb(skb);
 	int ret;
-- 
cgit v1.2.3


From e800a333135bef633ffb21bdd471b8ffc491db7b Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Fri, 3 Aug 2018 13:44:40 +0200
Subject: mt76x0: rename trace symbols

Rename trace symbols that conflict with mt7601u and remove some
definitions that are not used.

Patch fixes build errors like this:
ld: drivers/net/wireless/mediatek/mt76/mt76x0/trace.o:(__tracepoints+0x0): multiple definition of `__tracepoint_set_shared_key'; drivers/net/wireless/mediatek/mt7601u/trace.o:(__tracepoints+0x0): first defined here

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 7b4859026ccd ("mt76x0: core files")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/dma.c    |  8 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c    |  4 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c    |  8 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h |  6 --
 drivers/net/wireless/mediatek/mt76/mt76x0/phy.c    |  4 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/trace.h  | 87 +++++-----------------
 drivers/net/wireless/mediatek/mt76/mt76x0/tx.c     |  4 +-
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c    |  8 +-
 8 files changed, 35 insertions(+), 94 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
index d91b1bb8fcc7..e2efb430419b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/dma.c
@@ -105,7 +105,7 @@ static void mt76x0_rx_process_seg(struct mt76x0_dev *dev, u8 *data,
 	if (unlikely(FIELD_GET(MT_RXD_INFO_TYPE, fce_info)))
 		dev_err_once(dev->mt76.dev, "Error: RX path seen a non-pkt urb\n");
 
-	trace_mt_rx(&dev->mt76, rxwi, fce_info);
+	trace_mt76x0_rx(&dev->mt76, rxwi, fce_info);
 
 	skb = mt76x0_rx_skb_from_seg(dev, rxwi, data, seg_len, truesize, p);
 	if (!skb)
@@ -155,7 +155,7 @@ mt76x0_rx_process_entry(struct mt76x0_dev *dev, struct mt76x0_dma_buf_rx *e)
 	}
 
 	if (cnt > 1)
-		trace_mt_rx_dma_aggr(&dev->mt76, cnt, !!new_p);
+		trace_mt76x0_rx_dma_aggr(&dev->mt76, cnt, !!new_p);
 
 	if (new_p) {
 		/* we have one extra ref from the allocator */
@@ -235,7 +235,7 @@ static void mt76x0_complete_tx(struct urb *urb)
 		goto out;
 
 	skb = q->e[q->start].skb;
-	trace_mt_tx_dma_done(&dev->mt76, skb);
+	trace_mt76x0_tx_dma_done(&dev->mt76, skb);
 
 	__skb_queue_tail(&dev->tx_skb_done, skb);
 	tasklet_schedule(&dev->tx_tasklet);
@@ -384,7 +384,7 @@ static int mt76x0_submit_rx_buf(struct mt76x0_dev *dev,
 	usb_fill_bulk_urb(e->urb, usb_dev, pipe, buf, MT_RX_URB_SIZE,
 			  mt76x0_complete_rx, dev);
 
-	trace_mt_submit_urb(&dev->mt76, e->urb);
+	trace_mt76x0_submit_urb(&dev->mt76, e->urb);
 	ret = usb_submit_urb(e->urb, gfp);
 	if (ret)
 		dev_err(dev->mt76.dev, "Error: submit RX URB failed:%d\n", ret);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 5f12724eeb62..95f28492a843 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -606,7 +606,7 @@ int mt76x0_mac_wcid_set_key(struct mt76x0_dev *dev, u8 idx,
 	if (cipher == MT_CIPHER_NONE && key)
 		return -EINVAL;
 
-	trace_set_key(&dev->mt76, idx);
+	trace_mt76x0_set_key(&dev->mt76, idx);
 
 	mt76_wr_copy(dev, MT_WCID_KEY(idx), key_data, sizeof(key_data));
 
@@ -646,7 +646,7 @@ int mt76x0_mac_shared_key_setup(struct mt76x0_dev *dev, u8 vif_idx, u8 key_idx,
 	if (cipher == MT_CIPHER_NONE && key)
 		return -EINVAL;
 
-	trace_set_shared_key(&dev->mt76, vif_idx, key_idx);
+	trace_mt76x0_set_shared_key(&dev->mt76, vif_idx, key_idx);
 
 	mt76_wr_copy(dev, MT_SKEY(vif_idx, key_idx),
 			key_data, sizeof(key_data));
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
index 979ba519e54f..8affacbab90a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mcu.c
@@ -48,7 +48,7 @@ static inline void mt76x0_dma_skb_wrap_cmd(struct sk_buff *skb,
 				     FIELD_PREP(MT_TXD_CMD_TYPE, cmd)));
 }
 
-static inline void trace_mt_mcu_msg_send_cs(struct mt76_dev *dev,
+static inline void trace_mt76x0_mcu_msg_send_cs(struct mt76_dev *dev,
 					    struct sk_buff *skb, bool need_resp)
 {
 	u32 i, csum = 0;
@@ -56,7 +56,7 @@ static inline void trace_mt_mcu_msg_send_cs(struct mt76_dev *dev,
 	for (i = 0; i < skb->len / 4; i++)
 		csum ^= get_unaligned_le32(skb->data + i * 4);
 
-	trace_mt_mcu_msg_send(dev, skb, csum, need_resp);
+	trace_mt76x0_mcu_msg_send(dev, skb, csum, need_resp);
 }
 
 static struct sk_buff *
@@ -168,8 +168,8 @@ __mt76x0_mcu_msg_send(struct mt76x0_dev *dev, struct sk_buff *skb,
 	if (dev->mcu.resp_cmpl.done)
 		dev_err(dev->mt76.dev, "Error: MCU response pre-completed!\n");
 
-	trace_mt_mcu_msg_send_cs(&dev->mt76, skb, wait_resp);
-	trace_mt_submit_urb_sync(&dev->mt76, cmd_pipe, skb->len);
+	trace_mt76x0_mcu_msg_send_cs(&dev->mt76, skb, wait_resp);
+	trace_mt76x0_submit_urb_sync(&dev->mt76, cmd_pipe, skb->len);
 
 	ret = usb_bulk_msg(usb_dev, cmd_pipe, skb->data, skb->len, &sent, 500);
 	if (ret) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
index c1feca3ea016..fc9857f61771 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mt76x0.h
@@ -124,12 +124,6 @@ struct mt76x0_eeprom_params;
 
 #define MT_VEND_ADDR(type, n)	(MT_VEND_TYPE_##type | (n))
 
-enum mt_temp_mode {
-	MT_TEMP_MODE_NORMAL,
-	MT_TEMP_MODE_HIGH,
-	MT_TEMP_MODE_LOW,
-};
-
 enum mt_bw {
 	MT_BW_20,
 	MT_BW_40,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
index e52a50661b1a..5da7bfbe907f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/phy.c
@@ -52,7 +52,7 @@ mt76x0_rf_csr_wr(struct mt76x0_dev *dev, u32 offset, u8 value)
 		   FIELD_PREP(MT_RF_CSR_CFG_REG_ID, reg) |
 		   MT_RF_CSR_CFG_WR |
 		   MT_RF_CSR_CFG_KICK);
-	trace_rf_write(&dev->mt76, bank, offset, value);
+	trace_mt76x0_rf_write(&dev->mt76, bank, offset, value);
 out:
 	mutex_unlock(&dev->reg_atomic_mutex);
 
@@ -96,7 +96,7 @@ mt76x0_rf_csr_rr(struct mt76x0_dev *dev, u32 offset)
 	if (FIELD_GET(MT_RF_CSR_CFG_REG_ID, val) == reg &&
 	    FIELD_GET(MT_RF_CSR_CFG_REG_BANK, val) == bank) {
 		ret = FIELD_GET(MT_RF_CSR_CFG_DATA, val);
-		trace_rf_read(&dev->mt76, bank, offset, ret);
+		trace_mt76x0_rf_read(&dev->mt76, bank, offset, ret);
 	}
 out:
 	mutex_unlock(&dev->reg_atomic_mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
index cdf53e5442d8..8a752a09f2dc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/trace.h
@@ -51,17 +51,17 @@ DECLARE_EVENT_CLASS(dev_reg_evt,
 	)
 );
 
-DEFINE_EVENT(dev_reg_evt, reg_read,
+DEFINE_EVENT(dev_reg_evt, mt76x0_reg_read,
 	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
 	TP_ARGS(dev, reg, val)
 );
 
-DEFINE_EVENT(dev_reg_evt, reg_write,
+DEFINE_EVENT(dev_reg_evt, mt76x0_reg_write,
 	TP_PROTO(struct mt76_dev *dev, u32 reg, u32 val),
 	TP_ARGS(dev, reg, val)
 );
 
-TRACE_EVENT(mt_submit_urb,
+TRACE_EVENT(mt76x0_submit_urb,
 	TP_PROTO(struct mt76_dev *dev, struct urb *u),
 	TP_ARGS(dev, u),
 	TP_STRUCT__entry(
@@ -76,14 +76,14 @@ TRACE_EVENT(mt_submit_urb,
 		  DEV_PR_ARG, __entry->pipe, __entry->len)
 );
 
-#define trace_mt_submit_urb_sync(__dev, __pipe, __len) ({	\
+#define trace_mt76x0_submit_urb_sync(__dev, __pipe, __len) ({	\
 	struct urb u;					\
 	u.pipe = __pipe;				\
 	u.transfer_buffer_length = __len;		\
-	trace_mt_submit_urb(__dev, &u);			\
+	trace_mt76x0_submit_urb(__dev, &u);			\
 })
 
-TRACE_EVENT(mt_mcu_msg_send,
+TRACE_EVENT(mt76x0_mcu_msg_send,
 	TP_PROTO(struct mt76_dev *dev,
 		 struct sk_buff *skb, u32 csum, bool resp),
 	TP_ARGS(dev, skb, csum, resp),
@@ -103,7 +103,7 @@ TRACE_EVENT(mt_mcu_msg_send,
 		  DEV_PR_ARG, __entry->info, __entry->csum, __entry->resp)
 );
 
-TRACE_EVENT(mt_vend_req,
+TRACE_EVENT(mt76x0_vend_req,
 	TP_PROTO(struct mt76_dev *dev, unsigned pipe, u8 req, u8 req_type,
 		 u16 val, u16 offset, void *buf, size_t buflen, int ret),
 	TP_ARGS(dev, pipe, req, req_type, val, offset, buf, buflen, ret),
@@ -131,21 +131,6 @@ TRACE_EVENT(mt_vend_req,
 		  !!__entry->buf, __entry->buflen)
 );
 
-TRACE_EVENT(ee_read,
-	TP_PROTO(struct mt76_dev *dev, int offset, u16 val),
-	TP_ARGS(dev, offset, val),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(int, o) __field(u16, v)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		__entry->o = offset;
-		__entry->v = val;
-	),
-	TP_printk(DEV_PR_FMT "%04x=%04x", DEV_PR_ARG, __entry->o, __entry->v)
-);
-
 DECLARE_EVENT_CLASS(dev_rf_reg_evt,
 	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
 	TP_ARGS(dev, bank, reg, val),
@@ -166,44 +151,16 @@ DECLARE_EVENT_CLASS(dev_rf_reg_evt,
 	)
 );
 
-DEFINE_EVENT(dev_rf_reg_evt, rf_read,
+DEFINE_EVENT(dev_rf_reg_evt, mt76x0_rf_read,
 	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
 	TP_ARGS(dev, bank, reg, val)
 );
 
-DEFINE_EVENT(dev_rf_reg_evt, rf_write,
+DEFINE_EVENT(dev_rf_reg_evt, mt76x0_rf_write,
 	TP_PROTO(struct mt76_dev *dev, u8 bank, u8 reg, u8 val),
 	TP_ARGS(dev, bank, reg, val)
 );
 
-DECLARE_EVENT_CLASS(dev_bbp_reg_evt,
-	TP_PROTO(struct mt76_dev *dev, u8 reg, u8 val),
-	TP_ARGS(dev, reg, val),
-	TP_STRUCT__entry(
-		DEV_ENTRY
-		__field(u8, reg)
-		__field(u8, val)
-	),
-	TP_fast_assign(
-		DEV_ASSIGN;
-		REG_ASSIGN;
-	),
-	TP_printk(
-		DEV_PR_FMT "%02hhx=%02hhx",
-		DEV_PR_ARG, __entry->reg, __entry->val
-	)
-);
-
-DEFINE_EVENT(dev_bbp_reg_evt, bbp_read,
-	TP_PROTO(struct mt76_dev *dev, u8 reg, u8 val),
-	TP_ARGS(dev, reg, val)
-);
-
-DEFINE_EVENT(dev_bbp_reg_evt, bbp_write,
-	TP_PROTO(struct mt76_dev *dev, u8 reg, u8 val),
-	TP_ARGS(dev, reg, val)
-);
-
 DECLARE_EVENT_CLASS(dev_simple_evt,
 	TP_PROTO(struct mt76_dev *dev, u8 val),
 	TP_ARGS(dev, val),
@@ -220,17 +177,7 @@ DECLARE_EVENT_CLASS(dev_simple_evt,
 	)
 );
 
-DEFINE_EVENT(dev_simple_evt, temp_mode,
-	TP_PROTO(struct mt76_dev *dev, u8 val),
-	TP_ARGS(dev, val)
-);
-
-DEFINE_EVENT(dev_simple_evt, read_temp,
-	TP_PROTO(struct mt76_dev *dev, u8 val),
-	TP_ARGS(dev, val)
-);
-
-TRACE_EVENT(mt_rx,
+TRACE_EVENT(mt76x0_rx,
 	TP_PROTO(struct mt76_dev *dev, struct mt76x0_rxwi *rxwi, u32 f),
 	TP_ARGS(dev, rxwi, f),
 	TP_STRUCT__entry(
@@ -248,7 +195,7 @@ TRACE_EVENT(mt_rx,
 		  le32_to_cpu(__entry->rxwi.ctl))
 );
 
-TRACE_EVENT(mt_tx,
+TRACE_EVENT(mt76x0_tx,
 	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb,
 		 struct mt76_sta *sta, struct mt76_txwi *h),
 	TP_ARGS(dev, skb, sta, h),
@@ -273,7 +220,7 @@ TRACE_EVENT(mt_tx,
 		  le16_to_cpu(__entry->h.len_ctl))
 );
 
-TRACE_EVENT(mt_tx_dma_done,
+TRACE_EVENT(mt76x0_tx_dma_done,
 	TP_PROTO(struct mt76_dev *dev, struct sk_buff *skb),
 	TP_ARGS(dev, skb),
 	TP_STRUCT__entry(
@@ -287,7 +234,7 @@ TRACE_EVENT(mt_tx_dma_done,
 	TP_printk(DEV_PR_FMT "%p", DEV_PR_ARG, __entry->skb)
 );
 
-TRACE_EVENT(mt_tx_status_cleaned,
+TRACE_EVENT(mt76x0_tx_status_cleaned,
 	TP_PROTO(struct mt76_dev *dev, int cleaned),
 	TP_ARGS(dev, cleaned),
 	TP_STRUCT__entry(
@@ -301,7 +248,7 @@ TRACE_EVENT(mt_tx_status_cleaned,
 	TP_printk(DEV_PR_FMT "%d", DEV_PR_ARG, __entry->cleaned)
 );
 
-TRACE_EVENT(mt_tx_status,
+TRACE_EVENT(mt76x0_tx_status,
 	TP_PROTO(struct mt76_dev *dev, u32 stat1, u32 stat2),
 	TP_ARGS(dev, stat1, stat2),
 	TP_STRUCT__entry(
@@ -317,7 +264,7 @@ TRACE_EVENT(mt_tx_status,
 		  DEV_PR_ARG, __entry->stat1, __entry->stat2)
 );
 
-TRACE_EVENT(mt_rx_dma_aggr,
+TRACE_EVENT(mt76x0_rx_dma_aggr,
 	TP_PROTO(struct mt76_dev *dev, int cnt, bool paged),
 	TP_ARGS(dev, cnt, paged),
 	TP_STRUCT__entry(
@@ -334,12 +281,12 @@ TRACE_EVENT(mt_rx_dma_aggr,
 		  DEV_PR_ARG, __entry->cnt, __entry->paged)
 );
 
-DEFINE_EVENT(dev_simple_evt, set_key,
+DEFINE_EVENT(dev_simple_evt, mt76x0_set_key,
 	TP_PROTO(struct mt76_dev *dev, u8 val),
 	TP_ARGS(dev, val)
 );
 
-TRACE_EVENT(set_shared_key,
+TRACE_EVENT(mt76x0_set_shared_key,
 	TP_PROTO(struct mt76_dev *dev, u8 vid, u8 key),
 	TP_ARGS(dev, vid, key),
 	TP_STRUCT__entry(
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
index 976d3ee91f67..751b49c28ae5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/tx.c
@@ -177,7 +177,7 @@ void mt76x0_tx(struct ieee80211_hw *hw, struct ieee80211_tx_control *control,
 	if (mt76x0_dma_enqueue_tx(dev, skb, wcid, hw_q))
 		return;
 
-	trace_mt_tx(&dev->mt76, skb, msta, txwi);
+	trace_mt76x0_tx(&dev->mt76, skb, msta, txwi);
 }
 
 void mt76x0_tx_stat(struct work_struct *work)
@@ -198,7 +198,7 @@ void mt76x0_tx_stat(struct work_struct *work)
 
 		cleaned++;
 	}
-	trace_mt_tx_status_cleaned(&dev->mt76, cleaned);
+	trace_mt76x0_tx_status_cleaned(&dev->mt76, cleaned);
 
 	spin_lock_irqsave(&dev->tx_lock, flags);
 	if (cleaned)
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 7a635cdcbae0..54ae1f113be2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -84,7 +84,7 @@ int mt76x0_usb_submit_buf(struct mt76x0_dev *dev, int dir, int ep_idx,
 	buf->urb->transfer_dma = buf->dma;
 	buf->urb->transfer_flags |= URB_NO_TRANSFER_DMA_MAP;
 
-	trace_mt_submit_urb(&dev->mt76, buf->urb);
+	trace_mt76x0_submit_urb(&dev->mt76, buf->urb);
 	ret = usb_submit_urb(buf->urb, gfp);
 	if (ret)
 		dev_err(dev->mt76.dev, "Error: submit URB dir:%d ep:%d failed:%d\n",
@@ -113,7 +113,7 @@ int mt76x0_vendor_request(struct mt76x0_dev *dev, const u8 req,
 		ret = usb_control_msg(usb_dev, pipe, req, req_type,
 				      val, offset, buf, buflen,
 				      MT_VEND_REQ_TOUT_MS);
-		trace_mt_vend_req(&dev->mt76, pipe, req, req_type, val, offset,
+		trace_mt76x0_vend_req(&dev->mt76, pipe, req, req_type, val, offset,
 				  buf, buflen, ret);
 
 		if (ret == -ENODEV)
@@ -156,7 +156,7 @@ static u32 mt76x0_rr(struct mt76_dev *dev, u32 offset)
 
 	mutex_unlock(&mdev->usb_ctrl_mtx);
 
-	trace_reg_read(dev, offset, val);
+	trace_mt76x0_reg_read(dev, offset, val);
 	return val;
 }
 
@@ -191,7 +191,7 @@ static void mt76x0_wr(struct mt76_dev *dev, u32 offset, u32 val)
 	put_unaligned_le32(val, mdev->data);
 	ret = mt76x0_vendor_request(mdev, MT_VEND_MULTI_WRITE, USB_DIR_OUT,
 				    0, offset, mdev->data, MT_VEND_BUF);
-	trace_reg_write(dev, offset, val);
+	trace_mt76x0_reg_write(dev, offset, val);
 
 	mutex_unlock(&mdev->usb_ctrl_mtx);
 }
-- 
cgit v1.2.3


From 2f3b94e539a46052f8eba1f295ff5646e227578a Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 15:52:33 -0500
Subject: ALSA: seq: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I replaced the code comment with
a proper "fall through" annotation, which is what GCC is expecting
to find.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_midi_emul.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/core/seq/seq_midi_emul.c b/sound/core/seq/seq_midi_emul.c
index f9f21331aeea..c1975dd31871 100644
--- a/sound/core/seq/seq_midi_emul.c
+++ b/sound/core/seq/seq_midi_emul.c
@@ -318,7 +318,7 @@ do_control(struct snd_midi_op *ops, void *drv, struct snd_midi_channel_set *chse
 		break;
 	case MIDI_CTL_MSB_DATA_ENTRY:
 		chan->control[MIDI_CTL_LSB_DATA_ENTRY] = 0;
-		/* go through here */
+		/* fall through */
 	case MIDI_CTL_LSB_DATA_ENTRY:
 		if (chan->param_type == SNDRV_MIDI_PARAM_TYPE_REGISTERED)
 			rpn(ops, drv, chan, chset);
-- 
cgit v1.2.3


From eb2caeb88c181904110f8e74995c7b0bb7fd39f6 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Fri, 3 Aug 2018 15:53:54 -0500
Subject: ALSA: seq_oss: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Warning level 2 was used: -Wimplicit-fallthrough=2

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/oss/seq_oss_timer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/core/seq/oss/seq_oss_timer.c b/sound/core/seq/oss/seq_oss_timer.c
index 4f24ea9fad93..ba127c22539a 100644
--- a/sound/core/seq/oss/seq_oss_timer.c
+++ b/sound/core/seq/oss/seq_oss_timer.c
@@ -92,7 +92,7 @@ snd_seq_oss_process_timer_event(struct seq_oss_timer *rec, union evrec *ev)
 		case TMR_WAIT_REL:
 			parm += rec->cur_tick;
 			rec->realtime = 0;
-			/* continue to next */
+			/* fall through and continue to next */
 		case TMR_WAIT_ABS:
 			if (parm == 0) {
 				rec->realtime = 1;
-- 
cgit v1.2.3


From 0c26159352ba1cdc5a8c8d74131cc19cdfdf9371 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Fri, 3 Aug 2018 22:06:00 -0700
Subject: nfp: bpf: xdp_adjust_tail support

Add support for adjust_tail.  There are no FW changes needed but add
a FW capability just in case there would be any issue with previously
released FW, or we will have to change the ABI in the future.

The helper is trivial and shouldn't be used too often so just inline
the body of the function.  We add the delta to locally maintained
packet length register and check for overflow, since add of negative
value must overflow if result is positive.  Note that if delta of 0
would be allowed in the kernel this trick stops working and we need
one more instruction to compare lengths before and after the change.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/ethernet/netronome/nfp/bpf/fw.h       |  1 +
 drivers/net/ethernet/netronome/nfp/bpf/jit.c      | 47 +++++++++++++++++++++++
 drivers/net/ethernet/netronome/nfp/bpf/main.c     | 13 +++++++
 drivers/net/ethernet/netronome/nfp/bpf/main.h     |  2 +
 drivers/net/ethernet/netronome/nfp/bpf/verifier.c |  7 ++++
 drivers/net/ethernet/netronome/nfp/nfp_asm.h      |  1 +
 6 files changed, 71 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
index 4c7972e3db63..e4f9b7ec8528 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h
@@ -51,6 +51,7 @@ enum bpf_cap_tlv_type {
 	NFP_BPF_CAP_TYPE_MAPS		= 3,
 	NFP_BPF_CAP_TYPE_RANDOM		= 4,
 	NFP_BPF_CAP_TYPE_QUEUE_SELECT	= 5,
+	NFP_BPF_CAP_TYPE_ADJUST_TAIL	= 6,
 };
 
 struct nfp_bpf_cap_tlv_func {
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
index 3c22d27de9da..eff57f7d056a 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c
@@ -1642,6 +1642,51 @@ static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	return 0;
 }
 
+static int adjust_tail(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
+{
+	u32 ret_einval, end;
+	swreg plen, delta;
+
+	BUILD_BUG_ON(plen_reg(nfp_prog) != reg_b(STATIC_REG_PKT_LEN));
+
+	plen = imm_a(nfp_prog);
+	delta = reg_a(2 * 2);
+
+	ret_einval = nfp_prog_current_offset(nfp_prog) + 9;
+	end = nfp_prog_current_offset(nfp_prog) + 11;
+
+	/* Calculate resulting length */
+	emit_alu(nfp_prog, plen, plen_reg(nfp_prog), ALU_OP_ADD, delta);
+	/* delta == 0 is not allowed by the kernel, add must overflow to make
+	 * length smaller.
+	 */
+	emit_br(nfp_prog, BR_BCC, ret_einval, 0);
+
+	/* if (new_len < 14) then -EINVAL */
+	emit_alu(nfp_prog, reg_none(), plen, ALU_OP_SUB, reg_imm(ETH_HLEN));
+	emit_br(nfp_prog, BR_BMI, ret_einval, 0);
+
+	emit_alu(nfp_prog, plen_reg(nfp_prog),
+		 plen_reg(nfp_prog), ALU_OP_ADD, delta);
+	emit_alu(nfp_prog, pv_len(nfp_prog),
+		 pv_len(nfp_prog), ALU_OP_ADD, delta);
+
+	emit_br(nfp_prog, BR_UNC, end, 2);
+	wrp_immed(nfp_prog, reg_both(0), 0);
+	wrp_immed(nfp_prog, reg_both(1), 0);
+
+	if (!nfp_prog_confirm_current_offset(nfp_prog, ret_einval))
+		return -EINVAL;
+
+	wrp_immed(nfp_prog, reg_both(0), -22);
+	wrp_immed(nfp_prog, reg_both(1), ~0);
+
+	if (!nfp_prog_confirm_current_offset(nfp_prog, end))
+		return -EINVAL;
+
+	return 0;
+}
+
 static int
 map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 {
@@ -3041,6 +3086,8 @@ static int call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta)
 	switch (meta->insn.imm) {
 	case BPF_FUNC_xdp_adjust_head:
 		return adjust_head(nfp_prog, meta);
+	case BPF_FUNC_xdp_adjust_tail:
+		return adjust_tail(nfp_prog, meta);
 	case BPF_FUNC_map_lookup_elem:
 	case BPF_FUNC_map_update_elem:
 	case BPF_FUNC_map_delete_elem:
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c
index cce1d2945a32..970af07f4656 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c
@@ -334,6 +334,14 @@ nfp_bpf_parse_cap_qsel(struct nfp_app_bpf *bpf, void __iomem *value, u32 length)
 	return 0;
 }
 
+static int
+nfp_bpf_parse_cap_adjust_tail(struct nfp_app_bpf *bpf, void __iomem *value,
+			      u32 length)
+{
+	bpf->adjust_tail = true;
+	return 0;
+}
+
 static int nfp_bpf_parse_capabilities(struct nfp_app *app)
 {
 	struct nfp_cpp *cpp = app->pf->cpp;
@@ -380,6 +388,11 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app)
 			if (nfp_bpf_parse_cap_qsel(app->priv, value, length))
 				goto err_release_free;
 			break;
+		case NFP_BPF_CAP_TYPE_ADJUST_TAIL:
+			if (nfp_bpf_parse_cap_adjust_tail(app->priv, value,
+							  length))
+				goto err_release_free;
+			break;
 		default:
 			nfp_dbg(cpp, "unknown BPF capability: %d\n", type);
 			break;
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h
index 57573bfa8c03..dbd00982fd2b 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/main.h
+++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h
@@ -150,6 +150,7 @@ enum pkt_vec {
  *
  * @pseudo_random:	FW initialized the pseudo-random machinery (CSRs)
  * @queue_select:	BPF can set the RX queue ID in packet vector
+ * @adjust_tail:	BPF can simply trunc packet size for adjust tail
  */
 struct nfp_app_bpf {
 	struct nfp_app *app;
@@ -195,6 +196,7 @@ struct nfp_app_bpf {
 
 	bool pseudo_random;
 	bool queue_select;
+	bool adjust_tail;
 };
 
 enum nfp_bpf_map_use {
diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
index 49ba0d645d36..a6e9248669e1 100644
--- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
+++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c
@@ -178,6 +178,13 @@ nfp_bpf_check_call(struct nfp_prog *nfp_prog, struct bpf_verifier_env *env,
 		nfp_record_adjust_head(bpf, nfp_prog, meta, reg2);
 		break;
 
+	case BPF_FUNC_xdp_adjust_tail:
+		if (!bpf->adjust_tail) {
+			pr_vlog(env, "adjust_tail not supported by FW\n");
+			return -EOPNOTSUPP;
+		}
+		break;
+
 	case BPF_FUNC_map_lookup_elem:
 		if (!nfp_bpf_map_call_ok("map_lookup", env, meta,
 					 bpf->helpers.map_lookup, reg1) ||
diff --git a/drivers/net/ethernet/netronome/nfp/nfp_asm.h b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
index cdc4e065f6f5..fad0e62a910c 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_asm.h
+++ b/drivers/net/ethernet/netronome/nfp/nfp_asm.h
@@ -93,6 +93,7 @@ enum br_mask {
 	BR_BNE = 0x01,
 	BR_BMI = 0x02,
 	BR_BHS = 0x04,
+	BR_BCC = 0x05,
 	BR_BLO = 0x05,
 	BR_BGE = 0x08,
 	BR_BLT = 0x09,
-- 
cgit v1.2.3


From 07d53ae4fbdf7458f4d51249aa24d75c76fe52a8 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Sat, 4 Aug 2018 19:41:41 +0800
Subject: net: Remove some unneeded semicolon

These semicolons are not needed.  Just remove them.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/utils.c               | 2 +-
 net/netfilter/ipvs/ip_vs_ctl.c | 2 +-
 net/packet/af_packet.c         | 4 ++--
 net/sunrpc/auth_gss/auth_gss.c | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/utils.c b/net/core/utils.c
index d47863b07a60..2a597ac7808e 100644
--- a/net/core/utils.c
+++ b/net/core/utils.c
@@ -397,7 +397,7 @@ int inet_pton_with_scope(struct net *net, __kernel_sa_family_t af,
 		break;
 	default:
 		pr_err("unexpected address family %d\n", af);
-	};
+	}
 
 	return ret;
 }
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index dd21782e2f12..62eefea48973 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -134,7 +134,7 @@ static void update_defense_level(struct netns_ipvs *ipvs)
 		} else {
 			atomic_set(&ipvs->dropentry, 0);
 			ipvs->sysctl_drop_entry = 1;
-		};
+		}
 		break;
 	case 3:
 		atomic_set(&ipvs->dropentry, 1);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index e3e00d3a972e..345e38058ae5 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -1582,7 +1582,7 @@ static int fanout_set_data(struct packet_sock *po, char __user *data,
 		return fanout_set_data_ebpf(po, data, len);
 	default:
 		return -EINVAL;
-	};
+	}
 }
 
 static void fanout_release_data(struct packet_fanout *f)
@@ -1591,7 +1591,7 @@ static void fanout_release_data(struct packet_fanout *f)
 	case PACKET_FANOUT_CBPF:
 	case PACKET_FANOUT_EBPF:
 		__fanout_set_data_bpf(f, NULL);
-	};
+	}
 }
 
 static bool __fanout_id_is_free(struct sock *sk, u16 candidate_id)
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index be8f103d22fd..0fc397fae42b 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -517,7 +517,7 @@ gss_alloc_msg(struct gss_auth *gss_auth,
 		err = gss_encode_v1_msg(gss_msg, service_name, gss_auth->target_name);
 		if (err)
 			goto err_put_pipe_version;
-	};
+	}
 	kref_get(&gss_auth->kref);
 	return gss_msg;
 err_put_pipe_version:
-- 
cgit v1.2.3


From 039b1d5e5862375b0da534bb75fc580eaa547d53 Mon Sep 17 00:00:00 2001
From: Jia-Ju Bai <baijiaju1990@gmail.com>
Date: Sat, 4 Aug 2018 08:40:09 +0800
Subject: net: cisco: enic: Replace GFP_ATOMIC with GFP_KERNEL

vnic_dev_register(), vnic_rq_alloc_bufs() and vnic_wq_alloc_bufs()
are never called in atomic context.
They call kzalloc() with GFP_ATOMIC, which is not necessary.
GFP_ATOMIC can be replaced with GFP_KERNEL.

This is found by a static analysis tool named DCNS written by myself.

Signed-off-by: Jia-Ju Bai <baijiaju1990@gmail.com>
Acked-by: Govindarajulu Varadarajan <gvaradar@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cisco/enic/vnic_dev.c | 2 +-
 drivers/net/ethernet/cisco/enic/vnic_rq.c  | 2 +-
 drivers/net/ethernet/cisco/enic/vnic_wq.c  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/vnic_dev.c b/drivers/net/ethernet/cisco/enic/vnic_dev.c
index e9db811df59c..901e44b0b795 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_dev.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_dev.c
@@ -1071,7 +1071,7 @@ struct vnic_dev *vnic_dev_register(struct vnic_dev *vdev,
 	unsigned int num_bars)
 {
 	if (!vdev) {
-		vdev = kzalloc(sizeof(struct vnic_dev), GFP_ATOMIC);
+		vdev = kzalloc(sizeof(struct vnic_dev), GFP_KERNEL);
 		if (!vdev)
 			return NULL;
 	}
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.c b/drivers/net/ethernet/cisco/enic/vnic_rq.c
index f8aa326d1d58..a3e7b003ada1 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.c
@@ -35,7 +35,7 @@ static int vnic_rq_alloc_bufs(struct vnic_rq *rq)
 	unsigned int blks = VNIC_RQ_BUF_BLKS_NEEDED(count);
 
 	for (i = 0; i < blks; i++) {
-		rq->bufs[i] = kzalloc(VNIC_RQ_BUF_BLK_SZ(count), GFP_ATOMIC);
+		rq->bufs[i] = kzalloc(VNIC_RQ_BUF_BLK_SZ(count), GFP_KERNEL);
 		if (!rq->bufs[i])
 			return -ENOMEM;
 	}
diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.c b/drivers/net/ethernet/cisco/enic/vnic_wq.c
index 090cc65658a3..eb75891974df 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_wq.c
+++ b/drivers/net/ethernet/cisco/enic/vnic_wq.c
@@ -35,7 +35,7 @@ static int vnic_wq_alloc_bufs(struct vnic_wq *wq)
 	unsigned int blks = VNIC_WQ_BUF_BLKS_NEEDED(count);
 
 	for (i = 0; i < blks; i++) {
-		wq->bufs[i] = kzalloc(VNIC_WQ_BUF_BLK_SZ(count), GFP_ATOMIC);
+		wq->bufs[i] = kzalloc(VNIC_WQ_BUF_BLK_SZ(count), GFP_KERNEL);
 		if (!wq->bufs[i])
 			return -ENOMEM;
 	}
-- 
cgit v1.2.3


From f13b546847ff5862ea313f3e79010c52c3fe32b4 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 3 Aug 2018 15:50:02 +0800
Subject: tun: not use hardcoded mask value

0x3ff in tun_hashfn is mask of TUN_NUM_FLOW_ENTRIES, instead
of hardcode, define a macro to setup the relationship with
TUN_NUM_FLOW_ENTRIES

Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/tun.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0a3134712652..2bbefe828670 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -200,6 +200,7 @@ struct tun_flow_entry {
 };
 
 #define TUN_NUM_FLOW_ENTRIES 1024
+#define TUN_MASK_FLOW_ENTRIES (TUN_NUM_FLOW_ENTRIES - 1)
 
 struct tun_prog {
 	struct rcu_head rcu;
@@ -406,7 +407,7 @@ static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
 
 static inline u32 tun_hashfn(u32 rxhash)
 {
-	return rxhash & 0x3ff;
+	return rxhash & TUN_MASK_FLOW_ENTRIES;
 }
 
 static struct tun_flow_entry *tun_flow_find(struct hlist_head *head, u32 rxhash)
-- 
cgit v1.2.3


From bf37afceaf549ce9ef50e3042f64d257a3d4be80 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Fri, 3 Aug 2018 14:53:14 +0800
Subject: net:usb: Use ARRAY_SIZE instead of calculating the array size

We use ARRAY_SIZE to replace open code sizeof(lan78xx_regs) / sizeof(u32).
It make the code concise.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/lan78xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 4662fa0381f9..a9991c5f4736 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1649,7 +1649,7 @@ lan78xx_get_regs(struct net_device *netdev, struct ethtool_regs *regs,
 	struct lan78xx_net *dev = netdev_priv(netdev);
 
 	/* Read Device/MAC registers */
-	for (i = 0; i < (sizeof(lan78xx_regs) / sizeof(u32)); i++)
+	for (i = 0; i < ARRAY_SIZE(lan78xx_regs); i++)
 		lan78xx_read_reg(dev, lan78xx_regs[i], &data[i]);
 
 	if (!netdev->phydev)
-- 
cgit v1.2.3


From 31ba191bf5ab2975c1955f1adf771a5a0b57afaa Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Fri, 3 Aug 2018 14:53:15 +0800
Subject: include/net/bond_3ad: Simplify the code by using the ARRAY_SIZE

We prefer to ARRAY_SIZE rather than the open code to calculate size.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/bond_3ad.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/bond_3ad.h b/include/net/bond_3ad.h
index f358ad5e4214..fc3111515f5c 100644
--- a/include/net/bond_3ad.h
+++ b/include/net/bond_3ad.h
@@ -283,7 +283,7 @@ static inline const char *bond_3ad_churn_desc(churn_state_t state)
 		"none",
 		"unknown"
 	};
-	int max_size = sizeof(churn_description) / sizeof(churn_description[0]);
+	int max_size = ARRAY_SIZE(churn_description);
 
 	if (state >= max_size)
 		state = max_size - 1;
-- 
cgit v1.2.3


From 6c3711ec64fd23a9abc8aaf59a9429569a6282df Mon Sep 17 00:00:00 2001
From: Johan Hedberg <johan.hedberg@intel.com>
Date: Sat, 4 Aug 2018 23:40:26 +0300
Subject: Bluetooth: h5: Fix missing dependency on BT_HCIUART_SERDEV
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This driver was recently updated to use serdev, so add the appropriate
dependency. Without this one can get compiler warnings like this if
CONFIG_SERIAL_DEV_BUS is not enabled:

  CC [M]  drivers/bluetooth/hci_h5.o
drivers/bluetooth/hci_h5.c:934:36: warning: ‘h5_serdev_driver’ defined but not used [-Wunused-variable]
 static struct serdev_device_driver h5_serdev_driver = {
                                    ^~~~~~~~~~~~~~~~

Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index f3c643a0473c..5f953ca8ac5b 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -159,6 +159,7 @@ config BT_HCIUART_LL
 config BT_HCIUART_3WIRE
 	bool "Three-wire UART (H5) protocol support"
 	depends on BT_HCIUART
+	depends on BT_HCIUART_SERDEV
 	help
 	  The HCI Three-wire UART Transport Layer makes it possible to
 	  user the Bluetooth HCI over a serial port interface. The HCI
-- 
cgit v1.2.3


From 863c37fcb14f8b66ea831b45fb35a53ac4a8d69e Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Sat, 4 Aug 2018 17:34:07 -0400
Subject: ext4: remove unneeded variable "err" in ext4_mb_release_inode_pa()

The err is not used after initalization. So just remove the variable.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Theodore Ts'o <tytso@mit.edu>
---
 fs/ext4/mballoc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 8b24d3d42cb3..e29fce2fbf25 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -3801,7 +3801,6 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	ext4_group_t group;
 	ext4_grpblk_t bit;
 	unsigned long long grp_blk_start;
-	int err = 0;
 	int free = 0;
 
 	BUG_ON(pa->pa_deleted == 0);
@@ -3842,7 +3841,7 @@ ext4_mb_release_inode_pa(struct ext4_buddy *e4b, struct buffer_head *bitmap_bh,
 	}
 	atomic_add(free, &sbi->s_mb_discarded);
 
-	return err;
+	return 0;
 }
 
 static noinline_for_stack int
-- 
cgit v1.2.3


From d89d41556141a527030a15233135ba622ba3350d Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Sat, 4 Aug 2018 14:20:40 -0700
Subject: ethtool: Remove trailing semicolon for static inline

Android's header sanitization tool chokes on static inline functions having a
trailing semicolon, leading to an incorrectly parsed header file. While the
tool should obviously be fixed, also fix the header files for the two affected
functions: ethtool_get_flow_spec_ring() and ethtool_get_flow_spec_ring_vf().

Fixes: 8cf6f497de40 ("ethtool: Add helper routines to pass vf to rx_flow_spec")
Reporetd-by: Blair Prescott <blair.prescott@broadcom.com>
Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 7363f18e65a5..813282cc8af6 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -902,13 +902,13 @@ struct ethtool_rx_flow_spec {
 static inline __u64 ethtool_get_flow_spec_ring(__u64 ring_cookie)
 {
 	return ETHTOOL_RX_FLOW_SPEC_RING & ring_cookie;
-};
+}
 
 static inline __u64 ethtool_get_flow_spec_ring_vf(__u64 ring_cookie)
 {
 	return (ETHTOOL_RX_FLOW_SPEC_RING_VF & ring_cookie) >>
 				ETHTOOL_RX_FLOW_SPEC_RING_VF_OFF;
-};
+}
 
 /**
  * struct ethtool_rxnfc - command to get or set RX flow classification rules
-- 
cgit v1.2.3


From 379fd0c7e6a391e5565336a646f19f218fb98c6c Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Sat, 21 Jul 2018 22:16:56 +0200
Subject: x86/KVM/VMX: Don't set l1tf_flush_l1d to true from vmx_l1d_flush()

vmx_l1d_flush() gets invoked only if l1tf_flush_l1d is true. There's no
point in setting l1tf_flush_l1d to true from there again.

Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b4b8e8cb4a7e..695e161ffb36 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9691,15 +9691,15 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	/*
 	 * This code is only executed when the the flush mode is 'cond' or
 	 * 'always'
-	 *
-	 * If 'flush always', keep the flush bit set, otherwise clear
-	 * it. The flush bit gets set again either from vcpu_run() or from
-	 * one of the unsafe VMEXIT handlers.
 	 */
-	if (static_branch_unlikely(&vmx_l1d_flush_always))
-		vcpu->arch.l1tf_flush_l1d = true;
-	else
+	if (!static_branch_unlikely(&vmx_l1d_flush_always)) {
+		/*
+		 * Clear the flush bit, it gets set again either from
+		 * vcpu_run() or from one of the unsafe VMEXIT
+		 * handlers.
+		 */
 		vcpu->arch.l1tf_flush_l1d = false;
+	}
 
 	vcpu->stat.l1d_flush++;
 
-- 
cgit v1.2.3


From 427362a142441f08051369db6fbe7f61c73b3dca Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Sat, 21 Jul 2018 22:25:00 +0200
Subject: x86/KVM/VMX: Replace 'vmx_l1d_flush_always' with 'vmx_l1d_flush_cond'

The vmx_l1d_flush_always static key is only ever evaluated if
vmx_l1d_should_flush is enabled. In that case however, there are only two
L1d flushing modes possible: "always" and "conditional".

The "conditional" mode's implementation tends to require more sophisticated
logic than the "always" mode.

Avoid inverted logic by replacing the 'vmx_l1d_flush_always' static key
with a 'vmx_l1d_flush_cond' one.

There is no change in functionality.

Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 695e161ffb36..5139738cc5a9 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -189,7 +189,7 @@ module_param(ple_window_max, uint, 0444);
 extern const ulong vmx_return;
 
 static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush);
-static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_always);
+static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond);
 static DEFINE_MUTEX(vmx_l1d_flush_mutex);
 
 /* Storage for pre module init parameter parsing */
@@ -263,10 +263,10 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 	else
 		static_branch_disable(&vmx_l1d_should_flush);
 
-	if (l1tf == VMENTER_L1D_FLUSH_ALWAYS)
-		static_branch_enable(&vmx_l1d_flush_always);
+	if (l1tf == VMENTER_L1D_FLUSH_COND)
+		static_branch_enable(&vmx_l1d_flush_cond);
 	else
-		static_branch_disable(&vmx_l1d_flush_always);
+		static_branch_disable(&vmx_l1d_flush_cond);
 	return 0;
 }
 
@@ -9692,7 +9692,7 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	 * This code is only executed when the the flush mode is 'cond' or
 	 * 'always'
 	 */
-	if (!static_branch_unlikely(&vmx_l1d_flush_always)) {
+	if (static_branch_likely(&vmx_l1d_flush_cond)) {
 		/*
 		 * Clear the flush bit, it gets set again either from
 		 * vcpu_run() or from one of the unsafe VMEXIT
-- 
cgit v1.2.3


From 5b6ccc6c3b1a477fbac9ec97a0b4c1c48e765209 Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Sat, 21 Jul 2018 22:35:28 +0200
Subject: x86/KVM/VMX: Move the l1tf_flush_l1d test to vmx_l1d_flush()

Currently, vmx_vcpu_run() checks if l1tf_flush_l1d is set and invokes
vmx_l1d_flush() if so.

This test is unncessary for the "always flush L1D" mode.

Move the check to vmx_l1d_flush()'s conditional mode code path.

Notes:
- vmx_l1d_flush() is likely to get inlined anyway and thus, there's no
  extra function call.

- This inverts the (static) branch prediction, but there hadn't been any
  explicit likely()/unlikely() annotations before and so it stays as is.

Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 5139738cc5a9..ec955b870756 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9693,12 +9693,16 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	 * 'always'
 	 */
 	if (static_branch_likely(&vmx_l1d_flush_cond)) {
+		bool flush_l1d = vcpu->arch.l1tf_flush_l1d;
+
 		/*
 		 * Clear the flush bit, it gets set again either from
 		 * vcpu_run() or from one of the unsafe VMEXIT
 		 * handlers.
 		 */
 		vcpu->arch.l1tf_flush_l1d = false;
+		if (!flush_l1d)
+			return;
 	}
 
 	vcpu->stat.l1d_flush++;
@@ -10228,10 +10232,8 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
 	evmcs_rsp = static_branch_unlikely(&enable_evmcs) ?
 		(unsigned long)&current_evmcs->host_rsp : 0;
 
-	if (static_branch_unlikely(&vmx_l1d_should_flush)) {
-		if (vcpu->arch.l1tf_flush_l1d)
-			vmx_l1d_flush(vcpu);
-	}
+	if (static_branch_unlikely(&vmx_l1d_should_flush))
+		vmx_l1d_flush(vcpu);
 
 	asm(
 		/* Store host registers */
-- 
cgit v1.2.3


From 9aee5f8a7e30330d0a8f4c626dc924ca5590aba5 Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Fri, 27 Jul 2018 12:46:29 +0200
Subject: x86/irq: Demote irq_cpustat_t::__softirq_pending to u16

An upcoming patch will extend KVM's L1TF mitigation in conditional mode
to also cover interrupts after VMEXITs. For tracking those, stores to a
new per-cpu flag from interrupt handlers will become necessary.

In order to improve cache locality, this new flag will be added to x86's
irq_cpustat_t.

Make some space available there by shrinking the ->softirq_pending bitfield
from 32 to 16 bits: the number of bits actually used is only NR_SOFTIRQS,
i.e. 10.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/hardirq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 740a428acf1e..e39c606de6f6 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -6,7 +6,7 @@
 #include <linux/irq.h>
 
 typedef struct {
-	unsigned int __softirq_pending;
+	u16	     __softirq_pending;
 	unsigned int __nmi_count;	/* arch dependent */
 #ifdef CONFIG_X86_LOCAL_APIC
 	unsigned int apic_timer_irqs;	/* arch dependent */
-- 
cgit v1.2.3


From 45b575c00d8e72d69d75dd8c112f044b7b01b069 Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Fri, 27 Jul 2018 13:22:16 +0200
Subject: x86/KVM/VMX: Introduce per-host-cpu analogue of l1tf_flush_l1d

Part of the L1TF mitigation for vmx includes flushing the L1D cache upon
VMENTRY.

L1D flushes are costly and two modes of operations are provided to users:
"always" and the more selective "conditional" mode.

If operating in the latter, the cache would get flushed only if a host side
code path considered unconfined had been traversed. "Unconfined" in this
context means that it might have pulled in sensitive data like user data
or kernel crypto keys.

The need for L1D flushes is tracked by means of the per-vcpu flag
l1tf_flush_l1d. KVM exit handlers considered unconfined set it. A
vmx_l1d_flush() subsequently invoked before the next VMENTER will conduct a
L1d flush based on its value and reset that flag again.

Currently, interrupts delivered "normally" while in root operation between
VMEXIT and VMENTER are not taken into account. Part of the reason is that
these don't leave any traces and thus, the vmx code is unable to tell if
any such has happened.

As proposed by Paolo Bonzini, prepare for tracking all interrupts by
introducing a new per-cpu flag, "kvm_cpu_l1tf_flush_l1d". It will be in
strong analogy to the per-vcpu ->l1tf_flush_l1d.

A later patch will make interrupt handlers set it.

For the sake of cache locality, group kvm_cpu_l1tf_flush_l1d into x86'
per-cpu irq_cpustat_t as suggested by Peter Zijlstra.

Provide the helpers kvm_set_cpu_l1tf_flush_l1d(),
kvm_clear_cpu_l1tf_flush_l1d() and kvm_get_cpu_l1tf_flush_l1d(). Make them
trivial resp. non-existent for !CONFIG_KVM_INTEL as appropriate.

Let vmx_l1d_flush() handle kvm_cpu_l1tf_flush_l1d in the same way as
l1tf_flush_l1d.

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/include/asm/hardirq.h | 23 +++++++++++++++++++++++
 arch/x86/kvm/vmx.c             | 17 +++++++++++++----
 2 files changed, 36 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index e39c606de6f6..0b854ebb99df 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -7,6 +7,9 @@
 
 typedef struct {
 	u16	     __softirq_pending;
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+	u8	     kvm_cpu_l1tf_flush_l1d;
+#endif
 	unsigned int __nmi_count;	/* arch dependent */
 #ifdef CONFIG_X86_LOCAL_APIC
 	unsigned int apic_timer_irqs;	/* arch dependent */
@@ -58,4 +61,24 @@ extern u64 arch_irq_stat_cpu(unsigned int cpu);
 extern u64 arch_irq_stat(void);
 #define arch_irq_stat		arch_irq_stat
 
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+static inline void kvm_set_cpu_l1tf_flush_l1d(void)
+{
+	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1);
+}
+
+static inline void kvm_clear_cpu_l1tf_flush_l1d(void)
+{
+	__this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 0);
+}
+
+static inline bool kvm_get_cpu_l1tf_flush_l1d(void)
+{
+	return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d);
+}
+#else /* !IS_ENABLED(CONFIG_KVM_INTEL) */
+static inline void kvm_set_cpu_l1tf_flush_l1d(void) { }
+#endif /* IS_ENABLED(CONFIG_KVM_INTEL) */
+
 #endif /* _ASM_X86_HARDIRQ_H */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ec955b870756..33892ddd229f 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9693,14 +9693,23 @@ static void vmx_l1d_flush(struct kvm_vcpu *vcpu)
 	 * 'always'
 	 */
 	if (static_branch_likely(&vmx_l1d_flush_cond)) {
-		bool flush_l1d = vcpu->arch.l1tf_flush_l1d;
+		bool flush_l1d;
 
 		/*
-		 * Clear the flush bit, it gets set again either from
-		 * vcpu_run() or from one of the unsafe VMEXIT
-		 * handlers.
+		 * Clear the per-vcpu flush bit, it gets set again
+		 * either from vcpu_run() or from one of the unsafe
+		 * VMEXIT handlers.
 		 */
+		flush_l1d = vcpu->arch.l1tf_flush_l1d;
 		vcpu->arch.l1tf_flush_l1d = false;
+
+		/*
+		 * Clear the per-cpu flush bit, it gets set again from
+		 * the interrupt handlers.
+		 */
+		flush_l1d |= kvm_get_cpu_l1tf_flush_l1d();
+		kvm_clear_cpu_l1tf_flush_l1d();
+
 		if (!flush_l1d)
 			return;
 	}
-- 
cgit v1.2.3


From 447ae316670230d7d29430e2cbf1f5db4f49d14c Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Sun, 29 Jul 2018 12:15:33 +0200
Subject: x86: Don't include linux/irq.h from asm/hardirq.h

The next patch in this series will have to make the definition of
irq_cpustat_t available to entering_irq().

Inclusion of asm/hardirq.h into asm/apic.h would cause circular header
dependencies like

  asm/smp.h
    asm/apic.h
      asm/hardirq.h
        linux/irq.h
          linux/topology.h
            linux/smp.h
              asm/smp.h

or

  linux/gfp.h
    linux/mmzone.h
      asm/mmzone.h
        asm/mmzone_64.h
          asm/smp.h
            asm/apic.h
              asm/hardirq.h
                linux/irq.h
                  linux/irqdesc.h
                    linux/kobject.h
                      linux/sysfs.h
                        linux/kernfs.h
                          linux/idr.h
                            linux/gfp.h

and others.

This causes compilation errors because of the header guards becoming
effective in the second inclusion: symbols/macros that had been defined
before wouldn't be available to intermediate headers in the #include chain
anymore.

A possible workaround would be to move the definition of irq_cpustat_t
into its own header and include that from both, asm/hardirq.h and
asm/apic.h.

However, this wouldn't solve the real problem, namely asm/harirq.h
unnecessarily pulling in all the linux/irq.h cruft: nothing in
asm/hardirq.h itself requires it. Also, note that there are some other
archs, like e.g. arm64, which don't have that #include in their
asm/hardirq.h.

Remove the linux/irq.h #include from x86' asm/hardirq.h.

Fix resulting compilation errors by adding appropriate #includes to *.c
files as needed.

Note that some of these *.c files could be cleaned up a bit wrt. to their
set of #includes, but that should better be done from separate patches, if
at all.

Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/dmi.h                                   | 2 +-
 arch/x86/include/asm/hardirq.h                               | 1 -
 arch/x86/include/asm/kvm_host.h                              | 1 +
 arch/x86/kernel/apic/apic.c                                  | 1 +
 arch/x86/kernel/apic/io_apic.c                               | 1 +
 arch/x86/kernel/apic/msi.c                                   | 1 +
 arch/x86/kernel/apic/vector.c                                | 1 +
 arch/x86/kernel/fpu/core.c                                   | 1 +
 arch/x86/kernel/hpet.c                                       | 1 +
 arch/x86/kernel/i8259.c                                      | 1 +
 arch/x86/kernel/idt.c                                        | 1 +
 arch/x86/kernel/irq.c                                        | 1 +
 arch/x86/kernel/irq_32.c                                     | 1 +
 arch/x86/kernel/irq_64.c                                     | 1 +
 arch/x86/kernel/irqinit.c                                    | 1 +
 arch/x86/kernel/smpboot.c                                    | 1 +
 arch/x86/kernel/time.c                                       | 1 +
 arch/x86/mm/pti.c                                            | 1 +
 arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c | 1 +
 arch/x86/xen/enlighten.c                                     | 1 +
 drivers/gpu/drm/i915/i915_pmu.c                              | 1 +
 drivers/gpu/drm/i915/intel_lpe_audio.c                       | 1 +
 drivers/pci/controller/pci-hyperv.c                          | 1 +
 23 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/dmi.h b/arch/x86/include/asm/dmi.h
index 0ab2ab27ad1f..b825cb201251 100644
--- a/arch/x86/include/asm/dmi.h
+++ b/arch/x86/include/asm/dmi.h
@@ -4,8 +4,8 @@
 
 #include <linux/compiler.h>
 #include <linux/init.h>
+#include <linux/io.h>
 
-#include <asm/io.h>
 #include <asm/setup.h>
 
 static __always_inline __init void *dmi_alloc(unsigned len)
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 0b854ebb99df..d9069bb26c7f 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -3,7 +3,6 @@
 #define _ASM_X86_HARDIRQ_H
 
 #include <linux/threads.h>
-#include <linux/irq.h>
 
 typedef struct {
 	u16	     __softirq_pending;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 57d418061c55..37749429afd9 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -17,6 +17,7 @@
 #include <linux/tracepoint.h>
 #include <linux/cpumask.h>
 #include <linux/irq_work.h>
+#include <linux/irq.h>
 
 #include <linux/kvm.h>
 #include <linux/kvm_para.h>
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 8703caa9d6db..f93a21b01072 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -56,6 +56,7 @@
 #include <asm/hypervisor.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
+#include <asm/irq_regs.h>
 
 unsigned int num_processors;
 
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 3982f79d2377..ff0d14cd9e82 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -33,6 +33,7 @@
 
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/init.h>
 #include <linux/delay.h>
 #include <linux/sched.h>
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index ce503c99f5c4..72a94401f9e0 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -12,6 +12,7 @@
  */
 #include <linux/mm.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/dmar.h>
 #include <linux/hpet.h>
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 35aaee4fc028..c9b773401fd8 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -11,6 +11,7 @@
  * published by the Free Software Foundation.
  */
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/init.h>
 #include <linux/compiler.h>
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index f92a6593de1e..2ea85b32421a 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -10,6 +10,7 @@
 #include <asm/fpu/signal.h>
 #include <asm/fpu/types.h>
 #include <asm/traps.h>
+#include <asm/irq_regs.h>
 
 #include <linux/hardirq.h>
 #include <linux/pkeys.h>
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 346b24883911..b0acb22e5a46 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -1,6 +1,7 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/errno.h>
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index 86c4439f9d74..519649ddf100 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/random.h>
 #include <linux/init.h>
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index 74383a3780dc..01adea278a71 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -8,6 +8,7 @@
 #include <asm/traps.h>
 #include <asm/proto.h>
 #include <asm/desc.h>
+#include <asm/hw_irq.h>
 
 struct idt_data {
 	unsigned int	vector;
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 328d027d829d..59b5f2ea7c2f 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -10,6 +10,7 @@
 #include <linux/ftrace.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/irq.h>
 
 #include <asm/apic.h>
 #include <asm/io_apic.h>
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c1bdbd3d3232..95600a99ae93 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -11,6 +11,7 @@
 
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel_stat.h>
 #include <linux/notifier.h>
 #include <linux/cpu.h>
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index d86e344f5b3d..0469cd078db1 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -11,6 +11,7 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/seq_file.h>
 #include <linux/delay.h>
 #include <linux/ftrace.h>
diff --git a/arch/x86/kernel/irqinit.c b/arch/x86/kernel/irqinit.c
index 772196c1b8c4..a0693b71cfc1 100644
--- a/arch/x86/kernel/irqinit.c
+++ b/arch/x86/kernel/irqinit.c
@@ -5,6 +5,7 @@
 #include <linux/sched.h>
 #include <linux/ioport.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/timex.h>
 #include <linux/random.h>
 #include <linux/kprobes.h>
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 7f7def989fb0..f5d30c68fd09 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -80,6 +80,7 @@
 #include <asm/intel-family.h>
 #include <asm/cpu_device_id.h>
 #include <asm/spec-ctrl.h>
+#include <asm/hw_irq.h>
 
 /* representing HT siblings of each logical CPU */
 DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map);
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 774ebafa97c4..be01328eb755 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -12,6 +12,7 @@
 
 #include <linux/clockchips.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/i8253.h>
 #include <linux/time.h>
 #include <linux/export.h>
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 4d418e705878..fb752d9a3ce9 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -45,6 +45,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/desc.h>
+#include <asm/sections.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)     "Kernel/User page tables isolation: " fmt
diff --git a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
index 4f5fa65a1011..2acd6be13375 100644
--- a/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
+++ b/arch/x86/platform/intel-mid/device_libs/platform_mrfld_wdt.c
@@ -18,6 +18,7 @@
 #include <asm/intel-mid.h>
 #include <asm/intel_scu_ipc.h>
 #include <asm/io_apic.h>
+#include <asm/hw_irq.h>
 
 #define TANGIER_EXT_TIMER0_MSI 12
 
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index c9081c6671f0..df208af3cd74 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -3,6 +3,7 @@
 #endif
 #include <linux/cpu.h>
 #include <linux/kexec.h>
+#include <linux/slab.h>
 
 #include <xen/features.h>
 #include <xen/page.h>
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index dc87797db500..b50b74053664 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -4,6 +4,7 @@
  * Copyright © 2017-2018 Intel Corporation
  */
 
+#include <linux/irq.h>
 #include "i915_pmu.h"
 #include "intel_ringbuffer.h"
 #include "i915_drv.h"
diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c
index 6269750e2b54..b4941101f21a 100644
--- a/drivers/gpu/drm/i915/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/intel_lpe_audio.c
@@ -62,6 +62,7 @@
 
 #include <linux/acpi.h>
 #include <linux/device.h>
+#include <linux/irq.h>
 #include <linux/pci.h>
 #include <linux/pm_runtime.h>
 
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 6cc5036ac83c..fadc305533d9 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -45,6 +45,7 @@
 #include <linux/irqdomain.h>
 #include <asm/irqdomain.h>
 #include <asm/apic.h>
+#include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/hyperv.h>
 #include <linux/refcount.h>
-- 
cgit v1.2.3


From ffcba43ff66c7dab34ec700debd491d2a4d319b4 Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Sun, 29 Jul 2018 13:06:04 +0200
Subject: x86/irq: Let interrupt handlers set kvm_cpu_l1tf_flush_l1d

The last missing piece to having vmx_l1d_flush() take interrupts after
VMEXIT into account is to set the kvm_cpu_l1tf_flush_l1d per-cpu flag on
irq entry.

Issue calls to kvm_set_cpu_l1tf_flush_l1d() from entering_irq(),
ipi_entering_ack_irq(), smp_reschedule_interrupt() and
uv_bau_message_interrupt().

Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/apic.h   | 3 +++
 arch/x86/kernel/smp.c         | 1 +
 arch/x86/platform/uv/tlb_uv.c | 1 +
 3 files changed, 5 insertions(+)

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 9362a3aae927..130e81e10fc7 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -10,6 +10,7 @@
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
 #include <asm/msr.h>
+#include <asm/hardirq.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
 
@@ -514,6 +515,7 @@ extern void irq_exit(void);
 static inline void entering_irq(void)
 {
 	irq_enter();
+	kvm_set_cpu_l1tf_flush_l1d();
 }
 
 static inline void entering_ack_irq(void)
@@ -526,6 +528,7 @@ static inline void ipi_entering_ack_irq(void)
 {
 	irq_enter();
 	ack_APIC_irq();
+	kvm_set_cpu_l1tf_flush_l1d();
 }
 
 static inline void exiting_irq(void)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 5c574dff4c1a..04adc8d60aed 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -261,6 +261,7 @@ __visible void __irq_entry smp_reschedule_interrupt(struct pt_regs *regs)
 {
 	ack_APIC_irq();
 	inc_irq_stat(irq_resched_count);
+	kvm_set_cpu_l1tf_flush_l1d();
 
 	if (trace_resched_ipi_enabled()) {
 		/*
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index ca446da48fd2..3866b96a7ee7 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1285,6 +1285,7 @@ void uv_bau_message_interrupt(struct pt_regs *regs)
 	struct msg_desc msgdesc;
 
 	ack_APIC_irq();
+	kvm_set_cpu_l1tf_flush_l1d();
 	time_start = get_cycles();
 
 	bcp = &per_cpu(bau_control, smp_processor_id());
-- 
cgit v1.2.3


From 18b57ce2eb8c8b9a24174a89250cf5f57c76ecdc Mon Sep 17 00:00:00 2001
From: Nicolai Stange <nstange@suse.de>
Date: Sun, 22 Jul 2018 13:38:18 +0200
Subject: x86/KVM/VMX: Don't set l1tf_flush_l1d from vmx_handle_external_intr()

For VMEXITs caused by external interrupts, vmx_handle_external_intr()
indirectly calls into the interrupt handlers through the host's IDT.

It follows that these interrupts get accounted for in the
kvm_cpu_l1tf_flush_l1d per-cpu flag.

The subsequently executed vmx_l1d_flush() will thus be aware that some
interrupts have happened and conduct a L1d flush anyway.

Setting l1tf_flush_l1d from vmx_handle_external_intr() isn't needed
anymore. Drop it.

Signed-off-by: Nicolai Stange <nstange@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kvm/vmx.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 33892ddd229f..c6594fe38437 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9983,7 +9983,6 @@ static void vmx_handle_external_intr(struct kvm_vcpu *vcpu)
 			[ss]"i"(__KERNEL_DS),
 			[cs]"i"(__KERNEL_CS)
 			);
-		vcpu->arch.l1tf_flush_l1d = true;
 	}
 }
 STACK_FRAME_NON_STANDARD(vmx_handle_external_intr);
-- 
cgit v1.2.3


From 58331136136935c631c2b5f06daf4c3006416e91 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 5 Aug 2018 17:06:12 +0200
Subject: Documentation/l1tf: Remove Yonah processors from not vulnerable list

Dave reported, that it's not confirmed that Yonah processors are
unaffected. Remove them from the list.

Reported-by: ave Hansen <dave.hansen@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/admin-guide/l1tf.rst | 2 --
 1 file changed, 2 deletions(-)

diff --git a/Documentation/admin-guide/l1tf.rst b/Documentation/admin-guide/l1tf.rst
index ccf649cabdcd..5dadb4503ec9 100644
--- a/Documentation/admin-guide/l1tf.rst
+++ b/Documentation/admin-guide/l1tf.rst
@@ -19,8 +19,6 @@ vulnerability is not present on:
    - A range of Intel ATOM processors (Cedarview, Cloverview, Lincroft,
      Penwell, Pineview, Silvermont, Airmont, Merrifield)
 
-   - The Intel Core Duo Yonah variants (2006 - 2008)
-
    - The Intel XEON PHI family
 
    - Intel processors which have the ARCH_CAP_RDCL_NO bit set in the
-- 
cgit v1.2.3


From ea156d192f5257a5bf393d33910d3b481bf8a401 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sun, 5 Aug 2018 16:07:45 +0200
Subject: x86/speculation: Simplify sysfs report of VMX L1TF vulnerability

Three changes to the content of the sysfs file:

 - If EPT is disabled, L1TF cannot be exploited even across threads on the
   same core, and SMT is irrelevant.

 - If mitigation is completely disabled, and SMT is enabled, print "vulnerable"
   instead of "vulnerable, SMT vulnerable"

 - Reorder the two parts so that the main vulnerability state comes first
   and the detail on SMT is second.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/bugs.c | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index eb4b574be237..b0886bd24164 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -762,9 +762,15 @@ static ssize_t l1tf_show_state(char *buf)
 	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_AUTO)
 		return sprintf(buf, "%s\n", L1TF_DEFAULT_MSG);
 
-	return sprintf(buf, "%s; VMX: SMT %s, L1D %s\n", L1TF_DEFAULT_MSG,
-		       cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled",
-		       l1tf_vmx_states[l1tf_vmx_mitigation]);
+	if (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_EPT_DISABLED ||
+	    (l1tf_vmx_mitigation == VMENTER_L1D_FLUSH_NEVER &&
+	     cpu_smt_control == CPU_SMT_ENABLED))
+		return sprintf(buf, "%s; VMX: %s\n", L1TF_DEFAULT_MSG,
+			       l1tf_vmx_states[l1tf_vmx_mitigation]);
+
+	return sprintf(buf, "%s; VMX: %s, SMT %s\n", L1TF_DEFAULT_MSG,
+		       l1tf_vmx_states[l1tf_vmx_mitigation],
+		       cpu_smt_control == CPU_SMT_ENABLED ? "vulnerable" : "disabled");
 }
 #else
 static ssize_t l1tf_show_state(char *buf)
-- 
cgit v1.2.3


From 8e0b2b916662e09dd4d09e5271cdf214c6b80e62 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sun, 5 Aug 2018 16:07:46 +0200
Subject: x86/speculation: Use ARCH_CAPABILITIES to skip L1D flush on vmentry

Bit 3 of ARCH_CAPABILITIES tells a hypervisor that L1D flush on vmentry is
not needed.  Add a new value to enum vmx_l1d_flush_state, which is used
either if there is no L1TF bug at all, or if bit 3 is set in ARCH_CAPABILITIES.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/msr-index.h |  1 +
 arch/x86/include/asm/vmx.h       |  1 +
 arch/x86/kernel/cpu/bugs.c       |  1 +
 arch/x86/kvm/vmx.c               | 10 ++++++++++
 4 files changed, 13 insertions(+)

diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 0e7517089b80..4731f0cf97c5 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -70,6 +70,7 @@
 #define MSR_IA32_ARCH_CAPABILITIES	0x0000010a
 #define ARCH_CAP_RDCL_NO		(1 << 0)   /* Not susceptible to Meltdown */
 #define ARCH_CAP_IBRS_ALL		(1 << 1)   /* Enhanced IBRS support */
+#define ARCH_CAP_SKIP_VMENTRY_L1DFLUSH	(1 << 3)   /* Skip L1D flush on vmentry */
 #define ARCH_CAP_SSB_NO			(1 << 4)   /*
 						    * Not susceptible to Speculative Store Bypass
 						    * attack, so no Speculative Store Bypass
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 91241ccd4cfa..95f9107449bf 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -582,6 +582,7 @@ enum vmx_l1d_flush_state {
 	VMENTER_L1D_FLUSH_COND,
 	VMENTER_L1D_FLUSH_ALWAYS,
 	VMENTER_L1D_FLUSH_EPT_DISABLED,
+	VMENTER_L1D_FLUSH_NOT_REQUIRED,
 };
 
 extern enum vmx_l1d_flush_state l1tf_vmx_mitigation;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index b0886bd24164..86f4549b7c9f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -755,6 +755,7 @@ static const char *l1tf_vmx_states[] = {
 	[VMENTER_L1D_FLUSH_COND]		= "conditional cache flushes",
 	[VMENTER_L1D_FLUSH_ALWAYS]		= "cache flushes",
 	[VMENTER_L1D_FLUSH_EPT_DISABLED]	= "EPT disabled",
+	[VMENTER_L1D_FLUSH_NOT_REQUIRED]	= "flush not necessary"
 };
 
 static ssize_t l1tf_show_state(char *buf)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 8384f7cb30d8..29d6eab6920e 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -218,6 +218,16 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
 		return 0;
 	}
 
+       if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) {
+	       u64 msr;
+
+	       rdmsrl(MSR_IA32_ARCH_CAPABILITIES, msr);
+	       if (msr & ARCH_CAP_SKIP_VMENTRY_L1DFLUSH) {
+		       l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NOT_REQUIRED;
+		       return 0;
+	       }
+       }
+
 	/* If set to auto use the default l1tf mitigation method */
 	if (l1tf == VMENTER_L1D_FLUSH_AUTO) {
 		switch (l1tf_mitigation) {
-- 
cgit v1.2.3


From 5b76a3cff011df2dcb6186c965a2e4d809a05ad4 Mon Sep 17 00:00:00 2001
From: Paolo Bonzini <pbonzini@redhat.com>
Date: Sun, 5 Aug 2018 16:07:47 +0200
Subject: KVM: VMX: Tell the nested hypervisor to skip L1D flush on vmentry

When nested virtualization is in use, VMENTER operations from the nested
hypervisor into the nested guest will always be processed by the bare metal
hypervisor, and KVM's "conditional cache flushes" mode in particular does a
flush on nested vmentry.  Therefore, include the "skip L1D flush on
vmentry" bit in KVM's suggested ARCH_CAPABILITIES setting.

Add the relevant Documentation.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 Documentation/admin-guide/l1tf.rst | 21 +++++++++++++++++++++
 arch/x86/include/asm/kvm_host.h    |  1 +
 arch/x86/kvm/vmx.c                 |  3 +--
 arch/x86/kvm/x86.c                 | 26 +++++++++++++++++++++++++-
 4 files changed, 48 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/l1tf.rst b/Documentation/admin-guide/l1tf.rst
index 5dadb4503ec9..bae52b845de0 100644
--- a/Documentation/admin-guide/l1tf.rst
+++ b/Documentation/admin-guide/l1tf.rst
@@ -546,6 +546,27 @@ available:
     EPT can be disabled in the hypervisor via the 'kvm-intel.ept'
     parameter.
 
+3.4. Nested virtual machines
+""""""""""""""""""""""""""""
+
+When nested virtualization is in use, three operating systems are involved:
+the bare metal hypervisor, the nested hypervisor and the nested virtual
+machine.  VMENTER operations from the nested hypervisor into the nested
+guest will always be processed by the bare metal hypervisor. If KVM is the
+bare metal hypervisor it wiil:
+
+ - Flush the L1D cache on every switch from the nested hypervisor to the
+   nested virtual machine, so that the nested hypervisor's secrets are not
+   exposed to the nested virtual machine;
+
+ - Flush the L1D cache on every switch from the nested virtual machine to
+   the nested hypervisor; this is a complex operation, and flushing the L1D
+   cache avoids that the bare metal hypervisor's secrets are exposed to the
+   nested virtual machine;
+
+ - Instruct the nested hypervisor to not perform any L1D cache flush. This
+   is an optimization to avoid double L1D flushing.
+
 
 .. _default_mitigations:
 
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 37749429afd9..acebb808c4b5 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1418,6 +1418,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
 void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
 void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
 
+u64 kvm_get_arch_capabilities(void);
 void kvm_define_shared_msr(unsigned index, u32 msr);
 int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
 
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 29d6eab6920e..58bba7a7572a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6465,8 +6465,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
 		++vmx->nmsrs;
 	}
 
-	if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
-		rdmsrl(MSR_IA32_ARCH_CAPABILITIES, vmx->arch_capabilities);
+	vmx->arch_capabilities = kvm_get_arch_capabilities();
 
 	vm_exit_controls_init(vmx, vmcs_config.vmexit_ctrl);
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 79c8ca2c2ad9..a5caa5e5480c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1103,11 +1103,35 @@ static u32 msr_based_features[] = {
 
 static unsigned int num_msr_based_features;
 
+u64 kvm_get_arch_capabilities(void)
+{
+	u64 data;
+
+	rdmsrl_safe(MSR_IA32_ARCH_CAPABILITIES, &data);
+
+	/*
+	 * If we're doing cache flushes (either "always" or "cond")
+	 * we will do one whenever the guest does a vmlaunch/vmresume.
+	 * If an outer hypervisor is doing the cache flush for us
+	 * (VMENTER_L1D_FLUSH_NESTED_VM), we can safely pass that
+	 * capability to the guest too, and if EPT is disabled we're not
+	 * vulnerable.  Overall, only VMENTER_L1D_FLUSH_NEVER will
+	 * require a nested hypervisor to do a flush of its own.
+	 */
+	if (l1tf_vmx_mitigation != VMENTER_L1D_FLUSH_NEVER)
+		data |= ARCH_CAP_SKIP_VMENTRY_L1DFLUSH;
+
+	return data;
+}
+EXPORT_SYMBOL_GPL(kvm_get_arch_capabilities);
+
 static int kvm_get_msr_feature(struct kvm_msr_entry *msr)
 {
 	switch (msr->index) {
-	case MSR_IA32_UCODE_REV:
 	case MSR_IA32_ARCH_CAPABILITIES:
+		msr->data = kvm_get_arch_capabilities();
+		break;
+	case MSR_IA32_UCODE_REV:
 		rdmsrl_safe(msr->index, &msr->data);
 		break;
 	default:
-- 
cgit v1.2.3


From 56e40eb6d656194e55ce2012fee9d5a496270aaa Mon Sep 17 00:00:00 2001
From: Alexandru Gagniuc <mr.nuke.me@gmail.com>
Date: Sat, 4 Aug 2018 11:44:44 -0500
Subject: ALSA: hda/realtek - Add mute LED quirk for HP Spectre x360

This device has the same issues as the HP x360 wrt the MUTE LED and
the front speakers not working. This patch fixes the MUTE LED issue,
but doesn't touch the HDA verbs. The fix for the x360 does not work
on the Spectre.

Signed-off-by: Alexandru Gagniuc <mr.nuke.me@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e2d0b2f3bd30..b20974ef1e13 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -6474,6 +6474,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x827e, "HP x360", ALC295_FIXUP_HP_X360),
 	SND_PCI_QUIRK(0x103c, 0x82bf, "HP", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x103c, 0x82c0, "HP", ALC221_FIXUP_HP_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x103c, 0x83b9, "HP Spectre x360", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
-- 
cgit v1.2.3


From 855371bd01b4cd8cf0e2b8ca172a5c30a481f963 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 23 Jun 2018 20:48:31 -0400
Subject: afs: switch dynroot lookups to d_splice_alias()

->lookup() methods can (and should) use d_splice_alias() instead of
d_add().  Even if they are not going to be hit by open_by_handle(),
code does get copied around...

Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/afs/dynroot.c | 18 +++---------------
 1 file changed, 3 insertions(+), 15 deletions(-)

diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 174e843f0633..40fea59067b3 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -143,7 +143,6 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr
 {
 	struct afs_vnode *vnode;
 	struct inode *inode;
-	int ret;
 
 	vnode = AFS_FS_I(dir);
 
@@ -161,21 +160,10 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr
 		return afs_lookup_atcell(dentry);
 
 	inode = afs_try_auto_mntpt(dentry, dir);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		if (ret == -ENOENT) {
-			d_add(dentry, NULL);
-			_leave(" = NULL [negative]");
-			return NULL;
-		}
-		_leave(" = %d [do]", ret);
-		return ERR_PTR(ret);
-	}
+	if (inode == ERR_PTR(-ENOENT))
+		inode = NULL;
 
-	d_add(dentry, inode);
-	_leave(" = 0 { ino=%lu v=%u }",
-	       d_inode(dentry)->i_ino, d_inode(dentry)->i_generation);
-	return NULL;
+	return d_splice_alias(inode, dentry);
 }
 
 const struct inode_operations afs_dynroot_inode_operations = {
-- 
cgit v1.2.3


From 34b2a88fb4aa4de34e1d5f9fc2761b746980f9b1 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 24 Jun 2018 10:43:51 -0400
Subject: afs_lookup(): switch to d_splice_alias()

->lookup() methods can (and should) use d_splice_alias() instead of
d_add().  Even if they are not going to be hit by open_by_handle(),
code does get copied around; besides, d_splice_alias() has better
calling conventions for use in ->lookup(), so the code gets simpler.

Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/afs/dir.c | 47 ++++++++++++-----------------------------------
 1 file changed, 12 insertions(+), 35 deletions(-)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 7d623008157f..52f44255f65d 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -822,6 +822,7 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 {
 	struct afs_vnode *dvnode = AFS_FS_I(dir);
 	struct inode *inode;
+	struct dentry *d;
 	struct key *key;
 	int ret;
 
@@ -862,43 +863,19 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 
 	afs_stat_v(dvnode, n_lookup);
 	inode = afs_do_lookup(dir, dentry, key);
-	if (IS_ERR(inode)) {
-		ret = PTR_ERR(inode);
-		if (ret == -ENOENT) {
-			inode = afs_try_auto_mntpt(dentry, dir);
-			if (!IS_ERR(inode)) {
-				key_put(key);
-				goto success;
-			}
-
-			ret = PTR_ERR(inode);
-		}
-
-		key_put(key);
-		if (ret == -ENOENT) {
-			d_add(dentry, NULL);
-			_leave(" = NULL [negative]");
-			return NULL;
-		}
-		_leave(" = %d [do]", ret);
-		return ERR_PTR(ret);
-	}
-	dentry->d_fsdata = (void *)(unsigned long)dvnode->status.data_version;
-
-	/* instantiate the dentry */
 	key_put(key);
-	if (IS_ERR(inode)) {
-		_leave(" = %ld", PTR_ERR(inode));
-		return ERR_CAST(inode);
+	if (inode == ERR_PTR(-ENOENT)) {
+		inode = afs_try_auto_mntpt(dentry, dir);
+		if (inode == ERR_PTR(-ENOENT))
+			inode = NULL;
+	} else {
+		dentry->d_fsdata =
+			(void *)(unsigned long)dvnode->status.data_version;
 	}
-
-success:
-	d_add(dentry, inode);
-	_leave(" = 0 { ino=%lu v=%u }",
-	       d_inode(dentry)->i_ino,
-	       d_inode(dentry)->i_generation);
-
-	return NULL;
+	d = d_splice_alias(inode, dentry);
+	if (!IS_ERR_OR_NULL(d))
+		d->d_fsdata = dentry->d_fsdata;
+	return d;
 }
 
 /*
-- 
cgit v1.2.3


From 1401a0fc2d47988677dc1dbfd56ff89daa323717 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 24 Jun 2018 10:45:44 -0400
Subject: afs_try_auto_mntpt(): return NULL instead of ERR_PTR(-ENOENT)

simpler logics in callers that way

Acked-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/afs/dir.c     |  2 --
 fs/afs/dynroot.c | 13 ++-----------
 2 files changed, 2 insertions(+), 13 deletions(-)

diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 52f44255f65d..855bf2b79fed 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -866,8 +866,6 @@ static struct dentry *afs_lookup(struct inode *dir, struct dentry *dentry,
 	key_put(key);
 	if (inode == ERR_PTR(-ENOENT)) {
 		inode = afs_try_auto_mntpt(dentry, dir);
-		if (inode == ERR_PTR(-ENOENT))
-			inode = NULL;
 	} else {
 		dentry->d_fsdata =
 			(void *)(unsigned long)dvnode->status.data_version;
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index 40fea59067b3..1cde710a8013 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -83,7 +83,7 @@ struct inode *afs_try_auto_mntpt(struct dentry *dentry, struct inode *dir)
 
 out:
 	_leave("= %d", ret);
-	return ERR_PTR(ret);
+	return ret == -ENOENT ? NULL : ERR_PTR(ret);
 }
 
 /*
@@ -141,11 +141,6 @@ out_p:
 static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentry,
 					 unsigned int flags)
 {
-	struct afs_vnode *vnode;
-	struct inode *inode;
-
-	vnode = AFS_FS_I(dir);
-
 	_enter("%pd", dentry);
 
 	ASSERTCMP(d_inode(dentry), ==, NULL);
@@ -159,11 +154,7 @@ static struct dentry *afs_dynroot_lookup(struct inode *dir, struct dentry *dentr
 	    memcmp(dentry->d_name.name, "@cell", 5) == 0)
 		return afs_lookup_atcell(dentry);
 
-	inode = afs_try_auto_mntpt(dentry, dir);
-	if (inode == ERR_PTR(-ENOENT))
-		inode = NULL;
-
-	return d_splice_alias(inode, dentry);
+	return d_splice_alias(afs_try_auto_mntpt(dentry, dir), dentry);
 }
 
 const struct inode_operations afs_dynroot_inode_operations = {
-- 
cgit v1.2.3


From 7964410fcf135d7e76deef4e475816ec02482f7b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 1 Aug 2018 19:39:05 -0500
Subject: fs: dcache: Use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This issue was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/dcache.c b/fs/dcache.c
index 0e8e5de3c48a..6fd5c1aa4620 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -732,16 +732,16 @@ static inline bool fast_dput(struct dentry *dentry)
 		if (dentry->d_lockref.count > 1) {
 			dentry->d_lockref.count--;
 			spin_unlock(&dentry->d_lock);
-			return 1;
+			return true;
 		}
-		return 0;
+		return false;
 	}
 
 	/*
 	 * If we weren't the last ref, we're done.
 	 */
 	if (ret)
-		return 1;
+		return true;
 
 	/*
 	 * Careful, careful. The reference count went down
@@ -770,7 +770,7 @@ static inline bool fast_dput(struct dentry *dentry)
 
 	/* Nothing to do? Dropping the reference was all we needed? */
 	if (d_flags == (DCACHE_REFERENCED | DCACHE_LRU_LIST) && !d_unhashed(dentry))
-		return 1;
+		return true;
 
 	/*
 	 * Not the fast normal case? Get the lock. We've already decremented
@@ -787,7 +787,7 @@ static inline bool fast_dput(struct dentry *dentry)
 	 */
 	if (dentry->d_lockref.count) {
 		spin_unlock(&dentry->d_lock);
-		return 1;
+		return true;
 	}
 
 	/*
@@ -796,7 +796,7 @@ static inline bool fast_dput(struct dentry *dentry)
 	 * set it to 1.
 	 */
 	dentry->d_lockref.count = 1;
-	return 0;
+	return false;
 }
 
 
-- 
cgit v1.2.3


From cfd355145c32bb7ccb65fccbe2d67280dc2119e1 Mon Sep 17 00:00:00 2001
From: Prasad Sodagudi <psodagud@codeaurora.org>
Date: Fri, 3 Aug 2018 13:56:06 -0700
Subject: stop_machine: Atomically queue and wake stopper threads

When cpu_stop_queue_work() releases the lock for the stopper
thread that was queued into its wake queue, preemption is
enabled, which leads to the following deadlock:

CPU0                              CPU1
sched_setaffinity(0, ...)
__set_cpus_allowed_ptr()
stop_one_cpu(0, ...)              stop_two_cpus(0, 1, ...)
cpu_stop_queue_work(0, ...)       cpu_stop_queue_two_works(0, ..., 1, ...)

-grabs lock for migration/0-
                                  -spins with preemption disabled,
                                   waiting for migration/0's lock to be
                                   released-

-adds work items for migration/0
and queues migration/0 to its
wake_q-

-releases lock for migration/0
 and preemption is enabled-

-current thread is preempted,
and __set_cpus_allowed_ptr
has changed the thread's
cpu allowed mask to CPU1 only-

                                  -acquires migration/0 and migration/1's
                                   locks-

                                  -adds work for migration/0 but does not
                                   add migration/0 to wake_q, since it is
                                   already in a wake_q-

                                  -adds work for migration/1 and adds
                                   migration/1 to its wake_q-

                                  -releases migration/0 and migration/1's
                                   locks, wakes migration/1, and enables
                                   preemption-

                                  -since migration/1 is requested to run,
                                   migration/1 begins to run and waits on
                                   migration/0, but migration/0 will never
                                   be able to run, since the thread that
                                   can wake it is affine to CPU1-

Disable preemption in cpu_stop_queue_work() before queueing works for
stopper threads, and queueing the stopper thread in the wake queue, to
ensure that the operation of queueing the works and waking the stopper
threads is atomic.

Fixes: 0b26351b910f ("stop_machine, sched: Fix migrate_swap() vs. active_balance() deadlock")
Signed-off-by: Prasad Sodagudi <psodagud@codeaurora.org>
Signed-off-by: Isaac J. Manjarres <isaacm@codeaurora.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: peterz@infradead.org
Cc: matt@codeblueprint.co.uk
Cc: bigeasy@linutronix.de
Cc: gregkh@linuxfoundation.org
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/1533329766-4856-1-git-send-email-isaacm@codeaurora.org

Co-Developed-by: Isaac J. Manjarres <isaacm@codeaurora.org>
---
 kernel/stop_machine.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index e190d1ef3a23..69eb76daed34 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -81,6 +81,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	unsigned long flags;
 	bool enabled;
 
+	preempt_disable();
 	raw_spin_lock_irqsave(&stopper->lock, flags);
 	enabled = stopper->enabled;
 	if (enabled)
@@ -90,6 +91,7 @@ static bool cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work)
 	raw_spin_unlock_irqrestore(&stopper->lock, flags);
 
 	wake_up_q(&wakeq);
+	preempt_enable();
 
 	return enabled;
 }
-- 
cgit v1.2.3


From eac7073aa69aa1cac819aa712146284f53f642b1 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 2 Aug 2018 15:58:25 -0700
Subject: x86/mm/pti: Clear Global bit more aggressively

The kernel image starts out with the Global bit set across the entire
kernel image.  The bit is cleared with set_memory_nonglobal() in the
configurations with PCIDs where the performance benefits of the Global bit
are not needed.

However, this is fragile.  It means that we are stuck opting *out* of the
less-secure (Global bit set) configuration, which seems backwards.  Let's
start more secure (Global bit clear) and then let things opt back in if
they want performance, or are truly mapping common data between kernel and
userspace.

This fixes a bug.  Before this patch, there are areas that are unmapped
from the user page tables (like like everything above 0xffffffff82600000 in
the example below).  These have the hallmark of being a wrong Global area:
they are not identical in the 'current_kernel' and 'current_user' page
table dumps.  They are also read-write, which means they're much more
likely to contain secrets.

Before this patch:

current_kernel:---[ High Kernel Mapping ]---
current_kernel-0xffffffff80000000-0xffffffff81000000          16M                               pmd
current_kernel-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
current_kernel-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
current_kernel-0xffffffff81e11000-0xffffffff82000000        1980K     RW                 GLB NX pte
current_kernel-0xffffffff82000000-0xffffffff82600000           6M     ro         PSE     GLB NX pmd
current_kernel-0xffffffff82600000-0xffffffff82c00000           6M     RW         PSE     GLB NX pmd
current_kernel-0xffffffff82c00000-0xffffffff82e00000           2M     RW                 GLB NX pte
current_kernel-0xffffffff82e00000-0xffffffff83200000           4M     RW         PSE     GLB NX pmd
current_kernel-0xffffffff83200000-0xffffffffa0000000         462M                               pmd

 current_user:---[ High Kernel Mapping ]---
 current_user-0xffffffff80000000-0xffffffff81000000          16M                               pmd
 current_user-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
 current_user-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
 current_user-0xffffffff81e11000-0xffffffff82000000        1980K     RW                 GLB NX pte
 current_user-0xffffffff82000000-0xffffffff82600000           6M     ro         PSE     GLB NX pmd
 current_user-0xffffffff82600000-0xffffffffa0000000         474M                               pmd

After this patch:

current_kernel:---[ High Kernel Mapping ]---
current_kernel-0xffffffff80000000-0xffffffff81000000          16M                               pmd
current_kernel-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
current_kernel-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
current_kernel-0xffffffff81e11000-0xffffffff82000000        1980K     RW                     NX pte
current_kernel-0xffffffff82000000-0xffffffff82600000           6M     ro         PSE     GLB NX pmd
current_kernel-0xffffffff82600000-0xffffffff82c00000           6M     RW         PSE         NX pmd
current_kernel-0xffffffff82c00000-0xffffffff82e00000           2M     RW                     NX pte
current_kernel-0xffffffff82e00000-0xffffffff83200000           4M     RW         PSE         NX pmd
current_kernel-0xffffffff83200000-0xffffffffa0000000         462M                               pmd

  current_user:---[ High Kernel Mapping ]---
  current_user-0xffffffff80000000-0xffffffff81000000          16M                               pmd
  current_user-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
  current_user-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
  current_user-0xffffffff81e11000-0xffffffff82000000        1980K     RW                     NX pte
  current_user-0xffffffff82000000-0xffffffff82600000           6M     ro         PSE     GLB NX pmd
  current_user-0xffffffff82600000-0xffffffffa0000000         474M                               pmd

Fixes: 0f561fce4d69 ("x86/pti: Enable global pages for shared areas")
Reported-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: keescook@google.com
Cc: aarcange@redhat.com
Cc: jgross@suse.com
Cc: jpoimboe@redhat.com
Cc: gregkh@linuxfoundation.org
Cc: peterz@infradead.org
Cc: torvalds@linux-foundation.org
Cc: bp@alien8.de
Cc: luto@kernel.org
Cc: ak@linux.intel.com
Cc: Kees Cook <keescook@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20180802225825.A100C071@viggo.jf.intel.com
---
 arch/x86/mm/pageattr.c |  6 ++++++
 arch/x86/mm/pti.c      | 34 ++++++++++++++++++++++++----------
 2 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3bded76e8d5c..c04153796f61 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1784,6 +1784,12 @@ int set_memory_nonglobal(unsigned long addr, int numpages)
 				      __pgprot(_PAGE_GLOBAL), 0);
 }
 
+int set_memory_global(unsigned long addr, int numpages)
+{
+	return change_page_attr_set(&addr, numpages,
+				    __pgprot(_PAGE_GLOBAL), 0);
+}
+
 static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 {
 	struct cpa_data cpa;
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 4d418e705878..8d88d067b3d7 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -434,6 +434,13 @@ static inline bool pti_kernel_image_global_ok(void)
 	return true;
 }
 
+/*
+ * This is the only user for these and it is not arch-generic
+ * like the other set_memory.h functions.  Just extern them.
+ */
+extern int set_memory_nonglobal(unsigned long addr, int numpages);
+extern int set_memory_global(unsigned long addr, int numpages);
+
 /*
  * For some configurations, map all of kernel text into the user page
  * tables.  This reduces TLB misses, especially on non-PCID systems.
@@ -446,7 +453,8 @@ void pti_clone_kernel_text(void)
 	 * clone the areas past rodata, they might contain secrets.
 	 */
 	unsigned long start = PFN_ALIGN(_text);
-	unsigned long end = (unsigned long)__end_rodata_hpage_align;
+	unsigned long end_clone  = (unsigned long)__end_rodata_hpage_align;
+	unsigned long end_global = PFN_ALIGN((unsigned long)__stop___ex_table);
 
 	if (!pti_kernel_image_global_ok())
 		return;
@@ -458,14 +466,18 @@ void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end, _PAGE_RW);
+	pti_clone_pmds(start, end_clone, _PAGE_RW);
+
+	/*
+	 * pti_clone_pmds() will set the global bit in any PMDs
+	 * that it clones, but we also need to get any PTEs in
+	 * the last level for areas that are not huge-page-aligned.
+	 */
+
+	/* Set the global bit for normal non-__init kernel text: */
+	set_memory_global(start, (end_global - start) >> PAGE_SHIFT);
 }
 
-/*
- * This is the only user for it and it is not arch-generic like
- * the other set_memory.h functions.  Just extern it.
- */
-extern int set_memory_nonglobal(unsigned long addr, int numpages);
 void pti_set_kernel_image_nonglobal(void)
 {
 	/*
@@ -477,9 +489,11 @@ void pti_set_kernel_image_nonglobal(void)
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long end = ALIGN((unsigned long)_end, PMD_PAGE_SIZE);
 
-	if (pti_kernel_image_global_ok())
-		return;
-
+	/*
+	 * This clears _PAGE_GLOBAL from the entire kernel image.
+	 * pti_clone_kernel_text() map put _PAGE_GLOBAL back for
+	 * areas that are mapped to userspace.
+	 */
 	set_memory_nonglobal(start, (end - start) >> PAGE_SHIFT);
 }
 
-- 
cgit v1.2.3


From 0d83432811f26871295a9bc24d3c387924da6071 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 2 Aug 2018 15:58:26 -0700
Subject: mm: Allow non-direct-map arguments to free_reserved_area()

free_reserved_area() takes pointers as arguments to show which addresses
should be freed.  However, it does this in a somewhat ambiguous way.  If it
gets a kernel direct map address, it always works.  However, if it gets an
address that is part of the kernel image alias mapping, it can fail.

It fails if all of the following happen:
 * The specified address is part of the kernel image alias
 * Poisoning is requested (forcing a memset())
 * The address is in a read-only portion of the kernel image

The memset() fails on the read-only mapping, of course.
free_reserved_area() *is* called both on the direct map and on kernel image
alias addresses.  We've just lucked out thus far that the kernel image
alias areas it gets used on are read-write.  I'm fairly sure this has been
just a happy accident.

It is quite easy to make free_reserved_area() work for all cases: just
convert the address to a direct map address before doing the memset(), and
do this unconditionally.  There is little chance of a regression here
because we previously did a virt_to_page() on the address for the memset,
so we know these are not highmem pages for which virt_to_page() would fail.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: keescook@google.com
Cc: aarcange@redhat.com
Cc: jgross@suse.com
Cc: jpoimboe@redhat.com
Cc: gregkh@linuxfoundation.org
Cc: peterz@infradead.org
Cc: hughd@google.com
Cc: torvalds@linux-foundation.org
Cc: bp@alien8.de
Cc: luto@kernel.org
Cc: ak@linux.intel.com
Cc: Kees Cook <keescook@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20180802225826.1287AE3E@viggo.jf.intel.com
---
 mm/page_alloc.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index a790ef4be74e..3222193c46c6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6939,9 +6939,21 @@ unsigned long free_reserved_area(void *start, void *end, int poison, char *s)
 	start = (void *)PAGE_ALIGN((unsigned long)start);
 	end = (void *)((unsigned long)end & PAGE_MASK);
 	for (pos = start; pos < end; pos += PAGE_SIZE, pages++) {
+		struct page *page = virt_to_page(pos);
+		void *direct_map_addr;
+
+		/*
+		 * 'direct_map_addr' might be different from 'pos'
+		 * because some architectures' virt_to_page()
+		 * work with aliases.  Getting the direct map
+		 * address ensures that we get a _writeable_
+		 * alias for the memset().
+		 */
+		direct_map_addr = page_address(page);
 		if ((unsigned int)poison <= 0xFF)
-			memset(pos, poison, PAGE_SIZE);
-		free_reserved_page(virt_to_page(pos));
+			memset(direct_map_addr, poison, PAGE_SIZE);
+
+		free_reserved_page(page);
 	}
 
 	if (pages && s)
-- 
cgit v1.2.3


From 9f515cdb411ef34f1aaf4c40bb0c932cf6db5de1 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 2 Aug 2018 15:58:28 -0700
Subject: x86/mm/init: Pass unconverted symbol addresses to free_init_pages()

The x86 code has several places where it frees parts of kernel image:

 1. Unused SMP alternative
 2. __init code
 3. The hole between text and rodata
 4. The hole between rodata and data

We call free_init_pages() to do this.  Strangely, we convert the symbol
addresses to kernel direct map addresses in some cases (#3, #4) but not
others (#1, #2).

The virt_to_page() and the other code in free_reserved_area() now works
fine for for symbol addresses on x86, so don't bother converting the
addresses to direct map addresses before freeing them.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: keescook@google.com
Cc: aarcange@redhat.com
Cc: jgross@suse.com
Cc: jpoimboe@redhat.com
Cc: gregkh@linuxfoundation.org
Cc: peterz@infradead.org
Cc: hughd@google.com
Cc: torvalds@linux-foundation.org
Cc: bp@alien8.de
Cc: luto@kernel.org
Cc: ak@linux.intel.com
Cc: Kees Cook <keescook@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20180802225828.89B2D0E2@viggo.jf.intel.com
---
 arch/x86/mm/init_64.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index a688617c727e..73158655c4a7 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1283,12 +1283,8 @@ void mark_rodata_ro(void)
 	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
 #endif
 
-	free_init_pages("unused kernel",
-			(unsigned long) __va(__pa_symbol(text_end)),
-			(unsigned long) __va(__pa_symbol(rodata_start)));
-	free_init_pages("unused kernel",
-			(unsigned long) __va(__pa_symbol(rodata_end)),
-			(unsigned long) __va(__pa_symbol(_sdata)));
+	free_init_pages("unused kernel", text_end, rodata_start);
+	free_init_pages("unused kernel", rodata_end, _sdata);
 
 	debug_checkwx();
 
-- 
cgit v1.2.3


From 6ea2738e0ca0e626c75202fb051c1e88d7a950fa Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 2 Aug 2018 15:58:29 -0700
Subject: x86/mm/init: Add helper for freeing kernel image pages

When chunks of the kernel image are freed, free_init_pages() is used
directly.  Consolidate the three sites that do this.  Also update the
string to give an incrementally better description of that memory versus
what was there before.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: keescook@google.com
Cc: aarcange@redhat.com
Cc: jgross@suse.com
Cc: jpoimboe@redhat.com
Cc: gregkh@linuxfoundation.org
Cc: peterz@infradead.org
Cc: hughd@google.com
Cc: torvalds@linux-foundation.org
Cc: bp@alien8.de
Cc: luto@kernel.org
Cc: ak@linux.intel.com
Cc: Kees Cook <keescook@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Link: https://lkml.kernel.org/r/20180802225829.FE0E32EA@viggo.jf.intel.com
---
 arch/x86/include/asm/processor.h |  1 +
 arch/x86/mm/init.c               | 15 ++++++++++++---
 arch/x86/mm/init_64.c            |  4 ++--
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index cfd29ee8c3da..59663c08c949 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -966,6 +966,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)
 
 extern unsigned long arch_align_stack(unsigned long sp);
 extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+extern void free_kernel_image_pages(void *begin, void *end);
 
 void default_idle(void);
 #ifdef	CONFIG_XEN
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index cee58a972cb2..bc11dedffc45 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -773,13 +773,22 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
 	}
 }
 
+/*
+ * begin/end can be in the direct map or the "high kernel mapping"
+ * used for the kernel image only.  free_init_pages() will do the
+ * right thing for either kind of address.
+ */
+void free_kernel_image_pages(void *begin, void *end)
+{
+	free_init_pages("unused kernel image",
+			(unsigned long)begin, (unsigned long)end);
+}
+
 void __ref free_initmem(void)
 {
 	e820__reallocate_tables();
 
-	free_init_pages("unused kernel",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
+	free_kernel_image_pages(&__init_begin, &__init_end);
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 73158655c4a7..68c292cb1ebf 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1283,8 +1283,8 @@ void mark_rodata_ro(void)
 	set_memory_ro(start, (end-start) >> PAGE_SHIFT);
 #endif
 
-	free_init_pages("unused kernel", text_end, rodata_start);
-	free_init_pages("unused kernel", rodata_end, _sdata);
+	free_kernel_image_pages((void *)text_end, (void *)rodata_start);
+	free_kernel_image_pages((void *)rodata_end, (void *)_sdata);
 
 	debug_checkwx();
 
-- 
cgit v1.2.3


From 208cbb32558907f68b3b2a081ca2337ac3744794 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Fri, 3 Aug 2018 10:05:50 -0700
Subject: x86/irqflags: Provide a declaration for native_save_fl

It was reported that the commit d0a8d9378d16 is causing users of gcc < 4.9
to observe -Werror=missing-prototypes errors.

Indeed, it seems that:
extern inline unsigned long native_save_fl(void) { return 0; }

compiled with -Werror=missing-prototypes produces this warning in gcc <
4.9, but not gcc >= 4.9.

Fixes: d0a8d9378d16 ("x86/paravirt: Make native_save_fl() extern inline").
Reported-by: David Laight <david.laight@aculab.com>
Reported-by: Jean Delvare <jdelvare@suse.de>
Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: hpa@zytor.com
Cc: jgross@suse.com
Cc: kstewart@linuxfoundation.org
Cc: gregkh@linuxfoundation.org
Cc: boris.ostrovsky@oracle.com
Cc: astrachan@google.com
Cc: mka@chromium.org
Cc: arnd@arndb.de
Cc: tstellar@redhat.com
Cc: sedat.dilek@gmail.com
Cc: David.Laight@aculab.com
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20180803170550.164688-1-ndesaulniers@google.com
---
 arch/x86/include/asm/irqflags.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index c4fc17220df9..c14f2a74b2be 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -13,6 +13,8 @@
  * Interrupt control:
  */
 
+/* Declaration required for gcc < 4.9 to prevent -Werror=missing-prototypes */
+extern inline unsigned long native_save_fl(void);
 extern inline unsigned long native_save_fl(void)
 {
 	unsigned long flags;
-- 
cgit v1.2.3


From 379d98ddf41344273d9718556f761420f4dc80b3 Mon Sep 17 00:00:00 2001
From: Alistair Strachan <astrachan@google.com>
Date: Fri, 3 Aug 2018 10:39:31 -0700
Subject: x86: vdso: Use $LD instead of $CC to link

The vdso{32,64}.so can fail to link with CC=clang when clang tries to find
a suitable GCC toolchain to link these libraries with.

/usr/bin/ld: arch/x86/entry/vdso/vclock_gettime.o:
  access beyond end of merged section (782)

This happens because the host environment leaked into the cross compiler
environment due to the way clang searches for suitable GCC toolchains.

Clang is a retargetable compiler, and each invocation of it must provide
--target=<something> --gcc-toolchain=<something> to allow it to find the
correct binutils for cross compilation. These flags had been added to
KBUILD_CFLAGS, but the vdso code uses CC and not KBUILD_CFLAGS (for various
reasons) which breaks clang's ability to find the correct linker when cross
compiling.

Most of the time this goes unnoticed because the host linker is new enough
to work anyway, or is incompatible and skipped, but this cannot be reliably
assumed.

This change alters the vdso makefile to just use LD directly, which
bypasses clang and thus the searching problem. The makefile will just use
${CROSS_COMPILE}ld instead, which is always what we want. This matches the
method used to link vmlinux.

This drops references to DISABLE_LTO; this option doesn't seem to be set
anywhere, and not knowing what its possible values are, it's not clear how
to convert it from CC to LD flag.

Signed-off-by: Alistair Strachan <astrachan@google.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Andy Lutomirski <luto@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: kernel-team@android.com
Cc: joel@joelfernandes.org
Cc: Andi Kleen <andi.kleen@intel.com>
Link: https://lkml.kernel.org/r/20180803173931.117515-1-astrachan@google.com
---
 arch/x86/entry/vdso/Makefile | 22 +++++++++-------------
 1 file changed, 9 insertions(+), 13 deletions(-)

diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 261802b1cc50..42c6c1bea4f4 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -46,10 +46,8 @@ targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
 
 CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
-			-Wl,--no-undefined \
-			-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096 \
-			$(DISABLE_LTO)
+VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -soname linux-vdso.so.1 --no-undefined \
+			-z max-page-size=4096 -z common-page-size=4096
 
 $(obj)/vdso64.so.dbg: $(obj)/vdso.lds $(vobjs) FORCE
 	$(call if_changed,vdso)
@@ -95,10 +93,8 @@ CFLAGS_REMOVE_vvar.o = -pg
 #
 
 CPPFLAGS_vdsox32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdsox32.lds = -Wl,-m,elf32_x86_64 \
-			   -Wl,-soname=linux-vdso.so.1 \
-			   -Wl,-z,max-page-size=4096 \
-			   -Wl,-z,common-page-size=4096
+VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
+			   -z max-page-size=4096 -z common-page-size=4096
 
 # x32-rebranded versions
 vobjx32s-y := $(vobjs-y:.o=-x32.o)
@@ -123,7 +119,7 @@ $(obj)/vdsox32.so.dbg: $(obj)/vdsox32.lds $(vobjx32s) FORCE
 	$(call if_changed,vdso)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -soname linux-gate.so.1
 
 targets += vdso32/vdso32.lds
 targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
@@ -157,13 +153,13 @@ $(obj)/vdso32.so.dbg: FORCE \
 # The DSO images are built using a special linker script.
 #
 quiet_cmd_vdso = VDSO    $@
-      cmd_vdso = $(CC) -nostdlib -o $@ \
+      cmd_vdso = $(LD) -nostdlib -o $@ \
 		       $(VDSO_LDFLAGS) $(VDSO_LDFLAGS_$(filter %.lds,$(^F))) \
-		       -Wl,-T,$(filter %.lds,$^) $(filter %.o,$^) && \
+		       -T $(filter %.lds,$^) $(filter %.o,$^) && \
 		 sh $(srctree)/$(src)/checkundef.sh '$(NM)' '$@'
 
-VDSO_LDFLAGS = -fPIC -shared $(call cc-ldoption, -Wl$(comma)--hash-style=both) \
-	$(call cc-ldoption, -Wl$(comma)--build-id) -Wl,-Bsymbolic $(LTO_CFLAGS)
+VDSO_LDFLAGS = -shared $(call ld-option, --hash-style=both) \
+	$(call ld-option, --build-id) -Bsymbolic
 GCOV_PROFILE := n
 
 #
-- 
cgit v1.2.3


From 6fc92c33854b7844745ce424e1cb8029c06d1cf1 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:46 -0400
Subject: bnxt_en: Update firmware interface version to 1.9.2.25.

New interface has firmware core dump support, new extended port
statistics, and IF state change notifications to the firmware.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |    4 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c |    8 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |    6 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h     | 1227 +++++++++++++++------
 4 files changed, 924 insertions(+), 321 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 934aa11c82eb..3b5a55ce11ea 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -12,11 +12,11 @@
 #define BNXT_H
 
 #define DRV_MODULE_NAME		"bnxt_en"
-#define DRV_MODULE_VERSION	"1.9.1"
+#define DRV_MODULE_VERSION	"1.9.2"
 
 #define DRV_VER_MAJ	1
 #define DRV_VER_MIN	9
-#define DRV_VER_UPD	1
+#define DRV_VER_UPD	2
 
 #include <linux/interrupt.h>
 #include <linux/rhashtable.h>
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 7bd96ab4f7c5..f3b9fbcc705b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -29,7 +29,7 @@ static const struct bnxt_dl_nvm_param nvm_params[] = {
 static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 			     int msg_len, union devlink_param_value *val)
 {
-	struct hwrm_nvm_variable_input *req = msg;
+	struct hwrm_nvm_get_variable_input *req = msg;
 	void *data_addr = NULL, *buf = NULL;
 	struct bnxt_dl_nvm_param nvm_param;
 	int bytesize, idx = 0, rc, i;
@@ -60,18 +60,18 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	if (!data_addr)
 		return -ENOMEM;
 
-	req->data_addr = cpu_to_le64(data_dma_addr);
+	req->dest_data_addr = cpu_to_le64(data_dma_addr);
 	req->data_len = cpu_to_le16(nvm_param.num_bits);
 	req->option_num = cpu_to_le16(nvm_param.offset);
 	req->index_0 = cpu_to_le16(idx);
 	if (idx)
 		req->dimensions = cpu_to_le16(1);
 
-	if (req->req_type == HWRM_NVM_SET_VARIABLE)
+	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE))
 		memcpy(data_addr, buf, bytesize);
 
 	rc = hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
-	if (!rc && req->req_type == HWRM_NVM_GET_VARIABLE)
+	if (!rc && req->req_type == cpu_to_le16(HWRM_NVM_GET_VARIABLE))
 		memcpy(buf, data_addr, bytesize);
 
 	dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 7270c8b0cef3..3d40e494614d 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -162,7 +162,7 @@ static const struct {
 	BNXT_RX_STATS_ENTRY(rx_128b_255b_frames),
 	BNXT_RX_STATS_ENTRY(rx_256b_511b_frames),
 	BNXT_RX_STATS_ENTRY(rx_512b_1023b_frames),
-	BNXT_RX_STATS_ENTRY(rx_1024b_1518_frames),
+	BNXT_RX_STATS_ENTRY(rx_1024b_1518b_frames),
 	BNXT_RX_STATS_ENTRY(rx_good_vlan_frames),
 	BNXT_RX_STATS_ENTRY(rx_1519b_2047b_frames),
 	BNXT_RX_STATS_ENTRY(rx_2048b_4095b_frames),
@@ -205,9 +205,9 @@ static const struct {
 	BNXT_TX_STATS_ENTRY(tx_128b_255b_frames),
 	BNXT_TX_STATS_ENTRY(tx_256b_511b_frames),
 	BNXT_TX_STATS_ENTRY(tx_512b_1023b_frames),
-	BNXT_TX_STATS_ENTRY(tx_1024b_1518_frames),
+	BNXT_TX_STATS_ENTRY(tx_1024b_1518b_frames),
 	BNXT_TX_STATS_ENTRY(tx_good_vlan_frames),
-	BNXT_TX_STATS_ENTRY(tx_1519b_2047_frames),
+	BNXT_TX_STATS_ENTRY(tx_1519b_2047b_frames),
 	BNXT_TX_STATS_ENTRY(tx_2048b_4095b_frames),
 	BNXT_TX_STATS_ENTRY(tx_4096b_9216b_frames),
 	BNXT_TX_STATS_ENTRY(tx_9217b_16383b_frames),
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index c75d7fa6dab6..971ace5d0d4a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -96,6 +96,7 @@ struct hwrm_short_input {
 struct cmd_nums {
 	__le16	req_type;
 	#define HWRM_VER_GET                              0x0UL
+	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
 	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
 	#define HWRM_FUNC_VF_CFG                          0xfUL
 	#define HWRM_RESERVED1                            0x10UL
@@ -159,6 +160,7 @@ struct cmd_nums {
 	#define HWRM_RING_FREE                            0x51UL
 	#define HWRM_RING_CMPL_RING_QAGGINT_PARAMS        0x52UL
 	#define HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS     0x53UL
+	#define HWRM_RING_AGGINT_QCAPS                    0x54UL
 	#define HWRM_RING_RESET                           0x5eUL
 	#define HWRM_RING_GRP_ALLOC                       0x60UL
 	#define HWRM_RING_GRP_FREE                        0x61UL
@@ -191,6 +193,8 @@ struct cmd_nums {
 	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
 	#define HWRM_FW_RESET                             0xc0UL
 	#define HWRM_FW_QSTATUS                           0xc1UL
+	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
+	#define HWRM_FW_SYNC                              0xc3UL
 	#define HWRM_FW_SET_TIME                          0xc8UL
 	#define HWRM_FW_GET_TIME                          0xc9UL
 	#define HWRM_FW_SET_STRUCTURED_DATA               0xcaUL
@@ -269,6 +273,11 @@ struct cmd_nums {
 	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
 	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
 	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
+	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
+	#define HWRM_FUNC_BACKING_STORE_CFG               0x193UL
+	#define HWRM_FUNC_BACKING_STORE_QCFG              0x194UL
+	#define HWRM_FUNC_VF_BW_CFG                       0x195UL
+	#define HWRM_FUNC_VF_BW_QCFG                      0x196UL
 	#define HWRM_SELFTEST_QLIST                       0x200UL
 	#define HWRM_SELFTEST_EXEC                        0x201UL
 	#define HWRM_SELFTEST_IRQ                         0x202UL
@@ -284,6 +293,8 @@ struct cmd_nums {
 	#define HWRM_DBG_COREDUMP_LIST                    0xff17UL
 	#define HWRM_DBG_COREDUMP_INITIATE                0xff18UL
 	#define HWRM_DBG_COREDUMP_RETRIEVE                0xff19UL
+	#define HWRM_DBG_FW_CLI                           0xff1aUL
+	#define HWRM_DBG_I2C_CMD                          0xff1bUL
 	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
 	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
 	#define HWRM_NVM_FLUSH                            0xfff0UL
@@ -318,6 +329,7 @@ struct ret_codes {
 	#define HWRM_ERR_CODE_INVALID_ENABLES        0x6UL
 	#define HWRM_ERR_CODE_UNSUPPORTED_TLV        0x7UL
 	#define HWRM_ERR_CODE_NO_BUFFER              0x8UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR 0x9UL
 	#define HWRM_ERR_CODE_HWRM_ERROR             0xfUL
 	#define HWRM_ERR_CODE_UNKNOWN_ERR            0xfffeUL
 	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED      0xffffUL
@@ -344,9 +356,9 @@ struct hwrm_err_output {
 #define HWRM_RESP_VALID_KEY 1
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 9
-#define HWRM_VERSION_UPDATE 1
-#define HWRM_VERSION_RSVD 15
-#define HWRM_VERSION_STR "1.9.1.15"
+#define HWRM_VERSION_UPDATE 2
+#define HWRM_VERSION_RSVD 25
+#define HWRM_VERSION_STR "1.9.2.25"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -526,6 +538,7 @@ struct hwrm_async_event_cmpl {
 	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE   0x32UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE              0x33UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE            0x34UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE        0x35UL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                 0xffUL
 	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                      ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
 	__le32	event_data2;
@@ -564,6 +577,8 @@ struct hwrm_async_event_cmpl_link_status_change {
 	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT        1
 	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK    0xffff0UL
 	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT     4
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_MASK      0xff00000UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_SFT       20
 };
 
 /* hwrm_async_event_cmpl_port_conn_not_allowed (size:128b/16B) */
@@ -817,23 +832,26 @@ struct hwrm_func_qcaps_output {
 	__le16	fid;
 	__le16	port_id;
 	__le32	flags;
-	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED            0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING        0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                  0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED              0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED              0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED         0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED              0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED           0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED            0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED        0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED            0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED     0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED     0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED      0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED        0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED       0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED           0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED             0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING         0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                   0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED               0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED               0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED          0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED               0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED            0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED             0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED         0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED             0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED      0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED      0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED       0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED         0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED        0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED            0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED            0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED              0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED     0x80000UL
 	u8	mac_address[6];
 	__le16	max_rsscos_ctx;
 	__le16	max_cmpl_rings;
@@ -947,58 +965,26 @@ struct hwrm_func_qcfg_output {
 	#define FUNC_QCFG_RESP_EVB_MODE_VEPA   0x2UL
 	#define FUNC_QCFG_RESP_EVB_MODE_LAST  FUNC_QCFG_RESP_EVB_MODE_VEPA
 	u8	options;
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK    0x3UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT     0
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64   0x0UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128  0x1UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST     FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK              0xfcUL
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT               2
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST          FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT                    4
 	__le16	alloc_vfs;
 	__le32	alloc_mcast_filters;
 	__le32	alloc_hw_ring_grps;
 	__le16	alloc_sp_tx_rings;
 	__le16	alloc_stat_ctx;
-	u8	unused_2[7];
-	u8	valid;
-};
-
-/* hwrm_func_vlan_cfg_input (size:384b/48B) */
-struct hwrm_func_vlan_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[2];
-	__le32	enables;
-	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_VID      0x1UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_VID      0x2UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_PCP      0x4UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_PCP      0x8UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_STAG_TPID     0x10UL
-	#define FUNC_VLAN_CFG_REQ_ENABLES_CTAG_TPID     0x20UL
-	__le16	stag_vid;
-	u8	stag_pcp;
-	u8	unused_1;
-	__be16	stag_tpid;
-	__le16	ctag_vid;
-	u8	ctag_pcp;
-	u8	unused_2;
-	__be16	ctag_tpid;
-	__le32	rsvd1;
-	__le32	rsvd2;
-	u8	unused_3[4];
-};
-
-/* hwrm_func_vlan_cfg_output (size:128b/16B) */
-struct hwrm_func_vlan_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
+	__le16	alloc_msix;
+	u8	unused_2[5];
 	u8	valid;
 };
 
@@ -1010,7 +996,7 @@ struct hwrm_func_cfg_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le16	fid;
-	u8	unused_0[2];
+	__le16	num_msix;
 	__le32	flags;
 	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE     0x1UL
 	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE      0x2UL
@@ -1050,6 +1036,8 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_ENABLES_NUM_MCAST_FILTERS       0x40000UL
 	#define FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS        0x80000UL
 	#define FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE          0x100000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_MSIX                0x200000UL
+	#define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE        0x400000UL
 	__le16	mtu;
 	__le16	mru;
 	__le16	num_rsscos_ctxs;
@@ -1109,13 +1097,19 @@ struct hwrm_func_cfg_input {
 	#define FUNC_CFG_REQ_EVB_MODE_VEPA   0x2UL
 	#define FUNC_CFG_REQ_EVB_MODE_LAST  FUNC_CFG_REQ_EVB_MODE_VEPA
 	u8	options;
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK    0x3UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT     0
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64   0x0UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128  0x1UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST     FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK              0xfcUL
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT               2
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST          FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT                    4
 	__le16	num_mcast_filters;
 };
 
@@ -1212,30 +1206,6 @@ struct hwrm_func_vf_resc_free_output {
 	u8	valid;
 };
 
-/* hwrm_func_vf_vnic_ids_query_input (size:256b/32B) */
-struct hwrm_func_vf_vnic_ids_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	u8	unused_0[2];
-	__le32	max_vnic_id_cnt;
-	__le64	vnic_id_tbl_addr;
-};
-
-/* hwrm_func_vf_vnic_ids_query_output (size:128b/16B) */
-struct hwrm_func_vf_vnic_ids_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	vnic_id_cnt;
-	u8	unused_0[3];
-	u8	valid;
-};
-
 /* hwrm_func_drv_rgtr_input (size:896b/112B) */
 struct hwrm_func_drv_rgtr_input {
 	__le16	req_type;
@@ -1286,7 +1256,9 @@ struct hwrm_func_drv_rgtr_output {
 	__le16	req_type;
 	__le16	seq_id;
 	__le16	resp_len;
-	u8	unused_0[7];
+	__le32	flags;
+	#define FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED     0x1UL
+	u8	unused_0[3];
 	u8	valid;
 };
 
@@ -1372,7 +1344,7 @@ struct hwrm_func_drv_qver_input {
 	u8	unused_0[2];
 };
 
-/* hwrm_func_drv_qver_output (size:192b/24B) */
+/* hwrm_func_drv_qver_output (size:256b/32B) */
 struct hwrm_func_drv_qver_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -1394,12 +1366,13 @@ struct hwrm_func_drv_qver_output {
 	u8	ver_maj_8b;
 	u8	ver_min_8b;
 	u8	ver_upd_8b;
-	u8	unused_0[2];
-	u8	valid;
+	u8	unused_0[3];
 	__le16	ver_maj;
 	__le16	ver_min;
 	__le16	ver_upd;
 	__le16	ver_patch;
+	u8	unused_1[7];
+	u8	valid;
 };
 
 /* hwrm_func_resource_qcaps_input (size:192b/24B) */
@@ -1493,6 +1466,410 @@ struct hwrm_func_vf_resource_cfg_output {
 	u8	valid;
 };
 
+/* hwrm_func_backing_store_qcaps_input (size:128b/16B) */
+struct hwrm_func_backing_store_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_func_backing_store_qcaps_output (size:576b/72B) */
+struct hwrm_func_backing_store_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	qp_max_entries;
+	__le16	qp_min_qp1_entries;
+	__le16	qp_max_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_max_l2_entries;
+	__le32	srq_max_entries;
+	__le16	srq_entry_size;
+	__le16	cq_max_l2_entries;
+	__le32	cq_max_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_max_vnic_entries;
+	__le16	vnic_max_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le32	stat_max_entries;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le32	tqm_min_entries_per_ring;
+	__le32	tqm_max_entries_per_ring;
+	__le32	mrav_max_entries;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+	__le32	tim_max_entries;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_cfg_input (size:2048b/256B) */
+struct hwrm_func_backing_store_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE     0x1UL
+	__le32	enables;
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP            0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ           0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ            0x4UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC          0x8UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT          0x10UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP        0x20UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING0     0x40UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING1     0x80UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING2     0x100UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING3     0x200UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING4     0x400UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING5     0x800UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING6     0x1000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING7     0x2000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV          0x4000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM           0x8000UL
+	u8	qpc_pg_size_qpc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G
+	u8	srq_pg_size_srq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G
+	u8	cq_pg_size_cq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G
+	u8	vnic_pg_size_vnic_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G
+	u8	stat_pg_size_stat_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G
+	u8	tqm_sp_pg_size_tqm_sp_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G
+	u8	tqm_ring0_pg_size_tqm_ring0_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G
+	u8	tqm_ring1_pg_size_tqm_ring1_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G
+	u8	tqm_ring2_pg_size_tqm_ring2_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G
+	u8	tqm_ring3_pg_size_tqm_ring3_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G
+	u8	tqm_ring4_pg_size_tqm_ring4_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G
+	u8	tqm_ring5_pg_size_tqm_ring5_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G
+	u8	tqm_ring6_pg_size_tqm_ring6_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G
+	u8	tqm_ring7_pg_size_tqm_ring7_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G
+	u8	mrav_pg_size_mrav_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G
+	u8	tim_pg_size_tim_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G
+	__le64	qpc_page_dir;
+	__le64	srq_page_dir;
+	__le64	cq_page_dir;
+	__le64	vnic_page_dir;
+	__le64	stat_page_dir;
+	__le64	tqm_sp_page_dir;
+	__le64	tqm_ring0_page_dir;
+	__le64	tqm_ring1_page_dir;
+	__le64	tqm_ring2_page_dir;
+	__le64	tqm_ring3_page_dir;
+	__le64	tqm_ring4_page_dir;
+	__le64	tqm_ring5_page_dir;
+	__le64	tqm_ring6_page_dir;
+	__le64	tqm_ring7_page_dir;
+	__le64	mrav_page_dir;
+	__le64	tim_page_dir;
+	__le32	qp_num_entries;
+	__le32	srq_num_entries;
+	__le32	cq_num_entries;
+	__le32	stat_num_entries;
+	__le32	tqm_sp_num_entries;
+	__le32	tqm_ring0_num_entries;
+	__le32	tqm_ring1_num_entries;
+	__le32	tqm_ring2_num_entries;
+	__le32	tqm_ring3_num_entries;
+	__le32	tqm_ring4_num_entries;
+	__le32	tqm_ring5_num_entries;
+	__le32	tqm_ring6_num_entries;
+	__le32	tqm_ring7_num_entries;
+	__le32	mrav_num_entries;
+	__le32	tim_num_entries;
+	__le16	qp_num_qp1_entries;
+	__le16	qp_num_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_num_l2_entries;
+	__le16	srq_entry_size;
+	__le16	cq_num_l2_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_num_vnic_entries;
+	__le16	vnic_num_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+};
+
+/* hwrm_func_backing_store_cfg_output (size:128b/16B) */
+struct hwrm_func_backing_store_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_if_change_input (size:192b/24B) */
+struct hwrm_func_drv_if_change_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP     0x1UL
+	__le32	unused;
+};
+
+/* hwrm_func_drv_if_change_output (size:128b/16B) */
+struct hwrm_func_drv_if_change_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE     0x1UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
 /* hwrm_port_phy_cfg_input (size:448b/56B) */
 struct hwrm_port_phy_cfg_input {
 	__le16	req_type;
@@ -1592,10 +1969,11 @@ struct hwrm_port_phy_cfg_input {
 	#define PORT_PHY_CFG_REQ_WIRESPEED_ON  0x1UL
 	#define PORT_PHY_CFG_REQ_WIRESPEED_LAST PORT_PHY_CFG_REQ_WIRESPEED_ON
 	u8	lpbk;
-	#define PORT_PHY_CFG_REQ_LPBK_NONE   0x0UL
-	#define PORT_PHY_CFG_REQ_LPBK_LOCAL  0x1UL
-	#define PORT_PHY_CFG_REQ_LPBK_REMOTE 0x2UL
-	#define PORT_PHY_CFG_REQ_LPBK_LAST  PORT_PHY_CFG_REQ_LPBK_REMOTE
+	#define PORT_PHY_CFG_REQ_LPBK_NONE     0x0UL
+	#define PORT_PHY_CFG_REQ_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_CFG_REQ_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_CFG_REQ_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_CFG_REQ_LPBK_LAST    PORT_PHY_CFG_REQ_LPBK_EXTERNAL
 	u8	force_pause;
 	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_TX     0x1UL
 	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_RX     0x2UL
@@ -1751,10 +2129,11 @@ struct hwrm_port_phy_qcfg_output {
 	#define PORT_PHY_QCFG_RESP_WIRESPEED_ON  0x1UL
 	#define PORT_PHY_QCFG_RESP_WIRESPEED_LAST PORT_PHY_QCFG_RESP_WIRESPEED_ON
 	u8	lpbk;
-	#define PORT_PHY_QCFG_RESP_LPBK_NONE   0x0UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL  0x1UL
-	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE 0x2UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LAST  PORT_PHY_QCFG_RESP_LPBK_REMOTE
+	#define PORT_PHY_QCFG_RESP_LPBK_NONE     0x0UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_QCFG_RESP_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LAST    PORT_PHY_QCFG_RESP_LPBK_EXTERNAL
 	u8	force_pause;
 	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX     0x1UL
 	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX     0x2UL
@@ -2014,6 +2393,131 @@ struct hwrm_port_mac_ptp_qcfg_output {
 	u8	valid;
 };
 
+/* tx_port_stats (size:3264b/408B) */
+struct tx_port_stats {
+	__le64	tx_64b_frames;
+	__le64	tx_65b_127b_frames;
+	__le64	tx_128b_255b_frames;
+	__le64	tx_256b_511b_frames;
+	__le64	tx_512b_1023b_frames;
+	__le64	tx_1024b_1518b_frames;
+	__le64	tx_good_vlan_frames;
+	__le64	tx_1519b_2047b_frames;
+	__le64	tx_2048b_4095b_frames;
+	__le64	tx_4096b_9216b_frames;
+	__le64	tx_9217b_16383b_frames;
+	__le64	tx_good_frames;
+	__le64	tx_total_frames;
+	__le64	tx_ucast_frames;
+	__le64	tx_mcast_frames;
+	__le64	tx_bcast_frames;
+	__le64	tx_pause_frames;
+	__le64	tx_pfc_frames;
+	__le64	tx_jabber_frames;
+	__le64	tx_fcs_err_frames;
+	__le64	tx_control_frames;
+	__le64	tx_oversz_frames;
+	__le64	tx_single_dfrl_frames;
+	__le64	tx_multi_dfrl_frames;
+	__le64	tx_single_coll_frames;
+	__le64	tx_multi_coll_frames;
+	__le64	tx_late_coll_frames;
+	__le64	tx_excessive_coll_frames;
+	__le64	tx_frag_frames;
+	__le64	tx_err;
+	__le64	tx_tagged_frames;
+	__le64	tx_dbl_tagged_frames;
+	__le64	tx_runt_frames;
+	__le64	tx_fifo_underruns;
+	__le64	tx_pfc_ena_frames_pri0;
+	__le64	tx_pfc_ena_frames_pri1;
+	__le64	tx_pfc_ena_frames_pri2;
+	__le64	tx_pfc_ena_frames_pri3;
+	__le64	tx_pfc_ena_frames_pri4;
+	__le64	tx_pfc_ena_frames_pri5;
+	__le64	tx_pfc_ena_frames_pri6;
+	__le64	tx_pfc_ena_frames_pri7;
+	__le64	tx_eee_lpi_events;
+	__le64	tx_eee_lpi_duration;
+	__le64	tx_llfc_logical_msgs;
+	__le64	tx_hcfc_msgs;
+	__le64	tx_total_collisions;
+	__le64	tx_bytes;
+	__le64	tx_xthol_frames;
+	__le64	tx_stat_discard;
+	__le64	tx_stat_error;
+};
+
+/* rx_port_stats (size:4224b/528B) */
+struct rx_port_stats {
+	__le64	rx_64b_frames;
+	__le64	rx_65b_127b_frames;
+	__le64	rx_128b_255b_frames;
+	__le64	rx_256b_511b_frames;
+	__le64	rx_512b_1023b_frames;
+	__le64	rx_1024b_1518b_frames;
+	__le64	rx_good_vlan_frames;
+	__le64	rx_1519b_2047b_frames;
+	__le64	rx_2048b_4095b_frames;
+	__le64	rx_4096b_9216b_frames;
+	__le64	rx_9217b_16383b_frames;
+	__le64	rx_total_frames;
+	__le64	rx_ucast_frames;
+	__le64	rx_mcast_frames;
+	__le64	rx_bcast_frames;
+	__le64	rx_fcs_err_frames;
+	__le64	rx_ctrl_frames;
+	__le64	rx_pause_frames;
+	__le64	rx_pfc_frames;
+	__le64	rx_unsupported_opcode_frames;
+	__le64	rx_unsupported_da_pausepfc_frames;
+	__le64	rx_wrong_sa_frames;
+	__le64	rx_align_err_frames;
+	__le64	rx_oor_len_frames;
+	__le64	rx_code_err_frames;
+	__le64	rx_false_carrier_frames;
+	__le64	rx_ovrsz_frames;
+	__le64	rx_jbr_frames;
+	__le64	rx_mtu_err_frames;
+	__le64	rx_match_crc_frames;
+	__le64	rx_promiscuous_frames;
+	__le64	rx_tagged_frames;
+	__le64	rx_double_tagged_frames;
+	__le64	rx_trunc_frames;
+	__le64	rx_good_frames;
+	__le64	rx_pfc_xon2xoff_frames_pri0;
+	__le64	rx_pfc_xon2xoff_frames_pri1;
+	__le64	rx_pfc_xon2xoff_frames_pri2;
+	__le64	rx_pfc_xon2xoff_frames_pri3;
+	__le64	rx_pfc_xon2xoff_frames_pri4;
+	__le64	rx_pfc_xon2xoff_frames_pri5;
+	__le64	rx_pfc_xon2xoff_frames_pri6;
+	__le64	rx_pfc_xon2xoff_frames_pri7;
+	__le64	rx_pfc_ena_frames_pri0;
+	__le64	rx_pfc_ena_frames_pri1;
+	__le64	rx_pfc_ena_frames_pri2;
+	__le64	rx_pfc_ena_frames_pri3;
+	__le64	rx_pfc_ena_frames_pri4;
+	__le64	rx_pfc_ena_frames_pri5;
+	__le64	rx_pfc_ena_frames_pri6;
+	__le64	rx_pfc_ena_frames_pri7;
+	__le64	rx_sch_crc_err_frames;
+	__le64	rx_undrsz_frames;
+	__le64	rx_frag_frames;
+	__le64	rx_eee_lpi_events;
+	__le64	rx_eee_lpi_duration;
+	__le64	rx_llfc_physical_msgs;
+	__le64	rx_llfc_logical_msgs;
+	__le64	rx_llfc_msgs_with_crc_err;
+	__le64	rx_hcfc_msgs;
+	__le64	rx_hcfc_msgs_with_crc_err;
+	__le64	rx_bytes;
+	__le64	rx_runt_bytes;
+	__le64	rx_runt_frames;
+	__le64	rx_stat_discard;
+	__le64	rx_stat_err;
+};
+
 /* hwrm_port_qstats_input (size:320b/40B) */
 struct hwrm_port_qstats_input {
 	__le16	req_type;
@@ -2039,6 +2543,83 @@ struct hwrm_port_qstats_output {
 	u8	valid;
 };
 
+/* tx_port_stats_ext (size:2048b/256B) */
+struct tx_port_stats_ext {
+	__le64	tx_bytes_cos0;
+	__le64	tx_bytes_cos1;
+	__le64	tx_bytes_cos2;
+	__le64	tx_bytes_cos3;
+	__le64	tx_bytes_cos4;
+	__le64	tx_bytes_cos5;
+	__le64	tx_bytes_cos6;
+	__le64	tx_bytes_cos7;
+	__le64	tx_packets_cos0;
+	__le64	tx_packets_cos1;
+	__le64	tx_packets_cos2;
+	__le64	tx_packets_cos3;
+	__le64	tx_packets_cos4;
+	__le64	tx_packets_cos5;
+	__le64	tx_packets_cos6;
+	__le64	tx_packets_cos7;
+	__le64	pfc_pri0_tx_duration_us;
+	__le64	pfc_pri0_tx_transitions;
+	__le64	pfc_pri1_tx_duration_us;
+	__le64	pfc_pri1_tx_transitions;
+	__le64	pfc_pri2_tx_duration_us;
+	__le64	pfc_pri2_tx_transitions;
+	__le64	pfc_pri3_tx_duration_us;
+	__le64	pfc_pri3_tx_transitions;
+	__le64	pfc_pri4_tx_duration_us;
+	__le64	pfc_pri4_tx_transitions;
+	__le64	pfc_pri5_tx_duration_us;
+	__le64	pfc_pri5_tx_transitions;
+	__le64	pfc_pri6_tx_duration_us;
+	__le64	pfc_pri6_tx_transitions;
+	__le64	pfc_pri7_tx_duration_us;
+	__le64	pfc_pri7_tx_transitions;
+};
+
+/* rx_port_stats_ext (size:2368b/296B) */
+struct rx_port_stats_ext {
+	__le64	link_down_events;
+	__le64	continuous_pause_events;
+	__le64	resume_pause_events;
+	__le64	continuous_roce_pause_events;
+	__le64	resume_roce_pause_events;
+	__le64	rx_bytes_cos0;
+	__le64	rx_bytes_cos1;
+	__le64	rx_bytes_cos2;
+	__le64	rx_bytes_cos3;
+	__le64	rx_bytes_cos4;
+	__le64	rx_bytes_cos5;
+	__le64	rx_bytes_cos6;
+	__le64	rx_bytes_cos7;
+	__le64	rx_packets_cos0;
+	__le64	rx_packets_cos1;
+	__le64	rx_packets_cos2;
+	__le64	rx_packets_cos3;
+	__le64	rx_packets_cos4;
+	__le64	rx_packets_cos5;
+	__le64	rx_packets_cos6;
+	__le64	rx_packets_cos7;
+	__le64	pfc_pri0_rx_duration_us;
+	__le64	pfc_pri0_rx_transitions;
+	__le64	pfc_pri1_rx_duration_us;
+	__le64	pfc_pri1_rx_transitions;
+	__le64	pfc_pri2_rx_duration_us;
+	__le64	pfc_pri2_rx_transitions;
+	__le64	pfc_pri3_rx_duration_us;
+	__le64	pfc_pri3_rx_transitions;
+	__le64	pfc_pri4_rx_duration_us;
+	__le64	pfc_pri4_rx_transitions;
+	__le64	pfc_pri5_rx_duration_us;
+	__le64	pfc_pri5_rx_transitions;
+	__le64	pfc_pri6_rx_duration_us;
+	__le64	pfc_pri6_rx_transitions;
+	__le64	pfc_pri7_rx_duration_us;
+	__le64	pfc_pri7_rx_transitions;
+};
+
 /* hwrm_port_qstats_ext_input (size:320b/40B) */
 struct hwrm_port_qstats_ext_input {
 	__le16	req_type;
@@ -2062,7 +2643,8 @@ struct hwrm_port_qstats_ext_output {
 	__le16	resp_len;
 	__le16	tx_stat_size;
 	__le16	rx_stat_size;
-	u8	unused_0[3];
+	__le16	total_active_cos_queues;
+	u8	unused_0;
 	u8	valid;
 };
 
@@ -2153,9 +2735,10 @@ struct hwrm_port_phy_qcaps_output {
 	__le16	seq_id;
 	__le16	resp_len;
 	u8	flags;
-	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED     0x1UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK        0xfeUL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT         1
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED               0x1UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED     0x2UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_MASK                  0xfcUL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_RSVD1_SFT                   2
 	u8	port_cnt;
 	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL
 	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1       0x1UL
@@ -2612,6 +3195,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id0;
 	u8	queue_id0_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2620,6 +3204,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id1;
 	u8	queue_id1_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2628,6 +3213,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id2;
 	u8	queue_id2_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2636,6 +3222,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id3;
 	u8	queue_id3_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2644,6 +3231,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id4;
 	u8	queue_id4_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2652,6 +3240,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id5;
 	u8	queue_id5_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2660,6 +3249,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id6;
 	u8	queue_id6_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -2668,6 +3258,7 @@ struct hwrm_queue_qportcfg_output {
 	u8	queue_id7;
 	u8	queue_id7_service_profile;
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS       0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
 	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
@@ -3689,18 +4280,21 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE                     0x20UL
 	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE     0x40UL
 	__le32	enables;
-	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP     0x1UL
-	#define VNIC_CFG_REQ_ENABLES_RSS_RULE          0x2UL
-	#define VNIC_CFG_REQ_ENABLES_COS_RULE          0x4UL
-	#define VNIC_CFG_REQ_ENABLES_LB_RULE           0x8UL
-	#define VNIC_CFG_REQ_ENABLES_MRU               0x10UL
+	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP            0x1UL
+	#define VNIC_CFG_REQ_ENABLES_RSS_RULE                 0x2UL
+	#define VNIC_CFG_REQ_ENABLES_COS_RULE                 0x4UL
+	#define VNIC_CFG_REQ_ENABLES_LB_RULE                  0x8UL
+	#define VNIC_CFG_REQ_ENABLES_MRU                      0x10UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID       0x20UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID     0x40UL
 	__le16	vnic_id;
 	__le16	dflt_ring_grp;
 	__le16	rss_rule;
 	__le16	cos_rule;
 	__le16	lb_rule;
 	__le16	mru;
-	u8	unused_0[4];
+	__le16	default_rx_ring_id;
+	__le16	default_cmpl_ring_id;
 };
 
 /* hwrm_vnic_cfg_output (size:128b/16B) */
@@ -3740,6 +4334,7 @@ struct hwrm_vnic_qcaps_output {
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP                  0x10UL
 	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP                     0x20UL
 	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP     0x40UL
+	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP                   0x80UL
 	u8	unused_1[7];
 	u8	valid;
 };
@@ -3857,7 +4452,14 @@ struct hwrm_vnic_rss_cfg_input {
 	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6         0x8UL
 	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6     0x10UL
 	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6     0x20UL
-	u8	unused_0[4];
+	__le16	vnic_id;
+	u8	ring_table_pair_index;
+	u8	hash_mode_flags;
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT         0x1UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
 	__le64	ring_grp_tbl_addr;
 	__le64	hash_key_tbl_addr;
 	__le16	rss_ctx_idx;
@@ -3950,7 +4552,7 @@ struct hwrm_vnic_rss_cos_lb_ctx_free_output {
 	u8	valid;
 };
 
-/* hwrm_ring_alloc_input (size:640b/80B) */
+/* hwrm_ring_alloc_input (size:704b/88B) */
 struct hwrm_ring_alloc_input {
 	__le16	req_type;
 	__le16	cmpl_ring;
@@ -3961,12 +4563,17 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG          0x2UL
 	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID     0x8UL
 	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID          0x20UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID      0x40UL
+	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID      0x80UL
+	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID     0x100UL
 	u8	ring_type;
 	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
 	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
 	#define RING_ALLOC_REQ_RING_TYPE_RX        0x2UL
 	#define RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL
+	#define RING_ALLOC_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_ALLOC_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_NQ
 	u8	unused_0[3];
 	__le64	page_tbl_addr;
 	__le32	fbo;
@@ -3977,8 +4584,9 @@ struct hwrm_ring_alloc_input {
 	__le16	logical_id;
 	__le16	cmpl_ring_id;
 	__le16	queue_id;
-	u8	unused_2[2];
-	__le32	reserved1;
+	__le16	rx_buf_size;
+	__le16	rx_ring_id;
+	__le16	nq_ring_id;
 	__le16	ring_arb_cfg;
 	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_MASK      0xfUL
 	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SFT       0
@@ -4016,6 +4624,7 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_INT_MODE_POLL   0x3UL
 	#define RING_ALLOC_REQ_INT_MODE_LAST  RING_ALLOC_REQ_INT_MODE_POLL
 	u8	unused_4[3];
+	__le64	cq_handle;
 };
 
 /* hwrm_ring_alloc_output (size:128b/16B) */
@@ -4042,7 +4651,9 @@ struct hwrm_ring_free_input {
 	#define RING_FREE_REQ_RING_TYPE_TX        0x1UL
 	#define RING_FREE_REQ_RING_TYPE_RX        0x2UL
 	#define RING_FREE_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_ROCE_CMPL
+	#define RING_FREE_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_FREE_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_NQ
 	u8	unused_0;
 	__le16	ring_id;
 	u8	unused_1[4];
@@ -4058,6 +4669,52 @@ struct hwrm_ring_free_output {
 	u8	valid;
 };
 
+/* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
+struct hwrm_ring_aggint_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_ring_aggint_qcaps_output (size:384b/48B) */
+struct hwrm_ring_aggint_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	cmpl_params;
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MIN                  0x1UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MAX                  0x2UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_TIMER_RESET                      0x4UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_RING_IDLE                        0x8UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR                0x10UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR_DURING_INT     0x20UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR                0x40UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR_DURING_INT     0x80UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_AGGR_INT                0x100UL
+	__le32	nq_params;
+	#define RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN     0x1UL
+	__le16	num_cmpl_dma_aggr_min;
+	__le16	num_cmpl_dma_aggr_max;
+	__le16	num_cmpl_dma_aggr_during_int_min;
+	__le16	num_cmpl_dma_aggr_during_int_max;
+	__le16	cmpl_aggr_dma_tmr_min;
+	__le16	cmpl_aggr_dma_tmr_max;
+	__le16	cmpl_aggr_dma_tmr_during_int_min;
+	__le16	cmpl_aggr_dma_tmr_during_int_max;
+	__le16	int_lat_tmr_min_min;
+	__le16	int_lat_tmr_min_max;
+	__le16	int_lat_tmr_max_min;
+	__le16	int_lat_tmr_max_max;
+	__le16	num_cmpl_aggr_int_min;
+	__le16	num_cmpl_aggr_int_max;
+	__le16	timer_units;
+	u8	unused_0[1];
+	u8	valid;
+};
+
 /* hwrm_ring_cmpl_ring_qaggint_params_input (size:192b/24B) */
 struct hwrm_ring_cmpl_ring_qaggint_params_input {
 	__le16	req_type;
@@ -4100,6 +4757,7 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
 	__le16	flags;
 	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET     0x1UL
 	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE       0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ           0x4UL
 	__le16	num_cmpl_dma_aggr;
 	__le16	num_cmpl_dma_aggr_during_int;
 	__le16	cmpl_aggr_dma_tmr;
@@ -4107,7 +4765,14 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
 	__le16	int_lat_tmr_min;
 	__le16	int_lat_tmr_max;
 	__le16	num_cmpl_aggr_int;
-	u8	unused_0[6];
+	__le16	enables;
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR                0x1UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR_DURING_INT     0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_CMPL_AGGR_DMA_TMR                0x4UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MIN                  0x8UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MAX                  0x10UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_AGGR_INT                0x20UL
+	u8	unused_0[4];
 };
 
 /* hwrm_ring_cmpl_ring_cfg_aggint_params_output (size:128b/16B) */
@@ -4120,34 +4785,6 @@ struct hwrm_ring_cmpl_ring_cfg_aggint_params_output {
 	u8	valid;
 };
 
-/* hwrm_ring_reset_input (size:192b/24B) */
-struct hwrm_ring_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define RING_RESET_REQ_RING_TYPE_L2_CMPL   0x0UL
-	#define RING_RESET_REQ_RING_TYPE_TX        0x1UL
-	#define RING_RESET_REQ_RING_TYPE_RX        0x2UL
-	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_RESET_REQ_RING_TYPE_LAST     RING_RESET_REQ_RING_TYPE_ROCE_CMPL
-	u8	unused_0;
-	__le16	ring_id;
-	u8	unused_1[4];
-};
-
-/* hwrm_ring_reset_output (size:128b/16B) */
-struct hwrm_ring_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
 /* hwrm_ring_grp_alloc_input (size:192b/24B) */
 struct hwrm_ring_grp_alloc_input {
 	__le16	req_type;
@@ -5032,7 +5669,8 @@ struct hwrm_tunnel_dst_port_query_input {
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN    0x1UL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE   0x5UL
 	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1
 	u8	unused_0[7];
 };
 
@@ -5059,7 +5697,8 @@ struct hwrm_tunnel_dst_port_alloc_input {
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN    0x1UL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE   0x5UL
 	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1
 	u8	unused_0;
 	__be16	tunnel_dst_port_val;
 	u8	unused_1[4];
@@ -5087,7 +5726,8 @@ struct hwrm_tunnel_dst_port_free_input {
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN    0x1UL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE   0x5UL
 	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4 0x9UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1 0xaUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST    TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1
 	u8	unused_0;
 	__le16	tunnel_dst_port_id;
 	u8	unused_1[4];
@@ -5259,140 +5899,6 @@ struct hwrm_pcie_qstats_output {
 	u8	valid;
 };
 
-/* tx_port_stats (size:3264b/408B) */
-struct tx_port_stats {
-	__le64	tx_64b_frames;
-	__le64	tx_65b_127b_frames;
-	__le64	tx_128b_255b_frames;
-	__le64	tx_256b_511b_frames;
-	__le64	tx_512b_1023b_frames;
-	__le64	tx_1024b_1518_frames;
-	__le64	tx_good_vlan_frames;
-	__le64	tx_1519b_2047_frames;
-	__le64	tx_2048b_4095b_frames;
-	__le64	tx_4096b_9216b_frames;
-	__le64	tx_9217b_16383b_frames;
-	__le64	tx_good_frames;
-	__le64	tx_total_frames;
-	__le64	tx_ucast_frames;
-	__le64	tx_mcast_frames;
-	__le64	tx_bcast_frames;
-	__le64	tx_pause_frames;
-	__le64	tx_pfc_frames;
-	__le64	tx_jabber_frames;
-	__le64	tx_fcs_err_frames;
-	__le64	tx_control_frames;
-	__le64	tx_oversz_frames;
-	__le64	tx_single_dfrl_frames;
-	__le64	tx_multi_dfrl_frames;
-	__le64	tx_single_coll_frames;
-	__le64	tx_multi_coll_frames;
-	__le64	tx_late_coll_frames;
-	__le64	tx_excessive_coll_frames;
-	__le64	tx_frag_frames;
-	__le64	tx_err;
-	__le64	tx_tagged_frames;
-	__le64	tx_dbl_tagged_frames;
-	__le64	tx_runt_frames;
-	__le64	tx_fifo_underruns;
-	__le64	tx_pfc_ena_frames_pri0;
-	__le64	tx_pfc_ena_frames_pri1;
-	__le64	tx_pfc_ena_frames_pri2;
-	__le64	tx_pfc_ena_frames_pri3;
-	__le64	tx_pfc_ena_frames_pri4;
-	__le64	tx_pfc_ena_frames_pri5;
-	__le64	tx_pfc_ena_frames_pri6;
-	__le64	tx_pfc_ena_frames_pri7;
-	__le64	tx_eee_lpi_events;
-	__le64	tx_eee_lpi_duration;
-	__le64	tx_llfc_logical_msgs;
-	__le64	tx_hcfc_msgs;
-	__le64	tx_total_collisions;
-	__le64	tx_bytes;
-	__le64	tx_xthol_frames;
-	__le64	tx_stat_discard;
-	__le64	tx_stat_error;
-};
-
-/* rx_port_stats (size:4224b/528B) */
-struct rx_port_stats {
-	__le64	rx_64b_frames;
-	__le64	rx_65b_127b_frames;
-	__le64	rx_128b_255b_frames;
-	__le64	rx_256b_511b_frames;
-	__le64	rx_512b_1023b_frames;
-	__le64	rx_1024b_1518_frames;
-	__le64	rx_good_vlan_frames;
-	__le64	rx_1519b_2047b_frames;
-	__le64	rx_2048b_4095b_frames;
-	__le64	rx_4096b_9216b_frames;
-	__le64	rx_9217b_16383b_frames;
-	__le64	rx_total_frames;
-	__le64	rx_ucast_frames;
-	__le64	rx_mcast_frames;
-	__le64	rx_bcast_frames;
-	__le64	rx_fcs_err_frames;
-	__le64	rx_ctrl_frames;
-	__le64	rx_pause_frames;
-	__le64	rx_pfc_frames;
-	__le64	rx_unsupported_opcode_frames;
-	__le64	rx_unsupported_da_pausepfc_frames;
-	__le64	rx_wrong_sa_frames;
-	__le64	rx_align_err_frames;
-	__le64	rx_oor_len_frames;
-	__le64	rx_code_err_frames;
-	__le64	rx_false_carrier_frames;
-	__le64	rx_ovrsz_frames;
-	__le64	rx_jbr_frames;
-	__le64	rx_mtu_err_frames;
-	__le64	rx_match_crc_frames;
-	__le64	rx_promiscuous_frames;
-	__le64	rx_tagged_frames;
-	__le64	rx_double_tagged_frames;
-	__le64	rx_trunc_frames;
-	__le64	rx_good_frames;
-	__le64	rx_pfc_xon2xoff_frames_pri0;
-	__le64	rx_pfc_xon2xoff_frames_pri1;
-	__le64	rx_pfc_xon2xoff_frames_pri2;
-	__le64	rx_pfc_xon2xoff_frames_pri3;
-	__le64	rx_pfc_xon2xoff_frames_pri4;
-	__le64	rx_pfc_xon2xoff_frames_pri5;
-	__le64	rx_pfc_xon2xoff_frames_pri6;
-	__le64	rx_pfc_xon2xoff_frames_pri7;
-	__le64	rx_pfc_ena_frames_pri0;
-	__le64	rx_pfc_ena_frames_pri1;
-	__le64	rx_pfc_ena_frames_pri2;
-	__le64	rx_pfc_ena_frames_pri3;
-	__le64	rx_pfc_ena_frames_pri4;
-	__le64	rx_pfc_ena_frames_pri5;
-	__le64	rx_pfc_ena_frames_pri6;
-	__le64	rx_pfc_ena_frames_pri7;
-	__le64	rx_sch_crc_err_frames;
-	__le64	rx_undrsz_frames;
-	__le64	rx_frag_frames;
-	__le64	rx_eee_lpi_events;
-	__le64	rx_eee_lpi_duration;
-	__le64	rx_llfc_physical_msgs;
-	__le64	rx_llfc_logical_msgs;
-	__le64	rx_llfc_msgs_with_crc_err;
-	__le64	rx_hcfc_msgs;
-	__le64	rx_hcfc_msgs_with_crc_err;
-	__le64	rx_bytes;
-	__le64	rx_runt_bytes;
-	__le64	rx_runt_frames;
-	__le64	rx_stat_discard;
-	__le64	rx_stat_err;
-};
-
-/* rx_port_stats_ext (size:320b/40B) */
-struct rx_port_stats_ext {
-	__le64	link_down_events;
-	__le64	continuous_pause_events;
-	__le64	resume_pause_events;
-	__le64	continuous_roce_pause_events;
-	__le64	resume_roce_pause_events;
-};
-
 /* pcie_ctx_hw_stats (size:768b/96B) */
 struct pcie_ctx_hw_stats {
 	__le64	pcie_pl_signal_integrity;
@@ -5884,6 +6390,114 @@ struct hwrm_wol_reason_qcfg_output {
 	u8	valid;
 };
 
+/* coredump_segment_record (size:128b/16B) */
+struct coredump_segment_record {
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	max_instances;
+	u8	version_hi;
+	u8	version_low;
+	u8	seg_flags;
+	u8	unused_0[7];
+};
+
+/* hwrm_dbg_coredump_list_input (size:256b/32B) */
+struct hwrm_dbg_coredump_list_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le16	seq_no;
+	u8	unused_0[2];
+};
+
+/* hwrm_dbg_coredump_list_output (size:128b/16B) */
+struct hwrm_dbg_coredump_list_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_LIST_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	total_segments;
+	__le16	data_len;
+	u8	unused_1;
+	u8	valid;
+};
+
+/* hwrm_dbg_coredump_initiate_input (size:256b/32B) */
+struct hwrm_dbg_coredump_initiate_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_0;
+	u8	seg_flags;
+	u8	unused_1[7];
+};
+
+/* hwrm_dbg_coredump_initiate_output (size:128b/16B) */
+struct hwrm_dbg_coredump_initiate_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* coredump_data_hdr (size:128b/16B) */
+struct coredump_data_hdr {
+	__le32	address;
+	__le32	flags_length;
+	__le32	instance;
+	__le32	next_offset;
+};
+
+/* hwrm_dbg_coredump_retrieve_input (size:448b/56B) */
+struct hwrm_dbg_coredump_retrieve_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le32	unused_0;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_1;
+	u8	seg_flags;
+	u8	unused_2;
+	__le16	unused_3;
+	__le32	unused_4;
+	__le32	seq_no;
+	__le32	unused_5;
+};
+
+/* hwrm_dbg_coredump_retrieve_output (size:128b/16B) */
+struct hwrm_dbg_coredump_retrieve_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_RETRIEVE_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	data_len;
+	u8	unused_1[3];
+	u8	valid;
+};
+
 /* hwrm_nvm_read_input (size:320b/40B) */
 struct hwrm_nvm_read_input {
 	__le16	req_type;
@@ -6201,19 +6815,6 @@ struct hwrm_nvm_install_update_cmd_err {
 	u8	unused_0[7];
 };
 
-struct hwrm_nvm_variable_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	data_addr;
-	__le16	data_len;
-	__le16	option_num;
-	__le16	dimensions;
-	__le16	index_0;
-};
-
 /* hwrm_nvm_get_variable_input (size:320b/40B) */
 struct hwrm_nvm_get_variable_input {
 	__le16	req_type;
@@ -6282,12 +6883,14 @@ struct hwrm_nvm_set_variable_input {
 	__le16	index_2;
 	__le16	index_3;
 	u8	flags;
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH           0x1UL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK     0xeUL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT      1
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE       (0x0UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1  (0x1UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST      NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH                0x1UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK          0xeUL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT           1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE            (0x0UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1       (0x1UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256          (0x2UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH  (0x3UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST           NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH
 	u8	unused_0;
 };
 
-- 
cgit v1.2.3


From e795892e93b6ccbda7e0f0fc476d0d4629b44f84 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:47 -0400
Subject: bnxt_en: Adjust timer based on ethtool stats-block-usecs settings.

The driver gathers statistics using 2 mechanisms.  Some stats are DMA'ed
directly from hardware and others are polled from the driver's timer.
Currently, we only adjust the DMA frequency based on the ethtool
stats-block-usecs setting.  This patch adjusts the driver's timer
frequency as well to make everything consistent.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 3d40e494614d..1f626afb2118 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -112,6 +112,11 @@ static int bnxt_set_coalesce(struct net_device *dev,
 					      BNXT_MAX_STATS_COAL_TICKS);
 		stats_ticks = rounddown(stats_ticks, BNXT_MIN_STATS_COAL_TICKS);
 		bp->stats_coal_ticks = stats_ticks;
+		if (bp->stats_coal_ticks)
+			bp->current_interval =
+				bp->stats_coal_ticks * HZ / 1000000;
+		else
+			bp->current_interval = BNXT_TIMER_INTERVAL;
 		update_stats = true;
 	}
 
-- 
cgit v1.2.3


From 55fd0cf320c3051f8dcb88c07ddd1e4c54b82cba Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:48 -0400
Subject: bnxt_en: Add external loopback test to ethtool selftest.

Add code to detect firmware support for external loopback and the extra
test entry for external loopback.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         |  4 +++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  2 ++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 32 ++++++++++++++++++-----
 3 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c612d74451a7..d9fc905c5996 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6337,6 +6337,10 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp)
 		bp->lpi_tmr_hi = le32_to_cpu(resp->valid_tx_lpi_timer_high) &
 				 PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK;
 	}
+	if (resp->flags & PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED) {
+		if (bp->test_info)
+			bp->test_info->flags |= BNXT_TEST_FL_EXT_LPBK;
+	}
 	if (resp->supported_speeds_auto_mode)
 		link_info->support_auto_speeds =
 			le16_to_cpu(resp->supported_speeds_auto_mode);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 3b5a55ce11ea..0d49fe015ba9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -990,6 +990,8 @@ struct bnxt_led_info {
 
 struct bnxt_test_info {
 	u8 offline_mask;
+	u8 flags;
+#define BNXT_TEST_FL_EXT_LPBK	0x1
 	u16 timeout;
 	char string[BNXT_MAX_TEST][ETH_GSTRING_LEN];
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 1f626afb2118..9517633f947a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2397,7 +2397,7 @@ static int bnxt_disable_an_for_lpbk(struct bnxt *bp,
 	return rc;
 }
 
-static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable)
+static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable, bool ext)
 {
 	struct hwrm_port_phy_cfg_input req = {0};
 
@@ -2405,7 +2405,10 @@ static int bnxt_hwrm_phy_loopback(struct bnxt *bp, bool enable)
 
 	if (enable) {
 		bnxt_disable_an_for_lpbk(bp, &req);
-		req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
+		if (ext)
+			req.lpbk = PORT_PHY_CFG_REQ_LPBK_EXTERNAL;
+		else
+			req.lpbk = PORT_PHY_CFG_REQ_LPBK_LOCAL;
 	} else {
 		req.lpbk = PORT_PHY_CFG_REQ_LPBK_NONE;
 	}
@@ -2538,15 +2541,17 @@ static int bnxt_run_fw_tests(struct bnxt *bp, u8 test_mask, u8 *test_results)
 	return rc;
 }
 
-#define BNXT_DRV_TESTS			3
+#define BNXT_DRV_TESTS			4
 #define BNXT_MACLPBK_TEST_IDX		(bp->num_tests - BNXT_DRV_TESTS)
 #define BNXT_PHYLPBK_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 1)
-#define BNXT_IRQ_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 2)
+#define BNXT_EXTLPBK_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 2)
+#define BNXT_IRQ_TEST_IDX		(BNXT_MACLPBK_TEST_IDX + 3)
 
 static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 			   u64 *buf)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	bool do_ext_lpbk = false;
 	bool offline = false;
 	u8 test_results = 0;
 	u8 test_mask = 0;
@@ -2560,6 +2565,10 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 		return;
 	}
 
+	if ((etest->flags & ETH_TEST_FL_EXTERNAL_LB) &&
+	    (bp->test_info->flags & BNXT_TEST_FL_EXT_LPBK))
+		do_ext_lpbk = true;
+
 	if (etest->flags & ETH_TEST_FL_OFFLINE) {
 		if (bp->pf.active_vfs) {
 			etest->flags |= ETH_TEST_FL_FAILED;
@@ -2600,13 +2609,22 @@ static void bnxt_self_test(struct net_device *dev, struct ethtool_test *etest,
 			buf[BNXT_MACLPBK_TEST_IDX] = 0;
 
 		bnxt_hwrm_mac_loopback(bp, false);
-		bnxt_hwrm_phy_loopback(bp, true);
+		bnxt_hwrm_phy_loopback(bp, true, false);
 		msleep(1000);
 		if (bnxt_run_loopback(bp)) {
 			buf[BNXT_PHYLPBK_TEST_IDX] = 1;
 			etest->flags |= ETH_TEST_FL_FAILED;
 		}
-		bnxt_hwrm_phy_loopback(bp, false);
+		if (do_ext_lpbk) {
+			etest->flags |= ETH_TEST_FL_EXTERNAL_LB_DONE;
+			bnxt_hwrm_phy_loopback(bp, true, true);
+			msleep(1000);
+			if (bnxt_run_loopback(bp)) {
+				buf[BNXT_EXTLPBK_TEST_IDX] = 1;
+				etest->flags |= ETH_TEST_FL_FAILED;
+			}
+		}
+		bnxt_hwrm_phy_loopback(bp, false, false);
 		bnxt_half_close_nic(bp);
 		bnxt_open_nic(bp, false, true);
 	}
@@ -2707,6 +2725,8 @@ void bnxt_ethtool_init(struct bnxt *bp)
 			strcpy(str, "Mac loopback test (offline)");
 		} else if (i == BNXT_PHYLPBK_TEST_IDX) {
 			strcpy(str, "Phy loopback test (offline)");
+		} else if (i == BNXT_EXTLPBK_TEST_IDX) {
+			strcpy(str, "Ext loopback test (offline)");
 		} else if (i == BNXT_IRQ_TEST_IDX) {
 			strcpy(str, "Interrupt_test (offline)");
 		} else {
-- 
cgit v1.2.3


From a1ef4a7920549d015128a8a49d7c9e654d197c98 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:49 -0400
Subject: bnxt_en: Add PHY retry logic.

During hotplug, the driver's open function can be called almost
immediately after power on reset.  The PHY may not be ready and the
firmware may return failure when the driver tries to update PHY
settings.  Add retry logic fired from the driver's timer to retry
the operation for 5 seconds.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 31 ++++++++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  4 ++++
 2 files changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d9fc905c5996..fd936c5e8760 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6898,8 +6898,14 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		mutex_lock(&bp->link_lock);
 		rc = bnxt_update_phy_setting(bp);
 		mutex_unlock(&bp->link_lock);
-		if (rc)
+		if (rc) {
 			netdev_warn(bp->dev, "failed to update phy settings\n");
+			if (BNXT_SINGLE_PF(bp)) {
+				bp->link_info.phy_retry = true;
+				bp->link_info.phy_retry_expires =
+					jiffies + 5 * HZ;
+			}
+		}
 	}
 
 	if (irq_re_init)
@@ -7583,6 +7589,16 @@ static void bnxt_timer(struct timer_list *t)
 		set_bit(BNXT_FLOW_STATS_SP_EVENT, &bp->sp_event);
 		bnxt_queue_sp_work(bp);
 	}
+
+	if (bp->link_info.phy_retry) {
+		if (time_after(jiffies, bp->link_info.phy_retry_expires)) {
+			bp->link_info.phy_retry = 0;
+			netdev_warn(bp->dev, "failed to update phy settings after maximum retries.\n");
+		} else {
+			set_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event);
+			bnxt_queue_sp_work(bp);
+		}
+	}
 bnxt_restart_timer:
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
@@ -7670,6 +7686,19 @@ static void bnxt_sp_task(struct work_struct *work)
 			netdev_err(bp->dev, "SP task can't update link (rc: %x)\n",
 				   rc);
 	}
+	if (test_and_clear_bit(BNXT_UPDATE_PHY_SP_EVENT, &bp->sp_event)) {
+		int rc;
+
+		mutex_lock(&bp->link_lock);
+		rc = bnxt_update_phy_setting(bp);
+		mutex_unlock(&bp->link_lock);
+		if (rc) {
+			netdev_warn(bp->dev, "update phy settings retry failed\n");
+		} else {
+			bp->link_info.phy_retry = false;
+			netdev_info(bp->dev, "update phy settings retry succeeded\n");
+		}
+	}
 	if (test_and_clear_bit(BNXT_HWRM_PORT_MODULE_SP_EVENT, &bp->sp_event)) {
 		mutex_lock(&bp->link_lock);
 		bnxt_get_port_module_status(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 0d49fe015ba9..47eec148e745 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -959,6 +959,9 @@ struct bnxt_link_info {
 	u16			advertising;	/* user adv setting */
 	bool			force_link_chng;
 
+	bool			phy_retry;
+	unsigned long		phy_retry_expires;
+
 	/* a copy of phy_qcfg output used to report link
 	 * info to VF
 	 */
@@ -1344,6 +1347,7 @@ struct bnxt {
 #define BNXT_GENEVE_DEL_PORT_SP_EVENT	13
 #define BNXT_LINK_SPEED_CHNG_SP_EVENT	14
 #define BNXT_FLOW_STATS_SP_EVENT	15
+#define BNXT_UPDATE_PHY_SP_EVENT	16
 
 	struct bnxt_hw_resc	hw_resc;
 	struct bnxt_pf_info	pf;
-- 
cgit v1.2.3


From bf82736da3c376c03a42c74ea6fa971e89740d7a Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:50 -0400
Subject: bnxt_en: Add new VF resource allocation strategy mode.

The new mode is "minimal-static" to be used when resources are more
limited to support a large number of VFs, for example  The PF driver
will provision guaranteed minimum resources of 0.  Each VF has no
guranteed resources until it tries to reserve resources during device
open.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c       |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h       |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c | 23 ++++++++++++++---------
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fd936c5e8760..e0e3b4b72c01 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5162,7 +5162,7 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all)
 
 		pf->vf_resv_strategy =
 			le16_to_cpu(resp->vf_reservation_strategy);
-		if (pf->vf_resv_strategy > BNXT_VF_RESV_STRATEGY_MINIMAL)
+		if (pf->vf_resv_strategy > BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC)
 			pf->vf_resv_strategy = BNXT_VF_RESV_STRATEGY_MAXIMAL;
 	}
 hwrm_func_resc_qcaps_exit:
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 47eec148e745..b44a75874a2f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -862,6 +862,7 @@ struct bnxt_pf_info {
 	u8	vf_resv_strategy;
 #define BNXT_VF_RESV_STRATEGY_MAXIMAL	0
 #define BNXT_VF_RESV_STRATEGY_MINIMAL	1
+#define BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC	2
 	void			*hwrm_cmd_req_addr[4];
 	dma_addr_t		hwrm_cmd_req_dma_addr[4];
 	struct bnxt_vf_info	*vf;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index f560845c5a9d..b896a52ee8be 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -447,7 +447,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 	u16 vf_tx_rings, vf_rx_rings, vf_cp_rings;
 	u16 vf_stat_ctx, vf_vnics, vf_ring_grps;
 	struct bnxt_pf_info *pf = &bp->pf;
-	int i, rc = 0;
+	int i, rc = 0, min = 1;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_VF_RESOURCE_CFG, -1, -1);
 
@@ -464,14 +464,19 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs)
 
 	req.min_rsscos_ctx = cpu_to_le16(BNXT_VF_MIN_RSS_CTX);
 	req.max_rsscos_ctx = cpu_to_le16(BNXT_VF_MAX_RSS_CTX);
-	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL) {
-		req.min_cmpl_rings = cpu_to_le16(1);
-		req.min_tx_rings = cpu_to_le16(1);
-		req.min_rx_rings = cpu_to_le16(1);
-		req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MIN_L2_CTX);
-		req.min_vnics = cpu_to_le16(1);
-		req.min_stat_ctx = cpu_to_le16(1);
-		req.min_hw_ring_grps = cpu_to_le16(1);
+	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) {
+		min = 0;
+		req.min_rsscos_ctx = cpu_to_le16(min);
+	}
+	if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL ||
+	    pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL_STATIC) {
+		req.min_cmpl_rings = cpu_to_le16(min);
+		req.min_tx_rings = cpu_to_le16(min);
+		req.min_rx_rings = cpu_to_le16(min);
+		req.min_l2_ctxs = cpu_to_le16(min);
+		req.min_vnics = cpu_to_le16(min);
+		req.min_stat_ctx = cpu_to_le16(min);
+		req.min_hw_ring_grps = cpu_to_le16(min);
 	} else {
 		vf_cp_rings /= num_vfs;
 		vf_tx_rings /= num_vfs;
-- 
cgit v1.2.3


From 50f011b63d8caab7f40de52ca6cf4807aea7a941 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:51 -0400
Subject: bnxt_en: Update RSS setup and GRO-HW logic according to the latest
 spec.

Set the default hash mode flag in HWRM_VNIC_RSS_CFG to signal to the
firmware that the driver is compliant with the latest spec.  With
that, the firmware can return expanded RSS profile IDs that the driver
checks to setup the proper gso_type for GRO-HW packets.  But instead
of checking for the new profile IDs, we check the IP_TYPE flag
in TPA_START which is more straight forward than checking a list of
profile IDs.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 4 ++++
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e0e3b4b72c01..1714850df234 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1115,7 +1115,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr,
 		tpa_info->hash_type = PKT_HASH_TYPE_L4;
 		tpa_info->gso_type = SKB_GSO_TCPV4;
 		/* RSS profiles 1 and 3 with extract code 0 for inner 4-tuple */
-		if (hash_type == 3)
+		if (hash_type == 3 || TPA_START_IS_IPV6(tpa_start1))
 			tpa_info->gso_type = SKB_GSO_TCPV6;
 		tpa_info->rss_hash =
 			le32_to_cpu(tpa_start->rx_tpa_start_cmp_rss_hash);
@@ -3981,6 +3981,7 @@ static int bnxt_hwrm_vnic_set_rss(struct bnxt *bp, u16 vnic_id, bool set_rss)
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VNIC_RSS_CFG, -1, -1);
 	if (set_rss) {
 		req.hash_type = cpu_to_le32(bp->rss_hash_cfg);
+		req.hash_mode_flags = VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT;
 		if (vnic->flags & BNXT_VNIC_RSS_FLAG) {
 			if (BNXT_CHIP_TYPE_NITRO_A0(bp))
 				max_rings = bp->rx_nr_rings - 1;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index b44a75874a2f..7ea022df3526 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -326,6 +326,10 @@ struct rx_tpa_start_cmp_ext {
 	((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) &	\
 	 RX_TPA_START_CMP_CFA_CODE) >> RX_TPA_START_CMPL_CFA_CODE_SHIFT)
 
+#define TPA_START_IS_IPV6(rx_tpa_start)				\
+	(!!((rx_tpa_start)->rx_tpa_start_cmp_flags2 &		\
+	    cpu_to_le32(RX_TPA_START_CMP_FLAGS2_IP_TYPE)))
+
 struct rx_tpa_end_cmp {
 	__le32 rx_tpa_end_cmp_len_flags_type;
 	#define RX_TPA_END_CMP_TYPE				(0x3f << 0)
-- 
cgit v1.2.3


From 6c5657d085ae8c13a8565b98e6a23fe68f0bede4 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:52 -0400
Subject: bnxt_en: Add support for ethtool get dump.

Add support to collect live firmware coredump via ethtool.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h |  66 ++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c  | 333 +++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h  |  37 +++
 3 files changed, 436 insertions(+)
 create mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
new file mode 100644
index 000000000000..09c22f8fe399
--- /dev/null
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.h
@@ -0,0 +1,66 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2018 Broadcom Inc
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#ifndef BNXT_COREDUMP_H
+#define BNXT_COREDUMP_H
+
+struct bnxt_coredump_segment_hdr {
+	__u8 signature[4];
+	__le32 component_id;
+	__le32 segment_id;
+	__le32 flags;
+	__u8 low_version;
+	__u8 high_version;
+	__le16 function_id;
+	__le32 offset;
+	__le32 length;
+	__le32 status;
+	__le32 duration;
+	__le32 data_offset;
+	__le32 instance;
+	__le32 rsvd[5];
+};
+
+struct bnxt_coredump_record {
+	__u8 signature[4];
+	__le32 flags;
+	__u8 low_version;
+	__u8 high_version;
+	__u8 asic_state;
+	__u8 rsvd0[5];
+	char system_name[32];
+	__le16 year;
+	__le16 month;
+	__le16 day;
+	__le16 hour;
+	__le16 minute;
+	__le16 second;
+	__le16 utc_bias;
+	__le16 rsvd1;
+	char commandline[256];
+	__le32 total_segments;
+	__le32 os_ver_major;
+	__le32 os_ver_minor;
+	__le32 rsvd2;
+	char os_name[32];
+	__le16 end_year;
+	__le16 end_month;
+	__le16 end_day;
+	__le16 end_hour;
+	__le16 end_minute;
+	__le16 end_second;
+	__le16 end_utc_bias;
+	__le32 asic_id1;
+	__le32 asic_id2;
+	__le32 coredump_status;
+	__u8 ioctl_low_version;
+	__u8 ioctl_high_version;
+	__le16 rsvd3[313];
+};
+#endif
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9517633f947a..3fc7c741bdfe 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -16,12 +16,15 @@
 #include <linux/etherdevice.h>
 #include <linux/crc32.h>
 #include <linux/firmware.h>
+#include <linux/utsname.h>
+#include <linux/time.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 #include "bnxt_ethtool.h"
 #include "bnxt_nvm_defs.h"	/* NVRAM content constant and structure defs */
 #include "bnxt_fw_hdr.h"	/* Firmware hdr constant and structure defs */
+#include "bnxt_coredump.h"
 #define FLASH_NVRAM_TIMEOUT	((HWRM_CMD_TIMEOUT) * 100)
 #define FLASH_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
 #define INSTALL_PACKAGE_TIMEOUT	((HWRM_CMD_TIMEOUT) * 200)
@@ -2685,6 +2688,334 @@ static int bnxt_reset(struct net_device *dev, u32 *flags)
 	return rc;
 }
 
+static int bnxt_hwrm_dbg_dma_data(struct bnxt *bp, void *msg, int msg_len,
+				  struct bnxt_hwrm_dbg_dma_info *info)
+{
+	struct hwrm_dbg_cmn_output *cmn_resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_dbg_cmn_input *cmn_req = msg;
+	__le16 *seq_ptr = msg + info->seq_off;
+	u16 seq = 0, len, segs_off;
+	void *resp = cmn_resp;
+	dma_addr_t dma_handle;
+	int rc, off = 0;
+	void *dma_buf;
+
+	dma_buf = dma_alloc_coherent(&bp->pdev->dev, info->dma_len, &dma_handle,
+				     GFP_KERNEL);
+	if (!dma_buf)
+		return -ENOMEM;
+
+	segs_off = offsetof(struct hwrm_dbg_coredump_list_output,
+			    total_segments);
+	cmn_req->host_dest_addr = cpu_to_le64(dma_handle);
+	cmn_req->host_buf_len = cpu_to_le32(info->dma_len);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	while (1) {
+		*seq_ptr = cpu_to_le16(seq);
+		rc = _hwrm_send_message(bp, msg, msg_len, HWRM_CMD_TIMEOUT);
+		if (rc)
+			break;
+
+		len = le16_to_cpu(*((__le16 *)(resp + info->data_len_off)));
+		if (!seq &&
+		    cmn_req->req_type == cpu_to_le16(HWRM_DBG_COREDUMP_LIST)) {
+			info->segs = le16_to_cpu(*((__le16 *)(resp +
+							      segs_off)));
+			if (!info->segs) {
+				rc = -EIO;
+				break;
+			}
+
+			info->dest_buf_size = info->segs *
+					sizeof(struct coredump_segment_record);
+			info->dest_buf = kmalloc(info->dest_buf_size,
+						 GFP_KERNEL);
+			if (!info->dest_buf) {
+				rc = -ENOMEM;
+				break;
+			}
+		}
+
+		if (info->dest_buf)
+			memcpy(info->dest_buf + off, dma_buf, len);
+
+		if (cmn_req->req_type ==
+				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))
+			info->dest_buf_size += len;
+
+		if (!(cmn_resp->flags & HWRM_DBG_CMN_FLAGS_MORE))
+			break;
+
+		seq++;
+		off += len;
+	}
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	dma_free_coherent(&bp->pdev->dev, info->dma_len, dma_buf, dma_handle);
+	return rc;
+}
+
+static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp,
+				       struct bnxt_coredump *coredump)
+{
+	struct hwrm_dbg_coredump_list_input req = {0};
+	struct bnxt_hwrm_dbg_dma_info info = {NULL};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_LIST, -1, -1);
+
+	info.dma_len = COREDUMP_LIST_BUF_LEN;
+	info.seq_off = offsetof(struct hwrm_dbg_coredump_list_input, seq_no);
+	info.data_len_off = offsetof(struct hwrm_dbg_coredump_list_output,
+				     data_len);
+
+	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
+	if (!rc) {
+		coredump->data = info.dest_buf;
+		coredump->data_size = info.dest_buf_size;
+		coredump->total_segs = info.segs;
+	}
+	return rc;
+}
+
+static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
+					   u16 segment_id)
+{
+	struct hwrm_dbg_coredump_initiate_input req = {0};
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_INITIATE, -1, -1);
+	req.component_id = cpu_to_le16(component_id);
+	req.segment_id = cpu_to_le16(segment_id);
+
+	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+}
+
+static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
+					   u16 segment_id, u32 *seg_len,
+					   void *buf, u32 offset)
+{
+	struct hwrm_dbg_coredump_retrieve_input req = {0};
+	struct bnxt_hwrm_dbg_dma_info info = {NULL};
+	int rc;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_DBG_COREDUMP_RETRIEVE, -1, -1);
+	req.component_id = cpu_to_le16(component_id);
+	req.segment_id = cpu_to_le16(segment_id);
+
+	info.dma_len = COREDUMP_RETRIEVE_BUF_LEN;
+	info.seq_off = offsetof(struct hwrm_dbg_coredump_retrieve_input,
+				seq_no);
+	info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output,
+				     data_len);
+	if (buf)
+		info.dest_buf = buf + offset;
+
+	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
+	if (!rc)
+		*seg_len = info.dest_buf_size;
+
+	return rc;
+}
+
+static void
+bnxt_fill_coredump_seg_hdr(struct bnxt *bp,
+			   struct bnxt_coredump_segment_hdr *seg_hdr,
+			   struct coredump_segment_record *seg_rec, u32 seg_len,
+			   int status, u32 duration, u32 instance)
+{
+	memset(seg_hdr, 0, sizeof(*seg_hdr));
+	strcpy(seg_hdr->signature, "sEgM");
+	if (seg_rec) {
+		seg_hdr->component_id = (__force __le32)seg_rec->component_id;
+		seg_hdr->segment_id = (__force __le32)seg_rec->segment_id;
+		seg_hdr->low_version = seg_rec->version_low;
+		seg_hdr->high_version = seg_rec->version_hi;
+	} else {
+		/* For hwrm_ver_get response Component id = 2
+		 * and Segment id = 0
+		 */
+		seg_hdr->component_id = cpu_to_le32(2);
+		seg_hdr->segment_id = 0;
+	}
+	seg_hdr->function_id = cpu_to_le16(bp->pdev->devfn);
+	seg_hdr->length = cpu_to_le32(seg_len);
+	seg_hdr->status = cpu_to_le32(status);
+	seg_hdr->duration = cpu_to_le32(duration);
+	seg_hdr->data_offset = cpu_to_le32(sizeof(*seg_hdr));
+	seg_hdr->instance = cpu_to_le32(instance);
+}
+
+static void
+bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record,
+			  time64_t start, s16 start_utc, u16 total_segs,
+			  int status)
+{
+	time64_t end = ktime_get_real_seconds();
+	u32 os_ver_major = 0, os_ver_minor = 0;
+	struct tm tm;
+
+	time64_to_tm(start, 0, &tm);
+	memset(record, 0, sizeof(*record));
+	strcpy(record->signature, "cOrE");
+	record->flags = 0;
+	record->low_version = 0;
+	record->high_version = 1;
+	record->asic_state = 0;
+	strncpy(record->system_name, utsname()->nodename,
+		strlen(utsname()->nodename));
+	record->year = cpu_to_le16(tm.tm_year);
+	record->month = cpu_to_le16(tm.tm_mon);
+	record->day = cpu_to_le16(tm.tm_mday);
+	record->hour = cpu_to_le16(tm.tm_hour);
+	record->minute = cpu_to_le16(tm.tm_min);
+	record->second = cpu_to_le16(tm.tm_sec);
+	record->utc_bias = cpu_to_le16(start_utc);
+	strcpy(record->commandline, "ethtool -w");
+	record->total_segments = cpu_to_le32(total_segs);
+
+	sscanf(utsname()->release, "%u.%u", &os_ver_major, &os_ver_minor);
+	record->os_ver_major = cpu_to_le32(os_ver_major);
+	record->os_ver_minor = cpu_to_le32(os_ver_minor);
+
+	strcpy(record->os_name, utsname()->sysname);
+	time64_to_tm(end, 0, &tm);
+	record->end_year = cpu_to_le16(tm.tm_year + 1900);
+	record->end_month = cpu_to_le16(tm.tm_mon + 1);
+	record->end_day = cpu_to_le16(tm.tm_mday);
+	record->end_hour = cpu_to_le16(tm.tm_hour);
+	record->end_minute = cpu_to_le16(tm.tm_min);
+	record->end_second = cpu_to_le16(tm.tm_sec);
+	record->end_utc_bias = cpu_to_le16(sys_tz.tz_minuteswest * 60);
+	record->asic_id1 = cpu_to_le32(bp->chip_num << 16 |
+				       bp->ver_resp.chip_rev << 8 |
+				       bp->ver_resp.chip_metal);
+	record->asic_id2 = 0;
+	record->coredump_status = cpu_to_le32(status);
+	record->ioctl_low_version = 0;
+	record->ioctl_high_version = 0;
+}
+
+static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
+{
+	u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output);
+	struct coredump_segment_record *seg_record = NULL;
+	u32 offset = 0, seg_hdr_len, seg_record_len;
+	struct bnxt_coredump_segment_hdr seg_hdr;
+	struct bnxt_coredump_record coredump_rec;
+	struct bnxt_coredump coredump = {NULL};
+	time64_t start_time;
+	u16 start_utc;
+	int rc = 0, i;
+
+	start_time = ktime_get_real_seconds();
+	start_utc = sys_tz.tz_minuteswest * 60;
+	seg_hdr_len = sizeof(seg_hdr);
+
+	/* First segment should be hwrm_ver_get response */
+	*dump_len = seg_hdr_len + ver_get_resp_len;
+	if (buf) {
+		bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, NULL, ver_get_resp_len,
+					   0, 0, 0);
+		memcpy(buf + offset, &seg_hdr, seg_hdr_len);
+		offset += seg_hdr_len;
+		memcpy(buf + offset, &bp->ver_resp, ver_get_resp_len);
+		offset += ver_get_resp_len;
+	}
+
+	rc = bnxt_hwrm_dbg_coredump_list(bp, &coredump);
+	if (rc) {
+		netdev_err(bp->dev, "Failed to get coredump segment list\n");
+		goto err;
+	}
+
+	*dump_len += seg_hdr_len * coredump.total_segs;
+
+	seg_record = (struct coredump_segment_record *)coredump.data;
+	seg_record_len = sizeof(*seg_record);
+
+	for (i = 0; i < coredump.total_segs; i++) {
+		u16 comp_id = le16_to_cpu(seg_record->component_id);
+		u16 seg_id = le16_to_cpu(seg_record->segment_id);
+		u32 duration = 0, seg_len = 0;
+		unsigned long start, end;
+
+		start = jiffies;
+
+		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);
+		if (rc) {
+			netdev_err(bp->dev,
+				   "Failed to initiate coredump for seg = %d\n",
+				   seg_record->segment_id);
+			goto next_seg;
+		}
+
+		/* Write segment data into the buffer */
+		rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id,
+						     &seg_len, buf,
+						     offset + seg_hdr_len);
+		if (rc)
+			netdev_err(bp->dev,
+				   "Failed to retrieve coredump for seg = %d\n",
+				   seg_record->segment_id);
+
+next_seg:
+		end = jiffies;
+		duration = jiffies_to_msecs(end - start);
+		bnxt_fill_coredump_seg_hdr(bp, &seg_hdr, seg_record, seg_len,
+					   rc, duration, 0);
+
+		if (buf) {
+			/* Write segment header into the buffer */
+			memcpy(buf + offset, &seg_hdr, seg_hdr_len);
+			offset += seg_hdr_len + seg_len;
+		}
+
+		*dump_len += seg_len;
+		seg_record =
+			(struct coredump_segment_record *)((u8 *)seg_record +
+							   seg_record_len);
+	}
+
+err:
+	if (buf) {
+		bnxt_fill_coredump_record(bp, &coredump_rec, start_time,
+					  start_utc, coredump.total_segs + 1,
+					  rc);
+		memcpy(buf + offset, &coredump_rec, sizeof(coredump_rec));
+	}
+	kfree(coredump.data);
+	*dump_len += sizeof(coredump_rec);
+
+	return rc;
+}
+
+static int bnxt_get_dump_flag(struct net_device *dev, struct ethtool_dump *dump)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (bp->hwrm_spec_code < 0x10801)
+		return -EOPNOTSUPP;
+
+	dump->version = bp->ver_resp.hwrm_fw_maj_8b << 24 |
+			bp->ver_resp.hwrm_fw_min_8b << 16 |
+			bp->ver_resp.hwrm_fw_bld_8b << 8 |
+			bp->ver_resp.hwrm_fw_rsvd_8b;
+
+	return bnxt_get_coredump(bp, NULL, &dump->len);
+}
+
+static int bnxt_get_dump_data(struct net_device *dev, struct ethtool_dump *dump,
+			      void *buf)
+{
+	struct bnxt *bp = netdev_priv(dev);
+
+	if (bp->hwrm_spec_code < 0x10801)
+		return -EOPNOTSUPP;
+
+	memset(buf, 0, dump->len);
+
+	return bnxt_get_coredump(bp, buf, &dump->len);
+}
+
 void bnxt_ethtool_init(struct bnxt *bp)
 {
 	struct hwrm_selftest_qlist_output *resp = bp->hwrm_cmd_resp_addr;
@@ -2788,4 +3119,6 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.set_phys_id		= bnxt_set_phys_id,
 	.self_test		= bnxt_self_test,
 	.reset			= bnxt_reset,
+	.get_dump_flag		= bnxt_get_dump_flag,
+	.get_dump_data		= bnxt_get_dump_data,
 };
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
index 836ef682f24c..b5b65b3f8534 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.h
@@ -22,6 +22,43 @@ struct bnxt_led_cfg {
 	u8 rsvd;
 };
 
+#define COREDUMP_LIST_BUF_LEN		2048
+#define COREDUMP_RETRIEVE_BUF_LEN	4096
+
+struct bnxt_coredump {
+	void		*data;
+	int		data_size;
+	u16		total_segs;
+};
+
+struct bnxt_hwrm_dbg_dma_info {
+	void *dest_buf;
+	int dest_buf_size;
+	u16 dma_len;
+	u16 seq_off;
+	u16 data_len_off;
+	u16 segs;
+};
+
+struct hwrm_dbg_cmn_input {
+	__le16 req_type;
+	__le16 cmpl_ring;
+	__le16 seq_id;
+	__le16 target_id;
+	__le64 resp_addr;
+	__le64 host_dest_addr;
+	__le32 host_buf_len;
+};
+
+struct hwrm_dbg_cmn_output {
+	__le16 error_code;
+	__le16 req_type;
+	__le16 seq_id;
+	__le16 resp_len;
+	u8 flags;
+	#define HWRM_DBG_CMN_FLAGS_MORE	1
+};
+
 #define BNXT_LED_DFLT_ENA				\
 	(PORT_LED_CFG_REQ_ENABLES_LED0_ID |		\
 	 PORT_LED_CFG_REQ_ENABLES_LED0_STATE |		\
-- 
cgit v1.2.3


From f1ca94de0d8760726dc615e8b4f9801f7ad9cf3b Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:53 -0400
Subject: bnxt_en: Add BNXT_NEW_RM() macro.

The BNXT_FLAG_NEW_RM flag is checked a lot in the code to determine if
the new resource manager is in effect.  Define a macro to perform
this check.

Signed-off-by: Michael Chan <michael.chan@broadocm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 27 +++++++++++------------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c   |  2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c     |  4 ++--
 5 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1714850df234..5c9ee3c12323 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -4579,7 +4579,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp)
 	}
 
 	hw_resc->resv_tx_rings = le16_to_cpu(resp->alloc_tx_rings);
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		u16 cp, stats;
 
 		hw_resc->resv_rx_rings = le16_to_cpu(resp->alloc_rx_rings);
@@ -4625,7 +4625,7 @@ __bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, struct hwrm_func_cfg_input *req,
 	req->fid = cpu_to_le16(0xffff);
 	enables |= tx_rings ? FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS : 0;
 	req->num_tx_rings = cpu_to_le16(tx_rings);
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		enables |= rx_rings ? FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS : 0;
 		enables |= cp_rings ? FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS |
 				      FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS : 0;
@@ -4698,7 +4698,7 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	struct hwrm_func_vf_cfg_input req = {0};
 	int rc;
 
-	if (!(bp->flags & BNXT_FLAG_NEW_RM)) {
+	if (!BNXT_NEW_RM(bp)) {
 		bp->hw_resc.resv_tx_rings = tx_rings;
 		return 0;
 	}
@@ -4758,7 +4758,7 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
 		vnic = rx + 1;
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx <<= 1;
-	if ((bp->flags & BNXT_FLAG_NEW_RM) &&
+	if (BNXT_NEW_RM(bp) &&
 	    (hw_resc->resv_rx_rings != rx || hw_resc->resv_cp_rings != cp ||
 	     hw_resc->resv_hw_ring_grps != grp || hw_resc->resv_vnics != vnic))
 		return true;
@@ -4794,7 +4794,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
 		return rc;
 
 	tx = hw_resc->resv_tx_rings;
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		rx = hw_resc->resv_rx_rings;
 		cp = hw_resc->resv_cp_rings;
 		grp = hw_resc->resv_hw_ring_grps;
@@ -4838,7 +4838,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	u32 flags;
 	int rc;
 
-	if (!(bp->flags & BNXT_FLAG_NEW_RM))
+	if (!BNXT_NEW_RM(bp))
 		return 0;
 
 	__bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
@@ -4867,7 +4867,7 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings,
 	__bnxt_hwrm_reserve_pf_rings(bp, &req, tx_rings, rx_rings, ring_grps,
 				     cp_rings, vnics);
 	flags = FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST;
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		flags |= FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST |
 			 FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST |
@@ -5921,7 +5921,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num)
 
 	max_idx = min_t(int, bp->total_irqs, max_cp);
 	avail_msix = max_idx - bp->cp_nr_rings;
-	if (!(bp->flags & BNXT_FLAG_NEW_RM) || avail_msix >= num)
+	if (!BNXT_NEW_RM(bp) || avail_msix >= num)
 		return avail_msix;
 
 	if (max_irq < total_req) {
@@ -5934,7 +5934,7 @@ int bnxt_get_avail_msix(struct bnxt *bp, int num)
 
 static int bnxt_get_num_msix(struct bnxt *bp)
 {
-	if (!(bp->flags & BNXT_FLAG_NEW_RM))
+	if (!BNXT_NEW_RM(bp))
 		return bnxt_get_max_func_irqs(bp);
 
 	return bnxt_cp_rings_in_use(bp);
@@ -6057,8 +6057,7 @@ int bnxt_reserve_rings(struct bnxt *bp)
 		netdev_err(bp->dev, "ring reservation failure rc: %d\n", rc);
 		return rc;
 	}
-	if ((bp->flags & BNXT_FLAG_NEW_RM) &&
-	    (bnxt_get_num_msix(bp) != bp->total_irqs)) {
+	if (BNXT_NEW_RM(bp) && (bnxt_get_num_msix(bp) != bp->total_irqs)) {
 		bnxt_ulp_irq_stop(bp);
 		bnxt_clear_int_mode(bp);
 		rc = bnxt_init_int_mode(bp);
@@ -7306,7 +7305,7 @@ skip_uc:
 static bool bnxt_can_reserve_rings(struct bnxt *bp)
 {
 #ifdef CONFIG_BNXT_SRIOV
-	if ((bp->flags & BNXT_FLAG_NEW_RM) && BNXT_VF(bp)) {
+	if (BNXT_NEW_RM(bp) && BNXT_VF(bp)) {
 		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
 		/* No minimum rings were provisioned by the PF.  Don't
@@ -7356,7 +7355,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp)
 		return false;
 	}
 
-	if (!(bp->flags & BNXT_FLAG_NEW_RM))
+	if (!BNXT_NEW_RM(bp))
 		return true;
 
 	if (vnics == bp->hw_resc.resv_vnics)
@@ -7752,7 +7751,7 @@ int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		rx_rings <<= 1;
 	cp = sh ? max_t(int, tx_rings_needed, rx) : tx_rings_needed + rx;
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		cp += bnxt_get_ulp_msix_num(bp);
 	return bnxt_hwrm_check_rings(bp, tx_rings_needed, rx_rings, rx, cp,
 				     vnics);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 7ea022df3526..37dc896da9dc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1195,6 +1195,7 @@ struct bnxt {
 #define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp) && !BNXT_MH(bp))
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 #define BNXT_RX_PAGE_MODE(bp)	((bp)->flags & BNXT_FLAG_RX_PAGE_MODE)
+#define BNXT_NEW_RM(bp)		((bp)->flags & BNXT_FLAG_NEW_RM)
 
 /* Chip class phase 4 and later */
 #define BNXT_CHIP_P4_PLUS(bp)			\
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 3fc7c741bdfe..b6dbc3f6d309 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -471,7 +471,7 @@ static void bnxt_get_channels(struct net_device *dev,
 	int max_tx_sch_inputs;
 
 	/* Get the most up-to-date max_tx_sch_inputs. */
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		bnxt_hwrm_func_resc_qcaps(bp, false);
 	max_tx_sch_inputs = hw_resc->max_tx_sch_inputs;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index b896a52ee8be..6d583bcd2a81 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -623,7 +623,7 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs)
 
 static int bnxt_func_cfg(struct bnxt *bp, int num_vfs)
 {
-	if (bp->flags & BNXT_FLAG_NEW_RM)
+	if (BNXT_NEW_RM(bp))
 		return bnxt_hwrm_func_vf_resc_cfg(bp, num_vfs);
 	else
 		return bnxt_hwrm_func_cfg(bp, num_vfs);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 840f6e505f73..c37b2842f972 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -141,7 +141,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 	if (avail_msix > num_msix)
 		avail_msix = num_msix;
 
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		idx = bp->cp_nr_rings;
 	} else {
 		max_idx = min_t(int, bp->total_irqs, max_cp_rings);
@@ -162,7 +162,7 @@ static int bnxt_req_msix_vecs(struct bnxt_en_dev *edev, int ulp_id,
 		return -EAGAIN;
 	}
 
-	if (bp->flags & BNXT_FLAG_NEW_RM) {
+	if (BNXT_NEW_RM(bp)) {
 		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 
 		avail_msix = hw_resc->resv_cp_rings - bp->cp_nr_rings;
-- 
cgit v1.2.3


From 97381a1831124c95801fbfaba8436b4abc7d03f5 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:54 -0400
Subject: bnxt_en: Move firmware related flags to a new fw_cap field in struct
 bnxt.

The flags field is almost getting full.  Move firmware capability flags
to a new fw_cap field to better organize these firmware flags.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 12 ++++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     | 13 +++++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c |  6 +++---
 3 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 5c9ee3c12323..165994047f81 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3445,7 +3445,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len,
 	cp_ring_id = le16_to_cpu(req->cmpl_ring);
 	intr_process = (cp_ring_id == INVALID_HW_RING_ID) ? 0 : 1;
 
-	if (bp->flags & BNXT_FLAG_SHORT_CMD) {
+	if (bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) {
 		void *short_cmd_req = bp->hwrm_short_cmd_req_addr;
 
 		memcpy(short_cmd_req, req, msg_len);
@@ -5089,9 +5089,9 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 	flags = le16_to_cpu(resp->flags);
 	if (flags & (FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED |
 		     FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED)) {
-		bp->flags |= BNXT_FLAG_FW_LLDP_AGENT;
+		bp->fw_cap |= BNXT_FW_CAP_LLDP_AGENT;
 		if (flags & FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED)
-			bp->flags |= BNXT_FLAG_FW_DCBX_AGENT;
+			bp->fw_cap |= BNXT_FW_CAP_DCBX_AGENT;
 	}
 	if (BNXT_PF(bp) && (flags & FUNC_QCFG_RESP_FLAGS_MULTI_HOST))
 		bp->flags |= BNXT_FLAG_MULTI_HOST;
@@ -5249,7 +5249,7 @@ static int bnxt_hwrm_func_qcaps(struct bnxt *bp)
 	if (bp->hwrm_spec_code >= 0x10803) {
 		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
 		if (!rc)
-			bp->flags |= BNXT_FLAG_NEW_RM;
+			bp->fw_cap |= BNXT_FW_CAP_NEW_RM;
 	}
 	return 0;
 }
@@ -5352,7 +5352,7 @@ static int bnxt_hwrm_ver_get(struct bnxt *bp)
 	dev_caps_cfg = le32_to_cpu(resp->dev_caps_cfg);
 	if ((dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED) &&
 	    (dev_caps_cfg & VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED))
-		bp->flags |= BNXT_FLAG_SHORT_CMD;
+		bp->fw_cap |= BNXT_FW_CAP_SHORT_CMD;
 
 hwrm_ver_get_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
@@ -8760,7 +8760,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (rc)
 		goto init_err_pci_clean;
 
-	if (bp->flags & BNXT_FLAG_SHORT_CMD) {
+	if (bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) {
 		rc = bnxt_alloc_hwrm_short_cmd_req(bp);
 		if (rc)
 			goto init_err_pci_clean;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 37dc896da9dc..ded2affd9ee8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1144,7 +1144,6 @@ struct bnxt {
 	atomic_t		intr_sem;
 
 	u32			flags;
-	#define BNXT_FLAG_DCB_ENABLED	0x1
 	#define BNXT_FLAG_VF		0x2
 	#define BNXT_FLAG_LRO		0x4
 #ifdef CONFIG_INET
@@ -1173,15 +1172,11 @@ struct bnxt {
 					 BNXT_FLAG_ROCEV2_CAP)
 	#define BNXT_FLAG_NO_AGG_RINGS	0x20000
 	#define BNXT_FLAG_RX_PAGE_MODE	0x40000
-	#define BNXT_FLAG_FW_LLDP_AGENT	0x80000
 	#define BNXT_FLAG_MULTI_HOST	0x100000
-	#define BNXT_FLAG_SHORT_CMD	0x200000
 	#define BNXT_FLAG_DOUBLE_DB	0x400000
-	#define BNXT_FLAG_FW_DCBX_AGENT	0x800000
 	#define BNXT_FLAG_CHIP_NITRO_A0	0x1000000
 	#define BNXT_FLAG_DIM		0x2000000
 	#define BNXT_FLAG_ROCE_MIRROR_CAP	0x4000000
-	#define BNXT_FLAG_NEW_RM	0x8000000
 	#define BNXT_FLAG_PORT_STATS_EXT	0x10000000
 
 	#define BNXT_FLAG_ALL_CONFIG_FEATS (BNXT_FLAG_TPA |		\
@@ -1195,7 +1190,6 @@ struct bnxt {
 #define BNXT_SINGLE_PF(bp)	(BNXT_PF(bp) && !BNXT_NPAR(bp) && !BNXT_MH(bp))
 #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0)
 #define BNXT_RX_PAGE_MODE(bp)	((bp)->flags & BNXT_FLAG_RX_PAGE_MODE)
-#define BNXT_NEW_RM(bp)		((bp)->flags & BNXT_FLAG_NEW_RM)
 
 /* Chip class phase 4 and later */
 #define BNXT_CHIP_P4_PLUS(bp)			\
@@ -1291,6 +1285,13 @@ struct bnxt {
 
 	u32			msg_enable;
 
+	u32			fw_cap;
+	#define BNXT_FW_CAP_SHORT_CMD	0x00000001
+	#define BNXT_FW_CAP_LLDP_AGENT	0x00000002
+	#define BNXT_FW_CAP_DCBX_AGENT	0x00000004
+	#define BNXT_FW_CAP_NEW_RM	0x00000008
+
+#define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
 	u16			hwrm_cmd_seq;
 	u32			hwrm_intr_seq_id;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index d5bc72cecde3..00dd26dd2100 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -610,7 +610,7 @@ static u8 bnxt_dcbnl_setdcbx(struct net_device *dev, u8 mode)
 		return 1;
 
 	if (mode & DCB_CAP_DCBX_HOST) {
-		if (BNXT_VF(bp) || (bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
+		if (BNXT_VF(bp) || (bp->fw_cap & BNXT_FW_CAP_LLDP_AGENT))
 			return 1;
 
 		/* only support IEEE */
@@ -643,9 +643,9 @@ void bnxt_dcb_init(struct bnxt *bp)
 		return;
 
 	bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE;
-	if (BNXT_PF(bp) && !(bp->flags & BNXT_FLAG_FW_LLDP_AGENT))
+	if (BNXT_PF(bp) && !(bp->fw_cap & BNXT_FW_CAP_LLDP_AGENT))
 		bp->dcbx_cap |= DCB_CAP_DCBX_HOST;
-	else if (bp->flags & BNXT_FLAG_FW_DCBX_AGENT)
+	else if (bp->fw_cap & BNXT_FW_CAP_DCBX_AGENT)
 		bp->dcbx_cap |= DCB_CAP_DCBX_LLD_MANAGED;
 	bp->dev->dcbnl_ops = &dcbnl_ops;
 }
-- 
cgit v1.2.3


From 25e1acd6b92bde36c03273d883c44c4d0e8995e6 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:55 -0400
Subject: bnxt_en: Notify firmware about IF state changes.

Use latest firmware API to notify firmware about IF state changes.
Firmware has the option to clean up resources during IF down and
to require the driver to reserve resources again during IF up.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 53 +++++++++++++++++++++++++++++--
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 2 files changed, 52 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 165994047f81..56bd09758e22 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3638,7 +3638,9 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap,
 
 static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 {
+	struct hwrm_func_drv_rgtr_output *resp = bp->hwrm_cmd_resp_addr;
 	struct hwrm_func_drv_rgtr_input req = {0};
+	int rc;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1);
 
@@ -3676,7 +3678,15 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp)
 			cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD);
 	}
 
-	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		rc = -EIO;
+	else if (resp->flags &
+		 cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED))
+		bp->fw_cap |= BNXT_FW_CAP_IF_CHANGE;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
 }
 
 static int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp)
@@ -6637,6 +6647,39 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp)
 	return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 }
 
+static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
+{
+	struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_func_drv_if_change_input req = {0};
+	bool resc_reinit = false;
+	int rc;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_IF_CHANGE, -1, -1);
+	if (up)
+		req.flags = cpu_to_le32(FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc && (resp->flags &
+		    cpu_to_le32(FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE)))
+		resc_reinit = true;
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	if (up && resc_reinit && BNXT_NEW_RM(bp)) {
+		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
+
+		rc = bnxt_hwrm_func_resc_qcaps(bp, true);
+		hw_resc->resv_cp_rings = 0;
+		hw_resc->resv_tx_rings = 0;
+		hw_resc->resv_rx_rings = 0;
+		hw_resc->resv_hw_ring_grps = 0;
+		hw_resc->resv_vnics = 0;
+	}
+	return rc;
+}
+
 static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp)
 {
 	struct hwrm_port_led_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
@@ -6991,8 +7034,13 @@ void bnxt_half_close_nic(struct bnxt *bp)
 static int bnxt_open(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
+	int rc;
 
-	return __bnxt_open_nic(bp, true, true);
+	bnxt_hwrm_if_change(bp, true);
+	rc = __bnxt_open_nic(bp, true, true);
+	if (rc)
+		bnxt_hwrm_if_change(bp, false);
+	return rc;
 }
 
 static bool bnxt_drv_busy(struct bnxt *bp)
@@ -7056,6 +7104,7 @@ static int bnxt_close(struct net_device *dev)
 
 	bnxt_close_nic(bp, true, true);
 	bnxt_hwrm_shutdown_link(bp);
+	bnxt_hwrm_if_change(bp, false);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index ded2affd9ee8..6c40b25716d3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1290,6 +1290,7 @@ struct bnxt {
 	#define BNXT_FW_CAP_LLDP_AGENT	0x00000002
 	#define BNXT_FW_CAP_DCBX_AGENT	0x00000004
 	#define BNXT_FW_CAP_NEW_RM	0x00000008
+	#define BNXT_FW_CAP_IF_CHANGE	0x00000010
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;
-- 
cgit v1.2.3


From cde49a42a9bbba18d7f33550fd70037930c14e97 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:56 -0400
Subject: bnxt_en: Add hwmon sysfs support to read temperature

Export temperature sensor reading via hwmon sysfs.

Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/Kconfig     |  8 ++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 62 +++++++++++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  1 +
 3 files changed, 71 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/Kconfig b/drivers/net/ethernet/broadcom/Kconfig
index b7aa8ad96dfb..c1d3ee9baf7e 100644
--- a/drivers/net/ethernet/broadcom/Kconfig
+++ b/drivers/net/ethernet/broadcom/Kconfig
@@ -230,4 +230,12 @@ config BNXT_DCB
 
 	  If unsure, say N.
 
+config BNXT_HWMON
+	bool "Broadcom NetXtreme-C/E HWMON support"
+	default y
+	depends on BNXT && HWMON && !(BNXT=y && HWMON=m)
+	---help---
+	  Say Y if you want to expose the thermal sensor data on NetXtreme-C/E
+	  devices, via the hwmon sysfs interface.
+
 endif # NET_VENDOR_BROADCOM
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 56bd09758e22..dde904bccab9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -51,6 +51,8 @@
 #include <linux/cpu_rmap.h>
 #include <linux/cpumask.h>
 #include <net/pkt_cls.h>
+#include <linux/hwmon.h>
+#include <linux/hwmon-sysfs.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -6789,6 +6791,62 @@ static void bnxt_get_wol_settings(struct bnxt *bp)
 	} while (handle && handle != 0xffff);
 }
 
+#ifdef CONFIG_BNXT_HWMON
+static ssize_t bnxt_show_temp(struct device *dev,
+			      struct device_attribute *devattr, char *buf)
+{
+	struct hwrm_temp_monitor_query_input req = {0};
+	struct hwrm_temp_monitor_query_output *resp;
+	struct bnxt *bp = dev_get_drvdata(dev);
+	u32 temp = 0;
+
+	resp = bp->hwrm_cmd_resp_addr;
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_TEMP_MONITOR_QUERY, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	if (!_hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT))
+		temp = resp->temp * 1000; /* display millidegree */
+	mutex_unlock(&bp->hwrm_cmd_lock);
+
+	return sprintf(buf, "%u\n", temp);
+}
+static SENSOR_DEVICE_ATTR(temp1_input, 0444, bnxt_show_temp, NULL, 0);
+
+static struct attribute *bnxt_attrs[] = {
+	&sensor_dev_attr_temp1_input.dev_attr.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(bnxt);
+
+static void bnxt_hwmon_close(struct bnxt *bp)
+{
+	if (bp->hwmon_dev) {
+		hwmon_device_unregister(bp->hwmon_dev);
+		bp->hwmon_dev = NULL;
+	}
+}
+
+static void bnxt_hwmon_open(struct bnxt *bp)
+{
+	struct pci_dev *pdev = bp->pdev;
+
+	bp->hwmon_dev = hwmon_device_register_with_groups(&pdev->dev,
+							  DRV_MODULE_NAME, bp,
+							  bnxt_groups);
+	if (IS_ERR(bp->hwmon_dev)) {
+		bp->hwmon_dev = NULL;
+		dev_warn(&pdev->dev, "Cannot register hwmon device\n");
+	}
+}
+#else
+static void bnxt_hwmon_close(struct bnxt *bp)
+{
+}
+
+static void bnxt_hwmon_open(struct bnxt *bp)
+{
+}
+#endif
+
 static bool bnxt_eee_config_ok(struct bnxt *bp)
 {
 	struct ethtool_eee *eee = &bp->eee;
@@ -7040,6 +7098,9 @@ static int bnxt_open(struct net_device *dev)
 	rc = __bnxt_open_nic(bp, true, true);
 	if (rc)
 		bnxt_hwrm_if_change(bp, false);
+
+	bnxt_hwmon_open(bp);
+
 	return rc;
 }
 
@@ -7102,6 +7163,7 @@ static int bnxt_close(struct net_device *dev)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
+	bnxt_hwmon_close(bp);
 	bnxt_close_nic(bp, true, true);
 	bnxt_hwrm_shutdown_link(bp);
 	bnxt_hwrm_if_change(bp, false);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 6c40b25716d3..006726c02f51 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1411,6 +1411,7 @@ struct bnxt {
 	struct bnxt_tc_info	*tc_info;
 	struct dentry		*debugfs_pdev;
 	struct dentry		*debugfs_dim;
+	struct device		*hwmon_dev;
 };
 
 #define BNXT_RX_STATS_OFFSET(counter)			\
-- 
cgit v1.2.3


From afdc8a84844a2163e25ad735f9f69d220ae02529 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:57 -0400
Subject: bnxt_en: Add DCBNL DSCP application protocol support.

Expand the .ieee_setapp() and ieee_delapp() DCBNL methods to support
DSCP.  This allows DSCP values to user priority mappings instead
of using VLAN priorities.  Each DSCP mapping is added or deleted one
entry at a time using the firmware API.  The firmware call can only be
made from a PF.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h     |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c | 83 ++++++++++++++++++++++++++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h |  6 ++
 3 files changed, 89 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 006726c02f51..fefa011320e0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1281,6 +1281,7 @@ struct bnxt {
 	struct ieee_ets		*ieee_ets;
 	u8			dcbx_cap;
 	u8			default_pri;
+	u8			max_dscp_value;
 #endif /* CONFIG_BNXT_DCB */
 
 	u32			msg_enable;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 00dd26dd2100..ddc98c359488 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -385,6 +385,61 @@ set_app_exit:
 	return rc;
 }
 
+static int bnxt_hwrm_queue_dscp_qcaps(struct bnxt *bp)
+{
+	struct hwrm_queue_dscp_qcaps_output *resp = bp->hwrm_cmd_resp_addr;
+	struct hwrm_queue_dscp_qcaps_input req = {0};
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10800 || BNXT_VF(bp))
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP_QCAPS, -1, -1);
+	mutex_lock(&bp->hwrm_cmd_lock);
+	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (!rc) {
+		bp->max_dscp_value = (1 << resp->num_dscp_bits) - 1;
+		if (bp->max_dscp_value < 0x3f)
+			bp->max_dscp_value = 0;
+	}
+
+	mutex_unlock(&bp->hwrm_cmd_lock);
+	return rc;
+}
+
+static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app,
+					bool add)
+{
+	struct hwrm_queue_dscp2pri_cfg_input req = {0};
+	struct bnxt_dscp2pri_entry *dscp2pri;
+	dma_addr_t mapping;
+	int rc;
+
+	if (bp->hwrm_spec_code < 0x10800)
+		return 0;
+
+	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_DSCP2PRI_CFG, -1, -1);
+	dscp2pri = dma_alloc_coherent(&bp->pdev->dev, sizeof(*dscp2pri),
+				      &mapping, GFP_KERNEL);
+	if (!dscp2pri)
+		return -ENOMEM;
+
+	req.src_data_addr = cpu_to_le64(mapping);
+	dscp2pri->dscp = app->protocol;
+	if (add)
+		dscp2pri->mask = 0x3f;
+	else
+		dscp2pri->mask = 0;
+	dscp2pri->pri = app->priority;
+	req.entry_cnt = cpu_to_le16(1);
+	rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
+	if (rc)
+		rc = -EIO;
+	dma_free_coherent(&bp->pdev->dev, sizeof(*dscp2pri), dscp2pri,
+			  mapping);
+	return rc;
+}
+
 static int bnxt_ets_validate(struct bnxt *bp, struct ieee_ets *ets, u8 *tc)
 {
 	int total_ets_bw = 0;
@@ -551,15 +606,30 @@ static int bnxt_dcbnl_ieee_setpfc(struct net_device *dev, struct ieee_pfc *pfc)
 	return rc;
 }
 
+static int bnxt_dcbnl_ieee_dscp_app_prep(struct bnxt *bp, struct dcb_app *app)
+{
+	if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP) {
+		if (!bp->max_dscp_value)
+			return -ENOTSUPP;
+		if (app->protocol > bp->max_dscp_value)
+			return -EINVAL;
+	}
+	return 0;
+}
+
 static int bnxt_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 {
 	struct bnxt *bp = netdev_priv(dev);
-	int rc = -EINVAL;
+	int rc;
 
 	if (!(bp->dcbx_cap & DCB_CAP_DCBX_VER_IEEE) ||
 	    !(bp->dcbx_cap & DCB_CAP_DCBX_HOST))
 		return -EINVAL;
 
+	rc = bnxt_dcbnl_ieee_dscp_app_prep(bp, app);
+	if (rc)
+		return rc;
+
 	rc = dcb_ieee_setapp(dev, app);
 	if (rc)
 		return rc;
@@ -570,6 +640,9 @@ static int bnxt_dcbnl_ieee_setapp(struct net_device *dev, struct dcb_app *app)
 	     app->protocol == ROCE_V2_UDP_DPORT))
 		rc = bnxt_hwrm_set_dcbx_app(bp, app, true);
 
+	if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP)
+		rc = bnxt_hwrm_queue_dscp2pri_cfg(bp, app, true);
+
 	return rc;
 }
 
@@ -582,6 +655,10 @@ static int bnxt_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	    !(bp->dcbx_cap & DCB_CAP_DCBX_HOST))
 		return -EINVAL;
 
+	rc = bnxt_dcbnl_ieee_dscp_app_prep(bp, app);
+	if (rc)
+		return rc;
+
 	rc = dcb_ieee_delapp(dev, app);
 	if (rc)
 		return rc;
@@ -591,6 +668,9 @@ static int bnxt_dcbnl_ieee_delapp(struct net_device *dev, struct dcb_app *app)
 	     app->protocol == ROCE_V2_UDP_DPORT))
 		rc = bnxt_hwrm_set_dcbx_app(bp, app, false);
 
+	if (app->selector == IEEE_8021QAZ_APP_SEL_DSCP)
+		rc = bnxt_hwrm_queue_dscp2pri_cfg(bp, app, false);
+
 	return rc;
 }
 
@@ -642,6 +722,7 @@ void bnxt_dcb_init(struct bnxt *bp)
 	if (bp->hwrm_spec_code < 0x10501)
 		return;
 
+	bnxt_hwrm_queue_dscp_qcaps(bp);
 	bp->dcbx_cap = DCB_CAP_DCBX_VER_IEEE;
 	if (BNXT_PF(bp) && !(bp->fw_cap & BNXT_FW_CAP_LLDP_AGENT))
 		bp->dcbx_cap |= DCB_CAP_DCBX_HOST;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
index 69efde785f23..c0e16c03195a 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
@@ -33,6 +33,12 @@ struct bnxt_cos2bw_cfg {
 	u8			unused;
 };
 
+struct bnxt_dscp2pri_entry {
+	u8	dscp;
+	u8	mask;
+	u8	pri;
+};
+
 #define BNXT_LLQ(q_profile)	\
 	((q_profile) ==		\
 	 QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE)
-- 
cgit v1.2.3


From aabfc016e9a6db2a8c2da815fc84bfd5a2e8d221 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Sun, 5 Aug 2018 16:51:58 -0400
Subject: bnxt_en: Do not use the CNP CoS queue for networking traffic.

The CNP CoS queue is reserved for internal RDMA Congestion Notification
Packets (CNP) and should not be used for a TC.  Modify the CoS queue
discovery code to skip over the CNP CoS queue and to reduce
bp->max_tc accordingly.  However, if RDMA is disabled in NVRAM, the
the CNP CoS queue can be used for a TC.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 22 ++++++++++++++--------
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h |  4 ++++
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index dde904bccab9..d7f51ab85b45 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5281,7 +5281,8 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 	int rc = 0;
 	struct hwrm_queue_qportcfg_input req = {0};
 	struct hwrm_queue_qportcfg_output *resp = bp->hwrm_cmd_resp_addr;
-	u8 i, *qptr;
+	u8 i, j, *qptr;
+	bool no_rdma;
 
 	bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_QPORTCFG, -1, -1);
 
@@ -5299,19 +5300,24 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp)
 	if (bp->max_tc > BNXT_MAX_QUEUE)
 		bp->max_tc = BNXT_MAX_QUEUE;
 
+	no_rdma = !(bp->flags & BNXT_FLAG_ROCE_CAP);
+	qptr = &resp->queue_id0;
+	for (i = 0, j = 0; i < bp->max_tc; i++) {
+		bp->q_info[j].queue_id = *qptr++;
+		bp->q_info[j].queue_profile = *qptr++;
+		bp->tc_to_qidx[j] = j;
+		if (!BNXT_CNPQ(bp->q_info[j].queue_profile) ||
+		    (no_rdma && BNXT_PF(bp)))
+			j++;
+	}
+	bp->max_tc = max_t(u8, j, 1);
+
 	if (resp->queue_cfg_info & QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG)
 		bp->max_tc = 1;
 
 	if (bp->max_lltc > bp->max_tc)
 		bp->max_lltc = bp->max_tc;
 
-	qptr = &resp->queue_id0;
-	for (i = 0; i < bp->max_tc; i++) {
-		bp->q_info[i].queue_id = *qptr++;
-		bp->q_info[i].queue_profile = *qptr++;
-		bp->tc_to_qidx[i] = i;
-	}
-
 qportcfg_exit:
 	mutex_unlock(&bp->hwrm_cmd_lock);
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
index c0e16c03195a..6eed231de565 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.h
@@ -43,6 +43,10 @@ struct bnxt_dscp2pri_entry {
 	((q_profile) ==		\
 	 QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE)
 
+#define BNXT_CNPQ(q_profile)	\
+	((q_profile) ==		\
+	 QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP)
+
 #define HWRM_STRUCT_DATA_SUBTYPE_HOST_OPERATIONAL	0x0300
 
 void bnxt_dcb_init(struct bnxt *bp);
-- 
cgit v1.2.3


From f63421a70f9e7d6dac6ec06b4d9f7cf516f8a885 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Wed, 1 Aug 2018 18:05:52 +0800
Subject: arm64: dts: fsl: add clocks property for fman ptp timer node

This patch is to add clocks property for fman ptp timer node.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
index a56a408e9bf7..4664c33e0763 100644
--- a/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
+++ b/arch/arm64/boot/dts/freescale/qoriq-fman3-0.dtsi
@@ -80,4 +80,5 @@ ptp_timer0: ptp-timer@1afe000 {
 	compatible = "fsl,fman-ptp-timer";
 	reg = <0x0 0x1afe000 0x0 0x1000>;
 	interrupts = <GIC_SPI 44 IRQ_TYPE_LEVEL_HIGH>;
+	clocks = <&clockgen 3 0>;
 };
-- 
cgit v1.2.3


From a16b5da54d1f3a06df642b866779358fc64d00e2 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Wed, 1 Aug 2018 18:05:53 +0800
Subject: powerpc/mpc85xx: add clocks property for fman ptp timer node

This patch is to add clocks property for fman ptp timer node.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi   | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi   | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi  | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi  | 1 +
 arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi | 1 +
 5 files changed, 5 insertions(+)

diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi
index 6b124f73f67a..9b6cf9149937 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-0.dtsi
@@ -100,4 +100,5 @@ ptp_timer0: ptp-timer@4fe000 {
 	compatible = "fsl,fman-ptp-timer";
 	reg = <0x4fe000 0x1000>;
 	interrupts = <96 2 0 0>;
+	clocks = <&clockgen 3 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi
index b80aaf5f00a1..e95c11ff0417 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman-1.dtsi
@@ -100,4 +100,5 @@ ptp_timer1: ptp-timer@5fe000 {
 	compatible = "fsl,fman-ptp-timer";
 	reg = <0x5fe000 0x1000>;
 	interrupts = <97 2 0 0>;
+	clocks = <&clockgen 3 1>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi
index d3720fdde26c..d62b36c5a329 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-0.dtsi
@@ -105,4 +105,5 @@ ptp_timer0: ptp-timer@4fe000 {
 	compatible = "fsl,fman-ptp-timer";
 	reg = <0x4fe000 0x1000>;
 	interrupts = <96 2 0 0>;
+	clocks = <&clockgen 3 0>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi
index ae34c204a5bc..310232460500 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3-1.dtsi
@@ -105,4 +105,5 @@ ptp_timer1: ptp-timer@5fe000 {
 	compatible = "fsl,fman-ptp-timer";
 	reg = <0x5fe000 0x1000>;
 	interrupts = <97 2 0 0>;
+	clocks = <&clockgen 3 1>;
 };
diff --git a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
index 02f2755842cc..c90702b04a53 100644
--- a/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
+++ b/arch/powerpc/boot/dts/fsl/qoriq-fman3l-0.dtsi
@@ -93,4 +93,5 @@ ptp_timer0: ptp-timer@4fe000 {
 	compatible = "fsl,fman-ptp-timer";
 	reg = <0x4fe000 0x1000>;
 	interrupts = <96 2 0 0>;
+	clocks = <&clockgen 3 0>;
 };
-- 
cgit v1.2.3


From 91305f2812624c0cf7ccbb44133b66d3b24676e4 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Wed, 1 Aug 2018 18:05:54 +0800
Subject: ptp_qoriq: support automatic configuration for ptp timer

This patch is to support automatic configuration for ptp timer.
If required ptp dts properties are not provided, driver could
try to calculate a set of default configurations to initialize
the ptp timer. This makes the driver work for many boards which
don't have the required ptp dts properties in current kernel.
Also the users could set dts properties by themselves according
to their requirement.

Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c       | 111 ++++++++++++++++++++++++++++++++++++++++--
 include/linux/fsl/ptp_qoriq.h |   6 ++-
 2 files changed, 113 insertions(+), 4 deletions(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index a14c317b5a38..095c18532dc7 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -29,6 +29,7 @@
 #include <linux/of_platform.h>
 #include <linux/timex.h>
 #include <linux/slab.h>
+#include <linux/clk.h>
 
 #include <linux/fsl/ptp_qoriq.h>
 
@@ -317,6 +318,105 @@ static const struct ptp_clock_info ptp_qoriq_caps = {
 	.enable		= ptp_qoriq_enable,
 };
 
+/**
+ * qoriq_ptp_nominal_freq - calculate nominal frequency according to
+ *			    reference clock frequency
+ *
+ * @clk_src: reference clock frequency
+ *
+ * The nominal frequency is the desired clock frequency.
+ * It should be less than the reference clock frequency.
+ * It should be a factor of 1000MHz.
+ *
+ * Return the nominal frequency
+ */
+static u32 qoriq_ptp_nominal_freq(u32 clk_src)
+{
+	u32 remainder = 0;
+
+	clk_src /= 1000000;
+	remainder = clk_src % 100;
+	if (remainder) {
+		clk_src -= remainder;
+		clk_src += 100;
+	}
+
+	do {
+		clk_src -= 100;
+
+	} while (1000 % clk_src);
+
+	return clk_src * 1000000;
+}
+
+/**
+ * qoriq_ptp_auto_config - calculate a set of default configurations
+ *
+ * @qoriq_ptp: pointer to qoriq_ptp
+ * @node: pointer to device_node
+ *
+ * If below dts properties are not provided, this function will be
+ * called to calculate a set of default configurations for them.
+ *   "fsl,tclk-period"
+ *   "fsl,tmr-prsc"
+ *   "fsl,tmr-add"
+ *   "fsl,tmr-fiper1"
+ *   "fsl,tmr-fiper2"
+ *   "fsl,max-adj"
+ *
+ * Return 0 if success
+ */
+static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp,
+				 struct device_node *node)
+{
+	struct clk *clk;
+	u64 freq_comp;
+	u64 max_adj;
+	u32 nominal_freq;
+	u32 clk_src = 0;
+
+	qoriq_ptp->cksel = DEFAULT_CKSEL;
+
+	clk = of_clk_get(node, 0);
+	if (!IS_ERR(clk)) {
+		clk_src = clk_get_rate(clk);
+		clk_put(clk);
+	}
+
+	if (clk_src <= 100000000UL) {
+		pr_err("error reference clock value, or lower than 100MHz\n");
+		return -EINVAL;
+	}
+
+	nominal_freq = qoriq_ptp_nominal_freq(clk_src);
+	if (!nominal_freq)
+		return -EINVAL;
+
+	qoriq_ptp->tclk_period = 1000000000UL / nominal_freq;
+	qoriq_ptp->tmr_prsc = DEFAULT_TMR_PRSC;
+
+	/* Calculate initial frequency compensation value for TMR_ADD register.
+	 * freq_comp = ceil(2^32 / freq_ratio)
+	 * freq_ratio = reference_clock_freq / nominal_freq
+	 */
+	freq_comp = ((u64)1 << 32) * nominal_freq;
+	if (do_div(freq_comp, clk_src))
+		freq_comp++;
+
+	qoriq_ptp->tmr_add = freq_comp;
+	qoriq_ptp->tmr_fiper1 = DEFAULT_FIPER1_PERIOD - qoriq_ptp->tclk_period;
+	qoriq_ptp->tmr_fiper2 = DEFAULT_FIPER2_PERIOD - qoriq_ptp->tclk_period;
+
+	/* max_adj = 1000000000 * (freq_ratio - 1.0) - 1
+	 * freq_ratio = reference_clock_freq / nominal_freq
+	 */
+	max_adj = 1000000000ULL * (clk_src - nominal_freq);
+	max_adj = max_adj / nominal_freq - 1;
+	qoriq_ptp->caps.max_adj = max_adj;
+
+	return 0;
+}
+
 static int qoriq_ptp_probe(struct platform_device *dev)
 {
 	struct device_node *node = dev->dev.of_node;
@@ -332,7 +432,7 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 	if (!qoriq_ptp)
 		goto no_memory;
 
-	err = -ENODEV;
+	err = -EINVAL;
 
 	qoriq_ptp->caps = ptp_qoriq_caps;
 
@@ -351,10 +451,14 @@ static int qoriq_ptp_probe(struct platform_device *dev)
 				 "fsl,tmr-fiper2", &qoriq_ptp->tmr_fiper2) ||
 	    of_property_read_u32(node,
 				 "fsl,max-adj", &qoriq_ptp->caps.max_adj)) {
-		pr_err("device tree node missing required elements\n");
-		goto no_node;
+		pr_warn("device tree node missing required elements, try automatic configuration\n");
+
+		if (qoriq_ptp_auto_config(qoriq_ptp, node))
+			goto no_config;
 	}
 
+	err = -ENODEV;
+
 	qoriq_ptp->irq = platform_get_irq(dev, 0);
 
 	if (qoriq_ptp->irq < 0) {
@@ -436,6 +540,7 @@ no_ioremap:
 	release_resource(qoriq_ptp->rsrc);
 no_resource:
 	free_irq(qoriq_ptp->irq, qoriq_ptp);
+no_config:
 no_node:
 	kfree(qoriq_ptp);
 no_memory:
diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h
index dc3dac40f069..c1f003aadcce 100644
--- a/include/linux/fsl/ptp_qoriq.h
+++ b/include/linux/fsl/ptp_qoriq.h
@@ -127,9 +127,13 @@ struct qoriq_ptp_registers {
 
 
 #define DRIVER		"ptp_qoriq"
-#define DEFAULT_CKSEL	1
 #define N_EXT_TS	2
 
+#define DEFAULT_CKSEL		1
+#define DEFAULT_TMR_PRSC	2
+#define DEFAULT_FIPER1_PERIOD	1000000000
+#define DEFAULT_FIPER2_PERIOD	100000
+
 struct qoriq_ptp {
 	void __iomem *base;
 	struct qoriq_ptp_registers regs;
-- 
cgit v1.2.3


From 5f379ef51bc967567bbddacdcdecb772d4d7c3b3 Mon Sep 17 00:00:00 2001
From: Georg Kohmann <geokohma@cisco.com>
Date: Thu, 2 Aug 2018 13:56:58 +0200
Subject: ipv6: icmp: Updating pmtu for link local route

When a ICMPV6_PKT_TOOBIG is received from a link local address the pmtu will
be updated on a route with an arbitrary interface index. Subsequent packets
sent back to the same link local address may therefore end up not
considering the updated pmtu.

Current behavior breaks TAHI v6LC4.1.4 Reduce PMTU On-link. Referring to RFC
1981: Section 3: "Note that Path MTU Discovery must be performed even in
cases where a node "thinks" a destination is attached to the same link as
itself. In a situation such as when a neighboring router acts as proxy [ND]
for some destination, the destination can to appear to be directly
connected but is in fact more than one hop away."

Using the interface index from the incoming ICMPV6_PKT_TOOBIG when updating
the pmtu.

Signed-off-by: Georg Kohmann <geokohma@cisco.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/icmp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 00d159d431dc..7f6b1f81c200 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -92,7 +92,7 @@ static void icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct net *net = dev_net(skb->dev);
 
 	if (type == ICMPV6_PKT_TOOBIG)
-		ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL));
+		ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL));
 	else if (type == NDISC_REDIRECT)
 		ip6_redirect(skb, net, skb->dev->ifindex, 0,
 			     sock_net_uid(net, NULL));
-- 
cgit v1.2.3


From cfb4099fb4c101dad283a163c9525240ef4a1a99 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Thu, 2 Aug 2018 20:43:10 +0530
Subject: net/tls: Mark the end in scatterlist table

Function zerocopy_from_iter() unmarks the 'end' in input sgtable while
adding new entries in it. The last entry in sgtable remained unmarked.
This results in KASAN error report on using apis like sg_nents(). Before
returning, the function needs to mark the 'end' in the last entry it
adds.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Acked-by: Dave Watson <davejwatson@fb.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/tls/tls_sw.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index ff3a6904a722..83d67df33f0c 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -311,6 +311,9 @@ static int zerocopy_from_iter(struct sock *sk, struct iov_iter *from,
 		}
 	}
 
+	/* Mark the end in the last sg entry if newly added */
+	if (num_elem > *pages_used)
+		sg_mark_end(&to[num_elem - 1]);
 out:
 	if (rc)
 		iov_iter_revert(from, size - *size_used);
-- 
cgit v1.2.3


From 7969e5c40dfd04799d4341f1b7cd266b6e47f227 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Thu, 2 Aug 2018 23:34:37 +0000
Subject: ip: discard IPv4 datagrams with overlapping segments.

This behavior is required in IPv6, and there is little need
to tolerate overlapping fragments in IPv4. This change
simplifies the code and eliminates potential DDoS attack vectors.

Tested: ran ip_defrag selftest (not yet available uptream).

Suggested-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Acked-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/snmp.h |  1 +
 net/ipv4/ip_fragment.c    | 75 ++++++++++++-----------------------------------
 net/ipv4/proc.c           |  1 +
 3 files changed, 21 insertions(+), 56 deletions(-)

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index e5ebc83827ab..f80135e5feaa 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -56,6 +56,7 @@ enum
 	IPSTATS_MIB_ECT1PKTS,			/* InECT1Pkts */
 	IPSTATS_MIB_ECT0PKTS,			/* InECT0Pkts */
 	IPSTATS_MIB_CEPKTS,			/* InCEPkts */
+	IPSTATS_MIB_REASM_OVERLAPS,		/* ReasmOverlaps */
 	__IPSTATS_MIB_MAX
 };
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index d14d741fb05e..960bf5eab59f 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -277,6 +277,7 @@ static int ip_frag_reinit(struct ipq *qp)
 /* Add new segment to existing queue. */
 static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 {
+	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct sk_buff *prev, *next;
 	struct net_device *dev;
 	unsigned int fragsize;
@@ -357,65 +358,23 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	}
 
 found:
-	/* We found where to put this one.  Check for overlap with
-	 * preceding fragment, and, if needed, align things so that
-	 * any overlaps are eliminated.
+	/* RFC5722, Section 4, amended by Errata ID : 3089
+	 *                          When reassembling an IPv6 datagram, if
+	 *   one or more its constituent fragments is determined to be an
+	 *   overlapping fragment, the entire datagram (and any constituent
+	 *   fragments) MUST be silently discarded.
+	 *
+	 * We do the same here for IPv4.
 	 */
-	if (prev) {
-		int i = (prev->ip_defrag_offset + prev->len) - offset;
 
-		if (i > 0) {
-			offset += i;
-			err = -EINVAL;
-			if (end <= offset)
-				goto err;
-			err = -ENOMEM;
-			if (!pskb_pull(skb, i))
-				goto err;
-			if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-				skb->ip_summed = CHECKSUM_NONE;
-		}
-	}
+	/* Is there an overlap with the previous fragment? */
+	if (prev &&
+	    (prev->ip_defrag_offset + prev->len) > offset)
+		goto discard_qp;
 
-	err = -ENOMEM;
-
-	while (next && next->ip_defrag_offset < end) {
-		int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */
-
-		if (i < next->len) {
-			int delta = -next->truesize;
-
-			/* Eat head of the next overlapped fragment
-			 * and leave the loop. The next ones cannot overlap.
-			 */
-			if (!pskb_pull(next, i))
-				goto err;
-			delta += next->truesize;
-			if (delta)
-				add_frag_mem_limit(qp->q.net, delta);
-			next->ip_defrag_offset += i;
-			qp->q.meat -= i;
-			if (next->ip_summed != CHECKSUM_UNNECESSARY)
-				next->ip_summed = CHECKSUM_NONE;
-			break;
-		} else {
-			struct sk_buff *free_it = next;
-
-			/* Old fragment is completely overridden with
-			 * new one drop it.
-			 */
-			next = next->next;
-
-			if (prev)
-				prev->next = next;
-			else
-				qp->q.fragments = next;
-
-			qp->q.meat -= free_it->len;
-			sub_frag_mem_limit(qp->q.net, free_it->truesize);
-			kfree_skb(free_it);
-		}
-	}
+	/* Is there an overlap with the next fragment? */
+	if (next && next->ip_defrag_offset < end)
+		goto discard_qp;
 
 	/* Note : skb->ip_defrag_offset and skb->dev share the same location */
 	dev = skb->dev;
@@ -463,6 +422,10 @@ found:
 	skb_dst_drop(skb);
 	return -EINPROGRESS;
 
+discard_qp:
+	inet_frag_kill(&qp->q);
+	err = -EINVAL;
+	__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
 err:
 	kfree_skb(skb);
 	return err;
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index b46e4cf9a55a..70289682a670 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -119,6 +119,7 @@ static const struct snmp_mib snmp4_ipextstats_list[] = {
 	SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
 	SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
 	SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
+	SNMP_MIB_ITEM("ReasmOverlaps", IPSTATS_MIB_REASM_OVERLAPS),
 	SNMP_MIB_SENTINEL
 };
 
-- 
cgit v1.2.3


From 385114dec8a49b5e5945e77ba7de6356106713f4 Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Thu, 2 Aug 2018 23:34:38 +0000
Subject: net: modify skb_rbtree_purge to return the truesize of all purged
 skbs.

Tested: see the next patch is the series.

Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 +-
 net/core/skbuff.c      | 6 +++++-
 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index fd3cb1b247df..47848367c816 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2585,7 +2585,7 @@ static inline void __skb_queue_purge(struct sk_buff_head *list)
 		kfree_skb(skb);
 }
 
-void skb_rbtree_purge(struct rb_root *root);
+unsigned int skb_rbtree_purge(struct rb_root *root);
 
 void *netdev_alloc_frag(unsigned int fragsz);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 51b0a9126e12..8d574a88125d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2858,23 +2858,27 @@ EXPORT_SYMBOL(skb_queue_purge);
 /**
  *	skb_rbtree_purge - empty a skb rbtree
  *	@root: root of the rbtree to empty
+ *	Return value: the sum of truesizes of all purged skbs.
  *
  *	Delete all buffers on an &sk_buff rbtree. Each buffer is removed from
  *	the list and one reference dropped. This function does not take
  *	any lock. Synchronization should be handled by the caller (e.g., TCP
  *	out-of-order queue is protected by the socket lock).
  */
-void skb_rbtree_purge(struct rb_root *root)
+unsigned int skb_rbtree_purge(struct rb_root *root)
 {
 	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
 
 	while (p) {
 		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
 
 		p = rb_next(p);
 		rb_erase(&skb->rbnode, root);
+		sum += skb->truesize;
 		kfree_skb(skb);
 	}
+	return sum;
 }
 
 /**
-- 
cgit v1.2.3


From fa0f527358bd900ef92f925878ed6bfbd51305cc Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Thu, 2 Aug 2018 23:34:39 +0000
Subject: ip: use rb trees for IP frag queue.

Similar to TCP OOO RX queue, it makes sense to use rb trees to store
IP fragments, so that OOO fragments are inserted faster.

Tested:

- a follow-up patch contains a rather comprehensive ip defrag
  self-test (functional)
- ran neper `udp_stream -c -H <host> -F 100 -l 300 -T 20`:
    netstat --statistics
    Ip:
        282078937 total packets received
        0 forwarded
        0 incoming packets discarded
        946760 incoming packets delivered
        18743456 requests sent out
        101 fragments dropped after timeout
        282077129 reassemblies required
        944952 packets reassembled ok
        262734239 packet reassembles failed
   (The numbers/stats above are somewhat better re:
    reassemblies vs a kernel without this patchset. More
    comprehensive performance testing TBD).

Reported-by: Jann Horn <jannh@google.com>
Reported-by: Juha-Matti Tilli <juha-matti.tilli@iki.fi>
Suggested-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h                  |   9 +-
 include/net/inet_frag.h                 |   3 +-
 net/ipv4/inet_fragment.c                |  16 +--
 net/ipv4/ip_fragment.c                  | 182 ++++++++++++++++++--------------
 net/ipv6/netfilter/nf_conntrack_reasm.c |   1 +
 net/ipv6/reassembly.c                   |   1 +
 6 files changed, 121 insertions(+), 91 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 47848367c816..7ebdf158a795 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -676,13 +676,16 @@ struct sk_buff {
 				 * UDP receive path is one user.
 				 */
 				unsigned long		dev_scratch;
-				int			ip_defrag_offset;
 			};
 		};
-		struct rb_node		rbnode; /* used in netem & tcp stack */
+		struct rb_node		rbnode; /* used in netem, ip4 defrag, and tcp stack */
 		struct list_head	list;
 	};
-	struct sock		*sk;
+
+	union {
+		struct sock		*sk;
+		int			ip_defrag_offset;
+	};
 
 	union {
 		ktime_t		tstamp;
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index f4272a29dc44..b86d14528188 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -75,7 +75,8 @@ struct inet_frag_queue {
 	struct timer_list	timer;
 	spinlock_t		lock;
 	refcount_t		refcnt;
-	struct sk_buff		*fragments;
+	struct sk_buff		*fragments;  /* Used in IPv6. */
+	struct rb_root		rb_fragments; /* Used in IPv4. */
 	struct sk_buff		*fragments_tail;
 	ktime_t			stamp;
 	int			len;
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index ccd140e4082d..6d258a5669e7 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -137,12 +137,16 @@ void inet_frag_destroy(struct inet_frag_queue *q)
 	fp = q->fragments;
 	nf = q->net;
 	f = nf->f;
-	while (fp) {
-		struct sk_buff *xp = fp->next;
-
-		sum_truesize += fp->truesize;
-		kfree_skb(fp);
-		fp = xp;
+	if (fp) {
+		do {
+			struct sk_buff *xp = fp->next;
+
+			sum_truesize += fp->truesize;
+			kfree_skb(fp);
+			fp = xp;
+		} while (fp);
+	} else {
+		sum_truesize = skb_rbtree_purge(&q->rb_fragments);
 	}
 	sum = sum_truesize + f->qsize;
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 960bf5eab59f..0e8f8de77e71 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -136,7 +136,7 @@ static void ip_expire(struct timer_list *t)
 {
 	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	const struct iphdr *iph;
-	struct sk_buff *head;
+	struct sk_buff *head = NULL;
 	struct net *net;
 	struct ipq *qp;
 	int err;
@@ -152,14 +152,31 @@ static void ip_expire(struct timer_list *t)
 
 	ipq_kill(qp);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
-
-	head = qp->q.fragments;
-
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
-	if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head)
+	if (!qp->q.flags & INET_FRAG_FIRST_IN)
 		goto out;
 
+	/* sk_buff::dev and sk_buff::rbnode are unionized. So we
+	 * pull the head out of the tree in order to be able to
+	 * deal with head->dev.
+	 */
+	if (qp->q.fragments) {
+		head = qp->q.fragments;
+		qp->q.fragments = head->next;
+	} else {
+		head = skb_rb_first(&qp->q.rb_fragments);
+		if (!head)
+			goto out;
+		rb_erase(&head->rbnode, &qp->q.rb_fragments);
+		memset(&head->rbnode, 0, sizeof(head->rbnode));
+		barrier();
+	}
+	if (head == qp->q.fragments_tail)
+		qp->q.fragments_tail = NULL;
+
+	sub_frag_mem_limit(qp->q.net, head->truesize);
+
 	head->dev = dev_get_by_index_rcu(net, qp->iif);
 	if (!head->dev)
 		goto out;
@@ -179,16 +196,16 @@ static void ip_expire(struct timer_list *t)
 	    (skb_rtable(head)->rt_type != RTN_LOCAL))
 		goto out;
 
-	skb_get(head);
 	spin_unlock(&qp->q.lock);
 	icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0);
-	kfree_skb(head);
 	goto out_rcu_unlock;
 
 out:
 	spin_unlock(&qp->q.lock);
 out_rcu_unlock:
 	rcu_read_unlock();
+	if (head)
+		kfree_skb(head);
 	ipq_put(qp);
 }
 
@@ -231,7 +248,7 @@ static int ip_frag_too_far(struct ipq *qp)
 	end = atomic_inc_return(&peer->rid);
 	qp->rid = end;
 
-	rc = qp->q.fragments && (end - start) > max;
+	rc = qp->q.fragments_tail && (end - start) > max;
 
 	if (rc) {
 		struct net *net;
@@ -245,7 +262,6 @@ static int ip_frag_too_far(struct ipq *qp)
 
 static int ip_frag_reinit(struct ipq *qp)
 {
-	struct sk_buff *fp;
 	unsigned int sum_truesize = 0;
 
 	if (!mod_timer(&qp->q.timer, jiffies + qp->q.net->timeout)) {
@@ -253,20 +269,14 @@ static int ip_frag_reinit(struct ipq *qp)
 		return -ETIMEDOUT;
 	}
 
-	fp = qp->q.fragments;
-	do {
-		struct sk_buff *xp = fp->next;
-
-		sum_truesize += fp->truesize;
-		kfree_skb(fp);
-		fp = xp;
-	} while (fp);
+	sum_truesize = skb_rbtree_purge(&qp->q.rb_fragments);
 	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	qp->q.flags = 0;
 	qp->q.len = 0;
 	qp->q.meat = 0;
 	qp->q.fragments = NULL;
+	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
 	qp->iif = 0;
 	qp->ecn = 0;
@@ -278,7 +288,8 @@ static int ip_frag_reinit(struct ipq *qp)
 static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
-	struct sk_buff *prev, *next;
+	struct rb_node **rbn, *parent;
+	struct sk_buff *skb1;
 	struct net_device *dev;
 	unsigned int fragsize;
 	int flags, offset;
@@ -341,58 +352,58 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	if (err)
 		goto err;
 
-	/* Find out which fragments are in front and at the back of us
-	 * in the chain of fragments so far.  We must know where to put
-	 * this fragment, right?
-	 */
-	prev = qp->q.fragments_tail;
-	if (!prev || prev->ip_defrag_offset < offset) {
-		next = NULL;
-		goto found;
-	}
-	prev = NULL;
-	for (next = qp->q.fragments; next != NULL; next = next->next) {
-		if (next->ip_defrag_offset >= offset)
-			break;	/* bingo! */
-		prev = next;
-	}
+	/* Note : skb->rbnode and skb->dev share the same location. */
+	dev = skb->dev;
+	/* Makes sure compiler wont do silly aliasing games */
+	barrier();
 
-found:
 	/* RFC5722, Section 4, amended by Errata ID : 3089
 	 *                          When reassembling an IPv6 datagram, if
 	 *   one or more its constituent fragments is determined to be an
 	 *   overlapping fragment, the entire datagram (and any constituent
 	 *   fragments) MUST be silently discarded.
 	 *
-	 * We do the same here for IPv4.
+	 * We do the same here for IPv4 (and increment an snmp counter).
 	 */
 
-	/* Is there an overlap with the previous fragment? */
-	if (prev &&
-	    (prev->ip_defrag_offset + prev->len) > offset)
-		goto discard_qp;
-
-	/* Is there an overlap with the next fragment? */
-	if (next && next->ip_defrag_offset < end)
-		goto discard_qp;
+	/* Find out where to put this fragment.  */
+	skb1 = qp->q.fragments_tail;
+	if (!skb1) {
+		/* This is the first fragment we've received. */
+		rb_link_node(&skb->rbnode, NULL, &qp->q.rb_fragments.rb_node);
+		qp->q.fragments_tail = skb;
+	} else if ((skb1->ip_defrag_offset + skb1->len) < end) {
+		/* This is the common/special case: skb goes to the end. */
+		/* Detect and discard overlaps. */
+		if (offset < (skb1->ip_defrag_offset + skb1->len))
+			goto discard_qp;
+		/* Insert after skb1. */
+		rb_link_node(&skb->rbnode, &skb1->rbnode, &skb1->rbnode.rb_right);
+		qp->q.fragments_tail = skb;
+	} else {
+		/* Binary search. Note that skb can become the first fragment, but
+		 * not the last (covered above). */
+		rbn = &qp->q.rb_fragments.rb_node;
+		do {
+			parent = *rbn;
+			skb1 = rb_to_skb(parent);
+			if (end <= skb1->ip_defrag_offset)
+				rbn = &parent->rb_left;
+			else if (offset >= skb1->ip_defrag_offset + skb1->len)
+				rbn = &parent->rb_right;
+			else /* Found an overlap with skb1. */
+				goto discard_qp;
+		} while (*rbn);
+		/* Here we have parent properly set, and rbn pointing to
+		 * one of its NULL left/right children. Insert skb. */
+		rb_link_node(&skb->rbnode, parent, rbn);
+	}
+	rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
 
-	/* Note : skb->ip_defrag_offset and skb->dev share the same location */
-	dev = skb->dev;
 	if (dev)
 		qp->iif = dev->ifindex;
-	/* Makes sure compiler wont do silly aliasing games */
-	barrier();
 	skb->ip_defrag_offset = offset;
 
-	/* Insert this fragment in the chain of fragments. */
-	skb->next = next;
-	if (!next)
-		qp->q.fragments_tail = skb;
-	if (prev)
-		prev->next = skb;
-	else
-		qp->q.fragments = skb;
-
 	qp->q.stamp = skb->tstamp;
 	qp->q.meat += skb->len;
 	qp->ecn |= ecn;
@@ -414,7 +425,7 @@ found:
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = ip_frag_reasm(qp, prev, dev);
+		err = ip_frag_reasm(qp, skb, dev);
 		skb->_skb_refdst = orefdst;
 		return err;
 	}
@@ -431,15 +442,15 @@ err:
 	return err;
 }
 
-
 /* Build a new IP datagram from all its fragments. */
-
-static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
+static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 			 struct net_device *dev)
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct iphdr *iph;
-	struct sk_buff *fp, *head = qp->q.fragments;
+	struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments);
+	struct sk_buff **nextp; /* To build frag_list. */
+	struct rb_node *rbn;
 	int len;
 	int ihlen;
 	int err;
@@ -453,25 +464,20 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		goto out_fail;
 	}
 	/* Make the one we just received the head. */
-	if (prev) {
-		head = prev->next;
-		fp = skb_clone(head, GFP_ATOMIC);
+	if (head != skb) {
+		fp = skb_clone(skb, GFP_ATOMIC);
 		if (!fp)
 			goto out_nomem;
-
-		fp->next = head->next;
-		if (!fp->next)
+		rb_replace_node(&skb->rbnode, &fp->rbnode, &qp->q.rb_fragments);
+		if (qp->q.fragments_tail == skb)
 			qp->q.fragments_tail = fp;
-		prev->next = fp;
-
-		skb_morph(head, qp->q.fragments);
-		head->next = qp->q.fragments->next;
-
-		consume_skb(qp->q.fragments);
-		qp->q.fragments = head;
+		skb_morph(skb, head);
+		rb_replace_node(&head->rbnode, &skb->rbnode,
+				&qp->q.rb_fragments);
+		consume_skb(head);
+		head = skb;
 	}
 
-	WARN_ON(!head);
 	WARN_ON(head->ip_defrag_offset != 0);
 
 	/* Allocate a new buffer for the datagram. */
@@ -496,24 +502,35 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 		clone = alloc_skb(0, GFP_ATOMIC);
 		if (!clone)
 			goto out_nomem;
-		clone->next = head->next;
-		head->next = clone;
 		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
 		skb_frag_list_init(head);
 		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
 			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
 		clone->len = clone->data_len = head->data_len - plen;
-		head->data_len -= clone->len;
-		head->len -= clone->len;
+		skb->truesize += clone->truesize;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
 		add_frag_mem_limit(qp->q.net, clone->truesize);
+		skb_shinfo(head)->frag_list = clone;
+		nextp = &clone->next;
+	} else {
+		nextp = &skb_shinfo(head)->frag_list;
 	}
 
-	skb_shinfo(head)->frag_list = head->next;
 	skb_push(head, head->data - skb_network_header(head));
 
-	for (fp=head->next; fp; fp = fp->next) {
+	/* Traverse the tree in order, to build frag_list. */
+	rbn = rb_next(&head->rbnode);
+	rb_erase(&head->rbnode, &qp->q.rb_fragments);
+	while (rbn) {
+		struct rb_node *rbnext = rb_next(rbn);
+		fp = rb_to_skb(rbn);
+		rb_erase(rbn, &qp->q.rb_fragments);
+		rbn = rbnext;
+		*nextp = fp;
+		nextp = &fp->next;
+		fp->prev = NULL;
+		memset(&fp->rbnode, 0, sizeof(fp->rbnode));
 		head->data_len += fp->len;
 		head->len += fp->len;
 		if (head->ip_summed != fp->ip_summed)
@@ -524,7 +541,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 	}
 	sub_frag_mem_limit(qp->q.net, head->truesize);
 
+	*nextp = NULL;
 	head->next = NULL;
+	head->prev = NULL;
 	head->dev = dev;
 	head->tstamp = qp->q.stamp;
 	IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size);
@@ -552,6 +571,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
 
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMOKS);
 	qp->q.fragments = NULL;
+	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
 	return 0;
 
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 0610bdab721c..38d69ef516d5 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -463,6 +463,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev,  struct net_devic
 					  head->csum);
 
 	fq->q.fragments = NULL;
+	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 
 	return true;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 6edd2ac8ae4b..b4e558ab39fa 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -405,6 +405,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
 	__IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS);
 	rcu_read_unlock();
 	fq->q.fragments = NULL;
+	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 	return 1;
 
-- 
cgit v1.2.3


From 0ed4229b08c13c84a3c301a08defdc9e7f4467e6 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Fri, 3 Aug 2018 02:22:20 +0200
Subject: ipv6: defrag: drop non-last frags smaller than min mtu

don't bother with pathological cases, they only waste cycles.
IPv6 requires a minimum MTU of 1280 so we should never see fragments
smaller than this (except last frag).

v3: don't use awkward "-offset + len"
v2: drop IPv4 part, which added same check w. IPV4_MIN_MTU (68).
    There were concerns that there could be even smaller frags
    generated by intermediate nodes, e.g. on radio networks.

Cc: Peter Oskolkov <posk@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++++
 net/ipv6/reassembly.c                   | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 38d69ef516d5..2a14d8b65924 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -558,6 +558,10 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
+	if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
+	    fhdr->frag_off & htons(IP6_MF))
+		return -EINVAL;
+
 	skb_orphan(skb);
 	fq = fq_find(net, fhdr->identification, user, hdr,
 		     skb->dev ? skb->dev->ifindex : 0);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index b4e558ab39fa..5c5b4f79296e 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -456,6 +456,10 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		return 1;
 	}
 
+	if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU &&
+	    fhdr->frag_off & htons(IP6_MF))
+		goto fail_hdr;
+
 	iif = skb->dev ? skb->dev->ifindex : 0;
 	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
-- 
cgit v1.2.3


From a6bcfc89694ed8cb482a82cdc8b93aae63a8b691 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Fri, 3 Aug 2018 15:45:21 +0800
Subject: net: check extack._msg before print

dev_set_mtu_ext is able to fail with a valid mtu value, at that
condition, extack._msg is not set and random since it is in stack,
then kernel will crash when print it.

Fixes: 7a4c53bee3324a ("net: report invalid mtu value via netlink extack")
Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/dev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 36e994519488..f68122f0ab02 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7583,8 +7583,9 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 	struct netlink_ext_ack extack;
 	int err;
 
+	memset(&extack, 0, sizeof(extack));
 	err = dev_set_mtu_ext(dev, new_mtu, &extack);
-	if (err)
+	if (err && extack._msg)
 		net_err_ratelimited("%s: %s\n", dev->name, extack._msg);
 	return err;
 }
-- 
cgit v1.2.3


From 1cbc36a53b60d43daa686280385b1ddbe51d5809 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Fri, 3 Aug 2018 22:27:55 +0300
Subject: net: sched: cls_flower: Fix an error code in fl_tmplt_create()

We forgot to set the error code on this path, so we return NULL instead
of an error pointer.  In the current code kzalloc() won't fail for small
allocations so this doesn't really affect runtime.

Fixes: b95ec7eb3b4d ("net: sched: cls_flower: implement chain templates")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index e8bd08ba998a..a3b69bb6f4b0 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1250,8 +1250,10 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain,
 		goto errout_tb;
 
 	tmplt = kzalloc(sizeof(*tmplt), GFP_KERNEL);
-	if (!tmplt)
+	if (!tmplt) {
+		err = -ENOMEM;
 		goto errout_tb;
+	}
 	tmplt->chain = chain;
 	err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack);
 	if (err)
-- 
cgit v1.2.3


From b633d4405bb276518812fbc20a5c61ce4cef25ae Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 21:42:05 -0500
Subject: virtio-net: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1402059 ("Missing break in switch")
Addresses-Coverity-ID: 1402060 ("Missing break in switch")
Addresses-Coverity-ID: 1402061 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 14f661cbae18..62311dde6e71 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -697,6 +697,7 @@ static struct sk_buff *receive_small(struct net_device *dev,
 			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
+			/* fall through */
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
 		case XDP_DROP:
@@ -876,8 +877,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev,
 			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
+			/* fall through */
 		case XDP_ABORTED:
 			trace_xdp_exception(vi->dev, xdp_prog, act);
+			/* fall through */
 		case XDP_DROP:
 			if (unlikely(xdp_page != page))
 				__free_pages(xdp_page, 0);
-- 
cgit v1.2.3


From 671ae8af05d58a74e58c39a7243836ec836baf2d Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 5 Aug 2018 09:03:06 +0300
Subject: mlxsw: reg: Add QoS Switch Traffic Class Table is Multicast-Aware
 Register

This register configures if the Switch Priority to Traffic Class mapping
is based on Multicast packet indication. If so, then multicast packets
will get a Traffic Class that is plus (cap_max_tclass_data/2) the value
configured by QTCT.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/reg.h | 37 +++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index e52841627966..9f344914c4a5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -3544,6 +3544,42 @@ mlxsw_reg_qpdpm_dscp_pack(char *payload, unsigned short dscp, u8 prio)
 	mlxsw_reg_qpdpm_dscp_entry_prio_set(payload, dscp, prio);
 }
 
+/* QTCTM - QoS Switch Traffic Class Table is Multicast-Aware Register
+ * ------------------------------------------------------------------
+ * This register configures if the Switch Priority to Traffic Class mapping is
+ * based on Multicast packet indication. If so, then multicast packets will get
+ * a Traffic Class that is plus (cap_max_tclass_data/2) the value configured by
+ * QTCT.
+ * By default, Switch Priority to Traffic Class mapping is not based on
+ * Multicast packet indication.
+ */
+#define MLXSW_REG_QTCTM_ID 0x401A
+#define MLXSW_REG_QTCTM_LEN 0x08
+
+MLXSW_REG_DEFINE(qtctm, MLXSW_REG_QTCTM_ID, MLXSW_REG_QTCTM_LEN);
+
+/* reg_qtctm_local_port
+ * Local port number.
+ * No support for CPU port.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, qtctm, local_port, 0x00, 16, 8);
+
+/* reg_qtctm_mc
+ * Multicast Mode
+ * Whether Switch Priority to Traffic Class mapping is based on Multicast packet
+ * indication (default is 0, not based on Multicast packet indication).
+ */
+MLXSW_ITEM32(reg, qtctm, mc, 0x04, 0, 1);
+
+static inline void
+mlxsw_reg_qtctm_pack(char *payload, u8 local_port, bool mc)
+{
+	MLXSW_REG_ZERO(qtctm, payload);
+	mlxsw_reg_qtctm_local_port_set(payload, local_port);
+	mlxsw_reg_qtctm_mc_set(payload, mc);
+}
+
 /* PMLP - Ports Module to Local Port Register
  * ------------------------------------------
  * Configures the assignment of modules to local ports.
@@ -8761,6 +8797,7 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(qrwe),
 	MLXSW_REG(qpdsm),
 	MLXSW_REG(qpdpm),
+	MLXSW_REG(qtctm),
 	MLXSW_REG(pmlp),
 	MLXSW_REG(pmtu),
 	MLXSW_REG(ptys),
-- 
cgit v1.2.3


From d0a07d6ada004ddaf010888a66d72ef606336bf4 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 5 Aug 2018 09:03:07 +0300
Subject: mlxsw: spectrum: Fix a typo

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 039228525fb1..f75bc11f6357 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2795,7 +2795,7 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 			return err;
 	}
 
-	/* Make sure the max shaper is disabled in all hierarcies that
+	/* Make sure the max shaper is disabled in all hierarchies that
 	 * support it.
 	 */
 	err = mlxsw_sp_port_ets_maxrate_set(mlxsw_sp_port,
-- 
cgit v1.2.3


From 7b819530669458c3af6d44edfc9cb34958492bca Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Sun, 5 Aug 2018 09:03:08 +0300
Subject: mlxsw: spectrum: Configure MC-aware mode on mlxsw ports

In order to give unicast traffic precedence over BUM traffic, configure
multicast-aware mode on all ports.

Under multicast-aware regime, when assigning traffic class to a packet,
the switch doesn't merely take the value prescribed by the QTCT
register. For BUM traffic, it instead assigns that value plus 8.

ETS elements for TCs 8..15 thus need to be configured as well. Extend
mlxsw_sp_port_ets_init() so that it maps each of them to the same
subgroup as their corresponding TC from the range 0..7, such that TCs X
and X+8 map to the same subgroup.

The existing code configures TCs with strict priority. So far this was
immaterial, because each TC had its own subgroup. Now that two TCs share
a subgroup it becomes important. TCs are prioritized in order of 7, 6,
..., 0, 15, 14, ..., 8: the higher TCs used for BUM traffic end up being
deprioritized. Since that's what's needed, keep that configuration as it
is, and configure the new TCs likewise.

Finally in mlxsw_sp_port_create(), invoke configuration of QTCTM to
enable MC-aware mode on each port.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 27 ++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index f75bc11f6357..028ecc9aa5f1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2793,6 +2793,13 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 					    false, 0);
 		if (err)
 			return err;
+
+		err = mlxsw_sp_port_ets_set(mlxsw_sp_port,
+					    MLXSW_REG_QEEC_HIERARCY_TC,
+					    i + 8, i,
+					    false, 0);
+		if (err)
+			return err;
 	}
 
 	/* Make sure the max shaper is disabled in all hierarchies that
@@ -2830,6 +2837,16 @@ static int mlxsw_sp_port_ets_init(struct mlxsw_sp_port *mlxsw_sp_port)
 	return 0;
 }
 
+static int mlxsw_sp_port_tc_mc_mode_set(struct mlxsw_sp_port *mlxsw_sp_port,
+					bool enable)
+{
+	struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp;
+	char qtctm_pl[MLXSW_REG_QTCTM_LEN];
+
+	mlxsw_reg_qtctm_pack(qtctm_pl, mlxsw_sp_port->local_port, enable);
+	return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qtctm), qtctm_pl);
+}
+
 static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 				bool split, u8 module, u8 width, u8 lane)
 {
@@ -2958,6 +2975,13 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u8 local_port,
 		goto err_port_ets_init;
 	}
 
+	err = mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, true);
+	if (err) {
+		dev_err(mlxsw_sp->bus_info->dev, "Port %d: Failed to initialize TC MC mode\n",
+			mlxsw_sp_port->local_port);
+		goto err_port_tc_mc_mode;
+	}
+
 	/* ETS and buffers must be initialized before DCB. */
 	err = mlxsw_sp_port_dcb_init(mlxsw_sp_port);
 	if (err) {
@@ -3014,6 +3038,8 @@ err_port_qdiscs_init:
 err_port_fids_init:
 	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
 err_port_dcb_init:
+	mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false);
+err_port_tc_mc_mode:
 err_port_ets_init:
 err_port_buffers_init:
 err_port_admin_status_set:
@@ -3048,6 +3074,7 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port)
 	mlxsw_sp_tc_qdisc_fini(mlxsw_sp_port);
 	mlxsw_sp_port_fids_fini(mlxsw_sp_port);
 	mlxsw_sp_port_dcb_fini(mlxsw_sp_port);
+	mlxsw_sp_port_tc_mc_mode_set(mlxsw_sp_port, false);
 	mlxsw_sp_port_swid_set(mlxsw_sp_port, MLXSW_PORT_SWID_DISABLED_PORT);
 	mlxsw_sp_port_module_unmap(mlxsw_sp_port);
 	kfree(mlxsw_sp_port->sample);
-- 
cgit v1.2.3


From 64f61cddf1934277e9fbb77d3d67308ffbfd4fa3 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Sun, 5 Aug 2018 22:35:56 +0300
Subject: tc-testing: fix ip address in u32 test

Fix expected ip address to actually match configured ip address.
Fix test to expect single matched filter.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tc-tests/filters/tests.json | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
index 5fa02d86b35f..99a5ffca1088 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json
@@ -12,8 +12,8 @@
         "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: protocol ip prio 1 u32 match ip src 127.0.0.1/32 flowid 1:1 action ok",
         "expExitCode": "0",
         "verifyCmd": "$TC filter show dev $DEV1 parent ffff:",
-        "matchPattern": "match 7f000002/ffffffff at 12",
-        "matchCount": "0",
+        "matchPattern": "match 7f000001/ffffffff at 12",
+        "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
         ]
-- 
cgit v1.2.3


From 0c62f8a820b7fdeacf5ad9f9e24b53043d372c97 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Sun, 5 Aug 2018 22:36:25 +0300
Subject: tc-testing: flush gact actions on test teardown

Test 6fb4 creates one mirred and one pipe action, but only flushes mirred
on teardown. Leaking pipe action causes failures in other tests.

Add additional teardown command to also flush gact actions.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
index 6e4edfae1799..db49fd0f8445 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/mirred.json
@@ -44,7 +44,8 @@
         "matchPattern": "action order [0-9]*: mirred \\(Egress Redirect to device lo\\).*index 2 ref",
         "matchCount": "1",
         "teardown": [
-            "$TC actions flush action mirred"
+            "$TC actions flush action mirred",
+            "$TC actions flush action gact"
         ]
     },
     {
-- 
cgit v1.2.3


From 757a9a39d483ae415a712388c33d4042a98b751f Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Sun, 5 Aug 2018 22:36:44 +0300
Subject: tc-testing: remove duplicate spaces in connmark match patterns

Match patterns for some connmark tests contain duplicate whitespace that is
not present in actual tc output. This causes tests to fail because they
can't match required action, even when it was successfully created.

Fixes: 1dad0f9ffff7 ("tc-testing: add connmark action tests")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/connmark.json      | 24 +++++++++++-----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
index 70952bd98ff9..13147a1f5731 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/connmark.json
@@ -17,7 +17,7 @@
         "cmdUnderTest": "$TC actions add action connmark",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 pipe",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pipe",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -41,7 +41,7 @@
         "cmdUnderTest": "$TC actions add action connmark pass index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 1",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 pass.*index 1 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pass.*index 1 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -65,7 +65,7 @@
         "cmdUnderTest": "$TC actions add action connmark drop index 100",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 100",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 drop.*index 100 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 drop.*index 100 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -89,7 +89,7 @@
         "cmdUnderTest": "$TC actions add action connmark pipe index 455",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 455",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 pipe.*index 455 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 pipe.*index 455 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -113,7 +113,7 @@
         "cmdUnderTest": "$TC actions add action connmark reclassify index 7",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 reclassify.*index 7 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 reclassify.*index 7 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -137,7 +137,7 @@
         "cmdUnderTest": "$TC actions add action connmark continue index 17",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 continue.*index 17 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 continue.*index 17 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -161,7 +161,7 @@
         "cmdUnderTest": "$TC actions add action connmark jump 10 index 17",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action connmark",
-        "matchPattern": "action order [0-9]+:  connmark zone 0 jump 10.*index 17 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 0 jump 10.*index 17 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -185,7 +185,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 100 pipe index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 1",
-        "matchPattern": "action order [0-9]+:  connmark zone 100 pipe.*index 1 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 100 pipe.*index 1 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -209,7 +209,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 65536 reclassify index 21",
         "expExitCode": "255",
         "verifyCmd": "$TC actions get action connmark index 1",
-        "matchPattern": "action order [0-9]+:  connmark zone 65536 reclassify.*index 21 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 65536 reclassify.*index 21 ref",
         "matchCount": "0",
         "teardown": [
             "$TC actions flush action connmark"
@@ -233,7 +233,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 655 unsupp_arg pass index 2",
         "expExitCode": "255",
         "verifyCmd": "$TC actions get action connmark index 2",
-        "matchPattern": "action order [0-9]+:  connmark zone 655 unsupp_arg pass.*index 2 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 655 unsupp_arg pass.*index 2 ref",
         "matchCount": "0",
         "teardown": [
             "$TC actions flush action connmark"
@@ -258,7 +258,7 @@
         "cmdUnderTest": "$TC actions replace action connmark zone 555 reclassify index 555",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 555",
-        "matchPattern": "action order [0-9]+:  connmark zone 555 reclassify.*index 555 ref",
+        "matchPattern": "action order [0-9]+: connmark zone 555 reclassify.*index 555 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
@@ -282,7 +282,7 @@
         "cmdUnderTest": "$TC actions add action connmark zone 555 pipe index 5 cookie aabbccddeeff112233445566778800a1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action connmark index 5",
-        "matchPattern": "action order [0-9]+:  connmark zone 555 pipe.*index 5 ref.*cookie aabbccddeeff112233445566778800a1",
+        "matchPattern": "action order [0-9]+: connmark zone 555 pipe.*index 5 ref.*cookie aabbccddeeff112233445566778800a1",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action connmark"
-- 
cgit v1.2.3


From 981467033a37d916649647fa3afe1fe99bba1817 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Sun, 5 Aug 2018 22:37:09 +0300
Subject: tc-testing: remove duplicate spaces in skbedit match patterns

Match patterns for some skbedit tests contain duplicate whitespace that is
not present in actual tc output. This causes tests to fail because they
can't match required action, even when it was successfully created.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../tc-testing/tc-tests/actions/skbedit.json       | 26 +++++++++++-----------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
index 37ecc2716fee..5aaf593b914a 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbedit.json
@@ -17,7 +17,7 @@
         "cmdUnderTest": "$TC actions add action skbedit mark 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit mark 1",
+        "matchPattern": "action order [0-9]*: skbedit  mark 1",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -65,7 +65,7 @@
         "cmdUnderTest": "$TC actions add action skbedit prio 99",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit priority :99",
+        "matchPattern": "action order [0-9]*: skbedit  priority :99",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -113,7 +113,7 @@
         "cmdUnderTest": "$TC actions add action skbedit queue_mapping 909",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 909",
+        "matchPattern": "action order [0-9]*: skbedit queue_mapping 909",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -161,7 +161,7 @@
         "cmdUnderTest": "$TC actions add action skbedit ptype host",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype host",
+        "matchPattern": "action order [0-9]*: skbedit  ptype host",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -185,7 +185,7 @@
         "cmdUnderTest": "$TC actions add action skbedit ptype otherhost",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit ptype otherhost",
+        "matchPattern": "action order [0-9]*: skbedit  ptype otherhost",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -233,7 +233,7 @@
         "cmdUnderTest": "$TC actions add action skbedit ptype host pipe index 11",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 11",
-        "matchPattern": "action order [0-9]*:  skbedit ptype host pipe.*index 11 ref",
+        "matchPattern": "action order [0-9]*: skbedit  ptype host pipe.*index 11 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -257,7 +257,7 @@
         "cmdUnderTest": "$TC actions add action skbedit mark 56789 reclassify index 90",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 90",
-        "matchPattern": "action order [0-9]*:  skbedit mark 56789 reclassify.*index 90 ref",
+        "matchPattern": "action order [0-9]*: skbedit  mark 56789 reclassify.*index 90 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -281,7 +281,7 @@
         "cmdUnderTest": "$TC actions add action skbedit queue_mapping 3 pass index 271",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 271",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 3 pass.*index 271 ref",
+        "matchPattern": "action order [0-9]*: skbedit queue_mapping 3 pass.*index 271 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -305,7 +305,7 @@
         "cmdUnderTest": "$TC actions add action skbedit queue_mapping 3 drop index 271",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 271",
-        "matchPattern": "action order [0-9]*:  skbedit queue_mapping 3 drop.*index 271 ref",
+        "matchPattern": "action order [0-9]*: skbedit queue_mapping 3 drop.*index 271 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -329,7 +329,7 @@
         "cmdUnderTest": "$TC actions add action skbedit priority 8 jump 9 index 2",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 2",
-        "matchPattern": "action order [0-9]*:  skbedit priority :8 jump 9.*index 2 ref",
+        "matchPattern": "action order [0-9]*: skbedit  priority :8 jump 9.*index 2 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -353,7 +353,7 @@
         "cmdUnderTest": "$TC actions add action skbedit priority 16 continue index 32",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 32",
-        "matchPattern": "action order [0-9]*:  skbedit priority :16 continue.*index 32 ref",
+        "matchPattern": "action order [0-9]*: skbedit  priority :16 continue.*index 32 ref",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -377,7 +377,7 @@
         "cmdUnderTest": "$TC actions add action skbedit priority 16 continue index 32 cookie deadbeef",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbedit index 32",
-        "matchPattern": "action order [0-9]*:  skbedit priority :16 continue.*index 32 ref.*cookie deadbeef",
+        "matchPattern": "action order [0-9]*: skbedit  priority :16 continue.*index 32 ref.*cookie deadbeef",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbedit"
@@ -405,7 +405,7 @@
         "cmdUnderTest": "$TC actions list action skbedit",
         "expExitCode": "0",
         "verifyCmd": "$TC actions list action skbedit",
-        "matchPattern": "action order [0-9]*:  skbedit",
+        "matchPattern": "action order [0-9]*: skbedit",
         "matchCount": "4",
         "teardown": [
             "$TC actions flush action skbedit"
-- 
cgit v1.2.3


From f10fe9d85dc0802b54519c917716e6f0092b4ce7 Mon Sep 17 00:00:00 2001
From: Matias Bjørling <mb@lightnvm.io>
Date: Sun, 5 Aug 2018 08:25:19 -0600
Subject: lightnvm: remove minor version check for 2.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A minor version number increase should not break backwards
compatibility.

Fixes: 3cb98f84d368b ("lightnvm: add minor version to generic geometry")
Reviewed-by: Javier González <javier@cnexlabs.com>
Signed-off-by: Matias Bjørling <mb@lightnvm.io>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/lightnvm.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
index 7e4cf4eb9d66..6fe5923c95d4 100644
--- a/drivers/nvme/host/lightnvm.c
+++ b/drivers/nvme/host/lightnvm.c
@@ -414,12 +414,6 @@ static int nvme_nvm_setup_20(struct nvme_nvm_id20 *id,
 	/* Set compacted version for upper layers */
 	geo->version = NVM_OCSSD_SPEC_20;
 
-	if (!(geo->major_ver_id == 2 && geo->minor_ver_id == 0)) {
-		pr_err("nvm: OCSSD version not supported (v%d.%d)\n",
-				geo->major_ver_id, geo->minor_ver_id);
-		return -EINVAL;
-	}
-
 	geo->num_ch = le16_to_cpu(id->num_grp);
 	geo->num_lun = le16_to_cpu(id->num_pu);
 	geo->all_luns = geo->num_ch * geo->num_lun;
-- 
cgit v1.2.3


From ac69c2f578bf51a3804c5e96467571ea5be0e882 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 15:11:03 -0500
Subject: ALSA: mixart: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/mixart/mixart.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/mixart/mixart.c b/sound/pci/mixart/mixart.c
index a74f1ad7e7b8..9cd297a42f24 100644
--- a/sound/pci/mixart/mixart.c
+++ b/sound/pci/mixart/mixart.c
@@ -182,6 +182,7 @@ static int mixart_set_clock(struct mixart_mgr *mgr,
 	case PIPE_RUNNING:
 		if(rate != 0)
 			break;
+		/* fall through */
 	default:
 		if(rate == 0)
 			return 0; /* nothing to do */
-- 
cgit v1.2.3


From 9d5a289a86a15a1a4248022f9338517f7e62832b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 15:12:09 -0500
Subject: ALSA: emu10k1: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I replaced the code comment with
a proper "fall through" annotation, which is what GCC is expecting
to find.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/emu10k1/emupcm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/emu10k1/emupcm.c b/sound/pci/emu10k1/emupcm.c
index 26f6eda3e766..9f2b6097f486 100644
--- a/sound/pci/emu10k1/emupcm.c
+++ b/sound/pci/emu10k1/emupcm.c
@@ -778,7 +778,7 @@ static int snd_emu10k1_playback_trigger(struct snd_pcm_substream *substream,
 	case SNDRV_PCM_TRIGGER_START:
 		snd_emu10k1_playback_invalidate_cache(emu, 1, epcm->extra);	/* do we need this? */
 		snd_emu10k1_playback_invalidate_cache(emu, 0, epcm->voices[0]);
-		/* follow thru */
+		/* fall through */
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
 		if (cmd == SNDRV_PCM_TRIGGER_PAUSE_RELEASE)
@@ -928,7 +928,7 @@ static int snd_emu10k1_efx_playback_trigger(struct snd_pcm_substream *substream,
 		}
 		snd_emu10k1_playback_invalidate_cache(emu, 1, epcm->extra);
 
-		/* follow thru */
+		/* fall through */
 	case SNDRV_PCM_TRIGGER_PAUSE_RELEASE:
 	case SNDRV_PCM_TRIGGER_RESUME:
 		snd_emu10k1_playback_prepare_voice(emu, epcm->extra, 1, 1, NULL);
-- 
cgit v1.2.3


From ef0075280cfe09ef076ce1b85f0a2294c5ed86f3 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 15:13:26 -0500
Subject: ALSA: echoaudio: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 115156 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/echoaudio/echoaudio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/echoaudio/echoaudio.c b/sound/pci/echoaudio/echoaudio.c
index 358ef7dcf410..907cf1a46712 100644
--- a/sound/pci/echoaudio/echoaudio.c
+++ b/sound/pci/echoaudio/echoaudio.c
@@ -713,6 +713,7 @@ static int pcm_prepare(struct snd_pcm_substream *substream)
 		break;
 	case SNDRV_PCM_FORMAT_S32_BE:
 		format.data_are_bigendian = 1;
+		/* fall through */
 	case SNDRV_PCM_FORMAT_S32_LE:
 		format.bits_per_sample = 32;
 		break;
@@ -764,6 +765,7 @@ static int pcm_trigger(struct snd_pcm_substream *substream, int cmd)
 					pipe->last_counter = 0;
 					pipe->position = 0;
 					*pipe->dma_counter = 0;
+					/* fall through */
 				case PIPE_STATE_PAUSED:
 					pipe->state = PIPE_STATE_STARTED;
 					break;
-- 
cgit v1.2.3


From 627661ced8246c8e833f3bc3817070e934cd79ba Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Mon, 6 Aug 2018 16:14:06 +0900
Subject: ALSA: dice: fix wrong copy to rx parameters for Alesis iO26

A commit 28b208f600a3 ('ALSA: dice: add parameters of stream formats for
models produced by Alesis') adds wrong copy to rx parameters instead of
tx parameters for Alesis iO26.

This commit fixes the bug for v4.18-rc8.

Fixes: 28b208f600a3 ('ALSA: dice: add parameters of stream formats for models produced by Alesis')
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Cc: <stable@vger.kernel.org> # v4.18
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/firewire/dice/dice-alesis.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/firewire/dice/dice-alesis.c b/sound/firewire/dice/dice-alesis.c
index b2efb1c71a98..218292bdace6 100644
--- a/sound/firewire/dice/dice-alesis.c
+++ b/sound/firewire/dice/dice-alesis.c
@@ -37,7 +37,7 @@ int snd_dice_detect_alesis_formats(struct snd_dice *dice)
 				MAX_STREAMS * SND_DICE_RATE_MODE_COUNT *
 				sizeof(unsigned int));
 	} else {
-		memcpy(dice->rx_pcm_chs, alesis_io26_tx_pcm_chs,
+		memcpy(dice->tx_pcm_chs, alesis_io26_tx_pcm_chs,
 				MAX_STREAMS * SND_DICE_RATE_MODE_COUNT *
 				sizeof(unsigned int));
 	}
-- 
cgit v1.2.3


From b047c62e24418b9f62b721be017ec5c0364166a5 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma@canonical.com>
Date: Tue, 31 Jul 2018 18:52:39 +0800
Subject: ACPI / EC: Use ec_no_wakeup on ThinkPad X1 Yoga 3rd

Like on X1C6, on X1Y3 EC interrupts constantly wake up system from
s2idle, the power consumption is extremely high.
So make ec_no_wakeup be true as default to keep system in s2idle mode
and reduce power consumption.

Power button works when ec_no_wakeup=true.

Signed-off-by: Aaron Ma <aaron.ma@canonical.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/ec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 917f77f4cb55..6291d5c77267 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2045,6 +2045,13 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"),
 		},
 	},
+	{
+		.ident = "ThinkPad X1 Yoga 3rd",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Yoga 3rd"),
+		},
+	},
 	{ },
 };
 
-- 
cgit v1.2.3


From a8db74564b0c634667e1722264bde303d296f566 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Wed, 18 Jul 2018 17:42:04 +0200
Subject: irqchip/gic-v3-its: Make its_lock a raw_spin_lock_t

The its_lock lock is held while a new device is added to the list and
during setup while the CPU is booted. Even on -RT the CPU-bootup is
performed with disabled interrupts.

Make its_lock a raw_spin_lock_t.

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>
---
 drivers/irqchip/irq-gic-v3-its.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index f56c84977241..316a57530f6d 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -162,7 +162,7 @@ static struct {
 } vpe_proxy;
 
 static LIST_HEAD(its_nodes);
-static DEFINE_SPINLOCK(its_lock);
+static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
 static struct irq_domain *its_parent;
 
@@ -2063,12 +2063,12 @@ static void its_cpu_init_collections(void)
 {
 	struct its_node *its;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 
 	list_for_each_entry(its, &its_nodes, entry)
 		its_cpu_init_collection(its);
 
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct its_device *its_find_device(struct its_node *its, u32 dev_id)
@@ -3139,7 +3139,7 @@ static int its_save_disable(void)
 	struct its_node *its;
 	int err = 0;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 
@@ -3171,7 +3171,7 @@ err:
 			writel_relaxed(its->ctlr_save, base + GITS_CTLR);
 		}
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return err;
 }
@@ -3181,7 +3181,7 @@ static void its_restore_enable(void)
 	struct its_node *its;
 	int ret;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_for_each_entry(its, &its_nodes, entry) {
 		void __iomem *base;
 		int i;
@@ -3233,7 +3233,7 @@ static void its_restore_enable(void)
 		    GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER)))
 			its_cpu_init_collection(its);
 	}
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 }
 
 static struct syscore_ops its_syscore_ops = {
@@ -3467,9 +3467,9 @@ static int __init its_probe_one(struct resource *res,
 	if (err)
 		goto out_free_tables;
 
-	spin_lock(&its_lock);
+	raw_spin_lock(&its_lock);
 	list_add(&its->entry, &its_nodes);
-	spin_unlock(&its_lock);
+	raw_spin_unlock(&its_lock);
 
 	return 0;
 
-- 
cgit v1.2.3


From d3264f752a1aedac98aa90e50853df149d1346f2 Mon Sep 17 00:00:00 2001
From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date: Wed, 1 Aug 2018 17:26:06 -0700
Subject: cpufreq: intel_pstate: Ignore turbo active ratio in HWP

When HWP is active turbo active ratio is not used, so we should allow
policy max frequency above turbo activation ratio to be set. When HWP is
not active, then any policy max frequency above turbo activation ratio
can result upto max one-core turbo frequency.

This fix helps better thermal control in turbo region when other methods
like "Running Average Power Limit" is not available to use.

Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/cpufreq/intel_pstate.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 7bfb98380db9..b6a1aadaff9f 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -2008,7 +2008,8 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 static void intel_pstate_adjust_policy_max(struct cpufreq_policy *policy,
 					 struct cpudata *cpu)
 {
-	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
+	if (!hwp_active &&
+	    cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate &&
 	    policy->max < policy->cpuinfo.max_freq &&
 	    policy->max > cpu->pstate.max_freq) {
 		pr_debug("policy->max > max non turbo frequency\n");
-- 
cgit v1.2.3


From 7dda712818373d4d8ecc5dca2293664fcd3b0158 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Jul 2018 12:25:50 +0200
Subject: timerfd: add support for keyed wakeups

This prepares timerfd for use with aio poll.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Avi Kivity <avi@scylladb.com>
---
 fs/timerfd.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/timerfd.c b/fs/timerfd.c
index cdad49da3ff7..f6c54fd56645 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -66,7 +66,7 @@ static void timerfd_triggered(struct timerfd_ctx *ctx)
 	spin_lock_irqsave(&ctx->wqh.lock, flags);
 	ctx->expired = 1;
 	ctx->ticks++;
-	wake_up_locked(&ctx->wqh);
+	wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 	spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 }
 
@@ -107,7 +107,7 @@ void timerfd_clock_was_set(void)
 		if (ctx->moffs != moffs) {
 			ctx->moffs = KTIME_MAX;
 			ctx->ticks++;
-			wake_up_locked(&ctx->wqh);
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 		}
 		spin_unlock_irqrestore(&ctx->wqh.lock, flags);
 	}
@@ -345,7 +345,7 @@ static long timerfd_ioctl(struct file *file, unsigned int cmd, unsigned long arg
 		spin_lock_irq(&ctx->wqh.lock);
 		if (!timerfd_canceled(ctx)) {
 			ctx->ticks = ticks;
-			wake_up_locked(&ctx->wqh);
+			wake_up_locked_poll(&ctx->wqh, EPOLLIN);
 		} else
 			ret = -ECANCELED;
 		spin_unlock_irq(&ctx->wqh.lock);
-- 
cgit v1.2.3


From 9018ccc453af063d16b3b6b5dfa2ad0635390371 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 24 Jul 2018 11:36:37 +0200
Subject: aio: add a iocb refcount

This is needed to prevent races caused by the way the ->poll API works.
To avoid introducing overhead for other users of the iocbs we initialize
it to zero and only do refcount operations if it is non-zero in the
completion path.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Avi Kivity <avi@scylladb.com>
---
 fs/aio.c | 17 +++++++++++++----
 1 file changed, 13 insertions(+), 4 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 27454594e37a..fe2018ada32c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -18,6 +18,7 @@
 #include <linux/export.h>
 #include <linux/syscalls.h>
 #include <linux/backing-dev.h>
+#include <linux/refcount.h>
 #include <linux/uio.h>
 
 #include <linux/sched/signal.h>
@@ -178,6 +179,7 @@ struct aio_kiocb {
 
 	struct list_head	ki_list;	/* the aio core uses this
 						 * for cancellation */
+	refcount_t		ki_refcnt;
 
 	/*
 	 * If the aio_resfd field of the userspace iocb is not zero,
@@ -1015,6 +1017,7 @@ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx)
 
 	percpu_ref_get(&ctx->reqs);
 	INIT_LIST_HEAD(&req->ki_list);
+	refcount_set(&req->ki_refcnt, 0);
 	req->ki_ctx = ctx;
 	return req;
 out_put:
@@ -1049,6 +1052,15 @@ out:
 	return ret;
 }
 
+static inline void iocb_put(struct aio_kiocb *iocb)
+{
+	if (refcount_read(&iocb->ki_refcnt) == 0 ||
+	    refcount_dec_and_test(&iocb->ki_refcnt)) {
+		percpu_ref_put(&iocb->ki_ctx->reqs);
+		kmem_cache_free(kiocb_cachep, iocb);
+	}
+}
+
 /* aio_complete
  *	Called when the io request on the given iocb is complete.
  */
@@ -1118,8 +1130,6 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 		eventfd_ctx_put(iocb->ki_eventfd);
 	}
 
-	kmem_cache_free(kiocb_cachep, iocb);
-
 	/*
 	 * We have to order our ring_info tail store above and test
 	 * of the wait list below outside the wait lock.  This is
@@ -1130,8 +1140,7 @@ static void aio_complete(struct aio_kiocb *iocb, long res, long res2)
 
 	if (waitqueue_active(&ctx->wait))
 		wake_up(&ctx->wait);
-
-	percpu_ref_put(&ctx->reqs);
+	iocb_put(iocb);
 }
 
 /* aio_read_events_ring
-- 
cgit v1.2.3


From bfe4037e722ec672c9dafd5730d9132afeeb76e9 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Jul 2018 09:08:20 +0200
Subject: aio: implement IOCB_CMD_POLL

Simple one-shot poll through the io_submit() interface.  To poll for
a file descriptor the application should submit an iocb of type
IOCB_CMD_POLL.  It will poll the fd for the events specified in the
the first 32 bits of the aio_buf field of the iocb.

Unlike poll or epoll without EPOLLONESHOT this interface always works
in one shot mode, that is once the iocb is completed, it will have to be
resubmitted.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Avi Kivity <avi@scylladb.com>
---
 fs/aio.c                     | 178 +++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/aio_abi.h |   6 +-
 2 files changed, 180 insertions(+), 4 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index fe2018ada32c..2fd19521d8a8 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -5,6 +5,7 @@
  *	Implements an efficient asynchronous io interface.
  *
  *	Copyright 2000, 2001, 2002 Red Hat, Inc.  All Rights Reserved.
+ *	Copyright 2018 Christoph Hellwig.
  *
  *	See ../COPYING for licensing terms.
  */
@@ -165,10 +166,21 @@ struct fsync_iocb {
 	bool			datasync;
 };
 
+struct poll_iocb {
+	struct file		*file;
+	struct wait_queue_head	*head;
+	__poll_t		events;
+	bool			woken;
+	bool			cancelled;
+	struct wait_queue_entry	wait;
+	struct work_struct	work;
+};
+
 struct aio_kiocb {
 	union {
 		struct kiocb		rw;
 		struct fsync_iocb	fsync;
+		struct poll_iocb	poll;
 	};
 
 	struct kioctx		*ki_ctx;
@@ -1601,6 +1613,169 @@ static int aio_fsync(struct fsync_iocb *req, struct iocb *iocb, bool datasync)
 	return 0;
 }
 
+static inline void aio_poll_complete(struct aio_kiocb *iocb, __poll_t mask)
+{
+	struct file *file = iocb->poll.file;
+
+	aio_complete(iocb, mangle_poll(mask), 0);
+	fput(file);
+}
+
+static void aio_poll_complete_work(struct work_struct *work)
+{
+	struct poll_iocb *req = container_of(work, struct poll_iocb, work);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
+	struct poll_table_struct pt = { ._key = req->events };
+	struct kioctx *ctx = iocb->ki_ctx;
+	__poll_t mask = 0;
+
+	if (!READ_ONCE(req->cancelled))
+		mask = vfs_poll(req->file, &pt) & req->events;
+
+	/*
+	 * Note that ->ki_cancel callers also delete iocb from active_reqs after
+	 * calling ->ki_cancel.  We need the ctx_lock roundtrip here to
+	 * synchronize with them.  In the cancellation case the list_del_init
+	 * itself is not actually needed, but harmless so we keep it in to
+	 * avoid further branches in the fast path.
+	 */
+	spin_lock_irq(&ctx->ctx_lock);
+	if (!mask && !READ_ONCE(req->cancelled)) {
+		add_wait_queue(req->head, &req->wait);
+		spin_unlock_irq(&ctx->ctx_lock);
+		return;
+	}
+	list_del_init(&iocb->ki_list);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+	aio_poll_complete(iocb, mask);
+}
+
+/* assumes we are called with irqs disabled */
+static int aio_poll_cancel(struct kiocb *iocb)
+{
+	struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw);
+	struct poll_iocb *req = &aiocb->poll;
+
+	spin_lock(&req->head->lock);
+	WRITE_ONCE(req->cancelled, true);
+	if (!list_empty(&req->wait.entry)) {
+		list_del_init(&req->wait.entry);
+		schedule_work(&aiocb->poll.work);
+	}
+	spin_unlock(&req->head->lock);
+
+	return 0;
+}
+
+static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
+		void *key)
+{
+	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+	__poll_t mask = key_to_poll(key);
+
+	req->woken = true;
+
+	/* for instances that support it check for an event match first: */
+	if (mask && !(mask & req->events))
+		return 0;
+
+	list_del_init(&req->wait.entry);
+	schedule_work(&req->work);
+	return 1;
+}
+
+struct aio_poll_table {
+	struct poll_table_struct	pt;
+	struct aio_kiocb		*iocb;
+	int				error;
+};
+
+static void
+aio_poll_queue_proc(struct file *file, struct wait_queue_head *head,
+		struct poll_table_struct *p)
+{
+	struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt);
+
+	/* multiple wait queues per file are not supported */
+	if (unlikely(pt->iocb->poll.head)) {
+		pt->error = -EINVAL;
+		return;
+	}
+
+	pt->error = 0;
+	pt->iocb->poll.head = head;
+	add_wait_queue(head, &pt->iocb->poll.wait);
+}
+
+static ssize_t aio_poll(struct aio_kiocb *aiocb, struct iocb *iocb)
+{
+	struct kioctx *ctx = aiocb->ki_ctx;
+	struct poll_iocb *req = &aiocb->poll;
+	struct aio_poll_table apt;
+	__poll_t mask;
+
+	/* reject any unknown events outside the normal event mask. */
+	if ((u16)iocb->aio_buf != iocb->aio_buf)
+		return -EINVAL;
+	/* reject fields that are not defined for poll */
+	if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)
+		return -EINVAL;
+
+	INIT_WORK(&req->work, aio_poll_complete_work);
+	req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP;
+	req->file = fget(iocb->aio_fildes);
+	if (unlikely(!req->file))
+		return -EBADF;
+
+	apt.pt._qproc = aio_poll_queue_proc;
+	apt.pt._key = req->events;
+	apt.iocb = aiocb;
+	apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */
+
+	/* initialized the list so that we can do list_empty checks */
+	INIT_LIST_HEAD(&req->wait.entry);
+	init_waitqueue_func_entry(&req->wait, aio_poll_wake);
+
+	/* one for removal from waitqueue, one for this function */
+	refcount_set(&aiocb->ki_refcnt, 2);
+
+	mask = vfs_poll(req->file, &apt.pt) & req->events;
+	if (unlikely(!req->head)) {
+		/* we did not manage to set up a waitqueue, done */
+		goto out;
+	}
+
+	spin_lock_irq(&ctx->ctx_lock);
+	spin_lock(&req->head->lock);
+	if (req->woken) {
+		/* wake_up context handles the rest */
+		mask = 0;
+		apt.error = 0;
+	} else if (mask || apt.error) {
+		/* if we get an error or a mask we are done */
+		WARN_ON_ONCE(list_empty(&req->wait.entry));
+		list_del_init(&req->wait.entry);
+	} else {
+		/* actually waiting for an event */
+		list_add_tail(&aiocb->ki_list, &ctx->active_reqs);
+		aiocb->ki_cancel = aio_poll_cancel;
+	}
+	spin_unlock(&req->head->lock);
+	spin_unlock_irq(&ctx->ctx_lock);
+
+out:
+	if (unlikely(apt.error)) {
+		fput(req->file);
+		return apt.error;
+	}
+
+	if (mask)
+		aio_poll_complete(aiocb, mask);
+	iocb_put(aiocb);
+	return 0;
+}
+
 static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 			 bool compat)
 {
@@ -1674,6 +1849,9 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	case IOCB_CMD_FDSYNC:
 		ret = aio_fsync(&req->fsync, &iocb, true);
 		break;
+	case IOCB_CMD_POLL:
+		ret = aio_poll(req, &iocb);
+		break;
 	default:
 		pr_debug("invalid aio operation %d\n", iocb.aio_lio_opcode);
 		ret = -EINVAL;
diff --git a/include/uapi/linux/aio_abi.h b/include/uapi/linux/aio_abi.h
index d4593a6062ef..ce43d340f010 100644
--- a/include/uapi/linux/aio_abi.h
+++ b/include/uapi/linux/aio_abi.h
@@ -38,10 +38,8 @@ enum {
 	IOCB_CMD_PWRITE = 1,
 	IOCB_CMD_FSYNC = 2,
 	IOCB_CMD_FDSYNC = 3,
-	/* These two are experimental.
-	 * IOCB_CMD_PREADX = 4,
-	 * IOCB_CMD_POLL = 5,
-	 */
+	/* 4 was the experimental IOCB_CMD_PREADX */
+	IOCB_CMD_POLL = 5,
 	IOCB_CMD_NOOP = 6,
 	IOCB_CMD_PREADV = 7,
 	IOCB_CMD_PWRITEV = 8,
-- 
cgit v1.2.3


From e8693bcfa0b4a56268946f0756153d942cb66cf7 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 16 Jul 2018 12:25:17 +0200
Subject: aio: allow direct aio poll comletions for keyed wakeups

If we get a keyed wakeup for a aio poll waitqueue and wake can acquire the
ctx_lock without spinning we can just complete the iocb straight from the
wakeup callback to avoid a context switch.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Tested-by: Avi Kivity <avi@scylladb.com>
---
 fs/aio.c | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/fs/aio.c b/fs/aio.c
index 2fd19521d8a8..29f2b5b57d32 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1672,13 +1672,26 @@ static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync,
 		void *key)
 {
 	struct poll_iocb *req = container_of(wait, struct poll_iocb, wait);
+	struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll);
 	__poll_t mask = key_to_poll(key);
 
 	req->woken = true;
 
 	/* for instances that support it check for an event match first: */
-	if (mask && !(mask & req->events))
-		return 0;
+	if (mask) {
+		if (!(mask & req->events))
+			return 0;
+
+		/* try to complete the iocb inline if we can: */
+		if (spin_trylock(&iocb->ki_ctx->ctx_lock)) {
+			list_del(&iocb->ki_list);
+			spin_unlock(&iocb->ki_ctx->ctx_lock);
+
+			list_del_init(&req->wait.entry);
+			aio_poll_complete(iocb, mask);
+			return 1;
+		}
+	}
 
 	list_del_init(&req->wait.entry);
 	schedule_work(&req->work);
-- 
cgit v1.2.3


From 82837ad5bda79cd13d64b9abad92e7872a06bc65 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 21:12:00 -0500
Subject: PM / hibernate: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

This addresses Coverity-ID: 114713 ("Missing break in switch").

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/power/hibernate.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 9c85c7822383..38f3f96b4b12 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -638,6 +638,7 @@ static void power_down(void)
 		break;
 	case HIBERNATION_PLATFORM:
 		hibernation_platform_enter();
+		/* Fall through */
 	case HIBERNATION_SHUTDOWN:
 		if (pm_power_off)
 			kernel_power_off();
-- 
cgit v1.2.3


From ac74f87c789af40936a80131c4759f3e72579c3a Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Sat, 14 Jul 2018 12:52:10 -0400
Subject: net: 6lowpan: fix reserved space for single frames

This patch fixes patch add handling to take care tail and headroom for
single 6lowpan frames. We need to be sure we have a skb with the right
head and tailroom for single frames. This patch do it by using
skb_copy_expand() if head and tailroom is not enough allocated by upper
layer.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=195059
Reported-by: David Palma <david.palma@ntnu.no>
Reported-by: Rabi Narayan Sahoo <rabinarayans0828@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/6lowpan/tx.c | 21 ++++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/net/ieee802154/6lowpan/tx.c b/net/ieee802154/6lowpan/tx.c
index e6ff5128e61a..ca53efa17be1 100644
--- a/net/ieee802154/6lowpan/tx.c
+++ b/net/ieee802154/6lowpan/tx.c
@@ -265,9 +265,24 @@ netdev_tx_t lowpan_xmit(struct sk_buff *skb, struct net_device *ldev)
 	/* We must take a copy of the skb before we modify/replace the ipv6
 	 * header as the header could be used elsewhere
 	 */
-	skb = skb_unshare(skb, GFP_ATOMIC);
-	if (!skb)
-		return NET_XMIT_DROP;
+	if (unlikely(skb_headroom(skb) < ldev->needed_headroom ||
+		     skb_tailroom(skb) < ldev->needed_tailroom)) {
+		struct sk_buff *nskb;
+
+		nskb = skb_copy_expand(skb, ldev->needed_headroom,
+				       ldev->needed_tailroom, GFP_ATOMIC);
+		if (likely(nskb)) {
+			consume_skb(skb);
+			skb = nskb;
+		} else {
+			kfree_skb(skb);
+			return NET_XMIT_DROP;
+		}
+	} else {
+		skb = skb_unshare(skb, GFP_ATOMIC);
+		if (!skb)
+			return NET_XMIT_DROP;
+	}
 
 	ret = lowpan_header(skb, ldev, &dgram_size, &dgram_offset);
 	if (ret < 0) {
-- 
cgit v1.2.3


From f9c52831133050c6b82aa8b6831c92da2bbf2a0b Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Mon, 2 Jul 2018 16:32:03 -0400
Subject: net: mac802154: tx: expand tailroom if necessary

This patch is necessary if case of AF_PACKET or other socket interface
which I am aware of it and didn't allocated the necessary room.

Reported-by: David Palma <david.palma@ntnu.no>
Reported-by: Rabi Narayan Sahoo <rabinarayans0828@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/mac802154/tx.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/net/mac802154/tx.c b/net/mac802154/tx.c
index 7e253455f9dd..bcd1a5e6ebf4 100644
--- a/net/mac802154/tx.c
+++ b/net/mac802154/tx.c
@@ -63,8 +63,21 @@ ieee802154_tx(struct ieee802154_local *local, struct sk_buff *skb)
 	int ret;
 
 	if (!(local->hw.flags & IEEE802154_HW_TX_OMIT_CKSUM)) {
-		u16 crc = crc_ccitt(0, skb->data, skb->len);
+		struct sk_buff *nskb;
+		u16 crc;
+
+		if (unlikely(skb_tailroom(skb) < IEEE802154_FCS_LEN)) {
+			nskb = skb_copy_expand(skb, 0, IEEE802154_FCS_LEN,
+					       GFP_ATOMIC);
+			if (likely(nskb)) {
+				consume_skb(skb);
+				skb = nskb;
+			} else {
+				goto err_tx;
+			}
+		}
 
+		crc = crc_ccitt(0, skb->data, skb->len);
 		put_unaligned_le16(crc, skb_put(skb, 2));
 	}
 
-- 
cgit v1.2.3


From 4e54acb2022099e41231271b5a8ec58ca8ac2d86 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 31 Jul 2018 16:45:07 +0100
Subject: net: ieee802154: 6lowpan: remove redundant pointers 'fq' and 'net'

Pointers fq and net are being assigned but are never used hence they
are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'fq' set but not used [-Wunused-but-set-variable]
warning: variable 'net' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 net/ieee802154/6lowpan/reassembly.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index ec7a5da56129..e7857a8ac86d 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -40,9 +40,6 @@ static int lowpan_frag_reasm(struct lowpan_frag_queue *fq,
 static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
 {
 	const struct frag_lowpan_compare_key *key = a;
-	struct lowpan_frag_queue *fq;
-
-	fq = container_of(q, struct lowpan_frag_queue, q);
 
 	BUILD_BUG_ON(sizeof(*key) > sizeof(q->key));
 	memcpy(&q->key, key, sizeof(*key));
@@ -52,10 +49,8 @@ static void lowpan_frag_expire(struct timer_list *t)
 {
 	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	struct frag_queue *fq;
-	struct net *net;
 
 	fq = container_of(frag, struct frag_queue, q);
-	net = container_of(fq->q.net, struct net, ieee802154_lowpan.frags);
 
 	spin_lock(&fq->q.lock);
 
-- 
cgit v1.2.3


From f25da51fdc381ca2863248c7060b3662632f0872 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Sat, 14 Jul 2018 12:33:05 -0400
Subject: ieee802154: hwsim: add replacement for fakelb

This patch adds a new virtual driver mac802154_hwsim which is based on
the fakelb driver.
The fakelb driver will get deprecated and hopefully removed someday.
The main reason for doing this step is to rename the driver to
mac802154_hwsim to have a similar naming scheme as mac80211_hwsim,
which is more popular in the 802.11 wireless word and the idea is the
same behind this driver.

The new features of this driver are to have knowledge about connected
edges, which can be changed during runtime. This offers a testing
environment for routing protocols e.g. RPL.
The default behaviour is still as fakelb: two radios connected to each
other. New added radios during runtime will not be connected to other
wpan_hwsim instances.

The netlink api is not namespace aware on purpose, only the registered
wpan_phy's can be moved to namespaces. The physical layer according to
wiresless "air" communication can be handled across namespaces.

Furthermore the edges can be weighted with the LQI value according IEEE
802.15.4 which offers additional handling to mark bad or good connection
indicators to other connected virtual phys.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/net/ieee802154/Kconfig           |  11 +
 drivers/net/ieee802154/Makefile          |   1 +
 drivers/net/ieee802154/mac802154_hwsim.c | 919 +++++++++++++++++++++++++++++++
 drivers/net/ieee802154/mac802154_hwsim.h |  73 +++
 4 files changed, 1004 insertions(+)
 create mode 100644 drivers/net/ieee802154/mac802154_hwsim.c
 create mode 100644 drivers/net/ieee802154/mac802154_hwsim.h

diff --git a/drivers/net/ieee802154/Kconfig b/drivers/net/ieee802154/Kconfig
index 8782f5655e3f..0e372f392cb1 100644
--- a/drivers/net/ieee802154/Kconfig
+++ b/drivers/net/ieee802154/Kconfig
@@ -115,3 +115,14 @@ config IEEE802154_MCR20A
 
 	  This driver can also be built as a module. To do so, say M here.
 	  the module will be called 'mcr20a'.
+
+config IEEE802154_HWSIM
+	depends on IEEE802154_DRIVERS && MAC802154
+	tristate "Simulated radio testing tool for mac802154"
+	---help---
+	  This driver is a developer testing tool that can be used to test
+	  IEEE 802.15.4 networking stack (mac802154) functionality. This is not
+	  needed for normal wpan usage and is only for testing.
+
+	  This driver can also be built as a module. To do so say M here.
+	  The module will be called 'mac802154_hwsim'.
diff --git a/drivers/net/ieee802154/Makefile b/drivers/net/ieee802154/Makefile
index 104744d5a668..0c78b6298060 100644
--- a/drivers/net/ieee802154/Makefile
+++ b/drivers/net/ieee802154/Makefile
@@ -7,3 +7,4 @@ obj-$(CONFIG_IEEE802154_ATUSB) += atusb.o
 obj-$(CONFIG_IEEE802154_ADF7242) += adf7242.o
 obj-$(CONFIG_IEEE802154_CA8210) += ca8210.o
 obj-$(CONFIG_IEEE802154_MCR20A) += mcr20a.o
+obj-$(CONFIG_IEEE802154_HWSIM) += mac802154_hwsim.o
diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
new file mode 100644
index 000000000000..1982308b9b1c
--- /dev/null
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -0,0 +1,919 @@
+/*
+ * HWSIM IEEE 802.15.4 interface
+ *
+ * (C) 2018 Mojatau, Alexander Aring <aring@mojatau.com>
+ * Copyright 2007-2012 Siemens AG
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * Based on fakelb, original Written by:
+ * Sergey Lapin <slapin@ossfans.org>
+ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Alexander Smirnov <alex.bluesman.smirnov@gmail.com>
+ */
+
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/platform_device.h>
+#include <linux/netdevice.h>
+#include <linux/device.h>
+#include <linux/spinlock.h>
+#include <net/mac802154.h>
+#include <net/cfg802154.h>
+#include <net/genetlink.h>
+#include "mac802154_hwsim.h"
+
+MODULE_DESCRIPTION("Software simulator of IEEE 802.15.4 radio(s) for mac802154");
+MODULE_LICENSE("GPL");
+
+static LIST_HEAD(hwsim_phys);
+static DEFINE_MUTEX(hwsim_phys_lock);
+
+static __rcu LIST_HEAD(hwsim_ifup_phys);
+
+static struct platform_device *mac802154hwsim_dev;
+
+/* MAC802154_HWSIM netlink family */
+static struct genl_family hwsim_genl_family;
+
+static int hwsim_radio_idx;
+
+enum hwsim_multicast_groups {
+	HWSIM_MCGRP_CONFIG,
+};
+
+static const struct genl_multicast_group hwsim_mcgrps[] = {
+	[HWSIM_MCGRP_CONFIG] = { .name = "config", },
+};
+
+struct hwsim_pib {
+	u8 page;
+	u8 channel;
+
+	struct rcu_head rcu;
+};
+
+struct hwsim_edge_info {
+	u8 lqi;
+
+	struct rcu_head rcu;
+};
+
+struct hwsim_edge {
+	struct hwsim_phy *endpoint;
+	struct hwsim_edge_info *info;
+
+	struct list_head list;
+	struct rcu_head rcu;
+};
+
+struct hwsim_phy {
+	struct ieee802154_hw *hw;
+	u32 idx;
+
+	struct hwsim_pib __rcu *pib;
+
+	bool suspended;
+	struct list_head __rcu edges;
+
+	struct list_head list;
+	struct list_head list_ifup;
+};
+
+static int hwsim_add_one(struct genl_info *info, struct device *dev,
+			 bool init);
+static void hwsim_del(struct hwsim_phy *phy);
+
+static int hwsim_hw_ed(struct ieee802154_hw *hw, u8 *level)
+{
+	*level = 0xbe;
+
+	return 0;
+}
+
+static int hwsim_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
+{
+	struct hwsim_phy *phy = hw->priv;
+	struct hwsim_pib *pib, *pib_old;
+
+	pib = kzalloc(sizeof(*pib), GFP_KERNEL);
+	if (!pib)
+		return -ENOMEM;
+
+	pib->page = page;
+	pib->channel = channel;
+
+	pib_old = phy->pib;
+	rcu_assign_pointer(phy->pib, pib);
+	kfree_rcu(pib_old, rcu);
+	return 0;
+}
+
+static int hwsim_hw_xmit(struct ieee802154_hw *hw, struct sk_buff *skb)
+{
+	struct hwsim_phy *current_phy = hw->priv;
+	struct hwsim_pib *current_pib, *endpoint_pib;
+	struct hwsim_edge_info *einfo;
+	struct hwsim_edge *e;
+
+	WARN_ON(current_phy->suspended);
+
+	rcu_read_lock();
+	current_pib = rcu_dereference(current_phy->pib);
+	list_for_each_entry_rcu(e, &current_phy->edges, list) {
+		/* Can be changed later in rx_irqsafe, but this is only a
+		 * performance tweak. Received radio should drop the frame
+		 * in mac802154 stack anyway... so we don't need to be
+		 * 100% of locking here to check on suspended
+		 */
+		if (e->endpoint->suspended)
+			continue;
+
+		endpoint_pib = rcu_dereference(e->endpoint->pib);
+		if (current_pib->page == endpoint_pib->page &&
+		    current_pib->channel == endpoint_pib->channel) {
+			struct sk_buff *newskb = pskb_copy(skb, GFP_ATOMIC);
+
+			einfo = rcu_dereference(e->info);
+			if (newskb)
+				ieee802154_rx_irqsafe(e->endpoint->hw, newskb,
+						      einfo->lqi);
+		}
+	}
+	rcu_read_unlock();
+
+	ieee802154_xmit_complete(hw, skb, false);
+	return 0;
+}
+
+static int hwsim_hw_start(struct ieee802154_hw *hw)
+{
+	struct hwsim_phy *phy = hw->priv;
+
+	phy->suspended = false;
+	list_add_rcu(&phy->list_ifup, &hwsim_ifup_phys);
+	synchronize_rcu();
+
+	return 0;
+}
+
+static void hwsim_hw_stop(struct ieee802154_hw *hw)
+{
+	struct hwsim_phy *phy = hw->priv;
+
+	phy->suspended = true;
+	list_del_rcu(&phy->list_ifup);
+	synchronize_rcu();
+}
+
+static int
+hwsim_set_promiscuous_mode(struct ieee802154_hw *hw, const bool on)
+{
+	return 0;
+}
+
+static const struct ieee802154_ops hwsim_ops = {
+	.owner = THIS_MODULE,
+	.xmit_async = hwsim_hw_xmit,
+	.ed = hwsim_hw_ed,
+	.set_channel = hwsim_hw_channel,
+	.start = hwsim_hw_start,
+	.stop = hwsim_hw_stop,
+	.set_promiscuous_mode = hwsim_set_promiscuous_mode,
+};
+
+static int hwsim_new_radio_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	return hwsim_add_one(info, &mac802154hwsim_dev->dev, false);
+}
+
+static int hwsim_del_radio_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct hwsim_phy *phy, *tmp;
+	s64 idx = -1;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID])
+		return -EINVAL;
+
+	idx = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &hwsim_phys, list) {
+		if (idx == phy->idx) {
+			hwsim_del(phy);
+			mutex_unlock(&hwsim_phys_lock);
+			return 0;
+		}
+	}
+	mutex_unlock(&hwsim_phys_lock);
+
+	return -ENODEV;
+}
+
+static int append_radio_msg(struct sk_buff *skb, struct hwsim_phy *phy)
+{
+	struct nlattr *nl_edges, *nl_edge;
+	struct hwsim_edge_info *einfo;
+	struct hwsim_edge *e;
+	int ret;
+
+	ret = nla_put_u32(skb, MAC802154_HWSIM_ATTR_RADIO_ID, phy->idx);
+	if (ret < 0)
+		return ret;
+
+	rcu_read_lock();
+	if (list_empty(&phy->edges)) {
+		rcu_read_unlock();
+		return 0;
+	}
+
+	nl_edges = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGES);
+	if (!nl_edges) {
+		rcu_read_unlock();
+		return -ENOBUFS;
+	}
+
+	list_for_each_entry_rcu(e, &phy->edges, list) {
+		nl_edge = nla_nest_start(skb, MAC802154_HWSIM_ATTR_RADIO_EDGE);
+		if (!nl_edge) {
+			rcu_read_unlock();
+			nla_nest_cancel(skb, nl_edges);
+			return -ENOBUFS;
+		}
+
+		ret = nla_put_u32(skb, MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID,
+				  e->endpoint->idx);
+		if (ret < 0) {
+			rcu_read_unlock();
+			nla_nest_cancel(skb, nl_edge);
+			nla_nest_cancel(skb, nl_edges);
+			return ret;
+		}
+
+		einfo = rcu_dereference(e->info);
+		ret = nla_put_u8(skb, MAC802154_HWSIM_EDGE_ATTR_LQI,
+				 einfo->lqi);
+		if (ret < 0) {
+			rcu_read_unlock();
+			nla_nest_cancel(skb, nl_edge);
+			nla_nest_cancel(skb, nl_edges);
+			return ret;
+		}
+
+		nla_nest_end(skb, nl_edge);
+	}
+	rcu_read_unlock();
+
+	nla_nest_end(skb, nl_edges);
+
+	return 0;
+}
+
+static int hwsim_get_radio(struct sk_buff *skb, struct hwsim_phy *phy,
+			   u32 portid, u32 seq,
+			   struct netlink_callback *cb, int flags)
+{
+	void *hdr;
+	int res = -EMSGSIZE;
+
+	hdr = genlmsg_put(skb, portid, seq, &hwsim_genl_family, flags,
+			  MAC802154_HWSIM_CMD_GET_RADIO);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (cb)
+		genl_dump_check_consistent(cb, hdr);
+
+	res = append_radio_msg(skb, phy);
+	if (res < 0)
+		goto out_err;
+
+	genlmsg_end(skb, hdr);
+	return 0;
+
+out_err:
+	genlmsg_cancel(skb, hdr);
+	return res;
+}
+
+static int hwsim_get_radio_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct hwsim_phy *phy;
+	struct sk_buff *skb;
+	int idx, res = -ENODEV;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID])
+		return -EINVAL;
+	idx = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry(phy, &hwsim_phys, list) {
+		if (phy->idx != idx)
+			continue;
+
+		skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+		if (!skb) {
+			res = -ENOMEM;
+			goto out_err;
+		}
+
+		res = hwsim_get_radio(skb, phy, info->snd_portid,
+				      info->snd_seq, NULL, 0);
+		if (res < 0) {
+			nlmsg_free(skb);
+			goto out_err;
+		}
+
+		genlmsg_reply(skb, info);
+		break;
+	}
+
+out_err:
+	mutex_unlock(&hwsim_phys_lock);
+
+	return res;
+}
+
+static int hwsim_dump_radio_nl(struct sk_buff *skb,
+			       struct netlink_callback *cb)
+{
+	int idx = cb->args[0];
+	struct hwsim_phy *phy;
+	int res;
+
+	mutex_lock(&hwsim_phys_lock);
+
+	if (idx == hwsim_radio_idx)
+		goto done;
+
+	list_for_each_entry(phy, &hwsim_phys, list) {
+		if (phy->idx < idx)
+			continue;
+
+		res = hwsim_get_radio(skb, phy, NETLINK_CB(cb->skb).portid,
+				      cb->nlh->nlmsg_seq, cb, NLM_F_MULTI);
+		if (res < 0)
+			break;
+
+		idx = phy->idx + 1;
+	}
+
+	cb->args[0] = idx;
+
+done:
+	mutex_unlock(&hwsim_phys_lock);
+	return skb->len;
+}
+
+/* caller need to held hwsim_phys_lock */
+static struct hwsim_phy *hwsim_get_radio_by_id(uint32_t idx)
+{
+	struct hwsim_phy *phy;
+
+	list_for_each_entry(phy, &hwsim_phys, list) {
+		if (phy->idx == idx)
+			return phy;
+	}
+
+	return NULL;
+}
+
+static const struct nla_policy hwsim_edge_policy[MAC802154_HWSIM_EDGE_ATTR_MAX + 1] = {
+	[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] = { .type = NLA_U32 },
+	[MAC802154_HWSIM_EDGE_ATTR_LQI] = { .type = NLA_U8 },
+};
+
+static struct hwsim_edge *hwsim_alloc_edge(struct hwsim_phy *endpoint, u8 lqi)
+{
+	struct hwsim_edge_info *einfo;
+	struct hwsim_edge *e;
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return NULL;
+
+	einfo = kzalloc(sizeof(*einfo), GFP_KERNEL);
+	if (!einfo) {
+		kfree(e);
+		return NULL;
+	}
+
+	einfo->lqi = 0xff;
+	e->info = einfo;
+	e->endpoint = endpoint;
+
+	return e;
+}
+
+static void hwsim_free_edge(struct hwsim_edge *e)
+{
+	kfree_rcu(e->info, rcu);
+	kfree_rcu(e, rcu);
+}
+
+static int hwsim_new_edge_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1];
+	struct hwsim_phy *phy_v0, *phy_v1;
+	struct hwsim_edge *e;
+	u32 v0, v1;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] &&
+	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
+		return -EINVAL;
+
+	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX,
+			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
+			     hwsim_edge_policy, NULL))
+		return -EINVAL;
+
+	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID])
+		return -EINVAL;
+
+	v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+	v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]);
+
+	if (v0 == v1)
+		return -EINVAL;
+
+	mutex_lock(&hwsim_phys_lock);
+	phy_v0 = hwsim_get_radio_by_id(v0);
+	if (!phy_v0) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	phy_v1 = hwsim_get_radio_by_id(v1);
+	if (!phy_v1) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy_v0->edges, list) {
+		if (e->endpoint->idx == v1) {
+			mutex_unlock(&hwsim_phys_lock);
+			rcu_read_unlock();
+			return -EEXIST;
+		}
+	}
+	rcu_read_unlock();
+
+	e = hwsim_alloc_edge(phy_v1, 0xff);
+	if (!e) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOMEM;
+	}
+	list_add_rcu(&e->list, &phy_v0->edges);
+	/* wait until changes are done under hwsim_phys_lock lock
+	 * should prevent of calling this function twice while
+	 * edges list has not the changes yet.
+	 */
+	synchronize_rcu();
+	mutex_unlock(&hwsim_phys_lock);
+
+	return 0;
+}
+
+static int hwsim_del_edge_nl(struct sk_buff *msg, struct genl_info *info)
+{
+	struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1];
+	struct hwsim_phy *phy_v0;
+	struct hwsim_edge *e;
+	u32 v0, v1;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] &&
+	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
+		return -EINVAL;
+
+	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX + 1,
+			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
+			     hwsim_edge_policy, NULL))
+		return -EINVAL;
+
+	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID])
+		return -EINVAL;
+
+	v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+	v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]);
+
+	mutex_lock(&hwsim_phys_lock);
+	phy_v0 = hwsim_get_radio_by_id(v0);
+	if (!phy_v0) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy_v0->edges, list) {
+		if (e->endpoint->idx == v1) {
+			rcu_read_unlock();
+			list_del_rcu(&e->list);
+			hwsim_free_edge(e);
+			/* same again - wait until list changes are done */
+			synchronize_rcu();
+			mutex_unlock(&hwsim_phys_lock);
+			return 0;
+		}
+	}
+	rcu_read_unlock();
+
+	mutex_unlock(&hwsim_phys_lock);
+
+	return -ENOENT;
+}
+
+static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info)
+{
+	struct nlattr *edge_attrs[MAC802154_HWSIM_EDGE_ATTR_MAX + 1];
+	struct hwsim_edge_info *einfo;
+	struct hwsim_phy *phy_v0;
+	struct hwsim_edge *e;
+	u32 v0, v1;
+	u8 lqi;
+
+	if (!info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID] &&
+	    !info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE])
+		return -EINVAL;
+
+	if (nla_parse_nested(edge_attrs, MAC802154_HWSIM_EDGE_ATTR_MAX + 1,
+			     info->attrs[MAC802154_HWSIM_ATTR_RADIO_EDGE],
+			     hwsim_edge_policy, NULL))
+		return -EINVAL;
+
+	if (!edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID] &&
+	    !edge_attrs[MAC802154_HWSIM_EDGE_ATTR_LQI])
+		return -EINVAL;
+
+	v0 = nla_get_u32(info->attrs[MAC802154_HWSIM_ATTR_RADIO_ID]);
+	v1 = nla_get_u32(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID]);
+	lqi = nla_get_u8(edge_attrs[MAC802154_HWSIM_EDGE_ATTR_LQI]);
+
+	mutex_lock(&hwsim_phys_lock);
+	phy_v0 = hwsim_get_radio_by_id(v0);
+	if (!phy_v0) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOENT;
+	}
+
+	einfo = kzalloc(sizeof(*einfo), GFP_KERNEL);
+	if (!info) {
+		mutex_unlock(&hwsim_phys_lock);
+		return -ENOMEM;
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy_v0->edges, list) {
+		if (e->endpoint->idx == v1) {
+			einfo->lqi = lqi;
+			rcu_assign_pointer(e->info, einfo);
+			rcu_read_unlock();
+			mutex_unlock(&hwsim_phys_lock);
+			return 0;
+		}
+	}
+	rcu_read_unlock();
+
+	kfree(einfo);
+	mutex_unlock(&hwsim_phys_lock);
+
+	return -ENOENT;
+}
+
+/* MAC802154_HWSIM netlink policy */
+
+static const struct nla_policy hwsim_genl_policy[MAC802154_HWSIM_ATTR_MAX + 1] = {
+	[MAC802154_HWSIM_ATTR_RADIO_ID] = { .type = NLA_U32 },
+	[MAC802154_HWSIM_ATTR_RADIO_EDGE] = { .type = NLA_NESTED },
+	[MAC802154_HWSIM_ATTR_RADIO_EDGES] = { .type = NLA_NESTED },
+};
+
+/* Generic Netlink operations array */
+static const struct genl_ops hwsim_nl_ops[] = {
+	{
+		.cmd = MAC802154_HWSIM_CMD_NEW_RADIO,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_new_radio_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_DEL_RADIO,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_del_radio_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_GET_RADIO,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_get_radio_nl,
+		.dumpit = hwsim_dump_radio_nl,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_NEW_EDGE,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_new_edge_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_DEL_EDGE,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_del_edge_nl,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+	{
+		.cmd = MAC802154_HWSIM_CMD_SET_EDGE,
+		.policy = hwsim_genl_policy,
+		.doit = hwsim_set_edge_lqi,
+		.flags = GENL_UNS_ADMIN_PERM,
+	},
+};
+
+static struct genl_family hwsim_genl_family __ro_after_init = {
+	.name = "MAC802154_HWSIM",
+	.version = 1,
+	.maxattr = MAC802154_HWSIM_ATTR_MAX,
+	.module = THIS_MODULE,
+	.ops = hwsim_nl_ops,
+	.n_ops = ARRAY_SIZE(hwsim_nl_ops),
+	.mcgrps = hwsim_mcgrps,
+	.n_mcgrps = ARRAY_SIZE(hwsim_mcgrps),
+};
+
+static void hwsim_mcast_config_msg(struct sk_buff *mcast_skb,
+				   struct genl_info *info)
+{
+	if (info)
+		genl_notify(&hwsim_genl_family, mcast_skb, info,
+			    HWSIM_MCGRP_CONFIG, GFP_KERNEL);
+	else
+		genlmsg_multicast(&hwsim_genl_family, mcast_skb, 0,
+				  HWSIM_MCGRP_CONFIG, GFP_KERNEL);
+}
+
+static void hwsim_mcast_new_radio(struct genl_info *info, struct hwsim_phy *phy)
+{
+	struct sk_buff *mcast_skb;
+	void *data;
+
+	mcast_skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!mcast_skb)
+		return;
+
+	data = genlmsg_put(mcast_skb, 0, 0, &hwsim_genl_family, 0,
+			   MAC802154_HWSIM_CMD_NEW_RADIO);
+	if (!data)
+		goto out_err;
+
+	if (append_radio_msg(mcast_skb, phy) < 0)
+		goto out_err;
+
+	genlmsg_end(mcast_skb, data);
+
+	hwsim_mcast_config_msg(mcast_skb, info);
+	return;
+
+out_err:
+	genlmsg_cancel(mcast_skb, data);
+	nlmsg_free(mcast_skb);
+}
+
+static void hwsim_edge_unsubscribe_me(struct hwsim_phy *phy)
+{
+	struct hwsim_phy *tmp;
+	struct hwsim_edge *e;
+
+	rcu_read_lock();
+	/* going to all phy edges and remove phy from it */
+	list_for_each_entry(tmp, &hwsim_phys, list) {
+		list_for_each_entry_rcu(e, &tmp->edges, list) {
+			if (e->endpoint->idx == phy->idx) {
+				list_del_rcu(&e->list);
+				hwsim_free_edge(e);
+			}
+		}
+	}
+	rcu_read_unlock();
+
+	synchronize_rcu();
+}
+
+static int hwsim_subscribe_all_others(struct hwsim_phy *phy)
+{
+	struct hwsim_phy *sub;
+	struct hwsim_edge *e;
+
+	list_for_each_entry(sub, &hwsim_phys, list) {
+		e = hwsim_alloc_edge(sub, 0xff);
+		if (!e)
+			goto me_fail;
+
+		list_add_rcu(&e->list, &phy->edges);
+	}
+
+	list_for_each_entry(sub, &hwsim_phys, list) {
+		e = hwsim_alloc_edge(phy, 0xff);
+		if (!e)
+			goto sub_fail;
+
+		list_add_rcu(&e->list, &sub->edges);
+	}
+
+	return 0;
+
+me_fail:
+	list_for_each_entry(phy, &hwsim_phys, list) {
+		list_del_rcu(&e->list);
+		hwsim_free_edge(e);
+	}
+sub_fail:
+	hwsim_edge_unsubscribe_me(phy);
+	return -ENOMEM;
+}
+
+static int hwsim_add_one(struct genl_info *info, struct device *dev,
+			 bool init)
+{
+	struct ieee802154_hw *hw;
+	struct hwsim_phy *phy;
+	struct hwsim_pib *pib;
+	int idx;
+	int err;
+
+	idx = hwsim_radio_idx++;
+
+	hw = ieee802154_alloc_hw(sizeof(*phy), &hwsim_ops);
+	if (!hw)
+		return -ENOMEM;
+
+	phy = hw->priv;
+	phy->hw = hw;
+
+	/* 868 MHz BPSK	802.15.4-2003 */
+	hw->phy->supported.channels[0] |= 1;
+	/* 915 MHz BPSK	802.15.4-2003 */
+	hw->phy->supported.channels[0] |= 0x7fe;
+	/* 2.4 GHz O-QPSK 802.15.4-2003 */
+	hw->phy->supported.channels[0] |= 0x7FFF800;
+	/* 868 MHz ASK 802.15.4-2006 */
+	hw->phy->supported.channels[1] |= 1;
+	/* 915 MHz ASK 802.15.4-2006 */
+	hw->phy->supported.channels[1] |= 0x7fe;
+	/* 868 MHz O-QPSK 802.15.4-2006 */
+	hw->phy->supported.channels[2] |= 1;
+	/* 915 MHz O-QPSK 802.15.4-2006 */
+	hw->phy->supported.channels[2] |= 0x7fe;
+	/* 2.4 GHz CSS 802.15.4a-2007 */
+	hw->phy->supported.channels[3] |= 0x3fff;
+	/* UWB Sub-gigahertz 802.15.4a-2007 */
+	hw->phy->supported.channels[4] |= 1;
+	/* UWB Low band 802.15.4a-2007 */
+	hw->phy->supported.channels[4] |= 0x1e;
+	/* UWB High band 802.15.4a-2007 */
+	hw->phy->supported.channels[4] |= 0xffe0;
+	/* 750 MHz O-QPSK 802.15.4c-2009 */
+	hw->phy->supported.channels[5] |= 0xf;
+	/* 750 MHz MPSK 802.15.4c-2009 */
+	hw->phy->supported.channels[5] |= 0xf0;
+	/* 950 MHz BPSK 802.15.4d-2009 */
+	hw->phy->supported.channels[6] |= 0x3ff;
+	/* 950 MHz GFSK 802.15.4d-2009 */
+	hw->phy->supported.channels[6] |= 0x3ffc00;
+
+	ieee802154_random_extended_addr(&hw->phy->perm_extended_addr);
+
+	/* hwsim phy channel 13 as default */
+	hw->phy->current_channel = 13;
+	pib = kzalloc(sizeof(*pib), GFP_KERNEL);
+	if (!pib) {
+		err = -ENOMEM;
+		goto err_pib;
+	}
+
+	phy->pib = pib;
+	phy->idx = idx;
+	INIT_LIST_HEAD(&phy->edges);
+
+	hw->flags = IEEE802154_HW_PROMISCUOUS;
+	hw->parent = dev;
+
+	err = ieee802154_register_hw(hw);
+	if (err)
+		goto err_reg;
+
+	mutex_lock(&hwsim_phys_lock);
+	if (init) {
+		err = hwsim_subscribe_all_others(phy);
+		if (err < 0)
+			goto err_reg;
+	}
+	list_add_tail(&phy->list, &hwsim_phys);
+	mutex_unlock(&hwsim_phys_lock);
+
+	hwsim_mcast_new_radio(info, phy);
+
+	return idx;
+
+err_reg:
+	kfree(pib);
+err_pib:
+	ieee802154_free_hw(phy->hw);
+	return err;
+}
+
+static void hwsim_del(struct hwsim_phy *phy)
+{
+	hwsim_edge_unsubscribe_me(phy);
+
+	list_del(&phy->list);
+	kfree_rcu(phy->pib, rcu);
+
+	ieee802154_unregister_hw(phy->hw);
+	ieee802154_free_hw(phy->hw);
+}
+
+static int hwsim_probe(struct platform_device *pdev)
+{
+	struct hwsim_phy *phy, *tmp;
+	int err, i;
+
+	for (i = 0; i < 2; i++) {
+		err = hwsim_add_one(NULL, &pdev->dev, true);
+		if (err < 0)
+			goto err_slave;
+	}
+
+	dev_info(&pdev->dev, "Added 2 mac802154 hwsim hardware radios\n");
+	return 0;
+
+err_slave:
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &hwsim_phys, list)
+		hwsim_del(phy);
+	mutex_unlock(&hwsim_phys_lock);
+	return err;
+}
+
+static int hwsim_remove(struct platform_device *pdev)
+{
+	struct hwsim_phy *phy, *tmp;
+
+	mutex_lock(&hwsim_phys_lock);
+	list_for_each_entry_safe(phy, tmp, &hwsim_phys, list)
+		hwsim_del(phy);
+	mutex_unlock(&hwsim_phys_lock);
+
+	return 0;
+}
+
+static struct platform_driver mac802154hwsim_driver = {
+	.probe = hwsim_probe,
+	.remove = hwsim_remove,
+	.driver = {
+			.name = "mac802154_hwsim",
+	},
+};
+
+static __init int hwsim_init_module(void)
+{
+	int rc;
+
+	rc = genl_register_family(&hwsim_genl_family);
+	if (rc)
+		return rc;
+
+	mac802154hwsim_dev = platform_device_register_simple("mac802154_hwsim",
+							     -1, NULL, 0);
+	if (IS_ERR(mac802154hwsim_dev)) {
+		rc = PTR_ERR(mac802154hwsim_dev);
+		goto platform_dev;
+	}
+
+	rc = platform_driver_register(&mac802154hwsim_driver);
+	if (rc < 0)
+		goto platform_drv;
+
+	return 0;
+
+platform_drv:
+	genl_unregister_family(&hwsim_genl_family);
+platform_dev:
+	platform_device_unregister(mac802154hwsim_dev);
+	return rc;
+}
+
+static __exit void hwsim_remove_module(void)
+{
+	genl_unregister_family(&hwsim_genl_family);
+	platform_driver_unregister(&mac802154hwsim_driver);
+	platform_device_unregister(mac802154hwsim_dev);
+}
+
+module_init(hwsim_init_module);
+module_exit(hwsim_remove_module);
diff --git a/drivers/net/ieee802154/mac802154_hwsim.h b/drivers/net/ieee802154/mac802154_hwsim.h
new file mode 100644
index 000000000000..6c6e30e3871d
--- /dev/null
+++ b/drivers/net/ieee802154/mac802154_hwsim.h
@@ -0,0 +1,73 @@
+#ifndef __MAC802154_HWSIM_H
+#define __MAC802154_HWSIM_H
+
+/* mac802154 hwsim netlink commands
+ *
+ * @MAC802154_HWSIM_CMD_UNSPEC: unspecified command to catch error
+ * @MAC802154_HWSIM_CMD_GET_RADIO: fetch information about existing radios
+ * @MAC802154_HWSIM_CMD_SET_RADIO: change radio parameters during runtime
+ * @MAC802154_HWSIM_CMD_NEW_RADIO: create a new radio with the given parameters
+ *	returns the radio ID (>= 0) or negative on errors, if successful
+ *	then multicast the result
+ * @MAC802154_HWSIM_CMD_DEL_RADIO: destroy a radio, reply is multicasted
+ * @MAC802154_HWSIM_CMD_GET_EDGE: fetch information about existing edges
+ * @MAC802154_HWSIM_CMD_SET_EDGE: change edge parameters during runtime
+ * @MAC802154_HWSIM_CMD_DEL_EDGE: delete edges between radios
+ * @MAC802154_HWSIM_CMD_NEW_EDGE: create a new edge between two radios
+ * @__MAC802154_HWSIM_CMD_MAX: enum limit
+ */
+enum {
+	MAC802154_HWSIM_CMD_UNSPEC,
+
+	MAC802154_HWSIM_CMD_GET_RADIO,
+	MAC802154_HWSIM_CMD_SET_RADIO,
+	MAC802154_HWSIM_CMD_NEW_RADIO,
+	MAC802154_HWSIM_CMD_DEL_RADIO,
+
+	MAC802154_HWSIM_CMD_GET_EDGE,
+	MAC802154_HWSIM_CMD_SET_EDGE,
+	MAC802154_HWSIM_CMD_DEL_EDGE,
+	MAC802154_HWSIM_CMD_NEW_EDGE,
+
+	__MAC802154_HWSIM_CMD_MAX,
+};
+
+#define MAC802154_HWSIM_CMD_MAX (__MAC802154_HWSIM_MAX - 1)
+
+/* mac802154 hwsim netlink attributes
+ *
+ * @MAC802154_HWSIM_ATTR_UNSPEC: unspecified attribute to catch error
+ * @MAC802154_HWSIM_ATTR_RADIO_ID: u32 attribute to identify the radio
+ * @MAC802154_HWSIM_ATTR_EDGE: nested attribute of edges
+ * @MAC802154_HWSIM_ATTR_EDGES: list if nested attributes which contains the
+ *	edge information according the radio id
+ * @__MAC802154_HWSIM_ATTR_MAX: enum limit
+ */
+enum {
+	MAC802154_HWSIM_ATTR_UNSPEC,
+	MAC802154_HWSIM_ATTR_RADIO_ID,
+	MAC802154_HWSIM_ATTR_RADIO_EDGE,
+	MAC802154_HWSIM_ATTR_RADIO_EDGES,
+	__MAC802154_HWSIM_ATTR_MAX,
+};
+
+#define MAC802154_HWSIM_ATTR_MAX (__MAC802154_HWSIM_ATTR_MAX - 1)
+
+/* mac802154 hwsim edge netlink attributes
+ *
+ * @MAC802154_HWSIM_EDGE_ATTR_UNSPEC: unspecified attribute to catch error
+ * @MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID: radio id where the edge points to
+ * @MAC802154_HWSIM_EDGE_ATTR_LQI: LQI value which the endpoint radio will
+ *	receive for this edge
+ * @__MAC802154_HWSIM_ATTR_MAX: enum limit
+ */
+enum {
+	MAC802154_HWSIM_EDGE_ATTR_UNSPEC,
+	MAC802154_HWSIM_EDGE_ATTR_ENDPOINT_ID,
+	MAC802154_HWSIM_EDGE_ATTR_LQI,
+	__MAC802154_HWSIM_EDGE_ATTR_MAX,
+};
+
+#define MAC802154_HWSIM_EDGE_ATTR_MAX (__MAC802154_HWSIM_EDGE_ATTR_MAX - 1)
+
+#endif /* __MAC802154_HWSIM_H */
-- 
cgit v1.2.3


From be10d5d1c2d15252624e965202508f30a218a46a Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Sat, 14 Jul 2018 12:33:06 -0400
Subject: ieee802154: fakelb: add deprecated msg while probe

Since mac802154_hwsim the fakelb driver will get deprecated. This patch will
notifier all users of fakelb to switch to the new mac802154_hwsim driver.

Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/net/ieee802154/fakelb.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ieee802154/fakelb.c b/drivers/net/ieee802154/fakelb.c
index 176395e4b7bb..3b0588d7e702 100644
--- a/drivers/net/ieee802154/fakelb.c
+++ b/drivers/net/ieee802154/fakelb.c
@@ -254,6 +254,9 @@ static __init int fakelb_init_module(void)
 {
 	ieee802154fake_dev = platform_device_register_simple(
 			     "ieee802154fakelb", -1, NULL, 0);
+
+	pr_warn("fakelb driver is marked as deprecated, please use mac802154_hwsim!\n");
+
 	return platform_driver_register(&ieee802154fake_driver);
 }
 
-- 
cgit v1.2.3


From 55f2503c3b69328735e88031ff8d6ba291bd952b Mon Sep 17 00:00:00 2001
From: Pingfan Liu <kernelfans@gmail.com>
Date: Tue, 31 Jul 2018 16:51:32 +0800
Subject: PM / reboot: Eliminate race between reboot and suspend

At present, "systemctl suspend" and "shutdown" can run in parrallel. A
system can suspend after devices_shutdown(), and resume. Then the shutdown
task goes on to power off. This causes many devices are not really shut
off. Hence replacing reboot_mutex with system_transition_mutex (renamed
from pm_mutex) to achieve the exclusion. The renaming of pm_mutex as
system_transition_mutex can be better to reflect the purpose of the mutex.

Signed-off-by: Pingfan Liu <kernelfans@gmail.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/freezing-of-tasks.txt      | 12 ++++++------
 Documentation/power/suspend-and-cpuhotplug.txt |  6 +++---
 include/linux/suspend.h                        |  2 +-
 kernel/freezer.c                               |  4 +++-
 kernel/power/hibernate.c                       | 15 ++++++++-------
 kernel/power/main.c                            | 12 ++++++------
 kernel/power/suspend.c                         |  4 ++--
 kernel/power/user.c                            |  4 ++--
 kernel/reboot.c                                |  6 +++---
 mm/page_alloc.c                                | 11 ++++++-----
 10 files changed, 40 insertions(+), 36 deletions(-)

diff --git a/Documentation/power/freezing-of-tasks.txt b/Documentation/power/freezing-of-tasks.txt
index af005770e767..cd283190855a 100644
--- a/Documentation/power/freezing-of-tasks.txt
+++ b/Documentation/power/freezing-of-tasks.txt
@@ -204,26 +204,26 @@ VI. Are there any precautions to be taken to prevent freezing failures?
 
 Yes, there are.
 
-First of all, grabbing the 'pm_mutex' lock to mutually exclude a piece of code
+First of all, grabbing the 'system_transition_mutex' lock to mutually exclude a piece of code
 from system-wide sleep such as suspend/hibernation is not encouraged.
 If possible, that piece of code must instead hook onto the suspend/hibernation
 notifiers to achieve mutual exclusion. Look at the CPU-Hotplug code
 (kernel/cpu.c) for an example.
 
-However, if that is not feasible, and grabbing 'pm_mutex' is deemed necessary,
-it is strongly discouraged to directly call mutex_[un]lock(&pm_mutex) since
+However, if that is not feasible, and grabbing 'system_transition_mutex' is deemed necessary,
+it is strongly discouraged to directly call mutex_[un]lock(&system_transition_mutex) since
 that could lead to freezing failures, because if the suspend/hibernate code
-successfully acquired the 'pm_mutex' lock, and hence that other entity failed
+successfully acquired the 'system_transition_mutex' lock, and hence that other entity failed
 to acquire the lock, then that task would get blocked in TASK_UNINTERRUPTIBLE
 state. As a consequence, the freezer would not be able to freeze that task,
 leading to freezing failure.
 
 However, the [un]lock_system_sleep() APIs are safe to use in this scenario,
 since they ask the freezer to skip freezing this task, since it is anyway
-"frozen enough" as it is blocked on 'pm_mutex', which will be released
+"frozen enough" as it is blocked on 'system_transition_mutex', which will be released
 only after the entire suspend/hibernation sequence is complete.
 So, to summarize, use [un]lock_system_sleep() instead of directly using
-mutex_[un]lock(&pm_mutex). That would prevent freezing failures.
+mutex_[un]lock(&system_transition_mutex). That would prevent freezing failures.
 
 V. Miscellaneous
 /sys/power/pm_freeze_timeout controls how long it will cost at most to freeze
diff --git a/Documentation/power/suspend-and-cpuhotplug.txt b/Documentation/power/suspend-and-cpuhotplug.txt
index 6f55eb960a6d..a8751b8df10e 100644
--- a/Documentation/power/suspend-and-cpuhotplug.txt
+++ b/Documentation/power/suspend-and-cpuhotplug.txt
@@ -32,7 +32,7 @@ More details follow:
                                     sysfs file
                                         |
                                         v
-                               Acquire pm_mutex lock
+                               Acquire system_transition_mutex lock
                                         |
                                         v
                              Send PM_SUSPEND_PREPARE
@@ -96,10 +96,10 @@ execution during resume):
 
 * thaw tasks
 * send PM_POST_SUSPEND notifications
-* Release pm_mutex lock.
+* Release system_transition_mutex lock.
 
 
-It is to be noted here that the pm_mutex lock is acquired at the very
+It is to be noted here that the system_transition_mutex lock is acquired at the very
 beginning, when we are just starting out to suspend, and then released only
 after the entire cycle is complete (i.e., suspend + resume).
 
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 440b62f7502e..5a28ac9284f0 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -414,7 +414,7 @@ static inline bool hibernation_available(void) { return false; }
 #define PM_RESTORE_PREPARE	0x0005 /* Going to restore a saved image */
 #define PM_POST_RESTORE		0x0006 /* Restore failed */
 
-extern struct mutex pm_mutex;
+extern struct mutex system_transition_mutex;
 
 #ifdef CONFIG_PM_SLEEP
 void save_processor_state(void);
diff --git a/kernel/freezer.c b/kernel/freezer.c
index 6f56a9e219fa..b162b74611e4 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -15,7 +15,9 @@
 atomic_t system_freezing_cnt = ATOMIC_INIT(0);
 EXPORT_SYMBOL(system_freezing_cnt);
 
-/* indicate whether PM freezing is in effect, protected by pm_mutex */
+/* indicate whether PM freezing is in effect, protected by
+ * system_transition_mutex
+ */
 bool pm_freezing;
 bool pm_nosig_freezing;
 
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 38f3f96b4b12..abef759de7c8 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -338,7 +338,7 @@ static int create_image(int platform_mode)
  * hibernation_snapshot - Quiesce devices and create a hibernation image.
  * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- * This routine must be called with pm_mutex held.
+ * This routine must be called with system_transition_mutex held.
  */
 int hibernation_snapshot(int platform_mode)
 {
@@ -500,8 +500,9 @@ static int resume_target_kernel(bool platform_mode)
  * hibernation_restore - Quiesce devices and restore from a hibernation image.
  * @platform_mode: If set, use platform driver to prepare for the transition.
  *
- * This routine must be called with pm_mutex held.  If it is successful, control
- * reappears in the restored target kernel in hibernation_snapshot().
+ * This routine must be called with system_transition_mutex held.  If it is
+ * successful, control reappears in the restored target kernel in
+ * hibernation_snapshot().
  */
 int hibernation_restore(int platform_mode)
 {
@@ -806,13 +807,13 @@ static int software_resume(void)
 	 * name_to_dev_t() below takes a sysfs buffer mutex when sysfs
 	 * is configured into the kernel. Since the regular hibernate
 	 * trigger path is via sysfs which takes a buffer mutex before
-	 * calling hibernate functions (which take pm_mutex) this can
-	 * cause lockdep to complain about a possible ABBA deadlock
+	 * calling hibernate functions (which take system_transition_mutex)
+	 * this can cause lockdep to complain about a possible ABBA deadlock
 	 * which cannot happen since we're in the boot code here and
 	 * sysfs can't be invoked yet. Therefore, we use a subclass
 	 * here to avoid lockdep complaining.
 	 */
-	mutex_lock_nested(&pm_mutex, SINGLE_DEPTH_NESTING);
+	mutex_lock_nested(&system_transition_mutex, SINGLE_DEPTH_NESTING);
 
 	if (swsusp_resume_device)
 		goto Check_image;
@@ -900,7 +901,7 @@ static int software_resume(void)
 	atomic_inc(&snapshot_device_available);
 	/* For success case, the suspend path will release the lock */
  Unlock:
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 	pm_pr_dbg("Hibernation image not present or could not be loaded.\n");
 	return error;
  Close_Finish:
diff --git a/kernel/power/main.c b/kernel/power/main.c
index d9706da10930..35b50823d83b 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -15,17 +15,16 @@
 #include <linux/workqueue.h>
 #include <linux/debugfs.h>
 #include <linux/seq_file.h>
+#include <linux/suspend.h>
 
 #include "power.h"
 
-DEFINE_MUTEX(pm_mutex);
-
 #ifdef CONFIG_PM_SLEEP
 
 void lock_system_sleep(void)
 {
 	current->flags |= PF_FREEZER_SKIP;
-	mutex_lock(&pm_mutex);
+	mutex_lock(&system_transition_mutex);
 }
 EXPORT_SYMBOL_GPL(lock_system_sleep);
 
@@ -37,8 +36,9 @@ void unlock_system_sleep(void)
 	 *
 	 * Reason:
 	 * Fundamentally, we just don't need it, because freezing condition
-	 * doesn't come into effect until we release the pm_mutex lock,
-	 * since the freezer always works with pm_mutex held.
+	 * doesn't come into effect until we release the
+	 * system_transition_mutex lock, since the freezer always works with
+	 * system_transition_mutex held.
 	 *
 	 * More importantly, in the case of hibernation,
 	 * unlock_system_sleep() gets called in snapshot_read() and
@@ -47,7 +47,7 @@ void unlock_system_sleep(void)
 	 * enter the refrigerator, thus causing hibernation to lockup.
 	 */
 	current->flags &= ~PF_FREEZER_SKIP;
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 }
 EXPORT_SYMBOL_GPL(unlock_system_sleep);
 
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 87331565e505..9e13afe65a14 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -556,7 +556,7 @@ static int enter_state(suspend_state_t state)
 	} else if (!valid_state(state)) {
 		return -EINVAL;
 	}
-	if (!mutex_trylock(&pm_mutex))
+	if (!mutex_trylock(&system_transition_mutex))
 		return -EBUSY;
 
 	if (state == PM_SUSPEND_TO_IDLE)
@@ -590,7 +590,7 @@ static int enter_state(suspend_state_t state)
 	pm_pr_dbg("Finishing wakeup.\n");
 	suspend_finish();
  Unlock:
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 	return error;
 }
 
diff --git a/kernel/power/user.c b/kernel/power/user.c
index abd225550271..2d8b60a3c86b 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -216,7 +216,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!mutex_trylock(&pm_mutex))
+	if (!mutex_trylock(&system_transition_mutex))
 		return -EBUSY;
 
 	lock_device_hotplug();
@@ -394,7 +394,7 @@ static long snapshot_ioctl(struct file *filp, unsigned int cmd,
 	}
 
 	unlock_device_hotplug();
-	mutex_unlock(&pm_mutex);
+	mutex_unlock(&system_transition_mutex);
 
 	return error;
 }
diff --git a/kernel/reboot.c b/kernel/reboot.c
index e4ced883d8de..8fb44dec9ad7 100644
--- a/kernel/reboot.c
+++ b/kernel/reboot.c
@@ -294,7 +294,7 @@ void kernel_power_off(void)
 }
 EXPORT_SYMBOL_GPL(kernel_power_off);
 
-static DEFINE_MUTEX(reboot_mutex);
+DEFINE_MUTEX(system_transition_mutex);
 
 /*
  * Reboot system call: for obvious reasons only root may call it,
@@ -338,7 +338,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 	if ((cmd == LINUX_REBOOT_CMD_POWER_OFF) && !pm_power_off)
 		cmd = LINUX_REBOOT_CMD_HALT;
 
-	mutex_lock(&reboot_mutex);
+	mutex_lock(&system_transition_mutex);
 	switch (cmd) {
 	case LINUX_REBOOT_CMD_RESTART:
 		kernel_restart(NULL);
@@ -389,7 +389,7 @@ SYSCALL_DEFINE4(reboot, int, magic1, int, magic2, unsigned int, cmd,
 		ret = -EINVAL;
 		break;
 	}
-	mutex_unlock(&reboot_mutex);
+	mutex_unlock(&system_transition_mutex);
 	return ret;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1521100f1e63..e47f9e467408 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -155,16 +155,17 @@ static inline void set_pcppage_migratetype(struct page *page, int migratetype)
  * The following functions are used by the suspend/hibernate code to temporarily
  * change gfp_allowed_mask in order to avoid using I/O during memory allocations
  * while devices are suspended.  To avoid races with the suspend/hibernate code,
- * they should always be called with pm_mutex held (gfp_allowed_mask also should
- * only be modified with pm_mutex held, unless the suspend/hibernate code is
- * guaranteed not to run in parallel with that modification).
+ * they should always be called with system_transition_mutex held
+ * (gfp_allowed_mask also should only be modified with system_transition_mutex
+ * held, unless the suspend/hibernate code is guaranteed not to run in parallel
+ * with that modification).
  */
 
 static gfp_t saved_gfp_mask;
 
 void pm_restore_gfp_mask(void)
 {
-	WARN_ON(!mutex_is_locked(&pm_mutex));
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 	if (saved_gfp_mask) {
 		gfp_allowed_mask = saved_gfp_mask;
 		saved_gfp_mask = 0;
@@ -173,7 +174,7 @@ void pm_restore_gfp_mask(void)
 
 void pm_restrict_gfp_mask(void)
 {
-	WARN_ON(!mutex_is_locked(&pm_mutex));
+	WARN_ON(!mutex_is_locked(&system_transition_mutex));
 	WARN_ON(saved_gfp_mask);
 	saved_gfp_mask = gfp_allowed_mask;
 	gfp_allowed_mask &= ~(__GFP_IO | __GFP_FS);
-- 
cgit v1.2.3


From 34dbc9c6584d28d307690e13af882d159562581f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Sat, 4 Aug 2018 12:14:02 +0200
Subject: PCI/xilinx: Depend on OF instead of the ARCH

There isn't a hard dependency of the Xilinx AXI-PCIe host bridge on any
architecture.  For example: at SiFive we map RISC-V cores to Xilinx FPGAs
and connect the Xilinx IP via a TileLink adapter, so the RISC-V Linux
port will need to be able to enable PCIE_XILINX in order to have PCIe
support.

This patch decouples the PCIE_XILINX support from ARCH.  Instead it just
depends on OF, which is the only true dependency.

Signed-off-by: Palmer Dabbelt <palmer@dabbelt.com>
[hch: switch to OF instead of OF_PCI now that the latter is gone]
Signed-off-by: Christoph Hellwig <hch@lst.de>
[lorenzo.pieralisi@arm.com: trimmed the commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 18fa09b3ac8f..1fc3d4eb373d 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -103,7 +103,7 @@ config PCI_HOST_GENERIC
 
 config PCIE_XILINX
 	bool "Xilinx AXI PCIe host bridge support"
-	depends on ARCH_ZYNQ || MICROBLAZE || (MIPS && PCI_DRIVERS_GENERIC) || COMPILE_TEST
+	depends on OF || COMPILE_TEST
 	help
 	  Say 'Y' here if you want kernel to support the Xilinx AXI PCIe
 	  Host Bridge driver.
-- 
cgit v1.2.3


From be36abb71d878f3320412a84e6bbec8dd796010c Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@bootlin.com>
Date: Wed, 25 Jul 2018 14:26:21 +0200
Subject: pinctrl: ocelot: add support for interrupt controller

This GPIO controller can serve as an interrupt controller as well on the
GPIOs it handles.

An interrupt is generated whenever a GPIO line changes and the
interrupt for this GPIO line is enabled. This means that both the
changes from low to high and high to low generate an interrupt.

For some use cases, it makes sense to ignore the high to low change and
not generate an interrupt. Such a use case is a line that is hold in a
level high/low manner until the event holding the line gets acked.
This can be achieved by making sure the interrupt on the GPIO controller
side gets acked and masked only after the line gets hold in its default
state, this is what's done with the fasteoi functions.

Only IRQ_TYPE_EDGE_BOTH and IRQ_TYPE_LEVEL_HIGH are supported for now.

Signed-off-by: Quentin Schulz <quentin.schulz@bootlin.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/Kconfig          |   1 +
 drivers/pinctrl/pinctrl-ocelot.c | 102 ++++++++++++++++++++++++++++++++++++++-
 2 files changed, 101 insertions(+), 2 deletions(-)

diff --git a/drivers/pinctrl/Kconfig b/drivers/pinctrl/Kconfig
index 522782d1ea49..8d4b7e999f02 100644
--- a/drivers/pinctrl/Kconfig
+++ b/drivers/pinctrl/Kconfig
@@ -332,6 +332,7 @@ config PINCTRL_OCELOT
 	depends on OF
 	depends on MSCC_OCELOT || COMPILE_TEST
 	select GPIOLIB
+	select GPIOLIB_IRQCHIP
 	select GENERIC_PINCONF
 	select GENERIC_PINCTRL_GROUPS
 	select GENERIC_PINMUX_FUNCTIONS
diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index e93669f4d1c8..f9fc2b3a8731 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -11,6 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/of_platform.h>
 #include <linux/pinctrl/pinctrl.h>
 #include <linux/pinctrl/pinmux.h>
@@ -427,11 +428,98 @@ static const struct gpio_chip ocelot_gpiolib_chip = {
 	.owner = THIS_MODULE,
 };
 
+static void ocelot_irq_mask(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_update_bits(info->map, OCELOT_GPIO_INTR_ENA, BIT(gpio), 0);
+}
+
+static void ocelot_irq_unmask(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_update_bits(info->map, OCELOT_GPIO_INTR_ENA, BIT(gpio),
+			   BIT(gpio));
+}
+
+static void ocelot_irq_ack(struct irq_data *data)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(data);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int gpio = irqd_to_hwirq(data);
+
+	regmap_write_bits(info->map, OCELOT_GPIO_INTR, BIT(gpio), BIT(gpio));
+}
+
+static int ocelot_irq_set_type(struct irq_data *data, unsigned int type);
+
+static struct irq_chip ocelot_eoi_irqchip = {
+	.name		= "gpio",
+	.irq_mask	= ocelot_irq_mask,
+	.irq_eoi	= ocelot_irq_ack,
+	.irq_unmask	= ocelot_irq_unmask,
+	.flags          = IRQCHIP_EOI_THREADED | IRQCHIP_EOI_IF_HANDLED,
+	.irq_set_type	= ocelot_irq_set_type,
+};
+
+static struct irq_chip ocelot_irqchip = {
+	.name		= "gpio",
+	.irq_mask	= ocelot_irq_mask,
+	.irq_ack	= ocelot_irq_ack,
+	.irq_unmask	= ocelot_irq_unmask,
+	.irq_set_type	= ocelot_irq_set_type,
+};
+
+static int ocelot_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	type &= IRQ_TYPE_SENSE_MASK;
+
+	if (!(type & (IRQ_TYPE_EDGE_BOTH | IRQ_TYPE_LEVEL_HIGH)))
+		return -EINVAL;
+
+	if (type & IRQ_TYPE_LEVEL_HIGH)
+		irq_set_chip_handler_name_locked(data, &ocelot_eoi_irqchip,
+						 handle_fasteoi_irq, NULL);
+	if (type & IRQ_TYPE_EDGE_BOTH)
+		irq_set_chip_handler_name_locked(data, &ocelot_irqchip,
+						 handle_edge_irq, NULL);
+
+	return 0;
+}
+
+static void ocelot_irq_handler(struct irq_desc *desc)
+{
+	struct irq_chip *parent_chip = irq_desc_get_chip(desc);
+	struct gpio_chip *chip = irq_desc_get_handler_data(desc);
+	struct ocelot_pinctrl *info = gpiochip_get_data(chip);
+	unsigned int reg = 0, irq;
+	unsigned long irqs;
+
+	regmap_read(info->map, OCELOT_GPIO_INTR_IDENT, &reg);
+	if (!reg)
+		return;
+
+	chained_irq_enter(parent_chip, desc);
+
+	irqs = reg;
+
+	for_each_set_bit(irq, &irqs, OCELOT_PINS) {
+		generic_handle_irq(irq_linear_revmap(chip->irq.domain, irq));
+	}
+
+	chained_irq_exit(parent_chip, desc);
+}
+
 static int ocelot_gpiochip_register(struct platform_device *pdev,
 				    struct ocelot_pinctrl *info)
 {
 	struct gpio_chip *gc;
-	int ret;
+	int ret, irq;
 
 	info->gpio_chip = ocelot_gpiolib_chip;
 
@@ -446,7 +534,17 @@ static int ocelot_gpiochip_register(struct platform_device *pdev,
 	if (ret)
 		return ret;
 
-	/* TODO: this can be used as an irqchip but no board is using that */
+	irq = irq_of_parse_and_map(pdev->dev.of_node, 0);
+	if (irq <= 0)
+		return irq;
+
+	ret = gpiochip_irqchip_add(gc, &ocelot_irqchip, 0, handle_edge_irq,
+				   IRQ_TYPE_NONE);
+	if (ret)
+		return ret;
+
+	gpiochip_set_chained_irqchip(gc, &ocelot_irqchip, irq,
+				     ocelot_irq_handler);
 
 	return 0;
 }
-- 
cgit v1.2.3


From a944442c2b8a420301e7830f976bab8cc86a2b4d Mon Sep 17 00:00:00 2001
From: Allen Pais <allen.lkml@gmail.com>
Date: Tue, 12 Jun 2018 17:18:25 +0530
Subject: btrfs: replace get_seconds with new 64bit time API

The get_seconds() function is deprecated as it truncates the timestamp
to 32 bits. Change it to or ktime_get_real_seconds().

Signed-off-by: Allen Pais <allen.lkml@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 4 ++--
 fs/btrfs/dev-replace.c | 8 ++++----
 fs/btrfs/disk-io.c     | 4 ++--
 fs/btrfs/transaction.c | 2 +-
 fs/btrfs/transaction.h | 2 +-
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 118346aceea9..e671a1fcbbec 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -342,8 +342,8 @@ struct btrfs_path {
 					sizeof(struct btrfs_item))
 struct btrfs_dev_replace {
 	u64 replace_state;	/* see #define above */
-	u64 time_started;	/* seconds since 1-Jan-1970 */
-	u64 time_stopped;	/* seconds since 1-Jan-1970 */
+	time64_t time_started;	/* seconds since 1-Jan-1970 */
+	time64_t time_stopped;	/* seconds since 1-Jan-1970 */
 	atomic64_t num_write_errors;
 	atomic64_t num_uncorrectable_read_errors;
 
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index e2ba0419297a..1b30c38d05c9 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -465,7 +465,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
 	 * go to the tgtdev as well (refer to btrfs_map_block()).
 	 */
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED;
-	dev_replace->time_started = get_seconds();
+	dev_replace->time_started = ktime_get_real_seconds();
 	dev_replace->cursor_left = 0;
 	dev_replace->committed_cursor_left = 0;
 	dev_replace->cursor_left_last_write_of_item = 0;
@@ -618,7 +618,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 			  : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED;
 	dev_replace->tgtdev = NULL;
 	dev_replace->srcdev = NULL;
-	dev_replace->time_stopped = get_seconds();
+	dev_replace->time_stopped = ktime_get_real_seconds();
 	dev_replace->item_needs_writeback = 1;
 
 	/* replace old device with new one in mapping tree */
@@ -807,7 +807,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		break;
 	}
 	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED;
-	dev_replace->time_stopped = get_seconds();
+	dev_replace->time_stopped = ktime_get_real_seconds();
 	dev_replace->item_needs_writeback = 1;
 	btrfs_dev_replace_write_unlock(dev_replace);
 	btrfs_scrub_cancel(fs_info);
@@ -848,7 +848,7 @@ void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 		dev_replace->replace_state =
 			BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
-		dev_replace->time_stopped = get_seconds();
+		dev_replace->time_stopped = ktime_get_real_seconds();
 		dev_replace->item_needs_writeback = 1;
 		btrfs_info(fs_info, "suspending dev_replace for unmount");
 		break;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 205092dc9390..f3224e23d5fa 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1803,7 +1803,7 @@ static int transaction_kthread(void *arg)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_transaction *cur;
 	u64 transid;
-	unsigned long now;
+	time64_t now;
 	unsigned long delay;
 	bool cannot_commit;
 
@@ -1819,7 +1819,7 @@ static int transaction_kthread(void *arg)
 			goto sleep;
 		}
 
-		now = get_seconds();
+		now = ktime_get_real_seconds();
 		if (cur->state < TRANS_STATE_BLOCKED &&
 		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index ff5f6c719976..56c8bab0b816 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -241,7 +241,7 @@ loop:
 	refcount_set(&cur_trans->use_count, 2);
 	atomic_set(&cur_trans->pending_ordered, 0);
 	cur_trans->flags = 0;
-	cur_trans->start_time = get_seconds();
+	cur_trans->start_time = ktime_get_real_seconds();
 
 	memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs));
 
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 94439482a0ec..4cbb1b55387d 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -48,7 +48,7 @@ struct btrfs_transaction {
 	int aborted;
 	struct list_head list;
 	struct extent_io_tree dirty_pages;
-	unsigned long start_time;
+	time64_t start_time;
 	wait_queue_head_t writer_wait;
 	wait_queue_head_t commit_wait;
 	wait_queue_head_t pending_wait;
-- 
cgit v1.2.3


From 9bebe665c3e4f4af30add8602217938d8c17ee23 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 6 Jun 2018 13:13:12 +0800
Subject: btrfs: scrub: Remove unused copy_nocow_pages and its callchain

Since commit ac0b4145d662a3b9e340 ("btrfs: scrub: Don't use inode pages
for device replace") the function is not used and we can remove all
functions down the call chain.

There was an optimization that reused inode pages to speed up device
replace, but broke when there was nodatasum and compressed page. The
potential performance gain is small so we don't loose much by removing
it and using scrub_pages same as the other pages.

Signed-off-by: Qu Wenruo <wqu@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/scrub.c | 365 -------------------------------------------------------
 1 file changed, 365 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 6702896cdb8f..5bce2330ec64 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -197,23 +197,6 @@ struct scrub_fixup_nodatasum {
 	int			mirror_num;
 };
 
-struct scrub_nocow_inode {
-	u64			inum;
-	u64			offset;
-	u64			root;
-	struct list_head	list;
-};
-
-struct scrub_copy_nocow_ctx {
-	struct scrub_ctx	*sctx;
-	u64			logical;
-	u64			len;
-	int			mirror_num;
-	u64			physical_for_dev_replace;
-	struct list_head	inodes;
-	struct btrfs_work	work;
-};
-
 struct scrub_warning {
 	struct btrfs_path	*path;
 	u64			extent_item_size;
@@ -277,13 +260,6 @@ static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 static void scrub_wr_submit(struct scrub_ctx *sctx);
 static void scrub_wr_bio_end_io(struct bio *bio);
 static void scrub_wr_bio_end_io_worker(struct btrfs_work *work);
-static int write_page_nocow(struct scrub_ctx *sctx,
-			    u64 physical_for_dev_replace, struct page *page);
-static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
-				      struct scrub_copy_nocow_ctx *ctx);
-static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
-			    int mirror_num, u64 physical_for_dev_replace);
-static void copy_nocow_pages_worker(struct btrfs_work *work);
 static void __scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info);
 static void scrub_put_ctx(struct scrub_ctx *sctx);
@@ -2800,17 +2776,10 @@ static int scrub_extent(struct scrub_ctx *sctx, struct map_lookup *map,
 			have_csum = scrub_find_csum(sctx, logical, csum);
 			if (have_csum == 0)
 				++sctx->stat.no_csum;
-			if (0 && sctx->is_dev_replace && !have_csum) {
-				ret = copy_nocow_pages(sctx, logical, l,
-						       mirror_num,
-						      physical_for_dev_replace);
-				goto behind_scrub_pages;
-			}
 		}
 		ret = scrub_pages(sctx, logical, l, physical, dev, flags, gen,
 				  mirror_num, have_csum ? csum : NULL, 0,
 				  physical_for_dev_replace);
-behind_scrub_pages:
 		if (ret)
 			return ret;
 		len -= l;
@@ -4072,10 +4041,6 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 		if (!fs_info->scrub_wr_completion_workers)
 			goto fail_scrub_wr_completion_workers;
 
-		fs_info->scrub_nocow_workers =
-			btrfs_alloc_workqueue(fs_info, "scrubnc", flags, 1, 0);
-		if (!fs_info->scrub_nocow_workers)
-			goto fail_scrub_nocow_workers;
 		fs_info->scrub_parity_workers =
 			btrfs_alloc_workqueue(fs_info, "scrubparity", flags,
 					      max_active, 2);
@@ -4086,8 +4051,6 @@ static noinline_for_stack int scrub_workers_get(struct btrfs_fs_info *fs_info,
 	return 0;
 
 fail_scrub_parity_workers:
-	btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
-fail_scrub_nocow_workers:
 	btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
 fail_scrub_wr_completion_workers:
 	btrfs_destroy_workqueue(fs_info->scrub_workers);
@@ -4100,7 +4063,6 @@ static noinline_for_stack void scrub_workers_put(struct btrfs_fs_info *fs_info)
 	if (--fs_info->scrub_workers_refcnt == 0) {
 		btrfs_destroy_workqueue(fs_info->scrub_workers);
 		btrfs_destroy_workqueue(fs_info->scrub_wr_completion_workers);
-		btrfs_destroy_workqueue(fs_info->scrub_nocow_workers);
 		btrfs_destroy_workqueue(fs_info->scrub_parity_workers);
 	}
 	WARN_ON(fs_info->scrub_workers_refcnt < 0);
@@ -4359,330 +4321,3 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 	*extent_dev = bbio->stripes[0].dev;
 	btrfs_put_bbio(bbio);
 }
-
-static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
-			    int mirror_num, u64 physical_for_dev_replace)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx;
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	nocow_ctx = kzalloc(sizeof(*nocow_ctx), GFP_NOFS);
-	if (!nocow_ctx) {
-		spin_lock(&sctx->stat_lock);
-		sctx->stat.malloc_errors++;
-		spin_unlock(&sctx->stat_lock);
-		return -ENOMEM;
-	}
-
-	scrub_pending_trans_workers_inc(sctx);
-
-	nocow_ctx->sctx = sctx;
-	nocow_ctx->logical = logical;
-	nocow_ctx->len = len;
-	nocow_ctx->mirror_num = mirror_num;
-	nocow_ctx->physical_for_dev_replace = physical_for_dev_replace;
-	btrfs_init_work(&nocow_ctx->work, btrfs_scrubnc_helper,
-			copy_nocow_pages_worker, NULL, NULL);
-	INIT_LIST_HEAD(&nocow_ctx->inodes);
-	btrfs_queue_work(fs_info->scrub_nocow_workers,
-			 &nocow_ctx->work);
-
-	return 0;
-}
-
-static int record_inode_for_nocow(u64 inum, u64 offset, u64 root, void *ctx)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx = ctx;
-	struct scrub_nocow_inode *nocow_inode;
-
-	nocow_inode = kzalloc(sizeof(*nocow_inode), GFP_NOFS);
-	if (!nocow_inode)
-		return -ENOMEM;
-	nocow_inode->inum = inum;
-	nocow_inode->offset = offset;
-	nocow_inode->root = root;
-	list_add_tail(&nocow_inode->list, &nocow_ctx->inodes);
-	return 0;
-}
-
-#define COPY_COMPLETE 1
-
-static void copy_nocow_pages_worker(struct btrfs_work *work)
-{
-	struct scrub_copy_nocow_ctx *nocow_ctx =
-		container_of(work, struct scrub_copy_nocow_ctx, work);
-	struct scrub_ctx *sctx = nocow_ctx->sctx;
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-	struct btrfs_root *root = fs_info->extent_root;
-	u64 logical = nocow_ctx->logical;
-	u64 len = nocow_ctx->len;
-	int mirror_num = nocow_ctx->mirror_num;
-	u64 physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
-	int ret;
-	struct btrfs_trans_handle *trans = NULL;
-	struct btrfs_path *path;
-	int not_written = 0;
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		spin_lock(&sctx->stat_lock);
-		sctx->stat.malloc_errors++;
-		spin_unlock(&sctx->stat_lock);
-		not_written = 1;
-		goto out;
-	}
-
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans)) {
-		not_written = 1;
-		goto out;
-	}
-
-	ret = iterate_inodes_from_logical(logical, fs_info, path,
-			record_inode_for_nocow, nocow_ctx, false);
-	if (ret != 0 && ret != -ENOENT) {
-		btrfs_warn(fs_info,
-			   "iterate_inodes_from_logical() failed: log %llu, phys %llu, len %llu, mir %u, ret %d",
-			   logical, physical_for_dev_replace, len, mirror_num,
-			   ret);
-		not_written = 1;
-		goto out;
-	}
-
-	btrfs_end_transaction(trans);
-	trans = NULL;
-	while (!list_empty(&nocow_ctx->inodes)) {
-		struct scrub_nocow_inode *entry;
-		entry = list_first_entry(&nocow_ctx->inodes,
-					 struct scrub_nocow_inode,
-					 list);
-		list_del_init(&entry->list);
-		ret = copy_nocow_pages_for_inode(entry->inum, entry->offset,
-						 entry->root, nocow_ctx);
-		kfree(entry);
-		if (ret == COPY_COMPLETE) {
-			ret = 0;
-			break;
-		} else if (ret) {
-			break;
-		}
-	}
-out:
-	while (!list_empty(&nocow_ctx->inodes)) {
-		struct scrub_nocow_inode *entry;
-		entry = list_first_entry(&nocow_ctx->inodes,
-					 struct scrub_nocow_inode,
-					 list);
-		list_del_init(&entry->list);
-		kfree(entry);
-	}
-	if (trans && !IS_ERR(trans))
-		btrfs_end_transaction(trans);
-	if (not_written)
-		btrfs_dev_replace_stats_inc(&fs_info->dev_replace.
-					    num_uncorrectable_read_errors);
-
-	btrfs_free_path(path);
-	kfree(nocow_ctx);
-
-	scrub_pending_trans_workers_dec(sctx);
-}
-
-static int check_extent_to_block(struct btrfs_inode *inode, u64 start, u64 len,
-				 u64 logical)
-{
-	struct extent_state *cached_state = NULL;
-	struct btrfs_ordered_extent *ordered;
-	struct extent_io_tree *io_tree;
-	struct extent_map *em;
-	u64 lockstart = start, lockend = start + len - 1;
-	int ret = 0;
-
-	io_tree = &inode->io_tree;
-
-	lock_extent_bits(io_tree, lockstart, lockend, &cached_state);
-	ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
-	if (ordered) {
-		btrfs_put_ordered_extent(ordered);
-		ret = 1;
-		goto out_unlock;
-	}
-
-	em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
-	if (IS_ERR(em)) {
-		ret = PTR_ERR(em);
-		goto out_unlock;
-	}
-
-	/*
-	 * This extent does not actually cover the logical extent anymore,
-	 * move on to the next inode.
-	 */
-	if (em->block_start > logical ||
-	    em->block_start + em->block_len < logical + len ||
-	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags)) {
-		free_extent_map(em);
-		ret = 1;
-		goto out_unlock;
-	}
-	free_extent_map(em);
-
-out_unlock:
-	unlock_extent_cached(io_tree, lockstart, lockend, &cached_state);
-	return ret;
-}
-
-static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
-				      struct scrub_copy_nocow_ctx *nocow_ctx)
-{
-	struct btrfs_fs_info *fs_info = nocow_ctx->sctx->fs_info;
-	struct btrfs_key key;
-	struct inode *inode;
-	struct page *page;
-	struct btrfs_root *local_root;
-	struct extent_io_tree *io_tree;
-	u64 physical_for_dev_replace;
-	u64 nocow_ctx_logical;
-	u64 len = nocow_ctx->len;
-	unsigned long index;
-	int srcu_index;
-	int ret = 0;
-	int err = 0;
-
-	key.objectid = root;
-	key.type = BTRFS_ROOT_ITEM_KEY;
-	key.offset = (u64)-1;
-
-	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
-
-	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root)) {
-		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-		return PTR_ERR(local_root);
-	}
-
-	key.type = BTRFS_INODE_ITEM_KEY;
-	key.objectid = inum;
-	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
-	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
-	/* Avoid truncate/dio/punch hole.. */
-	inode_lock(inode);
-	inode_dio_wait(inode);
-
-	physical_for_dev_replace = nocow_ctx->physical_for_dev_replace;
-	io_tree = &BTRFS_I(inode)->io_tree;
-	nocow_ctx_logical = nocow_ctx->logical;
-
-	ret = check_extent_to_block(BTRFS_I(inode), offset, len,
-			nocow_ctx_logical);
-	if (ret) {
-		ret = ret > 0 ? 0 : ret;
-		goto out;
-	}
-
-	while (len >= PAGE_SIZE) {
-		index = offset >> PAGE_SHIFT;
-again:
-		page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
-		if (!page) {
-			btrfs_err(fs_info, "find_or_create_page() failed");
-			ret = -ENOMEM;
-			goto out;
-		}
-
-		if (PageUptodate(page)) {
-			if (PageDirty(page))
-				goto next_page;
-		} else {
-			ClearPageError(page);
-			err = extent_read_full_page(io_tree, page,
-							   btrfs_get_extent,
-							   nocow_ctx->mirror_num);
-			if (err) {
-				ret = err;
-				goto next_page;
-			}
-
-			lock_page(page);
-			/*
-			 * If the page has been remove from the page cache,
-			 * the data on it is meaningless, because it may be
-			 * old one, the new data may be written into the new
-			 * page in the page cache.
-			 */
-			if (page->mapping != inode->i_mapping) {
-				unlock_page(page);
-				put_page(page);
-				goto again;
-			}
-			if (!PageUptodate(page)) {
-				ret = -EIO;
-				goto next_page;
-			}
-		}
-
-		ret = check_extent_to_block(BTRFS_I(inode), offset, len,
-					    nocow_ctx_logical);
-		if (ret) {
-			ret = ret > 0 ? 0 : ret;
-			goto next_page;
-		}
-
-		err = write_page_nocow(nocow_ctx->sctx,
-				       physical_for_dev_replace, page);
-		if (err)
-			ret = err;
-next_page:
-		unlock_page(page);
-		put_page(page);
-
-		if (ret)
-			break;
-
-		offset += PAGE_SIZE;
-		physical_for_dev_replace += PAGE_SIZE;
-		nocow_ctx_logical += PAGE_SIZE;
-		len -= PAGE_SIZE;
-	}
-	ret = COPY_COMPLETE;
-out:
-	inode_unlock(inode);
-	iput(inode);
-	return ret;
-}
-
-static int write_page_nocow(struct scrub_ctx *sctx,
-			    u64 physical_for_dev_replace, struct page *page)
-{
-	struct bio *bio;
-	struct btrfs_device *dev;
-
-	dev = sctx->wr_tgtdev;
-	if (!dev)
-		return -EIO;
-	if (!dev->bdev) {
-		btrfs_warn_rl(dev->fs_info,
-			"scrub write_page_nocow(bdev == NULL) is unexpected");
-		return -EIO;
-	}
-	bio = btrfs_io_bio_alloc(1);
-	bio->bi_iter.bi_size = 0;
-	bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
-	bio_set_dev(bio, dev->bdev);
-	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC;
-	/* bio_add_page won't fail on a freshly allocated bio */
-	bio_add_page(bio, page, PAGE_SIZE, 0);
-
-	if (btrfsic_submit_bio_wait(bio)) {
-		bio_put(bio);
-		btrfs_dev_stat_inc_and_print(dev, BTRFS_DEV_STAT_WRITE_ERRS);
-		return -EIO;
-	}
-
-	bio_put(bio);
-	return 0;
-}
-- 
cgit v1.2.3


From bd3c685ed9fd3763615a51a70e19ff08a456e3e1 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 18 Jun 2018 14:59:25 +0300
Subject: btrfs: Document __btrfs_inc_extent_ref

Here is a doc-only patch which tires to deobfuscate the terra-incognita
that arguments for delayed refs are.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 3d9fe58c0080..2c55f3dce27b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2207,6 +2207,40 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+/*
+ * __btrfs_inc_extent_ref - insert backreference for a given extent
+ *
+ * @trans:	    Handle of transaction
+ *
+ * @node:	    The delayed ref node used to get the bytenr/length for
+ *		    extent whose references are incremented.
+ *
+ * @parent:	    If this is a shared extent (BTRFS_SHARED_DATA_REF_KEY/
+ *		    BTRFS_SHARED_BLOCK_REF_KEY) then it holds the logical
+ *		    bytenr of the parent block. Since new extents are always
+ *		    created with indirect references, this will only be the case
+ *		    when relocating a shared extent. In that case, root_objectid
+ *		    will be BTRFS_TREE_RELOC_OBJECTID. Otheriwse, parent must
+ *		    be 0
+ *
+ * @root_objectid:  The id of the root where this modification has originated,
+ *		    this can be either one of the well-known metadata trees or
+ *		    the subvolume id which references this extent.
+ *
+ * @owner:	    For data extents it is the inode number of the owning file.
+ *		    For metadata extents this parameter holds the level in the
+ *		    tree of the extent.
+ *
+ * @offset:	    For metadata extents the offset is ignored and is currently
+ *		    always passed as 0. For data extents it is the fileoffset
+ *		    this extent belongs to.
+ *
+ * @refs_to_add     Number of references to add
+ *
+ * @extent_op       Pointer to a structure, holding information necessary when
+ *                  updating a tree block's flags
+ *
+ */
 static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_delayed_ref_node *node,
-- 
cgit v1.2.3


From 16d1c062c7de2999ea7be61d31070fa4ce3d99c4 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 18 Jun 2018 14:59:26 +0300
Subject: btrfs: Fix comment in lookup_inline_extent_backref

The comment wrongfully states that the owner parameter is the level of
the parent block. In fact owner is the level of the current block and
by adding 1 to it we can eventually get to the parent/root.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2c55f3dce27b..bdd5091433ab 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1635,8 +1635,8 @@ int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
 		extra_size = -1;
 
 	/*
-	 * Owner is our parent level, so we can just add one to get the level
-	 * for the block we are interested in.
+	 * Owner is our level, so we can just add one to get the level for the
+	 * block we are interested in.
 	 */
 	if (skinny_metadata && owner < BTRFS_FIRST_FREE_OBJECTID) {
 		key.type = BTRFS_METADATA_ITEM_KEY;
-- 
cgit v1.2.3


From b5e6c3e170b77025b5f6174258c7ad71eed2d4de Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Wed, 23 May 2018 11:58:33 -0400
Subject: btrfs: always wait on ordered extents at fsync time

There's a priority inversion that exists currently with btrfs fsync.  In
some cases we will collect outstanding ordered extents onto a list and
only wait on them at the very last second.  However this "very last
second" falls inside of a transaction handle, so if we are in a lower
priority cgroup we can end up holding the transaction open for longer
than needed, so if a high priority cgroup is also trying to fsync()
it'll see latency.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 56 ++++----------------------------------------------------
 1 file changed, 4 insertions(+), 52 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 51e77d72068a..d5be80fb427c 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2068,53 +2068,12 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	atomic_inc(&root->log_batch);
 	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
 			     &BTRFS_I(inode)->runtime_flags);
+
 	/*
-	 * We might have have had more pages made dirty after calling
-	 * start_ordered_ops and before acquiring the inode's i_mutex.
+	 * We have to do this here to avoid the priority inversion of waiting on
+	 * IO of a lower priority task while holding a transaciton open.
 	 */
-	if (full_sync) {
-		/*
-		 * For a full sync, we need to make sure any ordered operations
-		 * start and finish before we start logging the inode, so that
-		 * all extents are persisted and the respective file extent
-		 * items are in the fs/subvol btree.
-		 */
-		ret = btrfs_wait_ordered_range(inode, start, len);
-	} else {
-		/*
-		 * Start any new ordered operations before starting to log the
-		 * inode. We will wait for them to finish in btrfs_sync_log().
-		 *
-		 * Right before acquiring the inode's mutex, we might have new
-		 * writes dirtying pages, which won't immediately start the
-		 * respective ordered operations - that is done through the
-		 * fill_delalloc callbacks invoked from the writepage and
-		 * writepages address space operations. So make sure we start
-		 * all ordered operations before starting to log our inode. Not
-		 * doing this means that while logging the inode, writeback
-		 * could start and invoke writepage/writepages, which would call
-		 * the fill_delalloc callbacks (cow_file_range,
-		 * submit_compressed_extents). These callbacks add first an
-		 * extent map to the modified list of extents and then create
-		 * the respective ordered operation, which means in
-		 * tree-log.c:btrfs_log_inode() we might capture all existing
-		 * ordered operations (with btrfs_get_logged_extents()) before
-		 * the fill_delalloc callback adds its ordered operation, and by
-		 * the time we visit the modified list of extent maps (with
-		 * btrfs_log_changed_extents()), we see and process the extent
-		 * map they created. We then use the extent map to construct a
-		 * file extent item for logging without waiting for the
-		 * respective ordered operation to finish - this file extent
-		 * item points to a disk location that might not have yet been
-		 * written to, containing random data - so after a crash a log
-		 * replay will make our inode have file extent items that point
-		 * to disk locations containing invalid data, as we returned
-		 * success to userspace without waiting for the respective
-		 * ordered operation to finish, because it wasn't captured by
-		 * btrfs_get_logged_extents().
-		 */
-		ret = start_ordered_ops(inode, start, end);
-	}
+	ret = btrfs_wait_ordered_range(inode, start, len);
 	if (ret) {
 		inode_unlock(inode);
 		goto out;
@@ -2239,13 +2198,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 				goto out;
 			}
 		}
-		if (!full_sync) {
-			ret = btrfs_wait_ordered_range(inode, start, len);
-			if (ret) {
-				btrfs_end_transaction(trans);
-				goto out;
-			}
-		}
 		ret = btrfs_commit_transaction(trans);
 	} else {
 		ret = btrfs_end_transaction(trans);
-- 
cgit v1.2.3


From e7175a692765940f3ac3f0c005b9a766a59303d7 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Wed, 23 May 2018 11:58:34 -0400
Subject: btrfs: remove the wait ordered logic in the log_one_extent path

Since we are waiting on all ordered extents at the start of the fsync()
path we don't need to wait on any logged ordered extents, and we don't
need to look up the checksums on the ordered extents as they will
already be on disk prior to getting here.  Rework this so we're only
looking up and copying the on-disk checksums for the extent range we
care about.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 118 +++++-----------------------------------------------
 1 file changed, 10 insertions(+), 108 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index f8220ec02036..98cbb31ec5a8 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4078,127 +4078,30 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
 	return 0;
 }
 
-static int wait_ordered_extents(struct btrfs_trans_handle *trans,
-				struct inode *inode,
-				struct btrfs_root *root,
-				const struct extent_map *em,
-				const struct list_head *logged_list,
-				bool *ordered_io_error)
+static int log_extent_csums(struct btrfs_trans_handle *trans,
+			    struct btrfs_inode *inode,
+			    struct btrfs_root *root,
+			    const struct extent_map *em)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_ordered_extent *ordered;
 	struct btrfs_root *log = root->log_root;
-	u64 mod_start = em->mod_start;
-	u64 mod_len = em->mod_len;
-	const bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 	u64 csum_offset;
 	u64 csum_len;
 	LIST_HEAD(ordered_sums);
 	int ret = 0;
 
-	*ordered_io_error = false;
-
-	if (test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
+	if (inode->flags & BTRFS_INODE_NODATASUM ||
+	    test_bit(EXTENT_FLAG_PREALLOC, &em->flags) ||
 	    em->block_start == EXTENT_MAP_HOLE)
 		return 0;
 
-	/*
-	 * Wait far any ordered extent that covers our extent map. If it
-	 * finishes without an error, first check and see if our csums are on
-	 * our outstanding ordered extents.
-	 */
-	list_for_each_entry(ordered, logged_list, log_list) {
-		struct btrfs_ordered_sum *sum;
-
-		if (!mod_len)
-			break;
-
-		if (ordered->file_offset + ordered->len <= mod_start ||
-		    mod_start + mod_len <= ordered->file_offset)
-			continue;
-
-		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_IOERR, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
-			const u64 start = ordered->file_offset;
-			const u64 end = ordered->file_offset + ordered->len - 1;
-
-			WARN_ON(ordered->inode != inode);
-			filemap_fdatawrite_range(inode->i_mapping, start, end);
-		}
-
-		wait_event(ordered->wait,
-			   (test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) ||
-			    test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)));
-
-		if (test_bit(BTRFS_ORDERED_IOERR, &ordered->flags)) {
-			/*
-			 * Clear the AS_EIO/AS_ENOSPC flags from the inode's
-			 * i_mapping flags, so that the next fsync won't get
-			 * an outdated io error too.
-			 */
-			filemap_check_errors(inode->i_mapping);
-			*ordered_io_error = true;
-			break;
-		}
-		/*
-		 * We are going to copy all the csums on this ordered extent, so
-		 * go ahead and adjust mod_start and mod_len in case this
-		 * ordered extent has already been logged.
-		 */
-		if (ordered->file_offset > mod_start) {
-			if (ordered->file_offset + ordered->len >=
-			    mod_start + mod_len)
-				mod_len = ordered->file_offset - mod_start;
-			/*
-			 * If we have this case
-			 *
-			 * |--------- logged extent ---------|
-			 *       |----- ordered extent ----|
-			 *
-			 * Just don't mess with mod_start and mod_len, we'll
-			 * just end up logging more csums than we need and it
-			 * will be ok.
-			 */
-		} else {
-			if (ordered->file_offset + ordered->len <
-			    mod_start + mod_len) {
-				mod_len = (mod_start + mod_len) -
-					(ordered->file_offset + ordered->len);
-				mod_start = ordered->file_offset +
-					ordered->len;
-			} else {
-				mod_len = 0;
-			}
-		}
-
-		if (skip_csum)
-			continue;
-
-		/*
-		 * To keep us from looping for the above case of an ordered
-		 * extent that falls inside of the logged extent.
-		 */
-		if (test_and_set_bit(BTRFS_ORDERED_LOGGED_CSUM,
-				     &ordered->flags))
-			continue;
-
-		list_for_each_entry(sum, &ordered->list, list) {
-			ret = btrfs_csum_file_blocks(trans, log, sum);
-			if (ret)
-				break;
-		}
-	}
-
-	if (*ordered_io_error || !mod_len || ret || skip_csum)
-		return ret;
-
+	/* If we're compressed we have to save the entire range of csums. */
 	if (em->compress_type) {
 		csum_offset = 0;
 		csum_len = max(em->block_len, em->orig_block_len);
 	} else {
-		csum_offset = mod_start - em->start;
-		csum_len = mod_len;
+		csum_offset = em->mod_start - em->start;
+		csum_len = em->mod_len;
 	}
 
 	/* block start is already adjusted for the file extent offset. */
@@ -4240,8 +4143,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	int extent_inserted = 0;
 	bool ordered_io_err = false;
 
-	ret = wait_ordered_extents(trans, &inode->vfs_inode, root, em,
-			logged_list, &ordered_io_err);
+	ret = log_extent_csums(trans, inode, root, em);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From a2120a473a80905e0275df9b0427fa7fa1187b72 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Wed, 23 May 2018 11:58:35 -0400
Subject: btrfs: clean up the left over logged_list usage

We no longer use this list we've passed around so remove it everywhere.
Also remove the extra checks for ordered/filemap errors as this is
handled higher up now that we're waiting on ordered_extents before
getting to the tree log code.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 32 ++------------------------------
 1 file changed, 2 insertions(+), 30 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 98cbb31ec5a8..dce499071c86 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4129,7 +4129,6 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 			  struct btrfs_inode *inode, struct btrfs_root *root,
 			  const struct extent_map *em,
 			  struct btrfs_path *path,
-			  const struct list_head *logged_list,
 			  struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_root *log = root->log_root;
@@ -4141,17 +4140,11 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	u64 block_len;
 	int ret;
 	int extent_inserted = 0;
-	bool ordered_io_err = false;
 
 	ret = log_extent_csums(trans, inode, root, em);
 	if (ret)
 		return ret;
 
-	if (ordered_io_err) {
-		ctx->io_err = -EIO;
-		return ctx->io_err;
-	}
-
 	btrfs_init_map_token(&token);
 
 	ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start,
@@ -4326,7 +4319,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
 				     struct btrfs_inode *inode,
 				     struct btrfs_path *path,
-				     struct list_head *logged_list,
 				     struct btrfs_log_ctx *ctx,
 				     const u64 start,
 				     const u64 end)
@@ -4382,20 +4374,6 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	}
 
 	list_sort(NULL, &extents, extent_cmp);
-	btrfs_get_logged_extents(inode, logged_list, logged_start, logged_end);
-	/*
-	 * Some ordered extents started by fsync might have completed
-	 * before we could collect them into the list logged_list, which
-	 * means they're gone, not in our logged_list nor in the inode's
-	 * ordered tree. We want the application/user space to know an
-	 * error happened while attempting to persist file data so that
-	 * it can take proper action. If such error happened, we leave
-	 * without writing to the log tree and the fsync must report the
-	 * file data write error and not commit the current transaction.
-	 */
-	ret = filemap_check_errors(inode->vfs_inode.i_mapping);
-	if (ret)
-		ctx->io_err = ret;
 process:
 	while (!list_empty(&extents)) {
 		em = list_entry(extents.next, struct extent_map, list);
@@ -4414,8 +4392,7 @@ process:
 
 		write_unlock(&tree->lock);
 
-		ret = log_one_extent(trans, inode, root, em, path, logged_list,
-				     ctx);
+		ret = log_one_extent(trans, inode, root, em, path, ctx);
 		write_lock(&tree->lock);
 		clear_em_logging(tree, em);
 		free_extent_map(em);
@@ -4800,7 +4777,6 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_key min_key;
 	struct btrfs_key max_key;
 	struct btrfs_root *log = root->log_root;
-	LIST_HEAD(logged_list);
 	u64 last_extent = 0;
 	int err = 0;
 	int ret;
@@ -5137,7 +5113,7 @@ log_extents:
 	}
 	if (fast_search) {
 		ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
-						&logged_list, ctx, start, end);
+						ctx, start, end);
 		if (ret) {
 			err = ret;
 			goto out_unlock;
@@ -5188,10 +5164,6 @@ log_extents:
 	inode->last_log_commit = inode->last_sub_trans;
 	spin_unlock(&inode->lock);
 out_unlock:
-	if (unlikely(err))
-		btrfs_put_logged_extents(&logged_list);
-	else
-		btrfs_submit_logged_extents(&logged_list, log);
 	mutex_unlock(&inode->log_mutex);
 
 	btrfs_free_path(path);
-- 
cgit v1.2.3


From 5636cf7d6dc86f47fd66757dae088e35014da464 Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Wed, 23 May 2018 11:58:36 -0400
Subject: btrfs: remove the logged extents infrastructure

This is no longer used anywhere, remove all of it.

Signed-off-by: Josef Bacik <jbacik@fb.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ordered-data.c      | 123 -------------------------------------------
 fs/btrfs/ordered-data.h      |  20 ++-----
 fs/btrfs/tree-log.c          |  16 ------
 include/trace/events/btrfs.h |   1 -
 4 files changed, 3 insertions(+), 157 deletions(-)

diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 2e1a1694a33d..c35d2aed5ff8 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -421,129 +421,6 @@ out:
 	return ret == 0;
 }
 
-/* Needs to either be called under a log transaction or the log_mutex */
-void btrfs_get_logged_extents(struct btrfs_inode *inode,
-			      struct list_head *logged_list,
-			      const loff_t start,
-			      const loff_t end)
-{
-	struct btrfs_ordered_inode_tree *tree;
-	struct btrfs_ordered_extent *ordered;
-	struct rb_node *n;
-	struct rb_node *prev;
-
-	tree = &inode->ordered_tree;
-	spin_lock_irq(&tree->lock);
-	n = __tree_search(&tree->tree, end, &prev);
-	if (!n)
-		n = prev;
-	for (; n; n = rb_prev(n)) {
-		ordered = rb_entry(n, struct btrfs_ordered_extent, rb_node);
-		if (ordered->file_offset > end)
-			continue;
-		if (entry_end(ordered) <= start)
-			break;
-		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
-			continue;
-		list_add(&ordered->log_list, logged_list);
-		refcount_inc(&ordered->refs);
-	}
-	spin_unlock_irq(&tree->lock);
-}
-
-void btrfs_put_logged_extents(struct list_head *logged_list)
-{
-	struct btrfs_ordered_extent *ordered;
-
-	while (!list_empty(logged_list)) {
-		ordered = list_first_entry(logged_list,
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		btrfs_put_ordered_extent(ordered);
-	}
-}
-
-void btrfs_submit_logged_extents(struct list_head *logged_list,
-				 struct btrfs_root *log)
-{
-	int index = log->log_transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	list_splice_tail(logged_list, &log->logged_list[index]);
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
-void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *log, u64 transid)
-{
-	struct btrfs_ordered_extent *ordered;
-	int index = transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	while (!list_empty(&log->logged_list[index])) {
-		struct inode *inode;
-		ordered = list_first_entry(&log->logged_list[index],
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		inode = ordered->inode;
-		spin_unlock_irq(&log->log_extents_lock[index]);
-
-		if (!test_bit(BTRFS_ORDERED_IO_DONE, &ordered->flags) &&
-		    !test_bit(BTRFS_ORDERED_DIRECT, &ordered->flags)) {
-			u64 start = ordered->file_offset;
-			u64 end = ordered->file_offset + ordered->len - 1;
-
-			WARN_ON(!inode);
-			filemap_fdatawrite_range(inode->i_mapping, start, end);
-		}
-		wait_event(ordered->wait, test_bit(BTRFS_ORDERED_IO_DONE,
-						   &ordered->flags));
-
-		/*
-		 * In order to keep us from losing our ordered extent
-		 * information when committing the transaction we have to make
-		 * sure that any logged extents are completed when we go to
-		 * commit the transaction.  To do this we simply increase the
-		 * current transactions pending_ordered counter and decrement it
-		 * when the ordered extent completes.
-		 */
-		if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
-			struct btrfs_ordered_inode_tree *tree;
-
-			tree = &BTRFS_I(inode)->ordered_tree;
-			spin_lock_irq(&tree->lock);
-			if (!test_bit(BTRFS_ORDERED_COMPLETE, &ordered->flags)) {
-				set_bit(BTRFS_ORDERED_PENDING, &ordered->flags);
-				atomic_inc(&trans->transaction->pending_ordered);
-			}
-			spin_unlock_irq(&tree->lock);
-		}
-		btrfs_put_ordered_extent(ordered);
-		spin_lock_irq(&log->log_extents_lock[index]);
-	}
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
-void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid)
-{
-	struct btrfs_ordered_extent *ordered;
-	int index = transid % 2;
-
-	spin_lock_irq(&log->log_extents_lock[index]);
-	while (!list_empty(&log->logged_list[index])) {
-		ordered = list_first_entry(&log->logged_list[index],
-					   struct btrfs_ordered_extent,
-					   log_list);
-		list_del_init(&ordered->log_list);
-		spin_unlock_irq(&log->log_extents_lock[index]);
-		btrfs_put_ordered_extent(ordered);
-		spin_lock_irq(&log->log_extents_lock[index]);
-	}
-	spin_unlock_irq(&log->log_extents_lock[index]);
-}
-
 /*
  * used to drop a reference on an ordered extent.  This will free
  * the extent if the last reference is dropped
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 3be443fb3001..b2d3f6a091f7 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -54,15 +54,11 @@ struct btrfs_ordered_sum {
 #define BTRFS_ORDERED_UPDATED_ISIZE 7 /* indicates whether this ordered extent
 				       * has done its due diligence in updating
 				       * the isize. */
-#define BTRFS_ORDERED_LOGGED_CSUM 8 /* We've logged the csums on this ordered
-				       ordered extent */
-#define BTRFS_ORDERED_TRUNCATED 9 /* Set when we have to truncate an extent */
+#define BTRFS_ORDERED_TRUNCATED 8 /* Set when we have to truncate an extent */
 
-#define BTRFS_ORDERED_LOGGED 10 /* Set when we've waited on this ordered extent
-				 * in the logging code. */
-#define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to
+#define BTRFS_ORDERED_PENDING 9 /* We are waiting for this ordered extent to
 				  * complete in the current transaction. */
-#define BTRFS_ORDERED_REGULAR 12 /* Regular IO for COW */
+#define BTRFS_ORDERED_REGULAR 10 /* Regular IO for COW */
 
 struct btrfs_ordered_extent {
 	/* logical offset in the file */
@@ -193,16 +189,6 @@ u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len);
 u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			      const u64 range_start, const u64 range_len);
-void btrfs_get_logged_extents(struct btrfs_inode *inode,
-			      struct list_head *logged_list,
-			      const loff_t start,
-			      const loff_t end);
-void btrfs_put_logged_extents(struct list_head *logged_list);
-void btrfs_submit_logged_extents(struct list_head *logged_list,
-				 struct btrfs_root *log);
-void btrfs_wait_logged_extents(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *log, u64 transid);
-void btrfs_free_logged_extents(struct btrfs_root *log, u64 transid);
 int __init ordered_data_init(void);
 void __cold ordered_data_exit(void);
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index dce499071c86..daf32dc94dc3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2933,7 +2933,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	/* bail out if we need to do a full commit */
 	if (btrfs_need_log_full_commit(fs_info, trans)) {
 		ret = -EAGAIN;
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&root->log_mutex);
 		goto out;
 	}
@@ -2951,7 +2950,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (ret) {
 		blk_finish_plug(&plug);
 		btrfs_abort_transaction(trans, ret);
-		btrfs_free_logged_extents(log, log_transid);
 		btrfs_set_log_full_commit(fs_info, trans);
 		mutex_unlock(&root->log_mutex);
 		goto out;
@@ -3002,7 +3000,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 		btrfs_wait_tree_log_extents(log, mark);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = -EAGAIN;
 		goto out;
@@ -3020,7 +3017,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (atomic_read(&log_root_tree->log_commit[index2])) {
 		blk_finish_plug(&plug);
 		ret = btrfs_wait_tree_log_extents(log, mark);
-		btrfs_wait_logged_extents(trans, log, log_transid);
 		wait_log_commit(log_root_tree,
 				root_log_ctx.log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
@@ -3045,7 +3041,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (btrfs_need_log_full_commit(fs_info, trans)) {
 		blk_finish_plug(&plug);
 		btrfs_wait_tree_log_extents(log, mark);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = -EAGAIN;
 		goto out_wake_log_root;
@@ -3058,7 +3053,6 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	if (ret) {
 		btrfs_set_log_full_commit(fs_info, trans);
 		btrfs_abort_transaction(trans, ret);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
@@ -3068,11 +3062,9 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 						  EXTENT_NEW | EXTENT_DIRTY);
 	if (ret) {
 		btrfs_set_log_full_commit(fs_info, trans);
-		btrfs_free_logged_extents(log, log_transid);
 		mutex_unlock(&log_root_tree->log_mutex);
 		goto out_wake_log_root;
 	}
-	btrfs_wait_logged_extents(trans, log, log_transid);
 
 	btrfs_set_super_log_root(fs_info->super_for_commit,
 				 log_root_tree->node->start);
@@ -3159,14 +3151,6 @@ static void free_log_tree(struct btrfs_trans_handle *trans,
 				  EXTENT_DIRTY | EXTENT_NEW | EXTENT_NEED_WAIT);
 	}
 
-	/*
-	 * We may have short-circuited the log tree with the full commit logic
-	 * and left ordered extents on our list, so clear these out to keep us
-	 * from leaking inodes and memory.
-	 */
-	btrfs_free_logged_extents(log, 0);
-	btrfs_free_logged_extents(log, 1);
-
 	free_extent_buffer(log->node);
 	kfree(log);
 }
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 39b94ec965be..7057cc99d267 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -433,7 +433,6 @@ DEFINE_EVENT(
 		{ (1 << BTRFS_ORDERED_DIRECT),	 	"DIRECT" 	}, \
 		{ (1 << BTRFS_ORDERED_IOERR), 		"IOERR" 	}, \
 		{ (1 << BTRFS_ORDERED_UPDATED_ISIZE), 	"UPDATED_ISIZE"	}, \
-		{ (1 << BTRFS_ORDERED_LOGGED_CSUM), 	"LOGGED_CSUM"	}, \
 		{ (1 << BTRFS_ORDERED_TRUNCATED), 	"TRUNCATED"	})
 
 
-- 
cgit v1.2.3


From ca5788aba3e8153da38cf99ca3ce2294f032fb51 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Thu, 19 Jul 2018 15:27:46 +0200
Subject: btrfs: remove remaing full_sync logic from btrfs_sync_file

The logic to check if the inode is already in the log can now be
simplified since we always wait for the ordered extents to complete
before deciding whether the inode needs to be logged. The big comment
about it can go away too.

CC: Filipe Manana <fdmanana@suse.com>
Suggested-by: Filipe Manana <fdmanana@suse.com>
[ code and changelog copied from mail discussion ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c         | 37 +------------------------------------
 fs/btrfs/ordered-data.c | 14 --------------
 fs/btrfs/ordered-data.h |  3 ---
 3 files changed, 1 insertion(+), 53 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index d5be80fb427c..975c590c50d8 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -2042,7 +2042,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
 	int ret = 0, err;
-	bool full_sync = false;
 	u64 len;
 
 	/*
@@ -2066,8 +2065,6 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 
 	inode_lock(inode);
 	atomic_inc(&root->log_batch);
-	full_sync = test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			     &BTRFS_I(inode)->runtime_flags);
 
 	/*
 	 * We have to do this here to avoid the priority inversion of waiting on
@@ -2080,41 +2077,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	}
 	atomic_inc(&root->log_batch);
 
-	/*
-	 * If the last transaction that changed this file was before the current
-	 * transaction and we have the full sync flag set in our inode, we can
-	 * bail out now without any syncing.
-	 *
-	 * Note that we can't bail out if the full sync flag isn't set. This is
-	 * because when the full sync flag is set we start all ordered extents
-	 * and wait for them to fully complete - when they complete they update
-	 * the inode's last_trans field through:
-	 *
-	 *     btrfs_finish_ordered_io() ->
-	 *         btrfs_update_inode_fallback() ->
-	 *             btrfs_update_inode() ->
-	 *                 btrfs_set_inode_last_trans()
-	 *
-	 * So we are sure that last_trans is up to date and can do this check to
-	 * bail out safely. For the fast path, when the full sync flag is not
-	 * set in our inode, we can not do it because we start only our ordered
-	 * extents and don't wait for them to complete (that is when
-	 * btrfs_finish_ordered_io runs), so here at this point their last_trans
-	 * value might be less than or equals to fs_info->last_trans_committed,
-	 * and setting a speculative last_trans for an inode when a buffered
-	 * write is made (such as fs_info->generation + 1 for example) would not
-	 * be reliable since after setting the value and before fsync is called
-	 * any number of transactions can start and commit (transaction kthread
-	 * commits the current transaction periodically), and a transaction
-	 * commit does not start nor waits for ordered extents to complete.
-	 */
 	smp_mb();
 	if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
-	    (full_sync && BTRFS_I(inode)->last_trans <=
-	     fs_info->last_trans_committed) ||
-	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
-	     BTRFS_I(inode)->last_trans
-	     <= fs_info->last_trans_committed)) {
+	    BTRFS_I(inode)->last_trans <= fs_info->last_trans_committed) {
 		/*
 		 * We've had everything committed since the last time we were
 		 * modified so clear this flag in case it was set for whatever
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index c35d2aed5ff8..e173b252d795 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -790,20 +790,6 @@ out:
 	return entry;
 }
 
-bool btrfs_have_ordered_extents_in_range(struct inode *inode,
-					 u64 file_offset,
-					 u64 len)
-{
-	struct btrfs_ordered_extent *oe;
-
-	oe = btrfs_lookup_ordered_range(BTRFS_I(inode), file_offset, len);
-	if (oe) {
-		btrfs_put_ordered_extent(oe);
-		return true;
-	}
-	return false;
-}
-
 /*
  * lookup and return any extent before 'file_offset'.  NULL is returned
  * if none is found
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index b2d3f6a091f7..02d813aaa261 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -178,9 +178,6 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
 		struct btrfs_inode *inode,
 		u64 file_offset,
 		u64 len);
-bool btrfs_have_ordered_extents_in_range(struct inode *inode,
-					 u64 file_offset,
-					 u64 len);
 int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 				struct btrfs_ordered_extent *ordered);
 int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
-- 
cgit v1.2.3


From a9ecb653b0ac9ed95671aa494015bbb705bf3eae Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 17:26:42 +0300
Subject: btrfs: Streamline log_extent_csums a bit

Currently this function takes the root as an argument only to get the
log_root from it. Simplify this by directly passing the log root from
the caller. Also eliminate the fs_info local variable, since it's used
only once, so directly reference it from the transaction handle.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index daf32dc94dc3..7f6aaeb4bd22 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -4064,11 +4064,9 @@ static int extent_cmp(void *priv, struct list_head *a, struct list_head *b)
 
 static int log_extent_csums(struct btrfs_trans_handle *trans,
 			    struct btrfs_inode *inode,
-			    struct btrfs_root *root,
+			    struct btrfs_root *log_root,
 			    const struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
-	struct btrfs_root *log = root->log_root;
 	u64 csum_offset;
 	u64 csum_len;
 	LIST_HEAD(ordered_sums);
@@ -4089,7 +4087,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 	}
 
 	/* block start is already adjusted for the file extent offset. */
-	ret = btrfs_lookup_csums_range(fs_info->csum_root,
+	ret = btrfs_lookup_csums_range(trans->fs_info->csum_root,
 				       em->block_start + csum_offset,
 				       em->block_start + csum_offset +
 				       csum_len - 1, &ordered_sums, 0);
@@ -4101,7 +4099,7 @@ static int log_extent_csums(struct btrfs_trans_handle *trans,
 						   struct btrfs_ordered_sum,
 						   list);
 		if (!ret)
-			ret = btrfs_csum_file_blocks(trans, log, sums);
+			ret = btrfs_csum_file_blocks(trans, log_root, sums);
 		list_del(&sums->list);
 		kfree(sums);
 	}
@@ -4125,7 +4123,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	int ret;
 	int extent_inserted = 0;
 
-	ret = log_extent_csums(trans, inode, root, em);
+	ret = log_extent_csums(trans, inode, log, em);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From bece2e8239331d382f98b381f90e425a11157653 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Wed, 20 Jun 2018 10:03:31 -0700
Subject: btrfs: Fix misleading indentation reported by smatch

This patch avoids that building the BTRFS source code with smatch
triggers complaints about inconsistent indenting.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 4 ++--
 fs/btrfs/ioctl.c       | 4 ++--
 fs/btrfs/reada.c       | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bdd5091433ab..e0e0f3dad206 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6313,7 +6313,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		if (list_empty(&cache->dirty_list)) {
 			list_add_tail(&cache->dirty_list,
 				      &trans->transaction->dirty_bgs);
-				trans->transaction->num_dirty_bgs++;
+			trans->transaction->num_dirty_bgs++;
 			btrfs_get_block_group(cache);
 		}
 		spin_unlock(&trans->transaction->dirty_bgs_lock);
@@ -7568,7 +7568,7 @@ search:
 		 * for the proper type.
 		 */
 		if (!block_group_bits(block_group, flags)) {
-		    u64 extra = BTRFS_BLOCK_GROUP_DUP |
+			u64 extra = BTRFS_BLOCK_GROUP_DUP |
 				BTRFS_BLOCK_GROUP_RAID1 |
 				BTRFS_BLOCK_GROUP_RAID5 |
 				BTRFS_BLOCK_GROUP_RAID6 |
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index b077544b5232..0c4b9f364e84 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2507,8 +2507,8 @@ out:
 static noinline int btrfs_ioctl_ino_lookup(struct file *file,
 					   void __user *argp)
 {
-	 struct btrfs_ioctl_ino_lookup_args *args;
-	 struct inode *inode;
+	struct btrfs_ioctl_ino_lookup_args *args;
+	struct inode *inode;
 	int ret = 0;
 
 	args = memdup_user(argp, sizeof(*args));
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 40f1bcef394d..4be425f70c2d 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -355,7 +355,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 		dev = bbio->stripes[nzones].dev;
 
 		/* cannot read ahead on missing device. */
-		 if (!dev->bdev)
+		if (!dev->bdev)
 			continue;
 
 		zone = reada_find_zone(dev, logical, bbio);
-- 
cgit v1.2.3


From acd43e3cdffcb2e361e8b481c72e057d34fcd780 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Wed, 20 Jun 2018 10:03:32 -0700
Subject: btrfs: Annotate fall-through when parsing mount option

This patch avoids that the compiler complains that a fall-through
annotation is missing when building with W=1.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 81107ad49f3a..3e298f26a383 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -760,6 +760,7 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_recovery:
 			btrfs_warn(info,
 				   "'recovery' is deprecated, use 'usebackuproot' instead");
+			/* fall through */
 		case Opt_usebackuproot:
 			btrfs_info(info,
 				   "trying to use backup root at mount time");
-- 
cgit v1.2.3


From edf57cbf2b030781885e339f32e35a470d2f8eba Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Wed, 20 Jun 2018 10:03:33 -0700
Subject: btrfs: Fix a C compliance issue

The C programming language does not allow to use preprocessor statements
inside macro arguments (pr_info() is defined as a macro). Hence rework
the pr_info() statement in btrfs_print_mod_info() such that it becomes
compliant. This patch allows tools like sparse to analyze the BTRFS
source code.

Fixes: 62e855771dac ("btrfs: convert printk(KERN_* to use pr_* calls")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3e298f26a383..3c5f221b5303 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2370,7 +2370,7 @@ static __cold void btrfs_interface_exit(void)
 
 static void __init btrfs_print_mod_info(void)
 {
-	pr_info("Btrfs loaded, crc32c=%s"
+	static const char options[] = ""
 #ifdef CONFIG_BTRFS_DEBUG
 			", debug=on"
 #endif
@@ -2383,8 +2383,8 @@ static void __init btrfs_print_mod_info(void)
 #ifdef CONFIG_BTRFS_FS_REF_VERIFY
 			", ref-verify=on"
 #endif
-			"\n",
-			crc32c_impl());
+			;
+	pr_info("Btrfs loaded, crc32c=%s%s\n", crc32c_impl(), options);
 }
 
 static int __init init_btrfs_fs(void)
-- 
cgit v1.2.3


From 10728404c6f64a570f5be95cd5b237c69d94d818 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:43 +0300
Subject: btrfs: Remove fs_info from insert_tree_block_ref

This function is always called with a valid transaction so there is no
need to duplicate the fs_info, we can reference it directly from the
trans handle. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index e0e0f3dad206..082e9f1c1f1a 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1523,7 +1523,6 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 }
 
 static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
@@ -1540,7 +1539,7 @@ static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
 		key.offset = root_objectid;
 	}
 
-	ret = btrfs_insert_empty_item(trans, fs_info->extent_root,
+	ret = btrfs_insert_empty_item(trans, trans->fs_info->extent_root,
 				      path, &key, 0);
 	btrfs_release_path(path);
 	return ret;
@@ -2000,8 +1999,8 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans,
 	int ret;
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
 		BUG_ON(refs_to_add != 1);
-		ret = insert_tree_block_ref(trans, fs_info, path, bytenr,
-					    parent, root_objectid);
+		ret = insert_tree_block_ref(trans, path, bytenr, parent,
+					    root_objectid);
 	} else {
 		ret = insert_extent_data_ref(trans, fs_info, path, bytenr,
 					     parent, root_objectid,
-- 
cgit v1.2.3


From 62b895af4022017c11855087801b0575a442ccc6 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:44 +0300
Subject: btrfs: Remove fs_info from insert_extent_data_ref

This function is always called with a valid transaction handle from
where fs_info can be referenced. So remove the redundant argument.
No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 082e9f1c1f1a..bb89522c0de6 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1304,13 +1304,12 @@ fail:
 }
 
 static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid, u64 owner,
 					   u64 offset, int refs_to_add)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
 	u32 size;
@@ -2002,9 +2001,9 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans,
 		ret = insert_tree_block_ref(trans, path, bytenr, parent,
 					    root_objectid);
 	} else {
-		ret = insert_extent_data_ref(trans, fs_info, path, bytenr,
-					     parent, root_objectid,
-					     owner, offset, refs_to_add);
+		ret = insert_extent_data_ref(trans, path, bytenr, parent,
+					     root_objectid, owner, offset,
+					     refs_to_add);
 	}
 	return ret;
 }
-- 
cgit v1.2.3


From 375934105c97476f88eefe5f836808dd0cfc3eeb Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:45 +0300
Subject: btrfs: Remove fs_info argument from insert_extent_backref

This function is always called with a valid transaction handle from
where fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bb89522c0de6..9d08bd65ed44 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1990,7 +1990,6 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 }
 
 static int insert_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int refs_to_add)
@@ -2288,8 +2287,8 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* now insert the actual backref */
-	ret = insert_extent_backref(trans, fs_info, path, bytenr, parent,
-				    root_objectid, owner, offset, refs_to_add);
+	ret = insert_extent_backref(trans, path, bytenr, parent, root_objectid,
+				    owner, offset, refs_to_add);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 out:
-- 
cgit v1.2.3


From e9f6290d593a8b2f6a3cf90e4ffd446ca25faea9 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:46 +0300
Subject: btrfs: Remove fs_info from remove_extent_data_ref

This function is always called with a valid transaction from where the
fs_info can be referenced. No functional change.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9d08bd65ed44..64346986f6f0 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1383,7 +1383,6 @@ fail:
 }
 
 static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   int refs_to_drop, int *last_ref)
 {
@@ -1420,7 +1419,7 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 	num_refs -= refs_to_drop;
 
 	if (num_refs == 0) {
-		ret = btrfs_del_item(trans, fs_info->extent_root, path);
+		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
 		*last_ref = 1;
 	} else {
 		if (key.type == BTRFS_EXTENT_DATA_REF_KEY)
@@ -2020,7 +2019,7 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 		update_inline_extent_backref(fs_info, path, iref,
 					     -refs_to_drop, NULL, last_ref);
 	} else if (is_data) {
-		ret = remove_extent_data_ref(trans, fs_info, path, refs_to_drop,
+		ret = remove_extent_data_ref(trans, path, refs_to_drop,
 					     last_ref);
 	} else {
 		*last_ref = 1;
-- 
cgit v1.2.3


From b167fa9152015c91fef9489d059e9dd80d1032fd Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:47 +0300
Subject: btrfs: Remove fs_info from fixup_low_keys

This argument is unused. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.c | 18 ++++++++----------
 1 file changed, 8 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 4bc326df472e..18fd80e2f278 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -3128,8 +3128,7 @@ again:
  * higher levels
  *
  */
-static void fixup_low_keys(struct btrfs_fs_info *fs_info,
-			   struct btrfs_path *path,
+static void fixup_low_keys(struct btrfs_path *path,
 			   struct btrfs_disk_key *key, int level)
 {
 	int i;
@@ -3181,7 +3180,7 @@ void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
 	btrfs_set_item_key(eb, &disk_key, slot);
 	btrfs_mark_buffer_dirty(eb);
 	if (slot == 0)
-		fixup_low_keys(fs_info, path, &disk_key, 1);
+		fixup_low_keys(path, &disk_key, 1);
 }
 
 /*
@@ -3945,7 +3944,7 @@ static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info,
 		clean_tree_block(fs_info, right);
 
 	btrfs_item_key(right, &disk_key, 0);
-	fixup_low_keys(fs_info, path, &disk_key, 1);
+	fixup_low_keys(path, &disk_key, 1);
 
 	/* then fixup the leaf pointer in the path */
 	if (path->slots[0] < push_items) {
@@ -4320,7 +4319,7 @@ again:
 			path->nodes[0] = right;
 			path->slots[0] = 0;
 			if (path->slots[1] == 0)
-				fixup_low_keys(fs_info, path, &disk_key, 1);
+				fixup_low_keys(path, &disk_key, 1);
 		}
 		/*
 		 * We create a new leaf 'right' for the required ins_len and
@@ -4642,7 +4641,7 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info,
 		btrfs_set_disk_key_offset(&disk_key, offset + size_diff);
 		btrfs_set_item_key(leaf, &disk_key, slot);
 		if (slot == 0)
-			fixup_low_keys(fs_info, path, &disk_key, 1);
+			fixup_low_keys(path, &disk_key, 1);
 	}
 
 	item = btrfs_item_nr(slot);
@@ -4744,7 +4743,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 
 	if (path->slots[0] == 0) {
 		btrfs_cpu_key_to_disk(&disk_key, cpu_key);
-		fixup_low_keys(fs_info, path, &disk_key, 1);
+		fixup_low_keys(path, &disk_key, 1);
 	}
 	btrfs_unlock_up_safe(path, 1);
 
@@ -4886,7 +4885,6 @@ int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 		    int level, int slot)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *parent = path->nodes[level];
 	u32 nritems;
 	int ret;
@@ -4919,7 +4917,7 @@ static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
 		struct btrfs_disk_key disk_key;
 
 		btrfs_node_key(parent, &disk_key, 0);
-		fixup_low_keys(fs_info, path, &disk_key, level + 1);
+		fixup_low_keys(path, &disk_key, level + 1);
 	}
 	btrfs_mark_buffer_dirty(parent);
 }
@@ -5022,7 +5020,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			struct btrfs_disk_key disk_key;
 
 			btrfs_item_key(leaf, &disk_key, 0);
-			fixup_low_keys(fs_info, path, &disk_key, 1);
+			fixup_low_keys(path, &disk_key, 1);
 		}
 
 		/* delete the leaf if it is mostly empty */
-- 
cgit v1.2.3


From 867cc1fbebea7029ee5f95ea7e54f927ef7972b6 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:48 +0300
Subject: btrfs: Remove fs_info from lookup_inline_extent_backref

This function is always called with a valid transaction handle from
where the fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 64346986f6f0..99e6a70b8fe5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1596,13 +1596,13 @@ static int find_next_key(struct btrfs_path *path, int level,
  */
 static noinline_for_stack
 int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes,
 				 u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int insert)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
@@ -1868,9 +1868,9 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 {
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, fs_info, path, ref_ret,
-					   bytenr, num_bytes, parent,
-					   root_objectid, owner, offset, 0);
+	ret = lookup_inline_extent_backref(trans, path, ref_ret, bytenr,
+					   num_bytes, parent, root_objectid,
+					   owner, offset, 0);
 	if (ret != -ENOENT)
 		return ret;
 
@@ -1972,9 +1972,9 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 	struct btrfs_extent_inline_ref *iref;
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, fs_info, path, &iref,
-					   bytenr, num_bytes, parent,
-					   root_objectid, owner, offset, 1);
+	ret = lookup_inline_extent_backref(trans, path, &iref, bytenr,
+					   num_bytes, parent, root_objectid,
+					   owner, offset, 1);
 	if (ret == 0) {
 		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
 		update_inline_extent_backref(fs_info, path, iref,
-- 
cgit v1.2.3


From 61a18f1c66636c3226598719935eca06e81976ca Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:49 +0300
Subject: btrfs: Remove fs_info argument from update_inline_extent_backref

This function always uses the leaf's extent_buffer which already
contains a reference to the fs_info. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 99e6a70b8fe5..102911286497 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1892,14 +1892,14 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
  * helper to update/remove inline back ref
  */
 static noinline_for_stack
-void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
-				  struct btrfs_path *path,
+void update_inline_extent_backref(struct btrfs_path *path,
 				  struct btrfs_extent_inline_ref *iref,
 				  int refs_to_mod,
 				  struct btrfs_delayed_extent_op *extent_op,
 				  int *last_ref)
 {
-	struct extent_buffer *leaf;
+	struct extent_buffer *leaf = path->nodes[0];
+	struct btrfs_fs_info *fs_info = leaf->fs_info;
 	struct btrfs_extent_item *ei;
 	struct btrfs_extent_data_ref *dref = NULL;
 	struct btrfs_shared_data_ref *sref = NULL;
@@ -1910,7 +1910,6 @@ void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
 	int type;
 	u64 refs;
 
-	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	refs = btrfs_extent_refs(leaf, ei);
 	WARN_ON(refs_to_mod < 0 && refs + refs_to_mod <= 0);
@@ -1977,8 +1976,8 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 					   owner, offset, 1);
 	if (ret == 0) {
 		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
-		update_inline_extent_backref(fs_info, path, iref,
-					     refs_to_add, extent_op, NULL);
+		update_inline_extent_backref(path, iref, refs_to_add,
+					     extent_op, NULL);
 	} else if (ret == -ENOENT) {
 		setup_inline_extent_backref(fs_info, path, iref, parent,
 					    root_objectid, owner, offset,
@@ -2016,8 +2015,8 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 
 	BUG_ON(!is_data && refs_to_drop != 1);
 	if (iref) {
-		update_inline_extent_backref(fs_info, path, iref,
-					     -refs_to_drop, NULL, last_ref);
+		update_inline_extent_backref(path, iref, -refs_to_drop, NULL,
+					     last_ref);
 	} else if (is_data) {
 		ret = remove_extent_data_ref(trans, path, refs_to_drop,
 					     last_ref);
-- 
cgit v1.2.3


From b8582eeabb727f24ad0f128141558e4eb0928aec Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:50 +0300
Subject: btrfs: Remove fs_info argument from lookup_tree_block_ref

This function is always called with a valid transaction handle from
where the fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 102911286497..85e1b54bc2ea 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1487,12 +1487,11 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 }
 
 static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	int ret;
 
@@ -1878,8 +1877,8 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 	*ref_ret = NULL;
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = lookup_tree_block_ref(trans, fs_info, path, bytenr,
-					    parent, root_objectid);
+		ret = lookup_tree_block_ref(trans, path, bytenr, parent,
+					    root_objectid);
 	} else {
 		ret = lookup_extent_data_ref(trans, fs_info, path, bytenr,
 					     parent, root_objectid, owner,
-- 
cgit v1.2.3


From bd1d53ef358d584a0aa9dbd304c807fcc5e3dd5f Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:51 +0300
Subject: btrfs: Remove fs_info argument from lookup_extent_data_ref

This function is always called with a valid transaction handle from
where fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 85e1b54bc2ea..2fc879a0a2b7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1216,13 +1216,12 @@ static int match_extent_data_ref(struct extent_buffer *leaf,
 }
 
 static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid,
 					   u64 owner, u64 offset)
 {
-	struct btrfs_root *root = fs_info->extent_root;
+	struct btrfs_root *root = trans->fs_info->extent_root;
 	struct btrfs_key key;
 	struct btrfs_extent_data_ref *ref;
 	struct extent_buffer *leaf;
@@ -1880,9 +1879,8 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 		ret = lookup_tree_block_ref(trans, path, bytenr, parent,
 					    root_objectid);
 	} else {
-		ret = lookup_extent_data_ref(trans, fs_info, path, bytenr,
-					     parent, root_objectid, owner,
-					     offset);
+		ret = lookup_extent_data_ref(trans, path, bytenr, parent,
+					     root_objectid, owner, offset);
 	}
 	return ret;
 }
-- 
cgit v1.2.3


From fbe4801b26c3ca4192e679f04c0cf0dda32a6cda Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:52 +0300
Subject: btrfs: Remove fs_info from lookup_extent_backref

This argument is unused. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2fc879a0a2b7..19239ad3c6d1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1858,7 +1858,6 @@ void setup_inline_extent_backref(struct btrfs_fs_info *fs_info,
 }
 
 static int lookup_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes, u64 parent,
@@ -6878,9 +6877,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	if (is_data)
 		skinny_metadata = false;
 
-	ret = lookup_extent_backref(trans, info, path, &iref,
-				    bytenr, num_bytes, parent,
-				    root_objectid, owner_objectid,
+	ret = lookup_extent_backref(trans, path, &iref, bytenr, num_bytes,
+				    parent, root_objectid, owner_objectid,
 				    owner_offset);
 	if (ret == 0) {
 		extent_slot = path->slots[0];
-- 
cgit v1.2.3


From 44e1c47d5c3f31a9f5c883834eb9e29d0b165ea8 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:53 +0300
Subject: btrfs: Remove fs_info from btrfs_add_delayed_tree_ref

This function is always called with a valid transaction handle from
where fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-ref.c | 4 ++--
 fs/btrfs/delayed-ref.h | 3 +--
 fs/btrfs/extent-tree.c | 8 ++++----
 3 files changed, 7 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 03dec673d12a..82ac1273c65f 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -709,13 +709,13 @@ static void init_delayed_ref_common(struct btrfs_fs_info *fs_info,
  * to make sure the delayed ref is eventually processed before this
  * transaction commits.
  */
-int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root,  int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int *old_ref_mod, int *new_ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index ea1aecb6a50d..31729302c827 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -234,8 +234,7 @@ static inline void btrfs_put_delayed_ref_head(struct btrfs_delayed_ref_head *hea
 		kmem_cache_free(btrfs_delayed_ref_head_cachep, head);
 }
 
-int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root, int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 19239ad3c6d1..6b74ffc47ae4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2176,7 +2176,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			   owner, offset, BTRFS_ADD_DELAYED_REF);
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, (int)owner,
 						 BTRFS_ADD_DELAYED_REF, NULL,
@@ -7196,7 +7196,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 				   root->root_key.objectid,
 				   btrfs_header_level(buf), 0,
 				   BTRFS_DROP_DELAYED_REF);
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, buf->start,
+		ret = btrfs_add_delayed_tree_ref(trans, buf->start,
 						 buf->len, parent,
 						 root->root_key.objectid,
 						 btrfs_header_level(buf),
@@ -7275,7 +7275,7 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		old_ref_mod = new_ref_mod = 0;
 		ret = 0;
 	} else if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_tree_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, (int)owner,
 						 BTRFS_DROP_DELAYED_REF, NULL,
@@ -8491,7 +8491,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		btrfs_ref_tree_mod(root, ins.objectid, ins.offset, parent,
 				   root_objectid, level, 0,
 				   BTRFS_ADD_DELAYED_EXTENT);
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans, ins.objectid,
+		ret = btrfs_add_delayed_tree_ref(trans, ins.objectid,
 						 ins.offset, parent,
 						 root_objectid, level,
 						 BTRFS_ADD_DELAYED_EXTENT,
-- 
cgit v1.2.3


From 88a979c615d0d9da19498b3b7692e725fb2f387e Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:54 +0300
Subject: btrfs: Remove fs_info from btrfs_add_delayed_data_ref

This function is always called with a valid transaction handle from
where fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-ref.c | 4 ++--
 fs/btrfs/delayed-ref.h | 3 +--
 fs/btrfs/extent-tree.c | 7 +++----
 3 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 82ac1273c65f..6eb00eb65d76 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -791,13 +791,13 @@ free_ref:
 /*
  * add a delayed data ref. it's similar to btrfs_add_delayed_tree_ref.
  */
-int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
 			       int *old_ref_mod, int *new_ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_data_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 31729302c827..d9f2a4ebd5db 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -239,8 +239,7 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 			       u64 ref_root, int level, int action,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int *old_ref_mod, int *new_ref_mod);
-int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
-			       struct btrfs_trans_handle *trans,
+int btrfs_add_delayed_data_ref(struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6b74ffc47ae4..10586687753c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2182,7 +2182,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 						 BTRFS_ADD_DELAYED_REF, NULL,
 						 &old_ref_mod, &new_ref_mod);
 	} else {
-		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_data_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, owner, offset,
 						 0, BTRFS_ADD_DELAYED_REF,
@@ -7281,7 +7281,7 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 						 BTRFS_DROP_DELAYED_REF, NULL,
 						 &old_ref_mod, &new_ref_mod);
 	} else {
-		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
+		ret = btrfs_add_delayed_data_ref(trans, bytenr,
 						 num_bytes, parent,
 						 root_objectid, owner, offset,
 						 0, BTRFS_DROP_DELAYED_REF,
@@ -8255,7 +8255,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 
 	BUG_ON(root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID);
@@ -8264,7 +8263,7 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 			   root->root_key.objectid, owner, offset,
 			   BTRFS_ADD_DELAYED_EXTENT);
 
-	ret = btrfs_add_delayed_data_ref(fs_info, trans, ins->objectid,
+	ret = btrfs_add_delayed_data_ref(trans, ins->objectid,
 					 ins->offset, 0,
 					 root->root_key.objectid, owner,
 					 offset, ram_bytes,
-- 
cgit v1.2.3


From e7e02096d98388a003323c4223630d011ba1b382 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:55 +0300
Subject: btrfs: Remove fs_info from btrfs_make_block_group

This function is always called with a valid transaction handle from
where we can reference the fs_info. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 4 ++--
 fs/btrfs/extent-tree.c | 4 ++--
 fs/btrfs/volumes.c     | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index e671a1fcbbec..b77f9ac699c1 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2716,8 +2716,8 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info);
 int btrfs_read_block_groups(struct btrfs_fs_info *info);
 int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr);
 int btrfs_make_block_group(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info, u64 bytes_used,
-			   u64 type, u64 chunk_offset, u64 size);
+			   u64 bytes_used, u64 type, u64 chunk_offset,
+			   u64 size);
 void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
 struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 10586687753c..fa78a0175f80 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -10241,10 +10241,10 @@ next:
 	trans->can_flush_pending_bgs = can_flush_pending_bgs;
 }
 
-int btrfs_make_block_group(struct btrfs_trans_handle *trans,
-			   struct btrfs_fs_info *fs_info, u64 bytes_used,
+int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 			   u64 type, u64 chunk_offset, u64 size)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_block_group_cache *cache;
 	int ret;
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1da162928d1a..e806669dc43a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4900,7 +4900,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	refcount_inc(&em->refs);
 	write_unlock(&em_tree->lock);
 
-	ret = btrfs_make_block_group(trans, info, 0, type, start, num_bytes);
+	ret = btrfs_make_block_group(trans, 0, type, start, num_bytes);
 	if (ret)
 		goto error_del_extent;
 
@@ -5175,7 +5175,7 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 		/*
 		 * There could be two corrupted data stripes, we need
 		 * to loop retry in order to rebuild the correct data.
-		 * 
+		 *
 		 * Fail a stripe at a time on every retry except the
 		 * stripe under reconstruction.
 		 */
-- 
cgit v1.2.3


From 5a98ec0141805a0ff9adb18fd18834a906637f2f Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:56 +0300
Subject: btrfs: Remove fs_info from btrfs_remove_block_group

This function is always called with a valid transaction handle from
where we can reference fs_info. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 3 +--
 fs/btrfs/extent-tree.c | 4 ++--
 fs/btrfs/volumes.c     | 2 +-
 3 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index b77f9ac699c1..7df6739e8eca 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2723,8 +2723,7 @@ struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
 				struct btrfs_fs_info *fs_info,
 				const u64 chunk_offset);
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info, u64 group_start,
-			     struct extent_map *em);
+			     u64 group_start, struct extent_map *em);
 void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
 void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index fa78a0175f80..cb1716caf11b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -10334,9 +10334,9 @@ static void clear_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 }
 
 int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info, u64 group_start,
-			     struct extent_map *em)
+			     u64 group_start, struct extent_map *em)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_path *path;
 	struct btrfs_block_group_cache *block_group;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index e806669dc43a..ff7c8cdacd85 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2885,7 +2885,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	ret = btrfs_remove_block_group(trans, fs_info, chunk_offset, em);
+	ret = btrfs_remove_block_group(trans, chunk_offset, em);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
-- 
cgit v1.2.3


From e72cb9235d26e5b7360a38a702e644a24d8975e6 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:57 +0300
Subject: btrfs: Remove fs_info from __btrfs_free_extent

This function is always called with a valid transaction handle so we
can reference the fs_info from there. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index cb1716caf11b..67a3aa8bc283 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -52,11 +52,10 @@ enum {
 };
 
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
-				struct btrfs_delayed_ref_node *node, u64 parent,
-				u64 root_objectid, u64 owner_objectid,
-				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extra_op);
+			       struct btrfs_delayed_ref_node *node, u64 parent,
+			       u64 root_objectid, u64 owner_objectid,
+			       u64 owner_offset, int refs_to_drop,
+			       struct btrfs_delayed_extent_op *extra_op);
 static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 				    struct extent_buffer *leaf,
 				    struct btrfs_extent_item *ei);
@@ -2327,7 +2326,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 					     ref->offset, node->ref_mod,
 					     extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, fs_info, node, parent,
+		ret = __btrfs_free_extent(trans, node, parent,
 					  ref_root, ref->objectid,
 					  ref->offset, node->ref_mod,
 					  extent_op);
@@ -2480,8 +2479,7 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 					     ref->level, 0, 1,
 					     extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
-		ret = __btrfs_free_extent(trans, fs_info, node,
-					  parent, ref_root,
+		ret = __btrfs_free_extent(trans, node, parent, ref_root,
 					  ref->level, 0, 1, extent_op);
 	} else {
 		BUG();
@@ -6840,12 +6838,12 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans)
 }
 
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *info,
-				struct btrfs_delayed_ref_node *node, u64 parent,
-				u64 root_objectid, u64 owner_objectid,
-				u64 owner_offset, int refs_to_drop,
-				struct btrfs_delayed_extent_op *extent_op)
+			       struct btrfs_delayed_ref_node *node, u64 parent,
+			       u64 root_objectid, u64 owner_objectid,
+			       u64 owner_offset, int refs_to_drop,
+			       struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *info = trans->fs_info;
 	struct btrfs_key key;
 	struct btrfs_path *path;
 	struct btrfs_root *extent_root = info->extent_root;
-- 
cgit v1.2.3


From ef89b8245bc77a29f31cad2dec5be5f50d3a7c2b Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:58 +0300
Subject: btrfs: Remove fs_info from alloc_reserved_file_extent

fs_info can be referenced from the transaction handle, which is always
valid. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 67a3aa8bc283..f9f5c8f06021 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -60,7 +60,6 @@ static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 				    struct extent_buffer *leaf,
 				    struct btrfs_extent_item *ei);
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
-				      struct btrfs_fs_info *fs_info,
 				      u64 parent, u64 root_objectid,
 				      u64 flags, u64 owner, u64 offset,
 				      struct btrfs_key *ins, int ref_mod);
@@ -2316,10 +2315,10 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 	if (node->action == BTRFS_ADD_DELAYED_REF && insert_reserved) {
 		if (extent_op)
 			flags |= extent_op->flags_to_set;
-		ret = alloc_reserved_file_extent(trans, fs_info,
-						 parent, ref_root, flags,
-						 ref->objectid, ref->offset,
-						 &ins, node->ref_mod);
+		ret = alloc_reserved_file_extent(trans, parent, ref_root,
+						 flags, ref->objectid,
+						 ref->offset, &ins,
+						 node->ref_mod);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
 		ret = __btrfs_inc_extent_ref(trans, fs_info, node, parent,
 					     ref_root, ref->objectid,
@@ -8075,11 +8074,11 @@ int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
 }
 
 static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
-				      struct btrfs_fs_info *fs_info,
 				      u64 parent, u64 root_objectid,
 				      u64 flags, u64 owner, u64 offset,
 				      struct btrfs_key *ins, int ref_mod)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_extent_item *extent_item;
 	struct btrfs_extent_inline_ref *iref;
@@ -8306,8 +8305,8 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 	spin_unlock(&block_group->lock);
 	spin_unlock(&space_info->lock);
 
-	ret = alloc_reserved_file_extent(trans, fs_info, 0, root_objectid,
-					 0, owner, offset, ins, 1);
+	ret = alloc_reserved_file_extent(trans, 0, root_objectid, 0, owner,
+					 offset, ins, 1);
 	btrfs_put_block_group(block_group);
 	return ret;
 }
-- 
cgit v1.2.3


From 2590d0f155c7c133b0c05048526ccc0a8dd5e9e4 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:48:59 +0300
Subject: btrfs: Remove fs_info argument from __btrfs_inc_extent_ref

This function already takes a transaction which holds a reference to
the fs_info struct. Use that reference and remove the extra arg. No
functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f9f5c8f06021..15fd8223344c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2231,12 +2231,12 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
  *
  */
 static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_delayed_ref_node *node,
 				  u64 parent, u64 root_objectid,
 				  u64 owner, u64 offset, int refs_to_add,
 				  struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_extent_item *item;
@@ -2320,10 +2320,9 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 						 ref->offset, &ins,
 						 node->ref_mod);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, fs_info, node, parent,
-					     ref_root, ref->objectid,
-					     ref->offset, node->ref_mod,
-					     extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
+					     ref->objectid, ref->offset,
+					     node->ref_mod, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
 		ret = __btrfs_free_extent(trans, node, parent,
 					  ref_root, ref->objectid,
@@ -2473,10 +2472,8 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		BUG_ON(!extent_op || !extent_op->update_flags);
 		ret = alloc_reserved_tree_block(trans, node, extent_op);
 	} else if (node->action == BTRFS_ADD_DELAYED_REF) {
-		ret = __btrfs_inc_extent_ref(trans, fs_info, node,
-					     parent, ref_root,
-					     ref->level, 0, 1,
-					     extent_op);
+		ret = __btrfs_inc_extent_ref(trans, node, parent, ref_root,
+					     ref->level, 0, 1, extent_op);
 	} else if (node->action == BTRFS_DROP_DELAYED_REF) {
 		ret = __btrfs_free_extent(trans, node, parent, ref_root,
 					  ref->level, 0, 1, extent_op);
-- 
cgit v1.2.3


From 2bf98ef35f7fd4b5222b0d82e3abd3a27eb49a50 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:00 +0300
Subject: btrfs: Remove fs_info from run_delayed_data_ref

This function is always called with a valid transaction from where
fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 15fd8223344c..dbc936ff52a4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2289,7 +2289,6 @@ out:
 }
 
 static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_node *node,
 				struct btrfs_delayed_extent_op *extent_op,
 				int insert_reserved)
@@ -2306,7 +2305,7 @@ static int run_delayed_data_ref(struct btrfs_trans_handle *trans,
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
 
 	ref = btrfs_delayed_node_to_data_ref(node);
-	trace_run_delayed_data_ref(fs_info, node, ref, node->action);
+	trace_run_delayed_data_ref(trans->fs_info, node, ref, node->action);
 
 	if (node->type == BTRFS_SHARED_DATA_REF_KEY)
 		parent = ref->parent;
@@ -2505,7 +2504,7 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 					   insert_reserved);
 	else if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
 		 node->type == BTRFS_SHARED_DATA_REF_KEY)
-		ret = run_delayed_data_ref(trans, fs_info, node, extent_op,
+		ret = run_delayed_data_ref(trans, node, extent_op,
 					   insert_reserved);
 	else
 		BUG();
-- 
cgit v1.2.3


From 20b9a2d670fa9f06d9f682cc414f3d1cb0adf440 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:01 +0300
Subject: btrfs: Remove fs_info from run_delayed_extent_op

This function is always called with a valid transaction handle so
fs_info can be referenced from there. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index dbc936ff52a4..1c6c9ed1f7d2 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2352,10 +2352,10 @@ static void __run_delayed_extent_op(struct btrfs_delayed_extent_op *extent_op,
 }
 
 static int run_delayed_extent_op(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_delayed_ref_head *head,
 				 struct btrfs_delayed_extent_op *extent_op)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_key key;
 	struct btrfs_path *path;
 	struct btrfs_extent_item *ei;
@@ -2560,7 +2560,7 @@ static int cleanup_extent_op(struct btrfs_trans_handle *trans,
 		return 0;
 	}
 	spin_unlock(&head->lock);
-	ret = run_delayed_extent_op(trans, fs_info, head, extent_op);
+	ret = run_delayed_extent_op(trans, head, extent_op);
 	btrfs_free_delayed_extent_op(extent_op);
 	return ret ? ret : 1;
 }
-- 
cgit v1.2.3


From c4d56d4a1688e9cb926fd4abb428e5a9c1f963b9 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:02 +0300
Subject: btrfs: Remove unused fs_info from cleanup_extent_op

The argument is no longer used so remove it.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 1c6c9ed1f7d2..25a6202be4e3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2546,7 +2546,6 @@ static void unselect_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_ref
 }
 
 static int cleanup_extent_op(struct btrfs_trans_handle *trans,
-			     struct btrfs_fs_info *fs_info,
 			     struct btrfs_delayed_ref_head *head)
 {
 	struct btrfs_delayed_extent_op *extent_op = head->extent_op;
@@ -2574,7 +2573,7 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 
 	delayed_refs = &trans->transaction->delayed_refs;
 
-	ret = cleanup_extent_op(trans, fs_info, head);
+	ret = cleanup_extent_op(trans, head);
 	if (ret < 0) {
 		unselect_delayed_ref_head(delayed_refs, head);
 		btrfs_debug(fs_info, "run_delayed_extent_op returned %d", ret);
-- 
cgit v1.2.3


From f9871eddd9cb1acff770e03344a4cf12c343546f Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:03 +0300
Subject: btrfs: Remove fs_info from cleanup_ref_head

fs_info can be refenreced from the transaction handle, since it's always
valid. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 25a6202be4e3..9f630298ea11 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2565,9 +2565,10 @@ static int cleanup_extent_op(struct btrfs_trans_handle *trans,
 }
 
 static int cleanup_ref_head(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
 			    struct btrfs_delayed_ref_head *head)
 {
+
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
 
@@ -2722,7 +2723,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		 * up and move on to the next ref_head.
 		 */
 		if (!ref) {
-			ret = cleanup_ref_head(trans, fs_info, locked_ref);
+			ret = cleanup_ref_head(trans, locked_ref);
 			if (ret > 0 ) {
 				/* We dropped our lock, we need to loop. */
 				ret = 0;
-- 
cgit v1.2.3


From f97806f2eefdd762304e078fdbb2f8b994942ea6 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:04 +0300
Subject: btrfs: Remove fs_info from run_delayed_tree_ref

It can always be referneced from the passed transaction handle since
it's always valid. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9f630298ea11..c7a66dd434fc 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2443,7 +2443,6 @@ out:
 }
 
 static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_node *node,
 				struct btrfs_delayed_extent_op *extent_op,
 				int insert_reserved)
@@ -2454,14 +2453,14 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	u64 ref_root = 0;
 
 	ref = btrfs_delayed_node_to_tree_ref(node);
-	trace_run_delayed_tree_ref(fs_info, node, ref, node->action);
+	trace_run_delayed_tree_ref(trans->fs_info, node, ref, node->action);
 
 	if (node->type == BTRFS_SHARED_BLOCK_REF_KEY)
 		parent = ref->parent;
 	ref_root = ref->root;
 
 	if (node->ref_mod != 1) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 	"btree block(%llu) has %d references rather than 1: action %d ref_root %llu parent %llu",
 			  node->bytenr, node->ref_mod, node->action, ref_root,
 			  parent);
@@ -2500,7 +2499,7 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 
 	if (node->type == BTRFS_TREE_BLOCK_REF_KEY ||
 	    node->type == BTRFS_SHARED_BLOCK_REF_KEY)
-		ret = run_delayed_tree_ref(trans, fs_info, node, extent_op,
+		ret = run_delayed_tree_ref(trans, node, extent_op,
 					   insert_reserved);
 	else if (node->type == BTRFS_EXTENT_DATA_REF_KEY ||
 		 node->type == BTRFS_SHARED_DATA_REF_KEY)
-- 
cgit v1.2.3


From 01458828bb420d6a8f9aa09af2376caab71660b3 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:05 +0300
Subject: btrfs: Remove fs_info from do_chunk_alloc

This function is always called with a valid transaction handle from
where fs_info can be referenced. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c7a66dd434fc..556b93c05ee3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -66,8 +66,7 @@ static int alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 static int alloc_reserved_tree_block(struct btrfs_trans_handle *trans,
 				     struct btrfs_delayed_ref_node *node,
 				     struct btrfs_delayed_extent_op *extent_op);
-static int do_chunk_alloc(struct btrfs_trans_handle *trans,
-			  struct btrfs_fs_info *fs_info, u64 flags,
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 			  int force);
 static int find_next_key(struct btrfs_path *path, int level,
 			 struct btrfs_key *key);
@@ -4306,7 +4305,7 @@ again:
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
-			ret = do_chunk_alloc(trans, fs_info, alloc_target,
+			ret = do_chunk_alloc(trans, alloc_target,
 					     CHUNK_ALLOC_NO_FORCE);
 			btrfs_end_transaction(trans);
 			if (ret < 0) {
@@ -4590,9 +4589,10 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
  *    - return 1 if it successfully allocates a chunk,
  *    - return errors including -ENOSPC otherwise.
  */
-static int do_chunk_alloc(struct btrfs_trans_handle *trans,
-			  struct btrfs_fs_info *fs_info, u64 flags, int force)
+static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
+			  int force)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *space_info;
 	int wait_for_alloc = 0;
 	int ret = 0;
@@ -5001,7 +5001,7 @@ static void flush_space(struct btrfs_fs_info *fs_info,
 			ret = PTR_ERR(trans);
 			break;
 		}
-		ret = do_chunk_alloc(trans, fs_info,
+		ret = do_chunk_alloc(trans,
 				     btrfs_metadata_alloc_profile(fs_info),
 				     CHUNK_ALLOC_NO_FORCE);
 		btrfs_end_transaction(trans);
@@ -7842,8 +7842,7 @@ loop:
 				goto out;
 			}
 
-			ret = do_chunk_alloc(trans, fs_info, flags,
-					     CHUNK_ALLOC_FORCE);
+			ret = do_chunk_alloc(trans, flags, CHUNK_ALLOC_FORCE);
 
 			/*
 			 * If we can't allocate a new chunk we've already looped
@@ -9469,7 +9468,7 @@ again:
 	 */
 	alloc_flags = update_block_group_flags(fs_info, cache->flags);
 	if (alloc_flags != cache->flags) {
-		ret = do_chunk_alloc(trans, fs_info, alloc_flags,
+		ret = do_chunk_alloc(trans, alloc_flags,
 				     CHUNK_ALLOC_FORCE);
 		/*
 		 * ENOSPC is allowed here, we may have enough space
@@ -9486,8 +9485,7 @@ again:
 	if (!ret)
 		goto out;
 	alloc_flags = get_alloc_profile(fs_info, cache->space_info->flags);
-	ret = do_chunk_alloc(trans, fs_info, alloc_flags,
-			     CHUNK_ALLOC_FORCE);
+	ret = do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 	if (ret < 0)
 		goto out;
 	ret = inc_block_group_ro(cache, 0);
@@ -9509,7 +9507,7 @@ int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
 {
 	u64 alloc_flags = get_alloc_profile(fs_info, type);
 
-	return do_chunk_alloc(trans, fs_info, alloc_flags, CHUNK_ALLOC_FORCE);
+	return do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 }
 
 /*
-- 
cgit v1.2.3


From c216b2039aa06f9be23a9f385cb2d2f6434927d7 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:06 +0300
Subject: btrfs: Remove fs_info from btrfs_alloc_chunk

It can be referenced from trans since the function is always called
within a transaction.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 4 ++--
 fs/btrfs/volumes.c     | 7 +++----
 fs/btrfs/volumes.h     | 3 +--
 3 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 556b93c05ee3..c0928fcb3f32 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4568,7 +4568,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
 		 * the paths we visit in the chunk tree (they were already COWed
 		 * or created in the current transaction for example).
 		 */
-		ret = btrfs_alloc_chunk(trans, fs_info, flags);
+		ret = btrfs_alloc_chunk(trans, flags);
 	}
 
 	if (!ret) {
@@ -4670,7 +4670,7 @@ again:
 	 */
 	check_system_chunk(trans, fs_info, flags);
 
-	ret = btrfs_alloc_chunk(trans, fs_info, flags);
+	ret = btrfs_alloc_chunk(trans, flags);
 	trans->allocating_chunk = false;
 
 	spin_lock(&space_info->lock);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index ff7c8cdacd85..4a7423294270 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -5038,13 +5038,12 @@ out:
  * require modifying the chunk tree. This division is important for the
  * bootstrap process of adding storage to a seed btrfs.
  */
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, u64 type)
+int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
 	u64 chunk_offset;
 
-	lockdep_assert_held(&fs_info->chunk_mutex);
-	chunk_offset = find_next_chunk(fs_info);
+	lockdep_assert_held(&trans->fs_info->chunk_mutex);
+	chunk_offset = find_next_chunk(trans->fs_info);
 	return __btrfs_alloc_chunk(trans, chunk_offset, type);
 }
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 5139ec8daf4c..df2d8bdf8c9a 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -396,8 +396,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info, u64 chunk_start,
 		     u64 physical, u64 **logical, int *naddrs, int *stripe_len);
 int btrfs_read_sys_array(struct btrfs_fs_info *fs_info);
 int btrfs_read_chunk_tree(struct btrfs_fs_info *fs_info);
-int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, u64 type);
+int btrfs_alloc_chunk(struct btrfs_trans_handle *trans, u64 type);
 void btrfs_mapping_init(struct btrfs_mapping_tree *tree);
 void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree);
 blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
-- 
cgit v1.2.3


From 451a2c130342125ca44dbbf3b62521c3f0041cfb Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:07 +0300
Subject: btrfs: Remove fs_info from check_system_chunk

It can be referenced from trans since the function is always called
within a transaction.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 3 +--
 fs/btrfs/extent-tree.c | 8 ++++----
 fs/btrfs/volumes.c     | 2 +-
 3 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 7df6739e8eca..db97e34aa113 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2821,8 +2821,7 @@ int btrfs_delayed_refs_qgroup_accounting(struct btrfs_trans_handle *trans,
 int btrfs_start_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_end_write_no_snapshotting(struct btrfs_root *root);
 void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
-void check_system_chunk(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, const u64 type);
+void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		       u64 start, u64 end);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c0928fcb3f32..ca88a86b1c73 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4527,9 +4527,9 @@ static u64 get_profile_num_devs(struct btrfs_fs_info *fs_info, u64 type)
  * for allocating a chunk, otherwise if it's false, reserve space necessary for
  * removing a chunk.
  */
-void check_system_chunk(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 type)
+void check_system_chunk(struct btrfs_trans_handle *trans, u64 type)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *info;
 	u64 left;
 	u64 thresh;
@@ -4668,7 +4668,7 @@ again:
 	 * Check if we have enough space in SYSTEM chunk because we may need
 	 * to update devices.
 	 */
-	check_system_chunk(trans, fs_info, flags);
+	check_system_chunk(trans, flags);
 
 	ret = btrfs_alloc_chunk(trans, flags);
 	trans->allocating_chunk = false;
@@ -9493,7 +9493,7 @@ out:
 	if (cache->flags & BTRFS_BLOCK_GROUP_SYSTEM) {
 		alloc_flags = update_block_group_flags(fs_info, cache->flags);
 		mutex_lock(&fs_info->chunk_mutex);
-		check_system_chunk(trans, fs_info, alloc_flags);
+		check_system_chunk(trans, alloc_flags);
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
 	mutex_unlock(&fs_info->ro_block_group_mutex);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 4a7423294270..9795d5079907 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2829,7 +2829,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	}
 	map = em->map_lookup;
 	mutex_lock(&fs_info->chunk_mutex);
-	check_system_chunk(trans, fs_info, map->type);
+	check_system_chunk(trans, map->type);
 	mutex_unlock(&fs_info->chunk_mutex);
 
 	/*
-- 
cgit v1.2.3


From 9e715da86001cdbb2d802f1ac8eb5e12c6eb0d08 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:08 +0300
Subject: btrfs: Remove fs_info from free_excluded_extents

It can be referenced from the passed block group.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 22 +++++++++++-----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ca88a86b1c73..86c57b70ed28 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -217,9 +217,9 @@ static int add_excluded_extent(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-static void free_excluded_extents(struct btrfs_fs_info *fs_info,
-				  struct btrfs_block_group_cache *cache)
+static void free_excluded_extents(struct btrfs_block_group_cache *cache)
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 start, end;
 
 	start = cache->key.objectid;
@@ -555,7 +555,7 @@ static noinline void caching_thread(struct btrfs_work *work)
 	caching_ctl->progress = (u64)-1;
 
 	up_read(&fs_info->commit_root_sem);
-	free_excluded_extents(fs_info, block_group);
+	free_excluded_extents(block_group);
 	mutex_unlock(&caching_ctl->mutex);
 
 	wake_up(&caching_ctl->wait);
@@ -663,7 +663,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 		wake_up(&caching_ctl->wait);
 		if (ret == 1) {
 			put_caching_control(caching_ctl);
-			free_excluded_extents(fs_info, cache);
+			free_excluded_extents(cache);
 			return 0;
 		}
 	} else {
@@ -9860,7 +9860,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		 */
 		if (block_group->cached == BTRFS_CACHE_NO ||
 		    block_group->cached == BTRFS_CACHE_ERROR)
-			free_excluded_extents(info, block_group);
+			free_excluded_extents(block_group);
 
 		btrfs_remove_free_space_cache(block_group);
 		ASSERT(block_group->cached != BTRFS_CACHE_STARTED);
@@ -10108,7 +10108,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 			 * We may have excluded something, so call this just in
 			 * case.
 			 */
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 			btrfs_put_block_group(cache);
 			goto error;
 		}
@@ -10123,14 +10123,14 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (found_key.offset == btrfs_block_group_used(&cache->item)) {
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
 			cache->last_byte_to_unpin = (u64)-1;
 			cache->cached = BTRFS_CACHE_FINISHED;
 			add_new_free_space(cache, found_key.objectid,
 					   found_key.objectid +
 					   found_key.offset);
-			free_excluded_extents(info, cache);
+			free_excluded_extents(cache);
 		}
 
 		ret = btrfs_add_block_group_cache(info, cache);
@@ -10259,14 +10259,14 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 		 * We may have excluded something, so call this just in
 		 * case.
 		 */
-		free_excluded_extents(fs_info, cache);
+		free_excluded_extents(cache);
 		btrfs_put_block_group(cache);
 		return ret;
 	}
 
 	add_new_free_space(cache, chunk_offset, chunk_offset + size);
 
-	free_excluded_extents(fs_info, cache);
+	free_excluded_extents(cache);
 
 #ifdef CONFIG_BTRFS_DEBUG
 	if (btrfs_should_fragment_free_space(cache)) {
@@ -10350,7 +10350,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * Free the reserved super bytes from this block group before
 	 * remove it.
 	 */
-	free_excluded_extents(fs_info, block_group);
+	free_excluded_extents(block_group);
 	btrfs_free_ref_tree_range(fs_info, block_group->key.objectid,
 				  block_group->key.offset);
 
-- 
cgit v1.2.3


From 3c4da6574e7749353be6d5e9f06d17388c241469 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:09 +0300
Subject: btrfs: Remove fs_info from exclude_super_stripes

It can be referenced from the passed block group.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 86c57b70ed28..18f51478242b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -231,9 +231,9 @@ static void free_excluded_extents(struct btrfs_block_group_cache *cache)
 			  start, end, EXTENT_UPTODATE);
 }
 
-static int exclude_super_stripes(struct btrfs_fs_info *fs_info,
-				 struct btrfs_block_group_cache *cache)
+static int exclude_super_stripes(struct btrfs_block_group_cache *cache)
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	u64 bytenr;
 	u64 *logical;
 	int stripe_len;
@@ -10102,7 +10102,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		 * info has super bytes accounted for, otherwise we'll think
 		 * we have more space than we actually do.
 		 */
-		ret = exclude_super_stripes(info, cache);
+		ret = exclude_super_stripes(cache);
 		if (ret) {
 			/*
 			 * We may have excluded something, so call this just in
@@ -10253,7 +10253,7 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans, u64 bytes_used,
 	cache->last_byte_to_unpin = (u64)-1;
 	cache->cached = BTRFS_CACHE_FINISHED;
 	cache->needs_free_space = 1;
-	ret = exclude_super_stripes(fs_info, cache);
+	ret = exclude_super_stripes(cache);
 	if (ret) {
 		/*
 		 * We may have excluded something, so call this just in
-- 
cgit v1.2.3


From a639cdeba3486883be9f016c96d03bbb31063f11 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:10 +0300
Subject: btrfs: Remove fs_info from insert_inline_extent_backref

It can be referenced from the passed transaction handle, since it's
always valid.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 18f51478242b..283a3e967184 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1954,7 +1954,6 @@ void update_inline_extent_backref(struct btrfs_path *path,
 
 static noinline_for_stack
 int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 num_bytes, u64 parent,
 				 u64 root_objectid, u64 owner,
@@ -1972,7 +1971,7 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 		update_inline_extent_backref(path, iref, refs_to_add,
 					     extent_op, NULL);
 	} else if (ret == -ENOENT) {
-		setup_inline_extent_backref(fs_info, path, iref, parent,
+		setup_inline_extent_backref(trans->fs_info, path, iref, parent,
 					    root_objectid, owner, offset,
 					    refs_to_add, extent_op);
 		ret = 0;
@@ -2235,7 +2234,6 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 				  u64 owner, u64 offset, int refs_to_add,
 				  struct btrfs_delayed_extent_op *extent_op)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_extent_item *item;
@@ -2252,10 +2250,9 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
-	ret = insert_inline_extent_backref(trans, fs_info, path, bytenr,
-					   num_bytes, parent, root_objectid,
-					   owner, offset,
-					   refs_to_add, extent_op);
+	ret = insert_inline_extent_backref(trans, path, bytenr, num_bytes,
+					   parent, root_objectid, owner,
+					   offset, refs_to_add, extent_op);
 	if ((ret < 0 && ret != -EAGAIN) || !ret)
 		goto out;
 
-- 
cgit v1.2.3


From 5fac7f9ee142a3f498137669931265bc7207135d Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:11 +0300
Subject: btrfs: Remove fs_info from run_one_delayed_ref

It can be referenced from the passed transaction handle, since it's
always valid.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 283a3e967184..781e8529e9a3 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -2479,7 +2479,6 @@ static int run_delayed_tree_ref(struct btrfs_trans_handle *trans,
 
 /* helper function to actually process a single delayed ref entry */
 static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
 			       struct btrfs_delayed_ref_node *node,
 			       struct btrfs_delayed_extent_op *extent_op,
 			       int insert_reserved)
@@ -2488,7 +2487,7 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 
 	if (trans->aborted) {
 		if (insert_reserved)
-			btrfs_pin_extent(fs_info, node->bytenr,
+			btrfs_pin_extent(trans->fs_info, node->bytenr,
 					 node->num_bytes, 1);
 		return 0;
 	}
@@ -2765,7 +2764,7 @@ static noinline int __btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 		locked_ref->extent_op = NULL;
 		spin_unlock(&locked_ref->lock);
 
-		ret = run_one_delayed_ref(trans, fs_info, ref, extent_op,
+		ret = run_one_delayed_ref(trans, ref, extent_op,
 					  must_insert_reserved);
 
 		btrfs_free_delayed_extent_op(extent_op);
-- 
cgit v1.2.3


From 87cc7a8a2afbe806bb18ef440277c4f2e58224fa Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:12 +0300
Subject: btrfs: Remove fs_info from remove_extent_backref

It can be referenced directly from the transaction handle since it's
always valid.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 781e8529e9a3..004c4e0fce36 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1998,7 +1998,6 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans,
 }
 
 static int remove_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref *iref,
 				 int refs_to_drop, int is_data, int *last_ref)
@@ -2014,7 +2013,7 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 					     last_ref);
 	} else {
 		*last_ref = 1;
-		ret = btrfs_del_item(trans, fs_info->extent_root, path);
+		ret = btrfs_del_item(trans, trans->fs_info->extent_root, path);
 	}
 	return ret;
 }
@@ -6896,7 +6895,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 #endif
 		if (!found_extent) {
 			BUG_ON(iref);
-			ret = remove_extent_backref(trans, info, path, NULL,
+			ret = remove_extent_backref(trans, path, NULL,
 						    refs_to_drop,
 						    is_data, &last_ref);
 			if (ret) {
@@ -7040,9 +7039,9 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			btrfs_mark_buffer_dirty(leaf);
 		}
 		if (found_extent) {
-			ret = remove_extent_backref(trans, info, path,
-						    iref, refs_to_drop,
-						    is_data, &last_ref);
+			ret = remove_extent_backref(trans, path, iref,
+						    refs_to_drop, is_data,
+						    &last_ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, ret);
 				goto out;
-- 
cgit v1.2.3


From 61da2abfcad9c7e1a9c2f74ae7af8637d9fba36e Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:13 +0300
Subject: btrfs: Remove fs_info from btrfs_alloc_logged_file_extent

It can be referenced from trans since the function is always called
within a valid transaction.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 1 -
 fs/btrfs/extent-tree.c | 2 +-
 fs/btrfs/tree-log.c    | 1 -
 3 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index db97e34aa113..bc4bb275e339 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2676,7 +2676,6 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 				     u64 offset, u64 ram_bytes,
 				     struct btrfs_key *ins);
 int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   u64 root_objectid, u64 owner, u64 offset,
 				   struct btrfs_key *ins);
 int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes, u64 num_bytes,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 004c4e0fce36..c27215dc8b84 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -8263,10 +8263,10 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
  * space cache bits as well
  */
 int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   u64 root_objectid, u64 owner, u64 offset,
 				   struct btrfs_key *ins)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_block_group_cache *block_group;
 	struct btrfs_space_info *space_info;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7f6aaeb4bd22..b3b1d424f2d8 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -715,7 +715,6 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 				 * allocation tree
 				 */
 				ret = btrfs_alloc_logged_file_extent(trans,
-						fs_info,
 						root->root_key.objectid,
 						key->objectid, offset, &ins);
 				if (ret)
-- 
cgit v1.2.3


From c83488afc5a772e424d8f159236bcf805b3c249c Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:14 +0300
Subject: btrfs: Remove fs_info from btrfs_inc_block_group_ro

It can be referenced from the passed bg cache.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 3 +--
 fs/btrfs/extent-tree.c | 4 ++--
 fs/btrfs/relocation.c  | 2 +-
 fs/btrfs/scrub.c       | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index bc4bb275e339..5bb083de8f2c 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2801,8 +2801,7 @@ int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
 void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_rsv *block_rsv,
 			     u64 num_bytes);
-int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_group_cache *cache);
+int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
 u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c27215dc8b84..5e15b0c319f5 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9426,10 +9426,10 @@ out:
 	return ret;
 }
 
-int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
-			     struct btrfs_block_group_cache *cache)
+int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache)
 
 {
+	struct btrfs_fs_info *fs_info = cache->fs_info;
 	struct btrfs_trans_handle *trans;
 	u64 alloc_flags;
 	int ret;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 879b76fa881a..ef1b5aad035e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4375,7 +4375,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	rc->block_group = btrfs_lookup_block_group(fs_info, group_start);
 	BUG_ON(!rc->block_group);
 
-	ret = btrfs_inc_block_group_ro(fs_info, rc->block_group);
+	ret = btrfs_inc_block_group_ro(rc->block_group);
 	if (ret) {
 		err = ret;
 		goto out;
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 5bce2330ec64..67bb003323e7 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3832,7 +3832,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * -> btrfs_scrub_pause()
 		 */
 		scrub_pause_on(fs_info);
-		ret = btrfs_inc_block_group_ro(fs_info, cache);
+		ret = btrfs_inc_block_group_ro(cache);
 		if (!ret && is_dev_replace) {
 			/*
 			 * If we are doing a device replace wait for any tasks
-- 
cgit v1.2.3


From 43a7e99db6788110fb2bd97bdad5aa5c0c004aff Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 15:49:15 +0300
Subject: btrfs: Remove fs_info from btrfs_force_chunk_alloc

It can be referenced from the passed transaction handle.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 3 +--
 fs/btrfs/extent-tree.c | 5 ++---
 fs/btrfs/relocation.c  | 3 +--
 fs/btrfs/volumes.c     | 2 +-
 4 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5bb083de8f2c..12cb327cd16e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2809,8 +2809,7 @@ int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
 				   u64 start, u64 end);
 int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
 			 u64 num_bytes, u64 *actual_bytes);
-int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 type);
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
 int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
 
 int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 5e15b0c319f5..472872a6cc27 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9497,10 +9497,9 @@ out:
 	return ret;
 }
 
-int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 type)
+int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type)
 {
-	u64 alloc_flags = get_alloc_profile(fs_info, type);
+	u64 alloc_flags = get_alloc_profile(trans->fs_info, type);
 
 	return do_chunk_alloc(trans, alloc_flags, CHUNK_ALLOC_FORCE);
 }
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ef1b5aad035e..22214033a4a2 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -4169,8 +4169,7 @@ restart:
 		}
 	}
 	if (trans && progress && err == -ENOSPC) {
-		ret = btrfs_force_chunk_alloc(trans, fs_info,
-					      rc->block_group->flags);
+		ret = btrfs_force_chunk_alloc(trans, rc->block_group->flags);
 		if (ret == 1) {
 			err = 0;
 			progress = 0;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9795d5079907..fe497937933f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -3059,7 +3059,7 @@ static int btrfs_may_alloc_data_chunk(struct btrfs_fs_info *fs_info,
 			if (IS_ERR(trans))
 				return PTR_ERR(trans);
 
-			ret = btrfs_force_chunk_alloc(trans, fs_info,
+			ret = btrfs_force_chunk_alloc(trans,
 						      BTRFS_BLOCK_GROUP_DATA);
 			btrfs_end_transaction(trans);
 			if (ret < 0)
-- 
cgit v1.2.3


From 9912bbf6440ba0555e91d3306520da01872c7c1d Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 20 Jun 2018 15:38:58 +0800
Subject: btrfs: check-integrity: Fix NULL pointer dereference for degraded
 mount

Commit f8f84b2dfda5 ("btrfs: index check-integrity state hash by a dev_t")
changed how btrfsic indexes device state.

Now we need to access device->bdev->bd_dev, while for degraded mount
it's completely possible to have device->bdev as NULL, thus it will
trigger a NULL pointer dereference at mount time.

Fix it by checking if the device is degraded before accessing
device->bdev->bd_dev.

There are a lot of other places accessing device->bdev->bd_dev, however
the other call sites have either checked device->bdev, or the
device->bdev is passed from btrfsic_map_block(), so it won't cause harm.

Fixes: f8f84b2dfda5 ("btrfs: index check-integrity state hash by a dev_t")
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/check-integrity.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index a3fdb4fe967d..daf45472bef9 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1539,7 +1539,12 @@ static int btrfsic_map_block(struct btrfsic_state *state, u64 bytenr, u32 len,
 	}
 
 	device = multi->stripes[0].dev;
-	block_ctx_out->dev = btrfsic_dev_state_lookup(device->bdev->bd_dev);
+	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state) ||
+	    !device->bdev || !device->name)
+		block_ctx_out->dev = NULL;
+	else
+		block_ctx_out->dev = btrfsic_dev_state_lookup(
+							device->bdev->bd_dev);
 	block_ctx_out->dev_bytenr = multi->stripes[0].physical;
 	block_ctx_out->start = bytenr;
 	block_ctx_out->len = len;
-- 
cgit v1.2.3


From bc877d285ca3dba24c52406946a4a69847cc7422 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Mon, 18 Jun 2018 14:13:19 +0300
Subject: btrfs: Deduplicate extent_buffer init code

When a new extent buffer is allocated there are a few mandatory fields
which need to be set in order for the buffer to be sane: level,
generation, bytenr, backref_rev, owner and FSID/UUID. Currently this
is open coded in the callers of btrfs_alloc_tree_block, meaning it's
fairly high in the abstraction hierarchy of operations. This patch
solves this by simply moving this init code in btrfs_init_new_buffer,
since this is the function which initializes a newly allocated
extent buffer. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.c       | 29 +----------------------------
 fs/btrfs/disk-io.c     | 14 --------------
 fs/btrfs/extent-tree.c | 16 ++++++++++++----
 fs/btrfs/ioctl.c       |  8 --------
 4 files changed, 13 insertions(+), 54 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 18fd80e2f278..18f1ca1c5bd9 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -3358,17 +3358,7 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
 
 	root_add_used(root, fs_info->nodesize);
 
-	memzero_extent_buffer(c, 0, sizeof(struct btrfs_header));
 	btrfs_set_header_nritems(c, 1);
-	btrfs_set_header_level(c, level);
-	btrfs_set_header_bytenr(c, c->start);
-	btrfs_set_header_generation(c, trans->transid);
-	btrfs_set_header_backref_rev(c, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(c, root->root_key.objectid);
-
-	write_extent_buffer_fsid(c, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(c, fs_info->chunk_tree_uuid);
-
 	btrfs_set_node_key(c, &lower_key, 0);
 	btrfs_set_node_blockptr(c, 0, lower->start);
 	lower_gen = btrfs_header_generation(lower);
@@ -3497,15 +3487,7 @@ static noinline int split_node(struct btrfs_trans_handle *trans,
 		return PTR_ERR(split);
 
 	root_add_used(root, fs_info->nodesize);
-
-	memzero_extent_buffer(split, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_level(split, btrfs_header_level(c));
-	btrfs_set_header_bytenr(split, split->start);
-	btrfs_set_header_generation(split, trans->transid);
-	btrfs_set_header_backref_rev(split, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(split, root->root_key.objectid);
-	write_extent_buffer_fsid(split, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(split, fs_info->chunk_tree_uuid);
+	ASSERT(btrfs_header_level(c) == level);
 
 	ret = tree_mod_log_eb_copy(fs_info, split, c, 0, mid, c_nritems - mid);
 	if (ret) {
@@ -4291,15 +4273,6 @@ again:
 
 	root_add_used(root, fs_info->nodesize);
 
-	memzero_extent_buffer(right, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(right, right->start);
-	btrfs_set_header_generation(right, trans->transid);
-	btrfs_set_header_backref_rev(right, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(right, root->root_key.objectid);
-	btrfs_set_header_level(right, 0);
-	write_extent_buffer_fsid(right, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(right, fs_info->chunk_tree_uuid);
-
 	if (split == 0) {
 		if (mid <= slot) {
 			btrfs_set_header_nritems(right, 0);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index f3224e23d5fa..6318ac2539d3 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1292,15 +1292,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, objectid);
 	root->node = leaf;
-
-	write_extent_buffer_fsid(leaf, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	root->commit_root = btrfs_root_node(root);
@@ -1374,14 +1366,8 @@ static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
 		return ERR_CAST(leaf);
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, BTRFS_TREE_LOG_OBJECTID);
 	root->node = leaf;
 
-	write_extent_buffer_fsid(root->node, fs_info->fsid);
 	btrfs_mark_buffer_dirty(root->node);
 	btrfs_tree_unlock(root->node);
 	return root;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 472872a6cc27..0ca3999356c7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -8302,7 +8302,7 @@ int btrfs_alloc_logged_file_extent(struct btrfs_trans_handle *trans,
 
 static struct extent_buffer *
 btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		      u64 bytenr, int level)
+		      u64 bytenr, int level, u64 owner)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *buf;
@@ -8311,7 +8311,6 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	if (IS_ERR(buf))
 		return buf;
 
-	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
 	clean_tree_block(fs_info, buf);
@@ -8320,6 +8319,14 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_lock_blocking(buf);
 	set_extent_buffer_uptodate(buf);
 
+	memzero_extent_buffer(buf, 0, sizeof(struct btrfs_header));
+	btrfs_set_header_level(buf, level);
+	btrfs_set_header_bytenr(buf, buf->start);
+	btrfs_set_header_generation(buf, trans->transid);
+	btrfs_set_header_backref_rev(buf, BTRFS_MIXED_BACKREF_REV);
+	btrfs_set_header_owner(buf, owner);
+	write_extent_buffer_fsid(buf, fs_info->fsid);
+	write_extent_buffer_chunk_tree_uuid(buf, fs_info->chunk_tree_uuid);
 	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID) {
 		buf->log_index = root->log_transid % 2;
 		/*
@@ -8428,7 +8435,7 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	if (btrfs_is_testing(fs_info)) {
 		buf = btrfs_init_new_buffer(trans, root, root->alloc_bytenr,
-					    level);
+					    level, root_objectid);
 		if (!IS_ERR(buf))
 			root->alloc_bytenr += blocksize;
 		return buf;
@@ -8444,7 +8451,8 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out_unuse;
 
-	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level);
+	buf = btrfs_init_new_buffer(trans, root, ins.objectid, level,
+				    root_objectid);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
 		goto out_free_reserved;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 0c4b9f364e84..08b8c0b346b3 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -616,14 +616,6 @@ static noinline int create_subvol(struct inode *dir,
 		goto fail;
 	}
 
-	memzero_extent_buffer(leaf, 0, sizeof(struct btrfs_header));
-	btrfs_set_header_bytenr(leaf, leaf->start);
-	btrfs_set_header_generation(leaf, trans->transid);
-	btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
-	btrfs_set_header_owner(leaf, objectid);
-
-	write_extent_buffer_fsid(leaf, fs_info->fsid);
-	write_extent_buffer_chunk_tree_uuid(leaf, fs_info->chunk_tree_uuid);
 	btrfs_mark_buffer_dirty(leaf);
 
 	inode_item = &root_item->inode;
-- 
cgit v1.2.3


From e41ca5897489b1c18af75ff0cc8f5c80260b3281 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 6 Jun 2018 15:41:49 +0800
Subject: btrfs: Get rid of the confusing btrfs_file_extent_inline_len

We used to call btrfs_file_extent_inline_len() to get the uncompressed
data size of an inlined extent.

However this function is hiding evil, for compressed extent, it has no
choice but to directly read out ram_bytes from btrfs_file_extent_item.
While for uncompressed extent, it uses item size to calculate the real
data size, and ignoring ram_bytes completely.

In fact, for corrupted ram_bytes, due to above behavior kernel
btrfs_print_leaf() can't even print correct ram_bytes to expose the bug.

Since we have the tree-checker to verify all EXTENT_DATA, such mismatch
can be detected pretty easily, thus we can trust ram_bytes without the
evil btrfs_file_extent_inline_len().

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h             | 26 --------------------------
 fs/btrfs/file-item.c         |  2 +-
 fs/btrfs/file.c              |  3 +--
 fs/btrfs/inode.c             | 12 ++++++------
 fs/btrfs/print-tree.c        |  4 ++--
 fs/btrfs/send.c              | 17 +++++++----------
 fs/btrfs/tree-log.c          | 12 ++++--------
 include/trace/events/btrfs.h |  2 +-
 8 files changed, 22 insertions(+), 56 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 12cb327cd16e..41ba770b9db9 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2428,32 +2428,6 @@ static inline u32 btrfs_file_extent_inline_item_len(
 	return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
 }
 
-/* this returns the number of file bytes represented by the inline item.
- * If an item is compressed, this is the uncompressed size
- */
-static inline u32 btrfs_file_extent_inline_len(const struct extent_buffer *eb,
-					int slot,
-					const struct btrfs_file_extent_item *fi)
-{
-	struct btrfs_map_token token;
-
-	btrfs_init_map_token(&token);
-	/*
-	 * return the space used on disk if this item isn't
-	 * compressed or encoded
-	 */
-	if (btrfs_token_file_extent_compression(eb, fi, &token) == 0 &&
-	    btrfs_token_file_extent_encryption(eb, fi, &token) == 0 &&
-	    btrfs_token_file_extent_other_encoding(eb, fi, &token) == 0) {
-		return btrfs_file_extent_inline_item_len(eb,
-							 btrfs_item_nr(slot));
-	}
-
-	/* otherwise use the ram bytes field */
-	return btrfs_token_file_extent_ram_bytes(eb, fi, &token);
-}
-
-
 /* btrfs_dev_stats_item */
 static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb,
 					const struct btrfs_dev_stats_item *ptr,
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index f9dd6d1836a3..8c3cd7072caf 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -942,7 +942,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 			btrfs_file_extent_num_bytes(leaf, fi);
 	} else if (type == BTRFS_FILE_EXTENT_INLINE) {
 		size_t size;
-		size = btrfs_file_extent_inline_len(leaf, slot, fi);
+		size = btrfs_file_extent_ram_bytes(leaf, fi);
 		extent_end = ALIGN(extent_start + size,
 				   fs_info->sectorsize);
 	}
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 975c590c50d8..4cd8af14f915 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -833,8 +833,7 @@ next_slot:
 				btrfs_file_extent_num_bytes(leaf, fi);
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = key.offset +
-				btrfs_file_extent_inline_len(leaf,
-						     path->slots[0], fi);
+				btrfs_file_extent_ram_bytes(leaf, fi);
 		} else {
 			/* can't happen */
 			BUG();
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index eba61bcb9bb3..1ade43c02b81 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1443,8 +1443,7 @@ next_slot:
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
-				btrfs_file_extent_inline_len(leaf,
-						     path->slots[0], fi);
+				btrfs_file_extent_ram_bytes(leaf, fi);
 			extent_end = ALIGN(extent_end,
 					   fs_info->sectorsize);
 		} else {
@@ -4643,8 +4642,8 @@ search_again:
 					BTRFS_I(inode), leaf, fi,
 					found_key.offset);
 			} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
-				item_end += btrfs_file_extent_inline_len(leaf,
-							 path->slots[0], fi);
+				item_end += btrfs_file_extent_ram_bytes(leaf,
+									fi);
 
 				trace_btrfs_truncate_show_fi_inline(
 					BTRFS_I(inode), leaf, fi, path->slots[0],
@@ -6943,7 +6942,8 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 						       extent_start);
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		size_t size;
-		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
+
+		size = btrfs_file_extent_ram_bytes(leaf, item);
 		extent_end = ALIGN(extent_start + size,
 				   fs_info->sectorsize);
 
@@ -6994,7 +6994,7 @@ next:
 		if (new_inline)
 			goto out;
 
-		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
+		size = btrfs_file_extent_ram_bytes(leaf, item);
 		extent_offset = page_offset(page) + pg_offset - extent_start;
 		copy_size = min_t(u64, PAGE_SIZE - pg_offset,
 				  size - extent_offset);
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index a4e11cf04671..59efcf2e0de8 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -267,8 +267,8 @@ void btrfs_print_leaf(struct extent_buffer *l)
 					    struct btrfs_file_extent_item);
 			if (btrfs_file_extent_type(l, fi) ==
 			    BTRFS_FILE_EXTENT_INLINE) {
-				pr_info("\t\tinline extent data size %u\n",
-				       btrfs_file_extent_inline_len(l, i, fi));
+				pr_info("\t\tinline extent data size %llu\n",
+				       btrfs_file_extent_ram_bytes(l, fi));
 				break;
 			}
 			pr_info("\t\textent data disk bytenr %llu nr %llu\n",
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index c47f62b19226..6ff7a1315e52 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1500,7 +1500,7 @@ static int read_symlink(struct btrfs_root *root,
 	BUG_ON(compression);
 
 	off = btrfs_file_extent_inline_start(ei);
-	len = btrfs_file_extent_inline_len(path->nodes[0], path->slots[0], ei);
+	len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
 
 	ret = fs_path_add_from_extent_buffer(dest, path->nodes[0], off, len);
 
@@ -5160,7 +5160,7 @@ static int clone_range(struct send_ctx *sctx,
 		ei = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 		type = btrfs_file_extent_type(leaf, ei);
 		if (type == BTRFS_FILE_EXTENT_INLINE) {
-			ext_len = btrfs_file_extent_inline_len(leaf, slot, ei);
+			ext_len = btrfs_file_extent_ram_bytes(leaf, ei);
 			ext_len = PAGE_ALIGN(ext_len);
 		} else {
 			ext_len = btrfs_file_extent_num_bytes(leaf, ei);
@@ -5236,8 +5236,7 @@ static int send_write_or_clone(struct send_ctx *sctx,
 			struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], ei);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		len = btrfs_file_extent_inline_len(path->nodes[0],
-						   path->slots[0], ei);
+		len = btrfs_file_extent_ram_bytes(path->nodes[0], ei);
 		/*
 		 * it is possible the inline item won't cover the whole page,
 		 * but there may be items after this page.  Make
@@ -5375,7 +5374,7 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 		}
 
 		if (right_type == BTRFS_FILE_EXTENT_INLINE) {
-			right_len = btrfs_file_extent_inline_len(eb, slot, ei);
+			right_len = btrfs_file_extent_ram_bytes(eb, ei);
 			right_len = PAGE_ALIGN(right_len);
 		} else {
 			right_len = btrfs_file_extent_num_bytes(eb, ei);
@@ -5496,8 +5495,7 @@ static int get_last_extent(struct send_ctx *sctx, u64 offset)
 			    struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], fi);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_inline_len(path->nodes[0],
-							path->slots[0], fi);
+		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
 		extent_end = ALIGN(key.offset + size,
 				   sctx->send_root->fs_info->sectorsize);
 	} else {
@@ -5560,7 +5558,7 @@ static int range_is_hole_in_parent(struct send_ctx *sctx,
 		fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(leaf, fi) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			u64 size = btrfs_file_extent_inline_len(leaf, slot, fi);
+			u64 size = btrfs_file_extent_ram_bytes(leaf, fi);
 
 			extent_end = ALIGN(key.offset + size,
 					   root->fs_info->sectorsize);
@@ -5606,8 +5604,7 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			    struct btrfs_file_extent_item);
 	type = btrfs_file_extent_type(path->nodes[0], fi);
 	if (type == BTRFS_FILE_EXTENT_INLINE) {
-		u64 size = btrfs_file_extent_inline_len(path->nodes[0],
-							path->slots[0], fi);
+		u64 size = btrfs_file_extent_ram_bytes(path->nodes[0], fi);
 		extent_end = ALIGN(key->offset + size,
 				   sctx->send_root->fs_info->sectorsize);
 	} else {
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index b3b1d424f2d8..6bca8f88ade0 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -597,7 +597,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
 			nbytes = 0;
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
-		size = btrfs_file_extent_inline_len(eb, slot, item);
+		size = btrfs_file_extent_ram_bytes(eb, item);
 		nbytes = btrfs_file_extent_ram_bytes(eb, item);
 		extent_end = ALIGN(start + size,
 				   fs_info->sectorsize);
@@ -3920,9 +3920,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 					struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(src, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(src,
-							   src_path->slots[0],
-							   extent);
+			len = btrfs_file_extent_ram_bytes(src, extent);
 			*last_extent = ALIGN(key.offset + len,
 					     fs_info->sectorsize);
 		} else {
@@ -3987,7 +3985,7 @@ fill_holes:
 		extent = btrfs_item_ptr(src, i, struct btrfs_file_extent_item);
 		if (btrfs_file_extent_type(src, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(src, i, extent);
+			len = btrfs_file_extent_ram_bytes(src, extent);
 			extent_end = ALIGN(key.offset + len,
 					   fs_info->sectorsize);
 		} else {
@@ -4572,9 +4570,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 
 		if (btrfs_file_extent_type(leaf, extent) ==
 		    BTRFS_FILE_EXTENT_INLINE) {
-			len = btrfs_file_extent_inline_len(leaf,
-							   path->slots[0],
-							   extent);
+			len = btrfs_file_extent_ram_bytes(leaf, extent);
 			ASSERT(len == i_size ||
 			       (len == fs_info->sectorsize &&
 				btrfs_file_extent_compression(leaf, extent) !=
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 7057cc99d267..b401c4e36394 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -374,7 +374,7 @@ DECLARE_EVENT_CLASS(
 		__entry->extent_type	= btrfs_file_extent_type(l, fi);
 		__entry->compression	= btrfs_file_extent_compression(l, fi);
 		__entry->extent_start	= start;
-		__entry->extent_end	= (start + btrfs_file_extent_inline_len(l, slot, fi));
+		__entry->extent_end	= (start + btrfs_file_extent_ram_bytes(l, fi));
 	),
 
 	TP_printk_btrfs(
-- 
cgit v1.2.3


From afd48513f0019a2048afed0d98904d3fec7e05dd Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 21 Jun 2018 18:04:05 +0200
Subject: btrfs: use monotonic time for transaction handling

The transaction times were changed to ktime_get_real_seconds to avoid
the y2038 overflow, but they still have a minor problem when they go
backwards or jump due to settimeofday() or leap seconds.

This changes the transaction handling to instead use ktime_get_seconds(),
which returns a CLOCK_MONOTONIC timestamp that has neither of those
problems.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c     | 2 +-
 fs/btrfs/transaction.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6318ac2539d3..2de3da7b7bdc 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1805,7 +1805,7 @@ static int transaction_kthread(void *arg)
 			goto sleep;
 		}
 
-		now = ktime_get_real_seconds();
+		now = ktime_get_seconds();
 		if (cur->state < TRANS_STATE_BLOCKED &&
 		    !test_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags) &&
 		    (now < cur->start_time ||
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 56c8bab0b816..ebe50dfb8947 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -241,7 +241,7 @@ loop:
 	refcount_set(&cur_trans->use_count, 2);
 	atomic_set(&cur_trans->pending_ordered, 0);
 	cur_trans->flags = 0;
-	cur_trans->start_time = ktime_get_real_seconds();
+	cur_trans->start_time = ktime_get_seconds();
 
 	memset(&cur_trans->delayed_refs, 0, sizeof(cur_trans->delayed_refs));
 
-- 
cgit v1.2.3


From d3c6be6fdab48dd26af3d3e01c5972ffe20985b9 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 21 Jun 2018 18:04:06 +0200
Subject: btrfs: use timespec64 for i_otime

While the regular inode timestamps all use timespec64 now, the i_otime
field is btrfs specific and still needs to be converted to correctly
represent times beyond 2038.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/btrfs_inode.h | 2 +-
 fs/btrfs/inode.c       | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 7e075343daa5..1343ac57b438 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -178,7 +178,7 @@ struct btrfs_inode {
 	struct btrfs_delayed_node *delayed_node;
 
 	/* File creation time. */
-	struct timespec i_otime;
+	struct timespec64 i_otime;
 
 	/* Hook into fs_info->delayed_iputs */
 	struct list_head delayed_iput;
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1ade43c02b81..2858bc355920 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5744,7 +5744,7 @@ static struct inode *new_simple_dir(struct super_block *s,
 	inode->i_mtime = current_time(inode);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
-	BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	return inode;
 }
@@ -6348,7 +6348,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	inode->i_mtime = current_time(inode);
 	inode->i_atime = inode->i_mtime;
 	inode->i_ctime = inode->i_mtime;
-	BTRFS_I(inode)->i_otime = timespec64_to_timespec(inode->i_mtime);
+	BTRFS_I(inode)->i_otime = inode->i_mtime;
 
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				  struct btrfs_inode_item);
-- 
cgit v1.2.3


From bc931c0ef8f9e21ed5732ea148aeea9d0fffd3f8 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Fri, 22 Jun 2018 09:18:29 +0200
Subject: btrfs: Refactor count handling in btrfs_unpin_free_ino
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With gcc 4.1.2:

    fs/btrfs/inode-map.c: In function ‘btrfs_unpin_free_ino’:
    fs/btrfs/inode-map.c:241: warning: ‘count’ may be used uninitialized in this function

While this warning is a false-positive, it can easily be killed by
refactoring the code.

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode-map.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 12fcd8897c33..a56f88ea9c73 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -244,8 +244,6 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		return;
 
 	while (1) {
-		bool add_to_ctl = true;
-
 		spin_lock(rbroot_lock);
 		n = rb_first(rbroot);
 		if (!n) {
@@ -257,15 +255,14 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
 		BUG_ON(info->bitmap); /* Logic error */
 
 		if (info->offset > root->ino_cache_progress)
-			add_to_ctl = false;
-		else if (info->offset + info->bytes > root->ino_cache_progress)
-			count = root->ino_cache_progress - info->offset + 1;
+			count = 0;
 		else
-			count = info->bytes;
+			count = min(root->ino_cache_progress - info->offset + 1,
+				    info->bytes);
 
 		rb_erase(&info->offset_index, rbroot);
 		spin_unlock(rbroot_lock);
-		if (add_to_ctl)
+		if (count)
 			__btrfs_add_free_space(root->fs_info, ctl,
 					       info->offset, count);
 		kmem_cache_free(btrfs_free_space_cachep, info);
-- 
cgit v1.2.3


From 43794446548730ac8461be30bbe47d5d027d1d16 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Fri, 22 Jun 2018 12:35:00 +0800
Subject: btrfs: Don't remove block group that still has pinned down bytes

[BUG]
Under certain KVM load and LTP tests, it is possible to hit the
following calltrace if quota is enabled:

BTRFS critical (device vda2): unable to find logical 8820195328 length 4096
BTRFS critical (device vda2): unable to find logical 8820195328 length 4096

WARNING: CPU: 0 PID: 49 at ../block/blk-core.c:172 blk_status_to_errno+0x1a/0x30
CPU: 0 PID: 49 Comm: kworker/u2:1 Not tainted 4.12.14-15-default #1 SLE15 (unreleased)
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.0.0-prebuilt.qemu-project.org 04/01/2014
Workqueue: btrfs-endio-write btrfs_endio_write_helper [btrfs]
task: ffff9f827b340bc0 task.stack: ffffb4f8c0304000
RIP: 0010:blk_status_to_errno+0x1a/0x30
Call Trace:
 submit_extent_page+0x191/0x270 [btrfs]
 ? btrfs_create_repair_bio+0x130/0x130 [btrfs]
 __do_readpage+0x2d2/0x810 [btrfs]
 ? btrfs_create_repair_bio+0x130/0x130 [btrfs]
 ? run_one_async_done+0xc0/0xc0 [btrfs]
 __extent_read_full_page+0xe7/0x100 [btrfs]
 ? run_one_async_done+0xc0/0xc0 [btrfs]
 read_extent_buffer_pages+0x1ab/0x2d0 [btrfs]
 ? run_one_async_done+0xc0/0xc0 [btrfs]
 btree_read_extent_buffer_pages+0x94/0xf0 [btrfs]
 read_tree_block+0x31/0x60 [btrfs]
 read_block_for_search.isra.35+0xf0/0x2e0 [btrfs]
 btrfs_search_slot+0x46b/0xa00 [btrfs]
 ? kmem_cache_alloc+0x1a8/0x510
 ? btrfs_get_token_32+0x5b/0x120 [btrfs]
 find_parent_nodes+0x11d/0xeb0 [btrfs]
 ? leaf_space_used+0xb8/0xd0 [btrfs]
 ? btrfs_leaf_free_space+0x49/0x90 [btrfs]
 ? btrfs_find_all_roots_safe+0x93/0x100 [btrfs]
 btrfs_find_all_roots_safe+0x93/0x100 [btrfs]
 btrfs_find_all_roots+0x45/0x60 [btrfs]
 btrfs_qgroup_trace_extent_post+0x20/0x40 [btrfs]
 btrfs_add_delayed_data_ref+0x1a3/0x1d0 [btrfs]
 btrfs_alloc_reserved_file_extent+0x38/0x40 [btrfs]
 insert_reserved_file_extent.constprop.71+0x289/0x2e0 [btrfs]
 btrfs_finish_ordered_io+0x2f4/0x7f0 [btrfs]
 ? pick_next_task_fair+0x2cd/0x530
 ? __switch_to+0x92/0x4b0
 btrfs_worker_helper+0x81/0x300 [btrfs]
 process_one_work+0x1da/0x3f0
 worker_thread+0x2b/0x3f0
 ? process_one_work+0x3f0/0x3f0
 kthread+0x11a/0x130
 ? kthread_create_on_node+0x40/0x40
 ret_from_fork+0x35/0x40

BTRFS critical (device vda2): unable to find logical 8820195328 length 16384
BTRFS: error (device vda2) in btrfs_finish_ordered_io:3023: errno=-5 IO failure
BTRFS info (device vda2): forced readonly
BTRFS error (device vda2): pending csums is 2887680

[CAUSE]
It's caused by race with block group auto removal:

- There is a meta block group X, which has only one tree block
  The tree block belongs to fs tree 257.
- In current transaction, some operation modified fs tree 257
  The tree block gets COWed, so the block group X is empty, and marked
  as unused, queued to be deleted.
- Some workload (like fsync) wakes up cleaner_kthread()
  Which will call btrfs_delete_unused_bgs() to remove unused block
  groups.
  So block group X along its chunk map get removed.
- Some delalloc work finished for fs tree 257
  Quota needs to get the original reference of the extent, which will
  read tree blocks of commit root of 257.
  Then since the chunk map gets removed, the above warning gets
  triggered.

[FIX]
Just let btrfs_delete_unused_bgs() skip block group which still has
pinned bytes.

However there is a minor side effect: currently we only queue empty
blocks at update_block_group(), and such empty block group with pinned
bytes won't go through update_block_group() again, such block group
won't be removed, until it gets new extent allocated and removed.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 0ca3999356c7..37d8927015d9 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -10702,7 +10702,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		/* Don't want to race with allocators so take the groups_sem */
 		down_write(&space_info->groups_sem);
 		spin_lock(&block_group->lock);
-		if (block_group->reserved ||
+		if (block_group->reserved || block_group->pinned ||
 		    btrfs_block_group_used(&block_group->item) ||
 		    block_group->ro ||
 		    list_is_singular(&block_group->list)) {
-- 
cgit v1.2.3


From 7b4284de93c51b1d78699bf06bccee892699aa4e Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 20 Jun 2018 18:43:12 +0300
Subject: btrfs: Streamline memory allocation failure handling in
 btrfs_add_delayed_tree_ref

Currently the function uses 2 goto labels to properly handle allocation
failures. This could be simplified by simply re-arranging the code so
that allocations are the in the beginning of the function. This allows
to use simple return statements. No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-ref.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index 6eb00eb65d76..62ff545ba1f7 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -730,27 +730,33 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 	if (!ref)
 		return -ENOMEM;
 
+	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
+	if (!head_ref) {
+		kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+		return -ENOMEM;
+	}
+
+	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
+	    is_fstree(ref_root)) {
+		record = kmalloc(sizeof(*record), GFP_NOFS);
+		if (!record) {
+			kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
+			kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
+			return -ENOMEM;
+		}
+	}
+
 	if (parent)
 		ref_type = BTRFS_SHARED_BLOCK_REF_KEY;
 	else
 		ref_type = BTRFS_TREE_BLOCK_REF_KEY;
+
 	init_delayed_ref_common(fs_info, &ref->node, bytenr, num_bytes,
 				ref_root, action, ref_type);
 	ref->root = ref_root;
 	ref->parent = parent;
 	ref->level = level;
 
-	head_ref = kmem_cache_alloc(btrfs_delayed_ref_head_cachep, GFP_NOFS);
-	if (!head_ref)
-		goto free_ref;
-
-	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) &&
-	    is_fstree(ref_root)) {
-		record = kmalloc(sizeof(*record), GFP_NOFS);
-		if (!record)
-			goto free_head_ref;
-	}
-
 	init_delayed_ref_head(head_ref, record, bytenr, num_bytes,
 			      ref_root, 0, action, false, is_system);
 	head_ref->extent_op = extent_op;
@@ -779,13 +785,6 @@ int btrfs_add_delayed_tree_ref(struct btrfs_trans_handle *trans,
 		btrfs_qgroup_trace_extent_post(fs_info, record);
 
 	return 0;
-
-free_head_ref:
-	kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
-free_ref:
-	kmem_cache_free(btrfs_delayed_tree_ref_cachep, ref);
-
-	return -ENOMEM;
 }
 
 /*
-- 
cgit v1.2.3


From 893bf4b115c713738df05bb557f8fba14f07c077 Mon Sep 17 00:00:00 2001
From: Su Yue <suy.fnst@cn.fujitsu.com>
Date: Fri, 22 Jun 2018 09:52:15 +0800
Subject: btrfs: print more details when checking tree block finds a problem

For easier debugging, print eb->start if level is invalid.  Also make
clear if bytenr found is not expected.

Signed-off-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 2de3da7b7bdc..c77afa9e5d91 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -615,8 +615,8 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 
 	found_start = btrfs_header_bytenr(eb);
 	if (found_start != eb->start) {
-		btrfs_err_rl(fs_info, "bad tree block start %llu %llu",
-			     found_start, eb->start);
+		btrfs_err_rl(fs_info, "bad tree block start, want %llu have %llu",
+			     eb->start, found_start);
 		ret = -EIO;
 		goto err;
 	}
@@ -628,8 +628,8 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 	}
 	found_level = btrfs_header_level(eb);
 	if (found_level >= BTRFS_MAX_LEVEL) {
-		btrfs_err(fs_info, "bad tree block level %d",
-			  (int)btrfs_header_level(eb));
+		btrfs_err(fs_info, "bad tree block level %d on %llu",
+			  (int)btrfs_header_level(eb), eb->start);
 		ret = -EIO;
 		goto err;
 	}
-- 
cgit v1.2.3


From e4af400a9c5081e7d2b703e4c479cb9831cc1117 Mon Sep 17 00:00:00 2001
From: Goldwyn Rodrigues <rgoldwyn@suse.com>
Date: Sun, 17 Jun 2018 12:39:47 -0500
Subject: btrfs: Use iocb to derive pos instead of passing a separate parameter

struct kiocb carries the ki_pos, so there is no need to pass it as
a separate function parameter.

generic_file_direct_write() increments ki_pos, so we now assign pos
after the function.

Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
Reviewed-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
[ rename to btrfs_buffered_write ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 4cd8af14f915..89c9404fee9a 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1568,10 +1568,11 @@ static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 	return ret;
 }
 
-static noinline ssize_t __btrfs_buffered_write(struct file *file,
-					       struct iov_iter *i,
-					       loff_t pos)
+static noinline ssize_t btrfs_buffered_write(struct kiocb *iocb,
+					       struct iov_iter *i)
 {
+	struct file *file = iocb->ki_filp;
+	loff_t pos = iocb->ki_pos;
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
@@ -1803,7 +1804,7 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
-	loff_t pos = iocb->ki_pos;
+	loff_t pos;
 	ssize_t written;
 	ssize_t written_buffered;
 	loff_t endbyte;
@@ -1814,8 +1815,8 @@ static ssize_t __btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	if (written < 0 || !iov_iter_count(from))
 		return written;
 
-	pos += written;
-	written_buffered = __btrfs_buffered_write(file, from, pos);
+	pos = iocb->ki_pos;
+	written_buffered = btrfs_buffered_write(iocb, from);
 	if (written_buffered < 0) {
 		err = written_buffered;
 		goto out;
@@ -1952,7 +1953,7 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	if (iocb->ki_flags & IOCB_DIRECT) {
 		num_written = __btrfs_direct_write(iocb, from);
 	} else {
-		num_written = __btrfs_buffered_write(file, from, pos);
+		num_written = btrfs_buffered_write(iocb, from);
 		if (num_written > 0)
 			iocb->ki_pos = pos + num_written;
 		if (clean_page)
-- 
cgit v1.2.3


From af431dcb249ffff20b16e08adaa4b624405a046b Mon Sep 17 00:00:00 2001
From: Su Yue <suy.fnst@cn.fujitsu.com>
Date: Fri, 22 Jun 2018 16:18:01 +0800
Subject: btrfs: return EUCLEAN if extent_inline_ref type is invalid

If type of extent_inline_ref found is not expected, filesystem may have
been corrupted, should return EUCLEAN instead of EINVAL.

Signed-off-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/backref.c     | 4 ++--
 fs/btrfs/extent-tree.c | 2 +-
 fs/btrfs/relocation.c  | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 0a8e2e29a66b..60f4afa8ecbc 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -925,7 +925,7 @@ static int add_inline_refs(const struct btrfs_fs_info *fs_info,
 		type = btrfs_get_extent_inline_ref_type(leaf, iref,
 							BTRFS_REF_TYPE_ANY);
 		if (type == BTRFS_REF_TYPE_INVALID)
-			return -EINVAL;
+			return -EUCLEAN;
 
 		offset = btrfs_extent_inline_ref_offset(leaf, iref);
 
@@ -1793,7 +1793,7 @@ static int get_extent_inline_ref(unsigned long *ptr,
 	*out_type = btrfs_get_extent_inline_ref_type(eb, *out_eiref,
 						     BTRFS_REF_TYPE_ANY);
 	if (*out_type == BTRFS_REF_TYPE_INVALID)
-		return -EINVAL;
+		return -EUCLEAN;
 
 	*ptr += btrfs_extent_inline_ref_size(*out_type);
 	WARN_ON(*ptr > end);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 37d8927015d9..b28fa3d20ef7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1719,7 +1719,7 @@ again:
 		iref = (struct btrfs_extent_inline_ref *)ptr;
 		type = btrfs_get_extent_inline_ref_type(leaf, iref, needed);
 		if (type == BTRFS_REF_TYPE_INVALID) {
-			err = -EINVAL;
+			err = -EUCLEAN;
 			goto out;
 		}
 
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 22214033a4a2..44722e939e34 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -792,7 +792,7 @@ again:
 			type = btrfs_get_extent_inline_ref_type(eb, iref,
 							BTRFS_REF_TYPE_BLOCK);
 			if (type == BTRFS_REF_TYPE_INVALID) {
-				err = -EINVAL;
+				err = -EUCLEAN;
 				goto out;
 			}
 			key.type = type;
@@ -3801,7 +3801,7 @@ int add_data_references(struct reloc_control *rc,
 			ret = find_data_references(rc, extent_key,
 						   eb, dref, blocks);
 		} else {
-			ret = -EINVAL;
+			ret = -EUCLEAN;
 			btrfs_err(rc->extent_root->fs_info,
 		     "extent %llu slot %d has an invalid inline ref type",
 			     eb->start, path->slots[0]);
-- 
cgit v1.2.3


From ab3629ed86ec43e7d95cf087d0b5a9d403fcd822 Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Wed, 27 Jun 2018 12:16:34 +0800
Subject: btrfs: return error instead of crash when detecting unexpected type
 in btrfs_get_acl

The caller of btrfs_get_acl() checks error condition so there is no
impact from this change. In practice there is no chance to get into
default case of switch statement because VFS has already checked the
type.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/acl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 15e1dfef56a5..60f83a3bd77c 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -30,7 +30,7 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		name = XATTR_NAME_POSIX_ACL_DEFAULT;
 		break;
 	default:
-		BUG();
+		return ERR_PTR(-EINVAL);
 	}
 
 	size = btrfs_getxattr(inode, name, "", 0);
-- 
cgit v1.2.3


From 7e35eab958e30d15743b1f9928d15b559a6e432d Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Wed, 27 Jun 2018 12:16:35 +0800
Subject: btrfs: replace empty string with NULL when getting attribute length
 in btrfs_get_acl

In btrfs_get_acl() the first call of btr_getxattr() is for getting the
length of attribute, the value buffer is never used in this case. So
it's better to replace empty string with NULL.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/acl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 60f83a3bd77c..83fdd80c51c6 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -33,7 +33,7 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 		return ERR_PTR(-EINVAL);
 	}
 
-	size = btrfs_getxattr(inode, name, "", 0);
+	size = btrfs_getxattr(inode, name, NULL, 0);
 	if (size > 0) {
 		value = kzalloc(size, GFP_KERNEL);
 		if (!value)
-- 
cgit v1.2.3


From 5ee552da503961e6df785b8495bcfc98eb30eb2a Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Wed, 27 Jun 2018 12:16:36 +0800
Subject: btrfs: remove unnecessary -ERANGE check in btrfs_get_acl

There is no chance to get into -ERANGE error condition because we first
call btrfs_getxattr to get the length of the attribute, then we do a
subsequent call with the size from the first call.  Between the 2 calls
the size shouldn't change. So remove the unnecessary -ERANGE error
check.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/acl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 83fdd80c51c6..a1d7211c8884 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -42,7 +42,7 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 	}
 	if (size > 0) {
 		acl = posix_acl_from_xattr(&init_user_ns, value, size);
-	} else if (size == -ERANGE || size == -ENODATA || size == 0) {
+	} else if (size == -ENODATA || size == 0) {
 		acl = NULL;
 	} else {
 		acl = ERR_PTR(-EIO);
-- 
cgit v1.2.3


From dc7789ef8785ea996ecf302a89415439ccf10faa Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Wed, 27 Jun 2018 12:16:37 +0800
Subject: btrfs: avoid error code override in btrfs_get_acl

It's not good to override the error code when failing from
btrfs_getxattr() in btrfs_get_acl() because it hides the real reason of
the failure.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/acl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index a1d7211c8884..7d673ec9e54a 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -45,7 +45,7 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 	} else if (size == -ENODATA || size == 0) {
 		acl = NULL;
 	} else {
-		acl = ERR_PTR(-EIO);
+		acl = ERR_PTR(size);
 	}
 	kfree(value);
 
-- 
cgit v1.2.3


From 4de426cd394e4de4d3039aff7d20724d7d988dcf Mon Sep 17 00:00:00 2001
From: Chengguang Xu <cgxu519@gmx.com>
Date: Wed, 27 Jun 2018 12:16:38 +0800
Subject: btrfs: remove unnecessary curly braces in btrfs_get_acl

It's only coding style fix not functinal change.  When if/else has only
one statement then the braces are not needed.

Signed-off-by: Chengguang Xu <cgxu519@gmx.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/acl.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 7d673ec9e54a..3b66c957ea6f 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -40,13 +40,12 @@ struct posix_acl *btrfs_get_acl(struct inode *inode, int type)
 			return ERR_PTR(-ENOMEM);
 		size = btrfs_getxattr(inode, name, value, size);
 	}
-	if (size > 0) {
+	if (size > 0)
 		acl = posix_acl_from_xattr(&init_user_ns, value, size);
-	} else if (size == -ENODATA || size == 0) {
+	else if (size == -ENODATA || size == 0)
 		acl = NULL;
-	} else {
+	else
 		acl = ERR_PTR(size);
-	}
 	kfree(value);
 
 	return acl;
-- 
cgit v1.2.3


From a79865c680d81220a1355cd13098e75227dc2994 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Thu, 21 Jun 2018 09:45:00 +0300
Subject: btrfs: Remove V0 extent support

The v0 compat code was introduced in commit 5d4f98a28c7d
("Btrfs: Mixed back reference  (FORWARD ROLLING FORMAT CHANGE)") 9
years ago, which was merged in 2.6.31. This means that the code is
there to support filesystems which are _VERY_ old and if you are using
btrfs on such an old kernel, you have much bigger problems. This coupled
with the fact that no one is likely testing/maintining this code likely
means it has bugs lurking. All things considered I think 43 kernel
releases later it's high time this remnant of the past got removed.

This patch removes all code wrapped in #ifdefs but leaves the BUG_ONs in case
we have a v0 with no support intact as a sort of safety-net.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.c       |   6 +-
 fs/btrfs/ctree.h       |   2 -
 fs/btrfs/extent-tree.c | 209 +------------------------------------------------
 fs/btrfs/print-tree.c  |  30 +------
 fs/btrfs/relocation.c  | 151 +----------------------------------
 5 files changed, 4 insertions(+), 394 deletions(-)

diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 18f1ca1c5bd9..d436fb4c002e 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -888,11 +888,7 @@ int btrfs_block_can_be_shared(struct btrfs_root *root,
 	     btrfs_root_last_snapshot(&root->root_item) ||
 	     btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
 		return 1;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
-		return 1;
-#endif
+
 	return 0;
 }
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 41ba770b9db9..9fa958ed065e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -55,8 +55,6 @@ struct btrfs_ordered_sum;
 
 #define BTRFS_OLDEST_GENERATION	0ULL
 
-#define BTRFS_COMPAT_EXTENT_TREE_V0
-
 /*
  * the max metadata block size.  This limit is somewhat artificial,
  * but the memmove costs go through the roof for larger blocks.
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index b28fa3d20ef7..6a73d2698807 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -867,17 +867,7 @@ search_again:
 			num_refs = btrfs_extent_refs(leaf, ei);
 			extent_flags = btrfs_extent_flags(leaf, ei);
 		} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			struct btrfs_extent_item_v0 *ei0;
-			BUG_ON(item_size != sizeof(*ei0));
-			ei0 = btrfs_item_ptr(leaf, path->slots[0],
-					     struct btrfs_extent_item_v0);
-			num_refs = btrfs_extent_refs_v0(leaf, ei0);
-			/* FIXME: this isn't correct for data */
-			extent_flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
-#else
 			BUG();
-#endif
 		}
 		BUG_ON(num_refs == 0);
 	} else {
@@ -1036,89 +1026,6 @@ out_free:
  * tree block info structure.
  */
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
-				  struct btrfs_path *path,
-				  u64 owner, u32 extra_size)
-{
-	struct btrfs_root *root = fs_info->extent_root;
-	struct btrfs_extent_item *item;
-	struct btrfs_extent_item_v0 *ei0;
-	struct btrfs_extent_ref_v0 *ref0;
-	struct btrfs_tree_block_info *bi;
-	struct extent_buffer *leaf;
-	struct btrfs_key key;
-	struct btrfs_key found_key;
-	u32 new_size = sizeof(*item);
-	u64 refs;
-	int ret;
-
-	leaf = path->nodes[0];
-	BUG_ON(btrfs_item_size_nr(leaf, path->slots[0]) != sizeof(*ei0));
-
-	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-	ei0 = btrfs_item_ptr(leaf, path->slots[0],
-			     struct btrfs_extent_item_v0);
-	refs = btrfs_extent_refs_v0(leaf, ei0);
-
-	if (owner == (u64)-1) {
-		while (1) {
-			if (path->slots[0] >= btrfs_header_nritems(leaf)) {
-				ret = btrfs_next_leaf(root, path);
-				if (ret < 0)
-					return ret;
-				BUG_ON(ret > 0); /* Corruption */
-				leaf = path->nodes[0];
-			}
-			btrfs_item_key_to_cpu(leaf, &found_key,
-					      path->slots[0]);
-			BUG_ON(key.objectid != found_key.objectid);
-			if (found_key.type != BTRFS_EXTENT_REF_V0_KEY) {
-				path->slots[0]++;
-				continue;
-			}
-			ref0 = btrfs_item_ptr(leaf, path->slots[0],
-					      struct btrfs_extent_ref_v0);
-			owner = btrfs_ref_objectid_v0(leaf, ref0);
-			break;
-		}
-	}
-	btrfs_release_path(path);
-
-	if (owner < BTRFS_FIRST_FREE_OBJECTID)
-		new_size += sizeof(*bi);
-
-	new_size -= sizeof(*ei0);
-	ret = btrfs_search_slot(trans, root, &key, path,
-				new_size + extra_size, 1);
-	if (ret < 0)
-		return ret;
-	BUG_ON(ret); /* Corruption */
-
-	btrfs_extend_item(fs_info, path, new_size);
-
-	leaf = path->nodes[0];
-	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
-	btrfs_set_extent_refs(leaf, item, refs);
-	/* FIXME: get real generation */
-	btrfs_set_extent_generation(leaf, item, 0);
-	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		btrfs_set_extent_flags(leaf, item,
-				       BTRFS_EXTENT_FLAG_TREE_BLOCK |
-				       BTRFS_BLOCK_FLAG_FULL_BACKREF);
-		bi = (struct btrfs_tree_block_info *)(item + 1);
-		/* FIXME: get first key of the block */
-		memzero_extent_buffer(leaf, (unsigned long)bi, sizeof(*bi));
-		btrfs_set_tree_block_level(leaf, bi, (int)owner);
-	} else {
-		btrfs_set_extent_flags(leaf, item, BTRFS_EXTENT_FLAG_DATA);
-	}
-	btrfs_mark_buffer_dirty(leaf);
-	return 0;
-}
-#endif
-
 /*
  * is_data == BTRFS_REF_TYPE_BLOCK, tree block type is required,
  * is_data == BTRFS_REF_TYPE_DATA, data type is requried,
@@ -1247,17 +1154,6 @@ again:
 	if (parent) {
 		if (!ret)
 			return 0;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		key.type = BTRFS_EXTENT_REF_V0_KEY;
-		btrfs_release_path(path);
-		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-		if (ret < 0) {
-			err = ret;
-			goto fail;
-		}
-		if (!ret)
-			return 0;
-#endif
 		goto fail;
 	}
 
@@ -1400,13 +1296,6 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-		struct btrfs_extent_ref_v0 *ref0;
-		ref0 = btrfs_item_ptr(leaf, path->slots[0],
-				      struct btrfs_extent_ref_v0);
-		num_refs = btrfs_ref_count_v0(leaf, ref0);
-#endif
 	} else {
 		BUG();
 	}
@@ -1422,14 +1311,6 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 			btrfs_set_extent_data_ref_count(leaf, ref1, num_refs);
 		else if (key.type == BTRFS_SHARED_DATA_REF_KEY)
 			btrfs_set_shared_data_ref_count(leaf, ref2, num_refs);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		else {
-			struct btrfs_extent_ref_v0 *ref0;
-			ref0 = btrfs_item_ptr(leaf, path->slots[0],
-					struct btrfs_extent_ref_v0);
-			btrfs_set_ref_count_v0(leaf, ref0, num_refs);
-		}
-#endif
 		btrfs_mark_buffer_dirty(leaf);
 	}
 	return ret;
@@ -1469,13 +1350,6 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-		struct btrfs_extent_ref_v0 *ref0;
-		ref0 = btrfs_item_ptr(leaf, path->slots[0],
-				      struct btrfs_extent_ref_v0);
-		num_refs = btrfs_ref_count_v0(leaf, ref0);
-#endif
 	} else {
 		WARN_ON(1);
 	}
@@ -1503,15 +1377,6 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0)
 		ret = -ENOENT;
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (ret == -ENOENT && parent) {
-		btrfs_release_path(path);
-		key.type = BTRFS_EXTENT_REF_V0_KEY;
-		ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
-		if (ret > 0)
-			ret = -ENOENT;
-	}
-#endif
 	return ret;
 }
 
@@ -1676,22 +1541,6 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		if (!insert) {
-			err = -ENOENT;
-			goto out;
-		}
-		ret = convert_extent_item_v0(trans, fs_info, path, owner,
-					     extra_size);
-		if (ret < 0) {
-			err = ret;
-			goto out;
-		}
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-	}
-#endif
 	BUG_ON(item_size < sizeof(*ei));
 
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
@@ -2416,17 +2265,6 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		ret = convert_extent_item_v0(trans, fs_info, path, (u64)-1, 0);
-		if (ret < 0) {
-			err = ret;
-			goto out;
-		}
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-	}
-#endif
 	BUG_ON(item_size < sizeof(*ei));
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	__run_delayed_extent_op(extent_op, leaf, ei);
@@ -3238,12 +3076,6 @@ static noinline int check_committed_ref(struct btrfs_root *root,
 
 	ret = 1;
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
-		goto out;
-	}
-#endif
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 
 	if (item_size != sizeof(*ei) +
@@ -6888,11 +6720,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				break;
 			extent_slot--;
 		}
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		item_size = btrfs_item_size_nr(path->nodes[0], extent_slot);
-		if (found_extent && item_size < sizeof(*ei))
-			found_extent = 0;
-#endif
+
 		if (!found_extent) {
 			BUG_ON(iref);
 			ret = remove_extent_backref(trans, path, NULL,
@@ -6968,41 +6796,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, extent_slot);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		BUG_ON(found_extent || extent_slot != path->slots[0]);
-		ret = convert_extent_item_v0(trans, info, path, owner_objectid,
-					     0);
-		if (ret < 0) {
-			btrfs_abort_transaction(trans, ret);
-			goto out;
-		}
-
-		btrfs_release_path(path);
-		path->leave_spinning = 1;
-
-		key.objectid = bytenr;
-		key.type = BTRFS_EXTENT_ITEM_KEY;
-		key.offset = num_bytes;
-
-		ret = btrfs_search_slot(trans, extent_root, &key, path,
-					-1, 1);
-		if (ret) {
-			btrfs_err(info,
-				  "umm, got %d back from search, was looking for %llu",
-				ret, bytenr);
-			btrfs_print_leaf(path->nodes[0]);
-		}
-		if (ret < 0) {
-			btrfs_abort_transaction(trans, ret);
-			goto out;
-		}
-
-		extent_slot = path->slots[0];
-		leaf = path->nodes[0];
-		item_size = btrfs_item_size_nr(leaf, extent_slot);
-	}
-#endif
 	BUG_ON(item_size < sizeof(*ei));
 	ei = btrfs_item_ptr(leaf, extent_slot,
 			    struct btrfs_extent_item);
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index 59efcf2e0de8..c0dac9d7ce33 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -52,18 +52,8 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	u64 offset;
 	int ref_index = 0;
 
-	if (item_size < sizeof(*ei)) {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		struct btrfs_extent_item_v0 *ei0;
-		BUG_ON(item_size != sizeof(*ei0));
-		ei0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_item_v0);
-		pr_info("\t\textent refs %u\n",
-		       btrfs_extent_refs_v0(eb, ei0));
-		return;
-#else
+	if (item_size < sizeof(*ei))
 		BUG();
-#endif
-	}
 
 	ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
 	flags = btrfs_extent_flags(eb, ei);
@@ -133,20 +123,6 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	WARN_ON(ptr > end);
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static void print_extent_ref_v0(struct extent_buffer *eb, int slot)
-{
-	struct btrfs_extent_ref_v0 *ref0;
-
-	ref0 = btrfs_item_ptr(eb, slot, struct btrfs_extent_ref_v0);
-	printk("\t\textent back ref root %llu gen %llu owner %llu num_refs %lu\n",
-		btrfs_ref_root_v0(eb, ref0),
-		btrfs_ref_generation_v0(eb, ref0),
-		btrfs_ref_objectid_v0(eb, ref0),
-		(unsigned long)btrfs_ref_count_v0(eb, ref0));
-}
-#endif
-
 static void print_uuid_item(struct extent_buffer *l, unsigned long offset,
 			    u32 item_size)
 {
@@ -280,11 +256,7 @@ void btrfs_print_leaf(struct extent_buffer *l)
 			       btrfs_file_extent_ram_bytes(l, fi));
 			break;
 		case BTRFS_EXTENT_REF_V0_KEY:
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			print_extent_ref_v0(l, i);
-#else
 			BUG();
-#endif
 			break;
 		case BTRFS_BLOCK_GROUP_ITEM_KEY:
 			bi = btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 44722e939e34..6dfa92e5ceed 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -586,29 +586,6 @@ static struct btrfs_root *read_fs_root(struct btrfs_fs_info *fs_info,
 	return btrfs_get_fs_root(fs_info, &key, false);
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static noinline_for_stack
-struct btrfs_root *find_tree_root(struct reloc_control *rc,
-				  struct extent_buffer *leaf,
-				  struct btrfs_extent_ref_v0 *ref0)
-{
-	struct btrfs_root *root;
-	u64 root_objectid = btrfs_ref_root_v0(leaf, ref0);
-	u64 generation = btrfs_ref_generation_v0(leaf, ref0);
-
-	BUG_ON(root_objectid == BTRFS_TREE_RELOC_OBJECTID);
-
-	root = read_fs_root(rc->extent_root->fs_info, root_objectid);
-	BUG_ON(IS_ERR(root));
-
-	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
-	    generation != btrfs_root_generation(&root->root_item))
-		return NULL;
-
-	return root;
-}
-#endif
-
 static noinline_for_stack
 int find_inline_backref(struct extent_buffer *leaf, int slot,
 			unsigned long *ptr, unsigned long *end)
@@ -621,12 +598,6 @@ int find_inline_backref(struct extent_buffer *leaf, int slot,
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 
 	item_size = btrfs_item_size_nr(leaf, slot);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (item_size < sizeof(*ei)) {
-		WARN_ON(item_size != sizeof(struct btrfs_extent_item_v0));
-		return 1;
-	}
-#endif
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 	WARN_ON(!(btrfs_extent_flags(leaf, ei) &
 		  BTRFS_EXTENT_FLAG_TREE_BLOCK));
@@ -811,29 +782,8 @@ again:
 			goto next;
 		}
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY ||
-		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
-			if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
-				struct btrfs_extent_ref_v0 *ref0;
-				ref0 = btrfs_item_ptr(eb, path1->slots[0],
-						struct btrfs_extent_ref_v0);
-				if (key.objectid == key.offset) {
-					root = find_tree_root(rc, eb, ref0);
-					if (root && !should_ignore_root(root))
-						cur->root = root;
-					else
-						list_add(&cur->list, &useless);
-					break;
-				}
-				if (is_cowonly_root(btrfs_ref_root_v0(eb,
-								      ref0)))
-					cur->cowonly = 1;
-			}
-#else
 		ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
-#endif
 			if (key.objectid == key.offset) {
 				/*
 				 * only root blocks of reloc trees use
@@ -3333,48 +3283,6 @@ int relocate_data_extent(struct inode *inode, struct btrfs_key *extent_key,
 	return 0;
 }
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-static int get_ref_objectid_v0(struct reloc_control *rc,
-			       struct btrfs_path *path,
-			       struct btrfs_key *extent_key,
-			       u64 *ref_objectid, int *path_change)
-{
-	struct btrfs_key key;
-	struct extent_buffer *leaf;
-	struct btrfs_extent_ref_v0 *ref0;
-	int ret;
-	int slot;
-
-	leaf = path->nodes[0];
-	slot = path->slots[0];
-	while (1) {
-		if (slot >= btrfs_header_nritems(leaf)) {
-			ret = btrfs_next_leaf(rc->extent_root, path);
-			if (ret < 0)
-				return ret;
-			BUG_ON(ret > 0);
-			leaf = path->nodes[0];
-			slot = path->slots[0];
-			if (path_change)
-				*path_change = 1;
-		}
-		btrfs_item_key_to_cpu(leaf, &key, slot);
-		if (key.objectid != extent_key->objectid)
-			return -ENOENT;
-
-		if (key.type != BTRFS_EXTENT_REF_V0_KEY) {
-			slot++;
-			continue;
-		}
-		ref0 = btrfs_item_ptr(leaf, slot,
-				struct btrfs_extent_ref_v0);
-		*ref_objectid = btrfs_ref_objectid_v0(leaf, ref0);
-		break;
-	}
-	return 0;
-}
-#endif
-
 /*
  * helper to add a tree block to the list.
  * the major work is getting the generation and level of the block
@@ -3408,22 +3316,7 @@ static int add_tree_block(struct reloc_control *rc,
 		}
 		generation = btrfs_extent_generation(eb, ei);
 	} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		u64 ref_owner;
-		int ret;
-
-		BUG_ON(item_size != sizeof(struct btrfs_extent_item_v0));
-		ret = get_ref_objectid_v0(rc, path, extent_key,
-					  &ref_owner, NULL);
-		if (ret < 0)
-			return ret;
-		BUG_ON(ref_owner >= BTRFS_MAX_LEVEL);
-		level = (int)ref_owner;
-		/* FIXME: get real generation */
-		generation = 0;
-#else
 		BUG();
-#endif
 	}
 
 	btrfs_release_path(path);
@@ -3781,12 +3674,7 @@ int add_data_references(struct reloc_control *rc,
 	eb = path->nodes[0];
 	ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
 	end = ptr + btrfs_item_size_nr(eb, path->slots[0]);
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-	if (ptr + sizeof(struct btrfs_extent_item_v0) == end)
-		ptr = end;
-	else
-#endif
-		ptr += sizeof(struct btrfs_extent_item);
+	ptr += sizeof(struct btrfs_extent_item);
 
 	while (ptr < end) {
 		iref = (struct btrfs_extent_inline_ref *)ptr;
@@ -3832,13 +3720,8 @@ int add_data_references(struct reloc_control *rc,
 		if (key.objectid != extent_key->objectid)
 			break;
 
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-		if (key.type == BTRFS_SHARED_DATA_REF_KEY ||
-		    key.type == BTRFS_EXTENT_REF_V0_KEY) {
-#else
 		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
-#endif
 			ret = __add_tree_block(rc, key.offset, blocksize,
 					       blocks);
 		} else if (key.type == BTRFS_EXTENT_DATA_REF_KEY) {
@@ -4086,39 +3969,7 @@ restart:
 			BUG_ON(ret);
 
 		} else {
-#ifdef BTRFS_COMPAT_EXTENT_TREE_V0
-			u64 ref_owner;
-			int path_change = 0;
-
-			BUG_ON(item_size !=
-			       sizeof(struct btrfs_extent_item_v0));
-			ret = get_ref_objectid_v0(rc, path, &key, &ref_owner,
-						  &path_change);
-			if (ret < 0) {
-				err = ret;
-				break;
-			}
-			if (ref_owner < BTRFS_FIRST_FREE_OBJECTID)
-				flags = BTRFS_EXTENT_FLAG_TREE_BLOCK;
-			else
-				flags = BTRFS_EXTENT_FLAG_DATA;
-
-			if (path_change) {
-				btrfs_release_path(path);
-
-				path->search_commit_root = 1;
-				path->skip_locking = 1;
-				ret = btrfs_search_slot(NULL, rc->extent_root,
-							&key, path, 0, 0);
-				if (ret < 0) {
-					err = ret;
-					break;
-				}
-				BUG_ON(ret > 0);
-			}
-#else
 			BUG();
-#endif
 		}
 
 		if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-- 
cgit v1.2.3


From ba3c2b196bf59ba8574808fe6f8fd88d0fed7510 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Tue, 26 Jun 2018 16:57:36 +0300
Subject: btrfs: Add graceful handling of V0 extents

Following the removal of the v0 handling code let's be courteous and
print an error message when such extents are handled. In the cases
where we have a transaction just abort it, otherwise just call
btrfs_handle_fs_error. Both cases result in the FS being re-mounted RO.

In case the error handling would be too intrusive, leave the BUG_ON in
place, like extent_data_ref_count, other proper handling would catch
that earlier.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  7 +++++++
 fs/btrfs/extent-tree.c | 39 +++++++++++++++++++++++++++++++++++----
 fs/btrfs/print-tree.c  |  9 ++++++---
 fs/btrfs/relocation.c  | 27 ++++++++++++++++++++++++---
 4 files changed, 72 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9fa958ed065e..427ca5de8542 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3432,6 +3432,13 @@ static inline void assfail(char *expr, char *file, int line)
 #define ASSERT(expr)	((void)0)
 #endif
 
+__cold
+static inline void btrfs_print_v0_err(struct btrfs_fs_info *fs_info)
+{
+	btrfs_err(fs_info,
+"Unsupported V0 extent filesystem detected. Aborting. Please re-create your filesystem with a newer kernel");
+}
+
 __printf(5, 6)
 __cold
 void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6a73d2698807..71283faa85e2 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -867,8 +867,16 @@ search_again:
 			num_refs = btrfs_extent_refs(leaf, ei);
 			extent_flags = btrfs_extent_flags(leaf, ei);
 		} else {
-			BUG();
+			ret = -EINVAL;
+			btrfs_print_v0_err(fs_info);
+			if (trans)
+				btrfs_abort_transaction(trans, ret);
+			else
+				btrfs_handle_fs_error(fs_info, ret, NULL);
+
+			goto out_free;
 		}
+
 		BUG_ON(num_refs == 0);
 	} else {
 		num_refs = 0;
@@ -1296,6 +1304,10 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
+	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+		btrfs_print_v0_err(trans->fs_info);
+		btrfs_abort_transaction(trans, -EINVAL);
+		return -EINVAL;
 	} else {
 		BUG();
 	}
@@ -1328,6 +1340,8 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
+
+	BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
 	if (iref) {
 		/*
 		 * If type is invalid, we should have bailed out earlier than
@@ -1541,7 +1555,12 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-	BUG_ON(item_size < sizeof(*ei));
+	if (item_size < sizeof(*ei)) {
+		err = -EINVAL;
+		btrfs_print_v0_err(fs_info);
+		btrfs_abort_transaction(trans, err);
+		goto out;
+	}
 
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	flags = btrfs_extent_flags(leaf, ei);
@@ -2265,7 +2284,14 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-	BUG_ON(item_size < sizeof(*ei));
+
+	if (item_size < sizeof(*ei)) {
+		err = -EINVAL;
+		btrfs_print_v0_err(fs_info);
+		btrfs_abort_transaction(trans, err);
+		goto out;
+	}
+
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	__run_delayed_extent_op(extent_op, leaf, ei);
 
@@ -6796,7 +6822,12 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, extent_slot);
-	BUG_ON(item_size < sizeof(*ei));
+	if (item_size < sizeof(*ei)) {
+		ret = -EINVAL;
+		btrfs_print_v0_err(info);
+		btrfs_abort_transaction(trans, ret);
+		goto out;
+	}
 	ei = btrfs_item_ptr(leaf, extent_slot,
 			    struct btrfs_extent_item);
 	if (owner_objectid < BTRFS_FIRST_FREE_OBJECTID &&
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index c0dac9d7ce33..cc945376c244 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -52,8 +52,10 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	u64 offset;
 	int ref_index = 0;
 
-	if (item_size < sizeof(*ei))
-		BUG();
+	if (item_size < sizeof(*ei)) {
+		btrfs_print_v0_err(eb->fs_info);
+		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
+	}
 
 	ei = btrfs_item_ptr(eb, slot, struct btrfs_extent_item);
 	flags = btrfs_extent_flags(eb, ei);
@@ -256,7 +258,8 @@ void btrfs_print_leaf(struct extent_buffer *l)
 			       btrfs_file_extent_ram_bytes(l, fi));
 			break;
 		case BTRFS_EXTENT_REF_V0_KEY:
-			BUG();
+			btrfs_print_v0_err(fs_info);
+			btrfs_handle_fs_error(fs_info, -EINVAL, NULL);
 			break;
 		case BTRFS_BLOCK_GROUP_ITEM_KEY:
 			bi = btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 6dfa92e5ceed..eaf59c742dc8 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -598,6 +598,11 @@ int find_inline_backref(struct extent_buffer *leaf, int slot,
 	btrfs_item_key_to_cpu(leaf, &key, slot);
 
 	item_size = btrfs_item_size_nr(leaf, slot);
+	if (item_size < sizeof(*ei)) {
+		btrfs_print_v0_err(leaf->fs_info);
+		btrfs_handle_fs_error(leaf->fs_info, -EINVAL, NULL);
+		return 1;
+	}
 	ei = btrfs_item_ptr(leaf, slot, struct btrfs_extent_item);
 	WARN_ON(!(btrfs_extent_flags(leaf, ei) &
 		  BTRFS_EXTENT_FLAG_TREE_BLOCK));
@@ -782,7 +787,6 @@ again:
 			goto next;
 		}
 
-		ASSERT(key.type != BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_BLOCK_REF_KEY) {
 			if (key.objectid == key.offset) {
 				/*
@@ -826,6 +830,12 @@ again:
 			edge->node[UPPER] = upper;
 
 			goto next;
+		} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+			err = -EINVAL;
+			btrfs_print_v0_err(rc->extent_root->fs_info);
+			btrfs_handle_fs_error(rc->extent_root->fs_info, err,
+					      NULL);
+			goto out;
 		} else if (key.type != BTRFS_TREE_BLOCK_REF_KEY) {
 			goto next;
 		}
@@ -3315,6 +3325,10 @@ static int add_tree_block(struct reloc_control *rc,
 			level = (int)extent_key->offset;
 		}
 		generation = btrfs_extent_generation(eb, ei);
+	} else if (item_size == sizeof(struct btrfs_extent_item_v0)) {
+		btrfs_print_v0_err(eb->fs_info);
+		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
+		return -EINVAL;
 	} else {
 		BUG();
 	}
@@ -3720,7 +3734,6 @@ int add_data_references(struct reloc_control *rc,
 		if (key.objectid != extent_key->objectid)
 			break;
 
-		BUG_ON(key.type == BTRFS_EXTENT_REF_V0_KEY);
 		if (key.type == BTRFS_SHARED_DATA_REF_KEY) {
 			ret = __add_tree_block(rc, key.offset, blocksize,
 					       blocks);
@@ -3729,6 +3742,10 @@ int add_data_references(struct reloc_control *rc,
 					      struct btrfs_extent_data_ref);
 			ret = find_data_references(rc, extent_key,
 						   eb, dref, blocks);
+		} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+			btrfs_print_v0_err(eb->fs_info);
+			btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
+			ret = -EINVAL;
 		} else {
 			ret = 0;
 		}
@@ -3967,7 +3984,11 @@ restart:
 			flags = btrfs_extent_flags(path->nodes[0], ei);
 			ret = check_extent_flags(flags);
 			BUG_ON(ret);
-
+		} else if (item_size == sizeof(struct btrfs_extent_item_v0)) {
+			err = -EINVAL;
+			btrfs_print_v0_err(trans->fs_info);
+			btrfs_abort_transaction(trans, err);
+			break;
 		} else {
 			BUG();
 		}
-- 
cgit v1.2.3


From 6d8ff4e4584cd84093b751671351c8103ead551d Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 26 Jun 2018 16:20:59 +0200
Subject: btrfs: annotate unlikely branches after V0 extent type removal

The v0 extent type checks are the right case for the unlikely
annotations as we don't expect to ever see them, so let's give the
compiler some hint.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 8 ++++----
 fs/btrfs/print-tree.c  | 2 +-
 fs/btrfs/relocation.c  | 8 ++++----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 71283faa85e2..352b7e95f657 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -1304,7 +1304,7 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 		ref2 = btrfs_item_ptr(leaf, path->slots[0],
 				      struct btrfs_shared_data_ref);
 		num_refs = btrfs_shared_data_ref_count(leaf, ref2);
-	} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+	} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
 		btrfs_print_v0_err(trans->fs_info);
 		btrfs_abort_transaction(trans, -EINVAL);
 		return -EINVAL;
@@ -1555,7 +1555,7 @@ again:
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
-	if (item_size < sizeof(*ei)) {
+	if (unlikely(item_size < sizeof(*ei))) {
 		err = -EINVAL;
 		btrfs_print_v0_err(fs_info);
 		btrfs_abort_transaction(trans, err);
@@ -2285,7 +2285,7 @@ again:
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
 
-	if (item_size < sizeof(*ei)) {
+	if (unlikely(item_size < sizeof(*ei))) {
 		err = -EINVAL;
 		btrfs_print_v0_err(fs_info);
 		btrfs_abort_transaction(trans, err);
@@ -6822,7 +6822,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 
 	leaf = path->nodes[0];
 	item_size = btrfs_item_size_nr(leaf, extent_slot);
-	if (item_size < sizeof(*ei)) {
+	if (unlikely(item_size < sizeof(*ei))) {
 		ret = -EINVAL;
 		btrfs_print_v0_err(info);
 		btrfs_abort_transaction(trans, ret);
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index cc945376c244..df49931ffe92 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -52,7 +52,7 @@ static void print_extent_item(struct extent_buffer *eb, int slot, int type)
 	u64 offset;
 	int ref_index = 0;
 
-	if (item_size < sizeof(*ei)) {
+	if (unlikely(item_size < sizeof(*ei))) {
 		btrfs_print_v0_err(eb->fs_info);
 		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
 	}
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index eaf59c742dc8..229f721cbde9 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -830,7 +830,7 @@ again:
 			edge->node[UPPER] = upper;
 
 			goto next;
-		} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+		} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
 			err = -EINVAL;
 			btrfs_print_v0_err(rc->extent_root->fs_info);
 			btrfs_handle_fs_error(rc->extent_root->fs_info, err,
@@ -3325,7 +3325,7 @@ static int add_tree_block(struct reloc_control *rc,
 			level = (int)extent_key->offset;
 		}
 		generation = btrfs_extent_generation(eb, ei);
-	} else if (item_size == sizeof(struct btrfs_extent_item_v0)) {
+	} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
 		btrfs_print_v0_err(eb->fs_info);
 		btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
 		return -EINVAL;
@@ -3742,7 +3742,7 @@ int add_data_references(struct reloc_control *rc,
 					      struct btrfs_extent_data_ref);
 			ret = find_data_references(rc, extent_key,
 						   eb, dref, blocks);
-		} else if (key.type == BTRFS_EXTENT_REF_V0_KEY) {
+		} else if (unlikely(key.type == BTRFS_EXTENT_REF_V0_KEY)) {
 			btrfs_print_v0_err(eb->fs_info);
 			btrfs_handle_fs_error(eb->fs_info, -EINVAL, NULL);
 			ret = -EINVAL;
@@ -3984,7 +3984,7 @@ restart:
 			flags = btrfs_extent_flags(path->nodes[0], ei);
 			ret = check_extent_flags(flags);
 			BUG_ON(ret);
-		} else if (item_size == sizeof(struct btrfs_extent_item_v0)) {
+		} else if (unlikely(item_size == sizeof(struct btrfs_extent_item_v0))) {
 			err = -EINVAL;
 			btrfs_print_v0_err(trans->fs_info);
 			btrfs_abort_transaction(trans, err);
-- 
cgit v1.2.3


From fce466eab7ac6baa9d2dcd88abcf945be3d4a089 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 3 Jul 2018 17:10:05 +0800
Subject: btrfs: tree-checker: Verify block_group_item

A crafted image with invalid block group items could make free space cache
code to cause panic.

We could detect such invalid block group item by checking:
1) Item size
   Known fixed value.
2) Block group size (key.offset)
   We have an upper limit on block group item (10G)
3) Chunk objectid
   Known fixed value.
4) Type
   Only 4 valid type values, DATA, METADATA, SYSTEM and DATA|METADATA.
   No more than 1 bit set for profile type.
5) Used space
   No more than the block group size.

This should allow btrfs to detect and refuse to mount the crafted image.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199849
Reported-by: Xu Wen <wen.xu@gatech.edu>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Tested-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 100 ++++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/volumes.c      |   2 +-
 fs/btrfs/volumes.h      |   2 +
 3 files changed, 103 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 8d40e7dd8c30..3bade2ad39e8 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -19,6 +19,7 @@
 #include "tree-checker.h"
 #include "disk-io.h"
 #include "compression.h"
+#include "volumes.h"
 
 /*
  * Error message should follow the following format:
@@ -353,6 +354,102 @@ static int check_dir_item(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+__printf(4, 5)
+__cold
+static void block_group_err(const struct btrfs_fs_info *fs_info,
+			    const struct extent_buffer *eb, int slot,
+			    const char *fmt, ...)
+{
+	struct btrfs_key key;
+	struct va_format vaf;
+	va_list args;
+
+	btrfs_item_key_to_cpu(eb, &key, slot);
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	btrfs_crit(fs_info,
+	"corrupt %s: root=%llu block=%llu slot=%d bg_start=%llu bg_len=%llu, %pV",
+		btrfs_header_level(eb) == 0 ? "leaf" : "node",
+		btrfs_header_owner(eb), btrfs_header_bytenr(eb), slot,
+		key.objectid, key.offset, &vaf);
+	va_end(args);
+}
+
+static int check_block_group_item(struct btrfs_fs_info *fs_info,
+				  struct extent_buffer *leaf,
+				  struct btrfs_key *key, int slot)
+{
+	struct btrfs_block_group_item bgi;
+	u32 item_size = btrfs_item_size_nr(leaf, slot);
+	u64 flags;
+	u64 type;
+
+	/*
+	 * Here we don't really care about alignment since extent allocator can
+	 * handle it.  We care more about the size, as if one block group is
+	 * larger than maximum size, it's must be some obvious corruption.
+	 */
+	if (key->offset > BTRFS_MAX_DATA_CHUNK_SIZE || key->offset == 0) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group size, have %llu expect (0, %llu]",
+				key->offset, BTRFS_MAX_DATA_CHUNK_SIZE);
+		return -EUCLEAN;
+	}
+
+	if (item_size != sizeof(bgi)) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid item size, have %u expect %zu",
+				item_size, sizeof(bgi));
+		return -EUCLEAN;
+	}
+
+	read_extent_buffer(leaf, &bgi, btrfs_item_ptr_offset(leaf, slot),
+			   sizeof(bgi));
+	if (btrfs_block_group_chunk_objectid(&bgi) !=
+	    BTRFS_FIRST_CHUNK_TREE_OBJECTID) {
+		block_group_err(fs_info, leaf, slot,
+		"invalid block group chunk objectid, have %llu expect %llu",
+				btrfs_block_group_chunk_objectid(&bgi),
+				BTRFS_FIRST_CHUNK_TREE_OBJECTID);
+		return -EUCLEAN;
+	}
+
+	if (btrfs_block_group_used(&bgi) > key->offset) {
+		block_group_err(fs_info, leaf, slot,
+			"invalid block group used, have %llu expect [0, %llu)",
+				btrfs_block_group_used(&bgi), key->offset);
+		return -EUCLEAN;
+	}
+
+	flags = btrfs_block_group_flags(&bgi);
+	if (hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) > 1) {
+		block_group_err(fs_info, leaf, slot,
+"invalid profile flags, have 0x%llx (%lu bits set) expect no more than 1 bit set",
+			flags & BTRFS_BLOCK_GROUP_PROFILE_MASK,
+			hweight64(flags & BTRFS_BLOCK_GROUP_PROFILE_MASK));
+		return -EUCLEAN;
+	}
+
+	type = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+	if (type != BTRFS_BLOCK_GROUP_DATA &&
+	    type != BTRFS_BLOCK_GROUP_METADATA &&
+	    type != BTRFS_BLOCK_GROUP_SYSTEM &&
+	    type != (BTRFS_BLOCK_GROUP_METADATA |
+			   BTRFS_BLOCK_GROUP_DATA)) {
+		block_group_err(fs_info, leaf, slot,
+"invalid type, have 0x%llx (%lu bits set) expect either 0x%llx, 0x%llx, 0x%llu or 0x%llx",
+			type, hweight64(type),
+			BTRFS_BLOCK_GROUP_DATA, BTRFS_BLOCK_GROUP_METADATA,
+			BTRFS_BLOCK_GROUP_SYSTEM,
+			BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA);
+		return -EUCLEAN;
+	}
+	return 0;
+}
+
 /*
  * Common point to switch the item-specific validation.
  */
@@ -374,6 +471,9 @@ static int check_leaf_item(struct btrfs_fs_info *fs_info,
 	case BTRFS_XATTR_ITEM_KEY:
 		ret = check_dir_item(fs_info, leaf, key, slot);
 		break;
+	case BTRFS_BLOCK_GROUP_ITEM_KEY:
+		ret = check_block_group_item(fs_info, leaf, key, slot);
+		break;
 	}
 	return ret;
 }
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fe497937933f..256e57eec8ec 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -4692,7 +4692,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	if (type & BTRFS_BLOCK_GROUP_DATA) {
 		max_stripe_size = SZ_1G;
-		max_chunk_size = 10 * max_stripe_size;
+		max_chunk_size = BTRFS_MAX_DATA_CHUNK_SIZE;
 		if (!devs_max)
 			devs_max = BTRFS_MAX_DEVS(info);
 	} else if (type & BTRFS_BLOCK_GROUP_METADATA) {
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index df2d8bdf8c9a..275c31c730cf 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -11,6 +11,8 @@
 #include <linux/btrfs.h>
 #include "async-thread.h"
 
+#define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)
+
 extern struct mutex uuid_mutex;
 
 #define BTRFS_STRIPE_LEN	SZ_64K
-- 
cgit v1.2.3


From ba480dd4db9f1798541eb2d1c423fc95feee8d36 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 3 Jul 2018 17:10:06 +0800
Subject: btrfs: tree-checker: Detect invalid and empty essential trees

A crafted image has empty root tree block, which will later cause NULL
pointer dereference.

The following trees should never be empty:
1) Tree root
   Must contain at least root items for extent tree, device tree and fs
   tree

2) Chunk tree
   Or we can't even bootstrap as it contains the mapping.

3) Fs tree
   At least inode item for top level inode (.).

4) Device tree
   Dev extents for chunks

5) Extent tree
   Must have corresponding extent for each chunk.

If any of them is empty, we are sure the fs is corrupted and no need to
mount it.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199847
Reported-by: Xu Wen <wen.xu@gatech.edu>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Tested-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-checker.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
index 3bade2ad39e8..db835635372f 100644
--- a/fs/btrfs/tree-checker.c
+++ b/fs/btrfs/tree-checker.c
@@ -496,9 +496,22 @@ static int check_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *leaf,
 	 * skip this check for relocation trees.
 	 */
 	if (nritems == 0 && !btrfs_header_flag(leaf, BTRFS_HEADER_FLAG_RELOC)) {
+		u64 owner = btrfs_header_owner(leaf);
 		struct btrfs_root *check_root;
 
-		key.objectid = btrfs_header_owner(leaf);
+		/* These trees must never be empty */
+		if (owner == BTRFS_ROOT_TREE_OBJECTID ||
+		    owner == BTRFS_CHUNK_TREE_OBJECTID ||
+		    owner == BTRFS_EXTENT_TREE_OBJECTID ||
+		    owner == BTRFS_DEV_TREE_OBJECTID ||
+		    owner == BTRFS_FS_TREE_OBJECTID ||
+		    owner == BTRFS_DATA_RELOC_TREE_OBJECTID) {
+			generic_err(fs_info, leaf, 0,
+			"invalid root, root %llu must never be empty",
+				    owner);
+			return -EUCLEAN;
+		}
+		key.objectid = owner;
 		key.type = BTRFS_ROOT_ITEM_KEY;
 		key.offset = (u64)-1;
 
-- 
cgit v1.2.3


From 389305b2aa68723c754f88d9dbd268a400e10664 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 3 Jul 2018 17:10:07 +0800
Subject: btrfs: relocation: Only remove reloc rb_trees if reloc control has
 been initialized

Invalid reloc tree can cause kernel NULL pointer dereference when btrfs
does some cleanup of the reloc roots.

It turns out that fs_info::reloc_ctl can be NULL in
btrfs_recover_relocation() as we allocate relocation control after all
reloc roots have been verified.
So when we hit: note, we haven't called set_reloc_control() thus
fs_info::reloc_ctl is still NULL.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199833
Reported-by: Xu Wen <wen.xu@gatech.edu>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Tested-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/relocation.c | 23 ++++++++++++-----------
 1 file changed, 12 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 229f721cbde9..b98d7a594542 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1281,18 +1281,19 @@ static void __del_reloc_root(struct btrfs_root *root)
 	struct mapping_node *node = NULL;
 	struct reloc_control *rc = fs_info->reloc_ctl;
 
-	spin_lock(&rc->reloc_root_tree.lock);
-	rb_node = tree_search(&rc->reloc_root_tree.rb_root,
-			      root->node->start);
-	if (rb_node) {
-		node = rb_entry(rb_node, struct mapping_node, rb_node);
-		rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+	if (rc) {
+		spin_lock(&rc->reloc_root_tree.lock);
+		rb_node = tree_search(&rc->reloc_root_tree.rb_root,
+				      root->node->start);
+		if (rb_node) {
+			node = rb_entry(rb_node, struct mapping_node, rb_node);
+			rb_erase(&node->rb_node, &rc->reloc_root_tree.rb_root);
+		}
+		spin_unlock(&rc->reloc_root_tree.lock);
+		if (!node)
+			return;
+		BUG_ON((struct btrfs_root *)node->data != root);
 	}
-	spin_unlock(&rc->reloc_root_tree.lock);
-
-	if (!node)
-		return;
-	BUG_ON((struct btrfs_root *)node->data != root);
 
 	spin_lock(&fs_info->trans_lock);
 	list_del_init(&root->root_list);
-- 
cgit v1.2.3


From 5da54bc13801d378bf2e868beb623fc13ba40a83 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 3 Jul 2018 13:14:50 +0800
Subject: btrfs: use a temporary variable for fs_devices in
 btrfs_init_new_device

There are many instances of the %fs_info->fs_devices pointer
dereferences, use a temporary variable instead.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 42 +++++++++++++++++++++---------------------
 1 file changed, 21 insertions(+), 21 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 256e57eec8ec..adce1c2e9b7b 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2410,12 +2410,13 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct list_head *devices;
 	struct super_block *sb = fs_info->sb;
 	struct rcu_string *name;
+	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	u64 tmp;
 	int seeding_dev = 0;
 	int ret = 0;
 	bool unlocked = false;
 
-	if (sb_rdonly(sb) && !fs_info->fs_devices->seeding)
+	if (sb_rdonly(sb) && !fs_devices->seeding)
 		return -EROFS;
 
 	bdev = blkdev_get_by_path(device_path, FMODE_WRITE | FMODE_EXCL,
@@ -2423,7 +2424,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (IS_ERR(bdev))
 		return PTR_ERR(bdev);
 
-	if (fs_info->fs_devices->seeding) {
+	if (fs_devices->seeding) {
 		seeding_dev = 1;
 		down_write(&sb->s_umount);
 		mutex_lock(&uuid_mutex);
@@ -2431,18 +2432,18 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	filemap_write_and_wait(bdev->bd_inode->i_mapping);
 
-	devices = &fs_info->fs_devices->devices;
+	devices = &fs_devices->devices;
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry(device, devices, dev_list) {
 		if (device->bdev == bdev) {
 			ret = -EEXIST;
 			mutex_unlock(
-				&fs_info->fs_devices->device_list_mutex);
+				&fs_devices->device_list_mutex);
 			goto error;
 		}
 	}
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	device = btrfs_alloc_device(fs_info, NULL, NULL);
 	if (IS_ERR(device)) {
@@ -2491,23 +2492,22 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		}
 	}
 
-	device->fs_devices = fs_info->fs_devices;
+	device->fs_devices = fs_devices;
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	mutex_lock(&fs_info->chunk_mutex);
-	list_add_rcu(&device->dev_list, &fs_info->fs_devices->devices);
-	list_add(&device->dev_alloc_list,
-		 &fs_info->fs_devices->alloc_list);
-	fs_info->fs_devices->num_devices++;
-	fs_info->fs_devices->open_devices++;
-	fs_info->fs_devices->rw_devices++;
-	fs_info->fs_devices->total_devices++;
-	fs_info->fs_devices->total_rw_bytes += device->total_bytes;
+	list_add_rcu(&device->dev_list, &fs_devices->devices);
+	list_add(&device->dev_alloc_list, &fs_devices->alloc_list);
+	fs_devices->num_devices++;
+	fs_devices->open_devices++;
+	fs_devices->rw_devices++;
+	fs_devices->total_devices++;
+	fs_devices->total_rw_bytes += device->total_bytes;
 
 	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
 	if (!blk_queue_nonrot(q))
-		fs_info->fs_devices->rotating = 1;
+		fs_devices->rotating = 1;
 
 	tmp = btrfs_super_total_bytes(fs_info->super_copy);
 	btrfs_set_super_total_bytes(fs_info->super_copy,
@@ -2517,7 +2517,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	btrfs_set_super_num_devices(fs_info->super_copy, tmp + 1);
 
 	/* add sysfs device entry */
-	btrfs_sysfs_add_device_link(fs_info->fs_devices, device);
+	btrfs_sysfs_add_device_link(fs_devices, device);
 
 	/*
 	 * we've got more storage, clear any full flags on the space
@@ -2526,7 +2526,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	btrfs_clear_space_info_full(fs_info);
 
 	mutex_unlock(&fs_info->chunk_mutex);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	if (seeding_dev) {
 		mutex_lock(&fs_info->chunk_mutex);
@@ -2558,7 +2558,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		 */
 		snprintf(fsid_buf, BTRFS_UUID_UNPARSED_SIZE, "%pU",
 						fs_info->fsid);
-		if (kobject_rename(&fs_info->fs_devices->fsid_kobj, fsid_buf))
+		if (kobject_rename(&fs_devices->fsid_kobj, fsid_buf))
 			btrfs_warn(fs_info,
 				   "sysfs: failed to create fsid for sprout");
 	}
@@ -2593,7 +2593,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	return ret;
 
 error_sysfs:
-	btrfs_sysfs_rm_device_link(fs_info->fs_devices, device);
+	btrfs_sysfs_rm_device_link(fs_devices, device);
 error_trans:
 	if (seeding_dev)
 		sb->s_flags |= SB_RDONLY;
-- 
cgit v1.2.3


From 694c51fb2eb6b6d7c9552af78ba646023a843366 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 3 Jul 2018 13:14:51 +0800
Subject: btrfs: drop unnecessary variable in btrfs_init_new_device

There is only usage of the declared devices variable, instead use its
value directly.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index adce1c2e9b7b..1ffc49c9c02f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2407,7 +2407,6 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct btrfs_trans_handle *trans;
 	struct btrfs_device *device;
 	struct block_device *bdev;
-	struct list_head *devices;
 	struct super_block *sb = fs_info->sb;
 	struct rcu_string *name;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
@@ -2432,10 +2431,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 	filemap_write_and_wait(bdev->bd_inode->i_mapping);
 
-	devices = &fs_devices->devices;
-
 	mutex_lock(&fs_devices->device_list_mutex);
-	list_for_each_entry(device, devices, dev_list) {
+	list_for_each_entry(device, &fs_devices->devices, dev_list) {
 		if (device->bdev == bdev) {
 			ret = -EEXIST;
 			mutex_unlock(
-- 
cgit v1.2.3


From 8f6c72a9e08c2a74d2159d2fc986fa9b29ceb851 Mon Sep 17 00:00:00 2001
From: Zhihui Zhang <zzhsuny@gmail.com>
Date: Mon, 2 Jul 2018 20:00:54 -0400
Subject: Btrfs: free space cache: make sure there is always room for
 generation number

io_ctl_set_generation() assumes that the generation number shares
the same page with inline CRCs. Let's make sure this is always true.

Signed-off-by: Zhihui Zhang <zzhsuny@gmail.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/free-space-cache.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d5f80cb300be..d2c0bdbd79ec 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -300,9 +300,9 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FREE_INO_OBJECTID)
 		check_crcs = 1;
 
-	/* Make sure we can fit our crcs into the first page */
+	/* Make sure we can fit our crcs and generation into the first page */
 	if (write && check_crcs &&
-	    (num_pages * sizeof(u32)) >= PAGE_SIZE)
+	    (num_pages * sizeof(u32) + sizeof(u64)) > PAGE_SIZE)
 		return -ENOSPC;
 
 	memset(io_ctl, 0, sizeof(struct btrfs_io_ctl));
-- 
cgit v1.2.3


From 37508515621551538addaf826ab4b8a9aaf0a382 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:40 +0200
Subject: btrfs: simplify some assignments of inode numbers

There are several places when the btrfs inode is converted to the
generic inode, back to btrfs and then passed to btrfs_ino. We can remove
the extra back and forth conversions.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 2858bc355920..17816c455786 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4242,9 +4242,9 @@ again:
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		if (objectid < btrfs_ino(entry))
 			node = node->rb_left;
-		else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		else if (objectid > btrfs_ino(entry))
 			node = node->rb_right;
 		else
 			break;
@@ -4252,7 +4252,7 @@ again:
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
+			if (objectid <= btrfs_ino(entry)) {
 				node = prev;
 				break;
 			}
@@ -4261,7 +4261,7 @@ again:
 	}
 	while (node) {
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
+		objectid = btrfs_ino(entry) + 1;
 		inode = igrab(&entry->vfs_inode);
 		if (inode) {
 			spin_unlock(&root->inode_lock);
@@ -5614,9 +5614,9 @@ static void inode_tree_add(struct inode *inode)
 		parent = *p;
 		entry = rb_entry(parent, struct btrfs_inode, rb_node);
 
-		if (ino < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		if (ino < btrfs_ino(entry))
 			p = &parent->rb_left;
-		else if (ino > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
+		else if (ino > btrfs_ino(entry))
 			p = &parent->rb_right;
 		else {
 			WARN_ON(!(entry->vfs_inode.i_state &
-- 
cgit v1.2.3


From 3ffbd68c48320730ef64ebfb5e639220f1f65483 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:42 +0200
Subject: btrfs: simplify pointer chasing of local fs_info variables

Functions that get btrfs inode can simply reach the fs_info by
dereferencing the root and this looks a bit more straightforward
compared to the btrfs_sb(...) indirection.

If the transaction handle is available and not NULL it's used instead.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-inode.c    |  4 ++--
 fs/btrfs/disk-io.c          |  2 +-
 fs/btrfs/extent-tree.c      |  6 +++---
 fs/btrfs/file-item.c        |  2 +-
 fs/btrfs/file.c             | 14 +++++++-------
 fs/btrfs/free-space-cache.c |  7 ++-----
 fs/btrfs/inode.c            |  6 +++---
 fs/btrfs/tree-log.c         |  6 +++---
 8 files changed, 22 insertions(+), 25 deletions(-)

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index fe6caa7e698b..596d2af0c8aa 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1222,7 +1222,7 @@ int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
 
 int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
 	struct btrfs_path *path;
@@ -1837,7 +1837,7 @@ release_node:
 
 int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_delayed_node *delayed_node;
 
 	/*
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c77afa9e5d91..e0baf2f3154d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -212,7 +212,7 @@ struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 352b7e95f657..6bba288133b8 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5889,7 +5889,7 @@ static void btrfs_calculate_inode_block_rsv_size(struct btrfs_fs_info *fs_info,
 
 int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	unsigned nr_extents;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
@@ -5962,7 +5962,7 @@ out_fail:
 void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 				     bool qgroup_free)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 	spin_lock(&inode->lock);
@@ -5991,7 +5991,7 @@ void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
 void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
 				    bool qgroup_free)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	unsigned num_extents;
 
 	spin_lock(&inode->lock);
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index 8c3cd7072caf..ba74827beb32 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -922,7 +922,7 @@ void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const bool new_inline,
 				     struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf = path->nodes[0];
 	const int slot = path->slots[0];
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 89c9404fee9a..da53e45705ba 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -83,7 +83,7 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1,
 static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
 				    struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct inode_defrag *entry;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -135,8 +135,8 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 			   struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct btrfs_root *root = inode->root;
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct inode_defrag *defrag;
 	u64 transid;
 	int ret;
@@ -185,7 +185,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode,
 				       struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 
 	if (!__need_auto_defrag(fs_info))
@@ -1132,7 +1132,7 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
 			      struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
@@ -1469,7 +1469,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	u64 start_pos;
 	u64 last_pos;
 	int i;
@@ -1525,7 +1525,7 @@ lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 				    size_t *write_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct btrfs_ordered_extent *ordered;
 	u64 lockstart, lockend;
@@ -2227,7 +2227,7 @@ static int fill_holes(struct btrfs_trans_handle *trans,
 		struct btrfs_inode *inode,
 		struct btrfs_path *path, u64 offset, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *fi;
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d2c0bdbd79ec..354d55f22d99 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -655,7 +655,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 				   struct btrfs_free_space_ctl *ctl,
 				   struct btrfs_path *path, u64 offset)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_free_space_header *header;
 	struct extent_buffer *leaf;
 	struct btrfs_io_ctl io_ctl;
@@ -1123,13 +1123,10 @@ static int __btrfs_wait_cache_io(struct btrfs_root *root,
 {
 	int ret;
 	struct inode *inode = io_ctl->inode;
-	struct btrfs_fs_info *fs_info;
 
 	if (!inode)
 		return 0;
 
-	fs_info = btrfs_sb(inode->i_sb);
-
 	/* Flush the dirty pages in the cache file. */
 	ret = flush_dirty_cache(inode);
 	if (ret)
@@ -1145,7 +1142,7 @@ out:
 		BTRFS_I(inode)->generation = 0;
 		if (block_group) {
 #ifdef DEBUG
-			btrfs_err(fs_info,
+			btrfs_err(root->fs_info,
 				  "failed to write free space cache for block group %llu",
 				  block_group->key.objectid);
 #endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 17816c455786..32613dca13c1 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1751,7 +1751,7 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
 void __btrfs_del_delalloc_inode(struct btrfs_root *root,
 				struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = root->fs_info;
 
 	if (!list_empty(&inode->delalloc_inodes)) {
 		list_del_init(&inode->delalloc_inodes);
@@ -6418,7 +6418,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 	struct btrfs_key key;
 	struct btrfs_root *root = parent_inode->root;
@@ -6846,7 +6846,7 @@ struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
 	    size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	int ret;
 	int err = 0;
 	u64 extent_start = 0;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 6bca8f88ade0..7b7498f1f641 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -3739,7 +3739,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 			       int start_slot, int nr, int inode_only,
 			       u64 logged_isize)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	unsigned long src_offset;
 	unsigned long dst_offset;
 	struct btrfs_root *log = inode->root->log_root;
@@ -5436,7 +5436,7 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 				 struct btrfs_inode *inode,
 				 struct btrfs_log_ctx *ctx)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_key key;
@@ -5971,7 +5971,7 @@ int btrfs_log_new_name(struct btrfs_trans_handle *trans,
 			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
 			struct dentry *parent)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 
 	/*
 	 * this will force the logging code to walk the dentry chain
-- 
cgit v1.2.3


From 69d2480456d1baf027a86e530989d7bedd698d5f Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:44 +0200
Subject: btrfs: use copy_page for copying pages instead of memcpy

Use the helper that's possibly optimized for full page copies.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/free-space-cache.c |  4 ++--
 fs/btrfs/raid56.c           | 12 +++++-------
 2 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 354d55f22d99..57e7ab7f5e03 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -547,7 +547,7 @@ static int io_ctl_add_bitmap(struct btrfs_io_ctl *io_ctl, void *bitmap)
 		io_ctl_map_page(io_ctl, 0);
 	}
 
-	memcpy(io_ctl->cur, bitmap, PAGE_SIZE);
+	copy_page(io_ctl->cur, bitmap);
 	io_ctl_set_crc(io_ctl, io_ctl->index - 1);
 	if (io_ctl->index < io_ctl->num_pages)
 		io_ctl_map_page(io_ctl, 0);
@@ -607,7 +607,7 @@ static int io_ctl_read_bitmap(struct btrfs_io_ctl *io_ctl,
 	if (ret)
 		return ret;
 
-	memcpy(entry->bitmap, io_ctl->cur, PAGE_SIZE);
+	copy_page(entry->bitmap, io_ctl->cur);
 	io_ctl_unmap_page(io_ctl);
 
 	return 0;
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 5e4ad134b9ad..27ed47a23f26 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -260,7 +260,7 @@ static void cache_rbio_pages(struct btrfs_raid_bio *rbio)
 		s = kmap(rbio->bio_pages[i]);
 		d = kmap(rbio->stripe_pages[i]);
 
-		memcpy(d, s, PAGE_SIZE);
+		copy_page(d, s);
 
 		kunmap(rbio->bio_pages[i]);
 		kunmap(rbio->stripe_pages[i]);
@@ -1275,7 +1275,7 @@ static noinline void finish_rmw(struct btrfs_raid_bio *rbio)
 						pointers);
 		} else {
 			/* raid5 */
-			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+			copy_page(pointers[nr_data], pointers[0]);
 			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
@@ -1941,9 +1941,7 @@ static void __raid_recover_end_io(struct btrfs_raid_bio *rbio)
 			BUG_ON(failb != -1);
 pstripe:
 			/* Copy parity block into failed block to start with */
-			memcpy(pointers[faila],
-			       pointers[rbio->nr_data],
-			       PAGE_SIZE);
+			copy_page(pointers[faila], pointers[rbio->nr_data]);
 
 			/* rearrange the pointer array */
 			p = pointers[faila];
@@ -2448,7 +2446,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 						pointers);
 		} else {
 			/* raid5 */
-			memcpy(pointers[nr_data], pointers[0], PAGE_SIZE);
+			copy_page(pointers[nr_data], pointers[0]);
 			run_xor(pointers + 1, nr_data - 1, PAGE_SIZE);
 		}
 
@@ -2456,7 +2454,7 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 		p = rbio_stripe_page(rbio, rbio->scrubp, pagenr);
 		parity = kmap(p);
 		if (memcmp(parity, pointers[rbio->scrubp], PAGE_SIZE))
-			memcpy(parity, pointers[rbio->scrubp], PAGE_SIZE);
+			copy_page(parity, pointers[rbio->scrubp]);
 		else
 			/* Parity is right, needn't writeback */
 			bitmap_clear(rbio->dbitmap, pagenr, 1);
-- 
cgit v1.2.3


From d7f663fa3ff906247a979c1115bc92cbabfb19ba Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:47 +0200
Subject: btrfs: prune unused includes

Remove includes if none of the interfaces and exports is used in the
given source file.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c  |  4 ----
 fs/btrfs/dev-replace.c  |  5 -----
 fs/btrfs/disk-io.c      |  2 --
 fs/btrfs/file.c         |  3 ---
 fs/btrfs/inode-map.c    |  1 -
 fs/btrfs/inode.c        |  4 ----
 fs/btrfs/ioctl.c        |  5 -----
 fs/btrfs/ordered-data.c |  1 -
 fs/btrfs/raid56.c       | 13 -------------
 fs/btrfs/reada.c        |  1 -
 fs/btrfs/struct-funcs.c |  1 -
 fs/btrfs/super.c        |  3 ---
 fs/btrfs/sysfs.c        |  2 --
 fs/btrfs/volumes.c      |  3 ---
 14 files changed, 48 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index d3e447b45bf7..f48794a36068 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -5,7 +5,6 @@
 
 #include <linux/kernel.h>
 #include <linux/bio.h>
-#include <linux/buffer_head.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
@@ -14,10 +13,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
-#include <linux/bit_spinlock.h>
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
 #include <linux/log2.h>
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 1b30c38d05c9..059ca3d5ddd3 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -6,14 +6,9 @@
 #include <linux/sched.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/random.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
 #include <linux/kthread.h>
 #include <linux/math64.h>
-#include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
 #include "disk-io.h"
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e0baf2f3154d..6023eed3e805 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -5,8 +5,6 @@
 
 #include <linux/fs.h>
 #include <linux/blkdev.h>
-#include <linux/scatterlist.h>
-#include <linux/swap.h>
 #include <linux/radix-tree.h>
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index da53e45705ba..2be00e873e92 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -5,14 +5,11 @@
 
 #include <linux/fs.h>
 #include <linux/pagemap.h>
-#include <linux/highmem.h>
 #include <linux/time.h>
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
 #include <linux/falloc.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
 #include <linux/slab.h>
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index a56f88ea9c73..ffca2abf13d0 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2007 Oracle.  All rights reserved.
  */
 
-#include <linux/delay.h>
 #include <linux/kthread.h>
 #include <linux/pagemap.h>
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 32613dca13c1..ada8a698af10 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -14,17 +14,13 @@
 #include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
-#include <linux/bit_spinlock.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/falloc.h>
 #include <linux/slab.h>
 #include <linux/ratelimit.h>
-#include <linux/mount.h>
 #include <linux/btrfs.h>
 #include <linux/blkdev.h>
 #include <linux/posix_acl_xattr.h>
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 08b8c0b346b3..802918507cc0 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5,23 +5,18 @@
 
 #include <linux/kernel.h>
 #include <linux/bio.h>
-#include <linux/buffer_head.h>
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
 #include <linux/time.h>
-#include <linux/init.h>
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
-#include <linux/mpage.h>
 #include <linux/namei.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/compat.h>
-#include <linux/bit_spinlock.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
 #include <linux/mm.h>
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index e173b252d795..0c4ef208b8b9 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -6,7 +6,6 @@
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/writeback.h>
-#include <linux/pagevec.h>
 #include "ctree.h"
 #include "transaction.h"
 #include "btrfs_inode.h"
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 27ed47a23f26..42631079c492 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -5,32 +5,19 @@
  */
 
 #include <linux/sched.h>
-#include <linux/wait.h>
 #include <linux/bio.h>
 #include <linux/slab.h>
-#include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/random.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
-#include <linux/ratelimit.h>
-#include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/hash.h>
 #include <linux/list_sort.h>
 #include <linux/raid/xor.h>
 #include <linux/mm.h>
-#include <asm/div64.h>
 #include "ctree.h"
-#include "extent_map.h"
 #include "disk-io.h"
-#include "transaction.h"
-#include "print-tree.h"
 #include "volumes.h"
 #include "raid56.h"
 #include "async-thread.h"
-#include "check-integrity.h"
-#include "rcu-string.h"
 
 /* set when additional merges to this rbio are not allowed */
 #define RBIO_RMW_LOCKED_BIT	1
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 4be425f70c2d..dec14b739b10 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -7,7 +7,6 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
-#include <linux/rbtree.h>
 #include <linux/slab.h>
 #include <linux/workqueue.h>
 #include "ctree.h"
diff --git a/fs/btrfs/struct-funcs.c b/fs/btrfs/struct-funcs.c
index b7b4acb12833..4c13b737f568 100644
--- a/fs/btrfs/struct-funcs.c
+++ b/fs/btrfs/struct-funcs.c
@@ -3,7 +3,6 @@
  * Copyright (C) 2007 Oracle.  All rights reserved.
  */
 
-#include <linux/highmem.h>
 #include <asm/unaligned.h>
 
 #include "ctree.h"
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 3c5f221b5303..e04bcf0b0ed4 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -5,7 +5,6 @@
 
 #include <linux/blkdev.h>
 #include <linux/module.h>
-#include <linux/buffer_head.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/highmem.h>
@@ -15,8 +14,6 @@
 #include <linux/string.h>
 #include <linux/backing-dev.h>
 #include <linux/mount.h>
-#include <linux/mpage.h>
-#include <linux/swap.h>
 #include <linux/writeback.h>
 #include <linux/statfs.h>
 #include <linux/compat.h>
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 4a4e960c7c66..3717c864ba23 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -7,10 +7,8 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
-#include <linux/buffer_head.h>
 #include <linux/kobject.h>
 #include <linux/bug.h>
-#include <linux/genhd.h>
 #include <linux/debugfs.h>
 
 #include "ctree.h"
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1ffc49c9c02f..211fb2161487 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -8,15 +8,12 @@
 #include <linux/slab.h>
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
-#include <linux/iocontext.h>
-#include <linux/capability.h>
 #include <linux/ratelimit.h>
 #include <linux/kthread.h>
 #include <linux/raid/pq.h>
 #include <linux/semaphore.h>
 #include <linux/uuid.h>
 #include <linux/list_sort.h>
-#include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
 #include "disk-io.h"
-- 
cgit v1.2.3


From 65ad010488a5cc0f123a9924f7ad26a1b3f6a4f6 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:49 +0200
Subject: btrfs: pass only eb to num_extent_pages

Almost all callers pass the start and len as 2 arguments but this is not
necessary, all the information is provided by the eb. By reordering the
calls to num_extent_pages, we don't need the local variables with
start/len.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 30 +++++++++++++++---------------
 fs/btrfs/extent_io.h |  6 +++---
 2 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index b3e45714d28f..fd34c749209e 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2059,7 +2059,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *eb, int mirror_num)
 {
 	u64 start = eb->start;
-	unsigned long i, num_pages = num_extent_pages(eb->start, eb->len);
+	unsigned long i, num_pages = num_extent_pages(eb);
 	int ret = 0;
 
 	if (sb_rdonly(fs_info->sb))
@@ -3588,7 +3588,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 	if (!ret)
 		return ret;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
@@ -3718,7 +3718,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	int ret = 0;
 
 	clear_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	atomic_set(&eb->io_pages, num_pages);
 
 	/* set btree blocks beyond nritems with 0 to avoid stale content. */
@@ -4653,7 +4653,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 
 	BUG_ON(extent_buffer_under_io(eb));
 
-	index = num_extent_pages(eb->start, eb->len);
+	index = num_extent_pages(eb);
 	if (index == 0)
 		return;
 
@@ -4746,7 +4746,7 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	unsigned long i;
 	struct page *p;
 	struct extent_buffer *new;
-	unsigned long num_pages = num_extent_pages(src->start, src->len);
+	unsigned long num_pages = num_extent_pages(src);
 
 	new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
 	if (new == NULL)
@@ -4778,12 +4778,11 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 	unsigned long num_pages;
 	unsigned long i;
 
-	num_pages = num_extent_pages(start, len);
-
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
 		return NULL;
 
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		eb->pages[i] = alloc_page(GFP_NOFS);
 		if (!eb->pages[i])
@@ -4847,7 +4846,7 @@ static void mark_extent_buffer_accessed(struct extent_buffer *eb,
 
 	check_buffer_tree_ref(eb);
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
@@ -4944,7 +4943,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start)
 {
 	unsigned long len = fs_info->nodesize;
-	unsigned long num_pages = num_extent_pages(start, len);
+	unsigned long num_pages;
 	unsigned long i;
 	unsigned long index = start >> PAGE_SHIFT;
 	struct extent_buffer *eb;
@@ -4967,6 +4966,7 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 	if (!eb)
 		return ERR_PTR(-ENOMEM);
 
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++, index++) {
 		p = find_or_create_page(mapping, index, GFP_NOFS|__GFP_NOFAIL);
 		if (!p) {
@@ -5163,7 +5163,7 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 	unsigned long num_pages;
 	struct page *page;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
@@ -5197,7 +5197,7 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
 
 	was_dirty = test_and_set_bit(EXTENT_BUFFER_DIRTY, &eb->bflags);
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	WARN_ON(!test_bit(EXTENT_BUFFER_TREE_REF, &eb->bflags));
 
@@ -5213,7 +5213,7 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 	unsigned long num_pages;
 
 	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (page)
@@ -5228,7 +5228,7 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 	unsigned long num_pages;
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		SetPageUptodate(page);
@@ -5252,7 +5252,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 	if (test_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags))
 		return 0;
 
-	num_pages = num_extent_pages(eb->start, eb->len);
+	num_pages = num_extent_pages(eb);
 	for (i = 0; i < num_pages; i++) {
 		page = eb->pages[i];
 		if (wait == WAIT_NONE) {
@@ -5580,7 +5580,7 @@ void copy_extent_buffer_full(struct extent_buffer *dst,
 
 	ASSERT(dst->len == src->len);
 
-	num_pages = num_extent_pages(dst->start, dst->len);
+	num_pages = num_extent_pages(dst);
 	for (i = 0; i < num_pages; i++)
 		copy_page(page_address(dst->pages[i]),
 				page_address(src->pages[i]));
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0bfd4aeb822d..d8382a4a7f46 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -440,10 +440,10 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     int mirror_num);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
-static inline unsigned long num_extent_pages(u64 start, u64 len)
+static inline unsigned long num_extent_pages(const struct extent_buffer *eb)
 {
-	return ((start + len + PAGE_SIZE - 1) >> PAGE_SHIFT) -
-		(start >> PAGE_SHIFT);
+	return ((eb->start + eb->len + PAGE_SIZE - 1) >> PAGE_SHIFT) -
+		(eb->start >> PAGE_SHIFT);
 }
 
 static inline void extent_buffer_get(struct extent_buffer *eb)
-- 
cgit v1.2.3


From 8791d43207966f40d8ffba18c663514aca5a6f3e Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 4 Jul 2018 17:49:31 +0200
Subject: btrfs: use round_up wrapper in num_extent_pages

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index d8382a4a7f46..7a3c15b55f2b 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -442,8 +442,8 @@ void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
 static inline unsigned long num_extent_pages(const struct extent_buffer *eb)
 {
-	return ((eb->start + eb->len + PAGE_SIZE - 1) >> PAGE_SHIFT) -
-		(eb->start >> PAGE_SHIFT);
+	return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) -
+	       (eb->start >> PAGE_SHIFT);
 }
 
 static inline void extent_buffer_get(struct extent_buffer *eb)
-- 
cgit v1.2.3


From cc5e31a4775d0d6b98139fdee51868a270bda42f Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Thu, 1 Mar 2018 18:20:27 +0100
Subject: btrfs: switch types to int when counting eb pages

The loops iterating eb pages use unsigned long, that's an overkill as
we know that there are at most 16 pages (64k / 4k), and 4 by default
(with nodesize 16k).

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 44 ++++++++++++++++++++++----------------------
 fs/btrfs/extent_io.h |  2 +-
 2 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fd34c749209e..4fc37e284a79 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2059,7 +2059,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *eb, int mirror_num)
 {
 	u64 start = eb->start;
-	unsigned long i, num_pages = num_extent_pages(eb);
+	int i, num_pages = num_extent_pages(eb);
 	int ret = 0;
 
 	if (sb_rdonly(fs_info->sb))
@@ -3538,7 +3538,7 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 			  struct btrfs_fs_info *fs_info,
 			  struct extent_page_data *epd)
 {
-	unsigned long i, num_pages;
+	int i, num_pages;
 	int flush = 0;
 	int ret = 0;
 
@@ -3712,7 +3712,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 	struct extent_io_tree *tree = &BTRFS_I(fs_info->btree_inode)->io_tree;
 	u64 offset = eb->start;
 	u32 nritems;
-	unsigned long i, num_pages;
+	int i, num_pages;
 	unsigned long start, end;
 	unsigned int write_flags = wbc_to_write_flags(wbc) | REQ_META;
 	int ret = 0;
@@ -4647,7 +4647,7 @@ int extent_buffer_under_io(struct extent_buffer *eb)
  */
 static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 {
-	unsigned long index;
+	int index;
 	struct page *page;
 	int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
 
@@ -4743,10 +4743,10 @@ __alloc_extent_buffer(struct btrfs_fs_info *fs_info, u64 start,
 
 struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 {
-	unsigned long i;
+	int i;
 	struct page *p;
 	struct extent_buffer *new;
-	unsigned long num_pages = num_extent_pages(src);
+	int num_pages = num_extent_pages(src);
 
 	new = __alloc_extent_buffer(src->fs_info, src->start, src->len);
 	if (new == NULL)
@@ -4775,8 +4775,8 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 						  u64 start, unsigned long len)
 {
 	struct extent_buffer *eb;
-	unsigned long num_pages;
-	unsigned long i;
+	int num_pages;
+	int i;
 
 	eb = __alloc_extent_buffer(fs_info, start, len);
 	if (!eb)
@@ -4842,7 +4842,7 @@ static void check_buffer_tree_ref(struct extent_buffer *eb)
 static void mark_extent_buffer_accessed(struct extent_buffer *eb,
 		struct page *accessed)
 {
-	unsigned long num_pages, i;
+	int num_pages, i;
 
 	check_buffer_tree_ref(eb);
 
@@ -4943,8 +4943,8 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 					  u64 start)
 {
 	unsigned long len = fs_info->nodesize;
-	unsigned long num_pages;
-	unsigned long i;
+	int num_pages;
+	int i;
 	unsigned long index = start >> PAGE_SHIFT;
 	struct extent_buffer *eb;
 	struct extent_buffer *exists = NULL;
@@ -5159,8 +5159,8 @@ void free_extent_buffer_stale(struct extent_buffer *eb)
 
 void clear_extent_buffer_dirty(struct extent_buffer *eb)
 {
-	unsigned long i;
-	unsigned long num_pages;
+	int i;
+	int num_pages;
 	struct page *page;
 
 	num_pages = num_extent_pages(eb);
@@ -5189,8 +5189,8 @@ void clear_extent_buffer_dirty(struct extent_buffer *eb)
 
 int set_extent_buffer_dirty(struct extent_buffer *eb)
 {
-	unsigned long i;
-	unsigned long num_pages;
+	int i;
+	int num_pages;
 	int was_dirty = 0;
 
 	check_buffer_tree_ref(eb);
@@ -5208,9 +5208,9 @@ int set_extent_buffer_dirty(struct extent_buffer *eb)
 
 void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
-	unsigned long num_pages;
+	int num_pages;
 
 	clear_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 	num_pages = num_extent_pages(eb);
@@ -5223,9 +5223,9 @@ void clear_extent_buffer_uptodate(struct extent_buffer *eb)
 
 void set_extent_buffer_uptodate(struct extent_buffer *eb)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
-	unsigned long num_pages;
+	int num_pages;
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &eb->bflags);
 	num_pages = num_extent_pages(eb);
@@ -5238,13 +5238,13 @@ void set_extent_buffer_uptodate(struct extent_buffer *eb)
 int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     struct extent_buffer *eb, int wait, int mirror_num)
 {
-	unsigned long i;
+	int i;
 	struct page *page;
 	int err;
 	int ret = 0;
 	int locked_pages = 0;
 	int all_uptodate = 1;
-	unsigned long num_pages;
+	int num_pages;
 	unsigned long num_reads = 0;
 	struct bio *bio = NULL;
 	unsigned long bio_flags = 0;
@@ -5576,7 +5576,7 @@ void copy_extent_buffer_full(struct extent_buffer *dst,
 			     struct extent_buffer *src)
 {
 	int i;
-	unsigned num_pages;
+	int num_pages;
 
 	ASSERT(dst->len == src->len);
 
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 7a3c15b55f2b..48f1ee9ad379 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -440,7 +440,7 @@ int read_extent_buffer_pages(struct extent_io_tree *tree,
 			     int mirror_num);
 void wait_on_extent_buffer_writeback(struct extent_buffer *eb);
 
-static inline unsigned long num_extent_pages(const struct extent_buffer *eb)
+static inline int num_extent_pages(const struct extent_buffer *eb)
 {
 	return (round_up(eb->start + eb->len, PAGE_SIZE) >> PAGE_SHIFT) -
 	       (eb->start >> PAGE_SHIFT);
-- 
cgit v1.2.3


From ebcc326316f3d798e9715e5ca1451c3e457b95dd Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:53 +0200
Subject: btrfs: open-code bio_set_op_attrs

The helper is trivial and marked as deprecated.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/check-integrity.c |  2 +-
 fs/btrfs/compression.c     |  4 ++--
 fs/btrfs/extent_io.c       |  2 +-
 fs/btrfs/inode.c           |  2 +-
 fs/btrfs/raid56.c          | 10 +++++-----
 fs/btrfs/scrub.c           |  6 +++---
 6 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index daf45472bef9..833cf3c35b4d 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -1629,7 +1629,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		bio = btrfs_io_bio_alloc(num_pages - i);
 		bio_set_dev(bio, block_ctx->dev->bdev);
 		bio->bi_iter.bi_sector = dev_bytenr >> 9;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		for (j = i; j < num_pages; j++) {
 			ret = bio_add_page(bio, block_ctx->pagev[j],
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index f48794a36068..70dace47258b 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -609,7 +609,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	cb->len = bio->bi_iter.bi_size;
 
 	comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
-	bio_set_op_attrs (comp_bio, REQ_OP_READ, 0);
+	comp_bio->bi_opf = REQ_OP_READ;
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
 	refcount_set(&cb->pending_bios, 1);
@@ -656,7 +656,7 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			}
 
 			comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
-			bio_set_op_attrs(comp_bio, REQ_OP_READ, 0);
+			comp_bio->bi_opf = REQ_OP_READ;
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4fc37e284a79..fea015be4ce1 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2398,7 +2398,7 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 				      start - page_offset(page),
 				      (int)phy_offset, failed_bio->bi_end_io,
 				      NULL);
-	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
+	bio->bi_opf = REQ_OP_READ | read_mode;
 
 	btrfs_debug(btrfs_sb(inode->i_sb),
 		"Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d",
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index ada8a698af10..564ec00c765b 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -7861,7 +7861,7 @@ static blk_status_t dio_read_error(struct inode *inode, struct bio *failed_bio,
 	isector >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
 				pgoff, isector, repair_endio, repair_arg);
-	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
+	bio->bi_opf = REQ_OP_READ | read_mode;
 
 	btrfs_debug(BTRFS_I(inode)->root->fs_info,
 		    "repair DIO read error: submitting new dio read[%#x] to this_mirror=%d, in_validation=%d",
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 42631079c492..1a1b7d6c44cb 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1330,7 +1330,7 @@ write_data:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -1586,7 +1586,7 @@ static int raid56_rmw_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_rmw_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2130,7 +2130,7 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_recover_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
@@ -2502,7 +2502,7 @@ submit_write:
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid_write_end_io;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		submit_bio(bio);
 	}
@@ -2684,7 +2684,7 @@ static void raid56_parity_scrub_stripe(struct btrfs_raid_bio *rbio)
 
 		bio->bi_private = rbio;
 		bio->bi_end_io = raid56_parity_scrub_end_io;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 
 		btrfs_bio_wq_end_io(rbio->fs_info, bio, BTRFS_WQ_ENDIO_RAID56);
 
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 67bb003323e7..bf4f262f9a52 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -1842,7 +1842,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 		bio = btrfs_io_bio_alloc(1);
 		bio_set_dev(bio, page_bad->dev->bdev);
 		bio->bi_iter.bi_sector = page_bad->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 
 		ret = bio_add_page(bio, page_good->page, PAGE_SIZE, 0);
 		if (PAGE_SIZE != ret) {
@@ -1937,7 +1937,7 @@ again:
 		bio->bi_end_io = scrub_wr_bio_end_io;
 		bio_set_dev(bio, sbio->dev->bdev);
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		bio->bi_opf = REQ_OP_WRITE;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical_for_dev_replace ||
@@ -2337,7 +2337,7 @@ again:
 		bio->bi_end_io = scrub_bio_end_io;
 		bio_set_dev(bio, sbio->dev->bdev);
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
-		bio_set_op_attrs(bio, REQ_OP_READ, 0);
+		bio->bi_opf = REQ_OP_READ;
 		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical ||
-- 
cgit v1.2.3


From ac63885907ee25bf277fa39ba66a0d85dec20786 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:56 +0200
Subject: btrfs: raid56: add new helper for starting async work

Add helper that schedules a given function to run on the rmw workqueue.
This will replace several standalone helpers.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/raid56.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 1a1b7d6c44cb..f30d847baf07 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -174,6 +174,12 @@ static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check);
 static void async_scrub_parity(struct btrfs_raid_bio *rbio);
 
+static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
+{
+	btrfs_init_work(&rbio->work, btrfs_rmw_helper, work_func, NULL, NULL);
+	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
+}
+
 /*
  * the stripe hash table is used for locking, and to collect
  * bios in hopes of making a full stripe
-- 
cgit v1.2.3


From cf6a4a7587dc997b29359e29cf14079e1931715b Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:56:58 +0200
Subject: btrfs: raid56: use new helper for async_rmw_stripe

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/raid56.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index f30d847baf07..96a7d3445623 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -162,7 +162,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
 static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
 static void rmw_work(struct btrfs_work *work);
 static void read_rebuild_work(struct btrfs_work *work);
-static void async_rmw_stripe(struct btrfs_raid_bio *rbio);
 static void async_read_rebuild(struct btrfs_raid_bio *rbio);
 static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio);
 static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed);
@@ -811,7 +810,7 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 				async_read_rebuild(next);
 			} else if (next->operation == BTRFS_RBIO_WRITE) {
 				steal_rbio(rbio, next);
-				async_rmw_stripe(next);
+				start_async_work(next, rmw_work);
 			} else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) {
 				steal_rbio(rbio, next);
 				async_scrub_parity(next);
@@ -1501,12 +1500,6 @@ cleanup:
 	rbio_orig_end_io(rbio, BLK_STS_IOERR);
 }
 
-static void async_rmw_stripe(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper, rmw_work, NULL, NULL);
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
 static void async_read_rebuild(struct btrfs_raid_bio *rbio)
 {
 	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
@@ -1645,7 +1638,7 @@ static int partial_stripe_write(struct btrfs_raid_bio *rbio)
 
 	ret = lock_stripe_add(rbio);
 	if (ret == 0)
-		async_rmw_stripe(rbio);
+		start_async_work(rbio, rmw_work);
 	return 0;
 }
 
-- 
cgit v1.2.3


From e66d8d5a41c1e3c560fc7aba4edcb53caf4f26c8 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:57:00 +0200
Subject: btrfs: raid56: use new helper for async_read_rebuild

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/raid56.c | 15 +++------------
 1 file changed, 3 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 96a7d3445623..f9b349171d61 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -162,7 +162,6 @@ static int __raid56_parity_recover(struct btrfs_raid_bio *rbio);
 static noinline void finish_rmw(struct btrfs_raid_bio *rbio);
 static void rmw_work(struct btrfs_work *work);
 static void read_rebuild_work(struct btrfs_work *work);
-static void async_read_rebuild(struct btrfs_raid_bio *rbio);
 static int fail_bio_stripe(struct btrfs_raid_bio *rbio, struct bio *bio);
 static int fail_rbio_index(struct btrfs_raid_bio *rbio, int failed);
 static void __free_raid_bio(struct btrfs_raid_bio *rbio);
@@ -804,10 +803,10 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 			spin_unlock_irqrestore(&h->lock, flags);
 
 			if (next->operation == BTRFS_RBIO_READ_REBUILD)
-				async_read_rebuild(next);
+				start_async_work(next, read_rebuild_work);
 			else if (next->operation == BTRFS_RBIO_REBUILD_MISSING) {
 				steal_rbio(rbio, next);
-				async_read_rebuild(next);
+				start_async_work(next, read_rebuild_work);
 			} else if (next->operation == BTRFS_RBIO_WRITE) {
 				steal_rbio(rbio, next);
 				start_async_work(next, rmw_work);
@@ -1500,14 +1499,6 @@ cleanup:
 	rbio_orig_end_io(rbio, BLK_STS_IOERR);
 }
 
-static void async_read_rebuild(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
-			read_rebuild_work, NULL, NULL);
-
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
 /*
  * the stripe must be locked by the caller.  It will
  * unlock after all the writes are done
@@ -2765,5 +2756,5 @@ raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 void raid56_submit_missing_rbio(struct btrfs_raid_bio *rbio)
 {
 	if (!lock_stripe_add(rbio))
-		async_read_rebuild(rbio);
+		start_async_work(rbio, read_rebuild_work);
 }
-- 
cgit v1.2.3


From a81b747d0f6efc01506fbd5335e91607dc013b8d Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:57:03 +0200
Subject: btrfs: raid56: use new helper for async_scrub_parity

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/raid56.c | 14 +++-----------
 1 file changed, 3 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index f9b349171d61..339cce0878d1 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -170,7 +170,7 @@ static int alloc_rbio_pages(struct btrfs_raid_bio *rbio);
 
 static noinline void finish_parity_scrub(struct btrfs_raid_bio *rbio,
 					 int need_check);
-static void async_scrub_parity(struct btrfs_raid_bio *rbio);
+static void scrub_parity_work(struct btrfs_work *work);
 
 static void start_async_work(struct btrfs_raid_bio *rbio, btrfs_func_t work_func)
 {
@@ -812,7 +812,7 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 				start_async_work(next, rmw_work);
 			} else if (next->operation == BTRFS_RBIO_PARITY_SCRUB) {
 				steal_rbio(rbio, next);
-				async_scrub_parity(next);
+				start_async_work(next, scrub_parity_work);
 			}
 
 			goto done_nolock;
@@ -2703,18 +2703,10 @@ static void scrub_parity_work(struct btrfs_work *work)
 	raid56_parity_scrub_stripe(rbio);
 }
 
-static void async_scrub_parity(struct btrfs_raid_bio *rbio)
-{
-	btrfs_init_work(&rbio->work, btrfs_rmw_helper,
-			scrub_parity_work, NULL, NULL);
-
-	btrfs_queue_work(rbio->fs_info->rmw_workers, &rbio->work);
-}
-
 void raid56_parity_submit_scrub_rbio(struct btrfs_raid_bio *rbio)
 {
 	if (!lock_stripe_add(rbio))
-		async_scrub_parity(rbio);
+		start_async_work(rbio, scrub_parity_work);
 }
 
 /* The following code is used for dev replace of a missing RAID 5/6 device. */
-- 
cgit v1.2.3


From 176571a1f64f7670c87c3f8d3b50c11cc836110e Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:57:05 +0200
Subject: btrfs: raid56: merge rbio_is_full helpers

There's only one call site of the unlocked helper so it can be folded
into the caller.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/raid56.c | 23 ++++++-----------------
 1 file changed, 6 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 339cce0878d1..272acd9b1192 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -507,32 +507,21 @@ static void run_xor(void **pages, int src_cnt, ssize_t len)
 }
 
 /*
- * returns true if the bio list inside this rbio
- * covers an entire stripe (no rmw required).
- * Must be called with the bio list lock held, or
- * at a time when you know it is impossible to add
- * new bios into the list
+ * Returns true if the bio list inside this rbio covers an entire stripe (no
+ * rmw required).
  */
-static int __rbio_is_full(struct btrfs_raid_bio *rbio)
+static int rbio_is_full(struct btrfs_raid_bio *rbio)
 {
+	unsigned long flags;
 	unsigned long size = rbio->bio_list_bytes;
 	int ret = 1;
 
+	spin_lock_irqsave(&rbio->bio_list_lock, flags);
 	if (size != rbio->nr_data * rbio->stripe_len)
 		ret = 0;
-
 	BUG_ON(size > rbio->nr_data * rbio->stripe_len);
-	return ret;
-}
-
-static int rbio_is_full(struct btrfs_raid_bio *rbio)
-{
-	unsigned long flags;
-	int ret;
-
-	spin_lock_irqsave(&rbio->bio_list_lock, flags);
-	ret = __rbio_is_full(rbio);
 	spin_unlock_irqrestore(&rbio->bio_list_lock, flags);
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From c7b562c5480322ffaf591f45a4ff7ee089340ab4 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 29 Jun 2018 10:57:10 +0200
Subject: btrfs: raid56: catch errors from full_stripe_write

Add fall-back code to catch failure of full_stripe_write. Proper error
handling from inside run_plug would need more code restructuring as it's
called at arbitrary points by io scheduler.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/raid56.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index 272acd9b1192..df41d7049936 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -1686,8 +1686,11 @@ static void run_plug(struct btrfs_plug_cb *plug)
 		list_del_init(&cur->plug_list);
 
 		if (rbio_is_full(cur)) {
+			int ret;
+
 			/* we have a full stripe, send it down */
-			full_stripe_write(cur);
+			ret = full_stripe_write(cur);
+			BUG_ON(ret);
 			continue;
 		}
 		if (last) {
-- 
cgit v1.2.3


From 340f1aa27f367e0c3d2662d44f356b05087fea05 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Thu, 5 Jul 2018 14:50:48 +0300
Subject: btrfs: qgroups: Move transaction management inside
 btrfs_quota_enable/disable

Commit 5d23515be669 ("btrfs: Move qgroup rescan on quota enable to
btrfs_quota_enable") not only resulted in an easier to follow code but
it also introduced a subtle bug. It changed the timing when the initial
transaction rescan was happening:

- before the commit: it would happen after transaction commit had occured
- after the commit: it might happen before the transaction was committed

This results in failure to correctly rescan the quota since there could
be data which is still not committed on disk.

This patch aims to fix this by moving the transaction creation/commit
inside btrfs_quota_enable, which allows to schedule the quota commit
after the transaction has been committed.

Fixes: 5d23515be669 ("btrfs: Move qgroup rescan on quota enable to btrfs_quota_enable")
Reported-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Link: https://marc.info/?l=linux-btrfs&m=152999289017582
Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c  | 15 ++--------
 fs/btrfs/qgroup.c | 86 ++++++++++++++++++++++++++++++++++++++++++++++---------
 fs/btrfs/qgroup.h |  6 ++--
 3 files changed, 76 insertions(+), 31 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 802918507cc0..9dcd16dec754 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5105,9 +5105,7 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ioctl_quota_ctl_args *sa;
-	struct btrfs_trans_handle *trans = NULL;
 	int ret;
-	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -5123,28 +5121,19 @@ static long btrfs_ioctl_quota_ctl(struct file *file, void __user *arg)
 	}
 
 	down_write(&fs_info->subvol_sem);
-	trans = btrfs_start_transaction(fs_info->tree_root, 2);
-	if (IS_ERR(trans)) {
-		ret = PTR_ERR(trans);
-		goto out;
-	}
 
 	switch (sa->cmd) {
 	case BTRFS_QUOTA_CTL_ENABLE:
-		ret = btrfs_quota_enable(trans, fs_info);
+		ret = btrfs_quota_enable(fs_info);
 		break;
 	case BTRFS_QUOTA_CTL_DISABLE:
-		ret = btrfs_quota_disable(trans, fs_info);
+		ret = btrfs_quota_disable(fs_info);
 		break;
 	default:
 		ret = -EINVAL;
 		break;
 	}
 
-	err = btrfs_commit_transaction(trans);
-	if (err && !ret)
-		ret = err;
-out:
 	kfree(sa);
 	up_write(&fs_info->subvol_sem);
 drop_write:
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c25dc47210a3..97a59a444500 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -875,8 +875,7 @@ out:
 	return ret;
 }
 
-int btrfs_quota_enable(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info)
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *quota_root;
 	struct btrfs_root *tree_root = fs_info->tree_root;
@@ -886,6 +885,7 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	struct btrfs_key found_key;
 	struct btrfs_qgroup *qgroup = NULL;
+	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 	int slot;
 
@@ -893,9 +893,25 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	if (fs_info->quota_root)
 		goto out;
 
+	/*
+	 * 1 for quota root item
+	 * 1 for BTRFS_QGROUP_STATUS item
+	 *
+	 * Yet we also need 2*n items for a QGROUP_INFO/QGROUP_LIMIT items
+	 * per subvolume. However those are not currently reserved since it
+	 * would be a lot of overkill.
+	 */
+	trans = btrfs_start_transaction(tree_root, 2);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		trans = NULL;
+		goto out;
+	}
+
 	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
 	if (!fs_info->qgroup_ulist) {
 		ret = -ENOMEM;
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
@@ -906,12 +922,14 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 				       BTRFS_QUOTA_TREE_OBJECTID);
 	if (IS_ERR(quota_root)) {
 		ret =  PTR_ERR(quota_root);
+		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
 	path = btrfs_alloc_path();
 	if (!path) {
 		ret = -ENOMEM;
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_root;
 	}
 
@@ -921,8 +939,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_empty_item(trans, quota_root, path, &key,
 				      sizeof(*ptr));
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
+	}
 
 	leaf = path->nodes[0];
 	ptr = btrfs_item_ptr(leaf, path->slots[0],
@@ -944,9 +964,10 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 	ret = btrfs_search_slot_for_read(tree_root, &key, path, 1, 0);
 	if (ret > 0)
 		goto out_add_root;
-	if (ret < 0)
+	if (ret < 0) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
-
+	}
 
 	while (1) {
 		slot = path->slots[0];
@@ -956,18 +977,23 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 		if (found_key.type == BTRFS_ROOT_REF_KEY) {
 			ret = add_qgroup_item(trans, quota_root,
 					      found_key.offset);
-			if (ret)
+			if (ret) {
+				btrfs_abort_transaction(trans, ret);
 				goto out_free_path;
+			}
 
 			qgroup = add_qgroup_rb(fs_info, found_key.offset);
 			if (IS_ERR(qgroup)) {
 				ret = PTR_ERR(qgroup);
+				btrfs_abort_transaction(trans, ret);
 				goto out_free_path;
 			}
 		}
 		ret = btrfs_next_item(tree_root, path);
-		if (ret < 0)
+		if (ret < 0) {
+			btrfs_abort_transaction(trans, ret);
 			goto out_free_path;
+		}
 		if (ret)
 			break;
 	}
@@ -975,18 +1001,28 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 out_add_root:
 	btrfs_release_path(path);
 	ret = add_qgroup_item(trans, quota_root, BTRFS_FS_TREE_OBJECTID);
-	if (ret)
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
+	}
 
 	qgroup = add_qgroup_rb(fs_info, BTRFS_FS_TREE_OBJECTID);
 	if (IS_ERR(qgroup)) {
 		ret = PTR_ERR(qgroup);
+		btrfs_abort_transaction(trans, ret);
 		goto out_free_path;
 	}
 	spin_lock(&fs_info->qgroup_lock);
 	fs_info->quota_root = quota_root;
 	set_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	spin_unlock(&fs_info->qgroup_lock);
+
+	ret = btrfs_commit_transaction(trans);
+	if (ret) {
+		trans = NULL;
+		goto out_free_path;
+	}
+
 	ret = qgroup_rescan_init(fs_info, 0, 1);
 	if (!ret) {
 	        qgroup_rescan_zero_tracking(fs_info);
@@ -1006,20 +1042,35 @@ out:
 	if (ret) {
 		ulist_free(fs_info->qgroup_ulist);
 		fs_info->qgroup_ulist = NULL;
+		if (trans)
+			btrfs_end_transaction(trans);
 	}
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
 }
 
-int btrfs_quota_disable(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info)
+int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_root *quota_root;
+	struct btrfs_trans_handle *trans = NULL;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
 	if (!fs_info->quota_root)
 		goto out;
+
+	/*
+	 * 1 For the root item
+	 *
+	 * We should also reserve enough items for the quota tree deletion in
+	 * btrfs_clean_quota_tree but this is not done.
+	 */
+	trans = btrfs_start_transaction(fs_info->tree_root, 1);
+	if (IS_ERR(trans)) {
+		ret = PTR_ERR(trans);
+		goto out;
+	}
+
 	clear_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags);
 	btrfs_qgroup_wait_for_completion(fs_info, false);
 	spin_lock(&fs_info->qgroup_lock);
@@ -1031,12 +1082,16 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	btrfs_free_qgroup_config(fs_info);
 
 	ret = btrfs_clean_quota_tree(trans, quota_root);
-	if (ret)
-		goto out;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto end_trans;
+	}
 
 	ret = btrfs_del_root(trans, fs_info, &quota_root->root_key);
-	if (ret)
-		goto out;
+	if (ret) {
+		btrfs_abort_transaction(trans, ret);
+		goto end_trans;
+	}
 
 	list_del(&quota_root->dirty_list);
 
@@ -1048,6 +1103,9 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	free_extent_buffer(quota_root->node);
 	free_extent_buffer(quota_root->commit_root);
 	kfree(quota_root);
+
+end_trans:
+	ret = btrfs_end_transaction(trans);
 out:
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 	return ret;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index d60dd06445ce..bec7c9b17a8e 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -141,10 +141,8 @@ struct btrfs_qgroup {
 #define QGROUP_RELEASE		(1<<1)
 #define QGROUP_FREE		(1<<2)
 
-int btrfs_quota_enable(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info);
-int btrfs_quota_disable(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info);
+int btrfs_quota_enable(struct btrfs_fs_info *fs_info);
+int btrfs_quota_disable(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
 void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
-- 
cgit v1.2.3


From b4993e64f78a9605b45252fa9ba385c88a1f4ce9 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 3 Jul 2018 17:07:23 +0800
Subject: btrfs: fix in-memory value of total_devices after seed device
 deletion

In case of deleting the seed device the %cur_devices (seed) and the
%fs_devices (parent) are different. Now, as the parent
fs_devices::total_devices also maintains the total number of devices
including the seed device, so decrement its in-memory value for the
successful seed delete. We are already updating its corresponding
on-disk btrfs_super_block::number_devices value.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 211fb2161487..f532e855b507 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2026,6 +2026,9 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 
 	cur_devices->num_devices--;
 	cur_devices->total_devices--;
+	/* Update total_devices of the parent fs_devices if it's seed */
+	if (cur_devices != fs_devices)
+		fs_devices->total_devices--;
 
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 		cur_devices->missing_devices--;
-- 
cgit v1.2.3


From 93b9bcdf9fbcb683d4e8c44ee8cec0989053d4de Mon Sep 17 00:00:00 2001
From: Gu Jinxiang <gujx@cn.fujitsu.com>
Date: Mon, 9 Jul 2018 14:39:15 +0800
Subject: btrfs: remove unused parameter from btrfs_parse_subvol_options

Since parameter flags is no more used since commit d7407606564c ("btrfs:
split parse_early_options() in two"), remove it.

Signed-off-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index e04bcf0b0ed4..39d8e39b2fe1 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -933,8 +933,8 @@ out:
  *
  * The value is later passed to mount_subvol()
  */
-static int btrfs_parse_subvol_options(const char *options, fmode_t flags,
-		char **subvol_name, u64 *subvol_objectid)
+static int btrfs_parse_subvol_options(const char *options, char **subvol_name,
+		u64 *subvol_objectid)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *opts, *orig, *p;
@@ -1648,8 +1648,8 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
-	error = btrfs_parse_subvol_options(data, mode,
-					  &subvol_name, &subvol_objectid);
+	error = btrfs_parse_subvol_options(data, &subvol_name,
+					&subvol_objectid);
 	if (error) {
 		kfree(subvol_name);
 		return ERR_PTR(error);
-- 
cgit v1.2.3


From 621567a28ce081424bdcaaef7763a34b204d5be0 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 9 Jul 2018 14:52:54 +0800
Subject: btrfs: Remove unused function btrfs_account_dev_extents_size

This function is not used since the alloc_start parameter has been
obsoleted in commit 0d0c71b317207082856 ("btrfs: obsolete and remove
mount option alloc_start").

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 85 ------------------------------------------------------
 fs/btrfs/volumes.h |  2 --
 2 files changed, 87 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f532e855b507..f7191fdfb44c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1258,91 +1258,6 @@ error_bdev_put:
 	return ret;
 }
 
-/* helper to account the used device space in the range */
-int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
-				   u64 end, u64 *length)
-{
-	struct btrfs_key key;
-	struct btrfs_root *root = device->fs_info->dev_root;
-	struct btrfs_dev_extent *dev_extent;
-	struct btrfs_path *path;
-	u64 extent_end;
-	int ret;
-	int slot;
-	struct extent_buffer *l;
-
-	*length = 0;
-
-	if (start >= device->total_bytes ||
-		test_bit(BTRFS_DEV_STATE_REPLACE_TGT, &device->dev_state))
-		return 0;
-
-	path = btrfs_alloc_path();
-	if (!path)
-		return -ENOMEM;
-	path->reada = READA_FORWARD;
-
-	key.objectid = device->devid;
-	key.offset = start;
-	key.type = BTRFS_DEV_EXTENT_KEY;
-
-	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
-	if (ret < 0)
-		goto out;
-	if (ret > 0) {
-		ret = btrfs_previous_item(root, path, key.objectid, key.type);
-		if (ret < 0)
-			goto out;
-	}
-
-	while (1) {
-		l = path->nodes[0];
-		slot = path->slots[0];
-		if (slot >= btrfs_header_nritems(l)) {
-			ret = btrfs_next_leaf(root, path);
-			if (ret == 0)
-				continue;
-			if (ret < 0)
-				goto out;
-
-			break;
-		}
-		btrfs_item_key_to_cpu(l, &key, slot);
-
-		if (key.objectid < device->devid)
-			goto next;
-
-		if (key.objectid > device->devid)
-			break;
-
-		if (key.type != BTRFS_DEV_EXTENT_KEY)
-			goto next;
-
-		dev_extent = btrfs_item_ptr(l, slot, struct btrfs_dev_extent);
-		extent_end = key.offset + btrfs_dev_extent_length(l,
-								  dev_extent);
-		if (key.offset <= start && extent_end > end) {
-			*length = end - start + 1;
-			break;
-		} else if (key.offset <= start && extent_end > start)
-			*length += extent_end - start;
-		else if (key.offset > start && extent_end <= end)
-			*length += extent_end - key.offset;
-		else if (key.offset > start && key.offset <= end) {
-			*length += end - key.offset + 1;
-			break;
-		} else if (key.offset > end)
-			break;
-
-next:
-		path->slots[0]++;
-	}
-	ret = 0;
-out:
-	btrfs_free_path(path);
-	return ret;
-}
-
 static int contains_pending_extent(struct btrfs_transaction *transaction,
 				   struct btrfs_device *device,
 				   u64 *start, u64 len)
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 275c31c730cf..9665b84b1026 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -384,8 +384,6 @@ static inline enum btrfs_map_op btrfs_op(struct bio *bio)
 	}
 }
 
-int btrfs_account_dev_extents_size(struct btrfs_device *device, u64 start,
-				   u64 end, u64 *length);
 void btrfs_get_bbio(struct btrfs_bio *bbio);
 void btrfs_put_bbio(struct btrfs_bio *bbio);
 int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
-- 
cgit v1.2.3


From 959b1c04675735aa51b9a7b3e28963c4141bf3e7 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 29 Jun 2018 08:26:05 +0300
Subject: btrfs: close devices without offloading to a temporary list

Since commit 88c14590cdd6 ("btrfs: use RCU in btrfs_show_devname for
device list traversal") btrfs_show_devname no longer takes
device_list_mutex. As such the deadlock that 0ccd05285e7f ("btrfs: fix a
possible umount deadlock") aimed to fix no longer exists, we can free
the devices immediatelly and remove the code that does the pending work.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Anand Jain <anand.jain@oracle.com>
[ update changelog ]
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 26 ++++++--------------------
 1 file changed, 6 insertions(+), 20 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f7191fdfb44c..3c3359d7e91d 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1001,7 +1001,7 @@ static void btrfs_close_bdev(struct btrfs_device *device)
 	blkdev_put(device->bdev, device->mode);
 }
 
-static void btrfs_prepare_close_one_device(struct btrfs_device *device)
+static void btrfs_close_one_device(struct btrfs_device *device)
 {
 	struct btrfs_fs_devices *fs_devices = device->fs_devices;
 	struct btrfs_device *new_device;
@@ -1019,6 +1019,8 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 		fs_devices->missing_devices--;
 
+	btrfs_close_bdev(device);
+
 	new_device = btrfs_alloc_device(NULL, &device->devid,
 					device->uuid);
 	BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
@@ -1032,39 +1034,23 @@ static void btrfs_prepare_close_one_device(struct btrfs_device *device)
 
 	list_replace_rcu(&device->dev_list, &new_device->dev_list);
 	new_device->fs_devices = device->fs_devices;
+
+	call_rcu(&device->rcu, free_device_rcu);
 }
 
 static int close_fs_devices(struct btrfs_fs_devices *fs_devices)
 {
 	struct btrfs_device *device, *tmp;
-	struct list_head pending_put;
-
-	INIT_LIST_HEAD(&pending_put);
 
 	if (--fs_devices->opened > 0)
 		return 0;
 
 	mutex_lock(&fs_devices->device_list_mutex);
 	list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list) {
-		btrfs_prepare_close_one_device(device);
-		list_add(&device->dev_list, &pending_put);
+		btrfs_close_one_device(device);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	/*
-	 * btrfs_show_devname() is using the device_list_mutex,
-	 * sometimes call to blkdev_put() leads vfs calling
-	 * into this func. So do put outside of device_list_mutex,
-	 * as of now.
-	 */
-	while (!list_empty(&pending_put)) {
-		device = list_first_entry(&pending_put,
-				struct btrfs_device, dev_list);
-		list_del(&device->dev_list);
-		btrfs_close_bdev(device);
-		call_rcu(&device->rcu, free_device_rcu);
-	}
-
 	WARN_ON(fs_devices->open_devices);
 	WARN_ON(fs_devices->rw_devices);
 	fs_devices->opened = 0;
-- 
cgit v1.2.3


From 4306a97449f9a0f9e5229af7889d4401315355aa Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 29 May 2018 12:28:37 +0800
Subject: btrfs: do btrfs_free_stale_devices outside of device_list_add

btrfs_free_stale_devices() looks for device path reused for another
filesystem, and deletes the older fs_devices::device entry.

In preparation to handle locking in device_list_add, move
btrfs_free_stale_devices outside as these two functions serve a
different purpose.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3c3359d7e91d..c84a9e22daf1 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -747,7 +747,8 @@ error_brelse:
  * error pointer when failed
  */
 static noinline struct btrfs_device *device_list_add(const char *path,
-			   struct btrfs_super_block *disk_super)
+			   struct btrfs_super_block *disk_super,
+			   bool *new_device_added)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *fs_devices;
@@ -793,7 +794,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		mutex_unlock(&fs_devices->device_list_mutex);
 
 		device->fs_devices = fs_devices;
-		btrfs_free_stale_devices(path, device);
+		*new_device_added = true;
 
 		if (disk_super->label[0])
 			pr_info("BTRFS: device label %s devid %llu transid %llu %s\n",
@@ -1204,6 +1205,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 			  struct btrfs_fs_devices **fs_devices_ret)
 {
 	struct btrfs_super_block *disk_super;
+	bool new_device_added = false;
 	struct btrfs_device *device;
 	struct block_device *bdev;
 	struct page *page;
@@ -1229,11 +1231,14 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	}
 
 	mutex_lock(&uuid_mutex);
-	device = device_list_add(path, disk_super);
-	if (IS_ERR(device))
+	device = device_list_add(path, disk_super, &new_device_added);
+	if (IS_ERR(device)) {
 		ret = PTR_ERR(device);
-	else
+	} else {
 		*fs_devices_ret = device->fs_devices;
+		if (new_device_added)
+			btrfs_free_stale_devices(path, device);
+	}
 	mutex_unlock(&uuid_mutex);
 
 	btrfs_release_disk_super(page);
-- 
cgit v1.2.3


From 9c6d173ea6e4c8c939ae6c257c7fc18f7b320316 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 29 May 2018 14:10:20 +0800
Subject: btrfs: extend locked section when adding a new device in
 device_list_add

Make sure the device_list_lock is held the whole time:

* when the device is being looked up
* new device is initialized and put to the list
* the list counters are updated (fs_devices::opened, fs_devices::total_devices)

Signed-off-by: Anand Jain <anand.jain@oracle.com>
[ update changelog ]
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c84a9e22daf1..870732ef356c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -762,21 +762,26 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		if (IS_ERR(fs_devices))
 			return ERR_CAST(fs_devices);
 
+		mutex_lock(&fs_devices->device_list_mutex);
 		list_add(&fs_devices->fs_list, &fs_uuids);
 
 		device = NULL;
 	} else {
+		mutex_lock(&fs_devices->device_list_mutex);
 		device = find_device(fs_devices, devid,
 				disk_super->dev_item.uuid);
 	}
 
 	if (!device) {
-		if (fs_devices->opened)
+		if (fs_devices->opened) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EBUSY);
+		}
 
 		device = btrfs_alloc_device(NULL, &devid,
 					    disk_super->dev_item.uuid);
 		if (IS_ERR(device)) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			/* we can safely leave the fs_devices entry around */
 			return device;
 		}
@@ -784,14 +789,13 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 		name = rcu_string_strdup(path, GFP_NOFS);
 		if (!name) {
 			btrfs_free_device(device);
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-ENOMEM);
 		}
 		rcu_assign_pointer(device->name, name);
 
-		mutex_lock(&fs_devices->device_list_mutex);
 		list_add_rcu(&device->dev_list, &fs_devices->devices);
 		fs_devices->num_devices++;
-		mutex_unlock(&fs_devices->device_list_mutex);
 
 		device->fs_devices = fs_devices;
 		*new_device_added = true;
@@ -838,12 +842,15 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 			 * with larger generation number or the last-in if
 			 * generation are equal.
 			 */
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-EEXIST);
 		}
 
 		name = rcu_string_strdup(path, GFP_NOFS);
-		if (!name)
+		if (!name) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			return ERR_PTR(-ENOMEM);
+		}
 		rcu_string_free(device->name);
 		rcu_assign_pointer(device->name, name);
 		if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state)) {
@@ -863,6 +870,7 @@ static noinline struct btrfs_device *device_list_add(const char *path,
 
 	fs_devices->total_devices = btrfs_super_num_devices(disk_super);
 
+	mutex_unlock(&fs_devices->device_list_mutex);
 	return device;
 }
 
-- 
cgit v1.2.3


From fa6d2ae540a200a17bb7ee769f9df22d411c9404 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 29 May 2018 15:33:08 +0800
Subject: btrfs: rename local devices for fs_devices in
 btrfs_free_stale_devices(

Over the years we named %fs_devices and %devices to represent the
struct btrfs_fs_devices and the struct btrfs_device. So follow the same
scheme here too. No functional changes.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 35 +++++++++++++++++------------------
 1 file changed, 17 insertions(+), 18 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 870732ef356c..f4ce081bbe46 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -631,43 +631,42 @@ static void pending_bios_fn(struct btrfs_work *work)
  *		devices.
  */
 static void btrfs_free_stale_devices(const char *path,
-				     struct btrfs_device *skip_dev)
+				     struct btrfs_device *skip_device)
 {
-	struct btrfs_fs_devices *fs_devs, *tmp_fs_devs;
-	struct btrfs_device *dev, *tmp_dev;
+	struct btrfs_fs_devices *fs_devices, *tmp_fs_devices;
+	struct btrfs_device *device, *tmp_device;
 
-	list_for_each_entry_safe(fs_devs, tmp_fs_devs, &fs_uuids, fs_list) {
-
-		if (fs_devs->opened)
+	list_for_each_entry_safe(fs_devices, tmp_fs_devices, &fs_uuids, fs_list) {
+		if (fs_devices->opened)
 			continue;
 
-		list_for_each_entry_safe(dev, tmp_dev,
-					 &fs_devs->devices, dev_list) {
+		list_for_each_entry_safe(device, tmp_device,
+					 &fs_devices->devices, dev_list) {
 			int not_found = 0;
 
-			if (skip_dev && skip_dev == dev)
+			if (skip_device && skip_device == device)
 				continue;
-			if (path && !dev->name)
+			if (path && !device->name)
 				continue;
 
 			rcu_read_lock();
 			if (path)
-				not_found = strcmp(rcu_str_deref(dev->name),
+				not_found = strcmp(rcu_str_deref(device->name),
 						   path);
 			rcu_read_unlock();
 			if (not_found)
 				continue;
 
 			/* delete the stale device */
-			if (fs_devs->num_devices == 1) {
-				btrfs_sysfs_remove_fsid(fs_devs);
-				list_del(&fs_devs->fs_list);
-				free_fs_devices(fs_devs);
+			if (fs_devices->num_devices == 1) {
+				btrfs_sysfs_remove_fsid(fs_devices);
+				list_del(&fs_devices->fs_list);
+				free_fs_devices(fs_devices);
 				break;
 			} else {
-				fs_devs->num_devices--;
-				list_del(&dev->dev_list);
-				btrfs_free_device(dev);
+				fs_devices->num_devices--;
+				list_del(&device->dev_list);
+				btrfs_free_device(device);
 			}
 		}
 	}
-- 
cgit v1.2.3


From 7bcb8164ad9435068d9bc3b83b8a002c64d63ff6 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Tue, 29 May 2018 17:23:20 +0800
Subject: btrfs: use device_list_mutex when removing stale devices

btrfs_free_stale_devices() finds a stale (not opened) device matching
path in the fs_uuid list. We are already under uuid_mutex so when we
check for each fs_devices, hold the device_list_mutex too.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f4ce081bbe46..6a8f1e2c116f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -637,8 +637,11 @@ static void btrfs_free_stale_devices(const char *path,
 	struct btrfs_device *device, *tmp_device;
 
 	list_for_each_entry_safe(fs_devices, tmp_fs_devices, &fs_uuids, fs_list) {
-		if (fs_devices->opened)
+		mutex_lock(&fs_devices->device_list_mutex);
+		if (fs_devices->opened) {
+			mutex_unlock(&fs_devices->device_list_mutex);
 			continue;
+		}
 
 		list_for_each_entry_safe(device, tmp_device,
 					 &fs_devices->devices, dev_list) {
@@ -658,16 +661,18 @@ static void btrfs_free_stale_devices(const char *path,
 				continue;
 
 			/* delete the stale device */
-			if (fs_devices->num_devices == 1) {
-				btrfs_sysfs_remove_fsid(fs_devices);
-				list_del(&fs_devices->fs_list);
-				free_fs_devices(fs_devices);
+			fs_devices->num_devices--;
+			list_del(&device->dev_list);
+			btrfs_free_device(device);
+
+			if (fs_devices->num_devices == 0)
 				break;
-			} else {
-				fs_devices->num_devices--;
-				list_del(&device->dev_list);
-				btrfs_free_device(device);
-			}
+		}
+		mutex_unlock(&fs_devices->device_list_mutex);
+		if (fs_devices->num_devices == 0) {
+			btrfs_sysfs_remove_fsid(fs_devices);
+			list_del(&fs_devices->fs_list);
+			free_fs_devices(fs_devices);
 		}
 	}
 }
-- 
cgit v1.2.3


From 899f9307c33ce4758c30a076b10ed54d5c91c6e7 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 19 Jun 2018 16:37:36 +0200
Subject: btrfs: lift uuid_mutex to callers of btrfs_scan_one_device

Prepartory work to fix race between mount and device scan.

The callers will have to manage the critical section, eg. mount wants to
scan and then call btrfs_open_devices without the ioctl scan walking in
and modifying the fs devices in the meantime.

Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c   | 12 +++++++++++-
 fs/btrfs/volumes.c |  4 ++--
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 39d8e39b2fe1..0b6567f0c63d 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -915,8 +915,10 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 				error = -ENOMEM;
 				goto out;
 			}
+			mutex_lock(&uuid_mutex);
 			error = btrfs_scan_one_device(device_name,
 					flags, holder, fs_devices);
+			mutex_unlock(&uuid_mutex);
 			kfree(device_name);
 			if (error)
 				goto out;
@@ -1537,7 +1539,9 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 			return ERR_PTR(error);
 	}
 
+	mutex_lock(&uuid_mutex);
 	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
+	mutex_unlock(&uuid_mutex);
 	if (error)
 		goto error_sec_opts;
 
@@ -2232,15 +2236,21 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
+		mutex_lock(&uuid_mutex);
 		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
 					    &btrfs_root_fs_type, &fs_devices);
+		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_DEVICES_READY:
+		mutex_lock(&uuid_mutex);
 		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
 					    &btrfs_root_fs_type, &fs_devices);
-		if (ret)
+		if (ret) {
+			mutex_unlock(&uuid_mutex);
 			break;
+		}
 		ret = !(fs_devices->num_devices == fs_devices->total_devices);
+		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
 		ret = btrfs_ioctl_get_supported_features((void __user*)arg);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 6a8f1e2c116f..df5dd6f67887 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1224,6 +1224,8 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 	int ret = 0;
 	u64 bytenr;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	/*
 	 * we would like to check all the supers, but that would make
 	 * a btrfs mount succeed after a mkfs from a different FS.
@@ -1242,7 +1244,6 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 		goto error_bdev_put;
 	}
 
-	mutex_lock(&uuid_mutex);
 	device = device_list_add(path, disk_super, &new_device_added);
 	if (IS_ERR(device)) {
 		ret = PTR_ERR(device);
@@ -1251,7 +1252,6 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 		if (new_device_added)
 			btrfs_free_stale_devices(path, device);
 	}
-	mutex_unlock(&uuid_mutex);
 
 	btrfs_release_disk_super(page);
 
-- 
cgit v1.2.3


From f5194e34cabaddd348a90f950e0a8188dd26cdc0 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 19 Jun 2018 17:09:47 +0200
Subject: btrfs: lift uuid_mutex to callers of btrfs_open_devices

Prepartory work to fix race between mount and device scan.

The callers will have to manage the critical section, eg. mount wants to
scan and then call btrfs_open_devices without the ioctl scan walking in
and modifying the fs devices in the meantime.

Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c   | 2 ++
 fs/btrfs/volumes.c | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 0b6567f0c63d..d470eb6b9226 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1567,7 +1567,9 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_fs_info;
 	}
 
+	mutex_lock(&uuid_mutex);
 	error = btrfs_open_devices(fs_devices, mode, fs_type);
+	mutex_unlock(&uuid_mutex);
 	if (error)
 		goto error_fs_info;
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index df5dd6f67887..459cc2a2a31c 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1142,7 +1142,8 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 {
 	int ret;
 
-	mutex_lock(&uuid_mutex);
+	lockdep_assert_held(&uuid_mutex);
+
 	mutex_lock(&fs_devices->device_list_mutex);
 	if (fs_devices->opened) {
 		fs_devices->opened++;
@@ -1152,7 +1153,6 @@ int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		ret = open_fs_devices(fs_devices, flags, holder);
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
-	mutex_unlock(&uuid_mutex);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 5139cff598d42b1e531f40c84691a7e945f04553 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 19 Jun 2018 17:50:25 +0200
Subject: btrfs: lift uuid_mutex to callers of btrfs_parse_early_options

Prepartory work to fix race between mount and device scan.

btrfs_parse_early_options calls the device scan from mount and we'll
need to let mount completely manage the critical section.

Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d470eb6b9226..de87b7b0367d 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -890,6 +890,8 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 	char *device_name, *opts, *orig, *p;
 	int error = 0;
 
+	lockdep_assert_held(&uuid_mutex);
+
 	if (!options)
 		return 0;
 
@@ -915,10 +917,8 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 				error = -ENOMEM;
 				goto out;
 			}
-			mutex_lock(&uuid_mutex);
 			error = btrfs_scan_one_device(device_name,
 					flags, holder, fs_devices);
-			mutex_unlock(&uuid_mutex);
 			kfree(device_name);
 			if (error)
 				goto out;
@@ -1526,8 +1526,10 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
+	mutex_lock(&uuid_mutex);
 	error = btrfs_parse_early_options(data, mode, fs_type,
 					  &fs_devices);
+	mutex_unlock(&uuid_mutex);
 	if (error) {
 		return ERR_PTR(error);
 	}
-- 
cgit v1.2.3


From 399f7f4c42e8a58c8456264d5112287aefe44cf4 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 19 Jun 2018 18:01:24 +0200
Subject: btrfs: reorder initialization before the mount locks uuid_mutex

In preparation to take a big lock, move resource initialization before
the critical section. It's not obvious from the diff, the desired order
is:

- initialize mount security options
- allocate temporary fs_info
- allocate superblock buffers

Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 30 ++++++++++++++----------------
 1 file changed, 14 insertions(+), 16 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index de87b7b0367d..d33fc1fc4285 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1526,14 +1526,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	if (!(flags & SB_RDONLY))
 		mode |= FMODE_WRITE;
 
-	mutex_lock(&uuid_mutex);
-	error = btrfs_parse_early_options(data, mode, fs_type,
-					  &fs_devices);
-	mutex_unlock(&uuid_mutex);
-	if (error) {
-		return ERR_PTR(error);
-	}
-
 	security_init_mnt_opts(&new_sec_opts);
 	if (data) {
 		error = parse_security_options(data, &new_sec_opts);
@@ -1541,12 +1533,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 			return ERR_PTR(error);
 	}
 
-	mutex_lock(&uuid_mutex);
-	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
-	mutex_unlock(&uuid_mutex);
-	if (error)
-		goto error_sec_opts;
-
 	/*
 	 * Setup a dummy root and fs_info for test/set super.  This is because
 	 * we don't actually fill this stuff out until open_ctree, but we need
@@ -1559,8 +1545,6 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_sec_opts;
 	}
 
-	fs_info->fs_devices = fs_devices;
-
 	fs_info->super_copy = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	fs_info->super_for_commit = kzalloc(BTRFS_SUPER_INFO_SIZE, GFP_KERNEL);
 	security_init_mnt_opts(&fs_info->security_opts);
@@ -1569,6 +1553,20 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_fs_info;
 	}
 
+	mutex_lock(&uuid_mutex);
+	error = btrfs_parse_early_options(data, mode, fs_type, &fs_devices);
+	mutex_unlock(&uuid_mutex);
+	if (error)
+		goto error_fs_info;
+
+	mutex_lock(&uuid_mutex);
+	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
+	mutex_unlock(&uuid_mutex);
+	if (error)
+		goto error_fs_info;
+
+	fs_info->fs_devices = fs_devices;
+
 	mutex_lock(&uuid_mutex);
 	error = btrfs_open_devices(fs_devices, mode, fs_type);
 	mutex_unlock(&uuid_mutex);
-- 
cgit v1.2.3


From 81ffd56b5745355b70d54ca4e1bdd0d64a66ff9f Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 19 Jun 2018 18:04:07 +0200
Subject: btrfs: fix mount and ioctl device scan ioctl race

Technically this extends the critical section covered by uuid_mutex to:

- parse early mount options -- here we can call device scan on paths
  that can be passed as 'device=/dev/...'

- scan the device passed to mount

- open the devices related to the fs_devices -- this increases
  fs_devices::opened

The race can happen when mount calls one of the scans and there's
another one called eg. by mkfs or 'btrfs dev scan':

Mount                                  Scan
-----                                  ----
scan_one_device (dev1, fsid1)
                                       scan_one_device (dev2, fsid1)
				           add the device
					   free stale devices
					       fsid1 fs_devices::opened == 0
					           find fsid1:dev1
					           free fsid1:dev1
					           if it's the last one,
					            free fs_devices of fsid1
						    too

open_devices (dev1, fsid1)
   dev1 not found

When fixed, the uuid mutex will make sure that mount will increase
fs_devices::opened and this will not be touched by the racing scan
ioctl.

Reported-and-tested-by: syzbot+909a5177749d7990ffa4@syzkaller.appspotmail.com
Reported-and-tested-by: syzbot+ceb2606025ec1cc3479c@syzkaller.appspotmail.com
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d33fc1fc4285..28ab75ebb983 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1555,19 +1555,19 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 
 	mutex_lock(&uuid_mutex);
 	error = btrfs_parse_early_options(data, mode, fs_type, &fs_devices);
-	mutex_unlock(&uuid_mutex);
-	if (error)
+	if (error) {
+		mutex_unlock(&uuid_mutex);
 		goto error_fs_info;
+	}
 
-	mutex_lock(&uuid_mutex);
 	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
-	mutex_unlock(&uuid_mutex);
-	if (error)
+	if (error) {
+		mutex_unlock(&uuid_mutex);
 		goto error_fs_info;
+	}
 
 	fs_info->fs_devices = fs_devices;
 
-	mutex_lock(&uuid_mutex);
 	error = btrfs_open_devices(fs_devices, mode, fs_type);
 	mutex_unlock(&uuid_mutex);
 	if (error)
-- 
cgit v1.2.3


From d64dcbd183abab251beb0fa0acd81a772a09887e Mon Sep 17 00:00:00 2001
From: Gu Jinxiang <gujx@cn.fujitsu.com>
Date: Thu, 12 Jul 2018 14:23:15 +0800
Subject: btrfs: make fs_devices a local variable in btrfs_parse_early_options

fs_devices is always passed to btrfs_scan_one_device which overrides it.
In the call stack below fs_devices is passed to btrfs_scan_one_device
from btrfs_mount_root.  In btrfs_mount_root the output fs_devices of
this call stack is not used.

btrfs_mount_root
  btrfs_parse_early_options
    btrfs_scan_one_device

So, it is not necessary to pass fs_devices from btrfs_mount_root, using
a local variable in btrfs_parse_early_options is enough.

Signed-off-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: Anand Jain <Anand.Jain@oracle.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 28ab75ebb983..909ea2564e84 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -884,10 +884,11 @@ out:
  * only when we need to allocate a new super block.
  */
 static int btrfs_parse_early_options(const char *options, fmode_t flags,
-		void *holder, struct btrfs_fs_devices **fs_devices)
+				     void *holder)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
+	struct btrfs_fs_devices *fs_devices = NULL;
 	int error = 0;
 
 	lockdep_assert_held(&uuid_mutex);
@@ -918,7 +919,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 				goto out;
 			}
 			error = btrfs_scan_one_device(device_name,
-					flags, holder, fs_devices);
+					flags, holder, &fs_devices);
 			kfree(device_name);
 			if (error)
 				goto out;
@@ -1554,7 +1555,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	}
 
 	mutex_lock(&uuid_mutex);
-	error = btrfs_parse_early_options(data, mode, fs_type, &fs_devices);
+	error = btrfs_parse_early_options(data, mode, fs_type);
 	if (error) {
 		mutex_unlock(&uuid_mutex);
 		goto error_fs_info;
-- 
cgit v1.2.3


From 36350e95a2b1feed6382fe38cc80f79ec35a1323 Mon Sep 17 00:00:00 2001
From: Gu Jinxiang <gujx@cn.fujitsu.com>
Date: Thu, 12 Jul 2018 14:23:16 +0800
Subject: btrfs: return device pointer from btrfs_scan_one_device

Return device pointer (with the IS_ERR semantics) from
btrfs_scan_one_device so we don't have to return in through pointer.

And since btrfs_fs_devices can be obtained from btrfs_device, return that.

Signed-off-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ fixed conflics after recent changes to btrfs_scan_one_device ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c   | 34 +++++++++++++++++++++-------------
 fs/btrfs/volumes.c | 18 +++++++-----------
 fs/btrfs/volumes.h |  4 ++--
 3 files changed, 30 insertions(+), 26 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 909ea2564e84..5384afae3364 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -888,7 +888,7 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
-	struct btrfs_fs_devices *fs_devices = NULL;
+	struct btrfs_device *device = NULL;
 	int error = 0;
 
 	lockdep_assert_held(&uuid_mutex);
@@ -918,11 +918,13 @@ static int btrfs_parse_early_options(const char *options, fmode_t flags,
 				error = -ENOMEM;
 				goto out;
 			}
-			error = btrfs_scan_one_device(device_name,
-					flags, holder, &fs_devices);
+			device = btrfs_scan_one_device(device_name, flags,
+					holder);
 			kfree(device_name);
-			if (error)
+			if (IS_ERR(device)) {
+				error = PTR_ERR(device);
 				goto out;
+			}
 		}
 	}
 
@@ -1518,6 +1520,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 {
 	struct block_device *bdev = NULL;
 	struct super_block *s;
+	struct btrfs_device *device = NULL;
 	struct btrfs_fs_devices *fs_devices = NULL;
 	struct btrfs_fs_info *fs_info = NULL;
 	struct security_mnt_opts new_sec_opts;
@@ -1561,12 +1564,14 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 		goto error_fs_info;
 	}
 
-	error = btrfs_scan_one_device(device_name, mode, fs_type, &fs_devices);
-	if (error) {
+	device = btrfs_scan_one_device(device_name, mode, fs_type);
+	if (IS_ERR(device)) {
 		mutex_unlock(&uuid_mutex);
+		error = PTR_ERR(device);
 		goto error_fs_info;
 	}
 
+	fs_devices = device->fs_devices;
 	fs_info->fs_devices = fs_devices;
 
 	error = btrfs_open_devices(fs_devices, mode, fs_type);
@@ -2227,7 +2232,7 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 				unsigned long arg)
 {
 	struct btrfs_ioctl_vol_args *vol;
-	struct btrfs_fs_devices *fs_devices;
+	struct btrfs_device *device = NULL;
 	int ret = -ENOTTY;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -2240,19 +2245,22 @@ static long btrfs_control_ioctl(struct file *file, unsigned int cmd,
 	switch (cmd) {
 	case BTRFS_IOC_SCAN_DEV:
 		mutex_lock(&uuid_mutex);
-		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_root_fs_type, &fs_devices);
+		device = btrfs_scan_one_device(vol->name, FMODE_READ,
+					       &btrfs_root_fs_type);
+		ret = PTR_ERR_OR_ZERO(device);
 		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_DEVICES_READY:
 		mutex_lock(&uuid_mutex);
-		ret = btrfs_scan_one_device(vol->name, FMODE_READ,
-					    &btrfs_root_fs_type, &fs_devices);
-		if (ret) {
+		device = btrfs_scan_one_device(vol->name, FMODE_READ,
+					       &btrfs_root_fs_type);
+		if (IS_ERR(device)) {
 			mutex_unlock(&uuid_mutex);
+			ret = PTR_ERR(device);
 			break;
 		}
-		ret = !(fs_devices->num_devices == fs_devices->total_devices);
+		ret = !(device->fs_devices->num_devices ==
+			device->fs_devices->total_devices);
 		mutex_unlock(&uuid_mutex);
 		break;
 	case BTRFS_IOC_GET_SUPPORTED_FEATURES:
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 459cc2a2a31c..fd9d4e056b37 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1213,15 +1213,14 @@ static int btrfs_read_disk_super(struct block_device *bdev, u64 bytenr,
  * and we are not allowed to call set_blocksize during the scan. The superblock
  * is read via pagecache
  */
-int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
-			  struct btrfs_fs_devices **fs_devices_ret)
+struct btrfs_device *btrfs_scan_one_device(const char *path, fmode_t flags,
+					   void *holder)
 {
 	struct btrfs_super_block *disk_super;
 	bool new_device_added = false;
-	struct btrfs_device *device;
+	struct btrfs_device *device = NULL;
 	struct block_device *bdev;
 	struct page *page;
-	int ret = 0;
 	u64 bytenr;
 
 	lockdep_assert_held(&uuid_mutex);
@@ -1237,18 +1236,15 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 
 	bdev = blkdev_get_by_path(path, flags, holder);
 	if (IS_ERR(bdev))
-		return PTR_ERR(bdev);
+		return ERR_CAST(bdev);
 
 	if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super)) {
-		ret = -EINVAL;
+		device = ERR_PTR(-EINVAL);
 		goto error_bdev_put;
 	}
 
 	device = device_list_add(path, disk_super, &new_device_added);
-	if (IS_ERR(device)) {
-		ret = PTR_ERR(device);
-	} else {
-		*fs_devices_ret = device->fs_devices;
+	if (!IS_ERR(device)) {
 		if (new_device_added)
 			btrfs_free_stale_devices(path, device);
 	}
@@ -1258,7 +1254,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
 error_bdev_put:
 	blkdev_put(bdev, flags);
 
-	return ret;
+	return device;
 }
 
 static int contains_pending_extent(struct btrfs_transaction *transaction,
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 9665b84b1026..06d8bb7dd557 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -403,8 +403,8 @@ blk_status_t btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			   int mirror_num, int async_submit);
 int btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		       fmode_t flags, void *holder);
-int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
-			  struct btrfs_fs_devices **fs_devices_ret);
+struct btrfs_device *btrfs_scan_one_device(const char *path,
+					   fmode_t flags, void *holder);
 int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
 void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step);
 void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
-- 
cgit v1.2.3


From d814a49198eafa6163698bdd93961302f3a877a4 Mon Sep 17 00:00:00 2001
From: Ethan Lien <ethanlien@synology.com>
Date: Mon, 2 Jul 2018 15:44:58 +0800
Subject: btrfs: use correct compare function of dirty_metadata_bytes

We use customized, nodesize batch value to update dirty_metadata_bytes.
We should also use batch version of compare function or we will easily
goto fast path and get false result from percpu_counter_compare().

Fixes: e2d845211eda ("Btrfs: use percpu counter for dirty metadata count")
CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Ethan Lien <ethanlien@synology.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6023eed3e805..e3858b2fe014 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -959,8 +959,9 @@ static int btree_writepages(struct address_space *mapping,
 
 		fs_info = BTRFS_I(mapping->host)->root->fs_info;
 		/* this is a bit racy, but that's ok */
-		ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
-					     BTRFS_DIRTY_METADATA_THRESH);
+		ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
+					     BTRFS_DIRTY_METADATA_THRESH,
+					     fs_info->dirty_metadata_batch);
 		if (ret < 0)
 			return 0;
 	}
@@ -4134,8 +4135,9 @@ static void __btrfs_btree_balance_dirty(struct btrfs_fs_info *fs_info,
 	if (flush_delayed)
 		btrfs_balance_delayed_items(fs_info);
 
-	ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
-				     BTRFS_DIRTY_METADATA_THRESH);
+	ret = __percpu_counter_compare(&fs_info->dirty_metadata_bytes,
+				     BTRFS_DIRTY_METADATA_THRESH,
+				     fs_info->dirty_metadata_batch);
 	if (ret > 0) {
 		balance_dirty_pages_ratelimited(fs_info->btree_inode->i_mapping);
 	}
-- 
cgit v1.2.3


From dec59fa3a760952fc71f2e122e66a7291109670a Mon Sep 17 00:00:00 2001
From: Ethan Lien <ethanlien@synology.com>
Date: Fri, 13 Jul 2018 16:50:42 +0800
Subject: btrfs: use customized batch size for total_bytes_pinned

In commit b150a4f10d878 ("Btrfs: use a percpu to keep track of possibly
pinned bytes") we use total_bytes_pinned to track how many bytes we are
going to free in this transaction. When we are close to ENOSPC, we check it
and know if we can make the allocation by commit the current transaction.
For every data/metadata extent we are going to free, we add
total_bytes_pinned in btrfs_free_extent() and btrfs_free_tree_block(), and
release it in unpin_extent_range() when we finish the transaction. So this
is a variable we frequently update but rarely read - just the suitable
use of percpu_counter. But in previous commit we update total_bytes_pinned
by default 32 batch size, making every update essentially a spin lock
protected update. Since every spin lock/unlock operation involves syncing
a globally used variable and some kind of barrier in a SMP system, this is
more expensive than using total_bytes_pinned as a simple atomic64_t.

So fix this by using a customized batch size. Since we only read
total_bytes_pinned when we are close to ENOSPC and fail to allocate new
chunk, we can use a really large batch size and have nearly no penalty
in most cases.

[Test]
We tested the patch on a 4-cores x86 machine:

1. fallocate a 16GiB size test file
2. take snapshot (so all following writes will be COW)
3. run a 180 sec, 4 jobs, 4K random write fio on test file

We also added a temporary lockdep class on percpu_counter's spin lock
used by total_bytes_pinned to track it by lock_stat.

[Results]
unpatched:
lock_stat version 0.4
-----------------------------------------------------------------------
                              class name    con-bounces    contentions
waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces
acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg

               total_bytes_pinned_percpu:            82             82
        0.21           0.61          29.46           0.36         298340
      635973           0.09          11.01      173476.25           0.27

patched:
lock_stat version 0.4
-----------------------------------------------------------------------
                              class name    con-bounces    contentions
waittime-min   waittime-max waittime-total   waittime-avg    acq-bounces
acquisitions   holdtime-min   holdtime-max holdtime-total   holdtime-avg

               total_bytes_pinned_percpu:             1              1
        0.62           0.62           0.62           0.62          13601
       31542           0.14           9.61       11016.90           0.35

[Analysis]
Since the spin lock only protects a single in-memory variable, the
contentions (number of lock acquisitions that had to wait) in both
unpatched and patched version are low. But when we see acquisitions and
acq-bounces, we get much lower counts in patched version. Here the most
important metric is acq-bounces. It means how many times the lock gets
transferred between different cpus, so the patch can really reduce
cacheline bouncing of spin lock (also the global counter of percpu_counter)
in a SMP system.

Fixes: b150a4f10d878 ("Btrfs: use a percpu to keep track of possibly pinned bytes")
Signed-off-by: Ethan Lien <ethanlien@synology.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  8 ++++++++
 fs/btrfs/extent-tree.c | 39 ++++++++++++++++++++++++---------------
 2 files changed, 32 insertions(+), 15 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 427ca5de8542..bf1451bf3ed7 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -84,6 +84,14 @@ static const int btrfs_csum_sizes[] = { 4 };
 
 #define BTRFS_DIRTY_METADATA_THRESH	SZ_32M
 
+/*
+ * Use large batch size to reduce overhead of metadata updates.  On the reader
+ * side, we only read it when we are close to ENOSPC and the read overhead is
+ * mostly related to the number of CPUs, so it is OK to use arbitrary large
+ * value here.
+ */
+#define BTRFS_TOTAL_BYTES_PINNED_BATCH	SZ_128M
+
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 6bba288133b8..2d1f893902f1 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -755,7 +755,8 @@ static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes,
 
 	space_info = __find_space_info(fs_info, flags);
 	ASSERT(space_info);
-	percpu_counter_add(&space_info->total_bytes_pinned, num_bytes);
+	percpu_counter_add_batch(&space_info->total_bytes_pinned, num_bytes,
+		    BTRFS_TOTAL_BYTES_PINNED_BATCH);
 }
 
 /*
@@ -2473,8 +2474,9 @@ static int cleanup_ref_head(struct btrfs_trans_handle *trans,
 			flags = BTRFS_BLOCK_GROUP_METADATA;
 		space_info = __find_space_info(fs_info, flags);
 		ASSERT(space_info);
-		percpu_counter_add(&space_info->total_bytes_pinned,
-				   -head->num_bytes);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+				   -head->num_bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 
 		if (head->is_data) {
 			spin_lock(&delayed_refs->lock);
@@ -4178,9 +4180,10 @@ again:
 		 * allocation, and no removed chunk in current transaction,
 		 * don't bother committing the transaction.
 		 */
-		have_pinned_space = percpu_counter_compare(
+		have_pinned_space = __percpu_counter_compare(
 			&data_sinfo->total_bytes_pinned,
-			used + bytes - data_sinfo->total_bytes);
+			used + bytes - data_sinfo->total_bytes,
+			BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		spin_unlock(&data_sinfo->lock);
 
 		/* commit the current transaction and try again */
@@ -4782,8 +4785,9 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		return 0;
 
 	/* See if there is enough pinned space to make this reservation */
-	if (percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes) >= 0)
+	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
+				   bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH) >= 0)
 		goto commit;
 
 	/*
@@ -4800,8 +4804,9 @@ static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 		bytes -= delayed_rsv->size;
 	spin_unlock(&delayed_rsv->lock);
 
-	if (percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes) < 0) {
+	if (__percpu_counter_compare(&space_info->total_bytes_pinned,
+				   bytes,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH) < 0) {
 		return -ENOSPC;
 	}
 
@@ -6138,8 +6143,9 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			trace_btrfs_space_reservation(info, "pinned",
 						      cache->space_info->flags,
 						      num_bytes, 1);
-			percpu_counter_add(&cache->space_info->total_bytes_pinned,
-					   num_bytes);
+			percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
+					   num_bytes,
+					   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 			set_extent_dirty(info->pinned_extents,
 					 bytenr, bytenr + num_bytes - 1,
 					 GFP_NOFS | __GFP_NOFAIL);
@@ -6217,7 +6223,8 @@ static int pin_down_extent(struct btrfs_fs_info *fs_info,
 
 	trace_btrfs_space_reservation(fs_info, "pinned",
 				      cache->space_info->flags, num_bytes, 1);
-	percpu_counter_add(&cache->space_info->total_bytes_pinned, num_bytes);
+	percpu_counter_add_batch(&cache->space_info->total_bytes_pinned,
+		    num_bytes, BTRFS_TOTAL_BYTES_PINNED_BATCH);
 	set_extent_dirty(fs_info->pinned_extents, bytenr,
 			 bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL);
 	return 0;
@@ -6581,7 +6588,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
 		trace_btrfs_space_reservation(fs_info, "pinned",
 					      space_info->flags, len, 0);
 		space_info->max_extent_size = 0;
-		percpu_counter_add(&space_info->total_bytes_pinned, -len);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+			    -len, BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		if (cache->ro) {
 			space_info->bytes_readonly += len;
 			readonly = true;
@@ -10603,8 +10611,9 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 
 		space_info->bytes_pinned -= block_group->pinned;
 		space_info->bytes_readonly += block_group->pinned;
-		percpu_counter_add(&space_info->total_bytes_pinned,
-				   -block_group->pinned);
+		percpu_counter_add_batch(&space_info->total_bytes_pinned,
+				   -block_group->pinned,
+				   BTRFS_TOTAL_BYTES_PINNED_BATCH);
 		block_group->pinned = 0;
 
 		spin_unlock(&block_group->lock);
-- 
cgit v1.2.3


From 2556fbb0bead7929ddf67f8b4184f434cee4e7d7 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 18 Apr 2018 10:27:57 +0300
Subject: btrfs: Rewrite retry logic in do_chunk_alloc

do_chunk_alloc implements logic to detect whether there is currently
pending chunk allocation (by means of space_info->chunk_alloc being
set) and if so it loops around to the 'again' label. Additionally,
based on the state of the space_info (e.g. whether it's full or not)
and the return value of should_alloc_chunk() it decides whether this
is a "hard" error (ENOSPC) or we can just return 0.

This patch refactors all of this:

1. Put order to the scattered ifs handling the various cases in an
easy-to-read if {} else if{} branches. This makes clear the various
cases we are interested in handling.

2. Call should_alloc_chunk only once and use the result in the
if/else if constructs. All of this is done under space_info->lock, so
even before multiple calls of should_alloc_chunk were unnecessary.

3. Rewrite the "do {} while()" loop currently implemented via label
into an explicit loop construct.

4. Move the mutex locking for the case where the caller is the one doing
the allocation. For the case where the caller needs to wait a concurrent
allocation, introduce a pair of mutex_lock/mutex_unlock to act as a
barrier and reword the comment.

5. Switch local vars to bool type where pertinent.

All in all this shouldn't introduce any functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 74 +++++++++++++++++++++++++-------------------------
 1 file changed, 37 insertions(+), 37 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2d1f893902f1..bbd756223b23 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4450,7 +4450,8 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 {
 	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_space_info *space_info;
-	int wait_for_alloc = 0;
+	bool wait_for_alloc = false;
+	bool should_alloc = false;
 	int ret = 0;
 
 	/* Don't re-enter if we're already allocating a chunk */
@@ -4460,45 +4461,44 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans, u64 flags,
 	space_info = __find_space_info(fs_info, flags);
 	ASSERT(space_info);
 
-again:
-	spin_lock(&space_info->lock);
-	if (force < space_info->force_alloc)
-		force = space_info->force_alloc;
-	if (space_info->full) {
-		if (should_alloc_chunk(fs_info, space_info, force))
-			ret = -ENOSPC;
-		else
-			ret = 0;
-		spin_unlock(&space_info->lock);
-		return ret;
-	}
-
-	if (!should_alloc_chunk(fs_info, space_info, force)) {
-		spin_unlock(&space_info->lock);
-		return 0;
-	} else if (space_info->chunk_alloc) {
-		wait_for_alloc = 1;
-	} else {
-		space_info->chunk_alloc = 1;
-	}
-
-	spin_unlock(&space_info->lock);
-
-	mutex_lock(&fs_info->chunk_mutex);
+	do {
+		spin_lock(&space_info->lock);
+		if (force < space_info->force_alloc)
+			force = space_info->force_alloc;
+		should_alloc = should_alloc_chunk(fs_info, space_info, force);
+		if (space_info->full) {
+			/* No more free physical space */
+			if (should_alloc)
+				ret = -ENOSPC;
+			else
+				ret = 0;
+			spin_unlock(&space_info->lock);
+			return ret;
+		} else if (!should_alloc) {
+			spin_unlock(&space_info->lock);
+			return 0;
+		} else if (space_info->chunk_alloc) {
+			/*
+			 * Someone is already allocating, so we need to block
+			 * until this someone is finished and then loop to
+			 * recheck if we should continue with our allocation
+			 * attempt.
+			 */
+			wait_for_alloc = true;
+			spin_unlock(&space_info->lock);
+			mutex_lock(&fs_info->chunk_mutex);
+			mutex_unlock(&fs_info->chunk_mutex);
+		} else {
+			/* Proceed with allocation */
+			space_info->chunk_alloc = 1;
+			wait_for_alloc = false;
+			spin_unlock(&space_info->lock);
+		}
 
-	/*
-	 * The chunk_mutex is held throughout the entirety of a chunk
-	 * allocation, so once we've acquired the chunk_mutex we know that the
-	 * other guy is done and we need to recheck and see if we should
-	 * allocate.
-	 */
-	if (wait_for_alloc) {
-		mutex_unlock(&fs_info->chunk_mutex);
-		wait_for_alloc = 0;
 		cond_resched();
-		goto again;
-	}
+	} while (wait_for_alloc);
 
+	mutex_lock(&fs_info->chunk_mutex);
 	trans->allocating_chunk = true;
 
 	/*
-- 
cgit v1.2.3


From 031f24da2c8a7b611331c368d7bfabccafda09fa Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Tue, 22 May 2018 16:43:47 +0800
Subject: btrfs: Use btrfs_mark_bg_unused to replace open code

Introduce a small helper, btrfs_mark_bg_unused(), to acquire locks and
add a block group to unused_bgs list.

No functional modification, and only 3 callers are involved.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       |  1 +
 fs/btrfs/extent-tree.c | 36 +++++++++++++++++-------------------
 fs/btrfs/scrub.c       |  9 +--------
 3 files changed, 19 insertions(+), 27 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index bf1451bf3ed7..ee1e152cb94b 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2801,6 +2801,7 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
 void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
 u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		       u64 start, u64 end);
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
 
 /* ctree.c */
 int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index bbd756223b23..ced26ba8d392 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -6166,16 +6166,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		 * dirty list to avoid races between cleaner kthread and space
 		 * cache writeout.
 		 */
-		if (!alloc && old_val == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
-		}
+		if (!alloc && old_val == 0)
+			btrfs_mark_bg_unused(cache);
 
 		btrfs_put_block_group(cache);
 		total -= num_bytes;
@@ -9987,15 +9979,8 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		if (btrfs_chunk_readonly(info, cache->key.objectid)) {
 			inc_block_group_ro(cache, 1);
 		} else if (btrfs_block_group_used(&cache->item) == 0) {
-			spin_lock(&info->unused_bgs_lock);
-			/* Should always be true but just in case. */
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &info->unused_bgs);
-			}
-			spin_unlock(&info->unused_bgs_lock);
+			ASSERT(list_empty(&cache->bg_list));
+			btrfs_mark_bg_unused(cache);
 		}
 	}
 
@@ -10914,3 +10899,16 @@ void btrfs_wait_for_snapshot_creation(struct btrfs_root *root)
 			       !atomic_read(&root->will_be_snapshotted));
 	}
 }
+
+void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg)
+{
+	struct btrfs_fs_info *fs_info = bg->fs_info;
+
+	spin_lock(&fs_info->unused_bgs_lock);
+	if (list_empty(&bg->bg_list)) {
+		btrfs_get_block_group(bg);
+		trace_btrfs_add_unused_block_group(bg);
+		list_add_tail(&bg->bg_list, &fs_info->unused_bgs);
+	}
+	spin_unlock(&fs_info->unused_bgs_lock);
+}
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index bf4f262f9a52..1235ad8dd9d7 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3951,14 +3951,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		if (!cache->removed && !cache->ro && cache->reserved == 0 &&
 		    btrfs_block_group_used(&cache->item) == 0) {
 			spin_unlock(&cache->lock);
-			spin_lock(&fs_info->unused_bgs_lock);
-			if (list_empty(&cache->bg_list)) {
-				btrfs_get_block_group(cache);
-				trace_btrfs_add_unused_block_group(cache);
-				list_add_tail(&cache->bg_list,
-					      &fs_info->unused_bgs);
-			}
-			spin_unlock(&fs_info->unused_bgs_lock);
+			btrfs_mark_bg_unused(cache);
 		} else {
 			spin_unlock(&cache->lock);
 		}
-- 
cgit v1.2.3


From c8389d4c0d6eb7c0b7f8b8a98620874f9123cd20 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Tue, 17 Jul 2018 16:58:22 +0800
Subject: btrfs: qgroup: cleanup the unused srcroot from btrfs_qgroup_inherit

Since commit 0b246afa62b0 ("btrfs: root->fs_info cleanup, add fs_info
convenience variables"), the srcroot is no longer used to get
fs_info::nodesize.  In fact, it can be dropped after commit 707e8a071528
("btrfs: use nodesize everywhere, kill leafsize").

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 17 +----------------
 1 file changed, 1 insertion(+), 16 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 97a59a444500..e0bd48c5a98b 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2287,22 +2287,6 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	if (srcid) {
-		struct btrfs_root *srcroot;
-		struct btrfs_key srckey;
-
-		srckey.objectid = srcid;
-		srckey.type = BTRFS_ROOT_ITEM_KEY;
-		srckey.offset = (u64)-1;
-		srcroot = btrfs_read_fs_root_no_name(fs_info, &srckey);
-		if (IS_ERR(srcroot)) {
-			ret = PTR_ERR(srcroot);
-			goto out;
-		}
-
-		level_size = fs_info->nodesize;
-	}
-
 	/*
 	 * add qgroup to all inherited groups
 	 */
@@ -2359,6 +2343,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		 * our counts don't go crazy, so at this point the only
 		 * difference between the two roots should be the root node.
 		 */
+		level_size = fs_info->nodesize;
 		dstgroup->rfer = srcgroup->rfer;
 		dstgroup->rfer_cmpr = srcgroup->rfer_cmpr;
 		dstgroup->excl = level_size;
-- 
cgit v1.2.3


From fa59f27c8c35bbe00af8eff23de446a7f4b048b0 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Mon, 16 Jul 2018 22:18:07 +0800
Subject: btrfs: rename btrfs_parse_early_options

Rename btrfs_parse_early_options() to btrfs_parse_device_options(). As
btrfs_parse_early_options() parses the -o device options and scan the
device provided. So this rename specifies its action. Also the function
name is in line with btrfs_parse_subvol_options().
No functional changes.

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/super.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 5384afae3364..d7a54c648c5f 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -465,9 +465,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_subvolrootid:
 		case Opt_device:
 			/*
-			 * These are parsed by btrfs_parse_subvol_options
-			 * and btrfs_parse_early_options
-			 * and can be happily ignored here.
+			 * These are parsed by btrfs_parse_subvol_options or
+			 * btrfs_parse_device_options and can be ignored here.
 			 */
 			break;
 		case Opt_nodatasum:
@@ -883,8 +882,8 @@ out:
  * All other options will be parsed on much later in the mount process and
  * only when we need to allocate a new super block.
  */
-static int btrfs_parse_early_options(const char *options, fmode_t flags,
-				     void *holder)
+static int btrfs_parse_device_options(const char *options, fmode_t flags,
+				      void *holder)
 {
 	substring_t args[MAX_OPT_ARGS];
 	char *device_name, *opts, *orig, *p;
@@ -951,7 +950,7 @@ static int btrfs_parse_subvol_options(const char *options, char **subvol_name,
 
 	/*
 	 * strsep changes the string, duplicate it because
-	 * btrfs_parse_early_options gets called later
+	 * btrfs_parse_device_options gets called later
 	 */
 	opts = kstrdup(options, GFP_KERNEL);
 	if (!opts)
@@ -1558,7 +1557,7 @@ static struct dentry *btrfs_mount_root(struct file_system_type *fs_type,
 	}
 
 	mutex_lock(&uuid_mutex);
-	error = btrfs_parse_early_options(data, mode, fs_type);
+	error = btrfs_parse_device_options(data, mode, fs_type);
 	if (error) {
 		mutex_unlock(&uuid_mutex);
 		goto error_fs_info;
-- 
cgit v1.2.3


From 711169c40f908df6df91ba2672d05b44243833e4 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:24 +0800
Subject: btrfs: qgroup: Drop quota_root parameter from
 add_qgroup_relation_item

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index e0bd48c5a98b..4f523b7a3e91 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -530,11 +530,11 @@ void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info)
 	fs_info->qgroup_ulist = NULL;
 }
 
-static int add_qgroup_relation_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *quota_root,
-				    u64 src, u64 dst)
+static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
+				    u64 dst)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -1274,11 +1274,11 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
 		}
 	}
 
-	ret = add_qgroup_relation_item(trans, quota_root, src, dst);
+	ret = add_qgroup_relation_item(trans, src, dst);
 	if (ret)
 		goto out;
 
-	ret = add_qgroup_relation_item(trans, quota_root, dst, src);
+	ret = add_qgroup_relation_item(trans, dst, src);
 	if (ret) {
 		del_qgroup_relation_item(trans, quota_root, src, dst);
 		goto out;
@@ -2295,12 +2295,12 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		for (i = 0; i < inherit->num_qgroups; ++i, ++i_qgroups) {
 			if (*i_qgroups == 0)
 				continue;
-			ret = add_qgroup_relation_item(trans, quota_root,
-						       objectid, *i_qgroups);
+			ret = add_qgroup_relation_item(trans, objectid,
+						       *i_qgroups);
 			if (ret && ret != -EEXIST)
 				goto out;
-			ret = add_qgroup_relation_item(trans, quota_root,
-						       *i_qgroups, objectid);
+			ret = add_qgroup_relation_item(trans, *i_qgroups,
+						       objectid);
 			if (ret && ret != -EEXIST)
 				goto out;
 		}
-- 
cgit v1.2.3


From 99d7f09ac01cbea28767a84d4d34dd5b1922a245 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:25 +0800
Subject: btrfs: qgroup: Drop quota_root parameter from
 del_qgroup_relation_item

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 4f523b7a3e91..c22f1e655a60 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -554,11 +554,11 @@ static int add_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
 	return ret;
 }
 
-static int del_qgroup_relation_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *quota_root,
-				    u64 src, u64 dst)
+static int del_qgroup_relation_item(struct btrfs_trans_handle *trans, u64 src,
+				    u64 dst)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -1280,7 +1280,7 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
 
 	ret = add_qgroup_relation_item(trans, dst, src);
 	if (ret) {
-		del_qgroup_relation_item(trans, quota_root, src, dst);
+		del_qgroup_relation_item(trans, src, dst);
 		goto out;
 	}
 
@@ -1334,8 +1334,8 @@ static int __del_qgroup_relation(struct btrfs_trans_handle *trans,
 	ret = -ENOENT;
 	goto out;
 exist:
-	ret = del_qgroup_relation_item(trans, quota_root, src, dst);
-	err = del_qgroup_relation_item(trans, quota_root, dst, src);
+	ret = del_qgroup_relation_item(trans, src, dst);
+	err = del_qgroup_relation_item(trans, dst, src);
 	if (err && !ret)
 		ret = err;
 
-- 
cgit v1.2.3


From 69104618f4b9dd445109e8dd755406427bd75b76 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:26 +0800
Subject: btrfs: qgroup: Drop quota_root parameter from del_qgroup_item

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index c22f1e655a60..67e0f4f38c31 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -653,10 +653,10 @@ out:
 	return ret;
 }
 
-static int del_qgroup_item(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *quota_root, u64 qgroupid)
+static int del_qgroup_item(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
 	int ret;
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 
@@ -1420,7 +1420,7 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 	}
-	ret = del_qgroup_item(trans, quota_root, qgroupid);
+	ret = del_qgroup_item(trans, qgroupid);
 	if (ret && ret != -ENOENT)
 		goto out;
 
-- 
cgit v1.2.3


From ac8a866af17edc692b50cbdd2aec612de4205c8f Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:27 +0800
Subject: btrfs: qgroup: Drop root parameter from update_qgroup_limit_item

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 67e0f4f38c31..44e1462e0f76 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -700,9 +700,9 @@ out:
 }
 
 static int update_qgroup_limit_item(struct btrfs_trans_handle *trans,
-				    struct btrfs_root *root,
 				    struct btrfs_qgroup *qgroup)
 {
+	struct btrfs_root *quota_root = trans->fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -718,7 +718,7 @@ static int update_qgroup_limit_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -1509,7 +1509,7 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
 
 	spin_unlock(&fs_info->qgroup_lock);
 
-	ret = update_qgroup_limit_item(trans, quota_root, qgroup);
+	ret = update_qgroup_limit_item(trans, qgroup);
 	if (ret) {
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 		btrfs_info(fs_info, "unable to update quota limit for %llu",
@@ -2214,7 +2214,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 		if (ret)
 			fs_info->qgroup_flags |=
 					BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
-		ret = update_qgroup_limit_item(trans, quota_root, qgroup);
+		ret = update_qgroup_limit_item(trans, qgroup);
 		if (ret)
 			fs_info->qgroup_flags |=
 					BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
@@ -2323,7 +2323,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 		dstgroup->rsv_rfer = inherit->lim.rsv_rfer;
 		dstgroup->rsv_excl = inherit->lim.rsv_excl;
 
-		ret = update_qgroup_limit_item(trans, quota_root, dstgroup);
+		ret = update_qgroup_limit_item(trans, dstgroup);
 		if (ret) {
 			fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 			btrfs_info(fs_info,
-- 
cgit v1.2.3


From 3e07e9a09f27868dbc63d07db8677fcd256e3bbc Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:28 +0800
Subject: btrfs: qgroup: Drop root parameter from update_qgroup_info_item

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 44e1462e0f76..f4b25e0a32f8 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -742,9 +742,10 @@ out:
 }
 
 static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
-				   struct btrfs_root *root,
 				   struct btrfs_qgroup *qgroup)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -752,7 +753,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	int ret;
 	int slot;
 
-	if (btrfs_is_testing(root->fs_info))
+	if (btrfs_is_testing(fs_info))
 		return 0;
 
 	key.objectid = 0;
@@ -763,7 +764,7 @@ static int update_qgroup_info_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -2210,7 +2211,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 					  struct btrfs_qgroup, dirty);
 		list_del_init(&qgroup->dirty);
 		spin_unlock(&fs_info->qgroup_lock);
-		ret = update_qgroup_info_item(trans, quota_root, qgroup);
+		ret = update_qgroup_info_item(trans, qgroup);
 		if (ret)
 			fs_info->qgroup_flags |=
 					BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
-- 
cgit v1.2.3


From 2e980acdd829742966c6a7e565ef3382c0717295 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:29 +0800
Subject: btrfs: qgroup: Drop quota_root and fs_info parameters from
 update_qgroup_status_item

They can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index f4b25e0a32f8..a7890183f20f 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -787,10 +787,10 @@ out:
 	return ret;
 }
 
-static int update_qgroup_status_item(struct btrfs_trans_handle *trans,
-				     struct btrfs_fs_info *fs_info,
-				    struct btrfs_root *root)
+static int update_qgroup_status_item(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
+	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
 	struct extent_buffer *l;
@@ -806,7 +806,7 @@ static int update_qgroup_status_item(struct btrfs_trans_handle *trans,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_search_slot(trans, root, &key, path, 0, 1);
+	ret = btrfs_search_slot(trans, quota_root, &key, path, 0, 1);
 	if (ret > 0)
 		ret = -ENOENT;
 
@@ -2227,7 +2227,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 		fs_info->qgroup_flags &= ~BTRFS_QGROUP_STATUS_FLAG_ON;
 	spin_unlock(&fs_info->qgroup_lock);
 
-	ret = update_qgroup_status_item(trans, fs_info, quota_root);
+	ret = update_qgroup_status_item(trans);
 	if (ret)
 		fs_info->qgroup_flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
 
@@ -2795,7 +2795,7 @@ out:
 			  err);
 		goto done;
 	}
-	ret = update_qgroup_status_item(trans, fs_info, fs_info->quota_root);
+	ret = update_qgroup_status_item(trans);
 	if (ret < 0) {
 		err = ret;
 		btrfs_err(fs_info, "fail to update qgroup status: %d", err);
-- 
cgit v1.2.3


From 9f8a6ce6ba8ebeb86de59b1adfdc64087049f76f Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:30 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_add_qgroup_relation

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c  | 3 +--
 fs/btrfs/qgroup.c | 5 +++--
 fs/btrfs/qgroup.h | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 9dcd16dec754..70b6f943fd70 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5171,8 +5171,7 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 	}
 
 	if (sa->assign) {
-		ret = btrfs_add_qgroup_relation(trans, fs_info,
-						sa->src, sa->dst);
+		ret = btrfs_add_qgroup_relation(trans, sa->src, sa->dst);
 	} else {
 		ret = btrfs_del_qgroup_relation(trans, fs_info,
 						sa->src, sa->dst);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index a7890183f20f..8b71aec85d84 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1236,9 +1236,10 @@ out:
 	return ret;
 }
 
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index bec7c9b17a8e..cb4d0e58f486 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -147,8 +147,8 @@ int btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info);
 void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info);
 int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
 				     bool interruptible);
-int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
+int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst);
 int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
 			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
 int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-- 
cgit v1.2.3


From 6b36f1aa5cda39acac50f6f80c81776a31fccd24 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:31 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from __del_qgroup_relation

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 8b71aec85d84..953b0d54e5d6 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1300,9 +1300,10 @@ out:
 	return ret;
 }
 
-static int __del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+static int __del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+				 u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *parent;
 	struct btrfs_qgroup *member;
@@ -1356,7 +1357,7 @@ int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	ret = __del_qgroup_relation(trans, fs_info, src, dst);
+	ret = __del_qgroup_relation(trans, src, dst);
 	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 
 	return ret;
@@ -1429,9 +1430,8 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
 	while (!list_empty(&qgroup->groups)) {
 		list = list_first_entry(&qgroup->groups,
 					struct btrfs_qgroup_list, next_group);
-		ret = __del_qgroup_relation(trans, fs_info,
-					   qgroupid,
-					   list->group->qgroupid);
+		ret = __del_qgroup_relation(trans, qgroupid,
+					    list->group->qgroupid);
 		if (ret)
 			goto out;
 	}
-- 
cgit v1.2.3


From 39616c2735ad04ecf4874519b64556decb73d968 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:32 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_del_qgroup_relation

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c  | 3 +--
 fs/btrfs/qgroup.c | 5 +++--
 fs/btrfs/qgroup.h | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 70b6f943fd70..09943e396c77 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5173,8 +5173,7 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 	if (sa->assign) {
 		ret = btrfs_add_qgroup_relation(trans, sa->src, sa->dst);
 	} else {
-		ret = btrfs_del_qgroup_relation(trans, fs_info,
-						sa->src, sa->dst);
+		ret = btrfs_del_qgroup_relation(trans, sa->src, sa->dst);
 	}
 
 	/* update qgroup status and info */
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 953b0d54e5d6..8c6f594a7ee8 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1351,9 +1351,10 @@ out:
 	return ret;
 }
 
-int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
+int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_ioctl_lock);
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index cb4d0e58f486..539d4c449f26 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -149,8 +149,8 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
 				     bool interruptible);
 int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 			      u64 dst);
-int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 src, u64 dst);
+int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
+			      u64 dst);
 int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info, u64 qgroupid);
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-- 
cgit v1.2.3


From 49a05ecde3f130ae9d69ab619e3ea125cf1f32c9 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:33 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_create_qgroup

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c              | 2 +-
 fs/btrfs/qgroup.c             | 4 ++--
 fs/btrfs/qgroup.h             | 3 +--
 fs/btrfs/tests/qgroup-tests.c | 4 ++--
 4 files changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 09943e396c77..2fdc34a67139 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5227,7 +5227,7 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 	}
 
 	if (sa->create) {
-		ret = btrfs_create_qgroup(trans, fs_info, sa->qgroupid);
+		ret = btrfs_create_qgroup(trans, sa->qgroupid);
 	} else {
 		ret = btrfs_remove_qgroup(trans, fs_info, sa->qgroupid);
 	}
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 8c6f594a7ee8..9c97be3fbf35 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1364,9 +1364,9 @@ int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 	return ret;
 }
 
-int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid)
+int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 539d4c449f26..03adfedd9d01 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -151,8 +151,7 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 			      u64 dst);
 int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 			      u64 dst);
-int btrfs_create_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid);
+int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
 			      struct btrfs_fs_info *fs_info, u64 qgroupid);
 int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index ace94db09d29..b5e332d45d37 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -216,7 +216,7 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 	btrfs_init_dummy_trans(&trans, fs_info);
 
 	test_msg("qgroup basic add");
-	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FS_TREE_OBJECTID);
+	ret = btrfs_create_qgroup(&trans, BTRFS_FS_TREE_OBJECTID);
 	if (ret) {
 		test_err("couldn't create a qgroup %d", ret);
 		return ret;
@@ -322,7 +322,7 @@ static int test_multiple_refs(struct btrfs_root *root,
 	 * We have BTRFS_FS_TREE_OBJECTID created already from the
 	 * previous test.
 	 */
-	ret = btrfs_create_qgroup(NULL, fs_info, BTRFS_FIRST_FREE_OBJECTID);
+	ret = btrfs_create_qgroup(&trans, BTRFS_FIRST_FREE_OBJECTID);
 	if (ret) {
 		test_err("couldn't create a qgroup %d", ret);
 		return ret;
-- 
cgit v1.2.3


From 3efbee1d006a97eaec5f070430c75010ef8746f1 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:34 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_remove_qgroup

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c  | 3 +--
 fs/btrfs/qgroup.c | 4 ++--
 fs/btrfs/qgroup.h | 3 +--
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2fdc34a67139..cb2b74db24ea 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5195,7 +5195,6 @@ drop_write:
 static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ioctl_qgroup_create_args *sa;
 	struct btrfs_trans_handle *trans;
@@ -5229,7 +5228,7 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 	if (sa->create) {
 		ret = btrfs_create_qgroup(trans, sa->qgroupid);
 	} else {
-		ret = btrfs_remove_qgroup(trans, fs_info, sa->qgroupid);
+		ret = btrfs_remove_qgroup(trans, sa->qgroupid);
 	}
 
 	err = btrfs_end_transaction(trans);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 9c97be3fbf35..d3d205d0e176 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1398,9 +1398,9 @@ out:
 	return ret;
 }
 
-int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-			struct btrfs_fs_info *fs_info, u64 qgroupid)
+int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_qgroup_list *list;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 03adfedd9d01..41516dddf123 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -152,8 +152,7 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 			      u64 dst);
 int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
-int btrfs_remove_qgroup(struct btrfs_trans_handle *trans,
-			      struct btrfs_fs_info *fs_info, u64 qgroupid);
+int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
 int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
 		       struct btrfs_fs_info *fs_info, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit);
-- 
cgit v1.2.3


From f0042d5e92b66969a12166d1deb5a979250d6c25 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:35 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_limit_qgroup

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c  | 3 +--
 fs/btrfs/qgroup.c | 4 ++--
 fs/btrfs/qgroup.h | 3 +--
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index cb2b74db24ea..01aab038120e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5245,7 +5245,6 @@ drop_write:
 static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 {
 	struct inode *inode = file_inode(file);
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_ioctl_qgroup_limit_args *sa;
 	struct btrfs_trans_handle *trans;
@@ -5278,7 +5277,7 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 		qgroupid = root->root_key.objectid;
 	}
 
-	ret = btrfs_limit_qgroup(trans, fs_info, qgroupid, &sa->lim);
+	ret = btrfs_limit_qgroup(trans, qgroupid, &sa->lim);
 
 	err = btrfs_end_transaction(trans);
 	if (err && !ret)
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d3d205d0e176..8953d0264887 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1445,10 +1445,10 @@ out:
 	return ret;
 }
 
-int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 qgroupid,
+int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	int ret = 0;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 41516dddf123..385367989ed6 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -153,8 +153,7 @@ int btrfs_del_qgroup_relation(struct btrfs_trans_handle *trans, u64 src,
 			      u64 dst);
 int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
 int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid);
-int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 qgroupid,
+int btrfs_limit_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid,
 		       struct btrfs_qgroup_limit *limit);
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
-- 
cgit v1.2.3


From a95f3aafd6a2d0e8de834c95e91066825e3e7787 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 16:28:03 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_qgroup_trace_extent

It can be fetched from the transaction handle. In addition, remove the
WARN_ON(trans == NULL) because it's not possible to hit this condition.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c   | 15 ++++++---------
 fs/btrfs/qgroup.h   |  5 ++---
 fs/btrfs/tree-log.c |  2 +-
 3 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 8953d0264887..d1e8b4851912 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1580,10 +1580,10 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
-		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
-		gfp_t gfp_flag)
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+			      u64 num_bytes, gfp_t gfp_flag)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_qgroup_extent_record *record;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int ret;
@@ -1591,8 +1591,6 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)
 	    || bytenr == 0 || num_bytes == 0)
 		return 0;
-	if (WARN_ON(trans == NULL))
-		return -EINVAL;
 	record = kmalloc(sizeof(*record), gfp_flag);
 	if (!record)
 		return -ENOMEM;
@@ -1645,8 +1643,8 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
 
 		num_bytes = btrfs_file_extent_disk_num_bytes(eb, fi);
 
-		ret = btrfs_qgroup_trace_extent(trans, fs_info, bytenr,
-						num_bytes, GFP_NOFS);
+		ret = btrfs_qgroup_trace_extent(trans, bytenr, num_bytes,
+						GFP_NOFS);
 		if (ret)
 			return ret;
 	}
@@ -1797,8 +1795,7 @@ walk_down:
 			btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
 			path->locks[level] = BTRFS_READ_LOCK_BLOCKING;
 
-			ret = btrfs_qgroup_trace_extent(trans, fs_info,
-							child_bytenr,
+			ret = btrfs_qgroup_trace_extent(trans, child_bytenr,
 							fs_info->nodesize,
 							GFP_NOFS);
 			if (ret)
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 385367989ed6..0215dc0b1710 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -212,9 +212,8 @@ int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
  * Return <0 for error, like memory allocation failure or invalid parameter
  * (NULL trans)
  */
-int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
-		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
-		gfp_t gfp_flag);
+int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+			      u64 num_bytes, gfp_t gfp_flag);
 
 /*
  * Inform qgroup to trace all leaf items of data
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 7b7498f1f641..10f6a4223897 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -685,7 +685,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		 * as the owner of the file extent changed from log tree
 		 * (doesn't affect qgroup) to fs/file tree(affects qgroup)
 		 */
-		ret = btrfs_qgroup_trace_extent(trans, fs_info,
+		ret = btrfs_qgroup_trace_extent(trans,
 				btrfs_file_extent_disk_bytenr(eb, item),
 				btrfs_file_extent_disk_num_bytes(eb, item),
 				GFP_NOFS);
-- 
cgit v1.2.3


From 8d38d7eb7bb60a7a441cec3ba92784d9f1e20d5f Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:37 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from
 btrfs_qgroup_trace_leaf_items

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 2 +-
 fs/btrfs/qgroup.c      | 8 ++++----
 fs/btrfs/qgroup.h      | 1 -
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index ced26ba8d392..51da902a0ad7 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -8760,7 +8760,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			else
 				ret = btrfs_dec_ref(trans, root, eb, 0);
 			BUG_ON(ret); /* -ENOMEM */
-			ret = btrfs_qgroup_trace_leaf_items(trans, fs_info, eb);
+			ret = btrfs_qgroup_trace_leaf_items(trans, eb);
 			if (ret) {
 				btrfs_err_rl(fs_info,
 					     "error %d accounting leaf items. Quota is out of sync, rescan required.",
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index d1e8b4851912..11a23b17a432 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1611,9 +1611,9 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 }
 
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct extent_buffer *eb)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int nr = btrfs_header_nritems(eb);
 	int i, extent_type, ret;
 	struct btrfs_key key;
@@ -1737,7 +1737,7 @@ int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 	}
 
 	if (root_level == 0) {
-		ret = btrfs_qgroup_trace_leaf_items(trans, fs_info, root_eb);
+		ret = btrfs_qgroup_trace_leaf_items(trans, root_eb);
 		goto out;
 	}
 
@@ -1803,8 +1803,8 @@ walk_down:
 		}
 
 		if (level == 0) {
-			ret = btrfs_qgroup_trace_leaf_items(trans,fs_info,
-							   path->nodes[level]);
+			ret = btrfs_qgroup_trace_leaf_items(trans,
+							    path->nodes[level]);
 			if (ret)
 				goto out;
 
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 0215dc0b1710..9d434a01d467 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -222,7 +222,6 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans, u64 bytenr,
  * Return <0 for error(ENOMEM)
  */
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
-				  struct btrfs_fs_info *fs_info,
 				  struct extent_buffer *eb);
 /*
  * Inform qgroup to trace a whole subtree, including all its child tree
-- 
cgit v1.2.3


From deb406274339f386836313af7eeb8001cca6c33f Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:38 +0800
Subject: btrfs: qgroup: Drop root parameter from btrfs_qgroup_trace_subtree

The fs_info can be fetched from the transaction handle directly.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 2 +-
 fs/btrfs/qgroup.c      | 3 +--
 fs/btrfs/qgroup.h      | 1 -
 fs/btrfs/relocation.c  | 5 ++---
 4 files changed, 4 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 51da902a0ad7..4f19bdca3214 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -8660,7 +8660,7 @@ skip:
 		}
 
 		if (need_account) {
-			ret = btrfs_qgroup_trace_subtree(trans, root, next,
+			ret = btrfs_qgroup_trace_subtree(trans, next,
 							 generation, level - 1);
 			if (ret) {
 				btrfs_err_rl(fs_info,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 11a23b17a432..0b43e9e2a71e 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1714,11 +1714,10 @@ static int adjust_slots_upwards(struct btrfs_path *path, int root_level)
 }
 
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 	int level;
 	struct extent_buffer *eb = root_eb;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 9d434a01d467..b8f15ce6c83d 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -234,7 +234,6 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
  * Return <0 for error(ENOMEM or tree search error)
  */
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
-			       struct btrfs_root *root,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level);
 int
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index b98d7a594542..d6bcf558789e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1879,13 +1879,12 @@ again:
 		 *    and tree block numbers, if current trans doesn't free
 		 *    data reloc tree inode.
 		 */
-		ret = btrfs_qgroup_trace_subtree(trans, src, parent,
+		ret = btrfs_qgroup_trace_subtree(trans, parent,
 				btrfs_header_generation(parent),
 				btrfs_header_level(parent));
 		if (ret < 0)
 			break;
-		ret = btrfs_qgroup_trace_subtree(trans, dest,
-				path->nodes[level],
+		ret = btrfs_qgroup_trace_subtree(trans, path->nodes[level],
 				btrfs_header_generation(path->nodes[level]),
 				btrfs_header_level(path->nodes[level]));
 		if (ret < 0)
-- 
cgit v1.2.3


From 8696d76045579c9611fe1cfc064e48ada32bb796 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:39 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from
 btrfs_qgroup_account_extent

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c             | 20 ++++++++++----------
 fs/btrfs/qgroup.h             |  8 +++-----
 fs/btrfs/tests/qgroup-tests.c | 20 ++++++++++----------
 3 files changed, 23 insertions(+), 25 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 0b43e9e2a71e..5ac57fc3fa4b 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2038,12 +2038,11 @@ static int maybe_fs_roots(struct ulist *roots)
 	return is_fstree(unode->val);
 }
 
-int
-btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
-			    u64 bytenr, u64 num_bytes,
-			    struct ulist *old_roots, struct ulist *new_roots)
+int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+				u64 num_bytes, struct ulist *old_roots,
+				struct ulist *new_roots)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct ulist *qgroups = NULL;
 	struct ulist *tmp = NULL;
 	u64 seq;
@@ -2173,9 +2172,10 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans)
 				ulist_del(record->old_roots, qgroup_to_skip,
 					  0);
 			}
-			ret = btrfs_qgroup_account_extent(trans, fs_info,
-					record->bytenr, record->num_bytes,
-					record->old_roots, new_roots);
+			ret = btrfs_qgroup_account_extent(trans, record->bytenr,
+							  record->num_bytes,
+							  record->old_roots,
+							  new_roots);
 			record->old_roots = NULL;
 			new_roots = NULL;
 		}
@@ -2711,8 +2711,8 @@ qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 		if (ret < 0)
 			goto out;
 		/* For rescan, just pass old_roots as NULL */
-		ret = btrfs_qgroup_account_extent(trans, fs_info,
-				found.objectid, num_bytes, NULL, roots);
+		ret = btrfs_qgroup_account_extent(trans, found.objectid,
+						  num_bytes, NULL, roots);
 		if (ret < 0)
 			goto out;
 	}
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index b8f15ce6c83d..61b723b1e4d8 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -236,11 +236,9 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
 int btrfs_qgroup_trace_subtree(struct btrfs_trans_handle *trans,
 			       struct extent_buffer *root_eb,
 			       u64 root_gen, int root_level);
-int
-btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
-			    u64 bytenr, u64 num_bytes,
-			    struct ulist *old_roots, struct ulist *new_roots);
+int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
+				u64 num_bytes, struct ulist *old_roots,
+				struct ulist *new_roots);
 int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans);
 int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 		      struct btrfs_fs_info *fs_info);
diff --git a/fs/btrfs/tests/qgroup-tests.c b/fs/btrfs/tests/qgroup-tests.c
index b5e332d45d37..412b910b04cc 100644
--- a/fs/btrfs/tests/qgroup-tests.c
+++ b/fs/btrfs/tests/qgroup-tests.c
@@ -249,8 +249,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -285,8 +285,8 @@ static int test_no_shared_qgroup(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return -EINVAL;
@@ -350,8 +350,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -385,8 +385,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
@@ -426,8 +426,8 @@ static int test_multiple_refs(struct btrfs_root *root,
 		return ret;
 	}
 
-	ret = btrfs_qgroup_account_extent(&trans, fs_info, nodesize,
-					  nodesize, old_roots, new_roots);
+	ret = btrfs_qgroup_account_extent(&trans, nodesize, nodesize, old_roots,
+					  new_roots);
 	if (ret) {
 		test_err("couldn't account space for a qgroup %d", ret);
 		return ret;
-- 
cgit v1.2.3


From 280f8bd2cbe0b4b578c217b8fa504294c30abde1 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:40 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_run_qgroups

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c       | 2 +-
 fs/btrfs/qgroup.c      | 4 ++--
 fs/btrfs/qgroup.h      | 3 +--
 fs/btrfs/transaction.c | 2 +-
 4 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 01aab038120e..d0096383ac3d 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -5177,7 +5177,7 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 	}
 
 	/* update qgroup status and info */
-	err = btrfs_run_qgroups(trans, fs_info);
+	err = btrfs_run_qgroups(trans);
 	if (err < 0)
 		btrfs_handle_fs_error(fs_info, err,
 				      "failed to update qgroup status and info");
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 5ac57fc3fa4b..819cdaea51ab 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2193,9 +2193,9 @@ cleanup:
 /*
  * called from commit_transaction. Writes all changed qgroups to disk.
  */
-int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info)
+int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root = fs_info->quota_root;
 	int ret = 0;
 
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 61b723b1e4d8..2c8960f9028c 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -240,8 +240,7 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 				u64 num_bytes, struct ulist *old_roots,
 				struct ulist *new_roots);
 int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans);
-int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info);
+int btrfs_run_qgroups(struct btrfs_trans_handle *trans);
 int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
 			 struct btrfs_qgroup_inherit *inherit);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index ebe50dfb8947..0cbd55c498a1 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1152,7 +1152,7 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans)
 	ret = btrfs_run_dev_replace(trans, fs_info);
 	if (ret)
 		return ret;
-	ret = btrfs_run_qgroups(trans, fs_info);
+	ret = btrfs_run_qgroups(trans);
 	if (ret)
 		return ret;
 
-- 
cgit v1.2.3


From a937742250199a37358a4da0a990744b92c8623c Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:41 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from btrfs_qgroup_inherit

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c       | 2 +-
 fs/btrfs/qgroup.c      | 6 +++---
 fs/btrfs/qgroup.h      | 5 ++---
 fs/btrfs/transaction.c | 3 +--
 4 files changed, 7 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index d0096383ac3d..4482cf35522e 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -601,7 +601,7 @@ static noinline int create_subvol(struct inode *dir,
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
-	ret = btrfs_qgroup_inherit(trans, fs_info, 0, objectid, inherit);
+	ret = btrfs_qgroup_inherit(trans, 0, objectid, inherit);
 	if (ret)
 		goto fail;
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 819cdaea51ab..96640c56c910 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2238,13 +2238,13 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans)
  * cause a transaction abort so we take extra care here to only error
  * when a readonly fs is a reasonable outcome.
  */
-int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
-			 struct btrfs_qgroup_inherit *inherit)
+int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
+			 u64 objectid, struct btrfs_qgroup_inherit *inherit)
 {
 	int ret = 0;
 	int i;
 	u64 *i_qgroups;
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *quota_root = fs_info->quota_root;
 	struct btrfs_qgroup *srcgroup;
 	struct btrfs_qgroup *dstgroup;
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 2c8960f9028c..54b8bb282c0e 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -241,9 +241,8 @@ int btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans, u64 bytenr,
 				struct ulist *new_roots);
 int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans);
 int btrfs_run_qgroups(struct btrfs_trans_handle *trans);
-int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
-			 struct btrfs_fs_info *fs_info, u64 srcid, u64 objectid,
-			 struct btrfs_qgroup_inherit *inherit);
+int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans, u64 srcid,
+			 u64 objectid, struct btrfs_qgroup_inherit *inherit);
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes,
 			       enum btrfs_qgroup_rsv_type type);
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 0cbd55c498a1..aec208cbff00 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1355,8 +1355,7 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 		goto out;
 
 	/* Now qgroup are all updated, we can inherit it to new qgroups */
-	ret = btrfs_qgroup_inherit(trans, fs_info,
-				   src->root_key.objectid, dst_objectid,
+	ret = btrfs_qgroup_inherit(trans, src->root_key.objectid, dst_objectid,
 				   inherit);
 	if (ret < 0)
 		goto out;
-- 
cgit v1.2.3


From 62088ca7427d23ec1a5def9143098ca9c41c5302 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 18 Jul 2018 14:45:42 +0800
Subject: btrfs: qgroup: Drop fs_info parameter from qgroup_rescan_leaf

It can be fetched from the transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/qgroup.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 96640c56c910..e11ed7b3f32a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2640,10 +2640,10 @@ static bool is_last_leaf(struct btrfs_path *path)
  * returns < 0 on error, 0 when more leafs are to be scanned.
  * returns 1 when done.
  */
-static int
-qgroup_rescan_leaf(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
-		   struct btrfs_trans_handle *trans)
+static int qgroup_rescan_leaf(struct btrfs_trans_handle *trans,
+			      struct btrfs_path *path)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_key found;
 	struct extent_buffer *scratch_leaf = NULL;
 	struct ulist *roots = NULL;
@@ -2758,7 +2758,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 		if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
 			err = -EINTR;
 		} else {
-			err = qgroup_rescan_leaf(fs_info, path, trans);
+			err = qgroup_rescan_leaf(trans, path);
 		}
 		if (err > 0)
 			btrfs_commit_transaction(trans);
-- 
cgit v1.2.3


From 321a4bf72b251319aa456ea542161729442b6f61 Mon Sep 17 00:00:00 2001
From: Anand Jain <anand.jain@oracle.com>
Date: Mon, 16 Jul 2018 22:58:09 +0800
Subject: btrfs: use the assigned fs_devices instead of the dereference

We have assigned the %fs_info->fs_devices in %fs_devices as its not
modified just use it for the mutex_lock().

Signed-off-by: Anand Jain <anand.jain@oracle.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fd9d4e056b37..0b9023f52b2a 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2211,7 +2211,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&seed_devices->alloc_list);
 	mutex_init(&seed_devices->device_list_mutex);
 
-	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_devices->device_list_mutex);
 	list_splice_init_rcu(&fs_devices->devices, &seed_devices->devices,
 			      synchronize_rcu);
 	list_for_each_entry(device, &seed_devices->devices, dev_list)
@@ -2231,7 +2231,7 @@ static int btrfs_prepare_sprout(struct btrfs_fs_info *fs_info)
 	generate_random_uuid(fs_devices->fsid);
 	memcpy(fs_info->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
 	memcpy(disk_super->fsid, fs_devices->fsid, BTRFS_FSID_SIZE);
-	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
+	mutex_unlock(&fs_devices->device_list_mutex);
 
 	super_flags = btrfs_super_flags(disk_super) &
 		      ~BTRFS_SUPER_FLAG_SEEDING;
-- 
cgit v1.2.3


From 46df06b85e28eaf430aa5c8f8aa26120fa746b72 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 13 Jul 2018 20:46:30 +0200
Subject: btrfs: refactor block group replication factor calculation to a
 helper

There are many places that open code the duplicity factor of the block
group profiles, create a common helper. This can be easily extended for
more copies.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 36 ++++++++----------------------------
 fs/btrfs/super.c       | 11 +++--------
 fs/btrfs/volumes.c     | 11 +++++++++++
 fs/btrfs/volumes.h     |  2 ++
 4 files changed, 24 insertions(+), 36 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 4f19bdca3214..fd109bfd528d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3931,11 +3931,7 @@ static void update_space_info(struct btrfs_fs_info *info, u64 flags,
 	struct btrfs_space_info *found;
 	int factor;
 
-	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
-		     BTRFS_BLOCK_GROUP_RAID10))
-		factor = 2;
-	else
-		factor = 1;
+	factor = btrfs_bg_type_to_factor(flags);
 
 	found = __find_space_info(info, flags);
 	ASSERT(found);
@@ -4576,6 +4572,7 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	u64 space_size;
 	u64 avail;
 	u64 used;
+	int factor;
 
 	/* Don't overcommit when in mixed mode. */
 	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
@@ -4610,10 +4607,8 @@ static int can_overcommit(struct btrfs_fs_info *fs_info,
 	 * doesn't include the parity drive, so we don't have to
 	 * change the math
 	 */
-	if (profile & (BTRFS_BLOCK_GROUP_DUP |
-		       BTRFS_BLOCK_GROUP_RAID1 |
-		       BTRFS_BLOCK_GROUP_RAID10))
-		avail >>= 1;
+	factor = btrfs_bg_type_to_factor(profile);
+	avail = div_u64(avail, factor);
 
 	/*
 	 * If we aren't flushing all things, let us overcommit up to
@@ -6094,12 +6089,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 		cache = btrfs_lookup_block_group(info, bytenr);
 		if (!cache)
 			return -ENOENT;
-		if (cache->flags & (BTRFS_BLOCK_GROUP_DUP |
-				    BTRFS_BLOCK_GROUP_RAID1 |
-				    BTRFS_BLOCK_GROUP_RAID10))
-			factor = 2;
-		else
-			factor = 1;
+		factor = btrfs_bg_type_to_factor(cache->flags);
+
 		/*
 		 * If this block group has free space cache written out, we
 		 * need to make sure to load it if we are removing space.  This
@@ -9359,13 +9350,7 @@ u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo)
 			continue;
 		}
 
-		if (block_group->flags & (BTRFS_BLOCK_GROUP_RAID1 |
-					  BTRFS_BLOCK_GROUP_RAID10 |
-					  BTRFS_BLOCK_GROUP_DUP))
-			factor = 2;
-		else
-			factor = 1;
-
+		factor = btrfs_bg_type_to_factor(block_group->flags);
 		free_bytes += (block_group->key.offset -
 			       btrfs_block_group_used(&block_group->item)) *
 			       factor;
@@ -10175,12 +10160,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 
 	memcpy(&key, &block_group->key, sizeof(key));
 	index = btrfs_bg_flags_to_raid_index(block_group->flags);
-	if (block_group->flags & (BTRFS_BLOCK_GROUP_DUP |
-				  BTRFS_BLOCK_GROUP_RAID1 |
-				  BTRFS_BLOCK_GROUP_RAID10))
-		factor = 2;
-	else
-		factor = 1;
+	factor = btrfs_bg_type_to_factor(block_group->flags);
 
 	/* make sure this block group isn't part of an allocation cluster */
 	cluster = &fs_info->data_alloc_cluster;
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index d7a54c648c5f..efe8b03ce380 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2107,14 +2107,9 @@ static int btrfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 				btrfs_account_ro_block_groups_free_space(found);
 
 			for (i = 0; i < BTRFS_NR_RAID_TYPES; i++) {
-				if (!list_empty(&found->block_groups[i])) {
-					switch (i) {
-					case BTRFS_RAID_DUP:
-					case BTRFS_RAID_RAID1:
-					case BTRFS_RAID_RAID10:
-						factor = 2;
-					}
-				}
+				if (!list_empty(&found->block_groups[i]))
+					factor = btrfs_bg_type_to_factor(
+						btrfs_raid_array[i].bg_flag);
 			}
 		}
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 0b9023f52b2a..eca67529e536 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7292,3 +7292,14 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info)
 		fs_devices = fs_devices->seed;
 	}
 }
+
+/*
+ * Multiplicity factor for simple profiles: DUP, RAID1-like and RAID10.
+ */
+int btrfs_bg_type_to_factor(u64 flags)
+{
+	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
+		     BTRFS_BLOCK_GROUP_RAID10))
+		return 2;
+	return 1;
+}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 06d8bb7dd557..6943aab9bdd7 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -559,4 +559,6 @@ void btrfs_reset_fs_info_ptr(struct btrfs_fs_info *fs_info);
 bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev);
 
+int btrfs_bg_type_to_factor(u64 flags);
+
 #endif
-- 
cgit v1.2.3


From 8b9b6f255485a4354da5474b16e79c447222e9ed Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 11 Jul 2018 13:41:22 +0800
Subject: btrfs: scrub: cleanup the remaining nodatasum fixup code

Remove the remaining code that misused the page cache pages during
device replace and could cause data corruption for compressed nodatasum
extents. Such files do not normally exist but there's a bug that allows
this combination and the corruption was exposed by device replace fixup
code.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/scrub.c | 289 -------------------------------------------------------
 1 file changed, 289 deletions(-)

diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 1235ad8dd9d7..c4eb9eca13b8 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -188,15 +188,6 @@ struct scrub_ctx {
 	refcount_t              refs;
 };
 
-struct scrub_fixup_nodatasum {
-	struct scrub_ctx	*sctx;
-	struct btrfs_device	*dev;
-	u64			logical;
-	struct btrfs_root	*root;
-	struct btrfs_work	work;
-	int			mirror_num;
-};
-
 struct scrub_warning {
 	struct btrfs_path	*path;
 	u64			extent_item_size;
@@ -215,8 +206,6 @@ struct full_stripe_lock {
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
 static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
-static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
-static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx);
 static int scrub_handle_errored_block(struct scrub_block *sblock_to_check);
 static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 				     struct scrub_block *sblocks_for_recheck);
@@ -531,60 +520,6 @@ out:
 	return ret;
 }
 
-/*
- * used for workers that require transaction commits (i.e., for the
- * NOCOW case)
- */
-static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx)
-{
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	refcount_inc(&sctx->refs);
-	/*
-	 * increment scrubs_running to prevent cancel requests from
-	 * completing as long as a worker is running. we must also
-	 * increment scrubs_paused to prevent deadlocking on pause
-	 * requests used for transactions commits (as the worker uses a
-	 * transaction context). it is safe to regard the worker
-	 * as paused for all matters practical. effectively, we only
-	 * avoid cancellation requests from completing.
-	 */
-	mutex_lock(&fs_info->scrub_lock);
-	atomic_inc(&fs_info->scrubs_running);
-	atomic_inc(&fs_info->scrubs_paused);
-	mutex_unlock(&fs_info->scrub_lock);
-
-	/*
-	 * check if @scrubs_running=@scrubs_paused condition
-	 * inside wait_event() is not an atomic operation.
-	 * which means we may inc/dec @scrub_running/paused
-	 * at any time. Let's wake up @scrub_pause_wait as
-	 * much as we can to let commit transaction blocked less.
-	 */
-	wake_up(&fs_info->scrub_pause_wait);
-
-	atomic_inc(&sctx->workers_pending);
-}
-
-/* used for workers that require transaction commits */
-static void scrub_pending_trans_workers_dec(struct scrub_ctx *sctx)
-{
-	struct btrfs_fs_info *fs_info = sctx->fs_info;
-
-	/*
-	 * see scrub_pending_trans_workers_inc() why we're pretending
-	 * to be paused in the scrub counters
-	 */
-	mutex_lock(&fs_info->scrub_lock);
-	atomic_dec(&fs_info->scrubs_running);
-	atomic_dec(&fs_info->scrubs_paused);
-	mutex_unlock(&fs_info->scrub_lock);
-	atomic_dec(&sctx->workers_pending);
-	wake_up(&fs_info->scrub_pause_wait);
-	wake_up(&sctx->list_wait);
-	scrub_put_ctx(sctx);
-}
-
 static void scrub_free_csums(struct scrub_ctx *sctx)
 {
 	while (!list_empty(&sctx->csum_list)) {
@@ -858,194 +793,6 @@ out:
 	btrfs_free_path(path);
 }
 
-static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
-{
-	struct page *page = NULL;
-	unsigned long index;
-	struct scrub_fixup_nodatasum *fixup = fixup_ctx;
-	int ret;
-	int corrected = 0;
-	struct btrfs_key key;
-	struct inode *inode = NULL;
-	struct btrfs_fs_info *fs_info;
-	u64 end = offset + PAGE_SIZE - 1;
-	struct btrfs_root *local_root;
-	int srcu_index;
-
-	key.objectid = root;
-	key.type = BTRFS_ROOT_ITEM_KEY;
-	key.offset = (u64)-1;
-
-	fs_info = fixup->root->fs_info;
-	srcu_index = srcu_read_lock(&fs_info->subvol_srcu);
-
-	local_root = btrfs_read_fs_root_no_name(fs_info, &key);
-	if (IS_ERR(local_root)) {
-		srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-		return PTR_ERR(local_root);
-	}
-
-	key.type = BTRFS_INODE_ITEM_KEY;
-	key.objectid = inum;
-	key.offset = 0;
-	inode = btrfs_iget(fs_info->sb, &key, local_root, NULL);
-	srcu_read_unlock(&fs_info->subvol_srcu, srcu_index);
-	if (IS_ERR(inode))
-		return PTR_ERR(inode);
-
-	index = offset >> PAGE_SHIFT;
-
-	page = find_or_create_page(inode->i_mapping, index, GFP_NOFS);
-	if (!page) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	if (PageUptodate(page)) {
-		if (PageDirty(page)) {
-			/*
-			 * we need to write the data to the defect sector. the
-			 * data that was in that sector is not in memory,
-			 * because the page was modified. we must not write the
-			 * modified page to that sector.
-			 *
-			 * TODO: what could be done here: wait for the delalloc
-			 *       runner to write out that page (might involve
-			 *       COW) and see whether the sector is still
-			 *       referenced afterwards.
-			 *
-			 * For the meantime, we'll treat this error
-			 * incorrectable, although there is a chance that a
-			 * later scrub will find the bad sector again and that
-			 * there's no dirty page in memory, then.
-			 */
-			ret = -EIO;
-			goto out;
-		}
-		ret = repair_io_failure(fs_info, inum, offset, PAGE_SIZE,
-					fixup->logical, page,
-					offset - page_offset(page),
-					fixup->mirror_num);
-		unlock_page(page);
-		corrected = !ret;
-	} else {
-		/*
-		 * we need to get good data first. the general readpage path
-		 * will call repair_io_failure for us, we just have to make
-		 * sure we read the bad mirror.
-		 */
-		ret = set_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-					EXTENT_DAMAGED);
-		if (ret) {
-			/* set_extent_bits should give proper error */
-			WARN_ON(ret > 0);
-			if (ret > 0)
-				ret = -EFAULT;
-			goto out;
-		}
-
-		ret = extent_read_full_page(&BTRFS_I(inode)->io_tree, page,
-						btrfs_get_extent,
-						fixup->mirror_num);
-		wait_on_page_locked(page);
-
-		corrected = !test_range_bit(&BTRFS_I(inode)->io_tree, offset,
-						end, EXTENT_DAMAGED, 0, NULL);
-		if (!corrected)
-			clear_extent_bits(&BTRFS_I(inode)->io_tree, offset, end,
-						EXTENT_DAMAGED);
-	}
-
-out:
-	if (page)
-		put_page(page);
-
-	iput(inode);
-
-	if (ret < 0)
-		return ret;
-
-	if (ret == 0 && corrected) {
-		/*
-		 * we only need to call readpage for one of the inodes belonging
-		 * to this extent. so make iterate_extent_inodes stop
-		 */
-		return 1;
-	}
-
-	return -EIO;
-}
-
-static void scrub_fixup_nodatasum(struct btrfs_work *work)
-{
-	struct btrfs_fs_info *fs_info;
-	int ret;
-	struct scrub_fixup_nodatasum *fixup;
-	struct scrub_ctx *sctx;
-	struct btrfs_trans_handle *trans = NULL;
-	struct btrfs_path *path;
-	int uncorrectable = 0;
-
-	fixup = container_of(work, struct scrub_fixup_nodatasum, work);
-	sctx = fixup->sctx;
-	fs_info = fixup->root->fs_info;
-
-	path = btrfs_alloc_path();
-	if (!path) {
-		spin_lock(&sctx->stat_lock);
-		++sctx->stat.malloc_errors;
-		spin_unlock(&sctx->stat_lock);
-		uncorrectable = 1;
-		goto out;
-	}
-
-	trans = btrfs_join_transaction(fixup->root);
-	if (IS_ERR(trans)) {
-		uncorrectable = 1;
-		goto out;
-	}
-
-	/*
-	 * the idea is to trigger a regular read through the standard path. we
-	 * read a page from the (failed) logical address by specifying the
-	 * corresponding copynum of the failed sector. thus, that readpage is
-	 * expected to fail.
-	 * that is the point where on-the-fly error correction will kick in
-	 * (once it's finished) and rewrite the failed sector if a good copy
-	 * can be found.
-	 */
-	ret = iterate_inodes_from_logical(fixup->logical, fs_info, path,
-					  scrub_fixup_readpage, fixup, false);
-	if (ret < 0) {
-		uncorrectable = 1;
-		goto out;
-	}
-	WARN_ON(ret != 1);
-
-	spin_lock(&sctx->stat_lock);
-	++sctx->stat.corrected_errors;
-	spin_unlock(&sctx->stat_lock);
-
-out:
-	if (trans && !IS_ERR(trans))
-		btrfs_end_transaction(trans);
-	if (uncorrectable) {
-		spin_lock(&sctx->stat_lock);
-		++sctx->stat.uncorrectable_errors;
-		spin_unlock(&sctx->stat_lock);
-		btrfs_dev_replace_stats_inc(
-			&fs_info->dev_replace.num_uncorrectable_read_errors);
-		btrfs_err_rl_in_rcu(fs_info,
-		    "unable to fixup (nodatasum) error at logical %llu on dev %s",
-			fixup->logical, rcu_str_deref(fixup->dev->name));
-	}
-
-	btrfs_free_path(path);
-	kfree(fixup);
-
-	scrub_pending_trans_workers_dec(sctx);
-}
-
 static inline void scrub_get_recover(struct scrub_recover *recover)
 {
 	refcount_inc(&recover->refs);
@@ -1239,42 +986,6 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 		goto out;
 	}
 
-	/*
-	 * NOTE: Even for nodatasum case, it's still possible that it's a
-	 * compressed data extent, thus scrub_fixup_nodatasum(), which write
-	 * inode page cache onto disk, could cause serious data corruption.
-	 *
-	 * So here we could only read from disk, and hope our recovery could
-	 * reach disk before the newer write.
-	 */
-	if (0 && !is_metadata && !have_csum) {
-		struct scrub_fixup_nodatasum *fixup_nodatasum;
-
-		WARN_ON(sctx->is_dev_replace);
-
-		/*
-		 * !is_metadata and !have_csum, this means that the data
-		 * might not be COWed, that it might be modified
-		 * concurrently. The general strategy to work on the
-		 * commit root does not help in the case when COW is not
-		 * used.
-		 */
-		fixup_nodatasum = kzalloc(sizeof(*fixup_nodatasum), GFP_NOFS);
-		if (!fixup_nodatasum)
-			goto did_not_correct_error;
-		fixup_nodatasum->sctx = sctx;
-		fixup_nodatasum->dev = dev;
-		fixup_nodatasum->logical = logical;
-		fixup_nodatasum->root = fs_info->extent_root;
-		fixup_nodatasum->mirror_num = failed_mirror_index + 1;
-		scrub_pending_trans_workers_inc(sctx);
-		btrfs_init_work(&fixup_nodatasum->work, btrfs_scrub_helper,
-				scrub_fixup_nodatasum, NULL, NULL);
-		btrfs_queue_work(fs_info->scrub_workers,
-				 &fixup_nodatasum->work);
-		goto out;
-	}
-
 	/*
 	 * now build and submit the bios for the other mirrors, check
 	 * checksums.
-- 
cgit v1.2.3


From 28187ae569e8a6c34eb7ac8871f479d94be31e16 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 4 Jul 2018 10:24:51 +0300
Subject: btrfs: Simplify page unlocking in alloc_extent_buffer

Current version of the page unlocking code was added in
727011e07cbd ("Btrfs: allow metadata blocks larger than the page size")
but even in this commit that particular flag was never used per-se. In
fact, btrfs only uses PageChecked for data pages to identify pages
which have been dirtied but don't have ORDERED bit set. For more
information see 247e743cbe6e ("Btrfs: Use async helpers to deal with
pages that have been improperly dirtied").

However, this doesn't apply to extent buffer pages. The important bit
here is that the pages are unlocked AFTER the extent buffer has been
properly recorded in the radix tree to avoid races with
btree_releasepage. Let's exploit this fact and simplify the page
unlocking sequence by unlocking the pages in-order and removing the
redundant PageChecked flag setting/clearing.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index fea015be4ce1..e9c74ce9623f 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5047,13 +5047,8 @@ again:
 	 * after the extent buffer is in the radix tree so
 	 * it doesn't get lost
 	 */
-	SetPageChecked(eb->pages[0]);
-	for (i = 1; i < num_pages; i++) {
-		p = eb->pages[i];
-		ClearPageChecked(p);
-		unlock_page(p);
-	}
-	unlock_page(eb->pages[0]);
+	for (i = 0; i < num_pages; i++)
+		unlock_page(eb->pages[i]);
 	return eb;
 
 free_eb:
-- 
cgit v1.2.3


From b16d011e79fb353abff70b2ef35b22ed90dc8db5 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 4 Jul 2018 10:24:52 +0300
Subject: btrfs: Reword dodgy comments in alloc_extent_buffer

Commit eb14ab8ed24a ("Btrfs: fix page->private races") fixed a genuine
race between extent buffer initialisation and btree_releasepage.
Unfortunately as the code has evolved the comments weren't changed which
made them slightly wrong and they weren't very clear in the fist place.
Fix this by (hopefully) rewording them in a more approachable manner.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 17 ++++++++---------
 1 file changed, 8 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index e9c74ce9623f..96039dd56c72 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5009,8 +5009,11 @@ struct extent_buffer *alloc_extent_buffer(struct btrfs_fs_info *fs_info,
 			uptodate = 0;
 
 		/*
-		 * see below about how we avoid a nasty race with release page
-		 * and why we unlock later
+		 * We can't unlock the pages just yet since the extent buffer
+		 * hasn't been properly inserted in the radix tree, this
+		 * opens a race with btree_releasepage which can free a page
+		 * while we are still filling in all pages for the buffer and
+		 * we could crash.
 		 */
 	}
 	if (uptodate)
@@ -5039,13 +5042,9 @@ again:
 	set_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags);
 
 	/*
-	 * there is a race where release page may have
-	 * tried to find this extent buffer in the radix
-	 * but failed.  It will tell the VM it is safe to
-	 * reclaim the, and it will clear the page private bit.
-	 * We must make sure to set the page private bit properly
-	 * after the extent buffer is in the radix tree so
-	 * it doesn't get lost
+	 * Now it's safe to unlock the pages because any calls to
+	 * btree_releasepage will correctly detect that a page belongs to a
+	 * live buffer and won't free them prematurely.
 	 */
 	for (i = 0; i < num_pages; i++)
 		unlock_page(eb->pages[i]);
-- 
cgit v1.2.3


From d64766fdf9cd172f8416d898cc9d5219ed933b96 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 27 Jun 2018 16:38:22 +0300
Subject: btrfs: Refactor loop in btrfs_release_extent_buffer_page

The purpose of the function is to free all the pages comprising an
extent buffer. This can be achieved with a simple for loop rather than
the slightly more involved 'do {} while' construct. So rewrite the
loop using a 'for' construct. Additionally we can never have an
extent_buffer that has 0 pages so remove the check for index == 0. No
functional changes.

The reversed order used to have a meaning in the past where the first
page served as a blocking point for several callers. See eg
4f2de97acee6532b36dd6e99 ("Btrfs: set page->private to the eb").

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 96039dd56c72..66b5272bbaab 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4647,19 +4647,16 @@ int extent_buffer_under_io(struct extent_buffer *eb)
  */
 static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 {
-	int index;
-	struct page *page;
+	int i;
+	int num_pages;
 	int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
 
 	BUG_ON(extent_buffer_under_io(eb));
 
-	index = num_extent_pages(eb);
-	if (index == 0)
-		return;
+	num_pages = num_extent_pages(eb);
+	for (i = 0; i < num_pages; i++) {
+		struct page *page = eb->pages[i];
 
-	do {
-		index--;
-		page = eb->pages[index];
 		if (!page)
 			continue;
 		if (mapped)
@@ -4691,7 +4688,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
 
 		/* One for when we allocated the page */
 		put_page(page);
-	} while (index != 0);
+	}
 }
 
 /*
-- 
cgit v1.2.3


From 55ac01396ae8cfc0616e85bb4b49a130144633c2 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Thu, 19 Jul 2018 17:24:32 +0200
Subject: btrfs: rename btrfs_release_extent_buffer_page

The function used to release one page (and always the first one), but
not anymore since a50924e3a4d7fccb0ecfbd4 ("btrfs: drop constant param
from btrfs_release_extent_buffer_page").  Update the name and comment.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 66b5272bbaab..6a4013ddcf73 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4643,9 +4643,9 @@ int extent_buffer_under_io(struct extent_buffer *eb)
 }
 
 /*
- * Helper for releasing extent buffer page.
+ * Release all pages attached to the extent buffer.
  */
-static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
+static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb)
 {
 	int i;
 	int num_pages;
@@ -4696,7 +4696,7 @@ static void btrfs_release_extent_buffer_page(struct extent_buffer *eb)
  */
 static inline void btrfs_release_extent_buffer(struct extent_buffer *eb)
 {
-	btrfs_release_extent_buffer_page(eb);
+	btrfs_release_extent_buffer_pages(eb);
 	__free_extent_buffer(eb);
 }
 
@@ -5085,7 +5085,7 @@ static int release_extent_buffer(struct extent_buffer *eb)
 		}
 
 		/* Should be safe to release our pages at this point */
-		btrfs_release_extent_buffer_page(eb);
+		btrfs_release_extent_buffer_pages(eb);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 		if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
 			__free_extent_buffer(eb);
-- 
cgit v1.2.3


From 07e21c4dad42be8d2a6b8cd0b98cf8e6931e12fd Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 27 Jun 2018 16:38:23 +0300
Subject: btrfs: Document locking requirement via lockdep_assert_held

Remove stale comment since there is no longer an eb->eb_lock and
document the locking expectation with a lockdep_assert_held statement.
No functional changes.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_io.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 6a4013ddcf73..5ab401f79683 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -5066,9 +5066,10 @@ static inline void btrfs_release_extent_buffer_rcu(struct rcu_head *head)
 	__free_extent_buffer(eb);
 }
 
-/* Expects to have eb->eb_lock already held */
 static int release_extent_buffer(struct extent_buffer *eb)
 {
+	lockdep_assert_held(&eb->refs_lock);
+
 	WARN_ON(atomic_read(&eb->refs) == 0);
 	if (atomic_dec_and_test(&eb->refs)) {
 		if (test_and_clear_bit(EXTENT_BUFFER_IN_TREE, &eb->bflags)) {
-- 
cgit v1.2.3


From b0132a3be5daf84116833542717ff5692f51640e Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Wed, 27 Jun 2018 16:38:24 +0300
Subject: btrfs: Rename EXTENT_BUFFER_DUMMY to EXTENT_BUFFER_UNMAPPED

EXTENT_BUFFER_DUMMY is an awful name for this flag. Buffers which have
this flag set are not in any way dummy. Rather, they are private in the
sense that are not mapped and linked to the global buffer tree. This
flag has subtle implications to the way free_extent_buffer works for
example, as well as controls whether page->mapping->private_lock is held
during extent_buffer release. Pages for an unmapped buffer cannot be
under io, nor can they be written by a 3rd party so taking the lock is
unnecessary.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
[ EXTENT_BUFFER_UNMAPPED, update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c   |  4 ++--
 fs/btrfs/extent_io.c | 10 +++++-----
 fs/btrfs/extent_io.h |  2 +-
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index e3858b2fe014..a4b713d03a33 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4089,10 +4089,10 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	/*
 	 * This is a fast path so only do this check if we have sanity tests
-	 * enabled.  Normal people shouldn't be marking dummy buffers as dirty
+	 * enabled.  Normal people shouldn't be using umapped buffers as dirty
 	 * outside of the sanity tests.
 	 */
-	if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &buf->bflags)))
+	if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &buf->bflags)))
 		return;
 #endif
 	root = BTRFS_I(buf->pages[0]->mapping->host)->root;
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 5ab401f79683..3440053f3599 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -4649,7 +4649,7 @@ static void btrfs_release_extent_buffer_pages(struct extent_buffer *eb)
 {
 	int i;
 	int num_pages;
-	int mapped = !test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+	int mapped = !test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	BUG_ON(extent_buffer_under_io(eb));
 
@@ -4763,7 +4763,7 @@ struct extent_buffer *btrfs_clone_extent_buffer(struct extent_buffer *src)
 	}
 
 	set_bit(EXTENT_BUFFER_UPTODATE, &new->bflags);
-	set_bit(EXTENT_BUFFER_DUMMY, &new->bflags);
+	set_bit(EXTENT_BUFFER_UNMAPPED, &new->bflags);
 
 	return new;
 }
@@ -4787,7 +4787,7 @@ struct extent_buffer *__alloc_dummy_extent_buffer(struct btrfs_fs_info *fs_info,
 	}
 	set_extent_buffer_uptodate(eb);
 	btrfs_set_header_nritems(eb, 0);
-	set_bit(EXTENT_BUFFER_DUMMY, &eb->bflags);
+	set_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags);
 
 	return eb;
 err:
@@ -5088,7 +5088,7 @@ static int release_extent_buffer(struct extent_buffer *eb)
 		/* Should be safe to release our pages at this point */
 		btrfs_release_extent_buffer_pages(eb);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-		if (unlikely(test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))) {
+		if (unlikely(test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))) {
 			__free_extent_buffer(eb);
 			return 1;
 		}
@@ -5119,7 +5119,7 @@ void free_extent_buffer(struct extent_buffer *eb)
 
 	spin_lock(&eb->refs_lock);
 	if (atomic_read(&eb->refs) == 2 &&
-	    test_bit(EXTENT_BUFFER_DUMMY, &eb->bflags))
+	    test_bit(EXTENT_BUFFER_UNMAPPED, &eb->bflags))
 		atomic_dec(&eb->refs);
 
 	if (atomic_read(&eb->refs) == 2 &&
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 48f1ee9ad379..0ecc13b7d6f7 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -46,7 +46,7 @@
 #define EXTENT_BUFFER_STALE 6
 #define EXTENT_BUFFER_WRITEBACK 7
 #define EXTENT_BUFFER_READ_ERR 8        /* read IO error */
-#define EXTENT_BUFFER_DUMMY 9
+#define EXTENT_BUFFER_UNMAPPED 9
 #define EXTENT_BUFFER_IN_TREE 10
 #define EXTENT_BUFFER_WRITE_ERR 11    /* write IO error */
 
-- 
cgit v1.2.3


From 315409b0098fb2651d86553f0436b70502b29bb2 Mon Sep 17 00:00:00 2001
From: Gu Jinxiang <gujx@cn.fujitsu.com>
Date: Wed, 4 Jul 2018 18:16:39 +0800
Subject: btrfs: validate type when reading a chunk

Reported in https://bugzilla.kernel.org/show_bug.cgi?id=199839, with an
image that has an invalid chunk type but does not return an error.

Add chunk type check in btrfs_check_chunk_valid, to detect the wrong
type combinations.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199839
Reported-by: Xu Wen <wen.xu@gatech.edu>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index eca67529e536..f237ef9e70a7 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6313,6 +6313,8 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 	u16 num_stripes;
 	u16 sub_stripes;
 	u64 type;
+	u64 features;
+	bool mixed = false;
 
 	length = btrfs_chunk_length(leaf, chunk);
 	stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
@@ -6351,6 +6353,32 @@ static int btrfs_check_chunk_valid(struct btrfs_fs_info *fs_info,
 			  btrfs_chunk_type(leaf, chunk));
 		return -EIO;
 	}
+
+	if ((type & BTRFS_BLOCK_GROUP_TYPE_MASK) == 0) {
+		btrfs_err(fs_info, "missing chunk type flag: 0x%llx", type);
+		return -EIO;
+	}
+
+	if ((type & BTRFS_BLOCK_GROUP_SYSTEM) &&
+	    (type & (BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA))) {
+		btrfs_err(fs_info,
+			"system chunk with data or metadata type: 0x%llx", type);
+		return -EIO;
+	}
+
+	features = btrfs_super_incompat_flags(fs_info->super_copy);
+	if (features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS)
+		mixed = true;
+
+	if (!mixed) {
+		if ((type & BTRFS_BLOCK_GROUP_METADATA) &&
+		    (type & BTRFS_BLOCK_GROUP_DATA)) {
+			btrfs_err(fs_info,
+			"mixed chunk type in non-mixed mode: 0x%llx", type);
+			return -EIO;
+		}
+	}
+
 	if ((type & BTRFS_BLOCK_GROUP_RAID10 && sub_stripes != 2) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID1 && num_stripes < 1) ||
 	    (type & BTRFS_BLOCK_GROUP_RAID5 && num_stripes < 2) ||
-- 
cgit v1.2.3


From d7e8555b1dd493c809e56e359974eecabe7d3fde Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 18 Jul 2018 17:31:19 +0200
Subject: btrfs: remove unused member async_submit_bio::fs_info

Introduced by c6100a4b4e3d1 ("Btrfs: replace tree->mapping with
tree->private_data") to be used in run_one_async_done where it got
unused after 736cd52e0c720103 ("Btrfs: remove nr_async_submits and
async_submit_draining").

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a4b713d03a33..8033289d2189 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -106,7 +106,6 @@ void __cold btrfs_end_io_wq_exit(void)
  */
 struct async_submit_bio {
 	void *private_data;
-	struct btrfs_fs_info *fs_info;
 	struct bio *bio;
 	extent_submit_bio_start_t *submit_bio_start;
 	extent_submit_bio_done_t *submit_bio_done;
@@ -801,7 +800,6 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 		return BLK_STS_RESOURCE;
 
 	async->private_data = private_data;
-	async->fs_info = fs_info;
 	async->bio = bio;
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
-- 
cgit v1.2.3


From d7cbfafc4bc37ed21351cdedbc6f9d979545dbf3 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 18 Jul 2018 17:31:10 +0200
Subject: btrfs: remove unused member async_submit_bio::bio_flags

After splitting the start and end hooks in a758781d4b76c3 ("btrfs:
separate types for submit_bio_start and submit_bio_done"), some of
the function arguments were dropped but not removed from the structure.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 8033289d2189..d82df15af89c 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -110,7 +110,6 @@ struct async_submit_bio {
 	extent_submit_bio_start_t *submit_bio_start;
 	extent_submit_bio_done_t *submit_bio_done;
 	int mirror_num;
-	unsigned long bio_flags;
 	/*
 	 * bio_offset is optional, can be used if the pages in the bio
 	 * can't tell us where in the file the bio should go
@@ -808,7 +807,6 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
 			run_one_async_done, run_one_async_free);
 
-	async->bio_flags = bio_flags;
 	async->bio_offset = bio_offset;
 
 	async->status = 0;
-- 
cgit v1.2.3


From e288c080dddd1fdc3b7e0165cebd7af51a52d016 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 18 Jul 2018 17:36:24 +0200
Subject: btrfs: unify end_io callbacks of async_submit_bio

The end_io callbacks passed to btrfs_wq_submit_bio
(btrfs_submit_bio_done and btree_submit_bio_done) are effectively the
same code, there's no point to do the indirection. Export
btrfs_submit_bio_done and call it directly.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c   | 28 +++-------------------------
 fs/btrfs/disk-io.h   |  5 +++--
 fs/btrfs/extent_io.h |  3 ---
 fs/btrfs/inode.c     |  8 +++-----
 4 files changed, 9 insertions(+), 35 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index d82df15af89c..03a7ed448f38 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -108,7 +108,6 @@ struct async_submit_bio {
 	void *private_data;
 	struct bio *bio;
 	extent_submit_bio_start_t *submit_bio_start;
-	extent_submit_bio_done_t *submit_bio_done;
 	int mirror_num;
 	/*
 	 * bio_offset is optional, can be used if the pages in the bio
@@ -775,7 +774,7 @@ static void run_one_async_done(struct btrfs_work *work)
 		return;
 	}
 
-	async->submit_bio_done(async->private_data, async->bio, async->mirror_num);
+	btrfs_submit_bio_done(async->private_data, async->bio, async->mirror_num);
 }
 
 static void run_one_async_free(struct btrfs_work *work)
@@ -789,8 +788,7 @@ static void run_one_async_free(struct btrfs_work *work)
 blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags,
 				 u64 bio_offset, void *private_data,
-				 extent_submit_bio_start_t *submit_bio_start,
-				 extent_submit_bio_done_t *submit_bio_done)
+				 extent_submit_bio_start_t *submit_bio_start)
 {
 	struct async_submit_bio *async;
 
@@ -802,7 +800,6 @@ blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	async->bio = bio;
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
-	async->submit_bio_done = submit_bio_done;
 
 	btrfs_init_work(&async->work, btrfs_worker_helper, run_one_async_start,
 			run_one_async_done, run_one_async_free);
@@ -845,24 +842,6 @@ static blk_status_t btree_submit_bio_start(void *private_data, struct bio *bio,
 	return btree_csum_one_bio(bio);
 }
 
-static blk_status_t btree_submit_bio_done(void *private_data, struct bio *bio,
-					    int mirror_num)
-{
-	struct inode *inode = private_data;
-	blk_status_t ret;
-
-	/*
-	 * when we're called for a write, we're already in the async
-	 * submission context.  Just jump into btrfs_map_bio
-	 */
-	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), bio, mirror_num, 1);
-	if (ret) {
-		bio->bi_status = ret;
-		bio_endio(bio);
-	}
-	return ret;
-}
-
 static int check_async_write(struct btrfs_inode *bi)
 {
 	if (atomic_read(&bi->sync_writers))
@@ -905,8 +884,7 @@ static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
 		 */
 		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0,
 					  bio_offset, private_data,
-					  btree_submit_bio_start,
-					  btree_submit_bio_done);
+					  btree_submit_bio_start);
 	}
 
 	if (ret)
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 1a3d277b027b..4cccba22640f 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -120,8 +120,9 @@ blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 			int mirror_num, unsigned long bio_flags,
 			u64 bio_offset, void *private_data,
-			extent_submit_bio_start_t *submit_bio_start,
-			extent_submit_bio_done_t *submit_bio_done);
+			extent_submit_bio_start_t *submit_bio_start);
+blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
+			  int mirror_num);
 int btrfs_write_tree_block(struct extent_buffer *buf);
 void btrfs_wait_tree_block_writeback(struct extent_buffer *buf);
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 0ecc13b7d6f7..4e6d34dd7caf 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -92,9 +92,6 @@ typedef	blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *
 typedef blk_status_t (extent_submit_bio_start_t)(void *private_data,
 		struct bio *bio, u64 bio_offset);
 
-typedef blk_status_t (extent_submit_bio_done_t)(void *private_data,
-		struct bio *bio, int mirror_num);
-
 struct extent_io_ops {
 	/*
 	 * The following callbacks must be allways defined, the function
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 564ec00c765b..6cb42e33fdc3 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1957,7 +1957,7 @@ static blk_status_t btrfs_submit_bio_start(void *private_data, struct bio *bio,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
+blk_status_t btrfs_submit_bio_done(void *private_data, struct bio *bio,
 			  int mirror_num)
 {
 	struct inode *inode = private_data;
@@ -2030,8 +2030,7 @@ static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
 		/* we're doing a write, do the async checksumming */
 		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags,
 					  bio_offset, inode,
-					  btrfs_submit_bio_start,
-					  btrfs_submit_bio_done);
+					  btrfs_submit_bio_start);
 		goto out;
 	} else if (!skip_sum) {
 		ret = btrfs_csum_one_bio(inode, bio, 0, 0);
@@ -8295,8 +8294,7 @@ static inline blk_status_t btrfs_submit_dio_bio(struct bio *bio,
 	if (write && async_submit) {
 		ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0,
 					  file_offset, inode,
-					  btrfs_submit_bio_start_direct_io,
-					  btrfs_submit_bio_done);
+					  btrfs_submit_bio_start_direct_io);
 		goto err;
 	} else if (write) {
 		/*
-- 
cgit v1.2.3


From 05912a3c04ebca217507b4323b679c60eda4ac11 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 18 Jul 2018 19:23:45 +0200
Subject: btrfs: drop extent_io_ops::tree_fs_info callback

All implementations of the callback are trivial and do the same and
there's only one user. Merge everything together.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c   |  7 -------
 fs/btrfs/extent_io.c | 14 ++++----------
 fs/btrfs/extent_io.h |  1 -
 fs/btrfs/inode.c     |  7 -------
 4 files changed, 4 insertions(+), 25 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 03a7ed448f38..126460214512 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4523,12 +4523,6 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
-static struct btrfs_fs_info *btree_fs_info(void *private_data)
-{
-	struct inode *inode = private_data;
-	return btrfs_sb(inode->i_sb);
-}
-
 static const struct extent_io_ops btree_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btree_submit_bio_hook,
@@ -4537,7 +4531,6 @@ static const struct extent_io_ops btree_extent_io_ops = {
 	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btree_io_failed_hook,
 	.set_range_writeback = btrfs_set_range_writeback,
-	.tree_fs_info = btree_fs_info,
 
 	/* optional callbacks */
 };
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 3440053f3599..7a19437c6eda 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -140,14 +140,6 @@ static int add_extent_changeset(struct extent_state *state, unsigned bits,
 
 static void flush_write_bio(struct extent_page_data *epd);
 
-static inline struct btrfs_fs_info *
-tree_fs_info(struct extent_io_tree *tree)
-{
-	if (tree->ops)
-		return tree->ops->tree_fs_info(tree->private_data);
-	return NULL;
-}
-
 int __init extent_io_init(void)
 {
 	extent_state_cache = kmem_cache_create("btrfs_extent_state",
@@ -564,8 +556,10 @@ alloc_extent_state_atomic(struct extent_state *prealloc)
 
 static void extent_io_tree_panic(struct extent_io_tree *tree, int err)
 {
-	btrfs_panic(tree_fs_info(tree), err,
-		    "Locking error: Extent tree was modified by another thread while locked.");
+	struct inode *inode = tree->private_data;
+
+	btrfs_panic(btrfs_sb(inode->i_sb), err,
+	"locking error: extent tree was modified by another thread while locked");
 }
 
 /*
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 4e6d34dd7caf..004517f3eb35 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -105,7 +105,6 @@ struct extent_io_ops {
 			      size_t size, struct bio *bio,
 			      unsigned long bio_flags);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
-	struct btrfs_fs_info *(*tree_fs_info)(void *private_data);
 	void (*set_range_writeback)(void *private_data, u64 start, u64 end);
 
 	/*
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 6cb42e33fdc3..f279e380f36e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10473,12 +10473,6 @@ static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
 	return -EAGAIN;
 }
 
-static struct btrfs_fs_info *iotree_fs_info(void *private_data)
-{
-	struct inode *inode = private_data;
-	return btrfs_sb(inode->i_sb);
-}
-
 static void btrfs_check_extent_io_range(void *private_data, const char *caller,
 					u64 start, u64 end)
 {
@@ -10553,7 +10547,6 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
 	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
-	.tree_fs_info = iotree_fs_info,
 	.set_range_writeback = btrfs_set_range_writeback,
 
 	/* optional callbacks */
-- 
cgit v1.2.3


From 00032d38eaa89c76de7d9c1ae6de8c48c14edd74 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 18 Jul 2018 19:28:09 +0200
Subject: btrfs: drop extent_io_ops::merge_bio_hook callback

The data and metadata callback implementation both use the same
function. We can remove the call indirection completely.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/compression.c | 10 +++-------
 fs/btrfs/disk-io.c     |  2 --
 fs/btrfs/extent_io.c   |  4 ++--
 fs/btrfs/extent_io.h   |  3 ---
 fs/btrfs/inode.c       |  5 ++---
 5 files changed, 7 insertions(+), 17 deletions(-)

diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 70dace47258b..9bfa66592aa7 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -299,7 +299,6 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	struct bio *bio = NULL;
 	struct compressed_bio *cb;
 	unsigned long bytes_left;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	int pg_index = 0;
 	struct page *page;
 	u64 first_byte = disk_start;
@@ -338,9 +337,7 @@ blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 		page = compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		if (bio->bi_iter.bi_size)
-			submit = io_tree->ops->merge_bio_hook(page, 0,
-							   PAGE_SIZE,
-							   bio, 0);
+			submit = btrfs_merge_bio_hook(page, 0, PAGE_SIZE, bio, 0);
 
 		page->mapping = NULL;
 		if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) <
@@ -622,9 +619,8 @@ blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 		page->index = em_start >> PAGE_SHIFT;
 
 		if (comp_bio->bi_iter.bi_size)
-			submit = tree->ops->merge_bio_hook(page, 0,
-							PAGE_SIZE,
-							comp_bio, 0);
+			submit = btrfs_merge_bio_hook(page, 0, PAGE_SIZE,
+					comp_bio, 0);
 
 		page->mapping = NULL;
 		if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 126460214512..0c9c029ade72 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4527,8 +4527,6 @@ static const struct extent_io_ops btree_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btree_submit_bio_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
-	/* note we're sharing with inode.c for the merge bio hook */
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btree_io_failed_hook,
 	.set_range_writeback = btrfs_set_range_writeback,
 
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 7a19437c6eda..20af0efd7c17 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2784,8 +2784,8 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 		else
 			contig = bio_end_sector(bio) == sector;
 
-		if (tree->ops && tree->ops->merge_bio_hook(page, offset,
-					page_size, bio, bio_flags))
+		if (tree->ops && btrfs_merge_bio_hook(page, offset, page_size,
+						      bio, bio_flags))
 			can_merge = false;
 
 		if (prev_bio_flags != bio_flags || !contig || !can_merge ||
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 004517f3eb35..5c07f87c2ec9 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -101,9 +101,6 @@ struct extent_io_ops {
 	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
 				    struct page *page, u64 start, u64 end,
 				    int mirror);
-	int (*merge_bio_hook)(struct page *page, unsigned long offset,
-			      size_t size, struct bio *bio,
-			      unsigned long bio_flags);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
 	void (*set_range_writeback)(void *private_data, u64 start, u64 end);
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index f279e380f36e..a72784d5666f 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1898,8 +1898,8 @@ static void btrfs_clear_bit_hook(void *private_data,
 }
 
 /*
- * extent_io.c merge_bio_hook, this must check the chunk tree to make sure
- * we don't create bios that span stripes or chunks
+ * Merge bio hook, this must check the chunk tree to make sure we don't create
+ * bios that span stripes or chunks
  *
  * return 1 if page cannot be merged to bio
  * return 0 if page can be merged to bio
@@ -10545,7 +10545,6 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
 	/* mandatory callbacks */
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
 	.set_range_writeback = btrfs_set_range_writeback,
 
-- 
cgit v1.2.3


From 5cdc84bfde22dc17b11ee7cb18cebd48f4a09f70 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Wed, 18 Jul 2018 20:32:52 +0200
Subject: btrfs: drop extent_io_ops::set_range_writeback callback

The data and metadata callback implementation both use the same
function. We can remove the call indirection and intermediate helper
completely.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h     |  2 +-
 fs/btrfs/disk-io.c   |  1 -
 fs/btrfs/extent_io.c | 10 +---------
 fs/btrfs/extent_io.h |  1 -
 fs/btrfs/inode.c     |  5 ++---
 5 files changed, 4 insertions(+), 15 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index ee1e152cb94b..9c638931b75e 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3172,7 +3172,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio,
 			 unsigned long bio_flags);
-void btrfs_set_range_writeback(void *private_data, u64 start, u64 end);
+void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end);
 vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_evict_inode(struct inode *inode);
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 0c9c029ade72..9b208ccf24fe 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -4528,7 +4528,6 @@ static const struct extent_io_ops btree_extent_io_ops = {
 	.submit_bio_hook = btree_submit_bio_hook,
 	.readpage_end_io_hook = btree_readpage_end_io_hook,
 	.readpage_io_failed_hook = btree_io_failed_hook,
-	.set_range_writeback = btrfs_set_range_writeback,
 
 	/* optional callbacks */
 };
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 20af0efd7c17..628f1aef34b0 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1380,14 +1380,6 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
 	}
 }
 
-/*
- * helper function to set both pages and extents in the tree writeback
- */
-static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
-{
-	tree->ops->set_range_writeback(tree->private_data, start, end);
-}
-
 /* find the first state struct with 'bits' set after 'start', and
  * return it.  tree->lock must be held.  NULL will returned if
  * nothing was found after 'start'
@@ -3416,7 +3408,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			continue;
 		}
 
-		set_range_writeback(tree, cur, cur + iosize - 1);
+		btrfs_set_range_writeback(tree, cur, cur + iosize - 1);
 		if (!PageWriteback(page)) {
 			btrfs_err(BTRFS_I(inode)->root->fs_info,
 				   "page %lu not writeback, cur %llu end %llu",
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 5c07f87c2ec9..b4d03e677e1d 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -102,7 +102,6 @@ struct extent_io_ops {
 				    struct page *page, u64 start, u64 end,
 				    int mirror);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
-	void (*set_range_writeback)(void *private_data, u64 start, u64 end);
 
 	/*
 	 * Optional hooks, called if the pointer is not NULL
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index a72784d5666f..4955e04da4c8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -10487,9 +10487,9 @@ static void btrfs_check_extent_io_range(void *private_data, const char *caller,
 	}
 }
 
-void btrfs_set_range_writeback(void *private_data, u64 start, u64 end)
+void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 {
-	struct inode *inode = private_data;
+	struct inode *inode = tree->private_data;
 	unsigned long index = start >> PAGE_SHIFT;
 	unsigned long end_index = end >> PAGE_SHIFT;
 	struct page *page;
@@ -10546,7 +10546,6 @@ static const struct extent_io_ops btrfs_extent_io_ops = {
 	.submit_bio_hook = btrfs_submit_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
 	.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
-	.set_range_writeback = btrfs_set_range_writeback,
 
 	/* optional callbacks */
 	.fill_delalloc = run_delalloc_range,
-- 
cgit v1.2.3


From ca5d2ba1ae2dfd651b798218d56c3277784fa499 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 23 Jul 2018 09:10:09 +0100
Subject: Btrfs: remove unused key assignment when doing a full send

At send.c:full_send_tree() we were setting the 'key' variable in the loop
while never using it later. We were also using two btrfs_key variables
to store the initial key for search and the key found in every iteration
of the loop. So remove this useless key assignment and use the same
btrfs_key variable to store the initial search key and the key found in
each iteration. This was introduced in the initial send commit but was
never used (commit 31db9f7c23fb ("Btrfs: introduce BTRFS_IOC_SEND for
btrfs send/receive").

Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/send.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 6ff7a1315e52..42e04cd3cd95 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -6325,7 +6325,6 @@ static int full_send_tree(struct send_ctx *sctx)
 	int ret;
 	struct btrfs_root *send_root = sctx->send_root;
 	struct btrfs_key key;
-	struct btrfs_key found_key;
 	struct btrfs_path *path;
 	struct extent_buffer *eb;
 	int slot;
@@ -6347,17 +6346,13 @@ static int full_send_tree(struct send_ctx *sctx)
 	while (1) {
 		eb = path->nodes[0];
 		slot = path->slots[0];
-		btrfs_item_key_to_cpu(eb, &found_key, slot);
+		btrfs_item_key_to_cpu(eb, &key, slot);
 
-		ret = changed_cb(path, NULL, &found_key,
+		ret = changed_cb(path, NULL, &key,
 				 BTRFS_COMPARE_TREE_NEW, sctx);
 		if (ret < 0)
 			goto out;
 
-		key.objectid = found_key.objectid;
-		key.type = found_key.type;
-		key.offset = found_key.offset + 1;
-
 		ret = btrfs_next_item(send_root, path);
 		if (ret < 0)
 			goto out;
-- 
cgit v1.2.3


From 5e23a6fea6189d1f9d6e6ca5cb3290b4a0fe2d48 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 23 Jul 2018 14:47:29 +0800
Subject: btrfs: extent-tree: Remove dead alignment check

In find_free_extent() under checks: label, we have the following code:

		search_start = ALIGN(offset, fs_info->stripesize);
		/* move on to the next group */
		if (search_start + num_bytes >
		    block_group->key.objectid + block_group->key.offset) {
			btrfs_add_free_space(block_group, offset, num_bytes);
			goto loop;
		}
		if (offset < search_start)
			btrfs_add_free_space(block_group, offset,
					     search_start - offset);
		BUG_ON(offset > search_start);

However ALIGN() is rounding up, thus @search_start >= @offset and that
BUG_ON() will never be triggered.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index fd109bfd528d..c71aa118679d 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -7564,7 +7564,7 @@ unclustered_alloc:
 			goto loop;
 		}
 checks:
-		search_start = ALIGN(offset, fs_info->stripesize);
+		search_start = round_up(offset, fs_info->stripesize);
 
 		/* move on to the next group */
 		if (search_start + num_bytes >
@@ -7576,7 +7576,6 @@ checks:
 		if (offset < search_start)
 			btrfs_add_free_space(block_group, offset,
 					     search_start - offset);
-		BUG_ON(offset > search_start);
 
 		ret = btrfs_add_reserved_bytes(block_group, ram_bytes,
 				num_bytes, delalloc);
-- 
cgit v1.2.3


From 8e87e8562744e23e10afea98d610cc6b7f4ba9bb Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 20 Jul 2018 19:37:47 +0300
Subject: btrfs: Remove fs_info argument from btrfs_add_dev_item

It can be referenced form the passed transaction handle.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f237ef9e70a7..1c88c4c947bb 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1666,10 +1666,8 @@ error:
  * the btrfs_device struct should be fully filled in
  */
 static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info,
 			    struct btrfs_device *device)
 {
-	struct btrfs_root *root = fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_dev_item *dev_item;
@@ -1685,8 +1683,8 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	key.type = BTRFS_DEV_ITEM_KEY;
 	key.offset = device->devid;
 
-	ret = btrfs_insert_empty_item(trans, root, path, &key,
-				      sizeof(*dev_item));
+	ret = btrfs_insert_empty_item(trans, trans->fs_info->chunk_root, path,
+				      &key, sizeof(*dev_item));
 	if (ret)
 		goto out;
 
@@ -1711,7 +1709,7 @@ static int btrfs_add_dev_item(struct btrfs_trans_handle *trans,
 	ptr = btrfs_device_uuid(dev_item);
 	write_extent_buffer(leaf, device->uuid, ptr, BTRFS_UUID_SIZE);
 	ptr = btrfs_device_fsid(dev_item);
-	write_extent_buffer(leaf, fs_info->fsid, ptr, BTRFS_FSID_SIZE);
+	write_extent_buffer(leaf, trans->fs_info->fsid, ptr, BTRFS_FSID_SIZE);
 	btrfs_mark_buffer_dirty(leaf);
 
 	ret = 0;
@@ -2449,7 +2447,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 		}
 	}
 
-	ret = btrfs_add_dev_item(trans, fs_info, device);
+	ret = btrfs_add_dev_item(trans, device);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto error_sysfs;
-- 
cgit v1.2.3


From 68a9db5f2395cdef98b387bbb816604f6f298056 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 20 Jul 2018 19:37:48 +0300
Subject: btrfs: Remove fs_info from btrfs_rm_dev_replace_remove_srcdev

It can be referenced from the passed srcdev argument.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dev-replace.c | 2 +-
 fs/btrfs/volumes.c     | 5 ++---
 fs/btrfs/volumes.h     | 3 +--
 3 files changed, 4 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 059ca3d5ddd3..df375e1a0c9f 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -667,7 +667,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 
 	btrfs_rm_dev_replace_blocked(fs_info);
 
-	btrfs_rm_dev_replace_remove_srcdev(fs_info, src_device);
+	btrfs_rm_dev_replace_remove_srcdev(src_device);
 
 	btrfs_rm_dev_replace_unblocked(fs_info);
 
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 1c88c4c947bb..d82658b01773 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1996,12 +1996,11 @@ error_undo:
 	goto out;
 }
 
-void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
-					struct btrfs_device *srcdev)
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev)
 {
 	struct btrfs_fs_devices *fs_devices;
 
-	lockdep_assert_held(&fs_info->fs_devices->device_list_mutex);
+	lockdep_assert_held(&srcdev->fs_info->fs_devices->device_list_mutex);
 
 	/*
 	 * in case of fs with no seed, srcdev->fs_devices will point
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 6943aab9bdd7..0ae45ff1961b 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -452,8 +452,7 @@ void btrfs_init_devices_late(struct btrfs_fs_info *fs_info);
 int btrfs_init_dev_stats(struct btrfs_fs_info *fs_info);
 int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 			struct btrfs_fs_info *fs_info);
-void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_fs_info *fs_info,
-					struct btrfs_device *srcdev);
+void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev);
 void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *srcdev);
 void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-- 
cgit v1.2.3


From 5495f195fc5b246d8b0b8a2e0fbbc9c94b3ebf24 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 20 Jul 2018 19:37:49 +0300
Subject: btrfs: remove fs_info argument from update_dev_stat_item

It can be referenced from the passed transaction handle.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d82658b01773..fc9d70a16d82 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7043,9 +7043,9 @@ out:
 }
 
 static int update_dev_stat_item(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
 				struct btrfs_device *device)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *dev_root = fs_info->dev_root;
 	struct btrfs_path *path;
 	struct btrfs_key key;
@@ -7138,7 +7138,7 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 		 */
 		smp_rmb();
 
-		ret = update_dev_stat_item(trans, fs_info, device);
+		ret = update_dev_stat_item(trans, device);
 		if (!ret)
 			atomic_sub(stats_cnt, &device->dev_stats_ccnt);
 	}
-- 
cgit v1.2.3


From d6507cf1e2dfa4f6888cd90e4c9a307f7ac9b383 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 20 Jul 2018 19:37:50 +0300
Subject: btrfs: Remove fs_info from btrfs_assign_next_active_device

It can be referenced from the passed 'device' argument which is always
a well-formed device.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dev-replace.c | 2 +-
 fs/btrfs/volumes.c     | 9 +++++----
 fs/btrfs/volumes.h     | 4 ++--
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index df375e1a0c9f..dd17a4d7bea2 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -658,7 +658,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 	tgt_device->commit_total_bytes = src_device->commit_total_bytes;
 	tgt_device->commit_bytes_used = src_device->bytes_used;
 
-	btrfs_assign_next_active_device(fs_info, src_device, tgt_device);
+	btrfs_assign_next_active_device(src_device, tgt_device);
 
 	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
 	fs_info->fs_devices->rw_devices++;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index fc9d70a16d82..9cd15964ab6f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -1833,9 +1833,10 @@ static struct btrfs_device * btrfs_find_next_active_device(
  * where this function called, there should be always be another device (or
  * this_dev) which is active.
  */
-void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
-		struct btrfs_device *device, struct btrfs_device *this_dev)
+void btrfs_assign_next_active_device(struct btrfs_device *device,
+				     struct btrfs_device *this_dev)
 {
+	struct btrfs_fs_info *fs_info = device->fs_info;
 	struct btrfs_device *next_device;
 
 	if (this_dev)
@@ -1945,7 +1946,7 @@ int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
 	if (test_bit(BTRFS_DEV_STATE_MISSING, &device->dev_state))
 		cur_devices->missing_devices--;
 
-	btrfs_assign_next_active_device(fs_info, device, NULL);
+	btrfs_assign_next_active_device(device, NULL);
 
 	if (device->bdev) {
 		cur_devices->open_devices--;
@@ -2077,7 +2078,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 
 	fs_devices->num_devices--;
 
-	btrfs_assign_next_active_device(fs_info, tgtdev, NULL);
+	btrfs_assign_next_active_device(tgtdev, NULL);
 
 	list_del_rcu(&tgtdev->dev_list);
 
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 0ae45ff1961b..1bcf0f34e8dc 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -407,8 +407,8 @@ struct btrfs_device *btrfs_scan_one_device(const char *path,
 					   fmode_t flags, void *holder);
 int btrfs_close_devices(struct btrfs_fs_devices *fs_devices);
 void btrfs_free_extra_devids(struct btrfs_fs_devices *fs_devices, int step);
-void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
-		struct btrfs_device *device, struct btrfs_device *this_dev);
+void btrfs_assign_next_active_device(struct btrfs_device *device,
+				     struct btrfs_device *this_dev);
 int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
 					 const char *device_path,
 					 struct btrfs_device **device);
-- 
cgit v1.2.3


From 4f5ad7bd6315528ed50a11d53c66854a5d16425b Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 20 Jul 2018 19:37:51 +0300
Subject: btrfs: Remove fs_info from btrfs_destroy_dev_replace_tgtdev

This function is always passed a well-formed tgtdevice so the fs_info
can be referenced from there.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dev-replace.c | 6 +++---
 fs/btrfs/volumes.c     | 5 ++---
 fs/btrfs/volumes.h     | 3 +--
 3 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index dd17a4d7bea2..5a72f9933e58 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -506,7 +506,7 @@ leave:
 	dev_replace->srcdev = NULL;
 	dev_replace->tgtdev = NULL;
 	btrfs_dev_replace_write_unlock(dev_replace);
-	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+	btrfs_destroy_dev_replace_tgtdev(tgt_device);
 	return ret;
 }
 
@@ -632,7 +632,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
-			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+			btrfs_destroy_dev_replace_tgtdev(tgt_device);
 		btrfs_rm_dev_replace_unblocked(fs_info);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
@@ -821,7 +821,7 @@ int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
 		btrfs_dev_name(tgt_device));
 
 	if (tgt_device)
-		btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+		btrfs_destroy_dev_replace_tgtdev(tgt_device);
 
 leave:
 	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 9cd15964ab6f..45d7c37050ce 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2063,10 +2063,9 @@ void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 	}
 }
 
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				      struct btrfs_device *tgtdev)
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev)
 {
-	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
+	struct btrfs_fs_devices *fs_devices = tgtdev->fs_info->fs_devices;
 
 	WARN_ON(!tgtdev);
 	mutex_lock(&fs_devices->device_list_mutex);
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 1bcf0f34e8dc..69a028058c43 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -455,8 +455,7 @@ int btrfs_run_dev_stats(struct btrfs_trans_handle *trans,
 void btrfs_rm_dev_replace_remove_srcdev(struct btrfs_device *srcdev);
 void btrfs_rm_dev_replace_free_srcdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *srcdev);
-void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				      struct btrfs_device *tgtdev);
+void btrfs_destroy_dev_replace_tgtdev(struct btrfs_device *tgtdev);
 void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path);
 int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 			   u64 logical, u64 len);
-- 
cgit v1.2.3


From f4208794d02e74f16e5744fe2fe294d7f71fa0f9 Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 20 Jul 2018 19:37:52 +0300
Subject: btrfs: Remove fs_info form btrfs_free_chunk

It can be referenced from the passed transaction handle.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 45d7c37050ce..991022f5219f 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2605,9 +2605,9 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 	return btrfs_update_device(trans, device);
 }
 
-static int btrfs_free_chunk(struct btrfs_trans_handle *trans,
-			    struct btrfs_fs_info *fs_info, u64 chunk_offset)
+static int btrfs_free_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *root = fs_info->chunk_root;
 	int ret;
 	struct btrfs_path *path;
@@ -2777,7 +2777,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	}
 	mutex_unlock(&fs_devices->device_list_mutex);
 
-	ret = btrfs_free_chunk(trans, fs_info, chunk_offset);
+	ret = btrfs_free_chunk(trans, chunk_offset);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
-- 
cgit v1.2.3


From 97aff912a2fa75555641303d42bd4c723a98df5d Mon Sep 17 00:00:00 2001
From: Nikolay Borisov <nborisov@suse.com>
Date: Fri, 20 Jul 2018 19:37:53 +0300
Subject: btrfs: Remove fs_info from btrfs_finish_chunk_alloc

It can be referenced from the passed transaction handle.

Signed-off-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c |  6 ++----
 fs/btrfs/volumes.c     | 10 +++++-----
 fs/btrfs/volumes.h     |  6 ++----
 3 files changed, 9 insertions(+), 13 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index c71aa118679d..16b916a33e56 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -10022,8 +10022,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans)
 					sizeof(item));
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
-		ret = btrfs_finish_chunk_alloc(trans, fs_info, key.objectid,
-					       key.offset);
+		ret = btrfs_finish_chunk_alloc(trans, key.objectid, key.offset);
 		if (ret)
 			btrfs_abort_transaction(trans, ret);
 		add_block_group_free_space(trans, block_group);
@@ -10594,8 +10593,7 @@ void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info)
 		 * Btrfs_remove_chunk will abort the transaction if things go
 		 * horribly wrong.
 		 */
-		ret = btrfs_remove_chunk(trans, fs_info,
-					 block_group->key.objectid);
+		ret = btrfs_remove_chunk(trans, block_group->key.objectid);
 
 		if (ret) {
 			if (trimming)
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 991022f5219f..d86346f83a08 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2716,9 +2716,9 @@ static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info,
 	return em;
 }
 
-int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 chunk_offset)
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct extent_map *em;
 	struct map_lookup *map;
 	u64 dev_extent_len = 0;
@@ -2858,7 +2858,7 @@ static int btrfs_relocate_chunk(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 	 * step two, delete the device extents and the
 	 * chunk tree entries
 	 */
-	ret = btrfs_remove_chunk(trans, fs_info, chunk_offset);
+	ret = btrfs_remove_chunk(trans, chunk_offset);
 	btrfs_end_transaction(trans);
 	return ret;
 }
@@ -4842,9 +4842,9 @@ error:
 }
 
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
-				u64 chunk_offset, u64 chunk_size)
+			     u64 chunk_offset, u64 chunk_size)
 {
+	struct btrfs_fs_info *fs_info = trans->fs_info;
 	struct btrfs_root *extent_root = fs_info->extent_root;
 	struct btrfs_root *chunk_root = fs_info->chunk_root;
 	struct btrfs_key key;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 69a028058c43..049619176831 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -462,10 +462,8 @@ int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    u64 logical);
 int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
-				u64 chunk_offset, u64 chunk_size);
-int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info, u64 chunk_offset);
+			     u64 chunk_offset, u64 chunk_size);
+int btrfs_remove_chunk(struct btrfs_trans_handle *trans, u64 chunk_offset);
 
 static inline void btrfs_dev_stat_inc(struct btrfs_device *dev,
 				      int index)
-- 
cgit v1.2.3


From 3c4276936f6fbe52884b4ea4e6cc120b890a0f9f Mon Sep 17 00:00:00 2001
From: Josef Bacik <jbacik@fb.com>
Date: Fri, 20 Jul 2018 11:46:10 -0700
Subject: Btrfs: fix btrfs_write_inode vs delayed iput deadlock

We recently ran into the following deadlock involving
btrfs_write_inode():

[  +0.005066]  __schedule+0x38e/0x8c0
[  +0.007144]  schedule+0x36/0x80
[  +0.006447]  bit_wait+0x11/0x60
[  +0.006446]  __wait_on_bit+0xbe/0x110
[  +0.007487]  ? bit_wait_io+0x60/0x60
[  +0.007319]  __inode_wait_for_writeback+0x96/0xc0
[  +0.009568]  ? autoremove_wake_function+0x40/0x40
[  +0.009565]  inode_wait_for_writeback+0x21/0x30
[  +0.009224]  evict+0xb0/0x190
[  +0.006099]  iput+0x1a8/0x210
[  +0.006103]  btrfs_run_delayed_iputs+0x73/0xc0
[  +0.009047]  btrfs_commit_transaction+0x799/0x8c0
[  +0.009567]  btrfs_write_inode+0x81/0xb0
[  +0.008008]  __writeback_single_inode+0x267/0x320
[  +0.009569]  writeback_sb_inodes+0x25b/0x4e0
[  +0.008702]  wb_writeback+0x102/0x2d0
[  +0.007487]  wb_workfn+0xa4/0x310
[  +0.006794]  ? wb_workfn+0xa4/0x310
[  +0.007143]  process_one_work+0x150/0x410
[  +0.008179]  worker_thread+0x6d/0x520
[  +0.007490]  kthread+0x12c/0x160
[  +0.006620]  ? put_pwq_unlocked+0x80/0x80
[  +0.008185]  ? kthread_park+0xa0/0xa0
[  +0.007484]  ? do_syscall_64+0x53/0x150
[  +0.007837]  ret_from_fork+0x29/0x40

Writeback calls:

btrfs_write_inode
  btrfs_commit_transaction
    btrfs_run_delayed_iputs

If iput() is called on that same inode, evict() will wait for writeback
forever.

btrfs_write_inode() was originally added way back in 4730a4bc5bf3
("btrfs_dirty_inode") to support O_SYNC writes. However, ->write_inode()
hasn't been used for O_SYNC since 148f948ba877 ("vfs: Introduce new
helpers for syncing after writing to O_SYNC file or IS_SYNC inode"), so
btrfs_write_inode() is actually unnecessary (and leads to a bunch of
unnecessary commits). Get rid of it, which also gets rid of the
deadlock.

CC: stable@vger.kernel.org # 3.2+
Signed-off-by: Josef Bacik <jbacik@fb.com>
[Omar: new commit message]
Signed-off-by: Omar Sandoval <osandov@fb.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 26 --------------------------
 fs/btrfs/super.c |  1 -
 2 files changed, 27 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 4955e04da4c8..472457795486 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6021,32 +6021,6 @@ err:
 	return ret;
 }
 
-int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
-{
-	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_trans_handle *trans;
-	int ret = 0;
-	bool nolock = false;
-
-	if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
-		return 0;
-
-	if (btrfs_fs_closing(root->fs_info) &&
-			btrfs_is_free_space_inode(BTRFS_I(inode)))
-		nolock = true;
-
-	if (wbc->sync_mode == WB_SYNC_ALL) {
-		if (nolock)
-			trans = btrfs_join_transaction_nolock(root);
-		else
-			trans = btrfs_join_transaction(root);
-		if (IS_ERR(trans))
-			return PTR_ERR(trans);
-		ret = btrfs_commit_transaction(trans);
-	}
-	return ret;
-}
-
 /*
  * This is somewhat expensive, updating the tree every time the
  * inode changes.  But, it is most likely to find the inode in cache.
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index efe8b03ce380..67de3c0fc85b 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2344,7 +2344,6 @@ static const struct super_operations btrfs_super_ops = {
 	.sync_fs	= btrfs_sync_fs,
 	.show_options	= btrfs_show_options,
 	.show_devname	= btrfs_show_devname,
-	.write_inode	= btrfs_write_inode,
 	.alloc_inode	= btrfs_alloc_inode,
 	.destroy_inode	= btrfs_destroy_inode,
 	.statfs		= btrfs_statfs,
-- 
cgit v1.2.3


From 616d374efa23cb699074ea02b301254ad64d224a Mon Sep 17 00:00:00 2001
From: Adam Borowski <kilobyte@angband.pl>
Date: Wed, 18 Jul 2018 00:08:59 +0200
Subject: btrfs: allow defrag on a file opened read-only that has rw
 permissions

Requiring a read-write descriptor conflicts both ways with exec,
returning ETXTBSY whenever you try to defrag a program that's currently
being run, or causing intermittent exec failures on a live system being
defragged.

As defrag doesn't change the file's contents in any way, there's no
reason to consider it a rw operation.  Thus, let's check only whether
the file could have been opened rw.  Such access control is still needed
as currently defrag can use extra disk space, and might trigger bugs.

We return EINVAL when the request is invalid; here it's ok but merely
the user has insufficient privileges.  Thus, the EPERM return value
reflects the error better -- as discussed in the identical case for
dedupe.

According to codesearch.debian.net, no userspace program distinguishes
these values beyond strerror().

Signed-off-by: Adam Borowski <kilobyte@angband.pl>
Reviewed-by: David Sterba <dsterba@suse.com>
[ fold the EPERM patch from Adam ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 4482cf35522e..80fe3c654612 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -2928,8 +2928,14 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 		ret = btrfs_defrag_root(root);
 		break;
 	case S_IFREG:
-		if (!(file->f_mode & FMODE_WRITE)) {
-			ret = -EINVAL;
+		/*
+		 * Note that this does not check the file descriptor for write
+		 * access. This prevents defragmenting executables that are
+		 * running and allows defrag on files open in read-only mode.
+		 */
+		if (!capable(CAP_SYS_ADMIN) &&
+		    inode_permission(inode, MAY_WRITE)) {
+			ret = -EPERM;
 			goto out;
 		}
 
-- 
cgit v1.2.3


From e17385ca2960177da402d6f4d80bdc5b53c29bc4 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 20 Jul 2018 16:30:18 +0200
Subject: btrfs: remove unused member btrfs_root::name

Added in 58176a9604c ("Btrfs: Add per-root block accounting and sysfs
entries") in 2007, the roots had names exported in sysfs. The code
was commented out in 4df27c4d5cc1dda54ed ("Btrfs: change how subvolumes
are organized") and cleaned by 182608c8294b5fe9 ("btrfs: remove old
unused commented out code").

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h   | 1 -
 fs/btrfs/disk-io.c | 2 --
 2 files changed, 3 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9c638931b75e..4ca6c4e141ea 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1219,7 +1219,6 @@ struct btrfs_root {
 	u64 defrag_trans_start;
 	struct btrfs_key defrag_progress;
 	struct btrfs_key defrag_max;
-	char *name;
 
 	/* the dirty list is only used by non-reference counted roots */
 	struct list_head dirty_list;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 9b208ccf24fe..3830867e0225 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1154,7 +1154,6 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	root->highest_objectid = 0;
 	root->nr_delalloc_inodes = 0;
 	root->nr_ordered_extents = 0;
-	root->name = NULL;
 	root->inode_tree = RB_ROOT;
 	INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
 	root->block_rsv = NULL;
@@ -3849,7 +3848,6 @@ static void free_fs_root(struct btrfs_root *root)
 	free_extent_buffer(root->commit_root);
 	kfree(root->free_ino_ctl);
 	kfree(root->free_ino_pinned);
-	kfree(root->name);
 	btrfs_put_fs_root(root);
 }
 
-- 
cgit v1.2.3


From e9539cff04728e31e150b41000b828745fc0c2b3 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 20 Jul 2018 16:30:20 +0200
Subject: btrfs: dev-replace: remove unused members of btrfs_dev_replace

Lock owner and nesting level have been unused since day 1, probably
copy&pasted from the extent_buffer locking scheme without much thinking.
The locking of device replace is simpler and does not need any lock
nesting.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h   | 2 --
 fs/btrfs/disk-io.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 4ca6c4e141ea..5f6ec80d374f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -365,8 +365,6 @@ struct btrfs_dev_replace {
 	struct btrfs_device *srcdev;
 	struct btrfs_device *tgtdev;
 
-	pid_t lock_owner;
-	atomic_t nesting_level;
 	struct mutex lock_finishing_cancel_unmount;
 	rwlock_t lock;
 	atomic_t read_locks;
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 3830867e0225..c1d287a766c1 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2154,8 +2154,6 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 
 static void btrfs_init_dev_replace_locks(struct btrfs_fs_info *fs_info)
 {
-	fs_info->dev_replace.lock_owner = 0;
-	atomic_set(&fs_info->dev_replace.nesting_level, 0);
 	mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
 	rwlock_init(&fs_info->dev_replace.lock);
 	atomic_set(&fs_info->dev_replace.read_locks, 0);
-- 
cgit v1.2.3


From 2ffad70ed3b6fbc946bc102f9d11c0e7c1cd380f Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 20 Jul 2018 16:30:23 +0200
Subject: btrfs: constify strings passed to assertion helper

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 5f6ec80d374f..2e32584c635f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -3425,7 +3425,7 @@ do {								\
 #ifdef CONFIG_BTRFS_ASSERT
 
 __cold
-static inline void assfail(char *expr, char *file, int line)
+static inline void assfail(const char *expr, const char *file, int line)
 {
 	pr_err("assertion failed: %s, file: %s, line: %d\n",
 	       expr, file, line);
-- 
cgit v1.2.3


From 84db5ccf4262894852e0d178d250678945d9b0b8 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Fri, 20 Jul 2018 16:30:25 +0200
Subject: btrfs: merge free_fs_root helpers

The exported helper just calls the static one. There's no obvious reason
to have them separate eg. for performance reasons where the static one
could be better optimized in the same unit. There's a slight decrease in
code size and stack consumption.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index c1d287a766c1..6a5a3cd12886 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -52,7 +52,6 @@
 
 static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
-static void free_fs_root(struct btrfs_root *root);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_fs_info *fs_info);
@@ -1504,7 +1503,7 @@ int btrfs_init_fs_root(struct btrfs_root *root)
 
 	return 0;
 fail:
-	/* the caller is responsible to call free_fs_root */
+	/* The caller is responsible to call btrfs_free_fs_root */
 	return ret;
 }
 
@@ -1609,14 +1608,14 @@ again:
 	ret = btrfs_insert_fs_root(fs_info, root);
 	if (ret) {
 		if (ret == -EEXIST) {
-			free_fs_root(root);
+			btrfs_free_fs_root(root);
 			goto again;
 		}
 		goto fail;
 	}
 	return root;
 fail:
-	free_fs_root(root);
+	btrfs_free_fs_root(root);
 	return ERR_PTR(ret);
 }
 
@@ -3831,10 +3830,10 @@ void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 		__btrfs_remove_free_space_cache(root->free_ino_pinned);
 	if (root->free_ino_ctl)
 		__btrfs_remove_free_space_cache(root->free_ino_ctl);
-	free_fs_root(root);
+	btrfs_free_fs_root(root);
 }
 
-static void free_fs_root(struct btrfs_root *root)
+void btrfs_free_fs_root(struct btrfs_root *root)
 {
 	iput(root->ino_cache_inode);
 	WARN_ON(!RB_EMPTY_ROOT(&root->inode_tree));
@@ -3849,11 +3848,6 @@ static void free_fs_root(struct btrfs_root *root)
 	btrfs_put_fs_root(root);
 }
 
-void btrfs_free_fs_root(struct btrfs_root *root)
-{
-	free_fs_root(root);
-}
-
 int btrfs_cleanup_fs_roots(struct btrfs_fs_info *fs_info)
 {
 	u64 root_objectid = 0;
-- 
cgit v1.2.3


From 4559b0a71749c442d34f7cfb9e72c9e58db83948 Mon Sep 17 00:00:00 2001
From: Josef Bacik <josef@toxicpanda.com>
Date: Thu, 19 Jul 2018 10:49:51 -0400
Subject: btrfs: don't leak ret from do_chunk_alloc

If we're trying to make a data reservation and we have to allocate a
data chunk we could leak ret == 1, as do_chunk_alloc() will return 1 if
it allocated a chunk.  Since the end of the function is the success path
just return 0.

CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Josef Bacik <josef@toxicpanda.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 16b916a33e56..2eb2d7ac0ba4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4226,7 +4226,7 @@ commit_trans:
 				      data_sinfo->flags, bytes, 1);
 	spin_unlock(&data_sinfo->lock);
 
-	return ret;
+	return 0;
 }
 
 int btrfs_check_data_free_space(struct inode *inode,
-- 
cgit v1.2.3


From 0d836392cadd5535f4184d46d901a82eb276ed62 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Fri, 20 Jul 2018 10:59:06 +0100
Subject: Btrfs: fix mount failure after fsync due to hard link recreation

If we end up with logging an inode reference item which has the same name
but different index from the one we have persisted, we end up failing when
replaying the log with an errno value of -EEXIST. The error comes from
btrfs_add_link(), which is called from add_inode_ref(), when we are
replaying an inode reference item.

Example scenario where this happens:

  $ mkfs.btrfs -f /dev/sdb
  $ mount /dev/sdb /mnt

  $ touch /mnt/foo
  $ ln /mnt/foo /mnt/bar

  $ sync

  # Rename the first hard link (foo) to a new name and rename the second
  # hard link (bar) to the old name of the first hard link (foo).
  $ mv /mnt/foo /mnt/qwerty
  $ mv /mnt/bar /mnt/foo

  # Create a new file, in the same parent directory, with the old name of
  # the second hard link (bar) and fsync this new file.
  # We do this instead of calling fsync on foo/qwerty because if we did
  # that the fsync resulted in a full transaction commit, not triggering
  # the problem.
  $ touch /mnt/bar
  $ xfs_io -c "fsync" /mnt/bar

  <power fail>

  $ mount /dev/sdb /mnt
  mount: mount /dev/sdb on /mnt failed: File exists

So fix this by checking if a conflicting inode reference exists (same
name, same parent but different index), removing it (and the associated
dir index entries from the parent inode) if it exists, before attempting
to add the new reference.

A test case for fstests follows soon.

CC: stable@vger.kernel.org # 4.4+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tree-log.c | 66 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 10f6a4223897..033aeebbe9de 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -1290,6 +1290,46 @@ again:
 	return ret;
 }
 
+static int btrfs_inode_ref_exists(struct inode *inode, struct inode *dir,
+				  const u8 ref_type, const char *name,
+				  const int namelen)
+{
+	struct btrfs_key key;
+	struct btrfs_path *path;
+	const u64 parent_id = btrfs_ino(BTRFS_I(dir));
+	int ret;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = btrfs_ino(BTRFS_I(inode));
+	key.type = ref_type;
+	if (key.type == BTRFS_INODE_REF_KEY)
+		key.offset = parent_id;
+	else
+		key.offset = btrfs_extref_hash(parent_id, name, namelen);
+
+	ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0) {
+		ret = 0;
+		goto out;
+	}
+	if (key.type == BTRFS_INODE_EXTREF_KEY)
+		ret = btrfs_find_name_in_ext_backref(path->nodes[0],
+						     path->slots[0], parent_id,
+						     name, namelen, NULL);
+	else
+		ret = btrfs_find_name_in_backref(path->nodes[0], path->slots[0],
+						 name, namelen, NULL);
+
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 /*
  * replay one inode back reference item found in the log tree.
  * eb, slot and key refer to the buffer and key found in the log tree.
@@ -1399,6 +1439,32 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				}
 			}
 
+			/*
+			 * If a reference item already exists for this inode
+			 * with the same parent and name, but different index,
+			 * drop it and the corresponding directory index entries
+			 * from the parent before adding the new reference item
+			 * and dir index entries, otherwise we would fail with
+			 * -EEXIST returned from btrfs_add_link() below.
+			 */
+			ret = btrfs_inode_ref_exists(inode, dir, key->type,
+						     name, namelen);
+			if (ret > 0) {
+				ret = btrfs_unlink_inode(trans, root,
+							 BTRFS_I(dir),
+							 BTRFS_I(inode),
+							 name, namelen);
+				/*
+				 * If we dropped the link count to 0, bump it so
+				 * that later the iput() on the inode will not
+				 * free it. We will fixup the link count later.
+				 */
+				if (!ret && inode->i_nlink == 0)
+					inc_nlink(inode);
+			}
+			if (ret < 0)
+				goto out;
+
 			/* insert our name */
 			ret = btrfs_add_link(trans, BTRFS_I(dir),
 					BTRFS_I(inode),
-- 
cgit v1.2.3


From 46b2f4590aab71d31088a265c86026b1e96c9de4 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Tue, 24 Jul 2018 11:54:04 +0100
Subject: Btrfs: fix send failure when root has deleted files still open

The more common use case of send involves creating a RO snapshot and then
use it for a send operation. In this case it's not possible to have inodes
in the snapshot that have a link count of zero (inode with an orphan item)
since during snapshot creation we do the orphan cleanup. However, other
less common use cases for send can end up seeing inodes with a link count
of zero and in this case the send operation fails with a ENOENT error
because any attempt to generate a path for the inode, with the purpose
of creating it or updating it at the receiver, fails since there are no
inode reference items. One use case it to use a regular subvolume for
a send operation after turning it to RO mode or turning a RW snapshot
into RO mode and then using it for a send operation. In both cases, if a
file gets all its hard links deleted while there is an open file
descriptor before turning the subvolume/snapshot into RO mode, the send
operation will encounter an inode with a link count of zero and then
fail with errno ENOENT.

Example using a full send with a subvolume:

  $ mkfs.btrfs -f /dev/sdb
  $ mount /dev/sdb /mnt

  $ btrfs subvolume create /mnt/sv1
  $ touch /mnt/sv1/foo
  $ touch /mnt/sv1/bar

  # keep an open file descriptor on file bar
  $ exec 73</mnt/sv1/bar
  $ unlink /mnt/sv1/bar

  # Turn the subvolume to RO mode and use it for a full send, while
  # holding the open file descriptor.
  $ btrfs property set /mnt/sv1 ro true

  $ btrfs send -f /tmp/full.send /mnt/sv1
  At subvol /mnt/sv1
  ERROR: send ioctl failed with -2: No such file or directory

Example using an incremental send with snapshots:

  $ mkfs.btrfs -f /dev/sdb
  $ mount /dev/sdb /mnt

  $ btrfs subvolume create /mnt/sv1
  $ touch /mnt/sv1/foo
  $ touch /mnt/sv1/bar

  $ btrfs subvolume snapshot -r /mnt/sv1 /mnt/snap1

  $ echo "hello world" >> /mnt/sv1/bar

  $ btrfs subvolume snapshot -r /mnt/sv1 /mnt/snap2

  # Turn the second snapshot to RW mode and delete file foo while
  # holding an open file descriptor on it.
  $ btrfs property set /mnt/snap2 ro false
  $ exec 73</mnt/snap2/foo
  $ unlink /mnt/snap2/foo

  # Set the second snapshot back to RO mode and do an incremental send.
  $ btrfs property set /mnt/snap2 ro true

  $ btrfs send -f /tmp/inc.send -p /mnt/snap1 /mnt/snap2
  At subvol /mnt/snap2
  ERROR: send ioctl failed with -2: No such file or directory

So fix this by ignoring inodes with a link count of zero if we are either
doing a full send or if they do not exist in the parent snapshot (they
are new in the send snapshot), and unlink all paths found in the parent
snapshot when doing an incremental send (and ignoring all other inode
items, such as xattrs and extents).

A test case for fstests follows soon.

CC: stable@vger.kernel.org # 4.4+
Reported-by: Martin Wilck <martin.wilck@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/send.c | 137 ++++++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 129 insertions(+), 8 deletions(-)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 42e04cd3cd95..551294a6c9e2 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -100,6 +100,7 @@ struct send_ctx {
 	u64 cur_inode_rdev;
 	u64 cur_inode_last_extent;
 	u64 cur_inode_next_write_offset;
+	bool ignore_cur_inode;
 
 	u64 send_progress;
 
@@ -5796,6 +5797,9 @@ static int finish_inode_if_needed(struct send_ctx *sctx, int at_end)
 	int pending_move = 0;
 	int refs_processed = 0;
 
+	if (sctx->ignore_cur_inode)
+		return 0;
+
 	ret = process_recorded_refs_if_needed(sctx, at_end, &pending_move,
 					      &refs_processed);
 	if (ret < 0)
@@ -5914,6 +5918,93 @@ out:
 	return ret;
 }
 
+struct parent_paths_ctx {
+	struct list_head *refs;
+	struct send_ctx *sctx;
+};
+
+static int record_parent_ref(int num, u64 dir, int index, struct fs_path *name,
+			     void *ctx)
+{
+	struct parent_paths_ctx *ppctx = ctx;
+
+	return record_ref(ppctx->sctx->parent_root, dir, name, ppctx->sctx,
+			  ppctx->refs);
+}
+
+/*
+ * Issue unlink operations for all paths of the current inode found in the
+ * parent snapshot.
+ */
+static int btrfs_unlink_all_paths(struct send_ctx *sctx)
+{
+	LIST_HEAD(deleted_refs);
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct parent_paths_ctx ctx;
+	int ret;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = sctx->cur_ino;
+	key.type = BTRFS_INODE_REF_KEY;
+	key.offset = 0;
+	ret = btrfs_search_slot(NULL, sctx->parent_root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	ctx.refs = &deleted_refs;
+	ctx.sctx = sctx;
+
+	while (true) {
+		struct extent_buffer *eb = path->nodes[0];
+		int slot = path->slots[0];
+
+		if (slot >= btrfs_header_nritems(eb)) {
+			ret = btrfs_next_leaf(sctx->parent_root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(eb, &key, slot);
+		if (key.objectid != sctx->cur_ino)
+			break;
+		if (key.type != BTRFS_INODE_REF_KEY &&
+		    key.type != BTRFS_INODE_EXTREF_KEY)
+			break;
+
+		ret = iterate_inode_ref(sctx->parent_root, path, &key, 1,
+					record_parent_ref, &ctx);
+		if (ret < 0)
+			goto out;
+
+		path->slots[0]++;
+	}
+
+	while (!list_empty(&deleted_refs)) {
+		struct recorded_ref *ref;
+
+		ref = list_first_entry(&deleted_refs, struct recorded_ref, list);
+		ret = send_unlink(sctx, ref->full_path);
+		if (ret < 0)
+			goto out;
+		fs_path_free(ref->full_path);
+		list_del(&ref->list);
+		kfree(ref);
+	}
+	ret = 0;
+out:
+	btrfs_free_path(path);
+	if (ret)
+		__free_recorded_refs(&deleted_refs);
+	return ret;
+}
+
 static int changed_inode(struct send_ctx *sctx,
 			 enum btrfs_compare_tree_result result)
 {
@@ -5928,6 +6019,7 @@ static int changed_inode(struct send_ctx *sctx,
 	sctx->cur_inode_new_gen = 0;
 	sctx->cur_inode_last_extent = (u64)-1;
 	sctx->cur_inode_next_write_offset = 0;
+	sctx->ignore_cur_inode = false;
 
 	/*
 	 * Set send_progress to current inode. This will tell all get_cur_xxx
@@ -5968,6 +6060,33 @@ static int changed_inode(struct send_ctx *sctx,
 			sctx->cur_inode_new_gen = 1;
 	}
 
+	/*
+	 * Normally we do not find inodes with a link count of zero (orphans)
+	 * because the most common case is to create a snapshot and use it
+	 * for a send operation. However other less common use cases involve
+	 * using a subvolume and send it after turning it to RO mode just
+	 * after deleting all hard links of a file while holding an open
+	 * file descriptor against it or turning a RO snapshot into RW mode,
+	 * keep an open file descriptor against a file, delete it and then
+	 * turn the snapshot back to RO mode before using it for a send
+	 * operation. So if we find such cases, ignore the inode and all its
+	 * items completely if it's a new inode, or if it's a changed inode
+	 * make sure all its previous paths (from the parent snapshot) are all
+	 * unlinked and all other the inode items are ignored.
+	 */
+	if (result == BTRFS_COMPARE_TREE_NEW ||
+	    result == BTRFS_COMPARE_TREE_CHANGED) {
+		u32 nlinks;
+
+		nlinks = btrfs_inode_nlink(sctx->left_path->nodes[0], left_ii);
+		if (nlinks == 0) {
+			sctx->ignore_cur_inode = true;
+			if (result == BTRFS_COMPARE_TREE_CHANGED)
+				ret = btrfs_unlink_all_paths(sctx);
+			goto out;
+		}
+	}
+
 	if (result == BTRFS_COMPARE_TREE_NEW) {
 		sctx->cur_inode_gen = left_gen;
 		sctx->cur_inode_new = 1;
@@ -6306,15 +6425,17 @@ static int changed_cb(struct btrfs_path *left_path,
 	    key->objectid == BTRFS_FREE_SPACE_OBJECTID)
 		goto out;
 
-	if (key->type == BTRFS_INODE_ITEM_KEY)
+	if (key->type == BTRFS_INODE_ITEM_KEY) {
 		ret = changed_inode(sctx, result);
-	else if (key->type == BTRFS_INODE_REF_KEY ||
-		 key->type == BTRFS_INODE_EXTREF_KEY)
-		ret = changed_ref(sctx, result);
-	else if (key->type == BTRFS_XATTR_ITEM_KEY)
-		ret = changed_xattr(sctx, result);
-	else if (key->type == BTRFS_EXTENT_DATA_KEY)
-		ret = changed_extent(sctx, result);
+	} else if (!sctx->ignore_cur_inode) {
+		if (key->type == BTRFS_INODE_REF_KEY ||
+		    key->type == BTRFS_INODE_EXTREF_KEY)
+			ret = changed_ref(sctx, result);
+		else if (key->type == BTRFS_XATTR_ITEM_KEY)
+			ret = changed_xattr(sctx, result);
+		else if (key->type == BTRFS_EXTENT_DATA_KEY)
+			ret = changed_extent(sctx, result);
+	}
 
 out:
 	return ret;
-- 
cgit v1.2.3


From b5851021f1ea0e099543fa125744368de7e9b865 Mon Sep 17 00:00:00 2001
From: David Sterba <dsterba@suse.com>
Date: Tue, 24 Jul 2018 17:19:48 +0200
Subject: btrfs: extent-tree: remove unused member walk_control::for_reloc

Leftover after fix e339a6b097c5 ("Btrfs: __btrfs_mod_ref should always
use no_quota"), that removed it from the function calls but not the
structure.

Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 2eb2d7ac0ba4..fcaf598f4222 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -8330,7 +8330,6 @@ struct walk_control {
 	int keep_locks;
 	int reada_slot;
 	int reada_count;
-	int for_reloc;
 };
 
 #define DROP_REFERENCE	1
@@ -8967,7 +8966,6 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = update_ref;
 	wc->keep_locks = 0;
-	wc->for_reloc = for_reloc;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);
 
 	while (1) {
@@ -9133,7 +9131,6 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
 	wc->stage = DROP_REFERENCE;
 	wc->update_ref = 0;
 	wc->keep_locks = 1;
-	wc->for_reloc = 1;
 	wc->reada_count = BTRFS_NODEPTRS_PER_BLOCK(fs_info);
 
 	while (1) {
-- 
cgit v1.2.3


From 4465c8b4229de50f17b6780677ce068b3582a55d Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 1 Aug 2018 11:32:25 +0800
Subject: btrfs: Remove fs_info from btrfs_insert_delayed_dir_index

It can be referenced from the passed transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-inode.c | 4 +---
 fs/btrfs/delayed-inode.h | 1 -
 fs/btrfs/dir-item.c      | 4 ++--
 3 files changed, 3 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 596d2af0c8aa..5d103eda1874 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1418,7 +1418,6 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 
 /* Will return 0 or -ENOMEM */
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
@@ -1458,11 +1457,10 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 	 */
 	BUG_ON(ret);
 
-
 	mutex_lock(&delayed_node->mutex);
 	ret = __btrfs_add_delayed_insertion_item(delayed_node, delayed_item);
 	if (unlikely(ret)) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 			  "err add delayed dir index item(name: %.*s) into the insertion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
 			  name_len, name, delayed_node->root->objectid,
 			  delayed_node->inode_id, ret);
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index ca7a97f3ab6b..44558ededcf5 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -86,7 +86,6 @@ static inline void btrfs_init_delayed_root(
 }
 
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
 				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 39e9766d1cbd..a678b07fcf01 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -160,8 +160,8 @@ second_insert:
 	}
 	btrfs_release_path(path);
 
-	ret2 = btrfs_insert_delayed_dir_index(trans, root->fs_info, name,
-			name_len, dir, &disk_key, type, index);
+	ret2 = btrfs_insert_delayed_dir_index(trans, name, name_len, dir,
+					      &disk_key, type, index);
 out_free:
 	btrfs_free_path(path);
 	if (ret)
-- 
cgit v1.2.3


From 9add29457ac124e846cde4b875c632edaa722c08 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 1 Aug 2018 11:32:26 +0800
Subject: btrfs: Remove fs_info from btrfs_delete_delayed_dir_index

It can be referenced from the passed transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/delayed-inode.c | 6 +++---
 fs/btrfs/delayed-inode.h | 1 -
 fs/btrfs/inode.c         | 4 ++--
 3 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 5d103eda1874..f51b509f2d9b 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -1493,7 +1493,6 @@ static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   struct btrfs_inode *dir, u64 index)
 {
 	struct btrfs_delayed_node *node;
@@ -1509,7 +1508,8 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	item_key.type = BTRFS_DIR_INDEX_KEY;
 	item_key.offset = index;
 
-	ret = btrfs_delete_delayed_insertion_item(fs_info, node, &item_key);
+	ret = btrfs_delete_delayed_insertion_item(trans->fs_info, node,
+						  &item_key);
 	if (!ret)
 		goto end;
 
@@ -1531,7 +1531,7 @@ int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 	mutex_lock(&node->mutex);
 	ret = __btrfs_add_delayed_deletion_item(node, item);
 	if (unlikely(ret)) {
-		btrfs_err(fs_info,
+		btrfs_err(trans->fs_info,
 			  "err add delayed dir index item(index: %llu) into the deletion tree of the delayed node(root id: %llu, inode id: %llu, errno: %d)",
 			  index, node->root->objectid, node->inode_id, ret);
 		BUG();
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 44558ededcf5..33536cd681d4 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -92,7 +92,6 @@ int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   u64 index);
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
-				   struct btrfs_fs_info *fs_info,
 				   struct btrfs_inode *dir, u64 index);
 
 int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 472457795486..59b3ea32b6de 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3978,7 +3978,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		goto err;
 	}
 skip_backref:
-	ret = btrfs_delete_delayed_dir_index(trans, fs_info, dir, index);
+	ret = btrfs_delete_delayed_dir_index(trans, dir, index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto err;
@@ -4144,7 +4144,7 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_delete_delayed_dir_index(trans, fs_info, BTRFS_I(dir), index);
+	ret = btrfs_delete_delayed_dir_index(trans, BTRFS_I(dir), index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
-- 
cgit v1.2.3


From ab9ce7d42bf66f0750a4ca4a228a2db238376afb Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 1 Aug 2018 11:32:27 +0800
Subject: btrfs: Remove fs_info from btrfs_del_root

It can be referenced from the passed transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h           | 2 +-
 fs/btrfs/extent-tree.c     | 2 +-
 fs/btrfs/free-space-tree.c | 2 +-
 fs/btrfs/qgroup.c          | 2 +-
 fs/btrfs/root-tree.c       | 4 ++--
 5 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2e32584c635f..9ef47a171e2f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2993,7 +2993,7 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
 		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
 		       const char *name, int name_len);
 int btrfs_del_root(struct btrfs_trans_handle *trans,
-		   struct btrfs_fs_info *fs_info, const struct btrfs_key *key);
+		   const struct btrfs_key *key);
 int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 		      const struct btrfs_key *key,
 		      struct btrfs_root_item *item);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index fcaf598f4222..042dd4186fb8 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9028,7 +9028,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root,
 	if (err)
 		goto out_end_trans;
 
-	ret = btrfs_del_root(trans, fs_info, &root->root_key);
+	ret = btrfs_del_root(trans, &root->root_key);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		err = ret;
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index b5950aacd697..d6736595ec57 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -1236,7 +1236,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	if (ret)
 		goto abort;
 
-	ret = btrfs_del_root(trans, fs_info, &free_space_root->root_key);
+	ret = btrfs_del_root(trans, &free_space_root->root_key);
 	if (ret)
 		goto abort;
 
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index e11ed7b3f32a..4353bb69bb86 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -1088,7 +1088,7 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
 		goto end_trans;
 	}
 
-	ret = btrfs_del_root(trans, fs_info, &quota_root->root_key);
+	ret = btrfs_del_root(trans, &quota_root->root_key);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto end_trans;
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index c451285976ac..f7c14c454f91 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -320,9 +320,9 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
 
 /* drop the root item for 'key' from the tree root */
 int btrfs_del_root(struct btrfs_trans_handle *trans,
-		   struct btrfs_fs_info *fs_info, const struct btrfs_key *key)
+		   const struct btrfs_key *key)
 {
-	struct btrfs_root *root = fs_info->tree_root;
+	struct btrfs_root *root = trans->fs_info->tree_root;
 	struct btrfs_path *path;
 	int ret;
 
-- 
cgit v1.2.3


From 3ee1c5530e649182e602eb2f81193289c4d2e655 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 1 Aug 2018 11:32:28 +0800
Subject: btrfs: Remove fs_info from btrfs_del_root_ref

It can be referenced from the passed transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h     | 7 +++----
 fs/btrfs/inode.c     | 8 +++-----
 fs/btrfs/root-tree.c | 9 ++++-----
 3 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9ef47a171e2f..3677082ddf4c 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2988,10 +2988,9 @@ int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
 		       struct btrfs_fs_info *fs_info,
 		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
 		       const char *name, int name_len);
-int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
-		       const char *name, int name_len);
+int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 *sequence, const char *name,
+		       int name_len);
 int btrfs_del_root(struct btrfs_trans_handle *trans,
 		   const struct btrfs_key *key);
 int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 59b3ea32b6de..7bf4a8d07e1e 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4085,7 +4085,6 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct inode *dir, u64 objectid,
 			const char *name, int name_len)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
@@ -4118,9 +4117,8 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_del_root_ref(trans, fs_info, objectid,
-				 root->root_key.objectid, dir_ino,
-				 &index, name, name_len);
+	ret = btrfs_del_root_ref(trans, objectid, root->root_key.objectid,
+				 dir_ino, &index, name, name_len);
 	if (ret < 0) {
 		if (ret != -ENOENT) {
 			btrfs_abort_transaction(trans, ret);
@@ -6439,7 +6437,7 @@ fail_dir_item:
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		u64 local_index;
 		int err;
-		err = btrfs_del_root_ref(trans, fs_info, key.objectid,
+		err = btrfs_del_root_ref(trans, key.objectid,
 					 root->root_key.objectid, parent_ino,
 					 &local_index, name, name_len);
 
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index f7c14c454f91..52fa133ab53c 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -341,13 +341,12 @@ out:
 	return ret;
 }
 
-int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
-		       const char *name, int name_len)
+int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 *sequence, const char *name,
+		       int name_len)
 
 {
-	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *tree_root = trans->fs_info->tree_root;
 	struct btrfs_path *path;
 	struct btrfs_root_ref *ref;
 	struct extent_buffer *leaf;
-- 
cgit v1.2.3


From 6025c19fb208e93b99eafc304e7f16160e49fc88 Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 1 Aug 2018 11:32:29 +0800
Subject: btrfs: Remove fs_info from btrfs_add_root_ref

It can be referenced from the passed transaction handle.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 7 +++----
 fs/btrfs/inode.c       | 3 +--
 fs/btrfs/ioctl.c       | 3 +--
 fs/btrfs/root-tree.c   | 9 ++++-----
 fs/btrfs/transaction.c | 2 +-
 5 files changed, 10 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 3677082ddf4c..c275ea258f9a 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2984,10 +2984,9 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 int btrfs_old_root_level(struct btrfs_root *root, u64 time_seq);
 
 /* root-item.c */
-int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
-		       const char *name, int name_len);
+int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 sequence, const char *name,
+		       int name_len);
 int btrfs_del_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
 		       u64 ref_id, u64 dirid, u64 *sequence, const char *name,
 		       int name_len);
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7bf4a8d07e1e..407d068d4208 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -6385,7 +6385,6 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index)
 {
-	struct btrfs_fs_info *fs_info = trans->fs_info;
 	int ret = 0;
 	struct btrfs_key key;
 	struct btrfs_root *root = parent_inode->root;
@@ -6401,7 +6400,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 	}
 
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
-		ret = btrfs_add_root_ref(trans, fs_info, key.objectid,
+		ret = btrfs_add_root_ref(trans, key.objectid,
 					 root->root_key.objectid, parent_ino,
 					 index, name, name_len);
 	} else if (add_backref) {
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 80fe3c654612..6eaadddaca9f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -698,8 +698,7 @@ static noinline int create_subvol(struct inode *dir,
 	ret = btrfs_update_inode(trans, root, dir);
 	BUG_ON(ret);
 
-	ret = btrfs_add_root_ref(trans, fs_info,
-				 objectid, root->root_key.objectid,
+	ret = btrfs_add_root_ref(trans, objectid, root->root_key.objectid,
 				 btrfs_ino(BTRFS_I(dir)), index, name, namelen);
 	BUG_ON(ret);
 
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 52fa133ab53c..65bda0682928 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -412,12 +412,11 @@ out:
  *
  * Will return 0, -ENOMEM, or anything from the CoW path
  */
-int btrfs_add_root_ref(struct btrfs_trans_handle *trans,
-		       struct btrfs_fs_info *fs_info,
-		       u64 root_id, u64 ref_id, u64 dirid, u64 sequence,
-		       const char *name, int name_len)
+int btrfs_add_root_ref(struct btrfs_trans_handle *trans, u64 root_id,
+		       u64 ref_id, u64 dirid, u64 sequence, const char *name,
+		       int name_len)
 {
-	struct btrfs_root *tree_root = fs_info->tree_root;
+	struct btrfs_root *tree_root = trans->fs_info->tree_root;
 	struct btrfs_key key;
 	int ret;
 	struct btrfs_path *path;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index aec208cbff00..001ed1bc2aa8 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -1573,7 +1573,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	/*
 	 * insert root back/forward references
 	 */
-	ret = btrfs_add_root_ref(trans, fs_info, objectid,
+	ret = btrfs_add_root_ref(trans, objectid,
 				 parent_root->root_key.objectid,
 				 btrfs_ino(BTRFS_I(parent_inode)), index,
 				 dentry->d_name.name, dentry->d_name.len);
-- 
cgit v1.2.3


From 401b3b19d592391b718b7a17295ae34eace973dd Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 1 Aug 2018 11:32:30 +0800
Subject: btrfs: Remove root parameter from btrfs_unlink_subvol

All callers pass the root tree of dir, we can push that down to the
function itself.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 407d068d4208..b8c131b82978 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4081,10 +4081,10 @@ out:
 }
 
 static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
-			struct btrfs_root *root,
-			struct inode *dir, u64 objectid,
-			const char *name, int name_len)
+			       struct inode *dir, u64 objectid,
+			       const char *name, int name_len)
 {
+	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_dir_item *di;
@@ -4335,10 +4335,8 @@ int btrfs_delete_subvolume(struct inode *dir, struct dentry *dentry)
 
 	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
 
-	ret = btrfs_unlink_subvol(trans, root, dir,
-				dest->root_key.objectid,
-				dentry->d_name.name,
-				dentry->d_name.len);
+	ret = btrfs_unlink_subvol(trans, dir, dest->root_key.objectid,
+				  dentry->d_name.name, dentry->d_name.len);
 	if (ret) {
 		err = ret;
 		btrfs_abort_transaction(trans, ret);
@@ -4433,7 +4431,7 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		return PTR_ERR(trans);
 
 	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
-		err = btrfs_unlink_subvol(trans, root, dir,
+		err = btrfs_unlink_subvol(trans, dir,
 					  BTRFS_I(inode)->location.objectid,
 					  dentry->d_name.name,
 					  dentry->d_name.len);
@@ -9505,8 +9503,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	/* src is a subvolume */
 	if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, root, old_dir,
-					  root_objectid,
+		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
 					  old_dentry->d_name.name,
 					  old_dentry->d_name.len);
 	} else { /* src is an inode */
@@ -9525,8 +9522,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	/* dest is a subvolume */
 	if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
 		root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, dest, new_dir,
-					  root_objectid,
+		ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
 					  new_dentry->d_name.name,
 					  new_dentry->d_name.len);
 	} else { /* dest is an inode */
@@ -9786,7 +9782,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
-		ret = btrfs_unlink_subvol(trans, root, old_dir, root_objectid,
+		ret = btrfs_unlink_subvol(trans, old_dir, root_objectid,
 					old_dentry->d_name.name,
 					old_dentry->d_name.len);
 	} else {
@@ -9808,8 +9804,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (unlikely(btrfs_ino(BTRFS_I(new_inode)) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 			root_objectid = BTRFS_I(new_inode)->location.objectid;
-			ret = btrfs_unlink_subvol(trans, dest, new_dir,
-						root_objectid,
+			ret = btrfs_unlink_subvol(trans, new_dir, root_objectid,
 						new_dentry->d_name.name,
 						new_dentry->d_name.len);
 			BUG_ON(new_inode->i_nlink == 0);
-- 
cgit v1.2.3


From 5b7d687ad5913a56b6a8788435d7a53990b4176d Mon Sep 17 00:00:00 2001
From: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Date: Wed, 1 Aug 2018 11:32:31 +0800
Subject: btrfs: Remove redundant btrfs_release_path from btrfs_unlink_subvol

Although it is safe to call this on already released paths with no locks
held or extent buffers, removing the redundant btrfs_release_path is
reasonable.

Signed-off-by: Lu Fengqi <lufq.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index b8c131b82978..7e56a203c109 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -4137,7 +4137,6 @@ static int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 
 		leaf = path->nodes[0];
 		btrfs_item_key_to_cpu(leaf, &key, path->slots[0]);
-		btrfs_release_path(path);
 		index = key.offset;
 	}
 	btrfs_release_path(path);
-- 
cgit v1.2.3


From afc6961ffd96ee7e2a86e70e9691a008eadf2926 Mon Sep 17 00:00:00 2001
From: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Date: Thu, 26 Jul 2018 10:22:58 +0900
Subject: btrfs: backref: Use ERR_CAST to return error code

Use ERR_CAST() instead of void * to make meaning clear.

Signed-off-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/backref.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 60f4afa8ecbc..ae750b1574a2 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -2225,7 +2225,7 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 
 	fspath = init_data_container(total_bytes);
 	if (IS_ERR(fspath))
-		return (void *)fspath;
+		return ERR_CAST(fspath);
 
 	ifp = kmalloc(sizeof(*ifp), GFP_KERNEL);
 	if (!ifp) {
-- 
cgit v1.2.3


From 85c39548199b966062578fb99d4d4ecdeae2afae Mon Sep 17 00:00:00 2001
From: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Date: Thu, 26 Jul 2018 11:40:54 +0900
Subject: btrfs: extent-tree: Remove unused __btrfs_free_block_rsv

There is no user of this function anymore.

This was forgotten to be removed in commit a575ceeb1338
("Btrfs: get rid of unused orphan infrastructure").

Signed-off-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ctree.h       | 1 -
 fs/btrfs/extent-tree.c | 5 -----
 2 files changed, 6 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index c275ea258f9a..318be7864072 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -2761,7 +2761,6 @@ void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
 				   unsigned short type);
 void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 			  struct btrfs_block_rsv *rsv);
-void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv);
 int btrfs_block_rsv_add(struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 042dd4186fb8..9e7b237b9547 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -5529,11 +5529,6 @@ void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
 	kfree(rsv);
 }
 
-void __btrfs_free_block_rsv(struct btrfs_block_rsv *rsv)
-{
-	kfree(rsv);
-}
-
 int btrfs_block_rsv_add(struct btrfs_root *root,
 			struct btrfs_block_rsv *block_rsv, u64 num_bytes,
 			enum btrfs_reserve_flush_enum flush)
-- 
cgit v1.2.3


From 1e7e1f9e3aba00c9b9c323bfeeddafe69ff21ff6 Mon Sep 17 00:00:00 2001
From: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Date: Tue, 31 Jul 2018 16:20:21 +0900
Subject: btrfs: replace: Reset on-disk dev stats value after replace

on-disk devs stats value is updated in btrfs_run_dev_stats(),
which is called during commit transaction, if device->dev_stats_ccnt
is not zero.

Since current replace operation does not touch dev_stats_ccnt,
on-disk dev stats value is not updated. Therefore "btrfs device stats"
may return old device's value after umount/mount
(Example: See "btrfs ins dump-t -t DEV $DEV" after btrfs/100 finish).

Fix this by just incrementing dev_stats_ccnt in
btrfs_dev_replace_finishing() when replace is succeeded and this will
update the values.

Signed-off-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/dev-replace.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 5a72f9933e58..dec01970d8c5 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -671,6 +671,12 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 
 	btrfs_rm_dev_replace_unblocked(fs_info);
 
+	/*
+	 * Increment dev_stats_ccnt so that btrfs_run_dev_stats() will
+	 * update on-disk dev stats value during commit transaction
+	 */
+	atomic_inc(&tgt_device->dev_stats_ccnt);
+
 	/*
 	 * this is again a consistent state where no dev_replace procedure
 	 * is running, the target device is part of the filesystem, the
-- 
cgit v1.2.3


From 2e19f1f9d31b3515356710b8bdfb655f47a98448 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 29 Jul 2018 23:04:45 +0100
Subject: btrfs: btrfs_iget never returns an is_bad_inode inode

Just get rid of pointless checks.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/free-space-cache.c | 4 ----
 fs/btrfs/relocation.c       | 7 ++-----
 fs/btrfs/tree-log.c         | 6 +-----
 3 files changed, 3 insertions(+), 14 deletions(-)

diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 57e7ab7f5e03..0adf38b00fa0 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -71,10 +71,6 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	inode = btrfs_iget(fs_info->sb, &location, root, NULL);
 	if (IS_ERR(inode))
 		return inode;
-	if (is_bad_inode(inode)) {
-		iput(inode);
-		return ERR_PTR(-ENOENT);
-	}
 
 	mapping_set_gfp_mask(inode->i_mapping,
 			mapping_gfp_constraint(inode->i_mapping,
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index d6bcf558789e..8783a1776540 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -3470,11 +3470,8 @@ static int delete_block_group_cache(struct btrfs_fs_info *fs_info,
 	key.offset = 0;
 
 	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
-	if (IS_ERR(inode) || is_bad_inode(inode)) {
-		if (!IS_ERR(inode))
-			iput(inode);
+	if (IS_ERR(inode))
 		return -ENOENT;
-	}
 
 truncate:
 	ret = btrfs_check_trunc_cache_free_space(fs_info,
@@ -4155,7 +4152,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 	inode = btrfs_iget(fs_info->sb, &key, root, NULL);
-	BUG_ON(IS_ERR(inode) || is_bad_inode(inode));
+	BUG_ON(IS_ERR(inode));
 	BTRFS_I(inode)->index_cnt = group->key.objectid;
 
 	err = btrfs_orphan_add(trans, BTRFS_I(inode));
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 033aeebbe9de..730b97dee955 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -545,12 +545,8 @@ static noinline struct inode *read_one_inode(struct btrfs_root *root,
 	key.type = BTRFS_INODE_ITEM_KEY;
 	key.offset = 0;
 	inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
-	if (IS_ERR(inode)) {
+	if (IS_ERR(inode))
 		inode = NULL;
-	} else if (is_bad_inode(inode)) {
-		iput(inode);
-		inode = NULL;
-	}
 	return inode;
 }
 
-- 
cgit v1.2.3


From 8d9e220ca0844bf75b98cb5b8e2c25d203c0d0f6 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 29 Jul 2018 23:04:46 +0100
Subject: btrfs: simplify IS_ERR/PTR_ERR checks

IS_ERR(p) && PTR_ERR(p) == n is a weird way to spell p == ERR_PTR(n).

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: David Sterba <dsterba@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
[ update changelog ]
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/transaction.c | 2 +-
 fs/btrfs/tree-log.c    | 5 ++---
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 001ed1bc2aa8..3b84f5015029 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -680,7 +680,7 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root)
 
 	trans = start_transaction(root, 0, TRANS_ATTACH,
 				  BTRFS_RESERVE_NO_FLUSH, true);
-	if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT)
+	if (trans == ERR_PTR(-ENOENT))
 		btrfs_wait_for_commit(root->fs_info, 0);
 
 	return trans;
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 730b97dee955..1650dc44a5e3 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2181,7 +2181,7 @@ again:
 						     dir_key->offset,
 						     name, name_len, 0);
 		}
-		if (!log_di || (IS_ERR(log_di) && PTR_ERR(log_di) == -ENOENT)) {
+		if (!log_di || log_di == ERR_PTR(-ENOENT)) {
 			btrfs_dir_item_key_to_cpu(eb, di, &location);
 			btrfs_release_path(path);
 			btrfs_release_path(log_path);
@@ -5011,8 +5011,7 @@ again:
 				 * we don't need to do more work nor fallback to
 				 * a transaction commit.
 				 */
-				if (IS_ERR(other_inode) &&
-				    PTR_ERR(other_inode) == -ENOENT) {
+				if (other_inode == ERR_PTR(-ENOENT)) {
 					goto next_key;
 				} else if (IS_ERR(other_inode)) {
 					err = PTR_ERR(other_inode);
-- 
cgit v1.2.3


From 9bc2ceff660580454f971ed3f891a2c82085433a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 29 Jul 2018 23:04:50 +0100
Subject: btrfs: lift make_bad_inode into btrfs_iget

We don't need to check is_bad_inode() after the call of
btrfs_read_locked_inode() - it's exactly the same as checking return
value for being non-zero.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: David Sterba <dsterba@suse.com>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 7e56a203c109..cd99ce8583a8 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3771,7 +3771,6 @@ cache_acl:
 
 make_bad:
 	btrfs_free_path(path);
-	make_bad_inode(inode);
 	return ret;
 }
 
@@ -5697,12 +5696,13 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 		int ret;
 
 		ret = btrfs_read_locked_inode(inode);
-		if (!is_bad_inode(inode)) {
+		if (!ret) {
 			inode_tree_add(inode);
 			unlock_new_inode(inode);
 			if (new)
 				*new = 1;
 		} else {
+			make_bad_inode(inode);
 			unlock_new_inode(inode);
 			iput(inode);
 			ASSERT(ret < 0);
-- 
cgit v1.2.3


From f5b3a4173ff624b766c56936bb315e1517603891 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 29 Jul 2018 23:04:51 +0100
Subject: btrfs: simplify btrfs_iget

Don't open-code iget_failed(), don't bother with btrfs_free_path(NULL),
move handling of positive return values of btrfs_lookup_inode() from
btrfs_read_locked_inode() to btrfs_iget() and kill now obviously
pointless ASSERT() in there.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Reviewed-by: Nikolay Borisov <nborisov@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 29 +++++++++++++----------------
 1 file changed, 13 insertions(+), 16 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index cd99ce8583a8..3f51ddc18f98 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3604,18 +3604,15 @@ static int btrfs_read_locked_inode(struct inode *inode)
 		filled = true;
 
 	path = btrfs_alloc_path();
-	if (!path) {
-		ret = -ENOMEM;
-		goto make_bad;
-	}
+	if (!path)
+		return -ENOMEM;
 
 	memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
 	ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
 	if (ret) {
-		if (ret > 0)
-			ret = -ENOENT;
-		goto make_bad;
+		btrfs_free_path(path);
+		return ret;
 	}
 
 	leaf = path->nodes[0];
@@ -3768,10 +3765,6 @@ cache_acl:
 
 	btrfs_sync_inode_flags_to_i_flags(inode);
 	return 0;
-
-make_bad:
-	btrfs_free_path(path);
-	return ret;
 }
 
 /*
@@ -5702,11 +5695,15 @@ struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			if (new)
 				*new = 1;
 		} else {
-			make_bad_inode(inode);
-			unlock_new_inode(inode);
-			iput(inode);
-			ASSERT(ret < 0);
-			inode = ERR_PTR(ret < 0 ? ret : -ESTALE);
+			iget_failed(inode);
+			/*
+			 * ret > 0 can come from btrfs_search_slot called by
+			 * btrfs_read_locked_inode, this means the inode item
+			 * was not found.
+			 */
+			if (ret > 0)
+				ret = -ENOENT;
+			inode = ERR_PTR(ret);
 		}
 	}
 
-- 
cgit v1.2.3


From 672d599041c862dd61a1576c32e946ef0d77aa34 Mon Sep 17 00:00:00 2001
From: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Date: Thu, 2 Aug 2018 16:19:07 +0900
Subject: btrfs: Use wrapper macro for rcu string to remove duplicate code

Cleanup patch and no functional changes.

Signed-off-by: Misono Tomohiro <misono.tomohiro@jp.fujitsu.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/ioctl.c   |  6 ++----
 fs/btrfs/scrub.c   |  8 ++------
 fs/btrfs/super.c   |  9 +++------
 fs/btrfs/volumes.c | 20 +++++---------------
 4 files changed, 12 insertions(+), 31 deletions(-)

diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 6eaadddaca9f..d3a5d2a41e5f 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -3157,10 +3157,8 @@ static long btrfs_ioctl_dev_info(struct btrfs_fs_info *fs_info,
 	di_args->total_bytes = btrfs_device_get_total_bytes(dev);
 	memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
 	if (dev->name) {
-		struct rcu_string *name;
-
-		name = rcu_dereference(dev->name);
-		strncpy(di_args->path, name->str, sizeof(di_args->path) - 1);
+		strncpy(di_args->path, rcu_str_deref(dev->name),
+				sizeof(di_args->path) - 1);
 		di_args->path[sizeof(di_args->path) - 1] = 0;
 	} else {
 		di_args->path[0] = '\0';
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index c4eb9eca13b8..3be1456b5116 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -3779,7 +3779,6 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	struct scrub_ctx *sctx;
 	int ret;
 	struct btrfs_device *dev;
-	struct rcu_string *name;
 
 	if (btrfs_fs_closing(fs_info))
 		return -EINVAL;
@@ -3833,11 +3832,8 @@ int btrfs_scrub_dev(struct btrfs_fs_info *fs_info, u64 devid, u64 start,
 	if (!is_dev_replace && !readonly &&
 	    !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) {
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
-		rcu_read_lock();
-		name = rcu_dereference(dev->name);
-		btrfs_err(fs_info, "scrub: device %s is not writable",
-			  name->str);
-		rcu_read_unlock();
+		btrfs_err_in_rcu(fs_info, "scrub: device %s is not writable",
+				rcu_str_deref(dev->name));
 		return -EROFS;
 	}
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 67de3c0fc85b..6601c9aa5e35 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -2303,7 +2303,6 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 	struct btrfs_fs_devices *cur_devices;
 	struct btrfs_device *dev, *first_dev = NULL;
 	struct list_head *head;
-	struct rcu_string *name;
 
 	/*
 	 * Lightweight locking of the devices. We should not need
@@ -2327,12 +2326,10 @@ static int btrfs_show_devname(struct seq_file *m, struct dentry *root)
 		cur_devices = cur_devices->seed;
 	}
 
-	if (first_dev) {
-		name = rcu_dereference(first_dev->name);
-		seq_escape(m, name->str, " \t\n\\");
-	} else {
+	if (first_dev)
+		seq_escape(m, rcu_str_deref(first_dev->name), " \t\n\\");
+	else
 		WARN_ON(1);
-	}
 	rcu_read_unlock();
 	return 0;
 }
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index d86346f83a08..74977203fc85 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6094,21 +6094,11 @@ static void submit_stripe_bio(struct btrfs_bio *bbio, struct bio *bio,
 	btrfs_io_bio(bio)->stripe_index = dev_nr;
 	bio->bi_end_io = btrfs_end_bio;
 	bio->bi_iter.bi_sector = physical >> 9;
-#ifdef DEBUG
-	{
-		struct rcu_string *name;
-
-		rcu_read_lock();
-		name = rcu_dereference(dev->name);
-		btrfs_debug(fs_info,
-			"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
-			bio_op(bio), bio->bi_opf,
-			(u64)bio->bi_iter.bi_sector,
-			(u_long)dev->bdev->bd_dev, name->str, dev->devid,
-			bio->bi_iter.bi_size);
-		rcu_read_unlock();
-	}
-#endif
+	btrfs_debug_in_rcu(fs_info,
+	"btrfs_map_bio: rw %d 0x%x, sector=%llu, dev=%lu (%s id %llu), size=%u",
+		bio_op(bio), bio->bi_opf, (u64)bio->bi_iter.bi_sector,
+		(u_long)dev->bdev->bd_dev, rcu_str_deref(dev->name), dev->devid,
+		bio->bi_iter.bi_size);
 	bio_set_dev(bio, dev->bdev);
 
 	btrfs_bio_counter_inc_noblocked(fs_info);
-- 
cgit v1.2.3


From 22d3151c2c4cb517a309154d1e828a28106508c7 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Mon, 30 Jul 2018 12:39:58 +0100
Subject: Btrfs: send, fix incorrect file layout after hole punching beyond eof

When doing an incremental send, if we have a file in the parent snapshot
that has prealloc extents beyond EOF and in the send snapshot it got a
hole punch that partially covers the prealloc extents, the send stream,
when replayed by a receiver, can result in a file that has a size bigger
than it should and filled with zeroes past the correct EOF.

For example:

  $ mkfs.btrfs -f /dev/sdb
  $ mount /dev/sdb /mnt

  $ xfs_io -f -c "falloc -k 0 4M" /mnt/foobar
  $ xfs_io -c "pwrite -S 0xea 0 1M" /mnt/foobar

  $ btrfs subvolume snapshot -r /mnt /mnt/snap1
  $ btrfs send -f /tmp/1.send /mnt/snap1

  $ xfs_io -c "fpunch 1M 2M" /mnt/foobar

  $ btrfs subvolume snapshot -r /mnt /mnt/snap2
  $ btrfs send -f /tmp/2.send -p /mnt/snap1 /mnt/snap2

  $ stat --format %s /mnt/snap2/foobar
  1048576
  $ md5sum /mnt/snap2/foobar
  d31659e82e87798acd4669a1e0a19d4f  /mnt/snap2/foobar

  $ umount /mnt
  $ mkfs.btrfs -f /dev/sdc
  $ mount /dev/sdc /mnt

  $ btrfs receive -f /mnt/1.snap /mnt
  $ btrfs receive -f /mnt/2.snap /mnt

  $ stat --format %s /mnt/snap2/foobar
  3145728
  # --> should be 1Mb and not 3Mb (which was the end offset of hole
  #     punch operation)
  $ md5sum /mnt/snap2/foobar
  117baf295297c2a995f92da725b0b651  /mnt/snap2/foobar
  # --> should be d31659e82e87798acd4669a1e0a19d4f as in the original fs

This issue actually happens only since commit ffa7c4296e93 ("Btrfs: send,
do not issue unnecessary truncate operations"), but before that commit we
were issuing a write operation full of zeroes (to "punch" a hole) which
was extending the file size beyond the correct value and then immediately
issue a truncate operation to the correct size and undoing the previous
write operation. Since the send protocol does not support fallocate, for
extent preallocation and hole punching, fix this by not even attempting
to send a "hole" (regular write full of zeroes) if it starts at an offset
greater then or equals to the file's size. This approach, besides being
much more simple then making send issue the truncate operation, adds the
benefit of avoiding the useless pair of write of zeroes and truncate
operations, saving time and IO at the receiver and reducing the size of
the send stream.

A test case for fstests follows soon.

Fixes: ffa7c4296e93 ("Btrfs: send, do not issue unnecessary truncate operations")
CC: stable@vger.kernel.org # 4.17+
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/send.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index 551294a6c9e2..ba8950bfd9c7 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -5007,6 +5007,15 @@ static int send_hole(struct send_ctx *sctx, u64 end)
 	u64 len;
 	int ret = 0;
 
+	/*
+	 * A hole that starts at EOF or beyond it. Since we do not yet support
+	 * fallocate (for extent preallocation and hole punching), sending a
+	 * write of zeroes starting at EOF or beyond would later require issuing
+	 * a truncate operation which would undo the write and achieve nothing.
+	 */
+	if (offset >= sctx->cur_inode_size)
+		return 0;
+
 	if (sctx->flags & BTRFS_SEND_FLAG_NO_FILE_DATA)
 		return send_update_extent(sctx, offset, end - offset);
 
-- 
cgit v1.2.3


From 514c7dca85a0bf40be984dab0b477403a6db901f Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 1 Aug 2018 10:37:16 +0800
Subject: btrfs: Check that each block group has corresponding chunk at mount
 time

A crafted btrfs image with incorrect chunk<->block group mapping will
trigger a lot of unexpected things as the mapping is essential.

Although the problem can be caught by block group item checker
added in "btrfs: tree-checker: Verify block_group_item", it's still not
sufficient.  A sufficiently valid block group item can pass the check
added by the mentioned patch but could fail to match the existing chunk.

This patch will add extra block group -> chunk mapping check, to ensure
we have a completely matching (start, len, flags) chunk for each block
group at mount time.

Here we reuse the original helper find_first_block_group(), which is
already doing the basic bg -> chunk checks, adding further checks of the
start/len and type flags.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199837
Reported-by: Xu Wen <wen.xu@gatech.edu>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 9e7b237b9547..54a0cfef5c5c 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9532,6 +9532,8 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 	struct btrfs_key found_key;
 	struct extent_buffer *leaf;
+	struct btrfs_block_group_item bg;
+	u64 flags;
 	int slot;
 
 	ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
@@ -9566,8 +9568,32 @@ static int find_first_block_group(struct btrfs_fs_info *fs_info,
 			"logical %llu len %llu found bg but no related chunk",
 					  found_key.objectid, found_key.offset);
 				ret = -ENOENT;
+			} else if (em->start != found_key.objectid ||
+				   em->len != found_key.offset) {
+				btrfs_err(fs_info,
+		"block group %llu len %llu mismatch with chunk %llu len %llu",
+					  found_key.objectid, found_key.offset,
+					  em->start, em->len);
+				ret = -EUCLEAN;
 			} else {
-				ret = 0;
+				read_extent_buffer(leaf, &bg,
+					btrfs_item_ptr_offset(leaf, slot),
+					sizeof(bg));
+				flags = btrfs_block_group_flags(&bg) &
+					BTRFS_BLOCK_GROUP_TYPE_MASK;
+
+				if (flags != (em->map_lookup->type &
+					      BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+					btrfs_err(fs_info,
+"block group %llu len %llu type flags 0x%llx mismatch with chunk type flags 0x%llx",
+						found_key.objectid,
+						found_key.offset, flags,
+						(BTRFS_BLOCK_GROUP_TYPE_MASK &
+						 em->map_lookup->type));
+					ret = -EUCLEAN;
+				} else {
+					ret = 0;
+				}
 			}
 			free_extent_map(em);
 			goto out;
-- 
cgit v1.2.3


From 7ef49515fa6727cb4b6f2f5b0ffbc5fc20a9f8c6 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 1 Aug 2018 10:37:17 +0800
Subject: btrfs: Verify that every chunk has corresponding block group at mount
 time

If a crafted image has missing block group items, it could cause
unexpected behavior and breaks the assumption of 1:1 chunk<->block group
mapping.

Although we have the block group -> chunk mapping check, we still need
chunk -> block group mapping check.

This patch will do extra check to ensure each chunk has its
corresponding block group.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=199847
Reported-by: Xu Wen <wen.xu@gatech.edu>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Gu Jinxiang <gujx@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent-tree.c | 58 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 54a0cfef5c5c..de6f75f5547b 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -9844,6 +9844,62 @@ btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info,
 	return cache;
 }
 
+
+/*
+ * Iterate all chunks and verify that each of them has the corresponding block
+ * group
+ */
+static int check_chunk_block_group_mappings(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
+	struct extent_map *em;
+	struct btrfs_block_group_cache *bg;
+	u64 start = 0;
+	int ret = 0;
+
+	while (1) {
+		read_lock(&map_tree->map_tree.lock);
+		/*
+		 * lookup_extent_mapping will return the first extent map
+		 * intersecting the range, so setting @len to 1 is enough to
+		 * get the first chunk.
+		 */
+		em = lookup_extent_mapping(&map_tree->map_tree, start, 1);
+		read_unlock(&map_tree->map_tree.lock);
+		if (!em)
+			break;
+
+		bg = btrfs_lookup_block_group(fs_info, em->start);
+		if (!bg) {
+			btrfs_err(fs_info,
+	"chunk start=%llu len=%llu doesn't have corresponding block group",
+				     em->start, em->len);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			break;
+		}
+		if (bg->key.objectid != em->start ||
+		    bg->key.offset != em->len ||
+		    (bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK) !=
+		    (em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK)) {
+			btrfs_err(fs_info,
+"chunk start=%llu len=%llu flags=0x%llx doesn't match block group start=%llu len=%llu flags=0x%llx",
+				em->start, em->len,
+				em->map_lookup->type & BTRFS_BLOCK_GROUP_TYPE_MASK,
+				bg->key.objectid, bg->key.offset,
+				bg->flags & BTRFS_BLOCK_GROUP_TYPE_MASK);
+			ret = -EUCLEAN;
+			free_extent_map(em);
+			btrfs_put_block_group(bg);
+			break;
+		}
+		start = em->start + em->len;
+		free_extent_map(em);
+		btrfs_put_block_group(bg);
+	}
+	return ret;
+}
+
 int btrfs_read_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_path *path;
@@ -10010,7 +10066,7 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 
 	btrfs_add_raid_kobjects(info);
 	init_global_block_rsv(info);
-	ret = 0;
+	ret = check_chunk_block_group_mappings(info);
 error:
 	btrfs_free_path(path);
 	return ret;
-- 
cgit v1.2.3


From cf90d884b347c50a1e8c1effc4093e497dd68b4b Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 1 Aug 2018 10:37:19 +0800
Subject: btrfs: Introduce mount time chunk <-> dev extent mapping check

This patch will introduce chunk <-> dev extent mapping check, to protect
us against invalid dev extents or chunks.

Since chunk mapping is the fundamental infrastructure of btrfs, extra
check at mount time could prevent a lot of unexpected behavior (BUG_ON).

Reported-by: Xu Wen <wen.xu@gatech.edu>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=200403
Link: https://bugzilla.kernel.org/show_bug.cgi?id=200407
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Su Yue <suy.fnst@cn.fujitsu.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/disk-io.c |   7 ++
 fs/btrfs/volumes.c | 184 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/btrfs/volumes.h |   2 +
 3 files changed, 193 insertions(+)

diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 6a5a3cd12886..5124c15705ce 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3030,6 +3030,13 @@ retry_root_backup:
 	fs_info->generation = generation;
 	fs_info->last_trans_committed = generation;
 
+	ret = btrfs_verify_dev_extents(fs_info);
+	if (ret) {
+		btrfs_err(fs_info,
+			  "failed to verify dev extents against chunks: %d",
+			  ret);
+		goto fail_block_groups;
+	}
 	ret = btrfs_recover_balance(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "failed to recover balance: %d", ret);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 74977203fc85..96be1e50b027 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6452,6 +6452,7 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	map->stripe_len = btrfs_chunk_stripe_len(leaf, chunk);
 	map->type = btrfs_chunk_type(leaf, chunk);
 	map->sub_stripes = btrfs_chunk_sub_stripes(leaf, chunk);
+	map->verified_stripes = 0;
 	for (i = 0; i < num_stripes; i++) {
 		map->stripes[i].physical =
 			btrfs_stripe_offset_nr(leaf, chunk, i);
@@ -7318,3 +7319,186 @@ int btrfs_bg_type_to_factor(u64 flags)
 		return 2;
 	return 1;
 }
+
+
+static u64 calc_stripe_length(u64 type, u64 chunk_len, int num_stripes)
+{
+	int index = btrfs_bg_flags_to_raid_index(type);
+	int ncopies = btrfs_raid_array[index].ncopies;
+	int data_stripes;
+
+	switch (type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+	case BTRFS_BLOCK_GROUP_RAID5:
+		data_stripes = num_stripes - 1;
+		break;
+	case BTRFS_BLOCK_GROUP_RAID6:
+		data_stripes = num_stripes - 2;
+		break;
+	default:
+		data_stripes = num_stripes / ncopies;
+		break;
+	}
+	return div_u64(chunk_len, data_stripes);
+}
+
+static int verify_one_dev_extent(struct btrfs_fs_info *fs_info,
+				 u64 chunk_offset, u64 devid,
+				 u64 physical_offset, u64 physical_len)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+	struct extent_map *em;
+	struct map_lookup *map;
+	u64 stripe_len;
+	bool found = false;
+	int ret = 0;
+	int i;
+
+	read_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
+	read_unlock(&em_tree->lock);
+
+	if (!em) {
+		btrfs_err(fs_info,
+"dev extent physical offset %llu on devid %llu doesn't have corresponding chunk",
+			  physical_offset, devid);
+		ret = -EUCLEAN;
+		goto out;
+	}
+
+	map = em->map_lookup;
+	stripe_len = calc_stripe_length(map->type, em->len, map->num_stripes);
+	if (physical_len != stripe_len) {
+		btrfs_err(fs_info,
+"dev extent physical offset %llu on devid %llu length doesn't match chunk %llu, have %llu expect %llu",
+			  physical_offset, devid, em->start, physical_len,
+			  stripe_len);
+		ret = -EUCLEAN;
+		goto out;
+	}
+
+	for (i = 0; i < map->num_stripes; i++) {
+		if (map->stripes[i].dev->devid == devid &&
+		    map->stripes[i].physical == physical_offset) {
+			found = true;
+			if (map->verified_stripes >= map->num_stripes) {
+				btrfs_err(fs_info,
+				"too many dev extents for chunk %llu found",
+					  em->start);
+				ret = -EUCLEAN;
+				goto out;
+			}
+			map->verified_stripes++;
+			break;
+		}
+	}
+	if (!found) {
+		btrfs_err(fs_info,
+	"dev extent physical offset %llu devid %llu has no corresponding chunk",
+			physical_offset, devid);
+		ret = -EUCLEAN;
+	}
+out:
+	free_extent_map(em);
+	return ret;
+}
+
+static int verify_chunk_dev_extent_mapping(struct btrfs_fs_info *fs_info)
+{
+	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
+	struct extent_map *em;
+	struct rb_node *node;
+	int ret = 0;
+
+	read_lock(&em_tree->lock);
+	for (node = rb_first(&em_tree->map); node; node = rb_next(node)) {
+		em = rb_entry(node, struct extent_map, rb_node);
+		if (em->map_lookup->num_stripes !=
+		    em->map_lookup->verified_stripes) {
+			btrfs_err(fs_info,
+			"chunk %llu has missing dev extent, have %d expect %d",
+				  em->start, em->map_lookup->verified_stripes,
+				  em->map_lookup->num_stripes);
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+out:
+	read_unlock(&em_tree->lock);
+	return ret;
+}
+
+/*
+ * Ensure that all dev extents are mapped to correct chunk, otherwise
+ * later chunk allocation/free would cause unexpected behavior.
+ *
+ * NOTE: This will iterate through the whole device tree, which should be of
+ * the same size level as the chunk tree.  This slightly increases mount time.
+ */
+int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info)
+{
+	struct btrfs_path *path;
+	struct btrfs_root *root = fs_info->dev_root;
+	struct btrfs_key key;
+	int ret = 0;
+
+	key.objectid = 1;
+	key.type = BTRFS_DEV_EXTENT_KEY;
+	key.offset = 0;
+
+	path = btrfs_alloc_path();
+	if (!path)
+		return -ENOMEM;
+
+	path->reada = READA_FORWARD;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+
+	if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		/* No dev extents at all? Not good */
+		if (ret > 0) {
+			ret = -EUCLEAN;
+			goto out;
+		}
+	}
+	while (1) {
+		struct extent_buffer *leaf = path->nodes[0];
+		struct btrfs_dev_extent *dext;
+		int slot = path->slots[0];
+		u64 chunk_offset;
+		u64 physical_offset;
+		u64 physical_len;
+		u64 devid;
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.type != BTRFS_DEV_EXTENT_KEY)
+			break;
+		devid = key.objectid;
+		physical_offset = key.offset;
+
+		dext = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
+		chunk_offset = btrfs_dev_extent_chunk_offset(leaf, dext);
+		physical_len = btrfs_dev_extent_length(leaf, dext);
+
+		ret = verify_one_dev_extent(fs_info, chunk_offset, devid,
+					    physical_offset, physical_len);
+		if (ret < 0)
+			goto out;
+		ret = btrfs_next_item(root, path);
+		if (ret < 0)
+			goto out;
+		if (ret > 0) {
+			ret = 0;
+			break;
+		}
+	}
+
+	/* Ensure all chunks have corresponding dev extents */
+	ret = verify_chunk_dev_extent_mapping(fs_info);
+out:
+	btrfs_free_path(path);
+	return ret;
+}
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 049619176831..23e9285d88de 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -345,6 +345,7 @@ struct map_lookup {
 	u64 stripe_len;
 	int num_stripes;
 	int sub_stripes;
+	int verified_stripes; /* For mount time dev extent verification */
 	struct btrfs_bio_stripe stripes[];
 };
 
@@ -556,5 +557,6 @@ bool btrfs_check_rw_degradable(struct btrfs_fs_info *fs_info,
 					struct btrfs_device *failing_dev);
 
 int btrfs_bg_type_to_factor(u64 flags);
+int btrfs_verify_dev_extents(struct btrfs_fs_info *fs_info);
 
 #endif
-- 
cgit v1.2.3


From 64f64f43c89aca1782aa672e0586f6903c5d8979 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 1 Aug 2018 10:37:20 +0800
Subject: btrfs: Exit gracefully when chunk map cannot be inserted to the tree

It's entirely possible that a crafted btrfs image contains overlapping
chunks.

Although we can't detect such problem by tree-checker, it's not a
catastrophic problem, current extent map can already detect such problem
and return -EEXIST.

We just only need to exit gracefully and fail the mount.

Reported-by: Xu Wen <wen.xu@gatech.edu>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=200409
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 96be1e50b027..7218a79a0e57 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -6489,10 +6489,14 @@ static int read_one_chunk(struct btrfs_fs_info *fs_info, struct btrfs_key *key,
 	write_lock(&map_tree->map_tree.lock);
 	ret = add_extent_mapping(&map_tree->map_tree, em, 0);
 	write_unlock(&map_tree->map_tree.lock);
-	BUG_ON(ret); /* Tree corruption */
+	if (ret < 0) {
+		btrfs_err(fs_info,
+			  "failed to add chunk map, start=%llu len=%llu: %d",
+			  em->start, em->len, ret);
+	}
 	free_extent_map(em);
 
-	return 0;
+	return ret;
 }
 
 static void fill_device_from_item(struct extent_buffer *leaf,
-- 
cgit v1.2.3


From 39379faaad79e3cf403a6904a08676b7850043ae Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naota@elisp.net>
Date: Fri, 27 Jul 2018 09:04:55 +0900
Subject: btrfs: revert fs_devices state on error of btrfs_init_new_device

When btrfs hits error after modifying fs_devices in
btrfs_init_new_device() (such as btrfs_add_dev_item() returns error), it
leaves everything as is, but frees allocated btrfs_device. As a result,
fs_devices->devices and fs_devices->alloc_list contain already freed
btrfs_device, leading to later use-after-free bug.

Error path also messes the things like ->num_devices. While they go back
to the original value by unscanning btrfs devices, it is safe to revert
them here.

Fixes: 79787eaab461 ("btrfs: replace many BUG_ONs with proper error handling")
Signed-off-by: Naohiro Aota <naota@elisp.net>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 29 ++++++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 7218a79a0e57..da86706123ff 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -2321,7 +2321,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	struct super_block *sb = fs_info->sb;
 	struct rcu_string *name;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
-	u64 tmp;
+	u64 orig_super_total_bytes;
+	u64 orig_super_num_devices;
 	int seeding_dev = 0;
 	int ret = 0;
 	bool unlocked = false;
@@ -2417,12 +2418,14 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 	if (!blk_queue_nonrot(q))
 		fs_devices->rotating = 1;
 
-	tmp = btrfs_super_total_bytes(fs_info->super_copy);
+	orig_super_total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
 	btrfs_set_super_total_bytes(fs_info->super_copy,
-		round_down(tmp + device->total_bytes, fs_info->sectorsize));
+		round_down(orig_super_total_bytes + device->total_bytes,
+			   fs_info->sectorsize));
 
-	tmp = btrfs_super_num_devices(fs_info->super_copy);
-	btrfs_set_super_num_devices(fs_info->super_copy, tmp + 1);
+	orig_super_num_devices = btrfs_super_num_devices(fs_info->super_copy);
+	btrfs_set_super_num_devices(fs_info->super_copy,
+				    orig_super_num_devices + 1);
 
 	/* add sysfs device entry */
 	btrfs_sysfs_add_device_link(fs_devices, device);
@@ -2502,6 +2505,22 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path
 
 error_sysfs:
 	btrfs_sysfs_rm_device_link(fs_devices, device);
+	mutex_lock(&fs_info->fs_devices->device_list_mutex);
+	mutex_lock(&fs_info->chunk_mutex);
+	list_del_rcu(&device->dev_list);
+	list_del(&device->dev_alloc_list);
+	fs_info->fs_devices->num_devices--;
+	fs_info->fs_devices->open_devices--;
+	fs_info->fs_devices->rw_devices--;
+	fs_info->fs_devices->total_devices--;
+	fs_info->fs_devices->total_rw_bytes -= device->total_bytes;
+	atomic64_sub(device->total_bytes, &fs_info->free_chunk_space);
+	btrfs_set_super_total_bytes(fs_info->super_copy,
+				    orig_super_total_bytes);
+	btrfs_set_super_num_devices(fs_info->super_copy,
+				    orig_super_num_devices);
+	mutex_unlock(&fs_info->chunk_mutex);
+	mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 error_trans:
 	if (seeding_dev)
 		sb->s_flags |= SB_RDONLY;
-- 
cgit v1.2.3


From 038541dae968dbef99edca4b22bbb2a7b4afdc83 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:49:02 -0500
Subject: ASoC: max9850: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/max9850.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/max9850.c b/sound/soc/codecs/max9850.c
index 74d7f52c7e73..6e6134589588 100644
--- a/sound/soc/codecs/max9850.c
+++ b/sound/soc/codecs/max9850.c
@@ -52,9 +52,9 @@ static bool max9850_volatile_register(struct device *dev, unsigned int reg)
 	switch (reg) {
 	case MAX9850_STATUSA:
 	case MAX9850_STATUSB:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From 508e8641f89cc89554adbec3ce59bcd28a4ced4b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:49:55 -0500
Subject: ASoC: rt5631: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5631.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/rt5631.c b/sound/soc/codecs/rt5631.c
index e52e4670cf65..865f49ac38dd 100644
--- a/sound/soc/codecs/rt5631.c
+++ b/sound/soc/codecs/rt5631.c
@@ -105,9 +105,9 @@ static bool rt5631_volatile_register(struct device *dev, unsigned int reg)
 	case RT5631_INDEX_ADD:
 	case RT5631_INDEX_DATA:
 	case RT5631_EQ_CTRL:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -164,9 +164,9 @@ static bool rt5631_readable_register(struct device *dev, unsigned int reg)
 	case RT5631_VENDOR_ID:
 	case RT5631_VENDOR_ID1:
 	case RT5631_VENDOR_ID2:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From 10754bfc051256ab922b818de3ddd11391862a5f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:50:27 -0500
Subject: ASoC: tda7419: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tda7419.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/tda7419.c b/sound/soc/codecs/tda7419.c
index 225c210ac38f..7f3b79c5a563 100644
--- a/sound/soc/codecs/tda7419.c
+++ b/sound/soc/codecs/tda7419.c
@@ -142,9 +142,9 @@ struct tda7419_vol_control {
 static inline bool tda7419_vol_is_stereo(struct tda7419_vol_control *tvc)
 {
 	if (tvc->reg == tvc->rreg)
-		return 0;
+		return false;
 
-	return 1;
+	return true;
 }
 
 static int tda7419_vol_info(struct snd_kcontrol *kcontrol,
-- 
cgit v1.2.3


From 064ee5a370150534e12e5bac4ff81f86528e27ca Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:51:01 -0500
Subject: ASoC: wm8990: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8990.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/wm8990.c b/sound/soc/codecs/wm8990.c
index 411b9eee88c2..457bc437ce54 100644
--- a/sound/soc/codecs/wm8990.c
+++ b/sound/soc/codecs/wm8990.c
@@ -40,9 +40,9 @@ static bool wm8990_volatile_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
 	case WM8990_RESET:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From c34c4515286f27e7e99d8a0011b4322d1de6c9bc Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:52:01 -0500
Subject: ASoC: cs4270: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs4270.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs4270.c b/sound/soc/codecs/cs4270.c
index 2a7a4168c072..3c266eeb89bf 100644
--- a/sound/soc/codecs/cs4270.c
+++ b/sound/soc/codecs/cs4270.c
@@ -219,7 +219,7 @@ static bool cs4270_reg_is_volatile(struct device *dev, unsigned int reg)
 {
 	/* Unreadable registers are considered volatile */
 	if ((reg < CS4270_FIRSTREG) || (reg > CS4270_LASTREG))
-		return 1;
+		return true;
 
 	return reg == CS4270_CHIPID;
 }
-- 
cgit v1.2.3


From eb086306bc6b42dc2c538ec2350d44a82d1a835b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:52:35 -0500
Subject: ASoC: wm8996: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8996.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index 78a408236cfb..91711f8958c5 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -1498,9 +1498,9 @@ static bool wm8996_readable_register(struct device *dev, unsigned int reg)
 	case WM8996_RIGHT_PDM_SPEAKER:
 	case WM8996_PDM_SPEAKER_MUTE_SEQUENCE:
 	case WM8996_PDM_SPEAKER_VOLUME:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
@@ -1522,9 +1522,9 @@ static bool wm8996_volatile_register(struct device *dev, unsigned int reg)
 	case WM8996_MIC_DETECT_3:
 	case WM8996_HEADPHONE_DETECT_1:
 	case WM8996_HEADPHONE_DETECT_2:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From 965afd3c1dbaf293bfa9452aaf0a7e53d78d07f3 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:53:10 -0500
Subject: ASoC: da7219: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/da7219.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c
index 980a6a8bf56d..c0144f2f8174 100644
--- a/sound/soc/codecs/da7219.c
+++ b/sound/soc/codecs/da7219.c
@@ -2143,9 +2143,9 @@ static bool da7219_volatile_register(struct device *dev, unsigned int reg)
 	case DA7219_ACCDET_IRQ_EVENT_B:
 	case DA7219_ACCDET_CONFIG_8:
 	case DA7219_SYSTEM_STATUS:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From bc94c8884e5a94914ec950dfc615563a1253e3f3 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:53:38 -0500
Subject: ASoC: twl6040: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/twl6040.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/twl6040.c b/sound/soc/codecs/twl6040.c
index bfd1abd72253..94675da514c8 100644
--- a/sound/soc/codecs/twl6040.c
+++ b/sound/soc/codecs/twl6040.c
@@ -148,7 +148,7 @@ static bool twl6040_can_write_to_chip(struct snd_soc_component *component,
 	case TWL6040_REG_HFRCTL:
 		return priv->dl2_unmuted;
 	default:
-		return 1;
+		return true;
 	}
 }
 
-- 
cgit v1.2.3


From 1752a35acd8e837463fb7b7d9492b18e2a2ed5e3 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:54:10 -0500
Subject: ASoC: da7213: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/da7213.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/da7213.c b/sound/soc/codecs/da7213.c
index 54cb5f24969f..92d006a5283e 100644
--- a/sound/soc/codecs/da7213.c
+++ b/sound/soc/codecs/da7213.c
@@ -1140,9 +1140,9 @@ static bool da7213_volatile_register(struct device *dev, unsigned int reg)
 	case DA7213_ALC_OFFSET_AUTO_M_R:
 	case DA7213_ALC_OFFSET_AUTO_U_R:
 	case DA7213_ALC_CIC_OP_LVL_DATA:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From 380ae4ec420304aa59adb36776eaf78aef37192c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:54:54 -0500
Subject: ASoC: wm5100-tables: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm5100-tables.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/sound/soc/codecs/wm5100-tables.c b/sound/soc/codecs/wm5100-tables.c
index e239f4bf2460..9e987cf07450 100644
--- a/sound/soc/codecs/wm5100-tables.c
+++ b/sound/soc/codecs/wm5100-tables.c
@@ -30,7 +30,7 @@ bool wm5100_volatile_register(struct device *dev, unsigned int reg)
 	case WM5100_OUTPUT_STATUS_2:
 	case WM5100_INPUT_ENABLES_STATUS:
 	case WM5100_MIC_DETECT_3:
-		return 1;
+		return true;
 	default:
 		if ((reg >= WM5100_DSP1_PM_0 && reg <= WM5100_DSP1_PM_1535) ||
 		    (reg >= WM5100_DSP1_ZM_0 && reg <= WM5100_DSP1_ZM_2047) ||
@@ -41,9 +41,9 @@ bool wm5100_volatile_register(struct device *dev, unsigned int reg)
 		    (reg >= WM5100_DSP3_PM_0 && reg <= WM5100_DSP3_PM_1535) ||
 		    (reg >= WM5100_DSP3_ZM_0 && reg <= WM5100_DSP3_ZM_2047) ||
 		    (reg >= WM5100_DSP3_DM_0 && reg <= WM5100_DSP3_DM_511))
-			return 1;
+			return true;
 		else
-			return 0;
+			return false;
 	}
 }
 
@@ -798,7 +798,7 @@ bool wm5100_readable_register(struct device *dev, unsigned int reg)
 	case WM5100_DSP3_CONTROL_28:
 	case WM5100_DSP3_CONTROL_29:
 	case WM5100_DSP3_CONTROL_30:
-		return 1;
+		return true;
 	default:
 		if ((reg >= WM5100_DSP1_PM_0 && reg <= WM5100_DSP1_PM_1535) ||
 		    (reg >= WM5100_DSP1_ZM_0 && reg <= WM5100_DSP1_ZM_2047) ||
@@ -809,9 +809,9 @@ bool wm5100_readable_register(struct device *dev, unsigned int reg)
 		    (reg >= WM5100_DSP3_PM_0 && reg <= WM5100_DSP3_PM_1535) ||
 		    (reg >= WM5100_DSP3_ZM_0 && reg <= WM5100_DSP3_ZM_2047) ||
 		    (reg >= WM5100_DSP3_DM_0 && reg <= WM5100_DSP3_DM_511))
-			return 1;
+			return true;
 		else
-			return 0;
+			return false;
 	}
 }
 
-- 
cgit v1.2.3


From e1ec62b147c2f2deae66e69ee4f7347dc80123ae Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:55:28 -0500
Subject: ASoC: da9055: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/da9055.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/da9055.c b/sound/soc/codecs/da9055.c
index afdf90c78884..f6a7bf9560e7 100644
--- a/sound/soc/codecs/da9055.c
+++ b/sound/soc/codecs/da9055.c
@@ -1041,9 +1041,9 @@ static bool da9055_volatile_register(struct device *dev,
 	case DA9055_HP_R_GAIN_STATUS:
 	case DA9055_LINE_GAIN_STATUS:
 	case DA9055_ALC_CIC_OP_LVL_DATA:
-		return 1;
+		return true;
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From bee7d3c9f89a1bbe3d5f88ac9d6946de4705731b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 16:56:02 -0500
Subject: ASoC: wm8903: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm8903.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index 7b8b6ef2f632..6cb3c153ba19 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -251,10 +251,10 @@ static bool wm8903_volatile_register(struct device *dev, unsigned int reg)
 	case WM8903_DC_SERVO_READBACK_2:
 	case WM8903_DC_SERVO_READBACK_3:
 	case WM8903_DC_SERVO_READBACK_4:
-		return 1;
+		return true;
 
 	default:
-		return 0;
+		return false;
 	}
 }
 
-- 
cgit v1.2.3


From 8e3684f66e15c354dba5544c2af8ce973ed40cf6 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Mon, 6 Aug 2018 11:12:05 +0100
Subject: ASoC: qcom: make common.c as proper module

This patch converts common helper functions in to proper module
and also fixes below warning.

WARNING: sound/soc/qcom/snd-soc-sdm845: 'qcom_snd_parse_of' exported twice.
Previous export was in sound/soc/qcom/snd-soc-apq8096.ko

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/Kconfig  | 5 +++++
 sound/soc/qcom/Makefile | 6 ++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/sound/soc/qcom/Kconfig b/sound/soc/qcom/Kconfig
index 5f03312ef007..2a4c912d1e48 100644
--- a/sound/soc/qcom/Kconfig
+++ b/sound/soc/qcom/Kconfig
@@ -41,6 +41,9 @@ config SND_SOC_APQ8016_SBC
           APQ8016 SOC-based systems.
           Say Y if you want to use audio devices on MI2S.
 
+config SND_SOC_QCOM_COMMON
+	tristate
+
 config SND_SOC_QDSP6_COMMON
 	tristate
 
@@ -86,6 +89,7 @@ config SND_SOC_MSM8996
 	tristate "SoC Machine driver for MSM8996 and APQ8096 boards"
 	depends on QCOM_APR
 	select SND_SOC_QDSP6
+	select SND_SOC_QCOM_COMMON
 	help
           Support for Qualcomm Technologies LPASS audio block in
           APQ8096 SoC-based systems.
@@ -95,6 +99,7 @@ config SND_SOC_SDM845
 	tristate "SoC Machine driver for SDM845 boards"
 	depends on QCOM_APR
 	select SND_SOC_QDSP6
+	select SND_SOC_QCOM_COMMON
 	help
 	  To add support for audio on Qualcomm Technologies Inc.
 	  SDM845 SoC-based systems.
diff --git a/sound/soc/qcom/Makefile b/sound/soc/qcom/Makefile
index f0e94d48ba98..41b2c7a23a4d 100644
--- a/sound/soc/qcom/Makefile
+++ b/sound/soc/qcom/Makefile
@@ -13,13 +13,15 @@ obj-$(CONFIG_SND_SOC_LPASS_APQ8016) += snd-soc-lpass-apq8016.o
 # Machine
 snd-soc-storm-objs := storm.o
 snd-soc-apq8016-sbc-objs := apq8016_sbc.o
-snd-soc-apq8096-objs := apq8096.o common.o
-snd-soc-sdm845-objs := sdm845.o common.o
+snd-soc-apq8096-objs := apq8096.o
+snd-soc-sdm845-objs := sdm845.o
+snd-soc-qcom-common-objs := common.o
 
 obj-$(CONFIG_SND_SOC_STORM) += snd-soc-storm.o
 obj-$(CONFIG_SND_SOC_APQ8016_SBC) += snd-soc-apq8016-sbc.o
 obj-$(CONFIG_SND_SOC_MSM8996) += snd-soc-apq8096.o
 obj-$(CONFIG_SND_SOC_SDM845) += snd-soc-sdm845.o
+obj-$(CONFIG_SND_SOC_QCOM_COMMON) += snd-soc-qcom-common.o
 
 #DSP lib
 obj-$(CONFIG_SND_SOC_QDSP6) += qdsp6/
-- 
cgit v1.2.3


From e9d244b14dd5cf9a78ab256a4463d946e580ca63 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Mon, 6 Aug 2018 11:12:06 +0100
Subject: ASoC: apq8096: remove unused header files

This patch removes unused header files from the driver.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/apq8096.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/soc/qcom/apq8096.c b/sound/soc/qcom/apq8096.c
index 6ee7e66cbaaa..1543e85629f8 100644
--- a/sound/soc/qcom/apq8096.c
+++ b/sound/soc/qcom/apq8096.c
@@ -1,9 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Copyright (c) 2018, Linaro Limited
 
-#include <linux/soc/qcom/apr.h>
 #include <linux/module.h>
-#include <linux/component.h>
 #include <linux/platform_device.h>
 #include <linux/of_device.h>
 #include <sound/soc.h>
-- 
cgit v1.2.3


From 846b2c96808cc7cdf4e0619d00604b3edd15b35a Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Mon, 6 Aug 2018 11:12:07 +0100
Subject: ASoC: sdm845: remove unused header files

This patch removes unused header files from the driver.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/sdm845.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/soc/qcom/sdm845.c b/sound/soc/qcom/sdm845.c
index c1adb77230eb..2a781d87ee65 100644
--- a/sound/soc/qcom/sdm845.c
+++ b/sound/soc/qcom/sdm845.c
@@ -5,11 +5,9 @@
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/atomic.h>
 #include <linux/of_device.h>
 #include <sound/pcm.h>
 #include <sound/pcm_params.h>
-#include <linux/soc/qcom/apr.h>
 #include "common.h"
 #include "qdsp6/q6afe.h"
 
-- 
cgit v1.2.3


From d72117d0c89a3f5657ef91d5eef31337964e3cb2 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Mon, 6 Aug 2018 11:12:08 +0100
Subject: ASoC: qcom: remove unused header files from common.h

This patch removes unused header files from common.h.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/common.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/soc/qcom/common.h b/sound/soc/qcom/common.h
index ad5d2cf27459..f05c05b12bd7 100644
--- a/sound/soc/qcom/common.h
+++ b/sound/soc/qcom/common.h
@@ -4,7 +4,6 @@
 #ifndef __QCOM_SND_COMMON_H__
 #define __QCOM_SND_COMMON_H__
 
-#include <linux/component.h>
 #include <sound/soc.h>
 
 int qcom_snd_parse_of(struct snd_soc_card *card);
-- 
cgit v1.2.3


From 0961503412e3e13d82f885f9fb3af527edd58e47 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Mon, 6 Aug 2018 11:12:09 +0100
Subject: ASoC: qdsp6: q6afe-dai: add SLIM tx AIF_IN dapm

Add missing AIF_IN dapm for slim tx ports.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/qcom/qdsp6/q6afe-dai.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/qcom/qdsp6/q6afe-dai.c b/sound/soc/qcom/qdsp6/q6afe-dai.c
index e988692a3ced..139d24be3fb9 100644
--- a/sound/soc/qcom/qdsp6/q6afe-dai.c
+++ b/sound/soc/qcom/qdsp6/q6afe-dai.c
@@ -1117,6 +1117,13 @@ static const struct snd_soc_dapm_widget q6afe_dai_widgets[] = {
 	SND_SOC_DAPM_AIF_OUT("SLIMBUS_4_RX", "Slimbus4 Playback", 0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SLIMBUS_5_RX", "Slimbus5 Playback", 0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("SLIMBUS_6_RX", "Slimbus6 Playback", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_0_TX", "Slimbus Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_1_TX", "Slimbus1 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_2_TX", "Slimbus2 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_3_TX", "Slimbus3 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_4_TX", "Slimbus4 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_5_TX", "Slimbus5 Capture", 0, 0, 0, 0),
+	SND_SOC_DAPM_AIF_IN("SLIMBUS_6_TX", "Slimbus6 Capture", 0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_OUT("QUAT_MI2S_RX", "Quaternary MI2S Playback",
 						0, 0, 0, 0),
 	SND_SOC_DAPM_AIF_IN("QUAT_MI2S_TX", "Quaternary MI2S Capture",
-- 
cgit v1.2.3


From ad0eaee6195db1db1749dd46b9e6f4466793d178 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 6 Aug 2018 07:14:51 -0500
Subject: ASoC: wm8994: Fix missing break in switch

Add missing break statement in order to prevent the code from falling
through to the default case.

Addresses-Coverity-ID: 115050 ("Missing break in switch")
Reported-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
---
 sound/soc/codecs/wm8994.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/wm8994.c b/sound/soc/codecs/wm8994.c
index 62f8c5b9ba92..14f1b0c0d286 100644
--- a/sound/soc/codecs/wm8994.c
+++ b/sound/soc/codecs/wm8994.c
@@ -2432,7 +2432,7 @@ static int wm8994_set_dai_sysclk(struct snd_soc_dai *dai,
 			snd_soc_component_update_bits(component, WM8994_POWER_MANAGEMENT_2,
 					    WM8994_OPCLK_ENA, 0);
 		}
-		/* fall through */
+		break;
 
 	default:
 		return -EINVAL;
-- 
cgit v1.2.3


From 6ae9c84ff249f2756086e71405375fd06124cf1f Mon Sep 17 00:00:00 2001
From: Philipp Zabel <p.zabel@pengutronix.de>
Date: Tue, 15 May 2018 16:09:15 +0200
Subject: drm/etnaviv: mmuv2: use memset32 to init scratch page

Replace the open-coded scratch page initialization loop with memset32

Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
---
 drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
index 71fbc1f96cb6..f1c88d8ad5ba 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_iommu_v2.c
@@ -119,8 +119,7 @@ static size_t etnaviv_iommuv2_unmap(struct etnaviv_iommu_domain *domain,
 
 static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain)
 {
-	u32 *p;
-	int ret, i;
+	int ret;
 
 	/* allocate scratch page */
 	etnaviv_domain->base.bad_page_cpu =
@@ -131,9 +130,9 @@ static int etnaviv_iommuv2_init(struct etnaviv_iommuv2_domain *etnaviv_domain)
 		ret = -ENOMEM;
 		goto fail_mem;
 	}
-	p = etnaviv_domain->base.bad_page_cpu;
-	for (i = 0; i < SZ_4K / 4; i++)
-		*p++ = 0xdead55aa;
+
+	memset32(etnaviv_domain->base.bad_page_cpu, 0xdead55aa,
+		 SZ_4K / sizeof(u32));
 
 	etnaviv_domain->pta_cpu = dma_alloc_wc(etnaviv_domain->base.dev,
 					       SZ_4K, &etnaviv_domain->pta_dma,
-- 
cgit v1.2.3


From a0780bb1df60f00e4573db7bd53e7039e9eee1cb Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Fri, 25 May 2018 16:51:25 +0200
Subject: drm/etnaviv: protect sched job submission with fence mutex

The documentation of drm_sched_job_init and drm_sched_entity_push_job has
been clarified. Both functions should be called under a shared lock, to
avoid jobs getting pushed into the scheduler queue in a different order
than their sched_fence seqnos, which will confuse checks that are looking
at the seqnos to infer information about completion order.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
---
 drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c |  4 ++--
 drivers/gpu/drm/etnaviv/etnaviv_gpu.c        |  2 +-
 drivers/gpu/drm/etnaviv/etnaviv_gpu.h        |  2 +-
 drivers/gpu/drm/etnaviv/etnaviv_sched.c      | 24 +++++++++++++++++-------
 4 files changed, 21 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
index 46ecd3e66ac9..983e67f19e45 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem_submit.c
@@ -388,9 +388,9 @@ static void submit_cleanup(struct kref *kref)
 		dma_fence_put(submit->in_fence);
 	if (submit->out_fence) {
 		/* first remove from IDR, so fence can not be found anymore */
-		mutex_lock(&submit->gpu->fence_idr_lock);
+		mutex_lock(&submit->gpu->fence_lock);
 		idr_remove(&submit->gpu->fence_idr, submit->out_fence_id);
-		mutex_unlock(&submit->gpu->fence_idr_lock);
+		mutex_unlock(&submit->gpu->fence_lock);
 		dma_fence_put(submit->out_fence);
 	}
 	kfree(submit->pmrs);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 686f6552db48..18c2224ba0b8 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -1733,7 +1733,7 @@ static int etnaviv_gpu_platform_probe(struct platform_device *pdev)
 
 	gpu->dev = &pdev->dev;
 	mutex_init(&gpu->lock);
-	mutex_init(&gpu->fence_idr_lock);
+	mutex_init(&gpu->fence_lock);
 
 	/* Map registers: */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
index 90f17ff7888e..9a75a6937268 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.h
@@ -118,7 +118,7 @@ struct etnaviv_gpu {
 	u32 idle_mask;
 
 	/* Fencing support */
-	struct mutex fence_idr_lock;
+	struct mutex fence_lock;
 	struct idr fence_idr;
 	u32 next_fence;
 	u32 active_fence;
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
index 50d6b88cb7aa..b267d9c4d91c 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
@@ -140,28 +140,38 @@ static const struct drm_sched_backend_ops etnaviv_sched_ops = {
 int etnaviv_sched_push_job(struct drm_sched_entity *sched_entity,
 			   struct etnaviv_gem_submit *submit)
 {
-	int ret;
+	int ret = 0;
+
+	/*
+	 * Hold the fence lock across the whole operation to avoid jobs being
+	 * pushed out of order with regard to their sched fence seqnos as
+	 * allocated in drm_sched_job_init.
+	 */
+	mutex_lock(&submit->gpu->fence_lock);
 
 	ret = drm_sched_job_init(&submit->sched_job, &submit->gpu->sched,
 				 sched_entity, submit->cmdbuf.ctx);
 	if (ret)
-		return ret;
+		goto out_unlock;
 
 	submit->out_fence = dma_fence_get(&submit->sched_job.s_fence->finished);
-	mutex_lock(&submit->gpu->fence_idr_lock);
 	submit->out_fence_id = idr_alloc_cyclic(&submit->gpu->fence_idr,
 						submit->out_fence, 0,
 						INT_MAX, GFP_KERNEL);
-	mutex_unlock(&submit->gpu->fence_idr_lock);
-	if (submit->out_fence_id < 0)
-		return -ENOMEM;
+	if (submit->out_fence_id < 0) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
 
 	/* the scheduler holds on to the job now */
 	kref_get(&submit->refcount);
 
 	drm_sched_entity_push_job(&submit->sched_job, sched_entity);
 
-	return 0;
+out_unlock:
+	mutex_unlock(&submit->gpu->fence_lock);
+
+	return ret;
 }
 
 int etnaviv_sched_init(struct etnaviv_gpu *gpu)
-- 
cgit v1.2.3


From cfad05a24dcb2bf09ba6438e0843c6a0ed90381c Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Tue, 29 May 2018 19:17:27 +0530
Subject: drm/etnaviv: change return type to vm_fault_t

Use new return type vm_fault_t for fault handler. For
now, this is just documenting that the function returns
a VM_FAULT value rather than an errno. Once all instances
are converted, vm_fault_t will become a distinct type.

Ref- commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Previously vm_insert_page() returns err which driver
mapped into VM_FAULT_* type. The new function
vmf_insert_page() will replace this inefficiency by
returning VM_FAULT_* type.

vmf_error() is the newly introduce inline function
in 4.17-rc6.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
---
 drivers/gpu/drm/etnaviv/etnaviv_drv.h |  3 ++-
 drivers/gpu/drm/etnaviv/etnaviv_gem.c | 37 +++++++++--------------------------
 2 files changed, 11 insertions(+), 29 deletions(-)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_drv.h b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
index d36c7bbe66db..8d02d1b7dcf5 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_drv.h
+++ b/drivers/gpu/drm/etnaviv/etnaviv_drv.h
@@ -18,6 +18,7 @@
 #include <linux/time64.h>
 #include <linux/types.h>
 #include <linux/sizes.h>
+#include <linux/mm_types.h>
 
 #include <drm/drmP.h>
 #include <drm/drm_crtc_helper.h>
@@ -53,7 +54,7 @@ int etnaviv_ioctl_gem_submit(struct drm_device *dev, void *data,
 		struct drm_file *file);
 
 int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma);
-int etnaviv_gem_fault(struct vm_fault *vmf);
+vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf);
 int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset);
 struct sg_table *etnaviv_gem_prime_get_sg_table(struct drm_gem_object *obj);
 void *etnaviv_gem_prime_vmap(struct drm_gem_object *obj);
diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
index 209ef1274b80..1fa74226db91 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
@@ -169,31 +169,30 @@ int etnaviv_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	return obj->ops->mmap(obj, vma);
 }
 
-int etnaviv_gem_fault(struct vm_fault *vmf)
+vm_fault_t etnaviv_gem_fault(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
 	struct drm_gem_object *obj = vma->vm_private_data;
 	struct etnaviv_gem_object *etnaviv_obj = to_etnaviv_bo(obj);
 	struct page **pages, *page;
 	pgoff_t pgoff;
-	int ret;
+	int err;
 
 	/*
 	 * Make sure we don't parallel update on a fault, nor move or remove
-	 * something from beneath our feet.  Note that vm_insert_page() is
+	 * something from beneath our feet.  Note that vmf_insert_page() is
 	 * specifically coded to take care of this, so we don't have to.
 	 */
-	ret = mutex_lock_interruptible(&etnaviv_obj->lock);
-	if (ret)
-		goto out;
-
+	err = mutex_lock_interruptible(&etnaviv_obj->lock);
+	if (err)
+		return VM_FAULT_NOPAGE;
 	/* make sure we have pages attached now */
 	pages = etnaviv_gem_get_pages(etnaviv_obj);
 	mutex_unlock(&etnaviv_obj->lock);
 
 	if (IS_ERR(pages)) {
-		ret = PTR_ERR(pages);
-		goto out;
+		err = PTR_ERR(pages);
+		return vmf_error(err);
 	}
 
 	/* We don't use vmf->pgoff since that has the fake offset: */
@@ -204,25 +203,7 @@ int etnaviv_gem_fault(struct vm_fault *vmf)
 	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 	     page_to_pfn(page), page_to_pfn(page) << PAGE_SHIFT);
 
-	ret = vm_insert_page(vma, vmf->address, page);
-
-out:
-	switch (ret) {
-	case -EAGAIN:
-	case 0:
-	case -ERESTARTSYS:
-	case -EINTR:
-	case -EBUSY:
-		/*
-		 * EBUSY is ok: this just means that another thread
-		 * already did the job.
-		 */
-		return VM_FAULT_NOPAGE;
-	case -ENOMEM:
-		return VM_FAULT_OOM;
-	default:
-		return VM_FAULT_SIGBUS;
-	}
+	return vmf_insert_page(vma, vmf->address, page);
 }
 
 int etnaviv_gem_mmap_offset(struct drm_gem_object *obj, u64 *offset)
-- 
cgit v1.2.3


From 5b147465532365dc4e2fee8499d6ca1f52dd0d16 Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Mon, 23 Jul 2018 14:27:23 +0200
Subject: drm/etnaviv: fix crash in GPU suspend when init failed due to buffer
 placement

When the suballocator was unable to provide a suitable buffer for the MMUv1
linear window, we roll back the GPU initialization. As the GPU is runtime
resumed at that point we need to clear the kernel cmdbuf suballoc entry to
properly skip any attempt to manipulate the cmdbuf when the GPU gets shut
down in the runtime suspend later on.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
---
 drivers/gpu/drm/etnaviv/etnaviv_gpu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
index 18c2224ba0b8..ab8dfe7f69d6 100644
--- a/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
+++ b/drivers/gpu/drm/etnaviv/etnaviv_gpu.c
@@ -799,6 +799,7 @@ int etnaviv_gpu_init(struct etnaviv_gpu *gpu)
 
 free_buffer:
 	etnaviv_cmdbuf_free(&gpu->buffer);
+	gpu->buffer.suballoc = NULL;
 destroy_iommu:
 	etnaviv_iommu_destroy(gpu->mmu);
 	gpu->mmu = NULL;
-- 
cgit v1.2.3


From ad3e0b2f3c9483fa79bb4148464dba52ce33ae46 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 6 Aug 2018 19:08:51 +0800
Subject: Bluetooth: remove redundant variables 'adv_set' and 'cp'

Variables 'adv_set' and 'cp'  are being assigned but are never used hence
they are redundant and can be removed.

Cleans up clang warnings:
net/bluetooth/hci_event.c:1135:29: warning: variable 'adv_set' set but not used [-Wunused-but-set-variable]
net/bluetooth/mgmt.c:3359:39: warning: variable 'cp' set but not used [-Wunused-but-set-variable]

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 net/bluetooth/hci_event.c | 3 ---
 net/bluetooth/mgmt.c      | 3 ---
 2 files changed, 6 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 754714c8d752..8078587572fe 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1132,7 +1132,6 @@ static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev,
 					 struct sk_buff *skb)
 {
 	struct hci_cp_le_set_ext_adv_enable *cp;
-	struct hci_cp_ext_adv_set *adv_set;
 	__u8 status = *((__u8 *) skb->data);
 
 	BT_DBG("%s status 0x%2.2x", hdev->name, status);
@@ -1144,8 +1143,6 @@ static void hci_cc_le_set_ext_adv_enable(struct hci_dev *hdev,
 	if (!cp)
 		return;
 
-	adv_set = (void *) cp->data;
-
 	hci_dev_lock(hdev);
 
 	if (cp->enable) {
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 231602f7cb66..3bdc8f3ca259 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3356,7 +3356,6 @@ int mgmt_phy_configuration_changed(struct hci_dev *hdev, struct sock *skip)
 static void set_default_phy_complete(struct hci_dev *hdev, u8 status,
 				     u16 opcode, struct sk_buff *skb)
 {
-	struct mgmt_cp_set_phy_confguration *cp;
 	struct mgmt_pending_cmd *cmd;
 
 	BT_DBG("status 0x%02x", status);
@@ -3367,8 +3366,6 @@ static void set_default_phy_complete(struct hci_dev *hdev, u8 status,
 	if (!cmd)
 		goto unlock;
 
-	cp = cmd->param;
-
 	if (status) {
 		mgmt_cmd_status(cmd->sk, hdev->id,
 				MGMT_OP_SET_PHY_CONFIGURATION,
-- 
cgit v1.2.3


From f87c30c96cd9b5baa28bc63900f16e04e8c7cbb2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 6 Aug 2018 08:14:55 -0600
Subject: xen-blkfront: use true and false for boolean values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Acked-by: Roger Pau Monné <roger.pau@citrix.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/xen-blkfront.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 94300dbe358b..8986adab9bf5 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -1436,7 +1436,7 @@ static bool blkif_completion(unsigned long *id,
 
 		/* Wait the second response if not yet here. */
 		if (s2->status == REQ_WAITING)
-			return 0;
+			return false;
 
 		bret->status = blkif_get_final_status(s->status,
 						      s2->status);
@@ -1537,7 +1537,7 @@ static bool blkif_completion(unsigned long *id,
 		}
 	}
 
-	return 1;
+	return true;
 }
 
 static irqreturn_t blkif_interrupt(int irq, void *dev_id)
-- 
cgit v1.2.3


From bf06bad958c4536ee5ac3461a18976ea3e896f26 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 19:50:14 -0500
Subject: xen/biomerge: Use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/biomerge.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/xen/biomerge.c b/drivers/xen/biomerge.c
index 30d7f52eb7ca..55ed80c3a17c 100644
--- a/drivers/xen/biomerge.c
+++ b/drivers/xen/biomerge.c
@@ -17,7 +17,7 @@ bool xen_biovec_phys_mergeable(const struct bio_vec *vec1,
 	 * XXX: Add support for merging bio_vec when using different page
 	 * size in Xen and Linux.
 	 */
-	return 0;
+	return false;
 #endif
 }
 EXPORT_SYMBOL(xen_biovec_phys_mergeable);
-- 
cgit v1.2.3


From bbdb7012b0736cda0b9b00a2949e9207cf2f892f Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Mon, 6 Aug 2018 12:57:14 +0530
Subject: ASoC: AMD: Make ACP->SYSMEM DMA non circular

In capture case we don't want ACP to SYSMEM dma
to be circular. This is because if an in place DSP
filter is applied to captured output then circular DMA
can overwrite the filter value with stale data.

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 36 +++++++++++++++++++++++++++++++-----
 1 file changed, 31 insertions(+), 5 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 94bcf69008df..816abd65a6ed 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -400,7 +400,7 @@ static void acp_dma_cap_channel_disable(void __iomem *acp_mmio,
 }
 
 /* Start a given DMA channel transfer */
-static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
+static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num, bool is_circular)
 {
 	u32 dma_ctrl;
 
@@ -429,8 +429,11 @@ static void acp_dma_start(void __iomem *acp_mmio, u16 ch_num)
 		break;
 	}
 
-	/* circular for both DMA channel */
-	dma_ctrl |= ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
+	/* enable for ACP to SRAM DMA channel */
+	if (is_circular == true)
+		dma_ctrl |= ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
+	else
+		dma_ctrl &= ~ACP_DMA_CNTL_0__Circular_DMA_En_MASK;
 
 	acp_reg_write(dma_ctrl, acp_mmio, mmACP_DMA_CNTL_0 + ch_num);
 }
@@ -674,6 +677,7 @@ static int acp_deinit(void __iomem *acp_mmio)
 /* ACP DMA irq handler routine for playback, capture usecases */
 static irqreturn_t dma_irq_handler(int irq, void *arg)
 {
+	u16 dscr_idx;
 	u32 intr_flag, ext_intr_status;
 	struct audio_drv_data *irq_data;
 	void __iomem *acp_mmio;
@@ -705,6 +709,15 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 
 	if ((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) != 0) {
 		valid_irq = true;
+		if (acp_reg_read(acp_mmio, mmACP_DMA_CUR_DSCR_14) ==
+				CAPTURE_START_DMA_DESCR_CH15)
+			dscr_idx = CAPTURE_END_DMA_DESCR_CH14;
+		else
+			dscr_idx = CAPTURE_START_DMA_DESCR_CH14;
+		config_acp_dma_channel(acp_mmio, ACP_TO_SYSRAM_CH_NUM, dscr_idx,
+				       1, 0);
+		acp_dma_start(acp_mmio, ACP_TO_SYSRAM_CH_NUM, false);
+
 		snd_pcm_period_elapsed(irq_data->capture_i2ssp_stream);
 		acp_reg_write((intr_flag & BIT(I2S_TO_ACP_DMA_CH_NUM)) << 16,
 			      acp_mmio, mmACP_EXTERNAL_INTR_STAT);
@@ -712,6 +725,17 @@ static irqreturn_t dma_irq_handler(int irq, void *arg)
 
 	if ((intr_flag & BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) != 0) {
 		valid_irq = true;
+		if (acp_reg_read(acp_mmio, mmACP_DMA_CUR_DSCR_10) ==
+			CAPTURE_START_DMA_DESCR_CH11)
+			dscr_idx = CAPTURE_END_DMA_DESCR_CH10;
+		else
+			dscr_idx = CAPTURE_START_DMA_DESCR_CH10;
+		config_acp_dma_channel(acp_mmio,
+				       ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM,
+				       dscr_idx, 1, 0);
+		acp_dma_start(acp_mmio, ACP_TO_SYSRAM_BT_INSTANCE_CH_NUM,
+			      false);
+
 		snd_pcm_period_elapsed(irq_data->capture_i2sbt_stream);
 		acp_reg_write((intr_flag &
 			      BIT(I2S_TO_ACP_DMA_BT_INSTANCE_CH_NUM)) << 16,
@@ -1053,9 +1077,11 @@ static int acp_dma_trigger(struct snd_pcm_substream *substream, int cmd)
 				acp_dma_cap_channel_enable(rtd->acp_mmio,
 							   CAP_CHANNEL1);
 			}
+			acp_dma_start(rtd->acp_mmio, rtd->ch1, true);
+		} else {
+			acp_dma_start(rtd->acp_mmio, rtd->ch1, true);
+			acp_dma_start(rtd->acp_mmio, rtd->ch2, true);
 		}
-		acp_dma_start(rtd->acp_mmio, rtd->ch1);
-		acp_dma_start(rtd->acp_mmio, rtd->ch2);
 		ret = 0;
 		break;
 	case SNDRV_PCM_TRIGGER_STOP:
-- 
cgit v1.2.3


From 662fb3efe7ee835f0eeba6bc63b81e82a97fc312 Mon Sep 17 00:00:00 2001
From: "Mukunda, Vijendar" <Vijendar.Mukunda@amd.com>
Date: Mon, 6 Aug 2018 12:57:15 +0530
Subject: ASoC: AMD: Modified DMA pointer for capture

Give position on ACP->SYSMEM DMA channel for
the number of bytes that have been transferred on
the basis of current descriptor under service.

Signed-off-by: Vijendar Mukunda <Vijendar.Mukunda@amd.com>
Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 31 ++++++++++++++++++-------------
 sound/soc/amd/acp.h         |  1 +
 2 files changed, 19 insertions(+), 13 deletions(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 816abd65a6ed..32f27c5e4d93 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -922,10 +922,7 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 			rtd->destination = FROM_BLUETOOTH;
 			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH10;
 			rtd->dma_dscr_idx_2 = CAPTURE_START_DMA_DESCR_CH11;
-			rtd->byte_cnt_high_reg_offset =
-					mmACP_I2S_BT_RECEIVE_BYTE_CNT_HIGH;
-			rtd->byte_cnt_low_reg_offset =
-					mmACP_I2S_BT_RECEIVE_BYTE_CNT_LOW;
+			rtd->dma_curr_dscr = mmACP_DMA_CUR_DSCR_11;
 			adata->capture_i2sbt_stream = substream;
 			break;
 		case I2S_SP_INSTANCE:
@@ -945,10 +942,7 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 			rtd->destination = FROM_ACP_I2S_1;
 			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH14;
 			rtd->dma_dscr_idx_2 = CAPTURE_START_DMA_DESCR_CH15;
-			rtd->byte_cnt_high_reg_offset =
-					mmACP_I2S_RECEIVED_BYTE_CNT_HIGH;
-			rtd->byte_cnt_low_reg_offset =
-					mmACP_I2S_RECEIVED_BYTE_CNT_LOW;
+			rtd->dma_curr_dscr = mmACP_DMA_CUR_DSCR_15;
 			adata->capture_i2ssp_stream = substream;
 		}
 	}
@@ -1002,6 +996,8 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 	u32 buffersize;
 	u32 pos = 0;
 	u64 bytescount = 0;
+	u16 dscr;
+	u32 period_bytes;
 
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
@@ -1009,11 +1005,20 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 	if (!rtd)
 		return -EINVAL;
 
-	buffersize = frames_to_bytes(runtime, runtime->buffer_size);
-	bytescount = acp_get_byte_count(rtd);
-
-	bytescount -= rtd->bytescount;
-	pos = do_div(bytescount, buffersize);
+	if (substream->stream == SNDRV_PCM_STREAM_CAPTURE) {
+		period_bytes = frames_to_bytes(runtime, runtime->period_size);
+		dscr = acp_reg_read(rtd->acp_mmio, rtd->dma_curr_dscr);
+		if (dscr == rtd->dma_dscr_idx_1)
+			pos = period_bytes;
+		else
+			pos = 0;
+	} else {
+		buffersize = frames_to_bytes(runtime, runtime->buffer_size);
+		bytescount = acp_get_byte_count(rtd);
+		if (bytescount > rtd->bytescount)
+			bytescount -= rtd->bytescount;
+		pos = do_div(bytescount, buffersize);
+	}
 	return bytes_to_frames(runtime, pos);
 }
 
diff --git a/sound/soc/amd/acp.h b/sound/soc/amd/acp.h
index 0a2240bff62e..be3963e8f4fa 100644
--- a/sound/soc/amd/acp.h
+++ b/sound/soc/amd/acp.h
@@ -138,6 +138,7 @@ struct audio_substream_data {
 	u32 sram_bank;
 	u32 byte_cnt_high_reg_offset;
 	u32 byte_cnt_low_reg_offset;
+	u32 dma_curr_dscr;
 	uint64_t size;
 	u64 bytescount;
 	void __iomem *acp_mmio;
-- 
cgit v1.2.3


From c21c834adb5bc81e7081aa93ac50619c6d060506 Mon Sep 17 00:00:00 2001
From: Akshu Agrawal <akshu.agrawal@amd.com>
Date: Mon, 6 Aug 2018 12:57:16 +0530
Subject: ASoC: AMD: Set delay value for the capture case

ACP->SYSMEM DMA happens at every I2S->SYSMEM period
completion. Thus, there is delay of x frames till
I2S->SYSMEM reaches a period length. This delay is
communicated to user space.

Signed-off-by: Akshu Agrawal <akshu.agrawal@amd.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/acp-pcm-dma.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/sound/soc/amd/acp-pcm-dma.c b/sound/soc/amd/acp-pcm-dma.c
index 32f27c5e4d93..e359938e3d7e 100644
--- a/sound/soc/amd/acp-pcm-dma.c
+++ b/sound/soc/amd/acp-pcm-dma.c
@@ -922,6 +922,10 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 			rtd->destination = FROM_BLUETOOTH;
 			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH10;
 			rtd->dma_dscr_idx_2 = CAPTURE_START_DMA_DESCR_CH11;
+			rtd->byte_cnt_high_reg_offset =
+					mmACP_I2S_BT_RECEIVE_BYTE_CNT_HIGH;
+			rtd->byte_cnt_low_reg_offset =
+					mmACP_I2S_BT_RECEIVE_BYTE_CNT_LOW;
 			rtd->dma_curr_dscr = mmACP_DMA_CUR_DSCR_11;
 			adata->capture_i2sbt_stream = substream;
 			break;
@@ -942,6 +946,10 @@ static int acp_dma_hw_params(struct snd_pcm_substream *substream,
 			rtd->destination = FROM_ACP_I2S_1;
 			rtd->dma_dscr_idx_1 = CAPTURE_START_DMA_DESCR_CH14;
 			rtd->dma_dscr_idx_2 = CAPTURE_START_DMA_DESCR_CH15;
+			rtd->byte_cnt_high_reg_offset =
+					mmACP_I2S_RECEIVED_BYTE_CNT_HIGH;
+			rtd->byte_cnt_low_reg_offset =
+					mmACP_I2S_RECEIVED_BYTE_CNT_LOW;
 			rtd->dma_curr_dscr = mmACP_DMA_CUR_DSCR_15;
 			adata->capture_i2ssp_stream = substream;
 		}
@@ -997,7 +1005,7 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 	u32 pos = 0;
 	u64 bytescount = 0;
 	u16 dscr;
-	u32 period_bytes;
+	u32 period_bytes, delay;
 
 	struct snd_pcm_runtime *runtime = substream->runtime;
 	struct audio_substream_data *rtd = runtime->private_data;
@@ -1012,6 +1020,11 @@ static snd_pcm_uframes_t acp_dma_pointer(struct snd_pcm_substream *substream)
 			pos = period_bytes;
 		else
 			pos = 0;
+		bytescount = acp_get_byte_count(rtd);
+		if (bytescount > rtd->bytescount)
+			bytescount -= rtd->bytescount;
+		delay = do_div(bytescount, period_bytes);
+		runtime->delay = bytes_to_frames(runtime, delay);
 	} else {
 		buffersize = frames_to_bytes(runtime, runtime->buffer_size);
 		bytescount = acp_get_byte_count(rtd);
-- 
cgit v1.2.3


From 7dc084d62591bd5d7d09b4801fd4ec4ea3c59dca Mon Sep 17 00:00:00 2001
From: "Robert P. J. Day" <rpjday@crashcourse.ca>
Date: Mon, 6 Aug 2018 12:26:48 -0400
Subject: MIPS: Remove obsolete MIPS checks for DST node "chosen@0"

As there is precious little left in any DTS files referring to the
node "/chosen@0" as opposed to "/chosen", remove the two checks for
the former node name.

[paul.burton@mips.com:
  The modified yamon-dt code only operates on
  arch/mips/boot/dts/mti/sead3.dts right now, and that uses chosen
  rather than chosen@0 anyway, so this should have no behavioural
  effect.]

Signed-off-by: Robert P. J. Day <rpjday@crashcourse.ca>
Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20131/
Cc: linux-mips@linux-mips.org
---
 arch/mips/generic/yamon-dt.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/arch/mips/generic/yamon-dt.c b/arch/mips/generic/yamon-dt.c
index b408dac722ac..7ba4ad5cc1d6 100644
--- a/arch/mips/generic/yamon-dt.c
+++ b/arch/mips/generic/yamon-dt.c
@@ -27,8 +27,6 @@ __init int yamon_dt_append_cmdline(void *fdt)
 
 	/* find or add chosen node */
 	chosen_off = fdt_path_offset(fdt, "/chosen");
-	if (chosen_off == -FDT_ERR_NOTFOUND)
-		chosen_off = fdt_path_offset(fdt, "/chosen@0");
 	if (chosen_off == -FDT_ERR_NOTFOUND)
 		chosen_off = fdt_add_subnode(fdt, 0, "chosen");
 	if (chosen_off < 0) {
@@ -220,8 +218,6 @@ __init int yamon_dt_serial_config(void *fdt)
 
 	/* find or add chosen node */
 	chosen_off = fdt_path_offset(fdt, "/chosen");
-	if (chosen_off == -FDT_ERR_NOTFOUND)
-		chosen_off = fdt_path_offset(fdt, "/chosen@0");
 	if (chosen_off == -FDT_ERR_NOTFOUND)
 		chosen_off = fdt_add_subnode(fdt, 0, "chosen");
 	if (chosen_off < 0) {
-- 
cgit v1.2.3


From c883da313ebf459efd33d262ca963e3a5f0ac024 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 30 Jul 2018 07:54:56 -0400
Subject: locks: add tracepoint in flock codepath

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/locks.c                      | 1 +
 include/trace/events/filelock.h | 5 ++++-
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/locks.c b/fs/locks.c
index e533623e2e99..6138a9bcd924 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -990,6 +990,7 @@ out:
 	if (new_fl)
 		locks_free_lock(new_fl);
 	locks_dispose_list(&dispose);
+	trace_flock_lock_inode(inode, request, error);
 	return error;
 }
 
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index d1faf3597b9d..68b17c116907 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -112,8 +112,11 @@ DEFINE_EVENT(filelock_lock, locks_remove_posix,
 		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
 		TP_ARGS(inode, fl, ret));
 
-DECLARE_EVENT_CLASS(filelock_lease,
+DEFINE_EVENT(filelock_lock, flock_lock_inode,
+		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
+		TP_ARGS(inode, fl, ret));
 
+DECLARE_EVENT_CLASS(filelock_lease,
 	TP_PROTO(struct inode *inode, struct file_lock *fl),
 
 	TP_ARGS(inode, fl),
-- 
cgit v1.2.3


From 96c25b777442d3a875b1921b1f047ea00d96c8ea Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@redhat.com>
Date: Sun, 17 Jun 2018 05:31:17 -0400
Subject: mailmap: remap some of my email addresses to kernel.org address

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 .mailmap | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/.mailmap b/.mailmap
index 29ddeb1bf015..d96147eb1a68 100644
--- a/.mailmap
+++ b/.mailmap
@@ -81,6 +81,9 @@ Javi Merino <javi.merino@kernel.org> <javi.merino@arm.com>
 <javier@osg.samsung.com> <javier.martinez@collabora.co.uk>
 Jean Tourrilhes <jt@hpl.hp.com>
 Jeff Garzik <jgarzik@pretzel.yyz.us>
+Jeff Layton <jlayton@kernel.org> <jlayton@redhat.com>
+Jeff Layton <jlayton@kernel.org> <jlayton@poochiereds.net>
+Jeff Layton <jlayton@kernel.org> <jlayton@primarydata.com>
 Jens Axboe <axboe@suse.de>
 Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
 Johan Hovold <johan@kernel.org> <jhovold@gmail.com>
-- 
cgit v1.2.3


From be1459de2eea3619dbbb8f1f9a420e103a85986a Mon Sep 17 00:00:00 2001
From: Al Viro <viro@ZenIV.linux.org.uk>
Date: Sat, 4 Aug 2018 21:41:27 +0100
Subject: mellanox: fix the dport endianness in call of
 __inet6_lookup_established()

__inet6_lookup_established() expect th->dport passed in host-endian,
not net-endian.  The reason is microoptimization in __inet6_lookup(),
but if you use the lower-level helpers, you have to play by their
rules...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
index 92d37459850e..be137d4a9169 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c
@@ -328,7 +328,7 @@ static int tls_update_resync_sn(struct net_device *netdev,
 
 		sk = __inet6_lookup_established(dev_net(netdev), &tcp_hashinfo,
 						&ipv6h->saddr, th->source,
-						&ipv6h->daddr, th->dest,
+						&ipv6h->daddr, ntohs(th->dest),
 						netdev->ifindex, 0);
 #endif
 	}
-- 
cgit v1.2.3


From 9c2e955c48363a6a000a684aa49be7f4ac1120ad Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Mon, 6 Aug 2018 11:07:23 +0800
Subject: net/bridge/br_multicast: remove redundant variable "err"

The err is not modified after initalization, So remove it and make
it to be void function.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/bridge/br_multicast.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index 920665dd92db..20ed7adcf1cc 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1423,10 +1423,10 @@ static void br_multicast_query_received(struct net_bridge *br,
 	br_multicast_mark_router(br, port);
 }
 
-static int br_ip4_multicast_query(struct net_bridge *br,
-				  struct net_bridge_port *port,
-				  struct sk_buff *skb,
-				  u16 vid)
+static void br_ip4_multicast_query(struct net_bridge *br,
+				   struct net_bridge_port *port,
+				   struct sk_buff *skb,
+				   u16 vid)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct igmphdr *ih = igmp_hdr(skb);
@@ -1439,7 +1439,6 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 	unsigned long now = jiffies;
 	unsigned int offset = skb_transport_offset(skb);
 	__be32 group;
-	int err = 0;
 
 	spin_lock(&br->multicast_lock);
 	if (!netif_running(br->dev) ||
@@ -1498,7 +1497,6 @@ static int br_ip4_multicast_query(struct net_bridge *br,
 
 out:
 	spin_unlock(&br->multicast_lock);
-	return err;
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
@@ -1828,7 +1826,7 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br,
 		err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid);
 		break;
 	case IGMP_HOST_MEMBERSHIP_QUERY:
-		err = br_ip4_multicast_query(br, port, skb_trimmed, vid);
+		br_ip4_multicast_query(br, port, skb_trimmed, vid);
 		break;
 	case IGMP_HOST_LEAVE_MESSAGE:
 		br_ip4_multicast_leave_group(br, port, ih->group, vid, src);
-- 
cgit v1.2.3


From 429711aec282c4b5fe5bbd7b2f0bbbff4110ffb2 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Mon, 6 Aug 2018 11:17:47 +0800
Subject: vhost: switch to use new message format

We use to have message like:

struct vhost_msg {
	int type;
	union {
		struct vhost_iotlb_msg iotlb;
		__u8 padding[64];
	};
};

Unfortunately, there will be a hole of 32bit in 64bit machine because
of the alignment. This leads a different formats between 32bit API and
64bit API. What's more it will break 32bit program running on 64bit
machine.

So fixing this by introducing a new message type with an explicit
32bit reserved field after type like:

struct vhost_msg_v2 {
	__u32 type;
	__u32 reserved;
	union {
		struct vhost_iotlb_msg iotlb;
		__u8 padding[64];
	};
};

We will have a consistent ABI after switching to use this. To enable
this capability, introduce a new ioctl (VHOST_SET_BAKCEND_FEATURE) for
userspace to enable this feature (VHOST_BACKEND_F_IOTLB_V2).

Fixes: 6b1e6cc7855b ("vhost: new device IOTLB API")
Signed-off-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/vhost/net.c        | 30 ++++++++++++++++++++
 drivers/vhost/vhost.c      | 71 ++++++++++++++++++++++++++++++++++------------
 drivers/vhost/vhost.h      | 11 ++++++-
 include/uapi/linux/vhost.h | 18 ++++++++++++
 4 files changed, 111 insertions(+), 19 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 367d8023b54d..4e656f89cb22 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -77,6 +77,10 @@ enum {
 			 (1ULL << VIRTIO_F_IOMMU_PLATFORM)
 };
 
+enum {
+	VHOST_NET_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2)
+};
+
 enum {
 	VHOST_NET_VQ_RX = 0,
 	VHOST_NET_VQ_TX = 1,
@@ -1399,6 +1403,21 @@ done:
 	return err;
 }
 
+static int vhost_net_set_backend_features(struct vhost_net *n, u64 features)
+{
+	int i;
+
+	mutex_lock(&n->dev.mutex);
+	for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
+		mutex_lock(&n->vqs[i].vq.mutex);
+		n->vqs[i].vq.acked_backend_features = features;
+		mutex_unlock(&n->vqs[i].vq.mutex);
+	}
+	mutex_unlock(&n->dev.mutex);
+
+	return 0;
+}
+
 static int vhost_net_set_features(struct vhost_net *n, u64 features)
 {
 	size_t vhost_hlen, sock_hlen, hdr_len;
@@ -1489,6 +1508,17 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 		if (features & ~VHOST_NET_FEATURES)
 			return -EOPNOTSUPP;
 		return vhost_net_set_features(n, features);
+	case VHOST_GET_BACKEND_FEATURES:
+		features = VHOST_NET_BACKEND_FEATURES;
+		if (copy_to_user(featurep, &features, sizeof(features)))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_BACKEND_FEATURES:
+		if (copy_from_user(&features, featurep, sizeof(features)))
+			return -EFAULT;
+		if (features & ~VHOST_NET_BACKEND_FEATURES)
+			return -EOPNOTSUPP;
+		return vhost_net_set_backend_features(n, features);
 	case VHOST_RESET_OWNER:
 		return vhost_net_reset_owner(n);
 	case VHOST_SET_OWNER:
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a502f1af4a21..6f6c42d5e4be 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -315,6 +315,7 @@ static void vhost_vq_reset(struct vhost_dev *dev,
 	vq->log_addr = -1ull;
 	vq->private_data = NULL;
 	vq->acked_features = 0;
+	vq->acked_backend_features = 0;
 	vq->log_base = NULL;
 	vq->error_ctx = NULL;
 	vq->kick = NULL;
@@ -1027,28 +1028,40 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 			     struct iov_iter *from)
 {
-	struct vhost_msg_node node;
-	unsigned size = sizeof(struct vhost_msg);
-	size_t ret;
-	int err;
+	struct vhost_iotlb_msg msg;
+	size_t offset;
+	int type, ret;
 
-	if (iov_iter_count(from) < size)
-		return 0;
-	ret = copy_from_iter(&node.msg, size, from);
-	if (ret != size)
+	ret = copy_from_iter(&type, sizeof(type), from);
+	if (ret != sizeof(type))
 		goto done;
 
-	switch (node.msg.type) {
+	switch (type) {
 	case VHOST_IOTLB_MSG:
-		err = vhost_process_iotlb_msg(dev, &node.msg.iotlb);
-		if (err)
-			ret = err;
+		/* There maybe a hole after type for V1 message type,
+		 * so skip it here.
+		 */
+		offset = offsetof(struct vhost_msg, iotlb) - sizeof(int);
+		break;
+	case VHOST_IOTLB_MSG_V2:
+		offset = sizeof(__u32);
 		break;
 	default:
 		ret = -EINVAL;
-		break;
+		goto done;
+	}
+
+	iov_iter_advance(from, offset);
+	ret = copy_from_iter(&msg, sizeof(msg), from);
+	if (ret != sizeof(msg))
+		goto done;
+	if (vhost_process_iotlb_msg(dev, &msg)) {
+		ret = -EFAULT;
+		goto done;
 	}
 
+	ret = (type == VHOST_IOTLB_MSG) ? sizeof(struct vhost_msg) :
+	      sizeof(struct vhost_msg_v2);
 done:
 	return ret;
 }
@@ -1107,13 +1120,28 @@ ssize_t vhost_chr_read_iter(struct vhost_dev *dev, struct iov_iter *to,
 		finish_wait(&dev->wait, &wait);
 
 	if (node) {
-		ret = copy_to_iter(&node->msg, size, to);
+		struct vhost_iotlb_msg *msg;
+		void *start = &node->msg;
+
+		switch (node->msg.type) {
+		case VHOST_IOTLB_MSG:
+			size = sizeof(node->msg);
+			msg = &node->msg.iotlb;
+			break;
+		case VHOST_IOTLB_MSG_V2:
+			size = sizeof(node->msg_v2);
+			msg = &node->msg_v2.iotlb;
+			break;
+		default:
+			BUG();
+			break;
+		}
 
-		if (ret != size || node->msg.type != VHOST_IOTLB_MISS) {
+		ret = copy_to_iter(start, size, to);
+		if (ret != size || msg->type != VHOST_IOTLB_MISS) {
 			kfree(node);
 			return ret;
 		}
-
 		vhost_enqueue_msg(dev, &dev->pending_list, node);
 	}
 
@@ -1126,12 +1154,19 @@ static int vhost_iotlb_miss(struct vhost_virtqueue *vq, u64 iova, int access)
 	struct vhost_dev *dev = vq->dev;
 	struct vhost_msg_node *node;
 	struct vhost_iotlb_msg *msg;
+	bool v2 = vhost_backend_has_feature(vq, VHOST_BACKEND_F_IOTLB_MSG_V2);
 
-	node = vhost_new_msg(vq, VHOST_IOTLB_MISS);
+	node = vhost_new_msg(vq, v2 ? VHOST_IOTLB_MSG_V2 : VHOST_IOTLB_MSG);
 	if (!node)
 		return -ENOMEM;
 
-	msg = &node->msg.iotlb;
+	if (v2) {
+		node->msg_v2.type = VHOST_IOTLB_MSG_V2;
+		msg = &node->msg_v2.iotlb;
+	} else {
+		msg = &node->msg.iotlb;
+	}
+
 	msg->type = VHOST_IOTLB_MISS;
 	msg->iova = iova;
 	msg->perm = access;
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index 6c844b90a168..466ef7542291 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -132,6 +132,7 @@ struct vhost_virtqueue {
 	struct vhost_umem *iotlb;
 	void *private_data;
 	u64 acked_features;
+	u64 acked_backend_features;
 	/* Log write descriptors */
 	void __user *log_base;
 	struct vhost_log *log;
@@ -147,7 +148,10 @@ struct vhost_virtqueue {
 };
 
 struct vhost_msg_node {
-  struct vhost_msg msg;
+  union {
+	  struct vhost_msg msg;
+	  struct vhost_msg_v2 msg_v2;
+  };
   struct vhost_virtqueue *vq;
   struct list_head node;
 };
@@ -238,6 +242,11 @@ static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
 	return vq->acked_features & (1ULL << bit);
 }
 
+static inline bool vhost_backend_has_feature(struct vhost_virtqueue *vq, int bit)
+{
+	return vq->acked_backend_features & (1ULL << bit);
+}
+
 #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
 static inline bool vhost_is_little_endian(struct vhost_virtqueue *vq)
 {
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index c51f8e5cc608..b1e22c40c4b6 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -65,6 +65,7 @@ struct vhost_iotlb_msg {
 };
 
 #define VHOST_IOTLB_MSG 0x1
+#define VHOST_IOTLB_MSG_V2 0x2
 
 struct vhost_msg {
 	int type;
@@ -74,6 +75,15 @@ struct vhost_msg {
 	};
 };
 
+struct vhost_msg_v2 {
+	__u32 type;
+	__u32 reserved;
+	union {
+		struct vhost_iotlb_msg iotlb;
+		__u8 padding[64];
+	};
+};
+
 struct vhost_memory_region {
 	__u64 guest_phys_addr;
 	__u64 memory_size; /* bytes */
@@ -160,6 +170,14 @@ struct vhost_memory {
 #define VHOST_GET_VRING_BUSYLOOP_TIMEOUT _IOW(VHOST_VIRTIO, 0x24,	\
 					 struct vhost_vring_state)
 
+/* Set or get vhost backend capability */
+
+/* Use message type V2 */
+#define VHOST_BACKEND_F_IOTLB_MSG_V2 0x1
+
+#define VHOST_SET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x25, __u64)
+#define VHOST_GET_BACKEND_FEATURES _IOW(VHOST_VIRTIO, 0x26, __u64)
+
 /* VHOST_NET specific defines */
 
 /* Attach virtio net ring to a raw socket, or tap device.
-- 
cgit v1.2.3


From 9dae34978d83df06fc59aff5cf0d88ce41b80643 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Mon, 6 Aug 2018 11:57:02 +0800
Subject: net: avoid unnecessary sock_flag() check when enable timestamp

The sock_flag() check is alreay inside sock_enable_timestamp(), so it is
unnecessary checking it in the caller.

    void sock_enable_timestamp(struct sock *sk, int flag)
    {
        if (!sock_flag(sk, flag)) {
            ...
        }
    }

Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/compat.c    | 6 ++----
 net/core/sock.c | 8 ++++----
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/compat.c b/net/compat.c
index 7242cce5631b..3b2105f6549d 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -466,8 +466,7 @@ int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 
 	ctv = (struct compat_timeval __user *) userstamp;
 	err = -ENOENT;
-	if (!sock_flag(sk, SOCK_TIMESTAMP))
-		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
+	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	tv = ktime_to_timeval(sk->sk_stamp);
 	if (tv.tv_sec == -1)
 		return err;
@@ -494,8 +493,7 @@ int compat_sock_get_timestampns(struct sock *sk, struct timespec __user *usersta
 
 	ctv = (struct compat_timespec __user *) userstamp;
 	err = -ENOENT;
-	if (!sock_flag(sk, SOCK_TIMESTAMP))
-		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
+	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	ts = ktime_to_timespec(sk->sk_stamp);
 	if (ts.tv_sec == -1)
 		return err;
diff --git a/net/core/sock.c b/net/core/sock.c
index e31233f5ba39..3730eb855095 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2900,8 +2900,8 @@ EXPORT_SYMBOL(lock_sock_fast);
 int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
 {
 	struct timeval tv;
-	if (!sock_flag(sk, SOCK_TIMESTAMP))
-		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
+
+	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	tv = ktime_to_timeval(sk->sk_stamp);
 	if (tv.tv_sec == -1)
 		return -ENOENT;
@@ -2916,8 +2916,8 @@ EXPORT_SYMBOL(sock_get_timestamp);
 int sock_get_timestampns(struct sock *sk, struct timespec __user *userstamp)
 {
 	struct timespec ts;
-	if (!sock_flag(sk, SOCK_TIMESTAMP))
-		sock_enable_timestamp(sk, SOCK_TIMESTAMP);
+
+	sock_enable_timestamp(sk, SOCK_TIMESTAMP);
 	ts = ktime_to_timespec(sk->sk_stamp);
 	if (ts.tv_sec == -1)
 		return -ENOENT;
-- 
cgit v1.2.3


From 74c05a33cb02e75888771bc39e22e438195d6427 Mon Sep 17 00:00:00 2001
From: Yangbo Lu <yangbo.lu@nxp.com>
Date: Mon, 6 Aug 2018 12:39:11 +0800
Subject: ptp_qoriq: use div_u64/div_u64_rem for 64-bit division

This is a fix-up patch for below build issue with multi_v7_defconfig.

drivers/ptp/ptp_qoriq.o: In function `qoriq_ptp_probe':
ptp_qoriq.c:(.text+0xd0c): undefined reference to `__aeabi_uldivmod'

Fixes: 91305f281262 ("ptp_qoriq: support automatic configuration for ptp timer")
Signed-off-by: Yangbo Lu <yangbo.lu@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_qoriq.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/ptp/ptp_qoriq.c b/drivers/ptp/ptp_qoriq.c
index 095c18532dc7..fdd49c26bbcc 100644
--- a/drivers/ptp/ptp_qoriq.c
+++ b/drivers/ptp/ptp_qoriq.c
@@ -373,6 +373,7 @@ static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp,
 	u64 freq_comp;
 	u64 max_adj;
 	u32 nominal_freq;
+	u32 remainder = 0;
 	u32 clk_src = 0;
 
 	qoriq_ptp->cksel = DEFAULT_CKSEL;
@@ -400,7 +401,8 @@ static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp,
 	 * freq_ratio = reference_clock_freq / nominal_freq
 	 */
 	freq_comp = ((u64)1 << 32) * nominal_freq;
-	if (do_div(freq_comp, clk_src))
+	freq_comp = div_u64_rem(freq_comp, clk_src, &remainder);
+	if (remainder)
 		freq_comp++;
 
 	qoriq_ptp->tmr_add = freq_comp;
@@ -411,7 +413,7 @@ static int qoriq_ptp_auto_config(struct qoriq_ptp *qoriq_ptp,
 	 * freq_ratio = reference_clock_freq / nominal_freq
 	 */
 	max_adj = 1000000000ULL * (clk_src - nominal_freq);
-	max_adj = max_adj / nominal_freq - 1;
+	max_adj = div_u64(max_adj, nominal_freq) - 1;
 	qoriq_ptp->caps.max_adj = max_adj;
 
 	return 0;
-- 
cgit v1.2.3


From 656921a51244b72cd1105df61b0af15825bddb72 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Thu, 19 Jul 2018 17:31:55 -0700
Subject: drm/i915: Fix psr sink status report.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

First of all don't try to read dpcd if PSR is not even supported.

But also, if read failed return -EIO instead of reporting via a
backchannel.

v2: fix dev_priv: At this level m->private is the connector. (CI/DK)
    don't convert dpcd read errors to EIO. (DK)

Fixes: 5b7b30864d1d ("drm/i915/psr: Split sink status into a separate debugfs node")
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Dhinakaran Pandiyan <dhinakaran.pandiyan@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180720003155.16290-1-rodrigo.vivi@intel.com
(cherry picked from commit 7a72c78bdd0a1ea1d879610542679cc680398220)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index b3aefd623557..59dc0610ea44 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2606,13 +2606,22 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data)
 		"sink internal error",
 	};
 	struct drm_connector *connector = m->private;
+	struct drm_i915_private *dev_priv = to_i915(connector->dev);
 	struct intel_dp *intel_dp =
 		enc_to_intel_dp(&intel_attached_encoder(connector)->base);
+	int ret;
+
+	if (!CAN_PSR(dev_priv)) {
+		seq_puts(m, "PSR Unsupported\n");
+		return -ENODEV;
+	}
 
 	if (connector->status != connector_status_connected)
 		return -ENODEV;
 
-	if (drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val) == 1) {
+	ret = drm_dp_dpcd_readb(&intel_dp->aux, DP_PSR_STATUS, &val);
+
+	if (ret == 1) {
 		const char *str = "unknown";
 
 		val &= DP_PSR_SINK_STATE_MASK;
@@ -2620,7 +2629,7 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data)
 			str = sink_status[val];
 		seq_printf(m, "Sink PSR status: 0x%x [%s]\n", val, str);
 	} else {
-		DRM_ERROR("dpcd read (at %u) failed\n", DP_PSR_STATUS);
+		return ret;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 027063b1606fea6df15c270e5f2a072d1dfa8fef Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Tue, 31 Jul 2018 14:26:29 +0100
Subject: drm/i915: Interactive RPS mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

RPS provides a feedback loop where we use the load during the previous
evaluation interval to decide whether to up or down clock the GPU
frequency. Our responsiveness is split into 3 regimes, a high and low
plateau with the intent to keep the gpu clocked high to cover occasional
stalls under high load, and low despite occasional glitches under steady
low load, and inbetween. However, we run into situations like kodi where
we want to stay at low power (video decoding is done efficiently
inside the fixed function HW and doesn't need high clocks even for high
bitrate streams), but just occasionally the pipeline is more complex
than a video decode and we need a smidgen of extra GPU power to present
on time. In the high power regime, we sample at sub frame intervals with
a bias to upclocking, and conversely at low power we sample over a few
frames worth to provide what we consider to be the right levels of
responsiveness respectively. At low power, we more or less expect to be
kicked out to high power at the start of a busy sequence by waitboosting.

Prior to commit e9af4ea2b9e7 ("drm/i915: Avoid waitboosting on the active
request") whenever we missed the frame or stalled, we would immediate go
full throttle and upclock the GPU to max. But in commit e9af4ea2b9e7, we
relaxed the waitboosting to only apply if the pipeline was deep to avoid
over-committing resources for a near miss. Sadly though, a near miss is
still a miss, and perceptible as jitter in the frame delivery.

To try and prevent the near miss before having to resort to boosting
after the fact, we use the pageflip queue as an indication that we are
in an "interactive" regime and so should sample the load more frequently
to provide power before the frame misses it vblank. This will make us
more favorable to providing a small power increase (one or two bins) as
required rather than going all the way to maximum and then having to
work back down again. (We still keep the waitboosting mechanism around
just in case a dramatic change in system load requires urgent uplocking,
faster than we can provide in a few evaluation intervals.)

v2: Reduce rps_set_interactive to a boolean parameter to avoid the
confusion of what if they wanted a new power mode after pinning to a
different mode (which to choose?)
v3: Only reprogram RPS while the GT is awake, it will be set when we
wake the GT, and while off warns about being used outside of rpm.
v4: Fix deferred application of interactive mode
v5: s/state/interactive/
v6: Group the mutex with its principle in a substruct

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107111
Fixes: e9af4ea2b9e7 ("drm/i915: Avoid waitboosting on the active request")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Cc: Radoslaw Szwichtenberg <radoslaw.szwichtenberg@intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180731132629.3381-1-chris@chris-wilson.co.uk
(cherry picked from commit 60548c554be2830d29d2533dad0ac8133347ee51)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c  |  13 +++--
 drivers/gpu/drm/i915/i915_drv.h      |  16 ++++--
 drivers/gpu/drm/i915/i915_irq.c      |   4 +-
 drivers/gpu/drm/i915/intel_display.c |  20 +++++++
 drivers/gpu/drm/i915/intel_drv.h     |   2 +
 drivers/gpu/drm/i915/intel_pm.c      | 101 +++++++++++++++++++++++------------
 6 files changed, 111 insertions(+), 45 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 59dc0610ea44..f9ce35da4123 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -1218,7 +1218,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			   rpcurup, GT_PM_INTERVAL_TO_US(dev_priv, rpcurup));
 		seq_printf(m, "RP PREV UP: %d (%dus)\n",
 			   rpprevup, GT_PM_INTERVAL_TO_US(dev_priv, rpprevup));
-		seq_printf(m, "Up threshold: %d%%\n", rps->up_threshold);
+		seq_printf(m, "Up threshold: %d%%\n",
+			   rps->power.up_threshold);
 
 		seq_printf(m, "RP CUR DOWN EI: %d (%dus)\n",
 			   rpdownei, GT_PM_INTERVAL_TO_US(dev_priv, rpdownei));
@@ -1226,7 +1227,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 			   rpcurdown, GT_PM_INTERVAL_TO_US(dev_priv, rpcurdown));
 		seq_printf(m, "RP PREV DOWN: %d (%dus)\n",
 			   rpprevdown, GT_PM_INTERVAL_TO_US(dev_priv, rpprevdown));
-		seq_printf(m, "Down threshold: %d%%\n", rps->down_threshold);
+		seq_printf(m, "Down threshold: %d%%\n",
+			   rps->power.down_threshold);
 
 		max_freq = (IS_GEN9_LP(dev_priv) ? rp_state_cap >> 0 :
 			    rp_state_cap >> 16) & 0xff;
@@ -2218,6 +2220,7 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 	seq_printf(m, "CPU waiting? %d\n", count_irq_waiters(dev_priv));
 	seq_printf(m, "Boosts outstanding? %d\n",
 		   atomic_read(&rps->num_waiters));
+	seq_printf(m, "Interactive? %d\n", READ_ONCE(rps->power.interactive));
 	seq_printf(m, "Frequency requested %d\n",
 		   intel_gpu_freq(dev_priv, rps->cur_freq));
 	seq_printf(m, "  min hard:%d, soft:%d; max soft:%d, hard:%d\n",
@@ -2261,13 +2264,13 @@ static int i915_rps_boost_info(struct seq_file *m, void *data)
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 
 		seq_printf(m, "\nRPS Autotuning (current \"%s\" window):\n",
-			   rps_power_to_str(rps->power));
+			   rps_power_to_str(rps->power.mode));
 		seq_printf(m, "  Avg. up: %d%% [above threshold? %d%%]\n",
 			   rpup && rpupei ? 100 * rpup / rpupei : 0,
-			   rps->up_threshold);
+			   rps->power.up_threshold);
 		seq_printf(m, "  Avg. down: %d%% [below threshold? %d%%]\n",
 			   rpdown && rpdownei ? 100 * rpdown / rpdownei : 0,
-			   rps->down_threshold);
+			   rps->power.down_threshold);
 	} else {
 		seq_puts(m, "\nRPS Autotuning inactive\n");
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 0f49f9988dfa..4aca5344863d 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -779,11 +779,17 @@ struct intel_rps {
 	u8 rp0_freq;		/* Non-overclocked max frequency. */
 	u16 gpll_ref_freq;	/* vlv/chv GPLL reference frequency */
 
-	u8 up_threshold; /* Current %busy required to uplock */
-	u8 down_threshold; /* Current %busy required to downclock */
-
 	int last_adj;
-	enum { LOW_POWER, BETWEEN, HIGH_POWER } power;
+
+	struct {
+		struct mutex mutex;
+
+		enum { LOW_POWER, BETWEEN, HIGH_POWER } mode;
+		unsigned int interactive;
+
+		u8 up_threshold; /* Current %busy required to uplock */
+		u8 down_threshold; /* Current %busy required to downclock */
+	} power;
 
 	bool enabled;
 	atomic_t num_waiters;
@@ -3422,6 +3428,8 @@ extern void i915_redisable_vga_power_on(struct drm_i915_private *dev_priv);
 extern bool ironlake_set_drps(struct drm_i915_private *dev_priv, u8 val);
 extern void intel_init_pch_refclk(struct drm_i915_private *dev_priv);
 extern int intel_set_rps(struct drm_i915_private *dev_priv, u8 val);
+extern void intel_rps_mark_interactive(struct drm_i915_private *i915,
+				       bool interactive);
 extern bool intel_set_memory_cxsr(struct drm_i915_private *dev_priv,
 				  bool enable);
 
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 5dadefca2ad2..90628a47ae17 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1265,9 +1265,9 @@ static u32 vlv_wa_c0_ei(struct drm_i915_private *dev_priv, u32 pm_iir)
 		c0 = max(render, media);
 		c0 *= 1000 * 100 << 8; /* to usecs and scale to threshold% */
 
-		if (c0 > time * rps->up_threshold)
+		if (c0 > time * rps->power.up_threshold)
 			events = GEN6_PM_RP_UP_THRESHOLD;
-		else if (c0 < time * rps->down_threshold)
+		else if (c0 < time * rps->power.down_threshold)
 			events = GEN6_PM_RP_DOWN_THRESHOLD;
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 87e4cfbfd096..ed3fa1c8a983 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -13104,6 +13104,19 @@ intel_prepare_plane_fb(struct drm_plane *plane,
 		add_rps_boost_after_vblank(new_state->crtc, new_state->fence);
 	}
 
+	/*
+	 * We declare pageflips to be interactive and so merit a small bias
+	 * towards upclocking to deliver the frame on time. By only changing
+	 * the RPS thresholds to sample more regularly and aim for higher
+	 * clocks we can hopefully deliver low power workloads (like kodi)
+	 * that are not quite steady state without resorting to forcing
+	 * maximum clocks following a vblank miss (see do_rps_boost()).
+	 */
+	if (!intel_state->rps_interactive) {
+		intel_rps_mark_interactive(dev_priv, true);
+		intel_state->rps_interactive = true;
+	}
+
 	return 0;
 }
 
@@ -13120,8 +13133,15 @@ void
 intel_cleanup_plane_fb(struct drm_plane *plane,
 		       struct drm_plane_state *old_state)
 {
+	struct intel_atomic_state *intel_state =
+		to_intel_atomic_state(old_state->state);
 	struct drm_i915_private *dev_priv = to_i915(plane->dev);
 
+	if (intel_state->rps_interactive) {
+		intel_rps_mark_interactive(dev_priv, false);
+		intel_state->rps_interactive = false;
+	}
+
 	/* Should only be called after a successful intel_prepare_plane_fb()! */
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_plane_unpin_fb(to_intel_plane_state(old_state));
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index c275f91244a6..17af06d8a43e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -484,6 +484,8 @@ struct intel_atomic_state {
 	 */
 	bool skip_intermediate_wm;
 
+	bool rps_interactive;
+
 	/* Gen9+ only */
 	struct skl_ddb_values wm_results;
 
diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c
index 7312ecb73415..43ae9de12ba3 100644
--- a/drivers/gpu/drm/i915/intel_pm.c
+++ b/drivers/gpu/drm/i915/intel_pm.c
@@ -6264,42 +6264,15 @@ static u32 intel_rps_limits(struct drm_i915_private *dev_priv, u8 val)
 	return limits;
 }
 
-static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
+static void rps_set_power(struct drm_i915_private *dev_priv, int new_power)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
-	int new_power;
 	u32 threshold_up = 0, threshold_down = 0; /* in % */
 	u32 ei_up = 0, ei_down = 0;
 
-	new_power = rps->power;
-	switch (rps->power) {
-	case LOW_POWER:
-		if (val > rps->efficient_freq + 1 &&
-		    val > rps->cur_freq)
-			new_power = BETWEEN;
-		break;
-
-	case BETWEEN:
-		if (val <= rps->efficient_freq &&
-		    val < rps->cur_freq)
-			new_power = LOW_POWER;
-		else if (val >= rps->rp0_freq &&
-			 val > rps->cur_freq)
-			new_power = HIGH_POWER;
-		break;
+	lockdep_assert_held(&rps->power.mutex);
 
-	case HIGH_POWER:
-		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
-		    val < rps->cur_freq)
-			new_power = BETWEEN;
-		break;
-	}
-	/* Max/min bins are special */
-	if (val <= rps->min_freq_softlimit)
-		new_power = LOW_POWER;
-	if (val >= rps->max_freq_softlimit)
-		new_power = HIGH_POWER;
-	if (new_power == rps->power)
+	if (new_power == rps->power.mode)
 		return;
 
 	/* Note the units here are not exactly 1us, but 1280ns. */
@@ -6362,12 +6335,71 @@ static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
 		   GEN6_RP_DOWN_IDLE_AVG);
 
 skip_hw_write:
-	rps->power = new_power;
-	rps->up_threshold = threshold_up;
-	rps->down_threshold = threshold_down;
+	rps->power.mode = new_power;
+	rps->power.up_threshold = threshold_up;
+	rps->power.down_threshold = threshold_down;
+}
+
+static void gen6_set_rps_thresholds(struct drm_i915_private *dev_priv, u8 val)
+{
+	struct intel_rps *rps = &dev_priv->gt_pm.rps;
+	int new_power;
+
+	new_power = rps->power.mode;
+	switch (rps->power.mode) {
+	case LOW_POWER:
+		if (val > rps->efficient_freq + 1 &&
+		    val > rps->cur_freq)
+			new_power = BETWEEN;
+		break;
+
+	case BETWEEN:
+		if (val <= rps->efficient_freq &&
+		    val < rps->cur_freq)
+			new_power = LOW_POWER;
+		else if (val >= rps->rp0_freq &&
+			 val > rps->cur_freq)
+			new_power = HIGH_POWER;
+		break;
+
+	case HIGH_POWER:
+		if (val < (rps->rp1_freq + rps->rp0_freq) >> 1 &&
+		    val < rps->cur_freq)
+			new_power = BETWEEN;
+		break;
+	}
+	/* Max/min bins are special */
+	if (val <= rps->min_freq_softlimit)
+		new_power = LOW_POWER;
+	if (val >= rps->max_freq_softlimit)
+		new_power = HIGH_POWER;
+
+	mutex_lock(&rps->power.mutex);
+	if (rps->power.interactive)
+		new_power = HIGH_POWER;
+	rps_set_power(dev_priv, new_power);
+	mutex_unlock(&rps->power.mutex);
 	rps->last_adj = 0;
 }
 
+void intel_rps_mark_interactive(struct drm_i915_private *i915, bool interactive)
+{
+	struct intel_rps *rps = &i915->gt_pm.rps;
+
+	if (INTEL_GEN(i915) < 6)
+		return;
+
+	mutex_lock(&rps->power.mutex);
+	if (interactive) {
+		if (!rps->power.interactive++ && READ_ONCE(i915->gt.awake))
+			rps_set_power(i915, HIGH_POWER);
+	} else {
+		GEM_BUG_ON(!rps->power.interactive);
+		rps->power.interactive--;
+	}
+	mutex_unlock(&rps->power.mutex);
+}
+
 static u32 gen6_rps_pm_mask(struct drm_i915_private *dev_priv, u8 val)
 {
 	struct intel_rps *rps = &dev_priv->gt_pm.rps;
@@ -6780,7 +6812,7 @@ static void reset_rps(struct drm_i915_private *dev_priv,
 	u8 freq = rps->cur_freq;
 
 	/* force a reset */
-	rps->power = -1;
+	rps->power.mode = -1;
 	rps->cur_freq = -1;
 
 	if (set(dev_priv, freq))
@@ -9604,6 +9636,7 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val)
 void intel_pm_setup(struct drm_i915_private *dev_priv)
 {
 	mutex_init(&dev_priv->pcu_lock);
+	mutex_init(&dev_priv->gt_pm.rps.power.mutex);
 
 	atomic_set(&dev_priv->gt_pm.rps.num_waiters, 0);
 
-- 
cgit v1.2.3


From 497bfb706844892d07495f2ed5dff977fede5e25 Mon Sep 17 00:00:00 2001
From: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Date: Mon, 30 Jul 2018 15:06:36 +0300
Subject: Revert "drm/i915/icl: WaEnableFloatBlendOptimization"

The register for 0xe420 is unable to hold any value, including
this bit. The documentation is also mixed between having a
register bit for toggle and having a state command setup
for it. Apparently the register toggle is deprecated.

Remove the register toggle as evidence shows it's futile.

The thing remaining is an apology and humble request for
Mesa folks to resurrect their state setup for this as they
were on right track from start.

This reverts commit 0bf059f3532bb39c52d917142206a8554fc2f1c5.

Fixes: 0bf059f3532b ("drm/i915/icl: WaEnableFloatBlendOptimization")
References: HSDES#1406393558
Cc: Oscar Mateo <oscar.mateo@intel.com>
Cc: Anuj Phogat <anuj.phogat@gmail.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Acked-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20180730120636.26958-1-mika.kuoppala@linux.intel.com
(cherry picked from commit c358514ba8da9e235876db1628cedd19a35803c6)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/i915_reg.h          | 3 ---
 drivers/gpu/drm/i915/intel_workarounds.c | 3 ---
 2 files changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 8af945d8a995..91e7483228e1 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -2780,9 +2780,6 @@ enum i915_power_well_id {
 #define   GEN8_4x4_STC_OPTIMIZATION_DISABLE	(1 << 6)
 #define   GEN9_PARTIAL_RESOLVE_IN_VC_DISABLE	(1 << 1)
 
-#define GEN10_CACHE_MODE_SS			_MMIO(0xe420)
-#define   FLOAT_BLEND_OPTIMIZATION_ENABLE	(1 << 4)
-
 #define GEN6_BLITTER_ECOSKPD	_MMIO(0x221d0)
 #define   GEN6_BLITTER_LOCK_SHIFT			16
 #define   GEN6_BLITTER_FBC_NOTIFY			(1 << 3)
diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c
index f8bb32e974f6..4bcdeaf8d98f 100644
--- a/drivers/gpu/drm/i915/intel_workarounds.c
+++ b/drivers/gpu/drm/i915/intel_workarounds.c
@@ -508,9 +508,6 @@ static int icl_ctx_workarounds_init(struct drm_i915_private *dev_priv)
 		WA_SET_BIT_MASKED(GEN11_COMMON_SLICE_CHICKEN3,
 				  GEN11_BLEND_EMB_FIX_DISABLE_IN_RCC);
 
-	/* WaEnableFloatBlendOptimization:icl */
-	WA_SET_BIT_MASKED(GEN10_CACHE_MODE_SS, FLOAT_BLEND_OPTIMIZATION_ENABLE);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From 75eef0f1ed478284911b8723a5bdb659499a7aac Mon Sep 17 00:00:00 2001
From: Chris Wilson <chris@chris-wilson.co.uk>
Date: Thu, 2 Aug 2018 15:04:16 +0100
Subject: drm/i915/lpe: Mark LPE audio runtime pm as "no callbacks"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The LPE audio is a child device of i915, it is powered up and down
alongside the igfx and presents no independent runtime interface. This
aptly fulfils the description of a "No-Callback" Device, so mark it
thus.

Fixes: 183c00350ccd ("drm/i915: Fix runtime PM for LPE audio")
Testcase: igt/pm_rpm/basic-pci-d3-state
Testcase: igt/pm_rpm/basic-rte
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Takashi Iwai <tiwai@suse.de>
Cc: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180802140416.6062-1-chris@chris-wilson.co.uk
(cherry picked from commit 46e831abe864a6b59fa3de253a681c0f2ee1bf2f)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/intel_lpe_audio.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/intel_lpe_audio.c b/drivers/gpu/drm/i915/intel_lpe_audio.c
index 6269750e2b54..430732720e65 100644
--- a/drivers/gpu/drm/i915/intel_lpe_audio.c
+++ b/drivers/gpu/drm/i915/intel_lpe_audio.c
@@ -126,9 +126,7 @@ lpe_audio_platdev_create(struct drm_i915_private *dev_priv)
 		return platdev;
 	}
 
-	pm_runtime_forbid(&platdev->dev);
-	pm_runtime_set_active(&platdev->dev);
-	pm_runtime_enable(&platdev->dev);
+	pm_runtime_no_callbacks(&platdev->dev);
 
 	return platdev;
 }
-- 
cgit v1.2.3


From 544c05a60aef7de34ef60eebaf46582ca2bf05f9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Mon, 9 Jul 2018 17:53:09 -0500
Subject: vfio: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c     | 2 +-
 drivers/vfio/vfio_iommu_type1.c | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 125b58eff936..7fe2748ba101 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -789,7 +789,7 @@ static long vfio_pci_ioctl(void *device_data,
 		case VFIO_PCI_ERR_IRQ_INDEX:
 			if (pci_is_pcie(vdev->pdev))
 				break;
-		/* pass thru to return error */
+		/* fall through */
 		default:
 			return -EINVAL;
 		}
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 3e5b17710a4f..d9fd3188615d 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -1601,6 +1601,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
 		break;
 	case VFIO_TYPE1_NESTING_IOMMU:
 		iommu->nesting = true;
+		/* fall through */
 	case VFIO_TYPE1v2_IOMMU:
 		iommu->v2 = true;
 		break;
-- 
cgit v1.2.3


From 0dd0e297f0ec780b6b3484ba38b27d18c8ca7af9 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Thu, 12 Jul 2018 16:33:04 -0600
Subject: vfio-pci: Disable binding to PFs with SR-IOV enabled

We expect to receive PFs with SR-IOV disabled, however some host
drivers leave SR-IOV enabled at unbind.  This puts us in a state where
we can potentially assign both the PF and the VF, leading to both
functionality as well as security concerns due to lack of managing the
SR-IOV state as well as vendor dependent isolation from the PF to VF.
If we were to attempt to actively disable SR-IOV on driver probe, we
risk VF bound drivers blocking, potentially risking live lock
scenarios.  Therefore simply refuse to bind to PFs with SR-IOV enabled
with a warning message indicating the issue.  Users can resolve this
by re-binding to the host driver and disabling SR-IOV before
attempting to use the device with vfio-pci.

Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/pci/vfio_pci.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 7fe2748ba101..9979d3ba9e52 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -1193,6 +1193,19 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (pdev->hdr_type != PCI_HEADER_TYPE_NORMAL)
 		return -EINVAL;
 
+	/*
+	 * Prevent binding to PFs with VFs enabled, this too easily allows
+	 * userspace instance with VFs and PFs from the same device, which
+	 * cannot work.  Disabling SR-IOV here would initiate removing the
+	 * VFs, which would unbind the driver, which is prone to blocking
+	 * if that VF is also in use by vfio-pci.  Just reject these PFs
+	 * and let the user sort it out.
+	 */
+	if (pci_num_vf(pdev)) {
+		pci_warn(pdev, "Cannot bind to PF with SR-IOV enabled\n");
+		return -EBUSY;
+	}
+
 	group = vfio_iommu_group_get(&pdev->dev);
 	if (!group)
 		return -EINVAL;
-- 
cgit v1.2.3


From e4cc5a1873ac1297615962185f94adbbfaf6456b Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Mon, 6 Aug 2018 17:58:40 +0200
Subject: Bluetooth: btqca: Introduce HCI_EV_VENDOR and use it

Using HCI_VENDOR_PKT for vendor specific events does work since it has
also the value 0xff, but it is actually the packet type indicator
constant and not the event constant. So introduce HCI_EV_VENDOR and
use it.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 drivers/bluetooth/btqca.c   | 6 +++---
 include/net/bluetooth/hci.h | 2 ++
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 488f5e7521dd..ec9e03a6b778 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -39,7 +39,7 @@ int qca_read_soc_version(struct hci_dev *hdev, u32 *soc_version)
 
 	cmd = EDL_PATCH_VER_REQ_CMD;
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, EDL_PATCH_CMD_LEN,
-				&cmd, HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+				&cmd, HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		bt_dev_err(hdev, "Reading QCA version information failed (%d)",
@@ -229,7 +229,7 @@ static int qca_tlv_send_segment(struct hci_dev *hdev, int seg_size,
 				      cmd);
 
 	skb = __hci_cmd_sync_ev(hdev, EDL_PATCH_CMD_OPCODE, seg_size + 2, cmd,
-				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+				HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		bt_dev_err(hdev, "QCA Failed to send TLV segment (%d)", err);
@@ -318,7 +318,7 @@ int qca_set_bdaddr_rome(struct hci_dev *hdev, const bdaddr_t *bdaddr)
 	cmd[2] = sizeof(bdaddr_t);	/* size */
 	memcpy(cmd + 3, bdaddr, sizeof(bdaddr_t));
 	skb = __hci_cmd_sync_ev(hdev, EDL_NVM_ACCESS_OPCODE, sizeof(cmd), cmd,
-				HCI_VENDOR_PKT, HCI_INIT_TIMEOUT);
+				HCI_EV_VENDOR, HCI_INIT_TIMEOUT);
 	if (IS_ERR(skb)) {
 		err = PTR_ERR(skb);
 		bt_dev_err(hdev, "QCA Change address command failed (%d)", err);
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 7f008097552e..4619a79b1bbb 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -2176,6 +2176,8 @@ struct hci_evt_le_ext_adv_set_term {
 	__u8	num_evts;
 } __packed;
 
+#define HCI_EV_VENDOR			0xff
+
 /* Internal events generated by Bluetooth stack */
 #define HCI_EV_STACK_INTERNAL	0xfd
 struct hci_ev_stack_internal {
-- 
cgit v1.2.3


From 3237c0dbe21f8d2ca2feaa3891aff3619873cd30 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Thu, 12 Jul 2018 17:53:30 +0200
Subject: drm/i915/kvmgt: Fix compilation error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

gvt_pin_guest_page extracted some of the gvt_dma_map_page functionality:
commit 79e542f5af79 ("drm/i915/kvmgt: Support setting dma map for huge pages")

And yet, part of it was reintroduced in:
commit 39b4cbadb9a9 ("drm/i915/kvmgt: Check the pfn got from vfio_pin_pages")

Causing kvmgt part to no longer build. Let's remove it.

Reported-by: Tomasz Lis <tomasz.lis@intel.com>
Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Zhenyu Wang <zhenyuw@linux.intel.com>
Acked-by: Zhenyu Wang <zhenyuw@linux.intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180712155330.32055-1-michal.winiarski@intel.com
(cherry picked from commit 4eaf317a60fbea0555b936035002ca9bd9b9105d)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gvt/kvmgt.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index 718ab307a500..4d2f53ae9f0f 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -185,12 +185,6 @@ static int gvt_dma_map_page(struct intel_vgpu *vgpu, unsigned long gfn,
 	if (ret)
 		return ret;
 
-	if (!pfn_valid(pfn)) {
-		gvt_vgpu_err("pfn 0x%lx is not mem backed\n", pfn);
-		vfio_unpin_pages(mdev_dev(vgpu->vdev.mdev), &gfn, 1);
-		return -EINVAL;
-	}
-
 	/* Setup DMA mapping. */
 	*dma_addr = dma_map_page(dev, page, 0, size, PCI_DMA_BIDIRECTIONAL);
 	ret = dma_mapping_error(dev, *dma_addr);
-- 
cgit v1.2.3


From c40a56a7818cfe735fc93a69e1875f8bba834483 Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Thu, 2 Aug 2018 15:58:31 -0700
Subject: x86/mm/init: Remove freed kernel image areas from alias mapping

The kernel image is mapped into two places in the virtual address space
(addresses without KASLR, of course):

	1. The kernel direct map (0xffff880000000000)
	2. The "high kernel map" (0xffffffff81000000)

We actually execute out of #2.  If we get the address of a kernel symbol,
it points to #2, but almost all physical-to-virtual translations point to

Parts of the "high kernel map" alias are mapped in the userspace page
tables with the Global bit for performance reasons.  The parts that we map
to userspace do not (er, should not) have secrets. When PTI is enabled then
the global bit is usually not set in the high mapping and just used to
compensate for poor performance on systems which lack PCID.

This is fine, except that some areas in the kernel image that are adjacent
to the non-secret-containing areas are unused holes.  We free these holes
back into the normal page allocator and reuse them as normal kernel memory.
The memory will, of course, get *used* via the normal map, but the alias
mapping is kept.

This otherwise unused alias mapping of the holes will, by default keep the
Global bit, be mapped out to userspace, and be vulnerable to Meltdown.

Remove the alias mapping of these pages entirely.  This is likely to
fracture the 2M page mapping the kernel image near these areas, but this
should affect a minority of the area.

The pageattr code changes *all* aliases mapping the physical pages that it
operates on (by default).  We only want to modify a single alias, so we
need to tweak its behavior.

This unmapping behavior is currently dependent on PTI being in place.
Going forward, we should at least consider doing this for all
configurations.  Having an extra read-write alias for memory is not exactly
ideal for debugging things like random memory corruption and this does
undercut features like DEBUG_PAGEALLOC or future work like eXclusive Page
Frame Ownership (XPFO).

Before this patch:

current_kernel:---[ High Kernel Mapping ]---
current_kernel-0xffffffff80000000-0xffffffff81000000          16M                               pmd
current_kernel-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
current_kernel-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
current_kernel-0xffffffff81e11000-0xffffffff82000000        1980K     RW                     NX pte
current_kernel-0xffffffff82000000-0xffffffff82600000           6M     ro         PSE     GLB NX pmd
current_kernel-0xffffffff82600000-0xffffffff82c00000           6M     RW         PSE         NX pmd
current_kernel-0xffffffff82c00000-0xffffffff82e00000           2M     RW                     NX pte
current_kernel-0xffffffff82e00000-0xffffffff83200000           4M     RW         PSE         NX pmd
current_kernel-0xffffffff83200000-0xffffffffa0000000         462M                               pmd

  current_user:---[ High Kernel Mapping ]---
  current_user-0xffffffff80000000-0xffffffff81000000          16M                               pmd
  current_user-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
  current_user-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
  current_user-0xffffffff81e11000-0xffffffff82000000        1980K     RW                     NX pte
  current_user-0xffffffff82000000-0xffffffff82600000           6M     ro         PSE     GLB NX pmd
  current_user-0xffffffff82600000-0xffffffffa0000000         474M                               pmd

After this patch:

current_kernel:---[ High Kernel Mapping ]---
current_kernel-0xffffffff80000000-0xffffffff81000000          16M                               pmd
current_kernel-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
current_kernel-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
current_kernel-0xffffffff81e11000-0xffffffff82000000        1980K                               pte
current_kernel-0xffffffff82000000-0xffffffff82400000           4M     ro         PSE     GLB NX pmd
current_kernel-0xffffffff82400000-0xffffffff82488000         544K     ro                     NX pte
current_kernel-0xffffffff82488000-0xffffffff82600000        1504K                               pte
current_kernel-0xffffffff82600000-0xffffffff82c00000           6M     RW         PSE         NX pmd
current_kernel-0xffffffff82c00000-0xffffffff82c0d000          52K     RW                     NX pte
current_kernel-0xffffffff82c0d000-0xffffffff82dc0000        1740K                               pte

  current_user:---[ High Kernel Mapping ]---
  current_user-0xffffffff80000000-0xffffffff81000000          16M                               pmd
  current_user-0xffffffff81000000-0xffffffff81e00000          14M     ro         PSE     GLB x  pmd
  current_user-0xffffffff81e00000-0xffffffff81e11000          68K     ro                 GLB x  pte
  current_user-0xffffffff81e11000-0xffffffff82000000        1980K                               pte
  current_user-0xffffffff82000000-0xffffffff82400000           4M     ro         PSE     GLB NX pmd
  current_user-0xffffffff82400000-0xffffffff82488000         544K     ro                     NX pte
  current_user-0xffffffff82488000-0xffffffff82600000        1504K                               pte
  current_user-0xffffffff82600000-0xffffffffa0000000         474M                               pmd

[ tglx: Do not unmap on 32bit as there is only one mapping ]

Fixes: 0f561fce4d69 ("x86/pti: Enable global pages for shared areas")
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Kees Cook <keescook@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Joerg Roedel <jroedel@suse.de>
Link: https://lkml.kernel.org/r/20180802225831.5F6A2BFC@viggo.jf.intel.com
---
 arch/x86/include/asm/set_memory.h |  1 +
 arch/x86/mm/init.c                | 26 ++++++++++++++++++++++++--
 arch/x86/mm/pageattr.c            | 13 +++++++++++++
 3 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index bd090367236c..34cffcef7375 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -46,6 +46,7 @@ int set_memory_np(unsigned long addr, int numpages);
 int set_memory_4k(unsigned long addr, int numpages);
 int set_memory_encrypted(unsigned long addr, int numpages);
 int set_memory_decrypted(unsigned long addr, int numpages);
+int set_memory_np_noalias(unsigned long addr, int numpages);
 
 int set_memory_array_uc(unsigned long *addr, int addrinarray);
 int set_memory_array_wc(unsigned long *addr, int addrinarray);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index bc11dedffc45..74b157ac078d 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -780,8 +780,30 @@ void free_init_pages(char *what, unsigned long begin, unsigned long end)
  */
 void free_kernel_image_pages(void *begin, void *end)
 {
-	free_init_pages("unused kernel image",
-			(unsigned long)begin, (unsigned long)end);
+	unsigned long begin_ul = (unsigned long)begin;
+	unsigned long end_ul = (unsigned long)end;
+	unsigned long len_pages = (end_ul - begin_ul) >> PAGE_SHIFT;
+
+
+	free_init_pages("unused kernel image", begin_ul, end_ul);
+
+	/*
+	 * PTI maps some of the kernel into userspace.  For performance,
+	 * this includes some kernel areas that do not contain secrets.
+	 * Those areas might be adjacent to the parts of the kernel image
+	 * being freed, which may contain secrets.  Remove the "high kernel
+	 * image mapping" for these freed areas, ensuring they are not even
+	 * potentially vulnerable to Meltdown regardless of the specific
+	 * optimizations PTI is currently using.
+	 *
+	 * The "noalias" prevents unmapping the direct map alias which is
+	 * needed to access the freed pages.
+	 *
+	 * This is only valid for 64bit kernels. 32bit has only one mapping
+	 * which can't be treated in this way for obvious reasons.
+	 */
+	if (IS_ENABLED(CONFIG_X86_64) && cpu_feature_enabled(X86_FEATURE_PTI))
+		set_memory_np_noalias(begin_ul, len_pages);
 }
 
 void __ref free_initmem(void)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index c04153796f61..0a74996a1149 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -53,6 +53,7 @@ static DEFINE_SPINLOCK(cpa_lock);
 #define CPA_FLUSHTLB 1
 #define CPA_ARRAY 2
 #define CPA_PAGES_ARRAY 4
+#define CPA_NO_CHECK_ALIAS 8 /* Do not search for aliases */
 
 #ifdef CONFIG_PROC_FS
 static unsigned long direct_pages_count[PG_LEVEL_NUM];
@@ -1486,6 +1487,9 @@ static int change_page_attr_set_clr(unsigned long *addr, int numpages,
 
 	/* No alias checking for _NX bit modifications */
 	checkalias = (pgprot_val(mask_set) | pgprot_val(mask_clr)) != _PAGE_NX;
+	/* Has caller explicitly disabled alias checking? */
+	if (in_flag & CPA_NO_CHECK_ALIAS)
+		checkalias = 0;
 
 	ret = __change_page_attr_set_clr(&cpa, checkalias);
 
@@ -1772,6 +1776,15 @@ int set_memory_np(unsigned long addr, int numpages)
 	return change_page_attr_clear(&addr, numpages, __pgprot(_PAGE_PRESENT), 0);
 }
 
+int set_memory_np_noalias(unsigned long addr, int numpages)
+{
+	int cpa_flags = CPA_NO_CHECK_ALIAS;
+
+	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
+					__pgprot(_PAGE_PRESENT), 0,
+					cpa_flags, NULL);
+}
+
 int set_memory_4k(unsigned long addr, int numpages)
 {
 	return change_page_attr_set_clr(&addr, numpages, __pgprot(0),
-- 
cgit v1.2.3


From 36131ce9a0b23ed6feb04f8a3ffaa44b804abd5e Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 6 Aug 2018 14:30:34 -0500
Subject: PCI/ASPM: Convert to use sysfs_match_string() helper

The sysfs_match_string() helper returns index of the matching string in an
array.  Use it in pcie_aspm_set_policy() to simplify the code.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
[bhelgaas: squash sysfs_match_string() fix into original patch for issue
Reported-by: Heiner Kallweit <hkallweit1@gmail.com>]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aspm.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index c687c817b47d..5326916715d2 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1127,11 +1127,9 @@ static int pcie_aspm_set_policy(const char *val,
 
 	if (aspm_disabled)
 		return -EPERM;
-	for (i = 0; i < ARRAY_SIZE(policy_str); i++)
-		if (!strncmp(val, policy_str[i], strlen(policy_str[i])))
-			break;
-	if (i >= ARRAY_SIZE(policy_str))
-		return -EINVAL;
+	i = sysfs_match_string(policy_str, val);
+	if (i < 0)
+		return i;
 	if (i == aspm_policy)
 		return 0;
 
-- 
cgit v1.2.3


From f5ddcf71e66eac681500ab94df0f9e33c4f2b4a7 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 25 Jul 2018 14:53:40 -0500
Subject: igb: Remove unnecessary include of <linux/pci-aspm.h>

The igb driver doesn't need anything provided by pci-aspm.h, so remove
the unnecessary include of it.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Acked-by: Alexander Duyck <alexander.h.duyck@intel.com>
Acked-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index f707709969ac..c77fda05f683 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -22,7 +22,6 @@
 #include <linux/if.h>
 #include <linux/if_vlan.h>
 #include <linux/pci.h>
-#include <linux/pci-aspm.h>
 #include <linux/delay.h>
 #include <linux/interrupt.h>
 #include <linux/ip.h>
-- 
cgit v1.2.3


From a78613c08267107e3ffaa40290a269be79386fce Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 25 Jul 2018 14:53:40 -0500
Subject: ath9k: Remove unnecessary include of <linux/pci-aspm.h>

The ath9k driver doesn't need anything provided by pci-aspm.h, so remove
the unnecessary include of it.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Acked-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/ath/ath9k/pci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/pci.c b/drivers/net/wireless/ath/ath9k/pci.c
index 645f0fbd9179..92b2dd396436 100644
--- a/drivers/net/wireless/ath/ath9k/pci.c
+++ b/drivers/net/wireless/ath/ath9k/pci.c
@@ -18,7 +18,6 @@
 
 #include <linux/nl80211.h>
 #include <linux/pci.h>
-#include <linux/pci-aspm.h>
 #include <linux/module.h>
 #include "ath9k.h"
 
-- 
cgit v1.2.3


From 2b2654b8922a46aeabc9bf13e0361a96110317e7 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 25 Jul 2018 14:53:41 -0500
Subject: iwlwifi: Remove unnecessary include of <linux/pci-aspm.h>

This part of the iwlwifi driver doesn't need anything provided by
pci-aspm.h, so remove the unnecessary include of it.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
Acked-by: Luca Coelho <luciano.coelho@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 38234bda9017..d6c55e111fda 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -72,7 +72,6 @@
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/pci.h>
-#include <linux/pci-aspm.h>
 #include <linux/acpi.h>
 
 #include "fw/acpi.h"
-- 
cgit v1.2.3


From ce29af2a505627cc8f1deddb84bcbaf186b0bfd5 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Wed, 25 Jul 2018 14:53:42 -0500
Subject: PCI: Remove unnecessary include of <linux/pci-aspm.h>

Several PCI core files include pci-aspm.h even though they don't need
anything provided by that file.  Remove the unnecessary includes of it.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Sinan Kaya <okaya@kernel.org>
---
 drivers/pci/pci-sysfs.c | 1 -
 drivers/pci/pci.c       | 1 -
 drivers/pci/probe.c     | 1 -
 drivers/pci/remove.c    | 1 -
 4 files changed, 4 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 0c4653c1d2ce..91337faae60d 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -23,7 +23,6 @@
 #include <linux/fs.h>
 #include <linux/capability.h>
 #include <linux/security.h>
-#include <linux/pci-aspm.h>
 #include <linux/slab.h>
 #include <linux/vgaarb.h>
 #include <linux/pm_runtime.h>
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..d92d216e4f64 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -23,7 +23,6 @@
 #include <linux/string.h>
 #include <linux/log2.h>
 #include <linux/logic_pio.h>
-#include <linux/pci-aspm.h>
 #include <linux/pm_wakeup.h>
 #include <linux/interrupt.h>
 #include <linux/device.h>
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index ac876e32de4b..1ed2852dee21 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -13,7 +13,6 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
-#include <linux/pci-aspm.h>
 #include <linux/aer.h>
 #include <linux/acpi.h>
 #include <linux/hypervisor.h>
diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c
index 6f072eae4f7a..01ec7fcb5634 100644
--- a/drivers/pci/remove.c
+++ b/drivers/pci/remove.c
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/pci.h>
 #include <linux/module.h>
-#include <linux/pci-aspm.h>
 #include "pci.h"
 
 static void pci_free_resources(struct pci_dev *dev)
-- 
cgit v1.2.3


From e11d41472a50742c16d53c968e143fb498fa482f Mon Sep 17 00:00:00 2001
From: "Leo (Sunpeng) Li" <sunpeng.li@amd.com>
Date: Thu, 19 Jul 2018 08:22:16 -0400
Subject: drm/amd/display: Use requested HDMI aspect ratio

[Why]
The DRM mode's HDMI picture aspect ratio field was never saved in
dc_stream's timing struct. This causes us to mistake a new stream to
have the same timings as the old, even though the user has requested a
different aspect ratio.

[How]
Save DRM's aspect ratio field within dc_stream's timing struct.

Bug: https://bugs.freedesktop.org/show_bug.cgi?id=107153
Signed-off-by: Leo (Sunpeng) Li <sunpeng.li@amd.com>
Reviewed-by: Mikita Lipski <Mikita.Lipski@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 45e062022461..c1631d61336e 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -2109,13 +2109,8 @@ convert_color_depth_from_display_info(const struct drm_connector *connector)
 static enum dc_aspect_ratio
 get_aspect_ratio(const struct drm_display_mode *mode_in)
 {
-	int32_t width = mode_in->crtc_hdisplay * 9;
-	int32_t height = mode_in->crtc_vdisplay * 16;
-
-	if ((width - height) < 10 && (width - height) > -10)
-		return ASPECT_RATIO_16_9;
-	else
-		return ASPECT_RATIO_4_3;
+	/* 1-1 mapping, since both enums follow the HDMI spec. */
+	return (enum dc_aspect_ratio) mode_in->picture_aspect_ratio;
 }
 
 static enum dc_color_space
-- 
cgit v1.2.3


From 0301ccbaf67d3d9aea97156c5eb85233bb5a5178 Mon Sep 17 00:00:00 2001
From: abdoulaye berthe <abdoulaye.berthe@amd.com>
Date: Thu, 19 Jul 2018 15:39:55 -0400
Subject: drm/amd/display: DP Compliance 400.1.1 failure

[Why]
400.1.1 is failing because we are not performing link training when
we get an HPD pulse for the same display. This is breaking DP
compliance

[How]
Always perform link training after HPD pulse if the detection
reason is not  DETECT_REASON_HPDRX.

Signed-off-by: abdoulaye berthe <abdoulaye.berthe@amd.com>
Reviewed-by: Wenjing Liu <Wenjing.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 54 ++++++++++++++-------------
 1 file changed, 28 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 89d7c1e99168..ce65b4d5062e 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -764,39 +764,41 @@ bool dc_link_detect(struct dc_link *link, enum dc_detect_reason reason)
 		if ((prev_sink != NULL) && ((edid_status == EDID_THE_SAME) || (edid_status == EDID_OK)))
 			same_edid = is_same_edid(&prev_sink->dc_edid, &sink->dc_edid);
 
-		// If both edid and dpcd are the same, then discard new sink and revert back to original sink
-		if ((same_edid) && (same_dpcd)) {
-			link_disconnect_remap(prev_sink, link);
-			sink = prev_sink;
-			prev_sink = NULL;
-		} else {
-			if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
-					sink_caps.transaction_type ==
-						DDC_TRANSACTION_TYPE_I2C_OVER_AUX) {
-				/*
-				 * TODO debug why Dell 2413 doesn't like
-				 *  two link trainings
-				 */
+		if (link->connector_signal == SIGNAL_TYPE_DISPLAY_PORT &&
+			sink_caps.transaction_type == DDC_TRANSACTION_TYPE_I2C_OVER_AUX &&
+			reason != DETECT_REASON_HPDRX) {
+			/*
+			 * TODO debug why Dell 2413 doesn't like
+			 *  two link trainings
+			 */
 
-				/* deal with non-mst cases */
-				for (i = 0; i < LINK_TRAINING_MAX_VERIFY_RETRY; i++) {
-					int fail_count = 0;
+			/* deal with non-mst cases */
+			for (i = 0; i < LINK_TRAINING_MAX_VERIFY_RETRY; i++) {
+				int fail_count = 0;
 
-					dp_verify_link_cap(link,
-							  &link->reported_link_cap,
-							  &fail_count);
+				dp_verify_link_cap(link,
+						  &link->reported_link_cap,
+						  &fail_count);
 
-					if (fail_count == 0)
-						break;
-				}
+				if (fail_count == 0)
+					break;
 			}
 
-			/* HDMI-DVI Dongle */
-			if (sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A &&
-					!sink->edid_caps.edid_hdmi)
-				sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
+		} else {
+			// If edid is the same, then discard new sink and revert back to original sink
+			if (same_edid) {
+				link_disconnect_remap(prev_sink, link);
+				sink = prev_sink;
+				prev_sink = NULL;
+
+			}
 		}
 
+		/* HDMI-DVI Dongle */
+		if (sink->sink_signal == SIGNAL_TYPE_HDMI_TYPE_A &&
+				!sink->edid_caps.edid_hdmi)
+			sink->sink_signal = SIGNAL_TYPE_DVI_SINGLE_LINK;
+
 		/* Connectivity log: detection */
 		for (i = 0; i < sink->dc_edid.length / EDID_BLOCK_SIZE; i++) {
 			CONN_DATA_DETECT(link,
-- 
cgit v1.2.3


From 620a0d27b211aa03d3f99accfdd58b88e6e0504c Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Thu, 19 Jul 2018 11:25:05 -0400
Subject: drm/amd/display: Implement backlight_ops.get_brightness

[Why]
This hook that is supposed to read the actual backlight value
is used in a few places throughout the kernel to setup or force
update on backlight

[How]
Create a dc function that calls the existing abm function, and
call that function from amdgpu

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 ++++++-
 drivers/gpu/drm/amd/display/dc/core/dc_link.c     | 9 +++++++++
 drivers/gpu/drm/amd/display/dc/dc_link.h          | 2 ++
 3 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index c1631d61336e..dcae658fbc50 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1320,7 +1320,12 @@ static int amdgpu_dm_backlight_update_status(struct backlight_device *bd)
 
 static int amdgpu_dm_backlight_get_brightness(struct backlight_device *bd)
 {
-	return bd->props.brightness;
+	struct amdgpu_display_manager *dm = bl_get_data(bd);
+	int ret = dc_link_get_backlight_level(dm->backlight_link);
+
+	if (ret == DC_ERROR_UNEXPECTED)
+		return bd->props.brightness;
+	return ret;
 }
 
 static const struct backlight_ops amdgpu_dm_backlight_ops = {
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index ce65b4d5062e..9a6448e2089c 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -2026,6 +2026,15 @@ enum dc_status dc_link_validate_mode_timing(
 	return DC_OK;
 }
 
+int dc_link_get_backlight_level(const struct dc_link *link)
+{
+	struct abm *abm = link->ctx->dc->res_pool->abm;
+
+	if (abm == NULL || abm->funcs->get_current_backlight_8_bit == NULL)
+		return DC_ERROR_UNEXPECTED;
+
+	return (int) abm->funcs->get_current_backlight_8_bit(abm);
+}
 
 bool dc_link_set_backlight_level(const struct dc_link *link, uint32_t level,
 		uint32_t frame_ramp, const struct dc_stream_state *stream)
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 070a56926308..22f4ddd219d1 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -141,6 +141,8 @@ static inline struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_
 bool dc_link_set_backlight_level(const struct dc_link *dc_link, uint32_t level,
 		uint32_t frame_ramp, const struct dc_stream_state *stream);
 
+int dc_link_get_backlight_level(const struct dc_link *dc_link);
+
 bool dc_link_set_abm_disable(const struct dc_link *dc_link);
 
 bool dc_link_set_psr_enable(const struct dc_link *dc_link, bool enable, bool wait);
-- 
cgit v1.2.3


From 53a53f8687faf492df2644d8c18ff0217fc18730 Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Wed, 18 Jul 2018 16:03:30 -0400
Subject: drm/amd/display: Read back max backlight value at boot

[Why]
If there is no program explicitly setting the backlight
brightness (for example, during a minimal install of linux), the
hardware defaults to maximum brightness but the backlight_device
defaults to 0 value.  Thus, settings displays the wrong brightness
value.

[How]
When creating the backlight device, set brightness to max

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index dcae658fbc50..34f34823bab5 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1340,6 +1340,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_display_manager *dm)
 	struct backlight_properties props = { 0 };
 
 	props.max_brightness = AMDGPU_MAX_BL_LEVEL;
+	props.brightness = AMDGPU_MAX_BL_LEVEL;
 	props.type = BACKLIGHT_RAW;
 
 	snprintf(bl_name, sizeof(bl_name), "amdgpu_bl%d",
-- 
cgit v1.2.3


From d90e9a3bf5e747f0e3b0c8bec96d8699493f63ab Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Thu, 19 Jul 2018 15:48:24 -0400
Subject: drm/amd/display: Destroy aux_engines only once

[Why]
In the dce112 function to destroy the resource pool, engines
(the aux engines) is destroyed twice.  This has no ill effects
but is a tad redundant.

[How]
Remove the redundant call

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
index 84a05ff2d674..288129343c77 100644
--- a/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce112/dce112_resource.c
@@ -677,9 +677,6 @@ static void destruct(struct dce110_resource_pool *pool)
 			pool->base.timing_generators[i] = NULL;
 		}
 
-		if (pool->base.engines[i] != NULL)
-			dce110_engine_destroy(&pool->base.engines[i]);
-
 	}
 
 	for (i = 0; i < pool->base.stream_enc_count; i++) {
-- 
cgit v1.2.3


From 78e4405cec6cb0780b27b222685dde33934b38e4 Mon Sep 17 00:00:00 2001
From: David Francis <David.Francis@amd.com>
Date: Thu, 12 Jul 2018 15:46:41 -0400
Subject: drm/amd/display: Implement custom degamma lut on dcn

[Why]
Custom degamma lut functions are a feature we would
like to support on compatible hardware

[How]
In atomic check, convert from array of drm_color_lut to
dc_transfer_func.  On hardware commit, allow for possibility
of custom degamma.  Both are based on the equivalent
regamma pipeline.

Signed-off-by: David Francis <David.Francis@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_color.c    | 42 ++++++++++++++++------
 drivers/gpu/drm/amd/display/dc/dc_hw_types.h       |  2 ++
 .../drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c  |  7 ++--
 .../drm/amd/display/modules/color/color_gamma.c    | 10 ++++--
 4 files changed, 46 insertions(+), 15 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
index b329393307e5..326f6fb7e0bc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_color.c
@@ -231,18 +231,21 @@ void amdgpu_dm_set_ctm(struct dm_crtc_state *crtc)
  * preparation for hardware commit. If no lut is specified by user, we default
  * to SRGB degamma.
  *
- * Currently, we only support degamma bypass, or preprogrammed SRGB degamma.
- * Programmable degamma is not supported, and an attempt to do so will return
- * -EINVAL.
+ * We support degamma bypass, predefined SRGB, and custom degamma
  *
  * RETURNS:
- * 0 on success, -EINVAL if custom degamma curve is given.
+ * 0 on success
+ * -EINVAL if crtc_state has a degamma_lut of invalid size
+ * -ENOMEM if gamma allocation fails
  */
 int amdgpu_dm_set_degamma_lut(struct drm_crtc_state *crtc_state,
 			      struct dc_plane_state *dc_plane_state)
 {
 	struct drm_property_blob *blob = crtc_state->degamma_lut;
 	struct drm_color_lut *lut;
+	uint32_t lut_size;
+	struct dc_gamma *gamma;
+	bool ret;
 
 	if (!blob) {
 		/* Default to SRGB */
@@ -258,11 +261,30 @@ int amdgpu_dm_set_degamma_lut(struct drm_crtc_state *crtc_state,
 		return 0;
 	}
 
-	/* Otherwise, assume SRGB, since programmable degamma is not
-	 * supported.
-	 */
-	dc_plane_state->in_transfer_func->type = TF_TYPE_PREDEFINED;
-	dc_plane_state->in_transfer_func->tf = TRANSFER_FUNCTION_SRGB;
-	return -EINVAL;
+	gamma = dc_create_gamma();
+	if (!gamma)
+		return -ENOMEM;
+
+	lut_size = blob->length / sizeof(struct drm_color_lut);
+	gamma->num_entries = lut_size;
+	if (gamma->num_entries == MAX_COLOR_LUT_ENTRIES)
+		gamma->type = GAMMA_CUSTOM;
+	else {
+		dc_gamma_release(&gamma);
+		return -EINVAL;
+	}
+
+	__drm_lut_to_dc_gamma(lut, gamma, false);
+
+	dc_plane_state->in_transfer_func->type = TF_TYPE_DISTRIBUTED_POINTS;
+	ret = mod_color_calculate_degamma_params(dc_plane_state->in_transfer_func, gamma, true);
+	dc_gamma_release(&gamma);
+	if (!ret) {
+		dc_plane_state->in_transfer_func->type = TF_TYPE_BYPASS;
+		DRM_ERROR("Out of memory when calculating degamma params\n");
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
diff --git a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
index 1d1f2d5ece51..b789cb2b354b 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_hw_types.h
@@ -417,6 +417,7 @@ enum {
 	GAMMA_RGB_256_ENTRIES = 256,
 	GAMMA_RGB_FLOAT_1024_ENTRIES = 1024,
 	GAMMA_CS_TFM_1D_ENTRIES = 4096,
+	GAMMA_CUSTOM_ENTRIES = 4096,
 	GAMMA_MAX_ENTRIES = 4096
 };
 
@@ -424,6 +425,7 @@ enum dc_gamma_type {
 	GAMMA_RGB_256 = 1,
 	GAMMA_RGB_FLOAT_1024 = 2,
 	GAMMA_CS_TFM_1D = 3,
+	GAMMA_CUSTOM = 4,
 };
 
 struct dc_csc_transform {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index c87f6e603055..f5d8242eb047 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1213,8 +1213,11 @@ static bool dcn10_set_input_transfer_func(struct pipe_ctx *pipe_ctx,
 	} else if (tf->type == TF_TYPE_BYPASS) {
 		dpp_base->funcs->dpp_set_degamma(dpp_base, IPP_DEGAMMA_MODE_BYPASS);
 	} else {
-		/*TF_TYPE_DISTRIBUTED_POINTS*/
-		result = false;
+		cm_helper_translate_curve_to_degamma_hw_format(tf,
+					&dpp_base->degamma_params);
+		dpp_base->funcs->dpp_program_degamma_pwl(dpp_base,
+				&dpp_base->degamma_params);
+		result = true;
 	}
 
 	return result;
diff --git a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
index ee69c949bfbf..bf29733958c3 100644
--- a/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
+++ b/drivers/gpu/drm/amd/display/modules/color/color_gamma.c
@@ -997,7 +997,9 @@ static void scale_user_regamma_ramp(struct pwl_float_data *pwl_rgb,
  * norm_y = 4095*regamma_y, and index is just truncating to nearest integer
  * lut1 = lut1D[index], lut2 = lut1D[index+1]
  *
- *adjustedY is then linearly interpolating regamma Y between lut1 and lut2
+ * adjustedY is then linearly interpolating regamma Y between lut1 and lut2
+ *
+ * Custom degamma on Linux uses the same interpolation math, so is handled here
  */
 static void apply_lut_1d(
 		const struct dc_gamma *ramp,
@@ -1018,7 +1020,7 @@ static void apply_lut_1d(
 	struct fixed31_32 delta_lut;
 	struct fixed31_32 delta_index;
 
-	if (ramp->type != GAMMA_CS_TFM_1D)
+	if (ramp->type != GAMMA_CS_TFM_1D && ramp->type != GAMMA_CUSTOM)
 		return; // this is not expected
 
 	for (i = 0; i < num_hw_points; i++) {
@@ -1636,7 +1638,9 @@ bool mod_color_calculate_degamma_params(struct dc_transfer_func *input_tf,
 	map_regamma_hw_to_x_user(ramp, coeff, rgb_user,
 			coordinates_x, axix_x, curve,
 			MAX_HW_POINTS, tf_pts,
-			mapUserRamp);
+			mapUserRamp && ramp->type != GAMMA_CUSTOM);
+	if (ramp->type == GAMMA_CUSTOM)
+		apply_lut_1d(ramp, MAX_HW_POINTS, tf_pts);
 
 	ret = true;
 
-- 
cgit v1.2.3


From 5ae6fe572929587a304471bf4a641361a45152b5 Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Mon, 23 Jul 2018 14:13:23 -0400
Subject: drm/amd/display: Use calculated disp_clk_khz value for dce110

[Why]

The calculated values for actual disp_clk_khz were ignored when
notifying pplib of the new display requirements. In order to honor DFS
bypass clocks from the hardware, the calculated value should be used.

[How]

The return value for set_dispclk is now assigned back into new_clocks
and correctly carried through into dccg->clks.phyclk_khz. When notifying
pplib of new display requirements dccg->clks.phyclk_khz is used
instead of dce.dispclk_khz. The value of dce.dispclk_khz was never
explicitly set to anything before.

A 15% higher display clock value than calculated is no longer requested
for dce110 since it now makes use of the calculated value.

Since dce112 makes use of dce110's set_bandwidth but not its
update_clocks it needs to have the value correctly carried through.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Reviewed-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c             | 4 ++--
 drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index 0db8d1da3d0e..f17677971d0f 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -463,7 +463,7 @@ static void dce12_update_clocks(struct dccg *dccg,
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
 		clock_voltage_req.clk_type = DM_PP_CLOCK_TYPE_DISPLAY_CLK;
 		clock_voltage_req.clocks_in_khz = new_clocks->dispclk_khz;
-		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		new_clocks->dispclk_khz = dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
 		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
 
 		dm_pp_apply_clock_for_voltage_request(dccg->ctx, &clock_voltage_req);
@@ -661,7 +661,7 @@ static void dce_update_clocks(struct dccg *dccg,
 	}
 
 	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
-		dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
+		new_clocks->dispclk_khz = dccg->funcs->set_dispclk(dccg, new_clocks->dispclk_khz);
 		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
 	}
 }
diff --git a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
index 1149c413f6d2..1d98e3678b04 100644
--- a/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dce110/dce110_hw_sequencer.c
@@ -2530,7 +2530,7 @@ static void pplib_apply_display_requirements(
 	/* TODO: dce11.2*/
 	pp_display_cfg->avail_mclk_switch_time_in_disp_active_us = 0;
 
-	pp_display_cfg->disp_clk_khz = context->bw.dce.dispclk_khz;
+	pp_display_cfg->disp_clk_khz = dc->res_pool->dccg->clks.dispclk_khz;
 
 	dce110_fill_display_configs(context, pp_display_cfg);
 
@@ -2559,7 +2559,7 @@ void dce110_set_bandwidth(
 {
 	struct dc_clocks req_clks;
 
-	req_clks.dispclk_khz = context->bw.dce.dispclk_khz * 115 / 100;
+	req_clks.dispclk_khz = context->bw.dce.dispclk_khz;
 	req_clks.phyclk_khz = get_max_pixel_clock_for_all_paths(dc, context);
 
 	if (decrease_allowed)
-- 
cgit v1.2.3


From 9315e2399a2cdc236e8d42c1a21fb1071cdad03d Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Mon, 16 Jul 2018 11:21:12 -0400
Subject: drm/amd/display: Fix DP HBR2 Eye Diagram Pattern on Carrizo

[why] dp hbr2 eye diagram pattern for raven asic is not stabled.
workaround is to use tp4 pattern. But this should not be
applied to asic before raven.

[how] add new bool varilable in asic caps. for raven asic,
use the workaround. for carrizo, vega, do not use workaround.

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Harry Wentland <Harry.Wentland@amd.com>
Acked-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c      | 8 +++-----
 drivers/gpu/drm/amd/display/dc/dc.h                   | 1 +
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c | 2 ++
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 58ee9aad13fb..160841da72a7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -1784,12 +1784,10 @@ static void dp_test_send_link_training(struct dc_link *link)
 	dp_retrain_link_dp_test(link, &link_settings, false);
 }
 
-/* TODO hbr2 compliance eye output is unstable
+/* TODO Raven hbr2 compliance eye output is unstable
  * (toggling on and off) with debugger break
  * This caueses intermittent PHY automation failure
  * Need to look into the root cause */
-static uint8_t force_tps4_for_cp2520 = 1;
-
 static void dp_test_send_phy_test_pattern(struct dc_link *link)
 {
 	union phy_test_pattern dpcd_test_pattern;
@@ -1849,13 +1847,13 @@ static void dp_test_send_phy_test_pattern(struct dc_link *link)
 		break;
 	case PHY_TEST_PATTERN_CP2520_1:
 		/* CP2520 pattern is unstable, temporarily use TPS4 instead */
-		test_pattern = (force_tps4_for_cp2520 == 1) ?
+		test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
 				DP_TEST_PATTERN_TRAINING_PATTERN4 :
 				DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
 		break;
 	case PHY_TEST_PATTERN_CP2520_2:
 		/* CP2520 pattern is unstable, temporarily use TPS4 instead */
-		test_pattern = (force_tps4_for_cp2520 == 1) ?
+		test_pattern = (link->dc->caps.force_dp_tps4_for_cp2520 == 1) ?
 				DP_TEST_PATTERN_TRAINING_PATTERN4 :
 				DP_TEST_PATTERN_HBR2_COMPLIANCE_EYE;
 		break;
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index c2d390fba0bf..55bcc3bdc6a3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -77,6 +77,7 @@ struct dc_caps {
 	bool is_apu;
 	bool dual_link_dvi;
 	bool post_blend_color_processing;
+	bool force_dp_tps4_for_cp2520;
 };
 
 struct dc_dcc_surface_param {
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
index 5d169f07d745..6b44ed3697a4 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_resource.c
@@ -1127,6 +1127,8 @@ static bool construct(
 	dc->caps.max_slave_planes = 1;
 	dc->caps.is_apu = true;
 	dc->caps.post_blend_color_processing = false;
+	/* Raven DP PHY HBR2 eye diagram pattern is not stable. Use TP4 */
+	dc->caps.force_dp_tps4_for_cp2520 = true;
 
 	if (dc->ctx->dce_environment == DCE_ENV_PRODUCTION_DRV)
 		dc->debug = debug_defaults_drv;
-- 
cgit v1.2.3


From 3e27e10e2ecee0d3a0083f8ae76354ac9c6ad15c Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Thu, 12 Jul 2018 16:44:05 -0400
Subject: drm/amd/display: Don't share clk source between DP and HDMI

[why]
Prevent clock source sharing between HDMI and DP connectors.
DP shouldn't be sharing its ref clock with phy clock,
which caused an issue of older ASICS booting up with multiple
diplays plugged in.

[how]
Add an extra check that would prevent HDMI and DP sharing clk.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Hersen Wu <hersenxs.wu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c  | 22 +++++++++++++++++++++-
 drivers/gpu/drm/amd/display/dc/dc.h                |  1 +
 .../drm/amd/display/dc/dce100/dce100_resource.c    |  2 +-
 .../gpu/drm/amd/display/dc/dce80/dce80_resource.c  |  3 +++
 4 files changed, 26 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 2e65715f76a1..4ca41d6e3bcf 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -330,6 +330,9 @@ bool resource_are_streams_timing_synchronizable(
 				!= stream2->timing.pix_clk_khz)
 		return false;
 
+	if (stream1->clamping.c_depth != stream2->clamping.c_depth)
+		return false;
+
 	if (stream1->phy_pix_clk != stream2->phy_pix_clk
 			&& (!dc_is_dp_signal(stream1->signal)
 			|| !dc_is_dp_signal(stream2->signal)))
@@ -337,6 +340,20 @@ bool resource_are_streams_timing_synchronizable(
 
 	return true;
 }
+static bool is_dp_and_hdmi_sharable(
+		struct dc_stream_state *stream1,
+		struct dc_stream_state *stream2)
+{
+	if (stream1->ctx->dc->caps.disable_dp_clk_share)
+		return false;
+
+	if (stream1->clamping.c_depth != COLOR_DEPTH_888 ||
+	    stream2->clamping.c_depth != COLOR_DEPTH_888)
+	return false;
+
+	return true;
+
+}
 
 static bool is_sharable_clk_src(
 	const struct pipe_ctx *pipe_with_clk_src,
@@ -348,7 +365,10 @@ static bool is_sharable_clk_src(
 	if (pipe_with_clk_src->stream->signal == SIGNAL_TYPE_VIRTUAL)
 		return false;
 
-	if (dc_is_dp_signal(pipe_with_clk_src->stream->signal))
+	if (dc_is_dp_signal(pipe_with_clk_src->stream->signal) ||
+		(dc_is_dp_signal(pipe->stream->signal) &&
+		!is_dp_and_hdmi_sharable(pipe_with_clk_src->stream,
+				     pipe->stream)))
 		return false;
 
 	if (dc_is_hdmi_signal(pipe_with_clk_src->stream->signal)
diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 55bcc3bdc6a3..3ecd2d614f41 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -78,6 +78,7 @@ struct dc_caps {
 	bool dual_link_dvi;
 	bool post_blend_color_processing;
 	bool force_dp_tps4_for_cp2520;
+	bool disable_dp_clk_share;
 };
 
 struct dc_dcc_surface_param {
diff --git a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
index fd2bdae4dcec..3f76e6019546 100644
--- a/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce100/dce100_resource.c
@@ -919,7 +919,7 @@ static bool construct(
 	dc->caps.i2c_speed_in_khz = 40;
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
-
+	dc->caps.disable_dp_clk_share = true;
 	for (i = 0; i < pool->base.pipe_count; i++) {
 		pool->base.timing_generators[i] =
 			dce100_timing_generator_create(
diff --git a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
index dc9f3e9afc33..604c62969ead 100644
--- a/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce80/dce80_resource.c
@@ -946,6 +946,7 @@ static bool dce80_construct(
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
+	dc->caps.disable_dp_clk_share = true;
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
@@ -1131,6 +1132,7 @@ static bool dce81_construct(
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
+	dc->caps.disable_dp_clk_share = true;
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
@@ -1312,6 +1314,7 @@ static bool dce83_construct(
 	}
 
 	dc->caps.max_planes =  pool->base.pipe_count;
+	dc->caps.disable_dp_clk_share = true;
 
 	if (!resource_construct(num_virtual_links, dc, &pool->base,
 			&res_create_funcs))
-- 
cgit v1.2.3


From d2f884612c42850db0b3521b74a05636a5fc035f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 1 Aug 2018 11:47:42 +0100
Subject: ALSA: intel_hdmi: remove redundant variable cfg_val

Variable cfg_val is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'cfg_val' set but not used [-Wunused-but-set-variable]

[ Background info about val_bit field from alsa-devel ML thread:
 tiwai: Actually this made me wonder what is the definition of val_bit.
	It seems always 1 in the current code after the commit
	964ca8083c02. Pierre?
 pbossart: This val_bit is only there for debug/test, it should be set
	to one by default and has nothing to do with the lpcm_id.
	This variable was set even in patches before upstream
	submission and was never needed, I guess it must be a 9-yr
	old issue. Good catch!
]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Pierre-Louis Bossart <pierre-louis.bossart@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/x86/intel_hdmi_audio.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/sound/x86/intel_hdmi_audio.c b/sound/x86/intel_hdmi_audio.c
index edc9f5a34eff..fa7dca5a68c8 100644
--- a/sound/x86/intel_hdmi_audio.c
+++ b/sound/x86/intel_hdmi_audio.c
@@ -290,7 +290,6 @@ static void had_reset_audio(struct snd_intelhad *intelhaddata)
 static int had_prog_status_reg(struct snd_pcm_substream *substream,
 			struct snd_intelhad *intelhaddata)
 {
-	union aud_cfg cfg_val = {.regval = 0};
 	union aud_ch_status_0 ch_stat0 = {.regval = 0};
 	union aud_ch_status_1 ch_stat1 = {.regval = 0};
 
@@ -298,7 +297,6 @@ static int had_prog_status_reg(struct snd_pcm_substream *substream,
 					  IEC958_AES0_NONAUDIO) >> 1;
 	ch_stat0.regx.clk_acc = (intelhaddata->aes_bits &
 					  IEC958_AES3_CON_CLOCK) >> 4;
-	cfg_val.regx.val_bit = ch_stat0.regx.lpcm_id;
 
 	switch (substream->runtime->rate) {
 	case AUD_SAMPLE_RATE_32:
-- 
cgit v1.2.3


From 673bb2dfc36488abfdbbfc2ce2631204eaf682f2 Mon Sep 17 00:00:00 2001
From: Ben Hutchings <ben@decadent.org.uk>
Date: Sun, 5 Aug 2018 17:41:09 +0100
Subject: scripts/kernel-doc: Escape all literal braces in regexes

Commit 701b3a3c0ac4 ("PATCH scripts/kernel-doc") fixed the two
instances of literal braces that Perl 5.28 warns about, but there are
still more than it doesn't warn about.

Escape all left braces that are treated as literal characters.  Also
escape literal right braces, for consistency and to avoid confusing
bracket-matching in text editors.

Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 scripts/kernel-doc | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/scripts/kernel-doc b/scripts/kernel-doc
index 31a34ced55a3..8f0f508a78e9 100755
--- a/scripts/kernel-doc
+++ b/scripts/kernel-doc
@@ -1062,7 +1062,7 @@ sub dump_struct($$) {
     my $x = shift;
     my $file = shift;
 
-    if ($x =~ /(struct|union)\s+(\w+)\s*{(.*)}/) {
+    if ($x =~ /(struct|union)\s+(\w+)\s*\{(.*)\}/) {
 	my $decl_type = $1;
 	$declaration_name = $2;
 	my $members = $3;
@@ -1148,20 +1148,20 @@ sub dump_struct($$) {
 				}
 			}
 		}
-		$members =~ s/(struct|union)([^\{\};]+)\{([^\{\}]*)}([^\{\}\;]*)\;/$newmember/;
+		$members =~ s/(struct|union)([^\{\};]+)\{([^\{\}]*)\}([^\{\}\;]*)\;/$newmember/;
 	}
 
 	# Ignore other nested elements, like enums
-	$members =~ s/(\{[^\{\}]*})//g;
+	$members =~ s/(\{[^\{\}]*\})//g;
 
 	create_parameterlist($members, ';', $file, $declaration_name);
 	check_sections($file, $declaration_name, $decl_type, $sectcheck, $struct_actual);
 
 	# Adjust declaration for better display
-	$declaration =~ s/([{;])/$1\n/g;
-	$declaration =~ s/}\s+;/};/g;
+	$declaration =~ s/([\{;])/$1\n/g;
+	$declaration =~ s/\}\s+;/};/g;
 	# Better handle inlined enums
-	do {} while ($declaration =~ s/(enum\s+{[^}]+),([^\n])/$1,\n$2/);
+	do {} while ($declaration =~ s/(enum\s+\{[^\}]+),([^\n])/$1,\n$2/);
 
 	my @def_args = split /\n/, $declaration;
 	my $level = 1;
@@ -1171,12 +1171,12 @@ sub dump_struct($$) {
 		$clause =~ s/\s+$//;
 		$clause =~ s/\s+/ /;
 		next if (!$clause);
-		$level-- if ($clause =~ m/(})/ && $level > 1);
+		$level-- if ($clause =~ m/(\})/ && $level > 1);
 		if (!($clause =~ m/^\s*#/)) {
 			$declaration .= "\t" x $level;
 		}
 		$declaration .= "\t" . $clause . "\n";
-		$level++ if ($clause =~ m/(\{)/ && !($clause =~m/}/));
+		$level++ if ($clause =~ m/(\{)/ && !($clause =~m/\}/));
 	}
 	output_declaration($declaration_name,
 			   'struct',
@@ -1244,7 +1244,7 @@ sub dump_enum($$) {
     # strip #define macros inside enums
     $x =~ s@#\s*((define|ifdef)\s+|endif)[^;]*;@@gos;
 
-    if ($x =~ /enum\s+(\w+)\s*{(.*)}/) {
+    if ($x =~ /enum\s+(\w+)\s*\{(.*)\}/) {
 	$declaration_name = $1;
 	my $members = $2;
 	my %_members;
@@ -1785,7 +1785,7 @@ sub process_proto_type($$) {
     }
 
     while (1) {
-	if ( $x =~ /([^{};]*)([{};])(.*)/ ) {
+	if ( $x =~ /([^\{\};]*)([\{\};])(.*)/ ) {
             if( length $prototype ) {
                 $prototype .= " "
             }
-- 
cgit v1.2.3


From 70837ffe3085c9a91488b52ca13ac84424da1042 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 6 Aug 2018 22:17:35 +0300
Subject: ipv4: frags: precedence bug in ip_expire()

We accidentally removed the parentheses here, but they are required
because '!' has higher precedence than '&'.

Fixes: fa0f527358bd ("ip: use rb trees for IP frag queue.")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/ip_fragment.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 0e8f8de77e71..7cb7ed761d8c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -154,7 +154,7 @@ static void ip_expire(struct timer_list *t)
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
-	if (!qp->q.flags & INET_FRAG_FIRST_IN)
+	if (!(qp->q.flags & INET_FRAG_FIRST_IN))
 		goto out;
 
 	/* sk_buff::dev and sk_buff::rbnode are unionized. So we
-- 
cgit v1.2.3


From 405c018a25fe464dc68057bbc8014a58f2bd4422 Mon Sep 17 00:00:00 2001
From: "M. Vefa Bicakci" <m.v.b@runbox.com>
Date: Tue, 24 Jul 2018 08:45:47 -0400
Subject: xen/pv: Call get_cpu_address_sizes to set x86_virt/phys_bits

Commit d94a155c59c9 ("x86/cpu: Prevent cpuinfo_x86::x86_phys_bits
adjustment corruption") has moved the query and calculation of the
x86_virt_bits and x86_phys_bits fields of the cpuinfo_x86 struct
from the get_cpu_cap function to a new function named
get_cpu_address_sizes.

One of the call sites related to Xen PV VMs was unfortunately missed
in the aforementioned commit. This prevents successful boot-up of
kernel versions 4.17 and up in Xen PV VMs if CONFIG_DEBUG_VIRTUAL
is enabled, due to the following code path:

  enlighten_pv.c::xen_start_kernel
    mmu_pv.c::xen_reserve_special_pages
      page.h::__pa
        physaddr.c::__phys_addr
          physaddr.h::phys_addr_valid

phys_addr_valid uses boot_cpu_data.x86_phys_bits to validate physical
addresses. boot_cpu_data.x86_phys_bits is no longer populated before
the call to xen_reserve_special_pages due to the aforementioned commit
though, so the validation performed by phys_addr_valid fails, which
causes __phys_addr to trigger a BUG, preventing boot-up.

Signed-off-by: M. Vefa Bicakci <m.v.b@runbox.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: xen-devel@lists.xenproject.org
Cc: x86@kernel.org
Cc: stable@vger.kernel.org # for v4.17 and up
Fixes: d94a155c59c9 ("x86/cpu: Prevent cpuinfo_x86::x86_phys_bits adjustment corruption")
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/kernel/cpu/common.c | 2 +-
 arch/x86/kernel/cpu/cpu.h    | 1 +
 arch/x86/xen/enlighten_pv.c  | 3 +++
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index eb4cb3efd20e..2322d0c4bfd2 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -911,7 +911,7 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
 	apply_forced_caps(c);
 }
 
-static void get_cpu_address_sizes(struct cpuinfo_x86 *c)
+void get_cpu_address_sizes(struct cpuinfo_x86 *c)
 {
 	u32 eax, ebx, ecx, edx;
 
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 38216f678fc3..12a5f0cec0b2 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -46,6 +46,7 @@ extern const struct cpu_dev *const __x86_cpu_dev_start[],
 			    *const __x86_cpu_dev_end[];
 
 extern void get_cpu_cap(struct cpuinfo_x86 *c);
+extern void get_cpu_address_sizes(struct cpuinfo_x86 *c);
 extern void cpu_detect_cache_sizes(struct cpuinfo_x86 *c);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
 extern u32 get_scattered_cpuid_leaf(unsigned int level,
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 439a94bf89ad..c5e3f2acc7f0 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -1259,6 +1259,9 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	get_cpu_cap(&boot_cpu_data);
 	x86_configure_nx();
 
+	/* Determine virtual and physical address sizes */
+	get_cpu_address_sizes(&boot_cpu_data);
+
 	/* Let's presume PV guests always boot on vCPU with id 0. */
 	per_cpu(xen_vcpu_id, 0) = 0;
 
-- 
cgit v1.2.3


From ad830e7ab1847f4a014c04496b2581a7497b204f Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Wed, 18 Jul 2018 15:25:34 -0400
Subject: drm/amd/display: add vbios table check for enabling dp ss

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Eric Bernstein <Eric.Bernstein@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c               | 1 +
 drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c            | 5 ++++-
 drivers/gpu/drm/amd/display/dc/dc_link.h                    | 1 +
 drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h | 2 ++
 4 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 9a6448e2089c..016587675da4 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1038,6 +1038,7 @@ static bool construct(
 	link->link_index = init_params->link_index;
 
 	link->link_id = bios->funcs->get_connector_id(bios, init_params->connector_index);
+	link->dp_ss_off = !!dc_ctx->dc_bios->integrated_info->dp_ss_control;;
 
 	if (link->link_id.type != OBJECT_TYPE_CONNECTOR) {
 		dm_error("%s: Invalid Connector ObjectID from Adapter Service for connector index:%d! type %d expected %d\n",
diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
index 160841da72a7..a7553b6d59c2 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_dp.c
@@ -953,7 +953,10 @@ enum link_training_result dc_link_dp_perform_link_training(
 	 * LINK_SPREAD_05_DOWNSPREAD_30KHZ :
 	 * LINK_SPREAD_DISABLED;
 	 */
-	lt_settings.link_settings.link_spread = LINK_SPREAD_05_DOWNSPREAD_30KHZ;
+	if (link->dp_ss_off)
+		lt_settings.link_settings.link_spread = LINK_SPREAD_DISABLED;
+	else
+		lt_settings.link_settings.link_spread = LINK_SPREAD_05_DOWNSPREAD_30KHZ;
 
 	/* 1. set link rate, lane count and spread*/
 	dpcd_set_link_settings(link, &lt_settings);
diff --git a/drivers/gpu/drm/amd/display/dc/dc_link.h b/drivers/gpu/drm/amd/display/dc/dc_link.h
index 22f4ddd219d1..d43cefbc43d3 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_link.h
+++ b/drivers/gpu/drm/amd/display/dc/dc_link.h
@@ -73,6 +73,7 @@ struct dc_link {
 	enum dc_irq_source irq_source_hpd;
 	enum dc_irq_source irq_source_hpd_rx;/* aka DP Short Pulse  */
 	bool is_hpd_filter_disabled;
+	bool dp_ss_off;
 
 	/* caps is the same as reported_link_cap. link_traing use
 	 * reported_link_cap. Will clean up.  TODO
diff --git a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
index 36bbad594267..f312834fef50 100644
--- a/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
+++ b/drivers/gpu/drm/amd/display/include/grph_object_ctrl_defs.h
@@ -395,6 +395,8 @@ struct integrated_info {
 	struct i2c_reg_info dp3_ext_hdmi_reg_settings[9];
 	unsigned char dp3_ext_hdmi_6g_reg_num;
 	struct i2c_reg_info dp3_ext_hdmi_6g_reg_settings[3];
+	/* V11 */
+	uint32_t dp_ss_control;
 };
 
 /**
-- 
cgit v1.2.3


From fb7b11e1633e50b9a6b3fffe5cd151474aee9802 Mon Sep 17 00:00:00 2001
From: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Date: Mon, 30 Jul 2018 12:27:23 -0400
Subject: drm/amd/display: Add NULL check for enabling dp ss

[Why]

The pointer for integrated_info can be NULL which causes the system to
do a null pointer deference and hang on boot.

[How]

Add a check to ensure that integrated_info is not null before enabling
DP ss.

Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Reviewed-by: Sun peng Li <Sunpeng.Li@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/core/dc_link.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
index 016587675da4..a38e7ad36a7e 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c
@@ -1038,7 +1038,9 @@ static bool construct(
 	link->link_index = init_params->link_index;
 
 	link->link_id = bios->funcs->get_connector_id(bios, init_params->connector_index);
-	link->dp_ss_off = !!dc_ctx->dc_bios->integrated_info->dp_ss_control;;
+
+	if (dc_ctx->dc_bios->integrated_info)
+		link->dp_ss_off = !!dc_ctx->dc_bios->integrated_info->dp_ss_control;
 
 	if (link->link_id.type != OBJECT_TYPE_CONNECTOR) {
 		dm_error("%s: Invalid Connector ObjectID from Adapter Service for connector index:%d! type %d expected %d\n",
-- 
cgit v1.2.3


From 99326ee3624b90d176a8f7e2aa3d15dfaa59c8f1 Mon Sep 17 00:00:00 2001
From: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Date: Thu, 26 Jul 2018 12:17:58 -0400
Subject: drm/amd/display: program display clock on cache match

[Why]
We seem to have an issue where high enough display clock
will not get set properly during S3 resume if we only
call vbios once

[How]
Expand condition of display clock programming to happen
even when cached display clock matches requested display
clock

Signed-off-by: Dmytro Laktyushkin <Dmytro.Laktyushkin@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c           | 4 +++-
 drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c | 2 ++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
index f17677971d0f..684da3db7568 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_clocks.c
@@ -625,7 +625,9 @@ static void dcn1_update_clocks(struct dccg *dccg,
 	}
 
 	/* dcn1 dppclk is tied to dispclk */
-	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)) {
+	/* program dispclk on = as a w/a for sleep resume clock ramping issues */
+	if (should_set_clock(safe_to_lower, new_clocks->dispclk_khz, dccg->clks.dispclk_khz)
+			|| new_clocks->dispclk_khz == dccg->clks.dispclk_khz) {
 		dcn1_ramp_up_dispclk_with_dpp(dccg, new_clocks);
 		dccg->clks.dispclk_khz = new_clocks->dispclk_khz;
 
diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
index f5d8242eb047..cfcc54f2ce65 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_hw_sequencer.c
@@ -1089,6 +1089,8 @@ static void dcn10_init_hw(struct dc *dc)
 	}
 
 	enable_power_gating_plane(dc->hwseq, true);
+
+	memset(&dc->res_pool->dccg->clks, 0, sizeof(dc->res_pool->dccg->clks));
 }
 
 static void reset_hw_ctx_wrap(
-- 
cgit v1.2.3


From 81aca8e75c1b046865fb2badef95a0dcff6f73de Mon Sep 17 00:00:00 2001
From: Mikita Lipski <mikita.lipski@amd.com>
Date: Fri, 13 Jul 2018 09:07:35 -0400
Subject: drm/amd/display: update clk for various HDMI color depths

[why]
When programming tonga's connector's backend we didn't take
in account that HDMI's colour depth might be more than 8bpc
therefore we need to add a switch statement that would adjust
the pixel clock accordingly.

[how]
Add a switch statement updating clock by its appropriate
coefficient.

Signed-off-by: Mikita Lipski <mikita.lipski@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/bios/command_table.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table.c b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
index 651e1fd4622f..a558bfaa0c46 100644
--- a/drivers/gpu/drm/amd/display/dc/bios/command_table.c
+++ b/drivers/gpu/drm/amd/display/dc/bios/command_table.c
@@ -808,6 +808,24 @@ static enum bp_result transmitter_control_v1_5(
 	 * (=1: 8bpp, =1.25: 10bpp, =1.5:12bpp, =2: 16bpp)
 	 * LVDS mode: usPixelClock = pixel clock
 	 */
+	if  (cntl->signal == SIGNAL_TYPE_HDMI_TYPE_A) {
+		switch (cntl->color_depth) {
+		case COLOR_DEPTH_101010:
+			params.usSymClock =
+				cpu_to_le16((le16_to_cpu(params.usSymClock) * 30) / 24);
+			break;
+		case COLOR_DEPTH_121212:
+			params.usSymClock =
+				cpu_to_le16((le16_to_cpu(params.usSymClock) * 36) / 24);
+			break;
+		case COLOR_DEPTH_161616:
+			params.usSymClock =
+				cpu_to_le16((le16_to_cpu(params.usSymClock) * 48) / 24);
+			break;
+		default:
+			break;
+		}
+	}
 
 	if (EXEC_BIOS_CMD_TABLE(UNIPHYTransmitterControl, params))
 		result = BP_RESULT_OK;
-- 
cgit v1.2.3


From 1e1dbd6fd10031bf46d9e44b6ad423e2ee39e2a7 Mon Sep 17 00:00:00 2001
From: Hersen Wu <hersenxs.wu@amd.com>
Date: Fri, 27 Jul 2018 14:52:37 -0400
Subject: drm/amd/display: display connected to dp-1 does not light up

[why]
for vega, dp set_panel_mode is
handled by psp firmware. dal should not program the
register again.

[how]
dal does not program panel mode.

Signed-off-by: Hersen Wu <hersenxs.wu@amd.com>
Reviewed-by: Charlene Liu <Charlene.Liu@amd.com>
Acked-by: Bhawanpreet Lakha <Bhawanpreet.Lakha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/display/dc/dc.h                     | 1 +
 drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c   | 5 +++++
 drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c | 1 +
 3 files changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
index 3ecd2d614f41..e2f033d420a0 100644
--- a/drivers/gpu/drm/amd/display/dc/dc.h
+++ b/drivers/gpu/drm/amd/display/dc/dc.h
@@ -79,6 +79,7 @@ struct dc_caps {
 	bool post_blend_color_processing;
 	bool force_dp_tps4_for_cp2520;
 	bool disable_dp_clk_share;
+	bool psp_setup_panel_mode;
 };
 
 struct dc_dcc_surface_param {
diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
index 60e3c6a73d37..752b3d62e793 100644
--- a/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
+++ b/drivers/gpu/drm/amd/display/dc/dce/dce_link_encoder.c
@@ -256,6 +256,11 @@ static void setup_panel_mode(
 	enum dp_panel_mode panel_mode)
 {
 	uint32_t value;
+	struct dc_context *ctx = enc110->base.ctx;
+
+	/* if psp set panel mode, dal should be program it */
+	if (ctx->dc->caps.psp_setup_panel_mode)
+		return;
 
 	ASSERT(REG(DP_DPHY_INTERNAL_CTRL));
 	value = REG_READ(DP_DPHY_INTERNAL_CTRL);
diff --git a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
index 61d8e22d23c9..d43f37d99c7d 100644
--- a/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/dce120/dce120_resource.c
@@ -883,6 +883,7 @@ static bool construct(
 	dc->caps.i2c_speed_in_khz = 100;
 	dc->caps.max_cursor_size = 128;
 	dc->caps.dual_link_dvi = true;
+	dc->caps.psp_setup_panel_mode = true;
 
 	dc->debug = debug_defaults;
 
-- 
cgit v1.2.3


From 4823e5da2ea9061011242db81334d6ebbd2ed0a5 Mon Sep 17 00:00:00 2001
From: Lucas Stach <l.stach@pengutronix.de>
Date: Mon, 6 Aug 2018 15:12:48 +0200
Subject: drm/scheduler: fix timeout worker setup for out of order job
 completions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drm_sched_job_finish() is a work item scheduled for each finished job on
a unbound system workqueue. This means the workers can execute out of order
with regard to the real hardware job completions.

If this happens queueing a timeout worker for the first job on the ring
mirror list is wrong, as this may be a job which has already finished
executing. Fix this by reorganizing the code to always queue the worker
for the next job on the list, if this job hasn't finished yet. This is
robust against a potential reordering of the finish workers.

Also move out the timeout worker cancelling, so that we don't need to
take the job list lock twice. As a small optimization list_del is used
to remove the job from the ring mirror list, as there is no need to
reinit the list head in the job we are about to free.

Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index 1b733229201e..a70c7f7fd6fe 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -552,24 +552,28 @@ static void drm_sched_job_finish(struct work_struct *work)
 						   finish_work);
 	struct drm_gpu_scheduler *sched = s_job->sched;
 
-	/* remove job from ring_mirror_list */
-	spin_lock(&sched->job_list_lock);
-	list_del_init(&s_job->node);
-	if (sched->timeout != MAX_SCHEDULE_TIMEOUT) {
-		struct drm_sched_job *next;
-
-		spin_unlock(&sched->job_list_lock);
-		cancel_delayed_work_sync(&s_job->work_tdr);
-		spin_lock(&sched->job_list_lock);
+	/*
+	 * Canceling the timeout without removing our job from the ring mirror
+	 * list is safe, as we will only end up in this worker if our jobs
+	 * finished fence has been signaled. So even if some another worker
+	 * manages to find this job as the next job in the list, the fence
+	 * signaled check below will prevent the timeout to be restarted.
+	 */
+	cancel_delayed_work_sync(&s_job->work_tdr);
 
-		/* queue TDR for next job */
-		next = list_first_entry_or_null(&sched->ring_mirror_list,
-						struct drm_sched_job, node);
+	spin_lock(&sched->job_list_lock);
+	/* queue TDR for next job */
+	if (sched->timeout != MAX_SCHEDULE_TIMEOUT &&
+	    !list_is_last(&s_job->node, &sched->ring_mirror_list)) {
+		struct drm_sched_job *next = list_next_entry(s_job, node);
 
-		if (next)
+		if (!dma_fence_is_signaled(&next->s_fence->finished))
 			schedule_delayed_work(&next->work_tdr, sched->timeout);
 	}
+	/* remove job from ring_mirror_list */
+	list_del(&s_job->node);
 	spin_unlock(&sched->job_list_lock);
+
 	dma_fence_put(&s_job->s_fence->finished);
 	sched->ops->free_job(s_job);
 }
-- 
cgit v1.2.3


From 2224f2ff9670b899983ff1b42d85530e889cfea1 Mon Sep 17 00:00:00 2001
From: Kitone Elvis Peter <elviskitone@gmail.com>
Date: Mon, 6 Aug 2018 20:27:59 +0300
Subject: leds: ns2: Change unsigned to unsigned int

Use unsigned int, because it's preferred to unsigned.

Signed-off-by: Kitone Elvis Peter <elviskitone@gmail.com>
Acked-by: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Jacek Anaszewski <jacek.anaszewski@gmail.com>
---
 drivers/leds/leds-ns2.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index 14fe5cd43232..a0a7dc2ef87c 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -42,8 +42,8 @@
 
 struct ns2_led_data {
 	struct led_classdev	cdev;
-	unsigned		cmd;
-	unsigned		slow;
+	unsigned int		cmd;
+	unsigned int		slow;
 	bool			can_sleep;
 	unsigned char		sata; /* True when SATA mode active. */
 	rwlock_t		rw_lock; /* Lock GPIOs. */
-- 
cgit v1.2.3


From 640332d1a089909df08bc9f3e42888a2019c66e2 Mon Sep 17 00:00:00 2001
From: Levin Du <djw@t-chip.com.cn>
Date: Sat, 4 Aug 2018 15:31:02 +0800
Subject: clk: rockchip: Add pclk_rkpwm_pmu to PMU critical clocks in rk3399

PWM2 is commonly used to control voltage of PWM regulator of VDD_LOG in
RK3399. On the Firefly-RK3399 board, PWM2 outputs 40 KHz square wave
from power on and the VDD_LOG is about 0.9V. When the kernel boots
normally into the system, the PWM2 keeps outputing PWM signal.

But the kernel hangs randomly after "Starting kernel ..." line on that
board. When it happens, PWM2 outputs high level which causes VDD_LOG
drops to 0.4V below the normal operating voltage.

By adding "pclk_rkpwm_pmu" to the rk3399_pmucru_critical_clocks array,
PWM clock is ensured to be prepared at startup and the PWM2 output is
normal. After repeated tests, the early boot hang is gone.

This patch works on both Firefly-RK3399 and ROC-RK3399-PC boards.

Signed-off-by: Levin Du <djw@t-chip.com.cn>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 drivers/clk/rockchip/clk-rk3399.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/clk/rockchip/clk-rk3399.c b/drivers/clk/rockchip/clk-rk3399.c
index 2a8634a52856..5a628148f3f0 100644
--- a/drivers/clk/rockchip/clk-rk3399.c
+++ b/drivers/clk/rockchip/clk-rk3399.c
@@ -1523,6 +1523,7 @@ static const char *const rk3399_pmucru_critical_clocks[] __initconst = {
 	"pclk_pmu_src",
 	"fclk_cm0s_src_pmu",
 	"clk_timer_src_pmu",
+	"pclk_rkpwm_pmu",
 };
 
 static void __init rk3399_clk_init(struct device_node *np)
-- 
cgit v1.2.3


From 442af1403a2886f8f6d43f2f67f8a8b001e048d8 Mon Sep 17 00:00:00 2001
From: Janusz Krzysztofik <jmkrzyszt@gmail.com>
Date: Thu, 19 Jul 2018 01:57:08 +0200
Subject: gpio: omap: Add get/set_multiple() callbacks

This should make applications utilizing whole banks work faster.

Signed-off-by: Janusz Krzysztofik <jmkrzyszt@gmail.com>
Acked-by: Grygorii Strashko <grygorii.strashko@ti.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-omap.c | 88 ++++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 86 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index d1afedf4dcbf..e81008678a38 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -77,6 +77,8 @@ struct gpio_bank {
 	bool workaround_enabled;
 
 	void (*set_dataout)(struct gpio_bank *bank, unsigned gpio, int enable);
+	void (*set_dataout_multiple)(struct gpio_bank *bank,
+				     unsigned long *mask, unsigned long *bits);
 	int (*get_context_loss_count)(struct device *dev);
 
 	struct omap_gpio_reg_offs *regs;
@@ -161,6 +163,51 @@ static int omap_get_gpio_dataout(struct gpio_bank *bank, int offset)
 	return (readl_relaxed(reg) & (BIT(offset))) != 0;
 }
 
+/* set multiple data out values using dedicate set/clear register */
+static void omap_set_gpio_dataout_reg_multiple(struct gpio_bank *bank,
+					       unsigned long *mask,
+					       unsigned long *bits)
+{
+	void __iomem *reg = bank->base;
+	u32 l;
+
+	l = *bits & *mask;
+	writel_relaxed(l, reg + bank->regs->set_dataout);
+	bank->context.dataout |= l;
+
+	l = ~*bits & *mask;
+	writel_relaxed(l, reg + bank->regs->clr_dataout);
+	bank->context.dataout &= ~l;
+}
+
+/* set multiple data out values using mask register */
+static void omap_set_gpio_dataout_mask_multiple(struct gpio_bank *bank,
+						unsigned long *mask,
+						unsigned long *bits)
+{
+	void __iomem *reg = bank->base + bank->regs->dataout;
+	u32 l = (readl_relaxed(reg) & ~*mask) | (*bits & *mask);
+
+	writel_relaxed(l, reg);
+	bank->context.dataout = l;
+}
+
+static unsigned long omap_get_gpio_datain_multiple(struct gpio_bank *bank,
+					      unsigned long *mask)
+{
+	void __iomem *reg = bank->base + bank->regs->datain;
+
+	return readl_relaxed(reg) & *mask;
+}
+
+static unsigned long omap_get_gpio_dataout_multiple(struct gpio_bank *bank,
+					       unsigned long *mask)
+{
+	void __iomem *reg = bank->base + bank->regs->dataout;
+
+	return readl_relaxed(reg) & *mask;
+}
+
 static inline void omap_gpio_rmw(void __iomem *base, u32 reg, u32 mask, bool set)
 {
 	int l = readl_relaxed(base + reg);
@@ -968,6 +1015,26 @@ static int omap_gpio_output(struct gpio_chip *chip, unsigned offset, int value)
 	return 0;
 }
 
+static int omap_gpio_get_multiple(struct gpio_chip *chip, unsigned long *mask,
+				  unsigned long *bits)
+{
+	struct gpio_bank *bank = gpiochip_get_data(chip);
+	void __iomem *reg = bank->base + bank->regs->direction;
+	unsigned long in = readl_relaxed(reg), l;
+
+	*bits = 0;
+
+	l = in & *mask;
+	if (l)
+		*bits |= omap_get_gpio_datain_multiple(bank, &l);
+
+	l = ~in & *mask;
+	if (l)
+		*bits |= omap_get_gpio_dataout_multiple(bank, &l);
+
+	return 0;
+}
+
 static int omap_gpio_debounce(struct gpio_chip *chip, unsigned offset,
 			      unsigned debounce)
 {
@@ -1012,6 +1079,17 @@ static void omap_gpio_set(struct gpio_chip *chip, unsigned offset, int value)
 	raw_spin_unlock_irqrestore(&bank->lock, flags);
 }
 
+static void omap_gpio_set_multiple(struct gpio_chip *chip, unsigned long *mask,
+				   unsigned long *bits)
+{
+	struct gpio_bank *bank = gpiochip_get_data(chip);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&bank->lock, flags);
+	bank->set_dataout_multiple(bank, mask, bits);
+	raw_spin_unlock_irqrestore(&bank->lock, flags);
+}
+
 /*---------------------------------------------------------------------*/
 
 static void omap_gpio_show_rev(struct gpio_bank *bank)
@@ -1073,9 +1151,11 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct irq_chip *irqc)
 	bank->chip.get_direction = omap_gpio_get_direction;
 	bank->chip.direction_input = omap_gpio_input;
 	bank->chip.get = omap_gpio_get;
+	bank->chip.get_multiple = omap_gpio_get_multiple;
 	bank->chip.direction_output = omap_gpio_output;
 	bank->chip.set_config = omap_gpio_set_config;
 	bank->chip.set = omap_gpio_set;
+	bank->chip.set_multiple = omap_gpio_set_multiple;
 	if (bank->is_mpuio) {
 		bank->chip.label = "mpuio";
 		if (bank->regs->wkup_en)
@@ -1209,10 +1289,14 @@ static int omap_gpio_probe(struct platform_device *pdev)
 				pdata->get_context_loss_count;
 	}
 
-	if (bank->regs->set_dataout && bank->regs->clr_dataout)
+	if (bank->regs->set_dataout && bank->regs->clr_dataout) {
 		bank->set_dataout = omap_set_gpio_dataout_reg;
-	else
+		bank->set_dataout_multiple = omap_set_gpio_dataout_reg_multiple;
+	} else {
 		bank->set_dataout = omap_set_gpio_dataout_mask;
+		bank->set_dataout_multiple =
+				omap_set_gpio_dataout_mask_multiple;
+	}
 
 	raw_spin_lock_init(&bank->lock);
 	raw_spin_lock_init(&bank->wa_lock);
-- 
cgit v1.2.3


From cf2ff877a4eea5f5ad959050284eb93d5d2f803a Mon Sep 17 00:00:00 2001
From: Levin Du <djw@t-chip.com.cn>
Date: Tue, 31 Jul 2018 13:59:19 +0800
Subject: gpio: syscon: rockchip: add GRF GPIO support for rk3328

In Rockchip RK3328, the output only GPIO_MUTE pin, originally for codec
mute control, can also be used for general purpose. It is manipulated by
the GRF_SOC_CON10 register in GRF. Aside from the GPIO_MUTE pin, the HDMI
pins can also be set in the same way.

Currently this GRF GPIO controller only supports the mute pin. If needed
in the future, the HDMI pins support can also be added.

Signed-off-by: Levin Du <djw@t-chip.com.cn>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 .../bindings/gpio/rockchip,rk3328-grf-gpio.txt     | 32 ++++++++++++++++++++++
 drivers/gpio/gpio-syscon.c                         | 31 +++++++++++++++++++++
 2 files changed, 63 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/gpio/rockchip,rk3328-grf-gpio.txt

diff --git a/Documentation/devicetree/bindings/gpio/rockchip,rk3328-grf-gpio.txt b/Documentation/devicetree/bindings/gpio/rockchip,rk3328-grf-gpio.txt
new file mode 100644
index 000000000000..f9231df17c2b
--- /dev/null
+++ b/Documentation/devicetree/bindings/gpio/rockchip,rk3328-grf-gpio.txt
@@ -0,0 +1,32 @@
+Rockchip RK3328 GRF (General Register Files) GPIO controller.
+
+In Rockchip RK3328, the output only GPIO_MUTE pin, originally for codec mute
+control, can also be used for general purpose. It is manipulated by the
+GRF_SOC_CON10 register in GRF. Aside from the GPIO_MUTE pin, the HDMI pins can
+also be set in the same way.
+
+Currently this GPIO controller only supports the mute pin. If needed in the
+future, the HDMI pins support can also be added.
+
+Required properties:
+- compatible: Should contain "rockchip,rk3328-grf-gpio".
+- gpio-controller: Marks the device node as a gpio controller.
+- #gpio-cells: Should be 2. The first cell is the pin number and
+  the second cell is used to specify the gpio polarity:
+    0 = Active high,
+    1 = Active low.
+
+Example:
+
+	grf: syscon@ff100000 {
+		compatible = "rockchip,rk3328-grf", "syscon", "simple-mfd";
+
+		grf_gpio: grf-gpio {
+			compatible = "rockchip,rk3328-grf-gpio";
+			gpio-controller;
+			#gpio-cells = <2>;
+		};
+	};
+
+Note: The grf_gpio node should be declared as the child of the GRF (General
+Register File) node. The GPIO_MUTE pin is referred to as <&grf_gpio 0>.
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index d40cabd15e9e..87c18a544513 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -135,6 +135,33 @@ static const struct syscon_gpio_data clps711x_mctrl_gpio = {
 	.dat_bit_offset	= 0x40 * 8 + 8,
 };
 
+static void rockchip_gpio_set(struct gpio_chip *chip, unsigned int offset,
+			      int val)
+{
+	struct syscon_gpio_priv *priv = gpiochip_get_data(chip);
+	unsigned int offs;
+	u8 bit;
+	u32 data;
+	int ret;
+
+	offs = priv->dreg_offset + priv->data->dat_bit_offset + offset;
+	bit = offs % SYSCON_REG_BITS;
+	data = (val ? BIT(bit) : 0) | BIT(bit + 16);
+	ret = regmap_write(priv->syscon,
+			   (offs / SYSCON_REG_BITS) * SYSCON_REG_SIZE,
+			   data);
+	if (ret < 0)
+		dev_err(chip->parent, "gpio write failed ret(%d)\n", ret);
+}
+
+static const struct syscon_gpio_data rockchip_rk3328_gpio_mute = {
+	/* RK3328 GPIO_MUTE is an output only pin at GRF_SOC_CON10[1] */
+	.flags		= GPIO_SYSCON_FEAT_OUT,
+	.bit_count	= 1,
+	.dat_bit_offset = 0x0428 * 8 + 1,
+	.set		= rockchip_gpio_set,
+};
+
 #define KEYSTONE_LOCK_BIT BIT(0)
 
 static void keystone_gpio_set(struct gpio_chip *chip, unsigned offset, int val)
@@ -175,6 +202,10 @@ static const struct of_device_id syscon_gpio_ids[] = {
 		.compatible	= "ti,keystone-dsp-gpio",
 		.data		= &keystone_dsp_gpio,
 	},
+	{
+		.compatible	= "rockchip,rk3328-grf-gpio",
+		.data		= &rockchip_rk3328_gpio_mute,
+	},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, syscon_gpio_ids);
-- 
cgit v1.2.3


From 3a2f335c418fed18fc3e4b3d0ee0955e8b2c5f21 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:31 +0300
Subject: gpiolib: Don't shadow error code of gpiochip_lock_as_irq()

gpiochip_lock_as_irq() may return a few error codes,
do not shadow them by -EINVAL and let caller to decide.

No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index bdbfc95793e7..6bfd4e5cc161 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1805,16 +1805,18 @@ static const struct irq_domain_ops gpiochip_domain_ops = {
 static int gpiochip_irq_reqres(struct irq_data *d)
 {
 	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	int ret;
 
 	if (!try_module_get(chip->gpiodev->owner))
 		return -ENODEV;
 
-	if (gpiochip_lock_as_irq(chip, d->hwirq)) {
+	ret = gpiochip_lock_as_irq(chip, d->hwirq);
+	if (ret) {
 		chip_err(chip,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
 		module_put(chip->gpiodev->owner);
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 9b073332dd12553751951b08f78d7d1416f5bee2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:32 +0300
Subject: gpio: bcm-kona: Don't shadow error code of gpiochip_lock_as_irq()

gpiochip_lock_as_irq() may return a few error codes,
do not shadow them by -EINVAL and let caller to decide.

No functional change intended.

Cc: Ray Jui <rjui@broadcom.com>
Cc: Scott Branden <sbranden@broadcom.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-bcm-kona.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 00272fa7cc4f..d0707fc23afd 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -485,12 +485,14 @@ static void bcm_kona_gpio_irq_handler(struct irq_desc *desc)
 static int bcm_kona_gpio_irq_reqres(struct irq_data *d)
 {
 	struct bcm_kona_gpio *kona_gpio = irq_data_get_irq_chip_data(d);
+	int ret;
 
-	if (gpiochip_lock_as_irq(&kona_gpio->gpio_chip, d->hwirq)) {
+	ret = gpiochip_lock_as_irq(&kona_gpio->gpio_chip, d->hwirq);
+	if (ret) {
 		dev_err(kona_gpio->gpio_chip.parent,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			d->hwirq);
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 10ed35399ab0a46c2ff07b35977e0d423bde48f2 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:33 +0300
Subject: gpio: dwapb: Don't shadow error code of gpiochip_lock_as_irq()

gpiochip_lock_as_irq() may return a few error codes,
do not shadow them by -EINVAL and let caller to decide.

No functional change intended.

Cc: Hoan Tran <hotran@apm.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-dwapb.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index 7a2de3de6571..28da700f5f52 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -255,11 +255,13 @@ static int dwapb_irq_reqres(struct irq_data *d)
 	struct irq_chip_generic *igc = irq_data_get_irq_chip_data(d);
 	struct dwapb_gpio *gpio = igc->private;
 	struct gpio_chip *gc = &gpio->ports[0].gc;
+	int ret;
 
-	if (gpiochip_lock_as_irq(gc, irqd_to_hwirq(d))) {
+	ret = gpiochip_lock_as_irq(gc, irqd_to_hwirq(d));
+	if (ret) {
 		dev_err(gpio->dev, "unable to lock HW IRQ %lu for IRQ\n",
 			irqd_to_hwirq(d));
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 41d69087fd75f7288378082ee45c850109d9d289 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:34 +0300
Subject: gpio: em: Don't shadow error code of gpiochip_lock_as_irq()

gpiochip_lock_as_irq() may return a few error codes,
do not shadow them by -EINVAL and let caller to decide.

No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-em.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index 2b466b80e70a..982e699a5b81 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -101,12 +101,14 @@ static void em_gio_irq_enable(struct irq_data *d)
 static int em_gio_irq_reqres(struct irq_data *d)
 {
 	struct em_gio_priv *p = irq_data_get_irq_chip_data(d);
+	int ret;
 
-	if (gpiochip_lock_as_irq(&p->gpio_chip, irqd_to_hwirq(d))) {
+	ret = gpiochip_lock_as_irq(&p->gpio_chip, irqd_to_hwirq(d));
+	if (ret) {
 		dev_err(p->gpio_chip.parent,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			irqd_to_hwirq(d));
-		return -EINVAL;
+		return ret;
 	}
 	return 0;
 }
-- 
cgit v1.2.3


From 6d7a2b8b559e5682167187d4413d5f11251fcb01 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:35 +0300
Subject: gpio: xgene-sb: Don't shadow error code of gpiochip_lock_as_irq()

gpiochip_lock_as_irq() may return a few error codes,
do not shadow them by -ENOSPC and let caller to decide.

No functional change intended.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-xgene-sb.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-xgene-sb.c b/drivers/gpio/gpio-xgene-sb.c
index acd59113e08b..2eb76f35aa7e 100644
--- a/drivers/gpio/gpio-xgene-sb.c
+++ b/drivers/gpio/gpio-xgene-sb.c
@@ -143,12 +143,14 @@ static int xgene_gpio_sb_domain_activate(struct irq_domain *d,
 {
 	struct xgene_gpio_sb *priv = d->host_data;
 	u32 gpio = HWIRQ_TO_GPIO(priv, irq_data->hwirq);
+	int ret;
 
-	if (gpiochip_lock_as_irq(&priv->gc, gpio)) {
+	ret = gpiochip_lock_as_irq(&priv->gc, gpio);
+	if (ret) {
 		dev_err(priv->gc.parent,
 		"Unable to configure XGene GPIO standby pin %d as IRQ\n",
 				gpio);
-		return -ENOSPC;
+		return ret;
 	}
 
 	xgene_gpio_set_bit(&priv->gc, priv->regs + MPA_GPIO_SEL_LO,
-- 
cgit v1.2.3


From d124339da78d1f3b97d1dfa01dc4b52fca2f28e0 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:36 +0300
Subject: gpio: uniphier: Bail out on gpiochip_lock_as_irq() error

gpiochip_lock_as_irq() may return a few error codes,
bail out if it fails with corresponding returned code.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-uniphier.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c
index d3cf9502e7e7..ed2badecc050 100644
--- a/drivers/gpio/gpio-uniphier.c
+++ b/drivers/gpio/gpio-uniphier.c
@@ -306,8 +306,7 @@ static int uniphier_gpio_irq_domain_activate(struct irq_domain *domain,
 	struct uniphier_gpio_priv *priv = domain->host_data;
 	struct gpio_chip *chip = &priv->chip;
 
-	gpiochip_lock_as_irq(chip, data->hwirq + UNIPHIER_GPIO_IRQ_OFFSET);
-	return 0;
+	return gpiochip_lock_as_irq(chip, data->hwirq + UNIPHIER_GPIO_IRQ_OFFSET);
 }
 
 static void uniphier_gpio_irq_domain_deactivate(struct irq_domain *domain,
-- 
cgit v1.2.3


From f8ad8aa551af812adf2ba49a554c73cc9daa8d36 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jul 2018 15:38:37 +0300
Subject: gpio: vr41xx: Bail out on gpiochip_lock_as_irq() error

gpiochip_lock_as_irq() may return a few error codes,
bail out if it fails with corresponding returned code.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-vr41xx.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-vr41xx.c b/drivers/gpio/gpio-vr41xx.c
index ac8deb01f6f6..027699cec911 100644
--- a/drivers/gpio/gpio-vr41xx.c
+++ b/drivers/gpio/gpio-vr41xx.c
@@ -138,10 +138,16 @@ static void unmask_giuint_low(struct irq_data *d)
 
 static unsigned int startup_giuint(struct irq_data *data)
 {
-	if (gpiochip_lock_as_irq(&vr41xx_gpio_chip, data->hwirq))
+	int ret;
+
+	ret = gpiochip_lock_as_irq(&vr41xx_gpio_chip, irqd_to_hwirq(data));
+	if (ret) {
 		dev_err(vr41xx_gpio_chip.parent,
 			"unable to lock HW IRQ %lu for IRQ\n",
 			data->hwirq);
+		return ret;
+	}
+
 	/* Satisfy the .enable semantics by unmasking the line */
 	unmask_giuint_low(data);
 	return 0;
-- 
cgit v1.2.3


From 4467f7ad7dbb0af5136fadb32dba37bc0388194f Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 6 Aug 2018 15:24:25 -0700
Subject: MIPS: genvdso: Remove GOT checks

Our genvdso tool performs some rather paranoid checking that the VDSO
library isn't attempting to make use of a GOT by constraining the number
of entries that the GOT is allowed to contain to the minimum 2 entries
that are always generated by binutils.

Unfortunately lld prior to revision 334390 generates a third entry,
which is unused & thus harmless but falls foul of genvdso's checks &
causes the build to fail.

Since we already check that the VDSO contains no relocations it seems
reasonable to presume that it also doesn't contain use of a GOT, which
would involve relocations. Thus rather than attempting to work around
this issue by allowing 3 GOT entries when using lld, simply remove the
GOT checks which seem overly paranoid.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20152/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/vdso/genvdso.h | 51 ------------------------------------------------
 1 file changed, 51 deletions(-)

diff --git a/arch/mips/vdso/genvdso.h b/arch/mips/vdso/genvdso.h
index 94334727059a..611b06f01a3c 100644
--- a/arch/mips/vdso/genvdso.h
+++ b/arch/mips/vdso/genvdso.h
@@ -15,8 +15,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 	ELF(Shdr) *shdr;
 	char *shstrtab, *name;
 	uint16_t sh_count, sh_entsize, i;
-	unsigned int local_gotno, symtabno, gotsym;
-	ELF(Dyn) *dyn = NULL;
 
 	shdrs = vdso + FUNC(swap_uint)(ehdr->e_shoff);
 	sh_count = swap_uint16(ehdr->e_shnum);
@@ -41,9 +39,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 				"%s: '%s' contains relocation sections\n",
 				program_name, path);
 			return false;
-		case SHT_DYNAMIC:
-			dyn = vdso + FUNC(swap_uint)(shdr->sh_offset);
-			break;
 		}
 
 		/* Check for existing sections. */
@@ -61,52 +56,6 @@ static inline bool FUNC(patch_vdso)(const char *path, void *vdso)
 		}
 	}
 
-	/*
-	 * Ensure the GOT has no entries other than the standard 2, for the same
-	 * reason we check that there's no relocation sections above.
-	 * The standard two entries are:
-	 * - Lazy resolver
-	 * - Module pointer
-	 */
-	if (dyn) {
-		local_gotno = symtabno = gotsym = 0;
-
-		while (FUNC(swap_uint)(dyn->d_tag) != DT_NULL) {
-			switch (FUNC(swap_uint)(dyn->d_tag)) {
-			/*
-			 * This member holds the number of local GOT entries.
-			 */
-			case DT_MIPS_LOCAL_GOTNO:
-				local_gotno = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			/*
-			 * This member holds the number of entries in the
-			 * .dynsym section.
-			 */
-			case DT_MIPS_SYMTABNO:
-				symtabno = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			/*
-			 * This member holds the index of the first dynamic
-			 * symbol table entry that corresponds to an entry in
-			 * the GOT.
-			 */
-			case DT_MIPS_GOTSYM:
-				gotsym = FUNC(swap_uint)(dyn->d_un.d_val);
-				break;
-			}
-
-			dyn++;
-		}
-
-		if (local_gotno > 2 || symtabno - gotsym) {
-			fprintf(stderr,
-				"%s: '%s' contains unexpected GOT entries\n",
-				program_name, path);
-			return false;
-		}
-	}
-
 	return true;
 }
 
-- 
cgit v1.2.3


From ee67855ecd9d02da348af11ec8474698b886a0e6 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 6 Aug 2018 15:24:27 -0700
Subject: MIPS: vdso: Allow clang's --target flag in VDSO cflags

The MIPS VDSO code filters out a subset of known-good flags from
KBUILD_CFLAGS to use when building VDSO libraries. When we build using
clang we need to allow the --target flag through, otherwise we'll
generally attempt to build the VDSO for the architecture of the build
machine rather than for MIPS.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20154/
Cc: James Hogan <jhogan@kernel.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/vdso/Makefile | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index 477c463c89ec..bd79b27faa2b 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -9,6 +9,11 @@ ccflags-vdso := \
 	$(filter -mmicromips,$(KBUILD_CFLAGS)) \
 	$(filter -march=%,$(KBUILD_CFLAGS)) \
 	-D__VDSO__
+
+ifeq ($(cc-name),clang)
+ccflags-vdso += $(filter --target=%,$(KBUILD_CFLAGS))
+endif
+
 cflags-vdso := $(ccflags-vdso) \
 	$(filter -W%,$(filter-out -Wa$(comma)%,$(KBUILD_CFLAGS))) \
 	-O2 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
-- 
cgit v1.2.3


From b023a9396062df289399c6c4eab1f78c73199751 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 6 Aug 2018 18:18:52 -0700
Subject: MIPS: Avoid using array as parameter to write_c0_kpgd()

Passing an array (swapper_pg_dir) as the argument to write_c0_kpgd() in
setup_pw() will become problematic if we modify __write_64bit_c0_split()
to cast its val argument to unsigned long long, because for 32-bit
kernel builds the size of a pointer will differ from the size of an
unsigned long long. This would fall foul of gcc's pointer-to-int-cast
diagnostic.

Cast the value to a long, which should be the same width as the pointer
that we ultimately want & will be sign extended if required to the
unsigned long long that __write_64bit_c0_split() ultimately needs.

Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/mm/tlbex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/mips/mm/tlbex.c b/arch/mips/mm/tlbex.c
index 79b9f2ad3ff5..49312a14cd17 100644
--- a/arch/mips/mm/tlbex.c
+++ b/arch/mips/mm/tlbex.c
@@ -1509,7 +1509,7 @@ static void setup_pw(void)
 #ifdef CONFIG_MIPS_HUGE_TLB_SUPPORT
 	write_c0_pwctl(1 << 6 | psn);
 #endif
-	write_c0_kpgd(swapper_pg_dir);
+	write_c0_kpgd((long)swapper_pg_dir);
 	kscratch_used_mask |= (1 << 7); /* KScratch6 is used for KPGD */
 }
 
-- 
cgit v1.2.3


From 554ec508653688c21d9b8024af73a1ffaa0164b9 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Mon, 6 Aug 2018 15:34:21 -0700
Subject: lib/vsprintf: Do not handle %pO[^F] as %px

This patch avoids that gcc reports the following when building with W=1:

lib/vsprintf.c:1941:3: warning: this statement may fall through [-Wimplicit-fallthrough=]
   switch (fmt[1]) {
   ^~~~~~

Fixes: 7b1924a1d930eb2 ("vsprintf: add printk specifier %px")
Link: http://lkml.kernel.org/r/20180806223421.11995-1-bart.vanassche@wdc.com
Cc: linux-kernel@vger.kernel.org
Cc: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Pantelis Antoniou <pantelis.antoniou@konsulko.com>
Cc: Joe Perches <joe@perches.com>
Cc: Rob Herring <robh@kernel.org>
Cc: v4.15+ <stable@vger.kernel.org>
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 lib/vsprintf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index a48aaa79d352..cda186230287 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -1942,6 +1942,7 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 		case 'F':
 			return device_node_string(buf, end, ptr, spec, fmt + 1);
 		}
+		break;
 	case 'x':
 		return pointer_string(buf, end, ptr, spec);
 	}
-- 
cgit v1.2.3


From 30bd8b862f5466fe5aee9a9fcdaea5a4fad83f91 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:25:19 +0100
Subject: drm/i2c: tda998x: convert to bridge driver

Convert tda998x to a bridge driver with built-in encoder support for
compatibility with existing component drivers.

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 156 ++++++++++++++++++++------------------
 1 file changed, 81 insertions(+), 75 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index c35b52a83001..999810d8e3d0 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -69,6 +69,7 @@ struct tda998x_priv {
 	bool edid_delay_active;
 
 	struct drm_encoder encoder;
+	struct drm_bridge bridge;
 	struct drm_connector connector;
 
 	struct tda998x_audio_port audio_port[2];
@@ -79,9 +80,10 @@ struct tda998x_priv {
 
 #define conn_to_tda998x_priv(x) \
 	container_of(x, struct tda998x_priv, connector)
-
 #define enc_to_tda998x_priv(x) \
 	container_of(x, struct tda998x_priv, encoder)
+#define bridge_to_tda998x_priv(x) \
+	container_of(x, struct tda998x_priv, bridge)
 
 /* The TDA9988 series of devices use a paged register scheme.. to simplify
  * things we encode the page # in upper bits of the register #.  To read/
@@ -1271,7 +1273,7 @@ tda998x_connector_best_encoder(struct drm_connector *connector)
 {
 	struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
 
-	return &priv->encoder;
+	return priv->bridge.encoder;
 }
 
 static
@@ -1301,15 +1303,32 @@ static int tda998x_connector_init(struct tda998x_priv *priv,
 	if (ret)
 		return ret;
 
-	drm_mode_connector_attach_encoder(&priv->connector, &priv->encoder);
+	drm_mode_connector_attach_encoder(&priv->connector,
+					  priv->bridge.encoder);
 
 	return 0;
 }
 
-/* DRM encoder functions */
+/* DRM bridge functions */
+
+static int tda998x_bridge_attach(struct drm_bridge *bridge)
+{
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
+	return tda998x_connector_init(priv, bridge->dev);
+}
+
+static void tda998x_bridge_detach(struct drm_bridge *bridge)
+{
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
+	drm_connector_cleanup(&priv->connector);
+}
 
-static void tda998x_enable(struct tda998x_priv *priv)
+static void tda998x_bridge_enable(struct drm_bridge *bridge)
 {
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
 	if (!priv->is_on) {
 		/* enable video ports, audio will be enabled later */
 		reg_write(priv, REG_ENA_VP_0, 0xff);
@@ -1324,8 +1343,10 @@ static void tda998x_enable(struct tda998x_priv *priv)
 	}
 }
 
-static void tda998x_disable(struct tda998x_priv *priv)
+static void tda998x_bridge_disable(struct drm_bridge *bridge)
 {
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
 	if (priv->is_on) {
 		/* disable video ports */
 		reg_write(priv, REG_ENA_VP_0, 0x00);
@@ -1336,29 +1357,11 @@ static void tda998x_disable(struct tda998x_priv *priv)
 	}
 }
 
-static void tda998x_encoder_dpms(struct drm_encoder *encoder, int mode)
-{
-	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
-	bool on;
-
-	/* we only care about on or off: */
-	on = mode == DRM_MODE_DPMS_ON;
-
-	if (on == priv->is_on)
-		return;
-
-	if (on)
-		tda998x_enable(priv);
-	else
-		tda998x_disable(priv);
-}
-
-static void
-tda998x_encoder_mode_set(struct drm_encoder *encoder,
-			 struct drm_display_mode *mode,
-			 struct drm_display_mode *adjusted_mode)
+static void tda998x_bridge_mode_set(struct drm_bridge *bridge,
+				    struct drm_display_mode *mode,
+				    struct drm_display_mode *adjusted_mode)
 {
-	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
 	u16 ref_pix, ref_line, n_pix, n_line;
 	u16 hs_pix_s, hs_pix_e;
 	u16 vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e;
@@ -1565,8 +1568,18 @@ tda998x_encoder_mode_set(struct drm_encoder *encoder,
 	mutex_unlock(&priv->audio_mutex);
 }
 
+static const struct drm_bridge_funcs tda998x_bridge_funcs = {
+	.attach = tda998x_bridge_attach,
+	.detach = tda998x_bridge_detach,
+	.disable = tda998x_bridge_disable,
+	.mode_set = tda998x_bridge_mode_set,
+	.enable = tda998x_bridge_enable,
+};
+
 static void tda998x_destroy(struct tda998x_priv *priv)
 {
+	drm_bridge_remove(&priv->bridge);
+
 	/* disable all IRQs and free the IRQ handler */
 	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
 	reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
@@ -1659,6 +1672,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	mutex_init(&priv->mutex);	/* protect the page access */
 	mutex_init(&priv->audio_mutex); /* protect access from audio thread */
 	mutex_init(&priv->edid_mutex);
+	INIT_LIST_HEAD(&priv->bridge.list);
 	init_waitqueue_head(&priv->edid_delay_waitq);
 	timer_setup(&priv->edid_delay_timer, tda998x_edid_delay_done, 0);
 	INIT_WORK(&priv->detect_work, tda998x_detect_work);
@@ -1819,43 +1833,25 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 		tda998x_set_config(priv, client->dev.platform_data);
 	}
 
+	priv->bridge.funcs = &tda998x_bridge_funcs;
+#ifdef CONFIG_OF
+	priv->bridge.of_node = dev->of_node;
+#endif
+
+	drm_bridge_add(&priv->bridge);
+
 	return 0;
 
 fail:
-	/* if encoder_init fails, the encoder slave is never registered,
-	 * so cleanup here:
-	 */
-	i2c_unregister_device(priv->cec);
-	if (priv->cec_notify)
-		cec_notifier_put(priv->cec_notify);
-	if (client->irq)
-		free_irq(client->irq, priv);
+	tda998x_destroy(priv);
 err_irq:
 	return ret;
 }
 
-static void tda998x_encoder_prepare(struct drm_encoder *encoder)
-{
-	tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_OFF);
-}
-
-static void tda998x_encoder_commit(struct drm_encoder *encoder)
-{
-	tda998x_encoder_dpms(encoder, DRM_MODE_DPMS_ON);
-}
-
-static const struct drm_encoder_helper_funcs tda998x_encoder_helper_funcs = {
-	.dpms = tda998x_encoder_dpms,
-	.prepare = tda998x_encoder_prepare,
-	.commit = tda998x_encoder_commit,
-	.mode_set = tda998x_encoder_mode_set,
-};
+/* DRM encoder functions */
 
 static void tda998x_encoder_destroy(struct drm_encoder *encoder)
 {
-	struct tda998x_priv *priv = enc_to_tda998x_priv(encoder);
-
-	tda998x_destroy(priv);
 	drm_encoder_cleanup(encoder);
 }
 
@@ -1863,20 +1859,12 @@ static const struct drm_encoder_funcs tda998x_encoder_funcs = {
 	.destroy = tda998x_encoder_destroy,
 };
 
-static int tda998x_bind(struct device *dev, struct device *master, void *data)
+static int tda998x_encoder_init(struct device *dev, struct drm_device *drm)
 {
-	struct i2c_client *client = to_i2c_client(dev);
-	struct drm_device *drm = data;
-	struct tda998x_priv *priv;
+	struct tda998x_priv *priv = dev_get_drvdata(dev);
 	u32 crtcs = 0;
 	int ret;
 
-	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	dev_set_drvdata(dev, priv);
-
 	if (dev->of_node)
 		crtcs = drm_of_find_possible_crtcs(drm, dev->of_node);
 
@@ -1888,35 +1876,53 @@ static int tda998x_bind(struct device *dev, struct device *master, void *data)
 
 	priv->encoder.possible_crtcs = crtcs;
 
-	ret = tda998x_create(client, priv);
-	if (ret)
-		return ret;
-
-	drm_encoder_helper_add(&priv->encoder, &tda998x_encoder_helper_funcs);
 	ret = drm_encoder_init(drm, &priv->encoder, &tda998x_encoder_funcs,
 			       DRM_MODE_ENCODER_TMDS, NULL);
 	if (ret)
 		goto err_encoder;
 
-	ret = tda998x_connector_init(priv, drm);
+	ret = drm_bridge_attach(&priv->encoder, &priv->bridge, NULL);
 	if (ret)
-		goto err_connector;
+		goto err_bridge;
 
 	return 0;
 
-err_connector:
+err_bridge:
 	drm_encoder_cleanup(&priv->encoder);
 err_encoder:
-	tda998x_destroy(priv);
 	return ret;
 }
 
+static int tda998x_bind(struct device *dev, struct device *master, void *data)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct drm_device *drm = data;
+	struct tda998x_priv *priv;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, priv);
+
+	ret = tda998x_create(client, priv);
+	if (ret)
+		return ret;
+
+	ret = tda998x_encoder_init(dev, drm);
+	if (ret) {
+		tda998x_destroy(priv);
+		return ret;
+	}
+	return 0;
+}
+
 static void tda998x_unbind(struct device *dev, struct device *master,
 			   void *data)
 {
 	struct tda998x_priv *priv = dev_get_drvdata(dev);
 
-	drm_connector_cleanup(&priv->connector);
 	drm_encoder_cleanup(&priv->encoder);
 	tda998x_destroy(priv);
 }
-- 
cgit v1.2.3


From 2143adb04b357e192a9717a42554b1fd65c60fd2 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:25:19 +0100
Subject: drm/i2c: tda998x: allocate tda998x_priv inside tda998x_create()

Move the tda998x_priv allocation inside tda998x_create() and simplify
the tda998x_create()'s arguments.  Pass the same to tda998x_destroy().

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 999810d8e3d0..74c2e5e59922 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1576,8 +1576,10 @@ static const struct drm_bridge_funcs tda998x_bridge_funcs = {
 	.enable = tda998x_bridge_enable,
 };
 
-static void tda998x_destroy(struct tda998x_priv *priv)
+static void tda998x_destroy(struct device *dev)
 {
+	struct tda998x_priv *priv = dev_get_drvdata(dev);
+
 	drm_bridge_remove(&priv->bridge);
 
 	/* disable all IRQs and free the IRQ handler */
@@ -1662,13 +1664,21 @@ static void tda998x_set_config(struct tda998x_priv *priv,
 	priv->audio_params = p->audio_params;
 }
 
-static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
+static int tda998x_create(struct device *dev)
 {
+	struct i2c_client *client = to_i2c_client(dev);
 	struct device_node *np = client->dev.of_node;
 	struct i2c_board_info cec_info;
+	struct tda998x_priv *priv;
 	u32 video;
 	int rev_lo, rev_hi, ret;
 
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, priv);
+
 	mutex_init(&priv->mutex);	/* protect the page access */
 	mutex_init(&priv->audio_mutex); /* protect access from audio thread */
 	mutex_init(&priv->edid_mutex);
@@ -1843,7 +1853,7 @@ static int tda998x_create(struct i2c_client *client, struct tda998x_priv *priv)
 	return 0;
 
 fail:
-	tda998x_destroy(priv);
+	tda998x_destroy(dev);
 err_irq:
 	return ret;
 }
@@ -1895,24 +1905,16 @@ err_encoder:
 
 static int tda998x_bind(struct device *dev, struct device *master, void *data)
 {
-	struct i2c_client *client = to_i2c_client(dev);
 	struct drm_device *drm = data;
-	struct tda998x_priv *priv;
 	int ret;
 
-	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
-	if (!priv)
-		return -ENOMEM;
-
-	dev_set_drvdata(dev, priv);
-
-	ret = tda998x_create(client, priv);
+	ret = tda998x_create(dev);
 	if (ret)
 		return ret;
 
 	ret = tda998x_encoder_init(dev, drm);
 	if (ret) {
-		tda998x_destroy(priv);
+		tda998x_destroy(dev);
 		return ret;
 	}
 	return 0;
@@ -1924,7 +1926,7 @@ static void tda998x_unbind(struct device *dev, struct device *master,
 	struct tda998x_priv *priv = dev_get_drvdata(dev);
 
 	drm_encoder_cleanup(&priv->encoder);
-	tda998x_destroy(priv);
+	tda998x_destroy(dev);
 }
 
 static const struct component_ops tda998x_ops = {
-- 
cgit v1.2.3


From 76767fdabadbea7dec2cdd741c0177e4fab3c75a Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:25:19 +0100
Subject: drm/i2c: tda998x: cleanup from previous changes

Cleanup the code a little from the effects of the previous changes:
- Move tda998x_destroy() to be above tda998x_create()
- Use 'dev' directly in tda998x_create() where appropriate.

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 76 +++++++++++++++++++--------------------
 1 file changed, 37 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 74c2e5e59922..f486d85ac575 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1576,31 +1576,6 @@ static const struct drm_bridge_funcs tda998x_bridge_funcs = {
 	.enable = tda998x_bridge_enable,
 };
 
-static void tda998x_destroy(struct device *dev)
-{
-	struct tda998x_priv *priv = dev_get_drvdata(dev);
-
-	drm_bridge_remove(&priv->bridge);
-
-	/* disable all IRQs and free the IRQ handler */
-	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
-	reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
-
-	if (priv->audio_pdev)
-		platform_device_unregister(priv->audio_pdev);
-
-	if (priv->hdmi->irq)
-		free_irq(priv->hdmi->irq, priv);
-
-	del_timer_sync(&priv->edid_delay_timer);
-	cancel_work_sync(&priv->detect_work);
-
-	i2c_unregister_device(priv->cec);
-
-	if (priv->cec_notify)
-		cec_notifier_put(priv->cec_notify);
-}
-
 /* I2C driver functions */
 
 static int tda998x_get_audio_ports(struct tda998x_priv *priv,
@@ -1664,6 +1639,31 @@ static void tda998x_set_config(struct tda998x_priv *priv,
 	priv->audio_params = p->audio_params;
 }
 
+static void tda998x_destroy(struct device *dev)
+{
+	struct tda998x_priv *priv = dev_get_drvdata(dev);
+
+	drm_bridge_remove(&priv->bridge);
+
+	/* disable all IRQs and free the IRQ handler */
+	cec_write(priv, REG_CEC_RXSHPDINTENA, 0);
+	reg_clear(priv, REG_INT_FLAGS_2, INT_FLAGS_2_EDID_BLK_RD);
+
+	if (priv->audio_pdev)
+		platform_device_unregister(priv->audio_pdev);
+
+	if (priv->hdmi->irq)
+		free_irq(priv->hdmi->irq, priv);
+
+	del_timer_sync(&priv->edid_delay_timer);
+	cancel_work_sync(&priv->detect_work);
+
+	i2c_unregister_device(priv->cec);
+
+	if (priv->cec_notify)
+		cec_notifier_put(priv->cec_notify);
+}
+
 static int tda998x_create(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
@@ -1705,13 +1705,13 @@ static int tda998x_create(struct device *dev)
 	/* read version: */
 	rev_lo = reg_read(priv, REG_VERSION_LSB);
 	if (rev_lo < 0) {
-		dev_err(&client->dev, "failed to read version: %d\n", rev_lo);
+		dev_err(dev, "failed to read version: %d\n", rev_lo);
 		return rev_lo;
 	}
 
 	rev_hi = reg_read(priv, REG_VERSION_MSB);
 	if (rev_hi < 0) {
-		dev_err(&client->dev, "failed to read version: %d\n", rev_hi);
+		dev_err(dev, "failed to read version: %d\n", rev_hi);
 		return rev_hi;
 	}
 
@@ -1722,20 +1722,19 @@ static int tda998x_create(struct device *dev)
 
 	switch (priv->rev) {
 	case TDA9989N2:
-		dev_info(&client->dev, "found TDA9989 n2");
+		dev_info(dev, "found TDA9989 n2");
 		break;
 	case TDA19989:
-		dev_info(&client->dev, "found TDA19989");
+		dev_info(dev, "found TDA19989");
 		break;
 	case TDA19989N2:
-		dev_info(&client->dev, "found TDA19989 n2");
+		dev_info(dev, "found TDA19989 n2");
 		break;
 	case TDA19988:
-		dev_info(&client->dev, "found TDA19988");
+		dev_info(dev, "found TDA19988");
 		break;
 	default:
-		dev_err(&client->dev, "found unsupported device: %04x\n",
-			priv->rev);
+		dev_err(dev, "found unsupported device: %04x\n", priv->rev);
 		return -ENXIO;
 	}
 
@@ -1778,8 +1777,7 @@ static int tda998x_create(struct device *dev)
 					   tda998x_irq_thread, irq_flags,
 					   "tda998x", priv);
 		if (ret) {
-			dev_err(&client->dev,
-				"failed to request IRQ#%u: %d\n",
+			dev_err(dev, "failed to request IRQ#%u: %d\n",
 				client->irq, ret);
 			goto err_irq;
 		}
@@ -1788,13 +1786,13 @@ static int tda998x_create(struct device *dev)
 		cec_write(priv, REG_CEC_RXSHPDINTENA, CEC_RXSHPDLEV_HPD);
 	}
 
-	priv->cec_notify = cec_notifier_get(&client->dev);
+	priv->cec_notify = cec_notifier_get(dev);
 	if (!priv->cec_notify) {
 		ret = -ENOMEM;
 		goto fail;
 	}
 
-	priv->cec_glue.parent = &client->dev;
+	priv->cec_glue.parent = dev;
 	priv->cec_glue.data = priv;
 	priv->cec_glue.init = tda998x_cec_hook_init;
 	priv->cec_glue.exit = tda998x_cec_hook_exit;
@@ -1839,8 +1837,8 @@ static int tda998x_create(struct device *dev)
 
 		if (priv->audio_port[0].format != AFMT_UNUSED)
 			tda998x_audio_codec_init(priv, &client->dev);
-	} else if (client->dev.platform_data) {
-		tda998x_set_config(priv, client->dev.platform_data);
+	} else if (dev->platform_data) {
+		tda998x_set_config(priv, dev->platform_data);
 	}
 
 	priv->bridge.funcs = &tda998x_bridge_funcs;
-- 
cgit v1.2.3


From 5a03f5346fedc8b5f1a8601aa46a0930ba56a7ae Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:25:19 +0100
Subject: drm/i2c: tda998x: register bridge outside of component helper

Register the bridge outside of the component helper as we have
drivers that wish to use the tda998x without its encoder.

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index f486d85ac575..a7a4307f7fcb 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1904,18 +1904,8 @@ err_encoder:
 static int tda998x_bind(struct device *dev, struct device *master, void *data)
 {
 	struct drm_device *drm = data;
-	int ret;
-
-	ret = tda998x_create(dev);
-	if (ret)
-		return ret;
 
-	ret = tda998x_encoder_init(dev, drm);
-	if (ret) {
-		tda998x_destroy(dev);
-		return ret;
-	}
-	return 0;
+	return tda998x_encoder_init(dev, drm);
 }
 
 static void tda998x_unbind(struct device *dev, struct device *master,
@@ -1924,7 +1914,6 @@ static void tda998x_unbind(struct device *dev, struct device *master,
 	struct tda998x_priv *priv = dev_get_drvdata(dev);
 
 	drm_encoder_cleanup(&priv->encoder);
-	tda998x_destroy(dev);
 }
 
 static const struct component_ops tda998x_ops = {
@@ -1935,16 +1924,27 @@ static const struct component_ops tda998x_ops = {
 static int
 tda998x_probe(struct i2c_client *client, const struct i2c_device_id *id)
 {
+	int ret;
+
 	if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) {
 		dev_warn(&client->dev, "adapter does not support I2C\n");
 		return -EIO;
 	}
-	return component_add(&client->dev, &tda998x_ops);
+
+	ret = tda998x_create(&client->dev);
+	if (ret)
+		return ret;
+
+	ret = component_add(&client->dev, &tda998x_ops);
+	if (ret)
+		tda998x_destroy(&client->dev);
+	return ret;
 }
 
 static int tda998x_remove(struct i2c_client *client)
 {
 	component_del(&client->dev, &tda998x_ops);
+	tda998x_destroy(&client->dev);
 	return 0;
 }
 
-- 
cgit v1.2.3


From b073a70ecd37bc6e7c25a47315cd8d65e7b313fd Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:27:15 +0100
Subject: drm/i2c: tda998x: move mode_valid() to bridge

Move the mode_valid() implementation to the bridge instead of the
connector, as we're checking the bridge's capabilities.

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index a7a4307f7fcb..6308e8ec25df 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1253,21 +1253,6 @@ static int tda998x_connector_get_modes(struct drm_connector *connector)
 	return n;
 }
 
-static enum drm_mode_status tda998x_connector_mode_valid(struct drm_connector *connector,
-					struct drm_display_mode *mode)
-{
-	/* TDA19988 dotclock can go up to 165MHz */
-	struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
-
-	if (mode->clock > ((priv->rev == TDA19988) ? 165000 : 150000))
-		return MODE_CLOCK_HIGH;
-	if (mode->htotal >= BIT(13))
-		return MODE_BAD_HVALUE;
-	if (mode->vtotal >= BIT(11))
-		return MODE_BAD_VVALUE;
-	return MODE_OK;
-}
-
 static struct drm_encoder *
 tda998x_connector_best_encoder(struct drm_connector *connector)
 {
@@ -1279,7 +1264,6 @@ tda998x_connector_best_encoder(struct drm_connector *connector)
 static
 const struct drm_connector_helper_funcs tda998x_connector_helper_funcs = {
 	.get_modes = tda998x_connector_get_modes,
-	.mode_valid = tda998x_connector_mode_valid,
 	.best_encoder = tda998x_connector_best_encoder,
 };
 
@@ -1325,6 +1309,21 @@ static void tda998x_bridge_detach(struct drm_bridge *bridge)
 	drm_connector_cleanup(&priv->connector);
 }
 
+static enum drm_mode_status tda998x_bridge_mode_valid(struct drm_bridge *bridge,
+				     const struct drm_display_mode *mode)
+{
+	/* TDA19988 dotclock can go up to 165MHz */
+	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+
+	if (mode->clock > ((priv->rev == TDA19988) ? 165000 : 150000))
+		return MODE_CLOCK_HIGH;
+	if (mode->htotal >= BIT(13))
+		return MODE_BAD_HVALUE;
+	if (mode->vtotal >= BIT(11))
+		return MODE_BAD_VVALUE;
+	return MODE_OK;
+}
+
 static void tda998x_bridge_enable(struct drm_bridge *bridge)
 {
 	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
@@ -1571,6 +1570,7 @@ static void tda998x_bridge_mode_set(struct drm_bridge *bridge,
 static const struct drm_bridge_funcs tda998x_bridge_funcs = {
 	.attach = tda998x_bridge_attach,
 	.detach = tda998x_bridge_detach,
+	.mode_valid = tda998x_bridge_mode_valid,
 	.disable = tda998x_bridge_disable,
 	.mode_set = tda998x_bridge_mode_set,
 	.enable = tda998x_bridge_enable,
-- 
cgit v1.2.3


From a3d335f5de7cdd714737a9f8bdcc7b205b0f8d5e Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:27:15 +0100
Subject: drm/i2c: tda998x: get rid of private fill_modes function

We can achieve the same effect via the get_modes() method, rather than
wrapping the fill_modes helper.

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 30 ++++++------------------------
 1 file changed, 6 insertions(+), 24 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 6308e8ec25df..7313ff835f35 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1106,29 +1106,6 @@ static int tda998x_audio_codec_init(struct tda998x_priv *priv,
 
 /* DRM connector functions */
 
-static int tda998x_connector_fill_modes(struct drm_connector *connector,
-					uint32_t maxX, uint32_t maxY)
-{
-	struct tda998x_priv *priv = conn_to_tda998x_priv(connector);
-	int ret;
-
-	mutex_lock(&priv->audio_mutex);
-	ret = drm_helper_probe_single_connector_modes(connector, maxX, maxY);
-
-	if (connector->edid_blob_ptr) {
-		struct edid *edid = (void *)connector->edid_blob_ptr->data;
-
-		cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid);
-
-		priv->sink_has_audio = drm_detect_monitor_audio(edid);
-	} else {
-		priv->sink_has_audio = false;
-	}
-	mutex_unlock(&priv->audio_mutex);
-
-	return ret;
-}
-
 static enum drm_connector_status
 tda998x_connector_detect(struct drm_connector *connector, bool force)
 {
@@ -1147,7 +1124,7 @@ static void tda998x_connector_destroy(struct drm_connector *connector)
 static const struct drm_connector_funcs tda998x_connector_funcs = {
 	.dpms = drm_helper_connector_dpms,
 	.reset = drm_atomic_helper_connector_reset,
-	.fill_modes = tda998x_connector_fill_modes,
+	.fill_modes = drm_helper_probe_single_connector_modes,
 	.detect = tda998x_connector_detect,
 	.destroy = tda998x_connector_destroy,
 	.atomic_duplicate_state = drm_atomic_helper_connector_duplicate_state,
@@ -1246,7 +1223,12 @@ static int tda998x_connector_get_modes(struct drm_connector *connector)
 	}
 
 	drm_mode_connector_update_edid_property(connector, edid);
+	cec_notifier_set_phys_addr_from_edid(priv->cec_notify, edid);
+
+	mutex_lock(&priv->audio_mutex);
 	n = drm_add_edid_modes(connector, edid);
+	priv->sink_has_audio = drm_detect_monitor_audio(edid);
+	mutex_unlock(&priv->audio_mutex);
 
 	kfree(edid);
 
-- 
cgit v1.2.3


From 926a299c42e38bbe8bb909eae0146e676b66afe4 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 2 Aug 2018 10:27:15 +0100
Subject: drm/i2c: tda998x: correct PLL divider calculation

The serializer PLL divider is a power-of-two divider, so our calculation
which assumes that it's a numerical divider is incorrect.  Replace it
with one that results in a power-of-two divider value instead.

Tested with all supported modes with a Samsung S24C750.

Tested-by: Peter Rosin <peda@axentia.se>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/gpu/drm/i2c/tda998x_drv.c | 20 ++++++++++++++------
 1 file changed, 14 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index 7313ff835f35..0df86e928191 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -1343,6 +1343,7 @@ static void tda998x_bridge_mode_set(struct drm_bridge *bridge,
 				    struct drm_display_mode *adjusted_mode)
 {
 	struct tda998x_priv *priv = bridge_to_tda998x_priv(bridge);
+	unsigned long tmds_clock;
 	u16 ref_pix, ref_line, n_pix, n_line;
 	u16 hs_pix_s, hs_pix_e;
 	u16 vs1_pix_s, vs1_pix_e, vs1_line_s, vs1_line_e;
@@ -1413,12 +1414,19 @@ static void tda998x_bridge_mode_set(struct drm_bridge *bridge,
 			       (mode->vsync_end - mode->vsync_start)/2;
 	}
 
-	div = 148500 / mode->clock;
-	if (div != 0) {
-		div--;
-		if (div > 3)
-			div = 3;
-	}
+	tmds_clock = mode->clock;
+
+	/*
+	 * The divisor is power-of-2. The TDA9983B datasheet gives
+	 * this as ranges of Msample/s, which is 10x the TMDS clock:
+	 *   0 - 800 to 1500 Msample/s
+	 *   1 - 400 to 800 Msample/s
+	 *   2 - 200 to 400 Msample/s
+	 *   3 - as 2 above
+	 */
+	for (div = 0; div < 3; div++)
+		if (80000 >> div <= tmds_clock)
+			break;
 
 	mutex_lock(&priv->audio_mutex);
 
-- 
cgit v1.2.3


From 71e52c278c54db10e368c54687234390357b08d6 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 30 Jul 2018 23:06:40 +0200
Subject: crypto: arm64/aes-ce-gcm - operate on two input blocks at a time

Update the core AES/GCM transform and the associated plumbing to operate
on 2 AES/GHASH blocks at a time. By itself, this is not expected to
result in a noticeable speedup, but it paves the way for reimplementing
the GHASH component using 2-way aggregation.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm64/crypto/ghash-ce-core.S | 127 +++++++++++++++++++++++++++++---------
 arch/arm64/crypto/ghash-ce-glue.c | 103 +++++++++++++++++++------------
 2 files changed, 161 insertions(+), 69 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index c723647b37db..dac0df29d194 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -286,9 +286,10 @@ ENTRY(pmull_ghash_update_p8)
 	__pmull_ghash	p8
 ENDPROC(pmull_ghash_update_p8)
 
-	KS		.req	v8
-	CTR		.req	v9
-	INP		.req	v10
+	KS0		.req	v8
+	KS1		.req	v9
+	INP0		.req	v10
+	INP1		.req	v11
 
 	.macro		load_round_keys, rounds, rk
 	cmp		\rounds, #12
@@ -336,84 +337,146 @@ CPU_LE(	rev		x8, x8		)
 
 	.if		\enc == 1
 	ldr		x10, [sp]
-	ld1		{KS.16b}, [x10]
+	ld1		{KS0.16b-KS1.16b}, [x10]
 	.endif
 
-0:	ld1		{CTR.8b}, [x5]			// load upper counter
-	ld1		{INP.16b}, [x3], #16
+0:	ld1		{INP0.16b-INP1.16b}, [x3], #32
+
 	rev		x9, x8
-	add		x8, x8, #1
-	sub		w0, w0, #1
-	ins		CTR.d[1], x9			// set lower counter
+	add		x11, x8, #1
+	add		x8, x8, #2
 
 	.if		\enc == 1
-	eor		INP.16b, INP.16b, KS.16b	// encrypt input
-	st1		{INP.16b}, [x2], #16
+	eor		INP0.16b, INP0.16b, KS0.16b	// encrypt input
+	eor		INP1.16b, INP1.16b, KS1.16b
 	.endif
 
-	rev64		T1.16b, INP.16b
+	ld1		{KS0.8b}, [x5]			// load upper counter
+	rev		x11, x11
+	sub		w0, w0, #2
+	mov		KS1.8b, KS0.8b
+	ins		KS0.d[1], x9			// set lower counter
+	ins		KS1.d[1], x11
+
+	rev64		T1.16b, INP0.16b
 
 	cmp		w7, #12
 	b.ge		2f				// AES-192/256?
 
-1:	enc_round	CTR, v21
+1:	enc_round	KS0, v21
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
 
-	enc_round	CTR, v22
+	enc_round	KS1, v21
 
 	eor		T1.16b, T1.16b, T2.16b
 	eor		XL.16b, XL.16b, IN1.16b
 
-	enc_round	CTR, v23
+	enc_round	KS0, v22
 
 	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
 	eor		T1.16b, T1.16b, XL.16b
 
-	enc_round	CTR, v24
+	enc_round	KS1, v22
 
 	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
 	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
 
-	enc_round	CTR, v25
+	enc_round	KS0, v23
 
 	ext		T1.16b, XL.16b, XH.16b, #8
 	eor		T2.16b, XL.16b, XH.16b
 	eor		XM.16b, XM.16b, T1.16b
 
-	enc_round	CTR, v26
+	enc_round	KS1, v23
 
 	eor		XM.16b, XM.16b, T2.16b
 	pmull		T2.1q, XL.1d, MASK.1d
 
-	enc_round	CTR, v27
+	enc_round	KS0, v24
 
 	mov		XH.d[0], XM.d[1]
 	mov		XM.d[1], XL.d[0]
 
-	enc_round	CTR, v28
+	enc_round	KS1, v24
 
 	eor		XL.16b, XM.16b, T2.16b
 
-	enc_round	CTR, v29
+	enc_round	KS0, v25
 
 	ext		T2.16b, XL.16b, XL.16b, #8
 
-	aese		CTR.16b, v30.16b
+	enc_round	KS1, v25
 
 	pmull		XL.1q, XL.1d, MASK.1d
 	eor		T2.16b, T2.16b, XH.16b
 
-	eor		KS.16b, CTR.16b, v31.16b
+	enc_round	KS0, v26
+
+	eor		XL.16b, XL.16b, T2.16b
+	rev64		T1.16b, INP1.16b
+
+	enc_round	KS1, v26
+
+	ext		T2.16b, XL.16b, XL.16b, #8
+	ext		IN1.16b, T1.16b, T1.16b, #8
+
+	enc_round	KS0, v27
+
+	eor		T1.16b, T1.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
+
+	enc_round	KS1, v27
+
+	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+
+	enc_round	KS0, v28
+
+	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
+	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
+
+	enc_round	KS1, v28
+
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		T2.16b, XL.16b, XH.16b
+	eor		XM.16b, XM.16b, T1.16b
+
+	enc_round	KS0, v29
+
+	eor		XM.16b, XM.16b, T2.16b
+	pmull		T2.1q, XL.1d, MASK.1d
+
+	enc_round	KS1, v29
+
+	mov		XH.d[0], XM.d[1]
+	mov		XM.d[1], XL.d[0]
+
+	aese		KS0.16b, v30.16b
+
+	eor		XL.16b, XM.16b, T2.16b
+
+	aese		KS1.16b, v30.16b
+
+	ext		T2.16b, XL.16b, XL.16b, #8
+
+	eor		KS0.16b, KS0.16b, v31.16b
+
+	pmull		XL.1q, XL.1d, MASK.1d
+	eor		T2.16b, T2.16b, XH.16b
+
+	eor		KS1.16b, KS1.16b, v31.16b
 
 	eor		XL.16b, XL.16b, T2.16b
 
 	.if		\enc == 0
-	eor		INP.16b, INP.16b, KS.16b
-	st1		{INP.16b}, [x2], #16
+	eor		INP0.16b, INP0.16b, KS0.16b
+	eor		INP1.16b, INP1.16b, KS1.16b
 	.endif
 
+	st1		{INP0.16b-INP1.16b}, [x2], #32
+
 	cbnz		w0, 0b
 
 CPU_LE(	rev		x8, x8		)
@@ -421,16 +484,20 @@ CPU_LE(	rev		x8, x8		)
 	str		x8, [x5, #8]			// store lower counter
 
 	.if		\enc == 1
-	st1		{KS.16b}, [x10]
+	st1		{KS0.16b-KS1.16b}, [x10]
 	.endif
 
 	ret
 
 2:	b.eq		3f				// AES-192?
-	enc_round	CTR, v17
-	enc_round	CTR, v18
-3:	enc_round	CTR, v19
-	enc_round	CTR, v20
+	enc_round	KS0, v17
+	enc_round	KS1, v17
+	enc_round	KS0, v18
+	enc_round	KS1, v18
+3:	enc_round	KS0, v19
+	enc_round	KS1, v19
+	enc_round	KS0, v20
+	enc_round	KS1, v20
 	b		1b
 	.endm
 
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 18b4d1b96a7e..8ff6732c4fb5 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -348,9 +348,10 @@ static int gcm_encrypt(struct aead_request *req)
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
 	struct skcipher_walk walk;
 	u8 iv[AES_BLOCK_SIZE];
-	u8 ks[AES_BLOCK_SIZE];
+	u8 ks[2 * AES_BLOCK_SIZE];
 	u8 tag[AES_BLOCK_SIZE];
 	u64 dg[2] = {};
+	int nrounds = num_rounds(&ctx->aes_key);
 	int err;
 
 	if (req->assoclen)
@@ -362,32 +363,31 @@ static int gcm_encrypt(struct aead_request *req)
 	if (likely(may_use_simd())) {
 		kernel_neon_begin();
 
-		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc,
-					num_rounds(&ctx->aes_key));
+		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
-		pmull_gcm_encrypt_block(ks, iv, NULL,
-					num_rounds(&ctx->aes_key));
+		pmull_gcm_encrypt_block(ks, iv, NULL, nrounds);
 		put_unaligned_be32(3, iv + GCM_IV_SIZE);
+		pmull_gcm_encrypt_block(ks + AES_BLOCK_SIZE, iv, NULL, nrounds);
+		put_unaligned_be32(4, iv + GCM_IV_SIZE);
 		kernel_neon_end();
 
 		err = skcipher_walk_aead_encrypt(&walk, req, false);
 
-		while (walk.nbytes >= AES_BLOCK_SIZE) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+		while (walk.nbytes >= 2 * AES_BLOCK_SIZE) {
+			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 
 			kernel_neon_begin();
 			pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, ctx->aes_key.key_enc,
-					  num_rounds(&ctx->aes_key), ks);
+					  iv, ctx->aes_key.key_enc, nrounds,
+					  ks);
 			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
-						 walk.nbytes % AES_BLOCK_SIZE);
+					walk.nbytes % (2 * AES_BLOCK_SIZE));
 		}
 	} else {
-		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
-				    num_rounds(&ctx->aes_key));
+		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		err = skcipher_walk_aead_encrypt(&walk, req, false);
@@ -399,8 +399,7 @@ static int gcm_encrypt(struct aead_request *req)
 
 			do {
 				__aes_arm64_encrypt(ctx->aes_key.key_enc,
-						    ks, iv,
-						    num_rounds(&ctx->aes_key));
+						    ks, iv, nrounds);
 				crypto_xor_cpy(dst, src, ks, AES_BLOCK_SIZE);
 				crypto_inc(iv, AES_BLOCK_SIZE);
 
@@ -417,19 +416,28 @@ static int gcm_encrypt(struct aead_request *req)
 		}
 		if (walk.nbytes)
 			__aes_arm64_encrypt(ctx->aes_key.key_enc, ks, iv,
-					    num_rounds(&ctx->aes_key));
+					    nrounds);
 	}
 
 	/* handle the tail */
 	if (walk.nbytes) {
 		u8 buf[GHASH_BLOCK_SIZE];
+		unsigned int nbytes = walk.nbytes;
+		u8 *dst = walk.dst.virt.addr;
+		u8 *head = NULL;
 
 		crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, ks,
 			       walk.nbytes);
 
-		memcpy(buf, walk.dst.virt.addr, walk.nbytes);
-		memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes);
-		ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL);
+		if (walk.nbytes > GHASH_BLOCK_SIZE) {
+			head = dst;
+			dst += GHASH_BLOCK_SIZE;
+			nbytes %= GHASH_BLOCK_SIZE;
+		}
+
+		memcpy(buf, dst, nbytes);
+		memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes);
+		ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head);
 
 		err = skcipher_walk_done(&walk, 0);
 	}
@@ -452,10 +460,11 @@ static int gcm_decrypt(struct aead_request *req)
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(aead);
 	unsigned int authsize = crypto_aead_authsize(aead);
 	struct skcipher_walk walk;
-	u8 iv[AES_BLOCK_SIZE];
+	u8 iv[2 * AES_BLOCK_SIZE];
 	u8 tag[AES_BLOCK_SIZE];
-	u8 buf[GHASH_BLOCK_SIZE];
+	u8 buf[2 * GHASH_BLOCK_SIZE];
 	u64 dg[2] = {};
+	int nrounds = num_rounds(&ctx->aes_key);
 	int err;
 
 	if (req->assoclen)
@@ -466,37 +475,44 @@ static int gcm_decrypt(struct aead_request *req)
 
 	if (likely(may_use_simd())) {
 		kernel_neon_begin();
-
-		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc,
-					num_rounds(&ctx->aes_key));
+		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 		kernel_neon_end();
 
 		err = skcipher_walk_aead_decrypt(&walk, req, false);
 
-		while (walk.nbytes >= AES_BLOCK_SIZE) {
-			int blocks = walk.nbytes / AES_BLOCK_SIZE;
+		while (walk.nbytes >= 2 * AES_BLOCK_SIZE) {
+			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 
 			kernel_neon_begin();
 			pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, ctx->aes_key.key_enc,
-					  num_rounds(&ctx->aes_key));
+					  iv, ctx->aes_key.key_enc, nrounds);
 			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
-						 walk.nbytes % AES_BLOCK_SIZE);
+					walk.nbytes % (2 * AES_BLOCK_SIZE));
 		}
+
 		if (walk.nbytes) {
+			u8 *iv2 = iv + AES_BLOCK_SIZE;
+
+			if (walk.nbytes > AES_BLOCK_SIZE) {
+				memcpy(iv2, iv, AES_BLOCK_SIZE);
+				crypto_inc(iv2, AES_BLOCK_SIZE);
+			}
+
 			kernel_neon_begin();
 			pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc,
-						num_rounds(&ctx->aes_key));
+						nrounds);
+
+			if (walk.nbytes > AES_BLOCK_SIZE)
+				pmull_gcm_encrypt_block(iv2, iv2, NULL,
+							nrounds);
 			kernel_neon_end();
 		}
-
 	} else {
-		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv,
-				    num_rounds(&ctx->aes_key));
+		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
 		err = skcipher_walk_aead_decrypt(&walk, req, false);
@@ -511,8 +527,7 @@ static int gcm_decrypt(struct aead_request *req)
 
 			do {
 				__aes_arm64_encrypt(ctx->aes_key.key_enc,
-						    buf, iv,
-						    num_rounds(&ctx->aes_key));
+						    buf, iv, nrounds);
 				crypto_xor_cpy(dst, src, buf, AES_BLOCK_SIZE);
 				crypto_inc(iv, AES_BLOCK_SIZE);
 
@@ -525,14 +540,24 @@ static int gcm_decrypt(struct aead_request *req)
 		}
 		if (walk.nbytes)
 			__aes_arm64_encrypt(ctx->aes_key.key_enc, iv, iv,
-					    num_rounds(&ctx->aes_key));
+					    nrounds);
 	}
 
 	/* handle the tail */
 	if (walk.nbytes) {
-		memcpy(buf, walk.src.virt.addr, walk.nbytes);
-		memset(buf + walk.nbytes, 0, GHASH_BLOCK_SIZE - walk.nbytes);
-		ghash_do_update(1, dg, buf, &ctx->ghash_key, NULL);
+		const u8 *src = walk.src.virt.addr;
+		const u8 *head = NULL;
+		unsigned int nbytes = walk.nbytes;
+
+		if (walk.nbytes > GHASH_BLOCK_SIZE) {
+			head = src;
+			src += GHASH_BLOCK_SIZE;
+			nbytes %= GHASH_BLOCK_SIZE;
+		}
+
+		memcpy(buf, src, nbytes);
+		memset(buf + nbytes, 0, GHASH_BLOCK_SIZE - nbytes);
+		ghash_do_update(!!nbytes, dg, buf, &ctx->ghash_key, head);
 
 		crypto_xor_cpy(walk.dst.virt.addr, walk.src.virt.addr, iv,
 			       walk.nbytes);
@@ -557,7 +582,7 @@ static int gcm_decrypt(struct aead_request *req)
 
 static struct aead_alg gcm_aes_alg = {
 	.ivsize			= GCM_IV_SIZE,
-	.chunksize		= AES_BLOCK_SIZE,
+	.chunksize		= 2 * AES_BLOCK_SIZE,
 	.maxauthsize		= AES_BLOCK_SIZE,
 	.setkey			= gcm_setkey,
 	.setauthsize		= gcm_setauthsize,
-- 
cgit v1.2.3


From e0bd888dc487e0c444ee5f3bf55020862d16a225 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 30 Jul 2018 23:06:41 +0200
Subject: crypto: arm64/aes-ce-gcm - implement 2-way aggregation

Implement a faster version of the GHASH transform which amortizes
the reduction modulo the characteristic polynomial across two
input blocks at a time.

On a Cortex-A53, the gcm(aes) performance increases 24%, from
3.0 cycles per byte to 2.4 cpb for large input sizes.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm64/crypto/ghash-ce-core.S | 86 +++++++++++++--------------------------
 arch/arm64/crypto/ghash-ce-glue.c | 34 +++++++++++-----
 2 files changed, 52 insertions(+), 68 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index dac0df29d194..f7281e7a592f 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -290,6 +290,10 @@ ENDPROC(pmull_ghash_update_p8)
 	KS1		.req	v9
 	INP0		.req	v10
 	INP1		.req	v11
+	HH		.req	v12
+	XL2		.req	v13
+	XM2		.req	v14
+	XH2		.req	v15
 
 	.macro		load_round_keys, rounds, rk
 	cmp		\rounds, #12
@@ -323,6 +327,7 @@ ENDPROC(pmull_ghash_update_p8)
 	.endm
 
 	.macro		pmull_gcm_do_crypt, enc
+	ld1		{HH.2d}, [x4], #16
 	ld1		{SHASH.2d}, [x4]
 	ld1		{XL.2d}, [x1]
 	ldr		x8, [x5, #8]			// load lower counter
@@ -330,10 +335,11 @@ ENDPROC(pmull_ghash_update_p8)
 	load_round_keys	w7, x6
 
 	movi		MASK.16b, #0xe1
-	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	trn1		SHASH2.2d, SHASH.2d, HH.2d
+	trn2		T1.2d, SHASH.2d, HH.2d
 CPU_LE(	rev		x8, x8		)
 	shl		MASK.2d, MASK.2d, #57
-	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
+	eor		SHASH2.16b, SHASH2.16b, T1.16b
 
 	.if		\enc == 1
 	ldr		x10, [sp]
@@ -358,116 +364,82 @@ CPU_LE(	rev		x8, x8		)
 	ins		KS0.d[1], x9			// set lower counter
 	ins		KS1.d[1], x11
 
-	rev64		T1.16b, INP0.16b
+	rev64		T1.16b, INP1.16b
 
 	cmp		w7, #12
 	b.ge		2f				// AES-192/256?
 
 1:	enc_round	KS0, v21
-
-	ext		T2.16b, XL.16b, XL.16b, #8
 	ext		IN1.16b, T1.16b, T1.16b, #8
 
 	enc_round	KS1, v21
-
-	eor		T1.16b, T1.16b, T2.16b
-	eor		XL.16b, XL.16b, IN1.16b
+	pmull2		XH2.1q, SHASH.2d, IN1.2d	// a1 * b1
 
 	enc_round	KS0, v22
-
-	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
-	eor		T1.16b, T1.16b, XL.16b
+	eor		T1.16b, T1.16b, IN1.16b
 
 	enc_round	KS1, v22
-
-	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
-	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
+	pmull		XL2.1q, SHASH.1d, IN1.1d	// a0 * b0
 
 	enc_round	KS0, v23
-
-	ext		T1.16b, XL.16b, XH.16b, #8
-	eor		T2.16b, XL.16b, XH.16b
-	eor		XM.16b, XM.16b, T1.16b
+	pmull		XM2.1q, SHASH2.1d, T1.1d	// (a1 + a0)(b1 + b0)
 
 	enc_round	KS1, v23
-
-	eor		XM.16b, XM.16b, T2.16b
-	pmull		T2.1q, XL.1d, MASK.1d
+	rev64		T1.16b, INP0.16b
+	ext		T2.16b, XL.16b, XL.16b, #8
 
 	enc_round	KS0, v24
-
-	mov		XH.d[0], XM.d[1]
-	mov		XM.d[1], XL.d[0]
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	eor		T1.16b, T1.16b, T2.16b
 
 	enc_round	KS1, v24
-
-	eor		XL.16b, XM.16b, T2.16b
+	eor		XL.16b, XL.16b, IN1.16b
 
 	enc_round	KS0, v25
-
-	ext		T2.16b, XL.16b, XL.16b, #8
+	eor		T1.16b, T1.16b, XL.16b
 
 	enc_round	KS1, v25
-
-	pmull		XL.1q, XL.1d, MASK.1d
-	eor		T2.16b, T2.16b, XH.16b
+	pmull2		XH.1q, HH.2d, XL.2d		// a1 * b1
 
 	enc_round	KS0, v26
-
-	eor		XL.16b, XL.16b, T2.16b
-	rev64		T1.16b, INP1.16b
+	pmull		XL.1q, HH.1d, XL.1d		// a0 * b0
 
 	enc_round	KS1, v26
-
-	ext		T2.16b, XL.16b, XL.16b, #8
-	ext		IN1.16b, T1.16b, T1.16b, #8
+	pmull2		XM.1q, SHASH2.2d, T1.2d		// (a1 + a0)(b1 + b0)
 
 	enc_round	KS0, v27
-
-	eor		T1.16b, T1.16b, T2.16b
-	eor		XL.16b, XL.16b, IN1.16b
+	eor		XL.16b, XL.16b, XL2.16b
+	eor		XH.16b, XH.16b, XH2.16b
 
 	enc_round	KS1, v27
-
-	pmull2		XH.1q, SHASH.2d, XL.2d		// a1 * b1
-	eor		T1.16b, T1.16b, XL.16b
+	eor		XM.16b, XM.16b, XM2.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
 
 	enc_round	KS0, v28
-
-	pmull		XL.1q, SHASH.1d, XL.1d		// a0 * b0
-	pmull		XM.1q, SHASH2.1d, T1.1d		// (a1 + a0)(b1 + b0)
-
-	enc_round	KS1, v28
-
-	ext		T1.16b, XL.16b, XH.16b, #8
 	eor		T2.16b, XL.16b, XH.16b
 	eor		XM.16b, XM.16b, T1.16b
 
-	enc_round	KS0, v29
-
+	enc_round	KS1, v28
 	eor		XM.16b, XM.16b, T2.16b
+
+	enc_round	KS0, v29
 	pmull		T2.1q, XL.1d, MASK.1d
 
 	enc_round	KS1, v29
-
 	mov		XH.d[0], XM.d[1]
 	mov		XM.d[1], XL.d[0]
 
 	aese		KS0.16b, v30.16b
-
 	eor		XL.16b, XM.16b, T2.16b
 
 	aese		KS1.16b, v30.16b
-
 	ext		T2.16b, XL.16b, XL.16b, #8
 
 	eor		KS0.16b, KS0.16b, v31.16b
-
 	pmull		XL.1q, XL.1d, MASK.1d
 	eor		T2.16b, T2.16b, XH.16b
 
 	eor		KS1.16b, KS1.16b, v31.16b
-
 	eor		XL.16b, XL.16b, T2.16b
 
 	.if		\enc == 0
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 8ff6732c4fb5..cd91b146c87d 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -46,6 +46,7 @@ struct ghash_desc_ctx {
 
 struct gcm_aes_ctx {
 	struct crypto_aes_ctx	aes_key;
+	u64			h2[2];
 	struct ghash_key	ghash_key;
 };
 
@@ -62,12 +63,11 @@ static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
 				  const char *head);
 
 asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
-				  const u8 src[], struct ghash_key const *k,
-				  u8 ctr[], u32 const rk[], int rounds,
-				  u8 ks[]);
+				  const u8 src[], u64 const *k, u8 ctr[],
+				  u32 const rk[], int rounds, u8 ks[]);
 
 asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
-				  const u8 src[], struct ghash_key const *k,
+				  const u8 src[], u64 const *k,
 				  u8 ctr[], u32 const rk[], int rounds);
 
 asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
@@ -232,7 +232,8 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 		      unsigned int keylen)
 {
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm);
-	u8 key[GHASH_BLOCK_SIZE];
+	be128 h1, h2;
+	u8 *key = (u8 *)&h1;
 	int ret;
 
 	ret = crypto_aes_expand_key(&ctx->aes_key, inkey, keylen);
@@ -244,7 +245,19 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 	__aes_arm64_encrypt(ctx->aes_key.key_enc, key, (u8[AES_BLOCK_SIZE]){},
 			    num_rounds(&ctx->aes_key));
 
-	return __ghash_setkey(&ctx->ghash_key, key, sizeof(key));
+	__ghash_setkey(&ctx->ghash_key, key, sizeof(be128));
+
+	/* calculate H^2 (used for 2-way aggregation) */
+	h2 = h1;
+	gf128mul_lle(&h2, &h1);
+
+	ctx->h2[0] = (be64_to_cpu(h2.b) << 1) | (be64_to_cpu(h2.a) >> 63);
+	ctx->h2[1] = (be64_to_cpu(h2.a) << 1) | (be64_to_cpu(h2.b) >> 63);
+
+	if (be64_to_cpu(h2.a) >> 63)
+		ctx->h2[1] ^= 0xc200000000000000UL;
+
+	return 0;
 }
 
 static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
@@ -378,9 +391,8 @@ static int gcm_encrypt(struct aead_request *req)
 
 			kernel_neon_begin();
 			pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
-					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, ctx->aes_key.key_enc, nrounds,
-					  ks);
+					  walk.src.virt.addr, ctx->h2, iv,
+					  ctx->aes_key.key_enc, nrounds, ks);
 			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
@@ -486,8 +498,8 @@ static int gcm_decrypt(struct aead_request *req)
 
 			kernel_neon_begin();
 			pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
-					  walk.src.virt.addr, &ctx->ghash_key,
-					  iv, ctx->aes_key.key_enc, nrounds);
+					  walk.src.virt.addr, ctx->h2, iv,
+					  ctx->aes_key.key_enc, nrounds);
 			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
-- 
cgit v1.2.3


From 30f1a9f53e77e4c9ddf55ebfda8a9d7666e46964 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Mon, 30 Jul 2018 23:06:42 +0200
Subject: crypto: arm64/aes-ce-gcm - don't reload key schedule if avoidable

Squeeze out another 5% of performance by minimizing the number
of invocations of kernel_neon_begin()/kernel_neon_end() on the
common path, which also allows some reloads of the key schedule
to be optimized away.

The resulting code runs at 2.3 cycles per byte on a Cortex-A53.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm64/crypto/ghash-ce-core.S |  9 +++--
 arch/arm64/crypto/ghash-ce-glue.c | 81 +++++++++++++++++++++------------------
 2 files changed, 49 insertions(+), 41 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index f7281e7a592f..913e49932ae6 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -1,7 +1,7 @@
 /*
  * Accelerated GHASH implementation with ARMv8 PMULL instructions.
  *
- * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published
@@ -332,8 +332,6 @@ ENDPROC(pmull_ghash_update_p8)
 	ld1		{XL.2d}, [x1]
 	ldr		x8, [x5, #8]			// load lower counter
 
-	load_round_keys	w7, x6
-
 	movi		MASK.16b, #0xe1
 	trn1		SHASH2.2d, SHASH.2d, HH.2d
 	trn2		T1.2d, SHASH.2d, HH.2d
@@ -346,6 +344,8 @@ CPU_LE(	rev		x8, x8		)
 	ld1		{KS0.16b-KS1.16b}, [x10]
 	.endif
 
+	cbnz		x6, 4f
+
 0:	ld1		{INP0.16b-INP1.16b}, [x3], #32
 
 	rev		x9, x8
@@ -471,6 +471,9 @@ CPU_LE(	rev		x8, x8		)
 	enc_round	KS0, v20
 	enc_round	KS1, v20
 	b		1b
+
+4:	load_round_keys	w7, x6
+	b		0b
 	.endm
 
 	/*
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index cd91b146c87d..42a0e84e276c 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -1,7 +1,7 @@
 /*
  * Accelerated GHASH implementation with ARMv8 PMULL instructions.
  *
- * Copyright (C) 2014 - 2017 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ * Copyright (C) 2014 - 2018 Linaro Ltd. <ard.biesheuvel@linaro.org>
  *
  * This program is free software; you can redistribute it and/or modify it
  * under the terms of the GNU General Public License version 2 as published
@@ -373,37 +373,39 @@ static int gcm_encrypt(struct aead_request *req)
 	memcpy(iv, req->iv, GCM_IV_SIZE);
 	put_unaligned_be32(1, iv + GCM_IV_SIZE);
 
-	if (likely(may_use_simd())) {
-		kernel_neon_begin();
+	err = skcipher_walk_aead_encrypt(&walk, req, false);
 
+	if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) {
+		u32 const *rk = NULL;
+
+		kernel_neon_begin();
 		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 		pmull_gcm_encrypt_block(ks, iv, NULL, nrounds);
 		put_unaligned_be32(3, iv + GCM_IV_SIZE);
 		pmull_gcm_encrypt_block(ks + AES_BLOCK_SIZE, iv, NULL, nrounds);
 		put_unaligned_be32(4, iv + GCM_IV_SIZE);
-		kernel_neon_end();
-
-		err = skcipher_walk_aead_encrypt(&walk, req, false);
 
-		while (walk.nbytes >= 2 * AES_BLOCK_SIZE) {
+		do {
 			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
 
-			kernel_neon_begin();
+			if (rk)
+				kernel_neon_begin();
+
 			pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, ctx->h2, iv,
-					  ctx->aes_key.key_enc, nrounds, ks);
+					  rk, nrounds, ks);
 			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
 					walk.nbytes % (2 * AES_BLOCK_SIZE));
-		}
+
+			rk = ctx->aes_key.key_enc;
+		} while (walk.nbytes >= 2 * AES_BLOCK_SIZE);
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		err = skcipher_walk_aead_encrypt(&walk, req, false);
-
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 			u8 *dst = walk.dst.virt.addr;
@@ -485,50 +487,53 @@ static int gcm_decrypt(struct aead_request *req)
 	memcpy(iv, req->iv, GCM_IV_SIZE);
 	put_unaligned_be32(1, iv + GCM_IV_SIZE);
 
-	if (likely(may_use_simd())) {
+	err = skcipher_walk_aead_decrypt(&walk, req, false);
+
+	if (likely(may_use_simd() && walk.total >= 2 * AES_BLOCK_SIZE)) {
+		u32 const *rk = NULL;
+
 		kernel_neon_begin();
 		pmull_gcm_encrypt_block(tag, iv, ctx->aes_key.key_enc, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
-		kernel_neon_end();
 
-		err = skcipher_walk_aead_decrypt(&walk, req, false);
-
-		while (walk.nbytes >= 2 * AES_BLOCK_SIZE) {
+		do {
 			int blocks = walk.nbytes / (2 * AES_BLOCK_SIZE) * 2;
+			int rem = walk.total - blocks * AES_BLOCK_SIZE;
+
+			if (rk)
+				kernel_neon_begin();
 
-			kernel_neon_begin();
 			pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
 					  walk.src.virt.addr, ctx->h2, iv,
-					  ctx->aes_key.key_enc, nrounds);
-			kernel_neon_end();
+					  rk, nrounds);
 
-			err = skcipher_walk_done(&walk,
-					walk.nbytes % (2 * AES_BLOCK_SIZE));
-		}
+			/* check if this is the final iteration of the loop */
+			if (rem < (2 * AES_BLOCK_SIZE)) {
+				u8 *iv2 = iv + AES_BLOCK_SIZE;
 
-		if (walk.nbytes) {
-			u8 *iv2 = iv + AES_BLOCK_SIZE;
+				if (rem > AES_BLOCK_SIZE) {
+					memcpy(iv2, iv, AES_BLOCK_SIZE);
+					crypto_inc(iv2, AES_BLOCK_SIZE);
+				}
 
-			if (walk.nbytes > AES_BLOCK_SIZE) {
-				memcpy(iv2, iv, AES_BLOCK_SIZE);
-				crypto_inc(iv2, AES_BLOCK_SIZE);
-			}
+				pmull_gcm_encrypt_block(iv, iv, NULL, nrounds);
 
-			kernel_neon_begin();
-			pmull_gcm_encrypt_block(iv, iv, ctx->aes_key.key_enc,
-						nrounds);
+				if (rem > AES_BLOCK_SIZE)
+					pmull_gcm_encrypt_block(iv2, iv2, NULL,
+								nrounds);
+			}
 
-			if (walk.nbytes > AES_BLOCK_SIZE)
-				pmull_gcm_encrypt_block(iv2, iv2, NULL,
-							nrounds);
 			kernel_neon_end();
-		}
+
+			err = skcipher_walk_done(&walk,
+					walk.nbytes % (2 * AES_BLOCK_SIZE));
+
+			rk = ctx->aes_key.key_enc;
+		} while (walk.nbytes >= 2 * AES_BLOCK_SIZE);
 	} else {
 		__aes_arm64_encrypt(ctx->aes_key.key_enc, tag, iv, nrounds);
 		put_unaligned_be32(2, iv + GCM_IV_SIZE);
 
-		err = skcipher_walk_aead_decrypt(&walk, req, false);
-
 		while (walk.nbytes >= AES_BLOCK_SIZE) {
 			int blocks = walk.nbytes / AES_BLOCK_SIZE;
 			u8 *dst = walk.dst.virt.addr;
-- 
cgit v1.2.3


From 6122bbbdc65630d202e5494d5b9678676f2883f8 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 30 Jul 2018 09:59:36 +0100
Subject: lib/mpi: remove redundant variable esign

Variable esign is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'esign' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 lib/mpi/mpi-pow.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/lib/mpi/mpi-pow.c b/lib/mpi/mpi-pow.c
index 468fb7cd1221..a5c921e6d667 100644
--- a/lib/mpi/mpi-pow.c
+++ b/lib/mpi/mpi-pow.c
@@ -41,7 +41,7 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod)
 	mpi_ptr_t tspace = NULL;
 	mpi_ptr_t rp, ep, mp, bp;
 	mpi_size_t esize, msize, bsize, rsize;
-	int esign, msign, bsign, rsign;
+	int msign, bsign, rsign;
 	mpi_size_t size;
 	int mod_shift_cnt;
 	int negative_result;
@@ -53,7 +53,6 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod)
 	esize = exp->nlimbs;
 	msize = mod->nlimbs;
 	size = 2 * msize;
-	esign = exp->sign;
 	msign = mod->sign;
 
 	rp = res->d;
-- 
cgit v1.2.3


From 8418cf54df0c22332e0cd855b9e1e7aac3fab20e Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Sat, 4 Aug 2018 06:21:01 +0800
Subject: crypto: hisilicon - sec_send_request() can be static

Fixes: 915e4e8413da ("crypto: hisilicon - SEC security accelerator driver")
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/sec/sec_algs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/crypto/hisilicon/sec/sec_algs.c b/drivers/crypto/hisilicon/sec/sec_algs.c
index d69d3ce358b0..f7d6d690116e 100644
--- a/drivers/crypto/hisilicon/sec/sec_algs.c
+++ b/drivers/crypto/hisilicon/sec/sec_algs.c
@@ -393,7 +393,7 @@ static void sec_alg_free_el(struct sec_request_el *el,
 }
 
 /* queuelock must be held */
-int sec_send_request(struct sec_request *sec_req, struct sec_queue *queue)
+static int sec_send_request(struct sec_request *sec_req, struct sec_queue *queue)
 {
 	struct sec_request_el *el, *temp;
 	int ret = 0;
-- 
cgit v1.2.3


From 8e492eff7de955e6ed1dc2989b17c41cd862aa28 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Sat, 4 Aug 2018 20:46:24 +0200
Subject: crypto: arm64/ghash-ce - replace NEON yield check with block limit

Checking the TIF_NEED_RESCHED flag is disproportionately costly on cores
with fast crypto instructions and comparatively slow memory accesses.

On algorithms such as GHASH, which executes at ~1 cycle per byte on
cores that implement support for 64 bit polynomial multiplication,
there is really no need to check the TIF_NEED_RESCHED particularly
often, and so we can remove the NEON yield check from the assembler
routines.

However, unlike the AEAD or skcipher APIs, the shash/ahash APIs take
arbitrary input lengths, and so there needs to be some sanity check
to ensure that we don't hog the CPU for excessive amounts of time.

So let's simply cap the maximum input size that is processed in one go
to 64 KB.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm64/crypto/ghash-ce-core.S | 39 +++++++++++----------------------------
 arch/arm64/crypto/ghash-ce-glue.c | 16 ++++++++++++----
 2 files changed, 23 insertions(+), 32 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 913e49932ae6..344811c6a0ca 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -213,31 +213,23 @@
 	.endm
 
 	.macro		__pmull_ghash, pn
-	frame_push	5
-
-	mov		x19, x0
-	mov		x20, x1
-	mov		x21, x2
-	mov		x22, x3
-	mov		x23, x4
-
-0:	ld1		{SHASH.2d}, [x22]
-	ld1		{XL.2d}, [x20]
+	ld1		{SHASH.2d}, [x3]
+	ld1		{XL.2d}, [x1]
 	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
 	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	__pmull_pre_\pn
 
 	/* do the head block first, if supplied */
-	cbz		x23, 1f
-	ld1		{T1.2d}, [x23]
-	mov		x23, xzr
-	b		2f
+	cbz		x4, 0f
+	ld1		{T1.2d}, [x4]
+	mov		x4, xzr
+	b		1f
 
-1:	ld1		{T1.2d}, [x21], #16
-	sub		w19, w19, #1
+0:	ld1		{T1.2d}, [x2], #16
+	sub		w0, w0, #1
 
-2:	/* multiply XL by SHASH in GF(2^128) */
+1:	/* multiply XL by SHASH in GF(2^128) */
 CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	ext		T2.16b, XL.16b, XL.16b, #8
@@ -259,18 +251,9 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 	eor		T2.16b, T2.16b, XH.16b
 	eor		XL.16b, XL.16b, T2.16b
 
-	cbz		w19, 3f
-
-	if_will_cond_yield_neon
-	st1		{XL.2d}, [x20]
-	do_cond_yield_neon
-	b		0b
-	endif_yield_neon
-
-	b		1b
+	cbnz		w0, 0b
 
-3:	st1		{XL.2d}, [x20]
-	frame_pop
+	st1		{XL.2d}, [x1]
 	ret
 	.endm
 
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 42a0e84e276c..3c2c446dc96c 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -113,6 +113,9 @@ static void ghash_do_update(int blocks, u64 dg[], const char *src,
 	}
 }
 
+/* avoid hogging the CPU for too long */
+#define MAX_BLOCKS	(SZ_64K / GHASH_BLOCK_SIZE)
+
 static int ghash_update(struct shash_desc *desc, const u8 *src,
 			unsigned int len)
 {
@@ -136,11 +139,16 @@ static int ghash_update(struct shash_desc *desc, const u8 *src,
 		blocks = len / GHASH_BLOCK_SIZE;
 		len %= GHASH_BLOCK_SIZE;
 
-		ghash_do_update(blocks, ctx->digest, src, key,
-				partial ? ctx->buf : NULL);
+		do {
+			int chunk = min(blocks, MAX_BLOCKS);
+
+			ghash_do_update(chunk, ctx->digest, src, key,
+					partial ? ctx->buf : NULL);
 
-		src += blocks * GHASH_BLOCK_SIZE;
-		partial = 0;
+			blocks -= chunk;
+			src += chunk * GHASH_BLOCK_SIZE;
+			partial = 0;
+		} while (unlikely(blocks > 0));
 	}
 	if (len)
 		memcpy(ctx->buf + partial, src, len);
-- 
cgit v1.2.3


From 22240df7ac6d76a271197571a7be45addef2ba15 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Date: Sat, 4 Aug 2018 20:46:25 +0200
Subject: crypto: arm64/ghash-ce - implement 4-way aggregation

Enhance the GHASH implementation that uses 64-bit polynomial
multiplication by adding support for 4-way aggregation. This
more than doubles the performance, from 2.4 cycles per byte
to 1.1 cpb on Cortex-A53.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 arch/arm64/crypto/ghash-ce-core.S | 122 ++++++++++++++++++++++++++++++++------
 arch/arm64/crypto/ghash-ce-glue.c |  71 +++++++++++-----------
 2 files changed, 142 insertions(+), 51 deletions(-)

diff --git a/arch/arm64/crypto/ghash-ce-core.S b/arch/arm64/crypto/ghash-ce-core.S
index 344811c6a0ca..1b319b716d5e 100644
--- a/arch/arm64/crypto/ghash-ce-core.S
+++ b/arch/arm64/crypto/ghash-ce-core.S
@@ -46,6 +46,19 @@
 	ss3		.req	v26
 	ss4		.req	v27
 
+	XL2		.req	v8
+	XM2		.req	v9
+	XH2		.req	v10
+	XL3		.req	v11
+	XM3		.req	v12
+	XH3		.req	v13
+	TT3		.req	v14
+	TT4		.req	v15
+	HH		.req	v16
+	HH3		.req	v17
+	HH4		.req	v18
+	HH34		.req	v19
+
 	.text
 	.arch		armv8-a+crypto
 
@@ -134,11 +147,25 @@
 	.endm
 
 	.macro		__pmull_pre_p64
+	add		x8, x3, #16
+	ld1		{HH.2d-HH4.2d}, [x8]
+
+	trn1		SHASH2.2d, SHASH.2d, HH.2d
+	trn2		T1.2d, SHASH.2d, HH.2d
+	eor		SHASH2.16b, SHASH2.16b, T1.16b
+
+	trn1		HH34.2d, HH3.2d, HH4.2d
+	trn2		T1.2d, HH3.2d, HH4.2d
+	eor		HH34.16b, HH34.16b, T1.16b
+
 	movi		MASK.16b, #0xe1
 	shl		MASK.2d, MASK.2d, #57
 	.endm
 
 	.macro		__pmull_pre_p8
+	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
+	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
+
 	// k00_16 := 0x0000000000000000_000000000000ffff
 	// k32_48 := 0x00000000ffffffff_0000ffffffffffff
 	movi		k32_48.2d, #0xffffffff
@@ -215,8 +242,6 @@
 	.macro		__pmull_ghash, pn
 	ld1		{SHASH.2d}, [x3]
 	ld1		{XL.2d}, [x1]
-	ext		SHASH2.16b, SHASH.16b, SHASH.16b, #8
-	eor		SHASH2.16b, SHASH2.16b, SHASH.16b
 
 	__pmull_pre_\pn
 
@@ -224,12 +249,79 @@
 	cbz		x4, 0f
 	ld1		{T1.2d}, [x4]
 	mov		x4, xzr
-	b		1f
+	b		3f
+
+0:	.ifc		\pn, p64
+	tbnz		w0, #0, 2f		// skip until #blocks is a
+	tbnz		w0, #1, 2f		// round multiple of 4
+
+1:	ld1		{XM3.16b-TT4.16b}, [x2], #64
+
+	sub		w0, w0, #4
+
+	rev64		T1.16b, XM3.16b
+	rev64		T2.16b, XH3.16b
+	rev64		TT4.16b, TT4.16b
+	rev64		TT3.16b, TT3.16b
+
+	ext		IN1.16b, TT4.16b, TT4.16b, #8
+	ext		XL3.16b, TT3.16b, TT3.16b, #8
+
+	eor		TT4.16b, TT4.16b, IN1.16b
+	pmull2		XH2.1q, SHASH.2d, IN1.2d	// a1 * b1
+	pmull		XL2.1q, SHASH.1d, IN1.1d	// a0 * b0
+	pmull		XM2.1q, SHASH2.1d, TT4.1d	// (a1 + a0)(b1 + b0)
+
+	eor		TT3.16b, TT3.16b, XL3.16b
+	pmull2		XH3.1q, HH.2d, XL3.2d		// a1 * b1
+	pmull		XL3.1q, HH.1d, XL3.1d		// a0 * b0
+	pmull2		XM3.1q, SHASH2.2d, TT3.2d	// (a1 + a0)(b1 + b0)
+
+	ext		IN1.16b, T2.16b, T2.16b, #8
+	eor		XL2.16b, XL2.16b, XL3.16b
+	eor		XH2.16b, XH2.16b, XH3.16b
+	eor		XM2.16b, XM2.16b, XM3.16b
+
+	eor		T2.16b, T2.16b, IN1.16b
+	pmull2		XH3.1q, HH3.2d, IN1.2d		// a1 * b1
+	pmull		XL3.1q, HH3.1d, IN1.1d		// a0 * b0
+	pmull		XM3.1q, HH34.1d, T2.1d		// (a1 + a0)(b1 + b0)
 
-0:	ld1		{T1.2d}, [x2], #16
+	eor		XL2.16b, XL2.16b, XL3.16b
+	eor		XH2.16b, XH2.16b, XH3.16b
+	eor		XM2.16b, XM2.16b, XM3.16b
+
+	ext		IN1.16b, T1.16b, T1.16b, #8
+	ext		TT3.16b, XL.16b, XL.16b, #8
+	eor		XL.16b, XL.16b, IN1.16b
+	eor		T1.16b, T1.16b, TT3.16b
+
+	pmull2		XH.1q, HH4.2d, XL.2d		// a1 * b1
+	eor		T1.16b, T1.16b, XL.16b
+	pmull		XL.1q, HH4.1d, XL.1d		// a0 * b0
+	pmull2		XM.1q, HH34.2d, T1.2d		// (a1 + a0)(b1 + b0)
+
+	eor		XL.16b, XL.16b, XL2.16b
+	eor		XH.16b, XH.16b, XH2.16b
+	eor		XM.16b, XM.16b, XM2.16b
+
+	eor		T2.16b, XL.16b, XH.16b
+	ext		T1.16b, XL.16b, XH.16b, #8
+	eor		XM.16b, XM.16b, T2.16b
+
+	__pmull_reduce_p64
+
+	eor		T2.16b, T2.16b, XH.16b
+	eor		XL.16b, XL.16b, T2.16b
+
+	cbz		w0, 5f
+	b		1b
+	.endif
+
+2:	ld1		{T1.2d}, [x2], #16
 	sub		w0, w0, #1
 
-1:	/* multiply XL by SHASH in GF(2^128) */
+3:	/* multiply XL by SHASH in GF(2^128) */
 CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	ext		T2.16b, XL.16b, XL.16b, #8
@@ -242,7 +334,7 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 	__pmull_\pn 	XL, XL, SHASH			// a0 * b0
 	__pmull_\pn	XM, T1, SHASH2			// (a1 + a0)(b1 + b0)
 
-	eor		T2.16b, XL.16b, XH.16b
+4:	eor		T2.16b, XL.16b, XH.16b
 	ext		T1.16b, XL.16b, XH.16b, #8
 	eor		XM.16b, XM.16b, T2.16b
 
@@ -253,7 +345,7 @@ CPU_LE(	rev64		T1.16b, T1.16b	)
 
 	cbnz		w0, 0b
 
-	st1		{XL.2d}, [x1]
+5:	st1		{XL.2d}, [x1]
 	ret
 	.endm
 
@@ -269,14 +361,10 @@ ENTRY(pmull_ghash_update_p8)
 	__pmull_ghash	p8
 ENDPROC(pmull_ghash_update_p8)
 
-	KS0		.req	v8
-	KS1		.req	v9
-	INP0		.req	v10
-	INP1		.req	v11
-	HH		.req	v12
-	XL2		.req	v13
-	XM2		.req	v14
-	XH2		.req	v15
+	KS0		.req	v12
+	KS1		.req	v13
+	INP0		.req	v14
+	INP1		.req	v15
 
 	.macro		load_round_keys, rounds, rk
 	cmp		\rounds, #12
@@ -310,8 +398,8 @@ ENDPROC(pmull_ghash_update_p8)
 	.endm
 
 	.macro		pmull_gcm_do_crypt, enc
-	ld1		{HH.2d}, [x4], #16
-	ld1		{SHASH.2d}, [x4]
+	ld1		{SHASH.2d}, [x4], #16
+	ld1		{HH.2d}, [x4]
 	ld1		{XL.2d}, [x1]
 	ldr		x8, [x5, #8]			// load lower counter
 
diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c
index 3c2c446dc96c..6e9f33d14930 100644
--- a/arch/arm64/crypto/ghash-ce-glue.c
+++ b/arch/arm64/crypto/ghash-ce-glue.c
@@ -33,9 +33,12 @@ MODULE_ALIAS_CRYPTO("ghash");
 #define GCM_IV_SIZE		12
 
 struct ghash_key {
-	u64 a;
-	u64 b;
-	be128 k;
+	u64			h[2];
+	u64			h2[2];
+	u64			h3[2];
+	u64			h4[2];
+
+	be128			k;
 };
 
 struct ghash_desc_ctx {
@@ -46,7 +49,6 @@ struct ghash_desc_ctx {
 
 struct gcm_aes_ctx {
 	struct crypto_aes_ctx	aes_key;
-	u64			h2[2];
 	struct ghash_key	ghash_key;
 };
 
@@ -63,11 +65,12 @@ static void (*pmull_ghash_update)(int blocks, u64 dg[], const char *src,
 				  const char *head);
 
 asmlinkage void pmull_gcm_encrypt(int blocks, u64 dg[], u8 dst[],
-				  const u8 src[], u64 const *k, u8 ctr[],
-				  u32 const rk[], int rounds, u8 ks[]);
+				  const u8 src[], struct ghash_key const *k,
+				  u8 ctr[], u32 const rk[], int rounds,
+				  u8 ks[]);
 
 asmlinkage void pmull_gcm_decrypt(int blocks, u64 dg[], u8 dst[],
-				  const u8 src[], u64 const *k,
+				  const u8 src[], struct ghash_key const *k,
 				  u8 ctr[], u32 const rk[], int rounds);
 
 asmlinkage void pmull_gcm_encrypt_block(u8 dst[], u8 const src[],
@@ -174,23 +177,36 @@ static int ghash_final(struct shash_desc *desc, u8 *dst)
 	return 0;
 }
 
+static void ghash_reflect(u64 h[], const be128 *k)
+{
+	u64 carry = be64_to_cpu(k->a) & BIT(63) ? 1 : 0;
+
+	h[0] = (be64_to_cpu(k->b) << 1) | carry;
+	h[1] = (be64_to_cpu(k->a) << 1) | (be64_to_cpu(k->b) >> 63);
+
+	if (carry)
+		h[1] ^= 0xc200000000000000UL;
+}
+
 static int __ghash_setkey(struct ghash_key *key,
 			  const u8 *inkey, unsigned int keylen)
 {
-	u64 a, b;
+	be128 h;
 
 	/* needed for the fallback */
 	memcpy(&key->k, inkey, GHASH_BLOCK_SIZE);
 
-	/* perform multiplication by 'x' in GF(2^128) */
-	b = get_unaligned_be64(inkey);
-	a = get_unaligned_be64(inkey + 8);
+	ghash_reflect(key->h, &key->k);
+
+	h = key->k;
+	gf128mul_lle(&h, &key->k);
+	ghash_reflect(key->h2, &h);
 
-	key->a = (a << 1) | (b >> 63);
-	key->b = (b << 1) | (a >> 63);
+	gf128mul_lle(&h, &key->k);
+	ghash_reflect(key->h3, &h);
 
-	if (b >> 63)
-		key->b ^= 0xc200000000000000UL;
+	gf128mul_lle(&h, &key->k);
+	ghash_reflect(key->h4, &h);
 
 	return 0;
 }
@@ -240,8 +256,7 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 		      unsigned int keylen)
 {
 	struct gcm_aes_ctx *ctx = crypto_aead_ctx(tfm);
-	be128 h1, h2;
-	u8 *key = (u8 *)&h1;
+	u8 key[GHASH_BLOCK_SIZE];
 	int ret;
 
 	ret = crypto_aes_expand_key(&ctx->aes_key, inkey, keylen);
@@ -253,19 +268,7 @@ static int gcm_setkey(struct crypto_aead *tfm, const u8 *inkey,
 	__aes_arm64_encrypt(ctx->aes_key.key_enc, key, (u8[AES_BLOCK_SIZE]){},
 			    num_rounds(&ctx->aes_key));
 
-	__ghash_setkey(&ctx->ghash_key, key, sizeof(be128));
-
-	/* calculate H^2 (used for 2-way aggregation) */
-	h2 = h1;
-	gf128mul_lle(&h2, &h1);
-
-	ctx->h2[0] = (be64_to_cpu(h2.b) << 1) | (be64_to_cpu(h2.a) >> 63);
-	ctx->h2[1] = (be64_to_cpu(h2.a) << 1) | (be64_to_cpu(h2.b) >> 63);
-
-	if (be64_to_cpu(h2.a) >> 63)
-		ctx->h2[1] ^= 0xc200000000000000UL;
-
-	return 0;
+	return __ghash_setkey(&ctx->ghash_key, key, sizeof(be128));
 }
 
 static int gcm_setauthsize(struct crypto_aead *tfm, unsigned int authsize)
@@ -401,8 +404,8 @@ static int gcm_encrypt(struct aead_request *req)
 				kernel_neon_begin();
 
 			pmull_gcm_encrypt(blocks, dg, walk.dst.virt.addr,
-					  walk.src.virt.addr, ctx->h2, iv,
-					  rk, nrounds, ks);
+					  walk.src.virt.addr, &ctx->ghash_key,
+					  iv, rk, nrounds, ks);
 			kernel_neon_end();
 
 			err = skcipher_walk_done(&walk,
@@ -512,8 +515,8 @@ static int gcm_decrypt(struct aead_request *req)
 				kernel_neon_begin();
 
 			pmull_gcm_decrypt(blocks, dg, walk.dst.virt.addr,
-					  walk.src.virt.addr, ctx->h2, iv,
-					  rk, nrounds);
+					  walk.src.virt.addr, &ctx->ghash_key,
+					  iv, rk, nrounds);
 
 			/* check if this is the final iteration of the loop */
 			if (rem < (2 * AES_BLOCK_SIZE)) {
-- 
cgit v1.2.3


From 132f3c7bb98673f713be9511de16b7622803df36 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 05:52:36 -0400
Subject: media: imx: shut up a false positive warning

With imx, gcc produces a false positive warning:

	drivers/staging/media/imx/imx-media-csi.c: In function 'csi_idmac_setup_channel':
	drivers/staging/media/imx/imx-media-csi.c:457:6: warning: this statement may fall through [-Wimplicit-fallthrough=]
	   if (passthrough) {
	      ^
	drivers/staging/media/imx/imx-media-csi.c:464:2: note: here
	  default:
	  ^~~~~~~

That's because the regex it uses for fall trough is not
good enough. So, rearrange the fall through comment in a way
that gcc will recognize.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/staging/media/imx/imx-media-csi.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index 4647206f92ca..b7ffd231c64b 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -460,7 +460,8 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 			passthrough_cycles = incc->cycles;
 			break;
 		}
-		/* fallthrough for non-passthrough RGB565 (CSI-2 bus) */
+		/* for non-passthrough RGB565 (CSI-2 bus) */
+		/* Falls through */
 	default:
 		burst_size = (image.pix.width & 0xf) ? 8 : 16;
 		passthrough_bits = 16;
-- 
cgit v1.2.3


From 4effa8bfe4f6bacd041f98775f49cdc550502dc2 Mon Sep 17 00:00:00 2001
From: Jasmin Jessich <jasmin@anw.at>
Date: Sat, 28 Jul 2018 09:54:49 -0400
Subject: media: i2c: fix warning in Aptina MT9V111

This fixes the "'idx' may be used uninitialized in this function"
warning:

	drivers/media/i2c/mt9v111.c: In function 'mt9v111_set_format':
	drivers/media/i2c/mt9v111.c:887:15: warning: 'idx' may be used uninitialized in this function [-Wmaybe-uninitialized]
	  unsigned int idx;
	               ^~~

Signed-off-by: Jasmin Jessich <jasmin@anw.at>
Acked-by: Jacopo Mondi <jacopo@jmondi.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/mt9v111.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
index da8f6ab91307..58d5f2224bff 100644
--- a/drivers/media/i2c/mt9v111.c
+++ b/drivers/media/i2c/mt9v111.c
@@ -884,7 +884,7 @@ static int mt9v111_set_format(struct v4l2_subdev *subdev,
 	struct v4l2_mbus_framefmt new_fmt;
 	struct v4l2_mbus_framefmt *__fmt;
 	unsigned int best_fit = ~0L;
-	unsigned int idx;
+	unsigned int idx = 0;
 	unsigned int i;
 
 	mutex_lock(&mt9v111->stream_mutex);
-- 
cgit v1.2.3


From b07b684930fe0b8032bddba5aa60686011932019 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 06:06:17 -0400
Subject: media: v4l2-mem2mem: add descriptions to MC fields

drivers/media/v4l2-core/v4l2-mem2mem.c:90: warning: Function parameter or member 'source_pad' not described in 'v4l2_m2m_dev'
drivers/media/v4l2-core/v4l2-mem2mem.c:90: warning: Function parameter or member 'sink' not described in 'v4l2_m2m_dev'
drivers/media/v4l2-core/v4l2-mem2mem.c:90: warning: Function parameter or member 'sink_pad' not described in 'v4l2_m2m_dev'
drivers/media/v4l2-core/v4l2-mem2mem.c:90: warning: Function parameter or member 'proc' not described in 'v4l2_m2m_dev'
drivers/media/v4l2-core/v4l2-mem2mem.c:90: warning: Function parameter or member 'proc_pads' not described in 'v4l2_m2m_dev'
drivers/media/v4l2-core/v4l2-mem2mem.c:90: warning: Function parameter or member 'intf_devnode' not described in 'v4l2_m2m_dev'

Fixes: be2fff656322 ("media: add helpers for memory-to-memory media controller")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/v4l2-core/v4l2-mem2mem.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/media/v4l2-core/v4l2-mem2mem.c b/drivers/media/v4l2-core/v4l2-mem2mem.c
index 0a93c5b173c2..ce9bd1b91210 100644
--- a/drivers/media/v4l2-core/v4l2-mem2mem.c
+++ b/drivers/media/v4l2-core/v4l2-mem2mem.c
@@ -66,6 +66,24 @@ static const char * const m2m_entity_name[] = {
 
 /**
  * struct v4l2_m2m_dev - per-device context
+ * @source:		&struct media_entity pointer with the source entity
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @source_pad:		&struct media_pad with the source pad.
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @sink:		&struct media_entity pointer with the sink entity
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @sink_pad:		&struct media_pad with the sink pad.
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @proc:		&struct media_entity pointer with the M2M device itself.
+ * @proc_pads:		&struct media_pad with the @proc pads.
+ *			Used only when the M2M device is registered via
+ *			v4l2_m2m_unregister_media_controller().
+ * @intf_devnode:	&struct media_intf devnode pointer with the interface
+ *			with controls the M2M device.
  * @curr_ctx:		currently running instance
  * @job_queue:		instances queued to run
  * @job_spinlock:	protects job_queue
-- 
cgit v1.2.3


From 51be5a2b43f86af40b3fb78d7e4a22b5357fbc0d Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 06:13:36 -0400
Subject: media: sta2x11: add a missing parameter description

Fixes this warning:
	drivers/media/pci/sta2x11/sta2x11_vip.c:156: warning: Function parameter or member 'v4l_lock' not described in 'sta2x11_vip'

Fixes: cd63c0288fd7 ("media: sta2x11: Add video_device and vb2_queue locks")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/sta2x11/sta2x11_vip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/media/pci/sta2x11/sta2x11_vip.c b/drivers/media/pci/sta2x11/sta2x11_vip.c
index da2b2a2292d0..1858efedaf1a 100644
--- a/drivers/media/pci/sta2x11/sta2x11_vip.c
+++ b/drivers/media/pci/sta2x11/sta2x11_vip.c
@@ -116,6 +116,7 @@ static inline struct vip_buffer *to_vip_buffer(struct vb2_v4l2_buffer *vb2)
  * @sequence: sequence number of acquired buffer
  * @active: current active buffer
  * @lock: used in videobuf2 callback
+ * @v4l_lock: serialize its video4linux ioctls
  * @tcount: Number of top frames
  * @bcount: Number of bottom frames
  * @overflow: Number of FIFO overflows
-- 
cgit v1.2.3


From bc2d8d262cba5736332cbc866acb11b1c5748aa9 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 7 Aug 2018 08:19:57 +0200
Subject: cpu/hotplug: Fix SMT supported evaluation

Josh reported that the late SMT evaluation in cpu_smt_state_init() sets
cpu_smt_control to CPU_SMT_NOT_SUPPORTED in case that 'nosmt' was supplied
on the kernel command line as it cannot differentiate between SMT disabled
by BIOS and SMT soft disable via 'nosmt'. That wreckages the state and
makes the sysfs interface unusable.

Rework this so that during bringup of the non boot CPUs the availability of
SMT is determined in cpu_smt_allowed(). If a newly booted CPU is not a
'primary' thread then set the local cpu_smt_available marker and evaluate
this explicitely right after the initial SMP bringup has finished.

SMT evaulation on x86 is a trainwreck as the firmware has all the
information _before_ booting the kernel, but there is no interface to query
it.

Fixes: 73d5e2b47264 ("cpu/hotplug: detect SMT disabled by BIOS")
Reported-by: Josh Poimboeuf <jpoimboe@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/bugs.c |  2 +-
 include/linux/cpu.h        |  2 ++
 kernel/cpu.c               | 41 ++++++++++++++++++++++++++++-------------
 kernel/smp.c               |  2 ++
 4 files changed, 33 insertions(+), 14 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 86f4549b7c9f..be79b7599dda 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -63,7 +63,7 @@ void __init check_bugs(void)
 	 * identify_boot_cpu() initialized SMT support information, let the
 	 * core code know.
 	 */
-	cpu_smt_check_topology();
+	cpu_smt_check_topology_early();
 
 	if (!IS_ENABLED(CONFIG_SMP)) {
 		pr_info("CPU: ");
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index ccdf3a67ce56..b216bd5bfd20 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -178,10 +178,12 @@ enum cpuhp_smt_control {
 #if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
 extern enum cpuhp_smt_control cpu_smt_control;
 extern void cpu_smt_disable(bool force);
+extern void cpu_smt_check_topology_early(void);
 extern void cpu_smt_check_topology(void);
 #else
 # define cpu_smt_control		(CPU_SMT_ENABLED)
 static inline void cpu_smt_disable(bool force) { }
+static inline void cpu_smt_check_topology_early(void) { }
 static inline void cpu_smt_check_topology(void) { }
 #endif
 
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 2bc3d2f5b2a5..9d2512dd263c 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -347,6 +347,8 @@ EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED;
 EXPORT_SYMBOL_GPL(cpu_smt_control);
 
+static bool cpu_smt_available __read_mostly;
+
 void __init cpu_smt_disable(bool force)
 {
 	if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
@@ -363,14 +365,28 @@ void __init cpu_smt_disable(bool force)
 
 /*
  * The decision whether SMT is supported can only be done after the full
- * CPU identification. Called from architecture code.
+ * CPU identification. Called from architecture code before non boot CPUs
+ * are brought up.
  */
-void __init cpu_smt_check_topology(void)
+void __init cpu_smt_check_topology_early(void)
 {
 	if (!topology_smt_supported())
 		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
 }
 
+/*
+ * If SMT was disabled by BIOS, detect it here, after the CPUs have been
+ * brought online. This ensures the smt/l1tf sysfs entries are consistent
+ * with reality. cpu_smt_available is set to true during the bringup of non
+ * boot CPUs when a SMT sibling is detected. Note, this may overwrite
+ * cpu_smt_control's previous setting.
+ */
+void __init cpu_smt_check_topology(void)
+{
+	if (!cpu_smt_available)
+		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
+}
+
 static int __init smt_cmdline_disable(char *str)
 {
 	cpu_smt_disable(str && !strcmp(str, "force"));
@@ -380,10 +396,18 @@ early_param("nosmt", smt_cmdline_disable);
 
 static inline bool cpu_smt_allowed(unsigned int cpu)
 {
-	if (cpu_smt_control == CPU_SMT_ENABLED)
+	if (topology_is_primary_thread(cpu))
 		return true;
 
-	if (topology_is_primary_thread(cpu))
+	/*
+	 * If the CPU is not a 'primary' thread and the booted_once bit is
+	 * set then the processor has SMT support. Store this information
+	 * for the late check of SMT support in cpu_smt_check_topology().
+	 */
+	if (per_cpu(cpuhp_state, cpu).booted_once)
+		cpu_smt_available = true;
+
+	if (cpu_smt_control == CPU_SMT_ENABLED)
 		return true;
 
 	/*
@@ -2125,15 +2149,6 @@ static const struct attribute_group cpuhp_smt_attr_group = {
 
 static int __init cpu_smt_state_init(void)
 {
-	/*
-	 * If SMT was disabled by BIOS, detect it here, after the CPUs have
-	 * been brought online.  This ensures the smt/l1tf sysfs entries are
-	 * consistent with reality.  Note this may overwrite cpu_smt_control's
-	 * previous setting.
-	 */
-	if (topology_max_smt_threads() == 1)
-		cpu_smt_control = CPU_SMT_NOT_SUPPORTED;
-
 	return sysfs_create_group(&cpu_subsys.dev_root->kobj,
 				  &cpuhp_smt_attr_group);
 }
diff --git a/kernel/smp.c b/kernel/smp.c
index 084c8b3a2681..d86eec5f51c1 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -584,6 +584,8 @@ void __init smp_init(void)
 		num_nodes, (num_nodes > 1 ? "s" : ""),
 		num_cpus,  (num_cpus  > 1 ? "s" : ""));
 
+	/* Final decision about SMT support */
+	cpu_smt_check_topology();
 	/* Any cleanup work */
 	smp_cpus_done(setup_max_cpus);
 }
-- 
cgit v1.2.3


From 5eda25b10297684c1f46a14199ec00210f3c346e Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Mon, 6 Aug 2018 13:49:47 +0200
Subject: s390/lib: use expoline for all bcr instructions

The memove, memset, memcpy, __memset16, __memset32 and __memset64
function have an additional indirect return branch in form of a
"bzr" instruction. These need to use expolines as well.

Cc: <stable@vger.kernel.org> # v4.17+
Fixes: 97489e0663 ("s390/lib: use expoline for indirect branches")
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/lib/mem.S | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index 2311f15be9cf..40c4d59c926e 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -17,7 +17,7 @@
 ENTRY(memmove)
 	ltgr	%r4,%r4
 	lgr	%r1,%r2
-	bzr	%r14
+	jz	.Lmemmove_exit
 	aghi	%r4,-1
 	clgr	%r2,%r3
 	jnh	.Lmemmove_forward
@@ -36,6 +36,7 @@ ENTRY(memmove)
 .Lmemmove_forward_remainder:
 	larl	%r5,.Lmemmove_mvc
 	ex	%r4,0(%r5)
+.Lmemmove_exit:
 	BR_EX	%r14
 .Lmemmove_reverse:
 	ic	%r0,0(%r4,%r3)
@@ -65,7 +66,7 @@ EXPORT_SYMBOL(memmove)
  */
 ENTRY(memset)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemset_exit
 	ltgr	%r3,%r3
 	jnz	.Lmemset_fill
 	aghi	%r4,-1
@@ -80,6 +81,7 @@ ENTRY(memset)
 .Lmemset_clear_remainder:
 	larl	%r3,.Lmemset_xc
 	ex	%r4,0(%r3)
+.Lmemset_exit:
 	BR_EX	%r14
 .Lmemset_fill:
 	cghi	%r4,1
@@ -115,7 +117,7 @@ EXPORT_SYMBOL(memset)
  */
 ENTRY(memcpy)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.Lmemcpy_exit
 	aghi	%r4,-1
 	srlg	%r5,%r4,8
 	ltgr	%r5,%r5
@@ -124,6 +126,7 @@ ENTRY(memcpy)
 .Lmemcpy_remainder:
 	larl	%r5,.Lmemcpy_mvc
 	ex	%r4,0(%r5)
+.Lmemcpy_exit:
 	BR_EX	%r14
 .Lmemcpy_loop:
 	mvc	0(256,%r1),0(%r3)
@@ -145,9 +148,9 @@ EXPORT_SYMBOL(memcpy)
 .macro __MEMSET bits,bytes,insn
 ENTRY(__memset\bits)
 	ltgr	%r4,%r4
-	bzr	%r14
+	jz	.L__memset_exit\bits
 	cghi	%r4,\bytes
-	je	.L__memset_exit\bits
+	je	.L__memset_store\bits
 	aghi	%r4,-(\bytes+1)
 	srlg	%r5,%r4,8
 	ltgr	%r5,%r5
@@ -163,8 +166,9 @@ ENTRY(__memset\bits)
 	larl	%r5,.L__memset_mvc\bits
 	ex	%r4,0(%r5)
 	BR_EX	%r14
-.L__memset_exit\bits:
+.L__memset_store\bits:
 	\insn	%r3,0(%r2)
+.L__memset_exit\bits:
 	BR_EX	%r14
 .L__memset_mvc\bits:
 	mvc	\bytes(1,%r1),0(%r1)
-- 
cgit v1.2.3


From 26f843848bae973817b3587780ce6b7b0200d3e4 Mon Sep 17 00:00:00 2001
From: Martin Schwidefsky <schwidefsky@de.ibm.com>
Date: Mon, 6 Aug 2018 14:26:39 +0200
Subject: s390: fix br_r1_trampoline for machines without exrl

For machines without the exrl instruction the BFP jit generates
code that uses an "br %r1" instruction located in the lowcore page.
Unfortunately there is a cut & paste error that puts an additional
"larl %r1,.+14" instruction in the code that clobbers the branch
target address in %r1. Remove the larl instruction.

Cc: <stable@vger.kernel.org> # v4.17+
Fixes: de5cb6eb51 ("s390: use expoline thunks in the BPF JIT")
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/net/bpf_jit_comp.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index d2db8acb1a55..9d4399a87fa2 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -485,8 +485,6 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
 			/* br %r1 */
 			_EMIT2(0x07f1);
 		} else {
-			/* larl %r1,.+14 */
-			EMIT6_PCREL_RILB(0xc0000000, REG_1, jit->prg + 14);
 			/* ex 0,S390_lowcore.br_r1_tampoline */
 			EMIT4_DISP(0x44000000, REG_0, REG_0,
 				   offsetof(struct lowcore, br_r1_trampoline));
-- 
cgit v1.2.3


From 85fc4b16aaf05fc8978d242c556a1711dce15cf8 Mon Sep 17 00:00:00 2001
From: Roman Gushchin <guro@fb.com>
Date: Mon, 6 Aug 2018 14:27:28 -0700
Subject: bpf: introduce update_effective_progs()

__cgroup_bpf_attach() and __cgroup_bpf_detach() functions have
a good amount of duplicated code, which is possible to eliminate
by introducing the update_effective_progs() helper function.

The update_effective_progs() calls compute_effective_progs()
and then in case of success it calls activate_effective_progs()
for each descendant cgroup. In case of failure (OOM), it releases
allocated prog arrays and return the error code.

Signed-off-by: Roman Gushchin <guro@fb.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/cgroup.c | 99 ++++++++++++++++++++++++-----------------------------
 1 file changed, 45 insertions(+), 54 deletions(-)

diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 0a4fe5a7dc91..6a7d931bbc55 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -177,6 +177,45 @@ cleanup:
 	return -ENOMEM;
 }
 
+static int update_effective_progs(struct cgroup *cgrp,
+				  enum bpf_attach_type type)
+{
+	struct cgroup_subsys_state *css;
+	int err;
+
+	/* allocate and recompute effective prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
+		if (err)
+			goto cleanup;
+	}
+
+	/* all allocations were successful. Activate all prog arrays */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		activate_effective_progs(desc, type, desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
+
+	return 0;
+
+cleanup:
+	/* oom while computing effective. Free all computed effective arrays
+	 * since they were not activated
+	 */
+	css_for_each_descendant_pre(css, &cgrp->self) {
+		struct cgroup *desc = container_of(css, struct cgroup, self);
+
+		bpf_prog_array_free(desc->bpf.inactive);
+		desc->bpf.inactive = NULL;
+	}
+
+	return err;
+}
+
 #define BPF_CGROUP_MAX_PROGS 64
 
 /**
@@ -194,7 +233,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	struct bpf_prog *old_prog = NULL;
 	struct bpf_cgroup_storage *storage, *old_storage = NULL;
-	struct cgroup_subsys_state *css;
 	struct bpf_prog_list *pl;
 	bool pl_was_allocated;
 	int err;
@@ -261,22 +299,9 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 
 	cgrp->bpf.flags[type] = flags;
 
-	/* allocate and recompute effective prog arrays */
-	css_for_each_descendant_pre(css, &cgrp->self) {
-		struct cgroup *desc = container_of(css, struct cgroup, self);
-
-		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
-		if (err)
-			goto cleanup;
-	}
-
-	/* all allocations were successful. Activate all prog arrays */
-	css_for_each_descendant_pre(css, &cgrp->self) {
-		struct cgroup *desc = container_of(css, struct cgroup, self);
-
-		activate_effective_progs(desc, type, desc->bpf.inactive);
-		desc->bpf.inactive = NULL;
-	}
+	err = update_effective_progs(cgrp, type);
+	if (err)
+		goto cleanup;
 
 	static_branch_inc(&cgroup_bpf_enabled_key);
 	if (old_storage)
@@ -289,16 +314,6 @@ int __cgroup_bpf_attach(struct cgroup *cgrp, struct bpf_prog *prog,
 	return 0;
 
 cleanup:
-	/* oom while computing effective. Free all computed effective arrays
-	 * since they were not activated
-	 */
-	css_for_each_descendant_pre(css, &cgrp->self) {
-		struct cgroup *desc = container_of(css, struct cgroup, self);
-
-		bpf_prog_array_free(desc->bpf.inactive);
-		desc->bpf.inactive = NULL;
-	}
-
 	/* and cleanup the prog list */
 	pl->prog = old_prog;
 	bpf_cgroup_storage_free(pl->storage);
@@ -326,7 +341,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 	struct list_head *progs = &cgrp->bpf.progs[type];
 	u32 flags = cgrp->bpf.flags[type];
 	struct bpf_prog *old_prog = NULL;
-	struct cgroup_subsys_state *css;
 	struct bpf_prog_list *pl;
 	int err;
 
@@ -365,22 +379,9 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 		pl->prog = NULL;
 	}
 
-	/* allocate and recompute effective prog arrays */
-	css_for_each_descendant_pre(css, &cgrp->self) {
-		struct cgroup *desc = container_of(css, struct cgroup, self);
-
-		err = compute_effective_progs(desc, type, &desc->bpf.inactive);
-		if (err)
-			goto cleanup;
-	}
-
-	/* all allocations were successful. Activate all prog arrays */
-	css_for_each_descendant_pre(css, &cgrp->self) {
-		struct cgroup *desc = container_of(css, struct cgroup, self);
-
-		activate_effective_progs(desc, type, desc->bpf.inactive);
-		desc->bpf.inactive = NULL;
-	}
+	err = update_effective_progs(cgrp, type);
+	if (err)
+		goto cleanup;
 
 	/* now can actually delete it from this cgroup list */
 	list_del(&pl->node);
@@ -396,16 +397,6 @@ int __cgroup_bpf_detach(struct cgroup *cgrp, struct bpf_prog *prog,
 	return 0;
 
 cleanup:
-	/* oom while computing effective. Free all computed effective arrays
-	 * since they were not activated
-	 */
-	css_for_each_descendant_pre(css, &cgrp->self) {
-		struct cgroup *desc = container_of(css, struct cgroup, self);
-
-		bpf_prog_array_free(desc->bpf.inactive);
-		desc->bpf.inactive = NULL;
-	}
-
 	/* and restore back old_prog */
 	pl->prog = old_prog;
 	return err;
-- 
cgit v1.2.3


From 13d3d01e26b942ada7cfced68ccb6db49597874a Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 4 Aug 2018 13:47:01 +0900
Subject: um: fix parallel building with O= option

Randy Dunlap reports UML occasionally fails to build with -j<N> and
O=<builddir> options.

  make[1]: Entering directory '/home/rdunlap/mmotm-2018-0802-1529/UM64'
    UPD     include/generated/uapi/linux/version.h
    WRAP    arch/x86/include/generated/asm/dma-contiguous.h
    WRAP    arch/x86/include/generated/asm/export.h
    WRAP    arch/x86/include/generated/asm/early_ioremap.h
    WRAP    arch/x86/include/generated/asm/mcs_spinlock.h
    WRAP    arch/x86/include/generated/asm/mm-arch-hooks.h
    WRAP    arch/x86/include/generated/uapi/asm/bpf_perf_event.h
    WRAP    arch/x86/include/generated/uapi/asm/poll.h
    GEN     ./Makefile
  make[2]: *** No rule to make target 'archheaders'.  Stop.
  arch/um/Makefile:119: recipe for target 'archheaders' failed
  make[1]: *** [archheaders] Error 2
  make[1]: *** Waiting for unfinished jobs....
    UPD     include/config/kernel.release
  make[1]: *** wait: No child processes.  Stop.
  Makefile:146: recipe for target 'sub-make' failed
  make: *** [sub-make] Error 2

The cause of the problem is the use of '$(MAKE) KBUILD_SRC=',
which recurses to the top Makefile via the $(objtree)/Makefile
generated by scripts/mkmakefile.

When you run "make -j<N> O=<builddir> ARCH=um", Make can execute
'archheaders' and 'outputmakefile' targets simultaneously because
there is no dependency between them.

If it happens,

  $(Q)$(MAKE) KBUILD_SRC= ARCH=$(HEADER_ARCH) archheaders

... tries to run $(objtree)/Makefile that is being updated.

The correct way for the recursion is

  $(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) archheaders

..., which does not rely on the generated Makefile.

Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Richard Weinberger <richard@nod.at>
---
 arch/um/Makefile | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/um/Makefile b/arch/um/Makefile
index 8c35261f5706..613fc3c79de0 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -122,8 +122,7 @@ archheaders:
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \
 	            kbuild-file=$(HOST_DIR)/include/uapi/asm/Kbuild \
 		    obj=$(HOST_DIR)/include/generated/uapi/asm
-	$(Q)$(MAKE) KBUILD_SRC= ARCH=$(HEADER_ARCH) archheaders
-
+	$(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) archheaders
 
 archprepare: include/generated/user_constants.h
 
-- 
cgit v1.2.3


From 63e31a67f12855129740943a4f826f05ddd0a2d0 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 4 Aug 2018 13:47:02 +0900
Subject: kbuild: add %asm-generic to no-dot-config-targets

asm-generic and uapi-asm-generic do not depend on the kernel
configuration.  In fact, uapi-asm-generic is the prerequisite of
headers_{install,check}, hence it should not require the .config file.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Richard Weinberger <richard@nod.at>
---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index bc3a65be9035..d2832a45dffe 100644
--- a/Makefile
+++ b/Makefile
@@ -224,7 +224,7 @@ clean-targets := %clean mrproper cleandocs
 no-dot-config-targets := $(clean-targets) \
 			 cscope gtags TAGS tags help% %docs check% coccicheck \
 			 $(version_h) headers_% archheaders archscripts \
-			 kernelversion %src-pkg
+			 %asm-generic kernelversion %src-pkg
 
 config-targets := 0
 mixed-targets  := 0
-- 
cgit v1.2.3


From 0004438a165b18d4a611745f12e328e65f46c8f2 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Sat, 4 Aug 2018 13:47:03 +0900
Subject: um: clean up archheaders recipe

Now that '%asm-generic' is added to no-dot-config-targets,
'make asm-generic' does not include the kernel configuration.

You can simply do 'make asm-generic' in the recursed top Makefile
without bothering syncconfig.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Richard Weinberger <richard@nod.at>
---
 arch/um/Makefile | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/arch/um/Makefile b/arch/um/Makefile
index 613fc3c79de0..306ee51c189f 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -116,13 +116,7 @@ endef
 KBUILD_KCONFIG := $(HOST_DIR)/um/Kconfig
 
 archheaders:
-	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \
-	            kbuild-file=$(HOST_DIR)/include/asm/Kbuild \
-		    obj=$(HOST_DIR)/include/generated/asm
-	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.asm-generic \
-	            kbuild-file=$(HOST_DIR)/include/uapi/asm/Kbuild \
-		    obj=$(HOST_DIR)/include/generated/uapi/asm
-	$(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) archheaders
+	$(Q)$(MAKE) -f $(srctree)/Makefile ARCH=$(HEADER_ARCH) asm-generic archheaders
 
 archprepare: include/generated/user_constants.h
 
-- 
cgit v1.2.3


From 8f220c418d070a097f7d292cf6b37f88d67845ad Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.de>
Date: Tue, 7 Aug 2018 12:43:42 +0200
Subject: nvme: fixup crash on failed discovery

When the initial discovery fails the subsystem hasn't been setup yet
in nvme_mpath_stop, and we can't dereference ctrl->subsys.

Fixes: 0d0b660f ("nvme: add ANA support")
Signed-off-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/multipath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index c643872f8dac..5a9562881d4e 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -22,7 +22,7 @@ MODULE_PARM_DESC(multipath,
 
 inline bool nvme_ctrl_use_ana(struct nvme_ctrl *ctrl)
 {
-	return multipath && (ctrl->subsys->cmic & (1 << 3));
+	return multipath && ctrl->subsys && (ctrl->subsys->cmic & (1 << 3));
 }
 
 /*
-- 
cgit v1.2.3


From 0b0722e191757ca6851382d78c15277ca9c5c211 Mon Sep 17 00:00:00 2001
From: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Date: Fri, 3 Aug 2018 13:30:03 +0100
Subject: ASoC: compress: make BE and FE order inline with dpcm

For some reason order of startup/hw_params/prepare are reversed
in dynamic compress usecase when compared to dpcm usecase. This is
a issue with platforms like QCOM where it expects the BE to be
initialized before FE.

Interestingly the compress trigger callback order is inline with dpcm.

Am not 100% sure why the compress audio case has been reversed.
This patch is making the order inline with dpcm.

If the reverse ordering is just co-incendental then this change
makes sense and will avoid inventing some new mechanism to cope
with ordering.

Signed-off-by: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/soc-compress.c | 96 +++++++++++++++++++++++-------------------------
 1 file changed, 46 insertions(+), 50 deletions(-)

diff --git a/sound/soc/soc-compress.c b/sound/soc/soc-compress.c
index b9e1673fea51..409d082e80d1 100644
--- a/sound/soc/soc-compress.c
+++ b/sound/soc/soc-compress.c
@@ -140,6 +140,30 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 		stream = SNDRV_PCM_STREAM_CAPTURE;
 
 	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
+	fe->dpcm[stream].runtime = fe_substream->runtime;
+
+	ret = dpcm_path_get(fe, stream, &list);
+	if (ret < 0)
+		goto be_err;
+	else if (ret == 0)
+		dev_dbg(fe->dev, "Compress ASoC: %s no valid %s route\n",
+			fe->dai_link->name, stream ? "capture" : "playback");
+	/* calculate valid and active FE <-> BE dpcms */
+	dpcm_process_paths(fe, stream, &list, 1);
+	fe->dpcm[stream].runtime = fe_substream->runtime;
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_startup(fe, stream);
+	if (ret < 0) {
+		/* clean up all links */
+		list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
+			dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
+
+		dpcm_be_disconnect(fe, stream);
+		fe->dpcm[stream].runtime = NULL;
+		goto out;
+	}
 
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->startup) {
 		ret = cpu_dai->driver->cops->startup(cstream, cpu_dai);
@@ -153,7 +177,7 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 
 	ret = soc_compr_components_open(cstream, &component);
 	if (ret < 0)
-		goto machine_err;
+		goto open_err;
 
 	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->startup) {
 		ret = fe->dai_link->compr_ops->startup(cstream);
@@ -164,31 +188,6 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 		}
 	}
 
-	fe->dpcm[stream].runtime = fe_substream->runtime;
-
-	ret = dpcm_path_get(fe, stream, &list);
-	if (ret < 0)
-		goto fe_err;
-	else if (ret == 0)
-		dev_dbg(fe->dev, "Compress ASoC: %s no valid %s route\n",
-			fe->dai_link->name, stream ? "capture" : "playback");
-
-	/* calculate valid and active FE <-> BE dpcms */
-	dpcm_process_paths(fe, stream, &list, 1);
-
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
-
-	ret = dpcm_be_dai_startup(fe, stream);
-	if (ret < 0) {
-		/* clean up all links */
-		list_for_each_entry(dpcm, &fe->dpcm[stream].be_clients, list_be)
-			dpcm->state = SND_SOC_DPCM_LINK_STATE_FREE;
-
-		dpcm_be_disconnect(fe, stream);
-		fe->dpcm[stream].runtime = NULL;
-		goto path_err;
-	}
-
 	dpcm_clear_pending_state(fe, stream);
 	dpcm_path_put(&list);
 
@@ -201,17 +200,14 @@ static int soc_compr_open_fe(struct snd_compr_stream *cstream)
 
 	return 0;
 
-path_err:
-	dpcm_path_put(&list);
-fe_err:
-	if (fe->dai_link->compr_ops && fe->dai_link->compr_ops->shutdown)
-		fe->dai_link->compr_ops->shutdown(cstream);
 machine_err:
 	soc_compr_components_free(cstream, component);
-
+open_err:
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->shutdown)
 		cpu_dai->driver->cops->shutdown(cstream, cpu_dai);
 out:
+	dpcm_path_put(&list);
+be_err:
 	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_NO;
 	mutex_unlock(&fe->card->mutex);
 	return ret;
@@ -551,6 +547,24 @@ static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
 
 	mutex_lock_nested(&fe->card->mutex, SND_SOC_CARD_CLASS_RUNTIME);
 
+	/*
+	 * Create an empty hw_params for the BE as the machine driver must
+	 * fix this up to match DSP decoder and ASRC configuration.
+	 * I.e. machine driver fixup for compressed BE is mandatory.
+	 */
+	memset(&fe->dpcm[fe_substream->stream].hw_params, 0,
+		sizeof(struct snd_pcm_hw_params));
+
+	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
+
+	ret = dpcm_be_dai_hw_params(fe, stream);
+	if (ret < 0)
+		goto out;
+
+	ret = dpcm_be_dai_prepare(fe, stream);
+	if (ret < 0)
+		goto out;
+
 	if (cpu_dai->driver->cops && cpu_dai->driver->cops->set_params) {
 		ret = cpu_dai->driver->cops->set_params(cstream, params, cpu_dai);
 		if (ret < 0)
@@ -577,24 +591,6 @@ static int soc_compr_set_params_fe(struct snd_compr_stream *cstream,
 			goto out;
 	}
 
-	/*
-	 * Create an empty hw_params for the BE as the machine driver must
-	 * fix this up to match DSP decoder and ASRC configuration.
-	 * I.e. machine driver fixup for compressed BE is mandatory.
-	 */
-	memset(&fe->dpcm[fe_substream->stream].hw_params, 0,
-		sizeof(struct snd_pcm_hw_params));
-
-	fe->dpcm[stream].runtime_update = SND_SOC_DPCM_UPDATE_FE;
-
-	ret = dpcm_be_dai_hw_params(fe, stream);
-	if (ret < 0)
-		goto out;
-
-	ret = dpcm_be_dai_prepare(fe, stream);
-	if (ret < 0)
-		goto out;
-
 	dpcm_dapm_stream_event(fe, stream, SND_SOC_DAPM_STREAM_START);
 	fe->dpcm[stream].state = SND_SOC_DPCM_STATE_PREPARE;
 
-- 
cgit v1.2.3


From e33e5c85763e8ac1899ec382c1ebc4603d8c52ae Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Aug 2018 09:42:22 +0200
Subject: target/loop: depend on SCSI

The target loopback driver is a low-level driver for the SCSI subsystem,
and as such needs to depend on it.

Fixes: 8a39a047 ("target: don't depend on SCSI")
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/target/loopback/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/target/loopback/Kconfig b/drivers/target/loopback/Kconfig
index abe8ecbcdf06..158ee9d522f7 100644
--- a/drivers/target/loopback/Kconfig
+++ b/drivers/target/loopback/Kconfig
@@ -1,5 +1,6 @@
 config LOOPBACK_TARGET
 	tristate "TCM Virtual SAS target and Linux/SCSI LDD fabric loopback module"
+	depends on SCSI
 	help
 	  Say Y here to enable the TCM Virtual SAS target and Linux/SCSI LLD
 	  fabric loopback module.
-- 
cgit v1.2.3


From dffe12a82826082d2129ef91b17b257254cb60fc Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Tue, 7 Aug 2018 10:07:00 -0500
Subject: gfs2: Fix gfs2_testbit to use clone bitmaps

Function gfs2_testbit is called in three places. Two of those places,
gfs2_alloc_extent and gfs2_unaligned_extlen, should be using the clone
bitmaps, not the "real" bitmaps. Function gfs2_unaligned_extlen is used
by the block reservations scheme to determine the length of an extent of
free blocks. Before this patch, it wasn't using the clone bitmap, which
means recently-freed blocks were treated as free blocks for the purposes
of an allocation.

This patch adds a new parameter to gfs2_testbit to indicate whether or
not the clone bitmaps should be used (if available).

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Reviewed-by: Andreas Gruenbacher <agruenba@redhat.com>
---
 fs/gfs2/incore.h | 21 +++++++++++++++++++++
 fs/gfs2/rgrp.c   | 44 +++++++++++++++++++-------------------------
 2 files changed, 40 insertions(+), 25 deletions(-)

diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index b50908211b69..b96d39c28e17 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -65,6 +65,27 @@ struct gfs2_log_operations {
 
 #define GBF_FULL 1
 
+/**
+ * Clone bitmaps (bi_clone):
+ *
+ * - When a block is freed, we remember the previous state of the block in the
+ *   clone bitmap, and only mark the block as free in the real bitmap.
+ *
+ * - When looking for a block to allocate, we check for a free block in the
+ *   clone bitmap, and if no clone bitmap exists, in the real bitmap.
+ *
+ * - For allocating a block, we mark it as allocated in the real bitmap, and if
+ *   a clone bitmap exists, also in the clone bitmap.
+ *
+ * - At the end of a log_flush, we copy the real bitmap into the clone bitmap
+ *   to make the clone bitmap reflect the current allocation state.
+ *   (Alternatively, we could remove the clone bitmap.)
+ *
+ * The clone bitmaps are in-core only, and is never written to disk.
+ *
+ * These steps ensure that blocks which have been freed in a transaction cannot
+ * be reallocated in that same transaction.
+ */
 struct gfs2_bitmap {
 	struct buffer_head *bi_bh;
 	char *bi_clone;
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 7c5afeba8888..ef50fe9b880a 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -123,17 +123,26 @@ static inline void gfs2_setbit(const struct gfs2_rbm *rbm, bool do_clone,
 /**
  * gfs2_testbit - test a bit in the bitmaps
  * @rbm: The bit to test
+ * @use_clone: If true, test the clone bitmap, not the official bitmap.
+ *
+ * Some callers like gfs2_unaligned_extlen need to test the clone bitmaps,
+ * not the "real" bitmaps, to avoid allocating recently freed blocks.
  *
  * Returns: The two bit block state of the requested bit
  */
 
-static inline u8 gfs2_testbit(const struct gfs2_rbm *rbm)
+static inline u8 gfs2_testbit(const struct gfs2_rbm *rbm, bool use_clone)
 {
 	struct gfs2_bitmap *bi = rbm_bi(rbm);
-	const u8 *buffer = bi->bi_bh->b_data + bi->bi_offset;
+	const u8 *buffer;
 	const u8 *byte;
 	unsigned int bit;
 
+	if (use_clone && bi->bi_clone)
+		buffer = bi->bi_clone;
+	else
+		buffer = bi->bi_bh->b_data;
+	buffer += bi->bi_offset;
 	byte = buffer + (rbm->offset / GFS2_NBBY);
 	bit = (rbm->offset % GFS2_NBBY) * GFS2_BIT_SIZE;
 
@@ -322,7 +331,7 @@ static bool gfs2_unaligned_extlen(struct gfs2_rbm *rbm, u32 n_unaligned, u32 *le
 	u8 res;
 
 	for (n = 0; n < n_unaligned; n++) {
-		res = gfs2_testbit(rbm);
+		res = gfs2_testbit(rbm, true);
 		if (res != GFS2_BLKST_FREE)
 			return true;
 		(*len)--;
@@ -2146,26 +2155,6 @@ void gfs2_inplace_release(struct gfs2_inode *ip)
 		gfs2_glock_dq_uninit(&rs->rs_rgd_gh);
 }
 
-/**
- * gfs2_get_block_type - Check a block in a RG is of given type
- * @rgd: the resource group holding the block
- * @block: the block number
- *
- * Returns: The block type (GFS2_BLKST_*)
- */
-
-static unsigned char gfs2_get_block_type(struct gfs2_rgrpd *rgd, u64 block)
-{
-	struct gfs2_rbm rbm = { .rgd = rgd, };
-	int ret;
-
-	ret = gfs2_rbm_from_block(&rbm, block);
-	WARN_ON_ONCE(ret != 0);
-
-	return gfs2_testbit(&rbm);
-}
-
-
 /**
  * gfs2_alloc_extent - allocate an extent from a given bitmap
  * @rbm: the resource group information
@@ -2190,7 +2179,7 @@ static void gfs2_alloc_extent(const struct gfs2_rbm *rbm, bool dinode,
 	block++;
 	while (*n < elen) {
 		ret = gfs2_rbm_from_block(&pos, block);
-		if (ret || gfs2_testbit(&pos) != GFS2_BLKST_FREE)
+		if (ret || gfs2_testbit(&pos, true) != GFS2_BLKST_FREE)
 			break;
 		gfs2_trans_add_meta(pos.rgd->rd_gl, rbm_bi(&pos)->bi_bh);
 		gfs2_setbit(&pos, true, GFS2_BLKST_USED);
@@ -2543,6 +2532,7 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
 {
 	struct gfs2_rgrpd *rgd;
 	struct gfs2_holder rgd_gh;
+	struct gfs2_rbm rbm;
 	int error = -EINVAL;
 
 	rgd = gfs2_blk2rgrpd(sdp, no_addr, 1);
@@ -2553,7 +2543,11 @@ int gfs2_check_blk_type(struct gfs2_sbd *sdp, u64 no_addr, unsigned int type)
 	if (error)
 		goto fail;
 
-	if (gfs2_get_block_type(rgd, no_addr) != type)
+	rbm.rgd = rgd;
+	error = gfs2_rbm_from_block(&rbm, no_addr);
+	WARN_ON_ONCE(error != 0);
+
+	if (gfs2_testbit(&rbm, false) != type)
 		error = -ESTALE;
 
 	gfs2_glock_dq_uninit(&rgd_gh);
-- 
cgit v1.2.3


From 35a8a3bd1c2e29bb6baec501c6f56abaaa10a48a Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Tue, 7 Aug 2018 11:43:02 +0200
Subject: netfilter: nft_osf: use NFT_OSF_MAXGENRELEN instead of IFNAMSIZ

As no "genre" on pf.os exceed 16 bytes of length, we reduce
NFT_OSF_MAXGENRELEN parameter to 16 bytes and use it instead of IFNAMSIZ.

Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h | 1 +
 net/netfilter/nft_osf.c                  | 8 +++-----
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 357862d948de..94657c701f22 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -8,6 +8,7 @@
 #define NFT_SET_MAXNAMELEN	NFT_NAME_MAXLEN
 #define NFT_OBJ_MAXNAMELEN	NFT_NAME_MAXLEN
 #define NFT_USERDATA_MAXLEN	256
+#define NFT_OSF_MAXGENRELEN	16
 
 /**
  * enum nft_registers - nf_tables registers
diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c
index 9b2f3de7be4f..5af74b37f423 100644
--- a/net/netfilter/nft_osf.c
+++ b/net/netfilter/nft_osf.c
@@ -4,8 +4,6 @@
 #include <net/netfilter/nf_tables.h>
 #include <linux/netfilter/nfnetlink_osf.h>
 
-#define OSF_GENRE_SIZE		32
-
 struct nft_osf {
 	enum nft_registers	dreg:8;
 };
@@ -37,9 +35,9 @@ static void nft_osf_eval(const struct nft_expr *expr, struct nft_regs *regs,
 
 	os_name = nf_osf_find(skb, nf_osf_fingers);
 	if (!os_name)
-		strncpy((char *)dest, "unknown", IFNAMSIZ);
+		strncpy((char *)dest, "unknown", NFT_OSF_MAXGENRELEN);
 	else
-		strncpy((char *)dest, os_name, IFNAMSIZ);
+		strncpy((char *)dest, os_name, NFT_OSF_MAXGENRELEN);
 }
 
 static int nft_osf_init(const struct nft_ctx *ctx,
@@ -51,7 +49,7 @@ static int nft_osf_init(const struct nft_ctx *ctx,
 
 	priv->dreg = nft_parse_register(tb[NFTA_OSF_DREG]);
 	err = nft_validate_register_store(ctx, priv->dreg, NULL,
-					  NFTA_DATA_VALUE, OSF_GENRE_SIZE);
+					  NFTA_DATA_VALUE, NFT_OSF_MAXGENRELEN);
 	if (err < 0)
 		return err;
 
-- 
cgit v1.2.3


From 4e665afbd7bee29b44b5d22821b56207f8459e39 Mon Sep 17 00:00:00 2001
From: Harsha Sharma <harshasharmaiitr@gmail.com>
Date: Tue, 7 Aug 2018 17:14:10 +0200
Subject: netfilter: cttimeout: move ctnl_untimeout to nf_conntrack

As, ctnl_untimeout is required by nft_ct, so move ctnl_timeout from
nfnetlink_cttimeout to nf_conntrack_timeout and rename as nf_ct_timeout.

Signed-off-by: Harsha Sharma <harshasharmaiitr@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_timeout.h |  1 +
 net/netfilter/nf_conntrack_timeout.c         | 17 +++++++++++++++++
 net/netfilter/nfnetlink_cttimeout.c          | 20 ++------------------
 3 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 80ceb3d0291d..7a21bc0f00eb 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -83,6 +83,7 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 int nf_conntrack_timeout_init(void);
 void nf_conntrack_timeout_fini(void);
+void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout);
 #else
 static inline int nf_conntrack_timeout_init(void)
 {
diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c
index 46aee65f339b..401c2cce4a61 100644
--- a/net/netfilter/nf_conntrack_timeout.c
+++ b/net/netfilter/nf_conntrack_timeout.c
@@ -31,6 +31,23 @@ EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook);
 void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout) __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook);
 
+static int untimeout(struct nf_conn *ct, void *timeout)
+{
+	struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct);
+
+	if (timeout_ext && (!timeout || timeout_ext->timeout == timeout))
+		RCU_INIT_POINTER(timeout_ext->timeout, NULL);
+
+	/* We are not intended to delete this conntrack. */
+	return 0;
+}
+
+void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout)
+{
+	nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0);
+}
+EXPORT_SYMBOL_GPL(nf_ct_untimeout);
+
 static const struct nf_ct_ext_type timeout_extend = {
 	.len	= sizeof(struct nf_conn_timeout),
 	.align	= __alignof__(struct nf_conn_timeout),
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 4199e5300575..df53aef2d642 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -297,22 +297,6 @@ static int cttimeout_get_timeout(struct net *net, struct sock *ctnl,
 	return ret;
 }
 
-static int untimeout(struct nf_conn *ct, void *timeout)
-{
-	struct nf_conn_timeout *timeout_ext = nf_ct_timeout_find(ct);
-
-	if (timeout_ext && (!timeout || timeout_ext->timeout == timeout))
-		RCU_INIT_POINTER(timeout_ext->timeout, NULL);
-
-	/* We are not intended to delete this conntrack. */
-	return 0;
-}
-
-static void ctnl_untimeout(struct net *net, struct ctnl_timeout *timeout)
-{
-	nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0);
-}
-
 /* try to delete object, fail if it is still in use. */
 static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
 {
@@ -325,7 +309,7 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&timeout->head);
 		nf_ct_l4proto_put(timeout->l4proto);
-		ctnl_untimeout(net, timeout);
+		nf_ct_untimeout(net, timeout);
 		kfree_rcu(timeout, rcu_head);
 	} else {
 		ret = -EBUSY;
@@ -573,7 +557,7 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 	struct ctnl_timeout *cur, *tmp;
 
 	nf_ct_unconfirmed_destroy(net);
-	ctnl_untimeout(net, NULL);
+	nf_ct_untimeout(net, NULL);
 
 	list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) {
 		list_del_rcu(&cur->head);
-- 
cgit v1.2.3


From 6c1fd7dc489d9bf64196f5b0fa33e059f64460c8 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 7 Aug 2018 17:14:15 +0200
Subject: netfilter: cttimeout: decouple timeout policy from
 nfnetlink_cttimeout object

The timeout policy is currently embedded into the nfnetlink_cttimeout
object, move the policy into an independent object. This allows us to
reuse part of the existing conntrack timeout extension from nf_tables
without adding dependencies with the nfnetlink_cttimeout object layout.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_timeout.h | 22 ++++++++++-------
 net/netfilter/nf_conntrack_timeout.c         |  6 ++---
 net/netfilter/nfnetlink_cttimeout.c          | 37 ++++++++++++++++------------
 net/netfilter/xt_CT.c                        |  4 +--
 4 files changed, 39 insertions(+), 30 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_timeout.h b/include/net/netfilter/nf_conntrack_timeout.h
index 7a21bc0f00eb..d5f62cc6c2ae 100644
--- a/include/net/netfilter/nf_conntrack_timeout.h
+++ b/include/net/netfilter/nf_conntrack_timeout.h
@@ -11,24 +11,28 @@
 
 #define CTNL_TIMEOUT_NAME_MAX	32
 
+struct nf_ct_timeout {
+	__u16			l3num;
+	const struct nf_conntrack_l4proto *l4proto;
+	char			data[0];
+};
+
 struct ctnl_timeout {
 	struct list_head	head;
 	struct rcu_head		rcu_head;
 	refcount_t		refcnt;
 	char			name[CTNL_TIMEOUT_NAME_MAX];
-	__u16			l3num;
-	const struct nf_conntrack_l4proto *l4proto;
-	char			data[0];
+	struct nf_ct_timeout	timeout;
 };
 
 struct nf_conn_timeout {
-	struct ctnl_timeout __rcu *timeout;
+	struct nf_ct_timeout __rcu *timeout;
 };
 
 static inline unsigned int *
 nf_ct_timeout_data(struct nf_conn_timeout *t)
 {
-	struct ctnl_timeout *timeout;
+	struct nf_ct_timeout *timeout;
 
 	timeout = rcu_dereference(t->timeout);
 	if (timeout == NULL)
@@ -49,7 +53,7 @@ struct nf_conn_timeout *nf_ct_timeout_find(const struct nf_conn *ct)
 
 static inline
 struct nf_conn_timeout *nf_ct_timeout_ext_add(struct nf_conn *ct,
-					      struct ctnl_timeout *timeout,
+					      struct nf_ct_timeout *timeout,
 					      gfp_t gfp)
 {
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
@@ -83,7 +87,7 @@ static inline unsigned int *nf_ct_timeout_lookup(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 int nf_conntrack_timeout_init(void);
 void nf_conntrack_timeout_fini(void);
-void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout);
+void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout);
 #else
 static inline int nf_conntrack_timeout_init(void)
 {
@@ -97,8 +101,8 @@ static inline void nf_conntrack_timeout_fini(void)
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-extern struct ctnl_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name);
-extern void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout);
+extern struct nf_ct_timeout *(*nf_ct_timeout_find_get_hook)(struct net *net, const char *name);
+extern void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout);
 #endif
 
 #endif /* _NF_CONNTRACK_TIMEOUT_H */
diff --git a/net/netfilter/nf_conntrack_timeout.c b/net/netfilter/nf_conntrack_timeout.c
index 401c2cce4a61..91fbd183da2d 100644
--- a/net/netfilter/nf_conntrack_timeout.c
+++ b/net/netfilter/nf_conntrack_timeout.c
@@ -24,11 +24,11 @@
 #include <net/netfilter/nf_conntrack_extend.h>
 #include <net/netfilter/nf_conntrack_timeout.h>
 
-struct ctnl_timeout *
+struct nf_ct_timeout *
 (*nf_ct_timeout_find_get_hook)(struct net *net, const char *name) __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_timeout_find_get_hook);
 
-void (*nf_ct_timeout_put_hook)(struct ctnl_timeout *timeout) __read_mostly;
+void (*nf_ct_timeout_put_hook)(struct nf_ct_timeout *timeout) __read_mostly;
 EXPORT_SYMBOL_GPL(nf_ct_timeout_put_hook);
 
 static int untimeout(struct nf_conn *ct, void *timeout)
@@ -42,7 +42,7 @@ static int untimeout(struct nf_conn *ct, void *timeout)
 	return 0;
 }
 
-void nf_ct_untimeout(struct net *net, struct ctnl_timeout *timeout)
+void nf_ct_untimeout(struct net *net, struct nf_ct_timeout *timeout)
 {
 	nf_ct_iterate_cleanup_net(net, untimeout, timeout, 0, 0);
 }
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index df53aef2d642..d46a236cdf31 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -113,13 +113,13 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl,
 			/* You cannot replace one timeout policy by another of
 			 * different kind, sorry.
 			 */
-			if (matching->l3num != l3num ||
-			    matching->l4proto->l4proto != l4num)
+			if (matching->timeout.l3num != l3num ||
+			    matching->timeout.l4proto->l4proto != l4num)
 				return -EINVAL;
 
-			return ctnl_timeout_parse_policy(&matching->data,
-							 matching->l4proto, net,
-							 cda[CTA_TIMEOUT_DATA]);
+			return ctnl_timeout_parse_policy(&matching->timeout.data,
+							 matching->timeout.l4proto,
+							 net, cda[CTA_TIMEOUT_DATA]);
 		}
 
 		return -EBUSY;
@@ -140,14 +140,14 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl,
 		goto err_proto_put;
 	}
 
-	ret = ctnl_timeout_parse_policy(&timeout->data, l4proto, net,
+	ret = ctnl_timeout_parse_policy(&timeout->timeout.data, l4proto, net,
 					cda[CTA_TIMEOUT_DATA]);
 	if (ret < 0)
 		goto err;
 
 	strcpy(timeout->name, nla_data(cda[CTA_TIMEOUT_NAME]));
-	timeout->l3num = l3num;
-	timeout->l4proto = l4proto;
+	timeout->timeout.l3num = l3num;
+	timeout->timeout.l4proto = l4proto;
 	refcount_set(&timeout->refcnt, 1);
 	list_add_tail_rcu(&timeout->head, &net->nfct_timeout_list);
 
@@ -166,7 +166,7 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 	unsigned int flags = portid ? NLM_F_MULTI : 0;
-	const struct nf_conntrack_l4proto *l4proto = timeout->l4proto;
+	const struct nf_conntrack_l4proto *l4proto = timeout->timeout.l4proto;
 
 	event = nfnl_msg_type(NFNL_SUBSYS_CTNETLINK_TIMEOUT, event);
 	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nfmsg), flags);
@@ -179,8 +179,9 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 	nfmsg->res_id = 0;
 
 	if (nla_put_string(skb, CTA_TIMEOUT_NAME, timeout->name) ||
-	    nla_put_be16(skb, CTA_TIMEOUT_L3PROTO, htons(timeout->l3num)) ||
-	    nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) ||
+	    nla_put_be16(skb, CTA_TIMEOUT_L3PROTO,
+			 htons(timeout->timeout.l3num)) ||
+	    nla_put_u8(skb, CTA_TIMEOUT_L4PROTO, l4proto->l4proto) ||
 	    nla_put_be32(skb, CTA_TIMEOUT_USE,
 			 htonl(refcount_read(&timeout->refcnt))))
 		goto nla_put_failure;
@@ -194,7 +195,8 @@ ctnl_timeout_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type,
 		if (!nest_parms)
 			goto nla_put_failure;
 
-		ret = l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->data);
+		ret = l4proto->ctnl_timeout.obj_to_nlattr(skb,
+							&timeout->timeout.data);
 		if (ret < 0)
 			goto nla_put_failure;
 
@@ -308,8 +310,8 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
 	if (refcount_dec_if_one(&timeout->refcnt)) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&timeout->head);
-		nf_ct_l4proto_put(timeout->l4proto);
-		nf_ct_untimeout(net, timeout);
+		nf_ct_l4proto_put(timeout->timeout.l4proto);
+		nf_ct_untimeout(net, &timeout->timeout);
 		kfree_rcu(timeout, rcu_head);
 	} else {
 		ret = -EBUSY;
@@ -510,8 +512,11 @@ err:
 	return matching;
 }
 
-static void ctnl_timeout_put(struct ctnl_timeout *timeout)
+static void ctnl_timeout_put(struct nf_ct_timeout *t)
 {
+	struct ctnl_timeout *timeout =
+		container_of(t, struct ctnl_timeout, timeout);
+
 	if (refcount_dec_and_test(&timeout->refcnt))
 		kfree_rcu(timeout, rcu_head);
 
@@ -561,7 +566,7 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 
 	list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) {
 		list_del_rcu(&cur->head);
-		nf_ct_l4proto_put(cur->l4proto);
+		nf_ct_l4proto_put(cur->timeout.l4proto);
 
 		if (refcount_dec_and_test(&cur->refcnt))
 			kfree_rcu(cur, rcu_head);
diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c
index 7ba454e9e3fa..89457efd2e00 100644
--- a/net/netfilter/xt_CT.c
+++ b/net/netfilter/xt_CT.c
@@ -104,7 +104,7 @@ xt_ct_set_helper(struct nf_conn *ct, const char *helper_name,
 }
 
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-static void __xt_ct_tg_timeout_put(struct ctnl_timeout *timeout)
+static void __xt_ct_tg_timeout_put(struct nf_ct_timeout *timeout)
 {
 	typeof(nf_ct_timeout_put_hook) timeout_put;
 
@@ -121,7 +121,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par,
 #ifdef CONFIG_NF_CONNTRACK_TIMEOUT
 	typeof(nf_ct_timeout_find_get_hook) timeout_find_get;
 	const struct nf_conntrack_l4proto *l4proto;
-	struct ctnl_timeout *timeout;
+	struct nf_ct_timeout *timeout;
 	struct nf_conn_timeout *timeout_ext;
 	const char *errmsg = NULL;
 	int ret = 0;
-- 
cgit v1.2.3


From ad83f2a9ce37a264202f48f4fd8889ee9056b703 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 7 Aug 2018 17:14:19 +0200
Subject: netfilter: remove ifdef around cttimeout in struct
 nf_conntrack_l4proto

Simplify this, include it inconditionally in this structure layout as we
do with ctnetlink.

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_conntrack_l4proto.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 6068c6da3eac..8465263b297d 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -77,7 +77,6 @@ struct nf_conntrack_l4proto {
 			       struct nf_conntrack_tuple *t);
 	const struct nla_policy *nla_policy;
 
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
 	struct {
 		int (*nlattr_to_obj)(struct nlattr *tb[],
 				     struct net *net, void *data);
@@ -87,7 +86,6 @@ struct nf_conntrack_l4proto {
 		u16 nlattr_max;
 		const struct nla_policy *nla_policy;
 	} ctnl_timeout;
-#endif
 #ifdef CONFIG_NF_CONNTRACK_PROCFS
 	/* Print out the private part of the conntrack. */
 	void (*print_conntrack)(struct seq_file *s, struct nf_conn *);
-- 
cgit v1.2.3


From 7e0b2b57f01d183e1c84114f1f2287737358d748 Mon Sep 17 00:00:00 2001
From: Harsha Sharma <harshasharmaiitr@gmail.com>
Date: Tue, 7 Aug 2018 17:14:23 +0200
Subject: netfilter: nft_ct: add ct timeout support

This patch allows to add, list and delete connection tracking timeout
policies via nft objref infrastructure and assigning these timeout
via nft rule.

%./libnftnl/examples/nft-ct-timeout-add ip raw cttime tcp

Ruleset:

table ip raw {
   ct timeout cttime {
       protocol tcp;
       policy = {established: 111, close: 13 }
   }

   chain output {
       type filter hook output priority -300; policy accept;
       ct timeout set "cttime"
   }
}

%./libnftnl/examples/nft-rule-ct-timeout-add ip raw output cttime

%conntrack -E
[NEW] tcp      6 111 ESTABLISHED src=172.16.19.128 dst=172.16.19.1
sport=22 dport=41360 [UNREPLIED] src=172.16.19.1 dst=172.16.19.128
sport=41360 dport=22

%nft delete rule ip raw output handle <handle>
%./libnftnl/examples/nft-ct-timeout-del ip raw cttime

Joint work with Pablo Neira.

Signed-off-by: Harsha Sharma <harshasharmaiitr@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/uapi/linux/netfilter/nf_tables.h |  14 ++-
 net/netfilter/nft_ct.c                   | 204 ++++++++++++++++++++++++++++++-
 2 files changed, 216 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
index 94657c701f22..e23290ffdc77 100644
--- a/include/uapi/linux/netfilter/nf_tables.h
+++ b/include/uapi/linux/netfilter/nf_tables.h
@@ -958,6 +958,7 @@ enum nft_socket_keys {
  * @NFT_CT_DST_IP: conntrack layer 3 protocol destination (IPv4 address)
  * @NFT_CT_SRC_IP6: conntrack layer 3 protocol source (IPv6 address)
  * @NFT_CT_DST_IP6: conntrack layer 3 protocol destination (IPv6 address)
+ * @NFT_CT_TIMEOUT: connection tracking timeout policy assigned to conntrack
  */
 enum nft_ct_keys {
 	NFT_CT_STATE,
@@ -983,6 +984,7 @@ enum nft_ct_keys {
 	NFT_CT_DST_IP,
 	NFT_CT_SRC_IP6,
 	NFT_CT_DST_IP6,
+	NFT_CT_TIMEOUT,
 	__NFT_CT_MAX
 };
 #define NFT_CT_MAX		(__NFT_CT_MAX - 1)
@@ -1411,6 +1413,15 @@ enum nft_ct_helper_attributes {
 };
 #define NFTA_CT_HELPER_MAX	(__NFTA_CT_HELPER_MAX - 1)
 
+enum nft_ct_timeout_timeout_attributes {
+	NFTA_CT_TIMEOUT_UNSPEC,
+	NFTA_CT_TIMEOUT_L3PROTO,
+	NFTA_CT_TIMEOUT_L4PROTO,
+	NFTA_CT_TIMEOUT_DATA,
+	__NFTA_CT_TIMEOUT_MAX,
+};
+#define NFTA_CT_TIMEOUT_MAX	(__NFTA_CT_TIMEOUT_MAX - 1)
+
 #define NFT_OBJECT_UNSPEC	0
 #define NFT_OBJECT_COUNTER	1
 #define NFT_OBJECT_QUOTA	2
@@ -1418,7 +1429,8 @@ enum nft_ct_helper_attributes {
 #define NFT_OBJECT_LIMIT	4
 #define NFT_OBJECT_CONNLIMIT	5
 #define NFT_OBJECT_TUNNEL	6
-#define __NFT_OBJECT_MAX	7
+#define NFT_OBJECT_CT_TIMEOUT	7
+#define __NFT_OBJECT_MAX	8
 #define NFT_OBJECT_MAX		(__NFT_OBJECT_MAX - 1)
 
 /**
diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 3bc82ee5464d..4788458a0931 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -22,6 +22,8 @@
 #include <net/netfilter/nf_conntrack_helper.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_labels.h>
+#include <net/netfilter/nf_conntrack_timeout.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
 
 struct nft_ct {
 	enum nft_ct_keys	key:8;
@@ -765,6 +767,194 @@ static struct nft_expr_type nft_notrack_type __read_mostly = {
 	.owner		= THIS_MODULE,
 };
 
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+static int
+nft_ct_timeout_parse_policy(void *timeouts,
+			    const struct nf_conntrack_l4proto *l4proto,
+			    struct net *net, const struct nlattr *attr)
+{
+	struct nlattr **tb;
+	int ret = 0;
+
+	if (!l4proto->ctnl_timeout.nlattr_to_obj)
+		return 0;
+
+	tb = kcalloc(l4proto->ctnl_timeout.nlattr_max + 1, sizeof(*tb),
+		     GFP_KERNEL);
+
+	if (!tb)
+		return -ENOMEM;
+
+	ret = nla_parse_nested(tb, l4proto->ctnl_timeout.nlattr_max,
+			       attr, l4proto->ctnl_timeout.nla_policy,
+			       NULL);
+	if (ret < 0)
+		goto err;
+
+	ret = l4proto->ctnl_timeout.nlattr_to_obj(tb, net, timeouts);
+
+err:
+	kfree(tb);
+	return ret;
+}
+
+struct nft_ct_timeout_obj {
+	struct nf_conn		*tmpl;
+	u8			l4proto;
+};
+
+static void nft_ct_timeout_obj_eval(struct nft_object *obj,
+				    struct nft_regs *regs,
+				    const struct nft_pktinfo *pkt)
+{
+	const struct nft_ct_timeout_obj *priv = nft_obj_data(obj);
+	struct nf_conn *ct = (struct nf_conn *)skb_nfct(pkt->skb);
+	struct sk_buff *skb = pkt->skb;
+
+	if (ct ||
+	    priv->l4proto != pkt->tprot)
+		return;
+
+	nf_ct_set(skb, priv->tmpl, IP_CT_NEW);
+}
+
+static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx,
+				   const struct nlattr * const tb[],
+				   struct nft_object *obj)
+{
+	const struct nf_conntrack_zone *zone = &nf_ct_zone_dflt;
+	struct nft_ct_timeout_obj *priv = nft_obj_data(obj);
+	const struct nf_conntrack_l4proto *l4proto;
+	struct nf_conn_timeout *timeout_ext;
+	struct nf_ct_timeout *timeout;
+	int l3num = ctx->family;
+	struct nf_conn *tmpl;
+	__u8 l4num;
+	int ret;
+
+	if (!tb[NFTA_CT_TIMEOUT_L3PROTO] ||
+	    !tb[NFTA_CT_TIMEOUT_L4PROTO] ||
+	    !tb[NFTA_CT_TIMEOUT_DATA])
+		return -EINVAL;
+
+	l3num = ntohs(nla_get_be16(tb[NFTA_CT_TIMEOUT_L3PROTO]));
+	l4num = nla_get_u8(tb[NFTA_CT_TIMEOUT_L4PROTO]);
+	priv->l4proto = l4num;
+
+	l4proto = nf_ct_l4proto_find_get(l3num, l4num);
+
+	if (l4proto->l4proto != l4num) {
+		ret = -EOPNOTSUPP;
+		goto err_proto_put;
+	}
+
+	timeout = kzalloc(sizeof(struct nf_ct_timeout) +
+			  l4proto->ctnl_timeout.obj_size, GFP_KERNEL);
+	if (timeout == NULL) {
+		ret = -ENOMEM;
+		goto err_proto_put;
+	}
+
+	ret = nft_ct_timeout_parse_policy(&timeout->data, l4proto, ctx->net,
+					  tb[NFTA_CT_TIMEOUT_DATA]);
+	if (ret < 0)
+		goto err_free_timeout;
+
+	timeout->l3num = l3num;
+	timeout->l4proto = l4proto;
+	tmpl = nf_ct_tmpl_alloc(ctx->net, zone, GFP_ATOMIC);
+	if (!tmpl) {
+		ret = -ENOMEM;
+		goto err_free_timeout;
+	}
+
+	timeout_ext = nf_ct_timeout_ext_add(tmpl, timeout, GFP_ATOMIC);
+	if (!timeout_ext) {
+		ret = -ENOMEM;
+		goto err_free_tmpl;
+	}
+
+	ret = nf_ct_netns_get(ctx->net, ctx->family);
+	if (ret < 0)
+		goto err_free_tmpl;
+
+	priv->tmpl = tmpl;
+
+	return 0;
+
+err_free_tmpl:
+	nf_ct_tmpl_free(tmpl);
+err_free_timeout:
+	kfree(timeout);
+err_proto_put:
+	nf_ct_l4proto_put(l4proto);
+	return ret;
+}
+
+static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx,
+				       struct nft_object *obj)
+{
+	struct nft_ct_timeout_obj *priv = nft_obj_data(obj);
+	struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl);
+	struct nf_ct_timeout *timeout;
+
+	timeout = rcu_dereference_raw(t->timeout);
+	nf_ct_untimeout(ctx->net, timeout);
+	nf_ct_l4proto_put(timeout->l4proto);
+	nf_ct_netns_put(ctx->net, ctx->family);
+	nf_ct_tmpl_free(priv->tmpl);
+}
+
+static int nft_ct_timeout_obj_dump(struct sk_buff *skb,
+				   struct nft_object *obj, bool reset)
+{
+	const struct nft_ct_timeout_obj *priv = nft_obj_data(obj);
+	const struct nf_conn_timeout *t = nf_ct_timeout_find(priv->tmpl);
+	const struct nf_ct_timeout *timeout = rcu_dereference_raw(t->timeout);
+	struct nlattr *nest_params;
+	int ret;
+
+	if (nla_put_u8(skb, NFTA_CT_TIMEOUT_L4PROTO, timeout->l4proto->l4proto) ||
+	    nla_put_be16(skb, NFTA_CT_TIMEOUT_L3PROTO, htons(timeout->l3num)))
+		return -1;
+
+	nest_params = nla_nest_start(skb, NFTA_CT_TIMEOUT_DATA | NLA_F_NESTED);
+	if (!nest_params)
+		return -1;
+
+	ret = timeout->l4proto->ctnl_timeout.obj_to_nlattr(skb, &timeout->data);
+	if (ret < 0)
+		return -1;
+	nla_nest_end(skb, nest_params);
+	return 0;
+}
+
+static const struct nla_policy nft_ct_timeout_policy[NFTA_CT_TIMEOUT_MAX + 1] = {
+	[NFTA_CT_TIMEOUT_L3PROTO] = {.type = NLA_U16 },
+	[NFTA_CT_TIMEOUT_L4PROTO] = {.type = NLA_U8 },
+	[NFTA_CT_TIMEOUT_DATA]	  = {.type = NLA_NESTED },
+};
+
+static struct nft_object_type nft_ct_timeout_obj_type;
+
+static const struct nft_object_ops nft_ct_timeout_obj_ops = {
+	.type		= &nft_ct_timeout_obj_type,
+	.size		= sizeof(struct nft_ct_timeout_obj),
+	.eval		= nft_ct_timeout_obj_eval,
+	.init		= nft_ct_timeout_obj_init,
+	.destroy	= nft_ct_timeout_obj_destroy,
+	.dump		= nft_ct_timeout_obj_dump,
+};
+
+static struct nft_object_type nft_ct_timeout_obj_type __read_mostly = {
+	.type		= NFT_OBJECT_CT_TIMEOUT,
+	.ops		= &nft_ct_timeout_obj_ops,
+	.maxattr	= NFTA_CT_TIMEOUT_MAX,
+	.policy		= nft_ct_timeout_policy,
+	.owner		= THIS_MODULE,
+};
+#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
+
 static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
 				  const struct nlattr * const tb[],
 				  struct nft_object *obj)
@@ -949,9 +1139,17 @@ static int __init nft_ct_module_init(void)
 	err = nft_register_obj(&nft_ct_helper_obj_type);
 	if (err < 0)
 		goto err2;
-
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+	err = nft_register_obj(&nft_ct_timeout_obj_type);
+	if (err < 0)
+		goto err3;
+#endif
 	return 0;
 
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+err3:
+	nft_unregister_obj(&nft_ct_helper_obj_type);
+#endif
 err2:
 	nft_unregister_expr(&nft_notrack_type);
 err1:
@@ -961,6 +1159,9 @@ err1:
 
 static void __exit nft_ct_module_exit(void)
 {
+#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
+	nft_unregister_obj(&nft_ct_timeout_obj_type);
+#endif
 	nft_unregister_obj(&nft_ct_helper_obj_type);
 	nft_unregister_expr(&nft_notrack_type);
 	nft_unregister_expr(&nft_ct_type);
@@ -974,3 +1175,4 @@ MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
 MODULE_ALIAS_NFT_EXPR("ct");
 MODULE_ALIAS_NFT_EXPR("notrack");
 MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_HELPER);
+MODULE_ALIAS_NFT_OBJ(NFT_OBJECT_CT_TIMEOUT);
-- 
cgit v1.2.3


From f699edb12a25a3dc8ecf72fe0a9b2fa42bd6a5da Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 7 Aug 2018 17:14:27 +0200
Subject: netfilter: nft_ct: enable conntrack for helpers

Enable conntrack if the user defines a helper to be used from the
ruleset policy.

Fixes: 1a64edf54f55 ("netfilter: nft_ct: add helper set support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_ct.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 4788458a0931..4855d4ce1c8f 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -963,6 +963,7 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
 	struct nf_conntrack_helper *help4, *help6;
 	char name[NF_CT_HELPER_NAME_LEN];
 	int family = ctx->family;
+	int err;
 
 	if (!tb[NFTA_CT_HELPER_NAME] || !tb[NFTA_CT_HELPER_L4PROTO])
 		return -EINVAL;
@@ -1013,7 +1014,18 @@ static int nft_ct_helper_obj_init(const struct nft_ctx *ctx,
 	priv->helper4 = help4;
 	priv->helper6 = help6;
 
+	err = nf_ct_netns_get(ctx->net, ctx->family);
+	if (err < 0)
+		goto err_put_helper;
+
 	return 0;
+
+err_put_helper:
+	if (priv->helper4)
+		nf_conntrack_helper_put(priv->helper4);
+	if (priv->helper6)
+		nf_conntrack_helper_put(priv->helper6);
+	return err;
 }
 
 static void nft_ct_helper_obj_destroy(const struct nft_ctx *ctx,
@@ -1025,6 +1037,8 @@ static void nft_ct_helper_obj_destroy(const struct nft_ctx *ctx,
 		nf_conntrack_helper_put(priv->helper4);
 	if (priv->helper6)
 		nf_conntrack_helper_put(priv->helper6);
+
+	nf_ct_netns_put(ctx->net, ctx->family);
 }
 
 static void nft_ct_helper_obj_eval(struct nft_object *obj,
-- 
cgit v1.2.3


From e661414c98dfbdcf8666a058a6278cd7a2f20c95 Mon Sep 17 00:00:00 2001
From: Sergey Nemov <sergey.nemov@intel.com>
Date: Thu, 19 Jul 2018 13:25:22 +0200
Subject: i40e: Remove duplicated prepare call in i40e_shutdown

Function call to i40e_prep_for_reset() is duplicated in
i40e_shutdown routine and gets called before
i40e_enable_mc_magic_wake() which blocks it from being executed
correctly on system reboot or shutdown because adminq is already
disabled by first i40e_prep_for_reset() call.

Two register write calls are also duplicated.

Signed-off-by: Sergey Nemov <sergey.nemov@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 51762428b40e..13940e0ba939 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -14353,12 +14353,6 @@ static void i40e_shutdown(struct pci_dev *pdev)
 
 	set_bit(__I40E_SUSPENDED, pf->state);
 	set_bit(__I40E_DOWN, pf->state);
-	rtnl_lock();
-	i40e_prep_for_reset(pf, true);
-	rtnl_unlock();
-
-	wr32(hw, I40E_PFPM_APM, (pf->wol_en ? I40E_PFPM_APM_APME_MASK : 0));
-	wr32(hw, I40E_PFPM_WUFC, (pf->wol_en ? I40E_PFPM_WUFC_MAG_MASK : 0));
 
 	del_timer_sync(&pf->service_timer);
 	cancel_work_sync(&pf->service_task);
-- 
cgit v1.2.3


From 1b4b6f3a2a653cb9131664deed3f1e44f60a6e14 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Thu, 26 Jul 2018 14:37:36 +0800
Subject: i40e/i40evf: remove redundant functions
 i40evf_aq_{set/get}_phy_register

There are no in-tree callers.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40evf/i40e_common.c | 69 -------------------------
 1 file changed, 69 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c
index 9cef54971312..eea280ba411e 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c
@@ -1020,75 +1020,6 @@ do_retry:
 		wr32(hw, reg_addr, reg_val);
 }
 
-/**
- * i40evf_aq_set_phy_register
- * @hw: pointer to the hw struct
- * @phy_select: select which phy should be accessed
- * @dev_addr: PHY device address
- * @reg_addr: PHY register address
- * @reg_val: new register value
- * @cmd_details: pointer to command details structure or NULL
- *
- * Reset the external PHY.
- **/
-i40e_status i40evf_aq_set_phy_register(struct i40e_hw *hw,
-				       u8 phy_select, u8 dev_addr,
-				       u32 reg_addr, u32 reg_val,
-				       struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
-	i40e_status status;
-
-	i40evf_fill_default_direct_cmd_desc(&desc,
-					    i40e_aqc_opc_set_phy_register);
-
-	cmd->phy_interface = phy_select;
-	cmd->dev_address = dev_addr;
-	cmd->reg_address = cpu_to_le32(reg_addr);
-	cmd->reg_value = cpu_to_le32(reg_val);
-
-	status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-
-	return status;
-}
-
-/**
- * i40evf_aq_get_phy_register
- * @hw: pointer to the hw struct
- * @phy_select: select which phy should be accessed
- * @dev_addr: PHY device address
- * @reg_addr: PHY register address
- * @reg_val: read register value
- * @cmd_details: pointer to command details structure or NULL
- *
- * Reset the external PHY.
- **/
-i40e_status i40evf_aq_get_phy_register(struct i40e_hw *hw,
-				       u8 phy_select, u8 dev_addr,
-				       u32 reg_addr, u32 *reg_val,
-				       struct i40e_asq_cmd_details *cmd_details)
-{
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
-	i40e_status status;
-
-	i40evf_fill_default_direct_cmd_desc(&desc,
-					    i40e_aqc_opc_get_phy_register);
-
-	cmd->phy_interface = phy_select;
-	cmd->dev_address = dev_addr;
-	cmd->reg_address = cpu_to_le32(reg_addr);
-
-	status = i40evf_asq_send_command(hw, &desc, NULL, 0, cmd_details);
-	if (!status)
-		*reg_val = le32_to_cpu(cmd->reg_value);
-
-	return status;
-}
-
 /**
  * i40e_aq_send_msg_to_pf
  * @hw: pointer to the hardware structure
-- 
cgit v1.2.3


From 91f0654461f615247fb6cef6fc9de57f6607a677 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 31 Jul 2018 03:41:38 -0700
Subject: i40e: add helper function for copying strings from stat arrays

Many of the ethtool statistics use the same basic logic for copying
strings into the supplied buffer. A set of stats are stored in a const
array of i40e_stats structures, and we apply these all together.

Simplify the stats code by introducing a helper function which can take
a stats array and copy the strings into the buffer, updating the buffer
pointer as we go.

We use a macro to implement i40e_add_stat_strings so that ARRAY_SIZE can
be used on the array passed in. This ensures that we always use the
matching size in __i40e_add_stat_strings.

More complex stats currently do not use i40e_stats arrays, usually due
to custom formatted strings, or because the stats are not laid out in
the expected way. These stats will be updated to use the helper function
in separate future patches.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 59 +++++++++++++++++---------
 1 file changed, 39 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 6947a2a571cb..20e86304e346 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1815,6 +1815,37 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 		*(data++) = pf->stats.priority_xon_2_xoff[i];
 }
 
+/**
+ * __i40e_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ * @size: size of the stats array
+ *
+ * Copy the strings described by stats into the buffer pointed at by p.
+ **/
+static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[],
+				    const unsigned int size)
+{
+	unsigned int i;
+
+	for (i = 0; i < size; i++) {
+		snprintf(*p, ETH_GSTRING_LEN, "%s", stats[i].stat_string);
+		*p += ETH_GSTRING_LEN;
+	}
+}
+
+/**
+ * 40e_add_stat_strings - copy stat strings into ethtool buffer
+ * @p: ethtool supplied buffer
+ * @stats: stat definitions array
+ *
+ * Format and copy the strings described by the const static stats value into
+ * the buffer pointed at by p. Assumes that stats can have ARRAY_SIZE called
+ * for it.
+ **/
+#define i40e_add_stat_strings(p, stats, ...) \
+	__i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats))
+
 /**
  * i40e_get_stat_strings - copy stat strings into supplied buffer
  * @netdev: the netdev to collect strings for
@@ -1833,16 +1864,10 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 	unsigned int i;
 	u8 *p = data;
 
-	for (i = 0; i < I40E_NETDEV_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_net_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MISC_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_misc_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
+	i40e_add_stat_strings(&data, i40e_gstrings_net_stats);
+
+	i40e_add_stat_strings(&data, i40e_gstrings_misc_stats);
+
 	for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev); i++) {
 		snprintf(data, ETH_GSTRING_LEN, "tx-%u.tx_packets", i);
 		data += ETH_GSTRING_LEN;
@@ -1856,11 +1881,8 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 	if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
 		return;
 
-	for (i = 0; i < I40E_VEB_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_veb_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
+	i40e_add_stat_strings(&data, i40e_gstrings_veb_stats);
+
 	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
 		snprintf(data, ETH_GSTRING_LEN,
 			 "veb.tc_%u_tx_packets", i);
@@ -1876,11 +1898,8 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 		data += ETH_GSTRING_LEN;
 	}
 
-	for (i = 0; i < I40E_GLOBAL_STATS_LEN; i++) {
-		snprintf(data, ETH_GSTRING_LEN, "%s",
-			 i40e_gstrings_stats[i].stat_string);
-		data += ETH_GSTRING_LEN;
-	}
+	i40e_add_stat_strings(&data, i40e_gstrings_stats);
+
 	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
 		snprintf(data, ETH_GSTRING_LEN,
 			 "port.tx_priority_%u_xon", i);
-- 
cgit v1.2.3


From f303048067a78d95947c1748ce1e55940ab2100b Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 31 Jul 2018 03:41:39 -0700
Subject: i40e: add helper to copy statistic values into ethtool buffer

Similar to the helper function to copy the ethtool stats strings, add
and use a helper function for copying the ethtool stats into the
supplied buffer.

Just like before, we use a macro to avoid having to pass ARRAY_SIZE
manually, so as to reduce chance of bugs.

Some of the stats, especially queue stats, are a bit trickier, and will
be handled in future patches.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 116 ++++++++++++++++++++-----
 1 file changed, 93 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 20e86304e346..c051afe98b49 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1705,6 +1705,89 @@ static int i40e_get_sset_count(struct net_device *netdev, int sset)
 	}
 }
 
+/**
+ * i40e_add_one_ethtool_stat - copy the stat into the supplied buffer
+ * @data: location to store the stat value
+ * @pointer: basis for where to copy from
+ * @stat: the stat definition
+ *
+ * Copies the stat data defined by the pointer and stat structure pair into
+ * the memory supplied as data. Used to implement i40e_add_ethtool_stats.
+ * If the pointer is null, data will be zero'd.
+ */
+static inline void
+i40e_add_one_ethtool_stat(u64 *data, void *pointer,
+			  const struct i40e_stats *stat)
+{
+	char *p;
+
+	if (!pointer) {
+		/* ensure that the ethtool data buffer is zero'd for any stats
+		 * which don't have a valid pointer.
+		 */
+		*data = 0;
+		return;
+	}
+
+	p = (char *)pointer + stat->stat_offset;
+	switch (stat->sizeof_stat) {
+	case sizeof(u64):
+		*data = *((u64 *)p);
+		break;
+	case sizeof(u32):
+		*data = *((u32 *)p);
+		break;
+	case sizeof(u16):
+		*data = *((u16 *)p);
+		break;
+	case sizeof(u8):
+		*data = *((u8 *)p);
+		break;
+	default:
+		WARN_ONCE(1, "unexpected stat size for %s",
+			  stat->stat_string);
+		*data = 0;
+	}
+}
+
+/**
+ * __i40e_add_ethtool_stats - copy stats into the ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location to copy stats from
+ * @stats: array of stats to copy
+ * @size: the size of the stats definition
+ *
+ * Copy the stats defined by the stats array using the pointer as a base into
+ * the data buffer supplied by ethtool. Updates the data pointer to point to
+ * the next empty location for successive calls to __i40e_add_ethtool_stats.
+ * If pointer is null, set the data values to zero and update the pointer to
+ * skip these stats.
+ **/
+static inline void
+__i40e_add_ethtool_stats(u64 **data, void *pointer,
+			 const struct i40e_stats stats[],
+			 const unsigned int size)
+{
+	unsigned int i;
+
+	for (i = 0; i < size; i++)
+		i40e_add_one_ethtool_stat((*data)++, pointer, &stats[i]);
+}
+
+/**
+ * i40e_add_ethtool_stats - copy stats into ethtool supplied buffer
+ * @data: ethtool stats buffer
+ * @pointer: location where stats are stored
+ * @stats: static const array of stat definitions
+ *
+ * Macro to ease the use of __i40e_add_ethtool_stats by taking a static
+ * constant stats array and passing the ARRAY_SIZE(). This avoids typos by
+ * ensuring that we pass the size associated with the given stats array.
+ * Assumes that stats is an array.
+ **/
+#define i40e_add_ethtool_stats(data, pointer, stats) \
+	__i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
+
 /**
  * i40e_get_ethtool_stats - copy stat values into supplied buffer
  * @netdev: the netdev to collect stats for
@@ -1727,22 +1810,15 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
 	unsigned int i;
-	char *p;
-	struct rtnl_link_stats64 *net_stats = i40e_get_vsi_stats_struct(vsi);
 	unsigned int start;
 
 	i40e_update_stats(vsi);
 
-	for (i = 0; i < I40E_NETDEV_STATS_LEN; i++) {
-		p = (char *)net_stats + i40e_gstrings_net_stats[i].stat_offset;
-		*(data++) = (i40e_gstrings_net_stats[i].sizeof_stat ==
-			sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
-	for (i = 0; i < I40E_MISC_STATS_LEN; i++) {
-		p = (char *)vsi + i40e_gstrings_misc_stats[i].stat_offset;
-		*(data++) = (i40e_gstrings_misc_stats[i].sizeof_stat ==
-			    sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
+	i40e_add_ethtool_stats(&data, i40e_get_vsi_stats_struct(vsi),
+			       i40e_gstrings_net_stats);
+
+	i40e_add_ethtool_stats(&data, vsi, i40e_gstrings_misc_stats);
+
 	rcu_read_lock();
 	for (i = 0; i < I40E_MAX_NUM_QUEUES(netdev) ; i++) {
 		tx_ring = READ_ONCE(vsi->tx_rings[i]);
@@ -1783,12 +1859,8 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	    (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
 		struct i40e_veb *veb = pf->veb[pf->lan_veb];
 
-		for (i = 0; i < I40E_VEB_STATS_LEN; i++) {
-			p = (char *)veb;
-			p += i40e_gstrings_veb_stats[i].stat_offset;
-			*(data++) = (i40e_gstrings_veb_stats[i].sizeof_stat ==
-				     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-		}
+		i40e_add_ethtool_stats(&data, veb, i40e_gstrings_veb_stats);
+
 		for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
 			*(data++) = veb->tc_stats.tc_tx_packets[i];
 			*(data++) = veb->tc_stats.tc_tx_bytes[i];
@@ -1798,11 +1870,9 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	} else {
 		data += I40E_VEB_STATS_TOTAL;
 	}
-	for (i = 0; i < I40E_GLOBAL_STATS_LEN; i++) {
-		p = (char *)pf + i40e_gstrings_stats[i].stat_offset;
-		*(data++) = (i40e_gstrings_stats[i].sizeof_stat ==
-			     sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
-	}
+
+	i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats);
+
 	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
 		*(data++) = pf->stats.priority_xon_tx[i];
 		*(data++) = pf->stats.priority_xoff_tx[i];
-- 
cgit v1.2.3


From 1ac2ee231f922d46cc7bb4c9f02eeb841b3e4b47 Mon Sep 17 00:00:00 2001
From: Mariusz Stachura <mariusz.stachura@intel.com>
Date: Tue, 31 Jul 2018 03:41:40 -0700
Subject: i40e: Set fec_config when forcing link state

This patch configures FEC setting in i40e_force_link_state().
For some reason setting this field was overlooked thus causing
25G link to be configured incorrectly.

Signed-off-by: Mariusz Stachura <mariusz.stachura@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 13940e0ba939..a730f48b102c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -6597,6 +6597,8 @@ static i40e_status i40e_force_link_state(struct i40e_pf *pf, bool is_up)
 	config.eee_capability = abilities.eee_capability;
 	config.eeer = abilities.eeer_val;
 	config.low_power_ctrl = abilities.d3_lpan;
+	config.fec_config = abilities.fec_cfg_curr_mod_ext_info &
+			    I40E_AQ_PHY_FEC_CONFIG_MASK;
 	err = i40e_aq_set_phy_config(hw, &config, NULL);
 
 	if (err) {
-- 
cgit v1.2.3


From 1510ae0be2a4d4630823752235c41f8a0e06f37a Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 31 Jul 2018 03:41:41 -0700
Subject: i40e: convert VEB TC stats to use an i40e_stats array

The VEB TC stats are currently implemented with separate parsing,
instead of using the i40e_stats array and associated helper functions.
This is likely because the stats rely on embedding the TC number into
the stat name.

Update i40e_add_stat_strings to take variadic arguments, and use these
to vsnprintf the i40e_stats string as a string containing format
specifiers.

Create a stats array for the VEB TC related stats,
i40e_gstrings_veb_tc_stats, and use this along with the helper functions
to remove the specialized boiler plate code.

Always call i40e_add_ethtool_stats for both this array and the general
VEB stats array. This ensures that we zero out any memory in case it was
not zero-allocated for us.

This ultimately results in less boiler plate code for the
i40e_get_stat_strings and i40e_get_ethtool_stats.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 83 +++++++++++++-------------
 1 file changed, 43 insertions(+), 40 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index c051afe98b49..52ccafe1d257 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -7,6 +7,11 @@
 #include "i40e_diag.h"
 
 struct i40e_stats {
+	/* The stat_string is expected to be a format string formatted using
+	 * vsnprintf by i40e_add_stat_strings. Every member of a stats array
+	 * should use the same format specifiers as they will be formatted
+	 * using the same variadic arguments.
+	 */
 	char stat_string[ETH_GSTRING_LEN];
 	int sizeof_stat;
 	int stat_offset;
@@ -56,6 +61,13 @@ static const struct i40e_stats i40e_gstrings_veb_stats[] = {
 	I40E_VEB_STAT("veb.rx_unknown_protocol", stats.rx_unknown_protocol),
 };
 
+static const struct i40e_stats i40e_gstrings_veb_tc_stats[] = {
+	I40E_VEB_STAT("veb.tc_%u_tx_packets", tc_stats.tc_tx_packets),
+	I40E_VEB_STAT("veb.tc_%u_tx_bytes", tc_stats.tc_tx_bytes),
+	I40E_VEB_STAT("veb.tc_%u_rx_packets", tc_stats.tc_rx_packets),
+	I40E_VEB_STAT("veb.tc_%u_rx_bytes", tc_stats.tc_rx_bytes),
+};
+
 static const struct i40e_stats i40e_gstrings_misc_stats[] = {
 	I40E_VSI_STAT("rx_unicast", eth_stats.rx_unicast),
 	I40E_VSI_STAT("tx_unicast", eth_stats.tx_unicast),
@@ -162,16 +174,14 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
 		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_tx) + \
 		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_2_xoff)) \
 		 / sizeof(u64))
-#define I40E_VEB_TC_STATS_LEN ( \
-		(FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_rx_packets) + \
-		 FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_rx_bytes) + \
-		 FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_tx_packets) + \
-		 FIELD_SIZEOF(struct i40e_veb, tc_stats.tc_tx_bytes)) \
-		 / sizeof(u64))
-#define I40E_VEB_STATS_LEN	ARRAY_SIZE(i40e_gstrings_veb_stats)
-#define I40E_VEB_STATS_TOTAL	(I40E_VEB_STATS_LEN + I40E_VEB_TC_STATS_LEN)
+
+#define I40E_VEB_STATS_LEN	(ARRAY_SIZE(i40e_gstrings_veb_stats) + \
+				 (ARRAY_SIZE(i40e_gstrings_veb_tc_stats) * \
+				  I40E_MAX_TRAFFIC_CLASS))
+
 #define I40E_PF_STATS_LEN(n)	(I40E_GLOBAL_STATS_LEN + \
 				 I40E_PFC_STATS_LEN + \
+				 I40E_VEB_STATS_LEN + \
 				 I40E_VSI_STATS_LEN((n)))
 
 enum i40e_ethtool_test_id {
@@ -1681,7 +1691,7 @@ static int i40e_get_stats_count(struct net_device *netdev)
 	struct i40e_pf *pf = vsi->back;
 
 	if (vsi == pf->vsi[pf->lan_vsi] && pf->hw.partition_id == 1)
-		return I40E_PF_STATS_LEN(netdev) + I40E_VEB_STATS_TOTAL;
+		return I40E_PF_STATS_LEN(netdev);
 	else
 		return I40E_VSI_STATS_LEN(netdev);
 }
@@ -1809,8 +1819,10 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	struct i40e_ring *tx_ring, *rx_ring;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	struct i40e_veb *veb = pf->veb[pf->lan_veb];
 	unsigned int i;
 	unsigned int start;
+	bool veb_stats;
 
 	i40e_update_stats(vsi);
 
@@ -1855,21 +1867,19 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
 		return;
 
-	if ((pf->lan_veb != I40E_NO_VEB) &&
-	    (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)) {
-		struct i40e_veb *veb = pf->veb[pf->lan_veb];
+	veb_stats = ((pf->lan_veb != I40E_NO_VEB) &&
+		     (pf->flags & I40E_FLAG_VEB_STATS_ENABLED));
 
-		i40e_add_ethtool_stats(&data, veb, i40e_gstrings_veb_stats);
+	/* If veb stats aren't enabled, pass NULL instead of the veb so that
+	 * we initialize stats to zero and update the data pointer
+	 * intelligently
+	 */
+	i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL,
+			       i40e_gstrings_veb_stats);
 
-		for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
-			*(data++) = veb->tc_stats.tc_tx_packets[i];
-			*(data++) = veb->tc_stats.tc_tx_bytes[i];
-			*(data++) = veb->tc_stats.tc_rx_packets[i];
-			*(data++) = veb->tc_stats.tc_rx_bytes[i];
-		}
-	} else {
-		data += I40E_VEB_STATS_TOTAL;
-	}
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+		i40e_add_ethtool_stats(&data, veb_stats ? veb : NULL,
+				       i40e_gstrings_veb_tc_stats);
 
 	i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats);
 
@@ -1891,16 +1901,21 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
  * @stats: stat definitions array
  * @size: size of the stats array
  *
- * Copy the strings described by stats into the buffer pointed at by p.
+ * Format and copy the strings described by stats into the buffer pointed at
+ * by p.
  **/
 static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[],
-				    const unsigned int size)
+				    const unsigned int size, ...)
 {
 	unsigned int i;
 
 	for (i = 0; i < size; i++) {
-		snprintf(*p, ETH_GSTRING_LEN, "%s", stats[i].stat_string);
+		va_list args;
+
+		va_start(args, size);
+		vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args);
 		*p += ETH_GSTRING_LEN;
+		va_end(args);
 	}
 }
 
@@ -1914,7 +1929,7 @@ static void __i40e_add_stat_strings(u8 **p, const struct i40e_stats stats[],
  * for it.
  **/
 #define i40e_add_stat_strings(p, stats, ...) \
-	__i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats))
+	__i40e_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__)
 
 /**
  * i40e_get_stat_strings - copy stat strings into supplied buffer
@@ -1953,20 +1968,8 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 
 	i40e_add_stat_strings(&data, i40e_gstrings_veb_stats);
 
-	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_tx_packets", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_tx_bytes", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_rx_packets", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "veb.tc_%u_rx_bytes", i);
-		data += ETH_GSTRING_LEN;
-	}
+	for (i = 0; i < I40E_MAX_TRAFFIC_CLASS; i++)
+		i40e_add_stat_strings(&data, i40e_gstrings_veb_tc_stats, i);
 
 	i40e_add_stat_strings(&data, i40e_gstrings_stats);
 
-- 
cgit v1.2.3


From f25848d4cdf2c5db5c506ca6553c79f97db19975 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 31 Jul 2018 03:41:42 -0700
Subject: i40e: convert priority flow control stats to use helpers

The priority flow control statistics are laid out in the stats structure
using arrays. This made it unwieldy to use as part of an i40e_stats
array.

Add a new structure type, i40e_pfc_stats, and a helper function
i40e_get_pfc_stats which can return the stats for a given priority
value as an i40e_pfc_stats structure.

Use this to create an i40e_stats array, which we'll use to format and
copy the strings and stats into the supplied buffers.

This reduces even more boiler plate code in i40e_get_ethtool_stats and
i40e_get_stat_strings.

An alternative would be to modify the structure definition for the pfc
stats, but this is more invasive to the rest of the code base.

Note that a macro was used to setup the copy of stats from the
pf->stats, as this reduces the chance of typos in the code names. It
will produce a checkpatch.pl warning due to re-use of a macro argument.
In this case, it should be safe, as the macro will fail to compile in
cases where the argument is not a simple structure member name, and thus
arguments with side effects should not be an issue.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 87 +++++++++++++++-----------
 1 file changed, 51 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 52ccafe1d257..9c380c0b0202 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -31,6 +31,8 @@ struct i40e_stats {
 	I40E_STAT(struct i40e_vsi, _name, _stat)
 #define I40E_VEB_STAT(_name, _stat) \
 	I40E_STAT(struct i40e_veb, _name, _stat)
+#define I40E_PFC_STAT(_name, _stat) \
+	I40E_STAT(struct i40e_pfc_stats, _name, _stat)
 
 static const struct i40e_stats i40e_gstrings_net_stats[] = {
 	I40E_NETDEV_STAT(rx_packets),
@@ -153,6 +155,22 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
 	I40E_PF_STAT("port.rx_lpi_count", stats.rx_lpi_count),
 };
 
+struct i40e_pfc_stats {
+	u64 priority_xon_rx;
+	u64 priority_xoff_rx;
+	u64 priority_xon_tx;
+	u64 priority_xoff_tx;
+	u64 priority_xon_2_xoff;
+};
+
+static const struct i40e_stats i40e_gstrings_pfc_stats[] = {
+	I40E_PFC_STAT("port.tx_priority_%u_xon_tx", priority_xon_tx),
+	I40E_PFC_STAT("port.tx_priority_%u_xoff_tx", priority_xoff_tx),
+	I40E_PFC_STAT("port.rx_priority_%u_xon_rx", priority_xon_rx),
+	I40E_PFC_STAT("port.rx_priority_%u_xoff_rx", priority_xoff_rx),
+	I40E_PFC_STAT("port.rx_priority_%u_xon_2_xoff", priority_xon_2_xoff),
+};
+
 /* We use num_tx_queues here as a proxy for the maximum number of queues
  * available because we always allocate queues symmetrically.
  */
@@ -167,13 +185,9 @@ static const struct i40e_stats i40e_gstrings_stats[] = {
 #define I40E_VSI_STATS_LEN(n)	(I40E_NETDEV_STATS_LEN + \
 				 I40E_MISC_STATS_LEN + \
 				 I40E_QUEUE_STATS_LEN((n)))
-#define I40E_PFC_STATS_LEN ( \
-		(FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_rx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_rx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xoff_tx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_tx) + \
-		 FIELD_SIZEOF(struct i40e_pf, stats.priority_xon_2_xoff)) \
-		 / sizeof(u64))
+
+#define I40E_PFC_STATS_LEN	(ARRAY_SIZE(i40e_gstrings_pfc_stats) * \
+				 I40E_MAX_USER_PRIORITY)
 
 #define I40E_VEB_STATS_LEN	(ARRAY_SIZE(i40e_gstrings_veb_stats) + \
 				 (ARRAY_SIZE(i40e_gstrings_veb_tc_stats) * \
@@ -1798,6 +1812,31 @@ __i40e_add_ethtool_stats(u64 **data, void *pointer,
 #define i40e_add_ethtool_stats(data, pointer, stats) \
 	__i40e_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats))
 
+/**
+ * i40e_get_pfc_stats - copy HW PFC statistics to formatted structure
+ * @pf: the PF device structure
+ * @i: the priority value to copy
+ *
+ * The PFC stats are found as arrays in pf->stats, which is not easy to pass
+ * into i40e_add_ethtool_stats. Produce a formatted i40e_pfc_stats structure
+ * of the PFC stats for the given priority.
+ **/
+static inline struct i40e_pfc_stats
+i40e_get_pfc_stats(struct i40e_pf *pf, unsigned int i)
+{
+#define I40E_GET_PFC_STAT(stat, priority) \
+	.stat = pf->stats.stat[priority]
+
+	struct i40e_pfc_stats pfc = {
+		I40E_GET_PFC_STAT(priority_xon_rx, i),
+		I40E_GET_PFC_STAT(priority_xoff_rx, i),
+		I40E_GET_PFC_STAT(priority_xon_tx, i),
+		I40E_GET_PFC_STAT(priority_xoff_tx, i),
+		I40E_GET_PFC_STAT(priority_xon_2_xoff, i),
+	};
+	return pfc;
+}
+
 /**
  * i40e_get_ethtool_stats - copy stat values into supplied buffer
  * @netdev: the netdev to collect stats for
@@ -1884,15 +1923,10 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	i40e_add_ethtool_stats(&data, pf, i40e_gstrings_stats);
 
 	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		*(data++) = pf->stats.priority_xon_tx[i];
-		*(data++) = pf->stats.priority_xoff_tx[i];
-	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		*(data++) = pf->stats.priority_xon_rx[i];
-		*(data++) = pf->stats.priority_xoff_rx[i];
+		struct i40e_pfc_stats pfc = i40e_get_pfc_stats(pf, i);
+
+		i40e_add_ethtool_stats(&data, &pfc, i40e_gstrings_pfc_stats);
 	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++)
-		*(data++) = pf->stats.priority_xon_2_xoff[i];
 }
 
 /**
@@ -1973,27 +2007,8 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data)
 
 	i40e_add_stat_strings(&data, i40e_gstrings_stats);
 
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.tx_priority_%u_xon", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.tx_priority_%u_xoff", i);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.rx_priority_%u_xon", i);
-		data += ETH_GSTRING_LEN;
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.rx_priority_%u_xoff", i);
-		data += ETH_GSTRING_LEN;
-	}
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		snprintf(data, ETH_GSTRING_LEN,
-			 "port.rx_priority_%u_xon_2_xoff", i);
-		data += ETH_GSTRING_LEN;
-	}
+	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++)
+		i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i);
 
 	WARN_ONCE(p - data != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN,
 		  "stat strings count mismatch!");
-- 
cgit v1.2.3


From cd9139220b87f40ea83858de1d6436c639376ce7 Mon Sep 17 00:00:00 2001
From: Juergen Gross <jgross@suse.com>
Date: Wed, 13 Jun 2018 11:58:06 +0200
Subject: xen: don't use privcmd_call() from xen_mc_flush()

Using privcmd_call() for a singleton multicall seems to be wrong, as
privcmd_call() is using stac()/clac() to enable hypervisor access to
Linux user space.

Even if currently not a problem (pv domains can't use SMAP while HVM
and PVH domains can't use multicalls) things might change when
PVH dom0 support is added to the kernel.

Reported-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 arch/x86/include/asm/xen/hypercall.h | 25 +++++++++++++++++++------
 arch/x86/xen/multicalls.c            |  6 +++---
 2 files changed, 22 insertions(+), 9 deletions(-)

diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index bfd882617613..6b2f90a0b149 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -209,24 +209,37 @@ extern struct { char _entry[32]; } hypercall_page[];
 })
 
 static inline long
-privcmd_call(unsigned call,
-	     unsigned long a1, unsigned long a2,
-	     unsigned long a3, unsigned long a4,
-	     unsigned long a5)
+xen_single_call(unsigned int call,
+		unsigned long a1, unsigned long a2,
+		unsigned long a3, unsigned long a4,
+		unsigned long a5)
 {
 	__HYPERCALL_DECLS;
 	__HYPERCALL_5ARG(a1, a2, a3, a4, a5);
 
-	stac();
 	asm volatile(CALL_NOSPEC
 		     : __HYPERCALL_5PARAM
 		     : [thunk_target] "a" (&hypercall_page[call])
 		     : __HYPERCALL_CLOBBER5);
-	clac();
 
 	return (long)__res;
 }
 
+static inline long
+privcmd_call(unsigned int call,
+	     unsigned long a1, unsigned long a2,
+	     unsigned long a3, unsigned long a4,
+	     unsigned long a5)
+{
+	long res;
+
+	stac();
+	res = xen_single_call(call, a1, a2, a3, a4, a5);
+	clac();
+
+	return res;
+}
+
 static inline int
 HYPERVISOR_set_trap_table(struct trap_info *table)
 {
diff --git a/arch/x86/xen/multicalls.c b/arch/x86/xen/multicalls.c
index dc502ca8263e..2bce7958ce8b 100644
--- a/arch/x86/xen/multicalls.c
+++ b/arch/x86/xen/multicalls.c
@@ -80,9 +80,9 @@ void xen_mc_flush(void)
 		   and just do the call directly. */
 		mc = &b->entries[0];
 
-		mc->result = privcmd_call(mc->op,
-					  mc->args[0], mc->args[1], mc->args[2], 
-					  mc->args[3], mc->args[4]);
+		mc->result = xen_single_call(mc->op, mc->args[0], mc->args[1],
+					     mc->args[2], mc->args[3],
+					     mc->args[4]);
 		ret = mc->result < 0;
 		break;
 
-- 
cgit v1.2.3


From c5d99d2b35dadebab2408bb10dcd50364eaaf9f4 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Tue, 7 Aug 2018 10:34:44 -0400
Subject: ieee802154: hwsim: fix rcu address annotation

This patch fixes the following sparse warning about mismatch rcu
attribute for address space annotation:

...
error: incompatible types in comparison expression (different modifiers)
error: incompatible types in comparison expression (different address spaces)
...

Some __rcu annotation was at non-pointers list head structures and one was
missing in edge information which is used by rcu_assign_pointer() to
update edge setting information.

Cc: Stefan Schmidt <stefan@datenfreihafen.org>
Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb")
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/mac802154_hwsim.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 1982308b9b1c..f4e92054f7df 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -36,7 +36,7 @@ MODULE_LICENSE("GPL");
 static LIST_HEAD(hwsim_phys);
 static DEFINE_MUTEX(hwsim_phys_lock);
 
-static __rcu LIST_HEAD(hwsim_ifup_phys);
+static LIST_HEAD(hwsim_ifup_phys);
 
 static struct platform_device *mac802154hwsim_dev;
 
@@ -68,7 +68,7 @@ struct hwsim_edge_info {
 
 struct hwsim_edge {
 	struct hwsim_phy *endpoint;
-	struct hwsim_edge_info *info;
+	struct hwsim_edge_info __rcu *info;
 
 	struct list_head list;
 	struct rcu_head rcu;
@@ -81,7 +81,7 @@ struct hwsim_phy {
 	struct hwsim_pib __rcu *pib;
 
 	bool suspended;
-	struct list_head __rcu edges;
+	struct list_head edges;
 
 	struct list_head list;
 	struct list_head list_ifup;
-- 
cgit v1.2.3


From 484a84f25ca7817c3662001316ba7d1e06b74ae2 Mon Sep 17 00:00:00 2001
From: Michael Larabel <michael@phoronix.com>
Date: Tue, 7 Aug 2018 09:54:54 -0400
Subject: hwmon: (k10temp) 27C Offset needed for Threadripper2

For at least the Threadripper 2950X and Threadripper 2990WX,
it's confirmed a 27 degree offset is needed.

Signed-off-by: Michael Larabel <michael@phoronix.com>
Cc: stable@vger.kernel.org
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/k10temp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 17c6460ae351..577e2ede5a1a 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -105,6 +105,8 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen Threadripper 1950", 10000 },
 	{ 0x17, "AMD Ryzen Threadripper 1920", 10000 },
 	{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
+	{ 0x17, "AMD Ryzen Threadripper 2950X", 27000 },
+	{ 0x17, "AMD Ryzen Threadripper 2990WX", 27000 },
 };
 
 static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
-- 
cgit v1.2.3


From 88c6f8a3977cc35997b47e2f99f080a15559c1eb Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Tue, 7 Aug 2018 12:24:29 +0200
Subject: x86/mm/pti: Fix 32 bit PCID check

The check uses the wrong operator and causes false positive
warnings in the kernel log on some systems.

Fixes: 5e8105950a8b3 ('x86/mm/pti: Add Warning when booting on a PCID capable CPU')
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1533637471-30953-2-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index ef8db6ffc836..113ba14a03d8 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -549,7 +549,7 @@ void __init pti_init(void)
 	 * supported on 32 bit anyway. To print the warning we need to
 	 * check with cpuid directly again.
 	 */
-	if (cpuid_ecx(0x1) && BIT(17)) {
+	if (cpuid_ecx(0x1) & BIT(17)) {
 		/* Use printk to work around pr_fmt() */
 		printk(KERN_WARNING "\n");
 		printk(KERN_WARNING "************************************************************\n");
-- 
cgit v1.2.3


From 08eeb44b2466feb1cf98fb0e8e6a1cf932ece6df Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Mon, 6 Aug 2018 18:29:51 -0700
Subject: MIPS: Use read-write output operand in __write_64bit_c0_split()

Commit c22c80431055 ("MIPS: Fix input modify in
__write_64bit_c0_split()") modified __write_64bit_c0_split() constraints
such that we have both an input & an output which we hope to assign to
the same registers, and modify the output rather than incorrectly
clobbering an input.

The way in which we use both an output & an input parameter with the
input constrained to share the output registers is a little convoluted &
also problematic for clang, which complains if the input & output values
have different widths. For example:

  In file included from kernel/fork.c:98:
  ./arch/mips/include/asm/mmu_context.h:149:19: error: unsupported
    inline asm: input with type 'unsigned long' matching output with
    type 'unsigned long long'
          write_c0_entryhi(cpu_asid(cpu, next));
          ~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~~~~~~~
  ./arch/mips/include/asm/mmu_context.h:93:2: note: expanded from macro
    'cpu_asid'
          (cpu_context((cpu), (mm)) & cpu_asid_mask(&cpu_data[cpu]))
          ^
  ./arch/mips/include/asm/mipsregs.h:1617:65: note: expanded from macro
    'write_c0_entryhi'
  #define write_c0_entryhi(val)   __write_ulong_c0_register($10, 0, val)
                                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~
  ./arch/mips/include/asm/mipsregs.h:1430:39: note: expanded from macro
    '__write_ulong_c0_register'
                  __write_64bit_c0_register(reg, sel, val);               \
                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~
  ./arch/mips/include/asm/mipsregs.h:1400:41: note: expanded from macro
    '__write_64bit_c0_register'
                  __write_64bit_c0_split(register, sel, value);           \
                  ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~
  ./arch/mips/include/asm/mipsregs.h:1498:13: note: expanded from macro
    '__write_64bit_c0_split'
                          : "r,0" (val));                                 \
                                   ^~~

We can both fix this build failure & simplify the code somewhat by
assigning the __tmp variable with the input value in C prior to our
inline assembly, and then using a single read-write output operand (ie.
a constraint beginning with +) to provide this value to our assembly.

Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/include/asm/mipsregs.h | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index b6237ffbacf5..dd46ab2a4ffd 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1485,32 +1485,30 @@ do {									\
 
 #define __write_64bit_c0_split(source, sel, val)			\
 do {									\
-	unsigned long long __tmp;					\
+	unsigned long long __tmp = (val);				\
 	unsigned long __flags;						\
 									\
 	local_irq_save(__flags);					\
 	if (sel == 0)							\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L1, 32\n\t"			\
+			"dsll\t%L0, %L0, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M1, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source "\n\t"			\
 			".set\tmips0"					\
-			: "=&r,r" (__tmp)				\
-			: "r,0" (val));					\
+			: "+r" (__tmp));				\
 	else								\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
-			"dsll\t%L0, %L1, 32\n\t"			\
+			"dsll\t%L0, %L0, 32\n\t"			\
 			"dsrl\t%L0, %L0, 32\n\t"			\
-			"dsll\t%M0, %M1, 32\n\t"			\
+			"dsll\t%M0, %M0, 32\n\t"			\
 			"or\t%L0, %L0, %M0\n\t"				\
 			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
 			".set\tmips0"					\
-			: "=&r,r" (__tmp)				\
-			: "r,0" (val));					\
+			: "+r" (__tmp));				\
 	local_irq_restore(__flags);					\
 } while (0)
 
-- 
cgit v1.2.3


From 36dc5b20e31db5cd470eb1934815320e7a0434c3 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Tue, 7 Aug 2018 10:15:04 -0700
Subject: MIPS: Use dins to simplify __write_64bit_c0_split()

The code in __write_64bit_c0_split() is used by MIPS32 kernels running
on MIPS64 CPUs to write a 64-bit value to a 64-bit coprocessor 0
register using a single 64-bit dmtc0 instruction. It does this by
combining the 2x 32-bit registers used to hold the 64-bit value into a
single register, which in the existing code involves three steps:

  1) Zero extend register A which holds bits 31:0 of our data, since it
     may have previously held a sign-extended value.

  2) Shift register B which holds bits 63:32 of our data in bits 31:0
     left by 32 bits, such that the bits forming our data are in the
     position they'll be in the final 64-bit value & bits 31:0 of the
     register are zero.

  3) Or the two registers together to form the 64-bit value in one
     64-bit register.

From MIPS r2 onwards we have a dins instruction which can effectively
perform all 3 of those steps using a single instruction.

Add a path for MIPS r2 & beyond which uses dins to take bits 31:0 from
register B & insert them into bits 63:32 of register A, giving us our
full 64-bit value in register A with one instruction.

Since we know that MIPS r2 & above support the sel field for the dmtc0
instruction, we don't bother special casing sel==0. Omiting the sel
field would assemble to exactly the same instruction as when we
explicitly specify that it equals zero.

Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/include/asm/mipsregs.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index dd46ab2a4ffd..a3ee982b4c1a 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -16,6 +16,7 @@
 #include <linux/linkage.h>
 #include <linux/types.h>
 #include <asm/hazards.h>
+#include <asm/isa-rev.h>
 #include <asm/war.h>
 
 /*
@@ -1489,7 +1490,15 @@ do {									\
 	unsigned long __flags;						\
 									\
 	local_irq_save(__flags);					\
-	if (sel == 0)							\
+	if (MIPS_ISA_REV >= 2)						\
+		__asm__ __volatile__(					\
+			".set\tpush\n\t"				\
+			".set\t" MIPS_ISA_LEVEL "\n\t"			\
+			"dins\t%L0, %M0, 32, 32\n\t"			\
+			"dmtc0\t%L0, " #source ", " #sel "\n\t"		\
+			".set\tpop"					\
+			: "+r" (__tmp));				\
+	else if (sel == 0)						\
 		__asm__ __volatile__(					\
 			".set\tmips64\n\t"				\
 			"dsll\t%L0, %L0, 32\n\t"			\
-- 
cgit v1.2.3


From 2ba090d521c5e09f32316c179d25bb6f699d3568 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 7 Aug 2018 10:57:12 -0700
Subject: xfs: use WRITE_ONCE to update if_seq

This adds ordering of the updates and makes sure we always see the if_seq
update before the extent tree is modified.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_iext_tree.c | 20 +++++++++++++++++---
 fs/xfs/xfs_aops.c             |  4 ++--
 fs/xfs/xfs_iomap.c            |  3 ++-
 3 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_iext_tree.c b/fs/xfs/libxfs/xfs_iext_tree.c
index 8a7aea041ee1..771dd072015d 100644
--- a/fs/xfs/libxfs/xfs_iext_tree.c
+++ b/fs/xfs/libxfs/xfs_iext_tree.c
@@ -14,6 +14,7 @@
 #include "xfs_inode_fork.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_bmap.h"
 #include "xfs_trace.h"
 
 /*
@@ -612,6 +613,19 @@ xfs_iext_realloc_root(
 	cur->leaf = new;
 }
 
+/*
+ * Increment the sequence counter if we are on a COW fork.  This allows
+ * the writeback code to skip looking for a COW extent if the COW fork
+ * hasn't changed.  We use WRITE_ONCE here to ensure the update to the
+ * sequence counter is seen before the modifications to the extent
+ * tree itself take effect.
+ */
+static inline void xfs_iext_inc_seq(struct xfs_ifork *ifp, int state)
+{
+	if (state & BMAP_COWFORK)
+		WRITE_ONCE(ifp->if_seq, READ_ONCE(ifp->if_seq) + 1);
+}
+
 void
 xfs_iext_insert(
 	struct xfs_inode	*ip,
@@ -624,7 +638,7 @@ xfs_iext_insert(
 	struct xfs_iext_leaf	*new = NULL;
 	int			nr_entries, i;
 
-	ifp->if_seq++;
+	xfs_iext_inc_seq(ifp, state);
 
 	if (ifp->if_height == 0)
 		xfs_iext_alloc_root(ifp, cur);
@@ -866,7 +880,7 @@ xfs_iext_remove(
 	ASSERT(ifp->if_u1.if_root != NULL);
 	ASSERT(xfs_iext_valid(ifp, cur));
 
-	ifp->if_seq++;
+	xfs_iext_inc_seq(ifp, state);
 
 	nr_entries = xfs_iext_leaf_nr_entries(ifp, leaf, cur->pos) - 1;
 	for (i = cur->pos; i < nr_entries; i++)
@@ -974,7 +988,7 @@ xfs_iext_update_extent(
 {
 	struct xfs_ifork	*ifp = xfs_iext_state_to_fork(ip, state);
 
-	ifp->if_seq++;
+	xfs_iext_inc_seq(ifp, state);
 
 	if (cur->pos == 0) {
 		struct xfs_bmbt_irec	old;
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 235b4ddcd324..49f5f5896a43 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -351,7 +351,7 @@ xfs_map_blocks(
 	if (imap_valid &&
 	    (!xfs_inode_has_cow_data(ip) ||
 	     wpc->io_type == XFS_IO_COW ||
-	     wpc->cow_seq == ip->i_cowfp->if_seq))
+	     wpc->cow_seq == READ_ONCE(ip->i_cowfp->if_seq)))
 		return 0;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -380,7 +380,7 @@ xfs_map_blocks(
 	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
 		cow_fsb = imap.br_startoff;
 	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
-		wpc->cow_seq = ip->i_cowfp->if_seq;
+		wpc->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
 		xfs_iunlock(ip, XFS_ILOCK_SHARED);
 		/*
 		 * Truncate can race with writeback since writeback doesn't
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 3282575e2df4..6320aca39f39 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -655,6 +655,7 @@ xfs_iomap_write_allocate(
 	unsigned int	*cow_seq)
 {
 	xfs_mount_t	*mp = ip->i_mount;
+	struct xfs_ifork *ifp = XFS_IFORK_PTR(ip, whichfork);
 	xfs_fileoff_t	offset_fsb, last_block;
 	xfs_fileoff_t	end_fsb, map_start_fsb;
 	xfs_filblks_t	count_fsb;
@@ -768,7 +769,7 @@ xfs_iomap_write_allocate(
 				goto error0;
 
 			if (whichfork == XFS_COW_FORK)
-				*cow_seq = XFS_IFORK_PTR(ip, whichfork)->if_seq;
+				*cow_seq = READ_ONCE(ifp->if_seq);
 			xfs_iunlock(ip, XFS_ILOCK_EXCL);
 		}
 
-- 
cgit v1.2.3


From 73971b172a435079340007bee12b4944cc599a8a Mon Sep 17 00:00:00 2001
From: Brian Foster <bfoster@redhat.com>
Date: Tue, 7 Aug 2018 10:57:13 -0700
Subject: xfs: remove dead error handling code in xfs_dquot_disk_alloc()

Colin Ian King reports that commit 82ff27bc52 ("xfs: automatic dfops
buffer relogging") leaves around some dead error handling code in
xfs_dquot_disk_alloc(). This was discovered via Coverity scan.

Since the associated commit eliminates the act of joining a buffer
to a dfops, this intermediate error state is no longer possible and
the error handling code can be removed. Since the caller cancels the
transaction on error, which cancels the dfops, eliminate the
unnecessary xfs_defer_cancel() call and error handling labels.

Fixes: 82ff27bc52 ("xfs: automatic dfops buffer relogging")
Reported-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_dquot.c | 26 ++++++--------------------
 1 file changed, 6 insertions(+), 20 deletions(-)

diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 70a76ac41f01..87e6dd5326d5 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -311,7 +311,7 @@ xfs_dquot_disk_alloc(
 			XFS_DQUOT_CLUSTER_SIZE_FSB, XFS_BMAPI_METADATA,
 			XFS_QM_DQALLOC_SPACE_RES(mp), &map, &nmaps);
 	if (error)
-		goto error0;
+		return error;
 	ASSERT(map.br_blockcount == XFS_DQUOT_CLUSTER_SIZE_FSB);
 	ASSERT(nmaps == 1);
 	ASSERT((map.br_startblock != DELAYSTARTBLOCK) &&
@@ -325,10 +325,8 @@ xfs_dquot_disk_alloc(
 	/* now we can just get the buffer (there's nothing to read yet) */
 	bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, dqp->q_blkno,
 			mp->m_quotainfo->qi_dqchunklen, 0);
-	if (!bp) {
-		error = -ENOMEM;
-		goto error1;
-	}
+	if (!bp)
+		return -ENOMEM;
 	bp->b_ops = &xfs_dquot_buf_ops;
 
 	/*
@@ -349,10 +347,8 @@ xfs_dquot_disk_alloc(
 	 * the buffer locked across the _defer_finish call.  We can now do
 	 * this correctly with xfs_defer_bjoin.
 	 *
-	 * Above, we allocated a disk block for the dquot information and
-	 * used get_buf to initialize the dquot.  If the _defer_bjoin fails,
-	 * the buffer is still locked to *tpp, so we must _bhold_release and
-	 * then _trans_brelse the buffer.  If the _defer_finish fails, the old
+	 * Above, we allocated a disk block for the dquot information and used
+	 * get_buf to initialize the dquot. If the _defer_finish fails, the old
 	 * transaction is gone but the new buffer is not joined or held to any
 	 * transaction, so we must _buf_relse it.
 	 *
@@ -362,24 +358,14 @@ xfs_dquot_disk_alloc(
 	 * manually or by committing the transaction.
 	 */
 	xfs_trans_bhold(tp, bp);
-	if (error) {
-		xfs_trans_bhold_release(tp, bp);
-		xfs_trans_brelse(tp, bp);
-		goto error1;
-	}
 	error = xfs_defer_finish(tpp);
 	tp = *tpp;
 	if (error) {
 		xfs_buf_relse(bp);
-		goto error0;
+		return error;
 	}
 	*bpp = bp;
 	return 0;
-
-error1:
-	xfs_defer_cancel(tp);
-error0:
-	return error;
 }
 
 /*
-- 
cgit v1.2.3


From da653130a9faaf5df18c5f84e7bf5cb5f5d256e4 Mon Sep 17 00:00:00 2001
From: Michael Ellerman <mpe@ellerman.id.au>
Date: Fri, 27 Jul 2018 15:35:55 +1000
Subject: of/fdt: Remove PPC32 longtrail hack in memory scan

When the OF code was originally made common by Grant in commit
51975db0b733 ("of/flattree: merge early_init_dt_scan_memory() common
code") (Feb 2010), the common code inherited a hack to handle
PPC "longtrail" machines, which had a "memory@0" node with no
device_type.

That check was then made to only apply to PPC32 in b44aa25d20e2 ("of:
Handle memory@0 node on PPC32 only") (May 2014).

But according to Paul Mackerras the "longtrail" machines are long
dead, if they were ever seen in the wild at all. If someone does still
have one, we can handle this firmware wart in powerpc platform code.

So remove the hack once and for all.

Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 drivers/of/fdt.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c
index 6da20b9688f7..800ad252cf9c 100644
--- a/drivers/of/fdt.c
+++ b/drivers/of/fdt.c
@@ -1034,14 +1034,7 @@ int __init early_init_dt_scan_memory(unsigned long node, const char *uname,
 	bool hotpluggable;
 
 	/* We are scanning "memory" nodes only */
-	if (type == NULL) {
-		/*
-		 * The longtrail doesn't have a device_type on the
-		 * /memory node, so look for the node called /memory@0.
-		 */
-		if (!IS_ENABLED(CONFIG_PPC32) || depth != 1 || strcmp(uname, "memory@0") != 0)
-			return 0;
-	} else if (strcmp(type, "memory") != 0)
+	if (type == NULL || strcmp(type, "memory") != 0)
 		return 0;
 
 	reg = of_get_flat_dt_prop(node, "linux,usable-memory", &l);
-- 
cgit v1.2.3


From a3cfcecdb38b2f562fd6608ad4b1f8c1115cddd0 Mon Sep 17 00:00:00 2001
From: Michal Vokáč <michal.vokac@ysoft.com>
Date: Fri, 27 Jul 2018 14:15:15 +0200
Subject: dt-bindings: Add Y Soft Corporation vendor prefix
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Y Soft is headquartered in the Czech Republic and it is a worldwide
provider of enterprise office solutions for print management.

Signed-off-by: Michal Vokáč <michal.vokac@ysoft.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/bindings/vendor-prefixes.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/vendor-prefixes.txt b/Documentation/devicetree/bindings/vendor-prefixes.txt
index 5b2d71a8907b..c401d10335bc 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -414,6 +414,7 @@ xes	Extreme Engineering Solutions (X-ES)
 xillybus	Xillybus Ltd.
 xlnx	Xilinx
 xunlong	Shenzhen Xunlong Software CO.,Limited
+ysoft	Y Soft Corporation a.s.
 zarlink	Zarlink Semiconductor
 zeitec	ZEITEC Semiconductor Co., LTD.
 zidoo	Shenzhen Zidoo Technology Co., Ltd.
-- 
cgit v1.2.3


From 6cfef793b558eee47bac720574aff0d36b89d20a Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 7 Aug 2018 10:50:20 -0700
Subject: ethtool: Add WAKE_FILTER and RX_CLS_FLOW_WAKE

Add the ability to specify through ethtool::rxnfc that a rule location is
special and will be used to participate in Wake-on-LAN, by e.g: having a
specific pattern be matched. When this is the case, fs->ring_cookie must
be set to the special value RX_CLS_FLOW_WAKE.

We also define an additional ethtool::wolinfo flag: WAKE_FILTER which
can be used to configure an Ethernet adapter to allow Wake-on-LAN using
previously programmed filters.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ethtool.h | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 813282cc8af6..dc69391d2bba 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -870,7 +870,8 @@ struct ethtool_flow_ext {
  *	includes the %FLOW_EXT or %FLOW_MAC_EXT flag
  *	(see &struct ethtool_flow_ext description).
  * @ring_cookie: RX ring/queue index to deliver to, or %RX_CLS_FLOW_DISC
- *	if packets should be discarded
+ *	if packets should be discarded, or %RX_CLS_FLOW_WAKE if the
+ *	packets should be used for Wake-on-LAN with %WAKE_FILTER
  * @location: Location of rule in the table.  Locations must be
  *	numbered such that a flow matching multiple rules will be
  *	classified according to the first (lowest numbered) rule.
@@ -1634,6 +1635,7 @@ static inline int ethtool_validate_duplex(__u8 duplex)
 #define WAKE_ARP		(1 << 4)
 #define WAKE_MAGIC		(1 << 5)
 #define WAKE_MAGICSECURE	(1 << 6) /* only meaningful if WAKE_MAGIC */
+#define WAKE_FILTER		(1 << 7)
 
 /* L2-L4 network traffic flow types */
 #define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
@@ -1671,6 +1673,7 @@ static inline int ethtool_validate_duplex(__u8 duplex)
 #define	RXH_DISCARD	(1 << 31)
 
 #define	RX_CLS_FLOW_DISC	0xffffffffffffffffULL
+#define RX_CLS_FLOW_WAKE	0xfffffffffffffffeULL
 
 /* Special RX classification rule insert location values */
 #define RX_CLS_LOC_SPECIAL	0x80000000	/* flag */
-- 
cgit v1.2.3


From 8a75f4f2acd78adfaf4b96939322d8a1de97d378 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 7 Aug 2018 10:50:22 -0700
Subject: net: dsa: bcm_sf2: Propagate ethtool::rxnfc to CPU port

Allow propagating ethtool::rxnfc programming to the CPU/management port
such that it is possible for such a CPU to perform e.g: Wake-on-LAN
using filters configured by the switch. We need a tiny bit of
cooperation between the switch drivers which is able to do the full flow
matching, whereas the CPU/management port might not. The CPU/management
driver needs to return -EOPNOTSUPP to indicate an non critical error,
any other error code otherwise.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/bcm_sf2_cfp.c | 43 ++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 40 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/bcm_sf2_cfp.c b/drivers/net/dsa/bcm_sf2_cfp.c
index 1e37b65aab93..47c5f272a084 100644
--- a/drivers/net/dsa/bcm_sf2_cfp.c
+++ b/drivers/net/dsa/bcm_sf2_cfp.c
@@ -732,6 +732,8 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 				struct ethtool_rx_flow_spec *fs)
 {
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
+	s8 cpu_port = ds->ports[port].cpu_dp->index;
+	__u64 ring_cookie = fs->ring_cookie;
 	unsigned int queue_num, port_num;
 	int ret = -EINVAL;
 
@@ -748,13 +750,19 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	    fs->location > bcm_sf2_cfp_rule_size(priv))
 		return -EINVAL;
 
+	/* This rule is a Wake-on-LAN filter and we must specifically
+	 * target the CPU port in order for it to be working.
+	 */
+	if (ring_cookie == RX_CLS_FLOW_WAKE)
+		ring_cookie = cpu_port * SF2_NUM_EGRESS_QUEUES;
+
 	/* We do not support discarding packets, check that the
 	 * destination port is enabled and that we are within the
 	 * number of ports supported by the switch
 	 */
-	port_num = fs->ring_cookie / SF2_NUM_EGRESS_QUEUES;
+	port_num = ring_cookie / SF2_NUM_EGRESS_QUEUES;
 
-	if (fs->ring_cookie == RX_CLS_FLOW_DISC ||
+	if (ring_cookie == RX_CLS_FLOW_DISC ||
 	    !(dsa_is_user_port(ds, port_num) ||
 	      dsa_is_cpu_port(ds, port_num)) ||
 	    port_num >= priv->hw_params.num_ports)
@@ -763,7 +771,7 @@ static int bcm_sf2_cfp_rule_set(struct dsa_switch *ds, int port,
 	 * We have a small oddity where Port 6 just does not have a
 	 * valid bit here (so we substract by one).
 	 */
-	queue_num = fs->ring_cookie % SF2_NUM_EGRESS_QUEUES;
+	queue_num = ring_cookie % SF2_NUM_EGRESS_QUEUES;
 	if (port_num >= 7)
 		port_num -= 1;
 
@@ -1188,6 +1196,7 @@ static int bcm_sf2_cfp_rule_get_all(struct bcm_sf2_priv *priv,
 int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc, u32 *rule_locs)
 {
+	struct net_device *p = ds->ports[port].cpu_dp->master;
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	int ret = 0;
 
@@ -1214,12 +1223,23 @@ int bcm_sf2_get_rxnfc(struct dsa_switch *ds, int port,
 
 	mutex_unlock(&priv->cfp.lock);
 
+	if (ret)
+		return ret;
+
+	/* Pass up the commands to the attached master network device */
+	if (p->ethtool_ops->get_rxnfc) {
+		ret = p->ethtool_ops->get_rxnfc(p, nfc, rule_locs);
+		if (ret == -EOPNOTSUPP)
+			ret = 0;
+	}
+
 	return ret;
 }
 
 int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 		      struct ethtool_rxnfc *nfc)
 {
+	struct net_device *p = ds->ports[port].cpu_dp->master;
 	struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds);
 	int ret = 0;
 
@@ -1240,6 +1260,23 @@ int bcm_sf2_set_rxnfc(struct dsa_switch *ds, int port,
 
 	mutex_unlock(&priv->cfp.lock);
 
+	if (ret)
+		return ret;
+
+	/* Pass up the commands to the attached master network device.
+	 * This can fail, so rollback the operation if we need to.
+	 */
+	if (p->ethtool_ops->set_rxnfc) {
+		ret = p->ethtool_ops->set_rxnfc(p, nfc);
+		if (ret && ret != -EOPNOTSUPP) {
+			mutex_lock(&priv->cfp.lock);
+			bcm_sf2_cfp_rule_del(priv, port, nfc->fs.location);
+			mutex_unlock(&priv->cfp.lock);
+		} else {
+			ret = 0;
+		}
+	}
+
 	return ret;
 }
 
-- 
cgit v1.2.3


From bb9051a2b23005a18826a2c33c98e5d977332352 Mon Sep 17 00:00:00 2001
From: Florian Fainelli <f.fainelli@gmail.com>
Date: Tue, 7 Aug 2018 10:50:23 -0700
Subject: net: systemport: Add support for WAKE_FILTER

The SYSTEMPORT MAC allows up to 8 filters to be programmed to wake-up
from LAN. Verify that we have up to 8 filters and program them to the
appropriate RXCHK entries to be matched (along with their masks).

We need to update the entry and exit to Wake-on-LAN mode to keep the
RXCHK engine running to match during suspend, but this is otherwise
fairly similar to Magic Packet detection.

Signed-off-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 193 +++++++++++++++++++++++++++--
 drivers/net/ethernet/broadcom/bcmsysport.h |  11 +-
 2 files changed, 195 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index 284581c9680e..ca47309d4494 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -521,7 +521,7 @@ static void bcm_sysport_get_wol(struct net_device *dev,
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	u32 reg;
 
-	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE;
+	wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 	wol->wolopts = priv->wolopts;
 
 	if (!(priv->wolopts & WAKE_MAGICSECURE))
@@ -539,7 +539,7 @@ static int bcm_sysport_set_wol(struct net_device *dev,
 {
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct device *kdev = &priv->pdev->dev;
-	u32 supported = WAKE_MAGIC | WAKE_MAGICSECURE;
+	u32 supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
 
 	if (!device_can_wakeup(kdev))
 		return -ENOTSUPP;
@@ -1043,7 +1043,7 @@ static int bcm_sysport_poll(struct napi_struct *napi, int budget)
 
 static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable)
 {
-	u32 reg;
+	u32 reg, bit;
 
 	reg = umac_readl(priv, UMAC_MPD_CTRL);
 	if (enable)
@@ -1051,12 +1051,32 @@ static void mpd_enable_set(struct bcm_sysport_priv *priv, bool enable)
 	else
 		reg &= ~MPD_EN;
 	umac_writel(priv, reg, UMAC_MPD_CTRL);
+
+	if (priv->is_lite)
+		bit = RBUF_ACPI_EN_LITE;
+	else
+		bit = RBUF_ACPI_EN;
+
+	reg = rbuf_readl(priv, RBUF_CONTROL);
+	if (enable)
+		reg |= bit;
+	else
+		reg &= ~bit;
+	rbuf_writel(priv, reg, RBUF_CONTROL);
 }
 
 static void bcm_sysport_resume_from_wol(struct bcm_sysport_priv *priv)
 {
+	u32 reg;
+
 	/* Stop monitoring MPD interrupt */
-	intrl2_0_mask_set(priv, INTRL2_0_MPD);
+	intrl2_0_mask_set(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG);
+
+	/* Disable RXCHK, active filters and Broadcom tag matching */
+	reg = rxchk_readl(priv, RXCHK_CONTROL);
+	reg &= ~(RXCHK_BRCM_TAG_MATCH_MASK <<
+		 RXCHK_BRCM_TAG_MATCH_SHIFT | RXCHK_EN | RXCHK_BRCM_TAG_EN);
+	rxchk_writel(priv, reg, RXCHK_CONTROL);
 
 	/* Clear the MagicPacket detection logic */
 	mpd_enable_set(priv, false);
@@ -1085,6 +1105,7 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
 	struct bcm_sysport_tx_ring *txr;
 	unsigned int ring, ring_bit;
+	u32 reg;
 
 	priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) &
 			  ~intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
@@ -1111,7 +1132,14 @@ static irqreturn_t bcm_sysport_rx_isr(int irq, void *dev_id)
 		bcm_sysport_tx_reclaim_all(priv);
 
 	if (priv->irq0_stat & INTRL2_0_MPD)
-		netdev_info(priv->netdev, "Wake-on-LAN interrupt!\n");
+		netdev_info(priv->netdev, "Wake-on-LAN (MPD) interrupt!\n");
+
+	if (priv->irq0_stat & INTRL2_0_BRCM_MATCH_TAG) {
+		reg = rxchk_readl(priv, RXCHK_BRCM_TAG_MATCH_STATUS) &
+				  RXCHK_BRCM_TAG_MATCH_MASK;
+		netdev_info(priv->netdev,
+			    "Wake-on-LAN (filters 0x%02x) interrupt!\n", reg);
+	}
 
 	if (!priv->is_lite)
 		goto out;
@@ -2096,6 +2124,132 @@ static int bcm_sysport_stop(struct net_device *dev)
 	return 0;
 }
 
+static int bcm_sysport_rule_find(struct bcm_sysport_priv *priv,
+				 u64 location)
+{
+	unsigned int index;
+	u32 reg;
+
+	for_each_set_bit(index, priv->filters, RXCHK_BRCM_TAG_MAX) {
+		reg = rxchk_readl(priv, RXCHK_BRCM_TAG(index));
+		reg >>= RXCHK_BRCM_TAG_CID_SHIFT;
+		reg &= RXCHK_BRCM_TAG_CID_MASK;
+		if (reg == location)
+			return index;
+	}
+
+	return -EINVAL;
+}
+
+static int bcm_sysport_rule_get(struct bcm_sysport_priv *priv,
+				struct ethtool_rxnfc *nfc)
+{
+	int index;
+
+	/* This is not a rule that we know about */
+	index = bcm_sysport_rule_find(priv, nfc->fs.location);
+	if (index < 0)
+		return -EOPNOTSUPP;
+
+	nfc->fs.ring_cookie = RX_CLS_FLOW_WAKE;
+
+	return 0;
+}
+
+static int bcm_sysport_rule_set(struct bcm_sysport_priv *priv,
+				struct ethtool_rxnfc *nfc)
+{
+	unsigned int index;
+	u32 reg;
+
+	/* We cannot match locations greater than what the classification ID
+	 * permits (256 entries)
+	 */
+	if (nfc->fs.location > RXCHK_BRCM_TAG_CID_MASK)
+		return -E2BIG;
+
+	/* We cannot support flows that are not destined for a wake-up */
+	if (nfc->fs.ring_cookie != RX_CLS_FLOW_WAKE)
+		return -EOPNOTSUPP;
+
+	/* All filters are already in use, we cannot match more rules */
+	if (bitmap_weight(priv->filters, RXCHK_BRCM_TAG_MAX) ==
+	    RXCHK_BRCM_TAG_MAX)
+		return -ENOSPC;
+
+	index = find_first_zero_bit(priv->filters, RXCHK_BRCM_TAG_MAX);
+	if (index > RXCHK_BRCM_TAG_MAX)
+		return -ENOSPC;
+
+	/* Location is the classification ID, and index is the position
+	 * within one of our 8 possible filters to be programmed
+	 */
+	reg = rxchk_readl(priv, RXCHK_BRCM_TAG(index));
+	reg &= ~(RXCHK_BRCM_TAG_CID_MASK << RXCHK_BRCM_TAG_CID_SHIFT);
+	reg |= nfc->fs.location << RXCHK_BRCM_TAG_CID_SHIFT;
+	rxchk_writel(priv, reg, RXCHK_BRCM_TAG(index));
+	rxchk_writel(priv, 0xff00ffff, RXCHK_BRCM_TAG_MASK(index));
+
+	set_bit(index, priv->filters);
+
+	return 0;
+}
+
+static int bcm_sysport_rule_del(struct bcm_sysport_priv *priv,
+				u64 location)
+{
+	int index;
+
+	/* This is not a rule that we know about */
+	index = bcm_sysport_rule_find(priv, location);
+	if (index < 0)
+		return -EOPNOTSUPP;
+
+	/* No need to disable this filter if it was enabled, this will
+	 * be taken care of during suspend time by bcm_sysport_suspend_to_wol
+	 */
+	clear_bit(index, priv->filters);
+
+	return 0;
+}
+
+static int bcm_sysport_get_rxnfc(struct net_device *dev,
+				 struct ethtool_rxnfc *nfc, u32 *rule_locs)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (nfc->cmd) {
+	case ETHTOOL_GRXCLSRULE:
+		ret = bcm_sysport_rule_get(priv, nfc);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
+static int bcm_sysport_set_rxnfc(struct net_device *dev,
+				 struct ethtool_rxnfc *nfc)
+{
+	struct bcm_sysport_priv *priv = netdev_priv(dev);
+	int ret = -EOPNOTSUPP;
+
+	switch (nfc->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		ret = bcm_sysport_rule_set(priv, nfc);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = bcm_sysport_rule_del(priv, nfc->fs.location);
+		break;
+	default:
+		break;
+	}
+
+	return ret;
+}
+
 static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.get_drvinfo		= bcm_sysport_get_drvinfo,
 	.get_msglevel		= bcm_sysport_get_msglvl,
@@ -2110,6 +2264,8 @@ static const struct ethtool_ops bcm_sysport_ethtool_ops = {
 	.set_coalesce		= bcm_sysport_set_coalesce,
 	.get_link_ksettings     = phy_ethtool_get_link_ksettings,
 	.set_link_ksettings     = phy_ethtool_set_link_ksettings,
+	.get_rxnfc		= bcm_sysport_get_rxnfc,
+	.set_rxnfc		= bcm_sysport_set_rxnfc,
 };
 
 static u16 bcm_sysport_select_queue(struct net_device *dev, struct sk_buff *skb,
@@ -2434,16 +2590,39 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 {
 	struct net_device *ndev = priv->netdev;
 	unsigned int timeout = 1000;
+	unsigned int index, i = 0;
 	u32 reg;
 
 	/* Password has already been programmed */
 	reg = umac_readl(priv, UMAC_MPD_CTRL);
-	reg |= MPD_EN;
+	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE))
+		reg |= MPD_EN;
 	reg &= ~PSW_EN;
 	if (priv->wolopts & WAKE_MAGICSECURE)
 		reg |= PSW_EN;
 	umac_writel(priv, reg, UMAC_MPD_CTRL);
 
+	if (priv->wolopts & WAKE_FILTER) {
+		/* Turn on ACPI matching to steal packets from RBUF */
+		reg = rbuf_readl(priv, RBUF_CONTROL);
+		if (priv->is_lite)
+			reg |= RBUF_ACPI_EN_LITE;
+		else
+			reg |= RBUF_ACPI_EN;
+		rbuf_writel(priv, reg, RBUF_CONTROL);
+
+		/* Enable RXCHK, active filters and Broadcom tag matching */
+		reg = rxchk_readl(priv, RXCHK_CONTROL);
+		reg &= ~(RXCHK_BRCM_TAG_MATCH_MASK <<
+			 RXCHK_BRCM_TAG_MATCH_SHIFT);
+		for_each_set_bit(index, priv->filters, RXCHK_BRCM_TAG_MAX) {
+			reg |= BIT(RXCHK_BRCM_TAG_MATCH_SHIFT + i);
+			i++;
+		}
+		reg |= RXCHK_EN | RXCHK_BRCM_TAG_EN;
+		rxchk_writel(priv, reg, RXCHK_CONTROL);
+	}
+
 	/* Make sure RBUF entered WoL mode as result */
 	do {
 		reg = rbuf_readl(priv, RBUF_STATUS);
@@ -2464,7 +2643,7 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 	umac_enable_set(priv, CMD_RX_EN, 1);
 
 	/* Enable the interrupt wake-up source */
-	intrl2_0_mask_clear(priv, INTRL2_0_MPD);
+	intrl2_0_mask_clear(priv, INTRL2_0_MPD | INTRL2_0_BRCM_MATCH_TAG);
 
 	netif_dbg(priv, wol, ndev, "entered WOL mode\n");
 
diff --git a/drivers/net/ethernet/broadcom/bcmsysport.h b/drivers/net/ethernet/broadcom/bcmsysport.h
index cf440b91fd04..046c6c1d97fd 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.h
+++ b/drivers/net/ethernet/broadcom/bcmsysport.h
@@ -11,6 +11,7 @@
 #ifndef __BCM_SYSPORT_H
 #define __BCM_SYSPORT_H
 
+#include <linux/bitmap.h>
 #include <linux/if_vlan.h>
 #include <linux/net_dim.h>
 
@@ -155,14 +156,18 @@ struct bcm_rsb {
 #define  RXCHK_PARSE_AUTH		(1 << 22)
 
 #define RXCHK_BRCM_TAG0			0x04
-#define RXCHK_BRCM_TAG(i)		((i) * RXCHK_BRCM_TAG0)
+#define RXCHK_BRCM_TAG(i)		((i) * 0x4 + RXCHK_BRCM_TAG0)
 #define RXCHK_BRCM_TAG0_MASK		0x24
-#define RXCHK_BRCM_TAG_MASK(i)		((i) * RXCHK_BRCM_TAG0_MASK)
+#define RXCHK_BRCM_TAG_MASK(i)		((i) * 0x4 + RXCHK_BRCM_TAG0_MASK)
 #define RXCHK_BRCM_TAG_MATCH_STATUS	0x44
 #define RXCHK_ETHERTYPE			0x48
 #define RXCHK_BAD_CSUM_CNTR		0x4C
 #define RXCHK_OTHER_DISC_CNTR		0x50
 
+#define RXCHK_BRCM_TAG_MAX		8
+#define RXCHK_BRCM_TAG_CID_SHIFT	16
+#define RXCHK_BRCM_TAG_CID_MASK		0xff
+
 /* TXCHCK offsets and defines */
 #define SYS_PORT_TXCHK_OFFSET		0x380
 #define TXCHK_PKT_RDY_THRESH		0x00
@@ -185,6 +190,7 @@ struct bcm_rsb {
 #define  RBUF_RSB_SWAP0			(1 << 22)
 #define  RBUF_RSB_SWAP1			(1 << 23)
 #define  RBUF_ACPI_EN			(1 << 23)
+#define  RBUF_ACPI_EN_LITE		(1 << 24)
 
 #define RBUF_PKT_RDY_THRESH		0x04
 
@@ -777,6 +783,7 @@ struct bcm_sysport_priv {
 
 	/* Ethtool */
 	u32			msg_enable;
+	DECLARE_BITMAP(filters, RXCHK_BRCM_TAG_MAX);
 
 	struct bcm_sysport_stats64	stats64;
 
-- 
cgit v1.2.3


From ff361fda55fda55031252aca1f8afef735fe057c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 19 Jun 2018 15:25:30 +0300
Subject: cifs: Silence uninitialized variable warning

This is not really a runtime issue but Smatch complains that:

    fs/cifs/smb2ops.c:1740 smb2_query_symlink()
    error: uninitialized symbol 'resp_buftype'.

The warning is right that it can be uninitialized...  Also "err_buf"
would be NULL at this point and we're not supposed to pass NULLs to
free_rsp_buf() or it might trigger some extra output if we turn on
debugging.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/smb2ops.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index ea92a38b2f08..ae64cbef5e07 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1700,7 +1700,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 		       &resp_buftype);
 	if (!rc || !err_iov.iov_base) {
 		rc = -ENOENT;
-		goto querty_exit;
+		goto free_path;
 	}
 
 	err_buf = err_iov.iov_base;
@@ -1741,6 +1741,7 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 
  querty_exit:
 	free_rsp_buf(resp_buftype, err_buf);
+ free_path:
 	kfree(utf16_path);
 	return rc;
 }
-- 
cgit v1.2.3


From 95390201e7d8dd1eb764a3cbd50ae538a17fcd02 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 19 Jun 2018 17:27:58 +0200
Subject: cifs: use timespec64 internally

In cifs, the timestamps are stored in memory in the cifs_fattr structure,
which uses the deprecated 'timespec' structure. Now that the VFS code
has moved on to 'timespec64', the next step is to change over the fattr
as well.

This also makes 32-bit and 64-bit systems behave the same way, and
no longer overflow the 32-bit time_t in year 2038.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Paulo Alcantara <palcantara@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsencrypt.c |  4 ++--
 fs/cifs/cifsglob.h    |  6 +++---
 fs/cifs/cifsproto.h   |  6 +++---
 fs/cifs/cifssmb.c     | 12 ++++++------
 fs/cifs/inode.c       | 34 ++++++++++++++++------------------
 fs/cifs/netmisc.c     | 19 ++++++++++---------
 6 files changed, 40 insertions(+), 41 deletions(-)

diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index ee2a8ec70056..b4672eafc5bf 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -452,7 +452,7 @@ find_timestamp(struct cifs_ses *ses)
 	unsigned char *blobptr;
 	unsigned char *blobend;
 	struct ntlmssp2_name *attrptr;
-	struct timespec ts;
+	struct timespec64 ts;
 
 	if (!ses->auth_key.len || !ses->auth_key.response)
 		return 0;
@@ -477,7 +477,7 @@ find_timestamp(struct cifs_ses *ses)
 		blobptr += attrsize; /* advance attr value */
 	}
 
-	ktime_get_real_ts(&ts);
+	ktime_get_real_ts64(&ts);
 	return cpu_to_le64(cifs_UnixTimeToNT(ts));
 }
 
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index c923c7854027..b57d1e22ecb5 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -1544,9 +1544,9 @@ struct cifs_fattr {
 	dev_t		cf_rdev;
 	unsigned int	cf_nlink;
 	unsigned int	cf_dtype;
-	struct timespec	cf_atime;
-	struct timespec	cf_mtime;
-	struct timespec	cf_ctime;
+	struct timespec64 cf_atime;
+	struct timespec64 cf_mtime;
+	struct timespec64 cf_ctime;
 };
 
 static inline void free_dfs_info_param(struct dfs_info3_param *param)
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 1890f534c88b..7ead1a9ac6fb 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -143,9 +143,9 @@ extern enum securityEnum select_sectype(struct TCP_Server_Info *server,
 				enum securityEnum requested);
 extern int CIFS_SessSetup(const unsigned int xid, struct cifs_ses *ses,
 			  const struct nls_table *nls_cp);
-extern struct timespec cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
-extern u64 cifs_UnixTimeToNT(struct timespec);
-extern struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
+extern struct timespec64 cifs_NTtimeToUnix(__le64 utc_nanoseconds_since_1601);
+extern u64 cifs_UnixTimeToNT(struct timespec64);
+extern struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time,
 				      int offset);
 extern void cifs_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock);
 extern int cifs_get_writer(struct cifsInodeInfo *cinode);
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index 93408eab92e7..dc2f4cf08fe9 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -508,13 +508,13 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr)
 		 * this requirement.
 		 */
 		int val, seconds, remain, result;
-		struct timespec ts;
-		unsigned long utc = ktime_get_real_seconds();
+		struct timespec64 ts;
+		time64_t utc = ktime_get_real_seconds();
 		ts = cnvrtDosUnixTm(rsp->SrvTime.Date,
 				    rsp->SrvTime.Time, 0);
-		cifs_dbg(FYI, "SrvTime %d sec since 1970 (utc: %d) diff: %d\n",
-			 (int)ts.tv_sec, (int)utc,
-			 (int)(utc - ts.tv_sec));
+		cifs_dbg(FYI, "SrvTime %lld sec since 1970 (utc: %lld) diff: %lld\n",
+			 ts.tv_sec, utc,
+			 utc - ts.tv_sec);
 		val = (int)(utc - ts.tv_sec);
 		seconds = abs(val);
 		result = (seconds / MIN_TZ_ADJ) * MIN_TZ_ADJ;
@@ -4082,7 +4082,7 @@ QInfRetry:
 	if (rc) {
 		cifs_dbg(FYI, "Send error in QueryInfo = %d\n", rc);
 	} else if (data) {
-		struct timespec ts;
+		struct timespec64 ts;
 		__u32 time = le32_to_cpu(pSMBr->last_write_time);
 
 		/* decode response */
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a2cfb33e85c1..f6abf18ca492 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -95,7 +95,6 @@ static void
 cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 {
 	struct cifsInodeInfo *cifs_i = CIFS_I(inode);
-	struct timespec ts;
 
 	cifs_dbg(FYI, "%s: revalidating inode %llu\n",
 		 __func__, cifs_i->uniqueid);
@@ -114,8 +113,7 @@ cifs_revalidate_cache(struct inode *inode, struct cifs_fattr *fattr)
 	}
 
 	 /* revalidate if mtime or size have changed */
-	ts = timespec64_to_timespec(inode->i_mtime);
-	if (timespec_equal(&ts, &fattr->cf_mtime) &&
+	if (timespec64_equal(&inode->i_mtime, &fattr->cf_mtime) &&
 	    cifs_i->server_eof == fattr->cf_eof) {
 		cifs_dbg(FYI, "%s: inode %llu is unchanged\n",
 			 __func__, cifs_i->uniqueid);
@@ -164,9 +162,9 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr)
 	cifs_revalidate_cache(inode, fattr);
 
 	spin_lock(&inode->i_lock);
-	inode->i_atime = timespec_to_timespec64(fattr->cf_atime);
-	inode->i_mtime = timespec_to_timespec64(fattr->cf_mtime);
-	inode->i_ctime = timespec_to_timespec64(fattr->cf_ctime);
+	inode->i_atime = fattr->cf_atime;
+	inode->i_mtime = fattr->cf_mtime;
+	inode->i_ctime = fattr->cf_ctime;
 	inode->i_rdev = fattr->cf_rdev;
 	cifs_nlink_fattr_to_inode(inode, fattr);
 	inode->i_uid = fattr->cf_uid;
@@ -327,8 +325,8 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb)
 	fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU;
 	fattr->cf_uid = cifs_sb->mnt_uid;
 	fattr->cf_gid = cifs_sb->mnt_gid;
-	ktime_get_real_ts(&fattr->cf_mtime);
-	fattr->cf_mtime = timespec_trunc(fattr->cf_mtime, sb->s_time_gran);
+	ktime_get_real_ts64(&fattr->cf_mtime);
+	fattr->cf_mtime = timespec64_trunc(fattr->cf_mtime, sb->s_time_gran);
 	fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime;
 	fattr->cf_nlink = 2;
 	fattr->cf_flags |= CIFS_FATTR_DFS_REFERRAL;
@@ -604,8 +602,8 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 	if (info->LastAccessTime)
 		fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
 	else {
-		ktime_get_real_ts(&fattr->cf_atime);
-		fattr->cf_atime = timespec_trunc(fattr->cf_atime, sb->s_time_gran);
+		ktime_get_real_ts64(&fattr->cf_atime);
+		fattr->cf_atime = timespec64_trunc(fattr->cf_atime, sb->s_time_gran);
 	}
 
 	fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
@@ -1125,14 +1123,14 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
 	if (attrs->ia_valid & ATTR_ATIME) {
 		set_time = true;
 		info_buf.LastAccessTime =
-			cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime)));
+			cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_atime));
 	} else
 		info_buf.LastAccessTime = 0;
 
 	if (attrs->ia_valid & ATTR_MTIME) {
 		set_time = true;
 		info_buf.LastWriteTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime)));
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_mtime));
 	} else
 		info_buf.LastWriteTime = 0;
 
@@ -1145,7 +1143,7 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
 	if (set_time && (attrs->ia_valid & ATTR_CTIME)) {
 		cifs_dbg(FYI, "CIFS - CTIME changed\n");
 		info_buf.ChangeTime =
-		    cpu_to_le64(cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime)));
+		    cpu_to_le64(cifs_UnixTimeToNT(attrs->ia_ctime));
 	} else
 		info_buf.ChangeTime = 0;
 
@@ -2071,8 +2069,8 @@ int cifs_getattr(const struct path *path, struct kstat *stat,
 	/* old CIFS Unix Extensions doesn't return create time */
 	if (CIFS_I(inode)->createtime) {
 		stat->result_mask |= STATX_BTIME;
-		stat->btime = timespec_to_timespec64(
-		      cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime)));
+		stat->btime =
+		      cifs_NTtimeToUnix(cpu_to_le64(CIFS_I(inode)->createtime));
 	}
 
 	stat->attributes_mask |= (STATX_ATTR_COMPRESSED | STATX_ATTR_ENCRYPTED);
@@ -2278,17 +2276,17 @@ cifs_setattr_unix(struct dentry *direntry, struct iattr *attrs)
 		args->gid = INVALID_GID; /* no change */
 
 	if (attrs->ia_valid & ATTR_ATIME)
-		args->atime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_atime));
+		args->atime = cifs_UnixTimeToNT(attrs->ia_atime);
 	else
 		args->atime = NO_CHANGE_64;
 
 	if (attrs->ia_valid & ATTR_MTIME)
-		args->mtime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_mtime));
+		args->mtime = cifs_UnixTimeToNT(attrs->ia_mtime);
 	else
 		args->mtime = NO_CHANGE_64;
 
 	if (attrs->ia_valid & ATTR_CTIME)
-		args->ctime = cifs_UnixTimeToNT(timespec64_to_timespec(attrs->ia_ctime));
+		args->ctime = cifs_UnixTimeToNT(attrs->ia_ctime);
 	else
 		args->ctime = NO_CHANGE_64;
 
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index d7ad0dfe4e68..fdd908e4a26b 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -918,10 +918,10 @@ smbCalcSize(void *buf, struct TCP_Server_Info *server)
  * Convert the NT UTC (based 1601-01-01, in hundred nanosecond units)
  * into Unix UTC (based 1970-01-01, in seconds).
  */
-struct timespec
+struct timespec64
 cifs_NTtimeToUnix(__le64 ntutc)
 {
-	struct timespec ts;
+	struct timespec64 ts;
 	/* BB what about the timezone? BB */
 
 	/* Subtract the NTFS time offset, then convert to 1s intervals. */
@@ -935,12 +935,12 @@ cifs_NTtimeToUnix(__le64 ntutc)
 	 */
 	if (t < 0) {
 		abs_t = -t;
-		ts.tv_nsec = (long)(do_div(abs_t, 10000000) * 100);
+		ts.tv_nsec = (time64_t)(do_div(abs_t, 10000000) * 100);
 		ts.tv_nsec = -ts.tv_nsec;
 		ts.tv_sec = -abs_t;
 	} else {
 		abs_t = t;
-		ts.tv_nsec = (long)do_div(abs_t, 10000000) * 100;
+		ts.tv_nsec = (time64_t)do_div(abs_t, 10000000) * 100;
 		ts.tv_sec = abs_t;
 	}
 
@@ -949,7 +949,7 @@ cifs_NTtimeToUnix(__le64 ntutc)
 
 /* Convert the Unix UTC into NT UTC. */
 u64
-cifs_UnixTimeToNT(struct timespec t)
+cifs_UnixTimeToNT(struct timespec64 t)
 {
 	/* Convert to 100ns intervals and then add the NTFS time offset. */
 	return (u64) t.tv_sec * 10000000 + t.tv_nsec/100 + NTFS_TIME_OFFSET;
@@ -959,10 +959,11 @@ static const int total_days_of_prev_months[] = {
 	0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334
 };
 
-struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
+struct timespec64 cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 {
-	struct timespec ts;
-	int sec, min, days, month, year;
+	struct timespec64 ts;
+	time64_t sec;
+	int min, days, month, year;
 	u16 date = le16_to_cpu(le_date);
 	u16 time = le16_to_cpu(le_time);
 	SMB_TIME *st = (SMB_TIME *)&time;
@@ -973,7 +974,7 @@ struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 	sec = 2 * st->TwoSeconds;
 	min = st->Minutes;
 	if ((sec > 59) || (min > 59))
-		cifs_dbg(VFS, "illegal time min %d sec %d\n", min, sec);
+		cifs_dbg(VFS, "illegal time min %d sec %lld\n", min, sec);
 	sec += (min * 60);
 	sec += 60 * 60 * st->Hours;
 	if (st->Hours > 24)
-- 
cgit v1.2.3


From cbedeadf9c44a1a135293717d501882f2933a534 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 19 Jun 2018 17:27:59 +0200
Subject: cifs: use 64-bit timestamps for fscache

In the fscache, we just need the timestamps as cookies to check for
changes, so we don't really care about the overflow, but it's better
to stop using the deprecated timespec so we don't have to go through
explicit conversion functions.

To avoid comparing uninitialized padding values that are copied
while assigning the timespec values, this rearranges the members of
cifs_fscache_inode_auxdata to avoid padding, and assigns them
individually.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Paulo Alcantara <palcantara@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cache.c   |  6 ++++--
 fs/cifs/fscache.c | 12 ++++++++----
 fs/cifs/fscache.h |  8 +++++---
 3 files changed, 17 insertions(+), 9 deletions(-)

diff --git a/fs/cifs/cache.c b/fs/cifs/cache.c
index e1553d1e0e50..b7420e605b28 100644
--- a/fs/cifs/cache.c
+++ b/fs/cifs/cache.c
@@ -128,8 +128,10 @@ fscache_checkaux cifs_fscache_inode_check_aux(void *cookie_netfs_data,
 
 	memset(&auxdata, 0, sizeof(auxdata));
 	auxdata.eof = cifsi->server_eof;
-	auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-	auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+	auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+	auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+	auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 	if (memcmp(data, &auxdata, datalen) != 0)
 		return FSCACHE_CHECKAUX_OBSOLETE;
diff --git a/fs/cifs/fscache.c b/fs/cifs/fscache.c
index 85145a763021..ea6ace9c2417 100644
--- a/fs/cifs/fscache.c
+++ b/fs/cifs/fscache.c
@@ -129,8 +129,10 @@ static void cifs_fscache_acquire_inode_cookie(struct cifsInodeInfo *cifsi,
 
 	memset(&auxdata, 0, sizeof(auxdata));
 	auxdata.eof = cifsi->server_eof;
-	auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-	auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+	auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+	auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+	auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+	auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 	cifsi->fscache =
 		fscache_acquire_cookie(tcon->fscache,
@@ -166,8 +168,10 @@ void cifs_fscache_release_inode_cookie(struct inode *inode)
 	if (cifsi->fscache) {
 		memset(&auxdata, 0, sizeof(auxdata));
 		auxdata.eof = cifsi->server_eof;
-		auxdata.last_write_time = timespec64_to_timespec(cifsi->vfs_inode.i_mtime);
-		auxdata.last_change_time = timespec64_to_timespec(cifsi->vfs_inode.i_ctime);
+		auxdata.last_write_time_sec = cifsi->vfs_inode.i_mtime.tv_sec;
+		auxdata.last_change_time_sec = cifsi->vfs_inode.i_ctime.tv_sec;
+		auxdata.last_write_time_nsec = cifsi->vfs_inode.i_mtime.tv_nsec;
+		auxdata.last_change_time_nsec = cifsi->vfs_inode.i_ctime.tv_nsec;
 
 		cifs_dbg(FYI, "%s: (0x%p)\n", __func__, cifsi->fscache);
 		fscache_relinquish_cookie(cifsi->fscache, &auxdata, false);
diff --git a/fs/cifs/fscache.h b/fs/cifs/fscache.h
index c7e3ac251e16..8c0862e41306 100644
--- a/fs/cifs/fscache.h
+++ b/fs/cifs/fscache.h
@@ -31,9 +31,11 @@
  * Auxiliary data attached to CIFS inode within the cache
  */
 struct cifs_fscache_inode_auxdata {
-	struct timespec	last_write_time;
-	struct timespec	last_change_time;
-	u64		eof;
+	u64 last_write_time_sec;
+	u64 last_change_time_sec;
+	u32 last_write_time_nsec;
+	u32 last_change_time_nsec;
+	u64 eof;
 };
 
 /*
-- 
cgit v1.2.3


From 8505c8bfd85a260c9dc5c47e15bd8c5357fcbcd2 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Mon, 18 Jun 2018 14:01:59 -0500
Subject: smb3: if server does not support posix do not allow posix mount
 option

If user specifies "posix" on an SMB3.11 mount, then fail the mount
if server does not return the POSIX negotiate context indicating
support for posix.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/connect.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 5df2c0698cda..9d02563b2147 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -3031,11 +3031,15 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	}
 
 #ifdef CONFIG_CIFS_SMB311
-	if ((volume_info->linux_ext) && (ses->server->posix_ext_supported)) {
-		if (ses->server->vals->protocol_id == SMB311_PROT_ID) {
+	if (volume_info->linux_ext) {
+		if (ses->server->posix_ext_supported) {
 			tcon->posix_extensions = true;
 			printk_once(KERN_WARNING
 				"SMB3.11 POSIX Extensions are experimental\n");
+		} else {
+			cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions.\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
 		}
 	}
 #endif /* 311 */
-- 
cgit v1.2.3


From 7420451f6a109f7f8f1bf283f34d08eba3259fb3 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 19 Jun 2018 14:34:08 -0500
Subject: cifs: allow disabling insecure dialects in the config

allow disabling cifs (SMB1 ie vers=1.0) and vers=2.0 in the
config for the build of cifs.ko if want to always prevent mounting
with these less secure dialects.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Jeremy Allison <jra@samba.org>
---
 fs/cifs/Kconfig   | 17 ++++++++++++++++-
 fs/cifs/connect.c |  9 +++++++++
 2 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 5f132d59dfc2..832eafbf803f 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -66,9 +66,24 @@ config CIFS_STATS2
 	  Unless you are a developer or are doing network performance analysis
 	  or tuning, say N.
 
+config CIFS_ALLOW_INSECURE_LEGACY
+	bool "Support legacy servers which use less secure dialects"
+	depends on CIFS
+	default y
+	help
+	  Modern dialects, SMB2.1 and later (including SMB3 and 3.1.1), have
+	  additional security features, including protection against
+	  man-in-the-middle attacks and stronger crypto hashes, so the use
+	  of legacy dialects (SMB1/CIFS and SMB2.0) is discouraged.
+
+	  Disabling this option prevents users from using vers=1.0 or vers=2.0
+	  on mounts with cifs.ko
+
+	  If unsure, say Y.
+
 config CIFS_WEAK_PW_HASH
 	bool "Support legacy servers which use weaker LANMAN security"
-	depends on CIFS
+	depends on CIFS && CIFS_ALLOW_INSECURE_LEGACY
 	help
 	  Modern CIFS servers including Samba and most Windows versions
 	  (since 1997) support stronger NTLM (and even NTLMv2 and Kerberos)
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 9d02563b2147..842f45859968 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -1174,6 +1174,7 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 	substring_t args[MAX_OPT_ARGS];
 
 	switch (match_token(value, cifs_smb_version_tokens, args)) {
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
 	case Smb_1:
 		if (disable_legacy_dialects) {
 			cifs_dbg(VFS, "mount with legacy dialect disabled\n");
@@ -1198,6 +1199,14 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 		vol->ops = &smb20_operations;
 		vol->vals = &smb20_values;
 		break;
+#else
+	case Smb_1:
+		cifs_dbg(VFS, "vers=1.0 (cifs) mount not permitted when legacy dialects disabled\n");
+		return 1;
+	case Smb_20:
+		cifs_dbg(VFS, "vers=2.0 mount not permitted when legacy dialects disabled\n");
+		return 1;
+#endif /* CIFS_ALLOW_INSECURE_LEGACY */
 	case Smb_21:
 		vol->ops = &smb21_operations;
 		vol->vals = &smb21_values;
-- 
cgit v1.2.3


From 256b4c3f03d77d8c0dc69e3a6ceb3afd0d1810bd Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Tue, 19 Jun 2018 15:18:48 -0700
Subject: CIFS: fix memory leak and remove dead code

also fixes error code in smb311_posix_mkdir() (where
the error assignment needs to go before the goto)
a typo that Dan Carpenter and Paulo and Gustavo
pointed out.

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.de>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/smb2pdu.c | 101 +++++++++++++++++++++++++++---------------------------
 1 file changed, 50 insertions(+), 51 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 3c92678cb45b..641fe79708d0 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1928,7 +1928,7 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 {
 	struct smb_rqst rqst;
 	struct smb2_create_req *req;
-	struct smb2_create_rsp *rsp;
+	struct smb2_create_rsp *rsp = NULL;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[3]; /* make sure at least one for each open context */
@@ -1943,27 +1943,31 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	char *pc_buf = NULL;
 	int flags = 0;
 	unsigned int total_len;
-	__le16 *path = cifs_convert_path_to_utf16(full_path, cifs_sb);
-
-	if (!path)
-		return -ENOMEM;
+	__le16 *utf16_path = NULL;
 
 	cifs_dbg(FYI, "mkdir\n");
 
+	/* resource #1: path allocation */
+	utf16_path = cifs_convert_path_to_utf16(full_path, cifs_sb);
+	if (!utf16_path)
+		return -ENOMEM;
+
 	if (ses && (ses->server))
 		server = ses->server;
-	else
-		return -EIO;
+	else {
+		rc = -EIO;
+		goto err_free_path;
+	}
 
+	/* resource #2: request */
 	rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
-
 	if (rc)
-		return rc;
+		goto err_free_path;
+
 
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-
 	req->ImpersonationLevel = IL_IMPERSONATION;
 	req->DesiredAccess = cpu_to_le32(FILE_WRITE_ATTRIBUTES);
 	/* File attributes ignored on open (used in create though) */
@@ -1992,50 +1996,44 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 		req->sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
 		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
 						 &name_len,
-						 tcon->treeName, path);
-		if (rc) {
-			cifs_small_buf_release(req);
-			return rc;
-		}
+						 tcon->treeName, utf16_path);
+		if (rc)
+			goto err_free_req;
+
 		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
-		path = copy_path;
+		/* free before overwriting resource */
+		kfree(utf16_path);
+		utf16_path = copy_path;
 	} else {
-		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
+		uni_path_len = (2 * UniStrnlen((wchar_t *)utf16_path, PATH_MAX)) + 2;
 		/* MUST set path len (NameLength) to 0 opening root of share */
 		req->NameLength = cpu_to_le16(uni_path_len - 2);
 		if (uni_path_len % 8 != 0) {
 			copy_size = roundup(uni_path_len, 8);
 			copy_path = kzalloc(copy_size, GFP_KERNEL);
 			if (!copy_path) {
-				cifs_small_buf_release(req);
-				return -ENOMEM;
+				rc = -ENOMEM;
+				goto err_free_req;
 			}
-			memcpy((char *)copy_path, (const char *)path,
+			memcpy((char *)copy_path, (const char *)utf16_path,
 			       uni_path_len);
 			uni_path_len = copy_size;
-			path = copy_path;
+			/* free before overwriting resource */
+			kfree(utf16_path);
+			utf16_path = copy_path;
 		}
 	}
 
 	iov[1].iov_len = uni_path_len;
-	iov[1].iov_base = path;
+	iov[1].iov_base = utf16_path;
 	req->RequestedOplockLevel = SMB2_OPLOCK_LEVEL_NONE;
 
 	if (tcon->posix_extensions) {
-		if (n_iov > 2) {
-			struct create_context *ccontext =
-			    (struct create_context *)iov[n_iov-1].iov_base;
-			ccontext->Next =
-				cpu_to_le32(iov[n_iov-1].iov_len);
-		}
-
+		/* resource #3: posix buf */
 		rc = add_posix_context(iov, &n_iov, mode);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			return rc;
-		}
+		if (rc)
+			goto err_free_req;
 		pc_buf = iov[n_iov-1].iov_base;
 	}
 
@@ -2044,32 +2042,33 @@ int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = n_iov;
 
-	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
-			    &rsp_iov);
-
-	cifs_small_buf_release(req);
-	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
-
-	if (rc != 0) {
+	/* resource #4: response buffer */
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
 		trace_smb3_posix_mkdir_err(xid, tcon->tid, ses->Suid,
-				    CREATE_NOT_FILE, FILE_WRITE_ATTRIBUTES, rc);
-		goto smb311_mkdir_exit;
-	} else
-		trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
-				     ses->Suid, CREATE_NOT_FILE,
-				     FILE_WRITE_ATTRIBUTES);
+					   CREATE_NOT_FILE,
+					   FILE_WRITE_ATTRIBUTES, rc);
+		goto err_free_rsp_buf;
+	}
+
+	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
+	trace_smb3_posix_mkdir_done(xid, rsp->PersistentFileId, tcon->tid,
+				    ses->Suid, CREATE_NOT_FILE,
+				    FILE_WRITE_ATTRIBUTES);
 
 	SMB2_close(xid, tcon, rsp->PersistentFileId, rsp->VolatileFileId);
 
 	/* Eventually save off posix specific response info and timestaps */
 
-smb311_mkdir_exit:
-	kfree(copy_path);
-	kfree(pc_buf);
+err_free_rsp_buf:
 	free_rsp_buf(resp_buftype, rsp);
+	kfree(pc_buf);
+err_free_req:
+	cifs_small_buf_release(req);
+err_free_path:
+	kfree(utf16_path);
 	return rc;
-
 }
 #endif /* SMB311 */
 
-- 
cgit v1.2.3


From a12d0c590cc7ae01892f06c5ad6d19580ecdd0de Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <paulo@paulo.ac>
Date: Sat, 23 Jun 2018 14:52:25 -0300
Subject: cifs: Make sure all data pages are signed correctly

Check if every data page is signed correctly in sigining helper.

Signed-off-by: Paulo Alcantara <palcantara@suse.de>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/cifsencrypt.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index b4672eafc5bf..85b31cfa2f3c 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -83,7 +83,13 @@ int __cifs_calc_signature(struct smb_rqst *rqst,
 
 		kaddr = (char *) kmap(rqst->rq_pages[i]) + offset;
 
-		crypto_shash_update(shash, kaddr, len);
+		rc = crypto_shash_update(shash, kaddr, len);
+		if (rc) {
+			cifs_dbg(VFS, "%s: Could not update with payload\n",
+				 __func__);
+			kunmap(rqst->rq_pages[i]);
+			return rc;
+		}
 
 		kunmap(rqst->rq_pages[i]);
 	}
-- 
cgit v1.2.3


From 21ba3845b59c733a79ed4fe1c4f3732e7ece9df7 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sun, 24 Jun 2018 23:18:52 -0500
Subject: smb3: fill in statfs fsid and correct namelen

Fil in the correct namelen (typically 255 not 4096) in the
statfs response and also fill in a reasonably unique fsid
(in this case taken from the volume id, and the creation time
of the volume).

In the case of the POSIX statfs all fields are now filled in,
and in the case of non-POSIX mounts, all fields are filled
in which can be.

Signed-off-by: Steve French <stfrench@gmail.com>
CC: Stable <stable@vger.kernel.org>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/cifsfs.c  | 18 ++++++++++--------
 fs/cifs/smb2ops.c |  2 ++
 fs/cifs/smb2pdu.c |  8 ++++++++
 fs/cifs/smb2pdu.h | 11 +++++++++++
 4 files changed, 31 insertions(+), 8 deletions(-)

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index d5aa7ae917bf..69ec5427769c 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -209,14 +209,16 @@ cifs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	xid = get_xid();
 
-	/*
-	 * PATH_MAX may be too long - it would presumably be total path,
-	 * but note that some servers (includinng Samba 3) have a shorter
-	 * maximum path.
-	 *
-	 * Instead could get the real value via SMB_QUERY_FS_ATTRIBUTE_INFO.
-	 */
-	buf->f_namelen = PATH_MAX;
+	if (le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength) > 0)
+		buf->f_namelen =
+		       le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength);
+	else
+		buf->f_namelen = PATH_MAX;
+
+	buf->f_fsid.val[0] = tcon->vol_serial_number;
+	/* are using part of create time for more randomness, see man statfs */
+	buf->f_fsid.val[1] =  (int)le64_to_cpu(tcon->vol_create_time);
+
 	buf->f_files = 0;	/* undefined */
 	buf->f_ffree = 0;	/* unlimited */
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index ae64cbef5e07..09506d918ecb 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -548,6 +548,8 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 			FS_ATTRIBUTE_INFORMATION);
 	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
 			FS_DEVICE_INFORMATION);
+	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
+			FS_VOLUME_INFORMATION);
 	SMB2_QFS_attr(xid, tcon, fid.persistent_fid, fid.volatile_fid,
 			FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
 	if (no_cached_open)
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 641fe79708d0..6852ff5f06be 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -4045,6 +4045,9 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	} else if (level == FS_SECTOR_SIZE_INFORMATION) {
 		max_len = sizeof(struct smb3_fs_ss_info);
 		min_len = sizeof(struct smb3_fs_ss_info);
+	} else if (level == FS_VOLUME_INFORMATION) {
+		max_len = sizeof(struct smb3_fs_vol_info) + MAX_VOL_LABEL_LEN;
+		min_len = sizeof(struct smb3_fs_vol_info);
 	} else {
 		cifs_dbg(FYI, "Invalid qfsinfo level %d\n", level);
 		return -EINVAL;
@@ -4089,6 +4092,11 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 		tcon->ss_flags = le32_to_cpu(ss_info->Flags);
 		tcon->perf_sector_size =
 			le32_to_cpu(ss_info->PhysicalBytesPerSectorForPerf);
+	} else if (level == FS_VOLUME_INFORMATION) {
+		struct smb3_fs_vol_info *vol_info = (struct smb3_fs_vol_info *)
+			(offset + (char *)rsp);
+		tcon->vol_serial_number = vol_info->VolumeSerialNumber;
+		tcon->vol_create_time = vol_info->VolumeCreationTime;
 	}
 
 qfsattr_exit:
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index a671adcc44a6..c2a4526512b5 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -1248,6 +1248,17 @@ struct smb3_fs_ss_info {
 	__le32 ByteOffsetForPartitionAlignment;
 } __packed;
 
+/* volume info struct - see MS-FSCC 2.5.9 */
+#define MAX_VOL_LABEL_LEN	32
+struct smb3_fs_vol_info {
+	__le64	VolumeCreationTime;
+	__u32	VolumeSerialNumber;
+	__le32	VolumeLabelLength; /* includes trailing null */
+	__u8	SupportsObjects; /* True if eg like NTFS, supports objects */
+	__u8	Reserved;
+	__u8	VolumeLabel[0]; /* variable len */
+} __packed;
+
 /* partial list of QUERY INFO levels */
 #define FILE_DIRECTORY_INFORMATION	1
 #define FILE_FULL_DIRECTORY_INFORMATION 2
-- 
cgit v1.2.3


From 2d304217832ea720337e7a6aa012aa828a77f9d4 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sun, 24 Jun 2018 23:28:12 -0500
Subject: smb3: add support for statfs for smb3.1.1 posix extensions

Output now matches expected stat -f output for all fields
except for Namelen and ID which were addressed in a companion
patch (which retrieves them from existing SMB3 mechanisms
and works whether POSIX enabled or not)

Signed-off-by: Steve French <smfrench@gmail.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/smb2ops.c   | 35 +++++++++++++++++++++++++-
 fs/cifs/smb2pdu.c   | 71 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/cifs/smb2pdu.h   |  1 +
 fs/cifs/smb2proto.h |  3 +++
 4 files changed, 109 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 09506d918ecb..e2a8b9d90ad8 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1533,6 +1533,39 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
+#ifdef CONFIG_CIFS_SMB311
+static int
+smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
+	     struct kstatfs *buf)
+{
+	int rc;
+	__le16 srch_path = 0; /* Null - open root of share */
+	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+	struct cifs_open_parms oparms;
+	struct cifs_fid fid;
+
+	if (!tcon->posix_extensions)
+		return smb2_queryfs(xid, tcon, buf);
+
+	oparms.tcon = tcon;
+	oparms.desired_access = FILE_READ_ATTRIBUTES;
+	oparms.disposition = FILE_OPEN;
+	oparms.create_options = 0;
+	oparms.fid = &fid;
+	oparms.reconnect = false;
+
+	rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL);
+	if (rc)
+		return rc;
+
+	rc = SMB311_posix_qfs_info(xid, tcon, fid.persistent_fid,
+				   fid.volatile_fid, buf);
+	buf->f_type = SMB2_MAGIC_NUMBER;
+	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	return rc;
+}
+#endif /* SMB311 */
+
 static bool
 smb2_compare_fids(struct cifsFileInfo *ob1, struct cifsFileInfo *ob2)
 {
@@ -3338,7 +3371,7 @@ struct smb_version_operations smb311_operations = {
 	.is_status_pending = smb2_is_status_pending,
 	.is_session_expired = smb2_is_session_expired,
 	.oplock_response = smb2_oplock_response,
-	.queryfs = smb2_queryfs,
+	.queryfs = smb311_queryfs,
 	.mand_lock = smb2_mand_lock,
 	.mand_unlock_range = smb2_unlock_range,
 	.push_mand_locks = smb2_push_mandatory_locks,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 6852ff5f06be..fa9fc3fab60e 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -3938,6 +3938,27 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
 	return;
 }
 
+#ifdef CONFIG_CIFS_SMB311
+static void
+copy_posix_fs_info_to_kstatfs(FILE_SYSTEM_POSIX_INFO *response_data,
+			struct kstatfs *kst)
+{
+	kst->f_bsize = le32_to_cpu(response_data->BlockSize);
+	kst->f_blocks = le64_to_cpu(response_data->TotalBlocks);
+	kst->f_bfree =  le64_to_cpu(response_data->BlocksAvail);
+	if (response_data->UserBlocksAvail == cpu_to_le64(-1))
+		kst->f_bavail = kst->f_bfree;
+	else
+		kst->f_bavail = le64_to_cpu(response_data->UserBlocksAvail);
+	if (response_data->TotalFileNodes != cpu_to_le64(-1))
+		kst->f_files = le64_to_cpu(response_data->TotalFileNodes);
+	if (response_data->FreeFileNodes != cpu_to_le64(-1))
+		kst->f_ffree = le64_to_cpu(response_data->FreeFileNodes);
+
+	return;
+}
+#endif /* SMB311 */
+
 static int
 build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 		   int outbuf_len, u64 persistent_fid, u64 volatile_fid)
@@ -3974,6 +3995,56 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 	return 0;
 }
 
+#ifdef CONFIG_CIFS_SMB311
+int
+SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
+	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
+{
+	struct smb_rqst rqst;
+	struct smb2_query_info_rsp *rsp = NULL;
+	struct kvec iov;
+	struct kvec rsp_iov;
+	int rc = 0;
+	int resp_buftype;
+	struct cifs_ses *ses = tcon->ses;
+	FILE_SYSTEM_POSIX_INFO *info = NULL;
+	int flags = 0;
+
+	rc = build_qfs_info_req(&iov, tcon, FS_POSIX_INFORMATION,
+				sizeof(FILE_SYSTEM_POSIX_INFO),
+				persistent_fid, volatile_fid);
+	if (rc)
+		return rc;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	memset(&rqst, 0, sizeof(struct smb_rqst));
+	rqst.rq_iov = &iov;
+	rqst.rq_nvec = 1;
+
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(iov.iov_base);
+	if (rc) {
+		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
+		goto posix_qfsinf_exit;
+	}
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
+
+	info = (FILE_SYSTEM_POSIX_INFO *)(
+		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			  sizeof(FILE_SYSTEM_POSIX_INFO));
+	if (!rc)
+		copy_posix_fs_info_to_kstatfs(info, fsdata);
+
+posix_qfsinf_exit:
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
+	return rc;
+}
+#endif /* SMB311 */
+
 int
 SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index c2a4526512b5..ecb0feeac844 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -1223,6 +1223,7 @@ struct smb2_lease_ack {
 #define FS_DRIVER_PATH_INFORMATION	9 /* Local only */
 #define FS_VOLUME_FLAGS_INFORMATION	10 /* Local only */
 #define FS_SECTOR_SIZE_INFORMATION	11 /* SMB3 or later. Query */
+#define FS_POSIX_INFORMATION		100 /* SMB3.1.1 POSIX. Query */
 
 struct smb2_fs_full_size_info {
 	__le64 TotalAllocationUnits;
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 6e6a4f2ec890..7019459c5748 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -197,6 +197,9 @@ void smb2_cancelled_close_fid(struct work_struct *work);
 extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
 			 struct kstatfs *FSData);
+extern int SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
+			 u64 persistent_file_id, u64 volatile_file_id,
+			 struct kstatfs *FSData);
 extern int SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id, int lvl);
 extern int SMB2_lock(const unsigned int xid, struct cifs_tcon *tcon,
-- 
cgit v1.2.3


From 876fe8870dcebdfa7dbd03075f111065f47aef38 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 28 Jun 2018 17:52:03 -0500
Subject: documentation update - remove old out of date feature info

Following up on a suggestion by Matthew Wilcox ...

The cifs CHANGES documentation file is out of date, and more
current information is in the wiki.  Delete the old version
information that is of little use to make this documentation
file more readable.

CC: Matthew Wilcox <mawilcox@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 Documentation/filesystems/cifs/CHANGES | 1072 +-------------------------------
 1 file changed, 4 insertions(+), 1068 deletions(-)

diff --git a/Documentation/filesystems/cifs/CHANGES b/Documentation/filesystems/cifs/CHANGES
index 455e1cc494a9..1df7f4910eb2 100644
--- a/Documentation/filesystems/cifs/CHANGES
+++ b/Documentation/filesystems/cifs/CHANGES
@@ -1,1068 +1,4 @@
-See https://wiki.samba.org/index.php/LinuxCIFSKernel for
-more current information.
-
-Version 1.62
-------------
-Add sockopt=TCP_NODELAY mount option. EA (xattr) routines hardened
-to more strictly handle corrupt frames.
-
-Version 1.61
-------------
-Fix append problem to Samba servers (files opened with O_APPEND could
-have duplicated data). Fix oops in cifs_lookup. Workaround problem
-mounting to OS/400 Netserve. Fix oops in cifs_get_tcp_session.
-Disable use of server inode numbers when server only
-partially supports them (e.g. for one server querying inode numbers on
-FindFirst fails but QPathInfo queries works). Fix oops with dfs in 
-cifs_put_smb_ses. Fix mmap to work on directio mounts (needed
-for OpenOffice when on forcedirectio mount e.g.)
-
-Version 1.60
--------------
-Fix memory leak in reconnect.  Fix oops in DFS mount error path.
-Set s_maxbytes to smaller (the max that vfs can handle) so that
-sendfile will now work over cifs mounts again.  Add noforcegid
-and noforceuid mount parameters. Fix small mem leak when using
-ntlmv2. Fix 2nd mount to same server but with different port to
-be allowed (rather than reusing the 1st port) - only when the
-user explicitly overrides the port on the 2nd mount.
-
-Version 1.59
-------------
-Client uses server inode numbers (which are persistent) rather than
-client generated ones by default (mount option "serverino" turned
-on by default if server supports it).  Add forceuid and forcegid
-mount options (so that when negotiating unix extensions specifying
-which uid mounted does not immediately force the server's reported
-uids to be overridden).  Add support for scope mount parm. Improve
-hard link detection to use same inode for both.  Do not set
-read-only dos attribute on directories (for chmod) since Windows
-explorer special cases this attribute bit for directories for
-a different purpose.
-
-Version 1.58
-------------
-Guard against buffer overruns in various UCS-2 to UTF-8 string conversions
-when the UTF-8 string is composed of unusually long (more than 4 byte) converted
-characters. Add support for mounting root of a share which redirects immediately
-to DFS target. Convert string conversion functions from Unicode to more
-accurately mark string length before allocating memory (which may help the
-rare cases where a UTF-8 string is much larger than the UCS2 string that
-we converted from).  Fix endianness of the vcnum field used during
-session setup to distinguish multiple mounts to same server from different
-userids. Raw NTLMSSP fixed (it requires /proc/fs/cifs/experimental
-flag to be set to 2, and mount must enable krb5 to turn on extended security).
-Performance of file create to Samba improved (posix create on lookup
-removes 1 of 2 network requests sent on file create)
- 
-Version 1.57
-------------
-Improve support for multiple security contexts to the same server. We
-used to use the same "vcnumber" for all connections which could cause
-the server to treat subsequent connections, especially those that
-are authenticated as guest, as reconnections, invalidating the earlier
-user's smb session.  This fix allows cifs to mount multiple times to the
-same server with different userids without risking invalidating earlier
-established security contexts.  fsync now sends SMB Flush operation
-to better ensure that we wait for server to write all of the data to
-server disk (not just write it over the network).  Add new mount
-parameter to allow user to disable sending the (slow) SMB flush on
-fsync if desired (fsync still flushes all cached write data to the server).
-Posix file open support added (turned off after one attempt if server
-fails to support it properly, as with Samba server versions prior to 3.3.2)
-Fix "redzone overwritten" bug in cifs_put_tcon (CIFSTcon may allocate too
-little memory for the "nativeFileSystem" field returned by the server
-during mount).  Endian convert inode numbers if necessary (makes it easier
-to compare inode numbers on network files from big endian systems). 
-
-Version 1.56
-------------
-Add "forcemandatorylock" mount option to allow user to use mandatory
-rather than posix (advisory) byte range locks, even though server would
-support posix byte range locks.  Fix query of root inode when prefixpath
-specified and user does not have access to query information about the
-top of the share.  Fix problem in 2.6.28 resolving DFS paths to
-Samba servers (worked to Windows).  Fix rmdir so that pending search
-(readdir) requests do not get invalid results which include the now
-removed directory.  Fix oops in cifs_dfs_ref.c when prefixpath is not reachable
-when using DFS.  Add better file create support to servers which support
-the CIFS POSIX protocol extensions (this adds support for new flags
-on create, and improves semantics for write of locked ranges).
-
-Version 1.55
-------------
-Various fixes to make delete of open files behavior more predictable
-(when delete of an open file fails we mark the file as "delete-on-close"
-in a way that more servers accept, but only if we can first rename the
-file to a temporary name).  Add experimental support for more safely
-handling fcntl(F_SETLEASE).  Convert cifs to using blocking tcp
-sends, and also let tcp autotune the socket send and receive buffers.
-This reduces the number of EAGAIN errors returned by TCP/IP in
-high stress workloads (and the number of retries on socket writes
-when sending large SMBWriteX requests).  Fix case in which a portion of
-data can in some cases not get written to the file on the server before the
-file is closed.  Fix DFS parsing to properly handle path consumed field,
-and to handle certain codepage conversions better.  Fix mount and
-umount race that can cause oops in mount or umount or reconnect.
-
-Version 1.54
-------------
-Fix premature write failure on congested networks (we would give up
-on EAGAIN from the socket too quickly on large writes).
-Cifs_mkdir and cifs_create now respect the setgid bit on parent dir.
-Fix endian problems in acl (mode from/to cifs acl) on bigendian
-architectures.  Fix problems with preserving timestamps on copying open
-files (e.g. "cp -a") to Windows servers.  For mkdir and create honor setgid bit
-on parent directory when server supports Unix Extensions but not POSIX
-create. Update cifs.upcall version to handle new Kerberos sec flags
-(this requires update of cifs.upcall program from Samba).  Fix memory leak
-on dns_upcall (resolving DFS referralls).  Fix plain text password
-authentication (requires setting SecurityFlags to 0x30030 to enable
-lanman and plain text though).  Fix writes to be at correct offset when
-file is open with O_APPEND and file is on a directio (forcediretio) mount.
-Fix bug in rewinding readdir directory searches.  Add nodfs mount option.
-
-Version 1.53
-------------
-DFS support added (Microsoft Distributed File System client support needed
-for referrals which enable a hierarchical name space among servers).
-Disable temporary caching of mode bits to servers which do not support
-storing of mode (e.g. Windows servers, when client mounts without cifsacl
-mount option) and add new "dynperm" mount option to enable temporary caching
-of mode (enable old behavior).  Fix hang on mount caused when server crashes
-tcp session during negotiate protocol.
-
-Version 1.52
-------------
-Fix oops on second mount to server when null auth is used.
-Enable experimental Kerberos support.  Return writebehind errors on flush
-and sync so that events like out of disk space get reported properly on
-cached files. Fix setxattr failure to certain Samba versions. Fix mount
-of second share to disconnected server session (autoreconnect on this).
-Add ability to modify cifs acls for handling chmod (when mounted with
-cifsacl flag). Fix prefixpath path separator so we can handle mounts
-with prefixpaths longer than one directory (one path component) when
-mounted to Windows servers.  Fix slow file open when cifsacl
-enabled. Fix memory leak in FindNext when the SMB call returns -EBADF.
-
-
-Version 1.51
-------------
-Fix memory leak in statfs when mounted to very old servers (e.g.
-Windows 9x).  Add new feature "POSIX open" which allows servers
-which support the current POSIX Extensions to provide better semantics
-(e.g. delete for open files opened with posix open).  Take into
-account umask on posix mkdir not just older style mkdir.  Add
-ability to mount to IPC$ share (which allows CIFS named pipes to be
-opened, read and written as if they were files).  When 1st tree
-connect fails (e.g. due to signing negotiation failure) fix
-leak that causes cifsd not to stop and rmmod to fail to cleanup
-cifs_request_buffers pool. Fix problem with POSIX Open/Mkdir on
-bigendian architectures. Fix possible memory corruption when
-EAGAIN returned on kern_recvmsg. Return better error if server
-requires packet signing but client has disabled it. When mounted
-with cifsacl mount option - mode bits are approximated based
-on the contents of the ACL of the file or directory. When cifs
-mount helper is missing convert make sure that UNC name 
-has backslash (not forward slash) between ip address of server
-and the share name.
-
-Version 1.50
-------------
-Fix NTLMv2 signing. NFS server mounted over cifs works (if cifs mount is
-done with "serverino" mount option).  Add support for POSIX Unlink
-(helps with certain sharing violation cases when server such as
-Samba supports newer POSIX CIFS Protocol Extensions). Add "nounix"
-mount option to allow disabling the CIFS Unix Extensions for just
-that mount. Fix hang on spinlock in find_writable_file (race when
-reopening file after session crash).  Byte range unlock request to
-windows server could unlock more bytes (on server copy of file)
-than intended if start of unlock request is well before start of
-a previous byte range lock that we issued.
-
-Version 1.49
-------------
-IPv6 support.  Enable ipv6 addresses to be passed on mount (put the ipv6
-address after the "ip=" mount option, at least until mount.cifs is fixed to
-handle DNS host to ipv6 name translation).  Accept override of uid or gid
-on mount even when Unix Extensions are negotiated (it used to be ignored
-when Unix Extensions were ignored).  This allows users to override the
-default uid and gid for files when they are certain that the uids or
-gids on the server do not match those of the client.  Make "sec=none"
-mount override username (so that null user connection is attempted)
-to match what documentation said. Support for very large reads, over 127K,
-available to some newer servers (such as Samba 3.0.26 and later but
-note that it also requires setting CIFSMaxBufSize at module install
-time to a larger value which may hurt performance in some cases).
-Make sign option force signing (or fail if server does not support it).
-
-Version 1.48
-------------
-Fix mtime bouncing around from local idea of last write times to remote time.
-Fix hang (in i_size_read) when simultaneous size update of same remote file
-on smp system corrupts sequence number. Do not reread unnecessarily partial page
-(which we are about to overwrite anyway) when writing out file opened rw.
-When DOS attribute of file on non-Unix server's file changes on the server side
-from read-only back to read-write, reflect this change in default file mode
-(we had been leaving a file's mode read-only until the inode were reloaded).
-Allow setting of attribute back to ATTR_NORMAL (removing readonly dos attribute
-when archive dos attribute not set and we are changing mode back to writeable
-on server which does not support the Unix Extensions).  Remove read only dos
-attribute on chmod when adding any write permission (ie on any of
-user/group/other (not all of user/group/other ie  0222) when
-mounted to windows.  Add support for POSIX MkDir (slight performance
-enhancement and eliminates the network race between the mkdir and set 
-path info of the mode).
-
-
-Version 1.47
-------------
-Fix oops in list_del during mount caused by unaligned string.
-Fix file corruption which could occur on some large file
-copies caused by writepages page i/o completion bug.
-Seek to SEEK_END forces check for update of file size for non-cached
-files. Allow file size to be updated on remote extend of locally open,
-non-cached file.  Fix reconnect to newer Samba servers (or other servers
-which support the CIFS Unix/POSIX extensions) so that we again tell the
-server the Unix/POSIX cifs capabilities which we support (SetFSInfo).
-Add experimental support for new POSIX Open/Mkdir (which returns
-stat information on the open, and allows setting the mode).
-
-Version 1.46
-------------
-Support deep tree mounts.  Better support OS/2, Win9x (DOS) time stamps.
-Allow null user to be specified on mount ("username="). Do not return
-EINVAL on readdir when filldir fails due to overwritten blocksize
-(fixes FC problem).  Return error in rename 2nd attempt retry (ie report
-if rename by handle also fails, after rename by path fails, we were
-not reporting whether the retry worked or not). Fix NTLMv2 to
-work to Windows servers (mount with option "sec=ntlmv2").
-
-Version 1.45
-------------
-Do not time out lockw calls when using posix extensions. Do not
-time out requests if server still responding reasonably fast
-on requests on other threads.  Improve POSIX locking emulation,
-(lock cancel now works, and unlock of merged range works even
-to Windows servers now).  Fix oops on mount to lanman servers
-(win9x, os/2 etc.) when null password.  Do not send listxattr
-(SMB to query all EAs) if nouser_xattr specified.  Fix SE Linux
-problem (instantiate inodes/dentries in right order for readdir).
-
-Version 1.44
-------------
-Rewritten sessionsetup support, including support for legacy SMB
-session setup needed for OS/2 and older servers such as Windows 95 and 98.
-Fix oops on ls to OS/2 servers.  Add support for level 1 FindFirst
-so we can do search (ls etc.) to OS/2.  Do not send NTCreateX
-or recent levels of FindFirst unless server says it supports NT SMBs
-(instead use legacy equivalents from LANMAN dialect). Fix to allow
-NTLMv2 authentication support (now can use stronger password hashing
-on mount if corresponding /proc/fs/cifs/SecurityFlags is set (0x4004).
-Allow override of global cifs security flags on mount via "sec=" option(s).
-
-Version 1.43
-------------
-POSIX locking to servers which support CIFS POSIX Extensions
-(disabled by default controlled by proc/fs/cifs/Experimental).
-Handle conversion of long share names (especially Asian languages)
-to Unicode during mount. Fix memory leak in sess struct on reconnect.
-Fix rare oops after acpi suspend.  Fix O_TRUNC opens to overwrite on
-cifs open which helps rare case when setpathinfo fails or server does
-not support it. 
-
-Version 1.42
-------------
-Fix slow oplock break when mounted to different servers at the same time and
-the tids match and we try to find matching fid on wrong server. Fix read
-looping when signing required by server (2.6.16 kernel only). Fix readdir
-vs. rename race which could cause each to hang. Return . and .. even
-if server does not.  Allow searches to skip first three entries and
-begin at any location. Fix oops in find_writeable_file.
-
-Version 1.41
-------------
-Fix NTLMv2 security (can be enabled in /proc/fs/cifs) so customers can
-configure stronger authentication.  Fix sfu symlinks so they can
-be followed (not just recognized).  Fix wraparound of bcc on
-read responses when buffer size over 64K and also fix wrap of
-max smb buffer size when CIFSMaxBufSize over 64K.  Fix oops in
-cifs_user_read and cifs_readpages (when EAGAIN on send of smb
-on socket is returned over and over).  Add POSIX (advisory) byte range
-locking support (requires server with newest CIFS UNIX Extensions
-to the protocol implemented). Slow down negprot slightly in port 139
-RFC1001 case to give session_init time on buggy servers.
-
-Version 1.40
-------------
-Use fsuid (fsgid) more consistently instead of uid (gid). Improve performance
-of readpages by eliminating one extra memcpy. Allow update of file size
-from remote server even if file is open for write as long as mount is
-directio.  Recognize share mode security and send NTLM encrypted password
-on tree connect if share mode negotiated.
-
-Version 1.39
-------------
-Defer close of a file handle slightly if pending writes depend on that handle
-(this reduces the EBADF bad file handle errors that can be logged under heavy
-stress on writes). Modify cifs Kconfig options to expose CONFIG_CIFS_STATS2 
-Fix SFU style symlinks and mknod needed for servers which do not support the
-CIFS Unix Extensions.  Fix setfacl/getfacl on bigendian. Timeout negative
-dentries so files that the client sees as deleted but that later get created
-on the server will be recognized.  Add client side permission check on setattr.
-Timeout stuck requests better (where server has never responded or sent corrupt
-responses)
-
-Version 1.38
-------------
-Fix tcp socket retransmission timeouts (e.g. on ENOSPACE from the socket)
-to be smaller at first (but increasing) so large write performance performance
-over GigE is better.  Do not hang thread on illegal byte range lock response
-from Windows (Windows can send an RFC1001 size which does not match smb size) by
-allowing an SMBs TCP length to be up to a few bytes longer than it should be.
-wsize and rsize can now be larger than negotiated buffer size if server
-supports large readx/writex, even when directio mount flag not specified.
-Write size will in many cases now be 16K instead of 4K which greatly helps
-file copy performance on lightly loaded networks.  Fix oops in dnotify
-when experimental config flag enabled. Make cifsFYI more granular.
-
-Version 1.37
-------------
-Fix readdir caching when unlink removes file in current search buffer,
-and this is followed by a rewind search to just before the deleted entry.
-Do not attempt to set ctime unless atime and/or mtime change requested
-(most servers throw it away anyway). Fix length check of received smbs
-to be more accurate. Fix big endian problem with mapchars mount option,
-and with a field returned by statfs.
-
-Version 1.36
-------------
-Add support for mounting to older pre-CIFS servers such as Windows9x and ME.
-For these older servers, add option for passing netbios name of server in
-on mount (servernetbiosname).  Add suspend support for power management, to
-avoid cifsd thread preventing software suspend from working.
-Add mount option for disabling the default behavior of sending byte range lock
-requests to the server (necessary for certain applications which break with
-mandatory lock behavior such as Evolution), and also mount option for
-requesting case insensitive matching for path based requests (requesting
-case sensitive is the default).
-
-Version 1.35
-------------
-Add writepage performance improvements.  Fix path name conversions
-for long filenames on mounts which were done with "mapchars" mount option
-specified.  Ensure multiplex ids do not collide.  Fix case in which 
-rmmod can oops if done soon after last unmount.  Fix truncated
-search (readdir) output when resume filename was a long filename.
-Fix filename conversion when mapchars mount option was specified and
-filename was a long filename.
-
-Version 1.34
-------------
-Fix error mapping of the TOO_MANY_LINKS (hardlinks) case.
-Do not oops if root user kills cifs oplock kernel thread or
-kills the cifsd thread (NB: killing the cifs kernel threads is not
-recommended, unmount and rmmod cifs will kill them when they are
-no longer needed).  Fix readdir to ASCII servers (ie older servers
-which do not support Unicode) and also require asterisk.
-Fix out of memory case in which data could be written one page
-off in the page cache.
-
-Version 1.33
-------------
-Fix caching problem, in which readdir of directory containing a file
-which was cached could cause the file's time stamp to be updated
-without invalidating the readahead data (so we could get stale
-file data on the client for that file even as the server copy changed).
-Cleanup response processing so cifsd can not loop when abnormally
-terminated.
-
-
-Version 1.32
-------------
-Fix oops in ls when Transact2 FindFirst (or FindNext) returns more than one
-transact response for an SMB request and search entry split across two frames.
-Add support for lsattr (getting ext2/ext3/reiserfs attr flags from the server)
-as new protocol extensions. Do not send Get/Set calls for POSIX ACLs
-unless server explicitly claims to support them in CIFS Unix extensions
-POSIX ACL capability bit. Fix packet signing when multiuser mounting with
-different users from the same client to the same server. Fix oops in
-cifs_close. Add mount option for remapping reserved characters in
-filenames (also allow recognizing files with created by SFU which have any
-of these seven reserved characters, except backslash, to be recognized).
-Fix invalid transact2 message (we were sometimes trying to interpret
-oplock breaks as SMB responses). Add ioctl for checking that the
-current uid matches the uid of the mounter (needed by umount.cifs).
-Reduce the number of large buffer allocations in cifs response processing
-(significantly reduces memory pressure under heavy stress with multiple
-processes accessing the same server at the same time).
-
-Version 1.31
-------------
-Fix updates of DOS attributes and time fields so that files on NT4 servers
-do not get marked delete on close. Display sizes of cifs buffer pools in
-cifs stats. Fix oops in unmount when cifsd thread being killed by 
-shutdown. Add generic readv/writev and aio support. Report inode numbers 
-consistently in readdir and lookup (when serverino mount option is
-specified use the inode number that the server reports - for both lookup
-and readdir, otherwise by default the locally generated inode number is used
-for inodes created in either path since servers are not always able to 
-provide unique inode numbers when exporting multiple volumes from under one
-sharename).
-
-Version 1.30
-------------
-Allow new nouser_xattr mount parm to disable xattr support for user namespace.
-Do not flag user_xattr mount parm in dmesg.  Retry failures setting file time  
-(mostly affects NT4 servers) by retry with handle based network operation. 
-Add new POSIX Query FS Info for returning statfs info more accurately.
-Handle passwords with multiple commas in them.
-
-Version 1.29
-------------
-Fix default mode in sysfs of cifs module parms.  Remove old readdir routine.
-Fix capabilities flags for large readx so as to allow reads larger than 64K.
-
-Version 1.28
-------------
-Add module init parm for large SMB buffer size (to allow it to be changed
-from its default of 16K) which is especially useful for large file copy
-when mounting with the directio mount option. Fix oops after 
-returning from mount when experimental ExtendedSecurity enabled and
-SpnegoNegotiated returning invalid error. Fix case to retry better when 
-peek returns from 1 to 3 bytes on socket which should have more data.
-Fixed path based calls (such as cifs lookup) to handle path names
-longer than 530 (now can handle PATH_MAX). Fix pass through authentication
-from Samba server to DC (Samba required dummy LM password).
-
-Version 1.27
-------------
-Turn off DNOTIFY (directory change notification support) by default
-(unless built with the experimental flag) to fix hang with KDE
-file browser. Fix DNOTIFY flag mappings.  Fix hang (in wait_event
-waiting on an SMB response) in SendReceive when session dies but
-reconnects quickly from another task.  Add module init  parms for
-minimum number of large and small network buffers in the buffer pools,
-and for the maximum number of simultaneous requests.
-
-Version 1.26
-------------
-Add setfacl support to allow setting of ACLs remotely to Samba 3.10 and later
-and other POSIX CIFS compliant servers.  Fix error mapping for getfacl 
-to EOPNOTSUPP when server does not support posix acls on the wire. Fix 
-improperly zeroed buffer in CIFS Unix extensions set times call. 
-
-Version 1.25
-------------
-Fix internationalization problem in cifs readdir with filenames that map to 
-longer UTF-8 strings than the string on the wire was in Unicode.  Add workaround
-for readdir to netapp servers. Fix search rewind (seek into readdir to return 
-non-consecutive entries).  Do not do readdir when server negotiates 
-buffer size to small to fit filename. Add support for reading POSIX ACLs from
-the server (add also acl and noacl mount options).
-
-Version 1.24
-------------
-Optionally allow using server side inode numbers, rather than client generated
-ones by specifying mount option "serverino" - this is required for some apps
-to work which double check hardlinked files and have persistent inode numbers.
-
-Version 1.23
-------------
-Multiple bigendian fixes. On little endian systems (for reconnect after
-network failure) fix tcp session reconnect code so we do not try first
-to reconnect on reverse of port 445. Treat reparse points (NTFS junctions)
-as directories rather than symlinks because we can do follow link on them.
-
-Version 1.22
-------------
-Add config option to enable XATTR (extended attribute) support, mapping
-xattr names in the "user." namespace space to SMB/CIFS EAs. Lots of
-minor fixes pointed out by the Stanford SWAT checker (mostly missing
-or out of order NULL pointer checks in little used error paths).
-
-Version 1.21
-------------
-Add new mount parm to control whether mode check (generic_permission) is done
-on the client.  If Unix extensions are enabled and the uids on the client
-and server do not match, client permission checks are meaningless on
-server uids that do not exist on the client (this does not affect the
-normal ACL check which occurs on the server).  Fix default uid
-on mknod to match create and mkdir. Add optional mount parm to allow
-override of the default uid behavior (in which the server sets the uid
-and gid of newly created files). Normally for network filesystem mounts
-user want the server to set the uid/gid on newly created files (rather than 
-using uid of the client processes you would in a local filesystem).
-
-Version 1.20
-------------
-Make transaction counts more consistent. Merge /proc/fs/cifs/SimultaneousOps
-info into /proc/fs/cifs/DebugData.  Fix oops in rare oops in readdir 
-(in build_wildcard_path_from_dentry).  Fix mknod to pass type field
-(block/char/fifo) properly.  Remove spurious mount warning log entry when
-credentials passed as mount argument. Set major/minor device number in
-inode for block and char devices when unix extensions enabled.
-
-Version 1.19
-------------
-Fix /proc/fs/cifs/Stats and DebugData display to handle larger
-amounts of return data. Properly limit requests to MAX_REQ (50
-is the usual maximum active multiplex SMB/CIFS requests per server).
-Do not kill cifsd (and thus hurt the other SMB session) when more than one
-session to the same server (but with different userids) exists and one
-of the two user's smb sessions is being removed while leaving the other.
-Do not loop reconnecting in cifsd demultiplex thread when admin
-kills the thread without going through unmount.
-
-Version 1.18
-------------
-Do not rename hardlinked files (since that should be a noop). Flush
-cached write behind data when reopening a file after session abend,
-except when already in write. Grab per socket sem during reconnect 
-to avoid oops in sendmsg if overlapping with reconnect. Do not
-reset cached inode file size on readdir for files open for write on 
-client.
-
-
-Version 1.17
-------------
-Update number of blocks in file so du command is happier (in Linux a fake
-blocksize of 512 is required for calculating number of blocks in inode).
-Fix prepare write of partial pages to read in data from server if possible.
-Fix race on tcpStatus field between unmount and reconnection code, causing
-cifsd process sometimes to hang around forever. Improve out of memory
-checks in cifs_filldir
-
-Version 1.16
-------------
-Fix incorrect file size in file handle based setattr on big endian hardware.
-Fix oops in build_path_from_dentry when out of memory.  Add checks for invalid
-and closing file structs in writepage/partialpagewrite.  Add statistics
-for each mounted share (new menuconfig option). Fix endianness problem in
-volume information displayed in /proc/fs/cifs/DebugData (only affects
-affects big endian architectures). Prevent renames while constructing
-path names for open, mkdir and rmdir.
-
-Version 1.15
-------------
-Change to mempools for alloc smb request buffers and multiplex structs
-to better handle low memory problems (and potential deadlocks).
-
-Version 1.14
-------------
-Fix incomplete listings of large directories on Samba servers when Unix
-extensions enabled.  Fix oops when smb_buffer can not be allocated. Fix
-rename deadlock when writing out dirty pages at same time.
-
-Version 1.13
-------------
-Fix open of files in which O_CREATE can cause the mode to change in
-some cases. Fix case in which retry of write overlaps file close.
-Fix PPC64 build error.  Reduce excessive stack usage in smb password
-hashing. Fix overwrite of Linux user's view of file mode to Windows servers.
-
-Version 1.12
-------------
-Fixes for large file copy, signal handling, socket retry, buffer
-allocation and low memory situations.
-
-Version 1.11
-------------
-Better port 139 support to Windows servers (RFC1001/RFC1002 Session_Initialize)
-also now allowing support for specifying client netbiosname.  NT4 support added.
-
-Version 1.10
-------------
-Fix reconnection (and certain failed mounts) to properly wake up the
-blocked users thread so it does not seem hung (in some cases was blocked
-until the cifs receive timeout expired). Fix spurious error logging
-to kernel log when application with open network files killed. 
-
-Version 1.09
-------------
-Fix /proc/fs module unload warning message (that could be logged
-to the kernel log). Fix intermittent failure in connectathon
-test7 (hardlink count not immediately refreshed in case in which
-inode metadata can be incorrectly kept cached when time near zero)
-
-Version 1.08
-------------
-Allow file_mode and dir_mode (specified at mount time) to be enforced
-locally (the server already enforced its own ACLs too) for servers
-that do not report the correct mode (do not support the 
-CIFS Unix Extensions).
-
-Version 1.07
-------------
-Fix some small memory leaks in some unmount error paths. Fix major leak
-of cache pages in readpages causing multiple read oriented stress
-testcases (including fsx, and even large file copy) to fail over time. 
-
-Version 1.06
-------------
-Send NTCreateX with ATTR_POSIX if Linux/Unix extensions negotiated with server.
-This allows files that differ only in case and improves performance of file
-creation and file open to such servers.  Fix semaphore conflict which causes 
-slow delete of open file to Samba (which unfortunately can cause an oplock
-break to self while vfs_unlink held i_sem) which can hang for 20 seconds.
-
-Version 1.05
-------------
-fixes to cifs_readpages for fsx test case
-
-Version 1.04
-------------
-Fix caching data integrity bug when extending file size especially when no
-oplock on file.  Fix spurious logging of valid already parsed mount options
-that are parsed outside of the cifs vfs such as nosuid.
-
-
-Version 1.03
-------------
-Connect to server when port number override not specified, and tcp port
-unitialized.  Reset search to restart at correct file when kernel routine
-filldir returns error during large directory searches (readdir). 
-
-Version 1.02
-------------
-Fix caching problem when files opened by multiple clients in which 
-page cache could contain stale data, and write through did
-not occur often enough while file was still open when read ahead
-(read oplock) not allowed.  Treat "sep=" when first mount option
-as an override of comma as the default separator between mount
-options. 
-
-Version 1.01
-------------
-Allow passwords longer than 16 bytes. Allow null password string.
-
-Version 1.00
-------------
-Gracefully clean up failed mounts when attempting to mount to servers such as
-Windows 98 that terminate tcp sessions during protocol negotiation.  Handle
-embedded commas in mount parsing of passwords.
-
-Version 0.99
-------------
-Invalidate local inode cached pages on oplock break and when last file
-instance is closed so that the client does not continue using stale local
-copy rather than later modified server copy of file.  Do not reconnect
-when server drops the tcp session prematurely before negotiate
-protocol response.  Fix oops in reopen_file when dentry freed.  Allow
-the support for CIFS Unix Extensions to be disabled via proc interface.
-
-Version 0.98
-------------
-Fix hang in commit_write during reconnection of open files under heavy load.
-Fix unload_nls oops in a mount failure path. Serialize writes to same socket
-which also fixes any possible races when cifs signatures are enabled in SMBs
-being sent out of signature sequence number order.    
-
-Version 0.97
-------------
-Fix byte range locking bug (endian problem) causing bad offset and
-length.
-
-Version 0.96
-------------
-Fix oops (in send_sig) caused by CIFS unmount code trying to
-wake up the demultiplex thread after it had exited. Do not log
-error on harmless oplock release of closed handle.
-
-Version 0.95
-------------
-Fix unsafe global variable usage and password hash failure on gcc 3.3.1
-Fix problem reconnecting secondary mounts to same server after session 
-failure.  Fix invalid dentry - race in mkdir when directory gets created
-by another client between the lookup and mkdir.
- 
-Version 0.94
-------------
-Fix to list processing in reopen_files. Fix reconnection when server hung
-but tcpip session still alive.  Set proper timeout on socket read.
-
-Version 0.93
-------------
-Add missing mount options including iocharset.  SMP fixes in write and open. 
-Fix errors in reconnecting after TCP session failure.  Fix module unloading
-of default nls codepage
-
-Version 0.92
-------------
-Active smb transactions should never go negative (fix double FreeXid). Fix
-list processing in file routines. Check return code on kmalloc in open.
-Fix spinlock usage for SMP.
-
-Version 0.91
-------------
-Fix oops in reopen_files when invalid dentry. drop dentry on server rename 
-and on revalidate errors. Fix cases where pid is now tgid.  Fix return code
-on create hard link when server does not support them. 
-
-Version 0.90
-------------
-Fix scheduling while atomic error in getting inode info on newly created file. 
-Fix truncate of existing files opened with O_CREAT but not O_TRUNC set.
-
-Version 0.89
-------------
-Fix oops on write to dead tcp session. Remove error log write for case when file open
-O_CREAT but not O_EXCL
-
-Version 0.88
-------------
-Fix non-POSIX behavior on rename of open file and delete of open file by taking 
-advantage of trans2 SetFileInfo rename facility if available on target server.
-Retry on ENOSPC and EAGAIN socket errors.
-
-Version 0.87
-------------
-Fix oops on big endian readdir.  Set blksize to be even power of two (2**blkbits) to fix
-allocation size miscalculation. After oplock token lost do not read through
-cache. 
-
-Version 0.86
-------------
-Fix oops on empty file readahead.  Fix for file size handling for locally cached files.
-
-Version 0.85
-------------
-Fix oops in mkdir when server fails to return inode info. Fix oops in reopen_files
-during auto reconnection to server after server recovered from failure.
-
-Version 0.84
-------------
-Finish support for Linux 2.5 open/create changes, which removes the
-redundant NTCreate/QPathInfo/close that was sent during file create.
-Enable oplock by default. Enable packet signing by default (needed to 
-access many recent Windows servers)
-
-Version 0.83
-------------
-Fix oops when mounting to long server names caused by inverted parms to kmalloc.
-Fix MultiuserMount (/proc/fs/cifs configuration setting) so that when enabled
-we will choose a cifs user session (smb uid) that better matches the local
-uid if a) the mount uid does not match the current uid and b) we have another
-session to the same server (ip address) for a different mount which
-matches the current local uid.
-
-Version 0.82
-------------
-Add support for mknod of block or character devices.  Fix oplock
-code (distributed caching) to properly send response to oplock
-break from server.
-
-Version 0.81
-------------
-Finish up CIFS packet digital signing for the default
-NTLM security case. This should help Windows 2003
-network interoperability since it is common for
-packet signing to be required now. Fix statfs (stat -f)
-which recently started returning errors due to 
-invalid value (-1 instead of 0) being set in the
-struct kstatfs f_ffiles field.
-
-Version 0.80
------------
-Fix oops on stopping oplock thread when removing cifs when
-built as module.
-
-Version 0.79
-------------
-Fix mount options for ro (readonly), uid, gid and file and directory mode. 
-
-Version 0.78
-------------
-Fix errors displayed on failed mounts to be more understandable.
-Fixed various incorrect or misleading smb to posix error code mappings.
-
-Version 0.77
-------------
-Fix display of NTFS DFS junctions to display as symlinks.
-They are the network equivalent.  Fix oops in 
-cifs_partialpagewrite caused by missing spinlock protection
-of openfile linked list.  Allow writebehind caching errors to 
-be returned to the application at file close.
-
-Version 0.76
-------------
-Clean up options displayed in /proc/mounts by show_options to
-be more consistent with other filesystems.
-
-Version 0.75
-------------
-Fix delete of readonly file to Windows servers.  Reflect
-presence or absence of read only dos attribute in mode
-bits for servers that do not support CIFS Unix extensions.
-Fix shortened results on readdir of large directories to
-servers supporting CIFS Unix extensions (caused by
-incorrect resume key).
-
-Version 0.74
-------------
-Fix truncate bug (set file size) that could cause hangs e.g. running fsx
-
-Version 0.73
-------------
-unload nls if mount fails.
-
-Version 0.72
-------------
-Add resume key support to search (readdir) code to workaround
-Windows bug.  Add /proc/fs/cifs/LookupCacheEnable which
-allows disabling caching of attribute information for
-lookups.
-
-Version 0.71
-------------
-Add more oplock handling (distributed caching code).  Remove
-dead code.  Remove excessive stack space utilization from
-symlink routines.
-
-Version 0.70
-------------
-Fix oops in get dfs referral (triggered when null path sent in to
-mount).  Add support for overriding rsize at mount time.
-
-Version 0.69
-------------
-Fix buffer overrun in readdir which caused intermittent kernel oopses.
-Fix writepage code to release kmap on write data.  Allow "-ip=" new 
-mount option to be passed in on parameter distinct from the first part
-(server name portion of) the UNC name.  Allow override of the
-tcp port of the target server via new mount option "-port="  
-
-Version 0.68
-------------
-Fix search handle leak on rewind.  Fix setuid and gid so that they are 
-reflected in the local inode immediately.  Cleanup of whitespace
-to make 2.4 and 2.5 versions more consistent.
-
-
-Version 0.67
-------------
-Fix signal sending so that captive thread (cifsd) exits on umount 
-(which was causing the warning in kmem_cache_free of the request buffers
-at rmmod time).  This had broken as a sideeffect of the recent global
-kernel change to daemonize.  Fix memory leak in readdir code which
-showed up in "ls -R" (and applications that did search rewinding).
-
-Version 0.66
-------------
-Reconnect tids and fids after session reconnection (still do not
-reconnect byte range locks though).  Fix problem caching
-lookup information for directory inodes, improving performance,
-especially in deep directory trees.  Fix various build warnings.
-
-Version 0.65
-------------
-Finish fixes to commit write for caching/readahead consistency.  fsx 
-now works to Samba servers.  Fix oops caused when readahead
-was interrupted by a signal.
-
-Version 0.64
-------------
-Fix data corruption (in partial page after truncate) that caused fsx to
-fail to Windows servers.  Cleaned up some extraneous error logging in
-common error paths.  Add generic sendfile support.
-
-Version 0.63
-------------
-Fix memory leak in AllocMidQEntry.
-Finish reconnection logic, so connection with server can be dropped
-(or server rebooted) and the cifs client will reconnect.  
-
-Version 0.62
-------------
-Fix temporary socket leak when bad userid or password specified 
-(or other SMBSessSetup failure).  Increase maximum buffer size to slightly
-over 16K to allow negotiation of up to Samba and Windows server default read 
-sizes.  Add support for readpages
-
-Version 0.61
-------------
-Fix oops when username not passed in on mount.  Extensive fixes and improvements
-to error logging (strip redundant newlines, change debug macros to ensure newline
-passed in and to be more consistent).  Fix writepage wrong file handle problem,
-a readonly file handle could be incorrectly used to attempt to write out
-file updates through the page cache to multiply open files.  This could cause
-the iozone benchmark to fail on the fwrite test. Fix bug mounting two different
-shares to the same Windows server when using different usernames
-(doing this to Samba servers worked but Windows was rejecting it) - now it is
-possible to use different userids when connecting to the same server from a
-Linux client. Fix oops when treeDisconnect called during unmount on
-previously freed socket.
-
-Version 0.60
-------------
-Fix oops in readpages caused by not setting address space operations in inode in 
-rare code path. 
-
-Version 0.59
-------------
-Includes support for deleting of open files and renaming over existing files (per POSIX
-requirement).  Add readlink support for Windows junction points (directory symlinks).
-
-Version 0.58
-------------
-Changed read and write to go through pagecache. Added additional address space operations.
-Memory mapped operations now working.
-
-Version 0.57
-------------
-Added writepage code for additional memory mapping support.  Fixed leak in xids causing
-the simultaneous operations counter (/proc/fs/cifs/SimultaneousOps) to increase on 
-every stat call.  Additional formatting cleanup. 
-
-Version 0.56
-------------
-Fix bigendian bug in order of time conversion. Merge 2.5 to 2.4 version.  Formatting cleanup.   
-
-Version 0.55
-------------
-Fixes from Zwane Mwaikambo for adding missing return code checking in a few places.
-Also included a modified version of his fix to protect global list manipulation of
-the smb session and tree connection and mid related global variables.
-
-Version 0.54
-------------
-Fix problem with captive thread hanging around at unmount time.  Adjust to 2.5.42-pre
-changes to superblock layout.   Remove wasteful allocation of smb buffers (now the send 
-buffer is reused for responses).  Add more oplock handling. Additional minor cleanup.
-
-Version 0.53
-------------
-More stylistic updates to better match kernel style.  Add additional statistics
-for filesystem which can be viewed via /proc/fs/cifs.  Add more pieces of NTLMv2
-and CIFS Packet Signing enablement.
-
-Version 0.52
-------------
-Replace call to sleep_on with safer wait_on_event.
-Make stylistic changes to better match kernel style recommendations.
-Remove most typedef usage (except for the PDUs themselves).
-
-Version 0.51
-------------
-Update mount so the -unc mount option is no longer required (the ip address can be specified
-in a UNC style device name.   Implementation of readpage/writepage started.
-
-Version 0.50
-------------
-Fix intermittent problem with incorrect smb header checking on badly 
-fragmented tcp responses
-
-Version 0.49
-------------
-Fixes to setting of allocation size and file size.
-
-Version 0.48
-------------
-Various 2.5.38 fixes.  Now works on 2.5.38
-
-Version 0.47
-------------
-Prepare for 2.5 kernel merge.  Remove ifdefs.
-
-Version 0.46
-------------
-Socket buffer management fixes.  Fix dual free.
-
-Version 0.45
-------------
-Various big endian fixes for hardlinks and symlinks and also for dfs.
-
-Version 0.44
-------------
-Various big endian fixes for servers with Unix extensions such as Samba
-
-Version 0.43
-------------
-Various FindNext fixes for incorrect filenames on large directory searches on big endian
-clients.  basic posix file i/o tests now work on big endian machines, not just le
-
-Version 0.42
-------------
-SessionSetup and NegotiateProtocol now work from Big Endian machines.
-Various Big Endian fixes found during testing on the Linux on 390.  Various fixes for compatibility with older
-versions of 2.4 kernel (now builds and works again on kernels at least as early as 2.4.7).
-
-Version 0.41
-------------
-Various minor fixes for Connectathon Posix "basic" file i/o test suite.  Directory caching fixed so hardlinked
-files now return the correct number of links on fstat as they are repeatedly linked and unlinked.
-
-Version 0.40
-------------
-Implemented "Raw" (i.e. not encapsulated in SPNEGO) NTLMSSP (i.e. the Security Provider Interface used to negotiate
-session advanced session authentication).  Raw NTLMSSP is preferred by Windows 2000 Professional and Windows XP.
-Began implementing support for SPNEGO encapsulation of NTLMSSP based session authentication blobs
-(which is the mechanism preferred by Windows 2000 server in the absence of Kerberos).
-
-Version 0.38
-------------
-Introduced optional mount helper utility mount.cifs and made coreq changes to cifs vfs to enable
-it. Fixed a few bugs in the DFS code (e.g. bcc two bytes too short and incorrect uid in PDU).
-
-Version 0.37
-------------
-Rewrote much of connection and mount/unmount logic to handle bugs with
-multiple uses to same share, multiple users to same server etc.
-
-Version 0.36
-------------
-Fixed major problem with dentry corruption (missing call to dput)
-
-Version 0.35
-------------
-Rewrite of readdir code to fix bug. Various fixes for bigendian machines.
-Begin adding oplock support.  Multiusermount and oplockEnabled flags added to /proc/fs/cifs
-although corresponding function not fully implemented in the vfs yet
-
-Version 0.34
-------------
-Fixed dentry caching bug, misc. cleanup 
-
-Version 0.33
-------------
-Fixed 2.5 support to handle build and configure changes as well as misc. 2.5 changes.  Now can build
-on current 2.5 beta version (2.5.24) of the Linux kernel as well as on 2.4 Linux kernels.
-Support for STATUS codes (newer 32 bit NT error codes) added.  DFS support begun to be added.
-
-Version 0.32
-------------
-Unix extensions (symlink, readlink, hardlink, chmod and some chgrp and chown) implemented
-and tested against Samba 2.2.5
-
-
-Version 0.31
-------------
-1) Fixed lockrange to be correct (it was one byte too short)
-
-2) Fixed GETLK (i.e. the fcntl call to test a range of bytes in a file to see if locked) to correctly 
-show range as locked when there is a conflict with an existing lock.
-
-3) default file perms are now 2767 (indicating support for mandatory locks) instead of 777 for directories
-in most cases.  Eventually will offer optional ability to query server for the correct perms.
-
-3) Fixed eventual trap when mounting twice to different shares on the same server when the first succeeded 
-but the second one was invalid and failed (the second one was incorrectly disconnecting the tcp and smb
-session) 
-
-4) Fixed error logging of valid mount options
-
-5) Removed logging of password field.
-
-6) Moved negotiate, treeDisconnect and uloggoffX (only tConx and SessSetup remain in connect.c) to cifssmb.c
-and cleaned them up and made them more consistent with other cifs functions. 
-
-7) Server support for Unix extensions is now fully detected and FindFirst is implemented both ways 
-(with or without Unix extensions) but FindNext and QueryPathInfo with the Unix extensions are not completed,
-nor is the symlink support using the Unix extensions
-
-8) Started adding the readlink and follow_link code 
-
-Version 0.3 
------------
-Initial drop
-
+See https://wiki.samba.org/index.php/LinuxCIFSKernel for summary
+information (that may be easier to read than parsing the output of
+"git log fs/cifs") about fixes/improvements to CIFS/SMB2/SMB3 support (changes
+to cifs.ko module) by kernel version (and cifs internal module version).
-- 
cgit v1.2.3


From 950132afd59385caf6e2b84e5235d069fa10681d Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 28 Jun 2018 18:46:40 -0500
Subject: cifs: add missing debug entries for kconfig options

/proc/fs/cifs/DebugData displays the features (Kconfig options)
used to build cifs.ko but it was missing some, and needed comma
separator.  These can be useful in debugging certain problems
so we know which optional features were enabled in the user's build.
Also clarify them, by making them more closely match the
corresponding CONFIG_CIFS_* parm.

Old format:
Features: dfs fscache posix spnego xattr acl

New format:
Features: DFS,FSCACHE,SMB_DIRECT,STATS,DEBUG2,ALLOW_INSECURE_LEGACY,CIFS_POSIX,UPCALL(SPNEGO),XATTR,ACL

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.de>
CC: Stable <stable@vger.kernel.org>
---
 fs/cifs/cifs_debug.c | 30 +++++++++++++++++++++++-------
 1 file changed, 23 insertions(+), 7 deletions(-)

diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index bfe999505815..991bfb271908 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -160,25 +160,41 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 	seq_printf(m, "CIFS Version %s\n", CIFS_VERSION);
 	seq_printf(m, "Features:");
 #ifdef CONFIG_CIFS_DFS_UPCALL
-	seq_printf(m, " dfs");
+	seq_printf(m, " DFS");
 #endif
 #ifdef CONFIG_CIFS_FSCACHE
-	seq_printf(m, " fscache");
+	seq_printf(m, ",FSCACHE");
+#endif
+#ifdef CONFIG_CIFS_SMB_DIRECT
+	seq_printf(m, ",SMB_DIRECT");
+#endif
+#ifdef CONFIG_CIFS_STATS2
+	seq_printf(m, ",STATS2");
+#elif defined(CONFIG_CIFS_STATS)
+	seq_printf(m, ",STATS");
+#endif
+#ifdef CONFIG_CIFS_DEBUG2
+	seq_printf(m, ",DEBUG2");
+#elif defined(CONFIG_CIFS_DEBUG)
+	seq_printf(m, ",DEBUG");
+#endif
+#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
+	seq_printf(m, ",ALLOW_INSECURE_LEGACY");
 #endif
 #ifdef CONFIG_CIFS_WEAK_PW_HASH
-	seq_printf(m, " lanman");
+	seq_printf(m, ",WEAK_PW_HASH");
 #endif
 #ifdef CONFIG_CIFS_POSIX
-	seq_printf(m, " posix");
+	seq_printf(m, ",CIFS_POSIX");
 #endif
 #ifdef CONFIG_CIFS_UPCALL
-	seq_printf(m, " spnego");
+	seq_printf(m, ",UPCALL(SPNEGO)");
 #endif
 #ifdef CONFIG_CIFS_XATTR
-	seq_printf(m, " xattr");
+	seq_printf(m, ",XATTR");
 #endif
 #ifdef CONFIG_CIFS_ACL
-	seq_printf(m, " acl");
+	seq_printf(m, ",ACL");
 #endif
 	seq_putc(m, '\n');
 	seq_printf(m, "Active VFS Requests: %d\n", GlobalTotalActiveXid);
-- 
cgit v1.2.3


From 0fdfef9aa7ee68ddd508aef7c98630cfc054f8d6 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 28 Jun 2018 19:30:23 -0500
Subject: smb3: simplify code by removing CONFIG_CIFS_SMB311

We really, really want to be encouraging use of secure dialects,
and SMB3.1.1 offers useful security features, and will soon
be the recommended dialect for many use cases. Simplify the code
by removing the CONFIG_CIFS_SMB311 ifdef so users don't disable
it in the build, and create compatibility and/or security issues
with modern servers - many of which have been supporting this
dialect for multiple years.

Also clarify some of the Kconfig text for cifs.ko about
SMB3.1.1 and current supported features in the module.

Signed-off-by: Steve French <stfrench@microsoft.com>
Acked-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
---
 fs/cifs/Kconfig         | 33 ++++++++++++++-------------------
 fs/cifs/cifs_debug.c    |  3 +--
 fs/cifs/cifsfs.c        |  8 --------
 fs/cifs/cifsglob.h      |  8 --------
 fs/cifs/connect.c       | 11 +----------
 fs/cifs/inode.c         |  2 --
 fs/cifs/smb2misc.c      | 13 +++----------
 fs/cifs/smb2ops.c       |  6 ------
 fs/cifs/smb2pdu.c       | 31 +++----------------------------
 fs/cifs/smb2proto.h     |  2 --
 fs/cifs/smb2transport.c |  4 ----
 fs/cifs/transport.c     |  4 ----
 12 files changed, 22 insertions(+), 103 deletions(-)

diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 832eafbf803f..63d0d852998a 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -16,24 +16,28 @@ config CIFS
 	select CRYPTO_DES
 	help
 	  This is the client VFS module for the SMB3 family of NAS protocols,
-	  as well as for earlier dialects such as SMB2.1, SMB2 and the
+	  (including support for the most recent, most secure dialect SMB3.1.1)
+	  as well as for earlier dialects such as SMB2.1, SMB2 and the older
 	  Common Internet File System (CIFS) protocol.  CIFS was the successor
 	  to the original dialect, the Server Message Block (SMB) protocol, the
 	  native file sharing mechanism for most early PC operating systems.
 
-	  The SMB3 protocol is supported by most modern operating systems and
-	  NAS appliances (e.g. Samba, Windows 8, Windows 2012, MacOS).
+	  The SMB3 protocol is supported by most modern operating systems
+	  and NAS appliances (e.g. Samba, Windows 10, Windows Server 2016,
+	  MacOS) and even in the cloud (e.g. Microsoft Azure).
 	  The older CIFS protocol was included in Windows NT4, 2000 and XP (and
 	  later) as well by Samba (which provides excellent CIFS and SMB3
-	  server support for Linux and many other operating systems). Limited
-	  support for OS/2 and Windows ME and similar very old servers is
-	  provided as well.
+	  server support for Linux and many other operating systems). Use of
+	  dialects older than SMB2.1 is often discouraged on public networks.
+	  This module also provides limited support for OS/2 and Windows ME
+	  and similar very old servers.
 
-	  The cifs module provides an advanced network file system client
+	  This module provides an advanced network file system client
 	  for mounting to SMB3 (and CIFS) compliant servers.  It includes
 	  support for DFS (hierarchical name space), secure per-user
-	  session establishment via Kerberos or NTLM or NTLMv2,
-	  safe distributed caching (oplock), optional packet
+	  session establishment via Kerberos or NTLM or NTLMv2, RDMA
+	  (smbdirect), advanced security features, per-share encryption,
+	  directory leases, safe distributed caching (oplock), optional packet
 	  signing, Unicode and other internationalization improvements.
 
 	  In general, the default dialects, SMB3 and later, enable better
@@ -43,7 +47,7 @@ config CIFS
 	  than SMB3 mounts. SMB2/SMB3 mount options are also
 	  slightly simpler (compared to CIFS) due to protocol improvements.
 
-	  If you need to mount to Samba, Macs or Windows from this machine, say Y.
+	  If you need to mount to Samba, Azure, Macs or Windows from this machine, say Y.
 
 config CIFS_STATS
         bool "CIFS statistics"
@@ -201,15 +205,6 @@ config CIFS_NFSD_EXPORT
 	  help
 	   Allows NFS server to export a CIFS mounted share (nfsd over cifs)
 
-config CIFS_SMB311
-	bool "SMB3.1.1 network file system support"
-	depends on CIFS
-	select CRYPTO_SHA512
-
-	help
-	  This enables support for the newest, and most secure dialect, SMB3.11.
-	  If unsure, say Y
-
 config CIFS_SMB_DIRECT
 	bool "SMB Direct support (Experimental)"
 	depends on CIFS=m && INFINIBAND && INFINIBAND_ADDR_TRANS || CIFS=y && INFINIBAND=y && INFINIBAND_ADDR_TRANS=y
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 991bfb271908..cb516c950438 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -275,10 +275,9 @@ skip_rdma:
 			server->credits,  server->dialect);
 		if (server->sign)
 			seq_printf(m, " signed");
-#ifdef CONFIG_CIFS_SMB311
 		if (server->posix_ext_supported)
 			seq_printf(m, " posix");
-#endif /* 3.1.1 */
+
 		i++;
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 69ec5427769c..c162a416ddbf 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -483,20 +483,12 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",persistenthandles");
 	else if (tcon->use_resilient)
 		seq_puts(s, ",resilienthandles");
-
-#ifdef CONFIG_CIFS_SMB311
 	if (tcon->posix_extensions)
 		seq_puts(s, ",posix");
 	else if (tcon->unix_ext)
 		seq_puts(s, ",unix");
 	else
 		seq_puts(s, ",nounix");
-#else
-	if (tcon->unix_ext)
-		seq_puts(s, ",unix");
-	else
-		seq_puts(s, ",nounix");
-#endif /* SMB311 */
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIX_PATHS)
 		seq_puts(s, ",posixpaths");
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index b57d1e22ecb5..3ec7e3063865 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -191,9 +191,7 @@ enum smb_version {
 	Smb_21,
 	Smb_30,
 	Smb_302,
-#ifdef CONFIG_CIFS_SMB311
 	Smb_311,
-#endif /* SMB311 */
 	Smb_3any,
 	Smb_default,
 	Smb_version_err
@@ -687,12 +685,10 @@ struct TCP_Server_Info {
 #endif
 	unsigned int	max_read;
 	unsigned int	max_write;
-#ifdef CONFIG_CIFS_SMB311
 	__le16	cipher_type;
 	 /* save initital negprot hash */
 	__u8	preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
 	bool	posix_ext_supported;
-#endif /* 3.1.1 */
 	struct delayed_work reconnect; /* reconnect workqueue job */
 	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
 	unsigned long echo_interval;
@@ -886,9 +882,7 @@ struct cifs_ses {
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
-#ifdef CONFIG_CIFS_SMB311
 	__u8 preauth_sha_hash[SMB2_PREAUTH_HASH_SIZE];
-#endif /* 3.1.1 */
 
 	/*
 	 * Network interfaces available on the server this session is
@@ -997,9 +991,7 @@ struct cifs_tcon {
 	bool seal:1;      /* transport encryption for this mounted share */
 	bool unix_ext:1;  /* if false disable Linux extensions to CIFS protocol
 				for this mount even if server would support */
-#ifdef CONFIG_CIFS_SMB311
 	bool posix_extensions; /* if true SMB3.11 posix extensions enabled */
-#endif /* CIFS_311 */
 	bool local_lease:1; /* check leases (only) on local system not remote */
 	bool broken_posix_open; /* e.g. Samba server versions < 3.3.2, 3.2.9 */
 	bool broken_sparse_sup; /* if server or share does not support sparse */
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 842f45859968..67f91a6313a0 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -303,10 +303,8 @@ static const match_table_t cifs_smb_version_tokens = {
 	{ Smb_21, SMB21_VERSION_STRING },
 	{ Smb_30, SMB30_VERSION_STRING },
 	{ Smb_302, SMB302_VERSION_STRING },
-#ifdef CONFIG_CIFS_SMB311
 	{ Smb_311, SMB311_VERSION_STRING },
 	{ Smb_311, ALT_SMB311_VERSION_STRING },
-#endif /* SMB311 */
 	{ Smb_3any, SMB3ANY_VERSION_STRING },
 	{ Smb_default, SMBDEFAULT_VERSION_STRING },
 	{ Smb_version_err, NULL }
@@ -1219,12 +1217,10 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol, bool is_smb3)
 		vol->ops = &smb30_operations; /* currently identical with 3.0 */
 		vol->vals = &smb302_values;
 		break;
-#ifdef CONFIG_CIFS_SMB311
 	case Smb_311:
 		vol->ops = &smb311_operations;
 		vol->vals = &smb311_values;
 		break;
-#endif /* SMB311 */
 	case Smb_3any:
 		vol->ops = &smb30_operations; /* currently identical with 3.0 */
 		vol->vals = &smb3any_values;
@@ -3039,7 +3035,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		}
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	if (volume_info->linux_ext) {
 		if (ses->server->posix_ext_supported) {
 			tcon->posix_extensions = true;
@@ -3051,7 +3046,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 			goto out_fail;
 		}
 	}
-#endif /* 311 */
 
 	/*
 	 * BB Do we need to wrap session_mutex around this TCon call and Unix
@@ -4005,11 +3999,9 @@ try_mount_again:
 		goto remote_path_check;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
 	if (tcon->posix_extensions)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-#endif /* SMB3.11 */
 
 	/* tell server which Unix caps we support */
 	if (cap_unix(tcon->ses)) {
@@ -4472,11 +4464,10 @@ cifs_construct_tcon(struct cifs_sb_info *cifs_sb, kuid_t fsuid)
 		goto out;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	/* if new SMB3.11 POSIX extensions are supported do not remap / and \ */
 	if (tcon->posix_extensions)
 		cifs_sb->mnt_cifs_flags |= CIFS_MOUNT_POSIX_PATHS;
-#endif /* SMB3.11 */
+
 	if (cap_unix(ses))
 		reset_cifs_unix_caps(0, tcon, NULL, vol_info);
 
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index f6abf18ca492..054e880c1dac 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1575,14 +1575,12 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
 
 	server = tcon->ses->server;
 
-#ifdef CONFIG_CIFS_SMB311
 	if ((server->ops->posix_mkdir) && (tcon->posix_extensions)) {
 		rc = server->ops->posix_mkdir(xid, inode, mode, tcon, full_path,
 					      cifs_sb);
 		d_drop(direntry); /* for time being always refresh inode info */
 		goto mkdir_out;
 	}
-#endif /* SMB311 */
 
 	if (cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
 				le64_to_cpu(tcon->fsUnixInfo.Capability))) {
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 3ff7cec2da81..303d4592ebe7 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -93,7 +93,6 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ cpu_to_le16(24)
 };
 
-#ifdef CONFIG_CIFS_SMB311
 static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
 			      __u32 non_ctxlen)
 {
@@ -127,7 +126,6 @@ static __u32 get_neg_ctxt_len(struct smb2_sync_hdr *hdr, __u32 len,
 	/* length of negcontexts including pad from end of sec blob to them */
 	return (len - nc_offset) + size_of_pad_before_neg_ctxts;
 }
-#endif /* CIFS_SMB311 */
 
 int
 smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
@@ -222,10 +220,9 @@ smb2_check_message(char *buf, unsigned int len, struct TCP_Server_Info *srvr)
 
 	clc_len = smb2_calc_size(buf, srvr);
 
-#ifdef CONFIG_CIFS_SMB311
 	if (shdr->Command == SMB2_NEGOTIATE)
 		clc_len += get_neg_ctxt_len(shdr, len, clc_len);
-#endif /* SMB311 */
+
 	if (len != clc_len) {
 		cifs_dbg(FYI, "Calculated size %u length %u mismatch mid %llu\n",
 			 clc_len, len, mid);
@@ -451,15 +448,13 @@ cifs_convert_path_to_utf16(const char *from, struct cifs_sb_info *cifs_sb)
 	/* Windows doesn't allow paths beginning with \ */
 	if (from[0] == '\\')
 		start_of_path = from + 1;
-#ifdef CONFIG_CIFS_SMB311
+
 	/* SMB311 POSIX extensions paths do not include leading slash */
 	else if (cifs_sb_master_tlink(cifs_sb) &&
 		 cifs_sb_master_tcon(cifs_sb)->posix_extensions &&
 		 (from[0] == '/')) {
 		start_of_path = from + 1;
-	}
-#endif /* 311 */
-	else
+	} else
 		start_of_path = from;
 
 	to = cifs_strndup_to_utf16(start_of_path, PATH_MAX, &len,
@@ -759,7 +754,6 @@ smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 /**
  * smb311_update_preauth_hash - update @ses hash with the packet data in @iov
  *
@@ -821,4 +815,3 @@ smb311_update_preauth_hash(struct cifs_ses *ses, struct kvec *iov, int nvec)
 
 	return 0;
 }
-#endif
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index e2a8b9d90ad8..27b69977809d 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1533,7 +1533,6 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 static int
 smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	     struct kstatfs *buf)
@@ -1564,7 +1563,6 @@ smb311_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	return rc;
 }
-#endif /* SMB311 */
 
 static bool
 smb2_compare_fids(struct cifsFileInfo *ob1, struct cifsFileInfo *ob2)
@@ -3303,7 +3301,6 @@ struct smb_version_operations smb30_operations = {
 	.next_header = smb2_next_header,
 };
 
-#ifdef CONFIG_CIFS_SMB311
 struct smb_version_operations smb311_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -3404,7 +3401,6 @@ struct smb_version_operations smb311_operations = {
 #endif /* CIFS_XATTR */
 	.next_header = smb2_next_header,
 };
-#endif /* CIFS_SMB311 */
 
 struct smb_version_values smb20_values = {
 	.version_string = SMB20_VERSION_STRING,
@@ -3532,7 +3528,6 @@ struct smb_version_values smb302_values = {
 	.create_lease_size = sizeof(struct create_lease_v2),
 };
 
-#ifdef CONFIG_CIFS_SMB311
 struct smb_version_values smb311_values = {
 	.version_string = SMB311_VERSION_STRING,
 	.protocol_id = SMB311_PROT_ID,
@@ -3553,4 +3548,3 @@ struct smb_version_values smb311_values = {
 	.signing_required = SMB2_NEGOTIATE_SIGNING_REQUIRED,
 	.create_lease_size = sizeof(struct create_lease_v2),
 };
-#endif /* SMB311 */
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index fa9fc3fab60e..4ea5528fc15c 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -370,7 +370,7 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 	return rc;
 }
 
-#ifdef CONFIG_CIFS_SMB311
+
 /* offset is sizeof smb2_negotiate_req but rounded up to 8 bytes */
 #define OFFSET_OF_NEG_CONTEXT 0x68  /* sizeof(struct smb2_negotiate_req) */
 
@@ -585,13 +585,6 @@ add_posix_context(struct kvec *iov, unsigned int *num_iovec, umode_t mode)
 	return 0;
 }
 
-#else
-static void assemble_neg_contexts(struct smb2_negotiate_req *req,
-				  unsigned int *total_len)
-{
-	return;
-}
-#endif /* SMB311 */
 
 /*
  *
@@ -636,10 +629,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		return rc;
 
 	req->sync_hdr.SessionId = 0;
-#ifdef CONFIG_CIFS_SMB311
+
 	memset(server->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
 	memset(ses->preauth_sha_hash, 0, SMB2_PREAUTH_HASH_SIZE);
-#endif
 
 	if (strcmp(ses->server->vals->version_string,
 		   SMB3ANY_VERSION_STRING) == 0) {
@@ -741,10 +733,8 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		cifs_dbg(FYI, "negotiated smb3.0 dialect\n");
 	else if (rsp->DialectRevision == cpu_to_le16(SMB302_PROT_ID))
 		cifs_dbg(FYI, "negotiated smb3.02 dialect\n");
-#ifdef CONFIG_CIFS_SMB311
 	else if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID))
 		cifs_dbg(FYI, "negotiated smb3.1.1 dialect\n");
-#endif /* SMB311 */
 	else {
 		cifs_dbg(VFS, "Illegal dialect returned by server 0x%x\n",
 			 le16_to_cpu(rsp->DialectRevision));
@@ -753,9 +743,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	}
 	server->dialect = le16_to_cpu(rsp->DialectRevision);
 
-	/* BB: add check that dialect was valid given dialect(s) we asked for */
-
-#ifdef CONFIG_CIFS_SMB311
 	/*
 	 * Keep a copy of the hash after negprot. This hash will be
 	 * the starting hash value for all sessions made from this
@@ -763,7 +750,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	 */
 	memcpy(server->preauth_sha_hash, ses->preauth_sha_hash,
 	       SMB2_PREAUTH_HASH_SIZE);
-#endif
+
 	/* SMB2 only has an extended negflavor */
 	server->negflavor = CIFS_NEGFLAVOR_EXTENDED;
 	/* set it to the maximum buffer size value we can send with 1 credit */
@@ -804,7 +791,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 			rc = -EIO;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	if (rsp->DialectRevision == cpu_to_le16(SMB311_PROT_ID)) {
 		if (rsp->NegotiateContextCount)
 			rc = smb311_decode_neg_context(rsp, server,
@@ -812,7 +798,6 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		else
 			cifs_dbg(VFS, "Missing expected negotiate contexts\n");
 	}
-#endif /* CONFIG_CIFS_SMB311 */
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -1373,13 +1358,11 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	sess_data->nls_cp = (struct nls_table *) nls_cp;
 	sess_data->previous_session = ses->Suid;
 
-#ifdef CONFIG_CIFS_SMB311
 	/*
 	 * Initialize the session hash with the server one.
 	 */
 	memcpy(ses->preauth_sha_hash, ses->server->preauth_sha_hash,
 	       SMB2_PREAUTH_HASH_SIZE);
-#endif
 
 	while (sess_data->func)
 		sess_data->func(sess_data);
@@ -1920,7 +1903,6 @@ alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int smb311_posix_mkdir(const unsigned int xid, struct inode *inode,
 			       umode_t mode, struct cifs_tcon *tcon,
 			       const char *full_path,
@@ -2070,7 +2052,6 @@ err_free_path:
 	kfree(utf16_path);
 	return rc;
 }
-#endif /* SMB311 */
 
 int
 SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
@@ -2210,7 +2191,6 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		dhc_buf = iov[n_iov-1].iov_base;
 	}
 
-#ifdef CONFIG_CIFS_SMB311
 	if (tcon->posix_extensions) {
 		if (n_iov > 2) {
 			struct create_context *ccontext =
@@ -2229,7 +2209,6 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		}
 		pc_buf = iov[n_iov-1].iov_base;
 	}
-#endif /* SMB311 */
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
 	rqst.rq_iov = iov;
@@ -3938,7 +3917,6 @@ copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
 	return;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 static void
 copy_posix_fs_info_to_kstatfs(FILE_SYSTEM_POSIX_INFO *response_data,
 			struct kstatfs *kst)
@@ -3957,7 +3935,6 @@ copy_posix_fs_info_to_kstatfs(FILE_SYSTEM_POSIX_INFO *response_data,
 
 	return;
 }
-#endif /* SMB311 */
 
 static int
 build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
@@ -3995,7 +3972,6 @@ build_qfs_info_req(struct kvec *iov, struct cifs_tcon *tcon, int level,
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int
 SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 	      u64 persistent_fid, u64 volatile_fid, struct kstatfs *fsdata)
@@ -4043,7 +4019,6 @@ posix_qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
 }
-#endif /* SMB311 */
 
 int
 SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 7019459c5748..98d9b30c16a6 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -216,9 +216,7 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
 					enum securityEnum);
-#ifdef CONFIG_CIFS_SMB311
 extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server);
 extern int smb311_update_preauth_hash(struct cifs_ses *ses,
 				      struct kvec *iov, int nvec);
-#endif
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 719d55e63d88..3f778937c0e2 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -70,7 +70,6 @@ err:
 	return rc;
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int
 smb311_crypto_shash_allocate(struct TCP_Server_Info *server)
 {
@@ -98,7 +97,6 @@ err:
 	cifs_free_hash(&p->hmacsha256, &p->sdeschmacsha256);
 	return rc;
 }
-#endif
 
 static struct cifs_ses *
 smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
@@ -395,7 +393,6 @@ generate_smb30signingkey(struct cifs_ses *ses)
 	return generate_smb3signingkey(ses, &triplet);
 }
 
-#ifdef CONFIG_CIFS_SMB311
 int
 generate_smb311signingkey(struct cifs_ses *ses)
 
@@ -423,7 +420,6 @@ generate_smb311signingkey(struct cifs_ses *ses)
 
 	return generate_smb3signingkey(ses, &triplet);
 }
-#endif /* 311 */
 
 int
 smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index a341ec839c83..0f9156af5eb0 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -807,11 +807,9 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 	if (rc < 0)
 		goto out;
 
-#ifdef CONFIG_CIFS_SMB311
 	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
 		smb311_update_preauth_hash(ses, rqst->rq_iov,
 					   rqst->rq_nvec);
-#endif
 
 	if (timeout == CIFS_ASYNC_OP)
 		goto out;
@@ -852,7 +850,6 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 	else
 		*resp_buf_type = CIFS_SMALL_BUFFER;
 
-#ifdef CONFIG_CIFS_SMB311
 	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
 		struct kvec iov = {
 			.iov_base = resp_iov->iov_base,
@@ -860,7 +857,6 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 		};
 		smb311_update_preauth_hash(ses, &iov, 1);
 	}
-#endif
 
 	credits = ses->server->ops->get_credits(midQ);
 
-- 
cgit v1.2.3


From c3ed44026cd07fda5976ecb79225759901a160b4 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 28 Jun 2018 22:53:39 -0500
Subject: smb3: remove noisy warning message on mount

Some servers, like Samba, don't support the fsctl for
query_network_interface_info so don't log a noisy warning
message on mount for this by default unless the error is more serious.
Lower the error to an FYI level so it does not get logged by
default.

Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/smb2ops.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 27b69977809d..4ce72055ca0a 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -444,7 +444,11 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
 			NULL /* no data input */, 0 /* no data input */,
 			(char **)&out_buf, &ret_data_len);
-	if (rc != 0) {
+	if (rc == -EOPNOTSUPP) {
+		cifs_dbg(FYI,
+			 "server does not support query network interfaces\n");
+		goto out;
+	} else if (rc != 0) {
 		cifs_dbg(VFS, "error %d on ioctl to get interface list\n", rc);
 		goto out;
 	}
-- 
cgit v1.2.3


From 8a69e96e610b3ec8a55f6fd4e44363452838caa7 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 29 Jun 2018 16:06:15 -0500
Subject: smb3: snapshot mounts are read-only and make sure info is displayable
 about the mount

snapshot mounts were not marked as read-only and did not display the snapshot
time (in /proc/mounts) specified on mount

With this patch - note that can not write to the snapshot mount (see "ro" in
/proc/mounts line) and also the missing snapshot timewarp token time is
dumped.  Sample line from /proc/mounts with the patch:

//127.0.0.1/scratch /mnt2 smb3 ro,relatime,vers=default,cache=strict,username=testuser,domain=,uid=0,noforceuid,gid=0,noforcegid,addr=127.0.0.1,file_mode=0755,dir_mode=0755,soft,nounix,serverino,mapposix,noperm,rsize=1048576,wsize=1048576,echo_interval=60,snapshot=1234567,actimeo=1 0 0

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.de>
---
 fs/cifs/cifsfs.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index c162a416ddbf..de16078e456b 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -139,6 +139,9 @@ cifs_read_super(struct super_block *sb)
 	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_POSIXACL)
 		sb->s_flags |= SB_POSIXACL;
 
+	if (tcon->snapshot_time)
+		sb->s_flags |= SB_RDONLY;
+
 	if (tcon->ses->capabilities & tcon->ses->server->vals->cap_large_files)
 		sb->s_maxbytes = MAX_LFS_FILESIZE;
 	else
@@ -540,6 +543,8 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	seq_printf(s, ",wsize=%u", cifs_sb->wsize);
 	seq_printf(s, ",echo_interval=%lu",
 			tcon->ses->server->echo_interval / HZ);
+	if (tcon->snapshot_time)
+		seq_printf(s, ",snapshot=%llu", tcon->snapshot_time);
 	/* convert actimeo and display it in seconds */
 	seq_printf(s, ",actimeo=%lu", cifs_sb->actimeo / HZ);
 
-- 
cgit v1.2.3


From 289131e1f1e6ad8c661ec05e176b8f0915672059 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Mon, 23 Jul 2018 09:15:18 -0500
Subject: SMB3: Number of requests sent should be displayed for SMB3 not just
 CIFS

For SMB2/SMB3 the number of requests sent was not displayed
in /proc/fs/cifs/Stats unless CONFIG_CIFS_STATS2 was
enabled (only number of failed requests displayed). As
with earlier dialects, we should be displaying these
counters if CONFIG_CIFS_STATS is enabled. They
are important for debugging.

e.g. when you cat /proc/fs/cifs/Stats (before the patch)
Resources in use
CIFS Session: 1
Share (unique mount targets): 2
SMB Request/Response Buffer: 1 Pool size: 5
SMB Small Req/Resp Buffer: 1 Pool size: 30
Operations (MIDs): 0

0 session 0 share reconnects
Total vfs operations: 690 maximum at one time: 2

1) \\localhost\test
SMBs: 975
Negotiates: 0 sent 0 failed
SessionSetups: 0 sent 0 failed
Logoffs: 0 sent 0 failed
TreeConnects: 0 sent 0 failed
TreeDisconnects: 0 sent 0 failed
Creates: 0 sent 2 failed
Closes: 0 sent 0 failed
Flushes: 0 sent 0 failed
Reads: 0 sent 0 failed
Writes: 0 sent 0 failed
Locks: 0 sent 0 failed
IOCTLs: 0 sent 1 failed
Cancels: 0 sent 0 failed
Echos: 0 sent 0 failed
QueryDirectories: 0 sent 63 failed

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/smb2pdu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 4ea5528fc15c..0b4d7ebb812d 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -360,7 +360,7 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		       total_len);
 
 	if (tcon != NULL) {
-#ifdef CONFIG_CIFS_STATS2
+#ifdef CONFIG_CIFS_STATS
 		uint16_t com_code = le16_to_cpu(smb2_command);
 		cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_sent[com_code]);
 #endif
-- 
cgit v1.2.3


From 1995d28f84b3d2a8f586fcd271207f798b80ccd8 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 27 Jul 2018 15:14:04 -0500
Subject: smb3: remove per-session operations from per-tree connection stats

Remove counters from the per-tree connection /proc/fs/cifs/Stats
output that will always be zero (since they are not per-tcon ops)
ie SMB3 Negotiate, SessionSetup, Logoff, Echo, Cancel.

Also clarify "sent" to be "total" per-Pavel's suggestion
(since this "total" includes total for all operations that we try to
send whether or not succesffully sent). Sample output below:

Resources in use
CIFS Session: 1
Share (unique mount targets): 2
SMB Request/Response Buffer: 1 Pool size: 5
SMB Small Req/Resp Buffer: 1 Pool size: 30
Operations (MIDs): 0

1 session 2 share reconnects
Total vfs operations: 23 maximum at one time: 2

1) \\localhost\test
SMBs: 45
TreeConnects: 2 total 0 failed
TreeDisconnects: 0 total 0 failed
Creates: 13 total 2 failed
Closes: 9 total 0 failed
Flushes: 0 total 0 failed
Reads: 0 total 0 failed
Writes: 1 total 0 failed
Locks: 0 total 0 failed
IOCTLs: 3 total 1 failed
QueryDirectories: 4 total 2 failed
ChangeNotifies: 0 total 0 failed
QueryInfos: 10 total 0 failed
SetInfos: 3 total 0 failed
OplockBreaks: 0 sent 0 failed

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/smb2ops.c | 46 ++++++++++++++++++----------------------------
 1 file changed, 18 insertions(+), 28 deletions(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 4ce72055ca0a..dad6dc763200 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -927,58 +927,48 @@ smb2_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 #ifdef CONFIG_CIFS_STATS
 	atomic_t *sent = tcon->stats.smb2_stats.smb2_com_sent;
 	atomic_t *failed = tcon->stats.smb2_stats.smb2_com_failed;
-	seq_printf(m, "\nNegotiates: %d sent %d failed",
-		   atomic_read(&sent[SMB2_NEGOTIATE_HE]),
-		   atomic_read(&failed[SMB2_NEGOTIATE_HE]));
-	seq_printf(m, "\nSessionSetups: %d sent %d failed",
-		   atomic_read(&sent[SMB2_SESSION_SETUP_HE]),
-		   atomic_read(&failed[SMB2_SESSION_SETUP_HE]));
-	seq_printf(m, "\nLogoffs: %d sent %d failed",
-		   atomic_read(&sent[SMB2_LOGOFF_HE]),
-		   atomic_read(&failed[SMB2_LOGOFF_HE]));
-	seq_printf(m, "\nTreeConnects: %d sent %d failed",
+
+	/*
+	 *  Can't display SMB2_NEGOTIATE, SESSION_SETUP, LOGOFF, CANCEL and ECHO
+	 *  totals (requests sent) since those SMBs are per-session not per tcon
+	 */
+	seq_printf(m, "\nTreeConnects: %d total %d failed",
 		   atomic_read(&sent[SMB2_TREE_CONNECT_HE]),
 		   atomic_read(&failed[SMB2_TREE_CONNECT_HE]));
-	seq_printf(m, "\nTreeDisconnects: %d sent %d failed",
+	seq_printf(m, "\nTreeDisconnects: %d total %d failed",
 		   atomic_read(&sent[SMB2_TREE_DISCONNECT_HE]),
 		   atomic_read(&failed[SMB2_TREE_DISCONNECT_HE]));
-	seq_printf(m, "\nCreates: %d sent %d failed",
+	seq_printf(m, "\nCreates: %d total %d failed",
 		   atomic_read(&sent[SMB2_CREATE_HE]),
 		   atomic_read(&failed[SMB2_CREATE_HE]));
-	seq_printf(m, "\nCloses: %d sent %d failed",
+	seq_printf(m, "\nCloses: %d total %d failed",
 		   atomic_read(&sent[SMB2_CLOSE_HE]),
 		   atomic_read(&failed[SMB2_CLOSE_HE]));
-	seq_printf(m, "\nFlushes: %d sent %d failed",
+	seq_printf(m, "\nFlushes: %d total %d failed",
 		   atomic_read(&sent[SMB2_FLUSH_HE]),
 		   atomic_read(&failed[SMB2_FLUSH_HE]));
-	seq_printf(m, "\nReads: %d sent %d failed",
+	seq_printf(m, "\nReads: %d total %d failed",
 		   atomic_read(&sent[SMB2_READ_HE]),
 		   atomic_read(&failed[SMB2_READ_HE]));
-	seq_printf(m, "\nWrites: %d sent %d failed",
+	seq_printf(m, "\nWrites: %d total %d failed",
 		   atomic_read(&sent[SMB2_WRITE_HE]),
 		   atomic_read(&failed[SMB2_WRITE_HE]));
-	seq_printf(m, "\nLocks: %d sent %d failed",
+	seq_printf(m, "\nLocks: %d total %d failed",
 		   atomic_read(&sent[SMB2_LOCK_HE]),
 		   atomic_read(&failed[SMB2_LOCK_HE]));
-	seq_printf(m, "\nIOCTLs: %d sent %d failed",
+	seq_printf(m, "\nIOCTLs: %d total %d failed",
 		   atomic_read(&sent[SMB2_IOCTL_HE]),
 		   atomic_read(&failed[SMB2_IOCTL_HE]));
-	seq_printf(m, "\nCancels: %d sent %d failed",
-		   atomic_read(&sent[SMB2_CANCEL_HE]),
-		   atomic_read(&failed[SMB2_CANCEL_HE]));
-	seq_printf(m, "\nEchos: %d sent %d failed",
-		   atomic_read(&sent[SMB2_ECHO_HE]),
-		   atomic_read(&failed[SMB2_ECHO_HE]));
-	seq_printf(m, "\nQueryDirectories: %d sent %d failed",
+	seq_printf(m, "\nQueryDirectories: %d total %d failed",
 		   atomic_read(&sent[SMB2_QUERY_DIRECTORY_HE]),
 		   atomic_read(&failed[SMB2_QUERY_DIRECTORY_HE]));
-	seq_printf(m, "\nChangeNotifies: %d sent %d failed",
+	seq_printf(m, "\nChangeNotifies: %d total %d failed",
 		   atomic_read(&sent[SMB2_CHANGE_NOTIFY_HE]),
 		   atomic_read(&failed[SMB2_CHANGE_NOTIFY_HE]));
-	seq_printf(m, "\nQueryInfos: %d sent %d failed",
+	seq_printf(m, "\nQueryInfos: %d total %d failed",
 		   atomic_read(&sent[SMB2_QUERY_INFO_HE]),
 		   atomic_read(&failed[SMB2_QUERY_INFO_HE]));
-	seq_printf(m, "\nSetInfos: %d sent %d failed",
+	seq_printf(m, "\nSetInfos: %d total %d failed",
 		   atomic_read(&sent[SMB2_SET_INFO_HE]),
 		   atomic_read(&failed[SMB2_SET_INFO_HE]));
 	seq_printf(m, "\nOplockBreaks: %d sent %d failed",
-- 
cgit v1.2.3


From 22783155f4bf956c346a81624ec9258930a6fe06 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 27 Jul 2018 22:01:49 -0500
Subject: smb3: don't request leases in symlink creation and query

Fixes problem pointed out by Pavel in discussions about commit
729c0c9dd55204f0c9a823ac8a7bfa83d36c7e78

Signed-off-by: Pavel Shilovsky <pshilov@microsoft.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
CC: Stable <stable@vger.kernel.org> # 3.18.x+
---
 fs/cifs/link.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index de41f96aba49..2148b0f60e5e 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -396,7 +396,7 @@ smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_io_parms io_parms;
 	int buf_type = CIFS_NO_BUFFER;
 	__le16 *utf16_path;
-	__u8 oplock = SMB2_OPLOCK_LEVEL_II;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct smb2_file_all_info *pfile_info = NULL;
 
 	oparms.tcon = tcon;
@@ -459,7 +459,7 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	struct cifs_io_parms io_parms;
 	int create_options = CREATE_NOT_DIR;
 	__le16 *utf16_path;
-	__u8 oplock = SMB2_OPLOCK_LEVEL_EXCLUSIVE;
+	__u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct kvec iov[2];
 
 	if (backup_cred(cifs_sb))
-- 
cgit v1.2.3


From 06188fcf9c068a2a8e82ad1e2510a008373150e2 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sun, 29 Jul 2018 17:13:39 -0500
Subject: cifs: remove unused stats

These timers were a good idea but weren't used in current code,
and the idea was cifs specific.  Future patch will add similar timers
for SMB2/SMB3, but no sense using memory for cifs timers that
aren't used in current code.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
---
 fs/cifs/cifsglob.h | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 3ec7e3063865..8826bc0a9b15 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -961,20 +961,6 @@ struct cifs_tcon {
 			atomic_t smb2_com_failed[NUMBER_OF_SMB2_COMMANDS];
 		} smb2_stats;
 	} stats;
-#ifdef CONFIG_CIFS_STATS2
-	unsigned long long time_writes;
-	unsigned long long time_reads;
-	unsigned long long time_opens;
-	unsigned long long time_deletes;
-	unsigned long long time_closes;
-	unsigned long long time_mkdirs;
-	unsigned long long time_rmdirs;
-	unsigned long long time_renames;
-	unsigned long long time_t2renames;
-	unsigned long long time_ffirst;
-	unsigned long long time_fnext;
-	unsigned long long time_fclose;
-#endif /* CONFIG_CIFS_STATS2 */
 	__u64    bytes_read;
 	__u64    bytes_written;
 	spinlock_t stat_lock;  /* protects the two fields above */
-- 
cgit v1.2.3


From e68a932b0b8e38eaa2111fc3aab31ff66988f1c4 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Mon, 30 Jul 2018 14:23:58 -0500
Subject: smb3: add tracepoint for session expired or deleted

In debugging reconnection problems, want to be able to more easily
trace cases in which the server has marked the SMB3 session
expired or deleted (to distinguish from timeout cases).

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
---
 fs/cifs/smb2ops.c | 4 ++++
 fs/cifs/trace.h   | 1 +
 2 files changed, 5 insertions(+)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index dad6dc763200..314556c083f3 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1483,7 +1483,11 @@ smb2_is_session_expired(char *buf)
 	    shdr->Status != STATUS_USER_SESSION_DELETED)
 		return false;
 
+	trace_smb3_ses_expired(shdr->TreeId, shdr->SessionId,
+			       le16_to_cpu(shdr->Command),
+			       le64_to_cpu(shdr->MessageId));
 	cifs_dbg(FYI, "Session expired or deleted\n");
+
 	return true;
 }
 
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index 67e413f6ee4d..0fdf2f5c07ba 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -281,6 +281,7 @@ DEFINE_EVENT(smb3_cmd_done_class, smb3_##name,    \
 	TP_ARGS(tid, sesid, cmd, mid))
 
 DEFINE_SMB3_CMD_DONE_EVENT(cmd_done);
+DEFINE_SMB3_CMD_DONE_EVENT(ses_expired);
 
 DECLARE_EVENT_CLASS(smb3_exit_err_class,
 	TP_PROTO(unsigned int xid,
-- 
cgit v1.2.3


From 4d9768237c19d7bcea8b284ec98c04a5846977be Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 31 Jul 2018 03:41:44 -0700
Subject: i40e: remove unnecessary i variable causing -Wshadow warning

Commit c61c8fe1d592 ("i40e: Implement an ethtool private flag to stop
LLDP in FW") added an extra for-loop which added a shadowing 'i'
variable as the index.

However, the local variable i already exists, and we already use it as
a loop index. Additionally, at this point, there is no further use of
the variable, so it's safe to simply overwrite the variable contents.

This fixes a -Wshadow warning which has started being enabled on some
distributions

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Patryk Malek <patryk.malek@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 9c380c0b0202..12d279a6eae8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -4642,7 +4642,6 @@ flags_complete:
 	if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) {
 		if (pf->flags & I40E_FLAG_DISABLE_FW_LLDP) {
 			struct i40e_dcbx_config *dcbcfg;
-			int i;
 
 			i40e_aq_stop_lldp(&pf->hw, true, NULL);
 			i40e_aq_set_dcb_parameters(&pf->hw, true, NULL);
-- 
cgit v1.2.3


From 6e2feaa344e651bc1a1ec224018827e36192c039 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 31 Jul 2018 03:41:45 -0700
Subject: i40e: fix warning about shadowed ring parameter

In commit 147e81ec7568 ("i40e: Test memory before ethtool alloc succeeds")
code was added to handle ring allocation on systems with low memory.

It shadowed the ring parameter pointer by introducing a local ring
pointer inside the for loop. Most of the code in the loop already just
accessed the ring via &rx_rings[i]. Since most of the code already does
this, just remove the local variable.

If someone considers it worth keeping a local around, they should use it
for the whole section instead of just a couple of accesses.

This fixes a warning when -Wshadow is enabled

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 12d279a6eae8..cd23d1e169c2 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1589,7 +1589,6 @@ static int i40e_set_ringparam(struct net_device *netdev,
 		}
 
 		for (i = 0; i < vsi->num_queue_pairs; i++) {
-			struct i40e_ring *ring;
 			u16 unused;
 
 			/* clone ring and setup updated count */
@@ -1613,9 +1612,8 @@ static int i40e_set_ringparam(struct net_device *netdev,
 			/* now allocate the Rx buffers to make sure the OS
 			 * has enough memory, any failure here means abort
 			 */
-			ring = &rx_rings[i];
-			unused = I40E_DESC_UNUSED(ring);
-			err = i40e_alloc_rx_buffers(ring, unused);
+			unused = I40E_DESC_UNUSED(&rx_rings[i]);
+			err = i40e_alloc_rx_buffers(&rx_rings[i], unused);
 rx_unwind:
 			if (err) {
 				do {
-- 
cgit v1.2.3


From bf1fdeb7899a86adfbe0b521bee5cf78bb870a14 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Mon, 30 Jul 2018 19:23:09 -0500
Subject: smb3: add reconnect tracepoints

Add tracepoints for reconnecting an smb3 session

Example output (from trace-cmd) with the patch
(showing the session marked for reconnect, the stat failing, and then
the subsequent SMB3 commands after the server comes back up).
The "smb3_reconnect" event is the new one.

           cifsd-25993 [000] .... 29635.368265: smb3_reconnect: server=localhost current_mid=0x1e
            stat-26200 [001] .... 29638.516403: smb3_enter: 	cifs_revalidate_dentry_attr: xid=22
            stat-26200 [001] .... 29648.723296: smb3_exit_err: 	cifs_revalidate_dentry_attr: xid=22 rc=-112
     kworker/0:1-22830 [000] .... 29653.850947: smb3_cmd_done: 	sid=0x0 tid=0x0 cmd=0 mid=0
     kworker/0:1-22830 [000] .... 29653.851191: smb3_cmd_err: 	sid=0x8ae4683c tid=0x0 cmd=1 mid=1 status=0xc0000016 rc=-5
     kworker/0:1-22830 [000] .... 29653.855254: smb3_cmd_done: 	sid=0x8ae4683c tid=0x0 cmd=1 mid=2
     kworker/0:1-22830 [000] .... 29653.855482: smb3_cmd_done: 	sid=0x8ae4683c tid=0x8084f30d cmd=3 mid=3

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/connect.c   |  1 +
 fs/cifs/trace.h     | 26 ++++++++++++++++++++++++++
 fs/cifs/transport.c |  2 ++
 3 files changed, 29 insertions(+)

diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 67f91a6313a0..d9bd10d295a9 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -348,6 +348,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 	server->max_read = 0;
 
 	cifs_dbg(FYI, "Reconnecting tcp session\n");
+	trace_smb3_reconnect(server->CurrentMid, server->hostname);
 
 	/* before reconnecting the tcp session, mark the smb session (uid)
 		and the tid bad so they are not used until reconnected */
diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index 0fdf2f5c07ba..6b50b57e2416 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -423,6 +423,32 @@ DEFINE_EVENT(smb3_open_done_class, smb3_##name,  \
 DEFINE_SMB3_OPEN_DONE_EVENT(open_done);
 DEFINE_SMB3_OPEN_DONE_EVENT(posix_mkdir_done);
 
+DECLARE_EVENT_CLASS(smb3_reconnect_class,
+	TP_PROTO(__u64	currmid,
+		char *hostname),
+	TP_ARGS(currmid, hostname),
+	TP_STRUCT__entry(
+		__field(__u64, currmid)
+		__field(char *, hostname)
+	),
+	TP_fast_assign(
+		__entry->currmid = currmid;
+		__entry->hostname = hostname;
+	),
+	TP_printk("server=%s current_mid=0x%llx",
+		__entry->hostname,
+		__entry->currmid)
+)
+
+#define DEFINE_SMB3_RECONNECT_EVENT(name)        \
+DEFINE_EVENT(smb3_reconnect_class, smb3_##name,  \
+	TP_PROTO(__u64	currmid,		\
+		char *hostname),		\
+	TP_ARGS(currmid, hostname))
+
+DEFINE_SMB3_RECONNECT_EVENT(reconnect);
+DEFINE_SMB3_RECONNECT_EVENT(partial_send_reconnect);
+
 #endif /* _CIFS_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 0f9156af5eb0..357d25351ffa 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -361,6 +361,8 @@ uncork:
 		 * socket so the server throws away the partial SMB
 		 */
 		server->tcpStatus = CifsNeedReconnect;
+		trace_smb3_partial_send_reconnect(server->CurrentMid,
+						  server->hostname);
 	}
 smbd_done:
 	if (rc < 0 && rc != -EINTR)
-- 
cgit v1.2.3


From 9da6ec7775d2cd76df53fbf4f1f35f6d490204f5 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Tue, 31 Jul 2018 08:48:22 +1000
Subject: cifs: use a refcount to protect open/closing the cached file handle

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Cc: <stable@vger.kernel.org>
---
 fs/cifs/cifsglob.h  |  1 +
 fs/cifs/smb2inode.c |  4 +++-
 fs/cifs/smb2ops.c   | 31 ++++++++++++++++++++++++++-----
 fs/cifs/smb2proto.h |  1 +
 4 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 8826bc0a9b15..0e6fd5fa4eb6 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -907,6 +907,7 @@ cap_unix(struct cifs_ses *ses)
 
 struct cached_fid {
 	bool is_valid:1;	/* Do we have a useable root fid */
+	struct kref refcount;
 	struct cifs_fid *fid;
 	struct mutex fid_mutex;
 	struct cifs_tcon *tcon;
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index d01ad706d7fc..f22cbc0d1869 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -120,7 +120,9 @@ smb2_open_op_close(const unsigned int xid, struct cifs_tcon *tcon,
 		break;
 	}
 
-	if (use_cached_root_handle == false)
+	if (use_cached_root_handle)
+		close_shroot(&tcon->crfid);
+	else
 		rc = SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
 	if (tmprc)
 		rc = tmprc;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 314556c083f3..8929426ddaa6 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -470,21 +470,36 @@ out:
 	return rc;
 }
 
-void
-smb2_cached_lease_break(struct work_struct *work)
+static void
+smb2_close_cached_fid(struct kref *ref)
 {
-	struct cached_fid *cfid = container_of(work,
-				struct cached_fid, lease_break);
-	mutex_lock(&cfid->fid_mutex);
+	struct cached_fid *cfid = container_of(ref, struct cached_fid,
+					       refcount);
+
 	if (cfid->is_valid) {
 		cifs_dbg(FYI, "clear cached root file handle\n");
 		SMB2_close(0, cfid->tcon, cfid->fid->persistent_fid,
 			   cfid->fid->volatile_fid);
 		cfid->is_valid = false;
 	}
+}
+
+void close_shroot(struct cached_fid *cfid)
+{
+	mutex_lock(&cfid->fid_mutex);
+	kref_put(&cfid->refcount, smb2_close_cached_fid);
 	mutex_unlock(&cfid->fid_mutex);
 }
 
+void
+smb2_cached_lease_break(struct work_struct *work)
+{
+	struct cached_fid *cfid = container_of(work,
+				struct cached_fid, lease_break);
+
+	close_shroot(cfid);
+}
+
 /*
  * Open the directory at the root of a share
  */
@@ -499,6 +514,7 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 	if (tcon->crfid.is_valid) {
 		cifs_dbg(FYI, "found a cached root file handle\n");
 		memcpy(pfid, tcon->crfid.fid, sizeof(struct cifs_fid));
+		kref_get(&tcon->crfid.refcount);
 		mutex_unlock(&tcon->crfid.fid_mutex);
 		return 0;
 	}
@@ -515,6 +531,8 @@ int open_shroot(unsigned int xid, struct cifs_tcon *tcon, struct cifs_fid *pfid)
 		memcpy(tcon->crfid.fid, pfid, sizeof(struct cifs_fid));
 		tcon->crfid.tcon = tcon;
 		tcon->crfid.is_valid = true;
+		kref_init(&tcon->crfid.refcount);
+		kref_get(&tcon->crfid.refcount);
 	}
 	mutex_unlock(&tcon->crfid.fid_mutex);
 	return rc;
@@ -558,6 +576,9 @@ smb3_qfs_tcon(const unsigned int xid, struct cifs_tcon *tcon)
 			FS_SECTOR_SIZE_INFORMATION); /* SMB3 specific */
 	if (no_cached_open)
 		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	else
+		close_shroot(&tcon->crfid);
+
 	return;
 }
 
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 98d9b30c16a6..19aa483395c7 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -68,6 +68,7 @@ extern int smb3_handle_read_data(struct TCP_Server_Info *server,
 
 extern int open_shroot(unsigned int xid, struct cifs_tcon *tcon,
 			struct cifs_fid *pfid);
+extern void close_shroot(struct cached_fid *cfid);
 extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
 				   struct smb2_file_all_info *src);
 extern int smb2_query_path_info(const unsigned int xid, struct cifs_tcon *tcon,
-- 
cgit v1.2.3


From fcabb89299d79010eb923afdd26de04afcc0527f Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 31 Jul 2018 01:21:37 -0500
Subject: cifs: simple stats should always be enabled

CONFIG_CIFS_STATS should always be enabled as Pavel recently
noted.  Simple statistics are not a significant performance hit,
and removing the ifdef simplifies the code slightly.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/Kconfig      |  9 +--------
 fs/cifs/cifs_debug.c |  6 ------
 fs/cifs/cifsglob.h   | 10 ----------
 fs/cifs/misc.c       |  2 --
 fs/cifs/smb1ops.c    |  4 ----
 fs/cifs/smb2ops.c    |  4 ----
 fs/cifs/smb2pdu.c    |  2 --
 7 files changed, 1 insertion(+), 36 deletions(-)

diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index 63d0d852998a..35c83fe7dba0 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -49,16 +49,9 @@ config CIFS
 
 	  If you need to mount to Samba, Azure, Macs or Windows from this machine, say Y.
 
-config CIFS_STATS
-        bool "CIFS statistics"
-        depends on CIFS
-        help
-          Enabling this option will cause statistics for each server share
-	  mounted by the cifs client to be displayed in /proc/fs/cifs/Stats
-
 config CIFS_STATS2
 	bool "Extended statistics"
-	depends on CIFS_STATS
+	depends on CIFS
 	help
 	  Enabling this option will allow more detailed statistics on SMB
 	  request timing to be displayed in /proc/fs/cifs/DebugData and also
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index cb516c950438..3270d9b74603 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -365,7 +365,6 @@ skip_rdma:
 	return 0;
 }
 
-#ifdef CONFIG_CIFS_STATS
 static ssize_t cifs_stats_proc_write(struct file *file,
 		const char __user *buffer, size_t count, loff_t *ppos)
 {
@@ -481,7 +480,6 @@ static const struct file_operations cifs_stats_proc_fops = {
 	.release	= single_release,
 	.write		= cifs_stats_proc_write,
 };
-#endif /* STATS */
 
 #ifdef CONFIG_CIFS_SMB_DIRECT
 #define PROC_FILE_DEFINE(name) \
@@ -539,9 +537,7 @@ cifs_proc_init(void)
 	proc_create_single("DebugData", 0, proc_fs_cifs,
 			cifs_debug_data_proc_show);
 
-#ifdef CONFIG_CIFS_STATS
 	proc_create("Stats", 0644, proc_fs_cifs, &cifs_stats_proc_fops);
-#endif /* STATS */
 	proc_create("cifsFYI", 0644, proc_fs_cifs, &cifsFYI_proc_fops);
 	proc_create("traceSMB", 0644, proc_fs_cifs, &traceSMB_proc_fops);
 	proc_create("LinuxExtensionsEnabled", 0644, proc_fs_cifs,
@@ -579,9 +575,7 @@ cifs_proc_clean(void)
 	remove_proc_entry("DebugData", proc_fs_cifs);
 	remove_proc_entry("cifsFYI", proc_fs_cifs);
 	remove_proc_entry("traceSMB", proc_fs_cifs);
-#ifdef CONFIG_CIFS_STATS
 	remove_proc_entry("Stats", proc_fs_cifs);
-#endif
 	remove_proc_entry("SecurityFlags", proc_fs_cifs);
 	remove_proc_entry("LinuxExtensionsEnabled", proc_fs_cifs);
 	remove_proc_entry("LookupCacheEnabled", proc_fs_cifs);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 0e6fd5fa4eb6..4a3a737134ea 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -931,7 +931,6 @@ struct cifs_tcon {
 	__u32 tid;		/* The 4 byte tree id */
 	__u16 Flags;		/* optional support bits */
 	enum statusEnum tidStatus;
-#ifdef CONFIG_CIFS_STATS
 	atomic_t num_smbs_sent;
 	union {
 		struct {
@@ -965,7 +964,6 @@ struct cifs_tcon {
 	__u64    bytes_read;
 	__u64    bytes_written;
 	spinlock_t stat_lock;  /* protects the two fields above */
-#endif /* CONFIG_CIFS_STATS */
 	FILE_SYSTEM_DEVICE_INFO fsDevInfo;
 	FILE_SYSTEM_ATTRIBUTE_INFO fsAttrInfo; /* ok if fs name truncated */
 	FILE_SYSTEM_UNIX_INFO fsUnixInfo;
@@ -1331,7 +1329,6 @@ convert_delimiter(char *path, char delim)
 		*pos = delim;
 }
 
-#ifdef CONFIG_CIFS_STATS
 #define cifs_stats_inc atomic_inc
 
 static inline void cifs_stats_bytes_written(struct cifs_tcon *tcon,
@@ -1351,13 +1348,6 @@ static inline void cifs_stats_bytes_read(struct cifs_tcon *tcon,
 	tcon->bytes_read += bytes;
 	spin_unlock(&tcon->stat_lock);
 }
-#else
-
-#define  cifs_stats_inc(field) do {} while (0)
-#define  cifs_stats_bytes_written(tcon, bytes) do {} while (0)
-#define  cifs_stats_bytes_read(tcon, bytes) do {} while (0)
-
-#endif
 
 
 /*
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index 53e8362cbc4a..dacb2c05674c 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -122,9 +122,7 @@ tconInfoAlloc(void)
 		mutex_init(&ret_buf->crfid.fid_mutex);
 		ret_buf->crfid.fid = kzalloc(sizeof(struct cifs_fid),
 					     GFP_KERNEL);
-#ifdef CONFIG_CIFS_STATS
 		spin_lock_init(&ret_buf->stat_lock);
-#endif
 	}
 	return ret_buf;
 }
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index 646dcd149de1..378151e09e91 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -624,7 +624,6 @@ cifs_query_file_info(const unsigned int xid, struct cifs_tcon *tcon,
 static void
 cifs_clear_stats(struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	atomic_set(&tcon->stats.cifs_stats.num_writes, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_reads, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_flushes, 0);
@@ -646,13 +645,11 @@ cifs_clear_stats(struct cifs_tcon *tcon)
 	atomic_set(&tcon->stats.cifs_stats.num_locks, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_acl_get, 0);
 	atomic_set(&tcon->stats.cifs_stats.num_acl_set, 0);
-#endif
 }
 
 static void
 cifs_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	seq_printf(m, " Oplocks breaks: %d",
 		   atomic_read(&tcon->stats.cifs_stats.num_oplock_brks));
 	seq_printf(m, "\nReads:  %d Bytes: %llu",
@@ -684,7 +681,6 @@ cifs_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 		   atomic_read(&tcon->stats.cifs_stats.num_ffirst),
 		   atomic_read(&tcon->stats.cifs_stats.num_fnext),
 		   atomic_read(&tcon->stats.cifs_stats.num_fclose));
-#endif
 }
 
 static void
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 8929426ddaa6..831249001384 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -900,13 +900,11 @@ smb2_can_echo(struct TCP_Server_Info *server)
 static void
 smb2_clear_stats(struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	int i;
 	for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++) {
 		atomic_set(&tcon->stats.smb2_stats.smb2_com_sent[i], 0);
 		atomic_set(&tcon->stats.smb2_stats.smb2_com_failed[i], 0);
 	}
-#endif
 }
 
 static void
@@ -945,7 +943,6 @@ smb2_dump_share_caps(struct seq_file *m, struct cifs_tcon *tcon)
 static void
 smb2_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 {
-#ifdef CONFIG_CIFS_STATS
 	atomic_t *sent = tcon->stats.smb2_stats.smb2_com_sent;
 	atomic_t *failed = tcon->stats.smb2_stats.smb2_com_failed;
 
@@ -995,7 +992,6 @@ smb2_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 	seq_printf(m, "\nOplockBreaks: %d sent %d failed",
 		   atomic_read(&sent[SMB2_OPLOCK_BREAK_HE]),
 		   atomic_read(&failed[SMB2_OPLOCK_BREAK_HE]));
-#endif
 }
 
 static void
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 0b4d7ebb812d..7c0b30321d9a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -360,10 +360,8 @@ smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		       total_len);
 
 	if (tcon != NULL) {
-#ifdef CONFIG_CIFS_STATS
 		uint16_t com_code = le16_to_cpu(smb2_command);
 		cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_sent[com_code]);
-#endif
 		cifs_stats_inc(&tcon->num_smbs_sent);
 	}
 
-- 
cgit v1.2.3


From 52ce1ac4298309d76859307967c58835c0b2ce3e Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Tue, 31 Jul 2018 01:46:47 -0500
Subject: smb3: display bytes_read and bytes_written in smb3 stats

We were only displaying bytes_read and bytes_written in cifs
stats, fix smb3 stats to also display them.  Sample output
with this patch:

    cat /proc/fs/cifs/Stats:

CIFS Session: 1
Share (unique mount targets): 2
SMB Request/Response Buffer: 1 Pool size: 5
SMB Small Req/Resp Buffer: 1 Pool size: 30
Operations (MIDs): 0

0 session 0 share reconnects
Total vfs operations: 94 maximum at one time: 2

1) \\localhost\test
SMBs: 214
Bytes read: 502092  Bytes written: 31457286
TreeConnects: 1 total 0 failed
TreeDisconnects: 0 total 0 failed
Creates: 52 total 3 failed
Closes: 48 total 0 failed
Flushes: 0 total 0 failed
Reads: 17 total 0 failed
Writes: 31 total 0 failed
...

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
---
 fs/cifs/smb2ops.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 831249001384..85e848007f91 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -950,6 +950,9 @@ smb2_print_stats(struct seq_file *m, struct cifs_tcon *tcon)
 	 *  Can't display SMB2_NEGOTIATE, SESSION_SETUP, LOGOFF, CANCEL and ECHO
 	 *  totals (requests sent) since those SMBs are per-session not per tcon
 	 */
+	seq_printf(m, "\nBytes read: %llu  Bytes written: %llu",
+		   (long long)(tcon->bytes_read),
+		   (long long)(tcon->bytes_written));
 	seq_printf(m, "\nTreeConnects: %d total %d failed",
 		   atomic_read(&sent[SMB2_TREE_CONNECT_HE]),
 		   atomic_read(&failed[SMB2_TREE_CONNECT_HE]));
-- 
cgit v1.2.3


From c281bc0c7412308c7ec0888904f7c99353da4796 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 1 Aug 2018 00:56:12 -0500
Subject: smb3: fix reset of bytes read and written stats

echo 0 > /proc/fs/cifs/Stats is supposed to reset the stats
but there were four (see example below) that were not reset
(bytes read and witten, total vfs ops and max ops
at one time).

...
0 session 0 share reconnects
Total vfs operations: 100 maximum at one time: 2

1) \\localhost\test
SMBs: 0
Bytes read: 502092  Bytes written: 31457286
TreeConnects: 0 total 0 failed
TreeDisconnects: 0 total 0 failed
...

This patch fixes cifs_stats_proc_write to properly reset
those four.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/cifs_debug.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 3270d9b74603..e074820bd4ed 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -381,6 +381,10 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
 #endif /* CONFIG_CIFS_STATS2 */
+		spin_lock(&GlobalMid_Lock);
+		GlobalMaxActiveXid = 0;
+		GlobalCurrentXid = 0;
+		spin_unlock(&GlobalMid_Lock);
 		spin_lock(&cifs_tcp_ses_lock);
 		list_for_each(tmp1, &cifs_tcp_ses_list) {
 			server = list_entry(tmp1, struct TCP_Server_Info,
@@ -393,6 +397,10 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 							  struct cifs_tcon,
 							  tcon_list);
 					atomic_set(&tcon->num_smbs_sent, 0);
+					spin_lock(&tcon->stat_lock);
+					tcon->bytes_read = 0;
+					tcon->bytes_written = 0;
+					spin_unlock(&tcon->stat_lock);
 					if (server->ops->clear_stats)
 						server->ops->clear_stats(tcon);
 				}
-- 
cgit v1.2.3


From 3de5e974ba65fd1629fb6ea0cb5222c78b1580ec Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 1 Aug 2018 01:13:55 -0500
Subject: smb3: update readme to correct information about /proc/fs/cifs/Stats

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 Documentation/filesystems/cifs/README | 22 ++++++++++------------
 1 file changed, 10 insertions(+), 12 deletions(-)

diff --git a/Documentation/filesystems/cifs/README b/Documentation/filesystems/cifs/README
index 99ce3d25003d..4a804619cff2 100644
--- a/Documentation/filesystems/cifs/README
+++ b/Documentation/filesystems/cifs/README
@@ -603,8 +603,7 @@ DebugData		Displays information about active CIFS sessions and
 			shares, features enabled as well as the cifs.ko
 			version.
 Stats			Lists summary resource usage information as well as per
-			share statistics, if CONFIG_CIFS_STATS in enabled
-			in the kernel configuration.
+			share statistics.
 
 Configuration pseudo-files:
 SecurityFlags		Flags which control security negotiation and
@@ -687,23 +686,22 @@ cifsFYI functions as a bit mask. Setting it to 1 enables additional kernel
 logging of various informational messages.  2 enables logging of non-zero
 SMB return codes while 4 enables logging of requests that take longer
 than one second to complete (except for byte range lock requests). 
-Setting it to 4 requires defining CONFIG_CIFS_STATS2 manually in the
-source code (typically by setting it in the beginning of cifsglob.h),
-and setting it to seven enables all three.  Finally, tracing
+Setting it to 4 requires CONFIG_CIFS_STATS2 to be set in kernel configuration
+(.config). Setting it to seven enables all three.  Finally, tracing
 the start of smb requests and responses can be enabled via:
 
 	echo 1 > /proc/fs/cifs/traceSMB
 
-Per share (per client mount) statistics are available in /proc/fs/cifs/Stats
-if the kernel was configured with cifs statistics enabled.  The statistics
-represent the number of successful (ie non-zero return code from the server) 
-SMB responses to some of the more common commands (open, delete, mkdir etc.).
+Per share (per client mount) statistics are available in /proc/fs/cifs/Stats.
+Additional information is available if CONFIG_CIFS_STATS2 is enabled in the
+kernel configuration (.config).  The statistics returned include counters which
+represent the number of attempted and failed (ie non-zero return code from the
+server) SMB3 (or cifs) requests grouped by request type (read, write, close etc.).
 Also recorded is the total bytes read and bytes written to the server for
 that share.  Note that due to client caching effects this can be less than the
 number of bytes read and written by the application running on the client.
-The statistics for the number of total SMBs and oplock breaks are different in
-that they represent all for that share, not just those for which the server
-returned success.
+Statistics can be reset to zero by "echo 0 > /proc/fs/cifs/Stats" which may be
+useful if comparing performance of two different scenarios.
 	
 Also note that "cat /proc/fs/cifs/DebugData" will display information about
 the active sessions and the shares that are mounted.
-- 
cgit v1.2.3


From b2b57b29588c36920fe1364f3f24bebfbe8bf321 Mon Sep 17 00:00:00 2001
From: Piotr Azarewicz <piotr.azarewicz@intel.com>
Date: Tue, 31 Jul 2018 03:41:46 -0700
Subject: i40e: Add additional return code to i40e_asq_send_command

Firmware can return a busy state, so the function return
I40E_ERR_NOT_READY.

Signed-off-by: Piotr Azarewicz <piotr.azarewicz@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq.c   | 2 ++
 drivers/net/ethernet/intel/i40evf/i40e_adminq.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index ddbea79d18e5..501ee718177f 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -868,6 +868,8 @@ i40e_status i40e_asq_send_command(struct i40e_hw *hw,
 		cmd_completed = true;
 		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
 			status = 0;
+		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
+			status = I40E_ERR_NOT_READY;
 		else
 			status = I40E_ERR_ADMIN_QUEUE_ERROR;
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index c355120dfdfd..21a0dbf6ccf6 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -797,6 +797,8 @@ i40e_status i40evf_asq_send_command(struct i40e_hw *hw,
 		cmd_completed = true;
 		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
 			status = 0;
+		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
+			status = I40E_ERR_NOT_READY;
 		else
 			status = I40E_ERR_ADMIN_QUEUE_ERROR;
 		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
-- 
cgit v1.2.3


From f05798b4ff82d919e94e5060d1e9993a3e025361 Mon Sep 17 00:00:00 2001
From: Piotr Azarewicz <piotr.azarewicz@intel.com>
Date: Tue, 31 Jul 2018 03:41:47 -0700
Subject: i40e: Add AQ command for rearrange NVM structure

During switching between old NVM structure approach (called structured
NVM) to new one (called flat NVM) or backward flash needs to be
rearranged to required NVM structure. This is a part of transition from
one NVM structure to another. The function is introduced to command
firmware to start rearrangement process.

Signed-off-by: Piotr Azarewicz <piotr.azarewicz@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h  |  2 ++
 drivers/net/ethernet/intel/i40e/i40e_common.c      | 35 ++++++++++++++++++++++
 drivers/net/ethernet/intel/i40e/i40e_prototype.h   |  3 ++
 .../net/ethernet/intel/i40evf/i40e_adminq_cmd.h    |  2 ++
 4 files changed, 42 insertions(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index 7d888e05f96f..80e3eec6134e 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -2247,6 +2247,8 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
 struct i40e_aqc_nvm_update {
 	u8	command_flags;
 #define I40E_AQ_NVM_LAST_CMD			0x01
+#define I40E_AQ_NVM_REARRANGE_TO_FLAT		0x20
+#define I40E_AQ_NVM_REARRANGE_TO_STRUCT		0x40
 #define I40E_AQ_NVM_FLASH_ONLY			0x80
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT	1
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK	0x03
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index eb2d1530d331..85f75b5978fc 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -3540,6 +3540,41 @@ i40e_aq_update_nvm_exit:
 	return status;
 }
 
+/**
+ * i40e_aq_rearrange_nvm
+ * @hw: pointer to the hw struct
+ * @rearrange_nvm: defines direction of rearrangement
+ * @cmd_details: pointer to command details structure or NULL
+ *
+ * Rearrange NVM structure, available only for transition FW
+ **/
+i40e_status i40e_aq_rearrange_nvm(struct i40e_hw *hw,
+				  u8 rearrange_nvm,
+				  struct i40e_asq_cmd_details *cmd_details)
+{
+	struct i40e_aqc_nvm_update *cmd;
+	i40e_status status;
+	struct i40e_aq_desc desc;
+
+	cmd = (struct i40e_aqc_nvm_update *)&desc.params.raw;
+
+	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update);
+
+	rearrange_nvm &= (I40E_AQ_NVM_REARRANGE_TO_FLAT |
+			 I40E_AQ_NVM_REARRANGE_TO_STRUCT);
+
+	if (!rearrange_nvm) {
+		status = I40E_ERR_PARAM;
+		goto i40e_aq_rearrange_nvm_exit;
+	}
+
+	cmd->command_flags |= rearrange_nvm;
+	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
+
+i40e_aq_rearrange_nvm_exit:
+	return status;
+}
+
 /**
  * i40e_aq_get_lldp_mib
  * @hw: pointer to the hw struct
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 3170655cdeb9..e08d754824b1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -193,6 +193,9 @@ i40e_status i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 				u32 offset, u16 length, void *data,
 				bool last_command, u8 preservation_flags,
 				struct i40e_asq_cmd_details *cmd_details);
+i40e_status i40e_aq_rearrange_nvm(struct i40e_hw *hw,
+				  u8 rearrange_nvm,
+				  struct i40e_asq_cmd_details *cmd_details);
 i40e_status i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 				u8 mib_type, void *buff, u16 buff_size,
 				u16 *local_len, u16 *remote_len,
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
index aa81e87cd471..5fd8529465d4 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h
@@ -2175,6 +2175,8 @@ I40E_CHECK_CMD_LENGTH(i40e_aqc_phy_register_access);
 struct i40e_aqc_nvm_update {
 	u8	command_flags;
 #define I40E_AQ_NVM_LAST_CMD			0x01
+#define I40E_AQ_NVM_REARRANGE_TO_FLAT		0x20
+#define I40E_AQ_NVM_REARRANGE_TO_STRUCT		0x40
 #define I40E_AQ_NVM_FLASH_ONLY			0x80
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_SHIFT	1
 #define I40E_AQ_NVM_PRESERVATION_FLAGS_MASK	0x03
-- 
cgit v1.2.3


From 333e2f2cea6cbffd75aa4969afad7409d7fad74c Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Tue, 31 Jul 2018 03:41:48 -0700
Subject: i40e: fix i40e_add_queue_stats data pointer update

This function accidentally failed to update the data pointer, which
caused the reported stats to be incorrect. Additionally, statistics
which follow queue stats in the output would potentially read non-zeroed
garbage data from the ethtool buffer.

This occurred because the data double pointer was not dereferenced
before incrementing the size.

Additionally, make sure this issue is more visible by adding a WARN_ONCE
to the i40e_get_ethtool_stats function. This warning will trigger
whenever the data pointer is not at the expected address, similar to the
check that we make in the i40e_get_stat_strings() function.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index cd23d1e169c2..abcd096ede14 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1860,6 +1860,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	unsigned int i;
 	unsigned int start;
 	bool veb_stats;
+	u64 *p = data;
 
 	i40e_update_stats(vsi);
 
@@ -1902,7 +1903,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 	}
 	rcu_read_unlock();
 	if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1)
-		return;
+		goto check_data_pointer;
 
 	veb_stats = ((pf->lan_veb != I40E_NO_VEB) &&
 		     (pf->flags & I40E_FLAG_VEB_STATS_ENABLED));
@@ -1925,6 +1926,10 @@ static void i40e_get_ethtool_stats(struct net_device *netdev,
 
 		i40e_add_ethtool_stats(&data, &pfc, i40e_gstrings_pfc_stats);
 	}
+
+check_data_pointer:
+	WARN_ONCE(data - p != i40e_get_stats_count(netdev),
+		  "ethtool stats count mismatch!");
 }
 
 /**
-- 
cgit v1.2.3


From b2c96de7fe3cd306df039c89727cb137b89d82ef Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 1 Aug 2018 09:26:11 +1000
Subject: cifs: update init_sg, crypt_message to take an array of rqst

These are used for SMB3 encryption and compounded requests.
Update these functions and the other functions related to SMB3 encryption to
take an array of requests.

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/cifsglob.h  |   7 +-
 fs/cifs/smb2ops.c   | 206 +++++++++++++++++++++++++++-------------------------
 fs/cifs/transport.c |  27 +++++--
 3 files changed, 131 insertions(+), 109 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 4a3a737134ea..0553929e8339 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -454,10 +454,8 @@ struct smb_version_operations {
 	long (*fallocate)(struct file *, struct cifs_tcon *, int, loff_t,
 			  loff_t);
 	/* init transform request - used for encryption for now */
-	int (*init_transform_rq)(struct TCP_Server_Info *, struct smb_rqst *,
-				 struct smb_rqst *);
-	/* free transform request */
-	void (*free_transform_rq)(struct smb_rqst *);
+	int (*init_transform_rq)(struct TCP_Server_Info *, int num_rqst,
+				 struct smb_rqst *, struct smb_rqst *);
 	int (*is_transform_hdr)(void *buf);
 	int (*receive_transform)(struct TCP_Server_Info *,
 				 struct mid_q_entry **);
@@ -1023,6 +1021,7 @@ struct tcon_link {
 };
 
 extern struct tcon_link *cifs_sb_tlink(struct cifs_sb_info *cifs_sb);
+extern void smb3_free_compound_rqst(int num_rqst, struct smb_rqst *rqst);
 
 static inline struct cifs_tcon *
 tlink_tcon(struct tcon_link *tlink)
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 85e848007f91..ebc13ebebddf 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2378,35 +2378,51 @@ static inline void smb2_sg_set_buf(struct scatterlist *sg, const void *buf,
 	sg_set_page(sg, virt_to_page(buf), buflen, offset_in_page(buf));
 }
 
-/* Assumes:
- * rqst->rq_iov[0]  is transform header
- * rqst->rq_iov[1+] data to be encrypted/decrypted
+/* Assumes the first rqst has a transform header as the first iov.
+ * I.e.
+ * rqst[0].rq_iov[0]  is transform header
+ * rqst[0].rq_iov[1+] data to be encrypted/decrypted
+ * rqst[1+].rq_iov[0+] data to be encrypted/decrypted
  */
 static struct scatterlist *
-init_sg(struct smb_rqst *rqst, u8 *sign)
+init_sg(int num_rqst, struct smb_rqst *rqst, u8 *sign)
 {
-	unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
-	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
+	unsigned int sg_len;
 	struct scatterlist *sg;
 	unsigned int i;
 	unsigned int j;
+	unsigned int idx = 0;
+	int skip;
+
+	sg_len = 1;
+	for (i = 0; i < num_rqst; i++)
+		sg_len += rqst[i].rq_nvec + rqst[i].rq_npages;
 
 	sg = kmalloc_array(sg_len, sizeof(struct scatterlist), GFP_KERNEL);
 	if (!sg)
 		return NULL;
 
 	sg_init_table(sg, sg_len);
-	smb2_sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 20, assoc_data_len);
-	for (i = 1; i < rqst->rq_nvec; i++)
-		smb2_sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
-						rqst->rq_iov[i].iov_len);
-	for (j = 0; i < sg_len - 1; i++, j++) {
-		unsigned int len, offset;
+	for (i = 0; i < num_rqst; i++) {
+		for (j = 0; j < rqst[i].rq_nvec; j++) {
+			/*
+			 * The first rqst has a transform header where the
+			 * first 20 bytes are not part of the encrypted blob
+			 */
+			skip = (i == 0) && (j == 0) ? 20 : 0;
+			smb2_sg_set_buf(&sg[idx++],
+					rqst[i].rq_iov[j].iov_base + skip,
+					rqst[i].rq_iov[j].iov_len - skip);
+		}
+
+		for (j = 0; j < rqst[i].rq_npages; j++) {
+			unsigned int len, offset;
 
-		rqst_page_get_length(rqst, j, &len, &offset);
-		sg_set_page(&sg[i], rqst->rq_pages[j], len, offset);
+			rqst_page_get_length(&rqst[i], j, &len, &offset);
+			sg_set_page(&sg[idx++], rqst[i].rq_pages[j], len, offset);
+		}
 	}
-	smb2_sg_set_buf(&sg[sg_len - 1], sign, SMB2_SIGNATURE_SIZE);
+	smb2_sg_set_buf(&sg[idx], sign, SMB2_SIGNATURE_SIZE);
 	return sg;
 }
 
@@ -2438,10 +2454,11 @@ smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
  * untouched.
  */
 static int
-crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
+crypt_message(struct TCP_Server_Info *server, int num_rqst,
+	      struct smb_rqst *rqst, int enc)
 {
 	struct smb2_transform_hdr *tr_hdr =
-			(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
+		(struct smb2_transform_hdr *)rqst[0].rq_iov[0].iov_base;
 	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 20;
 	int rc = 0;
 	struct scatterlist *sg;
@@ -2492,7 +2509,7 @@ crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
 		crypt_len += SMB2_SIGNATURE_SIZE;
 	}
 
-	sg = init_sg(rqst, sign);
+	sg = init_sg(num_rqst, rqst, sign);
 	if (!sg) {
 		cifs_dbg(VFS, "%s: Failed to init sg", __func__);
 		rc = -ENOMEM;
@@ -2529,103 +2546,98 @@ free_req:
 	return rc;
 }
 
+void
+smb3_free_compound_rqst(int num_rqst, struct smb_rqst *rqst)
+{
+	int i, j;
+
+	for (i = 0; i < num_rqst; i++) {
+		if (rqst[i].rq_pages) {
+			for (j = rqst[i].rq_npages - 1; j >= 0; j--)
+				put_page(rqst[i].rq_pages[j]);
+			kfree(rqst[i].rq_pages);
+		}
+	}
+}
+
+/*
+ * This function will initialize new_rq and encrypt the content.
+ * The first entry, new_rq[0], only contains a single iov which contains
+ * a smb2_transform_hdr and is pre-allocated by the caller.
+ * This function then populates new_rq[1+] with the content from olq_rq[0+].
+ *
+ * The end result is an array of smb_rqst structures where the first structure
+ * only contains a single iov for the transform header which we then can pass
+ * to crypt_message().
+ *
+ * new_rq[0].rq_iov[0] :  smb2_transform_hdr pre-allocated by the caller
+ * new_rq[1+].rq_iov[*] == old_rq[0+].rq_iov[*] : SMB2/3 requests
+ */
 static int
-smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
-		       struct smb_rqst *old_rq)
+smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst,
+		       struct smb_rqst *new_rq, struct smb_rqst *old_rq)
 {
-	struct kvec *iov;
 	struct page **pages;
-	struct smb2_transform_hdr *tr_hdr;
-	unsigned int npages = old_rq->rq_npages;
-	unsigned int orig_len;
-	int i;
+	struct smb2_transform_hdr *tr_hdr = new_rq[0].rq_iov[0].iov_base;
+	unsigned int npages;
+	unsigned int orig_len = 0;
+	int i, j;
 	int rc = -ENOMEM;
 
-	pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
-	if (!pages)
-		return rc;
-
-	new_rq->rq_pages = pages;
-	new_rq->rq_offset = old_rq->rq_offset;
-	new_rq->rq_npages = old_rq->rq_npages;
-	new_rq->rq_pagesz = old_rq->rq_pagesz;
-	new_rq->rq_tailsz = old_rq->rq_tailsz;
-
-	for (i = 0; i < npages; i++) {
-		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
-		if (!pages[i])
-			goto err_free_pages;
-	}
-
-	iov = kmalloc_array(old_rq->rq_nvec + 1, sizeof(struct kvec),
-			    GFP_KERNEL);
-	if (!iov)
-		goto err_free_pages;
+	for (i = 1; i < num_rqst; i++) {
+		npages = old_rq[i - 1].rq_npages;
+		pages = kmalloc_array(npages, sizeof(struct page *),
+				      GFP_KERNEL);
+		if (!pages)
+			goto err_free;
+
+		new_rq[i].rq_pages = pages;
+		new_rq[i].rq_npages = npages;
+		new_rq[i].rq_offset = old_rq[i - 1].rq_offset;
+		new_rq[i].rq_pagesz = old_rq[i - 1].rq_pagesz;
+		new_rq[i].rq_tailsz = old_rq[i - 1].rq_tailsz;
+		new_rq[i].rq_iov = old_rq[i - 1].rq_iov;
+		new_rq[i].rq_nvec = old_rq[i - 1].rq_nvec;
+
+		orig_len += smb_rqst_len(server, &old_rq[i - 1]);
+
+		for (j = 0; j < npages; j++) {
+			pages[j] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
+			if (!pages[j])
+				goto err_free;
+		}
 
-	/* copy all iovs from the old */
-	memcpy(&iov[1], &old_rq->rq_iov[0],
-				sizeof(struct kvec) * old_rq->rq_nvec);
+		/* copy pages form the old */
+		for (j = 0; j < npages; j++) {
+			char *dst, *src;
+			unsigned int offset, len;
 
-	new_rq->rq_iov = iov;
-	new_rq->rq_nvec = old_rq->rq_nvec + 1;
+			rqst_page_get_length(&new_rq[i], j, &len, &offset);
 
-	tr_hdr = kmalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
-	if (!tr_hdr)
-		goto err_free_iov;
+			dst = (char *) kmap(new_rq[i].rq_pages[j]) + offset;
+			src = (char *) kmap(old_rq[i - 1].rq_pages[j]) + offset;
 
-	orig_len = smb_rqst_len(server, old_rq);
+			memcpy(dst, src, len);
+			kunmap(new_rq[i].rq_pages[j]);
+			kunmap(old_rq[i - 1].rq_pages[j]);
+		}
+	}
 
-	/* fill the 2nd iov with a transform header */
+	/* fill the 1st iov with a transform header */
 	fill_transform_hdr(tr_hdr, orig_len, old_rq);
-	new_rq->rq_iov[0].iov_base = tr_hdr;
-	new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
-
-	/* copy pages form the old */
-	for (i = 0; i < npages; i++) {
-		char *dst, *src;
-		unsigned int offset, len;
-
-		rqst_page_get_length(new_rq, i, &len, &offset);
 
-		dst = (char *) kmap(new_rq->rq_pages[i]) + offset;
-		src = (char *) kmap(old_rq->rq_pages[i]) + offset;
-
-		memcpy(dst, src, len);
-		kunmap(new_rq->rq_pages[i]);
-		kunmap(old_rq->rq_pages[i]);
-	}
-
-	rc = crypt_message(server, new_rq, 1);
+	rc = crypt_message(server, num_rqst, new_rq, 1);
 	cifs_dbg(FYI, "encrypt message returned %d", rc);
 	if (rc)
-		goto err_free_tr_hdr;
+		goto err_free;
 
 	return rc;
 
-err_free_tr_hdr:
-	kfree(tr_hdr);
-err_free_iov:
-	kfree(iov);
-err_free_pages:
-	for (i = i - 1; i >= 0; i--)
-		put_page(pages[i]);
-	kfree(pages);
+err_free:
+	smb3_free_compound_rqst(num_rqst - 1, &new_rq[1]);
 	return rc;
 }
 
-static void
-smb3_free_transform_rq(struct smb_rqst *rqst)
-{
-	int i = rqst->rq_npages - 1;
-
-	for (; i >= 0; i--)
-		put_page(rqst->rq_pages[i]);
-	kfree(rqst->rq_pages);
-	/* free transform header */
-	kfree(rqst->rq_iov[0].iov_base);
-	kfree(rqst->rq_iov);
-}
-
 static int
 smb3_is_transform_hdr(void *buf)
 {
@@ -2655,7 +2667,7 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
 	rqst.rq_pagesz = PAGE_SIZE;
 	rqst.rq_tailsz = (page_data_size % PAGE_SIZE) ? : PAGE_SIZE;
 
-	rc = crypt_message(server, &rqst, 0);
+	rc = crypt_message(server, 1, &rqst, 0);
 	cifs_dbg(FYI, "decrypt message returned %d\n", rc);
 
 	if (rc)
@@ -3302,7 +3314,6 @@ struct smb_version_operations smb30_operations = {
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
 	.init_transform_rq = smb3_init_transform_rq,
-	.free_transform_rq = smb3_free_transform_rq,
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
 	.get_dfs_refer = smb2_get_dfs_refer,
@@ -3408,7 +3419,6 @@ struct smb_version_operations smb311_operations = {
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
 	.init_transform_rq = smb3_init_transform_rq,
-	.free_transform_rq = smb3_free_transform_rq,
 	.is_transform_hdr = smb3_is_transform_hdr,
 	.receive_transform = smb3_receive_transform,
 	.get_dfs_refer = smb2_get_dfs_refer,
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 357d25351ffa..8039c93ba57a 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -374,27 +374,40 @@ smbd_done:
 	return rc;
 }
 
+#define MAX_COMPOUND 2
+
 static int
 smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
 {
-	struct smb_rqst cur_rqst;
+	struct kvec iov;
+	struct smb2_transform_hdr tr_hdr;
+	struct smb_rqst cur_rqst[MAX_COMPOUND];
 	int rc;
 
 	if (!(flags & CIFS_TRANSFORM_REQ))
 		return __smb_send_rqst(server, 1, rqst);
 
-	if (!server->ops->init_transform_rq ||
-	    !server->ops->free_transform_rq) {
-		cifs_dbg(VFS, "Encryption requested but transform callbacks are missed\n");
+	memset(&cur_rqst[0], 0, sizeof(cur_rqst));
+	memset(&iov, 0, sizeof(iov));
+	memset(&tr_hdr, 0, sizeof(tr_hdr));
+
+	iov.iov_base = &tr_hdr;
+	iov.iov_len = sizeof(tr_hdr);
+	cur_rqst[0].rq_iov = &iov;
+	cur_rqst[0].rq_nvec = 1;
+
+	if (!server->ops->init_transform_rq) {
+		cifs_dbg(VFS, "Encryption requested but transform callback "
+			 "is missing\n");
 		return -EIO;
 	}
 
-	rc = server->ops->init_transform_rq(server, &cur_rqst, rqst);
+	rc = server->ops->init_transform_rq(server, 2, &cur_rqst[0], rqst);
 	if (rc)
 		return rc;
 
-	rc = __smb_send_rqst(server, 1, &cur_rqst);
-	server->ops->free_transform_rq(&cur_rqst);
+	rc = __smb_send_rqst(server, 2, &cur_rqst[0]);
+	smb3_free_compound_rqst(1, &cur_rqst[1]);
 	return rc;
 }
 
-- 
cgit v1.2.3


From 2a43747147699c6187d8508b40a28a50f42b0ee5 Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Tue, 7 Aug 2018 17:35:58 +0200
Subject: nfp: flower: set ip tunnel ttl from encap action

The TTL for encapsulating headers in IPv4 UDP tunnels is taken from a
route lookup. Modify this to first check if a user has specified a TTL to
be used in the TC action.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 39 ++++++++++++----------
 1 file changed, 21 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index e56b815a8dc6..a79d078ab3e8 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -238,18 +238,12 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
 	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
 	u32 tmp_set_ip_tun_type_index = 0;
-	struct flowi4 flow = {};
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
-	struct rtable *rt;
-	struct net *net;
-	int err;
 
 	if (ip_tun->options_len)
 		return -EOPNOTSUPP;
 
-	net = dev_net(netdev);
-
 	set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
 	set_tun->head.len_lw = act_size >> NFP_FL_LW_SIZ;
 
@@ -261,19 +255,28 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 	set_tun->tun_type_index = cpu_to_be32(tmp_set_ip_tun_type_index);
 	set_tun->tun_id = ip_tun->key.tun_id;
 
-	/* Do a route lookup to determine ttl - if fails then use default.
-	 * Note that CONFIG_INET is a requirement of CONFIG_NET_SWITCHDEV so
-	 * must be defined here.
-	 */
-	flow.daddr = ip_tun->key.u.ipv4.dst;
-	flow.flowi4_proto = IPPROTO_UDP;
-	rt = ip_route_output_key(net, &flow);
-	err = PTR_ERR_OR_ZERO(rt);
-	if (!err) {
-		set_tun->ttl = ip4_dst_hoplimit(&rt->dst);
-		ip_rt_put(rt);
+	if (ip_tun->key.ttl) {
+		set_tun->ttl = ip_tun->key.ttl;
 	} else {
-		set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+		struct net *net = dev_net(netdev);
+		struct flowi4 flow = {};
+		struct rtable *rt;
+		int err;
+
+		/* Do a route lookup to determine ttl - if fails then use
+		 * default. Note that CONFIG_INET is a requirement of
+		 * CONFIG_NET_SWITCHDEV so must be defined here.
+		 */
+		flow.daddr = ip_tun->key.u.ipv4.dst;
+		flow.flowi4_proto = IPPROTO_UDP;
+		rt = ip_route_output_key(net, &flow);
+		err = PTR_ERR_OR_ZERO(rt);
+		if (!err) {
+			set_tun->ttl = ip4_dst_hoplimit(&rt->dst);
+			ip_rt_put(rt);
+		} else {
+			set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+		}
 	}
 
 	set_tun->tos = ip_tun->key.tos;
-- 
cgit v1.2.3


From d7ff7ec573860dc654fa4c8641684ba3db03004e Mon Sep 17 00:00:00 2001
From: John Hurley <john.hurley@netronome.com>
Date: Tue, 7 Aug 2018 17:35:59 +0200
Subject: nfp: flower: allow matching on ipv4 UDP tunnel tos and ttl

The addition of FLOW_DISSECTOR_KEY_ENC_IP to TC flower means that the ToS
and TTL of the tunnel header can now be matched on.

Extend the NFP tunnel match function to include these new fields.

Signed-off-by: John Hurley <john.hurley@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h    | 7 +++++--
 drivers/net/ethernet/netronome/nfp/flower/match.c   | 9 +++++++++
 drivers/net/ethernet/netronome/nfp/flower/offload.c | 4 +++-
 3 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 15f1eacd76b6..174acecfba01 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -346,7 +346,7 @@ struct nfp_flower_ipv6 {
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * |                         ipv4_addr_dst                         |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
- * |                            Reserved                           |
+ * |           Reserved            |      tos      |      ttl      |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
  * |                            Reserved                           |
  * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
@@ -356,7 +356,10 @@ struct nfp_flower_ipv6 {
 struct nfp_flower_ipv4_udp_tun {
 	__be32 ip_src;
 	__be32 ip_dst;
-	__be32 reserved[2];
+	__be16 reserved1;
+	u8 tos;
+	u8 ttl;
+	__be32 reserved2;
 	__be32 tun_id;
 };
 
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index 84f7a5dbea9d..b1cbe6927cba 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -270,6 +270,7 @@ nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
 	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
 	struct flow_dissector_key_ipv4_addrs *tun_ips;
 	struct flow_dissector_key_keyid *vni;
+	struct flow_dissector_key_ip *ip;
 
 	memset(frame, 0, sizeof(struct nfp_flower_ipv4_udp_tun));
 
@@ -293,6 +294,14 @@ nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
 		frame->ip_src = tun_ips->src;
 		frame->ip_dst = tun_ips->dst;
 	}
+
+	if (dissector_uses_key(flow->dissector, FLOW_DISSECTOR_KEY_ENC_IP)) {
+		ip = skb_flow_dissector_target(flow->dissector,
+					       FLOW_DISSECTOR_KEY_ENC_IP,
+					       target);
+		frame->tos = ip->tos;
+		frame->ttl = ip->ttl;
+	}
 }
 
 int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index 6bc8a97f7e03..d2230a0e49b9 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -66,6 +66,7 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IP) | \
 	 BIT(FLOW_DISSECTOR_KEY_MPLS) | \
 	 BIT(FLOW_DISSECTOR_KEY_IP))
 
@@ -74,7 +75,8 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
-	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS))
+	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_IP))
 
 #define NFP_FLOWER_WHITELIST_TUN_DISSECTOR_R \
 	(BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
-- 
cgit v1.2.3


From 92e2c4053623f21d61a683f7ef7bd61c8300ac7d Mon Sep 17 00:00:00 2001
From: Simon Horman <simon.horman@netronome.com>
Date: Tue, 7 Aug 2018 17:36:00 +0200
Subject: flow_dissector: allow dissection of tunnel options from metadata

Allow the existing 'dissection' of tunnel metadata to 'dissect'
options already present in tunnel metadata. This dissection is
controlled by a new dissector key, FLOW_DISSECTOR_KEY_ENC_OPTS.

This dissection only occurs when skb_flow_dissect_tunnel_info()
is called, currently only the Flower classifier makes that call.
So there should be no impact on other users of the flow dissector.

This is in preparation for allowing the flower classifier to
match on Geneve options.

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/flow_dissector.h | 17 +++++++++++++++++
 net/core/flow_dissector.c    | 19 ++++++++++++++++++-
 2 files changed, 35 insertions(+), 1 deletion(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index 2a17f041f7a1..6a4586dcdede 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -57,6 +57,21 @@ struct flow_dissector_key_mpls {
 		mpls_label:20;
 };
 
+#define FLOW_DIS_TUN_OPTS_MAX 255
+/**
+ * struct flow_dissector_key_enc_opts:
+ * @data: tunnel option data
+ * @len: length of tunnel option data
+ * @dst_opt_type: tunnel option type
+ */
+struct flow_dissector_key_enc_opts {
+	u8 data[FLOW_DIS_TUN_OPTS_MAX];	/* Using IP_TUNNEL_OPTS_MAX is desired
+					 * here but seems difficult to #include
+					 */
+	u8 len;
+	__be16 dst_opt_type;
+};
+
 struct flow_dissector_key_keyid {
 	__be32	keyid;
 };
@@ -208,6 +223,8 @@ enum flow_dissector_key_id {
 	FLOW_DISSECTOR_KEY_IP, /* struct flow_dissector_key_ip */
 	FLOW_DISSECTOR_KEY_CVLAN, /* struct flow_dissector_key_flow_vlan */
 	FLOW_DISSECTOR_KEY_ENC_IP, /* struct flow_dissector_key_ip */
+	FLOW_DISSECTOR_KEY_ENC_OPTS, /* struct flow_dissector_key_enc_opts */
+
 	FLOW_DISSECTOR_KEY_MAX,
 };
 
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 08a5184f4b34..ce9eeeb7c024 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -154,7 +154,9 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 	    !dissector_uses_key(flow_dissector,
 				FLOW_DISSECTOR_KEY_ENC_PORTS) &&
 	    !dissector_uses_key(flow_dissector,
-				FLOW_DISSECTOR_KEY_ENC_IP))
+				FLOW_DISSECTOR_KEY_ENC_IP) &&
+	    !dissector_uses_key(flow_dissector,
+				FLOW_DISSECTOR_KEY_ENC_OPTS))
 		return;
 
 	info = skb_tunnel_info(skb);
@@ -224,6 +226,21 @@ skb_flow_dissect_tunnel_info(const struct sk_buff *skb,
 		ip->tos = key->tos;
 		ip->ttl = key->ttl;
 	}
+
+	if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+		struct flow_dissector_key_enc_opts *enc_opt;
+
+		enc_opt = skb_flow_dissector_target(flow_dissector,
+						    FLOW_DISSECTOR_KEY_ENC_OPTS,
+						    target_container);
+
+		if (info->options_len) {
+			enc_opt->len = info->options_len;
+			ip_tunnel_info_opts_get(enc_opt->data, info);
+			enc_opt->dst_opt_type = info->key.tun_flags &
+						TUNNEL_OPTIONS_PRESENT;
+		}
+	}
 }
 EXPORT_SYMBOL(skb_flow_dissect_tunnel_info);
 
-- 
cgit v1.2.3


From 0a6e77784f490912d81b92cfd48424541c04691e Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 7 Aug 2018 17:36:01 +0200
Subject: net/sched: allow flower to match tunnel options

Allow matching on options in Geneve tunnel headers.
This makes use of existing tunnel metadata support.

The options can be described in the form
CLASS:TYPE:DATA/CLASS_MASK:TYPE_MASK:DATA_MASK, where CLASS is
represented as a 16bit hexadecimal value, TYPE as an 8bit
hexadecimal value and DATA as a variable length hexadecimal value.

e.g.
 # ip link add name geneve0 type geneve dstport 0 external
 # tc qdisc add dev geneve0 ingress
 # tc filter add dev geneve0 protocol ip parent ffff: \
     flower \
       enc_src_ip 10.0.99.192 \
       enc_dst_ip 10.0.99.193 \
       enc_key_id 11 \
       geneve_opts 0102:80:1122334421314151/ffff:ff:ffffffffffffffff \
       ip_proto udp \
       action mirred egress redirect dev eth1

This patch adds support for matching Geneve options in the order
supplied by the user. This leads to an efficient implementation in
the software datapath (and in our opinion hardware datapaths that
offload this feature). It is also compatible with Geneve options
matching provided by the Open vSwitch kernel datapath which is
relevant here as the Flower classifier may be used as a mechanism
to program flows into hardware as a form of Open vSwitch datapath
offload (sometimes referred to as OVS-TC). The netlink
Kernel/Userspace API may be extended, for example by adding a flag,
if other matching options are desired, for example matching given
options in any order. This would require an implementation in the
TC software datapath. And be done in a way that drivers that
facilitate offload of the Flower classifier can reject or accept
such flows based on hardware datapath capabilities.

This approach was discussed and agreed on at Netconf 2017 in Seoul.

Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Acked-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/pkt_cls.h |  26 +++++
 net/sched/cls_flower.c       | 244 ++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 269 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/pkt_cls.h b/include/uapi/linux/pkt_cls.h
index 48e5b5d49a34..be382fb0592d 100644
--- a/include/uapi/linux/pkt_cls.h
+++ b/include/uapi/linux/pkt_cls.h
@@ -480,11 +480,37 @@ enum {
 	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
 	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
 
+	TCA_FLOWER_KEY_ENC_OPTS,
+	TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
 	__TCA_FLOWER_MAX,
 };
 
 #define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
 
+enum {
+	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+					 * attributes
+					 */
+	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,            /* u16 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,             /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,             /* 4 to 128 bytes */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
 enum {
 	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
 	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index a3b69bb6f4b0..9da244235170 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -24,6 +24,7 @@
 #include <net/pkt_cls.h>
 #include <net/ip.h>
 #include <net/flow_dissector.h>
+#include <net/geneve.h>
 
 #include <net/dst.h>
 #include <net/dst_metadata.h>
@@ -53,6 +54,7 @@ struct fl_flow_key {
 	struct flow_dissector_key_tcp tcp;
 	struct flow_dissector_key_ip ip;
 	struct flow_dissector_key_ip enc_ip;
+	struct flow_dissector_key_enc_opts enc_opts;
 } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
 
 struct fl_flow_mask_range {
@@ -482,6 +484,21 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
 	[TCA_FLOWER_KEY_ENC_IP_TOS_MASK] = { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_ENC_IP_TTL]	 = { .type = NLA_U8 },
 	[TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_OPTS]	= { .type = NLA_NESTED },
+	[TCA_FLOWER_KEY_ENC_OPTS_MASK]	= { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+enc_opts_policy[TCA_FLOWER_KEY_ENC_OPTS_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPTS_GENEVE]        = { .type = NLA_NESTED },
+};
+
+static const struct nla_policy
+geneve_opt_policy[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1] = {
+	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]      = { .type = NLA_U16 },
+	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]       = { .type = NLA_U8 },
+	[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]       = { .type = NLA_BINARY,
+						       .len = 128 },
 };
 
 static void fl_set_key_val(struct nlattr **tb,
@@ -603,6 +620,145 @@ static void fl_set_key_ip(struct nlattr **tb, bool encap,
 	fl_set_key_val(tb, &key->ttl, ttl_key, &mask->ttl, ttl_mask, sizeof(key->ttl));
 }
 
+static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key,
+			     int depth, int option_len,
+			     struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX + 1];
+	struct nlattr *class = NULL, *type = NULL, *data = NULL;
+	struct geneve_opt *opt;
+	int err, data_len = 0;
+
+	if (option_len > sizeof(struct geneve_opt))
+		data_len = option_len - sizeof(struct geneve_opt);
+
+	opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len];
+	memset(opt, 0xff, option_len);
+	opt->length = data_len / 4;
+	opt->r1 = 0;
+	opt->r2 = 0;
+	opt->r3 = 0;
+
+	/* If no mask has been prodived we assume an exact match. */
+	if (!depth)
+		return sizeof(struct geneve_opt) + data_len;
+
+	if (nla_type(nla) != TCA_FLOWER_KEY_ENC_OPTS_GENEVE) {
+		NL_SET_ERR_MSG(extack, "Non-geneve option type for mask");
+		return -EINVAL;
+	}
+
+	err = nla_parse_nested(tb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+			       nla, geneve_opt_policy, extack);
+	if (err < 0)
+		return err;
+
+	/* We are not allowed to omit any of CLASS, TYPE or DATA
+	 * fields from the key.
+	 */
+	if (!option_len &&
+	    (!tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS] ||
+	     !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE] ||
+	     !tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA])) {
+		NL_SET_ERR_MSG(extack, "Missing tunnel key geneve option class, type or data");
+		return -EINVAL;
+	}
+
+	/* Omitting any of CLASS, TYPE or DATA fields is allowed
+	 * for the mask.
+	 */
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA]) {
+		int new_len = key->enc_opts.len;
+
+		data = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA];
+		data_len = nla_len(data);
+		if (data_len < 4) {
+			NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is less than 4 bytes long");
+			return -ERANGE;
+		}
+		if (data_len % 4) {
+			NL_SET_ERR_MSG(extack, "Tunnel key geneve option data is not a multiple of 4 bytes long");
+			return -ERANGE;
+		}
+
+		new_len += sizeof(struct geneve_opt) + data_len;
+		BUILD_BUG_ON(FLOW_DIS_TUN_OPTS_MAX != IP_TUNNEL_OPTS_MAX);
+		if (new_len > FLOW_DIS_TUN_OPTS_MAX) {
+			NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size");
+			return -ERANGE;
+		}
+		opt->length = data_len / 4;
+		memcpy(opt->opt_data, nla_data(data), data_len);
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS]) {
+		class = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS];
+		opt->opt_class = nla_get_be16(class);
+	}
+
+	if (tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE]) {
+		type = tb[TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE];
+		opt->type = nla_get_u8(type);
+	}
+
+	return sizeof(struct geneve_opt) + data_len;
+}
+
+static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
+			  struct fl_flow_key *mask,
+			  struct netlink_ext_ack *extack)
+{
+	const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
+	int option_len, key_depth, msk_depth = 0;
+
+	nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
+
+	if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
+		nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
+		msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
+	}
+
+	nla_for_each_attr(nla_opt_key, nla_enc_key,
+			  nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS]), key_depth) {
+		switch (nla_type(nla_opt_key)) {
+		case TCA_FLOWER_KEY_ENC_OPTS_GENEVE:
+			option_len = 0;
+			key->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT;
+			option_len = fl_set_geneve_opt(nla_opt_key, key,
+						       key_depth, option_len,
+						       extack);
+			if (option_len < 0)
+				return option_len;
+
+			key->enc_opts.len += option_len;
+			/* At the same time we need to parse through the mask
+			 * in order to verify exact and mask attribute lengths.
+			 */
+			mask->enc_opts.dst_opt_type = TUNNEL_GENEVE_OPT;
+			option_len = fl_set_geneve_opt(nla_opt_msk, mask,
+						       msk_depth, option_len,
+						       extack);
+			if (option_len < 0)
+				return option_len;
+
+			mask->enc_opts.len += option_len;
+			if (key->enc_opts.len != mask->enc_opts.len) {
+				NL_SET_ERR_MSG(extack, "Key and mask miss aligned");
+				return -EINVAL;
+			}
+
+			if (msk_depth)
+				nla_opt_msk = nla_next(nla_opt_msk, &msk_depth);
+			break;
+		default:
+			NL_SET_ERR_MSG(extack, "Unknown tunnel option type");
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
 static int fl_set_key(struct net *net, struct nlattr **tb,
 		      struct fl_flow_key *key, struct fl_flow_key *mask,
 		      struct netlink_ext_ack *extack)
@@ -799,6 +955,12 @@ static int fl_set_key(struct net *net, struct nlattr **tb,
 
 	fl_set_key_ip(tb, true, &key->enc_ip, &mask->enc_ip);
 
+	if (tb[TCA_FLOWER_KEY_ENC_OPTS]) {
+		ret = fl_set_enc_opt(tb, key, mask, extack);
+		if (ret)
+			return ret;
+	}
+
 	if (tb[TCA_FLOWER_KEY_FLAGS])
 		ret = fl_set_key_flags(tb, &key->control.flags, &mask->control.flags);
 
@@ -894,6 +1056,8 @@ static void fl_init_dissector(struct flow_dissector *dissector,
 			     FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp);
 	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
 			     FLOW_DISSECTOR_KEY_ENC_IP, enc_ip);
+	FL_KEY_SET_IF_MASKED(mask, keys, cnt,
+			     FLOW_DISSECTOR_KEY_ENC_OPTS, enc_opts);
 
 	skb_flow_dissector_init(dissector, keys, cnt);
 }
@@ -1414,6 +1578,83 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask)
 	return nla_put(skb, TCA_FLOWER_KEY_FLAGS_MASK, 4, &_mask);
 }
 
+static int fl_dump_key_geneve_opt(struct sk_buff *skb,
+				  struct flow_dissector_key_enc_opts *enc_opts)
+{
+	struct geneve_opt *opt;
+	struct nlattr *nest;
+	int opt_off = 0;
+
+	nest = nla_nest_start(skb, TCA_FLOWER_KEY_ENC_OPTS_GENEVE);
+	if (!nest)
+		goto nla_put_failure;
+
+	while (enc_opts->len > opt_off) {
+		opt = (struct geneve_opt *)&enc_opts->data[opt_off];
+
+		if (nla_put_be16(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,
+				 opt->opt_class))
+			goto nla_put_failure;
+		if (nla_put_u8(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,
+			       opt->type))
+			goto nla_put_failure;
+		if (nla_put(skb, TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,
+			    opt->length * 4, opt->opt_data))
+			goto nla_put_failure;
+
+		opt_off += sizeof(struct geneve_opt) + opt->length * 4;
+	}
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int fl_dump_key_options(struct sk_buff *skb, int enc_opt_type,
+			       struct flow_dissector_key_enc_opts *enc_opts)
+{
+	struct nlattr *nest;
+	int err;
+
+	if (!enc_opts->len)
+		return 0;
+
+	nest = nla_nest_start(skb, enc_opt_type);
+	if (!nest)
+		goto nla_put_failure;
+
+	switch (enc_opts->dst_opt_type) {
+	case TUNNEL_GENEVE_OPT:
+		err = fl_dump_key_geneve_opt(skb, enc_opts);
+		if (err)
+			goto nla_put_failure;
+		break;
+	default:
+		goto nla_put_failure;
+	}
+	nla_nest_end(skb, nest);
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, nest);
+	return -EMSGSIZE;
+}
+
+static int fl_dump_key_enc_opt(struct sk_buff *skb,
+			       struct flow_dissector_key_enc_opts *key_opts,
+			       struct flow_dissector_key_enc_opts *msk_opts)
+{
+	int err;
+
+	err = fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS, key_opts);
+	if (err)
+		return err;
+
+	return fl_dump_key_options(skb, TCA_FLOWER_KEY_ENC_OPTS_MASK, msk_opts);
+}
+
 static int fl_dump_key(struct sk_buff *skb, struct net *net,
 		       struct fl_flow_key *key, struct fl_flow_key *mask)
 {
@@ -1594,7 +1835,8 @@ static int fl_dump_key(struct sk_buff *skb, struct net *net,
 			    &mask->enc_tp.dst,
 			    TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,
 			    sizeof(key->enc_tp.dst)) ||
-	    fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip))
+	    fl_dump_key_ip(skb, true, &key->enc_ip, &mask->enc_ip) ||
+	    fl_dump_key_enc_opt(skb, &key->enc_opts, &mask->enc_opts))
 		goto nla_put_failure;
 
 	if (fl_dump_key_flags(skb, key->control.flags, mask->control.flags))
-- 
cgit v1.2.3


From 9e7c32fe44248b5101173b1184707bc5506e00f3 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 7 Aug 2018 17:36:02 +0200
Subject: nfp: flower: add geneve option push action offload

Introduce new push geneve option action. This allows offloading
filters configured to entunnel geneve with options.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Reviewed-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/action.c | 100 +++++++++++++++++++--
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   |  20 ++++-
 drivers/net/ethernet/netronome/nfp/flower/main.h   |   1 +
 3 files changed, 114 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index a79d078ab3e8..0ba0356ec4e6 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -32,6 +32,7 @@
  */
 
 #include <linux/bitfield.h>
+#include <net/geneve.h>
 #include <net/pkt_cls.h>
 #include <net/switchdev.h>
 #include <net/tc_act/tc_csum.h>
@@ -45,7 +46,15 @@
 #include "main.h"
 #include "../nfp_net_repr.h"
 
-#define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS	(TUNNEL_CSUM | TUNNEL_KEY)
+/* The kernel versions of TUNNEL_* are not ABI and therefore vulnerable
+ * to change. Such changes will break our FW ABI.
+ */
+#define NFP_FL_TUNNEL_CSUM			cpu_to_be16(0x01)
+#define NFP_FL_TUNNEL_KEY			cpu_to_be16(0x04)
+#define NFP_FL_TUNNEL_GENEVE_OPT		cpu_to_be16(0x0800)
+#define NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS	(NFP_FL_TUNNEL_CSUM | \
+						 NFP_FL_TUNNEL_KEY | \
+						 NFP_FL_TUNNEL_GENEVE_OPT)
 
 static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan)
 {
@@ -229,7 +238,71 @@ static struct nfp_fl_pre_tunnel *nfp_fl_pre_tunnel(char *act_data, int act_len)
 }
 
 static int
-nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
+nfp_fl_push_geneve_options(struct nfp_fl_payload *nfp_fl, int *list_len,
+			   const struct tc_action *action)
+{
+	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	int opt_len, opt_cnt, act_start, tot_push_len;
+	u8 *src = ip_tunnel_info_opts(ip_tun);
+
+	/* We need to populate the options in reverse order for HW.
+	 * Therefore we go through the options, calculating the
+	 * number of options and the total size, then we populate
+	 * them in reverse order in the action list.
+	 */
+	opt_cnt = 0;
+	tot_push_len = 0;
+	opt_len = ip_tun->options_len;
+	while (opt_len > 0) {
+		struct geneve_opt *opt = (struct geneve_opt *)src;
+
+		opt_cnt++;
+		if (opt_cnt > NFP_FL_MAX_GENEVE_OPT_CNT)
+			return -EOPNOTSUPP;
+
+		tot_push_len += sizeof(struct nfp_fl_push_geneve) +
+			       opt->length * 4;
+		if (tot_push_len > NFP_FL_MAX_GENEVE_OPT_ACT)
+			return -EOPNOTSUPP;
+
+		opt_len -= sizeof(struct geneve_opt) + opt->length * 4;
+		src += sizeof(struct geneve_opt) + opt->length * 4;
+	}
+
+	if (*list_len + tot_push_len > NFP_FL_MAX_A_SIZ)
+		return -EOPNOTSUPP;
+
+	act_start = *list_len;
+	*list_len += tot_push_len;
+	src = ip_tunnel_info_opts(ip_tun);
+	while (opt_cnt) {
+		struct geneve_opt *opt = (struct geneve_opt *)src;
+		struct nfp_fl_push_geneve *push;
+		size_t act_size, len;
+
+		opt_cnt--;
+		act_size = sizeof(struct nfp_fl_push_geneve) + opt->length * 4;
+		tot_push_len -= act_size;
+		len = act_start + tot_push_len;
+
+		push = (struct nfp_fl_push_geneve *)&nfp_fl->action_data[len];
+		push->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_GENEVE;
+		push->head.len_lw = act_size >> NFP_FL_LW_SIZ;
+		push->reserved = 0;
+		push->class = opt->opt_class;
+		push->type = opt->type;
+		push->length = opt->length;
+		memcpy(&push->opt_data, opt->opt_data, opt->length * 4);
+
+		src += sizeof(struct geneve_opt) + opt->length * 4;
+	}
+
+	return 0;
+}
+
+static int
+nfp_fl_set_ipv4_udp_tun(struct nfp_app *app,
+			struct nfp_fl_set_ipv4_udp_tun *set_tun,
 			const struct tc_action *action,
 			struct nfp_fl_pre_tunnel *pre_tun,
 			enum nfp_flower_tun_type tun_type,
@@ -237,11 +310,17 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 {
 	size_t act_size = sizeof(struct nfp_fl_set_ipv4_udp_tun);
 	struct ip_tunnel_info *ip_tun = tcf_tunnel_info(action);
+	struct nfp_flower_priv *priv = app->priv;
 	u32 tmp_set_ip_tun_type_index = 0;
 	/* Currently support one pre-tunnel so index is always 0. */
 	int pretun_idx = 0;
 
-	if (ip_tun->options_len)
+	BUILD_BUG_ON(NFP_FL_TUNNEL_CSUM != TUNNEL_CSUM ||
+		     NFP_FL_TUNNEL_KEY	!= TUNNEL_KEY ||
+		     NFP_FL_TUNNEL_GENEVE_OPT != TUNNEL_GENEVE_OPT);
+	if (ip_tun->options_len &&
+	    (tun_type != NFP_FL_TUNNEL_GENEVE ||
+	    !(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT)))
 		return -EOPNOTSUPP;
 
 	set_tun->head.jump_id = NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL;
@@ -281,11 +360,16 @@ nfp_fl_set_ipv4_udp_tun(struct nfp_fl_set_ipv4_udp_tun *set_tun,
 
 	set_tun->tos = ip_tun->key.tos;
 
-	if (!(ip_tun->key.tun_flags & TUNNEL_KEY) ||
+	if (!(ip_tun->key.tun_flags & NFP_FL_TUNNEL_KEY) ||
 	    ip_tun->key.tun_flags & ~NFP_FL_SUPPORTED_IPV4_UDP_TUN_FLAGS)
 		return -EOPNOTSUPP;
 	set_tun->tun_flags = ip_tun->key.tun_flags;
 
+	if (tun_type == NFP_FL_TUNNEL_GENEVE) {
+		set_tun->tun_proto = htons(ETH_P_TEB);
+		set_tun->tun_len = ip_tun->options_len / 4;
+	}
+
 	/* Complete pre_tunnel action. */
 	pre_tun->ipv4_dst = ip_tun->key.u.ipv4.dst;
 
@@ -674,9 +758,13 @@ nfp_flower_loop_action(struct nfp_app *app, const struct tc_action *a,
 		nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL);
 		*a_len += sizeof(struct nfp_fl_pre_tunnel);
 
+		err = nfp_fl_push_geneve_options(nfp_fl, a_len, a);
+		if (err)
+			return err;
+
 		set_tun = (void *)&nfp_fl->action_data[*a_len];
-		err = nfp_fl_set_ipv4_udp_tun(set_tun, a, pre_tun, *tun_type,
-					      netdev);
+		err = nfp_fl_set_ipv4_udp_tun(app, set_tun, a, pre_tun,
+					      *tun_type, netdev);
 		if (err)
 			return err;
 		*a_len += sizeof(struct nfp_fl_set_ipv4_udp_tun);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index 174acecfba01..f2aeae88cbf0 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -37,6 +37,7 @@
 #include <linux/bitfield.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
+#include <net/geneve.h>
 
 #include "../nfp_app.h"
 #include "../nfpcore/nfp_cpp.h"
@@ -81,6 +82,10 @@
 #define NFP_FL_MAX_A_SIZ		1216
 #define NFP_FL_LW_SIZ			2
 
+/* Maximum allowed geneve options */
+#define NFP_FL_MAX_GENEVE_OPT_ACT	32
+#define NFP_FL_MAX_GENEVE_OPT_CNT	64
+
 /* Action opcodes */
 #define NFP_FL_ACTION_OPCODE_OUTPUT		0
 #define NFP_FL_ACTION_OPCODE_PUSH_VLAN		1
@@ -94,6 +99,7 @@
 #define NFP_FL_ACTION_OPCODE_SET_TCP		15
 #define NFP_FL_ACTION_OPCODE_PRE_LAG		16
 #define NFP_FL_ACTION_OPCODE_PRE_TUNNEL		17
+#define NFP_FL_ACTION_OPCODE_PUSH_GENEVE	26
 #define NFP_FL_ACTION_OPCODE_NUM		32
 
 #define NFP_FL_OUT_FLAGS_LAST		BIT(15)
@@ -206,7 +212,19 @@ struct nfp_fl_set_ipv4_udp_tun {
 	__be16 tun_flags;
 	u8 ttl;
 	u8 tos;
-	__be32 extra[2];
+	__be32 extra;
+	u8 tun_len;
+	u8 res2;
+	__be16 tun_proto;
+};
+
+struct nfp_fl_push_geneve {
+	struct nfp_fl_act_head head;
+	__be16 reserved;
+	__be16 class;
+	u8 type;
+	u8 length;
+	u8 opt_data[];
 };
 
 /* Metadata with L2 (1W/4B)
diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h
index ef2114d13387..85f8209bf007 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/main.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/main.h
@@ -69,6 +69,7 @@ struct nfp_app;
 /* Extra features bitmap. */
 #define NFP_FL_FEATS_GENEVE		BIT(0)
 #define NFP_FL_NBI_MTU_SETTING		BIT(1)
+#define NFP_FL_FEATS_GENEVE_OPT		BIT(2)
 #define NFP_FL_FEATS_LAG		BIT(31)
 
 struct nfp_fl_mask_id {
-- 
cgit v1.2.3


From 0a22b17a6b1ddb161fae7452faa892ba4d77ebe9 Mon Sep 17 00:00:00 2001
From: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Date: Tue, 7 Aug 2018 17:36:03 +0200
Subject: nfp: flower: add geneve option match offload

Introduce a new layer for matching on geneve options. This allows
offloading filters configured to match geneve with options.

Signed-off-by: Pieter Jansen van Vuuren <pieter.jansenvanvuuren@netronome.com>
Signed-off-by: Simon Horman <simon.horman@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/flower/cmsg.h   |  6 ++++
 drivers/net/ethernet/netronome/nfp/flower/match.c  | 25 ++++++++++++++
 .../net/ethernet/netronome/nfp/flower/offload.c    | 38 ++++++++++++++++++++++
 3 files changed, 69 insertions(+)

diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
index f2aeae88cbf0..325954b829c8 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
+++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h
@@ -52,6 +52,7 @@
 #define NFP_FLOWER_LAYER_VXLAN		BIT(7)
 
 #define NFP_FLOWER_LAYER2_GENEVE	BIT(5)
+#define NFP_FLOWER_LAYER2_GENEVE_OP	BIT(6)
 
 #define NFP_FLOWER_MASK_VLAN_PRIO	GENMASK(15, 13)
 #define NFP_FLOWER_MASK_VLAN_CFI	BIT(12)
@@ -85,6 +86,7 @@
 /* Maximum allowed geneve options */
 #define NFP_FL_MAX_GENEVE_OPT_ACT	32
 #define NFP_FL_MAX_GENEVE_OPT_CNT	64
+#define NFP_FL_MAX_GENEVE_OPT_KEY	32
 
 /* Action opcodes */
 #define NFP_FL_ACTION_OPCODE_OUTPUT		0
@@ -381,6 +383,10 @@ struct nfp_flower_ipv4_udp_tun {
 	__be32 tun_id;
 };
 
+struct nfp_flower_geneve_options {
+	u8 data[NFP_FL_MAX_GENEVE_OPT_KEY];
+};
+
 #define NFP_FL_TUN_VNI_OFFSET 8
 
 /* The base header for a control message packet.
diff --git a/drivers/net/ethernet/netronome/nfp/flower/match.c b/drivers/net/ethernet/netronome/nfp/flower/match.c
index b1cbe6927cba..a0c72f277faa 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/match.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/match.c
@@ -262,6 +262,21 @@ nfp_flower_compile_ipv6(struct nfp_flower_ipv6 *frame,
 	nfp_flower_compile_ip_ext(&frame->ip_ext, flow, mask_version);
 }
 
+static int
+nfp_flower_compile_geneve_opt(void *key_buf, struct tc_cls_flower_offload *flow,
+			      bool mask_version)
+{
+	struct fl_flow_key *target = mask_version ? flow->mask : flow->key;
+	struct flow_dissector_key_enc_opts *opts;
+
+	opts = skb_flow_dissector_target(flow->dissector,
+					 FLOW_DISSECTOR_KEY_ENC_OPTS,
+					 target);
+	memcpy(key_buf, opts->data, opts->len);
+
+	return 0;
+}
+
 static void
 nfp_flower_compile_ipv4_udp_tun(struct nfp_flower_ipv4_udp_tun *frame,
 				struct tc_cls_flower_offload *flow,
@@ -424,6 +439,16 @@ int nfp_flower_compile_flow_match(struct tc_cls_flower_offload *flow,
 			nfp_flow->nfp_tun_ipv4_addr = tun_dst;
 			nfp_tunnel_add_ipv4_off(netdev_repr->app, tun_dst);
 		}
+
+		if (key_ls->key_layer_two & NFP_FLOWER_LAYER2_GENEVE_OP) {
+			err = nfp_flower_compile_geneve_opt(ext, flow, false);
+			if (err)
+				return err;
+
+			err = nfp_flower_compile_geneve_opt(msk, flow, true);
+			if (err)
+				return err;
+		}
 	}
 
 	return 0;
diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c
index d2230a0e49b9..2edab01c3beb 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/offload.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c
@@ -66,6 +66,7 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_CONTROL) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IP) | \
 	 BIT(FLOW_DISSECTOR_KEY_MPLS) | \
 	 BIT(FLOW_DISSECTOR_KEY_IP))
@@ -75,6 +76,7 @@
 	 BIT(FLOW_DISSECTOR_KEY_ENC_KEYID) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS) | \
+	 BIT(FLOW_DISSECTOR_KEY_ENC_OPTS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_PORTS) | \
 	 BIT(FLOW_DISSECTOR_KEY_ENC_IP))
 
@@ -140,6 +142,21 @@ static bool nfp_flower_check_higher_than_mac(struct tc_cls_flower_offload *f)
 		dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ICMP);
 }
 
+static int
+nfp_flower_calc_opt_layer(struct flow_dissector_key_enc_opts *enc_opts,
+			  u32 *key_layer_two, int *key_size)
+{
+	if (enc_opts->len > NFP_FL_MAX_GENEVE_OPT_KEY)
+		return -EOPNOTSUPP;
+
+	if (enc_opts->len > 0) {
+		*key_layer_two |= NFP_FLOWER_LAYER2_GENEVE_OP;
+		*key_size += sizeof(struct nfp_flower_geneve_options);
+	}
+
+	return 0;
+}
+
 static int
 nfp_flower_calculate_key_layers(struct nfp_app *app,
 				struct nfp_fl_key_ls *ret_key_ls,
@@ -153,6 +170,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 	u32 key_layer_two;
 	u8 key_layer;
 	int key_size;
+	int err;
 
 	if (flow->dissector->used_keys & ~NFP_FLOWER_WHITELIST_DISSECTOR)
 		return -EOPNOTSUPP;
@@ -178,6 +196,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			       FLOW_DISSECTOR_KEY_ENC_CONTROL)) {
 		struct flow_dissector_key_ipv4_addrs *mask_ipv4 = NULL;
 		struct flow_dissector_key_ports *mask_enc_ports = NULL;
+		struct flow_dissector_key_enc_opts *enc_op = NULL;
 		struct flow_dissector_key_ports *enc_ports = NULL;
 		struct flow_dissector_key_control *mask_enc_ctl =
 			skb_flow_dissector_target(flow->dissector,
@@ -214,11 +233,21 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 		if (mask_enc_ports->dst != cpu_to_be16(~0))
 			return -EOPNOTSUPP;
 
+		if (dissector_uses_key(flow->dissector,
+				       FLOW_DISSECTOR_KEY_ENC_OPTS)) {
+			enc_op = skb_flow_dissector_target(flow->dissector,
+							   FLOW_DISSECTOR_KEY_ENC_OPTS,
+							   flow->key);
+		}
+
 		switch (enc_ports->dst) {
 		case htons(NFP_FL_VXLAN_PORT):
 			*tun_type = NFP_FL_TUNNEL_VXLAN;
 			key_layer |= NFP_FLOWER_LAYER_VXLAN;
 			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+
+			if (enc_op)
+				return -EOPNOTSUPP;
 			break;
 		case htons(NFP_FL_GENEVE_PORT):
 			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE))
@@ -228,6 +257,15 @@ nfp_flower_calculate_key_layers(struct nfp_app *app,
 			key_size += sizeof(struct nfp_flower_ext_meta);
 			key_layer_two |= NFP_FLOWER_LAYER2_GENEVE;
 			key_size += sizeof(struct nfp_flower_ipv4_udp_tun);
+
+			if (!enc_op)
+				break;
+			if (!(priv->flower_ext_feats & NFP_FL_FEATS_GENEVE_OPT))
+				return -EOPNOTSUPP;
+			err = nfp_flower_calc_opt_layer(enc_op, &key_layer_two,
+							&key_size);
+			if (err)
+				return err;
 			break;
 		default:
 			return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 1f3a8f5f7ac3de4abae9d2c118ffaeed1676fe1c Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 1 Aug 2018 09:26:12 +1000
Subject: cifs: make smb_send_rqst take an array of requests

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/transport.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 8039c93ba57a..169e767ff57f 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -374,10 +374,11 @@ smbd_done:
 	return rc;
 }
 
-#define MAX_COMPOUND 2
+#define MAX_COMPOUND 5
 
 static int
-smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
+smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
+	      struct smb_rqst *rqst, int flags)
 {
 	struct kvec iov;
 	struct smb2_transform_hdr tr_hdr;
@@ -385,7 +386,10 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
 	int rc;
 
 	if (!(flags & CIFS_TRANSFORM_REQ))
-		return __smb_send_rqst(server, 1, rqst);
+		return __smb_send_rqst(server, num_rqst, rqst);
+
+	if (num_rqst > MAX_COMPOUND - 1)
+		return -ENOMEM;
 
 	memset(&cur_rqst[0], 0, sizeof(cur_rqst));
 	memset(&iov, 0, sizeof(iov));
@@ -402,12 +406,13 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
 		return -EIO;
 	}
 
-	rc = server->ops->init_transform_rq(server, 2, &cur_rqst[0], rqst);
+	rc = server->ops->init_transform_rq(server, num_rqst + 1,
+					    &cur_rqst[0], rqst);
 	if (rc)
 		return rc;
 
-	rc = __smb_send_rqst(server, 2, &cur_rqst[0]);
-	smb3_free_compound_rqst(1, &cur_rqst[1]);
+	rc = __smb_send_rqst(server, num_rqst + 1, &cur_rqst[0]);
+	smb3_free_compound_rqst(num_rqst, &cur_rqst[1]);
 	return rc;
 }
 
@@ -621,7 +626,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	 */
 	cifs_save_when_sent(mid);
 	cifs_in_send_inc(server);
-	rc = smb_send_rqst(server, rqst, flags);
+	rc = smb_send_rqst(server, 1, rqst, flags);
 	cifs_in_send_dec(server);
 
 	if (rc < 0) {
@@ -811,7 +816,7 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 
 	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_send_rqst(ses->server, rqst, flags);
+	rc = smb_send_rqst(ses->server, 1, rqst, flags);
 	cifs_in_send_dec(ses->server);
 	cifs_save_when_sent(midQ);
 
-- 
cgit v1.2.3


From e0bba0b8548179b696e86c158ea8f45f2ef6ad14 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 1 Aug 2018 09:26:13 +1000
Subject: cifs: add compound_send_recv()

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/cifsproto.h |   4 ++
 fs/cifs/transport.c | 156 ++++++++++++++++++++++++++++++----------------------
 2 files changed, 94 insertions(+), 66 deletions(-)

diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index 7ead1a9ac6fb..20adda4de83b 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -94,6 +94,10 @@ extern int cifs_call_async(struct TCP_Server_Info *server,
 extern int cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 			  struct smb_rqst *rqst, int *resp_buf_type,
 			  const int flags, struct kvec *resp_iov);
+extern int compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
+			      const int flags, const int num_rqst,
+			      struct smb_rqst *rqst, int *resp_buf_type,
+			      struct kvec *resp_iov);
 extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
 			struct smb_hdr * /* input */ ,
 			struct smb_hdr * /* out */ ,
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 169e767ff57f..0b9d0e859f86 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -766,20 +766,21 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 }
 
 int
-cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
-	       struct smb_rqst *rqst, int *resp_buf_type, const int flags,
-	       struct kvec *resp_iov)
+compound_send_recv(const unsigned int xid, struct cifs_ses *ses,
+		   const int flags, const int num_rqst, struct smb_rqst *rqst,
+		   int *resp_buf_type, struct kvec *resp_iov)
 {
-	int rc = 0;
+	int i, j, rc = 0;
 	int timeout, optype;
-	struct mid_q_entry *midQ;
+	struct mid_q_entry *midQ[MAX_COMPOUND];
 	unsigned int credits = 1;
 	char *buf;
 
 	timeout = flags & CIFS_TIMEOUT_MASK;
 	optype = flags & CIFS_OP_MASK;
 
-	*resp_buf_type = CIFS_NO_BUFFER;  /* no response buf yet */
+	for (i = 0; i < num_rqst; i++)
+		resp_buf_type[i] = CIFS_NO_BUFFER;  /* no response buf yet */
 
 	if ((ses == NULL) || (ses->server == NULL)) {
 		cifs_dbg(VFS, "Null session\n");
@@ -806,93 +807,116 @@ cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
 
 	mutex_lock(&ses->server->srv_mutex);
 
-	midQ = ses->server->ops->setup_request(ses, rqst);
-	if (IS_ERR(midQ)) {
-		mutex_unlock(&ses->server->srv_mutex);
-		/* Update # of requests on wire to server */
-		add_credits(ses->server, 1, optype);
-		return PTR_ERR(midQ);
+	for (i = 0; i < num_rqst; i++) {
+		midQ[i] = ses->server->ops->setup_request(ses, &rqst[i]);
+		if (IS_ERR(midQ[i])) {
+			for (j = 0; j < i; j++)
+				cifs_delete_mid(midQ[j]);
+			mutex_unlock(&ses->server->srv_mutex);
+			/* Update # of requests on wire to server */
+			add_credits(ses->server, 1, optype);
+			return PTR_ERR(midQ[i]);
+		}
+
+		midQ[i]->mid_state = MID_REQUEST_SUBMITTED;
 	}
 
-	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_send_rqst(ses->server, 1, rqst, flags);
+	rc = smb_send_rqst(ses->server, num_rqst, rqst, flags);
 	cifs_in_send_dec(ses->server);
-	cifs_save_when_sent(midQ);
+
+	for (i = 0; i < num_rqst; i++)
+		cifs_save_when_sent(midQ[i]);
 
 	if (rc < 0)
 		ses->server->sequence_number -= 2;
+
 	mutex_unlock(&ses->server->srv_mutex);
 
-	if (rc < 0)
-		goto out;
+	for (i = 0; i < num_rqst; i++) {
+		if (rc < 0)
+			goto out;
 
-	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
-		smb311_update_preauth_hash(ses, rqst->rq_iov,
-					   rqst->rq_nvec);
+		if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP))
+			smb311_update_preauth_hash(ses, rqst[i].rq_iov,
+						   rqst[i].rq_nvec);
 
-	if (timeout == CIFS_ASYNC_OP)
-		goto out;
+		if (timeout == CIFS_ASYNC_OP)
+			goto out;
 
-	rc = wait_for_response(ses->server, midQ);
-	if (rc != 0) {
-		cifs_dbg(FYI, "Cancelling wait for mid %llu\n",	midQ->mid);
-		send_cancel(ses->server, rqst, midQ);
-		spin_lock(&GlobalMid_Lock);
-		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
-			midQ->mid_flags |= MID_WAIT_CANCELLED;
-			midQ->callback = DeleteMidQEntry;
+		rc = wait_for_response(ses->server, midQ[i]);
+		if (rc != 0) {
+			cifs_dbg(FYI, "Cancelling wait for mid %llu\n",
+				 midQ[i]->mid);
+			send_cancel(ses->server, &rqst[i], midQ[i]);
+			spin_lock(&GlobalMid_Lock);
+			if (midQ[i]->mid_state == MID_REQUEST_SUBMITTED) {
+				midQ[i]->mid_flags |= MID_WAIT_CANCELLED;
+				midQ[i]->callback = DeleteMidQEntry;
+				spin_unlock(&GlobalMid_Lock);
+				add_credits(ses->server, 1, optype);
+				return rc;
+			}
 			spin_unlock(&GlobalMid_Lock);
+		}
+
+		rc = cifs_sync_mid_result(midQ[i], ses->server);
+		if (rc != 0) {
 			add_credits(ses->server, 1, optype);
 			return rc;
 		}
-		spin_unlock(&GlobalMid_Lock);
-	}
-
-	rc = cifs_sync_mid_result(midQ, ses->server);
-	if (rc != 0) {
-		add_credits(ses->server, 1, optype);
-		return rc;
-	}
 
-	if (!midQ->resp_buf || midQ->mid_state != MID_RESPONSE_RECEIVED) {
-		rc = -EIO;
-		cifs_dbg(FYI, "Bad MID state?\n");
-		goto out;
-	}
-
-	buf = (char *)midQ->resp_buf;
-	resp_iov->iov_base = buf;
-	resp_iov->iov_len = midQ->resp_buf_size +
-		ses->server->vals->header_preamble_size;
-	if (midQ->large_buf)
-		*resp_buf_type = CIFS_LARGE_BUFFER;
-	else
-		*resp_buf_type = CIFS_SMALL_BUFFER;
+		if (!midQ[i]->resp_buf ||
+		    midQ[i]->mid_state != MID_RESPONSE_RECEIVED) {
+			rc = -EIO;
+			cifs_dbg(FYI, "Bad MID state?\n");
+			goto out;
+		}
 
-	if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
-		struct kvec iov = {
-			.iov_base = resp_iov->iov_base,
-			.iov_len = resp_iov->iov_len
-		};
-		smb311_update_preauth_hash(ses, &iov, 1);
-	}
+		buf = (char *)midQ[i]->resp_buf;
+		resp_iov[i].iov_base = buf;
+		resp_iov[i].iov_len = midQ[i]->resp_buf_size +
+			ses->server->vals->header_preamble_size;
+
+		if (midQ[i]->large_buf)
+			resp_buf_type[i] = CIFS_LARGE_BUFFER;
+		else
+			resp_buf_type[i] = CIFS_SMALL_BUFFER;
+
+		if ((ses->status == CifsNew) || (optype & CIFS_NEG_OP)) {
+			struct kvec iov = {
+				.iov_base = resp_iov[i].iov_base,
+				.iov_len = resp_iov[i].iov_len
+			};
+			smb311_update_preauth_hash(ses, &iov, 1);
+		}
 
-	credits = ses->server->ops->get_credits(midQ);
+		credits = ses->server->ops->get_credits(midQ[i]);
 
-	rc = ses->server->ops->check_receive(midQ, ses->server,
-					     flags & CIFS_LOG_ERROR);
+		rc = ses->server->ops->check_receive(midQ[i], ses->server,
+						     flags & CIFS_LOG_ERROR);
 
-	/* mark it so buf will not be freed by cifs_delete_mid */
-	if ((flags & CIFS_NO_RESP) == 0)
-		midQ->resp_buf = NULL;
+		/* mark it so buf will not be freed by cifs_delete_mid */
+		if ((flags & CIFS_NO_RESP) == 0)
+			midQ[i]->resp_buf = NULL;
+	}
 out:
-	cifs_delete_mid(midQ);
+	for (i = 0; i < num_rqst; i++)
+		cifs_delete_mid(midQ[i]);
 	add_credits(ses->server, credits, optype);
 
 	return rc;
 }
 
+int
+cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
+	       struct smb_rqst *rqst, int *resp_buf_type, const int flags,
+	       struct kvec *resp_iov)
+{
+	return compound_send_recv(xid, ses, flags, 1, rqst, resp_buf_type,
+				  resp_iov);
+}
+
 int
 SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	     struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
-- 
cgit v1.2.3


From 020eec5f712ffb4254233490076cc21600b810db Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 1 Aug 2018 16:38:07 -0500
Subject: smb3: add tracepoint for slow responses

If responses take longer than one second from the server,
we can optionally log them to dmesg in current cifs.ko code
(CONFIG_CIFS_STATS2 must be configured and a
/proc/fs/cifs/cifsFYI flag must be set), but can be more useful
to log these via ftrace (tracepoint is smb3_slow_rsp) which
is easier and more granular (still requires CONFIG_CIFS_STATS2
to be configured in the build though).

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/trace.h     | 37 +++++++++++++++++++++++++++++++++++++
 fs/cifs/transport.c |  8 ++++++--
 2 files changed, 43 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/trace.h b/fs/cifs/trace.h
index 6b50b57e2416..d4aed5217a56 100644
--- a/fs/cifs/trace.h
+++ b/fs/cifs/trace.h
@@ -283,6 +283,43 @@ DEFINE_EVENT(smb3_cmd_done_class, smb3_##name,    \
 DEFINE_SMB3_CMD_DONE_EVENT(cmd_done);
 DEFINE_SMB3_CMD_DONE_EVENT(ses_expired);
 
+DECLARE_EVENT_CLASS(smb3_mid_class,
+	TP_PROTO(__u16	cmd,
+		__u64	mid,
+		__u32	pid,
+		unsigned long when_sent,
+		unsigned long when_received),
+	TP_ARGS(cmd, mid, pid, when_sent, when_received),
+	TP_STRUCT__entry(
+		__field(__u16, cmd)
+		__field(__u64, mid)
+		__field(__u32, pid)
+		__field(unsigned long, when_sent)
+		__field(unsigned long, when_received)
+	),
+	TP_fast_assign(
+		__entry->cmd = cmd;
+		__entry->mid = mid;
+		__entry->pid = pid;
+		__entry->when_sent = when_sent;
+		__entry->when_received = when_received;
+	),
+	TP_printk("\tcmd=%u mid=%llu pid=%u, when_sent=%lu when_rcv=%lu",
+		__entry->cmd, __entry->mid, __entry->pid, __entry->when_sent,
+		__entry->when_received)
+)
+
+#define DEFINE_SMB3_MID_EVENT(name)          \
+DEFINE_EVENT(smb3_mid_class, smb3_##name,    \
+	TP_PROTO(__u16	cmd,			\
+		__u64	mid,			\
+		__u32	pid,			\
+		unsigned long when_sent,	\
+		unsigned long when_received),	\
+	TP_ARGS(cmd, mid, pid, when_sent, when_received))
+
+DEFINE_SMB3_MID_EVENT(slow_rsp);
+
 DECLARE_EVENT_CLASS(smb3_exit_err_class,
 	TP_PROTO(unsigned int xid,
 		const char *func_name,
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 0b9d0e859f86..92de5c528161 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -115,8 +115,12 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 	now = jiffies;
 	/* commands taking longer than one second are indications that
 	   something is wrong, unless it is quite a slow link or server */
-	if (time_after(now, midEntry->when_alloc + HZ)) {
-		if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) {
+	if (time_after(now, midEntry->when_alloc + HZ) &&
+	    (midEntry->command != command)) {
+		trace_smb3_slow_rsp(le16_to_cpu(midEntry->command),
+			       midEntry->mid, midEntry->pid,
+			       midEntry->when_sent, midEntry->when_received);
+		if (cifsFYI & CIFS_TIMER) {
 			pr_debug(" CIFS slow rsp: cmd %d mid %llu",
 			       midEntry->command, midEntry->mid);
 			pr_info(" A: 0x%lx S: 0x%lx R: 0x%lx\n",
-- 
cgit v1.2.3


From d258650004617fbd5dfe97d77d26fb37187d06e9 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Wed, 1 Aug 2018 22:34:04 -0500
Subject: smb3: fix minor debug output for CONFIG_CIFS_STATS

CONFIG_CIFS_STATS is now always enabled (to simplify the
code and since the STATS are important for some common
customer use cases and also debugging), but needed one
minor change so that STATS shows as enabled in the debug
output in /proc/fs/cifs/DebugData, otherwise it could
get confusing with STATS no longer showing up in the
"Features" list in /proc/fs/cifs/DebugData when basic
stats were in fact available.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
---
 fs/cifs/cifs_debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index e074820bd4ed..748cabd6d20b 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -170,7 +170,7 @@ static int cifs_debug_data_proc_show(struct seq_file *m, void *v)
 #endif
 #ifdef CONFIG_CIFS_STATS2
 	seq_printf(m, ",STATS2");
-#elif defined(CONFIG_CIFS_STATS)
+#else
 	seq_printf(m, ",STATS");
 #endif
 #ifdef CONFIG_CIFS_DEBUG2
-- 
cgit v1.2.3


From fd09b7d3b352105f08b8e02f7afecf7e816380ef Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 2 Aug 2018 20:28:18 -0500
Subject: smb3: Do not send SMB3 SET_INFO if nothing changed

An earlier commit had a typo which prevented the
optimization from working:

commit 18dd8e1a65dd ("Do not send SMB3 SET_INFO request if nothing is changing")

Thank you to Metze for noticing this.  Also clear a
reserved field in the FILE_BASIC_INFO struct we send
that should be zero (all the other fields in that
struct were set or cleared explicitly already in
cifs_set_file_info).

Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
CC: Stable <stable@vger.kernel.org> # 4.9.x+
Reported-by: Stefan Metzmacher <metze@samba.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/inode.c     | 2 ++
 fs/cifs/smb2inode.c | 2 +-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 054e880c1dac..d32eaa4b2437 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1120,6 +1120,8 @@ cifs_set_file_info(struct inode *inode, struct iattr *attrs, unsigned int xid,
 	if (!server->ops->set_file_info)
 		return -ENOSYS;
 
+	info_buf.Pad = 0;
+
 	if (attrs->ia_valid & ATTR_ATIME) {
 		set_time = true;
 		info_buf.LastAccessTime =
diff --git a/fs/cifs/smb2inode.c b/fs/cifs/smb2inode.c
index f22cbc0d1869..1eef1791d0c4 100644
--- a/fs/cifs/smb2inode.c
+++ b/fs/cifs/smb2inode.c
@@ -283,7 +283,7 @@ smb2_set_file_info(struct inode *inode, const char *full_path,
 	int rc;
 
 	if ((buf->CreationTime == 0) && (buf->LastAccessTime == 0) &&
-	    (buf->LastWriteTime == 0) && (buf->ChangeTime) &&
+	    (buf->LastWriteTime == 0) && (buf->ChangeTime == 0) &&
 	    (buf->Attributes == 0))
 		return 0; /* would be a no op, no sense sending this */
 
-- 
cgit v1.2.3


From a5c62f4833c2c8e6e0f35367b99b717b78f5c029 Mon Sep 17 00:00:00 2001
From: Aurelien Aptel <aaptel@suse.com>
Date: Thu, 2 Aug 2018 16:39:52 +0200
Subject: CIFS: fix uninitialized ptr deref in smb2 signing

server->secmech.sdeschmacsha256 is not properly initialized before
smb2_shash_allocate(), set shash after that call.

also fix typo in error message

Fixes: 8de8c4608fe9 ("cifs: Fix validation of signed data in smb2")

Signed-off-by: Aurelien Aptel <aaptel@suse.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.com>
Reported-by: Xiaoli Feng <xifeng@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
CC: Stable <stable@vger.kernel.org>
---
 fs/cifs/smb2transport.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index 3f778937c0e2..7b351c65ee46 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -171,7 +171,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	struct kvec *iov = rqst->rq_iov;
 	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[0].iov_base;
 	struct cifs_ses *ses;
-	struct shash_desc *shash = &server->secmech.sdeschmacsha256->shash;
+	struct shash_desc *shash;
 	struct smb_rqst drqst;
 
 	ses = smb2_find_smb_ses(server, shdr->SessionId);
@@ -185,7 +185,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 
 	rc = smb2_crypto_shash_allocate(server);
 	if (rc) {
-		cifs_dbg(VFS, "%s: shah256 alloc failed\n", __func__);
+		cifs_dbg(VFS, "%s: sha256 alloc failed\n", __func__);
 		return rc;
 	}
 
@@ -196,6 +196,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 		return rc;
 	}
 
+	shash = &server->secmech.sdeschmacsha256->shash;
 	rc = crypto_shash_init(shash);
 	if (rc) {
 		cifs_dbg(VFS, "%s: Could not init sha256", __func__);
-- 
cgit v1.2.3


From 468d677954c0d94fec59275d91222257fe8b4416 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Sat, 4 Aug 2018 05:24:34 -0500
Subject: smb3: display stats counters for number of slow commands

When CONFIG_CIFS_STATS2 is enabled keep counters for slow
commands (ie server took longer than 1 second to respond)
by SMB2/SMB3 command code.  This can help in diagnosing
whether performance problems are on server (instead of
client) and which commands are causing the problem.

Sample output (the new lines contain words "slow responses ...")

$ cat /proc/fs/cifs/Stats
Resources in use
CIFS Session: 1
Share (unique mount targets): 2
SMB Request/Response Buffer: 1 Pool size: 5
SMB Small Req/Resp Buffer: 1 Pool size: 30
Total Large 10 Small 490 Allocations
Operations (MIDs): 0

0 session 0 share reconnects
Total vfs operations: 67 maximum at one time: 2
4 slow responses from localhost for command 5
1 slow responses from localhost for command 6
1 slow responses from localhost for command 14
1 slow responses from localhost for command 16

1) \\localhost\test
SMBs: 243
Bytes read: 1024000  Bytes written: 104857600
TreeConnects: 1 total 0 failed
TreeDisconnects: 0 total 0 failed
Creates: 40 total 0 failed
Closes: 39 total 0 failed
...

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Reviewed-by: Aurelien Aptel <aaptel@suse.com>
---
 fs/cifs/cifs_debug.c | 19 +++++++++++++++++--
 fs/cifs/cifsglob.h   |  3 ++-
 fs/cifs/transport.c  |  5 +++++
 3 files changed, 24 insertions(+), 3 deletions(-)

diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 748cabd6d20b..f1fbea947fef 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -378,6 +378,8 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 	rc = kstrtobool_from_user(buffer, count, &bv);
 	if (rc == 0) {
 #ifdef CONFIG_CIFS_STATS2
+		int i;
+
 		atomic_set(&totBufAllocCount, 0);
 		atomic_set(&totSmBufAllocCount, 0);
 #endif /* CONFIG_CIFS_STATS2 */
@@ -389,6 +391,10 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 		list_for_each(tmp1, &cifs_tcp_ses_list) {
 			server = list_entry(tmp1, struct TCP_Server_Info,
 					    tcp_ses_list);
+#ifdef CONFIG_CIFS_STATS2
+			for (i = 0; i < NUMBER_OF_SMB2_COMMANDS; i++)
+				atomic_set(&server->smb2slowcmd[i], 0);
+#endif /* CONFIG_CIFS_STATS2 */
 			list_for_each(tmp2, &server->smb_ses_list) {
 				ses = list_entry(tmp2, struct cifs_ses,
 						 smb_ses_list);
@@ -417,13 +423,15 @@ static ssize_t cifs_stats_proc_write(struct file *file,
 static int cifs_stats_proc_show(struct seq_file *m, void *v)
 {
 	int i;
+#ifdef CONFIG_CIFS_STATS2
+	int j;
+#endif /* STATS2 */
 	struct list_head *tmp1, *tmp2, *tmp3;
 	struct TCP_Server_Info *server;
 	struct cifs_ses *ses;
 	struct cifs_tcon *tcon;
 
-	seq_printf(m,
-			"Resources in use\nCIFS Session: %d\n",
+	seq_printf(m, "Resources in use\nCIFS Session: %d\n",
 			sesInfoAllocCount.counter);
 	seq_printf(m, "Share (unique mount targets): %d\n",
 			tconInfoAllocCount.counter);
@@ -452,6 +460,13 @@ static int cifs_stats_proc_show(struct seq_file *m, void *v)
 	list_for_each(tmp1, &cifs_tcp_ses_list) {
 		server = list_entry(tmp1, struct TCP_Server_Info,
 				    tcp_ses_list);
+#ifdef CONFIG_CIFS_STATS2
+		for (j = 0; j < NUMBER_OF_SMB2_COMMANDS; j++)
+			if (atomic_read(&server->smb2slowcmd[j]))
+				seq_printf(m, "%d slow responses from %s for command %d\n",
+					atomic_read(&server->smb2slowcmd[j]),
+					server->hostname, j);
+#endif /* STATS2 */
 		list_for_each(tmp2, &server->smb_ses_list) {
 			ses = list_entry(tmp2, struct cifs_ses,
 					 smb_ses_list);
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 0553929e8339..41803d374da0 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -680,7 +680,8 @@ struct TCP_Server_Info {
 #ifdef CONFIG_CIFS_STATS2
 	atomic_t in_send; /* requests trying to send */
 	atomic_t num_waiters;   /* blocked waiting to get in sendrecv */
-#endif
+	atomic_t smb2slowcmd[NUMBER_OF_SMB2_COMMANDS]; /* count resps > 1 sec */
+#endif /* STATS2 */
 	unsigned int	max_read;
 	unsigned int	max_write;
 	__le16	cipher_type;
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index 92de5c528161..c53c0908d4c6 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -117,6 +117,11 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 	   something is wrong, unless it is quite a slow link or server */
 	if (time_after(now, midEntry->when_alloc + HZ) &&
 	    (midEntry->command != command)) {
+		/* smb2slowcmd[NUMBER_OF_SMB2_COMMANDS] counts by command */
+		if ((le16_to_cpu(midEntry->command) < NUMBER_OF_SMB2_COMMANDS) &&
+		    (le16_to_cpu(midEntry->command) >= 0))
+			cifs_stats_inc(&midEntry->server->smb2slowcmd[le16_to_cpu(midEntry->command)]);
+
 		trace_smb3_slow_rsp(le16_to_cpu(midEntry->command),
 			       midEntry->mid, midEntry->pid,
 			       midEntry->when_sent, midEntry->when_received);
-- 
cgit v1.2.3


From 819731596aec45012ebc1185b4276a4a0bbc95ac Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Wed, 8 Aug 2018 01:52:47 +0800
Subject: dt-bindings: net: bluetooth: Add mediatek-bluetooth

Add binding document for a SoC built-in device using MediaTek protocol.
Which could be found on MT7622 SoC or other similar MediaTek SoCs.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 .../devicetree/bindings/net/mediatek-bluetooth.txt | 35 ++++++++++++++++++++++
 1 file changed, 35 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/mediatek-bluetooth.txt

diff --git a/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt b/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt
new file mode 100644
index 000000000000..14ceb2a5b4e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/mediatek-bluetooth.txt
@@ -0,0 +1,35 @@
+MediaTek SoC built-in Bluetooth Devices
+==================================
+
+This device is a serial attached device to BTIF device and thus it must be a
+child node of the serial node with BTIF. The dt-bindings details for BTIF
+device can be known via Documentation/devicetree/bindings/serial/8250.txt.
+
+Required properties:
+
+- compatible:	Must be
+		  "mediatek,mt7622-bluetooth": for MT7622 SoC
+- clocks:	Should be the clock specifiers corresponding to the entry in
+		clock-names property.
+- clock-names:	Should contain "ref" entries.
+- power-domains: Phandle to the power domain that the device is part of
+
+Example:
+
+	btif: serial@1100c000 {
+		compatible = "mediatek,mt7622-btif",
+			     "mediatek,mtk-btif";
+		reg = <0 0x1100c000 0 0x1000>;
+		interrupts = <GIC_SPI 90 IRQ_TYPE_LEVEL_LOW>;
+		clocks = <&pericfg CLK_PERI_BTIF_PD>;
+		clock-names = "main";
+		reg-shift = <2>;
+		reg-io-width = <4>;
+
+		bluetooth {
+			compatible = "mediatek,mt7622-bluetooth";
+			power-domains = <&scpsys MT7622_POWER_DOMAIN_WB>;
+			clocks = <&clk25m>;
+			clock-names = "ref";
+		};
+	};
-- 
cgit v1.2.3


From 7237c4c9ec92e1a4f6ef1f712bf9105d7b392c6a Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Wed, 8 Aug 2018 01:52:48 +0800
Subject: Bluetooth: mediatek: Add protocol support for MediaTek serial devices

This adds a driver based on serdev driver for the MediaTek serial protocol
based on running H:4, which can enable the built-in Bluetooth device inside
MT7622 SoC.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/Kconfig     |  11 +
 drivers/bluetooth/Makefile    |   1 +
 drivers/bluetooth/btmtkuart.c | 629 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 641 insertions(+)
 create mode 100644 drivers/bluetooth/btmtkuart.c

diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 5f953ca8ac5b..c3736103c2ac 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -365,6 +365,17 @@ config BT_WILINK
 	  Say Y here to compile support for Texas Instrument's WiLink7 driver
 	  into the kernel or say M to compile it as module (btwilink).
 
+config BT_MTKUART
+	tristate "MediaTek HCI UART driver"
+	depends on SERIAL_DEV_BUS
+	help
+	  MediaTek Bluetooth HCI UART driver.
+	  This driver is required if you want to use MediaTek Bluetooth
+	  with serial interface.
+
+	  Say Y here to compile support for MediaTek Bluetooth UART devices
+	  into the kernel or say M to compile it as module (btmtkuart).
+
 config BT_QCOMSMD
 	tristate "Qualcomm SMD based HCI support"
 	depends on RPMSG || (COMPILE_TEST && RPMSG=n)
diff --git a/drivers/bluetooth/Makefile b/drivers/bluetooth/Makefile
index ec16c55eb6e9..b7e393cfc1e3 100644
--- a/drivers/bluetooth/Makefile
+++ b/drivers/bluetooth/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_BT_ATH3K)		+= ath3k.o
 obj-$(CONFIG_BT_MRVL)		+= btmrvl.o
 obj-$(CONFIG_BT_MRVL_SDIO)	+= btmrvl_sdio.o
 obj-$(CONFIG_BT_WILINK)		+= btwilink.o
+obj-$(CONFIG_BT_MTKUART)	+= btmtkuart.o
 obj-$(CONFIG_BT_QCOMSMD)	+= btqcomsmd.o
 obj-$(CONFIG_BT_BCM)		+= btbcm.o
 obj-$(CONFIG_BT_RTL)		+= btrtl.o
diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
new file mode 100644
index 000000000000..e0571fe04d00
--- /dev/null
+++ b/drivers/bluetooth/btmtkuart.c
@@ -0,0 +1,629 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 MediaTek Inc.
+
+/*
+ * Bluetooth support for MediaTek serial devices
+ *
+ * Author: Sean Wang <sean.wang@mediatek.com>
+ *
+ */
+
+#include <asm/unaligned.h>
+#include <linux/atomic.h>
+#include <linux/clk.h>
+#include <linux/firmware.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pm_runtime.h>
+#include <linux/serdev.h>
+#include <linux/skbuff.h>
+
+#include <net/bluetooth/bluetooth.h>
+#include <net/bluetooth/hci_core.h>
+
+#include "h4_recv.h"
+
+#define VERSION "0.1"
+
+#define FIRMWARE_MT7622		"mediatek/mt7622pr2h.bin"
+
+#define MTK_STP_TLR_SIZE	2
+
+#define BTMTKUART_TX_STATE_ACTIVE	1
+#define BTMTKUART_TX_STATE_WAKEUP	2
+#define BTMTKUART_TX_WAIT_VND_EVT	3
+
+enum {
+	MTK_WMT_PATCH_DWNLD = 0x1,
+	MTK_WMT_FUNC_CTRL = 0x6,
+	MTK_WMT_RST = 0x7
+};
+
+struct mtk_stp_hdr {
+	u8	prefix;
+	__be16	dlen;
+	u8	cs;
+} __packed;
+
+struct mtk_wmt_hdr {
+	u8	dir;
+	u8	op;
+	__le16	dlen;
+	u8	flag;
+} __packed;
+
+struct mtk_hci_wmt_cmd {
+	struct mtk_wmt_hdr hdr;
+	u8 data[256];
+} __packed;
+
+struct btmtkuart_dev {
+	struct hci_dev *hdev;
+	struct serdev_device *serdev;
+	struct clk *clk;
+
+	struct work_struct tx_work;
+	unsigned long tx_state;
+	struct sk_buff_head txq;
+
+	struct sk_buff *rx_skb;
+
+	u8	stp_pad[6];
+	u8	stp_cursor;
+	u16	stp_dlen;
+};
+
+static int mtk_hci_wmt_sync(struct hci_dev *hdev, u8 op, u8 flag, u16 plen,
+			    const void *param)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct mtk_hci_wmt_cmd wc;
+	struct mtk_wmt_hdr *hdr;
+	u32 hlen;
+	int err;
+
+	hlen = sizeof(*hdr) + plen;
+	if (hlen > 255)
+		return -EINVAL;
+
+	hdr = (struct mtk_wmt_hdr *)&wc;
+	hdr->dir = 1;
+	hdr->op = op;
+	hdr->dlen = cpu_to_le16(plen + 1);
+	hdr->flag = flag;
+	memcpy(wc.data, param, plen);
+
+	set_bit(BTMTKUART_TX_WAIT_VND_EVT, &bdev->tx_state);
+
+	err = __hci_cmd_send(hdev, 0xfc6f, hlen, &wc);
+	if (err < 0) {
+		clear_bit(BTMTKUART_TX_WAIT_VND_EVT, &bdev->tx_state);
+		return err;
+	}
+
+	/* The vendor specific WMT commands are all answered by a vendor
+	 * specific event and will not have the Command Status or Command
+	 * Complete as with usual HCI command flow control.
+	 *
+	 * After sending the command, wait for BTMTKUART_TX_WAIT_VND_EVT
+	 * state to be cleared. The driver speicfic event receive routine
+	 * will clear that state and with that indicate completion of the
+	 * WMT command.
+	 */
+	err = wait_on_bit_timeout(&bdev->tx_state, BTMTKUART_TX_WAIT_VND_EVT,
+				  TASK_INTERRUPTIBLE, HCI_INIT_TIMEOUT);
+	if (err == -EINTR) {
+		bt_dev_err(hdev, "Execution of wmt command interrupted");
+		return err;
+	}
+
+	if (err) {
+		bt_dev_err(hdev, "Execution of wmt command timed out");
+		return -ETIMEDOUT;
+	}
+
+	return 0;
+}
+
+static int mtk_setup_fw(struct hci_dev *hdev)
+{
+	const struct firmware *fw;
+	const u8 *fw_ptr;
+	size_t fw_size;
+	int err, dlen;
+	u8 flag;
+
+	err = request_firmware(&fw, FIRMWARE_MT7622, &hdev->dev);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to load firmware file (%d)", err);
+		return err;
+	}
+
+	fw_ptr = fw->data;
+	fw_size = fw->size;
+
+	/* The size of patch header is 30 bytes, should be skip */
+	if (fw_size < 30)
+		return -EINVAL;
+
+	fw_size -= 30;
+	fw_ptr += 30;
+	flag = 1;
+
+	while (fw_size > 0) {
+		dlen = min_t(int, 250, fw_size);
+
+		/* Tell device the position in sequence */
+		if (fw_size - dlen <= 0)
+			flag = 3;
+		else if (fw_size < fw->size - 30)
+			flag = 2;
+
+		err = mtk_hci_wmt_sync(hdev, MTK_WMT_PATCH_DWNLD, flag, dlen,
+				       fw_ptr);
+		if (err < 0) {
+			bt_dev_err(hdev, "Failed to send wmt patch dwnld (%d)",
+				   err);
+			break;
+		}
+
+		fw_size -= dlen;
+		fw_ptr += dlen;
+	}
+
+	release_firmware(fw);
+
+	return err;
+}
+
+static int btmtkuart_recv_event(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct hci_event_hdr *hdr = (void *)skb->data;
+	int err;
+
+	/* Fix up the vendor event id with 0xff for vendor specific instead
+	 * of 0xe4 so that event send via monitoring socket can be parsed
+	 * properly.
+	 */
+	if (hdr->evt == 0xe4)
+		hdr->evt = HCI_EV_VENDOR;
+
+	err = hci_recv_frame(hdev, skb);
+
+	if (hdr->evt == HCI_EV_VENDOR) {
+		if (test_and_clear_bit(BTMTKUART_TX_WAIT_VND_EVT,
+				       &bdev->tx_state)) {
+			/* Barrier to sync with other CPUs */
+			smp_mb__after_atomic();
+			wake_up_bit(&bdev->tx_state, BTMTKUART_TX_WAIT_VND_EVT);
+		}
+	}
+
+	return err;
+}
+
+static const struct h4_recv_pkt mtk_recv_pkts[] = {
+	{ H4_RECV_ACL,      .recv = hci_recv_frame },
+	{ H4_RECV_SCO,      .recv = hci_recv_frame },
+	{ H4_RECV_EVENT,    .recv = btmtkuart_recv_event },
+};
+
+static void btmtkuart_tx_work(struct work_struct *work)
+{
+	struct btmtkuart_dev *bdev = container_of(work, struct btmtkuart_dev,
+						   tx_work);
+	struct serdev_device *serdev = bdev->serdev;
+	struct hci_dev *hdev = bdev->hdev;
+
+	while (1) {
+		clear_bit(BTMTKUART_TX_STATE_WAKEUP, &bdev->tx_state);
+
+		while (1) {
+			struct sk_buff *skb = skb_dequeue(&bdev->txq);
+			int len;
+
+			if (!skb)
+				break;
+
+			len = serdev_device_write_buf(serdev, skb->data,
+						      skb->len);
+			hdev->stat.byte_tx += len;
+
+			skb_pull(skb, len);
+			if (skb->len > 0) {
+				skb_queue_head(&bdev->txq, skb);
+				break;
+			}
+
+			switch (hci_skb_pkt_type(skb)) {
+			case HCI_COMMAND_PKT:
+				hdev->stat.cmd_tx++;
+				break;
+			case HCI_ACLDATA_PKT:
+				hdev->stat.acl_tx++;
+				break;
+			case HCI_SCODATA_PKT:
+				hdev->stat.sco_tx++;
+				break;
+			}
+
+			kfree_skb(skb);
+		}
+
+		if (!test_bit(BTMTKUART_TX_STATE_WAKEUP, &bdev->tx_state))
+			break;
+	}
+
+	clear_bit(BTMTKUART_TX_STATE_ACTIVE, &bdev->tx_state);
+}
+
+static void btmtkuart_tx_wakeup(struct btmtkuart_dev *bdev)
+{
+	if (test_and_set_bit(BTMTKUART_TX_STATE_ACTIVE, &bdev->tx_state))
+		set_bit(BTMTKUART_TX_STATE_WAKEUP, &bdev->tx_state);
+
+	schedule_work(&bdev->tx_work);
+}
+
+static const unsigned char *
+mtk_stp_split(struct btmtkuart_dev *bdev, const unsigned char *data, int count,
+	      int *sz_h4)
+{
+	struct mtk_stp_hdr *shdr;
+
+	/* The cursor is reset when all the data of STP is consumed out */
+	if (!bdev->stp_dlen && bdev->stp_cursor >= 6)
+		bdev->stp_cursor = 0;
+
+	/* Filling pad until all STP info is obtained */
+	while (bdev->stp_cursor < 6 && count > 0) {
+		bdev->stp_pad[bdev->stp_cursor] = *data;
+		bdev->stp_cursor++;
+		data++;
+		count--;
+	}
+
+	/* Retrieve STP info and have a sanity check */
+	if (!bdev->stp_dlen && bdev->stp_cursor >= 6) {
+		shdr = (struct mtk_stp_hdr *)&bdev->stp_pad[2];
+		bdev->stp_dlen = be16_to_cpu(shdr->dlen) & 0x0fff;
+
+		/* Resync STP when unexpected data is being read */
+		if (shdr->prefix != 0x80 || bdev->stp_dlen > 2048) {
+			bt_dev_err(bdev->hdev, "stp format unexpect (%d, %d)",
+				   shdr->prefix, bdev->stp_dlen);
+			bdev->stp_cursor = 2;
+			bdev->stp_dlen = 0;
+		}
+	}
+
+	/* Directly quit when there's no data found for H4 can process */
+	if (count <= 0)
+		return NULL;
+
+	/* Tranlate to how much the size of data H4 can handle so far */
+	*sz_h4 = min_t(int, count, bdev->stp_dlen);
+
+	/* Update the remaining size of STP packet */
+	bdev->stp_dlen -= *sz_h4;
+
+	/* Data points to STP payload which can be handled by H4 */
+	return data;
+}
+
+static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	const unsigned char *p_left = data, *p_h4;
+	int sz_left = count, sz_h4, adv;
+	int err;
+
+	while (sz_left > 0) {
+		/*  The serial data received from MT7622 BT controller is
+		 *  at all time padded around with the STP header and tailer.
+		 *
+		 *  A full STP packet is looking like
+		 *   -----------------------------------
+		 *  | STP header  |  H:4   | STP tailer |
+		 *   -----------------------------------
+		 *  but it doesn't guarantee to contain a full H:4 packet which
+		 *  means that it's possible for multiple STP packets forms a
+		 *  full H:4 packet that means extra STP header + length doesn't
+		 *  indicate a full H:4 frame, things can fragment. Whose length
+		 *  recorded in STP header just shows up the most length the
+		 *  H:4 engine can handle currently.
+		 */
+
+		p_h4 = mtk_stp_split(bdev, p_left, sz_left, &sz_h4);
+		if (!p_h4)
+			break;
+
+		adv = p_h4 - p_left;
+		sz_left -= adv;
+		p_left += adv;
+
+		bdev->rx_skb = h4_recv_buf(bdev->hdev, bdev->rx_skb, p_h4,
+					   sz_h4, mtk_recv_pkts,
+					   sizeof(mtk_recv_pkts));
+		if (IS_ERR(bdev->rx_skb)) {
+			err = PTR_ERR(bdev->rx_skb);
+			bt_dev_err(bdev->hdev,
+				   "Frame reassembly failed (%d)", err);
+			bdev->rx_skb = NULL;
+			return err;
+		}
+
+		sz_left -= sz_h4;
+		p_left += sz_h4;
+	}
+
+	return 0;
+}
+
+static int btmtkuart_receive_buf(struct serdev_device *serdev, const u8 *data,
+				 size_t count)
+{
+	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
+	int err;
+
+	err = btmtkuart_recv(bdev->hdev, data, count);
+	if (err < 0)
+		return err;
+
+	bdev->hdev->stat.byte_rx += count;
+
+	return count;
+}
+
+static void btmtkuart_write_wakeup(struct serdev_device *serdev)
+{
+	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
+
+	btmtkuart_tx_wakeup(bdev);
+}
+
+static const struct serdev_device_ops btmtkuart_client_ops = {
+	.receive_buf = btmtkuart_receive_buf,
+	.write_wakeup = btmtkuart_write_wakeup,
+};
+
+static int btmtkuart_open(struct hci_dev *hdev)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct device *dev;
+	int err;
+
+	err = serdev_device_open(bdev->serdev);
+	if (err) {
+		bt_dev_err(hdev, "Unable to open UART device %s",
+			   dev_name(&bdev->serdev->dev));
+		goto err_open;
+	}
+
+	bdev->stp_cursor = 2;
+	bdev->stp_dlen = 0;
+
+	dev = &bdev->serdev->dev;
+
+	/* Enable the power domain and clock the device requires */
+	pm_runtime_enable(dev);
+	err = pm_runtime_get_sync(dev);
+	if (err < 0) {
+		pm_runtime_put_noidle(dev);
+		goto err_disable_rpm;
+	}
+
+	err = clk_prepare_enable(bdev->clk);
+	if (err < 0)
+		goto err_put_rpm;
+
+	return 0;
+
+err_put_rpm:
+	pm_runtime_put_sync(dev);
+err_disable_rpm:
+	pm_runtime_disable(dev);
+err_open:
+	return err;
+}
+
+static int btmtkuart_close(struct hci_dev *hdev)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct device *dev = &bdev->serdev->dev;
+
+	/* Shutdown the clock and power domain the device requires */
+	clk_disable_unprepare(bdev->clk);
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+
+	serdev_device_close(bdev->serdev);
+
+	return 0;
+}
+
+static int btmtkuart_flush(struct hci_dev *hdev)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+
+	/* Flush any pending characters */
+	serdev_device_write_flush(bdev->serdev);
+	skb_queue_purge(&bdev->txq);
+
+	cancel_work_sync(&bdev->tx_work);
+
+	kfree_skb(bdev->rx_skb);
+	bdev->rx_skb = NULL;
+
+	bdev->stp_cursor = 2;
+	bdev->stp_dlen = 0;
+
+	return 0;
+}
+
+static int btmtkuart_setup(struct hci_dev *hdev)
+{
+	u8 param = 0x1;
+	int err = 0;
+
+	/* Setup a firmware which the device definitely requires */
+	err = mtk_setup_fw(hdev);
+	if (err < 0)
+		return err;
+
+	/* Activate function the firmware providing to */
+	err = mtk_hci_wmt_sync(hdev, MTK_WMT_RST, 0x4, 0, 0);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send wmt rst (%d)", err);
+		return err;
+	}
+
+	/* Enable Bluetooth protocol */
+	err = mtk_hci_wmt_sync(hdev, MTK_WMT_FUNC_CTRL, 0x0, sizeof(param),
+			       &param);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send wmt func ctrl (%d)", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int btmtkuart_shutdown(struct hci_dev *hdev)
+{
+	u8 param = 0x0;
+	int err;
+
+	/* Disable the device */
+	err = mtk_hci_wmt_sync(hdev, MTK_WMT_FUNC_CTRL, 0x0, sizeof(param),
+			       &param);
+	if (err < 0) {
+		bt_dev_err(hdev, "Failed to send wmt func ctrl (%d)", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static int btmtkuart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btmtkuart_dev *bdev = hci_get_drvdata(hdev);
+	struct mtk_stp_hdr *shdr;
+	int err, dlen, type = 0;
+
+	/* Prepend skb with frame type */
+	memcpy(skb_push(skb, 1), &hci_skb_pkt_type(skb), 1);
+
+	/* Make sure that there is enough rooms for STP header and trailer */
+	if (unlikely(skb_headroom(skb) < sizeof(*shdr)) ||
+	    (skb_tailroom(skb) < MTK_STP_TLR_SIZE)) {
+		err = pskb_expand_head(skb, sizeof(*shdr), MTK_STP_TLR_SIZE,
+				       GFP_ATOMIC);
+		if (err < 0)
+			return err;
+	}
+
+	/* Add the STP header */
+	dlen = skb->len;
+	shdr = skb_push(skb, sizeof(*shdr));
+	shdr->prefix = 0x80;
+	shdr->dlen = cpu_to_be16((dlen & 0x0fff) | (type << 12));
+	shdr->cs = 0;		/* MT7622 doesn't care about checksum value */
+
+	/* Add the STP trailer */
+	skb_put_zero(skb, MTK_STP_TLR_SIZE);
+
+	skb_queue_tail(&bdev->txq, skb);
+
+	btmtkuart_tx_wakeup(bdev);
+	return 0;
+}
+
+static int btmtkuart_probe(struct serdev_device *serdev)
+{
+	struct btmtkuart_dev *bdev;
+	struct hci_dev *hdev;
+
+	bdev = devm_kzalloc(&serdev->dev, sizeof(*bdev), GFP_KERNEL);
+	if (!bdev)
+		return -ENOMEM;
+
+	bdev->clk = devm_clk_get(&serdev->dev, "ref");
+	if (IS_ERR(bdev->clk))
+		return PTR_ERR(bdev->clk);
+
+	bdev->serdev = serdev;
+	serdev_device_set_drvdata(serdev, bdev);
+
+	serdev_device_set_client_ops(serdev, &btmtkuart_client_ops);
+
+	INIT_WORK(&bdev->tx_work, btmtkuart_tx_work);
+	skb_queue_head_init(&bdev->txq);
+
+	/* Initialize and register HCI device */
+	hdev = hci_alloc_dev();
+	if (!hdev) {
+		dev_err(&serdev->dev, "Can't allocate HCI device\n");
+		return -ENOMEM;
+	}
+
+	bdev->hdev = hdev;
+
+	hdev->bus = HCI_UART;
+	hci_set_drvdata(hdev, bdev);
+
+	hdev->open     = btmtkuart_open;
+	hdev->close    = btmtkuart_close;
+	hdev->flush    = btmtkuart_flush;
+	hdev->setup    = btmtkuart_setup;
+	hdev->shutdown = btmtkuart_shutdown;
+	hdev->send     = btmtkuart_send_frame;
+	SET_HCIDEV_DEV(hdev, &serdev->dev);
+
+	hdev->manufacturer = 70;
+	set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks);
+
+	if (hci_register_dev(hdev) < 0) {
+		dev_err(&serdev->dev, "Can't register HCI device\n");
+		hci_free_dev(hdev);
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static void btmtkuart_remove(struct serdev_device *serdev)
+{
+	struct btmtkuart_dev *bdev = serdev_device_get_drvdata(serdev);
+	struct hci_dev *hdev = bdev->hdev;
+
+	hci_unregister_dev(hdev);
+	hci_free_dev(hdev);
+}
+
+#ifdef CONFIG_OF
+static const struct of_device_id mtk_of_match_table[] = {
+	{ .compatible = "mediatek,mt7622-bluetooth"},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, mtk_of_match_table);
+#endif
+
+static struct serdev_device_driver btmtkuart_driver = {
+	.probe = btmtkuart_probe,
+	.remove = btmtkuart_remove,
+	.driver = {
+		.name = "btmtkuart",
+		.of_match_table = of_match_ptr(mtk_of_match_table),
+	},
+};
+
+module_serdev_device_driver(btmtkuart_driver);
+
+MODULE_AUTHOR("Sean Wang <sean.wang@mediatek.com>");
+MODULE_DESCRIPTION("MediaTek Bluetooth Serial driver ver " VERSION);
+MODULE_VERSION(VERSION);
+MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(FIRMWARE_MT7622);
-- 
cgit v1.2.3


From 9ca6163005e6abdf2a39eb581abc6060f677a2d7 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Mon, 6 Aug 2018 11:27:10 +0300
Subject: net: sched: cls_flower: set correct offload data in fl_reoffload

fl_reoffload implementation sets following members of struct
tc_cls_flower_offload incorrectly:
 - masked key instead of mask
 - key instead of masked key

Fix fl_reoffload to provide correct data to offload callback.

Fixes: 31533cba4327 ("net: sched: cls_flower: implement offload tcf_proto_op")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_flower.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9da244235170..6fd9bdd93796 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -1338,8 +1338,8 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb,
 				TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY;
 			cls_flower.cookie = (unsigned long)f;
 			cls_flower.dissector = &mask->dissector;
-			cls_flower.mask = &f->mkey;
-			cls_flower.key = &f->key;
+			cls_flower.mask = &mask->key;
+			cls_flower.key = &f->mkey;
 			cls_flower.exts = &f->exts;
 			cls_flower.classid = f->res.classid;
 
-- 
cgit v1.2.3


From 7d2eb6de6e6315ad5b93b848ba14360b2370ac4d Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Wed, 8 Aug 2018 01:52:49 +0800
Subject: MAINTAINERS: add an entry for MediaTek Bluetooth driver

Add an entry for the MediaTek Bluetooth driver.

Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 MAINTAINERS | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 82f277462349..9777a1dd6ff6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8988,6 +8988,14 @@ F:	include/uapi/linux/meye.h
 F:	include/uapi/linux/ivtv*
 F:	include/uapi/linux/uvcvideo.h
 
+MEDIATEK BLUETOOTH DRIVER
+M:	Sean Wang <sean.wang@mediatek.com>
+L:	linux-bluetooth@vger.kernel.org
+L:	linux-mediatek@lists.infradead.org (moderated for non-subscribers)
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/mediatek-bluetooth.txt
+F:	drivers/bluetooth/btmtkuart.c
+
 MEDIATEK CIR DRIVER
 M:	Sean Wang <sean.wang@mediatek.com>
 S:	Maintained
-- 
cgit v1.2.3


From 3789cabaab1a939eb56edd76bbde2c2e49f081da Mon Sep 17 00:00:00 2001
From: Shmulik Ladkani <shmulik@metanetworks.com>
Date: Mon, 6 Aug 2018 15:00:59 +0300
Subject: ip6_tunnel: collect_md xmit: Use ip_tunnel_key's provided src address

When using an ip6tnl device in collect_md mode, the xmit methods ignore
the ipv6.src field present in skb_tunnel_info's key, both for route
calculation purposes (flowi6 construction) and for assigning the
packet's final ipv6h->saddr.

This makes it impossible specifying a desired ipv6 local address in the
encapsulating header (for example, when using tc action tunnel_key).

This is also not aligned with behavior of ipip (ipv4) in collect_md
mode, where the key->u.ipv4.src gets used.

Fix, by assigning fl6.saddr with given key->u.ipv6.src.
In case ipv6.src is not specified, ip6_tnl_xmit uses existing saddr
selection code.

Fixes: 8d79266bc48c ("ip6_tunnel: add collect_md mode to IPv6 tunnels")
Signed-off-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Reviewed-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_tunnel.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 00e138a44cbb..820cebe0c687 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1113,7 +1113,7 @@ route_lookup:
 			dst = NULL;
 			goto tx_err_link_failure;
 		}
-		if (t->parms.collect_md &&
+		if (t->parms.collect_md && ipv6_addr_any(&fl6->saddr) &&
 		    ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev,
 				       &fl6->daddr, 0, &fl6->saddr))
 			goto tx_err_link_failure;
@@ -1255,6 +1255,7 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		key = &tun_info->key;
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_IPIP;
+		fl6.saddr = key->u.ipv6.src;
 		fl6.daddr = key->u.ipv6.dst;
 		fl6.flowlabel = key->label;
 		dsfield =  key->tos;
@@ -1326,6 +1327,7 @@ ip6ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev)
 		key = &tun_info->key;
 		memset(&fl6, 0, sizeof(fl6));
 		fl6.flowi6_proto = IPPROTO_IPV6;
+		fl6.saddr = key->u.ipv6.src;
 		fl6.daddr = key->u.ipv6.dst;
 		fl6.flowlabel = key->label;
 		dsfield = key->tos;
-- 
cgit v1.2.3


From 7395a8845588ebdf170f4d3796d44142458741be Mon Sep 17 00:00:00 2001
From: Intiyaz Basha <intiyaz.basha@cavium.com>
Date: Mon, 6 Aug 2018 13:09:40 -0700
Subject: liquidio: avoided acquiring post_lock for data only queues

All control commands (soft commands) goes through only Queue 0
(control and data queue). So only queue-0 needs post_lock,
other queues are only data queues and does not need post_lock

Added a flag to indicate the queue can be used for soft commands.

If this flag is set, post_lock must be acquired before posting
a command to the queue.
If this flag is clear, post_lock is invalid for the queue.

Signed-off-by: Intiyaz Basha <intiyaz.basha@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/octeon_iq.h   | 10 ++++++++++
 .../net/ethernet/cavium/liquidio/request_manager.c | 22 +++++++++++++++++++---
 2 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
index 5fed7b63223e..2327062e8af6 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h
@@ -82,6 +82,16 @@ struct octeon_instr_queue {
 	/** A spinlock to protect while posting on the ring.  */
 	spinlock_t post_lock;
 
+	/** This flag indicates if the queue can be used for soft commands.
+	 *  If this flag is set, post_lock must be acquired before posting
+	 *  a command to the queue.
+	 *  If this flag is clear, post_lock is invalid for the queue.
+	 *  All control commands (soft commands) will go through only Queue 0
+	 *  (control and data queue). So only queue-0 needs post_lock,
+	 *  other queues are only data queues and does not need post_lock
+	 */
+	bool allow_soft_cmds;
+
 	u32 pkt_in_done;
 
 	/** A spinlock to protect access to the input ring.*/
diff --git a/drivers/net/ethernet/cavium/liquidio/request_manager.c b/drivers/net/ethernet/cavium/liquidio/request_manager.c
index d5d9e47daa4b..8f746e1348d4 100644
--- a/drivers/net/ethernet/cavium/liquidio/request_manager.c
+++ b/drivers/net/ethernet/cavium/liquidio/request_manager.c
@@ -126,7 +126,12 @@ int octeon_init_instr_queue(struct octeon_device *oct,
 
 	/* Initialize the spinlock for this instruction queue */
 	spin_lock_init(&iq->lock);
-	spin_lock_init(&iq->post_lock);
+	if (iq_no == 0) {
+		iq->allow_soft_cmds = true;
+		spin_lock_init(&iq->post_lock);
+	} else {
+		iq->allow_soft_cmds = false;
+	}
 
 	spin_lock_init(&iq->iq_flush_running_lock);
 
@@ -566,7 +571,8 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 	/* Get the lock and prevent other tasks and tx interrupt handler from
 	 * running.
 	 */
-	spin_lock_bh(&iq->post_lock);
+	if (iq->allow_soft_cmds)
+		spin_lock_bh(&iq->post_lock);
 
 	st = __post_command2(iq, cmd);
 
@@ -583,7 +589,8 @@ octeon_send_command(struct octeon_device *oct, u32 iq_no,
 		INCR_INSTRQUEUE_PKT_COUNT(oct, iq_no, instr_dropped, 1);
 	}
 
-	spin_unlock_bh(&iq->post_lock);
+	if (iq->allow_soft_cmds)
+		spin_unlock_bh(&iq->post_lock);
 
 	/* This is only done here to expedite packets being flushed
 	 * for cases where there are no IQ completion interrupts.
@@ -702,11 +709,20 @@ octeon_prepare_soft_command(struct octeon_device *oct,
 int octeon_send_soft_command(struct octeon_device *oct,
 			     struct octeon_soft_command *sc)
 {
+	struct octeon_instr_queue *iq;
 	struct octeon_instr_ih2 *ih2;
 	struct octeon_instr_ih3 *ih3;
 	struct octeon_instr_irh *irh;
 	u32 len;
 
+	iq = oct->instr_queue[sc->iq_no];
+	if (!iq->allow_soft_cmds) {
+		dev_err(&oct->pci_dev->dev, "Soft commands are not allowed on Queue %d\n",
+			sc->iq_no);
+		INCR_INSTRQUEUE_PKT_COUNT(oct, sc->iq_no, instr_dropped, 1);
+		return IQ_SEND_FAILED;
+	}
+
 	if (OCTEON_CN23XX_PF(oct) || OCTEON_CN23XX_VF(oct)) {
 		ih3 =  (struct octeon_instr_ih3 *)&sc->cmd.cmd3.ih3;
 		if (ih3->dlengsz) {
-- 
cgit v1.2.3


From 79dabbb7161f43ed29ca888a2488f59e47171aee Mon Sep 17 00:00:00 2001
From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Date: Mon, 6 Aug 2018 21:39:58 -0500
Subject: ibmvnic: Remove code to request error information

When backing device firmware reports an error, it provides an
error ID, which is meant to be queried for more detailed error
information. Currently, however, an error ID is not provided by
the Virtual I/O server and there are not any plans to do so. For
now, it is always unfilled or zero, so request_error_information
will never be called.  Remove it.

Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 144 +------------------------------------
 drivers/net/ethernet/ibm/ibmvnic.h |  33 ---------
 2 files changed, 1 insertion(+), 176 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index ffe7acbeaa22..109e4a58efad 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -718,23 +718,6 @@ static int init_tx_pools(struct net_device *netdev)
 	return 0;
 }
 
-static void release_error_buffers(struct ibmvnic_adapter *adapter)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff, *tmp;
-	unsigned long flags;
-
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list) {
-		list_del(&error_buff->list);
-		dma_unmap_single(dev, error_buff->dma, error_buff->len,
-				 DMA_FROM_DEVICE);
-		kfree(error_buff->buff);
-		kfree(error_buff);
-	}
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-}
-
 static void ibmvnic_napi_enable(struct ibmvnic_adapter *adapter)
 {
 	int i;
@@ -896,7 +879,6 @@ static void release_resources(struct ibmvnic_adapter *adapter)
 	release_tx_pools(adapter);
 	release_rx_pools(adapter);
 
-	release_error_buffers(adapter);
 	release_napi(adapter);
 	release_login_rsp_buffer(adapter);
 }
@@ -3843,133 +3825,16 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	ibmvnic_send_crq(adapter, &crq);
 }
 
-static void handle_error_info_rsp(union ibmvnic_crq *crq,
-				  struct ibmvnic_adapter *adapter)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct ibmvnic_error_buff *error_buff, *tmp;
-	unsigned long flags;
-	bool found = false;
-	int i;
-
-	if (!crq->request_error_rsp.rc.code) {
-		dev_info(dev, "Request Error Rsp returned with rc=%x\n",
-			 crq->request_error_rsp.rc.code);
-		return;
-	}
-
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_for_each_entry_safe(error_buff, tmp, &adapter->errors, list)
-		if (error_buff->error_id == crq->request_error_rsp.error_id) {
-			found = true;
-			list_del(&error_buff->list);
-			break;
-		}
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-
-	if (!found) {
-		dev_err(dev, "Couldn't find error id %x\n",
-			be32_to_cpu(crq->request_error_rsp.error_id));
-		return;
-	}
-
-	dev_err(dev, "Detailed info for error id %x:",
-		be32_to_cpu(crq->request_error_rsp.error_id));
-
-	for (i = 0; i < error_buff->len; i++) {
-		pr_cont("%02x", (int)error_buff->buff[i]);
-		if (i % 8 == 7)
-			pr_cont(" ");
-	}
-	pr_cont("\n");
-
-	dma_unmap_single(dev, error_buff->dma, error_buff->len,
-			 DMA_FROM_DEVICE);
-	kfree(error_buff->buff);
-	kfree(error_buff);
-}
-
-static void request_error_information(struct ibmvnic_adapter *adapter,
-				      union ibmvnic_crq *err_crq)
-{
-	struct device *dev = &adapter->vdev->dev;
-	struct net_device *netdev = adapter->netdev;
-	struct ibmvnic_error_buff *error_buff;
-	unsigned long timeout = msecs_to_jiffies(30000);
-	union ibmvnic_crq crq;
-	unsigned long flags;
-	int rc, detail_len;
-
-	error_buff = kmalloc(sizeof(*error_buff), GFP_ATOMIC);
-	if (!error_buff)
-		return;
-
-	detail_len = be32_to_cpu(err_crq->error_indication.detail_error_sz);
-	error_buff->buff = kmalloc(detail_len, GFP_ATOMIC);
-	if (!error_buff->buff) {
-		kfree(error_buff);
-		return;
-	}
-
-	error_buff->dma = dma_map_single(dev, error_buff->buff, detail_len,
-					 DMA_FROM_DEVICE);
-	if (dma_mapping_error(dev, error_buff->dma)) {
-		netdev_err(netdev, "Couldn't map error buffer\n");
-		kfree(error_buff->buff);
-		kfree(error_buff);
-		return;
-	}
-
-	error_buff->len = detail_len;
-	error_buff->error_id = err_crq->error_indication.error_id;
-
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_add_tail(&error_buff->list, &adapter->errors);
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-
-	memset(&crq, 0, sizeof(crq));
-	crq.request_error_info.first = IBMVNIC_CRQ_CMD;
-	crq.request_error_info.cmd = REQUEST_ERROR_INFO;
-	crq.request_error_info.ioba = cpu_to_be32(error_buff->dma);
-	crq.request_error_info.len = cpu_to_be32(detail_len);
-	crq.request_error_info.error_id = err_crq->error_indication.error_id;
-
-	rc = ibmvnic_send_crq(adapter, &crq);
-	if (rc) {
-		netdev_err(netdev, "failed to request error information\n");
-		goto err_info_fail;
-	}
-
-	if (!wait_for_completion_timeout(&adapter->init_done, timeout)) {
-		netdev_err(netdev, "timeout waiting for error information\n");
-		goto err_info_fail;
-	}
-
-	return;
-
-err_info_fail:
-	spin_lock_irqsave(&adapter->error_list_lock, flags);
-	list_del(&error_buff->list);
-	spin_unlock_irqrestore(&adapter->error_list_lock, flags);
-
-	kfree(error_buff->buff);
-	kfree(error_buff);
-}
-
 static void handle_error_indication(union ibmvnic_crq *crq,
 				    struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 
-	dev_err(dev, "Firmware reports %serror id %x, cause %d\n",
+	dev_err(dev, "Firmware reports %serror, cause %d\n",
 		crq->error_indication.flags
 			& IBMVNIC_FATAL_ERROR ? "FATAL " : "",
-		be32_to_cpu(crq->error_indication.error_id),
 		be16_to_cpu(crq->error_indication.error_cause));
 
-	if (be32_to_cpu(crq->error_indication.error_id))
-		request_error_information(adapter, crq);
-
 	if (crq->error_indication.flags & IBMVNIC_FATAL_ERROR)
 		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
 	else
@@ -4468,10 +4333,6 @@ static void ibmvnic_handle_crq(union ibmvnic_crq *crq,
 		netdev_dbg(netdev, "Got Error Indication\n");
 		handle_error_indication(crq, adapter);
 		break;
-	case REQUEST_ERROR_RSP:
-		netdev_dbg(netdev, "Got Error Detail Response\n");
-		handle_error_info_rsp(crq, adapter);
-		break;
 	case REQUEST_STATISTICS_RSP:
 		netdev_dbg(netdev, "Got Statistics Response\n");
 		complete(&adapter->stats_done);
@@ -4830,9 +4691,6 @@ static int ibmvnic_probe(struct vio_dev *dev, const struct vio_device_id *id)
 
 	spin_lock_init(&adapter->stats_lock);
 
-	INIT_LIST_HEAD(&adapter->errors);
-	spin_lock_init(&adapter->error_list_lock);
-
 	INIT_WORK(&adapter->ibmvnic_reset, __ibmvnic_reset);
 	INIT_LIST_HEAD(&adapter->rwi_list);
 	mutex_init(&adapter->reset_lock);
diff --git a/drivers/net/ethernet/ibm/ibmvnic.h b/drivers/net/ethernet/ibm/ibmvnic.h
index f9fb780102ac..f06eec145ca6 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.h
+++ b/drivers/net/ethernet/ibm/ibmvnic.h
@@ -512,24 +512,6 @@ struct ibmvnic_error_indication {
 	u8 reserved2[2];
 } __packed __aligned(8);
 
-struct ibmvnic_request_error_info {
-	u8 first;
-	u8 cmd;
-	u8 reserved[2];
-	__be32 ioba;
-	__be32 len;
-	__be32 error_id;
-} __packed __aligned(8);
-
-struct ibmvnic_request_error_rsp {
-	u8 first;
-	u8 cmd;
-	u8 reserved[2];
-	__be32 error_id;
-	__be32 len;
-	struct ibmvnic_rc rc;
-} __packed __aligned(8);
-
 struct ibmvnic_link_state_indication {
 	u8 first;
 	u8 cmd;
@@ -709,8 +691,6 @@ union ibmvnic_crq {
 	struct ibmvnic_request_debug_stats request_debug_stats;
 	struct ibmvnic_request_debug_stats request_debug_stats_rsp;
 	struct ibmvnic_error_indication error_indication;
-	struct ibmvnic_request_error_info request_error_info;
-	struct ibmvnic_request_error_rsp request_error_rsp;
 	struct ibmvnic_link_state_indication link_state_indication;
 	struct ibmvnic_change_mac_addr change_mac_addr;
 	struct ibmvnic_change_mac_addr change_mac_addr_rsp;
@@ -809,8 +789,6 @@ enum ibmvnic_commands {
 	SET_PHYS_PARMS = 0x07,
 	SET_PHYS_PARMS_RSP = 0x87,
 	ERROR_INDICATION = 0x08,
-	REQUEST_ERROR_INFO = 0x09,
-	REQUEST_ERROR_RSP = 0x89,
 	LOGICAL_LINK_STATE = 0x0C,
 	LOGICAL_LINK_STATE_RSP = 0x8C,
 	REQUEST_STATISTICS = 0x0D,
@@ -945,14 +923,6 @@ struct ibmvnic_rx_pool {
 	struct ibmvnic_long_term_buff long_term_buff;
 };
 
-struct ibmvnic_error_buff {
-	char *buff;
-	dma_addr_t dma;
-	int len;
-	struct list_head list;
-	__be32 error_id;
-};
-
 struct ibmvnic_vpd {
 	unsigned char *buff;
 	dma_addr_t dma_addr;
@@ -1047,9 +1017,6 @@ struct ibmvnic_adapter {
 	struct completion init_done;
 	int init_done_rc;
 
-	struct list_head errors;
-	spinlock_t error_list_lock;
-
 	struct completion fw_done;
 	int fw_done_rc;
 
-- 
cgit v1.2.3


From c9008d339bc40301a486ea62f36f106c4b2aad0e Mon Sep 17 00:00:00 2001
From: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Date: Mon, 6 Aug 2018 21:39:59 -0500
Subject: ibmvnic: Update firmware error reporting with cause string

Print a string instead of the error code. Since there is a
possibility that the driver can recover, classify it as a
warning instead of an error.

Signed-off-by: Thomas Falcon <tlfalcon@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 34 ++++++++++++++++++++++++++++++----
 1 file changed, 30 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 109e4a58efad..dafdd4ade705 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -3825,15 +3825,41 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 	ibmvnic_send_crq(adapter, &crq);
 }
 
+static const char *ibmvnic_fw_err_cause(u16 cause)
+{
+	switch (cause) {
+	case ADAPTER_PROBLEM:
+		return "adapter problem";
+	case BUS_PROBLEM:
+		return "bus problem";
+	case FW_PROBLEM:
+		return "firmware problem";
+	case DD_PROBLEM:
+		return "device driver problem";
+	case EEH_RECOVERY:
+		return "EEH recovery";
+	case FW_UPDATED:
+		return "firmware updated";
+	case LOW_MEMORY:
+		return "low Memory";
+	default:
+		return "unknown";
+	}
+}
+
 static void handle_error_indication(union ibmvnic_crq *crq,
 				    struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
+	u16 cause;
+
+	cause = be16_to_cpu(crq->error_indication.error_cause);
 
-	dev_err(dev, "Firmware reports %serror, cause %d\n",
-		crq->error_indication.flags
-			& IBMVNIC_FATAL_ERROR ? "FATAL " : "",
-		be16_to_cpu(crq->error_indication.error_cause));
+	dev_warn_ratelimited(dev,
+			     "Firmware reports %serror, cause: %s. Starting recovery...\n",
+			     crq->error_indication.flags
+				& IBMVNIC_FATAL_ERROR ? "FATAL " : "",
+			     ibmvnic_fw_err_cause(cause));
 
 	if (crq->error_indication.flags & IBMVNIC_FATAL_ERROR)
 		ibmvnic_reset(adapter, VNIC_RESET_FATAL);
-- 
cgit v1.2.3


From 5800dc5c19f34e6e03b5adab1282535cb102fafd Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 3 Aug 2018 16:41:39 +0200
Subject: x86/paravirt: Fix spectre-v2 mitigations for paravirt guests

Nadav reported that on guests we're failing to rewrite the indirect
calls to CALLEE_SAVE paravirt functions. In particular the
pv_queued_spin_unlock() call is left unpatched and that is all over the
place. This obviously wrecks Spectre-v2 mitigation (for paravirt
guests) which relies on not actually having indirect calls around.

The reason is an incorrect clobber test in paravirt_patch_call(); this
function rewrites an indirect call with a direct call to the _SAME_
function, there is no possible way the clobbers can be different
because of this.

Therefore remove this clobber check. Also put WARNs on the other patch
failure case (not enough room for the instruction) which I've not seen
trigger in my (limited) testing.

Three live kernel image disassemblies for lock_sock_nested (as a small
function that illustrates the problem nicely). PRE is the current
situation for guests, POST is with this patch applied and NATIVE is with
or without the patch for !guests.

PRE:

(gdb) disassemble lock_sock_nested
Dump of assembler code for function lock_sock_nested:
   0xffffffff817be970 <+0>:     push   %rbp
   0xffffffff817be971 <+1>:     mov    %rdi,%rbp
   0xffffffff817be974 <+4>:     push   %rbx
   0xffffffff817be975 <+5>:     lea    0x88(%rbp),%rbx
   0xffffffff817be97c <+12>:    callq  0xffffffff819f7160 <_cond_resched>
   0xffffffff817be981 <+17>:    mov    %rbx,%rdi
   0xffffffff817be984 <+20>:    callq  0xffffffff819fbb00 <_raw_spin_lock_bh>
   0xffffffff817be989 <+25>:    mov    0x8c(%rbp),%eax
   0xffffffff817be98f <+31>:    test   %eax,%eax
   0xffffffff817be991 <+33>:    jne    0xffffffff817be9ba <lock_sock_nested+74>
   0xffffffff817be993 <+35>:    movl   $0x1,0x8c(%rbp)
   0xffffffff817be99d <+45>:    mov    %rbx,%rdi
   0xffffffff817be9a0 <+48>:    callq  *0xffffffff822299e8
   0xffffffff817be9a7 <+55>:    pop    %rbx
   0xffffffff817be9a8 <+56>:    pop    %rbp
   0xffffffff817be9a9 <+57>:    mov    $0x200,%esi
   0xffffffff817be9ae <+62>:    mov    $0xffffffff817be993,%rdi
   0xffffffff817be9b5 <+69>:    jmpq   0xffffffff81063ae0 <__local_bh_enable_ip>
   0xffffffff817be9ba <+74>:    mov    %rbp,%rdi
   0xffffffff817be9bd <+77>:    callq  0xffffffff817be8c0 <__lock_sock>
   0xffffffff817be9c2 <+82>:    jmp    0xffffffff817be993 <lock_sock_nested+35>
End of assembler dump.

POST:

(gdb) disassemble lock_sock_nested
Dump of assembler code for function lock_sock_nested:
   0xffffffff817be970 <+0>:     push   %rbp
   0xffffffff817be971 <+1>:     mov    %rdi,%rbp
   0xffffffff817be974 <+4>:     push   %rbx
   0xffffffff817be975 <+5>:     lea    0x88(%rbp),%rbx
   0xffffffff817be97c <+12>:    callq  0xffffffff819f7160 <_cond_resched>
   0xffffffff817be981 <+17>:    mov    %rbx,%rdi
   0xffffffff817be984 <+20>:    callq  0xffffffff819fbb00 <_raw_spin_lock_bh>
   0xffffffff817be989 <+25>:    mov    0x8c(%rbp),%eax
   0xffffffff817be98f <+31>:    test   %eax,%eax
   0xffffffff817be991 <+33>:    jne    0xffffffff817be9ba <lock_sock_nested+74>
   0xffffffff817be993 <+35>:    movl   $0x1,0x8c(%rbp)
   0xffffffff817be99d <+45>:    mov    %rbx,%rdi
   0xffffffff817be9a0 <+48>:    callq  0xffffffff810a0c20 <__raw_callee_save___pv_queued_spin_unlock>
   0xffffffff817be9a5 <+53>:    xchg   %ax,%ax
   0xffffffff817be9a7 <+55>:    pop    %rbx
   0xffffffff817be9a8 <+56>:    pop    %rbp
   0xffffffff817be9a9 <+57>:    mov    $0x200,%esi
   0xffffffff817be9ae <+62>:    mov    $0xffffffff817be993,%rdi
   0xffffffff817be9b5 <+69>:    jmpq   0xffffffff81063aa0 <__local_bh_enable_ip>
   0xffffffff817be9ba <+74>:    mov    %rbp,%rdi
   0xffffffff817be9bd <+77>:    callq  0xffffffff817be8c0 <__lock_sock>
   0xffffffff817be9c2 <+82>:    jmp    0xffffffff817be993 <lock_sock_nested+35>
End of assembler dump.

NATIVE:

(gdb) disassemble lock_sock_nested
Dump of assembler code for function lock_sock_nested:
   0xffffffff817be970 <+0>:     push   %rbp
   0xffffffff817be971 <+1>:     mov    %rdi,%rbp
   0xffffffff817be974 <+4>:     push   %rbx
   0xffffffff817be975 <+5>:     lea    0x88(%rbp),%rbx
   0xffffffff817be97c <+12>:    callq  0xffffffff819f7160 <_cond_resched>
   0xffffffff817be981 <+17>:    mov    %rbx,%rdi
   0xffffffff817be984 <+20>:    callq  0xffffffff819fbb00 <_raw_spin_lock_bh>
   0xffffffff817be989 <+25>:    mov    0x8c(%rbp),%eax
   0xffffffff817be98f <+31>:    test   %eax,%eax
   0xffffffff817be991 <+33>:    jne    0xffffffff817be9ba <lock_sock_nested+74>
   0xffffffff817be993 <+35>:    movl   $0x1,0x8c(%rbp)
   0xffffffff817be99d <+45>:    mov    %rbx,%rdi
   0xffffffff817be9a0 <+48>:    movb   $0x0,(%rdi)
   0xffffffff817be9a3 <+51>:    nopl   0x0(%rax)
   0xffffffff817be9a7 <+55>:    pop    %rbx
   0xffffffff817be9a8 <+56>:    pop    %rbp
   0xffffffff817be9a9 <+57>:    mov    $0x200,%esi
   0xffffffff817be9ae <+62>:    mov    $0xffffffff817be993,%rdi
   0xffffffff817be9b5 <+69>:    jmpq   0xffffffff81063ae0 <__local_bh_enable_ip>
   0xffffffff817be9ba <+74>:    mov    %rbp,%rdi
   0xffffffff817be9bd <+77>:    callq  0xffffffff817be8c0 <__lock_sock>
   0xffffffff817be9c2 <+82>:    jmp    0xffffffff817be993 <lock_sock_nested+35>
End of assembler dump.


Fixes: 63f70270ccd9 ("[PATCH] i386: PARAVIRT: add common patching machinery")
Fixes: 3010a0663fd9 ("x86/paravirt, objtool: Annotate indirect calls")
Reported-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Juergen Gross <jgross@suse.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: David Woodhouse <dwmw2@infradead.org>
Cc: stable@vger.kernel.org
---
 arch/x86/kernel/paravirt.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 99dc79e76bdc..930c88341e4e 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -88,10 +88,12 @@ unsigned paravirt_patch_call(void *insnbuf,
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (tgt_clobbers & ~site_clobbers)
-		return len;	/* target would clobber too much for this site */
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect CALL in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe8; /* call */
 	b->delta = delta;
@@ -106,8 +108,12 @@ unsigned paravirt_patch_jmp(void *insnbuf, const void *target,
 	struct branch *b = insnbuf;
 	unsigned long delta = (unsigned long)target - (addr+5);
 
-	if (len < 5)
+	if (len < 5) {
+#ifdef CONFIG_RETPOLINE
+		WARN_ONCE("Failing to patch indirect JMP in %ps\n", (void *)addr);
+#endif
 		return len;	/* call too long for patch site */
+	}
 
 	b->opcode = 0xe9;	/* jmp */
 	b->delta = delta;
-- 
cgit v1.2.3


From d1c38957aaf3defe029f11761f3a4ae4c83ad690 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Tue, 7 Aug 2018 12:25:12 +0300
Subject: net: macb: use netdev_tx_t return type for ndo_start_xmit functions

Use netdev_tx_t return type for ndo_start_xmit function of macb driver.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index a6c911bb5ce2..bb1d7b8d7dd6 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1651,7 +1651,7 @@ static inline int macb_clear_csum(struct sk_buff *skb)
 	return 0;
 }
 
-static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	u16 queue_index = skb_get_queue_mapping(skb);
 	struct macb *bp = netdev_priv(dev);
@@ -1660,6 +1660,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	unsigned int desc_cnt, nr_frags, frag_size, f;
 	unsigned int hdrlen;
 	bool is_lso, is_udp = 0;
+	netdev_tx_t ret = NETDEV_TX_OK;
 
 	is_lso = (skb_shinfo(skb)->gso_size != 0);
 
@@ -1739,7 +1740,7 @@ static int macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 unlock:
 	spin_unlock_irqrestore(&bp->lock, flags);
 
-	return NETDEV_TX_OK;
+	return ret;
 }
 
 static void macb_init_rx_buffer_size(struct macb *bp, size_t size)
@@ -3549,7 +3550,8 @@ static int at91ether_close(struct net_device *dev)
 }
 
 /* Transmit packet */
-static int at91ether_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static netdev_tx_t at91ether_start_xmit(struct sk_buff *skb,
+					struct net_device *dev)
 {
 	struct macb *lp = netdev_priv(dev);
 
-- 
cgit v1.2.3


From 33729f25a31e84e665b5441181bf98a514740fcf Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Tue, 7 Aug 2018 12:25:13 +0300
Subject: net: macb: move checksum clearing outside of spinlock

Move checksum clearing outside of spinlock. The SKB is protected by
networking lock (HARD_TX_LOCK()).

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index bb1d7b8d7dd6..332b19c645b4 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1662,6 +1662,11 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool is_lso, is_udp = 0;
 	netdev_tx_t ret = NETDEV_TX_OK;
 
+	if (macb_clear_csum(skb)) {
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
+
 	is_lso = (skb_shinfo(skb)->gso_size != 0);
 
 	if (is_lso) {
@@ -1717,11 +1722,6 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return NETDEV_TX_BUSY;
 	}
 
-	if (macb_clear_csum(skb)) {
-		dev_kfree_skb_any(skb);
-		goto unlock;
-	}
-
 	/* Map socket buffer for DMA transfer */
 	if (!macb_tx_map(bp, queue, skb, hdrlen)) {
 		dev_kfree_skb_any(skb);
-- 
cgit v1.2.3


From 653e92a9175ea7ed67efe209c725222051a3713d Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Tue, 7 Aug 2018 12:25:14 +0300
Subject: net: macb: add support for padding and fcs computation

For packets with computed IP/TCP/UDP checksum there is no need to tell
hardware to recompute it. For such kind of packets hardware expects the
packet to be at least 64 bytes and FCS to be computed.

Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_main.c | 70 ++++++++++++++++++++++++++++++++
 1 file changed, 70 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 332b19c645b4..dc09f9a8a49b 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -10,6 +10,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 #include <linux/clk.h>
+#include <linux/crc32.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/kernel.h>
@@ -1565,6 +1566,9 @@ static unsigned int macb_tx_map(struct macb *bp,
 		if (i == queue->tx_head) {
 			ctrl |= MACB_BF(TX_LSO, lso_ctrl);
 			ctrl |= MACB_BF(TX_TCP_SEQ_SRC, seq_ctrl);
+			if ((bp->dev->features & NETIF_F_HW_CSUM) &&
+			    skb->ip_summed != CHECKSUM_PARTIAL && !lso_ctrl)
+				ctrl |= MACB_BIT(TX_NOCRC);
 		} else
 			/* Only set MSS/MFS on payload descriptors
 			 * (second or later descriptor)
@@ -1651,6 +1655,67 @@ static inline int macb_clear_csum(struct sk_buff *skb)
 	return 0;
 }
 
+static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
+{
+	bool cloned = skb_cloned(*skb) || skb_header_cloned(*skb);
+	int padlen = ETH_ZLEN - (*skb)->len;
+	int headroom = skb_headroom(*skb);
+	int tailroom = skb_tailroom(*skb);
+	struct sk_buff *nskb;
+	u32 fcs;
+
+	if (!(ndev->features & NETIF_F_HW_CSUM) ||
+	    !((*skb)->ip_summed != CHECKSUM_PARTIAL) ||
+	    skb_shinfo(*skb)->gso_size)	/* Not available for GSO */
+		return 0;
+
+	if (padlen <= 0) {
+		/* FCS could be appeded to tailroom. */
+		if (tailroom >= ETH_FCS_LEN)
+			goto add_fcs;
+		/* FCS could be appeded by moving data to headroom. */
+		else if (!cloned && headroom + tailroom >= ETH_FCS_LEN)
+			padlen = 0;
+		/* No room for FCS, need to reallocate skb. */
+		else
+			padlen = ETH_FCS_LEN - tailroom;
+	} else {
+		/* Add room for FCS. */
+		padlen += ETH_FCS_LEN;
+	}
+
+	if (!cloned && headroom + tailroom >= padlen) {
+		(*skb)->data = memmove((*skb)->head, (*skb)->data, (*skb)->len);
+		skb_set_tail_pointer(*skb, (*skb)->len);
+	} else {
+		nskb = skb_copy_expand(*skb, 0, padlen, GFP_ATOMIC);
+		if (!nskb)
+			return -ENOMEM;
+
+		dev_kfree_skb_any(*skb);
+		*skb = nskb;
+	}
+
+	if (padlen) {
+		if (padlen >= ETH_FCS_LEN)
+			skb_put_zero(*skb, padlen - ETH_FCS_LEN);
+		else
+			skb_trim(*skb, ETH_FCS_LEN - padlen);
+	}
+
+add_fcs:
+	/* set FCS to packet */
+	fcs = crc32_le(~0, (*skb)->data, (*skb)->len);
+	fcs = ~fcs;
+
+	skb_put_u8(*skb, fcs		& 0xff);
+	skb_put_u8(*skb, (fcs >> 8)	& 0xff);
+	skb_put_u8(*skb, (fcs >> 16)	& 0xff);
+	skb_put_u8(*skb, (fcs >> 24)	& 0xff);
+
+	return 0;
+}
+
 static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	u16 queue_index = skb_get_queue_mapping(skb);
@@ -1667,6 +1732,11 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 		return ret;
 	}
 
+	if (macb_pad_and_fcs(&skb, dev)) {
+		dev_kfree_skb_any(skb);
+		return ret;
+	}
+
 	is_lso = (skb_shinfo(skb)->gso_size != 0);
 
 	if (is_lso) {
-- 
cgit v1.2.3


From 5941923da29e84bc9e2a1abb2c14fffaf8d71e2f Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Tue, 7 Aug 2018 19:34:16 +0800
Subject: RDS: IB: fix 'passing zero to ERR_PTR()' warning

Fix a static code checker warning:
 net/rds/ib_frmr.c:82 rds_ib_alloc_frmr() warn: passing zero to 'ERR_PTR'

The error path for ib_alloc_mr failure should set err to PTR_ERR.

Fixes: 1659185fb4d0 ("RDS: IB: Support Fastreg MR (FRMR) memory registration mode")
Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/ib_frmr.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rds/ib_frmr.c b/net/rds/ib_frmr.c
index d152e48ea371..8596eed6d9a8 100644
--- a/net/rds/ib_frmr.c
+++ b/net/rds/ib_frmr.c
@@ -61,6 +61,7 @@ static struct rds_ib_mr *rds_ib_alloc_frmr(struct rds_ib_device *rds_ibdev,
 			 pool->fmr_attr.max_pages);
 	if (IS_ERR(frmr->mr)) {
 		pr_warn("RDS/IB: %s failed to allocate MR", __func__);
+		err = PTR_ERR(frmr->mr);
 		goto out_no_cigar;
 	}
 
-- 
cgit v1.2.3


From 2a1cb1bf439f6703f82f61d0424b41f42544e3ff Mon Sep 17 00:00:00 2001
From: Denis Bolotin <denis.bolotin@cavium.com>
Date: Tue, 7 Aug 2018 15:48:08 +0300
Subject: qed: Add DCBX API - qed_dcbx_get_priority_tc()

The API receives a priority and looks for the TC it is mapped to in the
operational DCBX configuration. The API returns QED_DCBX_DEFAULT_TC (0)
when DCBX is disabled.

Signed-off-by: Michal Kalderon <michal.kalderon@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 18 ++++++++++++++++++
 drivers/net/ethernet/qlogic/qed/qed_dcbx.h |  3 +++
 2 files changed, 21 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index d02e774c8d66..86307b90d835 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -989,6 +989,24 @@ void qed_dcbx_set_pf_update_params(struct qed_dcbx_results *p_src,
 	qed_dcbx_update_protocol_data(p_dcb_data, p_src, DCBX_PROTOCOL_ETH);
 }
 
+u8 qed_dcbx_get_priority_tc(struct qed_hwfn *p_hwfn, u8 pri)
+{
+	struct qed_dcbx_get *dcbx_info = &p_hwfn->p_dcbx_info->get;
+
+	if (pri >= QED_MAX_PFC_PRIORITIES) {
+		DP_ERR(p_hwfn, "Invalid priority %d\n", pri);
+		return QED_DCBX_DEFAULT_TC;
+	}
+
+	if (!dcbx_info->operational.valid) {
+		DP_VERBOSE(p_hwfn, QED_MSG_DCB,
+			   "Dcbx parameters not available\n");
+		return QED_DCBX_DEFAULT_TC;
+	}
+
+	return dcbx_info->operational.params.ets_pri_tc_tbl[pri];
+}
+
 #ifdef CONFIG_DCB
 static int qed_dcbx_query_params(struct qed_hwfn *p_hwfn,
 				 struct qed_dcbx_get *p_get,
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
index 5feb90e049e0..a4d688c04e18 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.h
@@ -123,4 +123,7 @@ void qed_dcbx_info_free(struct qed_hwfn *p_hwfn);
 void qed_dcbx_set_pf_update_params(struct qed_dcbx_results *p_src,
 				   struct pf_update_ramrod_data *p_dest);
 
+#define QED_DCBX_DEFAULT_TC	0
+
+u8 qed_dcbx_get_priority_tc(struct qed_hwfn *p_hwfn, u8 pri);
 #endif
-- 
cgit v1.2.3


From c4259dda171920bf25f92756aa5a5fd17bf7e19e Mon Sep 17 00:00:00 2001
From: Denis Bolotin <denis.bolotin@cavium.com>
Date: Tue, 7 Aug 2018 15:48:09 +0300
Subject: qed: Add a flag which indicates if offload TC is set

Distinguish not set offload_tc from offload_tc 0 and add getters and
setters.

Signed-off-by: Michal Kalderon <michal.kalderon@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h      |  3 +++
 drivers/net/ethernet/qlogic/qed/qed_dcbx.c |  2 +-
 drivers/net/ethernet/qlogic/qed/qed_dev.c  | 32 +++++++++++++++++++++++++-----
 drivers/net/ethernet/qlogic/qed/qed_mcp.c  |  3 ++-
 4 files changed, 33 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index 1dfaccd151f0..f916f139f80e 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -336,6 +336,7 @@ struct qed_hw_info {
 	 */
 	u8 num_active_tc;
 	u8				offload_tc;
+	bool				offload_tc_set;
 
 	u32				concrete_fid;
 	u16				opaque_fid;
@@ -921,4 +922,6 @@ int qed_mfw_tlv_req(struct qed_hwfn *hwfn);
 int qed_mfw_fill_tlv_data(struct qed_hwfn *hwfn,
 			  enum qed_mfw_tlv_type type,
 			  union qed_mfw_tlv_data *tlv_data);
+
+void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc);
 #endif /* _QED_H */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
index 86307b90d835..6bb76e6d3c14 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c
@@ -208,7 +208,7 @@ qed_dcbx_set_params(struct qed_dcbx_results *p_data,
 
 	/* QM reconf data */
 	if (p_info->personality == personality)
-		p_info->offload_tc = tc;
+		qed_hw_info_set_offload_tc(p_info, tc);
 }
 
 /* Update app protocol data and hw_info fields with the TLV info */
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index 6a0b46f214f4..a8e768342ad7 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -394,7 +394,25 @@ static void qed_init_qm_advance_vport(struct qed_hwfn *p_hwfn)
 /* defines for pq init */
 #define PQ_INIT_DEFAULT_WRR_GROUP       1
 #define PQ_INIT_DEFAULT_TC              0
-#define PQ_INIT_OFLD_TC                 (p_hwfn->hw_info.offload_tc)
+
+void qed_hw_info_set_offload_tc(struct qed_hw_info *p_info, u8 tc)
+{
+	p_info->offload_tc = tc;
+	p_info->offload_tc_set = true;
+}
+
+static bool qed_is_offload_tc_set(struct qed_hwfn *p_hwfn)
+{
+	return p_hwfn->hw_info.offload_tc_set;
+}
+
+static u32 qed_get_offload_tc(struct qed_hwfn *p_hwfn)
+{
+	if (qed_is_offload_tc_set(p_hwfn))
+		return p_hwfn->hw_info.offload_tc;
+
+	return PQ_INIT_DEFAULT_TC;
+}
 
 static void qed_init_qm_pq(struct qed_hwfn *p_hwfn,
 			   struct qed_qm_info *qm_info,
@@ -538,7 +556,8 @@ static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_ACK, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+		       PQ_INIT_SHARE_VPORT);
 }
 
 static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
@@ -549,7 +568,8 @@ static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+		       PQ_INIT_SHARE_VPORT);
 }
 
 static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
@@ -560,7 +580,8 @@ static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_SHARE_VPORT);
+	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+		       PQ_INIT_SHARE_VPORT);
 }
 
 static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
@@ -601,7 +622,8 @@ static void qed_init_qm_rl_pqs(struct qed_hwfn *p_hwfn)
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_RLS, qm_info->num_pqs);
 	for (pf_rls_idx = 0; pf_rls_idx < num_pf_rls; pf_rls_idx++)
-		qed_init_qm_pq(p_hwfn, qm_info, PQ_INIT_OFLD_TC, PQ_INIT_PF_RL);
+		qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
+			       PQ_INIT_PF_RL);
 }
 
 static void qed_init_qm_pq_params(struct qed_hwfn *p_hwfn)
diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
index 8e4f60e4520a..d89a0e22f6e4 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c
@@ -1552,7 +1552,8 @@ qed_mcp_handle_ufp_event(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt)
 
 	if (p_hwfn->ufp_info.mode == QED_UFP_MODE_VNIC_BW) {
 		p_hwfn->qm_info.ooo_tc = p_hwfn->ufp_info.tc;
-		p_hwfn->hw_info.offload_tc = p_hwfn->ufp_info.tc;
+		qed_hw_info_set_offload_tc(&p_hwfn->hw_info,
+					   p_hwfn->ufp_info.tc);
 
 		qed_qm_reconf(p_hwfn, p_ptt);
 	} else if (p_hwfn->ufp_info.mode == QED_UFP_MODE_ETS) {
-- 
cgit v1.2.3


From 61be82b087e201511bc53cf614f733dee1f47344 Mon Sep 17 00:00:00 2001
From: Denis Bolotin <denis.bolotin@cavium.com>
Date: Tue, 7 Aug 2018 15:48:10 +0300
Subject: qed: Add Multi-TC RoCE support

RoCE qps use a pair of physical queues (pq) received from the Queue Manager
(QM) - an offload queue (OFLD) and a low latency queue (LLT). The QM block
creates a pq for each TC, and allows RoCE qps to ask for a pq with a
specific TC. As a result, qps with different VLAN priorities can be mapped
to different TCs, and employ features such as PFC and ETS.

Signed-off-by: Michal Kalderon <michal.kalderon@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: Denis Bolotin <denis.bolotin@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed.h      | 10 +++-
 drivers/net/ethernet/qlogic/qed/qed_dev.c  | 89 +++++++++++++++++++++++++-----
 drivers/net/ethernet/qlogic/qed/qed_roce.c | 54 ++++++++++++------
 3 files changed, 121 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h
index f916f139f80e..a60e1c8d470a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed.h
+++ b/drivers/net/ethernet/qlogic/qed/qed.h
@@ -338,6 +338,9 @@ struct qed_hw_info {
 	u8				offload_tc;
 	bool				offload_tc_set;
 
+	bool				multi_tc_roce_en;
+#define IS_QED_MULTI_TC_ROCE(p_hwfn) (((p_hwfn)->hw_info.multi_tc_roce_en))
+
 	u32				concrete_fid;
 	u16				opaque_fid;
 	u16				ovlan;
@@ -400,8 +403,8 @@ struct qed_qm_info {
 	u16				start_pq;
 	u8				start_vport;
 	u16				 pure_lb_pq;
-	u16				offload_pq;
-	u16				low_latency_pq;
+	u16				first_ofld_pq;
+	u16				first_llt_pq;
 	u16				pure_ack_pq;
 	u16				ooo_pq;
 	u16				first_vf_pq;
@@ -882,11 +885,14 @@ void qed_set_fw_mac_addr(__le16 *fw_msb,
 #define PQ_FLAGS_OFLD   (BIT(5))
 #define PQ_FLAGS_VFS    (BIT(6))
 #define PQ_FLAGS_LLT    (BIT(7))
+#define PQ_FLAGS_MTC    (BIT(8))
 
 /* physical queue index for cm context intialization */
 u16 qed_get_cm_pq_idx(struct qed_hwfn *p_hwfn, u32 pq_flags);
 u16 qed_get_cm_pq_idx_mcos(struct qed_hwfn *p_hwfn, u8 tc);
 u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf);
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc);
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc);
 
 #define QED_LEADING_HWFN(dev)   (&dev->hwfns[0])
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index a8e768342ad7..d1ae11ab7927 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -215,6 +215,8 @@ static u32 qed_get_pq_flags(struct qed_hwfn *p_hwfn)
 		break;
 	case QED_PCI_ETH_ROCE:
 		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_OFLD | PQ_FLAGS_LLT;
+		if (IS_QED_MULTI_TC_ROCE(p_hwfn))
+			flags |= PQ_FLAGS_MTC;
 		break;
 	case QED_PCI_ETH_IWARP:
 		flags |= PQ_FLAGS_MCOS | PQ_FLAGS_ACK | PQ_FLAGS_OOO |
@@ -241,6 +243,16 @@ static u16 qed_init_qm_get_num_vfs(struct qed_hwfn *p_hwfn)
 	       p_hwfn->cdev->p_iov_info->total_vfs : 0;
 }
 
+static u8 qed_init_qm_get_num_mtc_tcs(struct qed_hwfn *p_hwfn)
+{
+	u32 pq_flags = qed_get_pq_flags(p_hwfn);
+
+	if (!(PQ_FLAGS_MTC & pq_flags))
+		return 1;
+
+	return qed_init_qm_get_num_tcs(p_hwfn);
+}
+
 #define NUM_DEFAULT_RLS 1
 
 static u16 qed_init_qm_get_num_pf_rls(struct qed_hwfn *p_hwfn)
@@ -282,8 +294,11 @@ static u16 qed_init_qm_get_num_pqs(struct qed_hwfn *p_hwfn)
 	       (!!(PQ_FLAGS_MCOS & pq_flags)) *
 	       qed_init_qm_get_num_tcs(p_hwfn) +
 	       (!!(PQ_FLAGS_LB & pq_flags)) + (!!(PQ_FLAGS_OOO & pq_flags)) +
-	       (!!(PQ_FLAGS_ACK & pq_flags)) + (!!(PQ_FLAGS_OFLD & pq_flags)) +
-	       (!!(PQ_FLAGS_LLT & pq_flags)) +
+	       (!!(PQ_FLAGS_ACK & pq_flags)) +
+	       (!!(PQ_FLAGS_OFLD & pq_flags)) *
+	       qed_init_qm_get_num_mtc_tcs(p_hwfn) +
+	       (!!(PQ_FLAGS_LLT & pq_flags)) *
+	       qed_init_qm_get_num_mtc_tcs(p_hwfn) +
 	       (!!(PQ_FLAGS_VFS & pq_flags)) * qed_init_qm_get_num_vfs(p_hwfn);
 }
 
@@ -474,9 +489,9 @@ static u16 *qed_init_qm_get_idx_from_flags(struct qed_hwfn *p_hwfn,
 	case PQ_FLAGS_ACK:
 		return &qm_info->pure_ack_pq;
 	case PQ_FLAGS_OFLD:
-		return &qm_info->offload_pq;
+		return &qm_info->first_ofld_pq;
 	case PQ_FLAGS_LLT:
-		return &qm_info->low_latency_pq;
+		return &qm_info->first_llt_pq;
 	case PQ_FLAGS_VFS:
 		return &qm_info->first_vf_pq;
 	default:
@@ -525,6 +540,28 @@ u16 qed_get_cm_pq_idx_vf(struct qed_hwfn *p_hwfn, u16 vf)
 	return qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_VFS) + vf;
 }
 
+u16 qed_get_cm_pq_idx_ofld_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+	u16 first_ofld_pq, pq_offset;
+
+	first_ofld_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
+	pq_offset = (tc < qed_init_qm_get_num_mtc_tcs(p_hwfn)) ?
+		    tc : PQ_INIT_DEFAULT_TC;
+
+	return first_ofld_pq + pq_offset;
+}
+
+u16 qed_get_cm_pq_idx_llt_mtc(struct qed_hwfn *p_hwfn, u8 tc)
+{
+	u16 first_llt_pq, pq_offset;
+
+	first_llt_pq = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_LLT);
+	pq_offset = (tc < qed_init_qm_get_num_mtc_tcs(p_hwfn)) ?
+		    tc : PQ_INIT_DEFAULT_TC;
+
+	return first_llt_pq + pq_offset;
+}
+
 /* Functions for creating specific types of pqs */
 static void qed_init_qm_lb_pq(struct qed_hwfn *p_hwfn)
 {
@@ -560,6 +597,20 @@ static void qed_init_qm_pure_ack_pq(struct qed_hwfn *p_hwfn)
 		       PQ_INIT_SHARE_VPORT);
 }
 
+static void qed_init_qm_mtc_pqs(struct qed_hwfn *p_hwfn)
+{
+	u8 num_tcs = qed_init_qm_get_num_mtc_tcs(p_hwfn);
+	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
+	u8 tc;
+
+	/* override pq's TC if offload TC is set */
+	for (tc = 0; tc < num_tcs; tc++)
+		qed_init_qm_pq(p_hwfn, qm_info,
+			       qed_is_offload_tc_set(p_hwfn) ?
+			       p_hwfn->hw_info.offload_tc : tc,
+			       PQ_INIT_SHARE_VPORT);
+}
+
 static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
 {
 	struct qed_qm_info *qm_info = &p_hwfn->qm_info;
@@ -568,8 +619,7 @@ static void qed_init_qm_offload_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_OFLD, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
-		       PQ_INIT_SHARE_VPORT);
+	qed_init_qm_mtc_pqs(p_hwfn);
 }
 
 static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
@@ -580,8 +630,7 @@ static void qed_init_qm_low_latency_pq(struct qed_hwfn *p_hwfn)
 		return;
 
 	qed_init_qm_set_idx(p_hwfn, PQ_FLAGS_LLT, qm_info->num_pqs);
-	qed_init_qm_pq(p_hwfn, qm_info, qed_get_offload_tc(p_hwfn),
-		       PQ_INIT_SHARE_VPORT);
+	qed_init_qm_mtc_pqs(p_hwfn);
 }
 
 static void qed_init_qm_mcos_pqs(struct qed_hwfn *p_hwfn)
@@ -664,12 +713,19 @@ static int qed_init_qm_sanity(struct qed_hwfn *p_hwfn)
 		return -EINVAL;
 	}
 
-	if (qed_init_qm_get_num_pqs(p_hwfn) > RESC_NUM(p_hwfn, QED_PQ)) {
-		DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
-		return -EINVAL;
+	if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+		return 0;
+
+	if (QED_IS_ROCE_PERSONALITY(p_hwfn)) {
+		p_hwfn->hw_info.multi_tc_roce_en = 0;
+		DP_NOTICE(p_hwfn,
+			  "multi-tc roce was disabled to reduce requested amount of pqs\n");
+		if (qed_init_qm_get_num_pqs(p_hwfn) <= RESC_NUM(p_hwfn, QED_PQ))
+			return 0;
 	}
 
-	return 0;
+	DP_ERR(p_hwfn, "requested amount of pqs exceeds resource\n");
+	return -EINVAL;
 }
 
 static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
@@ -683,11 +739,13 @@ static void qed_dp_init_qm_params(struct qed_hwfn *p_hwfn)
 	/* top level params */
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_HW,
-		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, pure_ack_pq %d\n",
+		   "qm init top level params: start_pq %d, start_vport %d, pure_lb_pq %d, offload_pq %d, llt_pq %d, pure_ack_pq %d\n",
 		   qm_info->start_pq,
 		   qm_info->start_vport,
 		   qm_info->pure_lb_pq,
-		   qm_info->offload_pq, qm_info->pure_ack_pq);
+		   qm_info->first_ofld_pq,
+		   qm_info->first_llt_pq,
+		   qm_info->pure_ack_pq);
 	DP_VERBOSE(p_hwfn,
 		   NETIF_MSG_HW,
 		   "ooo_pq %d, first_vf_pq %d, num_pqs %d, num_vf_pqs %d, num_vports %d, max_phys_tcs_per_port %d\n",
@@ -2920,6 +2978,9 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn,
 		p_hwfn->hw_info.personality = protocol;
 	}
 
+	if (QED_IS_ROCE_PERSONALITY(p_hwfn))
+		p_hwfn->hw_info.multi_tc_roce_en = 1;
+
 	p_hwfn->hw_info.num_hw_tc = NUM_PHYS_TCS_4PORT_K2;
 	p_hwfn->hw_info.num_active_tc = 1;
 
diff --git a/drivers/net/ethernet/qlogic/qed/qed_roce.c b/drivers/net/ethernet/qlogic/qed/qed_roce.c
index ada4c1810864..7d7a64c55ff1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_roce.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_roce.c
@@ -44,8 +44,10 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/if_vlan.h>
 #include "qed.h"
 #include "qed_cxt.h"
+#include "qed_dcbx.h"
 #include "qed_hsi.h"
 #include "qed_hw.h"
 #include "qed_init_ops.h"
@@ -231,16 +233,33 @@ static void qed_roce_set_real_cid(struct qed_hwfn *p_hwfn, u32 cid)
 	spin_unlock_bh(&p_hwfn->p_rdma_info->lock);
 }
 
+static u8 qed_roce_get_qp_tc(struct qed_hwfn *p_hwfn, struct qed_rdma_qp *qp)
+{
+	u8 pri, tc = 0;
+
+	if (qp->vlan_id) {
+		pri = (qp->vlan_id & VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
+		tc = qed_dcbx_get_priority_tc(p_hwfn, pri);
+	}
+
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u tc: %u (vlan priority %s)\n",
+		   qp->icid, tc, qp->vlan_id ? "enabled" : "disabled");
+
+	return tc;
+}
+
 static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_resp_ramrod_data *p_ramrod;
+	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 regular_latency_queue;
 	enum protocol_type proto;
 	int rc;
+	u8 tc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
@@ -324,12 +343,17 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 	p_ramrod->cq_cid = cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) |
 				       qp->rq_cq_id);
 
-	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+	tc = qed_roce_get_qp_tc(p_hwfn, qp);
+	regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+	low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u pqs: regular_latency %u low_latency %u\n",
+		   qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+		   low_latency_queue - CM_TX_PQ_BASE);
 	p_ramrod->regular_latency_phy_queue =
 	    cpu_to_le16(regular_latency_queue);
 	p_ramrod->low_latency_phy_queue =
-	    cpu_to_le16(regular_latency_queue);
+	    cpu_to_le16(low_latency_queue);
 
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
@@ -345,11 +369,6 @@ static int qed_roce_sp_create_responder(struct qed_hwfn *p_hwfn,
 				     qp->stats_queue;
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA,
-		   "rc = %d regular physical queue = 0x%x\n", rc,
-		   regular_latency_queue);
-
 	if (rc)
 		goto err;
 
@@ -375,12 +394,13 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 					struct qed_rdma_qp *qp)
 {
 	struct roce_create_qp_req_ramrod_data *p_ramrod;
+	u16 regular_latency_queue, low_latency_queue;
 	struct qed_sp_init_data init_data;
 	enum roce_flavor roce_flavor;
 	struct qed_spq_entry *p_ent;
-	u16 regular_latency_queue;
 	enum protocol_type proto;
 	int rc;
+	u8 tc;
 
 	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "icid = %08x\n", qp->icid);
 
@@ -453,12 +473,17 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 	p_ramrod->cq_cid =
 	    cpu_to_le32((p_hwfn->hw_info.opaque_fid << 16) | qp->sq_cq_id);
 
-	regular_latency_queue = qed_get_cm_pq_idx(p_hwfn, PQ_FLAGS_OFLD);
-
+	tc = qed_roce_get_qp_tc(p_hwfn, qp);
+	regular_latency_queue = qed_get_cm_pq_idx_ofld_mtc(p_hwfn, tc);
+	low_latency_queue = qed_get_cm_pq_idx_llt_mtc(p_hwfn, tc);
+	DP_VERBOSE(p_hwfn, QED_MSG_SP,
+		   "qp icid %u pqs: regular_latency %u low_latency %u\n",
+		   qp->icid, regular_latency_queue - CM_TX_PQ_BASE,
+		   low_latency_queue - CM_TX_PQ_BASE);
 	p_ramrod->regular_latency_phy_queue =
 	    cpu_to_le16(regular_latency_queue);
 	p_ramrod->low_latency_phy_queue =
-	    cpu_to_le16(regular_latency_queue);
+	    cpu_to_le16(low_latency_queue);
 
 	p_ramrod->dpi = cpu_to_le16(qp->dpi);
 
@@ -471,9 +496,6 @@ static int qed_roce_sp_create_requester(struct qed_hwfn *p_hwfn,
 				     qp->stats_queue;
 
 	rc = qed_spq_post(p_hwfn, p_ent, NULL);
-
-	DP_VERBOSE(p_hwfn, QED_MSG_RDMA, "rc = %d\n", rc);
-
 	if (rc)
 		goto err;
 
-- 
cgit v1.2.3


From 2887e41b910bb14fd847cf01ab7a5993db989d88 Mon Sep 17 00:00:00 2001
From: Anchal Agarwal <anchalag@amazon.com>
Date: Tue, 7 Aug 2018 14:40:49 -0600
Subject: blk-wbt: Avoid lock contention and thundering herd issue in wbt_wait

I am currently running a large bare metal instance (i3.metal)
on EC2 with 72 cores, 512GB of RAM and NVME drives, with a
4.18 kernel. I have a workload that simulates a database
workload and I am running into lockup issues when writeback
throttling is enabled,with the hung task detector also
kicking in.

Crash dumps show that most CPUs (up to 50 of them) are
all trying to get the wbt wait queue lock while trying to add
themselves to it in __wbt_wait (see stack traces below).

[    0.948118] CPU: 45 PID: 0 Comm: swapper/45 Not tainted 4.14.51-62.38.amzn1.x86_64 #1
[    0.948119] Hardware name: Amazon EC2 i3.metal/Not Specified, BIOS 1.0 10/16/2017
[    0.948120] task: ffff883f7878c000 task.stack: ffffc9000c69c000
[    0.948124] RIP: 0010:native_queued_spin_lock_slowpath+0xf8/0x1a0
[    0.948125] RSP: 0018:ffff883f7fcc3dc8 EFLAGS: 00000046
[    0.948126] RAX: 0000000000000000 RBX: ffff887f7709ca68 RCX: ffff883f7fce2a00
[    0.948128] RDX: 000000000000001c RSI: 0000000000740001 RDI: ffff887f7709ca68
[    0.948129] RBP: 0000000000000002 R08: 0000000000b80000 R09: 0000000000000000
[    0.948130] R10: ffff883f7fcc3d78 R11: 000000000de27121 R12: 0000000000000002
[    0.948131] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000000
[    0.948132] FS:  0000000000000000(0000) GS:ffff883f7fcc0000(0000) knlGS:0000000000000000
[    0.948134] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    0.948135] CR2: 000000c424c77000 CR3: 0000000002010005 CR4: 00000000003606e0
[    0.948136] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    0.948137] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    0.948138] Call Trace:
[    0.948139]  <IRQ>
[    0.948142]  do_raw_spin_lock+0xad/0xc0
[    0.948145]  _raw_spin_lock_irqsave+0x44/0x4b
[    0.948149]  ? __wake_up_common_lock+0x53/0x90
[    0.948150]  __wake_up_common_lock+0x53/0x90
[    0.948155]  wbt_done+0x7b/0xa0
[    0.948158]  blk_mq_free_request+0xb7/0x110
[    0.948161]  __blk_mq_complete_request+0xcb/0x140
[    0.948166]  nvme_process_cq+0xce/0x1a0 [nvme]
[    0.948169]  nvme_irq+0x23/0x50 [nvme]
[    0.948173]  __handle_irq_event_percpu+0x46/0x300
[    0.948176]  handle_irq_event_percpu+0x20/0x50
[    0.948179]  handle_irq_event+0x34/0x60
[    0.948181]  handle_edge_irq+0x77/0x190
[    0.948185]  handle_irq+0xaf/0x120
[    0.948188]  do_IRQ+0x53/0x110
[    0.948191]  common_interrupt+0x87/0x87
[    0.948192]  </IRQ>
....
[    0.311136] CPU: 4 PID: 9737 Comm: run_linux_amd64 Not tainted 4.14.51-62.38.amzn1.x86_64 #1
[    0.311137] Hardware name: Amazon EC2 i3.metal/Not Specified, BIOS 1.0 10/16/2017
[    0.311138] task: ffff883f6e6a8000 task.stack: ffffc9000f1ec000
[    0.311141] RIP: 0010:native_queued_spin_lock_slowpath+0xf5/0x1a0
[    0.311142] RSP: 0018:ffffc9000f1efa28 EFLAGS: 00000046
[    0.311144] RAX: 0000000000000000 RBX: ffff887f7709ca68 RCX: ffff883f7f722a00
[    0.311145] RDX: 0000000000000035 RSI: 0000000000d80001 RDI: ffff887f7709ca68
[    0.311146] RBP: 0000000000000202 R08: 0000000000140000 R09: 0000000000000000
[    0.311147] R10: ffffc9000f1ef9d8 R11: 000000001a249fa0 R12: ffff887f7709ca68
[    0.311148] R13: ffffc9000f1efad0 R14: 0000000000000000 R15: ffff887f7709ca00
[    0.311149] FS:  000000c423f30090(0000) GS:ffff883f7f700000(0000) knlGS:0000000000000000
[    0.311150] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[    0.311151] CR2: 00007feefcea4000 CR3: 0000007f7016e001 CR4: 00000000003606e0
[    0.311152] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[    0.311153] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[    0.311154] Call Trace:
[    0.311157]  do_raw_spin_lock+0xad/0xc0
[    0.311160]  _raw_spin_lock_irqsave+0x44/0x4b
[    0.311162]  ? prepare_to_wait_exclusive+0x28/0xb0
[    0.311164]  prepare_to_wait_exclusive+0x28/0xb0
[    0.311167]  wbt_wait+0x127/0x330
[    0.311169]  ? finish_wait+0x80/0x80
[    0.311172]  ? generic_make_request+0xda/0x3b0
[    0.311174]  blk_mq_make_request+0xd6/0x7b0
[    0.311176]  ? blk_queue_enter+0x24/0x260
[    0.311178]  ? generic_make_request+0xda/0x3b0
[    0.311181]  generic_make_request+0x10c/0x3b0
[    0.311183]  ? submit_bio+0x5c/0x110
[    0.311185]  submit_bio+0x5c/0x110
[    0.311197]  ? __ext4_journal_stop+0x36/0xa0 [ext4]
[    0.311210]  ext4_io_submit+0x48/0x60 [ext4]
[    0.311222]  ext4_writepages+0x810/0x11f0 [ext4]
[    0.311229]  ? do_writepages+0x3c/0xd0
[    0.311239]  ? ext4_mark_inode_dirty+0x260/0x260 [ext4]
[    0.311240]  do_writepages+0x3c/0xd0
[    0.311243]  ? _raw_spin_unlock+0x24/0x30
[    0.311245]  ? wbc_attach_and_unlock_inode+0x165/0x280
[    0.311248]  ? __filemap_fdatawrite_range+0xa3/0xe0
[    0.311250]  __filemap_fdatawrite_range+0xa3/0xe0
[    0.311253]  file_write_and_wait_range+0x34/0x90
[    0.311264]  ext4_sync_file+0x151/0x500 [ext4]
[    0.311267]  do_fsync+0x38/0x60
[    0.311270]  SyS_fsync+0xc/0x10
[    0.311272]  do_syscall_64+0x6f/0x170
[    0.311274]  entry_SYSCALL_64_after_hwframe+0x42/0xb7

In the original patch, wbt_done is waking up all the exclusive
processes in the wait queue, which can cause a thundering herd
if there is a large number of writer threads in the queue. The
original intention of the code seems to be to wake up one thread
only however, it uses wake_up_all() in __wbt_done(), and then
uses the following check in __wbt_wait to have only one thread
actually get out of the wait loop:

if (waitqueue_active(&rqw->wait) &&
            rqw->wait.head.next != &wait->entry)
                return false;

The problem with this is that the wait entry in wbt_wait is
define with DEFINE_WAIT, which uses the autoremove wakeup function.
That means that the above check is invalid - the wait entry will
have been removed from the queue already by the time we hit the
check in the loop.

Secondly, auto-removing the wait entries also means that the wait
queue essentially gets reordered "randomly" (e.g. threads re-add
themselves in the order they got to run after being woken up).
Additionally, new requests entering wbt_wait might overtake requests
that were queued earlier, because the wait queue will be
(temporarily) empty after the wake_up_all, so the waitqueue_active
check will not stop them. This can cause certain threads to starve
under high load.

The fix is to leave the woken up requests in the queue and remove
them in finish_wait() once the current thread breaks out of the
wait loop in __wbt_wait. This will ensure new requests always
end up at the back of the queue, and they won't overtake requests
that are already in the wait queue. With that change, the loop
in wbt_wait is also in line with many other wait loops in the kernel.
Waking up just one thread drastically reduces lock contention, as
does moving the wait queue add/remove out of the loop.

A significant drop in lockdep's lock contention numbers is seen when
running the test application on the patched kernel.

Signed-off-by: Anchal Agarwal <anchalag@amazon.com>
Signed-off-by: Frank van der Linden <fllinden@amazon.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-wbt.c | 55 ++++++++++++++++++++++++-------------------------------
 1 file changed, 24 insertions(+), 31 deletions(-)

diff --git a/block/blk-wbt.c b/block/blk-wbt.c
index 461a9af11efe..1d94a20374fc 100644
--- a/block/blk-wbt.c
+++ b/block/blk-wbt.c
@@ -166,7 +166,7 @@ static void __wbt_done(struct rq_qos *rqos, enum wbt_flags wb_acct)
 		int diff = limit - inflight;
 
 		if (!inflight || diff >= rwb->wb_background / 2)
-			wake_up_all(&rqw->wait);
+			wake_up(&rqw->wait);
 	}
 }
 
@@ -474,30 +474,6 @@ static inline unsigned int get_limit(struct rq_wb *rwb, unsigned long rw)
 	return limit;
 }
 
-static inline bool may_queue(struct rq_wb *rwb, struct rq_wait *rqw,
-			     wait_queue_entry_t *wait, unsigned long rw)
-{
-	/*
-	 * inc it here even if disabled, since we'll dec it at completion.
-	 * this only happens if the task was sleeping in __wbt_wait(),
-	 * and someone turned it off at the same time.
-	 */
-	if (!rwb_enabled(rwb)) {
-		atomic_inc(&rqw->inflight);
-		return true;
-	}
-
-	/*
-	 * If the waitqueue is already active and we are not the next
-	 * in line to be woken up, wait for our turn.
-	 */
-	if (waitqueue_active(&rqw->wait) &&
-	    rqw->wait.head.next != &wait->entry)
-		return false;
-
-	return rq_wait_inc_below(rqw, get_limit(rwb, rw));
-}
-
 /*
  * Block if we will exceed our limit, or if we are currently waiting for
  * the timer to kick off queuing again.
@@ -508,16 +484,32 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 	__acquires(lock)
 {
 	struct rq_wait *rqw = get_rq_wait(rwb, wb_acct);
-	DEFINE_WAIT(wait);
+	DECLARE_WAITQUEUE(wait, current);
+
+	/*
+	* inc it here even if disabled, since we'll dec it at completion.
+	* this only happens if the task was sleeping in __wbt_wait(),
+	* and someone turned it off at the same time.
+	*/
+	if (!rwb_enabled(rwb)) {
+		atomic_inc(&rqw->inflight);
+		return;
+	}
 
-	if (may_queue(rwb, rqw, &wait, rw))
+	if (!waitqueue_active(&rqw->wait)
+		&& rq_wait_inc_below(rqw, get_limit(rwb, rw)))
 		return;
 
+	add_wait_queue_exclusive(&rqw->wait, &wait);
 	do {
-		prepare_to_wait_exclusive(&rqw->wait, &wait,
-						TASK_UNINTERRUPTIBLE);
+		set_current_state(TASK_UNINTERRUPTIBLE);
+
+		if (!rwb_enabled(rwb)) {
+			atomic_inc(&rqw->inflight);
+			break;
+		}
 
-		if (may_queue(rwb, rqw, &wait, rw))
+		if (rq_wait_inc_below(rqw, get_limit(rwb, rw)))
 			break;
 
 		if (lock) {
@@ -528,7 +520,8 @@ static void __wbt_wait(struct rq_wb *rwb, enum wbt_flags wb_acct,
 			io_schedule();
 	} while (1);
 
-	finish_wait(&rqw->wait, &wait);
+	__set_current_state(TASK_RUNNING);
+	remove_wait_queue(&rqw->wait, &wait);
 }
 
 static inline bool wbt_should_throttle(struct rq_wb *rwb, struct bio *bio)
-- 
cgit v1.2.3


From 7e4237faa7213c1cc1d0aa65a44c67ba4729ce9f Mon Sep 17 00:00:00 2001
From: nixiaoming <nixiaoming@huawei.com>
Date: Sun, 5 Aug 2018 17:10:36 +0800
Subject: selinux: cleanup dentry and inodes on error in selinuxfs

If the resource requested by d_alloc_name is not added to the linked
list through d_add, then dput needs to be called to release the
subsequent abnormal branch to avoid resource leakage.

Add missing dput to selinuxfs.c

Signed-off-by: nixiaoming <nixiaoming@huawei.com>
[PM: tweak the subject line]
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 security/selinux/selinuxfs.c | 33 +++++++++++++++++++++++++--------
 1 file changed, 25 insertions(+), 8 deletions(-)

diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c
index eb7f12ab5c33..5cc9101ab79b 100644
--- a/security/selinux/selinuxfs.c
+++ b/security/selinux/selinuxfs.c
@@ -1377,13 +1377,18 @@ static int sel_make_bools(struct selinux_fs_info *fsi)
 
 		ret = -ENOMEM;
 		inode = sel_make_inode(dir->d_sb, S_IFREG | S_IRUGO | S_IWUSR);
-		if (!inode)
+		if (!inode) {
+			dput(dentry);
 			goto out;
+		}
 
 		ret = -ENAMETOOLONG;
 		len = snprintf(page, PAGE_SIZE, "/%s/%s", BOOL_DIR_NAME, names[i]);
-		if (len >= PAGE_SIZE)
+		if (len >= PAGE_SIZE) {
+			dput(dentry);
+			iput(inode);
 			goto out;
+		}
 
 		isec = (struct inode_security_struct *)inode->i_security;
 		ret = security_genfs_sid(fsi->state, "selinuxfs", page,
@@ -1598,8 +1603,10 @@ static int sel_make_avc_files(struct dentry *dir)
 			return -ENOMEM;
 
 		inode = sel_make_inode(dir->d_sb, S_IFREG|files[i].mode);
-		if (!inode)
+		if (!inode) {
+			dput(dentry);
 			return -ENOMEM;
+		}
 
 		inode->i_fop = files[i].ops;
 		inode->i_ino = ++fsi->last_ino;
@@ -1644,8 +1651,10 @@ static int sel_make_initcon_files(struct dentry *dir)
 			return -ENOMEM;
 
 		inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO);
-		if (!inode)
+		if (!inode) {
+			dput(dentry);
 			return -ENOMEM;
+		}
 
 		inode->i_fop = &sel_initcon_ops;
 		inode->i_ino = i|SEL_INITCON_INO_OFFSET;
@@ -1745,8 +1754,10 @@ static int sel_make_perm_files(char *objclass, int classvalue,
 
 		rc = -ENOMEM;
 		inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO);
-		if (!inode)
+		if (!inode) {
+			dput(dentry);
 			goto out;
+		}
 
 		inode->i_fop = &sel_perm_ops;
 		/* i+1 since perm values are 1-indexed */
@@ -1775,8 +1786,10 @@ static int sel_make_class_dir_entries(char *classname, int index,
 		return -ENOMEM;
 
 	inode = sel_make_inode(dir->d_sb, S_IFREG|S_IRUGO);
-	if (!inode)
+	if (!inode) {
+		dput(dentry);
 		return -ENOMEM;
+	}
 
 	inode->i_fop = &sel_class_ops;
 	inode->i_ino = sel_class_to_ino(index);
@@ -1850,8 +1863,10 @@ static int sel_make_policycap(struct selinux_fs_info *fsi)
 			return -ENOMEM;
 
 		inode = sel_make_inode(fsi->sb, S_IFREG | 0444);
-		if (inode == NULL)
+		if (inode == NULL) {
+			dput(dentry);
 			return -ENOMEM;
+		}
 
 		inode->i_fop = &sel_policycap_ops;
 		inode->i_ino = iter | SEL_POLICYCAP_INO_OFFSET;
@@ -1944,8 +1959,10 @@ static int sel_fill_super(struct super_block *sb, void *data, int silent)
 
 	ret = -ENOMEM;
 	inode = sel_make_inode(sb, S_IFCHR | S_IRUGO | S_IWUGO);
-	if (!inode)
+	if (!inode) {
+		dput(dentry);
 		goto err;
+	}
 
 	inode->i_ino = ++fsi->last_ino;
 	isec = (struct inode_security_struct *)inode->i_security;
-- 
cgit v1.2.3


From 30514effc9206d4e084ec32239ae221db157d43a Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Tue, 7 Aug 2018 12:24:30 +0200
Subject: x86/mm/pti: Don't clear permissions in pti_clone_pmd()

The function sets the global-bit on cloned PMD entries, which only makes
sense when the permissions are identical between the user and the kernel
page-table. Further, only write-permissions are cleared for entry-text and
kernel-text sections, which are not writeable at the end of the boot
process.

The reason why this RW clearing exists is that in the early PTI
implementations the cloned kernel areas were set up during early boot
before the kernel text is set to read only and not touched afterwards.

This is not longer true. The cloned areas are still set up early to get the
entry code working for interrupts and other things, but after the kernel
text has been set RO the clone is repeated which copies the RO PMD/PTEs
over to the user visible clone. That means the initial clearing of the
writable bit can be avoided.

[ tglx: Amended changelog ]

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1533637471-30953-3-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 113ba14a03d8..5164c987b1f1 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -291,7 +291,7 @@ static void __init pti_setup_vsyscall(void) { }
 #endif
 
 static void
-pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
+pti_clone_pmds(unsigned long start, unsigned long end)
 {
 	unsigned long addr;
 
@@ -352,7 +352,7 @@ pti_clone_pmds(unsigned long start, unsigned long end, pmdval_t clear)
 		 * tables will share the last-level page tables of this
 		 * address range
 		 */
-		*target_pmd = pmd_clear_flags(*pmd, clear);
+		*target_pmd = *pmd;
 	}
 }
 
@@ -398,7 +398,7 @@ static void __init pti_clone_user_shared(void)
 	start = CPU_ENTRY_AREA_BASE;
 	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
 
-	pti_clone_pmds(start, end, 0);
+	pti_clone_pmds(start, end);
 }
 #endif /* CONFIG_X86_64 */
 
@@ -418,8 +418,7 @@ static void __init pti_setup_espfix64(void)
 static void pti_clone_entry_text(void)
 {
 	pti_clone_pmds((unsigned long) __entry_text_start,
-			(unsigned long) __irqentry_text_end,
-		       _PAGE_RW);
+		       (unsigned long) __irqentry_text_end);
 }
 
 /*
@@ -501,7 +500,7 @@ static void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end_clone, _PAGE_RW);
+	pti_clone_pmds(start, end_clone);
 
 	/*
 	 * pti_clone_pmds() will set the global bit in any PMDs
-- 
cgit v1.2.3


From 16a3fe634f6a568c6234b8747e5d50487fed3526 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Tue, 7 Aug 2018 12:24:31 +0200
Subject: x86/mm/pti: Clone kernel-image on PTE level for 32 bit

On 32 bit the kernel sections are not huge-page aligned.  When we clone
them on PMD-level we unevitably map some areas that are normal kernel
memory and may contain secrets to user-space. To prevent that we need to
clone the kernel-image on PTE-level for 32 bit.

Also make the page-table cloning code more general so that it can handle
PMD and PTE level cloning. This can be generalized further in the future to
also handle clones on the P4D-level.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1533637471-30953-4-git-send-email-joro@8bytes.org
---
 arch/x86/mm/pti.c | 140 ++++++++++++++++++++++++++++++++++++++----------------
 1 file changed, 99 insertions(+), 41 deletions(-)

diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 5164c987b1f1..1dc5c683e7a5 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -54,6 +54,16 @@
 #define __GFP_NOTRACK	0
 #endif
 
+/*
+ * Define the page-table levels we clone for user-space on 32
+ * and 64 bit.
+ */
+#ifdef CONFIG_X86_64
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PMD
+#else
+#define	PTI_LEVEL_KERNEL_IMAGE	PTI_CLONE_PTE
+#endif
+
 static void __init pti_print_if_insecure(const char *reason)
 {
 	if (boot_cpu_has_bug(X86_BUG_CPU_MELTDOWN))
@@ -228,7 +238,6 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
 	return pmd_offset(pud, address);
 }
 
-#ifdef CONFIG_X86_VSYSCALL_EMULATION
 /*
  * Walk the shadow copy of the page tables (optionally) trying to allocate
  * page table pages on the way down.  Does not support large pages.
@@ -270,6 +279,7 @@ static __init pte_t *pti_user_pagetable_walk_pte(unsigned long address)
 	return pte;
 }
 
+#ifdef CONFIG_X86_VSYSCALL_EMULATION
 static void __init pti_setup_vsyscall(void)
 {
 	pte_t *pte, *target_pte;
@@ -290,8 +300,14 @@ static void __init pti_setup_vsyscall(void)
 static void __init pti_setup_vsyscall(void) { }
 #endif
 
+enum pti_clone_level {
+	PTI_CLONE_PMD,
+	PTI_CLONE_PTE,
+};
+
 static void
-pti_clone_pmds(unsigned long start, unsigned long end)
+pti_clone_pgtable(unsigned long start, unsigned long end,
+		  enum pti_clone_level level)
 {
 	unsigned long addr;
 
@@ -299,7 +315,8 @@ pti_clone_pmds(unsigned long start, unsigned long end)
 	 * Clone the populated PMDs which cover start to end. These PMD areas
 	 * can have holes.
 	 */
-	for (addr = start; addr < end; addr += PMD_SIZE) {
+	for (addr = start; addr < end;) {
+		pte_t *pte, *target_pte;
 		pmd_t *pmd, *target_pmd;
 		pgd_t *pgd;
 		p4d_t *p4d;
@@ -315,44 +332,84 @@ pti_clone_pmds(unsigned long start, unsigned long end)
 		p4d = p4d_offset(pgd, addr);
 		if (WARN_ON(p4d_none(*p4d)))
 			return;
+
 		pud = pud_offset(p4d, addr);
-		if (pud_none(*pud))
+		if (pud_none(*pud)) {
+			addr += PUD_SIZE;
 			continue;
+		}
+
 		pmd = pmd_offset(pud, addr);
-		if (pmd_none(*pmd))
+		if (pmd_none(*pmd)) {
+			addr += PMD_SIZE;
 			continue;
+		}
 
-		target_pmd = pti_user_pagetable_walk_pmd(addr);
-		if (WARN_ON(!target_pmd))
-			return;
-
-		/*
-		 * Only clone present PMDs.  This ensures only setting
-		 * _PAGE_GLOBAL on present PMDs.  This should only be
-		 * called on well-known addresses anyway, so a non-
-		 * present PMD would be a surprise.
-		 */
-		if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
-			return;
-
-		/*
-		 * Setting 'target_pmd' below creates a mapping in both
-		 * the user and kernel page tables.  It is effectively
-		 * global, so set it as global in both copies.  Note:
-		 * the X86_FEATURE_PGE check is not _required_ because
-		 * the CPU ignores _PAGE_GLOBAL when PGE is not
-		 * supported.  The check keeps consistentency with
-		 * code that only set this bit when supported.
-		 */
-		if (boot_cpu_has(X86_FEATURE_PGE))
-			*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
-
-		/*
-		 * Copy the PMD.  That is, the kernelmode and usermode
-		 * tables will share the last-level page tables of this
-		 * address range
-		 */
-		*target_pmd = *pmd;
+		if (pmd_large(*pmd) || level == PTI_CLONE_PMD) {
+			target_pmd = pti_user_pagetable_walk_pmd(addr);
+			if (WARN_ON(!target_pmd))
+				return;
+
+			/*
+			 * Only clone present PMDs.  This ensures only setting
+			 * _PAGE_GLOBAL on present PMDs.  This should only be
+			 * called on well-known addresses anyway, so a non-
+			 * present PMD would be a surprise.
+			 */
+			if (WARN_ON(!(pmd_flags(*pmd) & _PAGE_PRESENT)))
+				return;
+
+			/*
+			 * Setting 'target_pmd' below creates a mapping in both
+			 * the user and kernel page tables.  It is effectively
+			 * global, so set it as global in both copies.  Note:
+			 * the X86_FEATURE_PGE check is not _required_ because
+			 * the CPU ignores _PAGE_GLOBAL when PGE is not
+			 * supported.  The check keeps consistentency with
+			 * code that only set this bit when supported.
+			 */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pmd = pmd_set_flags(*pmd, _PAGE_GLOBAL);
+
+			/*
+			 * Copy the PMD.  That is, the kernelmode and usermode
+			 * tables will share the last-level page tables of this
+			 * address range
+			 */
+			*target_pmd = *pmd;
+
+			addr += PMD_SIZE;
+
+		} else if (level == PTI_CLONE_PTE) {
+
+			/* Walk the page-table down to the pte level */
+			pte = pte_offset_kernel(pmd, addr);
+			if (pte_none(*pte)) {
+				addr += PAGE_SIZE;
+				continue;
+			}
+
+			/* Only clone present PTEs */
+			if (WARN_ON(!(pte_flags(*pte) & _PAGE_PRESENT)))
+				return;
+
+			/* Allocate PTE in the user page-table */
+			target_pte = pti_user_pagetable_walk_pte(addr);
+			if (WARN_ON(!target_pte))
+				return;
+
+			/* Set GLOBAL bit in both PTEs */
+			if (boot_cpu_has(X86_FEATURE_PGE))
+				*pte = pte_set_flags(*pte, _PAGE_GLOBAL);
+
+			/* Clone the PTE */
+			*target_pte = *pte;
+
+			addr += PAGE_SIZE;
+
+		} else {
+			BUG();
+		}
 	}
 }
 
@@ -398,7 +455,7 @@ static void __init pti_clone_user_shared(void)
 	start = CPU_ENTRY_AREA_BASE;
 	end   = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
 
-	pti_clone_pmds(start, end);
+	pti_clone_pgtable(start, end, PTI_CLONE_PMD);
 }
 #endif /* CONFIG_X86_64 */
 
@@ -417,8 +474,9 @@ static void __init pti_setup_espfix64(void)
  */
 static void pti_clone_entry_text(void)
 {
-	pti_clone_pmds((unsigned long) __entry_text_start,
-		       (unsigned long) __irqentry_text_end);
+	pti_clone_pgtable((unsigned long) __entry_text_start,
+			  (unsigned long) __irqentry_text_end,
+			  PTI_CLONE_PMD);
 }
 
 /*
@@ -500,10 +558,10 @@ static void pti_clone_kernel_text(void)
 	 * pti_set_kernel_image_nonglobal() did to clear the
 	 * global bit.
 	 */
-	pti_clone_pmds(start, end_clone);
+	pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
 
 	/*
-	 * pti_clone_pmds() will set the global bit in any PMDs
+	 * pti_clone_pgtable() will set the global bit in any PMDs
 	 * that it clones, but we also need to get any PTEs in
 	 * the last level for areas that are not huge-page-aligned.
 	 */
-- 
cgit v1.2.3


From b0a0962519e3bf03bfc5e14c1dc4c21f00f69861 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Tue, 7 Aug 2018 10:02:42 -0700
Subject: dt-bindings: net: dsa: Add compatibility strings for Broadcom Omega

Add compatibility strings for the internal switch in the Broadcom
Omega SoC family (BCM5831X/BCM1140X) to B53.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/dsa/b53.txt | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/dsa/b53.txt b/Documentation/devicetree/bindings/net/dsa/b53.txt
index 47a6a7fe0b86..1811e1972a7a 100644
--- a/Documentation/devicetree/bindings/net/dsa/b53.txt
+++ b/Documentation/devicetree/bindings/net/dsa/b53.txt
@@ -24,6 +24,14 @@ Required properties:
       "brcm,bcm53018-srab"
       "brcm,bcm53019-srab" and the mandatory "brcm,bcm5301x-srab" string
 
+  For the BCM5831X/BCM1140x SoCs with an integrated switch, must be one of:
+      "brcm,bcm11404-srab"
+      "brcm,bcm11407-srab"
+      "brcm,bcm11409-srab"
+      "brcm,bcm58310-srab"
+      "brcm,bcm58311-srab"
+      "brcm,bcm58313-srab" and the mandatory "brcm,omega-srab" string
+
   For the BCM585xx/586XX/88312 SoCs with an integrated switch, must be one of:
       "brcm,bcm58522-srab"
       "brcm,bcm58523-srab"
-- 
cgit v1.2.3


From ae7a03bbcf08737957c66c0e75238c97cc221e44 Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Tue, 7 Aug 2018 10:02:43 -0700
Subject: net: dsa: b53: Add support for Broadcom Omega SoC internal switch

Add support for the Broadcom Omega SoC internal ethernet switch
to the b53 srab driver in the DSA framework.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/b53/b53_srab.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/b53/b53_srab.c b/drivers/net/dsa/b53/b53_srab.c
index 8247481eaa06..91de2ba99ad1 100644
--- a/drivers/net/dsa/b53/b53_srab.c
+++ b/drivers/net/dsa/b53/b53_srab.c
@@ -374,6 +374,7 @@ static const struct of_device_id b53_srab_of_match[] = {
 	{ .compatible = "brcm,bcm88312-srab", .data = (void *)BCM58XX_DEVICE_ID },
 	{ .compatible = "brcm,cygnus-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ .compatible = "brcm,nsp-srab", .data = (void *)BCM58XX_DEVICE_ID },
+	{ .compatible = "brcm,omega-srab", .data = (void *)BCM583XX_DEVICE_ID },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, b53_srab_of_match);
-- 
cgit v1.2.3


From 6fdecfe32f903d9f5f35ee4464fd32ede470dcad Mon Sep 17 00:00:00 2001
From: Arun Parameswaran <arun.parameswaran@broadcom.com>
Date: Tue, 7 Aug 2018 10:02:44 -0700
Subject: net: phy: Add support for Broadcom Omega internal Combo GPHY

Add support for the Broadcom Omega SoC internal Combo Ethernet
GPHY to the bcm7xxx phy driver.

Signed-off-by: Arun Parameswaran <arun.parameswaran@broadcom.com>
Reviewed-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/bcm7xxx.c | 2 ++
 include/linux/brcmphy.h   | 1 +
 2 files changed, 3 insertions(+)

diff --git a/drivers/net/phy/bcm7xxx.c b/drivers/net/phy/bcm7xxx.c
index 01d2ff2f6241..b2b6307d64a4 100644
--- a/drivers/net/phy/bcm7xxx.c
+++ b/drivers/net/phy/bcm7xxx.c
@@ -229,6 +229,7 @@ static int bcm7xxx_28nm_config_init(struct phy_device *phydev)
 	phy_read(phydev, MII_BMSR);
 
 	switch (rev) {
+	case 0xa0:
 	case 0xb0:
 		ret = bcm7xxx_28nm_b0_afe_config_init(phydev);
 		break;
@@ -659,6 +660,7 @@ static struct phy_driver bcm7xxx_driver[] = {
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439, "Broadcom BCM7439"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7439_2, "Broadcom BCM7439 (2)"),
 	BCM7XXX_28NM_GPHY(PHY_ID_BCM7445, "Broadcom BCM7445"),
+	BCM7XXX_28NM_GPHY(PHY_ID_BCM_OMEGA, "Broadcom Omega Combo GPHY"),
 	BCM7XXX_40NM_EPHY(PHY_ID_BCM7346, "Broadcom BCM7346"),
 	BCM7XXX_40NM_EPHY(PHY_ID_BCM7362, "Broadcom BCM7362"),
 	BCM7XXX_40NM_EPHY(PHY_ID_BCM7425, "Broadcom BCM7425"),
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index daa9234a9baf..949e9af8d9d6 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -45,6 +45,7 @@
 #define PHY_ID_BCM7445			0x600d8510
 
 #define PHY_ID_BCM_CYGNUS		0xae025200
+#define PHY_ID_BCM_OMEGA		0xae025100
 
 #define PHY_BCM_OUI_MASK		0xfffffc00
 #define PHY_BCM_OUI_1			0x00206000
-- 
cgit v1.2.3


From 736ac8146404560215e7aaf4e28fc2d8746a72d1 Mon Sep 17 00:00:00 2001
From: Keara Leibovitz <kleib@mojatatu.com>
Date: Tue, 7 Aug 2018 15:18:43 -0400
Subject: tc-tests: initial version of nat action unit tests

Initial set of nat action unit tests.

Signed-off-by: Keara Leibovitz <kleib@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../selftests/tc-testing/tc-tests/actions/nat.json | 593 +++++++++++++++++++++
 1 file changed, 593 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/actions/nat.json

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
new file mode 100644
index 000000000000..0080dc2fd41c
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/nat.json
@@ -0,0 +1,593 @@
+[
+    {
+        "id": "7565",
+        "name": "Add nat action on ingress with default control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.1.1 200.200.200.1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.1.1/32 200.200.200.1 pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "fd79",
+        "name": "Add nat action on ingress with pipe control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.1.1.1 2.2.2.1 pipe index 77",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 77",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.1.1.1/32 2.2.2.1 pipe.*index 77 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "eab9",
+        "name": "Add nat action on ingress with continue control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.10.10 192.168.20.20 continue index 1000",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 1000",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.10.10/32 192.168.20.20 continue.*index 1000 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "c53a",
+        "name": "Add nat action on ingress with reclassify control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.10.10 192.168.20.20 reclassify index 1000",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 1000",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.10.10/32 192.168.20.20 reclassify.*index 1000 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "76c9",
+        "name": "Add nat action on ingress with jump control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 12.18.10.10 12.18.20.20 jump 10 index 22",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 22",
+        "matchPattern": "action order [0-9]+:  nat ingress 12.18.10.10/32 12.18.20.20 jump 10.*index 22 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "24c6",
+        "name": "Add nat action on ingress with drop control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 drop index 722",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 722",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 drop.*index 722 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "2120",
+        "name": "Add nat action on ingress with maximum index value",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 index 4294967295",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 4294967295",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 pass.*index 4294967295 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "3e9d",
+        "name": "Add nat action on ingress with invalid index value",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.18.1.1 1.18.2.2 index 4294967295555",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 4294967295555",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.18.1.1/32 1.18.2.2 pass.*index 4294967295555 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "f6c9",
+        "name": "Add nat action on ingress with invalid IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.1.1.1 1.1888.2.2 index 7",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 7",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.1.1.1/32 1.1888.2.2 pass.*index 7 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "be25",
+        "name": "Add nat action on ingress with invalid argument",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 1.1.1.1 1.18.2.2 another_arg index 12",
+        "expExitCode": "255",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 1.1.1.1/32 1.18.2.2 pass.*another_arg.*index 12 ref",
+        "matchCount": "0",
+        "teardown": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ]
+    },
+    {
+        "id": "a7bd",
+        "name": "Add nat action on ingress with DEFAULT IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress default 10.10.10.1 index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "ee1e",
+        "name": "Add nat action on ingress with ANY IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress any 10.10.10.1 index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "1de8",
+        "name": "Add nat action on ingress with ALL IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress all 10.10.10.1 index 12",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 12",
+        "matchPattern": "action order [0-9]+:  nat ingress 0.0.0.0/32 10.10.10.1 pass.*index 12 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "8dba",
+        "name": "Add nat action on egress with default control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 pass",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "19a7",
+        "name": "Add nat action on egress with pipe control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 pipe",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 pipe",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "f1d9",
+        "name": "Add nat action on egress with continue control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 continue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 continue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "6d4a",
+        "name": "Add nat action on egress with reclassify control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 reclassify",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 reclassify",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "b313",
+        "name": "Add nat action on egress with jump control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 jump 777",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 jump 777",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "d9fc",
+        "name": "Add nat action on egress with drop control action",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress 10.10.10.1 20.20.20.1 drop",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions ls action nat",
+        "matchPattern": "action order [0-9]+:  nat egress 10.10.10.1/32 20.20.20.1 drop",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "a895",
+        "name": "Add nat action on egress with DEFAULT IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress default 20.20.20.1 pipe index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "2572",
+        "name": "Add nat action on egress with ANY IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress any 20.20.20.1 pipe index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "37f3",
+        "name": "Add nat action on egress with ALL IP address",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "6054",
+        "name": "Add nat action on egress with cookie",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat egress all 20.20.20.1 pipe index 10 cookie aa1bc2d3eeff112233445566778800a1",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 10",
+        "matchPattern": "action order [0-9]+:  nat egress 0.0.0.0/32 20.20.20.1 pipe.*index 10 ref.*cookie aa1bc2d3eeff112233445566778800a1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    },
+    {
+        "id": "79d6",
+        "name": "Add nat action on ingress with cookie",
+        "category": [
+            "actions",
+            "nat"
+        ],
+        "setup": [
+            [
+                "$TC actions flush action nat",
+                0,
+                1,
+                255
+            ]
+        ],
+        "cmdUnderTest": "$TC actions add action nat ingress 192.168.1.1 10.10.10.1 reclassify index 1 cookie 112233445566778899aabbccddeeff11",
+        "expExitCode": "0",
+        "verifyCmd": "$TC actions get action nat index 1",
+        "matchPattern": "action order [0-9]+:  nat ingress 192.168.1.1/32 10.10.10.1 reclassify.*index 1 ref.*cookie 112233445566778899aabbccddeeff11",
+        "matchCount": "1",
+        "teardown": [
+            "$TC actions flush action nat"
+        ]
+    }
+]
-- 
cgit v1.2.3


From 541ad323db3a692a80c276785a15790ba52da24b Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Tue, 7 Aug 2018 19:41:55 +0300
Subject: selftests: forwarding: gre_multipath: Update next-hop statistics
 match criteria

gre_multipath test was using egress vlan_id matching on flows, for the
purpose of collecting next-hops statistics, later to be compared
against configured weights.
As matching on vlan_id on egress direction is not supported on all HW
devices, change the match criteria to use destination IP.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Acked-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/gre_multipath.sh | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/gre_multipath.sh b/tools/testing/selftests/net/forwarding/gre_multipath.sh
index 3b1e047f7617..cca2baa03fb8 100755
--- a/tools/testing/selftests/net/forwarding/gre_multipath.sh
+++ b/tools/testing/selftests/net/forwarding/gre_multipath.sh
@@ -95,10 +95,10 @@ sw1_create()
 	   nexthop dev g1b
 
 	tc qdisc add dev $ul1 clsact
-	tc filter add dev $ul1 egress pref 111 prot 802.1q \
-	   flower vlan_id 111 action pass
-	tc filter add dev $ul1 egress pref 222 prot 802.1q \
-	   flower vlan_id 222 action pass
+	tc filter add dev $ul1 egress pref 111 prot ipv4 \
+	   flower dst_ip 192.0.2.66 action pass
+	tc filter add dev $ul1 egress pref 222 prot ipv4 \
+	   flower dst_ip 192.0.2.82 action pass
 }
 
 sw1_destroy()
-- 
cgit v1.2.3


From c6d6f4c55f5cda5a7fa5a08eede0eb289937c328 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Tue, 7 Aug 2018 16:06:41 -0700
Subject: MIPS: Always specify -EB or -EL when using clang

When building using clang, always specify -EB or -EL in order to ensure
we target the desired endianness.

Since clang cross compiles using a single compiler build with multiple
targets, our -dumpmachine tests which don't specify clang's --target
argument check output based upon the build machine rather than the
machine our build will target. This means our detection of whether to
specify -EB fails miserably & we never do. Providing the endianness flag
unconditionally for clang resolves this issue & simplifies the clang
path somewhat.

Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/Makefile | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/mips/Makefile b/arch/mips/Makefile
index 1e98d22ec119..5425df002a6b 100644
--- a/arch/mips/Makefile
+++ b/arch/mips/Makefile
@@ -122,12 +122,22 @@ cflags-y += -ffreestanding
 # are used, so we kludge that here.  A bug has been filed at
 # http://gcc.gnu.org/bugzilla/show_bug.cgi?id=29413.
 #
+# clang doesn't suffer from these issues and our checks against -dumpmachine
+# don't work so well when cross compiling, since without providing --target
+# clang's output will be based upon the build machine. So for clang we simply
+# unconditionally specify -EB or -EL as appropriate.
+#
+ifeq ($(cc-name),clang)
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= -EB
+cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -EL
+else
 undef-all += -UMIPSEB -U_MIPSEB -U__MIPSEB -U__MIPSEB__
 undef-all += -UMIPSEL -U_MIPSEL -U__MIPSEL -U__MIPSEL__
 predef-be += -DMIPSEB -D_MIPSEB -D__MIPSEB -D__MIPSEB__
 predef-le += -DMIPSEL -D_MIPSEL -D__MIPSEL -D__MIPSEL__
 cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' && echo -EB $(undef-all) $(predef-be))
 cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= $(shell $(CC) -dumpmachine |grep -q 'mips.*el-.*' || echo -EL $(undef-all) $(predef-le))
+endif
 
 cflags-$(CONFIG_SB1XXX_CORELIS)	+= $(call cc-option,-mno-sched-prolog) \
 				   -fno-omit-frame-pointer
-- 
cgit v1.2.3


From 2f0025675fe51a353e308c38fc7ee0ad75151ef2 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Tue, 7 Aug 2018 16:09:56 -0700
Subject: MIPS: VDSO: Force link endianness

When building the VDSO with clang it appears to invoke ld without
specifying endianness, even though clang itself was provided with a -EB
or -EL flag. This results in the build failing due to a mismatch between
the objects that are the input to ld, and the output it is attempting to
create:

  VDSO    arch/mips/vdso/vdso.so.dbg.raw
  mips-linux-ld: arch/mips/vdso/elf.o: compiled for a big endian system
    and target is little endian
  mips-linux-ld: arch/mips/vdso/elf.o: endianness incompatible with that
    of the selected emulation
  mips-linux-ld: failed to merge target specific data of file
    arch/mips/vdso/elf.o
  ...

Work around this problem by explicitly specifying the link endianness
using -Wl,-EB or -Wl,-EL when -EB or -EL are part of KBUILD_CFLAGS. This
resolves the build failure when using clang, and doesn't have any
negative effect on gcc.

Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/vdso/Makefile | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
index bd79b27faa2b..34605ca21498 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
@@ -44,6 +44,7 @@ endif
 # VDSO linker flags.
 VDSO_LDFLAGS := \
 	-Wl,-Bsymbolic -Wl,--no-undefined -Wl,-soname=linux-vdso.so.1 \
+	$(addprefix -Wl$(comma),$(filter -E%,$(KBUILD_CFLAGS))) \
 	-nostdlib -shared \
 	$(call cc-ldoption, -Wl$(comma)--hash-style=sysv) \
 	$(call cc-ldoption, -Wl$(comma)--build-id)
-- 
cgit v1.2.3


From 9b4f43460dd0ee461f5dd65ee1efa152f2e52559 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Tue, 7 Aug 2018 16:17:28 -0700
Subject: cfq: Annotate fall-through in a switch statement

This patch avoids that gcc complains about fall-through when building
with W=1.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/cfq-iosched.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 82b6c27b3245..ec6acdd58b7a 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -3666,6 +3666,7 @@ static void cfq_init_prio_data(struct cfq_queue *cfqq, struct cfq_io_cq *cic)
 	switch (ioprio_class) {
 	default:
 		printk(KERN_ERR "cfq: bad prio %x\n", ioprio_class);
+		/* fall through */
 	case IOPRIO_CLASS_NONE:
 		/*
 		 * no prio set, inherit CPU scheduling settings
-- 
cgit v1.2.3


From f7ecb1b109da1006a08d5675debe60990e824432 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Tue, 7 Aug 2018 16:17:29 -0700
Subject: cfq: Suppress compiler warnings about comparisons

This patch does not change any functionality but avoids that gcc
reports the following warnings when building with W=1:

block/cfq-iosched.c: In function ?cfq_back_seek_max_store?:
block/cfq-iosched.c:4741:13: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  if (__data < (MIN))      \
             ^
block/cfq-iosched.c:4756:1: note: in expansion of macro ?STORE_FUNCTION?
 STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
 ^~~~~~~~~~~~~~
block/cfq-iosched.c: In function ?cfq_slice_idle_store?:
block/cfq-iosched.c:4741:13: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  if (__data < (MIN))      \
             ^
block/cfq-iosched.c:4759:1: note: in expansion of macro ?STORE_FUNCTION?
 STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
 ^~~~~~~~~~~~~~
block/cfq-iosched.c: In function ?cfq_group_idle_store?:
block/cfq-iosched.c:4741:13: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  if (__data < (MIN))      \
             ^
block/cfq-iosched.c:4760:1: note: in expansion of macro ?STORE_FUNCTION?
 STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1);
 ^~~~~~~~~~~~~~
block/cfq-iosched.c: In function ?cfq_low_latency_store?:
block/cfq-iosched.c:4741:13: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  if (__data < (MIN))      \
             ^
block/cfq-iosched.c:4765:1: note: in expansion of macro ?STORE_FUNCTION?
 STORE_FUNCTION(cfq_low_latency_store, &cfqd->cfq_latency, 0, 1, 0);
 ^~~~~~~~~~~~~~
block/cfq-iosched.c: In function ?cfq_slice_idle_us_store?:
block/cfq-iosched.c:4775:13: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  if (__data < (MIN))      \
             ^
block/cfq-iosched.c:4782:1: note: in expansion of macro ?USEC_STORE_FUNCTION?
 USEC_STORE_FUNCTION(cfq_slice_idle_us_store, &cfqd->cfq_slice_idle, 0, UINT_MAX);
 ^~~~~~~~~~~~~~~~~~~
block/cfq-iosched.c: In function ?cfq_group_idle_us_store?:
block/cfq-iosched.c:4775:13: warning: comparison of unsigned expression < 0 is always false [-Wtype-limits]
  if (__data < (MIN))      \
             ^
block/cfq-iosched.c:4783:1: note: in expansion of macro ?USEC_STORE_FUNCTION?
 USEC_STORE_FUNCTION(cfq_group_idle_us_store, &cfqd->cfq_group_idle, 0, UINT_MAX);
 ^~~~~~~~~~~~~~~~~~~

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/cfq-iosched.c | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index ec6acdd58b7a..2eb87444b157 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -4736,12 +4736,13 @@ USEC_SHOW_FUNCTION(cfq_target_latency_us_show, cfqd->cfq_target_latency);
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data;						\
+	unsigned int __data, __min = (MIN), __max = (MAX);		\
+									\
 	cfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	if (__CONV)							\
 		*(__PTR) = (u64)__data * NSEC_PER_MSEC;			\
 	else								\
@@ -4770,12 +4771,13 @@ STORE_FUNCTION(cfq_target_latency_store, &cfqd->cfq_target_latency, 1, UINT_MAX,
 static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
 {									\
 	struct cfq_data *cfqd = e->elevator_data;			\
-	unsigned int __data;						\
+	unsigned int __data, __min = (MIN), __max = (MAX);		\
+									\
 	cfq_var_store(&__data, (page));					\
-	if (__data < (MIN))						\
-		__data = (MIN);						\
-	else if (__data > (MAX))					\
-		__data = (MAX);						\
+	if (__data < __min)						\
+		__data = __min;						\
+	else if (__data > __max)					\
+		__data = __max;						\
 	*(__PTR) = (u64)__data * NSEC_PER_USEC;				\
 	return count;							\
 }
-- 
cgit v1.2.3


From 497e0049b6c8b1923ba6ccb58f3ccf840a32be7e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:09:09 -0500
Subject: 8390: axnet_cs: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114889 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/8390/axnet_cs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/8390/axnet_cs.c b/drivers/net/ethernet/8390/axnet_cs.c
index d422a124cd7c..0b6bbf63f7ca 100644
--- a/drivers/net/ethernet/8390/axnet_cs.c
+++ b/drivers/net/ethernet/8390/axnet_cs.c
@@ -610,6 +610,7 @@ static int axnet_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
     switch (cmd) {
     case SIOCGMIIPHY:
 	data->phy_id = info->phy_id;
+	/* Fall through */
     case SIOCGMIIREG:		/* Read MII PHY register. */
 	data->val_out = mdio_read(mii_addr, data->phy_id, data->reg_num & 0x1f);
 	return 0;
-- 
cgit v1.2.3


From 8ea34505060486010f27e323c741eeca5af7980e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:09:19 -0500
Subject: alteon: acenic: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114891 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/alteon/acenic.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/alteon/acenic.c b/drivers/net/ethernet/alteon/acenic.c
index 08945baee48a..4f11f98347ed 100644
--- a/drivers/net/ethernet/alteon/acenic.c
+++ b/drivers/net/ethernet/alteon/acenic.c
@@ -551,6 +551,7 @@ static int acenic_probe_one(struct pci_dev *pdev,
 			       ap->name);
 			break;
 		}
+		/* Fall through */
 	case PCI_VENDOR_ID_SGI:
 		printk(KERN_INFO "%s: SGI AceNIC ", ap->name);
 		break;
-- 
cgit v1.2.3


From bc171e87a7e29a41b119fdfccd378f7179b39c23 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:11:14 -0500
Subject: bnx2x: Mark expected switch fall-thoughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114878 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index d7f51ab85b45..8bb1e38b1681 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -1729,8 +1729,8 @@ static int bnxt_async_event_process(struct bnxt *bp,
 					    speed);
 		}
 		set_bit(BNXT_LINK_SPEED_CHNG_SP_EVENT, &bp->sp_event);
-		/* fall through */
 	}
+	/* fall through */
 	case ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE:
 		set_bit(BNXT_LINK_CHNG_SP_EVENT, &bp->sp_event);
 		break;
-- 
cgit v1.2.3


From b4bc39a3f666c3e93590aefbc00d94b95f80567f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:11:26 -0500
Subject: net: macb: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cadence/macb_ptp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c
index 678835136bf8..cd5296b84229 100644
--- a/drivers/net/ethernet/cadence/macb_ptp.c
+++ b/drivers/net/ethernet/cadence/macb_ptp.c
@@ -466,6 +466,7 @@ int gem_set_hwtst(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case HWTSTAMP_TX_ONESTEP_SYNC:
 		if (gem_ptp_set_one_step_sync(bp, 1) != 0)
 			return -ERANGE;
+		/* fall through */
 	case HWTSTAMP_TX_ON:
 		tx_bd_control = TSTAMP_ALL_FRAMES;
 		break;
-- 
cgit v1.2.3


From 19aa45d447002798ec006faddd4f491a5839bebe Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:13:05 -0500
Subject: liquidio: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 143135 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/lio_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c
index 8ef87a76692b..6fb13fa73b27 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_main.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c
@@ -2209,6 +2209,7 @@ static int liquidio_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
 	case SIOCSHWTSTAMP:
 		if (lio->oct_dev->ptp_enable)
 			return hwtstamp_ioctl(netdev, ifr);
+		/* fall through */
 	default:
 		return -EOPNOTSUPP;
 	}
-- 
cgit v1.2.3


From 20e4fb12b146cab4ca9c4f1e10c04fcd67823f43 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:13:12 -0500
Subject: cxgb4/l2t: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114910 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/l2t.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/l2t.c b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
index 77c2c538b1fd..301c4df8a566 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/l2t.c
@@ -231,6 +231,7 @@ again:
 		if (e->state == L2T_STATE_STALE)
 			e->state = L2T_STATE_VALID;
 		spin_unlock_bh(&e->lock);
+		/* fall through */
 	case L2T_STATE_VALID:     /* fast-path, send the packet on */
 		return t4_ofld_send(adap, skb);
 	case L2T_STATE_RESOLVING:
-- 
cgit v1.2.3


From d135955f550df5d61bf973a71b758384b32fe638 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:13:44 -0500
Subject: cxgb4/t4_hw: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114777 ("Missing break in switch")
Addresses-Coverity-ID: 114778 ("Missing break in switch")
Addresses-Coverity-ID: 114779 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_hw.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
index 2d9943f90a75..5fe5d16dee72 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c
@@ -7504,10 +7504,13 @@ int t4_alloc_vi(struct adapter *adap, unsigned int mbox, unsigned int port,
 		switch (nmac) {
 		case 5:
 			memcpy(mac + 24, c.nmac3, sizeof(c.nmac3));
+			/* Fall through */
 		case 4:
 			memcpy(mac + 18, c.nmac2, sizeof(c.nmac2));
+			/* Fall through */
 		case 3:
 			memcpy(mac + 12, c.nmac1, sizeof(c.nmac1));
+			/* Fall through */
 		case 2:
 			memcpy(mac + 6,  c.nmac0, sizeof(c.nmac0));
 		}
-- 
cgit v1.2.3


From 92072679a8036215b9ef8fd68d7ef9eef786a9e9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:14:18 -0500
Subject: cxgb3/l2t: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114780 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb3/l2t.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb3/l2t.c b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
index 248e40c6966c..0e9182d3f02c 100644
--- a/drivers/net/ethernet/chelsio/cxgb3/l2t.c
+++ b/drivers/net/ethernet/chelsio/cxgb3/l2t.c
@@ -136,6 +136,7 @@ again:
 		if (e->state == L2T_STATE_STALE)
 			e->state = L2T_STATE_VALID;
 		spin_unlock_bh(&e->lock);
+		/* fall through */
 	case L2T_STATE_VALID:	/* fast-path, send the packet on */
 		return cxgb3_ofld_send(dev, skb);
 	case L2T_STATE_RESOLVING:
-- 
cgit v1.2.3


From 6da5ae5f00e84b469ba52e734c856b707eac90a6 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:15:32 -0500
Subject: net: thunderx: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114781 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 5603f5ab1fee..92ba958e204e 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -527,6 +527,7 @@ static int nicvf_get_rss_hash_opts(struct nicvf *nic,
 	case SCTP_V4_FLOW:
 	case SCTP_V6_FLOW:
 		info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case IPV4_FLOW:
 	case IPV6_FLOW:
 		info->data |= RXH_IP_SRC | RXH_IP_DST;
-- 
cgit v1.2.3


From 10c7666e70d979d78bf6b8c1b6ab6dd68cd0d96b Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:15:35 -0500
Subject: net: tulip_core: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114782 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/dec/tulip/tulip_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 00d02a0967d0..3e3e08698876 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -923,6 +923,7 @@ static int private_ioctl (struct net_device *dev, struct ifreq *rq, int cmd)
 			data->phy_id = 1;
 		else
 			return -ENODEV;
+		/* Fall through */
 
 	case SIOCGMIIREG:		/* Read MII PHY register. */
 		if (data->phy_id == 32 && (tp->flags & HAS_NWAY)) {
-- 
cgit v1.2.3


From 8fc85c25c1f3f05ccc147af4c470c911afc54998 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:16:07 -0500
Subject: net: tulip: de4x5: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114784 ("Missing break in switch")
Addresses-Coverity-ID: 114785 ("Missing break in switch")
Addresses-Coverity-ID: 114786 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/dec/tulip/de4x5.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/dec/tulip/de4x5.c b/drivers/net/ethernet/dec/tulip/de4x5.c
index a31b4df3e7ff..66535d1653f6 100644
--- a/drivers/net/ethernet/dec/tulip/de4x5.c
+++ b/drivers/net/ethernet/dec/tulip/de4x5.c
@@ -3204,6 +3204,8 @@ srom_map_media(struct net_device *dev)
       case SROM_10BASETF:
 	if (!lp->params.fdx) return -1;
 	lp->fdx = true;
+	/* fall through */
+
       case SROM_10BASET:
 	if (lp->params.fdx && !lp->fdx) return -1;
 	if ((lp->chipset == DC21140) || ((lp->chipset & ~0x00ff) == DC2114x)) {
@@ -3224,6 +3226,8 @@ srom_map_media(struct net_device *dev)
       case SROM_100BASETF:
         if (!lp->params.fdx) return -1;
 	lp->fdx = true;
+	/* fall through */
+
       case SROM_100BASET:
 	if (lp->params.fdx && !lp->fdx) return -1;
 	lp->media = _100Mb;
@@ -3236,6 +3240,8 @@ srom_map_media(struct net_device *dev)
       case SROM_100BASEFF:
 	if (!lp->params.fdx) return -1;
 	lp->fdx = true;
+	/* fall through */
+
       case SROM_100BASEF:
 	if (lp->params.fdx && !lp->fdx) return -1;
 	lp->media = _100Mb;
-- 
cgit v1.2.3


From 40f99eda21bd14c7bbc62caee42c9b604ea24f6e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:17:08 -0500
Subject: be2net: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114787 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/be_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c
index 7f7e206f95f8..3f6749fc889f 100644
--- a/drivers/net/ethernet/emulex/benet/be_ethtool.c
+++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c
@@ -575,6 +575,7 @@ static u32 convert_to_et_setting(struct be_adapter *adapter, u32 if_speeds)
 				break;
 			}
 		}
+		/* fall through */
 	case PHY_TYPE_SFP_PLUS_10GB:
 	case PHY_TYPE_XFP_10GB:
 	case PHY_TYPE_SFP_1GB:
-- 
cgit v1.2.3


From 1e14ef19fb49ed6f822129ce7bc819a462b88e11 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:17:50 -0500
Subject: net: hns: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114788 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns/hns_ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 3957205abb81..08f3c4743f74 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -307,6 +307,7 @@ static int __lb_setup(struct net_device *ndev,
 		break;
 	case MAC_LOOP_PHY_NONE:
 		ret = hns_nic_config_phy_loopback(phy_dev, 0x0);
+		/* fall through */
 	case MAC_LOOP_NONE:
 		if (!ret && h->dev->ops->set_loopback) {
 			if (priv->ae_handle->phy_if != PHY_INTERFACE_MODE_XGMII)
-- 
cgit v1.2.3


From be44b3afa98205607a7930b155557ccda9efd1e2 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:18:30 -0500
Subject: net: hns3: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114789 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index bd031af38a96..a64d69c87f13 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2104,6 +2104,7 @@ static void hns3_rx_checksum(struct hns3_enet_ring *ring, struct sk_buff *skb,
 	case HNS3_OL4_TYPE_MAC_IN_UDP:
 	case HNS3_OL4_TYPE_NVGRE:
 		skb->csum_level = 1;
+		/* fall through */
 	case HNS3_OL4_TYPE_NO_TUN:
 		/* Can checksum ipv4 or ipv6 + UDP/TCP/SCTP packets */
 		if ((l3_type == HNS3_L3_TYPE_IPV4 ||
-- 
cgit v1.2.3


From 1e84374f1c3c233c64be6122742c85446c774689 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:19:42 -0500
Subject: i40e_main: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114790 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index a730f48b102c..f2c622e78802 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -1800,6 +1800,7 @@ static void i40e_vsi_setup_queue_map(struct i40e_vsi *vsi,
 						       num_tc_qps);
 					break;
 				}
+				/* fall through */
 			case I40E_VSI_FDIR:
 			case I40E_VSI_SRIOV:
 			case I40E_VSI_VMDQ2:
-- 
cgit v1.2.3


From f7c3ca2da4640143f04fc50dba74804be02c16ac Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:20:27 -0500
Subject: i40e_txrx: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114791 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/i40e/i40e_txrx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index b151ae316546..b5042d1a63c0 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2253,9 +2253,10 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring,
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
 	case XDP_ABORTED:
 		trace_xdp_exception(rx_ring->netdev, xdp_prog, act);
-		/* fallthrough -- handle aborts by dropping packet */
+		/* fall through -- handle aborts by dropping packet */
 	case XDP_DROP:
 		result = I40E_XDP_CONSUMED;
 		break;
-- 
cgit v1.2.3


From 49a9776fe5d62fd4ff87406efa390a5de9f5f07d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:21:05 -0500
Subject: net/mlx4/mcg: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114792 ("Missing break in switch")
Addresses-Coverity-ID: 114793 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/mcg.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index 4c5306dbcf11..ffed2d4c9403 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1412,6 +1412,7 @@ int mlx4_multicast_attach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	case MLX4_STEERING_MODE_A0:
 		if (prot == MLX4_PROT_ETH)
 			return 0;
+		/* fall through */
 
 	case MLX4_STEERING_MODE_B0:
 		if (prot == MLX4_PROT_ETH)
@@ -1441,6 +1442,7 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 	case MLX4_STEERING_MODE_A0:
 		if (prot == MLX4_PROT_ETH)
 			return 0;
+		/* fall through */
 
 	case MLX4_STEERING_MODE_B0:
 		if (prot == MLX4_PROT_ETH)
-- 
cgit v1.2.3


From c8581f2bb5dd02d14be61ed9faa052a693a3960e Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:21:40 -0500
Subject: net/mlx4/en_rx: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114794 ("Missing break in switch")
Addresses-Coverity-ID: 114795 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 3360f7b9ee73..a1aeeb8094c3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -795,8 +795,10 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 				goto xdp_drop_no_cnt; /* Drop on xmit failure */
 			default:
 				bpf_warn_invalid_xdp_action(act);
+				/* fall through */
 			case XDP_ABORTED:
 				trace_xdp_exception(dev, xdp_prog, act);
+				/* fall through */
 			case XDP_DROP:
 				ring->xdp_drop++;
 xdp_drop_no_cnt:
-- 
cgit v1.2.3


From 7e9660ff6ff1c154f2590ade0ac3ad563f1522ab Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:22:22 -0500
Subject: igb_main: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 200521 ("Missing break in switch")
Addresses-Coverity-ID: 114797 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 25720d95d4ea..221a735dc956 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -5176,6 +5176,7 @@ bool igb_has_link(struct igb_adapter *adapter)
 	case e1000_media_type_copper:
 		if (!hw->mac.get_link_status)
 			return true;
+		/* fall through */
 	case e1000_media_type_internal_serdes:
 		hw->mac.ops.check_for_link(hw);
 		link_active = !hw->mac.get_link_status;
@@ -5836,6 +5837,7 @@ csum_failed:
 			type_tucmd = E1000_ADVTXD_TUCMD_L4T_SCTP;
 			break;
 		}
+		/* fall through */
 	default:
 		skb_checksum_help(skb);
 		goto csum_failed;
-- 
cgit v1.2.3


From b9e0e23f918bafddaaf3b91b099f027679a77467 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:22:57 -0500
Subject: igb: e1000_82575: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114799 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/e1000_82575.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c
index a795c07d0df7..bafdcf70a353 100644
--- a/drivers/net/ethernet/intel/igb/e1000_82575.c
+++ b/drivers/net/ethernet/intel/igb/e1000_82575.c
@@ -1708,6 +1708,7 @@ static s32 igb_setup_serdes_link_82575(struct e1000_hw *hw)
 	case E1000_CTRL_EXT_LINK_MODE_1000BASE_KX:
 		/* disable PCS autoneg and support parallel detect only */
 		pcs_autoneg = false;
+		/* fall through */
 	default:
 		if (hw->mac.type == e1000_82575 ||
 		    hw->mac.type == e1000_82576) {
-- 
cgit v1.2.3


From eed05a094a0dd03f181d3fd65e4be375d88a582c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:23:31 -0500
Subject: igb: e1000_phy: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114800 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igb/e1000_phy.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c
index 2be0e762ec69..ad2125e5a7f7 100644
--- a/drivers/net/ethernet/intel/igb/e1000_phy.c
+++ b/drivers/net/ethernet/intel/igb/e1000_phy.c
@@ -659,6 +659,7 @@ s32 igb_copper_link_setup_m88_gen2(struct e1000_hw *hw)
 			phy_data |= M88E1000_PSCR_AUTO_X_1000T;
 			break;
 		}
+		/* fall through */
 	case 0:
 	default:
 		phy_data |= M88E1000_PSCR_AUTO_X_MODE;
-- 
cgit v1.2.3


From 76df93b1779563cda9d38237e5b6422df9ebd2e5 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:24:04 -0500
Subject: igbvf: netdev: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114801 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/intel/igbvf/netdev.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index f818f060e5a7..e0c989ffb2b3 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -2102,6 +2102,7 @@ csum_failed:
 			type_tucmd = E1000_ADVTXD_TUCMD_L4T_SCTP;
 			break;
 		}
+		/* fall through */
 	default:
 		skb_checksum_help(skb);
 		goto csum_failed;
-- 
cgit v1.2.3


From 9d81e6a3f64315fa3af3e8f880bbfda35be04188 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:24:38 -0500
Subject: vxge: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114796 ("Missing break in switch")
Addresses-Coverity-ID: 114804 ("Missing break in switch")
Addresses-Coverity-ID: 114806 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/neterion/vxge/vxge-config.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index a2c0a93ca8b6..ae8149831e47 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -3783,17 +3783,20 @@ vxge_hw_rts_rth_data0_data1_get(u32 j, u64 *data0, u64 *data1,
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_DATA(
 			itable[j]);
+		/* fall through */
 	case 2:
 		*data0 |=
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_NUM(j)|
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_DATA(
 			itable[j]);
+		/* fall through */
 	case 3:
 		*data1 = VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_NUM(j)|
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_ENTRY_EN |
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_DATA(
 			itable[j]);
+		/* fall through */
 	case 4:
 		*data1 |=
 			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_NUM(j)|
-- 
cgit v1.2.3


From e77f02b812ccb10396d9e5a9a23db14983a344a9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:25:26 -0500
Subject: net/mlx5e: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114808 ("Missing break in switch")
Addresses-Coverity-ID: 114802 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 1881468dbcfa..ad6d471d00dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -91,9 +91,11 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di,
 		return true;
 	default:
 		bpf_warn_invalid_xdp_action(act);
+		/* fall through */
 	case XDP_ABORTED:
 xdp_abort:
 		trace_xdp_exception(rq->netdev, prog, act);
+		/* fall through */
 	case XDP_DROP:
 		rq->stats->xdp_drop++;
 		return true;
-- 
cgit v1.2.3


From 53a42286f29f88663d7b40922eca978c88e69709 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:25:57 -0500
Subject: qed: qed_dev: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I replaced the code comments with
a proper "fall through" annotation, which is what GCC is expecting
to find.

Addresses-Coverity-ID: 114809 ("Missing break in switch")
Addresses-Coverity-ID: 114810 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_dev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c
index d1ae11ab7927..016ca8a7ec8a 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_dev.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c
@@ -1789,14 +1789,14 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params)
 						p_hwfn->hw_info.hw_mode);
 			if (rc)
 				break;
-		/* Fall into */
+		/* Fall through */
 		case FW_MSG_CODE_DRV_LOAD_PORT:
 			rc = qed_hw_init_port(p_hwfn, p_hwfn->p_main_ptt,
 					      p_hwfn->hw_info.hw_mode);
 			if (rc)
 				break;
 
-		/* Fall into */
+		/* Fall through */
 		case FW_MSG_CODE_DRV_LOAD_FUNCTION:
 			rc = qed_hw_init_pf(p_hwfn, p_hwfn->p_main_ptt,
 					    p_params->p_tunn,
-- 
cgit v1.2.3


From fd3da12dba0d91d817adc4a6037513906bb4e8e9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:26:49 -0500
Subject: netxen_nic: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1410182 ("Missing break in switch")
Addresses-Coverity-ID: 1410183 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
index 3157f97dd782..3c1be87cdfa5 100644
--- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_ethtool.c
@@ -167,9 +167,9 @@ skip:
 	case NETXEN_BRDTYPE_P3_REF_QG:
 	case NETXEN_BRDTYPE_P3_4_GB:
 	case NETXEN_BRDTYPE_P3_4_GB_MM:
-
 		supported |= SUPPORTED_Autoneg;
 		advertising |= ADVERTISED_Autoneg;
+		/* fall through */
 	case NETXEN_BRDTYPE_P2_SB31_10G_CX4:
 	case NETXEN_BRDTYPE_P3_10G_CX4:
 	case NETXEN_BRDTYPE_P3_10G_CX4_LP:
@@ -198,6 +198,7 @@ skip:
 		supported |= SUPPORTED_TP;
 		check_sfp_module = netif_running(dev) &&
 			adapter->has_link_events;
+		/* fall through */
 	case NETXEN_BRDTYPE_P2_SB31_10G:
 	case NETXEN_BRDTYPE_P3_10G_XFP:
 		supported |= SUPPORTED_FIBRE;
-- 
cgit v1.2.3


From b84ad65a75f36abfe20b3c9386e8377982ca8eaa Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:27:36 -0500
Subject: qede: qede_fp: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1384501 ("Missing break in switch")
Addresses-Coverity-ID: 1398869 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_fp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 6c702399b801..8c9e95ba9917 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -1119,8 +1119,10 @@ static bool qede_rx_xdp(struct qede_dev *edev,
 
 	default:
 		bpf_warn_invalid_xdp_action(act);
+		/* Fall through */
 	case XDP_ABORTED:
 		trace_xdp_exception(edev->ndev, prog, act);
+		/* Fall through */
 	case XDP_DROP:
 		qede_recycle_rx_bd_ring(rxq, cqe->bd_num);
 	}
-- 
cgit v1.2.3


From d19911ca0521623bcc306738f7a1298f9f56d3c9 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:28:20 -0500
Subject: qlcnic: Mark expected switch fall-througs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1410181 ("Missing break in switch")
Addresses-Coverity-ID: 1410184 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
index 7f7deeaf1cf0..3b0adda7cc9c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_ethtool.c
@@ -351,9 +351,9 @@ skip:
 	case QLCNIC_BRDTYPE_P3P_REF_QG:
 	case QLCNIC_BRDTYPE_P3P_4_GB:
 	case QLCNIC_BRDTYPE_P3P_4_GB_MM:
-
 		supported |= SUPPORTED_Autoneg;
 		advertising |= ADVERTISED_Autoneg;
+		/* fall through */
 	case QLCNIC_BRDTYPE_P3P_10G_CX4:
 	case QLCNIC_BRDTYPE_P3P_10G_CX4_LP:
 	case QLCNIC_BRDTYPE_P3P_10000_BASE_T:
@@ -377,6 +377,7 @@ skip:
 		supported |= SUPPORTED_TP;
 		check_sfp_module = netif_running(adapter->netdev) &&
 				   ahw->has_link_events;
+		/* fall through */
 	case QLCNIC_BRDTYPE_P3P_10G_XFP:
 		supported |= SUPPORTED_FIBRE;
 		advertising |= ADVERTISED_FIBRE;
-- 
cgit v1.2.3


From 201e894570b182ab6e49097ed3b3fcc1a7e3cf3c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:29:12 -0500
Subject: qlge: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114811 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlge/qlge_mpi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c b/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
index 4be65d6761b3..957c72985a06 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c
@@ -1176,6 +1176,7 @@ void ql_mpi_idc_work(struct work_struct *work)
 	case MB_CMD_PORT_RESET:
 	case MB_CMD_STOP_FW:
 		ql_link_off(qdev);
+		/* Fall through */
 	case MB_CMD_SET_PORT_CFG:
 		/* Signal the resulting link up AEN
 		 * that the frame routing and mac addr
-- 
cgit v1.2.3


From 4e50ffcf1fb65375bed0cdb44ee369f33ee3729d Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:30:22 -0500
Subject: net: ethernet: sxgbe: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1357414 ("Missing break in switch")
Addresses-Coverity-ID: 1357415 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
index 542b67d436df..c9aad0eda57f 100644
--- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
+++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_ethtool.c
@@ -319,6 +319,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -329,6 +330,7 @@ static int sxgbe_get_rss_hash_opts(struct sxgbe_priv_data *priv,
 	case TCP_V6_FLOW:
 	case UDP_V6_FLOW:
 		cmd->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+		/* Fall through */
 	case SCTP_V6_FLOW:
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
-- 
cgit v1.2.3


From 5683a7a6972059611ea164be0529fdb8db28938c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:31:16 -0500
Subject: net: sfc: falcon: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1384500 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/sfc/falcon/ethtool.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/sfc/falcon/ethtool.c b/drivers/net/ethernet/sfc/falcon/ethtool.c
index 56049157a5af..1ccdb7a82e2a 100644
--- a/drivers/net/ethernet/sfc/falcon/ethtool.c
+++ b/drivers/net/ethernet/sfc/falcon/ethtool.c
@@ -963,6 +963,7 @@ ef4_ethtool_get_rxnfc(struct net_device *net_dev,
 		switch (info->flow_type) {
 		case TCP_V4_FLOW:
 			info->data |= RXH_L4_B_0_1 | RXH_L4_B_2_3;
+			/* Fall through */
 		case UDP_V4_FLOW:
 		case SCTP_V4_FLOW:
 		case AH_ESP_V4_FLOW:
-- 
cgit v1.2.3


From 681685a1ce060c4fd69b0a1124ef40baadb330a4 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:31:46 -0500
Subject: net: tlan: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 141440 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/tlan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ti/tlan.c b/drivers/net/ethernet/ti/tlan.c
index c769cd9d11e7..93d142867c2a 100644
--- a/drivers/net/ethernet/ti/tlan.c
+++ b/drivers/net/ethernet/ti/tlan.c
@@ -966,6 +966,7 @@ static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 	switch (cmd) {
 	case SIOCGMIIPHY:		/* get address of MII PHY in use. */
 		data->phy_id = phy;
+		/* fall through */
 
 
 	case SIOCGMIIREG:		/* read MII PHY register. */
-- 
cgit v1.2.3


From e38c2e11ebcc2bd13aa8220bc4ccce5228030526 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:32:19 -0500
Subject: net: ethernet: ti: cpts: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114813 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/cpts.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index b4ea58dc8caf..b96b93c686bf 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -161,6 +161,7 @@ static int cpts_fifo_read(struct cpts *cpts, int match)
 				 */
 				break;
 			}
+			/* fall through */
 		case CPTS_EV_PUSH:
 		case CPTS_EV_RX:
 			list_del_init(&event->list);
-- 
cgit v1.2.3


From e93dd8a1ac3141290936f174b81f4a9ba0c1c8a6 Mon Sep 17 00:00:00 2001
From: Moritz Fischer <mdf@kernel.org>
Date: Tue, 7 Aug 2018 16:35:20 -0700
Subject: net: nixge: Get rid of unused struct member 'last_link'

Get rid of unused struct member 'last_link'

Signed-off-by: Moritz Fischer <mdf@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ni/nixge.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 09f674ec0f9e..9ae4fcef725e 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -155,7 +155,6 @@ struct nixge_priv {
 
 	int tx_irq;
 	int rx_irq;
-	u32 last_link;
 
 	/* Buffer descriptors */
 	struct nixge_hw_dma_bd *tx_bd_v;
-- 
cgit v1.2.3


From f22cc87f6c1f771b57c407555cfefd811cdd9507 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 7 Aug 2018 15:09:36 -0700
Subject: x86/speculation/l1tf: Invert all not present mappings

For kernel mappings PAGE_PROTNONE is not necessarily set for a non present
mapping, but the inversion logic explicitely checks for !PRESENT and
PROT_NONE.

Remove the PROT_NONE check and make the inversion unconditional for all not
present mappings.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/pgtable-invert.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/pgtable-invert.h b/arch/x86/include/asm/pgtable-invert.h
index 177564187fc0..44b1203ece12 100644
--- a/arch/x86/include/asm/pgtable-invert.h
+++ b/arch/x86/include/asm/pgtable-invert.h
@@ -6,7 +6,7 @@
 
 static inline bool __pte_needs_invert(u64 val)
 {
-	return (val & (_PAGE_PRESENT|_PAGE_PROTNONE)) == _PAGE_PROTNONE;
+	return !(val & _PAGE_PRESENT);
 }
 
 /* Get a mask to xor with the page table entry to get the correct pfn. */
-- 
cgit v1.2.3


From 0768f91530ff46683e0b372df14fd79fe8d156e5 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 7 Aug 2018 15:09:37 -0700
Subject: x86/speculation/l1tf: Make pmd/pud_mknotpresent() invert

Some cases in THP like:
  - MADV_FREE
  - mprotect
  - split

mark the PMD non present for temporarily to prevent races. The window for
an L1TF attack in these contexts is very small, but it wants to be fixed
for correctness sake.

Use the proper low level functions for pmd/pud_mknotpresent() to address
this.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/pgtable.h | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index df58cdbad841..13125aad804c 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -410,11 +410,6 @@ static inline pmd_t pmd_mkwrite(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_RW);
 }
 
-static inline pmd_t pmd_mknotpresent(pmd_t pmd)
-{
-	return pmd_clear_flags(pmd, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
 static inline pud_t pud_set_flags(pud_t pud, pudval_t set)
 {
 	pudval_t v = native_pud_val(pud);
@@ -469,11 +464,6 @@ static inline pud_t pud_mkwrite(pud_t pud)
 	return pud_set_flags(pud, _PAGE_RW);
 }
 
-static inline pud_t pud_mknotpresent(pud_t pud)
-{
-	return pud_clear_flags(pud, _PAGE_PRESENT | _PAGE_PROTNONE);
-}
-
 #ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY
 static inline int pte_soft_dirty(pte_t pte)
 {
@@ -577,6 +567,18 @@ static inline pud_t pfn_pud(unsigned long page_nr, pgprot_t pgprot)
 	return __pud(pfn | check_pgprot(pgprot));
 }
 
+static inline pmd_t pmd_mknotpresent(pmd_t pmd)
+{
+	return pfn_pmd(pmd_pfn(pmd),
+		      __pgprot(pmd_flags(pmd) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
+}
+
+static inline pud_t pud_mknotpresent(pud_t pud)
+{
+	return pfn_pud(pud_pfn(pud),
+	      __pgprot(pud_flags(pud) & ~(_PAGE_PRESENT|_PAGE_PROTNONE)));
+}
+
 static inline u64 flip_protnone_guard(u64 oldval, u64 val, u64 mask);
 
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
-- 
cgit v1.2.3


From 958f79b9ee55dfaf00c8106ed1c22a2919e0028b Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 7 Aug 2018 15:09:39 -0700
Subject: x86/mm/pat: Make set_memory_np() L1TF safe

set_memory_np() is used to mark kernel mappings not present, but it has
it's own open coded mechanism which does not have the L1TF protection of
inverting the address bits.

Replace the open coded PTE manipulation with the L1TF protecting low level
PTE routines.

Passes the CPA self test.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/pageattr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 3bded76e8d5c..7bb6f65c79de 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1014,8 +1014,8 @@ static long populate_pmd(struct cpa_data *cpa,
 
 		pmd = pmd_offset(pud, start);
 
-		set_pmd(pmd, __pmd(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
-				   massage_pgprot(pmd_pgprot)));
+		set_pmd(pmd, pmd_mkhuge(pfn_pmd(cpa->pfn,
+					canon_pgprot(pmd_pgprot))));
 
 		start	  += PMD_SIZE;
 		cpa->pfn  += PMD_SIZE >> PAGE_SHIFT;
@@ -1087,8 +1087,8 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, p4d_t *p4d,
 	 * Map everything starting from the Gb boundary, possibly with 1G pages
 	 */
 	while (boot_cpu_has(X86_FEATURE_GBPAGES) && end - start >= PUD_SIZE) {
-		set_pud(pud, __pud(cpa->pfn << PAGE_SHIFT | _PAGE_PSE |
-				   massage_pgprot(pud_pgprot)));
+		set_pud(pud, pud_mkhuge(pfn_pud(cpa->pfn,
+				   canon_pgprot(pud_pgprot))));
 
 		start	  += PUD_SIZE;
 		cpa->pfn  += PUD_SIZE >> PAGE_SHIFT;
-- 
cgit v1.2.3


From f861e3e28a3016a2064d9f600eaa92a530b732b4 Mon Sep 17 00:00:00 2001
From: Matthias Kaehlcke <mka@chromium.org>
Date: Tue, 7 Aug 2018 10:19:40 -0700
Subject: ASoC: rt5677: Fix initialization of rt5677_of_match.data

The driver expects to find the device id in rt5677_of_match.data, however
it is currently assigned to rt5677_of_match.type. Fix this.

The problem was found with the help of clang:
  sound/soc/codecs/rt5677.c:5010:36: warning: expression which evaluates to
  zero treated as a null pointer constant of type 'const void *'
  [-Wnon-literal-null-conversion]
    { .compatible = "realtek,rt5677", RT5677 },
                                      ^~~~~~

Fixes: ddc9e69b9dc2 ("ASoC: rt5677: Hide platform data in the module sources")
Signed-off-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Guenter Roeck <groeck@chromium.org>
Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt5677.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 922becfee59b..9b7a1833d331 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -5008,7 +5008,7 @@ static const struct regmap_config rt5677_regmap = {
 };
 
 static const struct of_device_id rt5677_of_match[] = {
-	{ .compatible = "realtek,rt5677", RT5677 },
+	{ .compatible = "realtek,rt5677", .data = (const void *)RT5677 },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, rt5677_of_match);
-- 
cgit v1.2.3


From 5e9384c705fcfa6bf6d3937967df3ab1f5e414cb Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 7 Aug 2018 18:18:25 +0200
Subject: regulator: maxim: Add SPDX license identifiers

Replace GPL v2.0 and v2.0+ license statements with SPDX license
identifiers.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/max14577-regulator.c         | 22 +++++------------
 drivers/regulator/max77686-regulator.c         | 32 +++++++-----------------
 drivers/regulator/max77693-regulator.c         | 32 +++++++-----------------
 drivers/regulator/max77802-regulator.c         | 34 +++++++++-----------------
 drivers/regulator/max8997-regulator.c          | 30 ++++++-----------------
 drivers/regulator/max8998.c                    | 28 ++++++---------------
 include/dt-bindings/regulator/maxim,max77802.h |  5 +---
 7 files changed, 52 insertions(+), 131 deletions(-)

diff --git a/drivers/regulator/max14577-regulator.c b/drivers/regulator/max14577-regulator.c
index 0db288ce319c..bc7f4751bf9c 100644
--- a/drivers/regulator/max14577-regulator.c
+++ b/drivers/regulator/max14577-regulator.c
@@ -1,19 +1,9 @@
-/*
- * max14577.c - Regulator driver for the Maxim 14577/77836
- *
- * Copyright (C) 2013,2014 Samsung Electronics
- * Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max14577.c - Regulator driver for the Maxim 14577/77836
+//
+// Copyright (C) 2013,2014 Samsung Electronics
+// Krzysztof Kozlowski <krzk@kernel.org>
 
 #include <linux/module.h>
 #include <linux/platform_device.h>
diff --git a/drivers/regulator/max77686-regulator.c b/drivers/regulator/max77686-regulator.c
index c301f3733475..bee060937f56 100644
--- a/drivers/regulator/max77686-regulator.c
+++ b/drivers/regulator/max77686-regulator.c
@@ -1,26 +1,12 @@
-/*
- * max77686.c - Regulator driver for the Maxim 77686
- *
- * Copyright (C) 2012 Samsung Electronics
- * Chiwoong Byun <woong.byun@samsung.com>
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max8997.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77686.c - Regulator driver for the Maxim 77686
+//
+// Copyright (C) 2012 Samsung Electronics
+// Chiwoong Byun <woong.byun@samsung.com>
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+//
+// This driver is based on max8997.c
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
diff --git a/drivers/regulator/max77693-regulator.c b/drivers/regulator/max77693-regulator.c
index e7000e777292..077ecbbfdf76 100644
--- a/drivers/regulator/max77693-regulator.c
+++ b/drivers/regulator/max77693-regulator.c
@@ -1,26 +1,12 @@
-/*
- * max77693.c - Regulator driver for the Maxim 77693 and 77843
- *
- * Copyright (C) 2013-2015 Samsung Electronics
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- * Krzysztof Kozlowski <krzk@kernel.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max77686.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77693.c - Regulator driver for the Maxim 77693 and 77843
+//
+// Copyright (C) 2013-2015 Samsung Electronics
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+// Krzysztof Kozlowski <krzk@kernel.org>
+//
+// This driver is based on max77686.c
 
 #include <linux/err.h>
 #include <linux/slab.h>
diff --git a/drivers/regulator/max77802-regulator.c b/drivers/regulator/max77802-regulator.c
index b6261903818c..c30cf5c9f2de 100644
--- a/drivers/regulator/max77802-regulator.c
+++ b/drivers/regulator/max77802-regulator.c
@@ -1,25 +1,15 @@
-/*
- * max77802.c - Regulator driver for the Maxim 77802
- *
- * Copyright (C) 2013-2014 Google, Inc
- * Simon Glass <sjg@chromium.org>
- *
- * Copyright (C) 2012 Samsung Electronics
- * Chiwoong Byun <woong.byun@samsung.com>
- * Jonghwa Lee <jonghwa3.lee@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * This driver is based on max8997.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max77802.c - Regulator driver for the Maxim 77802
+//
+// Copyright (C) 2013-2014 Google, Inc
+// Simon Glass <sjg@chromium.org>
+//
+// Copyright (C) 2012 Samsung Electronics
+// Chiwoong Byun <woong.byun@samsung.com>
+// Jonghwa Lee <jonghwa3.lee@samsung.com>
+//
+// This driver is based on max8997.c
 
 #include <linux/kernel.h>
 #include <linux/bug.h>
diff --git a/drivers/regulator/max8997-regulator.c b/drivers/regulator/max8997-regulator.c
index 029a6ee426ab..ad0c806b0737 100644
--- a/drivers/regulator/max8997-regulator.c
+++ b/drivers/regulator/max8997-regulator.c
@@ -1,25 +1,11 @@
-/*
- * max8997.c - Regulator driver for the Maxim 8997/8966
- *
- * Copyright (C) 2011 Samsung Electronics
- * MyungJoo Ham <myungjoo.ham@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- *
- * This driver is based on max8998.c
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max8997.c - Regulator driver for the Maxim 8997/8966
+//
+// Copyright (C) 2011 Samsung Electronics
+// MyungJoo Ham <myungjoo.ham@samsung.com>
+//
+// This driver is based on max8998.c
 
 #include <linux/bug.h>
 #include <linux/err.h>
diff --git a/drivers/regulator/max8998.c b/drivers/regulator/max8998.c
index 6b9f262ebbb0..271bb736f3f5 100644
--- a/drivers/regulator/max8998.c
+++ b/drivers/regulator/max8998.c
@@ -1,24 +1,10 @@
-/*
- * max8998.c - Voltage regulator driver for the Maxim 8998
- *
- *  Copyright (C) 2009-2010 Samsung Electronics
- *  Kyungmin Park <kyungmin.park@samsung.com>
- *  Marek Szyprowski <m.szyprowski@samsung.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// max8998.c - Voltage regulator driver for the Maxim 8998
+//
+//  Copyright (C) 2009-2010 Samsung Electronics
+//  Kyungmin Park <kyungmin.park@samsung.com>
+//  Marek Szyprowski <m.szyprowski@samsung.com>
 
 #include <linux/module.h>
 #include <linux/init.h>
diff --git a/include/dt-bindings/regulator/maxim,max77802.h b/include/dt-bindings/regulator/maxim,max77802.h
index cf28631d7109..d0baba1973d4 100644
--- a/include/dt-bindings/regulator/maxim,max77802.h
+++ b/include/dt-bindings/regulator/maxim,max77802.h
@@ -1,10 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2014 Google, Inc
  *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
  * Device Tree binding constants for the Maxim 77802 PMIC regulators
  */
 
-- 
cgit v1.2.3


From 4f3fb287358337d739bd2186769a8c74aae19ac6 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Tue, 7 Aug 2018 18:18:26 +0200
Subject: regulator: samsung: Add SPDX license identifiers

Replace GPL v2.0+ license statements with SPDX license
identifiers.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/s2mpa01.c | 14 ++++----------
 drivers/regulator/s2mps11.c | 21 ++++-----------------
 drivers/regulator/s5m8767.c | 16 ++++------------
 3 files changed, 12 insertions(+), 39 deletions(-)

diff --git a/drivers/regulator/s2mpa01.c b/drivers/regulator/s2mpa01.c
index 48f0ca90743c..095d25f3d2ea 100644
--- a/drivers/regulator/s2mpa01.c
+++ b/drivers/regulator/s2mpa01.c
@@ -1,13 +1,7 @@
-/*
- * Copyright (c) 2013 Samsung Electronics Co., Ltd
- *		http://www.samsung.com
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2013 Samsung Electronics Co., Ltd
+//		http://www.samsung.com
 
 #include <linux/bug.h>
 #include <linux/err.h>
diff --git a/drivers/regulator/s2mps11.c b/drivers/regulator/s2mps11.c
index d1207ec683db..5bb6f4ca48db 100644
--- a/drivers/regulator/s2mps11.c
+++ b/drivers/regulator/s2mps11.c
@@ -1,20 +1,7 @@
-/*
- * s2mps11.c
- *
- * Copyright (c) 2012-2014 Samsung Electronics Co., Ltd
- *              http://www.samsung.com
- *
- * This program is free software; you can redistribute  it and/or modify it
- * under  the terms of  the GNU General  Public License as published by the
- * Free Software Foundation;  either version 2 of the  License, or (at your
- * option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2012-2014 Samsung Electronics Co., Ltd
+//              http://www.samsung.com
 
 #include <linux/bug.h>
 #include <linux/err.h>
diff --git a/drivers/regulator/s5m8767.c b/drivers/regulator/s5m8767.c
index 0cbc980753c2..667d16dc83ce 100644
--- a/drivers/regulator/s5m8767.c
+++ b/drivers/regulator/s5m8767.c
@@ -1,15 +1,7 @@
-/*
- * s5m8767.c
- *
- * Copyright (c) 2011 Samsung Electronics Co., Ltd
- *              http://www.samsung.com
- *
- *  This program is free software; you can redistribute  it and/or modify it
- *  under  the terms of  the GNU General  Public License as published by the
- *  Free Software Foundation;  either version 2 of the  License, or (at your
- *  option) any later version.
- *
- */
+// SPDX-License-Identifier: GPL-2.0+
+//
+// Copyright (c) 2011 Samsung Electronics Co., Ltd
+//              http://www.samsung.com
 
 #include <linux/err.h>
 #include <linux/of_gpio.h>
-- 
cgit v1.2.3


From b1470d4ce77c2d60661c7d5325d4fb8063e15ff8 Mon Sep 17 00:00:00 2001
From: Ajit Pandey <ajit.pandey@cirrus.com>
Date: Tue, 7 Aug 2018 18:30:42 +0100
Subject: ASoC: wm_adsp: Correct DSP pointer for preloader control

The offset of the DSP core needs to be taken into account for the DSP
preloader control get and put. Currently the dsp->preloaded variable
will only ever be read/updated on the first DSP, whilst this doesn't
affect the operation of the control the readback will be incorrect.

Signed-off-by: Ajit Pandey <ajit.pandey@cirrus.com>
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
---
 sound/soc/codecs/wm_adsp.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 4e7f8525449e..08dc82770273 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -2643,7 +2643,10 @@ int wm_adsp2_preloader_get(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct wm_adsp *dsp = snd_soc_component_get_drvdata(component);
+	struct wm_adsp *dsps = snd_soc_component_get_drvdata(component);
+	struct soc_mixer_control *mc =
+		(struct soc_mixer_control *)kcontrol->private_value;
+	struct wm_adsp *dsp = &dsps[mc->shift - 1];
 
 	ucontrol->value.integer.value[0] = dsp->preloaded;
 
@@ -2655,10 +2658,11 @@ int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
-	struct wm_adsp *dsp = snd_soc_component_get_drvdata(component);
+	struct wm_adsp *dsps = snd_soc_component_get_drvdata(component);
 	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
+	struct wm_adsp *dsp = &dsps[mc->shift - 1];
 	char preload[32];
 
 	snprintf(preload, ARRAY_SIZE(preload), "DSP%u Preload", mc->shift);
-- 
cgit v1.2.3


From 0717edbdfed61b4c1e8291140f78882d3a481042 Mon Sep 17 00:00:00 2001
From: Ryan Lee <ryans.lee@maximintegrated.com>
Date: Tue, 7 Aug 2018 20:06:38 -0700
Subject: ASoC: max98373: Added software reset register to readable registers

Signed-off-by: Ryan Lee <ryans.lee@maximintegrated.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/max98373.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/max98373.c b/sound/soc/codecs/max98373.c
index a92586106932..92b7125ea169 100644
--- a/sound/soc/codecs/max98373.c
+++ b/sound/soc/codecs/max98373.c
@@ -488,6 +488,7 @@ static const DECLARE_TLV_DB_RANGE(max98373_bde_gain_tlv,
 static bool max98373_readable_register(struct device *dev, unsigned int reg)
 {
 	switch (reg) {
+	case MAX98373_R2000_SW_RESET:
 	case MAX98373_R2001_INT_RAW1 ... MAX98373_R200C_INT_EN3:
 	case MAX98373_R2010_IRQ_CTRL:
 	case MAX98373_R2014_THERM_WARN_THRESH
-- 
cgit v1.2.3


From 8b92d0e3d400390660a26ef7f475524700fb86cf Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@suse.com>
Date: Wed, 8 Aug 2018 08:35:29 +0200
Subject: nvme.h: fixup ANA group descriptor format

ANA Phase 3 draft had the 'reserved' field in the group descriptor
format set to '23:17' (so that the first namespace identifier started
at byte 24), but that got move with the approved TP to '31:17'
(so that the first namespace identifier started at byte 32).

Signed-off-by: Hannes Reinecke <hare@suse.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/nvme.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 64c9175723de..a661861e9d56 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -446,7 +446,7 @@ struct nvme_ana_group_desc {
 	__le32	nnsids;
 	__le64	chgcnt;
 	__u8	state;
-	__u8	rsvd17[7];
+	__u8	rsvd17[15];
 	__le32	nsids[];
 };
 
-- 
cgit v1.2.3


From 93045d5942da60801e71764597d448cf37a798c1 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Tue, 7 Aug 2018 23:01:05 -0700
Subject: nvme.h: add support for ns write protect definitions

Add various definitions from NVMe 1.3 TP 4005.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 include/linux/nvme.h | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index a661861e9d56..68e91ef5494c 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -259,7 +259,7 @@ struct nvme_id_ctrl {
 	__le16			awun;
 	__le16			awupf;
 	__u8			nvscc;
-	__u8			rsvd531;
+	__u8			nwpc;
 	__le16			acwu;
 	__u8			rsvd534[2];
 	__le32			sgls;
@@ -320,7 +320,9 @@ struct nvme_id_ns {
 	__u8			nvmcap[16];
 	__u8			rsvd64[28];
 	__le32			anagrpid;
-	__u8			rsvd96[8];
+	__u8			rsvd96[3];
+	__u8			nsattr;
+	__u8			rsvd100[4];
 	__u8			nguid[16];
 	__u8			eui64[8];
 	struct nvme_lbaf	lbaf[16];
@@ -794,6 +796,7 @@ enum {
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
 	NVME_FEAT_RESV_PERSIST	= 0x83,
+	NVME_FEAT_WRITE_PROTECT	= 0x84,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
@@ -807,6 +810,14 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+/* NVMe Namespace Write Protect State */
+enum {
+	NVME_NS_NO_WRITE_PROTECT = 0,
+	NVME_NS_WRITE_PROTECT,
+	NVME_NS_WRITE_PROTECT_POWER_CYCLE,
+	NVME_NS_WRITE_PROTECT_PERMANENT,
+};
+
 #define NVME_MAX_CHANGED_NAMESPACES	1024
 
 struct nvme_identify {
@@ -1153,6 +1164,8 @@ enum {
 	NVME_SC_SGL_INVALID_OFFSET	= 0x16,
 	NVME_SC_SGL_INVALID_SUBTYPE	= 0x17,
 
+	NVME_SC_NS_WRITE_PROTECTED	= 0x20,
+
 	NVME_SC_LBA_RANGE		= 0x80,
 	NVME_SC_CAP_EXCEEDED		= 0x81,
 	NVME_SC_NS_NOT_READY		= 0x82,
-- 
cgit v1.2.3


From 1293477f4f324f9cf23a36f6cc0adc6801f1baac Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Tue, 7 Aug 2018 23:01:06 -0700
Subject: nvme: set gendisk read only based on nsattr

NVMe 1.3 TP 4005 introduces new filed (NSATTR). This field indicates
whether given namespace is write protected or not. This patch sets the
gendisk associated with the namespace to read only based on the identify
namespace nsattr field.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 603fe59756fb..dd8ec1dd9219 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1484,6 +1484,12 @@ static void nvme_update_disk_info(struct gendisk *disk,
 
 	set_capacity(disk, capacity);
 	nvme_config_discard(ns);
+
+	if (id->nsattr & (1 << 0))
+		set_disk_ro(disk, true);
+	else
+		set_disk_ro(disk, false);
+
 	blk_mq_unfreeze_queue(disk->queue);
 }
 
-- 
cgit v1.2.3


From dedf0be544614b6d9d395e78d72cc8c30d03e440 Mon Sep 17 00:00:00 2001
From: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Date: Tue, 7 Aug 2018 23:01:07 -0700
Subject: nvmet: add ns write protect support

This patch implements the Namespace Write Protect feature described in
"NVMe TP 4005a Namespace Write Protect". In this version, we implement
No Write Protect and Write Protect states for target ns which can be
toggled by set-features commands from the host side.

For write-protect state transition, we need to flush the ns specified
as a part of command so we also add helpers for carrying out synchronous
flush operations.

Signed-off-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
[hch: fixed an incorrect endianess conversion, minor cleanups]
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/target/admin-cmd.c   | 76 +++++++++++++++++++++++++++++++++++++++
 drivers/nvme/target/core.c        | 20 ++++++++++-
 drivers/nvme/target/io-cmd-bdev.c |  7 ++++
 drivers/nvme/target/io-cmd-file.c | 12 ++++---
 drivers/nvme/target/nvmet.h       |  4 +++
 5 files changed, 114 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
index f517bc562d26..a21caea1e080 100644
--- a/drivers/nvme/target/admin-cmd.c
+++ b/drivers/nvme/target/admin-cmd.c
@@ -372,6 +372,8 @@ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
 	id->psd[0].entry_lat = cpu_to_le32(0x10);
 	id->psd[0].exit_lat = cpu_to_le32(0x4);
 
+	id->nwpc = 1 << 0; /* write protect and no write protect */
+
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
 
 	kfree(id);
@@ -433,6 +435,8 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
 
 	id->lbaf[0].ds = ns->blksize_shift;
 
+	if (ns->readonly)
+		id->nsattr |= (1 << 0);
 	nvmet_put_namespace(ns);
 done:
 	status = nvmet_copy_to_sgl(req, 0, id, sizeof(*id));
@@ -545,6 +549,52 @@ static void nvmet_execute_abort(struct nvmet_req *req)
 	nvmet_req_complete(req, 0);
 }
 
+static u16 nvmet_write_protect_flush_sync(struct nvmet_req *req)
+{
+	u16 status;
+
+	if (req->ns->file)
+		status = nvmet_file_flush(req);
+	else
+		status = nvmet_bdev_flush(req);
+
+	if (status)
+		pr_err("write protect flush failed nsid: %u\n", req->ns->nsid);
+	return status;
+}
+
+static u16 nvmet_set_feat_write_protect(struct nvmet_req *req)
+{
+	u32 write_protect = le32_to_cpu(req->cmd->common.cdw10[1]);
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u16 status = NVME_SC_FEATURE_NOT_CHANGEABLE;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->rw.nsid);
+	if (unlikely(!req->ns))
+		return status;
+
+	mutex_lock(&subsys->lock);
+	switch (write_protect) {
+	case NVME_NS_WRITE_PROTECT:
+		req->ns->readonly = true;
+		status = nvmet_write_protect_flush_sync(req);
+		if (status)
+			req->ns->readonly = false;
+		break;
+	case NVME_NS_NO_WRITE_PROTECT:
+		req->ns->readonly = false;
+		status = 0;
+		break;
+	default:
+		break;
+	}
+
+	if (!status)
+		nvmet_ns_changed(subsys, req->ns->nsid);
+	mutex_unlock(&subsys->lock);
+	return status;
+}
+
 static void nvmet_execute_set_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -575,6 +625,9 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	case NVME_FEAT_HOST_ID:
 		status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_set_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
@@ -583,6 +636,26 @@ static void nvmet_execute_set_features(struct nvmet_req *req)
 	nvmet_req_complete(req, status);
 }
 
+static u16 nvmet_get_feat_write_protect(struct nvmet_req *req)
+{
+	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
+	u32 result;
+
+	req->ns = nvmet_find_namespace(req->sq->ctrl, req->cmd->common.nsid);
+	if (!req->ns)
+		return NVME_SC_INVALID_NS | NVME_SC_DNR;
+
+	mutex_lock(&subsys->lock);
+	if (req->ns->readonly == true)
+		result = NVME_NS_WRITE_PROTECT;
+	else
+		result = NVME_NS_NO_WRITE_PROTECT;
+	nvmet_set_result(req, result);
+	mutex_unlock(&subsys->lock);
+
+	return 0;
+}
+
 static void nvmet_execute_get_features(struct nvmet_req *req)
 {
 	struct nvmet_subsys *subsys = req->sq->ctrl->subsys;
@@ -634,6 +707,9 @@ static void nvmet_execute_get_features(struct nvmet_req *req)
 		status = nvmet_copy_to_sgl(req, 0, &req->sq->ctrl->hostid,
 				sizeof(req->sq->ctrl->hostid));
 		break;
+	case NVME_FEAT_WRITE_PROTECT:
+		status = nvmet_get_feat_write_protect(req);
+		break;
 	default:
 		status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
 		break;
diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index 3ceb7a03bb2a..14b4c4916a8e 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -180,7 +180,7 @@ out_unlock:
 	mutex_unlock(&ctrl->lock);
 }
 
-static void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid)
 {
 	struct nvmet_ctrl *ctrl;
 
@@ -609,6 +609,21 @@ static inline u16 nvmet_check_ana_state(struct nvmet_port *port,
 	return 0;
 }
 
+static inline u16 nvmet_io_cmd_check_access(struct nvmet_req *req)
+{
+	if (unlikely(req->ns->readonly)) {
+		switch (req->cmd->common.opcode) {
+		case nvme_cmd_read:
+		case nvme_cmd_flush:
+			break;
+		default:
+			return NVME_SC_NS_WRITE_PROTECTED;
+		}
+	}
+
+	return 0;
+}
+
 static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 {
 	struct nvme_command *cmd = req->cmd;
@@ -622,6 +637,9 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
 	if (unlikely(!req->ns))
 		return NVME_SC_INVALID_NS | NVME_SC_DNR;
 	ret = nvmet_check_ana_state(req->port, req->ns);
+	if (unlikely(ret))
+		return ret;
+	ret = nvmet_io_cmd_check_access(req);
 	if (unlikely(ret))
 		return ret;
 
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index e0b0f7df70c2..7bc9f6240432 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -124,6 +124,13 @@ static void nvmet_bdev_execute_flush(struct nvmet_req *req)
 	submit_bio(bio);
 }
 
+u16 nvmet_bdev_flush(struct nvmet_req *req)
+{
+	if (blkdev_issue_flush(req->ns->bdev, GFP_KERNEL, NULL))
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
 static u16 nvmet_bdev_discard_range(struct nvmet_ns *ns,
 		struct nvme_dsm_range *range, struct bio **bio)
 {
diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c
index c2d0d08b59c8..81a9dc5290a8 100644
--- a/drivers/nvme/target/io-cmd-file.c
+++ b/drivers/nvme/target/io-cmd-file.c
@@ -211,14 +211,18 @@ static void nvmet_file_execute_rw_buffered_io(struct nvmet_req *req)
 	queue_work(buffered_io_wq, &req->f.work);
 }
 
+u16 nvmet_file_flush(struct nvmet_req *req)
+{
+	if (vfs_fsync(req->ns->file, 1) < 0)
+		return NVME_SC_INTERNAL | NVME_SC_DNR;
+	return 0;
+}
+
 static void nvmet_file_flush_work(struct work_struct *w)
 {
 	struct nvmet_req *req = container_of(w, struct nvmet_req, f.work);
-	int ret;
-
-	ret = vfs_fsync(req->ns->file, 1);
 
-	nvmet_req_complete(req, ret < 0 ? NVME_SC_INTERNAL | NVME_SC_DNR : 0);
+	nvmet_req_complete(req, nvmet_file_flush(req));
 }
 
 static void nvmet_file_execute_flush(struct nvmet_req *req)
diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 22941045f46e..ec9af4ee03b6 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -58,6 +58,7 @@ struct nvmet_ns {
 	struct percpu_ref	ref;
 	struct block_device	*bdev;
 	struct file		*file;
+	bool			readonly;
 	u32			nsid;
 	u32			blksize_shift;
 	loff_t			size;
@@ -429,6 +430,9 @@ int nvmet_bdev_ns_enable(struct nvmet_ns *ns);
 int nvmet_file_ns_enable(struct nvmet_ns *ns);
 void nvmet_bdev_ns_disable(struct nvmet_ns *ns);
 void nvmet_file_ns_disable(struct nvmet_ns *ns);
+u16 nvmet_bdev_flush(struct nvmet_req *req);
+u16 nvmet_file_flush(struct nvmet_req *req);
+void nvmet_ns_changed(struct nvmet_subsys *subsys, u32 nsid);
 
 static inline u32 nvmet_rw_len(struct nvmet_req *req)
 {
-- 
cgit v1.2.3


From 66414e80245e1e73222f67ee711951c7f4bdedab Mon Sep 17 00:00:00 2001
From: Tal Shorer <tal.shorer@gmail.com>
Date: Tue, 7 Aug 2018 23:42:39 +0300
Subject: nvme-fabrics: fix ctrl_loss_tmo < 0 to reconnect forever

When the user supplies a ctrl_loss_tmo < 0, we warn them that this will
cause the fabrics layer to attempt reconnection forever.  However, in
reality the fabrics layer never attempts to reconnect because the
condition to test whether we should reconnect is backwards in this case.

Signed-off-by: Tal Shorer <tal.shorer@gmail.com>
Reviewed-by: Chaitanya Kulkarni <chaitanya.kulkarni@wdc.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/fabrics.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
index 903eb4545e26..3c6cd0f81ba6 100644
--- a/drivers/nvme/host/fabrics.c
+++ b/drivers/nvme/host/fabrics.c
@@ -474,7 +474,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
 
 bool nvmf_should_reconnect(struct nvme_ctrl *ctrl)
 {
-	if (ctrl->opts->max_reconnects != -1 &&
+	if (ctrl->opts->max_reconnects == -1 ||
 	    ctrl->nr_reconnects < ctrl->opts->max_reconnects)
 		return true;
 
-- 
cgit v1.2.3


From 3c4d9137eefecf273a520d392071ffc9df0a9a7a Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 7 Aug 2018 18:59:57 -0500
Subject: arm64: alternative: Use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value. This code was detected with the help of
Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
---
 arch/arm64/kernel/alternative.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c
index 36fb069fd049..b5d603992d40 100644
--- a/arch/arm64/kernel/alternative.c
+++ b/arch/arm64/kernel/alternative.c
@@ -47,11 +47,11 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 	unsigned long replptr;
 
 	if (kernel_text_address(pc))
-		return 1;
+		return true;
 
 	replptr = (unsigned long)ALT_REPL_PTR(alt);
 	if (pc >= replptr && pc <= (replptr + alt->alt_len))
-		return 0;
+		return false;
 
 	/*
 	 * Branching into *another* alternate sequence is doomed, and
-- 
cgit v1.2.3


From 6554f9501915101ba89aab6e40c83139d23f853a Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 3 Aug 2018 16:38:43 +0200
Subject: PCI: mvebu: Remove redundant platform_set_drvdata() call

This is already done earlier in mvebu_pcie_probe().

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-mvebu.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 23e270839e6a..38fa2d08527d 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1283,8 +1283,6 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 
 	mvebu_pcie_enable(pcie);
 
-	platform_set_drvdata(pdev, pcie);
-
 	return 0;
 }
 
-- 
cgit v1.2.3


From dfd0309fd7b30a5baffaf47b2fccb88b46d64d69 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 3 Aug 2018 16:38:44 +0200
Subject: PCI: mvebu: Fix I/O space end address calculation

pcie->realio.end should be the address of last byte of the area,
therefore using resource_size() of another resource is not correct, we
must substract 1 to get the address of the last byte.

Fixes: 11be65472a427 ("PCI: mvebu: Adapt to the new device tree layout")
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-mvebu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 38fa2d08527d..a195592723c2 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1219,7 +1219,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 		pcie->realio.start = PCIBIOS_MIN_IO;
 		pcie->realio.end = min_t(resource_size_t,
 					 IO_SPACE_LIMIT,
-					 resource_size(&pcie->io));
+					 resource_size(&pcie->io) - 1);
 	} else
 		pcie->realio = pcie->io;
 
-- 
cgit v1.2.3


From ee1604381a371b3ea6aec7d5e43b6e3f5e153854 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 3 Aug 2018 16:38:45 +0200
Subject: PCI: mvebu: Only remap I/O space if configured

If there is no PCI I/O aperture configured in the Device Tree, it does
not make sense to create the virtual mapping for the PCI I/O space,
since we will anyway not create the MBus window that will allow to
access it. Therefore, do the pci_ioremap_io() only if necessary.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-mvebu.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index a195592723c2..9aa224f2f009 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1220,6 +1220,9 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 		pcie->realio.end = min_t(resource_size_t,
 					 IO_SPACE_LIMIT,
 					 resource_size(&pcie->io) - 1);
+
+		for (i = 0; i < (IO_SPACE_LIMIT - SZ_64K); i += SZ_64K)
+			pci_ioremap_io(i, pcie->io.start + i);
 	} else
 		pcie->realio = pcie->io;
 
@@ -1278,9 +1281,6 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 
 	pcie->nports = i;
 
-	for (i = 0; i < (IO_SPACE_LIMIT - SZ_64K); i += SZ_64K)
-		pci_ioremap_io(i, pcie->io.start + i);
-
 	mvebu_pcie_enable(pcie);
 
 	return 0;
-- 
cgit v1.2.3


From 5a553d6ba103e28247f4e2d10bcc25545cd4d9cb Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 3 Aug 2018 16:38:46 +0200
Subject: PCI: mvebu: Use resource_size() to remap I/O space

Instead of hardcoding the remapping of IO_SPACE_LIMIT - SZ_64K, use
resource_size().

However, we cannot use just IO_SPACE_LIMIT, because pci_ioremap_io() has
a bug and doesn't allow remapping the last 64 KB before IO_SPACE_LIMIT,
so we ensure that we do not exceed this limit. When the pci_ioremap_io()
issue is fixed, this work around can be dropped.

Note that this workaround already existed, since we were mapping only
up to IO_SPACE_LIMIT - SZ_64K.

Suggested-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
[lorenzo.pieralisi@arm.com: tweaked the commit log]
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-mvebu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 9aa224f2f009..05f863435e5e 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -1218,10 +1218,10 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 		pcie->realio.flags = pcie->io.flags;
 		pcie->realio.start = PCIBIOS_MIN_IO;
 		pcie->realio.end = min_t(resource_size_t,
-					 IO_SPACE_LIMIT,
+					 IO_SPACE_LIMIT - SZ_64K,
 					 resource_size(&pcie->io) - 1);
 
-		for (i = 0; i < (IO_SPACE_LIMIT - SZ_64K); i += SZ_64K)
+		for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K)
 			pci_ioremap_io(i, pcie->io.start + i);
 	} else
 		pcie->realio = pcie->io;
-- 
cgit v1.2.3


From 75070c6a3311e320508427bbc779c4de6942872e Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 06:17:00 -0400
Subject: media: vsp1_dl: add a description for cmdpool field

Gets rid of this build warning:
	drivers/media/platform/vsp1/vsp1_dl.c:229: warning: Function parameter or member 'cmdpool' not described in 'vsp1_dl_manager'

Fixes: f3b98e3c4d2e ("media: vsp1: Provide support for extended command pools")
Reviewed-by: Kieran Bingham <kieran.bingham+renesas@ideasonboard.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vsp1/vsp1_dl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/vsp1/vsp1_dl.c b/drivers/media/platform/vsp1/vsp1_dl.c
index 9255b5ee2cb8..26289adaf658 100644
--- a/drivers/media/platform/vsp1/vsp1_dl.c
+++ b/drivers/media/platform/vsp1/vsp1_dl.c
@@ -211,7 +211,7 @@ struct vsp1_dl_list {
  * @queued: list queued to the hardware (written to the DL registers)
  * @pending: list waiting to be queued to the hardware
  * @pool: body pool for the display list bodies
- * @autofld_cmds: command pool to support auto-fld interlaced mode
+ * @cmdpool: commands pool for extended display list
  */
 struct vsp1_dl_manager {
 	unsigned int index;
-- 
cgit v1.2.3


From d9a71866944967b8622c493ef1b570ccb74e45ae Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 06:36:31 -0400
Subject: media: mt9v111: avoid going past the buffer

As warned by smatch:
	drivers/media/i2c/mt9v111.c:854 mt9v111_enum_frame_size() error: buffer overflow 'mt9v111_frame_sizes' 5 <= 5
	drivers/media/i2c/mt9v111.c:855 mt9v111_enum_frame_size() error: buffer overflow 'mt9v111_frame_sizes' 5 <= 5
	drivers/media/i2c/mt9v111.c:856 mt9v111_enum_frame_size() error: buffer overflow 'mt9v111_frame_sizes' 5 <= 5
	drivers/media/i2c/mt9v111.c:857 mt9v111_enum_frame_size() error: buffer overflow 'mt9v111_frame_sizes' 5 <= 5

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/mt9v111.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
index 58d5f2224bff..70fad0940435 100644
--- a/drivers/media/i2c/mt9v111.c
+++ b/drivers/media/i2c/mt9v111.c
@@ -848,7 +848,7 @@ static int mt9v111_enum_frame_size(struct v4l2_subdev *subdev,
 				   struct v4l2_subdev_pad_config *cfg,
 				   struct v4l2_subdev_frame_size_enum *fse)
 {
-	if (fse->pad || fse->index > ARRAY_SIZE(mt9v111_frame_sizes))
+	if (fse->pad || fse->index >= ARRAY_SIZE(mt9v111_frame_sizes))
 		return -EINVAL;
 
 	fse->min_width = mt9v111_frame_sizes[fse->index].width;
-- 
cgit v1.2.3


From 845b978a871bff3707eee611b32e4be0b9a94dd2 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 06:49:26 -0400
Subject: media: rtl28xxu: be sure that it won't go past the array size

smatch warns that the RC query code could go past the array size:

	drivers/media/usb/dvb-usb-v2/rtl28xxu.c:1757 rtl2832u_rc_query() error: buffer overflow 'buf' 128 <= 130
	drivers/media/usb/dvb-usb-v2/rtl28xxu.c:1758 rtl2832u_rc_query() error: buffer overflow 'buf' 128 <= 130

The driver logic gets the length of the IR RX buffer with:

        ret = rtl28xxu_rd_reg(d, IR_RX_BC, &buf[0]);
	...
        len = buf[0];

In thesis, this could range between 0 and 255 [1].

While this should never happen in practice, due to hardware limits,
smatch is right when it complains about that, as there's nothing at
the logic that would prevent it. So, if for whatever reason, buf[0]
gets filled by rtl28xx read functions with a value bigger than 128,
it will go past the array.

So, add an explicit check.

[1] I've no idea why smatch thinks that the maximum value is 130.
I double-checked the code several times. Was unable to find any
reason for assuming 130. Perhaps smatch is not properly parsing
u8 here?

Fixes: b5cbaa43a676 ("[media] rtl28xx: initial support for rtl2832u")
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/usb/dvb-usb-v2/rtl28xxu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
index c76e78f9638a..a970224a94bd 100644
--- a/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
+++ b/drivers/media/usb/dvb-usb-v2/rtl28xxu.c
@@ -1732,7 +1732,7 @@ static int rtl2832u_rc_query(struct dvb_usb_device *d)
 		goto exit;
 
 	ret = rtl28xxu_rd_reg(d, IR_RX_BC, &buf[0]);
-	if (ret)
+	if (ret || buf[0] > sizeof(buf))
 		goto err;
 
 	len = buf[0];
-- 
cgit v1.2.3


From 3354b54f9f7037a1122d3b6009aa9d39829d6843 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 07:29:12 -0400
Subject: media: vivid: shut up warnings due to a non-trivial logic

The vivid driver uses a complex logic to save one kalloc/kfree
allocation. That non-trivial way of allocating data causes
smatch to warn:
	drivers/media/platform/vivid/vivid-core.c:869 vivid_create_instance() warn: potentially one past the end of array 'dev->query_dv_timings_qmenu[dev->query_dv_timings_size]'
	drivers/media/platform/vivid/vivid-core.c:869 vivid_create_instance() warn: potentially one past the end of array 'dev->query_dv_timings_qmenu[dev->query_dv_timings_size]'

I also needed to read the code several times in order to understand
what it was desired there. It turns that the logic was right,
although confusing to read.

As it is doing allocations on a non-standard way, let's add some
documentation while shutting up the false positive.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/vivid/vivid-core.c | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/vivid/vivid-core.c b/drivers/media/platform/vivid/vivid-core.c
index 31db363602e5..4c235ea27987 100644
--- a/drivers/media/platform/vivid/vivid-core.c
+++ b/drivers/media/platform/vivid/vivid-core.c
@@ -647,6 +647,7 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	unsigned node_type = node_types[inst];
 	unsigned int allocator = allocators[inst];
 	v4l2_std_id tvnorms_cap = 0, tvnorms_out = 0;
+	char *strings_base;
 	int ret;
 	int i;
 
@@ -859,17 +860,33 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	/* create a string array containing the names of all the preset timings */
 	while (v4l2_dv_timings_presets[dev->query_dv_timings_size].bt.width)
 		dev->query_dv_timings_size++;
+
+	/*
+	 * In order to save one allocation and an extra free, let's optimize
+	 * the allocation here: we'll use the first elements of the
+	 * dev->query_dv_timings_qmenu to store the timing strings pointer,
+	 * adding an extra space there to a store a string up to 32 bytes.
+	 * So, instead of allocating an array with size of:
+	 * 	dev->query_dv_timings_size * (sizeof(void *)
+	 * it will allocate:
+	 * 	dev->query_dv_timings_size * (sizeof(void *) +
+	 *	dev->query_dv_timings_size * 32
+	 */
 	dev->query_dv_timings_qmenu = kmalloc_array(dev->query_dv_timings_size,
 						    (sizeof(void *) + 32),
 						    GFP_KERNEL);
 	if (dev->query_dv_timings_qmenu == NULL)
 		goto free_dev;
+
+	/* Sets strings_base to be after the space to store the pointers */
+	strings_base = ((char *)&dev->query_dv_timings_qmenu)
+		       + dev->query_dv_timings_size * sizeof(void *);
+
 	for (i = 0; i < dev->query_dv_timings_size; i++) {
 		const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt;
-		char *p = (char *)&dev->query_dv_timings_qmenu[dev->query_dv_timings_size];
+		char *p = strings_base + i * 32;
 		u32 htot, vtot;
 
-		p += i * 32;
 		dev->query_dv_timings_qmenu[i] = p;
 
 		htot = V4L2_DV_BT_FRAME_WIDTH(bt);
-- 
cgit v1.2.3


From 40e431112c63296a6130810ab62a5fe73953f074 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 07:59:20 -0400
Subject: media: cleanup fall-through comments

As Ian pointed out, adding a '-' to the fallthrough seems to meet
the regex requirements at level 3 of the warning, at least when
the comment fits into a single line.

So, replace by a single line the comments that were broken into
multiple lines just to make gcc -Wimplicit-fallthrough=3 happy.

Suggested-by: Ian Arkver <ian.arkver.dev@gmail.com>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/drx39xyj/drxj.c |  3 +--
 drivers/media/dvb-frontends/drxd_hard.c     |  6 ++----
 drivers/media/dvb-frontends/drxk_hard.c     | 18 ++++++------------
 drivers/staging/media/imx/imx-media-csi.c   |  3 +--
 4 files changed, 10 insertions(+), 20 deletions(-)

diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 2ddb7d218ace..2948d12d7c14 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -2841,8 +2841,7 @@ ctrl_set_cfg_mpeg_output(struct drx_demod_instance *demod, struct drx_cfg_mpeg_o
 			/* coef = 188/204                          */
 			max_bit_rate =
 			    (ext_attr->curr_symbol_rate / 8) * nr_bits * 188;
-			/* pass through as b/c Annex A/c need following settings */
-			/* fall-through */
+			/* fall-through - as b/c Annex A/C need following settings */
 		case DRX_STANDARD_ITU_B:
 			rc = drxj_dap_write_reg16(dev_addr, FEC_OC_FCT_USAGE__A, FEC_OC_FCT_USAGE__PRE, 0);
 			if (rc != 0) {
diff --git a/drivers/media/dvb-frontends/drxd_hard.c b/drivers/media/dvb-frontends/drxd_hard.c
index 11fc259e4383..684d428efb0d 100644
--- a/drivers/media/dvb-frontends/drxd_hard.c
+++ b/drivers/media/dvb-frontends/drxd_hard.c
@@ -1970,8 +1970,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 		switch (p->transmission_mode) {
 		default:	/* Not set, detect it automatically */
 			operationMode |= SC_RA_RAM_OP_AUTO_MODE__M;
-			/* try first guess DRX_FFTMODE_8K */
-			/* fall through */
+			/* fall through - try first guess DRX_FFTMODE_8K */
 		case TRANSMISSION_MODE_8K:
 			transmissionParams |= SC_RA_RAM_OP_PARAM_MODE_8K;
 			if (state->type_A) {
@@ -2144,8 +2143,7 @@ static int DRX_Start(struct drxd_state *state, s32 off)
 		switch (p->modulation) {
 		default:
 			operationMode |= SC_RA_RAM_OP_AUTO_CONST__M;
-			/* try first guess DRX_CONSTELLATION_QAM64 */
-			/* fall through */
+			/* fall through - try first guess DRX_CONSTELLATION_QAM64 */
 		case QAM_64:
 			transmissionParams |= SC_RA_RAM_OP_PARAM_CONST_QAM64;
 			if (state->type_A) {
diff --git a/drivers/media/dvb-frontends/drxk_hard.c b/drivers/media/dvb-frontends/drxk_hard.c
index ac10781d3550..f1886945a7bc 100644
--- a/drivers/media/dvb-frontends/drxk_hard.c
+++ b/drivers/media/dvb-frontends/drxk_hard.c
@@ -3270,13 +3270,11 @@ static int dvbt_sc_command(struct drxk_state *state,
 	case OFDM_SC_RA_RAM_CMD_SET_PREF_PARAM:
 	case OFDM_SC_RA_RAM_CMD_PROGRAM_PARAM:
 		status |= write16(state, OFDM_SC_RA_RAM_PARAM1__A, param1);
-		/* All commands using 1 parameters */
-		/* fall through */
+		/* fall through - All commands using 1 parameters */
 	case OFDM_SC_RA_RAM_CMD_SET_ECHO_TIMING:
 	case OFDM_SC_RA_RAM_CMD_USER_IO:
 		status |= write16(state, OFDM_SC_RA_RAM_PARAM0__A, param0);
-		/* All commands using 0 parameters */
-		/* fall through */
+		/* fall through - All commands using 0 parameters */
 	case OFDM_SC_RA_RAM_CMD_GET_OP_PARAM:
 	case OFDM_SC_RA_RAM_CMD_NULL:
 		/* Write command */
@@ -3784,8 +3782,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case TRANSMISSION_MODE_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_MODE__M;
-		/* try first guess DRX_FFTMODE_8K */
-		/* fall through */
+		/* fall through - try first guess DRX_FFTMODE_8K */
 	case TRANSMISSION_MODE_8K:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_MODE_8K;
 		break;
@@ -3799,8 +3796,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	default:
 	case GUARD_INTERVAL_AUTO:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_GUARD__M;
-		/* try first guess DRX_GUARD_1DIV4 */
-		/* fall through */
+		/* fall through - try first guess DRX_GUARD_1DIV4 */
 	case GUARD_INTERVAL_1_4:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_GUARD_4;
 		break;
@@ -3841,8 +3837,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case QAM_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_CONST__M;
-		/* try first guess DRX_CONSTELLATION_QAM64 */
-		/* fall through */
+		/* fall through - try first guess DRX_CONSTELLATION_QAM64 */
 	case QAM_64:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_CONST_QAM64;
 		break;
@@ -3885,8 +3880,7 @@ static int set_dvbt(struct drxk_state *state, u16 intermediate_freqk_hz,
 	case FEC_AUTO:
 	default:
 		operation_mode |= OFDM_SC_RA_RAM_OP_AUTO_RATE__M;
-		/* try first guess DRX_CODERATE_2DIV3 */
-		/* fall through */
+		/* fall through - try first guess DRX_CODERATE_2DIV3 */
 	case FEC_2_3:
 		transmission_params |= OFDM_SC_RA_RAM_OP_PARAM_RATE_2_3;
 		break;
diff --git a/drivers/staging/media/imx/imx-media-csi.c b/drivers/staging/media/imx/imx-media-csi.c
index b7ffd231c64b..cd2c291e1e94 100644
--- a/drivers/staging/media/imx/imx-media-csi.c
+++ b/drivers/staging/media/imx/imx-media-csi.c
@@ -460,8 +460,7 @@ static int csi_idmac_setup_channel(struct csi_priv *priv)
 			passthrough_cycles = incc->cycles;
 			break;
 		}
-		/* for non-passthrough RGB565 (CSI-2 bus) */
-		/* Falls through */
+		/* fallthrough - non-passthrough RGB565 (CSI-2 bus) */
 	default:
 		burst_size = (image.pix.width & 0xf) ? 8 : 16;
 		passthrough_bits = 16;
-- 
cgit v1.2.3


From 3fcb3c836ef413d3fc848288b308eb655e08d853 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 08:10:34 -0400
Subject: media: tuner-xc2028: don't use casts for printing sizes

Makes smatch happier by using %zd instead of casting sizes:
	drivers/media/tuners/tuner-xc2028.c:378 load_all_firmwares() warn: argument 4 to %d specifier is cast from pointer
	drivers/media/tuners/tuner-xc2028.c:619 load_firmware() warn: argument 6 to %d specifier is cast from pointer

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/tuners/tuner-xc2028.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/media/tuners/tuner-xc2028.c b/drivers/media/tuners/tuner-xc2028.c
index 222b93ef31c0..aa6861dcd3fd 100644
--- a/drivers/media/tuners/tuner-xc2028.c
+++ b/drivers/media/tuners/tuner-xc2028.c
@@ -376,9 +376,8 @@ static int load_all_firmwares(struct dvb_frontend *fe,
 			tuner_err("Firmware type ");
 			dump_firm_type(type);
 			printk(KERN_CONT
-			       "(%x), id %llx is corrupted (size=%d, expected %d)\n",
-			       type, (unsigned long long)id,
-			       (unsigned)(endp - p), size);
+			       "(%x), id %llx is corrupted (size=%zd, expected %d)\n",
+			       type, (unsigned long long)id, (endp - p), size);
 			goto corrupt;
 		}
 
@@ -616,8 +615,8 @@ static int load_firmware(struct dvb_frontend *fe, unsigned int type,
 		}
 
 		if ((size + p > endp)) {
-			tuner_err("missing bytes: need %d, have %d\n",
-				   size, (int)(endp - p));
+			tuner_err("missing bytes: need %d, have %zd\n",
+				   size, (endp - p));
 			return -EINVAL;
 		}
 
-- 
cgit v1.2.3


From c4f047969fa1707e1312e6600b630aef516e13c6 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 08:14:43 -0400
Subject: media: drxj: get rid of uneeded casts

Instead of doing casts, use %zd to print sizes, in order to make
smatch happier:
	drivers/media/dvb-frontends/drx39xyj/drxj.c:11814 drx_ctrl_u_code() warn: argument 4 to %u specifier is cast from pointer
	drivers/media/dvb-frontends/drx39xyj/drxj.c:11845 drx_ctrl_u_code() warn: argument 3 to %u specifier is cast from pointer
	drivers/media/dvb-frontends/drx39xyj/drxj.c:11869 drx_ctrl_u_code() warn: argument 3 to %u specifier is cast from pointer
	drivers/media/dvb-frontends/drx39xyj/drxj.c:11878 drx_ctrl_u_code() warn: argument 3 to %u specifier is cast from pointer

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/dvb-frontends/drx39xyj/drxj.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/media/dvb-frontends/drx39xyj/drxj.c b/drivers/media/dvb-frontends/drx39xyj/drxj.c
index 2948d12d7c14..9628d4067fe1 100644
--- a/drivers/media/dvb-frontends/drx39xyj/drxj.c
+++ b/drivers/media/dvb-frontends/drx39xyj/drxj.c
@@ -11810,8 +11810,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 		block_hdr.CRC = be16_to_cpu(*(__be16 *)(mc_data));
 		mc_data += sizeof(u16);
 
-		pr_debug("%u: addr %u, size %u, flags 0x%04x, CRC 0x%04x\n",
-			(unsigned)(mc_data - mc_data_init), block_hdr.addr,
+		pr_debug("%zd: addr %u, size %u, flags 0x%04x, CRC 0x%04x\n",
+			(mc_data - mc_data_init), block_hdr.addr,
 			 block_hdr.size, block_hdr.flags, block_hdr.CRC);
 
 		/* Check block header on:
@@ -11841,8 +11841,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 							mc_block_nr_bytes,
 							mc_data, 0x0000)) {
 				rc = -EIO;
-				pr_err("error writing firmware at pos %u\n",
-				       (unsigned)(mc_data - mc_data_init));
+				pr_err("error writing firmware at pos %zd\n",
+				       mc_data - mc_data_init);
 				goto release;
 			}
 			break;
@@ -11865,8 +11865,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 						    (u16)bytes_to_comp,
 						    (u8 *)mc_data_buffer,
 						    0x0000)) {
-					pr_err("error reading firmware at pos %u\n",
-					       (unsigned)(mc_data - mc_data_init));
+					pr_err("error reading firmware at pos %zd\n",
+					       mc_data - mc_data_init);
 					return -EIO;
 				}
 
@@ -11874,8 +11874,8 @@ static int drx_ctrl_u_code(struct drx_demod_instance *demod,
 						bytes_to_comp);
 
 				if (result) {
-					pr_err("error verifying firmware at pos %u\n",
-					       (unsigned)(mc_data - mc_data_init));
+					pr_err("error verifying firmware at pos %zd\n",
+					       mc_data - mc_data_init);
 					return -EIO;
 				}
 
-- 
cgit v1.2.3


From 8218840f76a525f014f404b5e97d9523e327f4b0 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 08:16:09 -0400
Subject: media: xc4000: get rid of uneeded casts

Instead of doing casts, use %zd to print sizes, in order to make
smatch happier:
	drivers/media/tuners/xc4000.c:818 xc4000_fwupload() warn: argument 4 to %d specifier is cast from pointer

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/tuners/xc4000.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/media/tuners/xc4000.c b/drivers/media/tuners/xc4000.c
index 76b3f37f24a8..eb6d65dae748 100644
--- a/drivers/media/tuners/xc4000.c
+++ b/drivers/media/tuners/xc4000.c
@@ -815,9 +815,9 @@ static int xc4000_fwupload(struct dvb_frontend *fe)
 		p += sizeof(size);
 
 		if (!size || size > endp - p) {
-			printk(KERN_ERR "Firmware type (%x), id %llx is corrupted (size=%d, expected %d)\n",
+			printk(KERN_ERR "Firmware type (%x), id %llx is corrupted (size=%zd, expected %d)\n",
 			       type, (unsigned long long)id,
-			       (unsigned)(endp - p), size);
+			       endp - p, size);
 			goto corrupt;
 		}
 
-- 
cgit v1.2.3


From 484f9b372dd8da6a4a9867ebcd10e5c2b21ab478 Mon Sep 17 00:00:00 2001
From: Jacopo Mondi <jacopo+renesas@jmondi.org>
Date: Tue, 7 Aug 2018 11:38:14 -0400
Subject: media: mt9v111: Fix build error with no VIDEO_V4L2_SUBDEV_API

The v4l2_subdev_get_try_format() function is only defined if the
VIDEO_V4L2_SUBDEV_API Kconfig option is enabled. Builds configured
without that symbol fails with:

drivers/media/i2c/mt9v111.c:801:10: error: implicit declaration of function
'v4l2_subdev_get_try_format';

Fix this by protecting the function call by testing for the right symbol.

media: mt9v111: fix random build errors

Fix the internal check for it to do the right thing if the
subdev API is not built.

Fixes: aab7ed1c ("media: i2c: Add driver for Aptina MT9V111")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Reported-by: kbuild test robot <lkp@intel.com>
Signed-off-by: Jacopo Mondi <jacopo+renesas@jmondi.org>
Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/i2c/mt9v111.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/i2c/mt9v111.c b/drivers/media/i2c/mt9v111.c
index 70fad0940435..b5410aeb5fe2 100644
--- a/drivers/media/i2c/mt9v111.c
+++ b/drivers/media/i2c/mt9v111.c
@@ -797,7 +797,7 @@ static struct v4l2_mbus_framefmt *__mt9v111_get_pad_format(
 {
 	switch (which) {
 	case V4L2_SUBDEV_FORMAT_TRY:
-#if IS_ENABLED(CONFIG_MEDIA_CONTROLLER)
+#if IS_ENABLED(CONFIG_VIDEO_V4L2_SUBDEV_API)
 		return v4l2_subdev_get_try_format(&mt9v111->sd, cfg, pad);
 #else
 		return &cfg->try_fmt;
-- 
cgit v1.2.3


From 541b647a34d36827bf06aa64c3a5e5936cffa10f Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 09:15:27 -0400
Subject: media: exynos-gsc: fix return code if mutex was interrupted

All poll routines expect a poll flag, and not error codes. So,
instead of returning -ERESTARTSYS if the mutex got interrupted,
return EPOLERR, just like the V4L2 VB2 code.

Solves this sparce warning:
	drivers/media/platform/exynos-gsc/gsc-m2m.c:716:24: warning: incorrect type in return expression (different base types)
	drivers/media/platform/exynos-gsc/gsc-m2m.c:716:24:    expected restricted __poll_t
	drivers/media/platform/exynos-gsc/gsc-m2m.c:716:24:    got int

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/exynos-gsc/gsc-m2m.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/exynos-gsc/gsc-m2m.c b/drivers/media/platform/exynos-gsc/gsc-m2m.c
index e9ff27949a91..c9d2f6c5311a 100644
--- a/drivers/media/platform/exynos-gsc/gsc-m2m.c
+++ b/drivers/media/platform/exynos-gsc/gsc-m2m.c
@@ -713,7 +713,7 @@ static __poll_t gsc_m2m_poll(struct file *file,
 	__poll_t ret;
 
 	if (mutex_lock_interruptible(&gsc->lock))
-		return -ERESTARTSYS;
+		return EPOLLERR;
 
 	ret = v4l2_m2m_poll(file, ctx->m2m_ctx, wait);
 	mutex_unlock(&gsc->lock);
-- 
cgit v1.2.3


From 9de1be6ec05a635079fbcf75c5d47f656b61fe4a Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 09:18:26 -0400
Subject: media: saa7164: fix return codes for the polling routine

All poll handlers should return a poll flag, and not error codes. So,
instead of returning an error, do the right thing at saa7164,
e. g. to return EPOLERR on errors, just like the V4L2 VB2 code.

Solves the following sparse warnings:
    drivers/media/pci/saa7164/saa7164-vbi.c:632:24: warning: incorrect type in return expression (different base types)
    drivers/media/pci/saa7164/saa7164-vbi.c:632:24:    expected restricted __poll_t
    drivers/media/pci/saa7164/saa7164-vbi.c:632:24:    got int
    drivers/media/pci/saa7164/saa7164-vbi.c:637:40: warning: incorrect type in return expression (different base types)
    drivers/media/pci/saa7164/saa7164-vbi.c:637:40:    expected restricted __poll_t
    drivers/media/pci/saa7164/saa7164-vbi.c:637:40:    got int
    drivers/media/pci/saa7164/saa7164-vbi.c:647:40: warning: incorrect type in return expression (different base types)
    drivers/media/pci/saa7164/saa7164-vbi.c:647:40:    expected restricted __poll_t
    drivers/media/pci/saa7164/saa7164-vbi.c:647:40:    got int

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/pci/saa7164/saa7164-vbi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/media/pci/saa7164/saa7164-vbi.c b/drivers/media/pci/saa7164/saa7164-vbi.c
index 64ab91c24c18..221de91a8bae 100644
--- a/drivers/media/pci/saa7164/saa7164-vbi.c
+++ b/drivers/media/pci/saa7164/saa7164-vbi.c
@@ -629,12 +629,12 @@ static __poll_t fops_poll(struct file *file, poll_table *wait)
 		port->last_poll_msecs_diff);
 
 	if (!video_is_registered(port->v4l_device))
-		return -EIO;
+		return EPOLLERR;
 
 	if (atomic_cmpxchg(&fh->v4l_reading, 0, 1) == 0) {
 		if (atomic_inc_return(&port->v4l_reader_count) == 1) {
 			if (saa7164_vbi_initialize(port) < 0)
-				return -EINVAL;
+				return EPOLLERR;
 			saa7164_vbi_start_streaming(port);
 			msleep(200);
 		}
@@ -644,7 +644,7 @@ static __poll_t fops_poll(struct file *file, poll_table *wait)
 	if ((file->f_flags & O_NONBLOCK) == 0) {
 		if (wait_event_interruptible(port->wait_read,
 			saa7164_vbi_next_buf(port))) {
-				return -ERESTARTSYS;
+				return EPOLLERR;
 		}
 	}
 
-- 
cgit v1.2.3


From c46aa8491dd40d4ede5c9196c20d78e1e8c27786 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 09:23:33 -0400
Subject: media: s3c-camif: fix return code for the polling routine

All poll handlers should return a poll flag, and not error codes. So,
instead of returning an error, do the right thing here,
e. g. to return EPOLERR on errors, just like the V4L2 VB2 code.

Solves the following sparse warning:
    drivers/media/platform/s3c-camif/camif-capture.c:604:21: warning: incorrect type in assignment (different base types)
    drivers/media/platform/s3c-camif/camif-capture.c:604:21:    expected restricted __poll_t [usertype] ret
    drivers/media/platform/s3c-camif/camif-capture.c:604:21:    got int

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/s3c-camif/camif-capture.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/s3c-camif/camif-capture.c b/drivers/media/platform/s3c-camif/camif-capture.c
index b1d9f3857d3d..c02dce8b4c6c 100644
--- a/drivers/media/platform/s3c-camif/camif-capture.c
+++ b/drivers/media/platform/s3c-camif/camif-capture.c
@@ -601,7 +601,7 @@ static __poll_t s3c_camif_poll(struct file *file,
 
 	mutex_lock(&camif->lock);
 	if (vp->owner && vp->owner != file->private_data)
-		ret = -EBUSY;
+		ret = EPOLLERR;
 	else
 		ret = vb2_poll(&vp->vb_queue, file, wait);
 
-- 
cgit v1.2.3


From dcefa533bd97922a3cac37f395247082be44600b Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 09:25:37 -0400
Subject: media: radio-wl1273: fix return code for the polling routine

All poll handlers should return a poll flag, and not error codes. So,
instead of returning an error, do the right thing here,
e. g. to return EPOLERR on errors, just like the V4L2 VB2 code.

Solves the following sparse warning:
    drivers/media/radio/radio-wl1273.c:1099:24: warning: incorrect type in return expression (different base types)
    drivers/media/radio/radio-wl1273.c:1099:24:    expected restricted __poll_t
    drivers/media/radio/radio-wl1273.c:1099:24:    got int

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/radio/radio-wl1273.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/radio/radio-wl1273.c b/drivers/media/radio/radio-wl1273.c
index 8f9f8dfc3497..11aa94f189cb 100644
--- a/drivers/media/radio/radio-wl1273.c
+++ b/drivers/media/radio/radio-wl1273.c
@@ -1096,7 +1096,7 @@ static __poll_t wl1273_fm_fops_poll(struct file *file,
 	struct wl1273_core *core = radio->core;
 
 	if (radio->owner && radio->owner != file)
-		return -EBUSY;
+		return EPOLLERR;
 
 	radio->owner = file;
 
-- 
cgit v1.2.3


From 6c33d826b5c468033c21d8653d148dd758bbab28 Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Tue, 7 Aug 2018 09:48:36 -0400
Subject: media: isp: fix a warning about a wrong struct initializer

As sparse complains:
	drivers/media/platform/omap3isp/isp.c:303:39: warning: Using plain integer as NULL pointer

when a struct is initialized with { 0 }, actually the first
element of the struct is initialized with zeros, initializing the
other elements recursively. That can even generate gcc warnings
on nested structs.

So, instead, use the gcc-specific syntax for that (with is used
broadly inside the Kernel), initializing it with {};

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/platform/omap3isp/isp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/platform/omap3isp/isp.c b/drivers/media/platform/omap3isp/isp.c
index 03354d513311..842e2235047d 100644
--- a/drivers/media/platform/omap3isp/isp.c
+++ b/drivers/media/platform/omap3isp/isp.c
@@ -300,7 +300,7 @@ static struct clk *isp_xclk_src_get(struct of_phandle_args *clkspec, void *data)
 static int isp_xclk_init(struct isp_device *isp)
 {
 	struct device_node *np = isp->dev->of_node;
-	struct clk_init_data init = { 0 };
+	struct clk_init_data init = {};
 	unsigned int i;
 
 	for (i = 0; i < ARRAY_SIZE(isp->xclks); ++i)
-- 
cgit v1.2.3


From 8179de98cd35242446f4c7a6ecdd73c6c41f0cfb Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Wed, 8 Aug 2018 09:54:49 -0400
Subject: siano: get rid of an unused return code for debugfs register

The siano's debugfs register logic is optional: it should be ok
if it fails. So, no need to check if debufs register succeeded.

Signed-off-by: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
---
 drivers/media/common/siano/smsdvb-debugfs.c | 10 +++++-----
 drivers/media/common/siano/smsdvb.h         |  7 ++-----
 2 files changed, 7 insertions(+), 10 deletions(-)

diff --git a/drivers/media/common/siano/smsdvb-debugfs.c b/drivers/media/common/siano/smsdvb-debugfs.c
index 40891f4f842b..c95d4583498e 100644
--- a/drivers/media/common/siano/smsdvb-debugfs.c
+++ b/drivers/media/common/siano/smsdvb-debugfs.c
@@ -500,7 +500,7 @@ void smsdvb_debugfs_release(struct smsdvb_client_t *client)
 	client->debugfs = NULL;
 }
 
-int smsdvb_debugfs_register(void)
+void smsdvb_debugfs_register(void)
 {
 	struct dentry *d;
 
@@ -517,15 +517,15 @@ int smsdvb_debugfs_register(void)
 	d = debugfs_create_dir("smsdvb", usb_debug_root);
 	if (IS_ERR_OR_NULL(d)) {
 		pr_err("Couldn't create sysfs node for smsdvb\n");
-		return PTR_ERR(d);
-	} else {
-		smsdvb_debugfs_usb_root = d;
+		return;
 	}
-	return 0;
+	smsdvb_debugfs_usb_root = d;
 }
 
 void smsdvb_debugfs_unregister(void)
 {
+	if (!smsdvb_debugfs_usb_root)
+		return;
 	debugfs_remove_recursive(smsdvb_debugfs_usb_root);
 	smsdvb_debugfs_usb_root = NULL;
 }
diff --git a/drivers/media/common/siano/smsdvb.h b/drivers/media/common/siano/smsdvb.h
index b15754d95ec0..befeb9817e54 100644
--- a/drivers/media/common/siano/smsdvb.h
+++ b/drivers/media/common/siano/smsdvb.h
@@ -107,7 +107,7 @@ struct RECEPTION_STATISTICS_PER_SLICES_S {
 
 int smsdvb_debugfs_create(struct smsdvb_client_t *client);
 void smsdvb_debugfs_release(struct smsdvb_client_t *client);
-int smsdvb_debugfs_register(void);
+void smsdvb_debugfs_register(void);
 void smsdvb_debugfs_unregister(void);
 
 #else
@@ -119,10 +119,7 @@ static inline int smsdvb_debugfs_create(struct smsdvb_client_t *client)
 
 static inline void smsdvb_debugfs_release(struct smsdvb_client_t *client) {}
 
-static inline int smsdvb_debugfs_register(void)
-{
-	return 0;
-};
+static inline void smsdvb_debugfs_register(void) {}
 
 static inline void smsdvb_debugfs_unregister(void) {};
 
-- 
cgit v1.2.3


From 42342073e38b50113354944cd51dcfed28d857a1 Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 3 Aug 2018 16:38:47 +0200
Subject: PCI: mvebu: Convert to use pci_host_bridge directly

Rather than using the ARM-specific pci_common_init_dev() API, use the
pci_host_bridge logic directly.

Unfortunately, we can't use devm_of_pci_get_host_bridge_resources(),
because the DT binding for describing PCIe apertures for this PCI
controller is a bit special, and we cannot retrieve them from the
'ranges' property. Therefore, we still have some special code to
handle this.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-mvebu.c | 136 +++++++++++++++++--------------------
 1 file changed, 63 insertions(+), 73 deletions(-)

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 05f863435e5e..9055f03596ef 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -125,6 +125,7 @@ struct mvebu_pcie {
 	struct platform_device *pdev;
 	struct mvebu_pcie_port *ports;
 	struct msi_controller *msi;
+	struct list_head resources;
 	struct resource io;
 	struct resource realio;
 	struct resource mem;
@@ -800,7 +801,7 @@ static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie,
 static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 			      int where, int size, u32 val)
 {
-	struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata);
+	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
 	int ret;
 
@@ -826,7 +827,7 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 			      int size, u32 *val)
 {
-	struct mvebu_pcie *pcie = sys_to_pcie(bus->sysdata);
+	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
 	int ret;
 
@@ -857,36 +858,6 @@ static struct pci_ops mvebu_pcie_ops = {
 	.write = mvebu_pcie_wr_conf,
 };
 
-static int mvebu_pcie_setup(int nr, struct pci_sys_data *sys)
-{
-	struct mvebu_pcie *pcie = sys_to_pcie(sys);
-	int err, i;
-
-	pcie->mem.name = "PCI MEM";
-	pcie->realio.name = "PCI I/O";
-
-	if (resource_size(&pcie->realio) != 0)
-		pci_add_resource_offset(&sys->resources, &pcie->realio,
-					sys->io_offset);
-
-	pci_add_resource_offset(&sys->resources, &pcie->mem, sys->mem_offset);
-	pci_add_resource(&sys->resources, &pcie->busn);
-
-	err = devm_request_pci_bus_resources(&pcie->pdev->dev, &sys->resources);
-	if (err)
-		return 0;
-
-	for (i = 0; i < pcie->nports; i++) {
-		struct mvebu_pcie_port *port = &pcie->ports[i];
-
-		if (!port->base)
-			continue;
-		mvebu_pcie_setup_hw(port);
-	}
-
-	return 1;
-}
-
 static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 						 const struct resource *res,
 						 resource_size_t start,
@@ -917,26 +888,6 @@ static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 		return start;
 }
 
-static void mvebu_pcie_enable(struct mvebu_pcie *pcie)
-{
-	struct hw_pci hw;
-
-	memset(&hw, 0, sizeof(hw));
-
-#ifdef CONFIG_PCI_MSI
-	hw.msi_ctrl = pcie->msi;
-#endif
-
-	hw.nr_controllers = 1;
-	hw.private_data   = (void **)&pcie;
-	hw.setup          = mvebu_pcie_setup;
-	hw.map_irq        = of_irq_parse_and_map_pci;
-	hw.ops            = &mvebu_pcie_ops;
-	hw.align_resource = mvebu_pcie_align_resource;
-
-	pci_common_init_dev(&pcie->pdev->dev, &hw);
-}
-
 /*
  * Looks up the list of register addresses encoded into the reg =
  * <...> property for one that matches the given port/lane. Once
@@ -1190,28 +1141,39 @@ static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port)
 	clk_disable_unprepare(port->clk);
 }
 
-static int mvebu_pcie_probe(struct platform_device *pdev)
+/*
+ * We can't use devm_of_pci_get_host_bridge_resources() because we
+ * need to parse our special DT properties encoding the MEM and IO
+ * apertures.
+ */
+static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie)
 {
-	struct device *dev = &pdev->dev;
-	struct mvebu_pcie *pcie;
+	struct device *dev = &pcie->pdev->dev;
 	struct device_node *np = dev->of_node;
-	struct device_node *child;
-	int num, i, ret;
+	unsigned int i;
+	int ret;
 
-	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
-	if (!pcie)
-		return -ENOMEM;
+	INIT_LIST_HEAD(&pcie->resources);
 
-	pcie->pdev = pdev;
-	platform_set_drvdata(pdev, pcie);
+	/* Get the bus range */
+	ret = of_pci_parse_bus_range(np, &pcie->busn);
+	if (ret) {
+		dev_err(dev, "failed to parse bus-range property: %d\n", ret);
+		return ret;
+	}
+	pci_add_resource(&pcie->resources, &pcie->busn);
 
-	/* Get the PCIe memory and I/O aperture */
+	/* Get the PCIe memory aperture */
 	mvebu_mbus_get_pcie_mem_aperture(&pcie->mem);
 	if (resource_size(&pcie->mem) == 0) {
 		dev_err(dev, "invalid memory aperture size\n");
 		return -EINVAL;
 	}
 
+	pcie->mem.name = "PCI MEM";
+	pci_add_resource(&pcie->resources, &pcie->mem);
+
+	/* Get the PCIe IO aperture */
 	mvebu_mbus_get_pcie_io_aperture(&pcie->io);
 
 	if (resource_size(&pcie->io) != 0) {
@@ -1220,19 +1182,38 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 		pcie->realio.end = min_t(resource_size_t,
 					 IO_SPACE_LIMIT - SZ_64K,
 					 resource_size(&pcie->io) - 1);
+		pcie->realio.name = "PCI I/O";
 
 		for (i = 0; i < resource_size(&pcie->realio); i += SZ_64K)
 			pci_ioremap_io(i, pcie->io.start + i);
-	} else
-		pcie->realio = pcie->io;
 
-	/* Get the bus range */
-	ret = of_pci_parse_bus_range(np, &pcie->busn);
-	if (ret) {
-		dev_err(dev, "failed to parse bus-range property: %d\n", ret);
-		return ret;
+		pci_add_resource(&pcie->resources, &pcie->realio);
 	}
 
+	return devm_request_pci_bus_resources(dev, &pcie->resources);
+}
+
+static int mvebu_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mvebu_pcie *pcie;
+	struct pci_host_bridge *bridge;
+	struct device_node *np = dev->of_node;
+	struct device_node *child;
+	int num, i, ret;
+
+	bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct mvebu_pcie));
+	if (!bridge)
+		return -ENOMEM;
+
+	pcie = pci_host_bridge_priv(bridge);
+	pcie->pdev = pdev;
+	platform_set_drvdata(pdev, pcie);
+
+	ret = mvebu_pcie_parse_request_resources(pcie);
+	if (ret)
+		return ret;
+
 	num = of_get_available_child_count(np);
 
 	pcie->ports = devm_kcalloc(dev, num, sizeof(*pcie->ports), GFP_KERNEL);
@@ -1275,15 +1256,24 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 			continue;
 		}
 
+		mvebu_pcie_setup_hw(port);
 		mvebu_pcie_set_local_dev_nr(port, 1);
 		mvebu_sw_pci_bridge_init(port);
 	}
 
 	pcie->nports = i;
 
-	mvebu_pcie_enable(pcie);
-
-	return 0;
+	list_splice_init(&pcie->resources, &bridge->windows);
+	bridge->dev.parent = dev;
+	bridge->sysdata = pcie;
+	bridge->busnr = 0;
+	bridge->ops = &mvebu_pcie_ops;
+	bridge->map_irq = of_irq_parse_and_map_pci;
+	bridge->swizzle_irq = pci_common_swizzle;
+	bridge->align_resource = mvebu_pcie_align_resource;
+	bridge->msi = pcie->msi;
+
+	return pci_host_probe(bridge);
 }
 
 static const struct of_device_id mvebu_pcie_of_match_table[] = {
-- 
cgit v1.2.3


From f23d0d449c169d94cc958196a1d088705ef26ebc Mon Sep 17 00:00:00 2001
From: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Date: Fri, 3 Aug 2018 16:38:48 +0200
Subject: PCI: mvebu: Drop bogus comment above mvebu_pcie_map_registers()

This comment has been there since the driver was introduced, but seems
to be a leftover from previous iterations of the driver. Indeed, we do
not lookup in a list to find the register ranges that matches the
given port/lane, as the "reg" property is in each sub-node
representing a PCI port. There is no lookup involved at all.

Signed-off-by: Thomas Petazzoni <thomas.petazzoni@bootlin.com>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
---
 drivers/pci/controller/pci-mvebu.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index 9055f03596ef..50eb0729385b 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -888,11 +888,6 @@ static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev,
 		return start;
 }
 
-/*
- * Looks up the list of register addresses encoded into the reg =
- * <...> property for one that matches the given port/lane. Once
- * found, maps it.
- */
 static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev,
 					      struct device_node *np,
 					      struct mvebu_pcie_port *port)
-- 
cgit v1.2.3


From 3596924a233e45aa918c961a902170fc4916461b Mon Sep 17 00:00:00 2001
From: Roger Pau Monne <roger.pau@citrix.com>
Date: Wed, 8 Aug 2018 13:46:41 +0200
Subject: xen/balloon: fix balloon initialization for PVH Dom0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current balloon code tries to calculate a delta factor for the
balloon target when running in HVM mode in order to account for memory
used by the firmware.

This workaround for memory accounting doesn't work properly on a PVH
Dom0, that has a static-max value different from the target value even
at startup. Note that this is not a problem for DomUs because guests are
started with a static-max value that matches the amount of RAM in the
memory map.

Fix this by forcefully setting target_diff for Dom0, regardless of
it's mode.

Reported-by: Gabriel Bercarug <bercarug@amazon.com>
Signed-off-by: Roger Pau Monné <roger.pau@citrix.com>
Reviewed-by: Juergen Gross <jgross@suse.com>
Signed-off-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
---
 drivers/xen/xen-balloon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/xen/xen-balloon.c b/drivers/xen/xen-balloon.c
index b437fccd4e62..294f35ce9e46 100644
--- a/drivers/xen/xen-balloon.c
+++ b/drivers/xen/xen-balloon.c
@@ -81,7 +81,7 @@ static void watch_target(struct xenbus_watch *watch,
 			static_max = new_target;
 		else
 			static_max >>= PAGE_SHIFT - 10;
-		target_diff = xen_pv_domain() ? 0
+		target_diff = (xen_pv_domain() || xen_initial_domain()) ? 0
 				: static_max - balloon_stats.target_pages;
 	}
 
-- 
cgit v1.2.3


From d5fcc4e46e5168e6a6ce1e350ad0714a9d880c8e Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 8 Aug 2018 22:58:33 +0800
Subject: drivers/block/mtip32xx: remove the null check for
 debugfs_remove_recursive

debugfs_remove_recursive has taken null pointer into account. So it is
safe to drop the null check before calling the function.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/mtip32xx/mtip32xx.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c
index c73626decb46..db253cd5b32a 100644
--- a/drivers/block/mtip32xx/mtip32xx.c
+++ b/drivers/block/mtip32xx/mtip32xx.c
@@ -2575,8 +2575,7 @@ static int mtip_hw_debugfs_init(struct driver_data *dd)
 
 static void mtip_hw_debugfs_exit(struct driver_data *dd)
 {
-	if (dd->dfs_node)
-		debugfs_remove_recursive(dd->dfs_node);
+	debugfs_remove_recursive(dd->dfs_node);
 }
 
 /*
-- 
cgit v1.2.3


From 69daf897d75b31ff90031bb0a49a8d65cedfe3ca Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 8 Aug 2018 23:00:35 +0800
Subject: drivers/block/aoe/aoedev: NULL check is not needed for
 mempool_destroy

mempool_destroy has taken the null pointer into account. So it is safe
to remove the null check.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/aoe/aoedev.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index 697f735b07a4..41060e9cedf2 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -284,8 +284,8 @@ freedev(struct aoedev *d)
 	e = t + d->ntargets;
 	for (; t < e && *t; t++)
 		freetgt(d, *t);
-	if (d->bufpool)
-		mempool_destroy(d->bufpool);
+
+	mempool_destroy(d->bufpool);
 	skbpoolfree(d);
 	minor_free(d->sysminor);
 
-- 
cgit v1.2.3


From f5580d0f8bf60993a5fbc73ee04678070ffbba57 Mon Sep 17 00:00:00 2001
From: Bob Peterson <rpeterso@redhat.com>
Date: Wed, 8 Aug 2018 09:53:30 -0500
Subject: gfs2: eliminate update_rgrp_lvb_unlinked

Function update_rgrp_lvb_unlinked used to do the same thing as
be32_add_cpu. This patch removes it in favor of using be32_add_cpu
directly.

Signed-off-by: Bob Peterson <rpeterso@redhat.com>
Reviewed-by: Andrew Price <anprice@redhat.com>
---
 fs/gfs2/rgrp.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index ef50fe9b880a..1ad3256b9cbc 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -1111,13 +1111,6 @@ static int gfs2_rgrp_lvb_valid(struct gfs2_rgrpd *rgd)
 	return 1;
 }
 
-static void update_rgrp_lvb_unlinked(struct gfs2_rgrpd *rgd, u32 change)
-{
-	struct gfs2_rgrp_lvb *rgl = rgd->rd_rgl;
-	u32 unlinked = be32_to_cpu(rgl->rl_unlinked) + change;
-	rgl->rl_unlinked = cpu_to_be32(unlinked);
-}
-
 static u32 count_unlinked(struct gfs2_rgrpd *rgd)
 {
 	struct gfs2_bitmap *bi;
@@ -2489,7 +2482,7 @@ void gfs2_unlink_di(struct inode *inode)
 	trace_gfs2_block_alloc(ip, rgd, blkno, 1, GFS2_BLKST_UNLINKED);
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
-	update_rgrp_lvb_unlinked(rgd, 1);
+	be32_add_cpu(&rgd->rd_rgl->rl_unlinked, 1);
 }
 
 void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
@@ -2509,7 +2502,7 @@ void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip)
 
 	gfs2_trans_add_meta(rgd->rd_gl, rgd->rd_bits[0].bi_bh);
 	gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
-	update_rgrp_lvb_unlinked(rgd, -1);
+	be32_add_cpu(&rgd->rd_rgl->rl_unlinked, -1);
 
 	gfs2_statfs_change(sdp, 0, +1, -1);
 	trace_gfs2_block_alloc(ip, rgd, ip->i_no_addr, 1, GFS2_BLKST_FREE);
-- 
cgit v1.2.3


From a12fc00b237c25519cc861b56dd4ca41bbec4ed3 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Wed, 8 Aug 2018 23:22:47 +0800
Subject: drivers/block/drbd: remove the null check for kmem_cache_destroy

kmem_cache_destroy has taken null pointer into account. So it is
safe to drop the null check before calling the function.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/drbd/drbd_main.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
index a80809bd3057..ef8212a4b73e 100644
--- a/drivers/block/drbd/drbd_main.c
+++ b/drivers/block/drbd/drbd_main.c
@@ -2103,14 +2103,10 @@ static void drbd_destroy_mempools(void)
 	mempool_exit(&drbd_md_io_page_pool);
 	mempool_exit(&drbd_ee_mempool);
 	mempool_exit(&drbd_request_mempool);
-	if (drbd_ee_cache)
-		kmem_cache_destroy(drbd_ee_cache);
-	if (drbd_request_cache)
-		kmem_cache_destroy(drbd_request_cache);
-	if (drbd_bm_ext_cache)
-		kmem_cache_destroy(drbd_bm_ext_cache);
-	if (drbd_al_ext_cache)
-		kmem_cache_destroy(drbd_al_ext_cache);
+	kmem_cache_destroy(drbd_ee_cache);
+	kmem_cache_destroy(drbd_request_cache);
+	kmem_cache_destroy(drbd_bm_ext_cache);
+	kmem_cache_destroy(drbd_al_ext_cache);
 
 	drbd_ee_cache        = NULL;
 	drbd_request_cache   = NULL;
-- 
cgit v1.2.3


From 212dfd909ea8b630e5d6fa4d25aeec9c4b4b14a5 Mon Sep 17 00:00:00 2001
From: Fernando Fernandez Mancera <ffmancera@riseup.net>
Date: Tue, 7 Aug 2018 22:06:52 +0200
Subject: netfilter: nfnetlink_osf: add missing enum in nfnetlink_osf uapi
 header

xt_osf_window_size_options was originally part of
include/uapi/linux/netfilter/xt_osf.h, restore it.

Fixes: bfb15f2a95cb ("netfilter: extract Passive OS fingerprint infrastructure from xt_osf")
Signed-off-by: Fernando Fernandez Mancera <ffmancera@riseup.net>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/nfnetlink_osf.h      | 12 ------------
 include/uapi/linux/netfilter/nfnetlink_osf.h | 12 ++++++++++++
 include/uapi/linux/netfilter/xt_osf.h        |  1 +
 3 files changed, 13 insertions(+), 12 deletions(-)

diff --git a/include/linux/netfilter/nfnetlink_osf.h b/include/linux/netfilter/nfnetlink_osf.h
index a7311bc03d3a..ecf7dab81e9e 100644
--- a/include/linux/netfilter/nfnetlink_osf.h
+++ b/include/linux/netfilter/nfnetlink_osf.h
@@ -4,18 +4,6 @@
 
 #include <uapi/linux/netfilter/nfnetlink_osf.h>
 
-/* Initial window size option state machine: multiple of mss, mtu or
- * plain numeric value. Can also be made as plain numeric value which
- * is not a multiple of specified value.
- */
-enum nf_osf_window_size_options {
-	OSF_WSS_PLAIN   = 0,
-	OSF_WSS_MSS,
-	OSF_WSS_MTU,
-	OSF_WSS_MODULO,
-	OSF_WSS_MAX,
-};
-
 enum osf_fmatch_states {
 	/* Packet does not match the fingerprint */
 	FMATCH_WRONG = 0,
diff --git a/include/uapi/linux/netfilter/nfnetlink_osf.h b/include/uapi/linux/netfilter/nfnetlink_osf.h
index 3b93fbb9fc24..76a3527df5dd 100644
--- a/include/uapi/linux/netfilter/nfnetlink_osf.h
+++ b/include/uapi/linux/netfilter/nfnetlink_osf.h
@@ -88,6 +88,18 @@ enum iana_options {
 	OSFOPT_EMPTY = 255,
 };
 
+/* Initial window size option state machine: multiple of mss, mtu or
+ * plain numeric value. Can also be made as plain numeric value which
+ * is not a multiple of specified value.
+ */
+enum nf_osf_window_size_options {
+	OSF_WSS_PLAIN	= 0,
+	OSF_WSS_MSS,
+	OSF_WSS_MTU,
+	OSF_WSS_MODULO,
+	OSF_WSS_MAX,
+};
+
 enum nf_osf_attr_type {
 	OSF_ATTR_UNSPEC,
 	OSF_ATTR_FINGER,
diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h
index c56c59605c2b..24102b5286ec 100644
--- a/include/uapi/linux/netfilter/xt_osf.h
+++ b/include/uapi/linux/netfilter/xt_osf.h
@@ -46,6 +46,7 @@
 #define xt_osf_finger		nf_osf_finger
 #define xt_osf_nlmsg		nf_osf_nlmsg
 
+#define xt_osf_window_size_options	nf_osf_window_size_options
 #define xt_osf_attr_type	nf_osf_attr_type
 #define xt_osf_msg_types	nf_osf_msg_types
 
-- 
cgit v1.2.3


From 0a047f07525fecfa8f6fccc5d30afff7e816de8d Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 8 Aug 2018 17:13:38 +0100
Subject: ASoC: wm_adsp: Declare firmware controls from codec driver

To allow for more flexibility in naming of DSP-type cores
move the creation of the firmware controls to the codec
drivers instead of having a hardcoded list in wm_adsp.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs47l24.c |  3 +++
 sound/soc/codecs/wm2200.c  | 10 ++++------
 sound/soc/codecs/wm5102.c  |  2 ++
 sound/soc/codecs/wm5110.c  |  5 +++++
 sound/soc/codecs/wm_adsp.c | 35 +++++++++--------------------------
 sound/soc/codecs/wm_adsp.h | 10 +++++++++-
 6 files changed, 32 insertions(+), 33 deletions(-)

diff --git a/sound/soc/codecs/cs47l24.c b/sound/soc/codecs/cs47l24.c
index 0da52ead91e0..45e50fe3bf25 100644
--- a/sound/soc/codecs/cs47l24.c
+++ b/sound/soc/codecs/cs47l24.c
@@ -235,6 +235,9 @@ ARIZONA_MIXER_CONTROLS("AIF2TX6", ARIZONA_AIF2TX6MIX_INPUT_1_SOURCE),
 
 ARIZONA_MIXER_CONTROLS("AIF3TX1", ARIZONA_AIF3TX1MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("AIF3TX2", ARIZONA_AIF3TX2MIX_INPUT_1_SOURCE),
+
+WM_ADSP_FW_CONTROL("DSP2", 1),
+WM_ADSP_FW_CONTROL("DSP3", 2),
 };
 
 ARIZONA_MIXER_ENUMS(EQ1, ARIZONA_EQ1MIX_INPUT_1_SOURCE);
diff --git a/sound/soc/codecs/wm2200.c b/sound/soc/codecs/wm2200.c
index 3663b9fd4d65..deff65161504 100644
--- a/sound/soc/codecs/wm2200.c
+++ b/sound/soc/codecs/wm2200.c
@@ -1180,6 +1180,9 @@ SOC_DOUBLE_R_TLV("OUT2 Digital Volume", WM2200_DAC_DIGITAL_VOLUME_2L,
 SOC_DOUBLE("OUT2 Switch", WM2200_PDM_1, WM2200_SPK1L_MUTE_SHIFT,
 	   WM2200_SPK1R_MUTE_SHIFT, 1, 1),
 SOC_ENUM("RxANC Src", wm2200_rxanc_input_sel),
+
+WM_ADSP_FW_CONTROL("DSP1", 0),
+WM_ADSP_FW_CONTROL("DSP2", 1),
 };
 
 WM2200_MIXER_ENUMS(OUT1L, WM2200_OUT1LMIX_INPUT_1_SOURCE);
@@ -1553,15 +1556,10 @@ static const struct snd_soc_dapm_route wm2200_dapm_routes[] = {
 static int wm2200_probe(struct snd_soc_component *component)
 {
 	struct wm2200_priv *wm2200 = snd_soc_component_get_drvdata(component);
-	int ret;
 
 	wm2200->component = component;
 
-	ret = snd_soc_add_component_controls(component, wm_adsp_fw_controls, 2);
-	if (ret != 0)
-		return ret;
-
-	return ret;
+	return 0;
 }
 
 static int wm2200_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
diff --git a/sound/soc/codecs/wm5102.c b/sound/soc/codecs/wm5102.c
index a01a0c0e01eb..7e817e1877c2 100644
--- a/sound/soc/codecs/wm5102.c
+++ b/sound/soc/codecs/wm5102.c
@@ -985,6 +985,8 @@ ARIZONA_MIXER_CONTROLS("SLIMTX5", ARIZONA_SLIMTX5MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX6", ARIZONA_SLIMTX6MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX7", ARIZONA_SLIMTX7MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX8", ARIZONA_SLIMTX8MIX_INPUT_1_SOURCE),
+
+WM_ADSP_FW_CONTROL("DSP1", 0),
 };
 
 ARIZONA_MIXER_ENUMS(EQ1, ARIZONA_EQ1MIX_INPUT_1_SOURCE);
diff --git a/sound/soc/codecs/wm5110.c b/sound/soc/codecs/wm5110.c
index 00c735c585d9..b0789a03d699 100644
--- a/sound/soc/codecs/wm5110.c
+++ b/sound/soc/codecs/wm5110.c
@@ -927,6 +927,11 @@ ARIZONA_MIXER_CONTROLS("SLIMTX5", ARIZONA_SLIMTX5MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX6", ARIZONA_SLIMTX6MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX7", ARIZONA_SLIMTX7MIX_INPUT_1_SOURCE),
 ARIZONA_MIXER_CONTROLS("SLIMTX8", ARIZONA_SLIMTX8MIX_INPUT_1_SOURCE),
+
+WM_ADSP_FW_CONTROL("DSP1", 0),
+WM_ADSP_FW_CONTROL("DSP2", 1),
+WM_ADSP_FW_CONTROL("DSP3", 2),
+WM_ADSP_FW_CONTROL("DSP4", 3),
 };
 
 ARIZONA_MIXER_ENUMS(EQ1, ARIZONA_EQ1MIX_INPUT_1_SOURCE);
diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index e39b0e0b04df..fbd0515c49d7 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -684,8 +684,8 @@ static inline void wm_adsp_debugfs_clear(struct wm_adsp *dsp)
 }
 #endif
 
-static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
-			  struct snd_ctl_elem_value *ucontrol)
+int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
@@ -695,9 +695,10 @@ static int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(wm_adsp_fw_get);
 
-static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
-			  struct snd_ctl_elem_value *ucontrol)
+int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol)
 {
 	struct snd_soc_component *component = snd_soc_kcontrol_component(kcontrol);
 	struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
@@ -721,8 +722,9 @@ static int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(wm_adsp_fw_put);
 
-static const struct soc_enum wm_adsp_fw_enum[] = {
+const struct soc_enum wm_adsp_fw_enum[] = {
 	SOC_ENUM_SINGLE(0, 0, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 	SOC_ENUM_SINGLE(0, 1, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 	SOC_ENUM_SINGLE(0, 2, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
@@ -731,24 +733,7 @@ static const struct soc_enum wm_adsp_fw_enum[] = {
 	SOC_ENUM_SINGLE(0, 5, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 	SOC_ENUM_SINGLE(0, 6, ARRAY_SIZE(wm_adsp_fw_text), wm_adsp_fw_text),
 };
-
-const struct snd_kcontrol_new wm_adsp_fw_controls[] = {
-	SOC_ENUM_EXT("DSP1 Firmware", wm_adsp_fw_enum[0],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP2 Firmware", wm_adsp_fw_enum[1],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP3 Firmware", wm_adsp_fw_enum[2],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP4 Firmware", wm_adsp_fw_enum[3],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP5 Firmware", wm_adsp_fw_enum[4],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP6 Firmware", wm_adsp_fw_enum[5],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-	SOC_ENUM_EXT("DSP7 Firmware", wm_adsp_fw_enum[6],
-		     wm_adsp_fw_get, wm_adsp_fw_put),
-};
-EXPORT_SYMBOL_GPL(wm_adsp_fw_controls);
+EXPORT_SYMBOL_GPL(wm_adsp_fw_enum);
 
 static struct wm_adsp_region const *wm_adsp_find_region(struct wm_adsp *dsp,
 							int type)
@@ -2884,9 +2869,7 @@ int wm_adsp2_component_probe(struct wm_adsp *dsp, struct snd_soc_component *comp
 
 	dsp->component = component;
 
-	return snd_soc_add_component_controls(component,
-					  &wm_adsp_fw_controls[dsp->num - 1],
-					  1);
+	return 0;
 }
 EXPORT_SYMBOL_GPL(wm_adsp2_component_probe);
 
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index bc6d359f0533..8d58cb9d9bb9 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -121,7 +121,11 @@ struct wm_adsp {
 	.reg = SND_SOC_NOPM, .shift = num, .event = wm_adsp2_event, \
 	.event_flags = SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_PRE_PMD }
 
-extern const struct snd_kcontrol_new wm_adsp_fw_controls[];
+#define WM_ADSP_FW_CONTROL(dspname, num) \
+	SOC_ENUM_EXT(dspname " Firmware", wm_adsp_fw_enum[num], \
+		     wm_adsp_fw_get, wm_adsp_fw_put)
+
+extern const struct soc_enum wm_adsp_fw_enum[];
 
 int wm_adsp1_init(struct wm_adsp *dsp);
 int wm_adsp2_init(struct wm_adsp *dsp);
@@ -144,6 +148,10 @@ int wm_adsp2_preloader_get(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol);
 int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 			   struct snd_ctl_elem_value *ucontrol);
+int wm_adsp_fw_get(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol);
+int wm_adsp_fw_put(struct snd_kcontrol *kcontrol,
+		   struct snd_ctl_elem_value *ucontrol);
 
 int wm_adsp_compr_open(struct wm_adsp *dsp, struct snd_compr_stream *stream);
 int wm_adsp_compr_free(struct snd_compr_stream *stream);
-- 
cgit v1.2.3


From 605391d0f4bfdff2f2c6c5477ce0ccf776d8d5c0 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Wed, 8 Aug 2018 17:13:39 +0100
Subject: ASoC: wm_adsp: Make DSP name configurable by codec driver

Instead of harcoding that a core must always be called "DSPn"
add a name member to struct wm_adsp so that the owning codec
driver can provide a custom name. This allows for re-use of
the wm_adsp driver with parts where the processing cores are
named differently.

If no name is provided the default DSPn name is used.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm_adsp.c | 69 ++++++++++++++++++++++++++++++++--------------
 sound/soc/codecs/wm_adsp.h |  2 ++
 2 files changed, 50 insertions(+), 21 deletions(-)

diff --git a/sound/soc/codecs/wm_adsp.c b/sound/soc/codecs/wm_adsp.c
index 1c12c78dbcce..f61656070225 100644
--- a/sound/soc/codecs/wm_adsp.c
+++ b/sound/soc/codecs/wm_adsp.c
@@ -10,6 +10,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/ctype.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/init.h>
@@ -35,15 +36,15 @@
 #include "wm_adsp.h"
 
 #define adsp_crit(_dsp, fmt, ...) \
-	dev_crit(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_crit(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_err(_dsp, fmt, ...) \
-	dev_err(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_err(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_warn(_dsp, fmt, ...) \
-	dev_warn(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_warn(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_info(_dsp, fmt, ...) \
-	dev_info(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_info(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 #define adsp_dbg(_dsp, fmt, ...) \
-	dev_dbg(_dsp->dev, "DSP%d: " fmt, _dsp->num, ##__VA_ARGS__)
+	dev_dbg(_dsp->dev, "%s: " fmt, _dsp->name, ##__VA_ARGS__)
 
 #define ADSP1_CONTROL_1                   0x00
 #define ADSP1_CONTROL_2                   0x02
@@ -608,7 +609,6 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp,
 				  struct snd_soc_component *component)
 {
 	struct dentry *root = NULL;
-	char *root_name;
 	int i;
 
 	if (!component->debugfs_root) {
@@ -616,13 +616,7 @@ static void wm_adsp2_init_debugfs(struct wm_adsp *dsp,
 		goto err;
 	}
 
-	root_name = kmalloc(PAGE_SIZE, GFP_KERNEL);
-	if (!root_name)
-		goto err;
-
-	snprintf(root_name, PAGE_SIZE, "dsp%d", dsp->num);
-	root = debugfs_create_dir(root_name, component->debugfs_root);
-	kfree(root_name);
+	root = debugfs_create_dir(dsp->name, component->debugfs_root);
 
 	if (!root)
 		goto err;
@@ -1315,12 +1309,12 @@ static int wm_adsp_create_control(struct wm_adsp *dsp,
 	switch (dsp->fw_ver) {
 	case 0:
 	case 1:
-		snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "DSP%d %s %x",
-			 dsp->num, region_name, alg_region->alg);
+		snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN, "%s %s %x",
+			 dsp->name, region_name, alg_region->alg);
 		break;
 	default:
 		ret = snprintf(name, SNDRV_CTL_ELEM_ID_NAME_MAXLEN,
-				"DSP%d%c %.12s %x", dsp->num, *region_name,
+				"%s%c %.12s %x", dsp->name, *region_name,
 				wm_adsp_fw_text[dsp->fw], alg_region->alg);
 
 		/* Truncate the subname from the start if it is too long */
@@ -1648,7 +1642,7 @@ static int wm_adsp_load(struct wm_adsp *dsp)
 	if (file == NULL)
 		return -ENOMEM;
 
-	snprintf(file, PAGE_SIZE, "%s-dsp%d-%s.wmfw", dsp->part, dsp->num,
+	snprintf(file, PAGE_SIZE, "%s-%s-%s.wmfw", dsp->part, dsp->fwf_name,
 		 wm_adsp_fw[dsp->fw].file);
 	file[PAGE_SIZE - 1] = '\0';
 
@@ -2226,7 +2220,7 @@ static int wm_adsp_load_coeff(struct wm_adsp *dsp)
 	if (file == NULL)
 		return -ENOMEM;
 
-	snprintf(file, PAGE_SIZE, "%s-dsp%d-%s.bin", dsp->part, dsp->num,
+	snprintf(file, PAGE_SIZE, "%s-%s-%s.bin", dsp->part, dsp->fwf_name,
 		 wm_adsp_fw[dsp->fw].file);
 	file[PAGE_SIZE - 1] = '\0';
 
@@ -2398,8 +2392,38 @@ out:
 	return ret;
 }
 
+static int wm_adsp_create_name(struct wm_adsp *dsp)
+{
+	char *p;
+
+	if (!dsp->name) {
+		dsp->name = devm_kasprintf(dsp->dev, GFP_KERNEL, "DSP%d",
+					   dsp->num);
+		if (!dsp->name)
+			return -ENOMEM;
+	}
+
+	if (!dsp->fwf_name) {
+		p = devm_kstrdup(dsp->dev, dsp->name, GFP_KERNEL);
+		if (!p)
+			return -ENOMEM;
+
+		dsp->fwf_name = p;
+		for (; *p != 0; ++p)
+			*p = tolower(*p);
+	}
+
+	return 0;
+}
+
 int wm_adsp1_init(struct wm_adsp *dsp)
 {
+	int ret;
+
+	ret = wm_adsp_create_name(dsp);
+	if (ret)
+		return ret;
+
 	INIT_LIST_HEAD(&dsp->alg_regions);
 
 	mutex_init(&dsp->pwr_lock);
@@ -2672,7 +2696,7 @@ int wm_adsp2_preloader_put(struct snd_kcontrol *kcontrol,
 	struct wm_adsp *dsp = &dsps[mc->shift - 1];
 	char preload[32];
 
-	snprintf(preload, ARRAY_SIZE(preload), "DSP%u Preload", mc->shift);
+	snprintf(preload, ARRAY_SIZE(preload), "%s Preload", dsp->name);
 
 	dsp->preloaded = ucontrol->value.integer.value[0];
 
@@ -2867,8 +2891,7 @@ int wm_adsp2_component_probe(struct wm_adsp *dsp, struct snd_soc_component *comp
 {
 	char preload[32];
 
-	snprintf(preload, ARRAY_SIZE(preload), "DSP%d Preload", dsp->num);
-
+	snprintf(preload, ARRAY_SIZE(preload), "%s Preload", dsp->name);
 	snd_soc_component_disable_pin(component, preload);
 
 	wm_adsp2_init_debugfs(dsp, component);
@@ -2891,6 +2914,10 @@ int wm_adsp2_init(struct wm_adsp *dsp)
 {
 	int ret;
 
+	ret = wm_adsp_create_name(dsp);
+	if (ret)
+		return ret;
+
 	switch (dsp->rev) {
 	case 0:
 		/*
diff --git a/sound/soc/codecs/wm_adsp.h b/sound/soc/codecs/wm_adsp.h
index 8d58cb9d9bb9..4b8778b0b06c 100644
--- a/sound/soc/codecs/wm_adsp.h
+++ b/sound/soc/codecs/wm_adsp.h
@@ -57,6 +57,8 @@ struct wm_adsp_compr_buf;
 
 struct wm_adsp {
 	const char *part;
+	const char *name;
+	const char *fwf_name;
 	int rev;
 	int num;
 	int type;
-- 
cgit v1.2.3


From fb3b467e067385748445c5295fdbde548b631cb2 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Tue, 7 Aug 2018 19:20:08 +0800
Subject: net:af_iucv: get rid of the unneeded variable 'err' in
 afiucv_pm_freeze

We will not use the variable 'err' after initalization, So remove it and
return 0.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/iucv/af_iucv.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
index 92ee91e34395..a21d8ed0a325 100644
--- a/net/iucv/af_iucv.c
+++ b/net/iucv/af_iucv.c
@@ -150,7 +150,6 @@ static int afiucv_pm_freeze(struct device *dev)
 {
 	struct iucv_sock *iucv;
 	struct sock *sk;
-	int err = 0;
 
 #ifdef CONFIG_PM_DEBUG
 	printk(KERN_WARNING "afiucv_pm_freeze\n");
@@ -175,7 +174,7 @@ static int afiucv_pm_freeze(struct device *dev)
 		skb_queue_purge(&iucv->backlog_skb_q);
 	}
 	read_unlock(&iucv_sk_list.lock);
-	return err;
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 5a0c6cee1767a551dacfa6e266ac4795bba0555e Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Tue, 7 Aug 2018 19:20:09 +0800
Subject: net:mod: remove unneeded variable 'ret' in init_p9

The ret is modified after initalization, so just remove it and
return 0.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/9p/mod.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/net/9p/mod.c b/net/9p/mod.c
index eb9777f05755..253ba824a325 100644
--- a/net/9p/mod.c
+++ b/net/9p/mod.c
@@ -171,13 +171,11 @@ void v9fs_put_trans(struct p9_trans_module *m)
  */
 static int __init init_p9(void)
 {
-	int ret = 0;
-
 	p9_error_init();
 	pr_info("Installing 9P2000 support\n");
 	p9_trans_fd_init();
 
-	return ret;
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 9c2956d2ad9e0e7d5827290ba9a716ed3fb83bcd Mon Sep 17 00:00:00 2001
From: Zhao Chen <zhaochen6@huawei.com>
Date: Wed, 8 Aug 2018 06:37:30 +0000
Subject: net-next: hinic: fix a problem in free_tx_poll()

This patch fixes the problem below. The problem can be reproduced by the
following steps:
1) Connecting all HiNIC interfaces
2) On server side
    # sudo ifconfig eth0 192.168.100.1 up #Using MLX CX4 card
    # iperf -s
3) On client side
    # sudo ifconfig eth0 192.168.100.2 up #Using our HiNIC card
    # iperf -c 192.168.101.1 -P 10 -t 100000

after hours of testing, we will see errors:

    hinic 0000:05:00.0: No MGMT msg handler, mod = 0
    hinic 0000:05:00.0: No MGMT msg handler, mod = 0
    hinic 0000:05:00.0: No MGMT msg handler, mod = 0
    hinic 0000:05:00.0: No MGMT msg handler, mod = 0

The errors are caused by the following problem.
1) The hinic_get_wqe() checks the "wq->delta" to allocate new WQEs:

	if (atomic_sub_return(num_wqebbs, &wq->delta) <= 0) {
		atomic_add(num_wqebbs, &wq->delta);
		return ERR_PTR(-EBUSY);
	}

If the WQE occupies multiple pages, the shadow WQE will be used. Then the
hinic_xmit_frame() fills the WQE.

2) While in parallel with 1), the free_tx_poll() checks the "wq->delta"
to free old WQEs:

	if ((atomic_read(&wq->delta) + num_wqebbs) > wq->q_depth)
		return ERR_PTR(-EBUSY);

There is a probability that the shadow WQE which hinic_xmit_frame() is
using will be damaged by copy_wqe_to_shadow():

	if (curr_pg != end_pg) {
		void *shadow_addr = &wq->shadow_wqe[curr_pg * wq->max_wqe_size];

		copy_wqe_to_shadow(wq, shadow_addr, num_wqebbs, *cons_idx);
		return shadow_addr;
	}

This can cause WQE data error and you will see the above error messages.
This patch fixes the problem.

Signed-off-by: Zhao Chen <zhaochen6@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c | 36 +++++++++++++++++++------
 drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h |  6 ++++-
 drivers/net/ethernet/huawei/hinic/hinic_tx.c    | 18 +++++++++++--
 3 files changed, 49 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
index b9db6d649743..cb239627770f 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.c
@@ -635,17 +635,18 @@ void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx,
 }
 
 /**
- * hinic_sq_read_wqe - read wqe ptr in the current ci and update the ci
+ * hinic_sq_read_wqebb - read wqe ptr in the current ci and update the ci, the
+ * wqe only have one wqebb
  * @sq: send queue
  * @skb: return skb that was saved
- * @wqe_size: the size of the wqe
+ * @wqe_size: the wqe size ptr
  * @cons_idx: consumer index of the wqe
  *
  * Return wqe in ci position
  **/
-struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
-				       struct sk_buff **skb,
-				       unsigned int *wqe_size, u16 *cons_idx)
+struct hinic_sq_wqe *hinic_sq_read_wqebb(struct hinic_sq *sq,
+					 struct sk_buff **skb,
+					 unsigned int *wqe_size, u16 *cons_idx)
 {
 	struct hinic_hw_wqe *hw_wqe;
 	struct hinic_sq_wqe *sq_wqe;
@@ -658,6 +659,8 @@ struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 	if (IS_ERR(hw_wqe))
 		return NULL;
 
+	*skb = sq->saved_skb[*cons_idx];
+
 	sq_wqe = &hw_wqe->sq_wqe;
 	ctrl = &sq_wqe->ctrl;
 	ctrl_info = be32_to_cpu(ctrl->ctrl_info);
@@ -665,11 +668,28 @@ struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 
 	*wqe_size = sizeof(*ctrl) + sizeof(sq_wqe->task);
 	*wqe_size += SECT_SIZE_FROM_8BYTES(buf_sect_len);
+	*wqe_size = ALIGN(*wqe_size, sq->wq->wqebb_size);
 
-	*skb = sq->saved_skb[*cons_idx];
+	return &hw_wqe->sq_wqe;
+}
+
+/**
+ * hinic_sq_read_wqe - read wqe ptr in the current ci and update the ci
+ * @sq: send queue
+ * @skb: return skb that was saved
+ * @wqe_size: the size of the wqe
+ * @cons_idx: consumer index of the wqe
+ *
+ * Return wqe in ci position
+ **/
+struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
+				       struct sk_buff **skb,
+				       unsigned int wqe_size, u16 *cons_idx)
+{
+	struct hinic_hw_wqe *hw_wqe;
 
-	/* using the real wqe size to read wqe again */
-	hw_wqe = hinic_read_wqe(sq->wq, *wqe_size, cons_idx);
+	hw_wqe = hinic_read_wqe(sq->wq, wqe_size, cons_idx);
+	*skb = sq->saved_skb[*cons_idx];
 
 	return &hw_wqe->sq_wqe;
 }
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
index df729a1587e9..6c84f83ec283 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
+++ b/drivers/net/ethernet/huawei/hinic/hinic_hw_qp.h
@@ -165,7 +165,11 @@ void hinic_sq_write_wqe(struct hinic_sq *sq, u16 prod_idx,
 
 struct hinic_sq_wqe *hinic_sq_read_wqe(struct hinic_sq *sq,
 				       struct sk_buff **skb,
-				       unsigned int *wqe_size, u16 *cons_idx);
+				       unsigned int wqe_size, u16 *cons_idx);
+
+struct hinic_sq_wqe *hinic_sq_read_wqebb(struct hinic_sq *sq,
+					 struct sk_buff **skb,
+					 unsigned int *wqe_size, u16 *cons_idx);
 
 void hinic_sq_put_wqe(struct hinic_sq *sq, unsigned int wqe_size);
 
diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
index 2353ec829c04..c5fca0356c9c 100644
--- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c
+++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c
@@ -283,7 +283,11 @@ static void free_all_tx_skbs(struct hinic_txq *txq)
 	int nr_sges;
 	u16 ci;
 
-	while ((sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &ci))) {
+	while ((sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &ci))) {
+		sq_wqe = hinic_sq_read_wqe(sq, &skb, wqe_size, &ci);
+		if (!sq_wqe)
+			break;
+
 		nr_sges = skb_shinfo(skb)->nr_frags + 1;
 
 		hinic_sq_get_sges(sq_wqe, txq->free_sges, nr_sges);
@@ -319,11 +323,21 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 	do {
 		hw_ci = HW_CONS_IDX(sq) & wq->mask;
 
-		sq_wqe = hinic_sq_read_wqe(sq, &skb, &wqe_size, &sw_ci);
+		/* Reading a WQEBB to get real WQE size and consumer index. */
+		sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &sw_ci);
 		if ((!sq_wqe) ||
 		    (((hw_ci - sw_ci) & wq->mask) * wq->wqebb_size < wqe_size))
 			break;
 
+		/* If this WQE have multiple WQEBBs, we will read again to get
+		 * full size WQE.
+		 */
+		if (wqe_size > wq->wqebb_size) {
+			sq_wqe = hinic_sq_read_wqe(sq, &skb, wqe_size, &sw_ci);
+			if (unlikely(!sq_wqe))
+				break;
+		}
+
 		tx_bytes += skb->len;
 		pkts++;
 
-- 
cgit v1.2.3


From 02eec6c9fc0cb13169cc97a6139771768791f92b Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Wed, 8 Aug 2018 09:30:56 -0700
Subject: MIPS: netlogic: xlr: Remove erroneous check in nlm_fmn_send()

In nlm_fmn_send() we have a loop which attempts to send a message
multiple times in order to handle the transient failure condition of a
lack of available credit. When examining the status register to detect
the failure we check for a condition that can never be true, which falls
foul of gcc 8's -Wtautological-compare:

  In file included from arch/mips/netlogic/common/irq.c:65:
  ./arch/mips/include/asm/netlogic/xlr/fmn.h: In function 'nlm_fmn_send':
  ./arch/mips/include/asm/netlogic/xlr/fmn.h:304:22: error: bitwise
    comparison always evaluates to false [-Werror=tautological-compare]
     if ((status & 0x2) == 1)
                        ^~

If the path taken if this condition were true all we do is print a
message to the kernel console. Since failures seem somewhat expected
here (making the console message questionable anyway) and the condition
has clearly never evaluated true we simply remove it, rather than
attempting to fix it to check status correctly.

Signed-off-by: Paul Burton <paul.burton@mips.com>
Patchwork: https://patchwork.linux-mips.org/patch/20174/
Cc: Ganesan Ramalingam <ganesanr@broadcom.com>
Cc: James Hogan <jhogan@kernel.org>
Cc: Jayachandran C <jnair@caviumnetworks.com>
Cc: John Crispin <john@phrozen.org>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
---
 arch/mips/include/asm/netlogic/xlr/fmn.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/mips/include/asm/netlogic/xlr/fmn.h b/arch/mips/include/asm/netlogic/xlr/fmn.h
index 5604db3d1836..d79c68fa78d9 100644
--- a/arch/mips/include/asm/netlogic/xlr/fmn.h
+++ b/arch/mips/include/asm/netlogic/xlr/fmn.h
@@ -301,8 +301,6 @@ static inline int nlm_fmn_send(unsigned int size, unsigned int code,
 	for (i = 0; i < 8; i++) {
 		nlm_msgsnd(dest);
 		status = nlm_read_c2_status0();
-		if ((status & 0x2) == 1)
-			pr_info("Send pending fail!\n");
 		if ((status & 0x4) == 0)
 			return 0;
 	}
-- 
cgit v1.2.3


From da33a871ba178dbe81da7d755818d3c2088cae32 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 8 Aug 2018 12:54:09 -0400
Subject: locks: remove misleading obsolete comment

The spinlock handling in this file has changed significantly since this
comment was written, and the file_lock_lock is no more. In addition,
this overall comment no longer applies. Deleting an entry now requires
both locks.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/locks.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/fs/locks.c b/fs/locks.c
index 6138a9bcd924..11a4d698aba8 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -202,10 +202,6 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS);
  * we often hold the flc_lock as well. In certain cases, when reading the fields
  * protected by this lock, we can skip acquiring it iff we already hold the
  * flc_lock.
- *
- * In particular, adding an entry to the fl_block list requires that you hold
- * both the flc_lock and the blocked_lock_lock (acquired in that order).
- * Deleting an entry from the list however only requires the file_lock_lock.
  */
 static DEFINE_SPINLOCK(blocked_lock_lock);
 
-- 
cgit v1.2.3


From e7ea2a52ffaf60a211edc0df97dcf194d1257714 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 8 Aug 2018 03:23:44 +0000
Subject: netfilter: nfnetlink_osf: fix using plain integer as NULL warning

Fixes the following sparse warning:

net/netfilter/nfnetlink_osf.c:274:24: warning:
 Using plain integer as NULL pointer

Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nfnetlink_osf.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c
index f9dba62c450f..00db27dfd2ff 100644
--- a/net/netfilter/nfnetlink_osf.c
+++ b/net/netfilter/nfnetlink_osf.c
@@ -271,7 +271,7 @@ const char *nf_osf_find(const struct sk_buff *skb,
 
 	tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts);
 	if (!tcp)
-		return false;
+		return NULL;
 
 	list_for_each_entry_rcu(kf, &nf_osf_fingers[ctx.df], finger_entry) {
 		f = &kf->finger;
-- 
cgit v1.2.3


From a62e4739473a29646af4e37a5da289795cde6dc0 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:12 -0400
Subject: ALSA: hda/ca0132 - Create mmio gpio function to make code clearer

This patch adds a new function, ca0132_mmio_gpio_set, to clear up what
is going on with writes to mmio region 0x320.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 62 +++++++++++++++++++++++++++-----------------
 1 file changed, 38 insertions(+), 24 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 27d3388cd2a2..665142ef1186 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -3072,6 +3072,24 @@ static bool dspload_wait_loaded(struct hda_codec *codec)
  * Setup GPIO for the other variants of Core3D.
  */
 
+/*
+ * For cards with PCI-E region2 (Sound Blaster Z/ZxR, Recon3D, and AE-5)
+ * the mmio address 0x320 is used to set GPIO pins. The format for the data
+ * The first eight bits are just the number of the pin. So far, I've only seen
+ * this number go to 7.
+ */
+static void ca0132_mmio_gpio_set(struct hda_codec *codec, unsigned int gpio_pin,
+		bool enable)
+{
+	struct ca0132_spec *spec = codec->spec;
+	unsigned short gpio_data;
+
+	gpio_data = gpio_pin & 0xF;
+	gpio_data |= ((enable << 8) & 0x100);
+
+	writew(gpio_data, spec->mem_base + 0x320);
+}
+
 /*
  * Sets up the GPIO pins so that they are discoverable. If this isn't done,
  * the card shows as having no GPIO pins.
@@ -3947,9 +3965,9 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 		/*speaker out config*/
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0007, spec->mem_base + 0x320);
-			writew(0x0104, spec->mem_base + 0x320);
-			writew(0x0101, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 7, false);
+			ca0132_mmio_gpio_set(codec, 4, true);
+			ca0132_mmio_gpio_set(codec, 1, true);
 			chipio_set_control_param(codec, 0x0D, 0x18);
 			break;
 		case QUIRK_R3DI:
@@ -3983,9 +4001,9 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 		/* Headphone out config*/
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0107, spec->mem_base + 0x320);
-			writew(0x0104, spec->mem_base + 0x320);
-			writew(0x0001, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 7, true);
+			ca0132_mmio_gpio_set(codec, 4, true);
+			ca0132_mmio_gpio_set(codec, 1, false);
 			chipio_set_control_param(codec, 0x0D, 0x12);
 			break;
 		case QUIRK_R3DI:
@@ -4025,9 +4043,9 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 		/* Surround out config*/
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0007, spec->mem_base + 0x320);
-			writew(0x0104, spec->mem_base + 0x320);
-			writew(0x0101, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 7, false);
+			ca0132_mmio_gpio_set(codec, 4, true);
+			ca0132_mmio_gpio_set(codec, 1, true);
 			chipio_set_control_param(codec, 0x0D, 0x18);
 			break;
 		case QUIRK_R3DI:
@@ -4291,7 +4309,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 	case REAR_MIC:
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0000, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 0, false);
 			tmp = FLOAT_THREE;
 			break;
 		case QUIRK_R3DI:
@@ -4323,7 +4341,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 		ca0132_mic_boost_set(codec, 0);
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0000, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 0, false);
 			break;
 		case QUIRK_R3DI:
 			r3di_gpio_mic_set(codec, R3DI_REAR_MIC);
@@ -4349,8 +4367,8 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 	case FRONT_MIC:
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
-			writew(0x0100, spec->mem_base + 0x320);
-			writew(0x0005, spec->mem_base + 0x320);
+			ca0132_mmio_gpio_set(codec, 0, true);
+			ca0132_mmio_gpio_set(codec, 5, false);
 			tmp = FLOAT_THREE;
 			break;
 		case QUIRK_R3DI:
@@ -6890,16 +6908,12 @@ static void sbz_region2_exit(struct hda_codec *codec)
 		writeb(0x0, spec->mem_base + 0x100);
 	for (i = 0; i < 8; i++)
 		writeb(0xb3, spec->mem_base + 0x304);
-	/*
-	 * I believe these are GPIO, with the right most hex digit being the
-	 * gpio pin, and the second digit being on or off. We see this more in
-	 * the input/output select functions.
-	 */
-	writew(0x0000, spec->mem_base + 0x320);
-	writew(0x0001, spec->mem_base + 0x320);
-	writew(0x0104, spec->mem_base + 0x320);
-	writew(0x0005, spec->mem_base + 0x320);
-	writew(0x0007, spec->mem_base + 0x320);
+
+	ca0132_mmio_gpio_set(codec, 0, false);
+	ca0132_mmio_gpio_set(codec, 1, false);
+	ca0132_mmio_gpio_set(codec, 4, true);
+	ca0132_mmio_gpio_set(codec, 5, false);
+	ca0132_mmio_gpio_set(codec, 7, false);
 }
 
 static void sbz_set_pin_ctl_default(struct hda_codec *codec)
@@ -7236,7 +7250,7 @@ static int ca0132_init(struct hda_codec *codec)
 	ca0132_refresh_widget_caps(codec);
 
 	if (spec->quirk == QUIRK_SBZ)
-		writew(0x0107, spec->mem_base + 0x320);
+		ca0132_mmio_gpio_set(codec, 7, true);
 
 	switch (spec->quirk) {
 	case QUIRK_R3DI:
-- 
cgit v1.2.3


From d97420d2b0379e498adc3fae5db8fa70945b5d56 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:13 -0400
Subject: ALSA: hda/ca0132 - Clean up ca0132_init function.

This patch cleans up ca0132_init by removing unnecessary commands and
ordering things better.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 16 +++-------------
 1 file changed, 3 insertions(+), 13 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 665142ef1186..8b98d18d97ac 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -7249,14 +7249,12 @@ static int ca0132_init(struct hda_codec *codec)
 
 	ca0132_refresh_widget_caps(codec);
 
-	if (spec->quirk == QUIRK_SBZ)
-		ca0132_mmio_gpio_set(codec, 7, true);
-
 	switch (spec->quirk) {
 	case QUIRK_R3DI:
 		r3di_setup_defaults(codec);
 		break;
 	case QUIRK_SBZ:
+		sbz_setup_defaults(codec);
 		break;
 	default:
 		ca0132_setup_defaults(codec);
@@ -7287,20 +7285,12 @@ static int ca0132_init(struct hda_codec *codec)
 		ca0132_gpio_setup(codec);
 
 	snd_hda_sequence_write(codec, spec->spec_init_verbs);
-	switch (spec->quirk) {
-	case QUIRK_SBZ:
-		sbz_setup_defaults(codec);
-		ca0132_alt_select_out(codec);
-		ca0132_alt_select_in(codec);
-		break;
-	case QUIRK_R3DI:
+	if (spec->use_alt_functions) {
 		ca0132_alt_select_out(codec);
 		ca0132_alt_select_in(codec);
-		break;
-	default:
+	} else {
 		ca0132_select_out(codec);
 		ca0132_select_mic(codec);
-		break;
 	}
 
 	snd_hda_jack_report_sync(codec);
-- 
cgit v1.2.3


From a1b7f016a1ae5e51f0e11a70cf1a5875d3ccee73 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:14 -0400
Subject: ALSA: hda/ca0132 - Add alt_functions unsolicited response

This patch fixes a previous oversight where the microphone unsolicited
response would use the wrong input selection function.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 8b98d18d97ac..3e43d5686207 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -6744,7 +6744,12 @@ static void hp_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 
 static void amic_callback(struct hda_codec *codec, struct hda_jack_callback *cb)
 {
-	ca0132_select_mic(codec);
+	struct ca0132_spec *spec = codec->spec;
+
+	if (spec->use_alt_functions)
+		ca0132_alt_select_in(codec);
+	else
+		ca0132_select_mic(codec);
 }
 
 static void ca0132_init_unsol(struct hda_codec *codec)
-- 
cgit v1.2.3


From 8f8c523c4604afe231196920bf08310141a4f0ba Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:15 -0400
Subject: ALSA: hda/ca0132 - Add quirk ID and enum for Recon3D

This patch adds the PCI subsys ID for the Recon3D that has been tested,
and adds the QUIRK_R3D enumeration.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 3e43d5686207..8a4be5fcba55 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -994,6 +994,7 @@ enum {
 	QUIRK_ALIENWARE_M17XR4,
 	QUIRK_SBZ,
 	QUIRK_R3DI,
+	QUIRK_R3D,
 };
 
 static const struct hda_pintbl alienware_pincfgs[] = {
@@ -1050,6 +1051,7 @@ static const struct snd_pci_quirk ca0132_quirks[] = {
 	SND_PCI_QUIRK(0x1458, 0xA016, "Recon3Di", QUIRK_R3DI),
 	SND_PCI_QUIRK(0x1458, 0xA026, "Gigabyte G1.Sniper Z97", QUIRK_R3DI),
 	SND_PCI_QUIRK(0x1458, 0xA036, "Gigabyte GA-Z170X-Gaming 7", QUIRK_R3DI),
+	SND_PCI_QUIRK(0x1102, 0x0013, "Recon3D", QUIRK_R3D),
 	{}
 };
 
-- 
cgit v1.2.3


From 7f73df95401f7a2392ccf1880ba1e54cfed62779 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:16 -0400
Subject: ALSA: hda/ca0132 - Add Recon3D pincfg

This patch adds pin configs from the Recon3D, taken from the Window's
driver.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 8a4be5fcba55..4d2b79e19516 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -1026,6 +1026,21 @@ static const struct hda_pintbl sbz_pincfgs[] = {
 	{}
 };
 
+/* Recon3D pin configs taken from Windows Driver */
+static const struct hda_pintbl r3d_pincfgs[] = {
+	{ 0x0b, 0x01014110 }, /* Port G -- Lineout FRONT L/R */
+	{ 0x0c, 0x014510f0 }, /* SPDIF Out 1 */
+	{ 0x0d, 0x014510f0 }, /* Digital Out */
+	{ 0x0e, 0x01c520f0 }, /* SPDIF In */
+	{ 0x0f, 0x0221401f }, /* Port A -- BackPanel HP */
+	{ 0x10, 0x01016011 }, /* Port D -- Center/LFE or FP Hp */
+	{ 0x11, 0x01011014 }, /* Port B -- LineMicIn2 / Rear L/R */
+	{ 0x12, 0x02a090f0 }, /* Port C -- LineIn1 */
+	{ 0x13, 0x908700f0 }, /* What U Hear In*/
+	{ 0x18, 0x50d000f0 }, /* N/A */
+	{}
+};
+
 /* Recon3D integrated pin configs taken from Windows Driver */
 static const struct hda_pintbl r3di_pincfgs[] = {
 	{ 0x0b, 0x01014110 }, /* Port G -- Lineout FRONT L/R */
@@ -7396,8 +7411,15 @@ static void ca0132_config(struct hda_codec *codec)
 		spec->unsol_tag_amic1 = 0x11;
 		break;
 	case QUIRK_SBZ:
-		codec_dbg(codec, "%s: QUIRK_SBZ applied.\n", __func__);
-		snd_hda_apply_pincfgs(codec, sbz_pincfgs);
+	case QUIRK_R3D:
+		if (spec->quirk == QUIRK_SBZ) {
+			codec_dbg(codec, "%s: QUIRK_SBZ applied.\n", __func__);
+			snd_hda_apply_pincfgs(codec, sbz_pincfgs);
+		}
+		if (spec->quirk == QUIRK_R3D) {
+			codec_dbg(codec, "%s: QUIRK_R3D applied.\n", __func__);
+			snd_hda_apply_pincfgs(codec, r3d_pincfgs);
+		}
 
 		spec->num_outputs = 2;
 		spec->out_pins[0] = 0x0B; /* Line out */
-- 
cgit v1.2.3


From 08eca6b1f1468a4021bac7b3929fd3eb491e2629 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:17 -0400
Subject: ALSA: hda/ca0132 - Add bool variable to enable/disable pci region2
 mmio

This patch adds the ability to choose whether or not to map the pci
region2, which is used for things such as GPIO on the Recon3D and Sound
Blaster Z.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 4d2b79e19516..989770797a00 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -965,9 +965,11 @@ struct ca0132_spec {
 	long cur_ctl_vals[TUNING_CTLS_COUNT];
 #endif
 	/*
-	 * Sound Blaster Z PCI region 2 iomem, used for input and output
-	 * switching, and other unknown commands.
+	 * The Recon3D, Sound Blaster Z, Sound Blaster ZxR, and Sound Blaster
+	 * AE-5 all use PCI region 2 to toggle GPIO and other currently unknown
+	 * things.
 	 */
+	bool use_pci_mmio;
 	void __iomem *mem_base;
 
 	/*
@@ -7562,16 +7564,6 @@ static int patch_ca0132(struct hda_codec *codec)
 	else
 		spec->quirk = QUIRK_NONE;
 
-	/* Setup BAR Region 2 for Sound Blaster Z */
-	if (spec->quirk == QUIRK_SBZ) {
-		spec->mem_base = pci_iomap(codec->bus->pci, 2, 0xC20);
-		if (spec->mem_base == NULL) {
-			codec_warn(codec, "pci_iomap failed!");
-			codec_info(codec, "perhaps this is not an SBZ?");
-			spec->quirk = QUIRK_NONE;
-		}
-	}
-
 	spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->num_mixers = 1;
 
@@ -7590,19 +7582,33 @@ static int patch_ca0132(struct hda_codec *codec)
 		break;
 	}
 
-	/* Setup whether or not to use alt functions/controls */
+	/* Setup whether or not to use alt functions/controls/pci_mmio */
 	switch (spec->quirk) {
 	case QUIRK_SBZ:
+		spec->use_alt_controls = true;
+		spec->use_alt_functions = true;
+		spec->use_pci_mmio = true;
+		break;
 	case QUIRK_R3DI:
 		spec->use_alt_controls = true;
 		spec->use_alt_functions = true;
+		spec->use_pci_mmio = false;
 		break;
 	default:
 		spec->use_alt_controls = false;
 		spec->use_alt_functions = false;
+		spec->use_pci_mmio = false;
 		break;
 	}
 
+	if (spec->use_pci_mmio) {
+		spec->mem_base = pci_iomap(codec->bus->pci, 2, 0xC20);
+		if (spec->mem_base == NULL) {
+			codec_warn(codec, "pci_iomap failed! Setting quirk to QUIRK_NONE.");
+			spec->quirk = QUIRK_NONE;
+		}
+	}
+
 	spec->base_init_verbs = ca0132_base_init_verbs;
 	spec->base_exit_verbs = ca0132_base_exit_verbs;
 
-- 
cgit v1.2.3


From e42c7c7313e41f121d252711e35deae7964c95ad Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:18 -0400
Subject: ALSA: hda/ca0132 - Add Recon3D startup functions and setup

This patch adds functions for Recon3D startup, and sets values for
things such as use_pci_mmio. It also renames some functions and tables
from the sbz prefix into ca0132, as the Recon3D uses them as well.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 49 ++++++++++++++++++++++++++++++++------------
 1 file changed, 36 insertions(+), 13 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 989770797a00..c938298cb103 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -897,7 +897,7 @@ struct ca0132_spec {
 	const struct hda_verb *base_init_verbs;
 	const struct hda_verb *base_exit_verbs;
 	const struct hda_verb *chip_init_verbs;
-	const struct hda_verb *sbz_init_verbs;
+	const struct hda_verb *desktop_init_verbs;
 	struct hda_verb *spec_init_verbs;
 	struct auto_pin_cfg autocfg;
 
@@ -6839,8 +6839,8 @@ static struct hda_verb ca0132_init_verbs0[] = {
 	{}
 };
 
-/* Extra init verbs for SBZ */
-static struct hda_verb sbz_init_verbs[] = {
+/* Extra init verbs for desktop cards. */
+static struct hda_verb ca0132_init_verbs1[] = {
 	{0x15, 0x70D, 0x20},
 	{0x15, 0x70E, 0x19},
 	{0x15, 0x707, 0x00},
@@ -7135,9 +7135,27 @@ static void sbz_pre_dsp_setup(struct hda_codec *codec)
 			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x44);
 }
 
-/*
- * Extra commands that don't really fit anywhere else.
- */
+static void r3d_pre_dsp_setup(struct hda_codec *codec)
+{
+
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfc);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfd);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xfe);
+	snd_hda_codec_write(codec, 0x15, 0, 0xd00, 0xff);
+
+	chipio_write(codec, 0x18b0a4, 0x000000c2);
+
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_LOW, 0x1E);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_ADDRESS_HIGH, 0x1C);
+	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
+			    VENDOR_CHIPIO_8051_DATA_WRITE, 0x5B);
+
+	snd_hda_codec_write(codec, 0x11, 0,
+			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x44);
+}
+
 static void r3di_pre_dsp_setup(struct hda_codec *codec)
 {
 	chipio_write(codec, 0x18b0a4, 0x000000c2);
@@ -7162,13 +7180,12 @@ static void r3di_pre_dsp_setup(struct hda_codec *codec)
 			AC_VERB_SET_PIN_WIDGET_CONTROL, 0x04);
 }
 
-
 /*
  * These are sent before the DSP is downloaded. Not sure
  * what they do, or if they're necessary. Could possibly
  * be removed. Figure they're better to leave in.
  */
-static void sbz_region2_startup(struct hda_codec *codec)
+static void ca0132_mmio_init(struct hda_codec *codec)
 {
 	struct ca0132_spec *spec = codec->spec;
 
@@ -7208,7 +7225,7 @@ static void ca0132_alt_init(struct hda_codec *codec)
 		ca0132_gpio_init(codec);
 		sbz_pre_dsp_setup(codec);
 		snd_hda_sequence_write(codec, spec->chip_init_verbs);
-		snd_hda_sequence_write(codec, spec->sbz_init_verbs);
+		snd_hda_sequence_write(codec, spec->desktop_init_verbs);
 		break;
 	case QUIRK_R3DI:
 		codec_dbg(codec, "R3DI alt_init");
@@ -7219,6 +7236,11 @@ static void ca0132_alt_init(struct hda_codec *codec)
 		snd_hda_sequence_write(codec, spec->chip_init_verbs);
 		snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0, 0x6FF, 0xC4);
 		break;
+	case QUIRK_R3D:
+		r3d_pre_dsp_setup(codec);
+		snd_hda_sequence_write(codec, spec->chip_init_verbs);
+		snd_hda_sequence_write(codec, spec->desktop_init_verbs);
+		break;
 	}
 }
 
@@ -7255,8 +7277,8 @@ static int ca0132_init(struct hda_codec *codec)
 		spec->dsp_state = DSP_DOWNLOAD_INIT;
 	spec->curr_chip_addx = INVALID_CHIP_ADDRESS;
 
-	if (spec->quirk == QUIRK_SBZ)
-		sbz_region2_startup(codec);
+	if (spec->use_pci_mmio)
+		ca0132_mmio_init(codec);
 
 	snd_hda_power_up_pm(codec);
 
@@ -7507,8 +7529,8 @@ static int ca0132_prepare_verbs(struct hda_codec *codec)
 	struct ca0132_spec *spec = codec->spec;
 
 	spec->chip_init_verbs = ca0132_init_verbs0;
-	if (spec->quirk == QUIRK_SBZ)
-		spec->sbz_init_verbs = sbz_init_verbs;
+	if (spec->quirk == QUIRK_SBZ || spec->quirk == QUIRK_R3D)
+		spec->desktop_init_verbs = ca0132_init_verbs1;
 	spec->spec_init_verbs = kcalloc(NUM_SPEC_VERBS,
 					sizeof(struct hda_verb),
 					GFP_KERNEL);
@@ -7585,6 +7607,7 @@ static int patch_ca0132(struct hda_codec *codec)
 	/* Setup whether or not to use alt functions/controls/pci_mmio */
 	switch (spec->quirk) {
 	case QUIRK_SBZ:
+	case QUIRK_R3D:
 		spec->use_alt_controls = true;
 		spec->use_alt_functions = true;
 		spec->use_pci_mmio = true;
-- 
cgit v1.2.3


From c986f50ca974397f8726bf6776ad8938d6808848 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:19 -0400
Subject: ALSA: hda/ca0132 - Add DSP setup defaults for Recon3D

The Recon3D can use many of the same functions as the Recon3Di, so many
of the r3di prefix function remain the same, but change their names to
the more generic r3d prefix. This patch does this, and adds quirk checks
for things specific to the Recon3Di.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index c938298cb103..8edd7675fb77 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -6223,10 +6223,10 @@ static void ca0132_refresh_widget_caps(struct hda_codec *codec)
 }
 
 /*
- * Recon3Di r3di_setup_defaults sub functions.
+ * Recon3D r3d_setup_defaults sub functions.
  */
 
-static void r3di_dsp_scp_startup(struct hda_codec *codec)
+static void r3d_dsp_scp_startup(struct hda_codec *codec)
 {
 	unsigned int tmp;
 
@@ -6247,7 +6247,7 @@ static void r3di_dsp_scp_startup(struct hda_codec *codec)
 
 }
 
-static void r3di_dsp_initial_mic_setup(struct hda_codec *codec)
+static void r3d_dsp_initial_mic_setup(struct hda_codec *codec)
 {
 	unsigned int tmp;
 
@@ -6457,10 +6457,10 @@ static void ca0132_setup_defaults(struct hda_codec *codec)
 }
 
 /*
- * Setup default parameters for Recon3Di DSP.
+ * Setup default parameters for Recon3D/Recon3Di DSP.
  */
 
-static void r3di_setup_defaults(struct hda_codec *codec)
+static void r3d_setup_defaults(struct hda_codec *codec)
 {
 	struct ca0132_spec *spec = codec->spec;
 	unsigned int tmp;
@@ -6470,9 +6470,9 @@ static void r3di_setup_defaults(struct hda_codec *codec)
 	if (spec->dsp_state != DSP_DOWNLOADED)
 		return;
 
-	r3di_dsp_scp_startup(codec);
+	r3d_dsp_scp_startup(codec);
 
-	r3di_dsp_initial_mic_setup(codec);
+	r3d_dsp_initial_mic_setup(codec);
 
 	/*remove DSP headroom*/
 	tmp = FLOAT_ZERO;
@@ -6486,7 +6486,8 @@ static void r3di_setup_defaults(struct hda_codec *codec)
 	/* Set speaker source? */
 	dspio_set_uint_param(codec, 0x32, 0x00, tmp);
 
-	r3di_gpio_dsp_status_set(codec, R3DI_DSP_DOWNLOADED);
+	if (spec->quirk == QUIRK_R3DI)
+		r3di_gpio_dsp_status_set(codec, R3DI_DSP_DOWNLOADED);
 
 	/* Setup effect defaults */
 	num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT + 1;
@@ -6498,7 +6499,6 @@ static void r3di_setup_defaults(struct hda_codec *codec)
 					ca0132_effects[idx].def_vals[i]);
 		}
 	}
-
 }
 
 /*
@@ -7297,7 +7297,8 @@ static int ca0132_init(struct hda_codec *codec)
 
 	switch (spec->quirk) {
 	case QUIRK_R3DI:
-		r3di_setup_defaults(codec);
+	case QUIRK_R3D:
+		r3d_setup_defaults(codec);
 		break;
 	case QUIRK_SBZ:
 		sbz_setup_defaults(codec);
-- 
cgit v1.2.3


From 42aa3a169062c48e5cbb1f3a6523f8b7c892b699 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:20 -0400
Subject: ALSA: hda/ca0132 - Add Recon3D input and output select commands

This patch adds commands to the alternative input and output select
commands to support the Recon3D.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 8edd7675fb77..d46695e133c0 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -3993,6 +3993,10 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 			chipio_set_control_param(codec, 0x0D, 0x24);
 			r3di_gpio_out_set(codec, R3DI_LINE_OUT);
 			break;
+		case QUIRK_R3D:
+			chipio_set_control_param(codec, 0x0D, 0x24);
+			ca0132_mmio_gpio_set(codec, 1, true);
+			break;
 		}
 
 		/* disable headphone node */
@@ -4029,6 +4033,10 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 			chipio_set_control_param(codec, 0x0D, 0x21);
 			r3di_gpio_out_set(codec, R3DI_HEADPHONE_OUT);
 			break;
+		case QUIRK_R3D:
+			chipio_set_control_param(codec, 0x0D, 0x21);
+			ca0132_mmio_gpio_set(codec, 0x1, false);
+			break;
 		}
 
 		snd_hda_codec_write(codec, spec->out_pins[0], 0,
@@ -4071,6 +4079,10 @@ static int ca0132_alt_select_out(struct hda_codec *codec)
 			chipio_set_control_param(codec, 0x0D, 0x24);
 			r3di_gpio_out_set(codec, R3DI_LINE_OUT);
 			break;
+		case QUIRK_R3D:
+			ca0132_mmio_gpio_set(codec, 1, true);
+			chipio_set_control_param(codec, 0x0D, 0x24);
+			break;
 		}
 		/* enable line out node */
 		pin_ctl = snd_hda_codec_read(codec, spec->out_pins[0], 0,
@@ -4328,6 +4340,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 	case REAR_MIC:
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
+		case QUIRK_R3D:
 			ca0132_mmio_gpio_set(codec, 0, false);
 			tmp = FLOAT_THREE;
 			break;
@@ -4360,6 +4373,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 		ca0132_mic_boost_set(codec, 0);
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
+		case QUIRK_R3D:
 			ca0132_mmio_gpio_set(codec, 0, false);
 			break;
 		case QUIRK_R3DI:
@@ -4386,6 +4400,7 @@ static int ca0132_alt_select_in(struct hda_codec *codec)
 	case FRONT_MIC:
 		switch (spec->quirk) {
 		case QUIRK_SBZ:
+		case QUIRK_R3D:
 			ca0132_mmio_gpio_set(codec, 0, true);
 			ca0132_mmio_gpio_set(codec, 5, false);
 			tmp = FLOAT_THREE;
-- 
cgit v1.2.3


From e25e3445049c353223752fd1bacead9d413b0a5a Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:21 -0400
Subject: ALSA: hda/ca0132 - Change mixer controls for Recon3D

This patch adds changes to setup the Recon3D's mixer controls.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index d46695e133c0..601efaa5c610 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -5780,11 +5780,11 @@ static const struct snd_kcontrol_new ca0132_mixer[] = {
 };
 
 /*
- * SBZ specific control mixer. Removes auto-detect for mic, and adds surround
- * controls. Also sets both the Front Playback and Capture Volume controls to
- * alt so they set the DSP's decibel level.
+ * Desktop specific control mixer. Removes auto-detect for mic, and adds
+ * surround controls. Also sets both the Front Playback and Capture Volume
+ * controls to alt so they set the DSP's decibel level.
  */
-static const struct snd_kcontrol_new sbz_mixer[] = {
+static const struct snd_kcontrol_new desktop_mixer[] = {
 	CA0132_ALT_CODEC_VOL("Front Playback Volume", 0x02, HDA_OUTPUT),
 	CA0132_CODEC_MUTE("Front Playback Switch", VNID_SPK, HDA_OUTPUT),
 	HDA_CODEC_VOLUME("Surround Playback Volume", 0x04, 0, HDA_OUTPUT),
@@ -5855,8 +5855,8 @@ static int ca0132_build_controls(struct hda_codec *codec)
 	 */
 	num_fx = OUT_EFFECTS_COUNT + IN_EFFECTS_COUNT;
 	for (i = 0; i < num_fx; i++) {
-		/* SBZ breaks if Echo Cancellation is used */
-		if (spec->quirk == QUIRK_SBZ) {
+		/* SBZ and R3D break if Echo Cancellation is used. */
+		if (spec->quirk == QUIRK_SBZ || spec->quirk == QUIRK_R3D) {
 			if (i == (ECHO_CANCELLATION - IN_EFFECT_START_NID +
 						OUT_EFFECTS_COUNT))
 				continue;
@@ -7608,9 +7608,13 @@ static int patch_ca0132(struct hda_codec *codec)
 	/* Set which mixers each quirk uses. */
 	switch (spec->quirk) {
 	case QUIRK_SBZ:
-		spec->mixers[0] = sbz_mixer;
+		spec->mixers[0] = desktop_mixer;
 		snd_hda_codec_set_name(codec, "Sound Blaster Z");
 		break;
+	case QUIRK_R3D:
+		spec->mixers[0] = desktop_mixer;
+		snd_hda_codec_set_name(codec, "Recon3D");
+		break;
 	case QUIRK_R3DI:
 		spec->mixers[0] = r3di_mixer;
 		snd_hda_codec_set_name(codec, "Recon3Di");
-- 
cgit v1.2.3


From 2f295f91b740f0055735a7528f8f4cf8b3111239 Mon Sep 17 00:00:00 2001
From: Connor McAdams <conmanx360@gmail.com>
Date: Wed, 8 Aug 2018 13:34:22 -0400
Subject: ALSA: hda/ca0132 - Add exit commands for Recon3D

This patch adds exit functions for the Recon3D, and cleans up the
current exit function.

Signed-off-by: Connor McAdams <conmanx360@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_ca0132.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/sound/pci/hda/patch_ca0132.c b/sound/pci/hda/patch_ca0132.c
index 601efaa5c610..0166a3d7cd55 100644
--- a/sound/pci/hda/patch_ca0132.c
+++ b/sound/pci/hda/patch_ca0132.c
@@ -6968,7 +6968,7 @@ static void sbz_set_pin_ctl_default(struct hda_codec *codec)
 				AC_VERB_SET_PIN_WIDGET_CONTROL, 0x00);
 }
 
-static void sbz_clear_unsolicited(struct hda_codec *codec)
+static void ca0132_clear_unsolicited(struct hda_codec *codec)
 {
 	hda_nid_t pins[7] = {0x0B, 0x0E, 0x0F, 0x10, 0x11, 0x12, 0x13};
 	unsigned int i;
@@ -7021,21 +7021,22 @@ static void sbz_exit_chip(struct hda_codec *codec)
 
 	chipio_set_control_param(codec, 0x0D, 0x24);
 
-	sbz_clear_unsolicited(codec);
+	ca0132_clear_unsolicited(codec);
 	sbz_set_pin_ctl_default(codec);
 
 	snd_hda_codec_write(codec, 0x0B, 0,
 		AC_VERB_SET_EAPD_BTLENABLE, 0x00);
 
-	if (dspload_is_loaded(codec))
-		dsp_reset(codec);
-
-	snd_hda_codec_write(codec, WIDGET_CHIP_CTRL, 0,
-		VENDOR_CHIPIO_CT_EXTENSIONS_ENABLE, 0x00);
-
 	sbz_region2_exit(codec);
 }
 
+static void r3d_exit_chip(struct hda_codec *codec)
+{
+	ca0132_clear_unsolicited(codec);
+	snd_hda_codec_write(codec, 0x01, 0, 0x793, 0x00);
+	snd_hda_codec_write(codec, 0x01, 0, 0x794, 0x5b);
+}
+
 static void ca0132_exit_chip(struct hda_codec *codec)
 {
 	/* put any chip cleanup stuffs here. */
@@ -7381,16 +7382,17 @@ static void ca0132_free(struct hda_codec *codec)
 	case QUIRK_SBZ:
 		sbz_exit_chip(codec);
 		break;
+	case QUIRK_R3D:
+		r3d_exit_chip(codec);
+		break;
 	case QUIRK_R3DI:
 		r3di_gpio_shutdown(codec);
-		snd_hda_sequence_write(codec, spec->base_exit_verbs);
-		ca0132_exit_chip(codec);
-		break;
-	default:
-		snd_hda_sequence_write(codec, spec->base_exit_verbs);
-		ca0132_exit_chip(codec);
 		break;
 	}
+
+	snd_hda_sequence_write(codec, spec->base_exit_verbs);
+	ca0132_exit_chip(codec);
+
 	snd_hda_power_down(codec);
 	if (spec->mem_base)
 		iounmap(spec->mem_base);
-- 
cgit v1.2.3


From 0c93c5ce107659069d16fa34ddce465acdf9d996 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 8 Aug 2018 14:25:16 -0500
Subject: ALSA: opl3: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 114878 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/drivers/opl3/opl3_midi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/drivers/opl3/opl3_midi.c b/sound/drivers/opl3/opl3_midi.c
index 471916ca0b6b..a33cb744e96c 100644
--- a/sound/drivers/opl3/opl3_midi.c
+++ b/sound/drivers/opl3/opl3_midi.c
@@ -368,6 +368,7 @@ void snd_opl3_note_on(void *p, int note, int vel, struct snd_midi_channel *chan)
 			instr_4op = 1;
 			break;
 		}
+		/* fall through */
 	default:
 		spin_unlock_irqrestore(&opl3->voice_lock, flags);
 		return;
-- 
cgit v1.2.3


From 1063711b57393c1999248cccb57bebfaf16739e7 Mon Sep 17 00:00:00 2001
From: Andi Kleen <ak@linux.intel.com>
Date: Tue, 7 Aug 2018 15:09:38 -0700
Subject: x86/mm/kmmio: Make the tracer robust against L1TF

The mmio tracer sets io mapping PTEs and PMDs to non present when enabled
without inverting the address bits, which makes the PTE entry vulnerable
for L1TF.

Make it use the right low level macros to actually invert the address bits
to protect against L1TF.

In principle this could be avoided because MMIO tracing is not likely to be
enabled on production machines, but the fix is straigt forward and for
consistency sake it's better to get rid of the open coded PTE manipulation.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/mm/kmmio.c | 25 +++++++++++++++----------
 1 file changed, 15 insertions(+), 10 deletions(-)

diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 7c8686709636..79eb55ce69a9 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -126,24 +126,29 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long addr)
 
 static void clear_pmd_presence(pmd_t *pmd, bool clear, pmdval_t *old)
 {
+	pmd_t new_pmd;
 	pmdval_t v = pmd_val(*pmd);
 	if (clear) {
-		*old = v & _PAGE_PRESENT;
-		v &= ~_PAGE_PRESENT;
-	} else	/* presume this has been called with clear==true previously */
-		v |= *old;
-	set_pmd(pmd, __pmd(v));
+		*old = v;
+		new_pmd = pmd_mknotpresent(*pmd);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		new_pmd = __pmd(*old);
+	}
+	set_pmd(pmd, new_pmd);
 }
 
 static void clear_pte_presence(pte_t *pte, bool clear, pteval_t *old)
 {
 	pteval_t v = pte_val(*pte);
 	if (clear) {
-		*old = v & _PAGE_PRESENT;
-		v &= ~_PAGE_PRESENT;
-	} else	/* presume this has been called with clear==true previously */
-		v |= *old;
-	set_pte_atomic(pte, __pte(v));
+		*old = v;
+		/* Nothing should care about address */
+		pte_clear(&init_mm, 0, pte);
+	} else {
+		/* Presume this has been called with clear==true previously */
+		set_pte_atomic(pte, __pte(*old));
+	}
 }
 
 static int clear_page_presence(struct kmmio_fault_page *f, bool clear)
-- 
cgit v1.2.3


From 8eb4ecfab03d21146e144b0693ce96839d58202d Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 1 Aug 2018 09:26:16 +1000
Subject: cifs: add SMB2_close_init()/SMB2_close_free()

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.com>
---
 fs/cifs/smb2pdu.c   | 48 ++++++++++++++++++++++++++++++++++--------------
 fs/cifs/smb2proto.h |  3 +++
 2 files changed, 37 insertions(+), 14 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 7c0b30321d9a..78c7190f2295 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2444,44 +2444,63 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
+int
+SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		u64 persistent_fid, u64 volatile_fid)
+{
+	struct smb2_close_req *req;
+	struct kvec *iov = rqst->rq_iov;
+	unsigned int total_len;
+	int rc;
+
+	rc = smb2_plain_req_init(SMB2_CLOSE, tcon, (void **) &req, &total_len);
+	if (rc)
+		return rc;
+
+	req->PersistentFileId = persistent_fid;
+	req->VolatileFileId = volatile_fid;
+	iov[0].iov_base = (char *)req;
+	iov[0].iov_len = total_len;
+
+	return 0;
+}
+
+void
+SMB2_close_free(struct smb_rqst *rqst)
+{
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+}
+
 int
 SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 		 u64 persistent_fid, u64 volatile_fid, int flags)
 {
 	struct smb_rqst rqst;
-	struct smb2_close_req *req;
-	struct smb2_close_rsp *rsp;
+	struct smb2_close_rsp *rsp = NULL;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[1];
 	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
-	unsigned int total_len;
 
 	cifs_dbg(FYI, "Close\n");
 
 	if (!ses || !(ses->server))
 		return -EIO;
 
-	rc = smb2_plain_req_init(SMB2_CLOSE, tcon, (void **) &req, &total_len);
-	if (rc)
-		return rc;
-
 	if (smb3_encryption_required(tcon))
 		flags |= CIFS_TRANSFORM_REQ;
 
-	req->PersistentFileId = persistent_fid;
-	req->VolatileFileId = volatile_fid;
-
-	iov[0].iov_base = (char *)req;
-	iov[0].iov_len = total_len;
-
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	rc = SMB2_close_init(tcon, &rqst, persistent_fid, volatile_fid);
+	if (rc)
+		goto close_exit;
+
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
@@ -2494,6 +2513,7 @@ SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 	/* BB FIXME - decode close response, update inode for caching */
 
 close_exit:
+	SMB2_close_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 19aa483395c7..fdd8c78648c6 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -141,6 +141,9 @@ extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_close_flags(const unsigned int xid, struct cifs_tcon *tcon,
 			    u64 persistent_fid, u64 volatile_fid, int flags);
+extern int SMB2_close_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		      u64 persistent_file_id, u64 volatile_file_id);
+extern void SMB2_close_free(struct smb_rqst *rqst);
 extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
 extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
-- 
cgit v1.2.3


From 296ecbae7fdf209b1e0fb08b8bd82e5e9b637439 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 1 Aug 2018 09:26:17 +1000
Subject: cifs: add SMB2_query_info_[init|free]()

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.com>
---
 fs/cifs/smb2pdu.c   | 68 ++++++++++++++++++++++++++++++++++++-----------------
 fs/cifs/smb2proto.h |  5 ++++
 2 files changed, 51 insertions(+), 22 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 78c7190f2295..821f21d4ada7 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2580,36 +2580,22 @@ validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
 	return 0;
 }
 
-static int
-query_info(const unsigned int xid, struct cifs_tcon *tcon,
-	   u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type,
-	   u32 additional_info, size_t output_len, size_t min_len, void **data,
-		u32 *dlen)
+int
+SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+		     u64 persistent_fid, u64 volatile_fid,
+		     u8 info_class, u8 info_type, u32 additional_info,
+		     size_t output_len)
 {
-	struct smb_rqst rqst;
 	struct smb2_query_info_req *req;
-	struct smb2_query_info_rsp *rsp = NULL;
-	struct kvec iov[2];
-	struct kvec rsp_iov;
-	int rc = 0;
-	int resp_buftype;
-	struct cifs_ses *ses = tcon->ses;
-	int flags = 0;
+	struct kvec *iov = rqst->rq_iov;
 	unsigned int total_len;
-
-	cifs_dbg(FYI, "Query Info\n");
-
-	if (!ses || !(ses->server))
-		return -EIO;
+	int rc;
 
 	rc = smb2_plain_req_init(SMB2_QUERY_INFO, tcon, (void **) &req,
 			     &total_len);
 	if (rc)
 		return rc;
 
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
-
 	req->InfoType = info_type;
 	req->FileInfoClass = info_class;
 	req->PersistentFileId = persistent_fid;
@@ -2626,13 +2612,50 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	iov[0].iov_base = (char *)req;
 	/* 1 for Buffer */
 	iov[0].iov_len = total_len - 1;
+	return 0;
+}
+
+void
+SMB2_query_info_free(struct smb_rqst *rqst)
+{
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base); /* request */
+}
+
+static int
+query_info(const unsigned int xid, struct cifs_tcon *tcon,
+	   u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type,
+	   u32 additional_info, size_t output_len, size_t min_len, void **data,
+		u32 *dlen)
+{
+	struct smb_rqst rqst;
+	struct smb2_query_info_rsp *rsp = NULL;
+	struct kvec iov[1];
+	struct kvec rsp_iov;
+	int rc = 0;
+	int resp_buftype;
+	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
+
+	cifs_dbg(FYI, "Query Info\n");
+
+	if (!ses || !(ses->server))
+		return -EIO;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
 	rqst.rq_nvec = 1;
 
+	rc = SMB2_query_info_init(tcon, &rqst, persistent_fid, volatile_fid,
+				  info_class, info_type, additional_info,
+				  output_len);
+	if (rc)
+		goto qinf_exit;
+
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
@@ -2661,6 +2684,7 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 				   &rsp_iov, min_len, *data);
 
 qinf_exit:
+	SMB2_query_info_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index fdd8c78648c6..1255cde5133b 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -153,6 +153,11 @@ extern int SMB2_query_eas(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
 			   struct smb2_file_all_info *data);
+extern int SMB2_query_info_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+				u64 persistent_fid, u64 volatile_fid,
+				u8 info_class, u8 info_type,
+				u32 additional_info, size_t output_len);
+extern void SMB2_query_info_free(struct smb_rqst *rqst);
 extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
 			   void **data, unsigned int *plen);
-- 
cgit v1.2.3


From 1eb9fb52040fc6e5656c277b562229f09467c9f8 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 8 Aug 2018 15:07:46 +1000
Subject: cifs: create SMB2_open_init()/SMB2_open_free() helpers.

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/smb2pdu.c   | 145 +++++++++++++++++++++++++++-------------------------
 fs/cifs/smb2proto.h |   4 ++
 2 files changed, 78 insertions(+), 71 deletions(-)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 821f21d4ada7..a5009a1c9bce 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -2052,43 +2052,27 @@ err_free_path:
 }
 
 int
-SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
-	  __u8 *oplock, struct smb2_file_all_info *buf,
-	  struct kvec *err_iov, int *buftype)
+SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock,
+	       struct cifs_open_parms *oparms, __le16 *path)
 {
-	struct smb_rqst rqst;
+	struct TCP_Server_Info *server = tcon->ses->server;
 	struct smb2_create_req *req;
-	struct smb2_create_rsp *rsp;
-	struct TCP_Server_Info *server;
-	struct cifs_tcon *tcon = oparms->tcon;
-	struct cifs_ses *ses = tcon->ses;
-	struct kvec iov[5]; /* make sure at least one for each open context */
-	struct kvec rsp_iov = {NULL, 0};
-	int resp_buftype;
-	int uni_path_len;
-	__le16 *copy_path = NULL;
-	int copy_size;
-	int rc = 0;
 	unsigned int n_iov = 2;
 	__u32 file_attributes = 0;
-	char *dhc_buf = NULL, *lc_buf = NULL, *pc_buf = NULL;
-	int flags = 0;
+	int copy_size;
+	int uni_path_len;
 	unsigned int total_len;
-
-	cifs_dbg(FYI, "create/open\n");
-
-	if (ses && (ses->server))
-		server = ses->server;
-	else
-		return -EIO;
+	struct kvec *iov = rqst->rq_iov;
+	__le16 *copy_path;
+	int rc;
 
 	rc = smb2_plain_req_init(SMB2_CREATE, tcon, (void **) &req, &total_len);
-
 	if (rc)
 		return rc;
 
-	if (smb3_encryption_required(tcon))
-		flags |= CIFS_TRANSFORM_REQ;
+	iov[0].iov_base = (char *)req;
+	/* -1 since last byte is buf[0] which is sent below (path) */
+	iov[0].iov_len = total_len - 1;
 
 	if (oparms->create_options & CREATE_OPTION_READONLY)
 		file_attributes |= ATTR_READONLY;
@@ -2102,11 +2086,6 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	req->ShareAccess = FILE_SHARE_ALL_LE;
 	req->CreateDisposition = cpu_to_le32(oparms->disposition);
 	req->CreateOptions = cpu_to_le32(oparms->create_options & CREATE_OPTIONS_MASK);
-
-	iov[0].iov_base = (char *)req;
-	/* -1 since last byte is buf[0] which is sent below (path) */
-	iov[0].iov_len = total_len - 1;
-
 	req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req));
 
 	/* [MS-SMB2] 2.2.13 NameOffset:
@@ -2124,10 +2103,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
 						 &name_len,
 						 tcon->treeName, path);
-		if (rc) {
-			cifs_small_buf_release(req);
+		if (rc)
 			return rc;
-		}
 		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
 		path = copy_path;
@@ -2135,18 +2112,16 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
 		/* MUST set path len (NameLength) to 0 opening root of share */
 		req->NameLength = cpu_to_le16(uni_path_len - 2);
-		if (uni_path_len % 8 != 0) {
-			copy_size = roundup(uni_path_len, 8);
-			copy_path = kzalloc(copy_size, GFP_KERNEL);
-			if (!copy_path) {
-				cifs_small_buf_release(req);
-				return -ENOMEM;
-			}
-			memcpy((char *)copy_path, (const char *)path,
-			       uni_path_len);
-			uni_path_len = copy_size;
-			path = copy_path;
-		}
+		copy_size = uni_path_len;
+		if (copy_size % 8 != 0)
+			copy_size = roundup(copy_size, 8);
+		copy_path = kzalloc(copy_size, GFP_KERNEL);
+		if (!copy_path)
+			return -ENOMEM;
+		memcpy((char *)copy_path, (const char *)path,
+		       uni_path_len);
+		uni_path_len = copy_size;
+		path = copy_path;
 	}
 
 	iov[1].iov_len = uni_path_len;
@@ -2161,12 +2136,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	else {
 		rc = add_lease_context(server, iov, &n_iov,
 				       oparms->fid->lease_key, oplock);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
+		if (rc)
 			return rc;
-		}
-		lc_buf = iov[n_iov-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
@@ -2180,13 +2151,8 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 
 		rc = add_durable_context(iov, &n_iov, oparms,
 					tcon->use_persistent);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			kfree(lc_buf);
+		if (rc)
 			return rc;
-		}
-		dhc_buf = iov[n_iov-1].iov_base;
 	}
 
 	if (tcon->posix_extensions) {
@@ -2198,23 +2164,63 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 		}
 
 		rc = add_posix_context(iov, &n_iov, oparms->mode);
-		if (rc) {
-			cifs_small_buf_release(req);
-			kfree(copy_path);
-			kfree(lc_buf);
-			kfree(dhc_buf);
+		if (rc)
 			return rc;
-		}
-		pc_buf = iov[n_iov-1].iov_base;
 	}
 
+	rqst->rq_nvec = n_iov;
+	return 0;
+}
+
+/* rq_iov[0] is the request and is released by cifs_small_buf_release().
+ * All other vectors are freed by kfree().
+ */
+void
+SMB2_open_free(struct smb_rqst *rqst)
+{
+	int i;
+
+	cifs_small_buf_release(rqst->rq_iov[0].iov_base);
+	for (i = 1; i < rqst->rq_nvec; i++)
+		kfree(rqst->rq_iov[i].iov_base);
+}
+
+int
+SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
+	  __u8 *oplock, struct smb2_file_all_info *buf,
+	  struct kvec *err_iov, int *buftype)
+{
+	struct smb_rqst rqst;
+	struct smb2_create_rsp *rsp = NULL;
+	struct TCP_Server_Info *server;
+	struct cifs_tcon *tcon = oparms->tcon;
+	struct cifs_ses *ses = tcon->ses;
+	struct kvec iov[5]; /* make sure at least one for each open context */
+	struct kvec rsp_iov = {NULL, 0};
+	int resp_buftype;
+	int rc = 0;
+	int flags = 0;
+
+	cifs_dbg(FYI, "create/open\n");
+	if (ses && (ses->server))
+		server = ses->server;
+	else
+		return -EIO;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	memset(&rqst, 0, sizeof(struct smb_rqst));
+	memset(&iov, 0, sizeof(iov));
 	rqst.rq_iov = iov;
-	rqst.rq_nvec = n_iov;
+	rqst.rq_nvec = 5;
+
+	rc = SMB2_open_init(tcon, &rqst, oplock, oparms, path);
+	if (rc)
+		goto creat_exit;
 
 	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags,
 			    &rsp_iov);
-	cifs_small_buf_release(req);
 	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
@@ -2251,10 +2257,7 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	else
 		*oplock = rsp->OplockLevel;
 creat_exit:
-	kfree(copy_path);
-	kfree(lc_buf);
-	kfree(dhc_buf);
-	kfree(pc_buf);
+	SMB2_open_free(&rqst);
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 1255cde5133b..57bdd2711974 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -133,6 +133,10 @@ extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms,
 		     __le16 *path, __u8 *oplock,
 		     struct smb2_file_all_info *buf,
 		     struct kvec *err_iov, int *resp_buftype);
+extern int SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst,
+			  __u8 *oplock, struct cifs_open_parms *oparms,
+			  __le16 *path);
+extern void SMB2_open_free(struct smb_rqst *rqst);
 extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     u64 persistent_fid, u64 volatile_fid, u32 opcode,
 		     bool is_fsctl, char *in_data, u32 indatalen,
-- 
cgit v1.2.3


From 990528171f0c31bd0dfe3da7f60b02664abbcf34 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 11:47:52 +0100
Subject: scsi: st: remove redundant pointer STbuffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Pointer STbuffer is being assigned but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: variable 'STbuffer' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Kai Mäkisara <kai.makisara@kolumbus.fi>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/st.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c
index 50c66ccc4b41..307df2fa39a3 100644
--- a/drivers/scsi/st.c
+++ b/drivers/scsi/st.c
@@ -828,11 +828,8 @@ static int st_flush_write_buffer(struct scsi_tape * STp)
 static int flush_buffer(struct scsi_tape *STp, int seek_next)
 {
 	int backspace, result;
-	struct st_buffer *STbuffer;
 	struct st_partstat *STps;
 
-	STbuffer = STp->buffer;
-
 	/*
 	 * If there was a bus reset, block further access
 	 * to this device.
-- 
cgit v1.2.3


From 0756c57bce3d26da2592d834d8910b6887021701 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 8 Aug 2018 17:29:09 +0300
Subject: scsi: aic94xx: fix an error code in aic94xx_init()

We accidentally return success instead of -ENOMEM on this error path.

Fixes: 2908d778ab3e ("[SCSI] aic94xx: new driver")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Reviewed-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aic94xx/aic94xx_init.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/aic94xx/aic94xx_init.c b/drivers/scsi/aic94xx/aic94xx_init.c
index 80e5b283fd81..1391e5f35918 100644
--- a/drivers/scsi/aic94xx/aic94xx_init.c
+++ b/drivers/scsi/aic94xx/aic94xx_init.c
@@ -1030,8 +1030,10 @@ static int __init aic94xx_init(void)
 
 	aic94xx_transport_template =
 		sas_domain_attach_transport(&aic94xx_transport_functions);
-	if (!aic94xx_transport_template)
+	if (!aic94xx_transport_template) {
+		err = -ENOMEM;
 		goto out_destroy_caches;
+	}
 
 	err = pci_register_driver(&aic94xx_pci_driver);
 	if (err)
-- 
cgit v1.2.3


From e70183143cc472960bc60dfee1b7bbe1949feffb Mon Sep 17 00:00:00 2001
From: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Date: Thu, 12 Jul 2018 12:53:29 -0400
Subject: scsi: mpt3sas: Fix calltrace observed while running IO & reset

Below kernel BUG was observed while running IOs with host reset (issued
from application),

mpt3sas_cm0: diag reset: SUCCESS
------------[ cut here ]------------
WARNING: CPU: 12 PID: 4336 at drivers/scsi/mpt3sas/mpt3sas_base.c:3282 mpt3sas_base_clear_st+0x3d/0x40 [mpt3sas]
Modules linked in: macsec tcp_diag udp_diag inet_diag unix_diag af_packet_diag netlink_diag binfmt_misc fuse xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun devlink ip6t_rpfilter ipt_REJECT nf_reject_ipv4 ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter sunrpc vfat fat sb_edac intel_powerclamp coretemp intel_rapl iosf_mbi kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd iTCO_wdt iTCO_vendor_support
 dcdbas pcspkr joydev ipmi_ssif ses enclosure sg ipmi_devintf acpi_pad ipmi_msghandler acpi_power_meter mei_me lpc_ich wmi mei shpchp ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic ata_generic pata_acpi uas usb_storage mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix mpt3sas libata crct10dif_pclmul crct10dif_common tg3 crc32c_intel i2c_core raid_class ptp scsi_transport_sas pps_core dm_mirror dm_region_hash dm_log dm_mod
CPU: 12 PID: 4336 Comm: python Kdump: loaded Tainted: G        W      ------------   3.10.0-875.el7.brdc.x86_64 #1
Hardware name: Dell Inc. PowerEdge R820/0YWR73, BIOS 1.5.0 03/08/2013
Call Trace:
 [<ffffffff9cf16583>] dump_stack+0x19/0x1b
 [<ffffffff9c891698>] __warn+0xd8/0x100
 [<ffffffff9c8917dd>] warn_slowpath_null+0x1d/0x20
 [<ffffffffc04f3f4d>] mpt3sas_base_clear_st+0x3d/0x40 [mpt3sas]
 [<ffffffffc05047d2>] _scsih_flush_running_cmds+0x92/0xe0 [mpt3sas]
 [<ffffffffc05095db>] mpt3sas_scsih_reset_handler+0x43b/0xaf0 [mpt3sas]
 [<ffffffff9c894829>] ? vprintk_default+0x29/0x40
 [<ffffffff9cf10531>] ? printk+0x60/0x77
 [<ffffffffc04f06c8>] ? _base_diag_reset+0x238/0x340 [mpt3sas]
 [<ffffffffc04f794d>] mpt3sas_base_hard_reset_handler+0x1ad/0x420 [mpt3sas]
 [<ffffffffc05132b9>] _ctl_ioctl_main.isra.12+0x11b9/0x1200 [mpt3sas]
 [<ffffffffc068d585>] ? xfs_file_aio_write+0x155/0x1b0 [xfs]
 [<ffffffff9ca1a4e3>] ? do_sync_write+0x93/0xe0
 [<ffffffffc051337a>] _ctl_ioctl+0x1a/0x20 [mpt3sas]
 [<ffffffff9ca2fe90>] do_vfs_ioctl+0x350/0x560
 [<ffffffff9ca1dec1>] ? __sb_end_write+0x31/0x60
 [<ffffffff9ca30141>] SyS_ioctl+0xa1/0xc0
 [<ffffffff9cf28715>] ? system_call_after_swapgs+0xa2/0x146
 [<ffffffff9cf287d5>] system_call_fastpath+0x1c/0x21
 [<ffffffff9cf28721>] ? system_call_after_swapgs+0xae/0x146
---[ end trace 5dac5b98d89aaa3c ]---
------------[ cut here ]------------
kernel BUG at block/blk-core.c:1476!
invalid opcode: 0000 [#1] SMP
Modules linked in: macsec tcp_diag udp_diag inet_diag unix_diag af_packet_diag netlink_diag binfmt_misc fuse xt_CHECKSUM ipt_MASQUERADE nf_nat_masquerade_ipv4 tun devlink ip6t_rpfilter ipt_REJECT nf_reject_ipv4 ip6t_REJECT nf_reject_ipv6 xt_conntrack ip_set nfnetlink ebtable_nat ebtable_broute bridge stp llc ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter sunrpc vfat fat sb_edac intel_powerclamp coretemp intel_rapl iosf_mbi kvm_intel kvm irqbypass crc32_pclmul ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd iTCO_wdt iTCO_vendor_support
 dcdbas pcspkr joydev ipmi_ssif ses enclosure sg ipmi_devintf acpi_pad ipmi_msghandler acpi_power_meter mei_me lpc_ich wmi mei shpchp ip_tables xfs libcrc32c sd_mod crc_t10dif crct10dif_generic ata_generic pata_acpi uas usb_storage mgag200 i2c_algo_bit drm_kms_helper syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm ata_piix mpt3sas libata crct10dif_pclmul crct10dif_common tg3 crc32c_intel i2c_core raid_class ptp scsi_transport_sas pps_core dm_mirror dm_region_hash dm_log dm_mod
CPU: 12 PID: 4336 Comm: python Kdump: loaded Tainted: G        W      ------------   3.10.0-875.el7.brdc.x86_64 #1
Hardware name: Dell Inc. PowerEdge R820/0YWR73, BIOS 1.5.0 03/08/2013
task: ffff903fc96e0fd0 ti: ffff903fb1eec000 task.ti: ffff903fb1eec000
RIP: 0010:[<ffffffff9cb19ec0>]  [<ffffffff9cb19ec0>] blk_requeue_request+0x90/0xa0
RSP: 0018:ffff903c6b783dc0  EFLAGS: 00010087
RAX: ffff903bb67026d0 RBX: ffff903b7d6a6140 RCX: dead000000000200
RDX: ffff903bb67026d0 RSI: ffff903bb6702580 RDI: ffff903bb67026d0
RBP: ffff903c6b783dd8 R08: ffff903bb67026d0 R09: ffffd97e80000000
R10: ffff903c658bac00 R11: 0000000000000000 R12: ffff903bb6702580
R13: ffff903fa9a292f0 R14: 0000000000000246 R15: 0000000000001057
FS:  00007f7026f5b740(0000) GS:ffff903c6b780000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f298877c004 CR3: 00000000caf36000 CR4: 00000000000607e0
Call Trace:
 <IRQ>
 [<ffffffff9cca68ff>] __scsi_queue_insert+0xbf/0x110
 [<ffffffff9cca79ca>] scsi_io_completion+0x5da/0x6a0
 [<ffffffff9cc9ca3c>] scsi_finish_command+0xdc/0x140
 [<ffffffff9cca6aa2>] scsi_softirq_done+0x132/0x160
 [<ffffffff9cb240c6>] blk_done_softirq+0x96/0xc0
 [<ffffffff9c89a905>] __do_softirq+0xf5/0x280
 [<ffffffff9cf2bd2c>] call_softirq+0x1c/0x30
 [<ffffffff9c82d625>] do_softirq+0x65/0xa0
 [<ffffffff9c89ac85>] irq_exit+0x105/0x110
 [<ffffffff9cf2d0a8>] smp_apic_timer_interrupt+0x48/0x60
 [<ffffffff9cf297f2>] apic_timer_interrupt+0x162/0x170
 <EOI>
 [<ffffffff9cca5f41>] ? scsi_done+0x21/0x60
 [<ffffffff9cb5ac18>] ? delay_tsc+0x38/0x60
 [<ffffffff9cb5ab5d>] __const_udelay+0x2d/0x30
 [<ffffffffc04effde>] _base_handshake_req_reply_wait+0x8e/0x4a0 [mpt3sas]
 [<ffffffffc04f0b13>] _base_get_ioc_facts+0x123/0x590 [mpt3sas]
 [<ffffffffc04f06c8>] ? _base_diag_reset+0x238/0x340 [mpt3sas]
 [<ffffffffc04f7993>] mpt3sas_base_hard_reset_handler+0x1f3/0x420 [mpt3sas]
 [<ffffffffc05132b9>] _ctl_ioctl_main.isra.12+0x11b9/0x1200 [mpt3sas]
 [<ffffffffc068d585>] ? xfs_file_aio_write+0x155/0x1b0 [xfs]
 [<ffffffff9ca1a4e3>] ? do_sync_write+0x93/0xe0
 [<ffffffffc051337a>] _ctl_ioctl+0x1a/0x20 [mpt3sas]
 [<ffffffff9ca2fe90>] do_vfs_ioctl+0x350/0x560
 [<ffffffff9ca1dec1>] ? __sb_end_write+0x31/0x60
 [<ffffffff9ca30141>] SyS_ioctl+0xa1/0xc0
 [<ffffffff9cf28715>] ? system_call_after_swapgs+0xa2/0x146
 [<ffffffff9cf287d5>] system_call_fastpath+0x1c/0x21
 [<ffffffff9cf28721>] ? system_call_after_swapgs+0xae/0x146
Code: 83 c3 10 4c 89 e2 4c 89 ee e8 8d 21 04 00 48 8b 03 48 85 c0 75 e5 41 f6 44 24 4a 10 74 ad 4c 89 e6 4c 89 ef e8 b2 42 00 00 eb a0 <0f> 0b 0f 1f 40 00 66 2e 0f 1f 84 00 00 00 00 00 66 66 66 66 90
RIP  [<ffffffff9cb19ec0>] blk_requeue_request+0x90/0xa0
 RSP <ffff903c6b783dc0>

As a part of host reset operation, driver will flushout all IOs outstanding
at driver level with "DID_RESET" result.  To find which are all commands
outstanding at the driver level, driver loops with smid starting from one
to HBA queue depth and calls mpt3sas_scsih_scsi_lookup_get() to get scmd as
shown below

 for (smid = 1; smid <= ioc->scsiio_depth; smid++) {
                scmd = mpt3sas_scsih_scsi_lookup_get(ioc, smid);
                if (!scmd)
                        continue;

But in mpt3sas_scsih_scsi_lookup_get() function, driver returns some scsi
cmnds which are not outstanding at the driver level (possibly request is
constructed at block layer since QUEUE_FLAG_QUIESCED is not set. Even if
driver uses scsi_block_requests and scsi_unblock_requests, issue still
persists as they will be just blocking further IO from scsi layer and not
from block layer) and these commands are flushed with DID_RESET host bytes
thus resulting into above kernel BUG.

This issue got introduced by commit dbec4c9040ed ("scsi: mpt3sas: lockless
command submission").

To fix this issue, we have modified the mpt3sas_scsih_scsi_lookup_get() to
check for smid equals to zero (note: whenever any scsi cmnd is processing
at the driver level then smid for that scsi cmnd will be non-zero, always
it starts from one) before it returns the scmd pointer to the caller. If
smid is zero then this function returns scmd pointer as NULL and driver
won't flushout those scsi cmnds at driver level with DID_RESET host byte
thus this issue will not be observed.

[mkp: amended with updated fix from Sreekanth]

Signed-off-by: Sreekanth Reddy <sreekanth.reddy@broadcom.com>
Fixes: dbec4c9040ed ("scsi: mpt3sas: lockless command submission")
Cc: stable@vger.kernel.org # v4.16+
Reviewed-by: Tomas Henzl <thenzl@redhat.com>
Reviewed-by: Bart Van Assche <bart.vanassche@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/mpt3sas/mpt3sas_base.c  | 1 +
 drivers/scsi/mpt3sas/mpt3sas_scsih.c | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
index 17b6b0a3455f..836b2e14e3b7 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
@@ -3264,6 +3264,7 @@ void mpt3sas_base_clear_st(struct MPT3SAS_ADAPTER *ioc,
 	st->cb_idx = 0xFF;
 	st->direct_io = 0;
 	atomic_set(&ioc->chain_lookup[st->smid - 1].chain_offset, 0);
+	st->smid = 0;
 }
 
 /**
diff --git a/drivers/scsi/mpt3sas/mpt3sas_scsih.c b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
index 061736f8025b..8dd3d6720217 100644
--- a/drivers/scsi/mpt3sas/mpt3sas_scsih.c
+++ b/drivers/scsi/mpt3sas/mpt3sas_scsih.c
@@ -1482,7 +1482,7 @@ mpt3sas_scsih_scsi_lookup_get(struct MPT3SAS_ADAPTER *ioc, u16 smid)
 		scmd = scsi_host_find_tag(ioc->shost, unique_tag);
 		if (scmd) {
 			st = scsi_cmd_priv(scmd);
-			if (st->cb_idx == 0xFF)
+			if (st->cb_idx == 0xFF || st->smid == 0)
 				scmd = NULL;
 		}
 	}
-- 
cgit v1.2.3


From d98e000cc79e740f0c9e2dee59cd4b12a2f11a52 Mon Sep 17 00:00:00 2001
From: Dongliang Mu <mudongliangabcd@gmail.com>
Date: Tue, 7 Aug 2018 01:14:29 -0400
Subject: scsi: aacraid: Spelling fix in comment

requesed -> requested

Signed-off-by: Dongliang Mu <mudongliangabcd@gmail.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/aacraid/commsup.c | 2 +-
 drivers/scsi/aacraid/dpcsup.c  | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c
index d62ddd63f4fe..6e1b022a823d 100644
--- a/drivers/scsi/aacraid/commsup.c
+++ b/drivers/scsi/aacraid/commsup.c
@@ -514,7 +514,7 @@ int aac_fib_send(u16 command, struct fib *fibptr, unsigned long size,
 	 *	The only invalid cases are if the caller requests to wait and
 	 *	does not request a response and if the caller does not want a
 	 *	response and the Fib is not allocated from pool. If a response
-	 *	is not requesed the Fib will just be deallocaed by the DPC
+	 *	is not requested the Fib will just be deallocaed by the DPC
 	 *	routine when the response comes back from the adapter. No
 	 *	further processing will be done besides deleting the Fib. We
 	 *	will have a debug mode where the adapter can notify the host
diff --git a/drivers/scsi/aacraid/dpcsup.c b/drivers/scsi/aacraid/dpcsup.c
index 417ba349e10e..ddc69738375f 100644
--- a/drivers/scsi/aacraid/dpcsup.c
+++ b/drivers/scsi/aacraid/dpcsup.c
@@ -65,7 +65,7 @@ unsigned int aac_response_normal(struct aac_queue * q)
 	/*
 	 *	Keep pulling response QEs off the response queue and waking
 	 *	up the waiters until there are no more QEs. We then return
-	 *	back to the system. If no response was requesed we just
+	 *	back to the system. If no response was requested we just
 	 *	deallocate the Fib here and continue.
 	 */
 	while(aac_consumer_get(dev, q, &entry))
-- 
cgit v1.2.3


From 1c9f4a3fce770f194647dd1441502dd5b84ca883 Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Tue, 7 Aug 2018 19:32:49 -0400
Subject: ieee802154: hwsim: fix rcu handling

This patch adds missing rcu_assign_pointer()/rcu_dereference() to used rcu
pointers. There was already a previous commit c5d99d2b35da ("ieee802154:
hwsim: fix rcu address annotation"), but there was more which was
pointed out on my side by using newest sparse version.

Cc: Stefan Schmidt <stefan@datenfreihafen.org>
Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb")
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/mac802154_hwsim.c | 24 +++++++++++++++++++-----
 1 file changed, 19 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index f4e92054f7df..53f39435321e 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/timer.h>
 #include <linux/platform_device.h>
+#include <linux/rtnetlink.h>
 #include <linux/netdevice.h>
 #include <linux/device.h>
 #include <linux/spinlock.h>
@@ -110,7 +111,7 @@ static int hwsim_hw_channel(struct ieee802154_hw *hw, u8 page, u8 channel)
 	pib->page = page;
 	pib->channel = channel;
 
-	pib_old = phy->pib;
+	pib_old = rtnl_dereference(phy->pib);
 	rcu_assign_pointer(phy->pib, pib);
 	kfree_rcu(pib_old, rcu);
 	return 0;
@@ -406,7 +407,7 @@ static struct hwsim_edge *hwsim_alloc_edge(struct hwsim_phy *endpoint, u8 lqi)
 	}
 
 	einfo->lqi = 0xff;
-	e->info = einfo;
+	rcu_assign_pointer(e->info, einfo);
 	e->endpoint = endpoint;
 
 	return e;
@@ -414,7 +415,13 @@ static struct hwsim_edge *hwsim_alloc_edge(struct hwsim_phy *endpoint, u8 lqi)
 
 static void hwsim_free_edge(struct hwsim_edge *e)
 {
-	kfree_rcu(e->info, rcu);
+	struct hwsim_edge_info *einfo;
+
+	rcu_read_lock();
+	einfo = rcu_dereference(e->info);
+	rcu_read_unlock();
+
+	kfree_rcu(einfo, rcu);
 	kfree_rcu(e, rcu);
 }
 
@@ -796,7 +803,7 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev,
 		goto err_pib;
 	}
 
-	phy->pib = pib;
+	rcu_assign_pointer(phy->pib, pib);
 	phy->idx = idx;
 	INIT_LIST_HEAD(&phy->edges);
 
@@ -829,10 +836,17 @@ err_pib:
 
 static void hwsim_del(struct hwsim_phy *phy)
 {
+	struct hwsim_pib *pib;
+
 	hwsim_edge_unsubscribe_me(phy);
 
 	list_del(&phy->list);
-	kfree_rcu(phy->pib, rcu);
+
+	rcu_read_lock();
+	pib = rcu_dereference(phy->pib);
+	rcu_read_unlock();
+
+	kfree_rcu(pib, rcu);
 
 	ieee802154_unregister_hw(phy->hw);
 	ieee802154_free_hw(phy->hw);
-- 
cgit v1.2.3


From 470770bf841b49fe129876300dfcb74a8bbabe99 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 8 Aug 2018 02:43:46 +0000
Subject: ieee802154: hwsim: fix copy-paste error in hwsim_set_edge_lqi()

The return value from kzalloc() is not checked correctly. The
test is done against a wrong variable. This patch fix it.

Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/mac802154_hwsim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 53f39435321e..9319780a52ca 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -571,7 +571,7 @@ static int hwsim_set_edge_lqi(struct sk_buff *msg, struct genl_info *info)
 	}
 
 	einfo = kzalloc(sizeof(*einfo), GFP_KERNEL);
-	if (!info) {
+	if (!einfo) {
 		mutex_unlock(&hwsim_phys_lock);
 		return -ENOMEM;
 	}
-- 
cgit v1.2.3


From 13403d6952a5adf80d3d5668c290490852b4def2 Mon Sep 17 00:00:00 2001
From: Wei Yongjun <weiyongjun1@huawei.com>
Date: Wed, 8 Aug 2018 03:10:39 +0000
Subject: ieee802154: hwsim: fix missing unlock on error in hwsim_add_one()

Add the missing unlock before return from function hwsim_add_one()
in the error handling case.

Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb")
Signed-off-by: Wei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/mac802154_hwsim.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 9319780a52ca..07a493dea11e 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -817,8 +817,10 @@ static int hwsim_add_one(struct genl_info *info, struct device *dev,
 	mutex_lock(&hwsim_phys_lock);
 	if (init) {
 		err = hwsim_subscribe_all_others(phy);
-		if (err < 0)
+		if (err < 0) {
+			mutex_unlock(&hwsim_phys_lock);
 			goto err_reg;
+		}
 	}
 	list_add_tail(&phy->list, &hwsim_phys);
 	mutex_unlock(&hwsim_phys_lock);
-- 
cgit v1.2.3


From e9f7be0c4316a0ea1c47b1e800baa58fb937096c Mon Sep 17 00:00:00 2001
From: Quinn Tran <quinn.tran@cavium.com>
Date: Tue, 7 Aug 2018 20:39:52 -0700
Subject: scsi: qla2xxx: Fix issue reported by static checker for
 qla2x00_els_dcmd2_sp_done()

This patch fixes following Smatch complaint:

drivers/scsi/qla2xxx/qla_iocb.c:2647 qla2x00_els_dcmd2_sp_done()
error: we previously assumed 'e' could be null (see line 2631)

Fixes: 8777e4314d39 ("scsi: qla2xxx: Migrate NVME N2N handling into state machine")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Quinn Tran <quinn.tran@cavium.com>
Signed-off-by: Himanshu Madhani <himanshu.madhani@cavium.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/qla2xxx/qla_iocb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 059f2c9dc192..213321295753 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -2642,6 +2642,7 @@ qla2x00_els_dcmd2_sp_done(void *ptr, int res)
 				    elsio->u.els_plogi.els_resp_pyld,
 				    elsio->u.els_plogi.els_resp_pyld_dma);
 			sp->free(sp);
+			return;
 		}
 		e->u.iosb.sp = sp;
 		qla2x00_post_work(vha, e);
-- 
cgit v1.2.3


From e7c3b37983c4ed038a3b982aa3dafc76dfa86249 Mon Sep 17 00:00:00 2001
From: Ohad Sharabi <ohad.sharabi@wdc.com>
Date: Sun, 5 Aug 2018 16:26:23 +0300
Subject: scsi: ufs: remove unnecessary query(DM) UPIU trace

This patch removes redundant trace that occurs when sending Device
Management(DM) request (fix behavior in commit 6667e6d91c88 ("scsi:
ufs: add trace event for ufs upiu").

Since the function send_command is called also for DM request, UPIU
trace for DM request is called twice- one identified as query_* the
other as send/complete.

Signed-off-by: Ohad Sharabi <ohad.sharabi@wdc.com>
Fixes: 6667e6d91c88 ("scsi: ufs: add trace event for ufs upiu")
Reviewed-by: Stanislav Nijnikov <stanislav.nijnikov@wdc.com>
Reviewed-by: Avri Altman <avri.altman@wdc.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/ufs/ufshcd.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c
index 3560185002da..9d5d2ca7fc4f 100644
--- a/drivers/scsi/ufs/ufshcd.c
+++ b/drivers/scsi/ufs/ufshcd.c
@@ -342,18 +342,19 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba,
 	sector_t lba = -1;
 	u8 opcode = 0;
 	u32 intr, doorbell;
-	struct ufshcd_lrb *lrbp;
+	struct ufshcd_lrb *lrbp = &hba->lrb[tag];
 	int transfer_len = -1;
 
-	/* trace UPIU also */
-	ufshcd_add_cmd_upiu_trace(hba, tag, str);
-
-	if (!trace_ufshcd_command_enabled())
+	if (!trace_ufshcd_command_enabled()) {
+		/* trace UPIU W/O tracing command */
+		if (lrbp->cmd)
+			ufshcd_add_cmd_upiu_trace(hba, tag, str);
 		return;
-
-	lrbp = &hba->lrb[tag];
+	}
 
 	if (lrbp->cmd) { /* data phase exists */
+		/* trace UPIU also */
+		ufshcd_add_cmd_upiu_trace(hba, tag, str);
 		opcode = (u8)(*lrbp->cmd->cmnd);
 		if ((opcode == READ_10) || (opcode == WRITE_10)) {
 			/*
-- 
cgit v1.2.3


From 51372570ac3c919b036e760f4ca449e81cf8e995 Mon Sep 17 00:00:00 2001
From: Jianchao Wang <jianchao.w.wang@oracle.com>
Date: Wed, 8 Aug 2018 14:24:59 +0800
Subject: scsi: core: use blk_mq_run_hw_queues in scsi_kick_queue

We don't use blk-mq start/stop hw queue any more, so no reason to use
blk_mq_start_hw_queues which does clear_bit, replace it with
blk_mq_run_hw_queues.

Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 93cf2ec2d13b..57201d8bdce4 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -372,7 +372,7 @@ void scsi_device_unbusy(struct scsi_device *sdev)
 static void scsi_kick_queue(struct request_queue *q)
 {
 	if (q->mq_ops)
-		blk_mq_start_hw_queues(q);
+		blk_mq_run_hw_queues(q, false);
 	else
 		blk_run_queue(q);
 }
-- 
cgit v1.2.3


From 342ac8448f1fb213908656ae5581d0f37a5954e8 Mon Sep 17 00:00:00 2001
From: Denis Drozdov <denisd@mellanox.com>
Date: Wed, 8 Aug 2018 16:23:48 -0700
Subject: net/mlx5: Use max_num_eqs for calculation of required MSIX vectors

New firmware has defined new HCA capability field called "max_num_eqs",
that is the number of available EQs after subtracting reserved FW EQs.

Before this capability the FW reported the EQ number in "log_max_eqs",
the reported value also contained FW reserved EQs, but the driver might
be failing to load on 320 cpus systems due to the fact that FW
reserved EQs were not available to the driver.

Now the driver has to obtain max_num_eqs value from new FW to get real
number of EQs available.

Signed-off-by: Denis Drozdov <denisd@mellanox.com>
Reviewed-by: Alex Vesker <valex@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 4 +++-
 include/linux/mlx5/mlx5_ifc.h                  | 5 ++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 03b9c6733eed..cf3e4a659052 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -323,7 +323,9 @@ static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
-	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
+	int num_eqs = MLX5_CAP_GEN(dev, max_num_eqs) ?
+		      MLX5_CAP_GEN(dev, max_num_eqs) :
+		      1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
 	int err;
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 60c2308fe062..63e1ce4c4826 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1133,7 +1133,10 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         general_obj_types[0x40];
 
-	u8         reserved_at_440[0x40];
+	u8         reserved_at_440[0x20];
+
+	u8         reserved_at_460[0x10];
+	u8         max_num_eqs[0x10];
 
 	u8         reserved_at_480[0x3];
 	u8         log_max_l2_table[0x5];
-- 
cgit v1.2.3


From cc9c82a8668cf98748bfbaa83c5c092d5115c25b Mon Sep 17 00:00:00 2001
From: Eran Ben Elisha <eranbe@mellanox.com>
Date: Wed, 8 Aug 2018 16:23:49 -0700
Subject: net/mlx5: Rename modify/query_vport state related enums

Modify and query vport state commands share the same admin_state and
op_mod values, rename the enums to fit them both.

In addition, remove the esw prefix from the admin state enum as this
also applied for vnic.

Signed-off-by: Eran Ben Elisha <eranbe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c     | 12 ++++++------
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c      |  8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c     | 10 +++++-----
 include/linux/mlx5/device.h                           |  6 +++---
 include/linux/mlx5/mlx5_ifc.h                         |  4 ++--
 6 files changed, 21 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a2fb21ca5767..2731ba2d8049 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -228,7 +228,7 @@ static void mlx5e_update_carrier(struct mlx5e_priv *priv)
 	u8 port_state;
 
 	port_state = mlx5_query_vport_state(mdev,
-					    MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT,
+					    MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT,
 					    0);
 
 	if (port_state == VPORT_STATE_UP) {
@@ -3916,9 +3916,9 @@ static int mlx5e_set_vf_rate(struct net_device *dev, int vf, int min_tx_rate,
 static int mlx5_vport_link2ifla(u8 esw_link)
 {
 	switch (esw_link) {
-	case MLX5_ESW_VPORT_ADMIN_STATE_DOWN:
+	case MLX5_VPORT_ADMIN_STATE_DOWN:
 		return IFLA_VF_LINK_STATE_DISABLE;
-	case MLX5_ESW_VPORT_ADMIN_STATE_UP:
+	case MLX5_VPORT_ADMIN_STATE_UP:
 		return IFLA_VF_LINK_STATE_ENABLE;
 	}
 	return IFLA_VF_LINK_STATE_AUTO;
@@ -3928,11 +3928,11 @@ static int mlx5_ifla_link2vport(u8 ifla_link)
 {
 	switch (ifla_link) {
 	case IFLA_VF_LINK_STATE_DISABLE:
-		return MLX5_ESW_VPORT_ADMIN_STATE_DOWN;
+		return MLX5_VPORT_ADMIN_STATE_DOWN;
 	case IFLA_VF_LINK_STATE_ENABLE:
-		return MLX5_ESW_VPORT_ADMIN_STATE_UP;
+		return MLX5_VPORT_ADMIN_STATE_UP;
 	}
-	return MLX5_ESW_VPORT_ADMIN_STATE_AUTO;
+	return MLX5_VPORT_ADMIN_STATE_AUTO;
 }
 
 static int mlx5e_set_vf_link_state(struct net_device *dev, int vf,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 8e3c5b4b90ab..c9cc9747d21d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -698,8 +698,8 @@ static int mlx5e_rep_open(struct net_device *dev)
 		goto unlock;
 
 	if (!mlx5_modify_vport_admin_state(priv->mdev,
-					   MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
-					   rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_UP))
+					   MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
+					   rep->vport, MLX5_VPORT_ADMIN_STATE_UP))
 		netif_carrier_on(dev);
 
 unlock:
@@ -716,8 +716,8 @@ static int mlx5e_rep_close(struct net_device *dev)
 
 	mutex_lock(&priv->state_lock);
 	mlx5_modify_vport_admin_state(priv->mdev,
-				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
-				      rep->vport, MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
+				      rep->vport, MLX5_VPORT_ADMIN_STATE_DOWN);
 	ret = mlx5e_close_locked(dev);
 	mutex_unlock(&priv->state_lock);
 	return ret;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 4d316cc9b008..35ded91203f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -74,7 +74,7 @@ static int mlx5e_test_link_state(struct mlx5e_priv *priv)
 	if (!netif_carrier_ok(priv->netdev))
 		return 1;
 
-	port_state = mlx5_query_vport_state(priv->mdev, MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT, 0);
+	port_state = mlx5_query_vport_state(priv->mdev, MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT, 0);
 	return port_state == VPORT_STATE_UP ? 0 : 1;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index 40dba9e8af92..cd0760a8d45a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -1469,7 +1469,7 @@ static void esw_apply_vport_conf(struct mlx5_eswitch *esw,
 		return;
 
 	mlx5_modify_vport_admin_state(esw->dev,
-				      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+				      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 				      vport_num,
 				      vport->info.link_state);
 	mlx5_modify_nic_vport_mac_address(esw->dev, vport_num, vport->info.mac);
@@ -1582,9 +1582,9 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	esw_vport_disable_qos(esw, vport_num);
 	if (vport_num && esw->mode == SRIOV_LEGACY) {
 		mlx5_modify_vport_admin_state(esw->dev,
-					      MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+					      MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					      vport_num,
-					      MLX5_ESW_VPORT_ADMIN_STATE_DOWN);
+					      MLX5_VPORT_ADMIN_STATE_DOWN);
 		esw_vport_disable_egress_acl(esw, vport);
 		esw_vport_disable_ingress_acl(esw, vport);
 		esw_vport_destroy_drop_counters(vport);
@@ -1736,7 +1736,7 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev)
 		struct mlx5_vport *vport = &esw->vports[vport_num];
 
 		vport->vport = vport_num;
-		vport->info.link_state = MLX5_ESW_VPORT_ADMIN_STATE_AUTO;
+		vport->info.link_state = MLX5_VPORT_ADMIN_STATE_AUTO;
 		vport->dev = dev;
 		INIT_WORK(&vport->vport_change_handler,
 			  esw_vport_change_handler);
@@ -1860,7 +1860,7 @@ int mlx5_eswitch_set_vport_state(struct mlx5_eswitch *esw,
 	evport = &esw->vports[vport];
 
 	err = mlx5_modify_vport_admin_state(esw->dev,
-					    MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT,
+					    MLX5_VPORT_STATE_OP_MOD_ESW_VPORT,
 					    vport, link_state);
 	if (err) {
 		mlx5_core_warn(esw->dev,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index d489494b0a84..11fa4e66afc5 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -946,9 +946,9 @@ enum {
 };
 
 enum {
-	MLX5_ESW_VPORT_ADMIN_STATE_DOWN  = 0x0,
-	MLX5_ESW_VPORT_ADMIN_STATE_UP    = 0x1,
-	MLX5_ESW_VPORT_ADMIN_STATE_AUTO  = 0x2,
+	MLX5_VPORT_ADMIN_STATE_DOWN  = 0x0,
+	MLX5_VPORT_ADMIN_STATE_UP    = 0x1,
+	MLX5_VPORT_ADMIN_STATE_AUTO  = 0x2,
 };
 
 enum {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 63e1ce4c4826..6ead9c1a5396 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -3764,8 +3764,8 @@ struct mlx5_ifc_query_vport_state_out_bits {
 };
 
 enum {
-	MLX5_QUERY_VPORT_STATE_IN_OP_MOD_VNIC_VPORT  = 0x0,
-	MLX5_QUERY_VPORT_STATE_IN_OP_MOD_ESW_VPORT   = 0x1,
+	MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT  = 0x0,
+	MLX5_VPORT_STATE_OP_MOD_ESW_VPORT   = 0x1,
 };
 
 struct mlx5_ifc_query_vport_state_in_bits {
-- 
cgit v1.2.3


From 8e3debc08b9a1a4c049c4e3bd2cfe73614a9a6cb Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 8 Aug 2018 16:23:50 -0700
Subject: net/mlx5: E-Switch, Remove unused argument when creating legacy FDB

Remove unused nvports argument.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/eswitch.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
index cd0760a8d45a..2b252cde5cc2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c
@@ -246,7 +246,7 @@ esw_fdb_set_vport_promisc_rule(struct mlx5_eswitch *esw, u32 vport)
 	return __esw_fdb_set_vport_rule(esw, vport, true, mac_c, mac_v);
 }
 
-static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw, int nvports)
+static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 {
 	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
 	struct mlx5_flow_table_attr ft_attr = {};
@@ -1618,7 +1618,7 @@ int mlx5_eswitch_enable_sriov(struct mlx5_eswitch *esw, int nvfs, int mode)
 	esw->mode = mode;
 
 	if (mode == SRIOV_LEGACY) {
-		err = esw_create_legacy_fdb_table(esw, nvfs + 1);
+		err = esw_create_legacy_fdb_table(esw);
 	} else {
 		mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB);
 
-- 
cgit v1.2.3


From 29d8ebd44de8999e292dbb4de76744d4a41039ec Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 8 Aug 2018 16:23:51 -0700
Subject: net/mlx5: Remove unused mlx5_query_vport_admin_state

mlx5_query_vport_admin_state() is not used anywhere. Remove it.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 10 ----------
 include/linux/mlx5/vport.h                      |  2 --
 2 files changed, 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 7eecd5b07bb1..fa6fa171b94c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -64,16 +64,6 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 }
 EXPORT_SYMBOL_GPL(mlx5_query_vport_state);
 
-u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
-{
-	u32 out[MLX5_ST_SZ_DW(query_vport_state_out)] = {0};
-
-	_mlx5_query_vport_state(mdev, opmod, vport, out, sizeof(out));
-
-	return MLX5_GET(query_vport_state_out, out, admin_state);
-}
-EXPORT_SYMBOL_GPL(mlx5_query_vport_admin_state);
-
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 state)
 {
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 9208cb8809ac..7e7c6dfcfb09 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -43,8 +43,6 @@ enum {
 };
 
 u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport);
-u8 mlx5_query_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
-				u16 vport);
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 state);
 int mlx5_query_nic_vport_mac_address(struct mlx5_core_dev *mdev,
-- 
cgit v1.2.3


From d1fd79f34f2d56f969472d7285ea5239ab7b7bf0 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 8 Aug 2018 16:23:52 -0700
Subject: net/mlx5: Unexport functions that need not be exported

mlx5_query_vport_state() and mlx5_modify_vport_admin_state() are used
only from within mlx5_core  - unexport them.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/vport.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index fa6fa171b94c..b02af317c125 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -62,7 +62,6 @@ u8 mlx5_query_vport_state(struct mlx5_core_dev *mdev, u8 opmod, u16 vport)
 
 	return MLX5_GET(query_vport_state_out, out, state);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_vport_state);
 
 int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 				  u16 vport, u8 state)
@@ -80,7 +79,6 @@ int mlx5_modify_vport_admin_state(struct mlx5_core_dev *mdev, u8 opmod,
 
 	return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out));
 }
-EXPORT_SYMBOL_GPL(mlx5_modify_vport_admin_state);
 
 static int mlx5_query_nic_vport_context(struct mlx5_core_dev *mdev, u16 vport,
 					u32 *out, int outlen)
-- 
cgit v1.2.3


From 269d26f47f6f7d4275b0e225c9ee80cf4a31aa8c Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Wed, 8 Aug 2018 16:23:53 -0700
Subject: net/mlx5: Reduce command polling interval

Use cond_resched() instead of usleep_range() to decrease the time
between polling attempts thus reducing overall driver load time.

Below is a comparison before and after the change, of loading eight
virtual functions.

Before:
real    0m8.785s
user    0m0.093s
sys     0m0.090s

After:
real    0m5.730s
user    0m0.097s
sys     0m0.087s

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index f498c7730c5b..fe4ac40dbade 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -211,7 +211,7 @@ static void poll_timeout(struct mlx5_cmd_work_ent *ent)
 			ent->ret = 0;
 			return;
 		}
-		usleep_range(5000, 10000);
+		cond_resched();
 	} while (time_before(jiffies, poll_end));
 
 	ent->ret = -ETIMEDOUT;
-- 
cgit v1.2.3


From 4c14d1ce17bcc4c0c0f291ee162f9de73c4ee2eb Mon Sep 17 00:00:00 2001
From: Vasily Gorbik <gor@linux.ibm.com>
Date: Mon, 9 Jul 2018 17:07:48 +0200
Subject: rseq/selftests: add s390 support

Implement support for s390 in the rseq selftests, in order to sanity
check the recently enabled rseq syscall. The Implementation covers both
64-bit and 31-bit mode.

Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 tools/testing/selftests/rseq/param_test.c |  24 ++
 tools/testing/selftests/rseq/rseq-s390.h  | 513 ++++++++++++++++++++++++++++++
 tools/testing/selftests/rseq/rseq.h       |   2 +
 3 files changed, 539 insertions(+)
 create mode 100644 tools/testing/selftests/rseq/rseq-s390.h

diff --git a/tools/testing/selftests/rseq/param_test.c b/tools/testing/selftests/rseq/param_test.c
index 615252331813..91cf50b2b0e5 100644
--- a/tools/testing/selftests/rseq/param_test.c
+++ b/tools/testing/selftests/rseq/param_test.c
@@ -90,6 +90,30 @@ unsigned int yield_mod_cnt, nr_abort;
 #error "Unsupported architecture"
 #endif
 
+#elif defined(__s390__)
+
+#define RSEQ_INJECT_INPUT \
+	, [loop_cnt_1]"m"(loop_cnt[1]) \
+	, [loop_cnt_2]"m"(loop_cnt[2]) \
+	, [loop_cnt_3]"m"(loop_cnt[3]) \
+	, [loop_cnt_4]"m"(loop_cnt[4]) \
+	, [loop_cnt_5]"m"(loop_cnt[5]) \
+	, [loop_cnt_6]"m"(loop_cnt[6])
+
+#define INJECT_ASM_REG	"r12"
+
+#define RSEQ_INJECT_CLOBBER \
+	, INJECT_ASM_REG
+
+#define RSEQ_INJECT_ASM(n) \
+	"l %%" INJECT_ASM_REG ", %[loop_cnt_" #n "]\n\t" \
+	"ltr %%" INJECT_ASM_REG ", %%" INJECT_ASM_REG "\n\t" \
+	"je 333f\n\t" \
+	"222:\n\t" \
+	"ahi %%" INJECT_ASM_REG ", -1\n\t" \
+	"jnz 222b\n\t" \
+	"333:\n\t"
+
 #elif defined(__ARMEL__)
 
 #define RSEQ_INJECT_INPUT \
diff --git a/tools/testing/selftests/rseq/rseq-s390.h b/tools/testing/selftests/rseq/rseq-s390.h
new file mode 100644
index 000000000000..1069e85258ce
--- /dev/null
+++ b/tools/testing/selftests/rseq/rseq-s390.h
@@ -0,0 +1,513 @@
+/* SPDX-License-Identifier: LGPL-2.1 OR MIT */
+
+#define RSEQ_SIG	0x53053053
+
+#define rseq_smp_mb()	__asm__ __volatile__ ("bcr 15,0" ::: "memory")
+#define rseq_smp_rmb()	rseq_smp_mb()
+#define rseq_smp_wmb()	rseq_smp_mb()
+
+#define rseq_smp_load_acquire(p)					\
+__extension__ ({							\
+	__typeof(*p) ____p1 = RSEQ_READ_ONCE(*p);			\
+	rseq_barrier();							\
+	____p1;								\
+})
+
+#define rseq_smp_acquire__after_ctrl_dep()	rseq_smp_rmb()
+
+#define rseq_smp_store_release(p, v)					\
+do {									\
+	rseq_barrier();							\
+	RSEQ_WRITE_ONCE(*p, v);						\
+} while (0)
+
+#ifdef RSEQ_SKIP_FASTPATH
+#include "rseq-skip.h"
+#else /* !RSEQ_SKIP_FASTPATH */
+
+#ifdef __s390x__
+
+#define LONG_L			"lg"
+#define LONG_S			"stg"
+#define LONG_LT_R		"ltgr"
+#define LONG_CMP		"cg"
+#define LONG_CMP_R		"cgr"
+#define LONG_ADDI		"aghi"
+#define LONG_ADD_R		"agr"
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_table, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".quad " __rseq_str(start_ip) ", " __rseq_str(post_commit_offset) ", " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"
+
+#elif __s390__
+
+#define __RSEQ_ASM_DEFINE_TABLE(label, version, flags,			\
+				start_ip, post_commit_offset, abort_ip)	\
+		".pushsection __rseq_table, \"aw\"\n\t"			\
+		".balign 32\n\t"					\
+		__rseq_str(label) ":\n\t"				\
+		".long " __rseq_str(version) ", " __rseq_str(flags) "\n\t" \
+		".long 0x0, " __rseq_str(start_ip) ", 0x0, " __rseq_str(post_commit_offset) ", 0x0, " __rseq_str(abort_ip) "\n\t" \
+		".popsection\n\t"
+
+#define LONG_L			"l"
+#define LONG_S			"st"
+#define LONG_LT_R		"ltr"
+#define LONG_CMP		"c"
+#define LONG_CMP_R		"cr"
+#define LONG_ADDI		"ahi"
+#define LONG_ADD_R		"ar"
+
+#endif
+
+#define RSEQ_ASM_DEFINE_TABLE(label, start_ip, post_commit_ip, abort_ip) \
+	__RSEQ_ASM_DEFINE_TABLE(label, 0x0, 0x0, start_ip,		\
+				(post_commit_ip - start_ip), abort_ip)
+
+#define RSEQ_ASM_STORE_RSEQ_CS(label, cs_label, rseq_cs)		\
+		RSEQ_INJECT_ASM(1)					\
+		"larl %%r0, " __rseq_str(cs_label) "\n\t"		\
+		LONG_S " %%r0, %[" __rseq_str(rseq_cs) "]\n\t"		\
+		__rseq_str(label) ":\n\t"
+
+#define RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, label)		\
+		RSEQ_INJECT_ASM(2)					\
+		"c %[" __rseq_str(cpu_id) "], %[" __rseq_str(current_cpu_id) "]\n\t" \
+		"jnz " __rseq_str(label) "\n\t"
+
+#define RSEQ_ASM_DEFINE_ABORT(label, teardown, abort_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		".long " __rseq_str(RSEQ_SIG) "\n\t"			\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"j %l[" __rseq_str(abort_label) "]\n\t"			\
+		".popsection\n\t"
+
+#define RSEQ_ASM_DEFINE_CMPFAIL(label, teardown, cmpfail_label)		\
+		".pushsection __rseq_failure, \"ax\"\n\t"		\
+		__rseq_str(label) ":\n\t"				\
+		teardown						\
+		"j %l[" __rseq_str(cmpfail_label) "]\n\t"		\
+		".popsection\n\t"
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_storev(intptr_t *v, intptr_t expect, intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/*
+ * Compare @v against @expectnot. When it does _not_ match, load @v
+ * into @load, and store the content of *@v + voffp into @v.
+ */
+static inline __attribute__((always_inline))
+int rseq_cmpnev_storeoffp_load(intptr_t *v, intptr_t expectnot,
+			       off_t voffp, intptr_t *load, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_L " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_L " %%r1, %[v]\n\t"
+		LONG_CMP_R " %%r1, %[expectnot]\n\t"
+		"je %l[error2]\n\t"
+#endif
+		LONG_S " %%r1, %[load]\n\t"
+		LONG_ADD_R " %%r1, %[voffp]\n\t"
+		LONG_L " %%r1, 0(%%r1)\n\t"
+		/* final store */
+		LONG_S " %%r1, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(5)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expectnot]		"r" (expectnot),
+		  [voffp]		"r" (voffp),
+		  [load]		"m" (*load)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0", "r1"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_addv(intptr_t *v, intptr_t count, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+#endif
+		LONG_L " %%r0, %[v]\n\t"
+		LONG_ADD_R " %%r0, %[count]\n\t"
+		/* final store */
+		LONG_S " %%r0, %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(4)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [count]		"r" (count)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev(intptr_t *v, intptr_t expect,
+				 intptr_t *v2, intptr_t newv2,
+				 intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+#endif
+		/* try store */
+		LONG_S " %[newv2], %[v2]\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* try store input */
+		  [v2]			"m" (*v2),
+		  [newv2]		"r" (newv2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trystorev_storev_release(intptr_t *v, intptr_t expect,
+					 intptr_t *v2, intptr_t newv2,
+					 intptr_t newv, int cpu)
+{
+	return rseq_cmpeqv_trystorev_storev(v, expect, v2, newv2, newv, cpu);
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_cmpeqv_storev(intptr_t *v, intptr_t expect,
+			      intptr_t *v2, intptr_t expect2,
+			      intptr_t newv, int cpu)
+{
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(4)
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %l[cmpfail]\n\t"
+		RSEQ_INJECT_ASM(5)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, %l[error1])
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz %l[error2]\n\t"
+		LONG_CMP " %[expect2], %[v2]\n\t"
+		"jnz %l[error3]\n\t"
+#endif
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		RSEQ_ASM_DEFINE_ABORT(4, "", abort)
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* cmp2 input */
+		  [v2]			"m" (*v2),
+		  [expect2]		"r" (expect2),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv)
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2, error3
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("1st expected value comparison failed");
+error3:
+	rseq_bug("2nd expected value comparison failed");
+#endif
+}
+
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev(intptr_t *v, intptr_t expect,
+				 void *dst, void *src, size_t len,
+				 intptr_t newv, int cpu)
+{
+	uint64_t rseq_scratch[3];
+
+	RSEQ_INJECT_C(9)
+
+	__asm__ __volatile__ goto (
+		RSEQ_ASM_DEFINE_TABLE(3, 1f, 2f, 4f) /* start, commit, abort */
+		LONG_S " %[src], %[rseq_scratch0]\n\t"
+		LONG_S " %[dst], %[rseq_scratch1]\n\t"
+		LONG_S " %[len], %[rseq_scratch2]\n\t"
+		/* Start rseq by storing table entry pointer into rseq_cs. */
+		RSEQ_ASM_STORE_RSEQ_CS(1, 3b, rseq_cs)
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 4f)
+		RSEQ_INJECT_ASM(3)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 5f\n\t"
+		RSEQ_INJECT_ASM(4)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, 6f)
+		LONG_CMP " %[expect], %[v]\n\t"
+		"jnz 7f\n\t"
+#endif
+		/* try memcpy */
+		LONG_LT_R " %[len], %[len]\n\t"
+		"jz 333f\n\t"
+		"222:\n\t"
+		"ic %%r0,0(%[src])\n\t"
+		"stc %%r0,0(%[dst])\n\t"
+		LONG_ADDI " %[src], 1\n\t"
+		LONG_ADDI " %[dst], 1\n\t"
+		LONG_ADDI " %[len], -1\n\t"
+		"jnz 222b\n\t"
+		"333:\n\t"
+		RSEQ_INJECT_ASM(5)
+		/* final store */
+		LONG_S " %[newv], %[v]\n\t"
+		"2:\n\t"
+		RSEQ_INJECT_ASM(6)
+		/* teardown */
+		LONG_L " %[len], %[rseq_scratch2]\n\t"
+		LONG_L " %[dst], %[rseq_scratch1]\n\t"
+		LONG_L " %[src], %[rseq_scratch0]\n\t"
+		RSEQ_ASM_DEFINE_ABORT(4,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			abort)
+		RSEQ_ASM_DEFINE_CMPFAIL(5,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			cmpfail)
+#ifdef RSEQ_COMPARE_TWICE
+		RSEQ_ASM_DEFINE_CMPFAIL(6,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			error1)
+		RSEQ_ASM_DEFINE_CMPFAIL(7,
+			LONG_L " %[len], %[rseq_scratch2]\n\t"
+			LONG_L " %[dst], %[rseq_scratch1]\n\t"
+			LONG_L " %[src], %[rseq_scratch0]\n\t",
+			error2)
+#endif
+		: /* gcc asm goto does not allow outputs */
+		: [cpu_id]		"r" (cpu),
+		  [current_cpu_id]	"m" (__rseq_abi.cpu_id),
+		  [rseq_cs]		"m" (__rseq_abi.rseq_cs),
+		  /* final store input */
+		  [v]			"m" (*v),
+		  [expect]		"r" (expect),
+		  [newv]		"r" (newv),
+		  /* try memcpy input */
+		  [dst]			"r" (dst),
+		  [src]			"r" (src),
+		  [len]			"r" (len),
+		  [rseq_scratch0]	"m" (rseq_scratch[0]),
+		  [rseq_scratch1]	"m" (rseq_scratch[1]),
+		  [rseq_scratch2]	"m" (rseq_scratch[2])
+		  RSEQ_INJECT_INPUT
+		: "memory", "cc", "r0"
+		  RSEQ_INJECT_CLOBBER
+		: abort, cmpfail
+#ifdef RSEQ_COMPARE_TWICE
+		  , error1, error2
+#endif
+	);
+	return 0;
+abort:
+	RSEQ_INJECT_FAILED
+	return -1;
+cmpfail:
+	return 1;
+#ifdef RSEQ_COMPARE_TWICE
+error1:
+	rseq_bug("cpu_id comparison failed");
+error2:
+	rseq_bug("expected value comparison failed");
+#endif
+}
+
+/* s390 is TSO. */
+static inline __attribute__((always_inline))
+int rseq_cmpeqv_trymemcpy_storev_release(intptr_t *v, intptr_t expect,
+					 void *dst, void *src, size_t len,
+					 intptr_t newv, int cpu)
+{
+	return rseq_cmpeqv_trymemcpy_storev(v, expect, dst, src, len,
+					    newv, cpu);
+}
+#endif /* !RSEQ_SKIP_FASTPATH */
diff --git a/tools/testing/selftests/rseq/rseq.h b/tools/testing/selftests/rseq/rseq.h
index a4684112676c..5d1ee38a64a3 100644
--- a/tools/testing/selftests/rseq/rseq.h
+++ b/tools/testing/selftests/rseq/rseq.h
@@ -75,6 +75,8 @@ extern __thread volatile struct rseq __rseq_abi;
 #include <rseq-ppc.h>
 #elif defined(__mips__)
 #include <rseq-mips.h>
+#elif defined(__s390__)
+#include <rseq-s390.h>
 #else
 #error unsupported target
 #endif
-- 
cgit v1.2.3


From 37a366face294facb9c9d9fdd9f5b64a27456cbd Mon Sep 17 00:00:00 2001
From: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Date: Tue, 7 Aug 2018 18:57:11 +0200
Subject: s390/mm: fix addressing exception after suspend/resume

Commit c9b5ad546e7d "s390/mm: tag normal pages vs pages used in page tables"
accidentally changed the logic in arch_set_page_states(), which is used by
the suspend/resume code. set_page_stable(page, order) was changed to
set_page_stable_dat(page, 0). After this, only the first page of higher order
pages will be set to stable, and a write to one of the unstable pages will
result in an addressing exception.

Fix this by using "order" again, instead of "0".

Fixes: c9b5ad546e7d ("s390/mm: tag normal pages vs pages used in page tables")
Cc: stable@vger.kernel.org # 4.14+
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 arch/s390/mm/page-states.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/mm/page-states.c b/arch/s390/mm/page-states.c
index 382153ff17e3..dc3cede7f2ec 100644
--- a/arch/s390/mm/page-states.c
+++ b/arch/s390/mm/page-states.c
@@ -271,7 +271,7 @@ void arch_set_page_states(int make_stable)
 			list_for_each(l, &zone->free_area[order].free_list[t]) {
 				page = list_entry(l, struct page, lru);
 				if (make_stable)
-					set_page_stable_dat(page, 0);
+					set_page_stable_dat(page, order);
 				else
 					set_page_unused(page, order);
 			}
-- 
cgit v1.2.3


From 725097323bbcbbca51ede20b542c6229a2869445 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 8 Aug 2018 17:11:48 -0500
Subject: ALSA: mixart: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I replaced the code comment with
a proper "fall through" annotation, which is what GCC is expecting
to find.

Addresses-Coverity-ID: 114889 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/mixart/mixart_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/mixart/mixart_core.c b/sound/pci/mixart/mixart_core.c
index 46c292b52fd6..71776bfe0485 100644
--- a/sound/pci/mixart/mixart_core.c
+++ b/sound/pci/mixart/mixart_core.c
@@ -540,7 +540,7 @@ irqreturn_t snd_mixart_threaded_irq(int irq, void *dev_id)
 				dev_err(&mgr->pci->dev,
 					"canceled notification %x !\n", msg);
 			}
-			/* no break, continue ! */
+			/* fall through */
 		case MSG_TYPE_ANSWER:
 			/* answer or notification to a message we are waiting for*/
 			mutex_lock(&mgr->msg_lock);
-- 
cgit v1.2.3


From 91c6e15efc1756b068dc6e945c1626397e60a119 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 8 Aug 2018 17:23:44 -0500
Subject: ALSA: usb-audio: Mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1357413 ("Missing break in switch")
Addresses-Coverity-ID: 114917 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/mixer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
index 73e811f86a95..c63c84b54969 100644
--- a/sound/usb/mixer.c
+++ b/sound/usb/mixer.c
@@ -856,12 +856,14 @@ static int check_input_term(struct mixer_build *state, int id,
 					term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
 				else /* UAC_VERSION_2 */
 					term->type = UAC3_EFFECT_UNIT << 16; /* virtual type */
+				/* fall through */
 			case UAC1_EXTENSION_UNIT:
 			/* UAC2_PROCESSING_UNIT_V2 */
 				if (protocol == UAC_VERSION_1 && !term->type)
 					term->type = UAC3_EXTENSION_UNIT << 16; /* virtual type */
 				else if (protocol == UAC_VERSION_2 && !term->type)
 					term->type = UAC3_PROCESSING_UNIT << 16; /* virtual type */
+				/* fall through */
 			case UAC2_EXTENSION_UNIT_V2: {
 				struct uac_processing_unit_descriptor *d = p1;
 
-- 
cgit v1.2.3


From e24f14b0ff985f3e09e573ba1134bfdf42987e05 Mon Sep 17 00:00:00 2001
From: David Woodhouse <dwmw@amazon.co.uk>
Date: Wed, 8 Aug 2018 11:00:16 +0100
Subject: tools headers: Synchronise x86 cpufeatures.h for L1TF additions

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 tools/arch/x86/include/asm/cpufeatures.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 5701f5cecd31..64aaa3f5f36c 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -219,6 +219,7 @@
 #define X86_FEATURE_IBPB		( 7*32+26) /* Indirect Branch Prediction Barrier */
 #define X86_FEATURE_STIBP		( 7*32+27) /* Single Thread Indirect Branch Predictors */
 #define X86_FEATURE_ZEN			( 7*32+28) /* "" CPU is AMD family 0x17 (Zen) */
+#define X86_FEATURE_L1TF_PTEINV		( 7*32+29) /* "" L1TF workaround PTE inversion */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW		( 8*32+ 0) /* Intel TPR Shadow */
@@ -341,6 +342,7 @@
 #define X86_FEATURE_PCONFIG		(18*32+18) /* Intel PCONFIG */
 #define X86_FEATURE_SPEC_CTRL		(18*32+26) /* "" Speculation Control (IBRS + IBPB) */
 #define X86_FEATURE_INTEL_STIBP		(18*32+27) /* "" Single Thread Indirect Branch Predictors */
+#define X86_FEATURE_FLUSH_L1D		(18*32+28) /* Flush L1D cache */
 #define X86_FEATURE_ARCH_CAPABILITIES	(18*32+29) /* IA32_ARCH_CAPABILITIES MSR (Intel) */
 #define X86_FEATURE_SPEC_CTRL_SSBD	(18*32+31) /* "" Speculative Store Bypass Disable */
 
@@ -373,5 +375,6 @@
 #define X86_BUG_SPECTRE_V1		X86_BUG(15) /* CPU is affected by Spectre variant 1 attack with conditional branches */
 #define X86_BUG_SPECTRE_V2		X86_BUG(16) /* CPU is affected by Spectre variant 2 attack with indirect branches */
 #define X86_BUG_SPEC_STORE_BYPASS	X86_BUG(17) /* CPU is affected by speculative store bypass attack */
+#define X86_BUG_L1TF			X86_BUG(18) /* CPU is affected by L1 Terminal Fault */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
-- 
cgit v1.2.3


From b41901a2cf06f33c030be96c075872201089d47a Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Tue, 7 Aug 2018 09:36:30 +0200
Subject: ACPI / battery: Do not export energy_full[_design] on devices without
 full_charge_capacity

On some devices (with a buggy _BIX implementation) full_charge_capacity
always reports as 0. This means that our energy_full sysfs attribute will
also always be 0, which is not useful to export.

Worse we calculate our reported capacity on full_charge_capacity and if it
is 0 we always report 0. This causes userspace to immediately shutdown or
hibernate the laptop since it assumes that the battery is critically low.

This commit makes us not report energy_full[_design] or capacity on such
broken devices, avoiding the immediate shutdown / hibernate from userspace.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=83941
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/battery.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
index cb664e87cde8..cb97b6105f52 100644
--- a/drivers/acpi/battery.c
+++ b/drivers/acpi/battery.c
@@ -364,6 +364,20 @@ static enum power_supply_property energy_battery_props[] = {
 	POWER_SUPPLY_PROP_SERIAL_NUMBER,
 };
 
+static enum power_supply_property energy_battery_full_cap_broken_props[] = {
+	POWER_SUPPLY_PROP_STATUS,
+	POWER_SUPPLY_PROP_PRESENT,
+	POWER_SUPPLY_PROP_TECHNOLOGY,
+	POWER_SUPPLY_PROP_CYCLE_COUNT,
+	POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
+	POWER_SUPPLY_PROP_VOLTAGE_NOW,
+	POWER_SUPPLY_PROP_POWER_NOW,
+	POWER_SUPPLY_PROP_ENERGY_NOW,
+	POWER_SUPPLY_PROP_MODEL_NAME,
+	POWER_SUPPLY_PROP_MANUFACTURER,
+	POWER_SUPPLY_PROP_SERIAL_NUMBER,
+};
+
 /* --------------------------------------------------------------------------
                                Battery Management
    -------------------------------------------------------------------------- */
@@ -798,6 +812,11 @@ static int sysfs_add_battery(struct acpi_battery *battery)
 		battery->bat_desc.properties = charge_battery_props;
 		battery->bat_desc.num_properties =
 			ARRAY_SIZE(charge_battery_props);
+	} else if (battery->full_charge_capacity == 0) {
+		battery->bat_desc.properties =
+			energy_battery_full_cap_broken_props;
+		battery->bat_desc.num_properties =
+			ARRAY_SIZE(energy_battery_full_cap_broken_props);
 	} else {
 		battery->bat_desc.properties = energy_battery_props;
 		battery->bat_desc.num_properties =
-- 
cgit v1.2.3


From a6f0729508df6a067c4a074ec187ecd9d2457a6b Mon Sep 17 00:00:00 2001
From: John Garry <john.garry@huawei.com>
Date: Tue, 7 Aug 2018 21:15:05 +0800
Subject: ACPI / scan: Add static attribute to indirect_io_hosts[]

Array indirect_io_hosts[] is declared in acpi_is_indirect_io_slave() as a
const array, which means that the array will be re-built for each call.

Optimise by adding the static attribute, which means that the array is
added to const-data pool and not re-built per function call.

Reported-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 970dd87d347c..199c8ea6896c 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1528,7 +1528,7 @@ static int acpi_check_serial_bus_slave(struct acpi_resource *ares, void *data)
 static bool acpi_is_indirect_io_slave(struct acpi_device *device)
 {
 	struct acpi_device *parent = device->parent;
-	const struct acpi_device_id indirect_io_hosts[] = {
+	static const struct acpi_device_id indirect_io_hosts[] = {
 		{"HISI0191", 0},
 		{}
 	};
-- 
cgit v1.2.3


From 1035a0783523d8c730c44944a71b254f3a649e25 Mon Sep 17 00:00:00 2001
From: Dongjiu Geng <gengdongjiu@huawei.com>
Date: Tue, 7 Aug 2018 12:26:15 -0400
Subject: arm64 / ACPI: clean the additional checks before calling
 ghes_notify_sea()

In order to remove the additional check before calling the
ghes_notify_sea(), make stub definition when !CONFIG_ACPI_APEI_SEA.

After this cleanup, we can simply call the ghes_notify_sea() to let
APEI driver handle the SEA notification.

Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com>
Acked-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 arch/arm64/mm/fault.c | 7 +------
 include/acpi/ghes.h   | 4 ++++
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index b8eecc7b9531..9ffe01d7042a 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -727,12 +727,7 @@ static const struct fault_info fault_info[] = {
 
 int handle_guest_sea(phys_addr_t addr, unsigned int esr)
 {
-	int ret = -ENOENT;
-
-	if (IS_ENABLED(CONFIG_ACPI_APEI_SEA))
-		ret = ghes_notify_sea();
-
-	return ret;
+	return ghes_notify_sea();
 }
 
 asmlinkage void __exception do_mem_abort(unsigned long addr, unsigned int esr,
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index 1624e2be485c..82cb4eb225a4 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -118,6 +118,10 @@ static inline void *acpi_hest_get_next(struct acpi_hest_generic_data *gdata)
 	     (void *)section - (void *)(estatus + 1) < estatus->data_length; \
 	     section = acpi_hest_get_next(section))
 
+#ifdef CONFIG_ACPI_APEI_SEA
 int ghes_notify_sea(void);
+#else
+static inline int ghes_notify_sea(void) { return -ENOENT; }
+#endif
 
 #endif /* GHES_H */
-- 
cgit v1.2.3


From 67fbd0a3a802bc80218f6c33d594f34f0ecb02f9 Mon Sep 17 00:00:00 2001
From: Tom Todd <thomas.m.a.todd@gmail.com>
Date: Wed, 8 Aug 2018 01:52:02 +0100
Subject: ACPI: bus: Fix a pointer coding style issue

Fix white space in the argument list of acpi_device_remove().

Signed-off-by: Tom Todd <thomas.m.a.todd@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/bus.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index f61f8927d843..292088fcc624 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -935,7 +935,7 @@ static int acpi_device_probe(struct device *dev)
 	return 0;
 }
 
-static int acpi_device_remove(struct device * dev)
+static int acpi_device_remove(struct device *dev)
 {
 	struct acpi_device *acpi_dev = to_acpi_device(dev);
 	struct acpi_driver *acpi_drv = acpi_dev->driver;
-- 
cgit v1.2.3


From 4c3be61e41b4206878cd021afbdb85f5b76f2099 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Wed, 8 Aug 2018 12:50:37 +0300
Subject: ACPI / EC: Add another entry for Thinkpad X1 Carbon 6th

Commit 2c4d6baf1bc4 (ACPI / EC: Use ec_no_wakeup on more Thinkpad X1
Carbon 6th systems) changed the DMI table to match all systems where
DMI product family is "Thinkpad X1 Carbon 6th". However, the system I
have here has this string written differently (ThinkPad vs. Thinkpad)
which makes the match fail.

In addition to that, after BIOS upgrade Robin now has the same string
than my system has (perhaps newer BIOS has changed the string).

In any case add another DMI entry to acpi_ec_no_wakeup[] table hopefully
covering all the X1 Carbon 6th systems out there.

Fixes: 2c4d6baf1bc4 (ACPI / EC: Use ec_no_wakeup on more Thinkpad X1 Carbon 6th systems)
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
[ rjw: Rebase and change the ident string to match the product familiy ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/ec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 6291d5c77267..d4e5610e09c5 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -2045,6 +2045,13 @@ static const struct dmi_system_id acpi_ec_no_wakeup[] = {
 			DMI_MATCH(DMI_PRODUCT_FAMILY, "Thinkpad X1 Carbon 6th"),
 		},
 	},
+	{
+		.ident = "ThinkPad X1 Carbon 6th",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_FAMILY, "ThinkPad X1 Carbon 6th"),
+		},
+	},
 	{
 		.ident = "ThinkPad X1 Yoga 3rd",
 		.matches = {
-- 
cgit v1.2.3


From 5971b0c1594d6c34e257101ed5fdffec65205c50 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Wed, 8 Aug 2018 10:30:03 +0200
Subject: ACPI / scan: Initialize status to ACPI_STA_DEFAULT

Since commit 63347db0affa "ACPI / scan: Use acpi_bus_get_status() to
initialize ACPI_TYPE_DEVICE devs" the status field of normal acpi_devices
gets set to 0 by acpi_bus_type_and_status() and filled with its actual
value later when acpi_add_single_object() calls acpi_bus_get_status().

This means that any acpi_match_device_ids() calls in between will always
fail with -ENOENT.

We already have a workaround for this, which temporary forces status to
ACPI_STA_DEFAULT in drivers/acpi/x86/utils.c: acpi_device_always_present()
and the next commit in this series adds another acpi_match_device_ids()
call between status being initialized as 0 and the acpi_bus_get_status()
call.

Rather then adding another workaround, this commit makes
acpi_bus_type_and_status() initialize status to ACPI_STA_DEFAULT, this is
safe to do as the only code looking at status between the initialization
and the acpi_bus_get_status() call is those acpi_match_device_ids() calls.

Note this does mean that we need to (re)set status to 0 in case the
acpi_bus_get_status() call fails.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 199c8ea6896c..798a73416af8 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1612,7 +1612,8 @@ static int acpi_add_single_object(struct acpi_device **child,
 	 * Note this must be done before the get power-/wakeup_dev-flags calls.
 	 */
 	if (type == ACPI_BUS_TYPE_DEVICE)
-		acpi_bus_get_status(device);
+		if (acpi_bus_get_status(device) < 0)
+			acpi_set_device_status(device, 0);
 
 	acpi_bus_get_power_flags(device);
 	acpi_bus_get_wakeup_device_flags(device);
@@ -1690,7 +1691,7 @@ static int acpi_bus_type_and_status(acpi_handle handle, int *type,
 		 * acpi_add_single_object updates this once we've an acpi_device
 		 * so that acpi_bus_get_status' quirk handling can be used.
 		 */
-		*sta = 0;
+		*sta = ACPI_STA_DEFAULT;
 		break;
 	case ACPI_TYPE_PROCESSOR:
 		*type = ACPI_BUS_TYPE_PROCESSOR;
-- 
cgit v1.2.3


From 17c81d2f5a59929c73a2a19fd49fe0b068fda76f Mon Sep 17 00:00:00 2001
From: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Date: Thu, 9 Aug 2018 10:48:50 +0100
Subject: ASoC: da7219: Add delays to capture path to remove DC offset noise

On some platforms it has been noted that a pop noise can be
witnessed when capturing audio, mainly for first time after a
headset jack has been inserted. This is due to a DC offset in the
Mic PGA and so to avoid this delays are required when powering
up the capture path.

This commit rectifies the problem by adding delays post Mic PGA and
post Mixin PGA. The post Mic PGA delay is determined based on
Mic Bias voltage, and is only applied the first time after a
headset jack is inserted.

Signed-off-by: Adam Thomson <Adam.Thomson.Opensource@diasemi.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/da7219-aad.c |  5 +++++
 sound/soc/codecs/da7219.c     | 44 +++++++++++++++++++++++++++++++++++++------
 sound/soc/codecs/da7219.h     |  8 ++++++--
 3 files changed, 49 insertions(+), 8 deletions(-)

diff --git a/sound/soc/codecs/da7219-aad.c b/sound/soc/codecs/da7219-aad.c
index a49ab751a036..2c7d5088e6f2 100644
--- a/sound/soc/codecs/da7219-aad.c
+++ b/sound/soc/codecs/da7219-aad.c
@@ -59,6 +59,7 @@ static void da7219_aad_btn_det_work(struct work_struct *work)
 		container_of(work, struct da7219_aad_priv, btn_det_work);
 	struct snd_soc_component *component = da7219_aad->component;
 	struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(component);
+	struct da7219_priv *da7219 = snd_soc_component_get_drvdata(component);
 	u8 statusa, micbias_ctrl;
 	bool micbias_up = false;
 	int retries = 0;
@@ -86,6 +87,8 @@ static void da7219_aad_btn_det_work(struct work_struct *work)
 	if (retries >= DA7219_AAD_MICBIAS_CHK_RETRIES)
 		dev_warn(component->dev, "Mic bias status check timed out");
 
+	da7219->micbias_on_event = true;
+
 	/*
 	 * Mic bias pulse required to enable mic, must be done before enabling
 	 * button detection to prevent erroneous button readings.
@@ -439,6 +442,8 @@ static irqreturn_t da7219_aad_irq_thread(int irq, void *data)
 			snd_soc_component_update_bits(component, DA7219_ACCDET_CONFIG_1,
 					    DA7219_BUTTON_CONFIG_MASK, 0);
 
+			da7219->micbias_on_event = false;
+
 			/* Disable mic bias */
 			snd_soc_dapm_disable_pin(dapm, "Mic Bias");
 			snd_soc_dapm_sync(dapm);
diff --git a/sound/soc/codecs/da7219.c b/sound/soc/codecs/da7219.c
index c0144f2f8174..e46e9f4bc994 100644
--- a/sound/soc/codecs/da7219.c
+++ b/sound/soc/codecs/da7219.c
@@ -768,6 +768,30 @@ static const struct snd_kcontrol_new da7219_st_out_filtr_mix_controls[] = {
  * DAPM Events
  */
 
+static int da7219_mic_pga_event(struct snd_soc_dapm_widget *w,
+				struct snd_kcontrol *kcontrol, int event)
+{
+	struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+	struct da7219_priv *da7219 = snd_soc_component_get_drvdata(component);
+
+	switch (event) {
+	case SND_SOC_DAPM_POST_PMU:
+		if (da7219->micbias_on_event) {
+			/*
+			 * Delay only for first capture after bias enabled to
+			 * avoid possible DC offset related noise.
+			 */
+			da7219->micbias_on_event = false;
+			msleep(da7219->mic_pga_delay);
+		}
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
 static int da7219_dai_event(struct snd_soc_dapm_widget *w,
 			    struct snd_kcontrol *kcontrol, int event)
 {
@@ -937,12 +961,12 @@ static const struct snd_soc_dapm_widget da7219_dapm_widgets[] = {
 	SND_SOC_DAPM_INPUT("MIC"),
 
 	/* Input PGAs */
-	SND_SOC_DAPM_PGA("Mic PGA", DA7219_MIC_1_CTRL,
-			 DA7219_MIC_1_AMP_EN_SHIFT, DA7219_NO_INVERT,
-			 NULL, 0),
-	SND_SOC_DAPM_PGA("Mixin PGA", DA7219_MIXIN_L_CTRL,
-			 DA7219_MIXIN_L_AMP_EN_SHIFT, DA7219_NO_INVERT,
-			 NULL, 0),
+	SND_SOC_DAPM_PGA_E("Mic PGA", DA7219_MIC_1_CTRL,
+			   DA7219_MIC_1_AMP_EN_SHIFT, DA7219_NO_INVERT,
+			   NULL, 0, da7219_mic_pga_event, SND_SOC_DAPM_POST_PMU),
+	SND_SOC_DAPM_PGA_E("Mixin PGA", DA7219_MIXIN_L_CTRL,
+			   DA7219_MIXIN_L_AMP_EN_SHIFT, DA7219_NO_INVERT,
+			   NULL, 0, da7219_settling_event, SND_SOC_DAPM_POST_PMU),
 
 	/* Input Filters */
 	SND_SOC_DAPM_ADC("ADC", NULL, DA7219_ADC_L_CTRL, DA7219_ADC_L_EN_SHIFT,
@@ -1847,6 +1871,14 @@ static void da7219_handle_pdata(struct snd_soc_component *component)
 
 		snd_soc_component_write(component, DA7219_MICBIAS_CTRL, micbias_lvl);
 
+		/*
+		 * Calculate delay required to compensate for DC offset in
+		 * Mic PGA, based on Mic Bias voltage.
+		 */
+		da7219->mic_pga_delay =  DA7219_MIC_PGA_BASE_DELAY +
+					(pdata->micbias_lvl *
+					 DA7219_MIC_PGA_OFFSET_DELAY);
+
 		/* Mic */
 		switch (pdata->mic_amp_in_sel) {
 		case DA7219_MIC_AMP_IN_SEL_DIFF:
diff --git a/sound/soc/codecs/da7219.h b/sound/soc/codecs/da7219.h
index 1b00023e33cd..3a006862f0e7 100644
--- a/sound/soc/codecs/da7219.h
+++ b/sound/soc/codecs/da7219.h
@@ -781,8 +781,10 @@
 #define DA7219_SYS_STAT_CHECK_DELAY	50
 
 /* Power up/down Delays */
-#define DA7219_SETTLING_DELAY	40
-#define DA7219_MIN_GAIN_DELAY	30
+#define DA7219_SETTLING_DELAY		40
+#define DA7219_MIN_GAIN_DELAY		30
+#define DA7219_MIC_PGA_BASE_DELAY	100
+#define DA7219_MIC_PGA_OFFSET_DELAY	40
 
 enum da7219_clk_src {
 	DA7219_CLKSRC_MCLK = 0,
@@ -828,6 +830,8 @@ struct da7219_priv {
 
 	bool master;
 	bool alc_en;
+	bool micbias_on_event;
+	unsigned int mic_pga_delay;
 	u8 gain_ramp_ctrl;
 };
 
-- 
cgit v1.2.3


From 74fe7b551f3385fa585d92616c85b3a575b2b2cb Mon Sep 17 00:00:00 2001
From: Crestez Dan Leonard <leonard.crestez@intel.com>
Date: Tue, 7 Aug 2018 17:52:17 +0300
Subject: regmap: Add regmap_noinc_read API

The regmap API usually assumes that bulk read operations will read a
range of registers but some I2C/SPI devices have certain registers for
which a such a read operation will return data from an internal FIFO
instead. Add an explicit API to support bulk read without range semantics.

Some linux drivers use regmap_bulk_read or regmap_raw_read for such
registers, for example mpu6050 or bmi150 from IIO. This only happens to
work because when caching is disabled a single regmap read op will map
to a single bus read op (as desired). This breaks if caching is enabled and
reg+1 happens to be a cacheable register.

Without regmap support refactoring a driver to enable regmap caching
requires separate I2C and SPI paths. This is exactly what regmap is
supposed to help avoid.

Suggested-by: Jonathan Cameron <jic23@kernel.org>
Signed-off-by: Crestez Dan Leonard <leonard.crestez@intel.com>
Signed-off-by: Stefan Popa <stefan.popa@analog.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/base/regmap/internal.h |  3 ++
 drivers/base/regmap/regmap.c   | 79 +++++++++++++++++++++++++++++++++++++++++-
 include/linux/regmap.h         | 19 ++++++++++
 3 files changed, 100 insertions(+), 1 deletion(-)

diff --git a/drivers/base/regmap/internal.h b/drivers/base/regmap/internal.h
index 53785e0e297a..a6bf34d6394e 100644
--- a/drivers/base/regmap/internal.h
+++ b/drivers/base/regmap/internal.h
@@ -94,10 +94,12 @@ struct regmap {
 	bool (*readable_reg)(struct device *dev, unsigned int reg);
 	bool (*volatile_reg)(struct device *dev, unsigned int reg);
 	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	bool (*readable_noinc_reg)(struct device *dev, unsigned int reg);
 	const struct regmap_access_table *wr_table;
 	const struct regmap_access_table *rd_table;
 	const struct regmap_access_table *volatile_table;
 	const struct regmap_access_table *precious_table;
+	const struct regmap_access_table *rd_noinc_table;
 
 	int (*reg_read)(void *context, unsigned int reg, unsigned int *val);
 	int (*reg_write)(void *context, unsigned int reg, unsigned int val);
@@ -181,6 +183,7 @@ bool regmap_writeable(struct regmap *map, unsigned int reg);
 bool regmap_readable(struct regmap *map, unsigned int reg);
 bool regmap_volatile(struct regmap *map, unsigned int reg);
 bool regmap_precious(struct regmap *map, unsigned int reg);
+bool regmap_readable_noinc(struct regmap *map, unsigned int reg);
 
 int _regmap_write(struct regmap *map, unsigned int reg,
 		  unsigned int val);
diff --git a/drivers/base/regmap/regmap.c b/drivers/base/regmap/regmap.c
index 3bc84885eb91..0360a90ad6b6 100644
--- a/drivers/base/regmap/regmap.c
+++ b/drivers/base/regmap/regmap.c
@@ -168,6 +168,17 @@ bool regmap_precious(struct regmap *map, unsigned int reg)
 	return false;
 }
 
+bool regmap_readable_noinc(struct regmap *map, unsigned int reg)
+{
+	if (map->readable_noinc_reg)
+		return map->readable_noinc_reg(map->dev, reg);
+
+	if (map->rd_noinc_table)
+		return regmap_check_range_table(map, reg, map->rd_noinc_table);
+
+	return true;
+}
+
 static bool regmap_volatile_range(struct regmap *map, unsigned int reg,
 	size_t num)
 {
@@ -766,10 +777,12 @@ struct regmap *__regmap_init(struct device *dev,
 	map->rd_table = config->rd_table;
 	map->volatile_table = config->volatile_table;
 	map->precious_table = config->precious_table;
+	map->rd_noinc_table = config->rd_noinc_table;
 	map->writeable_reg = config->writeable_reg;
 	map->readable_reg = config->readable_reg;
 	map->volatile_reg = config->volatile_reg;
 	map->precious_reg = config->precious_reg;
+	map->readable_noinc_reg = config->readable_noinc_reg;
 	map->cache_type = config->cache_type;
 
 	spin_lock_init(&map->async_lock);
@@ -1285,6 +1298,7 @@ int regmap_reinit_cache(struct regmap *map, const struct regmap_config *config)
 	map->readable_reg = config->readable_reg;
 	map->volatile_reg = config->volatile_reg;
 	map->precious_reg = config->precious_reg;
+	map->readable_noinc_reg = config->readable_noinc_reg;
 	map->cache_type = config->cache_type;
 
 	regmap_debugfs_init(map, config->name);
@@ -2564,7 +2578,70 @@ int regmap_raw_read(struct regmap *map, unsigned int reg, void *val,
 EXPORT_SYMBOL_GPL(regmap_raw_read);
 
 /**
- * regmap_field_read() - Read a value to a single register field
+ * regmap_noinc_read(): Read data from a register without incrementing the
+ *			register number
+ *
+ * @map: Register map to read from
+ * @reg: Register to read from
+ * @val: Pointer to data buffer
+ * @val_len: Length of output buffer in bytes.
+ *
+ * The regmap API usually assumes that bulk bus read operations will read a
+ * range of registers. Some devices have certain registers for which a read
+ * operation read will read from an internal FIFO.
+ *
+ * The target register must be volatile but registers after it can be
+ * completely unrelated cacheable registers.
+ *
+ * This will attempt multiple reads as required to read val_len bytes.
+ *
+ * A value of zero will be returned on success, a negative errno will be
+ * returned in error cases.
+ */
+int regmap_noinc_read(struct regmap *map, unsigned int reg,
+		      void *val, size_t val_len)
+{
+	size_t read_len;
+	int ret;
+
+	if (!map->bus)
+		return -EINVAL;
+	if (!map->bus->read)
+		return -ENOTSUPP;
+	if (val_len % map->format.val_bytes)
+		return -EINVAL;
+	if (!IS_ALIGNED(reg, map->reg_stride))
+		return -EINVAL;
+	if (val_len == 0)
+		return -EINVAL;
+
+	map->lock(map->lock_arg);
+
+	if (!regmap_volatile(map, reg) || !regmap_readable_noinc(map, reg)) {
+		ret = -EINVAL;
+		goto out_unlock;
+	}
+
+	while (val_len) {
+		if (map->max_raw_read && map->max_raw_read < val_len)
+			read_len = map->max_raw_read;
+		else
+			read_len = val_len;
+		ret = _regmap_raw_read(map, reg, val, read_len);
+		if (ret)
+			goto out_unlock;
+		val = ((u8 *)val) + read_len;
+		val_len -= read_len;
+	}
+
+out_unlock:
+	map->unlock(map->lock_arg);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regmap_noinc_read);
+
+/**
+ * regmap_field_read(): Read a value to a single register field
  *
  * @field: Register field to read from
  * @val: Pointer to store read value
diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 4f38068ffb71..19df946499d2 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -268,6 +268,13 @@ typedef void (*regmap_unlock)(void *);
  *                field is NULL but precious_table (see below) is not, the
  *                check is performed on such table (a register is precious if
  *                it belongs to one of the ranges specified by precious_table).
+ * @readable_noinc_reg: Optional callback returning true if the register
+ *			supports multiple read operations without incrementing
+ *			the register number. If this field is NULL but
+ *			rd_noinc_table (see below) is not, the check is
+ *			performed on such table (a register is no increment
+ *			readable if it belongs to one of the ranges specified
+ *			by rd_noinc_table).
  * @disable_locking: This regmap is either protected by external means or
  *                   is guaranteed not be be accessed from multiple threads.
  *                   Don't use any locking mechanisms.
@@ -295,6 +302,7 @@ typedef void (*regmap_unlock)(void *);
  * @rd_table:     As above, for read access.
  * @volatile_table: As above, for volatile registers.
  * @precious_table: As above, for precious registers.
+ * @rd_noinc_table: As above, for no increment readable registers.
  * @reg_defaults: Power on reset values for registers (for use with
  *                register cache support).
  * @num_reg_defaults: Number of elements in reg_defaults.
@@ -344,6 +352,7 @@ struct regmap_config {
 	bool (*readable_reg)(struct device *dev, unsigned int reg);
 	bool (*volatile_reg)(struct device *dev, unsigned int reg);
 	bool (*precious_reg)(struct device *dev, unsigned int reg);
+	bool (*readable_noinc_reg)(struct device *dev, unsigned int reg);
 
 	bool disable_locking;
 	regmap_lock lock;
@@ -360,6 +369,7 @@ struct regmap_config {
 	const struct regmap_access_table *rd_table;
 	const struct regmap_access_table *volatile_table;
 	const struct regmap_access_table *precious_table;
+	const struct regmap_access_table *rd_noinc_table;
 	const struct reg_default *reg_defaults;
 	unsigned int num_reg_defaults;
 	enum regcache_type cache_type;
@@ -946,6 +956,8 @@ int regmap_raw_write_async(struct regmap *map, unsigned int reg,
 int regmap_read(struct regmap *map, unsigned int reg, unsigned int *val);
 int regmap_raw_read(struct regmap *map, unsigned int reg,
 		    void *val, size_t val_len);
+int regmap_noinc_read(struct regmap *map, unsigned int reg,
+		      void *val, size_t val_len);
 int regmap_bulk_read(struct regmap *map, unsigned int reg, void *val,
 		     size_t val_count);
 int regmap_update_bits_base(struct regmap *map, unsigned int reg,
@@ -1196,6 +1208,13 @@ static inline int regmap_raw_read(struct regmap *map, unsigned int reg,
 	return -EINVAL;
 }
 
+static inline int regmap_noinc_read(struct regmap *map, unsigned int reg,
+				    void *val, size_t val_len)
+{
+	WARN_ONCE(1, "regmap API is disabled");
+	return -EINVAL;
+}
+
 static inline int regmap_bulk_read(struct regmap *map, unsigned int reg,
 				   void *val, size_t val_count)
 {
-- 
cgit v1.2.3


From aba941392aeef2d1bc064a1e4b09293473ef7b9b Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 9 Aug 2018 11:15:56 +0200
Subject: ACPI / scan: Create platform device for fwnodes with multiple i2c
 devices

Some devices have multiple I2cSerialBus resources and for things to work
an i2c-client must be instantiated for each, each with its own
i2c_device_id.

Normally we only instantiate an i2c-client for the first resource, using
the ACPI HID as id.

This commit adds a list of HIDs of devices, which need multiple i2c-clients
instantiated from a single fwnode, to acpi_device_enumeration_by_parent and
makes acpi_device_enumeration_by_parent return false for these devices so
that a platform device will be instantiated.

This allows the drivers/platform/x86/i2c-multi-instantiate.c driver, which
knows which i2c_device_id to use for each resource, to bind to the fwnode
and initiate an i2c-client for each resource.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/scan.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
index 798a73416af8..e1b6231cfa1c 100644
--- a/drivers/acpi/scan.c
+++ b/drivers/acpi/scan.c
@@ -1540,6 +1540,18 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 {
 	struct list_head resource_list;
 	bool is_serial_bus_slave = false;
+	/*
+	 * These devices have multiple I2cSerialBus resources and an i2c-client
+	 * must be instantiated for each, each with its own i2c_device_id.
+	 * Normally we only instantiate an i2c-client for the first resource,
+	 * using the ACPI HID as id. These special cases are handled by the
+	 * drivers/platform/x86/i2c-multi-instantiate.c driver, which knows
+	 * which i2c_device_id to use for each resource.
+	 */
+	static const struct acpi_device_id i2c_multi_instantiate_ids[] = {
+		{"BSG1160", },
+		{}
+	};
 
 	if (acpi_is_indirect_io_slave(device))
 		return true;
@@ -1551,6 +1563,10 @@ static bool acpi_device_enumeration_by_parent(struct acpi_device *device)
 	     fwnode_property_present(&device->fwnode, "baud")))
 		return true;
 
+	/* Instantiate a pdev for the i2c-multi-instantiate drv to bind to */
+	if (!acpi_match_device_ids(device, i2c_multi_instantiate_ids))
+		return false;
+
 	INIT_LIST_HEAD(&resource_list);
 	acpi_dev_get_resources(device, &resource_list,
 			       acpi_check_serial_bus_slave,
-- 
cgit v1.2.3


From 21ba074cb47171a34f60e250e8f7ef3dc1529e43 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 9 Aug 2018 11:15:57 +0200
Subject: ACPI / x86: utils: Remove status workaround from
 acpi_device_always_present()

Now that we init the status field to ACPI_STA_DEFAULT rather then to 0,
the workaround for acpi_match_device_ids() always returning -ENOENT when
status is 0 is no longer needed.

Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/x86/utils.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/acpi/x86/utils.c b/drivers/acpi/x86/utils.c
index 3a13b2af2bf8..06c31ec3cc70 100644
--- a/drivers/acpi/x86/utils.c
+++ b/drivers/acpi/x86/utils.c
@@ -109,13 +109,9 @@ static const struct always_present_id always_present_ids[] = {
 
 bool acpi_device_always_present(struct acpi_device *adev)
 {
-	u32 *status = (u32 *)&adev->status;
-	u32 old_status = *status;
 	bool ret = false;
 	unsigned int i;
 
-	/* acpi_match_device_ids checks status, so set it to default */
-	*status = ACPI_STA_DEFAULT;
 	for (i = 0; i < ARRAY_SIZE(always_present_ids); i++) {
 		if (acpi_match_device_ids(adev, always_present_ids[i].hid))
 			continue;
@@ -131,15 +127,9 @@ bool acpi_device_always_present(struct acpi_device *adev)
 		    !dmi_check_system(always_present_ids[i].dmi_ids))
 			continue;
 
-		if (old_status != ACPI_STA_DEFAULT) /* Log only once */
-			dev_info(&adev->dev,
-				 "Device [%s] is in always present list\n",
-				 adev->pnp.bus_id);
-
 		ret = true;
 		break;
 	}
-	*status = old_status;
 
 	return ret;
 }
-- 
cgit v1.2.3


From 7c6553d4db03350dad0110c3224194c19df76a8f Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Wed, 25 Jul 2018 13:27:10 +0200
Subject: s390/dasd: fix panic for failed online processing

Fix a panic that occurs for a device that got an error in
dasd_eckd_check_characteristics() during online processing.
For example the read configuration data command may have failed.

If this error occurs the device is not being set online and the earlier
invoked steps during online processing are rolled back. Therefore
dasd_eckd_uncheck_device() is called which needs a valid private
structure. But this pointer is not valid if
dasd_eckd_check_characteristics() has failed.

Check for a valid device->private pointer to prevent a panic.

Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/dasd_eckd.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index c5a55513b07c..1e97378d4f60 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -1780,6 +1780,9 @@ static void dasd_eckd_uncheck_device(struct dasd_device *device)
 	struct dasd_eckd_private *private = device->private;
 	int i;
 
+	if (!private)
+		return;
+
 	dasd_alias_disconnect_device_from_lcu(device);
 	private->ned = NULL;
 	private->sneq = NULL;
-- 
cgit v1.2.3


From 669f3765b755fd8739ab46ce3a9c6292ce8b3d2a Mon Sep 17 00:00:00 2001
From: Stefan Haberland <sth@linux.ibm.com>
Date: Wed, 25 Jul 2018 14:00:47 +0200
Subject: s390/dasd: fix hanging offline processing due to canceled worker

During offline processing two worker threads are canceled without
freeing the device reference which leads to a hanging offline process.

Reviewed-by: Jan Hoeppner <hoeppner@linux.ibm.com>
Signed-off-by: Stefan Haberland <sth@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
---
 drivers/s390/block/dasd_eckd.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
index 1e97378d4f60..4e7b55a14b1a 100644
--- a/drivers/s390/block/dasd_eckd.c
+++ b/drivers/s390/block/dasd_eckd.c
@@ -2038,8 +2038,11 @@ static int dasd_eckd_basic_to_ready(struct dasd_device *device)
 
 static int dasd_eckd_online_to_ready(struct dasd_device *device)
 {
-	cancel_work_sync(&device->reload_device);
-	cancel_work_sync(&device->kick_validate);
+	if (cancel_work_sync(&device->reload_device))
+		dasd_put_device(device);
+	if (cancel_work_sync(&device->kick_validate))
+		dasd_put_device(device);
+
 	return 0;
 };
 
-- 
cgit v1.2.3


From e64e84987de5486839afaccd191df71012ac1800 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 9 Aug 2018 13:40:46 +0200
Subject: platform/x86: Add ACPI i2c-multi-instantiate pseudo driver

On systems with ACPI instantiated i2c-clients, normally there is 1 fw_node
per i2c-device and that fw-node contains 1 I2cSerialBus resource for that 1
i2c-device.

But in some rare cases the manufacturer has decided to describe multiple
i2c-devices in a single ACPI fwnode with multiple I2cSerialBus resources.

An earlier attempt to fix this in the i2c-core resulted in a lot of extra
code to support this corner-case.

This commit introduces a new i2c-multi-instantiate driver which fixes this
in a different way. This new driver can be built as a module which will
only loaded on affected systems.

This driver will instantiate a new i2c-client per I2cSerialBus resource,
using the driver_data from the acpi_device_id it is binding to to tell it
which chip-type (and optional irq-resource) to use when instantiating.

Note this driver depends on a platform device being instantiated for the
ACPI fwnode, see the i2c_multi_instantiate_ids list of ACPI device-ids in
drivers/acpi/scan.c: acpi_device_enumeration_by_parent().

Acked-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Wolfram Sang <wsa@the-dreams.de>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 MAINTAINERS                                  |   6 ++
 drivers/platform/x86/Kconfig                 |  11 +++
 drivers/platform/x86/Makefile                |   1 +
 drivers/platform/x86/i2c-multi-instantiate.c | 132 +++++++++++++++++++++++++++
 4 files changed, 150 insertions(+)
 create mode 100644 drivers/platform/x86/i2c-multi-instantiate.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 7cebd5bba8a8..a7cf519991ec 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -367,6 +367,12 @@ L:	linux-acpi@vger.kernel.org
 S:	Maintained
 F:	drivers/acpi/arm64
 
+ACPI I2C MULTI INSTANTIATE DRIVER
+M:	Hans de Goede <hdegoede@redhat.com>
+L:	platform-driver-x86@vger.kernel.org
+S:	Maintained
+F:	drivers/platform/x86/i2c-multi-instantiate.c
+
 ACPI PMIC DRIVERS
 M:	"Rafael J. Wysocki" <rjw@rjwysocki.net>
 M:	Len Brown <lenb@kernel.org>
diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
index ac4d48830415..107d336453b2 100644
--- a/drivers/platform/x86/Kconfig
+++ b/drivers/platform/x86/Kconfig
@@ -1218,6 +1218,17 @@ config INTEL_CHTDC_TI_PWRBTN
 	  To compile this driver as a module, choose M here: the module
 	  will be called intel_chtdc_ti_pwrbtn.
 
+config I2C_MULTI_INSTANTIATE
+	tristate "I2C multi instantiate pseudo device driver"
+	depends on I2C && ACPI
+	help
+	  Some ACPI-based systems list multiple i2c-devices in a single ACPI
+	  firmware-node. This driver will instantiate separate i2c-clients
+	  for each device in the firmware-node.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called i2c-multi-instantiate.
+
 endif # X86_PLATFORM_DEVICES
 
 config PMC_ATOM
diff --git a/drivers/platform/x86/Makefile b/drivers/platform/x86/Makefile
index 2ba6cb795338..50dc8f280914 100644
--- a/drivers/platform/x86/Makefile
+++ b/drivers/platform/x86/Makefile
@@ -91,3 +91,4 @@ obj-$(CONFIG_PMC_ATOM)		+= pmc_atom.o
 obj-$(CONFIG_MLX_PLATFORM)	+= mlx-platform.o
 obj-$(CONFIG_INTEL_TURBO_MAX_3) += intel_turbo_max_3.o
 obj-$(CONFIG_INTEL_CHTDC_TI_PWRBTN)	+= intel_chtdc_ti_pwrbtn.o
+obj-$(CONFIG_I2C_MULTI_INSTANTIATE)	+= i2c-multi-instantiate.o
diff --git a/drivers/platform/x86/i2c-multi-instantiate.c b/drivers/platform/x86/i2c-multi-instantiate.c
new file mode 100644
index 000000000000..5456581b473c
--- /dev/null
+++ b/drivers/platform/x86/i2c-multi-instantiate.c
@@ -0,0 +1,132 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * I2C multi-instantiate driver, pseudo driver to instantiate multiple
+ * i2c-clients from a single fwnode.
+ *
+ * Copyright 2018 Hans de Goede <hdegoede@redhat.com>
+ */
+
+#include <linux/acpi.h>
+#include <linux/i2c.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+
+struct i2c_inst_data {
+	const char *type;
+	int gpio_irq_idx;
+};
+
+struct i2c_multi_inst_data {
+	int num_clients;
+	struct i2c_client *clients[0];
+};
+
+static int i2c_multi_inst_probe(struct platform_device *pdev)
+{
+	struct i2c_multi_inst_data *multi;
+	const struct acpi_device_id *match;
+	const struct i2c_inst_data *inst_data;
+	struct i2c_board_info board_info = {};
+	struct device *dev = &pdev->dev;
+	struct acpi_device *adev;
+	char name[32];
+	int i, ret;
+
+	match = acpi_match_device(dev->driver->acpi_match_table, dev);
+	if (!match) {
+		dev_err(dev, "Error ACPI match data is missing\n");
+		return -ENODEV;
+	}
+	inst_data = (const struct i2c_inst_data *)match->driver_data;
+
+	adev = ACPI_COMPANION(dev);
+
+	/* Count number of clients to instantiate */
+	for (i = 0; inst_data[i].type; i++) {}
+
+	multi = devm_kmalloc(dev,
+			offsetof(struct i2c_multi_inst_data, clients[i]),
+			GFP_KERNEL);
+	if (!multi)
+		return -ENOMEM;
+
+	multi->num_clients = i;
+
+	for (i = 0; i < multi->num_clients; i++) {
+		memset(&board_info, 0, sizeof(board_info));
+		strlcpy(board_info.type, inst_data[i].type, I2C_NAME_SIZE);
+		snprintf(name, sizeof(name), "%s-%s", match->id,
+			 inst_data[i].type);
+		board_info.dev_name = name;
+		board_info.irq = 0;
+		if (inst_data[i].gpio_irq_idx != -1) {
+			ret = acpi_dev_gpio_irq_get(adev,
+						    inst_data[i].gpio_irq_idx);
+			if (ret < 0) {
+				dev_err(dev, "Error requesting irq at index %d: %d\n",
+					inst_data[i].gpio_irq_idx, ret);
+				goto error;
+			}
+			board_info.irq = ret;
+		}
+		multi->clients[i] = i2c_acpi_new_device(dev, i, &board_info);
+		if (!multi->clients[i]) {
+			dev_err(dev, "Error creating i2c-client, idx %d\n", i);
+			ret = -ENODEV;
+			goto error;
+		}
+	}
+
+	platform_set_drvdata(pdev, multi);
+	return 0;
+
+error:
+	while (--i >= 0)
+		i2c_unregister_device(multi->clients[i]);
+
+	return ret;
+}
+
+static int i2c_multi_inst_remove(struct platform_device *pdev)
+{
+	struct i2c_multi_inst_data *multi = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < multi->num_clients; i++)
+		i2c_unregister_device(multi->clients[i]);
+
+	return 0;
+}
+
+static const struct i2c_inst_data bsg1160_data[]  = {
+	{ "bmc150_accel", 0 },
+	{ "bmc150_magn", -1 },
+	{ "bmg160", -1 },
+	{}
+};
+
+/*
+ * Note new device-ids must also be added to i2c_multi_instantiate_ids in
+ * drivers/acpi/scan.c: acpi_device_enumeration_by_parent().
+ */
+static const struct acpi_device_id i2c_multi_inst_acpi_ids[] = {
+	{ "BSG1160", (unsigned long)bsg1160_data },
+	{ }
+};
+MODULE_DEVICE_TABLE(acpi, i2c_multi_inst_acpi_ids);
+
+static struct platform_driver i2c_multi_inst_driver = {
+	.driver	= {
+		.name = "I2C multi instantiate pseudo device driver",
+		.acpi_match_table = ACPI_PTR(i2c_multi_inst_acpi_ids),
+	},
+	.probe = i2c_multi_inst_probe,
+	.remove = i2c_multi_inst_remove,
+};
+module_platform_driver(i2c_multi_inst_driver);
+
+MODULE_DESCRIPTION("I2C multi instantiate pseudo device driver");
+MODULE_AUTHOR("Hans de Goede <hdegoede@redhat.com>");
+MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 3fca1700c4c38aaec1cea0c143b0ff8da029fd9c Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Wed, 8 Aug 2018 11:14:14 +0900
Subject: kbuild: make samples really depend on headers_install

Kernel headers must be installed into $(objtree)/usr/include to avoid
the build failure of samples.

Commit ddea05fa148b ("kbuild: make samples depend on headers_install")
addressed this, but "samples/" is only used for the single target build.

"make samples/" properly installs kernel headers, but it does not work
for general building because a phony target "sample" (no trailing slash)
is used.

Reported-by: David Howells <dhowells@redhat.com>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Tested-by: David Howells <dhowells@redhat.com>
---
 Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index d2832a45dffe..bb917de24913 100644
--- a/Makefile
+++ b/Makefile
@@ -1010,9 +1010,10 @@ ifdef CONFIG_GDB_SCRIPTS
 endif
 	+$(call if_changed,link-vmlinux)
 
-# Build samples along the rest of the kernel
+# Build samples along the rest of the kernel. This needs headers_install.
 ifdef CONFIG_SAMPLES
 vmlinux-dirs += samples
+samples: headers_install
 endif
 
 # The actual objects are generated when descending,
-- 
cgit v1.2.3


From 47f38ae08df0aebb0e43fca50bf380aefea1f4d1 Mon Sep 17 00:00:00 2001
From: Rob Landley <rob@landley.net>
Date: Wed, 8 Aug 2018 13:06:43 +0900
Subject: init/Kconfig: Use short unix-style option instead of --longname

Avoids warning messages with the latest release of toybox, which never
bothered to implement the --longopts nothing was using.

Signed-off-by: Rob Landley <rob@landley.net>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 init/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/init/Kconfig b/init/Kconfig
index 041f3a022122..192d4006d57a 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -2,9 +2,9 @@ config DEFCONFIG_LIST
 	string
 	depends on !UML
 	option defconfig_list
-	default "/lib/modules/$(shell,uname --release)/.config"
+	default "/lib/modules/$(shell,uname -r)/.config"
 	default "/etc/kernel-config"
-	default "/boot/config-$(shell,uname --release)"
+	default "/boot/config-$(shell,uname -r)"
 	default ARCH_DEFCONFIG
 	default "arch/$(ARCH)/defconfig"
 
-- 
cgit v1.2.3


From d6c6ab93e17f139c9b7f9b077307ebddc05a7990 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 9 Aug 2018 14:19:31 +0900
Subject: kbuild: remove deprecated host-progs variable

The host-progs has been kept as an alias of hostprogs-y for a long time
(at least since the beginning of Git era), with the clear prompt:
  Usage of host-progs is deprecated. Please replace with hostprogs-y!

Enough time for the migration has passed.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Max Filippov <jcmvbkbc@gmail.com>
---
 arch/xtensa/boot/Makefile | 3 +--
 scripts/Makefile.build    | 7 -------
 scripts/Makefile.clean    | 1 -
 3 files changed, 1 insertion(+), 10 deletions(-)

diff --git a/arch/xtensa/boot/Makefile b/arch/xtensa/boot/Makefile
index 53e4178711e6..dc9e0ba7122c 100644
--- a/arch/xtensa/boot/Makefile
+++ b/arch/xtensa/boot/Makefile
@@ -30,8 +30,7 @@ Image: boot-elf
 zImage: boot-redboot
 uImage: $(obj)/uImage
 
-boot-elf boot-redboot: $(addprefix $(obj)/,$(subdir-y)) \
-		       $(addprefix $(obj)/,$(host-progs))
+boot-elf boot-redboot: $(addprefix $(obj)/,$(subdir-y))
 	$(Q)$(MAKE) $(build)=$(obj)/$@ $(MAKECMDGOALS)
 
 OBJCOPYFLAGS = --strip-all -R .comment -R .note.gnu.build-id -O binary
diff --git a/scripts/Makefile.build b/scripts/Makefile.build
index 514ed63ff571..1adaac4e10d8 100644
--- a/scripts/Makefile.build
+++ b/scripts/Makefile.build
@@ -53,13 +53,6 @@ endif
 
 include scripts/Makefile.lib
 
-ifdef host-progs
-ifneq ($(hostprogs-y),$(host-progs))
-$(warning kbuild: $(obj)/Makefile - Usage of host-progs is deprecated. Please replace with hostprogs-y!)
-hostprogs-y += $(host-progs)
-endif
-endif
-
 # Do not include host rules unless needed
 ifneq ($(hostprogs-y)$(hostprogs-m)$(hostlibs-y)$(hostlibs-m)$(hostcxxlibs-y)$(hostcxxlibs-m),)
 include scripts/Makefile.host
diff --git a/scripts/Makefile.clean b/scripts/Makefile.clean
index 17ef94c635cd..0b80e3207b20 100644
--- a/scripts/Makefile.clean
+++ b/scripts/Makefile.clean
@@ -38,7 +38,6 @@ subdir-ymn	:= $(addprefix $(obj)/,$(subdir-ymn))
 
 __clean-files	:= $(extra-y) $(extra-m) $(extra-)       \
 		   $(always) $(targets) $(clean-files)   \
-		   $(host-progs)                         \
 		   $(hostprogs-y) $(hostprogs-m) $(hostprogs-) \
 		   $(hostlibs-y) $(hostlibs-m) $(hostlibs-) \
 		   $(hostcxxlibs-y) $(hostcxxlibs-m)
-- 
cgit v1.2.3


From f2cf0ef7c0ce141bb38f315c34c56e6ef5667a27 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Wed, 8 Aug 2018 14:19:33 -0500
Subject: ASoC: adav80x: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1056531 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Lars-Peter Clausen <lars@metafoo.de>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/adav80x.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/soc/codecs/adav80x.c b/sound/soc/codecs/adav80x.c
index db21ecbe0762..8b9ca7e7a682 100644
--- a/sound/soc/codecs/adav80x.c
+++ b/sound/soc/codecs/adav80x.c
@@ -648,6 +648,7 @@ static int adav80x_set_pll(struct snd_soc_component *component, int pll_id,
 			pll_ctrl1 |= ADAV80X_PLL_CTRL1_PLLDIV;
 			break;
 		}
+		/* fall through */
 	default:
 		return -EINVAL;
 	}
-- 
cgit v1.2.3


From 78ac2107176baa0daf65b0fb8e561d2ed14c83ca Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:42 +0800
Subject: bcache: do not check return value of debugfs_create_dir()

Greg KH suggests that normal code should not care about debugfs. Therefore
no matter successful or failed of debugfs_create_dir() execution, it is
unncessary to check its return value.

There are two functions called debugfs_create_dir() and check the return
value, which are bch_debug_init() and closure_debug_init(). This patch
changes these two functions from int to void type, and ignore return values
of debugfs_create_dir().

This patch does not fix exact bug, just makes things work as they should.

Signed-off-by: Coly Li <colyli@suse.de>
Suggested-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: stable@vger.kernel.org
Cc: Kai Krakow <kai@kaishome.de>
Cc: Kent Overstreet <kent.overstreet@gmail.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bcache.h  |  2 +-
 drivers/md/bcache/closure.c | 13 +++++++++----
 drivers/md/bcache/closure.h |  4 ++--
 drivers/md/bcache/debug.c   | 11 ++++++-----
 drivers/md/bcache/super.c   |  4 +++-
 5 files changed, 21 insertions(+), 13 deletions(-)

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 872ef4d67711..0a3e82b0876d 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -1001,7 +1001,7 @@ void bch_open_buckets_free(struct cache_set *);
 int bch_cache_allocator_start(struct cache *ca);
 
 void bch_debug_exit(void);
-int bch_debug_init(struct kobject *);
+void bch_debug_init(struct kobject *kobj);
 void bch_request_exit(void);
 int bch_request_init(void);
 
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 0e14969182c6..618253683d40 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -199,11 +199,16 @@ static const struct file_operations debug_ops = {
 	.release	= single_release
 };
 
-int __init closure_debug_init(void)
+void  __init closure_debug_init(void)
 {
-	closure_debug = debugfs_create_file("closures",
-				0400, bcache_debug, NULL, &debug_ops);
-	return IS_ERR_OR_NULL(closure_debug);
+	if (!IS_ERR_OR_NULL(bcache_debug))
+		/*
+		 * it is unnecessary to check return value of
+		 * debugfs_create_file(), we should not care
+		 * about this.
+		 */
+		closure_debug = debugfs_create_file(
+			"closures", 0400, bcache_debug, NULL, &debug_ops);
 }
 #endif
 
diff --git a/drivers/md/bcache/closure.h b/drivers/md/bcache/closure.h
index 71427eb5fdae..7c2c5bc7c88b 100644
--- a/drivers/md/bcache/closure.h
+++ b/drivers/md/bcache/closure.h
@@ -186,13 +186,13 @@ static inline void closure_sync(struct closure *cl)
 
 #ifdef CONFIG_BCACHE_CLOSURES_DEBUG
 
-int closure_debug_init(void);
+void closure_debug_init(void);
 void closure_debug_create(struct closure *cl);
 void closure_debug_destroy(struct closure *cl);
 
 #else
 
-static inline int closure_debug_init(void) { return 0; }
+static inline void closure_debug_init(void) {}
 static inline void closure_debug_create(struct closure *cl) {}
 static inline void closure_debug_destroy(struct closure *cl) {}
 
diff --git a/drivers/md/bcache/debug.c b/drivers/md/bcache/debug.c
index 04d146711950..12034c07257b 100644
--- a/drivers/md/bcache/debug.c
+++ b/drivers/md/bcache/debug.c
@@ -252,11 +252,12 @@ void bch_debug_exit(void)
 		debugfs_remove_recursive(bcache_debug);
 }
 
-int __init bch_debug_init(struct kobject *kobj)
+void __init bch_debug_init(struct kobject *kobj)
 {
-	if (!IS_ENABLED(CONFIG_DEBUG_FS))
-		return 0;
-
+	/*
+	 * it is unnecessary to check return value of
+	 * debugfs_create_file(), we should not care
+	 * about this.
+	 */
 	bcache_debug = debugfs_create_dir("bcache", NULL);
-	return IS_ERR_OR_NULL(bcache_debug);
 }
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index e0a92104ca23..c7ffa6ef3f82 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -2345,10 +2345,12 @@ static int __init bcache_init(void)
 		goto err;
 
 	if (bch_request_init() ||
-	    bch_debug_init(bcache_kobj) || closure_debug_init() ||
 	    sysfs_create_files(bcache_kobj, files))
 		goto err;
 
+	bch_debug_init(bcache_kobj);
+	closure_debug_init();
+
 	return 0;
 err:
 	bcache_exit();
-- 
cgit v1.2.3


From b4cb6efc1af7da2fa1e9ff0eaf90e2be02cfdf5f Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:43 +0800
Subject: bcache: display rate debug parameters to 0 when writeback is not
 running

When writeback is not running, writeback rate should be 0, other value is
misleading. And the following dyanmic writeback rate debug parameters
should be 0 too,
	rate, proportional, integral, change
otherwise they are misleading when writeback is not running.

Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/sysfs.c | 26 ++++++++++++++++----------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 225b15aa0340..3e9d3459a224 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -149,6 +149,7 @@ SHOW(__bch_cached_dev)
 	struct cached_dev *dc = container_of(kobj, struct cached_dev,
 					     disk.kobj);
 	const char *states[] = { "no cache", "clean", "dirty", "inconsistent" };
+	int wb = dc->writeback_running;
 
 #define var(stat)		(dc->stat)
 
@@ -170,7 +171,7 @@ SHOW(__bch_cached_dev)
 	var_printf(writeback_running,	"%i");
 	var_print(writeback_delay);
 	var_print(writeback_percent);
-	sysfs_hprint(writeback_rate,	dc->writeback_rate.rate << 9);
+	sysfs_hprint(writeback_rate,	wb ? dc->writeback_rate.rate << 9 : 0);
 	sysfs_hprint(io_errors,		atomic_read(&dc->io_errors));
 	sysfs_printf(io_error_limit,	"%i", dc->error_limit);
 	sysfs_printf(io_disable,	"%i", dc->io_disable);
@@ -188,15 +189,20 @@ SHOW(__bch_cached_dev)
 		char change[20];
 		s64 next_io;
 
-		bch_hprint(rate,	dc->writeback_rate.rate << 9);
-		bch_hprint(dirty,	bcache_dev_sectors_dirty(&dc->disk) << 9);
-		bch_hprint(target,	dc->writeback_rate_target << 9);
-		bch_hprint(proportional,dc->writeback_rate_proportional << 9);
-		bch_hprint(integral,	dc->writeback_rate_integral_scaled << 9);
-		bch_hprint(change,	dc->writeback_rate_change << 9);
-
-		next_io = div64_s64(dc->writeback_rate.next - local_clock(),
-				    NSEC_PER_MSEC);
+		/*
+		 * Except for dirty and target, other values should
+		 * be 0 if writeback is not running.
+		 */
+		bch_hprint(rate, wb ? dc->writeback_rate.rate << 9 : 0);
+		bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9);
+		bch_hprint(target, dc->writeback_rate_target << 9);
+		bch_hprint(proportional,
+			   wb ? dc->writeback_rate_proportional << 9 : 0);
+		bch_hprint(integral,
+			   wb ? dc->writeback_rate_integral_scaled << 9 : 0);
+		bch_hprint(change, wb ? dc->writeback_rate_change << 9 : 0);
+		next_io = wb ? div64_s64(dc->writeback_rate.next-local_clock(),
+					 NSEC_PER_MSEC) : 0;
 
 		return sprintf(buf,
 			       "rate:\t\t%s/sec\n"
-- 
cgit v1.2.3


From c2e8dcf7fa43ed236cb341c33aa3a75687557c43 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:44 +0800
Subject: bcache: avoid unncessary cache prefetch bch_btree_node_get()

In bch_btree_node_get() the read-in btree node will be partially
prefetched into L1 cache for following bset iteration (if there is).
But if the btree node read is failed, the perfetch operations will
waste L1 cache space. This patch checkes whether read operation and
only does cache prefetch when read I/O succeeded.

Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/btree.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c
index 475008fbbaab..c19f7716df88 100644
--- a/drivers/md/bcache/btree.c
+++ b/drivers/md/bcache/btree.c
@@ -1011,6 +1011,13 @@ retry:
 		BUG_ON(b->level != level);
 	}
 
+	if (btree_node_io_error(b)) {
+		rw_unlock(write, b);
+		return ERR_PTR(-EIO);
+	}
+
+	BUG_ON(!b->written);
+
 	b->parent = parent;
 	b->accessed = 1;
 
@@ -1022,13 +1029,6 @@ retry:
 	for (; i <= b->keys.nsets; i++)
 		prefetch(b->keys.set[i].data);
 
-	if (btree_node_io_error(b)) {
-		rw_unlock(write, b);
-		return ERR_PTR(-EIO);
-	}
-
-	BUG_ON(!b->written);
-
 	return b;
 }
 
-- 
cgit v1.2.3


From e57fd746848597e9c701751e26416d4b2e3b27ea Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:45 +0800
Subject: bcache: add a comment in super.c

This patch adds a line of code comment in super.c:register_bdev(), to
make code to be more comprehensible.

Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/super.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index c7ffa6ef3f82..1e85cbb4c159 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -1291,6 +1291,7 @@ static void register_bdev(struct cache_sb *sb, struct page *sb_page,
 	pr_info("registered backing device %s", dc->backing_dev_name);
 
 	list_add(&dc->list, &uncached_devices);
+	/* attach to a matched cache set if it exists */
 	list_for_each_entry(c, &bch_cache_sets, list)
 		bch_cached_dev_attach(dc, c, NULL);
 
-- 
cgit v1.2.3


From cb329dec11822f84f9d7309766a1f3a35d3d182a Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:46 +0800
Subject: bcache: fix mistaken code comments in bcache.h

This patch updates the code comment in struct cache with correct array
names, to make the code to be more comprehensible.

Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bcache.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index 0a3e82b0876d..b393b3fd06b6 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -423,9 +423,9 @@ struct cache {
 	/*
 	 * When allocating new buckets, prio_write() gets first dibs - since we
 	 * may not be allocate at all without writing priorities and gens.
-	 * prio_buckets[] contains the last buckets we wrote priorities to (so
-	 * gc can mark them as metadata), prio_next[] contains the buckets
-	 * allocated for the next prio write.
+	 * prio_last_buckets[] contains the last buckets we wrote priorities to
+	 * (so gc can mark them as metadata), prio_buckets[] contains the
+	 * buckets allocated for the next prio write.
 	 */
 	uint64_t		*prio_buckets;
 	uint64_t		*prio_last_buckets;
-- 
cgit v1.2.3


From 0cba2e71111e4bd156e67086de3484c7b907a4fc Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:47 +0800
Subject: bcache: fix mistaken comments in request.c

This patch updates code comment in bch_keylist_realloc() by fixing
incorrected function names, to make the code to be more comprehennsible.

Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/request.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 43af905920f5..914d501ad1e0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -107,7 +107,7 @@ static int bch_keylist_realloc(struct keylist *l, unsigned u64s,
 	/*
 	 * The journalling code doesn't handle the case where the keys to insert
 	 * is bigger than an empty write: If we just return -ENOMEM here,
-	 * bio_insert() and bio_invalidate() will insert the keys created so far
+	 * bch_data_insert_keys() will insert the keys created so far
 	 * and finish the rest when the keylist is empty.
 	 */
 	if (newsize * sizeof(uint64_t) > block_bytes(c) - sizeof(struct jset))
-- 
cgit v1.2.3


From b467a6ac0b4bf57ec8c2329212e8a8a0231a2ef2 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:48 +0800
Subject: bcache: add code comments for bset.c

This patch tries to add code comments in bset.c, to make some
tricky code and designment to be more comprehensible. Most information
of this patch comes from the discussion between Kent and I, he
offers very informative details. If there is any mistake
of the idea behind the code, no doubt that's from me misrepresentation.

Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bset.c | 63 ++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 63 insertions(+)

diff --git a/drivers/md/bcache/bset.c b/drivers/md/bcache/bset.c
index f3403b45bc28..596c93b44e9b 100644
--- a/drivers/md/bcache/bset.c
+++ b/drivers/md/bcache/bset.c
@@ -366,6 +366,10 @@ EXPORT_SYMBOL(bch_btree_keys_init);
 
 /* Binary tree stuff for auxiliary search trees */
 
+/*
+ * return array index next to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_next(unsigned j, unsigned size)
 {
 	if (j * 2 + 1 < size) {
@@ -379,6 +383,10 @@ static unsigned inorder_next(unsigned j, unsigned size)
 	return j;
 }
 
+/*
+ * return array index previous to j when does in-order traverse
+ * of a binary tree which is stored in a linear array
+ */
 static unsigned inorder_prev(unsigned j, unsigned size)
 {
 	if (j * 2 < size) {
@@ -421,6 +429,10 @@ static unsigned __to_inorder(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return the cacheline index in bset_tree->data, where j is index
+ * from a linear array which stores the auxiliar binary tree
+ */
 static unsigned to_inorder(unsigned j, struct bset_tree *t)
 {
 	return __to_inorder(j, t->size, t->extra);
@@ -441,6 +453,10 @@ static unsigned __inorder_to_tree(unsigned j, unsigned size, unsigned extra)
 	return j;
 }
 
+/*
+ * Return an index from a linear array which stores the auxiliar binary
+ * tree, j is the cacheline index of t->data.
+ */
 static unsigned inorder_to_tree(unsigned j, struct bset_tree *t)
 {
 	return __inorder_to_tree(j, t->size, t->extra);
@@ -546,6 +562,20 @@ static inline uint64_t shrd128(uint64_t high, uint64_t low, uint8_t shift)
 	return low;
 }
 
+/*
+ * Calculate mantissa value for struct bkey_float.
+ * If most significant bit of f->exponent is not set, then
+ *  - f->exponent >> 6 is 0
+ *  - p[0] points to bkey->low
+ *  - p[-1] borrows bits from KEY_INODE() of bkey->high
+ * if most isgnificant bits of f->exponent is set, then
+ *  - f->exponent >> 6 is 1
+ *  - p[0] points to bits from KEY_INODE() of bkey->high
+ *  - p[-1] points to other bits from KEY_INODE() of
+ *    bkey->high too.
+ * See make_bfloat() to check when most significant bit of f->exponent
+ * is set or not.
+ */
 static inline unsigned bfloat_mantissa(const struct bkey *k,
 				       struct bkey_float *f)
 {
@@ -570,6 +600,16 @@ static void make_bfloat(struct bset_tree *t, unsigned j)
 	BUG_ON(m < l || m > r);
 	BUG_ON(bkey_next(p) != m);
 
+	/*
+	 * If l and r have different KEY_INODE values (different backing
+	 * device), f->exponent records how many least significant bits
+	 * are different in KEY_INODE values and sets most significant
+	 * bits to 1 (by +64).
+	 * If l and r have same KEY_INODE value, f->exponent records
+	 * how many different bits in least significant bits of bkey->low.
+	 * See bfloat_mantiss() how the most significant bit of
+	 * f->exponent is used to calculate bfloat mantissa value.
+	 */
 	if (KEY_INODE(l) != KEY_INODE(r))
 		f->exponent = fls64(KEY_INODE(r) ^ KEY_INODE(l)) + 64;
 	else
@@ -633,6 +673,15 @@ void bch_bset_init_next(struct btree_keys *b, struct bset *i, uint64_t magic)
 }
 EXPORT_SYMBOL(bch_bset_init_next);
 
+/*
+ * Build auxiliary binary tree 'struct bset_tree *t', this tree is used to
+ * accelerate bkey search in a btree node (pointed by bset_tree->data in
+ * memory). After search in the auxiliar tree by calling bset_search_tree(),
+ * a struct bset_search_iter is returned which indicates range [l, r] from
+ * bset_tree->data where the searching bkey might be inside. Then a followed
+ * linear comparison does the exact search, see __bch_bset_search() for how
+ * the auxiliary tree is used.
+ */
 void bch_bset_build_written_tree(struct btree_keys *b)
 {
 	struct bset_tree *t = bset_tree_last(b);
@@ -898,6 +947,17 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 	unsigned inorder, j, n = 1;
 
 	do {
+		/*
+		 * A bit trick here.
+		 * If p < t->size, (int)(p - t->size) is a minus value and
+		 * the most significant bit is set, right shifting 31 bits
+		 * gets 1. If p >= t->size, the most significant bit is
+		 * not set, right shifting 31 bits gets 0.
+		 * So the following 2 lines equals to
+		 *	if (p >= t->size)
+		 *		p = 0;
+		 * but a branch instruction is avoided.
+		 */
 		unsigned p = n << 4;
 		p &= ((int) (p - t->size)) >> 31;
 
@@ -907,6 +967,9 @@ static struct bset_search_iter bset_search_tree(struct bset_tree *t,
 		f = &t->tree[j];
 
 		/*
+		 * Similar bit trick, use subtract operation to avoid a branch
+		 * instruction.
+		 *
 		 * n = (f->mantissa > bfloat_mantissa())
 		 *	? j * 2
 		 *	: j * 2 + 1;
-- 
cgit v1.2.3


From ea8c5356d39048bc94bae068228f51ddbecc6b89 Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Thu, 9 Aug 2018 15:48:49 +0800
Subject: bcache: set max writeback rate when I/O request is idle

Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle")
allows the writeback rate to be faster if there is no I/O request on a
bcache device. It works well if there is only one bcache device attached
to the cache set. If there are many bcache devices attached to a cache
set, it may introduce performance regression because multiple faster
writeback threads of the idle bcache devices will compete the btree level
locks with the bcache device who have I/O requests coming.

This patch fixes the above issue by only permitting fast writebac when
all bcache devices attached on the cache set are idle. And if one of the
bcache devices has new I/O request coming, minimized all writeback
throughput immediately and let PI controller __update_writeback_rate()
to decide the upcoming writeback rate for each bcache device.

Also when all bcache devices are idle, limited wrieback rate to a small
number is wast of thoughput, especially when backing devices are slower
non-rotation devices (e.g. SATA SSD). This patch sets a max writeback
rate for each backing device if the whole cache set is idle. A faster
writeback rate in idle time means new I/Os may have more available space
for dirty data, and people may observe a better write performance then.

Please note bcache may change its cache mode in run time, and this patch
still works if the cache mode is switched from writeback mode and there
is still dirty data on cache.

Fixes: Commit b1092c9af9ed ("bcache: allow quick writeback when backing idle")
Cc: stable@vger.kernel.org #4.16+
Signed-off-by: Coly Li <colyli@suse.de>
Tested-by: Kai Krakow <kai@kaishome.de>
Tested-by: Stefan Priebe <s.priebe@profihost.ag>
Cc: Michael Lyle <mlyle@lyle.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/bcache.h    | 10 ++---
 drivers/md/bcache/request.c   | 59 +++++++++++++++++++++++++++-
 drivers/md/bcache/super.c     |  4 ++
 drivers/md/bcache/sysfs.c     | 15 +++++--
 drivers/md/bcache/util.c      |  2 +-
 drivers/md/bcache/util.h      |  2 +-
 drivers/md/bcache/writeback.c | 91 +++++++++++++++++++++++++++++--------------
 7 files changed, 138 insertions(+), 45 deletions(-)

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h
index b393b3fd06b6..05f82ff6f016 100644
--- a/drivers/md/bcache/bcache.h
+++ b/drivers/md/bcache/bcache.h
@@ -328,13 +328,6 @@ struct cached_dev {
 	 */
 	atomic_t		has_dirty;
 
-	/*
-	 * Set to zero by things that touch the backing volume-- except
-	 * writeback.  Incremented by writeback.  Used to determine when to
-	 * accelerate idle writeback.
-	 */
-	atomic_t		backing_idle;
-
 	struct bch_ratelimit	writeback_rate;
 	struct delayed_work	writeback_rate_update;
 
@@ -515,6 +508,8 @@ struct cache_set {
 	struct cache_accounting accounting;
 
 	unsigned long		flags;
+	atomic_t		idle_counter;
+	atomic_t		at_max_writeback_rate;
 
 	struct cache_sb		sb;
 
@@ -524,6 +519,7 @@ struct cache_set {
 
 	struct bcache_device	**devices;
 	unsigned		devices_max_used;
+	atomic_t		attached_dev_nr;
 	struct list_head	cached_devs;
 	uint64_t		cached_dev_sectors;
 	atomic_long_t		flash_dev_dirty_sectors;
diff --git a/drivers/md/bcache/request.c b/drivers/md/bcache/request.c
index 914d501ad1e0..7dbe8b6316a0 100644
--- a/drivers/md/bcache/request.c
+++ b/drivers/md/bcache/request.c
@@ -1103,6 +1103,44 @@ static void detached_dev_do_request(struct bcache_device *d, struct bio *bio)
 		generic_make_request(bio);
 }
 
+static void quit_max_writeback_rate(struct cache_set *c,
+				    struct cached_dev *this_dc)
+{
+	int i;
+	struct bcache_device *d;
+	struct cached_dev *dc;
+
+	/*
+	 * mutex bch_register_lock may compete with other parallel requesters,
+	 * or attach/detach operations on other backing device. Waiting to
+	 * the mutex lock may increase I/O request latency for seconds or more.
+	 * To avoid such situation, if mutext_trylock() failed, only writeback
+	 * rate of current cached device is set to 1, and __update_write_back()
+	 * will decide writeback rate of other cached devices (remember now
+	 * c->idle_counter is 0 already).
+	 */
+	if (mutex_trylock(&bch_register_lock)) {
+		for (i = 0; i < c->devices_max_used; i++) {
+			if (!c->devices[i])
+				continue;
+
+			if (UUID_FLASH_ONLY(&c->uuids[i]))
+				continue;
+
+			d = c->devices[i];
+			dc = container_of(d, struct cached_dev, disk);
+			/*
+			 * set writeback rate to default minimum value,
+			 * then let update_writeback_rate() to decide the
+			 * upcoming rate.
+			 */
+			atomic_long_set(&dc->writeback_rate.rate, 1);
+		}
+		mutex_unlock(&bch_register_lock);
+	} else
+		atomic_long_set(&this_dc->writeback_rate.rate, 1);
+}
+
 /* Cached devices - read & write stuff */
 
 static blk_qc_t cached_dev_make_request(struct request_queue *q,
@@ -1120,8 +1158,25 @@ static blk_qc_t cached_dev_make_request(struct request_queue *q,
 		return BLK_QC_T_NONE;
 	}
 
-	atomic_set(&dc->backing_idle, 0);
-	generic_start_io_acct(q, bio_op(bio), bio_sectors(bio), &d->disk->part0);
+	if (likely(d->c)) {
+		if (atomic_read(&d->c->idle_counter))
+			atomic_set(&d->c->idle_counter, 0);
+		/*
+		 * If at_max_writeback_rate of cache set is true and new I/O
+		 * comes, quit max writeback rate of all cached devices
+		 * attached to this cache set, and set at_max_writeback_rate
+		 * to false.
+		 */
+		if (unlikely(atomic_read(&d->c->at_max_writeback_rate) == 1)) {
+			atomic_set(&d->c->at_max_writeback_rate, 0);
+			quit_max_writeback_rate(d->c, dc);
+		}
+	}
+
+	generic_start_io_acct(q,
+			      bio_op(bio),
+			      bio_sectors(bio),
+			      &d->disk->part0);
 
 	bio_set_dev(bio, dc->bdev);
 	bio->bi_iter.bi_sector += dc->sb.data_offset;
diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c
index 1e85cbb4c159..55a37641aa95 100644
--- a/drivers/md/bcache/super.c
+++ b/drivers/md/bcache/super.c
@@ -696,6 +696,8 @@ static void bcache_device_detach(struct bcache_device *d)
 {
 	lockdep_assert_held(&bch_register_lock);
 
+	atomic_dec(&d->c->attached_dev_nr);
+
 	if (test_bit(BCACHE_DEV_DETACHING, &d->flags)) {
 		struct uuid_entry *u = d->c->uuids + d->id;
 
@@ -1144,6 +1146,7 @@ int bch_cached_dev_attach(struct cached_dev *dc, struct cache_set *c,
 
 	bch_cached_dev_run(dc);
 	bcache_device_link(&dc->disk, c, "bdev");
+	atomic_inc(&c->attached_dev_nr);
 
 	/* Allow the writeback thread to proceed */
 	up_write(&dc->writeback_lock);
@@ -1696,6 +1699,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb)
 	c->block_bits		= ilog2(sb->block_size);
 	c->nr_uuids		= bucket_bytes(c) / sizeof(struct uuid_entry);
 	c->devices_max_used	= 0;
+	atomic_set(&c->attached_dev_nr, 0);
 	c->btree_pages		= bucket_pages(c);
 	if (c->btree_pages > BTREE_MAX_PAGES)
 		c->btree_pages = max_t(int, c->btree_pages / 4,
diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 3e9d3459a224..6e88142514fb 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -171,7 +171,8 @@ SHOW(__bch_cached_dev)
 	var_printf(writeback_running,	"%i");
 	var_print(writeback_delay);
 	var_print(writeback_percent);
-	sysfs_hprint(writeback_rate,	wb ? dc->writeback_rate.rate << 9 : 0);
+	sysfs_hprint(writeback_rate,
+		     wb ? atomic_long_read(&dc->writeback_rate.rate) << 9 : 0);
 	sysfs_hprint(io_errors,		atomic_read(&dc->io_errors));
 	sysfs_printf(io_error_limit,	"%i", dc->error_limit);
 	sysfs_printf(io_disable,	"%i", dc->io_disable);
@@ -193,7 +194,9 @@ SHOW(__bch_cached_dev)
 		 * Except for dirty and target, other values should
 		 * be 0 if writeback is not running.
 		 */
-		bch_hprint(rate, wb ? dc->writeback_rate.rate << 9 : 0);
+		bch_hprint(rate,
+			   wb ? atomic_long_read(&dc->writeback_rate.rate) << 9
+			      : 0);
 		bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9);
 		bch_hprint(target, dc->writeback_rate_target << 9);
 		bch_hprint(proportional,
@@ -261,8 +264,12 @@ STORE(__cached_dev)
 
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
 
-	sysfs_strtoul_clamp(writeback_rate,
-			    dc->writeback_rate.rate, 1, INT_MAX);
+	if (attr == &sysfs_writeback_rate) {
+		int v;
+
+		sysfs_strtoul_clamp(writeback_rate, v, 1, INT_MAX);
+		atomic_long_set(&dc->writeback_rate.rate, v);
+	}
 
 	sysfs_strtoul_clamp(writeback_rate_update_seconds,
 			    dc->writeback_rate_update_seconds,
diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c
index fc479b026d6d..b15256bcf0e7 100644
--- a/drivers/md/bcache/util.c
+++ b/drivers/md/bcache/util.c
@@ -200,7 +200,7 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done)
 {
 	uint64_t now = local_clock();
 
-	d->next += div_u64(done * NSEC_PER_SEC, d->rate);
+	d->next += div_u64(done * NSEC_PER_SEC, atomic_long_read(&d->rate));
 
 	/* Bound the time.  Don't let us fall further than 2 seconds behind
 	 * (this prevents unnecessary backlog that would make it impossible
diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h
index cced87f8eb27..f7b0133c9d2f 100644
--- a/drivers/md/bcache/util.h
+++ b/drivers/md/bcache/util.h
@@ -442,7 +442,7 @@ struct bch_ratelimit {
 	 * Rate at which we want to do work, in units per second
 	 * The units here correspond to the units passed to bch_next_delay()
 	 */
-	uint32_t		rate;
+	atomic_long_t		rate;
 };
 
 static inline void bch_ratelimit_reset(struct bch_ratelimit *d)
diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c
index 912e969fedba..481d4cf38ac0 100644
--- a/drivers/md/bcache/writeback.c
+++ b/drivers/md/bcache/writeback.c
@@ -104,11 +104,56 @@ static void __update_writeback_rate(struct cached_dev *dc)
 
 	dc->writeback_rate_proportional = proportional_scaled;
 	dc->writeback_rate_integral_scaled = integral_scaled;
-	dc->writeback_rate_change = new_rate - dc->writeback_rate.rate;
-	dc->writeback_rate.rate = new_rate;
+	dc->writeback_rate_change = new_rate -
+			atomic_long_read(&dc->writeback_rate.rate);
+	atomic_long_set(&dc->writeback_rate.rate, new_rate);
 	dc->writeback_rate_target = target;
 }
 
+static bool set_at_max_writeback_rate(struct cache_set *c,
+				       struct cached_dev *dc)
+{
+	/*
+	 * Idle_counter is increased everytime when update_writeback_rate() is
+	 * called. If all backing devices attached to the same cache set have
+	 * identical dc->writeback_rate_update_seconds values, it is about 6
+	 * rounds of update_writeback_rate() on each backing device before
+	 * c->at_max_writeback_rate is set to 1, and then max wrteback rate set
+	 * to each dc->writeback_rate.rate.
+	 * In order to avoid extra locking cost for counting exact dirty cached
+	 * devices number, c->attached_dev_nr is used to calculate the idle
+	 * throushold. It might be bigger if not all cached device are in write-
+	 * back mode, but it still works well with limited extra rounds of
+	 * update_writeback_rate().
+	 */
+	if (atomic_inc_return(&c->idle_counter) <
+	    atomic_read(&c->attached_dev_nr) * 6)
+		return false;
+
+	if (atomic_read(&c->at_max_writeback_rate) != 1)
+		atomic_set(&c->at_max_writeback_rate, 1);
+
+	atomic_long_set(&dc->writeback_rate.rate, INT_MAX);
+
+	/* keep writeback_rate_target as existing value */
+	dc->writeback_rate_proportional = 0;
+	dc->writeback_rate_integral_scaled = 0;
+	dc->writeback_rate_change = 0;
+
+	/*
+	 * Check c->idle_counter and c->at_max_writeback_rate agagain in case
+	 * new I/O arrives during before set_at_max_writeback_rate() returns.
+	 * Then the writeback rate is set to 1, and its new value should be
+	 * decided via __update_writeback_rate().
+	 */
+	if ((atomic_read(&c->idle_counter) <
+	     atomic_read(&c->attached_dev_nr) * 6) ||
+	    !atomic_read(&c->at_max_writeback_rate))
+		return false;
+
+	return true;
+}
+
 static void update_writeback_rate(struct work_struct *work)
 {
 	struct cached_dev *dc = container_of(to_delayed_work(work),
@@ -136,13 +181,20 @@ static void update_writeback_rate(struct work_struct *work)
 		return;
 	}
 
-	down_read(&dc->writeback_lock);
-
-	if (atomic_read(&dc->has_dirty) &&
-	    dc->writeback_percent)
-		__update_writeback_rate(dc);
+	if (atomic_read(&dc->has_dirty) && dc->writeback_percent) {
+		/*
+		 * If the whole cache set is idle, set_at_max_writeback_rate()
+		 * will set writeback rate to a max number. Then it is
+		 * unncessary to update writeback rate for an idle cache set
+		 * in maximum writeback rate number(s).
+		 */
+		if (!set_at_max_writeback_rate(c, dc)) {
+			down_read(&dc->writeback_lock);
+			__update_writeback_rate(dc);
+			up_read(&dc->writeback_lock);
+		}
+	}
 
-	up_read(&dc->writeback_lock);
 
 	/*
 	 * CACHE_SET_IO_DISABLE might be set via sysfs interface,
@@ -422,27 +474,6 @@ static void read_dirty(struct cached_dev *dc)
 
 		delay = writeback_delay(dc, size);
 
-		/* If the control system would wait for at least half a
-		 * second, and there's been no reqs hitting the backing disk
-		 * for awhile: use an alternate mode where we have at most
-		 * one contiguous set of writebacks in flight at a time.  If
-		 * someone wants to do IO it will be quick, as it will only
-		 * have to contend with one operation in flight, and we'll
-		 * be round-tripping data to the backing disk as quickly as
-		 * it can accept it.
-		 */
-		if (delay >= HZ / 2) {
-			/* 3 means at least 1.5 seconds, up to 7.5 if we
-			 * have slowed way down.
-			 */
-			if (atomic_inc_return(&dc->backing_idle) >= 3) {
-				/* Wait for current I/Os to finish */
-				closure_sync(&cl);
-				/* And immediately launch a new set. */
-				delay = 0;
-			}
-		}
-
 		while (!kthread_should_stop() &&
 		       !test_bit(CACHE_SET_IO_DISABLE, &dc->disk.c->flags) &&
 		       delay) {
@@ -741,7 +772,7 @@ void bch_cached_dev_writeback_init(struct cached_dev *dc)
 	dc->writeback_running		= true;
 	dc->writeback_percent		= 10;
 	dc->writeback_delay		= 30;
-	dc->writeback_rate.rate		= 1024;
+	atomic_long_set(&dc->writeback_rate.rate, 1024);
 	dc->writeback_rate_minimum	= 8;
 
 	dc->writeback_rate_update_seconds = WRITEBACK_RATE_UPDATE_SECS_DEFAULT;
-- 
cgit v1.2.3


From e921efeb07048a6f5daa540e5f04f19ec9360da2 Mon Sep 17 00:00:00 2001
From: Shenghui Wang <shhuiw@foxmail.com>
Date: Thu, 9 Aug 2018 15:48:50 +0800
Subject: bcache: make the pr_err statement used for ENOENT only in
 sysfs_attatch section

The pr_err statement in the code for sysfs_attatch section would run
for various error codes, which maybe confusing.

E.g,

Run the command twice:
   echo 796b5c05-b03c-4bc7-9cbd-a8df5e8be891 > \
				/sys/block/bcache0/bcache/attach
   [the backing dev got attached on the first run]
   echo 796b5c05-b03c-4bc7-9cbd-a8df5e8be891 > \
				/sys/block/bcache0/bcache/attach

In dmesg, after the command run twice, we can get:
	bcache: bch_cached_dev_attach() Can't attach sda6: already attached
	bcache: __cached_dev_store() Can't attach 796b5c05-b03c-4bc7-9cbd-\
a8df5e8be891
               : cache set not found
The first statement in the message was right, but the second was
confusing.

bch_cached_dev_attach has various pr_ statements for various error
codes, except ENOENT.

After the change, rerun above command twice:
	echo 796b5c05-b03c-4bc7-9cbd-a8df5e8be891 > \
			/sys/block/bcache0/bcache/attach
	echo 796b5c05-b03c-4bc7-9cbd-a8df5e8be891 > \
			/sys/block/bcache0/bcache/attach

In dmesg we only got:
	bcache: bch_cached_dev_attach() Can't attach sda6: already attached
No confusing "cache set not found" message anymore.

And for some not exist SET-UUID:
	echo 796b5c05-b03c-4bc7-9cbd-a8df5e8be898 > \
			/sys/block/bcache0/bcache/attach
In dmesg we can get:
	bcache: __cached_dev_store() Can't attach 796b5c05-b03c-4bc7-9cbd-\
a8df5e8be898
	               : cache set not found

Signed-off-by: Shenghui Wang <shhuiw@foxmail.com>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/sysfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 6e88142514fb..22f8565d2bf1 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -351,8 +351,8 @@ STORE(__cached_dev)
 			if (!v)
 				return size;
 		}
-
-		pr_err("Can't attach %s: cache set not found", buf);
+		if (v == -ENOENT)
+			pr_err("Can't attach %s: cache set not found", buf);
 		return v;
 	}
 
-- 
cgit v1.2.3


From cbb751c060fe61140e3f23dc7cd95190bba4c89e Mon Sep 17 00:00:00 2001
From: Shenghui Wang <shhuiw@foxmail.com>
Date: Thu, 9 Aug 2018 15:48:51 +0800
Subject: bcache: trivial - remove tailing backslash in macro BTREE_FLAG

Remove the tailing backslash in macro BTREE_FLAG in btree.h

Signed-off-by: Shenghui Wang <shhuiw@foxmail.com>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/btree.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/bcache/btree.h b/drivers/md/bcache/btree.h
index d211e2c25b6b..68e9d926134d 100644
--- a/drivers/md/bcache/btree.h
+++ b/drivers/md/bcache/btree.h
@@ -152,7 +152,7 @@ static inline bool btree_node_ ## flag(struct btree *b)			\
 {	return test_bit(BTREE_NODE_ ## flag, &b->flags); }		\
 									\
 static inline void set_btree_node_ ## flag(struct btree *b)		\
-{	set_bit(BTREE_NODE_ ## flag, &b->flags); }			\
+{	set_bit(BTREE_NODE_ ## flag, &b->flags); }
 
 enum btree_flags {
 	BTREE_NODE_io_error,
-- 
cgit v1.2.3


From d6c02a9beb67f13d5f14f23e72fa9981e8b84477 Mon Sep 17 00:00:00 2001
From: Greg Edwards <gedwards@ddn.com>
Date: Wed, 8 Aug 2018 13:27:53 -0600
Subject: block: bvec_nr_vecs() returns value for wrong slab

In commit ed996a52c868 ("block: simplify and cleanup bvec pool
handling"), the value of the slab index is incremented by one in
bvec_alloc() after the allocation is done to indicate an index value of
0 does not need to be later freed.

bvec_nr_vecs() was not updated accordingly, and thus returns the wrong
value.  Decrement idx before performing the lookup.

Fixes: ed996a52c868 ("block: simplify and cleanup bvec pool handling")
Signed-off-by: Greg Edwards <gedwards@ddn.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bio.c b/block/bio.c
index b832151cd0bf..04969b392c72 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -158,7 +158,7 @@ out:
 
 unsigned int bvec_nr_vecs(unsigned short idx)
 {
-	return bvec_slabs[idx].nr_vecs;
+	return bvec_slabs[--idx].nr_vecs;
 }
 
 void bvec_free(mempool_t *pool, struct bio_vec *bv, unsigned int idx)
-- 
cgit v1.2.3


From d263ed9926823c462f99a7679e18f0c9e5b8550d Mon Sep 17 00:00:00 2001
From: Jianchao Wang <jianchao.w.wang@oracle.com>
Date: Thu, 9 Aug 2018 08:34:17 -0600
Subject: blk-mq: count the hctx as active before allocating tag

Currently, we count the hctx as active after allocate driver tag
successfully. If a previously inactive hctx try to get tag first
time, it may fails and need to wait. However, due to the stale tag
->active_queues, the other shared-tags users are still able to
occupy all driver tags while there is someone waiting for tag.
Consequently, even if the previously inactive hctx is waked up, it
still may not be able to get a tag and could be starved.

To fix it, we count the hctx as active before try to allocate driver
tag, then when it is waiting the tag, the other shared-tag users
will reserve budget for it.

Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Jianchao Wang <jianchao.w.wang@oracle.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-tag.c | 3 +++
 block/blk-mq.c     | 8 ++++++--
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
index c43b3398d7b4..c0c4e63583ae 100644
--- a/block/blk-mq-tag.c
+++ b/block/blk-mq-tag.c
@@ -23,6 +23,9 @@ bool blk_mq_has_free_tags(struct blk_mq_tags *tags)
 
 /*
  * If a previously inactive queue goes active, bump the active user count.
+ * We need to do this before try to allocate driver tag, then even if fail
+ * to get tag when first time, the other shared-tag users could reserve
+ * budget for it.
  */
 bool __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
 {
diff --git a/block/blk-mq.c b/block/blk-mq.c
index e13bdc2707ce..5efd789910e2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -285,7 +285,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
 		rq->tag = -1;
 		rq->internal_tag = tag;
 	} else {
-		if (blk_mq_tag_busy(data->hctx)) {
+		if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
 			rq_flags = RQF_MQ_INFLIGHT;
 			atomic_inc(&data->hctx->nr_active);
 		}
@@ -367,6 +367,8 @@ static struct request *blk_mq_get_request(struct request_queue *q,
 		if (!op_is_flush(op) && e->type->ops.mq.limit_depth &&
 		    !(data->flags & BLK_MQ_REQ_RESERVED))
 			e->type->ops.mq.limit_depth(op, data);
+	} else {
+		blk_mq_tag_busy(data->hctx);
 	}
 
 	tag = blk_mq_get_tag(data);
@@ -971,6 +973,7 @@ bool blk_mq_get_driver_tag(struct request *rq)
 		.hctx = blk_mq_map_queue(rq->q, rq->mq_ctx->cpu),
 		.flags = BLK_MQ_REQ_NOWAIT,
 	};
+	bool shared;
 
 	if (rq->tag != -1)
 		goto done;
@@ -978,9 +981,10 @@ bool blk_mq_get_driver_tag(struct request *rq)
 	if (blk_mq_tag_is_reserved(data.hctx->sched_tags, rq->internal_tag))
 		data.flags |= BLK_MQ_REQ_RESERVED;
 
+	shared = blk_mq_tag_busy(data.hctx);
 	rq->tag = blk_mq_get_tag(&data);
 	if (rq->tag >= 0) {
-		if (blk_mq_tag_busy(data.hctx)) {
+		if (shared) {
 			rq->rq_flags |= RQF_MQ_INFLIGHT;
 			atomic_inc(&data.hctx->nr_active);
 		}
-- 
cgit v1.2.3


From 27a8aea13053700ad2a08189024df7e341d1ee51 Mon Sep 17 00:00:00 2001
From: Winnie Chang <winnie.chang@cypress.com>
Date: Tue, 7 Aug 2018 21:19:41 -0500
Subject: brcmfmac: fix brcmf_wiphy_wowl_params() NULL pointer dereference

The kernel BUG happens when wowl is enabled from firmware. In
brcmf_wiphy_wowl_params(), cfg is a NULL pointer because it is
drvr->config returned from wiphy_to_cfg(), and drvr->config is not set
yet. To fix it, set drvr->config before brcmf_setup_wiphy() which
calls brcmf_wiphy_wowl_params().

Fixes: 856d5a011c86 ("brcmfmac: allocate struct brcmf_pub instance using wiphy_new()")
Signed-off-by: Winnie Chang <winnie.chang@cypress.com>
Signed-off-by: Chi-Hsien Lin <chi-hsien.lin@cypress.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
index 24c4e18e7d80..5444e6213d45 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
@@ -6926,15 +6926,15 @@ struct brcmf_cfg80211_info *brcmf_cfg80211_attach(struct brcmf_pub *drvr,
 	cfg->d11inf.io_type = (u8)io_type;
 	brcmu_d11_attach(&cfg->d11inf);
 
-	err = brcmf_setup_wiphy(wiphy, ifp);
-	if (err < 0)
-		goto priv_out;
-
 	/* regulatory notifer below needs access to cfg so
 	 * assign it now.
 	 */
 	drvr->config = cfg;
 
+	err = brcmf_setup_wiphy(wiphy, ifp);
+	if (err < 0)
+		goto priv_out;
+
 	brcmf_dbg(INFO, "Registering custom regulatory\n");
 	wiphy->reg_notifier = brcmf_cfg80211_reg_notifier;
 	wiphy->regulatory_flags |= REGULATORY_CUSTOM_REG;
-- 
cgit v1.2.3


From 5dc5bf2899a505085492b1273d34d4a51c41e093 Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 7 Aug 2018 10:43:09 +0200
Subject: mt76x0: correct type for eeprom gain value

Change type to u8 to allow sanity check agaist 0xff;

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: e87b5039511a ("mt76x0: eeprom files")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index 1ecd018f12b8..9ea5f5ebd3be 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -241,7 +241,7 @@ mt76x0_set_rf_freq_off(struct mt76x0_dev *dev, u8 *eeprom)
 static void
 mt76x0_set_lna_gain(struct mt76x0_dev *dev, u8 *eeprom)
 {
-	s8 gain;
+	u8 gain;
 
 	dev->ee->lna_gain_2ghz = eeprom[MT_EE_LNA_GAIN_2GHZ];
 	dev->ee->lna_gain_5ghz[0] = eeprom[MT_EE_LNA_GAIN_5GHZ_0];
-- 
cgit v1.2.3


From 1b622bd59e9fc4375febf8697684746211eaeb4a Mon Sep 17 00:00:00 2001
From: Stanislaw Gruszka <sgruszka@redhat.com>
Date: Tue, 7 Aug 2018 10:43:37 +0200
Subject: mt76x0: perform mt76x0_mac_set_ampdu_factor

Remove return added accidentally in mt76x0_mac_set_ampdu_factor.

Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: a77443498137 ("mt76x0: mac files")
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/mac.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
index 95f28492a843..91a84be36d3b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/mac.c
@@ -424,8 +424,6 @@ void mt76x0_mac_set_ampdu_factor(struct mt76x0_dev *dev)
 	u8 min_factor = 3;
 	int i;
 
-	return;
-
 	rcu_read_lock();
 	for (i = 0; i < ARRAY_SIZE(dev->wcid); i++) {
 		wcid = rcu_dereference(dev->wcid[i]);
-- 
cgit v1.2.3


From 17ad18fd12a35bf84109741415594e21f2577e5e Mon Sep 17 00:00:00 2001
From: Kees Cook <keescook@chromium.org>
Date: Tue, 7 Aug 2018 15:50:40 -0700
Subject: mt76x0: Remove VLA usage

Even with "const" variables, the compiler will generate warnings about
VLA usage. In the quest to remove all VLAs from the kernel[1], this uses
a #define instead of a const to do the array sizing.

[1] https://lkml.kernel.org/r/CA+55aFzCG-zNmZwX4A2FQpadafLfEzK6CC=qPXydAacU1RqZWA@mail.gmail.com

Fixes: e87b5039511a ("mt76x0: eeprom files")
Signed-off-by: Kees Cook <keescook@chromium.org>
Acked-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
index 9ea5f5ebd3be..36da1e6bc21a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/eeprom.c
@@ -81,15 +81,15 @@ mt76x0_efuse_read(struct mt76x0_dev *dev, u16 addr, u8 *data,
 	return 0;
 }
 
+#define MT_MAP_READS	DIV_ROUND_UP(MT_EFUSE_USAGE_MAP_SIZE, 16)
 static int
 mt76x0_efuse_physical_size_check(struct mt76x0_dev *dev)
 {
-	const int map_reads = DIV_ROUND_UP(MT_EFUSE_USAGE_MAP_SIZE, 16);
-	u8 data[map_reads * 16];
+	u8 data[MT_MAP_READS * 16];
 	int ret, i;
 	u32 start = 0, end = 0, cnt_free;
 
-	for (i = 0; i < map_reads; i++) {
+	for (i = 0; i < MT_MAP_READS; i++) {
 		ret = mt76x0_efuse_read(dev, MT_EE_USAGE_MAP_START + i * 16,
 					 data + i * 16, MT_EE_PHYSICAL_READ);
 		if (ret)
-- 
cgit v1.2.3


From b1f4267cc5448d20ae0c515a74141e74365e78a3 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Aug 2018 07:47:28 -0700
Subject: block: Remove two superfluous #include directives

Commit 12f5b9314545 ("blk-mq: Remove generation seqeunce") removed the
only seqcount_t and u64_stats_sync instances from <linux/blkdev.h> but
did not remove the corresponding #include directives. Since these
include directives are no longer needed, remove them.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Jianchao Wang <jianchao.w.wang@oracle.com>
Cc: Hannes Reinecke <hare@suse.com>,
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 050d599f5ea9..d6869e0e2b64 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -27,8 +27,6 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
-#include <linux/seqlock.h>
-#include <linux/u64_stats_sync.h>
 
 struct module;
 struct scsi_ioctl_command;
-- 
cgit v1.2.3


From 1ec49a236565060566be547b6e050bb414d0da96 Mon Sep 17 00:00:00 2001
From: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Date: Wed, 8 Aug 2018 16:16:54 -0400
Subject: mt76: fix build for MediaTek MT7610U USB wireless dongle

The mt76x0 driver requires the mt76 core driver to actually function.
So add a 'select' to avoid embarrassing 'symbol unknown' errors
when attempting to modprobe it in a module tree that doesn't
include mt76.ko

Signed-off-by: Valdis Kletnieks <valdis.kletnieks@vt.edu>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/mediatek/mt76/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/Kconfig b/drivers/net/wireless/mediatek/mt76/Kconfig
index 850611ad347a..b6c5f17dca30 100644
--- a/drivers/net/wireless/mediatek/mt76/Kconfig
+++ b/drivers/net/wireless/mediatek/mt76/Kconfig
@@ -11,6 +11,7 @@ config MT76x2_COMMON
 
 config MT76x0U
 	tristate "MediaTek MT76x0U (USB) support"
+	select MT76_CORE
 	depends on MAC80211
 	depends on USB
 	help
-- 
cgit v1.2.3


From 6bad9b210a228d2fe0e0efe26d9b115348529cee Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Aug 2018 07:53:36 -0700
Subject: blkcg: Introduce blkg_root_lookup()

This new function will be used in a later patch to verify whether a
queue has been dissociated from the cgroup controller before being
released.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Alexandru Moise <00moses.alexander00@gmail.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-cgroup.h | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index f7b910768306..1361cfc9b878 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -341,6 +341,23 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 	return __blkg_lookup(blkcg, q, false);
 }
 
+/**
+ * blkg_lookup - look up blkg for the specified request queue
+ * @q: request_queue of interest
+ *
+ * Lookup blkg for @q at the root level. See also blkg_lookup().
+ */
+static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q)
+{
+	struct blkcg_gq *blkg;
+
+	rcu_read_lock();
+	blkg = blkg_lookup(&blkcg_root, q);
+	rcu_read_unlock();
+
+	return blkg;
+}
+
 /**
  * blkg_to_pdata - get policy private data
  * @blkg: blkg of interest
@@ -864,6 +881,7 @@ static inline bool blk_cgroup_congested(void) { return false; }
 static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
 
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
+static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) { return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
 static inline void blkcg_exit_queue(struct request_queue *q) { }
-- 
cgit v1.2.3


From 4cf6324b17e96b7b7ab4021c6929500934d46750 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Aug 2018 07:53:37 -0700
Subject: block: Introduce blk_exit_queue()

This patch does not change any functionality.

Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Omar Sandoval <osandov@fb.com>
Cc: Alexandru Moise <00moses.alexander00@gmail.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-core.c | 54 ++++++++++++++++++++++++++++++------------------------
 block/blk.h      |  1 +
 2 files changed, 31 insertions(+), 24 deletions(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index f9ad73d8573c..49af34bf2119 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -715,6 +715,35 @@ void blk_set_queue_dying(struct request_queue *q)
 }
 EXPORT_SYMBOL_GPL(blk_set_queue_dying);
 
+/* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */
+void blk_exit_queue(struct request_queue *q)
+{
+	/*
+	 * Since the I/O scheduler exit code may access cgroup information,
+	 * perform I/O scheduler exit before disassociating from the block
+	 * cgroup controller.
+	 */
+	if (q->elevator) {
+		ioc_clear_queue(q);
+		elevator_exit(q, q->elevator);
+		q->elevator = NULL;
+	}
+
+	/*
+	 * Remove all references to @q from the block cgroup controller before
+	 * restoring @q->queue_lock to avoid that restoring this pointer causes
+	 * e.g. blkcg_print_blkgs() to crash.
+	 */
+	blkcg_exit_queue(q);
+
+	/*
+	 * Since the cgroup code may dereference the @q->backing_dev_info
+	 * pointer, only decrease its reference count after having removed the
+	 * association with the block cgroup controller.
+	 */
+	bdi_put(q->backing_dev_info);
+}
+
 /**
  * blk_cleanup_queue - shutdown a request queue
  * @q: request queue to shutdown
@@ -784,30 +813,7 @@ void blk_cleanup_queue(struct request_queue *q)
 	 */
 	WARN_ON_ONCE(q->kobj.state_in_sysfs);
 
-	/*
-	 * Since the I/O scheduler exit code may access cgroup information,
-	 * perform I/O scheduler exit before disassociating from the block
-	 * cgroup controller.
-	 */
-	if (q->elevator) {
-		ioc_clear_queue(q);
-		elevator_exit(q, q->elevator);
-		q->elevator = NULL;
-	}
-
-	/*
-	 * Remove all references to @q from the block cgroup controller before
-	 * restoring @q->queue_lock to avoid that restoring this pointer causes
-	 * e.g. blkcg_print_blkgs() to crash.
-	 */
-	blkcg_exit_queue(q);
-
-	/*
-	 * Since the cgroup code may dereference the @q->backing_dev_info
-	 * pointer, only decrease its reference count after having removed the
-	 * association with the block cgroup controller.
-	 */
-	bdi_put(q->backing_dev_info);
+	blk_exit_queue(q);
 
 	if (q->mq_ops)
 		blk_mq_free_queue(q);
diff --git a/block/blk.h b/block/blk.h
index 69b14cd2bb22..d4d67e948920 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -130,6 +130,7 @@ void blk_free_flush_queue(struct blk_flush_queue *q);
 int blk_init_rl(struct request_list *rl, struct request_queue *q,
 		gfp_t gfp_mask);
 void blk_exit_rl(struct request_queue *q, struct request_list *rl);
+void blk_exit_queue(struct request_queue *q);
 void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
 			struct bio *bio);
 void blk_queue_bypass_start(struct request_queue *q);
-- 
cgit v1.2.3


From 24ecc3585348b616993a3c4d6dc2c6b8007e358c Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Thu, 9 Aug 2018 07:53:38 -0700
Subject: block: Ensure that a request queue is dissociated from the cgroup
 controller

Several block drivers call alloc_disk() followed by put_disk() if
something fails before device_add_disk() is called without calling
blk_cleanup_queue(). Make sure that also for this scenario a request
queue is dissociated from the cgroup controller. This patch avoids
that loading the parport_pc, paride and pf drivers triggers the
following kernel crash:

BUG: KASAN: null-ptr-deref in pi_init+0x42e/0x580 [paride]
Read of size 4 at addr 0000000000000008 by task modprobe/744
Call Trace:
dump_stack+0x9a/0xeb
kasan_report+0x139/0x350
pi_init+0x42e/0x580 [paride]
pf_init+0x2bb/0x1000 [pf]
do_one_initcall+0x8e/0x405
do_init_module+0xd9/0x2f2
load_module+0x3ab4/0x4700
SYSC_finit_module+0x176/0x1a0
do_syscall_64+0xee/0x2b0
entry_SYSCALL_64_after_hwframe+0x42/0xb7

Reported-by: Alexandru Moise <00moses.alexander00@gmail.com>
Fixes: a063057d7c73 ("block: Fix a race between request queue removal and the block cgroup controller") # v4.17
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Tested-by: Alexandru Moise <00moses.alexander00@gmail.com>
Reviewed-by: Johannes Thumshirn <jthumshirn@suse.de>
Cc: Tejun Heo <tj@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ming Lei <ming.lei@redhat.com>
Cc: Alexandru Moise <00moses.alexander00@gmail.com>
Cc: Joseph Qi <joseph.qi@linux.alibaba.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-sysfs.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 49c29a5d06bb..380bc284ced1 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -802,6 +802,21 @@ static void __blk_release_queue(struct work_struct *work)
 		blk_stat_remove_callback(q, q->poll_cb);
 	blk_stat_free_callback(q->poll_cb);
 
+	if (!blk_queue_dead(q)) {
+		/*
+		 * Last reference was dropped without having called
+		 * blk_cleanup_queue().
+		 */
+		WARN_ONCE(blk_queue_init_done(q),
+			  "request queue %p has been registered but blk_cleanup_queue() has not been called for that queue\n",
+			  q);
+		blk_exit_queue(q);
+	}
+
+	WARN(blkg_root_lookup(q),
+	     "request queue %p is being released but it has not yet been removed from the blkcg controller\n",
+	     q);
+
 	blk_free_queue_stats(q->stats);
 
 	blk_exit_rl(q, &q->root_rl);
-- 
cgit v1.2.3


From 35204d0aa83ff4f8bdab7b0eab927dcaa7c4b7f6 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 08:46:36 +0100
Subject: rsi: remove redundant variables bss, wh and temp_flash_content

Variables bss, wh and temp_flash_content are being assigned but are
never used hence they are redundant and can be removed.

Cleans up clang warnings:
warning: variable 'bss' set but not used [-Wunused-but-set-variable]
warning: variable 'wh' set but not used [-Wunused-but-set-variable]
warning: variable 'temp_flash_content' set but not used
 [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/rsi/rsi_91x_hal.c | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/net/wireless/rsi/rsi_91x_hal.c b/drivers/net/wireless/rsi/rsi_91x_hal.c
index 27e6baf12e90..01edf960ff3c 100644
--- a/drivers/net/wireless/rsi/rsi_91x_hal.c
+++ b/drivers/net/wireless/rsi/rsi_91x_hal.c
@@ -57,7 +57,6 @@ int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 	struct ieee80211_vif *vif;
 	struct rsi_mgmt_desc *mgmt_desc;
 	struct skb_info *tx_params;
-	struct ieee80211_bss_conf *bss = NULL;
 	struct rsi_xtended_desc *xtend_desc = NULL;
 	u8 header_size;
 	u32 dword_align_bytes = 0;
@@ -91,7 +90,6 @@ int rsi_prepare_mgmt_desc(struct rsi_common *common, struct sk_buff *skb)
 
 	tx_params->internal_hdr_size = header_size;
 	memset(&skb->data[0], 0, header_size);
-	bss = &vif->bss_conf;
 	wh = (struct ieee80211_hdr *)&skb->data[header_size];
 
 	mgmt_desc = (struct rsi_mgmt_desc *)skb->data;
@@ -148,7 +146,6 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 	struct ieee80211_hdr *wh = NULL;
 	struct ieee80211_tx_info *info;
 	struct skb_info *tx_params;
-	struct ieee80211_bss_conf *bss;
 	struct rsi_data_desc *data_desc;
 	struct rsi_xtended_desc *xtend_desc;
 	u8 ieee80211_size = MIN_802_11_HDR_LEN;
@@ -159,7 +156,6 @@ int rsi_prepare_data_desc(struct rsi_common *common, struct sk_buff *skb)
 
 	info = IEEE80211_SKB_CB(skb);
 	vif = info->control.vif;
-	bss = &vif->bss_conf;
 	tx_params = (struct skb_info *)info->driver_data;
 
 	header_size = FRAME_DESC_SZ + sizeof(struct rsi_xtended_desc);
@@ -288,7 +284,6 @@ int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb)
 	struct ieee80211_tx_info *info;
 	struct skb_info *tx_params;
 	struct ieee80211_bss_conf *bss;
-	struct ieee80211_hdr *wh;
 	int status = -EINVAL;
 	u8 header_size;
 
@@ -304,7 +299,6 @@ int rsi_send_data_pkt(struct rsi_common *common, struct sk_buff *skb)
 	bss = &vif->bss_conf;
 	tx_params = (struct skb_info *)info->driver_data;
 	header_size = tx_params->internal_hdr_size;
-	wh = (struct ieee80211_hdr *)&skb->data[header_size];
 
 	if (((vif->type == NL80211_IFTYPE_STATION) ||
 	     (vif->type == NL80211_IFTYPE_P2P_CLIENT)) &&
@@ -747,13 +741,11 @@ static int ping_pong_write(struct rsi_hw *adapter, u8 cmd, u8 *addr, u32 size)
 static int auto_fw_upgrade(struct rsi_hw *adapter, u8 *flash_content,
 			   u32 content_size)
 {
-	u8 cmd, *temp_flash_content;
+	u8 cmd;
 	u32 temp_content_size, num_flash, index;
 	u32 flash_start_address;
 	int status;
 
-	temp_flash_content = flash_content;
-
 	if (content_size > MAX_FLASH_FILE_SIZE) {
 		rsi_dbg(ERR_ZONE,
 			"%s: Flash Content size is more than 400K %u\n",
-- 
cgit v1.2.3


From 26b701adc37855a51af3e998241791fae94f99ab Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 3 Aug 2018 14:42:24 +0100
Subject: iwlegacy: fix spelling mistake "acumulative" -> "accumulative"

fix spelling mistake in rx stats text

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/intel/iwlegacy/3945-debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/3945-debug.c b/drivers/net/wireless/intel/iwlegacy/3945-debug.c
index c1b4441fb8b2..a2960032be81 100644
--- a/drivers/net/wireless/intel/iwlegacy/3945-debug.c
+++ b/drivers/net/wireless/intel/iwlegacy/3945-debug.c
@@ -95,7 +95,7 @@ il3945_ucode_rx_stats_read(struct file *file, char __user *user_buf,
 	pos +=
 	    scnprintf(buf + pos, bufsz - pos,
 		      "%-32s     current"
-		      "acumulative       delta         max\n",
+		      "accumulative      delta         max\n",
 		      "Statistics_Rx - OFDM:");
 	pos +=
 	    scnprintf(buf + pos, bufsz - pos,
-- 
cgit v1.2.3


From ad2e6d23bdadd7db7086c578f3c77f244d405b3b Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 6 Aug 2018 12:54:40 +0800
Subject: rtlwifi: btcoex: Fix if == else warnings in halbtc8723b2ant.c

Fix following coccinelle warning:

./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:2952:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:2961:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3011:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3020:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3439:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3448:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3339:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3348:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3074:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3083:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3192:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3201:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3267:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3276:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3124:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:3133:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:2821:2-4: WARNING: possible condition with no effect (if == else)
./drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c:2830:2-4: WARNING: possible condition with no effect (if == else)

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 .../realtek/rtlwifi/btcoexist/halbtc8723b2ant.c    | 180 +++++----------------
 1 file changed, 36 insertions(+), 144 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
index df3facc8e5a4..6597f7cb3411 100644
--- a/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
+++ b/drivers/net/wireless/realtek/rtlwifi/btcoexist/halbtc8723b2ant.c
@@ -2818,23 +2818,11 @@ static void btc8723b2ant_action_sco(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
@@ -2949,23 +2937,11 @@ static void btc8723b2ant_action_a2dp(struct btc_coexist *btcoexist)
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3008,23 +2984,11 @@ static void btc8723b2ant_action_a2dp_pan_hs(struct btc_coexist *btcoexist)
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3071,23 +3035,11 @@ static void btc8723b2ant_action_pan_edr(struct btc_coexist *btcoexist)
 	/* sw mechanism */
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3121,23 +3073,11 @@ static void btc8723b2ant_action_pan_hs(struct btc_coexist *btcoexist)
 
 	btcoexist->btc_get(btcoexist, BTC_GET_U4_WIFI_BW, &wifi_bw);
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3189,23 +3129,11 @@ static void btc8723b2ant_action_pan_edr_a2dp(struct btc_coexist *btcoexist)
 
 	/* sw mechanism	*/
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, false,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, false,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, false,
+					  false, false);
 	}
 }
 
@@ -3264,23 +3192,11 @@ static void btc8723b2ant_action_pan_edr_hid(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
@@ -3336,23 +3252,11 @@ static void btc8723b2ant_action_hid_a2dp_pan_edr(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
@@ -3436,23 +3340,11 @@ static void btc8723b2ant_action_hid_a2dp(struct btc_coexist *btcoexist)
 
 	/* sw mechanism */
 	if (BTC_WIFI_BW_HT40 == wifi_bw) {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, true, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, true, true,
+					  false, false);
 	} else {
-		if ((wifi_rssi_state == BTC_RSSI_STATE_HIGH) ||
-		    (wifi_rssi_state == BTC_RSSI_STATE_STAY_HIGH)) {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		} else {
-			btc8723b2ant_sw_mechanism(btcoexist, false, true,
-						  false, false);
-		}
+		btc8723b2ant_sw_mechanism(btcoexist, false, true,
+					  false, false);
 	}
 }
 
-- 
cgit v1.2.3


From c7743c428111912fffceb38b860024f7e33b3e3c Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Sat, 4 Aug 2018 19:04:53 -0500
Subject: ssb: driver_gige: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This code was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Reviewed-by: Michael Buesch <m@bues.ch>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/ssb/driver_gige.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/ssb/driver_gige.c b/drivers/ssb/driver_gige.c
index e9734051e3c4..ebee6b0e3c34 100644
--- a/drivers/ssb/driver_gige.c
+++ b/drivers/ssb/driver_gige.c
@@ -242,7 +242,7 @@ static int ssb_gige_probe(struct ssb_device *sdev,
 bool pdev_is_ssb_gige_core(struct pci_dev *pdev)
 {
 	if (!pdev->resource[0].name)
-		return 0;
+		return false;
 	return (strcmp(pdev->resource[0].name, SSB_GIGE_MEM_RES_NAME) == 0);
 }
 EXPORT_SYMBOL(pdev_is_ssb_gige_core);
-- 
cgit v1.2.3


From 2aa650d1950fce94f696ebd7db30b8830c2c946f Mon Sep 17 00:00:00 2001
From: Michael Büsch <m@bues.ch>
Date: Tue, 31 Jul 2018 21:14:04 +0200
Subject: b43/leds: Ensure NUL-termination of LED name string

strncpy might not NUL-terminate the string, if the name equals the buffer size.
Use strlcpy instead.

Signed-off-by: Michael Buesch <m@bues.ch>
Cc: stable@vger.kernel.org
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/b43/leds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43/leds.c b/drivers/net/wireless/broadcom/b43/leds.c
index cb987c2ecc6b..87131f663292 100644
--- a/drivers/net/wireless/broadcom/b43/leds.c
+++ b/drivers/net/wireless/broadcom/b43/leds.c
@@ -131,7 +131,7 @@ static int b43_register_led(struct b43_wldev *dev, struct b43_led *led,
 	led->wl = dev->wl;
 	led->index = led_index;
 	led->activelow = activelow;
-	strncpy(led->name, name, sizeof(led->name));
+	strlcpy(led->name, name, sizeof(led->name));
 	atomic_set(&led->state, 0);
 
 	led->led_dev.name = led->name;
-- 
cgit v1.2.3


From 4d77a89e3924b12f4a5628b21237e57ab4703866 Mon Sep 17 00:00:00 2001
From: Michael Büsch <m@bues.ch>
Date: Tue, 31 Jul 2018 21:14:16 +0200
Subject: b43legacy/leds: Ensure NUL-termination of LED name string

strncpy might not NUL-terminate the string, if the name equals the buffer size.
Use strlcpy instead.

Signed-off-by: Michael Buesch <m@bues.ch>
Cc: stable@vger.kernel.org
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/net/wireless/broadcom/b43legacy/leds.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43legacy/leds.c b/drivers/net/wireless/broadcom/b43legacy/leds.c
index fd4565389c77..bc922118b6ac 100644
--- a/drivers/net/wireless/broadcom/b43legacy/leds.c
+++ b/drivers/net/wireless/broadcom/b43legacy/leds.c
@@ -101,7 +101,7 @@ static int b43legacy_register_led(struct b43legacy_wldev *dev,
 	led->dev = dev;
 	led->index = led_index;
 	led->activelow = activelow;
-	strncpy(led->name, name, sizeof(led->name));
+	strlcpy(led->name, name, sizeof(led->name));
 
 	led->led_dev.name = led->name;
 	led->led_dev.default_trigger = default_trigger;
-- 
cgit v1.2.3


From b8b6069cf2087545fe53ec920e8353133e9a70bf Mon Sep 17 00:00:00 2001
From: Michael Büsch <m@bues.ch>
Date: Tue, 31 Jul 2018 21:56:38 +0200
Subject: ssb: Remove home-grown printk wrappers

Replace the ssb printk wrappers by standard print helpers.
Also remove SSB_SILENT. Nobody should use it anyway.

Originally submitted by Joe Perches <joe@perches.com>.
Modified to add dev_... based printks.

Signed-off-by: Michael Buesch <m@bues.ch>
Tested-by: Michael Buesch <m@bues.ch>
Cc: Joe Perches <joe@perches.com>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 drivers/ssb/Kconfig                    | 14 +--------
 drivers/ssb/b43_pci_bridge.c           |  4 +--
 drivers/ssb/bridge_pcmcia_80211.c      |  6 ++--
 drivers/ssb/driver_chipcommon.c        |  6 ++--
 drivers/ssb/driver_chipcommon_pmu.c    | 30 +++++++++---------
 drivers/ssb/driver_chipcommon_sflash.c |  6 ++--
 drivers/ssb/driver_extif.c             |  4 +--
 drivers/ssb/driver_gpio.c              |  4 +--
 drivers/ssb/driver_mipscore.c          | 17 ++++++-----
 drivers/ssb/driver_pcicore.c           | 17 ++++++-----
 drivers/ssb/embedded.c                 |  8 ++---
 drivers/ssb/host_soc.c                 |  4 +--
 drivers/ssb/main.c                     | 45 +++++++++++++++------------
 drivers/ssb/pci.c                      | 56 ++++++++++++++++------------------
 drivers/ssb/pcmcia.c                   | 48 +++++++++++++----------------
 drivers/ssb/scan.c                     | 34 ++++++++++-----------
 drivers/ssb/sdio.c                     |  4 +--
 drivers/ssb/sprom.c                    |  4 +--
 drivers/ssb/ssb_private.h              | 30 ++----------------
 19 files changed, 152 insertions(+), 189 deletions(-)

diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index c574dd210500..6c438c819eb9 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -89,21 +89,9 @@ config SSB_HOST_SOC
 
 	  If unsure, say N
 
-config SSB_SILENT
-	bool "No SSB kernel messages"
-	depends on SSB && EXPERT
-	help
-	  This option turns off all Sonics Silicon Backplane printks.
-	  Note that you won't be able to identify problems, once
-	  messages are turned off.
-	  This might only be desired for production kernels on
-	  embedded devices to reduce the kernel size.
-
-	  Say N
-
 config SSB_DEBUG
 	bool "SSB debugging"
-	depends on SSB && !SSB_SILENT
+	depends on SSB
 	help
 	  This turns on additional runtime checks and debugging
 	  messages. Turn this on for SSB troubleshooting.
diff --git a/drivers/ssb/b43_pci_bridge.c b/drivers/ssb/b43_pci_bridge.c
index bed2fedeb057..9c7316b5685f 100644
--- a/drivers/ssb/b43_pci_bridge.c
+++ b/drivers/ssb/b43_pci_bridge.c
@@ -10,12 +10,12 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/pci.h>
 #include <linux/module.h>
 #include <linux/ssb/ssb.h>
 
-#include "ssb_private.h"
-
 
 static const struct pci_device_id b43_pci_bridge_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_BROADCOM, 0x4301) },
diff --git a/drivers/ssb/bridge_pcmcia_80211.c b/drivers/ssb/bridge_pcmcia_80211.c
index d70568ea02d5..f51f150307df 100644
--- a/drivers/ssb/bridge_pcmcia_80211.c
+++ b/drivers/ssb/bridge_pcmcia_80211.c
@@ -6,6 +6,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -15,8 +17,6 @@
 #include <pcmcia/ds.h>
 #include <pcmcia/cisreg.h>
 
-#include "ssb_private.h"
-
 static const struct pcmcia_device_id ssb_host_pcmcia_tbl[] = {
 	PCMCIA_DEVICE_MANF_CARD(0x2D0, 0x448),
 	PCMCIA_DEVICE_MANF_CARD(0x2D0, 0x476),
@@ -70,7 +70,7 @@ err_disable:
 err_kfree_ssb:
 	kfree(ssb);
 out_error:
-	ssb_err("Initialization failed (%d, %d)\n", res, err);
+	dev_err(&dev->dev, "Initialization failed (%d, %d)\n", res, err);
 	return err;
 }
 
diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index 7cb7d2c8fd86..48050c6fd847 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -9,14 +9,14 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/export.h>
 #include <linux/pci.h>
 #include <linux/bcm47xx_wdt.h>
 
-#include "ssb_private.h"
-
 
 /* Clock sources */
 enum ssb_clksrc {
@@ -354,7 +354,7 @@ void ssb_chipcommon_init(struct ssb_chipcommon *cc)
 
 	if (cc->dev->id.revision >= 11)
 		cc->status = chipco_read32(cc, SSB_CHIPCO_CHIPSTAT);
-	ssb_dbg("chipcommon status is 0x%x\n", cc->status);
+	dev_dbg(cc->dev->dev, "chipcommon status is 0x%x\n", cc->status);
 
 	if (cc->dev->id.revision >= 20) {
 		chipco_write32(cc, SSB_CHIPCO_GPIOPULLUP, 0);
diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c
index c5352ea4821e..e28682a53cdf 100644
--- a/drivers/ssb/driver_chipcommon_pmu.c
+++ b/drivers/ssb/driver_chipcommon_pmu.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/ssb/ssb_driver_chipcommon.h>
@@ -17,8 +19,6 @@
 #include <linux/bcm47xx_nvram.h>
 #endif
 
-#include "ssb_private.h"
-
 static u32 ssb_chipco_pll_read(struct ssb_chipcommon *cc, u32 offset)
 {
 	chipco_write32(cc, SSB_CHIPCO_PLLCTL_ADDR, offset);
@@ -110,7 +110,7 @@ static void ssb_pmu0_pllinit_r0(struct ssb_chipcommon *cc,
 		return;
 	}
 
-	ssb_info("Programming PLL to %u.%03u MHz\n",
+	dev_info(cc->dev->dev, "Programming PLL to %u.%03u MHz\n",
 		 crystalfreq / 1000, crystalfreq % 1000);
 
 	/* First turn the PLL off. */
@@ -138,7 +138,7 @@ static void ssb_pmu0_pllinit_r0(struct ssb_chipcommon *cc,
 	}
 	tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
 	if (tmp & SSB_CHIPCO_CLKCTLST_HAVEHT)
-		ssb_emerg("Failed to turn the PLL off!\n");
+		dev_emerg(cc->dev->dev, "Failed to turn the PLL off!\n");
 
 	/* Set PDIV in PLL control 0. */
 	pllctl = ssb_chipco_pll_read(cc, SSB_PMU0_PLLCTL0);
@@ -249,7 +249,7 @@ static void ssb_pmu1_pllinit_r0(struct ssb_chipcommon *cc,
 		return;
 	}
 
-	ssb_info("Programming PLL to %u.%03u MHz\n",
+	dev_info(cc->dev->dev, "Programming PLL to %u.%03u MHz\n",
 		 crystalfreq / 1000, crystalfreq % 1000);
 
 	/* First turn the PLL off. */
@@ -275,7 +275,7 @@ static void ssb_pmu1_pllinit_r0(struct ssb_chipcommon *cc,
 	}
 	tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
 	if (tmp & SSB_CHIPCO_CLKCTLST_HAVEHT)
-		ssb_emerg("Failed to turn the PLL off!\n");
+		dev_emerg(cc->dev->dev, "Failed to turn the PLL off!\n");
 
 	/* Set p1div and p2div. */
 	pllctl = ssb_chipco_pll_read(cc, SSB_PMU1_PLLCTL0);
@@ -349,7 +349,7 @@ static void ssb_pmu_pll_init(struct ssb_chipcommon *cc)
 	case 43222:
 		break;
 	default:
-		ssb_err("ERROR: PLL init unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PLL init unknown for device %04X\n",
 			bus->chip_id);
 	}
 }
@@ -471,7 +471,7 @@ static void ssb_pmu_resources_init(struct ssb_chipcommon *cc)
 		max_msk = 0xFFFFF;
 		break;
 	default:
-		ssb_err("ERROR: PMU resource config unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU resource config unknown for device %04X\n",
 			bus->chip_id);
 	}
 
@@ -524,7 +524,7 @@ void ssb_pmu_init(struct ssb_chipcommon *cc)
 	pmucap = chipco_read32(cc, SSB_CHIPCO_PMU_CAP);
 	cc->pmu.rev = (pmucap & SSB_CHIPCO_PMU_CAP_REVISION);
 
-	ssb_dbg("Found rev %u PMU (capabilities 0x%08X)\n",
+	dev_dbg(cc->dev->dev, "Found rev %u PMU (capabilities 0x%08X)\n",
 		cc->pmu.rev, pmucap);
 
 	if (cc->pmu.rev == 1)
@@ -636,7 +636,7 @@ u32 ssb_pmu_get_alp_clock(struct ssb_chipcommon *cc)
 	case 0x5354:
 		return ssb_pmu_get_alp_clock_clk0(cc);
 	default:
-		ssb_err("ERROR: PMU alp clock unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU alp clock unknown for device %04X\n",
 			bus->chip_id);
 		return 0;
 	}
@@ -651,7 +651,7 @@ u32 ssb_pmu_get_cpu_clock(struct ssb_chipcommon *cc)
 		/* 5354 chip uses a non programmable PLL of frequency 240MHz */
 		return 240000000;
 	default:
-		ssb_err("ERROR: PMU cpu clock unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU cpu clock unknown for device %04X\n",
 			bus->chip_id);
 		return 0;
 	}
@@ -665,7 +665,7 @@ u32 ssb_pmu_get_controlclock(struct ssb_chipcommon *cc)
 	case 0x5354:
 		return 120000000;
 	default:
-		ssb_err("ERROR: PMU controlclock unknown for device %04X\n",
+		dev_err(cc->dev->dev, "ERROR: PMU controlclock unknown for device %04X\n",
 			bus->chip_id);
 		return 0;
 	}
@@ -705,9 +705,9 @@ void ssb_pmu_spuravoid_pllupdate(struct ssb_chipcommon *cc, int spuravoid)
 		pmu_ctl = SSB_CHIPCO_PMU_CTL_PLL_UPD;
 		break;
 	default:
-		ssb_printk(KERN_ERR PFX
-			   "Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n",
-			   cc->dev->bus->chip_id);
+		dev_err(cc->dev->dev,
+			"Unknown spuravoidance settings for chip 0x%04X, not changing PLL\n",
+			cc->dev->bus->chip_id);
 		return;
 	}
 
diff --git a/drivers/ssb/driver_chipcommon_sflash.c b/drivers/ssb/driver_chipcommon_sflash.c
index 937fc31971a7..fac0e6828288 100644
--- a/drivers/ssb/driver_chipcommon_sflash.c
+++ b/drivers/ssb/driver_chipcommon_sflash.c
@@ -5,10 +5,10 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
-#include <linux/ssb/ssb.h>
-
 #include "ssb_private.h"
 
+#include <linux/ssb/ssb.h>
+
 static struct resource ssb_sflash_resource = {
 	.name	= "ssb_sflash",
 	.start	= SSB_FLASH2,
@@ -80,7 +80,7 @@ static void ssb_sflash_cmd(struct ssb_chipcommon *cc, u32 opcode)
 			return;
 		cpu_relax();
 	}
-	pr_err("SFLASH control command failed (timeout)!\n");
+	dev_err(cc->dev->dev, "SFLASH control command failed (timeout)!\n");
 }
 
 /* Initialize serial flash access */
diff --git a/drivers/ssb/driver_extif.c b/drivers/ssb/driver_extif.c
index 59385fdab5b0..06b68dd6e022 100644
--- a/drivers/ssb/driver_extif.c
+++ b/drivers/ssb/driver_extif.c
@@ -10,12 +10,12 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/serial.h>
 #include <linux/serial_core.h>
 #include <linux/serial_reg.h>
 
-#include "ssb_private.h"
-
 
 static inline u32 extif_read32(struct ssb_extif *extif, u16 offset)
 {
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index 796e22037bc4..6ce4abf7d473 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/gpio/driver.h>
 #include <linux/irq.h>
 #include <linux/interrupt.h>
@@ -15,8 +17,6 @@
 #include <linux/export.h>
 #include <linux/ssb/ssb.h>
 
-#include "ssb_private.h"
-
 
 /**************************************************
  * Shared
diff --git a/drivers/ssb/driver_mipscore.c b/drivers/ssb/driver_mipscore.c
index f87efef42252..1ca2ac5ef2b8 100644
--- a/drivers/ssb/driver_mipscore.c
+++ b/drivers/ssb/driver_mipscore.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 
 #include <linux/mtd/physmap.h>
@@ -19,8 +21,6 @@
 #include <linux/bcm47xx_nvram.h>
 #endif
 
-#include "ssb_private.h"
-
 static const char * const part_probes[] = { "bcm47xxpart", NULL };
 
 static struct physmap_flash_data ssb_pflash_data = {
@@ -170,14 +170,15 @@ static void set_irq(struct ssb_device *dev, unsigned int irq)
 		irqflag |= (ipsflag & ~ipsflag_irq_mask[irq]);
 		ssb_write32(mdev, SSB_IPSFLAG, irqflag);
 	}
-	ssb_dbg("set_irq: core 0x%04x, irq %d => %d\n",
+	dev_dbg(dev->dev, "set_irq: core 0x%04x, irq %d => %d\n",
 		dev->id.coreid, oldirq+2, irq+2);
 }
 
 static void print_irq(struct ssb_device *dev, unsigned int irq)
 {
 	static const char *irq_name[] = {"2(S)", "3", "4", "5", "6", "D", "I"};
-	ssb_dbg("core 0x%04x, irq : %s%s %s%s %s%s %s%s %s%s %s%s %s%s\n",
+	dev_dbg(dev->dev,
+		"core 0x%04x, irq : %s%s %s%s %s%s %s%s %s%s %s%s %s%s\n",
 		dev->id.coreid,
 		irq_name[0], irq == 0 ? "*" : " ",
 		irq_name[1], irq == 1 ? "*" : " ",
@@ -229,11 +230,11 @@ static void ssb_mips_flash_detect(struct ssb_mipscore *mcore)
 	switch (bus->chipco.capabilities & SSB_CHIPCO_CAP_FLASHT) {
 	case SSB_CHIPCO_FLASHT_STSER:
 	case SSB_CHIPCO_FLASHT_ATSER:
-		pr_debug("Found serial flash\n");
+		dev_dbg(mcore->dev->dev, "Found serial flash\n");
 		ssb_sflash_init(&bus->chipco);
 		break;
 	case SSB_CHIPCO_FLASHT_PARA:
-		pr_debug("Found parallel flash\n");
+		dev_dbg(mcore->dev->dev, "Found parallel flash\n");
 		pflash->present = true;
 		pflash->window = SSB_FLASH2;
 		pflash->window_size = SSB_FLASH2_SZ;
@@ -299,7 +300,7 @@ void ssb_mipscore_init(struct ssb_mipscore *mcore)
 	if (!mcore->dev)
 		return; /* We don't have a MIPS core */
 
-	ssb_dbg("Initializing MIPS core...\n");
+	dev_dbg(mcore->dev->dev, "Initializing MIPS core...\n");
 
 	bus = mcore->dev->bus;
 	hz = ssb_clockspeed(bus);
@@ -347,7 +348,7 @@ void ssb_mipscore_init(struct ssb_mipscore *mcore)
 			break;
 		}
 	}
-	ssb_dbg("after irq reconfiguration\n");
+	dev_dbg(mcore->dev->dev, "after irq reconfiguration\n");
 	dump_irq(bus);
 
 	ssb_mips_serial_init(mcore);
diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c
index 5fe1c22e289b..ae80b3171523 100644
--- a/drivers/ssb/driver_pcicore.c
+++ b/drivers/ssb/driver_pcicore.c
@@ -8,14 +8,14 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/pci.h>
 #include <linux/export.h>
 #include <linux/delay.h>
 #include <linux/ssb/ssb_embedded.h>
 
-#include "ssb_private.h"
-
 static u32 ssb_pcie_read(struct ssb_pcicore *pc, u32 address);
 static void ssb_pcie_write(struct ssb_pcicore *pc, u32 address, u32 data);
 static u16 ssb_pcie_mdio_read(struct ssb_pcicore *pc, u8 device, u8 address);
@@ -263,7 +263,7 @@ int ssb_pcicore_plat_dev_init(struct pci_dev *d)
 		return -ENODEV;
 	}
 
-	ssb_info("PCI: Fixing up device %s\n", pci_name(d));
+	dev_info(&d->dev, "PCI: Fixing up device %s\n", pci_name(d));
 
 	/* Fix up interrupt lines */
 	d->irq = ssb_mips_irq(extpci_core->dev) + 2;
@@ -284,12 +284,12 @@ static void ssb_pcicore_fixup_pcibridge(struct pci_dev *dev)
 	if (dev->bus->number != 0 || PCI_SLOT(dev->devfn) != 0)
 		return;
 
-	ssb_info("PCI: Fixing up bridge %s\n", pci_name(dev));
+	dev_info(&dev->dev, "PCI: Fixing up bridge %s\n", pci_name(dev));
 
 	/* Enable PCI bridge bus mastering and memory space */
 	pci_set_master(dev);
 	if (pcibios_enable_device(dev, ~0) < 0) {
-		ssb_err("PCI: SSB bridge enable failed\n");
+		dev_err(&dev->dev, "PCI: SSB bridge enable failed\n");
 		return;
 	}
 
@@ -298,7 +298,8 @@ static void ssb_pcicore_fixup_pcibridge(struct pci_dev *dev)
 
 	/* Make sure our latency is high enough to handle the devices behind us */
 	lat = 168;
-	ssb_info("PCI: Fixing latency timer of device %s to %u\n",
+	dev_info(&dev->dev,
+		 "PCI: Fixing latency timer of device %s to %u\n",
 		 pci_name(dev), lat);
 	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
 }
@@ -322,7 +323,7 @@ static void ssb_pcicore_init_hostmode(struct ssb_pcicore *pc)
 		return;
 	extpci_core = pc;
 
-	ssb_dbg("PCIcore in host mode found\n");
+	dev_dbg(pc->dev->dev, "PCIcore in host mode found\n");
 	/* Reset devices on the external PCI bus */
 	val = SSB_PCICORE_CTL_RST_OE;
 	val |= SSB_PCICORE_CTL_CLK_OE;
@@ -337,7 +338,7 @@ static void ssb_pcicore_init_hostmode(struct ssb_pcicore *pc)
 	udelay(1); /* Assertion time demanded by the PCI standard */
 
 	if (pc->dev->bus->has_cardbus_slot) {
-		ssb_dbg("CardBus slot detected\n");
+		dev_dbg(pc->dev->dev, "CardBus slot detected\n");
 		pc->cardbusmode = 1;
 		/* GPIO 1 resets the bridge */
 		ssb_gpio_out(pc->dev->bus, 1, 1);
diff --git a/drivers/ssb/embedded.c b/drivers/ssb/embedded.c
index 55e101115038..c39ddf8988c1 100644
--- a/drivers/ssb/embedded.c
+++ b/drivers/ssb/embedded.c
@@ -9,6 +9,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/export.h>
 #include <linux/platform_device.h>
 #include <linux/ssb/ssb.h>
@@ -17,8 +19,6 @@
 #include <linux/ssb/ssb_driver_gige.h>
 #include <linux/pci.h>
 
-#include "ssb_private.h"
-
 
 int ssb_watchdog_timer_set(struct ssb_bus *bus, u32 ticks)
 {
@@ -57,8 +57,8 @@ int ssb_watchdog_register(struct ssb_bus *bus)
 					     bus->busnumber, &wdt,
 					     sizeof(wdt));
 	if (IS_ERR(pdev)) {
-		ssb_dbg("can not register watchdog device, err: %li\n",
-			PTR_ERR(pdev));
+		pr_debug("can not register watchdog device, err: %li\n",
+			 PTR_ERR(pdev));
 		return PTR_ERR(pdev);
 	}
 
diff --git a/drivers/ssb/host_soc.c b/drivers/ssb/host_soc.c
index d62992dc08b2..eadaedf466f6 100644
--- a/drivers/ssb/host_soc.c
+++ b/drivers/ssb/host_soc.c
@@ -8,11 +8,11 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/bcm47xx_nvram.h>
 #include <linux/ssb/ssb.h>
 
-#include "ssb_private.h"
-
 static u8 ssb_host_soc_read8(struct ssb_device *dev, u16 offset)
 {
 	struct ssb_bus *bus = dev->bus;
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 116594413f66..9da56d2fdbd3 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -256,7 +256,8 @@ int ssb_devices_thaw(struct ssb_freeze_context *ctx)
 
 		err = sdrv->probe(sdev, &sdev->id);
 		if (err) {
-			ssb_err("Failed to thaw device %s\n",
+			dev_err(sdev->dev,
+				"Failed to thaw device %s\n",
 				dev_name(sdev->dev));
 			result = err;
 		}
@@ -431,9 +432,9 @@ void ssb_bus_unregister(struct ssb_bus *bus)
 
 	err = ssb_gpio_unregister(bus);
 	if (err == -EBUSY)
-		ssb_dbg("Some GPIOs are still in use\n");
+		pr_debug("Some GPIOs are still in use\n");
 	else if (err)
-		ssb_dbg("Can not unregister GPIO driver: %i\n", err);
+		pr_debug("Can not unregister GPIO driver: %i\n", err);
 
 	ssb_buses_lock();
 	ssb_devices_unregister(bus);
@@ -518,7 +519,7 @@ static int ssb_devices_register(struct ssb_bus *bus)
 		sdev->dev = dev;
 		err = device_register(dev);
 		if (err) {
-			ssb_err("Could not register %s\n", dev_name(dev));
+			pr_err("Could not register %s\n", dev_name(dev));
 			/* Set dev to NULL to not unregister
 			 * dev on error unwinding. */
 			sdev->dev = NULL;
@@ -576,9 +577,9 @@ static int ssb_attach_queued_buses(void)
 
 		err = ssb_gpio_init(bus);
 		if (err == -ENOTSUPP)
-			ssb_dbg("GPIO driver not activated\n");
+			pr_debug("GPIO driver not activated\n");
 		else if (err)
-			ssb_dbg("Error registering GPIO driver: %i\n", err);
+			pr_debug("Error registering GPIO driver: %i\n", err);
 
 		ssb_bus_may_powerdown(bus);
 
@@ -707,10 +708,12 @@ int ssb_bus_pcibus_register(struct ssb_bus *bus, struct pci_dev *host_pci)
 
 	err = ssb_bus_register(bus, ssb_pci_get_invariants, 0);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found on PCI device %s\n",
+		dev_info(&host_pci->dev,
+			 "Sonics Silicon Backplane found on PCI device %s\n",
 			 dev_name(&host_pci->dev));
 	} else {
-		ssb_err("Failed to register PCI version of SSB with error %d\n",
+		dev_err(&host_pci->dev,
+			"Failed to register PCI version of SSB with error %d\n",
 			err);
 	}
 
@@ -731,7 +734,8 @@ int ssb_bus_pcmciabus_register(struct ssb_bus *bus,
 
 	err = ssb_bus_register(bus, ssb_pcmcia_get_invariants, baseaddr);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found on PCMCIA device %s\n",
+		dev_info(&pcmcia_dev->dev,
+			 "Sonics Silicon Backplane found on PCMCIA device %s\n",
 			 pcmcia_dev->devname);
 	}
 
@@ -752,7 +756,8 @@ int ssb_bus_sdiobus_register(struct ssb_bus *bus, struct sdio_func *func,
 
 	err = ssb_bus_register(bus, ssb_sdio_get_invariants, ~0);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found on SDIO device %s\n",
+		dev_info(&func->dev,
+			 "Sonics Silicon Backplane found on SDIO device %s\n",
 			 sdio_func_id(func));
 	}
 
@@ -771,8 +776,8 @@ int ssb_bus_host_soc_register(struct ssb_bus *bus, unsigned long baseaddr)
 
 	err = ssb_bus_register(bus, ssb_host_soc_get_invariants, baseaddr);
 	if (!err) {
-		ssb_info("Sonics Silicon Backplane found at address 0x%08lX\n",
-			 baseaddr);
+		pr_info("Sonics Silicon Backplane found at address 0x%08lX\n",
+			baseaddr);
 	}
 
 	return err;
@@ -1057,9 +1062,9 @@ static int ssb_wait_bits(struct ssb_device *dev, u16 reg, u32 bitmask,
 		}
 		udelay(10);
 	}
-	printk(KERN_ERR PFX "Timeout waiting for bitmask %08X on "
-			    "register %04X to %s.\n",
-	       bitmask, reg, (set ? "set" : "clear"));
+	dev_err(dev->dev,
+		"Timeout waiting for bitmask %08X on register %04X to %s\n",
+		bitmask, reg, set ? "set" : "clear");
 
 	return -ETIMEDOUT;
 }
@@ -1169,7 +1174,7 @@ out:
 #endif
 	return err;
 error:
-	ssb_err("Bus powerdown failed\n");
+	pr_err("Bus powerdown failed\n");
 	goto out;
 }
 EXPORT_SYMBOL(ssb_bus_may_powerdown);
@@ -1192,7 +1197,7 @@ int ssb_bus_powerup(struct ssb_bus *bus, bool dynamic_pctl)
 
 	return 0;
 error:
-	ssb_err("Bus powerup failed\n");
+	pr_err("Bus powerup failed\n");
 	return err;
 }
 EXPORT_SYMBOL(ssb_bus_powerup);
@@ -1300,19 +1305,19 @@ static int __init ssb_modinit(void)
 
 	err = b43_pci_ssb_bridge_init();
 	if (err) {
-		ssb_err("Broadcom 43xx PCI-SSB-bridge initialization failed\n");
+		pr_err("Broadcom 43xx PCI-SSB-bridge initialization failed\n");
 		/* don't fail SSB init because of this */
 		err = 0;
 	}
 	err = ssb_host_pcmcia_init();
 	if (err) {
-		ssb_err("PCMCIA host initialization failed\n");
+		pr_err("PCMCIA host initialization failed\n");
 		/* don't fail SSB init because of this */
 		err = 0;
 	}
 	err = ssb_gige_init();
 	if (err) {
-		ssb_err("SSB Broadcom Gigabit Ethernet driver initialization failed\n");
+		pr_err("SSB Broadcom Gigabit Ethernet driver initialization failed\n");
 		/* don't fail SSB init because of this */
 		err = 0;
 	}
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index 77b551da5728..ad4308529eba 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -15,14 +15,14 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/slab.h>
 #include <linux/pci.h>
 #include <linux/delay.h>
 
-#include "ssb_private.h"
-
 
 /* Define the following to 1 to enable a printk on each coreswitch. */
 #define SSB_VERBOSE_PCICORESWITCH_DEBUG		0
@@ -56,7 +56,7 @@ int ssb_pci_switch_coreidx(struct ssb_bus *bus, u8 coreidx)
 	}
 	return 0;
 error:
-	ssb_err("Failed to switch to core %u\n", coreidx);
+	pr_err("Failed to switch to core %u\n", coreidx);
 	return -ENODEV;
 }
 
@@ -67,9 +67,8 @@ int ssb_pci_switch_core(struct ssb_bus *bus,
 	unsigned long flags;
 
 #if SSB_VERBOSE_PCICORESWITCH_DEBUG
-	ssb_info("Switching to %s core, index %d\n",
-		 ssb_core_name(dev->id.coreid),
-		 dev->core_index);
+	pr_info("Switching to %s core, index %d\n",
+		ssb_core_name(dev->id.coreid), dev->core_index);
 #endif
 
 	spin_lock_irqsave(&bus->bar_lock, flags);
@@ -161,7 +160,7 @@ out:
 	return err;
 
 err_pci:
-	printk(KERN_ERR PFX "Error: ssb_pci_xtal() could not access PCI config space!\n");
+	pr_err("Error: ssb_pci_xtal() could not access PCI config space!\n");
 	err = -EBUSY;
 	goto out;
 }
@@ -286,7 +285,7 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 	u32 spromctl;
 	u16 size = bus->sprom_size;
 
-	ssb_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
+	pr_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
 	err = pci_read_config_dword(pdev, SSB_SPROMCTL, &spromctl);
 	if (err)
 		goto err_ctlreg;
@@ -294,17 +293,17 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 	err = pci_write_config_dword(pdev, SSB_SPROMCTL, spromctl);
 	if (err)
 		goto err_ctlreg;
-	ssb_notice("[ 0%%");
+	pr_notice("[ 0%%");
 	msleep(500);
 	for (i = 0; i < size; i++) {
 		if (i == size / 4)
-			ssb_cont("25%%");
+			pr_cont("25%%");
 		else if (i == size / 2)
-			ssb_cont("50%%");
+			pr_cont("50%%");
 		else if (i == (size * 3) / 4)
-			ssb_cont("75%%");
+			pr_cont("75%%");
 		else if (i % 2)
-			ssb_cont(".");
+			pr_cont(".");
 		writew(sprom[i], bus->mmio + bus->sprom_offset + (i * 2));
 		mmiowb();
 		msleep(20);
@@ -317,12 +316,12 @@ static int sprom_do_write(struct ssb_bus *bus, const u16 *sprom)
 	if (err)
 		goto err_ctlreg;
 	msleep(500);
-	ssb_cont("100%% ]\n");
-	ssb_notice("SPROM written\n");
+	pr_cont("100%% ]\n");
+	pr_notice("SPROM written\n");
 
 	return 0;
 err_ctlreg:
-	ssb_err("Could not access SPROM control register.\n");
+	pr_err("Could not access SPROM control register.\n");
 	return err;
 }
 
@@ -816,7 +815,7 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out,
 	memset(out, 0, sizeof(*out));
 
 	out->revision = in[size - 1] & 0x00FF;
-	ssb_dbg("SPROM revision %d detected\n", out->revision);
+	pr_debug("SPROM revision %d detected\n", out->revision);
 	memset(out->et0mac, 0xFF, 6);		/* preset et0 and et1 mac */
 	memset(out->et1mac, 0xFF, 6);
 
@@ -825,7 +824,7 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out,
 		 * number stored in the SPROM.
 		 * Always extract r1. */
 		out->revision = 1;
-		ssb_dbg("SPROM treated as revision %d\n", out->revision);
+		pr_debug("SPROM treated as revision %d\n", out->revision);
 	}
 
 	switch (out->revision) {
@@ -842,8 +841,8 @@ static int sprom_extract(struct ssb_bus *bus, struct ssb_sprom *out,
 		sprom_extract_r8(out, in);
 		break;
 	default:
-		ssb_warn("Unsupported SPROM revision %d detected. Will extract v1\n",
-			 out->revision);
+		pr_warn("Unsupported SPROM revision %d detected. Will extract v1\n",
+			out->revision);
 		out->revision = 1;
 		sprom_extract_r123(out, in);
 	}
@@ -863,7 +862,7 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 	u16 *buf;
 
 	if (!ssb_is_sprom_available(bus)) {
-		ssb_err("No SPROM available!\n");
+		pr_err("No SPROM available!\n");
 		return -ENODEV;
 	}
 	if (bus->chipco.dev) {	/* can be unavailable! */
@@ -882,7 +881,7 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 	} else {
 		bus->sprom_offset = SSB_SPROM_BASE1;
 	}
-	ssb_dbg("SPROM offset is 0x%x\n", bus->sprom_offset);
+	pr_debug("SPROM offset is 0x%x\n", bus->sprom_offset);
 
 	buf = kcalloc(SSB_SPROMSIZE_WORDS_R123, sizeof(u16), GFP_KERNEL);
 	if (!buf)
@@ -907,16 +906,16 @@ static int ssb_pci_sprom_get(struct ssb_bus *bus,
 			 * available for this device in some other storage */
 			err = ssb_fill_sprom_with_fallback(bus, sprom);
 			if (err) {
-				ssb_warn("WARNING: Using fallback SPROM failed (err %d)\n",
-					 err);
+				pr_warn("WARNING: Using fallback SPROM failed (err %d)\n",
+					err);
 				goto out_free;
 			} else {
-				ssb_dbg("Using SPROM revision %d provided by platform\n",
-					sprom->revision);
+				pr_debug("Using SPROM revision %d provided by platform\n",
+					 sprom->revision);
 				err = 0;
 				goto out_free;
 			}
-			ssb_warn("WARNING: Invalid SPROM CRC (corrupt SPROM)\n");
+			pr_warn("WARNING: Invalid SPROM CRC (corrupt SPROM)\n");
 		}
 	}
 	err = sprom_extract(bus, sprom, buf, bus->sprom_size);
@@ -953,8 +952,7 @@ static int ssb_pci_assert_buspower(struct ssb_bus *bus)
 	if (likely(bus->powered_up))
 		return 0;
 
-	printk(KERN_ERR PFX "FATAL ERROR: Bus powered down "
-	       "while accessing PCI MMIO space\n");
+	pr_err("FATAL ERROR: Bus powered down while accessing PCI MMIO space\n");
 	if (bus->power_warn_count <= 10) {
 		bus->power_warn_count++;
 		dump_stack();
diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c
index f03422bbf087..20f63cc88e70 100644
--- a/drivers/ssb/pcmcia.c
+++ b/drivers/ssb/pcmcia.c
@@ -8,6 +8,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/delay.h>
 #include <linux/io.h>
@@ -18,8 +20,6 @@
 #include <pcmcia/ds.h>
 #include <pcmcia/cisreg.h>
 
-#include "ssb_private.h"
-
 
 /* Define the following to 1 to enable a printk on each coreswitch. */
 #define SSB_VERBOSE_PCMCIACORESWITCH_DEBUG		0
@@ -143,7 +143,7 @@ int ssb_pcmcia_switch_coreidx(struct ssb_bus *bus,
 
 	return 0;
 error:
-	ssb_err("Failed to switch to core %u\n", coreidx);
+	pr_err("Failed to switch to core %u\n", coreidx);
 	return err;
 }
 
@@ -152,9 +152,8 @@ static int ssb_pcmcia_switch_core(struct ssb_bus *bus, struct ssb_device *dev)
 	int err;
 
 #if SSB_VERBOSE_PCMCIACORESWITCH_DEBUG
-	ssb_info("Switching to %s core, index %d\n",
-		 ssb_core_name(dev->id.coreid),
-		 dev->core_index);
+	pr_info("Switching to %s core, index %d\n",
+		ssb_core_name(dev->id.coreid), dev->core_index);
 #endif
 
 	err = ssb_pcmcia_switch_coreidx(bus, dev->core_index);
@@ -190,7 +189,7 @@ int ssb_pcmcia_switch_segment(struct ssb_bus *bus, u8 seg)
 
 	return 0;
 error:
-	ssb_err("Failed to switch pcmcia segment\n");
+	pr_err("Failed to switch pcmcia segment\n");
 	return err;
 }
 
@@ -547,39 +546,39 @@ static int ssb_pcmcia_sprom_write_all(struct ssb_bus *bus, const u16 *sprom)
 	bool failed = 0;
 	size_t size = SSB_PCMCIA_SPROM_SIZE;
 
-	ssb_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
+	pr_notice("Writing SPROM. Do NOT turn off the power! Please stand by...\n");
 	err = ssb_pcmcia_sprom_command(bus, SSB_PCMCIA_SPROMCTL_WRITEEN);
 	if (err) {
-		ssb_notice("Could not enable SPROM write access\n");
+		pr_notice("Could not enable SPROM write access\n");
 		return -EBUSY;
 	}
-	ssb_notice("[ 0%%");
+	pr_notice("[ 0%%");
 	msleep(500);
 	for (i = 0; i < size; i++) {
 		if (i == size / 4)
-			ssb_cont("25%%");
+			pr_cont("25%%");
 		else if (i == size / 2)
-			ssb_cont("50%%");
+			pr_cont("50%%");
 		else if (i == (size * 3) / 4)
-			ssb_cont("75%%");
+			pr_cont("75%%");
 		else if (i % 2)
-			ssb_cont(".");
+			pr_cont(".");
 		err = ssb_pcmcia_sprom_write(bus, i, sprom[i]);
 		if (err) {
-			ssb_notice("Failed to write to SPROM\n");
+			pr_notice("Failed to write to SPROM\n");
 			failed = 1;
 			break;
 		}
 	}
 	err = ssb_pcmcia_sprom_command(bus, SSB_PCMCIA_SPROMCTL_WRITEDIS);
 	if (err) {
-		ssb_notice("Could not disable SPROM write access\n");
+		pr_notice("Could not disable SPROM write access\n");
 		failed = 1;
 	}
 	msleep(500);
 	if (!failed) {
-		ssb_cont("100%% ]\n");
-		ssb_notice("SPROM written\n");
+		pr_cont("100%% ]\n");
+		pr_notice("SPROM written\n");
 	}
 
 	return failed ? -EBUSY : 0;
@@ -693,9 +692,8 @@ static int ssb_pcmcia_do_get_invariants(struct pcmcia_device *p_dev,
 	return -ENOSPC; /* continue with next entry */
 
 error:
-	ssb_err(
-		   "PCMCIA: Failed to fetch device invariants: %s\n",
-		   error_description);
+	pr_err("PCMCIA: Failed to fetch device invariants: %s\n",
+	       error_description);
 	return -ENODEV;
 }
 
@@ -715,8 +713,7 @@ int ssb_pcmcia_get_invariants(struct ssb_bus *bus,
 	res = pcmcia_loop_tuple(bus->host_pcmcia, CISTPL_FUNCE,
 				ssb_pcmcia_get_mac, sprom);
 	if (res != 0) {
-		ssb_err(
-			"PCMCIA: Failed to fetch MAC address\n");
+		pr_err("PCMCIA: Failed to fetch MAC address\n");
 		return -ENODEV;
 	}
 
@@ -726,8 +723,7 @@ int ssb_pcmcia_get_invariants(struct ssb_bus *bus,
 	if ((res == 0) || (res == -ENOSPC))
 		return 0;
 
-	ssb_err(
-			"PCMCIA: Failed to fetch device invariants\n");
+	pr_err("PCMCIA: Failed to fetch device invariants\n");
 	return -ENODEV;
 }
 
@@ -836,6 +832,6 @@ int ssb_pcmcia_init(struct ssb_bus *bus)
 
 	return 0;
 error:
-	ssb_err("Failed to initialize PCMCIA host device\n");
+	pr_err("Failed to initialize PCMCIA host device\n");
 	return err;
 }
diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c
index b9429df583eb..71fbb4b3eb6a 100644
--- a/drivers/ssb/scan.c
+++ b/drivers/ssb/scan.c
@@ -12,6 +12,8 @@
  * Licensed under the GNU/GPL. See COPYING for details.
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/ssb/ssb_regs.h>
 #include <linux/pci.h>
@@ -20,8 +22,6 @@
 #include <pcmcia/cistpl.h>
 #include <pcmcia/ds.h>
 
-#include "ssb_private.h"
-
 
 const char *ssb_core_name(u16 coreid)
 {
@@ -125,7 +125,7 @@ static u16 pcidev_to_chipid(struct pci_dev *pci_dev)
 		chipid_fallback = 0x4401;
 		break;
 	default:
-		ssb_err("PCI-ID not in fallback list\n");
+		dev_err(&pci_dev->dev, "PCI-ID not in fallback list\n");
 	}
 
 	return chipid_fallback;
@@ -151,7 +151,7 @@ static u8 chipid_to_nrcores(u16 chipid)
 	case 0x4704:
 		return 9;
 	default:
-		ssb_err("CHIPID not in nrcores fallback list\n");
+		pr_err("CHIPID not in nrcores fallback list\n");
 	}
 
 	return 1;
@@ -318,13 +318,13 @@ int ssb_bus_scan(struct ssb_bus *bus,
 			bus->chip_package = 0;
 		}
 	}
-	ssb_info("Found chip with id 0x%04X, rev 0x%02X and package 0x%02X\n",
-		 bus->chip_id, bus->chip_rev, bus->chip_package);
+	pr_info("Found chip with id 0x%04X, rev 0x%02X and package 0x%02X\n",
+		bus->chip_id, bus->chip_rev, bus->chip_package);
 	if (!bus->nr_devices)
 		bus->nr_devices = chipid_to_nrcores(bus->chip_id);
 	if (bus->nr_devices > ARRAY_SIZE(bus->devices)) {
-		ssb_err("More than %d ssb cores found (%d)\n",
-			SSB_MAX_NR_CORES, bus->nr_devices);
+		pr_err("More than %d ssb cores found (%d)\n",
+		       SSB_MAX_NR_CORES, bus->nr_devices);
 		goto err_unmap;
 	}
 	if (bus->bustype == SSB_BUSTYPE_SSB) {
@@ -355,18 +355,16 @@ int ssb_bus_scan(struct ssb_bus *bus,
 		dev->bus = bus;
 		dev->ops = bus->ops;
 
-		printk(KERN_DEBUG PFX
-			    "Core %d found: %s "
-			    "(cc 0x%03X, rev 0x%02X, vendor 0x%04X)\n",
-			    i, ssb_core_name(dev->id.coreid),
-			    dev->id.coreid, dev->id.revision, dev->id.vendor);
+		pr_debug("Core %d found: %s (cc 0x%03X, rev 0x%02X, vendor 0x%04X)\n",
+			 i, ssb_core_name(dev->id.coreid),
+			 dev->id.coreid, dev->id.revision, dev->id.vendor);
 
 		switch (dev->id.coreid) {
 		case SSB_DEV_80211:
 			nr_80211_cores++;
 			if (nr_80211_cores > 1) {
 				if (!we_support_multiple_80211_cores(bus)) {
-					ssb_dbg("Ignoring additional 802.11 core\n");
+					pr_debug("Ignoring additional 802.11 core\n");
 					continue;
 				}
 			}
@@ -374,7 +372,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 		case SSB_DEV_EXTIF:
 #ifdef CONFIG_SSB_DRIVER_EXTIF
 			if (bus->extif.dev) {
-				ssb_warn("WARNING: Multiple EXTIFs found\n");
+				pr_warn("WARNING: Multiple EXTIFs found\n");
 				break;
 			}
 			bus->extif.dev = dev;
@@ -382,7 +380,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 			break;
 		case SSB_DEV_CHIPCOMMON:
 			if (bus->chipco.dev) {
-				ssb_warn("WARNING: Multiple ChipCommon found\n");
+				pr_warn("WARNING: Multiple ChipCommon found\n");
 				break;
 			}
 			bus->chipco.dev = dev;
@@ -391,7 +389,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 		case SSB_DEV_MIPS_3302:
 #ifdef CONFIG_SSB_DRIVER_MIPS
 			if (bus->mipscore.dev) {
-				ssb_warn("WARNING: Multiple MIPS cores found\n");
+				pr_warn("WARNING: Multiple MIPS cores found\n");
 				break;
 			}
 			bus->mipscore.dev = dev;
@@ -412,7 +410,7 @@ int ssb_bus_scan(struct ssb_bus *bus,
 				}
 			}
 			if (bus->pcicore.dev) {
-				ssb_warn("WARNING: Multiple PCI(E) cores found\n");
+				pr_warn("WARNING: Multiple PCI(E) cores found\n");
 				break;
 			}
 			bus->pcicore.dev = dev;
diff --git a/drivers/ssb/sdio.c b/drivers/ssb/sdio.c
index 2278e43614bd..1aedc5fbb62f 100644
--- a/drivers/ssb/sdio.c
+++ b/drivers/ssb/sdio.c
@@ -12,14 +12,14 @@
  *
  */
 
+#include "ssb_private.h"
+
 #include <linux/ssb/ssb.h>
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/etherdevice.h>
 #include <linux/mmc/sdio_func.h>
 
-#include "ssb_private.h"
-
 /* Define the following to 1 to enable a printk on each coreswitch. */
 #define SSB_VERBOSE_SDIOCORESWITCH_DEBUG		0
 
diff --git a/drivers/ssb/sprom.c b/drivers/ssb/sprom.c
index e753fbe302a7..4f028a80d6c4 100644
--- a/drivers/ssb/sprom.c
+++ b/drivers/ssb/sprom.c
@@ -127,13 +127,13 @@ ssize_t ssb_attr_sprom_store(struct ssb_bus *bus,
 		goto out_kfree;
 	err = ssb_devices_freeze(bus, &freeze);
 	if (err) {
-		ssb_err("SPROM write: Could not freeze all devices\n");
+		pr_err("SPROM write: Could not freeze all devices\n");
 		goto out_unlock;
 	}
 	res = sprom_write(bus, sprom);
 	err = ssb_devices_thaw(&freeze);
 	if (err)
-		ssb_err("SPROM write: Could not thaw all devices\n");
+		pr_err("SPROM write: Could not thaw all devices\n");
 out_unlock:
 	mutex_unlock(&bus->sprom_mutex);
 out_kfree:
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index ef9ac8efcab4..885e278c4487 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -2,37 +2,13 @@
 #ifndef LINUX_SSB_PRIVATE_H_
 #define LINUX_SSB_PRIVATE_H_
 
+#define PFX		"ssb: "
+#define pr_fmt(fmt)	PFX fmt
+
 #include <linux/ssb/ssb.h>
 #include <linux/types.h>
 #include <linux/bcm47xx_wdt.h>
 
-
-#define PFX	"ssb: "
-
-#ifdef CONFIG_SSB_SILENT
-# define ssb_printk(fmt, ...)					\
-	do { if (0) printk(fmt, ##__VA_ARGS__); } while (0)
-#else
-# define ssb_printk(fmt, ...)					\
-	printk(fmt, ##__VA_ARGS__)
-#endif /* CONFIG_SSB_SILENT */
-
-#define ssb_emerg(fmt, ...)	ssb_printk(KERN_EMERG PFX fmt, ##__VA_ARGS__)
-#define ssb_err(fmt, ...)	ssb_printk(KERN_ERR PFX fmt, ##__VA_ARGS__)
-#define ssb_warn(fmt, ...)	ssb_printk(KERN_WARNING PFX fmt, ##__VA_ARGS__)
-#define ssb_notice(fmt, ...)	ssb_printk(KERN_NOTICE PFX fmt, ##__VA_ARGS__)
-#define ssb_info(fmt, ...)	ssb_printk(KERN_INFO PFX fmt, ##__VA_ARGS__)
-#define ssb_cont(fmt, ...)	ssb_printk(KERN_CONT fmt, ##__VA_ARGS__)
-
-/* dprintk: Debugging printk; vanishes for non-debug compilation */
-#ifdef CONFIG_SSB_DEBUG
-# define ssb_dbg(fmt, ...)					\
-	ssb_printk(KERN_DEBUG PFX fmt, ##__VA_ARGS__)
-#else
-# define ssb_dbg(fmt, ...)					\
-	do { if (0) printk(KERN_DEBUG PFX fmt, ##__VA_ARGS__); } while (0)
-#endif
-
 #ifdef CONFIG_SSB_DEBUG
 # define SSB_WARN_ON(x)		WARN_ON(x)
 # define SSB_BUG_ON(x)		BUG_ON(x)
-- 
cgit v1.2.3


From 209b43759d65b2cc99ce7757249aacc82b03c4e2 Mon Sep 17 00:00:00 2001
From: Michael Büsch <m@bues.ch>
Date: Tue, 31 Jul 2018 22:15:09 +0200
Subject: ssb: Remove SSB_WARN_ON, SSB_BUG_ON and SSB_DEBUG

Use the standard WARN_ON instead.
If a small kernel is desired, WARN_ON can be disabled globally.

Also remove SSB_DEBUG. Besides WARN_ON it only adds a tiny debug check.
Include this check unconditionally.

Signed-off-by: Michael Buesch <m@bues.ch>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>
---
 arch/mips/configs/bcm47xx_defconfig |  1 -
 arch/powerpc/configs/wii_defconfig  |  1 -
 drivers/ssb/Kconfig                 |  9 ---------
 drivers/ssb/driver_chipcommon.c     |  8 ++++----
 drivers/ssb/driver_chipcommon_pmu.c | 10 +++++-----
 drivers/ssb/driver_gpio.c           |  4 ++--
 drivers/ssb/driver_pcicore.c        |  6 +++---
 drivers/ssb/embedded.c              | 10 +++++-----
 drivers/ssb/host_soc.c              | 12 ++++++------
 drivers/ssb/main.c                  | 38 +++++++++++++++++--------------------
 drivers/ssb/pci.c                   | 19 ++++++-------------
 drivers/ssb/pcmcia.c                | 14 +++++++-------
 drivers/ssb/scan.c                  |  4 ++--
 drivers/ssb/sdio.c                  | 12 ++++++------
 drivers/ssb/ssb_private.h           |  9 ---------
 include/linux/ssb/ssb.h             |  2 --
 16 files changed, 63 insertions(+), 96 deletions(-)

diff --git a/arch/mips/configs/bcm47xx_defconfig b/arch/mips/configs/bcm47xx_defconfig
index fad8e964f14c..ba800a892384 100644
--- a/arch/mips/configs/bcm47xx_defconfig
+++ b/arch/mips/configs/bcm47xx_defconfig
@@ -66,7 +66,6 @@ CONFIG_HW_RANDOM=y
 CONFIG_GPIO_SYSFS=y
 CONFIG_WATCHDOG=y
 CONFIG_BCM47XX_WDT=y
-CONFIG_SSB_DEBUG=y
 CONFIG_SSB_DRIVER_GIGE=y
 CONFIG_BCMA_DRIVER_GMAC_CMN=y
 CONFIG_USB=y
diff --git a/arch/powerpc/configs/wii_defconfig b/arch/powerpc/configs/wii_defconfig
index 10940533da71..f5c366b02828 100644
--- a/arch/powerpc/configs/wii_defconfig
+++ b/arch/powerpc/configs/wii_defconfig
@@ -78,7 +78,6 @@ CONFIG_GPIO_HLWD=y
 CONFIG_POWER_RESET=y
 CONFIG_POWER_RESET_GPIO=y
 # CONFIG_HWMON is not set
-CONFIG_SSB_DEBUG=y
 CONFIG_FB=y
 # CONFIG_VGA_CONSOLE is not set
 CONFIG_FRAMEBUFFER_CONSOLE=y
diff --git a/drivers/ssb/Kconfig b/drivers/ssb/Kconfig
index 6c438c819eb9..df30e1323252 100644
--- a/drivers/ssb/Kconfig
+++ b/drivers/ssb/Kconfig
@@ -89,15 +89,6 @@ config SSB_HOST_SOC
 
 	  If unsure, say N
 
-config SSB_DEBUG
-	bool "SSB debugging"
-	depends on SSB
-	help
-	  This turns on additional runtime checks and debugging
-	  messages. Turn this on for SSB troubleshooting.
-
-	  If unsure, say N
-
 config SSB_SERIAL
 	bool
 	depends on SSB
diff --git a/drivers/ssb/driver_chipcommon.c b/drivers/ssb/driver_chipcommon.c
index 48050c6fd847..99a4656d113d 100644
--- a/drivers/ssb/driver_chipcommon.c
+++ b/drivers/ssb/driver_chipcommon.c
@@ -56,7 +56,7 @@ void ssb_chipco_set_clockmode(struct ssb_chipcommon *cc,
 
 	if (cc->capabilities & SSB_CHIPCO_CAP_PMU)
 		return; /* PMU controls clockmode, separated function needed */
-	SSB_WARN_ON(ccdev->id.revision >= 20);
+	WARN_ON(ccdev->id.revision >= 20);
 
 	/* chipcommon cores prior to rev6 don't support dynamic clock control */
 	if (ccdev->id.revision < 6)
@@ -111,7 +111,7 @@ void ssb_chipco_set_clockmode(struct ssb_chipcommon *cc,
 		}
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 
@@ -164,7 +164,7 @@ static int chipco_pctl_clockfreqlimit(struct ssb_chipcommon *cc, int get_max)
 			divisor = 32;
 			break;
 		default:
-			SSB_WARN_ON(1);
+			WARN_ON(1);
 		}
 	} else if (cc->dev->id.revision < 10) {
 		switch (clocksrc) {
@@ -277,7 +277,7 @@ static void calc_fast_powerup_delay(struct ssb_chipcommon *cc)
 	minfreq = chipco_pctl_clockfreqlimit(cc, 0);
 	pll_on_delay = chipco_read32(cc, SSB_CHIPCO_PLLONDELAY);
 	tmp = (((pll_on_delay + 2) * 1000000) + (minfreq - 1)) / minfreq;
-	SSB_WARN_ON(tmp & ~0xFFFF);
+	WARN_ON(tmp & ~0xFFFF);
 
 	cc->fast_pwrup_delay = tmp;
 }
diff --git a/drivers/ssb/driver_chipcommon_pmu.c b/drivers/ssb/driver_chipcommon_pmu.c
index e28682a53cdf..0f60e90ded26 100644
--- a/drivers/ssb/driver_chipcommon_pmu.c
+++ b/drivers/ssb/driver_chipcommon_pmu.c
@@ -128,7 +128,7 @@ static void ssb_pmu0_pllinit_r0(struct ssb_chipcommon *cc,
 			      ~(1 << SSB_PMURES_5354_BB_PLL_PU));
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	for (i = 1500; i; i--) {
 		tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
@@ -265,7 +265,7 @@ static void ssb_pmu1_pllinit_r0(struct ssb_chipcommon *cc,
 		buffer_strength = 0x222222;
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	for (i = 1500; i; i--) {
 		tmp = chipco_read32(cc, SSB_CHIPCO_CLKCTLST);
@@ -501,7 +501,7 @@ static void ssb_pmu_resources_init(struct ssb_chipcommon *cc)
 					      ~(depend_tab[i].depend));
 				break;
 			default:
-				SSB_WARN_ON(1);
+				WARN_ON(1);
 			}
 		}
 	}
@@ -568,12 +568,12 @@ void ssb_pmu_set_ldo_voltage(struct ssb_chipcommon *cc,
 			mask = 0x3F;
 			break;
 		default:
-			SSB_WARN_ON(1);
+			WARN_ON(1);
 			return;
 		}
 		break;
 	case 0x4312:
-		if (SSB_WARN_ON(id != LDO_PAREF))
+		if (WARN_ON(id != LDO_PAREF))
 			return;
 		addr = 0;
 		shift = 21;
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index 6ce4abf7d473..e809dae4c470 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -461,7 +461,7 @@ int ssb_gpio_init(struct ssb_bus *bus)
 	else if (ssb_extif_available(&bus->extif))
 		return ssb_gpio_extif_init(bus);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 
 	return -1;
 }
@@ -473,7 +473,7 @@ int ssb_gpio_unregister(struct ssb_bus *bus)
 		gpiochip_remove(&bus->gpio);
 		return 0;
 	} else {
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	return -1;
diff --git a/drivers/ssb/driver_pcicore.c b/drivers/ssb/driver_pcicore.c
index ae80b3171523..6a5622e0ded5 100644
--- a/drivers/ssb/driver_pcicore.c
+++ b/drivers/ssb/driver_pcicore.c
@@ -115,7 +115,7 @@ static int ssb_extpci_read_config(struct ssb_pcicore *pc,
 	u32 addr, val;
 	void __iomem *mmio;
 
-	SSB_WARN_ON(!pc->hostmode);
+	WARN_ON(!pc->hostmode);
 	if (unlikely(len != 1 && len != 2 && len != 4))
 		goto out;
 	addr = get_cfgspace_addr(pc, bus, dev, func, off);
@@ -161,7 +161,7 @@ static int ssb_extpci_write_config(struct ssb_pcicore *pc,
 	u32 addr, val = 0;
 	void __iomem *mmio;
 
-	SSB_WARN_ON(!pc->hostmode);
+	WARN_ON(!pc->hostmode);
 	if (unlikely(len != 1 && len != 2 && len != 4))
 		goto out;
 	addr = get_cfgspace_addr(pc, bus, dev, func, off);
@@ -702,7 +702,7 @@ int ssb_pcicore_dev_irqvecs_enable(struct ssb_pcicore *pc,
 		/* Calculate the "coremask" for the device. */
 		coremask = (1 << dev->core_index);
 
-		SSB_WARN_ON(bus->bustype != SSB_BUSTYPE_PCI);
+		WARN_ON(bus->bustype != SSB_BUSTYPE_PCI);
 		err = pci_read_config_dword(bus->host_pci, SSB_PCI_IRQMASK, &tmp);
 		if (err)
 			goto out;
diff --git a/drivers/ssb/embedded.c b/drivers/ssb/embedded.c
index c39ddf8988c1..8254ed25e063 100644
--- a/drivers/ssb/embedded.c
+++ b/drivers/ssb/embedded.c
@@ -77,7 +77,7 @@ u32 ssb_gpio_in(struct ssb_bus *bus, u32 mask)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_in(&bus->extif, mask);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -95,7 +95,7 @@ u32 ssb_gpio_out(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_out(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -113,7 +113,7 @@ u32 ssb_gpio_outen(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_outen(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -145,7 +145,7 @@ u32 ssb_gpio_intmask(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_intmask(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
@@ -163,7 +163,7 @@ u32 ssb_gpio_polarity(struct ssb_bus *bus, u32 mask, u32 value)
 	else if (ssb_extif_available(&bus->extif))
 		res = ssb_extif_gpio_polarity(&bus->extif, mask, value);
 	else
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	spin_unlock_irqrestore(&bus->gpio_lock, flags);
 
 	return res;
diff --git a/drivers/ssb/host_soc.c b/drivers/ssb/host_soc.c
index eadaedf466f6..3b438480515c 100644
--- a/drivers/ssb/host_soc.c
+++ b/drivers/ssb/host_soc.c
@@ -61,7 +61,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u16): {
 		__le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			*buf = (__force __le16)__raw_readw(addr);
 			buf++;
@@ -72,7 +72,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u32): {
 		__le32 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			*buf = (__force __le32)__raw_readl(addr);
 			buf++;
@@ -81,7 +81,7 @@ static void ssb_host_soc_block_read(struct ssb_device *dev, void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 #endif /* CONFIG_SSB_BLOCKIO */
@@ -134,7 +134,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u16): {
 		const __le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			__raw_writew((__force u16)(*buf), addr);
 			buf++;
@@ -145,7 +145,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u32): {
 		const __le32 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			__raw_writel((__force u32)(*buf), addr);
 			buf++;
@@ -154,7 +154,7 @@ static void ssb_host_soc_block_write(struct ssb_device *dev, const void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 #endif /* CONFIG_SSB_BLOCKIO */
diff --git a/drivers/ssb/main.c b/drivers/ssb/main.c
index 9da56d2fdbd3..0a26984acb2c 100644
--- a/drivers/ssb/main.c
+++ b/drivers/ssb/main.c
@@ -209,7 +209,7 @@ int ssb_devices_freeze(struct ssb_bus *bus, struct ssb_freeze_context *ctx)
 
 	memset(ctx, 0, sizeof(*ctx));
 	ctx->bus = bus;
-	SSB_WARN_ON(bus->nr_devices > ARRAY_SIZE(ctx->device_frozen));
+	WARN_ON(bus->nr_devices > ARRAY_SIZE(ctx->device_frozen));
 
 	for (i = 0; i < bus->nr_devices; i++) {
 		sdev = ssb_device_get(&bus->devices[i]);
@@ -220,7 +220,7 @@ int ssb_devices_freeze(struct ssb_bus *bus, struct ssb_freeze_context *ctx)
 			continue;
 		}
 		sdrv = drv_to_ssb_drv(sdev->dev->driver);
-		if (SSB_WARN_ON(!sdrv->remove))
+		if (WARN_ON(!sdrv->remove))
 			continue;
 		sdrv->remove(sdev);
 		ctx->device_frozen[i] = 1;
@@ -248,10 +248,10 @@ int ssb_devices_thaw(struct ssb_freeze_context *ctx)
 			continue;
 		sdev = &bus->devices[i];
 
-		if (SSB_WARN_ON(!sdev->dev || !sdev->dev->driver))
+		if (WARN_ON(!sdev->dev || !sdev->dev->driver))
 			continue;
 		sdrv = drv_to_ssb_drv(sdev->dev->driver);
-		if (SSB_WARN_ON(!sdrv || !sdrv->probe))
+		if (WARN_ON(!sdrv || !sdrv->probe))
 			continue;
 
 		err = sdrv->probe(sdev, &sdev->id);
@@ -861,13 +861,13 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m)
 	case SSB_PLLTYPE_2: /* 48Mhz, 4 dividers */
 		n1 += SSB_CHIPCO_CLK_T2_BIAS;
 		n2 += SSB_CHIPCO_CLK_T2_BIAS;
-		SSB_WARN_ON(!((n1 >= 2) && (n1 <= 7)));
-		SSB_WARN_ON(!((n2 >= 5) && (n2 <= 23)));
+		WARN_ON(!((n1 >= 2) && (n1 <= 7)));
+		WARN_ON(!((n2 >= 5) && (n2 <= 23)));
 		break;
 	case SSB_PLLTYPE_5: /* 25Mhz, 4 dividers */
 		return 100000000;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	switch (plltype) {
@@ -916,9 +916,9 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m)
 		m1 += SSB_CHIPCO_CLK_T2_BIAS;
 		m2 += SSB_CHIPCO_CLK_T2M2_BIAS;
 		m3 += SSB_CHIPCO_CLK_T2_BIAS;
-		SSB_WARN_ON(!((m1 >= 2) && (m1 <= 7)));
-		SSB_WARN_ON(!((m2 >= 3) && (m2 <= 10)));
-		SSB_WARN_ON(!((m3 >= 2) && (m3 <= 7)));
+		WARN_ON(!((m1 >= 2) && (m1 <= 7)));
+		WARN_ON(!((m2 >= 3) && (m2 <= 10)));
+		WARN_ON(!((m3 >= 2) && (m3 <= 7)));
 
 		if (!(mc & SSB_CHIPCO_CLK_T2MC_M1BYP))
 			clock /= m1;
@@ -928,7 +928,7 @@ u32 ssb_calc_clock_rate(u32 plltype, u32 n, u32 m)
 			clock /= m3;
 		return clock;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	return 0;
 }
@@ -1169,9 +1169,7 @@ int ssb_bus_may_powerdown(struct ssb_bus *bus)
 	if (err)
 		goto error;
 out:
-#ifdef CONFIG_SSB_DEBUG
 	bus->powered_up = 0;
-#endif
 	return err;
 error:
 	pr_err("Bus powerdown failed\n");
@@ -1188,9 +1186,7 @@ int ssb_bus_powerup(struct ssb_bus *bus, bool dynamic_pctl)
 	if (err)
 		goto error;
 
-#ifdef CONFIG_SSB_DEBUG
 	bus->powered_up = 1;
-#endif
 
 	mode = dynamic_pctl ? SSB_CLKMODE_DYNAMIC : SSB_CLKMODE_FAST;
 	ssb_chipco_set_clockmode(&bus->chipco, mode);
@@ -1242,15 +1238,15 @@ u32 ssb_admatch_base(u32 adm)
 		base = (adm & SSB_ADM_BASE0);
 		break;
 	case SSB_ADM_TYPE1:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		base = (adm & SSB_ADM_BASE1);
 		break;
 	case SSB_ADM_TYPE2:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		base = (adm & SSB_ADM_BASE2);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	return base;
@@ -1266,15 +1262,15 @@ u32 ssb_admatch_size(u32 adm)
 		size = ((adm & SSB_ADM_SZ0) >> SSB_ADM_SZ0_SHIFT);
 		break;
 	case SSB_ADM_TYPE1:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		size = ((adm & SSB_ADM_SZ1) >> SSB_ADM_SZ1_SHIFT);
 		break;
 	case SSB_ADM_TYPE2:
-		SSB_WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
+		WARN_ON(adm & SSB_ADM_NEG); /* unsupported */
 		size = ((adm & SSB_ADM_SZ2) >> SSB_ADM_SZ2_SHIFT);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	size = (1 << (size + 1));
 
diff --git a/drivers/ssb/pci.c b/drivers/ssb/pci.c
index ad4308529eba..84807a9b4b13 100644
--- a/drivers/ssb/pci.c
+++ b/drivers/ssb/pci.c
@@ -946,7 +946,6 @@ out:
 	return err;
 }
 
-#ifdef CONFIG_SSB_DEBUG
 static int ssb_pci_assert_buspower(struct ssb_bus *bus)
 {
 	if (likely(bus->powered_up))
@@ -960,12 +959,6 @@ static int ssb_pci_assert_buspower(struct ssb_bus *bus)
 
 	return -ENODEV;
 }
-#else /* DEBUG */
-static inline int ssb_pci_assert_buspower(struct ssb_bus *bus)
-{
-	return 0;
-}
-#endif /* DEBUG */
 
 static u8 ssb_pci_read8(struct ssb_device *dev, u16 offset)
 {
@@ -1024,15 +1017,15 @@ static void ssb_pci_block_read(struct ssb_device *dev, void *buffer,
 		ioread8_rep(addr, buffer, count);
 		break;
 	case sizeof(u16):
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		ioread16_rep(addr, buffer, count >> 1);
 		break;
 	case sizeof(u32):
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		ioread32_rep(addr, buffer, count >> 2);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 
 	return;
@@ -1098,15 +1091,15 @@ static void ssb_pci_block_write(struct ssb_device *dev, const void *buffer,
 		iowrite8_rep(addr, buffer, count);
 		break;
 	case sizeof(u16):
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		iowrite16_rep(addr, buffer, count >> 1);
 		break;
 	case sizeof(u32):
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		iowrite32_rep(addr, buffer, count >> 2);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 }
 #endif /* CONFIG_SSB_BLOCKIO */
diff --git a/drivers/ssb/pcmcia.c b/drivers/ssb/pcmcia.c
index 20f63cc88e70..567013f8a8be 100644
--- a/drivers/ssb/pcmcia.c
+++ b/drivers/ssb/pcmcia.c
@@ -169,7 +169,7 @@ int ssb_pcmcia_switch_segment(struct ssb_bus *bus, u8 seg)
 	int err;
 	u8 val;
 
-	SSB_WARN_ON((seg != 0) && (seg != 1));
+	WARN_ON((seg != 0) && (seg != 1));
 	while (1) {
 		err = ssb_pcmcia_cfg_write(bus, SSB_PCMCIA_MEMSEG, seg);
 		if (err)
@@ -299,7 +299,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u16): {
 		__le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			*buf = (__force __le16)__raw_readw(addr);
 			buf++;
@@ -310,7 +310,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer,
 	case sizeof(u32): {
 		__le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			*buf = (__force __le16)__raw_readw(addr);
 			buf++;
@@ -321,7 +321,7 @@ static void ssb_pcmcia_block_read(struct ssb_device *dev, void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 unlock:
 	spin_unlock_irqrestore(&bus->bar_lock, flags);
@@ -399,7 +399,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u16): {
 		const __le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		while (count) {
 			__raw_writew((__force u16)(*buf), addr);
 			buf++;
@@ -410,7 +410,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 	case sizeof(u32): {
 		const __le16 *buf = buffer;
 
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		while (count) {
 			__raw_writew((__force u16)(*buf), addr);
 			buf++;
@@ -421,7 +421,7 @@ static void ssb_pcmcia_block_write(struct ssb_device *dev, const void *buffer,
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 unlock:
 	mmiowb();
diff --git a/drivers/ssb/scan.c b/drivers/ssb/scan.c
index 71fbb4b3eb6a..6ceee98ed6ff 100644
--- a/drivers/ssb/scan.c
+++ b/drivers/ssb/scan.c
@@ -210,7 +210,7 @@ void ssb_iounmap(struct ssb_bus *bus)
 #ifdef CONFIG_SSB_PCIHOST
 		pci_iounmap(bus->host_pci, bus->mmio);
 #else
-		SSB_BUG_ON(1); /* Can't reach this code. */
+		WARN_ON(1); /* Can't reach this code. */
 #endif
 		break;
 	case SSB_BUSTYPE_SDIO:
@@ -236,7 +236,7 @@ static void __iomem *ssb_ioremap(struct ssb_bus *bus,
 #ifdef CONFIG_SSB_PCIHOST
 		mmio = pci_iomap(bus->host_pci, 0, ~0UL);
 #else
-		SSB_BUG_ON(1); /* Can't reach this code. */
+		WARN_ON(1); /* Can't reach this code. */
 #endif
 		break;
 	case SSB_BUSTYPE_SDIO:
diff --git a/drivers/ssb/sdio.c b/drivers/ssb/sdio.c
index 1aedc5fbb62f..7fe0afb42234 100644
--- a/drivers/ssb/sdio.c
+++ b/drivers/ssb/sdio.c
@@ -316,18 +316,18 @@ static void ssb_sdio_block_read(struct ssb_device *dev, void *buffer,
 		break;
 	}
 	case sizeof(u16): {
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		error = sdio_readsb(bus->host_sdio, buffer, offset, count);
 		break;
 	}
 	case sizeof(u32): {
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		offset |= SBSDIO_SB_ACCESS_2_4B_FLAG;	/* 32 bit data access */
 		error = sdio_readsb(bus->host_sdio, buffer, offset, count);
 		break;
 	}
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	if (!error)
 		goto out;
@@ -423,18 +423,18 @@ static void ssb_sdio_block_write(struct ssb_device *dev, const void *buffer,
 				     (void *)buffer, count);
 		break;
 	case sizeof(u16):
-		SSB_WARN_ON(count & 1);
+		WARN_ON(count & 1);
 		error = sdio_writesb(bus->host_sdio, offset,
 				     (void *)buffer, count);
 		break;
 	case sizeof(u32):
-		SSB_WARN_ON(count & 3);
+		WARN_ON(count & 3);
 		offset |= SBSDIO_SB_ACCESS_2_4B_FLAG;	/* 32 bit data access */
 		error = sdio_writesb(bus->host_sdio, offset,
 				     (void *)buffer, count);
 		break;
 	default:
-		SSB_WARN_ON(1);
+		WARN_ON(1);
 	}
 	if (!error)
 		goto out;
diff --git a/drivers/ssb/ssb_private.h b/drivers/ssb/ssb_private.h
index 885e278c4487..5f31bdfbe77f 100644
--- a/drivers/ssb/ssb_private.h
+++ b/drivers/ssb/ssb_private.h
@@ -9,15 +9,6 @@
 #include <linux/types.h>
 #include <linux/bcm47xx_wdt.h>
 
-#ifdef CONFIG_SSB_DEBUG
-# define SSB_WARN_ON(x)		WARN_ON(x)
-# define SSB_BUG_ON(x)		BUG_ON(x)
-#else
-static inline int __ssb_do_nothing(int x) { return x; }
-# define SSB_WARN_ON(x)		__ssb_do_nothing(unlikely(!!(x)))
-# define SSB_BUG_ON(x)		__ssb_do_nothing(unlikely(!!(x)))
-#endif
-
 
 /* pci.c */
 #ifdef CONFIG_SSB_PCIHOST
diff --git a/include/linux/ssb/ssb.h b/include/linux/ssb/ssb.h
index 3b43655cabe6..0d5a2691e7e9 100644
--- a/include/linux/ssb/ssb.h
+++ b/include/linux/ssb/ssb.h
@@ -499,11 +499,9 @@ struct ssb_bus {
 
 	/* Internal-only stuff follows. Do not touch. */
 	struct list_head list;
-#ifdef CONFIG_SSB_DEBUG
 	/* Is the bus already powered up? */
 	bool powered_up;
 	int power_warn_count;
-#endif /* DEBUG */
 };
 
 enum ssb_quirks {
-- 
cgit v1.2.3


From 0a1c749dee4c52465d5580d77e0f8aaa9215c357 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 9 Aug 2018 10:54:46 -0500
Subject: block: paride: pd: mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1056543 ("Missing break in switch")
Addresses-Coverity-ID: 1056544 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/paride/pd.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/block/paride/pd.c b/drivers/block/paride/pd.c
index 8961b190e256..7cf947586fe4 100644
--- a/drivers/block/paride/pd.c
+++ b/drivers/block/paride/pd.c
@@ -426,6 +426,7 @@ static void run_fsm(void)
 				pd_claimed = 1;
 				if (!pi_schedule_claimed(pi_current, run_fsm))
 					return;
+				/* fall through */
 			case 1:
 				pd_claimed = 2;
 				pi_current->proto->connect(pi_current);
@@ -445,6 +446,7 @@ static void run_fsm(void)
 				spin_unlock_irqrestore(&pd_lock, saved_flags);
 				if (stop)
 					return;
+				/* fall through */
 			case Hold:
 				schedule_fsm();
 				return;
-- 
cgit v1.2.3


From 275e6fa8ecfd8ec1eb36a865d6dafc64f4bed462 Mon Sep 17 00:00:00 2001
From: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Date: Thu, 9 Aug 2018 15:18:12 +0530
Subject: drm/scheduler: fix param documentation

We no longer have sched parameter so remove its description
as well

Signed-off-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/scheduler/gpu_scheduler.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler.c b/drivers/gpu/drm/scheduler/gpu_scheduler.c
index a70c7f7fd6fe..4fc211e19d6e 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler.c
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler.c
@@ -249,7 +249,6 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f,
 /**
  * drm_sched_entity_flush - Flush a context entity
  *
- * @sched: scheduler instance
  * @entity: scheduler entity
  * @timeout: time to wait in for Q to become empty in jiffies.
  *
@@ -292,7 +291,6 @@ EXPORT_SYMBOL(drm_sched_entity_flush);
 /**
  * drm_sched_entity_cleanup - Destroy a context entity
  *
- * @sched: scheduler instance
  * @entity: scheduler entity
  *
  * This should be called after @drm_sched_entity_do_release. It goes over the
@@ -356,7 +354,6 @@ EXPORT_SYMBOL(drm_sched_entity_fini);
 /**
  * drm_sched_entity_fini - Destroy a context entity
  *
- * @sched: scheduler instance
  * @entity: scheduler entity
  *
  * Calls drm_sched_entity_do_release() and drm_sched_entity_cleanup()
@@ -719,7 +716,6 @@ EXPORT_SYMBOL(drm_sched_job_recovery);
  * drm_sched_job_init - init a scheduler job
  *
  * @job: scheduler job to init
- * @sched: scheduler instance
  * @entity: scheduler entity to use
  * @owner: job owner for debugging
  *
-- 
cgit v1.2.3


From b045d3af7d1f443dd5209a096568e0ce983127e9 Mon Sep 17 00:00:00 2001
From: Emily Deng <Emily.Deng@amd.com>
Date: Thu, 9 Aug 2018 10:03:04 +0800
Subject: drm/amdgpu/sriov: give 8s for recover vram under RUNTIME

Extend the timeout for recovering vram bos from shadows on sr-iov
to cover the worst case scenario for timeslices and VFs

Under runtime, the wait fence time could be quite long when
other VFs are in exclusive mode. For example, for 4 VF, every
VF's exclusive timeout time is set to 3s, then the worst case is
9s. If the VF number is more than 4,then the worst case time will
be longer.
The 8s is the test data, with setting to 8s, it will pass the TDR
test for 1000 times.

SWDEV-161490

Signed-off-by: Monk Liu <Monk.Liu@amd.com>
Signed-off-by: Emily Deng <Emily.Deng@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index ec53d8f96d06..3ef34df8937b 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -3105,7 +3105,7 @@ static int amdgpu_device_handle_vram_lost(struct amdgpu_device *adev)
 	long tmo;
 
 	if (amdgpu_sriov_runtime(adev))
-		tmo = msecs_to_jiffies(amdgpu_lockup_timeout);
+		tmo = msecs_to_jiffies(8000);
 	else
 		tmo = msecs_to_jiffies(100);
 
-- 
cgit v1.2.3


From 903fcf734f468afb5a3f153f870f58e4c1d5e525 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Thu, 9 Aug 2018 11:59:07 +0300
Subject: mlxsw: spectrum_flower: Disallow usage of vlan_id key on egress

As recent spectrum FW imposes a limitation on using vlan_id key for
egress ACL, disallow the usage of that key accordingly and return a
proper extack message.

Signed-off-by: Nir Dotan <nird@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h        |  1 +
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c    | 11 +++++++++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c |  5 +++++
 3 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 13eca1a79d52..0e02cfeba70d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -538,6 +538,7 @@ int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp,
 			      struct mlxsw_sp_acl_block *block,
 			      struct mlxsw_sp_port *mlxsw_sp_port,
 			      bool ingress);
+bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block);
 struct mlxsw_sp_acl_ruleset *
 mlxsw_sp_acl_ruleset_lookup(struct mlxsw_sp *mlxsw_sp,
 			    struct mlxsw_sp_acl_block *block, u32 chain_index,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 6a38763ad261..87f7433b004a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -158,6 +158,17 @@ bool mlxsw_sp_acl_block_disabled(struct mlxsw_sp_acl_block *block)
 	return block->disable_count;
 }
 
+bool mlxsw_sp_acl_block_is_egress_bound(struct mlxsw_sp_acl_block *block)
+{
+	struct mlxsw_sp_acl_block_binding *binding;
+
+	list_for_each_entry(binding, &block->binding_list, list) {
+		if (!binding->ingress)
+			return true;
+	}
+	return false;
+}
+
 static bool
 mlxsw_sp_acl_ruleset_is_singular(const struct mlxsw_sp_acl_ruleset *ruleset)
 {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 8213cb7190fa..8f3e0066dd53 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -386,6 +386,11 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp,
 			skb_flow_dissector_target(f->dissector,
 						  FLOW_DISSECTOR_KEY_VLAN,
 						  f->mask);
+
+		if (mlxsw_sp_acl_block_is_egress_bound(block)) {
+			NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress");
+			return -EOPNOTSUPP;
+		}
 		if (mask->vlan_id != 0)
 			mlxsw_sp_acl_rulei_keymask_u32(rulei,
 						       MLXSW_AFK_ELEMENT_VID,
-- 
cgit v1.2.3


From a716d55e4d52af551f250a54eb72882ddbc3fb87 Mon Sep 17 00:00:00 2001
From: Nir Dotan <nird@mellanox.com>
Date: Thu, 9 Aug 2018 11:59:08 +0300
Subject: mlxsw: spectrum: Update the supported firmware to version 13.1702.6

This new firmware contains:
        - Support for new types of cables
        - Support for flashing future firmware without reboot
        - Support for Router ARP BC and UC traps

Signed-off-by: Nir Dotan <nird@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 028ecc9aa5f1..ccda3640b9ed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -77,8 +77,8 @@
 #define MLXSW_SP_FWREV_MINOR_TO_BRANCH(minor) ((minor) / 100)
 
 #define MLXSW_SP1_FWREV_MAJOR 13
-#define MLXSW_SP1_FWREV_MINOR 1620
-#define MLXSW_SP1_FWREV_SUBMINOR 192
+#define MLXSW_SP1_FWREV_MINOR 1702
+#define MLXSW_SP1_FWREV_SUBMINOR 6
 
 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
 	.major = MLXSW_SP1_FWREV_MAJOR,
-- 
cgit v1.2.3


From c86d62cc410cc5ab54c7e53a0c58efd3a025cac3 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 9 Aug 2018 11:59:09 +0300
Subject: mlxsw: spectrum: Reset FW after flash

Recent FW fixes a bug and allows to load newly flashed FW image after
reset. So make sure the reset happens after flash. Indicate the need
down to PCI layer by -EAGAIN.

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.h     |  1 +
 drivers/net/ethernet/mellanox/mlxsw/pci.c      | 11 ++++++++++-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 17 +++++++++++++----
 3 files changed, 24 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 552cfa29c2f7..184d65b6abed 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -362,6 +362,7 @@ struct mlxsw_fw_rev {
 	u16 major;
 	u16 minor;
 	u16 subminor;
+	u16 can_reset_minor;
 };
 
 struct mlxsw_bus_info {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index fc4557245ff4..3a25250dc670 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1750,6 +1750,7 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	const char *driver_name = pdev->driver->name;
 	struct mlxsw_pci *mlxsw_pci;
+	bool called_again = false;
 	int err;
 
 	mlxsw_pci = kzalloc(sizeof(*mlxsw_pci), GFP_KERNEL);
@@ -1806,10 +1807,18 @@ static int mlxsw_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	mlxsw_pci->bus_info.dev = &pdev->dev;
 	mlxsw_pci->id = id;
 
+again:
 	err = mlxsw_core_bus_device_register(&mlxsw_pci->bus_info,
 					     &mlxsw_pci_bus, mlxsw_pci, false,
 					     NULL);
-	if (err) {
+	/* -EAGAIN is returned in case the FW was updated. FW needs
+	 * a reset, so lets try to call mlxsw_core_bus_device_register()
+	 * again.
+	 */
+	if (err == -EAGAIN && !called_again) {
+		called_again = true;
+		goto again;
+	} else if (err) {
 		dev_err(&pdev->dev, "cannot register bus device\n");
 		goto err_bus_device_register;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index ccda3640b9ed..e47c4e9f09a2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -79,11 +79,13 @@
 #define MLXSW_SP1_FWREV_MAJOR 13
 #define MLXSW_SP1_FWREV_MINOR 1702
 #define MLXSW_SP1_FWREV_SUBMINOR 6
+#define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702
 
 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = {
 	.major = MLXSW_SP1_FWREV_MAJOR,
 	.minor = MLXSW_SP1_FWREV_MINOR,
 	.subminor = MLXSW_SP1_FWREV_SUBMINOR,
+	.can_reset_minor = MLXSW_SP1_FWREV_CAN_RESET_MINOR,
 };
 
 #define MLXSW_SP1_FW_FILENAME \
@@ -380,7 +382,16 @@ static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp)
 
 	err = mlxsw_sp_firmware_flash(mlxsw_sp, firmware);
 	release_firmware(firmware);
-	return err;
+	if (err)
+		dev_err(mlxsw_sp->bus_info->dev, "Could not upgrade firmware\n");
+
+	/* On FW flash success, tell the caller FW reset is needed
+	 * if current FW supports it.
+	 */
+	if (rev->minor >= req_rev->can_reset_minor)
+		return err ? err : -EAGAIN;
+	else
+		return 0;
 }
 
 int mlxsw_sp_flow_counter_get(struct mlxsw_sp *mlxsw_sp,
@@ -3734,10 +3745,8 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core,
 	mlxsw_sp->bus_info = mlxsw_bus_info;
 
 	err = mlxsw_sp_fw_rev_validate(mlxsw_sp);
-	if (err) {
-		dev_err(mlxsw_sp->bus_info->dev, "Could not upgrade firmware\n");
+	if (err)
 		return err;
-	}
 
 	err = mlxsw_sp_base_mac_get(mlxsw_sp);
 	if (err) {
-- 
cgit v1.2.3


From 3dd91570564679e13c4755cc5cdf2a535e3e1e34 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@mellanox.com>
Date: Thu, 9 Aug 2018 11:59:10 +0300
Subject: selftests: mlxsw: Add TC flower test for Spectrum-2

Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Reviewed-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../drivers/net/mlxsw/spectrum-2/tc_flower.sh      | 366 +++++++++++++++++++++
 1 file changed, 366 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh

diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
new file mode 100755
index 000000000000..3b75180f455d
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
@@ -0,0 +1,366 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+# This test is for checking the A-TCAM and C-TCAM operation in Spectrum-2.
+# It tries to exercise as many code paths in the eRP state machine as
+# possible.
+
+lib_dir=$(dirname $0)/../../../../net/forwarding
+
+ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
+	multiple_masks_test ctcam_edge_cases_test"
+NUM_NETIFS=2
+source $lib_dir/tc_common.sh
+source $lib_dir/lib.sh
+
+tcflags="skip_hw"
+
+h1_create()
+{
+	simple_if_init $h1 192.0.2.1/24 198.51.100.1/24
+}
+
+h1_destroy()
+{
+	simple_if_fini $h1 192.0.2.1/24 198.51.100.1/24
+}
+
+h2_create()
+{
+	simple_if_init $h2 192.0.2.2/24 198.51.100.2/24
+	tc qdisc add dev $h2 clsact
+}
+
+h2_destroy()
+{
+	tc qdisc del dev $h2 clsact
+	simple_if_fini $h2 192.0.2.2/24 198.51.100.2/24
+}
+
+single_mask_test()
+{
+	# When only a single mask is required, the device uses the master
+	# mask and not the eRP table. Verify that under this mode the right
+	# filter is matched
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_err $? "Single filter - did not match"
+
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 198.51.100.2 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 2
+	check_err $? "Two filters - did not match highest priority"
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Two filters - did not match lowest priority"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 198.51.100.1 -B 198.51.100.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 2
+	check_err $? "Single filter - did not match after delete"
+
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+	log_test "single mask test ($tcflags)"
+}
+
+identical_filters_test()
+{
+	# When two filters that only differ in their priority are used,
+	# one needs to be inserted into the C-TCAM. This test verifies
+	# that filters are correctly spilled to C-TCAM and that the right
+	# filter is matched
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_err $? "Did not match A-TCAM filter"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Did not match C-TCAM filter after A-TCAM delete"
+
+	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 2
+	check_err $? "Did not match C-TCAM filter after A-TCAM add"
+
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_err $? "Did not match A-TCAM filter after C-TCAM delete"
+
+	tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+
+	log_test "identical filters test ($tcflags)"
+}
+
+two_masks_test()
+{
+	# When more than one mask is required, the eRP table is used. This
+	# test verifies that the eRP table is correctly allocated and used
+
+	RET=0
+
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+		$tcflags dst_ip 192.0.0.0/16 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_err $? "Two filters - did not match highest priority"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_err $? "Single filter - did not match"
+
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 192.0.2.0/24 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Two filters - did not match highest priority after add"
+
+	tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+	log_test "two masks test ($tcflags)"
+}
+
+multiple_masks_test()
+{
+	# The number of masks in a region is limited. Once the maximum
+	# number of masks has been reached filters that require new
+	# masks are spilled to the C-TCAM. This test verifies that
+	# spillage is performed correctly and that the right filter is
+	# matched
+
+	local index
+
+	RET=0
+
+	NUM_MASKS=32
+	BASE_INDEX=100
+
+	for i in $(eval echo {1..$NUM_MASKS}); do
+		index=$((BASE_INDEX - i))
+
+		tc filter add dev $h2 ingress protocol ip pref $index \
+			handle $index \
+			flower $tcflags dst_ip 192.0.2.2/${i} src_ip 192.0.2.1 \
+			action drop
+
+		$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 \
+			-B 192.0.2.2 -t ip -q
+
+		tc_check_packets "dev $h2 ingress" $index 1
+		check_err $? "$i filters - did not match highest priority (add)"
+	done
+
+	for i in $(eval echo {$NUM_MASKS..1}); do
+		index=$((BASE_INDEX - i))
+
+		$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 \
+			-B 192.0.2.2 -t ip -q
+
+		tc_check_packets "dev $h2 ingress" $index 2
+		check_err $? "$i filters - did not match highest priority (del)"
+
+		tc filter del dev $h2 ingress protocol ip pref $index \
+			handle $index flower
+	done
+
+	log_test "multiple masks test ($tcflags)"
+}
+
+ctcam_two_atcam_masks_test()
+{
+	RET=0
+
+	# First case: C-TCAM is disabled when there are two A-TCAM masks.
+	# We push a filter into the C-TCAM by using two identical filters
+	# as in identical_filters_test()
+
+	# Filter goes into A-TCAM
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	# Filter goes into C-TCAM
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	# Filter goes into A-TCAM
+	tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \
+		$tcflags dst_ip 192.0.2.0/24 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_err $? "Did not match A-TCAM filter"
+
+	# Delete both A-TCAM and C-TCAM filters and make sure the remaining
+	# A-TCAM filter still works
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 103 1
+	check_err $? "Did not match A-TCAM filter"
+
+	tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower
+
+	log_test "ctcam with two atcam masks test ($tcflags)"
+}
+
+ctcam_one_atcam_mask_test()
+{
+	RET=0
+
+	# Second case: C-TCAM is disabled when there is one A-TCAM mask.
+	# The test is similar to identical_filters_test()
+
+	# Filter goes into A-TCAM
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	# Filter goes into C-TCAM
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 101 1
+	check_err $? "Did not match C-TCAM filter"
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+
+	$MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+		-t ip -q
+
+	tc_check_packets "dev $h2 ingress" 102 1
+	check_err $? "Did not match A-TCAM filter"
+
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+	log_test "ctcam with one atcam mask test ($tcflags)"
+}
+
+ctcam_no_atcam_masks_test()
+{
+	RET=0
+
+	# Third case: C-TCAM is disabled when there are no A-TCAM masks
+	# This test exercises the code path that transitions the eRP table
+	# to its initial state after deleting the last C-TCAM mask
+
+	# Filter goes into A-TCAM
+	tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+	# Filter goes into C-TCAM
+	tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \
+		$tcflags dst_ip 192.0.2.2 action drop
+
+	tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower
+	tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower
+
+	log_test "ctcam with no atcam masks test ($tcflags)"
+}
+
+ctcam_edge_cases_test()
+{
+	# When the C-TCAM is disabled after deleting the last C-TCAM
+	# mask, we want to make sure the eRP state machine is put in
+	# the correct state
+
+	ctcam_two_atcam_masks_test
+	ctcam_one_atcam_mask_test
+	ctcam_no_atcam_masks_test
+}
+
+setup_prepare()
+{
+	h1=${NETIFS[p1]}
+	h2=${NETIFS[p2]}
+	h1mac=$(mac_get $h1)
+	h2mac=$(mac_get $h2)
+
+	vrf_prepare
+
+	h1_create
+	h2_create
+}
+
+cleanup()
+{
+	pre_cleanup
+
+	h2_destroy
+	h1_destroy
+
+	vrf_cleanup
+}
+
+trap cleanup EXIT
+
+setup_prepare
+setup_wait
+
+tests_run
+
+if ! tc_offload_check; then
+	check_err 1 "Could not test offloaded functionality"
+	log_test "mlxsw-specific tests for tc flower"
+	exit
+else
+	tcflags="skip_sw"
+	tests_run
+fi
+
+exit $EXIT_STATUS
-- 
cgit v1.2.3


From 9948a0641a17a38935a28d05f6c56d9d1ffabae6 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Thu, 9 Aug 2018 11:59:11 +0300
Subject: mlxsw: Replace license text with SPDX identifiers and adjust
 copyrights

Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/cmd.h          | 36 ++------------------
 drivers/net/ethernet/mellanox/mlxsw/core.c         | 37 ++------------------
 drivers/net/ethernet/mellanox/mlxsw/core.h         | 37 ++------------------
 .../mellanox/mlxsw/core_acl_flex_actions.c         | 35 ++-----------------
 .../mellanox/mlxsw/core_acl_flex_actions.h         | 35 ++-----------------
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.c   | 35 ++-----------------
 .../ethernet/mellanox/mlxsw/core_acl_flex_keys.h   | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c   | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/core_thermal.c | 32 ++----------------
 drivers/net/ethernet/mellanox/mlxsw/emad.h         | 36 ++------------------
 drivers/net/ethernet/mellanox/mlxsw/i2c.c          | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/i2c.h          | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/ib.h           | 36 ++------------------
 drivers/net/ethernet/mellanox/mlxsw/item.h         | 36 ++------------------
 drivers/net/ethernet/mellanox/mlxsw/minimal.c      | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/pci.c          | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/pci.h          | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h       | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/port.h         | 38 ++-------------------
 drivers/net/ethernet/mellanox/mlxsw/reg.h          | 39 ++--------------------
 drivers/net/ethernet/mellanox/mlxsw/resources.h    | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c     | 37 ++------------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum.h     | 37 ++------------------
 .../ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c   | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c   | 35 ++-----------------
 .../ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c    | 36 ++------------------
 .../ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c   | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c   | 35 ++-----------------
 .../ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c    | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c | 35 ++-----------------
 .../ethernet/mellanox/mlxsw/spectrum_acl_atcam.c   | 36 ++------------------
 .../ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c   | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c | 35 ++-----------------
 .../mellanox/mlxsw/spectrum_acl_flex_actions.c     | 36 ++------------------
 .../mellanox/mlxsw/spectrum_acl_flex_actions.h     | 36 ++------------------
 .../mellanox/mlxsw/spectrum_acl_flex_keys.c        | 35 ++-----------------
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.c    | 35 ++-----------------
 .../ethernet/mellanox/mlxsw/spectrum_acl_tcam.h    | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_buffers.c | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_dpipe.c   | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_dpipe.h   | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_flower.c  | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_ipip.c    | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_ipip.h    | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_kvdl.c    | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c  | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h  | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c | 36 ++------------------
 .../net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_qdisc.c   | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_router.c  | 38 ++-------------------
 .../net/ethernet/mellanox/mlxsw/spectrum_router.h  | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_span.c    | 35 ++-----------------
 .../net/ethernet/mellanox/mlxsw/spectrum_span.h    | 34 ++-----------------
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c   | 37 ++------------------
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.h   | 34 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/switchib.c     | 35 ++-----------------
 drivers/net/ethernet/mellanox/mlxsw/switchx2.c     | 37 ++------------------
 drivers/net/ethernet/mellanox/mlxsw/trap.h         | 38 ++-------------------
 drivers/net/ethernet/mellanox/mlxsw/txheader.h     | 36 ++------------------
 64 files changed, 131 insertions(+), 2139 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
index 2bc48054b685..0772e4339b33 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/cmd.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CMD_H
 #define _MLXSW_CMD_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index f9c724752a32..b5d5e57f1583 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h
index 184d65b6abed..655ddd204ab2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.h
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CORE_H
 #define _MLXSW_CORE_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
index 66ea256fe560..c51b2adfc1e1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.c
- * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
index a6ffadd30807..0e3a59dda12e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_actions.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CORE_ACL_FLEX_ACTIONS_H
 #define _MLXSW_CORE_ACL_FLEX_ACTIONS_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
index 9649b4d9349a..785bf01fe2be 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
index 18d9bfed6001..c29c045d826d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_acl_flex_keys.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_CORE_ACL_FLEX_KEYS_H
 #define _MLXSW_CORE_ACL_FLEX_KEYS_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
index 84185f8dfbae..f6cf2896d337 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_hwmon.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index d866c98c1a97..6d29dc428608 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -1,34 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved
  * Copyright (c) 2016 Ivan Vecera <cera@cera.cz>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
  */
 
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/emad.h b/drivers/net/ethernet/mellanox/mlxsw/emad.h
index 97b6bb5d9185..a33b896f4bb8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/emad.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/emad.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/emad.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_EMAD_H
 #define _MLXSW_EMAD_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index 25f9915ebd82..bd255417751b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/i2c.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/err.h>
 #include <linux/i2c.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.h b/drivers/net/ethernet/mellanox/mlxsw/i2c.h
index daa24b213ea4..17e059d47fae 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/i2c.h
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_I2C_H
 #define _MLXSW_I2C_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/ib.h b/drivers/net/ethernet/mellanox/mlxsw/ib.h
index ce313aaa6336..2d0cb0f5eb85 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/ib.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/ib.h
@@ -1,36 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/ib.h
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXSW_IB_H
 #define _MLXSW_IB_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/item.h b/drivers/net/ethernet/mellanox/mlxsw/item.h
index 31c886edc791..e92cadc98128 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/item.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/item.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/item.h
- * Copyright (c) 2015-2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_ITEM_H
 #define _MLXSW_ITEM_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/minimal.c b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
index 3dd16267b76c..5a6c4457fb55 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/minimal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/minimal.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/minimal.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Vadim Pasternak <vadimp@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/i2c.h>
 #include <linux/kernel.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 3a25250dc670..4bec4f6b80ca 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/pci.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h
index 7461f8fe1133..946339e13eb9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/pci.h
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_PCI_H
 #define _MLXSW_PCI_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 963155f6a17a..83f452b7ccbb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
- * Copyright (c) 2015-2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2016 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_PCI_HW_H
 #define _MLXSW_PCI_HW_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/port.h b/drivers/net/ethernet/mellanox/mlxsw/port.h
index c580abba8d34..a33eeef0b00c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/port.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/port.h
@@ -1,38 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/port.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXSW_PORT_H
 #define _MLXSW_PORT_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h
index 9f344914c4a5..6e8b619b769b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/reg.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h
@@ -1,40 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/reg.h
- * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2016 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com>
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_REG_H
 #define _MLXSW_REG_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h
index bf650f2cd5af..79a31de7c825 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/resources.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/resources.h
- * Copyright (c) 2016-2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016-2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_RESOURCES_H
 #define _MLXSW_RESOURCES_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index e47c4e9f09a2..6a0235395ac4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum.c
- * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index 0e02cfeba70d..3ae930196741 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum.h
- * Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015-2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_H
 #define _MLXSW_SPECTRUM_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
index 5c8956573632..2a9eac90002e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum1_acl_tcam.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
index 0d4583894a97..09ee0a807747 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum1_kvdl.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
index fc649fe7134e..c8c67536917b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum1_mr_tcam.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/parman.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
index 22c876496379..8ca77f3e8f27 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum2_acl_tcam.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
index bacf7483c3fb..68c8b148bef2 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum2_kvdl.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
index 53d4ab70da95..4dd62478162e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum2_mr_tcam.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
index 87f7433b004a..c4f9238591e6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
index 3a05e0b3f730..2dda028f94db 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2018 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/err.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
index 7440a1189250..e3c6fe8b1d40 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_ctcam.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
index 463590bbb348..0a4fd3c8662a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/bitmap.h>
 #include <linux/errno.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
index bca0def756cd..e47d1d286e93 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.c
- * Copyright (c) 2017, 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include "spectrum_acl_flex_actions.h"
 #include "core_acl_flex_actions.h"
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
index bd6d552d95b9..fe436d816d0c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_actions.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_ACL_FLEX_ACTIONS_H
 #define _MLXSW_SPECTRUM_ACL_FLEX_ACTIONS_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
index aa8927cee376..d409b09ba8df 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_flex_keys.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
index 245e2f473c6f..e171513bb32a 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
index 881ade760ace..219a4e26c332 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_ACL_TCAM_H
 #define _MLXSW_SPECTRUM_ACL_TCAM_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
index 0a9adc5962fb..4327487553c5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
index 0f46775e0307..83c2e1e5f216 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
index fd34d0a01073..81465e267b10 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_cnt.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkdis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_CNT_H
 #define _MLXSW_SPECTRUM_CNT_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
index c31aeb25ab5a..b25048c6c761 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_dcb.c
- * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/netdevice.h>
 #include <linux/string.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
index f56fa18d6b26..41e607a14846 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arakdis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <net/devlink.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
index 815d543cf114..e689576231ab 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_dpipe.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_PIPELINE_H_
 #define _MLXSW_PIPELINE_H_
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
index 54262af4e98f..715d24ff937e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_fid.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/bitops.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 8f3e0066dd53..75e5316ffebd 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
index 98d896c14b87..00db26c96bf5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <net/ip_tunnels.h>
 #include <net/ip6_tunnel.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
index 6909d867bb59..bb5c4d4a5872 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_ipip.h
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_IPIP_H_
 #define _MLXSW_IPIP_H_
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
index fd557585514d..1e4cdee7bcd7 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_kvdl.c
- * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016-2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
index 98dcaf78365c..54275624718b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/rhashtable.h>
 #include <net/ipv6.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
index c92fa90dca31..3cde3671fe35 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_MCROUTER_H
 #define _MLXSW_SPECTRUM_MCROUTER_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
index e9c9f1f45b9d..346f4a5fe053 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.c
- * Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- * Copyright (c) 2018 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/list.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
index f9b59ee25406..3c84151b4c33 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_mr_tcam.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_MCROUTER_TCAM_H
 #define _MLXSW_SPECTRUM_MCROUTER_TCAM_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
index cad603c35271..bdf53cf350f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_qdisc.c
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Nogah Frankel <nogahf@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/errno.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index eec7166fad62..3a96307f51b0 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -1,39 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
- * Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2016 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2016 Yotam Gigi <yotamg@mellanox.com>
- * Copyright (c) 2017-2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 52e25695625c..1a60391daafa 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
- * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2017 Arkadi Sharshevsky <arkadis@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2017-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_ROUTER_H_
 #define _MLXSW_ROUTER_H_
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
index e42d640cddab..d965fd275c90 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.c
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2018 Petr Machata <petrm@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/if_bridge.h>
 #include <linux/list.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
index 14a6de904db1..5e04252f2a11 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h
@@ -1,35 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/mlxsw_span.h
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_SPECTRUM_SPAN_H
 #define _MLXSW_SPECTRUM_SPAN_H
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index da94e1eb9e16..0d8444aaba01 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/types.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
index bc44d5effc28..c218e10bd835 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
@@ -1,35 +1,5 @@
-/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
- * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h
- * Copyright (c) 2018 Mellanox Technologies. All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/netdevice.h>
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchib.c b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
index c698ec4fd9d4..bcf2e79a21c8 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchib.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchib.c
@@ -1,36 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/switchib.c
- * Copyright (c) 2016 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2016 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2016-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
index 3922c1cfe5f5..2d4f213e154d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c
@@ -1,38 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/switchx2.c
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015-2016 Elad Raz <eladr@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index eb437f59640d..53020724c2f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -1,38 +1,6 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/trap.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Elad Raz <eladr@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
+
 #ifndef _MLXSW_TRAP_H
 #define _MLXSW_TRAP_H
 
diff --git a/drivers/net/ethernet/mellanox/mlxsw/txheader.h b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
index fdf94720ca62..da51dd9d5e44 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/txheader.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/txheader.h
@@ -1,37 +1,5 @@
-/*
- * drivers/net/ethernet/mellanox/mlxsw/txheader.h
- * Copyright (c) 2015 Mellanox Technologies. All rights reserved.
- * Copyright (c) 2015 Ido Schimmel <idosch@mellanox.com>
- * Copyright (c) 2015 Jiri Pirko <jiri@mellanox.com>
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions are met:
- *
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- * 3. Neither the names of the copyright holders nor the names of its
- *    contributors may be used to endorse or promote products derived from
- *    this software without specific prior written permission.
- *
- * Alternatively, this software may be distributed under the terms of the
- * GNU General Public License ("GPL") version 2 as published by the Free
- * Software Foundation.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
- * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
- * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
- * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
- * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
- * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
- * POSSIBILITY OF SUCH DAMAGE.
- */
+/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 */
+/* Copyright (c) 2015-2018 Mellanox Technologies. All rights reserved */
 
 #ifndef _MLXSW_TXHEADER_H
 #define _MLXSW_TXHEADER_H
-- 
cgit v1.2.3


From 9897dce2e39aa2f1fa7260b4a936a34f3fc6e775 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 9 Aug 2018 11:59:12 +0300
Subject: mlxsw: spectrum: Include RFC-2819 counters in stats length

The function mlxsw_sp_port_get_sset_count() is supposed to return the
total number of ethtool strings that mlxsw supports. Specifically for
names of statistic counters (the only string type that mlxsw supports
as of now), that number is stored in MLXSW_SP_PORT_ETHTOOL_STATS_LEN.
However, when adding RFC-2891 counters, that define wasn't updated to
include the new counters. As a result, ethtool snips out the counters
towards the end of the list, which contains per-TC counters, and only
the first three traffic classes end up being reported.

Fix by adding MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN as appropriate.

Fixes: 1222d15a01c7 ("mlxsw: spectrum: Expose counters for various packet sizes")
Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 6a0235395ac4..264e3aa805da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1971,6 +1971,7 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 #define MLXSW_SP_PORT_HW_TC_STATS_LEN ARRAY_SIZE(mlxsw_sp_port_hw_tc_stats)
 
 #define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \
+					 MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \
 					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN + \
 					  MLXSW_SP_PORT_HW_TC_STATS_LEN) * \
 					 IEEE_8021QAZ_MAX_TCS)
-- 
cgit v1.2.3


From 88cc318ebd8740eae4784566757cbbc760244f5b Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@mellanox.com>
Date: Thu, 9 Aug 2018 11:59:13 +0300
Subject: mlxsw: spectrum: Expose counter for all 16 TCs

Before MC-aware mode was enabled in commit 7b8195306694 ("mlxsw:
spectrum: Configure MC-aware mode on mlxsw ports"), only 8 traffic
classes were used. Under MC-aware regime, however, besides using TCs
0-7 for UC traffic, it additionally uses TCs 8-15 for BUM traffic. It
is therefore desirable to show counters for these TCs as well.

Update ethtool stats pool length, mlxsw_sp_port_get_strings() and
mlxsw_sp_port_get_stats() to include artifacts for all 16 TCs. For
consistency and simplicity, expose tc_no_buffer_discard_uc_tc for BUM
TCs as well, even though it ought to stay at 0 all the time.

Signed-off-by: Petr Machata <petrm@mellanox.com>
Signed-off-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 264e3aa805da..6070d1591d1e 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1972,9 +1972,10 @@ static struct mlxsw_sp_port_hw_stats mlxsw_sp_port_hw_tc_stats[] = {
 
 #define MLXSW_SP_PORT_ETHTOOL_STATS_LEN (MLXSW_SP_PORT_HW_STATS_LEN + \
 					 MLXSW_SP_PORT_HW_RFC_2819_STATS_LEN + \
-					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN + \
-					  MLXSW_SP_PORT_HW_TC_STATS_LEN) * \
-					 IEEE_8021QAZ_MAX_TCS)
+					 (MLXSW_SP_PORT_HW_PRIO_STATS_LEN * \
+					  IEEE_8021QAZ_MAX_TCS) + \
+					 (MLXSW_SP_PORT_HW_TC_STATS_LEN * \
+					  TC_MAX_QUEUE))
 
 static void mlxsw_sp_port_get_prio_strings(u8 **p, int prio)
 {
@@ -2020,7 +2021,7 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev,
 		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
 			mlxsw_sp_port_get_prio_strings(&p, i);
 
-		for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++)
+		for (i = 0; i < TC_MAX_QUEUE; i++)
 			mlxsw_sp_port_get_tc_strings(&p, i);
 
 		break;
@@ -2125,7 +2126,7 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev,
 	}
 
 	/* Per-TC Counters */
-	for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) {
+	for (i = 0; i < TC_MAX_QUEUE; i++) {
 		__mlxsw_sp_port_get_stats(dev, MLXSW_REG_PPCNT_TC_CNT, i,
 					  data, data_index);
 		data_index += MLXSW_SP_PORT_HW_TC_STATS_LEN;
-- 
cgit v1.2.3


From b9763cdfd4a91a34f95ccc5e881ff2aa366197ef Mon Sep 17 00:00:00 2001
From: Marcel Holtmann <marcel@holtmann.org>
Date: Thu, 9 Aug 2018 10:33:07 +0200
Subject: Bluetooth: Introduce BT_HCIUART_RTL configuration option

Like all the other UART protocols, introduce a configuration option for
Realtek based serial devices.

Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Johan Hedberg <johan.hedberg@intel.com>
---
 drivers/bluetooth/Kconfig  | 13 +++++++++++++
 drivers/bluetooth/hci_h5.c |  4 ++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index c3736103c2ac..2df11cc08a46 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -195,6 +195,19 @@ config BT_HCIUART_BCM
 
 	  Say Y here to compile support for Broadcom protocol.
 
+config BT_HCIUART_RTL
+	bool "Realtek protocol support"
+	depends on BT_HCIUART
+	depends on BT_HCIUART_SERDEV
+	depends on GPIOLIB
+	select BT_HCIUART_3WIRE
+	select BT_RTL
+	help
+	  The Realtek protocol support enables Bluetooth HCI over 3-Wire
+	  serial port internface for Realtek Bluetooth controllers.
+
+	  Say Y here to compile support for Realtek protocol.
+
 config BT_HCIUART_QCA
 	bool "Qualcomm Atheros protocol support"
 	depends on BT_HCIUART
diff --git a/drivers/bluetooth/hci_h5.c b/drivers/bluetooth/hci_h5.c
index 63c0dcbc4914..8eede1197cd2 100644
--- a/drivers/bluetooth/hci_h5.c
+++ b/drivers/bluetooth/hci_h5.c
@@ -841,6 +841,7 @@ static void h5_serdev_remove(struct serdev_device *serdev)
 	hci_uart_unregister_device(&h5->serdev_hu);
 }
 
+#ifdef CONFIG_BT_HCIUART_RTL
 static int h5_btrtl_setup(struct h5 *h5)
 {
 	struct btrtl_device_info *btrtl_dev;
@@ -922,10 +923,13 @@ static struct h5_vnd rtl_vnd = {
 	.close		= h5_btrtl_close,
 	.acpi_gpio_map	= acpi_btrtl_gpios,
 };
+#endif
 
 #ifdef CONFIG_ACPI
 static const struct acpi_device_id h5_acpi_match[] = {
+#ifdef CONFIG_BT_HCIUART_RTL
 	{ "OBDA8723", (kernel_ulong_t)&rtl_vnd },
+#endif
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, h5_acpi_match);
-- 
cgit v1.2.3


From 54186b91bde1711080d0b23ce25f0bee5a058fc9 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:37 +0200
Subject: net: dsa: mv88e6xxx: Add support to enabling pause

The 6185 can enable/disable 802.3z pause be setting the MyPause bit in
the port status register. Add an op to support this.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 20 ++++++++++++++++----
 drivers/net/dsa/mv88e6xxx/chip.h |  7 +++++++
 drivers/net/dsa/mv88e6xxx/port.c | 23 +++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/port.h |  2 ++
 4 files changed, 48 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 0b5a2c31f395..f7522d001365 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -524,7 +524,7 @@ int mv88e6xxx_update(struct mv88e6xxx_chip *chip, int addr, int reg, u16 update)
 }
 
 static int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port,
-				    int link, int speed, int duplex,
+				    int link, int speed, int duplex, int pause,
 				    phy_interface_t mode)
 {
 	int err;
@@ -543,6 +543,12 @@ static int mv88e6xxx_port_setup_mac(struct mv88e6xxx_chip *chip, int port,
 			goto restore_link;
 	}
 
+	if (chip->info->ops->port_set_pause) {
+		err = chip->info->ops->port_set_pause(chip, port, pause);
+		if (err)
+			goto restore_link;
+	}
+
 	if (chip->info->ops->port_set_duplex) {
 		err = chip->info->ops->port_set_duplex(chip, port, duplex);
 		if (err && err != -EOPNOTSUPP)
@@ -584,7 +590,8 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
 
 	mutex_lock(&chip->reg_lock);
 	err = mv88e6xxx_port_setup_mac(chip, port, phydev->link, phydev->speed,
-				       phydev->duplex, phydev->interface);
+				       phydev->duplex, phydev->pause,
+				       phydev->interface);
 	mutex_unlock(&chip->reg_lock);
 
 	if (err && err != -EOPNOTSUPP)
@@ -615,7 +622,7 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 				 const struct phylink_link_state *state)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
-	int speed, duplex, link, err;
+	int speed, duplex, link, pause, err;
 
 	if (mode == MLO_AN_PHY)
 		return;
@@ -629,9 +636,10 @@ static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port,
 		duplex = DUPLEX_UNFORCED;
 		link = LINK_UNFORCED;
 	}
+	pause = !!phylink_test(state->advertising, Pause);
 
 	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex,
+	err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex, pause,
 				       state->interface);
 	mutex_unlock(&chip->reg_lock);
 
@@ -2087,10 +2095,12 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	if (dsa_is_cpu_port(ds, port) || dsa_is_dsa_port(ds, port))
 		err = mv88e6xxx_port_setup_mac(chip, port, LINK_FORCED_UP,
 					       SPEED_MAX, DUPLEX_FULL,
+					       PAUSE_OFF,
 					       PHY_INTERFACE_MODE_NA);
 	else
 		err = mv88e6xxx_port_setup_mac(chip, port, LINK_UNFORCED,
 					       SPEED_UNFORCED, DUPLEX_UNFORCED,
+					       PAUSE_ON,
 					       PHY_INTERFACE_MODE_NA);
 	if (err)
 		return err;
@@ -2729,6 +2739,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.port_set_jumbo_size = mv88e6165_port_set_jumbo_size,
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_limit = mv88e6097_port_pause_limit,
+	.port_set_pause = mv88e6185_port_set_pause,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3021,6 +3032,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
+	.port_set_pause = mv88e6185_port_set_pause,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 6aa6197ddc10..92ebfd271168 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -351,6 +351,13 @@ struct mv88e6xxx_ops {
 	 */
 	int (*port_set_duplex)(struct mv88e6xxx_chip *chip, int port, int dup);
 
+#define PAUSE_ON		1
+#define PAUSE_OFF		0
+
+	/* Enable/disable sending Pause */
+	int (*port_set_pause)(struct mv88e6xxx_chip *chip, int port,
+			      int pause);
+
 #define SPEED_MAX		INT_MAX
 #define SPEED_UNFORCED		-2
 
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 429d0ebcd5b1..c0701deaca6a 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -36,6 +36,29 @@ int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
 	return mv88e6xxx_write(chip, addr, reg, val);
 }
 
+/* Offset 0x00: MAC (or PCS or Physical) Status Register
+ *
+ * For most devices, this is read only. However the 6185 has the MyPause
+ * bit read/write.
+ */
+int mv88e6185_port_set_pause(struct mv88e6xxx_chip *chip, int port,
+			     int pause)
+{
+	u16 reg;
+	int err;
+
+	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
+	if (err)
+		return err;
+
+	if (pause)
+		reg |= MV88E6XXX_PORT_STS_MY_PAUSE;
+	else
+		reg &= ~MV88E6XXX_PORT_STS_MY_PAUSE;
+
+	return mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_STS, reg);
+}
+
 /* Offset 0x01: MAC (or PCS or Physical) Control Register
  *
  * Link, Duplex and Flow Control have one force bit, one value bit.
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 5e1db1b221ca..44916251567b 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -242,6 +242,8 @@ int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
 int mv88e6xxx_port_write(struct mv88e6xxx_chip *chip, int port, int reg,
 			 u16 val);
 
+int mv88e6185_port_set_pause(struct mv88e6xxx_chip *chip, int port,
+			     int pause);
 int mv88e6352_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
 				   phy_interface_t mode);
 int mv88e6390_port_set_rgmii_delay(struct mv88e6xxx_chip *chip, int port,
-- 
cgit v1.2.3


From 624c0f0239f04cce78c86afa95eb2841c84fbab1 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 9 Aug 2018 15:38:38 +0200
Subject: phylink: add helper for configuring 2500BaseX modes

Add a helper for MAC drivers to use in their validate callback to deal
with 2500BaseX vs 1000BaseX modes, where the hardware supports both
but it is not possible to automatically select between them.

This helper defaults to 1000BaseX, as that is the 802.3 standard, and
will allow users to select 2500BaseX either by forcing the speed if
AN is disabled, or by changing the advertising mask if AN is enabled.
Disabling AN is not recommended as it is only the speed that we're
interested in controlling, not the duplex or pause mode parameters.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phylink.c | 30 ++++++++++++++++++++++++++++++
 include/linux/phylink.h   |  1 +
 2 files changed, 31 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index af4dc4425be2..3ba5cf2a8a5f 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1688,4 +1688,34 @@ static const struct sfp_upstream_ops sfp_phylink_ops = {
 	.disconnect_phy = phylink_sfp_disconnect_phy,
 };
 
+/* Helpers for MAC drivers */
+
+/**
+ * phylink_helper_basex_speed() - 1000BaseX/2500BaseX helper
+ * @state: a pointer to a &struct phylink_link_state
+ *
+ * Inspect the interface mode, advertising mask or forced speed and
+ * decide whether to run at 2.5Gbit or 1Gbit appropriately, switching
+ * the interface mode to suit.  @state->interface is appropriately
+ * updated, and the advertising mask has the "other" baseX_Full flag
+ * cleared.
+ */
+void phylink_helper_basex_speed(struct phylink_link_state *state)
+{
+	if (phy_interface_mode_is_8023z(state->interface)) {
+		bool want_2500 = state->an_enabled ?
+			phylink_test(state->advertising, 2500baseX_Full) :
+			state->speed == SPEED_2500;
+
+		if (want_2500) {
+			phylink_clear(state->advertising, 1000baseX_Full);
+			state->interface = PHY_INTERFACE_MODE_2500BASEX;
+		} else {
+			phylink_clear(state->advertising, 2500baseX_Full);
+			state->interface = PHY_INTERFACE_MODE_1000BASEX;
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(phylink_helper_basex_speed);
+
 MODULE_LICENSE("GPL");
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 50eeae025f1e..021fc6595856 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -234,5 +234,6 @@ int phylink_mii_ioctl(struct phylink *, struct ifreq *, int);
 #define phylink_test(bm, mode)	__phylink_do_bit(test_bit, bm, mode)
 
 void phylink_set_port_modes(unsigned long *bits);
+void phylink_helper_basex_speed(struct phylink_link_state *state);
 
 #endif
-- 
cgit v1.2.3


From 6c422e34b1b6533af5730280835365d4b50786d3 Mon Sep 17 00:00:00 2001
From: Russell King <rmk+kernel@armlinux.org.uk>
Date: Thu, 9 Aug 2018 15:38:39 +0200
Subject: net: dsa: mv88e6xxx: add phylink support

Add rudimentary phylink support to mv88e6xxx.

TODO:
- needs to call phylink_mac_change() when the port link comes up/goes down.

Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 139 ++++++++++++++++++++++++++++++++++++++-
 drivers/net/dsa/mv88e6xxx/chip.h |   8 +++
 drivers/net/dsa/mv88e6xxx/port.c |  56 +++++++++++++++-
 drivers/net/dsa/mv88e6xxx/port.h |  18 ++++-
 4 files changed, 217 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index f7522d001365..1427541df316 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -598,10 +598,92 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port,
 		dev_err(ds->dev, "p%d: failed to configure MAC\n", port);
 }
 
+static void mv88e6065_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	if (!phy_interface_mode_is_8023z(state->interface)) {
+		/* 10M and 100M are only supported in non-802.3z mode */
+		phylink_set(mask, 10baseT_Half);
+		phylink_set(mask, 10baseT_Full);
+		phylink_set(mask, 100baseT_Half);
+		phylink_set(mask, 100baseT_Full);
+	}
+}
+
+static void mv88e6185_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	/* FIXME: if the port is in 1000Base-X mode, then it only supports
+	 * 1000M FD speeds.  In this case, CMODE will indicate 5.
+	 */
+	phylink_set(mask, 1000baseT_Full);
+	phylink_set(mask, 1000baseX_Full);
+
+	mv88e6065_phylink_validate(chip, port, mask, state);
+}
+
+static void mv88e6352_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	/* No ethtool bits for 200Mbps */
+	phylink_set(mask, 1000baseT_Full);
+	phylink_set(mask, 1000baseX_Full);
+
+	mv88e6065_phylink_validate(chip, port, mask, state);
+}
+
+static void mv88e6390_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+				       unsigned long *mask,
+				       struct phylink_link_state *state)
+{
+	if (port >= 9)
+		phylink_set(mask, 2500baseX_Full);
+
+	/* No ethtool bits for 200Mbps */
+	phylink_set(mask, 1000baseT_Full);
+	phylink_set(mask, 1000baseX_Full);
+
+	mv88e6065_phylink_validate(chip, port, mask, state);
+}
+
+static void mv88e6390x_phylink_validate(struct mv88e6xxx_chip *chip, int port,
+					unsigned long *mask,
+					struct phylink_link_state *state)
+{
+	if (port >= 9) {
+		phylink_set(mask, 10000baseT_Full);
+		phylink_set(mask, 10000baseKR_Full);
+	}
+
+	mv88e6390_phylink_validate(chip, port, mask, state);
+}
+
 static void mv88e6xxx_validate(struct dsa_switch *ds, int port,
 			       unsigned long *supported,
 			       struct phylink_link_state *state)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+	struct mv88e6xxx_chip *chip = ds->priv;
+
+	/* Allow all the expected bits */
+	phylink_set(mask, Autoneg);
+	phylink_set(mask, Pause);
+	phylink_set_port_modes(mask);
+
+	if (chip->info->ops->phylink_validate)
+		chip->info->ops->phylink_validate(chip, port, mask, state);
+
+	bitmap_and(supported, supported, mask, __ETHTOOL_LINK_MODE_MASK_NBITS);
+	bitmap_and(state->advertising, state->advertising, mask,
+		   __ETHTOOL_LINK_MODE_MASK_NBITS);
+
+	/* We can only operate at 2500BaseX or 1000BaseX.  If requested
+	 * to advertise both, only report advertising at 2500BaseX.
+	 */
+	phylink_helper_basex_speed(state);
 }
 
 static int mv88e6xxx_link_state(struct dsa_switch *ds, int port,
@@ -611,7 +693,10 @@ static int mv88e6xxx_link_state(struct dsa_switch *ds, int port,
 	int err;
 
 	mutex_lock(&chip->reg_lock);
-	err = mv88e6xxx_port_link_state(chip, port, state);
+	if (chip->info->ops->port_link_state)
+		err = chip->info->ops->port_link_state(chip, port, state);
+	else
+		err = -EOPNOTSUPP;
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -2611,6 +2696,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2627,6 +2713,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.rmu_disable = mv88e6085_g1_rmu_disable,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6095_ops = {
@@ -2642,6 +2729,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.port_set_frame_mode = mv88e6085_port_set_frame_mode,
 	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
+	.port_link_state = mv88e6185_port_link_state,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2653,6 +2741,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.reset = mv88e6185_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6097_ops = {
@@ -2675,6 +2764,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2689,6 +2779,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.rmu_disable = mv88e6085_g1_rmu_disable,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6123_ops = {
@@ -2706,6 +2797,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.port_set_egress_floods = mv88e6352_port_set_egress_floods,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2719,6 +2811,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6131_ops = {
@@ -2740,6 +2833,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting,
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_set_pause = mv88e6185_port_set_pause,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2755,6 +2849,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.reset = mv88e6185_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6141_ops = {
@@ -2780,6 +2875,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -2795,6 +2891,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.serdes_power = mv88e6341_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6161_ops = {
@@ -2817,6 +2914,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2832,6 +2930,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6165_avb_ops,
 	.ptp_ops = &mv88e6165_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6165_ops = {
@@ -2847,6 +2946,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.port_set_speed = mv88e6185_port_set_speed,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2862,6 +2962,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6165_avb_ops,
 	.ptp_ops = &mv88e6165_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6171_ops = {
@@ -2885,6 +2986,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2898,6 +3000,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6172_ops = {
@@ -2923,6 +3026,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2939,6 +3043,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6175_ops = {
@@ -2962,6 +3067,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2975,6 +3081,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6176_ops = {
@@ -3000,6 +3107,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3016,6 +3124,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.serdes_power = mv88e6352_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6185_ops = {
@@ -3033,6 +3142,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.port_egress_rate_limiting = mv88e6095_port_egress_rate_limiting,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.port_set_pause = mv88e6185_port_set_pause,
+	.port_link_state = mv88e6185_port_link_state,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3048,6 +3158,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.reset = mv88e6185_g1_reset,
 	.vtu_getnext = mv88e6185_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6190_ops = {
@@ -3069,6 +3180,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.port_pause_limit = mv88e6390_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3085,6 +3197,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6190x_ops = {
@@ -3106,6 +3219,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.port_pause_limit = mv88e6390_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3122,6 +3236,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
+	.phylink_validate = mv88e6390x_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6191_ops = {
@@ -3143,6 +3258,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.port_pause_limit = mv88e6390_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3160,6 +3276,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.serdes_power = mv88e6390_serdes_power,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6240_ops = {
@@ -3185,6 +3302,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3203,6 +3321,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6290_ops = {
@@ -3225,6 +3344,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3243,6 +3363,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
@@ -3267,6 +3388,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3282,6 +3404,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6321_ops = {
@@ -3306,6 +3429,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3319,6 +3443,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6341_ops = {
@@ -3344,6 +3469,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3361,6 +3487,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6350_ops = {
@@ -3384,6 +3511,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3397,6 +3525,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6351_ops = {
@@ -3420,6 +3549,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3435,6 +3565,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6185_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6352_ops = {
@@ -3460,6 +3591,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3481,6 +3613,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.serdes_get_sset_count = mv88e6352_serdes_get_sset_count,
 	.serdes_get_strings = mv88e6352_serdes_get_strings,
 	.serdes_get_stats = mv88e6352_serdes_get_stats,
+	.phylink_validate = mv88e6352_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6390_ops = {
@@ -3505,6 +3638,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3523,6 +3657,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390_phylink_validate,
 };
 
 static const struct mv88e6xxx_ops mv88e6390x_ops = {
@@ -3547,6 +3682,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_set_cmode = mv88e6390x_port_set_cmode,
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
+	.port_link_state = mv88e6352_port_link_state,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3565,6 +3701,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
+	.phylink_validate = mv88e6390x_phylink_validate,
 };
 
 static const struct mv88e6xxx_info mv88e6xxx_table[] = {
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 92ebfd271168..cdc028fcdf96 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -396,6 +396,9 @@ struct mv88e6xxx_ops {
 	 */
 	int (*port_set_upstream_port)(struct mv88e6xxx_chip *chip, int port,
 				      int upstream_port);
+	/* Return the port link state, as required by phylink */
+	int (*port_link_state)(struct mv88e6xxx_chip *chip, int port,
+			       struct phylink_link_state *state);
 
 	/* Snapshot the statistics for a port. The statistics can then
 	 * be read back a leisure but still with a consistent view.
@@ -451,6 +454,11 @@ struct mv88e6xxx_ops {
 
 	/* Precision Time Protocol operations */
 	const struct mv88e6xxx_ptp_ops *ptp_ops;
+
+	/* Phylink */
+	void (*phylink_validate)(struct mv88e6xxx_chip *chip, int port,
+				 unsigned long *mask,
+				 struct phylink_link_state *state);
 };
 
 struct mv88e6xxx_irq_ops {
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index c0701deaca6a..2ff370cb2f3c 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -388,6 +388,19 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 	return 0;
 }
 
+/* mv88e6185 only has 3 bits for CMODE */
+static int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port)
+{
+	int err;
+	u16 reg;
+
+	err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
+	if (err)
+		return err;
+
+	return reg & MV88E6185_PORT_STS_CMODE_MASK;
+}
+
 int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
 {
 	int err;
@@ -402,7 +415,7 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
 	return 0;
 }
 
-int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
+int mv88e6352_port_link_state(struct mv88e6xxx_chip *chip, int port,
 			      struct phylink_link_state *state)
 {
 	int err;
@@ -423,7 +436,7 @@ int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
 		state->speed = SPEED_1000;
 		break;
 	case MV88E6XXX_PORT_STS_SPEED_10000:
-		if ((reg &MV88E6XXX_PORT_STS_CMODE_MASK) ==
+		if ((reg & MV88E6XXX_PORT_STS_CMODE_MASK) ==
 		    MV88E6XXX_PORT_STS_CMODE_2500BASEX)
 			state->speed = SPEED_2500;
 		else
@@ -440,6 +453,45 @@ int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
 	return 0;
 }
 
+int mv88e6185_port_link_state(struct mv88e6xxx_chip *chip, int port,
+			      struct phylink_link_state *state)
+{
+	if (state->interface == PHY_INTERFACE_MODE_1000BASEX) {
+		int cmode = mv88e6185_port_get_cmode(chip, port);
+
+		if (cmode < 0)
+			return cmode;
+
+		/* When a port is in "Cross-chip serdes" mode, it uses
+		 * 1000Base-X full duplex mode, but there is no automatic
+		 * link detection. Use the sync OK status for link (as it
+		 * would do for 1000Base-X mode.)
+		 */
+		if (cmode == MV88E6185_PORT_STS_CMODE_SERDES) {
+			u16 mac;
+			int err;
+
+			err = mv88e6xxx_port_read(chip, port,
+						  MV88E6XXX_PORT_MAC_CTL, &mac);
+			if (err)
+				return err;
+
+			state->link = !!(mac & MV88E6185_PORT_MAC_CTL_SYNC_OK);
+			state->an_enabled = 1;
+			state->an_complete =
+				!!(mac & MV88E6185_PORT_MAC_CTL_AN_DONE);
+			state->duplex =
+				state->link ? DUPLEX_FULL : DUPLEX_UNKNOWN;
+			state->speed =
+				state->link ? SPEED_1000 : SPEED_UNKNOWN;
+
+			return 0;
+		}
+	}
+
+	return mv88e6352_port_link_state(chip, port, state);
+}
+
 /* Offset 0x02: Jamming Control
  *
  * Do not limit the period of time that this port can be paused for by
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 44916251567b..9b8d2b229907 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -42,14 +42,28 @@
 #define MV88E6XXX_PORT_STS_CMODE_2500BASEX	0x000b
 #define MV88E6XXX_PORT_STS_CMODE_XAUI		0x000c
 #define MV88E6XXX_PORT_STS_CMODE_RXAUI		0x000d
+#define MV88E6185_PORT_STS_CDUPLEX		0x0008
+#define MV88E6185_PORT_STS_CMODE_MASK		0x0007
+#define MV88E6185_PORT_STS_CMODE_GMII_FD	0x0000
+#define MV88E6185_PORT_STS_CMODE_MII_100_FD_PS	0x0001
+#define MV88E6185_PORT_STS_CMODE_MII_100	0x0002
+#define MV88E6185_PORT_STS_CMODE_MII_10		0x0003
+#define MV88E6185_PORT_STS_CMODE_SERDES		0x0004
+#define MV88E6185_PORT_STS_CMODE_1000BASE_X	0x0005
+#define MV88E6185_PORT_STS_CMODE_PHY		0x0006
+#define MV88E6185_PORT_STS_CMODE_DISABLED	0x0007
 
 /* Offset 0x01: MAC (or PCS or Physical) Control Register */
 #define MV88E6XXX_PORT_MAC_CTL				0x01
 #define MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_RXCLK	0x8000
 #define MV88E6XXX_PORT_MAC_CTL_RGMII_DELAY_TXCLK	0x4000
+#define MV88E6185_PORT_MAC_CTL_SYNC_OK			0x4000
 #define MV88E6390_PORT_MAC_CTL_FORCE_SPEED		0x2000
 #define MV88E6390_PORT_MAC_CTL_ALTSPEED			0x1000
 #define MV88E6352_PORT_MAC_CTL_200BASE			0x1000
+#define MV88E6185_PORT_MAC_CTL_AN_EN			0x0400
+#define MV88E6185_PORT_MAC_CTL_AN_RESTART		0x0200
+#define MV88E6185_PORT_MAC_CTL_AN_DONE			0x0100
 #define MV88E6XXX_PORT_MAC_CTL_FC			0x0080
 #define MV88E6XXX_PORT_MAC_CTL_FORCE_FC			0x0040
 #define MV88E6XXX_PORT_MAC_CTL_LINK_UP			0x0020
@@ -298,7 +312,9 @@ int mv88e6390_port_pause_limit(struct mv88e6xxx_chip *chip, int port, u8 in,
 int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode);
 int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
-int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port,
+int mv88e6185_port_link_state(struct mv88e6xxx_chip *chip, int port,
+			      struct phylink_link_state *state);
+int mv88e6352_port_link_state(struct mv88e6xxx_chip *chip, int port,
 			      struct phylink_link_state *state);
 int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port);
 int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port,
-- 
cgit v1.2.3


From a8c01c0d941d2f220a5a31ded77a67d89ddec3b0 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:40 +0200
Subject: net: dsa: mv88e6xxx: Refactor SERDES lane code

The 6390 family has 8 SERDES lanes. What ports use these lanes depends
on how ports 9 and 10 are configured. If 9 and 10 does not make use of
a line, one of the lower ports can use it.

Add a function to return the lane a port is using, if any, and simplify
the code to power up/down the lane.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/serdes.c | 195 ++++++++++++++++++++++---------------
 1 file changed, 114 insertions(+), 81 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 880b2cf0a530..a218870971fe 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -174,8 +174,97 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 	return ARRAY_SIZE(mv88e6352_serdes_hw_stats);
 }
 
+/* Return the SERDES lane address a port is using. Ports 9 and 10 can
+ * use multiple lanes. If so, return the first lane the port uses.
+ * Returns -ENODEV if a port does not have a lane.
+ */
+static int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+{
+	u8 cmode_port9, cmode_port10, cmode_port;
+	int err;
+
+	err = mv88e6xxx_port_get_cmode(chip, 9, &cmode_port9);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_port_get_cmode(chip, 10, &cmode_port10);
+	if (err)
+		return err;
+
+	err = mv88e6xxx_port_get_cmode(chip, port, &cmode_port);
+	if (err)
+		return err;
+
+	switch (port) {
+	case 2:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT9_LANE1;
+		return -ENODEV;
+	case 3:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT9_LANE2;
+		return -ENODEV;
+	case 4:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT9_LANE3;
+		return -ENODEV;
+	case 5:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT10_LANE1;
+		return -ENODEV;
+	case 6:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT10_LANE2;
+		return -ENODEV;
+	case 7:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			if (cmode_port == MV88E6XXX_PORT_STS_CMODE_1000BASE_X)
+				return MV88E6390_PORT10_LANE3;
+		return -ENODEV;
+	case 9:
+		if (cmode_port9 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_XAUI ||
+		    cmode_port9 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			return MV88E6390_PORT9_LANE0;
+		return -ENODEV;
+	case 10:
+		if (cmode_port10 == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_2500BASEX ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_XAUI ||
+		    cmode_port10 == MV88E6XXX_PORT_STS_CMODE_RXAUI)
+			return MV88E6390_PORT10_LANE0;
+		return -ENODEV;
+	default:
+		return -ENODEV;
+	}
+}
+
 /* Set the power on/off for 10GBASE-R and 10GBASE-X4/X2 */
-static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int addr, bool on)
+static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int lane, bool on)
 {
 	u16 val, new_val;
 	int reg_c45;
@@ -183,7 +272,7 @@ static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int addr, bool on)
 
 	reg_c45 = MII_ADDR_C45 | MV88E6390_SERDES_DEVICE |
 		MV88E6390_PCS_CONTROL_1;
-	err = mv88e6xxx_phy_read(chip, addr, reg_c45, &val);
+	err = mv88e6xxx_phy_read(chip, lane, reg_c45, &val);
 	if (err)
 		return err;
 
@@ -195,13 +284,13 @@ static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int addr, bool on)
 		new_val = val | MV88E6390_PCS_CONTROL_1_PDOWN;
 
 	if (val != new_val)
-		err = mv88e6xxx_phy_write(chip, addr, reg_c45, new_val);
+		err = mv88e6xxx_phy_write(chip, lane, reg_c45, new_val);
 
 	return err;
 }
 
-/* Set the power on/off for 10GBASE-R and 10GBASE-X4/X2 */
-static int mv88e6390_serdes_sgmii(struct mv88e6xxx_chip *chip, int addr,
+/* Set the power on/off for SGMII and 1000Base-X */
+static int mv88e6390_serdes_sgmii(struct mv88e6xxx_chip *chip, int lane,
 				  bool on)
 {
 	u16 val, new_val;
@@ -210,7 +299,7 @@ static int mv88e6390_serdes_sgmii(struct mv88e6xxx_chip *chip, int addr,
 
 	reg_c45 = MII_ADDR_C45 | MV88E6390_SERDES_DEVICE |
 		MV88E6390_SGMII_CONTROL;
-	err = mv88e6xxx_phy_read(chip, addr, reg_c45, &val);
+	err = mv88e6xxx_phy_read(chip, lane, reg_c45, &val);
 	if (err)
 		return err;
 
@@ -222,63 +311,29 @@ static int mv88e6390_serdes_sgmii(struct mv88e6xxx_chip *chip, int addr,
 		new_val = val | MV88E6390_SGMII_CONTROL_PDOWN;
 
 	if (val != new_val)
-		err = mv88e6xxx_phy_write(chip, addr, reg_c45, new_val);
+		err = mv88e6xxx_phy_write(chip, lane, reg_c45, new_val);
 
 	return err;
 }
 
-static int mv88e6390_serdes_lower(struct mv88e6xxx_chip *chip, u8 cmode,
-				  int port_donor, int lane, bool rxaui, bool on)
+static int mv88e6390_serdes_power_lane(struct mv88e6xxx_chip *chip, int port,
+				       int lane, bool on)
 {
+	u8 cmode;
 	int err;
-	u8 cmode_donor;
 
-	err = mv88e6xxx_port_get_cmode(chip, port_donor, &cmode_donor);
+	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
 	if (err)
 		return err;
 
-	switch (cmode_donor) {
-	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
-		if (!rxaui)
-			break;
-		/* Fall through */
-	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
-		    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII)
-			return	mv88e6390_serdes_sgmii(chip, lane, on);
-	}
-	return 0;
-}
-
-static int mv88e6390_serdes_port9(struct mv88e6xxx_chip *chip, u8 cmode,
-				  bool on)
-{
 	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-		return mv88e6390_serdes_sgmii(chip, MV88E6390_PORT9_LANE0, on);
+	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+		return mv88e6390_serdes_sgmii(chip, lane, on);
 	case MV88E6XXX_PORT_STS_CMODE_XAUI:
 	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
 	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_10g(chip, MV88E6390_PORT9_LANE0, on);
-	}
-
-	return 0;
-}
-
-static int mv88e6390_serdes_port10(struct mv88e6xxx_chip *chip, u8 cmode,
-				   bool on)
-{
-	switch (cmode) {
-	case MV88E6XXX_PORT_STS_CMODE_SGMII:
-		return mv88e6390_serdes_sgmii(chip, MV88E6390_PORT10_LANE0, on);
-	case MV88E6XXX_PORT_STS_CMODE_XAUI:
-	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
-	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_10g(chip, MV88E6390_PORT10_LANE0, on);
+		return mv88e6390_serdes_10g(chip, lane, on);
 	}
 
 	return 0;
@@ -286,42 +341,20 @@ static int mv88e6390_serdes_port10(struct mv88e6xxx_chip *chip, u8 cmode,
 
 int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 {
-	u8 cmode;
-	int err;
+	int lane;
 
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err)
-		return err;
+	lane = mv88e6390_serdes_get_lane(chip, port);
+	if (lane == -ENODEV)
+		return 0;
+
+	if (lane < 0)
+		return lane;
 
 	switch (port) {
-	case 2:
-		return mv88e6390_serdes_lower(chip, cmode, 9,
-					      MV88E6390_PORT9_LANE1,
-					      false, on);
-	case 3:
-		return mv88e6390_serdes_lower(chip, cmode, 9,
-					      MV88E6390_PORT9_LANE2,
-					      true, on);
-	case 4:
-		return mv88e6390_serdes_lower(chip, cmode, 9,
-					      MV88E6390_PORT9_LANE3,
-					      true, on);
-	case 5:
-		return mv88e6390_serdes_lower(chip, cmode, 10,
-					      MV88E6390_PORT10_LANE1,
-					      false, on);
-	case 6:
-		return mv88e6390_serdes_lower(chip, cmode, 10,
-					      MV88E6390_PORT10_LANE2,
-					      true, on);
-	case 7:
-		return mv88e6390_serdes_lower(chip, cmode, 10,
-					      MV88E6390_PORT10_LANE3,
-					      true, on);
-	case 9:
-		return mv88e6390_serdes_port9(chip, cmode, on);
-	case 10:
-		return mv88e6390_serdes_port10(chip, cmode, on);
+	case 2 ... 4:
+	case 5 ... 7:
+	case 9 ... 10:
+		return mv88e6390_serdes_power_lane(chip, port, lane, on);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 07ffbd74d1786d13a4f3a6bc01400ea59e8b19c0 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:41 +0200
Subject: net: dsa: mv88e6xxx: 6390 vs 6390X SERDES support

The 6390 has two SERDES interfaces, used by ports 9 and 10.  The 6390X
has eight SERDES interfaces. These allow ports 9 and 10 to do 10G. Or
if lower speeds are used, some of the SERDES interfaces can be used by
ports 2-8 for 1000Base-X.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c   |  4 +--
 drivers/net/dsa/mv88e6xxx/serdes.c | 51 +++++++++++++++++++++++++++++++++++++-
 drivers/net/dsa/mv88e6xxx/serdes.h |  1 +
 3 files changed, 53 insertions(+), 3 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 1427541df316..4c9ae5b9440b 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3234,7 +3234,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.rmu_disable = mv88e6390_g1_rmu_disable,
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
+	.serdes_power = mv88e6390x_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_validate = mv88e6390x_phylink_validate,
 };
@@ -3697,7 +3697,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.rmu_disable = mv88e6390_g1_rmu_disable,
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
-	.serdes_power = mv88e6390_serdes_power,
+	.serdes_power = mv88e6390x_serdes_power,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index a218870971fe..c534749fb1b6 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -174,11 +174,41 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 	return ARRAY_SIZE(mv88e6352_serdes_hw_stats);
 }
 
+/* Return the SERDES lane address a port is using. Only Ports 9 and 10
+ * have SERDES lanes. Returns -ENODEV if a port does not have a lane.
+ */
+static int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+{
+	u8 cmode;
+	int err;
+
+	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
+	if (err)
+		return err;
+
+	switch (port) {
+	case 9:
+		if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			return MV88E6390_PORT9_LANE0;
+		return -ENODEV;
+	case 10:
+		if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
+		    cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
+			return MV88E6390_PORT10_LANE0;
+		return -ENODEV;
+	default:
+		return -ENODEV;
+	}
+}
+
 /* Return the SERDES lane address a port is using. Ports 9 and 10 can
  * use multiple lanes. If so, return the first lane the port uses.
  * Returns -ENODEV if a port does not have a lane.
  */
-static int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+static int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 {
 	u8 cmode_port9, cmode_port10, cmode_port;
 	int err;
@@ -350,6 +380,25 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 	if (lane < 0)
 		return lane;
 
+	switch (port) {
+	case 9 ... 10:
+		return mv88e6390_serdes_power_lane(chip, port, lane, on);
+	}
+
+	return 0;
+}
+
+int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
+{
+	int lane;
+
+	lane = mv88e6390x_serdes_get_lane(chip, port);
+	if (lane == -ENODEV)
+		return 0;
+
+	if (lane < 0)
+		return lane;
+
 	switch (port) {
 	case 2 ... 4:
 	case 5 ... 7:
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index b6e5fbd46b5e..05c4825c36e4 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -47,6 +47,7 @@
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
+int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
-- 
cgit v1.2.3


From 23ef57d8230b0f3a92443fc4c88b1ec52994a70a Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:42 +0200
Subject: net: dsa: mv88e6xxx: Rename sgmii/10g power functions

There is a need to add more functions manipulating the SERDES
interfaces. Cleanup the namespace.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/serdes.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index c534749fb1b6..496d422170ef 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -294,7 +294,8 @@ static int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 }
 
 /* Set the power on/off for 10GBASE-R and 10GBASE-X4/X2 */
-static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int lane, bool on)
+static int mv88e6390_serdes_power_10g(struct mv88e6xxx_chip *chip, int lane,
+				      bool on)
 {
 	u16 val, new_val;
 	int reg_c45;
@@ -320,8 +321,8 @@ static int mv88e6390_serdes_10g(struct mv88e6xxx_chip *chip, int lane, bool on)
 }
 
 /* Set the power on/off for SGMII and 1000Base-X */
-static int mv88e6390_serdes_sgmii(struct mv88e6xxx_chip *chip, int lane,
-				  bool on)
+static int mv88e6390_serdes_power_sgmii(struct mv88e6xxx_chip *chip, int lane,
+					bool on)
 {
 	u16 val, new_val;
 	int reg_c45;
@@ -359,11 +360,11 @@ static int mv88e6390_serdes_power_lane(struct mv88e6xxx_chip *chip, int port,
 	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
 	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
-		return mv88e6390_serdes_sgmii(chip, lane, on);
+		return mv88e6390_serdes_power_sgmii(chip, lane, on);
 	case MV88E6XXX_PORT_STS_CMODE_XAUI:
 	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
 	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
-		return mv88e6390_serdes_10g(chip, lane, on);
+		return mv88e6390_serdes_power_10g(chip, lane, on);
 	}
 
 	return 0;
@@ -424,7 +425,8 @@ int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 	if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
 	    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
 	    cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
-		return mv88e6390_serdes_sgmii(chip, MV88E6341_ADDR_SERDES, on);
+		return mv88e6390_serdes_power_sgmii(chip, MV88E6341_ADDR_SERDES,
+						    on);
 
 	return 0;
 }
-- 
cgit v1.2.3


From e6891c76dd89418d08efbf72f65c93efc4a94556 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:43 +0200
Subject: net: dsa: mv88e6xxx: Add serdes register read/write helper

Add a helper for accessing SERDES registers of the 6390 family.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/serdes.c | 35 +++++++++++++++++++++++++----------
 drivers/net/dsa/mv88e6xxx/serdes.h |  1 -
 2 files changed, 25 insertions(+), 11 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 496d422170ef..36050e429924 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -35,6 +35,22 @@ static int mv88e6352_serdes_write(struct mv88e6xxx_chip *chip, int reg,
 					reg, val);
 }
 
+static int mv88e6390_serdes_read(struct mv88e6xxx_chip *chip,
+				 int lane, int device, int reg, u16 *val)
+{
+	int reg_c45 = MII_ADDR_C45 | device << 16 | reg;
+
+	return mv88e6xxx_phy_read(chip, lane, reg_c45, val);
+}
+
+static int mv88e6390_serdes_write(struct mv88e6xxx_chip *chip,
+				  int lane, int device, int reg, u16 val)
+{
+	int reg_c45 = MII_ADDR_C45 | device << 16 | reg;
+
+	return mv88e6xxx_phy_write(chip, lane, reg_c45, val);
+}
+
 static int mv88e6352_serdes_power_set(struct mv88e6xxx_chip *chip, bool on)
 {
 	u16 val, new_val;
@@ -298,12 +314,11 @@ static int mv88e6390_serdes_power_10g(struct mv88e6xxx_chip *chip, int lane,
 				      bool on)
 {
 	u16 val, new_val;
-	int reg_c45;
 	int err;
 
-	reg_c45 = MII_ADDR_C45 | MV88E6390_SERDES_DEVICE |
-		MV88E6390_PCS_CONTROL_1;
-	err = mv88e6xxx_phy_read(chip, lane, reg_c45, &val);
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_PCS_CONTROL_1, &val);
+
 	if (err)
 		return err;
 
@@ -315,7 +330,8 @@ static int mv88e6390_serdes_power_10g(struct mv88e6xxx_chip *chip, int lane,
 		new_val = val | MV88E6390_PCS_CONTROL_1_PDOWN;
 
 	if (val != new_val)
-		err = mv88e6xxx_phy_write(chip, lane, reg_c45, new_val);
+		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+					     MV88E6390_PCS_CONTROL_1, new_val);
 
 	return err;
 }
@@ -325,12 +341,10 @@ static int mv88e6390_serdes_power_sgmii(struct mv88e6xxx_chip *chip, int lane,
 					bool on)
 {
 	u16 val, new_val;
-	int reg_c45;
 	int err;
 
-	reg_c45 = MII_ADDR_C45 | MV88E6390_SERDES_DEVICE |
-		MV88E6390_SGMII_CONTROL;
-	err = mv88e6xxx_phy_read(chip, lane, reg_c45, &val);
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_SGMII_CONTROL, &val);
 	if (err)
 		return err;
 
@@ -342,7 +356,8 @@ static int mv88e6390_serdes_power_sgmii(struct mv88e6xxx_chip *chip, int lane,
 		new_val = val | MV88E6390_SGMII_CONTROL_PDOWN;
 
 	if (val != new_val)
-		err = mv88e6xxx_phy_write(chip, lane, reg_c45, new_val);
+		err = mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+					     MV88E6390_SGMII_CONTROL, new_val);
 
 	return err;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index 05c4825c36e4..a64ca1974988 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -29,7 +29,6 @@
 #define MV88E6390_PORT10_LANE1		0x15
 #define MV88E6390_PORT10_LANE2		0x16
 #define MV88E6390_PORT10_LANE3		0x17
-#define MV88E6390_SERDES_DEVICE		(4 << 16)
 
 /* 10GBASE-R and 10GBASE-X4/X2 */
 #define MV88E6390_PCS_CONTROL_1		0x1000
-- 
cgit v1.2.3


From f8236a0835597b166a9f0bab38b9b31bd932ce98 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:44 +0200
Subject: net: dsa: mv88e6xxx: 2500Base-X uses the 1000Base-X SERDES

The 6390 has three different SERDES interface types. 2500Base-X is
implemented by the SGMII/1000Base-X SERDES. So power on/off the
correct SERDES.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/serdes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 36050e429924..b57d4271acdb 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -375,10 +375,10 @@ static int mv88e6390_serdes_power_lane(struct mv88e6xxx_chip *chip, int port,
 	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
 	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
 		return mv88e6390_serdes_power_sgmii(chip, lane, on);
 	case MV88E6XXX_PORT_STS_CMODE_XAUI:
 	case MV88E6XXX_PORT_STS_CMODE_RXAUI:
-	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
 		return mv88e6390_serdes_power_10g(chip, lane, on);
 	}
 
-- 
cgit v1.2.3


From 2d2e1dd29962ce0e6bc2c35fe804d919bf3e7f68 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:45 +0200
Subject: net: dsa: mv88e6xxx: Cache the port cmode

The ports CMODE indicates the type of link between the MAC and the
PHY. It is used often in the SERDES code. Rather than read it each
time, cache its value.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c   | 38 ++++++++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/chip.h   |  2 ++
 drivers/net/dsa/mv88e6xxx/port.c   | 16 +++++++-------
 drivers/net/dsa/mv88e6xxx/port.h   |  3 ++-
 drivers/net/dsa/mv88e6xxx/serdes.c | 45 ++++++--------------------------------
 5 files changed, 57 insertions(+), 47 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 4c9ae5b9440b..66e0281604df 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2381,6 +2381,7 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
 static int mv88e6xxx_setup(struct dsa_switch *ds)
 {
 	struct mv88e6xxx_chip *chip = ds->priv;
+	u8 cmode;
 	int err;
 	int i;
 
@@ -2389,6 +2390,17 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 
 	mutex_lock(&chip->reg_lock);
 
+	/* Cache the cmode of each port. */
+	for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
+		if (chip->info->ops->port_get_cmode) {
+			err = chip->info->ops->port_get_cmode(chip, i, &cmode);
+			if (err)
+				return err;
+
+			chip->ports[i].cmode = cmode;
+		}
+	}
+
 	/* Setup Switch Port Registers */
 	for (i = 0; i < mv88e6xxx_num_ports(chip); i++) {
 		if (dsa_is_unused_port(ds, i))
@@ -2697,6 +2709,7 @@ static const struct mv88e6xxx_ops mv88e6085_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2730,6 +2743,7 @@ static const struct mv88e6xxx_ops mv88e6095_ops = {
 	.port_set_egress_floods = mv88e6185_port_set_egress_floods,
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.port_link_state = mv88e6185_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2765,6 +2779,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2798,6 +2813,7 @@ static const struct mv88e6xxx_ops mv88e6123_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2834,6 +2850,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = {
 	.port_pause_limit = mv88e6097_port_pause_limit,
 	.port_set_pause = mv88e6185_port_set_pause,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2876,6 +2893,7 @@ static const struct mv88e6xxx_ops mv88e6141_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -2915,6 +2933,7 @@ static const struct mv88e6xxx_ops mv88e6161_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2947,6 +2966,7 @@ static const struct mv88e6xxx_ops mv88e6165_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -2987,6 +3007,7 @@ static const struct mv88e6xxx_ops mv88e6171_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3027,6 +3048,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3068,6 +3090,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3108,6 +3131,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3143,6 +3167,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = {
 	.port_set_upstream_port = mv88e6095_port_set_upstream_port,
 	.port_set_pause = mv88e6185_port_set_pause,
 	.port_link_state = mv88e6185_port_link_state,
+	.port_get_cmode = mv88e6185_port_get_cmode,
 	.stats_snapshot = mv88e6xxx_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3181,6 +3206,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3220,6 +3246,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3259,6 +3286,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3303,6 +3331,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3345,6 +3374,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3389,6 +3419,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3430,6 +3461,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3470,6 +3502,7 @@ static const struct mv88e6xxx_ops mv88e6341_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3512,6 +3545,7 @@ static const struct mv88e6xxx_ops mv88e6350_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3550,6 +3584,7 @@ static const struct mv88e6xxx_ops mv88e6351_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3592,6 +3627,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6320_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6095_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6095_stats_get_sset_count,
@@ -3639,6 +3675,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
@@ -3683,6 +3720,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.port_disable_learn_limit = mv88e6xxx_port_disable_learn_limit,
 	.port_disable_pri_override = mv88e6xxx_port_disable_pri_override,
 	.port_link_state = mv88e6352_port_link_state,
+	.port_get_cmode = mv88e6352_port_get_cmode,
 	.stats_snapshot = mv88e6390_g1_stats_snapshot,
 	.stats_set_histogram = mv88e6390_g1_stats_set_histogram,
 	.stats_get_sset_count = mv88e6320_stats_get_sset_count,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index cdc028fcdf96..08c74c88dbde 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -197,6 +197,7 @@ struct mv88e6xxx_port {
 	u64 atu_full_violation;
 	u64 vtu_member_violation;
 	u64 vtu_miss_violation;
+	u8 cmode;
 };
 
 struct mv88e6xxx_chip {
@@ -390,6 +391,7 @@ struct mv88e6xxx_ops {
 	 */
 	int (*port_set_cmode)(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode);
+	int (*port_get_cmode)(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
 
 	/* Some devices have a per port register indicating what is
 	 * the upstream port this port should forward to.
diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 2ff370cb2f3c..d236f3420f2d 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -385,11 +385,12 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			return err;
 	}
 
+	chip->ports[port].cmode = cmode;
+
 	return 0;
 }
 
-/* mv88e6185 only has 3 bits for CMODE */
-static int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port)
+int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
 {
 	int err;
 	u16 reg;
@@ -398,10 +399,12 @@ static int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port)
 	if (err)
 		return err;
 
-	return reg & MV88E6185_PORT_STS_CMODE_MASK;
+	*cmode = reg & MV88E6185_PORT_STS_CMODE_MASK;
+
+	return 0;
 }
 
-int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
+int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode)
 {
 	int err;
 	u16 reg;
@@ -457,10 +460,7 @@ int mv88e6185_port_link_state(struct mv88e6xxx_chip *chip, int port,
 			      struct phylink_link_state *state)
 {
 	if (state->interface == PHY_INTERFACE_MODE_1000BASEX) {
-		int cmode = mv88e6185_port_get_cmode(chip, port);
-
-		if (cmode < 0)
-			return cmode;
+		u8 cmode = chip->ports[port].cmode;
 
 		/* When a port is in "Cross-chip serdes" mode, it uses
 		 * 1000Base-X full duplex mode, but there is no automatic
diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h
index 9b8d2b229907..f32f56af8e35 100644
--- a/drivers/net/dsa/mv88e6xxx/port.h
+++ b/drivers/net/dsa/mv88e6xxx/port.h
@@ -311,7 +311,8 @@ int mv88e6390_port_pause_limit(struct mv88e6xxx_chip *chip, int port, u8 in,
 			       u8 out);
 int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode);
-int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
+int mv88e6185_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
+int mv88e6352_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode);
 int mv88e6185_port_link_state(struct mv88e6xxx_chip *chip, int port,
 			      struct phylink_link_state *state);
 int mv88e6352_port_link_state(struct mv88e6xxx_chip *chip, int port,
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index b57d4271acdb..064d0bb8fe02 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -73,14 +73,7 @@ static int mv88e6352_serdes_power_set(struct mv88e6xxx_chip *chip, bool on)
 
 static bool mv88e6352_port_has_serdes(struct mv88e6xxx_chip *chip, int port)
 {
-	u8 cmode;
-	int err;
-
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err) {
-		dev_err(chip->dev, "failed to read cmode\n");
-		return false;
-	}
+	u8 cmode = chip->ports[port].cmode;
 
 	if ((cmode == MV88E6XXX_PORT_STS_CMODE_100BASE_X) ||
 	    (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X) ||
@@ -195,12 +188,7 @@ int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
  */
 static int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 {
-	u8 cmode;
-	int err;
-
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err)
-		return err;
+	u8 cmode = chip->ports[port].cmode;
 
 	switch (port) {
 	case 9:
@@ -227,19 +215,10 @@ static int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 static int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 {
 	u8 cmode_port9, cmode_port10, cmode_port;
-	int err;
 
-	err = mv88e6xxx_port_get_cmode(chip, 9, &cmode_port9);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_port_get_cmode(chip, 10, &cmode_port10);
-	if (err)
-		return err;
-
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode_port);
-	if (err)
-		return err;
+	cmode_port9 = chip->ports[9].cmode;
+	cmode_port10 = chip->ports[10].cmode;
+	cmode_port = chip->ports[port].cmode;
 
 	switch (port) {
 	case 2:
@@ -365,12 +344,7 @@ static int mv88e6390_serdes_power_sgmii(struct mv88e6xxx_chip *chip, int lane,
 static int mv88e6390_serdes_power_lane(struct mv88e6xxx_chip *chip, int port,
 				       int lane, bool on)
 {
-	u8 cmode;
-	int err;
-
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err)
-		return err;
+	u8 cmode = chip->ports[port].cmode;
 
 	switch (cmode) {
 	case MV88E6XXX_PORT_STS_CMODE_SGMII:
@@ -427,16 +401,11 @@ int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 {
-	int err;
-	u8 cmode;
+	u8 cmode = chip->ports[port].cmode;
 
 	if (port != 5)
 		return 0;
 
-	err = mv88e6xxx_port_get_cmode(chip, port, &cmode);
-	if (err)
-		return err;
-
 	if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X ||
 	    cmode == MV88E6XXX_PORT_STS_CMODE_SGMII ||
 	    cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX)
-- 
cgit v1.2.3


From 364e9d7776a389941cea6c40783f90c236b402ce Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:46 +0200
Subject: net: dsa: mv88e6xxx: Power on/off SERDES on cmode change

The 6390 family has a number of SERDES interfaces per port. When the
cmode changes, eg 1000Base-X to XAUI, the SERDES interface in use will
also change. Power down the old SERDES interface and power up the new
SERDES interface.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index d236f3420f2d..977b4cb82299 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -19,6 +19,7 @@
 
 #include "chip.h"
 #include "port.h"
+#include "serdes.h"
 
 int mv88e6xxx_port_read(struct mv88e6xxx_chip *chip, int port, int reg,
 			u16 *val)
@@ -372,6 +373,10 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		cmode = 0;
 	}
 
+	err = mv88e6390_serdes_power(chip, port, false);
+	if (err)
+		return err;
+
 	if (cmode) {
 		err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, &reg);
 		if (err)
@@ -383,6 +388,10 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		err = mv88e6xxx_port_write(chip, port, MV88E6XXX_PORT_STS, reg);
 		if (err)
 			return err;
+
+		err = mv88e6390_serdes_power(chip, port, true);
+		if (err)
+			return err;
 	}
 
 	chip->ports[port].cmode = cmode;
-- 
cgit v1.2.3


From 7b898469b91ea08e42dbed52acf8dfcb4f5914d0 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:47 +0200
Subject: net: dsa: mv88e6xxx: link mv88e6xxx_port to mv88e6xxx_chip

An up coming change will register interrupts for individual switch
ports, using the mv88e6xxx_port as the interrupt context information.
Add members to the mv88e6xxx_port structure so we can link it back to
the mv88e6xxx_chip member the port belongs to and the port number of
the port.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 3 +++
 drivers/net/dsa/mv88e6xxx/chip.h | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 66e0281604df..5845cbf7f096 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2173,6 +2173,9 @@ static int mv88e6xxx_setup_port(struct mv88e6xxx_chip *chip, int port)
 	int err;
 	u16 reg;
 
+	chip->ports[port].chip = chip;
+	chip->ports[port].port = port;
+
 	/* MAC Forcing register: don't force link, speed, duplex or flow control
 	 * state to any particular values on physical ports, but force the CPU
 	 * port and all DSA ports to their maximum bandwidth and full duplex.
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 08c74c88dbde..577398fe36df 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -191,6 +191,8 @@ struct mv88e6xxx_port_hwtstamp {
 };
 
 struct mv88e6xxx_port {
+	struct mv88e6xxx_chip *chip;
+	int port;
 	u64 serdes_stats[2];
 	u64 atu_member_violation;
 	u64 atu_miss_violation;
-- 
cgit v1.2.3


From efd1ba6af93ff63d40f92515a83405133145c028 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:48 +0200
Subject: net: dsa: mv88e6xxx: Add SERDES phydev_mac_change up for 6390

phylink wants to know when the MAC layers notices a change in the
link. For the 6390 family, this is a change in the SERDES state.

Add interrupt support for the SERDES interface used to implement
SGMII/1000Base-X/2500Base-X. This is currently limited to ports 9 and
10. Support for the 10G SERDES and other ports will be added later,
building on this basic framework.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c   |  22 +++++
 drivers/net/dsa/mv88e6xxx/chip.h   |   5 ++
 drivers/net/dsa/mv88e6xxx/serdes.c | 179 +++++++++++++++++++++++++++++++++++++
 drivers/net/dsa/mv88e6xxx/serdes.h |  16 ++++
 4 files changed, 222 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 5845cbf7f096..17752316ab10 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2337,7 +2337,12 @@ static int mv88e6xxx_port_enable(struct dsa_switch *ds, int port,
 	int err;
 
 	mutex_lock(&chip->reg_lock);
+
 	err = mv88e6xxx_serdes_power(chip, port, true);
+
+	if (!err && chip->info->ops->serdes_irq_setup)
+		err = chip->info->ops->serdes_irq_setup(chip, port);
+
 	mutex_unlock(&chip->reg_lock);
 
 	return err;
@@ -2349,8 +2354,13 @@ static void mv88e6xxx_port_disable(struct dsa_switch *ds, int port,
 	struct mv88e6xxx_chip *chip = ds->priv;
 
 	mutex_lock(&chip->reg_lock);
+
+	if (chip->info->ops->serdes_irq_free)
+		chip->info->ops->serdes_irq_free(chip, port);
+
 	if (mv88e6xxx_serdes_power(chip, port, false))
 		dev_err(chip->dev, "failed to power off SERDES\n");
+
 	mutex_unlock(&chip->reg_lock);
 }
 
@@ -3225,6 +3235,8 @@ static const struct mv88e6xxx_ops mv88e6190_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_validate = mv88e6390_phylink_validate,
 };
@@ -3265,6 +3277,8 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390x_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.phylink_validate = mv88e6390x_phylink_validate,
 };
@@ -3305,6 +3319,8 @@ static const struct mv88e6xxx_ops mv88e6191_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
 	.phylink_validate = mv88e6390_phylink_validate,
@@ -3393,6 +3409,8 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -3694,6 +3712,8 @@ static const struct mv88e6xxx_ops mv88e6390_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -3739,6 +3759,8 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = {
 	.vtu_getnext = mv88e6390_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6390_g1_vtu_loadpurge,
 	.serdes_power = mv88e6390x_serdes_power,
+	.serdes_irq_setup = mv88e6390_serdes_irq_setup,
+	.serdes_irq_free = mv88e6390_serdes_irq_free,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6390_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 577398fe36df..f9ecb7872d32 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -200,6 +200,7 @@ struct mv88e6xxx_port {
 	u64 vtu_member_violation;
 	u64 vtu_miss_violation;
 	u8 cmode;
+	int serdes_irq;
 };
 
 struct mv88e6xxx_chip {
@@ -434,6 +435,10 @@ struct mv88e6xxx_ops {
 	/* Power on/off a SERDES interface */
 	int (*serdes_power)(struct mv88e6xxx_chip *chip, int port, bool on);
 
+	/* SERDES interrupt handling */
+	int (*serdes_irq_setup)(struct mv88e6xxx_chip *chip, int port);
+	void (*serdes_irq_free)(struct mv88e6xxx_chip *chip, int port);
+
 	/* Statistics from the SERDES interface */
 	int (*serdes_get_sset_count)(struct mv88e6xxx_chip *chip, int port);
 	int (*serdes_get_strings)(struct mv88e6xxx_chip *chip,  int port,
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 064d0bb8fe02..519346b81b87 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -11,6 +11,8 @@
  * (at your option) any later version.
  */
 
+#include <linux/interrupt.h>
+#include <linux/irqdomain.h>
 #include <linux/mii.h>
 
 #include "chip.h"
@@ -399,6 +401,183 @@ int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 	return 0;
 }
 
+static void mv88e6390_serdes_irq_link_sgmii(struct mv88e6xxx_chip *chip,
+					    int port, int lane)
+{
+	struct dsa_switch *ds = chip->ds;
+	u16 status;
+	bool up;
+
+	mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+			      MV88E6390_SGMII_STATUS, &status);
+
+	/* Status must be read twice in order to give the current link
+	 * status. Otherwise the change in link status since the last
+	 * read of the register is returned.
+	 */
+	mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+			      MV88E6390_SGMII_STATUS, &status);
+	up = status & MV88E6390_SGMII_STATUS_LINK;
+
+	dsa_port_phylink_mac_change(ds, port, up);
+}
+
+static int mv88e6390_serdes_irq_enable_sgmii(struct mv88e6xxx_chip *chip,
+					     int lane)
+{
+	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				      MV88E6390_SGMII_INT_ENABLE,
+				      MV88E6390_SGMII_INT_LINK_DOWN |
+				      MV88E6390_SGMII_INT_LINK_UP);
+}
+
+static int mv88e6390_serdes_irq_disable_sgmii(struct mv88e6xxx_chip *chip,
+					      int lane)
+{
+	return mv88e6390_serdes_write(chip, lane, MDIO_MMD_PHYXS,
+				      MV88E6390_SGMII_INT_ENABLE, 0);
+}
+
+int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
+				int lane)
+{
+	u8 cmode = chip->ports[port].cmode;
+	int err = 0;
+
+	switch (cmode) {
+	case MV88E6XXX_PORT_STS_CMODE_SGMII:
+	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
+		err = mv88e6390_serdes_irq_enable_sgmii(chip, lane);
+	}
+
+	return err;
+}
+
+int mv88e6390_serdes_irq_disable(struct mv88e6xxx_chip *chip, int port,
+				 int lane)
+{
+	u8 cmode = chip->ports[port].cmode;
+	int err = 0;
+
+	switch (cmode) {
+	case MV88E6XXX_PORT_STS_CMODE_SGMII:
+	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
+		err = mv88e6390_serdes_irq_disable_sgmii(chip, lane);
+	}
+
+	return err;
+}
+
+static int mv88e6390_serdes_irq_status_sgmii(struct mv88e6xxx_chip *chip,
+					     int lane, u16 *status)
+{
+	int err;
+
+	err = mv88e6390_serdes_read(chip, lane, MDIO_MMD_PHYXS,
+				    MV88E6390_SGMII_INT_STATUS, status);
+
+	return err;
+}
+
+static irqreturn_t mv88e6390_serdes_thread_fn(int irq, void *dev_id)
+{
+	struct mv88e6xxx_port *port = dev_id;
+	struct mv88e6xxx_chip *chip = port->chip;
+	irqreturn_t ret = IRQ_NONE;
+	u8 cmode = port->cmode;
+	u16 status;
+	int lane;
+	int err;
+
+	lane = mv88e6390x_serdes_get_lane(chip, port->port);
+
+	mutex_lock(&chip->reg_lock);
+
+	switch (cmode) {
+	case MV88E6XXX_PORT_STS_CMODE_SGMII:
+	case MV88E6XXX_PORT_STS_CMODE_1000BASE_X:
+	case MV88E6XXX_PORT_STS_CMODE_2500BASEX:
+		err = mv88e6390_serdes_irq_status_sgmii(chip, lane, &status);
+		if (err)
+			goto out;
+		if (status && (MV88E6390_SGMII_INT_LINK_DOWN ||
+			       MV88E6390_SGMII_INT_LINK_UP)) {
+			ret = IRQ_HANDLED;
+			mv88e6390_serdes_irq_link_sgmii(chip, port->port, lane);
+		}
+	}
+out:
+	mutex_unlock(&chip->reg_lock);
+
+	return ret;
+}
+
+int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port)
+{
+	int lane;
+	int err;
+
+	/* Only support ports 9 and 10 at the moment */
+	if (port < 9)
+		return 0;
+
+	lane = mv88e6390x_serdes_get_lane(chip, port);
+
+	if (lane == -ENODEV)
+		return 0;
+
+	if (lane < 0)
+		return lane;
+
+	chip->ports[port].serdes_irq = irq_find_mapping(chip->g2_irq.domain,
+							port);
+	if (chip->ports[port].serdes_irq < 0) {
+		dev_err(chip->dev, "Unable to map SERDES irq: %d\n",
+			chip->ports[port].serdes_irq);
+		return chip->ports[port].serdes_irq;
+	}
+
+	/* Requesting the IRQ will trigger irq callbacks. So we cannot
+	 * hold the reg_lock.
+	 */
+	mutex_unlock(&chip->reg_lock);
+	err = request_threaded_irq(chip->ports[port].serdes_irq, NULL,
+				   mv88e6390_serdes_thread_fn,
+				   IRQF_ONESHOT, "mv88e6xxx-serdes",
+				   &chip->ports[port]);
+	mutex_lock(&chip->reg_lock);
+
+	if (err) {
+		dev_err(chip->dev, "Unable to request SERDES interrupt: %d\n",
+			err);
+		return err;
+	}
+
+	return mv88e6390_serdes_irq_enable(chip, port, lane);
+}
+
+void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
+{
+	int lane = mv88e6390x_serdes_get_lane(chip, port);
+
+	if (port < 9)
+		return;
+
+	if (lane < 0)
+		return;
+
+	mv88e6390_serdes_irq_disable(chip, port, lane);
+
+	/* Freeing the IRQ will trigger irq callbacks. So we cannot
+	 * hold the reg_lock.
+	 */
+	mutex_unlock(&chip->reg_lock);
+	free_irq(chip->ports[port].serdes_irq, &chip->ports[port]);
+	mutex_lock(&chip->reg_lock);
+}
+
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
 {
 	u8 cmode = chip->ports[port].cmode;
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index a64ca1974988..09da08cb5261 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -42,11 +42,27 @@
 #define MV88E6390_SGMII_CONTROL_RESET		BIT(15)
 #define MV88E6390_SGMII_CONTROL_LOOPBACK	BIT(14)
 #define MV88E6390_SGMII_CONTROL_PDOWN		BIT(11)
+#define MV88E6390_SGMII_STATUS		0x2001
+#define MV88E6390_SGMII_STATUS_AN_DONE		BIT(5)
+#define MV88E6390_SGMII_STATUS_REMOTE_FAULT	BIT(4)
+#define MV88E6390_SGMII_STATUS_LINK		BIT(2)
+#define MV88E6390_SGMII_INT_ENABLE	0xa001
+#define MV88E6390_SGMII_INT_SPEED_CHANGE	BIT(14)
+#define MV88E6390_SGMII_INT_DUPLEX_CHANGE	BIT(13)
+#define MV88E6390_SGMII_INT_PAGE_RX		BIT(12)
+#define MV88E6390_SGMII_INT_AN_COMPLETE		BIT(11)
+#define MV88E6390_SGMII_INT_LINK_DOWN		BIT(10)
+#define MV88E6390_SGMII_INT_LINK_UP		BIT(9)
+#define MV88E6390_SGMII_INT_SYMBOL_ERROR	BIT(8)
+#define MV88E6390_SGMII_INT_FALSE_CARRIER	BIT(7)
+#define MV88E6390_SGMII_INT_STATUS	0xa002
 
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6390x_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
+int mv88e6390_serdes_irq_setup(struct mv88e6xxx_chip *chip, int port);
+void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port);
 int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
-- 
cgit v1.2.3


From 734447d4ed7b1f31617c28959fd5adfbd9e39d13 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Thu, 9 Aug 2018 15:38:49 +0200
Subject: net: dsa: mv88e6xxx: Re-setup interrupts on CMODE change.

When a port changes CMODE, the SERDES interface being used can change.
Disable interrupts for the old SERDES interface, and enable interrupts
on the new.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/port.c   | 19 ++++++++++++++++++-
 drivers/net/dsa/mv88e6xxx/serdes.c |  4 +++-
 drivers/net/dsa/mv88e6xxx/serdes.h |  6 ++++++
 3 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c
index 977b4cb82299..92945841c8e8 100644
--- a/drivers/net/dsa/mv88e6xxx/port.c
+++ b/drivers/net/dsa/mv88e6xxx/port.c
@@ -342,8 +342,9 @@ int mv88e6390x_port_set_speed(struct mv88e6xxx_chip *chip, int port, int speed)
 int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 			      phy_interface_t mode)
 {
-	u16 reg;
+	int lane;
 	u16 cmode;
+	u16 reg;
 	int err;
 
 	if (mode == PHY_INTERFACE_MODE_NA)
@@ -373,6 +374,16 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		cmode = 0;
 	}
 
+	lane = mv88e6390x_serdes_get_lane(chip, port);
+	if (lane < 0)
+		return lane;
+
+	if (chip->ports[port].serdes_irq) {
+		err = mv88e6390_serdes_irq_disable(chip, port, lane);
+		if (err)
+			return err;
+	}
+
 	err = mv88e6390_serdes_power(chip, port, false);
 	if (err)
 		return err;
@@ -392,6 +403,12 @@ int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port,
 		err = mv88e6390_serdes_power(chip, port, true);
 		if (err)
 			return err;
+
+		if (chip->ports[port].serdes_irq) {
+			err = mv88e6390_serdes_irq_enable(chip, port, lane);
+			if (err)
+				return err;
+		}
 	}
 
 	chip->ports[port].cmode = cmode;
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index 519346b81b87..f007d109b385 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -214,7 +214,7 @@ static int mv88e6390_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
  * use multiple lanes. If so, return the first lane the port uses.
  * Returns -ENODEV if a port does not have a lane.
  */
-static int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
+int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port)
 {
 	u8 cmode_port9, cmode_port10, cmode_port;
 
@@ -576,6 +576,8 @@ void mv88e6390_serdes_irq_free(struct mv88e6xxx_chip *chip, int port)
 	mutex_unlock(&chip->reg_lock);
 	free_irq(chip->ports[port].serdes_irq, &chip->ports[port]);
 	mutex_lock(&chip->reg_lock);
+
+	chip->ports[port].serdes_irq = 0;
 }
 
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on)
diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h
index 09da08cb5261..b1496de9c6fe 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.h
+++ b/drivers/net/dsa/mv88e6xxx/serdes.h
@@ -57,6 +57,7 @@
 #define MV88E6390_SGMII_INT_FALSE_CARRIER	BIT(7)
 #define MV88E6390_SGMII_INT_STATUS	0xa002
 
+int mv88e6390x_serdes_get_lane(struct mv88e6xxx_chip *chip, int port);
 int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
 int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on);
@@ -68,4 +69,9 @@ int mv88e6352_serdes_get_strings(struct mv88e6xxx_chip *chip,
 				 int port, uint8_t *data);
 int mv88e6352_serdes_get_stats(struct mv88e6xxx_chip *chip, int port,
 			       uint64_t *data);
+int mv88e6390_serdes_irq_enable(struct mv88e6xxx_chip *chip, int port,
+				int lane);
+int mv88e6390_serdes_irq_disable(struct mv88e6xxx_chip *chip, int port,
+				 int lane);
+
 #endif
-- 
cgit v1.2.3


From 48ae5554a076c1bca31448d60263e4038def9f6f Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:29 +0100
Subject: net: stmmac: Add XGMAC 2.10 HWIF entry

Add a new entry to HWIF table for XGMAC 2.10. For now we fill it with
empty callbacks which will be added in posterior patches.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/common.h | 14 +++++++------
 drivers/net/ethernet/stmicro/stmmac/hwif.c   | 31 ++++++++++++++++++++++++++--
 include/linux/stmmac.h                       |  1 +
 3 files changed, 38 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 78fd0f8b8e81..3fb81acbd274 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -36,12 +36,14 @@
 #include "mmc.h"
 
 /* Synopsys Core versions */
-#define	DWMAC_CORE_3_40	0x34
-#define	DWMAC_CORE_3_50	0x35
-#define	DWMAC_CORE_4_00	0x40
-#define DWMAC_CORE_4_10	0x41
-#define DWMAC_CORE_5_00 0x50
-#define DWMAC_CORE_5_10 0x51
+#define	DWMAC_CORE_3_40		0x34
+#define	DWMAC_CORE_3_50		0x35
+#define	DWMAC_CORE_4_00		0x40
+#define DWMAC_CORE_4_10		0x41
+#define DWMAC_CORE_5_00		0x50
+#define DWMAC_CORE_5_10		0x51
+#define DWXGMAC_CORE_2_10	0x21
+
 #define STMMAC_CHAN0	0	/* Always supported and default for all chips */
 
 /* These need to be power of two, and >= 4 */
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 1f50e83cafb2..24f5ff175aa4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -72,6 +72,7 @@ static int stmmac_dwmac4_quirks(struct stmmac_priv *priv)
 static const struct stmmac_hwif_entry {
 	bool gmac;
 	bool gmac4;
+	bool xgmac;
 	u32 min_id;
 	const struct stmmac_regs_off regs;
 	const void *desc;
@@ -87,6 +88,7 @@ static const struct stmmac_hwif_entry {
 	{
 		.gmac = false,
 		.gmac4 = false,
+		.xgmac = false,
 		.min_id = 0,
 		.regs = {
 			.ptp_off = PTP_GMAC3_X_OFFSET,
@@ -103,6 +105,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = true,
 		.gmac4 = false,
+		.xgmac = false,
 		.min_id = 0,
 		.regs = {
 			.ptp_off = PTP_GMAC3_X_OFFSET,
@@ -119,6 +122,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = 0,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -135,6 +139,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = DWMAC_CORE_4_00,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -151,6 +156,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = DWMAC_CORE_4_10,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -167,6 +173,7 @@ static const struct stmmac_hwif_entry {
 	}, {
 		.gmac = false,
 		.gmac4 = true,
+		.xgmac = false,
 		.min_id = DWMAC_CORE_5_10,
 		.regs = {
 			.ptp_off = PTP_GMAC4_OFFSET,
@@ -180,11 +187,29 @@ static const struct stmmac_hwif_entry {
 		.tc = &dwmac510_tc_ops,
 		.setup = dwmac4_setup,
 		.quirks = NULL,
-	}
+	}, {
+		.gmac = false,
+		.gmac4 = false,
+		.xgmac = true,
+		.min_id = DWXGMAC_CORE_2_10,
+		.regs = {
+			.ptp_off = 0,
+			.mmc_off = 0,
+		},
+		.desc = NULL,
+		.dma = NULL,
+		.mac = NULL,
+		.hwtimestamp = NULL,
+		.mode = NULL,
+		.tc = NULL,
+		.setup = NULL,
+		.quirks = NULL,
+	},
 };
 
 int stmmac_hwif_init(struct stmmac_priv *priv)
 {
+	bool needs_xgmac = priv->plat->has_xgmac;
 	bool needs_gmac4 = priv->plat->has_gmac4;
 	bool needs_gmac = priv->plat->has_gmac;
 	const struct stmmac_hwif_entry *entry;
@@ -195,7 +220,7 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 
 	if (needs_gmac) {
 		id = stmmac_get_id(priv, GMAC_VERSION);
-	} else if (needs_gmac4) {
+	} else if (needs_gmac4 || needs_xgmac) {
 		id = stmmac_get_id(priv, GMAC4_VERSION);
 	} else {
 		id = 0;
@@ -229,6 +254,8 @@ int stmmac_hwif_init(struct stmmac_priv *priv)
 			continue;
 		if (needs_gmac4 ^ entry->gmac4)
 			continue;
+		if (needs_xgmac ^ entry->xgmac)
+			continue;
 		/* Use synopsys_id var because some setups can override this */
 		if (priv->synopsys_id < entry->min_id)
 			continue;
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 32feac5bbd75..c43e9a01b892 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -190,5 +190,6 @@ struct plat_stmmacenet_data {
 	bool tso_en;
 	int mac_port_sel_speed;
 	bool en_tx_lpi_clockgating;
+	int has_xgmac;
 };
 #endif
-- 
cgit v1.2.3


From 2142754f8b9c619e22e1c9d1973cacc4a214695c Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:30 +0100
Subject: net: stmmac: Add MAC related callbacks for XGMAC2

Add the MAC related callbacks for the new IP block XGMAC2.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/Makefile       |   2 +-
 drivers/net/ethernet/stmicro/stmmac/common.h       |   3 +
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h     | 141 ++++++++
 .../net/ethernet/stmicro/stmmac/dwxgmac2_core.c    | 371 +++++++++++++++++++++
 drivers/net/ethernet/stmicro/stmmac/hwif.c         |   4 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |   1 +
 6 files changed, 519 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
 create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c

diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index 68e9e2640c62..a6cf632c9592 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -5,7 +5,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o	\
 	      dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
-	      stmmac_tc.o $(stmmac-y)
+	      stmmac_tc.o dwxgmac2_core.o $(stmmac-y)
 
 # Ordering matters. Generic driver must be last.
 obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 3fb81acbd274..1854f270ad66 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -400,6 +400,8 @@ struct mac_link {
 	u32 speed10;
 	u32 speed100;
 	u32 speed1000;
+	u32 speed2500;
+	u32 speed10000;
 	u32 duplex;
 };
 
@@ -441,6 +443,7 @@ struct stmmac_rx_routing {
 int dwmac100_setup(struct stmmac_priv *priv);
 int dwmac1000_setup(struct stmmac_priv *priv);
 int dwmac4_setup(struct stmmac_priv *priv);
+int dwxgmac2_setup(struct stmmac_priv *priv);
 
 void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6],
 			 unsigned int high, unsigned int low);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
new file mode 100644
index 000000000000..7832571f791f
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -0,0 +1,141 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC definitions.
+ */
+
+#ifndef __STMMAC_DWXGMAC2_H__
+#define __STMMAC_DWXGMAC2_H__
+
+#include "common.h"
+
+/* Misc */
+#define XGMAC_JUMBO_LEN			16368
+
+/* MAC Registers */
+#define XGMAC_TX_CONFIG			0x00000000
+#define XGMAC_CONFIG_SS_OFF		29
+#define XGMAC_CONFIG_SS_MASK		GENMASK(30, 29)
+#define XGMAC_CONFIG_SS_10000		(0x0 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_2500		(0x2 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SS_1000		(0x3 << XGMAC_CONFIG_SS_OFF)
+#define XGMAC_CONFIG_SARC		GENMASK(22, 20)
+#define XGMAC_CONFIG_SARC_SHIFT		20
+#define XGMAC_CONFIG_JD			BIT(16)
+#define XGMAC_CONFIG_TE			BIT(0)
+#define XGMAC_CORE_INIT_TX		(XGMAC_CONFIG_JD)
+#define XGMAC_RX_CONFIG			0x00000004
+#define XGMAC_CONFIG_ARPEN		BIT(31)
+#define XGMAC_CONFIG_GPSL		GENMASK(29, 16)
+#define XGMAC_CONFIG_GPSL_SHIFT		16
+#define XGMAC_CONFIG_S2KP		BIT(11)
+#define XGMAC_CONFIG_IPC		BIT(9)
+#define XGMAC_CONFIG_JE			BIT(8)
+#define XGMAC_CONFIG_WD			BIT(7)
+#define XGMAC_CONFIG_GPSLCE		BIT(6)
+#define XGMAC_CONFIG_CST		BIT(2)
+#define XGMAC_CONFIG_ACS		BIT(1)
+#define XGMAC_CONFIG_RE			BIT(0)
+#define XGMAC_CORE_INIT_RX		0
+#define XGMAC_PACKET_FILTER		0x00000008
+#define XGMAC_FILTER_RA			BIT(31)
+#define XGMAC_FILTER_PM			BIT(4)
+#define XGMAC_FILTER_HMC		BIT(2)
+#define XGMAC_FILTER_PR			BIT(0)
+#define XGMAC_HASH_TABLE(x)		(0x00000010 + (x) * 4)
+#define XGMAC_RXQ_CTRL0			0x000000a0
+#define XGMAC_RXQEN(x)			GENMASK((x) * 2 + 1, (x) * 2)
+#define XGMAC_RXQEN_SHIFT(x)		((x) * 2)
+#define XGMAC_RXQ_CTRL2			0x000000a8
+#define XGMAC_RXQ_CTRL3			0x000000ac
+#define XGMAC_PSRQ(x)			GENMASK((x) * 8 + 7, (x) * 8)
+#define XGMAC_PSRQ_SHIFT(x)		((x) * 8)
+#define XGMAC_INT_STATUS		0x000000b0
+#define XGMAC_PMTIS			BIT(4)
+#define XGMAC_INT_EN			0x000000b4
+#define XGMAC_TSIE			BIT(12)
+#define XGMAC_LPIIE			BIT(5)
+#define XGMAC_PMTIE			BIT(4)
+#define XGMAC_INT_DEFAULT_EN		(XGMAC_LPIIE | XGMAC_PMTIE | XGMAC_TSIE)
+#define XGMAC_Qx_TX_FLOW_CTRL(x)	(0x00000070 + (x) * 4)
+#define XGMAC_PT			GENMASK(31, 16)
+#define XGMAC_PT_SHIFT			16
+#define XGMAC_TFE			BIT(1)
+#define XGMAC_RX_FLOW_CTRL		0x00000090
+#define XGMAC_RFE			BIT(0)
+#define XGMAC_PMT			0x000000c0
+#define XGMAC_GLBLUCAST			BIT(9)
+#define XGMAC_RWKPKTEN			BIT(2)
+#define XGMAC_MGKPKTEN			BIT(1)
+#define XGMAC_PWRDWN			BIT(0)
+#define XGMAC_HW_FEATURE0		0x0000011c
+#define XGMAC_HWFEAT_SAVLANINS		BIT(27)
+#define XGMAC_HWFEAT_RXCOESEL		BIT(16)
+#define XGMAC_HWFEAT_TXCOESEL		BIT(14)
+#define XGMAC_HWFEAT_TSSEL		BIT(12)
+#define XGMAC_HWFEAT_AVSEL		BIT(11)
+#define XGMAC_HWFEAT_RAVSEL		BIT(10)
+#define XGMAC_HWFEAT_ARPOFFSEL		BIT(9)
+#define XGMAC_HWFEAT_MGKSEL		BIT(7)
+#define XGMAC_HWFEAT_RWKSEL		BIT(6)
+#define XGMAC_HWFEAT_GMIISEL		BIT(1)
+#define XGMAC_HW_FEATURE1		0x00000120
+#define XGMAC_HWFEAT_TSOEN		BIT(18)
+#define XGMAC_HWFEAT_TXFIFOSIZE		GENMASK(10, 6)
+#define XGMAC_HWFEAT_RXFIFOSIZE		GENMASK(4, 0)
+#define XGMAC_HW_FEATURE2		0x00000124
+#define XGMAC_HWFEAT_PPSOUTNUM		GENMASK(26, 24)
+#define XGMAC_HWFEAT_TXCHCNT		GENMASK(21, 18)
+#define XGMAC_HWFEAT_RXCHCNT		GENMASK(15, 12)
+#define XGMAC_HWFEAT_TXQCNT		GENMASK(9, 6)
+#define XGMAC_HWFEAT_RXQCNT		GENMASK(3, 0)
+#define XGMAC_MDIO_ADDR			0x00000200
+#define XGMAC_MDIO_DATA			0x00000204
+#define XGMAC_MDIO_C22P			0x00000220
+#define XGMAC_ADDR0_HIGH		0x00000300
+#define XGMAC_AE			BIT(31)
+#define XGMAC_DCS			GENMASK(19, 16)
+#define XGMAC_DCS_SHIFT			16
+#define XGMAC_ADDR0_LOW			0x00000304
+#define XGMAC_ARP_ADDR			0x00000c10
+#define XGMAC_TIMESTAMP_STATUS		0x00000d20
+#define XGMAC_TXTSC			BIT(15)
+#define XGMAC_TXTIMESTAMP_NSEC		0x00000d30
+#define XGMAC_TXTSSTSLO			GENMASK(30, 0)
+#define XGMAC_TXTIMESTAMP_SEC		0x00000d34
+
+/* MTL Registers */
+#define XGMAC_MTL_OPMODE		0x00001000
+#define XGMAC_ETSALG			GENMASK(6, 5)
+#define XGMAC_WRR			(0x0 << 5)
+#define XGMAC_WFQ			(0x1 << 5)
+#define XGMAC_DWRR			(0x2 << 5)
+#define XGMAC_RAA			BIT(2)
+#define XGMAC_MTL_INT_STATUS		0x00001020
+#define XGMAC_MTL_RXQ_DMA_MAP0		0x00001030
+#define XGMAC_MTL_RXQ_DMA_MAP1		0x00001034
+#define XGMAC_QxMDMACH(x)		GENMASK((x) * 8 + 3, (x) * 8)
+#define XGMAC_QxMDMACH_SHIFT(x)		((x) * 8)
+#define XGMAC_MTL_TXQ_OPMODE(x)		(0x00001100 + (0x80 * (x)))
+#define XGMAC_TQS			GENMASK(25, 16)
+#define XGMAC_TQS_SHIFT			16
+#define XGMAC_TTC			GENMASK(6, 4)
+#define XGMAC_TTC_SHIFT			4
+#define XGMAC_TXQEN			GENMASK(3, 2)
+#define XGMAC_TXQEN_SHIFT		2
+#define XGMAC_TSF			BIT(1)
+#define XGMAC_MTL_RXQ_OPMODE(x)		(0x00001140 + (0x80 * (x)))
+#define XGMAC_RQS			GENMASK(25, 16)
+#define XGMAC_RQS_SHIFT			16
+#define XGMAC_EHFC			BIT(7)
+#define XGMAC_RSF			BIT(5)
+#define XGMAC_RTC			GENMASK(1, 0)
+#define XGMAC_RTC_SHIFT			0
+#define XGMAC_MTL_QINTEN(x)		(0x00001170 + (0x80 * (x)))
+#define XGMAC_RXOIE			BIT(16)
+#define XGMAC_MTL_QINT_STATUS(x)	(0x00001174 + (0x80 * (x)))
+#define XGMAC_RXOVFIS			BIT(16)
+#define XGMAC_ABPSIS			BIT(1)
+#define XGMAC_TXUNFIS			BIT(0)
+
+#endif /* __STMMAC_DWXGMAC2_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
new file mode 100644
index 000000000000..d182f82f7b58
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -0,0 +1,371 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC support.
+ */
+
+#include "stmmac.h"
+#include "dwxgmac2.h"
+
+static void dwxgmac2_core_init(struct mac_device_info *hw,
+			       struct net_device *dev)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	int mtu = dev->mtu;
+	u32 tx, rx;
+
+	tx = readl(ioaddr + XGMAC_TX_CONFIG);
+	rx = readl(ioaddr + XGMAC_RX_CONFIG);
+
+	tx |= XGMAC_CORE_INIT_TX;
+	rx |= XGMAC_CORE_INIT_RX;
+
+	if (mtu >= 9000) {
+		rx |= XGMAC_CONFIG_GPSLCE;
+		rx |= XGMAC_JUMBO_LEN << XGMAC_CONFIG_GPSL_SHIFT;
+		rx |= XGMAC_CONFIG_WD;
+	} else if (mtu > 2000) {
+		rx |= XGMAC_CONFIG_JE;
+	} else if (mtu > 1500) {
+		rx |= XGMAC_CONFIG_S2KP;
+	}
+
+	if (hw->ps) {
+		tx |= XGMAC_CONFIG_TE;
+		tx &= ~hw->link.speed_mask;
+
+		switch (hw->ps) {
+		case SPEED_10000:
+			tx |= hw->link.speed10000;
+			break;
+		case SPEED_2500:
+			tx |= hw->link.speed2500;
+			break;
+		case SPEED_1000:
+		default:
+			tx |= hw->link.speed1000;
+			break;
+		}
+	}
+
+	writel(tx, ioaddr + XGMAC_TX_CONFIG);
+	writel(rx, ioaddr + XGMAC_RX_CONFIG);
+	writel(XGMAC_INT_DEFAULT_EN, ioaddr + XGMAC_INT_EN);
+}
+
+static void dwxgmac2_set_mac(void __iomem *ioaddr, bool enable)
+{
+	u32 tx = readl(ioaddr + XGMAC_TX_CONFIG);
+	u32 rx = readl(ioaddr + XGMAC_RX_CONFIG);
+
+	if (enable) {
+		tx |= XGMAC_CONFIG_TE;
+		rx |= XGMAC_CONFIG_RE;
+	} else {
+		tx &= ~XGMAC_CONFIG_TE;
+		rx &= ~XGMAC_CONFIG_RE;
+	}
+
+	writel(tx, ioaddr + XGMAC_TX_CONFIG);
+	writel(rx, ioaddr + XGMAC_RX_CONFIG);
+}
+
+static int dwxgmac2_rx_ipc(struct mac_device_info *hw)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_RX_CONFIG);
+	if (hw->rx_csum)
+		value |= XGMAC_CONFIG_IPC;
+	else
+		value &= ~XGMAC_CONFIG_IPC;
+	writel(value, ioaddr + XGMAC_RX_CONFIG);
+
+	return !!(readl(ioaddr + XGMAC_RX_CONFIG) & XGMAC_CONFIG_IPC);
+}
+
+static void dwxgmac2_rx_queue_enable(struct mac_device_info *hw, u8 mode,
+				     u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_RXQ_CTRL0) & ~XGMAC_RXQEN(queue);
+	if (mode == MTL_QUEUE_AVB)
+		value |= 0x1 << XGMAC_RXQEN_SHIFT(queue);
+	else if (mode == MTL_QUEUE_DCB)
+		value |= 0x2 << XGMAC_RXQEN_SHIFT(queue);
+	writel(value, ioaddr + XGMAC_RXQ_CTRL0);
+}
+
+static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio,
+				   u32 queue)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value, reg;
+
+	reg = (queue < 4) ? XGMAC_RXQ_CTRL2 : XGMAC_RXQ_CTRL3;
+
+	value = readl(ioaddr + reg);
+	value &= ~XGMAC_PSRQ(queue);
+	value |= (prio << XGMAC_PSRQ_SHIFT(queue)) & XGMAC_PSRQ(queue);
+
+	writel(value, ioaddr + reg);
+}
+
+static void dwxgmac2_prog_mtl_rx_algorithms(struct mac_device_info *hw,
+					    u32 rx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_MTL_OPMODE);
+	value &= ~XGMAC_RAA;
+
+	switch (rx_alg) {
+	case MTL_RX_ALGORITHM_SP:
+		break;
+	case MTL_RX_ALGORITHM_WSP:
+		value |= XGMAC_RAA;
+		break;
+	default:
+		break;
+	}
+
+	writel(value, ioaddr + XGMAC_MTL_OPMODE);
+}
+
+static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw,
+					    u32 tx_alg)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_MTL_OPMODE);
+	value &= ~XGMAC_ETSALG;
+
+	switch (tx_alg) {
+	case MTL_TX_ALGORITHM_WRR:
+		value |= XGMAC_WRR;
+		break;
+	case MTL_TX_ALGORITHM_WFQ:
+		value |= XGMAC_WFQ;
+		break;
+	case MTL_TX_ALGORITHM_DWRR:
+		value |= XGMAC_DWRR;
+		break;
+	default:
+		break;
+	}
+
+	writel(value, ioaddr + XGMAC_MTL_OPMODE);
+}
+
+static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue,
+				    u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value, reg;
+
+	reg = (queue < 4) ? XGMAC_MTL_RXQ_DMA_MAP0 : XGMAC_MTL_RXQ_DMA_MAP1;
+
+	value = readl(ioaddr + reg);
+	value &= ~XGMAC_QxMDMACH(queue);
+	value |= (chan << XGMAC_QxMDMACH_SHIFT(queue)) & XGMAC_QxMDMACH(queue);
+
+	writel(value, ioaddr + reg);
+}
+
+static int dwxgmac2_host_irq_status(struct mac_device_info *hw,
+				    struct stmmac_extra_stats *x)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 stat, en;
+
+	en = readl(ioaddr + XGMAC_INT_EN);
+	stat = readl(ioaddr + XGMAC_INT_STATUS);
+
+	stat &= en;
+
+	if (stat & XGMAC_PMTIS) {
+		x->irq_receive_pmt_irq_n++;
+		readl(ioaddr + XGMAC_PMT);
+	}
+
+	return 0;
+}
+
+static int dwxgmac2_host_mtl_irq_status(struct mac_device_info *hw, u32 chan)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	int ret = 0;
+	u32 status;
+
+	status = readl(ioaddr + XGMAC_MTL_INT_STATUS);
+	if (status & BIT(chan)) {
+		u32 chan_status = readl(ioaddr + XGMAC_MTL_QINT_STATUS(chan));
+
+		if (chan_status & XGMAC_RXOVFIS)
+			ret |= CORE_IRQ_MTL_RX_OVERFLOW;
+
+		writel(~0x0, ioaddr + XGMAC_MTL_QINT_STATUS(chan));
+	}
+
+	return ret;
+}
+
+static void dwxgmac2_flow_ctrl(struct mac_device_info *hw, unsigned int duplex,
+			       unsigned int fc, unsigned int pause_time,
+			       u32 tx_cnt)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 i;
+
+	if (fc & FLOW_RX)
+		writel(XGMAC_RFE, ioaddr + XGMAC_RX_FLOW_CTRL);
+	if (fc & FLOW_TX) {
+		for (i = 0; i < tx_cnt; i++) {
+			u32 value = XGMAC_TFE;
+
+			if (duplex)
+				value |= pause_time << XGMAC_PT_SHIFT;
+
+			writel(value, ioaddr + XGMAC_Qx_TX_FLOW_CTRL(i));
+		}
+	}
+}
+
+static void dwxgmac2_pmt(struct mac_device_info *hw, unsigned long mode)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 val = 0x0;
+
+	if (mode & WAKE_MAGIC)
+		val |= XGMAC_PWRDWN | XGMAC_MGKPKTEN;
+	if (mode & WAKE_UCAST)
+		val |= XGMAC_PWRDWN | XGMAC_GLBLUCAST | XGMAC_RWKPKTEN;
+	if (val) {
+		u32 cfg = readl(ioaddr + XGMAC_RX_CONFIG);
+		cfg |= XGMAC_CONFIG_RE;
+		writel(cfg, ioaddr + XGMAC_RX_CONFIG);
+	}
+
+	writel(val, ioaddr + XGMAC_PMT);
+}
+
+static void dwxgmac2_set_umac_addr(struct mac_device_info *hw,
+				   unsigned char *addr, unsigned int reg_n)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 value;
+
+	value = (addr[5] << 8) | addr[4];
+	writel(value | XGMAC_AE, ioaddr + XGMAC_ADDR0_HIGH);
+
+	value = (addr[3] << 24) | (addr[2] << 16) | (addr[1] << 8) | addr[0];
+	writel(value, ioaddr + XGMAC_ADDR0_LOW);
+}
+
+static void dwxgmac2_get_umac_addr(struct mac_device_info *hw,
+				   unsigned char *addr, unsigned int reg_n)
+{
+	void __iomem *ioaddr = hw->pcsr;
+	u32 hi_addr, lo_addr;
+
+	/* Read the MAC address from the hardware */
+	hi_addr = readl(ioaddr + XGMAC_ADDR0_HIGH);
+	lo_addr = readl(ioaddr + XGMAC_ADDR0_LOW);
+
+	/* Extract the MAC address from the high and low words */
+	addr[0] = lo_addr & 0xff;
+	addr[1] = (lo_addr >> 8) & 0xff;
+	addr[2] = (lo_addr >> 16) & 0xff;
+	addr[3] = (lo_addr >> 24) & 0xff;
+	addr[4] = hi_addr & 0xff;
+	addr[5] = (hi_addr >> 8) & 0xff;
+}
+
+static void dwxgmac2_set_filter(struct mac_device_info *hw,
+				struct net_device *dev)
+{
+	void __iomem *ioaddr = (void __iomem *)dev->base_addr;
+	u32 value = XGMAC_FILTER_RA;
+
+	if (dev->flags & IFF_PROMISC) {
+		value |= XGMAC_FILTER_PR;
+	} else if ((dev->flags & IFF_ALLMULTI) ||
+		   (netdev_mc_count(dev) > HASH_TABLE_SIZE)) {
+		value |= XGMAC_FILTER_PM;
+		writel(~0x0, ioaddr + XGMAC_HASH_TABLE(0));
+		writel(~0x0, ioaddr + XGMAC_HASH_TABLE(1));
+	}
+
+	writel(value, ioaddr + XGMAC_PACKET_FILTER);
+}
+
+const struct stmmac_ops dwxgmac210_ops = {
+	.core_init = dwxgmac2_core_init,
+	.set_mac = dwxgmac2_set_mac,
+	.rx_ipc = dwxgmac2_rx_ipc,
+	.rx_queue_enable = dwxgmac2_rx_queue_enable,
+	.rx_queue_prio = dwxgmac2_rx_queue_prio,
+	.tx_queue_prio = NULL,
+	.rx_queue_routing = NULL,
+	.prog_mtl_rx_algorithms = dwxgmac2_prog_mtl_rx_algorithms,
+	.prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms,
+	.set_mtl_tx_queue_weight = NULL,
+	.map_mtl_to_dma = dwxgmac2_map_mtl_to_dma,
+	.config_cbs = NULL,
+	.dump_regs = NULL,
+	.host_irq_status = dwxgmac2_host_irq_status,
+	.host_mtl_irq_status = dwxgmac2_host_mtl_irq_status,
+	.flow_ctrl = dwxgmac2_flow_ctrl,
+	.pmt = dwxgmac2_pmt,
+	.set_umac_addr = dwxgmac2_set_umac_addr,
+	.get_umac_addr = dwxgmac2_get_umac_addr,
+	.set_eee_mode = NULL,
+	.reset_eee_mode = NULL,
+	.set_eee_timer = NULL,
+	.set_eee_pls = NULL,
+	.pcs_ctrl_ane = NULL,
+	.pcs_rane = NULL,
+	.pcs_get_adv_lp = NULL,
+	.debug = NULL,
+	.set_filter = dwxgmac2_set_filter,
+};
+
+int dwxgmac2_setup(struct stmmac_priv *priv)
+{
+	struct mac_device_info *mac = priv->hw;
+
+	dev_info(priv->device, "\tXGMAC2\n");
+
+	priv->dev->priv_flags |= IFF_UNICAST_FLT;
+	mac->pcsr = priv->ioaddr;
+	mac->multicast_filter_bins = priv->plat->multicast_filter_bins;
+	mac->unicast_filter_entries = priv->plat->unicast_filter_entries;
+	mac->mcast_bits_log2 = 0;
+
+	if (mac->multicast_filter_bins)
+		mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins);
+
+	mac->link.duplex = 0;
+	mac->link.speed10 = 0;
+	mac->link.speed100 = 0;
+	mac->link.speed1000 = XGMAC_CONFIG_SS_1000;
+	mac->link.speed2500 = XGMAC_CONFIG_SS_2500;
+	mac->link.speed10000 = XGMAC_CONFIG_SS_10000;
+	mac->link.speed_mask = XGMAC_CONFIG_SS_MASK;
+
+	mac->mii.addr = XGMAC_MDIO_ADDR;
+	mac->mii.data = XGMAC_MDIO_DATA;
+	mac->mii.addr_shift = 16;
+	mac->mii.addr_mask = GENMASK(20, 16);
+	mac->mii.reg_shift = 0;
+	mac->mii.reg_mask = GENMASK(15, 0);
+	mac->mii.clk_csr_shift = 19;
+	mac->mii.clk_csr_mask = GENMASK(21, 19);
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 24f5ff175aa4..4fa46f064720 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -198,11 +198,11 @@ static const struct stmmac_hwif_entry {
 		},
 		.desc = NULL,
 		.dma = NULL,
-		.mac = NULL,
+		.mac = &dwxgmac210_ops,
 		.hwtimestamp = NULL,
 		.mode = NULL,
 		.tc = NULL,
-		.setup = NULL,
+		.setup = dwxgmac2_setup,
 		.quirks = NULL,
 	},
 };
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 79911eefc2a7..ff0fd6978260 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -479,6 +479,7 @@ extern const struct stmmac_ops dwmac410_ops;
 extern const struct stmmac_dma_ops dwmac410_dma_ops;
 extern const struct stmmac_ops dwmac510_ops;
 extern const struct stmmac_tc_ops dwmac510_tc_ops;
+extern const struct stmmac_ops dwxgmac210_ops;
 
 #define GMAC_VERSION		0x00000020	/* GMAC CORE Version */
 #define GMAC4_VERSION		0x00000110	/* GMAC4+ CORE Version */
-- 
cgit v1.2.3


From d6ddfacd95c79d43465d4a85dffb1c9beca343a9 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:31 +0100
Subject: net: stmmac: Add DMA related callbacks for XGMAC2

Add the DMA related callbacks for the new IP block XGMAC2.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/Makefile       |   2 +-
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h     |  57 +++
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c | 411 +++++++++++++++++++++
 drivers/net/ethernet/stmicro/stmmac/hwif.c         |   2 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |   1 +
 5 files changed, 471 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c

diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index a6cf632c9592..da40d3bba037 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -5,7 +5,7 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o	\
 	      dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
-	      stmmac_tc.o dwxgmac2_core.o $(stmmac-y)
+	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o $(stmmac-y)
 
 # Ordering matters. Generic driver must be last.
 obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 7832571f791f..a6992332f801 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -138,4 +138,61 @@
 #define XGMAC_ABPSIS			BIT(1)
 #define XGMAC_TXUNFIS			BIT(0)
 
+/* DMA Registers */
+#define XGMAC_DMA_MODE			0x00003000
+#define XGMAC_SWR			BIT(0)
+#define XGMAC_DMA_SYSBUS_MODE		0x00003004
+#define XGMAC_WR_OSR_LMT		GENMASK(29, 24)
+#define XGMAC_WR_OSR_LMT_SHIFT		24
+#define XGMAC_RD_OSR_LMT		GENMASK(21, 16)
+#define XGMAC_RD_OSR_LMT_SHIFT		16
+#define XGMAC_EN_LPI			BIT(15)
+#define XGMAC_LPI_XIT_PKT		BIT(14)
+#define XGMAC_AAL			BIT(12)
+#define XGMAC_BLEN			GENMASK(7, 1)
+#define XGMAC_BLEN256			BIT(7)
+#define XGMAC_BLEN128			BIT(6)
+#define XGMAC_BLEN64			BIT(5)
+#define XGMAC_BLEN32			BIT(4)
+#define XGMAC_BLEN16			BIT(3)
+#define XGMAC_BLEN8			BIT(2)
+#define XGMAC_BLEN4			BIT(1)
+#define XGMAC_UNDEF			BIT(0)
+#define XGMAC_DMA_CH_CONTROL(x)		(0x00003100 + (0x80 * (x)))
+#define XGMAC_PBLx8			BIT(16)
+#define XGMAC_DMA_CH_TX_CONTROL(x)	(0x00003104 + (0x80 * (x)))
+#define XGMAC_TxPBL			GENMASK(21, 16)
+#define XGMAC_TxPBL_SHIFT		16
+#define XGMAC_TSE			BIT(12)
+#define XGMAC_OSP			BIT(4)
+#define XGMAC_TXST			BIT(0)
+#define XGMAC_DMA_CH_RX_CONTROL(x)	(0x00003108 + (0x80 * (x)))
+#define XGMAC_RxPBL			GENMASK(21, 16)
+#define XGMAC_RxPBL_SHIFT		16
+#define XGMAC_RXST			BIT(0)
+#define XGMAC_DMA_CH_TxDESC_LADDR(x)	(0x00003114 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_LADDR(x)	(0x0000311c + (0x80 * (x)))
+#define XGMAC_DMA_CH_TxDESC_TAIL_LPTR(x)	(0x00003124 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_TAIL_LPTR(x)	(0x0000312c + (0x80 * (x)))
+#define XGMAC_DMA_CH_TxDESC_RING_LEN(x)		(0x00003130 + (0x80 * (x)))
+#define XGMAC_DMA_CH_RxDESC_RING_LEN(x)		(0x00003134 + (0x80 * (x)))
+#define XGMAC_DMA_CH_INT_EN(x)		(0x00003138 + (0x80 * (x)))
+#define XGMAC_NIE			BIT(15)
+#define XGMAC_AIE			BIT(14)
+#define XGMAC_RBUE			BIT(7)
+#define XGMAC_RIE			BIT(6)
+#define XGMAC_TIE			BIT(0)
+#define XGMAC_DMA_INT_DEFAULT_EN	(XGMAC_NIE | XGMAC_AIE | XGMAC_RBUE | \
+					XGMAC_RIE | XGMAC_TIE)
+#define XGMAC_DMA_CH_Rx_WATCHDOG(x)	(0x0000313c + (0x80 * (x)))
+#define XGMAC_RWT			GENMASK(7, 0)
+#define XGMAC_DMA_CH_STATUS(x)		(0x00003160 + (0x80 * (x)))
+#define XGMAC_NIS			BIT(15)
+#define XGMAC_AIS			BIT(14)
+#define XGMAC_FBE			BIT(12)
+#define XGMAC_RBU			BIT(7)
+#define XGMAC_RI			BIT(6)
+#define XGMAC_TPS			BIT(1)
+#define XGMAC_TI			BIT(0)
+
 #endif /* __STMMAC_DWXGMAC2_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
new file mode 100644
index 000000000000..20909036e002
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC support.
+ */
+
+#include <linux/iopoll.h>
+#include "stmmac.h"
+#include "dwxgmac2.h"
+
+static int dwxgmac2_dma_reset(void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_MODE);
+
+	/* DMA SW reset */
+	writel(value | XGMAC_SWR, ioaddr + XGMAC_DMA_MODE);
+
+	return readl_poll_timeout(ioaddr + XGMAC_DMA_MODE, value,
+				  !(value & XGMAC_SWR), 0, 100000);
+}
+
+static void dwxgmac2_dma_init(void __iomem *ioaddr,
+			      struct stmmac_dma_cfg *dma_cfg, int atds)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE);
+
+	if (dma_cfg->aal)
+		value |= XGMAC_AAL;
+
+	writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE);
+}
+
+static void dwxgmac2_dma_init_chan(void __iomem *ioaddr,
+				   struct stmmac_dma_cfg *dma_cfg, u32 chan)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_CH_CONTROL(chan));
+
+	if (dma_cfg->pblx8)
+		value |= XGMAC_PBLx8;
+
+	writel(value, ioaddr + XGMAC_DMA_CH_CONTROL(chan));
+	writel(XGMAC_DMA_INT_DEFAULT_EN, ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+}
+
+static void dwxgmac2_dma_init_rx_chan(void __iomem *ioaddr,
+				      struct stmmac_dma_cfg *dma_cfg,
+				      u32 dma_rx_phy, u32 chan)
+{
+	u32 rxpbl = dma_cfg->rxpbl ?: dma_cfg->pbl;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value &= ~XGMAC_RxPBL;
+	value |= (rxpbl << XGMAC_RxPBL_SHIFT) & XGMAC_RxPBL;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+
+	writel(dma_rx_phy, ioaddr + XGMAC_DMA_CH_RxDESC_LADDR(chan));
+}
+
+static void dwxgmac2_dma_init_tx_chan(void __iomem *ioaddr,
+				      struct stmmac_dma_cfg *dma_cfg,
+				      u32 dma_tx_phy, u32 chan)
+{
+	u32 txpbl = dma_cfg->txpbl ?: dma_cfg->pbl;
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+	value &= ~XGMAC_TxPBL;
+	value |= (txpbl << XGMAC_TxPBL_SHIFT) & XGMAC_TxPBL;
+	value |= XGMAC_OSP;
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	writel(dma_tx_phy, ioaddr + XGMAC_DMA_CH_TxDESC_LADDR(chan));
+}
+
+static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_SYSBUS_MODE);
+	int i;
+
+	if (axi->axi_lpi_en)
+		value |= XGMAC_EN_LPI;
+	if (axi->axi_xit_frm)
+		value |= XGMAC_LPI_XIT_PKT;
+
+	value &= ~XGMAC_WR_OSR_LMT;
+	value |= (axi->axi_wr_osr_lmt << XGMAC_WR_OSR_LMT_SHIFT) &
+		XGMAC_WR_OSR_LMT;
+
+	value &= ~XGMAC_RD_OSR_LMT;
+	value |= (axi->axi_rd_osr_lmt << XGMAC_RD_OSR_LMT_SHIFT) &
+		XGMAC_RD_OSR_LMT;
+
+	value &= ~XGMAC_BLEN;
+	for (i = 0; i < AXI_BLEN; i++) {
+		if (axi->axi_blen[i])
+			value &= ~XGMAC_UNDEF;
+
+		switch (axi->axi_blen[i]) {
+		case 256:
+			value |= XGMAC_BLEN256;
+			break;
+		case 128:
+			value |= XGMAC_BLEN128;
+			break;
+		case 64:
+			value |= XGMAC_BLEN64;
+			break;
+		case 32:
+			value |= XGMAC_BLEN32;
+			break;
+		case 16:
+			value |= XGMAC_BLEN16;
+			break;
+		case 8:
+			value |= XGMAC_BLEN8;
+			break;
+		case 4:
+			value |= XGMAC_BLEN4;
+			break;
+		}
+	}
+
+	writel(value, ioaddr + XGMAC_DMA_SYSBUS_MODE);
+}
+
+static void dwxgmac2_dma_rx_mode(void __iomem *ioaddr, int mode,
+				 u32 channel, int fifosz, u8 qmode)
+{
+	u32 value = readl(ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
+	unsigned int rqs = fifosz / 256 - 1;
+
+	if (mode == SF_DMA_MODE) {
+		value |= XGMAC_RSF;
+	} else {
+		value &= ~XGMAC_RSF;
+		value &= ~XGMAC_RTC;
+
+		if (mode <= 64)
+			value |= 0x0 << XGMAC_RTC_SHIFT;
+		else if (mode <= 96)
+			value |= 0x2 << XGMAC_RTC_SHIFT;
+		else
+			value |= 0x3 << XGMAC_RTC_SHIFT;
+	}
+
+	value &= ~XGMAC_RQS;
+	value |= (rqs << XGMAC_RQS_SHIFT) & XGMAC_RQS;
+
+	writel(value, ioaddr + XGMAC_MTL_RXQ_OPMODE(channel));
+
+	/* Enable MTL RX overflow */
+	value = readl(ioaddr + XGMAC_MTL_QINTEN(channel));
+	writel(value | XGMAC_RXOIE, ioaddr + XGMAC_MTL_QINTEN(channel));
+}
+
+static void dwxgmac2_dma_tx_mode(void __iomem *ioaddr, int mode,
+				 u32 channel, int fifosz, u8 qmode)
+{
+	u32 value = readl(ioaddr + XGMAC_MTL_TXQ_OPMODE(channel));
+	unsigned int tqs = fifosz / 256 - 1;
+
+	if (mode == SF_DMA_MODE) {
+		value |= XGMAC_TSF;
+	} else {
+		value &= ~XGMAC_TSF;
+		value &= ~XGMAC_TTC;
+
+		if (mode <= 64)
+			value |= 0x0 << XGMAC_TTC_SHIFT;
+		else if (mode <= 96)
+			value |= 0x2 << XGMAC_TTC_SHIFT;
+		else if (mode <= 128)
+			value |= 0x3 << XGMAC_TTC_SHIFT;
+		else if (mode <= 192)
+			value |= 0x4 << XGMAC_TTC_SHIFT;
+		else if (mode <= 256)
+			value |= 0x5 << XGMAC_TTC_SHIFT;
+		else if (mode <= 384)
+			value |= 0x6 << XGMAC_TTC_SHIFT;
+		else
+			value |= 0x7 << XGMAC_TTC_SHIFT;
+	}
+
+	value &= ~XGMAC_TXQEN;
+	if (qmode != MTL_QUEUE_AVB)
+		value |= 0x2 << XGMAC_TXQEN_SHIFT;
+	else
+		value |= 0x1 << XGMAC_TXQEN_SHIFT;
+
+	value &= ~XGMAC_TQS;
+	value |= (tqs << XGMAC_TQS_SHIFT) & XGMAC_TQS;
+
+	writel(value, ioaddr +  XGMAC_MTL_TXQ_OPMODE(channel));
+}
+
+static void dwxgmac2_enable_dma_irq(void __iomem *ioaddr, u32 chan)
+{
+	writel(XGMAC_DMA_INT_DEFAULT_EN, ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+}
+
+static void dwxgmac2_disable_dma_irq(void __iomem *ioaddr, u32 chan)
+{
+	writel(0, ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+}
+
+static void dwxgmac2_dma_start_tx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+	value |= XGMAC_TXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_TX_CONFIG);
+	value |= XGMAC_CONFIG_TE;
+	writel(value, ioaddr + XGMAC_TX_CONFIG);
+}
+
+static void dwxgmac2_dma_stop_tx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+	value &= ~XGMAC_TXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_TX_CONFIG);
+	value &= ~XGMAC_CONFIG_TE;
+	writel(value, ioaddr + XGMAC_TX_CONFIG);
+}
+
+static void dwxgmac2_dma_start_rx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value |= XGMAC_RXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_RX_CONFIG);
+	value |= XGMAC_CONFIG_RE;
+	writel(value, ioaddr + XGMAC_RX_CONFIG);
+}
+
+static void dwxgmac2_dma_stop_rx(void __iomem *ioaddr, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value &= ~XGMAC_RXST;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+
+	value = readl(ioaddr + XGMAC_RX_CONFIG);
+	value &= ~XGMAC_CONFIG_RE;
+	writel(value, ioaddr + XGMAC_RX_CONFIG);
+}
+
+static int dwxgmac2_dma_interrupt(void __iomem *ioaddr,
+				  struct stmmac_extra_stats *x, u32 chan)
+{
+	u32 intr_status = readl(ioaddr + XGMAC_DMA_CH_STATUS(chan));
+	int ret = 0;
+
+	/* ABNORMAL interrupts */
+	if (unlikely(intr_status & XGMAC_AIS)) {
+		if (unlikely(intr_status & XGMAC_TPS)) {
+			x->tx_process_stopped_irq++;
+			ret |= tx_hard_error;
+		}
+		if (unlikely(intr_status & XGMAC_FBE)) {
+			x->fatal_bus_error_irq++;
+			ret |= tx_hard_error;
+		}
+	}
+
+	/* TX/RX NORMAL interrupts */
+	if (likely(intr_status & XGMAC_NIS)) {
+		x->normal_irq_n++;
+
+		if (likely(intr_status & XGMAC_RI)) {
+			u32 value = readl(ioaddr + XGMAC_DMA_CH_INT_EN(chan));
+			if (likely(value & XGMAC_RIE)) {
+				x->rx_normal_irq_n++;
+				ret |= handle_rx;
+			}
+		}
+		if (likely(intr_status & XGMAC_TI)) {
+			x->tx_normal_irq_n++;
+			ret |= handle_tx;
+		}
+	}
+
+	/* Clear interrupts */
+	writel(~0x0, ioaddr + XGMAC_DMA_CH_STATUS(chan));
+
+	return ret;
+}
+
+static void dwxgmac2_get_hw_feature(void __iomem *ioaddr,
+				    struct dma_features *dma_cap)
+{
+	u32 hw_cap;
+
+	/*  MAC HW feature 0 */
+	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0);
+	dma_cap->rx_coe = (hw_cap & XGMAC_HWFEAT_RXCOESEL) >> 16;
+	dma_cap->tx_coe = (hw_cap & XGMAC_HWFEAT_TXCOESEL) >> 14;
+	dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12;
+	dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11;
+	dma_cap->av &= (hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10;
+	dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7;
+	dma_cap->pmt_remote_wake_up = (hw_cap & XGMAC_HWFEAT_RWKSEL) >> 6;
+	dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1;
+
+	/* MAC HW feature 1 */
+	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1);
+	dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18;
+	dma_cap->tx_fifo_size =
+		128 << ((hw_cap & XGMAC_HWFEAT_TXFIFOSIZE) >> 6);
+	dma_cap->rx_fifo_size =
+		128 << ((hw_cap & XGMAC_HWFEAT_RXFIFOSIZE) >> 0);
+
+	/* MAC HW feature 2 */
+	hw_cap = readl(ioaddr + XGMAC_HW_FEATURE2);
+	dma_cap->pps_out_num = (hw_cap & XGMAC_HWFEAT_PPSOUTNUM) >> 24;
+	dma_cap->number_tx_channel =
+		((hw_cap & XGMAC_HWFEAT_TXCHCNT) >> 18) + 1;
+	dma_cap->number_rx_channel =
+		((hw_cap & XGMAC_HWFEAT_RXCHCNT) >> 12) + 1;
+	dma_cap->number_tx_queues =
+		((hw_cap & XGMAC_HWFEAT_TXQCNT) >> 6) + 1;
+	dma_cap->number_rx_queues =
+		((hw_cap & XGMAC_HWFEAT_RXQCNT) >> 0) + 1;
+}
+
+static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 nchan)
+{
+	u32 i;
+
+	for (i = 0; i < nchan; i++)
+		writel(riwt & XGMAC_RWT, ioaddr + XGMAC_DMA_CH_Rx_WATCHDOG(i));
+}
+
+static void dwxgmac2_set_rx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
+{
+	writel(len, ioaddr + XGMAC_DMA_CH_RxDESC_RING_LEN(chan));
+}
+
+static void dwxgmac2_set_tx_ring_len(void __iomem *ioaddr, u32 len, u32 chan)
+{
+	writel(len, ioaddr + XGMAC_DMA_CH_TxDESC_RING_LEN(chan));
+}
+
+static void dwxgmac2_set_rx_tail_ptr(void __iomem *ioaddr, u32 ptr, u32 chan)
+{
+	writel(ptr, ioaddr + XGMAC_DMA_CH_RxDESC_TAIL_LPTR(chan));
+}
+
+static void dwxgmac2_set_tx_tail_ptr(void __iomem *ioaddr, u32 ptr, u32 chan)
+{
+	writel(ptr, ioaddr + XGMAC_DMA_CH_TxDESC_TAIL_LPTR(chan));
+}
+
+static void dwxgmac2_enable_tso(void __iomem *ioaddr, bool en, u32 chan)
+{
+	u32 value = readl(ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+
+	if (en)
+		value |= XGMAC_TSE;
+	else
+		value &= ~XGMAC_TSE;
+
+	writel(value, ioaddr + XGMAC_DMA_CH_TX_CONTROL(chan));
+}
+
+static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan)
+{
+	u32 value;
+
+	value = readl(ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+	value |= bfsize << 1;
+	writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan));
+}
+
+const struct stmmac_dma_ops dwxgmac210_dma_ops = {
+	.reset = dwxgmac2_dma_reset,
+	.init = dwxgmac2_dma_init,
+	.init_chan = dwxgmac2_dma_init_chan,
+	.init_rx_chan = dwxgmac2_dma_init_rx_chan,
+	.init_tx_chan = dwxgmac2_dma_init_tx_chan,
+	.axi = dwxgmac2_dma_axi,
+	.dump_regs = NULL,
+	.dma_rx_mode = dwxgmac2_dma_rx_mode,
+	.dma_tx_mode = dwxgmac2_dma_tx_mode,
+	.enable_dma_irq = dwxgmac2_enable_dma_irq,
+	.disable_dma_irq = dwxgmac2_disable_dma_irq,
+	.start_tx = dwxgmac2_dma_start_tx,
+	.stop_tx = dwxgmac2_dma_stop_tx,
+	.start_rx = dwxgmac2_dma_start_rx,
+	.stop_rx = dwxgmac2_dma_stop_rx,
+	.dma_interrupt = dwxgmac2_dma_interrupt,
+	.get_hw_feature = dwxgmac2_get_hw_feature,
+	.rx_watchdog = dwxgmac2_rx_watchdog,
+	.set_rx_ring_len = dwxgmac2_set_rx_ring_len,
+	.set_tx_ring_len = dwxgmac2_set_tx_ring_len,
+	.set_rx_tail_ptr = dwxgmac2_set_rx_tail_ptr,
+	.set_tx_tail_ptr = dwxgmac2_set_tx_tail_ptr,
+	.enable_tso = dwxgmac2_enable_tso,
+	.set_bfsize = dwxgmac2_set_bfsize,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 4fa46f064720..4030199aee7b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -197,7 +197,7 @@ static const struct stmmac_hwif_entry {
 			.mmc_off = 0,
 		},
 		.desc = NULL,
-		.dma = NULL,
+		.dma = &dwxgmac210_dma_ops,
 		.mac = &dwxgmac210_ops,
 		.hwtimestamp = NULL,
 		.mode = NULL,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index ff0fd6978260..3106eaca60cd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -480,6 +480,7 @@ extern const struct stmmac_dma_ops dwmac410_dma_ops;
 extern const struct stmmac_ops dwmac510_ops;
 extern const struct stmmac_tc_ops dwmac510_tc_ops;
 extern const struct stmmac_ops dwxgmac210_ops;
+extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
 
 #define GMAC_VERSION		0x00000020	/* GMAC CORE Version */
 #define GMAC4_VERSION		0x00000110	/* GMAC4+ CORE Version */
-- 
cgit v1.2.3


From 874dfb65a484cff9b95014ed66c7cc6d2d6c4436 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:32 +0100
Subject: net: stmmac: Add descriptor related callbacks for XGMAC2

Add the descriptor related callbacks for the new IP block XGMAC2.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/Makefile       |   3 +-
 drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h     |  30 +++
 .../net/ethernet/stmicro/stmmac/dwxgmac2_descs.c   | 280 +++++++++++++++++++++
 drivers/net/ethernet/stmicro/stmmac/hwif.c         |   2 +-
 drivers/net/ethernet/stmicro/stmmac/hwif.h         |   1 +
 5 files changed, 314 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c

diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index da40d3bba037..99967a80a8c8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -5,7 +5,8 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o	\
 	      dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o	\
 	      mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o	\
 	      dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \
-	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o $(stmmac-y)
+	      stmmac_tc.o dwxgmac2_core.o dwxgmac2_dma.o dwxgmac2_descs.o \
+	      $(stmmac-y)
 
 # Ordering matters. Generic driver must be last.
 obj-$(CONFIG_STMMAC_PLATFORM)	+= stmmac-platform.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index a6992332f801..0a80fa25afe3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -195,4 +195,34 @@
 #define XGMAC_TPS			BIT(1)
 #define XGMAC_TI			BIT(0)
 
+/* Descriptors */
+#define XGMAC_TDES2_IOC			BIT(31)
+#define XGMAC_TDES2_TTSE		BIT(30)
+#define XGMAC_TDES2_B2L			GENMASK(29, 16)
+#define XGMAC_TDES2_B2L_SHIFT		16
+#define XGMAC_TDES2_B1L			GENMASK(13, 0)
+#define XGMAC_TDES3_OWN			BIT(31)
+#define XGMAC_TDES3_CTXT		BIT(30)
+#define XGMAC_TDES3_FD			BIT(29)
+#define XGMAC_TDES3_LD			BIT(28)
+#define XGMAC_TDES3_CPC			GENMASK(27, 26)
+#define XGMAC_TDES3_CPC_SHIFT		26
+#define XGMAC_TDES3_TCMSSV		BIT(26)
+#define XGMAC_TDES3_THL			GENMASK(22, 19)
+#define XGMAC_TDES3_THL_SHIFT		19
+#define XGMAC_TDES3_TSE			BIT(18)
+#define XGMAC_TDES3_CIC			GENMASK(17, 16)
+#define XGMAC_TDES3_CIC_SHIFT		16
+#define XGMAC_TDES3_TPL			GENMASK(17, 0)
+#define XGMAC_TDES3_FL			GENMASK(14, 0)
+#define XGMAC_RDES3_OWN			BIT(31)
+#define XGMAC_RDES3_CTXT		BIT(30)
+#define XGMAC_RDES3_IOC			BIT(30)
+#define XGMAC_RDES3_LD			BIT(28)
+#define XGMAC_RDES3_CDA			BIT(27)
+#define XGMAC_RDES3_ES			BIT(15)
+#define XGMAC_RDES3_PL			GENMASK(13, 0)
+#define XGMAC_RDES3_TSD			BIT(6)
+#define XGMAC_RDES3_TSA			BIT(4)
+
 #endif /* __STMMAC_DWXGMAC2_H__ */
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
new file mode 100644
index 000000000000..1d858fdec997
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c
@@ -0,0 +1,280 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+/*
+ * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates.
+ * stmmac XGMAC support.
+ */
+
+#include <linux/stmmac.h>
+#include "common.h"
+#include "dwxgmac2.h"
+
+static int dwxgmac2_get_tx_status(void *data, struct stmmac_extra_stats *x,
+				  struct dma_desc *p, void __iomem *ioaddr)
+{
+	unsigned int tdes3 = le32_to_cpu(p->des3);
+	int ret = tx_done;
+
+	if (unlikely(tdes3 & XGMAC_TDES3_OWN))
+		return tx_dma_own;
+	if (likely(!(tdes3 & XGMAC_TDES3_LD)))
+		return tx_not_ls;
+
+	return ret;
+}
+
+static int dwxgmac2_get_rx_status(void *data, struct stmmac_extra_stats *x,
+				  struct dma_desc *p)
+{
+	unsigned int rdes3 = le32_to_cpu(p->des3);
+	int ret = good_frame;
+
+	if (unlikely(rdes3 & XGMAC_RDES3_OWN))
+		return dma_own;
+	if (likely(!(rdes3 & XGMAC_RDES3_LD)))
+		return discard_frame;
+	if (unlikely(rdes3 & XGMAC_RDES3_ES))
+		ret = discard_frame;
+
+	return ret;
+}
+
+static int dwxgmac2_get_tx_len(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des2) & XGMAC_TDES2_B1L);
+}
+
+static int dwxgmac2_get_tx_owner(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des3) & XGMAC_TDES3_OWN) > 0;
+}
+
+static void dwxgmac2_set_tx_owner(struct dma_desc *p)
+{
+	p->des3 |= cpu_to_le32(XGMAC_TDES3_OWN);
+}
+
+static void dwxgmac2_set_rx_owner(struct dma_desc *p, int disable_rx_ic)
+{
+	p->des3 = cpu_to_le32(XGMAC_RDES3_OWN);
+
+	if (!disable_rx_ic)
+		p->des3 |= cpu_to_le32(XGMAC_RDES3_IOC);
+}
+
+static int dwxgmac2_get_tx_ls(struct dma_desc *p)
+{
+	return (le32_to_cpu(p->des3) & XGMAC_RDES3_LD) > 0;
+}
+
+static int dwxgmac2_get_rx_frame_len(struct dma_desc *p, int rx_coe)
+{
+	return (le32_to_cpu(p->des3) & XGMAC_RDES3_PL);
+}
+
+static void dwxgmac2_enable_tx_timestamp(struct dma_desc *p)
+{
+	p->des2 |= cpu_to_le32(XGMAC_TDES2_TTSE);
+}
+
+static int dwxgmac2_get_tx_timestamp_status(struct dma_desc *p)
+{
+	return 0; /* Not supported */
+}
+
+static inline void dwxgmac2_get_timestamp(void *desc, u32 ats, u64 *ts)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	u64 ns = 0;
+
+	ns += le32_to_cpu(p->des1) * 1000000000ULL;
+	ns += le32_to_cpu(p->des0);
+
+	*ts = ns;
+}
+
+static int dwxgmac2_rx_check_timestamp(void *desc)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes3 = le32_to_cpu(p->des3);
+	bool desc_valid, ts_valid;
+
+	desc_valid = !(rdes3 & XGMAC_RDES3_OWN) && (rdes3 & XGMAC_RDES3_CTXT);
+	ts_valid = !(rdes3 & XGMAC_RDES3_TSD) && (rdes3 & XGMAC_RDES3_TSA);
+
+	if (likely(desc_valid && ts_valid))
+		return 0;
+	return -EINVAL;
+}
+
+static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc,
+					    u32 ats)
+{
+	struct dma_desc *p = (struct dma_desc *)desc;
+	unsigned int rdes3 = le32_to_cpu(p->des3);
+	int ret = -EBUSY;
+
+	if (likely(rdes3 & XGMAC_RDES3_CDA)) {
+		ret = dwxgmac2_rx_check_timestamp(next_desc);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic,
+				  int mode, int end)
+{
+	dwxgmac2_set_rx_owner(p, disable_rx_ic);
+}
+
+static void dwxgmac2_init_tx_desc(struct dma_desc *p, int mode, int end)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = 0;
+	p->des3 = 0;
+}
+
+static void dwxgmac2_prepare_tx_desc(struct dma_desc *p, int is_fs, int len,
+				     bool csum_flag, int mode, bool tx_own,
+				     bool ls, unsigned int tot_pkt_len)
+{
+	unsigned int tdes3 = le32_to_cpu(p->des3);
+
+	p->des2 |= cpu_to_le32(len & XGMAC_TDES2_B1L);
+
+	tdes3 = tot_pkt_len & XGMAC_TDES3_FL;
+	if (is_fs)
+		tdes3 |= XGMAC_TDES3_FD;
+	else
+		tdes3 &= ~XGMAC_TDES3_FD;
+
+	if (csum_flag)
+		tdes3 |= 0x3 << XGMAC_TDES3_CIC_SHIFT;
+	else
+		tdes3 &= ~XGMAC_TDES3_CIC;
+
+	if (ls)
+		tdes3 |= XGMAC_TDES3_LD;
+	else
+		tdes3 &= ~XGMAC_TDES3_LD;
+
+	/* Finally set the OWN bit. Later the DMA will start! */
+	if (tx_own)
+		tdes3 |= XGMAC_TDES3_OWN;
+
+	if (is_fs && tx_own)
+		/* When the own bit, for the first frame, has to be set, all
+		 * descriptors for the same frame has to be set before, to
+		 * avoid race condition.
+		 */
+		dma_wmb();
+
+	p->des3 = cpu_to_le32(tdes3);
+}
+
+static void dwxgmac2_prepare_tso_tx_desc(struct dma_desc *p, int is_fs,
+					 int len1, int len2, bool tx_own,
+					 bool ls, unsigned int tcphdrlen,
+					 unsigned int tcppayloadlen)
+{
+	unsigned int tdes3 = le32_to_cpu(p->des3);
+
+	if (len1)
+		p->des2 |= cpu_to_le32(len1 & XGMAC_TDES2_B1L);
+	if (len2)
+		p->des2 |= cpu_to_le32((len2 << XGMAC_TDES2_B2L_SHIFT) &
+				XGMAC_TDES2_B2L);
+	if (is_fs) {
+		tdes3 |= XGMAC_TDES3_FD | XGMAC_TDES3_TSE;
+		tdes3 |= (tcphdrlen << XGMAC_TDES3_THL_SHIFT) &
+			XGMAC_TDES3_THL;
+		tdes3 |= tcppayloadlen & XGMAC_TDES3_TPL;
+	} else {
+		tdes3 &= ~XGMAC_TDES3_FD;
+	}
+
+	if (ls)
+		tdes3 |= XGMAC_TDES3_LD;
+	else
+		tdes3 &= ~XGMAC_TDES3_LD;
+
+	/* Finally set the OWN bit. Later the DMA will start! */
+	if (tx_own)
+		tdes3 |= XGMAC_TDES3_OWN;
+
+	if (is_fs && tx_own)
+		/* When the own bit, for the first frame, has to be set, all
+		 * descriptors for the same frame has to be set before, to
+		 * avoid race condition.
+		 */
+		dma_wmb();
+
+	p->des3 = cpu_to_le32(tdes3);
+}
+
+static void dwxgmac2_release_tx_desc(struct dma_desc *p, int mode)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = 0;
+	p->des3 = 0;
+}
+
+static void dwxgmac2_set_tx_ic(struct dma_desc *p)
+{
+	p->des2 |= cpu_to_le32(XGMAC_TDES2_IOC);
+}
+
+static void dwxgmac2_set_mss(struct dma_desc *p, unsigned int mss)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = cpu_to_le32(mss);
+	p->des3 = cpu_to_le32(XGMAC_TDES3_CTXT | XGMAC_TDES3_TCMSSV);
+}
+
+static void dwxgmac2_get_addr(struct dma_desc *p, unsigned int *addr)
+{
+	*addr = le32_to_cpu(p->des0);
+}
+
+static void dwxgmac2_set_addr(struct dma_desc *p, dma_addr_t addr)
+{
+	p->des0 = cpu_to_le32(addr);
+	p->des1 = 0;
+}
+
+static void dwxgmac2_clear(struct dma_desc *p)
+{
+	p->des0 = 0;
+	p->des1 = 0;
+	p->des2 = 0;
+	p->des3 = 0;
+}
+
+const struct stmmac_desc_ops dwxgmac210_desc_ops = {
+	.tx_status = dwxgmac2_get_tx_status,
+	.rx_status = dwxgmac2_get_rx_status,
+	.get_tx_len = dwxgmac2_get_tx_len,
+	.get_tx_owner = dwxgmac2_get_tx_owner,
+	.set_tx_owner = dwxgmac2_set_tx_owner,
+	.set_rx_owner = dwxgmac2_set_rx_owner,
+	.get_tx_ls = dwxgmac2_get_tx_ls,
+	.get_rx_frame_len = dwxgmac2_get_rx_frame_len,
+	.enable_tx_timestamp = dwxgmac2_enable_tx_timestamp,
+	.get_tx_timestamp_status = dwxgmac2_get_tx_timestamp_status,
+	.get_rx_timestamp_status = dwxgmac2_get_rx_timestamp_status,
+	.get_timestamp = dwxgmac2_get_timestamp,
+	.set_tx_ic = dwxgmac2_set_tx_ic,
+	.prepare_tx_desc = dwxgmac2_prepare_tx_desc,
+	.prepare_tso_tx_desc = dwxgmac2_prepare_tso_tx_desc,
+	.release_tx_desc = dwxgmac2_release_tx_desc,
+	.init_rx_desc = dwxgmac2_init_rx_desc,
+	.init_tx_desc = dwxgmac2_init_tx_desc,
+	.set_mss = dwxgmac2_set_mss,
+	.get_addr = dwxgmac2_get_addr,
+	.set_addr = dwxgmac2_set_addr,
+	.clear = dwxgmac2_clear,
+};
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 4030199aee7b..4b4ba1c8bad5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -196,7 +196,7 @@ static const struct stmmac_hwif_entry {
 			.ptp_off = 0,
 			.mmc_off = 0,
 		},
-		.desc = NULL,
+		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
 		.mac = &dwxgmac210_ops,
 		.hwtimestamp = NULL,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 3106eaca60cd..92b8944f26e3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -481,6 +481,7 @@ extern const struct stmmac_ops dwmac510_ops;
 extern const struct stmmac_tc_ops dwmac510_tc_ops;
 extern const struct stmmac_ops dwxgmac210_ops;
 extern const struct stmmac_dma_ops dwxgmac210_dma_ops;
+extern const struct stmmac_desc_ops dwxgmac210_desc_ops;
 
 #define GMAC_VERSION		0x00000020	/* GMAC CORE Version */
 #define GMAC4_VERSION		0x00000110	/* GMAC4+ CORE Version */
-- 
cgit v1.2.3


From 6fc21117b791b601362fd2240fab833cbdbfdc15 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:33 +0100
Subject: net: stmmac: Add MDIO related functions for XGMAC2

Add the MDIO related funcionalities for the new IP block XGMAC2.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Cc: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 133 +++++++++++++++++++++-
 1 file changed, 129 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 5df1a608e566..b72ef171477e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -29,6 +29,7 @@
 #include <linux/phy.h>
 #include <linux/slab.h>
 
+#include "dwxgmac2.h"
 #include "stmmac.h"
 
 #define MII_BUSY 0x00000001
@@ -39,6 +40,115 @@
 #define MII_GMAC4_WRITE			(1 << MII_GMAC4_GOC_SHIFT)
 #define MII_GMAC4_READ			(3 << MII_GMAC4_GOC_SHIFT)
 
+/* XGMAC defines */
+#define MII_XGMAC_SADDR			BIT(18)
+#define MII_XGMAC_CMD_SHIFT		16
+#define MII_XGMAC_WRITE			(1 << MII_XGMAC_CMD_SHIFT)
+#define MII_XGMAC_READ			(3 << MII_XGMAC_CMD_SHIFT)
+#define MII_XGMAC_BUSY			BIT(22)
+#define MII_XGMAC_MAX_C22ADDR		3
+#define MII_XGMAC_C22P_MASK		GENMASK(MII_XGMAC_MAX_C22ADDR, 0)
+
+static int stmmac_xgmac2_c22_format(struct stmmac_priv *priv, int phyaddr,
+				    int phyreg, u32 *hw_addr)
+{
+	unsigned int mii_data = priv->hw->mii.data;
+	u32 tmp;
+
+	/* HW does not support C22 addr >= 4 */
+	if (phyaddr > MII_XGMAC_MAX_C22ADDR)
+		return -ENODEV;
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Set port as Clause 22 */
+	tmp = readl(priv->ioaddr + XGMAC_MDIO_C22P);
+	tmp &= ~MII_XGMAC_C22P_MASK;
+	tmp |= BIT(phyaddr);
+	writel(tmp, priv->ioaddr + XGMAC_MDIO_C22P);
+
+	*hw_addr = (phyaddr << 16) | (phyreg & 0x1f);
+	return 0;
+}
+
+static int stmmac_xgmac2_mdio_read(struct mii_bus *bus, int phyaddr, int phyreg)
+{
+	struct net_device *ndev = bus->priv;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int mii_address = priv->hw->mii.addr;
+	unsigned int mii_data = priv->hw->mii.data;
+	u32 tmp, addr, value = MII_XGMAC_BUSY;
+	int ret;
+
+	if (phyreg & MII_ADDR_C45) {
+		return -EOPNOTSUPP;
+	} else {
+		ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
+		if (ret)
+			return ret;
+	}
+
+	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
+		& priv->hw->mii.clk_csr_mask;
+	value |= MII_XGMAC_SADDR | MII_XGMAC_READ;
+
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Set the MII address register to read */
+	writel(addr, priv->ioaddr + mii_address);
+	writel(value, priv->ioaddr + mii_data);
+
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Read the data from the MII data register */
+	return readl(priv->ioaddr + mii_data) & GENMASK(15, 0);
+}
+
+static int stmmac_xgmac2_mdio_write(struct mii_bus *bus, int phyaddr,
+				    int phyreg, u16 phydata)
+{
+	struct net_device *ndev = bus->priv;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	unsigned int mii_address = priv->hw->mii.addr;
+	unsigned int mii_data = priv->hw->mii.data;
+	u32 addr, tmp, value = MII_XGMAC_BUSY;
+	int ret;
+
+	if (phyreg & MII_ADDR_C45) {
+		return -EOPNOTSUPP;
+	} else {
+		ret = stmmac_xgmac2_c22_format(priv, phyaddr, phyreg, &addr);
+		if (ret)
+			return ret;
+	}
+
+	value |= (priv->clk_csr << priv->hw->mii.clk_csr_shift)
+		& priv->hw->mii.clk_csr_mask;
+	value |= phydata | MII_XGMAC_SADDR;
+	value |= MII_XGMAC_WRITE;
+
+	/* Wait until any existing MII operation is complete */
+	if (readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+			       !(tmp & MII_XGMAC_BUSY), 100, 10000))
+		return -EBUSY;
+
+	/* Set the MII address register to write */
+	writel(addr, priv->ioaddr + mii_address);
+	writel(value, priv->ioaddr + mii_data);
+
+	/* Wait until any existing MII operation is complete */
+	return readl_poll_timeout(priv->ioaddr + mii_data, tmp,
+				  !(tmp & MII_XGMAC_BUSY), 100, 10000);
+}
+
 /**
  * stmmac_mdio_read
  * @bus: points to the mii_bus structure
@@ -205,7 +315,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 	struct stmmac_mdio_bus_data *mdio_bus_data = priv->plat->mdio_bus_data;
 	struct device_node *mdio_node = priv->plat->mdio_node;
 	struct device *dev = ndev->dev.parent;
-	int addr, found;
+	int addr, found, max_addr;
 
 	if (!mdio_bus_data)
 		return 0;
@@ -223,8 +333,23 @@ int stmmac_mdio_register(struct net_device *ndev)
 #endif
 
 	new_bus->name = "stmmac";
-	new_bus->read = &stmmac_mdio_read;
-	new_bus->write = &stmmac_mdio_write;
+
+	if (priv->plat->has_xgmac) {
+		new_bus->read = &stmmac_xgmac2_mdio_read;
+		new_bus->write = &stmmac_xgmac2_mdio_write;
+
+		/* Right now only C22 phys are supported */
+		max_addr = MII_XGMAC_MAX_C22ADDR + 1;
+
+		/* Check if DT specified an unsupported phy addr */
+		if (priv->plat->phy_addr > MII_XGMAC_MAX_C22ADDR)
+			dev_err(dev, "Unsupported phy_addr (max=%d)\n",
+					MII_XGMAC_MAX_C22ADDR);
+	} else {
+		new_bus->read = &stmmac_mdio_read;
+		new_bus->write = &stmmac_mdio_write;
+		max_addr = PHY_MAX_ADDR;
+	}
 
 	new_bus->reset = &stmmac_mdio_reset;
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x",
@@ -243,7 +368,7 @@ int stmmac_mdio_register(struct net_device *ndev)
 		goto bus_register_done;
 
 	found = 0;
-	for (addr = 0; addr < PHY_MAX_ADDR; addr++) {
+	for (addr = 0; addr < max_addr; addr++) {
 		struct phy_device *phydev = mdiobus_get_phy(new_bus, addr);
 
 		if (!phydev)
-- 
cgit v1.2.3


From 4bb7aff9e6d0f92483f27ec04683efc2fdd42d25 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:34 +0100
Subject: net: stmmac: Add PTP support for XGMAC2

XGMAC2 uses the same engine of timestamping as GMAC4. Let's use the same
callbacks.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/hwif.c       | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c | 6 ++++--
 drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h | 1 +
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c
index 4b4ba1c8bad5..357309a6d6a5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.c
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c
@@ -193,13 +193,13 @@ static const struct stmmac_hwif_entry {
 		.xgmac = true,
 		.min_id = DWXGMAC_CORE_2_10,
 		.regs = {
-			.ptp_off = 0,
+			.ptp_off = PTP_XGMAC_OFFSET,
 			.mmc_off = 0,
 		},
 		.desc = &dwxgmac210_desc_ops,
 		.dma = &dwxgmac210_dma_ops,
 		.mac = &dwxgmac210_ops,
-		.hwtimestamp = NULL,
+		.hwtimestamp = &stmmac_ptp,
 		.mode = NULL,
 		.tc = NULL,
 		.setup = dwxgmac2_setup,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
index 0cb0e39a2be9..2293e21f789f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c
@@ -71,6 +71,9 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 	u32 sec, nsec;
 	u32 quotient, reminder;
 	int neg_adj = 0;
+	bool xmac;
+
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (delta < 0) {
 		neg_adj = 1;
@@ -82,8 +85,7 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta)
 	nsec = reminder;
 
 	spin_lock_irqsave(&priv->ptp_lock, flags);
-	stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj,
-			priv->plat->has_gmac4);
+	stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, xmac);
 	spin_unlock_irqrestore(&priv->ptp_lock, flags);
 
 	return 0;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
index f4b31d69f60e..ecccf895fd7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.h
@@ -21,6 +21,7 @@
 #ifndef	__STMMAC_PTP_H__
 #define	__STMMAC_PTP_H__
 
+#define PTP_XGMAC_OFFSET	0xd00
 #define	PTP_GMAC4_OFFSET	0xb00
 #define	PTP_GMAC3_X_OFFSET	0x700
 
-- 
cgit v1.2.3


From 7d9e6c5afab6bfb932acaef93111448bb876911c Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:35 +0100
Subject: net: stmmac: Integrate XGMAC into main driver flow

Now that we have all the XGMAC related callbacks, lets start integrating
this IP block into main driver.

Also, we corrected the initialization flow to only start DMA after
setting descriptors length.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 67 ++++++++++++++++-------
 1 file changed, 48 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9d104a05044d..ff1ffb46198a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -51,6 +51,7 @@
 #include <linux/reset.h>
 #include <linux/of_mdio.h>
 #include "dwmac1000.h"
+#include "dwxgmac2.h"
 #include "hwif.h"
 
 #define	STMMAC_ALIGN(x)		__ALIGN_KERNEL(x, SMP_CACHE_BYTES)
@@ -262,6 +263,21 @@ static void stmmac_clk_csr_set(struct stmmac_priv *priv)
 		else
 			priv->clk_csr = 0;
 	}
+
+	if (priv->plat->has_xgmac) {
+		if (clk_rate > 400000000)
+			priv->clk_csr = 0x5;
+		else if (clk_rate > 350000000)
+			priv->clk_csr = 0x4;
+		else if (clk_rate > 300000000)
+			priv->clk_csr = 0x3;
+		else if (clk_rate > 250000000)
+			priv->clk_csr = 0x2;
+		else if (clk_rate > 150000000)
+			priv->clk_csr = 0x1;
+		else
+			priv->clk_csr = 0x0;
+	}
 }
 
 static void print_pkt(unsigned char *buf, int len)
@@ -498,7 +514,7 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p,
 	if (!priv->hwts_rx_en)
 		return;
 	/* For GMAC4, the valid timestamp is from CTX next desc. */
-	if (priv->plat->has_gmac4)
+	if (priv->plat->has_gmac4 || priv->plat->has_xgmac)
 		desc = np;
 
 	/* Check if timestamp is available */
@@ -540,6 +556,9 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 	u32 ts_event_en = 0;
 	u32 value = 0;
 	u32 sec_inc;
+	bool xmac;
+
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (!(priv->dma_cap.time_stamp || priv->adv_ts)) {
 		netdev_alert(priv->dev, "No support for HW time stamping\n");
@@ -575,7 +594,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			/* PTP v1, UDP, any kind of event packet */
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT;
 			/* take time stamp for all event messages */
-			if (priv->plat->has_gmac4)
+			if (xmac)
 				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
 			else
 				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -610,7 +629,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
-			if (priv->plat->has_gmac4)
+			if (xmac)
 				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
 			else
 				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -647,7 +666,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 			config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
 			ptp_v2 = PTP_TCR_TSVER2ENA;
 			/* take time stamp for all event messages */
-			if (priv->plat->has_gmac4)
+			if (xmac)
 				snap_type_sel = PTP_GMAC4_TCR_SNAPTYPSEL_1;
 			else
 				snap_type_sel = PTP_TCR_SNAPTYPSEL_1;
@@ -718,7 +737,7 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
 		/* program Sub Second Increment reg */
 		stmmac_config_sub_second_increment(priv,
 				priv->ptpaddr, priv->plat->clk_ptp_rate,
-				priv->plat->has_gmac4, &sec_inc);
+				xmac, &sec_inc);
 		temp = div_u64(1000000000ULL, sec_inc);
 
 		/* Store sub second increment and flags for later use */
@@ -755,12 +774,14 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr)
  */
 static int stmmac_init_ptp(struct stmmac_priv *priv)
 {
+	bool xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
+
 	if (!(priv->dma_cap.time_stamp || priv->dma_cap.atime_stamp))
 		return -EOPNOTSUPP;
 
 	priv->adv_ts = 0;
-	/* Check if adv_ts can be enabled for dwmac 4.x core */
-	if (priv->plat->has_gmac4 && priv->dma_cap.atime_stamp)
+	/* Check if adv_ts can be enabled for dwmac 4.x / xgmac core */
+	if (xmac && priv->dma_cap.atime_stamp)
 		priv->adv_ts = 1;
 	/* Dwmac 3.x core with extend_desc can support adv_ts */
 	else if (priv->extend_desc && priv->dma_cap.atime_stamp)
@@ -2173,6 +2194,12 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 		return ret;
 	}
 
+	/* DMA Configuration */
+	stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds);
+
+	if (priv->plat->axi)
+		stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
+
 	/* DMA RX Channel Configuration */
 	for (chan = 0; chan < rx_channels_count; chan++) {
 		rx_q = &priv->rx_queue[chan];
@@ -2203,12 +2230,6 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	for (chan = 0; chan < dma_csr_ch; chan++)
 		stmmac_init_chan(priv, priv->ioaddr, priv->plat->dma_cfg, chan);
 
-	/* DMA Configuration */
-	stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, atds);
-
-	if (priv->plat->axi)
-		stmmac_axi(priv, priv->ioaddr, priv->plat->axi);
-
 	return ret;
 }
 
@@ -2526,9 +2547,6 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 		netdev_warn(priv->dev, "%s: failed debugFS registration\n",
 			    __func__);
 #endif
-	/* Start the ball rolling... */
-	stmmac_start_all_dma(priv);
-
 	priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS;
 
 	if (priv->use_riwt) {
@@ -2549,6 +2567,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp)
 			stmmac_enable_tso(priv, priv->ioaddr, 1, chan);
 	}
 
+	/* Start the ball rolling... */
+	stmmac_start_all_dma(priv);
+
 	return 0;
 }
 
@@ -3305,6 +3326,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	int coe = priv->hw->rx_csum;
 	unsigned int next_entry;
 	unsigned int count = 0;
+	bool xmac;
+
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 
 	if (netif_msg_rx_status(priv)) {
 		void *rx_head;
@@ -3406,7 +3430,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			 * in case of GMAC4 because it needs
 			 * to refill the used descriptors, always.
 			 */
-			if (unlikely(!priv->plat->has_gmac4 &&
+			if (unlikely(!xmac &&
 				     ((frame_len < priv->rx_copybreak) ||
 				     stmmac_rx_threshold_count(rx_q)))) {
 				skb = netdev_alloc_skb_ip_align(priv->dev,
@@ -3642,7 +3666,9 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 	u32 queues_count;
 	u32 queue;
+	bool xmac;
 
+	xmac = priv->plat->has_gmac4 || priv->plat->has_xgmac;
 	queues_count = (rx_cnt > tx_cnt) ? rx_cnt : tx_cnt;
 
 	if (priv->irq_wake)
@@ -3661,7 +3687,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id)
 		return IRQ_HANDLED;
 
 	/* To handle GMAC own interrupts */
-	if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) {
+	if ((priv->plat->has_gmac) || xmac) {
 		int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats);
 		int mtl_status;
 
@@ -4269,6 +4295,8 @@ int stmmac_dvr_probe(struct device *device,
 	ndev->min_mtu = ETH_ZLEN - ETH_HLEN;
 	if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00))
 		ndev->max_mtu = JUMBO_LEN;
+	else if (priv->plat->has_xgmac)
+		ndev->max_mtu = XGMAC_JUMBO_LEN;
 	else
 		ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN);
 	/* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu
@@ -4290,7 +4318,8 @@ int stmmac_dvr_probe(struct device *device,
 	 * has to be disable and this can be done by passing the
 	 * riwt_off field from the platform.
 	 */
-	if ((priv->synopsys_id >= DWMAC_CORE_3_50) && (!priv->plat->riwt_off)) {
+	if (((priv->synopsys_id >= DWMAC_CORE_3_50) ||
+	    (priv->plat->has_xgmac)) && (!priv->plat->riwt_off)) {
 		priv->use_riwt = 1;
 		dev_info(priv->device,
 			 "Enable RX Mitigation via HW Watchdog Timer\n");
-- 
cgit v1.2.3


From a3f142478a5aa155fca461cb764ace6a317a4ff1 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:36 +0100
Subject: net: stmmac: Add the bindings parsing for XGMAC2

Add the bindings parsing for XGMAC2 IP block.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c   | 2 ++
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 6 ++++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
index 3304095c934c..fad503820e04 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-generic.c
@@ -78,6 +78,8 @@ static const struct of_device_id dwmac_generic_match[] = {
 	{ .compatible = "snps,dwmac-4.00"},
 	{ .compatible = "snps,dwmac-4.10a"},
 	{ .compatible = "snps,dwmac"},
+	{ .compatible = "snps,dwxgmac-2.10"},
+	{ .compatible = "snps,dwxgmac"},
 	{ }
 };
 MODULE_DEVICE_TABLE(of, dwmac_generic_match);
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 72da77b94ecd..3609c7b696c7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -486,6 +486,12 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac)
 		plat->force_sf_dma_mode = 1;
 	}
 
+	if (of_device_is_compatible(np, "snps,dwxgmac")) {
+		plat->has_xgmac = 1;
+		plat->pmt = 1;
+		plat->tso_en = of_property_read_bool(np, "snps,tso");
+	}
+
 	dma_cfg = devm_kzalloc(&pdev->dev, sizeof(*dma_cfg),
 			       GFP_KERNEL);
 	if (!dma_cfg) {
-- 
cgit v1.2.3


From 80dfb28641b2284df846f9005233e542e5c4ec68 Mon Sep 17 00:00:00 2001
From: Jose Abreu <Jose.Abreu@synopsys.com>
Date: Wed, 8 Aug 2018 09:04:37 +0100
Subject: dt-bindings: net: stmmac: Add the bindings documentation for XGMAC2.

Adds the documentation for XGMAC2 DT bindings.

Signed-off-by: Jose Abreu <joabreu@synopsys.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Joao Pinto <jpinto@synopsys.com>
Cc: Giuseppe Cavallaro <peppe.cavallaro@st.com>
Cc: Alexandre Torgue <alexandre.torgue@st.com>
Cc: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
Cc: devicetree@vger.kernel.org
Cc: Rob Herring <robh+dt@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/devicetree/bindings/net/stmmac.txt | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/stmmac.txt b/Documentation/devicetree/bindings/net/stmmac.txt
index 3a28a5d8857d..7f1385c4643d 100644
--- a/Documentation/devicetree/bindings/net/stmmac.txt
+++ b/Documentation/devicetree/bindings/net/stmmac.txt
@@ -1,7 +1,8 @@
-* STMicroelectronics 10/100/1000 Ethernet driver (GMAC)
+* STMicroelectronics 10/100/1000/2500/10000 Ethernet (GMAC/XGMAC)
 
 Required properties:
-- compatible: Should be "snps,dwmac-<ip_version>", "snps,dwmac"
+- compatible: Should be "snps,dwmac-<ip_version>", "snps,dwmac" or
+	"snps,dwxgmac-<ip_version>", "snps,dwxgmac".
 	For backwards compatibility: "st,spear600-gmac" is also supported.
 - reg: Address and length of the register set for the device
 - interrupt-parent: Should be the phandle for the interrupt controller
-- 
cgit v1.2.3


From a29dba161ad1a01bbfbc80aa184b089ddd169a4e Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Thu, 9 Aug 2018 11:44:49 +0200
Subject: x86/relocs: Add __end_rodata_aligned to S_REL

This new symbol needs to be in the workaround-list for buggy
binutils, otherwise the build with gcc-4.6 fails.

Fixes: 39d668e04eda ('x86/mm/pti: Make pti_clone_kernel_text() compile on 32 bit')
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linux-Next Mailing List <linux-next@vger.kernel.org>
Link: https://lkml.kernel.org/r/20180809094449.ddmnrkz7qkvo3j2x@suse.de
---
 arch/x86/tools/relocs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 220e97841e49..3a6c8ebc8032 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -67,6 +67,7 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
 	"__tracedata_(start|end)|"
 	"__(start|stop)_notes|"
 	"__end_rodata|"
+	"__end_rodata_aligned|"
 	"__initramfs_start|"
 	"(jiffies|jiffies_64)|"
 #if ELF_BITS == 64
-- 
cgit v1.2.3


From 991f61fe7e1db3f74b72a3a5cbe6b012804eb0ee Mon Sep 17 00:00:00 2001
From: Liu Bo <bo.liu@linux.alibaba.com>
Date: Fri, 10 Aug 2018 01:47:02 +0800
Subject: Blk-throttle: reduce tail io latency when iops limit is enforced

When an application's iops has exceeded its cgroup's iops limit, surely it
is throttled and kernel will set a timer for dispatching, thus IO latency
includes the delay.

However, the dispatch delay which is calculated by the limit and the
elapsed jiffies is suboptimal.  As the dispatch delay is only calculated
once the application's iops is (iops limit + 1), it doesn't need to wait
any longer than the remaining time of the current slice.

The difference can be proved by the following fio job and cgroup iops
setting,
-----
$ echo 4 > /mnt/config/nullb/disk1/mbps    # limit nullb's bandwidth to 4MB/s for testing.
$ echo "253:1 riops=100 rbps=max" > /sys/fs/cgroup/unified/cg1/io.max
$ cat r2.job
[global]
name=fio-rand-read
filename=/dev/nullb1
rw=randread
bs=4k
direct=1
numjobs=1
time_based=1
runtime=60
group_reporting=1

[file1]
size=4G
ioengine=libaio
iodepth=1
rate_iops=50000
norandommap=1
thinktime=4ms
-----

wo patch:
file1: (g=0): rw=randread, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=libaio, iodepth=1
fio-3.7-66-gedfc
Starting 1 process

   read: IOPS=99, BW=400KiB/s (410kB/s)(23.4MiB/60001msec)
    slat (usec): min=10, max=336, avg=27.71, stdev=17.82
    clat (usec): min=2, max=28887, avg=5929.81, stdev=7374.29
     lat (usec): min=24, max=28901, avg=5958.73, stdev=7366.22
    clat percentiles (usec):
     |  1.00th=[    4],  5.00th=[    4], 10.00th=[    4], 20.00th=[    4],
     | 30.00th=[    4], 40.00th=[    4], 50.00th=[    6], 60.00th=[11731],
     | 70.00th=[11863], 80.00th=[11994], 90.00th=[12911], 95.00th=[22676],
     | 99.00th=[23725], 99.50th=[23987], 99.90th=[23987], 99.95th=[25035],
     | 99.99th=[28967]

w/ patch:
file1: (g=0): rw=randread, bs=(R) 4096B-4096B, (W) 4096B-4096B, (T) 4096B-4096B, ioengine=libaio, iodepth=1
fio-3.7-66-gedfc
Starting 1 process

   read: IOPS=100, BW=400KiB/s (410kB/s)(23.4MiB/60005msec)
    slat (usec): min=10, max=155, avg=23.24, stdev=16.79
    clat (usec): min=2, max=12393, avg=5961.58, stdev=5959.25
     lat (usec): min=23, max=12412, avg=5985.91, stdev=5951.92
    clat percentiles (usec):
     |  1.00th=[    3],  5.00th=[    3], 10.00th=[    4], 20.00th=[    4],
     | 30.00th=[    4], 40.00th=[    5], 50.00th=[   47], 60.00th=[11863],
     | 70.00th=[11994], 80.00th=[11994], 90.00th=[11994], 95.00th=[11994],
     | 99.00th=[11994], 99.50th=[11994], 99.90th=[12125], 99.95th=[12125],
     | 99.99th=[12387]

Signed-off-by: Liu Bo <bo.liu@linux.alibaba.com>

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-throttle.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index caaabbe8a7a5..a3eede00d302 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -922,12 +922,7 @@ static bool tg_with_in_iops_limit(struct throtl_grp *tg, struct bio *bio,
 	}
 
 	/* Calc approx time to dispatch */
-	jiffy_wait = ((tg->io_disp[rw] + 1) * HZ) / tg_iops_limit(tg, rw) + 1;
-
-	if (jiffy_wait > jiffy_elapsed)
-		jiffy_wait = jiffy_wait - jiffy_elapsed;
-	else
-		jiffy_wait = 1;
+	jiffy_wait = jiffy_elapsed_rnd - jiffy_elapsed;
 
 	if (wait)
 		*wait = jiffy_wait;
-- 
cgit v1.2.3


From cd6a2064dbf9e485b80c54687f0ce91cca91a6df Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Thu, 9 Aug 2018 11:50:46 -0700
Subject: hwmon: k10temp: Support Threadripper 2920X, 2970WX; simplify offset
 table

All announced Threadripper 29xx models have a temperature offset of
27 degrees C. Simplify temperature offset table to match all 29xx
Threadripper models with a single entry. Also simplify the table to match
all 19xx Threadripper models with a single entry. This effectively drops
entries for Threadripper 1910/1920/1950 which never saw the light of day.

Cc: Michael Larabel <Michael@phoronix.com>
Cc: Clemens Ladisch <clemens@ladisch.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/k10temp.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
index 577e2ede5a1a..bb15d7816a29 100644
--- a/drivers/hwmon/k10temp.c
+++ b/drivers/hwmon/k10temp.c
@@ -99,14 +99,8 @@ static const struct tctl_offset tctl_offset_table[] = {
 	{ 0x17, "AMD Ryzen 7 1700X", 20000 },
 	{ 0x17, "AMD Ryzen 7 1800X", 20000 },
 	{ 0x17, "AMD Ryzen 7 2700X", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1900X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 1950", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1920", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 1910", 10000 },
-	{ 0x17, "AMD Ryzen Threadripper 2950X", 27000 },
-	{ 0x17, "AMD Ryzen Threadripper 2990WX", 27000 },
+	{ 0x17, "AMD Ryzen Threadripper 19", 27000 }, /* 19{00,20,50}X */
+	{ 0x17, "AMD Ryzen Threadripper 29", 27000 }, /* 29{20,50,70,90}[W]X */
 };
 
 static void read_htcreg_pci(struct pci_dev *pdev, u32 *regval)
-- 
cgit v1.2.3


From 2d2917f7747805a1f4188672f308d82a8ba01700 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Thu, 9 Aug 2018 14:04:14 -0600
Subject: PCI: Export pcie_has_flr()

pcie_flr() suggests pcie_has_flr() to ensure that PCIe FLR support is
present prior to calling.  pcie_flr() is exported while pcie_has_flr()
is not.  Resolve this.

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 3 ++-
 include/linux/pci.h | 1 +
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index d123c2b173da..85e5b80a69a7 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4039,7 +4039,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
  * Returns true if the device advertises support for PCIe function level
  * resets.
  */
-static bool pcie_has_flr(struct pci_dev *dev)
+bool pcie_has_flr(struct pci_dev *dev)
 {
 	u32 cap;
 
@@ -4049,6 +4049,7 @@ static bool pcie_has_flr(struct pci_dev *dev)
 	pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap);
 	return cap & PCI_EXP_DEVCAP_FLR;
 }
+EXPORT_SYMBOL_GPL(pcie_has_flr);
 
 /**
  * pcie_flr - initiate a PCIe function level reset
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 307b336496f6..bace761deff2 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1090,6 +1090,7 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 			     enum pci_bus_speed *speed,
 			     enum pcie_link_width *width);
 void pcie_print_link_status(struct pci_dev *dev);
+bool pcie_has_flr(struct pci_dev *dev);
 int pcie_flr(struct pci_dev *dev);
 int __pci_reset_function_locked(struct pci_dev *dev);
 int pci_reset_function(struct pci_dev *dev);
-- 
cgit v1.2.3


From ffb0863426eb91a14101376051cfafa5527e665d Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Thu, 9 Aug 2018 15:18:33 -0500
Subject: PCI: Disable Samsung SM961/PM961 NVMe before FLR

The Samsung SM961/PM961 (960 EVO) sometimes fails to return from FLR with
the PCI config space reading back as -1.  A reproducible instance of this
behavior is resolved by clearing the enable bit in the NVMe configuration
register and waiting for the ready status to clear (disabling the NVMe
controller) prior to FLR.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=1542494
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 83 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 83 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f439de848658..e249676fbf04 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -25,6 +25,7 @@
 #include <linux/sched.h>
 #include <linux/ktime.h>
 #include <linux/mm.h>
+#include <linux/nvme.h>
 #include <linux/platform_data/x86/apple.h>
 #include <linux/pm_runtime.h>
 #include <asm/dma.h>	/* isa_dma_bridge_buggy */
@@ -3664,6 +3665,87 @@ static int reset_chelsio_generic_dev(struct pci_dev *dev, int probe)
 #define PCI_DEVICE_ID_INTEL_IVB_M_VGA      0x0156
 #define PCI_DEVICE_ID_INTEL_IVB_M2_VGA     0x0166
 
+/*
+ * The Samsung SM961/PM961 controller can sometimes enter a fatal state after
+ * FLR where config space reads from the device return -1.  We seem to be
+ * able to avoid this condition if we disable the NVMe controller prior to
+ * FLR.  This quirk is generic for any NVMe class device requiring similar
+ * assistance to quiesce the device prior to FLR.
+ *
+ * NVMe specification: https://nvmexpress.org/resources/specifications/
+ * Revision 1.0e:
+ *    Chapter 2: Required and optional PCI config registers
+ *    Chapter 3: NVMe control registers
+ *    Chapter 7.3: Reset behavior
+ */
+static int nvme_disable_and_flr(struct pci_dev *dev, int probe)
+{
+	void __iomem *bar;
+	u16 cmd;
+	u32 cfg;
+
+	if (dev->class != PCI_CLASS_STORAGE_EXPRESS ||
+	    !pcie_has_flr(dev) || !pci_resource_start(dev, 0))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	bar = pci_iomap(dev, 0, NVME_REG_CC + sizeof(cfg));
+	if (!bar)
+		return -ENOTTY;
+
+	pci_read_config_word(dev, PCI_COMMAND, &cmd);
+	pci_write_config_word(dev, PCI_COMMAND, cmd | PCI_COMMAND_MEMORY);
+
+	cfg = readl(bar + NVME_REG_CC);
+
+	/* Disable controller if enabled */
+	if (cfg & NVME_CC_ENABLE) {
+		u32 cap = readl(bar + NVME_REG_CAP);
+		unsigned long timeout;
+
+		/*
+		 * Per nvme_disable_ctrl() skip shutdown notification as it
+		 * could complete commands to the admin queue.  We only intend
+		 * to quiesce the device before reset.
+		 */
+		cfg &= ~(NVME_CC_SHN_MASK | NVME_CC_ENABLE);
+
+		writel(cfg, bar + NVME_REG_CC);
+
+		/*
+		 * Some controllers require an additional delay here, see
+		 * NVME_QUIRK_DELAY_BEFORE_CHK_RDY.  None of those are yet
+		 * supported by this quirk.
+		 */
+
+		/* Cap register provides max timeout in 500ms increments */
+		timeout = ((NVME_CAP_TIMEOUT(cap) + 1) * HZ / 2) + jiffies;
+
+		for (;;) {
+			u32 status = readl(bar + NVME_REG_CSTS);
+
+			/* Ready status becomes zero on disable complete */
+			if (!(status & NVME_CSTS_RDY))
+				break;
+
+			msleep(100);
+
+			if (time_after(jiffies, timeout)) {
+				pci_warn(dev, "Timeout waiting for NVMe ready status to clear after disable\n");
+				break;
+			}
+		}
+	}
+
+	pci_iounmap(dev, bar);
+
+	pcie_flr(dev);
+
+	return 0;
+}
+
 static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
 		 reset_intel_82599_sfp_virtfn },
@@ -3671,6 +3753,7 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 		reset_ivb_igd },
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_M2_VGA,
 		reset_ivb_igd },
+	{ PCI_VENDOR_ID_SAMSUNG, 0xa804, nvme_disable_and_flr },
 	{ PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
 		reset_chelsio_generic_dev },
 	{ 0 }
-- 
cgit v1.2.3


From 51ba09452d11b17248d80c740c2fd14c9fdc2c99 Mon Sep 17 00:00:00 2001
From: Alex Williamson <alex.williamson@redhat.com>
Date: Thu, 9 Aug 2018 14:04:31 -0600
Subject: PCI: Delay after FLR of Intel DC P3700 NVMe

Add a device-specific reset for Intel DC P3700 NVMe device which exhibits a
timeout failure in drivers waiting for the ready status to update after
NVMe enable if the driver interacts with the device too soon after FLR.  As
this has been observed in device assignment scenarios, resolve this with a
device-specific reset quirk to add an additional, heuristically determined,
delay after the FLR completes.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=1592654
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e249676fbf04..deb051583eda 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3746,6 +3746,27 @@ static int nvme_disable_and_flr(struct pci_dev *dev, int probe)
 	return 0;
 }
 
+/*
+ * Intel DC P3700 NVMe controller will timeout waiting for ready status
+ * to change after NVMe enable if the driver starts interacting with the
+ * device too soon after FLR.  A 250ms delay after FLR has heuristically
+ * proven to produce reliably working results for device assignment cases.
+ */
+static int delay_250ms_after_flr(struct pci_dev *dev, int probe)
+{
+	if (!pcie_has_flr(dev))
+		return -ENOTTY;
+
+	if (probe)
+		return 0;
+
+	pcie_flr(dev);
+
+	msleep(250);
+
+	return 0;
+}
+
 static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82599_SFP_VF,
 		 reset_intel_82599_sfp_virtfn },
@@ -3754,6 +3775,7 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IVB_M2_VGA,
 		reset_ivb_igd },
 	{ PCI_VENDOR_ID_SAMSUNG, 0xa804, nvme_disable_and_flr },
+	{ PCI_VENDOR_ID_INTEL, 0x0953, delay_250ms_after_flr },
 	{ PCI_VENDOR_ID_CHELSIO, PCI_ANY_ID,
 		reset_chelsio_generic_dev },
 	{ 0 }
-- 
cgit v1.2.3


From 61884de08f8368b9aa289ab8dc953e0ce4c755b1 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 9 Aug 2018 14:22:41 -0600
Subject: null_blk: add lock drop/acquire annotation

sparse complains:

drivers/block/null_blk_main.c:816:24: sparse: context imbalance in 'null_insert_page' - unexpected unlock

Fix it by adding the necessary annotations to the function.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/block/null_blk_main.c b/drivers/block/null_blk_main.c
index 86cafa6d3b41..6127e3ff7b4b 100644
--- a/drivers/block/null_blk_main.c
+++ b/drivers/block/null_blk_main.c
@@ -804,7 +804,9 @@ static struct nullb_page *null_lookup_page(struct nullb *nullb,
 }
 
 static struct nullb_page *null_insert_page(struct nullb *nullb,
-	sector_t sector, bool ignore_cache)
+					   sector_t sector, bool ignore_cache)
+	__releases(&nullb->lock)
+	__acquires(&nullb->lock)
 {
 	u64 idx;
 	struct nullb_page *t_page;
-- 
cgit v1.2.3


From 73657a3e5b0de69ccdabed0e340dcbbc99f46119 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 9 Aug 2018 14:47:58 +0200
Subject: s390/qeth: extract helper for MPC protocol type

Just a little code deduplication.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 +-
 drivers/s390/net/qeth_core_main.c | 35 +++++++++++++----------------------
 drivers/s390/net/qeth_l2_main.c   |  2 +-
 3 files changed, 15 insertions(+), 24 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 605ec4706773..24e4f31a0f36 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -998,7 +998,7 @@ void qeth_tx_timeout(struct net_device *);
 void qeth_prepare_control_data(struct qeth_card *, int,
 				struct qeth_cmd_buffer *);
 void qeth_release_buffer(struct qeth_channel *, struct qeth_cmd_buffer *);
-void qeth_prepare_ipa_cmd(struct qeth_card *, struct qeth_cmd_buffer *, char);
+void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob);
 struct qeth_cmd_buffer *qeth_wait_for_buffer(struct qeth_channel *);
 int qeth_query_switch_attributes(struct qeth_card *card,
 				  struct qeth_switch_info *sw_info);
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index d09a7110b381..da9ac2129869 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -2367,12 +2367,19 @@ static int qeth_ulp_enable_cb(struct qeth_card *card, struct qeth_reply *reply,
 	return 0;
 }
 
+static u8 qeth_mpc_select_prot_type(struct qeth_card *card)
+{
+	if (IS_OSN(card))
+		return QETH_PROT_OSN2;
+	return (card->options.layer2 == 1) ? QETH_PROT_LAYER2 : QETH_PROT_TCPIP;
+}
+
 static int qeth_ulp_enable(struct qeth_card *card)
 {
-	int rc;
-	char prot_type;
+	u8 prot_type = qeth_mpc_select_prot_type(card);
 	struct qeth_cmd_buffer *iob;
 	u16 max_mtu;
+	int rc;
 
 	/*FIXME: trace view callbacks*/
 	QETH_DBF_TEXT(SETUP, 2, "ulpenabl");
@@ -2381,14 +2388,6 @@ static int qeth_ulp_enable(struct qeth_card *card)
 	memcpy(iob->data, ULP_ENABLE, ULP_ENABLE_SIZE);
 
 	*(QETH_ULP_ENABLE_LINKNUM(iob->data)) = (u8) card->dev->dev_port;
-	if (card->options.layer2)
-		if (card->info.type == QETH_CARD_TYPE_OSN)
-			prot_type = QETH_PROT_OSN2;
-		else
-			prot_type = QETH_PROT_LAYER2;
-	else
-		prot_type = QETH_PROT_TCPIP;
-
 	memcpy(QETH_ULP_ENABLE_PROT_TYPE(iob->data), &prot_type, 1);
 	memcpy(QETH_ULP_ENABLE_DEST_ADDR(iob->data),
 	       &card->token.cm_connection_r, QETH_MPC_TOKEN_LENGTH);
@@ -2939,9 +2938,10 @@ struct qeth_cmd_buffer *qeth_get_ipacmd_buffer(struct qeth_card *card,
 }
 EXPORT_SYMBOL_GPL(qeth_get_ipacmd_buffer);
 
-void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
-		char prot_type)
+void qeth_prepare_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob)
 {
+	u8 prot_type = qeth_mpc_select_prot_type(card);
+
 	memcpy(iob->data, IPA_PDU_HEADER, IPA_PDU_HEADER_SIZE);
 	memcpy(QETH_IPA_CMD_PROT_TYPE(iob->data), &prot_type, 1);
 	memcpy(QETH_IPA_CMD_DEST_ADDR(iob->data),
@@ -2961,18 +2961,9 @@ int qeth_send_ipa_cmd(struct qeth_card *card, struct qeth_cmd_buffer *iob,
 		void *reply_param)
 {
 	int rc;
-	char prot_type;
 
 	QETH_CARD_TEXT(card, 4, "sendipa");
-
-	if (card->options.layer2)
-		if (card->info.type == QETH_CARD_TYPE_OSN)
-			prot_type = QETH_PROT_OSN2;
-		else
-			prot_type = QETH_PROT_LAYER2;
-	else
-		prot_type = QETH_PROT_TCPIP;
-	qeth_prepare_ipa_cmd(card, iob, prot_type);
+	qeth_prepare_ipa_cmd(card, iob);
 	rc = qeth_send_control_data(card, IPA_CMD_LENGTH,
 						iob, reply_cb, reply_param);
 	if (rc == -ETIME) {
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index c1829a4b955d..efb84a75dd80 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1270,7 +1270,7 @@ static int qeth_osn_send_ipa_cmd(struct qeth_card *card,
 
 	QETH_CARD_TEXT(card, 4, "osndipa");
 
-	qeth_prepare_ipa_cmd(card, iob, QETH_PROT_OSN2);
+	qeth_prepare_ipa_cmd(card, iob);
 	s1 = (u16)(IPA_PDU_HEADER_SIZE + data_len);
 	s2 = (u16)data_len;
 	memcpy(QETH_IPA_PDU_LEN_TOTAL(iob->data), &s1, 2);
-- 
cgit v1.2.3


From 750b162598ec5b65cdb44d18f050b45cb7f8d31b Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 9 Aug 2018 14:47:59 +0200
Subject: s390/qeth: reduce hard-coded access to ccw channels

Where possible use accessor macros and local pointers to access the ccw
channels. This makes it less likely to miss a spot.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 46 ++++++++++++++++++++-------------------
 drivers/s390/net/qeth_l2_main.c   | 13 ++++++-----
 2 files changed, 31 insertions(+), 28 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index da9ac2129869..e459894e1926 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -534,13 +534,14 @@ static inline int qeth_is_cq(struct qeth_card *card, unsigned int queue)
 
 static int __qeth_issue_next_read(struct qeth_card *card)
 {
-	int rc;
+	struct qeth_channel *channel = &card->read;
 	struct qeth_cmd_buffer *iob;
+	int rc;
 
 	QETH_CARD_TEXT(card, 5, "issnxrd");
-	if (card->read.state != CH_STATE_UP)
+	if (channel->state != CH_STATE_UP)
 		return -EIO;
-	iob = qeth_get_buffer(&card->read);
+	iob = qeth_get_buffer(channel);
 	if (!iob) {
 		dev_warn(&card->gdev->dev, "The qeth device driver "
 			"failed to recover an error on the device\n");
@@ -548,14 +549,14 @@ static int __qeth_issue_next_read(struct qeth_card *card)
 			"available\n", dev_name(&card->gdev->dev));
 		return -ENOMEM;
 	}
-	qeth_setup_ccw(&card->read, iob->data, QETH_BUFSIZE);
+	qeth_setup_ccw(channel, iob->data, QETH_BUFSIZE);
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
-	rc = ccw_device_start(card->read.ccwdev, &card->read.ccw,
+	rc = ccw_device_start(channel->ccwdev, &channel->ccw,
 			      (addr_t) iob, 0, 0);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "%s error in starting next read ccw! "
 			"rc=%i\n", dev_name(&card->gdev->dev), rc);
-		atomic_set(&card->read.irq_pending, 0);
+		atomic_set(&channel->irq_pending, 0);
 		card->read_or_write_problem = 1;
 		qeth_schedule_recovery(card);
 		wake_up(&card->wait_q);
@@ -1987,20 +1988,20 @@ static void qeth_idx_write_cb(struct qeth_channel *channel,
 
 	if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) {
 		if (QETH_IDX_ACT_CAUSE_CODE(iob->data) == QETH_IDX_ACT_ERR_EXCL)
-			dev_err(&card->write.ccwdev->dev,
+			dev_err(&channel->ccwdev->dev,
 				"The adapter is used exclusively by another "
 				"host\n");
 		else
 			QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel:"
 				" negative reply\n",
-				dev_name(&card->write.ccwdev->dev));
+				dev_name(&channel->ccwdev->dev));
 		goto out;
 	}
 	memcpy(&temp, QETH_IDX_ACT_FUNC_LEVEL(iob->data), 2);
 	if ((temp & ~0x0100) != qeth_peer_func_level(card->info.func_level)) {
 		QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on write channel: "
 			"function level mismatch (sent: 0x%x, received: "
-			"0x%x)\n", dev_name(&card->write.ccwdev->dev),
+			"0x%x)\n", dev_name(&channel->ccwdev->dev),
 			card->info.func_level, temp);
 		goto out;
 	}
@@ -2028,20 +2029,20 @@ static void qeth_idx_read_cb(struct qeth_channel *channel,
 	if (!(QETH_IS_IDX_ACT_POS_REPLY(iob->data))) {
 		switch (QETH_IDX_ACT_CAUSE_CODE(iob->data)) {
 		case QETH_IDX_ACT_ERR_EXCL:
-			dev_err(&card->write.ccwdev->dev,
+			dev_err(&channel->ccwdev->dev,
 				"The adapter is used exclusively by another "
 				"host\n");
 			break;
 		case QETH_IDX_ACT_ERR_AUTH:
 		case QETH_IDX_ACT_ERR_AUTH_USER:
-			dev_err(&card->read.ccwdev->dev,
+			dev_err(&channel->ccwdev->dev,
 				"Setting the device online failed because of "
 				"insufficient authorization\n");
 			break;
 		default:
 			QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel:"
 				" negative reply\n",
-				dev_name(&card->read.ccwdev->dev));
+				dev_name(&channel->ccwdev->dev));
 		}
 		QETH_CARD_TEXT_(card, 2, "idxread%c",
 			QETH_IDX_ACT_CAUSE_CODE(iob->data));
@@ -2052,7 +2053,7 @@ static void qeth_idx_read_cb(struct qeth_channel *channel,
 	if (temp != qeth_peer_func_level(card->info.func_level)) {
 		QETH_DBF_MESSAGE(2, "%s IDX_ACTIVATE on read channel: function "
 			"level mismatch (sent: 0x%x, received: 0x%x)\n",
-			dev_name(&card->read.ccwdev->dev),
+			dev_name(&channel->ccwdev->dev),
 			card->info.func_level, temp);
 		goto out;
 	}
@@ -2069,7 +2070,7 @@ out:
 void qeth_prepare_control_data(struct qeth_card *card, int len,
 		struct qeth_cmd_buffer *iob)
 {
-	qeth_setup_ccw(&card->write, iob->data, len);
+	qeth_setup_ccw(iob->channel, iob->data, len);
 	iob->callback = qeth_release_buffer;
 
 	memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
@@ -2116,6 +2117,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 				unsigned long cb_cmd),
 		void *reply_param)
 {
+	struct qeth_channel *channel = iob->channel;
 	int rc;
 	unsigned long flags;
 	struct qeth_reply *reply = NULL;
@@ -2125,7 +2127,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	QETH_CARD_TEXT(card, 2, "sendctl");
 
 	if (card->read_or_write_problem) {
-		qeth_release_buffer(iob->channel, iob);
+		qeth_release_buffer(channel, iob);
 		return -EIO;
 	}
 	reply = qeth_alloc_reply(card);
@@ -2137,7 +2139,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 
 	init_waitqueue_head(&reply->wait_q);
 
-	while (atomic_cmpxchg(&card->write.irq_pending, 0, 1)) ;
+	while (atomic_cmpxchg(&channel->irq_pending, 0, 1)) ;
 
 	if (IS_IPA(iob->data)) {
 		cmd = __ipa_cmd(iob);
@@ -2157,21 +2159,21 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 	timeout = jiffies + event_timeout;
 
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
-	spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
-	rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
+	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
 				      (addr_t) iob, 0, 0, event_timeout);
-	spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "%s qeth_send_control_data: "
 			"ccw_device_start rc = %i\n",
-			dev_name(&card->write.ccwdev->dev), rc);
+			dev_name(&channel->ccwdev->dev), rc);
 		QETH_CARD_TEXT_(card, 2, " err%d", rc);
 		spin_lock_irqsave(&card->lock, flags);
 		list_del_init(&reply->list);
 		qeth_put_reply(reply);
 		spin_unlock_irqrestore(&card->lock, flags);
-		qeth_release_buffer(iob->channel, iob);
-		atomic_set(&card->write.irq_pending, 0);
+		qeth_release_buffer(channel, iob);
+		atomic_set(&channel->irq_pending, 0);
 		wake_up(&card->wait_q);
 		return rc;
 	}
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index efb84a75dd80..a86ba45ade05 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1239,25 +1239,26 @@ EXPORT_SYMBOL_GPL(qeth_l2_discipline);
 static int qeth_osn_send_control_data(struct qeth_card *card, int len,
 			   struct qeth_cmd_buffer *iob)
 {
+	struct qeth_channel *channel = iob->channel;
 	unsigned long flags;
 	int rc = 0;
 
 	QETH_CARD_TEXT(card, 5, "osndctrd");
 
 	wait_event(card->wait_q,
-		   atomic_cmpxchg(&card->write.irq_pending, 0, 1) == 0);
+		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	qeth_prepare_control_data(card, len, iob);
 	QETH_CARD_TEXT(card, 6, "osnoirqp");
-	spin_lock_irqsave(get_ccwdev_lock(card->write.ccwdev), flags);
-	rc = ccw_device_start_timeout(CARD_WDEV(card), &card->write.ccw,
+	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
+	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
 				      (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT);
-	spin_unlock_irqrestore(get_ccwdev_lock(card->write.ccwdev), flags);
+	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "qeth_osn_send_control_data: "
 			   "ccw_device_start rc = %i\n", rc);
 		QETH_CARD_TEXT_(card, 2, " err%d", rc);
-		qeth_release_buffer(iob->channel, iob);
-		atomic_set(&card->write.irq_pending, 0);
+		qeth_release_buffer(channel, iob);
+		atomic_set(&channel->irq_pending, 0);
 		wake_up(&card->wait_q);
 	}
 	return rc;
-- 
cgit v1.2.3


From 45ca2fd64682cd1ea14b480fbb4b38b601ac123b Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 9 Aug 2018 14:48:00 +0200
Subject: s390/qeth: use qeth_setup_ccw() to set up all CCWs

Re-work the helper a little bit, so that it can be used for all CCWs
that qeth issues.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 ++
 drivers/s390/net/qeth_core_main.c | 42 +++++++++++++--------------------------
 drivers/s390/net/qeth_core_mpc.c  | 11 ----------
 drivers/s390/net/qeth_core_mpc.h  |  4 ----
 4 files changed, 16 insertions(+), 43 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 24e4f31a0f36..9a700a618b3d 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -235,6 +235,8 @@ static inline int qeth_is_ipa_enabled(struct qeth_ipa_info *ipa,
 #define QETH_IDX_FUNC_LEVEL_IQD		 0x4108
 
 #define QETH_BUFSIZE		4096
+#define CCW_CMD_WRITE		0x01
+#define CCW_CMD_READ		0x02
 
 /**
  * some more defs
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index e459894e1926..714c71e30b7f 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -65,7 +65,6 @@ static struct mutex qeth_mod_mutex;
 static void qeth_send_control_data_cb(struct qeth_channel *,
 			struct qeth_cmd_buffer *);
 static struct qeth_cmd_buffer *qeth_get_buffer(struct qeth_channel *);
-static void qeth_setup_ccw(struct qeth_channel *, unsigned char *, __u32);
 static void qeth_free_buffer_pool(struct qeth_card *);
 static int qeth_qdio_establish(struct qeth_card *);
 static void qeth_free_qdio_buffers(struct qeth_card *);
@@ -532,6 +531,14 @@ static inline int qeth_is_cq(struct qeth_card *card, unsigned int queue)
 	    queue == card->qdio.no_in_queues - 1;
 }
 
+static void qeth_setup_ccw(struct ccw1 *ccw, u8 cmd_code, u32 len, void *data)
+{
+	ccw->cmd_code = cmd_code;
+	ccw->flags = CCW_FLAG_SLI;
+	ccw->count = len;
+	ccw->cda = (__u32) __pa(data);
+}
+
 static int __qeth_issue_next_read(struct qeth_card *card)
 {
 	struct qeth_channel *channel = &card->read;
@@ -549,7 +556,7 @@ static int __qeth_issue_next_read(struct qeth_card *card)
 			"available\n", dev_name(&card->gdev->dev));
 		return -ENOMEM;
 	}
-	qeth_setup_ccw(channel, iob->data, QETH_BUFSIZE);
+	qeth_setup_ccw(&channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
 	rc = ccw_device_start(channel->ccwdev, &channel->ccw,
 			      (addr_t) iob, 0, 0);
@@ -745,21 +752,6 @@ static struct qeth_card *CARD_FROM_CDEV(struct ccw_device *cdev)
 	return card;
 }
 
-static void qeth_setup_ccw(struct qeth_channel *channel, unsigned char *iob,
-		__u32 len)
-{
-	struct qeth_card *card;
-
-	card = CARD_FROM_CDEV(channel->ccwdev);
-	QETH_CARD_TEXT(card, 4, "setupccw");
-	if (channel == &card->read)
-		memcpy(&channel->ccw, READ_CCW, sizeof(struct ccw1));
-	else
-		memcpy(&channel->ccw, WRITE_CCW, sizeof(struct ccw1));
-	channel->ccw.count = len;
-	channel->ccw.cda = (__u32) __pa(iob);
-}
-
 static struct qeth_cmd_buffer *__qeth_get_buffer(struct qeth_channel *channel)
 {
 	__u8 index;
@@ -1680,10 +1672,7 @@ static int qeth_read_conf_data(struct qeth_card *card, void **buffer,
 	if (!rcd_buf)
 		return -ENOMEM;
 
-	channel->ccw.cmd_code = ciw->cmd;
-	channel->ccw.cda = (__u32) __pa(rcd_buf);
-	channel->ccw.count = ciw->count;
-	channel->ccw.flags = CCW_FLAG_SLI;
+	qeth_setup_ccw(&channel->ccw, ciw->cmd, ciw->count, rcd_buf);
 	channel->state = CH_STATE_RCD;
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
 	ret = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
@@ -1857,9 +1846,7 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel,
 	if (!iob)
 		return -ENOMEM;
 	iob->callback = idx_reply_cb;
-	memcpy(&channel->ccw, READ_CCW, sizeof(struct ccw1));
-	channel->ccw.count = QETH_BUFSIZE;
-	channel->ccw.cda = (__u32) __pa(iob->data);
+	qeth_setup_ccw(&channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
 
 	wait_event(card->wait_q,
 		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
@@ -1908,9 +1895,8 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 	if (!iob)
 		return -ENOMEM;
 	iob->callback = idx_reply_cb;
-	memcpy(&channel->ccw, WRITE_CCW, sizeof(struct ccw1));
-	channel->ccw.count = IDX_ACTIVATE_SIZE;
-	channel->ccw.cda = (__u32) __pa(iob->data);
+	qeth_setup_ccw(&channel->ccw, CCW_CMD_WRITE, IDX_ACTIVATE_SIZE,
+		       iob->data);
 	if (channel == &card->write) {
 		memcpy(iob->data, IDX_ACTIVATE_WRITE, IDX_ACTIVATE_SIZE);
 		memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
@@ -2070,7 +2056,7 @@ out:
 void qeth_prepare_control_data(struct qeth_card *card, int len,
 		struct qeth_cmd_buffer *iob)
 {
-	qeth_setup_ccw(iob->channel, iob->data, len);
+	qeth_setup_ccw(&iob->channel->ccw, CCW_CMD_WRITE, len, iob->data);
 	iob->callback = qeth_release_buffer;
 
 	memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
diff --git a/drivers/s390/net/qeth_core_mpc.c b/drivers/s390/net/qeth_core_mpc.c
index 22428b769f9b..5bcb8dafc3ee 100644
--- a/drivers/s390/net/qeth_core_mpc.c
+++ b/drivers/s390/net/qeth_core_mpc.c
@@ -146,17 +146,6 @@ unsigned char IPA_PDU_HEADER[] = {
 };
 EXPORT_SYMBOL_GPL(IPA_PDU_HEADER);
 
-unsigned char WRITE_CCW[] = {
-	0x01, CCW_FLAG_SLI, 0, 0,
-	0, 0, 0, 0
-};
-
-unsigned char READ_CCW[] = {
-	0x02, CCW_FLAG_SLI, 0, 0,
-	0, 0, 0, 0
-};
-
-
 struct ipa_rc_msg {
 	enum qeth_ipa_return_codes rc;
 	char *msg;
diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h
index cf5ad94e960a..aa8b9196b089 100644
--- a/drivers/s390/net/qeth_core_mpc.h
+++ b/drivers/s390/net/qeth_core_mpc.h
@@ -818,10 +818,6 @@ extern char *qeth_get_ipa_cmd_name(enum qeth_ipa_cmds cmd);
 /* END OF   IP Assist related definitions                                    */
 /*****************************************************************************/
 
-
-extern unsigned char WRITE_CCW[];
-extern unsigned char READ_CCW[];
-
 extern unsigned char CM_ENABLE[];
 #define CM_ENABLE_SIZE 0x63
 #define QETH_CM_ENABLE_ISSUER_RM_TOKEN(buffer) (buffer + 0x2c)
-- 
cgit v1.2.3


From 24142fd8d87d763bfc401cb0c496bb1050fea0b8 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 9 Aug 2018 14:48:01 +0200
Subject: s390/qeth: do basic setup for data channel

The data channel currently doesn't need a setup operation, because we
don't use pre-allocated cmd buffers for its IO. But subsequent changes
will introduce further setup that also applies to the data channel.
This refactors things a bit, so that the new stuff can then be
automatically applied to all channels.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 714c71e30b7f..eab8c4a182b0 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -899,11 +899,19 @@ out:
 	qeth_release_buffer(channel, iob);
 }
 
-static int qeth_setup_channel(struct qeth_channel *channel)
+static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers)
 {
 	int cnt;
 
 	QETH_DBF_TEXT(SETUP, 2, "setupch");
+
+	channel->state = CH_STATE_DOWN;
+	atomic_set(&channel->irq_pending, 0);
+	init_waitqueue_head(&channel->wait_q);
+
+	if (!alloc_buffers)
+		return 0;
+
 	for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++) {
 		channel->iob[cnt].data =
 			kzalloc(QETH_BUFSIZE, GFP_DMA|GFP_KERNEL);
@@ -920,10 +928,8 @@ static int qeth_setup_channel(struct qeth_channel *channel)
 		return -ENOMEM;
 	}
 	channel->io_buf_no = 0;
-	atomic_set(&channel->irq_pending, 0);
 	spin_lock_init(&channel->iob_lock);
 
-	init_waitqueue_head(&channel->wait_q);
 	return 0;
 }
 
@@ -1448,13 +1454,9 @@ static void qeth_start_kernel_thread(struct work_struct *work)
 static void qeth_buffer_reclaim_work(struct work_struct *);
 static int qeth_setup_card(struct qeth_card *card)
 {
-
 	QETH_DBF_TEXT(SETUP, 2, "setupcrd");
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
 
-	card->read.state  = CH_STATE_DOWN;
-	card->write.state = CH_STATE_DOWN;
-	card->data.state  = CH_STATE_DOWN;
 	card->state = CARD_STATE_DOWN;
 	card->lan_online = 0;
 	card->read_or_write_problem = 0;
@@ -1504,15 +1506,19 @@ static struct qeth_card *qeth_alloc_card(void)
 	if (!card)
 		goto out;
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
-	if (qeth_setup_channel(&card->read))
+	if (qeth_setup_channel(&card->read, true))
 		goto out_ip;
-	if (qeth_setup_channel(&card->write))
+	if (qeth_setup_channel(&card->write, true))
 		goto out_channel;
+	if (qeth_setup_channel(&card->data, false))
+		goto out_data;
 	card->options.layer2 = -1;
 	card->qeth_service_level.seq_print = qeth_core_sl_print;
 	register_service_level(&card->qeth_service_level);
 	return card;
 
+out_data:
+	qeth_clean_channel(&card->write);
 out_channel:
 	qeth_clean_channel(&card->read);
 out_ip:
-- 
cgit v1.2.3


From 95f4d8b75ad3fb774113450c9788af0dde91a27d Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 9 Aug 2018 14:48:02 +0200
Subject: s390/qeth: clean up card initialization

The qeth_card struct is kzalloc-ed, so remove all the redundant
0-initializations. While at it, split up what's left of
qeth_determine_card_type().

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core_main.c | 44 +++++++++------------------------------
 1 file changed, 10 insertions(+), 34 deletions(-)

diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index eab8c4a182b0..99ba0f067eea 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -1392,6 +1392,10 @@ static void qeth_init_qdio_info(struct qeth_card *card)
 {
 	QETH_DBF_TEXT(SETUP, 4, "intqdinf");
 	atomic_set(&card->qdio.state, QETH_QDIO_UNINITIALIZED);
+	card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT;
+	card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
+	card->qdio.no_out_queues = QETH_MAX_QUEUES;
+
 	/* inbound */
 	card->qdio.no_in_queues = 1;
 	card->qdio.in_buf_size = QETH_IN_BUF_SIZE_DEFAULT;
@@ -1404,12 +1408,10 @@ static void qeth_init_qdio_info(struct qeth_card *card)
 	INIT_LIST_HEAD(&card->qdio.init_pool.entry_list);
 }
 
-static void qeth_set_intial_options(struct qeth_card *card)
+static void qeth_set_initial_options(struct qeth_card *card)
 {
 	card->options.route4.type = NO_ROUTER;
 	card->options.route6.type = NO_ROUTER;
-	card->options.fake_broadcast = 0;
-	card->options.performance_stats = 0;
 	card->options.rx_sg_cb = QETH_RX_SG_CB;
 	card->options.isolation = ISOLATION_MODE_NONE;
 	card->options.cq = QETH_CQ_DISABLED;
@@ -1452,15 +1454,13 @@ static void qeth_start_kernel_thread(struct work_struct *work)
 }
 
 static void qeth_buffer_reclaim_work(struct work_struct *);
-static int qeth_setup_card(struct qeth_card *card)
+static void qeth_setup_card(struct qeth_card *card)
 {
 	QETH_DBF_TEXT(SETUP, 2, "setupcrd");
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
 
+	card->info.type = CARD_RDEV(card)->id.driver_info;
 	card->state = CARD_STATE_DOWN;
-	card->lan_online = 0;
-	card->read_or_write_problem = 0;
-	card->dev = NULL;
 	spin_lock_init(&card->mclock);
 	spin_lock_init(&card->lock);
 	spin_lock_init(&card->ip_lock);
@@ -1468,24 +1468,15 @@ static int qeth_setup_card(struct qeth_card *card)
 	mutex_init(&card->conf_mutex);
 	mutex_init(&card->discipline_mutex);
 	mutex_init(&card->vid_list_mutex);
-	card->thread_start_mask = 0;
-	card->thread_allowed_mask = 0;
-	card->thread_running_mask = 0;
 	INIT_WORK(&card->kernel_thread_starter, qeth_start_kernel_thread);
 	INIT_LIST_HEAD(&card->cmd_waiter_list);
 	init_waitqueue_head(&card->wait_q);
-	/* initial options */
-	qeth_set_intial_options(card);
+	qeth_set_initial_options(card);
 	/* IP address takeover */
 	INIT_LIST_HEAD(&card->ipato.entries);
-	card->ipato.enabled = false;
-	card->ipato.invert4 = false;
-	card->ipato.invert6 = false;
-	/* init QDIO stuff */
 	qeth_init_qdio_info(card);
 	INIT_DELAYED_WORK(&card->buffer_reclaim_work, qeth_buffer_reclaim_work);
 	INIT_WORK(&card->close_dev_work, qeth_close_dev_handler);
-	return 0;
 }
 
 static void qeth_core_sl_print(struct seq_file *m, struct service_level *slr)
@@ -1527,17 +1518,6 @@ out:
 	return NULL;
 }
 
-static void qeth_determine_card_type(struct qeth_card *card)
-{
-	QETH_DBF_TEXT(SETUP, 2, "detcdtyp");
-
-	card->qdio.do_prio_queueing = QETH_PRIOQ_DEFAULT;
-	card->qdio.default_out_queue = QETH_DEFAULT_QUEUE;
-	card->info.type = CARD_RDEV(card)->id.driver_info;
-	card->qdio.no_out_queues = QETH_MAX_QUEUES;
-	qeth_update_from_chp_desc(card);
-}
-
 static int qeth_clear_channel(struct qeth_channel *channel)
 {
 	unsigned long flags;
@@ -5779,12 +5759,8 @@ static int qeth_core_probe_device(struct ccwgroup_device *gdev)
 	gdev->cdev[1]->handler = qeth_irq;
 	gdev->cdev[2]->handler = qeth_irq;
 
-	qeth_determine_card_type(card);
-	rc = qeth_setup_card(card);
-	if (rc) {
-		QETH_DBF_TEXT_(SETUP, 2, "2err%d", rc);
-		goto err_card;
-	}
+	qeth_setup_card(card);
+	qeth_update_from_chp_desc(card);
 
 	card->dev = qeth_alloc_netdev(card);
 	if (!card->dev)
-- 
cgit v1.2.3


From f15cdaf237e9acc2ee14663ba53b872a27ee7015 Mon Sep 17 00:00:00 2001
From: Julian Wiedmann <jwi@linux.ibm.com>
Date: Thu, 9 Aug 2018 14:48:03 +0200
Subject: s390/qeth: don't restrict qeth_card to DMA memory

Allocating the main qeth_card struct with GFP_DMA blocks us from moving
it into netdev_priv(). But the only reason why we need DMA memory is the
ccw1 structs embedded into each ccw channel. So extract those into
separate allocations, like we already do for the cmd buffers.

Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_core.h      |  2 +-
 drivers/s390/net/qeth_core_main.c | 29 +++++++++++++++++------------
 drivers/s390/net/qeth_l2_main.c   |  2 +-
 3 files changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 9a700a618b3d..34e0d476c5c6 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -594,7 +594,7 @@ static inline struct qeth_ipa_cmd *__ipa_cmd(struct qeth_cmd_buffer *iob)
  */
 struct qeth_channel {
 	enum qeth_channel_states state;
-	struct ccw1 ccw;
+	struct ccw1 *ccw;
 	spinlock_t iob_lock;
 	wait_queue_head_t wait_q;
 	struct ccw_device *ccwdev;
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 99ba0f067eea..49f64eb3eab0 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -556,9 +556,9 @@ static int __qeth_issue_next_read(struct qeth_card *card)
 			"available\n", dev_name(&card->gdev->dev));
 		return -ENOMEM;
 	}
-	qeth_setup_ccw(&channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
+	qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
-	rc = ccw_device_start(channel->ccwdev, &channel->ccw,
+	rc = ccw_device_start(channel->ccwdev, channel->ccw,
 			      (addr_t) iob, 0, 0);
 	if (rc) {
 		QETH_DBF_MESSAGE(2, "%s error in starting next read ccw! "
@@ -905,6 +905,9 @@ static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers)
 
 	QETH_DBF_TEXT(SETUP, 2, "setupch");
 
+	channel->ccw = kmalloc(sizeof(struct ccw1), GFP_KERNEL | GFP_DMA);
+	if (!channel->ccw)
+		return -ENOMEM;
 	channel->state = CH_STATE_DOWN;
 	atomic_set(&channel->irq_pending, 0);
 	init_waitqueue_head(&channel->wait_q);
@@ -923,6 +926,7 @@ static int qeth_setup_channel(struct qeth_channel *channel, bool alloc_buffers)
 		channel->iob[cnt].rc = 0;
 	}
 	if (cnt < QETH_CMD_BUFFER_NO) {
+		kfree(channel->ccw);
 		while (cnt-- > 0)
 			kfree(channel->iob[cnt].data);
 		return -ENOMEM;
@@ -1336,6 +1340,7 @@ static void qeth_clean_channel(struct qeth_channel *channel)
 	QETH_DBF_TEXT(SETUP, 2, "freech");
 	for (cnt = 0; cnt < QETH_CMD_BUFFER_NO; cnt++)
 		kfree(channel->iob[cnt].data);
+	kfree(channel->ccw);
 }
 
 static void qeth_set_single_write_queues(struct qeth_card *card)
@@ -1493,7 +1498,7 @@ static struct qeth_card *qeth_alloc_card(void)
 	struct qeth_card *card;
 
 	QETH_DBF_TEXT(SETUP, 2, "alloccrd");
-	card = kzalloc(sizeof(struct qeth_card), GFP_DMA|GFP_KERNEL);
+	card = kzalloc(sizeof(*card), GFP_KERNEL);
 	if (!card)
 		goto out;
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
@@ -1658,10 +1663,10 @@ static int qeth_read_conf_data(struct qeth_card *card, void **buffer,
 	if (!rcd_buf)
 		return -ENOMEM;
 
-	qeth_setup_ccw(&channel->ccw, ciw->cmd, ciw->count, rcd_buf);
+	qeth_setup_ccw(channel->ccw, ciw->cmd, ciw->count, rcd_buf);
 	channel->state = CH_STATE_RCD;
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	ret = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	ret = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				       QETH_RCD_PARM, LPM_ANYPATH, 0,
 				       QETH_RCD_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
@@ -1832,13 +1837,13 @@ static int qeth_idx_activate_get_answer(struct qeth_channel *channel,
 	if (!iob)
 		return -ENOMEM;
 	iob->callback = idx_reply_cb;
-	qeth_setup_ccw(&channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
+	qeth_setup_ccw(channel->ccw, CCW_CMD_READ, QETH_BUFSIZE, iob->data);
 
 	wait_event(card->wait_q,
 		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, QETH_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 
@@ -1881,7 +1886,7 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 	if (!iob)
 		return -ENOMEM;
 	iob->callback = idx_reply_cb;
-	qeth_setup_ccw(&channel->ccw, CCW_CMD_WRITE, IDX_ACTIVATE_SIZE,
+	qeth_setup_ccw(channel->ccw, CCW_CMD_WRITE, IDX_ACTIVATE_SIZE,
 		       iob->data);
 	if (channel == &card->write) {
 		memcpy(iob->data, IDX_ACTIVATE_WRITE, IDX_ACTIVATE_SIZE);
@@ -1908,7 +1913,7 @@ static int qeth_idx_activate_channel(struct qeth_channel *channel,
 		   atomic_cmpxchg(&channel->irq_pending, 0, 1) == 0);
 	QETH_DBF_TEXT(SETUP, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, QETH_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 
@@ -2042,7 +2047,7 @@ out:
 void qeth_prepare_control_data(struct qeth_card *card, int len,
 		struct qeth_cmd_buffer *iob)
 {
-	qeth_setup_ccw(&iob->channel->ccw, CCW_CMD_WRITE, len, iob->data);
+	qeth_setup_ccw(iob->channel->ccw, CCW_CMD_WRITE, len, iob->data);
 	iob->callback = qeth_release_buffer;
 
 	memcpy(QETH_TRANSPORT_HEADER_SEQ_NO(iob->data),
@@ -2132,7 +2137,7 @@ int qeth_send_control_data(struct qeth_card *card, int len,
 
 	QETH_CARD_TEXT(card, 6, "noirqpnd");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, event_timeout);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 	if (rc) {
@@ -5031,11 +5036,11 @@ out_free_nothing:
 
 static void qeth_core_free_card(struct qeth_card *card)
 {
-
 	QETH_DBF_TEXT(SETUP, 2, "freecrd");
 	QETH_DBF_HEX(SETUP, 2, &card, sizeof(void *));
 	qeth_clean_channel(&card->read);
 	qeth_clean_channel(&card->write);
+	qeth_clean_channel(&card->data);
 	qeth_free_qdio_buffers(card);
 	unregister_service_level(&card->qeth_service_level);
 	kfree(card);
diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c
index a86ba45ade05..710fa74892ae 100644
--- a/drivers/s390/net/qeth_l2_main.c
+++ b/drivers/s390/net/qeth_l2_main.c
@@ -1250,7 +1250,7 @@ static int qeth_osn_send_control_data(struct qeth_card *card, int len,
 	qeth_prepare_control_data(card, len, iob);
 	QETH_CARD_TEXT(card, 6, "osnoirqp");
 	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start_timeout(channel->ccwdev, &channel->ccw,
+	rc = ccw_device_start_timeout(channel->ccwdev, channel->ccw,
 				      (addr_t) iob, 0, 0, QETH_IPA_TIMEOUT);
 	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
 	if (rc) {
-- 
cgit v1.2.3


From 1a363b0d3bdc7ee369d1f46f2ed7538b1d9481c7 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 9 Aug 2018 14:48:04 +0200
Subject: s390/qeth: use true and false for boolean values

Return statements in functions returning bool should use true or false
instead of an integer value.

This issue was detected with the help of Coccinelle.

Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/s390/net/qeth_l3_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c
index 1833e7505aca..7175086677fb 100644
--- a/drivers/s390/net/qeth_l3_main.c
+++ b/drivers/s390/net/qeth_l3_main.c
@@ -117,9 +117,9 @@ static bool qeth_l3_is_addr_covered_by_ipato(struct qeth_card *card,
 	int rc = 0;
 
 	if (!card->ipato.enabled)
-		return 0;
+		return false;
 	if (addr->type != QETH_IP_TYPE_NORMAL)
-		return 0;
+		return false;
 
 	qeth_l3_convert_addr_to_bits((u8 *) &addr->u, addr_bits,
 				  (addr->proto == QETH_PROT_IPV4)? 4:16);
-- 
cgit v1.2.3


From 5e7baf0fcb2a3aef7329f3c7543d4695a46bd321 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@cavium.com>
Date: Thu, 9 Aug 2018 11:13:49 -0700
Subject: qed/qede: Multi CoS support.

This patch adds support for tc mqprio offload,
using this different traffic classes on the adapter
can be utilized based on configured priority to tc map.

For example -

tc qdisc add dev eth0 root mqprio num_tc 4 map 0 1 2 3

This will cause SKBs with priority 0,1,2,3 to transmit
over tc 0,1,2,3 hardware queues respectively.

Signed-off-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qed/qed_l2.c        |   9 +-
 drivers/net/ethernet/qlogic/qed/qed_main.c      |   5 +-
 drivers/net/ethernet/qlogic/qede/qede.h         |  13 +++
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c |  48 ++++++--
 drivers/net/ethernet/qlogic/qede/qede_fp.c      |  29 +++--
 drivers/net/ethernet/qlogic/qede/qede_main.c    | 139 +++++++++++++++++++-----
 include/linux/qed/qed_eth_if.h                  |   6 +
 7 files changed, 200 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c
index 5ede6408649d..82a1bd1f8a8c 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_l2.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c
@@ -2188,16 +2188,17 @@ out:
 static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 				 struct qed_dev_eth_info *info)
 {
+	struct qed_hwfn *p_hwfn = QED_LEADING_HWFN(cdev);
 	int i;
 
 	memset(info, 0, sizeof(*info));
 
-	info->num_tc = 1;
-
 	if (IS_PF(cdev)) {
 		int max_vf_vlan_filters = 0;
 		int max_vf_mac_filters = 0;
 
+		info->num_tc = p_hwfn->hw_info.num_hw_tc;
+
 		if (cdev->int_params.out.int_mode == QED_INT_MODE_MSIX) {
 			u16 num_queues = 0;
 
@@ -2248,6 +2249,8 @@ static int qed_fill_eth_dev_info(struct qed_dev *cdev,
 	} else {
 		u16 total_cids = 0;
 
+		info->num_tc = 1;
+
 		/* Determine queues &  XDP support */
 		for_each_hwfn(cdev, i) {
 			struct qed_hwfn *p_hwfn = &cdev->hwfns[i];
@@ -2554,7 +2557,7 @@ static int qed_start_txq(struct qed_dev *cdev,
 
 	rc = qed_eth_tx_queue_start(p_hwfn,
 				    p_hwfn->hw_info.opaque_fid,
-				    p_params, 0,
+				    p_params, p_params->tc,
 				    pbl_addr, pbl_size, ret_params);
 
 	if (rc) {
diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index dbe81310c0b6..2094d86a7a08 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -948,13 +948,14 @@ static void qed_update_pf_params(struct qed_dev *cdev,
 		params->eth_pf_params.num_arfs_filters = 0;
 
 	/* In case we might support RDMA, don't allow qede to be greedy
-	 * with the L2 contexts. Allow for 64 queues [rx, tx, xdp] per hwfn.
+	 * with the L2 contexts. Allow for 64 queues [rx, tx cos, xdp]
+	 * per hwfn.
 	 */
 	if (QED_IS_RDMA_PERSONALITY(QED_LEADING_HWFN(cdev))) {
 		u16 *num_cons;
 
 		num_cons = &params->eth_pf_params.num_cons;
-		*num_cons = min_t(u16, *num_cons, 192);
+		*num_cons = min_t(u16, *num_cons, QED_MAX_L2_CONS);
 	}
 
 	for (i = 0; i < cdev->num_hwfns; i++) {
diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index d7ed0d3dbf71..e90c60a8fb01 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -386,6 +386,15 @@ struct qede_tx_queue {
 #define QEDE_TXQ_XDP_TO_IDX(edev, txq)	((txq)->index - \
 					 QEDE_MAX_TSS_CNT(edev))
 #define QEDE_TXQ_IDX_TO_XDP(edev, idx)	((idx) + QEDE_MAX_TSS_CNT(edev))
+#define QEDE_NDEV_TXQ_ID_TO_FP_ID(edev, idx)	((edev)->fp_num_rx + \
+						 ((idx) % QEDE_TSS_COUNT(edev)))
+#define QEDE_NDEV_TXQ_ID_TO_TXQ_COS(edev, idx)	((idx) / QEDE_TSS_COUNT(edev))
+#define QEDE_TXQ_TO_NDEV_TXQ_ID(edev, txq)	((QEDE_TSS_COUNT(edev) * \
+						 (txq)->cos) + (txq)->index)
+#define QEDE_NDEV_TXQ_ID_TO_TXQ(edev, idx)	\
+	(&((edev)->fp_array[QEDE_NDEV_TXQ_ID_TO_FP_ID(edev, idx)].txq \
+	[QEDE_NDEV_TXQ_ID_TO_TXQ_COS(edev, idx)]))
+#define QEDE_FP_TC0_TXQ(fp)	(&((fp)->txq[0]))
 
 	/* Regular Tx requires skb + metadata for release purpose,
 	 * while XDP requires the pages and the mapped address.
@@ -399,6 +408,8 @@ struct qede_tx_queue {
 
 	/* Slowpath; Should be kept in end [unless missing padding] */
 	void *handle;
+	u16 cos;
+	u16 ndev_txq_id;
 };
 
 #define BD_UNMAP_ADDR(bd)		HILO_U64(le32_to_cpu((bd)->addr.hi), \
@@ -541,5 +552,7 @@ void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
 #define QEDE_RX_HDR_SIZE		256
 #define QEDE_MAX_JUMBO_PACKET_SIZE	9600
 #define	for_each_queue(i) for (i = 0; i < edev->num_queues; i++)
+#define for_each_cos_in_txq(edev, var) \
+	for ((var) = 0; (var) < (edev)->dev_info.num_tc; (var)++)
 
 #endif /* _QEDE_H_ */
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index b37857f3f950..2bd84d6d9b15 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -222,7 +222,7 @@ static void qede_get_strings_stats_txq(struct qede_dev *edev,
 				QEDE_TXQ_XDP_TO_IDX(edev, txq),
 				qede_tqstats_arr[i].string);
 		else
-			sprintf(*buf, "%d: %s", txq->index,
+			sprintf(*buf, "%d_%d: %s", txq->index, txq->cos,
 				qede_tqstats_arr[i].string);
 		*buf += ETH_GSTRING_LEN;
 	}
@@ -262,8 +262,13 @@ static void qede_get_strings_stats(struct qede_dev *edev, u8 *buf)
 		if (fp->type & QEDE_FASTPATH_XDP)
 			qede_get_strings_stats_txq(edev, fp->xdp_tx, &buf);
 
-		if (fp->type & QEDE_FASTPATH_TX)
-			qede_get_strings_stats_txq(edev, fp->txq, &buf);
+		if (fp->type & QEDE_FASTPATH_TX) {
+			int cos;
+
+			for_each_cos_in_txq(edev, cos)
+				qede_get_strings_stats_txq(edev,
+							   &fp->txq[cos], &buf);
+		}
 	}
 
 	/* Account for non-queue statistics */
@@ -338,8 +343,12 @@ static void qede_get_ethtool_stats(struct net_device *dev,
 		if (fp->type & QEDE_FASTPATH_XDP)
 			qede_get_ethtool_stats_txq(fp->xdp_tx, &buf);
 
-		if (fp->type & QEDE_FASTPATH_TX)
-			qede_get_ethtool_stats_txq(fp->txq, &buf);
+		if (fp->type & QEDE_FASTPATH_TX) {
+			int cos;
+
+			for_each_cos_in_txq(edev, cos)
+				qede_get_ethtool_stats_txq(&fp->txq[cos], &buf);
+		}
 	}
 
 	for (i = 0; i < QEDE_NUM_STATS; i++) {
@@ -366,7 +375,8 @@ static int qede_get_sset_count(struct net_device *dev, int stringset)
 				num_stats--;
 
 		/* Account for the Regular Tx statistics */
-		num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS;
+		num_stats += QEDE_TSS_COUNT(edev) * QEDE_NUM_TQSTATS *
+				edev->dev_info.num_tc;
 
 		/* Account for the Regular Rx statistics */
 		num_stats += QEDE_RSS_COUNT(edev) * QEDE_NUM_RQSTATS;
@@ -741,9 +751,17 @@ static int qede_get_coalesce(struct net_device *dev,
 		}
 
 		for_each_queue(i) {
+			struct qede_tx_queue *txq;
+
 			fp = &edev->fp_array[i];
+
+			/* All TX queues of given fastpath uses same
+			 * coalescing value, so no need to iterate over
+			 * all TCs, TC0 txq should suffice.
+			 */
 			if (fp->type & QEDE_FASTPATH_TX) {
-				tx_handle = fp->txq->handle;
+				txq = QEDE_FP_TC0_TXQ(fp);
+				tx_handle = txq->handle;
 				break;
 			}
 		}
@@ -801,9 +819,17 @@ static int qede_set_coalesce(struct net_device *dev,
 		}
 
 		if (edev->fp_array[i].type & QEDE_FASTPATH_TX) {
+			struct qede_tx_queue *txq;
+
+			/* All TX queues of given fastpath uses same
+			 * coalescing value, so no need to iterate over
+			 * all TCs, TC0 txq should suffice.
+			 */
+			txq = QEDE_FP_TC0_TXQ(fp);
+
 			rc = edev->ops->common->set_coalesce(edev->cdev,
 							     0, txc,
-							     fp->txq->handle);
+							     txq->handle);
 			if (rc) {
 				DP_INFO(edev,
 					"Set TX coalesce error, rc = %d\n", rc);
@@ -1385,8 +1411,10 @@ static int qede_selftest_transmit_traffic(struct qede_dev *edev,
 	u16 val;
 
 	for_each_queue(i) {
-		if (edev->fp_array[i].type & QEDE_FASTPATH_TX) {
-			txq = edev->fp_array[i].txq;
+		struct qede_fastpath *fp = &edev->fp_array[i];
+
+		if (fp->type & QEDE_FASTPATH_TX) {
+			txq = QEDE_FP_TC0_TXQ(fp);
 			break;
 		}
 	}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_fp.c b/drivers/net/ethernet/qlogic/qede/qede_fp.c
index 8c9e95ba9917..1a78027de071 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_fp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_fp.c
@@ -408,12 +408,12 @@ static void qede_xdp_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq)
 
 static int qede_tx_int(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
+	unsigned int pkts_compl = 0, bytes_compl = 0;
 	struct netdev_queue *netdev_txq;
 	u16 hw_bd_cons;
-	unsigned int pkts_compl = 0, bytes_compl = 0;
 	int rc;
 
-	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->index);
+	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id);
 
 	hw_bd_cons = le16_to_cpu(*txq->hw_cons_ptr);
 	barrier();
@@ -1365,9 +1365,14 @@ static bool qede_poll_is_more_work(struct qede_fastpath *fp)
 		if (qede_txq_has_work(fp->xdp_tx))
 			return true;
 
-	if (likely(fp->type & QEDE_FASTPATH_TX))
-		if (qede_txq_has_work(fp->txq))
-			return true;
+	if (likely(fp->type & QEDE_FASTPATH_TX)) {
+		int cos;
+
+		for_each_cos_in_txq(fp->edev, cos) {
+			if (qede_txq_has_work(&fp->txq[cos]))
+				return true;
+		}
+	}
 
 	return false;
 }
@@ -1382,8 +1387,14 @@ int qede_poll(struct napi_struct *napi, int budget)
 	struct qede_dev *edev = fp->edev;
 	int rx_work_done = 0;
 
-	if (likely(fp->type & QEDE_FASTPATH_TX) && qede_txq_has_work(fp->txq))
-		qede_tx_int(edev, fp->txq);
+	if (likely(fp->type & QEDE_FASTPATH_TX)) {
+		int cos;
+
+		for_each_cos_in_txq(fp->edev, cos) {
+			if (qede_txq_has_work(&fp->txq[cos]))
+				qede_tx_int(edev, &fp->txq[cos]);
+		}
+	}
 
 	if ((fp->type & QEDE_FASTPATH_XDP) && qede_txq_has_work(fp->xdp_tx))
 		qede_xdp_tx_int(edev, fp->xdp_tx);
@@ -1444,8 +1455,8 @@ netdev_tx_t qede_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 
 	/* Get tx-queue context and netdev index */
 	txq_index = skb_get_queue_mapping(skb);
-	WARN_ON(txq_index >= QEDE_TSS_COUNT(edev));
-	txq = edev->fp_array[edev->fp_num_rx + txq_index].txq;
+	WARN_ON(txq_index >= QEDE_TSS_COUNT(edev) * edev->dev_info.num_tc);
+	txq = QEDE_NDEV_TXQ_ID_TO_TXQ(edev, txq_index);
 	netdev_txq = netdev_get_tx_queue(ndev, txq_index);
 
 	WARN_ON(qed_chain_get_elem_left(&txq->tx_pbl) < (MAX_SKB_FRAGS + 1));
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 6a796040a32c..d7299afa902c 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -536,6 +536,43 @@ static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return 0;
 }
 
+int qede_setup_tc(struct net_device *ndev, u8 num_tc)
+{
+	struct qede_dev *edev = netdev_priv(ndev);
+	int cos, count, offset;
+
+	if (num_tc > edev->dev_info.num_tc)
+		return -EINVAL;
+
+	netdev_reset_tc(ndev);
+	netdev_set_num_tc(ndev, num_tc);
+
+	for_each_cos_in_txq(edev, cos) {
+		count = QEDE_TSS_COUNT(edev);
+		offset = cos * QEDE_TSS_COUNT(edev);
+		netdev_set_tc_queue(ndev, cos, count, offset);
+	}
+
+	return 0;
+}
+
+static int
+qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
+		      void *type_data)
+{
+	struct tc_mqprio_qopt *mqprio;
+
+	switch (type) {
+	case TC_SETUP_QDISC_MQPRIO:
+		mqprio = type_data;
+
+		mqprio->hw = TC_MQPRIO_HW_OFFLOAD_TCS;
+		return qede_setup_tc(dev, mqprio->num_tc);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static const struct net_device_ops qede_netdev_ops = {
 	.ndo_open = qede_open,
 	.ndo_stop = qede_close,
@@ -568,6 +605,7 @@ static const struct net_device_ops qede_netdev_ops = {
 #ifdef CONFIG_RFS_ACCEL
 	.ndo_rx_flow_steer = qede_rx_flow_steer,
 #endif
+	.ndo_setup_tc = qede_setup_tc_offload,
 };
 
 static const struct net_device_ops qede_netdev_vf_ops = {
@@ -621,7 +659,8 @@ static struct qede_dev *qede_alloc_etherdev(struct qed_dev *cdev,
 	struct qede_dev *edev;
 
 	ndev = alloc_etherdev_mqs(sizeof(*edev),
-				  info->num_queues, info->num_queues);
+				  info->num_queues * info->num_tc,
+				  info->num_queues);
 	if (!ndev) {
 		pr_err("etherdev allocation failed\n");
 		return NULL;
@@ -830,7 +869,8 @@ static int qede_alloc_fp_array(struct qede_dev *edev)
 		}
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			fp->txq = kzalloc(sizeof(*fp->txq), GFP_KERNEL);
+			fp->txq = kcalloc(edev->dev_info.num_tc,
+					  sizeof(*fp->txq), GFP_KERNEL);
 			if (!fp->txq)
 				goto err;
 		}
@@ -879,10 +919,15 @@ static void qede_sp_task(struct work_struct *work)
 static void qede_update_pf_params(struct qed_dev *cdev)
 {
 	struct qed_pf_params pf_params;
+	u16 num_cons;
 
 	/* 64 rx + 64 tx + 64 XDP */
 	memset(&pf_params, 0, sizeof(struct qed_pf_params));
-	pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * 3;
+
+	/* 1 rx + 1 xdp + max tx cos */
+	num_cons = QED_MIN_L2_CONS;
+
+	pf_params.eth_pf_params.num_cons = (MAX_SB_PER_PF_MIMD - 1) * num_cons;
 
 	/* Same for VFs - make sure they'll have sufficient connections
 	 * to support XDP Tx queues.
@@ -1363,8 +1408,12 @@ static void qede_free_mem_fp(struct qede_dev *edev, struct qede_fastpath *fp)
 	if (fp->type & QEDE_FASTPATH_XDP)
 		qede_free_mem_txq(edev, fp->xdp_tx);
 
-	if (fp->type & QEDE_FASTPATH_TX)
-		qede_free_mem_txq(edev, fp->txq);
+	if (fp->type & QEDE_FASTPATH_TX) {
+		int cos;
+
+		for_each_cos_in_txq(edev, cos)
+			qede_free_mem_txq(edev, &fp->txq[cos]);
+	}
 }
 
 /* This function allocates all memory needed for a single fp (i.e. an entity
@@ -1391,9 +1440,13 @@ static int qede_alloc_mem_fp(struct qede_dev *edev, struct qede_fastpath *fp)
 	}
 
 	if (fp->type & QEDE_FASTPATH_TX) {
-		rc = qede_alloc_mem_txq(edev, fp->txq);
-		if (rc)
-			goto out;
+		int cos;
+
+		for_each_cos_in_txq(edev, cos) {
+			rc = qede_alloc_mem_txq(edev, &fp->txq[cos]);
+			if (rc)
+				goto out;
+		}
 	}
 
 out:
@@ -1466,10 +1519,23 @@ static void qede_init_fp(struct qede_dev *edev)
 		}
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			fp->txq->index = txq_index++;
-			if (edev->dev_info.is_legacy)
-				fp->txq->is_legacy = 1;
-			fp->txq->dev = &edev->pdev->dev;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				struct qede_tx_queue *txq = &fp->txq[cos];
+				u16 ndev_tx_id;
+
+				txq->cos = cos;
+				txq->index = txq_index;
+				ndev_tx_id = QEDE_TXQ_TO_NDEV_TXQ_ID(edev, txq);
+				txq->ndev_txq_id = ndev_tx_id;
+
+				if (edev->dev_info.is_legacy)
+					txq->is_legacy = 1;
+				txq->dev = &edev->pdev->dev;
+			}
+
+			txq_index++;
 		}
 
 		snprintf(fp->name, sizeof(fp->name), "%s-fp-%d",
@@ -1483,7 +1549,9 @@ static int qede_set_real_num_queues(struct qede_dev *edev)
 {
 	int rc = 0;
 
-	rc = netif_set_real_num_tx_queues(edev->ndev, QEDE_TSS_COUNT(edev));
+	rc = netif_set_real_num_tx_queues(edev->ndev,
+					  QEDE_TSS_COUNT(edev) *
+					  edev->dev_info.num_tc);
 	if (rc) {
 		DP_NOTICE(edev, "Failed to set real number of Tx queues\n");
 		return rc;
@@ -1685,9 +1753,13 @@ static int qede_stop_queues(struct qede_dev *edev)
 		fp = &edev->fp_array[i];
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			rc = qede_drain_txq(edev, fp->txq, true);
-			if (rc)
-				return rc;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				rc = qede_drain_txq(edev, &fp->txq[cos], true);
+				if (rc)
+					return rc;
+			}
 		}
 
 		if (fp->type & QEDE_FASTPATH_XDP) {
@@ -1703,9 +1775,13 @@ static int qede_stop_queues(struct qede_dev *edev)
 
 		/* Stop the Tx Queue(s) */
 		if (fp->type & QEDE_FASTPATH_TX) {
-			rc = qede_stop_txq(edev, fp->txq, i);
-			if (rc)
-				return rc;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				rc = qede_stop_txq(edev, &fp->txq[cos], i);
+				if (rc)
+					return rc;
+			}
 		}
 
 		/* Stop the Rx Queue */
@@ -1758,6 +1834,7 @@ static int qede_start_txq(struct qede_dev *edev,
 
 	params.p_sb = fp->sb_info;
 	params.sb_idx = sb_idx;
+	params.tc = txq->cos;
 
 	rc = edev->ops->q_tx_start(edev->cdev, rss_id, &params, phys_table,
 				   page_cnt, &ret_params);
@@ -1877,9 +1954,14 @@ static int qede_start_queues(struct qede_dev *edev, bool clear_stats)
 		}
 
 		if (fp->type & QEDE_FASTPATH_TX) {
-			rc = qede_start_txq(edev, fp, fp->txq, i, TX_PI(0));
-			if (rc)
-				goto out;
+			int cos;
+
+			for_each_cos_in_txq(edev, cos) {
+				rc = qede_start_txq(edev, fp, &fp->txq[cos], i,
+						    TX_PI(cos));
+				if (rc)
+					goto out;
+			}
 		}
 	}
 
@@ -1973,6 +2055,7 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 		     bool is_locked)
 {
 	struct qed_link_params link_params;
+	u8 num_tc;
 	int rc;
 
 	DP_INFO(edev, "Starting qede load\n");
@@ -2019,6 +2102,10 @@ static int qede_load(struct qede_dev *edev, enum qede_load_mode mode,
 		goto err4;
 	DP_INFO(edev, "Start VPORT, RXQ and TXQ succeeded\n");
 
+	num_tc = netdev_get_num_tc(edev->ndev);
+	num_tc = num_tc ? num_tc : edev->dev_info.num_tc;
+	qede_setup_tc(edev->ndev, num_tc);
+
 	/* Program un-configured VLANs */
 	qede_configure_vlan_filters(edev);
 
@@ -2143,7 +2230,7 @@ static bool qede_is_txq_full(struct qede_dev *edev, struct qede_tx_queue *txq)
 {
 	struct netdev_queue *netdev_txq;
 
-	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->index);
+	netdev_txq = netdev_get_tx_queue(edev->ndev, txq->ndev_txq_id);
 	if (netif_xmit_stopped(netdev_txq))
 		return true;
 
@@ -2208,9 +2295,11 @@ static void qede_get_eth_tlv_data(void *dev, void *data)
 	for_each_queue(i) {
 		fp = &edev->fp_array[i];
 		if (fp->type & QEDE_FASTPATH_TX) {
-			if (fp->txq->sw_tx_cons != fp->txq->sw_tx_prod)
+			struct qede_tx_queue *txq = QEDE_FP_TC0_TXQ(fp);
+
+			if (txq->sw_tx_cons != txq->sw_tx_prod)
 				etlv->txqs_empty = false;
-			if (qede_is_txq_full(edev, fp->txq))
+			if (qede_is_txq_full(edev, txq))
 				etlv->num_txqs_full++;
 		}
 		if (fp->type & QEDE_FASTPATH_RX) {
diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h
index 2978fa4add42..a1310482c4ed 100644
--- a/include/linux/qed/qed_eth_if.h
+++ b/include/linux/qed/qed_eth_if.h
@@ -39,6 +39,10 @@
 #include <linux/qed/qed_if.h>
 #include <linux/qed/qed_iov_if.h>
 
+/* 64 max queues * (1 rx + 4 tx-cos + 1 xdp) */
+#define QED_MIN_L2_CONS (2 + NUM_PHYS_TCS_4PORT_K2)
+#define QED_MAX_L2_CONS (64 * (QED_MIN_L2_CONS))
+
 struct qed_queue_start_common_params {
 	/* Should always be relative to entity sending this. */
 	u8 vport_id;
@@ -49,6 +53,8 @@ struct qed_queue_start_common_params {
 
 	struct qed_sb_info *p_sb;
 	u8 sb_idx;
+
+	u8 tc;
 };
 
 struct qed_rxq_start_ret_params {
-- 
cgit v1.2.3


From 91a56adbf178fa840069d000fb9d902f30e52456 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@cavium.com>
Date: Thu, 9 Aug 2018 11:13:50 -0700
Subject: qede: Add destination ip based flow profile.

This patch adds support for dropping and redirecting
the flows based on destination IP in the packet.

This also moves the profile mode settings in their own
functions which can be used through tc flows in successive
patch.

For example -

ethtool -N p5p1 flow-type tcp4 dst-ip 192.168.40.100 action -1
ethtool -N p5p1 flow-type udp4 dst-ip 192.168.50.100 action 1
ethtool -N p5p1 flow-type tcp4 dst-ip 192.168.60.100 action 0x100000000

Signed-off-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_filter.c | 114 ++++++++++++++-----------
 1 file changed, 66 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index f9a327c821eb..d0902573f38a 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -1599,6 +1599,69 @@ static int qede_flow_spec_validate_unused(struct qede_dev *edev,
 	return 0;
 }
 
+static int qede_set_v4_tuple_to_profile(struct qede_dev *edev,
+					struct qede_arfs_tuple *t)
+{
+	/* We must have Only 4-tuples/l4 port/src ip/dst ip
+	 * as an input.
+	 */
+	if (t->src_port && t->dst_port && t->src_ipv4 && t->dst_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
+	} else if (!t->src_port && t->dst_port &&
+		   !t->src_ipv4 && !t->dst_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
+	} else if (!t->src_port && !t->dst_port &&
+		   !t->dst_ipv4 && t->src_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
+	} else if (!t->src_port && !t->dst_port &&
+		   t->dst_ipv4 && !t->src_ipv4) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_DEST;
+	} else {
+		DP_INFO(edev, "Invalid N-tuple\n");
+		return -EOPNOTSUPP;
+	}
+
+	t->ip_comp = qede_flow_spec_ipv4_cmp;
+	t->build_hdr = qede_flow_build_ipv4_hdr;
+	t->stringify = qede_flow_stringify_ipv4_hdr;
+
+	return 0;
+}
+
+static int qede_set_v6_tuple_to_profile(struct qede_dev *edev,
+					struct qede_arfs_tuple *t,
+					struct in6_addr *zaddr)
+{
+	/* We must have Only 4-tuples/l4 port/src ip/dst ip
+	 * as an input.
+	 */
+	if (t->src_port && t->dst_port &&
+	    memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr)) &&
+	    memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
+	} else if (!t->src_port && t->dst_port &&
+		   !memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr)) &&
+		   !memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
+	} else if (!t->src_port && !t->dst_port &&
+		   !memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr)) &&
+		   memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
+	} else if (!t->src_port && !t->dst_port &&
+		   memcmp(&t->dst_ipv6, zaddr, sizeof(struct in6_addr)) &&
+		   !memcmp(&t->src_ipv6, zaddr, sizeof(struct in6_addr))) {
+		t->mode = QED_FILTER_CONFIG_MODE_IP_DEST;
+	} else {
+		DP_INFO(edev, "Invalid N-tuple\n");
+		return -EOPNOTSUPP;
+	}
+
+	t->ip_comp = qede_flow_spec_ipv6_cmp;
+	t->build_hdr = qede_flow_build_ipv6_hdr;
+
+	return 0;
+}
+
 static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev,
 					       struct qede_arfs_tuple *t,
 					       struct ethtool_rx_flow_spec *fs)
@@ -1638,27 +1701,7 @@ static int qede_flow_spec_to_tuple_ipv4_common(struct qede_dev *edev,
 	t->src_port = fs->h_u.tcp_ip4_spec.psrc;
 	t->dst_port = fs->h_u.tcp_ip4_spec.pdst;
 
-	/* We must either have a valid 4-tuple or only dst port
-	 * or only src ip as an input
-	 */
-	if (t->src_port && t->dst_port && t->src_ipv4 && t->dst_ipv4) {
-		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
-	} else if (!t->src_port && t->dst_port &&
-		   !t->src_ipv4 && !t->dst_ipv4) {
-		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
-	}  else if (!t->src_port && !t->dst_port &&
-		    !t->dst_ipv4 && t->src_ipv4) {
-		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
-	} else {
-		DP_INFO(edev, "Invalid N-tuple\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->ip_comp = qede_flow_spec_ipv4_cmp;
-	t->build_hdr = qede_flow_build_ipv4_hdr;
-	t->stringify = qede_flow_stringify_ipv4_hdr;
-
-	return 0;
+	return qede_set_v4_tuple_to_profile(edev, t);
 }
 
 static int qede_flow_spec_to_tuple_tcpv4(struct qede_dev *edev,
@@ -1690,10 +1733,8 @@ static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev,
 					       struct ethtool_rx_flow_spec *fs)
 {
 	struct in6_addr zero_addr;
-	void *p;
 
-	p = &zero_addr;
-	memset(p, 0, sizeof(zero_addr));
+	memset(&zero_addr, 0, sizeof(zero_addr));
 
 	if ((fs->h_u.tcp_ip6_spec.psrc &
 	     fs->m_u.tcp_ip6_spec.psrc) != fs->h_u.tcp_ip6_spec.psrc) {
@@ -1720,30 +1761,7 @@ static int qede_flow_spec_to_tuple_ipv6_common(struct qede_dev *edev,
 	t->src_port = fs->h_u.tcp_ip6_spec.psrc;
 	t->dst_port = fs->h_u.tcp_ip6_spec.pdst;
 
-	/* We must make sure we have a valid 4-tuple or only dest port
-	 * or only src ip as an input
-	 */
-	if (t->src_port && t->dst_port &&
-	    memcmp(&t->src_ipv6, p, sizeof(struct in6_addr)) &&
-	    memcmp(&t->dst_ipv6, p, sizeof(struct in6_addr))) {
-		t->mode = QED_FILTER_CONFIG_MODE_5_TUPLE;
-	} else if (!t->src_port && t->dst_port &&
-		   !memcmp(&t->src_ipv6, p, sizeof(struct in6_addr)) &&
-		   !memcmp(&t->dst_ipv6, p, sizeof(struct in6_addr))) {
-		t->mode = QED_FILTER_CONFIG_MODE_L4_PORT;
-	} else if (!t->src_port && !t->dst_port &&
-		   !memcmp(&t->dst_ipv6, p, sizeof(struct in6_addr)) &&
-		   memcmp(&t->src_ipv6, p, sizeof(struct in6_addr))) {
-		t->mode = QED_FILTER_CONFIG_MODE_IP_SRC;
-	} else {
-		DP_INFO(edev, "Invalid N-tuple\n");
-		return -EOPNOTSUPP;
-	}
-
-	t->ip_comp = qede_flow_spec_ipv6_cmp;
-	t->build_hdr = qede_flow_build_ipv6_hdr;
-
-	return 0;
+	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
 }
 
 static int qede_flow_spec_to_tuple_tcpv6(struct qede_dev *edev,
-- 
cgit v1.2.3


From 2ce9c93eaca6c67e3fa8828a471738a32cd66770 Mon Sep 17 00:00:00 2001
From: Manish Chopra <manish.chopra@cavium.com>
Date: Thu, 9 Aug 2018 11:13:51 -0700
Subject: qede: Ingress tc flower offload (drop action) support.

The main motive of this patch is to lay down driver's
tc offload infrastructure in place.

With these changes tc can offload various supported flow
profiles (4 tuples, src-ip, dst-ip, l4 port) for the drop
action. Dropped flows statistic is a global counter for
all the offloaded flows for drop action and is populated
in ethtool statistics as common "gft_filter_drop".

Examples -

tc qdisc add dev p4p1 ingress
tc filter add dev p4p1 protocol ipv4 parent ffff: flower \
	skip_sw ip_proto tcp dst_ip 192.168.40.200 action drop
tc filter add dev p4p1 protocol ipv4 parent ffff: flower \
	skip_sw ip_proto udp src_ip 192.168.40.100 action drop
tc filter add dev p4p1 protocol ipv4 parent ffff: flower \
	skip_sw ip_proto tcp src_ip 192.168.40.100 dst_ip 192.168.40.200 \
	src_port 453 dst_port 876 action drop
tc filter add dev p4p1 protocol ipv4 parent ffff: flower \
	skip_sw ip_proto tcp dst_port 98 action drop

Signed-off-by: Manish Chopra <manish.chopra@cavium.com>
Signed-off-by: Ariel Elior <ariel.elior@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede.h         |   7 +-
 drivers/net/ethernet/qlogic/qede/qede_ethtool.c |   2 +-
 drivers/net/ethernet/qlogic/qede/qede_filter.c  | 308 +++++++++++++++++++++++-
 drivers/net/ethernet/qlogic/qede/qede_main.c    |  56 ++++-
 4 files changed, 362 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h
index e90c60a8fb01..6a4d266fb8e2 100644
--- a/drivers/net/ethernet/qlogic/qede/qede.h
+++ b/drivers/net/ethernet/qlogic/qede/qede.h
@@ -52,6 +52,9 @@
 #include <linux/qed/qed_chain.h>
 #include <linux/qed/qed_eth_if.h>
 
+#include <net/pkt_cls.h>
+#include <net/tc_act/tc_gact.h>
+
 #define QEDE_MAJOR_VERSION		8
 #define QEDE_MINOR_VERSION		33
 #define QEDE_REVISION_VERSION		0
@@ -469,7 +472,7 @@ void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc);
 void qede_free_arfs(struct qede_dev *edev);
 int qede_alloc_arfs(struct qede_dev *edev);
 int qede_add_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info);
-int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info);
+int qede_delete_flow_filter(struct qede_dev *edev, u64 cookie);
 int qede_get_cls_rule_entry(struct qede_dev *edev, struct ethtool_rxnfc *cmd);
 int qede_get_cls_rule_all(struct qede_dev *edev, struct ethtool_rxnfc *info,
 			  u32 *rule_locs);
@@ -535,6 +538,8 @@ bool qede_has_rx_work(struct qede_rx_queue *rxq);
 int qede_txq_has_work(struct qede_tx_queue *txq);
 void qede_recycle_rx_bd_ring(struct qede_rx_queue *rxq, u8 count);
 void qede_update_rx_prod(struct qede_dev *edev, struct qede_rx_queue *rxq);
+int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
+			    struct tc_cls_flower_offload *f);
 
 #define RX_RING_SIZE_POW	13
 #define RX_RING_SIZE		((u16)BIT(RX_RING_SIZE_POW))
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
index 2bd84d6d9b15..19652cd27ca7 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c
@@ -1285,7 +1285,7 @@ static int qede_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info)
 		rc = qede_add_cls_rule(edev, info);
 		break;
 	case ETHTOOL_SRXCLSRLDEL:
-		rc = qede_del_cls_rule(edev, info);
+		rc = qede_delete_flow_filter(edev, info->fs.location);
 		break;
 	default:
 		DP_INFO(edev, "Command parameters not supported\n");
diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c
index d0902573f38a..9673d19308e6 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_filter.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c
@@ -83,7 +83,7 @@ struct qede_arfs_fltr_node {
 	struct qede_arfs_tuple tuple;
 
 	u32 flow_id;
-	u16 sw_id;
+	u64 sw_id;
 	u16 rxq_id;
 	u16 next_rxq_id;
 	u8 vfid;
@@ -138,7 +138,7 @@ static void qede_configure_arfs_fltr(struct qede_dev *edev,
 
 		n->tuple.stringify(&n->tuple, tuple_buffer);
 		DP_VERBOSE(edev, NETIF_MSG_RX_STATUS,
-			   "%s sw_id[0x%x]: %s [vf %u queue %d]\n",
+			   "%s sw_id[0x%llx]: %s [vf %u queue %d]\n",
 			   add_fltr ? "Adding" : "Deleting",
 			   n->sw_id, tuple_buffer, n->vfid, rxq_id);
 	}
@@ -152,7 +152,10 @@ static void
 qede_free_arfs_filter(struct qede_dev *edev,  struct qede_arfs_fltr_node *fltr)
 {
 	kfree(fltr->data);
-	clear_bit(fltr->sw_id, edev->arfs->arfs_fltr_bmap);
+
+	if (fltr->sw_id < QEDE_RFS_MAX_FLTR)
+		clear_bit(fltr->sw_id, edev->arfs->arfs_fltr_bmap);
+
 	kfree(fltr);
 }
 
@@ -214,7 +217,7 @@ void qede_arfs_filter_op(void *dev, void *filter, u8 fw_rc)
 
 	if (fw_rc) {
 		DP_NOTICE(edev,
-			  "Failed arfs filter configuration fw_rc=%d, flow_id=%d, sw_id=%d, src_port=%d, dst_port=%d, rxq=%d\n",
+			  "Failed arfs filter configuration fw_rc=%d, flow_id=%d, sw_id=0x%llx, src_port=%d, dst_port=%d, rxq=%d\n",
 			  fw_rc, fltr->flow_id, fltr->sw_id,
 			  ntohs(fltr->tuple.src_port),
 			  ntohs(fltr->tuple.dst_port), fltr->rxq_id);
@@ -1348,7 +1351,7 @@ out:
 }
 
 static struct qede_arfs_fltr_node *
-qede_get_arfs_fltr_by_loc(struct hlist_head *head, u32 location)
+qede_get_arfs_fltr_by_loc(struct hlist_head *head, u64 location)
 {
 	struct qede_arfs_fltr_node *fltr;
 
@@ -1959,9 +1962,8 @@ unlock:
 	return rc;
 }
 
-int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
+int qede_delete_flow_filter(struct qede_dev *edev, u64 cookie)
 {
-	struct ethtool_rx_flow_spec *fsp = &info->fs;
 	struct qede_arfs_fltr_node *fltr = NULL;
 	int rc = -EPERM;
 
@@ -1970,7 +1972,7 @@ int qede_del_cls_rule(struct qede_dev *edev, struct ethtool_rxnfc *info)
 		goto unlock;
 
 	fltr = qede_get_arfs_fltr_by_loc(QEDE_ARFS_BUCKET_HEAD(edev, 0),
-					 fsp->location);
+					 cookie);
 	if (!fltr)
 		goto unlock;
 
@@ -2000,3 +2002,293 @@ unlock:
 	__qede_unlock(edev);
 	return count;
 }
+
+static int qede_parse_actions(struct qede_dev *edev,
+			      struct tcf_exts *exts)
+{
+	int rc = -EINVAL, num_act = 0;
+	const struct tc_action *a;
+	bool is_drop = false;
+	LIST_HEAD(actions);
+
+	if (!tcf_exts_has_actions(exts)) {
+		DP_NOTICE(edev, "No tc actions received\n");
+		return rc;
+	}
+
+	tcf_exts_to_list(exts, &actions);
+	list_for_each_entry(a, &actions, list) {
+		num_act++;
+
+		if (is_tcf_gact_shot(a))
+			is_drop = true;
+	}
+
+	if (num_act == 1 && is_drop)
+		return 0;
+
+	return rc;
+}
+
+static int
+qede_tc_parse_ports(struct qede_dev *edev,
+		    struct tc_cls_flower_offload *f,
+		    struct qede_arfs_tuple *t)
+{
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_dissector_key_ports *key, *mask;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_PORTS,
+						f->key);
+		mask = skb_flow_dissector_target(f->dissector,
+						 FLOW_DISSECTOR_KEY_PORTS,
+						 f->mask);
+
+		if ((key->src && mask->src != U16_MAX) ||
+		    (key->dst && mask->dst != U16_MAX)) {
+			DP_NOTICE(edev, "Do not support ports masks\n");
+			return -EINVAL;
+		}
+
+		t->src_port = key->src;
+		t->dst_port = key->dst;
+	}
+
+	return 0;
+}
+
+static int
+qede_tc_parse_v6_common(struct qede_dev *edev,
+			struct tc_cls_flower_offload *f,
+			struct qede_arfs_tuple *t)
+{
+	struct in6_addr zero_addr, addr;
+
+	memset(&zero_addr, 0, sizeof(addr));
+	memset(&addr, 0xff, sizeof(addr));
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV6_ADDRS)) {
+		struct flow_dissector_key_ipv6_addrs *key, *mask;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						f->key);
+		mask = skb_flow_dissector_target(f->dissector,
+						 FLOW_DISSECTOR_KEY_IPV6_ADDRS,
+						 f->mask);
+
+		if ((memcmp(&key->src, &zero_addr, sizeof(addr)) &&
+		     memcmp(&mask->src, &addr, sizeof(addr))) ||
+		    (memcmp(&key->dst, &zero_addr, sizeof(addr)) &&
+		     memcmp(&mask->dst, &addr, sizeof(addr)))) {
+			DP_NOTICE(edev,
+				  "Do not support IPv6 address prefix/mask\n");
+			return -EINVAL;
+		}
+
+		memcpy(&t->src_ipv6, &key->src, sizeof(addr));
+		memcpy(&t->dst_ipv6, &key->dst, sizeof(addr));
+	}
+
+	if (qede_tc_parse_ports(edev, f, t))
+		return -EINVAL;
+
+	return qede_set_v6_tuple_to_profile(edev, t, &zero_addr);
+}
+
+static int
+qede_tc_parse_v4_common(struct qede_dev *edev,
+			struct tc_cls_flower_offload *f,
+			struct qede_arfs_tuple *t)
+{
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) {
+		struct flow_dissector_key_ipv4_addrs *key, *mask;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						f->key);
+		mask = skb_flow_dissector_target(f->dissector,
+						 FLOW_DISSECTOR_KEY_IPV4_ADDRS,
+						 f->mask);
+
+		if ((key->src && mask->src != U32_MAX) ||
+		    (key->dst && mask->dst != U32_MAX)) {
+			DP_NOTICE(edev, "Do not support ipv4 prefix/masks\n");
+			return -EINVAL;
+		}
+
+		t->src_ipv4 = key->src;
+		t->dst_ipv4 = key->dst;
+	}
+
+	if (qede_tc_parse_ports(edev, f, t))
+		return -EINVAL;
+
+	return qede_set_v4_tuple_to_profile(edev, t);
+}
+
+static int
+qede_tc_parse_tcp_v6(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_TCP;
+	tuple->eth_proto = htons(ETH_P_IPV6);
+
+	return qede_tc_parse_v6_common(edev, f, tuple);
+}
+
+static int
+qede_tc_parse_tcp_v4(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_TCP;
+	tuple->eth_proto = htons(ETH_P_IP);
+
+	return qede_tc_parse_v4_common(edev, f, tuple);
+}
+
+static int
+qede_tc_parse_udp_v6(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_UDP;
+	tuple->eth_proto = htons(ETH_P_IPV6);
+
+	return qede_tc_parse_v6_common(edev, f, tuple);
+}
+
+static int
+qede_tc_parse_udp_v4(struct qede_dev *edev,
+		     struct tc_cls_flower_offload *f,
+		     struct qede_arfs_tuple *tuple)
+{
+	tuple->ip_proto = IPPROTO_UDP;
+	tuple->eth_proto = htons(ETH_P_IP);
+
+	return qede_tc_parse_v4_common(edev, f, tuple);
+}
+
+static int
+qede_parse_flower_attr(struct qede_dev *edev, __be16 proto,
+		       struct tc_cls_flower_offload *f,
+		       struct qede_arfs_tuple *tuple)
+{
+	int rc = -EINVAL;
+	u8 ip_proto = 0;
+
+	memset(tuple, 0, sizeof(*tuple));
+
+	if (f->dissector->used_keys &
+	    ~(BIT(FLOW_DISSECTOR_KEY_CONTROL) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_BASIC) |
+	      BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS) |
+	      BIT(FLOW_DISSECTOR_KEY_PORTS))) {
+		DP_NOTICE(edev, "Unsupported key set:0x%x\n",
+			  f->dissector->used_keys);
+		return -EOPNOTSUPP;
+	}
+
+	if (proto != htons(ETH_P_IP) &&
+	    proto != htons(ETH_P_IPV6)) {
+		DP_NOTICE(edev, "Unsupported proto=0x%x\n", proto);
+		return -EPROTONOSUPPORT;
+	}
+
+	if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_dissector_key_basic *key;
+
+		key = skb_flow_dissector_target(f->dissector,
+						FLOW_DISSECTOR_KEY_BASIC,
+						f->key);
+		ip_proto = key->ip_proto;
+	}
+
+	if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IP))
+		rc = qede_tc_parse_tcp_v4(edev, f, tuple);
+	else if (ip_proto == IPPROTO_TCP && proto == htons(ETH_P_IPV6))
+		rc = qede_tc_parse_tcp_v6(edev, f, tuple);
+	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IP))
+		rc = qede_tc_parse_udp_v4(edev, f, tuple);
+	else if (ip_proto == IPPROTO_UDP && proto == htons(ETH_P_IPV6))
+		rc = qede_tc_parse_udp_v6(edev, f, tuple);
+	else
+		DP_NOTICE(edev, "Invalid tc protocol request\n");
+
+	return rc;
+}
+
+int qede_add_tc_flower_fltr(struct qede_dev *edev, __be16 proto,
+			    struct tc_cls_flower_offload *f)
+{
+	struct qede_arfs_fltr_node *n;
+	int min_hlen, rc = -EINVAL;
+	struct qede_arfs_tuple t;
+
+	__qede_lock(edev);
+
+	if (!edev->arfs) {
+		rc = -EPERM;
+		goto unlock;
+	}
+
+	/* parse flower attribute and prepare filter */
+	if (qede_parse_flower_attr(edev, proto, f, &t))
+		goto unlock;
+
+	/* Validate profile mode and number of filters */
+	if ((edev->arfs->filter_count && edev->arfs->mode != t.mode) ||
+	    edev->arfs->filter_count == QEDE_RFS_MAX_FLTR) {
+		DP_NOTICE(edev,
+			  "Filter configuration invalidated, filter mode=0x%x, configured mode=0x%x, filter count=0x%x\n",
+			  t.mode, edev->arfs->mode, edev->arfs->filter_count);
+		goto unlock;
+	}
+
+	/* parse tc actions and get the vf_id */
+	if (qede_parse_actions(edev, f->exts))
+		goto unlock;
+
+	if (qede_flow_find_fltr(edev, &t)) {
+		rc = -EEXIST;
+		goto unlock;
+	}
+
+	n = kzalloc(sizeof(*n), GFP_KERNEL);
+	if (!n) {
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	min_hlen = qede_flow_get_min_header_size(&t);
+
+	n->data = kzalloc(min_hlen, GFP_KERNEL);
+	if (!n->data) {
+		kfree(n);
+		rc = -ENOMEM;
+		goto unlock;
+	}
+
+	memcpy(&n->tuple, &t, sizeof(n->tuple));
+
+	n->buf_len = min_hlen;
+	n->b_is_drop = true;
+	n->sw_id = f->cookie;
+
+	n->tuple.build_hdr(&n->tuple, n->data);
+
+	rc = qede_enqueue_fltr_and_config_searcher(edev, n, 0);
+	if (rc)
+		goto unlock;
+
+	qede_configure_arfs_fltr(edev, n, n->rxq_id, true);
+	rc = qede_poll_arfs_filter_config(edev, n);
+
+unlock:
+	__qede_unlock(edev);
+	return rc;
+}
diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index d7299afa902c..4b5d98f60d32 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -556,13 +556,67 @@ int qede_setup_tc(struct net_device *ndev, u8 num_tc)
 	return 0;
 }
 
+static int
+qede_set_flower(struct qede_dev *edev, struct tc_cls_flower_offload *f,
+		__be16 proto)
+{
+	switch (f->command) {
+	case TC_CLSFLOWER_REPLACE:
+		return qede_add_tc_flower_fltr(edev, proto, f);
+	case TC_CLSFLOWER_DESTROY:
+		return qede_delete_flow_filter(edev, f->cookie);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int qede_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				  void *cb_priv)
+{
+	struct tc_cls_flower_offload *f;
+	struct qede_dev *edev = cb_priv;
+
+	if (!tc_cls_can_offload_and_chain0(edev->ndev, type_data))
+		return -EOPNOTSUPP;
+
+	switch (type) {
+	case TC_SETUP_CLSFLOWER:
+		f = type_data;
+		return qede_set_flower(edev, f, f->common.protocol);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int qede_setup_tc_block(struct qede_dev *edev,
+			       struct tc_block_offload *f)
+{
+	if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	switch (f->command) {
+	case TC_BLOCK_BIND:
+		return tcf_block_cb_register(f->block,
+					     qede_setup_tc_block_cb,
+					     edev, edev, f->extack);
+	case TC_BLOCK_UNBIND:
+		tcf_block_cb_unregister(f->block, qede_setup_tc_block_cb, edev);
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int
 qede_setup_tc_offload(struct net_device *dev, enum tc_setup_type type,
 		      void *type_data)
 {
+	struct qede_dev *edev = netdev_priv(dev);
 	struct tc_mqprio_qopt *mqprio;
 
 	switch (type) {
+	case TC_SETUP_BLOCK:
+		return qede_setup_tc_block(edev, type_data);
 	case TC_SETUP_QDISC_MQPRIO:
 		mqprio = type_data;
 
@@ -727,7 +781,7 @@ static void qede_init_ndev(struct qede_dev *edev)
 	/* user-changeble features */
 	hw_features = NETIF_F_GRO | NETIF_F_GRO_HW | NETIF_F_SG |
 		      NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
-		      NETIF_F_TSO | NETIF_F_TSO6;
+		      NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_HW_TC;
 
 	if (!IS_VF(edev) && edev->dev_info.common.num_hwfns == 1)
 		hw_features |= NETIF_F_NTUPLE;
-- 
cgit v1.2.3


From eb95f52fc72d15566fe06807c9e0cabbcd3480f1 Mon Sep 17 00:00:00 2001
From: Maria Pasechnik <mariap@mellanox.com>
Date: Wed, 8 Aug 2018 11:46:30 +0300
Subject: net: ipv6_gre: Fix GRO to work on IPv6 over GRE tap

IPv6 GRO over GRE tap is not working while GRO is not set
over the native interface.

gro_list_prepare function updates the same_flow variable
of existing sessions to 1 if their mac headers match the one
of the incoming packet.
same_flow is used to filter out non-matching sessions and keep
potential ones for aggregation.

The number of bytes to compare should be the number of bytes
in the mac headers. In gro_list_prepare this number is set to
be skb->dev->hard_header_len. For GRE interfaces this hard_header_len
should be as it is set in the initialization process (when GRE is
created), it should not be overridden. But currently it is being overridden
by the value that is actually supposed to represent the needed_headroom.
Therefore, the number of bytes compared in order to decide whether the
the mac headers are the same is greater than the length of the headers.

As it's documented in netdevice.h, hard_header_len is the maximum
hardware header length, and needed_headroom is the extra headroom
the hardware may need.
hard_header_len is basically all the bytes received by the physical
till layer 3 header of the packet received by the interface.
For example, if the interface is a GRE tap then the needed_headroom
should be the total length of the following headers:
IP header of the physical, GRE header, mac header of GRE.
It is often used to calculate the MTU of the created interface.

This patch removes the override of the hard_header_len, and
assigns the calculated value to needed_headroom.
This way, the comparison in gro_list_prepare is really of
the mac headers, and if the packets have the same mac headers
the same_flow will be set to 1.

Performance testing: 45% higher bandwidth.
Measuring bandwidth of single-stream IPv4 TCP traffic over IPv6
GRE tap while GRO is not set on the native.
NIC: ConnectX-4LX
Before (GRO not working) : 7.2 Gbits/sec
After (GRO working): 10.5 Gbits/sec

Signed-off-by: Maria Pasechnik <mariap@mellanox.com>
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv6/ip6_gre.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index fc7dd3a04360..18a3794b0f52 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1129,7 +1129,7 @@ static void ip6gre_tnl_link_config_route(struct ip6_tnl *t, int set_mtu,
 			return;
 
 		if (rt->dst.dev) {
-			dev->hard_header_len = rt->dst.dev->hard_header_len +
+			dev->needed_headroom = rt->dst.dev->hard_header_len +
 					       t_hlen;
 
 			if (set_mtu) {
@@ -1155,7 +1155,7 @@ static int ip6gre_calc_hlen(struct ip6_tnl *tunnel)
 	tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen;
 
 	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
-	tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
 	return t_hlen;
 }
 
@@ -1825,7 +1825,7 @@ static int ip6erspan_calc_hlen(struct ip6_tnl *tunnel)
 		       erspan_hdr_len(tunnel->parms.erspan_ver);
 
 	t_hlen = tunnel->hlen + sizeof(struct ipv6hdr);
-	tunnel->dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+	tunnel->dev->needed_headroom = LL_MAX_HEADER + t_hlen;
 	return t_hlen;
 }
 
-- 
cgit v1.2.3


From 98471b5b7294665aeb9345d65eea2bf69687ad11 Mon Sep 17 00:00:00 2001
From: Petr Oros <poros@redhat.com>
Date: Wed, 8 Aug 2018 13:35:01 +0200
Subject: be2net: Use Kconfig flag to support for enabling/disabling adapters

Add flags to enable/disable supported chips in be2net.

With disable support are removed coresponding PCI IDs and
also codepaths with [BE2|BE3|BEx|lancer|skyhawk]_chip checks.

Disable chip will reduce module size by:
BE2 ~2kb
BE3 ~3kb
Lancer ~10kb
Skyhawk ~9kb

When enable skyhawk only it will reduce module size by ~20kb

New help style in Kconfig

Reviewed-by: Ivan Vecera <ivecera@redhat.com>
Signed-off-by: Petr Oros <poros@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/emulex/benet/Kconfig   | 40 +++++++++++++++++++++++++++--
 drivers/net/ethernet/emulex/benet/be.h      | 16 ++++++++++++
 drivers/net/ethernet/emulex/benet/be_main.c | 10 +++++++-
 3 files changed, 63 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/Kconfig b/drivers/net/ethernet/emulex/benet/Kconfig
index b4853ec9de8d..8cf794edd3c3 100644
--- a/drivers/net/ethernet/emulex/benet/Kconfig
+++ b/drivers/net/ethernet/emulex/benet/Kconfig
@@ -1,7 +1,7 @@
 config BE2NET
 	tristate "ServerEngines' 10Gbps NIC - BladeEngine"
 	depends on PCI
-	---help---
+	help
 	  This driver implements the NIC functionality for ServerEngines'
 	  10Gbps network adapter - BladeEngine.
 
@@ -10,6 +10,42 @@ config BE2NET_HWMON
 	depends on BE2NET && HWMON
 	depends on !(BE2NET=y && HWMON=m)
 	default y
-	---help---
+	help
 	  Say Y here if you want to expose thermal sensor data on
 	  be2net network adapter.
+
+config BE2NET_BE2
+	bool "Support for BE2 chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on BE2
+	  chipsets. (e.g. OneConnect OCe10xxx)
+
+config BE2NET_BE3
+	bool "Support for BE3 chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on BE3
+	  chipsets. (e.g. OneConnect OCe11xxx)
+
+config BE2NET_LANCER
+	bool "Support for Lancer chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on Lancer
+	  chipsets. (e.g LightPulse LPe12xxx)
+
+config BE2NET_SKYHAWK
+	bool "Support for Skyhawk chipsets"
+	depends on BE2NET
+	default y
+	help
+	  Say Y here if you want to use devices based on Skyhawk
+	  chipsets. (e.g. OneConnect OCe14xxx)
+
+comment "WARNING: be2net is useless without any enabled chip"
+        depends on BE2NET_BE2=n && BE2NET_BE3=n && BE2NET_LANCER=n && \
+	BE2NET_SKYHAWK=n && BE2NET
diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index d80fe03d3107..58bcee8f0a58 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -752,17 +752,33 @@ static inline u16 be_max_any_irqs(struct be_adapter *adapter)
 /* Is BE in QNQ multi-channel mode */
 #define be_is_qnq_mode(adapter)		(adapter->function_mode & QNQ_MODE)
 
+#ifdef CONFIG_BE2NET_LANCER
 #define lancer_chip(adapter)	(adapter->pdev->device == OC_DEVICE_ID3 || \
 				 adapter->pdev->device == OC_DEVICE_ID4)
+#else
+#define lancer_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_LANCER */
 
+#ifdef CONFIG_BE2NET_SKYHAWK
 #define skyhawk_chip(adapter)	(adapter->pdev->device == OC_DEVICE_ID5 || \
 				 adapter->pdev->device == OC_DEVICE_ID6)
+#else
+#define skyhawk_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_SKYHAWK */
 
+#ifdef CONFIG_BE2NET_BE3
 #define BE3_chip(adapter)	(adapter->pdev->device == BE_DEVICE_ID2 || \
 				 adapter->pdev->device == OC_DEVICE_ID2)
+#else
+#define BE3_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_BE3 */
 
+#ifdef CONFIG_BE2NET_BE2
 #define BE2_chip(adapter)	(adapter->pdev->device == BE_DEVICE_ID1 || \
 				 adapter->pdev->device == OC_DEVICE_ID1)
+#else
+#define BE2_chip(adapter)	(0)
+#endif /* CONFIG_BE2NET_BE2 */
 
 #define BEx_chip(adapter)	(BE3_chip(adapter) || BE2_chip(adapter))
 
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index d0b9415d9ae7..74d122616e76 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -47,14 +47,22 @@ MODULE_PARM_DESC(rx_frag_size, "Size of a fragment that holds rcvd data.");
 static struct workqueue_struct *be_err_recovery_workq;
 
 static const struct pci_device_id be_dev_ids[] = {
+#ifdef CONFIG_BE2NET_BE2
 	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID1) },
-	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
 	{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID1) },
+#endif /* CONFIG_BE2NET_BE2 */
+#ifdef CONFIG_BE2NET_BE3
+	{ PCI_DEVICE(BE_VENDOR_ID, BE_DEVICE_ID2) },
 	{ PCI_DEVICE(BE_VENDOR_ID, OC_DEVICE_ID2) },
+#endif /* CONFIG_BE2NET_BE3 */
+#ifdef CONFIG_BE2NET_LANCER
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID3)},
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID4)},
+#endif /* CONFIG_BE2NET_LANCER */
+#ifdef CONFIG_BE2NET_SKYHAWK
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID5)},
 	{ PCI_DEVICE(EMULEX_VENDOR_ID, OC_DEVICE_ID6)},
+#endif /* CONFIG_BE2NET_SKYHAWK */
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, be_dev_ids);
-- 
cgit v1.2.3


From 15693fd37fc3a49da356164ed15b571c175efc34 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 8 Aug 2018 19:40:31 +0800
Subject: net: skbuff.h: fix using plain integer as NULL warning

Fixes the following sparse warning:
./include/linux/skbuff.h:2365:58: warning: Using plain integer as NULL pointer

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/skbuff.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7ebdf158a795..7e237a63a70c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2362,7 +2362,7 @@ static inline void skb_probe_transport_header(struct sk_buff *skb,
 	if (skb_transport_header_was_set(skb))
 		return;
 
-	if (skb_flow_dissect_flow_keys_basic(skb, &keys, 0, 0, 0, 0, 0))
+	if (skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0))
 		skb_set_transport_header(skb, keys.control.thoff);
 	else
 		skb_set_transport_header(skb, offset_hint);
-- 
cgit v1.2.3


From 0bab1cdc8c4d5392a5d9037cfbdbb2cacc91ce5e Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 8 Aug 2018 19:59:32 +0800
Subject: decnet: fix using plain integer as NULL warning

Fixes the following sparse warning:
net/decnet/dn_route.c:407:30: warning: Using plain integer as NULL pointer
net/decnet/dn_route.c:1923:22: warning: Using plain integer as NULL pointer

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Kees Cook <keescook@chromium.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/decnet/dn_route.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c
index 3107a2e24e6b..1c002c0fb712 100644
--- a/net/decnet/dn_route.c
+++ b/net/decnet/dn_route.c
@@ -404,7 +404,7 @@ void dn_rt_cache_flush(int delay)
 
 	if (delay <= 0) {
 		spin_unlock_bh(&dn_rt_flush_lock);
-		dn_run_flush(0);
+		dn_run_flush(NULL);
 		return;
 	}
 
@@ -1920,7 +1920,7 @@ void __init dn_route_init(void)
 void __exit dn_route_cleanup(void)
 {
 	del_timer(&dn_route_timer);
-	dn_run_flush(0);
+	dn_run_flush(NULL);
 
 	remove_proc_entry("decnet_cache", init_net.proc_net);
 	dst_entries_destroy(&dn_dst_ops);
-- 
cgit v1.2.3


From 63cc5bcc9fc467bbe61cc9ee52509294bdf04c4b Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@mellanox.com>
Date: Wed, 8 Aug 2018 14:04:13 +0200
Subject: net: sched: fix block->refcnt decrement

Currently the refcnt is never decremented in case the value is not 1.
Fix it by adding decrement in case the refcnt is not 1.

Reported-by: Vlad Buslov <vladbu@mellanox.com>
Fixes: f71e0ca4db18 ("net: sched: Avoid implicit chain 0 creation")
Signed-off-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_api.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index 194c2e0b2737..f922ce27ed5e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -780,6 +780,8 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q,
 		block->refcnt--;
 		if (list_empty(&block->chain_list))
 			kfree(block);
+	} else {
+		block->refcnt--;
 	}
 }
 EXPORT_SYMBOL(tcf_block_put_ext);
-- 
cgit v1.2.3


From cd16e5b233aadad5c4652f5466d1505a9f78bade Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Wed, 8 Aug 2018 20:29:08 +0800
Subject: mlxsw: spectrum_flower: use PTR_ERR_OR_ZERO()

Fix ptr_ret.cocci warnings:
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c:543:1-3: WARNING: PTR_ERR_OR_ZERO can be used

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
index 75e5316ffebd..ebd1b24ebaa5 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c
@@ -514,10 +514,9 @@ int mlxsw_sp_flower_tmplt_create(struct mlxsw_sp *mlxsw_sp,
 					   f->common.chain_index,
 					   MLXSW_SP_ACL_PROFILE_FLOWER,
 					   &rulei.values.elusage);
-	if (IS_ERR(ruleset))
-		return PTR_ERR(ruleset);
+
 	/* keep the reference to the ruleset */
-	return 0;
+	return PTR_ERR_OR_ZERO(ruleset);
 }
 
 void mlxsw_sp_flower_tmplt_destroy(struct mlxsw_sp *mlxsw_sp,
-- 
cgit v1.2.3


From 933de7866b57b2fc8adc160642a81f07175f138d Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Wed, 8 Aug 2018 14:38:55 +0200
Subject: net: dsa: rtl8366rb: Support port 4 (WAN)

The totally undocumented IO mode needs to be set to enumerator
0 to enable port 4 also known as WAN in most configurations,
for ordinary traffic. The 3 bits in the register come up as
010 after reset, but need to be set to 000.

The Realtek source code contains a name for these bits, but
no explanation of what the 8 different IO modes may be.

Set it to zero for the time being and drop a comment so
people know what is going on if they run into trouble. This
"mode zero" works fine with the D-Link DIR-685 with
RTL8366RB.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rtl8366rb.c | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/net/dsa/rtl8366rb.c b/drivers/net/dsa/rtl8366rb.c
index 1e55b9bf8b56..a4d5049df692 100644
--- a/drivers/net/dsa/rtl8366rb.c
+++ b/drivers/net/dsa/rtl8366rb.c
@@ -48,6 +48,23 @@
 #define RTL8366RB_SSCR2				0x0004
 #define RTL8366RB_SSCR2_DROP_UNKNOWN_DA		BIT(0)
 
+/* Port Mode Control registers */
+#define RTL8366RB_PMC0				0x0005
+#define RTL8366RB_PMC0_SPI			BIT(0)
+#define RTL8366RB_PMC0_EN_AUTOLOAD		BIT(1)
+#define RTL8366RB_PMC0_PROBE			BIT(2)
+#define RTL8366RB_PMC0_DIS_BISR			BIT(3)
+#define RTL8366RB_PMC0_ADCTEST			BIT(4)
+#define RTL8366RB_PMC0_SRAM_DIAG		BIT(5)
+#define RTL8366RB_PMC0_EN_SCAN			BIT(6)
+#define RTL8366RB_PMC0_P4_IOMODE_SHIFT		7
+#define RTL8366RB_PMC0_P4_IOMODE_MASK		GENMASK(9, 7)
+#define RTL8366RB_PMC0_P5_IOMODE_SHIFT		10
+#define RTL8366RB_PMC0_P5_IOMODE_MASK		GENMASK(12, 10)
+#define RTL8366RB_PMC0_SDSMODE_SHIFT		13
+#define RTL8366RB_PMC0_SDSMODE_MASK		GENMASK(15, 13)
+#define RTL8366RB_PMC1				0x0006
+
 /* Port Mirror Control Register */
 #define RTL8366RB_PMCR				0x0007
 #define RTL8366RB_PMCR_SOURCE_PORT(a)		(a)
@@ -860,6 +877,19 @@ static int rtl8366rb_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
+	/* Port 4 setup: this enables Port 4, usually the WAN port,
+	 * common PHY IO mode is apparently mode 0, and this is not what
+	 * the port is initialized to. There is no explanation of the
+	 * IO modes in the Realtek source code, if your WAN port is
+	 * connected to something exotic such as fiber, then this might
+	 * be worth experimenting with.
+	 */
+	ret = regmap_update_bits(smi->map, RTL8366RB_PMC0,
+				 RTL8366RB_PMC0_P4_IOMODE_MASK,
+				 0 << RTL8366RB_PMC0_P4_IOMODE_SHIFT);
+	if (ret)
+		return ret;
+
 	/* Discard VLAN tagged packets if the port is not a member of
 	 * the VLAN with which the packets is associated.
 	 */
-- 
cgit v1.2.3


From 51507c5f6484055c3d6071e9fb7aac5567efc20f Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Wed, 8 Aug 2018 19:04:27 +0100
Subject: ethernet/qlogic: remove unused array msi_tgt_status

Array msi_tgt_status is defined but never used, hence it is
redundant and can be removed.

Cleans up clang warning:
warning: 'msi_tgt_status' defined but not used [-Wunused-const-variable=]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
index 7848cf04b29a..822aa393c370 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_hw.c
@@ -276,13 +276,6 @@ static const unsigned crb_hub_agt[64] = {
 	0,
 };
 
-static const u32 msi_tgt_status[8] = {
-	ISR_INT_TARGET_STATUS, ISR_INT_TARGET_STATUS_F1,
-	ISR_INT_TARGET_STATUS_F2, ISR_INT_TARGET_STATUS_F3,
-	ISR_INT_TARGET_STATUS_F4, ISR_INT_TARGET_STATUS_F5,
-	ISR_INT_TARGET_STATUS_F6, ISR_INT_TARGET_STATUS_F7
-};
-
 /*  PCI Windowing for DDR regions.  */
 
 #define QLCNIC_PCIE_SEM_TIMEOUT	10000
-- 
cgit v1.2.3


From 4005a7cb4f553a21d60f24ed7a18fbd26c6db9f4 Mon Sep 17 00:00:00 2001
From: Andrew Lunn <andrew@lunn.ch>
Date: Wed, 8 Aug 2018 20:54:12 +0200
Subject: net: phy: sftp: print debug message with text, not numbers

Convert the state numbers, device state, etc from numbers to strings
when printing debug messages.

Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/sfp.c | 76 ++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 72 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 5661226cf75b..4637d980310e 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -60,6 +60,69 @@ enum {
 	SFP_S_TX_DISABLE,
 };
 
+static const char  * const mod_state_strings[] = {
+	[SFP_MOD_EMPTY] = "empty",
+	[SFP_MOD_PROBE] = "probe",
+	[SFP_MOD_HPOWER] = "hpower",
+	[SFP_MOD_PRESENT] = "present",
+	[SFP_MOD_ERROR] = "error",
+};
+
+static const char *mod_state_to_str(unsigned short mod_state)
+{
+	if (mod_state >= ARRAY_SIZE(mod_state_strings))
+		return "Unknown module state";
+	return mod_state_strings[mod_state];
+}
+
+static const char * const dev_state_strings[] = {
+	[SFP_DEV_DOWN] = "down",
+	[SFP_DEV_UP] = "up",
+};
+
+static const char *dev_state_to_str(unsigned short dev_state)
+{
+	if (dev_state >= ARRAY_SIZE(dev_state_strings))
+		return "Unknown device state";
+	return dev_state_strings[dev_state];
+}
+
+static const char * const event_strings[] = {
+	[SFP_E_INSERT] = "insert",
+	[SFP_E_REMOVE] = "remove",
+	[SFP_E_DEV_DOWN] = "dev_down",
+	[SFP_E_DEV_UP] = "dev_up",
+	[SFP_E_TX_FAULT] = "tx_fault",
+	[SFP_E_TX_CLEAR] = "tx_clear",
+	[SFP_E_LOS_HIGH] = "los_high",
+	[SFP_E_LOS_LOW] = "los_low",
+	[SFP_E_TIMEOUT] = "timeout",
+};
+
+static const char *event_to_str(unsigned short event)
+{
+	if (event >= ARRAY_SIZE(event_strings))
+		return "Unknown event";
+	return event_strings[event];
+}
+
+static const char * const sm_state_strings[] = {
+	[SFP_S_DOWN] = "down",
+	[SFP_S_INIT] = "init",
+	[SFP_S_WAIT_LOS] = "wait_los",
+	[SFP_S_LINK_UP] = "link_up",
+	[SFP_S_TX_FAULT] = "tx_fault",
+	[SFP_S_REINIT] = "reinit",
+	[SFP_S_TX_DISABLE] = "rx_disable",
+};
+
+static const char *sm_state_to_str(unsigned short sm_state)
+{
+	if (sm_state >= ARRAY_SIZE(sm_state_strings))
+		return "Unknown state";
+	return sm_state_strings[sm_state];
+}
+
 static const char *gpio_of_names[] = {
 	"mod-def0",
 	"los",
@@ -1388,8 +1451,11 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 {
 	mutex_lock(&sfp->sm_mutex);
 
-	dev_dbg(sfp->dev, "SM: enter %u:%u:%u event %u\n",
-		sfp->sm_mod_state, sfp->sm_dev_state, sfp->sm_state, event);
+	dev_dbg(sfp->dev, "SM: enter %s:%s:%s event %s\n",
+		mod_state_to_str(sfp->sm_mod_state),
+		dev_state_to_str(sfp->sm_dev_state),
+		sm_state_to_str(sfp->sm_state),
+		event_to_str(event));
 
 	/* This state machine tracks the insert/remove state of
 	 * the module, and handles probing the on-board EEPROM.
@@ -1520,8 +1586,10 @@ static void sfp_sm_event(struct sfp *sfp, unsigned int event)
 		break;
 	}
 
-	dev_dbg(sfp->dev, "SM: exit %u:%u:%u\n",
-		sfp->sm_mod_state, sfp->sm_dev_state, sfp->sm_state);
+	dev_dbg(sfp->dev, "SM: exit %s:%s:%s\n",
+		mod_state_to_str(sfp->sm_mod_state),
+		dev_state_to_str(sfp->sm_dev_state),
+		sm_state_to_str(sfp->sm_state));
 
 	mutex_unlock(&sfp->sm_mutex);
 }
-- 
cgit v1.2.3


From bd2e9567db72e37f7f4b90faa5133bc7365b5f65 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Thu, 9 Aug 2018 16:19:52 -0500
Subject: PCI: Hide ACS quirk declarations inside PCI core

Move declarations for these functions:

  pci_dev_specific_acs_enabled()
  pci_dev_specific_enable_acs()

from include/linux/pci.h to drivers/pci/pci.h because nothing outside the
PCI core needs to use them.

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.h   | 14 ++++++++++++++
 include/linux/pci.h | 11 -----------
 2 files changed, 14 insertions(+), 11 deletions(-)

diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index c358e7a07f3f..a1224fef3409 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -352,6 +352,20 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev,
 }
 
 void pci_enable_acs(struct pci_dev *dev);
+#ifdef CONFIG_PCI_QUIRKS
+int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
+int pci_dev_specific_enable_acs(struct pci_dev *dev);
+#else
+static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
+					       u16 acs_flags)
+{
+	return -ENOTTY;
+}
+static inline int pci_dev_specific_enable_acs(struct pci_dev *dev)
+{
+	return -ENOTTY;
+}
+#endif
 
 /* PCI error reporting and recovery */
 void pcie_do_fatal_recovery(struct pci_dev *dev, u32 service);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..1e1ed049dd1c 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1876,20 +1876,9 @@ enum pci_fixup_pass {
 
 #ifdef CONFIG_PCI_QUIRKS
 void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev);
-int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
-int pci_dev_specific_enable_acs(struct pci_dev *dev);
 #else
 static inline void pci_fixup_device(enum pci_fixup_pass pass,
 				    struct pci_dev *dev) { }
-static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
-					       u16 acs_flags)
-{
-	return -ENOTTY;
-}
-static inline int pci_dev_specific_enable_acs(struct pci_dev *dev)
-{
-	return -ENOTTY;
-}
 #endif
 
 void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen);
-- 
cgit v1.2.3


From 07d8d7e57c28ca9a07dab4efd75dad3a654aeb85 Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Mon, 30 Jul 2018 10:18:37 -0600
Subject: PCI: Make specifying PCI devices in kernel parameters reusable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Separate out the code to match a PCI device with a string (typically
originating from a kernel parameter) from the
pci_specified_resource_alignment() function into its own helper function.

While we are at it, this change fixes the kernel style of the function
(fixing a number of long lines and extra parentheses).

Additionally, make the analogous change to the kernel parameter
documentation: Separate the description of how to specify a PCI device
into its own section at the head of the "pci=" parameter.

This patch should have no functional alterations.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
[bhelgaas: use "device" instead of "slot" in documentation since that's the
usual language in the PCI specs]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Stephen Bates <sbates@raithlin.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  28 ++++-
 drivers/pci/pci.c                               | 157 ++++++++++++++++--------
 2 files changed, 126 insertions(+), 59 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index efc7aa7a0670..ab36fb34ed01 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -2994,7 +2994,26 @@
 			See header of drivers/block/paride/pcd.c.
 			See also Documentation/blockdev/paride.txt.
 
-	pci=option[,option...]	[PCI] various PCI subsystem options:
+	pci=option[,option...]	[PCI] various PCI subsystem options.
+
+				Some options herein operate on a specific device
+				or a set of devices (<pci_dev>). These are
+				specified in one of the following formats:
+
+				[<domain>:]<bus>:<device>.<func>
+				pci:<vendor>:<device>[:<subvendor>:<subdevice>]
+
+				Note: the first format specifies a PCI
+				bus/device/function address which may change
+				if new hardware is inserted, if motherboard
+				firmware changes, or due to changes caused
+				by other kernel parameters. If the
+				domain is left unspecified, it is
+				taken to be zero. The second format
+				selects devices using IDs from the
+				configuration space which may match multiple
+				devices in the system.
+
 		earlydump	[X86] dump PCI config space before the kernel
 				changes anything
 		off		[X86] don't probe for the PCI bus
@@ -3123,11 +3142,10 @@
 				window. The default value is 64 megabytes.
 		resource_alignment=
 				Format:
-				[<order of align>@][<domain>:]<bus>:<slot>.<func>[; ...]
-				[<order of align>@]pci:<vendor>:<device>\
-						[:<subvendor>:<subdevice>][; ...]
+				[<order of align>@]<pci_dev>[; ...]
 				Specifies alignment and device to reassign
-				aligned memory resources.
+				aligned memory resources. How to
+				specify the device is described above.
 				If <order of align> is not specified,
 				PAGE_SIZE is used as alignment.
 				PCI-PCI bridge can be specified, if resource
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..1574b2da25e7 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -191,6 +191,92 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
 EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
 #endif
 
+/**
+ * pci_dev_str_match - test if a string matches a device
+ * @dev:    the PCI device to test
+ * @p:      string to match the device against
+ * @endptr: pointer to the string after the match
+ *
+ * Test if a string (typically from a kernel parameter) matches a specified
+ * PCI device. The string may be of one of the following formats:
+ *
+ *   [<domain>:]<bus>:<device>.<func>
+ *   pci:<vendor>:<device>[:<subvendor>:<subdevice>]
+ *
+ * The first format specifies a PCI bus/device/function address which
+ * may change if new hardware is inserted, if motherboard firmware changes,
+ * or due to changes caused in kernel parameters. If the domain is
+ * left unspecified, it is taken to be 0.
+ *
+ * The second format matches devices using IDs in the configuration
+ * space which may match multiple devices in the system. A value of 0
+ * for any field will match all devices. (Note: this differs from
+ * in-kernel code that uses PCI_ANY_ID which is ~0; this is for
+ * legacy reasons and convenience so users don't have to specify
+ * FFFFFFFFs on the command line.)
+ *
+ * Returns 1 if the string matches the device, 0 if it does not and
+ * a negative error code if the string cannot be parsed.
+ */
+static int pci_dev_str_match(struct pci_dev *dev, const char *p,
+			     const char **endptr)
+{
+	int ret;
+	int seg, bus, slot, func, count;
+	unsigned short vendor, device, subsystem_vendor, subsystem_device;
+
+	if (strncmp(p, "pci:", 4) == 0) {
+		/* PCI vendor/device (subvendor/subdevice) IDs are specified */
+		p += 4;
+		ret = sscanf(p, "%hx:%hx:%hx:%hx%n", &vendor, &device,
+			     &subsystem_vendor, &subsystem_device, &count);
+		if (ret != 4) {
+			ret = sscanf(p, "%hx:%hx%n", &vendor, &device, &count);
+			if (ret != 2)
+				return -EINVAL;
+
+			subsystem_vendor = 0;
+			subsystem_device = 0;
+		}
+
+		p += count;
+
+		if ((!vendor || vendor == dev->vendor) &&
+		    (!device || device == dev->device) &&
+		    (!subsystem_vendor ||
+			    subsystem_vendor == dev->subsystem_vendor) &&
+		    (!subsystem_device ||
+			    subsystem_device == dev->subsystem_device))
+			goto found;
+
+	} else {
+		/* PCI Bus, Device, Function IDs are specified */
+		ret = sscanf(p, "%x:%x:%x.%x%n", &seg, &bus, &slot,
+			     &func, &count);
+		if (ret != 4) {
+			seg = 0;
+			ret = sscanf(p, "%x:%x.%x%n", &bus, &slot,
+				     &func, &count);
+			if (ret != 3)
+				return -EINVAL;
+		}
+
+		p += count;
+
+		if (seg == pci_domain_nr(dev->bus) &&
+		    bus == dev->bus->number &&
+		    slot == PCI_SLOT(dev->devfn) &&
+		    func == PCI_FUNC(dev->devfn))
+			goto found;
+	}
+
+	*endptr = p;
+	return 0;
+
+found:
+	*endptr = p;
+	return 1;
+}
 
 static int __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn,
 				   u8 pos, int cap, int *ttl)
@@ -5454,10 +5540,10 @@ static DEFINE_SPINLOCK(resource_alignment_lock);
 static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
 							bool *resize)
 {
-	int seg, bus, slot, func, align_order, count;
-	unsigned short vendor, device, subsystem_vendor, subsystem_device;
+	int align_order, count;
 	resource_size_t align = pcibios_default_alignment();
-	char *p;
+	const char *p;
+	int ret;
 
 	spin_lock(&resource_alignment_lock);
 	p = resource_alignment_param;
@@ -5477,58 +5563,21 @@ static resource_size_t pci_specified_resource_alignment(struct pci_dev *dev,
 		} else {
 			align_order = -1;
 		}
-		if (strncmp(p, "pci:", 4) == 0) {
-			/* PCI vendor/device (subvendor/subdevice) ids are specified */
-			p += 4;
-			if (sscanf(p, "%hx:%hx:%hx:%hx%n",
-				&vendor, &device, &subsystem_vendor, &subsystem_device, &count) != 4) {
-				if (sscanf(p, "%hx:%hx%n", &vendor, &device, &count) != 2) {
-					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: pci:%s\n",
-						p);
-					break;
-				}
-				subsystem_vendor = subsystem_device = 0;
-			}
-			p += count;
-			if ((!vendor || (vendor == dev->vendor)) &&
-				(!device || (device == dev->device)) &&
-				(!subsystem_vendor || (subsystem_vendor == dev->subsystem_vendor)) &&
-				(!subsystem_device || (subsystem_device == dev->subsystem_device))) {
-				*resize = true;
-				if (align_order == -1)
-					align = PAGE_SIZE;
-				else
-					align = 1 << align_order;
-				/* Found */
-				break;
-			}
-		}
-		else {
-			if (sscanf(p, "%x:%x:%x.%x%n",
-				&seg, &bus, &slot, &func, &count) != 4) {
-				seg = 0;
-				if (sscanf(p, "%x:%x.%x%n",
-						&bus, &slot, &func, &count) != 3) {
-					/* Invalid format */
-					printk(KERN_ERR "PCI: Can't parse resource_alignment parameter: %s\n",
-						p);
-					break;
-				}
-			}
-			p += count;
-			if (seg == pci_domain_nr(dev->bus) &&
-				bus == dev->bus->number &&
-				slot == PCI_SLOT(dev->devfn) &&
-				func == PCI_FUNC(dev->devfn)) {
-				*resize = true;
-				if (align_order == -1)
-					align = PAGE_SIZE;
-				else
-					align = 1 << align_order;
-				/* Found */
-				break;
-			}
+
+		ret = pci_dev_str_match(dev, p, &p);
+		if (ret == 1) {
+			*resize = true;
+			if (align_order == -1)
+				align = PAGE_SIZE;
+			else
+				align = 1 << align_order;
+			break;
+		} else if (ret < 0) {
+			pr_err("PCI: Can't parse resource_alignment parameter: %s\n",
+			       p);
+			break;
 		}
+
 		if (*p != ';' && *p != ',') {
 			/* End of param or invalid format */
 			break;
-- 
cgit v1.2.3


From 45db33709ccc7330c55fc6751c96468de407f2ac Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Mon, 30 Jul 2018 10:18:38 -0600
Subject: PCI: Allow specifying devices using a base bus and path of devfns
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When specifying PCI devices on the kernel command line using a
bus/device/function address, bus numbers can change when adding or
replacing a device, changing motherboard firmware, or applying kernel
parameters like "pci=assign-buses".  When bus numbers change, it's likely
the command line tweak will be applied to the wrong device.

Therefore, it is useful to be able to specify devices with a base bus
number and the path of devfns needed to get to it, similar to the "device
scope" structure in the Intel VT-d spec, Section 8.3.1.

Thus, we add an option to specify devices in the following format:

  [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*

The path can be any segment within the PCI hierarchy of any length and
determined through the use of 'lspci -t'.  When specified this way, it is
less likely that a renumbered bus will result in a valid device
specification and the tweak won't be applied to the wrong device.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
[bhelgaas: use "device" instead of "slot" in documentation since that's the
usual language in the PCI specs]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Stephen Bates <sbates@raithlin.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
 Documentation/admin-guide/kernel-parameters.txt |   8 +-
 drivers/pci/pci.c                               | 118 +++++++++++++++++++-----
 2 files changed, 103 insertions(+), 23 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index ab36fb34ed01..4fa4c9ff04ae 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3000,7 +3000,7 @@
 				or a set of devices (<pci_dev>). These are
 				specified in one of the following formats:
 
-				[<domain>:]<bus>:<device>.<func>
+				[<domain>:]<bus>:<dev>.<func>[/<dev>.<func>]*
 				pci:<vendor>:<device>[:<subvendor>:<subdevice>]
 
 				Note: the first format specifies a PCI
@@ -3009,7 +3009,11 @@
 				firmware changes, or due to changes caused
 				by other kernel parameters. If the
 				domain is left unspecified, it is
-				taken to be zero. The second format
+				taken to be zero. Optionally, a path
+				to a device through multiple device/function
+				addresses can be specified after the base
+				address (this is more robust against
+				renumbering issues).  The second format
 				selects devices using IDs from the
 				configuration space which may match multiple
 				devices in the system.
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 1574b2da25e7..a6c38b15ac33 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -191,6 +191,89 @@ void __iomem *pci_ioremap_wc_bar(struct pci_dev *pdev, int bar)
 EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
 #endif
 
+/**
+ * pci_dev_str_match_path - test if a path string matches a device
+ * @dev:    the PCI device to test
+ * @p:      string to match the device against
+ * @endptr: pointer to the string after the match
+ *
+ * Test if a string (typically from a kernel parameter) formatted as a
+ * path of device/function addresses matches a PCI device. The string must
+ * be of the form:
+ *
+ *   [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
+ *
+ * A path for a device can be obtained using 'lspci -t'.  Using a path
+ * is more robust against bus renumbering than using only a single bus,
+ * device and function address.
+ *
+ * Returns 1 if the string matches the device, 0 if it does not and
+ * a negative error code if it fails to parse the string.
+ */
+static int pci_dev_str_match_path(struct pci_dev *dev, const char *path,
+				  const char **endptr)
+{
+	int ret;
+	int seg, bus, slot, func;
+	char *wpath, *p;
+	char end;
+
+	*endptr = strchrnul(path, ';');
+
+	wpath = kmemdup_nul(path, *endptr - path, GFP_KERNEL);
+	if (!wpath)
+		return -ENOMEM;
+
+	while (1) {
+		p = strrchr(wpath, '/');
+		if (!p)
+			break;
+		ret = sscanf(p, "/%x.%x%c", &slot, &func, &end);
+		if (ret != 2) {
+			ret = -EINVAL;
+			goto free_and_exit;
+		}
+
+		if (dev->devfn != PCI_DEVFN(slot, func)) {
+			ret = 0;
+			goto free_and_exit;
+		}
+
+		/*
+		 * Note: we don't need to get a reference to the upstream
+		 * bridge because we hold a reference to the top level
+		 * device which should hold a reference to the bridge,
+		 * and so on.
+		 */
+		dev = pci_upstream_bridge(dev);
+		if (!dev) {
+			ret = 0;
+			goto free_and_exit;
+		}
+
+		*p = 0;
+	}
+
+	ret = sscanf(wpath, "%x:%x:%x.%x%c", &seg, &bus, &slot,
+		     &func, &end);
+	if (ret != 4) {
+		seg = 0;
+		ret = sscanf(wpath, "%x:%x.%x%c", &bus, &slot, &func, &end);
+		if (ret != 3) {
+			ret = -EINVAL;
+			goto free_and_exit;
+		}
+	}
+
+	ret = (seg == pci_domain_nr(dev->bus) &&
+	       bus == dev->bus->number &&
+	       dev->devfn == PCI_DEVFN(slot, func));
+
+free_and_exit:
+	kfree(wpath);
+	return ret;
+}
+
 /**
  * pci_dev_str_match - test if a string matches a device
  * @dev:    the PCI device to test
@@ -200,13 +283,16 @@ EXPORT_SYMBOL_GPL(pci_ioremap_wc_bar);
  * Test if a string (typically from a kernel parameter) matches a specified
  * PCI device. The string may be of one of the following formats:
  *
- *   [<domain>:]<bus>:<device>.<func>
+ *   [<domain>:]<bus>:<device>.<func>[/<device>.<func>]*
  *   pci:<vendor>:<device>[:<subvendor>:<subdevice>]
  *
  * The first format specifies a PCI bus/device/function address which
  * may change if new hardware is inserted, if motherboard firmware changes,
  * or due to changes caused in kernel parameters. If the domain is
- * left unspecified, it is taken to be 0.
+ * left unspecified, it is taken to be 0.  In order to be robust against
+ * bus renumbering issues, a path of PCI device/function numbers may be used
+ * to address the specific device.  The path for a device can be determined
+ * through the use of 'lspci -t'.
  *
  * The second format matches devices using IDs in the configuration
  * space which may match multiple devices in the system. A value of 0
@@ -222,7 +308,7 @@ static int pci_dev_str_match(struct pci_dev *dev, const char *p,
 			     const char **endptr)
 {
 	int ret;
-	int seg, bus, slot, func, count;
+	int count;
 	unsigned short vendor, device, subsystem_vendor, subsystem_device;
 
 	if (strncmp(p, "pci:", 4) == 0) {
@@ -248,25 +334,15 @@ static int pci_dev_str_match(struct pci_dev *dev, const char *p,
 		    (!subsystem_device ||
 			    subsystem_device == dev->subsystem_device))
 			goto found;
-
 	} else {
-		/* PCI Bus, Device, Function IDs are specified */
-		ret = sscanf(p, "%x:%x:%x.%x%n", &seg, &bus, &slot,
-			     &func, &count);
-		if (ret != 4) {
-			seg = 0;
-			ret = sscanf(p, "%x:%x.%x%n", &bus, &slot,
-				     &func, &count);
-			if (ret != 3)
-				return -EINVAL;
-		}
-
-		p += count;
-
-		if (seg == pci_domain_nr(dev->bus) &&
-		    bus == dev->bus->number &&
-		    slot == PCI_SLOT(dev->devfn) &&
-		    func == PCI_FUNC(dev->devfn))
+		/*
+		 * PCI Bus, Device, Function IDs are specified
+		 *  (optionally, may include a path of devfns following it)
+		 */
+		ret = pci_dev_str_match_path(dev, p, &p);
+		if (ret < 0)
+			return ret;
+		else if (ret)
 			goto found;
 	}
 
-- 
cgit v1.2.3


From 4d99f6602cb552fb58db0c3b1d935bb6fa017f24 Mon Sep 17 00:00:00 2001
From: Andrei Vagin <avagin@gmail.com>
Date: Wed, 8 Aug 2018 20:07:35 -0700
Subject: net: allow to call netif_reset_xps_queues() under cpus_read_lock

The definition of static_key_slow_inc() has cpus_read_lock in place. In the
virtio_net driver, XPS queues are initialized after setting the queue:cpu
affinity in virtnet_set_affinity() which is already protected within
cpus_read_lock. Lockdep prints a warning when we are trying to acquire
cpus_read_lock when it is already held.

This patch adds an ability to call __netif_set_xps_queue under
cpus_read_lock().
Acked-by: Jason Wang <jasowang@redhat.com>

============================================
WARNING: possible recursive locking detected
4.18.0-rc3-next-20180703+ #1 Not tainted
--------------------------------------------
swapper/0/1 is trying to acquire lock:
00000000cf973d46 (cpu_hotplug_lock.rw_sem){++++}, at: static_key_slow_inc+0xe/0x20

but task is already holding lock:
00000000cf973d46 (cpu_hotplug_lock.rw_sem){++++}, at: init_vqs+0x513/0x5a0

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(cpu_hotplug_lock.rw_sem);
  lock(cpu_hotplug_lock.rw_sem);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

3 locks held by swapper/0/1:
 #0: 00000000244bc7da (&dev->mutex){....}, at: __driver_attach+0x5a/0x110
 #1: 00000000cf973d46 (cpu_hotplug_lock.rw_sem){++++}, at: init_vqs+0x513/0x5a0
 #2: 000000005cd8463f (xps_map_mutex){+.+.}, at: __netif_set_xps_queue+0x8d/0xc60

v2: move cpus_read_lock() out of __netif_set_xps_queue()

Cc: "Nambiar, Amritha" <amritha.nambiar@intel.com>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Jason Wang <jasowang@redhat.com>
Fixes: 8af2c06ff4b1 ("net-sysfs: Add interface for Rx queue(s) map per Tx queue")

Signed-off-by: Andrei Vagin <avagin@gmail.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c |  4 +++-
 net/core/dev.c           | 20 +++++++++++++++-----
 net/core/net-sysfs.c     |  4 ++++
 3 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 62311dde6e71..39a7f4452587 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1903,9 +1903,11 @@ static void virtnet_set_affinity(struct virtnet_info *vi)
 
 	i = 0;
 	for_each_online_cpu(cpu) {
+		const unsigned long *mask = cpumask_bits(cpumask_of(cpu));
+
 		virtqueue_set_affinity(vi->rq[i].vq, cpu);
 		virtqueue_set_affinity(vi->sq[i].vq, cpu);
-		netif_set_xps_queue(vi->dev, cpumask_of(cpu), i);
+		__netif_set_xps_queue(vi->dev, mask, i, false);
 		i++;
 	}
 
diff --git a/net/core/dev.c b/net/core/dev.c
index f68122f0ab02..325fc5088370 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2176,6 +2176,7 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
 	if (!static_key_false(&xps_needed))
 		return;
 
+	cpus_read_lock();
 	mutex_lock(&xps_map_mutex);
 
 	if (static_key_false(&xps_rxqs_needed)) {
@@ -2199,10 +2200,11 @@ static void netif_reset_xps_queues(struct net_device *dev, u16 offset,
 
 out_no_maps:
 	if (static_key_enabled(&xps_rxqs_needed))
-		static_key_slow_dec(&xps_rxqs_needed);
+		static_key_slow_dec_cpuslocked(&xps_rxqs_needed);
 
-	static_key_slow_dec(&xps_needed);
+	static_key_slow_dec_cpuslocked(&xps_needed);
 	mutex_unlock(&xps_map_mutex);
+	cpus_read_unlock();
 }
 
 static void netif_reset_xps_queues_gt(struct net_device *dev, u16 index)
@@ -2250,6 +2252,7 @@ static struct xps_map *expand_xps_map(struct xps_map *map, int attr_index,
 	return new_map;
 }
 
+/* Must be called under cpus_read_lock */
 int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 			  u16 index, bool is_rxqs_map)
 {
@@ -2317,9 +2320,9 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	if (!new_dev_maps)
 		goto out_no_new_maps;
 
-	static_key_slow_inc(&xps_needed);
+	static_key_slow_inc_cpuslocked(&xps_needed);
 	if (is_rxqs_map)
-		static_key_slow_inc(&xps_rxqs_needed);
+		static_key_slow_inc_cpuslocked(&xps_rxqs_needed);
 
 	for (j = -1; j = netif_attrmask_next(j, possible_mask, nr_ids),
 	     j < nr_ids;) {
@@ -2448,11 +2451,18 @@ error:
 	kfree(new_dev_maps);
 	return -ENOMEM;
 }
+EXPORT_SYMBOL_GPL(__netif_set_xps_queue);
 
 int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 			u16 index)
 {
-	return __netif_set_xps_queue(dev, cpumask_bits(mask), index, false);
+	int ret;
+
+	cpus_read_lock();
+	ret =  __netif_set_xps_queue(dev, cpumask_bits(mask), index, false);
+	cpus_read_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL(netif_set_xps_queue);
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 0a95bcf64cdc..bd67c4d0fcfd 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -26,6 +26,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
+#include <linux/cpu.h>
 
 #include "net-sysfs.h"
 
@@ -1400,7 +1401,10 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
 		return err;
 	}
 
+	cpus_read_lock();
 	err = __netif_set_xps_queue(dev, mask, index, true);
+	cpus_read_unlock();
+
 	kfree(mask);
 	return err ? : len;
 }
-- 
cgit v1.2.3


From 36d2f761b5aa688567b6aebdc6d68e73682275d4 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Thu, 9 Aug 2018 12:32:03 +0530
Subject: cxgb4: update 1.20.8.0 as the latest firmware supported

Change t4fw_version.h to update latest firmware version
number to 1.20.8.0.

Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
index 4eb15ceddca3..a844296135b4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h
@@ -36,8 +36,8 @@
 #define __T4FW_VERSION_H__
 
 #define T4FW_VERSION_MAJOR 0x01
-#define T4FW_VERSION_MINOR 0x13
-#define T4FW_VERSION_MICRO 0x01
+#define T4FW_VERSION_MINOR 0x14
+#define T4FW_VERSION_MICRO 0x08
 #define T4FW_VERSION_BUILD 0x00
 
 #define T4FW_MIN_VERSION_MAJOR 0x01
@@ -45,8 +45,8 @@
 #define T4FW_MIN_VERSION_MICRO 0x00
 
 #define T5FW_VERSION_MAJOR 0x01
-#define T5FW_VERSION_MINOR 0x13
-#define T5FW_VERSION_MICRO 0x01
+#define T5FW_VERSION_MINOR 0x14
+#define T5FW_VERSION_MICRO 0x08
 #define T5FW_VERSION_BUILD 0x00
 
 #define T5FW_MIN_VERSION_MAJOR 0x00
@@ -54,8 +54,8 @@
 #define T5FW_MIN_VERSION_MICRO 0x00
 
 #define T6FW_VERSION_MAJOR 0x01
-#define T6FW_VERSION_MINOR 0x13
-#define T6FW_VERSION_MICRO 0x01
+#define T6FW_VERSION_MINOR 0x14
+#define T6FW_VERSION_MICRO 0x08
 #define T6FW_VERSION_BUILD 0x00
 
 #define T6FW_MIN_VERSION_MAJOR 0x00
-- 
cgit v1.2.3


From 22f20a110321efb7cde3e87ae99862e1036ca285 Mon Sep 17 00:00:00 2001
From: Paul Burton <paul.burton@mips.com>
Date: Thu, 9 Aug 2018 14:43:42 -0700
Subject: MIPS: Remove remnants of UASM_ISA

Commit 33679a50370d ("MIPS: uasm: Remove needless ISA abstraction")
removed use of the MIPS_ISA preprocessor macro, but left a couple of
unused definitions of it behind.

Remove the dead code.

Signed-off-by: Paul Burton <paul.burton@mips.com>
---
 arch/mips/mm/uasm-micromips.c | 1 -
 arch/mips/mm/uasm-mips.c      | 1 -
 2 files changed, 2 deletions(-)

diff --git a/arch/mips/mm/uasm-micromips.c b/arch/mips/mm/uasm-micromips.c
index 9bb6baa45da3..24e5b0d06899 100644
--- a/arch/mips/mm/uasm-micromips.c
+++ b/arch/mips/mm/uasm-micromips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_MICROMIPS
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f
diff --git a/arch/mips/mm/uasm-mips.c b/arch/mips/mm/uasm-mips.c
index 9fea6c6bbf49..60ceb93c71a0 100644
--- a/arch/mips/mm/uasm-mips.c
+++ b/arch/mips/mm/uasm-mips.c
@@ -19,7 +19,6 @@
 #include <asm/inst.h>
 #include <asm/elf.h>
 #include <asm/bugs.h>
-#define UASM_ISA	_UASM_ISA_CLASSIC
 #include <asm/uasm.h>
 
 #define RS_MASK		0x1f
-- 
cgit v1.2.3


From aaca43fda742223e4f62bd73e13055f5364e9a9b Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Mon, 30 Jul 2018 10:18:40 -0600
Subject: PCI: Add "pci=disable_acs_redir=" parameter for peer-to-peer support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To support peer-to-peer traffic on a segment of the PCI hierarchy, we must
disable the ACS redirect bits for select PCI bridges.  The bridges must be
selected before the devices are discovered by the kernel and the IOMMU
groups created.  Therefore, add a kernel command line parameter to specify
devices which must have their ACS bits disabled.

The new parameter takes a list of devices separated by a semicolon.  Each
device specified will have its ACS redirect bits disabled.  This is
similar to the existing 'resource_alignment' parameter.

The ACS Request P2P Request Redirect, P2P Completion Redirect and P2P
Egress Control bits are disabled, which is sufficient to always allow
passing P2P traffic uninterrupted.  The bits are set after the kernel
(optionally) enables the ACS bits itself.  It is also done regardless of
whether the kernel or platform firmware sets the bits.

If the user tries to disable the ACS redirect for a device without the ACS
capability, print a warning to dmesg.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
[bhelgaas: reorder to add the generic code first and move the
device-specific quirk to subsequent patches]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Stephen Bates <sbates@raithlin.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Christian König <christian.koenig@amd.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  9 +++
 drivers/pci/pci.c                               | 73 ++++++++++++++++++++++++-
 2 files changed, 80 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 4fa4c9ff04ae..d5c27d947c2e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -3192,6 +3192,15 @@
 				Adding the window is slightly risky (it may
 				conflict with unreported devices), so this
 				taints the kernel.
+		disable_acs_redir=<pci_dev>[; ...]
+				Specify one or more PCI devices (in the format
+				specified above) separated by semicolons.
+				Each device specified will have the PCI ACS
+				redirect capabilities forced off which will
+				allow P2P traffic between devices through
+				bridges without forcing it upstream. Note:
+				this removes isolation between devices and
+				may put more devices in an IOMMU group.
 
 	pcie_aspm=	[PCIE] Forcibly enable or disable PCIe Active State Power
 			Management.
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index a6c38b15ac33..822577d9b39e 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2982,6 +2982,63 @@ void pci_request_acs(void)
 	pci_acs_enable = 1;
 }
 
+static const char *disable_acs_redir_param;
+
+/**
+ * pci_disable_acs_redir - disable ACS redirect capabilities
+ * @dev: the PCI device
+ *
+ * For only devices specified in the disable_acs_redir parameter.
+ */
+static void pci_disable_acs_redir(struct pci_dev *dev)
+{
+	int ret = 0;
+	const char *p;
+	int pos;
+	u16 ctrl;
+
+	if (!disable_acs_redir_param)
+		return;
+
+	p = disable_acs_redir_param;
+	while (*p) {
+		ret = pci_dev_str_match(dev, p, &p);
+		if (ret < 0) {
+			pr_info_once("PCI: Can't parse disable_acs_redir parameter: %s\n",
+				     disable_acs_redir_param);
+
+			break;
+		} else if (ret == 1) {
+			/* Found a match */
+			break;
+		}
+
+		if (*p != ';' && *p != ',') {
+			/* End of param or invalid format */
+			break;
+		}
+		p++;
+	}
+
+	if (ret != 1)
+		return;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos) {
+		pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n");
+		return;
+	}
+
+	pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl);
+
+	/* P2P Request & Completion Redirect */
+	ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+	pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl);
+
+	pci_info(dev, "disabled ACS redirect\n");
+}
+
 /**
  * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites
  * @dev: the PCI device
@@ -3021,12 +3078,22 @@ static void pci_std_enable_acs(struct pci_dev *dev)
 void pci_enable_acs(struct pci_dev *dev)
 {
 	if (!pci_acs_enable)
-		return;
+		goto disable_acs_redir;
 
 	if (!pci_dev_specific_enable_acs(dev))
-		return;
+		goto disable_acs_redir;
 
 	pci_std_enable_acs(dev);
+
+disable_acs_redir:
+	/*
+	 * Note: pci_disable_acs_redir() must be called even if ACS was not
+	 * enabled by the kernel because it may have been enabled by
+	 * platform firmware.  So if we are told to disable it, we should
+	 * always disable it after setting the kernel's default
+	 * preferences.
+	 */
+	pci_disable_acs_redir(dev);
 }
 
 static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags)
@@ -5966,6 +6033,8 @@ static int __init pci_setup(char *str)
 				pcie_bus_config = PCIE_BUS_PEER2PEER;
 			} else if (!strncmp(str, "pcie_scan_all", 13)) {
 				pci_add_flags(PCI_SCAN_ALL_PCIE_DEVS);
+			} else if (!strncmp(str, "disable_acs_redir=", 18)) {
+				disable_acs_redir_param = str + 18;
 			} else {
 				printk(KERN_ERR "PCI: Unknown option `%s'\n",
 						str);
-- 
cgit v1.2.3


From 3b269185c19268027ac79388b03c9d7322518e4c Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Thu, 9 Aug 2018 16:45:47 -0500
Subject: PCI: Convert device-specific ACS quirks from NULL termination to
 ARRAY_SIZE

Convert the search for device-specific ACS enable quirks from searching a
NULL-terminated array to iterating through the array, which is always
fixed-size anyway.  No functional change intended.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
[bhelgaas: changelog, split to separate patch for reviewability]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/pci/quirks.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index f439de848658..823d8e4b4b37 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4560,20 +4560,20 @@ static const struct pci_dev_enable_acs {
 } pci_dev_enable_acs[] = {
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_pch_acs },
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_spt_pch_acs },
-	{ 0 }
 };
 
 int pci_dev_specific_enable_acs(struct pci_dev *dev)
 {
-	const struct pci_dev_enable_acs *i;
-	int ret;
+	const struct pci_dev_enable_acs *p;
+	int i, ret;
 
-	for (i = pci_dev_enable_acs; i->enable_acs; i++) {
-		if ((i->vendor == dev->vendor ||
-		     i->vendor == (u16)PCI_ANY_ID) &&
-		    (i->device == dev->device ||
-		     i->device == (u16)PCI_ANY_ID)) {
-			ret = i->enable_acs(dev);
+	for (i = 0; i < ARRAY_SIZE(pci_dev_enable_acs); i++) {
+		p = &pci_dev_enable_acs[i];
+		if ((p->vendor == dev->vendor ||
+		     p->vendor == (u16)PCI_ANY_ID) &&
+		    (p->device == dev->device ||
+		     p->device == (u16)PCI_ANY_ID)) {
+			ret = p->enable_acs(dev);
 			if (ret >= 0)
 				return ret;
 		}
-- 
cgit v1.2.3


From 73c47ddef29b5869a2221e93cefdb56fd8263718 Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Thu, 9 Aug 2018 16:51:43 -0500
Subject: PCI: Add device-specific ACS Redirect disable infrastructure

Intel Sunrise Point (SPT) PCH hardware has an implementation of the ACS
bits that does not comply with the PCIe standard.  To deal with this we
need device-specific quirks to disable ACS redirection.

Add a new pci_dev_specific_disable_acs_redir() quirk and a new
.disable_acs_redir() function pointer for use by non-compliant devices.  No
functional change intended.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
[bhelgaas: split to separate patch, move
pci_dev_specific_disable_acs_redir() declarations to drivers/pci/pci.h]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/pci/pci.c    |  3 +++
 drivers/pci/pci.h    |  5 +++++
 drivers/pci/quirks.c | 43 +++++++++++++++++++++++++++++++++++--------
 3 files changed, 43 insertions(+), 8 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 822577d9b39e..17d8de109556 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3023,6 +3023,9 @@ static void pci_disable_acs_redir(struct pci_dev *dev)
 	if (ret != 1)
 		return;
 
+	if (!pci_dev_specific_disable_acs_redir(dev))
+		return;
+
 	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
 	if (!pos) {
 		pci_warn(dev, "cannot disable ACS redirect for this hardware as it does not have ACS capabilities\n");
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index a1224fef3409..04f5035d12c6 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -355,6 +355,7 @@ void pci_enable_acs(struct pci_dev *dev);
 #ifdef CONFIG_PCI_QUIRKS
 int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
 int pci_dev_specific_enable_acs(struct pci_dev *dev);
+int pci_dev_specific_disable_acs_redir(struct pci_dev *dev);
 #else
 static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
 					       u16 acs_flags)
@@ -365,6 +366,10 @@ static inline int pci_dev_specific_enable_acs(struct pci_dev *dev)
 {
 	return -ENOTTY;
 }
+static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
+{
+	return -ENOTTY;
+}
 #endif
 
 /* PCI error reporting and recovery */
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 823d8e4b4b37..4f79631159eb 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4553,26 +4553,32 @@ static int pci_quirk_enable_intel_spt_pch_acs(struct pci_dev *dev)
 	return 0;
 }
 
-static const struct pci_dev_enable_acs {
+static const struct pci_dev_acs_ops {
 	u16 vendor;
 	u16 device;
 	int (*enable_acs)(struct pci_dev *dev);
-} pci_dev_enable_acs[] = {
-	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_pch_acs },
-	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID, pci_quirk_enable_intel_spt_pch_acs },
+	int (*disable_acs_redir)(struct pci_dev *dev);
+} pci_dev_acs_ops[] = {
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+	    .enable_acs = pci_quirk_enable_intel_pch_acs,
+	},
+	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
+	    .enable_acs = pci_quirk_enable_intel_spt_pch_acs,
+	},
 };
 
 int pci_dev_specific_enable_acs(struct pci_dev *dev)
 {
-	const struct pci_dev_enable_acs *p;
+	const struct pci_dev_acs_ops *p;
 	int i, ret;
 
-	for (i = 0; i < ARRAY_SIZE(pci_dev_enable_acs); i++) {
-		p = &pci_dev_enable_acs[i];
+	for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) {
+		p = &pci_dev_acs_ops[i];
 		if ((p->vendor == dev->vendor ||
 		     p->vendor == (u16)PCI_ANY_ID) &&
 		    (p->device == dev->device ||
-		     p->device == (u16)PCI_ANY_ID)) {
+		     p->device == (u16)PCI_ANY_ID) &&
+		    p->enable_acs) {
 			ret = p->enable_acs(dev);
 			if (ret >= 0)
 				return ret;
@@ -4582,6 +4588,27 @@ int pci_dev_specific_enable_acs(struct pci_dev *dev)
 	return -ENOTTY;
 }
 
+int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
+{
+	const struct pci_dev_acs_ops *p;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(pci_dev_acs_ops); i++) {
+		p = &pci_dev_acs_ops[i];
+		if ((p->vendor == dev->vendor ||
+		     p->vendor == (u16)PCI_ANY_ID) &&
+		    (p->device == dev->device ||
+		     p->device == (u16)PCI_ANY_ID) &&
+		    p->disable_acs_redir) {
+			ret = p->disable_acs_redir(dev);
+			if (ret >= 0)
+				return ret;
+		}
+	}
+
+	return -ENOTTY;
+}
+
 /*
  * The PCI capabilities list for Intel DH895xCC VFs (device ID 0x0443) with
  * QuickAssist Technology (QAT) is prematurely terminated in hardware.  The
-- 
cgit v1.2.3


From 10dbc9fedcf151ab794f5e22d4f34f1eff01a08f Mon Sep 17 00:00:00 2001
From: Logan Gunthorpe <logang@deltatee.com>
Date: Thu, 9 Aug 2018 17:09:17 -0500
Subject: PCI: Add ACS Redirect disable quirk for Intel Sunrise Point

Intel Sunrise Point PCH hardware has an implementation of the ACS bits that
does not comply with the PCIe standard.  Add a device-specific quirk,
pci_quirk_disable_intel_spt_pch_acs_redir() to disable ACS Redirection on
this system.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
[bhelgaas: changelog, split to separate patch]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/pci/quirks.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 4f79631159eb..dc2ee0de3c6b 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4553,6 +4553,30 @@ static int pci_quirk_enable_intel_spt_pch_acs(struct pci_dev *dev)
 	return 0;
 }
 
+static int pci_quirk_disable_intel_spt_pch_acs_redir(struct pci_dev *dev)
+{
+	int pos;
+	u32 cap, ctrl;
+
+	if (!pci_quirk_intel_spt_pch_acs_match(dev))
+		return -ENOTTY;
+
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS);
+	if (!pos)
+		return -ENOTTY;
+
+	pci_read_config_dword(dev, pos + PCI_ACS_CAP, &cap);
+	pci_read_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, &ctrl);
+
+	ctrl &= ~(PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_EC);
+
+	pci_write_config_dword(dev, pos + INTEL_SPT_ACS_CTRL, ctrl);
+
+	pci_info(dev, "Intel SPT PCH root port workaround: disabled ACS redirect\n");
+
+	return 0;
+}
+
 static const struct pci_dev_acs_ops {
 	u16 vendor;
 	u16 device;
@@ -4564,6 +4588,7 @@ static const struct pci_dev_acs_ops {
 	},
 	{ PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
 	    .enable_acs = pci_quirk_enable_intel_spt_pch_acs,
+	    .disable_acs_redir = pci_quirk_disable_intel_spt_pch_acs_redir,
 	},
 };
 
-- 
cgit v1.2.3


From b24df3e30cbf48255db866720fb71f14bf9d2f39 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 8 Aug 2018 15:07:45 +1000
Subject: cifs: update receive_encrypted_standard to handle compounded
 responses

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/cifsglob.h  |  5 +++-
 fs/cifs/connect.c   | 82 ++++++++++++++++++++++++++++++++---------------------
 fs/cifs/smb2ops.c   | 61 +++++++++++++++++++++++++++++++++------
 fs/cifs/transport.c |  2 --
 4 files changed, 107 insertions(+), 43 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 41803d374da0..0c9ab62c3df4 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -76,6 +76,9 @@
 #define SMB_ECHO_INTERVAL_MAX 600
 #define SMB_ECHO_INTERVAL_DEFAULT 60
 
+/* maximum number of PDUs in one compound */
+#define MAX_COMPOUND 5
+
 /*
  * Default number of credits to keep available for SMB3.
  * This value is chosen somewhat arbitrarily. The Windows client
@@ -458,7 +461,7 @@ struct smb_version_operations {
 				 struct smb_rqst *, struct smb_rqst *);
 	int (*is_transform_hdr)(void *buf);
 	int (*receive_transform)(struct TCP_Server_Info *,
-				 struct mid_q_entry **);
+				 struct mid_q_entry **, char **, int *);
 	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
 			    enum securityEnum);
 	int (*next_header)(char *);
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index d9bd10d295a9..c832a8a1970a 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -850,13 +850,14 @@ cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 static int
 cifs_demultiplex_thread(void *p)
 {
-	int length;
+	int i, num_mids, length;
 	struct TCP_Server_Info *server = p;
 	unsigned int pdu_length;
 	unsigned int next_offset;
 	char *buf = NULL;
 	struct task_struct *task_to_wake = NULL;
-	struct mid_q_entry *mid_entry;
+	struct mid_q_entry *mids[MAX_COMPOUND];
+	char *bufs[MAX_COMPOUND];
 
 	current->flags |= PF_MEMALLOC;
 	cifs_dbg(FYI, "Demultiplex PID: %d\n", task_pid_nr(current));
@@ -923,58 +924,75 @@ next_pdu:
 				server->pdu_size = next_offset;
 		}
 
-		mid_entry = NULL;
+		memset(mids, 0, sizeof(mids));
+		memset(bufs, 0, sizeof(bufs));
+		num_mids = 0;
+
 		if (server->ops->is_transform_hdr &&
 		    server->ops->receive_transform &&
 		    server->ops->is_transform_hdr(buf)) {
 			length = server->ops->receive_transform(server,
-								&mid_entry);
+								mids,
+								bufs,
+								&num_mids);
 		} else {
-			mid_entry = server->ops->find_mid(server, buf);
+			mids[0] = server->ops->find_mid(server, buf);
+			bufs[0] = buf;
+			if (mids[0])
+				num_mids = 1;
 
-			if (!mid_entry || !mid_entry->receive)
-				length = standard_receive3(server, mid_entry);
+			if (!mids[0] || !mids[0]->receive)
+				length = standard_receive3(server, mids[0]);
 			else
-				length = mid_entry->receive(server, mid_entry);
+				length = mids[0]->receive(server, mids[0]);
 		}
 
 		if (length < 0) {
-			if (mid_entry)
-				cifs_mid_q_entry_release(mid_entry);
+			for (i = 0; i < num_mids; i++)
+				if (mids[i])
+					cifs_mid_q_entry_release(mids[i]);
 			continue;
 		}
 
 		if (server->large_buf)
 			buf = server->bigbuf;
 
+
 		server->lstrp = jiffies;
-		if (mid_entry != NULL) {
-			mid_entry->resp_buf_size = server->pdu_size;
-			if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
-			     mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
-					server->ops->handle_cancelled_mid)
-				server->ops->handle_cancelled_mid(
-							mid_entry->resp_buf,
-							server);
 
-			if (!mid_entry->multiRsp || mid_entry->multiEnd)
-				mid_entry->callback(mid_entry);
+		for (i = 0; i < num_mids; i++) {
+			if (mids[i] != NULL) {
+				mids[i]->resp_buf_size = server->pdu_size;
+				if ((mids[i]->mid_flags & MID_WAIT_CANCELLED) &&
+				    mids[i]->mid_state == MID_RESPONSE_RECEIVED &&
+				    server->ops->handle_cancelled_mid)
+					server->ops->handle_cancelled_mid(
+							mids[i]->resp_buf,
+							server);
 
-			cifs_mid_q_entry_release(mid_entry);
-		} else if (server->ops->is_oplock_break &&
-			   server->ops->is_oplock_break(buf, server)) {
-			cifs_dbg(FYI, "Received oplock break\n");
-		} else {
-			cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
-				 atomic_read(&midCount));
-			cifs_dump_mem("Received Data is: ", buf,
-				      HEADER_SIZE(server));
+				if (!mids[i]->multiRsp || mids[i]->multiEnd)
+					mids[i]->callback(mids[i]);
+
+				cifs_mid_q_entry_release(mids[i]);
+			} else if (server->ops->is_oplock_break &&
+				   server->ops->is_oplock_break(bufs[i],
+								server)) {
+				cifs_dbg(FYI, "Received oplock break\n");
+			} else {
+				cifs_dbg(VFS, "No task to wake, unknown frame "
+					 "received! NumMids %d\n",
+					 atomic_read(&midCount));
+				cifs_dump_mem("Received Data is: ", bufs[i],
+					      HEADER_SIZE(server));
 #ifdef CONFIG_CIFS_DEBUG2
-			if (server->ops->dump_detail)
-				server->ops->dump_detail(buf, server);
-			cifs_dump_mids(server);
+				if (server->ops->dump_detail)
+					server->ops->dump_detail(bufs[i],
+								 server);
+				cifs_dump_mids(server);
 #endif /* CIFS_DEBUG2 */
+			}
 		}
+
 		if (pdu_length > server->pdu_size) {
 			if (!allocate_buffers(server))
 				continue;
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index ebc13ebebddf..d23715062c8e 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -2942,13 +2942,20 @@ discard_data:
 
 static int
 receive_encrypted_standard(struct TCP_Server_Info *server,
-			   struct mid_q_entry **mid)
+			   struct mid_q_entry **mids, char **bufs,
+			   int *num_mids)
 {
-	int length;
+	int ret, length;
 	char *buf = server->smallbuf;
+	char *tmpbuf;
+	struct smb2_sync_hdr *shdr;
 	unsigned int pdu_length = server->pdu_size;
 	unsigned int buf_size;
 	struct mid_q_entry *mid_entry;
+	int next_is_large;
+	char *next_buffer = NULL;
+
+	*num_mids = 0;
 
 	/* switch to large buffer if too big for a small one */
 	if (pdu_length > MAX_CIFS_SMALL_BUFFER_SIZE) {
@@ -2969,24 +2976,61 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 	if (length)
 		return length;
 
+	next_is_large = server->large_buf;
+ one_more:
+	shdr = (struct smb2_sync_hdr *)buf;
+	if (shdr->NextCommand) {
+		if (next_is_large) {
+			tmpbuf = server->bigbuf;
+			next_buffer = (char *)cifs_buf_get();
+		} else {
+			tmpbuf = server->smallbuf;
+			next_buffer = (char *)cifs_small_buf_get();
+		}
+		memcpy(next_buffer,
+		       tmpbuf + le32_to_cpu(shdr->NextCommand),
+		       pdu_length - le32_to_cpu(shdr->NextCommand));
+	}
+
 	mid_entry = smb2_find_mid(server, buf);
 	if (mid_entry == NULL)
 		cifs_dbg(FYI, "mid not found\n");
 	else {
 		cifs_dbg(FYI, "mid found\n");
 		mid_entry->decrypted = true;
+		mid_entry->resp_buf_size = server->pdu_size;
 	}
 
-	*mid = mid_entry;
+	if (*num_mids >= MAX_COMPOUND) {
+		cifs_dbg(VFS, "too many PDUs in compound\n");
+		return -1;
+	}
+	bufs[*num_mids] = buf;
+	mids[(*num_mids)++] = mid_entry;
 
 	if (mid_entry && mid_entry->handle)
-		return mid_entry->handle(server, mid_entry);
+		ret = mid_entry->handle(server, mid_entry);
+	else
+		ret = cifs_handle_standard(server, mid_entry);
+
+	if (ret == 0 && shdr->NextCommand) {
+		pdu_length -= le32_to_cpu(shdr->NextCommand);
+		server->large_buf = next_is_large;
+		if (next_is_large)
+			server->bigbuf = next_buffer;
+		else
+			server->smallbuf = next_buffer;
+
+		buf += le32_to_cpu(shdr->NextCommand);
+		goto one_more;
+	}
 
-	return cifs_handle_standard(server, mid_entry);
+	return ret;
 }
 
 static int
-smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
+smb3_receive_transform(struct TCP_Server_Info *server,
+		       struct mid_q_entry **mids, char **bufs, int *num_mids)
 {
 	char *buf = server->smallbuf;
 	unsigned int pdu_length = server->pdu_size;
@@ -3009,10 +3053,11 @@ smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
 		return -ECONNABORTED;
 	}
 
+	/* TODO: add support for compounds containing READ. */
 	if (pdu_length > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
-		return receive_encrypted_read(server, mid);
+		return receive_encrypted_read(server, &mids[0]);
 
-	return receive_encrypted_standard(server, mid);
+	return receive_encrypted_standard(server, mids, bufs, num_mids);
 }
 
 int
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index c53c0908d4c6..78f96fa3d7d9 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -383,8 +383,6 @@ smbd_done:
 	return rc;
 }
 
-#define MAX_COMPOUND 5
-
 static int
 smb_send_rqst(struct TCP_Server_Info *server, int num_rqst,
 	      struct smb_rqst *rqst, int flags)
-- 
cgit v1.2.3


From 730928c8f4be88e9d6a027a16b1e8fa9c59fc077 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Wed, 8 Aug 2018 15:07:49 +1000
Subject: cifs: update smb2_queryfs() to use compounding

Change smb2_queryfs() to use a Create/QueryInfo/Close compound request.

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Paulo Alcantara <palcantara@suse.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/smb2ops.c   | 106 +++++++++++++++++++++++++++++++++++++++++++++++++---
 fs/cifs/smb2pdu.c   |  41 ++++++++++----------
 fs/cifs/smb2pdu.h   |   4 ++
 fs/cifs/smb2proto.h |   6 +++
 4 files changed, 131 insertions(+), 26 deletions(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index d23715062c8e..15c7cbde2f39 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1524,15 +1524,66 @@ smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid,
 				 CIFS_CACHE_READ(cinode) ? 1 : 0);
 }
 
+static void
+smb2_set_related(struct smb_rqst *rqst)
+{
+	struct smb2_sync_hdr *shdr;
+
+	shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+	shdr->Flags |= SMB2_FLAGS_RELATED_OPERATIONS;
+}
+
+char smb2_padding[7] = {0, 0, 0, 0, 0, 0, 0};
+
+static void
+smb2_set_next_command(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+{
+	struct smb2_sync_hdr *shdr;
+	unsigned long len = smb_rqst_len(server, rqst);
+
+	/* SMB headers in a compound are 8 byte aligned. */
+	if (len & 7) {
+		rqst->rq_iov[rqst->rq_nvec].iov_base = smb2_padding;
+		rqst->rq_iov[rqst->rq_nvec].iov_len = 8 - (len & 7);
+		rqst->rq_nvec++;
+		len = smb_rqst_len(server, rqst);
+	}
+
+	shdr = (struct smb2_sync_hdr *)(rqst->rq_iov[0].iov_base);
+	shdr->NextCommand = cpu_to_le32(len);
+}
+
 static int
 smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	     struct kstatfs *buf)
 {
-	int rc;
+	struct smb2_query_info_rsp *rsp;
+	struct smb2_fs_full_size_info *info = NULL;
+	struct smb_rqst rqst[3];
+	int resp_buftype[3];
+	struct kvec rsp_iov[3];
+	struct kvec open_iov[5]; /* 4 + potential padding. */
+	struct kvec qi_iov[1];
+	struct kvec close_iov[1];
+	struct cifs_ses *ses = tcon->ses;
+	struct TCP_Server_Info *server = ses->server;
 	__le16 srch_path = 0; /* Null - open root of share */
 	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
 	struct cifs_open_parms oparms;
 	struct cifs_fid fid;
+	int flags = 0;
+	int rc;
+
+	if (smb3_encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	memset(rqst, 0, sizeof(rqst));
+	memset(resp_buftype, 0, sizeof(resp_buftype));
+	memset(rsp_iov, 0, sizeof(rsp_iov));
+
+	memset(&open_iov, 0, sizeof(open_iov));
+	rqst[0].rq_iov = open_iov;
+	rqst[0].rq_nvec = 4;
 
 	oparms.tcon = tcon;
 	oparms.desired_access = FILE_READ_ATTRIBUTES;
@@ -1541,13 +1592,56 @@ smb2_queryfs(const unsigned int xid, struct cifs_tcon *tcon,
 	oparms.fid = &fid;
 	oparms.reconnect = false;
 
-	rc = SMB2_open(xid, &oparms, &srch_path, &oplock, NULL, NULL, NULL);
+	rc = SMB2_open_init(tcon, &rqst[0], &oplock, &oparms, &srch_path);
 	if (rc)
-		return rc;
+		goto qfs_exit;
+	smb2_set_next_command(server, &rqst[0]);
+
+	memset(&qi_iov, 0, sizeof(qi_iov));
+	rqst[1].rq_iov = qi_iov;
+	rqst[1].rq_nvec = 1;
+
+	rc = SMB2_query_info_init(tcon, &rqst[1], COMPOUND_FID, COMPOUND_FID,
+				  FS_FULL_SIZE_INFORMATION,
+				  SMB2_O_INFO_FILESYSTEM, 0,
+				  sizeof(struct smb2_fs_full_size_info));
+	if (rc)
+		goto qfs_exit;
+	smb2_set_next_command(server, &rqst[1]);
+	smb2_set_related(&rqst[1]);
+
+	memset(&close_iov, 0, sizeof(close_iov));
+	rqst[2].rq_iov = close_iov;
+	rqst[2].rq_nvec = 1;
+
+	rc = SMB2_close_init(tcon, &rqst[2], COMPOUND_FID, COMPOUND_FID);
+	if (rc)
+		goto qfs_exit;
+	smb2_set_related(&rqst[2]);
+
+	rc = compound_send_recv(xid, ses, flags, 3, rqst,
+				resp_buftype, rsp_iov);
+	if (rc)
+		goto qfs_exit;
+
+	rsp = (struct smb2_query_info_rsp *)rsp_iov[1].iov_base;
 	buf->f_type = SMB2_MAGIC_NUMBER;
-	rc = SMB2_QFS_info(xid, tcon, fid.persistent_fid, fid.volatile_fid,
-			   buf);
-	SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	info = (struct smb2_fs_full_size_info *)(
+		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength),
+			       &rsp_iov[1],
+			       sizeof(struct smb2_fs_full_size_info));
+	if (!rc)
+		smb2_copy_fs_info_to_kstatfs(info, buf);
+
+qfs_exit:
+	SMB2_open_free(&rqst[0]);
+	SMB2_query_info_free(&rqst[1]);
+	SMB2_close_free(&rqst[2]);
+	free_rsp_buf(resp_buftype[0], rsp_iov[0].iov_base);
+	free_rsp_buf(resp_buftype[1], rsp_iov[1].iov_base);
+	free_rsp_buf(resp_buftype[2], rsp_iov[2].iov_base);
 	return rc;
 }
 
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index a5009a1c9bce..faf2b779e5cb 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -80,7 +80,7 @@ static const int smb2_req_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ 24 /* BB this is 36 for LEASE_BREAK variant */
 };
 
-static int smb3_encryption_required(const struct cifs_tcon *tcon)
+int smb3_encryption_required(const struct cifs_tcon *tcon)
 {
 	if (!tcon)
 		return 0;
@@ -2182,7 +2182,8 @@ SMB2_open_free(struct smb_rqst *rqst)
 
 	cifs_small_buf_release(rqst->rq_iov[0].iov_base);
 	for (i = 1; i < rqst->rq_nvec; i++)
-		kfree(rqst->rq_iov[i].iov_base);
+		if (rqst->rq_iov[i].iov_base != smb2_padding)
+			kfree(rqst->rq_iov[i].iov_base);
 }
 
 int
@@ -2528,9 +2529,9 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	return SMB2_close_flags(xid, tcon, persistent_fid, volatile_fid, 0);
 }
 
-static int
-validate_iov(unsigned int offset, unsigned int buffer_length,
-	     struct kvec *iov, unsigned int min_buf_size)
+int
+smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
+		  struct kvec *iov, unsigned int min_buf_size)
 {
 	unsigned int smb_len = iov->iov_len;
 	char *end_of_smb = smb_len + (char *)iov->iov_base;
@@ -2574,7 +2575,7 @@ validate_and_copy_iov(unsigned int offset, unsigned int buffer_length,
 	if (!data)
 		return -EINVAL;
 
-	rc = validate_iov(offset, buffer_length, iov, minbufsize);
+	rc = smb2_validate_iov(offset, buffer_length, iov, minbufsize);
 	if (rc)
 		return rc;
 
@@ -3646,9 +3647,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 		goto qdir_exit;
 	}
 
-	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			  info_buf_size);
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       info_buf_size);
 	if (rc)
 		goto qdir_exit;
 
@@ -3950,9 +3951,9 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
-static void
-copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
-			struct kstatfs *kst)
+void
+smb2_copy_fs_info_to_kstatfs(struct smb2_fs_full_size_info *pfs_inf,
+			     struct kstatfs *kst)
 {
 	kst->f_bsize = le32_to_cpu(pfs_inf->BytesPerSector) *
 			  le32_to_cpu(pfs_inf->SectorsPerAllocationUnit);
@@ -4054,9 +4055,9 @@ SMB311_posix_qfs_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	info = (FILE_SYSTEM_POSIX_INFO *)(
 		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
-	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			  sizeof(FILE_SYSTEM_POSIX_INFO));
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       sizeof(FILE_SYSTEM_POSIX_INFO));
 	if (!rc)
 		copy_posix_fs_info_to_kstatfs(info, fsdata);
 
@@ -4102,11 +4103,11 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 
 	info = (struct smb2_fs_full_size_info *)(
 		le16_to_cpu(rsp->OutputBufferOffset) + (char *)rsp);
-	rc = validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
-			  le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
-			  sizeof(struct smb2_fs_full_size_info));
+	rc = smb2_validate_iov(le16_to_cpu(rsp->OutputBufferOffset),
+			       le32_to_cpu(rsp->OutputBufferLength), &rsp_iov,
+			       sizeof(struct smb2_fs_full_size_info));
 	if (!rc)
-		copy_fs_info_to_kstatfs(info, fsdata);
+		smb2_copy_fs_info_to_kstatfs(info, fsdata);
 
 qfsinf_exit:
 	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
@@ -4166,7 +4167,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rsp_len = le32_to_cpu(rsp->OutputBufferLength);
 	offset = le16_to_cpu(rsp->OutputBufferOffset);
-	rc = validate_iov(offset, rsp_len, &rsp_iov, min_len);
+	rc = smb2_validate_iov(offset, rsp_len, &rsp_iov, min_len);
 	if (rc)
 		goto qfsattr_exit;
 
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index ecb0feeac844..cf37c2f3f3b8 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -153,6 +153,8 @@ struct smb2_transform_hdr {
  *
  */
 
+#define COMPOUND_FID 0xFFFFFFFFFFFFFFFFULL
+
 #define SMB2_ERROR_STRUCTURE_SIZE2 cpu_to_le16(9)
 
 struct smb2_err_rsp {
@@ -1373,4 +1375,6 @@ struct smb2_file_eof_info { /* encoding of request for level 10 */
 	__le64 EndOfFile; /* new end of file value */
 } __packed; /* level 20 Set */
 
+extern char smb2_padding[7];
+
 #endif				/* _SMB2PDU_H */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index 57bdd2711974..b4076577eeb7 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -229,6 +229,12 @@ extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
 extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
 					enum securityEnum);
+extern int smb3_encryption_required(const struct cifs_tcon *tcon);
+extern int smb2_validate_iov(unsigned int offset, unsigned int buffer_length,
+			     struct kvec *iov, unsigned int min_buf_size);
+extern void smb2_copy_fs_info_to_kstatfs(
+	 struct smb2_fs_full_size_info *pfs_inf,
+	 struct kstatfs *kst);
 extern int smb311_crypto_shash_allocate(struct TCP_Server_Info *server);
 extern int smb311_update_preauth_hash(struct cifs_ses *ses,
 				      struct kvec *iov, int nvec);
-- 
cgit v1.2.3


From e02789a53d71334b067ad72eee5d4e88a0158083 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Thu, 9 Aug 2018 14:33:12 -0500
Subject: smb3: enumerating snapshots was leaving part of the data off end

When enumerating snapshots, the last few bytes of the final
snapshot could be left off since we were miscalculating the
length returned (leaving off the sizeof struct SRV_SNAPSHOT_ARRAY)
See MS-SMB2 section 2.2.32.2. In addition fixup the length used
to allow smaller buffer to be passed in, in order to allow
returning the size of the whole snapshot array more easily.

Sample userspace output with a kernel patched with this
(mounted to a Windows volume with two snapshots).
Before this patch, the second snapshot would be missing a
few bytes at the end.

~/cifs-2.6# ~/enum-snapshots /mnt/file
press enter to issue the ioctl to retrieve snapshot information ...

size of snapshot array = 102
Num snapshots: 2 Num returned: 2 Array Size: 102

Snapshot 0:@GMT-2018.06.30-19.34.17
Snapshot 1:@GMT-2018.06.30-19.33.37

CC: Stable <stable@vger.kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/smb2ops.c | 34 +++++++++++++++++++++++++++-------
 1 file changed, 27 insertions(+), 7 deletions(-)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 15c7cbde2f39..7869ea4f6fab 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -1369,6 +1369,13 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 
 }
 
+/* GMT Token is @GMT-YYYY.MM.DD-HH.MM.SS Unicode which is 48 bytes + null */
+#define GMT_TOKEN_SIZE 50
+
+/*
+ * Input buffer contains (empty) struct smb_snapshot array with size filled in
+ * For output see struct SRV_SNAPSHOT_ARRAY in MS-SMB2 section 2.2.32.2
+ */
 static int
 smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 		   struct cifsFileInfo *cfile, void __user *ioc_buf)
@@ -1398,14 +1405,27 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 			kfree(retbuf);
 			return rc;
 		}
-		if (snapshot_in.snapshot_array_size < sizeof(struct smb_snapshot_array)) {
-			rc = -ERANGE;
-			kfree(retbuf);
-			return rc;
-		}
 
-		if (ret_data_len > snapshot_in.snapshot_array_size)
-			ret_data_len = snapshot_in.snapshot_array_size;
+		/*
+		 * Check for min size, ie not large enough to fit even one GMT
+		 * token (snapshot).  On the first ioctl some users may pass in
+		 * smaller size (or zero) to simply get the size of the array
+		 * so the user space caller can allocate sufficient memory
+		 * and retry the ioctl again with larger array size sufficient
+		 * to hold all of the snapshot GMT tokens on the second try.
+		 */
+		if (snapshot_in.snapshot_array_size < GMT_TOKEN_SIZE)
+			ret_data_len = sizeof(struct smb_snapshot_array);
+
+		/*
+		 * We return struct SRV_SNAPSHOT_ARRAY, followed by
+		 * the snapshot array (of 50 byte GMT tokens) each
+		 * representing an available previous version of the data
+		 */
+		if (ret_data_len > (snapshot_in.snapshot_array_size +
+					sizeof(struct smb_snapshot_array)))
+			ret_data_len = snapshot_in.snapshot_array_size +
+					sizeof(struct smb_snapshot_array);
 
 		if (copy_to_user(ioc_buf, retbuf, ret_data_len))
 			rc = -EFAULT;
-- 
cgit v1.2.3


From 07d981ad4cf1e78361c6db1c28ee5ba105f96cc1 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@redhat.com>
Date: Fri, 10 Aug 2018 08:31:10 +0100
Subject: x86/microcode: Allow late microcode loading with SMT disabled

The kernel unnecessarily prevents late microcode loading when SMT is
disabled.  It should be safe to allow it if all the primary threads are
online.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 arch/x86/kernel/cpu/microcode/core.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 08286269fd24..b9bc8a1a584e 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -509,12 +509,20 @@ static struct platform_device	*microcode_pdev;
 
 static int check_online_cpus(void)
 {
-	if (num_online_cpus() == num_present_cpus())
-		return 0;
+	unsigned int cpu;
 
-	pr_err("Not all CPUs online, aborting microcode update.\n");
+	/*
+	 * Make sure all CPUs are online.  It's fine for SMT to be disabled if
+	 * all the primary threads are still online.
+	 */
+	for_each_present_cpu(cpu) {
+		if (topology_is_primary_thread(cpu) && !cpu_online(cpu)) {
+			pr_err("Not all CPUs online, aborting microcode update.\n");
+			return -EINVAL;
+		}
+	}
 
-	return -EINVAL;
+	return 0;
 }
 
 static atomic_t late_cpus_in;
-- 
cgit v1.2.3


From 563a53f3906a6b43692498e5b3ae891fac93a4af Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Fri, 10 Aug 2018 11:13:52 +0200
Subject: spi: davinci: fix a NULL pointer dereference

On non-OF systems spi->controlled_data may be NULL. This causes a NULL
pointer derefence on dm365-evm.

Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
Cc: stable@vger.kernel.org
---
 drivers/spi/spi-davinci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/spi/spi-davinci.c b/drivers/spi/spi-davinci.c
index 60d59b003aa4..4ffc0f495be8 100644
--- a/drivers/spi/spi-davinci.c
+++ b/drivers/spi/spi-davinci.c
@@ -217,7 +217,7 @@ static void davinci_spi_chipselect(struct spi_device *spi, int value)
 	pdata = &dspi->pdata;
 
 	/* program delay transfers if tx_delay is non zero */
-	if (spicfg->wdelay)
+	if (spicfg && spicfg->wdelay)
 		spidat1 |= SPIDAT1_WDEL;
 
 	/*
-- 
cgit v1.2.3


From eb91e4d4db06adef06e7f50c02813c13c6ca5a5b Mon Sep 17 00:00:00 2001
From: Björn Töpel <bjorn.topel@intel.com>
Date: Fri, 10 Aug 2018 11:28:02 +0200
Subject: Revert "xdp: add NULL pointer check in __xdp_return()"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This reverts commit 36e0f12bbfd3016f495904b35e41c5711707509f.

The reverted commit adds a WARN to check against NULL entries in the
mem_id_ht rhashtable. Any kernel path implementing the XDP (generic or
driver) fast path is required to make a paired
xdp_rxq_info_reg/xdp_rxq_info_unreg call for proper function. In
addition, a driver using a different allocation scheme than the
default MEM_TYPE_PAGE_SHARED is required to additionally call
xdp_rxq_info_reg_mem_model.

For MEM_TYPE_ZERO_COPY, an xdp_rxq_info_reg_mem_model call ensures
that the mem_id_ht rhashtable has a properly inserted allocator id. If
not, this would be a driver bug. A NULL pointer kernel OOPS is
preferred to the WARN.

Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 net/core/xdp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/core/xdp.c b/net/core/xdp.c
index c013b836006b..57285383ed00 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -348,8 +348,7 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		rcu_read_lock();
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
-		if (!WARN_ON_ONCE(!xa))
-			xa->zc_alloc->free(xa->zc_alloc, handle);
+		xa->zc_alloc->free(xa->zc_alloc, handle);
 		rcu_read_unlock();
 	default:
 		/* Not possible, checked in xdp_rxq_info_reg_mem_model() */
-- 
cgit v1.2.3


From 11395686586bc9ca867b3f27501fd6c48244187a Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 10 Aug 2018 14:02:57 +0200
Subject: samples/bpf: add Paul Hsieh's (LGPL 2.1) hash function SuperFastHash

Adjusted function call API to take an initval. This allow the API
user to set the initial value, as a seed. This could also be used for
inputting the previous hash.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/hash_func01.h | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 samples/bpf/hash_func01.h

diff --git a/samples/bpf/hash_func01.h b/samples/bpf/hash_func01.h
new file mode 100644
index 000000000000..38255812e376
--- /dev/null
+++ b/samples/bpf/hash_func01.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: LGPL-2.1
+ *
+ * Based on Paul Hsieh's (LGPG 2.1) hash function
+ * From: http://www.azillionmonkeys.com/qed/hash.html
+ */
+
+#define get16bits(d) (*((const __u16 *) (d)))
+
+static __always_inline
+__u32 SuperFastHash (const char *data, int len, __u32 initval) {
+	__u32 hash = initval;
+	__u32 tmp;
+	int rem;
+
+	if (len <= 0 || data == NULL) return 0;
+
+	rem = len & 3;
+	len >>= 2;
+
+	/* Main loop */
+#pragma clang loop unroll(full)
+	for (;len > 0; len--) {
+		hash  += get16bits (data);
+		tmp    = (get16bits (data+2) << 11) ^ hash;
+		hash   = (hash << 16) ^ tmp;
+		data  += 2*sizeof (__u16);
+		hash  += hash >> 11;
+	}
+
+	/* Handle end cases */
+	switch (rem) {
+        case 3: hash += get16bits (data);
+                hash ^= hash << 16;
+                hash ^= ((signed char)data[sizeof (__u16)]) << 18;
+                hash += hash >> 11;
+                break;
+        case 2: hash += get16bits (data);
+                hash ^= hash << 11;
+                hash += hash >> 17;
+                break;
+        case 1: hash += (signed char)*data;
+                hash ^= hash << 10;
+                hash += hash >> 1;
+	}
+
+	/* Force "avalanching" of final 127 bits */
+	hash ^= hash << 3;
+	hash += hash >> 5;
+	hash ^= hash << 4;
+	hash += hash >> 17;
+	hash ^= hash << 25;
+	hash += hash >> 6;
+
+	return hash;
+}
-- 
cgit v1.2.3


From 1bca4e6b1863c0a006fde6a66720a87823109294 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <brouer@redhat.com>
Date: Fri, 10 Aug 2018 14:03:02 +0200
Subject: samples/bpf: xdp_redirect_cpu load balance like Suricata

This implement XDP CPU redirection load-balancing across available
CPUs, based on the hashing IP-pairs + L4-protocol.  This equivalent to
xdp-cpu-redirect feature in Suricata, which is inspired by the
Suricata 'ippair' hashing code.

An important property is that the hashing is flow symmetric, meaning
that if the source and destination gets swapped then the selected CPU
will remain the same.  This is helps locality by placing both directions
of a flows on the same CPU, in a forwarding/routing scenario.

The hashing INITVAL (15485863 the 10^6th prime number) was fairly
arbitrary choosen, but experiments with kernel tree pktgen scripts
(pktgen_sample04_many_flows.sh +pktgen_sample05_flow_per_thread.sh)
showed this improved the distribution.

This patch also change the default loaded XDP program to be this
load-balancer.  As based on different user feedback, this seems to be
the expected behavior of the sample xdp_redirect_cpu.

Link: https://github.com/OISF/suricata/commit/796ec08dd7a63
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 samples/bpf/xdp_redirect_cpu_kern.c | 103 ++++++++++++++++++++++++++++++++++++
 samples/bpf/xdp_redirect_cpu_user.c |   4 +-
 2 files changed, 105 insertions(+), 2 deletions(-)

diff --git a/samples/bpf/xdp_redirect_cpu_kern.c b/samples/bpf/xdp_redirect_cpu_kern.c
index 8cb703671b04..081ef4bb4fe3 100644
--- a/samples/bpf/xdp_redirect_cpu_kern.c
+++ b/samples/bpf/xdp_redirect_cpu_kern.c
@@ -13,6 +13,7 @@
 
 #include <uapi/linux/bpf.h>
 #include "bpf_helpers.h"
+#include "hash_func01.h"
 
 #define MAX_CPUS 12 /* WARNING - sync with _user.c */
 
@@ -461,6 +462,108 @@ int  xdp_prognum4_ddos_filter_pktgen(struct xdp_md *ctx)
 	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
 }
 
+/* Hashing initval */
+#define INITVAL 15485863
+
+static __always_inline
+u32 get_ipv4_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct iphdr *iph = data + nh_off;
+	u32 cpu_hash;
+
+	if (iph + 1 > data_end)
+		return 0;
+
+	cpu_hash = iph->saddr + iph->daddr;
+	cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + iph->protocol);
+
+	return cpu_hash;
+}
+
+static __always_inline
+u32 get_ipv6_hash_ip_pair(struct xdp_md *ctx, u64 nh_off)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ipv6hdr *ip6h = data + nh_off;
+	u32 cpu_hash;
+
+	if (ip6h + 1 > data_end)
+		return 0;
+
+	cpu_hash  = ip6h->saddr.s6_addr32[0] + ip6h->daddr.s6_addr32[0];
+	cpu_hash += ip6h->saddr.s6_addr32[1] + ip6h->daddr.s6_addr32[1];
+	cpu_hash += ip6h->saddr.s6_addr32[2] + ip6h->daddr.s6_addr32[2];
+	cpu_hash += ip6h->saddr.s6_addr32[3] + ip6h->daddr.s6_addr32[3];
+	cpu_hash = SuperFastHash((char *)&cpu_hash, 4, INITVAL + ip6h->nexthdr);
+
+	return cpu_hash;
+}
+
+/* Load-Balance traffic based on hashing IP-addrs + L4-proto.  The
+ * hashing scheme is symmetric, meaning swapping IP src/dest still hit
+ * same CPU.
+ */
+SEC("xdp_cpu_map5_lb_hash_ip_pairs")
+int  xdp_prognum5_lb_hash_ip_pairs(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data     = (void *)(long)ctx->data;
+	struct ethhdr *eth = data;
+	u8 ip_proto = IPPROTO_UDP;
+	struct datarec *rec;
+	u16 eth_proto = 0;
+	u64 l3_offset = 0;
+	u32 cpu_dest = 0;
+	u32 cpu_idx = 0;
+	u32 *cpu_lookup;
+	u32 *cpu_max;
+	u32 cpu_hash;
+	u32 key = 0;
+
+	/* Count RX packet in map */
+	rec = bpf_map_lookup_elem(&rx_cnt, &key);
+	if (!rec)
+		return XDP_ABORTED;
+	rec->processed++;
+
+	cpu_max = bpf_map_lookup_elem(&cpus_count, &key);
+	if (!cpu_max)
+		return XDP_ABORTED;
+
+	if (!(parse_eth(eth, data_end, &eth_proto, &l3_offset)))
+		return XDP_PASS; /* Just skip */
+
+	/* Hash for IPv4 and IPv6 */
+	switch (eth_proto) {
+	case ETH_P_IP:
+		cpu_hash = get_ipv4_hash_ip_pair(ctx, l3_offset);
+		break;
+	case ETH_P_IPV6:
+		cpu_hash = get_ipv6_hash_ip_pair(ctx, l3_offset);
+		break;
+	case ETH_P_ARP: /* ARP packet handled on CPU idx 0 */
+	default:
+		cpu_hash = 0;
+	}
+
+	/* Choose CPU based on hash */
+	cpu_idx = cpu_hash % *cpu_max;
+
+	cpu_lookup = bpf_map_lookup_elem(&cpus_available, &cpu_idx);
+	if (!cpu_lookup)
+		return XDP_ABORTED;
+	cpu_dest = *cpu_lookup;
+
+	if (cpu_dest >= MAX_CPUS) {
+		rec->issue++;
+		return XDP_ABORTED;
+	}
+
+	return bpf_redirect_map(&cpu_map, cpu_dest, 0);
+}
 
 char _license[] SEC("license") = "GPL";
 
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index f6efaefd485b..007710d7c748 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -22,7 +22,7 @@ static const char *__doc__ =
 #define MAX_CPUS 12 /* WARNING - sync with _kern.c */
 
 /* How many xdp_progs are defined in _kern.c */
-#define MAX_PROG 5
+#define MAX_PROG 6
 
 /* Wanted to get rid of bpf_load.h and fake-"libbpf.h" (and instead
  * use bpf/libbpf.h), but cannot as (currently) needed for XDP
@@ -567,7 +567,7 @@ int main(int argc, char **argv)
 	int added_cpus = 0;
 	int longindex = 0;
 	int interval = 2;
-	int prog_num = 0;
+	int prog_num = 5;
 	int add_cpu = -1;
 	__u32 qsize;
 	int opt;
-- 
cgit v1.2.3


From b0768a86585d4d951a30ff565f19598dbbd67897 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:09 +0900
Subject: net: Export skb_headers_offset_update

This is needed for veth XDP which does skb_copy_expand()-like operation.

v2:
- Drop skb_copy_header part because it has already been exported now.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/skbuff.h | 1 +
 net/core/skbuff.c      | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 7ebdf158a795..e93b157f526c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1038,6 +1038,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size,
 }
 
 struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src);
+void skb_headers_offset_update(struct sk_buff *skb, int off);
 int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask);
 struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority);
 void skb_copy_header(struct sk_buff *new, const struct sk_buff *old);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 8d574a88125d..c996c09d095f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -1291,7 +1291,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(skb_clone);
 
-static void skb_headers_offset_update(struct sk_buff *skb, int off)
+void skb_headers_offset_update(struct sk_buff *skb, int off)
 {
 	/* Only adjust this if it actually is csum_start rather than csum */
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
@@ -1305,6 +1305,7 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off)
 	skb->inner_network_header += off;
 	skb->inner_mac_header += off;
 }
+EXPORT_SYMBOL(skb_headers_offset_update);
 
 void skb_copy_header(struct sk_buff *new, const struct sk_buff *old)
 {
-- 
cgit v1.2.3


From 948d4f214fde43743c57aae0c708bff44f6345f2 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:10 +0900
Subject: veth: Add driver XDP

This is the basic implementation of veth driver XDP.

Incoming packets are sent from the peer veth device in the form of skb,
so this is generally doing the same thing as generic XDP.

This itself is not so useful, but a starting point to implement other
useful veth XDP features like TX and REDIRECT.

This introduces NAPI when XDP is enabled, because XDP is now heavily
relies on NAPI context. Use ptr_ring to emulate NIC ring. Tx function
enqueues packets to the ring and peer NAPI handler drains the ring.

Currently only one ring is allocated for each veth device, so it does
not scale on multiqueue env. This can be resolved by allocating rings
on the per-queue basis later.

Note that NAPI is not used but netif_rx is used when XDP is not loaded,
so this does not change the default behaviour.

v6:
- Check skb->len only when allocation is needed.
- Add __GFP_NOWARN to alloc_page() as it can be triggered by external
  events.

v3:
- Fix race on closing the device.
- Add extack messages in ndo_bpf.

v2:
- Squashed with the patch adding NAPI.
- Implement adjust_tail.
- Don't acquire consumer lock because it is guarded by NAPI.
- Make poll_controller noop since it is unnecessary.
- Register rxq_info on enabling XDP rather than on opening the device.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/veth.c | 374 ++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 367 insertions(+), 7 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index a69ad39ee57e..d3b9f10bea24 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -19,10 +19,18 @@
 #include <net/xfrm.h>
 #include <linux/veth.h>
 #include <linux/module.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/ptr_ring.h>
+#include <linux/skb_array.h>
+#include <linux/bpf_trace.h>
 
 #define DRV_NAME	"veth"
 #define DRV_VERSION	"1.0"
 
+#define VETH_RING_SIZE		256
+#define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
+
 struct pcpu_vstats {
 	u64			packets;
 	u64			bytes;
@@ -30,9 +38,16 @@ struct pcpu_vstats {
 };
 
 struct veth_priv {
+	struct napi_struct	xdp_napi;
+	struct net_device	*dev;
+	struct bpf_prog __rcu	*xdp_prog;
+	struct bpf_prog		*_xdp_prog;
 	struct net_device __rcu	*peer;
 	atomic64_t		dropped;
 	unsigned		requested_headroom;
+	bool			rx_notify_masked;
+	struct ptr_ring		xdp_ring;
+	struct xdp_rxq_info	xdp_rxq;
 };
 
 /*
@@ -98,11 +113,43 @@ static const struct ethtool_ops veth_ethtool_ops = {
 	.get_link_ksettings	= veth_get_link_ksettings,
 };
 
-static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
+/* general routines */
+
+static void __veth_xdp_flush(struct veth_priv *priv)
+{
+	/* Write ptr_ring before reading rx_notify_masked */
+	smp_mb();
+	if (!priv->rx_notify_masked) {
+		priv->rx_notify_masked = true;
+		napi_schedule(&priv->xdp_napi);
+	}
+}
+
+static int veth_xdp_rx(struct veth_priv *priv, struct sk_buff *skb)
+{
+	if (unlikely(ptr_ring_produce(&priv->xdp_ring, skb))) {
+		dev_kfree_skb_any(skb);
+		return NET_RX_DROP;
+	}
+
+	return NET_RX_SUCCESS;
+}
+
+static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb, bool xdp)
 {
 	struct veth_priv *priv = netdev_priv(dev);
+
+	return __dev_forward_skb(dev, skb) ?: xdp ?
+		veth_xdp_rx(priv, skb) :
+		netif_rx(skb);
+}
+
+static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct net_device *rcv;
 	int length = skb->len;
+	bool rcv_xdp = false;
 
 	rcu_read_lock();
 	rcv = rcu_dereference(priv->peer);
@@ -111,7 +158,10 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
-	if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
+	rcv_priv = netdev_priv(rcv);
+	rcv_xdp = rcu_access_pointer(rcv_priv->xdp_prog);
+
+	if (likely(veth_forward_skb(rcv, skb, rcv_xdp) == NET_RX_SUCCESS)) {
 		struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
 
 		u64_stats_update_begin(&stats->syncp);
@@ -122,14 +172,15 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 drop:
 		atomic64_inc(&priv->dropped);
 	}
+
+	if (rcv_xdp)
+		__veth_xdp_flush(rcv_priv);
+
 	rcu_read_unlock();
+
 	return NETDEV_TX_OK;
 }
 
-/*
- * general routines
- */
-
 static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
@@ -179,18 +230,254 @@ static void veth_set_multicast_list(struct net_device *dev)
 {
 }
 
+static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
+				      int buflen)
+{
+	struct sk_buff *skb;
+
+	if (!buflen) {
+		buflen = SKB_DATA_ALIGN(headroom + len) +
+			 SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+	}
+	skb = build_skb(head, buflen);
+	if (!skb)
+		return NULL;
+
+	skb_reserve(skb, headroom);
+	skb_put(skb, len);
+
+	return skb;
+}
+
+static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
+					struct sk_buff *skb)
+{
+	u32 pktlen, headroom, act, metalen;
+	void *orig_data, *orig_data_end;
+	struct bpf_prog *xdp_prog;
+	int mac_len, delta, off;
+	struct xdp_buff xdp;
+
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(priv->xdp_prog);
+	if (unlikely(!xdp_prog)) {
+		rcu_read_unlock();
+		goto out;
+	}
+
+	mac_len = skb->data - skb_mac_header(skb);
+	pktlen = skb->len + mac_len;
+	headroom = skb_headroom(skb) - mac_len;
+
+	if (skb_shared(skb) || skb_head_is_locked(skb) ||
+	    skb_is_nonlinear(skb) || headroom < XDP_PACKET_HEADROOM) {
+		struct sk_buff *nskb;
+		int size, head_off;
+		void *head, *start;
+		struct page *page;
+
+		size = SKB_DATA_ALIGN(VETH_XDP_HEADROOM + pktlen) +
+		       SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		if (size > PAGE_SIZE)
+			goto drop;
+
+		page = alloc_page(GFP_ATOMIC | __GFP_NOWARN);
+		if (!page)
+			goto drop;
+
+		head = page_address(page);
+		start = head + VETH_XDP_HEADROOM;
+		if (skb_copy_bits(skb, -mac_len, start, pktlen)) {
+			page_frag_free(head);
+			goto drop;
+		}
+
+		nskb = veth_build_skb(head,
+				      VETH_XDP_HEADROOM + mac_len, skb->len,
+				      PAGE_SIZE);
+		if (!nskb) {
+			page_frag_free(head);
+			goto drop;
+		}
+
+		skb_copy_header(nskb, skb);
+		head_off = skb_headroom(nskb) - skb_headroom(skb);
+		skb_headers_offset_update(nskb, head_off);
+		if (skb->sk)
+			skb_set_owner_w(nskb, skb->sk);
+		consume_skb(skb);
+		skb = nskb;
+	}
+
+	xdp.data_hard_start = skb->head;
+	xdp.data = skb_mac_header(skb);
+	xdp.data_end = xdp.data + pktlen;
+	xdp.data_meta = xdp.data;
+	xdp.rxq = &priv->xdp_rxq;
+	orig_data = xdp.data;
+	orig_data_end = xdp.data_end;
+
+	act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+	switch (act) {
+	case XDP_PASS:
+		break;
+	default:
+		bpf_warn_invalid_xdp_action(act);
+	case XDP_ABORTED:
+		trace_xdp_exception(priv->dev, xdp_prog, act);
+	case XDP_DROP:
+		goto drop;
+	}
+	rcu_read_unlock();
+
+	delta = orig_data - xdp.data;
+	off = mac_len + delta;
+	if (off > 0)
+		__skb_push(skb, off);
+	else if (off < 0)
+		__skb_pull(skb, -off);
+	skb->mac_header -= delta;
+	off = xdp.data_end - orig_data_end;
+	if (off != 0)
+		__skb_put(skb, off);
+	skb->protocol = eth_type_trans(skb, priv->dev);
+
+	metalen = xdp.data - xdp.data_meta;
+	if (metalen)
+		skb_metadata_set(skb, metalen);
+out:
+	return skb;
+drop:
+	rcu_read_unlock();
+	kfree_skb(skb);
+	return NULL;
+}
+
+static int veth_xdp_rcv(struct veth_priv *priv, int budget)
+{
+	int i, done = 0;
+
+	for (i = 0; i < budget; i++) {
+		struct sk_buff *skb = __ptr_ring_consume(&priv->xdp_ring);
+
+		if (!skb)
+			break;
+
+		skb = veth_xdp_rcv_skb(priv, skb);
+
+		if (skb)
+			napi_gro_receive(&priv->xdp_napi, skb);
+
+		done++;
+	}
+
+	return done;
+}
+
+static int veth_poll(struct napi_struct *napi, int budget)
+{
+	struct veth_priv *priv =
+		container_of(napi, struct veth_priv, xdp_napi);
+	int done;
+
+	done = veth_xdp_rcv(priv, budget);
+
+	if (done < budget && napi_complete_done(napi, done)) {
+		/* Write rx_notify_masked before reading ptr_ring */
+		smp_store_mb(priv->rx_notify_masked, false);
+		if (unlikely(!__ptr_ring_empty(&priv->xdp_ring))) {
+			priv->rx_notify_masked = true;
+			napi_schedule(&priv->xdp_napi);
+		}
+	}
+
+	return done;
+}
+
+static int veth_napi_add(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err;
+
+	err = ptr_ring_init(&priv->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
+	if (err)
+		return err;
+
+	netif_napi_add(dev, &priv->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
+	napi_enable(&priv->xdp_napi);
+
+	return 0;
+}
+
+static void veth_napi_del(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	napi_disable(&priv->xdp_napi);
+	netif_napi_del(&priv->xdp_napi);
+	priv->rx_notify_masked = false;
+	ptr_ring_cleanup(&priv->xdp_ring, __skb_array_destroy_skb);
+}
+
+static int veth_enable_xdp(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	int err;
+
+	if (!xdp_rxq_info_is_reg(&priv->xdp_rxq)) {
+		err = xdp_rxq_info_reg(&priv->xdp_rxq, dev, 0);
+		if (err < 0)
+			return err;
+
+		err = xdp_rxq_info_reg_mem_model(&priv->xdp_rxq,
+						 MEM_TYPE_PAGE_SHARED, NULL);
+		if (err < 0)
+			goto err;
+
+		err = veth_napi_add(dev);
+		if (err)
+			goto err;
+	}
+
+	rcu_assign_pointer(priv->xdp_prog, priv->_xdp_prog);
+
+	return 0;
+err:
+	xdp_rxq_info_unreg(&priv->xdp_rxq);
+
+	return err;
+}
+
+static void veth_disable_xdp(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	rcu_assign_pointer(priv->xdp_prog, NULL);
+	veth_napi_del(dev);
+	xdp_rxq_info_unreg(&priv->xdp_rxq);
+}
+
 static int veth_open(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
 	struct net_device *peer = rtnl_dereference(priv->peer);
+	int err;
 
 	if (!peer)
 		return -ENOTCONN;
 
+	if (priv->_xdp_prog) {
+		err = veth_enable_xdp(dev);
+		if (err)
+			return err;
+	}
+
 	if (peer->flags & IFF_UP) {
 		netif_carrier_on(dev);
 		netif_carrier_on(peer);
 	}
+
 	return 0;
 }
 
@@ -203,6 +490,9 @@ static int veth_close(struct net_device *dev)
 	if (peer)
 		netif_carrier_off(peer);
 
+	if (priv->_xdp_prog)
+		veth_disable_xdp(dev);
+
 	return 0;
 }
 
@@ -228,7 +518,7 @@ static void veth_dev_free(struct net_device *dev)
 static void veth_poll_controller(struct net_device *dev)
 {
 	/* veth only receives frames when its peer sends one
-	 * Since it's a synchronous operation, we are guaranteed
+	 * Since it has nothing to do with disabling irqs, we are guaranteed
 	 * never to have pending data when we poll for it so
 	 * there is nothing to do here.
 	 *
@@ -276,6 +566,72 @@ out:
 	rcu_read_unlock();
 }
 
+static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+			struct netlink_ext_ack *extack)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct bpf_prog *old_prog;
+	struct net_device *peer;
+	int err;
+
+	old_prog = priv->_xdp_prog;
+	priv->_xdp_prog = prog;
+	peer = rtnl_dereference(priv->peer);
+
+	if (prog) {
+		if (!peer) {
+			NL_SET_ERR_MSG_MOD(extack, "Cannot set XDP when peer is detached");
+			err = -ENOTCONN;
+			goto err;
+		}
+
+		if (dev->flags & IFF_UP) {
+			err = veth_enable_xdp(dev);
+			if (err) {
+				NL_SET_ERR_MSG_MOD(extack, "Setup for XDP failed");
+				goto err;
+			}
+		}
+	}
+
+	if (old_prog) {
+		if (!prog && dev->flags & IFF_UP)
+			veth_disable_xdp(dev);
+		bpf_prog_put(old_prog);
+	}
+
+	return 0;
+err:
+	priv->_xdp_prog = old_prog;
+
+	return err;
+}
+
+static u32 veth_xdp_query(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	const struct bpf_prog *xdp_prog;
+
+	xdp_prog = priv->_xdp_prog;
+	if (xdp_prog)
+		return xdp_prog->aux->id;
+
+	return 0;
+}
+
+static int veth_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return veth_xdp_set(dev, xdp->prog, xdp->extack);
+	case XDP_QUERY_PROG:
+		xdp->prog_id = veth_xdp_query(dev);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops veth_netdev_ops = {
 	.ndo_init            = veth_dev_init,
 	.ndo_open            = veth_open,
@@ -290,6 +646,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_get_iflink		= veth_get_iflink,
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
+	.ndo_bpf		= veth_xdp,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
@@ -451,10 +808,13 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	 */
 
 	priv = netdev_priv(dev);
+	priv->dev = dev;
 	rcu_assign_pointer(priv->peer, peer);
 
 	priv = netdev_priv(peer);
+	priv->dev = peer;
 	rcu_assign_pointer(priv->peer, dev);
+
 	return 0;
 
 err_register_dev:
-- 
cgit v1.2.3


From dc2248220a4aa61560c95aca98d4162095bd7e8a Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:11 +0900
Subject: veth: Avoid drops by oversized packets when XDP is enabled

Oversized packets including GSO packets can be dropped if XDP is
enabled on receiver side, so don't send such packets from peer.

Drop TSO and SCTP fragmentation features so that veth devices themselves
segment packets with XDP enabled. Also cap MTU accordingly.

v4:
- Don't auto-adjust MTU but cap max MTU.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/veth.c | 47 +++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 45 insertions(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index d3b9f10bea24..9edf104739da 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -543,6 +543,23 @@ static int veth_get_iflink(const struct net_device *dev)
 	return iflink;
 }
 
+static netdev_features_t veth_fix_features(struct net_device *dev,
+					   netdev_features_t features)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+	struct net_device *peer;
+
+	peer = rtnl_dereference(priv->peer);
+	if (peer) {
+		struct veth_priv *peer_priv = netdev_priv(peer);
+
+		if (peer_priv->_xdp_prog)
+			features &= ~NETIF_F_GSO_SOFTWARE;
+	}
+
+	return features;
+}
+
 static void veth_set_rx_headroom(struct net_device *dev, int new_hr)
 {
 	struct veth_priv *peer_priv, *priv = netdev_priv(dev);
@@ -572,6 +589,7 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	struct veth_priv *priv = netdev_priv(dev);
 	struct bpf_prog *old_prog;
 	struct net_device *peer;
+	unsigned int max_mtu;
 	int err;
 
 	old_prog = priv->_xdp_prog;
@@ -585,6 +603,15 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			goto err;
 		}
 
+		max_mtu = PAGE_SIZE - VETH_XDP_HEADROOM -
+			  peer->hard_header_len -
+			  SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
+		if (peer->mtu > max_mtu) {
+			NL_SET_ERR_MSG_MOD(extack, "Peer MTU is too large to set XDP");
+			err = -ERANGE;
+			goto err;
+		}
+
 		if (dev->flags & IFF_UP) {
 			err = veth_enable_xdp(dev);
 			if (err) {
@@ -592,14 +619,29 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 				goto err;
 			}
 		}
+
+		if (!old_prog) {
+			peer->hw_features &= ~NETIF_F_GSO_SOFTWARE;
+			peer->max_mtu = max_mtu;
+		}
 	}
 
 	if (old_prog) {
-		if (!prog && dev->flags & IFF_UP)
-			veth_disable_xdp(dev);
+		if (!prog) {
+			if (dev->flags & IFF_UP)
+				veth_disable_xdp(dev);
+
+			if (peer) {
+				peer->hw_features |= NETIF_F_GSO_SOFTWARE;
+				peer->max_mtu = ETH_MAX_MTU;
+			}
+		}
 		bpf_prog_put(old_prog);
 	}
 
+	if ((!!old_prog ^ !!prog) && peer)
+		netdev_update_features(peer);
+
 	return 0;
 err:
 	priv->_xdp_prog = old_prog;
@@ -644,6 +686,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_poll_controller	= veth_poll_controller,
 #endif
 	.ndo_get_iflink		= veth_get_iflink,
+	.ndo_fix_features	= veth_fix_features,
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
 	.ndo_bpf		= veth_xdp,
-- 
cgit v1.2.3


From a8d5b4ab353738e16e5f9d21ab1e3d44b37983d0 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:12 +0900
Subject: xdp: Helper function to clear kernel pointers in xdp_frame

xdp_frame has kernel pointers which should not be readable from bpf
programs. When we want to reuse xdp_frame region but it may be read by
bpf programs later, we can use this helper to clear kernel pointers.
This is more efficient than calling memset() for the entire struct.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/xdp.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/net/xdp.h b/include/net/xdp.h
index fcb033f51d8c..76b95256c266 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -84,6 +84,13 @@ struct xdp_frame {
 	struct net_device *dev_rx; /* used by cpumap */
 };
 
+/* Clear kernel pointers in xdp_frame */
+static inline void xdp_scrub_frame(struct xdp_frame *frame)
+{
+	frame->data = NULL;
+	frame->dev_rx = NULL;
+}
+
 /* Convert xdp_buff to xdp_frame */
 static inline
 struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
-- 
cgit v1.2.3


From 9fc8d518d9d590998209f2686e026a488f65d41e Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:13 +0900
Subject: veth: Handle xdp_frames in xdp napi ring

This is preparation for XDP TX and ndo_xdp_xmit.
This allows napi handler to handle xdp_frames through xdp ring as well
as sk_buff.

v8:
- Don't use xdp_frame pointer address to calculate skb->head and
  headroom.

v7:
- Use xdp_scrub_frame() instead of memset().

v3:
- Revert v2 change around rings and use a flag to differentiate skb and
  xdp_frame, since bulk skb xmit makes little performance difference
  for now.

v2:
- Use another ring instead of using flag to differentiate skb and
  xdp_frame. This approach makes bulk skb transmit possible in
  veth_xmit later.
- Clear xdp_frame feilds in skb->head.
- Implement adjust_tail.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/veth.c | 89 +++++++++++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 84 insertions(+), 5 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 9edf104739da..89f3059e603d 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -22,12 +22,12 @@
 #include <linux/bpf.h>
 #include <linux/filter.h>
 #include <linux/ptr_ring.h>
-#include <linux/skb_array.h>
 #include <linux/bpf_trace.h>
 
 #define DRV_NAME	"veth"
 #define DRV_VERSION	"1.0"
 
+#define VETH_XDP_FLAG		BIT(0)
 #define VETH_RING_SIZE		256
 #define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 
@@ -115,6 +115,24 @@ static const struct ethtool_ops veth_ethtool_ops = {
 
 /* general routines */
 
+static bool veth_is_xdp_frame(void *ptr)
+{
+	return (unsigned long)ptr & VETH_XDP_FLAG;
+}
+
+static void *veth_ptr_to_xdp(void *ptr)
+{
+	return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
+}
+
+static void veth_ptr_free(void *ptr)
+{
+	if (veth_is_xdp_frame(ptr))
+		xdp_return_frame(veth_ptr_to_xdp(ptr));
+	else
+		kfree_skb(ptr);
+}
+
 static void __veth_xdp_flush(struct veth_priv *priv)
 {
 	/* Write ptr_ring before reading rx_notify_masked */
@@ -249,6 +267,63 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
 	return skb;
 }
 
+static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
+					struct xdp_frame *frame)
+{
+	void *hard_start = frame->data - frame->headroom;
+	void *head = hard_start - sizeof(struct xdp_frame);
+	int len = frame->len, delta = 0;
+	struct bpf_prog *xdp_prog;
+	unsigned int headroom;
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+	xdp_prog = rcu_dereference(priv->xdp_prog);
+	if (likely(xdp_prog)) {
+		struct xdp_buff xdp;
+		u32 act;
+
+		xdp.data_hard_start = hard_start;
+		xdp.data = frame->data;
+		xdp.data_end = frame->data + frame->len;
+		xdp.data_meta = frame->data - frame->metasize;
+		xdp.rxq = &priv->xdp_rxq;
+
+		act = bpf_prog_run_xdp(xdp_prog, &xdp);
+
+		switch (act) {
+		case XDP_PASS:
+			delta = frame->data - xdp.data;
+			len = xdp.data_end - xdp.data;
+			break;
+		default:
+			bpf_warn_invalid_xdp_action(act);
+		case XDP_ABORTED:
+			trace_xdp_exception(priv->dev, xdp_prog, act);
+		case XDP_DROP:
+			goto err_xdp;
+		}
+	}
+	rcu_read_unlock();
+
+	headroom = sizeof(struct xdp_frame) + frame->headroom - delta;
+	skb = veth_build_skb(head, headroom, len, 0);
+	if (!skb) {
+		xdp_return_frame(frame);
+		goto err;
+	}
+
+	xdp_scrub_frame(frame);
+	skb->protocol = eth_type_trans(skb, priv->dev);
+err:
+	return skb;
+err_xdp:
+	rcu_read_unlock();
+	xdp_return_frame(frame);
+
+	return NULL;
+}
+
 static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 					struct sk_buff *skb)
 {
@@ -359,12 +434,16 @@ static int veth_xdp_rcv(struct veth_priv *priv, int budget)
 	int i, done = 0;
 
 	for (i = 0; i < budget; i++) {
-		struct sk_buff *skb = __ptr_ring_consume(&priv->xdp_ring);
+		void *ptr = __ptr_ring_consume(&priv->xdp_ring);
+		struct sk_buff *skb;
 
-		if (!skb)
+		if (!ptr)
 			break;
 
-		skb = veth_xdp_rcv_skb(priv, skb);
+		if (veth_is_xdp_frame(ptr))
+			skb = veth_xdp_rcv_one(priv, veth_ptr_to_xdp(ptr));
+		else
+			skb = veth_xdp_rcv_skb(priv, ptr);
 
 		if (skb)
 			napi_gro_receive(&priv->xdp_napi, skb);
@@ -417,7 +496,7 @@ static void veth_napi_del(struct net_device *dev)
 	napi_disable(&priv->xdp_napi);
 	netif_napi_del(&priv->xdp_napi);
 	priv->rx_notify_masked = false;
-	ptr_ring_cleanup(&priv->xdp_ring, __skb_array_destroy_skb);
+	ptr_ring_cleanup(&priv->xdp_ring, veth_ptr_free);
 }
 
 static int veth_enable_xdp(struct net_device *dev)
-- 
cgit v1.2.3


From af87a3aa1b5f397a2f5c99b97b000943c5177da7 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:14 +0900
Subject: veth: Add ndo_xdp_xmit

This allows NIC's XDP to redirect packets to veth. The destination veth
device enqueues redirected packets to the napi ring of its peer, then
they are processed by XDP on its peer veth device.
This can be thought as calling another XDP program by XDP program using
REDIRECT, when the peer enables driver XDP.

Note that when the peer veth device does not set driver xdp, redirected
packets will be dropped because the peer is not ready for NAPI.

v4:
- Don't use xdp_ok_fwd_dev() because checking IFF_UP is not necessary.
  Add comments about it and check only MTU.

v2:
- Drop the part converting xdp_frame into skb when XDP is not enabled.
- Implement bulk interface of ndo_xdp_xmit.
- Implement XDP_XMIT_FLUSH bit and drop ndo_xdp_flush.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/veth.c | 51 +++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 89f3059e603d..dbb693a7795e 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -17,6 +17,7 @@
 #include <net/rtnetlink.h>
 #include <net/dst.h>
 #include <net/xfrm.h>
+#include <net/xdp.h>
 #include <linux/veth.h>
 #include <linux/module.h>
 #include <linux/bpf.h>
@@ -125,6 +126,11 @@ static void *veth_ptr_to_xdp(void *ptr)
 	return (void *)((unsigned long)ptr & ~VETH_XDP_FLAG);
 }
 
+static void *veth_xdp_to_ptr(void *ptr)
+{
+	return (void *)((unsigned long)ptr | VETH_XDP_FLAG);
+}
+
 static void veth_ptr_free(void *ptr)
 {
 	if (veth_is_xdp_frame(ptr))
@@ -267,6 +273,50 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
 	return skb;
 }
 
+static int veth_xdp_xmit(struct net_device *dev, int n,
+			 struct xdp_frame **frames, u32 flags)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *rcv;
+	unsigned int max_len;
+	int i, drops = 0;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		return -ENXIO;
+
+	rcv_priv = netdev_priv(rcv);
+	/* Non-NULL xdp_prog ensures that xdp_ring is initialized on receive
+	 * side. This means an XDP program is loaded on the peer and the peer
+	 * device is up.
+	 */
+	if (!rcu_access_pointer(rcv_priv->xdp_prog))
+		return -ENXIO;
+
+	max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN;
+
+	spin_lock(&rcv_priv->xdp_ring.producer_lock);
+	for (i = 0; i < n; i++) {
+		struct xdp_frame *frame = frames[i];
+		void *ptr = veth_xdp_to_ptr(frame);
+
+		if (unlikely(frame->len > max_len ||
+			     __ptr_ring_produce(&rcv_priv->xdp_ring, ptr))) {
+			xdp_return_frame_rx_napi(frame);
+			drops++;
+		}
+	}
+	spin_unlock(&rcv_priv->xdp_ring.producer_lock);
+
+	if (flags & XDP_XMIT_FLUSH)
+		__veth_xdp_flush(rcv_priv);
+
+	return n - drops;
+}
+
 static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 					struct xdp_frame *frame)
 {
@@ -769,6 +819,7 @@ static const struct net_device_ops veth_netdev_ops = {
 	.ndo_features_check	= passthru_features_check,
 	.ndo_set_rx_headroom	= veth_set_rx_headroom,
 	.ndo_bpf		= veth_xdp,
+	.ndo_xdp_xmit		= veth_xdp_xmit,
 };
 
 #define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
-- 
cgit v1.2.3


From 0b19cc0a8694d4295383f88bc3441765875a57bc Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:15 +0900
Subject: bpf: Make redirect_info accessible from modules

We are going to add kern_flags field in redirect_info for kernel
internal use.
In order to avoid function call to access the flags, make redirect_info
accessible from modules. Also as it is now non-static, add prefix bpf_
to redirect_info.

v6:
- Fix sparse warning around EXPORT_SYMBOL.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/filter.h | 10 ++++++++++
 net/core/filter.c      | 29 +++++++++++------------------
 2 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index c73dd7396886..4717af8b95e6 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -537,6 +537,16 @@ struct sk_msg_buff {
 	struct list_head list;
 };
 
+struct bpf_redirect_info {
+	u32 ifindex;
+	u32 flags;
+	struct bpf_map *map;
+	struct bpf_map *map_to_flush;
+	unsigned long   map_owner;
+};
+
+DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
+
 /* Compute the linear packet data range [data, data_end) which
  * will be accessed by various program types (cls_bpf, act_bpf,
  * lwt, ...). Subsystems allowing direct data access must (!)
diff --git a/net/core/filter.c b/net/core/filter.c
index 587bbfbd7db3..2de7dd9f2a57 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2082,19 +2082,12 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 	.arg3_type      = ARG_ANYTHING,
 };
 
-struct redirect_info {
-	u32 ifindex;
-	u32 flags;
-	struct bpf_map *map;
-	struct bpf_map *map_to_flush;
-	unsigned long   map_owner;
-};
-
-static DEFINE_PER_CPU(struct redirect_info, redirect_info);
+DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
+EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 
 BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
 	if (unlikely(flags & ~(BPF_F_INGRESS)))
 		return TC_ACT_SHOT;
@@ -2107,7 +2100,7 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 
 int skb_do_redirect(struct sk_buff *skb)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct net_device *dev;
 
 	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex);
@@ -3200,7 +3193,7 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd,
 
 void xdp_do_flush_map(void)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct bpf_map *map = ri->map_to_flush;
 
 	ri->map_to_flush = NULL;
@@ -3245,7 +3238,7 @@ static inline bool xdp_map_invalid(const struct bpf_prog *xdp_prog,
 static int xdp_do_redirect_map(struct net_device *dev, struct xdp_buff *xdp,
 			       struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	u32 index = ri->ifindex;
@@ -3285,7 +3278,7 @@ err:
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	struct net_device *fwd;
 	u32 index = ri->ifindex;
 	int err;
@@ -3317,7 +3310,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       struct xdp_buff *xdp,
 				       struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	unsigned long map_owner = ri->map_owner;
 	struct bpf_map *map = ri->map;
 	u32 index = ri->ifindex;
@@ -3368,7 +3361,7 @@ err:
 int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 			    struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	u32 index = ri->ifindex;
 	struct net_device *fwd;
 	int err = 0;
@@ -3399,7 +3392,7 @@ EXPORT_SYMBOL_GPL(xdp_do_generic_redirect);
 
 BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
 	if (unlikely(flags))
 		return XDP_ABORTED;
@@ -3423,7 +3416,7 @@ static const struct bpf_func_proto bpf_xdp_redirect_proto = {
 BPF_CALL_4(bpf_xdp_redirect_map, struct bpf_map *, map, u32, ifindex, u64, flags,
 	   unsigned long, map_owner)
 {
-	struct redirect_info *ri = this_cpu_ptr(&redirect_info);
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
 	if (unlikely(flags))
 		return XDP_ABORTED;
-- 
cgit v1.2.3


From 2539650fadbf63a431e76535a9de7bff6ea5e409 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:16 +0900
Subject: xdp: Helpers for disabling napi_direct of xdp_return_frame

We need some mechanism to disable napi_direct on calling
xdp_return_frame_rx_napi() from some context.
When veth gets support of XDP_REDIRECT, it will redirects packets which
are redirected from other devices. On redirection veth will reuse
xdp_mem_info of the redirection source device to make return_frame work.
But in this case .ndo_xdp_xmit() called from veth redirection uses
xdp_mem_info which is not guarded by NAPI, because the .ndo_xdp_xmit()
is not called directly from the rxq which owns the xdp_mem_info.

This approach introduces a flag in bpf_redirect_info to indicate that
napi_direct should be disabled even when _rx_napi variant is used as
well as helper functions to use it.

A NAPI handler who wants to use this flag needs to call
xdp_set_return_frame_no_direct() before processing packets, and call
xdp_clear_return_frame_no_direct() after xdp_do_flush_map() before
exiting NAPI.

v4:
- Use bpf_redirect_info for storing the flag instead of xdp_mem_info to
  avoid per-frame copy cost.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/filter.h | 25 +++++++++++++++++++++++++
 net/core/xdp.c         |  6 ++++--
 2 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 4717af8b95e6..2b072dab32c0 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -543,10 +543,14 @@ struct bpf_redirect_info {
 	struct bpf_map *map;
 	struct bpf_map *map_to_flush;
 	unsigned long   map_owner;
+	u32 kern_flags;
 };
 
 DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
 
+/* flags for bpf_redirect_info kern_flags */
+#define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */
+
 /* Compute the linear packet data range [data, data_end) which
  * will be accessed by various program types (cls_bpf, act_bpf,
  * lwt, ...). Subsystems allowing direct data access must (!)
@@ -775,6 +779,27 @@ static inline bool bpf_dump_raw_ok(void)
 struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 
+static inline bool xdp_return_frame_no_direct(void)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT;
+}
+
+static inline void xdp_set_return_frame_no_direct(void)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT;
+}
+
+static inline void xdp_clear_return_frame_no_direct(void)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT;
+}
+
 static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
 				 unsigned int pktlen)
 {
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 57285383ed00..3dd99e1c04f5 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -330,10 +330,12 @@ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct,
 		/* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */
 		xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params);
 		page = virt_to_head_page(data);
-		if (xa)
+		if (xa) {
+			napi_direct &= !xdp_return_frame_no_direct();
 			page_pool_put_page(xa->page_pool, page, napi_direct);
-		else
+		} else {
 			put_page(page);
+		}
 		rcu_read_unlock();
 		break;
 	case MEM_TYPE_PAGE_SHARED:
-- 
cgit v1.2.3


From d1396004dd868642ea2596abe058d96dcf97990f Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:17 +0900
Subject: veth: Add XDP TX and REDIRECT

This allows further redirection of xdp_frames like

 NIC   -> veth--veth -> veth--veth
 (XDP)          (XDP)         (XDP)

The intermediate XDP, redirecting packets from NIC to the other veth,
reuses xdp_mem_info from NIC so that page recycling of the NIC works on
the destination veth's XDP.
In this way return_frame is not fully guarded by NAPI, since another
NAPI handler on another cpu may use the same xdp_mem_info concurrently.
Thus disable napi_direct by xdp_set_return_frame_no_direct() during the
NAPI context.

v8:
- Don't use xdp_frame pointer address for data_hard_start of xdp_buff.

v4:
- Use xdp_[set|clear]_return_frame_no_direct() instead of a flag in
  xdp_mem_info.

v3:
- Fix double free when veth_xdp_tx() returns a positive value.
- Convert xdp_xmit and xdp_redir variables into flags.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/veth.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++----
 1 file changed, 110 insertions(+), 9 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index dbb693a7795e..9b0a7b9ab1b8 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -32,6 +32,10 @@
 #define VETH_RING_SIZE		256
 #define VETH_XDP_HEADROOM	(XDP_PACKET_HEADROOM + NET_IP_ALIGN)
 
+/* Separating two types of XDP xmit */
+#define VETH_XDP_TX		BIT(0)
+#define VETH_XDP_REDIR		BIT(1)
+
 struct pcpu_vstats {
 	u64			packets;
 	u64			bytes;
@@ -45,6 +49,7 @@ struct veth_priv {
 	struct bpf_prog		*_xdp_prog;
 	struct net_device __rcu	*peer;
 	atomic64_t		dropped;
+	struct xdp_mem_info	xdp_mem;
 	unsigned		requested_headroom;
 	bool			rx_notify_masked;
 	struct ptr_ring		xdp_ring;
@@ -317,12 +322,44 @@ static int veth_xdp_xmit(struct net_device *dev, int n,
 	return n - drops;
 }
 
+static void veth_xdp_flush(struct net_device *dev)
+{
+	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct net_device *rcv;
+
+	rcu_read_lock();
+	rcv = rcu_dereference(priv->peer);
+	if (unlikely(!rcv))
+		goto out;
+
+	rcv_priv = netdev_priv(rcv);
+	/* xdp_ring is initialized on receive side? */
+	if (unlikely(!rcu_access_pointer(rcv_priv->xdp_prog)))
+		goto out;
+
+	__veth_xdp_flush(rcv_priv);
+out:
+	rcu_read_unlock();
+}
+
+static int veth_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
+{
+	struct xdp_frame *frame = convert_to_xdp_frame(xdp);
+
+	if (unlikely(!frame))
+		return -EOVERFLOW;
+
+	return veth_xdp_xmit(dev, 1, &frame, 0);
+}
+
 static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
-					struct xdp_frame *frame)
+					struct xdp_frame *frame,
+					unsigned int *xdp_xmit)
 {
 	void *hard_start = frame->data - frame->headroom;
 	void *head = hard_start - sizeof(struct xdp_frame);
 	int len = frame->len, delta = 0;
+	struct xdp_frame orig_frame;
 	struct bpf_prog *xdp_prog;
 	unsigned int headroom;
 	struct sk_buff *skb;
@@ -346,6 +383,29 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 			delta = frame->data - xdp.data;
 			len = xdp.data_end - xdp.data;
 			break;
+		case XDP_TX:
+			orig_frame = *frame;
+			xdp.data_hard_start = head;
+			xdp.rxq->mem = frame->mem;
+			if (unlikely(veth_xdp_tx(priv->dev, &xdp) < 0)) {
+				trace_xdp_exception(priv->dev, xdp_prog, act);
+				frame = &orig_frame;
+				goto err_xdp;
+			}
+			*xdp_xmit |= VETH_XDP_TX;
+			rcu_read_unlock();
+			goto xdp_xmit;
+		case XDP_REDIRECT:
+			orig_frame = *frame;
+			xdp.data_hard_start = head;
+			xdp.rxq->mem = frame->mem;
+			if (xdp_do_redirect(priv->dev, &xdp, xdp_prog)) {
+				frame = &orig_frame;
+				goto err_xdp;
+			}
+			*xdp_xmit |= VETH_XDP_REDIR;
+			rcu_read_unlock();
+			goto xdp_xmit;
 		default:
 			bpf_warn_invalid_xdp_action(act);
 		case XDP_ABORTED:
@@ -370,12 +430,13 @@ err:
 err_xdp:
 	rcu_read_unlock();
 	xdp_return_frame(frame);
-
+xdp_xmit:
 	return NULL;
 }
 
 static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
-					struct sk_buff *skb)
+					struct sk_buff *skb,
+					unsigned int *xdp_xmit)
 {
 	u32 pktlen, headroom, act, metalen;
 	void *orig_data, *orig_data_end;
@@ -447,6 +508,26 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	switch (act) {
 	case XDP_PASS:
 		break;
+	case XDP_TX:
+		get_page(virt_to_page(xdp.data));
+		consume_skb(skb);
+		xdp.rxq->mem = priv->xdp_mem;
+		if (unlikely(veth_xdp_tx(priv->dev, &xdp) < 0)) {
+			trace_xdp_exception(priv->dev, xdp_prog, act);
+			goto err_xdp;
+		}
+		*xdp_xmit |= VETH_XDP_TX;
+		rcu_read_unlock();
+		goto xdp_xmit;
+	case XDP_REDIRECT:
+		get_page(virt_to_page(xdp.data));
+		consume_skb(skb);
+		xdp.rxq->mem = priv->xdp_mem;
+		if (xdp_do_redirect(priv->dev, &xdp, xdp_prog))
+			goto err_xdp;
+		*xdp_xmit |= VETH_XDP_REDIR;
+		rcu_read_unlock();
+		goto xdp_xmit;
 	default:
 		bpf_warn_invalid_xdp_action(act);
 	case XDP_ABORTED:
@@ -477,9 +558,15 @@ drop:
 	rcu_read_unlock();
 	kfree_skb(skb);
 	return NULL;
+err_xdp:
+	rcu_read_unlock();
+	page_frag_free(xdp.data);
+xdp_xmit:
+	return NULL;
 }
 
-static int veth_xdp_rcv(struct veth_priv *priv, int budget)
+static int veth_xdp_rcv(struct veth_priv *priv, int budget,
+			unsigned int *xdp_xmit)
 {
 	int i, done = 0;
 
@@ -490,10 +577,12 @@ static int veth_xdp_rcv(struct veth_priv *priv, int budget)
 		if (!ptr)
 			break;
 
-		if (veth_is_xdp_frame(ptr))
-			skb = veth_xdp_rcv_one(priv, veth_ptr_to_xdp(ptr));
-		else
-			skb = veth_xdp_rcv_skb(priv, ptr);
+		if (veth_is_xdp_frame(ptr)) {
+			skb = veth_xdp_rcv_one(priv, veth_ptr_to_xdp(ptr),
+					       xdp_xmit);
+		} else {
+			skb = veth_xdp_rcv_skb(priv, ptr, xdp_xmit);
+		}
 
 		if (skb)
 			napi_gro_receive(&priv->xdp_napi, skb);
@@ -508,9 +597,11 @@ static int veth_poll(struct napi_struct *napi, int budget)
 {
 	struct veth_priv *priv =
 		container_of(napi, struct veth_priv, xdp_napi);
+	unsigned int xdp_xmit = 0;
 	int done;
 
-	done = veth_xdp_rcv(priv, budget);
+	xdp_set_return_frame_no_direct();
+	done = veth_xdp_rcv(priv, budget, &xdp_xmit);
 
 	if (done < budget && napi_complete_done(napi, done)) {
 		/* Write rx_notify_masked before reading ptr_ring */
@@ -521,6 +612,12 @@ static int veth_poll(struct napi_struct *napi, int budget)
 		}
 	}
 
+	if (xdp_xmit & VETH_XDP_TX)
+		veth_xdp_flush(priv->dev);
+	if (xdp_xmit & VETH_XDP_REDIR)
+		xdp_do_flush_map();
+	xdp_clear_return_frame_no_direct();
+
 	return done;
 }
 
@@ -567,6 +664,9 @@ static int veth_enable_xdp(struct net_device *dev)
 		err = veth_napi_add(dev);
 		if (err)
 			goto err;
+
+		/* Save original mem info as it can be overwritten */
+		priv->xdp_mem = priv->xdp_rxq.mem;
 	}
 
 	rcu_assign_pointer(priv->xdp_prog, priv->_xdp_prog);
@@ -584,6 +684,7 @@ static void veth_disable_xdp(struct net_device *dev)
 
 	rcu_assign_pointer(priv->xdp_prog, NULL);
 	veth_napi_del(dev);
+	priv->xdp_rxq.mem = priv->xdp_mem;
 	xdp_rxq_info_unreg(&priv->xdp_rxq);
 }
 
-- 
cgit v1.2.3


From 638264dc90227cca00d20c26680171addce18e51 Mon Sep 17 00:00:00 2001
From: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Date: Fri, 3 Aug 2018 16:58:18 +0900
Subject: veth: Support per queue XDP ring

Move XDP and napi related fields from veth_priv to newly created veth_rq
structure.

When xdp_frames are enqueued from ndo_xdp_xmit and XDP_TX, rxq is
selected by current cpu.

When skbs are enqueued from the peer device, rxq is one to one mapping
of its peer txq. This way we have a restriction that the number of rxqs
must not less than the number of peer txqs, but leave the possibility to
achieve bulk skb xmit in the future because txq lock would make it
possible to remove rxq ptr_ring lock.

v3:
- Add extack messages.
- Fix array overrun in veth_xmit.

Signed-off-by: Toshiaki Makita <makita.toshiaki@lab.ntt.co.jp>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 drivers/net/veth.c | 278 ++++++++++++++++++++++++++++++++++++-----------------
 1 file changed, 188 insertions(+), 90 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 9b0a7b9ab1b8..e3202af72df5 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -42,20 +42,24 @@ struct pcpu_vstats {
 	struct u64_stats_sync	syncp;
 };
 
-struct veth_priv {
+struct veth_rq {
 	struct napi_struct	xdp_napi;
 	struct net_device	*dev;
 	struct bpf_prog __rcu	*xdp_prog;
-	struct bpf_prog		*_xdp_prog;
-	struct net_device __rcu	*peer;
-	atomic64_t		dropped;
 	struct xdp_mem_info	xdp_mem;
-	unsigned		requested_headroom;
 	bool			rx_notify_masked;
 	struct ptr_ring		xdp_ring;
 	struct xdp_rxq_info	xdp_rxq;
 };
 
+struct veth_priv {
+	struct net_device __rcu	*peer;
+	atomic64_t		dropped;
+	struct bpf_prog		*_xdp_prog;
+	struct veth_rq		*rq;
+	unsigned int		requested_headroom;
+};
+
 /*
  * ethtool interface
  */
@@ -144,19 +148,19 @@ static void veth_ptr_free(void *ptr)
 		kfree_skb(ptr);
 }
 
-static void __veth_xdp_flush(struct veth_priv *priv)
+static void __veth_xdp_flush(struct veth_rq *rq)
 {
 	/* Write ptr_ring before reading rx_notify_masked */
 	smp_mb();
-	if (!priv->rx_notify_masked) {
-		priv->rx_notify_masked = true;
-		napi_schedule(&priv->xdp_napi);
+	if (!rq->rx_notify_masked) {
+		rq->rx_notify_masked = true;
+		napi_schedule(&rq->xdp_napi);
 	}
 }
 
-static int veth_xdp_rx(struct veth_priv *priv, struct sk_buff *skb)
+static int veth_xdp_rx(struct veth_rq *rq, struct sk_buff *skb)
 {
-	if (unlikely(ptr_ring_produce(&priv->xdp_ring, skb))) {
+	if (unlikely(ptr_ring_produce(&rq->xdp_ring, skb))) {
 		dev_kfree_skb_any(skb);
 		return NET_RX_DROP;
 	}
@@ -164,21 +168,22 @@ static int veth_xdp_rx(struct veth_priv *priv, struct sk_buff *skb)
 	return NET_RX_SUCCESS;
 }
 
-static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb, bool xdp)
+static int veth_forward_skb(struct net_device *dev, struct sk_buff *skb,
+			    struct veth_rq *rq, bool xdp)
 {
-	struct veth_priv *priv = netdev_priv(dev);
-
 	return __dev_forward_skb(dev, skb) ?: xdp ?
-		veth_xdp_rx(priv, skb) :
+		veth_xdp_rx(rq, skb) :
 		netif_rx(skb);
 }
 
 static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
+	struct veth_rq *rq = NULL;
 	struct net_device *rcv;
 	int length = skb->len;
 	bool rcv_xdp = false;
+	int rxq;
 
 	rcu_read_lock();
 	rcv = rcu_dereference(priv->peer);
@@ -188,9 +193,15 @@ static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	rcv_priv = netdev_priv(rcv);
-	rcv_xdp = rcu_access_pointer(rcv_priv->xdp_prog);
+	rxq = skb_get_queue_mapping(skb);
+	if (rxq < rcv->real_num_rx_queues) {
+		rq = &rcv_priv->rq[rxq];
+		rcv_xdp = rcu_access_pointer(rq->xdp_prog);
+		if (rcv_xdp)
+			skb_record_rx_queue(skb, rxq);
+	}
 
-	if (likely(veth_forward_skb(rcv, skb, rcv_xdp) == NET_RX_SUCCESS)) {
+	if (likely(veth_forward_skb(rcv, skb, rq, rcv_xdp) == NET_RX_SUCCESS)) {
 		struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
 
 		u64_stats_update_begin(&stats->syncp);
@@ -203,7 +214,7 @@ drop:
 	}
 
 	if (rcv_xdp)
-		__veth_xdp_flush(rcv_priv);
+		__veth_xdp_flush(rq);
 
 	rcu_read_unlock();
 
@@ -278,12 +289,18 @@ static struct sk_buff *veth_build_skb(void *head, int headroom, int len,
 	return skb;
 }
 
+static int veth_select_rxq(struct net_device *dev)
+{
+	return smp_processor_id() % dev->real_num_rx_queues;
+}
+
 static int veth_xdp_xmit(struct net_device *dev, int n,
 			 struct xdp_frame **frames, u32 flags)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct net_device *rcv;
 	unsigned int max_len;
+	struct veth_rq *rq;
 	int i, drops = 0;
 
 	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
@@ -294,30 +311,31 @@ static int veth_xdp_xmit(struct net_device *dev, int n,
 		return -ENXIO;
 
 	rcv_priv = netdev_priv(rcv);
+	rq = &rcv_priv->rq[veth_select_rxq(rcv)];
 	/* Non-NULL xdp_prog ensures that xdp_ring is initialized on receive
 	 * side. This means an XDP program is loaded on the peer and the peer
 	 * device is up.
 	 */
-	if (!rcu_access_pointer(rcv_priv->xdp_prog))
+	if (!rcu_access_pointer(rq->xdp_prog))
 		return -ENXIO;
 
 	max_len = rcv->mtu + rcv->hard_header_len + VLAN_HLEN;
 
-	spin_lock(&rcv_priv->xdp_ring.producer_lock);
+	spin_lock(&rq->xdp_ring.producer_lock);
 	for (i = 0; i < n; i++) {
 		struct xdp_frame *frame = frames[i];
 		void *ptr = veth_xdp_to_ptr(frame);
 
 		if (unlikely(frame->len > max_len ||
-			     __ptr_ring_produce(&rcv_priv->xdp_ring, ptr))) {
+			     __ptr_ring_produce(&rq->xdp_ring, ptr))) {
 			xdp_return_frame_rx_napi(frame);
 			drops++;
 		}
 	}
-	spin_unlock(&rcv_priv->xdp_ring.producer_lock);
+	spin_unlock(&rq->xdp_ring.producer_lock);
 
 	if (flags & XDP_XMIT_FLUSH)
-		__veth_xdp_flush(rcv_priv);
+		__veth_xdp_flush(rq);
 
 	return n - drops;
 }
@@ -326,6 +344,7 @@ static void veth_xdp_flush(struct net_device *dev)
 {
 	struct veth_priv *rcv_priv, *priv = netdev_priv(dev);
 	struct net_device *rcv;
+	struct veth_rq *rq;
 
 	rcu_read_lock();
 	rcv = rcu_dereference(priv->peer);
@@ -333,11 +352,12 @@ static void veth_xdp_flush(struct net_device *dev)
 		goto out;
 
 	rcv_priv = netdev_priv(rcv);
+	rq = &rcv_priv->rq[veth_select_rxq(rcv)];
 	/* xdp_ring is initialized on receive side? */
-	if (unlikely(!rcu_access_pointer(rcv_priv->xdp_prog)))
+	if (unlikely(!rcu_access_pointer(rq->xdp_prog)))
 		goto out;
 
-	__veth_xdp_flush(rcv_priv);
+	__veth_xdp_flush(rq);
 out:
 	rcu_read_unlock();
 }
@@ -352,7 +372,7 @@ static int veth_xdp_tx(struct net_device *dev, struct xdp_buff *xdp)
 	return veth_xdp_xmit(dev, 1, &frame, 0);
 }
 
-static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
+static struct sk_buff *veth_xdp_rcv_one(struct veth_rq *rq,
 					struct xdp_frame *frame,
 					unsigned int *xdp_xmit)
 {
@@ -365,7 +385,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 	struct sk_buff *skb;
 
 	rcu_read_lock();
-	xdp_prog = rcu_dereference(priv->xdp_prog);
+	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (likely(xdp_prog)) {
 		struct xdp_buff xdp;
 		u32 act;
@@ -374,7 +394,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 		xdp.data = frame->data;
 		xdp.data_end = frame->data + frame->len;
 		xdp.data_meta = frame->data - frame->metasize;
-		xdp.rxq = &priv->xdp_rxq;
+		xdp.rxq = &rq->xdp_rxq;
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 
@@ -387,8 +407,8 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 			orig_frame = *frame;
 			xdp.data_hard_start = head;
 			xdp.rxq->mem = frame->mem;
-			if (unlikely(veth_xdp_tx(priv->dev, &xdp) < 0)) {
-				trace_xdp_exception(priv->dev, xdp_prog, act);
+			if (unlikely(veth_xdp_tx(rq->dev, &xdp) < 0)) {
+				trace_xdp_exception(rq->dev, xdp_prog, act);
 				frame = &orig_frame;
 				goto err_xdp;
 			}
@@ -399,7 +419,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 			orig_frame = *frame;
 			xdp.data_hard_start = head;
 			xdp.rxq->mem = frame->mem;
-			if (xdp_do_redirect(priv->dev, &xdp, xdp_prog)) {
+			if (xdp_do_redirect(rq->dev, &xdp, xdp_prog)) {
 				frame = &orig_frame;
 				goto err_xdp;
 			}
@@ -409,7 +429,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 		default:
 			bpf_warn_invalid_xdp_action(act);
 		case XDP_ABORTED:
-			trace_xdp_exception(priv->dev, xdp_prog, act);
+			trace_xdp_exception(rq->dev, xdp_prog, act);
 		case XDP_DROP:
 			goto err_xdp;
 		}
@@ -424,7 +444,7 @@ static struct sk_buff *veth_xdp_rcv_one(struct veth_priv *priv,
 	}
 
 	xdp_scrub_frame(frame);
-	skb->protocol = eth_type_trans(skb, priv->dev);
+	skb->protocol = eth_type_trans(skb, rq->dev);
 err:
 	return skb;
 err_xdp:
@@ -434,8 +454,7 @@ xdp_xmit:
 	return NULL;
 }
 
-static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
-					struct sk_buff *skb,
+static struct sk_buff *veth_xdp_rcv_skb(struct veth_rq *rq, struct sk_buff *skb,
 					unsigned int *xdp_xmit)
 {
 	u32 pktlen, headroom, act, metalen;
@@ -445,7 +464,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	struct xdp_buff xdp;
 
 	rcu_read_lock();
-	xdp_prog = rcu_dereference(priv->xdp_prog);
+	xdp_prog = rcu_dereference(rq->xdp_prog);
 	if (unlikely(!xdp_prog)) {
 		rcu_read_unlock();
 		goto out;
@@ -499,7 +518,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	xdp.data = skb_mac_header(skb);
 	xdp.data_end = xdp.data + pktlen;
 	xdp.data_meta = xdp.data;
-	xdp.rxq = &priv->xdp_rxq;
+	xdp.rxq = &rq->xdp_rxq;
 	orig_data = xdp.data;
 	orig_data_end = xdp.data_end;
 
@@ -511,9 +530,9 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	case XDP_TX:
 		get_page(virt_to_page(xdp.data));
 		consume_skb(skb);
-		xdp.rxq->mem = priv->xdp_mem;
-		if (unlikely(veth_xdp_tx(priv->dev, &xdp) < 0)) {
-			trace_xdp_exception(priv->dev, xdp_prog, act);
+		xdp.rxq->mem = rq->xdp_mem;
+		if (unlikely(veth_xdp_tx(rq->dev, &xdp) < 0)) {
+			trace_xdp_exception(rq->dev, xdp_prog, act);
 			goto err_xdp;
 		}
 		*xdp_xmit |= VETH_XDP_TX;
@@ -522,8 +541,8 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	case XDP_REDIRECT:
 		get_page(virt_to_page(xdp.data));
 		consume_skb(skb);
-		xdp.rxq->mem = priv->xdp_mem;
-		if (xdp_do_redirect(priv->dev, &xdp, xdp_prog))
+		xdp.rxq->mem = rq->xdp_mem;
+		if (xdp_do_redirect(rq->dev, &xdp, xdp_prog))
 			goto err_xdp;
 		*xdp_xmit |= VETH_XDP_REDIR;
 		rcu_read_unlock();
@@ -531,7 +550,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	default:
 		bpf_warn_invalid_xdp_action(act);
 	case XDP_ABORTED:
-		trace_xdp_exception(priv->dev, xdp_prog, act);
+		trace_xdp_exception(rq->dev, xdp_prog, act);
 	case XDP_DROP:
 		goto drop;
 	}
@@ -547,7 +566,7 @@ static struct sk_buff *veth_xdp_rcv_skb(struct veth_priv *priv,
 	off = xdp.data_end - orig_data_end;
 	if (off != 0)
 		__skb_put(skb, off);
-	skb->protocol = eth_type_trans(skb, priv->dev);
+	skb->protocol = eth_type_trans(skb, rq->dev);
 
 	metalen = xdp.data - xdp.data_meta;
 	if (metalen)
@@ -565,27 +584,26 @@ xdp_xmit:
 	return NULL;
 }
 
-static int veth_xdp_rcv(struct veth_priv *priv, int budget,
-			unsigned int *xdp_xmit)
+static int veth_xdp_rcv(struct veth_rq *rq, int budget, unsigned int *xdp_xmit)
 {
 	int i, done = 0;
 
 	for (i = 0; i < budget; i++) {
-		void *ptr = __ptr_ring_consume(&priv->xdp_ring);
+		void *ptr = __ptr_ring_consume(&rq->xdp_ring);
 		struct sk_buff *skb;
 
 		if (!ptr)
 			break;
 
 		if (veth_is_xdp_frame(ptr)) {
-			skb = veth_xdp_rcv_one(priv, veth_ptr_to_xdp(ptr),
+			skb = veth_xdp_rcv_one(rq, veth_ptr_to_xdp(ptr),
 					       xdp_xmit);
 		} else {
-			skb = veth_xdp_rcv_skb(priv, ptr, xdp_xmit);
+			skb = veth_xdp_rcv_skb(rq, ptr, xdp_xmit);
 		}
 
 		if (skb)
-			napi_gro_receive(&priv->xdp_napi, skb);
+			napi_gro_receive(&rq->xdp_napi, skb);
 
 		done++;
 	}
@@ -595,25 +613,25 @@ static int veth_xdp_rcv(struct veth_priv *priv, int budget,
 
 static int veth_poll(struct napi_struct *napi, int budget)
 {
-	struct veth_priv *priv =
-		container_of(napi, struct veth_priv, xdp_napi);
+	struct veth_rq *rq =
+		container_of(napi, struct veth_rq, xdp_napi);
 	unsigned int xdp_xmit = 0;
 	int done;
 
 	xdp_set_return_frame_no_direct();
-	done = veth_xdp_rcv(priv, budget, &xdp_xmit);
+	done = veth_xdp_rcv(rq, budget, &xdp_xmit);
 
 	if (done < budget && napi_complete_done(napi, done)) {
 		/* Write rx_notify_masked before reading ptr_ring */
-		smp_store_mb(priv->rx_notify_masked, false);
-		if (unlikely(!__ptr_ring_empty(&priv->xdp_ring))) {
-			priv->rx_notify_masked = true;
-			napi_schedule(&priv->xdp_napi);
+		smp_store_mb(rq->rx_notify_masked, false);
+		if (unlikely(!__ptr_ring_empty(&rq->xdp_ring))) {
+			rq->rx_notify_masked = true;
+			napi_schedule(&rq->xdp_napi);
 		}
 	}
 
 	if (xdp_xmit & VETH_XDP_TX)
-		veth_xdp_flush(priv->dev);
+		veth_xdp_flush(rq->dev);
 	if (xdp_xmit & VETH_XDP_REDIR)
 		xdp_do_flush_map();
 	xdp_clear_return_frame_no_direct();
@@ -624,56 +642,90 @@ static int veth_poll(struct napi_struct *napi, int budget)
 static int veth_napi_add(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
-	int err;
+	int err, i;
 
-	err = ptr_ring_init(&priv->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
-	if (err)
-		return err;
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		err = ptr_ring_init(&rq->xdp_ring, VETH_RING_SIZE, GFP_KERNEL);
+		if (err)
+			goto err_xdp_ring;
+	}
 
-	netif_napi_add(dev, &priv->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
-	napi_enable(&priv->xdp_napi);
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		netif_napi_add(dev, &rq->xdp_napi, veth_poll, NAPI_POLL_WEIGHT);
+		napi_enable(&rq->xdp_napi);
+	}
 
 	return 0;
+err_xdp_ring:
+	for (i--; i >= 0; i--)
+		ptr_ring_cleanup(&priv->rq[i].xdp_ring, veth_ptr_free);
+
+	return err;
 }
 
 static void veth_napi_del(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
+	int i;
 
-	napi_disable(&priv->xdp_napi);
-	netif_napi_del(&priv->xdp_napi);
-	priv->rx_notify_masked = false;
-	ptr_ring_cleanup(&priv->xdp_ring, veth_ptr_free);
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		napi_disable(&rq->xdp_napi);
+		napi_hash_del(&rq->xdp_napi);
+	}
+	synchronize_net();
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		netif_napi_del(&rq->xdp_napi);
+		rq->rx_notify_masked = false;
+		ptr_ring_cleanup(&rq->xdp_ring, veth_ptr_free);
+	}
 }
 
 static int veth_enable_xdp(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
-	int err;
+	int err, i;
 
-	if (!xdp_rxq_info_is_reg(&priv->xdp_rxq)) {
-		err = xdp_rxq_info_reg(&priv->xdp_rxq, dev, 0);
-		if (err < 0)
-			return err;
+	if (!xdp_rxq_info_is_reg(&priv->rq[0].xdp_rxq)) {
+		for (i = 0; i < dev->real_num_rx_queues; i++) {
+			struct veth_rq *rq = &priv->rq[i];
 
-		err = xdp_rxq_info_reg_mem_model(&priv->xdp_rxq,
-						 MEM_TYPE_PAGE_SHARED, NULL);
-		if (err < 0)
-			goto err;
+			err = xdp_rxq_info_reg(&rq->xdp_rxq, dev, i);
+			if (err < 0)
+				goto err_rxq_reg;
+
+			err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+			if (err < 0)
+				goto err_reg_mem;
+
+			/* Save original mem info as it can be overwritten */
+			rq->xdp_mem = rq->xdp_rxq.mem;
+		}
 
 		err = veth_napi_add(dev);
 		if (err)
-			goto err;
-
-		/* Save original mem info as it can be overwritten */
-		priv->xdp_mem = priv->xdp_rxq.mem;
+			goto err_rxq_reg;
 	}
 
-	rcu_assign_pointer(priv->xdp_prog, priv->_xdp_prog);
+	for (i = 0; i < dev->real_num_rx_queues; i++)
+		rcu_assign_pointer(priv->rq[i].xdp_prog, priv->_xdp_prog);
 
 	return 0;
-err:
-	xdp_rxq_info_unreg(&priv->xdp_rxq);
+err_reg_mem:
+	xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
+err_rxq_reg:
+	for (i--; i >= 0; i--)
+		xdp_rxq_info_unreg(&priv->rq[i].xdp_rxq);
 
 	return err;
 }
@@ -681,11 +733,17 @@ err:
 static void veth_disable_xdp(struct net_device *dev)
 {
 	struct veth_priv *priv = netdev_priv(dev);
+	int i;
 
-	rcu_assign_pointer(priv->xdp_prog, NULL);
+	for (i = 0; i < dev->real_num_rx_queues; i++)
+		rcu_assign_pointer(priv->rq[i].xdp_prog, NULL);
 	veth_napi_del(dev);
-	priv->xdp_rxq.mem = priv->xdp_mem;
-	xdp_rxq_info_unreg(&priv->xdp_rxq);
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct veth_rq *rq = &priv->rq[i];
+
+		rq->xdp_rxq.mem = rq->xdp_mem;
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+	}
 }
 
 static int veth_open(struct net_device *dev)
@@ -842,6 +900,12 @@ static int veth_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 			goto err;
 		}
 
+		if (dev->real_num_rx_queues < peer->real_num_tx_queues) {
+			NL_SET_ERR_MSG_MOD(extack, "XDP expects number of rx queues not less than peer tx queues");
+			err = -ENOSPC;
+			goto err;
+		}
+
 		if (dev->flags & IFF_UP) {
 			err = veth_enable_xdp(dev);
 			if (err) {
@@ -976,13 +1040,31 @@ static int veth_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
+static int veth_alloc_queues(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	priv->rq = kcalloc(dev->num_rx_queues, sizeof(*priv->rq), GFP_KERNEL);
+	if (!priv->rq)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void veth_free_queues(struct net_device *dev)
+{
+	struct veth_priv *priv = netdev_priv(dev);
+
+	kfree(priv->rq);
+}
+
 static struct rtnl_link_ops veth_link_ops;
 
 static int veth_newlink(struct net *src_net, struct net_device *dev,
 			struct nlattr *tb[], struct nlattr *data[],
 			struct netlink_ext_ack *extack)
 {
-	int err;
+	int err, i;
 	struct net_device *peer;
 	struct veth_priv *priv;
 	char ifname[IFNAMSIZ];
@@ -1035,6 +1117,12 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 		return PTR_ERR(peer);
 	}
 
+	err = veth_alloc_queues(peer);
+	if (err) {
+		put_net(net);
+		goto err_peer_alloc_queues;
+	}
+
 	if (!ifmp || !tbp[IFLA_ADDRESS])
 		eth_hw_addr_random(peer);
 
@@ -1063,6 +1151,10 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	 * should be re-allocated
 	 */
 
+	err = veth_alloc_queues(dev);
+	if (err)
+		goto err_alloc_queues;
+
 	if (tb[IFLA_ADDRESS] == NULL)
 		eth_hw_addr_random(dev);
 
@@ -1082,22 +1174,28 @@ static int veth_newlink(struct net *src_net, struct net_device *dev,
 	 */
 
 	priv = netdev_priv(dev);
-	priv->dev = dev;
+	for (i = 0; i < dev->real_num_rx_queues; i++)
+		priv->rq[i].dev = dev;
 	rcu_assign_pointer(priv->peer, peer);
 
 	priv = netdev_priv(peer);
-	priv->dev = peer;
+	for (i = 0; i < peer->real_num_rx_queues; i++)
+		priv->rq[i].dev = peer;
 	rcu_assign_pointer(priv->peer, dev);
 
 	return 0;
 
 err_register_dev:
+	veth_free_queues(dev);
+err_alloc_queues:
 	/* nothing to do */
 err_configure_peer:
 	unregister_netdevice(peer);
 	return err;
 
 err_register_peer:
+	veth_free_queues(peer);
+err_peer_alloc_queues:
 	free_netdev(peer);
 	return err;
 }
-- 
cgit v1.2.3


From aa12af77aae05008b3e637b85944dcd512f75eba Mon Sep 17 00:00:00 2001
From: Ankit Navik <ankit.p.navik@intel.com>
Date: Tue, 7 Aug 2018 13:16:35 +0530
Subject: Bluetooth: Add definitions for LE set address resolution

Add the definitions for LE address resolution enable HCI commands.
When the LE address resolution enable gets changed via HCI commands
make sure that flag gets updated.

Signed-off-by: Ankit Navik <ankit.p.navik@intel.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 include/net/bluetooth/hci.h |  3 +++
 net/bluetooth/hci_event.c   | 28 ++++++++++++++++++++++++++++
 2 files changed, 31 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 4619a79b1bbb..cdd9f1fe7cfa 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -269,6 +269,7 @@ enum {
 	HCI_VENDOR_DIAG,
 	HCI_FORCE_BREDR_SMP,
 	HCI_FORCE_STATIC_ADDR,
+	HCI_LL_RPA_RESOLUTION,
 
 	__HCI_NUM_FLAGS,
 };
@@ -1524,6 +1525,8 @@ struct hci_rp_le_read_resolv_list_size {
 	__u8	size;
 } __packed;
 
+#define HCI_OP_LE_SET_ADDR_RESOLV_ENABLE 0x202d
+
 #define HCI_OP_LE_READ_MAX_DATA_LEN	0x202f
 struct hci_rp_le_read_max_data_len {
 	__u8	status;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 8078587572fe..f12555f23a49 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -1480,6 +1480,30 @@ static void hci_cc_le_read_resolv_list_size(struct hci_dev *hdev,
 	hdev->le_resolv_list_size = rp->size;
 }
 
+static void hci_cc_le_set_addr_resolution_enable(struct hci_dev *hdev,
+						struct sk_buff *skb)
+{
+	__u8 *sent, status = *((__u8 *) skb->data);
+
+	BT_DBG("%s status 0x%2.2x", hdev->name, status);
+
+	if (status)
+		return;
+
+	sent = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_ADDR_RESOLV_ENABLE);
+	if (!sent)
+		return;
+
+	hci_dev_lock(hdev);
+
+	if (*sent)
+		hci_dev_set_flag(hdev, HCI_LL_RPA_RESOLUTION);
+	else
+		hci_dev_clear_flag(hdev, HCI_LL_RPA_RESOLUTION);
+
+	hci_dev_unlock(hdev);
+}
+
 static void hci_cc_le_read_max_data_len(struct hci_dev *hdev,
 					struct sk_buff *skb)
 {
@@ -3263,6 +3287,10 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,
 		hci_cc_le_read_resolv_list_size(hdev, skb);
 		break;
 
+	case HCI_OP_LE_SET_ADDR_RESOLV_ENABLE:
+		hci_cc_le_set_addr_resolution_enable(hdev, skb);
+		break;
+
 	case HCI_OP_LE_READ_MAX_DATA_LEN:
 		hci_cc_le_read_max_data_len(hdev, skb);
 		break;
-- 
cgit v1.2.3


From 5cf943ede4af95313665ea81f224533d2aa272bb Mon Sep 17 00:00:00 2001
From: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Date: Wed, 8 Aug 2018 10:32:16 +0900
Subject: hwmon: (adt7475) Split device update function to measure and limits

The update function reads both measurement and limit values.
Those parts can be split so split them for a maintainability.

Signed-off-by: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Chris Packham <chris.packham@alliedtelesis.co.nz>
[groeck: Clarify description]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/adt7475.c | 210 +++++++++++++++++++++++++-----------------------
 1 file changed, 109 insertions(+), 101 deletions(-)

diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 9ef84998c7f3..d6fe4ddd9927 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -194,7 +194,6 @@ struct adt7475_data {
 	struct mutex lock;
 
 	unsigned long measure_updated;
-	unsigned long limits_updated;
 	char valid;
 
 	u8 config4;
@@ -1385,6 +1384,65 @@ static void adt7475_remove_files(struct i2c_client *client,
 		sysfs_remove_group(&client->dev.kobj, &vid_attr_group);
 }
 
+static void adt7475_update_limits(struct i2c_client *client)
+{
+	struct adt7475_data *data = i2c_get_clientdata(client);
+	int i;
+
+	data->config4 = adt7475_read(REG_CONFIG4);
+	data->config5 = adt7475_read(REG_CONFIG5);
+
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		/* Adjust values so they match the input precision */
+		data->voltage[MIN][i] =
+			adt7475_read(VOLTAGE_MIN_REG(i)) << 2;
+		data->voltage[MAX][i] =
+			adt7475_read(VOLTAGE_MAX_REG(i)) << 2;
+	}
+
+	if (data->has_voltage & (1 << 5)) {
+		data->voltage[MIN][5] = adt7475_read(REG_VTT_MIN) << 2;
+		data->voltage[MAX][5] = adt7475_read(REG_VTT_MAX) << 2;
+	}
+
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		/* Adjust values so they match the input precision */
+		data->temp[MIN][i] =
+			adt7475_read(TEMP_MIN_REG(i)) << 2;
+		data->temp[MAX][i] =
+			adt7475_read(TEMP_MAX_REG(i)) << 2;
+		data->temp[AUTOMIN][i] =
+			adt7475_read(TEMP_TMIN_REG(i)) << 2;
+		data->temp[THERM][i] =
+			adt7475_read(TEMP_THERM_REG(i)) << 2;
+		data->temp[OFFSET][i] =
+			adt7475_read(TEMP_OFFSET_REG(i));
+	}
+	adt7475_read_hystersis(client);
+
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		data->tach[MIN][i] =
+			adt7475_read_word(client, TACH_MIN_REG(i));
+	}
+
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		data->pwm[MAX][i] = adt7475_read(PWM_MAX_REG(i));
+		data->pwm[MIN][i] = adt7475_read(PWM_MIN_REG(i));
+		/* Set the channel and control information */
+		adt7475_read_pwm(client, i);
+	}
+
+	data->range[0] = adt7475_read(TEMP_TRANGE_REG(0));
+	data->range[1] = adt7475_read(TEMP_TRANGE_REG(1));
+	data->range[2] = adt7475_read(TEMP_TRANGE_REG(2));
+}
+
 static int adt7475_probe(struct i2c_client *client,
 			 const struct i2c_device_id *id)
 {
@@ -1562,6 +1620,9 @@ static int adt7475_probe(struct i2c_client *client,
 			 (data->bypass_attn & (1 << 3)) ? " in3" : "",
 			 (data->bypass_attn & (1 << 4)) ? " in4" : "");
 
+	/* Limits and settings, should never change update more than once */
+	adt7475_update_limits(client);
+
 	return 0;
 
 eremove:
@@ -1658,121 +1719,68 @@ static void adt7475_read_pwm(struct i2c_client *client, int index)
 	}
 }
 
-static struct adt7475_data *adt7475_update_device(struct device *dev)
+static void adt7475_update_measure(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adt7475_data *data = i2c_get_clientdata(client);
 	u16 ext;
 	int i;
 
-	mutex_lock(&data->lock);
-
-	/* Measurement values update every 2 seconds */
-	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
-	    !data->valid) {
-		data->alarms = adt7475_read(REG_STATUS2) << 8;
-		data->alarms |= adt7475_read(REG_STATUS1);
-
-		ext = (adt7475_read(REG_EXTEND2) << 8) |
-			adt7475_read(REG_EXTEND1);
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			data->voltage[INPUT][i] =
-				(adt7475_read(VOLTAGE_REG(i)) << 2) |
-				((ext >> (i * 2)) & 3);
-		}
-
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++)
-			data->temp[INPUT][i] =
-				(adt7475_read(TEMP_REG(i)) << 2) |
-				((ext >> ((i + 5) * 2)) & 3);
-
-		if (data->has_voltage & (1 << 5)) {
-			data->alarms |= adt7475_read(REG_STATUS4) << 24;
-			ext = adt7475_read(REG_EXTEND3);
-			data->voltage[INPUT][5] = adt7475_read(REG_VTT) << 2 |
-				((ext >> 4) & 3);
-		}
-
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[INPUT][i] =
-				adt7475_read_word(client, TACH_REG(i));
-		}
-
-		/* Updated by hw when in auto mode */
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[INPUT][i] = adt7475_read(PWM_REG(i));
-		}
+	data->alarms = adt7475_read(REG_STATUS2) << 8;
+	data->alarms |= adt7475_read(REG_STATUS1);
+
+	ext = (adt7475_read(REG_EXTEND2) << 8) |
+		adt7475_read(REG_EXTEND1);
+	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
+		if (!(data->has_voltage & (1 << i)))
+			continue;
+		data->voltage[INPUT][i] =
+			(adt7475_read(VOLTAGE_REG(i)) << 2) |
+			((ext >> (i * 2)) & 3);
+	}
 
-		if (data->has_vid)
-			data->vid = adt7475_read(REG_VID) & 0x3f;
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++)
+		data->temp[INPUT][i] =
+			(adt7475_read(TEMP_REG(i)) << 2) |
+			((ext >> ((i + 5) * 2)) & 3);
 
-		data->measure_updated = jiffies;
+	if (data->has_voltage & (1 << 5)) {
+		data->alarms |= adt7475_read(REG_STATUS4) << 24;
+		ext = adt7475_read(REG_EXTEND3);
+		data->voltage[INPUT][5] = adt7475_read(REG_VTT) << 2 |
+			((ext >> 4) & 3);
 	}
 
-	/* Limits and settings, should never change update every 60 seconds */
-	if (time_after(jiffies, data->limits_updated + HZ * 60) ||
-	    !data->valid) {
-		data->config4 = adt7475_read(REG_CONFIG4);
-		data->config5 = adt7475_read(REG_CONFIG5);
-
-		for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
-			if (!(data->has_voltage & (1 << i)))
-				continue;
-			/* Adjust values so they match the input precision */
-			data->voltage[MIN][i] =
-				adt7475_read(VOLTAGE_MIN_REG(i)) << 2;
-			data->voltage[MAX][i] =
-				adt7475_read(VOLTAGE_MAX_REG(i)) << 2;
-		}
-
-		if (data->has_voltage & (1 << 5)) {
-			data->voltage[MIN][5] = adt7475_read(REG_VTT_MIN) << 2;
-			data->voltage[MAX][5] = adt7475_read(REG_VTT_MAX) << 2;
-		}
+	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
+		if (i == 3 && !data->has_fan4)
+			continue;
+		data->tach[INPUT][i] =
+			adt7475_read_word(client, TACH_REG(i));
+	}
 
-		for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
-			/* Adjust values so they match the input precision */
-			data->temp[MIN][i] =
-				adt7475_read(TEMP_MIN_REG(i)) << 2;
-			data->temp[MAX][i] =
-				adt7475_read(TEMP_MAX_REG(i)) << 2;
-			data->temp[AUTOMIN][i] =
-				adt7475_read(TEMP_TMIN_REG(i)) << 2;
-			data->temp[THERM][i] =
-				adt7475_read(TEMP_THERM_REG(i)) << 2;
-			data->temp[OFFSET][i] =
-				adt7475_read(TEMP_OFFSET_REG(i));
-		}
-		adt7475_read_hystersis(client);
+	/* Updated by hw when in auto mode */
+	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
+		if (i == 1 && !data->has_pwm2)
+			continue;
+		data->pwm[INPUT][i] = adt7475_read(PWM_REG(i));
+	}
 
-		for (i = 0; i < ADT7475_TACH_COUNT; i++) {
-			if (i == 3 && !data->has_fan4)
-				continue;
-			data->tach[MIN][i] =
-				adt7475_read_word(client, TACH_MIN_REG(i));
-		}
+	if (data->has_vid)
+		data->vid = adt7475_read(REG_VID) & 0x3f;
+}
 
-		for (i = 0; i < ADT7475_PWM_COUNT; i++) {
-			if (i == 1 && !data->has_pwm2)
-				continue;
-			data->pwm[MAX][i] = adt7475_read(PWM_MAX_REG(i));
-			data->pwm[MIN][i] = adt7475_read(PWM_MIN_REG(i));
-			/* Set the channel and control information */
-			adt7475_read_pwm(client, i);
-		}
+static struct adt7475_data *adt7475_update_device(struct device *dev)
+{
+	struct i2c_client *client = to_i2c_client(dev);
+	struct adt7475_data *data = i2c_get_clientdata(client);
 
-		data->range[0] = adt7475_read(TEMP_TRANGE_REG(0));
-		data->range[1] = adt7475_read(TEMP_TRANGE_REG(1));
-		data->range[2] = adt7475_read(TEMP_TRANGE_REG(2));
+	mutex_lock(&data->lock);
 
-		data->limits_updated = jiffies;
-		data->valid = 1;
+	/* Measurement values update every 2 seconds */
+	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
+	    !data->valid) {
+		adt7475_update_measure(dev);
+		data->measure_updated = jiffies;
 	}
 
 	mutex_unlock(&data->lock);
-- 
cgit v1.2.3


From b36fb17159adad16a724f0d298a5b50269839ead Mon Sep 17 00:00:00 2001
From: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Date: Wed, 8 Aug 2018 10:32:17 +0900
Subject: hwmon: (adt7475) Change valid parameter to bool type

Currently the valid variable is of type char, but it is used as boolean.
So let's change it to bool.

Signed-off-by: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Chris Packham <chris.packham@alliedtelesis.co.nz>
[groeck: Update description]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/adt7475.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index d6fe4ddd9927..d90b31eb3472 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -194,7 +194,7 @@ struct adt7475_data {
 	struct mutex lock;
 
 	unsigned long measure_updated;
-	char valid;
+	bool valid;
 
 	u8 config4;
 	u8 config5;
@@ -1781,6 +1781,7 @@ static struct adt7475_data *adt7475_update_device(struct device *dev)
 	    !data->valid) {
 		adt7475_update_measure(dev);
 		data->measure_updated = jiffies;
+		data->valid = true;
 	}
 
 	mutex_unlock(&data->lock);
-- 
cgit v1.2.3


From 702afead45e15407bea94ccee16b801bbe9db13e Mon Sep 17 00:00:00 2001
From: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Date: Wed, 8 Aug 2018 10:32:18 +0900
Subject: hwmon: (adt7475) Change update functions to add error handling

I2C SMBus sometimes returns error codes.
In the error case, measurement values are updated incorrectly.
The sensor application then generates warning log messages and SNMP traps.
To prevent this, add error handling into the update functions.

Signed-off-by: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Chris Packham <chris.packham@alliedtelesis.co.nz>
[groeck: Update description]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/adt7475.c | 187 +++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 145 insertions(+), 42 deletions(-)

diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index d90b31eb3472..9f7e1a5b08a5 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -1384,63 +1384,119 @@ static void adt7475_remove_files(struct i2c_client *client,
 		sysfs_remove_group(&client->dev.kobj, &vid_attr_group);
 }
 
-static void adt7475_update_limits(struct i2c_client *client)
+static int adt7475_update_limits(struct i2c_client *client)
 {
 	struct adt7475_data *data = i2c_get_clientdata(client);
 	int i;
+	int ret;
 
-	data->config4 = adt7475_read(REG_CONFIG4);
-	data->config5 = adt7475_read(REG_CONFIG5);
+	ret = adt7475_read(REG_CONFIG4);
+	if (ret < 0)
+		return ret;
+	data->config4 = ret;
+
+	ret = adt7475_read(REG_CONFIG5);
+	if (ret < 0)
+		return ret;
+	data->config5 = ret;
 
 	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
 		if (!(data->has_voltage & (1 << i)))
 			continue;
 		/* Adjust values so they match the input precision */
-		data->voltage[MIN][i] =
-			adt7475_read(VOLTAGE_MIN_REG(i)) << 2;
-		data->voltage[MAX][i] =
-			adt7475_read(VOLTAGE_MAX_REG(i)) << 2;
+		ret = adt7475_read(VOLTAGE_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][i] = ret << 2;
+
+		ret = adt7475_read(VOLTAGE_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][i] = ret << 2;
 	}
 
 	if (data->has_voltage & (1 << 5)) {
-		data->voltage[MIN][5] = adt7475_read(REG_VTT_MIN) << 2;
-		data->voltage[MAX][5] = adt7475_read(REG_VTT_MAX) << 2;
+		ret = adt7475_read(REG_VTT_MIN);
+		if (ret < 0)
+			return ret;
+		data->voltage[MIN][5] = ret << 2;
+
+		ret = adt7475_read(REG_VTT_MAX);
+		if (ret < 0)
+			return ret;
+		data->voltage[MAX][5] = ret << 2;
 	}
 
 	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
 		/* Adjust values so they match the input precision */
-		data->temp[MIN][i] =
-			adt7475_read(TEMP_MIN_REG(i)) << 2;
-		data->temp[MAX][i] =
-			adt7475_read(TEMP_MAX_REG(i)) << 2;
-		data->temp[AUTOMIN][i] =
-			adt7475_read(TEMP_TMIN_REG(i)) << 2;
-		data->temp[THERM][i] =
-			adt7475_read(TEMP_THERM_REG(i)) << 2;
-		data->temp[OFFSET][i] =
-			adt7475_read(TEMP_OFFSET_REG(i));
+		ret = adt7475_read(TEMP_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[MAX][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_TMIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[AUTOMIN][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_THERM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[THERM][i] = ret << 2;
+
+		ret = adt7475_read(TEMP_OFFSET_REG(i));
+		if (ret < 0)
+			return ret;
+		data->temp[OFFSET][i] = ret;
 	}
 	adt7475_read_hystersis(client);
 
 	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
 		if (i == 3 && !data->has_fan4)
 			continue;
-		data->tach[MIN][i] =
-			adt7475_read_word(client, TACH_MIN_REG(i));
+		ret = adt7475_read_word(client, TACH_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[MIN][i] = ret;
 	}
 
 	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
 		if (i == 1 && !data->has_pwm2)
 			continue;
-		data->pwm[MAX][i] = adt7475_read(PWM_MAX_REG(i));
-		data->pwm[MIN][i] = adt7475_read(PWM_MIN_REG(i));
+		ret = adt7475_read(PWM_MAX_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MAX][i] = ret;
+
+		ret = adt7475_read(PWM_MIN_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[MIN][i] = ret;
 		/* Set the channel and control information */
 		adt7475_read_pwm(client, i);
 	}
 
-	data->range[0] = adt7475_read(TEMP_TRANGE_REG(0));
-	data->range[1] = adt7475_read(TEMP_TRANGE_REG(1));
-	data->range[2] = adt7475_read(TEMP_TRANGE_REG(2));
+	ret = adt7475_read(TEMP_TRANGE_REG(0));
+	if (ret < 0)
+		return ret;
+	data->range[0] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(1));
+	if (ret < 0)
+		return ret;
+	data->range[1] = ret;
+
+	ret = adt7475_read(TEMP_TRANGE_REG(2));
+	if (ret < 0)
+		return ret;
+	data->range[2] = ret;
+
+	return 0;
 }
 
 static int adt7475_probe(struct i2c_client *client,
@@ -1719,54 +1775,101 @@ static void adt7475_read_pwm(struct i2c_client *client, int index)
 	}
 }
 
-static void adt7475_update_measure(struct device *dev)
+static int adt7475_update_measure(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adt7475_data *data = i2c_get_clientdata(client);
 	u16 ext;
 	int i;
+	int ret;
+
+	ret = adt7475_read(REG_STATUS2);
+	if (ret < 0)
+		return ret;
+	data->alarms = ret << 8;
 
-	data->alarms = adt7475_read(REG_STATUS2) << 8;
-	data->alarms |= adt7475_read(REG_STATUS1);
+	ret = adt7475_read(REG_STATUS1);
+	if (ret < 0)
+		return ret;
+	data->alarms |= ret;
+
+	ret = adt7475_read(REG_EXTEND2);
+	if (ret < 0)
+		return ret;
+
+	ext = (ret << 8);
+
+	ret = adt7475_read(REG_EXTEND1);
+	if (ret < 0)
+		return ret;
+
+	ext |= ret;
 
-	ext = (adt7475_read(REG_EXTEND2) << 8) |
-		adt7475_read(REG_EXTEND1);
 	for (i = 0; i < ADT7475_VOLTAGE_COUNT; i++) {
 		if (!(data->has_voltage & (1 << i)))
 			continue;
+		ret = adt7475_read(VOLTAGE_REG(i));
+		if (ret < 0)
+			return ret;
 		data->voltage[INPUT][i] =
-			(adt7475_read(VOLTAGE_REG(i)) << 2) |
+			(ret << 2) |
 			((ext >> (i * 2)) & 3);
 	}
 
-	for (i = 0; i < ADT7475_TEMP_COUNT; i++)
+	for (i = 0; i < ADT7475_TEMP_COUNT; i++) {
+		ret = adt7475_read(TEMP_REG(i));
+		if (ret < 0)
+			return ret;
 		data->temp[INPUT][i] =
-			(adt7475_read(TEMP_REG(i)) << 2) |
+			(ret << 2) |
 			((ext >> ((i + 5) * 2)) & 3);
+	}
 
 	if (data->has_voltage & (1 << 5)) {
-		data->alarms |= adt7475_read(REG_STATUS4) << 24;
-		ext = adt7475_read(REG_EXTEND3);
-		data->voltage[INPUT][5] = adt7475_read(REG_VTT) << 2 |
+		ret = adt7475_read(REG_STATUS4);
+		if (ret < 0)
+			return ret;
+		data->alarms |= ret << 24;
+
+		ret = adt7475_read(REG_EXTEND3);
+		if (ret < 0)
+			return ret;
+		ext = ret;
+
+		ret = adt7475_read(REG_VTT);
+		if (ret < 0)
+			return ret;
+		data->voltage[INPUT][5] = ret << 2 |
 			((ext >> 4) & 3);
 	}
 
 	for (i = 0; i < ADT7475_TACH_COUNT; i++) {
 		if (i == 3 && !data->has_fan4)
 			continue;
-		data->tach[INPUT][i] =
-			adt7475_read_word(client, TACH_REG(i));
+		ret = adt7475_read_word(client, TACH_REG(i));
+		if (ret < 0)
+			return ret;
+		data->tach[INPUT][i] = ret;
 	}
 
 	/* Updated by hw when in auto mode */
 	for (i = 0; i < ADT7475_PWM_COUNT; i++) {
 		if (i == 1 && !data->has_pwm2)
 			continue;
-		data->pwm[INPUT][i] = adt7475_read(PWM_REG(i));
+		ret = adt7475_read(PWM_REG(i));
+		if (ret < 0)
+			return ret;
+		data->pwm[INPUT][i] = ret;
 	}
 
-	if (data->has_vid)
-		data->vid = adt7475_read(REG_VID) & 0x3f;
+	if (data->has_vid) {
+		ret = adt7475_read(REG_VID);
+		if (ret < 0)
+			return ret;
+		data->vid = ret & 0x3f;
+	}
+
+	return 0;
 }
 
 static struct adt7475_data *adt7475_update_device(struct device *dev)
-- 
cgit v1.2.3


From 4afec79f652b11189c07ce49498c4477adda887c Mon Sep 17 00:00:00 2001
From: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Date: Wed, 8 Aug 2018 10:32:19 +0900
Subject: hwmon: (adt7475) Change show functions to return error data correctly

Change update device function to return an error pointer if needed,
and report the error to user space.

Signed-off-by: Tokunori Ikegami <ikegami@allied-telesis.co.jp>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: Chris Packham <chris.packham@alliedtelesis.co.nz>
[groeck: Clarified/updated description]
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/adt7475.c | 40 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 38 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
index 9f7e1a5b08a5..90837f7c7d0f 100644
--- a/drivers/hwmon/adt7475.c
+++ b/drivers/hwmon/adt7475.c
@@ -325,6 +325,9 @@ static ssize_t show_voltage(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	unsigned short val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case ALARM:
 		return sprintf(buf, "%d\n",
@@ -380,6 +383,9 @@ static ssize_t show_temp(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	switch (sattr->nr) {
 	case HYSTERSIS:
 		mutex_lock(&data->lock);
@@ -624,6 +630,9 @@ static ssize_t show_point2(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out, val;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	mutex_lock(&data->lock);
 	out = (data->range[sattr->index] >> 4) & 0x0F;
 	val = reg2temp(data, data->temp[AUTOMIN][sattr->index]);
@@ -682,6 +691,9 @@ static ssize_t show_tach(struct device *dev, struct device_attribute *attr,
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 	int out;
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	if (sattr->nr == ALARM)
 		out = (data->alarms >> (sattr->index + 10)) & 1;
 	else
@@ -719,6 +731,9 @@ static ssize_t show_pwm(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwm[sattr->nr][sattr->index]);
 }
 
@@ -728,6 +743,9 @@ static ssize_t show_pwmchan(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmchan[sattr->index]);
 }
 
@@ -737,6 +755,9 @@ static ssize_t show_pwmctrl(struct device *dev, struct device_attribute *attr,
 	struct adt7475_data *data = adt7475_update_device(dev);
 	struct sensor_device_attribute_2 *sattr = to_sensor_dev_attr_2(attr);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", data->pwmctl[sattr->index]);
 }
 
@@ -944,6 +965,9 @@ static ssize_t show_pwmfreq(struct device *dev, struct device_attribute *attr,
 	int i = clamp_val(data->range[sattr->index] & 0xf, 0,
 			  ARRAY_SIZE(pwmfreq_table) - 1);
 
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", pwmfreq_table[i]);
 }
 
@@ -1034,6 +1058,10 @@ static ssize_t cpu0_vid_show(struct device *dev,
 			     struct device_attribute *devattr, char *buf)
 {
 	struct adt7475_data *data = adt7475_update_device(dev);
+
+	if (IS_ERR(data))
+		return PTR_ERR(data);
+
 	return sprintf(buf, "%d\n", vid_from_reg(data->vid, data->vrm));
 }
 
@@ -1677,7 +1705,9 @@ static int adt7475_probe(struct i2c_client *client,
 			 (data->bypass_attn & (1 << 4)) ? " in4" : "");
 
 	/* Limits and settings, should never change update more than once */
-	adt7475_update_limits(client);
+	ret = adt7475_update_limits(client);
+	if (ret)
+		goto eremove;
 
 	return 0;
 
@@ -1876,13 +1906,19 @@ static struct adt7475_data *adt7475_update_device(struct device *dev)
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct adt7475_data *data = i2c_get_clientdata(client);
+	int ret;
 
 	mutex_lock(&data->lock);
 
 	/* Measurement values update every 2 seconds */
 	if (time_after(jiffies, data->measure_updated + HZ * 2) ||
 	    !data->valid) {
-		adt7475_update_measure(dev);
+		ret = adt7475_update_measure(dev);
+		if (ret) {
+			data->valid = false;
+			mutex_unlock(&data->lock);
+			return ERR_PTR(ret);
+		}
 		data->measure_updated = jiffies;
 		data->valid = true;
 	}
-- 
cgit v1.2.3


From 0db021f7a2731cc559f0c5beb19ff3f677ff8626 Mon Sep 17 00:00:00 2001
From: David Collins <collinsd@codeaurora.org>
Date: Fri, 13 Jul 2018 18:50:58 -0700
Subject: regulator: dt-bindings: add QCOM RPMh regulator bindings

Introduce bindings for RPMh regulator devices found on some
Qualcomm Technlogies, Inc. SoCs.  These devices allow a given
processor within the SoC to make PMIC regulator requests which
are aggregated within the RPMh hardware block along with requests
from other processors in the SoC to determine the final PMIC
regulator hardware state.

Signed-off-by: David Collins <collinsd@codeaurora.org>
Reviewed-by: Rob Herring <robh@kernel.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 .../bindings/regulator/qcom,rpmh-regulator.txt     | 160 +++++++++++++++++++++
 .../dt-bindings/regulator/qcom,rpmh-regulator.h    |  36 +++++
 2 files changed, 196 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
 create mode 100644 include/dt-bindings/regulator/qcom,rpmh-regulator.h

diff --git a/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
new file mode 100644
index 000000000000..7ef2dbe48e8a
--- /dev/null
+++ b/Documentation/devicetree/bindings/regulator/qcom,rpmh-regulator.txt
@@ -0,0 +1,160 @@
+Qualcomm Technologies, Inc. RPMh Regulators
+
+rpmh-regulator devices support PMIC regulator management via the Voltage
+Regulator Manager (VRM) and Oscillator Buffer (XOB) RPMh accelerators.  The APPS
+processor communicates with these hardware blocks via a Resource State
+Coordinator (RSC) using command packets.  The VRM allows changing three
+parameters for a given regulator: enable state, output voltage, and operating
+mode.  The XOB allows changing only a single parameter for a given regulator:
+its enable state.  Despite its name, the XOB is capable of controlling the
+enable state of any PMIC peripheral.  It is used for clock buffers, low-voltage
+switches, and LDO/SMPS regulators which have a fixed voltage and mode.
+
+=======================
+Required Node Structure
+=======================
+
+RPMh regulators must be described in two levels of device nodes.  The first
+level describes the PMIC containing the regulators and must reside within an
+RPMh device node.  The second level describes each regulator within the PMIC
+which is to be used on the board.  Each of these regulators maps to a single
+RPMh resource.
+
+The names used for regulator nodes must match those supported by a given PMIC.
+Supported regulator node names:
+	PM8998:		smps1 - smps13, ldo1 - ldo28, lvs1 - lvs2
+	PMI8998:	bob
+	PM8005:		smps1 - smps4
+
+========================
+First Level Nodes - PMIC
+========================
+
+- compatible
+	Usage:      required
+	Value type: <string>
+	Definition: Must be one of: "qcom,pm8998-rpmh-regulators",
+		    "qcom,pmi8998-rpmh-regulators" or
+		    "qcom,pm8005-rpmh-regulators".
+
+- qcom,pmic-id
+	Usage:      required
+	Value type: <string>
+	Definition: RPMh resource name suffix used for the regulators found on
+		    this PMIC.  Typical values: "a", "b", "c", "d", "e", "f".
+
+- vdd-s1-supply
+- vdd-s2-supply
+- vdd-s3-supply
+- vdd-s4-supply
+	Usage:      optional (PM8998 and PM8005 only)
+	Value type: <phandle>
+	Definition: phandle of the parent supply regulator of one or more of the
+		    regulators for this PMIC.
+
+- vdd-s5-supply
+- vdd-s6-supply
+- vdd-s7-supply
+- vdd-s8-supply
+- vdd-s9-supply
+- vdd-s10-supply
+- vdd-s11-supply
+- vdd-s12-supply
+- vdd-s13-supply
+- vdd-l1-l27-supply
+- vdd-l2-l8-l17-supply
+- vdd-l3-l11-supply
+- vdd-l4-l5-supply
+- vdd-l6-supply
+- vdd-l7-l12-l14-l15-supply
+- vdd-l9-supply
+- vdd-l10-l23-l25-supply
+- vdd-l13-l19-l21-supply
+- vdd-l16-l28-supply
+- vdd-l18-l22-supply
+- vdd-l20-l24-supply
+- vdd-l26-supply
+- vin-lvs-1-2-supply
+	Usage:      optional (PM8998 only)
+	Value type: <phandle>
+	Definition: phandle of the parent supply regulator of one or more of the
+		    regulators for this PMIC.
+
+- vdd-bob-supply
+	Usage:      optional (PMI8998 only)
+	Value type: <phandle>
+	Definition: BOB regulator parent supply phandle
+
+===============================
+Second Level Nodes - Regulators
+===============================
+
+- qcom,always-wait-for-ack
+	Usage:      optional
+	Value type: <empty>
+	Definition: Boolean flag which indicates that the application processor
+		    must wait for an ACK or a NACK from RPMh for every request
+		    sent for this regulator including those which are for a
+		    strictly lower power state.
+
+Other properties defined in Documentation/devicetree/bindings/regulator.txt
+may also be used.  regulator-initial-mode and regulator-allowed-modes may be
+specified for VRM regulators using mode values from
+include/dt-bindings/regulator/qcom,rpmh-regulator.h.  regulator-allow-bypass
+may be specified for BOB type regulators managed via VRM.
+regulator-allow-set-load may be specified for LDO type regulators managed via
+VRM.
+
+========
+Examples
+========
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+
+&apps_rsc {
+	pm8998-rpmh-regulators {
+		compatible = "qcom,pm8998-rpmh-regulators";
+		qcom,pmic-id = "a";
+
+		vdd-l7-l12-l14-l15-supply = <&pm8998_s5>;
+
+		smps2 {
+			regulator-min-microvolt = <1100000>;
+			regulator-max-microvolt = <1100000>;
+		};
+
+		pm8998_s5: smps5 {
+			regulator-min-microvolt = <1904000>;
+			regulator-max-microvolt = <2040000>;
+		};
+
+		ldo7 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_HPM>;
+			regulator-allowed-modes =
+				<RPMH_REGULATOR_MODE_LPM
+				 RPMH_REGULATOR_MODE_HPM>;
+			regulator-allow-set-load;
+		};
+
+		lvs1 {
+			regulator-min-microvolt = <1800000>;
+			regulator-max-microvolt = <1800000>;
+		};
+	};
+
+	pmi8998-rpmh-regulators {
+		compatible = "qcom,pmi8998-rpmh-regulators";
+		qcom,pmic-id = "b";
+
+		bob {
+			regulator-min-microvolt = <3312000>;
+			regulator-max-microvolt = <3600000>;
+			regulator-allowed-modes =
+				<RPMH_REGULATOR_MODE_AUTO
+				 RPMH_REGULATOR_MODE_HPM>;
+			regulator-initial-mode = <RPMH_REGULATOR_MODE_AUTO>;
+		};
+	};
+};
diff --git a/include/dt-bindings/regulator/qcom,rpmh-regulator.h b/include/dt-bindings/regulator/qcom,rpmh-regulator.h
new file mode 100644
index 000000000000..86713dcf9e02
--- /dev/null
+++ b/include/dt-bindings/regulator/qcom,rpmh-regulator.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018, The Linux Foundation. All rights reserved. */
+
+#ifndef __QCOM_RPMH_REGULATOR_H
+#define __QCOM_RPMH_REGULATOR_H
+
+/*
+ * These mode constants may be used to specify modes for various RPMh regulator
+ * device tree properties (e.g. regulator-initial-mode).  Each type of regulator
+ * supports a subset of the possible modes.
+ *
+ * %RPMH_REGULATOR_MODE_RET:	Retention mode in which only an extremely small
+ *				load current is allowed.  This mode is supported
+ *				by LDO and SMPS type regulators.
+ * %RPMH_REGULATOR_MODE_LPM:	Low power mode in which a small load current is
+ *				allowed.  This mode corresponds to PFM for SMPS
+ *				and BOB type regulators.  This mode is supported
+ *				by LDO, HFSMPS, BOB, and PMIC4 FTSMPS type
+ *				regulators.
+ * %RPMH_REGULATOR_MODE_AUTO:	Auto mode in which the regulator hardware
+ *				automatically switches between LPM and HPM based
+ *				upon the real-time load current.  This mode is
+ *				supported by HFSMPS, BOB, and PMIC4 FTSMPS type
+ *				regulators.
+ * %RPMH_REGULATOR_MODE_HPM:	High power mode in which the full rated current
+ *				of the regulator is allowed.  This mode
+ *				corresponds to PWM for SMPS and BOB type
+ *				regulators.  This mode is supported by all types
+ *				of regulators.
+ */
+#define RPMH_REGULATOR_MODE_RET		0
+#define RPMH_REGULATOR_MODE_LPM		1
+#define RPMH_REGULATOR_MODE_AUTO	2
+#define RPMH_REGULATOR_MODE_HPM		3
+
+#endif
-- 
cgit v1.2.3


From 46fc033eba42f5a4fb583b2ab53f0a9918468452 Mon Sep 17 00:00:00 2001
From: David Collins <collinsd@codeaurora.org>
Date: Fri, 13 Jul 2018 18:50:59 -0700
Subject: regulator: add QCOM RPMh regulator driver

Add the QCOM RPMh regulator driver to manage PMIC regulators
which are controlled via RPMh on some Qualcomm Technologies, Inc.
SoCs.  RPMh is a hardware block which contains several
accelerators which are used to manage various hardware resources
that are shared between the processors of the SoC.  The final
hardware state of a regulator is determined within RPMh by
performing max aggregation of the requests made by all of the
processors.

Add support for PMIC regulator control via the voltage regulator
manager (VRM) and oscillator buffer (XOB) RPMh accelerators.
VRM supports manipulation of enable state, voltage, and mode.
XOB supports manipulation of enable state.

Signed-off-by: David Collins <collinsd@codeaurora.org>
Reviewed-by: Douglas Anderson <dianders@chromium.org>
Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/regulator/Kconfig               |   9 +
 drivers/regulator/Makefile              |   1 +
 drivers/regulator/qcom-rpmh-regulator.c | 769 ++++++++++++++++++++++++++++++++
 3 files changed, 779 insertions(+)
 create mode 100644 drivers/regulator/qcom-rpmh-regulator.c

diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 347351e79b1e..329cdd33ed62 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -682,6 +682,15 @@ config REGULATOR_QCOM_RPM
 	  Qualcomm RPM as a module. The module will be named
 	  "qcom_rpm-regulator".
 
+config REGULATOR_QCOM_RPMH
+	tristate "Qualcomm Technologies, Inc. RPMh regulator driver"
+	depends on QCOM_RPMH || COMPILE_TEST
+	help
+	  This driver supports control of PMIC regulators via the RPMh hardware
+	  block found on Qualcomm Technologies Inc. SoCs.  RPMh regulator
+	  control allows for voting on regulator state between multiple
+	  processors within the SoC.
+
 config REGULATOR_QCOM_SMD_RPM
 	tristate "Qualcomm SMD based RPM regulator driver"
 	depends on QCOM_SMD_RPM
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 18bfed61e7fe..801d9a34a203 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -78,6 +78,7 @@ obj-$(CONFIG_REGULATOR_MT6323)	+= mt6323-regulator.o
 obj-$(CONFIG_REGULATOR_MT6380)	+= mt6380-regulator.o
 obj-$(CONFIG_REGULATOR_MT6397)	+= mt6397-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_RPM) += qcom_rpm-regulator.o
+obj-$(CONFIG_REGULATOR_QCOM_RPMH) += qcom-rpmh-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_SMD_RPM) += qcom_smd-regulator.o
 obj-$(CONFIG_REGULATOR_QCOM_SPMI) += qcom_spmi-regulator.o
 obj-$(CONFIG_REGULATOR_PALMAS) += palmas-regulator.o
diff --git a/drivers/regulator/qcom-rpmh-regulator.c b/drivers/regulator/qcom-rpmh-regulator.c
new file mode 100644
index 000000000000..9f27daebd8c8
--- /dev/null
+++ b/drivers/regulator/qcom-rpmh-regulator.c
@@ -0,0 +1,769 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018, The Linux Foundation. All rights reserved.
+
+#define pr_fmt(fmt) "%s: " fmt, __func__
+
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/regulator/of_regulator.h>
+
+#include <soc/qcom/cmd-db.h>
+#include <soc/qcom/rpmh.h>
+
+#include <dt-bindings/regulator/qcom,rpmh-regulator.h>
+
+/**
+ * enum rpmh_regulator_type - supported RPMh accelerator types
+ * %VRM:	RPMh VRM accelerator which supports voting on enable, voltage,
+ *		and mode of LDO, SMPS, and BOB type PMIC regulators.
+ * %XOB:	RPMh XOB accelerator which supports voting on the enable state
+ *		of PMIC regulators.
+ */
+enum rpmh_regulator_type {
+	VRM,
+	XOB,
+};
+
+#define RPMH_REGULATOR_REG_VRM_VOLTAGE		0x0
+#define RPMH_REGULATOR_REG_ENABLE		0x4
+#define RPMH_REGULATOR_REG_VRM_MODE		0x8
+
+#define PMIC4_LDO_MODE_RETENTION		4
+#define PMIC4_LDO_MODE_LPM			5
+#define PMIC4_LDO_MODE_HPM			7
+
+#define PMIC4_SMPS_MODE_RETENTION		4
+#define PMIC4_SMPS_MODE_PFM			5
+#define PMIC4_SMPS_MODE_AUTO			6
+#define PMIC4_SMPS_MODE_PWM			7
+
+#define PMIC4_BOB_MODE_PASS			0
+#define PMIC4_BOB_MODE_PFM			1
+#define PMIC4_BOB_MODE_AUTO			2
+#define PMIC4_BOB_MODE_PWM			3
+
+/**
+ * struct rpmh_vreg_hw_data - RPMh regulator hardware configurations
+ * @regulator_type:		RPMh accelerator type used to manage this
+ *				regulator
+ * @ops:			Pointer to regulator ops callback structure
+ * @voltage_range:		The single range of voltages supported by this
+ *				PMIC regulator type
+ * @n_voltages:			The number of unique voltage set points defined
+ *				by voltage_range
+ * @hpm_min_load_uA:		Minimum load current in microamps that requires
+ *				high power mode (HPM) operation.  This is used
+ *				for LDO hardware type regulators only.
+ * @pmic_mode_map:		Array indexed by regulator framework mode
+ *				containing PMIC hardware modes.  Must be large
+ *				enough to index all framework modes supported
+ *				by this regulator hardware type.
+ * @of_map_mode:		Maps an RPMH_REGULATOR_MODE_* mode value defined
+ *				in device tree to a regulator framework mode
+ */
+struct rpmh_vreg_hw_data {
+	enum rpmh_regulator_type		regulator_type;
+	const struct regulator_ops		*ops;
+	const struct regulator_linear_range	voltage_range;
+	int					n_voltages;
+	int					hpm_min_load_uA;
+	const int				*pmic_mode_map;
+	unsigned int			      (*of_map_mode)(unsigned int mode);
+};
+
+/**
+ * struct rpmh_vreg - individual RPMh regulator data structure encapsulating a
+ *		single regulator device
+ * @dev:			Device pointer for the top-level PMIC RPMh
+ *				regulator parent device.  This is used as a
+ *				handle in RPMh write requests.
+ * @addr:			Base address of the regulator resource within
+ *				an RPMh accelerator
+ * @rdesc:			Regulator descriptor
+ * @hw_data:			PMIC regulator configuration data for this RPMh
+ *				regulator
+ * @always_wait_for_ack:	Boolean flag indicating if a request must always
+ *				wait for an ACK from RPMh before continuing even
+ *				if it corresponds to a strictly lower power
+ *				state (e.g. enabled --> disabled).
+ * @enabled:			Flag indicating if the regulator is enabled or
+ *				not
+ * @bypassed:			Boolean indicating if the regulator is in
+ *				bypass (pass-through) mode or not.  This is
+ *				only used by BOB rpmh-regulator resources.
+ * @voltage_selector:		Selector used for get_voltage_sel() and
+ *				set_voltage_sel() callbacks
+ * @mode:			RPMh VRM regulator current framework mode
+ */
+struct rpmh_vreg {
+	struct device			*dev;
+	u32				addr;
+	struct regulator_desc		rdesc;
+	const struct rpmh_vreg_hw_data	*hw_data;
+	bool				always_wait_for_ack;
+
+	int				enabled;
+	bool				bypassed;
+	int				voltage_selector;
+	unsigned int			mode;
+};
+
+/**
+ * struct rpmh_vreg_init_data - initialization data for an RPMh regulator
+ * @name:			Name for the regulator which also corresponds
+ *				to the device tree subnode name of the regulator
+ * @resource_name:		RPMh regulator resource name format string.
+ *				This must include exactly one field: '%s' which
+ *				is filled at run-time with the PMIC ID provided
+ *				by device tree property qcom,pmic-id.  Example:
+ *				"ldo%s1" for RPMh resource "ldoa1".
+ * @supply_name:		Parent supply regulator name
+ * @hw_data:			Configuration data for this PMIC regulator type
+ */
+struct rpmh_vreg_init_data {
+	const char			*name;
+	const char			*resource_name;
+	const char			*supply_name;
+	const struct rpmh_vreg_hw_data	*hw_data;
+};
+
+/**
+ * rpmh_regulator_send_request() - send the request to RPMh
+ * @vreg:		Pointer to the RPMh regulator
+ * @cmd:		Pointer to the RPMh command to send
+ * @wait_for_ack:	Boolean indicating if execution must wait until the
+ *			request has been acknowledged as complete
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_send_request(struct rpmh_vreg *vreg,
+			struct tcs_cmd *cmd, bool wait_for_ack)
+{
+	int ret;
+
+	if (wait_for_ack || vreg->always_wait_for_ack)
+		ret = rpmh_write(vreg->dev, RPMH_ACTIVE_ONLY_STATE, cmd, 1);
+	else
+		ret = rpmh_write_async(vreg->dev, RPMH_ACTIVE_ONLY_STATE, cmd,
+					1);
+
+	return ret;
+}
+
+static int _rpmh_regulator_vrm_set_voltage_sel(struct regulator_dev *rdev,
+				unsigned int selector, bool wait_for_ack)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_VRM_VOLTAGE,
+	};
+	int ret;
+
+	/* VRM voltage control register is set with voltage in millivolts. */
+	cmd.data = DIV_ROUND_UP(regulator_list_voltage_linear_range(rdev,
+							selector), 1000);
+
+	ret = rpmh_regulator_send_request(vreg, &cmd, wait_for_ack);
+	if (!ret)
+		vreg->voltage_selector = selector;
+
+	return ret;
+}
+
+static int rpmh_regulator_vrm_set_voltage_sel(struct regulator_dev *rdev,
+					unsigned int selector)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	if (vreg->enabled == -EINVAL) {
+		/*
+		 * Cache the voltage and send it later when the regulator is
+		 * enabled or disabled.
+		 */
+		vreg->voltage_selector = selector;
+		return 0;
+	}
+
+	return _rpmh_regulator_vrm_set_voltage_sel(rdev, selector,
+					selector > vreg->voltage_selector);
+}
+
+static int rpmh_regulator_vrm_get_voltage_sel(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->voltage_selector;
+}
+
+static int rpmh_regulator_is_enabled(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->enabled;
+}
+
+static int rpmh_regulator_set_enable_state(struct regulator_dev *rdev,
+					bool enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_ENABLE,
+		.data = enable,
+	};
+	int ret;
+
+	if (vreg->enabled == -EINVAL &&
+	    vreg->voltage_selector != -ENOTRECOVERABLE) {
+		ret = _rpmh_regulator_vrm_set_voltage_sel(rdev,
+						vreg->voltage_selector, true);
+		if (ret < 0)
+			return ret;
+	}
+
+	ret = rpmh_regulator_send_request(vreg, &cmd, enable);
+	if (!ret)
+		vreg->enabled = enable;
+
+	return ret;
+}
+
+static int rpmh_regulator_enable(struct regulator_dev *rdev)
+{
+	return rpmh_regulator_set_enable_state(rdev, true);
+}
+
+static int rpmh_regulator_disable(struct regulator_dev *rdev)
+{
+	return rpmh_regulator_set_enable_state(rdev, false);
+}
+
+static int rpmh_regulator_vrm_set_mode_bypass(struct rpmh_vreg *vreg,
+					unsigned int mode, bool bypassed)
+{
+	struct tcs_cmd cmd = {
+		.addr = vreg->addr + RPMH_REGULATOR_REG_VRM_MODE,
+	};
+	int pmic_mode;
+
+	if (mode > REGULATOR_MODE_STANDBY)
+		return -EINVAL;
+
+	pmic_mode = vreg->hw_data->pmic_mode_map[mode];
+	if (pmic_mode < 0)
+		return pmic_mode;
+
+	if (bypassed)
+		cmd.data = PMIC4_BOB_MODE_PASS;
+	else
+		cmd.data = pmic_mode;
+
+	return rpmh_regulator_send_request(vreg, &cmd, true);
+}
+
+static int rpmh_regulator_vrm_set_mode(struct regulator_dev *rdev,
+					unsigned int mode)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	int ret;
+
+	if (mode == vreg->mode)
+		return 0;
+
+	ret = rpmh_regulator_vrm_set_mode_bypass(vreg, mode, vreg->bypassed);
+	if (!ret)
+		vreg->mode = mode;
+
+	return ret;
+}
+
+static unsigned int rpmh_regulator_vrm_get_mode(struct regulator_dev *rdev)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	return vreg->mode;
+}
+
+/**
+ * rpmh_regulator_vrm_set_load() - set the regulator mode based upon the load
+ *		current requested
+ * @rdev:		Regulator device pointer for the rpmh-regulator
+ * @load_uA:		Aggregated load current in microamps
+ *
+ * This function is used in the regulator_ops for VRM type RPMh regulator
+ * devices.
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_vrm_set_load(struct regulator_dev *rdev, int load_uA)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	unsigned int mode;
+
+	if (load_uA >= vreg->hw_data->hpm_min_load_uA)
+		mode = REGULATOR_MODE_NORMAL;
+	else
+		mode = REGULATOR_MODE_IDLE;
+
+	return rpmh_regulator_vrm_set_mode(rdev, mode);
+}
+
+static int rpmh_regulator_vrm_set_bypass(struct regulator_dev *rdev,
+				bool enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+	int ret;
+
+	if (vreg->bypassed == enable)
+		return 0;
+
+	ret = rpmh_regulator_vrm_set_mode_bypass(vreg, vreg->mode, enable);
+	if (!ret)
+		vreg->bypassed = enable;
+
+	return ret;
+}
+
+static int rpmh_regulator_vrm_get_bypass(struct regulator_dev *rdev,
+				bool *enable)
+{
+	struct rpmh_vreg *vreg = rdev_get_drvdata(rdev);
+
+	*enable = vreg->bypassed;
+
+	return 0;
+}
+
+static const struct regulator_ops rpmh_regulator_vrm_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+};
+
+static const struct regulator_ops rpmh_regulator_vrm_drms_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+	.set_load		= rpmh_regulator_vrm_set_load,
+};
+
+static const struct regulator_ops rpmh_regulator_vrm_bypass_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+	.set_voltage_sel	= rpmh_regulator_vrm_set_voltage_sel,
+	.get_voltage_sel	= rpmh_regulator_vrm_get_voltage_sel,
+	.list_voltage		= regulator_list_voltage_linear_range,
+	.set_mode		= rpmh_regulator_vrm_set_mode,
+	.get_mode		= rpmh_regulator_vrm_get_mode,
+	.set_bypass		= rpmh_regulator_vrm_set_bypass,
+	.get_bypass		= rpmh_regulator_vrm_get_bypass,
+};
+
+static const struct regulator_ops rpmh_regulator_xob_ops = {
+	.enable			= rpmh_regulator_enable,
+	.disable		= rpmh_regulator_disable,
+	.is_enabled		= rpmh_regulator_is_enabled,
+};
+
+/**
+ * rpmh_regulator_init_vreg() - initialize all attributes of an rpmh-regulator
+ * vreg:		Pointer to the individual rpmh-regulator resource
+ * dev:			Pointer to the top level rpmh-regulator PMIC device
+ * node:		Pointer to the individual rpmh-regulator resource
+ *			device node
+ * pmic_id:		String used to identify the top level rpmh-regulator
+ *			PMIC device on the board
+ * pmic_rpmh_data:	Pointer to a null-terminated array of rpmh-regulator
+ *			resources defined for the top level PMIC device
+ *
+ * Return: 0 on success, errno on failure
+ */
+static int rpmh_regulator_init_vreg(struct rpmh_vreg *vreg, struct device *dev,
+			struct device_node *node, const char *pmic_id,
+			const struct rpmh_vreg_init_data *pmic_rpmh_data)
+{
+	struct regulator_config reg_config = {};
+	char rpmh_resource_name[20] = "";
+	const struct rpmh_vreg_init_data *rpmh_data;
+	struct regulator_init_data *init_data;
+	struct regulator_dev *rdev;
+	int ret;
+
+	vreg->dev = dev;
+
+	for (rpmh_data = pmic_rpmh_data; rpmh_data->name; rpmh_data++)
+		if (!strcmp(rpmh_data->name, node->name))
+			break;
+
+	if (!rpmh_data->name) {
+		dev_err(dev, "Unknown regulator %s\n", node->name);
+		return -EINVAL;
+	}
+
+	scnprintf(rpmh_resource_name, sizeof(rpmh_resource_name),
+		rpmh_data->resource_name, pmic_id);
+
+	vreg->addr = cmd_db_read_addr(rpmh_resource_name);
+	if (!vreg->addr) {
+		dev_err(dev, "%s: could not find RPMh address for resource %s\n",
+			node->name, rpmh_resource_name);
+		return -ENODEV;
+	}
+
+	vreg->rdesc.name = rpmh_data->name;
+	vreg->rdesc.supply_name = rpmh_data->supply_name;
+	vreg->hw_data = rpmh_data->hw_data;
+
+	vreg->enabled = -EINVAL;
+	vreg->voltage_selector = -ENOTRECOVERABLE;
+	vreg->mode = REGULATOR_MODE_INVALID;
+
+	if (rpmh_data->hw_data->n_voltages) {
+		vreg->rdesc.linear_ranges = &rpmh_data->hw_data->voltage_range;
+		vreg->rdesc.n_linear_ranges = 1;
+		vreg->rdesc.n_voltages = rpmh_data->hw_data->n_voltages;
+	}
+
+	vreg->always_wait_for_ack = of_property_read_bool(node,
+						"qcom,always-wait-for-ack");
+
+	vreg->rdesc.owner	= THIS_MODULE;
+	vreg->rdesc.type	= REGULATOR_VOLTAGE;
+	vreg->rdesc.ops		= vreg->hw_data->ops;
+	vreg->rdesc.of_map_mode	= vreg->hw_data->of_map_mode;
+
+	init_data = of_get_regulator_init_data(dev, node, &vreg->rdesc);
+	if (!init_data)
+		return -ENOMEM;
+
+	if (rpmh_data->hw_data->regulator_type == XOB &&
+	    init_data->constraints.min_uV &&
+	    init_data->constraints.min_uV == init_data->constraints.max_uV) {
+		vreg->rdesc.fixed_uV = init_data->constraints.min_uV;
+		vreg->rdesc.n_voltages = 1;
+	}
+
+	reg_config.dev		= dev;
+	reg_config.init_data	= init_data;
+	reg_config.of_node	= node;
+	reg_config.driver_data	= vreg;
+
+	rdev = devm_regulator_register(dev, &vreg->rdesc, &reg_config);
+	if (IS_ERR(rdev)) {
+		ret = PTR_ERR(rdev);
+		dev_err(dev, "%s: devm_regulator_register() failed, ret=%d\n",
+			node->name, ret);
+		return ret;
+	}
+
+	dev_dbg(dev, "%s regulator registered for RPMh resource %s @ 0x%05X\n",
+		node->name, rpmh_resource_name, vreg->addr);
+
+	return 0;
+}
+
+static const int pmic_mode_map_pmic4_ldo[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = PMIC4_LDO_MODE_RETENTION,
+	[REGULATOR_MODE_IDLE]    = PMIC4_LDO_MODE_LPM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_LDO_MODE_HPM,
+	[REGULATOR_MODE_FAST]    = -EINVAL,
+};
+
+static unsigned int rpmh_regulator_pmic4_ldo_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	case RPMH_REGULATOR_MODE_RET:
+		mode = REGULATOR_MODE_STANDBY;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const int pmic_mode_map_pmic4_smps[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = PMIC4_SMPS_MODE_RETENTION,
+	[REGULATOR_MODE_IDLE]    = PMIC4_SMPS_MODE_PFM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_SMPS_MODE_AUTO,
+	[REGULATOR_MODE_FAST]    = PMIC4_SMPS_MODE_PWM,
+};
+
+static unsigned int
+rpmh_regulator_pmic4_smps_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_FAST;
+		break;
+	case RPMH_REGULATOR_MODE_AUTO:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	case RPMH_REGULATOR_MODE_RET:
+		mode = REGULATOR_MODE_STANDBY;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const int pmic_mode_map_pmic4_bob[REGULATOR_MODE_STANDBY + 1] = {
+	[REGULATOR_MODE_INVALID] = -EINVAL,
+	[REGULATOR_MODE_STANDBY] = -EINVAL,
+	[REGULATOR_MODE_IDLE]    = PMIC4_BOB_MODE_PFM,
+	[REGULATOR_MODE_NORMAL]  = PMIC4_BOB_MODE_AUTO,
+	[REGULATOR_MODE_FAST]    = PMIC4_BOB_MODE_PWM,
+};
+
+static unsigned int rpmh_regulator_pmic4_bob_of_map_mode(unsigned int rpmh_mode)
+{
+	unsigned int mode;
+
+	switch (rpmh_mode) {
+	case RPMH_REGULATOR_MODE_HPM:
+		mode = REGULATOR_MODE_FAST;
+		break;
+	case RPMH_REGULATOR_MODE_AUTO:
+		mode = REGULATOR_MODE_NORMAL;
+		break;
+	case RPMH_REGULATOR_MODE_LPM:
+		mode = REGULATOR_MODE_IDLE;
+		break;
+	default:
+		mode = REGULATOR_MODE_INVALID;
+	}
+
+	return mode;
+}
+
+static const struct rpmh_vreg_hw_data pmic4_pldo = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1664000, 0, 255, 8000),
+	.n_voltages = 256,
+	.hpm_min_load_uA = 10000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_pldo_lv = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1256000, 0, 127, 8000),
+	.n_voltages = 128,
+	.hpm_min_load_uA = 10000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_nldo = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_drms_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(312000, 0, 127, 8000),
+	.n_voltages = 128,
+	.hpm_min_load_uA = 30000,
+	.pmic_mode_map = pmic_mode_map_pmic4_ldo,
+	.of_map_mode = rpmh_regulator_pmic4_ldo_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_hfsmps3 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 215, 8000),
+	.n_voltages = 216,
+	.pmic_mode_map = pmic_mode_map_pmic4_smps,
+	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_ftsmps426 = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(320000, 0, 258, 4000),
+	.n_voltages = 259,
+	.pmic_mode_map = pmic_mode_map_pmic4_smps,
+	.of_map_mode = rpmh_regulator_pmic4_smps_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_bob = {
+	.regulator_type = VRM,
+	.ops = &rpmh_regulator_vrm_bypass_ops,
+	.voltage_range = REGULATOR_LINEAR_RANGE(1824000, 0, 83, 32000),
+	.n_voltages = 84,
+	.pmic_mode_map = pmic_mode_map_pmic4_bob,
+	.of_map_mode = rpmh_regulator_pmic4_bob_of_map_mode,
+};
+
+static const struct rpmh_vreg_hw_data pmic4_lvs = {
+	.regulator_type = XOB,
+	.ops = &rpmh_regulator_xob_ops,
+	/* LVS hardware does not support voltage or mode configuration. */
+};
+
+#define RPMH_VREG(_name, _resource_name, _hw_data, _supply_name) \
+{ \
+	.name		= _name, \
+	.resource_name	= _resource_name, \
+	.hw_data	= _hw_data, \
+	.supply_name	= _supply_name, \
+}
+
+static const struct rpmh_vreg_init_data pm8998_vreg_data[] = {
+	RPMH_VREG("smps1",  "smp%s1",  &pmic4_ftsmps426, "vdd-s1"),
+	RPMH_VREG("smps2",  "smp%s2",  &pmic4_ftsmps426, "vdd-s2"),
+	RPMH_VREG("smps3",  "smp%s3",  &pmic4_hfsmps3,   "vdd-s3"),
+	RPMH_VREG("smps4",  "smp%s4",  &pmic4_hfsmps3,   "vdd-s4"),
+	RPMH_VREG("smps5",  "smp%s5",  &pmic4_hfsmps3,   "vdd-s5"),
+	RPMH_VREG("smps6",  "smp%s6",  &pmic4_ftsmps426, "vdd-s6"),
+	RPMH_VREG("smps7",  "smp%s7",  &pmic4_ftsmps426, "vdd-s7"),
+	RPMH_VREG("smps8",  "smp%s8",  &pmic4_ftsmps426, "vdd-s8"),
+	RPMH_VREG("smps9",  "smp%s9",  &pmic4_ftsmps426, "vdd-s9"),
+	RPMH_VREG("smps10", "smp%s10", &pmic4_ftsmps426, "vdd-s10"),
+	RPMH_VREG("smps11", "smp%s11", &pmic4_ftsmps426, "vdd-s11"),
+	RPMH_VREG("smps12", "smp%s12", &pmic4_ftsmps426, "vdd-s12"),
+	RPMH_VREG("smps13", "smp%s13", &pmic4_ftsmps426, "vdd-s13"),
+	RPMH_VREG("ldo1",   "ldo%s1",  &pmic4_nldo,      "vdd-l1-l27"),
+	RPMH_VREG("ldo2",   "ldo%s2",  &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo3",   "ldo%s3",  &pmic4_nldo,      "vdd-l3-l11"),
+	RPMH_VREG("ldo4",   "ldo%s4",  &pmic4_nldo,      "vdd-l4-l5"),
+	RPMH_VREG("ldo5",   "ldo%s5",  &pmic4_nldo,      "vdd-l4-l5"),
+	RPMH_VREG("ldo6",   "ldo%s6",  &pmic4_pldo,      "vdd-l6"),
+	RPMH_VREG("ldo7",   "ldo%s7",  &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo8",   "ldo%s8",  &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo9",   "ldo%s9",  &pmic4_pldo,      "vdd-l9"),
+	RPMH_VREG("ldo10",  "ldo%s10", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo11",  "ldo%s11", &pmic4_nldo,      "vdd-l3-l11"),
+	RPMH_VREG("ldo12",  "ldo%s12", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo13",  "ldo%s13", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo14",  "ldo%s14", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo15",  "ldo%s15", &pmic4_pldo_lv,   "vdd-l7-l12-l14-l15"),
+	RPMH_VREG("ldo16",  "ldo%s16", &pmic4_pldo,      "vdd-l16-l28"),
+	RPMH_VREG("ldo17",  "ldo%s17", &pmic4_nldo,      "vdd-l2-l8-l17"),
+	RPMH_VREG("ldo18",  "ldo%s18", &pmic4_pldo,      "vdd-l18-l22"),
+	RPMH_VREG("ldo19",  "ldo%s19", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo20",  "ldo%s20", &pmic4_pldo,      "vdd-l20-l24"),
+	RPMH_VREG("ldo21",  "ldo%s21", &pmic4_pldo,      "vdd-l13-l19-l21"),
+	RPMH_VREG("ldo22",  "ldo%s22", &pmic4_pldo,      "vdd-l18-l22"),
+	RPMH_VREG("ldo23",  "ldo%s23", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo24",  "ldo%s24", &pmic4_pldo,      "vdd-l20-l24"),
+	RPMH_VREG("ldo25",  "ldo%s25", &pmic4_pldo,      "vdd-l10-l23-l25"),
+	RPMH_VREG("ldo26",  "ldo%s26", &pmic4_nldo,      "vdd-l26"),
+	RPMH_VREG("ldo27",  "ldo%s27", &pmic4_nldo,      "vdd-l1-l27"),
+	RPMH_VREG("ldo28",  "ldo%s28", &pmic4_pldo,      "vdd-l16-l28"),
+	RPMH_VREG("lvs1",   "vs%s1",   &pmic4_lvs,       "vin-lvs-1-2"),
+	RPMH_VREG("lvs2",   "vs%s2",   &pmic4_lvs,       "vin-lvs-1-2"),
+	{},
+};
+
+static const struct rpmh_vreg_init_data pmi8998_vreg_data[] = {
+	RPMH_VREG("bob",    "bob%s1",  &pmic4_bob,       "vdd-bob"),
+	{},
+};
+
+static const struct rpmh_vreg_init_data pm8005_vreg_data[] = {
+	RPMH_VREG("smps1",  "smp%s1",  &pmic4_ftsmps426, "vdd-s1"),
+	RPMH_VREG("smps2",  "smp%s2",  &pmic4_ftsmps426, "vdd-s2"),
+	RPMH_VREG("smps3",  "smp%s3",  &pmic4_ftsmps426, "vdd-s3"),
+	RPMH_VREG("smps4",  "smp%s4",  &pmic4_ftsmps426, "vdd-s4"),
+	{},
+};
+
+static int rpmh_regulator_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	const struct rpmh_vreg_init_data *vreg_data;
+	struct device_node *node;
+	struct rpmh_vreg *vreg;
+	const char *pmic_id;
+	int ret;
+
+	vreg_data = of_device_get_match_data(dev);
+	if (!vreg_data)
+		return -ENODEV;
+
+	ret = of_property_read_string(dev->of_node, "qcom,pmic-id", &pmic_id);
+	if (ret < 0) {
+		dev_err(dev, "qcom,pmic-id missing in DT node\n");
+		return ret;
+	}
+
+	for_each_available_child_of_node(dev->of_node, node) {
+		vreg = devm_kzalloc(dev, sizeof(*vreg), GFP_KERNEL);
+		if (!vreg) {
+			of_node_put(node);
+			return -ENOMEM;
+		}
+
+		ret = rpmh_regulator_init_vreg(vreg, dev, node, pmic_id,
+						vreg_data);
+		if (ret < 0) {
+			of_node_put(node);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct of_device_id rpmh_regulator_match_table[] = {
+	{
+		.compatible = "qcom,pm8998-rpmh-regulators",
+		.data = pm8998_vreg_data,
+	},
+	{
+		.compatible = "qcom,pmi8998-rpmh-regulators",
+		.data = pmi8998_vreg_data,
+	},
+	{
+		.compatible = "qcom,pm8005-rpmh-regulators",
+		.data = pm8005_vreg_data,
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(of, rpmh_regulator_match_table);
+
+static struct platform_driver rpmh_regulator_driver = {
+	.driver = {
+		.name = "qcom-rpmh-regulator",
+		.of_match_table	= of_match_ptr(rpmh_regulator_match_table),
+	},
+	.probe = rpmh_regulator_probe,
+};
+module_platform_driver(rpmh_regulator_driver);
+
+MODULE_DESCRIPTION("Qualcomm RPMh regulator driver");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From c1777df1a5d541cda918ff0450c8adcc8b69c2fd Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Fri, 10 Aug 2018 11:03:55 +1000
Subject: cifs: add missing support for ACLs in SMB 3.11

We were missing the methods for get_acl and friends for the 3.11
dialect.

Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
CC: Stable <stable@vger.kernel.org>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/smb2ops.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 7869ea4f6fab..541258447c4c 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -3586,6 +3586,11 @@ struct smb_version_operations smb311_operations = {
 	.query_all_EAs = smb2_query_eas,
 	.set_EA = smb2_set_ea,
 #endif /* CIFS_XATTR */
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_smb2_acl,
+	.get_acl_by_fid = get_smb2_acl_by_fid,
+	.set_acl = set_smb2_acl,
+#endif /* CIFS_ACL */
 	.next_header = smb2_next_header,
 };
 
-- 
cgit v1.2.3


From e55954a5f7ce0e321cea9f91f4ebeb2a4e0165f4 Mon Sep 17 00:00:00 2001
From: Ronnie Sahlberg <lsahlber@redhat.com>
Date: Fri, 10 Aug 2018 11:31:10 +1000
Subject: cifs: don't show domain= in mount output when domain is empty

Reported-by: Xiaoli Feng <xifeng@redhat.com>
Signed-off-by: Ronnie Sahlberg <lsahlber@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Pavel Shilovsky <pshilov@microsoft.com>
---
 fs/cifs/cifsfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index de16078e456b..7065426b3280 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -432,7 +432,7 @@ cifs_show_options(struct seq_file *s, struct dentry *root)
 	else if (tcon->ses->user_name)
 		seq_show_option(s, "username", tcon->ses->user_name);
 
-	if (tcon->ses->domainName)
+	if (tcon->ses->domainName && tcon->ses->domainName[0] != 0)
 		seq_show_option(s, "domain", tcon->ses->domainName);
 
 	if (srcaddr->sa_family != AF_UNSPEC) {
-- 
cgit v1.2.3


From cdeaf9d04a5a0f51220d2f025385c553220bfb5c Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 10 Aug 2018 02:25:06 -0500
Subject: smb3: allow previous versions to be mounted with snapshot= mount parm

mounting with the "snapshots=" mount parm allows a read-only
view of a previous version of a file system (see MS-SMB2
and "timewarp" tokens, section 2.2.13.2.6) based on the timestamp
passed in on the snapshots mount parm.

Add processing to optionally send this create context.

Example output:

/mnt1 is mounted with "snapshots=..." and will see an earlier
version of the directory, with three fewer files than /mnt2
the current version of the directory.

root@Ubuntu-17-Virtual-Machine:~/cifs-2.6# cat /proc/mounts | grep cifs
//172.22.149.186/public /mnt1 cifs
ro,relatime,vers=default,cache=strict,username=smfrench,uid=0,noforceuid,gid=0,noforcegid,addr=172.22.149.186,file_mode=0755,dir_mode=0755,soft,nounix,mapposix,rsize=1048576,wsize=1048576,echo_interval=60,snapshot=131748608570000000,actimeo=1

//172.22.149.186/public /mnt2 cifs
rw,relatime,vers=default,cache=strict,username=smfrench,uid=0,noforceuid,gid=0,noforcegid,addr=172.22.149.186,file_mode=0755,dir_mode=0755,soft,nounix,mapposix,rsize=1048576,wsize=1048576,echo_interval=60,actimeo=1

root@Ubuntu-17-Virtual-Machine:~/cifs-2.6# ls /mnt1
EmptyDir  newerdir
root@Ubuntu-17-Virtual-Machine:~/cifs-2.6# ls /mnt1/newerdir

root@Ubuntu-17-Virtual-Machine:~/cifs-2.6# ls /mnt2
EmptyDir  file  newerdir  newestdir  timestamp-trace.cap
root@Ubuntu-17-Virtual-Machine:~/cifs-2.6# ls /mnt2/newerdir
new-file-not-in-snapshot

Snapshots are extremely useful for comparing previous versions of files or directories,
and recovering from data corruptions or mistakes.

Signed-off-by: Steve French <stfrench@microsoft.com>
Reviewed-by: Ronnie Sahlberg <lsahlber@redhat.com>
---
 fs/cifs/smb2pdu.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
 fs/cifs/smb2pdu.h |  8 ++++++++
 2 files changed, 68 insertions(+)

diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index faf2b779e5cb..2f1938011395 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -1856,6 +1856,51 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec,
 	return 0;
 }
 
+/* See MS-SMB2 2.2.13.2.7 */
+static struct crt_twarp_ctxt *
+create_twarp_buf(__u64 timewarp)
+{
+	struct crt_twarp_ctxt *buf;
+
+	buf = kzalloc(sizeof(struct crt_twarp_ctxt), GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	buf->ccontext.DataOffset = cpu_to_le16(offsetof
+					(struct crt_twarp_ctxt, Timestamp));
+	buf->ccontext.DataLength = cpu_to_le32(8);
+	buf->ccontext.NameOffset = cpu_to_le16(offsetof
+				(struct crt_twarp_ctxt, Name));
+	buf->ccontext.NameLength = cpu_to_le16(4);
+	/* SMB2_CREATE_TIMEWARP_TOKEN is "TWrp" */
+	buf->Name[0] = 'T';
+	buf->Name[1] = 'W';
+	buf->Name[2] = 'r';
+	buf->Name[3] = 'p';
+	buf->Timestamp = cpu_to_le64(timewarp);
+	return buf;
+}
+
+/* See MS-SMB2 2.2.13.2.7 */
+static int
+add_twarp_context(struct kvec *iov, unsigned int *num_iovec, __u64 timewarp)
+{
+	struct smb2_create_req *req = iov[0].iov_base;
+	unsigned int num = *num_iovec;
+
+	iov[num].iov_base = create_twarp_buf(timewarp);
+	if (iov[num].iov_base == NULL)
+		return -ENOMEM;
+	iov[num].iov_len = sizeof(struct crt_twarp_ctxt);
+	if (!req->CreateContextsOffset)
+		req->CreateContextsOffset = cpu_to_le32(
+				sizeof(struct smb2_create_req) +
+				iov[num - 1].iov_len);
+	le32_add_cpu(&req->CreateContextsLength, sizeof(struct crt_twarp_ctxt));
+	*num_iovec = num + 1;
+	return 0;
+}
+
 static int
 alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
 			    const char *treename, const __le16 *path)
@@ -2168,6 +2213,21 @@ SMB2_open_init(struct cifs_tcon *tcon, struct smb_rqst *rqst, __u8 *oplock,
 			return rc;
 	}
 
+	if (tcon->snapshot_time) {
+		cifs_dbg(FYI, "adding snapshot context\n");
+		if (n_iov > 2) {
+			struct create_context *ccontext =
+			    (struct create_context *)iov[n_iov-1].iov_base;
+			ccontext->Next =
+				cpu_to_le32(iov[n_iov-1].iov_len);
+		}
+
+		rc = add_twarp_context(iov, &n_iov, tcon->snapshot_time);
+		if (rc)
+			return rc;
+	}
+
+
 	rqst->rq_nvec = n_iov;
 	return 0;
 }
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index cf37c2f3f3b8..a2eeae9e0432 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -767,6 +767,14 @@ struct create_durable_handle_reconnect_v2 {
 	struct durable_reconnect_context_v2 dcontext;
 } __packed;
 
+/* See MS-SMB2 2.2.13.2.5 */
+struct crt_twarp_ctxt {
+	struct create_context ccontext;
+	__u8	Name[8];
+	__le64	Timestamp;
+
+} __packed;
+
 #define COPY_CHUNK_RES_KEY_SIZE	24
 struct resume_key_req {
 	char ResumeKey[COPY_CHUNK_RES_KEY_SIZE];
-- 
cgit v1.2.3


From c9fbb2d25295a566b97d62e6904741e8e1702d83 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Fri, 10 Aug 2018 10:47:43 +0200
Subject: net: Provide stub for __netif_set_xps_queue if there is no CONFIG_XPS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Building virtio_net driver without CONFIG_XPS fails with:

    drivers/net/virtio_net.c: In function ‘virtnet_set_affinity’:
    drivers/net/virtio_net.c:1910:3: error: implicit declaration of function ‘__netif_set_xps_queue’ [-Werror=implicit-function-declaration]
       __netif_set_xps_queue(vi->dev, mask, i, false);
       ^
Fixes: 4d99f6602cb5 ("net: allow to call netif_reset_xps_queues() under cpus_read_lock")
Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdevice.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 282e2e95ad5b..ca5ab98053c8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3412,6 +3412,13 @@ static inline int netif_set_xps_queue(struct net_device *dev,
 {
 	return 0;
 }
+
+static inline int __netif_set_xps_queue(struct net_device *dev,
+					const unsigned long *mask,
+					u16 index, bool is_rxqs_map)
+{
+	return 0;
+}
 #endif
 
 /**
-- 
cgit v1.2.3


From 29a06a779977d2af8ec783525e3d10cb616a4272 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 10 Aug 2018 08:53:28 +0100
Subject: mlxsw: remove unused arrays mlxsw_i2c_driver_name and
 mlxsw_pci_driver_name

Arrays mlxsw_i2c_driver_name and mlxsw_pci_driver_name are defined
but never used hence they are redundant and can be removed.

Cleans up clang warnings:
warning: 'mlxsw_i2c_driver_name' defined but not used
warning: 'mlxsw_pci_driver_name' defined but not used

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/i2c.c | 2 --
 drivers/net/ethernet/mellanox/mlxsw/pci.c | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/i2c.c b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
index bd255417751b..798bd5aca384 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/i2c.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/i2c.c
@@ -15,8 +15,6 @@
 #include "core.h"
 #include "i2c.h"
 
-static const char mlxsw_i2c_driver_name[] = "mlxsw_i2c";
-
 #define MLXSW_I2C_CIR2_BASE		0x72000
 #define MLXSW_I2C_CIR_STATUS_OFF	0x18
 #define MLXSW_I2C_CIR2_OFF_STATUS	(MLXSW_I2C_CIR2_BASE + \
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 4bec4f6b80ca..4d271fb3de3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -22,8 +22,6 @@
 #include "port.h"
 #include "resources.h"
 
-static const char mlxsw_pci_driver_name[] = "mlxsw_pci";
-
 #define mlxsw_pci_write32(mlxsw_pci, reg, val) \
 	iowrite32be(val, (mlxsw_pci)->hw_addr + (MLXSW_PCI_ ## reg))
 #define mlxsw_pci_read32(mlxsw_pci, reg) \
-- 
cgit v1.2.3


From e4ed2b9eff1dcc4ed7a85fa1e63f86b471215416 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Fri, 10 Aug 2018 09:02:17 +0100
Subject: net: chelsio: cxgb2: remove unused array pci_speed

Array pci_speed is defined but is never used hence it is redundant
and can be removed.

Cleans up clang warning:
warning: 'pci_speed' defined but not used [-Wunused-const-variable=]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb/cxgb2.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
index 8623be13bf86..0ccdde366ae1 100644
--- a/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
+++ b/drivers/net/ethernet/chelsio/cxgb/cxgb2.c
@@ -109,10 +109,6 @@ static int disable_msi = 0;
 module_param(disable_msi, int, 0);
 MODULE_PARM_DESC(disable_msi, "Disable Message Signaled Interrupt (MSI)");
 
-static const char pci_speed[][4] = {
-	"33", "66", "100", "133"
-};
-
 /*
  * Setup MAC to receive the types of packets we want.
  */
-- 
cgit v1.2.3


From ebddd97afb89cb1e88cc037aef2913ad4723a59f Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Fri, 10 Aug 2018 14:47:01 +0530
Subject: cxgb4: add support to display DCB info

display Data Center bridging information in debug
fs.

Signed-off-by: Casey Leedom <leedom@chelsio.com>
Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h         |   1 +
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c     |   2 +-
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c | 193 +++++++++++++++++++++
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c    |   3 +-
 4 files changed, 197 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index 3da9299cd786..76d16747f513 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1853,4 +1853,5 @@ void cxgb4_write_sgl(const struct sk_buff *skb, struct sge_txq *q,
 void cxgb4_ring_tx_db(struct adapter *adap, struct sge_txq *q, int n);
 int t4_set_vlan_acl(struct adapter *adap, unsigned int mbox, unsigned int vf,
 		    u16 vlan);
+int cxgb4_dcb_enabled(const struct net_device *dev);
 #endif /* __CXGB4_H__ */
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
index 4e7f72b17e82..b34f0f077a31 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c
@@ -22,7 +22,7 @@
 
 /* DCBx version control
  */
-static const char * const dcb_ver_array[] = {
+const char * const dcb_ver_array[] = {
 	"Unknown",
 	"DCBx-CIN",
 	"DCBx-CEE 1.01",
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
index 6f312e03432f..0f72f9c4ec74 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c
@@ -2414,6 +2414,196 @@ static const struct file_operations rss_vf_config_debugfs_fops = {
 	.release = seq_release_private
 };
 
+#ifdef CONFIG_CHELSIO_T4_DCB
+extern char *dcb_ver_array[];
+
+/* Data Center Briging information for each port.
+ */
+static int dcb_info_show(struct seq_file *seq, void *v)
+{
+	struct adapter *adap = seq->private;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Data Center Bridging Information\n");
+	} else {
+		int port = (uintptr_t)v - 2;
+		struct net_device *dev = adap->port[port];
+		struct port_info *pi = netdev2pinfo(dev);
+		struct port_dcb_info *dcb = &pi->dcb;
+
+		seq_puts(seq, "\n");
+		seq_printf(seq, "Port: %d (DCB negotiated: %s)\n",
+			   port,
+			   cxgb4_dcb_enabled(dev) ? "yes" : "no");
+
+		if (cxgb4_dcb_enabled(dev))
+			seq_printf(seq, "[ DCBx Version %s ]\n",
+				   dcb_ver_array[dcb->dcb_version]);
+
+		if (dcb->msgs) {
+			int i;
+
+			seq_puts(seq, "\n  Index\t\t\t  :\t");
+			for (i = 0; i < 8; i++)
+				seq_printf(seq, " %3d", i);
+			seq_puts(seq, "\n\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PGID) {
+			int prio, pgid;
+
+			seq_puts(seq, "  Priority Group IDs\t  :\t");
+			for (prio = 0; prio < 8; prio++) {
+				pgid = (dcb->pgid >> 4 * (7 - prio)) & 0xf;
+				seq_printf(seq, " %3d", pgid);
+			}
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PGRATE) {
+			int pg;
+
+			seq_puts(seq, "  Priority Group BW(%)\t  :\t");
+			for (pg = 0; pg < 8; pg++)
+				seq_printf(seq, " %3d", dcb->pgrate[pg]);
+			seq_puts(seq, "\n");
+
+			if (dcb->dcb_version == FW_PORT_DCB_VER_IEEE) {
+				seq_puts(seq, "  TSA Algorithm\t\t  :\t");
+				for (pg = 0; pg < 8; pg++)
+					seq_printf(seq, " %3d", dcb->tsa[pg]);
+				seq_puts(seq, "\n");
+			}
+
+			seq_printf(seq, "  Max PG Traffic Classes  [%3d  ]\n",
+				   dcb->pg_num_tcs_supported);
+
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PRIORATE) {
+			int prio;
+
+			seq_puts(seq, "  Priority Rate\t:\t");
+			for (prio = 0; prio < 8; prio++)
+				seq_printf(seq, " %3d", dcb->priorate[prio]);
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_PFC) {
+			int prio;
+
+			seq_puts(seq, "  Priority Flow Control   :\t");
+			for (prio = 0; prio < 8; prio++) {
+				int pfcen = (dcb->pfcen >> 1 * (7 - prio))
+					    & 0x1;
+				seq_printf(seq, " %3d", pfcen);
+			}
+			seq_puts(seq, "\n");
+
+			seq_printf(seq, "  Max PFC Traffic Classes [%3d  ]\n",
+				   dcb->pfc_num_tcs_supported);
+
+			seq_puts(seq, "\n");
+		}
+
+		if (dcb->msgs & CXGB4_DCB_FW_APP_ID) {
+			int app, napps;
+
+			seq_puts(seq, "  Application Information:\n");
+			seq_puts(seq, "  App    Priority    Selection         Protocol\n");
+			seq_puts(seq, "  Index  Map         Field             ID\n");
+			for (app = 0, napps = 0;
+			     app < CXGB4_MAX_DCBX_APP_SUPPORTED; app++) {
+				struct app_priority *ap;
+				static const char * const sel_names[] = {
+					"Ethertype",
+					"Socket TCP",
+					"Socket UDP",
+					"Socket All",
+				};
+				const char *sel_name;
+
+				ap = &dcb->app_priority[app];
+				/* skip empty slots */
+				if (ap->protocolid == 0)
+					continue;
+				napps++;
+
+				if (ap->sel_field < ARRAY_SIZE(sel_names))
+					sel_name = sel_names[ap->sel_field];
+				else
+					sel_name = "UNKNOWN";
+
+				seq_printf(seq, "  %3d    %#04x        %-10s (%d)    %#06x (%d)\n",
+					   app,
+					   ap->user_prio_map,
+					   sel_name, ap->sel_field,
+					   ap->protocolid, ap->protocolid);
+			}
+			if (napps == 0)
+				seq_puts(seq, "    --- None ---\n");
+		}
+	}
+	return 0;
+}
+
+static inline void *dcb_info_get_idx(struct adapter *adap, loff_t pos)
+{
+	return (pos <= adap->params.nports
+		? (void *)((uintptr_t)pos + 1)
+		: NULL);
+}
+
+static void *dcb_info_start(struct seq_file *seq, loff_t *pos)
+{
+	struct adapter *adap = seq->private;
+
+	return (*pos
+		? dcb_info_get_idx(adap, *pos)
+		: SEQ_START_TOKEN);
+}
+
+static void dcb_info_stop(struct seq_file *seq, void *v)
+{
+}
+
+static void *dcb_info_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct adapter *adap = seq->private;
+
+	(*pos)++;
+	return dcb_info_get_idx(adap, *pos);
+}
+
+static const struct seq_operations dcb_info_seq_ops = {
+	.start = dcb_info_start,
+	.next  = dcb_info_next,
+	.stop  = dcb_info_stop,
+	.show  = dcb_info_show
+};
+
+static int dcb_info_open(struct inode *inode, struct file *file)
+{
+	int res = seq_open(file, &dcb_info_seq_ops);
+
+	if (!res) {
+		struct seq_file *seq = file->private_data;
+
+		seq->private = inode->i_private;
+	}
+	return res;
+}
+
+static const struct file_operations dcb_info_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = dcb_info_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+#endif /* CONFIG_CHELSIO_T4_DCB */
+
 static int resources_show(struct seq_file *seq, void *v)
 {
 	struct adapter *adapter = seq->private;
@@ -3435,6 +3625,9 @@ int t4_setup_debugfs(struct adapter *adap)
 		{ "rss_pf_config", &rss_pf_config_debugfs_fops, 0400, 0 },
 		{ "rss_vf_config", &rss_vf_config_debugfs_fops, 0400, 0 },
 		{ "resources", &resources_debugfs_fops, 0400, 0 },
+#ifdef CONFIG_CHELSIO_T4_DCB
+		{ "dcb_info", &dcb_info_debugfs_fops, 0400, 0 },
+#endif
 		{ "sge_qinfo", &sge_qinfo_debugfs_fops, 0400, 0 },
 		{ "ibq_tp0",  &cim_ibq_fops, 0400, 0 },
 		{ "ibq_tp1",  &cim_ibq_fops, 0400, 1 },
diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 0f7ce71205e6..69590cff2a2d 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -267,7 +267,7 @@ static void dcb_tx_queue_prio_enable(struct net_device *dev, int enable)
 	}
 }
 
-static int cxgb4_dcb_enabled(const struct net_device *dev)
+int cxgb4_dcb_enabled(const struct net_device *dev)
 {
 	struct port_info *pi = netdev_priv(dev);
 
@@ -5658,6 +5658,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 #ifdef CONFIG_CHELSIO_T4_DCB
 		netdev->dcbnl_ops = &cxgb4_dcb_ops;
 		cxgb4_dcb_state_init(netdev);
+		cxgb4_dcb_version_init(netdev);
 #endif
 		cxgb4_set_ethtool_ops(netdev);
 	}
-- 
cgit v1.2.3


From 2d1ce5ec2117d16047334a1aa4b62e0cfb5a0605 Mon Sep 17 00:00:00 2001
From: Alexandru Gagniuc <mr.nuke.me@gmail.com>
Date: Mon, 6 Aug 2018 18:25:35 -0500
Subject: PCI: Check for PCIe Link downtraining

When both ends of a PCIe Link are capable of a higher bandwidth than is
currently in use, the Link is said to be "downtrained".  A downtrained Link
may indicate hardware or configuration problems in the system, but it's
hard to identify such Links from userspace.

Refactor pcie_print_link_status() so it continues to always print PCIe
bandwidth information, as several NIC drivers desire.

Add a new internal __pcie_print_link_status() to emit a message only when a
device's bandwidth is constrained by the fabric and call it from the PCI
core for all devices, which identifies all downtrained Links.  It also
emits messages for a few cases that are technically not downtrained, such
as a x4 device in an open-ended x1 slot.

Signed-off-by: Alexandru Gagniuc <mr.nuke.me@gmail.com>
[bhelgaas: changelog, move __pcie_print_link_status() declaration to
drivers/pci/, rename pcie_check_upstream_link() to
pcie_report_downtraining()]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pci.c   | 27 ++++++++++++++++++++-------
 drivers/pci/pci.h   |  1 +
 drivers/pci/probe.c | 21 +++++++++++++++++++++
 3 files changed, 42 insertions(+), 7 deletions(-)

diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 97acba712e4e..a84d341504a5 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -5264,14 +5264,16 @@ u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
 }
 
 /**
- * pcie_print_link_status - Report the PCI device's link speed and width
+ * __pcie_print_link_status - Report the PCI device's link speed and width
  * @dev: PCI device to query
+ * @verbose: Print info even when enough bandwidth is available
  *
- * Report the available bandwidth at the device.  If this is less than the
- * device is capable of, report the device's maximum possible bandwidth and
- * the upstream link that limits its performance to less than that.
+ * If the available bandwidth at the device is less than the device is
+ * capable of, report the device's maximum possible bandwidth and the
+ * upstream link that limits its performance.  If @verbose, always print
+ * the available bandwidth, even if the device isn't constrained.
  */
-void pcie_print_link_status(struct pci_dev *dev)
+void __pcie_print_link_status(struct pci_dev *dev, bool verbose)
 {
 	enum pcie_link_width width, width_cap;
 	enum pci_bus_speed speed, speed_cap;
@@ -5281,11 +5283,11 @@ void pcie_print_link_status(struct pci_dev *dev)
 	bw_cap = pcie_bandwidth_capable(dev, &speed_cap, &width_cap);
 	bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width);
 
-	if (bw_avail >= bw_cap)
+	if (bw_avail >= bw_cap && verbose)
 		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n",
 			 bw_cap / 1000, bw_cap % 1000,
 			 PCIE_SPEED2STR(speed_cap), width_cap);
-	else
+	else if (bw_avail < bw_cap)
 		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
 			 bw_avail / 1000, bw_avail % 1000,
 			 PCIE_SPEED2STR(speed), width,
@@ -5293,6 +5295,17 @@ void pcie_print_link_status(struct pci_dev *dev)
 			 bw_cap / 1000, bw_cap % 1000,
 			 PCIE_SPEED2STR(speed_cap), width_cap);
 }
+
+/**
+ * pcie_print_link_status - Report the PCI device's link speed and width
+ * @dev: PCI device to query
+ *
+ * Report the available bandwidth at the device.
+ */
+void pcie_print_link_status(struct pci_dev *dev)
+{
+	__pcie_print_link_status(dev, true);
+}
 EXPORT_SYMBOL(pcie_print_link_status);
 
 /**
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 70808c168fb9..ce880dab5bc8 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -263,6 +263,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
 			   enum pcie_link_width *width);
+void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
 
 /* Single Root I/O Virtualization */
 struct pci_sriov {
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 7c0c8ab94bcf..71412db3cbeb 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2223,6 +2223,25 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
 	return dev;
 }
 
+static void pcie_report_downtraining(struct pci_dev *dev)
+{
+	if (!pci_is_pcie(dev))
+		return;
+
+	/* Look from the device up to avoid downstream ports with no devices */
+	if ((pci_pcie_type(dev) != PCI_EXP_TYPE_ENDPOINT) &&
+	    (pci_pcie_type(dev) != PCI_EXP_TYPE_LEG_END) &&
+	    (pci_pcie_type(dev) != PCI_EXP_TYPE_UPSTREAM))
+		return;
+
+	/* Multi-function PCIe devices share the same link/status */
+	if (PCI_FUNC(dev->devfn) != 0 || dev->is_virtfn)
+		return;
+
+	/* Print link status only if the device is constrained by the fabric */
+	__pcie_print_link_status(dev, false);
+}
+
 static void pci_init_capabilities(struct pci_dev *dev)
 {
 	/* Enhanced Allocation */
@@ -2258,6 +2277,8 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	/* Advanced Error Reporting */
 	pci_aer_init(dev);
 
+	pcie_report_downtraining(dev);
+
 	if (pci_probe_reset_function(dev) == 0)
 		dev->reset_fn = 1;
 }
-- 
cgit v1.2.3


From 46451874c7c9afaa4e014aea0f0970f886444e0d Mon Sep 17 00:00:00 2001
From: Coly Li <colyli@suse.de>
Date: Fri, 10 Aug 2018 23:45:50 +0800
Subject: bcache: fix error setting writeback_rate through sysfs interface

Commit ea8c5356d390 ("bcache: set max writeback rate when I/O request
is idle") changes struct bch_ratelimit member rate from uint32_t to
atomic_long_t and uses atomic_long_set() in drivers/md/bcache/sysfs.c
to set new writeback rate, after the input is converted from memory
buf to long int by sysfs_strtoul_clamp().

The above change has a problem because there is an implicit return
inside sysfs_strtoul_clamp() so the following atomic_long_set()
won't be called. This error is detected by 0day system with following
snipped smatch warnings:

drivers/md/bcache/sysfs.c:271 __cached_dev_store() error: uninitialized
symbol 'v'.
270  sysfs_strtoul_clamp(writeback_rate, v, 1, INT_MAX);
     ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
@271 atomic_long_set(&dc->writeback_rate.rate, v);

This patch fixes the above error by using strtoul_safe_clamp() to
convert the input buffer into a long int type result.

Fixes: ea8c5356d390 ("bcache: set max writeback rate when I/O request is idle")
Cc: Kai Krakow <kai@kaishome.de>
Cc: Stefan Priebe <s.priebe@profihost.ag>
Signed-off-by: Coly Li <colyli@suse.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/md/bcache/sysfs.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c
index 22f8565d2bf1..81d3520b0702 100644
--- a/drivers/md/bcache/sysfs.c
+++ b/drivers/md/bcache/sysfs.c
@@ -265,10 +265,17 @@ STORE(__cached_dev)
 	sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40);
 
 	if (attr == &sysfs_writeback_rate) {
-		int v;
+		ssize_t ret;
+		long int v = atomic_long_read(&dc->writeback_rate.rate);
+
+		ret = strtoul_safe_clamp(buf, v, 1, INT_MAX);
 
-		sysfs_strtoul_clamp(writeback_rate, v, 1, INT_MAX);
-		atomic_long_set(&dc->writeback_rate.rate, v);
+		if (!ret) {
+			atomic_long_set(&dc->writeback_rate.rate, v);
+			ret = size;
+		}
+
+		return ret;
 	}
 
 	sysfs_strtoul_clamp(writeback_rate_update_seconds,
-- 
cgit v1.2.3


From f9ed6debca45dd9bcc02d77c98822d50aba342f4 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 9 Aug 2018 22:42:53 -0700
Subject: xfs: repair the AGF

Regenerate the AGF from the rmap data.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/agheader_repair.c | 379 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.c          |  27 ++-
 fs/xfs/scrub/repair.h          |   2 +
 fs/xfs/scrub/scrub.c           |   2 +-
 4 files changed, 400 insertions(+), 10 deletions(-)

diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 1e96621ece3a..aa180492a4a5 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -17,12 +17,19 @@
 #include "xfs_sb.h"
 #include "xfs_inode.h"
 #include "xfs_alloc.h"
+#include "xfs_alloc_btree.h"
 #include "xfs_ialloc.h"
+#include "xfs_ialloc_btree.h"
 #include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
+#include "scrub/repair.h"
+#include "scrub/bitmap.h"
 
 /* Superblock */
 
@@ -54,3 +61,375 @@ xrep_superblock(
 	xfs_trans_log_buf(sc->tp, bp, 0, BBTOB(bp->b_length) - 1);
 	return error;
 }
+
+/* AGF */
+
+struct xrep_agf_allocbt {
+	struct xfs_scrub	*sc;
+	xfs_agblock_t		freeblks;
+	xfs_agblock_t		longest;
+};
+
+/* Record free space shape information. */
+STATIC int
+xrep_agf_walk_allocbt(
+	struct xfs_btree_cur		*cur,
+	struct xfs_alloc_rec_incore	*rec,
+	void				*priv)
+{
+	struct xrep_agf_allocbt		*raa = priv;
+	int				error = 0;
+
+	if (xchk_should_terminate(raa->sc, &error))
+		return error;
+
+	raa->freeblks += rec->ar_blockcount;
+	if (rec->ar_blockcount > raa->longest)
+		raa->longest = rec->ar_blockcount;
+	return error;
+}
+
+/* Does this AGFL block look sane? */
+STATIC int
+xrep_agf_check_agfl_block(
+	struct xfs_mount	*mp,
+	xfs_agblock_t		agbno,
+	void			*priv)
+{
+	struct xfs_scrub	*sc = priv;
+
+	if (!xfs_verify_agbno(mp, sc->sa.agno, agbno))
+		return -EFSCORRUPTED;
+	return 0;
+}
+
+/*
+ * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
+ * XFS_BTNUM_ names here to avoid creating a sparse array.
+ */
+enum {
+	XREP_AGF_BNOBT = 0,
+	XREP_AGF_CNTBT,
+	XREP_AGF_RMAPBT,
+	XREP_AGF_REFCOUNTBT,
+	XREP_AGF_END,
+	XREP_AGF_MAX
+};
+
+/* Check a btree root candidate. */
+static inline bool
+xrep_check_btree_root(
+	struct xfs_scrub		*sc,
+	struct xrep_find_ag_btree	*fab)
+{
+	struct xfs_mount		*mp = sc->mp;
+	xfs_agnumber_t			agno = sc->sm->sm_agno;
+
+	return xfs_verify_agbno(mp, agno, fab->root) &&
+	       fab->height <= XFS_BTREE_MAXLEVELS;
+}
+
+/*
+ * Given the btree roots described by *fab, find the roots, check them for
+ * sanity, and pass the root data back out via *fab.
+ *
+ * This is /also/ a chicken and egg problem because we have to use the rmapbt
+ * (rooted in the AGF) to find the btrees rooted in the AGF.  We also have no
+ * idea if the btrees make any sense.  If we hit obvious corruptions in those
+ * btrees we'll bail out.
+ */
+STATIC int
+xrep_agf_find_btrees(
+	struct xfs_scrub		*sc,
+	struct xfs_buf			*agf_bp,
+	struct xrep_find_ag_btree	*fab,
+	struct xfs_buf			*agfl_bp)
+{
+	struct xfs_agf			*old_agf = XFS_BUF_TO_AGF(agf_bp);
+	int				error;
+
+	/* Go find the root data. */
+	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, agfl_bp);
+	if (error)
+		return error;
+
+	/* We must find the bnobt, cntbt, and rmapbt roots. */
+	if (!xrep_check_btree_root(sc, &fab[XREP_AGF_BNOBT]) ||
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_CNTBT]) ||
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_RMAPBT]))
+		return -EFSCORRUPTED;
+
+	/*
+	 * We relied on the rmapbt to reconstruct the AGF.  If we get a
+	 * different root then something's seriously wrong.
+	 */
+	if (fab[XREP_AGF_RMAPBT].root !=
+	    be32_to_cpu(old_agf->agf_roots[XFS_BTNUM_RMAPi]))
+		return -EFSCORRUPTED;
+
+	/* We must find the refcountbt root if that feature is enabled. */
+	if (xfs_sb_version_hasreflink(&sc->mp->m_sb) &&
+	    !xrep_check_btree_root(sc, &fab[XREP_AGF_REFCOUNTBT]))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/*
+ * Reinitialize the AGF header, making an in-core copy of the old contents so
+ * that we know which in-core state needs to be reinitialized.
+ */
+STATIC void
+xrep_agf_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	struct xfs_agf		*old_agf)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	memcpy(old_agf, agf, sizeof(*old_agf));
+	memset(agf, 0, BBTOB(agf_bp->b_length));
+	agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
+	agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
+	agf->agf_seqno = cpu_to_be32(sc->sa.agno);
+	agf->agf_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
+	agf->agf_flfirst = old_agf->agf_flfirst;
+	agf->agf_fllast = old_agf->agf_fllast;
+	agf->agf_flcount = old_agf->agf_flcount;
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agf->agf_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/* Mark the incore AGF data stale until we're done fixing things. */
+	ASSERT(sc->sa.pag->pagf_init);
+	sc->sa.pag->pagf_init = 0;
+}
+
+/* Set btree root information in an AGF. */
+STATIC void
+xrep_agf_set_roots(
+	struct xfs_scrub		*sc,
+	struct xfs_agf			*agf,
+	struct xrep_find_ag_btree	*fab)
+{
+	agf->agf_roots[XFS_BTNUM_BNOi] =
+			cpu_to_be32(fab[XREP_AGF_BNOBT].root);
+	agf->agf_levels[XFS_BTNUM_BNOi] =
+			cpu_to_be32(fab[XREP_AGF_BNOBT].height);
+
+	agf->agf_roots[XFS_BTNUM_CNTi] =
+			cpu_to_be32(fab[XREP_AGF_CNTBT].root);
+	agf->agf_levels[XFS_BTNUM_CNTi] =
+			cpu_to_be32(fab[XREP_AGF_CNTBT].height);
+
+	agf->agf_roots[XFS_BTNUM_RMAPi] =
+			cpu_to_be32(fab[XREP_AGF_RMAPBT].root);
+	agf->agf_levels[XFS_BTNUM_RMAPi] =
+			cpu_to_be32(fab[XREP_AGF_RMAPBT].height);
+
+	if (xfs_sb_version_hasreflink(&sc->mp->m_sb)) {
+		agf->agf_refcount_root =
+				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].root);
+		agf->agf_refcount_level =
+				cpu_to_be32(fab[XREP_AGF_REFCOUNTBT].height);
+	}
+}
+
+/* Update all AGF fields which derive from btree contents. */
+STATIC int
+xrep_agf_calc_from_btrees(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp)
+{
+	struct xrep_agf_allocbt	raa = { .sc = sc };
+	struct xfs_btree_cur	*cur = NULL;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agblock_t		btreeblks;
+	xfs_agblock_t		blocks;
+	int			error;
+
+	/* Update the AGF counters from the bnobt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_BNO);
+	error = xfs_alloc_query_all(cur, xrep_agf_walk_allocbt, &raa);
+	if (error)
+		goto err;
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	btreeblks = blocks - 1;
+	agf->agf_freeblks = cpu_to_be32(raa.freeblks);
+	agf->agf_longest = cpu_to_be32(raa.longest);
+
+	/* Update the AGF counters from the cntbt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_CNT);
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	btreeblks += blocks - 1;
+
+	/* Update the AGF counters from the rmapbt. */
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+	error = xfs_btree_count_blocks(cur, &blocks);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+	agf->agf_rmap_blocks = cpu_to_be32(blocks);
+	btreeblks += blocks - 1;
+
+	agf->agf_btreeblks = cpu_to_be32(btreeblks);
+
+	/* Update the AGF counters from the refcountbt. */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		cur = xfs_refcountbt_init_cursor(mp, sc->tp, agf_bp,
+				sc->sa.agno);
+		error = xfs_btree_count_blocks(cur, &blocks);
+		if (error)
+			goto err;
+		xfs_btree_del_cursor(cur, error);
+		agf->agf_refcount_blocks = cpu_to_be32(blocks);
+	}
+
+	return 0;
+err:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Commit the new AGF and reinitialize the incore state. */
+STATIC int
+xrep_agf_commit_new(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp)
+{
+	struct xfs_perag	*pag;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	/* Trigger fdblocks recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Write this to disk. */
+	xfs_trans_buf_set_type(sc->tp, agf_bp, XFS_BLFT_AGF_BUF);
+	xfs_trans_log_buf(sc->tp, agf_bp, 0, BBTOB(agf_bp->b_length) - 1);
+
+	/* Now reinitialize the in-core counters we changed. */
+	pag = sc->sa.pag;
+	pag->pagf_btreeblks = be32_to_cpu(agf->agf_btreeblks);
+	pag->pagf_freeblks = be32_to_cpu(agf->agf_freeblks);
+	pag->pagf_longest = be32_to_cpu(agf->agf_longest);
+	pag->pagf_levels[XFS_BTNUM_BNOi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNOi]);
+	pag->pagf_levels[XFS_BTNUM_CNTi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNTi]);
+	pag->pagf_levels[XFS_BTNUM_RMAPi] =
+			be32_to_cpu(agf->agf_levels[XFS_BTNUM_RMAPi]);
+	pag->pagf_refcount_level = be32_to_cpu(agf->agf_refcount_level);
+	pag->pagf_init = 1;
+
+	return 0;
+}
+
+/* Repair the AGF. v5 filesystems only. */
+int
+xrep_agf(
+	struct xfs_scrub		*sc)
+{
+	struct xrep_find_ag_btree	fab[XREP_AGF_MAX] = {
+		[XREP_AGF_BNOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_allocbt_buf_ops,
+			.magic = XFS_ABTB_CRC_MAGIC,
+		},
+		[XREP_AGF_CNTBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_allocbt_buf_ops,
+			.magic = XFS_ABTC_CRC_MAGIC,
+		},
+		[XREP_AGF_RMAPBT] = {
+			.rmap_owner = XFS_RMAP_OWN_AG,
+			.buf_ops = &xfs_rmapbt_buf_ops,
+			.magic = XFS_RMAP_CRC_MAGIC,
+		},
+		[XREP_AGF_REFCOUNTBT] = {
+			.rmap_owner = XFS_RMAP_OWN_REFC,
+			.buf_ops = &xfs_refcountbt_buf_ops,
+			.magic = XFS_REFC_CRC_MAGIC,
+		},
+		[XREP_AGF_END] = {
+			.buf_ops = NULL,
+		},
+	};
+	struct xfs_agf			old_agf;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*agf_bp;
+	struct xfs_buf			*agfl_bp;
+	struct xfs_agf			*agf;
+	int				error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	/*
+	 * Make sure we have the AGF buffer, as scrub might have decided it
+	 * was corrupt after xfs_alloc_read_agf failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGF_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agf_bp, NULL);
+	if (error)
+		return error;
+	agf_bp->b_ops = &xfs_agf_buf_ops;
+	agf = XFS_BUF_TO_AGF(agf_bp);
+
+	/*
+	 * Load the AGFL so that we can screen out OWN_AG blocks that are on
+	 * the AGFL now; these blocks might have once been part of the
+	 * bno/cnt/rmap btrees but are not now.  This is a chicken and egg
+	 * problem: the AGF is corrupt, so we have to trust the AGFL contents
+	 * because we can't do any serious cross-referencing with any of the
+	 * btrees rooted in the AGF.  If the AGFL contents are obviously bad
+	 * then we'll bail out.
+	 */
+	error = xfs_alloc_read_agfl(mp, sc->tp, sc->sa.agno, &agfl_bp);
+	if (error)
+		return error;
+
+	/*
+	 * Spot-check the AGFL blocks; if they're obviously corrupt then
+	 * there's nothing we can do but bail out.
+	 */
+	error = xfs_agfl_walk(sc->mp, XFS_BUF_TO_AGF(agf_bp), agfl_bp,
+			xrep_agf_check_agfl_block, sc);
+	if (error)
+		return error;
+
+	/*
+	 * Find the AGF btree roots.  This is also a chicken-and-egg situation;
+	 * see the function for more details.
+	 */
+	error = xrep_agf_find_btrees(sc, agf_bp, fab, agfl_bp);
+	if (error)
+		return error;
+
+	/* Start rewriting the header and implant the btrees we found. */
+	xrep_agf_init_header(sc, agf_bp, &old_agf);
+	xrep_agf_set_roots(sc, agf, fab);
+	error = xrep_agf_calc_from_btrees(sc, agf_bp);
+	if (error)
+		goto out_revert;
+
+	/* Commit the changes and reinitialize incore state. */
+	return xrep_agf_commit_new(sc, agf_bp);
+
+out_revert:
+	/* Mark the incore AGF state stale and revert the AGF. */
+	sc->sa.pag->pagf_init = 0;
+	memcpy(agf, &old_agf, sizeof(old_agf));
+	return error;
+}
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 85b048b341a0..17cf48564390 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -128,9 +128,12 @@ xrep_roll_ag_trans(
 	int			error;
 
 	/* Keep the AG header buffers locked so we can keep going. */
-	xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bhold(sc->tp, sc->sa.agfl_bp);
 
 	/* Roll the transaction. */
 	error = xfs_trans_roll(&sc->tp);
@@ -138,9 +141,12 @@ xrep_roll_ag_trans(
 		goto out_release;
 
 	/* Join AG headers to the new transaction. */
-	xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bjoin(sc->tp, sc->sa.agfl_bp);
 
 	return 0;
 
@@ -150,9 +156,12 @@ out_release:
 	 * buffers will be released during teardown on our way out
 	 * of the kernel.
 	 */
-	xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
-	xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
-	xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
+	if (sc->sa.agi_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agi_bp);
+	if (sc->sa.agf_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agf_bp);
+	if (sc->sa.agfl_bp)
+		xfs_trans_bhold_release(sc->tp, sc->sa.agfl_bp);
 
 	return error;
 }
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 5a4e92221916..6f0903c51a47 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -58,6 +58,7 @@ int xrep_ino_dqattach(struct xfs_scrub *sc);
 
 int xrep_probe(struct xfs_scrub *sc);
 int xrep_superblock(struct xfs_scrub *sc);
+int xrep_agf(struct xfs_scrub *sc);
 
 #else
 
@@ -81,6 +82,7 @@ xrep_calc_ag_resblks(
 
 #define xrep_probe			xrep_notsupported
 #define xrep_superblock			xrep_notsupported
+#define xrep_agf			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 6efb926f3cf8..1e8a17c8e2b9 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -214,7 +214,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_agf,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_agf,
 	},
 	[XFS_SCRUB_TYPE_AGFL]= {	/* agfl */
 		.type	= ST_PERAG,
-- 
cgit v1.2.3


From 0e93d3f43ec7d3308bff25ce1be81d46330168c9 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 9 Aug 2018 22:43:02 -0700
Subject: xfs: repair the AGFL

Repair the AGFL from the rmap data.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/agheader_repair.c | 281 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/bitmap.c          |  92 ++++++++++++++
 fs/xfs/scrub/bitmap.h          |   4 +
 fs/xfs/scrub/repair.h          |   2 +
 fs/xfs/scrub/scrub.c           |   2 +-
 5 files changed, 380 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index aa180492a4a5..9ce302360bbb 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -433,3 +433,284 @@ out_revert:
 	memcpy(agf, &old_agf, sizeof(old_agf));
 	return error;
 }
+
+/* AGFL */
+
+struct xrep_agfl {
+	/* Bitmap of other OWN_AG metadata blocks. */
+	struct xfs_bitmap	agmetablocks;
+
+	/* Bitmap of free space. */
+	struct xfs_bitmap	*freesp;
+
+	struct xfs_scrub	*sc;
+};
+
+/* Record all OWN_AG (free space btree) information from the rmap data. */
+STATIC int
+xrep_agfl_walk_rmap(
+	struct xfs_btree_cur	*cur,
+	struct xfs_rmap_irec	*rec,
+	void			*priv)
+{
+	struct xrep_agfl	*ra = priv;
+	xfs_fsblock_t		fsb;
+	int			error = 0;
+
+	if (xchk_should_terminate(ra->sc, &error))
+		return error;
+
+	/* Record all the OWN_AG blocks. */
+	if (rec->rm_owner == XFS_RMAP_OWN_AG) {
+		fsb = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_private.a.agno,
+				rec->rm_startblock);
+		error = xfs_bitmap_set(ra->freesp, fsb, rec->rm_blockcount);
+		if (error)
+			return error;
+	}
+
+	return xfs_bitmap_set_btcur_path(&ra->agmetablocks, cur);
+}
+
+/*
+ * Map out all the non-AGFL OWN_AG space in this AG so that we can deduce
+ * which blocks belong to the AGFL.
+ *
+ * Compute the set of old AGFL blocks by subtracting from the list of OWN_AG
+ * blocks the list of blocks owned by all other OWN_AG metadata (bnobt, cntbt,
+ * rmapbt).  These are the old AGFL blocks, so return that list and the number
+ * of blocks we're actually going to put back on the AGFL.
+ */
+STATIC int
+xrep_agfl_collect_blocks(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	struct xfs_bitmap	*agfl_extents,
+	xfs_agblock_t		*flcount)
+{
+	struct xrep_agfl	ra;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_btree_cur	*cur;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*n;
+	int			error;
+
+	ra.sc = sc;
+	ra.freesp = agfl_extents;
+	xfs_bitmap_init(&ra.agmetablocks);
+
+	/* Find all space used by the free space btrees & rmapbt. */
+	cur = xfs_rmapbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno);
+	error = xfs_rmap_query_all(cur, xrep_agfl_walk_rmap, &ra);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	/* Find all blocks currently being used by the bnobt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_BNO);
+	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	/* Find all blocks currently being used by the cntbt. */
+	cur = xfs_allocbt_init_cursor(mp, sc->tp, agf_bp, sc->sa.agno,
+			XFS_BTNUM_CNT);
+	error = xfs_bitmap_set_btblocks(&ra.agmetablocks, cur);
+	if (error)
+		goto err;
+
+	xfs_btree_del_cursor(cur, error);
+
+	/*
+	 * Drop the freesp meta blocks that are in use by btrees.
+	 * The remaining blocks /should/ be AGFL blocks.
+	 */
+	error = xfs_bitmap_disunion(agfl_extents, &ra.agmetablocks);
+	xfs_bitmap_destroy(&ra.agmetablocks);
+	if (error)
+		return error;
+
+	/*
+	 * Calculate the new AGFL size.  If we found more blocks than fit in
+	 * the AGFL we'll free them later.
+	 */
+	*flcount = 0;
+	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
+		*flcount += br->len;
+		if (*flcount > xfs_agfl_size(mp))
+			break;
+	}
+	if (*flcount > xfs_agfl_size(mp))
+		*flcount = xfs_agfl_size(mp);
+	return 0;
+
+err:
+	xfs_bitmap_destroy(&ra.agmetablocks);
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Update the AGF and reset the in-core state. */
+STATIC void
+xrep_agfl_update_agf(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agf_bp,
+	xfs_agblock_t		flcount)
+{
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agf_bp);
+
+	ASSERT(flcount <= xfs_agfl_size(sc->mp));
+
+	/* Trigger fdblocks recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Update the AGF counters. */
+	if (sc->sa.pag->pagf_init)
+		sc->sa.pag->pagf_flcount = flcount;
+	agf->agf_flfirst = cpu_to_be32(0);
+	agf->agf_flcount = cpu_to_be32(flcount);
+	agf->agf_fllast = cpu_to_be32(flcount - 1);
+
+	xfs_alloc_log_agf(sc->tp, agf_bp,
+			XFS_AGF_FLFIRST | XFS_AGF_FLLAST | XFS_AGF_FLCOUNT);
+}
+
+/* Write out a totally new AGFL. */
+STATIC void
+xrep_agfl_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agfl_bp,
+	struct xfs_bitmap	*agfl_extents,
+	xfs_agblock_t		flcount)
+{
+	struct xfs_mount	*mp = sc->mp;
+	__be32			*agfl_bno;
+	struct xfs_bitmap_range	*br;
+	struct xfs_bitmap_range	*n;
+	struct xfs_agfl		*agfl;
+	xfs_agblock_t		agbno;
+	unsigned int		fl_off;
+
+	ASSERT(flcount <= xfs_agfl_size(mp));
+
+	/*
+	 * Start rewriting the header by setting the bno[] array to
+	 * NULLAGBLOCK, then setting AGFL header fields.
+	 */
+	agfl = XFS_BUF_TO_AGFL(agfl_bp);
+	memset(agfl, 0xFF, BBTOB(agfl_bp->b_length));
+	agfl->agfl_magicnum = cpu_to_be32(XFS_AGFL_MAGIC);
+	agfl->agfl_seqno = cpu_to_be32(sc->sa.agno);
+	uuid_copy(&agfl->agfl_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/*
+	 * Fill the AGFL with the remaining blocks.  If agfl_extents has more
+	 * blocks than fit in the AGFL, they will be freed in a subsequent
+	 * step.
+	 */
+	fl_off = 0;
+	agfl_bno = XFS_BUF_TO_AGFL_BNO(mp, agfl_bp);
+	for_each_xfs_bitmap_extent(br, n, agfl_extents) {
+		agbno = XFS_FSB_TO_AGBNO(mp, br->start);
+
+		trace_xrep_agfl_insert(mp, sc->sa.agno, agbno, br->len);
+
+		while (br->len > 0 && fl_off < flcount) {
+			agfl_bno[fl_off] = cpu_to_be32(agbno);
+			fl_off++;
+			agbno++;
+
+			/*
+			 * We've now used br->start by putting it in the AGFL,
+			 * so bump br so that we don't reap the block later.
+			 */
+			br->start++;
+			br->len--;
+		}
+
+		if (br->len)
+			break;
+		list_del(&br->list);
+		kmem_free(br);
+	}
+
+	/* Write new AGFL to disk. */
+	xfs_trans_buf_set_type(sc->tp, agfl_bp, XFS_BLFT_AGFL_BUF);
+	xfs_trans_log_buf(sc->tp, agfl_bp, 0, BBTOB(agfl_bp->b_length) - 1);
+}
+
+/* Repair the AGFL. */
+int
+xrep_agfl(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_owner_info	oinfo;
+	struct xfs_bitmap	agfl_extents;
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_buf		*agf_bp;
+	struct xfs_buf		*agfl_bp;
+	xfs_agblock_t		flcount;
+	int			error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	xfs_bitmap_init(&agfl_extents);
+
+	/*
+	 * Read the AGF so that we can query the rmapbt.  We hope that there's
+	 * nothing wrong with the AGF, but all the AG header repair functions
+	 * have this chicken-and-egg problem.
+	 */
+	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return -ENOMEM;
+
+	/*
+	 * Make sure we have the AGFL buffer, as scrub might have decided it
+	 * was corrupt after xfs_alloc_read_agfl failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGFL_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agfl_bp, NULL);
+	if (error)
+		return error;
+	agfl_bp->b_ops = &xfs_agfl_buf_ops;
+
+	/* Gather all the extents we're going to put on the new AGFL. */
+	error = xrep_agfl_collect_blocks(sc, agf_bp, &agfl_extents, &flcount);
+	if (error)
+		goto err;
+
+	/*
+	 * Update AGF and AGFL.  We reset the global free block counter when
+	 * we adjust the AGF flcount (which can fail) so avoid updating any
+	 * buffers until we know that part works.
+	 */
+	xrep_agfl_update_agf(sc, agf_bp, flcount);
+	xrep_agfl_init_header(sc, agfl_bp, &agfl_extents, flcount);
+
+	/*
+	 * Ok, the AGFL should be ready to go now.  Roll the transaction to
+	 * make the new AGFL permanent before we start using it to return
+	 * freespace overflow to the freespace btrees.
+	 */
+	sc->sa.agf_bp = agf_bp;
+	sc->sa.agfl_bp = agfl_bp;
+	error = xrep_roll_ag_trans(sc);
+	if (error)
+		goto err;
+
+	/* Dump any AGFL overflow. */
+	xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+	return xrep_reap_extents(sc, &agfl_extents, &oinfo, XFS_AG_RESV_AGFL);
+err:
+	xfs_bitmap_destroy(&agfl_extents);
+	return error;
+}
diff --git a/fs/xfs/scrub/bitmap.c b/fs/xfs/scrub/bitmap.c
index c770e2d0b6aa..fdadc9e1dc49 100644
--- a/fs/xfs/scrub/bitmap.c
+++ b/fs/xfs/scrub/bitmap.c
@@ -9,6 +9,7 @@
 #include "xfs_format.h"
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
+#include "xfs_btree.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
@@ -209,3 +210,94 @@ out:
 }
 #undef LEFT_ALIGNED
 #undef RIGHT_ALIGNED
+
+/*
+ * Record all btree blocks seen while iterating all records of a btree.
+ *
+ * We know that the btree query_all function starts at the left edge and walks
+ * towards the right edge of the tree.  Therefore, we know that we can walk up
+ * the btree cursor towards the root; if the pointer for a given level points
+ * to the first record/key in that block, we haven't seen this block before;
+ * and therefore we need to remember that we saw this block in the btree.
+ *
+ * So if our btree is:
+ *
+ *    4
+ *  / | \
+ * 1  2  3
+ *
+ * Pretend for this example that each leaf block has 100 btree records.  For
+ * the first btree record, we'll observe that bc_ptrs[0] == 1, so we record
+ * that we saw block 1.  Then we observe that bc_ptrs[1] == 1, so we record
+ * block 4.  The list is [1, 4].
+ *
+ * For the second btree record, we see that bc_ptrs[0] == 2, so we exit the
+ * loop.  The list remains [1, 4].
+ *
+ * For the 101st btree record, we've moved onto leaf block 2.  Now
+ * bc_ptrs[0] == 1 again, so we record that we saw block 2.  We see that
+ * bc_ptrs[1] == 2, so we exit the loop.  The list is now [1, 4, 2].
+ *
+ * For the 102nd record, bc_ptrs[0] == 2, so we continue.
+ *
+ * For the 201st record, we've moved on to leaf block 3.  bc_ptrs[0] == 1, so
+ * we add 3 to the list.  Now it is [1, 4, 2, 3].
+ *
+ * For the 300th record we just exit, with the list being [1, 4, 2, 3].
+ */
+
+/*
+ * Record all the buffers pointed to by the btree cursor.  Callers already
+ * engaged in a btree walk should call this function to capture the list of
+ * blocks going from the leaf towards the root.
+ */
+int
+xfs_bitmap_set_btcur_path(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsb;
+	int			i;
+	int			error;
+
+	for (i = 0; i < cur->bc_nlevels && cur->bc_ptrs[i] == 1; i++) {
+		xfs_btree_get_block(cur, i, &bp);
+		if (!bp)
+			continue;
+		fsb = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn);
+		error = xfs_bitmap_set(bitmap, fsb, 1);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Collect a btree's block in the bitmap. */
+STATIC int
+xfs_bitmap_collect_btblock(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	void			*priv)
+{
+	struct xfs_bitmap	*bitmap = priv;
+	struct xfs_buf		*bp;
+	xfs_fsblock_t		fsbno;
+
+	xfs_btree_get_block(cur, level, &bp);
+	if (!bp)
+		return 0;
+
+	fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, bp->b_bn);
+	return xfs_bitmap_set(bitmap, fsbno, 1);
+}
+
+/* Walk the btree and mark the bitmap wherever a btree block is found. */
+int
+xfs_bitmap_set_btblocks(
+	struct xfs_bitmap	*bitmap,
+	struct xfs_btree_cur	*cur)
+{
+	return xfs_btree_visit_blocks(cur, xfs_bitmap_collect_btblock, bitmap);
+}
diff --git a/fs/xfs/scrub/bitmap.h b/fs/xfs/scrub/bitmap.h
index dad652ee9177..ae8ecbce6fa6 100644
--- a/fs/xfs/scrub/bitmap.h
+++ b/fs/xfs/scrub/bitmap.h
@@ -28,5 +28,9 @@ void xfs_bitmap_destroy(struct xfs_bitmap *bitmap);
 
 int xfs_bitmap_set(struct xfs_bitmap *bitmap, uint64_t start, uint64_t len);
 int xfs_bitmap_disunion(struct xfs_bitmap *bitmap, struct xfs_bitmap *sub);
+int xfs_bitmap_set_btcur_path(struct xfs_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
+int xfs_bitmap_set_btblocks(struct xfs_bitmap *bitmap,
+		struct xfs_btree_cur *cur);
 
 #endif	/* __XFS_SCRUB_BITMAP_H__ */
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 6f0903c51a47..1d283360b5ab 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -59,6 +59,7 @@ int xrep_ino_dqattach(struct xfs_scrub *sc);
 int xrep_probe(struct xfs_scrub *sc);
 int xrep_superblock(struct xfs_scrub *sc);
 int xrep_agf(struct xfs_scrub *sc);
+int xrep_agfl(struct xfs_scrub *sc);
 
 #else
 
@@ -83,6 +84,7 @@ xrep_calc_ag_resblks(
 #define xrep_probe			xrep_notsupported
 #define xrep_superblock			xrep_notsupported
 #define xrep_agf			xrep_notsupported
+#define xrep_agfl			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 1e8a17c8e2b9..2670f4cf62f4 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -220,7 +220,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_agfl,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_agfl,
 	},
 	[XFS_SCRUB_TYPE_AGI] = {	/* agi */
 		.type	= ST_PERAG,
-- 
cgit v1.2.3


From 13942aa94a8b5df662d93c42c307b2f50cbe88b0 Mon Sep 17 00:00:00 2001
From: "Darrick J. Wong" <darrick.wong@oracle.com>
Date: Thu, 9 Aug 2018 22:43:04 -0700
Subject: xfs: repair the AGI

Rebuild the AGI header items with some help from the rmapbt.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
---
 fs/xfs/scrub/agheader_repair.c | 217 +++++++++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/repair.h          |   2 +
 fs/xfs/scrub/scrub.c           |   2 +-
 3 files changed, 220 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/scrub/agheader_repair.c b/fs/xfs/scrub/agheader_repair.c
index 9ce302360bbb..f7568a4b5fe5 100644
--- a/fs/xfs/scrub/agheader_repair.c
+++ b/fs/xfs/scrub/agheader_repair.c
@@ -714,3 +714,220 @@ err:
 	xfs_bitmap_destroy(&agfl_extents);
 	return error;
 }
+
+/* AGI */
+
+/*
+ * Offset within the xrep_find_ag_btree array for each btree type.  Avoid the
+ * XFS_BTNUM_ names here to avoid creating a sparse array.
+ */
+enum {
+	XREP_AGI_INOBT = 0,
+	XREP_AGI_FINOBT,
+	XREP_AGI_END,
+	XREP_AGI_MAX
+};
+
+/*
+ * Given the inode btree roots described by *fab, find the roots, check them
+ * for sanity, and pass the root data back out via *fab.
+ */
+STATIC int
+xrep_agi_find_btrees(
+	struct xfs_scrub		*sc,
+	struct xrep_find_ag_btree	*fab)
+{
+	struct xfs_buf			*agf_bp;
+	struct xfs_mount		*mp = sc->mp;
+	int				error;
+
+	/* Read the AGF. */
+	error = xfs_alloc_read_agf(mp, sc->tp, sc->sa.agno, 0, &agf_bp);
+	if (error)
+		return error;
+	if (!agf_bp)
+		return -ENOMEM;
+
+	/* Find the btree roots. */
+	error = xrep_find_ag_btree_roots(sc, agf_bp, fab, NULL);
+	if (error)
+		return error;
+
+	/* We must find the inobt root. */
+	if (!xrep_check_btree_root(sc, &fab[XREP_AGI_INOBT]))
+		return -EFSCORRUPTED;
+
+	/* We must find the finobt root if that feature is enabled. */
+	if (xfs_sb_version_hasfinobt(&mp->m_sb) &&
+	    !xrep_check_btree_root(sc, &fab[XREP_AGI_FINOBT]))
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
+/*
+ * Reinitialize the AGI header, making an in-core copy of the old contents so
+ * that we know which in-core state needs to be reinitialized.
+ */
+STATIC void
+xrep_agi_init_header(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp,
+	struct xfs_agi		*old_agi)
+{
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+	struct xfs_mount	*mp = sc->mp;
+
+	memcpy(old_agi, agi, sizeof(*old_agi));
+	memset(agi, 0, BBTOB(agi_bp->b_length));
+	agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
+	agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
+	agi->agi_seqno = cpu_to_be32(sc->sa.agno);
+	agi->agi_length = cpu_to_be32(xfs_ag_block_count(mp, sc->sa.agno));
+	agi->agi_newino = cpu_to_be32(NULLAGINO);
+	agi->agi_dirino = cpu_to_be32(NULLAGINO);
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		uuid_copy(&agi->agi_uuid, &mp->m_sb.sb_meta_uuid);
+
+	/* We don't know how to fix the unlinked list yet. */
+	memcpy(&agi->agi_unlinked, &old_agi->agi_unlinked,
+			sizeof(agi->agi_unlinked));
+
+	/* Mark the incore AGF data stale until we're done fixing things. */
+	ASSERT(sc->sa.pag->pagi_init);
+	sc->sa.pag->pagi_init = 0;
+}
+
+/* Set btree root information in an AGI. */
+STATIC void
+xrep_agi_set_roots(
+	struct xfs_scrub		*sc,
+	struct xfs_agi			*agi,
+	struct xrep_find_ag_btree	*fab)
+{
+	agi->agi_root = cpu_to_be32(fab[XREP_AGI_INOBT].root);
+	agi->agi_level = cpu_to_be32(fab[XREP_AGI_INOBT].height);
+
+	if (xfs_sb_version_hasfinobt(&sc->mp->m_sb)) {
+		agi->agi_free_root = cpu_to_be32(fab[XREP_AGI_FINOBT].root);
+		agi->agi_free_level = cpu_to_be32(fab[XREP_AGI_FINOBT].height);
+	}
+}
+
+/* Update the AGI counters. */
+STATIC int
+xrep_agi_calc_from_btrees(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp)
+{
+	struct xfs_btree_cur	*cur;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+	struct xfs_mount	*mp = sc->mp;
+	xfs_agino_t		count;
+	xfs_agino_t		freecount;
+	int			error;
+
+	cur = xfs_inobt_init_cursor(mp, sc->tp, agi_bp, sc->sa.agno,
+			XFS_BTNUM_INO);
+	error = xfs_ialloc_count_inodes(cur, &count, &freecount);
+	if (error)
+		goto err;
+	xfs_btree_del_cursor(cur, error);
+
+	agi->agi_count = cpu_to_be32(count);
+	agi->agi_freecount = cpu_to_be32(freecount);
+	return 0;
+err:
+	xfs_btree_del_cursor(cur, error);
+	return error;
+}
+
+/* Trigger reinitialization of the in-core data. */
+STATIC int
+xrep_agi_commit_new(
+	struct xfs_scrub	*sc,
+	struct xfs_buf		*agi_bp)
+{
+	struct xfs_perag	*pag;
+	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agi_bp);
+
+	/* Trigger inode count recalculation */
+	xfs_force_summary_recalc(sc->mp);
+
+	/* Write this to disk. */
+	xfs_trans_buf_set_type(sc->tp, agi_bp, XFS_BLFT_AGI_BUF);
+	xfs_trans_log_buf(sc->tp, agi_bp, 0, BBTOB(agi_bp->b_length) - 1);
+
+	/* Now reinitialize the in-core counters if necessary. */
+	pag = sc->sa.pag;
+	pag->pagi_count = be32_to_cpu(agi->agi_count);
+	pag->pagi_freecount = be32_to_cpu(agi->agi_freecount);
+	pag->pagi_init = 1;
+
+	return 0;
+}
+
+/* Repair the AGI. */
+int
+xrep_agi(
+	struct xfs_scrub		*sc)
+{
+	struct xrep_find_ag_btree	fab[XREP_AGI_MAX] = {
+		[XREP_AGI_INOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_INOBT,
+			.buf_ops = &xfs_inobt_buf_ops,
+			.magic = XFS_IBT_CRC_MAGIC,
+		},
+		[XREP_AGI_FINOBT] = {
+			.rmap_owner = XFS_RMAP_OWN_INOBT,
+			.buf_ops = &xfs_inobt_buf_ops,
+			.magic = XFS_FIBT_CRC_MAGIC,
+		},
+		[XREP_AGI_END] = {
+			.buf_ops = NULL
+		},
+	};
+	struct xfs_agi			old_agi;
+	struct xfs_mount		*mp = sc->mp;
+	struct xfs_buf			*agi_bp;
+	struct xfs_agi			*agi;
+	int				error;
+
+	/* We require the rmapbt to rebuild anything. */
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	xchk_perag_get(sc->mp, &sc->sa);
+	/*
+	 * Make sure we have the AGI buffer, as scrub might have decided it
+	 * was corrupt after xfs_ialloc_read_agi failed with -EFSCORRUPTED.
+	 */
+	error = xfs_trans_read_buf(mp, sc->tp, mp->m_ddev_targp,
+			XFS_AG_DADDR(mp, sc->sa.agno, XFS_AGI_DADDR(mp)),
+			XFS_FSS_TO_BB(mp, 1), 0, &agi_bp, NULL);
+	if (error)
+		return error;
+	agi_bp->b_ops = &xfs_agi_buf_ops;
+	agi = XFS_BUF_TO_AGI(agi_bp);
+
+	/* Find the AGI btree roots. */
+	error = xrep_agi_find_btrees(sc, fab);
+	if (error)
+		return error;
+
+	/* Start rewriting the header and implant the btrees we found. */
+	xrep_agi_init_header(sc, agi_bp, &old_agi);
+	xrep_agi_set_roots(sc, agi, fab);
+	error = xrep_agi_calc_from_btrees(sc, agi_bp);
+	if (error)
+		goto out_revert;
+
+	/* Reinitialize in-core state. */
+	return xrep_agi_commit_new(sc, agi_bp);
+
+out_revert:
+	/* Mark the incore AGI state stale and revert the AGI. */
+	sc->sa.pag->pagi_init = 0;
+	memcpy(agi, &old_agi, sizeof(old_agi));
+	return error;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 1d283360b5ab..9de321eee4ab 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -60,6 +60,7 @@ int xrep_probe(struct xfs_scrub *sc);
 int xrep_superblock(struct xfs_scrub *sc);
 int xrep_agf(struct xfs_scrub *sc);
 int xrep_agfl(struct xfs_scrub *sc);
+int xrep_agi(struct xfs_scrub *sc);
 
 #else
 
@@ -85,6 +86,7 @@ xrep_calc_ag_resblks(
 #define xrep_superblock			xrep_notsupported
 #define xrep_agf			xrep_notsupported
 #define xrep_agfl			xrep_notsupported
+#define xrep_agi			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 2670f4cf62f4..4bfae1e61d30 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -226,7 +226,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_PERAG,
 		.setup	= xchk_setup_fs,
 		.scrub	= xchk_agi,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_agi,
 	},
 	[XFS_SCRUB_TYPE_BNOBT] = {	/* bnobt */
 		.type	= ST_PERAG,
-- 
cgit v1.2.3


From dc1508a579e682a1e5f1ed0753390e0aa7c23a97 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 9 Aug 2018 08:55:19 -0700
Subject: bpf: fix bpffs non-array map seq_show issue

In function map_seq_next() of kernel/bpf/inode.c,
the first key will be the "0" regardless of the map type.
This works for array. But for hash type, if it happens
key "0" is in the map, the bpffs map show will miss
some items if the key "0" is not the first element of
the first bucket.

This patch fixed the issue by guaranteeing to get
the first element, if the seq_show is just started,
by passing NULL pointer key to map_get_next_key() callback.
This way, no missing elements will occur for
bpffs hash table show even if key "0" is in the map.

Fixes: a26ca7c982cb5 ("bpf: btf: Add pretty print support to the basic arraymap")
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/inode.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index 76efe9a183f5..fc5b103512e7 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -196,19 +196,21 @@ static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct bpf_map *map = seq_file_to_map(m);
 	void *key = map_iter(m)->key;
+	void *prev_key;
 
 	if (map_iter(m)->done)
 		return NULL;
 
 	if (unlikely(v == SEQ_START_TOKEN))
-		goto done;
+		prev_key = NULL;
+	else
+		prev_key = key;
 
-	if (map->ops->map_get_next_key(map, key, key)) {
+	if (map->ops->map_get_next_key(map, prev_key, key)) {
 		map_iter(m)->done = true;
 		return NULL;
 	}
 
-done:
 	++(*pos);
 	return key;
 }
-- 
cgit v1.2.3


From 699c86d6ec21d0f885d12800249d138659de8489 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 9 Aug 2018 08:55:20 -0700
Subject: bpf: btf: add pretty print for hash/lru_hash maps

Commit a26ca7c982cb ("bpf: btf: Add pretty print support to
the basic arraymap") added pretty print support to array map.
This patch adds pretty print for hash and lru_hash maps.
The following example shows the pretty-print result of
a pinned hashmap:

    struct map_value {
            int count_a;
            int count_b;
    };

    cat /sys/fs/bpf/pinned_hash_map:

    87907: {87907,87908}
    57354: {37354,57355}
    76625: {76625,76626}
    ...

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 kernel/bpf/hashtab.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 513d9dfcf4ee..d6110042e0d9 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -11,9 +11,11 @@
  * General Public License for more details.
  */
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/jhash.h>
 #include <linux/filter.h>
 #include <linux/rculist_nulls.h>
+#include <uapi/linux/btf.h>
 #include "percpu_freelist.h"
 #include "bpf_lru_list.h"
 #include "map_in_map.h"
@@ -1162,6 +1164,44 @@ static void htab_map_free(struct bpf_map *map)
 	kfree(htab);
 }
 
+static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
+				   struct seq_file *m)
+{
+	void *value;
+
+	rcu_read_lock();
+
+	value = htab_map_lookup_elem(map, key);
+	if (!value) {
+		rcu_read_unlock();
+		return;
+	}
+
+	btf_type_seq_show(map->btf, map->btf_key_type_id, key, m);
+	seq_puts(m, ": ");
+	btf_type_seq_show(map->btf, map->btf_value_type_id, value, m);
+	seq_puts(m, "\n");
+
+	rcu_read_unlock();
+}
+
+static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf,
+			      u32 btf_key_id, u32 btf_value_id)
+{
+	const struct btf_type *key_type, *value_type;
+	u32 key_size, value_size;
+
+	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+	if (!key_type || key_size != map->key_size)
+		return -EINVAL;
+
+	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
+	if (!value_type || value_size != map->value_size)
+		return -EINVAL;
+
+	return 0;
+}
+
 const struct bpf_map_ops htab_map_ops = {
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
@@ -1171,6 +1211,8 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_update_elem = htab_map_update_elem,
 	.map_delete_elem = htab_map_delete_elem,
 	.map_gen_lookup = htab_map_gen_lookup,
+	.map_seq_show_elem = htab_map_seq_show_elem,
+	.map_check_btf = htab_map_check_btf,
 };
 
 const struct bpf_map_ops htab_lru_map_ops = {
@@ -1182,6 +1224,8 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_update_elem = htab_lru_map_update_elem,
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_gen_lookup = htab_lru_map_gen_lookup,
+	.map_seq_show_elem = htab_map_seq_show_elem,
+	.map_check_btf = htab_map_check_btf,
 };
 
 /* Called from eBPF program */
-- 
cgit v1.2.3


From af2a81dab44758de0b94679615ea75e8ee30aace Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Thu, 9 Aug 2018 08:55:21 -0700
Subject: tools/bpf: add bpffs pretty print btf test for hash/lru_hash maps

Pretty print tests for hash/lru_hash maps are added in test_btf.c.
The btf type blob is the same as pretty print array map test.
The test result:
  $ mount -t bpf bpf /sys/fs/bpf
  $ ./test_btf -p
    BTF pretty print array......OK
    BTF pretty print hash......OK
    BTF pretty print lru hash......OK
    PASS:3 SKIP:0 FAIL:0

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/test_btf.c | 87 ++++++++++++++++++++++++++++------
 1 file changed, 72 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index ffdd27737c9e..7fa8c800c540 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -131,6 +131,8 @@ struct btf_raw_test {
 	__u32 max_entries;
 	bool btf_load_err;
 	bool map_create_err;
+	bool ordered_map;
+	bool lossless_map;
 	int hdr_len_delta;
 	int type_off_delta;
 	int str_off_delta;
@@ -2093,8 +2095,7 @@ struct pprint_mapv {
 	} aenum;
 };
 
-static struct btf_raw_test pprint_test = {
-	.descr = "BTF pretty print test #1",
+static struct btf_raw_test pprint_test_template = {
 	.raw_types = {
 		/* unsighed char */			/* [1] */
 		BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1),
@@ -2146,8 +2147,6 @@ static struct btf_raw_test pprint_test = {
 	},
 	.str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum",
 	.str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"),
-	.map_type = BPF_MAP_TYPE_ARRAY,
-	.map_name = "pprint_test",
 	.key_size = sizeof(unsigned int),
 	.value_size = sizeof(struct pprint_mapv),
 	.key_type_id = 3,	/* unsigned int */
@@ -2155,6 +2154,40 @@ static struct btf_raw_test pprint_test = {
 	.max_entries = 128 * 1024,
 };
 
+static struct btf_pprint_test_meta {
+	const char *descr;
+	enum bpf_map_type map_type;
+	const char *map_name;
+	bool ordered_map;
+	bool lossless_map;
+} pprint_tests_meta[] = {
+{
+	.descr = "BTF pretty print array",
+	.map_type = BPF_MAP_TYPE_ARRAY,
+	.map_name = "pprint_test_array",
+	.ordered_map = true,
+	.lossless_map = true,
+},
+
+{
+	.descr = "BTF pretty print hash",
+	.map_type = BPF_MAP_TYPE_HASH,
+	.map_name = "pprint_test_hash",
+	.ordered_map = false,
+	.lossless_map = true,
+},
+
+{
+	.descr = "BTF pretty print lru hash",
+	.map_type = BPF_MAP_TYPE_LRU_HASH,
+	.map_name = "pprint_test_lru_hash",
+	.ordered_map = false,
+	.lossless_map = false,
+},
+
+};
+
+
 static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
 {
 	v->ui32 = i;
@@ -2166,10 +2199,12 @@ static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i)
 	v->aenum = i & 0x03;
 }
 
-static int test_pprint(void)
+static int do_test_pprint(void)
 {
-	const struct btf_raw_test *test = &pprint_test;
+	const struct btf_raw_test *test = &pprint_test_template;
 	struct bpf_create_map_attr create_attr = {};
+	unsigned int key, nr_read_elems;
+	bool ordered_map, lossless_map;
 	int map_fd = -1, btf_fd = -1;
 	struct pprint_mapv mapv = {};
 	unsigned int raw_btf_size;
@@ -2178,7 +2213,6 @@ static int test_pprint(void)
 	char pin_path[255];
 	size_t line_len = 0;
 	char *line = NULL;
-	unsigned int key;
 	uint8_t *raw_btf;
 	ssize_t nread;
 	int err, ret;
@@ -2251,14 +2285,18 @@ static int test_pprint(void)
 		goto done;
 	}
 
-	key = 0;
+	nr_read_elems = 0;
+	ordered_map = test->ordered_map;
+	lossless_map = test->lossless_map;
 	do {
 		ssize_t nexpected_line;
+		unsigned int next_key;
 
-		set_pprint_mapv(&mapv, key);
+		next_key = ordered_map ? nr_read_elems : atoi(line);
+		set_pprint_mapv(&mapv, next_key);
 		nexpected_line = snprintf(expected_line, sizeof(expected_line),
 					  "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n",
-					  key,
+					  next_key,
 					  mapv.ui32, mapv.si32,
 					  mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b,
 					  mapv.ui64,
@@ -2281,11 +2319,12 @@ static int test_pprint(void)
 		}
 
 		nread = getline(&line, &line_len, pin_file);
-	} while (++key < test->max_entries && nread > 0);
+	} while (++nr_read_elems < test->max_entries && nread > 0);
 
-	if (CHECK(key < test->max_entries,
-		  "Unexpected EOF. key:%u test->max_entries:%u",
-		  key, test->max_entries)) {
+	if (lossless_map &&
+	    CHECK(nr_read_elems < test->max_entries,
+		  "Unexpected EOF. nr_read_elems:%u test->max_entries:%u",
+		  nr_read_elems, test->max_entries)) {
 		err = -1;
 		goto done;
 	}
@@ -2314,6 +2353,24 @@ done:
 	return err;
 }
 
+static int test_pprint(void)
+{
+	unsigned int i;
+	int err = 0;
+
+	for (i = 0; i < ARRAY_SIZE(pprint_tests_meta); i++) {
+		pprint_test_template.descr = pprint_tests_meta[i].descr;
+		pprint_test_template.map_type = pprint_tests_meta[i].map_type;
+		pprint_test_template.map_name = pprint_tests_meta[i].map_name;
+		pprint_test_template.ordered_map = pprint_tests_meta[i].ordered_map;
+		pprint_test_template.lossless_map = pprint_tests_meta[i].lossless_map;
+
+		err |= count_result(do_test_pprint());
+	}
+
+	return err;
+}
+
 static void usage(const char *cmd)
 {
 	fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n",
@@ -2409,7 +2466,7 @@ int main(int argc, char **argv)
 		err |= test_file();
 
 	if (args.pprint_test)
-		err |= count_result(test_pprint());
+		err |= test_pprint();
 
 	if (args.raw_test || args.get_info_test || args.file_test ||
 	    args.pprint_test)
-- 
cgit v1.2.3


From da2048b7348a0be92f706ac019e022139e29495e Mon Sep 17 00:00:00 2001
From: Mauro Carvalho Chehab <mchehab+samsung@kernel.org>
Date: Fri, 10 Aug 2018 15:06:18 -0400
Subject: Revert "media: vivid: shut up warnings due to a non-trivial logic"

0day kernel testing robot got the below dmesg and the first bad commit is

https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git master
commit 3354b54f9f7037a1122d3b6009aa9d39829d6843

[  248.847809] BUG: unable to handle kernel paging request at ffffc90000393131

[  248.848015] Call Trace:
[  248.848015]  ? vivid_dev_release+0xc0/0xc0
[  248.848015]  ? acpi_dev_pm_attach+0x27/0xd0

This reverts commit 3354b54f9f7037a1122d3b6009aa9d39829d6843.
---
 drivers/media/platform/vivid/vivid-core.c | 21 ++-------------------
 1 file changed, 2 insertions(+), 19 deletions(-)

diff --git a/drivers/media/platform/vivid/vivid-core.c b/drivers/media/platform/vivid/vivid-core.c
index 4c235ea27987..31db363602e5 100644
--- a/drivers/media/platform/vivid/vivid-core.c
+++ b/drivers/media/platform/vivid/vivid-core.c
@@ -647,7 +647,6 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	unsigned node_type = node_types[inst];
 	unsigned int allocator = allocators[inst];
 	v4l2_std_id tvnorms_cap = 0, tvnorms_out = 0;
-	char *strings_base;
 	int ret;
 	int i;
 
@@ -860,33 +859,17 @@ static int vivid_create_instance(struct platform_device *pdev, int inst)
 	/* create a string array containing the names of all the preset timings */
 	while (v4l2_dv_timings_presets[dev->query_dv_timings_size].bt.width)
 		dev->query_dv_timings_size++;
-
-	/*
-	 * In order to save one allocation and an extra free, let's optimize
-	 * the allocation here: we'll use the first elements of the
-	 * dev->query_dv_timings_qmenu to store the timing strings pointer,
-	 * adding an extra space there to a store a string up to 32 bytes.
-	 * So, instead of allocating an array with size of:
-	 * 	dev->query_dv_timings_size * (sizeof(void *)
-	 * it will allocate:
-	 * 	dev->query_dv_timings_size * (sizeof(void *) +
-	 *	dev->query_dv_timings_size * 32
-	 */
 	dev->query_dv_timings_qmenu = kmalloc_array(dev->query_dv_timings_size,
 						    (sizeof(void *) + 32),
 						    GFP_KERNEL);
 	if (dev->query_dv_timings_qmenu == NULL)
 		goto free_dev;
-
-	/* Sets strings_base to be after the space to store the pointers */
-	strings_base = ((char *)&dev->query_dv_timings_qmenu)
-		       + dev->query_dv_timings_size * sizeof(void *);
-
 	for (i = 0; i < dev->query_dv_timings_size; i++) {
 		const struct v4l2_bt_timings *bt = &v4l2_dv_timings_presets[i].bt;
-		char *p = strings_base + i * 32;
+		char *p = (char *)&dev->query_dv_timings_qmenu[dev->query_dv_timings_size];
 		u32 htot, vtot;
 
+		p += i * 32;
 		dev->query_dv_timings_qmenu[i] = p;
 
 		htot = V4L2_DV_BT_FRAME_WIDTH(bt);
-- 
cgit v1.2.3


From d878efce73fe86db34ddb2013260adf571a701a7 Mon Sep 17 00:00:00 2001
From: Joerg Roedel <jroedel@suse.de>
Date: Wed, 8 Aug 2018 13:16:40 +0200
Subject: x86/mm/pti: Move user W+X check into pti_finalize()

The user page-table gets the updated kernel mappings in pti_finalize(),
which runs after the RO+X permissions got applied to the kernel page-table
in mark_readonly().

But with CONFIG_DEBUG_WX enabled, the user page-table is already checked in
mark_readonly() for insecure mappings.  This causes false-positive
warnings, because the user page-table did not get the updated mappings yet.

Move the W+X check for the user page-table into pti_finalize() after it
updated all required mappings.

[ tglx: Folded !NX supported fix ]

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1533727000-9172-1-git-send-email-joro@8bytes.org
---
 arch/x86/include/asm/pgtable.h | 7 +++++--
 arch/x86/mm/dump_pagetables.c  | 6 +++---
 arch/x86/mm/pti.c              | 2 ++
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index e39088cb59ab..a1cb3339da8d 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -30,11 +30,14 @@ int __init __early_make_pgtable(unsigned long address, pmdval_t pmd);
 void ptdump_walk_pgd_level(struct seq_file *m, pgd_t *pgd);
 void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user);
 void ptdump_walk_pgd_level_checkwx(void);
+void ptdump_walk_user_pgd_level_checkwx(void);
 
 #ifdef CONFIG_DEBUG_WX
-#define debug_checkwx() ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx()		ptdump_walk_pgd_level_checkwx()
+#define debug_checkwx_user()	ptdump_walk_user_pgd_level_checkwx()
 #else
-#define debug_checkwx() do { } while (0)
+#define debug_checkwx()		do { } while (0)
+#define debug_checkwx_user()	do { } while (0)
 #endif
 
 /*
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index ccd92c4da57c..a12afff146d1 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -569,12 +569,13 @@ void ptdump_walk_pgd_level_debugfs(struct seq_file *m, pgd_t *pgd, bool user)
 }
 EXPORT_SYMBOL_GPL(ptdump_walk_pgd_level_debugfs);
 
-static void ptdump_walk_user_pgd_level_checkwx(void)
+void ptdump_walk_user_pgd_level_checkwx(void)
 {
 #ifdef CONFIG_PAGE_TABLE_ISOLATION
 	pgd_t *pgd = INIT_PGD;
 
-	if (!static_cpu_has(X86_FEATURE_PTI))
+	if (!(__supported_pte_mask & _PAGE_NX) ||
+	    !static_cpu_has(X86_FEATURE_PTI))
 		return;
 
 	pr_info("x86/mm: Checking user space page tables\n");
@@ -586,7 +587,6 @@ static void ptdump_walk_user_pgd_level_checkwx(void)
 void ptdump_walk_pgd_level_checkwx(void)
 {
 	ptdump_walk_pgd_level_core(NULL, NULL, true, false);
-	ptdump_walk_user_pgd_level_checkwx();
 }
 
 static int __init pt_dump_init(void)
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 1dc5c683e7a5..d58b4aba9510 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -646,4 +646,6 @@ void pti_finalize(void)
 	 */
 	pti_clone_entry_text();
 	pti_clone_kernel_text();
+
+	debug_checkwx_user();
 }
-- 
cgit v1.2.3


From 01f1974e5f08732de6cecc4287788a99cfc3b325 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzk@kernel.org>
Date: Mon, 6 Aug 2018 18:33:40 +0200
Subject: pinctrl: samsung: Remove duplicated "wakeup" in printk

Double "wakeup" appears in printed message.

Signed-off-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/samsung/pinctrl-exynos.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 40ef14956876..f49ea3d92aa1 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -588,7 +588,7 @@ exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
 
 	pmu_regs = drvdata->retention_ctrl->priv;
 	dev_info(drvdata->dev,
-		 "Setting external wakeup interrupt wakeup mask: 0x%x\n",
+		 "Setting external wakeup interrupt mask: 0x%x\n",
 		 irq_chip->eint_wake_mask_value);
 
 	regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg,
-- 
cgit v1.2.3


From 6ff0497402ef7269ee6a72f62eb85adaa7a4768e Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Mon, 6 Aug 2018 10:48:01 +0100
Subject: gpiolib: Fix of_node inconsistency

Some platforms are not setting of_node in the driver. On these platforms
defining gpio-reserved-ranges on device tree leads to kernel crash.

It is due to some parts of the gpio core relying on the driver to set up
of_node,while other parts do themselves.This inconsistent behaviour leads
to a crash.

gpiochip_add_data_with_key() calls gpiochip_init_valid_mask() with of_node
as NULL. of_gpiochip_add() fills "of_node" and calls
of_gpiochip_init_valid_mask().

The fix is to move the assignment to chip->of_node from of_gpiochip_add()
to gpiochip_add_data_with_key().

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib-of.c | 3 ---
 drivers/gpio/gpiolib.c    | 2 ++
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 28d968088131..91174bf15cf3 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -620,9 +620,6 @@ int of_gpiochip_add(struct gpio_chip *chip)
 {
 	int status;
 
-	if ((!chip->of_node) && (chip->parent))
-		chip->of_node = chip->parent->of_node;
-
 	if (!chip->of_node)
 		return 0;
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 6bfd4e5cc161..2c457e604403 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1262,6 +1262,8 @@ int gpiochip_add_data_with_key(struct gpio_chip *chip, void *data,
 	/* If the gpiochip has an assigned OF node this takes precedence */
 	if (chip->of_node)
 		gdev->dev.of_node = chip->of_node;
+	else
+		chip->of_node = gdev->dev.of_node;
 #endif
 
 	gdev->id = ida_simple_get(&gpio_ida, 0, 0, GFP_KERNEL);
-- 
cgit v1.2.3


From 32e49b9a808a59791513ec59fec6466d8577a5fa Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 6 Aug 2018 16:18:05 +0200
Subject: gpio: tb10x: Use the right include

This driver includes the legacy <linux/gpio.h> and
<linux/of_gpio.h> but all it needs is really <linux/gpio/driver.h>.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tb10x.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-tb10x.c b/drivers/gpio/gpio-tb10x.c
index ac6f2a9841e5..a12cd0b5c972 100644
--- a/drivers/gpio/gpio-tb10x.c
+++ b/drivers/gpio/gpio-tb10x.c
@@ -22,7 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/slab.h>
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
@@ -30,7 +30,6 @@
 #include <linux/io.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
-#include <linux/of_gpio.h>
 #include <linux/spinlock.h>
 #include <linux/bitops.h>
 #include <linux/pinctrl/consumer.h>
-- 
cgit v1.2.3


From 50fe83a3eb5000a9ea3586e1fcd8034bd3892b90 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 6 Aug 2018 17:42:46 +0200
Subject: gpio: timberdale: Include the right header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is a GPIO driver so include only <linux/gpio/driver.h>.

Cc: Richard Röjfors <richard.rojfors@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-timberdale.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index 6520a8475910..314e300d6ba3 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -22,7 +22,7 @@
  */
 
 #include <linux/init.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/platform_device.h>
 #include <linux/irq.h>
 #include <linux/io.h>
-- 
cgit v1.2.3


From 504c76979bccec66e4c2e41f6a006e49e284466f Mon Sep 17 00:00:00 2001
From: Anton Vasilyev <vasilyev@ispras.ru>
Date: Mon, 6 Aug 2018 19:06:35 +0300
Subject: pinctrl: axp209: Fix NULL pointer dereference after allocation

There is no check that allocation in axp20x_funcs_groups_from_mask
is successful.
The patch adds corresponding check and return values.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Anton Vasilyev <vasilyev@ispras.ru>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/pinctrl-axp209.c | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/drivers/pinctrl/pinctrl-axp209.c b/drivers/pinctrl/pinctrl-axp209.c
index a52779f33ad4..afd0b533c40a 100644
--- a/drivers/pinctrl/pinctrl-axp209.c
+++ b/drivers/pinctrl/pinctrl-axp209.c
@@ -316,7 +316,7 @@ static const struct pinctrl_ops axp20x_pctrl_ops = {
 	.get_group_pins		= axp20x_group_pins,
 };
 
-static void axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
+static int axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
 					  unsigned int mask_len,
 					  struct axp20x_pinctrl_function *func,
 					  const struct pinctrl_pin_desc *pins)
@@ -331,18 +331,22 @@ static void axp20x_funcs_groups_from_mask(struct device *dev, unsigned int mask,
 		func->groups = devm_kcalloc(dev,
 					    ngroups, sizeof(const char *),
 					    GFP_KERNEL);
+		if (!func->groups)
+			return -ENOMEM;
 		group = func->groups;
 		for_each_set_bit(bit, &mask_cpy, mask_len) {
 			*group = pins[bit].name;
 			group++;
 		}
 	}
+
+	return 0;
 }
 
-static void axp20x_build_funcs_groups(struct platform_device *pdev)
+static int axp20x_build_funcs_groups(struct platform_device *pdev)
 {
 	struct axp20x_pctl *pctl = platform_get_drvdata(pdev);
-	int i, pin, npins = pctl->desc->npins;
+	int i, ret, pin, npins = pctl->desc->npins;
 
 	pctl->funcs[AXP20X_FUNC_GPIO_OUT].name = "gpio_out";
 	pctl->funcs[AXP20X_FUNC_GPIO_OUT].muxval = AXP20X_MUX_GPIO_OUT;
@@ -366,13 +370,19 @@ static void axp20x_build_funcs_groups(struct platform_device *pdev)
 			pctl->funcs[i].groups[pin] = pctl->desc->pins[pin].name;
 	}
 
-	axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->ldo_mask,
+	ret = axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->ldo_mask,
 				      npins, &pctl->funcs[AXP20X_FUNC_LDO],
 				      pctl->desc->pins);
+	if (ret)
+		return ret;
 
-	axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->adc_mask,
+	ret = axp20x_funcs_groups_from_mask(&pdev->dev, pctl->desc->adc_mask,
 				      npins, &pctl->funcs[AXP20X_FUNC_ADC],
 				      pctl->desc->pins);
+	if (ret)
+		return ret;
+
+	return 0;
 }
 
 static const struct of_device_id axp20x_pctl_match[] = {
@@ -424,7 +434,11 @@ static int axp20x_pctl_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pctl);
 
-	axp20x_build_funcs_groups(pdev);
+	ret = axp20x_build_funcs_groups(pdev);
+	if (ret) {
+		dev_err(&pdev->dev, "failed to build groups\n");
+		return ret;
+	}
 
 	pctrl_desc = devm_kzalloc(&pdev->dev, sizeof(*pctrl_desc), GFP_KERNEL);
 	if (!pctrl_desc)
-- 
cgit v1.2.3


From c2944a9a09a21b917fa86858f078e77115ca9d22 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Wed, 8 Aug 2018 15:04:49 +0300
Subject: pinctrl: nomadik: silence uninitialized variable warning

This is harmless, but "val" isn't necessarily initialized if
abx500_get_register_interruptible() fails.  I've re-arranged the code to
just return an error code in that situation.

Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/nomadik/pinctrl-abx500.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index aa592ef23a29..e3689cc62a41 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -101,15 +101,16 @@ static int abx500_gpio_get_bit(struct gpio_chip *chip, u8 reg,
 	reg += offset / 8;
 	ret = abx500_get_register_interruptible(pct->dev,
 						AB8500_MISC, reg, &val);
-
-	*bit = !!(val & BIT(pos));
-
-	if (ret < 0)
+	if (ret < 0) {
 		dev_err(pct->dev,
 			"%s read reg =%x, offset=%x failed (%d)\n",
 			__func__, reg, offset, ret);
+		return ret;
+	}
 
-	return ret;
+	*bit = !!(val & BIT(pos));
+
+	return 0;
 }
 
 static int abx500_gpio_set_bits(struct gpio_chip *chip, u8 reg,
-- 
cgit v1.2.3


From 516df4eb284d5a5ee8f80f7b59170ba8e919b299 Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 6 Aug 2018 18:39:59 +0200
Subject: gpio: xilinx: Use the right include

This is a GPIO driver so use only <linux/gpio/driver.h>.

Acked-by: Michal Simek <michal.simek@xilinx.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-xilinx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index e8ec0e33a0a9..8f24478cc18b 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -20,7 +20,7 @@
 #include <linux/of_platform.h>
 #include <linux/of_gpio.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/slab.h>
 
 /* Register Offset Definitions */
-- 
cgit v1.2.3


From d799a4de0a250f1bdd99765bb8e55a5e2f469a1f Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Fri, 3 Aug 2018 00:52:18 +0200
Subject: gpio: mmio: Fix up inverted direction registers

The bgpio_init() takes one of two arguments to specify a register
to set the direction of the GPIO line: either dirout that
indicates that a 1 in the bit in that register sets the
corresponding line to output, or dirin which indicates that
a 1 in the bit in that register sets the corresponding line to
input. Conversely setting the bit to 0 on these will turn the
line into input and output respectively. One of these can
be defined but not both.

This means that a platform that sets a bit to 1 for output
only defines dirout and a platform that sets a bit to 0 for
output only defines dirin. In short this defines the polarity
of the direction register.

Both can also be left as NULL meaning the GPIO chip is either
input only or output only.

Tomer Maimon discovered that for get/set chips (those where the
get and set registers are defined but no separate clear register,
and specifying BGPIOF_READ_OUTPUT_REG_SET so that we say we
want to read the output value from the SET register)
we are unconditionally reading the value from the SET register
when the direction bit is 1 and from the DAT register when the
direction bit is 0, not taking the direction bit polarity into
account.

It would be expected that when the direction bit is inverted
(dirin is defined but not dirout) we read the current value from
the DAT register when the bit is 1 and from the SET register
when the bit is 0.

Currently only some versions of ATH79, brcmstb, some versions of
CLP711x, GE, IOP and Loongson use the dirin mode (a 1 in the
register means input). They are unaffected because
BGPIOF_READ_OUTPUT_REG_SET is not set on any of them. (They
do not read back the SET register to figure out the output
value.) So this is no regression with current drivers.

However the behaviour is wrong and does not work with Tomer's
new driver where he needs to use the BGIOF_READ_OUTPUT_REG_SET.
This fixes the above issue by:

- Instead of defining separate functions for the inverted case,
  set up a flag in the gpio_chip that indicates that the
  direction is inverted.
- Remove the special inverted functions for setting
  input/output and getting the direction, rely on the flag
  instead.
- Respect this flag in bgpio_get_set() and
  bgpio_get_set_multiple()

Reported-by: Tomer Maimon <tmaimon77@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-mmio.c    | 108 ++++++++++++++++++++++++++------------------
 include/linux/gpio/driver.h |   3 ++
 2 files changed, 66 insertions(+), 45 deletions(-)

diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index 7b14d6280e44..935292a30c99 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -136,8 +136,20 @@ static unsigned long bgpio_line2mask(struct gpio_chip *gc, unsigned int line)
 static int bgpio_get_set(struct gpio_chip *gc, unsigned int gpio)
 {
 	unsigned long pinmask = bgpio_line2mask(gc, gpio);
+	bool dir = !!(gc->bgpio_dir & pinmask);
 
-	if (gc->bgpio_dir & pinmask)
+	/*
+	 * If the direction is OUT we read the value from the SET
+	 * register, and if the direction is IN we read the value
+	 * from the DAT register.
+	 *
+	 * If the direction bits are inverted, naturally this gets
+	 * inverted too.
+	 */
+	if (gc->bgpio_dir_inverted)
+		dir = !dir;
+
+	if (dir)
 		return !!(gc->read_reg(gc->reg_set) & pinmask);
 	else
 		return !!(gc->read_reg(gc->reg_dat) & pinmask);
@@ -157,8 +169,13 @@ static int bgpio_get_set_multiple(struct gpio_chip *gc, unsigned long *mask,
 	*bits &= ~*mask;
 
 	/* Exploit the fact that we know which directions are set */
-	set_mask = *mask & gc->bgpio_dir;
-	get_mask = *mask & ~gc->bgpio_dir;
+	if (gc->bgpio_dir_inverted) {
+		set_mask = *mask & ~gc->bgpio_dir;
+		get_mask = *mask & gc->bgpio_dir;
+	} else {
+		set_mask = *mask & gc->bgpio_dir;
+		get_mask = *mask & ~gc->bgpio_dir;
+	}
 
 	if (set_mask)
 		*bits |= gc->read_reg(gc->reg_set) & set_mask;
@@ -359,7 +376,10 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 
 	spin_lock_irqsave(&gc->bgpio_lock, flags);
 
-	gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
+	if (gc->bgpio_dir_inverted)
+		gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
+	else
+		gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
 	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
 
 	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
@@ -370,7 +390,10 @@ static int bgpio_dir_in(struct gpio_chip *gc, unsigned int gpio)
 static int bgpio_get_dir(struct gpio_chip *gc, unsigned int gpio)
 {
 	/* Return 0 if output, 1 of input */
-	return !(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
+	if (gc->bgpio_dir_inverted)
+		return !!(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
+	else
+		return !(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
 }
 
 static int bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
@@ -381,37 +404,10 @@ static int bgpio_dir_out(struct gpio_chip *gc, unsigned int gpio, int val)
 
 	spin_lock_irqsave(&gc->bgpio_lock, flags);
 
-	gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
-	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
-
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
-
-	return 0;
-}
-
-static int bgpio_dir_in_inv(struct gpio_chip *gc, unsigned int gpio)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
-
-	gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
-	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
-
-	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
-
-	return 0;
-}
-
-static int bgpio_dir_out_inv(struct gpio_chip *gc, unsigned int gpio, int val)
-{
-	unsigned long flags;
-
-	gc->set(gc, gpio, val);
-
-	spin_lock_irqsave(&gc->bgpio_lock, flags);
-
-	gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
+	if (gc->bgpio_dir_inverted)
+		gc->bgpio_dir &= ~bgpio_line2mask(gc, gpio);
+	else
+		gc->bgpio_dir |= bgpio_line2mask(gc, gpio);
 	gc->write_reg(gc->reg_dir, gc->bgpio_dir);
 
 	spin_unlock_irqrestore(&gc->bgpio_lock, flags);
@@ -419,12 +415,6 @@ static int bgpio_dir_out_inv(struct gpio_chip *gc, unsigned int gpio, int val)
 	return 0;
 }
 
-static int bgpio_get_dir_inv(struct gpio_chip *gc, unsigned int gpio)
-{
-	/* Return 0 if output, 1 if input */
-	return !!(gc->read_reg(gc->reg_dir) & bgpio_line2mask(gc, gpio));
-}
-
 static int bgpio_setup_accessors(struct device *dev,
 				 struct gpio_chip *gc,
 				 bool byte_be)
@@ -560,9 +550,10 @@ static int bgpio_setup_direction(struct gpio_chip *gc,
 		gc->get_direction = bgpio_get_dir;
 	} else if (dirin) {
 		gc->reg_dir = dirin;
-		gc->direction_output = bgpio_dir_out_inv;
-		gc->direction_input = bgpio_dir_in_inv;
-		gc->get_direction = bgpio_get_dir_inv;
+		gc->direction_output = bgpio_dir_out;
+		gc->direction_input = bgpio_dir_in;
+		gc->get_direction = bgpio_get_dir;
+		gc->bgpio_dir_inverted = true;
 	} else {
 		if (flags & BGPIOF_NO_OUTPUT)
 			gc->direction_output = bgpio_dir_out_err;
@@ -582,6 +573,33 @@ static int bgpio_request(struct gpio_chip *chip, unsigned gpio_pin)
 	return -EINVAL;
 }
 
+/**
+ * bgpio_init() - Initialize generic GPIO accessor functions
+ * @gc: the GPIO chip to set up
+ * @dev: the parent device of the new GPIO chip (compulsory)
+ * @sz: the size (width) of the MMIO registers in bytes, typically 1, 2 or 4
+ * @dat: MMIO address for the register to READ the value of the GPIO lines, it
+ *	is expected that a 1 in the corresponding bit in this register means the
+ *	line is asserted
+ * @set: MMIO address for the register to SET the value of the GPIO lines, it is
+ *	expected that we write the line with 1 in this register to drive the GPIO line
+ *	high.
+ * @clr: MMIO address for the register to CLEAR the value of the GPIO lines, it is
+ *	expected that we write the line with 1 in this register to drive the GPIO line
+ *	low. It is allowed to leave this address as NULL, in that case the SET register
+ *	will be assumed to also clear the GPIO lines, by actively writing the line
+ *	with 0.
+ * @dirout: MMIO address for the register to set the line as OUTPUT. It is assumed
+ *	that setting a line to 1 in this register will turn that line into an
+ *	output line. Conversely, setting the line to 0 will turn that line into
+ *	an input. Either this or @dirin can be defined, but never both.
+ * @dirin: MMIO address for the register to set this line as INPUT. It is assumed
+ *	that setting a line to 1 in this register will turn that line into an
+ *	input line. Conversely, setting the line to 0 will turn that line into
+ *	an output. Either this or @dirout can be defined, but never both.
+ * @flags: Different flags that will affect the behaviour of the device, such as
+ *	endianness etc.
+ */
 int bgpio_init(struct gpio_chip *gc, struct device *dev,
 	       unsigned long sz, void __iomem *dat, void __iomem *set,
 	       void __iomem *clr, void __iomem *dirout, void __iomem *dirin,
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 5382b5183b7e..0ea328e71ec9 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -201,6 +201,8 @@ static inline struct gpio_irq_chip *to_gpio_irq_chip(struct irq_chip *chip)
  * @reg_set: output set register (out=high) for generic GPIO
  * @reg_clr: output clear register (out=low) for generic GPIO
  * @reg_dir: direction setting register for generic GPIO
+ * @bgpio_dir_inverted: indicates that the direction register is inverted
+ *	(gpiolib private state variable)
  * @bgpio_bits: number of register bits used for a generic GPIO i.e.
  *	<register width> * 8
  * @bgpio_lock: used to lock chip->bgpio_data. Also, this is needed to keep
@@ -267,6 +269,7 @@ struct gpio_chip {
 	void __iomem *reg_set;
 	void __iomem *reg_clr;
 	void __iomem *reg_dir;
+	bool bgpio_dir_inverted;
 	int bgpio_bits;
 	spinlock_t bgpio_lock;
 	unsigned long bgpio_data;
-- 
cgit v1.2.3


From 21041daba2300c88f0da538b3480a9fae37430ea Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Mon, 6 Aug 2018 17:38:33 +0200
Subject: gpio: tegra: Include the right header

This is a GPIO driver so include only <linux/gpio/driver.h>.
Drop the use of GPIOF_* flags: these are for consumers, not
drivers. Just return 0/1.

Cc: Stefan Agner <stefan@agner.ch>
Cc: Thierry Reding <treding@nvidia.com>
Reviewed-by: Dmitry Osipenko <digetx@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-tegra.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 2d940785bad0..8e5f3150c6af 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -22,7 +22,7 @@
 #include <linux/irq.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
+#include <linux/gpio/driver.h>
 #include <linux/of_device.h>
 #include <linux/platform_device.h>
 #include <linux/module.h>
@@ -207,7 +207,7 @@ static int tegra_gpio_get_direction(struct gpio_chip *chip,
 
 	oe = tegra_gpio_readl(tgi, GPIO_OE(tgi, offset));
 
-	return (oe & pin_mask) ? GPIOF_DIR_OUT : GPIOF_DIR_IN;
+	return !(oe & pin_mask);
 }
 
 static int tegra_gpio_set_debounce(struct gpio_chip *chip, unsigned int offset,
-- 
cgit v1.2.3


From 3789f5acb9bbe088f70779002f32e7c6a64000bc Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das@bp.renesas.com>
Date: Tue, 7 Aug 2018 08:15:18 +0100
Subject: gpiolib: Avoid calling chip->request() for unused gpios

Add a check for unused gpios to avoid chip->request() call to client
driver for unused gpios.

Signed-off-by: Biju Das <biju.das@bp.renesas.com>
Reviewed-by: Fabrizio Castro <fabrizio.castro@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpiolib.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 2c457e604403..e8f8a1999393 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2267,6 +2267,7 @@ static int gpiod_request_commit(struct gpio_desc *desc, const char *label)
 	struct gpio_chip	*chip = desc->gdev->chip;
 	int			status;
 	unsigned long		flags;
+	unsigned		offset;
 
 	spin_lock_irqsave(&gpio_lock, flags);
 
@@ -2285,7 +2286,11 @@ static int gpiod_request_commit(struct gpio_desc *desc, const char *label)
 	if (chip->request) {
 		/* chip->request may sleep */
 		spin_unlock_irqrestore(&gpio_lock, flags);
-		status = chip->request(chip, gpio_chip_hwgpio(desc));
+		offset = gpio_chip_hwgpio(desc);
+		if (gpiochip_line_is_valid(chip, offset))
+			status = chip->request(chip, offset);
+		else
+			status = -EINVAL;
 		spin_lock_irqsave(&gpio_lock, flags);
 
 		if (status < 0) {
-- 
cgit v1.2.3


From 62885203f71b1116d6f56ae2e6014767e1d47995 Mon Sep 17 00:00:00 2001
From: Ivan Podovalov <ipodovalov@gmail.com>
Date: Wed, 8 Aug 2018 11:46:22 +0300
Subject: gpio: it87: add support for IT8718F Super I/O.

The DIO connector on the WAFER-945GSE is interfaced to GPIO ports
on the ITE IT8718F Super I/O chipset. From the datasheet of ITE IT8718F,
the GPIO interface is identical to IT8728, so just add it
to the same case as the other chip.

Signed-off-by: Ivan Podovalov <ipodovalov@gmail.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/gpio-it87.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c
index 7b017f43dc6b..d34f517fdd44 100644
--- a/drivers/gpio/gpio-it87.c
+++ b/drivers/gpio/gpio-it87.c
@@ -37,6 +37,7 @@
 #define NO_DEV_ID	0xffff
 #define IT8620_ID	0x8620
 #define IT8628_ID	0x8628
+#define IT8718_ID       0x8718
 #define IT8728_ID	0x8728
 #define IT8732_ID	0x8732
 #define IT8761_ID	0x8761
@@ -315,6 +316,7 @@ static int __init it87_gpio_init(void)
 		it87_gpio->simple_size = 0;
 		it87_gpio->chip.ngpio = 64;
 		break;
+	case IT8718_ID:
 	case IT8728_ID:
 	case IT8732_ID:
 	case IT8772_ID:
-- 
cgit v1.2.3


From a5ec96ddfd55c501d451cb310566a1170c267ecb Mon Sep 17 00:00:00 2001
From: Leonid Bloch <lbloch@janustech.com>
Date: Thu, 9 Aug 2018 01:26:36 +0300
Subject: gpio: it87: Add support for IT8613

This was tested on actual hardware and found to work fine, but currently
the official specifications of this chip could not be obtained to
confirm the numbers.

Signed-off-by: Leonid Bloch <lbloch@janustech.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/gpio/Kconfig     | 3 ++-
 drivers/gpio/gpio-it87.c | 9 +++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 7429b30e61b0..f7a0f576f918 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -693,7 +693,8 @@ config GPIO_IT87
 	  Say yes here to support GPIO functionality of IT87xx Super I/O chips.
 
 	  This driver is tested with ITE IT8728 and IT8732 Super I/O chips, and
-	  supports the IT8761E, IT8620E and IT8628E Super I/O chip as well.
+	  supports the IT8761E, IT8613, IT8620E, and IT8628E Super I/O chips as
+	  well.
 
 	  To compile this driver as a module, choose M here: the module will
 	  be called gpio_it87
diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c
index d34f517fdd44..389ecd8b7d26 100644
--- a/drivers/gpio/gpio-it87.c
+++ b/drivers/gpio/gpio-it87.c
@@ -35,6 +35,7 @@
 
 /* Chip Id numbers */
 #define NO_DEV_ID	0xffff
+#define IT8613_ID	0x8613
 #define IT8620_ID	0x8620
 #define IT8628_ID	0x8628
 #define IT8718_ID       0x8718
@@ -308,6 +309,14 @@ static int __init it87_gpio_init(void)
 	it87_gpio->chip = it87_template_chip;
 
 	switch (chip_type) {
+	case IT8613_ID:
+		gpio_ba_reg = 0x62;
+		it87_gpio->io_size = 8;  /* it8613 only needs 6, use 8 for alignment */
+		it87_gpio->output_base = 0xc8;
+		it87_gpio->simple_base = 0xc0;
+		it87_gpio->simple_size = 6;
+		it87_gpio->chip.ngpio = 64;  /* has 48, use 64 for convenient calc */
+		break;
 	case IT8620_ID:
 	case IT8628_ID:
 		gpio_ba_reg = 0x62;
-- 
cgit v1.2.3


From bc4fcd0a1b7635b012e5b2f3f0fb85a2d29fe13a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 10 Aug 2018 21:27:55 +0200
Subject: r8169: remove version info

The version number hasn't changed for ages and in general I doubt it
provides any benefit. The message in rtl_init_one() may even be
misleading because it's printed also if something fails in probe.
Therefore let's remove the version information.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 8ea1fa36ca43..77802a9d162e 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -32,7 +32,6 @@
 #include <asm/io.h>
 #include <asm/irq.h>
 
-#define RTL8169_VERSION "2.3LK-NAPI"
 #define MODULENAME "r8169"
 
 #define FIRMWARE_8168D_1	"rtl_nic/rtl8168d-1.fw"
@@ -784,7 +783,6 @@ MODULE_PARM_DESC(use_dac, "Enable PCI DAC. Unsafe on 32 bit PCI slot.");
 module_param_named(debug, debug.msg_enable, int, 0);
 MODULE_PARM_DESC(debug, "Debug verbosity level (0=none, ..., 16=all)");
 MODULE_LICENSE("GPL");
-MODULE_VERSION(RTL8169_VERSION);
 MODULE_FIRMWARE(FIRMWARE_8168D_1);
 MODULE_FIRMWARE(FIRMWARE_8168D_2);
 MODULE_FIRMWARE(FIRMWARE_8168E_1);
@@ -1635,7 +1633,6 @@ static void rtl8169_get_drvinfo(struct net_device *dev,
 	struct rtl_fw *rtl_fw = tp->rtl_fw;
 
 	strlcpy(info->driver, MODULENAME, sizeof(info->driver));
-	strlcpy(info->version, RTL8169_VERSION, sizeof(info->version));
 	strlcpy(info->bus_info, pci_name(tp->pci_dev), sizeof(info->bus_info));
 	BUILD_BUG_ON(sizeof(info->fw_version) < sizeof(rtl_fw->version));
 	if (!IS_ERR_OR_NULL(rtl_fw))
@@ -7292,11 +7289,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	int chipset, region, i;
 	int rc;
 
-	if (netif_msg_drv(&debug)) {
-		printk(KERN_INFO "%s Gigabit Ethernet driver %s loaded\n",
-		       MODULENAME, RTL8169_VERSION);
-	}
-
 	dev = devm_alloc_etherdev(&pdev->dev, sizeof (*tp));
 	if (!dev)
 		return -ENOMEM;
-- 
cgit v1.2.3


From 098b01ad9837b4d4d0022f407300f069a999e55a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 10 Aug 2018 22:37:31 +0200
Subject: r8169: don't include asm headers directly

The asm headers shouldn't be included directly. asm/irq.h is
implicitly included by linux/interrupt.h, and instead of
asm/io.h include linux/io.h.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 77802a9d162e..7f0975b61c53 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -19,6 +19,7 @@
 #include <linux/if_vlan.h>
 #include <linux/crc32.h>
 #include <linux/in.h>
+#include <linux/io.h>
 #include <linux/ip.h>
 #include <linux/tcp.h>
 #include <linux/interrupt.h>
@@ -29,9 +30,6 @@
 #include <linux/ipv6.h>
 #include <net/ip6_checksum.h>
 
-#include <asm/io.h>
-#include <asm/irq.h>
-
 #define MODULENAME "r8169"
 
 #define FIRMWARE_8168D_1	"rtl_nic/rtl8168d-1.fw"
-- 
cgit v1.2.3


From 05bbe5584ff9dc218f20398755de29f02dbc6093 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 10 Aug 2018 22:38:29 +0200
Subject: r8169: simplify interrupt handler

Simplify the interrupt handler a little and make it better readable.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 7f0975b61c53..fc6ae446816d 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6520,20 +6520,15 @@ release_descriptor:
 static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance)
 {
 	struct rtl8169_private *tp = dev_instance;
-	int handled = 0;
-	u16 status;
+	u16 status = rtl_get_events(tp);
 
-	status = rtl_get_events(tp);
-	if (status && status != 0xffff) {
-		status &= RTL_EVENT_NAPI | tp->event_slow;
-		if (status) {
-			handled = 1;
+	if (status == 0xffff || !(status & (RTL_EVENT_NAPI | tp->event_slow)))
+		return IRQ_NONE;
 
-			rtl_irq_disable(tp);
-			napi_schedule_irqoff(&tp->napi);
-		}
-	}
-	return IRQ_RETVAL(handled);
+	rtl_irq_disable(tp);
+	napi_schedule_irqoff(&tp->napi);
+
+	return IRQ_HANDLED;
 }
 
 /*
-- 
cgit v1.2.3


From eb88f5f7128ced3d6ab81004686035fb03087475 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 10 Aug 2018 22:39:29 +0200
Subject: r8169: don't configure csum function per chip version

We don't have to configure the csum function per chip (sub-)version.
The distinction is simple, versions RTL8102e and from RTL8168c onwards
support csum_v2.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 134 +++++++++++++++++------------------
 1 file changed, 67 insertions(+), 67 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index fc6ae446816d..891dda674d7c 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -141,134 +141,127 @@ enum mac_version {
 	RTL_GIGA_MAC_NONE   = 0xff,
 };
 
-enum rtl_tx_desc_version {
-	RTL_TD_0	= 0,
-	RTL_TD_1	= 1,
-};
-
 #define JUMBO_1K	ETH_DATA_LEN
 #define JUMBO_4K	(4*1024 - ETH_HLEN - 2)
 #define JUMBO_6K	(6*1024 - ETH_HLEN - 2)
 #define JUMBO_7K	(7*1024 - ETH_HLEN - 2)
 #define JUMBO_9K	(9*1024 - ETH_HLEN - 2)
 
-#define _R(NAME,TD,FW,SZ) {	\
+#define _R(NAME, FW, SZ) {	\
 	.name = NAME,		\
-	.txd_version = TD,	\
 	.fw_name = FW,		\
 	.jumbo_max = SZ,	\
 }
 
 static const struct {
 	const char *name;
-	enum rtl_tx_desc_version txd_version;
 	const char *fw_name;
 	u16 jumbo_max;
 } rtl_chip_infos[] = {
 	/* PCI devices. */
 	[RTL_GIGA_MAC_VER_01] =
-		_R("RTL8169",		RTL_TD_0, NULL, JUMBO_7K),
+		_R("RTL8169",		NULL, JUMBO_7K),
 	[RTL_GIGA_MAC_VER_02] =
-		_R("RTL8169s",		RTL_TD_0, NULL, JUMBO_7K),
+		_R("RTL8169s",		NULL, JUMBO_7K),
 	[RTL_GIGA_MAC_VER_03] =
-		_R("RTL8110s",		RTL_TD_0, NULL, JUMBO_7K),
+		_R("RTL8110s",		NULL, JUMBO_7K),
 	[RTL_GIGA_MAC_VER_04] =
-		_R("RTL8169sb/8110sb",	RTL_TD_0, NULL, JUMBO_7K),
+		_R("RTL8169sb/8110sb",	NULL, JUMBO_7K),
 	[RTL_GIGA_MAC_VER_05] =
-		_R("RTL8169sc/8110sc",	RTL_TD_0, NULL, JUMBO_7K),
+		_R("RTL8169sc/8110sc",	NULL, JUMBO_7K),
 	[RTL_GIGA_MAC_VER_06] =
-		_R("RTL8169sc/8110sc",	RTL_TD_0, NULL, JUMBO_7K),
+		_R("RTL8169sc/8110sc",	NULL, JUMBO_7K),
 	/* PCI-E devices. */
 	[RTL_GIGA_MAC_VER_07] =
-		_R("RTL8102e",		RTL_TD_1, NULL, JUMBO_1K),
+		_R("RTL8102e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_08] =
-		_R("RTL8102e",		RTL_TD_1, NULL, JUMBO_1K),
+		_R("RTL8102e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_09] =
-		_R("RTL8102e",		RTL_TD_1, NULL, JUMBO_1K),
+		_R("RTL8102e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_10] =
-		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K),
+		_R("RTL8101e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_11] =
-		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K),
+		_R("RTL8168b/8111b",	NULL, JUMBO_4K),
 	[RTL_GIGA_MAC_VER_12] =
-		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K),
+		_R("RTL8168b/8111b",	NULL, JUMBO_4K),
 	[RTL_GIGA_MAC_VER_13] =
-		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K),
+		_R("RTL8101e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_14] =
-		_R("RTL8100e",		RTL_TD_0, NULL, JUMBO_1K),
+		_R("RTL8100e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_15] =
-		_R("RTL8100e",		RTL_TD_0, NULL, JUMBO_1K),
+		_R("RTL8100e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_16] =
-		_R("RTL8101e",		RTL_TD_0, NULL, JUMBO_1K),
+		_R("RTL8101e",		NULL, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_17] =
-		_R("RTL8168b/8111b",	RTL_TD_0, NULL, JUMBO_4K),
+		_R("RTL8168b/8111b",	NULL, JUMBO_4K),
 	[RTL_GIGA_MAC_VER_18] =
-		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K),
+		_R("RTL8168cp/8111cp",	NULL, JUMBO_6K),
 	[RTL_GIGA_MAC_VER_19] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
+		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
 	[RTL_GIGA_MAC_VER_20] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
+		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
 	[RTL_GIGA_MAC_VER_21] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
+		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
 	[RTL_GIGA_MAC_VER_22] =
-		_R("RTL8168c/8111c",	RTL_TD_1, NULL, JUMBO_6K),
+		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
 	[RTL_GIGA_MAC_VER_23] =
-		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K),
+		_R("RTL8168cp/8111cp",	NULL, JUMBO_6K),
 	[RTL_GIGA_MAC_VER_24] =
-		_R("RTL8168cp/8111cp",	RTL_TD_1, NULL, JUMBO_6K),
+		_R("RTL8168cp/8111cp",	NULL, JUMBO_6K),
 	[RTL_GIGA_MAC_VER_25] =
-		_R("RTL8168d/8111d",	RTL_TD_1, FIRMWARE_8168D_1, JUMBO_9K),
+		_R("RTL8168d/8111d",	FIRMWARE_8168D_1, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_26] =
-		_R("RTL8168d/8111d",	RTL_TD_1, FIRMWARE_8168D_2, JUMBO_9K),
+		_R("RTL8168d/8111d",	FIRMWARE_8168D_2, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_27] =
-		_R("RTL8168dp/8111dp",	RTL_TD_1, NULL, JUMBO_9K),
+		_R("RTL8168dp/8111dp",	NULL, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_28] =
-		_R("RTL8168dp/8111dp",	RTL_TD_1, NULL, JUMBO_9K),
+		_R("RTL8168dp/8111dp",	NULL, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_29] =
-		_R("RTL8105e",		RTL_TD_1, FIRMWARE_8105E_1, JUMBO_1K),
+		_R("RTL8105e",		FIRMWARE_8105E_1, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_30] =
-		_R("RTL8105e",		RTL_TD_1, FIRMWARE_8105E_1, JUMBO_1K),
+		_R("RTL8105e",		FIRMWARE_8105E_1, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_31] =
-		_R("RTL8168dp/8111dp",	RTL_TD_1, NULL, JUMBO_9K),
+		_R("RTL8168dp/8111dp",	NULL, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_32] =
-		_R("RTL8168e/8111e",	RTL_TD_1, FIRMWARE_8168E_1, JUMBO_9K),
+		_R("RTL8168e/8111e",	FIRMWARE_8168E_1, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_33] =
-		_R("RTL8168e/8111e",	RTL_TD_1, FIRMWARE_8168E_2, JUMBO_9K),
+		_R("RTL8168e/8111e",	FIRMWARE_8168E_2, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_34] =
-		_R("RTL8168evl/8111evl",RTL_TD_1, FIRMWARE_8168E_3, JUMBO_9K),
+		_R("RTL8168evl/8111evl", FIRMWARE_8168E_3, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_35] =
-		_R("RTL8168f/8111f",	RTL_TD_1, FIRMWARE_8168F_1, JUMBO_9K),
+		_R("RTL8168f/8111f",	FIRMWARE_8168F_1, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_36] =
-		_R("RTL8168f/8111f",	RTL_TD_1, FIRMWARE_8168F_2, JUMBO_9K),
+		_R("RTL8168f/8111f",	FIRMWARE_8168F_2, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_37] =
-		_R("RTL8402",		RTL_TD_1, FIRMWARE_8402_1,  JUMBO_1K),
+		_R("RTL8402",		FIRMWARE_8402_1,  JUMBO_1K),
 	[RTL_GIGA_MAC_VER_38] =
-		_R("RTL8411",		RTL_TD_1, FIRMWARE_8411_1,  JUMBO_9K),
+		_R("RTL8411",		FIRMWARE_8411_1,  JUMBO_9K),
 	[RTL_GIGA_MAC_VER_39] =
-		_R("RTL8106e",		RTL_TD_1, FIRMWARE_8106E_1, JUMBO_1K),
+		_R("RTL8106e",		FIRMWARE_8106E_1, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_40] =
-		_R("RTL8168g/8111g",	RTL_TD_1, FIRMWARE_8168G_2, JUMBO_9K),
+		_R("RTL8168g/8111g",	FIRMWARE_8168G_2, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_41] =
-		_R("RTL8168g/8111g",	RTL_TD_1, NULL, JUMBO_9K),
+		_R("RTL8168g/8111g",	NULL, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_42] =
-		_R("RTL8168g/8111g",	RTL_TD_1, FIRMWARE_8168G_3, JUMBO_9K),
+		_R("RTL8168g/8111g",	FIRMWARE_8168G_3, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_43] =
-		_R("RTL8106e",		RTL_TD_1, FIRMWARE_8106E_2, JUMBO_1K),
+		_R("RTL8106e",		FIRMWARE_8106E_2, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_44] =
-		_R("RTL8411",		RTL_TD_1, FIRMWARE_8411_2,  JUMBO_9K),
+		_R("RTL8411",		FIRMWARE_8411_2,  JUMBO_9K),
 	[RTL_GIGA_MAC_VER_45] =
-		_R("RTL8168h/8111h",	RTL_TD_1, FIRMWARE_8168H_1, JUMBO_9K),
+		_R("RTL8168h/8111h",	FIRMWARE_8168H_1, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_46] =
-		_R("RTL8168h/8111h",	RTL_TD_1, FIRMWARE_8168H_2, JUMBO_9K),
+		_R("RTL8168h/8111h",	FIRMWARE_8168H_2, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_47] =
-		_R("RTL8107e",		RTL_TD_1, FIRMWARE_8107E_1, JUMBO_1K),
+		_R("RTL8107e",		FIRMWARE_8107E_1, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_48] =
-		_R("RTL8107e",		RTL_TD_1, FIRMWARE_8107E_2, JUMBO_1K),
+		_R("RTL8107e",		FIRMWARE_8107E_2, JUMBO_1K),
 	[RTL_GIGA_MAC_VER_49] =
-		_R("RTL8168ep/8111ep",	RTL_TD_1, NULL, JUMBO_9K),
+		_R("RTL8168ep/8111ep",	NULL, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_50] =
-		_R("RTL8168ep/8111ep",	RTL_TD_1, NULL, JUMBO_9K),
+		_R("RTL8168ep/8111ep",	NULL, JUMBO_9K),
 	[RTL_GIGA_MAC_VER_51] =
-		_R("RTL8168ep/8111ep",	RTL_TD_1, NULL, JUMBO_9K),
+		_R("RTL8168ep/8111ep",	NULL, JUMBO_9K),
 };
 #undef _R
 
@@ -7274,6 +7267,18 @@ static void rtl_hw_initialize(struct rtl8169_private *tp)
 	}
 }
 
+/* Versions RTL8102e and from RTL8168c onwards support csum_v2 */
+static bool rtl_chip_supports_csum_v2(struct rtl8169_private *tp)
+{
+	switch (tp->mac_version) {
+	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+	case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17:
+		return false;
+	default:
+		return true;
+	}
+}
+
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
@@ -7431,16 +7436,11 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		/* Disallow toggling */
 		dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX;
 
-	switch (rtl_chip_infos[chipset].txd_version) {
-	case RTL_TD_0:
-		tp->tso_csum = rtl8169_tso_csum_v1;
-		break;
-	case RTL_TD_1:
+	if (rtl_chip_supports_csum_v2(tp)) {
 		tp->tso_csum = rtl8169_tso_csum_v2;
 		dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6;
-		break;
-	default:
-		WARN_ON_ONCE(1);
+	} else {
+		tp->tso_csum = rtl8169_tso_csum_v1;
 	}
 
 	dev->hw_features |= NETIF_F_RXALL;
-- 
cgit v1.2.3


From abe8b2f71e28f0193e7a4c989ef5fae227e5a9f9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 10 Aug 2018 22:40:37 +0200
Subject: r8169: don't configure max jumbo frame size per chip version

We don't have to configure the max jumbo frame size per chip
(sub-)version. It can be easily determined based on the chip family.
And new members of the RTL8168 family (if there are any) should be
automatically covered.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 201 +++++++++++++++--------------------
 1 file changed, 83 insertions(+), 118 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 891dda674d7c..14d185b10cda 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -147,123 +147,64 @@ enum mac_version {
 #define JUMBO_7K	(7*1024 - ETH_HLEN - 2)
 #define JUMBO_9K	(9*1024 - ETH_HLEN - 2)
 
-#define _R(NAME, FW, SZ) {	\
-	.name = NAME,		\
-	.fw_name = FW,		\
-	.jumbo_max = SZ,	\
-}
-
 static const struct {
 	const char *name;
 	const char *fw_name;
-	u16 jumbo_max;
 } rtl_chip_infos[] = {
 	/* PCI devices. */
-	[RTL_GIGA_MAC_VER_01] =
-		_R("RTL8169",		NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_02] =
-		_R("RTL8169s",		NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_03] =
-		_R("RTL8110s",		NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_04] =
-		_R("RTL8169sb/8110sb",	NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_05] =
-		_R("RTL8169sc/8110sc",	NULL, JUMBO_7K),
-	[RTL_GIGA_MAC_VER_06] =
-		_R("RTL8169sc/8110sc",	NULL, JUMBO_7K),
+	[RTL_GIGA_MAC_VER_01] = {"RTL8169"				},
+	[RTL_GIGA_MAC_VER_02] = {"RTL8169s"				},
+	[RTL_GIGA_MAC_VER_03] = {"RTL8110s"				},
+	[RTL_GIGA_MAC_VER_04] = {"RTL8169sb/8110sb"			},
+	[RTL_GIGA_MAC_VER_05] = {"RTL8169sc/8110sc"			},
+	[RTL_GIGA_MAC_VER_06] = {"RTL8169sc/8110sc"			},
 	/* PCI-E devices. */
-	[RTL_GIGA_MAC_VER_07] =
-		_R("RTL8102e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_08] =
-		_R("RTL8102e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_09] =
-		_R("RTL8102e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_10] =
-		_R("RTL8101e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_11] =
-		_R("RTL8168b/8111b",	NULL, JUMBO_4K),
-	[RTL_GIGA_MAC_VER_12] =
-		_R("RTL8168b/8111b",	NULL, JUMBO_4K),
-	[RTL_GIGA_MAC_VER_13] =
-		_R("RTL8101e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_14] =
-		_R("RTL8100e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_15] =
-		_R("RTL8100e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_16] =
-		_R("RTL8101e",		NULL, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_17] =
-		_R("RTL8168b/8111b",	NULL, JUMBO_4K),
-	[RTL_GIGA_MAC_VER_18] =
-		_R("RTL8168cp/8111cp",	NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_19] =
-		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_20] =
-		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_21] =
-		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_22] =
-		_R("RTL8168c/8111c",	NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_23] =
-		_R("RTL8168cp/8111cp",	NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_24] =
-		_R("RTL8168cp/8111cp",	NULL, JUMBO_6K),
-	[RTL_GIGA_MAC_VER_25] =
-		_R("RTL8168d/8111d",	FIRMWARE_8168D_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_26] =
-		_R("RTL8168d/8111d",	FIRMWARE_8168D_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_27] =
-		_R("RTL8168dp/8111dp",	NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_28] =
-		_R("RTL8168dp/8111dp",	NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_29] =
-		_R("RTL8105e",		FIRMWARE_8105E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_30] =
-		_R("RTL8105e",		FIRMWARE_8105E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_31] =
-		_R("RTL8168dp/8111dp",	NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_32] =
-		_R("RTL8168e/8111e",	FIRMWARE_8168E_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_33] =
-		_R("RTL8168e/8111e",	FIRMWARE_8168E_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_34] =
-		_R("RTL8168evl/8111evl", FIRMWARE_8168E_3, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_35] =
-		_R("RTL8168f/8111f",	FIRMWARE_8168F_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_36] =
-		_R("RTL8168f/8111f",	FIRMWARE_8168F_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_37] =
-		_R("RTL8402",		FIRMWARE_8402_1,  JUMBO_1K),
-	[RTL_GIGA_MAC_VER_38] =
-		_R("RTL8411",		FIRMWARE_8411_1,  JUMBO_9K),
-	[RTL_GIGA_MAC_VER_39] =
-		_R("RTL8106e",		FIRMWARE_8106E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_40] =
-		_R("RTL8168g/8111g",	FIRMWARE_8168G_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_41] =
-		_R("RTL8168g/8111g",	NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_42] =
-		_R("RTL8168g/8111g",	FIRMWARE_8168G_3, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_43] =
-		_R("RTL8106e",		FIRMWARE_8106E_2, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_44] =
-		_R("RTL8411",		FIRMWARE_8411_2,  JUMBO_9K),
-	[RTL_GIGA_MAC_VER_45] =
-		_R("RTL8168h/8111h",	FIRMWARE_8168H_1, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_46] =
-		_R("RTL8168h/8111h",	FIRMWARE_8168H_2, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_47] =
-		_R("RTL8107e",		FIRMWARE_8107E_1, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_48] =
-		_R("RTL8107e",		FIRMWARE_8107E_2, JUMBO_1K),
-	[RTL_GIGA_MAC_VER_49] =
-		_R("RTL8168ep/8111ep",	NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_50] =
-		_R("RTL8168ep/8111ep",	NULL, JUMBO_9K),
-	[RTL_GIGA_MAC_VER_51] =
-		_R("RTL8168ep/8111ep",	NULL, JUMBO_9K),
+	[RTL_GIGA_MAC_VER_07] = {"RTL8102e"				},
+	[RTL_GIGA_MAC_VER_08] = {"RTL8102e"				},
+	[RTL_GIGA_MAC_VER_09] = {"RTL8102e"				},
+	[RTL_GIGA_MAC_VER_10] = {"RTL8101e"				},
+	[RTL_GIGA_MAC_VER_11] = {"RTL8168b/8111b"			},
+	[RTL_GIGA_MAC_VER_12] = {"RTL8168b/8111b"			},
+	[RTL_GIGA_MAC_VER_13] = {"RTL8101e"				},
+	[RTL_GIGA_MAC_VER_14] = {"RTL8100e"				},
+	[RTL_GIGA_MAC_VER_15] = {"RTL8100e"				},
+	[RTL_GIGA_MAC_VER_16] = {"RTL8101e"				},
+	[RTL_GIGA_MAC_VER_17] = {"RTL8168b/8111b"			},
+	[RTL_GIGA_MAC_VER_18] = {"RTL8168cp/8111cp"			},
+	[RTL_GIGA_MAC_VER_19] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_20] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_21] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_22] = {"RTL8168c/8111c"			},
+	[RTL_GIGA_MAC_VER_23] = {"RTL8168cp/8111cp"			},
+	[RTL_GIGA_MAC_VER_24] = {"RTL8168cp/8111cp"			},
+	[RTL_GIGA_MAC_VER_25] = {"RTL8168d/8111d",	FIRMWARE_8168D_1},
+	[RTL_GIGA_MAC_VER_26] = {"RTL8168d/8111d",	FIRMWARE_8168D_2},
+	[RTL_GIGA_MAC_VER_27] = {"RTL8168dp/8111dp"			},
+	[RTL_GIGA_MAC_VER_28] = {"RTL8168dp/8111dp"			},
+	[RTL_GIGA_MAC_VER_29] = {"RTL8105e",		FIRMWARE_8105E_1},
+	[RTL_GIGA_MAC_VER_30] = {"RTL8105e",		FIRMWARE_8105E_1},
+	[RTL_GIGA_MAC_VER_31] = {"RTL8168dp/8111dp"			},
+	[RTL_GIGA_MAC_VER_32] = {"RTL8168e/8111e",	FIRMWARE_8168E_1},
+	[RTL_GIGA_MAC_VER_33] = {"RTL8168e/8111e",	FIRMWARE_8168E_2},
+	[RTL_GIGA_MAC_VER_34] = {"RTL8168evl/8111evl",	FIRMWARE_8168E_3},
+	[RTL_GIGA_MAC_VER_35] = {"RTL8168f/8111f",	FIRMWARE_8168F_1},
+	[RTL_GIGA_MAC_VER_36] = {"RTL8168f/8111f",	FIRMWARE_8168F_2},
+	[RTL_GIGA_MAC_VER_37] = {"RTL8402",		FIRMWARE_8402_1 },
+	[RTL_GIGA_MAC_VER_38] = {"RTL8411",		FIRMWARE_8411_1 },
+	[RTL_GIGA_MAC_VER_39] = {"RTL8106e",		FIRMWARE_8106E_1},
+	[RTL_GIGA_MAC_VER_40] = {"RTL8168g/8111g",	FIRMWARE_8168G_2},
+	[RTL_GIGA_MAC_VER_41] = {"RTL8168g/8111g"			},
+	[RTL_GIGA_MAC_VER_42] = {"RTL8168g/8111g",	FIRMWARE_8168G_3},
+	[RTL_GIGA_MAC_VER_43] = {"RTL8106e",		FIRMWARE_8106E_2},
+	[RTL_GIGA_MAC_VER_44] = {"RTL8411",		FIRMWARE_8411_2 },
+	[RTL_GIGA_MAC_VER_45] = {"RTL8168h/8111h",	FIRMWARE_8168H_1},
+	[RTL_GIGA_MAC_VER_46] = {"RTL8168h/8111h",	FIRMWARE_8168H_2},
+	[RTL_GIGA_MAC_VER_47] = {"RTL8107e",		FIRMWARE_8107E_1},
+	[RTL_GIGA_MAC_VER_48] = {"RTL8107e",		FIRMWARE_8107E_2},
+	[RTL_GIGA_MAC_VER_49] = {"RTL8168ep/8111ep"			},
+	[RTL_GIGA_MAC_VER_50] = {"RTL8168ep/8111ep"			},
+	[RTL_GIGA_MAC_VER_51] = {"RTL8168ep/8111ep"			},
 };
-#undef _R
 
 enum cfg_version {
 	RTL_CFG_0 = 0x00,
@@ -7279,13 +7220,36 @@ static bool rtl_chip_supports_csum_v2(struct rtl8169_private *tp)
 	}
 }
 
+static int rtl_jumbo_max(struct rtl8169_private *tp)
+{
+	/* Non-GBit versions don't support jumbo frames */
+	if (!tp->supports_gmii)
+		return JUMBO_1K;
+
+	switch (tp->mac_version) {
+	/* RTL8169 */
+	case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06:
+		return JUMBO_7K;
+	/* RTL8168b */
+	case RTL_GIGA_MAC_VER_11:
+	case RTL_GIGA_MAC_VER_12:
+	case RTL_GIGA_MAC_VER_17:
+		return JUMBO_4K;
+	/* RTL8168c */
+	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24:
+		return JUMBO_6K;
+	default:
+		return JUMBO_9K;
+	}
+}
+
 static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 {
 	const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data;
 	struct rtl8169_private *tp;
 	struct net_device *dev;
 	int chipset, region, i;
-	int rc;
+	int jumbo_max, rc;
 
 	dev = devm_alloc_etherdev(&pdev->dev, sizeof (*tp));
 	if (!dev)
@@ -7448,7 +7412,8 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	/* MTU range: 60 - hw-specific max */
 	dev->min_mtu = ETH_ZLEN;
-	dev->max_mtu = rtl_chip_infos[chipset].jumbo_max;
+	jumbo_max = rtl_jumbo_max(tp);
+	dev->max_mtu = jumbo_max;
 
 	tp->hw_start = cfg->hw_start;
 	tp->event_slow = cfg->event_slow;
@@ -7479,12 +7444,12 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		   rtl_chip_infos[chipset].name, dev->dev_addr,
 		   (u32)(RTL_R32(tp, TxConfig) & 0xfcf0f8ff),
 		   pci_irq_vector(pdev, 0));
-	if (rtl_chip_infos[chipset].jumbo_max != JUMBO_1K) {
-		netif_info(tp, probe, dev, "jumbo features [frames: %d bytes, "
-			   "tx checksumming: %s]\n",
-			   rtl_chip_infos[chipset].jumbo_max,
-			  tp->mac_version <= RTL_GIGA_MAC_VER_06 ? "ok" : "ko");
-	}
+
+	if (jumbo_max > JUMBO_1K)
+		netif_info(tp, probe, dev,
+			   "jumbo features [frames: %d bytes, tx checksumming: %s]\n",
+			   jumbo_max, tp->mac_version <= RTL_GIGA_MAC_VER_06 ?
+			   "ok" : "ko");
 
 	if (r8168_check_dash(tp))
 		rtl8168_driver_start(tp);
-- 
cgit v1.2.3


From 0d86caff06363151df21603eb1f4e3207ea91bd2 Mon Sep 17 00:00:00 2001
From: Ursula Braun <ubraun@linux.ibm.com>
Date: Fri, 10 Aug 2018 17:45:11 +0200
Subject: net/smc: send response to test link signal

With SMC-D z/OS sends a test link signal every 10 seconds. Linux is
supposed to answer, otherwise the SMC-D connection breaks.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_ism.c | 34 ++++++++++++++++++++++++++++++++++
 1 file changed, 34 insertions(+)

diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c
index cfade7fdcc6d..e36f21ce7252 100644
--- a/net/smc/smc_ism.c
+++ b/net/smc/smc_ism.c
@@ -184,6 +184,37 @@ struct smc_ism_event_work {
 	struct smcd_event event;
 };
 
+#define ISM_EVENT_REQUEST		0x0001
+#define ISM_EVENT_RESPONSE		0x0002
+#define ISM_EVENT_REQUEST_IR		0x00000001
+#define ISM_EVENT_CODE_TESTLINK		0x83
+
+static void smcd_handle_sw_event(struct smc_ism_event_work *wrk)
+{
+	union {
+		u64	info;
+		struct {
+			u32		uid;
+			unsigned short	vlanid;
+			u16		code;
+		};
+	} ev_info;
+
+	switch (wrk->event.code) {
+	case ISM_EVENT_CODE_TESTLINK:	/* Activity timer */
+		ev_info.info = wrk->event.info;
+		if (ev_info.code == ISM_EVENT_REQUEST) {
+			ev_info.code = ISM_EVENT_RESPONSE;
+			wrk->smcd->ops->signal_event(wrk->smcd,
+						     wrk->event.tok,
+						     ISM_EVENT_REQUEST_IR,
+						     ISM_EVENT_CODE_TESTLINK,
+						     ev_info.info);
+			}
+		break;
+	}
+}
+
 /* worker for SMC-D events */
 static void smc_ism_event_work(struct work_struct *work)
 {
@@ -196,6 +227,9 @@ static void smc_ism_event_work(struct work_struct *work)
 		break;
 	case ISM_EVENT_DMB:
 		break;
+	case ISM_EVENT_SWR:	/* Software defined event */
+		smcd_handle_sw_event(wrk);
+		break;
 	}
 	kfree(wrk);
 }
-- 
cgit v1.2.3


From 0f5c6c30a0f8c629b92ecdaef61b315c43fde10a Mon Sep 17 00:00:00 2001
From: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Date: Fri, 10 Aug 2018 11:36:27 +0800
Subject: net: mvneta: fix mvneta_config_rss on armada 3700

The mvneta Ethernet driver is used on a few different Marvell SoCs.
Some SoCs have per cpu interrupts for Ethernet events, the driver uses
a per CPU napi structure for this case. Some SoCs such as armada 3700
have a single interrupt for Ethernet events, the driver uses a global
napi structure for this case.

Current mvneta_config_rss() always operates the per cpu napi structure.
Fix it by operating a global napi for "single interrupt" case, and per
cpu napi structure for remaining cases.

Signed-off-by: Jisheng Zhang <Jisheng.Zhang@synaptics.com>
Fixes: 2636ac3cc2b4 ("net: mvneta: Add network support for Armada 3700 SoC")
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/marvell/mvneta.c | 31 ++++++++++++++++++++-----------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 55c2a56c5dae..bc80a678abc3 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -4107,13 +4107,18 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 
 	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
 
-	/* We have to synchronise on the napi of each CPU */
-	for_each_online_cpu(cpu) {
-		struct mvneta_pcpu_port *pcpu_port =
-			per_cpu_ptr(pp->ports, cpu);
+	if (!pp->neta_armada3700) {
+		/* We have to synchronise on the napi of each CPU */
+		for_each_online_cpu(cpu) {
+			struct mvneta_pcpu_port *pcpu_port =
+				per_cpu_ptr(pp->ports, cpu);
 
-		napi_synchronize(&pcpu_port->napi);
-		napi_disable(&pcpu_port->napi);
+			napi_synchronize(&pcpu_port->napi);
+			napi_disable(&pcpu_port->napi);
+		}
+	} else {
+		napi_synchronize(&pp->napi);
+		napi_disable(&pp->napi);
 	}
 
 	pp->rxq_def = pp->indir[0];
@@ -4130,12 +4135,16 @@ static int  mvneta_config_rss(struct mvneta_port *pp)
 	mvneta_percpu_elect(pp);
 	spin_unlock(&pp->lock);
 
-	/* We have to synchronise on the napi of each CPU */
-	for_each_online_cpu(cpu) {
-		struct mvneta_pcpu_port *pcpu_port =
-			per_cpu_ptr(pp->ports, cpu);
+	if (!pp->neta_armada3700) {
+		/* We have to synchronise on the napi of each CPU */
+		for_each_online_cpu(cpu) {
+			struct mvneta_pcpu_port *pcpu_port =
+				per_cpu_ptr(pp->ports, cpu);
 
-		napi_enable(&pcpu_port->napi);
+			napi_enable(&pcpu_port->napi);
+		}
+	} else {
+		napi_enable(&pp->napi);
 	}
 
 	netif_tx_start_all_queues(pp->dev);
-- 
cgit v1.2.3


From 4f23c43c414d81b377a07b936e7edfe7167660b5 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 10 Aug 2018 10:37:30 +0800
Subject: mlxsw: core: remove unnecessary function mlxsw_core_driver_put

The function mlxsw_core_driver_put only traverse mlxsw_core_driver_list
to find the matched mlxsw_driver,but never used it.
So it can be removed safely.

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlxsw/core.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c
index b5d5e57f1583..81533d7f395c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core.c
@@ -726,15 +726,6 @@ static struct mlxsw_driver *mlxsw_core_driver_get(const char *kind)
 	return mlxsw_driver;
 }
 
-static void mlxsw_core_driver_put(const char *kind)
-{
-	struct mlxsw_driver *mlxsw_driver;
-
-	spin_lock(&mlxsw_core_driver_list_lock);
-	mlxsw_driver = __driver_find(kind);
-	spin_unlock(&mlxsw_core_driver_list_lock);
-}
-
 static int mlxsw_devlink_port_split(struct devlink *devlink,
 				    unsigned int port_index,
 				    unsigned int count,
@@ -1082,7 +1073,6 @@ err_bus_init:
 	if (!reload)
 		devlink_free(devlink);
 err_devlink_alloc:
-	mlxsw_core_driver_put(device_kind);
 	return err;
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_register);
@@ -1090,7 +1080,6 @@ EXPORT_SYMBOL(mlxsw_core_bus_device_register);
 void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 				      bool reload)
 {
-	const char *device_kind = mlxsw_core->bus_info->device_kind;
 	struct devlink *devlink = priv_to_devlink(mlxsw_core);
 
 	if (mlxsw_core->reload_fail)
@@ -1111,7 +1100,6 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core,
 		return;
 reload_fail:
 	devlink_free(devlink);
-	mlxsw_core_driver_put(device_kind);
 }
 EXPORT_SYMBOL(mlxsw_core_bus_device_unregister);
 
-- 
cgit v1.2.3


From 1e7953bc560451302dcb5d5b3fafd1949447579a Mon Sep 17 00:00:00 2001
From: kbuild test robot <fengguang.wu@intel.com>
Date: Fri, 10 Aug 2018 09:29:59 +0800
Subject: qed/qede: qede_setup_tc() can be static

Fixes: 5e7baf0fcb2a ("qed/qede: Multi CoS support.")
Signed-off-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/qlogic/qede/qede_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c
index 4b5d98f60d32..46d0f2eaa0c0 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_main.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_main.c
@@ -536,7 +536,7 @@ static int qede_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	return 0;
 }
 
-int qede_setup_tc(struct net_device *ndev, u8 num_tc)
+static int qede_setup_tc(struct net_device *ndev, u8 num_tc)
 {
 	struct qede_dev *edev = netdev_priv(ndev);
 	int cos, count, offset;
-- 
cgit v1.2.3


From 0520344cdb1efa7c6404168b66f8dd0b1fe5face Mon Sep 17 00:00:00 2001
From: Raghu Vatsavayi <raghu.vatsavayi@cavium.com>
Date: Thu, 9 Aug 2018 13:54:12 -0700
Subject: liquidio: copperhead LED identification

Add LED identification support for liquidio TP copperhead cards.

Signed-off-by: Raghu Vatsavayi <raghu.vatsavayi@cavium.com>
Acked-by: Derek Chickles <derek.chickles@cavium.com>
Signed-off-by: Felix Manlunas <felix.manlunas@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 27 ++++++++++++++++++----
 .../net/ethernet/cavium/liquidio/liquidio_common.h |  1 +
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 06f7449c569d..807ea2c61877 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -857,7 +857,14 @@ static int lio_set_phys_id(struct net_device *netdev,
 {
 	struct lio *lio = GET_LIO(netdev);
 	struct octeon_device *oct = lio->oct_dev;
+	struct oct_link_info *linfo;
 	int value, ret;
+	u32 cur_ver;
+
+	linfo = &lio->linfo;
+	cur_ver = OCT_FW_VER(oct->fw_info.ver.maj,
+			     oct->fw_info.ver.min,
+			     oct->fw_info.ver.rev);
 
 	switch (state) {
 	case ETHTOOL_ID_ACTIVE:
@@ -896,16 +903,22 @@ static int lio_set_phys_id(struct net_device *netdev,
 				return ret;
 		} else if (oct->chip_id == OCTEON_CN23XX_PF_VID) {
 			octnet_id_active(netdev, LED_IDENTIFICATION_ON);
-
-			/* returns 0 since updates are asynchronous */
-			return 0;
+			if (linfo->link.s.phy_type == LIO_PHY_PORT_TP &&
+			    cur_ver > OCT_FW_VER(1, 7, 2))
+				return 2;
+			else
+				return 0;
 		} else {
 			return -EINVAL;
 		}
 		break;
 
 	case ETHTOOL_ID_ON:
-		if (oct->chip_id == OCTEON_CN66XX)
+		if (oct->chip_id == OCTEON_CN23XX_PF_VID &&
+		    linfo->link.s.phy_type == LIO_PHY_PORT_TP &&
+		    cur_ver > OCT_FW_VER(1, 7, 2))
+			octnet_id_active(netdev, LED_IDENTIFICATION_ON);
+		else if (oct->chip_id == OCTEON_CN66XX)
 			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
 					   VITESSE_PHY_GPIO_HIGH);
 		else
@@ -914,7 +927,11 @@ static int lio_set_phys_id(struct net_device *netdev,
 		break;
 
 	case ETHTOOL_ID_OFF:
-		if (oct->chip_id == OCTEON_CN66XX)
+		if (oct->chip_id == OCTEON_CN23XX_PF_VID &&
+		    linfo->link.s.phy_type == LIO_PHY_PORT_TP &&
+		    cur_ver > OCT_FW_VER(1, 7, 2))
+			octnet_id_active(netdev, LED_IDENTIFICATION_OFF);
+		else if (oct->chip_id == OCTEON_CN66XX)
 			octnet_gpio_access(netdev, VITESSE_PHY_GPIO_CFG,
 					   VITESSE_PHY_GPIO_LOW);
 		else
diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
index 690424b6781a..7407fcd338e9 100644
--- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
+++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h
@@ -907,6 +907,7 @@ static inline int opcode_slow_path(union octeon_rh *rh)
 #define VITESSE_PHY_GPIO_LOW      0x3
 #define LED_IDENTIFICATION_ON     0x1
 #define LED_IDENTIFICATION_OFF    0x0
+#define LIO23XX_COPPERHEAD_LED_GPIO 0x2
 
 struct oct_mdio_cmd {
 	u64 op;
-- 
cgit v1.2.3


From ee97d8abacb90487a2314eac5dd632fac920ca32 Mon Sep 17 00:00:00 2001
From: Fox Foster <fox@tardis.ed.ac.uk>
Date: Tue, 7 Aug 2018 19:47:51 +0100
Subject: Remove gendered language from management style documentation

This small commit replaces gendered pronouns for neutral ones.

Signed-off-by: Fox Foster <fox@tardis.ed.ac.uk>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/process/management-style.rst | 25 +++++++++++++------------
 1 file changed, 13 insertions(+), 12 deletions(-)

diff --git a/Documentation/process/management-style.rst b/Documentation/process/management-style.rst
index 45595fd8a66b..85ef8ca8f639 100644
--- a/Documentation/process/management-style.rst
+++ b/Documentation/process/management-style.rst
@@ -105,7 +105,7 @@ to admit that you are stupid when you haven't **yet** done the really
 stupid thing.
 
 Then, when it really does turn out to be stupid, people just roll their
-eyes and say "Oops, he did it again".
+eyes and say "Oops, not again".
 
 This preemptive admission of incompetence might also make the people who
 actually do the work also think twice about whether it's worth doing or
@@ -172,10 +172,10 @@ To solve this problem, you really only have two options:
    might even be amused.
 
 The option of being unfailingly polite really doesn't exist. Nobody will
-trust somebody who is so clearly hiding his true character.
+trust somebody who is so clearly hiding their true character.
 
 .. [#f2] Paul Simon sang "Fifty Ways to Leave Your Lover", because quite
-  frankly, "A Million Ways to Tell a Developer He Is a D*ckhead" doesn't
+  frankly, "A Million Ways to Tell a Developer They're a D*ckhead" doesn't
   scan nearly as well.  But I'm sure he thought about it.
 
 
@@ -219,15 +219,16 @@ Things will go wrong, and people want somebody to blame. Tag, you're it.
 
 It's not actually that hard to accept the blame, especially if people
 kind of realize that it wasn't **all** your fault.  Which brings us to the
-best way of taking the blame: do it for another guy. You'll feel good
-for taking the fall, he'll feel good about not getting blamed, and the
-guy who lost his whole 36GB porn-collection because of your incompetence
-will grudgingly admit that you at least didn't try to weasel out of it.
-
-Then make the developer who really screwed up (if you can find him) know
-**in_private** that he screwed up.  Not just so he can avoid it in the
-future, but so that he knows he owes you one.  And, perhaps even more
-importantly, he's also likely the person who can fix it.  Because, let's
+best way of taking the blame: do it for someone else. You'll feel good
+for taking the fall, they'll feel good about not getting blamed, and the
+person who lost their whole 36GB porn-collection because of your
+incompetence will grudgingly admit that you at least didn't try to weasel
+out of it.
+
+Then make the developer who really screwed up (if you can find them) know
+**in_private** that they screwed up.  Not just so they can avoid it in the
+future, but so that they know they owe you one.  And, perhaps even more
+importantly, they're also likely the person who can fix it.  Because, let's
 face it, it sure ain't you.
 
 Taking the blame is also why you get to be manager in the first place.
-- 
cgit v1.2.3


From 96fdb7c49957085b575127ae226e8c076cfcdf31 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 7 Aug 2018 08:28:25 -0700
Subject: Documentation: add ioctl number entry for v4l2-subdev.h

Update ioctl-number.txt for ioctl's that are defined in
<media/v4l2-subdev.h>.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/ioctl/ioctl-number.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt
index 480c8609dc58..9aeb5f0ea701 100644
--- a/Documentation/ioctl/ioctl-number.txt
+++ b/Documentation/ioctl/ioctl-number.txt
@@ -274,6 +274,7 @@ Code  Seq#(hex)	Include File		Comments
 'v'	00-1F	linux/ext2_fs.h		conflict!
 'v'	00-1F	linux/fs.h		conflict!
 'v'	00-0F	linux/sonypi.h		conflict!
+'v'	00-0F	media/v4l2-subdev.h	conflict!
 'v'	C0-FF	linux/meye.h		conflict!
 'w'	all				CERN SCI driver
 'y'	00-1F				packet based user level communications
-- 
cgit v1.2.3


From 3d83d3188460bf97afa0ac9895265422411e473a Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Mon, 6 Aug 2018 16:24:55 -0700
Subject: Documentation: corrections to console/console.txt

Fix typos, line length, grammar, punctuation, and capitalization
in console.txt.

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: Antonino A. Daplas <adaplas@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
---
 Documentation/console/console.txt | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/Documentation/console/console.txt b/Documentation/console/console.txt
index f93810d599ad..d73c2ab4beda 100644
--- a/Documentation/console/console.txt
+++ b/Documentation/console/console.txt
@@ -1,7 +1,7 @@
 Console Drivers
 ===============
 
-The linux kernel has 2 general types of console drivers.  The first type is
+The Linux kernel has 2 general types of console drivers.  The first type is
 assigned by the kernel to all the virtual consoles during the boot process.
 This type will be called 'system driver', and only one system driver is allowed
 to exist. The system driver is persistent and it can never be unloaded, though
@@ -17,10 +17,11 @@ of driver occupying the consoles.) They can only take over the console that is
 occupied by the system driver. In the same token, if the modular driver is
 released by the console, the system driver will take over.
 
-Modular drivers, from the programmer's point of view, has to call:
+Modular drivers, from the programmer's point of view, have to call:
 
 	 do_take_over_console() - load and bind driver to console layer
-	 give_up_console() - unload driver, it will only work if driver is fully unbond
+	 give_up_console() - unload driver; it will only work if driver
+			     is fully unbound
 
 In newer kernels, the following are also available:
 
@@ -56,7 +57,7 @@ What do these files signify?
 	cat /sys/class/vtconsole/vtcon0/name
 	(S) VGA+
 
-	    '(S)' stands for a (S)ystem driver, ie, it cannot be directly
+	    '(S)' stands for a (S)ystem driver, i.e., it cannot be directly
 	    commanded to bind or unbind
 
 	    'VGA+' is the name of the driver
@@ -89,7 +90,7 @@ driver, make changes, recompile, reload and rebind the driver without any need
 for rebooting the kernel. For regular users who may want to switch from
 framebuffer console to VGA console and vice versa, this feature also makes
 this possible. (NOTE NOTE NOTE: Please read fbcon.txt under Documentation/fb
-for more details).
+for more details.)
 
 Notes for developers:
 =====================
@@ -110,8 +111,8 @@ In order for binding to and unbinding from the console to properly work,
 console drivers must follow these guidelines:
 
 1. All drivers, except system drivers, must call either do_register_con_driver()
-   or do_take_over_console(). do_register_con_driver() will just add the driver to
-   the console's internal list. It won't take over the
+   or do_take_over_console(). do_register_con_driver() will just add the driver
+   to the console's internal list. It won't take over the
    console. do_take_over_console(), as it name implies, will also take over (or
    bind to) the console.
 
-- 
cgit v1.2.3


From c4f7173ac3b7e22934e51f0121833642a581d723 Mon Sep 17 00:00:00 2001
From: Steve French <stfrench@microsoft.com>
Date: Fri, 10 Aug 2018 18:46:58 -0500
Subject: smb3: create smb3 equivalent alias for cifs pseudo-xattrs

We really, really don't want to be encouraging people to use
cifs (the dialect) since it is insecure, so to avoid confusion
we want to move them to names which include 'smb3' instead of
'cifs' - so this simply creates an alias for the pseudo-xattrs

e.g. can now do:
getfattr -n user.smb3.creationtime /mnt1/file
and
getfattr -n user.smb3.dosattrib /mnt1/file
and
getfattr -n system.smb3_acl /mnt1/file

instead of forcing you to use the string 'cifs' in
these (e.g. getfattr -n system.cifs_acl /mnt1/file)

Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/cifs/xattr.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 316af84674f1..50ddb795aaeb 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -35,6 +35,14 @@
 #define CIFS_XATTR_CIFS_ACL "system.cifs_acl"
 #define CIFS_XATTR_ATTRIB "cifs.dosattrib"  /* full name: user.cifs.dosattrib */
 #define CIFS_XATTR_CREATETIME "cifs.creationtime"  /* user.cifs.creationtime */
+/*
+ * Although these three are just aliases for the above, need to move away from
+ * confusing users and using the 20+ year old term 'cifs' when it is no longer
+ * secure, replaced by SMB2 (then even more highly secure SMB3) many years ago
+ */
+#define SMB3_XATTR_CIFS_ACL "system.smb3_acl"
+#define SMB3_XATTR_ATTRIB "smb3.dosattrib"  /* full name: user.smb3.dosattrib */
+#define SMB3_XATTR_CREATETIME "smb3.creationtime"  /* user.smb3.creationtime */
 /* BB need to add server (Samba e.g) support for security and trusted prefix */
 
 enum { XATTR_USER, XATTR_CIFS_ACL, XATTR_ACL_ACCESS, XATTR_ACL_DEFAULT };
@@ -220,10 +228,12 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
 	switch (handler->flags) {
 	case XATTR_USER:
 		cifs_dbg(FYI, "%s:querying user xattr %s\n", __func__, name);
-		if (strcmp(name, CIFS_XATTR_ATTRIB) == 0) {
+		if ((strcmp(name, CIFS_XATTR_ATTRIB) == 0) ||
+		    (strcmp(name, SMB3_XATTR_ATTRIB) == 0)) {
 			rc = cifs_attrib_get(dentry, inode, value, size);
 			break;
-		} else if (strcmp(name, CIFS_XATTR_CREATETIME) == 0) {
+		} else if ((strcmp(name, CIFS_XATTR_CREATETIME) == 0) ||
+		    (strcmp(name, SMB3_XATTR_CREATETIME) == 0)) {
 			rc = cifs_creation_time_get(dentry, inode, value, size);
 			break;
 		}
@@ -363,6 +373,19 @@ static const struct xattr_handler cifs_cifs_acl_xattr_handler = {
 	.set = cifs_xattr_set,
 };
 
+/*
+ * Although this is just an alias for the above, need to move away from
+ * confusing users and using the 20 year old term 'cifs' when it is no
+ * longer secure and was replaced by SMB2/SMB3 a long time ago, and
+ * SMB3 and later are highly secure.
+ */
+static const struct xattr_handler smb3_acl_xattr_handler = {
+	.name = SMB3_XATTR_CIFS_ACL,
+	.flags = XATTR_CIFS_ACL,
+	.get = cifs_xattr_get,
+	.set = cifs_xattr_set,
+};
+
 static const struct xattr_handler cifs_posix_acl_access_xattr_handler = {
 	.name = XATTR_NAME_POSIX_ACL_ACCESS,
 	.flags = XATTR_ACL_ACCESS,
@@ -381,6 +404,7 @@ const struct xattr_handler *cifs_xattr_handlers[] = {
 	&cifs_user_xattr_handler,
 	&cifs_os2_xattr_handler,
 	&cifs_cifs_acl_xattr_handler,
+	&smb3_acl_xattr_handler, /* alias for above since avoiding "cifs" */
 	&cifs_posix_acl_access_xattr_handler,
 	&cifs_posix_acl_default_xattr_handler,
 	NULL
-- 
cgit v1.2.3


From 40a1227ea845a37ab197dd1caffb60b047fa36b1 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:21 -0700
Subject: tcp: Avoid TCP syncookie rejected by SO_REUSEPORT socket

Although the actual cookie check "__cookie_v[46]_check()" does
not involve sk specific info, it checks whether the sk has recent
synq overflow event in "tcp_synq_no_recent_overflow()".  The
tcp_sk(sk)->rx_opt.ts_recent_stamp is updated every second
when it has sent out a syncookie (through "tcp_synq_overflow()").

The above per sk "recent synq overflow event timestamp" works well
for non SO_REUSEPORT use case.  However, it may cause random
connection request reject/discard when SO_REUSEPORT is used with
syncookie because it fails the "tcp_synq_no_recent_overflow()"
test.

When SO_REUSEPORT is used, it usually has multiple listening
socks serving TCP connection requests destinated to the same local IP:PORT.
There are cases that the TCP-ACK-COOKIE may not be received
by the same sk that sent out the syncookie.  For example,
if reuse->socks[] began with {sk0, sk1},
1) sk1 sent out syncookies and tcp_sk(sk1)->rx_opt.ts_recent_stamp
   was updated.
2) the reuse->socks[] became {sk1, sk2} later.  e.g. sk0 was first closed
   and then sk2 was added.  Here, sk2 does not have ts_recent_stamp set.
   There are other ordering that will trigger the similar situation
   below but the idea is the same.
3) When the TCP-ACK-COOKIE comes back, sk2 was selected.
   "tcp_synq_no_recent_overflow(sk2)" returns true. In this case,
   all syncookies sent by sk1 will be handled (and rejected)
   by sk2 while sk1 is still alive.

The userspace may create and remove listening SO_REUSEPORT sockets
as it sees fit.  E.g. Adding new thread (and SO_REUSEPORT sock) to handle
incoming requests, old process stopping and new process starting...etc.
With or without SO_ATTACH_REUSEPORT_[CB]BPF,
the sockets leaving and joining a reuseport group makes picking
the same sk to check the syncookie very difficult (if not impossible).

The later patches will allow bpf prog more flexibility in deciding
where a sk should be located in a bpf map and selecting a particular
SO_REUSEPORT sock as it sees fit.  e.g. Without closing any sock,
replace the whole bpf reuseport_array in one map_update() by using
map-in-map.  Getting the syncookie check working smoothly across
socks in the same "reuse->socks[]" is important.

A partial solution is to set the newly added sk's ts_recent_stamp
to the max ts_recent_stamp of a reuseport group but that will require
to iterate through reuse->socks[]  OR
pessimistically set it to "now - TCP_SYNCOOKIE_VALID" when a sk is
joining a reuseport group.  However, neither of them will solve the
existing sk getting moved around the reuse->socks[] and that
sk may not have ts_recent_stamp updated, unlikely under continuous
synflood but not impossible.

This patch opts to treat the reuseport group as a whole when
considering the last synq overflow timestamp since
they are serving the same IP:PORT from the userspace
(and BPF program) perspective.

"synq_overflow_ts" is added to "struct sock_reuseport".
The tcp_synq_overflow() and tcp_synq_no_recent_overflow()
will update/check reuse->synq_overflow_ts if the sk is
in a reuseport group.  Similar to the reuseport decision in
__inet_lookup_listener(), both sk->sk_reuseport and
sk->sk_reuseport_cb are tested for SO_REUSEPORT usage.
Update on "synq_overflow_ts" happens at roughly once
every second.

A synflood test was done with a 16 rx-queues and 16 reuseport sockets.
No meaningful performance change is observed.  Before and
after the change is ~9Mpps in IPv4.

Cc: Eric Dumazet <edumazet@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/sock_reuseport.h |  4 ++++
 include/net/tcp.h            | 30 ++++++++++++++++++++++++++++--
 net/core/sock_reuseport.c    |  1 +
 3 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 0054b3a9b923..6bef7a0052f2 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -12,6 +12,10 @@ struct sock_reuseport {
 
 	u16			max_socks;	/* length of socks */
 	u16			num_socks;	/* elements in socks */
+	/* The last synq overflow event timestamp of this
+	 * reuse->socks[] group.
+	 */
+	unsigned int		synq_overflow_ts;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
 	struct sock		*socks[0];	/* array of sock pointers */
 };
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d769dc20359b..d196901c9dba 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -36,6 +36,7 @@
 #include <net/inet_hashtables.h>
 #include <net/checksum.h>
 #include <net/request_sock.h>
+#include <net/sock_reuseport.h>
 #include <net/sock.h>
 #include <net/snmp.h>
 #include <net/ip.h>
@@ -473,9 +474,22 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb);
  */
 static inline void tcp_synq_overflow(const struct sock *sk)
 {
-	unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int last_overflow;
 	unsigned int now = jiffies;
 
+	if (sk->sk_reuseport) {
+		struct sock_reuseport *reuse;
+
+		reuse = rcu_dereference(sk->sk_reuseport_cb);
+		if (likely(reuse)) {
+			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
+			if (time_after32(now, last_overflow + HZ))
+				WRITE_ONCE(reuse->synq_overflow_ts, now);
+			return;
+		}
+	}
+
+	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
 	if (time_after32(now, last_overflow + HZ))
 		tcp_sk(sk)->rx_opt.ts_recent_stamp = now;
 }
@@ -483,9 +497,21 @@ static inline void tcp_synq_overflow(const struct sock *sk)
 /* syncookies: no recent synqueue overflow on this listening socket? */
 static inline bool tcp_synq_no_recent_overflow(const struct sock *sk)
 {
-	unsigned int last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
+	unsigned int last_overflow;
 	unsigned int now = jiffies;
 
+	if (sk->sk_reuseport) {
+		struct sock_reuseport *reuse;
+
+		reuse = rcu_dereference(sk->sk_reuseport_cb);
+		if (likely(reuse)) {
+			last_overflow = READ_ONCE(reuse->synq_overflow_ts);
+			return time_after32(now, last_overflow +
+					    TCP_SYNCOOKIE_VALID);
+		}
+	}
+
+	last_overflow = tcp_sk(sk)->rx_opt.ts_recent_stamp;
 	return time_after32(now, last_overflow + TCP_SYNCOOKIE_VALID);
 }
 
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 064acb04be0f..3f188fad0162 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -81,6 +81,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
+	more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts);
 
 	for (i = 0; i < reuse->num_socks; ++i)
 		rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb,
-- 
cgit v1.2.3


From 736b46027eb4a4c602d3b8b93d2f48c9facbd915 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:22 -0700
Subject: net: Add ID (if needed) to sock_reuseport and expose reuseport_lock

A later patch will introduce a BPF_MAP_TYPE_REUSEPORT_ARRAY which
allows a SO_REUSEPORT sk to be added to a bpf map.  When a sk
is removed from reuse->socks[], it also needs to be removed from
the bpf map.  Also, when adding a sk to a bpf map, the bpf
map needs to ensure it is indeed in a reuse->socks[].
Hence, reuseport_lock is needed by the bpf map to ensure its
map_update_elem() and map_delete_elem() operations are in-sync with
the reuse->socks[].  The BPF_MAP_TYPE_REUSEPORT_ARRAY map will only
acquire the reuseport_lock after ensuring the adding sk is already
in a reuseport group (i.e. reuse->socks[]).  The map_lookup_elem()
will be lockless.

This patch also adds an ID to sock_reuseport.  A later patch
will introduce BPF_PROG_TYPE_SK_REUSEPORT which allows
a bpf prog to select a sk from a bpf map.  It is inflexible to
statically enforce a bpf map can only contain the sk belonging to
a particular reuse->socks[] (i.e. same IP:PORT) during the bpf
verification time. For example, think about the the map-in-map situation
where the inner map can be dynamically changed in runtime and the outer
map may have inner maps belonging to different reuseport groups.
Hence, when the bpf prog (in the new BPF_PROG_TYPE_SK_REUSEPORT
type) selects a sk,  this selected sk has to be checked to ensure it
belongs to the requesting reuseport group (i.e. the group serving
that IP:PORT).

The "sk->sk_reuseport_cb" pointer cannot be used for this checking
purpose because the pointer value will change after reuseport_grow().
Instead of saving all checking conditions like the ones
preced calling "reuseport_add_sock()" and compare them everytime a
bpf_prog is run, a 32bits ID is introduced to survive the
reuseport_grow().  The ID is only acquired if any of the
reuse->socks[] is added to the newly introduced
"BPF_MAP_TYPE_REUSEPORT_ARRAY" map.

If "BPF_MAP_TYPE_REUSEPORT_ARRAY" is not used,  the changes in this
patch is a no-op.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/net/sock_reuseport.h |  6 ++++++
 net/core/sock_reuseport.c    | 27 ++++++++++++++++++++++++++-
 2 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 6bef7a0052f2..e1a7681856f7 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -5,8 +5,11 @@
 #include <linux/filter.h>
 #include <linux/skbuff.h>
 #include <linux/types.h>
+#include <linux/spinlock.h>
 #include <net/sock.h>
 
+extern spinlock_t reuseport_lock;
+
 struct sock_reuseport {
 	struct rcu_head		rcu;
 
@@ -16,6 +19,8 @@ struct sock_reuseport {
 	 * reuse->socks[] group.
 	 */
 	unsigned int		synq_overflow_ts;
+	/* ID stays the same even after the size of socks[] grows. */
+	unsigned int		reuseport_id;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
 	struct sock		*socks[0];	/* array of sock pointers */
 };
@@ -29,5 +34,6 @@ extern struct sock *reuseport_select_sock(struct sock *sk,
 					  int hdr_len);
 extern struct bpf_prog *reuseport_attach_prog(struct sock *sk,
 					      struct bpf_prog *prog);
+int reuseport_get_id(struct sock_reuseport *reuse);
 
 #endif  /* _SOCK_REUSEPORT_H */
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 3f188fad0162..cf2e4d305af9 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -8,11 +8,33 @@
 
 #include <net/sock_reuseport.h>
 #include <linux/bpf.h>
+#include <linux/idr.h>
 #include <linux/rcupdate.h>
 
 #define INIT_SOCKS 128
 
-static DEFINE_SPINLOCK(reuseport_lock);
+DEFINE_SPINLOCK(reuseport_lock);
+
+#define REUSEPORT_MIN_ID 1
+static DEFINE_IDA(reuseport_ida);
+
+int reuseport_get_id(struct sock_reuseport *reuse)
+{
+	int id;
+
+	if (reuse->reuseport_id)
+		return reuse->reuseport_id;
+
+	id = ida_simple_get(&reuseport_ida, REUSEPORT_MIN_ID, 0,
+			    /* Called under reuseport_lock */
+			    GFP_ATOMIC);
+	if (id < 0)
+		return id;
+
+	reuse->reuseport_id = id;
+
+	return reuse->reuseport_id;
+}
 
 static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 {
@@ -78,6 +100,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	more_reuse->max_socks = more_socks_size;
 	more_reuse->num_socks = reuse->num_socks;
 	more_reuse->prog = reuse->prog;
+	more_reuse->reuseport_id = reuse->reuseport_id;
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
@@ -102,6 +125,8 @@ static void reuseport_free_rcu(struct rcu_head *head)
 	reuse = container_of(head, struct sock_reuseport, rcu);
 	if (reuse->prog)
 		bpf_prog_destroy(reuse->prog);
+	if (reuse->reuseport_id)
+		ida_simple_remove(&reuseport_ida, reuse->reuseport_id);
 	kfree(reuse);
 }
 
-- 
cgit v1.2.3


From 5dc4c4b7d4e8115e7cde96a030f98cb3ab2e458c Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:24 -0700
Subject: bpf: Introduce BPF_MAP_TYPE_REUSEPORT_SOCKARRAY

This patch introduces a new map type BPF_MAP_TYPE_REUSEPORT_SOCKARRAY.

To unleash the full potential of a bpf prog, it is essential for the
userspace to be capable of directly setting up a bpf map which can then
be consumed by the bpf prog to make decision.  In this case, decide which
SO_REUSEPORT sk to serve the incoming request.

By adding BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, the userspace has total control
and visibility on where a SO_REUSEPORT sk should be located in a bpf map.
The later patch will introduce BPF_PROG_TYPE_SK_REUSEPORT such that
the bpf prog can directly select a sk from the bpf map.  That will
raise the programmability of the bpf prog attached to a reuseport
group (a group of sk serving the same IP:PORT).

For example, in UDP, the bpf prog can peek into the payload (e.g.
through the "data" pointer introduced in the later patch) to learn
the application level's connection information and then decide which sk
to pick from a bpf map.  The userspace can tightly couple the sk's location
in a bpf map with the application logic in generating the UDP payload's
connection information.  This connection info contact/API stays within the
userspace.

Also, when used with map-in-map, the userspace can switch the
old-server-process's inner map to a new-server-process's inner map
in one call "bpf_map_update_elem(outer_map, &index, &new_reuseport_array)".
The bpf prog will then direct incoming requests to the new process instead
of the old process.  The old process can finish draining the pending
requests (e.g. by "accept()") before closing the old-fds.  [Note that
deleting a fd from a bpf map does not necessary mean the fd is closed]

During map_update_elem(),
Only SO_REUSEPORT sk (i.e. which has already been added
to a reuse->socks[]) can be used.  That means a SO_REUSEPORT sk that is
"bind()" for UDP or "bind()+listen()" for TCP.  These conditions are
ensured in "reuseport_array_update_check()".

A SO_REUSEPORT sk can only be added once to a map (i.e. the
same sk cannot be added twice even to the same map).  SO_REUSEPORT
already allows another sk to be created for the same IP:PORT.
There is no need to re-create a similar usage in the BPF side.

When a SO_REUSEPORT is deleted from the "reuse->socks[]" (e.g. "close()"),
it will notify the bpf map to remove it from the map also.  It is
done through "bpf_sk_reuseport_detach()" and it will only be called
if >=1 of the "reuse->sock[]" has ever been added to a bpf map.

The map_update()/map_delete() has to be in-sync with the
"reuse->socks[]".  Hence, the same "reuseport_lock" used
by "reuse->socks[]" has to be used here also. Care has
been taken to ensure the lock is only acquired when the
adding sk passes some strict tests. and
freeing the map does not require the reuseport_lock.

The reuseport_array will also support lookup from the syscall
side.  It will return a sock_gen_cookie().  The sock_gen_cookie()
is on-demand (i.e. a sk's cookie is not generated until the very
first map_lookup_elem()).

The lookup cookie is 64bits but it goes against the logical userspace
expectation on 32bits sizeof(fd) (and as other fd based bpf maps do also).
It may catch user in surprise if we enforce value_size=8 while
userspace still pass a 32bits fd during update.  Supporting different
value_size between lookup and update seems unintuitive also.

We also need to consider what if other existing fd based maps want
to return 64bits value from syscall's lookup in the future.
Hence, reuseport_array supports both value_size 4 and 8, and
assuming user will usually use value_size=4.  The syscall's lookup
will return ENOSPC on value_size=4.  It will will only
return 64bits value from sock_gen_cookie() when user consciously
choose value_size=8 (as a signal that lookup is desired) which then
requires a 64bits value in both lookup and update.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf.h          |  28 ++++
 include/linux/bpf_types.h    |   3 +
 include/uapi/linux/bpf.h     |   1 +
 kernel/bpf/Makefile          |   3 +
 kernel/bpf/arraymap.c        |   2 +-
 kernel/bpf/reuseport_array.c | 363 +++++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c         |   6 +
 net/core/sock_reuseport.c    |   8 +
 8 files changed, 413 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/reuseport_array.c

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cd8790d2c6ed..db11662faea6 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -524,6 +524,7 @@ static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
 }
 
 struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
+int array_map_alloc_check(union bpf_attr *attr);
 
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
@@ -769,6 +770,33 @@ static inline void __xsk_map_flush(struct bpf_map *map)
 }
 #endif
 
+#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
+void bpf_sk_reuseport_detach(struct sock *sk);
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+				       void *value);
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 map_flags);
+#else
+static inline void bpf_sk_reuseport_detach(struct sock *sk)
+{
+}
+
+#ifdef CONFIG_BPF_SYSCALL
+static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map,
+						     void *key, void *value)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
+						     void *key, void *value,
+						     u64 map_flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_BPF_SYSCALL */
+#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */
+
 /* verifier prototypes for helper functions called from eBPF programs */
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index add08be53b6f..14fd6c02d258 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -60,4 +60,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops)
 #if defined(CONFIG_XDP_SOCKETS)
 BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
 #endif
+#ifdef CONFIG_INET
+BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
+#endif
 #endif
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dd5758dc35d3..40f584bc7da0 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -126,6 +126,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
 	BPF_MAP_TYPE_CGROUP_STORAGE,
+	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 };
 
 enum bpf_prog_type {
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e8906cbad81f..0488b8258321 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -23,3 +23,6 @@ ifeq ($(CONFIG_PERF_EVENTS),y)
 obj-$(CONFIG_BPF_SYSCALL) += stackmap.o
 endif
 obj-$(CONFIG_CGROUP_BPF) += cgroup.o
+ifeq ($(CONFIG_INET),y)
+obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
+endif
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 2aa55d030c77..f6ca3e712831 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -54,7 +54,7 @@ static int bpf_array_alloc_percpu(struct bpf_array *array)
 }
 
 /* Called from syscall */
-static int array_map_alloc_check(union bpf_attr *attr)
+int array_map_alloc_check(union bpf_attr *attr)
 {
 	bool percpu = attr->map_type == BPF_MAP_TYPE_PERCPU_ARRAY;
 	int numa_node = bpf_map_attr_numa_node(attr);
diff --git a/kernel/bpf/reuseport_array.c b/kernel/bpf/reuseport_array.c
new file mode 100644
index 000000000000..18e225de80ff
--- /dev/null
+++ b/kernel/bpf/reuseport_array.c
@@ -0,0 +1,363 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Facebook
+ */
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/sock_diag.h>
+#include <net/sock_reuseport.h>
+
+struct reuseport_array {
+	struct bpf_map map;
+	struct sock __rcu *ptrs[];
+};
+
+static struct reuseport_array *reuseport_array(struct bpf_map *map)
+{
+	return (struct reuseport_array *)map;
+}
+
+/* The caller must hold the reuseport_lock */
+void bpf_sk_reuseport_detach(struct sock *sk)
+{
+	struct sock __rcu **socks;
+
+	write_lock_bh(&sk->sk_callback_lock);
+	socks = sk->sk_user_data;
+	if (socks) {
+		WRITE_ONCE(sk->sk_user_data, NULL);
+		/*
+		 * Do not move this NULL assignment outside of
+		 * sk->sk_callback_lock because there is
+		 * a race with reuseport_array_free()
+		 * which does not hold the reuseport_lock.
+		 */
+		RCU_INIT_POINTER(*socks, NULL);
+	}
+	write_unlock_bh(&sk->sk_callback_lock);
+}
+
+static int reuseport_array_alloc_check(union bpf_attr *attr)
+{
+	if (attr->value_size != sizeof(u32) &&
+	    attr->value_size != sizeof(u64))
+		return -EINVAL;
+
+	return array_map_alloc_check(attr);
+}
+
+static void *reuseport_array_lookup_elem(struct bpf_map *map, void *key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = *(u32 *)key;
+
+	if (unlikely(index >= array->map.max_entries))
+		return NULL;
+
+	return rcu_dereference(array->ptrs[index]);
+}
+
+/* Called from syscall only */
+static int reuseport_array_delete_elem(struct bpf_map *map, void *key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = *(u32 *)key;
+	struct sock *sk;
+	int err;
+
+	if (index >= map->max_entries)
+		return -E2BIG;
+
+	if (!rcu_access_pointer(array->ptrs[index]))
+		return -ENOENT;
+
+	spin_lock_bh(&reuseport_lock);
+
+	sk = rcu_dereference_protected(array->ptrs[index],
+				       lockdep_is_held(&reuseport_lock));
+	if (sk) {
+		write_lock_bh(&sk->sk_callback_lock);
+		WRITE_ONCE(sk->sk_user_data, NULL);
+		RCU_INIT_POINTER(array->ptrs[index], NULL);
+		write_unlock_bh(&sk->sk_callback_lock);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+
+	spin_unlock_bh(&reuseport_lock);
+
+	return err;
+}
+
+static void reuseport_array_free(struct bpf_map *map)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	struct sock *sk;
+	u32 i;
+
+	synchronize_rcu();
+
+	/*
+	 * ops->map_*_elem() will not be able to access this
+	 * array now. Hence, this function only races with
+	 * bpf_sk_reuseport_detach() which was triggerred by
+	 * close() or disconnect().
+	 *
+	 * This function and bpf_sk_reuseport_detach() are
+	 * both removing sk from "array".  Who removes it
+	 * first does not matter.
+	 *
+	 * The only concern here is bpf_sk_reuseport_detach()
+	 * may access "array" which is being freed here.
+	 * bpf_sk_reuseport_detach() access this "array"
+	 * through sk->sk_user_data _and_ with sk->sk_callback_lock
+	 * held which is enough because this "array" is not freed
+	 * until all sk->sk_user_data has stopped referencing this "array".
+	 *
+	 * Hence, due to the above, taking "reuseport_lock" is not
+	 * needed here.
+	 */
+
+	/*
+	 * Since reuseport_lock is not taken, sk is accessed under
+	 * rcu_read_lock()
+	 */
+	rcu_read_lock();
+	for (i = 0; i < map->max_entries; i++) {
+		sk = rcu_dereference(array->ptrs[i]);
+		if (sk) {
+			write_lock_bh(&sk->sk_callback_lock);
+			/*
+			 * No need for WRITE_ONCE(). At this point,
+			 * no one is reading it without taking the
+			 * sk->sk_callback_lock.
+			 */
+			sk->sk_user_data = NULL;
+			write_unlock_bh(&sk->sk_callback_lock);
+			RCU_INIT_POINTER(array->ptrs[i], NULL);
+		}
+	}
+	rcu_read_unlock();
+
+	/*
+	 * Once reaching here, all sk->sk_user_data is not
+	 * referenceing this "array".  "array" can be freed now.
+	 */
+	bpf_map_area_free(array);
+}
+
+static struct bpf_map *reuseport_array_alloc(union bpf_attr *attr)
+{
+	int err, numa_node = bpf_map_attr_numa_node(attr);
+	struct reuseport_array *array;
+	u64 cost, array_size;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return ERR_PTR(-EPERM);
+
+	array_size = sizeof(*array);
+	array_size += (u64)attr->max_entries * sizeof(struct sock *);
+
+	/* make sure there is no u32 overflow later in round_up() */
+	cost = array_size;
+	if (cost >= U32_MAX - PAGE_SIZE)
+		return ERR_PTR(-ENOMEM);
+	cost = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;
+
+	err = bpf_map_precharge_memlock(cost);
+	if (err)
+		return ERR_PTR(err);
+
+	/* allocate all map elements and zero-initialize them */
+	array = bpf_map_area_alloc(array_size, numa_node);
+	if (!array)
+		return ERR_PTR(-ENOMEM);
+
+	/* copy mandatory map attributes */
+	bpf_map_init_from_attr(&array->map, attr);
+	array->map.pages = cost;
+
+	return &array->map;
+}
+
+int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
+				       void *value)
+{
+	struct sock *sk;
+	int err;
+
+	if (map->value_size != sizeof(u64))
+		return -ENOSPC;
+
+	rcu_read_lock();
+	sk = reuseport_array_lookup_elem(map, key);
+	if (sk) {
+		*(u64 *)value = sock_gen_cookie(sk);
+		err = 0;
+	} else {
+		err = -ENOENT;
+	}
+	rcu_read_unlock();
+
+	return err;
+}
+
+static int
+reuseport_array_update_check(const struct reuseport_array *array,
+			     const struct sock *nsk,
+			     const struct sock *osk,
+			     const struct sock_reuseport *nsk_reuse,
+			     u32 map_flags)
+{
+	if (osk && map_flags == BPF_NOEXIST)
+		return -EEXIST;
+
+	if (!osk && map_flags == BPF_EXIST)
+		return -ENOENT;
+
+	if (nsk->sk_protocol != IPPROTO_UDP && nsk->sk_protocol != IPPROTO_TCP)
+		return -ENOTSUPP;
+
+	if (nsk->sk_family != AF_INET && nsk->sk_family != AF_INET6)
+		return -ENOTSUPP;
+
+	if (nsk->sk_type != SOCK_STREAM && nsk->sk_type != SOCK_DGRAM)
+		return -ENOTSUPP;
+
+	/*
+	 * sk must be hashed (i.e. listening in the TCP case or binded
+	 * in the UDP case) and
+	 * it must also be a SO_REUSEPORT sk (i.e. reuse cannot be NULL).
+	 *
+	 * Also, sk will be used in bpf helper that is protected by
+	 * rcu_read_lock().
+	 */
+	if (!sock_flag(nsk, SOCK_RCU_FREE) || !sk_hashed(nsk) || !nsk_reuse)
+		return -EINVAL;
+
+	/* READ_ONCE because the sk->sk_callback_lock may not be held here */
+	if (READ_ONCE(nsk->sk_user_data))
+		return -EBUSY;
+
+	return 0;
+}
+
+/*
+ * Called from syscall only.
+ * The "nsk" in the fd refcnt.
+ * The "osk" and "reuse" are protected by reuseport_lock.
+ */
+int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
+				       void *value, u64 map_flags)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	struct sock *free_osk = NULL, *osk, *nsk;
+	struct sock_reuseport *reuse;
+	u32 index = *(u32 *)key;
+	struct socket *socket;
+	int err, fd;
+
+	if (map_flags > BPF_EXIST)
+		return -EINVAL;
+
+	if (index >= map->max_entries)
+		return -E2BIG;
+
+	if (map->value_size == sizeof(u64)) {
+		u64 fd64 = *(u64 *)value;
+
+		if (fd64 > S32_MAX)
+			return -EINVAL;
+		fd = fd64;
+	} else {
+		fd = *(int *)value;
+	}
+
+	socket = sockfd_lookup(fd, &err);
+	if (!socket)
+		return err;
+
+	nsk = socket->sk;
+	if (!nsk) {
+		err = -EINVAL;
+		goto put_file;
+	}
+
+	/* Quick checks before taking reuseport_lock */
+	err = reuseport_array_update_check(array, nsk,
+					   rcu_access_pointer(array->ptrs[index]),
+					   rcu_access_pointer(nsk->sk_reuseport_cb),
+					   map_flags);
+	if (err)
+		goto put_file;
+
+	spin_lock_bh(&reuseport_lock);
+	/*
+	 * Some of the checks only need reuseport_lock
+	 * but it is done under sk_callback_lock also
+	 * for simplicity reason.
+	 */
+	write_lock_bh(&nsk->sk_callback_lock);
+
+	osk = rcu_dereference_protected(array->ptrs[index],
+					lockdep_is_held(&reuseport_lock));
+	reuse = rcu_dereference_protected(nsk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	err = reuseport_array_update_check(array, nsk, osk, reuse, map_flags);
+	if (err)
+		goto put_file_unlock;
+
+	/* Ensure reuse->reuseport_id is set */
+	err = reuseport_get_id(reuse);
+	if (err < 0)
+		goto put_file_unlock;
+
+	WRITE_ONCE(nsk->sk_user_data, &array->ptrs[index]);
+	rcu_assign_pointer(array->ptrs[index], nsk);
+	free_osk = osk;
+	err = 0;
+
+put_file_unlock:
+	write_unlock_bh(&nsk->sk_callback_lock);
+
+	if (free_osk) {
+		write_lock_bh(&free_osk->sk_callback_lock);
+		WRITE_ONCE(free_osk->sk_user_data, NULL);
+		write_unlock_bh(&free_osk->sk_callback_lock);
+	}
+
+	spin_unlock_bh(&reuseport_lock);
+put_file:
+	fput(socket->file);
+	return err;
+}
+
+/* Called from syscall */
+static int reuseport_array_get_next_key(struct bpf_map *map, void *key,
+					void *next_key)
+{
+	struct reuseport_array *array = reuseport_array(map);
+	u32 index = key ? *(u32 *)key : U32_MAX;
+	u32 *next = (u32 *)next_key;
+
+	if (index >= array->map.max_entries) {
+		*next = 0;
+		return 0;
+	}
+
+	if (index == array->map.max_entries - 1)
+		return -ENOENT;
+
+	*next = index + 1;
+	return 0;
+}
+
+const struct bpf_map_ops reuseport_array_ops = {
+	.map_alloc_check = reuseport_array_alloc_check,
+	.map_alloc = reuseport_array_alloc,
+	.map_free = reuseport_array_free,
+	.map_lookup_elem = reuseport_array_lookup_elem,
+	.map_get_next_key = reuseport_array_get_next_key,
+	.map_delete_elem = reuseport_array_delete_elem,
+};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 5af4e9e2722d..57f4d076141b 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -684,6 +684,8 @@ static int map_lookup_elem(union bpf_attr *attr)
 		err = bpf_fd_array_map_lookup_elem(map, key, value);
 	} else if (IS_FD_HASH(map)) {
 		err = bpf_fd_htab_map_lookup_elem(map, key, value);
+	} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+		err = bpf_fd_reuseport_array_lookup_elem(map, key, value);
 	} else {
 		rcu_read_lock();
 		ptr = map->ops->map_lookup_elem(map, key);
@@ -790,6 +792,10 @@ static int map_update_elem(union bpf_attr *attr)
 		err = bpf_fd_htab_map_update_elem(map, f.file, key, value,
 						  attr->flags);
 		rcu_read_unlock();
+	} else if (map->map_type == BPF_MAP_TYPE_REUSEPORT_SOCKARRAY) {
+		/* rcu_read_lock() is not needed */
+		err = bpf_fd_reuseport_array_update_elem(map, key, value,
+							 attr->flags);
 	} else {
 		rcu_read_lock();
 		err = map->ops->map_update_elem(map, key, value, attr->flags);
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index cf2e4d305af9..8235f2439816 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -186,6 +186,14 @@ void reuseport_detach_sock(struct sock *sk)
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
+
+	/* At least one of the sk in this reuseport group is added to
+	 * a bpf map.  Notify the bpf side.  The bpf map logic will
+	 * remove the sk if it is indeed added to a bpf map.
+	 */
+	if (reuse->reuseport_id)
+		bpf_sk_reuseport_detach(sk);
+
 	rcu_assign_pointer(sk->sk_reuseport_cb, NULL);
 
 	for (i = 0; i < reuse->num_socks; i++) {
-- 
cgit v1.2.3


From 2dbb9b9e6df67d444fbe425c7f6014858d337adf Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:25 -0700
Subject: bpf: Introduce BPF_PROG_TYPE_SK_REUSEPORT

This patch adds a BPF_PROG_TYPE_SK_REUSEPORT which can select
a SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY.  Like other
non SK_FILTER/CGROUP_SKB program, it requires CAP_SYS_ADMIN.

BPF_PROG_TYPE_SK_REUSEPORT introduces "struct sk_reuseport_kern"
to store the bpf context instead of using the skb->cb[48].

At the SO_REUSEPORT sk lookup time, it is in the middle of transiting
from a lower layer (ipv4/ipv6) to a upper layer (udp/tcp).  At this
point,  it is not always clear where the bpf context can be appended
in the skb->cb[48] to avoid saving-and-restoring cb[].  Even putting
aside the difference between ipv4-vs-ipv6 and udp-vs-tcp.  It is not
clear if the lower layer is only ipv4 and ipv6 in the future and
will it not touch the cb[] again before transiting to the upper
layer.

For example, in udp_gro_receive(), it uses the 48 byte NAPI_GRO_CB
instead of IP[6]CB and it may still modify the cb[] after calling
the udp[46]_lib_lookup_skb().  Because of the above reason, if
sk->cb is used for the bpf ctx, saving-and-restoring is needed
and likely the whole 48 bytes cb[] has to be saved and restored.

Instead of saving, setting and restoring the cb[], this patch opts
to create a new "struct sk_reuseport_kern" and setting the needed
values in there.

The new BPF_PROG_TYPE_SK_REUSEPORT and "struct sk_reuseport_(kern|md)"
will serve all ipv4/ipv6 + udp/tcp combinations.  There is no protocol
specific usage at this point and it is also inline with the current
sock_reuseport.c implementation (i.e. no protocol specific requirement).

In "struct sk_reuseport_md", this patch exposes data/data_end/len
with semantic similar to other existing usages.  Together
with "bpf_skb_load_bytes()" and "bpf_skb_load_bytes_relative()",
the bpf prog can peek anywhere in the skb.  The "bind_inany" tells
the bpf prog that the reuseport group is bind-ed to a local
INANY address which cannot be learned from skb.

The new "bind_inany" is added to "struct sock_reuseport" which will be
used when running the new "BPF_PROG_TYPE_SK_REUSEPORT" bpf prog in order
to avoid repeating the "bind INANY" test on
"sk_v6_rcv_saddr/sk->sk_rcv_saddr" every time a bpf prog is run.  It can
only be properly initialized when a "sk->sk_reuseport" enabled sk is
adding to a hashtable (i.e. during "reuseport_alloc()" and
"reuseport_add_sock()").

The new "sk_select_reuseport()" is the main helper that the
bpf prog will use to select a SO_REUSEPORT sk.  It is the only function
that can use the new BPF_MAP_TYPE_REUSEPORT_ARRAY.  As mentioned in
the earlier patch, the validity of a selected sk is checked in
run time in "sk_select_reuseport()".  Doing the check in
verification time is difficult and inflexible (consider the map-in-map
use case).  The runtime check is to compare the selected sk's reuseport_id
with the reuseport_id that we want.  This helper will return -EXXX if the
selected sk cannot serve the incoming request (e.g. reuseport_id
not match).  The bpf prog can decide if it wants to do SK_DROP as its
discretion.

When the bpf prog returns SK_PASS, the kernel will check if a
valid sk has been selected (i.e. "reuse_kern->selected_sk != NULL").
If it does , it will use the selected sk.  If not, the kernel
will select one from "reuse->socks[]" (as before this patch).

The SK_DROP and SK_PASS handling logic will be in the next patch.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/bpf_types.h       |   3 +
 include/linux/filter.h          |  15 +++
 include/net/addrconf.h          |   1 +
 include/net/sock_reuseport.h    |   6 +-
 include/uapi/linux/bpf.h        |  36 +++++-
 kernel/bpf/verifier.c           |   9 ++
 net/core/filter.c               | 269 +++++++++++++++++++++++++++++++++++++++-
 net/core/sock_reuseport.c       |  20 ++-
 net/ipv4/inet_connection_sock.c |   9 ++
 net/ipv4/inet_hashtables.c      |   5 +-
 net/ipv4/udp.c                  |   5 +-
 11 files changed, 365 insertions(+), 13 deletions(-)

diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index 14fd6c02d258..cd26c090e7c0 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -29,6 +29,9 @@ BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
 #ifdef CONFIG_BPF_LIRC_MODE2
 BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
 #endif
+#ifdef CONFIG_INET
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport)
+#endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_PERCPU_ARRAY, percpu_array_map_ops)
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 2b072dab32c0..70e9d57677fe 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -32,6 +32,7 @@ struct seccomp_data;
 struct bpf_prog_aux;
 struct xdp_rxq_info;
 struct xdp_buff;
+struct sock_reuseport;
 
 /* ArgX, context and stack frame pointer register positions. Note,
  * Arg1, Arg2, Arg3, etc are used as argument mappings of function
@@ -833,6 +834,20 @@ void bpf_warn_invalid_xdp_action(u32 act);
 struct sock *do_sk_redirect_map(struct sk_buff *skb);
 struct sock *do_msg_redirect_map(struct sk_msg_buff *md);
 
+#ifdef CONFIG_INET
+struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
+				  struct bpf_prog *prog, struct sk_buff *skb,
+				  u32 hash);
+#else
+static inline struct sock *
+bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
+		     struct bpf_prog *prog, struct sk_buff *skb,
+		     u32 hash)
+{
+	return NULL;
+}
+#endif
+
 #ifdef CONFIG_BPF_JIT
 extern int bpf_jit_enable;
 extern int bpf_jit_harden;
diff --git a/include/net/addrconf.h b/include/net/addrconf.h
index 5f43f7a70fe6..6def0351bcc3 100644
--- a/include/net/addrconf.h
+++ b/include/net/addrconf.h
@@ -108,6 +108,7 @@ int ipv6_get_lladdr(struct net_device *dev, struct in6_addr *addr,
 		    u32 banned_flags);
 bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 			  bool match_wildcard);
+bool inet_rcv_saddr_any(const struct sock *sk);
 void addrconf_join_solict(struct net_device *dev, const struct in6_addr *addr);
 void addrconf_leave_solict(struct inet6_dev *idev, const struct in6_addr *addr);
 
diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index e1a7681856f7..73b569556be6 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -21,12 +21,14 @@ struct sock_reuseport {
 	unsigned int		synq_overflow_ts;
 	/* ID stays the same even after the size of socks[] grows. */
 	unsigned int		reuseport_id;
+	bool			bind_inany;
 	struct bpf_prog __rcu	*prog;		/* optional BPF sock selector */
 	struct sock		*socks[0];	/* array of sock pointers */
 };
 
-extern int reuseport_alloc(struct sock *sk);
-extern int reuseport_add_sock(struct sock *sk, struct sock *sk2);
+extern int reuseport_alloc(struct sock *sk, bool bind_inany);
+extern int reuseport_add_sock(struct sock *sk, struct sock *sk2,
+			      bool bind_inany);
 extern void reuseport_detach_sock(struct sock *sk);
 extern struct sock *reuseport_select_sock(struct sock *sk,
 					  u32 hash,
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 40f584bc7da0..3102a2a23c31 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -151,6 +151,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 	BPF_PROG_TYPE_LWT_SEG6LOCAL,
 	BPF_PROG_TYPE_LIRC_MODE2,
+	BPF_PROG_TYPE_SK_REUSEPORT,
 };
 
 enum bpf_attach_type {
@@ -2114,6 +2115,14 @@ union bpf_attr {
  *		the shared data.
  *	Return
  *		Pointer to the local storage area.
+ *
+ * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		Select a SO_REUSEPORT sk from a	BPF_MAP_TYPE_REUSEPORT_ARRAY map
+ *		It checks the selected sk is matching the incoming
+ *		request in the skb.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2197,7 +2206,8 @@ union bpf_attr {
 	FN(rc_keydown),			\
 	FN(skb_cgroup_id),		\
 	FN(get_current_cgroup_id),	\
-	FN(get_local_storage),
+	FN(get_local_storage),		\
+	FN(sk_select_reuseport),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2414,6 +2424,30 @@ struct sk_msg_md {
 	__u32 local_port;	/* stored in host byte order */
 };
 
+struct sk_reuseport_md {
+	/*
+	 * Start of directly accessible data. It begins from
+	 * the tcp/udp header.
+	 */
+	void *data;
+	void *data_end;		/* End of directly accessible data */
+	/*
+	 * Total length of packet (starting from the tcp/udp header).
+	 * Note that the directly accessible bytes (data_end - data)
+	 * could be less than this "len".  Those bytes could be
+	 * indirectly read by a helper "bpf_skb_load_bytes()".
+	 */
+	__u32 len;
+	/*
+	 * Eth protocol in the mac header (network byte order). e.g.
+	 * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
+	 */
+	__u32 eth_protocol;
+	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
+	__u32 bind_inany;	/* Is sock bound to an INANY address? */
+	__u32 hash;		/* A hash of the packet 4 tuples */
+};
+
 #define BPF_TAG_SIZE	8
 
 struct bpf_prog_info {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 587468a9c37d..ca90679a7fe5 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1310,6 +1310,7 @@ static bool may_access_direct_pkt_data(struct bpf_verifier_env *env,
 	case BPF_PROG_TYPE_LWT_IN:
 	case BPF_PROG_TYPE_LWT_OUT:
 	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+	case BPF_PROG_TYPE_SK_REUSEPORT:
 		/* dst_input() and dst_output() can't write for now */
 		if (t == BPF_WRITE)
 			return false;
@@ -2166,6 +2167,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		    func_id != BPF_FUNC_msg_redirect_hash)
 			goto error;
 		break;
+	case BPF_MAP_TYPE_REUSEPORT_SOCKARRAY:
+		if (func_id != BPF_FUNC_sk_select_reuseport)
+			goto error;
+		break;
 	default:
 		break;
 	}
@@ -2217,6 +2222,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 		if (map->map_type != BPF_MAP_TYPE_CGROUP_STORAGE)
 			goto error;
 		break;
+	case BPF_FUNC_sk_select_reuseport:
+		if (map->map_type != BPF_MAP_TYPE_REUSEPORT_SOCKARRAY)
+			goto error;
+		break;
 	default:
 		break;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index 2de7dd9f2a57..142595b4e0d1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1462,7 +1462,7 @@ static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk)
 		return -ENOMEM;
 
 	if (sk_unhashed(sk) && sk->sk_reuseport) {
-		err = reuseport_alloc(sk);
+		err = reuseport_alloc(sk, false);
 		if (err)
 			return err;
 	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
@@ -7013,3 +7013,270 @@ out:
 	release_sock(sk);
 	return ret;
 }
+
+#ifdef CONFIG_INET
+struct sk_reuseport_kern {
+	struct sk_buff *skb;
+	struct sock *sk;
+	struct sock *selected_sk;
+	void *data_end;
+	u32 hash;
+	u32 reuseport_id;
+	bool bind_inany;
+};
+
+static void bpf_init_reuseport_kern(struct sk_reuseport_kern *reuse_kern,
+				    struct sock_reuseport *reuse,
+				    struct sock *sk, struct sk_buff *skb,
+				    u32 hash)
+{
+	reuse_kern->skb = skb;
+	reuse_kern->sk = sk;
+	reuse_kern->selected_sk = NULL;
+	reuse_kern->data_end = skb->data + skb_headlen(skb);
+	reuse_kern->hash = hash;
+	reuse_kern->reuseport_id = reuse->reuseport_id;
+	reuse_kern->bind_inany = reuse->bind_inany;
+}
+
+struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
+				  struct bpf_prog *prog, struct sk_buff *skb,
+				  u32 hash)
+{
+	struct sk_reuseport_kern reuse_kern;
+	enum sk_action action;
+
+	bpf_init_reuseport_kern(&reuse_kern, reuse, sk, skb, hash);
+	action = BPF_PROG_RUN(prog, &reuse_kern);
+
+	if (action == SK_PASS)
+		return reuse_kern.selected_sk;
+	else
+		return ERR_PTR(-ECONNREFUSED);
+}
+
+BPF_CALL_4(sk_select_reuseport, struct sk_reuseport_kern *, reuse_kern,
+	   struct bpf_map *, map, void *, key, u32, flags)
+{
+	struct sock_reuseport *reuse;
+	struct sock *selected_sk;
+
+	selected_sk = map->ops->map_lookup_elem(map, key);
+	if (!selected_sk)
+		return -ENOENT;
+
+	reuse = rcu_dereference(selected_sk->sk_reuseport_cb);
+	if (!reuse)
+		/* selected_sk is unhashed (e.g. by close()) after the
+		 * above map_lookup_elem().  Treat selected_sk has already
+		 * been removed from the map.
+		 */
+		return -ENOENT;
+
+	if (unlikely(reuse->reuseport_id != reuse_kern->reuseport_id)) {
+		struct sock *sk;
+
+		if (unlikely(!reuse_kern->reuseport_id))
+			/* There is a small race between adding the
+			 * sk to the map and setting the
+			 * reuse_kern->reuseport_id.
+			 * Treat it as the sk has not been added to
+			 * the bpf map yet.
+			 */
+			return -ENOENT;
+
+		sk = reuse_kern->sk;
+		if (sk->sk_protocol != selected_sk->sk_protocol)
+			return -EPROTOTYPE;
+		else if (sk->sk_family != selected_sk->sk_family)
+			return -EAFNOSUPPORT;
+
+		/* Catch all. Likely bound to a different sockaddr. */
+		return -EBADFD;
+	}
+
+	reuse_kern->selected_sk = selected_sk;
+
+	return 0;
+}
+
+static const struct bpf_func_proto sk_select_reuseport_proto = {
+	.func           = sk_select_reuseport,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_CONST_MAP_PTR,
+	.arg3_type      = ARG_PTR_TO_MAP_KEY,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(sk_reuseport_load_bytes,
+	   const struct sk_reuseport_kern *, reuse_kern, u32, offset,
+	   void *, to, u32, len)
+{
+	return ____bpf_skb_load_bytes(reuse_kern->skb, offset, to, len);
+}
+
+static const struct bpf_func_proto sk_reuseport_load_bytes_proto = {
+	.func		= sk_reuseport_load_bytes,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+};
+
+BPF_CALL_5(sk_reuseport_load_bytes_relative,
+	   const struct sk_reuseport_kern *, reuse_kern, u32, offset,
+	   void *, to, u32, len, u32, start_header)
+{
+	return ____bpf_skb_load_bytes_relative(reuse_kern->skb, offset, to,
+					       len, start_header);
+}
+
+static const struct bpf_func_proto sk_reuseport_load_bytes_relative_proto = {
+	.func		= sk_reuseport_load_bytes_relative,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
+static const struct bpf_func_proto *
+sk_reuseport_func_proto(enum bpf_func_id func_id,
+			const struct bpf_prog *prog)
+{
+	switch (func_id) {
+	case BPF_FUNC_sk_select_reuseport:
+		return &sk_select_reuseport_proto;
+	case BPF_FUNC_skb_load_bytes:
+		return &sk_reuseport_load_bytes_proto;
+	case BPF_FUNC_skb_load_bytes_relative:
+		return &sk_reuseport_load_bytes_relative_proto;
+	default:
+		return bpf_base_func_proto(func_id);
+	}
+}
+
+static bool
+sk_reuseport_is_valid_access(int off, int size,
+			     enum bpf_access_type type,
+			     const struct bpf_prog *prog,
+			     struct bpf_insn_access_aux *info)
+{
+	const u32 size_default = sizeof(__u32);
+
+	if (off < 0 || off >= sizeof(struct sk_reuseport_md) ||
+	    off % size || type != BPF_READ)
+		return false;
+
+	switch (off) {
+	case offsetof(struct sk_reuseport_md, data):
+		info->reg_type = PTR_TO_PACKET;
+		return size == sizeof(__u64);
+
+	case offsetof(struct sk_reuseport_md, data_end):
+		info->reg_type = PTR_TO_PACKET_END;
+		return size == sizeof(__u64);
+
+	case offsetof(struct sk_reuseport_md, hash):
+		return size == size_default;
+
+	/* Fields that allow narrowing */
+	case offsetof(struct sk_reuseport_md, eth_protocol):
+		if (size < FIELD_SIZEOF(struct sk_buff, protocol))
+			return false;
+	case offsetof(struct sk_reuseport_md, ip_protocol):
+	case offsetof(struct sk_reuseport_md, bind_inany):
+	case offsetof(struct sk_reuseport_md, len):
+		bpf_ctx_record_field_size(info, size_default);
+		return bpf_ctx_narrow_access_ok(off, size, size_default);
+
+	default:
+		return false;
+	}
+}
+
+#define SK_REUSEPORT_LOAD_FIELD(F) ({					\
+	*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \
+			      si->dst_reg, si->src_reg,			\
+			      bpf_target_off(struct sk_reuseport_kern, F, \
+					     FIELD_SIZEOF(struct sk_reuseport_kern, F), \
+					     target_size));		\
+	})
+
+#define SK_REUSEPORT_LOAD_SKB_FIELD(SKB_FIELD)				\
+	SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern,		\
+				    struct sk_buff,			\
+				    skb,				\
+				    SKB_FIELD)
+
+#define SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(SK_FIELD, BPF_SIZE, EXTRA_OFF) \
+	SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(struct sk_reuseport_kern,	\
+					     struct sock,		\
+					     sk,			\
+					     SK_FIELD, BPF_SIZE, EXTRA_OFF)
+
+static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
+					   const struct bpf_insn *si,
+					   struct bpf_insn *insn_buf,
+					   struct bpf_prog *prog,
+					   u32 *target_size)
+{
+	struct bpf_insn *insn = insn_buf;
+
+	switch (si->off) {
+	case offsetof(struct sk_reuseport_md, data):
+		SK_REUSEPORT_LOAD_SKB_FIELD(data);
+		break;
+
+	case offsetof(struct sk_reuseport_md, len):
+		SK_REUSEPORT_LOAD_SKB_FIELD(len);
+		break;
+
+	case offsetof(struct sk_reuseport_md, eth_protocol):
+		SK_REUSEPORT_LOAD_SKB_FIELD(protocol);
+		break;
+
+	case offsetof(struct sk_reuseport_md, ip_protocol):
+		BUILD_BUG_ON(hweight_long(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
+		SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset,
+						    BPF_W, 0);
+		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
+		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
+					SK_FL_PROTO_SHIFT);
+		/* SK_FL_PROTO_MASK and SK_FL_PROTO_SHIFT are endian
+		 * aware.  No further narrowing or masking is needed.
+		 */
+		*target_size = 1;
+		break;
+
+	case offsetof(struct sk_reuseport_md, data_end):
+		SK_REUSEPORT_LOAD_FIELD(data_end);
+		break;
+
+	case offsetof(struct sk_reuseport_md, hash):
+		SK_REUSEPORT_LOAD_FIELD(hash);
+		break;
+
+	case offsetof(struct sk_reuseport_md, bind_inany):
+		SK_REUSEPORT_LOAD_FIELD(bind_inany);
+		break;
+	}
+
+	return insn - insn_buf;
+}
+
+const struct bpf_verifier_ops sk_reuseport_verifier_ops = {
+	.get_func_proto		= sk_reuseport_func_proto,
+	.is_valid_access	= sk_reuseport_is_valid_access,
+	.convert_ctx_access	= sk_reuseport_convert_ctx_access,
+};
+
+const struct bpf_prog_ops sk_reuseport_prog_ops = {
+};
+#endif /* CONFIG_INET */
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index 8235f2439816..d260167f5f77 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -51,7 +51,7 @@ static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks)
 	return reuse;
 }
 
-int reuseport_alloc(struct sock *sk)
+int reuseport_alloc(struct sock *sk, bool bind_inany)
 {
 	struct sock_reuseport *reuse;
 
@@ -63,9 +63,17 @@ int reuseport_alloc(struct sock *sk)
 	/* Allocation attempts can occur concurrently via the setsockopt path
 	 * and the bind/hash path.  Nothing to do when we lose the race.
 	 */
-	if (rcu_dereference_protected(sk->sk_reuseport_cb,
-				      lockdep_is_held(&reuseport_lock)))
+	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
+					  lockdep_is_held(&reuseport_lock));
+	if (reuse) {
+		/* Only set reuse->bind_inany if the bind_inany is true.
+		 * Otherwise, it will overwrite the reuse->bind_inany
+		 * which was set by the bind/hash path.
+		 */
+		if (bind_inany)
+			reuse->bind_inany = bind_inany;
 		goto out;
+	}
 
 	reuse = __reuseport_alloc(INIT_SOCKS);
 	if (!reuse) {
@@ -75,6 +83,7 @@ int reuseport_alloc(struct sock *sk)
 
 	reuse->socks[0] = sk;
 	reuse->num_socks = 1;
+	reuse->bind_inany = bind_inany;
 	rcu_assign_pointer(sk->sk_reuseport_cb, reuse);
 
 out:
@@ -101,6 +110,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse)
 	more_reuse->num_socks = reuse->num_socks;
 	more_reuse->prog = reuse->prog;
 	more_reuse->reuseport_id = reuse->reuseport_id;
+	more_reuse->bind_inany = reuse->bind_inany;
 
 	memcpy(more_reuse->socks, reuse->socks,
 	       reuse->num_socks * sizeof(struct sock *));
@@ -136,12 +146,12 @@ static void reuseport_free_rcu(struct rcu_head *head)
  *  @sk2: Socket belonging to the existing reuseport group.
  *  May return ENOMEM and not add socket to group under memory pressure.
  */
-int reuseport_add_sock(struct sock *sk, struct sock *sk2)
+int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany)
 {
 	struct sock_reuseport *old_reuse, *reuse;
 
 	if (!rcu_access_pointer(sk2->sk_reuseport_cb)) {
-		int err = reuseport_alloc(sk2);
+		int err = reuseport_alloc(sk2, bind_inany);
 
 		if (err)
 			return err;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 33a88e045efd..dfd5009f96ef 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -107,6 +107,15 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
 }
 EXPORT_SYMBOL(inet_rcv_saddr_equal);
 
+bool inet_rcv_saddr_any(const struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	if (sk->sk_family == AF_INET6)
+		return ipv6_addr_any(&sk->sk_v6_rcv_saddr);
+#endif
+	return !sk->sk_rcv_saddr;
+}
+
 void inet_get_local_port_range(struct net *net, int *low, int *high)
 {
 	unsigned int seq;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 3647167c8fa3..370e24463fb7 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -567,10 +567,11 @@ static int inet_reuseport_add_sock(struct sock *sk,
 		    inet_csk(sk2)->icsk_bind_hash == tb &&
 		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
 		    inet_rcv_saddr_equal(sk, sk2, false))
-			return reuseport_add_sock(sk, sk2);
+			return reuseport_add_sock(sk, sk2,
+						  inet_rcv_saddr_any(sk));
 	}
 
-	return reuseport_alloc(sk);
+	return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
 }
 
 int __inet_hash(struct sock *sk, struct sock *osk)
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 060e841dde40..038dd7909051 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -221,11 +221,12 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 		    (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
 		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
 		    inet_rcv_saddr_equal(sk, sk2, false)) {
-			return reuseport_add_sock(sk, sk2);
+			return reuseport_add_sock(sk, sk2,
+						  inet_rcv_saddr_any(sk));
 		}
 	}
 
-	return reuseport_alloc(sk);
+	return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
 }
 
 /**
-- 
cgit v1.2.3


From 8217ca653ec601246832d562207bc24bdf652d2f Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:26 -0700
Subject: bpf: Enable BPF_PROG_TYPE_SK_REUSEPORT bpf prog in reuseport
 selection

This patch allows a BPF_PROG_TYPE_SK_REUSEPORT bpf prog to select a
SO_REUSEPORT sk from a BPF_MAP_TYPE_REUSEPORT_ARRAY introduced in
the earlier patch.  "bpf_run_sk_reuseport()" will return -ECONNREFUSED
when the BPF_PROG_TYPE_SK_REUSEPORT prog returns SK_DROP.
The callers, in inet[6]_hashtable.c and ipv[46]/udp.c, are modified to
handle this case and return NULL immediately instead of continuing the
sk search from its hashtable.

It re-uses the existing SO_ATTACH_REUSEPORT_EBPF setsockopt to attach
BPF_PROG_TYPE_SK_REUSEPORT.  The "sk_reuseport_attach_bpf()" will check
if the attaching bpf prog is in the new SK_REUSEPORT or the existing
SOCKET_FILTER type and then check different things accordingly.

One level of "__reuseport_attach_prog()" call is removed.  The
"sk_unhashed() && ..." and "sk->sk_reuseport_cb" tests are pushed
back to "reuseport_attach_prog()" in sock_reuseport.c.  sock_reuseport.c
seems to have more knowledge on those test requirements than filter.c.
In "reuseport_attach_prog()", after new_prog is attached to reuse->prog,
the old_prog (if any) is also directly freed instead of returning the
old_prog to the caller and asking the caller to free.

The sysctl_optmem_max check is moved back to the
"sk_reuseport_attach_filter()" and "sk_reuseport_attach_bpf()".
As of other bpf prog types, the new BPF_PROG_TYPE_SK_REUSEPORT is only
bounded by the usual "bpf_prog_charge_memlock()" during load time
instead of bounded by both bpf_prog_charge_memlock and sysctl_optmem_max.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/filter.h       |  1 +
 include/net/sock_reuseport.h |  3 +-
 net/core/filter.c            | 87 ++++++++++++++++++++++++++------------------
 net/core/sock_reuseport.c    | 36 +++++++++++++-----
 net/ipv4/inet_hashtables.c   | 14 ++++---
 net/ipv4/udp.c               |  4 ++
 net/ipv6/inet6_hashtables.c  | 14 ++++---
 net/ipv6/udp.c               |  4 ++
 8 files changed, 106 insertions(+), 57 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 70e9d57677fe..5d565c50bcb2 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -753,6 +753,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_attach_bpf(u32 ufd, struct sock *sk);
 int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk);
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk);
+void sk_reuseport_prog_free(struct bpf_prog *prog);
 int sk_detach_filter(struct sock *sk);
 int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
 		  unsigned int len);
diff --git a/include/net/sock_reuseport.h b/include/net/sock_reuseport.h
index 73b569556be6..8a5f70c7cdf2 100644
--- a/include/net/sock_reuseport.h
+++ b/include/net/sock_reuseport.h
@@ -34,8 +34,7 @@ extern struct sock *reuseport_select_sock(struct sock *sk,
 					  u32 hash,
 					  struct sk_buff *skb,
 					  int hdr_len);
-extern struct bpf_prog *reuseport_attach_prog(struct sock *sk,
-					      struct bpf_prog *prog);
+extern int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog);
 int reuseport_get_id(struct sock_reuseport *reuse);
 
 #endif  /* _SOCK_REUSEPORT_H */
diff --git a/net/core/filter.c b/net/core/filter.c
index 142595b4e0d1..22906b31d43f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -1453,30 +1453,6 @@ static int __sk_attach_prog(struct bpf_prog *prog, struct sock *sk)
 	return 0;
 }
 
-static int __reuseport_attach_prog(struct bpf_prog *prog, struct sock *sk)
-{
-	struct bpf_prog *old_prog;
-	int err;
-
-	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
-		return -ENOMEM;
-
-	if (sk_unhashed(sk) && sk->sk_reuseport) {
-		err = reuseport_alloc(sk, false);
-		if (err)
-			return err;
-	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
-		/* The socket wasn't bound with SO_REUSEPORT */
-		return -EINVAL;
-	}
-
-	old_prog = reuseport_attach_prog(sk, prog);
-	if (old_prog)
-		bpf_prog_destroy(old_prog);
-
-	return 0;
-}
-
 static
 struct bpf_prog *__get_filter(struct sock_fprog *fprog, struct sock *sk)
 {
@@ -1550,13 +1526,15 @@ int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk)
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __reuseport_attach_prog(prog, sk);
-	if (err < 0) {
+	if (bpf_prog_size(prog->len) > sysctl_optmem_max)
+		err = -ENOMEM;
+	else
+		err = reuseport_attach_prog(sk, prog);
+
+	if (err)
 		__bpf_prog_release(prog);
-		return err;
-	}
 
-	return 0;
+	return err;
 }
 
 static struct bpf_prog *__get_bpf(u32 ufd, struct sock *sk)
@@ -1586,19 +1564,58 @@ int sk_attach_bpf(u32 ufd, struct sock *sk)
 
 int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk)
 {
-	struct bpf_prog *prog = __get_bpf(ufd, sk);
+	struct bpf_prog *prog;
 	int err;
 
+	if (sock_flag(sk, SOCK_FILTER_LOCKED))
+		return -EPERM;
+
+	prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SOCKET_FILTER);
+	if (IS_ERR(prog) && PTR_ERR(prog) == -EINVAL)
+		prog = bpf_prog_get_type(ufd, BPF_PROG_TYPE_SK_REUSEPORT);
 	if (IS_ERR(prog))
 		return PTR_ERR(prog);
 
-	err = __reuseport_attach_prog(prog, sk);
-	if (err < 0) {
-		bpf_prog_put(prog);
-		return err;
+	if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) {
+		/* Like other non BPF_PROG_TYPE_SOCKET_FILTER
+		 * bpf prog (e.g. sockmap).  It depends on the
+		 * limitation imposed by bpf_prog_load().
+		 * Hence, sysctl_optmem_max is not checked.
+		 */
+		if ((sk->sk_type != SOCK_STREAM &&
+		     sk->sk_type != SOCK_DGRAM) ||
+		    (sk->sk_protocol != IPPROTO_UDP &&
+		     sk->sk_protocol != IPPROTO_TCP) ||
+		    (sk->sk_family != AF_INET &&
+		     sk->sk_family != AF_INET6)) {
+			err = -ENOTSUPP;
+			goto err_prog_put;
+		}
+	} else {
+		/* BPF_PROG_TYPE_SOCKET_FILTER */
+		if (bpf_prog_size(prog->len) > sysctl_optmem_max) {
+			err = -ENOMEM;
+			goto err_prog_put;
+		}
 	}
 
-	return 0;
+	err = reuseport_attach_prog(sk, prog);
+err_prog_put:
+	if (err)
+		bpf_prog_put(prog);
+
+	return err;
+}
+
+void sk_reuseport_prog_free(struct bpf_prog *prog)
+{
+	if (!prog)
+		return;
+
+	if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
+		bpf_prog_put(prog);
+	else
+		bpf_prog_destroy(prog);
 }
 
 struct bpf_scratchpad {
diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c
index d260167f5f77..ba5cba56f574 100644
--- a/net/core/sock_reuseport.c
+++ b/net/core/sock_reuseport.c
@@ -9,6 +9,7 @@
 #include <net/sock_reuseport.h>
 #include <linux/bpf.h>
 #include <linux/idr.h>
+#include <linux/filter.h>
 #include <linux/rcupdate.h>
 
 #define INIT_SOCKS 128
@@ -133,8 +134,7 @@ static void reuseport_free_rcu(struct rcu_head *head)
 	struct sock_reuseport *reuse;
 
 	reuse = container_of(head, struct sock_reuseport, rcu);
-	if (reuse->prog)
-		bpf_prog_destroy(reuse->prog);
+	sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1));
 	if (reuse->reuseport_id)
 		ida_simple_remove(&reuseport_ida, reuse->reuseport_id);
 	kfree(reuse);
@@ -219,9 +219,9 @@ void reuseport_detach_sock(struct sock *sk)
 }
 EXPORT_SYMBOL(reuseport_detach_sock);
 
-static struct sock *run_bpf(struct sock_reuseport *reuse, u16 socks,
-			    struct bpf_prog *prog, struct sk_buff *skb,
-			    int hdr_len)
+static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks,
+				   struct bpf_prog *prog, struct sk_buff *skb,
+				   int hdr_len)
 {
 	struct sk_buff *nskb = NULL;
 	u32 index;
@@ -282,9 +282,15 @@ struct sock *reuseport_select_sock(struct sock *sk,
 		/* paired with smp_wmb() in reuseport_add_sock() */
 		smp_rmb();
 
-		if (prog && skb)
-			sk2 = run_bpf(reuse, socks, prog, skb, hdr_len);
+		if (!prog || !skb)
+			goto select_by_hash;
+
+		if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT)
+			sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash);
+		else
+			sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len);
 
+select_by_hash:
 		/* no bpf or invalid bpf result: fall back to hash usage */
 		if (!sk2)
 			sk2 = reuse->socks[reciprocal_scale(hash, socks)];
@@ -296,12 +302,21 @@ out:
 }
 EXPORT_SYMBOL(reuseport_select_sock);
 
-struct bpf_prog *
-reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
+int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 {
 	struct sock_reuseport *reuse;
 	struct bpf_prog *old_prog;
 
+	if (sk_unhashed(sk) && sk->sk_reuseport) {
+		int err = reuseport_alloc(sk, false);
+
+		if (err)
+			return err;
+	} else if (!rcu_access_pointer(sk->sk_reuseport_cb)) {
+		/* The socket wasn't bound with SO_REUSEPORT */
+		return -EINVAL;
+	}
+
 	spin_lock_bh(&reuseport_lock);
 	reuse = rcu_dereference_protected(sk->sk_reuseport_cb,
 					  lockdep_is_held(&reuseport_lock));
@@ -310,6 +325,7 @@ reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog)
 	rcu_assign_pointer(reuse->prog, prog);
 	spin_unlock_bh(&reuseport_lock);
 
-	return old_prog;
+	sk_reuseport_prog_free(old_prog);
+	return 0;
 }
 EXPORT_SYMBOL(reuseport_attach_prog);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 370e24463fb7..f5c9ef2586de 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -328,7 +328,7 @@ struct sock *__inet_lookup_listener(struct net *net,
 				    saddr, sport, daddr, hnum,
 				    dif, sdif);
 	if (result)
-		return result;
+		goto done;
 
 	/* Lookup lhash2 with INADDR_ANY */
 
@@ -337,9 +337,10 @@ struct sock *__inet_lookup_listener(struct net *net,
 	if (ilb2->count > ilb->count)
 		goto port_lookup;
 
-	return inet_lhash2_lookup(net, ilb2, skb, doff,
-				  saddr, sport, daddr, hnum,
-				  dif, sdif);
+	result = inet_lhash2_lookup(net, ilb2, skb, doff,
+				    saddr, sport, daddr, hnum,
+				    dif, sdif);
+	goto done;
 
 port_lookup:
 	sk_for_each_rcu(sk, &ilb->head) {
@@ -352,12 +353,15 @@ port_lookup:
 				result = reuseport_select_sock(sk, phash,
 							       skb, doff);
 				if (result)
-					return result;
+					goto done;
 			}
 			result = sk;
 			hiscore = score;
 		}
 	}
+done:
+	if (unlikely(IS_ERR(result)))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(__inet_lookup_listener);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 038dd7909051..f4e35b2ff8b8 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -499,6 +499,8 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 						  daddr, hnum, dif, sdif,
 						  exact_dif, hslot2, skb);
 		}
+		if (unlikely(IS_ERR(result)))
+			return NULL;
 		return result;
 	}
 begin:
@@ -513,6 +515,8 @@ begin:
 						   saddr, sport);
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
+				if (unlikely(IS_ERR(result)))
+					return NULL;
 				if (result)
 					return result;
 			}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 595ad408dba0..3d7c7460a0c5 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -191,7 +191,7 @@ struct sock *inet6_lookup_listener(struct net *net,
 				     saddr, sport, daddr, hnum,
 				     dif, sdif);
 	if (result)
-		return result;
+		goto done;
 
 	/* Lookup lhash2 with in6addr_any */
 
@@ -200,9 +200,10 @@ struct sock *inet6_lookup_listener(struct net *net,
 	if (ilb2->count > ilb->count)
 		goto port_lookup;
 
-	return inet6_lhash2_lookup(net, ilb2, skb, doff,
-				   saddr, sport, daddr, hnum,
-				   dif, sdif);
+	result = inet6_lhash2_lookup(net, ilb2, skb, doff,
+				     saddr, sport, daddr, hnum,
+				     dif, sdif);
+	goto done;
 
 port_lookup:
 	sk_for_each(sk, &ilb->head) {
@@ -214,12 +215,15 @@ port_lookup:
 				result = reuseport_select_sock(sk, phash,
 							       skb, doff);
 				if (result)
-					return result;
+					goto done;
 			}
 			result = sk;
 			hiscore = score;
 		}
 	}
+done:
+	if (unlikely(IS_ERR(result)))
+		return NULL;
 	return result;
 }
 EXPORT_SYMBOL_GPL(inet6_lookup_listener);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index f6b96956a8ed..83f4c77c79d8 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -235,6 +235,8 @@ struct sock *__udp6_lib_lookup(struct net *net,
 						  exact_dif, hslot2,
 						  skb);
 		}
+		if (unlikely(IS_ERR(result)))
+			return NULL;
 		return result;
 	}
 begin:
@@ -249,6 +251,8 @@ begin:
 						    saddr, sport);
 				result = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
+				if (unlikely(IS_ERR(result)))
+					return NULL;
 				if (result)
 					return result;
 			}
-- 
cgit v1.2.3


From aa5f0c96cc7b96a678779055b2ff4cd9dabd8ba7 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:27 -0700
Subject: bpf: Refactor ARRAY_SIZE macro to bpf_util.h

This patch refactors the ARRAY_SIZE macro to bpf_util.h.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/bpf_util.h       | 4 ++++
 tools/testing/selftests/bpf/test_align.c     | 5 +----
 tools/testing/selftests/bpf/test_btf.c       | 5 +----
 tools/testing/selftests/bpf/test_sock.c      | 5 +----
 tools/testing/selftests/bpf/test_sock_addr.c | 5 +----
 tools/testing/selftests/bpf/test_verifier.c  | 5 +----
 6 files changed, 9 insertions(+), 20 deletions(-)

diff --git a/tools/testing/selftests/bpf/bpf_util.h b/tools/testing/selftests/bpf/bpf_util.h
index d0811b3d6a6f..315a44fa32af 100644
--- a/tools/testing/selftests/bpf/bpf_util.h
+++ b/tools/testing/selftests/bpf/bpf_util.h
@@ -44,4 +44,8 @@ static inline unsigned int bpf_num_possible_cpus(void)
 		name[bpf_num_possible_cpus()]
 #define bpf_percpu(name, cpu) name[(cpu)].v
 
+#ifndef ARRAY_SIZE
+# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
+#endif
+
 #endif /* __BPF_UTIL__ */
diff --git a/tools/testing/selftests/bpf/test_align.c b/tools/testing/selftests/bpf/test_align.c
index 6b1b302310fe..5f377ec53f2f 100644
--- a/tools/testing/selftests/bpf/test_align.c
+++ b/tools/testing/selftests/bpf/test_align.c
@@ -18,10 +18,7 @@
 
 #include "../../../include/linux/filter.h"
 #include "bpf_rlimit.h"
-
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_util.h"
 
 #define MAX_INSNS	512
 #define MAX_MATCHES	16
diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c
index 7fa8c800c540..6b5cfeb7a9cc 100644
--- a/tools/testing/selftests/bpf/test_btf.c
+++ b/tools/testing/selftests/bpf/test_btf.c
@@ -19,6 +19,7 @@
 #include <bpf/btf.h>
 
 #include "bpf_rlimit.h"
+#include "bpf_util.h"
 
 static uint32_t pass_cnt;
 static uint32_t error_cnt;
@@ -93,10 +94,6 @@ static int __base_pr(const char *format, ...)
 #define MAX_NR_RAW_TYPES 1024
 #define BTF_LOG_BUF_SIZE 65535
 
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 static struct args {
 	unsigned int raw_test_num;
 	unsigned int file_test_num;
diff --git a/tools/testing/selftests/bpf/test_sock.c b/tools/testing/selftests/bpf/test_sock.c
index f4d99fabc56d..b8ebe2f58074 100644
--- a/tools/testing/selftests/bpf/test_sock.c
+++ b/tools/testing/selftests/bpf/test_sock.c
@@ -14,10 +14,7 @@
 
 #include "cgroup_helpers.h"
 #include "bpf_rlimit.h"
-
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
+#include "bpf_util.h"
 
 #define CG_PATH		"/foo"
 #define MAX_INSNS	512
diff --git a/tools/testing/selftests/bpf/test_sock_addr.c b/tools/testing/selftests/bpf/test_sock_addr.c
index 2e45c92d1111..aeeb76a54d63 100644
--- a/tools/testing/selftests/bpf/test_sock_addr.c
+++ b/tools/testing/selftests/bpf/test_sock_addr.c
@@ -20,15 +20,12 @@
 
 #include "cgroup_helpers.h"
 #include "bpf_rlimit.h"
+#include "bpf_util.h"
 
 #ifndef ENOTSUPP
 # define ENOTSUPP 524
 #endif
 
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 #define CG_PATH	"/foo"
 #define CONNECT4_PROG_PATH	"./connect4_prog.o"
 #define CONNECT6_PROG_PATH	"./connect6_prog.o"
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index 452cf5c6c784..67c412d19c09 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -42,12 +42,9 @@
 #endif
 #include "bpf_rlimit.h"
 #include "bpf_rand.h"
+#include "bpf_util.h"
 #include "../../../include/linux/filter.h"
 
-#ifndef ARRAY_SIZE
-# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0]))
-#endif
-
 #define MAX_INSNS	BPF_MAXINSNS
 #define MAX_FIXUPS	8
 #define MAX_NR_MAPS	8
-- 
cgit v1.2.3


From 3bd43a8c91cba0493e507ed7baefa9b5613c28a9 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:29 -0700
Subject: bpf: Sync bpf.h uapi to tools/

This patch sync include/uapi/linux/bpf.h to
tools/include/uapi/linux/

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 37 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 36 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index dd5758dc35d3..3102a2a23c31 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -126,6 +126,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_XSKMAP,
 	BPF_MAP_TYPE_SOCKHASH,
 	BPF_MAP_TYPE_CGROUP_STORAGE,
+	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 };
 
 enum bpf_prog_type {
@@ -150,6 +151,7 @@ enum bpf_prog_type {
 	BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 	BPF_PROG_TYPE_LWT_SEG6LOCAL,
 	BPF_PROG_TYPE_LIRC_MODE2,
+	BPF_PROG_TYPE_SK_REUSEPORT,
 };
 
 enum bpf_attach_type {
@@ -2113,6 +2115,14 @@ union bpf_attr {
  *		the shared data.
  *	Return
  *		Pointer to the local storage area.
+ *
+ * int bpf_sk_select_reuseport(struct sk_reuseport_md *reuse, struct bpf_map *map, void *key, u64 flags)
+ *	Description
+ *		Select a SO_REUSEPORT sk from a	BPF_MAP_TYPE_REUSEPORT_ARRAY map
+ *		It checks the selected sk is matching the incoming
+ *		request in the skb.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2196,7 +2206,8 @@ union bpf_attr {
 	FN(rc_keydown),			\
 	FN(skb_cgroup_id),		\
 	FN(get_current_cgroup_id),	\
-	FN(get_local_storage),
+	FN(get_local_storage),		\
+	FN(sk_select_reuseport),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -2413,6 +2424,30 @@ struct sk_msg_md {
 	__u32 local_port;	/* stored in host byte order */
 };
 
+struct sk_reuseport_md {
+	/*
+	 * Start of directly accessible data. It begins from
+	 * the tcp/udp header.
+	 */
+	void *data;
+	void *data_end;		/* End of directly accessible data */
+	/*
+	 * Total length of packet (starting from the tcp/udp header).
+	 * Note that the directly accessible bytes (data_end - data)
+	 * could be less than this "len".  Those bytes could be
+	 * indirectly read by a helper "bpf_skb_load_bytes()".
+	 */
+	__u32 len;
+	/*
+	 * Eth protocol in the mac header (network byte order). e.g.
+	 * ETH_P_IP(0x0800) and ETH_P_IPV6(0x86DD)
+	 */
+	__u32 eth_protocol;
+	__u32 ip_protocol;	/* IP protocol. e.g. IPPROTO_TCP, IPPROTO_UDP */
+	__u32 bind_inany;	/* Is sock bound to an INANY address? */
+	__u32 hash;		/* A hash of the packet 4 tuples */
+};
+
 #define BPF_TAG_SIZE	8
 
 struct bpf_prog_info {
-- 
cgit v1.2.3


From 6bc8529c414f931ce0acef3099b015cf2f5c4291 Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:30 -0700
Subject: bpf: test BPF_MAP_TYPE_REUSEPORT_SOCKARRAY

This patch adds tests for the new BPF_MAP_TYPE_REUSEPORT_SOCKARRAY.

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/libbpf.c                  |   1 +
 tools/testing/selftests/bpf/test_maps.c | 262 +++++++++++++++++++++++++++++++-
 2 files changed, 262 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 40211b51427a..2abd0f112627 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1501,6 +1501,7 @@ static bool bpf_prog_type__needs_kver(enum bpf_prog_type type)
 	case BPF_PROG_TYPE_SK_MSG:
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_LIRC_MODE2:
+	case BPF_PROG_TYPE_SK_REUSEPORT:
 		return false;
 	case BPF_PROG_TYPE_UNSPEC:
 	case BPF_PROG_TYPE_KPROBE:
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 6c253343a6f9..4b7c74f5faa7 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -17,7 +17,8 @@
 #include <stdlib.h>
 
 #include <sys/wait.h>
-
+#include <sys/socket.h>
+#include <netinet/in.h>
 #include <linux/bpf.h>
 
 #include <bpf/bpf.h>
@@ -26,8 +27,21 @@
 #include "bpf_util.h"
 #include "bpf_rlimit.h"
 
+#ifndef ENOTSUPP
+#define ENOTSUPP 524
+#endif
+
 static int map_flags;
 
+#define CHECK(condition, tag, format...) ({				\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);	\
+		printf(format);						\
+		exit(-1);						\
+	}								\
+})
+
 static void test_hashmap(int task, void *data)
 {
 	long long key, next_key, first_key, value;
@@ -1150,6 +1164,250 @@ static void test_map_wronly(void)
 	assert(bpf_map_get_next_key(fd, &key, &value) == -1 && errno == EPERM);
 }
 
+static void prepare_reuseport_grp(int type, int map_fd,
+				  __s64 *fds64, __u64 *sk_cookies,
+				  unsigned int n)
+{
+	socklen_t optlen, addrlen;
+	struct sockaddr_in6 s6;
+	const __u32 index0 = 0;
+	const int optval = 1;
+	unsigned int i;
+	u64 sk_cookie;
+	__s64 fd64;
+	int err;
+
+	s6.sin6_family = AF_INET6;
+	s6.sin6_addr = in6addr_any;
+	s6.sin6_port = 0;
+	addrlen = sizeof(s6);
+	optlen = sizeof(sk_cookie);
+
+	for (i = 0; i < n; i++) {
+		fd64 = socket(AF_INET6, type, 0);
+		CHECK(fd64 == -1, "socket()",
+		      "sock_type:%d fd64:%lld errno:%d\n",
+		      type, fd64, errno);
+
+		err = setsockopt(fd64, SOL_SOCKET, SO_REUSEPORT,
+				 &optval, sizeof(optval));
+		CHECK(err == -1, "setsockopt(SO_REUSEEPORT)",
+		      "err:%d errno:%d\n", err, errno);
+
+		/* reuseport_array does not allow unbound sk */
+		err = bpf_map_update_elem(map_fd, &index0, &fd64,
+					  BPF_ANY);
+		CHECK(err != -1 || errno != EINVAL,
+		      "reuseport array update unbound sk",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+
+		err = bind(fd64, (struct sockaddr *)&s6, sizeof(s6));
+		CHECK(err == -1, "bind()",
+		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+		if (i == 0) {
+			err = getsockname(fd64, (struct sockaddr *)&s6,
+					  &addrlen);
+			CHECK(err == -1, "getsockname()",
+			      "sock_type:%d err:%d errno:%d\n",
+			      type, err, errno);
+		}
+
+		err = getsockopt(fd64, SOL_SOCKET, SO_COOKIE, &sk_cookie,
+				 &optlen);
+		CHECK(err == -1, "getsockopt(SO_COOKIE)",
+		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+		if (type == SOCK_STREAM) {
+			/*
+			 * reuseport_array does not allow
+			 * non-listening tcp sk.
+			 */
+			err = bpf_map_update_elem(map_fd, &index0, &fd64,
+						  BPF_ANY);
+			CHECK(err != -1 || errno != EINVAL,
+			      "reuseport array update non-listening sk",
+			      "sock_type:%d err:%d errno:%d\n",
+			      type, err, errno);
+			err = listen(fd64, 0);
+			CHECK(err == -1, "listen()",
+			      "sock_type:%d, err:%d errno:%d\n",
+			      type, err, errno);
+		}
+
+		fds64[i] = fd64;
+		sk_cookies[i] = sk_cookie;
+	}
+}
+
+static void test_reuseport_array(void)
+{
+#define REUSEPORT_FD_IDX(err, last) ({ (err) ? last : !last; })
+
+	const __u32 array_size = 4, index0 = 0, index3 = 3;
+	int types[2] = { SOCK_STREAM, SOCK_DGRAM }, type;
+	__u64 grpa_cookies[2], sk_cookie, map_cookie;
+	__s64 grpa_fds64[2] = { -1, -1 }, fd64 = -1;
+	const __u32 bad_index = array_size;
+	int map_fd, err, t, f;
+	__u32 fds_idx = 0;
+	int fd;
+
+	map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+				sizeof(__u32), sizeof(__u64), array_size, 0);
+	CHECK(map_fd == -1, "reuseport array create",
+	      "map_fd:%d, errno:%d\n", map_fd, errno);
+
+	/* Test lookup/update/delete with invalid index */
+	err = bpf_map_delete_elem(map_fd, &bad_index);
+	CHECK(err != -1 || errno != E2BIG, "reuseport array del >=max_entries",
+	      "err:%d errno:%d\n", err, errno);
+
+	err = bpf_map_update_elem(map_fd, &bad_index, &fd64, BPF_ANY);
+	CHECK(err != -1 || errno != E2BIG,
+	      "reuseport array update >=max_entries",
+	      "err:%d errno:%d\n", err, errno);
+
+	err = bpf_map_lookup_elem(map_fd, &bad_index, &map_cookie);
+	CHECK(err != -1 || errno != ENOENT,
+	      "reuseport array update >=max_entries",
+	      "err:%d errno:%d\n", err, errno);
+
+	/* Test lookup/delete non existence elem */
+	err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+	CHECK(err != -1 || errno != ENOENT,
+	      "reuseport array lookup not-exist elem",
+	      "err:%d errno:%d\n", err, errno);
+	err = bpf_map_delete_elem(map_fd, &index3);
+	CHECK(err != -1 || errno != ENOENT,
+	      "reuseport array del not-exist elem",
+	      "err:%d errno:%d\n", err, errno);
+
+	for (t = 0; t < ARRAY_SIZE(types); t++) {
+		type = types[t];
+
+		prepare_reuseport_grp(type, map_fd, grpa_fds64,
+				      grpa_cookies, ARRAY_SIZE(grpa_fds64));
+
+		/* Test BPF_* update flags */
+		/* BPF_EXIST failure case */
+		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+					  BPF_EXIST);
+		CHECK(err != -1 || errno != ENOENT,
+		      "reuseport array update empty elem BPF_EXIST",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+		fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+		/* BPF_NOEXIST success case */
+		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+					  BPF_NOEXIST);
+		CHECK(err == -1,
+		      "reuseport array update empty elem BPF_NOEXIST",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+		fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+		/* BPF_EXIST success case. */
+		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+					  BPF_EXIST);
+		CHECK(err == -1,
+		      "reuseport array update same elem BPF_EXIST",
+		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+		fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+		/* BPF_NOEXIST failure case */
+		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+					  BPF_NOEXIST);
+		CHECK(err != -1 || errno != EEXIST,
+		      "reuseport array update non-empty elem BPF_NOEXIST",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+		fds_idx = REUSEPORT_FD_IDX(err, fds_idx);
+
+		/* BPF_ANY case (always succeed) */
+		err = bpf_map_update_elem(map_fd, &index3, &grpa_fds64[fds_idx],
+					  BPF_ANY);
+		CHECK(err == -1,
+		      "reuseport array update same sk with BPF_ANY",
+		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+		fd64 = grpa_fds64[fds_idx];
+		sk_cookie = grpa_cookies[fds_idx];
+
+		/* The same sk cannot be added to reuseport_array twice */
+		err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_ANY);
+		CHECK(err != -1 || errno != EBUSY,
+		      "reuseport array update same sk with same index",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+
+		err = bpf_map_update_elem(map_fd, &index0, &fd64, BPF_ANY);
+		CHECK(err != -1 || errno != EBUSY,
+		      "reuseport array update same sk with different index",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+
+		/* Test delete elem */
+		err = bpf_map_delete_elem(map_fd, &index3);
+		CHECK(err == -1, "reuseport array delete sk",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+
+		/* Add it back with BPF_NOEXIST */
+		err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST);
+		CHECK(err == -1,
+		      "reuseport array re-add with BPF_NOEXIST after del",
+		      "sock_type:%d err:%d errno:%d\n", type, err, errno);
+
+		/* Test cookie */
+		err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+		CHECK(err == -1 || sk_cookie != map_cookie,
+		      "reuseport array lookup re-added sk",
+		      "sock_type:%d err:%d errno:%d sk_cookie:0x%llx map_cookie:0x%llxn",
+		      type, err, errno, sk_cookie, map_cookie);
+
+		/* Test elem removed by close() */
+		for (f = 0; f < ARRAY_SIZE(grpa_fds64); f++)
+			close(grpa_fds64[f]);
+		err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+		CHECK(err != -1 || errno != ENOENT,
+		      "reuseport array lookup after close()",
+		      "sock_type:%d err:%d errno:%d\n",
+		      type, err, errno);
+	}
+
+	/* Test SOCK_RAW */
+	fd64 = socket(AF_INET6, SOCK_RAW, IPPROTO_UDP);
+	CHECK(fd64 == -1, "socket(SOCK_RAW)", "err:%d errno:%d\n",
+	      err, errno);
+	err = bpf_map_update_elem(map_fd, &index3, &fd64, BPF_NOEXIST);
+	CHECK(err != -1 || errno != ENOTSUPP, "reuseport array update SOCK_RAW",
+	      "err:%d errno:%d\n", err, errno);
+	close(fd64);
+
+	/* Close the 64 bit value map */
+	close(map_fd);
+
+	/* Test 32 bit fd */
+	map_fd = bpf_create_map(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
+				sizeof(__u32), sizeof(__u32), array_size, 0);
+	CHECK(map_fd == -1, "reuseport array create",
+	      "map_fd:%d, errno:%d\n", map_fd, errno);
+	prepare_reuseport_grp(SOCK_STREAM, map_fd, &fd64, &sk_cookie, 1);
+	fd = fd64;
+	err = bpf_map_update_elem(map_fd, &index3, &fd, BPF_NOEXIST);
+	CHECK(err == -1, "reuseport array update 32 bit fd",
+	      "err:%d errno:%d\n", err, errno);
+	err = bpf_map_lookup_elem(map_fd, &index3, &map_cookie);
+	CHECK(err != -1 || errno != ENOSPC,
+	      "reuseport array lookup 32 bit fd",
+	      "err:%d errno:%d\n", err, errno);
+	close(fd);
+	close(map_fd);
+}
+
 static void run_all_tests(void)
 {
 	test_hashmap(0, NULL);
@@ -1170,6 +1428,8 @@ static void run_all_tests(void)
 
 	test_map_rdonly();
 	test_map_wronly();
+
+	test_reuseport_array();
 }
 
 int main(void)
-- 
cgit v1.2.3


From 91134d849a0e8fbc70b8607d280e0d325dcaf7bb Mon Sep 17 00:00:00 2001
From: Martin KaFai Lau <kafai@fb.com>
Date: Wed, 8 Aug 2018 01:01:31 -0700
Subject: bpf: Test BPF_PROG_TYPE_SK_REUSEPORT

This patch add tests for the new BPF_PROG_TYPE_SK_REUSEPORT.

The tests cover:
- IPv4/IPv6 + TCP/UDP
- TCP syncookie
- TCP fastopen
- Cases when the bpf_sk_select_reuseport() returning errors
- Cases when the bpf prog returns SK_DROP
- Values from sk_reuseport_md
- outer_map => reuseport_array

The test depends on
commit 3eee1f75f2b9 ("bpf: fix bpf_skb_load_bytes_relative pkt length check")

Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/lib/bpf/bpf.c                                |   1 +
 tools/lib/bpf/bpf.h                                |   1 +
 tools/testing/selftests/bpf/Makefile               |   4 +-
 tools/testing/selftests/bpf/bpf_helpers.h          |   4 +
 .../testing/selftests/bpf/test_select_reuseport.c  | 688 +++++++++++++++++++++
 .../selftests/bpf/test_select_reuseport_common.h   |  36 ++
 .../selftests/bpf/test_select_reuseport_kern.c     | 180 ++++++
 7 files changed, 912 insertions(+), 2 deletions(-)
 create mode 100644 tools/testing/selftests/bpf/test_select_reuseport.c
 create mode 100644 tools/testing/selftests/bpf/test_select_reuseport_common.h
 create mode 100644 tools/testing/selftests/bpf/test_select_reuseport_kern.c

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9ddc89dae962..60aa4ca8b2c5 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -92,6 +92,7 @@ int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr)
 	attr.btf_key_type_id = create_attr->btf_key_type_id;
 	attr.btf_value_type_id = create_attr->btf_value_type_id;
 	attr.map_ifindex = create_attr->map_ifindex;
+	attr.inner_map_fd = create_attr->inner_map_fd;
 
 	return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr));
 }
diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h
index 0639a30a457d..6f38164b2618 100644
--- a/tools/lib/bpf/bpf.h
+++ b/tools/lib/bpf/bpf.h
@@ -39,6 +39,7 @@ struct bpf_create_map_attr {
 	__u32 btf_key_type_id;
 	__u32 btf_value_type_id;
 	__u32 map_ifindex;
+	__u32 inner_map_fd;
 };
 
 int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr);
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index 17a7a5818ee1..daed162043c2 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -23,7 +23,7 @@ $(TEST_CUSTOM_PROGS): $(OUTPUT)/%: %.c
 TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \
 	test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \
 	test_sock test_btf test_sockmap test_lirc_mode2_user get_cgroup_id_user \
-	test_socket_cookie test_cgroup_storage
+	test_socket_cookie test_cgroup_storage test_select_reuseport
 
 TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \
 	test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o     \
@@ -34,7 +34,7 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
-	get_cgroup_id_kern.o socket_cookie_prog.o
+	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 9ba1c72d7cf5..5c32266c2c38 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -111,6 +111,8 @@ static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
 static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
 				     int size, int flags) =
 	(void *) BPF_FUNC_skb_get_xfrm_state;
+static int (*bpf_sk_select_reuseport)(void *ctx, void *map, void *key, __u32 flags) =
+	(void *) BPF_FUNC_sk_select_reuseport;
 static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) =
 	(void *) BPF_FUNC_get_stack;
 static int (*bpf_fib_lookup)(void *ctx, struct bpf_fib_lookup *params,
@@ -173,6 +175,8 @@ struct bpf_map_def {
 
 static int (*bpf_skb_load_bytes)(void *ctx, int off, void *to, int len) =
 	(void *) BPF_FUNC_skb_load_bytes;
+static int (*bpf_skb_load_bytes_relative)(void *ctx, int off, void *to, int len, __u32 start_header) =
+	(void *) BPF_FUNC_skb_load_bytes_relative;
 static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
 	(void *) BPF_FUNC_skb_store_bytes;
 static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
diff --git a/tools/testing/selftests/bpf/test_select_reuseport.c b/tools/testing/selftests/bpf/test_select_reuseport.c
new file mode 100644
index 000000000000..75646d9b34aa
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_select_reuseport.c
@@ -0,0 +1,688 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <unistd.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <assert.h>
+#include <fcntl.h>
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+#include <sys/types.h>
+#include <sys/epoll.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+#include "bpf_rlimit.h"
+#include "bpf_util.h"
+#include "test_select_reuseport_common.h"
+
+#define MIN_TCPHDR_LEN 20
+#define UDPHDR_LEN 8
+
+#define TCP_SYNCOOKIE_SYSCTL "/proc/sys/net/ipv4/tcp_syncookies"
+#define TCP_FO_SYSCTL "/proc/sys/net/ipv4/tcp_fastopen"
+#define REUSEPORT_ARRAY_SIZE 32
+
+static int result_map, tmp_index_ovr_map, linum_map, data_check_map;
+static enum result expected_results[NR_RESULTS];
+static int sk_fds[REUSEPORT_ARRAY_SIZE];
+static int reuseport_array, outer_map;
+static int select_by_skb_data_prog;
+static int saved_tcp_syncookie;
+static struct bpf_object *obj;
+static int saved_tcp_fo;
+static __u32 index_zero;
+static int epfd;
+
+static union sa46 {
+	struct sockaddr_in6 v6;
+	struct sockaddr_in v4;
+	sa_family_t family;
+} srv_sa;
+
+#define CHECK(condition, tag, format...) ({				\
+	int __ret = !!(condition);					\
+	if (__ret) {							\
+		printf("%s(%d):FAIL:%s ", __func__, __LINE__, tag);	\
+		printf(format);						\
+		exit(-1);						\
+	}								\
+})
+
+static void create_maps(void)
+{
+	struct bpf_create_map_attr attr = {};
+
+	/* Creating reuseport_array */
+	attr.name = "reuseport_array";
+	attr.map_type = BPF_MAP_TYPE_REUSEPORT_SOCKARRAY;
+	attr.key_size = sizeof(__u32);
+	attr.value_size = sizeof(__u32);
+	attr.max_entries = REUSEPORT_ARRAY_SIZE;
+
+	reuseport_array = bpf_create_map_xattr(&attr);
+	CHECK(reuseport_array == -1, "creating reuseport_array",
+	      "reuseport_array:%d errno:%d\n", reuseport_array, errno);
+
+	/* Creating outer_map */
+	attr.name = "outer_map";
+	attr.map_type = BPF_MAP_TYPE_ARRAY_OF_MAPS;
+	attr.key_size = sizeof(__u32);
+	attr.value_size = sizeof(__u32);
+	attr.max_entries = 1;
+	attr.inner_map_fd = reuseport_array;
+	outer_map = bpf_create_map_xattr(&attr);
+	CHECK(outer_map == -1, "creating outer_map",
+	      "outer_map:%d errno:%d\n", outer_map, errno);
+}
+
+static void prepare_bpf_obj(void)
+{
+	struct bpf_program *prog;
+	struct bpf_map *map;
+	int err;
+	struct bpf_object_open_attr attr = {
+		.file = "test_select_reuseport_kern.o",
+		.prog_type = BPF_PROG_TYPE_SK_REUSEPORT,
+	};
+
+	obj = bpf_object__open_xattr(&attr);
+	CHECK(IS_ERR_OR_NULL(obj), "open test_select_reuseport_kern.o",
+	      "obj:%p PTR_ERR(obj):%ld\n", obj, PTR_ERR(obj));
+
+	prog = bpf_program__next(NULL, obj);
+	CHECK(!prog, "get first bpf_program", "!prog\n");
+	bpf_program__set_type(prog, attr.prog_type);
+
+	map = bpf_object__find_map_by_name(obj, "outer_map");
+	CHECK(!map, "find outer_map", "!map\n");
+	err = bpf_map__reuse_fd(map, outer_map);
+	CHECK(err, "reuse outer_map", "err:%d\n", err);
+
+	err = bpf_object__load(obj);
+	CHECK(err, "load bpf_object", "err:%d\n", err);
+
+	select_by_skb_data_prog = bpf_program__fd(prog);
+	CHECK(select_by_skb_data_prog == -1, "get prog fd",
+	      "select_by_skb_data_prog:%d\n", select_by_skb_data_prog);
+
+	map = bpf_object__find_map_by_name(obj, "result_map");
+	CHECK(!map, "find result_map", "!map\n");
+	result_map = bpf_map__fd(map);
+	CHECK(result_map == -1, "get result_map fd",
+	      "result_map:%d\n", result_map);
+
+	map = bpf_object__find_map_by_name(obj, "tmp_index_ovr_map");
+	CHECK(!map, "find tmp_index_ovr_map", "!map\n");
+	tmp_index_ovr_map = bpf_map__fd(map);
+	CHECK(tmp_index_ovr_map == -1, "get tmp_index_ovr_map fd",
+	      "tmp_index_ovr_map:%d\n", tmp_index_ovr_map);
+
+	map = bpf_object__find_map_by_name(obj, "linum_map");
+	CHECK(!map, "find linum_map", "!map\n");
+	linum_map = bpf_map__fd(map);
+	CHECK(linum_map == -1, "get linum_map fd",
+	      "linum_map:%d\n", linum_map);
+
+	map = bpf_object__find_map_by_name(obj, "data_check_map");
+	CHECK(!map, "find data_check_map", "!map\n");
+	data_check_map = bpf_map__fd(map);
+	CHECK(data_check_map == -1, "get data_check_map fd",
+	      "data_check_map:%d\n", data_check_map);
+}
+
+static void sa46_init_loopback(union sa46 *sa, sa_family_t family)
+{
+	memset(sa, 0, sizeof(*sa));
+	sa->family = family;
+	if (sa->family == AF_INET6)
+		sa->v6.sin6_addr = in6addr_loopback;
+	else
+		sa->v4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+}
+
+static void sa46_init_inany(union sa46 *sa, sa_family_t family)
+{
+	memset(sa, 0, sizeof(*sa));
+	sa->family = family;
+	if (sa->family == AF_INET6)
+		sa->v6.sin6_addr = in6addr_any;
+	else
+		sa->v4.sin_addr.s_addr = INADDR_ANY;
+}
+
+static int read_int_sysctl(const char *sysctl)
+{
+	char buf[16];
+	int fd, ret;
+
+	fd = open(sysctl, 0);
+	CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n",
+	      sysctl, fd, errno);
+
+	ret = read(fd, buf, sizeof(buf));
+	CHECK(ret <= 0, "read(sysctl)", "sysctl:%s ret:%d errno:%d\n",
+	      sysctl, ret, errno);
+	close(fd);
+
+	return atoi(buf);
+}
+
+static void write_int_sysctl(const char *sysctl, int v)
+{
+	int fd, ret, size;
+	char buf[16];
+
+	fd = open(sysctl, O_RDWR);
+	CHECK(fd == -1, "open(sysctl)", "sysctl:%s fd:%d errno:%d\n",
+	      sysctl, fd, errno);
+
+	size = snprintf(buf, sizeof(buf), "%d", v);
+	ret = write(fd, buf, size);
+	CHECK(ret != size, "write(sysctl)",
+	      "sysctl:%s ret:%d size:%d errno:%d\n", sysctl, ret, size, errno);
+	close(fd);
+}
+
+static void restore_sysctls(void)
+{
+	write_int_sysctl(TCP_FO_SYSCTL, saved_tcp_fo);
+	write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, saved_tcp_syncookie);
+}
+
+static void enable_fastopen(void)
+{
+	int fo;
+
+	fo = read_int_sysctl(TCP_FO_SYSCTL);
+	write_int_sysctl(TCP_FO_SYSCTL, fo | 7);
+}
+
+static void enable_syncookie(void)
+{
+	write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 2);
+}
+
+static void disable_syncookie(void)
+{
+	write_int_sysctl(TCP_SYNCOOKIE_SYSCTL, 0);
+}
+
+static __u32 get_linum(void)
+{
+	__u32 linum;
+	int err;
+
+	err = bpf_map_lookup_elem(linum_map, &index_zero, &linum);
+	CHECK(err == -1, "lookup_elem(linum_map)", "err:%d errno:%d\n",
+	      err, errno);
+
+	return linum;
+}
+
+static void check_data(int type, sa_family_t family, const struct cmd *cmd,
+		       int cli_fd)
+{
+	struct data_check expected = {}, result;
+	union sa46 cli_sa;
+	socklen_t addrlen;
+	int err;
+
+	addrlen = sizeof(cli_sa);
+	err = getsockname(cli_fd, (struct sockaddr *)&cli_sa,
+			  &addrlen);
+	CHECK(err == -1, "getsockname(cli_fd)", "err:%d errno:%d\n",
+	      err, errno);
+
+	err = bpf_map_lookup_elem(data_check_map, &index_zero, &result);
+	CHECK(err == -1, "lookup_elem(data_check_map)", "err:%d errno:%d\n",
+	      err, errno);
+
+	if (type == SOCK_STREAM) {
+		expected.len = MIN_TCPHDR_LEN;
+		expected.ip_protocol = IPPROTO_TCP;
+	} else {
+		expected.len = UDPHDR_LEN;
+		expected.ip_protocol = IPPROTO_UDP;
+	}
+
+	if (family == AF_INET6) {
+		expected.eth_protocol = htons(ETH_P_IPV6);
+		expected.bind_inany = !srv_sa.v6.sin6_addr.s6_addr32[3] &&
+			!srv_sa.v6.sin6_addr.s6_addr32[2] &&
+			!srv_sa.v6.sin6_addr.s6_addr32[1] &&
+			!srv_sa.v6.sin6_addr.s6_addr32[0];
+
+		memcpy(&expected.skb_addrs[0], cli_sa.v6.sin6_addr.s6_addr32,
+		       sizeof(cli_sa.v6.sin6_addr));
+		memcpy(&expected.skb_addrs[4], &in6addr_loopback,
+		       sizeof(in6addr_loopback));
+		expected.skb_ports[0] = cli_sa.v6.sin6_port;
+		expected.skb_ports[1] = srv_sa.v6.sin6_port;
+	} else {
+		expected.eth_protocol = htons(ETH_P_IP);
+		expected.bind_inany = !srv_sa.v4.sin_addr.s_addr;
+
+		expected.skb_addrs[0] = cli_sa.v4.sin_addr.s_addr;
+		expected.skb_addrs[1] = htonl(INADDR_LOOPBACK);
+		expected.skb_ports[0] = cli_sa.v4.sin_port;
+		expected.skb_ports[1] = srv_sa.v4.sin_port;
+	}
+
+	if (memcmp(&result, &expected, offsetof(struct data_check,
+						equal_check_end))) {
+		printf("unexpected data_check\n");
+		printf("  result: (0x%x, %u, %u)\n",
+		       result.eth_protocol, result.ip_protocol,
+		       result.bind_inany);
+		printf("expected: (0x%x, %u, %u)\n",
+		       expected.eth_protocol, expected.ip_protocol,
+		       expected.bind_inany);
+		CHECK(1, "data_check result != expected",
+		      "bpf_prog_linum:%u\n", get_linum());
+	}
+
+	CHECK(!result.hash, "data_check result.hash empty",
+	      "result.hash:%u", result.hash);
+
+	expected.len += cmd ? sizeof(*cmd) : 0;
+	if (type == SOCK_STREAM)
+		CHECK(expected.len > result.len, "expected.len > result.len",
+		      "expected.len:%u result.len:%u bpf_prog_linum:%u\n",
+		      expected.len, result.len, get_linum());
+	else
+		CHECK(expected.len != result.len, "expected.len != result.len",
+		      "expected.len:%u result.len:%u bpf_prog_linum:%u\n",
+		      expected.len, result.len, get_linum());
+}
+
+static void check_results(void)
+{
+	__u32 results[NR_RESULTS];
+	__u32 i, broken = 0;
+	int err;
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		err = bpf_map_lookup_elem(result_map, &i, &results[i]);
+		CHECK(err == -1, "lookup_elem(result_map)",
+		      "i:%u err:%d errno:%d\n", i, err, errno);
+	}
+
+	for (i = 0; i < NR_RESULTS; i++) {
+		if (results[i] != expected_results[i]) {
+			broken = i;
+			break;
+		}
+	}
+
+	if (i == NR_RESULTS)
+		return;
+
+	printf("unexpected result\n");
+	printf(" result: [");
+	printf("%u", results[0]);
+	for (i = 1; i < NR_RESULTS; i++)
+		printf(", %u", results[i]);
+	printf("]\n");
+
+	printf("expected: [");
+	printf("%u", expected_results[0]);
+	for (i = 1; i < NR_RESULTS; i++)
+		printf(", %u", expected_results[i]);
+	printf("]\n");
+
+	CHECK(expected_results[broken] != results[broken],
+	      "unexpected result",
+	      "expected_results[%u] != results[%u] bpf_prog_linum:%u\n",
+	      broken, broken, get_linum());
+}
+
+static int send_data(int type, sa_family_t family, void *data, size_t len,
+		     enum result expected)
+{
+	union sa46 cli_sa;
+	int fd, err;
+
+	fd = socket(family, type, 0);
+	CHECK(fd == -1, "socket()", "fd:%d errno:%d\n", fd, errno);
+
+	sa46_init_loopback(&cli_sa, family);
+	err = bind(fd, (struct sockaddr *)&cli_sa, sizeof(cli_sa));
+	CHECK(fd == -1, "bind(cli_sa)", "err:%d errno:%d\n", err, errno);
+
+	err = sendto(fd, data, len, MSG_FASTOPEN, (struct sockaddr *)&srv_sa,
+		     sizeof(srv_sa));
+	CHECK(err != len && expected >= PASS,
+	      "sendto()", "family:%u err:%d errno:%d expected:%d\n",
+	      family, err, errno, expected);
+
+	return fd;
+}
+
+static void do_test(int type, sa_family_t family, struct cmd *cmd,
+		    enum result expected)
+{
+	int nev, srv_fd, cli_fd;
+	struct epoll_event ev;
+	struct cmd rcv_cmd;
+	ssize_t nread;
+
+	cli_fd = send_data(type, family, cmd, cmd ? sizeof(*cmd) : 0,
+			   expected);
+	nev = epoll_wait(epfd, &ev, 1, expected >= PASS ? 5 : 0);
+	CHECK((nev <= 0 && expected >= PASS) ||
+	      (nev > 0 && expected < PASS),
+	      "nev <> expected",
+	      "nev:%d expected:%d type:%d family:%d data:(%d, %d)\n",
+	      nev, expected, type, family,
+	      cmd ? cmd->reuseport_index : -1,
+	      cmd ? cmd->pass_on_failure : -1);
+	check_results();
+	check_data(type, family, cmd, cli_fd);
+
+	if (expected < PASS)
+		return;
+
+	CHECK(expected != PASS_ERR_SK_SELECT_REUSEPORT &&
+	      cmd->reuseport_index != ev.data.u32,
+	      "check cmd->reuseport_index",
+	      "cmd:(%u, %u) ev.data.u32:%u\n",
+	      cmd->pass_on_failure, cmd->reuseport_index, ev.data.u32);
+
+	srv_fd = sk_fds[ev.data.u32];
+	if (type == SOCK_STREAM) {
+		int new_fd = accept(srv_fd, NULL, 0);
+
+		CHECK(new_fd == -1, "accept(srv_fd)",
+		      "ev.data.u32:%u new_fd:%d errno:%d\n",
+		      ev.data.u32, new_fd, errno);
+
+		nread = recv(new_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
+		CHECK(nread != sizeof(rcv_cmd),
+		      "recv(new_fd)",
+		      "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
+		      ev.data.u32, nread, sizeof(rcv_cmd), errno);
+
+		close(new_fd);
+	} else {
+		nread = recv(srv_fd, &rcv_cmd, sizeof(rcv_cmd), MSG_DONTWAIT);
+		CHECK(nread != sizeof(rcv_cmd),
+		      "recv(sk_fds)",
+		      "ev.data.u32:%u nread:%zd sizeof(rcv_cmd):%zu errno:%d\n",
+		      ev.data.u32, nread, sizeof(rcv_cmd), errno);
+	}
+
+	close(cli_fd);
+}
+
+static void test_err_inner_map(int type, sa_family_t family)
+{
+	struct cmd cmd = {
+		.reuseport_index = 0,
+		.pass_on_failure = 0,
+	};
+
+	printf("%s: ", __func__);
+	expected_results[DROP_ERR_INNER_MAP]++;
+	do_test(type, family, &cmd, DROP_ERR_INNER_MAP);
+	printf("OK\n");
+}
+
+static void test_err_skb_data(int type, sa_family_t family)
+{
+	printf("%s: ", __func__);
+	expected_results[DROP_ERR_SKB_DATA]++;
+	do_test(type, family, NULL, DROP_ERR_SKB_DATA);
+	printf("OK\n");
+}
+
+static void test_err_sk_select_port(int type, sa_family_t family)
+{
+	struct cmd cmd = {
+		.reuseport_index = REUSEPORT_ARRAY_SIZE,
+		.pass_on_failure = 0,
+	};
+
+	printf("%s: ", __func__);
+	expected_results[DROP_ERR_SK_SELECT_REUSEPORT]++;
+	do_test(type, family, &cmd, DROP_ERR_SK_SELECT_REUSEPORT);
+	printf("OK\n");
+}
+
+static void test_pass(int type, sa_family_t family)
+{
+	struct cmd cmd;
+	int i;
+
+	printf("%s: ", __func__);
+	cmd.pass_on_failure = 0;
+	for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
+		expected_results[PASS]++;
+		cmd.reuseport_index = i;
+		do_test(type, family, &cmd, PASS);
+	}
+	printf("OK\n");
+}
+
+static void test_syncookie(int type, sa_family_t family)
+{
+	int err, tmp_index = 1;
+	struct cmd cmd = {
+		.reuseport_index = 0,
+		.pass_on_failure = 0,
+	};
+
+	if (type != SOCK_STREAM)
+		return;
+
+	printf("%s: ", __func__);
+	/*
+	 * +1 for TCP-SYN and
+	 * +1 for the TCP-ACK (ack the syncookie)
+	 */
+	expected_results[PASS] += 2;
+	enable_syncookie();
+	/*
+	 * Simulate TCP-SYN and TCP-ACK are handled by two different sk:
+	 * TCP-SYN: select sk_fds[tmp_index = 1] tmp_index is from the
+	 *          tmp_index_ovr_map
+	 * TCP-ACK: select sk_fds[reuseport_index = 0] reuseport_index
+	 *          is from the cmd.reuseport_index
+	 */
+	err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero,
+				  &tmp_index, BPF_ANY);
+	CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, 1)",
+	      "err:%d errno:%d\n", err, errno);
+	do_test(type, family, &cmd, PASS);
+	err = bpf_map_lookup_elem(tmp_index_ovr_map, &index_zero,
+				  &tmp_index);
+	CHECK(err == -1 || tmp_index != -1,
+	      "lookup_elem(tmp_index_ovr_map)",
+	      "err:%d errno:%d tmp_index:%d\n",
+	      err, errno, tmp_index);
+	disable_syncookie();
+	printf("OK\n");
+}
+
+static void test_pass_on_err(int type, sa_family_t family)
+{
+	struct cmd cmd = {
+		.reuseport_index = REUSEPORT_ARRAY_SIZE,
+		.pass_on_failure = 1,
+	};
+
+	printf("%s: ", __func__);
+	expected_results[PASS_ERR_SK_SELECT_REUSEPORT] += 1;
+	do_test(type, family, &cmd, PASS_ERR_SK_SELECT_REUSEPORT);
+	printf("OK\n");
+}
+
+static void prepare_sk_fds(int type, sa_family_t family, bool inany)
+{
+	const int first = REUSEPORT_ARRAY_SIZE - 1;
+	int i, err, optval = 1;
+	struct epoll_event ev;
+	socklen_t addrlen;
+
+	if (inany)
+		sa46_init_inany(&srv_sa, family);
+	else
+		sa46_init_loopback(&srv_sa, family);
+	addrlen = sizeof(srv_sa);
+
+	/*
+	 * The sk_fds[] is filled from the back such that the order
+	 * is exactly opposite to the (struct sock_reuseport *)reuse->socks[].
+	 */
+	for (i = first; i >= 0; i--) {
+		sk_fds[i] = socket(family, type, 0);
+		CHECK(sk_fds[i] == -1, "socket()", "sk_fds[%d]:%d errno:%d\n",
+		      i, sk_fds[i], errno);
+		err = setsockopt(sk_fds[i], SOL_SOCKET, SO_REUSEPORT,
+				 &optval, sizeof(optval));
+		CHECK(err == -1, "setsockopt(SO_REUSEPORT)",
+		      "sk_fds[%d] err:%d errno:%d\n",
+		      i, err, errno);
+
+		if (i == first) {
+			err = setsockopt(sk_fds[i], SOL_SOCKET,
+					 SO_ATTACH_REUSEPORT_EBPF,
+					 &select_by_skb_data_prog,
+					 sizeof(select_by_skb_data_prog));
+			CHECK(err == -1, "setsockopt(SO_ATTACH_REUEPORT_EBPF)",
+			      "err:%d errno:%d\n", err, errno);
+		}
+
+		err = bind(sk_fds[i], (struct sockaddr *)&srv_sa, addrlen);
+		CHECK(err == -1, "bind()", "sk_fds[%d] err:%d errno:%d\n",
+		      i, err, errno);
+
+		if (type == SOCK_STREAM) {
+			err = listen(sk_fds[i], 10);
+			CHECK(err == -1, "listen()",
+			      "sk_fds[%d] err:%d errno:%d\n",
+			      i, err, errno);
+		}
+
+		err = bpf_map_update_elem(reuseport_array, &i, &sk_fds[i],
+					  BPF_NOEXIST);
+		CHECK(err == -1, "update_elem(reuseport_array)",
+		      "sk_fds[%d] err:%d errno:%d\n", i, err, errno);
+
+		if (i == first) {
+			socklen_t addrlen = sizeof(srv_sa);
+
+			err = getsockname(sk_fds[i], (struct sockaddr *)&srv_sa,
+					  &addrlen);
+			CHECK(err == -1, "getsockname()",
+			      "sk_fds[%d] err:%d errno:%d\n", i, err, errno);
+		}
+	}
+
+	epfd = epoll_create(1);
+	CHECK(epfd == -1, "epoll_create(1)",
+	      "epfd:%d errno:%d\n", epfd, errno);
+
+	ev.events = EPOLLIN;
+	for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++) {
+		ev.data.u32 = i;
+		err = epoll_ctl(epfd, EPOLL_CTL_ADD, sk_fds[i], &ev);
+		CHECK(err, "epoll_ctl(EPOLL_CTL_ADD)", "sk_fds[%d]\n", i);
+	}
+}
+
+static void setup_per_test(int type, unsigned short family, bool inany)
+{
+	int ovr = -1, err;
+
+	prepare_sk_fds(type, family, inany);
+	err = bpf_map_update_elem(tmp_index_ovr_map, &index_zero, &ovr,
+				  BPF_ANY);
+	CHECK(err == -1, "update_elem(tmp_index_ovr_map, 0, -1)",
+	      "err:%d errno:%d\n", err, errno);
+}
+
+static void cleanup_per_test(void)
+{
+	int i, err;
+
+	for (i = 0; i < REUSEPORT_ARRAY_SIZE; i++)
+		close(sk_fds[i]);
+	close(epfd);
+
+	err = bpf_map_delete_elem(outer_map, &index_zero);
+	CHECK(err == -1, "delete_elem(outer_map)",
+	      "err:%d errno:%d\n", err, errno);
+}
+
+static void cleanup(void)
+{
+	close(outer_map);
+	close(reuseport_array);
+	bpf_object__close(obj);
+}
+
+static void test_all(void)
+{
+	/* Extra SOCK_STREAM to test bind_inany==true */
+	const int types[] = { SOCK_STREAM, SOCK_DGRAM, SOCK_STREAM };
+	const char * const type_strings[] = { "TCP", "UDP", "TCP" };
+	const char * const family_strings[] = { "IPv6", "IPv4" };
+	const unsigned short families[] = { AF_INET6, AF_INET };
+	const bool bind_inany[] = { false, false, true };
+	int t, f, err;
+
+	for (f = 0; f < ARRAY_SIZE(families); f++) {
+		unsigned short family = families[f];
+
+		for (t = 0; t < ARRAY_SIZE(types); t++) {
+			bool inany = bind_inany[t];
+			int type = types[t];
+
+			printf("######## %s/%s %s ########\n",
+			       family_strings[f], type_strings[t],
+				inany ? " INANY  " : "LOOPBACK");
+
+			setup_per_test(type, family, inany);
+
+			test_err_inner_map(type, family);
+
+			/* Install reuseport_array to the outer_map */
+			err = bpf_map_update_elem(outer_map, &index_zero,
+						  &reuseport_array, BPF_ANY);
+			CHECK(err == -1, "update_elem(outer_map)",
+			      "err:%d errno:%d\n", err, errno);
+
+			test_err_skb_data(type, family);
+			test_err_sk_select_port(type, family);
+			test_pass(type, family);
+			test_syncookie(type, family);
+			test_pass_on_err(type, family);
+
+			cleanup_per_test();
+			printf("\n");
+		}
+	}
+}
+
+int main(int argc, const char **argv)
+{
+	create_maps();
+	prepare_bpf_obj();
+	saved_tcp_fo = read_int_sysctl(TCP_FO_SYSCTL);
+	saved_tcp_syncookie = read_int_sysctl(TCP_SYNCOOKIE_SYSCTL);
+	enable_fastopen();
+	disable_syncookie();
+	atexit(restore_sysctls);
+
+	test_all();
+
+	cleanup();
+	return 0;
+}
diff --git a/tools/testing/selftests/bpf/test_select_reuseport_common.h b/tools/testing/selftests/bpf/test_select_reuseport_common.h
new file mode 100644
index 000000000000..08eb2a9f145f
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_select_reuseport_common.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Facebook */
+
+#ifndef __TEST_SELECT_REUSEPORT_COMMON_H
+#define __TEST_SELECT_REUSEPORT_COMMON_H
+
+#include <linux/types.h>
+
+enum result {
+	DROP_ERR_INNER_MAP,
+	DROP_ERR_SKB_DATA,
+	DROP_ERR_SK_SELECT_REUSEPORT,
+	DROP_MISC,
+	PASS,
+	PASS_ERR_SK_SELECT_REUSEPORT,
+	NR_RESULTS,
+};
+
+struct cmd {
+	__u32 reuseport_index;
+	__u32 pass_on_failure;
+};
+
+struct data_check {
+	__u32 ip_protocol;
+	__u32 skb_addrs[8];
+	__u16 skb_ports[2];
+	__u16 eth_protocol;
+	__u8  bind_inany;
+	__u8  equal_check_end[0];
+
+	__u32 len;
+	__u32 hash;
+};
+
+#endif
diff --git a/tools/testing/selftests/bpf/test_select_reuseport_kern.c b/tools/testing/selftests/bpf/test_select_reuseport_kern.c
new file mode 100644
index 000000000000..5b54ec637ada
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_select_reuseport_kern.c
@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/bpf.h>
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#include "bpf_endian.h"
+#include "bpf_helpers.h"
+#include "test_select_reuseport_common.h"
+
+int _version SEC("version") = 1;
+
+#ifndef offsetof
+#define offsetof(TYPE, MEMBER) ((size_t) &((TYPE *)0)->MEMBER)
+#endif
+
+struct bpf_map_def SEC("maps") outer_map = {
+	.type = BPF_MAP_TYPE_ARRAY_OF_MAPS,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") result_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = NR_RESULTS,
+};
+
+struct bpf_map_def SEC("maps") tmp_index_ovr_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(int),
+	.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") linum_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u32),
+	.max_entries = 1,
+};
+
+struct bpf_map_def SEC("maps") data_check_map = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(struct data_check),
+	.max_entries = 1,
+};
+
+#define GOTO_DONE(_result) ({			\
+	result = (_result);			\
+	linum = __LINE__;			\
+	goto done;				\
+})
+
+SEC("select_by_skb_data")
+int _select_by_skb_data(struct sk_reuseport_md *reuse_md)
+{
+	__u32 linum, index = 0, flags = 0, index_zero = 0;
+	__u32 *result_cnt, *linum_value;
+	struct data_check data_check = {};
+	struct cmd *cmd, cmd_copy;
+	void *data, *data_end;
+	void *reuseport_array;
+	enum result result;
+	int *index_ovr;
+	int err;
+
+	data = reuse_md->data;
+	data_end = reuse_md->data_end;
+	data_check.len = reuse_md->len;
+	data_check.eth_protocol = reuse_md->eth_protocol;
+	data_check.ip_protocol = reuse_md->ip_protocol;
+	data_check.hash = reuse_md->hash;
+	data_check.bind_inany = reuse_md->bind_inany;
+	if (data_check.eth_protocol == bpf_htons(ETH_P_IP)) {
+		if (bpf_skb_load_bytes_relative(reuse_md,
+						offsetof(struct iphdr, saddr),
+						data_check.skb_addrs, 8,
+						BPF_HDR_START_NET))
+			GOTO_DONE(DROP_MISC);
+	} else {
+		if (bpf_skb_load_bytes_relative(reuse_md,
+						offsetof(struct ipv6hdr, saddr),
+						data_check.skb_addrs, 32,
+						BPF_HDR_START_NET))
+			GOTO_DONE(DROP_MISC);
+	}
+
+	/*
+	 * The ip_protocol could be a compile time decision
+	 * if the bpf_prog.o is dedicated to either TCP or
+	 * UDP.
+	 *
+	 * Otherwise, reuse_md->ip_protocol or
+	 * the protocol field in the iphdr can be used.
+	 */
+	if (data_check.ip_protocol == IPPROTO_TCP) {
+		struct tcphdr *th = data;
+
+		if (th + 1 > data_end)
+			GOTO_DONE(DROP_MISC);
+
+		data_check.skb_ports[0] = th->source;
+		data_check.skb_ports[1] = th->dest;
+
+		if ((th->doff << 2) + sizeof(*cmd) > data_check.len)
+			GOTO_DONE(DROP_ERR_SKB_DATA);
+		if (bpf_skb_load_bytes(reuse_md, th->doff << 2, &cmd_copy,
+				       sizeof(cmd_copy)))
+			GOTO_DONE(DROP_MISC);
+		cmd = &cmd_copy;
+	} else if (data_check.ip_protocol == IPPROTO_UDP) {
+		struct udphdr *uh = data;
+
+		if (uh + 1 > data_end)
+			GOTO_DONE(DROP_MISC);
+
+		data_check.skb_ports[0] = uh->source;
+		data_check.skb_ports[1] = uh->dest;
+
+		if (sizeof(struct udphdr) + sizeof(*cmd) > data_check.len)
+			GOTO_DONE(DROP_ERR_SKB_DATA);
+		if (data + sizeof(struct udphdr) + sizeof(*cmd) > data_end) {
+			if (bpf_skb_load_bytes(reuse_md, sizeof(struct udphdr),
+					       &cmd_copy, sizeof(cmd_copy)))
+				GOTO_DONE(DROP_MISC);
+			cmd = &cmd_copy;
+		} else {
+			cmd = data + sizeof(struct udphdr);
+		}
+	} else {
+		GOTO_DONE(DROP_MISC);
+	}
+
+	reuseport_array = bpf_map_lookup_elem(&outer_map, &index_zero);
+	if (!reuseport_array)
+		GOTO_DONE(DROP_ERR_INNER_MAP);
+
+	index = cmd->reuseport_index;
+	index_ovr = bpf_map_lookup_elem(&tmp_index_ovr_map, &index_zero);
+	if (!index_ovr)
+		GOTO_DONE(DROP_MISC);
+
+	if (*index_ovr != -1) {
+		index = *index_ovr;
+		*index_ovr = -1;
+	}
+	err = bpf_sk_select_reuseport(reuse_md, reuseport_array, &index,
+				      flags);
+	if (!err)
+		GOTO_DONE(PASS);
+
+	if (cmd->pass_on_failure)
+		GOTO_DONE(PASS_ERR_SK_SELECT_REUSEPORT);
+	else
+		GOTO_DONE(DROP_ERR_SK_SELECT_REUSEPORT);
+
+done:
+	result_cnt = bpf_map_lookup_elem(&result_map, &result);
+	if (!result_cnt)
+		return SK_DROP;
+
+	bpf_map_update_elem(&linum_map, &index_zero, &linum, BPF_ANY);
+	bpf_map_update_elem(&data_check_map, &index_zero, &data_check, BPF_ANY);
+
+	(*result_cnt)++;
+	return result < PASS ? SK_DROP : SK_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
-- 
cgit v1.2.3


From 8605212a7c37b5d786544263bae5e697c1aaaa16 Mon Sep 17 00:00:00 2001
From: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Date: Fri, 10 Aug 2018 18:24:43 -0400
Subject: bnxt_en: Fix strcpy() warnings in bnxt_ethtool.c

This patch fixes following smatch warnings:

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2826 bnxt_fill_coredump_seg_hdr() error: strcpy() '"sEgM"' too large for 'seg_hdr->signature' (5 vs 4)
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2858 bnxt_fill_coredump_record() error: strcpy() '"cOrE"' too large for 'record->signature' (5 vs 4)
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2879 bnxt_fill_coredump_record() error: strcpy() 'utsname()->sysname' too large for 'record->os_name' (65 vs 32)

Fixes: 6c5657d085ae ("bnxt_en: Add support for ethtool get dump.")
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Vasundhara Volam <vasundhara-v.volam@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index b6dbc3f6d309..9c929cd90b86 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2823,7 +2823,7 @@ bnxt_fill_coredump_seg_hdr(struct bnxt *bp,
 			   int status, u32 duration, u32 instance)
 {
 	memset(seg_hdr, 0, sizeof(*seg_hdr));
-	strcpy(seg_hdr->signature, "sEgM");
+	memcpy(seg_hdr->signature, "sEgM", 4);
 	if (seg_rec) {
 		seg_hdr->component_id = (__force __le32)seg_rec->component_id;
 		seg_hdr->segment_id = (__force __le32)seg_rec->segment_id;
@@ -2855,7 +2855,7 @@ bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record,
 
 	time64_to_tm(start, 0, &tm);
 	memset(record, 0, sizeof(*record));
-	strcpy(record->signature, "cOrE");
+	memcpy(record->signature, "cOrE", 4);
 	record->flags = 0;
 	record->low_version = 0;
 	record->high_version = 1;
@@ -2876,7 +2876,7 @@ bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record,
 	record->os_ver_major = cpu_to_le32(os_ver_major);
 	record->os_ver_minor = cpu_to_le32(os_ver_minor);
 
-	strcpy(record->os_name, utsname()->sysname);
+	strlcpy(record->os_name, utsname()->sysname, 32);
 	time64_to_tm(end, 0, &tm);
 	record->end_year = cpu_to_le16(tm.tm_year + 1900);
 	record->end_month = cpu_to_le16(tm.tm_mon + 1);
-- 
cgit v1.2.3


From 9805d4bcf8f98dbeb1a66c3195f2ea8b917a083e Mon Sep 17 00:00:00 2001
From: Boris Brezillon <boris.brezillon@bootlin.com>
Date: Sat, 11 Aug 2018 15:47:12 +0200
Subject: mtd: rawnand: atmel: Select GENERIC_ALLOCATOR

The driver uses genalloc functions. Select GENERIC_ALLOCATOR to prevent
build errors when selected through COMPILE_TEST.

Fixes: 88a40e7dca00 ("mtd: rawnand: atmel: Allow selection of this driver when COMPILE_TEST=y")
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
---
 drivers/mtd/nand/raw/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
index b6738ece16f1..5fc9a1bde4ac 100644
--- a/drivers/mtd/nand/raw/Kconfig
+++ b/drivers/mtd/nand/raw/Kconfig
@@ -279,6 +279,7 @@ config MTD_NAND_ATMEL
 	tristate "Support for NAND Flash / SmartMedia on AT91"
 	depends on ARCH_AT91 || COMPILE_TEST
 	depends on HAS_IOMEM
+	select GENERIC_ALLOCATOR
 	select MFD_ATMEL_SMC
 	help
 	  Enables support for NAND Flash / Smart Media Card interface
-- 
cgit v1.2.3


From f741917e24e9de4cf5abe041ff1b4f28f9522387 Mon Sep 17 00:00:00 2001
From: zhong jiang <zhongjiang@huawei.com>
Date: Thu, 9 Aug 2018 09:39:13 +0800
Subject: drivers/net/usb/r8152: remove the unneeded variable "ret" in
 rtl8152_system_suspend

rtl8152_system_suspend defines the variable "ret", but it is not modified
after initialization. So just remove it.

Signed-off-by: zhong jiang <zhongjiang@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/usb/r8152.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 124211afb023..97742708460b 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -4415,7 +4415,6 @@ out1:
 static int rtl8152_system_suspend(struct r8152 *tp)
 {
 	struct net_device *netdev = tp->netdev;
-	int ret = 0;
 
 	netif_device_detach(netdev);
 
@@ -4430,7 +4429,7 @@ static int rtl8152_system_suspend(struct r8152 *tp)
 		napi_enable(napi);
 	}
 
-	return ret;
+	return 0;
 }
 
 static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
-- 
cgit v1.2.3


From 98ed1e642c451b3ed9f4c5785b291a3fc9e82166 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Thu, 9 Aug 2018 12:00:49 +0100
Subject: rxrpc: remove redundant static int 'zero'

The static int 'zero' is defined but is never used hence it is
redundant and can be removed. The use of this variable was removed
with commit a158bdd3247b ("rxrpc: Fix call timeouts").

Cleans up clang warning:
warning: 'zero' defined but not used [-Wunused-const-variable=]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rxrpc/sysctl.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c
index 4a7af7aff37d..d75bd15151e6 100644
--- a/net/rxrpc/sysctl.c
+++ b/net/rxrpc/sysctl.c
@@ -15,7 +15,6 @@
 #include "ar-internal.h"
 
 static struct ctl_table_header *rxrpc_sysctl_reg_table;
-static const unsigned int zero = 0;
 static const unsigned int one = 1;
 static const unsigned int four = 4;
 static const unsigned int thirtytwo = 32;
-- 
cgit v1.2.3


From d331e7589753f02f93db350910e4bcbbecf6f726 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 9 Aug 2018 10:08:24 -0500
Subject: net: dp83640: Mark expected switch fall-throughs

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I replaced the code comment at the
top of the switch statement with a proper "fall through" annotation for
each case, which is what GCC is expecting to find.

Addresses-Coverity-ID: 1056542 ("Missing break in switch")
Addresses-Coverity-ID: 1339579 ("Missing break in switch")
Addresses-Coverity-ID: 1369526 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/dp83640.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83640.c b/drivers/net/phy/dp83640.c
index 79e9b103188b..29aa8d772b0c 100644
--- a/drivers/net/phy/dp83640.c
+++ b/drivers/net/phy/dp83640.c
@@ -757,13 +757,16 @@ static int decode_evnt(struct dp83640_private *dp83640,
 
 	phy_txts = data;
 
-	switch (words) { /* fall through in every case */
+	switch (words) {
 	case 3:
 		dp83640->edata.sec_hi = phy_txts->sec_hi;
+		/* fall through */
 	case 2:
 		dp83640->edata.sec_lo = phy_txts->sec_lo;
+		/* fall through */
 	case 1:
 		dp83640->edata.ns_hi = phy_txts->ns_hi;
+		/* fall through */
 	case 0:
 		dp83640->edata.ns_lo = phy_txts->ns_lo;
 	}
-- 
cgit v1.2.3


From 849063074a84fe388a15f5655bc26fdf3290a2ac Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 9 Aug 2018 10:39:44 -0500
Subject: wimax: usb-fw: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I placed the "fall through"
annotation at the bottom of the case, which is what GCC is expecting
to find.

Addresses-Coverity-ID: 1369529 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wimax/i2400m/usb-fw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wimax/i2400m/usb-fw.c b/drivers/net/wimax/i2400m/usb-fw.c
index 502c346aa790..529ebca1e9e1 100644
--- a/drivers/net/wimax/i2400m/usb-fw.c
+++ b/drivers/net/wimax/i2400m/usb-fw.c
@@ -130,12 +130,12 @@ retry:
 			dev_err(dev, "BM-CMD: too many stalls in "
 				"URB; resetting device\n");
 			usb_queue_reset_device(i2400mu->usb_iface);
-			/* fallthrough */
 		} else {
 			usb_clear_halt(i2400mu->usb_dev, pipe);
 			msleep(10);	/* give the device some time */
 			goto retry;
 		}
+		/* fall through */
 	case -EINVAL:			/* while removing driver */
 	case -ENODEV:			/* dev disconnect ... */
 	case -ENOENT:			/* just ignore it */
-- 
cgit v1.2.3


From 8a8a894ebbc23f52669b80c2ca5bf62d75267324 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Thu, 9 Aug 2018 10:47:20 -0500
Subject: wimax: usb-tx: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Notice that in this particular case, I placed the "fall through"
annotation at the bottom of the case, which is what GCC is expecting
to find.

Addresses-Coverity-ID: 115075 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/wimax/i2400m/usb-tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wimax/i2400m/usb-tx.c b/drivers/net/wimax/i2400m/usb-tx.c
index 99ef81b3d5a5..3a0e7226768a 100644
--- a/drivers/net/wimax/i2400m/usb-tx.c
+++ b/drivers/net/wimax/i2400m/usb-tx.c
@@ -131,12 +131,12 @@ retry:
 			dev_err(dev, "BM-CMD: too many stalls in "
 				"URB; resetting device\n");
 			usb_queue_reset_device(i2400mu->usb_iface);
-			/* fallthrough */
 		} else {
 			usb_clear_halt(i2400mu->usb_dev, usb_pipe);
 			msleep(10);	/* give the device some time */
 			goto retry;
 		}
+		/* fall through */
 	case -EINVAL:			/* while removing driver */
 	case -ENODEV:			/* dev disconnect ... */
 	case -ENOENT:			/* just ignore it */
-- 
cgit v1.2.3


From 466466dc6c28ca9dc401f10e235b9cde9a7c9162 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 9 Aug 2018 09:38:09 -0700
Subject: tcp: mandate a one-time immediate ACK

Add a new flag to indicate a one-time immediate ACK. This flag is
occasionaly set under specific TCP protocol states in addition to
the more common quickack mechanism for interactive application.

In several cases in the TCP code we want to force an immediate ACK
but do not want to call tcp_enter_quickack_mode() because we do
not want to forget the icsk_ack.pingpong or icsk_ack.ato state.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h | 3 ++-
 net/ipv4/tcp_input.c               | 4 +++-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 0a6c9e0f2b5a..fa43b82607d9 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -167,7 +167,8 @@ enum inet_csk_ack_state_t {
 	ICSK_ACK_SCHED	= 1,
 	ICSK_ACK_TIMER  = 2,
 	ICSK_ACK_PUSHED = 4,
-	ICSK_ACK_PUSHED2 = 8
+	ICSK_ACK_PUSHED2 = 8,
+	ICSK_ACK_NOW = 16	/* Send the next ACK immediately (once) */
 };
 
 void inet_csk_init_xmit_timers(struct sock *sk,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 715d541b52dd..b8849588c440 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5179,7 +5179,9 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible)
 	    (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat ||
 	     __tcp_select_window(sk) >= tp->rcv_wnd)) ||
 	    /* We ACK each frame or... */
-	    tcp_in_quickack_mode(sk)) {
+	    tcp_in_quickack_mode(sk) ||
+	    /* Protocol state mandates a one-time immediate ACK */
+	    inet_csk(sk)->icsk_ack.pending & ICSK_ACK_NOW) {
 send_now:
 		tcp_send_ack(sk);
 		return;
-- 
cgit v1.2.3


From d2ccd7bc8acdcb9166c07a0255fb85bf877edb1f Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 9 Aug 2018 09:38:10 -0700
Subject: tcp: avoid resetting ACK timer in DCTCP

The recent fix of acking immediately in DCTCP on CE status change
has an undesirable side-effect: it also resets TCP ack timer and
disables pingpong mode (interactive session). But the CE status
change has nothing to do with them. This patch addresses that by
using the new one-time immediate ACK flag instead of calling
tcp_enter_quickack_mode().

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_dctcp.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 8b637f9f23a2..ca61e2a659e7 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -136,7 +136,7 @@ static void dctcp_ce_state_0_to_1(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk, 1);
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
@@ -157,7 +157,7 @@ static void dctcp_ce_state_1_to_0(struct sock *sk)
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER)
 			__tcp_send_ack(sk, ca->prior_rcv_nxt);
-		tcp_enter_quickack_mode(sk, 1);
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 
 	ca->prior_rcv_nxt = tp->rcv_nxt;
-- 
cgit v1.2.3


From 15bdd5686c2c61373680b9015e95abf31778e4fd Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 9 Aug 2018 09:38:11 -0700
Subject: tcp: always ACK immediately on hole repairs

RFC 5681 sec 4.2:
  To provide feedback to senders recovering from losses, the receiver
  SHOULD send an immediate ACK when it receives a data segment that
  fills in all or part of a gap in the sequence space.

When a gap is partially filled, __tcp_ack_snd_check already checks
the out-of-order queue and correctly send an immediate ACK. However
when a gap is fully filled, the previous implementation only resets
pingpong mode which does not guarantee an immediate ACK because the
quick ACK counter may be zero. This patch addresses this issue by
marking the one-time immediate ACK flag instead.

Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b8849588c440..9a09ff3afef2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4735,11 +4735,11 @@ queue_and_out:
 		if (!RB_EMPTY_ROOT(&tp->out_of_order_queue)) {
 			tcp_ofo_queue(sk);
 
-			/* RFC2581. 4.2. SHOULD send immediate ACK, when
+			/* RFC5681. 4.2. SHOULD send immediate ACK, when
 			 * gap in queue is filled.
 			 */
 			if (RB_EMPTY_ROOT(&tp->out_of_order_queue))
-				inet_csk(sk)->icsk_ack.pingpong = 0;
+				inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 		}
 
 		if (tp->rx_opt.num_sacks)
-- 
cgit v1.2.3


From fd2123a3d7527d4c7092633d55e877c0cc1d84a3 Mon Sep 17 00:00:00 2001
From: Yuchung Cheng <ycheng@google.com>
Date: Thu, 9 Aug 2018 09:38:12 -0700
Subject: tcp: avoid resetting ACK timer upon receiving packet with ECN CWR
 flag

Previously commit 9aee40006190 ("tcp: ack immediately when a cwr
packet arrives") calls tcp_enter_quickack_mode to force sending
two immediate ACKs upon receiving a packet w/ CWR flag. The side
effect is it'll also reset the delayed ACK timer and interactive
session tracking. This patch removes that side effect by using the
new ACK_NOW flag to force an immmediate ACK.

Packetdrill to demonstrate:

    0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3
   +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0
   +0 setsockopt(3, SOL_TCP, TCP_CONGESTION, "dctcp", 5) = 0
   +0 bind(3, ..., ...) = 0
   +0 listen(3, 1) = 0

   +0 < [ect0] SEW 0:0(0) win 32792 <mss 1000,sackOK,nop,nop,nop,wscale 7>
   +0 > SE. 0:0(0) ack 1 <mss 1460,nop,nop,sackOK,nop,wscale 8>
  +.1 < [ect0] . 1:1(0) ack 1 win 257
   +0 accept(3, ..., ...) = 4

   +0 < [ect0] . 1:1001(1000) ack 1 win 257
   +0 > [ect01] . 1:1(0) ack 1001

   +0 write(4, ..., 1) = 1
   +0 > [ect01] P. 1:2(1) ack 1001

   +0 < [ect0] . 1001:2001(1000) ack 2 win 257
   +0 write(4, ..., 1) = 1
   +0 > [ect01] P. 2:3(1) ack 2001

   +0 < [ect0] . 2001:3001(1000) ack 3 win 257
   +0 < [ect0] . 3001:4001(1000) ack 3 win 257
   // Ack delayed ...

   +.01 < [ce] P. 4001:4501(500) ack 3 win 257
   +0 > [ect01] . 3:3(0) ack 4001
   +0 > [ect01] E. 3:3(0) ack 4501

+.001 read(4, ..., 4500) = 4500
   +0 write(4, ..., 1) = 1
   +0 > [ect01] PE. 3:4(1) ack 4501 win 100

 +.01 < [ect0] W. 4501:5501(1000) ack 4 win 257
   // No delayed ACK on CWR flag
   +0 > [ect01] . 4:4(0) ack 5501

 +.31 < [ect0] . 5501:6501(1000) ack 4 win 257
   +0 > [ect01] . 4:4(0) ack 6501

Fixes: 9aee40006190 ("tcp: ack immediately when a cwr packet arrives")
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9a09ff3afef2..4c2dd9f863f7 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -245,16 +245,16 @@ static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
 }
 
-static void tcp_ecn_accept_cwr(struct tcp_sock *tp, const struct sk_buff *skb)
+static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb)
 {
 	if (tcp_hdr(skb)->cwr) {
-		tp->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
+		tcp_sk(sk)->ecn_flags &= ~TCP_ECN_DEMAND_CWR;
 
 		/* If the sender is telling us it has entered CWR, then its
 		 * cwnd may be very low (even just 1 packet), so we should ACK
 		 * immediately.
 		 */
-		tcp_enter_quickack_mode((struct sock *)tp, 2);
+		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
 }
 
@@ -4703,7 +4703,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	skb_dst_drop(skb);
 	__skb_pull(skb, tcp_hdr(skb)->doff * 4);
 
-	tcp_ecn_accept_cwr(tp, skb);
+	tcp_ecn_accept_cwr(sk, skb);
 
 	tp->rx_opt.dsack = 0;
 
-- 
cgit v1.2.3


From 07624df1c9efd4b7f2f6762581587c590b03c7a2 Mon Sep 17 00:00:00 2001
From: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Date: Thu, 9 Aug 2018 15:36:10 -0400
Subject: lan743x: lan743x: Add PTP support

PTP support includes:
    Ingress, and egress timestamping.
    One step timestamping available.
    PTP clock support.
    Periodic output support.

Signed-off-by: Bryan Whitehead <Bryan.Whitehead@microchip.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/Makefile          |    2 +-
 drivers/net/ethernet/microchip/lan743x_ethtool.c |   27 +
 drivers/net/ethernet/microchip/lan743x_main.c    |   78 +-
 drivers/net/ethernet/microchip/lan743x_main.h    |  101 +-
 drivers/net/ethernet/microchip/lan743x_ptp.c     | 1164 ++++++++++++++++++++++
 drivers/net/ethernet/microchip/lan743x_ptp.h     |   76 ++
 6 files changed, 1443 insertions(+), 5 deletions(-)
 create mode 100644 drivers/net/ethernet/microchip/lan743x_ptp.c
 create mode 100644 drivers/net/ethernet/microchip/lan743x_ptp.h

diff --git a/drivers/net/ethernet/microchip/Makefile b/drivers/net/ethernet/microchip/Makefile
index 43f47cb45fe2..538926d2b43f 100644
--- a/drivers/net/ethernet/microchip/Makefile
+++ b/drivers/net/ethernet/microchip/Makefile
@@ -6,4 +6,4 @@ obj-$(CONFIG_ENC28J60) += enc28j60.o
 obj-$(CONFIG_ENCX24J600) += encx24j600.o encx24j600-regmap.o
 obj-$(CONFIG_LAN743X) += lan743x.o
 
-lan743x-objs := lan743x_main.o lan743x_ethtool.o
+lan743x-objs := lan743x_main.o lan743x_ethtool.o lan743x_ptp.o
diff --git a/drivers/net/ethernet/microchip/lan743x_ethtool.c b/drivers/net/ethernet/microchip/lan743x_ethtool.c
index c25b3e97ae26..07c1eb63415a 100644
--- a/drivers/net/ethernet/microchip/lan743x_ethtool.c
+++ b/drivers/net/ethernet/microchip/lan743x_ethtool.c
@@ -4,6 +4,7 @@
 #include <linux/netdevice.h>
 #include "lan743x_main.h"
 #include "lan743x_ethtool.h"
+#include <linux/net_tstamp.h>
 #include <linux/pci.h>
 #include <linux/phy.h>
 
@@ -542,6 +543,31 @@ static int lan743x_ethtool_set_rxfh(struct net_device *netdev,
 	return 0;
 }
 
+static int lan743x_ethtool_get_ts_info(struct net_device *netdev,
+				       struct ethtool_ts_info *ts_info)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+
+	ts_info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				   SOF_TIMESTAMPING_RX_SOFTWARE |
+				   SOF_TIMESTAMPING_SOFTWARE |
+				   SOF_TIMESTAMPING_TX_HARDWARE |
+				   SOF_TIMESTAMPING_RX_HARDWARE |
+				   SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (adapter->ptp.ptp_clock)
+		ts_info->phc_index = ptp_clock_index(adapter->ptp.ptp_clock);
+	else
+		ts_info->phc_index = -1;
+
+	ts_info->tx_types = BIT(HWTSTAMP_TX_OFF) |
+			    BIT(HWTSTAMP_TX_ON) |
+			    BIT(HWTSTAMP_TX_ONESTEP_SYNC);
+	ts_info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			      BIT(HWTSTAMP_FILTER_ALL);
+	return 0;
+}
+
 static int lan743x_ethtool_get_eee(struct net_device *netdev,
 				   struct ethtool_eee *eee)
 {
@@ -685,6 +711,7 @@ const struct ethtool_ops lan743x_ethtool_ops = {
 	.get_rxfh_indir_size = lan743x_ethtool_get_rxfh_indir_size,
 	.get_rxfh = lan743x_ethtool_get_rxfh,
 	.set_rxfh = lan743x_ethtool_set_rxfh,
+	.get_ts_info = lan743x_ethtool_get_ts_info,
 	.get_eee = lan743x_ethtool_get_eee,
 	.set_eee = lan743x_ethtool_set_eee,
 	.get_link_ksettings = phy_ethtool_get_link_ksettings,
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index bb323f269839..e7dce79ff2c9 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -267,6 +267,10 @@ static void lan743x_intr_shared_isr(void *context, u32 int_sts, u32 flags)
 			lan743x_intr_software_isr(adapter);
 			int_sts &= ~INT_BIT_SW_GP_;
 		}
+		if (int_sts & INT_BIT_1588_) {
+			lan743x_ptp_isr(adapter);
+			int_sts &= ~INT_BIT_1588_;
+		}
 	}
 	if (int_sts)
 		lan743x_csr_write(adapter, INT_EN_CLR, int_sts);
@@ -976,6 +980,7 @@ static void lan743x_phy_link_status_change(struct net_device *netdev)
 					       ksettings.base.duplex,
 					       local_advertisement,
 					       remote_advertisement);
+		lan743x_ptp_update_latency(adapter, ksettings.base.speed);
 	}
 }
 
@@ -1226,6 +1231,7 @@ static void lan743x_tx_release_desc(struct lan743x_tx *tx,
 	struct lan743x_tx_buffer_info *buffer_info = NULL;
 	struct lan743x_tx_descriptor *descriptor = NULL;
 	u32 descriptor_type = 0;
+	bool ignore_sync;
 
 	descriptor = &tx->ring_cpu_ptr[descriptor_index];
 	buffer_info = &tx->buffer_info[descriptor_index];
@@ -1256,11 +1262,27 @@ clean_up_data_descriptor:
 		buffer_info->dma_ptr = 0;
 		buffer_info->buffer_length = 0;
 	}
-	if (buffer_info->skb) {
+	if (!buffer_info->skb)
+		goto clear_active;
+
+	if (!(buffer_info->flags & TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED)) {
 		dev_kfree_skb(buffer_info->skb);
-		buffer_info->skb = NULL;
+		goto clear_skb;
+	}
+
+	if (cleanup) {
+		lan743x_ptp_unrequest_tx_timestamp(tx->adapter);
+		dev_kfree_skb(buffer_info->skb);
+	} else {
+		ignore_sync = (buffer_info->flags &
+			       TX_BUFFER_INFO_FLAG_IGNORE_SYNC) != 0;
+		lan743x_ptp_tx_timestamp_skb(tx->adapter,
+					     buffer_info->skb, ignore_sync);
 	}
 
+clear_skb:
+	buffer_info->skb = NULL;
+
 clear_active:
 	buffer_info->flags &= ~TX_BUFFER_INFO_FLAG_ACTIVE;
 
@@ -1321,10 +1343,25 @@ static int lan743x_tx_get_avail_desc(struct lan743x_tx *tx)
 		return last_head - last_tail - 1;
 }
 
+void lan743x_tx_set_timestamping_mode(struct lan743x_tx *tx,
+				      bool enable_timestamping,
+				      bool enable_onestep_sync)
+{
+	if (enable_timestamping)
+		tx->ts_flags |= TX_TS_FLAG_TIMESTAMPING_ENABLED;
+	else
+		tx->ts_flags &= ~TX_TS_FLAG_TIMESTAMPING_ENABLED;
+	if (enable_onestep_sync)
+		tx->ts_flags |= TX_TS_FLAG_ONE_STEP_SYNC;
+	else
+		tx->ts_flags &= ~TX_TS_FLAG_ONE_STEP_SYNC;
+}
+
 static int lan743x_tx_frame_start(struct lan743x_tx *tx,
 				  unsigned char *first_buffer,
 				  unsigned int first_buffer_length,
 				  unsigned int frame_length,
+				  bool time_stamp,
 				  bool check_sum)
 {
 	/* called only from within lan743x_tx_xmit_frame.
@@ -1362,6 +1399,8 @@ static int lan743x_tx_frame_start(struct lan743x_tx *tx,
 		TX_DESC_DATA0_DTYPE_DATA_ |
 		TX_DESC_DATA0_FS_ |
 		TX_DESC_DATA0_FCS_;
+	if (time_stamp)
+		tx->frame_data0 |= TX_DESC_DATA0_TSE_;
 
 	if (check_sum)
 		tx->frame_data0 |= TX_DESC_DATA0_ICE_ |
@@ -1475,6 +1514,7 @@ static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx,
 
 static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 				 struct sk_buff *skb,
+				 bool time_stamp,
 				 bool ignore_sync)
 {
 	/* called only from within lan743x_tx_xmit_frame
@@ -1492,6 +1532,8 @@ static void lan743x_tx_frame_end(struct lan743x_tx *tx,
 	tx_descriptor = &tx->ring_cpu_ptr[tx->frame_tail];
 	buffer_info = &tx->buffer_info[tx->frame_tail];
 	buffer_info->skb = skb;
+	if (time_stamp)
+		buffer_info->flags |= TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED;
 	if (ignore_sync)
 		buffer_info->flags |= TX_BUFFER_INFO_FLAG_IGNORE_SYNC;
 
@@ -1520,6 +1562,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	unsigned int frame_length = 0;
 	unsigned int head_length = 0;
 	unsigned long irq_flags = 0;
+	bool do_timestamp = false;
 	bool ignore_sync = false;
 	int nr_frags = 0;
 	bool gso = false;
@@ -1541,6 +1584,14 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	}
 
 	/* space available, transmit skb  */
+	if ((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    (tx->ts_flags & TX_TS_FLAG_TIMESTAMPING_ENABLED) &&
+	    (lan743x_ptp_request_tx_timestamp(tx->adapter))) {
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+		do_timestamp = true;
+		if (tx->ts_flags & TX_TS_FLAG_ONE_STEP_SYNC)
+			ignore_sync = true;
+	}
 	head_length = skb_headlen(skb);
 	frame_length = skb_pagelen(skb);
 	nr_frags = skb_shinfo(skb)->nr_frags;
@@ -1554,6 +1605,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	if (lan743x_tx_frame_start(tx,
 				   skb->data, head_length,
 				   start_frame_length,
+				   do_timestamp,
 				   skb->ip_summed == CHECKSUM_PARTIAL)) {
 		dev_kfree_skb(skb);
 		goto unlock;
@@ -1581,7 +1633,7 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx,
 	}
 
 finish:
-	lan743x_tx_frame_end(tx, skb, ignore_sync);
+	lan743x_tx_frame_end(tx, skb, do_timestamp, ignore_sync);
 
 unlock:
 	spin_unlock_irqrestore(&tx->ring_lock, irq_flags);
@@ -2410,6 +2462,8 @@ static int lan743x_netdev_close(struct net_device *netdev)
 	for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++)
 		lan743x_rx_close(&adapter->rx[index]);
 
+	lan743x_ptp_close(adapter);
+
 	lan743x_phy_close(adapter);
 
 	lan743x_mac_close(adapter);
@@ -2437,6 +2491,10 @@ static int lan743x_netdev_open(struct net_device *netdev)
 	if (ret)
 		goto close_mac;
 
+	ret = lan743x_ptp_open(adapter);
+	if (ret)
+		goto close_phy;
+
 	lan743x_rfe_open(adapter);
 
 	for (index = 0; index < LAN743X_USED_RX_CHANNELS; index++) {
@@ -2456,6 +2514,9 @@ close_rx:
 		if (adapter->rx[index].ring_cpu_ptr)
 			lan743x_rx_close(&adapter->rx[index]);
 	}
+	lan743x_ptp_close(adapter);
+
+close_phy:
 	lan743x_phy_close(adapter);
 
 close_mac:
@@ -2483,6 +2544,8 @@ static int lan743x_netdev_ioctl(struct net_device *netdev,
 {
 	if (!netif_running(netdev))
 		return -EINVAL;
+	if (cmd == SIOCSHWTSTAMP)
+		return lan743x_ptp_ioctl(netdev, ifr, cmd);
 	return phy_mii_ioctl(netdev->phydev, ifr, cmd);
 }
 
@@ -2607,6 +2670,11 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 	adapter->intr.irq = adapter->pdev->irq;
 	lan743x_csr_write(adapter, INT_EN_CLR, 0xFFFFFFFF);
 	mutex_init(&adapter->dp_lock);
+
+	ret = lan743x_gpio_init(adapter);
+	if (ret)
+		return ret;
+
 	ret = lan743x_mac_init(adapter);
 	if (ret)
 		return ret;
@@ -2615,6 +2683,10 @@ static int lan743x_hardware_init(struct lan743x_adapter *adapter,
 	if (ret)
 		return ret;
 
+	ret = lan743x_ptp_init(adapter);
+	if (ret)
+		return ret;
+
 	lan743x_rfe_update_mac_address(adapter);
 
 	ret = lan743x_dmac_init(adapter);
diff --git a/drivers/net/ethernet/microchip/lan743x_main.h b/drivers/net/ethernet/microchip/lan743x_main.h
index 4fa7a5e027f4..0e82b6368798 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.h
+++ b/drivers/net/ethernet/microchip/lan743x_main.h
@@ -4,12 +4,17 @@
 #ifndef _LAN743X_H
 #define _LAN743X_H
 
+#include "lan743x_ptp.h"
+
 #define DRIVER_AUTHOR   "Bryan Whitehead <Bryan.Whitehead@microchip.com>"
 #define DRIVER_DESC "LAN743x PCIe Gigabit Ethernet Driver"
 #define DRIVER_NAME "lan743x"
 
 /* Register Definitions */
 #define ID_REV				(0x00)
+#define ID_REV_ID_MASK_			(0xFFFF0000)
+#define ID_REV_ID_LAN7430_		(0x74300000)
+#define ID_REV_ID_LAN7431_		(0x74310000)
 #define ID_REV_IS_VALID_CHIP_ID_(id_rev)	\
 	(((id_rev) & 0xFFF00000) == 0x74300000)
 #define ID_REV_CHIP_REV_MASK_		(0x0000FFFF)
@@ -62,6 +67,21 @@
 
 #define E2P_DATA			(0x044)
 
+#define GPIO_CFG0			(0x050)
+#define GPIO_CFG0_GPIO_DIR_BIT_(bit)	BIT(16 + (bit))
+#define GPIO_CFG0_GPIO_DATA_BIT_(bit)	BIT(0 + (bit))
+
+#define GPIO_CFG1			(0x054)
+#define GPIO_CFG1_GPIOEN_BIT_(bit)	BIT(16 + (bit))
+#define GPIO_CFG1_GPIOBUF_BIT_(bit)	BIT(0 + (bit))
+
+#define GPIO_CFG2			(0x058)
+#define GPIO_CFG2_1588_POL_BIT_(bit)	BIT(0 + (bit))
+
+#define GPIO_CFG3			(0x05C)
+#define GPIO_CFG3_1588_CH_SEL_BIT_(bit)	BIT(16 + (bit))
+#define GPIO_CFG3_1588_OE_BIT_(bit)	BIT(0 + (bit))
+
 #define FCT_RX_CTL			(0xAC)
 #define FCT_RX_CTL_EN_(channel)		BIT(28 + (channel))
 #define FCT_RX_CTL_DIS_(channel)	BIT(24 + (channel))
@@ -193,7 +213,8 @@
 #define INT_BIT_DMA_TX_(channel)	BIT(16 + (channel))
 #define INT_BIT_ALL_TX_			(0x000F0000)
 #define INT_BIT_SW_GP_			BIT(9)
-#define INT_BIT_ALL_OTHER_		(0x00000280)
+#define INT_BIT_1588_			BIT(7)
+#define INT_BIT_ALL_OTHER_		(INT_BIT_SW_GP_ | INT_BIT_1588_)
 #define INT_BIT_MAS_			BIT(0)
 
 #define INT_SET				(0x784)
@@ -234,6 +255,71 @@
 #define INT_MOD_CFG6			(0x7D8)
 #define INT_MOD_CFG7			(0x7DC)
 
+#define PTP_CMD_CTL					(0x0A00)
+#define PTP_CMD_CTL_PTP_CLK_STP_NSEC_			BIT(6)
+#define PTP_CMD_CTL_PTP_CLOCK_STEP_SEC_			BIT(5)
+#define PTP_CMD_CTL_PTP_CLOCK_LOAD_			BIT(4)
+#define PTP_CMD_CTL_PTP_CLOCK_READ_			BIT(3)
+#define PTP_CMD_CTL_PTP_ENABLE_				BIT(2)
+#define PTP_CMD_CTL_PTP_DISABLE_			BIT(1)
+#define PTP_CMD_CTL_PTP_RESET_				BIT(0)
+#define PTP_GENERAL_CONFIG				(0x0A04)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_X_MASK_(channel) \
+	(0x7 << (1 + ((channel) << 2)))
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_	(0)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_	(1)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_	(2)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_	(3)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_	(4)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_	(5)
+#define PTP_GENERAL_CONFIG_CLOCK_EVENT_X_SET_(channel, value) \
+	(((value) & 0x7) << (1 + ((channel) << 2)))
+#define PTP_GENERAL_CONFIG_RELOAD_ADD_X_(channel)	(BIT((channel) << 2))
+
+#define PTP_INT_STS				(0x0A08)
+#define PTP_INT_EN_SET				(0x0A0C)
+#define PTP_INT_EN_CLR				(0x0A10)
+#define PTP_INT_BIT_TX_SWTS_ERR_		BIT(13)
+#define PTP_INT_BIT_TX_TS_			BIT(12)
+#define PTP_INT_BIT_TIMER_B_			BIT(1)
+#define PTP_INT_BIT_TIMER_A_			BIT(0)
+
+#define PTP_CLOCK_SEC				(0x0A14)
+#define PTP_CLOCK_NS				(0x0A18)
+#define PTP_CLOCK_SUBNS				(0x0A1C)
+#define PTP_CLOCK_RATE_ADJ			(0x0A20)
+#define PTP_CLOCK_RATE_ADJ_DIR_			BIT(31)
+#define PTP_CLOCK_STEP_ADJ			(0x0A2C)
+#define PTP_CLOCK_STEP_ADJ_DIR_			BIT(31)
+#define PTP_CLOCK_STEP_ADJ_VALUE_MASK_		(0x3FFFFFFF)
+#define PTP_CLOCK_TARGET_SEC_X(channel)		(0x0A30 + ((channel) << 4))
+#define PTP_CLOCK_TARGET_NS_X(channel)		(0x0A34 + ((channel) << 4))
+#define PTP_CLOCK_TARGET_RELOAD_SEC_X(channel)	(0x0A38 + ((channel) << 4))
+#define PTP_CLOCK_TARGET_RELOAD_NS_X(channel)	(0x0A3C + ((channel) << 4))
+#define PTP_LATENCY				(0x0A5C)
+#define PTP_LATENCY_TX_SET_(tx_latency)		(((u32)(tx_latency)) << 16)
+#define PTP_LATENCY_RX_SET_(rx_latency)		\
+	(((u32)(rx_latency)) & 0x0000FFFF)
+#define PTP_CAP_INFO				(0x0A60)
+#define PTP_CAP_INFO_TX_TS_CNT_GET_(reg_val)	(((reg_val) & 0x00000070) >> 4)
+
+#define PTP_TX_MOD				(0x0AA4)
+#define PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_	(0x10000000)
+
+#define PTP_TX_MOD2				(0x0AA8)
+#define PTP_TX_MOD2_TX_PTP_CLR_UDPV4_CHKSUM_	(0x00000001)
+
+#define PTP_TX_EGRESS_SEC			(0x0AAC)
+#define PTP_TX_EGRESS_NS			(0x0AB0)
+#define PTP_TX_EGRESS_NS_CAPTURE_CAUSE_MASK_	(0xC0000000)
+#define PTP_TX_EGRESS_NS_CAPTURE_CAUSE_AUTO_	(0x00000000)
+#define PTP_TX_EGRESS_NS_CAPTURE_CAUSE_SW_	(0x40000000)
+#define PTP_TX_EGRESS_NS_TS_NS_MASK_		(0x3FFFFFFF)
+
+#define PTP_TX_MSG_HEADER			(0x0AB4)
+#define PTP_TX_MSG_HEADER_MSG_TYPE_		(0x000F0000)
+#define PTP_TX_MSG_HEADER_MSG_TYPE_SYNC_	(0x00000000)
+
 #define DMAC_CFG				(0xC00)
 #define DMAC_CFG_COAL_EN_			BIT(16)
 #define DMAC_CFG_CH_ARB_SEL_RX_HIGH_		(0x00000000)
@@ -542,8 +628,12 @@ struct lan743x_tx_buffer_info;
 
 #define TX_FRAME_FLAG_IN_PROGRESS	BIT(0)
 
+#define TX_TS_FLAG_TIMESTAMPING_ENABLED	BIT(0)
+#define TX_TS_FLAG_ONE_STEP_SYNC	BIT(1)
+
 struct lan743x_tx {
 	struct lan743x_adapter *adapter;
+	u32	ts_flags;
 	u32	vector_flags;
 	int	channel_number;
 
@@ -570,6 +660,10 @@ struct lan743x_tx {
 	struct sk_buff *overflow_skb;
 };
 
+void lan743x_tx_set_timestamping_mode(struct lan743x_tx *tx,
+				      bool enable_timestamping,
+				      bool enable_onestep_sync);
+
 /* RX */
 struct lan743x_rx_descriptor;
 struct lan743x_rx_buffer_info;
@@ -610,6 +704,9 @@ struct lan743x_adapter {
 	/* lock, used to prevent concurrent access to data port */
 	struct mutex		dp_lock;
 
+	struct lan743x_gpio	gpio;
+	struct lan743x_ptp	ptp;
+
 	u8			mac_address[ETH_ALEN];
 
 	struct lan743x_phy      phy;
@@ -660,6 +757,7 @@ struct lan743x_adapter {
 #define TX_DESC_DATA0_IPE_			(0x00200000)
 #define TX_DESC_DATA0_TPE_			(0x00100000)
 #define TX_DESC_DATA0_FCS_			(0x00020000)
+#define TX_DESC_DATA0_TSE_			(0x00010000)
 #define TX_DESC_DATA0_BUF_LENGTH_MASK_		(0x0000FFFF)
 #define TX_DESC_DATA0_EXT_LSO_			(0x00200000)
 #define TX_DESC_DATA0_EXT_PAY_LENGTH_MASK_	(0x000FFFFF)
@@ -673,6 +771,7 @@ struct lan743x_tx_descriptor {
 } __aligned(DEFAULT_DMA_DESCRIPTOR_SPACING);
 
 #define TX_BUFFER_INFO_FLAG_ACTIVE		BIT(0)
+#define TX_BUFFER_INFO_FLAG_TIMESTAMP_REQUESTED	BIT(1)
 #define TX_BUFFER_INFO_FLAG_IGNORE_SYNC		BIT(2)
 #define TX_BUFFER_INFO_FLAG_SKB_FRAGMENT	BIT(3)
 struct lan743x_tx_buffer_info {
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
new file mode 100644
index 000000000000..42064fd2beb5
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -0,0 +1,1164 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#include <linux/netdevice.h>
+#include "lan743x_main.h"
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+#include <linux/net_tstamp.h>
+
+#include "lan743x_ptp.h"
+
+#define LAN743X_NUMBER_OF_GPIO			(12)
+#define LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB		(31249999)
+#define LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM	(2047999934)
+
+static bool lan743x_ptp_is_enabled(struct lan743x_adapter *adapter);
+static void lan743x_ptp_enable(struct lan743x_adapter *adapter);
+static void lan743x_ptp_disable(struct lan743x_adapter *adapter);
+static void lan743x_ptp_reset(struct lan743x_adapter *adapter);
+static void lan743x_ptp_clock_set(struct lan743x_adapter *adapter,
+				  u32 seconds, u32 nano_seconds,
+				  u32 sub_nano_seconds);
+
+int lan743x_gpio_init(struct lan743x_adapter *adapter)
+{
+	struct lan743x_gpio *gpio = &adapter->gpio;
+
+	spin_lock_init(&gpio->gpio_lock);
+
+	gpio->gpio_cfg0 = 0; /* set all direction to input, data = 0 */
+	gpio->gpio_cfg1 = 0x0FFF0000;/* disable all gpio, set to open drain */
+	gpio->gpio_cfg2 = 0;/* set all to 1588 low polarity level */
+	gpio->gpio_cfg3 = 0;/* disable all 1588 output */
+	lan743x_csr_write(adapter, GPIO_CFG0, gpio->gpio_cfg0);
+	lan743x_csr_write(adapter, GPIO_CFG1, gpio->gpio_cfg1);
+	lan743x_csr_write(adapter, GPIO_CFG2, gpio->gpio_cfg2);
+	lan743x_csr_write(adapter, GPIO_CFG3, gpio->gpio_cfg3);
+
+	return 0;
+}
+
+static void lan743x_ptp_wait_till_cmd_done(struct lan743x_adapter *adapter,
+					   u32 bit_mask)
+{
+	int timeout = 1000;
+	u32 data = 0;
+
+	while (timeout &&
+	       (data = (lan743x_csr_read(adapter, PTP_CMD_CTL) &
+	       bit_mask))) {
+		usleep_range(1000, 20000);
+		timeout--;
+	}
+	if (data) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "timeout waiting for cmd to be done, cmd = 0x%08X\n",
+			  bit_mask);
+	}
+}
+
+static void lan743x_ptp_tx_ts_enqueue_ts(struct lan743x_adapter *adapter,
+					 u32 seconds, u32 nano_seconds,
+					 u32 header)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->tx_ts_queue_size < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS) {
+		ptp->tx_ts_seconds_queue[ptp->tx_ts_queue_size] = seconds;
+		ptp->tx_ts_nseconds_queue[ptp->tx_ts_queue_size] = nano_seconds;
+		ptp->tx_ts_header_queue[ptp->tx_ts_queue_size] = header;
+		ptp->tx_ts_queue_size++;
+	} else {
+		netif_err(adapter, drv, adapter->netdev,
+			  "tx ts queue overflow\n");
+	}
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+static void lan743x_ptp_tx_ts_complete(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	struct skb_shared_hwtstamps tstamps;
+	u32 header, nseconds, seconds;
+	bool ignore_sync = false;
+	struct sk_buff *skb;
+	int c, i;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	c = ptp->tx_ts_skb_queue_size;
+
+	if (c > ptp->tx_ts_queue_size)
+		c = ptp->tx_ts_queue_size;
+	if (c <= 0)
+		goto done;
+
+	for (i = 0; i < c; i++) {
+		ignore_sync = ((ptp->tx_ts_ignore_sync_queue &
+				BIT(i)) != 0);
+		skb = ptp->tx_ts_skb_queue[i];
+		nseconds = ptp->tx_ts_nseconds_queue[i];
+		seconds = ptp->tx_ts_seconds_queue[i];
+		header = ptp->tx_ts_header_queue[i];
+
+		memset(&tstamps, 0, sizeof(tstamps));
+		tstamps.hwtstamp = ktime_set(seconds, nseconds);
+		if (!ignore_sync ||
+		    ((header & PTP_TX_MSG_HEADER_MSG_TYPE_) !=
+		    PTP_TX_MSG_HEADER_MSG_TYPE_SYNC_))
+			skb_tstamp_tx(skb, &tstamps);
+
+		dev_kfree_skb(skb);
+
+		ptp->tx_ts_skb_queue[i] = NULL;
+		ptp->tx_ts_seconds_queue[i] = 0;
+		ptp->tx_ts_nseconds_queue[i] = 0;
+		ptp->tx_ts_header_queue[i] = 0;
+	}
+
+	/* shift queue */
+	ptp->tx_ts_ignore_sync_queue >>= c;
+	for (i = c; i < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS; i++) {
+		ptp->tx_ts_skb_queue[i - c] = ptp->tx_ts_skb_queue[i];
+		ptp->tx_ts_seconds_queue[i - c] = ptp->tx_ts_seconds_queue[i];
+		ptp->tx_ts_nseconds_queue[i - c] = ptp->tx_ts_nseconds_queue[i];
+		ptp->tx_ts_header_queue[i - c] = ptp->tx_ts_header_queue[i];
+
+		ptp->tx_ts_skb_queue[i] = NULL;
+		ptp->tx_ts_seconds_queue[i] = 0;
+		ptp->tx_ts_nseconds_queue[i] = 0;
+		ptp->tx_ts_header_queue[i] = 0;
+	}
+	ptp->tx_ts_skb_queue_size -= c;
+	ptp->tx_ts_queue_size -= c;
+done:
+	ptp->pending_tx_timestamps -= c;
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+#ifdef CONFIG_PTP_1588_CLOCK
+static int lan743x_ptp_reserve_event_ch(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	int result = -ENODEV;
+	int index = 0;
+
+	mutex_lock(&ptp->command_lock);
+	for (index = 0; index < LAN743X_PTP_NUMBER_OF_EVENT_CHANNELS; index++) {
+		if (!(test_bit(index, &ptp->used_event_ch))) {
+			ptp->used_event_ch |= BIT(index);
+			result = index;
+			break;
+		}
+	}
+	mutex_unlock(&ptp->command_lock);
+	return result;
+}
+
+static void lan743x_ptp_release_event_ch(struct lan743x_adapter *adapter,
+					 int event_channel)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+	if (test_bit(event_channel, &ptp->used_event_ch)) {
+		ptp->used_event_ch &= ~BIT(event_channel);
+	} else {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "attempted release on a not used event_channel = %d\n",
+			   event_channel);
+	}
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_clock_get(struct lan743x_adapter *adapter,
+				  u32 *seconds, u32 *nano_seconds,
+				  u32 *sub_nano_seconds);
+static void lan743x_ptp_clock_step(struct lan743x_adapter *adapter,
+				   s64 time_step_ns);
+
+static int lan743x_gpio_rsrv_ptp_out(struct lan743x_adapter *adapter,
+				     int bit, int ptp_channel)
+{
+	struct lan743x_gpio *gpio = &adapter->gpio;
+	unsigned long irq_flags = 0;
+	int bit_mask = BIT(bit);
+	int ret = -EBUSY;
+
+	spin_lock_irqsave(&gpio->gpio_lock, irq_flags);
+
+	if (!(gpio->used_bits & bit_mask)) {
+		gpio->used_bits |= bit_mask;
+		gpio->output_bits |= bit_mask;
+		gpio->ptp_bits |= bit_mask;
+
+		/* set as output, and zero initial value */
+		gpio->gpio_cfg0 |= GPIO_CFG0_GPIO_DIR_BIT_(bit);
+		gpio->gpio_cfg0 &= ~GPIO_CFG0_GPIO_DATA_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG0, gpio->gpio_cfg0);
+
+		/* enable gpio, and set buffer type to push pull */
+		gpio->gpio_cfg1 &= ~GPIO_CFG1_GPIOEN_BIT_(bit);
+		gpio->gpio_cfg1 |= GPIO_CFG1_GPIOBUF_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG1, gpio->gpio_cfg1);
+
+		/* set 1588 polarity to high */
+		gpio->gpio_cfg2 |= GPIO_CFG2_1588_POL_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG2, gpio->gpio_cfg2);
+
+		if (!ptp_channel) {
+			/* use channel A */
+			gpio->gpio_cfg3 &= ~GPIO_CFG3_1588_CH_SEL_BIT_(bit);
+		} else {
+			/* use channel B */
+			gpio->gpio_cfg3 |= GPIO_CFG3_1588_CH_SEL_BIT_(bit);
+		}
+		gpio->gpio_cfg3 |= GPIO_CFG3_1588_OE_BIT_(bit);
+		lan743x_csr_write(adapter, GPIO_CFG3, gpio->gpio_cfg3);
+
+		ret = bit;
+	}
+	spin_unlock_irqrestore(&gpio->gpio_lock, irq_flags);
+	return ret;
+}
+
+static void lan743x_gpio_release(struct lan743x_adapter *adapter, int bit)
+{
+	struct lan743x_gpio *gpio = &adapter->gpio;
+	unsigned long irq_flags = 0;
+	int bit_mask = BIT(bit);
+
+	spin_lock_irqsave(&gpio->gpio_lock, irq_flags);
+	if (gpio->used_bits & bit_mask) {
+		gpio->used_bits &= ~bit_mask;
+		if (gpio->output_bits & bit_mask) {
+			gpio->output_bits &= ~bit_mask;
+
+			if (gpio->ptp_bits & bit_mask) {
+				gpio->ptp_bits &= ~bit_mask;
+				/* disable ptp output */
+				gpio->gpio_cfg3 &= ~GPIO_CFG3_1588_OE_BIT_(bit);
+				lan743x_csr_write(adapter, GPIO_CFG3,
+						  gpio->gpio_cfg3);
+			}
+			/* release gpio output */
+
+			/* disable gpio */
+			gpio->gpio_cfg1 |= GPIO_CFG1_GPIOEN_BIT_(bit);
+			gpio->gpio_cfg1 &= ~GPIO_CFG1_GPIOBUF_BIT_(bit);
+			lan743x_csr_write(adapter, GPIO_CFG1, gpio->gpio_cfg1);
+
+			/* reset back to input */
+			gpio->gpio_cfg0 &= ~GPIO_CFG0_GPIO_DIR_BIT_(bit);
+			gpio->gpio_cfg0 &= ~GPIO_CFG0_GPIO_DATA_BIT_(bit);
+			lan743x_csr_write(adapter, GPIO_CFG0, gpio->gpio_cfg0);
+		}
+	}
+	spin_unlock_irqrestore(&gpio->gpio_lock, irq_flags);
+}
+
+static int lan743x_ptpci_adjfine(struct ptp_clock_info *ptpci, long scaled_ppm)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 lan743x_rate_adj = 0;
+	bool positive = true;
+	u64 u64_delta = 0;
+
+	if ((scaled_ppm < (-LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM)) ||
+	    scaled_ppm > LAN743X_PTP_MAX_FINE_ADJ_IN_SCALED_PPM) {
+		return -EINVAL;
+	}
+	if (scaled_ppm > 0) {
+		u64_delta = (u64)scaled_ppm;
+		positive = true;
+	} else {
+		u64_delta = (u64)(-scaled_ppm);
+		positive = false;
+	}
+	u64_delta = (u64_delta << 19);
+	lan743x_rate_adj = div_u64(u64_delta, 1000000);
+
+	if (positive)
+		lan743x_rate_adj |= PTP_CLOCK_RATE_ADJ_DIR_;
+
+	lan743x_csr_write(adapter, PTP_CLOCK_RATE_ADJ,
+			  lan743x_rate_adj);
+
+	return 0;
+}
+
+static int lan743x_ptpci_adjfreq(struct ptp_clock_info *ptpci, s32 delta_ppb)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 lan743x_rate_adj = 0;
+	bool positive = true;
+	u32 u32_delta = 0;
+	u64 u64_delta = 0;
+
+	if ((delta_ppb < (-LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB)) ||
+	    delta_ppb > LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB) {
+		return -EINVAL;
+	}
+	if (delta_ppb > 0) {
+		u32_delta = (u32)delta_ppb;
+		positive = true;
+	} else {
+		u32_delta = (u32)(-delta_ppb);
+		positive = false;
+	}
+	u64_delta = (((u64)u32_delta) << 35);
+	lan743x_rate_adj = div_u64(u64_delta, 1000000000);
+
+	if (positive)
+		lan743x_rate_adj |= PTP_CLOCK_RATE_ADJ_DIR_;
+
+	lan743x_csr_write(adapter, PTP_CLOCK_RATE_ADJ,
+			  lan743x_rate_adj);
+
+	return 0;
+}
+
+static int lan743x_ptpci_adjtime(struct ptp_clock_info *ptpci, s64 delta)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+
+	lan743x_ptp_clock_step(adapter, delta);
+
+	return 0;
+}
+
+static int lan743x_ptpci_gettime64(struct ptp_clock_info *ptpci,
+				   struct timespec64 *ts)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 nano_seconds = 0;
+	u32 seconds = 0;
+
+	lan743x_ptp_clock_get(adapter, &seconds, &nano_seconds, NULL);
+	ts->tv_sec = seconds;
+	ts->tv_nsec = nano_seconds;
+
+	return 0;
+}
+
+static int lan743x_ptpci_settime64(struct ptp_clock_info *ptpci,
+				   const struct timespec64 *ts)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 nano_seconds = 0;
+	u32 seconds = 0;
+
+	if (ts) {
+		if (ts->tv_sec > 0xFFFFFFFFLL ||
+		    ts->tv_sec < 0) {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "ts->tv_sec out of range, %lld\n",
+				   ts->tv_sec);
+			return -ERANGE;
+		}
+		if (ts->tv_nsec >= 1000000000L ||
+		    ts->tv_nsec < 0) {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "ts->tv_nsec out of range, %ld\n",
+				   ts->tv_nsec);
+			return -ERANGE;
+		}
+		seconds = ts->tv_sec;
+		nano_seconds = ts->tv_nsec;
+		lan743x_ptp_clock_set(adapter, seconds, nano_seconds, 0);
+	} else {
+		netif_warn(adapter, drv, adapter->netdev, "ts == NULL\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void lan743x_ptp_perout_off(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	u32 general_config = 0;
+
+	if (ptp->perout_gpio_bit >= 0) {
+		lan743x_gpio_release(adapter, ptp->perout_gpio_bit);
+		ptp->perout_gpio_bit = -1;
+	}
+
+	if (ptp->perout_event_ch >= 0) {
+		/* set target to far in the future, effectively disabling it */
+		lan743x_csr_write(adapter,
+				  PTP_CLOCK_TARGET_SEC_X(ptp->perout_event_ch),
+				  0xFFFF0000);
+		lan743x_csr_write(adapter,
+				  PTP_CLOCK_TARGET_NS_X(ptp->perout_event_ch),
+				  0);
+
+		general_config = lan743x_csr_read(adapter, PTP_GENERAL_CONFIG);
+		general_config |= PTP_GENERAL_CONFIG_RELOAD_ADD_X_
+				  (ptp->perout_event_ch);
+		lan743x_csr_write(adapter, PTP_GENERAL_CONFIG, general_config);
+		lan743x_ptp_release_event_ch(adapter, ptp->perout_event_ch);
+		ptp->perout_event_ch = -1;
+	}
+}
+
+static int lan743x_ptp_perout(struct lan743x_adapter *adapter, int on,
+			      struct ptp_perout_request *perout)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	u32 period_sec = 0, period_nsec = 0;
+	u32 start_sec = 0, start_nsec = 0;
+	u32 general_config = 0;
+	int pulse_width = 0;
+	int perout_bit = 0;
+
+	if (!on) {
+		lan743x_ptp_perout_off(adapter);
+		return 0;
+	}
+
+	if (ptp->perout_event_ch >= 0 ||
+	    ptp->perout_gpio_bit >= 0) {
+		/* already on, turn off first */
+		lan743x_ptp_perout_off(adapter);
+	}
+
+	ptp->perout_event_ch = lan743x_ptp_reserve_event_ch(adapter);
+	if (ptp->perout_event_ch < 0) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "Failed to reserve event channel for PEROUT\n");
+		goto failed;
+	}
+
+	switch (adapter->csr.id_rev & ID_REV_ID_MASK_) {
+	case ID_REV_ID_LAN7430_:
+		perout_bit = 2;/* GPIO 2 is preferred on EVB LAN7430 */
+		break;
+	case ID_REV_ID_LAN7431_:
+		perout_bit = 4;/* GPIO 4 is preferred on EVB LAN7431 */
+		break;
+	}
+
+	ptp->perout_gpio_bit = lan743x_gpio_rsrv_ptp_out(adapter,
+							 perout_bit,
+							 ptp->perout_event_ch);
+
+	if (ptp->perout_gpio_bit < 0) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "Failed to reserve gpio %d for PEROUT\n",
+			   perout_bit);
+		goto failed;
+	}
+
+	start_sec = perout->start.sec;
+	start_sec += perout->start.nsec / 1000000000;
+	start_nsec = perout->start.nsec % 1000000000;
+
+	period_sec = perout->period.sec;
+	period_sec += perout->period.nsec / 1000000000;
+	period_nsec = perout->period.nsec % 1000000000;
+
+	if (period_sec == 0) {
+		if (period_nsec >= 400000000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_;
+		} else if (period_nsec >= 20000000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10MS_;
+		} else if (period_nsec >= 2000000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_1MS_;
+		} else if (period_nsec >= 200000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100US_;
+		} else if (period_nsec >= 20000) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_10US_;
+		} else if (period_nsec >= 200) {
+			pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_100NS_;
+		} else {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "perout period too small, minimum is 200nS\n");
+			goto failed;
+		}
+	} else {
+		pulse_width = PTP_GENERAL_CONFIG_CLOCK_EVENT_200MS_;
+	}
+
+	/* turn off by setting target far in future */
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_SEC_X(ptp->perout_event_ch),
+			  0xFFFF0000);
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_NS_X(ptp->perout_event_ch), 0);
+
+	/* Configure to pulse every period */
+	general_config = lan743x_csr_read(adapter, PTP_GENERAL_CONFIG);
+	general_config &= ~(PTP_GENERAL_CONFIG_CLOCK_EVENT_X_MASK_
+			  (ptp->perout_event_ch));
+	general_config |= PTP_GENERAL_CONFIG_CLOCK_EVENT_X_SET_
+			  (ptp->perout_event_ch, pulse_width);
+	general_config &= ~PTP_GENERAL_CONFIG_RELOAD_ADD_X_
+			  (ptp->perout_event_ch);
+	lan743x_csr_write(adapter, PTP_GENERAL_CONFIG, general_config);
+
+	/* set the reload to one toggle cycle */
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_RELOAD_SEC_X(ptp->perout_event_ch),
+			  period_sec);
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_RELOAD_NS_X(ptp->perout_event_ch),
+			  period_nsec);
+
+	/* set the start time */
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_SEC_X(ptp->perout_event_ch),
+			  start_sec);
+	lan743x_csr_write(adapter,
+			  PTP_CLOCK_TARGET_NS_X(ptp->perout_event_ch),
+			  start_nsec);
+
+	return 0;
+
+failed:
+	lan743x_ptp_perout_off(adapter);
+	return -ENODEV;
+}
+
+static int lan743x_ptpci_enable(struct ptp_clock_info *ptpci,
+				struct ptp_clock_request *request, int on)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+
+	if (request) {
+		switch (request->type) {
+		case PTP_CLK_REQ_EXTTS:
+			return -EINVAL;
+		case PTP_CLK_REQ_PEROUT:
+			if (request->perout.index == 0)
+				return lan743x_ptp_perout(adapter, on,
+							  &request->perout);
+			return -EINVAL;
+		case PTP_CLK_REQ_PPS:
+			return -EINVAL;
+		default:
+			netif_err(adapter, drv, adapter->netdev,
+				  "request->type == %d, Unknown\n",
+				  request->type);
+			break;
+		}
+	} else {
+		netif_err(adapter, drv, adapter->netdev, "request == NULL\n");
+	}
+	return 0;
+}
+
+static long lan743x_ptpci_do_aux_work(struct ptp_clock_info *ptpci)
+{
+	struct lan743x_ptp *ptp =
+		container_of(ptpci, struct lan743x_ptp, ptp_clock_info);
+	struct lan743x_adapter *adapter =
+		container_of(ptp, struct lan743x_adapter, ptp);
+	u32 cap_info, cause, header, nsec, seconds;
+	bool new_timestamp_available = false;
+	int count = 0;
+
+	while ((count < 100) &&
+	       (lan743x_csr_read(adapter, PTP_INT_STS) & PTP_INT_BIT_TX_TS_)) {
+		count++;
+		cap_info = lan743x_csr_read(adapter, PTP_CAP_INFO);
+
+		if (PTP_CAP_INFO_TX_TS_CNT_GET_(cap_info) > 0) {
+			seconds = lan743x_csr_read(adapter,
+						   PTP_TX_EGRESS_SEC);
+			nsec = lan743x_csr_read(adapter, PTP_TX_EGRESS_NS);
+			cause = (nsec &
+				 PTP_TX_EGRESS_NS_CAPTURE_CAUSE_MASK_);
+			header = lan743x_csr_read(adapter,
+						  PTP_TX_MSG_HEADER);
+
+			if (cause == PTP_TX_EGRESS_NS_CAPTURE_CAUSE_SW_) {
+				nsec &= PTP_TX_EGRESS_NS_TS_NS_MASK_;
+				lan743x_ptp_tx_ts_enqueue_ts(adapter,
+							     seconds, nsec,
+							     header);
+				new_timestamp_available = true;
+			} else if (cause ==
+				PTP_TX_EGRESS_NS_CAPTURE_CAUSE_AUTO_) {
+				netif_err(adapter, drv, adapter->netdev,
+					  "Auto capture cause not supported\n");
+			} else {
+				netif_warn(adapter, drv, adapter->netdev,
+					   "unknown tx timestamp capture cause\n");
+			}
+		} else {
+			netif_warn(adapter, drv, adapter->netdev,
+				   "TX TS INT but no TX TS CNT\n");
+		}
+		lan743x_csr_write(adapter, PTP_INT_STS, PTP_INT_BIT_TX_TS_);
+	}
+
+	if (new_timestamp_available)
+		lan743x_ptp_tx_ts_complete(adapter);
+
+	lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_1588_);
+
+	return -1;
+}
+
+static void lan743x_ptp_clock_get(struct lan743x_adapter *adapter,
+				  u32 *seconds, u32 *nano_seconds,
+				  u32 *sub_nano_seconds)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_CLOCK_READ_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_CLOCK_READ_);
+
+	if (seconds)
+		(*seconds) = lan743x_csr_read(adapter, PTP_CLOCK_SEC);
+
+	if (nano_seconds)
+		(*nano_seconds) = lan743x_csr_read(adapter, PTP_CLOCK_NS);
+
+	if (sub_nano_seconds)
+		(*sub_nano_seconds) =
+		lan743x_csr_read(adapter, PTP_CLOCK_SUBNS);
+
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_clock_step(struct lan743x_adapter *adapter,
+				   s64 time_step_ns)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	u32 nano_seconds_step = 0;
+	u64 abs_time_step_ns = 0;
+	u32 unsigned_seconds = 0;
+	u32 nano_seconds = 0;
+	u32 remainder = 0;
+	s32 seconds = 0;
+
+	if (time_step_ns >  15000000000LL) {
+		/* convert to clock set */
+		lan743x_ptp_clock_get(adapter, &unsigned_seconds,
+				      &nano_seconds, NULL);
+		unsigned_seconds += div_u64_rem(time_step_ns, 1000000000LL,
+						&remainder);
+		nano_seconds += remainder;
+		if (nano_seconds >= 1000000000) {
+			unsigned_seconds++;
+			nano_seconds -= 1000000000;
+		}
+		lan743x_ptp_clock_set(adapter, unsigned_seconds,
+				      nano_seconds, 0);
+		return;
+	} else if (time_step_ns < -15000000000LL) {
+		/* convert to clock set */
+		time_step_ns = -time_step_ns;
+
+		lan743x_ptp_clock_get(adapter, &unsigned_seconds,
+				      &nano_seconds, NULL);
+		unsigned_seconds -= div_u64_rem(time_step_ns, 1000000000LL,
+						&remainder);
+		nano_seconds_step = remainder;
+		if (nano_seconds < nano_seconds_step) {
+			unsigned_seconds--;
+			nano_seconds += 1000000000;
+		}
+		nano_seconds -= nano_seconds_step;
+		lan743x_ptp_clock_set(adapter, unsigned_seconds,
+				      nano_seconds, 0);
+		return;
+	}
+
+	/* do clock step */
+	if (time_step_ns >= 0) {
+		abs_time_step_ns = (u64)(time_step_ns);
+		seconds = (s32)div_u64_rem(abs_time_step_ns, 1000000000,
+					   &remainder);
+		nano_seconds = (u32)remainder;
+	} else {
+		abs_time_step_ns = (u64)(-time_step_ns);
+		seconds = -((s32)div_u64_rem(abs_time_step_ns, 1000000000,
+					     &remainder));
+		nano_seconds = (u32)remainder;
+		if (nano_seconds > 0) {
+			/* subtracting nano seconds is not allowed
+			 * convert to subtracting from seconds,
+			 * and adding to nanoseconds
+			 */
+			seconds--;
+			nano_seconds = (1000000000 - nano_seconds);
+		}
+	}
+
+	if (nano_seconds > 0) {
+		/* add 8 ns to cover the likely normal increment */
+		nano_seconds += 8;
+	}
+
+	if (nano_seconds >= 1000000000) {
+		/* carry into seconds */
+		seconds++;
+		nano_seconds -= 1000000000;
+	}
+
+	while (seconds) {
+		mutex_lock(&ptp->command_lock);
+		if (seconds > 0) {
+			u32 adjustment_value = (u32)seconds;
+
+			if (adjustment_value > 0xF)
+				adjustment_value = 0xF;
+			lan743x_csr_write(adapter, PTP_CLOCK_STEP_ADJ,
+					  PTP_CLOCK_STEP_ADJ_DIR_ |
+					  adjustment_value);
+			seconds -= ((s32)adjustment_value);
+		} else {
+			u32 adjustment_value = (u32)(-seconds);
+
+			if (adjustment_value > 0xF)
+				adjustment_value = 0xF;
+			lan743x_csr_write(adapter, PTP_CLOCK_STEP_ADJ,
+					  adjustment_value);
+			seconds += ((s32)adjustment_value);
+		}
+		lan743x_csr_write(adapter, PTP_CMD_CTL,
+				  PTP_CMD_CTL_PTP_CLOCK_STEP_SEC_);
+		lan743x_ptp_wait_till_cmd_done(adapter,
+					       PTP_CMD_CTL_PTP_CLOCK_STEP_SEC_);
+		mutex_unlock(&ptp->command_lock);
+	}
+	if (nano_seconds) {
+		mutex_lock(&ptp->command_lock);
+		lan743x_csr_write(adapter, PTP_CLOCK_STEP_ADJ,
+				  PTP_CLOCK_STEP_ADJ_DIR_ |
+				  (nano_seconds &
+				  PTP_CLOCK_STEP_ADJ_VALUE_MASK_));
+		lan743x_csr_write(adapter, PTP_CMD_CTL,
+				  PTP_CMD_CTL_PTP_CLK_STP_NSEC_);
+		lan743x_ptp_wait_till_cmd_done(adapter,
+					       PTP_CMD_CTL_PTP_CLK_STP_NSEC_);
+		mutex_unlock(&ptp->command_lock);
+	}
+}
+#endif /* CONFIG_PTP_1588_CLOCK */
+
+void lan743x_ptp_isr(void *context)
+{
+	struct lan743x_adapter *adapter = (struct lan743x_adapter *)context;
+	struct lan743x_ptp *ptp = NULL;
+	int enable_flag = 1;
+	u32 ptp_int_sts = 0;
+
+	ptp = &adapter->ptp;
+
+	lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_1588_);
+
+	ptp_int_sts = lan743x_csr_read(adapter, PTP_INT_STS);
+	ptp_int_sts &= lan743x_csr_read(adapter, PTP_INT_EN_SET);
+
+	if (ptp_int_sts & PTP_INT_BIT_TX_TS_) {
+		ptp_schedule_worker(ptp->ptp_clock, 0);
+		enable_flag = 0;/* tasklet will re-enable later */
+	}
+	if (ptp_int_sts & PTP_INT_BIT_TX_SWTS_ERR_) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "PTP TX Software Timestamp Error\n");
+		/* clear int status bit */
+		lan743x_csr_write(adapter, PTP_INT_STS,
+				  PTP_INT_BIT_TX_SWTS_ERR_);
+	}
+	if (ptp_int_sts & PTP_INT_BIT_TIMER_B_) {
+		/* clear int status bit */
+		lan743x_csr_write(adapter, PTP_INT_STS,
+				  PTP_INT_BIT_TIMER_B_);
+	}
+	if (ptp_int_sts & PTP_INT_BIT_TIMER_A_) {
+		/* clear int status bit */
+		lan743x_csr_write(adapter, PTP_INT_STS,
+				  PTP_INT_BIT_TIMER_A_);
+	}
+
+	if (enable_flag) {
+		/* re-enable isr */
+		lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_1588_);
+	}
+}
+
+static void lan743x_ptp_tx_ts_enqueue_skb(struct lan743x_adapter *adapter,
+					  struct sk_buff *skb, bool ignore_sync)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->tx_ts_skb_queue_size < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS) {
+		ptp->tx_ts_skb_queue[ptp->tx_ts_skb_queue_size] = skb;
+		if (ignore_sync)
+			ptp->tx_ts_ignore_sync_queue |=
+				BIT(ptp->tx_ts_skb_queue_size);
+		ptp->tx_ts_skb_queue_size++;
+	} else {
+		/* this should never happen, so long as the tx channel
+		 * calls and honors the result from
+		 * lan743x_ptp_request_tx_timestamp
+		 */
+		netif_err(adapter, drv, adapter->netdev,
+			  "tx ts skb queue overflow\n");
+		dev_kfree_skb(skb);
+	}
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+static void lan743x_ptp_sync_to_system_clock(struct lan743x_adapter *adapter)
+{
+	struct timespec64 ts;
+
+	memset(&ts, 0, sizeof(ts));
+	timekeeping_clocktai64(&ts);
+
+	lan743x_ptp_clock_set(adapter, ts.tv_sec, ts.tv_nsec, 0);
+}
+
+void lan743x_ptp_update_latency(struct lan743x_adapter *adapter,
+				u32 link_speed)
+{
+	switch (link_speed) {
+	case 10:
+		lan743x_csr_write(adapter, PTP_LATENCY,
+				  PTP_LATENCY_TX_SET_(0) |
+				  PTP_LATENCY_RX_SET_(0));
+		break;
+	case 100:
+		lan743x_csr_write(adapter, PTP_LATENCY,
+				  PTP_LATENCY_TX_SET_(181) |
+				  PTP_LATENCY_RX_SET_(594));
+		break;
+	case 1000:
+		lan743x_csr_write(adapter, PTP_LATENCY,
+				  PTP_LATENCY_TX_SET_(30) |
+				  PTP_LATENCY_RX_SET_(525));
+		break;
+	}
+}
+
+int lan743x_ptp_init(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_init(&ptp->command_lock);
+	spin_lock_init(&ptp->tx_ts_lock);
+	ptp->used_event_ch = 0;
+	ptp->perout_event_ch = -1;
+	ptp->perout_gpio_bit = -1;
+	return 0;
+}
+
+int lan743x_ptp_open(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	int ret = -ENODEV;
+	u32 temp;
+
+	lan743x_ptp_reset(adapter);
+	lan743x_ptp_sync_to_system_clock(adapter);
+	temp = lan743x_csr_read(adapter, PTP_TX_MOD2);
+	temp |= PTP_TX_MOD2_TX_PTP_CLR_UDPV4_CHKSUM_;
+	lan743x_csr_write(adapter, PTP_TX_MOD2, temp);
+	lan743x_ptp_enable(adapter);
+	lan743x_csr_write(adapter, INT_EN_SET, INT_BIT_1588_);
+	lan743x_csr_write(adapter, PTP_INT_EN_SET,
+			  PTP_INT_BIT_TX_SWTS_ERR_ | PTP_INT_BIT_TX_TS_);
+	ptp->flags |= PTP_FLAG_ISR_ENABLED;
+
+#ifdef CONFIG_PTP_1588_CLOCK
+	snprintf(ptp->pin_config[0].name, 32, "lan743x_ptp_pin_0");
+	ptp->pin_config[0].index = 0;
+	ptp->pin_config[0].func = PTP_PF_PEROUT;
+	ptp->pin_config[0].chan = 0;
+
+	ptp->ptp_clock_info.owner = THIS_MODULE;
+	snprintf(ptp->ptp_clock_info.name, 16, "%pm",
+		 adapter->netdev->dev_addr);
+	ptp->ptp_clock_info.max_adj = LAN743X_PTP_MAX_FREQ_ADJ_IN_PPB;
+	ptp->ptp_clock_info.n_alarm = 0;
+	ptp->ptp_clock_info.n_ext_ts = 0;
+	ptp->ptp_clock_info.n_per_out = 1;
+	ptp->ptp_clock_info.n_pins = 0;
+	ptp->ptp_clock_info.pps = 0;
+	ptp->ptp_clock_info.pin_config = NULL;
+	ptp->ptp_clock_info.adjfine = lan743x_ptpci_adjfine;
+	ptp->ptp_clock_info.adjfreq = lan743x_ptpci_adjfreq;
+	ptp->ptp_clock_info.adjtime = lan743x_ptpci_adjtime;
+	ptp->ptp_clock_info.gettime64 = lan743x_ptpci_gettime64;
+	ptp->ptp_clock_info.getcrosststamp = NULL;
+	ptp->ptp_clock_info.settime64 = lan743x_ptpci_settime64;
+	ptp->ptp_clock_info.enable = lan743x_ptpci_enable;
+	ptp->ptp_clock_info.do_aux_work = lan743x_ptpci_do_aux_work;
+	ptp->ptp_clock_info.verify = NULL;
+
+	ptp->ptp_clock = ptp_clock_register(&ptp->ptp_clock_info,
+					    &adapter->pdev->dev);
+
+	if (IS_ERR(ptp->ptp_clock)) {
+		netif_err(adapter, ifup, adapter->netdev,
+			  "ptp_clock_register failed\n");
+		goto done;
+	}
+	ptp->flags |= PTP_FLAG_PTP_CLOCK_REGISTERED;
+	netif_info(adapter, ifup, adapter->netdev,
+		   "successfully registered ptp clock\n");
+
+	return 0;
+done:
+	lan743x_ptp_close(adapter);
+	return ret;
+#else
+	return 0;
+#endif
+}
+
+void lan743x_ptp_close(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	int index;
+
+#ifdef CONFIG_PTP_1588_CLOCK
+	if (ptp->flags & PTP_FLAG_PTP_CLOCK_REGISTERED) {
+		ptp_clock_unregister(ptp->ptp_clock);
+		ptp->ptp_clock = NULL;
+		ptp->flags &= ~PTP_FLAG_PTP_CLOCK_REGISTERED;
+		netif_info(adapter, drv, adapter->netdev,
+			   "ptp clock unregister\n");
+	}
+#endif
+
+	if (ptp->flags & PTP_FLAG_ISR_ENABLED) {
+		lan743x_csr_write(adapter, PTP_INT_EN_CLR,
+				  PTP_INT_BIT_TX_SWTS_ERR_ |
+				  PTP_INT_BIT_TX_TS_);
+		lan743x_csr_write(adapter, INT_EN_CLR, INT_BIT_1588_);
+		ptp->flags &= ~PTP_FLAG_ISR_ENABLED;
+	}
+
+	/* clean up pending timestamp requests */
+	lan743x_ptp_tx_ts_complete(adapter);
+	spin_lock_bh(&ptp->tx_ts_lock);
+	for (index = 0;
+		index < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS;
+		index++) {
+		struct sk_buff *skb = ptp->tx_ts_skb_queue[index];
+
+		if (skb)
+			dev_kfree_skb(skb);
+		ptp->tx_ts_skb_queue[index] = NULL;
+		ptp->tx_ts_seconds_queue[index] = 0;
+		ptp->tx_ts_nseconds_queue[index] = 0;
+	}
+	ptp->tx_ts_skb_queue_size = 0;
+	ptp->tx_ts_queue_size = 0;
+	ptp->pending_tx_timestamps = 0;
+	spin_unlock_bh(&ptp->tx_ts_lock);
+
+	lan743x_ptp_disable(adapter);
+}
+
+void lan743x_ptp_set_sync_ts_insert(struct lan743x_adapter *adapter,
+				    bool ts_insert_enable)
+{
+	u32 ptp_tx_mod = lan743x_csr_read(adapter, PTP_TX_MOD);
+
+	if (ts_insert_enable)
+		ptp_tx_mod |= PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_;
+	else
+		ptp_tx_mod &= ~PTP_TX_MOD_TX_PTP_SYNC_TS_INSERT_;
+
+	lan743x_csr_write(adapter, PTP_TX_MOD, ptp_tx_mod);
+}
+
+static bool lan743x_ptp_is_enabled(struct lan743x_adapter *adapter)
+{
+	if (lan743x_csr_read(adapter, PTP_CMD_CTL) & PTP_CMD_CTL_PTP_ENABLE_)
+		return true;
+	return false;
+}
+
+static void lan743x_ptp_enable(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	if (lan743x_ptp_is_enabled(adapter)) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "PTP already enabled\n");
+		goto done;
+	}
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_ENABLE_);
+done:
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_disable(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+	if (!lan743x_ptp_is_enabled(adapter)) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "PTP already disabled\n");
+		goto done;
+	}
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_DISABLE_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_ENABLE_);
+done:
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_reset(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	if (lan743x_ptp_is_enabled(adapter)) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "Attempting reset while enabled\n");
+		goto done;
+	}
+
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_RESET_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_RESET_);
+done:
+	mutex_unlock(&ptp->command_lock);
+}
+
+static void lan743x_ptp_clock_set(struct lan743x_adapter *adapter,
+				  u32 seconds, u32 nano_seconds,
+				  u32 sub_nano_seconds)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	mutex_lock(&ptp->command_lock);
+
+	lan743x_csr_write(adapter, PTP_CLOCK_SEC, seconds);
+	lan743x_csr_write(adapter, PTP_CLOCK_NS, nano_seconds);
+	lan743x_csr_write(adapter, PTP_CLOCK_SUBNS, sub_nano_seconds);
+
+	lan743x_csr_write(adapter, PTP_CMD_CTL, PTP_CMD_CTL_PTP_CLOCK_LOAD_);
+	lan743x_ptp_wait_till_cmd_done(adapter, PTP_CMD_CTL_PTP_CLOCK_LOAD_);
+	mutex_unlock(&ptp->command_lock);
+}
+
+bool lan743x_ptp_request_tx_timestamp(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+	bool result = false;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->pending_tx_timestamps < LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS) {
+		/* request granted */
+		ptp->pending_tx_timestamps++;
+		result = true;
+	}
+	spin_unlock_bh(&ptp->tx_ts_lock);
+	return result;
+}
+
+void lan743x_ptp_unrequest_tx_timestamp(struct lan743x_adapter *adapter)
+{
+	struct lan743x_ptp *ptp = &adapter->ptp;
+
+	spin_lock_bh(&ptp->tx_ts_lock);
+	if (ptp->pending_tx_timestamps > 0)
+		ptp->pending_tx_timestamps--;
+	else
+		netif_err(adapter, drv, adapter->netdev,
+			  "unrequest failed, pending_tx_timestamps==0\n");
+	spin_unlock_bh(&ptp->tx_ts_lock);
+}
+
+void lan743x_ptp_tx_timestamp_skb(struct lan743x_adapter *adapter,
+				  struct sk_buff *skb, bool ignore_sync)
+{
+	lan743x_ptp_tx_ts_enqueue_skb(adapter, skb, ignore_sync);
+
+	lan743x_ptp_tx_ts_complete(adapter);
+}
+
+int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd)
+{
+	struct lan743x_adapter *adapter = netdev_priv(netdev);
+	struct hwtstamp_config config;
+	int ret = 0;
+	int index;
+
+	if (!ifr) {
+		netif_err(adapter, drv, adapter->netdev,
+			  "SIOCSHWTSTAMP, ifr == NULL\n");
+		return -EINVAL;
+	}
+
+	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
+		return -EFAULT;
+
+	if (config.flags) {
+		netif_warn(adapter, drv, adapter->netdev,
+			   "ignoring hwtstamp_config.flags == 0x%08X, expected 0\n",
+			   config.flags);
+	}
+
+	switch (config.tx_type) {
+	case HWTSTAMP_TX_OFF:
+		for (index = 0; index < LAN743X_MAX_TX_CHANNELS;
+			index++)
+			lan743x_tx_set_timestamping_mode(&adapter->tx[index],
+							 false, false);
+		lan743x_ptp_set_sync_ts_insert(adapter, false);
+		break;
+	case HWTSTAMP_TX_ON:
+		for (index = 0; index < LAN743X_MAX_TX_CHANNELS;
+			index++)
+			lan743x_tx_set_timestamping_mode(&adapter->tx[index],
+							 true, false);
+		lan743x_ptp_set_sync_ts_insert(adapter, false);
+		break;
+	case HWTSTAMP_TX_ONESTEP_SYNC:
+		for (index = 0; index < LAN743X_MAX_TX_CHANNELS;
+			index++)
+			lan743x_tx_set_timestamping_mode(&adapter->tx[index],
+							 true, true);
+
+		lan743x_ptp_set_sync_ts_insert(adapter, true);
+		break;
+	default:
+		netif_warn(adapter, drv, adapter->netdev,
+			   "  tx_type = %d, UNKNOWN\n", config.tx_type);
+		ret = -EINVAL;
+		break;
+	}
+
+	if (!ret)
+		return copy_to_user(ifr->ifr_data, &config,
+			sizeof(config)) ? -EFAULT : 0;
+	return ret;
+}
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
new file mode 100644
index 000000000000..20f2223024dc
--- /dev/null
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2018 Microchip Technology Inc. */
+
+#ifndef _LAN743X_PTP_H
+#define _LAN743X_PTP_H
+
+#include "linux/ptp_clock_kernel.h"
+#include "linux/netdevice.h"
+
+struct lan743x_adapter;
+
+/* GPIO */
+struct lan743x_gpio {
+	/* gpio_lock: used to prevent concurrent access to gpio settings */
+	spinlock_t gpio_lock;
+
+	int used_bits;
+	int output_bits;
+	int ptp_bits;
+	u32 gpio_cfg0;
+	u32 gpio_cfg1;
+	u32 gpio_cfg2;
+	u32 gpio_cfg3;
+};
+
+int lan743x_gpio_init(struct lan743x_adapter *adapter);
+
+void lan743x_ptp_isr(void *context);
+bool lan743x_ptp_request_tx_timestamp(struct lan743x_adapter *adapter);
+void lan743x_ptp_unrequest_tx_timestamp(struct lan743x_adapter *adapter);
+void lan743x_ptp_tx_timestamp_skb(struct lan743x_adapter *adapter,
+				  struct sk_buff *skb, bool ignore_sync);
+int lan743x_ptp_init(struct lan743x_adapter *adapter);
+int lan743x_ptp_open(struct lan743x_adapter *adapter);
+void lan743x_ptp_close(struct lan743x_adapter *adapter);
+void lan743x_ptp_update_latency(struct lan743x_adapter *adapter,
+				u32 link_speed);
+
+int lan743x_ptp_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd);
+
+#define LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS (4)
+
+#define PTP_FLAG_PTP_CLOCK_REGISTERED	BIT(1)
+#define PTP_FLAG_ISR_ENABLED			BIT(2)
+
+struct lan743x_ptp {
+	int flags;
+
+	/* command_lock: used to prevent concurrent ptp commands */
+	struct mutex	command_lock;
+
+#ifdef CONFIG_PTP_1588_CLOCK
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info ptp_clock_info;
+	struct ptp_pin_desc pin_config[1];
+#endif /* CONFIG_PTP_1588_CLOCK */
+
+#define LAN743X_PTP_NUMBER_OF_EVENT_CHANNELS (2)
+	unsigned long used_event_ch;
+
+	int perout_event_ch;
+	int perout_gpio_bit;
+
+	/* tx_ts_lock: used to prevent concurrent access to timestamp arrays */
+	spinlock_t	tx_ts_lock;
+	int pending_tx_timestamps;
+	struct sk_buff *tx_ts_skb_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	unsigned int	tx_ts_ignore_sync_queue;
+	int tx_ts_skb_queue_size;
+	u32 tx_ts_seconds_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	u32 tx_ts_nseconds_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	u32 tx_ts_header_queue[LAN743X_PTP_NUMBER_OF_TX_TIMESTAMPS];
+	int tx_ts_queue_size;
+};
+
+#endif /* _LAN743X_PTP_H */
-- 
cgit v1.2.3


From 19e226e8cc5da02f17ed119f9137036c0f0f5d80 Mon Sep 17 00:00:00 2001
From: Caleb Raitto <caraitto@google.com>
Date: Thu, 9 Aug 2018 18:18:28 -0700
Subject: virtio: Make vp_set_vq_affinity() take a mask.

Make vp_set_vq_affinity() take a cpumask instead of taking a single CPU.

If there are fewer queues than cores, queue affinity should be able to
map to multiple cores.

Link: https://patchwork.ozlabs.org/patch/948149/
Suggested-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Caleb Raitto <caraitto@google.com>
Acked-by: Gonglei <arei.gonglei@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/crypto/virtio/virtio_crypto_core.c | 4 ++--
 drivers/net/virtio_net.c                   | 8 ++++----
 drivers/virtio/virtio_pci_common.c         | 7 +++----
 drivers/virtio/virtio_pci_common.h         | 2 +-
 include/linux/virtio_config.h              | 7 ++++---
 5 files changed, 14 insertions(+), 14 deletions(-)

diff --git a/drivers/crypto/virtio/virtio_crypto_core.c b/drivers/crypto/virtio/virtio_crypto_core.c
index 83326986c113..7c7198553699 100644
--- a/drivers/crypto/virtio/virtio_crypto_core.c
+++ b/drivers/crypto/virtio/virtio_crypto_core.c
@@ -146,7 +146,7 @@ static void virtcrypto_clean_affinity(struct virtio_crypto *vi, long hcpu)
 
 	if (vi->affinity_hint_set) {
 		for (i = 0; i < vi->max_data_queues; i++)
-			virtqueue_set_affinity(vi->data_vq[i].vq, -1);
+			virtqueue_set_affinity(vi->data_vq[i].vq, NULL);
 
 		vi->affinity_hint_set = false;
 	}
@@ -173,7 +173,7 @@ static void virtcrypto_set_affinity(struct virtio_crypto *vcrypto)
 	 *
 	 */
 	for_each_online_cpu(cpu) {
-		virtqueue_set_affinity(vcrypto->data_vq[i].vq, cpu);
+		virtqueue_set_affinity(vcrypto->data_vq[i].vq, cpumask_of(cpu));
 		if (++i >= vcrypto->max_data_queues)
 			break;
 	}
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 39a7f4452587..43fabc0eb4d2 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1878,8 +1878,8 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
 
 	if (vi->affinity_hint_set) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtqueue_set_affinity(vi->rq[i].vq, -1);
-			virtqueue_set_affinity(vi->sq[i].vq, -1);
+			virtqueue_set_affinity(vi->rq[i].vq, NULL);
+			virtqueue_set_affinity(vi->sq[i].vq, NULL);
 		}
 
 		vi->affinity_hint_set = false;
@@ -1905,8 +1905,8 @@ static void virtnet_set_affinity(struct virtnet_info *vi)
 	for_each_online_cpu(cpu) {
 		const unsigned long *mask = cpumask_bits(cpumask_of(cpu));
 
-		virtqueue_set_affinity(vi->rq[i].vq, cpu);
-		virtqueue_set_affinity(vi->sq[i].vq, cpu);
+		virtqueue_set_affinity(vi->rq[i].vq, cpumask_of(cpu));
+		virtqueue_set_affinity(vi->sq[i].vq, cpumask_of(cpu));
 		__netif_set_xps_queue(vi->dev, mask, i, false);
 		i++;
 	}
diff --git a/drivers/virtio/virtio_pci_common.c b/drivers/virtio/virtio_pci_common.c
index 705aebd74e56..465a6f5142cc 100644
--- a/drivers/virtio/virtio_pci_common.c
+++ b/drivers/virtio/virtio_pci_common.c
@@ -421,7 +421,7 @@ const char *vp_bus_name(struct virtio_device *vdev)
  * - OR over all affinities for shared MSI
  * - ignore the affinity request if we're using INTX
  */
-int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
+int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 {
 	struct virtio_device *vdev = vq->vdev;
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
@@ -435,11 +435,10 @@ int vp_set_vq_affinity(struct virtqueue *vq, int cpu)
 	if (vp_dev->msix_enabled) {
 		mask = vp_dev->msix_affinity_masks[info->msix_vector];
 		irq = pci_irq_vector(vp_dev->pci_dev, info->msix_vector);
-		if (cpu == -1)
+		if (!cpu_mask)
 			irq_set_affinity_hint(irq, NULL);
 		else {
-			cpumask_clear(mask);
-			cpumask_set_cpu(cpu, mask);
+			cpumask_copy(mask, cpu_mask);
 			irq_set_affinity_hint(irq, mask);
 		}
 	}
diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h
index 135ee3cf7175..02271002c2f3 100644
--- a/drivers/virtio/virtio_pci_common.h
+++ b/drivers/virtio/virtio_pci_common.h
@@ -141,7 +141,7 @@ const char *vp_bus_name(struct virtio_device *vdev);
  * - OR over all affinities for shared MSI
  * - ignore the affinity request if we're using INTX
  */
-int vp_set_vq_affinity(struct virtqueue *vq, int cpu);
+int vp_set_vq_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask);
 
 const struct cpumask *vp_get_vq_affinity(struct virtio_device *vdev, int index);
 
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 5559a2d31c46..32baf8e26735 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -79,7 +79,8 @@ struct virtio_config_ops {
 	u64 (*get_features)(struct virtio_device *vdev);
 	int (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
-	int (*set_vq_affinity)(struct virtqueue *vq, int cpu);
+	int (*set_vq_affinity)(struct virtqueue *vq,
+			       const struct cpumask *cpu_mask);
 	const struct cpumask *(*get_vq_affinity)(struct virtio_device *vdev,
 			int index);
 };
@@ -236,11 +237,11 @@ const char *virtio_bus_name(struct virtio_device *vdev)
  *
  */
 static inline
-int virtqueue_set_affinity(struct virtqueue *vq, int cpu)
+int virtqueue_set_affinity(struct virtqueue *vq, const struct cpumask *cpu_mask)
 {
 	struct virtio_device *vdev = vq->vdev;
 	if (vdev->config->set_vq_affinity)
-		return vdev->config->set_vq_affinity(vq, cpu);
+		return vdev->config->set_vq_affinity(vq, cpu_mask);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 2ca653d607ce59f2729173a7ea56dbfa6330ec88 Mon Sep 17 00:00:00 2001
From: Caleb Raitto <caraitto@google.com>
Date: Thu, 9 Aug 2018 17:28:40 -0700
Subject: virtio_net: Stripe queue affinities across cores.

Always set the affinity hint, even if #cpu != #vq.

Handle the case where #cpu > #vq (including when #cpu % #vq != 0) and
when #vq > #cpu (including when #vq % #cpu != 0).

Signed-off-by: Caleb Raitto <caraitto@google.com>
Signed-off-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jon Olson <jonolson@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 42 +++++++++++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 15 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 43fabc0eb4d2..eb00ae6ee475 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -31,6 +31,7 @@
 #include <linux/average.h>
 #include <linux/filter.h>
 #include <linux/netdevice.h>
+#include <linux/kernel.h>
 #include <linux/pci.h>
 #include <net/route.h>
 #include <net/xdp.h>
@@ -1888,30 +1889,41 @@ static void virtnet_clean_affinity(struct virtnet_info *vi, long hcpu)
 
 static void virtnet_set_affinity(struct virtnet_info *vi)
 {
-	int i;
-	int cpu;
+	cpumask_var_t mask;
+	int stragglers;
+	int group_size;
+	int i, j, cpu;
+	int num_cpu;
+	int stride;
 
-	/* In multiqueue mode, when the number of cpu is equal to the number of
-	 * queue pairs, we let the queue pairs to be private to one cpu by
-	 * setting the affinity hint to eliminate the contention.
-	 */
-	if (vi->curr_queue_pairs == 1 ||
-	    vi->max_queue_pairs != num_online_cpus()) {
+	if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) {
 		virtnet_clean_affinity(vi, -1);
 		return;
 	}
 
-	i = 0;
-	for_each_online_cpu(cpu) {
-		const unsigned long *mask = cpumask_bits(cpumask_of(cpu));
+	num_cpu = num_online_cpus();
+	stride = max_t(int, num_cpu / vi->curr_queue_pairs, 1);
+	stragglers = num_cpu >= vi->curr_queue_pairs ?
+			num_cpu % vi->curr_queue_pairs :
+			0;
+	cpu = cpumask_next(-1, cpu_online_mask);
 
-		virtqueue_set_affinity(vi->rq[i].vq, cpumask_of(cpu));
-		virtqueue_set_affinity(vi->sq[i].vq, cpumask_of(cpu));
-		__netif_set_xps_queue(vi->dev, mask, i, false);
-		i++;
+	for (i = 0; i < vi->curr_queue_pairs; i++) {
+		group_size = stride + (i < stragglers ? 1 : 0);
+
+		for (j = 0; j < group_size; j++) {
+			cpumask_set_cpu(cpu, mask);
+			cpu = cpumask_next_wrap(cpu, cpu_online_mask,
+						nr_cpu_ids, false);
+		}
+		virtqueue_set_affinity(vi->rq[i].vq, mask);
+		virtqueue_set_affinity(vi->sq[i].vq, mask);
+		__netif_set_xps_queue(vi->dev, cpumask_bits(mask), i, false);
+		cpumask_clear(mask);
 	}
 
 	vi->affinity_hint_set = true;
+	free_cpumask_var(mask);
 }
 
 static int virtnet_cpu_online(unsigned int cpu, struct hlist_node *node)
-- 
cgit v1.2.3


From 78aca3bbee880ea4d6f30d603c057058b03bdc77 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Fri, 10 Aug 2018 14:08:37 +0800
Subject: vxge: remove set but not used variable 'req_out', 'status' and 'ret'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/neterion/vxge/vxge-config.c:1097:6: warning:
 variable 'ret' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/neterion/vxge/vxge-config.c:2263:6: warning:
 variable 'req_out' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/neterion/vxge/vxge-config.c:2262:22: warning:
 variable 'status' set but not used [-Wunused-but-set-variable]
drivers/net/ethernet/neterion/vxge/vxge-config.c:2360:22: warning:
 variable 'status' set but not used [-Wunused-but-set-variable]
  enum vxge_hw_status status = VXGE_HW_OK;

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/neterion/vxge/vxge-config.c | 27 ++++++------------------
 1 file changed, 6 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c
index ae8149831e47..398011c87643 100644
--- a/drivers/net/ethernet/neterion/vxge/vxge-config.c
+++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c
@@ -1094,12 +1094,9 @@ static void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool)
 {
 	struct __vxge_hw_device *hldev;
 	struct list_head *p, *n;
-	u16 ret;
 
-	if (blockpool == NULL) {
-		ret = 1;
-		goto exit;
-	}
+	if (!blockpool)
+		return;
 
 	hldev = blockpool->hldev;
 
@@ -1122,8 +1119,7 @@ static void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool)
 		list_del(&((struct __vxge_hw_blockpool_entry *)p)->item);
 		kfree((void *)p);
 	}
-	ret = 0;
-exit:
+
 	return;
 }
 
@@ -2259,14 +2255,11 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 	struct __vxge_hw_blockpool *blockpool;
 	struct __vxge_hw_blockpool_entry *entry = NULL;
 	dma_addr_t dma_addr;
-	enum vxge_hw_status status = VXGE_HW_OK;
-	u32 req_out;
 
 	blockpool = &devh->block_pool;
 
 	if (block_addr == NULL) {
 		blockpool->req_out--;
-		status = VXGE_HW_FAIL;
 		goto exit;
 	}
 
@@ -2276,7 +2269,6 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 	if (unlikely(pci_dma_mapping_error(devh->pdev, dma_addr))) {
 		vxge_os_dma_free(devh->pdev, block_addr, &acc_handle);
 		blockpool->req_out--;
-		status = VXGE_HW_FAIL;
 		goto exit;
 	}
 
@@ -2291,7 +2283,7 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 	else
 		list_del(&entry->item);
 
-	if (entry != NULL) {
+	if (entry) {
 		entry->length = length;
 		entry->memblock = block_addr;
 		entry->dma_addr = dma_addr;
@@ -2299,13 +2291,10 @@ static void vxge_hw_blockpool_block_add(struct __vxge_hw_device *devh,
 		entry->dma_handle = dma_h;
 		list_add(&entry->item, &blockpool->free_block_list);
 		blockpool->pool_size++;
-		status = VXGE_HW_OK;
-	} else
-		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+	}
 
 	blockpool->req_out--;
 
-	req_out = blockpool->req_out;
 exit:
 	return;
 }
@@ -2357,7 +2346,6 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 	struct __vxge_hw_blockpool_entry *entry = NULL;
 	struct __vxge_hw_blockpool  *blockpool;
 	void *memblock = NULL;
-	enum vxge_hw_status status = VXGE_HW_OK;
 
 	blockpool = &devh->block_pool;
 
@@ -2367,10 +2355,8 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 						&dma_object->handle,
 						&dma_object->acc_handle);
 
-		if (memblock == NULL) {
-			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		if (!memblock)
 			goto exit;
-		}
 
 		dma_object->addr = pci_map_single(devh->pdev, memblock, size,
 					PCI_DMA_BIDIRECTIONAL);
@@ -2379,7 +2365,6 @@ static void *__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
 				dma_object->addr))) {
 			vxge_os_dma_free(devh->pdev, memblock,
 				&dma_object->acc_handle);
-			status = VXGE_HW_ERR_OUT_OF_MEMORY;
 			goto exit;
 		}
 
-- 
cgit v1.2.3


From 63ae7949e94aad607c24d00b8ce3f5661c0a1e9d Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Fri, 10 Aug 2018 09:12:38 +0300
Subject: net: socionext: Use descriptor info instead of MMIO reads on Rx

MMIO reads for remaining packets in queue occur (at least)twice per
invocation of netsec_process_rx(). We can use the packet descriptor to
identify if it's owned by the hardware and break out, avoiding the more
expensive MMIO read operations. This has a ~2% increase on the pps of the
Rx path when tested with 64byte packets

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 25 ++++++++++---------------
 1 file changed, 10 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 01589b6982e4..334b6189b011 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -642,8 +642,6 @@ static struct sk_buff *netsec_get_rx_pkt_data(struct netsec_priv *priv,
 
 	tmp_skb = netsec_alloc_skb(priv, &td);
 
-	dma_rmb();
-
 	tail = dring->tail;
 
 	if (!tmp_skb) {
@@ -657,8 +655,6 @@ static struct sk_buff *netsec_get_rx_pkt_data(struct netsec_priv *priv,
 	/* move tail ahead */
 	dring->tail = (dring->tail + 1) % DESC_NUM;
 
-	dring->pkt_cnt--;
-
 	return skb;
 }
 
@@ -731,25 +727,24 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 	struct netsec_desc_ring *dring = &priv->desc_ring[NETSEC_RING_RX];
 	struct net_device *ndev = priv->ndev;
 	struct netsec_rx_pkt_info rx_info;
-	int done = 0, rx_num = 0;
+	int done = 0;
 	struct netsec_desc desc;
 	struct sk_buff *skb;
 	u16 len;
 
 	while (done < budget) {
-		if (!rx_num) {
-			rx_num = netsec_read(priv, NETSEC_REG_NRM_RX_PKTCNT);
-			dring->pkt_cnt += rx_num;
+		u16 idx = dring->tail;
+		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 
-			/* move head 'rx_num' */
-			dring->head = (dring->head + rx_num) % DESC_NUM;
+		if (de->attr & (1U << NETSEC_RX_PKT_OWN_FIELD))
+			break;
 
-			rx_num = dring->pkt_cnt;
-			if (!rx_num)
-				break;
-		}
+		/* This  barrier is needed to keep us from reading
+		 * any other fields out of the netsec_de until we have
+		 * verified the descriptor has been written back
+		 */
+		dma_rmb();
 		done++;
-		rx_num--;
 		skb = netsec_get_rx_pkt_data(priv, &rx_info, &desc, &len);
 		if (unlikely(!skb) || rx_info.err_flag) {
 			netif_err(priv, drv, priv->ndev,
-- 
cgit v1.2.3


From b6311b7bea41963c81da3ab58730dcc3c1aa388e Mon Sep 17 00:00:00 2001
From: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Date: Fri, 10 Aug 2018 09:12:39 +0300
Subject: net: socionext: Increase descriptors to 256

Increasing descriptors to 256 from 128 and adjusting the NAPI weight
to 64 increases performace on Rx by ~20% on 64byte packets

Signed-off-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/socionext/netsec.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index 334b6189b011..7aa5ebb6766c 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -232,8 +232,7 @@
 #define NETSEC_EEPROM_PKT_ME_ADDRESS		0x20
 #define NETSEC_EEPROM_PKT_ME_SIZE		0x24
 
-#define DESC_NUM	128
-#define NAPI_BUDGET	(DESC_NUM / 2)
+#define DESC_NUM	256
 
 #define DESC_SZ	sizeof(struct netsec_de)
 
@@ -1659,7 +1658,7 @@ static int netsec_probe(struct platform_device *pdev)
 	dev_info(&pdev->dev, "hardware revision %d.%d\n",
 		 hw_ver >> 16, hw_ver & 0xffff);
 
-	netif_napi_add(ndev, &priv->napi, netsec_napi_poll, NAPI_BUDGET);
+	netif_napi_add(ndev, &priv->napi, netsec_napi_poll, NAPI_POLL_WEIGHT);
 
 	ndev->netdev_ops = &netsec_netdev_ops;
 	ndev->ethtool_ops = &netsec_ethtool_ops;
-- 
cgit v1.2.3


From d6a61ec936676dbe25a6eb76e1229787dc2fbba8 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:21:55 +0200
Subject: l2tp: define l2tp_tunnel_uses_xfrm()

Use helper function to figure out if a tunnel is using ipsec.
Also, avoid accessing ->sk_policy directly since it's RCU protected.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.h    | 19 +++++++++++++++++++
 net/l2tp/l2tp_netlink.c |  7 +------
 net/l2tp/l2tp_ppp.c     |  5 +----
 3 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 5804065dfbfb..04a9488c54b4 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -15,6 +15,10 @@
 #include <net/dst.h>
 #include <net/sock.h>
 
+#ifdef CONFIG_XFRM
+#include <net/xfrm.h>
+#endif
+
 /* Just some random numbers */
 #define L2TP_TUNNEL_MAGIC	0x42114DDA
 #define L2TP_SESSION_MAGIC	0x0C04EB7D
@@ -284,6 +288,21 @@ static inline u32 l2tp_tunnel_dst_mtu(const struct l2tp_tunnel *tunnel)
 	return mtu;
 }
 
+#ifdef CONFIG_XFRM
+static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
+{
+	struct sock *sk = tunnel->sock;
+
+	return sk && (rcu_access_pointer(sk->sk_policy[0]) ||
+		      rcu_access_pointer(sk->sk_policy[1]));
+}
+#else
+static inline bool l2tp_tunnel_uses_xfrm(const struct l2tp_tunnel *tunnel)
+{
+	return false;
+}
+#endif
+
 #define l2tp_printk(ptr, type, func, fmt, ...)				\
 do {									\
 	if (((ptr)->debug) & (type))					\
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 2e1e92651545..357503e5acd5 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -710,9 +710,6 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	void *hdr;
 	struct nlattr *nest;
 	struct l2tp_tunnel *tunnel = session->tunnel;
-	struct sock *sk = NULL;
-
-	sk = tunnel->sock;
 
 	hdr = genlmsg_put(skb, portid, seq, &l2tp_nl_family, flags, cmd);
 	if (!hdr)
@@ -738,10 +735,8 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl
 	    nla_put_u8(skb, L2TP_ATTR_RECV_SEQ, session->recv_seq) ||
 	    nla_put_u8(skb, L2TP_ATTR_SEND_SEQ, session->send_seq) ||
 	    nla_put_u8(skb, L2TP_ATTR_LNS_MODE, session->lns_mode) ||
-#ifdef CONFIG_XFRM
-	    (((sk) && (sk->sk_policy[0] || sk->sk_policy[1])) &&
+	    (l2tp_tunnel_uses_xfrm(tunnel) &&
 	     nla_put_u8(skb, L2TP_ATTR_USING_IPSEC, 1)) ||
-#endif
 	    (session->reorder_timeout &&
 	     nla_put_msecs(skb, L2TP_ATTR_RECV_TIMEOUT,
 			   session->reorder_timeout, L2TP_ATTR_PAD)))
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 6e2c8e7595e0..c33ef9a3f3b5 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -95,7 +95,6 @@
 #include <net/netns/generic.h>
 #include <net/ip.h>
 #include <net/udp.h>
-#include <net/xfrm.h>
 #include <net/inet_common.h>
 
 #include <asm/byteorder.h>
@@ -1153,9 +1152,7 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
 			l2tp_session_dec_refcount(session);
 			break;
 		}
-#ifdef CONFIG_XFRM
-		stats.using_ipsec = (sk->sk_policy[0] || sk->sk_policy[1]) ? 1 : 0;
-#endif
+		stats.using_ipsec = l2tp_tunnel_uses_xfrm(tunnel);
 		pppol2tp_copy_stats(&stats, &tunnel->stats);
 		if (copy_to_user((void __user *) arg, &stats, sizeof(stats))) {
 			err = -EFAULT;
-- 
cgit v1.2.3


From 01e28b921b19cb99a09dda89ab0e5dc49bf4ab38 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:21:57 +0200
Subject: l2tp: split l2tp_session_get()

l2tp_session_get() is used for two different purposes. If 'tunnel' is
NULL, the session is searched globally in the supplied network
namespace. Otherwise it is searched exclusively in the tunnel context.

Callers always know the context in which they need to search the
session. But some of them do provide both a namespace and a tunnel,
making the semantic of the call unclear.

This patch defines l2tp_tunnel_get_session() for lookups done in a
tunnel and restricts l2tp_session_get() to namespace searches.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c    | 50 ++++++++++++++++++++++++-------------------------
 net/l2tp/l2tp_core.h    |  6 +++---
 net/l2tp/l2tp_ip.c      |  2 +-
 net/l2tp/l2tp_ip6.c     |  2 +-
 net/l2tp/l2tp_netlink.c |  4 ++--
 net/l2tp/l2tp_ppp.c     |  8 ++++----
 6 files changed, 36 insertions(+), 36 deletions(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index ac6a00bcec71..2bd701a58aa6 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -203,44 +203,44 @@ struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth)
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_get_nth);
 
-/* Lookup a session. A new reference is held on the returned session. */
-struct l2tp_session *l2tp_session_get(const struct net *net,
-				      struct l2tp_tunnel *tunnel,
-				      u32 session_id)
+struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel,
+					     u32 session_id)
 {
 	struct hlist_head *session_list;
 	struct l2tp_session *session;
 
-	if (!tunnel) {
-		struct l2tp_net *pn = l2tp_pernet(net);
-
-		session_list = l2tp_session_id_hash_2(pn, session_id);
+	session_list = l2tp_session_id_hash(tunnel, session_id);
 
-		rcu_read_lock_bh();
-		hlist_for_each_entry_rcu(session, session_list, global_hlist) {
-			if (session->session_id == session_id) {
-				l2tp_session_inc_refcount(session);
-				rcu_read_unlock_bh();
+	read_lock_bh(&tunnel->hlist_lock);
+	hlist_for_each_entry(session, session_list, hlist)
+		if (session->session_id == session_id) {
+			l2tp_session_inc_refcount(session);
+			read_unlock_bh(&tunnel->hlist_lock);
 
-				return session;
-			}
+			return session;
 		}
-		rcu_read_unlock_bh();
+	read_unlock_bh(&tunnel->hlist_lock);
 
-		return NULL;
-	}
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(l2tp_tunnel_get_session);
 
-	session_list = l2tp_session_id_hash(tunnel, session_id);
-	read_lock_bh(&tunnel->hlist_lock);
-	hlist_for_each_entry(session, session_list, hlist) {
+struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id)
+{
+	struct hlist_head *session_list;
+	struct l2tp_session *session;
+
+	session_list = l2tp_session_id_hash_2(l2tp_pernet(net), session_id);
+
+	rcu_read_lock_bh();
+	hlist_for_each_entry_rcu(session, session_list, global_hlist)
 		if (session->session_id == session_id) {
 			l2tp_session_inc_refcount(session);
-			read_unlock_bh(&tunnel->hlist_lock);
+			rcu_read_unlock_bh();
 
 			return session;
 		}
-	}
-	read_unlock_bh(&tunnel->hlist_lock);
+	rcu_read_unlock_bh();
 
 	return NULL;
 }
@@ -872,7 +872,7 @@ static int l2tp_udp_recv_core(struct l2tp_tunnel *tunnel, struct sk_buff *skb)
 	}
 
 	/* Find the session context */
-	session = l2tp_session_get(tunnel->l2tp_net, tunnel, session_id);
+	session = l2tp_tunnel_get_session(tunnel, session_id);
 	if (!session || !session->recv_skb) {
 		if (session)
 			l2tp_session_dec_refcount(session);
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 04a9488c54b4..8480a0af973e 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -196,12 +196,12 @@ static inline void *l2tp_session_priv(struct l2tp_session *session)
 
 struct l2tp_tunnel *l2tp_tunnel_get(const struct net *net, u32 tunnel_id);
 struct l2tp_tunnel *l2tp_tunnel_get_nth(const struct net *net, int nth);
+struct l2tp_session *l2tp_tunnel_get_session(struct l2tp_tunnel *tunnel,
+					     u32 session_id);
 
 void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
 
-struct l2tp_session *l2tp_session_get(const struct net *net,
-				      struct l2tp_tunnel *tunnel,
-				      u32 session_id);
+struct l2tp_session *l2tp_session_get(const struct net *net, u32 session_id);
 struct l2tp_session *l2tp_session_get_nth(struct l2tp_tunnel *tunnel, int nth);
 struct l2tp_session *l2tp_session_get_by_ifname(const struct net *net,
 						const char *ifname);
diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c
index 0bc39cc20a3f..35f6f86d4dcc 100644
--- a/net/l2tp/l2tp_ip.c
+++ b/net/l2tp/l2tp_ip.c
@@ -144,7 +144,7 @@ static int l2tp_ip_recv(struct sk_buff *skb)
 	}
 
 	/* Ok, this is a data packet. Lookup the session. */
-	session = l2tp_session_get(net, NULL, session_id);
+	session = l2tp_session_get(net, session_id);
 	if (!session)
 		goto discard;
 
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index 42f828cf62fb..237f1a4a0b0c 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -157,7 +157,7 @@ static int l2tp_ip6_recv(struct sk_buff *skb)
 	}
 
 	/* Ok, this is a data packet. Lookup the session. */
-	session = l2tp_session_get(net, NULL, session_id);
+	session = l2tp_session_get(net, session_id);
 	if (!session)
 		goto discard;
 
diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c
index 357503e5acd5..edbd5d1fbcde 100644
--- a/net/l2tp/l2tp_netlink.c
+++ b/net/l2tp/l2tp_netlink.c
@@ -66,7 +66,7 @@ static struct l2tp_session *l2tp_nl_session_get(struct genl_info *info)
 		session_id = nla_get_u32(info->attrs[L2TP_ATTR_SESSION_ID]);
 		tunnel = l2tp_tunnel_get(net, tunnel_id);
 		if (tunnel) {
-			session = l2tp_session_get(net, tunnel, session_id);
+			session = l2tp_tunnel_get_session(tunnel, session_id);
 			l2tp_tunnel_dec_refcount(tunnel);
 		}
 	}
@@ -627,7 +627,7 @@ static int l2tp_nl_cmd_session_create(struct sk_buff *skb, struct genl_info *inf
 							   &cfg);
 
 	if (ret >= 0) {
-		session = l2tp_session_get(net, tunnel, session_id);
+		session = l2tp_tunnel_get_session(tunnel, session_id);
 		if (session) {
 			ret = l2tp_session_notify(&l2tp_nl_family, info, session,
 						  L2TP_CMD_SESSION_CREATE);
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index c33ef9a3f3b5..cd43d02484e4 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -757,7 +757,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	if (tunnel->peer_tunnel_id == 0)
 		tunnel->peer_tunnel_id = info.peer_tunnel_id;
 
-	session = l2tp_session_get(sock_net(sk), tunnel, info.session_id);
+	session = l2tp_tunnel_get_session(tunnel, info.session_id);
 	if (session) {
 		drop_refcnt = true;
 
@@ -1134,10 +1134,10 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
 		}
 		if (stats.session_id != 0) {
 			/* resend to session ioctl handler */
-			struct l2tp_session *session =
-				l2tp_session_get(sock_net(sk), tunnel,
-						 stats.session_id);
+			struct l2tp_session *session;
 
+			session = l2tp_tunnel_get_session(tunnel,
+							  stats.session_id);
 			if (!session) {
 				err = -EBADR;
 				break;
-- 
cgit v1.2.3


From bdd0292f96e43de46283ea0efdef8d13b4ffe895 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:21:58 +0200
Subject: l2tp: simplify pppol2tp_ioctl()

* Drop test on 'sk': sock->sk cannot be NULL, or pppox_ioctl() could
    not have called us.

  * Drop test on 'SOCK_DEAD' state: if this flag was set, the socket
    would be in the process of being released and no ioctl could be
    running anymore.

  * Drop test on 'PPPOX_*' state: we depend on ->sk_user_data to get
    the session structure. If it is non-NULL, then the socket is
    connected. Testing for PPPOX_* is redundant.

  * Retrieve session using ->sk_user_data directly, instead of going
    through pppol2tp_sock_to_session(). This avoids grabbing a useless
    reference on the socket.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 33 ++++++---------------------------
 1 file changed, 6 insertions(+), 27 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index cd43d02484e4..e3ed8d473d91 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1179,28 +1179,12 @@ static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
 static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 			  unsigned long arg)
 {
-	struct sock *sk = sock->sk;
 	struct l2tp_session *session;
 	struct l2tp_tunnel *tunnel;
-	int err;
-
-	if (!sk)
-		return 0;
-
-	err = -EBADF;
-	if (sock_flag(sk, SOCK_DEAD) != 0)
-		goto end;
-
-	err = -ENOTCONN;
-	if ((sk->sk_user_data == NULL) ||
-	    (!(sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND))))
-		goto end;
 
-	/* Get session context from the socket */
-	err = -EBADF;
-	session = pppol2tp_sock_to_session(sk);
-	if (session == NULL)
-		goto end;
+	session = sock->sk->sk_user_data;
+	if (!session)
+		return -ENOTCONN;
 
 	/* Special case: if session's session_id is zero, treat ioctl as a
 	 * tunnel ioctl
@@ -1208,16 +1192,11 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 	if ((session->session_id == 0) &&
 	    (session->peer_session_id == 0)) {
 		tunnel = session->tunnel;
-		err = pppol2tp_tunnel_ioctl(tunnel, cmd, arg);
-		goto end_put_sess;
-	}
 
-	err = pppol2tp_session_ioctl(session, cmd, arg);
+		return pppol2tp_tunnel_ioctl(tunnel, cmd, arg);
+	}
 
-end_put_sess:
-	sock_put(sk);
-end:
-	return err;
+	return pppol2tp_session_ioctl(session, cmd, arg);
 }
 
 /*****************************************************************************
-- 
cgit v1.2.3


From 79e6760e64d1b69a20af4d97ead291159d4c11c2 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:21:58 +0200
Subject: l2tp: handle PPPIOC[GS]MRU and PPPIOC[GS]FLAGS in pppol2tp_ioctl()

Let pppol2tp_ioctl() handle ioctl commands directly. It still relies on
pppol2tp_{session,tunnel}_ioctl() for PPPIOCGL2TPSTATS.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 73 ++++++++++++++++++++++++++++++++---------------------
 1 file changed, 44 insertions(+), 29 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index e3ed8d473d91..f4ec6b2a093e 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1045,7 +1045,6 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 {
 	int err = 0;
 	struct sock *sk;
-	int val = (int) arg;
 	struct l2tp_tunnel *tunnel = session->tunnel;
 	struct pppol2tp_ioc_stats stats;
 
@@ -1058,22 +1057,6 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 		return -EBADR;
 
 	switch (cmd) {
-	case PPPIOCGMRU:
-	case PPPIOCGFLAGS:
-		err = -EFAULT;
-		if (put_user(0, (int __user *)arg))
-			break;
-		err = 0;
-		break;
-
-	case PPPIOCSMRU:
-	case PPPIOCSFLAGS:
-		err = -EFAULT;
-		if (get_user(val, (int __user *)arg))
-			break;
-		err = 0;
-		break;
-
 	case PPPIOCGL2TPSTATS:
 		err = -ENXIO;
 		if (!(sk->sk_state & PPPOX_CONNECTED))
@@ -1180,23 +1163,55 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 			  unsigned long arg)
 {
 	struct l2tp_session *session;
-	struct l2tp_tunnel *tunnel;
+	int val;
+
+	switch (cmd) {
+	case PPPIOCGMRU:
+	case PPPIOCGFLAGS:
+		session = sock->sk->sk_user_data;
+		if (!session)
+			return -ENOTCONN;
 
-	session = sock->sk->sk_user_data;
-	if (!session)
-		return -ENOTCONN;
+		/* Not defined for tunnels */
+		if (!session->session_id && !session->peer_session_id)
+			return -ENOSYS;
 
-	/* Special case: if session's session_id is zero, treat ioctl as a
-	 * tunnel ioctl
-	 */
-	if ((session->session_id == 0) &&
-	    (session->peer_session_id == 0)) {
-		tunnel = session->tunnel;
+		if (put_user(0, (int __user *)arg))
+			return -EFAULT;
+		break;
+
+	case PPPIOCSMRU:
+	case PPPIOCSFLAGS:
+		session = sock->sk->sk_user_data;
+		if (!session)
+			return -ENOTCONN;
 
-		return pppol2tp_tunnel_ioctl(tunnel, cmd, arg);
+		/* Not defined for tunnels */
+		if (!session->session_id && !session->peer_session_id)
+			return -ENOSYS;
+
+		if (get_user(val, (int __user *)arg))
+			return -EFAULT;
+		break;
+
+	case PPPIOCGL2TPSTATS:
+		session = sock->sk->sk_user_data;
+		if (!session)
+			return -ENOTCONN;
+
+		/* Session 0 represents the parent tunnel */
+		if (!session->session_id && !session->peer_session_id)
+			return pppol2tp_tunnel_ioctl(session->tunnel, cmd,
+						     arg);
+		else
+			return pppol2tp_session_ioctl(session, cmd, arg);
+		break;
+
+	default:
+		return -ENOSYS;
 	}
 
-	return pppol2tp_session_ioctl(session, cmd, arg);
+	return 0;
 }
 
 /*****************************************************************************
-- 
cgit v1.2.3


From 528534f0deda05c668756313a22974429a9df05a Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:22:00 +0200
Subject: l2tp: remove pppol2tp_tunnel_ioctl()

Handle PPPIOCGL2TPSTATS in pppol2tp_ioctl() if the socket represents a
tunnel. This one is a bit special because the caller may use the tunnel
socket to retrieve statistics of one of its sessions. If the session_id
is set, the corresponding session's statistics are returned, instead of
those of the tunnel. This is handled by the new
pppol2tp_tunnel_copy_stats() helper function.

Set ->tunnel_id and ->using_ipsec out of the conditional, so
that it can be used by the 'else' branch in the following patch.
We cannot do that for ->session_id, because tunnel sockets have to
report the value that was originally passed in 'stats.session_id',
while session sockets have to report their own session_id.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 132 +++++++++++++++++++++-------------------------------
 1 file changed, 53 insertions(+), 79 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index f4ec6b2a093e..2afd3ab8a551 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1038,6 +1038,36 @@ static void pppol2tp_copy_stats(struct pppol2tp_ioc_stats *dest,
 	dest->rx_errors = atomic_long_read(&stats->rx_errors);
 }
 
+static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats,
+				      struct l2tp_tunnel *tunnel)
+{
+	struct l2tp_session *session;
+
+	if (!stats->session_id) {
+		memset(stats, 0, sizeof(*stats));
+		pppol2tp_copy_stats(stats, &tunnel->stats);
+		return 0;
+	}
+
+	/* If session_id is set, search the corresponding session in the
+	 * context of this tunnel and record the session's statistics.
+	 */
+	session = l2tp_tunnel_get_session(tunnel, stats->session_id);
+	if (!session)
+		return -EBADR;
+
+	if (session->pwtype != L2TP_PWTYPE_PPP) {
+		l2tp_session_dec_refcount(session);
+		return -EBADR;
+	}
+
+	memset(stats, 0, sizeof(*stats));
+	pppol2tp_copy_stats(stats, &session->stats);
+	l2tp_session_dec_refcount(session);
+
+	return 0;
+}
+
 /* Session ioctl helper.
  */
 static int pppol2tp_session_ioctl(struct l2tp_session *session,
@@ -1084,84 +1114,10 @@ static int pppol2tp_session_ioctl(struct l2tp_session *session,
 	return err;
 }
 
-/* Tunnel ioctl helper.
- *
- * Note the special handling for PPPIOCGL2TPSTATS below. If the ioctl data
- * specifies a session_id, the session ioctl handler is called. This allows an
- * application to retrieve session stats via a tunnel socket.
- */
-static int pppol2tp_tunnel_ioctl(struct l2tp_tunnel *tunnel,
-				 unsigned int cmd, unsigned long arg)
-{
-	int err = 0;
-	struct sock *sk;
-	struct pppol2tp_ioc_stats stats;
-
-	l2tp_dbg(tunnel, L2TP_MSG_CONTROL,
-		 "%s: pppol2tp_tunnel_ioctl(cmd=%#x, arg=%#lx)\n",
-		 tunnel->name, cmd, arg);
-
-	sk = tunnel->sock;
-	sock_hold(sk);
-
-	switch (cmd) {
-	case PPPIOCGL2TPSTATS:
-		err = -ENXIO;
-		if (!(sk->sk_state & PPPOX_CONNECTED))
-			break;
-
-		if (copy_from_user(&stats, (void __user *) arg,
-				   sizeof(stats))) {
-			err = -EFAULT;
-			break;
-		}
-		if (stats.session_id != 0) {
-			/* resend to session ioctl handler */
-			struct l2tp_session *session;
-
-			session = l2tp_tunnel_get_session(tunnel,
-							  stats.session_id);
-			if (!session) {
-				err = -EBADR;
-				break;
-			}
-			if (session->pwtype != L2TP_PWTYPE_PPP) {
-				l2tp_session_dec_refcount(session);
-				err = -EBADR;
-				break;
-			}
-
-			err = pppol2tp_session_ioctl(session, cmd, arg);
-			l2tp_session_dec_refcount(session);
-			break;
-		}
-		stats.using_ipsec = l2tp_tunnel_uses_xfrm(tunnel);
-		pppol2tp_copy_stats(&stats, &tunnel->stats);
-		if (copy_to_user((void __user *) arg, &stats, sizeof(stats))) {
-			err = -EFAULT;
-			break;
-		}
-		l2tp_info(tunnel, L2TP_MSG_CONTROL, "%s: get L2TP stats\n",
-			  tunnel->name);
-		err = 0;
-		break;
-
-	default:
-		err = -ENOSYS;
-		break;
-	}
-
-	sock_put(sk);
-
-	return err;
-}
-
-/* Main ioctl() handler.
- * Dispatch to tunnel or session helpers depending on the socket.
- */
 static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 			  unsigned long arg)
 {
+	struct pppol2tp_ioc_stats stats;
 	struct l2tp_session *session;
 	int val;
 
@@ -1200,11 +1156,29 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 			return -ENOTCONN;
 
 		/* Session 0 represents the parent tunnel */
-		if (!session->session_id && !session->peer_session_id)
-			return pppol2tp_tunnel_ioctl(session->tunnel, cmd,
-						     arg);
-		else
+		if (!session->session_id && !session->peer_session_id) {
+			u32 session_id;
+			int err;
+
+			if (copy_from_user(&stats, (void __user *)arg,
+					   sizeof(stats)))
+				return -EFAULT;
+
+			session_id = stats.session_id;
+			err = pppol2tp_tunnel_copy_stats(&stats,
+							 session->tunnel);
+			if (err < 0)
+				return err;
+
+			stats.session_id = session_id;
+		} else {
 			return pppol2tp_session_ioctl(session, cmd, arg);
+		}
+		stats.tunnel_id = session->tunnel->tunnel_id;
+		stats.using_ipsec = l2tp_tunnel_uses_xfrm(session->tunnel);
+
+		if (copy_to_user((void __user *)arg, &stats, sizeof(stats)))
+			return -EFAULT;
 		break;
 
 	default:
-- 
cgit v1.2.3


From b0e29063dcb3bf14f515f95e748b60e4bab45e7c Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:22:01 +0200
Subject: l2tp: remove pppol2tp_session_ioctl()

pppol2tp_ioctl() has everything in place for handling PPPIOCGL2TPSTATS
on session sockets. We just need to copy the stats and set ->session_id.

As a side effect of sharing session and tunnel code, ->using_ipsec is
properly set even when the request was made using a session socket.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/uapi/linux/ppp-ioctl.h |  2 +-
 net/l2tp/l2tp_ppp.c            | 50 +++---------------------------------------
 2 files changed, 4 insertions(+), 48 deletions(-)

diff --git a/include/uapi/linux/ppp-ioctl.h b/include/uapi/linux/ppp-ioctl.h
index 784c2e3e572e..88b5f9990320 100644
--- a/include/uapi/linux/ppp-ioctl.h
+++ b/include/uapi/linux/ppp-ioctl.h
@@ -68,7 +68,7 @@ struct ppp_option_data {
 struct pppol2tp_ioc_stats {
 	__u16		tunnel_id;	/* redundant */
 	__u16		session_id;	/* if zero, get tunnel stats */
-	__u32		using_ipsec:1;	/* valid only for session_id == 0 */
+	__u32		using_ipsec:1;
 	__aligned_u64	tx_packets;
 	__aligned_u64	tx_bytes;
 	__aligned_u64	tx_errors;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 2afd3ab8a551..bdfbd3ed7e14 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1068,52 +1068,6 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats,
 	return 0;
 }
 
-/* Session ioctl helper.
- */
-static int pppol2tp_session_ioctl(struct l2tp_session *session,
-				  unsigned int cmd, unsigned long arg)
-{
-	int err = 0;
-	struct sock *sk;
-	struct l2tp_tunnel *tunnel = session->tunnel;
-	struct pppol2tp_ioc_stats stats;
-
-	l2tp_dbg(session, L2TP_MSG_CONTROL,
-		 "%s: pppol2tp_session_ioctl(cmd=%#x, arg=%#lx)\n",
-		 session->name, cmd, arg);
-
-	sk = pppol2tp_session_get_sock(session);
-	if (!sk)
-		return -EBADR;
-
-	switch (cmd) {
-	case PPPIOCGL2TPSTATS:
-		err = -ENXIO;
-		if (!(sk->sk_state & PPPOX_CONNECTED))
-			break;
-
-		memset(&stats, 0, sizeof(stats));
-		stats.tunnel_id = tunnel->tunnel_id;
-		stats.session_id = session->session_id;
-		pppol2tp_copy_stats(&stats, &session->stats);
-		if (copy_to_user((void __user *) arg, &stats,
-				 sizeof(stats)))
-			break;
-		l2tp_info(session, L2TP_MSG_CONTROL, "%s: get L2TP stats\n",
-			  session->name);
-		err = 0;
-		break;
-
-	default:
-		err = -ENOSYS;
-		break;
-	}
-
-	sock_put(sk);
-
-	return err;
-}
-
 static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 			  unsigned long arg)
 {
@@ -1172,7 +1126,9 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 
 			stats.session_id = session_id;
 		} else {
-			return pppol2tp_session_ioctl(session, cmd, arg);
+			memset(&stats, 0, sizeof(stats));
+			pppol2tp_copy_stats(&stats, &session->stats);
+			stats.session_id = session->session_id;
 		}
 		stats.tunnel_id = session->tunnel->tunnel_id;
 		stats.using_ipsec = l2tp_tunnel_uses_xfrm(session->tunnel);
-- 
cgit v1.2.3


From 7390ed8a405013d0a7e1f4dc8ac495e0ac04996f Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:22:02 +0200
Subject: l2tp: zero out stats in pppol2tp_copy_stats()

Integrate memset(0) in pppol2tp_copy_stats() to avoid calling it
manually every time.

While there, constify 'stats'.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index bdfbd3ed7e14..e2eea60bf875 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1026,8 +1026,10 @@ end:
  ****************************************************************************/
 
 static void pppol2tp_copy_stats(struct pppol2tp_ioc_stats *dest,
-				struct l2tp_stats *stats)
+				const struct l2tp_stats *stats)
 {
+	memset(dest, 0, sizeof(*dest));
+
 	dest->tx_packets = atomic_long_read(&stats->tx_packets);
 	dest->tx_bytes = atomic_long_read(&stats->tx_bytes);
 	dest->tx_errors = atomic_long_read(&stats->tx_errors);
@@ -1044,7 +1046,6 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats,
 	struct l2tp_session *session;
 
 	if (!stats->session_id) {
-		memset(stats, 0, sizeof(*stats));
 		pppol2tp_copy_stats(stats, &tunnel->stats);
 		return 0;
 	}
@@ -1061,7 +1062,6 @@ static int pppol2tp_tunnel_copy_stats(struct pppol2tp_ioc_stats *stats,
 		return -EBADR;
 	}
 
-	memset(stats, 0, sizeof(*stats));
 	pppol2tp_copy_stats(stats, &session->stats);
 	l2tp_session_dec_refcount(session);
 
@@ -1126,7 +1126,6 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 
 			stats.session_id = session_id;
 		} else {
-			memset(&stats, 0, sizeof(stats));
 			pppol2tp_copy_stats(&stats, &session->stats);
 			stats.session_id = session->session_id;
 		}
-- 
cgit v1.2.3


From 4f5f85e9a70e13c8919e26609914253d18fbf858 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <g.nault@alphalink.fr>
Date: Fri, 10 Aug 2018 13:22:03 +0200
Subject: l2tp: let pppol2tp_ioctl() fallback to dev_ioctl()

Return -ENOIOCTLCMD for unknown ioctl commands. This lets dev_ioctl()
handle generic socket ioctls like SIOCGIFNAME or SIOCGIFINDEX.
PF_PPPOX/PX_PROTO_OL2TP was one of the few socket types not honouring
this mechanism.

Signed-off-by: Guillaume Nault <g.nault@alphalink.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_ppp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index e2eea60bf875..62f2d3f1e431 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -1137,7 +1137,7 @@ static int pppol2tp_ioctl(struct socket *sock, unsigned int cmd,
 		break;
 
 	default:
-		return -ENOSYS;
+		return -ENOIOCTLCMD;
 	}
 
 	return 0;
-- 
cgit v1.2.3


From b70f1f3af47f4a21a25678f9ee587ed7986d62f8 Mon Sep 17 00:00:00 2001
From: Keara Leibovitz <kleib@mojatatu.com>
Date: Fri, 10 Aug 2018 10:09:41 -0400
Subject: tc: Update README and add config

Updated README.

Added config file that contains the minimum required features enabled to
run the tests currently present in the kernel.
This must be updated when new unittests are created and require their own
modules.

Signed-off-by: Keara Leibovitz <kleib@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/tc-testing/README | 16 +++++++----
 tools/testing/selftests/tc-testing/config | 48 +++++++++++++++++++++++++++++++
 2 files changed, 59 insertions(+), 5 deletions(-)
 create mode 100644 tools/testing/selftests/tc-testing/config

diff --git a/tools/testing/selftests/tc-testing/README b/tools/testing/selftests/tc-testing/README
index 3a0336782d2d..49a6f8c3fdae 100644
--- a/tools/testing/selftests/tc-testing/README
+++ b/tools/testing/selftests/tc-testing/README
@@ -17,6 +17,10 @@ REQUIREMENTS
 *  The kernel must have veth support available, as a veth pair is created
    prior to running the tests.
 
+*  The kernel must have the appropriate infrastructure enabled to run all tdc
+   unit tests. See the config file in this directory for minimum required
+   features. As new tests will be added, config options list will be updated.
+
 *  All tc-related features being tested must be built in or available as
    modules.  To check what is required in current setup run:
    ./tdc.py -c
@@ -109,8 +113,8 @@ COMMAND LINE ARGUMENTS
 Run tdc.py -h to see the full list of available arguments.
 
 usage: tdc.py [-h] [-p PATH] [-D DIR [DIR ...]] [-f FILE [FILE ...]]
-              [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v]
-              [-d DEVICE] [-n NS] [-V]
+              [-c [CATG [CATG ...]]] [-e ID [ID ...]] [-l] [-s] [-i] [-v] [-N]
+              [-d DEVICE] [-P] [-n] [-V]
 
 Linux TC unit tests
 
@@ -118,8 +122,10 @@ optional arguments:
   -h, --help            show this help message and exit
   -p PATH, --path PATH  The full path to the tc executable to use
   -v, --verbose         Show the commands that are being run
+  -N, --notap           Suppress tap results for command under test
   -d DEVICE, --device DEVICE
                         Execute the test case in flower category
+  -P, --pause           Pause execution just before post-suite stage
 
 selection:
   select which test cases: files plus directories; filtered by categories
@@ -146,10 +152,10 @@ action:
   -i, --id              Generate ID numbers for new test cases
 
 netns:
-  options for nsPlugin(run commands in net namespace)
+  options for nsPlugin (run commands in net namespace)
 
-  -n NS, --namespace NS
-                        Run commands in namespace NS
+  -n, --namespace
+                        Run commands in namespace as specified in tdc_config.py
 
 valgrind:
   options for valgrindPlugin (run command under test under Valgrind)
diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
new file mode 100644
index 000000000000..203302065458
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/config
@@ -0,0 +1,48 @@
+CONFIG_NET_SCHED=y
+
+#
+# Queueing/Scheduling
+#
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NET_SCH_INGRESS=m
+
+#
+# Classification
+#
+CONFIG_NET_CLS=y
+CONFIG_NET_CLS_FW=m
+CONFIG_NET_CLS_U32=m
+CONFIG_CLS_U32_PERF=y
+CONFIG_CLS_U32_MARK=y
+CONFIG_NET_EMATCH=y
+CONFIG_NET_EMATCH_STACK=32
+CONFIG_NET_EMATCH_CMP=m
+CONFIG_NET_EMATCH_NBYTE=m
+CONFIG_NET_EMATCH_U32=m
+CONFIG_NET_EMATCH_META=m
+CONFIG_NET_EMATCH_TEXT=m
+CONFIG_NET_EMATCH_IPSET=m
+CONFIG_NET_EMATCH_IPT=m
+CONFIG_NET_CLS_ACT=y
+CONFIG_NET_ACT_POLICE=m
+CONFIG_NET_ACT_GACT=m
+CONFIG_GACT_PROB=y
+CONFIG_NET_ACT_MIRRED=m
+CONFIG_NET_ACT_SAMPLE=m
+CONFIG_NET_ACT_IPT=m
+CONFIG_NET_ACT_NAT=m
+CONFIG_NET_ACT_PEDIT=m
+CONFIG_NET_ACT_SIMP=m
+CONFIG_NET_ACT_SKBEDIT=m
+CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_VLAN=m
+CONFIG_NET_ACT_BPF=m
+CONFIG_NET_ACT_CONNMARK=m
+CONFIG_NET_ACT_SKBMOD=m
+CONFIG_NET_ACT_IFE=m
+CONFIG_NET_ACT_TUNNEL_KEY=m
+CONFIG_NET_IFE_SKBMARK=m
+CONFIG_NET_IFE_SKBPRIO=m
+CONFIG_NET_IFE_SKBTCINDEX=m
+CONFIG_NET_CLS_IND=y
+CONFIG_NET_SCH_FIFO=y
-- 
cgit v1.2.3


From 05364ca03cfd419caecb292fede20eb39667eaae Mon Sep 17 00:00:00 2001
From: Konstantin Khorenko <khorenko@virtuozzo.com>
Date: Fri, 10 Aug 2018 20:11:42 +0300
Subject: net/sctp: Make wrappers for accessing in/out streams

This patch introduces wrappers for accessing in/out streams indirectly.
This will enable to replace physically contiguous memory arrays
of streams with flexible arrays (or maybe any other appropriate
mechanism) which do memory allocation on a per-page basis.

Signed-off-by: Oleg Babin <obabin@virtuozzo.com>
Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h   | 35 +++++++++++++++++-------
 net/sctp/chunk.c             |  6 ++--
 net/sctp/outqueue.c          | 11 ++++----
 net/sctp/socket.c            |  4 +--
 net/sctp/stream.c            | 65 +++++++++++++++++++++++---------------------
 net/sctp/stream_interleave.c | 20 +++++++-------
 net/sctp/stream_sched.c      | 13 +++++----
 net/sctp/stream_sched_prio.c | 22 +++++++--------
 net/sctp/stream_sched_rr.c   |  8 +++---
 9 files changed, 103 insertions(+), 81 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ab869e0d8326..6b2b8df8a1d2 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -398,37 +398,35 @@ void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new);
 
 /* What is the current SSN number for this stream? */
 #define sctp_ssn_peek(stream, type, sid) \
-	((stream)->type[sid].ssn)
+	(sctp_stream_##type((stream), (sid))->ssn)
 
 /* Return the next SSN number for this stream.	*/
 #define sctp_ssn_next(stream, type, sid) \
-	((stream)->type[sid].ssn++)
+	(sctp_stream_##type((stream), (sid))->ssn++)
 
 /* Skip over this ssn and all below. */
 #define sctp_ssn_skip(stream, type, sid, ssn) \
-	((stream)->type[sid].ssn = ssn + 1)
+	(sctp_stream_##type((stream), (sid))->ssn = ssn + 1)
 
 /* What is the current MID number for this stream? */
 #define sctp_mid_peek(stream, type, sid) \
-	((stream)->type[sid].mid)
+	(sctp_stream_##type((stream), (sid))->mid)
 
 /* Return the next MID number for this stream.  */
 #define sctp_mid_next(stream, type, sid) \
-	((stream)->type[sid].mid++)
+	(sctp_stream_##type((stream), (sid))->mid++)
 
 /* Skip over this mid and all below. */
 #define sctp_mid_skip(stream, type, sid, mid) \
-	((stream)->type[sid].mid = mid + 1)
-
-#define sctp_stream_in(asoc, sid) (&(asoc)->stream.in[sid])
+	(sctp_stream_##type((stream), (sid))->mid = mid + 1)
 
 /* What is the current MID_uo number for this stream? */
 #define sctp_mid_uo_peek(stream, type, sid) \
-	((stream)->type[sid].mid_uo)
+	(sctp_stream_##type((stream), (sid))->mid_uo)
 
 /* Return the next MID_uo number for this stream.  */
 #define sctp_mid_uo_next(stream, type, sid) \
-	((stream)->type[sid].mid_uo++)
+	(sctp_stream_##type((stream), (sid))->mid_uo++)
 
 /*
  * Pointers to address related SCTP functions.
@@ -1463,6 +1461,23 @@ struct sctp_stream {
 	struct sctp_stream_interleave *si;
 };
 
+static inline struct sctp_stream_out *sctp_stream_out(
+	const struct sctp_stream *stream,
+	__u16 sid)
+{
+	return ((struct sctp_stream_out *)(stream->out)) + sid;
+}
+
+static inline struct sctp_stream_in *sctp_stream_in(
+	const struct sctp_stream *stream,
+	__u16 sid)
+{
+	return ((struct sctp_stream_in *)(stream->in)) + sid;
+}
+
+#define SCTP_SO(s, i) sctp_stream_out((s), (i))
+#define SCTP_SI(s, i) sctp_stream_in((s), (i))
+
 #define SCTP_STREAM_CLOSED		0x00
 #define SCTP_STREAM_OPEN		0x01
 
diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c
index bfb9f812e2ef..ce8087846f05 100644
--- a/net/sctp/chunk.c
+++ b/net/sctp/chunk.c
@@ -325,7 +325,8 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
 	if (SCTP_PR_TTL_ENABLED(chunk->sinfo.sinfo_flags) &&
 	    time_after(jiffies, chunk->msg->expires_at)) {
 		struct sctp_stream_out *streamout =
-			&chunk->asoc->stream.out[chunk->sinfo.sinfo_stream];
+			SCTP_SO(&chunk->asoc->stream,
+				chunk->sinfo.sinfo_stream);
 
 		if (chunk->sent_count) {
 			chunk->asoc->abandoned_sent[SCTP_PR_INDEX(TTL)]++;
@@ -339,7 +340,8 @@ int sctp_chunk_abandoned(struct sctp_chunk *chunk)
 	} else if (SCTP_PR_RTX_ENABLED(chunk->sinfo.sinfo_flags) &&
 		   chunk->sent_count > chunk->sinfo.sinfo_timetolive) {
 		struct sctp_stream_out *streamout =
-			&chunk->asoc->stream.out[chunk->sinfo.sinfo_stream];
+			SCTP_SO(&chunk->asoc->stream,
+				chunk->sinfo.sinfo_stream);
 
 		chunk->asoc->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
 		streamout->ext->abandoned_sent[SCTP_PR_INDEX(RTX)]++;
diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c
index d68aa33485a9..d74d00b29942 100644
--- a/net/sctp/outqueue.c
+++ b/net/sctp/outqueue.c
@@ -80,7 +80,7 @@ static inline void sctp_outq_head_data(struct sctp_outq *q,
 	q->out_qlen += ch->skb->len;
 
 	stream = sctp_chunk_stream_no(ch);
-	oute = q->asoc->stream.out[stream].ext;
+	oute = SCTP_SO(&q->asoc->stream, stream)->ext;
 	list_add(&ch->stream_list, &oute->outq);
 }
 
@@ -101,7 +101,7 @@ static inline void sctp_outq_tail_data(struct sctp_outq *q,
 	q->out_qlen += ch->skb->len;
 
 	stream = sctp_chunk_stream_no(ch);
-	oute = q->asoc->stream.out[stream].ext;
+	oute = SCTP_SO(&q->asoc->stream, stream)->ext;
 	list_add_tail(&ch->stream_list, &oute->outq);
 }
 
@@ -372,7 +372,7 @@ static int sctp_prsctp_prune_sent(struct sctp_association *asoc,
 		sctp_insert_list(&asoc->outqueue.abandoned,
 				 &chk->transmitted_list);
 
-		streamout = &asoc->stream.out[chk->sinfo.sinfo_stream];
+		streamout = SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream);
 		asoc->sent_cnt_removable--;
 		asoc->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
 		streamout->ext->abandoned_sent[SCTP_PR_INDEX(PRIO)]++;
@@ -416,7 +416,7 @@ static int sctp_prsctp_prune_unsent(struct sctp_association *asoc,
 		asoc->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
 		if (chk->sinfo.sinfo_stream < asoc->stream.outcnt) {
 			struct sctp_stream_out *streamout =
-				&asoc->stream.out[chk->sinfo.sinfo_stream];
+				SCTP_SO(&asoc->stream, chk->sinfo.sinfo_stream);
 
 			streamout->ext->abandoned_unsent[SCTP_PR_INDEX(PRIO)]++;
 		}
@@ -1082,6 +1082,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
 	/* Finally, transmit new packets.  */
 	while ((chunk = sctp_outq_dequeue_data(ctx->q)) != NULL) {
 		__u32 sid = ntohs(chunk->subh.data_hdr->stream);
+		__u8 stream_state = SCTP_SO(&ctx->asoc->stream, sid)->state;
 
 		/* Has this chunk expired? */
 		if (sctp_chunk_abandoned(chunk)) {
@@ -1091,7 +1092,7 @@ static void sctp_outq_flush_data(struct sctp_flush_ctx *ctx,
 			continue;
 		}
 
-		if (ctx->asoc->stream.out[sid].state == SCTP_STREAM_CLOSED) {
+		if (stream_state == SCTP_STREAM_CLOSED) {
 			sctp_outq_head_data(ctx->q, chunk);
 			break;
 		}
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index 502c0d7cb105..e96b15a66aba 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -1911,7 +1911,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc,
 		goto err;
 	}
 
-	if (unlikely(!asoc->stream.out[sinfo->sinfo_stream].ext)) {
+	if (unlikely(!SCTP_SO(&asoc->stream, sinfo->sinfo_stream)->ext)) {
 		err = sctp_stream_init_ext(&asoc->stream, sinfo->sinfo_stream);
 		if (err)
 			goto err;
@@ -7154,7 +7154,7 @@ static int sctp_getsockopt_pr_streamstatus(struct sock *sk, int len,
 	if (!asoc || params.sprstat_sid >= asoc->stream.outcnt)
 		goto out;
 
-	streamoute = asoc->stream.out[params.sprstat_sid].ext;
+	streamoute = SCTP_SO(&asoc->stream, params.sprstat_sid)->ext;
 	if (!streamoute) {
 		/* Not allocated yet, means all stats are 0 */
 		params.sprstat_abandoned_unsent = 0;
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index f1f1d1b232ba..7ca6fe4e7882 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -162,7 +162,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt,
 
 	stream->outcnt = outcnt;
 	for (i = 0; i < stream->outcnt; i++)
-		stream->out[i].state = SCTP_STREAM_OPEN;
+		SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
 	sched->init(stream);
 
@@ -193,7 +193,7 @@ int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid)
 	soute = kzalloc(sizeof(*soute), GFP_KERNEL);
 	if (!soute)
 		return -ENOMEM;
-	stream->out[sid].ext = soute;
+	SCTP_SO(stream, sid)->ext = soute;
 
 	return sctp_sched_init_sid(stream, sid, GFP_KERNEL);
 }
@@ -205,7 +205,7 @@ void sctp_stream_free(struct sctp_stream *stream)
 
 	sched->free(stream);
 	for (i = 0; i < stream->outcnt; i++)
-		kfree(stream->out[i].ext);
+		kfree(SCTP_SO(stream, i)->ext);
 	kfree(stream->out);
 	kfree(stream->in);
 }
@@ -215,12 +215,12 @@ void sctp_stream_clear(struct sctp_stream *stream)
 	int i;
 
 	for (i = 0; i < stream->outcnt; i++) {
-		stream->out[i].mid = 0;
-		stream->out[i].mid_uo = 0;
+		SCTP_SO(stream, i)->mid = 0;
+		SCTP_SO(stream, i)->mid_uo = 0;
 	}
 
 	for (i = 0; i < stream->incnt; i++)
-		stream->in[i].mid = 0;
+		SCTP_SI(stream, i)->mid = 0;
 }
 
 void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new)
@@ -273,8 +273,8 @@ static bool sctp_stream_outq_is_empty(struct sctp_stream *stream,
 	for (i = 0; i < str_nums; i++) {
 		__u16 sid = ntohs(str_list[i]);
 
-		if (stream->out[sid].ext &&
-		    !list_empty(&stream->out[sid].ext->outq))
+		if (SCTP_SO(stream, sid)->ext &&
+		    !list_empty(&SCTP_SO(stream, sid)->ext->outq))
 			return false;
 	}
 
@@ -361,11 +361,11 @@ int sctp_send_reset_streams(struct sctp_association *asoc,
 	if (out) {
 		if (str_nums)
 			for (i = 0; i < str_nums; i++)
-				stream->out[str_list[i]].state =
+				SCTP_SO(stream, str_list[i])->state =
 						       SCTP_STREAM_CLOSED;
 		else
 			for (i = 0; i < stream->outcnt; i++)
-				stream->out[i].state = SCTP_STREAM_CLOSED;
+				SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED;
 	}
 
 	asoc->strreset_chunk = chunk;
@@ -380,11 +380,11 @@ int sctp_send_reset_streams(struct sctp_association *asoc,
 
 		if (str_nums)
 			for (i = 0; i < str_nums; i++)
-				stream->out[str_list[i]].state =
+				SCTP_SO(stream, str_list[i])->state =
 						       SCTP_STREAM_OPEN;
 		else
 			for (i = 0; i < stream->outcnt; i++)
-				stream->out[i].state = SCTP_STREAM_OPEN;
+				SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
 		goto out;
 	}
@@ -418,7 +418,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc)
 
 	/* Block further xmit of data until this request is completed */
 	for (i = 0; i < stream->outcnt; i++)
-		stream->out[i].state = SCTP_STREAM_CLOSED;
+		SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED;
 
 	asoc->strreset_chunk = chunk;
 	sctp_chunk_hold(asoc->strreset_chunk);
@@ -429,7 +429,7 @@ int sctp_send_reset_assoc(struct sctp_association *asoc)
 		asoc->strreset_chunk = NULL;
 
 		for (i = 0; i < stream->outcnt; i++)
-			stream->out[i].state = SCTP_STREAM_OPEN;
+			SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
 		return retval;
 	}
@@ -609,10 +609,10 @@ struct sctp_chunk *sctp_process_strreset_outreq(
 		}
 
 		for (i = 0; i < nums; i++)
-			stream->in[ntohs(str_p[i])].mid = 0;
+			SCTP_SI(stream, ntohs(str_p[i]))->mid = 0;
 	} else {
 		for (i = 0; i < stream->incnt; i++)
-			stream->in[i].mid = 0;
+			SCTP_SI(stream, i)->mid = 0;
 	}
 
 	result = SCTP_STRRESET_PERFORMED;
@@ -683,11 +683,11 @@ struct sctp_chunk *sctp_process_strreset_inreq(
 
 	if (nums)
 		for (i = 0; i < nums; i++)
-			stream->out[ntohs(str_p[i])].state =
+			SCTP_SO(stream, ntohs(str_p[i]))->state =
 					       SCTP_STREAM_CLOSED;
 	else
 		for (i = 0; i < stream->outcnt; i++)
-			stream->out[i].state = SCTP_STREAM_CLOSED;
+			SCTP_SO(stream, i)->state = SCTP_STREAM_CLOSED;
 
 	asoc->strreset_chunk = chunk;
 	asoc->strreset_outstanding = 1;
@@ -786,11 +786,11 @@ struct sctp_chunk *sctp_process_strreset_tsnreq(
 	 *      incoming and outgoing streams.
 	 */
 	for (i = 0; i < stream->outcnt; i++) {
-		stream->out[i].mid = 0;
-		stream->out[i].mid_uo = 0;
+		SCTP_SO(stream, i)->mid = 0;
+		SCTP_SO(stream, i)->mid_uo = 0;
 	}
 	for (i = 0; i < stream->incnt; i++)
-		stream->in[i].mid = 0;
+		SCTP_SI(stream, i)->mid = 0;
 
 	result = SCTP_STRRESET_PERFORMED;
 
@@ -979,15 +979,18 @@ struct sctp_chunk *sctp_process_strreset_resp(
 		       sizeof(__u16);
 
 		if (result == SCTP_STRRESET_PERFORMED) {
+			struct sctp_stream_out *sout;
 			if (nums) {
 				for (i = 0; i < nums; i++) {
-					stream->out[ntohs(str_p[i])].mid = 0;
-					stream->out[ntohs(str_p[i])].mid_uo = 0;
+					sout = SCTP_SO(stream, ntohs(str_p[i]));
+					sout->mid = 0;
+					sout->mid_uo = 0;
 				}
 			} else {
 				for (i = 0; i < stream->outcnt; i++) {
-					stream->out[i].mid = 0;
-					stream->out[i].mid_uo = 0;
+					sout = SCTP_SO(stream, i);
+					sout->mid = 0;
+					sout->mid_uo = 0;
 				}
 			}
 
@@ -995,7 +998,7 @@ struct sctp_chunk *sctp_process_strreset_resp(
 		}
 
 		for (i = 0; i < stream->outcnt; i++)
-			stream->out[i].state = SCTP_STREAM_OPEN;
+			SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
 		*evp = sctp_ulpevent_make_stream_reset_event(asoc, flags,
 			nums, str_p, GFP_ATOMIC);
@@ -1050,15 +1053,15 @@ struct sctp_chunk *sctp_process_strreset_resp(
 			asoc->adv_peer_ack_point = asoc->ctsn_ack_point;
 
 			for (i = 0; i < stream->outcnt; i++) {
-				stream->out[i].mid = 0;
-				stream->out[i].mid_uo = 0;
+				SCTP_SO(stream, i)->mid = 0;
+				SCTP_SO(stream, i)->mid_uo = 0;
 			}
 			for (i = 0; i < stream->incnt; i++)
-				stream->in[i].mid = 0;
+				SCTP_SI(stream, i)->mid = 0;
 		}
 
 		for (i = 0; i < stream->outcnt; i++)
-			stream->out[i].state = SCTP_STREAM_OPEN;
+			SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 
 		*evp = sctp_ulpevent_make_assoc_reset_event(asoc, flags,
 			stsn, rtsn, GFP_ATOMIC);
@@ -1072,7 +1075,7 @@ struct sctp_chunk *sctp_process_strreset_resp(
 
 		if (result == SCTP_STRRESET_PERFORMED)
 			for (i = number; i < stream->outcnt; i++)
-				stream->out[i].state = SCTP_STREAM_OPEN;
+				SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN;
 		else
 			stream->outcnt = number;
 
diff --git a/net/sctp/stream_interleave.c b/net/sctp/stream_interleave.c
index d3764c181299..0a78cdf86463 100644
--- a/net/sctp/stream_interleave.c
+++ b/net/sctp/stream_interleave.c
@@ -197,7 +197,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_partial(
 	__u32 next_fsn = 0;
 	int is_last = 0;
 
-	sin = sctp_stream_in(ulpq->asoc, event->stream);
+	sin = sctp_stream_in(&ulpq->asoc->stream, event->stream);
 
 	skb_queue_walk(&ulpq->reasm, pos) {
 		struct sctp_ulpevent *cevent = sctp_skb2event(pos);
@@ -278,7 +278,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled(
 	__u32 pd_len = 0;
 	__u32 mid = 0;
 
-	sin = sctp_stream_in(ulpq->asoc, event->stream);
+	sin = sctp_stream_in(&ulpq->asoc->stream, event->stream);
 
 	skb_queue_walk(&ulpq->reasm, pos) {
 		struct sctp_ulpevent *cevent = sctp_skb2event(pos);
@@ -368,7 +368,7 @@ static struct sctp_ulpevent *sctp_intl_reasm(struct sctp_ulpq *ulpq,
 
 	sctp_intl_store_reasm(ulpq, event);
 
-	sin = sctp_stream_in(ulpq->asoc, event->stream);
+	sin = sctp_stream_in(&ulpq->asoc->stream, event->stream);
 	if (sin->pd_mode && event->mid == sin->mid &&
 	    event->fsn == sin->fsn)
 		retval = sctp_intl_retrieve_partial(ulpq, event);
@@ -575,7 +575,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_partial_uo(
 	__u32 next_fsn = 0;
 	int is_last = 0;
 
-	sin = sctp_stream_in(ulpq->asoc, event->stream);
+	sin = sctp_stream_in(&ulpq->asoc->stream, event->stream);
 
 	skb_queue_walk(&ulpq->reasm_uo, pos) {
 		struct sctp_ulpevent *cevent = sctp_skb2event(pos);
@@ -659,7 +659,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_reassembled_uo(
 	__u32 pd_len = 0;
 	__u32 mid = 0;
 
-	sin = sctp_stream_in(ulpq->asoc, event->stream);
+	sin = sctp_stream_in(&ulpq->asoc->stream, event->stream);
 
 	skb_queue_walk(&ulpq->reasm_uo, pos) {
 		struct sctp_ulpevent *cevent = sctp_skb2event(pos);
@@ -750,7 +750,7 @@ static struct sctp_ulpevent *sctp_intl_reasm_uo(struct sctp_ulpq *ulpq,
 
 	sctp_intl_store_reasm_uo(ulpq, event);
 
-	sin = sctp_stream_in(ulpq->asoc, event->stream);
+	sin = sctp_stream_in(&ulpq->asoc->stream, event->stream);
 	if (sin->pd_mode_uo && event->mid == sin->mid_uo &&
 	    event->fsn == sin->fsn_uo)
 		retval = sctp_intl_retrieve_partial_uo(ulpq, event);
@@ -774,7 +774,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first_uo(struct sctp_ulpq *ulpq)
 	skb_queue_walk(&ulpq->reasm_uo, pos) {
 		struct sctp_ulpevent *cevent = sctp_skb2event(pos);
 
-		csin = sctp_stream_in(ulpq->asoc, cevent->stream);
+		csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream);
 		if (csin->pd_mode_uo)
 			continue;
 
@@ -875,7 +875,7 @@ static struct sctp_ulpevent *sctp_intl_retrieve_first(struct sctp_ulpq *ulpq)
 	skb_queue_walk(&ulpq->reasm, pos) {
 		struct sctp_ulpevent *cevent = sctp_skb2event(pos);
 
-		csin = sctp_stream_in(ulpq->asoc, cevent->stream);
+		csin = sctp_stream_in(&ulpq->asoc->stream, cevent->stream);
 		if (csin->pd_mode)
 			continue;
 
@@ -1053,7 +1053,7 @@ static void sctp_intl_abort_pd(struct sctp_ulpq *ulpq, gfp_t gfp)
 	__u16 sid;
 
 	for (sid = 0; sid < stream->incnt; sid++) {
-		struct sctp_stream_in *sin = &stream->in[sid];
+		struct sctp_stream_in *sin = SCTP_SI(stream, sid);
 		__u32 mid;
 
 		if (sin->pd_mode_uo) {
@@ -1247,7 +1247,7 @@ static void sctp_handle_fwdtsn(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk)
 static void sctp_intl_skip(struct sctp_ulpq *ulpq, __u16 sid, __u32 mid,
 			   __u8 flags)
 {
-	struct sctp_stream_in *sin = sctp_stream_in(ulpq->asoc, sid);
+	struct sctp_stream_in *sin = sctp_stream_in(&ulpq->asoc->stream, sid);
 	struct sctp_stream *stream  = &ulpq->asoc->stream;
 
 	if (flags & SCTP_FTSN_U_BIT) {
diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c
index f5fcd425232a..a6c04a94b08f 100644
--- a/net/sctp/stream_sched.c
+++ b/net/sctp/stream_sched.c
@@ -161,7 +161,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc,
 
 		/* Give the next scheduler a clean slate. */
 		for (i = 0; i < asoc->stream.outcnt; i++) {
-			void *p = asoc->stream.out[i].ext;
+			void *p = SCTP_SO(&asoc->stream, i)->ext;
 
 			if (!p)
 				continue;
@@ -175,7 +175,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc,
 	asoc->outqueue.sched = n;
 	n->init(&asoc->stream);
 	for (i = 0; i < asoc->stream.outcnt; i++) {
-		if (!asoc->stream.out[i].ext)
+		if (!SCTP_SO(&asoc->stream, i)->ext)
 			continue;
 
 		ret = n->init_sid(&asoc->stream, i, GFP_KERNEL);
@@ -217,7 +217,7 @@ int sctp_sched_set_value(struct sctp_association *asoc, __u16 sid,
 	if (sid >= asoc->stream.outcnt)
 		return -EINVAL;
 
-	if (!asoc->stream.out[sid].ext) {
+	if (!SCTP_SO(&asoc->stream, sid)->ext) {
 		int ret;
 
 		ret = sctp_stream_init_ext(&asoc->stream, sid);
@@ -234,7 +234,7 @@ int sctp_sched_get_value(struct sctp_association *asoc, __u16 sid,
 	if (sid >= asoc->stream.outcnt)
 		return -EINVAL;
 
-	if (!asoc->stream.out[sid].ext)
+	if (!SCTP_SO(&asoc->stream, sid)->ext)
 		return 0;
 
 	return asoc->outqueue.sched->get(&asoc->stream, sid, value);
@@ -252,7 +252,7 @@ void sctp_sched_dequeue_done(struct sctp_outq *q, struct sctp_chunk *ch)
 		 * priority stream comes in.
 		 */
 		sid = sctp_chunk_stream_no(ch);
-		sout = &q->asoc->stream.out[sid];
+		sout = SCTP_SO(&q->asoc->stream, sid);
 		q->asoc->stream.out_curr = sout;
 		return;
 	}
@@ -272,8 +272,9 @@ void sctp_sched_dequeue_common(struct sctp_outq *q, struct sctp_chunk *ch)
 int sctp_sched_init_sid(struct sctp_stream *stream, __u16 sid, gfp_t gfp)
 {
 	struct sctp_sched_ops *sched = sctp_sched_ops_from_stream(stream);
+	struct sctp_stream_out_ext *ext = SCTP_SO(stream, sid)->ext;
 
-	INIT_LIST_HEAD(&stream->out[sid].ext->outq);
+	INIT_LIST_HEAD(&ext->outq);
 	return sched->init_sid(stream, sid, gfp);
 }
 
diff --git a/net/sctp/stream_sched_prio.c b/net/sctp/stream_sched_prio.c
index 7997d35dd0fd..2245083a98f2 100644
--- a/net/sctp/stream_sched_prio.c
+++ b/net/sctp/stream_sched_prio.c
@@ -75,10 +75,10 @@ static struct sctp_stream_priorities *sctp_sched_prio_get_head(
 
 	/* No luck. So we search on all streams now. */
 	for (i = 0; i < stream->outcnt; i++) {
-		if (!stream->out[i].ext)
+		if (!SCTP_SO(stream, i)->ext)
 			continue;
 
-		p = stream->out[i].ext->prio_head;
+		p = SCTP_SO(stream, i)->ext->prio_head;
 		if (!p)
 			/* Means all other streams won't be initialized
 			 * as well.
@@ -165,7 +165,7 @@ static void sctp_sched_prio_sched(struct sctp_stream *stream,
 static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid,
 			       __u16 prio, gfp_t gfp)
 {
-	struct sctp_stream_out *sout = &stream->out[sid];
+	struct sctp_stream_out *sout = SCTP_SO(stream, sid);
 	struct sctp_stream_out_ext *soute = sout->ext;
 	struct sctp_stream_priorities *prio_head, *old;
 	bool reschedule = false;
@@ -186,7 +186,7 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid,
 		return 0;
 
 	for (i = 0; i < stream->outcnt; i++) {
-		soute = stream->out[i].ext;
+		soute = SCTP_SO(stream, i)->ext;
 		if (soute && soute->prio_head == old)
 			/* It's still in use, nothing else to do here. */
 			return 0;
@@ -201,7 +201,7 @@ static int sctp_sched_prio_set(struct sctp_stream *stream, __u16 sid,
 static int sctp_sched_prio_get(struct sctp_stream *stream, __u16 sid,
 			       __u16 *value)
 {
-	*value = stream->out[sid].ext->prio_head->prio;
+	*value = SCTP_SO(stream, sid)->ext->prio_head->prio;
 	return 0;
 }
 
@@ -215,7 +215,7 @@ static int sctp_sched_prio_init(struct sctp_stream *stream)
 static int sctp_sched_prio_init_sid(struct sctp_stream *stream, __u16 sid,
 				    gfp_t gfp)
 {
-	INIT_LIST_HEAD(&stream->out[sid].ext->prio_list);
+	INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->prio_list);
 	return sctp_sched_prio_set(stream, sid, 0, gfp);
 }
 
@@ -233,9 +233,9 @@ static void sctp_sched_prio_free(struct sctp_stream *stream)
 	 */
 	sctp_sched_prio_unsched_all(stream);
 	for (i = 0; i < stream->outcnt; i++) {
-		if (!stream->out[i].ext)
+		if (!SCTP_SO(stream, i)->ext)
 			continue;
-		prio = stream->out[i].ext->prio_head;
+		prio = SCTP_SO(stream, i)->ext->prio_head;
 		if (prio && list_empty(&prio->prio_sched))
 			list_add(&prio->prio_sched, &list);
 	}
@@ -255,7 +255,7 @@ static void sctp_sched_prio_enqueue(struct sctp_outq *q,
 	ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
 	sid = sctp_chunk_stream_no(ch);
 	stream = &q->asoc->stream;
-	sctp_sched_prio_sched(stream, stream->out[sid].ext);
+	sctp_sched_prio_sched(stream, SCTP_SO(stream, sid)->ext);
 }
 
 static struct sctp_chunk *sctp_sched_prio_dequeue(struct sctp_outq *q)
@@ -297,7 +297,7 @@ static void sctp_sched_prio_dequeue_done(struct sctp_outq *q,
 	 * this priority.
 	 */
 	sid = sctp_chunk_stream_no(ch);
-	soute = q->asoc->stream.out[sid].ext;
+	soute = SCTP_SO(&q->asoc->stream, sid)->ext;
 	prio = soute->prio_head;
 
 	sctp_sched_prio_next_stream(prio);
@@ -317,7 +317,7 @@ static void sctp_sched_prio_sched_all(struct sctp_stream *stream)
 		__u16 sid;
 
 		sid = sctp_chunk_stream_no(ch);
-		sout = &stream->out[sid];
+		sout = SCTP_SO(stream, sid);
 		if (sout->ext)
 			sctp_sched_prio_sched(stream, sout->ext);
 	}
diff --git a/net/sctp/stream_sched_rr.c b/net/sctp/stream_sched_rr.c
index 1155692448f1..52ba743fa7a7 100644
--- a/net/sctp/stream_sched_rr.c
+++ b/net/sctp/stream_sched_rr.c
@@ -100,7 +100,7 @@ static int sctp_sched_rr_init(struct sctp_stream *stream)
 static int sctp_sched_rr_init_sid(struct sctp_stream *stream, __u16 sid,
 				  gfp_t gfp)
 {
-	INIT_LIST_HEAD(&stream->out[sid].ext->rr_list);
+	INIT_LIST_HEAD(&SCTP_SO(stream, sid)->ext->rr_list);
 
 	return 0;
 }
@@ -120,7 +120,7 @@ static void sctp_sched_rr_enqueue(struct sctp_outq *q,
 	ch = list_first_entry(&msg->chunks, struct sctp_chunk, frag_list);
 	sid = sctp_chunk_stream_no(ch);
 	stream = &q->asoc->stream;
-	sctp_sched_rr_sched(stream, stream->out[sid].ext);
+	sctp_sched_rr_sched(stream, SCTP_SO(stream, sid)->ext);
 }
 
 static struct sctp_chunk *sctp_sched_rr_dequeue(struct sctp_outq *q)
@@ -154,7 +154,7 @@ static void sctp_sched_rr_dequeue_done(struct sctp_outq *q,
 
 	/* Last chunk on that msg, move to the next stream */
 	sid = sctp_chunk_stream_no(ch);
-	soute = q->asoc->stream.out[sid].ext;
+	soute = SCTP_SO(&q->asoc->stream, sid)->ext;
 
 	sctp_sched_rr_next_stream(&q->asoc->stream);
 
@@ -173,7 +173,7 @@ static void sctp_sched_rr_sched_all(struct sctp_stream *stream)
 		__u16 sid;
 
 		sid = sctp_chunk_stream_no(ch);
-		soute = stream->out[sid].ext;
+		soute = SCTP_SO(stream, sid)->ext;
 		if (soute)
 			sctp_sched_rr_sched(stream, soute);
 	}
-- 
cgit v1.2.3


From 0d493b4d0be352b5e361e4fa0bc3efe952d8b10e Mon Sep 17 00:00:00 2001
From: Konstantin Khorenko <khorenko@virtuozzo.com>
Date: Fri, 10 Aug 2018 20:11:43 +0300
Subject: net/sctp: Replace in/out stream arrays with flex_array

This path replaces physically contiguous memory arrays
allocated using kmalloc_array() with flexible arrays.
This enables to avoid memory allocation failures on the
systems under a memory stress.

Signed-off-by: Oleg Babin <obabin@virtuozzo.com>
Signed-off-by: Konstantin Khorenko <khorenko@virtuozzo.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/sctp/structs.h |  9 ++---
 net/sctp/stream.c          | 88 ++++++++++++++++++++++++++++++++++------------
 2 files changed, 71 insertions(+), 26 deletions(-)

diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 6b2b8df8a1d2..28a7c8e44636 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -57,6 +57,7 @@
 #include <linux/atomic.h>		/* This gets us atomic counters.  */
 #include <linux/skbuff.h>	/* We need sk_buff_head. */
 #include <linux/workqueue.h>	/* We need tq_struct.	 */
+#include <linux/flex_array.h>	/* We need flex_array.   */
 #include <linux/sctp.h>		/* We need sctp* header structs.  */
 #include <net/sctp/auth.h>	/* We need auth specific structs */
 #include <net/ip.h>		/* For inet_skb_parm */
@@ -1438,8 +1439,8 @@ struct sctp_stream_in {
 };
 
 struct sctp_stream {
-	struct sctp_stream_out *out;
-	struct sctp_stream_in *in;
+	struct flex_array *out;
+	struct flex_array *in;
 	__u16 outcnt;
 	__u16 incnt;
 	/* Current stream being sent, if any */
@@ -1465,14 +1466,14 @@ static inline struct sctp_stream_out *sctp_stream_out(
 	const struct sctp_stream *stream,
 	__u16 sid)
 {
-	return ((struct sctp_stream_out *)(stream->out)) + sid;
+	return flex_array_get(stream->out, sid);
 }
 
 static inline struct sctp_stream_in *sctp_stream_in(
 	const struct sctp_stream *stream,
 	__u16 sid)
 {
-	return ((struct sctp_stream_in *)(stream->in)) + sid;
+	return flex_array_get(stream->in, sid);
 }
 
 #define SCTP_SO(s, i) sctp_stream_out((s), (i))
diff --git a/net/sctp/stream.c b/net/sctp/stream.c
index 7ca6fe4e7882..ffb940d3b57c 100644
--- a/net/sctp/stream.c
+++ b/net/sctp/stream.c
@@ -37,6 +37,53 @@
 #include <net/sctp/sm.h>
 #include <net/sctp/stream_sched.h>
 
+static struct flex_array *fa_alloc(size_t elem_size, size_t elem_count,
+				   gfp_t gfp)
+{
+	struct flex_array *result;
+	int err;
+
+	result = flex_array_alloc(elem_size, elem_count, gfp);
+	if (result) {
+		err = flex_array_prealloc(result, 0, elem_count, gfp);
+		if (err) {
+			flex_array_free(result);
+			result = NULL;
+		}
+	}
+
+	return result;
+}
+
+static void fa_free(struct flex_array *fa)
+{
+	if (fa)
+		flex_array_free(fa);
+}
+
+static void fa_copy(struct flex_array *fa, struct flex_array *from,
+		    size_t index, size_t count)
+{
+	void *elem;
+
+	while (count--) {
+		elem = flex_array_get(from, index);
+		flex_array_put(fa, index, elem, 0);
+		index++;
+	}
+}
+
+static void fa_zero(struct flex_array *fa, size_t index, size_t count)
+{
+	void *elem;
+
+	while (count--) {
+		elem = flex_array_get(fa, index);
+		memset(elem, 0, fa->element_size);
+		index++;
+	}
+}
+
 /* Migrates chunks from stream queues to new stream queues if needed,
  * but not across associations. Also, removes those chunks to streams
  * higher than the new max.
@@ -78,34 +125,33 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream,
 		 * sctp_stream_update will swap ->out pointers.
 		 */
 		for (i = 0; i < outcnt; i++) {
-			kfree(new->out[i].ext);
-			new->out[i].ext = stream->out[i].ext;
-			stream->out[i].ext = NULL;
+			kfree(SCTP_SO(new, i)->ext);
+			SCTP_SO(new, i)->ext = SCTP_SO(stream, i)->ext;
+			SCTP_SO(stream, i)->ext = NULL;
 		}
 	}
 
 	for (i = outcnt; i < stream->outcnt; i++)
-		kfree(stream->out[i].ext);
+		kfree(SCTP_SO(stream, i)->ext);
 }
 
 static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 				 gfp_t gfp)
 {
-	struct sctp_stream_out *out;
+	struct flex_array *out;
+	size_t elem_size = sizeof(struct sctp_stream_out);
 
-	out = kmalloc_array(outcnt, sizeof(*out), gfp);
+	out = fa_alloc(elem_size, outcnt, gfp);
 	if (!out)
 		return -ENOMEM;
 
 	if (stream->out) {
-		memcpy(out, stream->out, min(outcnt, stream->outcnt) *
-					 sizeof(*out));
-		kfree(stream->out);
+		fa_copy(out, stream->out, 0, min(outcnt, stream->outcnt));
+		fa_free(stream->out);
 	}
 
 	if (outcnt > stream->outcnt)
-		memset(out + stream->outcnt, 0,
-		       (outcnt - stream->outcnt) * sizeof(*out));
+		fa_zero(out, stream->outcnt, (outcnt - stream->outcnt));
 
 	stream->out = out;
 
@@ -115,22 +161,20 @@ static int sctp_stream_alloc_out(struct sctp_stream *stream, __u16 outcnt,
 static int sctp_stream_alloc_in(struct sctp_stream *stream, __u16 incnt,
 				gfp_t gfp)
 {
-	struct sctp_stream_in *in;
-
-	in = kmalloc_array(incnt, sizeof(*stream->in), gfp);
+	struct flex_array *in;
+	size_t elem_size = sizeof(struct sctp_stream_in);
 
+	in = fa_alloc(elem_size, incnt, gfp);
 	if (!in)
 		return -ENOMEM;
 
 	if (stream->in) {
-		memcpy(in, stream->in, min(incnt, stream->incnt) *
-				       sizeof(*in));
-		kfree(stream->in);
+		fa_copy(in, stream->in, 0, min(incnt, stream->incnt));
+		fa_free(stream->in);
 	}
 
 	if (incnt > stream->incnt)
-		memset(in + stream->incnt, 0,
-		       (incnt - stream->incnt) * sizeof(*in));
+		fa_zero(in, stream->incnt, (incnt - stream->incnt));
 
 	stream->in = in;
 
@@ -174,7 +218,7 @@ in:
 	ret = sctp_stream_alloc_in(stream, incnt, gfp);
 	if (ret) {
 		sched->free(stream);
-		kfree(stream->out);
+		fa_free(stream->out);
 		stream->out = NULL;
 		stream->outcnt = 0;
 		goto out;
@@ -206,8 +250,8 @@ void sctp_stream_free(struct sctp_stream *stream)
 	sched->free(stream);
 	for (i = 0; i < stream->outcnt; i++)
 		kfree(SCTP_SO(stream, i)->ext);
-	kfree(stream->out);
-	kfree(stream->in);
+	fa_free(stream->out);
+	fa_free(stream->in);
 }
 
 void sctp_stream_clear(struct sctp_stream *stream)
-- 
cgit v1.2.3


From 2142236b45843dbcbe9691d24cf06caff91a78fd Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:41 +0300
Subject: net: sched: act_bpf: remove dependency on rtnl lock

Use tcf spinlock to protect bpf action private data from concurrent
modification during dump and init. Remove rtnl lock assertion that is no
longer necessary.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 6203eb075c9a..9e8a33f9fee3 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -143,11 +143,12 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
 		.index   = prog->tcf_index,
 		.refcnt  = refcount_read(&prog->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&prog->tcf_bindcnt) - bind,
-		.action  = prog->tcf_action,
 	};
 	struct tcf_t tm;
 	int ret;
 
+	spin_lock(&prog->tcf_lock);
+	opt.action = prog->tcf_action;
 	if (nla_put(skb, TCA_ACT_BPF_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
@@ -163,9 +164,11 @@ static int tcf_bpf_dump(struct sk_buff *skb, struct tc_action *act,
 			  TCA_ACT_BPF_PAD))
 		goto nla_put_failure;
 
+	spin_unlock(&prog->tcf_lock);
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&prog->tcf_lock);
 	nlmsg_trim(skb, tp);
 	return -1;
 }
@@ -264,7 +267,7 @@ static void tcf_bpf_prog_fill_cfg(const struct tcf_bpf *prog,
 {
 	cfg->is_ebpf = tcf_bpf_is_ebpf(prog);
 	/* updates to prog->filter are prevented, since it's called either
-	 * with rtnl lock or during final cleanup in rcu callback
+	 * with tcf lock or during final cleanup in rcu callback
 	 */
 	cfg->filter = rcu_dereference_protected(prog->filter, 1);
 
@@ -336,8 +339,8 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 		goto out;
 
 	prog = to_bpf(*act);
-	ASSERT_RTNL();
 
+	spin_lock(&prog->tcf_lock);
 	if (res != ACT_P_CREATED)
 		tcf_bpf_prog_fill_cfg(prog, &old);
 
@@ -349,6 +352,7 @@ static int tcf_bpf_init(struct net *net, struct nlattr *nla,
 
 	prog->tcf_action = parm->action;
 	rcu_assign_pointer(prog->filter, cfg.filter);
+	spin_unlock(&prog->tcf_lock);
 
 	if (res == ACT_P_CREATED) {
 		tcf_idr_insert(tn, *act);
-- 
cgit v1.2.3


From b6a2b971c0b00253197682fbdf1c55fc0e2610a4 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:42 +0300
Subject: net: sched: act_csum: remove dependency on rtnl lock

Use tcf lock to protect csum action struct private data from concurrent
modification in init and dump. Use rcu swap operation to reassign params
pointer under protection of tcf lock. (old params value is not used by
init, so there is no need of standalone rcu dereference step)

Remove rtnl assertion that is no longer necessary.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_csum.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index 648a3a35b720..f01c59ba6d12 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -50,7 +50,7 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 			 struct netlink_ext_ack *extack)
 {
 	struct tc_action_net *tn = net_generic(net, csum_net_id);
-	struct tcf_csum_params *params_old, *params_new;
+	struct tcf_csum_params *params_new;
 	struct nlattr *tb[TCA_CSUM_MAX + 1];
 	struct tc_csum *parm;
 	struct tcf_csum *p;
@@ -88,20 +88,22 @@ static int tcf_csum_init(struct net *net, struct nlattr *nla,
 	}
 
 	p = to_tcf_csum(*a);
-	ASSERT_RTNL();
 
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
 	if (unlikely(!params_new)) {
 		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
-	params_old = rtnl_dereference(p->params);
+	params_new->update_flags = parm->update_flags;
 
+	spin_lock(&p->tcf_lock);
 	p->tcf_action = parm->action;
-	params_new->update_flags = parm->update_flags;
-	rcu_assign_pointer(p->params, params_new);
-	if (params_old)
-		kfree_rcu(params_old, rcu);
+	rcu_swap_protected(p->params, params_new,
+			   lockdep_is_held(&p->tcf_lock));
+	spin_unlock(&p->tcf_lock);
+
+	if (params_new)
+		kfree_rcu(params_new, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -599,11 +601,13 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 		.index   = p->tcf_index,
 		.refcnt  = refcount_read(&p->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&p->tcf_bindcnt) - bind,
-		.action  = p->tcf_action,
 	};
 	struct tcf_t t;
 
-	params = rtnl_dereference(p->params);
+	spin_lock(&p->tcf_lock);
+	params = rcu_dereference_protected(p->params,
+					   lockdep_is_held(&p->tcf_lock));
+	opt.action = p->tcf_action;
 	opt.update_flags = params->update_flags;
 
 	if (nla_put(skb, TCA_CSUM_PARMS, sizeof(opt), &opt))
@@ -612,10 +616,12 @@ static int tcf_csum_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_CSUM_TM, sizeof(t), &t, TCA_CSUM_PAD))
 		goto nla_put_failure;
+	spin_unlock(&p->tcf_lock);
 
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&p->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From e8917f437006686b8fa1b9e54f31d7abc0ea7e97 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:43 +0300
Subject: net: sched: act_gact: remove dependency on rtnl lock

Use tcf spinlock to protect gact action private state from concurrent
modification during dump and init. Remove rtnl assertion that is no longer
necessary.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_gact.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index 661b72b9147d..bfccd34a3968 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -113,7 +113,7 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 
 	gact = to_gact(*a);
 
-	ASSERT_RTNL();
+	spin_lock(&gact->tcf_lock);
 	gact->tcf_action = parm->action;
 #ifdef CONFIG_GACT_PROB
 	if (p_parm) {
@@ -126,6 +126,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 		gact->tcfg_ptype   = p_parm->ptype;
 	}
 #endif
+	spin_unlock(&gact->tcf_lock);
+
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
@@ -178,10 +180,11 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
 		.index   = gact->tcf_index,
 		.refcnt  = refcount_read(&gact->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&gact->tcf_bindcnt) - bind,
-		.action  = gact->tcf_action,
 	};
 	struct tcf_t t;
 
+	spin_lock(&gact->tcf_lock);
+	opt.action = gact->tcf_action;
 	if (nla_put(skb, TCA_GACT_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 #ifdef CONFIG_GACT_PROB
@@ -199,9 +202,12 @@ static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a,
 	tcf_tm_dump(&t, &gact->tcf_tm);
 	if (nla_put_64bit(skb, TCA_GACT_TM, sizeof(t), &t, TCA_GACT_PAD))
 		goto nla_put_failure;
+	spin_unlock(&gact->tcf_lock);
+
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&gact->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From 54d0d423a48aa0e61bb39665d20376ba7b940535 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:44 +0300
Subject: net: sched: act_ife: remove dependency on rtnl lock

Use tcf spinlock and rcu to protect params pointer from concurrent
modification during dump and init. Use rcu swap operation to reassign
params pointer under protection of tcf lock. (old params value is not used
by init, so there is no need of standalone rcu dereference step)

Ife action has meta-actions that are compiled as standalone modules. Rtnl
mutex must be released while loading a kernel module. In order to support
execution without rtnl mutex, propagate 'rtnl_held' argument to meta action
loading functions. When requesting meta action module, conditionally
release rtnl lock depending on 'rtnl_held' argument.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 40 +++++++++++++++++++++++++---------------
 1 file changed, 25 insertions(+), 15 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index df4060e32d43..5d200495e467 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -268,7 +268,8 @@ static const char *ife_meta_id2name(u32 metaid)
  * under ife->tcf_lock for existing action
 */
 static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
-				void *val, int len, bool exists)
+				void *val, int len, bool exists,
+				bool rtnl_held)
 {
 	struct tcf_meta_ops *ops = find_ife_oplist(metaid);
 	int ret = 0;
@@ -278,9 +279,11 @@ static int load_metaops_and_vet(struct tcf_ife_info *ife, u32 metaid,
 #ifdef CONFIG_MODULES
 		if (exists)
 			spin_unlock_bh(&ife->tcf_lock);
-		rtnl_unlock();
+		if (rtnl_held)
+			rtnl_unlock();
 		request_module("ife-meta-%s", ife_meta_id2name(metaid));
-		rtnl_lock();
+		if (rtnl_held)
+			rtnl_lock();
 		if (exists)
 			spin_lock_bh(&ife->tcf_lock);
 		ops = find_ife_oplist(metaid);
@@ -421,7 +424,7 @@ static void tcf_ife_cleanup(struct tc_action *a)
 
 /* under ife->tcf_lock for existing action */
 static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
-			     bool exists)
+			     bool exists, bool rtnl_held)
 {
 	int len = 0;
 	int rc = 0;
@@ -433,7 +436,8 @@ static int populate_metalist(struct tcf_ife_info *ife, struct nlattr **tb,
 			val = nla_data(tb[i]);
 			len = nla_len(tb[i]);
 
-			rc = load_metaops_and_vet(ife, i, val, len, exists);
+			rc = load_metaops_and_vet(ife, i, val, len, exists,
+						  rtnl_held);
 			if (rc != 0)
 				return rc;
 
@@ -454,7 +458,7 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, ife_net_id);
 	struct nlattr *tb[TCA_IFE_MAX + 1];
 	struct nlattr *tb2[IFE_META_MAX + 1];
-	struct tcf_ife_params *p, *p_old;
+	struct tcf_ife_params *p;
 	struct tcf_ife_info *ife;
 	u16 ife_type = ETH_P_IFE;
 	struct tc_ife *parm;
@@ -558,7 +562,7 @@ metadata_parse_err:
 			return err;
 		}
 
-		err = populate_metalist(ife, tb2, exists);
+		err = populate_metalist(ife, tb2, exists, rtnl_held);
 		if (err)
 			goto metadata_parse_err;
 
@@ -581,13 +585,13 @@ metadata_parse_err:
 	}
 
 	ife->tcf_action = parm->action;
+	/* protected by tcf_lock when modifying existing action */
+	rcu_swap_protected(ife->params, p, 1);
+
 	if (exists)
 		spin_unlock_bh(&ife->tcf_lock);
-
-	p_old = rtnl_dereference(ife->params);
-	rcu_assign_pointer(ife->params, p);
-	if (p_old)
-		kfree_rcu(p_old, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -600,16 +604,20 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_ife_info *ife = to_ife(a);
-	struct tcf_ife_params *p = rtnl_dereference(ife->params);
+	struct tcf_ife_params *p;
 	struct tc_ife opt = {
 		.index = ife->tcf_index,
 		.refcnt = refcount_read(&ife->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&ife->tcf_bindcnt) - bind,
-		.action = ife->tcf_action,
-		.flags = p->flags,
 	};
 	struct tcf_t t;
 
+	spin_lock_bh(&ife->tcf_lock);
+	opt.action = ife->tcf_action;
+	p = rcu_dereference_protected(ife->params,
+				      lockdep_is_held(&ife->tcf_lock));
+	opt.flags = p->flags;
+
 	if (nla_put(skb, TCA_IFE_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
@@ -635,9 +643,11 @@ static int tcf_ife_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 		pr_info("Failed to dump metalist\n");
 	}
 
+	spin_unlock_bh(&ife->tcf_lock);
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock_bh(&ife->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From ff25276de997f41197ebab91935627c249a30fc4 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:45 +0300
Subject: net: sched: act_ipt: remove dependency on rtnl lock

Use tcf spinlock to protect ipt action private data from concurrent
modification during dump. Ipt init already takes tcf spinlock when
modifying ipt state.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index 0dc787a57798..e149f0e66cb6 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -288,6 +288,7 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	 * for foolproof you need to not assume this
 	 */
 
+	spin_lock_bh(&ipt->tcf_lock);
 	t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC);
 	if (unlikely(!t))
 		goto nla_put_failure;
@@ -307,10 +308,12 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 	if (nla_put_64bit(skb, TCA_IPT_TM, sizeof(tm), &tm, TCA_IPT_PAD))
 		goto nla_put_failure;
 
+	spin_unlock_bh(&ipt->tcf_lock);
 	kfree(t);
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock_bh(&ipt->tcf_lock);
 	nlmsg_trim(skb, b);
 	kfree(t);
 	return -1;
-- 
cgit v1.2.3


From 67b0c1a3c9ced3726dea73000f8900f453fc894f Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:46 +0300
Subject: net: sched: act_pedit: remove dependency on rtnl lock

Rearrange pedit init code to only access pedit action data while holding
tcf spinlock. Change keys allocation type to atomic to allow it to execute
while holding tcf spinlock. Take tcf spinlock in dump function when
accessing pedit action data.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 40 ++++++++++++++++++++--------------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 43ba999b2d23..3f62da72ab6a 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -187,44 +187,38 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			tcf_idr_cleanup(tn, parm->index);
 			goto out_free;
 		}
-		p = to_pedit(*a);
-		keys = kmalloc(ksize, GFP_KERNEL);
-		if (!keys) {
-			tcf_idr_release(*a, bind);
-			ret = -ENOMEM;
-			goto out_free;
-		}
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
 		if (bind)
 			goto out_free;
 		if (!ovr) {
-			tcf_idr_release(*a, bind);
 			ret = -EEXIST;
-			goto out_free;
-		}
-		p = to_pedit(*a);
-		if (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys) {
-			keys = kmalloc(ksize, GFP_KERNEL);
-			if (!keys) {
-				ret = -ENOMEM;
-				goto out_free;
-			}
+			goto out_release;
 		}
 	} else {
 		return err;
 	}
 
+	p = to_pedit(*a);
 	spin_lock_bh(&p->tcf_lock);
-	p->tcfp_flags = parm->flags;
-	p->tcf_action = parm->action;
-	if (keys) {
+
+	if (ret == ACT_P_CREATED ||
+	    (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys)) {
+		keys = kmalloc(ksize, GFP_ATOMIC);
+		if (!keys) {
+			spin_unlock_bh(&p->tcf_lock);
+			ret = -ENOMEM;
+			goto out_release;
+		}
 		kfree(p->tcfp_keys);
 		p->tcfp_keys = keys;
 		p->tcfp_nkeys = parm->nkeys;
 	}
 	memcpy(p->tcfp_keys, parm->keys, ksize);
 
+	p->tcfp_flags = parm->flags;
+	p->tcf_action = parm->action;
+
 	kfree(p->tcfp_keys_ex);
 	p->tcfp_keys_ex = keys_ex;
 
@@ -232,6 +226,9 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
+
+out_release:
+	tcf_idr_release(*a, bind);
 out_free:
 	kfree(keys_ex);
 	return ret;
@@ -410,6 +407,7 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 	if (unlikely(!opt))
 		return -ENOBUFS;
 
+	spin_lock_bh(&p->tcf_lock);
 	memcpy(opt->keys, p->tcfp_keys,
 	       p->tcfp_nkeys * sizeof(struct tc_pedit_key));
 	opt->index = p->tcf_index;
@@ -432,11 +430,13 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 	tcf_tm_dump(&t, &p->tcf_tm);
 	if (nla_put_64bit(skb, TCA_PEDIT_TM, sizeof(t), &t, TCA_PEDIT_PAD))
 		goto nla_put_failure;
+	spin_unlock_bh(&p->tcf_lock);
 
 	kfree(opt);
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock_bh(&p->tcf_lock);
 	nlmsg_trim(skb, b);
 	kfree(opt);
 	return -1;
-- 
cgit v1.2.3


From d7728495665601658c7f94f3b5fa4e3f54d71c18 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:47 +0300
Subject: net: sched: act_sample: remove dependency on rtnl lock

Use tcf spinlock to protect private sample action data from concurrent
modification during dump and init.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_sample.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c
index 2608ccc83e5e..81071afe1b43 100644
--- a/net/sched/act_sample.c
+++ b/net/sched/act_sample.c
@@ -80,11 +80,13 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 	}
 	s = to_sample(*a);
 
+	spin_lock(&s->tcf_lock);
 	s->tcf_action = parm->action;
 	s->rate = nla_get_u32(tb[TCA_SAMPLE_RATE]);
 	s->psample_group_num = nla_get_u32(tb[TCA_SAMPLE_PSAMPLE_GROUP]);
 	psample_group = psample_group_get(net, s->psample_group_num);
 	if (!psample_group) {
+		spin_unlock(&s->tcf_lock);
 		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
@@ -94,6 +96,7 @@ static int tcf_sample_init(struct net *net, struct nlattr *nla,
 		s->truncate = true;
 		s->trunc_size = nla_get_u32(tb[TCA_SAMPLE_TRUNC_SIZE]);
 	}
+	spin_unlock(&s->tcf_lock);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -105,7 +108,8 @@ static void tcf_sample_cleanup(struct tc_action *a)
 	struct tcf_sample *s = to_sample(a);
 	struct psample_group *psample_group;
 
-	psample_group = rtnl_dereference(s->psample_group);
+	/* last reference to action, no need to lock */
+	psample_group = rcu_dereference_protected(s->psample_group, 1);
 	RCU_INIT_POINTER(s->psample_group, NULL);
 	if (psample_group)
 		psample_group_put(psample_group);
@@ -174,12 +178,13 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_sample *s = to_sample(a);
 	struct tc_sample opt = {
 		.index      = s->tcf_index,
-		.action     = s->tcf_action,
 		.refcnt     = refcount_read(&s->tcf_refcnt) - ref,
 		.bindcnt    = atomic_read(&s->tcf_bindcnt) - bind,
 	};
 	struct tcf_t t;
 
+	spin_lock(&s->tcf_lock);
+	opt.action = s->tcf_action;
 	if (nla_put(skb, TCA_SAMPLE_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
@@ -196,9 +201,12 @@ static int tcf_sample_dump(struct sk_buff *skb, struct tc_action *a,
 
 	if (nla_put_u32(skb, TCA_SAMPLE_PSAMPLE_GROUP, s->psample_group_num))
 		goto nla_put_failure;
+	spin_unlock(&s->tcf_lock);
+
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&s->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From 5e48180ed8bcfa60e02887ba801307caf14bbe40 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:48 +0300
Subject: net: sched: act_simple: remove dependency on rtnl lock

Use tcf spinlock to protect private simple action data from concurrent
modification during dump. (simple init already uses tcf spinlock when
changing action state)

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_simple.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index aa51152e0066..18e4452574cd 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -156,10 +156,11 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
 		.index   = d->tcf_index,
 		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
-		.action  = d->tcf_action,
 	};
 	struct tcf_t t;
 
+	spin_lock_bh(&d->tcf_lock);
+	opt.action = d->tcf_action;
 	if (nla_put(skb, TCA_DEF_PARMS, sizeof(opt), &opt) ||
 	    nla_put_string(skb, TCA_DEF_DATA, d->tcfd_defdata))
 		goto nla_put_failure;
@@ -167,9 +168,12 @@ static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a,
 	tcf_tm_dump(&t, &d->tcf_tm);
 	if (nla_put_64bit(skb, TCA_DEF_TM, sizeof(t), &t, TCA_DEF_PAD))
 		goto nla_put_failure;
+	spin_unlock_bh(&d->tcf_lock);
+
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock_bh(&d->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From c8814552fe51358f5fc46bc1c4aa4bb68454f4eb Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:49 +0300
Subject: net: sched: act_skbmod: remove dependency on rtnl lock

Move read of skbmod_p rcu pointer to be protected by tcf spinlock. Use tcf
spinlock to protect private skbmod data from concurrent modification during
dump.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index c437c6d51a71..e9c86ade3b40 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -156,7 +156,6 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 
 	d = to_skbmod(*a);
 
-	ASSERT_RTNL();
 	p = kzalloc(sizeof(struct tcf_skbmod_params), GFP_KERNEL);
 	if (unlikely(!p)) {
 		tcf_idr_release(*a, bind);
@@ -166,10 +165,10 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla,
 	p->flags = lflags;
 	d->tcf_action = parm->action;
 
-	p_old = rtnl_dereference(d->skbmod_p);
-
 	if (ovr)
 		spin_lock_bh(&d->tcf_lock);
+	/* Protected by tcf_lock if overwriting existing action. */
+	p_old = rcu_dereference_protected(d->skbmod_p, 1);
 
 	if (lflags & SKBMOD_F_DMAC)
 		ether_addr_copy(p->eth_dst, daddr);
@@ -205,15 +204,18 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
 {
 	struct tcf_skbmod *d = to_skbmod(a);
 	unsigned char *b = skb_tail_pointer(skb);
-	struct tcf_skbmod_params  *p = rtnl_dereference(d->skbmod_p);
+	struct tcf_skbmod_params  *p;
 	struct tc_skbmod opt = {
 		.index   = d->tcf_index,
 		.refcnt  = refcount_read(&d->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&d->tcf_bindcnt) - bind,
-		.action  = d->tcf_action,
 	};
 	struct tcf_t t;
 
+	spin_lock_bh(&d->tcf_lock);
+	opt.action = d->tcf_action;
+	p = rcu_dereference_protected(d->skbmod_p,
+				      lockdep_is_held(&d->tcf_lock));
 	opt.flags  = p->flags;
 	if (nla_put(skb, TCA_SKBMOD_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
@@ -231,8 +233,10 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a,
 	if (nla_put_64bit(skb, TCA_SKBMOD_TM, sizeof(t), &t, TCA_SKBMOD_PAD))
 		goto nla_put_failure;
 
+	spin_unlock_bh(&d->tcf_lock);
 	return skb->len;
 nla_put_failure:
+	spin_unlock_bh(&d->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From 729e01260989cc06c8a78491b46545793aef323a Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:50 +0300
Subject: net: sched: act_tunnel_key: remove dependency on rtnl lock

Use tcf lock to protect tunnel key action struct private data from
concurrent modification in init and dump. Use rcu swap operation to
reassign params pointer under protection of tcf lock. (old params value is
not used by init, so there is no need of standalone rcu dereference step)

Remove rtnl lock assertion that is no longer required.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_tunnel_key.c | 26 +++++++++++++-------------
 1 file changed, 13 insertions(+), 13 deletions(-)

diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index d42d9e112789..ba2ae9f75ef5 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -204,7 +204,6 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 {
 	struct tc_action_net *tn = net_generic(net, tunnel_key_net_id);
 	struct nlattr *tb[TCA_TUNNEL_KEY_MAX + 1];
-	struct tcf_tunnel_key_params *params_old;
 	struct tcf_tunnel_key_params *params_new;
 	struct metadata_dst *metadata = NULL;
 	struct tc_tunnel_key *parm;
@@ -346,24 +345,22 @@ static int tunnel_key_init(struct net *net, struct nlattr *nla,
 
 	t = to_tunnel_key(*a);
 
-	ASSERT_RTNL();
 	params_new = kzalloc(sizeof(*params_new), GFP_KERNEL);
 	if (unlikely(!params_new)) {
 		tcf_idr_release(*a, bind);
 		NL_SET_ERR_MSG(extack, "Cannot allocate tunnel key parameters");
 		return -ENOMEM;
 	}
-
-	params_old = rtnl_dereference(t->params);
-
-	t->tcf_action = parm->action;
 	params_new->tcft_action = parm->t_action;
 	params_new->tcft_enc_metadata = metadata;
 
-	rcu_assign_pointer(t->params, params_new);
-
-	if (params_old)
-		kfree_rcu(params_old, rcu);
+	spin_lock(&t->tcf_lock);
+	t->tcf_action = parm->action;
+	rcu_swap_protected(t->params, params_new,
+			   lockdep_is_held(&t->tcf_lock));
+	spin_unlock(&t->tcf_lock);
+	if (params_new)
+		kfree_rcu(params_new, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -485,12 +482,13 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 		.index    = t->tcf_index,
 		.refcnt   = refcount_read(&t->tcf_refcnt) - ref,
 		.bindcnt  = atomic_read(&t->tcf_bindcnt) - bind,
-		.action   = t->tcf_action,
 	};
 	struct tcf_t tm;
 
-	params = rtnl_dereference(t->params);
-
+	spin_lock(&t->tcf_lock);
+	params = rcu_dereference_protected(t->params,
+					   lockdep_is_held(&t->tcf_lock));
+	opt.action   = t->tcf_action;
 	opt.t_action = params->tcft_action;
 
 	if (nla_put(skb, TCA_TUNNEL_KEY_PARMS, sizeof(opt), &opt))
@@ -522,10 +520,12 @@ static int tunnel_key_dump(struct sk_buff *skb, struct tc_action *a,
 	if (nla_put_64bit(skb, TCA_TUNNEL_KEY_TM, sizeof(tm),
 			  &tm, TCA_TUNNEL_KEY_PAD))
 		goto nla_put_failure;
+	spin_unlock(&t->tcf_lock);
 
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&t->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From 764e9a24480f6ffba5493fb21e6a7b030d6b8b67 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:51 +0300
Subject: net: sched: act_vlan: remove dependency on rtnl lock

Use tcf spinlock to protect vlan action private data from concurrent
modification during dump and init. Use rcu swap operation to reassign
params pointer under protection of tcf lock. (old params value is not used
by init, so there is no need of standalone rcu dereference step)

Remove rtnl assertion that is no longer necessary.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_vlan.c | 27 +++++++++++++++------------
 1 file changed, 15 insertions(+), 12 deletions(-)

diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 15a0ee214c9c..5bde17fe3608 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -109,7 +109,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
-	struct tcf_vlan_params *p, *p_old;
+	struct tcf_vlan_params *p;
 	struct tc_vlan *parm;
 	struct tcf_vlan *v;
 	int action;
@@ -202,26 +202,24 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 
 	v = to_vlan(*a);
 
-	ASSERT_RTNL();
 	p = kzalloc(sizeof(*p), GFP_KERNEL);
 	if (!p) {
 		tcf_idr_release(*a, bind);
 		return -ENOMEM;
 	}
 
-	v->tcf_action = parm->action;
-
-	p_old = rtnl_dereference(v->vlan_p);
-
 	p->tcfv_action = action;
 	p->tcfv_push_vid = push_vid;
 	p->tcfv_push_prio = push_prio;
 	p->tcfv_push_proto = push_proto;
 
-	rcu_assign_pointer(v->vlan_p, p);
+	spin_lock(&v->tcf_lock);
+	v->tcf_action = parm->action;
+	rcu_swap_protected(v->vlan_p, p, lockdep_is_held(&v->tcf_lock));
+	spin_unlock(&v->tcf_lock);
 
-	if (p_old)
-		kfree_rcu(p_old, rcu);
+	if (p)
+		kfree_rcu(p, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
@@ -243,16 +241,18 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_vlan *v = to_vlan(a);
-	struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p);
+	struct tcf_vlan_params *p;
 	struct tc_vlan opt = {
 		.index    = v->tcf_index,
 		.refcnt   = refcount_read(&v->tcf_refcnt) - ref,
 		.bindcnt  = atomic_read(&v->tcf_bindcnt) - bind,
-		.action   = v->tcf_action,
-		.v_action = p->tcfv_action,
 	};
 	struct tcf_t t;
 
+	spin_lock(&v->tcf_lock);
+	opt.action = v->tcf_action;
+	p = rcu_dereference_protected(v->vlan_p, lockdep_is_held(&v->tcf_lock));
+	opt.v_action = p->tcfv_action;
 	if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
@@ -268,9 +268,12 @@ static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 	tcf_tm_dump(&t, &v->tcf_tm);
 	if (nla_put_64bit(skb, TCA_VLAN_TM, sizeof(t), &t, TCA_VLAN_PAD))
 		goto nla_put_failure;
+	spin_unlock(&v->tcf_lock);
+
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&v->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From 84a75b329be84c108a21ab9c02a52a9bf9e5a919 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:52 +0300
Subject: net: sched: extend action ops with put_dev callback

As a preparation for removing dependency on rtnl lock from rules update
path, all users of shared objects must take reference while working with
them.

Extend action ops with put_dev() API to be used on net device returned by
get_dev().

Modify mirred action (only action that implements get_dev callback):
- Take reference to net device in get_dev.
- Implement put_dev API that releases reference to net device.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/act_api.h  |  1 +
 net/sched/act_mirred.c | 12 +++++++++++-
 net/sched/cls_api.c    |  1 +
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/net/act_api.h b/include/net/act_api.h
index 8c9bc02d05e1..1ad5b19e83a9 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -101,6 +101,7 @@ struct tc_action_ops {
 	void	(*stats_update)(struct tc_action *, u64, u32, u64);
 	size_t  (*get_fill_size)(const struct tc_action *act);
 	struct net_device *(*get_dev)(const struct tc_action *a);
+	void	(*put_dev)(struct net_device *dev);
 	int     (*delete)(struct net *net, u32 index);
 };
 
diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index b26d060da08e..7a045cc7fe3b 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -358,8 +358,17 @@ static struct notifier_block mirred_device_notifier = {
 static struct net_device *tcf_mirred_get_dev(const struct tc_action *a)
 {
 	struct tcf_mirred *m = to_mirred(a);
+	struct net_device *dev = rtnl_dereference(m->tcfm_dev);
+
+	if (dev)
+		dev_hold(dev);
 
-	return rtnl_dereference(m->tcfm_dev);
+	return dev;
+}
+
+static void tcf_mirred_put_dev(struct net_device *dev)
+{
+	dev_put(dev);
 }
 
 static int tcf_mirred_delete(struct net *net, u32 index)
@@ -382,6 +391,7 @@ static struct tc_action_ops act_mirred_ops = {
 	.lookup		=	tcf_mirred_search,
 	.size		=	sizeof(struct tcf_mirred),
 	.get_dev	=	tcf_mirred_get_dev,
+	.put_dev	=	tcf_mirred_put_dev,
 	.delete		=	tcf_mirred_delete,
 };
 
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index f922ce27ed5e..31bd1439cf60 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -2176,6 +2176,7 @@ static int tc_exts_setup_cb_egdev_call(struct tcf_exts *exts,
 		if (!dev)
 			continue;
 		ret = tc_setup_cb_egdev_call(dev, type, type_data, err_stop);
+		a->ops->put_dev(dev);
 		if (ret < 0)
 			return ret;
 		ok_count += ret;
-- 
cgit v1.2.3


From 4e232818bd32b29f15bef532f320a14367d172b4 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:53 +0300
Subject: net: sched: act_mirred: remove dependency on rtnl lock

Re-introduce mirred list spinlock, that was removed some time ago, in order
to protect it from concurrent modifications, instead of relying on rtnl
lock.

Use tcf spinlock to protect mirred action private data from concurrent
modification in init and dump. Rearrange access to mirred data in order to
be performed only while holding the lock.

Rearrange net dev access to always hold reference while working with it,
instead of relying on rntl lock.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_mirred.c | 78 +++++++++++++++++++++++++++++++++-----------------
 1 file changed, 51 insertions(+), 27 deletions(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 7a045cc7fe3b..327be257033d 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -30,6 +30,7 @@
 #include <net/tc_act/tc_mirred.h>
 
 static LIST_HEAD(mirred_list);
+static DEFINE_SPINLOCK(mirred_list_lock);
 
 static bool tcf_mirred_is_act_redirect(int action)
 {
@@ -62,13 +63,23 @@ static bool tcf_mirred_can_reinsert(int action)
 	return false;
 }
 
+static struct net_device *tcf_mirred_dev_dereference(struct tcf_mirred *m)
+{
+	return rcu_dereference_protected(m->tcfm_dev,
+					 lockdep_is_held(&m->tcf_lock));
+}
+
 static void tcf_mirred_release(struct tc_action *a)
 {
 	struct tcf_mirred *m = to_mirred(a);
 	struct net_device *dev;
 
+	spin_lock(&mirred_list_lock);
 	list_del(&m->tcfm_list);
-	dev = rtnl_dereference(m->tcfm_dev);
+	spin_unlock(&mirred_list_lock);
+
+	/* last reference to action, no need to lock */
+	dev = rcu_dereference_protected(m->tcfm_dev, 1);
 	if (dev)
 		dev_put(dev);
 }
@@ -128,22 +139,9 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 		NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option");
 		return -EINVAL;
 	}
-	if (parm->ifindex) {
-		dev = __dev_get_by_index(net, parm->ifindex);
-		if (dev == NULL) {
-			if (exists)
-				tcf_idr_release(*a, bind);
-			else
-				tcf_idr_cleanup(tn, parm->index);
-			return -ENODEV;
-		}
-		mac_header_xmit = dev_is_mac_header_xmit(dev);
-	} else {
-		dev = NULL;
-	}
 
 	if (!exists) {
-		if (!dev) {
+		if (!parm->ifindex) {
 			tcf_idr_cleanup(tn, parm->index);
 			NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist");
 			return -EINVAL;
@@ -161,19 +159,31 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	}
 	m = to_mirred(*a);
 
-	ASSERT_RTNL();
+	spin_lock(&m->tcf_lock);
 	m->tcf_action = parm->action;
 	m->tcfm_eaction = parm->eaction;
-	if (dev != NULL) {
-		if (ret != ACT_P_CREATED)
-			dev_put(rcu_dereference_protected(m->tcfm_dev, 1));
-		dev_hold(dev);
-		rcu_assign_pointer(m->tcfm_dev, dev);
+
+	if (parm->ifindex) {
+		dev = dev_get_by_index(net, parm->ifindex);
+		if (!dev) {
+			spin_unlock(&m->tcf_lock);
+			tcf_idr_release(*a, bind);
+			return -ENODEV;
+		}
+		mac_header_xmit = dev_is_mac_header_xmit(dev);
+		rcu_swap_protected(m->tcfm_dev, dev,
+				   lockdep_is_held(&m->tcf_lock));
+		if (dev)
+			dev_put(dev);
 		m->tcfm_mac_header_xmit = mac_header_xmit;
 	}
+	spin_unlock(&m->tcf_lock);
 
 	if (ret == ACT_P_CREATED) {
+		spin_lock(&mirred_list_lock);
 		list_add(&m->tcfm_list, &mirred_list);
+		spin_unlock(&mirred_list_lock);
+
 		tcf_idr_insert(tn, *a);
 	}
 
@@ -287,26 +297,33 @@ static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind,
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_mirred *m = to_mirred(a);
-	struct net_device *dev = rtnl_dereference(m->tcfm_dev);
 	struct tc_mirred opt = {
 		.index   = m->tcf_index,
-		.action  = m->tcf_action,
 		.refcnt  = refcount_read(&m->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&m->tcf_bindcnt) - bind,
-		.eaction = m->tcfm_eaction,
-		.ifindex = dev ? dev->ifindex : 0,
 	};
+	struct net_device *dev;
 	struct tcf_t t;
 
+	spin_lock(&m->tcf_lock);
+	opt.action = m->tcf_action;
+	opt.eaction = m->tcfm_eaction;
+	dev = tcf_mirred_dev_dereference(m);
+	if (dev)
+		opt.ifindex = dev->ifindex;
+
 	if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
 	tcf_tm_dump(&t, &m->tcf_tm);
 	if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD))
 		goto nla_put_failure;
+	spin_unlock(&m->tcf_lock);
+
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock(&m->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
@@ -337,15 +354,19 @@ static int mirred_device_event(struct notifier_block *unused,
 
 	ASSERT_RTNL();
 	if (event == NETDEV_UNREGISTER) {
+		spin_lock(&mirred_list_lock);
 		list_for_each_entry(m, &mirred_list, tcfm_list) {
-			if (rcu_access_pointer(m->tcfm_dev) == dev) {
+			spin_lock(&m->tcf_lock);
+			if (tcf_mirred_dev_dereference(m) == dev) {
 				dev_put(dev);
 				/* Note : no rcu grace period necessary, as
 				 * net_device are already rcu protected.
 				 */
 				RCU_INIT_POINTER(m->tcfm_dev, NULL);
 			}
+			spin_unlock(&m->tcf_lock);
 		}
+		spin_unlock(&mirred_list_lock);
 	}
 
 	return NOTIFY_DONE;
@@ -358,10 +379,13 @@ static struct notifier_block mirred_device_notifier = {
 static struct net_device *tcf_mirred_get_dev(const struct tc_action *a)
 {
 	struct tcf_mirred *m = to_mirred(a);
-	struct net_device *dev = rtnl_dereference(m->tcfm_dev);
+	struct net_device *dev;
 
+	rcu_read_lock();
+	dev = rcu_dereference(m->tcfm_dev);
 	if (dev)
 		dev_hold(dev);
+	rcu_read_unlock();
 
 	return dev;
 }
-- 
cgit v1.2.3


From 51a9f5ae653979ac4bdbd81778a10431f0177e3c Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:54 +0300
Subject: net: core: protect rate estimator statistics pointer with lock

Extend gen_new_estimator() to also take stats_lock when re-assigning rate
estimator statistics pointer. (to be used by unlocked actions)

Rename 'stats_lock' to 'lock' and change argument description to explain
that it is now also used for control path.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/gen_stats.h  |  4 ++--
 net/core/gen_estimator.c | 21 +++++++++++++--------
 2 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index 0304ba2ae353..883bb9085f15 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -59,13 +59,13 @@ int gnet_stats_finish_copy(struct gnet_dump *d);
 int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct net_rate_estimator __rcu **rate_est,
-		      spinlock_t *stats_lock,
+		      spinlock_t *lock,
 		      seqcount_t *running, struct nlattr *opt);
 void gen_kill_estimator(struct net_rate_estimator __rcu **ptr);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct net_rate_estimator __rcu **ptr,
-			  spinlock_t *stats_lock,
+			  spinlock_t *lock,
 			  seqcount_t *running, struct nlattr *opt);
 bool gen_estimator_active(struct net_rate_estimator __rcu **ptr);
 bool gen_estimator_read(struct net_rate_estimator __rcu **ptr,
diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c
index 98fd12721221..e4e442d70c2d 100644
--- a/net/core/gen_estimator.c
+++ b/net/core/gen_estimator.c
@@ -112,7 +112,7 @@ static void est_timer(struct timer_list *t)
  * @bstats: basic statistics
  * @cpu_bstats: bstats per cpu
  * @rate_est: rate estimator statistics
- * @stats_lock: statistics lock
+ * @lock: lock for statistics and control path
  * @running: qdisc running seqcount
  * @opt: rate estimator configuration TLV
  *
@@ -128,7 +128,7 @@ static void est_timer(struct timer_list *t)
 int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 		      struct net_rate_estimator __rcu **rate_est,
-		      spinlock_t *stats_lock,
+		      spinlock_t *lock,
 		      seqcount_t *running,
 		      struct nlattr *opt)
 {
@@ -154,19 +154,22 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 	seqcount_init(&est->seq);
 	intvl_log = parm->interval + 2;
 	est->bstats = bstats;
-	est->stats_lock = stats_lock;
+	est->stats_lock = lock;
 	est->running  = running;
 	est->ewma_log = parm->ewma_log;
 	est->intvl_log = intvl_log;
 	est->cpu_bstats = cpu_bstats;
 
-	if (stats_lock)
+	if (lock)
 		local_bh_disable();
 	est_fetch_counters(est, &b);
-	if (stats_lock)
+	if (lock)
 		local_bh_enable();
 	est->last_bytes = b.bytes;
 	est->last_packets = b.packets;
+
+	if (lock)
+		spin_lock_bh(lock);
 	old = rcu_dereference_protected(*rate_est, 1);
 	if (old) {
 		del_timer_sync(&old->timer);
@@ -179,6 +182,8 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
 	mod_timer(&est->timer, est->next_jiffies);
 
 	rcu_assign_pointer(*rate_est, est);
+	if (lock)
+		spin_unlock_bh(lock);
 	if (old)
 		kfree_rcu(old, rcu);
 	return 0;
@@ -209,7 +214,7 @@ EXPORT_SYMBOL(gen_kill_estimator);
  * @bstats: basic statistics
  * @cpu_bstats: bstats per cpu
  * @rate_est: rate estimator statistics
- * @stats_lock: statistics lock
+ * @lock: lock for statistics and control path
  * @running: qdisc running seqcount (might be NULL)
  * @opt: rate estimator configuration TLV
  *
@@ -221,11 +226,11 @@ EXPORT_SYMBOL(gen_kill_estimator);
 int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
 			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
 			  struct net_rate_estimator __rcu **rate_est,
-			  spinlock_t *stats_lock,
+			  spinlock_t *lock,
 			  seqcount_t *running, struct nlattr *opt)
 {
 	return gen_new_estimator(bstats, cpu_bstats, rate_est,
-				 stats_lock, running, opt);
+				 lock, running, opt);
 }
 EXPORT_SYMBOL(gen_replace_estimator);
 
-- 
cgit v1.2.3


From e329bc427395e2d74f2bb685ef3dddda91a6695f Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Fri, 10 Aug 2018 20:51:55 +0300
Subject: net: sched: act_police: remove dependency on rtnl lock

Use tcf spinlock to protect police action private data from concurrent
modification during dump. (init already uses tcf spinlock when changing
police action state)

Pass tcf spinlock as estimator lock argument to gen_replace_estimator()
during action init.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_police.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 1f3192ea8df7..88c16d80c1cf 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -274,14 +274,15 @@ static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a,
 	struct tcf_police *police = to_police(a);
 	struct tc_police opt = {
 		.index = police->tcf_index,
-		.action = police->tcf_action,
-		.mtu = police->tcfp_mtu,
-		.burst = PSCHED_NS2TICKS(police->tcfp_burst),
 		.refcnt = refcount_read(&police->tcf_refcnt) - ref,
 		.bindcnt = atomic_read(&police->tcf_bindcnt) - bind,
 	};
 	struct tcf_t t;
 
+	spin_lock_bh(&police->tcf_lock);
+	opt.action = police->tcf_action;
+	opt.mtu = police->tcfp_mtu;
+	opt.burst = PSCHED_NS2TICKS(police->tcfp_burst);
 	if (police->rate_present)
 		psched_ratecfg_getrate(&opt.rate, &police->rate);
 	if (police->peak_present)
@@ -301,10 +302,12 @@ static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a,
 	t.expires = jiffies_to_clock_t(police->tcf_tm.expires);
 	if (nla_put_64bit(skb, TCA_POLICE_TM, sizeof(t), &t, TCA_POLICE_PAD))
 		goto nla_put_failure;
+	spin_unlock_bh(&police->tcf_lock);
 
 	return skb->len;
 
 nla_put_failure:
+	spin_unlock_bh(&police->tcf_lock);
 	nlmsg_trim(skb, b);
 	return -1;
 }
-- 
cgit v1.2.3


From b86d865cb1cae1e61527ea0b8977078bbf694328 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bart.vanassche@wdc.com>
Date: Fri, 10 Aug 2018 13:28:07 -0700
Subject: blkcg: Make blkg_root_lookup() work for queues in bypass mode

For legacy queues the only call of blkg_root_lookup() happens after
bypass mode has been enabled. Since blkg_lookup() returns NULL for
queues in bypass mode, modify the blkg_root_lookup() such that it
no longer depends on bypass mode. Rename the function into
blk_queue_root_blkg() as suggested by Tejun.

Suggested-by: Tejun Heo <tj@kernel.org>
Fixes: 6bad9b210a22 ("blkcg: Introduce blkg_root_lookup()")
Signed-off-by: Bart Van Assche <bart.vanassche@wdc.com>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-sysfs.c          |  2 +-
 include/linux/blk-cgroup.h | 15 +++++----------
 2 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 380bc284ced1..bb109bb0a055 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -813,7 +813,7 @@ static void __blk_release_queue(struct work_struct *work)
 		blk_exit_queue(q);
 	}
 
-	WARN(blkg_root_lookup(q),
+	WARN(blk_queue_root_blkg(q),
 	     "request queue %p is being released but it has not yet been removed from the blkcg controller\n",
 	     q);
 
diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h
index 1361cfc9b878..34aec30e06c7 100644
--- a/include/linux/blk-cgroup.h
+++ b/include/linux/blk-cgroup.h
@@ -342,20 +342,14 @@ static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg,
 }
 
 /**
- * blkg_lookup - look up blkg for the specified request queue
+ * blk_queue_root_blkg - return blkg for the (blkcg_root, @q) pair
  * @q: request_queue of interest
  *
  * Lookup blkg for @q at the root level. See also blkg_lookup().
  */
-static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q)
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
 {
-	struct blkcg_gq *blkg;
-
-	rcu_read_lock();
-	blkg = blkg_lookup(&blkcg_root, q);
-	rcu_read_unlock();
-
-	return blkg;
+	return q->root_blkg;
 }
 
 /**
@@ -881,7 +875,8 @@ static inline bool blk_cgroup_congested(void) { return false; }
 static inline void blkcg_schedule_throttle(struct request_queue *q, bool use_memdelay) { }
 
 static inline struct blkcg_gq *blkg_lookup(struct blkcg *blkcg, void *key) { return NULL; }
-static inline struct blkcg_gq *blkg_root_lookup(struct request_queue *q) { return NULL; }
+static inline struct blkcg_gq *blk_queue_root_blkg(struct request_queue *q)
+{ return NULL; }
 static inline int blkcg_init_queue(struct request_queue *q) { return 0; }
 static inline void blkcg_drain_queue(struct request_queue *q) { }
 static inline void blkcg_exit_queue(struct request_queue *q) { }
-- 
cgit v1.2.3


From 353c9cb360874e737fb000545f783df756c06f9a Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Sat, 11 Aug 2018 20:27:24 +0000
Subject: ip: add helpers to process in-order fragments faster.

This patch introduces several helper functions/macros that will be
used in the follow-up patch. No runtime changes yet.

The new logic (fully implemented in the second patch) is as follows:

* Nodes in the rb-tree will now contain not single fragments, but lists
  of consecutive fragments ("runs").

* At each point in time, the current "active" run at the tail is
  maintained/tracked. Fragments that arrive in-order, adjacent
  to the previous tail fragment, are added to this tail run without
  triggering the re-balancing of the rb-tree.

* If a fragment arrives out of order with the offset _before_ the tail run,
  it is inserted into the rb-tree as a single fragment.

* If a fragment arrives after the current tail fragment (with a gap),
  it starts a new "tail" run, as is inserted into the rb-tree
  at the end as the head of the new run.

skb->cb is used to store additional information
needed here (suggested by Eric Dumazet).

Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_frag.h |  6 ++++
 net/ipv4/ip_fragment.c  | 73 +++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index b86d14528188..1662cbc0b46b 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -57,7 +57,9 @@ struct frag_v6_compare_key {
  * @lock: spinlock protecting this frag
  * @refcnt: reference count of the queue
  * @fragments: received fragments head
+ * @rb_fragments: received fragments rb-tree root
  * @fragments_tail: received fragments tail
+ * @last_run_head: the head of the last "run". see ip_fragment.c
  * @stamp: timestamp of the last received fragment
  * @len: total length of the original datagram
  * @meat: length of received fragments so far
@@ -78,6 +80,7 @@ struct inet_frag_queue {
 	struct sk_buff		*fragments;  /* Used in IPv6. */
 	struct rb_root		rb_fragments; /* Used in IPv4. */
 	struct sk_buff		*fragments_tail;
+	struct sk_buff		*last_run_head;
 	ktime_t			stamp;
 	int			len;
 	int			meat;
@@ -113,6 +116,9 @@ void inet_frag_kill(struct inet_frag_queue *q);
 void inet_frag_destroy(struct inet_frag_queue *q);
 struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);
 
+/* Free all skbs in the queue; return the sum of their truesizes. */
+unsigned int inet_frag_rbtree_purge(struct rb_root *root);
+
 static inline void inet_frag_put(struct inet_frag_queue *q)
 {
 	if (refcount_dec_and_test(&q->refcnt))
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 7cb7ed761d8c..26ace9d2d976 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -57,6 +57,57 @@
  */
 static const char ip_frag_cache_name[] = "ip4-frags";
 
+/* Use skb->cb to track consecutive/adjacent fragments coming at
+ * the end of the queue. Nodes in the rb-tree queue will
+ * contain "runs" of one or more adjacent fragments.
+ *
+ * Invariants:
+ * - next_frag is NULL at the tail of a "run";
+ * - the head of a "run" has the sum of all fragment lengths in frag_run_len.
+ */
+struct ipfrag_skb_cb {
+	struct inet_skb_parm	h;
+	struct sk_buff		*next_frag;
+	int			frag_run_len;
+};
+
+#define FRAG_CB(skb)		((struct ipfrag_skb_cb *)((skb)->cb))
+
+static void ip4_frag_init_run(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb));
+
+	FRAG_CB(skb)->next_frag = NULL;
+	FRAG_CB(skb)->frag_run_len = skb->len;
+}
+
+/* Append skb to the last "run". */
+static void ip4_frag_append_to_last_run(struct inet_frag_queue *q,
+					struct sk_buff *skb)
+{
+	RB_CLEAR_NODE(&skb->rbnode);
+	FRAG_CB(skb)->next_frag = NULL;
+
+	FRAG_CB(q->last_run_head)->frag_run_len += skb->len;
+	FRAG_CB(q->fragments_tail)->next_frag = skb;
+	q->fragments_tail = skb;
+}
+
+/* Create a new "run" with the skb. */
+static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb)
+{
+	if (q->last_run_head)
+		rb_link_node(&skb->rbnode, &q->last_run_head->rbnode,
+			     &q->last_run_head->rbnode.rb_right);
+	else
+		rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node);
+	rb_insert_color(&skb->rbnode, &q->rb_fragments);
+
+	ip4_frag_init_run(skb);
+	q->fragments_tail = skb;
+	q->last_run_head = skb;
+}
+
 /* Describe an entry in the "incomplete datagrams" queue. */
 struct ipq {
 	struct inet_frag_queue q;
@@ -654,6 +705,28 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user)
 }
 EXPORT_SYMBOL(ip_check_defrag);
 
+unsigned int inet_frag_rbtree_purge(struct rb_root *root)
+{
+	struct rb_node *p = rb_first(root);
+	unsigned int sum = 0;
+
+	while (p) {
+		struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode);
+
+		p = rb_next(p);
+		rb_erase(&skb->rbnode, root);
+		while (skb) {
+			struct sk_buff *next = FRAG_CB(skb)->next_frag;
+
+			sum += skb->truesize;
+			kfree_skb(skb);
+			skb = next;
+		}
+	}
+	return sum;
+}
+EXPORT_SYMBOL(inet_frag_rbtree_purge);
+
 #ifdef CONFIG_SYSCTL
 static int dist_min;
 
-- 
cgit v1.2.3


From a4fd284a1f8fd4b6c59aa59db2185b1e17c5c11c Mon Sep 17 00:00:00 2001
From: Peter Oskolkov <posk@google.com>
Date: Sat, 11 Aug 2018 20:27:25 +0000
Subject: ip: process in-order fragments efficiently

This patch changes the runtime behavior of IP defrag queue:
incoming in-order fragments are added to the end of the current
list/"run" of in-order fragments at the tail.

On some workloads, UDP stream performance is substantially improved:

RX: ./udp_stream -F 10 -T 2 -l 60
TX: ./udp_stream -c -H <host> -F 10 -T 5 -l 60

with this patchset applied on a 10Gbps receiver:

  throughput=9524.18
  throughput_units=Mbit/s

upstream (net-next):

  throughput=4608.93
  throughput_units=Mbit/s

Reported-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Peter Oskolkov <posk@google.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/inet_fragment.c |   2 +-
 net/ipv4/ip_fragment.c   | 110 +++++++++++++++++++++++++++++------------------
 2 files changed, 70 insertions(+), 42 deletions(-)

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 6d258a5669e7..bcb11f3a27c0 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -146,7 +146,7 @@ void inet_frag_destroy(struct inet_frag_queue *q)
 			fp = xp;
 		} while (fp);
 	} else {
-		sum_truesize = skb_rbtree_purge(&q->rb_fragments);
+		sum_truesize = inet_frag_rbtree_purge(&q->rb_fragments);
 	}
 	sum = sum_truesize + f->qsize;
 
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 26ace9d2d976..88281fbce88c 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -126,8 +126,8 @@ static u8 ip4_frag_ecn(u8 tos)
 
 static struct inet_frags ip4_frags;
 
-static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
-			 struct net_device *dev);
+static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
+			 struct sk_buff *prev_tail, struct net_device *dev);
 
 
 static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
@@ -219,7 +219,12 @@ static void ip_expire(struct timer_list *t)
 		head = skb_rb_first(&qp->q.rb_fragments);
 		if (!head)
 			goto out;
-		rb_erase(&head->rbnode, &qp->q.rb_fragments);
+		if (FRAG_CB(head)->next_frag)
+			rb_replace_node(&head->rbnode,
+					&FRAG_CB(head)->next_frag->rbnode,
+					&qp->q.rb_fragments);
+		else
+			rb_erase(&head->rbnode, &qp->q.rb_fragments);
 		memset(&head->rbnode, 0, sizeof(head->rbnode));
 		barrier();
 	}
@@ -320,7 +325,7 @@ static int ip_frag_reinit(struct ipq *qp)
 		return -ETIMEDOUT;
 	}
 
-	sum_truesize = skb_rbtree_purge(&qp->q.rb_fragments);
+	sum_truesize = inet_frag_rbtree_purge(&qp->q.rb_fragments);
 	sub_frag_mem_limit(qp->q.net, sum_truesize);
 
 	qp->q.flags = 0;
@@ -329,6 +334,7 @@ static int ip_frag_reinit(struct ipq *qp)
 	qp->q.fragments = NULL;
 	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
+	qp->q.last_run_head = NULL;
 	qp->iif = 0;
 	qp->ecn = 0;
 
@@ -340,7 +346,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct rb_node **rbn, *parent;
-	struct sk_buff *skb1;
+	struct sk_buff *skb1, *prev_tail;
 	struct net_device *dev;
 	unsigned int fragsize;
 	int flags, offset;
@@ -418,38 +424,41 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	 */
 
 	/* Find out where to put this fragment.  */
-	skb1 = qp->q.fragments_tail;
-	if (!skb1) {
-		/* This is the first fragment we've received. */
-		rb_link_node(&skb->rbnode, NULL, &qp->q.rb_fragments.rb_node);
-		qp->q.fragments_tail = skb;
-	} else if ((skb1->ip_defrag_offset + skb1->len) < end) {
-		/* This is the common/special case: skb goes to the end. */
+	prev_tail = qp->q.fragments_tail;
+	if (!prev_tail)
+		ip4_frag_create_run(&qp->q, skb);  /* First fragment. */
+	else if (prev_tail->ip_defrag_offset + prev_tail->len < end) {
+		/* This is the common case: skb goes to the end. */
 		/* Detect and discard overlaps. */
-		if (offset < (skb1->ip_defrag_offset + skb1->len))
+		if (offset < prev_tail->ip_defrag_offset + prev_tail->len)
 			goto discard_qp;
-		/* Insert after skb1. */
-		rb_link_node(&skb->rbnode, &skb1->rbnode, &skb1->rbnode.rb_right);
-		qp->q.fragments_tail = skb;
+		if (offset == prev_tail->ip_defrag_offset + prev_tail->len)
+			ip4_frag_append_to_last_run(&qp->q, skb);
+		else
+			ip4_frag_create_run(&qp->q, skb);
 	} else {
-		/* Binary search. Note that skb can become the first fragment, but
-		 * not the last (covered above). */
+		/* Binary search. Note that skb can become the first fragment,
+		 * but not the last (covered above).
+		 */
 		rbn = &qp->q.rb_fragments.rb_node;
 		do {
 			parent = *rbn;
 			skb1 = rb_to_skb(parent);
 			if (end <= skb1->ip_defrag_offset)
 				rbn = &parent->rb_left;
-			else if (offset >= skb1->ip_defrag_offset + skb1->len)
+			else if (offset >= skb1->ip_defrag_offset +
+						FRAG_CB(skb1)->frag_run_len)
 				rbn = &parent->rb_right;
 			else /* Found an overlap with skb1. */
 				goto discard_qp;
 		} while (*rbn);
 		/* Here we have parent properly set, and rbn pointing to
-		 * one of its NULL left/right children. Insert skb. */
+		 * one of its NULL left/right children. Insert skb.
+		 */
+		ip4_frag_init_run(skb);
 		rb_link_node(&skb->rbnode, parent, rbn);
+		rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
 	}
-	rb_insert_color(&skb->rbnode, &qp->q.rb_fragments);
 
 	if (dev)
 		qp->iif = dev->ifindex;
@@ -476,7 +485,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = ip_frag_reasm(qp, skb, dev);
+		err = ip_frag_reasm(qp, skb, prev_tail, dev);
 		skb->_skb_refdst = orefdst;
 		return err;
 	}
@@ -495,7 +504,7 @@ err:
 
 /* Build a new IP datagram from all its fragments. */
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
-			 struct net_device *dev)
+			 struct sk_buff *prev_tail, struct net_device *dev)
 {
 	struct net *net = container_of(qp->q.net, struct net, ipv4.frags);
 	struct iphdr *iph;
@@ -519,10 +528,16 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 		fp = skb_clone(skb, GFP_ATOMIC);
 		if (!fp)
 			goto out_nomem;
-		rb_replace_node(&skb->rbnode, &fp->rbnode, &qp->q.rb_fragments);
+		FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag;
+		if (RB_EMPTY_NODE(&skb->rbnode))
+			FRAG_CB(prev_tail)->next_frag = fp;
+		else
+			rb_replace_node(&skb->rbnode, &fp->rbnode,
+					&qp->q.rb_fragments);
 		if (qp->q.fragments_tail == skb)
 			qp->q.fragments_tail = fp;
 		skb_morph(skb, head);
+		FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag;
 		rb_replace_node(&head->rbnode, &skb->rbnode,
 				&qp->q.rb_fragments);
 		consume_skb(head);
@@ -558,7 +573,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
 			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
 		clone->len = clone->data_len = head->data_len - plen;
-		skb->truesize += clone->truesize;
+		head->truesize += clone->truesize;
 		clone->csum = 0;
 		clone->ip_summed = head->ip_summed;
 		add_frag_mem_limit(qp->q.net, clone->truesize);
@@ -571,24 +586,36 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	skb_push(head, head->data - skb_network_header(head));
 
 	/* Traverse the tree in order, to build frag_list. */
+	fp = FRAG_CB(head)->next_frag;
 	rbn = rb_next(&head->rbnode);
 	rb_erase(&head->rbnode, &qp->q.rb_fragments);
-	while (rbn) {
-		struct rb_node *rbnext = rb_next(rbn);
-		fp = rb_to_skb(rbn);
-		rb_erase(rbn, &qp->q.rb_fragments);
-		rbn = rbnext;
-		*nextp = fp;
-		nextp = &fp->next;
-		fp->prev = NULL;
-		memset(&fp->rbnode, 0, sizeof(fp->rbnode));
-		head->data_len += fp->len;
-		head->len += fp->len;
-		if (head->ip_summed != fp->ip_summed)
-			head->ip_summed = CHECKSUM_NONE;
-		else if (head->ip_summed == CHECKSUM_COMPLETE)
-			head->csum = csum_add(head->csum, fp->csum);
-		head->truesize += fp->truesize;
+	while (rbn || fp) {
+		/* fp points to the next sk_buff in the current run;
+		 * rbn points to the next run.
+		 */
+		/* Go through the current run. */
+		while (fp) {
+			*nextp = fp;
+			nextp = &fp->next;
+			fp->prev = NULL;
+			memset(&fp->rbnode, 0, sizeof(fp->rbnode));
+			head->data_len += fp->len;
+			head->len += fp->len;
+			if (head->ip_summed != fp->ip_summed)
+				head->ip_summed = CHECKSUM_NONE;
+			else if (head->ip_summed == CHECKSUM_COMPLETE)
+				head->csum = csum_add(head->csum, fp->csum);
+			head->truesize += fp->truesize;
+			fp = FRAG_CB(fp)->next_frag;
+		}
+		/* Move to the next run. */
+		if (rbn) {
+			struct rb_node *rbnext = rb_next(rbn);
+
+			fp = rb_to_skb(rbn);
+			rb_erase(rbn, &qp->q.rb_fragments);
+			rbn = rbnext;
+		}
 	}
 	sub_frag_mem_limit(qp->q.net, head->truesize);
 
@@ -624,6 +651,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	qp->q.fragments = NULL;
 	qp->q.rb_fragments = RB_ROOT;
 	qp->q.fragments_tail = NULL;
+	qp->q.last_run_head = NULL;
 	return 0;
 
 out_nomem:
-- 
cgit v1.2.3


From e25ff835af89a80aa6a4de58f413e494b2b96bd1 Mon Sep 17 00:00:00 2001
From: Dave Jiang <dave.jiang@intel.com>
Date: Fri, 10 Aug 2018 08:48:18 -0700
Subject: xfs: Close race between direct IO and xfs_break_layouts()

This patch is the duplicate of ross's fix for ext4 for xfs.

If the refcount of a page is lowered between the time that it is returned
by dax_busy_page() and when the refcount is again checked in
xfs_break_layouts() => ___wait_var_event(), the waiting function
xfs_wait_dax_page() will never be called.  This means that
xfs_break_layouts() will still have 'retry' set to false, so we'll stop
looping and never check the refcount of other pages in this inode.

Instead, always continue looping as long as dax_layout_busy_page() gives us
a page which it found with an elevated refcount.

Signed-off-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs_file.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 6b31f41eafa2..181e9084519b 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -721,12 +721,10 @@ xfs_file_write_iter(
 
 static void
 xfs_wait_dax_page(
-	struct inode		*inode,
-	bool			*did_unlock)
+	struct inode		*inode)
 {
 	struct xfs_inode        *ip = XFS_I(inode);
 
-	*did_unlock = true;
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	schedule();
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
@@ -735,7 +733,7 @@ xfs_wait_dax_page(
 static int
 xfs_break_dax_layouts(
 	struct inode		*inode,
-	bool			*did_unlock)
+	bool			*retry)
 {
 	struct page		*page;
 
@@ -745,9 +743,10 @@ xfs_break_dax_layouts(
 	if (!page)
 		return 0;
 
+	*retry = true;
 	return ___wait_var_event(&page->_refcount,
 			atomic_read(&page->_refcount) == 1, TASK_INTERRUPTIBLE,
-			0, 0, xfs_wait_dax_page(inode, did_unlock));
+			0, 0, xfs_wait_dax_page(inode));
 }
 
 int
-- 
cgit v1.2.3


From 10259de1d8690a8c6dd98d564ff2690b5511c8f7 Mon Sep 17 00:00:00 2001
From: Andreas Gruenbacher <agruenba@redhat.com>
Date: Fri, 10 Aug 2018 11:46:14 -0700
Subject: iomap: Switch to offset_in_page for clarity

Instead of open-coding pos & (PAGE_SIZE - 1) and pos & ~PAGE_MASK, use
the offset_in_page macro.

Signed-off-by: Andreas Gruenbacher <agruenba@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/iomap.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/fs/iomap.c b/fs/iomap.c
index 07501a647d13..8bd54c08deee 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -145,11 +145,11 @@ iomap_adjust_read_range(struct inode *inode, struct iomap_page *iop,
 {
 	unsigned block_bits = inode->i_blkbits;
 	unsigned block_size = (1 << block_bits);
-	unsigned poff = *pos & (PAGE_SIZE - 1);
+	unsigned poff = offset_in_page(*pos);
 	unsigned plen = min_t(loff_t, PAGE_SIZE - poff, length);
 	unsigned first = poff >> block_bits;
 	unsigned last = (poff + plen - 1) >> block_bits;
-	unsigned end = (i_size_read(inode) & (PAGE_SIZE - 1)) >> block_bits;
+	unsigned end = offset_in_page(i_size_read(inode)) >> block_bits;
 
 	/*
 	 * If the block size is smaller than the page size we need to check the
@@ -427,7 +427,7 @@ iomap_readpages_actor(struct inode *inode, loff_t pos, loff_t length,
 	loff_t done, ret;
 
 	for (done = 0; done < length; done += ret) {
-		if (ctx->cur_page && ((pos + done) & (PAGE_SIZE - 1)) == 0) {
+		if (ctx->cur_page && offset_in_page(pos + done) == 0) {
 			if (!ctx->cur_page_in_bio)
 				unlock_page(ctx->cur_page);
 			put_page(ctx->cur_page);
@@ -609,7 +609,7 @@ __iomap_write_begin(struct inode *inode, loff_t pos, unsigned len,
 	loff_t block_size = i_blocksize(inode);
 	loff_t block_start = pos & ~(block_size - 1);
 	loff_t block_end = (pos + len + block_size - 1) & ~(block_size - 1);
-	unsigned from = pos & (PAGE_SIZE - 1), to = from + len, poff, plen;
+	unsigned from = offset_in_page(pos), to = from + len, poff, plen;
 	int status = 0;
 
 	if (PageUptodate(page))
@@ -714,7 +714,7 @@ __iomap_write_end(struct inode *inode, loff_t pos, unsigned len,
 	if (unlikely(copied < len && !PageUptodate(page))) {
 		copied = 0;
 	} else {
-		iomap_set_range_uptodate(page, pos & (PAGE_SIZE - 1), len);
+		iomap_set_range_uptodate(page, offset_in_page(pos), len);
 		iomap_set_page_dirty(page);
 	}
 	return __generic_write_end(inode, pos, copied, page);
@@ -776,7 +776,7 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long bytes;	/* Bytes to write to page */
 		size_t copied;		/* Bytes copied from user */
 
-		offset = (pos & (PAGE_SIZE - 1));
+		offset = offset_in_page(pos);
 		bytes = min_t(unsigned long, PAGE_SIZE - offset,
 						iov_iter_count(i));
 again:
@@ -890,7 +890,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		unsigned long offset;	/* Offset into pagecache page */
 		unsigned long bytes;	/* Bytes to write to page */
 
-		offset = (pos & (PAGE_SIZE - 1));
+		offset = offset_in_page(pos);
 		bytes = min_t(loff_t, PAGE_SIZE - offset, length);
 
 		rpage = __iomap_read_page(inode, pos);
@@ -982,7 +982,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 	do {
 		unsigned offset, bytes;
 
-		offset = pos & (PAGE_SIZE - 1); /* Within page */
+		offset = offset_in_page(pos);
 		bytes = min_t(loff_t, PAGE_SIZE - offset, count);
 
 		if (IS_DAX(inode))
@@ -1075,7 +1075,7 @@ int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 
 	/* page is wholly or partially inside EOF */
 	if (((page->index + 1) << PAGE_SHIFT) > size)
-		length = size & ~PAGE_MASK;
+		length = offset_in_page(size);
 	else
 		length = PAGE_SIZE;
 
@@ -1238,7 +1238,7 @@ page_seek_hole_data(struct inode *inode, struct page *page, loff_t *lastoff,
 		goto out_unlock_not_found;
 
 	for (off = 0; off < PAGE_SIZE; off += bsize) {
-		if ((*lastoff & ~PAGE_MASK) >= off + bsize)
+		if (offset_in_page(*lastoff) >= off + bsize)
 			continue;
 		if (ops->is_partially_uptodate(page, off, bsize) == seek_data) {
 			unlock_page(page);
-- 
cgit v1.2.3


From fa6c668d807b1e9ac041101dfcb59bd8e279cfe5 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Fri, 10 Aug 2018 13:56:25 -0700
Subject: xfs: remove b_last_holder & associated macros

The old lock tracking infrastructure in xfs using the b_last_holder
field seems to only be useful if you can get into the system with a
debugger; it seems that the existing tracepoints would be the way to
go these days, and this old infrastructure can be removed.

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/xfs.h     |  1 -
 fs/xfs/xfs_buf.c | 20 ++------------------
 fs/xfs/xfs_buf.h |  4 ----
 3 files changed, 2 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index 583a9f539bf1..f6ffb4f248f7 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -8,7 +8,6 @@
 
 #ifdef CONFIG_XFS_DEBUG
 #define DEBUG 1
-#define XFS_BUF_LOCK_TRACKING 1
 #endif
 
 #ifdef CONFIG_XFS_ASSERT_FATAL
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index c641c7fa1a03..e839907e8492 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -34,16 +34,6 @@
 
 static kmem_zone_t *xfs_buf_zone;
 
-#ifdef XFS_BUF_LOCK_TRACKING
-# define XB_SET_OWNER(bp)	((bp)->b_last_holder = current->pid)
-# define XB_CLEAR_OWNER(bp)	((bp)->b_last_holder = -1)
-# define XB_GET_OWNER(bp)	((bp)->b_last_holder)
-#else
-# define XB_SET_OWNER(bp)	do { } while (0)
-# define XB_CLEAR_OWNER(bp)	do { } while (0)
-# define XB_GET_OWNER(bp)	do { } while (0)
-#endif
-
 #define xb_to_gfp(flags) \
 	((((flags) & XBF_READ_AHEAD) ? __GFP_NORETRY : GFP_NOFS) | __GFP_NOWARN)
 
@@ -226,7 +216,6 @@ _xfs_buf_alloc(
 	INIT_LIST_HEAD(&bp->b_li_list);
 	sema_init(&bp->b_sema, 0); /* held, no waiters */
 	spin_lock_init(&bp->b_lock);
-	XB_SET_OWNER(bp);
 	bp->b_target = target;
 	bp->b_flags = flags;
 
@@ -1091,12 +1080,10 @@ xfs_buf_trylock(
 	int			locked;
 
 	locked = down_trylock(&bp->b_sema) == 0;
-	if (locked) {
-		XB_SET_OWNER(bp);
+	if (locked)
 		trace_xfs_buf_trylock(bp, _RET_IP_);
-	} else {
+	else
 		trace_xfs_buf_trylock_fail(bp, _RET_IP_);
-	}
 	return locked;
 }
 
@@ -1118,7 +1105,6 @@ xfs_buf_lock(
 	if (atomic_read(&bp->b_pin_count) && (bp->b_flags & XBF_STALE))
 		xfs_log_force(bp->b_target->bt_mount, 0);
 	down(&bp->b_sema);
-	XB_SET_OWNER(bp);
 
 	trace_xfs_buf_lock_done(bp, _RET_IP_);
 }
@@ -1129,9 +1115,7 @@ xfs_buf_unlock(
 {
 	ASSERT(xfs_buf_islocked(bp));
 
-	XB_CLEAR_OWNER(bp);
 	up(&bp->b_sema);
-
 	trace_xfs_buf_unlock(bp, _RET_IP_);
 }
 
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index f04613181ca1..4e3171acd0f8 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -198,10 +198,6 @@ typedef struct xfs_buf {
 	int			b_last_error;
 
 	const struct xfs_buf_ops	*b_ops;
-
-#ifdef XFS_BUF_LOCK_TRACKING
-	int			b_last_holder;
-#endif
 } xfs_buf_t;
 
 /* Finding and Reading Buffers */
-- 
cgit v1.2.3


From 01239d77b9dd978863d1a75f0d095ab942a1fe66 Mon Sep 17 00:00:00 2001
From: Shan Hai <shan.hai@oracle.com>
Date: Fri, 10 Aug 2018 17:55:55 -0700
Subject: xfs: fix a null pointer dereference in xfs_bmap_extents_to_btree

Fuzzing tool reports a write to null pointer error in the
xfs_bmap_extents_to_btree, fix it by bailing out on encountering
a null pointer.

Signed-off-by: Shan Hai <shan.hai@oracle.com>
Reviewed-by: Darrick J. Wong <darrick.wong@oracle.com>
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/libxfs/xfs_bmap.c | 24 ++++++++++++++++--------
 1 file changed, 16 insertions(+), 8 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 5648a177e0ac..2760314fdf7f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -712,19 +712,14 @@ xfs_bmap_extents_to_btree(
 	args.wasdel = wasdel;
 	*logflagsp = 0;
 	if ((error = xfs_alloc_vextent(&args))) {
-		xfs_iroot_realloc(ip, -1, whichfork);
 		ASSERT(ifp->if_broot == NULL);
-		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
-		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-		return error;
+		goto err1;
 	}
 
 	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
-		xfs_iroot_realloc(ip, -1, whichfork);
 		ASSERT(ifp->if_broot == NULL);
-		XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
-		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-		return -ENOSPC;
+		error = -ENOSPC;
+		goto err1;
 	}
 	/*
 	 * Allocation can't fail, the space was reserved.
@@ -736,6 +731,10 @@ xfs_bmap_extents_to_btree(
 	ip->i_d.di_nblocks++;
 	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, 1L);
 	abp = xfs_btree_get_bufl(mp, tp, args.fsbno, 0);
+	if (!abp) {
+		error = -ENOSPC;
+		goto err2;
+	}
 	/*
 	 * Fill in the child block.
 	 */
@@ -775,6 +774,15 @@ xfs_bmap_extents_to_btree(
 	*curp = cur;
 	*logflagsp = XFS_ILOG_CORE | xfs_ilog_fbroot(whichfork);
 	return 0;
+
+err2:
+	xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L);
+err1:
+	xfs_iroot_realloc(ip, -1, whichfork);
+	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_EXTENTS);
+	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+
+	return error;
 }
 
 /*
-- 
cgit v1.2.3


From e8d2bec0457962e8f348a9a3627b398f7fe5c5fc Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Sun, 12 Aug 2018 01:59:17 +0200
Subject: bpf: decouple btf from seq bpf fs dump and enable more maps

Commit a26ca7c982cb ("bpf: btf: Add pretty print support to
the basic arraymap") and 699c86d6ec21 ("bpf: btf: add pretty
print for hash/lru_hash maps") enabled support for BTF and
dumping via BPF fs for array and hash/lru map. However, both
can be decoupled from each other such that regular BPF maps
can be supported for attaching BTF key/value information,
while not all maps necessarily need to dump via map_seq_show_elem()
callback.

The basic sanity check which is a prerequisite for all maps
is that key/value size has to match in any case, and some maps
can have extra checks via map_check_btf() callback, e.g.
probing certain types or indicating no support in general. With
that we can also enable retrieving BTF info for per-cpu map
types and lpm.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Yonghong Song <yhs@fb.com>
---
 include/linux/bpf.h        | 13 +++++++++----
 kernel/bpf/arraymap.c      | 26 ++++++++++++--------------
 kernel/bpf/cpumap.c        |  1 +
 kernel/bpf/devmap.c        |  1 +
 kernel/bpf/hashtab.c       | 20 +-------------------
 kernel/bpf/inode.c         |  3 ++-
 kernel/bpf/local_storage.c |  1 +
 kernel/bpf/lpm_trie.c      | 12 ++++++++++++
 kernel/bpf/sockmap.c       |  2 ++
 kernel/bpf/stackmap.c      |  1 +
 kernel/bpf/syscall.c       | 36 ++++++++++++++++++++++++++++++++----
 kernel/bpf/xskmap.c        |  3 +--
 12 files changed, 75 insertions(+), 44 deletions(-)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index db11662faea6..523481a3471b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -23,7 +23,7 @@ struct bpf_prog;
 struct bpf_map;
 struct sock;
 struct seq_file;
-struct btf;
+struct btf_type;
 
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
@@ -48,8 +48,9 @@ struct bpf_map_ops {
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
 				  struct seq_file *m);
-	int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf,
-			     u32 key_type_id, u32 value_type_id);
+	int (*map_check_btf)(const struct bpf_map *map,
+			     const struct btf_type *key_type,
+			     const struct btf_type *value_type);
 };
 
 struct bpf_map {
@@ -118,9 +119,13 @@ static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
 
 static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
 {
-	return map->ops->map_seq_show_elem && map->ops->map_check_btf;
+	return map->btf && map->ops->map_seq_show_elem;
 }
 
+int map_check_no_btf(const struct bpf_map *map,
+		     const struct btf_type *key_type,
+		     const struct btf_type *value_type);
+
 extern const struct bpf_map_ops bpf_map_offload_ops;
 
 /* function argument constraints */
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index f6ca3e712831..0c17aab3ce5f 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -358,27 +358,20 @@ static void array_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
-static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
-			       u32 btf_key_id, u32 btf_value_id)
+static int array_map_check_btf(const struct bpf_map *map,
+			       const struct btf_type *key_type,
+			       const struct btf_type *value_type)
 {
-	const struct btf_type *key_type, *value_type;
-	u32 key_size, value_size;
 	u32 int_data;
 
-	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
-	if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
+	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
 		return -EINVAL;
 
 	int_data = *(u32 *)(key_type + 1);
-	/* bpf array can only take a u32 key.  This check makes
-	 * sure that the btf matches the attr used during map_create.
+	/* bpf array can only take a u32 key. This check makes sure
+	 * that the btf matches the attr used during map_create.
 	 */
-	if (BTF_INT_BITS(int_data) != 32 || key_size != 4 ||
-	    BTF_INT_OFFSET(int_data))
-		return -EINVAL;
-
-	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
-	if (!value_type || value_size != map->value_size)
+	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
 		return -EINVAL;
 
 	return 0;
@@ -405,6 +398,7 @@ const struct bpf_map_ops percpu_array_map_ops = {
 	.map_lookup_elem = percpu_array_map_lookup_elem,
 	.map_update_elem = array_map_update_elem,
 	.map_delete_elem = array_map_delete_elem,
+	.map_check_btf = array_map_check_btf,
 };
 
 static int fd_array_map_alloc_check(union bpf_attr *attr)
@@ -546,6 +540,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
 	.map_release_uref = bpf_fd_array_map_clear,
+	.map_check_btf = map_check_no_btf,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
@@ -634,6 +629,7 @@ const struct bpf_map_ops perf_event_array_map_ops = {
 	.map_fd_get_ptr = perf_event_fd_array_get_ptr,
 	.map_fd_put_ptr = perf_event_fd_array_put_ptr,
 	.map_release = perf_event_fd_array_release,
+	.map_check_btf = map_check_no_btf,
 };
 
 #ifdef CONFIG_CGROUPS
@@ -665,6 +661,7 @@ const struct bpf_map_ops cgroup_array_map_ops = {
 	.map_delete_elem = fd_array_map_delete_elem,
 	.map_fd_get_ptr = cgroup_fd_array_get_ptr,
 	.map_fd_put_ptr = cgroup_fd_array_put_ptr,
+	.map_check_btf = map_check_no_btf,
 };
 #endif
 
@@ -749,4 +746,5 @@ const struct bpf_map_ops array_of_maps_map_ops = {
 	.map_fd_put_ptr = bpf_map_fd_put_ptr,
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = array_of_map_gen_lookup,
+	.map_check_btf = map_check_no_btf,
 };
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e0918d180f08..3b494941a44a 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -555,6 +555,7 @@ const struct bpf_map_ops cpu_map_ops = {
 	.map_update_elem	= cpu_map_update_elem,
 	.map_lookup_elem	= cpu_map_lookup_elem,
 	.map_get_next_key	= cpu_map_get_next_key,
+	.map_check_btf		= map_check_no_btf,
 };
 
 static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index d361fc1e3bf3..a7c6620d8389 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -484,6 +484,7 @@ const struct bpf_map_ops dev_map_ops = {
 	.map_lookup_elem = dev_map_lookup_elem,
 	.map_update_elem = dev_map_update_elem,
 	.map_delete_elem = dev_map_delete_elem,
+	.map_check_btf = map_check_no_btf,
 };
 
 static int dev_map_notification(struct notifier_block *notifier,
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index d6110042e0d9..04b8eda94e7d 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -1185,23 +1185,6 @@ static void htab_map_seq_show_elem(struct bpf_map *map, void *key,
 	rcu_read_unlock();
 }
 
-static int htab_map_check_btf(const struct bpf_map *map, const struct btf *btf,
-			      u32 btf_key_id, u32 btf_value_id)
-{
-	const struct btf_type *key_type, *value_type;
-	u32 key_size, value_size;
-
-	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
-	if (!key_type || key_size != map->key_size)
-		return -EINVAL;
-
-	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
-	if (!value_type || value_size != map->value_size)
-		return -EINVAL;
-
-	return 0;
-}
-
 const struct bpf_map_ops htab_map_ops = {
 	.map_alloc_check = htab_map_alloc_check,
 	.map_alloc = htab_map_alloc,
@@ -1212,7 +1195,6 @@ const struct bpf_map_ops htab_map_ops = {
 	.map_delete_elem = htab_map_delete_elem,
 	.map_gen_lookup = htab_map_gen_lookup,
 	.map_seq_show_elem = htab_map_seq_show_elem,
-	.map_check_btf = htab_map_check_btf,
 };
 
 const struct bpf_map_ops htab_lru_map_ops = {
@@ -1225,7 +1207,6 @@ const struct bpf_map_ops htab_lru_map_ops = {
 	.map_delete_elem = htab_lru_map_delete_elem,
 	.map_gen_lookup = htab_lru_map_gen_lookup,
 	.map_seq_show_elem = htab_map_seq_show_elem,
-	.map_check_btf = htab_map_check_btf,
 };
 
 /* Called from eBPF program */
@@ -1452,4 +1433,5 @@ const struct bpf_map_ops htab_of_maps_map_ops = {
 	.map_fd_put_ptr = bpf_map_fd_put_ptr,
 	.map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem,
 	.map_gen_lookup = htab_of_map_gen_lookup,
+	.map_check_btf = map_check_no_btf,
 };
diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c
index fc5b103512e7..2ada5e21dfa6 100644
--- a/kernel/bpf/inode.c
+++ b/kernel/bpf/inode.c
@@ -334,7 +334,8 @@ static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg)
 	struct bpf_map *map = arg;
 
 	return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops,
-			     map->btf ? &bpffs_map_fops : &bpffs_obj_fops);
+			     bpf_map_support_seq_show(map) ?
+			     &bpffs_map_fops : &bpffs_obj_fops);
 }
 
 static struct dentry *
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index fc4e37f68f2a..22ad967d1e5f 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -246,6 +246,7 @@ const struct bpf_map_ops cgroup_storage_map_ops = {
 	.map_lookup_elem = cgroup_storage_lookup_elem,
 	.map_update_elem = cgroup_storage_update_elem,
 	.map_delete_elem = cgroup_storage_delete_elem,
+	.map_check_btf = map_check_no_btf,
 };
 
 int bpf_cgroup_storage_assign(struct bpf_prog *prog, struct bpf_map *_map)
diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c
index 1603492c9cc7..9058317ba9de 100644
--- a/kernel/bpf/lpm_trie.c
+++ b/kernel/bpf/lpm_trie.c
@@ -10,11 +10,13 @@
  */
 
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/err.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/vmalloc.h>
 #include <net/ipv6.h>
+#include <uapi/linux/btf.h>
 
 /* Intermediate node */
 #define LPM_TREE_NODE_FLAG_IM BIT(0)
@@ -686,6 +688,15 @@ free_stack:
 	return err;
 }
 
+static int trie_check_btf(const struct bpf_map *map,
+			  const struct btf_type *key_type,
+			  const struct btf_type *value_type)
+{
+	/* Keys must have struct bpf_lpm_trie_key embedded. */
+	return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ?
+	       -EINVAL : 0;
+}
+
 const struct bpf_map_ops trie_map_ops = {
 	.map_alloc = trie_alloc,
 	.map_free = trie_free,
@@ -693,4 +704,5 @@ const struct bpf_map_ops trie_map_ops = {
 	.map_lookup_elem = trie_lookup_elem,
 	.map_update_elem = trie_update_elem,
 	.map_delete_elem = trie_delete_elem,
+	.map_check_btf = trie_check_btf,
 };
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 0b38be5a955c..e376ffffebce 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -2495,6 +2495,7 @@ const struct bpf_map_ops sock_map_ops = {
 	.map_update_elem = sock_map_update_elem,
 	.map_delete_elem = sock_map_delete_elem,
 	.map_release_uref = sock_map_release,
+	.map_check_btf = map_check_no_btf,
 };
 
 const struct bpf_map_ops sock_hash_ops = {
@@ -2505,6 +2506,7 @@ const struct bpf_map_ops sock_hash_ops = {
 	.map_update_elem = sock_hash_update_elem,
 	.map_delete_elem = sock_hash_delete_elem,
 	.map_release_uref = sock_map_release,
+	.map_check_btf = map_check_no_btf,
 };
 
 BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c
index b675a3f3d141..8061a439ef18 100644
--- a/kernel/bpf/stackmap.c
+++ b/kernel/bpf/stackmap.c
@@ -607,6 +607,7 @@ const struct bpf_map_ops stack_map_ops = {
 	.map_lookup_elem = stack_map_lookup_elem,
 	.map_update_elem = stack_map_update_elem,
 	.map_delete_elem = stack_map_delete_elem,
+	.map_check_btf = map_check_no_btf,
 };
 
 static int __init stack_map_init(void)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 57f4d076141b..43727ed0d94a 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -103,6 +103,7 @@ int bpf_check_uarg_tail_zero(void __user *uaddr,
 const struct bpf_map_ops bpf_map_offload_ops = {
 	.map_alloc = bpf_map_offload_map_alloc,
 	.map_free = bpf_map_offload_map_free,
+	.map_check_btf = map_check_no_btf,
 };
 
 static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
@@ -455,6 +456,34 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 	return 0;
 }
 
+int map_check_no_btf(const struct bpf_map *map,
+		     const struct btf_type *key_type,
+		     const struct btf_type *value_type)
+{
+	return -ENOTSUPP;
+}
+
+static int map_check_btf(const struct bpf_map *map, const struct btf *btf,
+			 u32 btf_key_id, u32 btf_value_id)
+{
+	const struct btf_type *key_type, *value_type;
+	u32 key_size, value_size;
+	int ret = 0;
+
+	key_type = btf_type_id_size(btf, &btf_key_id, &key_size);
+	if (!key_type || key_size != map->key_size)
+		return -EINVAL;
+
+	value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
+	if (!value_type || value_size != map->value_size)
+		return -EINVAL;
+
+	if (map->ops->map_check_btf)
+		ret = map->ops->map_check_btf(map, key_type, value_type);
+
+	return ret;
+}
+
 #define BPF_MAP_CREATE_LAST_FIELD btf_value_type_id
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
@@ -489,8 +518,7 @@ static int map_create(union bpf_attr *attr)
 	atomic_set(&map->refcnt, 1);
 	atomic_set(&map->usercnt, 1);
 
-	if (bpf_map_support_seq_show(map) &&
-	    (attr->btf_key_type_id || attr->btf_value_type_id)) {
+	if (attr->btf_key_type_id || attr->btf_value_type_id) {
 		struct btf *btf;
 
 		if (!attr->btf_key_type_id || !attr->btf_value_type_id) {
@@ -504,8 +532,8 @@ static int map_create(union bpf_attr *attr)
 			goto free_map_nouncharge;
 		}
 
-		err = map->ops->map_check_btf(map, btf, attr->btf_key_type_id,
-					      attr->btf_value_type_id);
+		err = map_check_btf(map, btf, attr->btf_key_type_id,
+				    attr->btf_value_type_id);
 		if (err) {
 			btf_put(btf);
 			goto free_map_nouncharge;
diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c
index b3c557476a8d..4ddf61e158f6 100644
--- a/kernel/bpf/xskmap.c
+++ b/kernel/bpf/xskmap.c
@@ -227,6 +227,5 @@ const struct bpf_map_ops xsk_map_ops = {
 	.map_lookup_elem = xsk_map_lookup_elem,
 	.map_update_elem = xsk_map_update_elem,
 	.map_delete_elem = xsk_map_delete_elem,
+	.map_check_btf = map_check_no_btf,
 };
-
-
-- 
cgit v1.2.3


From 7723628101aaeb1d723786747529b4ea65c5b5c5 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sun, 12 Aug 2018 10:49:27 -0700
Subject: bpf: Introduce bpf_skb_ancestor_cgroup_id helper

== Problem description ==

It's useful to be able to identify cgroup associated with skb in TC so
that a policy can be applied to this skb, and existing bpf_skb_cgroup_id
helper can help with this.

Though in real life cgroup hierarchy and hierarchy to apply a policy to
don't map 1:1.

It's often the case that there is a container and corresponding cgroup,
but there are many more sub-cgroups inside container, e.g. because it's
delegated to containerized application to control resources for its
subsystems, or to separate application inside container from infra that
belongs to containerization system (e.g. sshd).

At the same time it may be useful to apply a policy to container as a
whole.

If multiple containers like this are run on a host (what is often the
case) and many of them have sub-cgroups, it may not be possible to apply
per-container policy in TC with existing helpers such as
bpf_skb_under_cgroup or bpf_skb_cgroup_id:

* bpf_skb_cgroup_id will return id of immediate cgroup associated with
  skb, i.e. if it's a sub-cgroup inside container, it can't be used to
  identify container's cgroup;

* bpf_skb_under_cgroup can work only with one cgroup and doesn't scale,
  i.e. if there are N containers on a host and a policy has to be
  applied to M of them (0 <= M <= N), it'd require M calls to
  bpf_skb_under_cgroup, and, if M changes, it'd require to rebuild &
  load new BPF program.

== Solution ==

The patch introduces new helper bpf_skb_ancestor_cgroup_id that can be
used to get id of cgroup v2 that is an ancestor of cgroup associated
with skb at specified level of cgroup hierarchy.

That way admin can place all containers on one level of cgroup hierarchy
(what is a good practice in general and already used in many
configurations) and identify specific cgroup on this level no matter
what sub-cgroup skb is associated with.

E.g. if there is a cgroup hierarchy:
  root/
  root/container1/
  root/container1/app11/
  root/container1/app11/sub-app-a/
  root/container1/app12/
  root/container2/
  root/container2/app21/
  root/container2/app22/
  root/container2/app22/sub-app-b/

, then having skb associated with root/container1/app11/sub-app-a/ it's
possible to get ancestor at level 1, what is container1 and apply policy
for this container, or apply another policy if it's container2.

Policies can be kept e.g. in a hash map where key is a container cgroup
id and value is an action.

Levels where container cgroups are created are usually known in advance
whether cgroup hierarchy inside container may be hard to predict
especially in case when its creation is delegated to containerized
application.

== Implementation details ==

The helper gets ancestor by walking parents up to specified level.

Another option would be to get different kind of "id" from
cgroup->ancestor_ids[level] and use it with idr_find() to get struct
cgroup for ancestor. But that would require radix lookup what doesn't
seem to be better (at least it's not obviously better).

Format of return value of the new helper is same as that of
bpf_skb_cgroup_id.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 include/linux/cgroup.h   | 30 ++++++++++++++++++++++++++++++
 include/uapi/linux/bpf.h | 21 ++++++++++++++++++++-
 net/core/filter.c        | 28 ++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+), 1 deletion(-)

diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index c9fdf6f57913..32c553556bbd 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -553,6 +553,36 @@ static inline bool cgroup_is_descendant(struct cgroup *cgrp,
 	return cgrp->ancestor_ids[ancestor->level] == ancestor->id;
 }
 
+/**
+ * cgroup_ancestor - find ancestor of cgroup
+ * @cgrp: cgroup to find ancestor of
+ * @ancestor_level: level of ancestor to find starting from root
+ *
+ * Find ancestor of cgroup at specified level starting from root if it exists
+ * and return pointer to it. Return NULL if @cgrp doesn't have ancestor at
+ * @ancestor_level.
+ *
+ * This function is safe to call as long as @cgrp is accessible.
+ */
+static inline struct cgroup *cgroup_ancestor(struct cgroup *cgrp,
+					     int ancestor_level)
+{
+	struct cgroup *ptr;
+
+	if (cgrp->level < ancestor_level)
+		return NULL;
+
+	for (ptr = cgrp;
+	     ptr && ptr->level > ancestor_level;
+	     ptr = cgroup_parent(ptr))
+		;
+
+	if (ptr && ptr->level == ancestor_level)
+		return ptr;
+
+	return NULL;
+}
+
 /**
  * task_under_cgroup_hierarchy - test task's membership of cgroup ancestry
  * @task: the task to be tested
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3102a2a23c31..66917a4eba27 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2093,6 +2093,24 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *	Description
+ *		Return id of cgroup v2 that is ancestor of cgroup associated
+ *		with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *		*ancestor_level* zero and each step down the hierarchy
+ *		increments the level. If *ancestor_level* == level of cgroup
+ *		associated with *skb*, then return value will be same as that
+ *		of **bpf_skb_cgroup_id**\ ().
+ *
+ *		The helper is useful to implement policies based on cgroups
+ *		that are upper in hierarchy than immediate cgroup associated
+ *		with *skb*.
+ *
+ *		The format of returned id and helper limitations are same as in
+ *		**bpf_skb_cgroup_id**\ ().
+ *	Return
+ *		The id is returned or 0 in case the id could not be retrieved.
+ *
  * u64 bpf_get_current_cgroup_id(void)
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
@@ -2207,7 +2225,8 @@ union bpf_attr {
 	FN(skb_cgroup_id),		\
 	FN(get_current_cgroup_id),	\
 	FN(get_local_storage),		\
-	FN(sk_select_reuseport),
+	FN(sk_select_reuseport),	\
+	FN(skb_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
diff --git a/net/core/filter.c b/net/core/filter.c
index 22906b31d43f..15b9d2df92ca 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3778,6 +3778,32 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
 	.ret_type       = RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
+
+BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
+	   ancestor_level)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+	struct cgroup *ancestor;
+	struct cgroup *cgrp;
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	ancestor = cgroup_ancestor(cgrp, ancestor_level);
+	if (!ancestor)
+		return 0;
+
+	return ancestor->kn->id.id;
+}
+
+static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
+	.func           = bpf_skb_ancestor_cgroup_id,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_ANYTHING,
+};
 #endif
 
 static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
@@ -4966,6 +4992,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
+	case BPF_FUNC_skb_ancestor_cgroup_id:
+		return &bpf_skb_ancestor_cgroup_id_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
-- 
cgit v1.2.3


From 539764d07b49c5b322cc065d275f65df275e4991 Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sun, 12 Aug 2018 10:49:28 -0700
Subject: bpf: Sync bpf.h to tools/

Sync skb_ancestor_cgroup_id() related bpf UAPI changes to tools/.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/include/uapi/linux/bpf.h | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 3102a2a23c31..66917a4eba27 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -2093,6 +2093,24 @@ union bpf_attr {
  * 	Return
  * 		The id is returned or 0 in case the id could not be retrieved.
  *
+ * u64 bpf_skb_ancestor_cgroup_id(struct sk_buff *skb, int ancestor_level)
+ *	Description
+ *		Return id of cgroup v2 that is ancestor of cgroup associated
+ *		with the *skb* at the *ancestor_level*.  The root cgroup is at
+ *		*ancestor_level* zero and each step down the hierarchy
+ *		increments the level. If *ancestor_level* == level of cgroup
+ *		associated with *skb*, then return value will be same as that
+ *		of **bpf_skb_cgroup_id**\ ().
+ *
+ *		The helper is useful to implement policies based on cgroups
+ *		that are upper in hierarchy than immediate cgroup associated
+ *		with *skb*.
+ *
+ *		The format of returned id and helper limitations are same as in
+ *		**bpf_skb_cgroup_id**\ ().
+ *	Return
+ *		The id is returned or 0 in case the id could not be retrieved.
+ *
  * u64 bpf_get_current_cgroup_id(void)
  * 	Return
  * 		A 64-bit integer containing the current cgroup id based
@@ -2207,7 +2225,8 @@ union bpf_attr {
 	FN(skb_cgroup_id),		\
 	FN(get_current_cgroup_id),	\
 	FN(get_local_storage),		\
-	FN(sk_select_reuseport),
+	FN(sk_select_reuseport),	\
+	FN(skb_ancestor_cgroup_id),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
-- 
cgit v1.2.3


From 02f6ac7456a0d77360cb47b8d2ed4366b883096d Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sun, 12 Aug 2018 10:49:29 -0700
Subject: selftests/bpf: Add cgroup id helpers to bpf_helpers.h

Add bpf_skb_cgroup_id and bpf_skb_ancestor_cgroup_id helpers to
bpf_helpers.h to use them in tests and samples.

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/bpf_helpers.h | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h
index 5c32266c2c38..e4be7730222d 100644
--- a/tools/testing/selftests/bpf/bpf_helpers.h
+++ b/tools/testing/selftests/bpf/bpf_helpers.h
@@ -139,6 +139,10 @@ static unsigned long long (*bpf_get_current_cgroup_id)(void) =
 	(void *) BPF_FUNC_get_current_cgroup_id;
 static void *(*bpf_get_local_storage)(void *map, unsigned long long flags) =
 	(void *) BPF_FUNC_get_local_storage;
+static unsigned long long (*bpf_skb_cgroup_id)(void *ctx) =
+	(void *) BPF_FUNC_skb_cgroup_id;
+static unsigned long long (*bpf_skb_ancestor_cgroup_id)(void *ctx, int level) =
+	(void *) BPF_FUNC_skb_ancestor_cgroup_id;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions
-- 
cgit v1.2.3


From 5ecd8c22739b9a5f6d6431234decd912aa3f48ad Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Sun, 12 Aug 2018 10:49:30 -0700
Subject: selftests/bpf: Selftest for bpf_skb_ancestor_cgroup_id

Add selftests for bpf_skb_ancestor_cgroup_id helper.

test_skb_cgroup_id.sh prepares testing interface and adds tc qdisc and
filter for it using BPF object compiled from test_skb_cgroup_id_kern.c
program.

BPF program in test_skb_cgroup_id_kern.c gets ancestor cgroup id using
the new helper at different levels of cgroup hierarchy that skb belongs
to, including root level and non-existing level, and saves it to the map
where the key is the level of corresponding cgroup and the value is its
id.

To trigger BPF program, user space program test_skb_cgroup_id_user is
run. It adds itself into testing cgroup and sends UDP datagram to
link-local multicast address of testing interface. Then it reads cgroup
ids saved in kernel for different levels from the BPF map and compares
them with those in user space. They must be equal for every level of
ancestry.

Example of run:
  # ./test_skb_cgroup_id.sh
  Wait for testing link-local IP to become available ... OK
  Note: 8 bytes struct bpf_elf_map fixup performed due to size mismatch!
  [PASS]

Signed-off-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
---
 tools/testing/selftests/bpf/Makefile               |   9 +-
 tools/testing/selftests/bpf/test_skb_cgroup_id.sh  |  62 +++++++
 .../selftests/bpf/test_skb_cgroup_id_kern.c        |  47 ++++++
 .../selftests/bpf/test_skb_cgroup_id_user.c        | 187 +++++++++++++++++++++
 4 files changed, 302 insertions(+), 3 deletions(-)
 create mode 100755 tools/testing/selftests/bpf/test_skb_cgroup_id.sh
 create mode 100644 tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c
 create mode 100644 tools/testing/selftests/bpf/test_skb_cgroup_id_user.c

diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index daed162043c2..fff7fb1285fc 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -34,7 +34,8 @@ TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test
 	test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \
 	test_get_stack_rawtp.o test_sockmap_kern.o test_sockhash_kern.o \
 	test_lwt_seg6local.o sendmsg4_prog.o sendmsg6_prog.o test_lirc_mode2_kern.o \
-	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o
+	get_cgroup_id_kern.o socket_cookie_prog.o test_select_reuseport_kern.o \
+	test_skb_cgroup_id_kern.o
 
 # Order correspond to 'make run_tests' order
 TEST_PROGS := test_kmod.sh \
@@ -45,10 +46,11 @@ TEST_PROGS := test_kmod.sh \
 	test_sock_addr.sh \
 	test_tunnel.sh \
 	test_lwt_seg6local.sh \
-	test_lirc_mode2.sh
+	test_lirc_mode2.sh \
+	test_skb_cgroup_id.sh
 
 # Compile but not part of 'make run_tests'
-TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr
+TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user
 
 include ../lib.mk
 
@@ -59,6 +61,7 @@ $(TEST_GEN_PROGS): $(BPFOBJ)
 $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a
 
 $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c
+$(OUTPUT)/test_skb_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_sock: cgroup_helpers.c
 $(OUTPUT)/test_sock_addr: cgroup_helpers.c
 $(OUTPUT)/test_socket_cookie: cgroup_helpers.c
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id.sh b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
new file mode 100755
index 000000000000..42544a969abc
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id.sh
@@ -0,0 +1,62 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2018 Facebook
+
+set -eu
+
+wait_for_ip()
+{
+	local _i
+	echo -n "Wait for testing link-local IP to become available "
+	for _i in $(seq ${MAX_PING_TRIES}); do
+		echo -n "."
+		if ping -6 -q -c 1 -W 1 ff02::1%${TEST_IF} >/dev/null 2>&1; then
+			echo " OK"
+			return
+		fi
+		sleep 1
+	done
+	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
+	exit 1
+}
+
+setup()
+{
+	# Create testing interfaces not to interfere with current environment.
+	ip link add dev ${TEST_IF} type veth peer name ${TEST_IF_PEER}
+	ip link set ${TEST_IF} up
+	ip link set ${TEST_IF_PEER} up
+
+	wait_for_ip
+
+	tc qdisc add dev ${TEST_IF} clsact
+	tc filter add dev ${TEST_IF} egress bpf obj ${BPF_PROG_OBJ} \
+		sec ${BPF_PROG_SECTION} da
+
+	BPF_PROG_ID=$(tc filter show dev ${TEST_IF} egress | \
+			awk '/ id / {sub(/.* id /, "", $0); print($1)}')
+}
+
+cleanup()
+{
+	ip link del ${TEST_IF} 2>/dev/null || :
+	ip link del ${TEST_IF_PEER} 2>/dev/null || :
+}
+
+main()
+{
+	trap cleanup EXIT 2 3 6 15
+	setup
+	${PROG} ${TEST_IF} ${BPF_PROG_ID}
+}
+
+DIR=$(dirname $0)
+TEST_IF="test_cgid_1"
+TEST_IF_PEER="test_cgid_2"
+MAX_PING_TRIES=5
+BPF_PROG_OBJ="${DIR}/test_skb_cgroup_id_kern.o"
+BPF_PROG_SECTION="cgroup_id_logger"
+BPF_PROG_ID=0
+PROG="${DIR}/test_skb_cgroup_id_user"
+
+main
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c
new file mode 100644
index 000000000000..68cf9829f5a7
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_kern.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+
+#include <string.h>
+
+#include "bpf_helpers.h"
+
+#define NUM_CGROUP_LEVELS	4
+
+struct bpf_map_def SEC("maps") cgroup_ids = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = NUM_CGROUP_LEVELS,
+};
+
+static __always_inline void log_nth_level(struct __sk_buff *skb, __u32 level)
+{
+	__u64 id;
+
+	/* [1] &level passed to external function that may change it, it's
+	 *     incompatible with loop unroll.
+	 */
+	id = bpf_skb_ancestor_cgroup_id(skb, level);
+	bpf_map_update_elem(&cgroup_ids, &level, &id, 0);
+}
+
+SEC("cgroup_id_logger")
+int log_cgroup_id(struct __sk_buff *skb)
+{
+	/* Loop unroll can't be used here due to [1]. Unrolling manually.
+	 * Number of calls should be in sync with NUM_CGROUP_LEVELS.
+	 */
+	log_nth_level(skb, 0);
+	log_nth_level(skb, 1);
+	log_nth_level(skb, 2);
+	log_nth_level(skb, 3);
+
+	return TC_ACT_OK;
+}
+
+int _version SEC("version") = 1;
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
new file mode 100644
index 000000000000..c121cc59f314
--- /dev/null
+++ b/tools/testing/selftests/bpf/test_skb_cgroup_id_user.c
@@ -0,0 +1,187 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <sys/socket.h>
+#include <sys/types.h>
+
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+#define CGROUP_PATH		"/skb_cgroup_test"
+#define NUM_CGROUP_LEVELS	4
+
+/* RFC 4291, Section 2.7.1 */
+#define LINKLOCAL_MULTICAST	"ff02::1"
+
+static int mk_dst_addr(const char *ip, const char *iface,
+		       struct sockaddr_in6 *dst)
+{
+	memset(dst, 0, sizeof(*dst));
+
+	dst->sin6_family = AF_INET6;
+	dst->sin6_port = htons(1025);
+
+	if (inet_pton(AF_INET6, ip, &dst->sin6_addr) != 1) {
+		log_err("Invalid IPv6: %s", ip);
+		return -1;
+	}
+
+	dst->sin6_scope_id = if_nametoindex(iface);
+	if (!dst->sin6_scope_id) {
+		log_err("Failed to get index of iface: %s", iface);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int send_packet(const char *iface)
+{
+	struct sockaddr_in6 dst;
+	char msg[] = "msg";
+	int err = 0;
+	int fd = -1;
+
+	if (mk_dst_addr(LINKLOCAL_MULTICAST, iface, &dst))
+		goto err;
+
+	fd = socket(AF_INET6, SOCK_DGRAM, 0);
+	if (fd == -1) {
+		log_err("Failed to create UDP socket");
+		goto err;
+	}
+
+	if (sendto(fd, &msg, sizeof(msg), 0, (const struct sockaddr *)&dst,
+		   sizeof(dst)) == -1) {
+		log_err("Failed to send datagram");
+		goto err;
+	}
+
+	goto out;
+err:
+	err = -1;
+out:
+	if (fd >= 0)
+		close(fd);
+	return err;
+}
+
+int get_map_fd_by_prog_id(int prog_id)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 map_ids[1];
+	int prog_fd = -1;
+	int map_fd = -1;
+
+	prog_fd = bpf_prog_get_fd_by_id(prog_id);
+	if (prog_fd < 0) {
+		log_err("Failed to get fd by prog id %d", prog_id);
+		goto err;
+	}
+
+	info.nr_map_ids = 1;
+	info.map_ids = (__u64) (unsigned long) map_ids;
+
+	if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) {
+		log_err("Failed to get info by prog fd %d", prog_fd);
+		goto err;
+	}
+
+	if (!info.nr_map_ids) {
+		log_err("No maps found for prog fd %d", prog_fd);
+		goto err;
+	}
+
+	map_fd = bpf_map_get_fd_by_id(map_ids[0]);
+	if (map_fd < 0)
+		log_err("Failed to get fd by map id %d", map_ids[0]);
+err:
+	if (prog_fd >= 0)
+		close(prog_fd);
+	return map_fd;
+}
+
+int check_ancestor_cgroup_ids(int prog_id)
+{
+	__u64 actual_ids[NUM_CGROUP_LEVELS], expected_ids[NUM_CGROUP_LEVELS];
+	__u32 level;
+	int err = 0;
+	int map_fd;
+
+	expected_ids[0] = 0x100000001;	/* root cgroup */
+	expected_ids[1] = get_cgroup_id("");
+	expected_ids[2] = get_cgroup_id(CGROUP_PATH);
+	expected_ids[3] = 0; /* non-existent cgroup */
+
+	map_fd = get_map_fd_by_prog_id(prog_id);
+	if (map_fd < 0)
+		goto err;
+
+	for (level = 0; level < NUM_CGROUP_LEVELS; ++level) {
+		if (bpf_map_lookup_elem(map_fd, &level, &actual_ids[level])) {
+			log_err("Failed to lookup key %d", level);
+			goto err;
+		}
+		if (actual_ids[level] != expected_ids[level]) {
+			log_err("%llx (actual) != %llx (expected), level: %u\n",
+				actual_ids[level], expected_ids[level], level);
+			goto err;
+		}
+	}
+
+	goto out;
+err:
+	err = -1;
+out:
+	if (map_fd >= 0)
+		close(map_fd);
+	return err;
+}
+
+int main(int argc, char **argv)
+{
+	int cgfd = -1;
+	int err = 0;
+
+	if (argc < 3) {
+		fprintf(stderr, "Usage: %s iface prog_id\n", argv[0]);
+		exit(EXIT_FAILURE);
+	}
+
+	if (setup_cgroup_environment())
+		goto err;
+
+	cgfd = create_and_get_cgroup(CGROUP_PATH);
+	if (!cgfd)
+		goto err;
+
+	if (join_cgroup(CGROUP_PATH))
+		goto err;
+
+	if (send_packet(argv[1]))
+		goto err;
+
+	if (check_ancestor_cgroup_ids(atoi(argv[2])))
+		goto err;
+
+	goto out;
+err:
+	err = -1;
+out:
+	close(cgfd);
+	cleanup_cgroup_environment();
+	printf("[%s]\n", err ? "FAIL" : "PASS");
+	return err;
+}
-- 
cgit v1.2.3


From 56869d45e364244a721de34ce9c5dc9ed022779e Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Thu, 9 Aug 2018 15:47:06 +0900
Subject: kconfig: fix the rule of mainmenu_stmt symbol

The rule of mainmenu_stmt does not have debug print of zconf_lineno(),
but if it had, it would print a wrong line number for the same reason
as commit b2d00d7c61c8 ("kconfig: fix line numbers for if-entries in
menu tree").

The mainmenu_stmt does not need to eat following empty lines because
they are reduced to common_stmt.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/kconfig/zconf.y | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/scripts/kconfig/zconf.y b/scripts/kconfig/zconf.y
index 96081aa0fef0..22fceb264cf5 100644
--- a/scripts/kconfig/zconf.y
+++ b/scripts/kconfig/zconf.y
@@ -31,7 +31,7 @@ struct symbol *symbol_hash[SYMBOL_HASHSIZE];
 static struct menu *current_menu, *current_entry;
 
 %}
-%expect 31
+%expect 30
 
 %union
 {
@@ -117,7 +117,7 @@ start: mainmenu_stmt stmt_list | stmt_list;
 
 /* mainmenu entry */
 
-mainmenu_stmt: T_MAINMENU prompt nl
+mainmenu_stmt: T_MAINMENU prompt T_EOL
 {
 	menu_add_prompt(P_MENU, $2, NULL);
 };
-- 
cgit v1.2.3


From a34a9b9682a5a9de53386ed0872c7d38ca9d6b38 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jun 2018 09:04:53 +0200
Subject: parisc: merge pcx_dma_ops and pcxl_dma_ops

The only difference is that pcxl supports dma coherent allocations, while
pcx only supports non-consistent allocations and otherwise fails.

But dma_alloc* is not in the fast path, and merging these two allows an
easy migration path to the generic dma-noncoherent implementation, so
do it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/dma-mapping.h |  3 +-
 arch/parisc/kernel/pci-dma.c          | 80 ++++++++++++++++-------------------
 arch/parisc/kernel/setup.c            |  8 ++--
 arch/parisc/mm/init.c                 | 11 ++---
 4 files changed, 43 insertions(+), 59 deletions(-)

diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index 01e1fc057c83..eeec8dd18e74 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -22,8 +22,7 @@
 */
 
 #ifdef CONFIG_PA11
-extern const struct dma_map_ops pcxl_dma_ops;
-extern const struct dma_map_ops pcx_dma_ops;
+extern const struct dma_map_ops pa11_dma_ops;
 #endif
 
 extern const struct dma_map_ops *hppa_dma_ops;
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 6df07ce4f3c2..d34cd6d34717 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -395,7 +395,7 @@ pcxl_dma_init(void)
 
 __initcall(pcxl_dma_init);
 
-static void *pa11_dma_alloc(struct device *dev, size_t size,
+static void *pcxl_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
 {
 	unsigned long vaddr;
@@ -422,16 +422,44 @@ static void *pa11_dma_alloc(struct device *dev, size_t size,
 	return (void *)vaddr;
 }
 
+static void *pcx_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
+{
+	void *addr;
+
+	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
+		return NULL;
+
+	addr = (void *)__get_free_pages(flag, get_order(size));
+	if (addr)
+		*dma_handle = (dma_addr_t)virt_to_phys(addr);
+
+	return addr;
+}
+
+static void *pa11_dma_alloc(struct device *dev, size_t size,
+		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
+{
+
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl)
+		return pcxl_dma_alloc(dev, size, dma_handle, gfp, attrs);
+	else
+		return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs);
+}
+
 static void pa11_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
-	int order;
+	int order = get_order(size);
 
-	order = get_order(size);
-	size = 1 << (order + PAGE_SHIFT);
-	unmap_uncached_pages((unsigned long)vaddr, size);
-	pcxl_free_range((unsigned long)vaddr, size);
-	free_pages((unsigned long)__va(dma_handle), order);
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
+		size = 1 << (order + PAGE_SHIFT);
+		unmap_uncached_pages((unsigned long)vaddr, size);
+		pcxl_free_range((unsigned long)vaddr, size);
+
+		vaddr = __va(dma_handle);
+	}
+	free_pages((unsigned long)vaddr, get_order(size));
 }
 
 static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
@@ -560,7 +588,7 @@ static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	flush_kernel_dcache_range((unsigned long)vaddr, size);
 }
 
-const struct dma_map_ops pcxl_dma_ops = {
+const struct dma_map_ops pa11_dma_ops = {
 	.alloc =		pa11_dma_alloc,
 	.free =			pa11_dma_free,
 	.map_page =		pa11_dma_map_page,
@@ -573,39 +601,3 @@ const struct dma_map_ops pcxl_dma_ops = {
 	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
 	.cache_sync =		pa11_dma_cache_sync,
 };
-
-static void *pcx_dma_alloc(struct device *dev, size_t size,
-		dma_addr_t *dma_handle, gfp_t flag, unsigned long attrs)
-{
-	void *addr;
-
-	if ((attrs & DMA_ATTR_NON_CONSISTENT) == 0)
-		return NULL;
-
-	addr = (void *)__get_free_pages(flag, get_order(size));
-	if (addr)
-		*dma_handle = (dma_addr_t)virt_to_phys(addr);
-
-	return addr;
-}
-
-static void pcx_dma_free(struct device *dev, size_t size, void *vaddr,
-		dma_addr_t iova, unsigned long attrs)
-{
-	free_pages((unsigned long)vaddr, get_order(size));
-	return;
-}
-
-const struct dma_map_ops pcx_dma_ops = {
-	.alloc =		pcx_dma_alloc,
-	.free =			pcx_dma_free,
-	.map_page =		pa11_dma_map_page,
-	.unmap_page =		pa11_dma_unmap_page,
-	.map_sg =		pa11_dma_map_sg,
-	.unmap_sg =		pa11_dma_unmap_sg,
-	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
-	.sync_single_for_device = pa11_dma_sync_single_for_device,
-	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
-	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
-	.cache_sync =		pa11_dma_cache_sync,
-};
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 8d3a7b80ac42..5c8450a22255 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -97,14 +97,12 @@ void __init dma_ops_init(void)
 		panic(	"PA-RISC Linux currently only supports machines that conform to\n"
 			"the PA-RISC 1.1 or 2.0 architecture specification.\n");
 
-	case pcxs:
-	case pcxt:
-		hppa_dma_ops = &pcx_dma_ops;
-		break;
 	case pcxl2:
 		pa7300lc_init();
 	case pcxl: /* falls through */
-		hppa_dma_ops = &pcxl_dma_ops;
+	case pcxs:
+	case pcxt:
+		hppa_dma_ops = &pa11_dma_ops;
 		break;
 	default:
 		break;
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 2607d2d33405..74842d28a7a1 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -19,7 +19,6 @@
 #include <linux/gfp.h>
 #include <linux/delay.h>
 #include <linux/init.h>
-#include <linux/pci.h>		/* for hppa_dma_ops and pcxl_dma_ops */
 #include <linux/initrd.h>
 #include <linux/swap.h>
 #include <linux/unistd.h>
@@ -616,17 +615,13 @@ void __init mem_init(void)
 	free_all_bootmem();
 
 #ifdef CONFIG_PA11
-	if (hppa_dma_ops == &pcxl_dma_ops) {
+	if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) {
 		pcxl_dma_start = (unsigned long)SET_MAP_OFFSET(MAP_START);
 		parisc_vmalloc_start = SET_MAP_OFFSET(pcxl_dma_start
 						+ PCXL_DMA_MAP_SIZE);
-	} else {
-		pcxl_dma_start = 0;
-		parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
-	}
-#else
-	parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
+	} else
 #endif
+		parisc_vmalloc_start = SET_MAP_OFFSET(MAP_START);
 
 	mem_init_print_info(NULL);
 
-- 
cgit v1.2.3


From 7f1501053811414ddeff63db8f5d41bdbe38068f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jun 2018 09:04:54 +0200
Subject: parisc: always use flush_kernel_dcache_range for DMA cache
 maintainance

Current the S/G list based DMA ops use flush_kernel_vmap_range which
contains a few UP optimizations, while the rest of the DMA operations
uses flush_kernel_dcache_range.  The single vs sg operations are supposed
to have the same effect, so they should use the same routines.  Use
the more conservation version for now, but if people more familiar with
parisc think the vmap version is generally fine for DMA we should switch
all interfaces over to it.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/pci-dma.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index d34cd6d34717..1f85ca2c0c9e 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -537,7 +537,7 @@ static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
 	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
+		flush_kernel_dcache_range(sg_virt(sg), sg->length);
 }
 
 static void pa11_dma_sync_single_for_cpu(struct device *dev,
@@ -568,7 +568,7 @@ static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
 	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
+		flush_kernel_dcache_range(sg_virt(sg), sg->length);
 }
 
 static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
@@ -579,7 +579,7 @@ static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *
 	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
 
 	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_vmap_range(sg_virt(sg), sg->length);
+		flush_kernel_dcache_range(sg_virt(sg), sg->length);
 }
 
 static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-- 
cgit v1.2.3


From c1f59375b3782f478ac2c488889abdc00dd8e25f Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 19 Jun 2018 09:04:55 +0200
Subject: parisc: use generic dma_noncoherent_ops

Switch to the generic noncoherent direct mapping implementation.

Fix sync_single_for_cpu to do skip the cache flush unless the transfer
is to the device to match the more tested unmap_single path which should
have the same cache coherency implications.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/Kconfig                   |   4 +
 arch/parisc/include/asm/dma-mapping.h |   4 -
 arch/parisc/kernel/pci-dma.c          | 145 +++-------------------------------
 arch/parisc/kernel/setup.c            |   2 +-
 4 files changed, 16 insertions(+), 139 deletions(-)

diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index e7705dde953f..1fcdf1565b23 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -187,6 +187,10 @@ config PA20
 config PA11
 	def_bool y
 	depends on PA7000 || PA7100LC || PA7200 || PA7300LC
+	select ARCH_HAS_SYNC_DMA_FOR_CPU
+	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
+	select DMA_NONCOHERENT_OPS
+	select DMA_NONCOHERENT_CACHE_SYNC
 
 config PREFETCH
 	def_bool y
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index eeec8dd18e74..44a9f97194aa 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -21,10 +21,6 @@
 ** flush/purge and allocate "regular" cacheable pages for everything.
 */
 
-#ifdef CONFIG_PA11
-extern const struct dma_map_ops pa11_dma_ops;
-#endif
-
 extern const struct dma_map_ops *hppa_dma_ops;
 
 static inline const struct dma_map_ops *get_arch_dma_ops(struct bus_type *bus)
diff --git a/arch/parisc/kernel/pci-dma.c b/arch/parisc/kernel/pci-dma.c
index 1f85ca2c0c9e..04c48f1ef3fb 100644
--- a/arch/parisc/kernel/pci-dma.c
+++ b/arch/parisc/kernel/pci-dma.c
@@ -21,13 +21,12 @@
 #include <linux/init.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
-#include <linux/pci.h>
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/types.h>
-#include <linux/scatterlist.h>
-#include <linux/export.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
 
 #include <asm/cacheflush.h>
 #include <asm/dma.h>    /* for DMA_CHUNK_SIZE */
@@ -437,7 +436,7 @@ static void *pcx_dma_alloc(struct device *dev, size_t size,
 	return addr;
 }
 
-static void *pa11_dma_alloc(struct device *dev, size_t size,
+void *arch_dma_alloc(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp, unsigned long attrs)
 {
 
@@ -447,7 +446,7 @@ static void *pa11_dma_alloc(struct device *dev, size_t size,
 		return pcx_dma_alloc(dev, size, dma_handle, gfp, attrs);
 }
 
-static void pa11_dma_free(struct device *dev, size_t size, void *vaddr,
+void arch_dma_free(struct device *dev, size_t size, void *vaddr,
 		dma_addr_t dma_handle, unsigned long attrs)
 {
 	int order = get_order(size);
@@ -462,142 +461,20 @@ static void pa11_dma_free(struct device *dev, size_t size, void *vaddr,
 	free_pages((unsigned long)vaddr, get_order(size));
 }
 
-static dma_addr_t pa11_dma_map_page(struct device *dev, struct page *page,
-		unsigned long offset, size_t size,
-		enum dma_data_direction direction, unsigned long attrs)
+void arch_sync_dma_for_device(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	void *addr = page_address(page) + offset;
-	BUG_ON(direction == DMA_NONE);
-
-	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
-		flush_kernel_dcache_range((unsigned long) addr, size);
-
-	return virt_to_phys(addr);
-}
-
-static void pa11_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
-		size_t size, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	/*
-	 * For PCI_DMA_FROMDEVICE this flush is not necessary for the
-	 * simple map/unmap case. However, it IS necessary if if
-	 * pci_dma_sync_single_* has been called and the buffer reused.
-	 */
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle), size);
+	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-static int pa11_dma_map_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
+void arch_sync_dma_for_cpu(struct device *dev, phys_addr_t paddr,
+		size_t size, enum dma_data_direction dir)
 {
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
-
-	for_each_sg(sglist, sg, nents, i) {
-		unsigned long vaddr = (unsigned long)sg_virt(sg);
-
-		sg_dma_address(sg) = (dma_addr_t) virt_to_phys(vaddr);
-		sg_dma_len(sg) = sg->length;
-
-		if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-			continue;
-
-		flush_kernel_dcache_range(vaddr, sg->length);
-	}
-	return nents;
+	flush_kernel_dcache_range((unsigned long)phys_to_virt(paddr), size);
 }
 
-static void pa11_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
-		int nents, enum dma_data_direction direction,
-		unsigned long attrs)
-{
-	int i;
-	struct scatterlist *sg;
-
-	BUG_ON(direction == DMA_NONE);
-
-	if (attrs & DMA_ATTR_SKIP_CPU_SYNC)
-		return;
-
-	if (direction == DMA_TO_DEVICE)
-		return;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_dcache_range(sg_virt(sg), sg->length);
-}
-
-static void pa11_dma_sync_single_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
-			size);
-}
-
-static void pa11_dma_sync_single_for_device(struct device *dev,
-		dma_addr_t dma_handle, size_t size,
-		enum dma_data_direction direction)
-{
-	BUG_ON(direction == DMA_NONE);
-
-	flush_kernel_dcache_range((unsigned long) phys_to_virt(dma_handle),
-			size);
-}
-
-static void pa11_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_dcache_range(sg_virt(sg), sg->length);
-}
-
-static void pa11_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sglist, int nents, enum dma_data_direction direction)
-{
-	int i;
-	struct scatterlist *sg;
-
-	/* once we do combining we'll need to use phys_to_virt(sg_dma_address(sglist)) */
-
-	for_each_sg(sglist, sg, nents, i)
-		flush_kernel_dcache_range(sg_virt(sg), sg->length);
-}
-
-static void pa11_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+void arch_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 	       enum dma_data_direction direction)
 {
 	flush_kernel_dcache_range((unsigned long)vaddr, size);
 }
-
-const struct dma_map_ops pa11_dma_ops = {
-	.alloc =		pa11_dma_alloc,
-	.free =			pa11_dma_free,
-	.map_page =		pa11_dma_map_page,
-	.unmap_page =		pa11_dma_unmap_page,
-	.map_sg =		pa11_dma_map_sg,
-	.unmap_sg =		pa11_dma_unmap_sg,
-	.sync_single_for_cpu =	pa11_dma_sync_single_for_cpu,
-	.sync_single_for_device = pa11_dma_sync_single_for_device,
-	.sync_sg_for_cpu =	pa11_dma_sync_sg_for_cpu,
-	.sync_sg_for_device =	pa11_dma_sync_sg_for_device,
-	.cache_sync =		pa11_dma_cache_sync,
-};
diff --git a/arch/parisc/kernel/setup.c b/arch/parisc/kernel/setup.c
index 5c8450a22255..4e87c35c22b7 100644
--- a/arch/parisc/kernel/setup.c
+++ b/arch/parisc/kernel/setup.c
@@ -102,7 +102,7 @@ void __init dma_ops_init(void)
 	case pcxl: /* falls through */
 	case pcxs:
 	case pcxt:
-		hppa_dma_ops = &pa11_dma_ops;
+		hppa_dma_ops = &dma_noncoherent_ops;
 		break;
 	default:
 		break;
-- 
cgit v1.2.3


From 93cb8e20d56be40c541475f77b5f565fbb385a4b Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Sun, 1 Jul 2018 18:18:15 +0200
Subject: parisc: Drop architecture-specific ENOTSUP define

parisc is the only Linux architecture which has defined a value for ENOTSUP.
All other architectures #define ENOTSUP as EOPNOTSUPP in their libc headers.

Having an own value for ENOTSUP which is different than EOPNOTSUPP often gives
problems with userspace programs which expect both to be the same.  One such
example is a build error in the libuv package, as can be seen in
https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=900237.

Since we dropped HP-UX support, there is no real benefit in keeping an own
value for ENOTSUP. This patch drops the parisc value for ENOTSUP from the
kernel sources. glibc needs no patch, it reuses the exported headers.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/uapi/asm/errno.h       |  1 -
 kernel/time/posix-timers.c                 | 13 ++-----------
 tools/arch/parisc/include/uapi/asm/errno.h |  1 -
 3 files changed, 2 insertions(+), 13 deletions(-)

diff --git a/arch/parisc/include/uapi/asm/errno.h b/arch/parisc/include/uapi/asm/errno.h
index fc0df353ff0d..87245c584784 100644
--- a/arch/parisc/include/uapi/asm/errno.h
+++ b/arch/parisc/include/uapi/asm/errno.h
@@ -113,7 +113,6 @@
 #define	ELOOP		249	/* Too many symbolic links encountered */
 #define	ENOSYS		251	/* Function not implemented */
 
-#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
 #define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
 #define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
 
diff --git a/kernel/time/posix-timers.c b/kernel/time/posix-timers.c
index e08ce3f27447..66321cbdf90c 100644
--- a/kernel/time/posix-timers.c
+++ b/kernel/time/posix-timers.c
@@ -85,15 +85,6 @@ static const struct k_clock clock_realtime, clock_monotonic;
 #error "SIGEV_THREAD_ID must not share bit with other SIGEV values!"
 #endif
 
-/*
- * parisc wants ENOTSUP instead of EOPNOTSUPP
- */
-#ifndef ENOTSUP
-# define ENANOSLEEP_NOTSUP EOPNOTSUPP
-#else
-# define ENANOSLEEP_NOTSUP ENOTSUP
-#endif
-
 /*
  * The timer ID is turned into a timer address by idr_find().
  * Verifying a valid ID consists of:
@@ -1220,7 +1211,7 @@ SYSCALL_DEFINE4(clock_nanosleep, const clockid_t, which_clock, int, flags,
 	if (!kc)
 		return -EINVAL;
 	if (!kc->nsleep)
-		return -ENANOSLEEP_NOTSUP;
+		return -EOPNOTSUPP;
 
 	if (get_timespec64(&t, rqtp))
 		return -EFAULT;
@@ -1247,7 +1238,7 @@ COMPAT_SYSCALL_DEFINE4(clock_nanosleep, clockid_t, which_clock, int, flags,
 	if (!kc)
 		return -EINVAL;
 	if (!kc->nsleep)
-		return -ENANOSLEEP_NOTSUP;
+		return -EOPNOTSUPP;
 
 	if (compat_get_timespec64(&t, rqtp))
 		return -EFAULT;
diff --git a/tools/arch/parisc/include/uapi/asm/errno.h b/tools/arch/parisc/include/uapi/asm/errno.h
index fc0df353ff0d..87245c584784 100644
--- a/tools/arch/parisc/include/uapi/asm/errno.h
+++ b/tools/arch/parisc/include/uapi/asm/errno.h
@@ -113,7 +113,6 @@
 #define	ELOOP		249	/* Too many symbolic links encountered */
 #define	ENOSYS		251	/* Function not implemented */
 
-#define ENOTSUP		252	/* Function not implemented (POSIX.4 / HPUX) */
 #define ECANCELLED	253	/* aio request was canceled before complete (POSIX.4 / HPUX) */
 #define ECANCELED	ECANCELLED	/* SuSv3 and Solaris wants one 'L' */
 
-- 
cgit v1.2.3


From 75ebedf1d26376cafad87b43196c15161463b82a Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Thu, 28 Jun 2018 22:47:11 +0200
Subject: parisc: Add HAVE_REGS_AND_STACK_ACCESS_API feature

Some parts of the HAVE_REGS_AND_STACK_ACCESS_API feature is needed for
the rseq syscall. This patch adds the most important parts, and as long
as we don't support kprobes, we should be fine.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/Kconfig              |   1 +
 arch/parisc/include/asm/ptrace.h |  11 +++++
 arch/parisc/kernel/ptrace.c      | 100 +++++++++++++++++++++++++++++++++++++++
 3 files changed, 112 insertions(+)

diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index 1fcdf1565b23..e21751fb24aa 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -45,6 +45,7 @@ config PARISC
 	select HAVE_ARCH_HASH
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_REGS_AND_STACK_ACCESS_API
 	select GENERIC_SCHED_CLOCK
 	select HAVE_UNSTABLE_SCHED_CLOCK if SMP
 	select GENERIC_CLOCKEVENTS
diff --git a/arch/parisc/include/asm/ptrace.h b/arch/parisc/include/asm/ptrace.h
index 46da07670c2b..2a27b275ab09 100644
--- a/arch/parisc/include/asm/ptrace.h
+++ b/arch/parisc/include/asm/ptrace.h
@@ -25,4 +25,15 @@ static inline unsigned long regs_return_value(struct pt_regs *regs)
 	return regs->gr[20];
 }
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+						unsigned long val)
+{
+        regs->iaoq[0] = val;
+}
+
+/* Query offset/name of register from its name/offset */
+extern int regs_query_register_offset(const char *name);
+extern const char *regs_query_register_name(unsigned int offset);
+#define MAX_REG_OFFSET (offsetof(struct pt_regs, ipsw))
+
 #endif
diff --git a/arch/parisc/kernel/ptrace.c b/arch/parisc/kernel/ptrace.c
index 7aa1d4d0d444..2582df1c529b 100644
--- a/arch/parisc/kernel/ptrace.c
+++ b/arch/parisc/kernel/ptrace.c
@@ -676,3 +676,103 @@ const struct user_regset_view *task_user_regset_view(struct task_struct *task)
 #endif
 	return &user_parisc_native_view;
 }
+
+
+/* HAVE_REGS_AND_STACK_ACCESS_API feature */
+
+struct pt_regs_offset {
+	const char *name;
+	int offset;
+};
+
+#define REG_OFFSET_NAME(r)    {.name = #r, .offset = offsetof(struct pt_regs, r)}
+#define REG_OFFSET_INDEX(r,i) {.name = #r#i, .offset = offsetof(struct pt_regs, r[i])}
+#define REG_OFFSET_END {.name = NULL, .offset = 0}
+
+static const struct pt_regs_offset regoffset_table[] = {
+	REG_OFFSET_INDEX(gr,0),
+	REG_OFFSET_INDEX(gr,1),
+	REG_OFFSET_INDEX(gr,2),
+	REG_OFFSET_INDEX(gr,3),
+	REG_OFFSET_INDEX(gr,4),
+	REG_OFFSET_INDEX(gr,5),
+	REG_OFFSET_INDEX(gr,6),
+	REG_OFFSET_INDEX(gr,7),
+	REG_OFFSET_INDEX(gr,8),
+	REG_OFFSET_INDEX(gr,9),
+	REG_OFFSET_INDEX(gr,10),
+	REG_OFFSET_INDEX(gr,11),
+	REG_OFFSET_INDEX(gr,12),
+	REG_OFFSET_INDEX(gr,13),
+	REG_OFFSET_INDEX(gr,14),
+	REG_OFFSET_INDEX(gr,15),
+	REG_OFFSET_INDEX(gr,16),
+	REG_OFFSET_INDEX(gr,17),
+	REG_OFFSET_INDEX(gr,18),
+	REG_OFFSET_INDEX(gr,19),
+	REG_OFFSET_INDEX(gr,20),
+	REG_OFFSET_INDEX(gr,21),
+	REG_OFFSET_INDEX(gr,22),
+	REG_OFFSET_INDEX(gr,23),
+	REG_OFFSET_INDEX(gr,24),
+	REG_OFFSET_INDEX(gr,25),
+	REG_OFFSET_INDEX(gr,26),
+	REG_OFFSET_INDEX(gr,27),
+	REG_OFFSET_INDEX(gr,28),
+	REG_OFFSET_INDEX(gr,29),
+	REG_OFFSET_INDEX(gr,30),
+	REG_OFFSET_INDEX(gr,31),
+	REG_OFFSET_INDEX(sr,0),
+	REG_OFFSET_INDEX(sr,1),
+	REG_OFFSET_INDEX(sr,2),
+	REG_OFFSET_INDEX(sr,3),
+	REG_OFFSET_INDEX(sr,4),
+	REG_OFFSET_INDEX(sr,5),
+	REG_OFFSET_INDEX(sr,6),
+	REG_OFFSET_INDEX(sr,7),
+	REG_OFFSET_INDEX(iasq,0),
+	REG_OFFSET_INDEX(iasq,1),
+	REG_OFFSET_INDEX(iaoq,0),
+	REG_OFFSET_INDEX(iaoq,1),
+	REG_OFFSET_NAME(cr27),
+	REG_OFFSET_NAME(ksp),
+	REG_OFFSET_NAME(kpc),
+	REG_OFFSET_NAME(sar),
+	REG_OFFSET_NAME(iir),
+	REG_OFFSET_NAME(isr),
+	REG_OFFSET_NAME(ior),
+	REG_OFFSET_NAME(ipsw),
+	REG_OFFSET_END,
+};
+
+/**
+ * regs_query_register_offset() - query register offset from its name
+ * @name:	the name of a register
+ *
+ * regs_query_register_offset() returns the offset of a register in struct
+ * pt_regs from its name. If the name is invalid, this returns -EINVAL;
+ */
+int regs_query_register_offset(const char *name)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (!strcmp(roff->name, name))
+			return roff->offset;
+	return -EINVAL;
+}
+
+/**
+ * regs_query_register_name() - query register name from its offset
+ * @offset:	the offset of a register in struct pt_regs.
+ *
+ * regs_query_register_name() returns the name of a register from its
+ * offset in struct pt_regs. If the @offset is invalid, this returns NULL;
+ */
+const char *regs_query_register_name(unsigned int offset)
+{
+	const struct pt_regs_offset *roff;
+	for (roff = regoffset_table; roff->name != NULL; roff++)
+		if (roff->offset == offset)
+			return roff->name;
+	return NULL;
+}
-- 
cgit v1.2.3


From 4a53ec1ccf932f86845c96a5092ba4507621c84d Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Wed, 1 Aug 2018 11:22:56 -0700
Subject: parisc: prefer _THIS_IP_ and _RET_IP_ statement expressions

As part of the effort to reduce the code duplication between _THIS_IP_
and current_text_addr(), let's consolidate callers of
current_text_addr() to use _THIS_IP_.

Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/unwind.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index 2ef83d78eec4..a4b430f440a9 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -439,8 +439,8 @@ unsigned long return_address(unsigned int level)
 	/* initialize unwind info */
 	asm volatile ("copy %%r30, %0" : "=r"(sp));
 	memset(&r, 0, sizeof(struct pt_regs));
-	r.iaoq[0] = (unsigned long) current_text_addr();
-	r.gr[2] = (unsigned long) __builtin_return_address(0);
+	r.iaoq[0] = _THIS_IP_;
+	r.gr[2] = _RET_IP_;
 	r.gr[30] = sp;
 	unwind_frame_init(&info, current, &r);
 
-- 
cgit v1.2.3


From 7797167ffde1f00446301cb22b37b7c03194cfaf Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Sun, 12 Aug 2018 16:38:03 -0400
Subject: parisc: Remove ordered stores from syscall.S
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that we use a sync prior to releasing the locks in syscall.S, we don't need
the PA 2.0 ordered stores used to release some locks.  Using an ordered store,
potentially slows the release and subsequent code.

There are a number of other ordered stores and loads that serve no purpose.  I
have converted these to normal stores.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: stable@vger.kernel.org # 4.0+
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/kernel/syscall.S | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 4886a6db42e9..5f7e57fcaeef 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -629,12 +629,12 @@ cas_action:
 	stw	%r1, 4(%sr2,%r20)
 #endif
 	/* The load and store could fail */
-1:	ldw,ma	0(%r26), %r28
+1:	ldw	0(%r26), %r28
 	sub,<>	%r28, %r25, %r0
-2:	stw,ma	%r24, 0(%r26)
+2:	stw	%r24, 0(%r26)
 	/* Free lock */
 	sync
-	stw,ma	%r20, 0(%sr2,%r20)
+	stw	%r20, 0(%sr2,%r20)
 #if ENABLE_LWS_DEBUG
 	/* Clear thread register indicator */
 	stw	%r0, 4(%sr2,%r20)
@@ -798,30 +798,30 @@ cas2_action:
 	ldo	1(%r0),%r28
 
 	/* 8bit CAS */
-13:	ldb,ma	0(%r26), %r29
+13:	ldb	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-14:	stb,ma	%r24, 0(%r26)
+14:	stb	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 16bit CAS */
-15:	ldh,ma	0(%r26), %r29
+15:	ldh	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-16:	sth,ma	%r24, 0(%r26)
+16:	sth	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
 	nop
 
 	/* 32bit CAS */
-17:	ldw,ma	0(%r26), %r29
+17:	ldw	0(%r26), %r29
 	sub,=	%r29, %r25, %r0
 	b,n	cas2_end
-18:	stw,ma	%r24, 0(%r26)
+18:	stw	%r24, 0(%r26)
 	b	cas2_end
 	copy	%r0, %r28
 	nop
@@ -829,10 +829,10 @@ cas2_action:
 
 	/* 64bit CAS */
 #ifdef CONFIG_64BIT
-19:	ldd,ma	0(%r26), %r29
+19:	ldd	0(%r26), %r29
 	sub,*=	%r29, %r25, %r0
 	b,n	cas2_end
-20:	std,ma	%r24, 0(%r26)
+20:	std	%r24, 0(%r26)
 	copy	%r0, %r28
 #else
 	/* Compare first word */
@@ -851,7 +851,7 @@ cas2_action:
 cas2_end:
 	/* Free lock */
 	sync
-	stw,ma	%r20, 0(%sr2,%r20)
+	stw	%r20, 0(%sr2,%r20)
 	/* Enable interrupts */
 	ssm	PSW_SM_I, %r0
 	/* Return to userspace, set no error */
-- 
cgit v1.2.3


From 3b885ac1dc35b87a39ee176a6c7e2af9c789d8b8 Mon Sep 17 00:00:00 2001
From: John David Anglin <dave.anglin@bell.net>
Date: Sun, 12 Aug 2018 16:31:17 -0400
Subject: parisc: Remove unnecessary barriers from spinlock.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that mb() is an instruction barrier, it will slow performance if we issue
unnecessary barriers.

The spinlock defines have a number of unnecessary barriers.  The __ldcw()
define is both a hardware and compiler barrier.  The mb() barriers in the
routines using __ldcw() serve no purpose.

The only barrier needed is the one in arch_spin_unlock().  We need to ensure
all accesses are complete prior to releasing the lock.

Signed-off-by: John David Anglin <dave.anglin@bell.net>
Cc: stable@vger.kernel.org # 4.0+
Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/spinlock.h | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index 6f84b6acc86e..8a63515f03bf 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -20,7 +20,6 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 {
 	volatile unsigned int *a;
 
-	mb();
 	a = __ldcw_align(x);
 	while (__ldcw(a) == 0)
 		while (*a == 0)
@@ -30,17 +29,16 @@ static inline void arch_spin_lock_flags(arch_spinlock_t *x,
 				local_irq_disable();
 			} else
 				cpu_relax();
-	mb();
 }
 #define arch_spin_lock_flags arch_spin_lock_flags
 
 static inline void arch_spin_unlock(arch_spinlock_t *x)
 {
 	volatile unsigned int *a;
-	mb();
+
 	a = __ldcw_align(x);
-	*a = 1;
 	mb();
+	*a = 1;
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *x)
@@ -48,10 +46,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *x)
 	volatile unsigned int *a;
 	int ret;
 
-	mb();
 	a = __ldcw_align(x);
         ret = __ldcw(a) != 0;
-	mb();
 
 	return ret;
 }
-- 
cgit v1.2.3


From c8921d72e390cb6fca3fb2b0c2badfda851647eb Mon Sep 17 00:00:00 2001
From: Helge Deller <deller@gmx.de>
Date: Sun, 5 Aug 2018 00:03:29 +0200
Subject: parisc: Fix and improve kernel stack unwinding

This patchset fixes and improves stack unwinding a lot:
1. Show backward stack traces with up to 30 callsites
2. Add callinfo to ENTRY_CFI() such that every assembler function will get an
   entry in the unwind table
3. Use constants instead of numbers in call_on_stack()
4. Do not depend on CONFIG_KALLSYMS to generate backtraces.
5. Speed up backtrace generation

Make sure you have this patch to GNU as installed:
https://sourceware.org/ml/binutils/2018-07/msg00474.html
Without this patch, unwind info in the kernel is often wrong for various
functions.

Signed-off-by: Helge Deller <deller@gmx.de>
---
 arch/parisc/include/asm/assembly.h |   2 +
 arch/parisc/include/asm/linkage.h  |  17 +++--
 arch/parisc/include/asm/unwind.h   |   3 +
 arch/parisc/kernel/entry.S         |  53 +++++++---------
 arch/parisc/kernel/pacache.S       | 125 -------------------------------------
 arch/parisc/kernel/process.c       |   2 +-
 arch/parisc/kernel/real2.S         |   6 --
 arch/parisc/kernel/traps.c         |   2 +-
 arch/parisc/kernel/unwind.c        |  89 ++++++++++++++------------
 arch/parisc/lib/lusercopy.S        |  21 -------
 10 files changed, 88 insertions(+), 232 deletions(-)

diff --git a/arch/parisc/include/asm/assembly.h b/arch/parisc/include/asm/assembly.h
index 60e6f07b7e32..e9c6385ef0d1 100644
--- a/arch/parisc/include/asm/assembly.h
+++ b/arch/parisc/include/asm/assembly.h
@@ -36,6 +36,7 @@
 #define RP_OFFSET	16
 #define FRAME_SIZE	128
 #define CALLEE_REG_FRAME_SIZE	144
+#define REG_SZ		8
 #define ASM_ULONG_INSN	.dword
 #else	/* CONFIG_64BIT */
 #define LDREG	ldw
@@ -50,6 +51,7 @@
 #define RP_OFFSET	20
 #define FRAME_SIZE	64
 #define CALLEE_REG_FRAME_SIZE	128
+#define REG_SZ		4
 #define ASM_ULONG_INSN	.word
 #endif
 
diff --git a/arch/parisc/include/asm/linkage.h b/arch/parisc/include/asm/linkage.h
index 9a69bf6fc4b6..49f6f3d772cc 100644
--- a/arch/parisc/include/asm/linkage.h
+++ b/arch/parisc/include/asm/linkage.h
@@ -18,9 +18,9 @@
 #ifdef __ASSEMBLY__
 
 #define ENTRY(name) \
-	.export name !\
-	ALIGN !\
-name:
+	ALIGN	!\
+name:		ASM_NL\
+	.export name
 
 #ifdef CONFIG_64BIT
 #define ENDPROC(name) \
@@ -31,13 +31,18 @@ name:
 	END(name)
 #endif
 
-#define ENTRY_CFI(name) \
+#define ENTRY_CFI(name, ...) \
 	ENTRY(name)	ASM_NL\
+	.proc		ASM_NL\
+	.callinfo __VA_ARGS__	ASM_NL\
+	.entry		ASM_NL\
 	CFI_STARTPROC
 
 #define ENDPROC_CFI(name) \
-	ENDPROC(name)	ASM_NL\
-	CFI_ENDPROC
+	CFI_ENDPROC	ASM_NL\
+	.exit		ASM_NL\
+	.procend	ASM_NL\
+	ENDPROC(name)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/parisc/include/asm/unwind.h b/arch/parisc/include/asm/unwind.h
index c73a3ee20226..f133b7efbebb 100644
--- a/arch/parisc/include/asm/unwind.h
+++ b/arch/parisc/include/asm/unwind.h
@@ -4,6 +4,9 @@
 
 #include <linux/list.h>
 
+/* Max number of levels to backtrace */
+#define MAX_UNWIND_ENTRIES	30
+
 /* From ABI specifications */
 struct unwind_table_entry {
 	unsigned int region_start;
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 1b4732e20137..c7508f5717fb 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -766,7 +766,6 @@ END(fault_vector_11)
 #endif
 	/* Fault vector is separately protected and *must* be on its own page */
 	.align		PAGE_SIZE
-ENTRY(end_fault_vector)
 
 	.import		handle_interruption,code
 	.import		do_cpu_irq_mask,code
@@ -778,7 +777,6 @@ ENTRY(end_fault_vector)
 	 */
 
 ENTRY_CFI(ret_from_kernel_thread)
-
 	/* Call schedule_tail first though */
 	BL	schedule_tail, %r2
 	nop
@@ -817,8 +815,9 @@ ENTRY_CFI(_switch_to)
 	LDREG	TASK_THREAD_INFO(%r25), %r25
 	bv	%r0(%r2)
 	mtctl   %r25,%cr30
+ENDPROC_CFI(_switch_to)
 
-_switch_to_ret:
+ENTRY_CFI(_switch_to_ret)
 	mtctl	%r0, %cr0		/* Needed for single stepping */
 	callee_rest
 	callee_rest_float
@@ -826,7 +825,7 @@ _switch_to_ret:
 	LDREG	-RP_OFFSET(%r30), %r2
 	bv	%r0(%r2)
 	copy	%r26, %r28
-ENDPROC_CFI(_switch_to)
+ENDPROC_CFI(_switch_to_ret)
 
 	/*
 	 * Common rfi return path for interruptions, kernel execve, and
@@ -887,12 +886,14 @@ ENTRY_CFI(syscall_exit_rfi)
 	STREG   %r19,PT_SR5(%r16)
 	STREG   %r19,PT_SR6(%r16)
 	STREG   %r19,PT_SR7(%r16)
+ENDPROC_CFI(syscall_exit_rfi)
 
-intr_return:
+ENTRY_CFI(intr_return)
 	/* check for reschedule */
 	mfctl   %cr30,%r1
 	LDREG   TI_FLAGS(%r1),%r19	/* sched.h: TIF_NEED_RESCHED */
 	bb,<,n	%r19,31-TIF_NEED_RESCHED,intr_do_resched /* forward */
+ENDPROC_CFI(intr_return)
 
 	.import do_notify_resume,code
 intr_check_sig:
@@ -1048,7 +1049,6 @@ intr_extint:
 
 	b	do_cpu_irq_mask
 	ldo	R%intr_return(%r2), %r2	/* return to intr_return, not here */
-ENDPROC_CFI(syscall_exit_rfi)
 
 
 	/* Generic interruptions (illegal insn, unaligned, page fault, etc) */
@@ -1999,12 +1999,9 @@ ENDPROC_CFI(syscall_exit)
 	.align L1_CACHE_BYTES
 	.globl mcount
 	.type  mcount, @function
-ENTRY(mcount)
+ENTRY_CFI(mcount, caller)
 _mcount:
 	.export _mcount,data
-	.proc
-	.callinfo caller,frame=0
-	.entry
 	/*
 	 * The 64bit mcount() function pointer needs 4 dwords, of which the
 	 * first two are free.  We optimize it here and put 2 instructions for
@@ -2026,18 +2023,13 @@ ftrace_stub:
 	.dword mcount
 	.dword 0 /* code in head.S puts value of global gp here */
 #endif
-	.exit
-	.procend
-ENDPROC(mcount)
+ENDPROC_CFI(mcount)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	.align 8
 	.globl return_to_handler
 	.type  return_to_handler, @function
-ENTRY_CFI(return_to_handler)
-	.proc
-	.callinfo caller,frame=FRAME_SIZE
-	.entry
+ENTRY_CFI(return_to_handler, caller,frame=FRAME_SIZE)
 	.export parisc_return_to_handler,data
 parisc_return_to_handler:
 	copy %r3,%r1
@@ -2076,8 +2068,6 @@ parisc_return_to_handler:
 	bv	%r0(%rp)
 #endif
 	LDREGM -FRAME_SIZE(%sp),%r3
-	.exit
-	.procend
 ENDPROC_CFI(return_to_handler)
 
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
@@ -2087,31 +2077,30 @@ ENDPROC_CFI(return_to_handler)
 #ifdef CONFIG_IRQSTACKS
 /* void call_on_stack(unsigned long param1, void *func,
 		      unsigned long new_stack) */
-ENTRY_CFI(call_on_stack)
+ENTRY_CFI(call_on_stack, FRAME=2*FRAME_SIZE,CALLS,SAVE_RP,SAVE_SP)
 	copy	%sp, %r1
 
 	/* Regarding the HPPA calling conventions for function pointers,
 	   we assume the PIC register is not changed across call.  For
 	   CONFIG_64BIT, the argument pointer is left to point at the
 	   argument region allocated for the call to call_on_stack. */
+
+	/* Switch to new stack.  We allocate two frames.  */
+	ldo	2*FRAME_SIZE(%arg2), %sp
 # ifdef CONFIG_64BIT
-	/* Switch to new stack.  We allocate two 128 byte frames.  */
-	ldo	256(%arg2), %sp
 	/* Save previous stack pointer and return pointer in frame marker */
-	STREG	%rp, -144(%sp)
+	STREG	%rp, -FRAME_SIZE-RP_OFFSET(%sp)
 	/* Calls always use function descriptor */
 	LDREG	16(%arg1), %arg1
 	bve,l	(%arg1), %rp
-	STREG	%r1, -136(%sp)
-	LDREG	-144(%sp), %rp
+	STREG	%r1, -FRAME_SIZE-REG_SZ(%sp)
+	LDREG	-FRAME_SIZE-RP_OFFSET(%sp), %rp
 	bve	(%rp)
-	LDREG	-136(%sp), %sp
+	LDREG	-FRAME_SIZE-REG_SZ(%sp), %sp
 # else
-	/* Switch to new stack.  We allocate two 64 byte frames.  */
-	ldo	128(%arg2), %sp
 	/* Save previous stack pointer and return pointer in frame marker */
-	STREG	%r1, -68(%sp)
-	STREG	%rp, -84(%sp)
+	STREG	%r1, -FRAME_SIZE-REG_SZ(%sp)
+	STREG	%rp, -FRAME_SIZE-RP_OFFSET(%sp)
 	/* Calls use function descriptor if PLABEL bit is set */
 	bb,>=,n	%arg1, 30, 1f
 	depwi	0,31,2, %arg1
@@ -2119,9 +2108,9 @@ ENTRY_CFI(call_on_stack)
 1:
 	be,l	0(%sr4,%arg1), %sr0, %r31
 	copy	%r31, %rp
-	LDREG	-84(%sp), %rp
+	LDREG	-FRAME_SIZE-RP_OFFSET(%sp), %rp
 	bv	(%rp)
-	LDREG	-68(%sp), %sp
+	LDREG	-FRAME_SIZE-REG_SZ(%sp), %sp
 # endif /* CONFIG_64BIT */
 ENDPROC_CFI(call_on_stack)
 #endif /* CONFIG_IRQSTACKS */
diff --git a/arch/parisc/kernel/pacache.S b/arch/parisc/kernel/pacache.S
index 97451e67d35b..f33bf2d306d6 100644
--- a/arch/parisc/kernel/pacache.S
+++ b/arch/parisc/kernel/pacache.S
@@ -44,10 +44,6 @@
 	.align	16
 
 ENTRY_CFI(flush_tlb_all_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/*
 	 * The pitlbe and pdtlbe instructions should only be used to
 	 * flush the entire tlb. Also, there needs to be no intervening
@@ -189,18 +185,11 @@ fdtdone:
 
 2:      bv		%r0(%r2)
 	nop
-
-	.exit
-	.procend
 ENDPROC_CFI(flush_tlb_all_local)
 
 	.import cache_info,data
 
 ENTRY_CFI(flush_instruction_cache_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	load32		cache_info, %r1
 
 	/* Flush Instruction Cache */
@@ -256,18 +245,11 @@ fisync:
 	mtsm		%r22			/* restore I-bit */
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_instruction_cache_local)
 
 
 	.import cache_info, data
 ENTRY_CFI(flush_data_cache_local)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	load32		cache_info, %r1
 
 	/* Flush Data Cache */
@@ -324,9 +306,6 @@ fdsync:
 	mtsm		%r22			/* restore I-bit */
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_data_cache_local)
 
 /* Macros to serialize TLB purge operations on SMP.  */
@@ -362,10 +341,6 @@ ENDPROC_CFI(flush_data_cache_local)
 /* Clear page using kernel mapping.  */
 
 ENTRY_CFI(clear_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 #ifdef CONFIG_64BIT
 
 	/* Unroll the loop.  */
@@ -424,18 +399,11 @@ ENTRY_CFI(clear_page_asm)
 #endif
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(clear_page_asm)
 
 /* Copy page using kernel mapping.  */
 
 ENTRY_CFI(copy_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 #ifdef CONFIG_64BIT
 	/* PA8x00 CPUs can consume 2 loads or 1 store per cycle.
 	 * Unroll the loop by hand and arrange insn appropriately.
@@ -542,9 +510,6 @@ ENTRY_CFI(copy_page_asm)
 #endif
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(copy_page_asm)
 
 /*
@@ -598,10 +563,6 @@ ENDPROC_CFI(copy_page_asm)
 	 */
 
 ENTRY_CFI(copy_user_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/* Convert virtual `to' and `from' addresses to physical addresses.
 	   Move `from' physical address to non shadowed register.  */
 	ldil		L%(__PAGE_OFFSET), %r1
@@ -750,16 +711,9 @@ ENTRY_CFI(copy_user_page_asm)
 
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(copy_user_page_asm)
 
 ENTRY_CFI(clear_user_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	tophys_r1	%r26
 
 	ldil		L%(TMPALIAS_MAP_START), %r28
@@ -836,16 +790,9 @@ ENTRY_CFI(clear_user_page_asm)
 
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(clear_user_page_asm)
 
 ENTRY_CFI(flush_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
 #if (TMPALIAS_MAP_START >= 0x80000000)
@@ -903,16 +850,9 @@ ENTRY_CFI(flush_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_dcache_page_asm)
 
 ENTRY_CFI(flush_icache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%(TMPALIAS_MAP_START), %r28
 #ifdef CONFIG_64BIT
 #if (TMPALIAS_MAP_START >= 0x80000000)
@@ -977,16 +917,9 @@ ENTRY_CFI(flush_icache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_icache_page_asm)
 
 ENTRY_CFI(flush_kernel_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
@@ -1020,16 +953,9 @@ ENTRY_CFI(flush_kernel_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_dcache_page_asm)
 
 ENTRY_CFI(purge_kernel_dcache_page_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 
@@ -1062,16 +988,9 @@ ENTRY_CFI(purge_kernel_dcache_page_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(purge_kernel_dcache_page_asm)
 
 ENTRY_CFI(flush_user_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1083,16 +1002,9 @@ ENTRY_CFI(flush_user_dcache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_user_dcache_range_asm)
 
 ENTRY_CFI(flush_kernel_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1105,16 +1017,9 @@ ENTRY_CFI(flush_kernel_dcache_range_asm)
 	syncdma
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_dcache_range_asm)
 
 ENTRY_CFI(purge_kernel_dcache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%dcache_stride, %r1
 	ldw		R%dcache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1127,16 +1032,9 @@ ENTRY_CFI(purge_kernel_dcache_range_asm)
 	syncdma
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(purge_kernel_dcache_range_asm)
 
 ENTRY_CFI(flush_user_icache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1148,16 +1046,9 @@ ENTRY_CFI(flush_user_icache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_user_icache_range_asm)
 
 ENTRY_CFI(flush_kernel_icache_page)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 
@@ -1191,16 +1082,9 @@ ENTRY_CFI(flush_kernel_icache_page)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(flush_kernel_icache_page)
 
 ENTRY_CFI(flush_kernel_icache_range_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	ldil		L%icache_stride, %r1
 	ldw		R%icache_stride(%r1), %r23
 	ldo		-1(%r23), %r21
@@ -1212,8 +1096,6 @@ ENTRY_CFI(flush_kernel_icache_range_asm)
 	sync
 	bv		%r0(%r2)
 	nop
-	.exit
-	.procend
 ENDPROC_CFI(flush_kernel_icache_range_asm)
 
 	__INIT
@@ -1223,10 +1105,6 @@ ENDPROC_CFI(flush_kernel_icache_range_asm)
 	 */
 	.align	256
 ENTRY_CFI(disable_sr_hashing_asm)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/*
 	 * Switch to real mode
 	 */
@@ -1308,9 +1186,6 @@ srdis_done:
 
 2:      bv		%r0(%r2)
 	nop
-	.exit
-
-	.procend
 ENDPROC_CFI(disable_sr_hashing_asm)
 
 	.end
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index b931745815e0..eb39e7e380d7 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -302,7 +302,7 @@ get_wchan(struct task_struct *p)
 		ip = info.ip;
 		if (!in_sched_functions(ip))
 			return ip;
-	} while (count++ < 16);
+	} while (count++ < MAX_UNWIND_ENTRIES);
 	return 0;
 }
 
diff --git a/arch/parisc/kernel/real2.S b/arch/parisc/kernel/real2.S
index cc9963421a19..2b16d8d6598f 100644
--- a/arch/parisc/kernel/real2.S
+++ b/arch/parisc/kernel/real2.S
@@ -35,12 +35,6 @@ real32_stack:
 real64_stack:
 	.block	8192
 
-#ifdef CONFIG_64BIT
-#  define REG_SZ 8
-#else
-#  define REG_SZ 4
-#endif
-
 #define N_SAVED_REGS 9
 
 save_cr_space:
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index 4309ad31a874..318815212518 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -172,7 +172,7 @@ static void do_show_stack(struct unwind_frame_info *info)
 	int i = 1;
 
 	printk(KERN_CRIT "Backtrace:\n");
-	while (i <= 16) {
+	while (i <= MAX_UNWIND_ENTRIES) {
 		if (unwind_once(info) < 0 || info->ip == 0)
 			break;
 
diff --git a/arch/parisc/kernel/unwind.c b/arch/parisc/kernel/unwind.c
index a4b430f440a9..5cdf13069dd9 100644
--- a/arch/parisc/kernel/unwind.c
+++ b/arch/parisc/kernel/unwind.c
@@ -13,7 +13,6 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/slab.h>
-#include <linux/kallsyms.h>
 #include <linux/sort.h>
 
 #include <linux/uaccess.h>
@@ -117,7 +116,8 @@ unwind_table_init(struct unwind_table *table, const char *name,
 	for (; start <= end; start++) {
 		if (start < end && 
 		    start->region_end > (start+1)->region_start) {
-			printk("WARNING: Out of order unwind entry! %p and %p\n", start, start+1);
+			pr_warn("Out of order unwind entry! %px and %px\n",
+				start, start+1);
 		}
 
 		start->region_start += base_addr;
@@ -203,25 +203,60 @@ int __init unwind_init(void)
 	return 0;
 }
 
-#ifdef CONFIG_64BIT
-#define get_func_addr(fptr) fptr[2]
-#else
-#define get_func_addr(fptr) fptr[0]
-#endif
-
 static int unwind_special(struct unwind_frame_info *info, unsigned long pc, int frame_size)
 {
-	extern void handle_interruption(int, struct pt_regs *);
-	static unsigned long *hi = (unsigned long *)&handle_interruption;
-
-	if (pc == get_func_addr(hi)) {
+	/*
+	 * We have to use void * instead of a function pointer, because
+	 * function pointers aren't a pointer to the function on 64-bit.
+	 * Make them const so the compiler knows they live in .text
+	 */
+	extern void * const handle_interruption;
+	extern void * const ret_from_kernel_thread;
+	extern void * const syscall_exit;
+	extern void * const intr_return;
+	extern void * const _switch_to_ret;
+#ifdef CONFIG_IRQSTACKS
+	extern void * const call_on_stack;
+#endif /* CONFIG_IRQSTACKS */
+
+	if (pc == (unsigned long) &handle_interruption) {
 		struct pt_regs *regs = (struct pt_regs *)(info->sp - frame_size - PT_SZ_ALGN);
 		dbg("Unwinding through handle_interruption()\n");
 		info->prev_sp = regs->gr[30];
 		info->prev_ip = regs->iaoq[0];
+		return 1;
+	}
+
+	if (pc == (unsigned long) &ret_from_kernel_thread ||
+	    pc == (unsigned long) &syscall_exit) {
+		info->prev_sp = info->prev_ip = 0;
+		return 1;
+	}
+
+	if (pc == (unsigned long) &intr_return) {
+		struct pt_regs *regs;
+
+		dbg("Found intr_return()\n");
+		regs = (struct pt_regs *)(info->sp - PT_SZ_ALGN);
+		info->prev_sp = regs->gr[30];
+		info->prev_ip = regs->iaoq[0];
+		info->rp = regs->gr[2];
+		return 1;
+	}
+
+	if (pc == (unsigned long) &_switch_to_ret) {
+		info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
+		info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
+		return 1;
+	}
 
+#ifdef CONFIG_IRQSTACKS
+	if (pc == (unsigned long) &call_on_stack) {
+		info->prev_sp = *(unsigned long *)(info->sp - FRAME_SIZE - REG_SZ);
+		info->prev_ip = *(unsigned long *)(info->sp - FRAME_SIZE - RP_OFFSET);
 		return 1;
 	}
+#endif
 
 	return 0;
 }
@@ -238,34 +273,8 @@ static void unwind_frame_regs(struct unwind_frame_info *info)
 	if (e == NULL) {
 		unsigned long sp;
 
-		dbg("Cannot find unwind entry for 0x%lx; forced unwinding\n", info->ip);
-
-#ifdef CONFIG_KALLSYMS
-		/* Handle some frequent special cases.... */
-		{
-			char symname[KSYM_NAME_LEN];
-			char *modname;
-
-			kallsyms_lookup(info->ip, NULL, NULL, &modname,
-				symname);
-
-			dbg("info->ip = 0x%lx, name = %s\n", info->ip, symname);
-
-			if (strcmp(symname, "_switch_to_ret") == 0) {
-				info->prev_sp = info->sp - CALLEE_SAVE_FRAME_SIZE;
-				info->prev_ip = *(unsigned long *)(info->prev_sp - RP_OFFSET);
-				dbg("_switch_to_ret @ %lx - setting "
-				    "prev_sp=%lx prev_ip=%lx\n", 
-				    info->ip, info->prev_sp, 
-				    info->prev_ip);
-				return;
-			} else if (strcmp(symname, "ret_from_kernel_thread") == 0 ||
-				   strcmp(symname, "syscall_exit") == 0) {
-				info->prev_ip = info->prev_sp = 0;
-				return;
-			}
-		}
-#endif
+		dbg("Cannot find unwind entry for %pS; forced unwinding\n",
+			(void *) info->ip);
 
 		/* Since we are doing the unwinding blind, we don't know if
 		   we are adjusting the stack correctly or extracting the rp
diff --git a/arch/parisc/lib/lusercopy.S b/arch/parisc/lib/lusercopy.S
index d4fe19806d57..b53fb6fedf06 100644
--- a/arch/parisc/lib/lusercopy.S
+++ b/arch/parisc/lib/lusercopy.S
@@ -64,9 +64,6 @@
 	 */
 
 ENTRY_CFI(lclear_user)
-	.proc
-	.callinfo NO_CALLS
-	.entry
 	comib,=,n   0,%r25,$lclu_done
 	get_sr
 $lclu_loop:
@@ -81,13 +78,9 @@ $lclu_done:
 	ldo         1(%r25),%r25
 
 	ASM_EXCEPTIONTABLE_ENTRY(1b,2b)
-
-	.exit
 ENDPROC_CFI(lclear_user)
 
 
-	.procend
-
 	/*
 	 * long lstrnlen_user(char *s, long n)
 	 *
@@ -97,9 +90,6 @@ ENDPROC_CFI(lclear_user)
 	 */
 
 ENTRY_CFI(lstrnlen_user)
-	.proc
-	.callinfo NO_CALLS
-	.entry
 	comib,=     0,%r25,$lslen_nzero
 	copy	    %r26,%r24
 	get_sr
@@ -111,7 +101,6 @@ $lslen_loop:
 $lslen_done:
 	bv          %r0(%r2)
 	sub	    %r26,%r24,%r28
-	.exit
 
 $lslen_nzero:
 	b           $lslen_done
@@ -125,9 +114,6 @@ $lslen_nzero:
 
 ENDPROC_CFI(lstrnlen_user)
 
-	.procend
-
-
 
 /*
  * unsigned long pa_memcpy(void *dstp, const void *srcp, unsigned long len)
@@ -186,10 +172,6 @@ ENDPROC_CFI(lstrnlen_user)
 	save_len = r31
 
 ENTRY_CFI(pa_memcpy)
-	.proc
-	.callinfo NO_CALLS
-	.entry
-
 	/* Last destination address */
 	add	dst,len,end
 
@@ -439,9 +421,6 @@ ENTRY_CFI(pa_memcpy)
 	b	.Lcopy_done
 10:	stw,ma	t1,4(dstspc,dst)
 	ASM_EXCEPTIONTABLE_ENTRY(10b,.Lcopy_done)
-
-	.exit
 ENDPROC_CFI(pa_memcpy)
-	.procend
 
 	.end
-- 
cgit v1.2.3


From 330ad75f6a79d46f11f7bf8937852ebb4673b1d5 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Mon, 13 Aug 2018 12:32:35 +0300
Subject: Bluetooth: mediatek: pass correct size to h4_recv_buf()

We're supposed to pass the number of elements in the mtk_recv_pkts, not
the number of bytes.

Fixes: 7237c4c9ec92 ("Bluetooth: mediatek: Add protocol support for MediaTek serial devices")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Marcel Holtmann <marcel@holtmann.org>
---
 drivers/bluetooth/btmtkuart.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btmtkuart.c b/drivers/bluetooth/btmtkuart.c
index e0571fe04d00..ed2a5c7cb77f 100644
--- a/drivers/bluetooth/btmtkuart.c
+++ b/drivers/bluetooth/btmtkuart.c
@@ -346,7 +346,7 @@ static int btmtkuart_recv(struct hci_dev *hdev, const u8 *data, size_t count)
 
 		bdev->rx_skb = h4_recv_buf(bdev->hdev, bdev->rx_skb, p_h4,
 					   sz_h4, mtk_recv_pkts,
-					   sizeof(mtk_recv_pkts));
+					   ARRAY_SIZE(mtk_recv_pkts));
 		if (IS_ERR(bdev->rx_skb)) {
 			err = PTR_ERR(bdev->rx_skb);
 			bt_dev_err(bdev->hdev,
-- 
cgit v1.2.3


From f11b9abc9318d5506f08156b4950c24e3cba73e5 Mon Sep 17 00:00:00 2001
From: Harish Jenny K N <harish_kandiga@mentor.com>
Date: Thu, 19 Jul 2018 17:24:04 +0530
Subject: Documentation: remove dynamic-resolution-notes reference to
 non-existent file

File dt-object-internal.txt does not exist. This patch removes
a reference to it.

Signed-off-by: Harish Jenny K N <harish_kandiga@mentor.com>
Reviewed-by: Frank Rowand <frank.rowand@sony.com>
Signed-off-by: Rob Herring <robh@kernel.org>
---
 Documentation/devicetree/dynamic-resolution-notes.txt | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/dynamic-resolution-notes.txt b/Documentation/devicetree/dynamic-resolution-notes.txt
index 083d23262abe..c24ec366c5dc 100644
--- a/Documentation/devicetree/dynamic-resolution-notes.txt
+++ b/Documentation/devicetree/dynamic-resolution-notes.txt
@@ -2,15 +2,14 @@ Device Tree Dynamic Resolver Notes
 ----------------------------------
 
 This document describes the implementation of the in-kernel
-Device Tree resolver, residing in drivers/of/resolver.c and is a
-companion document to Documentation/devicetree/dt-object-internal.txt[1]
+Device Tree resolver, residing in drivers/of/resolver.c
 
 How the resolver works
 ----------------------
 
 The resolver is given as an input an arbitrary tree compiled with the
 proper dtc option and having a /plugin/ tag. This generates the
-appropriate __fixups__ & __local_fixups__ nodes as described in [1].
+appropriate __fixups__ & __local_fixups__ nodes.
 
 In sequence the resolver works by the following steps:
 
-- 
cgit v1.2.3


From 53ccb22b8d4a9293cf4249f3b526892810038fd3 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Date: Thu, 28 Jun 2018 15:42:20 +0100
Subject: ARM: 8778/1: clkdev: don't call __of_clk_get_by_name() unnecessarily
 from clk_get()

The way this function is implemented caused some confusion when
converting the TI DaVinci platform to using the common clock framework.

Current kernel supports booting DaVinci boards both in device tree as
well as legacy, board-file mode. In the latter, we always end up
calling clk_get_sys() as of_node is NULL and __of_clk_get_by_name()
returns -ENOENT.

It was not obvious at first glance how clk_get(dev, NULL) will work in
board-file mode since we always call __of_clk_get_by_name(). Let's make
it clearer by checking if of_node is NULL and skipping right to
clk_get_sys().

Cc: Sekhar Nori <nsekhar@ti.com>
Cc: Kevin Hilman <khilman@baylibre.com>
Cc: David Lechner <david@lechnology.com>
Reviewed-by: David Lechner <david@lechnology.com>
Reviewed-by: Sekhar Nori <nsekhar@ti.com>
Signed-off-by: Bartosz Golaszewski <bgolaszewski@baylibre.com>
Signed-off-by: Russell King <rmk+kernel@armlinux.org.uk>
---
 drivers/clk/clkdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/clk/clkdev.c b/drivers/clk/clkdev.c
index 02fcee2012e0..9ab3db8b3988 100644
--- a/drivers/clk/clkdev.c
+++ b/drivers/clk/clkdev.c
@@ -196,7 +196,7 @@ struct clk *clk_get(struct device *dev, const char *con_id)
 	const char *dev_id = dev ? dev_name(dev) : NULL;
 	struct clk *clk;
 
-	if (dev) {
+	if (dev && dev->of_node) {
 		clk = __of_clk_get_by_name(dev->of_node, dev_id, con_id);
 		if (!IS_ERR(clk) || PTR_ERR(clk) == -EPROBE_DEFER)
 			return clk;
-- 
cgit v1.2.3


From 0b243d004ea640875115d1500ec429a3e9f9fae9 Mon Sep 17 00:00:00 2001
From: Vakul Garg <vakul.garg@nxp.com>
Date: Fri, 10 Aug 2018 20:46:41 +0530
Subject: net/tls: Combined memory allocation for decryption request

For preparing decryption request, several memory chunks are required
(aead_req, sgin, sgout, iv, aad). For submitting the decrypt request to
an accelerator, it is required that the buffers which are read by the
accelerator must be dma-able and not come from stack. The buffers for
aad and iv can be separately kmalloced each, but it is inefficient.
This patch does a combined allocation for preparing decryption request
and then segments into aead_req || sgin || sgout || iv || aad.

Signed-off-by: Vakul Garg <vakul.garg@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tls.h |   4 -
 net/tls/tls_sw.c  | 238 ++++++++++++++++++++++++++++++++----------------------
 2 files changed, 142 insertions(+), 100 deletions(-)

diff --git a/include/net/tls.h b/include/net/tls.h
index d8b3b6578c01..d5c683e8bb22 100644
--- a/include/net/tls.h
+++ b/include/net/tls.h
@@ -124,10 +124,6 @@ struct tls_sw_context_rx {
 	struct sk_buff *recv_pkt;
 	u8 control;
 	bool decrypted;
-
-	char rx_aad_ciphertext[TLS_AAD_SPACE_SIZE];
-	char rx_aad_plaintext[TLS_AAD_SPACE_SIZE];
-
 };
 
 struct tls_record_info {
diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index 83d67df33f0c..52fbe727d7c1 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -48,19 +48,13 @@ static int tls_do_decryption(struct sock *sk,
 			     struct scatterlist *sgout,
 			     char *iv_recv,
 			     size_t data_len,
-			     struct sk_buff *skb,
-			     gfp_t flags)
+			     struct aead_request *aead_req)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
-	struct aead_request *aead_req;
-
 	int ret;
 
-	aead_req = aead_request_alloc(ctx->aead_recv, flags);
-	if (!aead_req)
-		return -ENOMEM;
-
+	aead_request_set_tfm(aead_req, ctx->aead_recv);
 	aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE);
 	aead_request_set_crypt(aead_req, sgin, sgout,
 			       data_len + tls_ctx->rx.tag_size,
@@ -69,8 +63,6 @@ static int tls_do_decryption(struct sock *sk,
 				  crypto_req_done, &ctx->async_wait);
 
 	ret = crypto_wait_req(crypto_aead_decrypt(aead_req), &ctx->async_wait);
-
-	aead_request_free(aead_req);
 	return ret;
 }
 
@@ -657,8 +649,132 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags,
 	return skb;
 }
 
+/* This function decrypts the input skb into either out_iov or in out_sg
+ * or in skb buffers itself. The input parameter 'zc' indicates if
+ * zero-copy mode needs to be tried or not. With zero-copy mode, either
+ * out_iov or out_sg must be non-NULL. In case both out_iov and out_sg are
+ * NULL, then the decryption happens inside skb buffers itself, i.e.
+ * zero-copy gets disabled and 'zc' is updated.
+ */
+
+static int decrypt_internal(struct sock *sk, struct sk_buff *skb,
+			    struct iov_iter *out_iov,
+			    struct scatterlist *out_sg,
+			    int *chunk, bool *zc)
+{
+	struct tls_context *tls_ctx = tls_get_ctx(sk);
+	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
+	struct strp_msg *rxm = strp_msg(skb);
+	int n_sgin, n_sgout, nsg, mem_size, aead_size, err, pages = 0;
+	struct aead_request *aead_req;
+	struct sk_buff *unused;
+	u8 *aad, *iv, *mem = NULL;
+	struct scatterlist *sgin = NULL;
+	struct scatterlist *sgout = NULL;
+	const int data_len = rxm->full_len - tls_ctx->rx.overhead_size;
+
+	if (*zc && (out_iov || out_sg)) {
+		if (out_iov)
+			n_sgout = iov_iter_npages(out_iov, INT_MAX) + 1;
+		else
+			n_sgout = sg_nents(out_sg);
+	} else {
+		n_sgout = 0;
+		*zc = false;
+	}
+
+	n_sgin = skb_cow_data(skb, 0, &unused);
+	if (n_sgin < 1)
+		return -EBADMSG;
+
+	/* Increment to accommodate AAD */
+	n_sgin = n_sgin + 1;
+
+	nsg = n_sgin + n_sgout;
+
+	aead_size = sizeof(*aead_req) + crypto_aead_reqsize(ctx->aead_recv);
+	mem_size = aead_size + (nsg * sizeof(struct scatterlist));
+	mem_size = mem_size + TLS_AAD_SPACE_SIZE;
+	mem_size = mem_size + crypto_aead_ivsize(ctx->aead_recv);
+
+	/* Allocate a single block of memory which contains
+	 * aead_req || sgin[] || sgout[] || aad || iv.
+	 * This order achieves correct alignment for aead_req, sgin, sgout.
+	 */
+	mem = kmalloc(mem_size, sk->sk_allocation);
+	if (!mem)
+		return -ENOMEM;
+
+	/* Segment the allocated memory */
+	aead_req = (struct aead_request *)mem;
+	sgin = (struct scatterlist *)(mem + aead_size);
+	sgout = sgin + n_sgin;
+	aad = (u8 *)(sgout + n_sgout);
+	iv = aad + TLS_AAD_SPACE_SIZE;
+
+	/* Prepare IV */
+	err = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
+			    iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
+			    tls_ctx->rx.iv_size);
+	if (err < 0) {
+		kfree(mem);
+		return err;
+	}
+	memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
+
+	/* Prepare AAD */
+	tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size,
+		     tls_ctx->rx.rec_seq, tls_ctx->rx.rec_seq_size,
+		     ctx->control);
+
+	/* Prepare sgin */
+	sg_init_table(sgin, n_sgin);
+	sg_set_buf(&sgin[0], aad, TLS_AAD_SPACE_SIZE);
+	err = skb_to_sgvec(skb, &sgin[1],
+			   rxm->offset + tls_ctx->rx.prepend_size,
+			   rxm->full_len - tls_ctx->rx.prepend_size);
+	if (err < 0) {
+		kfree(mem);
+		return err;
+	}
+
+	if (n_sgout) {
+		if (out_iov) {
+			sg_init_table(sgout, n_sgout);
+			sg_set_buf(&sgout[0], aad, TLS_AAD_SPACE_SIZE);
+
+			*chunk = 0;
+			err = zerocopy_from_iter(sk, out_iov, data_len, &pages,
+						 chunk, &sgout[1],
+						 (n_sgout - 1), false);
+			if (err < 0)
+				goto fallback_to_reg_recv;
+		} else if (out_sg) {
+			memcpy(sgout, out_sg, n_sgout * sizeof(*sgout));
+		} else {
+			goto fallback_to_reg_recv;
+		}
+	} else {
+fallback_to_reg_recv:
+		sgout = sgin;
+		pages = 0;
+		*chunk = 0;
+		*zc = false;
+	}
+
+	/* Prepare and submit AEAD request */
+	err = tls_do_decryption(sk, sgin, sgout, iv, data_len, aead_req);
+
+	/* Release the pages in case iov was mapped to pages */
+	for (; pages > 0; pages--)
+		put_page(sg_page(&sgout[pages]));
+
+	kfree(mem);
+	return err;
+}
+
 static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
-			      struct scatterlist *sgout, bool *zc)
+			      struct iov_iter *dest, int *chunk, bool *zc)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
@@ -671,7 +787,7 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
 		return err;
 #endif
 	if (!ctx->decrypted) {
-		err = decrypt_skb(sk, skb, sgout);
+		err = decrypt_internal(sk, skb, dest, NULL, chunk, zc);
 		if (err < 0)
 			return err;
 	} else {
@@ -690,54 +806,10 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb,
 int decrypt_skb(struct sock *sk, struct sk_buff *skb,
 		struct scatterlist *sgout)
 {
-	struct tls_context *tls_ctx = tls_get_ctx(sk);
-	struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx);
-	char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE];
-	struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2];
-	struct scatterlist *sgin = &sgin_arr[0];
-	struct strp_msg *rxm = strp_msg(skb);
-	int ret, nsg = ARRAY_SIZE(sgin_arr);
-	struct sk_buff *unused;
-
-	ret = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE,
-			    iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
-			    tls_ctx->rx.iv_size);
-	if (ret < 0)
-		return ret;
-
-	memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE);
-	if (!sgout) {
-		nsg = skb_cow_data(skb, 0, &unused) + 1;
-		sgin = kmalloc_array(nsg, sizeof(*sgin), sk->sk_allocation);
-		sgout = sgin;
-	}
-
-	sg_init_table(sgin, nsg);
-	sg_set_buf(&sgin[0], ctx->rx_aad_ciphertext, TLS_AAD_SPACE_SIZE);
-
-	nsg = skb_to_sgvec(skb, &sgin[1],
-			   rxm->offset + tls_ctx->rx.prepend_size,
-			   rxm->full_len - tls_ctx->rx.prepend_size);
-	if (nsg < 0) {
-		ret = nsg;
-		goto out;
-	}
-
-	tls_make_aad(ctx->rx_aad_ciphertext,
-		     rxm->full_len - tls_ctx->rx.overhead_size,
-		     tls_ctx->rx.rec_seq,
-		     tls_ctx->rx.rec_seq_size,
-		     ctx->control);
-
-	ret = tls_do_decryption(sk, sgin, sgout, iv,
-				rxm->full_len - tls_ctx->rx.overhead_size,
-				skb, sk->sk_allocation);
-
-out:
-	if (sgin != &sgin_arr[0])
-		kfree(sgin);
+	bool zc = true;
+	int chunk;
 
-	return ret;
+	return decrypt_internal(sk, skb, NULL, sgout, &chunk, &zc);
 }
 
 static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb,
@@ -816,43 +888,17 @@ int tls_sw_recvmsg(struct sock *sk,
 		}
 
 		if (!ctx->decrypted) {
-			int page_count;
-			int to_copy;
-
-			page_count = iov_iter_npages(&msg->msg_iter,
-						     MAX_SKB_FRAGS);
-			to_copy = rxm->full_len - tls_ctx->rx.overhead_size;
-			if (!is_kvec && to_copy <= len && page_count < MAX_SKB_FRAGS &&
-			    likely(!(flags & MSG_PEEK)))  {
-				struct scatterlist sgin[MAX_SKB_FRAGS + 1];
-				int pages = 0;
+			int to_copy = rxm->full_len - tls_ctx->rx.overhead_size;
 
+			if (!is_kvec && to_copy <= len &&
+			    likely(!(flags & MSG_PEEK)))
 				zc = true;
-				sg_init_table(sgin, MAX_SKB_FRAGS + 1);
-				sg_set_buf(&sgin[0], ctx->rx_aad_plaintext,
-					   TLS_AAD_SPACE_SIZE);
-
-				err = zerocopy_from_iter(sk, &msg->msg_iter,
-							 to_copy, &pages,
-							 &chunk, &sgin[1],
-							 MAX_SKB_FRAGS,	false);
-				if (err < 0)
-					goto fallback_to_reg_recv;
-
-				err = decrypt_skb_update(sk, skb, sgin, &zc);
-				for (; pages > 0; pages--)
-					put_page(sg_page(&sgin[pages]));
-				if (err < 0) {
-					tls_err_abort(sk, EBADMSG);
-					goto recv_end;
-				}
-			} else {
-fallback_to_reg_recv:
-				err = decrypt_skb_update(sk, skb, NULL, &zc);
-				if (err < 0) {
-					tls_err_abort(sk, EBADMSG);
-					goto recv_end;
-				}
+
+			err = decrypt_skb_update(sk, skb, &msg->msg_iter,
+						 &chunk, &zc);
+			if (err < 0) {
+				tls_err_abort(sk, EBADMSG);
+				goto recv_end;
 			}
 			ctx->decrypted = true;
 		}
@@ -903,7 +949,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	int err = 0;
 	long timeo;
 	int chunk;
-	bool zc;
+	bool zc = false;
 
 	lock_sock(sk);
 
@@ -920,7 +966,7 @@ ssize_t tls_sw_splice_read(struct socket *sock,  loff_t *ppos,
 	}
 
 	if (!ctx->decrypted) {
-		err = decrypt_skb_update(sk, skb, NULL, &zc);
+		err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc);
 
 		if (err < 0) {
 			tls_err_abort(sk, EBADMSG);
-- 
cgit v1.2.3


From e6f86b0f7ae473969a3301b74bf98af9e42ecd0e Mon Sep 17 00:00:00 2001
From: Virgile Jarry <virgile@acceis.fr>
Date: Fri, 10 Aug 2018 17:48:15 +0200
Subject: ipv6: Add icmp_echo_ignore_all support for ICMPv6

Preventing the kernel from responding to ICMP Echo Requests messages
can be useful in several ways. The sysctl parameter
'icmp_echo_ignore_all' can be used to prevent the kernel from
responding to IPv4 ICMP echo requests. For IPv6 pings, such
a sysctl kernel parameter did not exist.

Add the ability to prevent the kernel from responding to IPv6
ICMP echo requests through the use of the following sysctl
parameter : /proc/sys/net/ipv6/icmp/echo_ignore_all.
Update the documentation to reflect this change.

Signed-off-by: Virgile Jarry <virgile@acceis.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/ip-sysctl.txt |  5 +++++
 include/net/netns/ipv6.h               |  1 +
 include/uapi/linux/sysctl.h            |  3 ++-
 net/ipv6/af_inet6.c                    |  1 +
 net/ipv6/icmp.c                        | 16 +++++++++++++---
 5 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e74515ecaa9c..8313a636dd53 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -1882,6 +1882,11 @@ ratelimit - INTEGER
 	otherwise the minimal space between responses in milliseconds.
 	Default: 1000
 
+echo_ignore_all - BOOLEAN
+	If set non-zero, then the kernel will ignore all ICMP ECHO
+	requests sent to it over the IPv6 protocol.
+	Default: 0
+
 xfrm6_gc_thresh - INTEGER
 	The threshold at which we will start garbage collecting for IPv6
 	destination cache entries.  At twice this value the system will
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 762ac9931b62..f0e396ab9bec 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -32,6 +32,7 @@ struct netns_sysctl_ipv6 {
 	int flowlabel_consistency;
 	int auto_flowlabels;
 	int icmpv6_time;
+	int icmpv6_echo_ignore_all;
 	int anycast_src_echo_reply;
 	int ip_nonlocal_bind;
 	int fwmark_reflect;
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 6b58371b1f0d..d71013fffaf6 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -575,7 +575,8 @@ enum {
 
 /* /proc/sys/net/ipv6/icmp */
 enum {
-	NET_IPV6_ICMP_RATELIMIT=1
+	NET_IPV6_ICMP_RATELIMIT = 1,
+	NET_IPV6_ICMP_ECHO_IGNORE_ALL = 2
 };
 
 /* /proc/sys/net/<protocol>/neigh/<dev> */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 020f6e14a7af..673bba31eb18 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -832,6 +832,7 @@ static int __net_init inet6_net_init(struct net *net)
 
 	net->ipv6.sysctl.bindv6only = 0;
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
+	net->ipv6.sysctl.icmpv6_echo_ignore_all = 0;
 	net->ipv6.sysctl.flowlabel_consistency = 1;
 	net->ipv6.sysctl.auto_flowlabels = IP6_DEFAULT_AUTO_FLOW_LABELS;
 	net->ipv6.sysctl.idgen_retries = 3;
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 7f6b1f81c200..c9c53ade55c3 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -794,6 +794,7 @@ out:
 
 static int icmpv6_rcv(struct sk_buff *skb)
 {
+	struct net *net = dev_net(skb->dev);
 	struct net_device *dev = skb->dev;
 	struct inet6_dev *idev = __in6_dev_get(dev);
 	const struct in6_addr *saddr, *daddr;
@@ -843,7 +844,8 @@ static int icmpv6_rcv(struct sk_buff *skb)
 
 	switch (type) {
 	case ICMPV6_ECHO_REQUEST:
-		icmpv6_echo_reply(skb);
+		if (!net->ipv6.sysctl.icmpv6_echo_ignore_all)
+			icmpv6_echo_reply(skb);
 		break;
 
 	case ICMPV6_ECHO_REPLY:
@@ -1104,6 +1106,13 @@ static struct ctl_table ipv6_icmp_table_template[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_ms_jiffies,
 	},
+	{
+		.procname	= "echo_ignore_all",
+		.data		= &init_net.ipv6.sysctl.icmpv6_echo_ignore_all,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler = proc_dointvec,
+	},
 	{ },
 };
 
@@ -1115,9 +1124,10 @@ struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
 			sizeof(ipv6_icmp_table_template),
 			GFP_KERNEL);
 
-	if (table)
+	if (table) {
 		table[0].data = &net->ipv6.sysctl.icmpv6_time;
-
+		table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
+	}
 	return table;
 }
 #endif
-- 
cgit v1.2.3


From 6d37fa49da1e8db8fb1995be22ac837ca41ac8a8 Mon Sep 17 00:00:00 2001
From: Wei Wang <weiwan@google.com>
Date: Fri, 10 Aug 2018 11:14:56 -0700
Subject: l2tp: use sk_dst_check() to avoid race on sk->sk_dst_cache

In l2tp code, if it is a L2TP_UDP_ENCAP tunnel, tunnel->sk points to a
UDP socket. User could call sendmsg() on both this tunnel and the UDP
socket itself concurrently. As l2tp_xmit_skb() holds socket lock and call
__sk_dst_check() to refresh sk->sk_dst_cache, while udpv6_sendmsg() is
lockless and call sk_dst_check() to refresh sk->sk_dst_cache, there
could be a race and cause the dst cache to be freed multiple times.
So we fix l2tp side code to always call sk_dst_check() to garantee
xchg() is called when refreshing sk->sk_dst_cache to avoid race
conditions.

Syzkaller reported stack trace:
BUG: KASAN: use-after-free in atomic_read include/asm-generic/atomic-instrumented.h:21 [inline]
BUG: KASAN: use-after-free in atomic_fetch_add_unless include/linux/atomic.h:575 [inline]
BUG: KASAN: use-after-free in atomic_add_unless include/linux/atomic.h:597 [inline]
BUG: KASAN: use-after-free in dst_hold_safe include/net/dst.h:308 [inline]
BUG: KASAN: use-after-free in ip6_hold_safe+0xe6/0x670 net/ipv6/route.c:1029
Read of size 4 at addr ffff8801aea9a880 by task syz-executor129/4829

CPU: 0 PID: 4829 Comm: syz-executor129 Not tainted 4.18.0-rc7-next-20180802+ #30
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Call Trace:
 __dump_stack lib/dump_stack.c:77 [inline]
 dump_stack+0x1c9/0x2b4 lib/dump_stack.c:113
 print_address_description+0x6c/0x20b mm/kasan/report.c:256
 kasan_report_error mm/kasan/report.c:354 [inline]
 kasan_report.cold.7+0x242/0x30d mm/kasan/report.c:412
 check_memory_region_inline mm/kasan/kasan.c:260 [inline]
 check_memory_region+0x13e/0x1b0 mm/kasan/kasan.c:267
 kasan_check_read+0x11/0x20 mm/kasan/kasan.c:272
 atomic_read include/asm-generic/atomic-instrumented.h:21 [inline]
 atomic_fetch_add_unless include/linux/atomic.h:575 [inline]
 atomic_add_unless include/linux/atomic.h:597 [inline]
 dst_hold_safe include/net/dst.h:308 [inline]
 ip6_hold_safe+0xe6/0x670 net/ipv6/route.c:1029
 rt6_get_pcpu_route net/ipv6/route.c:1249 [inline]
 ip6_pol_route+0x354/0xd20 net/ipv6/route.c:1922
 ip6_pol_route_output+0x54/0x70 net/ipv6/route.c:2098
 fib6_rule_lookup+0x283/0x890 net/ipv6/fib6_rules.c:122
 ip6_route_output_flags+0x2c5/0x350 net/ipv6/route.c:2126
 ip6_dst_lookup_tail+0x1278/0x1da0 net/ipv6/ip6_output.c:978
 ip6_dst_lookup_flow+0xc8/0x270 net/ipv6/ip6_output.c:1079
 ip6_sk_dst_lookup_flow+0x5ed/0xc50 net/ipv6/ip6_output.c:1117
 udpv6_sendmsg+0x2163/0x36b0 net/ipv6/udp.c:1354
 inet_sendmsg+0x1a1/0x690 net/ipv4/af_inet.c:798
 sock_sendmsg_nosec net/socket.c:622 [inline]
 sock_sendmsg+0xd5/0x120 net/socket.c:632
 ___sys_sendmsg+0x51d/0x930 net/socket.c:2115
 __sys_sendmmsg+0x240/0x6f0 net/socket.c:2210
 __do_sys_sendmmsg net/socket.c:2239 [inline]
 __se_sys_sendmmsg net/socket.c:2236 [inline]
 __x64_sys_sendmmsg+0x9d/0x100 net/socket.c:2236
 do_syscall_64+0x1b9/0x820 arch/x86/entry/common.c:290
 entry_SYSCALL_64_after_hwframe+0x49/0xbe
RIP: 0033:0x446a29
Code: e8 ac b8 02 00 48 83 c4 18 c3 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 eb 08 fc ff c3 66 2e 0f 1f 84 00 00 00 00
RSP: 002b:00007f4de5532db8 EFLAGS: 00000246 ORIG_RAX: 0000000000000133
RAX: ffffffffffffffda RBX: 00000000006dcc38 RCX: 0000000000446a29
RDX: 00000000000000b8 RSI: 0000000020001b00 RDI: 0000000000000003
RBP: 00000000006dcc30 R08: 00007f4de5533700 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 00000000006dcc3c
R13: 00007ffe2b830fdf R14: 00007f4de55339c0 R15: 0000000000000001

Fixes: 71b1391a4128 ("l2tp: ensure sk->dst is still valid")
Reported-by: syzbot+05f840f3b04f211bad55@syzkaller.appspotmail.com
Signed-off-by: Wei Wang <weiwan@google.com>
Signed-off-by: Martin KaFai Lau <kafai@fb.com>
Cc: Guillaume Nault <g.nault@alphalink.fr>
Cc: David Ahern <dsahern@gmail.com>
Cc: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 2bd701a58aa6..82cdf9020b53 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1098,7 +1098,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
 
 	/* Get routing info from the tunnel socket */
 	skb_dst_drop(skb);
-	skb_dst_set(skb, dst_clone(__sk_dst_check(sk, 0)));
+	skb_dst_set(skb, sk_dst_check(sk, 0));
 
 	inet = inet_sk(sk);
 	fl = &inet->cork.fl;
-- 
cgit v1.2.3


From e158770e22892f8f8e11810267e2a100d25d22c7 Mon Sep 17 00:00:00 2001
From: Moritz Fischer <mdf@kernel.org>
Date: Fri, 10 Aug 2018 18:19:40 -0700
Subject: net: nixge: Do not zero application specific fields in desc

Do not zero application specific fields in DMA descriptors.
The hardware does ignore them, so should software.

Signed-off-by: Moritz Fischer <mdf@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ni/nixge.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index 9ae4fcef725e..ac31b0d30415 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -739,22 +739,12 @@ static void nixge_dma_err_handler(unsigned long data)
 		cur_p->phys = 0;
 		cur_p->cntrl = 0;
 		cur_p->status = 0;
-		cur_p->app0 = 0;
-		cur_p->app1 = 0;
-		cur_p->app2 = 0;
-		cur_p->app3 = 0;
-		cur_p->app4 = 0;
 		cur_p->sw_id_offset = 0;
 	}
 
 	for (i = 0; i < RX_BD_NUM; i++) {
 		cur_p = &lp->rx_bd_v[i];
 		cur_p->status = 0;
-		cur_p->app0 = 0;
-		cur_p->app1 = 0;
-		cur_p->app2 = 0;
-		cur_p->app3 = 0;
-		cur_p->app4 = 0;
 	}
 
 	lp->tx_bd_ci = 0;
-- 
cgit v1.2.3


From fd5cf434a4b0b25fc6f76b90373302a26d541ac8 Mon Sep 17 00:00:00 2001
From: Moritz Fischer <mdf@kernel.org>
Date: Fri, 10 Aug 2018 18:19:41 -0700
Subject: net: nixge: Don't store skb in app4 field of descriptor

Don't store skb in app4 field of descriptor since it is
not being used anywhere (including hardware).

Signed-off-by: Moritz Fischer <mdf@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ni/nixge.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/ni/nixge.c b/drivers/net/ethernet/ni/nixge.c
index ac31b0d30415..76efed058f33 100644
--- a/drivers/net/ethernet/ni/nixge.c
+++ b/drivers/net/ethernet/ni/nixge.c
@@ -503,7 +503,6 @@ static int nixge_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	tx_skb->skb = skb;
 
 	cur_p->cntrl |= XAXIDMA_BD_CTRL_TXEOF_MASK;
-	cur_p->app4 = (unsigned long)skb;
 
 	tail_p = priv->tx_bd_p + sizeof(*priv->tx_bd_v) * priv->tx_bd_tail;
 	/* Start the transfer */
-- 
cgit v1.2.3


From 7c53a722459c1d6ffb0f5b2058c06ca8980b8600 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 12 Aug 2018 13:26:26 +0200
Subject: r8169: don't use MSI-X on RTL8168g

There have been two reports that network doesn't come back on resume
from suspend when using MSI-X. Both cases affect the same chip version
(RTL8168g - version 40), on different systems. Falling back to MSI
fixes the issue.
Even though we don't really have a proof yet that the network chip
version is to blame, let's disable MSI-X for this version.

Reported-by: Steve Dodd <steved424@gmail.com>
Reported-by: Lou Reed <gogen@disroot.org>
Tested-by: Steve Dodd <steved424@gmail.com>
Tested-by: Lou Reed <gogen@disroot.org>
Fixes: 6c6aa15fdea5 ("r8169: improve interrupt handling")
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/realtek/r8169.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 14d185b10cda..0d9c3831838f 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -7076,6 +7076,11 @@ static int rtl_alloc_irq(struct rtl8169_private *tp)
 		RTL_W8(tp, Config2, RTL_R8(tp, Config2) & ~MSIEnable);
 		RTL_W8(tp, Cfg9346, Cfg9346_Lock);
 		flags = PCI_IRQ_LEGACY;
+	} else if (tp->mac_version == RTL_GIGA_MAC_VER_40) {
+		/* This version was reported to have issues with resume
+		 * from suspend when using MSI-X
+		 */
+		flags = PCI_IRQ_LEGACY | PCI_IRQ_MSI;
 	} else {
 		flags = PCI_IRQ_ALL_TYPES;
 	}
-- 
cgit v1.2.3


From 9af18e56d43ca4864ce65c3542c513827c2697de Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sun, 12 Aug 2018 09:14:03 -0400
Subject: cpumask: make cpumask_next_wrap available without smp

The kbuild robot shows build failure on machines without CONFIG_SMP:

  drivers/net/virtio_net.c:1916:10: error:
    implicit declaration of function 'cpumask_next_wrap'

cpumask_next_wrap is exported from lib/cpumask.o, which has

    lib-$(CONFIG_SMP) += cpumask.o

same as other functions, also define it as static inline in the
NR_CPUS==1 branch in include/linux/cpumask.h.

If wrap is true and next == start, return nr_cpumask_bits, or 1.
Else wrap across the range of valid cpus, here [0].

Fixes: 2ca653d607ce ("virtio_net: Stripe queue affinities across cores.")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Tested-by: Krzysztof Kozlowski <krzk@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/cpumask.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 57f20a0a7794..147bdec42215 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -159,6 +159,13 @@ static inline unsigned int cpumask_next_and(int n,
 	return n+1;
 }
 
+static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask,
+					     int start, bool wrap)
+{
+	/* cpu0 unless stop condition, wrap and at cpu0, then nr_cpumask_bits */
+	return (wrap && n == 0);
+}
+
 /* cpu must be a valid cpu, ie 0, so there's no other choice. */
 static inline unsigned int cpumask_any_but(const struct cpumask *mask,
 					   unsigned int cpu)
-- 
cgit v1.2.3


From 962ad1f937d86456e88d8cbcd93766746297f711 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:49 -0400
Subject: net: sched: act_connmark method rename for grep-ability and
 consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_connmark.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c
index 2f9bc833d046..54c0bf54f2ac 100644
--- a/net/sched/act_connmark.c
+++ b/net/sched/act_connmark.c
@@ -31,8 +31,8 @@
 static unsigned int connmark_net_id;
 static struct tc_action_ops act_connmark_ops;
 
-static int tcf_connmark(struct sk_buff *skb, const struct tc_action *a,
-			struct tcf_result *res)
+static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a,
+			    struct tcf_result *res)
 {
 	const struct nf_conntrack_tuple_hash *thash;
 	struct nf_conntrack_tuple tuple;
@@ -209,7 +209,7 @@ static struct tc_action_ops act_connmark_ops = {
 	.kind		=	"connmark",
 	.type		=	TCA_ACT_CONNMARK,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_connmark,
+	.act		=	tcf_connmark_act,
 	.dump		=	tcf_connmark_dump,
 	.init		=	tcf_connmark_init,
 	.walk		=	tcf_connmark_walker,
-- 
cgit v1.2.3


From 2fbec27f816bd95ebc468d17a784b20a72b95896 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:50 -0400
Subject: net: sched: act_bpf method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_bpf.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c
index 9e8a33f9fee3..9b30e62805c7 100644
--- a/net/sched/act_bpf.c
+++ b/net/sched/act_bpf.c
@@ -34,8 +34,8 @@ struct tcf_bpf_cfg {
 static unsigned int bpf_net_id;
 static struct tc_action_ops act_bpf_ops;
 
-static int tcf_bpf(struct sk_buff *skb, const struct tc_action *act,
-		   struct tcf_result *res)
+static int tcf_bpf_act(struct sk_buff *skb, const struct tc_action *act,
+		       struct tcf_result *res)
 {
 	bool at_ingress = skb_at_tc_ingress(skb);
 	struct tcf_bpf *prog = to_bpf(act);
@@ -406,7 +406,7 @@ static struct tc_action_ops act_bpf_ops __read_mostly = {
 	.kind		=	"bpf",
 	.type		=	TCA_ACT_BPF,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_bpf,
+	.act		=	tcf_bpf_act,
 	.dump		=	tcf_bpf_dump,
 	.cleanup	=	tcf_bpf_cleanup,
 	.init		=	tcf_bpf_init,
-- 
cgit v1.2.3


From c831549c3f53537e3b8a205c5d67cbc16c054f6a Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:51 -0400
Subject: net: sched: act_sum method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_csum.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c
index f01c59ba6d12..5596fae4e478 100644
--- a/net/sched/act_csum.c
+++ b/net/sched/act_csum.c
@@ -555,8 +555,8 @@ fail:
 	return 0;
 }
 
-static int tcf_csum(struct sk_buff *skb, const struct tc_action *a,
-		    struct tcf_result *res)
+static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a,
+			struct tcf_result *res)
 {
 	struct tcf_csum *p = to_tcf_csum(a);
 	struct tcf_csum_params *params;
@@ -670,7 +670,7 @@ static struct tc_action_ops act_csum_ops = {
 	.kind		= "csum",
 	.type		= TCA_ACT_CSUM,
 	.owner		= THIS_MODULE,
-	.act		= tcf_csum,
+	.act		= tcf_csum_act,
 	.dump		= tcf_csum_dump,
 	.init		= tcf_csum_init,
 	.cleanup	= tcf_csum_cleanup,
-- 
cgit v1.2.3


From 1740005e2a0cae1ba87e3efe2690755fe169837b Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:52 -0400
Subject: net: sched: act_gact method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_gact.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c
index bfccd34a3968..52a3e474d822 100644
--- a/net/sched/act_gact.c
+++ b/net/sched/act_gact.c
@@ -133,8 +133,8 @@ static int tcf_gact_init(struct net *net, struct nlattr *nla,
 	return ret;
 }
 
-static int tcf_gact(struct sk_buff *skb, const struct tc_action *a,
-		    struct tcf_result *res)
+static int tcf_gact_act(struct sk_buff *skb, const struct tc_action *a,
+			struct tcf_result *res)
 {
 	struct tcf_gact *gact = to_gact(a);
 	int action = READ_ONCE(gact->tcf_action);
@@ -254,7 +254,7 @@ static struct tc_action_ops act_gact_ops = {
 	.kind		=	"gact",
 	.type		=	TCA_ACT_GACT,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_gact,
+	.act		=	tcf_gact_act,
 	.stats_update	=	tcf_gact_stats_update,
 	.dump		=	tcf_gact_dump,
 	.init		=	tcf_gact_init,
-- 
cgit v1.2.3


From 11b9695b3ff06990333d77963607944574953c98 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:53 -0400
Subject: net: sched: act_ipt method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ipt.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c
index e149f0e66cb6..51f235bbeb5b 100644
--- a/net/sched/act_ipt.c
+++ b/net/sched/act_ipt.c
@@ -222,8 +222,8 @@ static int tcf_xt_init(struct net *net, struct nlattr *nla,
 			      bind);
 }
 
-static int tcf_ipt(struct sk_buff *skb, const struct tc_action *a,
-		   struct tcf_result *res)
+static int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a,
+		       struct tcf_result *res)
 {
 	int ret = 0, result = 0;
 	struct tcf_ipt *ipt = to_ipt(a);
@@ -348,7 +348,7 @@ static struct tc_action_ops act_ipt_ops = {
 	.kind		=	"ipt",
 	.type		=	TCA_ACT_IPT,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_ipt,
+	.act		=	tcf_ipt_act,
 	.dump		=	tcf_ipt_dump,
 	.cleanup	=	tcf_ipt_release,
 	.init		=	tcf_ipt_init,
@@ -406,7 +406,7 @@ static struct tc_action_ops act_xt_ops = {
 	.kind		=	"xt",
 	.type		=	TCA_ACT_XT,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_ipt,
+	.act		=	tcf_ipt_act,
 	.dump		=	tcf_ipt_dump,
 	.cleanup	=	tcf_ipt_release,
 	.init		=	tcf_xt_init,
-- 
cgit v1.2.3


From 0390514fe15501e9ddc4e87bdeed35fec9fc4802 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:54 -0400
Subject: net: sched: act_nat method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_nat.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c
index 4dd9188a72fd..822e903bfc25 100644
--- a/net/sched/act_nat.c
+++ b/net/sched/act_nat.c
@@ -93,8 +93,8 @@ static int tcf_nat_init(struct net *net, struct nlattr *nla, struct nlattr *est,
 	return ret;
 }
 
-static int tcf_nat(struct sk_buff *skb, const struct tc_action *a,
-		   struct tcf_result *res)
+static int tcf_nat_act(struct sk_buff *skb, const struct tc_action *a,
+		       struct tcf_result *res)
 {
 	struct tcf_nat *p = to_tcf_nat(a);
 	struct iphdr *iph;
@@ -311,7 +311,7 @@ static struct tc_action_ops act_nat_ops = {
 	.kind		=	"nat",
 	.type		=	TCA_ACT_NAT,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_nat,
+	.act		=	tcf_nat_act,
 	.dump		=	tcf_nat_dump,
 	.init		=	tcf_nat_init,
 	.walk		=	tcf_nat_walker,
-- 
cgit v1.2.3


From 6a2b401cd17d41944672563b2edf65cdef44c242 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:55 -0400
Subject: net: sched: act_pedit method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_pedit.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 3f62da72ab6a..8a7a7cb94e83 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -288,8 +288,8 @@ static int pedit_skb_hdr_offset(struct sk_buff *skb,
 	return ret;
 }
 
-static int tcf_pedit(struct sk_buff *skb, const struct tc_action *a,
-		     struct tcf_result *res)
+static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a,
+			 struct tcf_result *res)
 {
 	struct tcf_pedit *p = to_pedit(a);
 	int i;
@@ -471,7 +471,7 @@ static struct tc_action_ops act_pedit_ops = {
 	.kind		=	"pedit",
 	.type		=	TCA_ACT_PEDIT,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_pedit,
+	.act		=	tcf_pedit_act,
 	.dump		=	tcf_pedit_dump,
 	.cleanup	=	tcf_pedit_cleanup,
 	.init		=	tcf_pedit_init,
-- 
cgit v1.2.3


From 2ac063474dc738700eab3425d1f7c4ad98776bcd Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:56 -0400
Subject: net: sched: act_police method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_police.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 88c16d80c1cf..06f0742db593 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -56,7 +56,7 @@ struct tc_police_compat {
 static unsigned int police_net_id;
 static struct tc_action_ops act_police_ops;
 
-static int tcf_act_police_walker(struct net *net, struct sk_buff *skb,
+static int tcf_police_walker(struct net *net, struct sk_buff *skb,
 				 struct netlink_callback *cb, int type,
 				 const struct tc_action_ops *ops,
 				 struct netlink_ext_ack *extack)
@@ -73,7 +73,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = {
 	[TCA_POLICE_RESULT]	= { .type = NLA_U32 },
 };
 
-static int tcf_act_police_init(struct net *net, struct nlattr *nla,
+static int tcf_police_init(struct net *net, struct nlattr *nla,
 			       struct nlattr *est, struct tc_action **a,
 			       int ovr, int bind, bool rtnl_held,
 			       struct netlink_ext_ack *extack)
@@ -203,7 +203,7 @@ failure:
 	return err;
 }
 
-static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
+static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a,
 			  struct tcf_result *res)
 {
 	struct tcf_police *police = to_police(a);
@@ -267,7 +267,7 @@ static int tcf_act_police(struct sk_buff *skb, const struct tc_action *a,
 	return police->tcf_action;
 }
 
-static int tcf_act_police_dump(struct sk_buff *skb, struct tc_action *a,
+static int tcf_police_dump(struct sk_buff *skb, struct tc_action *a,
 			       int bind, int ref)
 {
 	unsigned char *b = skb_tail_pointer(skb);
@@ -335,10 +335,10 @@ static struct tc_action_ops act_police_ops = {
 	.kind		=	"police",
 	.type		=	TCA_ID_POLICE,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_act_police,
-	.dump		=	tcf_act_police_dump,
-	.init		=	tcf_act_police_init,
-	.walk		=	tcf_act_police_walker,
+	.act		=	tcf_police_act,
+	.dump		=	tcf_police_dump,
+	.init		=	tcf_police_init,
+	.walk		=	tcf_police_walker,
 	.lookup		=	tcf_police_search,
 	.delete		=	tcf_police_delete,
 	.size		=	sizeof(struct tcf_police),
-- 
cgit v1.2.3


From 798de374e50309dba39cee16527cb3534e84ba86 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:57 -0400
Subject: net: sched: act_simple method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_simple.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c
index 18e4452574cd..e616523ba3c1 100644
--- a/net/sched/act_simple.c
+++ b/net/sched/act_simple.c
@@ -28,8 +28,8 @@ static unsigned int simp_net_id;
 static struct tc_action_ops act_simp_ops;
 
 #define SIMP_MAX_DATA	32
-static int tcf_simp(struct sk_buff *skb, const struct tc_action *a,
-		    struct tcf_result *res)
+static int tcf_simp_act(struct sk_buff *skb, const struct tc_action *a,
+			struct tcf_result *res)
 {
 	struct tcf_defact *d = to_defact(a);
 
@@ -207,7 +207,7 @@ static struct tc_action_ops act_simp_ops = {
 	.kind		=	"simple",
 	.type		=	TCA_ACT_SIMP,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_simp,
+	.act		=	tcf_simp_act,
 	.dump		=	tcf_simp_dump,
 	.cleanup	=	tcf_simp_release,
 	.init		=	tcf_simp_init,
-- 
cgit v1.2.3


From 45da1dac612c0658ed946d573000e88f0d8ec5bc Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:58 -0400
Subject: net: sched: act_skbedit method rename for grep-ability and
 consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbedit.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c
index a6db47ebec11..926d7bc4a89d 100644
--- a/net/sched/act_skbedit.c
+++ b/net/sched/act_skbedit.c
@@ -33,8 +33,8 @@
 static unsigned int skbedit_net_id;
 static struct tc_action_ops act_skbedit_ops;
 
-static int tcf_skbedit(struct sk_buff *skb, const struct tc_action *a,
-		       struct tcf_result *res)
+static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a,
+			   struct tcf_result *res)
 {
 	struct tcf_skbedit *d = to_skbedit(a);
 	struct tcf_skbedit_params *params;
@@ -310,7 +310,7 @@ static struct tc_action_ops act_skbedit_ops = {
 	.kind		=	"skbedit",
 	.type		=	TCA_ACT_SKBEDIT,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_skbedit,
+	.act		=	tcf_skbedit_act,
 	.dump		=	tcf_skbedit_dump,
 	.init		=	tcf_skbedit_init,
 	.cleanup	=	tcf_skbedit_cleanup,
-- 
cgit v1.2.3


From 353d2c253f4cc5c7b28a041a79949f46ed5edb25 Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:34:59 -0400
Subject: net: sched: act_skbmod method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_skbmod.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c
index e9c86ade3b40..d6a1af0c4171 100644
--- a/net/sched/act_skbmod.c
+++ b/net/sched/act_skbmod.c
@@ -24,7 +24,7 @@ static unsigned int skbmod_net_id;
 static struct tc_action_ops act_skbmod_ops;
 
 #define MAX_EDIT_LEN ETH_HLEN
-static int tcf_skbmod_run(struct sk_buff *skb, const struct tc_action *a,
+static int tcf_skbmod_act(struct sk_buff *skb, const struct tc_action *a,
 			  struct tcf_result *res)
 {
 	struct tcf_skbmod *d = to_skbmod(a);
@@ -270,7 +270,7 @@ static struct tc_action_ops act_skbmod_ops = {
 	.kind		=	"skbmod",
 	.type		=	TCA_ACT_SKBMOD,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_skbmod_run,
+	.act		=	tcf_skbmod_act,
 	.dump		=	tcf_skbmod_dump,
 	.init		=	tcf_skbmod_init,
 	.cleanup	=	tcf_skbmod_cleanup,
-- 
cgit v1.2.3


From 8aa7f22e5649db6f994cda1212a37e7f8ae4e63e Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:35:00 -0400
Subject: net: sched: act_vlan method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_vlan.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 5bde17fe3608..d1f5028384c9 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -22,8 +22,8 @@
 static unsigned int vlan_net_id;
 static struct tc_action_ops act_vlan_ops;
 
-static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
-		    struct tcf_result *res)
+static int tcf_vlan_act(struct sk_buff *skb, const struct tc_action *a,
+			struct tcf_result *res)
 {
 	struct tcf_vlan *v = to_vlan(a);
 	struct tcf_vlan_params *p;
@@ -307,7 +307,7 @@ static struct tc_action_ops act_vlan_ops = {
 	.kind		=	"vlan",
 	.type		=	TCA_ACT_VLAN,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_vlan,
+	.act		=	tcf_vlan_act,
 	.dump		=	tcf_vlan_dump,
 	.init		=	tcf_vlan_init,
 	.cleanup	=	tcf_vlan_cleanup,
-- 
cgit v1.2.3


From 7c5790c4da0e5b96b147d683c94ba3ed93e5f0fe Mon Sep 17 00:00:00 2001
From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Sun, 12 Aug 2018 09:35:01 -0400
Subject: net: sched: act_mirred method rename for grep-ability and consistency

Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_mirred.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 327be257033d..8ec216001077 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -190,8 +190,8 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla,
 	return ret;
 }
 
-static int tcf_mirred(struct sk_buff *skb, const struct tc_action *a,
-		      struct tcf_result *res)
+static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
+			  struct tcf_result *res)
 {
 	struct tcf_mirred *m = to_mirred(a);
 	struct sk_buff *skb2 = skb;
@@ -406,7 +406,7 @@ static struct tc_action_ops act_mirred_ops = {
 	.kind		=	"mirred",
 	.type		=	TCA_ACT_MIRRED,
 	.owner		=	THIS_MODULE,
-	.act		=	tcf_mirred,
+	.act		=	tcf_mirred_act,
 	.stats_update	=	tcf_stats_update,
 	.dump		=	tcf_mirred_dump,
 	.cleanup	=	tcf_mirred_release,
-- 
cgit v1.2.3


From 0192e7d46c776f7f735560bfa4d40eac3fd700f9 Mon Sep 17 00:00:00 2001
From: Zong Li <zong@andestech.com>
Date: Mon, 13 Aug 2018 10:26:52 +0800
Subject: net: Change the layout of structure trace_event_raw_fib_table_lookup

There is an unalignment access about the structure
'trace_event_raw_fib_table_lookup'.

In include/trace/events/fib.h, there is a memory operation which casting
the 'src' data member to a pointer, and then store a value to this
pointer point to.

p32 = (__be32 *) __entry->src;
*p32 = flp->saddr;

The offset of 'src' in structure trace_event_raw_fib_table_lookup is not
four bytes alignment. On some architectures, they don't permit the
unalignment access, it need to pay the price to handle this situation in
exception handler.

Adjust the layout of structure to avoid this case.

Fixes: 9f323973c915 ("net/ipv4: Udate fib_table_lookup tracepoint")
Signed-off-by: Zong Li <zong@andestech.com>
Acked-by: David Ahern <dsahern@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/trace/events/fib.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/trace/events/fib.h b/include/trace/events/fib.h
index 9763cddd0594..6271bab63bfb 100644
--- a/include/trace/events/fib.h
+++ b/include/trace/events/fib.h
@@ -22,6 +22,7 @@ TRACE_EVENT(fib_table_lookup,
 		__field(	int,	err		)
 		__field(	int,	oif		)
 		__field(	int,	iif		)
+		__field(	u8,	proto		)
 		__field(	__u8,	tos		)
 		__field(	__u8,	scope		)
 		__field(	__u8,	flags		)
@@ -31,7 +32,6 @@ TRACE_EVENT(fib_table_lookup,
 		__array(	__u8,	saddr,	4	)
 		__field(	u16,	sport		)
 		__field(	u16,	dport		)
-		__field(	u8,	proto		)
 		__dynamic_array(char,  name,   IFNAMSIZ )
 	),
 
-- 
cgit v1.2.3


From 71e41286203c017d24f041a7cd71abea7ca7b1e0 Mon Sep 17 00:00:00 2001
From: Li RongQing <lirongqing@baidu.com>
Date: Mon, 13 Aug 2018 10:42:46 +0800
Subject: packet: switch kvzalloc to allocate memory

The patches includes following change:

*Use modern kvzalloc()/kvfree() instead of custom allocations.

*Remove order argument for alloc_pg_vec, it can get from req.

*Remove order argument for free_pg_vec, free_pg_vec now uses
kvfree which does not need order argument.

*Remove pg_vec_order from struct packet_ring_buffer, no longer
need to save/restore 'order'

*Remove variable 'order' for packet_set_ring, it is now unused

Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/packet/af_packet.c | 44 +++++++++++++-------------------------------
 net/packet/internal.h  |  1 -
 2 files changed, 13 insertions(+), 32 deletions(-)

diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 75c92a87e7b2..5610061e7f2e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -4137,52 +4137,36 @@ static const struct vm_operations_struct packet_mmap_ops = {
 	.close	=	packet_mm_close,
 };
 
-static void free_pg_vec(struct pgv *pg_vec, unsigned int order,
-			unsigned int len)
+static void free_pg_vec(struct pgv *pg_vec, unsigned int len)
 {
 	int i;
 
 	for (i = 0; i < len; i++) {
 		if (likely(pg_vec[i].buffer)) {
-			if (is_vmalloc_addr(pg_vec[i].buffer))
-				vfree(pg_vec[i].buffer);
-			else
-				free_pages((unsigned long)pg_vec[i].buffer,
-					   order);
+			kvfree(pg_vec[i].buffer);
 			pg_vec[i].buffer = NULL;
 		}
 	}
 	kfree(pg_vec);
 }
 
-static char *alloc_one_pg_vec_page(unsigned long order)
+static char *alloc_one_pg_vec_page(unsigned long size)
 {
 	char *buffer;
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP |
-			  __GFP_ZERO | __GFP_NOWARN | __GFP_NORETRY;
 
-	buffer = (char *) __get_free_pages(gfp_flags, order);
+	buffer = kvzalloc(size, GFP_KERNEL);
 	if (buffer)
 		return buffer;
 
-	/* __get_free_pages failed, fall back to vmalloc */
-	buffer = vzalloc(array_size((1 << order), PAGE_SIZE));
-	if (buffer)
-		return buffer;
+	buffer = kvzalloc(size, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
 
-	/* vmalloc failed, lets dig into swap here */
-	gfp_flags &= ~__GFP_NORETRY;
-	buffer = (char *) __get_free_pages(gfp_flags, order);
-	if (buffer)
-		return buffer;
-
-	/* complete and utter failure */
-	return NULL;
+	return buffer;
 }
 
-static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order)
+static struct pgv *alloc_pg_vec(struct tpacket_req *req)
 {
 	unsigned int block_nr = req->tp_block_nr;
+	unsigned long size = req->tp_block_size;
 	struct pgv *pg_vec;
 	int i;
 
@@ -4191,7 +4175,7 @@ static struct pgv *alloc_pg_vec(struct tpacket_req *req, int order)
 		goto out;
 
 	for (i = 0; i < block_nr; i++) {
-		pg_vec[i].buffer = alloc_one_pg_vec_page(order);
+		pg_vec[i].buffer = alloc_one_pg_vec_page(size);
 		if (unlikely(!pg_vec[i].buffer))
 			goto out_free_pgvec;
 	}
@@ -4200,7 +4184,7 @@ out:
 	return pg_vec;
 
 out_free_pgvec:
-	free_pg_vec(pg_vec, order, block_nr);
+	free_pg_vec(pg_vec, block_nr);
 	pg_vec = NULL;
 	goto out;
 }
@@ -4210,9 +4194,9 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 {
 	struct pgv *pg_vec = NULL;
 	struct packet_sock *po = pkt_sk(sk);
-	int was_running, order = 0;
 	struct packet_ring_buffer *rb;
 	struct sk_buff_head *rb_queue;
+	int was_running;
 	__be16 num;
 	int err = -EINVAL;
 	/* Added to avoid minimal code churn */
@@ -4274,8 +4258,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 			goto out;
 
 		err = -ENOMEM;
-		order = get_order(req->tp_block_size);
-		pg_vec = alloc_pg_vec(req, order);
+		pg_vec = alloc_pg_vec(req);
 		if (unlikely(!pg_vec))
 			goto out;
 		switch (po->tp_version) {
@@ -4329,7 +4312,6 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 		rb->frame_size = req->tp_frame_size;
 		spin_unlock_bh(&rb_queue->lock);
 
-		swap(rb->pg_vec_order, order);
 		swap(rb->pg_vec_len, req->tp_block_nr);
 
 		rb->pg_vec_pages = req->tp_block_size/PAGE_SIZE;
@@ -4355,7 +4337,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u,
 	}
 
 	if (pg_vec)
-		free_pg_vec(pg_vec, order, req->tp_block_nr);
+		free_pg_vec(pg_vec, req->tp_block_nr);
 out:
 	return err;
 }
diff --git a/net/packet/internal.h b/net/packet/internal.h
index 3bb7c5fb3bff..8f50036f62f0 100644
--- a/net/packet/internal.h
+++ b/net/packet/internal.h
@@ -64,7 +64,6 @@ struct packet_ring_buffer {
 	unsigned int		frame_size;
 	unsigned int		frame_max;
 
-	unsigned int		pg_vec_order;
 	unsigned int		pg_vec_pages;
 	unsigned int		pg_vec_len;
 
-- 
cgit v1.2.3


From 1150827b121e149632bc8f0d5d2b4453694648b6 Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 13 Aug 2018 14:13:15 +0800
Subject: virtio_net: remove duplicated include from virtio_net.c

Remove duplicated include linux/netdevice.h

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index eb00ae6ee475..765920905226 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -30,7 +30,6 @@
 #include <linux/cpu.h>
 #include <linux/average.h>
 #include <linux/filter.h>
-#include <linux/netdevice.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
 #include <net/route.h>
-- 
cgit v1.2.3


From 3b20818b0acdd493e5b891140310b1435cccf81b Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Mon, 13 Aug 2018 06:39:21 +0000
Subject: lan743x: lan743x: Remove duplicated include from lan743x_ptp.c

Remove duplicated include.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ptp.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 42064fd2beb5..029a2af90d5e 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -6,7 +6,6 @@
 
 #include <linux/module.h>
 #include <linux/pci.h>
-#include <linux/netdevice.h>
 #include <linux/net_tstamp.h>
 
 #include "lan743x_ptp.h"
-- 
cgit v1.2.3


From 0ec456802d133e0eeb4d9ac4283a9982ad9b89af Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 13 Aug 2018 14:59:02 +0800
Subject: cxgb4: remove set but not used variable 'spd'

Fixes gcc '-Wunused-but-set-variable' warning:
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c: In function 'print_port_info':
drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c:5147:14: warning:
 variable 'spd' set but not used [-Wunused-but-set-variable]

variable 'spd' is set but not used since
commit 547fd27241a8 ("cxgb4: Warn if device doesn't have enough PCI bandwidth")

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Acked-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index 69590cff2a2d..961e3087d1d3 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -5144,17 +5144,9 @@ static void print_port_info(const struct net_device *dev)
 {
 	char buf[80];
 	char *bufp = buf;
-	const char *spd = "";
 	const struct port_info *pi = netdev_priv(dev);
 	const struct adapter *adap = pi->adapter;
 
-	if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_2_5GB)
-		spd = " 2.5 GT/s";
-	else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_5_0GB)
-		spd = " 5 GT/s";
-	else if (adap->params.pci.speed == PCI_EXP_LNKSTA_CLS_8_0GB)
-		spd = " 8 GT/s";
-
 	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_100M)
 		bufp += sprintf(bufp, "100M/");
 	if (pi->link_cfg.pcaps & FW_PORT_CAP32_SPEED_1G)
-- 
cgit v1.2.3


From 45c91fb200936b2c48e8605539d800a61abb1cbf Mon Sep 17 00:00:00 2001
From: YueHaibing <yuehaibing@huawei.com>
Date: Mon, 13 Aug 2018 17:29:36 +0800
Subject: liquidio: remove set but not used variable 'is25G'

Fixes gcc '-Wunused-but-set-variable' warning:

drivers/net/ethernet/cavium/liquidio/lio_ethtool.c: In function 'lio_set_link_ksettings':
drivers/net/ethernet/cavium/liquidio/lio_ethtool.c:392:6: warning:
 variable 'is25G' set but not used [-Wunused-but-set-variable]

Signed-off-by: YueHaibing <yuehaibing@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/cavium/liquidio/lio_ethtool.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
index 807ea2c61877..8e05afd5e39c 100644
--- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
+++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c
@@ -389,18 +389,14 @@ static int lio_set_link_ksettings(struct net_device *netdev,
 	struct lio *lio = GET_LIO(netdev);
 	struct oct_link_info *linfo;
 	struct octeon_device *oct;
-	u32 is25G = 0;
 
 	oct = lio->oct_dev;
 
 	linfo = &lio->linfo;
 
-	if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID ||
-	    oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) {
-		is25G = 1;
-	} else {
+	if (!(oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID ||
+	      oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID))
 		return -EOPNOTSUPP;
-	}
 
 	if (oct->no_speed_setting) {
 		dev_err(&oct->pci_dev->dev, "%s: Changing speed is not supported\n",
-- 
cgit v1.2.3


From 42c625a486f367ad57d4257de6d9459daf9484a0 Mon Sep 17 00:00:00 2001
From: Vlad Buslov <vladbu@mellanox.com>
Date: Mon, 13 Aug 2018 20:20:11 +0300
Subject: net: sched: act_ife: disable bh when taking ife_mod_lock

Lockdep reports deadlock for following locking scenario in ife action:

Task one:
1) Executes ife action update.
2) Takes tcfa_lock.
3) Waits on ife_mod_lock which is already taken by task two.

Task two:

1) Executes any path that obtains ife_mod_lock without disabling bh (any
path that takes ife_mod_lock while holding tcfa_lock has bh disabled) like
loading a meta module, or creating new action.
2) Takes ife_mod_lock.
3) Task is preempted by rate estimator timer.
4) Timer callback waits on tcfa_lock which is taken by task one.

In described case tasks deadlock because they take same two locks in
different order. To prevent potential deadlock reported by lockdep, always
disable bh when obtaining ife_mod_lock.

Lockdep warning:

[  508.101192] =====================================================
[  508.107708] WARNING: SOFTIRQ-safe -> SOFTIRQ-unsafe lock order detected
[  508.114728] 4.18.0-rc8+ #646 Not tainted
[  508.119050] -----------------------------------------------------
[  508.125559] tc/5460 [HC0[0]:SC0[2]:HE1:SE0] is trying to acquire:
[  508.132025] 000000005a938c68 (ife_mod_lock){++++}, at: find_ife_oplist+0x1e/0xc0 [act_ife]
[  508.140996]
               and this task is already holding:
[  508.147548] 00000000d46f6c56 (&(&p->tcfa_lock)->rlock){+.-.}, at: tcf_ife_init+0x6ae/0xf40 [act_ife]
[  508.157371] which would create a new lock dependency:
[  508.162828]  (&(&p->tcfa_lock)->rlock){+.-.} -> (ife_mod_lock){++++}
[  508.169572]
               but this new dependency connects a SOFTIRQ-irq-safe lock:
[  508.178197]  (&(&p->tcfa_lock)->rlock){+.-.}
[  508.178201]
               ... which became SOFTIRQ-irq-safe at:
[  508.189771]   _raw_spin_lock+0x2c/0x40
[  508.193906]   est_fetch_counters+0x41/0xb0
[  508.198391]   est_timer+0x83/0x3c0
[  508.202180]   call_timer_fn+0x16a/0x5d0
[  508.206400]   run_timer_softirq+0x399/0x920
[  508.210967]   __do_softirq+0x157/0x97d
[  508.215102]   irq_exit+0x152/0x1c0
[  508.218888]   smp_apic_timer_interrupt+0xc0/0x4e0
[  508.223976]   apic_timer_interrupt+0xf/0x20
[  508.228540]   cpuidle_enter_state+0xf8/0x5d0
[  508.233198]   do_idle+0x28a/0x350
[  508.236881]   cpu_startup_entry+0xc7/0xe0
[  508.241296]   start_secondary+0x2e8/0x3f0
[  508.245678]   secondary_startup_64+0xa5/0xb0
[  508.250347]
               to a SOFTIRQ-irq-unsafe lock:  (ife_mod_lock){++++}
[  508.256531]
               ... which became SOFTIRQ-irq-unsafe at:
[  508.267279] ...
[  508.267283]   _raw_write_lock+0x2c/0x40
[  508.273653]   register_ife_op+0x118/0x2c0 [act_ife]
[  508.278926]   do_one_initcall+0xf7/0x4d9
[  508.283214]   do_init_module+0x18b/0x44e
[  508.287521]   load_module+0x4167/0x5730
[  508.291739]   __do_sys_finit_module+0x16d/0x1a0
[  508.296654]   do_syscall_64+0x7a/0x3f0
[  508.300788]   entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  508.306302]
               other info that might help us debug this:

[  508.315286]  Possible interrupt unsafe locking scenario:

[  508.322771]        CPU0                    CPU1
[  508.327681]        ----                    ----
[  508.332604]   lock(ife_mod_lock);
[  508.336300]                                local_irq_disable();
[  508.342608]                                lock(&(&p->tcfa_lock)->rlock);
[  508.349793]                                lock(ife_mod_lock);
[  508.355990]   <Interrupt>
[  508.358974]     lock(&(&p->tcfa_lock)->rlock);
[  508.363803]
                *** DEADLOCK ***

[  508.370715] 2 locks held by tc/5460:
[  508.374680]  #0: 00000000e27e4fa4 (rtnl_mutex){+.+.}, at: rtnetlink_rcv_msg+0x583/0x7b0
[  508.383366]  #1: 00000000d46f6c56 (&(&p->tcfa_lock)->rlock){+.-.}, at: tcf_ife_init+0x6ae/0xf40 [act_ife]
[  508.393648]
               the dependencies between SOFTIRQ-irq-safe lock and the holding lock:
[  508.403505] -> (&(&p->tcfa_lock)->rlock){+.-.} ops: 1001553 {
[  508.409646]    HARDIRQ-ON-W at:
[  508.413136]                     _raw_spin_lock_bh+0x34/0x40
[  508.419059]                     gnet_stats_start_copy_compat+0xa2/0x230
[  508.426021]                     gnet_stats_start_copy+0x16/0x20
[  508.432333]                     tcf_action_copy_stats+0x95/0x1d0
[  508.438735]                     tcf_action_dump_1+0xb0/0x4e0
[  508.444795]                     tcf_action_dump+0xca/0x200
[  508.450673]                     tcf_exts_dump+0xd9/0x320
[  508.456392]                     fl_dump+0x1b7/0x4a0 [cls_flower]
[  508.462798]                     tcf_fill_node+0x380/0x530
[  508.468601]                     tfilter_notify+0xdf/0x1c0
[  508.474404]                     tc_new_tfilter+0x84a/0xc90
[  508.480270]                     rtnetlink_rcv_msg+0x5bd/0x7b0
[  508.486419]                     netlink_rcv_skb+0x184/0x220
[  508.492394]                     netlink_unicast+0x31b/0x460
[  508.507411]                     netlink_sendmsg+0x3fb/0x840
[  508.513390]                     sock_sendmsg+0x7b/0xd0
[  508.518907]                     ___sys_sendmsg+0x4c6/0x610
[  508.524797]                     __sys_sendmsg+0xd7/0x150
[  508.530510]                     do_syscall_64+0x7a/0x3f0
[  508.536201]                     entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  508.543301]    IN-SOFTIRQ-W at:
[  508.546834]                     _raw_spin_lock+0x2c/0x40
[  508.552522]                     est_fetch_counters+0x41/0xb0
[  508.558571]                     est_timer+0x83/0x3c0
[  508.563912]                     call_timer_fn+0x16a/0x5d0
[  508.569699]                     run_timer_softirq+0x399/0x920
[  508.575840]                     __do_softirq+0x157/0x97d
[  508.581538]                     irq_exit+0x152/0x1c0
[  508.586882]                     smp_apic_timer_interrupt+0xc0/0x4e0
[  508.593533]                     apic_timer_interrupt+0xf/0x20
[  508.599686]                     cpuidle_enter_state+0xf8/0x5d0
[  508.605895]                     do_idle+0x28a/0x350
[  508.611147]                     cpu_startup_entry+0xc7/0xe0
[  508.617097]                     start_secondary+0x2e8/0x3f0
[  508.623029]                     secondary_startup_64+0xa5/0xb0
[  508.629245]    INITIAL USE at:
[  508.632686]                    _raw_spin_lock_bh+0x34/0x40
[  508.638557]                    gnet_stats_start_copy_compat+0xa2/0x230
[  508.645491]                    gnet_stats_start_copy+0x16/0x20
[  508.651719]                    tcf_action_copy_stats+0x95/0x1d0
[  508.657992]                    tcf_action_dump_1+0xb0/0x4e0
[  508.663937]                    tcf_action_dump+0xca/0x200
[  508.669716]                    tcf_exts_dump+0xd9/0x320
[  508.675337]                    fl_dump+0x1b7/0x4a0 [cls_flower]
[  508.681650]                    tcf_fill_node+0x380/0x530
[  508.687366]                    tfilter_notify+0xdf/0x1c0
[  508.693031]                    tc_new_tfilter+0x84a/0xc90
[  508.698820]                    rtnetlink_rcv_msg+0x5bd/0x7b0
[  508.704869]                    netlink_rcv_skb+0x184/0x220
[  508.710758]                    netlink_unicast+0x31b/0x460
[  508.716627]                    netlink_sendmsg+0x3fb/0x840
[  508.722510]                    sock_sendmsg+0x7b/0xd0
[  508.727931]                    ___sys_sendmsg+0x4c6/0x610
[  508.733729]                    __sys_sendmsg+0xd7/0x150
[  508.739346]                    do_syscall_64	+0x7a/0x3f0
[  508.744943]                    entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  508.751930]  }
[  508.753964]  ... key      at: [<ffffffff916b3e20>] __key.61145+0x0/0x40
[  508.760946]  ... acquired at:
[  508.764294]    _raw_read_lock+0x2f/0x40
[  508.768513]    find_ife_oplist+0x1e/0xc0 [act_ife]
[  508.773692]    tcf_ife_init+0x82f/0xf40 [act_ife]
[  508.778785]    tcf_action_init_1+0x510/0x750
[  508.783468]    tcf_action_init+0x1e8/0x340
[  508.787938]    tcf_action_add+0xc5/0x240
[  508.792241]    tc_ctl_action+0x203/0x2a0
[  508.796550]    rtnetlink_rcv_msg+0x5bd/0x7b0
[  508.801200]    netlink_rcv_skb+0x184/0x220
[  508.805674]    netlink_unicast+0x31b/0x460
[  508.810129]    netlink_sendmsg+0x3fb/0x840
[  508.814611]    sock_sendmsg+0x7b/0xd0
[  508.818665]    ___sys_sendmsg+0x4c6/0x610
[  508.823029]    __sys_sendmsg+0xd7/0x150
[  508.827246]    do_syscall_64+0x7a/0x3f0
[  508.831483]    entry_SYSCALL_64_after_hwframe+0x49/0xbe

               the dependencies between the lock to be acquired
[  508.838945]  and SOFTIRQ-irq-unsafe lock:
[  508.851177] -> (ife_mod_lock){++++} ops: 95 {
[  508.855920]    HARDIRQ-ON-W at:
[  508.859478]                     _raw_write_lock+0x2c/0x40
[  508.865264]                     register_ife_op+0x118/0x2c0 [act_ife]
[  508.872071]                     do_one_initcall+0xf7/0x4d9
[  508.877947]                     do_init_module+0x18b/0x44e
[  508.883819]                     load_module+0x4167/0x5730
[  508.889595]                     __do_sys_finit_module+0x16d/0x1a0
[  508.896043]                     do_syscall_64+0x7a/0x3f0
[  508.901734]                     entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  508.908827]    HARDIRQ-ON-R at:
[  508.912359]                     _raw_read_lock+0x2f/0x40
[  508.918043]                     find_ife_oplist+0x1e/0xc0 [act_ife]
[  508.924692]                     tcf_ife_init+0x82f/0xf40 [act_ife]
[  508.931252]                     tcf_action_init_1+0x510/0x750
[  508.937393]                     tcf_action_init+0x1e8/0x340
[  508.943366]                     tcf_action_add+0xc5/0x240
[  508.949130]                     tc_ctl_action+0x203/0x2a0
[  508.954922]                     rtnetlink_rcv_msg+0x5bd/0x7b0
[  508.961024]                     netlink_rcv_skb+0x184/0x220
[  508.966970]                     netlink_unicast+0x31b/0x460
[  508.972915]                     netlink_sendmsg+0x3fb/0x840
[  508.978859]                     sock_sendmsg+0x7b/0xd0
[  508.984400]                     ___sys_sendmsg+0x4c6/0x610
[  508.990264]                     __sys_sendmsg+0xd7/0x150
[  508.995952]                     do_syscall_64+0x7a/0x3f0
[  509.001643]                     entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  509.008722]    SOFTIRQ-ON-W at:\
[  509.012242]                     _raw_write_lock+0x2c/0x40
[  509.018013]                     register_ife_op+0x118/0x2c0 [act_ife]
[  509.024841]                     do_one_initcall+0xf7/0x4d9
[  509.030720]                     do_init_module+0x18b/0x44e
[  509.036604]                     load_module+0x4167/0x5730
[  509.042397]                     __do_sys_finit_module+0x16d/0x1a0
[  509.048865]                     do_syscall_64+0x7a/0x3f0
[  509.054551]                     entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  509.061636]    SOFTIRQ-ON-R at:
[  509.065145]                     _raw_read_lock+0x2f/0x40
[  509.070854]                     find_ife_oplist+0x1e/0xc0 [act_ife]
[  509.077515]                     tcf_ife_init+0x82f/0xf40 [act_ife]
[  509.084051]                     tcf_action_init_1+0x510/0x750
[  509.090172]                     tcf_action_init+0x1e8/0x340
[  509.096124]                     tcf_action_add+0xc5/0x240
[  509.101891]                     tc_ctl_action+0x203/0x2a0
[  509.107671]                     rtnetlink_rcv_msg+0x5bd/0x7b0
[  509.113811]                     netlink_rcv_skb+0x184/0x220
[  509.119768]                     netlink_unicast+0x31b/0x460
[  509.125716]                     netlink_sendmsg+0x3fb/0x840
[  509.131668]                     sock_sendmsg+0x7b/0xd0
[  509.137167]                     ___sys_sendmsg+0x4c6/0x610
[  509.143010]                     __sys_sendmsg+0xd7/0x150
[  509.148718]                     do_syscall_64+0x7a/0x3f0
[  509.154443]                     entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  509.161533]    INITIAL USE at:
[  509.164956]                    _raw_read_lock+0x2f/0x40
[  509.170574]                    find_ife_oplist+0x1e/0xc0 [act_ife]
[  509.177134]                    tcf_ife_init+0x82f/0xf40 [act_ife]
[  509.183619]                    tcf_action_init_1+0x510/0x750
[  509.189674]                    tcf_action_init+0x1e8/0x340
[  509.195534]                    tcf_action_add+0xc5/0x240
[  509.201229]                    tc_ctl_action+0x203/0x2a0
[  509.206920]                    rtnetlink_rcv_msg+0x5bd/0x7b0
[  509.212936]                    netlink_rcv_skb+0x184/0x220
[  509.218818]                    netlink_unicast+0x31b/0x460
[  509.224699]                    netlink_sendmsg+0x3fb/0x840
[  509.230581]                    sock_sendmsg+0x7b/0xd0
[  509.235984]                    ___sys_sendmsg+0x4c6/0x610
[  509.241791]                    __sys_sendmsg+0xd7/0x150
[  509.247425]                    do_syscall_64+0x7a/0x3f0
[  509.253007]                    entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  509.259975]  }
[  509.261998]  ... key      at: [<ffffffffc1554258>] ife_mod_lock+0x18/0xffffffffffff8dc0 [act_ife]
[  509.271569]  ... acquired at:
[  509.274912]    _raw_read_lock+0x2f/0x40
[  509.279134]    find_ife_oplist+0x1e/0xc0 [act_ife]
[  509.284324]    tcf_ife_init+0x82f/0xf40 [act_ife]
[  509.289425]    tcf_action_init_1+0x510/0x750
[  509.294068]    tcf_action_init+0x1e8/0x340
[  509.298553]    tcf_action_add+0xc5/0x240
[  509.302854]    tc_ctl_action+0x203/0x2a0
[  509.307153]    rtnetlink_rcv_msg+0x5bd/0x7b0
[  509.311805]    netlink_rcv_skb+0x184/0x220
[  509.316282]    netlink_unicast+0x31b/0x460
[  509.320769]    netlink_sendmsg+0x3fb/0x840
[  509.325248]    sock_sendmsg+0x7b/0xd0
[  509.329290]    ___sys_sendmsg+0x4c6/0x610
[  509.333687]    __sys_sendmsg+0xd7/0x150
[  509.337902]    do_syscall_64+0x7a/0x3f0
[  509.342116]    entry_SYSCALL_64_after_hwframe+0x49/0xbe
[  509.349601]
               stack backtrace:
[  509.354663] CPU: 6 PID: 5460 Comm: tc Not tainted 4.18.0-rc8+ #646
[  509.361216] Hardware name: Supermicro SYS-2028TP-DECR/X10DRT-P, BIOS 2.0b 03/30/2017

Fixes: ef6980b6becb ("introduce IFE action")
Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/act_ife.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c
index 5d200495e467..fdb928ca81bb 100644
--- a/net/sched/act_ife.c
+++ b/net/sched/act_ife.c
@@ -167,16 +167,16 @@ static struct tcf_meta_ops *find_ife_oplist(u16 metaid)
 {
 	struct tcf_meta_ops *o;
 
-	read_lock(&ife_mod_lock);
+	read_lock_bh(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
 		if (o->metaid == metaid) {
 			if (!try_module_get(o->owner))
 				o = NULL;
-			read_unlock(&ife_mod_lock);
+			read_unlock_bh(&ife_mod_lock);
 			return o;
 		}
 	}
-	read_unlock(&ife_mod_lock);
+	read_unlock_bh(&ife_mod_lock);
 
 	return NULL;
 }
@@ -190,12 +190,12 @@ int register_ife_op(struct tcf_meta_ops *mops)
 	    !mops->get || !mops->alloc)
 		return -EINVAL;
 
-	write_lock(&ife_mod_lock);
+	write_lock_bh(&ife_mod_lock);
 
 	list_for_each_entry(m, &ifeoplist, list) {
 		if (m->metaid == mops->metaid ||
 		    (strcmp(mops->name, m->name) == 0)) {
-			write_unlock(&ife_mod_lock);
+			write_unlock_bh(&ife_mod_lock);
 			return -EEXIST;
 		}
 	}
@@ -204,7 +204,7 @@ int register_ife_op(struct tcf_meta_ops *mops)
 		mops->release = ife_release_meta_gen;
 
 	list_add_tail(&mops->list, &ifeoplist);
-	write_unlock(&ife_mod_lock);
+	write_unlock_bh(&ife_mod_lock);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(unregister_ife_op);
@@ -214,7 +214,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops)
 	struct tcf_meta_ops *m;
 	int err = -ENOENT;
 
-	write_lock(&ife_mod_lock);
+	write_lock_bh(&ife_mod_lock);
 	list_for_each_entry(m, &ifeoplist, list) {
 		if (m->metaid == mops->metaid) {
 			list_del(&mops->list);
@@ -222,7 +222,7 @@ int unregister_ife_op(struct tcf_meta_ops *mops)
 			break;
 		}
 	}
-	write_unlock(&ife_mod_lock);
+	write_unlock_bh(&ife_mod_lock);
 
 	return err;
 }
@@ -343,13 +343,13 @@ static int use_all_metadata(struct tcf_ife_info *ife)
 	int rc = 0;
 	int installed = 0;
 
-	read_lock(&ife_mod_lock);
+	read_lock_bh(&ife_mod_lock);
 	list_for_each_entry(o, &ifeoplist, list) {
 		rc = add_metainfo(ife, o->metaid, NULL, 0, true);
 		if (rc == 0)
 			installed += 1;
 	}
-	read_unlock(&ife_mod_lock);
+	read_unlock_bh(&ife_mod_lock);
 
 	if (installed)
 		return 0;
-- 
cgit v1.2.3


From b29c61dac3a258575c438c7ae1fc4c20260d823c Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 5 Jul 2018 17:30:34 -0700
Subject: net/mlx5e: Ethtool steering flow validation refactoring

Have a ethtool rx flow spec validation helper function per flow type.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    | 164 +++++++++++++--------
 1 file changed, 100 insertions(+), 64 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index eafc59280ada..5301399164fb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -379,16 +379,95 @@ static struct mlx5e_ethtool_rule *get_ethtool_rule(struct mlx5e_priv *priv,
 #define all_zeros_or_all_ones(field)		\
 	((field) == 0 || (field) == (__force typeof(field))-1)
 
+static int validate_ethter(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethhdr *eth_mask = &fs->m_u.ether_spec;
+	int ntuples = 0;
+
+	if (!is_zero_ether_addr(eth_mask->h_dest))
+		ntuples++;
+	if (!is_zero_ether_addr(eth_mask->h_source))
+		ntuples++;
+	if (eth_mask->h_proto)
+		ntuples++;
+	return ntuples;
+}
+
+static int validate_tcpudp4(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.tcp_ip4_spec;
+	int ntuples = 0;
+
+	if (l4_mask->tos)
+		return -EINVAL;
+
+	if (l4_mask->ip4src) {
+		if (!all_ones(l4_mask->ip4src))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->ip4dst) {
+		if (!all_ones(l4_mask->ip4dst))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->psrc) {
+		if (!all_ones(l4_mask->psrc))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->pdst) {
+		if (!all_ones(l4_mask->pdst))
+			return -EINVAL;
+		ntuples++;
+	}
+	/* Flow is TCP/UDP */
+	return ++ntuples;
+}
+
+static int validate_ip4(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec;
+	int ntuples = 0;
+
+	if (l3_mask->l4_4_bytes || l3_mask->tos || l3_mask->proto ||
+	    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
+		return -EINVAL;
+	if (l3_mask->ip4src) {
+		if (!all_ones(l3_mask->ip4src))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l3_mask->ip4dst) {
+		if (!all_ones(l3_mask->ip4dst))
+			return -EINVAL;
+		ntuples++;
+	}
+	/* Flow is IPv4 */
+	return ++ntuples;
+}
+
+static int validate_vlan(struct ethtool_rx_flow_spec *fs)
+{
+	if (fs->m_ext.vlan_etype ||
+	    fs->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK))
+		return -EINVAL;
+
+	if (fs->m_ext.vlan_tci &&
+	    (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID))
+		return -EINVAL;
+
+	return 1;
+}
+
 static int validate_flow(struct mlx5e_priv *priv,
 			 struct ethtool_rx_flow_spec *fs)
 {
-	struct ethtool_tcpip4_spec *l4_mask;
-	struct ethtool_usrip4_spec *l3_mask;
-	struct ethhdr *eth_mask;
 	int num_tuples = 0;
+	int ret = 0;
 
 	if (fs->location >= MAX_NUM_OF_ETHTOOL_RULES)
-		return -EINVAL;
+		return -ENOSPC;
 
 	if (fs->ring_cookie >= priv->channels.params.num_channels &&
 	    fs->ring_cookie != RX_CLS_FLOW_DISC)
@@ -396,73 +475,29 @@ static int validate_flow(struct mlx5e_priv *priv,
 
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
 	case ETHER_FLOW:
-		eth_mask = &fs->m_u.ether_spec;
-		if (!is_zero_ether_addr(eth_mask->h_dest))
-			num_tuples++;
-		if (!is_zero_ether_addr(eth_mask->h_source))
-			num_tuples++;
-		if (eth_mask->h_proto)
-			num_tuples++;
+		num_tuples += validate_ethter(fs);
 		break;
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
-		if (fs->m_u.tcp_ip4_spec.tos)
-			return -EINVAL;
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		if (l4_mask->ip4src) {
-			if (!all_ones(l4_mask->ip4src))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->ip4dst) {
-			if (!all_ones(l4_mask->ip4dst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->psrc) {
-			if (!all_ones(l4_mask->psrc))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l4_mask->pdst) {
-			if (!all_ones(l4_mask->pdst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		/* Flow is TCP/UDP */
-		num_tuples++;
+		ret = validate_tcpudp4(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 		break;
 	case IP_USER_FLOW:
-		l3_mask = &fs->m_u.usr_ip4_spec;
-		if (l3_mask->l4_4_bytes || l3_mask->tos || l3_mask->proto ||
-		    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
-			return -EINVAL;
-		if (l3_mask->ip4src) {
-			if (!all_ones(l3_mask->ip4src))
-				return -EINVAL;
-			num_tuples++;
-		}
-		if (l3_mask->ip4dst) {
-			if (!all_ones(l3_mask->ip4dst))
-				return -EINVAL;
-			num_tuples++;
-		}
-		/* Flow is IPv4 */
-		num_tuples++;
+		ret = validate_ip4(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 		break;
 	default:
-		return -EINVAL;
+		return -ENOTSUPP;
 	}
 	if ((fs->flow_type & FLOW_EXT)) {
-		if (fs->m_ext.vlan_etype ||
-		    (fs->m_ext.vlan_tci != cpu_to_be16(VLAN_VID_MASK)))
-			return -EINVAL;
-
-		if (fs->m_ext.vlan_tci) {
-			if (be16_to_cpu(fs->h_ext.vlan_tci) >= VLAN_N_VID)
-				return -EINVAL;
-		}
-		num_tuples++;
+		ret = validate_vlan(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
 	}
 
 	if (fs->flow_type & FLOW_MAC_EXT &&
@@ -483,8 +518,9 @@ int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
 
 	num_tuples = validate_flow(priv, fs);
 	if (num_tuples <= 0) {
-		netdev_warn(priv->netdev, "%s: flow is not valid\n",  __func__);
-		return -EINVAL;
+		netdev_warn(priv->netdev, "%s: flow is not valid %d\n",
+			    __func__, num_tuples);
+		return num_tuples;
 	}
 
 	eth_ft = get_flow_table(priv, fs, num_tuples);
-- 
cgit v1.2.3


From 142644f8a1f8b419005d8b3c641e80b32ce2a5f7 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 5 Jul 2018 17:31:14 -0700
Subject: net/mlx5e: Ethtool steering flow parsing refactoring

Have a parsing function per flow type, that converts from ethtool rx flow
spec to mlx5 flow spec.

Will be useful to add support for ip6 ethtool flow steering in the
next patch.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    | 230 ++++++++++++---------
 1 file changed, 128 insertions(+), 102 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 5301399164fb..cf2491a54d32 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -115,29 +115,134 @@ static void mask_spec(u8 *mask, u8 *val, size_t size)
 		*((u8 *)val) = *((u8 *)mask) & *((u8 *)val);
 }
 
-static void set_ips(void *outer_headers_v, void *outer_headers_c, __be32 ip4src_m,
-		    __be32 ip4src_v, __be32 ip4dst_m, __be32 ip4dst_v)
+#define MLX5E_FTE_SET(header_p, fld, v)  \
+	MLX5_SET(fte_match_set_lyr_2_4, header_p, fld, v)
+
+#define MLX5E_FTE_ADDR_OF(header_p, fld) \
+	MLX5_ADDR_OF(fte_match_set_lyr_2_4, header_p, fld)
+
+static void
+set_ip4(void *headers_c, void *headers_v, __be32 ip4src_m,
+	__be32 ip4src_v, __be32 ip4dst_m, __be32 ip4dst_v)
 {
 	if (ip4src_m) {
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
-				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv4_layout.ipv4),
 		       &ip4src_v, sizeof(ip4src_v));
-		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
-				    src_ipv4_src_ipv6.ipv4_layout.ipv4),
+		memset(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv4_layout.ipv4),
 		       0xff, sizeof(ip4src_m));
 	}
 	if (ip4dst_m) {
-		memcpy(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_v,
-				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 		       &ip4dst_v, sizeof(ip4dst_v));
-		memset(MLX5_ADDR_OF(fte_match_set_lyr_2_4, outer_headers_c,
-				    dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
+		memset(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv4_layout.ipv4),
 		       0xff, sizeof(ip4dst_m));
 	}
-	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-		 ethertype, ETH_P_IP);
-	MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-		 ethertype, 0xffff);
+
+	MLX5E_FTE_SET(headers_c, ethertype, 0xffff);
+	MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IP);
+}
+
+static void
+set_tcp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
+	__be16 pdst_m, __be16 pdst_v)
+{
+	if (psrc_m) {
+		MLX5E_FTE_SET(headers_c, tcp_sport, 0xffff);
+		MLX5E_FTE_SET(headers_v, tcp_sport, ntohs(psrc_v));
+	}
+	if (pdst_m) {
+		MLX5E_FTE_SET(headers_c, tcp_dport, 0xffff);
+		MLX5E_FTE_SET(headers_v, tcp_dport, ntohs(pdst_v));
+	}
+
+	MLX5E_FTE_SET(headers_c, ip_protocol, 0xffff);
+	MLX5E_FTE_SET(headers_v, ip_protocol, IPPROTO_TCP);
+}
+
+static void
+set_udp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
+	__be16 pdst_m, __be16 pdst_v)
+{
+	if (psrc_m) {
+		MLX5E_FTE_SET(headers_c, udp_sport, 0xffff);
+		MLX5E_FTE_SET(headers_c, udp_sport, ntohs(psrc_v));
+	}
+
+	if (pdst_m) {
+		MLX5E_FTE_SET(headers_c, udp_dport, 0xffff);
+		MLX5E_FTE_SET(headers_v, udp_dport, ntohs(pdst_v));
+	}
+
+	MLX5E_FTE_SET(headers_c, ip_protocol, 0xffff);
+	MLX5E_FTE_SET(headers_v, ip_protocol, IPPROTO_UDP);
+}
+
+static void
+parse_tcp4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.tcp_ip4_spec;
+	struct ethtool_tcpip4_spec *l4_val  = &fs->h_u.tcp_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l4_mask->ip4src, l4_val->ip4src,
+		l4_mask->ip4dst, l4_val->ip4dst);
+
+	set_tcp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_udp4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip4_spec *l4_mask = &fs->m_u.udp_ip4_spec;
+	struct ethtool_tcpip4_spec *l4_val  = &fs->h_u.udp_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l4_mask->ip4src, l4_val->ip4src,
+		l4_mask->ip4dst, l4_val->ip4dst);
+
+	set_udp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_ip4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec;
+	struct ethtool_usrip4_spec *l3_val  = &fs->h_u.usr_ip4_spec;
+
+	set_ip4(headers_c, headers_v, l3_mask->ip4src, l3_val->ip4src,
+		l3_mask->ip4dst, l3_val->ip4dst);
+}
+
+static void
+parse_ether(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethhdr *eth_mask = &fs->m_u.ether_spec;
+	struct ethhdr *eth_val = &fs->h_u.ether_spec;
+
+	mask_spec((u8 *)eth_mask, (u8 *)eth_val, sizeof(*eth_mask));
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, smac_47_16), eth_mask->h_source);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, smac_47_16), eth_val->h_source);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, dmac_47_16), eth_mask->h_dest);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, dmac_47_16), eth_val->h_dest);
+	MLX5E_FTE_SET(headers_c, ethertype, ntohs(eth_mask->h_proto));
+	MLX5E_FTE_SET(headers_v, ethertype, ntohs(eth_val->h_proto));
+}
+
+static void
+set_cvlan(void *headers_c, void *headers_v, __be16 vlan_tci)
+{
+	MLX5E_FTE_SET(headers_c, cvlan_tag, 1);
+	MLX5E_FTE_SET(headers_v, cvlan_tag, 1);
+	MLX5E_FTE_SET(headers_c, first_vid, 0xfff);
+	MLX5E_FTE_SET(headers_v, first_vid, ntohs(vlan_tci));
+}
+
+static void
+set_dmac(void *headers_c, void *headers_v,
+	 unsigned char m_dest[ETH_ALEN], unsigned char v_dest[ETH_ALEN])
+{
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_c, dmac_47_16), m_dest);
+	ether_addr_copy(MLX5E_FTE_ADDR_OF(headers_v, dmac_47_16), v_dest);
 }
 
 static int set_flow_attrs(u32 *match_c, u32 *match_v,
@@ -148,112 +253,33 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
 	void *outer_headers_v = MLX5_ADDR_OF(fte_match_param, match_v,
 					     outer_headers);
 	u32 flow_type = fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT);
-	struct ethtool_tcpip4_spec *l4_mask;
-	struct ethtool_tcpip4_spec *l4_val;
-	struct ethtool_usrip4_spec *l3_mask;
-	struct ethtool_usrip4_spec *l3_val;
-	struct ethhdr *eth_val;
-	struct ethhdr *eth_mask;
 
 	switch (flow_type) {
 	case TCP_V4_FLOW:
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		l4_val = &fs->h_u.tcp_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
-			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
-
-		if (l4_mask->psrc) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_sport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_sport,
-				 ntohs(l4_val->psrc));
-		}
-		if (l4_mask->pdst) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, tcp_dport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, tcp_dport,
-				 ntohs(l4_val->pdst));
-		}
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
-			 0xffff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
-			 IPPROTO_TCP);
+		parse_tcp4(outer_headers_c, outer_headers_v, fs);
 		break;
 	case UDP_V4_FLOW:
-		l4_mask = &fs->m_u.tcp_ip4_spec;
-		l4_val = &fs->h_u.tcp_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l4_mask->ip4src,
-			l4_val->ip4src, l4_mask->ip4dst, l4_val->ip4dst);
-
-		if (l4_mask->psrc) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_sport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_sport,
-				 ntohs(l4_val->psrc));
-		}
-		if (l4_mask->pdst) {
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, udp_dport,
-				 0xffff);
-			MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, udp_dport,
-				 ntohs(l4_val->pdst));
-		}
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ip_protocol,
-			 0xffff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ip_protocol,
-			 IPPROTO_UDP);
+		parse_udp4(outer_headers_c, outer_headers_v, fs);
 		break;
 	case IP_USER_FLOW:
-		l3_mask = &fs->m_u.usr_ip4_spec;
-		l3_val = &fs->h_u.usr_ip4_spec;
-		set_ips(outer_headers_v, outer_headers_c, l3_mask->ip4src,
-			l3_val->ip4src, l3_mask->ip4dst, l3_val->ip4dst);
+		parse_ip4(outer_headers_c, outer_headers_v, fs);
 		break;
 	case ETHER_FLOW:
-		eth_mask = &fs->m_u.ether_spec;
-		eth_val = &fs->h_u.ether_spec;
-
-		mask_spec((u8 *)eth_mask, (u8 *)eth_val, sizeof(*eth_mask));
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, smac_47_16),
-				eth_mask->h_source);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, smac_47_16),
-				eth_val->h_source);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, dmac_47_16),
-				eth_mask->h_dest);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, dmac_47_16),
-				eth_val->h_dest);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c, ethertype,
-			 ntohs(eth_mask->h_proto));
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v, ethertype,
-			 ntohs(eth_val->h_proto));
+		parse_ether(outer_headers_c, outer_headers_v, fs);
 		break;
 	default:
 		return -EINVAL;
 	}
 
 	if ((fs->flow_type & FLOW_EXT) &&
-	    (fs->m_ext.vlan_tci & cpu_to_be16(VLAN_VID_MASK))) {
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-			 cvlan_tag, 1);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-			 cvlan_tag, 1);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_c,
-			 first_vid, 0xfff);
-		MLX5_SET(fte_match_set_lyr_2_4, outer_headers_v,
-			 first_vid, ntohs(fs->h_ext.vlan_tci));
-	}
+	    (fs->m_ext.vlan_tci & cpu_to_be16(VLAN_VID_MASK)))
+		set_cvlan(outer_headers_c, outer_headers_v, fs->h_ext.vlan_tci);
+
 	if (fs->flow_type & FLOW_MAC_EXT &&
 	    !is_zero_ether_addr(fs->m_ext.h_dest)) {
 		mask_spec(fs->m_ext.h_dest, fs->h_ext.h_dest, ETH_ALEN);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_c, dmac_47_16),
-				fs->m_ext.h_dest);
-		ether_addr_copy(MLX5_ADDR_OF(fte_match_set_lyr_2_4,
-					     outer_headers_v, dmac_47_16),
-				fs->h_ext.h_dest);
+		set_dmac(outer_headers_c, outer_headers_v, fs->m_ext.h_dest,
+			 fs->h_ext.h_dest);
 	}
 
 	return 0;
-- 
cgit v1.2.3


From 7695e73f3db4576ef3ce05063c28e9a673425763 Mon Sep 17 00:00:00 2001
From: Bjorn Helgaas <bhelgaas@google.com>
Date: Mon, 13 Aug 2018 14:30:41 -0500
Subject: PCI: Add function 1 DMA alias quirk for Marvell 88SS9183
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add function 1 DMA alias quirk for Marvell 88SS9183 PCIe SSD Controller.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=42679#c134
Reported-and-tested-by: Felix Blüthner <f.bluethner@mailbox.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/quirks.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index deb051583eda..6994544125ff 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -3845,6 +3845,9 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x917a,
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c78 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9182,
 			 quirk_dma_func1_alias);
+/* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c134 */
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x9183,
+			 quirk_dma_func1_alias);
 /* https://bugzilla.kernel.org/show_bug.cgi?id=42679#c46 */
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MARVELL_EXT, 0x91a0,
 			 quirk_dma_func1_alias);
-- 
cgit v1.2.3


From ca7deb028a2c7c38e6f743443376dd52ea526f0d Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 5 Jul 2018 17:11:09 -0700
Subject: net/mlx5e: Ethtool steering, ip6 support

Add ip6 support for ethtool flow steering.

New supported flow types: ip6|tcp6|udp6|
Supported fields: src-ip|dst-ip|src-port|dst-port

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    | 129 +++++++++++++++++++++
 1 file changed, 129 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index cf2491a54d32..c81ab2136cc5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -66,11 +66,14 @@ static struct mlx5e_ethtool_table *get_flow_table(struct mlx5e_priv *priv,
 	switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT)) {
 	case TCP_V4_FLOW:
 	case UDP_V4_FLOW:
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
 		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
 		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
 		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
 		break;
 	case IP_USER_FLOW:
+	case IPV6_USER_FLOW:
 		max_tuples = ETHTOOL_NUM_L3_L4_FTS;
 		prio = MLX5E_ETHTOOL_L3_L4_PRIO + (max_tuples - num_tuples);
 		eth_ft = &priv->fs.ethtool.l3_l4_ft[prio];
@@ -142,6 +145,29 @@ set_ip4(void *headers_c, void *headers_v, __be32 ip4src_m,
 	MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IP);
 }
 
+static void
+set_ip6(void *headers_c, void *headers_v, __be32 ip6src_m[4],
+	__be32 ip6src_v[4], __be32 ip6dst_m[4], __be32 ip6dst_v[4])
+{
+	u8 ip6_sz = MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6);
+
+	if (!ipv6_addr_any((struct in6_addr *)ip6src_m)) {
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       ip6src_v, ip6_sz);
+		memcpy(MLX5E_FTE_ADDR_OF(headers_c, src_ipv4_src_ipv6.ipv6_layout.ipv6),
+		       ip6src_m, ip6_sz);
+	}
+	if (!ipv6_addr_any((struct in6_addr *)ip6dst_m)) {
+		memcpy(MLX5E_FTE_ADDR_OF(headers_v, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       ip6dst_v, ip6_sz);
+		memcpy(MLX5E_FTE_ADDR_OF(headers_c, dst_ipv4_dst_ipv6.ipv6_layout.ipv6),
+		       ip6dst_m, ip6_sz);
+	}
+
+	MLX5E_FTE_SET(headers_c, ethertype, 0xffff);
+	MLX5E_FTE_SET(headers_v, ethertype, ETH_P_IPV6);
+}
+
 static void
 set_tcp(void *headers_c, void *headers_v, __be16 psrc_m, __be16 psrc_v,
 	__be16 pdst_m, __be16 pdst_v)
@@ -213,6 +239,42 @@ parse_ip4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
 		l3_mask->ip4dst, l3_val->ip4dst);
 }
 
+static void
+parse_ip6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+	struct ethtool_usrip6_spec *l3_val  = &fs->h_u.usr_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l3_mask->ip6src,
+		l3_val->ip6src, l3_mask->ip6dst, l3_val->ip6dst);
+}
+
+static void
+parse_tcp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+	struct ethtool_tcpip6_spec *l4_val  = &fs->h_u.tcp_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l4_mask->ip6src,
+		l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+	set_tcp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
+static void
+parse_udp6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.udp_ip6_spec;
+	struct ethtool_tcpip6_spec *l4_val  = &fs->h_u.udp_ip6_spec;
+
+	set_ip6(headers_c, headers_v, l4_mask->ip6src,
+		l4_val->ip6src, l4_mask->ip6dst, l4_val->ip6dst);
+
+	set_udp(headers_c, headers_v, l4_mask->psrc, l4_val->psrc,
+		l4_mask->pdst, l4_val->pdst);
+}
+
 static void
 parse_ether(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
 {
@@ -264,6 +326,15 @@ static int set_flow_attrs(u32 *match_c, u32 *match_v,
 	case IP_USER_FLOW:
 		parse_ip4(outer_headers_c, outer_headers_v, fs);
 		break;
+	case TCP_V6_FLOW:
+		parse_tcp6(outer_headers_c, outer_headers_v, fs);
+		break;
+	case UDP_V6_FLOW:
+		parse_udp6(outer_headers_c, outer_headers_v, fs);
+		break;
+	case IPV6_USER_FLOW:
+		parse_ip6(outer_headers_c, outer_headers_v, fs);
+		break;
 	case ETHER_FLOW:
 		parse_ether(outer_headers_c, outer_headers_v, fs);
 		break;
@@ -473,6 +544,51 @@ static int validate_ip4(struct ethtool_rx_flow_spec *fs)
 	return ++ntuples;
 }
 
+static int validate_ip6(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
+	int ntuples = 0;
+
+	if (l3_mask->l4_4_bytes || l3_mask->tclass || l3_mask->l4_proto)
+		return -EINVAL;
+	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6src))
+		ntuples++;
+
+	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6dst))
+		ntuples++;
+
+	/* Flow is IPv6 */
+	return ++ntuples;
+}
+
+static int validate_tcpudp6(struct ethtool_rx_flow_spec *fs)
+{
+	struct ethtool_tcpip6_spec *l4_mask = &fs->m_u.tcp_ip6_spec;
+	int ntuples = 0;
+
+	if (l4_mask->tclass)
+		return -EINVAL;
+
+	if (!ipv6_addr_any((struct in6_addr *)l4_mask->ip6src))
+		ntuples++;
+
+	if (!ipv6_addr_any((struct in6_addr *)l4_mask->ip6dst))
+		ntuples++;
+
+	if (l4_mask->psrc) {
+		if (!all_ones(l4_mask->psrc))
+			return -EINVAL;
+		ntuples++;
+	}
+	if (l4_mask->pdst) {
+		if (!all_ones(l4_mask->pdst))
+			return -EINVAL;
+		ntuples++;
+	}
+	/* Flow is TCP/UDP */
+	return ++ntuples;
+}
+
 static int validate_vlan(struct ethtool_rx_flow_spec *fs)
 {
 	if (fs->m_ext.vlan_etype ||
@@ -516,6 +632,19 @@ static int validate_flow(struct mlx5e_priv *priv,
 			return ret;
 		num_tuples += ret;
 		break;
+	case TCP_V6_FLOW:
+	case UDP_V6_FLOW:
+		ret = validate_tcpudp6(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
+		break;
+	case IPV6_USER_FLOW:
+		ret = validate_ip6(fs);
+		if (ret < 0)
+			return ret;
+		num_tuples += ret;
+		break;
 	default:
 		return -ENOTSUPP;
 	}
-- 
cgit v1.2.3


From 974ce34a0c1278957448d83f53ddfc7a565171ec Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Sun, 8 Jul 2018 00:24:21 -0700
Subject: net/mlx5e: Ethtool steering, l4 proto support

Add support for l4 proto ip field in ethtool flow steering.

Example: Redirect icmpv6 to rx queue #2

ethtool -U eth0 flow-type ip6 l4proto 58 action 2

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 .../net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c   | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index c81ab2136cc5..9e216f2dc16a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -237,6 +237,11 @@ parse_ip4(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
 
 	set_ip4(headers_c, headers_v, l3_mask->ip4src, l3_val->ip4src,
 		l3_mask->ip4dst, l3_val->ip4dst);
+
+	if (l3_mask->proto) {
+		MLX5E_FTE_SET(headers_c, ip_protocol, l3_mask->proto);
+		MLX5E_FTE_SET(headers_v, ip_protocol, l3_val->proto);
+	}
 }
 
 static void
@@ -247,6 +252,11 @@ parse_ip6(void *headers_c, void *headers_v, struct ethtool_rx_flow_spec *fs)
 
 	set_ip6(headers_c, headers_v, l3_mask->ip6src,
 		l3_val->ip6src, l3_mask->ip6dst, l3_val->ip6dst);
+
+	if (l3_mask->l4_proto) {
+		MLX5E_FTE_SET(headers_c, ip_protocol, l3_mask->l4_proto);
+		MLX5E_FTE_SET(headers_v, ip_protocol, l3_val->l4_proto);
+	}
 }
 
 static void
@@ -527,7 +537,7 @@ static int validate_ip4(struct ethtool_rx_flow_spec *fs)
 	struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec;
 	int ntuples = 0;
 
-	if (l3_mask->l4_4_bytes || l3_mask->tos || l3_mask->proto ||
+	if (l3_mask->l4_4_bytes || l3_mask->tos ||
 	    fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)
 		return -EINVAL;
 	if (l3_mask->ip4src) {
@@ -540,6 +550,8 @@ static int validate_ip4(struct ethtool_rx_flow_spec *fs)
 			return -EINVAL;
 		ntuples++;
 	}
+	if (l3_mask->proto)
+		ntuples++;
 	/* Flow is IPv4 */
 	return ++ntuples;
 }
@@ -549,14 +561,15 @@ static int validate_ip6(struct ethtool_rx_flow_spec *fs)
 	struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec;
 	int ntuples = 0;
 
-	if (l3_mask->l4_4_bytes || l3_mask->tclass || l3_mask->l4_proto)
+	if (l3_mask->l4_4_bytes || l3_mask->tclass)
 		return -EINVAL;
 	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6src))
 		ntuples++;
 
 	if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6dst))
 		ntuples++;
-
+	if (l3_mask->l4_proto)
+		ntuples++;
 	/* Flow is IPv6 */
 	return ++ntuples;
 }
-- 
cgit v1.2.3


From cff2b1e3e83286e569466663b35bf0ae23afcbcf Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 10 Jul 2018 17:04:49 -0700
Subject: net/mlx5e: Ethtool steering, move ethtool callbacks

Move ethool rxnfc callback into en_fs_etthool file where they belong.
This will allow us to make many ethtool fs related helper functions
static.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 11 +---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   | 48 ----------------
 .../ethernet/mellanox/mlx5/core/en_fs_ethtool.c    | 67 +++++++++++++++++++---
 3 files changed, 62 insertions(+), 64 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index dddd29a3be97..31a29b73f558 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -912,16 +912,11 @@ void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
 void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
 		     u64 *buf);
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-			   int location);
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
-				struct ethtool_rxnfc *info, u32 *rule_locs);
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
-			       struct ethtool_rx_flow_spec *fs);
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
-			      int location);
 void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
 void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
+int mlx5e_get_rxnfc(struct net_device *dev,
+		    struct ethtool_rxnfc *info, u32 *rule_locs);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fffe514ba855..cde1a0bb9c4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -969,33 +969,6 @@ static int mlx5e_set_rxfh(struct net_device *dev, const u32 *indir,
 	return 0;
 }
 
-static int mlx5e_get_rxnfc(struct net_device *netdev,
-			   struct ethtool_rxnfc *info, u32 *rule_locs)
-{
-	struct mlx5e_priv *priv = netdev_priv(netdev);
-	int err = 0;
-
-	switch (info->cmd) {
-	case ETHTOOL_GRXRINGS:
-		info->data = priv->channels.params.num_channels;
-		break;
-	case ETHTOOL_GRXCLSRLCNT:
-		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
-		break;
-	case ETHTOOL_GRXCLSRULE:
-		err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
-		break;
-	case ETHTOOL_GRXCLSRLALL:
-		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
 #define MLX5E_PFC_PREVEN_AUTO_TOUT_MSEC		100
 #define MLX5E_PFC_PREVEN_TOUT_MAX_MSEC		8000
 #define MLX5E_PFC_PREVEN_MINOR_PRECENT		85
@@ -1606,26 +1579,6 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev)
 	return priv->channels.params.pflags;
 }
 
-static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
-{
-	int err = 0;
-	struct mlx5e_priv *priv = netdev_priv(dev);
-
-	switch (cmd->cmd) {
-	case ETHTOOL_SRXCLSRLINS:
-		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
-		break;
-	case ETHTOOL_SRXCLSRLDEL:
-		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
-		break;
-	default:
-		err = -EOPNOTSUPP;
-		break;
-	}
-
-	return err;
-}
-
 int mlx5e_ethtool_flash_device(struct mlx5e_priv *priv,
 			       struct ethtool_flash *flash)
 {
@@ -1696,5 +1649,4 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.self_test         = mlx5e_self_test,
 	.get_msglevel      = mlx5e_get_msglevel,
 	.set_msglevel      = mlx5e_set_msglevel,
-
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 9e216f2dc16a..75bb981e00b7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -675,8 +675,9 @@ static int validate_flow(struct mlx5e_priv *priv,
 	return num_tuples;
 }
 
-int mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
-			       struct ethtool_rx_flow_spec *fs)
+static int
+mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
+			   struct ethtool_rx_flow_spec *fs)
 {
 	struct mlx5e_ethtool_table *eth_ft;
 	struct mlx5e_ethtool_rule *eth_rule;
@@ -723,8 +724,8 @@ del_ethtool_rule:
 	return err;
 }
 
-int mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv,
-			      int location)
+static int
+mlx5e_ethtool_flow_remove(struct mlx5e_priv *priv, int location)
 {
 	struct mlx5e_ethtool_rule *eth_rule;
 	int err = 0;
@@ -743,8 +744,9 @@ out:
 	return err;
 }
 
-int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-			   int location)
+static int
+mlx5e_ethtool_get_flow(struct mlx5e_priv *priv,
+		       struct ethtool_rxnfc *info, int location)
 {
 	struct mlx5e_ethtool_rule *eth_rule;
 
@@ -761,8 +763,9 @@ int mlx5e_ethtool_get_flow(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
 	return -ENOENT;
 }
 
-int mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv, struct ethtool_rxnfc *info,
-				u32 *rule_locs)
+static int
+mlx5e_ethtool_get_all_flows(struct mlx5e_priv *priv,
+			    struct ethtool_rxnfc *info, u32 *rule_locs)
 {
 	int location = 0;
 	int idx = 0;
@@ -791,3 +794,51 @@ void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)
 {
 	INIT_LIST_HEAD(&priv->fs.ethtool.rules);
 }
+
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd)
+{
+	int err = 0;
+	struct mlx5e_priv *priv = netdev_priv(dev);
+
+	switch (cmd->cmd) {
+	case ETHTOOL_SRXCLSRLINS:
+		err = mlx5e_ethtool_flow_replace(priv, &cmd->fs);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		err = mlx5e_ethtool_flow_remove(priv, cmd->fs.location);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
+int mlx5e_get_rxnfc(struct net_device *dev,
+		    struct ethtool_rxnfc *info, u32 *rule_locs)
+{
+	struct mlx5e_priv *priv = netdev_priv(dev);
+	int err = 0;
+
+	switch (info->cmd) {
+	case ETHTOOL_GRXRINGS:
+		info->data = priv->channels.params.num_channels;
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		info->rule_cnt = priv->fs.ethtool.tot_num_rules;
+		break;
+	case ETHTOOL_GRXCLSRULE:
+		err = mlx5e_ethtool_get_flow(priv, info, info->fs.location);
+		break;
+	case ETHTOOL_GRXCLSRLALL:
+		err = mlx5e_ethtool_get_all_flows(priv, info, rule_locs);
+		break;
+	default:
+		err = -EOPNOTSUPP;
+		break;
+	}
+
+	return err;
+}
+
-- 
cgit v1.2.3


From fe6d86b3c3165e6c55d6b0049a13d3b65371163a Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Wed, 11 Jul 2018 12:02:42 -0700
Subject: net/mlx5e: Add CONFIG_MLX5_EN_RXNFC for ethtool rx nfc

Add new mlx5 Kconfig flag to allow selecting ethtool rx nfc support,
and compile out en_fs_ehtool.c if not selected.

Add en/fs.h header file to host all steering declarations and
definitions.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    | 10 +++++++
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |  4 ++-
 drivers/net/ethernet/mellanox/mlx5/core/en.h       | 23 ++------------
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h    | 35 ++++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  2 ++
 5 files changed, 53 insertions(+), 21 deletions(-)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 7a84dd07ced2..1ff5f12ab12d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -35,6 +35,16 @@ config MLX5_CORE_EN
 	---help---
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
 
+config MLX5_EN_RXNFC
+	bool "Mellanox MLX5 ethernet rx nfc flow steering support"
+	depends on MLX5_CORE_EN
+	default y
+	---help---
+	  Mellanox MLX5 ethernet rx nfc flow steering support
+	  Enables ethtool receive network flow classification, which allows user defined
+	  flow rules to direct traffic into arbitrary rx queue via ethtool set/get_rxnfc
+	  API.
+
 config MLX5_MPFS
         bool "Mellanox Technologies MLX5 MPFS support"
         depends on MLX5_CORE_EN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index f20fda1ced4f..7b6f9d2c32c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -15,7 +15,9 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_arfs.o en_fs_ethtool.o en_selftest.o en/port.o lib/vxlan.o
+		en_arfs.o en_selftest.o en/port.o lib/vxlan.o
+
+mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 31a29b73f558..19728f9f25e7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -52,6 +52,7 @@
 #include "wq.h"
 #include "mlx5_core.h"
 #include "en_stats.h"
+#include "en/fs.h"
 
 struct page_pool;
 
@@ -746,24 +747,11 @@ enum {
 	MLX5E_TC_TTC_FT_LEVEL,
 };
 
-struct mlx5e_ethtool_table {
-	struct mlx5_flow_table *ft;
-	int                    num_rules;
-};
-
-#define ETHTOOL_NUM_L3_L4_FTS 7
-#define ETHTOOL_NUM_L2_FTS 4
-
-struct mlx5e_ethtool_steering {
-	struct mlx5e_ethtool_table      l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
-	struct mlx5e_ethtool_table      l2_ft[ETHTOOL_NUM_L2_FTS];
-	struct list_head                rules;
-	int                             tot_num_rules;
-};
-
 struct mlx5e_flow_steering {
 	struct mlx5_flow_namespace      *ns;
+#ifdef CONFIG_MLX5_EN_RXNFC
 	struct mlx5e_ethtool_steering   ethtool;
+#endif
 	struct mlx5e_tc_table           tc;
 	struct mlx5e_vlan_table         vlan;
 	struct mlx5e_l2_table           l2;
@@ -912,11 +900,6 @@ void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
 void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
 		     u64 *buf);
-void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
-void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
-int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
-int mlx5e_get_rxnfc(struct net_device *dev,
-		    struct ethtool_rxnfc *info, u32 *rule_locs);
 void mlx5e_set_rx_mode_work(struct work_struct *work);
 
 int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
new file mode 100644
index 000000000000..50b0784787bc
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2018 Mellanox Technologies. */
+
+#ifndef __MLX5E_FLOW_STEER_H__
+#define __MLX5E_FLOW_STEER_H__
+
+#ifdef CONFIG_MLX5_EN_RXNFC
+
+struct mlx5e_ethtool_table {
+	struct mlx5_flow_table *ft;
+	int                    num_rules;
+};
+
+#define ETHTOOL_NUM_L3_L4_FTS 7
+#define ETHTOOL_NUM_L2_FTS 4
+
+struct mlx5e_ethtool_steering {
+	struct mlx5e_ethtool_table      l3_l4_ft[ETHTOOL_NUM_L3_L4_FTS];
+	struct mlx5e_ethtool_table      l2_ft[ETHTOOL_NUM_L2_FTS];
+	struct list_head                rules;
+	int                             tot_num_rules;
+};
+
+void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv);
+void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv);
+int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd);
+int mlx5e_get_rxnfc(struct net_device *dev,
+		    struct ethtool_rxnfc *info, u32 *rule_locs);
+#else
+static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)    { }
+static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { }
+#endif /* CONFIG_MLX5_EN_RXNFC */
+
+#endif /* __MLX5E_FLOW_STEER_H__ */
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cde1a0bb9c4a..7787cc3a2c84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1631,8 +1631,10 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 	.get_rxfh_indir_size = mlx5e_get_rxfh_indir_size,
 	.get_rxfh          = mlx5e_get_rxfh,
 	.set_rxfh          = mlx5e_set_rxfh,
+#ifdef CONFIG_MLX5_EN_RXNFC
 	.get_rxnfc         = mlx5e_get_rxnfc,
 	.set_rxnfc         = mlx5e_set_rxnfc,
+#endif
 	.flash_device      = mlx5e_flash_device,
 	.get_tunable       = mlx5e_get_tunable,
 	.set_tunable       = mlx5e_set_tunable,
-- 
cgit v1.2.3


From ec080045977073c5e69a7fddee3a8aef9bf62881 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 12 Jul 2018 03:01:26 -0700
Subject: net/mlx5e: Add CONFIG_MLX5_EN_ARFS for accelerated flow steering
 support

Add new mlx5 Kconfig flag to allow selecting accelerated flow steering
support, and compile out en_arfs.c if not selected.

Move arfs declarations and definitions to en/fs.h header file.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig   |  8 +++
 drivers/net/ethernet/mellanox/mlx5/core/Makefile  |  3 +-
 drivers/net/ethernet/mellanox/mlx5/core/en.h      | 61 ++---------------------
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h   | 46 +++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c |  4 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 14 +++---
 6 files changed, 68 insertions(+), 68 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 1ff5f12ab12d..01f9ba1a2098 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -35,6 +35,14 @@ config MLX5_CORE_EN
 	---help---
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
 
+config MLX5_EN_ARFS
+	bool "Mellanox MLX5 ethernet accelerated receive flow steering (ARFS) support"
+	depends on MLX5_CORE_EN && RFS_ACCEL
+	default y
+	---help---
+	  Mellanox MLX5 ethernet hardware-accelerated receive flow steering support,
+	  Enables ethernet netdevice arfs support and ntuple filtering.
+
 config MLX5_EN_RXNFC
 	bool "Mellanox MLX5 ethernet rx nfc flow steering support"
 	depends on MLX5_CORE_EN
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 7b6f9d2c32c9..ae9da4b51487 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -15,8 +15,9 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_arfs.o en_selftest.o en/port.o lib/vxlan.o
+		en_selftest.o en/port.o lib/vxlan.o
 
+mlx5_core-$(CONFIG_MLX5_EN_ARFS)  += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
 
 mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 19728f9f25e7..8743bbe1baa2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -660,12 +660,6 @@ struct mlx5e_l2_rule {
 	struct mlx5_flow_handle *rule;
 };
 
-struct mlx5e_flow_table {
-	int num_groups;
-	struct mlx5_flow_table *t;
-	struct mlx5_flow_group **g;
-};
-
 #define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
 
 struct mlx5e_tc_table {
@@ -708,38 +702,15 @@ struct mlx5e_ttc_table {
 	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
 };
 
-#define ARFS_HASH_SHIFT BITS_PER_BYTE
-#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
-struct arfs_table {
-	struct mlx5e_flow_table  ft;
-	struct mlx5_flow_handle	 *default_rule;
-	struct hlist_head	 rules_hash[ARFS_HASH_SIZE];
-};
-
-enum  arfs_type {
-	ARFS_IPV4_TCP,
-	ARFS_IPV6_TCP,
-	ARFS_IPV4_UDP,
-	ARFS_IPV6_UDP,
-	ARFS_NUM_TYPES,
-};
-
-struct mlx5e_arfs_tables {
-	struct arfs_table arfs_tables[ARFS_NUM_TYPES];
-	/* Protect aRFS rules list */
-	spinlock_t                     arfs_lock;
-	struct list_head               rules;
-	int                            last_filter_id;
-	struct workqueue_struct        *wq;
-};
-
 /* NIC prio FTS */
 enum {
 	MLX5E_VLAN_FT_LEVEL = 0,
 	MLX5E_L2_FT_LEVEL,
 	MLX5E_TTC_FT_LEVEL,
 	MLX5E_INNER_TTC_FT_LEVEL,
+#ifdef CONFIG_MLX5_EN_ARFS
 	MLX5E_ARFS_FT_LEVEL
+#endif
 };
 
 enum {
@@ -757,7 +728,9 @@ struct mlx5e_flow_steering {
 	struct mlx5e_l2_table           l2;
 	struct mlx5e_ttc_table          ttc;
 	struct mlx5e_ttc_table          inner_ttc;
+#ifdef CONFIG_MLX5_EN_ARFS
 	struct mlx5e_arfs_tables        arfs;
+#endif
 };
 
 struct mlx5e_rqt {
@@ -1028,32 +1001,6 @@ void mlx5e_dcbnl_init_app(struct mlx5e_priv *priv);
 void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv);
 #endif
 
-#ifndef CONFIG_RFS_ACCEL
-static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv)
-{
-	return 0;
-}
-
-static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
-
-static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv)
-{
-	return -EOPNOTSUPP;
-}
-
-static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv)
-{
-	return -EOPNOTSUPP;
-}
-#else
-int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
-void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
-int mlx5e_arfs_enable(struct mlx5e_priv *priv);
-int mlx5e_arfs_disable(struct mlx5e_priv *priv);
-int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
-			u16 rxq_index, u32 flow_id);
-#endif
-
 int mlx5e_create_tir(struct mlx5_core_dev *mdev,
 		     struct mlx5e_tir *tir, u32 *in, int inlen);
 void mlx5e_destroy_tir(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 50b0784787bc..adc00ae7e9e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -4,6 +4,12 @@
 #ifndef __MLX5E_FLOW_STEER_H__
 #define __MLX5E_FLOW_STEER_H__
 
+struct mlx5e_flow_table {
+	int num_groups;
+	struct mlx5_flow_table *t;
+	struct mlx5_flow_group **g;
+};
+
 #ifdef CONFIG_MLX5_EN_RXNFC
 
 struct mlx5e_ethtool_table {
@@ -31,5 +37,45 @@ static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv)    { }
 static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { }
 #endif /* CONFIG_MLX5_EN_RXNFC */
 
+#ifdef CONFIG_MLX5_EN_ARFS
+#define ARFS_HASH_SHIFT BITS_PER_BYTE
+#define ARFS_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct arfs_table {
+	struct mlx5e_flow_table  ft;
+	struct mlx5_flow_handle	 *default_rule;
+	struct hlist_head	 rules_hash[ARFS_HASH_SIZE];
+};
+
+enum  arfs_type {
+	ARFS_IPV4_TCP,
+	ARFS_IPV6_TCP,
+	ARFS_IPV4_UDP,
+	ARFS_IPV6_UDP,
+	ARFS_NUM_TYPES,
+};
+
+struct mlx5e_arfs_tables {
+	struct arfs_table arfs_tables[ARFS_NUM_TYPES];
+	/* Protect aRFS rules list */
+	spinlock_t                     arfs_lock;
+	struct list_head               rules;
+	int                            last_filter_id;
+	struct workqueue_struct        *wq;
+};
+
+int mlx5e_arfs_create_tables(struct mlx5e_priv *priv);
+void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv);
+int mlx5e_arfs_enable(struct mlx5e_priv *priv);
+int mlx5e_arfs_disable(struct mlx5e_priv *priv);
+int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
+			u16 rxq_index, u32 flow_id);
+#else
+static inline int mlx5e_arfs_create_tables(struct mlx5e_priv *priv) { return 0; }
+static inline void mlx5e_arfs_destroy_tables(struct mlx5e_priv *priv) {}
+static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv) { return -EOPNOTSUPP; }
+static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv) {	return -EOPNOTSUPP; }
+#endif
+
 #endif /* __MLX5E_FLOW_STEER_H__ */
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
index d258bb679271..45cdde694d20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c
@@ -30,8 +30,6 @@
  * SOFTWARE.
  */
 
-#ifdef CONFIG_RFS_ACCEL
-
 #include <linux/hash.h>
 #include <linux/mlx5/fs.h>
 #include <linux/ip.h>
@@ -738,4 +736,4 @@ int mlx5e_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb,
 	spin_unlock_bh(&arfs->arfs_lock);
 	return arfs_rule->filter_id;
 }
-#endif
+
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2731ba2d8049..e09086f41365 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3624,7 +3624,7 @@ unlock:
 	return err;
 }
 
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 static int set_feature_arfs(struct net_device *netdev, bool enable)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
@@ -3679,7 +3679,7 @@ static int mlx5e_set_features(struct net_device *netdev,
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXALL, set_feature_rx_all);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_RXFCS, set_feature_rx_fcs);
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 	err |= MLX5E_HANDLE_FEATURE(NETIF_F_NTUPLE, set_feature_arfs);
 #endif
 
@@ -4348,12 +4348,12 @@ static const struct net_device_ops mlx5e_netdev_ops = {
 	.ndo_udp_tunnel_add      = mlx5e_add_vxlan_port,
 	.ndo_udp_tunnel_del      = mlx5e_del_vxlan_port,
 	.ndo_features_check      = mlx5e_features_check,
-#ifdef CONFIG_RFS_ACCEL
-	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
-#endif
 	.ndo_tx_timeout          = mlx5e_tx_timeout,
 	.ndo_bpf		 = mlx5e_xdp,
 	.ndo_xdp_xmit            = mlx5e_xdp_xmit,
+#ifdef CONFIG_MLX5_EN_ARFS
+	.ndo_rx_flow_steer	 = mlx5e_rx_flow_steer,
+#endif
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller     = mlx5e_netpoll,
 #endif
@@ -4703,7 +4703,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev)
 	    FT_CAP(identified_miss_table_mode) &&
 	    FT_CAP(flow_table_modify)) {
 		netdev->hw_features      |= NETIF_F_HW_TC;
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 		netdev->hw_features	 |= NETIF_F_NTUPLE;
 #endif
 	}
@@ -4947,7 +4947,7 @@ struct net_device *mlx5e_create_netdev(struct mlx5_core_dev *mdev,
 		return NULL;
 	}
 
-#ifdef CONFIG_RFS_ACCEL
+#ifdef CONFIG_MLX5_EN_ARFS
 	netdev->rx_cpu_rmap = mdev->rmap;
 #endif
 
-- 
cgit v1.2.3


From 44f68ae0cad6afbd72d3de1c7b0e149c1655b626 Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Thu, 12 Jul 2018 03:09:19 -0700
Subject: net/mlx5e: Move flow steering declarations into en/fs.h

Move flow steering declarations and definitions into the dedicated
en/fs.h header file

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h    | 126 -----------------------
 drivers/net/ethernet/mellanox/mlx5/core/en/fs.h | 129 ++++++++++++++++++++++++
 2 files changed, 129 insertions(+), 126 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8743bbe1baa2..db2cfcd21d43 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -627,112 +627,12 @@ struct mlx5e_channel_stats {
 	struct mlx5e_xdpsq_stats xdpsq;
 } ____cacheline_aligned_in_smp;
 
-enum mlx5e_traffic_types {
-	MLX5E_TT_IPV4_TCP,
-	MLX5E_TT_IPV6_TCP,
-	MLX5E_TT_IPV4_UDP,
-	MLX5E_TT_IPV6_UDP,
-	MLX5E_TT_IPV4_IPSEC_AH,
-	MLX5E_TT_IPV6_IPSEC_AH,
-	MLX5E_TT_IPV4_IPSEC_ESP,
-	MLX5E_TT_IPV6_IPSEC_ESP,
-	MLX5E_TT_IPV4,
-	MLX5E_TT_IPV6,
-	MLX5E_TT_ANY,
-	MLX5E_NUM_TT,
-	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
-};
-
-enum mlx5e_tunnel_types {
-	MLX5E_TT_IPV4_GRE,
-	MLX5E_TT_IPV6_GRE,
-	MLX5E_NUM_TUNNEL_TT,
-};
-
 enum {
 	MLX5E_STATE_ASYNC_EVENTS_ENABLED,
 	MLX5E_STATE_OPENED,
 	MLX5E_STATE_DESTROYING,
 };
 
-struct mlx5e_l2_rule {
-	u8  addr[ETH_ALEN + 2];
-	struct mlx5_flow_handle *rule;
-};
-
-#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
-
-struct mlx5e_tc_table {
-	struct mlx5_flow_table		*t;
-
-	struct rhashtable               ht;
-
-	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
-	DECLARE_HASHTABLE(hairpin_tbl, 8);
-};
-
-struct mlx5e_vlan_table {
-	struct mlx5e_flow_table		ft;
-	DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
-	DECLARE_BITMAP(active_svlans, VLAN_N_VID);
-	struct mlx5_flow_handle	*active_cvlans_rule[VLAN_N_VID];
-	struct mlx5_flow_handle	*active_svlans_rule[VLAN_N_VID];
-	struct mlx5_flow_handle	*untagged_rule;
-	struct mlx5_flow_handle	*any_cvlan_rule;
-	struct mlx5_flow_handle	*any_svlan_rule;
-	bool			cvlan_filter_disabled;
-};
-
-struct mlx5e_l2_table {
-	struct mlx5e_flow_table    ft;
-	struct hlist_head          netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
-	struct hlist_head          netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
-	struct mlx5e_l2_rule	   broadcast;
-	struct mlx5e_l2_rule	   allmulti;
-	struct mlx5e_l2_rule	   promisc;
-	bool                       broadcast_enabled;
-	bool                       allmulti_enabled;
-	bool                       promisc_enabled;
-};
-
-/* L3/L4 traffic type classifier */
-struct mlx5e_ttc_table {
-	struct mlx5e_flow_table  ft;
-	struct mlx5_flow_handle	 *rules[MLX5E_NUM_TT];
-	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
-};
-
-/* NIC prio FTS */
-enum {
-	MLX5E_VLAN_FT_LEVEL = 0,
-	MLX5E_L2_FT_LEVEL,
-	MLX5E_TTC_FT_LEVEL,
-	MLX5E_INNER_TTC_FT_LEVEL,
-#ifdef CONFIG_MLX5_EN_ARFS
-	MLX5E_ARFS_FT_LEVEL
-#endif
-};
-
-enum {
-	MLX5E_TC_FT_LEVEL = 0,
-	MLX5E_TC_TTC_FT_LEVEL,
-};
-
-struct mlx5e_flow_steering {
-	struct mlx5_flow_namespace      *ns;
-#ifdef CONFIG_MLX5_EN_RXNFC
-	struct mlx5e_ethtool_steering   ethtool;
-#endif
-	struct mlx5e_tc_table           tc;
-	struct mlx5e_vlan_table         vlan;
-	struct mlx5e_l2_table           l2;
-	struct mlx5e_ttc_table          ttc;
-	struct mlx5e_ttc_table          inner_ttc;
-#ifdef CONFIG_MLX5_EN_ARFS
-	struct mlx5e_arfs_tables        arfs;
-#endif
-};
-
 struct mlx5e_rqt {
 	u32              rqtn;
 	bool		 enabled;
@@ -866,10 +766,7 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe,
 
 void mlx5e_update_stats(struct mlx5e_priv *priv);
 
-int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
 void mlx5e_init_l2_addr(struct mlx5e_priv *priv);
-void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
 int mlx5e_self_test_num(struct mlx5e_priv *priv);
 void mlx5e_self_test(struct net_device *ndev, struct ethtool_test *etest,
 		     u64 *buf);
@@ -883,8 +780,6 @@ int mlx5e_vlan_rx_add_vid(struct net_device *dev, __always_unused __be16 proto,
 			  u16 vid);
 int mlx5e_vlan_rx_kill_vid(struct net_device *dev, __always_unused __be16 proto,
 			   u16 vid);
-void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
-void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
 void mlx5e_timestamp_init(struct mlx5e_priv *priv);
 
 struct mlx5e_redirect_rqt_param {
@@ -1021,27 +916,6 @@ int mlx5e_create_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_direct_tirs(struct mlx5e_priv *priv);
 void mlx5e_destroy_rqt(struct mlx5e_priv *priv, struct mlx5e_rqt *rqt);
 
-struct ttc_params {
-	struct mlx5_flow_table_attr ft_attr;
-	u32 any_tt_tirn;
-	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
-	struct mlx5e_ttc_table *inner_ttc;
-};
-
-void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
-void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
-void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
-
-int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-			   struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
-			     struct mlx5e_ttc_table *ttc);
-
-int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
-				 struct mlx5e_ttc_table *ttc);
-void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
-				   struct mlx5e_ttc_table *ttc);
-
 int mlx5e_create_tis(struct mlx5_core_dev *mdev, int tc,
 		     u32 underlay_qpn, u32 *tisn);
 void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index adc00ae7e9e9..bbf69e859b78 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -4,12 +4,97 @@
 #ifndef __MLX5E_FLOW_STEER_H__
 #define __MLX5E_FLOW_STEER_H__
 
+enum {
+	MLX5E_TC_FT_LEVEL = 0,
+	MLX5E_TC_TTC_FT_LEVEL,
+};
+
+struct mlx5e_tc_table {
+	struct mlx5_flow_table		*t;
+
+	struct rhashtable               ht;
+
+	DECLARE_HASHTABLE(mod_hdr_tbl, 8);
+	DECLARE_HASHTABLE(hairpin_tbl, 8);
+};
+
 struct mlx5e_flow_table {
 	int num_groups;
 	struct mlx5_flow_table *t;
 	struct mlx5_flow_group **g;
 };
 
+struct mlx5e_l2_rule {
+	u8  addr[ETH_ALEN + 2];
+	struct mlx5_flow_handle *rule;
+};
+
+#define MLX5E_L2_ADDR_HASH_SIZE BIT(BITS_PER_BYTE)
+
+struct mlx5e_vlan_table {
+	struct mlx5e_flow_table		ft;
+	DECLARE_BITMAP(active_cvlans, VLAN_N_VID);
+	DECLARE_BITMAP(active_svlans, VLAN_N_VID);
+	struct mlx5_flow_handle	*active_cvlans_rule[VLAN_N_VID];
+	struct mlx5_flow_handle	*active_svlans_rule[VLAN_N_VID];
+	struct mlx5_flow_handle	*untagged_rule;
+	struct mlx5_flow_handle	*any_cvlan_rule;
+	struct mlx5_flow_handle	*any_svlan_rule;
+	bool			cvlan_filter_disabled;
+};
+
+struct mlx5e_l2_table {
+	struct mlx5e_flow_table    ft;
+	struct hlist_head          netdev_uc[MLX5E_L2_ADDR_HASH_SIZE];
+	struct hlist_head          netdev_mc[MLX5E_L2_ADDR_HASH_SIZE];
+	struct mlx5e_l2_rule	   broadcast;
+	struct mlx5e_l2_rule	   allmulti;
+	struct mlx5e_l2_rule	   promisc;
+	bool                       broadcast_enabled;
+	bool                       allmulti_enabled;
+	bool                       promisc_enabled;
+};
+
+enum mlx5e_traffic_types {
+	MLX5E_TT_IPV4_TCP,
+	MLX5E_TT_IPV6_TCP,
+	MLX5E_TT_IPV4_UDP,
+	MLX5E_TT_IPV6_UDP,
+	MLX5E_TT_IPV4_IPSEC_AH,
+	MLX5E_TT_IPV6_IPSEC_AH,
+	MLX5E_TT_IPV4_IPSEC_ESP,
+	MLX5E_TT_IPV6_IPSEC_ESP,
+	MLX5E_TT_IPV4,
+	MLX5E_TT_IPV6,
+	MLX5E_TT_ANY,
+	MLX5E_NUM_TT,
+	MLX5E_NUM_INDIR_TIRS = MLX5E_TT_ANY,
+};
+
+enum mlx5e_tunnel_types {
+	MLX5E_TT_IPV4_GRE,
+	MLX5E_TT_IPV6_GRE,
+	MLX5E_NUM_TUNNEL_TT,
+};
+
+/* L3/L4 traffic type classifier */
+struct mlx5e_ttc_table {
+	struct mlx5e_flow_table  ft;
+	struct mlx5_flow_handle	 *rules[MLX5E_NUM_TT];
+	struct mlx5_flow_handle  *tunnel_rules[MLX5E_NUM_TUNNEL_TT];
+};
+
+/* NIC prio FTS */
+enum {
+	MLX5E_VLAN_FT_LEVEL = 0,
+	MLX5E_L2_FT_LEVEL,
+	MLX5E_TTC_FT_LEVEL,
+	MLX5E_INNER_TTC_FT_LEVEL,
+#ifdef CONFIG_MLX5_EN_ARFS
+	MLX5E_ARFS_FT_LEVEL
+#endif
+};
+
 #ifdef CONFIG_MLX5_EN_RXNFC
 
 struct mlx5e_ethtool_table {
@@ -77,5 +162,49 @@ static inline int mlx5e_arfs_enable(struct mlx5e_priv *priv) { return -EOPNOTSUP
 static inline int mlx5e_arfs_disable(struct mlx5e_priv *priv) {	return -EOPNOTSUPP; }
 #endif
 
+struct mlx5e_flow_steering {
+	struct mlx5_flow_namespace      *ns;
+#ifdef CONFIG_MLX5_EN_RXNFC
+	struct mlx5e_ethtool_steering   ethtool;
+#endif
+	struct mlx5e_tc_table           tc;
+	struct mlx5e_vlan_table         vlan;
+	struct mlx5e_l2_table           l2;
+	struct mlx5e_ttc_table          ttc;
+	struct mlx5e_ttc_table          inner_ttc;
+#ifdef CONFIG_MLX5_EN_ARFS
+	struct mlx5e_arfs_tables        arfs;
+#endif
+};
+
+struct ttc_params {
+	struct mlx5_flow_table_attr ft_attr;
+	u32 any_tt_tirn;
+	u32 indir_tirn[MLX5E_NUM_INDIR_TIRS];
+	struct mlx5e_ttc_table *inner_ttc;
+};
+
+void mlx5e_set_ttc_basic_params(struct mlx5e_priv *priv, struct ttc_params *ttc_params);
+void mlx5e_set_ttc_ft_params(struct ttc_params *ttc_params);
+void mlx5e_set_inner_ttc_ft_params(struct ttc_params *ttc_params);
+
+int mlx5e_create_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+			   struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_ttc_table(struct mlx5e_priv *priv,
+			     struct mlx5e_ttc_table *ttc);
+
+int mlx5e_create_inner_ttc_table(struct mlx5e_priv *priv, struct ttc_params *params,
+				 struct mlx5e_ttc_table *ttc);
+void mlx5e_destroy_inner_ttc_table(struct mlx5e_priv *priv,
+				   struct mlx5e_ttc_table *ttc);
+
+void mlx5e_destroy_flow_table(struct mlx5e_flow_table *ft);
+
+void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
+void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
+
+int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
+void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv);
+
 #endif /* __MLX5E_FLOW_STEER_H__ */
 
-- 
cgit v1.2.3


From c5791ab0abecb5e4a41673b83e3660f731b0717b Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Fri, 13 Jul 2018 10:58:49 -0700
Subject: net/mlx5e: vxlan.c depends on CONFIG_VXLAN

When vxlan is not enabled by kernel, no need to enable it in mlx5.
Compile out lib/vxlan.c if CONFIG_VXLAN is not selected.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Moshe Shemesh <moshe@mellanox.com>
Reviewed-by: Eran Ben Elisha <eranbe@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig     |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/Makefile    |  7 ++++---
 drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h | 12 ++++++------
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index 01f9ba1a2098..37a551436e4a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -7,6 +7,7 @@ config MLX5_CORE
 	depends on MAY_USE_DEVLINK
 	depends on PCI
 	imply PTP_1588_CLOCK
+	imply VXLAN
 	default n
 	---help---
 	  Core driver for low level functionality of the ConnectX-4 and
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index ae9da4b51487..09b5e235527b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -13,15 +13,16 @@ mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
 mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 		fpga/ipsec.o fpga/tls.o
 
+mlx5_core-$(CONFIG_MLX5_MPFS)  += lib/mpfs.o
+mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
+
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
-		en_selftest.o en/port.o lib/vxlan.o
+		en_selftest.o en/port.o
 
 mlx5_core-$(CONFIG_MLX5_EN_ARFS)  += en_arfs.o
 mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
 
-mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o
-
 mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o en/port_buffer.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
index fd874a30c4d0..8fb0eb08fa6d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.h
@@ -37,8 +37,6 @@
 struct mlx5_vxlan;
 struct mlx5_vxlan_port;
 
-#ifdef CONFIG_MLX5_CORE_EN
-
 static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
 {
 	/* not allowed reason is encoded in vxlan pointer as error,
@@ -47,18 +45,20 @@ static inline bool mlx5_vxlan_allowed(struct mlx5_vxlan *vxlan)
 	return !IS_ERR_OR_NULL(vxlan);
 }
 
+#if IS_ENABLED(CONFIG_VXLAN)
 struct mlx5_vxlan *mlx5_vxlan_create(struct mlx5_core_dev *mdev);
 void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan);
 int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port);
 int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port);
 struct mlx5_vxlan_port *mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port);
-
 #else
-
 static inline struct mlx5_vxlan*
-mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-ENOTSUPP); }
+mlx5_vxlan_create(struct mlx5_core_dev *mdev) { return ERR_PTR(-EOPNOTSUPP); }
 static inline void mlx5_vxlan_destroy(struct mlx5_vxlan *vxlan) { return; }
-
+static inline int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) { return -EOPNOTSUPP; }
+static inline struct mx5_vxlan_port*
+mlx5_vxlan_lookup_port(struct mlx5_vxlan *vxlan, u16 port) { return NULL; }
 #endif
 
 #endif /* __MLX5_VXLAN_H__ */
-- 
cgit v1.2.3


From 6dbc80ca41f5a76e0d2ae4e96b2476d68a2ea17f Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@mellanox.com>
Date: Sun, 29 Jul 2018 13:29:45 +0300
Subject: net/mlx5e: clock.c depends on CONFIG_PTP_1588_CLOCK

lib/clock.c includes clock related functions which require ptp support.
Thus compile out lib/clock.c and add the needed function stubs in case
kconfig CONFIG_PTP_1588_CLOCK is off.

Signed-off-by: Moshe Shemesh <moshe@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |  3 ++-
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c   |  7 ++++---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c  |  4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/eq.c       |  1 +
 .../net/ethernet/mellanox/mlx5/core/lib/clock.h    | 24 ++++++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |  1 -
 6 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 09b5e235527b..9e78c48b22dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -5,7 +5,7 @@ subdir-ccflags-y += -I$(src)
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
-		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \
+		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o  \
 		diag/fs_tracepoint.o diag/fw_tracer.o
 
 mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
@@ -15,6 +15,7 @@ mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
 
 mlx5_core-$(CONFIG_MLX5_MPFS)  += lib/mpfs.o
 mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
+mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
 
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 7787cc3a2c84..98dd3e0ada72 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -32,6 +32,7 @@
 
 #include "en.h"
 #include "en/port.h"
+#include "lib/clock.h"
 
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
@@ -1106,10 +1107,10 @@ int mlx5e_ethtool_get_ts_info(struct mlx5e_priv *priv,
 	if (ret)
 		return ret;
 
-	info->phc_index = mdev->clock.ptp ?
-			  ptp_clock_index(mdev->clock.ptp) : -1;
+	info->phc_index = mlx5_clock_get_ptp_index(mdev);
 
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+	    info->phc_index == -1)
 		return 0;
 
 	info->so_timestamping |= SOF_TIMESTAMPING_TX_HARDWARE |
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index e09086f41365..5a7939e70190 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -46,6 +46,7 @@
 #include "accel/ipsec.h"
 #include "accel/tls.h"
 #include "lib/vxlan.h"
+#include "lib/clock.h"
 #include "en/port.h"
 #include "en/xdp.h"
 
@@ -3782,7 +3783,8 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr)
 	struct hwtstamp_config config;
 	int err;
 
-	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz))
+	if (!MLX5_CAP_GEN(priv->mdev, device_frequency_khz) ||
+	    (mlx5_clock_get_ptp_index(priv->mdev) == -1))
 		return -EOPNOTSUPP;
 
 	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 7669b4380779..48864f4988a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -40,6 +40,7 @@
 #include "mlx5_core.h"
 #include "fpga/core.h"
 #include "eswitch.h"
+#include "lib/clock.h"
 #include "diag/fw_tracer.h"
 
 enum {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index a8eecedd46c2..02e2e4575e4f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,8 +33,15 @@
 #ifndef __LIB_CLOCK_H__
 #define __LIB_CLOCK_H__
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 void mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+	return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+}
 
 static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 						u64 timestamp)
@@ -48,4 +55,21 @@ static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
 	return ns_to_ktime(nsec);
 }
 
+#else
+static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe) {}
+
+static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
+{
+	return -1;
+}
+
+static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
+						u64 timestamp)
+{
+	return 0;
+}
+#endif
+
 #endif
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 49955117ae36..b4134fa0bba3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -99,7 +99,6 @@ void mlx5_core_event(struct mlx5_core_dev *dev, enum mlx5_dev_event event,
 		     unsigned long param);
 void mlx5_core_page_fault(struct mlx5_core_dev *dev,
 			  struct mlx5_pagefault *pfault);
-void mlx5_pps_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_port_module_event(struct mlx5_core_dev *dev, struct mlx5_eqe *eqe);
 void mlx5_enter_error_state(struct mlx5_core_dev *dev, bool force);
 void mlx5_disable_device(struct mlx5_core_dev *dev);
-- 
cgit v1.2.3


From a8274b854b5e7c78187d7b9eaf701e1f6e1ccfcb Mon Sep 17 00:00:00 2001
From: Saeed Mahameed <saeedm@mellanox.com>
Date: Tue, 31 Jul 2018 14:44:00 -0700
Subject: net/mlx5: Reorganize the makefile

Reorganize the Makefile and group files together according to their
functionality and importance.

Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile | 57 +++++++++++++++++-------
 1 file changed, 40 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index 9e78c48b22dd..d324a3884462 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -1,38 +1,61 @@
 # SPDX-License-Identifier: GPL-2.0
-obj-$(CONFIG_MLX5_CORE)		+= mlx5_core.o
+#
+# Makefile for Mellanox 5th generation network adapters
+# (ConnectX series) core & netdev driver
+#
+
 subdir-ccflags-y += -I$(src)
 
+obj-$(CONFIG_MLX5_CORE) += mlx5_core.o
+
+#
+# mlx5 core basic
+#
 mlx5_core-y :=	main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \
 		health.o mcg.o cq.o srq.o alloc.o qp.o port.o mr.o pd.o \
 		mad.o transobj.o vport.o sriov.o fs_cmd.o fs_core.o \
 		fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o  \
 		diag/fs_tracepoint.o diag/fw_tracer.o
 
-mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
-
-mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
-		fpga/ipsec.o fpga/tls.o
-
-mlx5_core-$(CONFIG_MLX5_MPFS)  += lib/mpfs.o
-mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o
-mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
-
+#
+# Netdev basic
+#
 mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \
 		en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \
 		en_selftest.o en/port.o
 
-mlx5_core-$(CONFIG_MLX5_EN_ARFS)  += en_arfs.o
-mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o
+#
+# Netdev extra
+#
+mlx5_core-$(CONFIG_MLX5_EN_ARFS)     += en_arfs.o
+mlx5_core-$(CONFIG_MLX5_EN_RXNFC)    += en_fs_ethtool.o
+mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o
+mlx5_core-$(CONFIG_MLX5_ESWITCH)     += en_rep.o en_tc.o
+
+#
+# Core extra
+#
+mlx5_core-$(CONFIG_MLX5_ESWITCH)   += eswitch.o eswitch_offloads.o
+mlx5_core-$(CONFIG_MLX5_MPFS)      += lib/mpfs.o
+mlx5_core-$(CONFIG_VXLAN)          += lib/vxlan.o
+mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o
 
-mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o en_rep.o en_tc.o
+#
+# Ipoib netdev
+#
+mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) +=  en_dcbnl.o en/port_buffer.o
+#
+# Accelerations & FPGA
+#
+mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o
 
-mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib_vlan.o
+mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \
+				 fpga/ipsec.o fpga/tls.o
 
 mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \
-		en_accel/ipsec_stats.o
+				     en_accel/ipsec_stats.o
 
-mlx5_core-$(CONFIG_MLX5_EN_TLS) +=  en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
+mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o
 
 CFLAGS_tracepoint.o := -I$(src)
-- 
cgit v1.2.3


From cf916ffbe0c628bb072ea829f300cff1874162ce Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.com>
Date: Sun, 29 Apr 2018 09:17:34 -0500
Subject: net/mlx5: Improve argument name for add flow API

The last argument to mlx5_add_flow_rules passes the number of
destinations in the struct pointed to by the dest arg. Change the name
to better reflect this fact.

Signed-off-by: Eli Cohen <eli@mellanox.com>
Reviewed-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 8 ++++----
 include/linux/mlx5/fs.h                           | 2 +-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a21df24b695e..261cb6aacf12 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1876,7 +1876,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		    struct mlx5_flow_spec *spec,
 		    struct mlx5_flow_act *flow_act,
 		    struct mlx5_flow_destination *dest,
-		    int dest_num)
+		    int num_dest)
 {
 	struct mlx5_flow_root_namespace *root = find_root(&ft->node);
 	struct mlx5_flow_destination gen_dest = {};
@@ -1889,7 +1889,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 	if (flow_act->action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!fwd_next_prio_supported(ft))
 			return ERR_PTR(-EOPNOTSUPP);
-		if (dest_num)
+		if (num_dest)
 			return ERR_PTR(-EINVAL);
 		mutex_lock(&root->chain_lock);
 		next_ft = find_next_chained_ft(prio);
@@ -1897,7 +1897,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 			gen_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 			gen_dest.ft = next_ft;
 			dest = &gen_dest;
-			dest_num = 1;
+			num_dest = 1;
 			flow_act->action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
 		} else {
 			mutex_unlock(&root->chain_lock);
@@ -1905,7 +1905,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		}
 	}
 
-	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, dest_num);
+	handle = _mlx5_add_flow_rules(ft, spec, flow_act, dest, num_dest);
 
 	if (sw_action == MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO) {
 		if (!IS_ERR_OR_NULL(handle) &&
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index c40f2fc68655..71fb503b2b52 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -177,7 +177,7 @@ mlx5_add_flow_rules(struct mlx5_flow_table *ft,
 		    struct mlx5_flow_spec *spec,
 		    struct mlx5_flow_act *flow_act,
 		    struct mlx5_flow_destination *dest,
-		    int dest_num);
+		    int num_dest);
 void mlx5_del_flow_rules(struct mlx5_flow_handle *fr);
 
 int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
-- 
cgit v1.2.3


From 09d4d9648bd01a4c124fcc30dd0c31503975e8c2 Mon Sep 17 00:00:00 2001
From: Julia Lawall <Julia.Lawall@lip6.fr>
Date: Fri, 3 Aug 2018 18:32:11 +0200
Subject: Coccinelle: doubletest: reduce side effect false positives

Ensure that the cited expression is not a function call or an
assignment to reduce the chance of false positives.

Slightly modify the warning message to indicate another source
of false positves.

Signed-off-by: Julia Lawall <Julia.Lawall@lip6.fr>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/coccinelle/tests/doubletest.cocci | 34 +++++++++++++++++++++++--------
 1 file changed, 26 insertions(+), 8 deletions(-)

diff --git a/scripts/coccinelle/tests/doubletest.cocci b/scripts/coccinelle/tests/doubletest.cocci
index 78d74c22ca12..7af2ce7eb9bf 100644
--- a/scripts/coccinelle/tests/doubletest.cocci
+++ b/scripts/coccinelle/tests/doubletest.cocci
@@ -1,6 +1,7 @@
 /// Find &&/|| operations that include the same argument more than once
-//# A common source of false positives is when the argument performs a side
-//# effect.
+//# A common source of false positives is when the expression, or
+//# another expresssion in the same && or || operation, performs a
+//# side effect.
 ///
 // Confidence: Moderate
 // Copyright: (C) 2010 Nicolas Palix, DIKU.  GPLv2.
@@ -20,20 +21,37 @@ position p;
 @@
 
 (
-* E@p
-  || ... || E
+ E@p || ... || E
 |
-* E@p
-  && ... && E
+ E@p && ... && E
 )
 
-@script:python depends on org@
+@bad@
+expression r.E,e1,e2,fn;
+position r.p;
+assignment operator op;
+@@
+
+(
+E@p
+&
+ <+... \(fn(...)\|e1 op e2\|e1++\|e1--\|++e1\|--e1\) ...+>
+)
+
+@depends on context && !bad@
+expression r.E;
+position r.p;
+@@
+
+*E@p
+
+@script:python depends on org && !bad@
 p << r.p;
 @@
 
 cocci.print_main("duplicated argument to && or ||",p)
 
-@script:python depends on report@
+@script:python depends on report && !bad@
 p << r.p;
 @@
 
-- 
cgit v1.2.3


From 512ddf7d7db056edfed3159ea7cb4e4a5eefddd4 Mon Sep 17 00:00:00 2001
From: Denis Efremov <efremov@linux.com>
Date: Fri, 10 Aug 2018 23:25:55 +0300
Subject: coccicheck: return proper error code on fail

If coccicheck fails, it should return an error code distinct from zero
to signal about an internal problem. Current code instead of exiting with
the tool's error code returns the error code of 'echo "coccicheck failed"'
which is almost always equals to zero, thus failing the original intention
of alerting about a problem. This patch fixes the code.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Denis Efremov <efremov@linux.com>
Acked-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
---
 scripts/coccicheck | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/scripts/coccicheck b/scripts/coccicheck
index 9fedca611b7f..e04d328210ac 100755
--- a/scripts/coccicheck
+++ b/scripts/coccicheck
@@ -128,9 +128,10 @@ run_cmd_parmap() {
 	fi
 	echo $@ >>$DEBUG_FILE
 	$@ 2>>$DEBUG_FILE
-	if [[ $? -ne 0 ]]; then
+	err=$?
+	if [[ $err -ne 0 ]]; then
 		echo "coccicheck failed"
-		exit $?
+		exit $err
 	fi
 }
 
-- 
cgit v1.2.3


From c151272d1687ce2a379a93bf848080f9a42f1cef Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 14 Aug 2018 01:48:38 +0900
Subject: kconfig: remove unused sym_get_env_prop() function

This function is unused since commit 104daea149c4 ("kconfig: reference
environment variables directly and remove 'option env='").

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
---
 scripts/kconfig/lkc.h    | 1 -
 scripts/kconfig/symbol.c | 9 ---------
 2 files changed, 10 deletions(-)

diff --git a/scripts/kconfig/lkc.h b/scripts/kconfig/lkc.h
index 6b7bbc6238e3..9eb7c837cd8f 100644
--- a/scripts/kconfig/lkc.h
+++ b/scripts/kconfig/lkc.h
@@ -125,7 +125,6 @@ const char *sym_get_string_default(struct symbol *sym);
 struct symbol *sym_check_deps(struct symbol *sym);
 struct property *prop_alloc(enum prop_type type, struct symbol *sym);
 struct symbol *prop_get_symbol(struct property *prop);
-struct property *sym_get_env_prop(struct symbol *sym);
 
 static inline tristate sym_get_tristate_value(struct symbol *sym)
 {
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 869a5e8e87a5..073d780f7ec9 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -76,15 +76,6 @@ struct property *sym_get_choice_prop(struct symbol *sym)
 	return NULL;
 }
 
-struct property *sym_get_env_prop(struct symbol *sym)
-{
-	struct property *prop;
-
-	for_all_properties(sym, prop, P_ENV)
-		return prop;
-	return NULL;
-}
-
 static struct property *sym_get_default_prop(struct symbol *sym)
 {
 	struct property *prop;
-- 
cgit v1.2.3


From 1880861226c13ddd42c34ddd30c3b502b650fe29 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <yamada.masahiro@socionext.com>
Date: Tue, 14 Aug 2018 01:48:39 +0900
Subject: kconfig: remove P_ENV property type

This property is not set by anyone since commit 104daea149c4 ("kconfig:
reference environment variables directly and remove 'option env='").

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Acked-by: Sam Ravnborg <sam@ravnborg.org>
---
 scripts/kconfig/expr.h   | 1 -
 scripts/kconfig/qconf.cc | 1 -
 scripts/kconfig/symbol.c | 2 --
 3 files changed, 4 deletions(-)

diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index 84a5199bb46b..7c329e179007 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -185,7 +185,6 @@ enum prop_type {
 	P_SELECT,   /* select BAR */
 	P_IMPLY,    /* imply BAR */
 	P_RANGE,    /* range 7..100 (for a symbol) */
-	P_ENV,      /* value from environment variable */
 	P_SYMBOL,   /* where a symbol is defined */
 };
 
diff --git a/scripts/kconfig/qconf.cc b/scripts/kconfig/qconf.cc
index 62261b3a13c7..ef4310f2558b 100644
--- a/scripts/kconfig/qconf.cc
+++ b/scripts/kconfig/qconf.cc
@@ -1149,7 +1149,6 @@ QString ConfigInfoView::debug_info(struct symbol *sym)
 		case P_DEFAULT:
 		case P_SELECT:
 		case P_RANGE:
-		case P_ENV:
 			debug += prop_get_type_name(prop->type);
 			debug += ": ";
 			expr_print(prop->expr, expr_print_help, &debug, E_NONE);
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 073d780f7ec9..4ec8b1f0d42c 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -1289,8 +1289,6 @@ const char *prop_get_type_name(enum prop_type type)
 	switch (type) {
 	case P_PROMPT:
 		return "prompt";
-	case P_ENV:
-		return "env";
 	case P_COMMENT:
 		return "comment";
 	case P_MENU:
-- 
cgit v1.2.3


From 19997ba7cb7473a4061f42bdfe7e7928a020e714 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Mon, 13 Aug 2018 18:31:05 -0700
Subject: nfp: clean up return types in kdoc comments

Remove 'Return:' information from functions which no longer
return a value.  Also update name and return types of nfp_nffw_info
access functions.

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Reviewed-by: Dirk van der Merwe <dirk.vandermerwe@netronome.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/netronome/nfp/nfp_net_common.c   | 2 --
 drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c | 6 ++----
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
index 0817c69fc568..a8b9fbab5f73 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c
@@ -949,8 +949,6 @@ err_free:
  * nfp_net_tx_complete() - Handled completed TX packets
  * @tx_ring:	TX ring structure
  * @budget:	NAPI budget (only used as bool to determine if in NAPI context)
- *
- * Return: Number of completed TX descriptors
  */
 static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget)
 {
diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
index 37a6d7822a38..40510860341b 100644
--- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
+++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nffw.c
@@ -207,7 +207,7 @@ nffw_res_fwinfos(struct nfp_nffw_info_data *fwinf, struct nffw_fwinfo **arr)
  * nfp_nffw_info_open() - Acquire the lock on the NFFW table
  * @cpp:	NFP CPP handle
  *
- * Return: 0, or -ERRNO
+ * Return: pointer to nfp_nffw_info object or ERR_PTR()
  */
 struct nfp_nffw_info *nfp_nffw_info_open(struct nfp_cpp *cpp)
 {
@@ -253,10 +253,8 @@ err_free:
 }
 
 /**
- * nfp_nffw_info_release() - Release the lock on the NFFW table
+ * nfp_nffw_info_close() - Release the lock on the NFFW table and free state
  * @state:	NFP FW info state
- *
- * Return: 0, or -ERRNO
  */
 void nfp_nffw_info_close(struct nfp_nffw_info *state)
 {
-- 
cgit v1.2.3


From 2df8bee5654bb2b7312662ca6810d4dc16b0b67f Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 13 Aug 2018 18:44:03 +0800
Subject: net_sched: fix NULL pointer dereference when delete tcindex filter

Li Shuang reported the following crash:

[   71.267724] BUG: unable to handle kernel NULL pointer dereference at 0000000000000004
[   71.276456] PGD 800000085d9bd067 P4D 800000085d9bd067 PUD 859a0b067 PMD 0
[   71.284127] Oops: 0000 [#1] SMP PTI
[   71.288015] CPU: 12 PID: 2386 Comm: tc Not tainted 4.18.0-rc8.latest+ #131
[   71.295686] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.1.5 04/11/2016
[   71.304037] RIP: 0010:tcindex_delete+0x72/0x280 [cls_tcindex]
[   71.310446] Code: 00 31 f6 48 87 75 20 48 85 f6 74 11 48 8b 47 18 48 8b 40 08 48 8b 40 50 e8 fb a6 f8 fc 48 85 db 0f 84 dc 00 00 00 48 8b 73 18 <8b> 56 04 48 8d 7e 04 85 d2 0f 84 7b 01 00
[   71.331517] RSP: 0018:ffffb45207b3f898 EFLAGS: 00010282
[   71.337345] RAX: ffff8ad3d72d6360 RBX: ffff8acc84393680 RCX: 000000000000002e
[   71.345306] RDX: ffff8ad3d72c8570 RSI: 0000000000000000 RDI: ffff8ad847a45800
[   71.353277] RBP: ffff8acc84393688 R08: ffff8ad3d72c8400 R09: 0000000000000000
[   71.361238] R10: ffff8ad3de786e00 R11: 0000000000000000 R12: ffffb45207b3f8c7
[   71.369199] R13: ffff8ad3d93bd2a0 R14: 000000000000002e R15: ffff8ad3d72c9600
[   71.377161] FS:  00007f9d3ec3e740(0000) GS:ffff8ad3df980000(0000) knlGS:0000000000000000
[   71.386188] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[   71.392597] CR2: 0000000000000004 CR3: 0000000852f06003 CR4: 00000000001606e0
[   71.400558] Call Trace:
[   71.403299]  tcindex_destroy_element+0x25/0x40 [cls_tcindex]
[   71.409611]  tcindex_walk+0xbb/0x110 [cls_tcindex]
[   71.414953]  tcindex_destroy+0x44/0x90 [cls_tcindex]
[   71.420492]  ? tcindex_delete+0x280/0x280 [cls_tcindex]
[   71.426323]  tcf_proto_destroy+0x16/0x40
[   71.430696]  tcf_chain_flush+0x51/0x70
[   71.434876]  tcf_block_put_ext.part.30+0x8f/0x1b0
[   71.440122]  tcf_block_put+0x4d/0x70
[   71.444108]  cbq_destroy+0x4d/0xd0 [sch_cbq]
[   71.448869]  qdisc_destroy+0x62/0x130
[   71.452951]  dsmark_destroy+0x2a/0x70 [sch_dsmark]
[   71.458300]  qdisc_destroy+0x62/0x130
[   71.462373]  qdisc_graft+0x3ba/0x470
[   71.466359]  tc_get_qdisc+0x2a6/0x2c0
[   71.470443]  ? cred_has_capability+0x7d/0x130
[   71.475307]  rtnetlink_rcv_msg+0x263/0x2d0
[   71.479875]  ? rtnl_calcit.isra.30+0x110/0x110
[   71.484832]  netlink_rcv_skb+0x4d/0x130
[   71.489109]  netlink_unicast+0x1a3/0x250
[   71.493482]  netlink_sendmsg+0x2ae/0x3a0
[   71.497859]  sock_sendmsg+0x36/0x40
[   71.501748]  ___sys_sendmsg+0x26f/0x2d0
[   71.506029]  ? handle_pte_fault+0x586/0xdf0
[   71.510694]  ? __handle_mm_fault+0x389/0x500
[   71.515457]  ? __sys_sendmsg+0x5e/0xa0
[   71.519636]  __sys_sendmsg+0x5e/0xa0
[   71.523626]  do_syscall_64+0x5b/0x180
[   71.527711]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   71.533345] RIP: 0033:0x7f9d3e257f10
[   71.537331] Code: c3 48 8b 05 82 6f 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d 8d d0 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8
[   71.558401] RSP: 002b:00007fff6f893398 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[   71.566848] RAX: ffffffffffffffda RBX: 000000005b71274d RCX: 00007f9d3e257f10
[   71.574810] RDX: 0000000000000000 RSI: 00007fff6f8933e0 RDI: 0000000000000003
[   71.582770] RBP: 00007fff6f8933e0 R08: 000000000000ffff R09: 0000000000000003
[   71.590729] R10: 00007fff6f892e20 R11: 0000000000000246 R12: 0000000000000000
[   71.598689] R13: 0000000000662ee0 R14: 0000000000000000 R15: 0000000000000000
[   71.606651] Modules linked in: sch_cbq cls_tcindex sch_dsmark xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat nf_nat_ipv4 nf_nat nf_conntrack_ipv4 nf_defrag_ipv4 xt_conntrack nf_coni
[   71.685425]  libahci i2c_algo_bit i2c_core i40e libata dca mdio megaraid_sas dm_mirror dm_region_hash dm_log dm_mod
[   71.697075] CR2: 0000000000000004
[   71.700792] ---[ end trace f604eb1acacd978b ]---

Reproducer:
tc qdisc add dev lo handle 1:0 root dsmark indices 64 set_tc_index
tc filter add dev lo parent 1:0 protocol ip prio 1 tcindex mask 0xfc shift 2
tc qdisc add dev lo parent 1:0 handle 2:0 cbq bandwidth 10Mbit cell 8 avpkt 1000 mpu 64
tc class add dev lo parent 2:0 classid 2:1 cbq bandwidth 10Mbit rate 1500Kbit avpkt 1000 prio 1 bounded isolated allot 1514 weight 1 maxburst 10
tc filter add dev lo parent 2:0 protocol ip prio 1 handle 0x2e tcindex classid 2:1 pass_on
tc qdisc add dev lo parent 2:1 pfifo limit 5
tc qdisc del dev lo root

This is because in tcindex_set_parms, when there is no old_r, we set new
exts to cr.exts. And we didn't set it to filter when r == &new_filter_result.

Then in tcindex_delete() -> tcf_exts_get_net(), we will get NULL pointer
dereference as we didn't init exts.

Fix it by moving tcf_exts_change() after "if (old_r && old_r != r)" check.
Then we don't need "cr" as there is no errout after that.

Fixes: bf63ac73b3e13 ("net_sched: fix an oops in tcindex filter")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index 32f4bbd82f35..ddaa4e63ce94 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -447,11 +447,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		tcf_bind_filter(tp, &cr.res, base);
 	}
 
-	if (old_r)
-		tcf_exts_change(&r->exts, &e);
-	else
-		tcf_exts_change(&cr.exts, &e);
-
 	if (old_r && old_r != r) {
 		err = tcindex_filter_result_init(old_r);
 		if (err < 0) {
@@ -462,6 +457,8 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 
 	oldp = p;
 	r->res = cr.res;
+	tcf_exts_change(&r->exts, &e);
+
 	rcu_assign_pointer(tp->root, cp);
 
 	if (r == &new_filter_result) {
-- 
cgit v1.2.3


From 008369dcc5f7bfba526c98054f8525322acf0ea3 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 13 Aug 2018 18:44:04 +0800
Subject: net_sched: Fix missing res info when create new tc_index filter

Li Shuang reported the following warn:

[  733.484610] WARNING: CPU: 6 PID: 21123 at net/sched/sch_cbq.c:1418 cbq_destroy_class+0x5d/0x70 [sch_cbq]
[  733.495190] Modules linked in: sch_cbq cls_tcindex sch_dsmark rpcsec_gss_krb5 auth_rpcgss nfsv4 dns_resolver nfs lockd grace fscache xt_CHECKSUM iptable_mangle ipt_MASQUERADE iptable_nat l
[  733.574155]  syscopyarea sysfillrect sysimgblt fb_sys_fops ttm drm igb ixgbe ahci libahci i2c_algo_bit libata i40e i2c_core dca mdio megaraid_sas dm_mirror dm_region_hash dm_log dm_mod
[  733.592500] CPU: 6 PID: 21123 Comm: tc Not tainted 4.18.0-rc8.latest+ #131
[  733.600169] Hardware name: Dell Inc. PowerEdge R730/0WCJNT, BIOS 2.1.5 04/11/2016
[  733.608518] RIP: 0010:cbq_destroy_class+0x5d/0x70 [sch_cbq]
[  733.614734] Code: e7 d9 d2 48 8b 7b 48 e8 61 05 da d2 48 8d bb f8 00 00 00 e8 75 ae d5 d2 48 39 eb 74 0a 48 89 df 5b 5d e9 16 6c 94 d2 5b 5d c3 <0f> 0b eb b6 0f 1f 44 00 00 66 2e 0f 1f 84
[  733.635798] RSP: 0018:ffffbfbb066bb9d8 EFLAGS: 00010202
[  733.641627] RAX: 0000000000000001 RBX: ffff9cdd17392800 RCX: 000000008010000f
[  733.649588] RDX: ffff9cdd1df547e0 RSI: ffff9cdd17392800 RDI: ffff9cdd0f84c800
[  733.657547] RBP: ffff9cdd0f84c800 R08: 0000000000000001 R09: 0000000000000000
[  733.665508] R10: ffff9cdd0f84d000 R11: 0000000000000001 R12: 0000000000000001
[  733.673469] R13: 0000000000000000 R14: 0000000000000001 R15: ffff9cdd17392200
[  733.681430] FS:  00007f911890a740(0000) GS:ffff9cdd1f8c0000(0000) knlGS:0000000000000000
[  733.690456] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  733.696864] CR2: 0000000000b5544c CR3: 0000000859374002 CR4: 00000000001606e0
[  733.704826] Call Trace:
[  733.707554]  cbq_destroy+0xa1/0xd0 [sch_cbq]
[  733.712318]  qdisc_destroy+0x62/0x130
[  733.716401]  dsmark_destroy+0x2a/0x70 [sch_dsmark]
[  733.721745]  qdisc_destroy+0x62/0x130
[  733.725829]  qdisc_graft+0x3ba/0x470
[  733.729817]  tc_get_qdisc+0x2a6/0x2c0
[  733.733901]  ? cred_has_capability+0x7d/0x130
[  733.738761]  rtnetlink_rcv_msg+0x263/0x2d0
[  733.743330]  ? rtnl_calcit.isra.30+0x110/0x110
[  733.748287]  netlink_rcv_skb+0x4d/0x130
[  733.752576]  netlink_unicast+0x1a3/0x250
[  733.756949]  netlink_sendmsg+0x2ae/0x3a0
[  733.761324]  sock_sendmsg+0x36/0x40
[  733.765213]  ___sys_sendmsg+0x26f/0x2d0
[  733.769493]  ? handle_pte_fault+0x586/0xdf0
[  733.774158]  ? __handle_mm_fault+0x389/0x500
[  733.778919]  ? __sys_sendmsg+0x5e/0xa0
[  733.783099]  __sys_sendmsg+0x5e/0xa0
[  733.787087]  do_syscall_64+0x5b/0x180
[  733.791171]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[  733.796805] RIP: 0033:0x7f9117f23f10
[  733.800791] Code: c3 48 8b 05 82 6f 2c 00 f7 db 64 89 18 48 83 cb ff eb dd 0f 1f 80 00 00 00 00 83 3d 8d d0 2c 00 00 75 10 b8 2e 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 31 c3 48 83 ec 08 e8
[  733.821873] RSP: 002b:00007ffe96818398 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
[  733.830319] RAX: ffffffffffffffda RBX: 000000005b71244c RCX: 00007f9117f23f10
[  733.838280] RDX: 0000000000000000 RSI: 00007ffe968183e0 RDI: 0000000000000003
[  733.846241] RBP: 00007ffe968183e0 R08: 000000000000ffff R09: 0000000000000003
[  733.854202] R10: 00007ffe96817e20 R11: 0000000000000246 R12: 0000000000000000
[  733.862161] R13: 0000000000662ee0 R14: 0000000000000000 R15: 0000000000000000
[  733.870121] ---[ end trace 28edd4aad712ddca ]---

This is because we didn't update f->result.res when create new filter. Then in
tcindex_delete() -> tcf_unbind_filter(), we will failed to find out the res
and unbind filter, which will trigger the WARN_ON() in cbq_destroy_class().

Fix it by updating f->result.res when create new filter.

Fixes: 6e0565697a106 ("net_sched: fix another crash in cls_tcindex")
Reported-by: Li Shuang <shuali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/sched/cls_tcindex.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c
index ddaa4e63ce94..9ccc93f257db 100644
--- a/net/sched/cls_tcindex.c
+++ b/net/sched/cls_tcindex.c
@@ -465,6 +465,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base,
 		struct tcindex_filter *nfp;
 		struct tcindex_filter __rcu **fp;
 
+		f->result.res = r->res;
 		tcf_exts_change(&f->result.exts, &r->exts);
 
 		fp = cp->h + (handle % cp->hash);
-- 
cgit v1.2.3


From 3aad924025e2865e80212b9154749303618a1826 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 13 Aug 2018 23:19:21 +0200
Subject: net: lan743x: select CRC16

lan743x now fails to build when CONFIG_CRC16 is disabled:

drivers/net/ethernet/microchip/lan743x_main.o: In function crc16'

Force it on like all other users do.

Fixes: 4d94282afd95 ("lan743x: Add power management support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/microchip/Kconfig b/drivers/net/ethernet/microchip/Kconfig
index 71dca8bd51ac..16bd3f44dbe8 100644
--- a/drivers/net/ethernet/microchip/Kconfig
+++ b/drivers/net/ethernet/microchip/Kconfig
@@ -46,6 +46,7 @@ config LAN743X
 	tristate "LAN743x support"
 	depends on PCI
 	select PHYLIB
+	select CRC16
 	---help---
 	  Support for the Microchip LAN743x PCI Express Gigabit Ethernet chip
 
-- 
cgit v1.2.3


From 9dc502d79778324df7db4e093ffddf5413a1cd5f Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 13 Aug 2018 23:19:22 +0200
Subject: net: lan743x: fix building without CONFIG_PTP_1588_CLOCK

Building without CONFIG_PTP_1588_CLOCK results in multiple failures,
this was obviously not well tested:

drivers/net/ethernet/microchip/lan743x_ptp.c: In function 'lan743x_ptp_isr':
drivers/net/ethernet/microchip/lan743x_ptp.c:781:28: error: 'struct lan743x_ptp' has no member named 'ptp_clock'; did you mean 'tx_ts_lock'?
   ptp_schedule_worker(ptp->ptp_clock, 0);
                            ^~~~~~~~~
                            tx_ts_lock
drivers/net/ethernet/microchip/lan743x_ptp.c: In function 'lan743x_ptp_open':
drivers/net/ethernet/microchip/lan743x_ptp.c:879:6: error: unused variable 'ret' [-Werror=unused-variable]
  int ret = -ENODEV;
      ^~~
At top level:
drivers/net/ethernet/microchip/lan743x_ptp.c:63:13: error: 'lan743x_ptp_tx_ts_enqueue_ts' defined but not used [-Werror=unused-function]
 static void lan743x_ptp_tx_ts_enqueue_ts(struct lan743x_adapter *adapter,
             ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
cc1: all warnings being treated as errors
drivers/net/ethernet/microchip/lan743x_ethtool.c: In function 'lan743x_ethtool_get_ts_info':
drivers/net/ethernet/microchip/lan743x_ethtool.c:558:19: error: 'struct lan743x_ptp' has no member named 'ptp_clock'; did you mean 'tx_ts_lock'?

Those #ifdef checks are hard to get right, replace them all with
IS_ENABLED() checks that leave the same code visible to the compiler
but let it optimize out the unused bits based on the configuration.

Fixes: 07624df1c9ef ("lan743x: lan743x: Add PTP support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microchip/lan743x_ptp.c | 15 ++++++---------
 drivers/net/ethernet/microchip/lan743x_ptp.h |  2 --
 2 files changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 029a2af90d5e..64dba96edc79 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -4,6 +4,7 @@
 #include <linux/netdevice.h>
 #include "lan743x_main.h"
 
+#include <linux/ptp_clock_kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/net_tstamp.h>
@@ -138,7 +139,6 @@ done:
 	spin_unlock_bh(&ptp->tx_ts_lock);
 }
 
-#ifdef CONFIG_PTP_1588_CLOCK
 static int lan743x_ptp_reserve_event_ch(struct lan743x_adapter *adapter)
 {
 	struct lan743x_ptp *ptp = &adapter->ptp;
@@ -760,7 +760,6 @@ static void lan743x_ptp_clock_step(struct lan743x_adapter *adapter,
 		mutex_unlock(&ptp->command_lock);
 	}
 }
-#endif /* CONFIG_PTP_1588_CLOCK */
 
 void lan743x_ptp_isr(void *context)
 {
@@ -889,7 +888,9 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter)
 			  PTP_INT_BIT_TX_SWTS_ERR_ | PTP_INT_BIT_TX_TS_);
 	ptp->flags |= PTP_FLAG_ISR_ENABLED;
 
-#ifdef CONFIG_PTP_1588_CLOCK
+	if (!IS_ENABLED(CONFIG_PTP_1588_CLOCK))
+		return 0;
+
 	snprintf(ptp->pin_config[0].name, 32, "lan743x_ptp_pin_0");
 	ptp->pin_config[0].index = 0;
 	ptp->pin_config[0].func = PTP_PF_PEROUT;
@@ -931,9 +932,6 @@ int lan743x_ptp_open(struct lan743x_adapter *adapter)
 done:
 	lan743x_ptp_close(adapter);
 	return ret;
-#else
-	return 0;
-#endif
 }
 
 void lan743x_ptp_close(struct lan743x_adapter *adapter)
@@ -941,15 +939,14 @@ void lan743x_ptp_close(struct lan743x_adapter *adapter)
 	struct lan743x_ptp *ptp = &adapter->ptp;
 	int index;
 
-#ifdef CONFIG_PTP_1588_CLOCK
-	if (ptp->flags & PTP_FLAG_PTP_CLOCK_REGISTERED) {
+	if (IS_ENABLED(CONFIG_PTP_1588_CLOCK) &&
+	    ptp->flags & PTP_FLAG_PTP_CLOCK_REGISTERED) {
 		ptp_clock_unregister(ptp->ptp_clock);
 		ptp->ptp_clock = NULL;
 		ptp->flags &= ~PTP_FLAG_PTP_CLOCK_REGISTERED;
 		netif_info(adapter, drv, adapter->netdev,
 			   "ptp clock unregister\n");
 	}
-#endif
 
 	if (ptp->flags & PTP_FLAG_ISR_ENABLED) {
 		lan743x_csr_write(adapter, PTP_INT_EN_CLR,
diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.h b/drivers/net/ethernet/microchip/lan743x_ptp.h
index 20f2223024dc..5fc1b3cd5e33 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.h
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.h
@@ -49,11 +49,9 @@ struct lan743x_ptp {
 	/* command_lock: used to prevent concurrent ptp commands */
 	struct mutex	command_lock;
 
-#ifdef CONFIG_PTP_1588_CLOCK
 	struct ptp_clock *ptp_clock;
 	struct ptp_clock_info ptp_clock_info;
 	struct ptp_pin_desc pin_config[1];
-#endif /* CONFIG_PTP_1588_CLOCK */
 
 #define LAN743X_PTP_NUMBER_OF_EVENT_CHANNELS (2)
 	unsigned long used_event_ch;
-- 
cgit v1.2.3


From 3d46eee5a5f2f22ca04e2139e8c9a16b81d16073 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 13 Aug 2018 23:26:54 +0200
Subject: bnxt_en: avoid string overflow for record->system_name

The utsname()->nodename string may be 64 bytes long, and it gets
copied without the trailing nul byte into the shorter record->system_name,
as gcc now warns:

In file included from include/linux/bitmap.h:9,
                 from include/linux/ethtool.h:16,
                 from drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:13:
In function 'strncpy',
    inlined from 'bnxt_fill_coredump_record' at drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2863:2:
include/linux/string.h:254:9: error: '__builtin_strncpy' output truncated before terminating nul copying as many bytes from a string as its length [-Werror=stringop-truncation]

Using strlcpy() at least avoids overflowing the destination buffer
and adds proper nul-termination. It may still truncate long names
though, which probably can't be solved here.

Fixes: 6c5657d085ae ("bnxt_en: Add support for ethtool get dump.")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9c929cd90b86..539be1d1b67f 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2860,8 +2860,8 @@ bnxt_fill_coredump_record(struct bnxt *bp, struct bnxt_coredump_record *record,
 	record->low_version = 0;
 	record->high_version = 1;
 	record->asic_state = 0;
-	strncpy(record->system_name, utsname()->nodename,
-		strlen(utsname()->nodename));
+	strlcpy(record->system_name, utsname()->nodename,
+		sizeof(record->system_name));
 	record->year = cpu_to_le16(tm.tm_year);
 	record->month = cpu_to_le16(tm.tm_mon);
 	record->day = cpu_to_le16(tm.tm_mday);
-- 
cgit v1.2.3


From c2ebc25674e5123d134e81758828084f1cc58cc3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 13 Aug 2018 23:43:05 +0200
Subject: l2tp: fix unused function warning

Removing one of the callers of pppol2tp_session_get_sock caused a harmless
warning in some configurations:

net/l2tp/l2tp_ppp.c:142:21: 'pppol2tp_session_get_sock' defined but not used [-Wunused-function]

Rather than adding another #ifdef here, using a proper IS_ENABLED()
check makes the code more readable and avoids those warnings while
letting the compiler figure out for itself which code is needed.

This adds one pointer for the unused show() callback in struct
l2tp_session, but that seems harmless.

Fixes: b0e29063dcb3 ("l2tp: remove pppol2tp_session_ioctl()")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/l2tp/l2tp_core.h | 2 --
 net/l2tp/l2tp_eth.c  | 7 ++-----
 net/l2tp/l2tp_ppp.c  | 7 ++-----
 3 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 8480a0af973e..9c9afe94d389 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -118,9 +118,7 @@ struct l2tp_session {
 	int (*build_header)(struct l2tp_session *session, void *buf);
 	void (*recv_skb)(struct l2tp_session *session, struct sk_buff *skb, int data_len);
 	void (*session_close)(struct l2tp_session *session);
-#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
 	void (*show)(struct seq_file *m, void *priv);
-#endif
 	uint8_t			priv[0];	/* private data */
 };
 
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index 3728986ec885..8aadc4f3bb9e 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -199,7 +199,6 @@ static void l2tp_eth_delete(struct l2tp_session *session)
 	}
 }
 
-#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
 static void l2tp_eth_show(struct seq_file *m, void *arg)
 {
 	struct l2tp_session *session = arg;
@@ -219,7 +218,6 @@ static void l2tp_eth_show(struct seq_file *m, void *arg)
 
 	dev_put(dev);
 }
-#endif
 
 static void l2tp_eth_adjust_mtu(struct l2tp_tunnel *tunnel,
 				struct l2tp_session *session,
@@ -305,9 +303,8 @@ static int l2tp_eth_create(struct net *net, struct l2tp_tunnel *tunnel,
 
 	session->recv_skb = l2tp_eth_dev_recv;
 	session->session_close = l2tp_eth_delete;
-#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
-	session->show = l2tp_eth_show;
-#endif
+	if (IS_ENABLED(CONFIG_L2TP_DEBUGFS))
+		session->show = l2tp_eth_show;
 
 	spriv = l2tp_session_priv(session);
 
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 62f2d3f1e431..04d9946dcdba 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -533,7 +533,6 @@ out:
 	return error;
 }
 
-#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
 static void pppol2tp_show(struct seq_file *m, void *arg)
 {
 	struct l2tp_session *session = arg;
@@ -547,16 +546,14 @@ static void pppol2tp_show(struct seq_file *m, void *arg)
 		sock_put(sk);
 	}
 }
-#endif
 
 static void pppol2tp_session_init(struct l2tp_session *session)
 {
 	struct pppol2tp_session *ps;
 
 	session->recv_skb = pppol2tp_recv;
-#if IS_ENABLED(CONFIG_L2TP_DEBUGFS)
-	session->show = pppol2tp_show;
-#endif
+	if (IS_ENABLED(CONFIG_L2TP_DEBUGFS))
+		session->show = pppol2tp_show;
 
 	ps = l2tp_session_priv(session);
 	mutex_init(&ps->sk_lock);
-- 
cgit v1.2.3


From 81a8b0799632627b587af31ecd06112397e4ec36 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 13 Aug 2018 23:50:41 +0200
Subject: net: stmmac: mark PM functions as __maybe_unused

The newly added suspend/resume functions cause a build warning
when CONFIG_PM is disabled:

drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c:324:12: error: 'stmmac_pci_resume' defined but not used [-Werror=unused-function]
drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c:306:12: error: 'stmmac_pci_suspend' defined but not used [-Werror=unused-function]

Mark them as __maybe_unused so gcc can drop them silently.

Fixes: b7d0f08e9129 ("net: stmmac: Fix WoL for PCI-based setups")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
index 6a393b16a1fc..c54a50dbd5ac 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c
@@ -303,7 +303,7 @@ static void stmmac_pci_remove(struct pci_dev *pdev)
 	pci_disable_device(pdev);
 }
 
-static int stmmac_pci_suspend(struct device *dev)
+static int __maybe_unused stmmac_pci_suspend(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int ret;
@@ -321,7 +321,7 @@ static int stmmac_pci_suspend(struct device *dev)
 	return 0;
 }
 
-static int stmmac_pci_resume(struct device *dev)
+static int __maybe_unused stmmac_pci_resume(struct device *dev)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
 	int ret;
-- 
cgit v1.2.3


From cf87615d15f37182b2a3a4cd722288d3d5956900 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 14 Aug 2018 00:10:34 +0200
Subject: net: systemport: fix unused function warning

The only remaining caller of this function is inside of an #ifdef
after another caller got removed. This causes a harmless warning
in some configurations:

drivers/net/ethernet/broadcom/bcmsysport.c:1068:13: error: 'bcm_sysport_resume_from_wol' defined but not used [-Werror=unused-function]

Removing the #ifdef around the PM functions simplifies the code
and avoids the problem but letting the compiler drop the unused
functions silently.

Fixes: 9e85e22713d6 ("net: systemport: Do not re-configure upon WoL interrupt")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Florian Fainelli <f.fainelli@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bcmsysport.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c
index ca47309d4494..147045757b10 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2585,7 +2585,6 @@ static int bcm_sysport_remove(struct platform_device *pdev)
 	return 0;
 }
 
-#ifdef CONFIG_PM_SLEEP
 static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 {
 	struct net_device *ndev = priv->netdev;
@@ -2650,7 +2649,7 @@ static int bcm_sysport_suspend_to_wol(struct bcm_sysport_priv *priv)
 	return 0;
 }
 
-static int bcm_sysport_suspend(struct device *d)
+static int __maybe_unused bcm_sysport_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -2712,7 +2711,7 @@ static int bcm_sysport_suspend(struct device *d)
 	return ret;
 }
 
-static int bcm_sysport_resume(struct device *d)
+static int __maybe_unused bcm_sysport_resume(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcm_sysport_priv *priv = netdev_priv(dev);
@@ -2805,7 +2804,6 @@ out_free_tx_rings:
 		bcm_sysport_fini_tx_ring(priv, i);
 	return ret;
 }
-#endif
 
 static SIMPLE_DEV_PM_OPS(bcm_sysport_pm_ops,
 		bcm_sysport_suspend, bcm_sysport_resume);
-- 
cgit v1.2.3


From 1bbf3aed25e0fc256e825da1f5c45d7b4daa828e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 14 Aug 2018 00:12:45 +0200
Subject: bnxt_en: take coredump_record structure off stack

The bnxt_coredump_record structure is very long, causing a warning
about possible stack overflow on 32-bit architectures:

drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c: In function 'bnxt_get_coredump':
drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c:2989:1: error: the frame size of 1188 bytes is larger than 1024 bytes [-Werror=frame-larger-than=]

I could not see any reason to operate on an on-stack copy of the
structure before copying it back into the caller-provided buffer, which
also simplifies the code here.

Fixes: 6c5657d085ae ("bnxt_en: Add support for ethtool get dump.")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 539be1d1b67f..e52d7af3ab3e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -2900,7 +2900,6 @@ static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 	struct coredump_segment_record *seg_record = NULL;
 	u32 offset = 0, seg_hdr_len, seg_record_len;
 	struct bnxt_coredump_segment_hdr seg_hdr;
-	struct bnxt_coredump_record coredump_rec;
 	struct bnxt_coredump coredump = {NULL};
 	time64_t start_time;
 	u16 start_utc;
@@ -2976,14 +2975,12 @@ next_seg:
 	}
 
 err:
-	if (buf) {
-		bnxt_fill_coredump_record(bp, &coredump_rec, start_time,
+	if (buf)
+		bnxt_fill_coredump_record(bp, buf + offset, start_time,
 					  start_utc, coredump.total_segs + 1,
 					  rc);
-		memcpy(buf + offset, &coredump_rec, sizeof(coredump_rec));
-	}
 	kfree(coredump.data);
-	*dump_len += sizeof(coredump_rec);
+	*dump_len += sizeof(struct bnxt_coredump_record);
 
 	return rc;
 }
-- 
cgit v1.2.3


From 3dbe97efe8bf450b183d6dee2305cbc032e6b8a4 Mon Sep 17 00:00:00 2001
From: Myron Stowe <myron.stowe@redhat.com>
Date: Mon, 13 Aug 2018 12:19:39 -0600
Subject: PCI: Skip MPS logic for Virtual Functions (VFs)

PCIe r4.0, sec 9.3.5.4, "Device Control Register", shows both
Max_Payload_Size (MPS) and Max_Read_request_Size (MRRS) to be 'RsvdP' for
VFs.  Just prior to the table it states:

  "PF and VF functionality is defined in Section 7.5.3.4 except where
   noted in Table 9-16.  For VF fields marked 'RsvdP', the PF setting
   applies to the VF."

All of which implies that with respect to Max_Payload_Size Supported
(MPSS), MPS, and MRRS values, we should not be paying any attention to the
VF's fields, but rather only to the PF's.  Only looking at the PF's fields
also logically makes sense as it's the sole physical interface to the PCIe
bus.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=200527
Fixes: 27d868b5e6cf ("PCI: Set MPS to match upstream bridge")
Signed-off-by: Myron Stowe <myron.stowe@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org # 4.3+
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sinan Kaya <okaya@kernel.org>
Cc: Dongdong Liu <liudongdong3@huawei.com>
Cc: Jon Mason <jdmason@kudzu.us>
---
 drivers/pci/probe.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 71412db3cbeb..c2533ed45fff 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1730,6 +1730,10 @@ static void pci_configure_mps(struct pci_dev *dev)
 	if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge))
 		return;
 
+	/* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */
+	if (dev->is_virtfn)
+		return;
+
 	mps = pcie_get_mps(dev);
 	p_mps = pcie_get_mps(bridge);
 
-- 
cgit v1.2.3


From 9f0e89359775ee21fe1ea732e34edb52aef5addf Mon Sep 17 00:00:00 2001
From: Myron Stowe <myron.stowe@redhat.com>
Date: Mon, 13 Aug 2018 12:19:46 -0600
Subject: PCI: Match Root Port's MPS to endpoint's MPSS as necessary

In commit 27d868b5e6cf ("PCI: Set MPS to match upstream bridge"), we made
sure every device's MPS setting matches its upstream bridge, making it more
likely that a hot-added device will work in a system with an optimized MPS
configuration.

Recently I've started encountering systems where the endpoint device's MPSS
capability is less than its Root Port's current MPS value, thus the
endpoint is not capable of matching its upstream bridge's MPS setting (see:
bugzilla via "Link:" below).  This leaves the system vulnerable - the
upstream Root Port could respond with larger TLPs than the device can
handle, and the device will consider them to be 'Malformed'.

One could use the "pci=pcie_bus_safe" kernel parameter to work around the
issue, but that forces a user to supply a kernel parameter to get the
system to function reliably and may end up limiting MPS settings of other
unrelated, sub-topologies which could benefit from maintaining their larger
values.

Augment Keith's approach to include tuning down a Root Port's MPS setting
when its hot-added endpoint device is not capable of matching it.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=200527
Signed-off-by: Myron Stowe <myron.stowe@redhat.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Jon Mason <jdmason@kudzu.us>
Cc: Keith Busch <keith.busch@intel.com>
Cc: Sinan Kaya <okaya@kernel.org>
Cc: Dongdong Liu <liudongdong3@huawei.com>
---
 drivers/pci/probe.c | 12 ++++++++++--
 1 file changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index c2533ed45fff..bca6d2741969 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1725,7 +1725,7 @@ int pci_setup_device(struct pci_dev *dev)
 static void pci_configure_mps(struct pci_dev *dev)
 {
 	struct pci_dev *bridge = pci_upstream_bridge(dev);
-	int mps, p_mps, rc;
+	int mps, mpss, p_mps, rc;
 
 	if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge))
 		return;
@@ -1753,6 +1753,14 @@ static void pci_configure_mps(struct pci_dev *dev)
 	if (pcie_bus_config != PCIE_BUS_DEFAULT)
 		return;
 
+	mpss = 128 << dev->pcie_mpss;
+	if (mpss < p_mps && pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) {
+		pcie_set_mps(bridge, mpss);
+		pci_info(dev, "Upstream bridge's Max Payload Size set to %d (was %d, max %d)\n",
+			 mpss, p_mps, 128 << bridge->pcie_mpss);
+		p_mps = pcie_get_mps(bridge);
+	}
+
 	rc = pcie_set_mps(dev, p_mps);
 	if (rc) {
 		pci_warn(dev, "can't set Max Payload Size to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n",
@@ -1761,7 +1769,7 @@ static void pci_configure_mps(struct pci_dev *dev)
 	}
 
 	pci_info(dev, "Max Payload Size set to %d (was %d, max %d)\n",
-		 p_mps, mps, 128 << dev->pcie_mpss);
+		 p_mps, mps, mpss);
 }
 
 static struct hpp_type0 pci_default_type0 = {
-- 
cgit v1.2.3


From 8bf782f64737be055e6c1fad7a4c7cae7aae2d99 Mon Sep 17 00:00:00 2001
From: Souptick Joarder <jrdr.linux@gmail.com>
Date: Fri, 29 Jun 2018 00:12:40 +0530
Subject: orangefs: Adding new return type vm_fault_t

Use new return type vm_fault_t for fault handler. For now,
this is just documenting that the function returns a VM_FAULT
value rather than an errno. Once all instances are converted,
vm_fault_t will become a distinct type.

See the following
commit 1c8f422059ae ("mm: change return type to vm_fault_t")

Fixed checkpatch.pl warning.

Signed-off-by: Souptick Joarder <jrdr.linux@gmail.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
---
 fs/orangefs/file.c | 19 ++++++++++---------
 1 file changed, 10 insertions(+), 9 deletions(-)

diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index db0b52187cbc..a5a2fe76568f 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -528,18 +528,19 @@ static long orangefs_ioctl(struct file *file, unsigned int cmd, unsigned long ar
 	return ret;
 }
 
-static int orangefs_fault(struct vm_fault *vmf)
+static vm_fault_t orangefs_fault(struct vm_fault *vmf)
 {
 	struct file *file = vmf->vma->vm_file;
-	int rc;
-	rc = orangefs_inode_getattr(file->f_mapping->host, 0, 1,
+	int ret;
+
+	ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1,
 	    STATX_SIZE);
-	if (rc == -ESTALE)
-		rc = -EIO;
-	if (rc) {
-		gossip_err("%s: orangefs_inode_getattr failed, "
-		    "rc:%d:.\n", __func__, rc);
-		return rc;
+	if (ret == -ESTALE)
+		ret = -EIO;
+	if (ret) {
+		gossip_err("%s: orangefs_inode_getattr failed, ret:%d:.\n",
+				__func__, ret);
+		return VM_FAULT_SIGBUS;
 	}
 	return filemap_fault(vmf);
 }
-- 
cgit v1.2.3


From e1b437691a624a7e767bbb140c730d2779797f53 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Tue, 17 Jul 2018 15:42:53 +0100
Subject: orangefs: remove redundant pointer orangefs_inode

Pointer orangefs_inode is being assigned but is never used hence it is
redundant and can be removed.

Cleans up clang warning:
warning: variable 'orangefs_inode' set but not used [-Wunused-but-set-variable]

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Signed-off-by: Mike Marshall <hubcap@omnibond.com>
---
 fs/orangefs/inode.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 6e4d2af8f5bc..31932879b716 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -251,7 +251,6 @@ int orangefs_getattr(const struct path *path, struct kstat *stat,
 {
 	int ret = -ENOENT;
 	struct inode *inode = path->dentry->d_inode;
-	struct orangefs_inode_s *orangefs_inode = NULL;
 
 	gossip_debug(GOSSIP_INODE_DEBUG,
 		     "orangefs_getattr: called on %pd\n",
@@ -262,8 +261,6 @@ int orangefs_getattr(const struct path *path, struct kstat *stat,
 		generic_fillattr(inode, stat);
 
 		/* override block size reported to stat */
-		orangefs_inode = ORANGEFS_I(inode);
-
 		if (request_mask & STATX_SIZE)
 			stat->result_mask = STATX_BASIC_STATS;
 		else
-- 
cgit v1.2.3


From 5fd50ac38fb66451672b75f8d143dbef6081dd3a Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Tue, 14 Aug 2018 17:13:12 +0100
Subject: net: hns3: Add support for serdes loopback selftest

This patch adds support for serdes loopback selftest in hns3
driver.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c | 11 +++--
 .../net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h | 12 +++++
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 57 +++++++++++++++++++++-
 3 files changed, 75 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index 80ba95d76260..f70ee6910ee2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -53,7 +53,7 @@ static const struct hns3_stats hns3_rxq_stats[] = {
 
 #define HNS3_TQP_STATS_COUNT (HNS3_TXQ_STATS_COUNT + HNS3_RXQ_STATS_COUNT)
 
-#define HNS3_SELF_TEST_TPYE_NUM		1
+#define HNS3_SELF_TEST_TYPE_NUM		2
 #define HNS3_NIC_LB_TEST_PKT_NUM	1
 #define HNS3_NIC_LB_TEST_RING_ID	0
 #define HNS3_NIC_LB_TEST_PACKET_SIZE	128
@@ -78,6 +78,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en)
 		return -EOPNOTSUPP;
 
 	switch (loop) {
+	case HNAE3_MAC_INTER_LOOP_SERDES:
 	case HNAE3_MAC_INTER_LOOP_MAC:
 		ret = h->ae_algo->ops->set_loopback(h, loop, en);
 		break;
@@ -287,7 +288,7 @@ static void hns3_self_test(struct net_device *ndev,
 {
 	struct hns3_nic_priv *priv = netdev_priv(ndev);
 	struct hnae3_handle *h = priv->ae_handle;
-	int st_param[HNS3_SELF_TEST_TPYE_NUM][2];
+	int st_param[HNS3_SELF_TEST_TYPE_NUM][2];
 	bool if_running = netif_running(ndev);
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	bool dis_vlan_filter;
@@ -303,6 +304,10 @@ static void hns3_self_test(struct net_device *ndev,
 	st_param[HNAE3_MAC_INTER_LOOP_MAC][1] =
 			h->flags & HNAE3_SUPPORT_MAC_LOOPBACK;
 
+	st_param[HNAE3_MAC_INTER_LOOP_SERDES][0] = HNAE3_MAC_INTER_LOOP_SERDES;
+	st_param[HNAE3_MAC_INTER_LOOP_SERDES][1] =
+			h->flags & HNAE3_SUPPORT_SERDES_LOOPBACK;
+
 	if (if_running)
 		dev_close(ndev);
 
@@ -316,7 +321,7 @@ static void hns3_self_test(struct net_device *ndev,
 
 	set_bit(HNS3_NIC_STATE_TESTING, &priv->state);
 
-	for (i = 0; i < HNS3_SELF_TEST_TPYE_NUM; i++) {
+	for (i = 0; i < HNS3_SELF_TEST_TYPE_NUM; i++) {
 		enum hnae3_loop loop_type = (enum hnae3_loop)st_param[i][0];
 
 		if (!st_param[i][1])
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
index cd0a4f228470..821d4c2f84bd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h
@@ -94,6 +94,7 @@ enum hclge_opcode_type {
 	HCLGE_OPC_QUERY_LINK_STATUS	= 0x0307,
 	HCLGE_OPC_CONFIG_MAX_FRM_SIZE	= 0x0308,
 	HCLGE_OPC_CONFIG_SPEED_DUP	= 0x0309,
+	HCLGE_OPC_SERDES_LOOPBACK       = 0x0315,
 
 	/* PFC/Pause commands */
 	HCLGE_OPC_CFG_MAC_PAUSE_EN      = 0x0701,
@@ -775,6 +776,17 @@ struct hclge_reset_cmd {
 	u8 fun_reset_vfid;
 	u8 rsv[22];
 };
+
+#define HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B	BIT(0)
+#define HCLGE_CMD_SERDES_DONE_B			BIT(0)
+#define HCLGE_CMD_SERDES_SUCCESS_B		BIT(1)
+struct hclge_serdes_lb_cmd {
+	u8 mask;
+	u8 enable;
+	u8 result;
+	u8 rsv[21];
+};
+
 #define HCLGE_DEFAULT_TX_BUF		0x4000	 /* 16k  bytes */
 #define HCLGE_TOTAL_PKT_BUF		0x108000 /* 1.03125M bytes */
 #define HCLGE_DEFAULT_DV		0xA000	 /* 40k byte */
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index fc813b7f20e8..92091221202b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -787,9 +787,10 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset)
 		    hdev->hw.mac.speed == HCLGE_MAC_SPEED_1G) {
 			count += 1;
 			handle->flags |= HNAE3_SUPPORT_MAC_LOOPBACK;
-		} else {
-			count = -EOPNOTSUPP;
 		}
+
+		count++;
+		handle->flags |= HNAE3_SUPPORT_SERDES_LOOPBACK;
 	} else if (stringset == ETH_SS_STATS) {
 		count = ARRAY_SIZE(g_mac_stats_string) +
 			ARRAY_SIZE(g_all_32bit_stats_string) +
@@ -3670,6 +3671,55 @@ static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en)
 	return ret;
 }
 
+static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en)
+{
+#define HCLGE_SERDES_RETRY_MS	10
+#define HCLGE_SERDES_RETRY_NUM	100
+	struct hclge_serdes_lb_cmd *req;
+	struct hclge_desc desc;
+	int ret, i = 0;
+
+	req = (struct hclge_serdes_lb_cmd *)&desc.data[0];
+	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK, false);
+
+	if (en) {
+		req->enable = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
+		req->mask = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
+	} else {
+		req->mask = HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
+	}
+
+	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+	if (ret) {
+		dev_err(&hdev->pdev->dev,
+			"serdes loopback set fail, ret = %d\n", ret);
+		return ret;
+	}
+
+	do {
+		msleep(HCLGE_SERDES_RETRY_MS);
+		hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_SERDES_LOOPBACK,
+					   true);
+		ret = hclge_cmd_send(&hdev->hw, &desc, 1);
+		if (ret) {
+			dev_err(&hdev->pdev->dev,
+				"serdes loopback get, ret = %d\n", ret);
+			return ret;
+		}
+	} while (++i < HCLGE_SERDES_RETRY_NUM &&
+		 !(req->result & HCLGE_CMD_SERDES_DONE_B));
+
+	if (!(req->result & HCLGE_CMD_SERDES_DONE_B)) {
+		dev_err(&hdev->pdev->dev, "serdes loopback set timeout\n");
+		return -EBUSY;
+	} else if (!(req->result & HCLGE_CMD_SERDES_SUCCESS_B)) {
+		dev_err(&hdev->pdev->dev, "serdes loopback set failed in fw\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static int hclge_set_loopback(struct hnae3_handle *handle,
 			      enum hnae3_loop loop_mode, bool en)
 {
@@ -3681,6 +3731,9 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 	case HNAE3_MAC_INTER_LOOP_MAC:
 		ret = hclge_set_mac_loopback(hdev, en);
 		break;
+	case HNAE3_MAC_INTER_LOOP_SERDES:
+		ret = hclge_set_serdes_loopback(hdev, en);
+		break;
 	default:
 		ret = -ENOTSUPP;
 		dev_err(&hdev->pdev->dev,
-- 
cgit v1.2.3


From 6c39d5278e62956238a681e4cfc69fae5507fc57 Mon Sep 17 00:00:00 2001
From: Xi Wang <wangxi11@huawei.com>
Date: Tue, 14 Aug 2018 17:13:13 +0100
Subject: net: hns3: Fix for command format parsing error in
 hclge_is_all_function_id_zero

According to the functional specification of hardware, the first
descriptor of response from command 'lookup vlan talbe' is not valid.
Currently, the first descriptor is parsed as normal value, which will
cause an expected error.

This patch fixes this problem by skipping the first descriptor.

Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support")
Signed-off-by: Xi Wang <wangxi11@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 92091221202b..5f30ea4c5142 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3930,7 +3930,7 @@ static bool hclge_is_all_function_id_zero(struct hclge_desc *desc)
 #define HCLGE_FUNC_NUMBER_PER_DESC 6
 	int i, j;
 
-	for (i = 0; i < HCLGE_DESC_NUMBER; i++)
+	for (i = 1; i < HCLGE_DESC_NUMBER; i++)
 		for (j = 0; j < HCLGE_FUNC_NUMBER_PER_DESC; j++)
 			if (desc[i].data[j])
 				return false;
-- 
cgit v1.2.3


From b01b7cf19bf4a677d5dd4e63b12d86a021db751d Mon Sep 17 00:00:00 2001
From: Fuyun Liang <liangfuyun1@huawei.com>
Date: Tue, 14 Aug 2018 17:13:14 +0100
Subject: net: hns3: Fix for information of phydev lost problem when down/up

Function call of phy_connect_direct will reinitialize phydev. Some
information like advertising will be lost. Phy_connect_direct only
needs to be called once. And driver can run well. This patch adds
some functions to ensure that phy_connect_direct is called only once
to solve the information of phydev lost problem occurring when we stop
the net and open it again.

Fixes: 46a3df9f9718 ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support
Signed-off-by: Fuyun Liang <liangfuyun1@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 24 +++++++++++++++++----
 .../ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c    | 25 ++++++++++++++++++----
 .../ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h    |  4 +++-
 3 files changed, 44 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 5f30ea4c5142..2e9c8b9a75ce 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -3782,7 +3782,7 @@ static int hclge_ae_start(struct hnae3_handle *handle)
 {
 	struct hclge_vport *vport = hclge_get_vport(handle);
 	struct hclge_dev *hdev = vport->back;
-	int i, ret;
+	int i;
 
 	for (i = 0; i < vport->alloc_tqps; i++)
 		hclge_tqp_enable(hdev, i, 0, true);
@@ -3796,9 +3796,7 @@ static int hclge_ae_start(struct hnae3_handle *handle)
 	/* reset tqp stats */
 	hclge_reset_tqp_stats(handle);
 
-	ret = hclge_mac_start_phy(hdev);
-	if (ret)
-		return ret;
+	hclge_mac_start_phy(hdev);
 
 	return 0;
 }
@@ -5417,6 +5415,16 @@ static void hclge_get_mdix_mode(struct hnae3_handle *handle,
 		*tp_mdix = ETH_TP_MDI;
 }
 
+static int hclge_init_instance_hw(struct hclge_dev *hdev)
+{
+	return hclge_mac_connect_phy(hdev);
+}
+
+static void hclge_uninit_instance_hw(struct hclge_dev *hdev)
+{
+	hclge_mac_disconnect_phy(hdev);
+}
+
 static int hclge_init_client_instance(struct hnae3_client *client,
 				      struct hnae3_ae_dev *ae_dev)
 {
@@ -5436,6 +5444,13 @@ static int hclge_init_client_instance(struct hnae3_client *client,
 			if (ret)
 				return ret;
 
+			ret = hclge_init_instance_hw(hdev);
+			if (ret) {
+			        client->ops->uninit_instance(&vport->nic,
+			                                     0);
+			        return ret;
+			}
+
 			if (hdev->roce_client &&
 			    hnae3_dev_roce_supported(hdev)) {
 				struct hnae3_client *rc = hdev->roce_client;
@@ -5498,6 +5513,7 @@ static void hclge_uninit_client_instance(struct hnae3_client *client,
 		if (client->type == HNAE3_CLIENT_ROCE)
 			return;
 		if (client->ops->uninit_instance) {
+			hclge_uninit_instance_hw(hdev);
 			client->ops->uninit_instance(&vport->nic, 0);
 			hdev->nic_client = NULL;
 			vport->nic.client = NULL;
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 2065ee2fd358..85a123d40e8b 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -193,7 +193,7 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
 		netdev_err(netdev, "failed to configure flow control.\n");
 }
 
-int hclge_mac_start_phy(struct hclge_dev *hdev)
+int hclge_mac_connect_phy(struct hclge_dev *hdev)
 {
 	struct net_device *netdev = hdev->vport[0].nic.netdev;
 	struct phy_device *phydev = hdev->hw.mac.phydev;
@@ -213,11 +213,29 @@ int hclge_mac_start_phy(struct hclge_dev *hdev)
 	phydev->supported &= HCLGE_PHY_SUPPORTED_FEATURES;
 	phydev->advertising = phydev->supported;
 
-	phy_start(phydev);
-
 	return 0;
 }
 
+void hclge_mac_disconnect_phy(struct hclge_dev *hdev)
+{
+	struct phy_device *phydev = hdev->hw.mac.phydev;
+
+	if (!phydev)
+		return;
+
+	phy_disconnect(phydev);
+}
+
+void hclge_mac_start_phy(struct hclge_dev *hdev)
+{
+	struct phy_device *phydev = hdev->hw.mac.phydev;
+
+	if (!phydev)
+		return;
+
+	phy_start(phydev);
+}
+
 void hclge_mac_stop_phy(struct hclge_dev *hdev)
 {
 	struct net_device *netdev = hdev->vport[0].nic.netdev;
@@ -227,5 +245,4 @@ void hclge_mac_stop_phy(struct hclge_dev *hdev)
 		return;
 
 	phy_stop(phydev);
-	phy_disconnect(phydev);
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
index bb3ce35e0d66..5fbf7dddb5d9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.h
@@ -5,7 +5,9 @@
 #define __HCLGE_MDIO_H
 
 int hclge_mac_mdio_config(struct hclge_dev *hdev);
-int hclge_mac_start_phy(struct hclge_dev *hdev);
+int hclge_mac_connect_phy(struct hclge_dev *hdev);
+void hclge_mac_disconnect_phy(struct hclge_dev *hdev);
+void hclge_mac_start_phy(struct hclge_dev *hdev);
 void hclge_mac_stop_phy(struct hclge_dev *hdev);
 
 #endif
-- 
cgit v1.2.3


From 60081dcc4fce385ade26d3145b2479789df0b7e5 Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Tue, 14 Aug 2018 17:13:15 +0100
Subject: net: hns3: Fix for phy link issue when using marvell phy driver

For marvell phy m88e1510, bit SUPPORTED_FIBRE of phydev->supported
is default on. Both phy_resume() and phy_suspend() will check the
SUPPORTED_FIBRE bit and write register of fibre page.

Currently in hns3 driver, the SUPPORTED_FIBRE bit will be cleared
after phy_connect_direct() finished. Because phy_resume() is called
in phy_connect_direct(), and phy_suspend() is called when disconnect
phy device, so the operation for fibre page register is not symmetrical.
It will cause phy link issue when reload hns3 driver.

This patch fixes it by disable the SUPPORTED_FIBRE before connecting
phy.

Fixes: 256727da7395 ("net: hns3: Add MDIO support to HNS3 Ethernet driver for hip08 SoC")
Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 85a123d40e8b..398971a062f4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -202,6 +202,8 @@ int hclge_mac_connect_phy(struct hclge_dev *hdev)
 	if (!phydev)
 		return 0;
 
+	phydev->supported &= ~SUPPORTED_FIBRE;
+
 	ret = phy_connect_direct(netdev, phydev,
 				 hclge_mac_adjust_link,
 				 PHY_INTERFACE_MODE_SGMII);
-- 
cgit v1.2.3


From 128b900de7df567ca7ca063bf5da4ed0f357db8c Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 14 Aug 2018 17:13:16 +0100
Subject: net: hns3: Fix desc num set to default when setting channel

When user set the channel num using "ethtool -L ethX", the desc num
of BD will set to default value, which will cause desc num set by
user lost problem.

This patch fixes it by restoring the desc num set by user when setting
channel num.

Fixes: 09f2af6405b8 ("net: hns3: add support to modify tqps number")
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../ethernet/hisilicon/hns3/hns3pf/hclge_main.c    | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 2e9c8b9a75ce..8577dfc799ad 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -1267,35 +1267,37 @@ static int hclge_map_tqps_to_func(struct hclge_dev *hdev, u16 func_id,
 	return ret;
 }
 
-static int  hclge_assign_tqp(struct hclge_vport *vport,
-			     struct hnae3_queue **tqp, u16 num_tqps)
+static int  hclge_assign_tqp(struct hclge_vport *vport)
 {
+	struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, alloced;
 
 	for (i = 0, alloced = 0; i < hdev->num_tqps &&
-	     alloced < num_tqps; i++) {
+	     alloced < kinfo->num_tqps; i++) {
 		if (!hdev->htqp[i].alloced) {
 			hdev->htqp[i].q.handle = &vport->nic;
 			hdev->htqp[i].q.tqp_index = alloced;
-			tqp[alloced] = &hdev->htqp[i].q;
+			hdev->htqp[i].q.desc_num = kinfo->num_desc;
+			kinfo->tqp[alloced] = &hdev->htqp[i].q;
 			hdev->htqp[i].alloced = true;
 			alloced++;
 		}
 	}
-	vport->alloc_tqps = num_tqps;
+	vport->alloc_tqps = kinfo->num_tqps;
 
 	return 0;
 }
 
-static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps)
+static int hclge_knic_setup(struct hclge_vport *vport,
+			    u16 num_tqps, u16 num_desc)
 {
 	struct hnae3_handle *nic = &vport->nic;
 	struct hnae3_knic_private_info *kinfo = &nic->kinfo;
 	struct hclge_dev *hdev = vport->back;
 	int i, ret;
 
-	kinfo->num_desc = hdev->num_desc;
+	kinfo->num_desc = num_desc;
 	kinfo->rx_buf_len = hdev->rx_buf_len;
 	kinfo->num_tc = min_t(u16, num_tqps, hdev->tm_info.num_tc);
 	kinfo->rss_size
@@ -1322,7 +1324,7 @@ static int hclge_knic_setup(struct hclge_vport *vport, u16 num_tqps)
 	if (!kinfo->tqp)
 		return -ENOMEM;
 
-	ret = hclge_assign_tqp(vport, kinfo->tqp, kinfo->num_tqps);
+	ret = hclge_assign_tqp(vport);
 	if (ret)
 		dev_err(&hdev->pdev->dev, "fail to assign TQPs %d.\n", ret);
 
@@ -1388,7 +1390,7 @@ static int hclge_vport_setup(struct hclge_vport *vport, u16 num_tqps)
 	nic->numa_node_mask = hdev->numa_node_mask;
 
 	if (hdev->ae_dev->dev_type == HNAE3_DEV_KNIC) {
-		ret = hclge_knic_setup(vport, num_tqps);
+		ret = hclge_knic_setup(vport, num_tqps, hdev->num_desc);
 		if (ret) {
 			dev_err(&hdev->pdev->dev, "knic setup failed %d\n",
 				ret);
@@ -5936,7 +5938,7 @@ static int hclge_set_channels(struct hnae3_handle *handle, u32 new_tqps_num)
 	/* Free old tqps, and reallocate with new tqp number when nic setup */
 	hclge_release_tqp(vport);
 
-	ret = hclge_knic_setup(vport, new_tqps_num);
+	ret = hclge_knic_setup(vport, new_tqps_num, kinfo->num_desc);
 	if (ret) {
 		dev_err(&hdev->pdev->dev, "setup nic fail, ret =%d\n", ret);
 		return ret;
-- 
cgit v1.2.3


From 26a07ccc1d0781fee3027e40a8bfa7a1a3358df3 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 14 Aug 2018 17:13:17 +0100
Subject: net: hns3: Remove tx ring BD len register in hns3_enet

There is no HNS3_RING_TX_RING_BD_LEN_REG register according
to UM, so this patch removes it.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 2 --
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h | 1 -
 2 files changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index a64d69c87f13..b7b9ee3f4d20 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2969,8 +2969,6 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring)
 		hns3_write_dev(q, HNS3_RING_TX_RING_BASEADDR_H_REG,
 			       (u32)((dma >> 31) >> 1));
 
-		hns3_write_dev(q, HNS3_RING_TX_RING_BD_LEN_REG,
-			       hns3_buf_size2type(ring->buf_size));
 		hns3_write_dev(q, HNS3_RING_TX_RING_BD_NUM_REG,
 			       ring->desc_num / 8 - 1);
 	}
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index e4b4a8f2ceaa..0f071a0f4ff9 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -37,7 +37,6 @@ enum hns3_nic_state {
 #define HNS3_RING_TX_RING_BASEADDR_L_REG	0x00040
 #define HNS3_RING_TX_RING_BASEADDR_H_REG	0x00044
 #define HNS3_RING_TX_RING_BD_NUM_REG		0x00048
-#define HNS3_RING_TX_RING_BD_LEN_REG		0x0004C
 #define HNS3_RING_TX_RING_TAIL_REG		0x00058
 #define HNS3_RING_TX_RING_HEAD_REG		0x0005C
 #define HNS3_RING_TX_RING_FBDNUM_REG		0x00060
-- 
cgit v1.2.3


From 1c77215480bcfa0852575180f997bd156f2aef17 Mon Sep 17 00:00:00 2001
From: Yunsheng Lin <linyunsheng@huawei.com>
Date: Tue, 14 Aug 2018 17:13:18 +0100
Subject: net: hns3: Set tx ring' tc info when netdev is up

The HNS3_RING_TX_RING_TC_REG register is used to map tx ring to
specific tc, the tx queue to tc mapping is needed by the hardware
to do the correct tx schedule.

Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 24 ++++++++++++++++++++++++
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.h |  1 +
 2 files changed, 25 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index b7b9ee3f4d20..b28c7e142308 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -2974,6 +2974,28 @@ static void hns3_init_ring_hw(struct hns3_enet_ring *ring)
 	}
 }
 
+static void hns3_init_tx_ring_tc(struct hns3_nic_priv *priv)
+{
+	struct hnae3_knic_private_info *kinfo = &priv->ae_handle->kinfo;
+	int i;
+
+	for (i = 0; i < HNAE3_MAX_TC; i++) {
+		struct hnae3_tc_info *tc_info = &kinfo->tc_info[i];
+		int j;
+
+		if (!tc_info->enable)
+			continue;
+
+		for (j = 0; j < tc_info->tqp_count; j++) {
+			struct hnae3_queue *q;
+
+			q = priv->ring_data[tc_info->tqp_offset + j].ring->tqp;
+			hns3_write_dev(q, HNS3_RING_TX_RING_TC_REG,
+				       tc_info->tc);
+		}
+	}
+}
+
 int hns3_init_all_ring(struct hns3_nic_priv *priv)
 {
 	struct hnae3_handle *h = priv->ae_handle;
@@ -3385,6 +3407,8 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h)
 		rx_ring->next_to_use = 0;
 	}
 
+	hns3_init_tx_ring_tc(priv);
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
index 0f071a0f4ff9..a02a96aee2a2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h
@@ -37,6 +37,7 @@ enum hns3_nic_state {
 #define HNS3_RING_TX_RING_BASEADDR_L_REG	0x00040
 #define HNS3_RING_TX_RING_BASEADDR_H_REG	0x00044
 #define HNS3_RING_TX_RING_BD_NUM_REG		0x00048
+#define HNS3_RING_TX_RING_TC_REG		0x00050
 #define HNS3_RING_TX_RING_TAIL_REG		0x00058
 #define HNS3_RING_TX_RING_HEAD_REG		0x0005C
 #define HNS3_RING_TX_RING_FBDNUM_REG		0x00060
-- 
cgit v1.2.3


From 3e85af6a6812d2d4778c3b19f17384c2a9f73200 Mon Sep 17 00:00:00 2001
From: Peng Li <lipeng321@huawei.com>
Date: Tue, 14 Aug 2018 17:13:19 +0100
Subject: net: hns3: Add vlan filter setting by ethtool command -K

Revision(0x20) HW does not support enabling or disabling individual
netdev's HW_VLAN_CTAG_FILTER feature, and Revision(0x21) supports
enabling or disabling individual netdev's HW_VLAN_CTAG_FILTER
feature.

Signed-off-by: Peng Li <lipeng321@huawei.com>
Signed-off-by: Salil Mehta <salil.mehta@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/hisilicon/hns3/hns3_enet.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
index b28c7e142308..3554dca7a680 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
@@ -1673,6 +1673,9 @@ static struct pci_driver hns3_driver = {
 /* set default feature to hns3 */
 static void hns3_set_default_feature(struct net_device *netdev)
 {
+	struct hnae3_handle *h = hns3_get_handle(netdev);
+	struct pci_dev *pdev = h->pdev;
+
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
 	netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM |
@@ -1706,6 +1709,9 @@ static void hns3_set_default_feature(struct net_device *netdev)
 		NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE |
 		NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL |
 		NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
+	if (pdev->revision != 0x20)
+		netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 }
 
 static int hns3_alloc_buffer(struct hns3_enet_ring *ring,
-- 
cgit v1.2.3


From 1c89a8e3d9a235454169e189ea6c463bfa8749ab Mon Sep 17 00:00:00 2001
From: Alexander Aring <aring@mojatatu.com>
Date: Sun, 12 Aug 2018 16:24:56 -0400
Subject: ieee802154: hwsim: using right kind of iteration

This patch fixes the error path to unsubscribe all other phy's from
current phy. The actually code using a wrong kind of list iteration may
copied from the case to unsubscribe the current phy from all other
phy's.

Cc: Stefan Schmidt <stefan@datenfreihafen.org>
Reported-by: Dan Carpenter <dan.carpenter@oracle.com>
Fixes: f25da51fdc38 ("ieee802154: hwsim: add replacement for fakelb")
Signed-off-by: Alexander Aring <aring@mojatatu.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ieee802154/mac802154_hwsim.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ieee802154/mac802154_hwsim.c b/drivers/net/ieee802154/mac802154_hwsim.c
index 07a493dea11e..bf70ab892e69 100644
--- a/drivers/net/ieee802154/mac802154_hwsim.c
+++ b/drivers/net/ieee802154/mac802154_hwsim.c
@@ -735,10 +735,12 @@ static int hwsim_subscribe_all_others(struct hwsim_phy *phy)
 	return 0;
 
 me_fail:
-	list_for_each_entry(phy, &hwsim_phys, list) {
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &phy->edges, list) {
 		list_del_rcu(&e->list);
 		hwsim_free_edge(e);
 	}
+	rcu_read_unlock();
 sub_fail:
 	hwsim_edge_unsubscribe_me(phy);
 	return -ENOMEM;
-- 
cgit v1.2.3


From 66b51b0a0341fd42ce657739bdae0561b0410a85 Mon Sep 17 00:00:00 2001
From: Jeremy Cline <jcline@redhat.com>
Date: Mon, 13 Aug 2018 22:23:13 +0000
Subject: net: sock_diag: Fix spectre v1 gadget in __sock_diag_cmd()

req->sdiag_family is a user-controlled value that's used as an array
index. Sanitize it after the bounds check to avoid speculative
out-of-bounds array access.

This also protects the sock_is_registered() call, so this removes the
sanitize call there.

Fixes: e978de7a6d38 ("net: socket: Fix potential spectre v1 gadget in sock_is_registered")
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: konrad.wilk@oracle.com
Cc: jamie.iles@oracle.com
Cc: liran.alon@oracle.com
Cc: stable@vger.kernel.org
Signed-off-by: Jeremy Cline <jcline@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/sock_diag.c | 2 ++
 net/socket.c         | 3 +--
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c
index c37b5be7c5e4..3312a5849a97 100644
--- a/net/core/sock_diag.c
+++ b/net/core/sock_diag.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/tcp.h>
 #include <linux/workqueue.h>
+#include <linux/nospec.h>
 
 #include <linux/inet_diag.h>
 #include <linux/sock_diag.h>
@@ -218,6 +219,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
 
 	if (req->sdiag_family >= AF_MAX)
 		return -EINVAL;
+	req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX);
 
 	if (sock_diag_handlers[req->sdiag_family] == NULL)
 		sock_load_diag_module(req->sdiag_family, 0);
diff --git a/net/socket.c b/net/socket.c
index b91949168a87..270f28264cb1 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -2697,8 +2697,7 @@ EXPORT_SYMBOL(sock_unregister);
 
 bool sock_is_registered(int family)
 {
-	return family < NPROTO &&
-		rcu_access_pointer(net_families[array_index_nospec(family, NPROTO)]);
+	return family < NPROTO && rcu_access_pointer(net_families[family]);
 }
 
 static int __init sock_init(void)
-- 
cgit v1.2.3


From 6feddb4913011437aaafe34d672aceebdb7c201f Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 14 Aug 2018 12:06:43 +0300
Subject: net: dsa: mv88e6xxx: bitwise vs logical bug

We are trying to test if these flags are set but there are some && vs &
typos.

Fixes: efd1ba6af93f ("net: dsa: mv88e6xxx: Add SERDES phydev_mac_change up for 6390")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/serdes.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c
index f007d109b385..e82983975754 100644
--- a/drivers/net/dsa/mv88e6xxx/serdes.c
+++ b/drivers/net/dsa/mv88e6xxx/serdes.c
@@ -502,8 +502,8 @@ static irqreturn_t mv88e6390_serdes_thread_fn(int irq, void *dev_id)
 		err = mv88e6390_serdes_irq_status_sgmii(chip, lane, &status);
 		if (err)
 			goto out;
-		if (status && (MV88E6390_SGMII_INT_LINK_DOWN ||
-			       MV88E6390_SGMII_INT_LINK_UP)) {
+		if (status & (MV88E6390_SGMII_INT_LINK_DOWN |
+			      MV88E6390_SGMII_INT_LINK_UP)) {
 			ret = IRQ_HANDLED;
 			mv88e6390_serdes_irq_link_sgmii(chip, port->port, lane);
 		}
-- 
cgit v1.2.3


From 96d18d8254dc5a3f0067a629866af4165b3afe32 Mon Sep 17 00:00:00 2001
From: Nick Desaulniers <ndesaulniers@google.com>
Date: Wed, 1 Aug 2018 14:57:59 -0700
Subject: inet/connection_sock: prefer _THIS_IP_ to current_text_addr

As part of the effort to reduce the code duplication between _THIS_IP_
and current_text_addr(), let's consolidate callers of
current_text_addr() to use _THIS_IP_.

Signed-off-by: Nick Desaulniers <ndesaulniers@google.com>
Acked-by: David S. Miller <davem@davemloft.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/inet_connection_sock.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index fa43b82607d9..371b3b45fd5c 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -19,6 +19,7 @@
 #include <linux/string.h>
 #include <linux/timer.h>
 #include <linux/poll.h>
+#include <linux/kernel.h>
 
 #include <net/inet_sock.h>
 #include <net/request_sock.h>
@@ -225,7 +226,7 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
 
 	if (when > max_when) {
 		pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
-			 sk, what, when, current_text_addr());
+			 sk, what, when, (void *)_THIS_IP_);
 		when = max_when;
 	}
 
-- 
cgit v1.2.3


From f6f7a26abd14cfa0f3f3009a2d274d36798668bb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 14 Aug 2018 11:07:42 +0200
Subject: rds: fix building with IPV6=m

When CONFIG_RDS_TCP is built-in and CONFIG_IPV6 is a loadable
module, we get a link error agains the modular ipv6_chk_addr()
function:

net/rds/tcp.o: In function `rds_tcp_laddr_check':
tcp.c:(.text+0x3b2): undefined reference to `ipv6_chk_addr'

This adds back a dependency that forces RDS_TCP to also be
a loadable module when IPV6 is one.

Fixes: e65d4d96334e ("rds: Remove IPv6 dependency")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/rds/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/rds/Kconfig b/net/rds/Kconfig
index 41f75563b54b..01b3bd6a3708 100644
--- a/net/rds/Kconfig
+++ b/net/rds/Kconfig
@@ -16,6 +16,7 @@ config RDS_RDMA
 config RDS_TCP
 	tristate "RDS over TCP"
 	depends on RDS
+	depends on IPV6 || !IPV6
 	---help---
 	  Allow RDS to use TCP as a transport.
 	  This transport does not support RDMA operations.
-- 
cgit v1.2.3


From e29129fcac4b7fe9e5d087e2590b9e2e7125e84c Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@oracle.com>
Date: Tue, 14 Aug 2018 12:09:05 +0300
Subject: net: dsa: mv88e6xxx: missing unlock on error path

We added a new error path, but we need to drop the lock before we return.

Fixes: 2d2e1dd29962 ("net: dsa: mv88e6xxx: Cache the port cmode")
Signed-off-by: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 17752316ab10..8da3d39e3218 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2408,7 +2408,7 @@ static int mv88e6xxx_setup(struct dsa_switch *ds)
 		if (chip->info->ops->port_get_cmode) {
 			err = chip->info->ops->port_get_cmode(chip, i, &cmode);
 			if (err)
-				return err;
+				goto unlock;
 
 			chip->ports[i].cmode = cmode;
 		}
-- 
cgit v1.2.3


From 6e24dcad021f82636709108a7f4c53f06ddf9ba0 Mon Sep 17 00:00:00 2001
From: Ganesh Goudar <ganeshgr@chelsio.com>
Date: Tue, 14 Aug 2018 16:21:37 +0530
Subject: cxgb4: Add new T5 PCI device ids 0x50af and 0x50b0

Signed-off-by: Ganesh Goudar <ganeshgr@chelsio.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
index e3adf435913e..60df66f4d21c 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h
@@ -189,6 +189,8 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN
 	CH_PCI_ID_TABLE_FENTRY(0x50ac), /* Custom T540-BT */
 	CH_PCI_ID_TABLE_FENTRY(0x50ad), /* Custom T520-CR */
 	CH_PCI_ID_TABLE_FENTRY(0x50ae), /* Custom T540-XL-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x50af), /* Custom T580-KR-SO */
+	CH_PCI_ID_TABLE_FENTRY(0x50b0), /* Custom T520-CR-LOM */
 
 	/* T6 adapters:
 	 */
-- 
cgit v1.2.3


From 21f2706b20100bb3db378461ab9b8e2035309b5b Mon Sep 17 00:00:00 2001
From: Xiao Liang <xiliang@redhat.com>
Date: Tue, 14 Aug 2018 23:21:28 +0800
Subject: xen-netfront: fix warn message as irq device name has '/'

There is a call trace generated after commit 2d408c0d4574b01b9ed45e02516888bf925e11a9(
xen-netfront: fix queue name setting). There is no 'device/vif/xx-q0-tx' file found
under /proc/irq/xx/.

This patch only picks up device type and id as its name.

With the patch, now /proc/interrupts looks like below and the warning message gone:
 70:         21          0          0          0   xen-dyn    -event     vif0-q0-tx
 71:         15          0          0          0   xen-dyn    -event     vif0-q0-rx
 72:         14          0          0          0   xen-dyn    -event     vif0-q1-tx
 73:         33          0          0          0   xen-dyn    -event     vif0-q1-rx
 74:         12          0          0          0   xen-dyn    -event     vif0-q2-tx
 75:         24          0          0          0   xen-dyn    -event     vif0-q2-rx
 76:         19          0          0          0   xen-dyn    -event     vif0-q3-tx
 77:         21          0          0          0   xen-dyn    -event     vif0-q3-rx

Below is call trace information without this patch:

name 'device/vif/0-q0-tx'
WARNING: CPU: 2 PID: 37 at fs/proc/generic.c:174 __xlate_proc_name+0x85/0xa0
RIP: 0010:__xlate_proc_name+0x85/0xa0
RSP: 0018:ffffb85c40473c18 EFLAGS: 00010286
RAX: 0000000000000000 RBX: 0000000000000006 RCX: 0000000000000006
RDX: 0000000000000007 RSI: 0000000000000096 RDI: ffff984c7f516930
RBP: ffffb85c40473cb8 R08: 000000000000002c R09: 0000000000000229
R10: 0000000000000000 R11: 0000000000000001 R12: ffffb85c40473c98
R13: ffffb85c40473cb8 R14: ffffb85c40473c50 R15: 0000000000000000
FS:  0000000000000000(0000) GS:ffff984c7f500000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f69b6899038 CR3: 000000001c20a006 CR4: 00000000001606e0
Call Trace:
__proc_create+0x45/0x230
? snprintf+0x49/0x60
proc_mkdir_data+0x35/0x90
register_handler_proc+0xef/0x110
? proc_register+0xfc/0x110
? proc_create_data+0x70/0xb0
__setup_irq+0x39b/0x660
? request_threaded_irq+0xad/0x160
request_threaded_irq+0xf5/0x160
? xennet_tx_buf_gc+0x1d0/0x1d0 [xen_netfront]
bind_evtchn_to_irqhandler+0x3d/0x70
? xenbus_alloc_evtchn+0x41/0xa0
netback_changed+0xa46/0xcda [xen_netfront]
? find_watch+0x40/0x40
xenwatch_thread+0xc5/0x160
? finish_wait+0x80/0x80
kthread+0x112/0x130
? kthread_create_worker_on_cpu+0x70/0x70
ret_from_fork+0x35/0x40
Code: 81 5c 00 48 85 c0 75 cc 5b 49 89 2e 31 c0 5d 4d 89 3c 24 41 5c 41 5d 41 5e 41 5f c3 4c 89 ee 48 c7 c7 40 4f 0e b4 e8 65 ea d8 ff <0f> 0b b8 fe ff ff ff 5b 5d 41 5c 41 5d 41 5e 41 5f c3 66 0f 1f
---[ end trace 650e5561b0caab3a ]---

Signed-off-by: Xiao Liang <xiliang@redhat.com>
Reviewed-by: Juergen Gross <jgross@suse.com>

Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/xen-netfront.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c
index 2ff874b6ec89..73f596a90c69 100644
--- a/drivers/net/xen-netfront.c
+++ b/drivers/net/xen-netfront.c
@@ -1604,14 +1604,16 @@ static int xennet_init_queue(struct netfront_queue *queue)
 {
 	unsigned short i;
 	int err = 0;
+	char *devid;
 
 	spin_lock_init(&queue->tx_lock);
 	spin_lock_init(&queue->rx_lock);
 
 	timer_setup(&queue->rx_refill_timer, rx_refill_timeout, 0);
 
-	snprintf(queue->name, sizeof(queue->name), "%s-q%u",
-		 queue->info->xbdev->nodename, queue->id);
+	devid = strrchr(queue->info->xbdev->nodename, '/') + 1;
+	snprintf(queue->name, sizeof(queue->name), "vif%s-q%u",
+		 devid, queue->id);
 
 	/* Initialise tx_skbs as a free chain containing every entry. */
 	queue->tx_skb_freelist = 0;
-- 
cgit v1.2.3


From 4597b62f7a60d912a2bd00ca574e6bc7b87be905 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavo@embeddedor.com>
Date: Tue, 14 Aug 2018 11:20:21 -0500
Subject: net: filter: mark expected switch fall-through

In preparation to enabling -Wimplicit-fallthrough, mark switch cases
where we are expecting to fall through.

Addresses-Coverity-ID: 1472592 ("Missing break in switch")
Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/core/filter.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 15b9d2df92ca..fd423ce3da34 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7235,6 +7235,7 @@ sk_reuseport_is_valid_access(int off, int size,
 	case offsetof(struct sk_reuseport_md, eth_protocol):
 		if (size < FIELD_SIZEOF(struct sk_buff, protocol))
 			return false;
+		/* fall through */
 	case offsetof(struct sk_reuseport_md, ip_protocol):
 	case offsetof(struct sk_reuseport_md, bind_inany):
 	case offsetof(struct sk_reuseport_md, len):
-- 
cgit v1.2.3


From b19b46346f483ae055fa027cb2d5c2ca91484b91 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 14 Aug 2018 19:10:50 +0200
Subject: hv/netvsc: Fix NULL dereference at single queue mode fallback

The recent commit 916c5e1413be ("hv/netvsc: fix handling of fallback
to single queue mode") tried to fix the fallback behavior to a single
queue mode, but it changed the function to return zero incorrectly,
while the function should return an object pointer.  Eventually this
leads to a NULL dereference at the callers that expect non-NULL
value.

Fix it by returning the proper net_device object.

Fixes: 916c5e1413be ("hv/netvsc: fix handling of fallback to single queue mode")
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Reviewed-by: Stephen Hemminger <stephen@networkplumber.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/rndis_filter.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index 408ece27131c..2a5209f23f29 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1338,7 +1338,7 @@ out:
 	/* setting up multiple channels failed */
 	net_device->max_chn = 1;
 	net_device->num_chn = 1;
-	return 0;
+	return net_device;
 
 err_dev_remv:
 	rndis_filter_device_remove(dev, net_device);
-- 
cgit v1.2.3


From 26a1ccc6c117be8e33e0410fce8c5298b0015b99 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.king@canonical.com>
Date: Mon, 13 Aug 2018 15:00:32 +0100
Subject: bpf: test: fix spelling mistake "REUSEEPORT" -> "REUSEPORT"

Trivial fix to spelling mistake in error message

Signed-off-by: Colin Ian King <colin.king@canonical.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/bpf/test_maps.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 4b7c74f5faa7..6f54f84144a0 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -1191,7 +1191,7 @@ static void prepare_reuseport_grp(int type, int map_fd,
 
 		err = setsockopt(fd64, SOL_SOCKET, SO_REUSEPORT,
 				 &optval, sizeof(optval));
-		CHECK(err == -1, "setsockopt(SO_REUSEEPORT)",
+		CHECK(err == -1, "setsockopt(SO_REUSEPORT)",
 		      "err:%d errno:%d\n", err, errno);
 
 		/* reuseport_array does not allow unbound sk */
-- 
cgit v1.2.3


From 792adb90fa724ce07c0171cbc96b9215af4b1045 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 14 Aug 2018 20:50:47 +0200
Subject: x86/init: fix build with CONFIG_SWAP=n

The introduction of generic_max_swapfile_size and arch-specific versions has
broken linking on x86 with CONFIG_SWAP=n due to undefined reference to
'generic_max_swapfile_size'. Fix it by compiling the x86-specific
max_swapfile_size() only with CONFIG_SWAP=y.

Reported-by: Tomas Pruzina <pruzinat@gmail.com>
Fixes: 377eeaa8e11f ("x86/speculation/l1tf: Limit swap file size to MAX_PA/2")
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/mm/init.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 156ed8154af8..acfab322fbe0 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -914,6 +914,7 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache)
 	__pte2cachemode_tbl[entry] = cache;
 }
 
+#ifdef CONFIG_SWAP
 unsigned long max_swapfile_size(void)
 {
 	unsigned long pages;
@@ -934,3 +935,4 @@ unsigned long max_swapfile_size(void)
 	}
 	return pages;
 }
+#endif
-- 
cgit v1.2.3


From b72ae8cac0caff86fe414fceb940655c2d1371c9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Sun, 29 Jul 2018 16:16:56 +0300
Subject: PCI: Add PCI_DEVICE_DATA() macro to fully describe device ID entry

There are a lot of examples in the kernel where PCI_VDEVICE() is used and
still looks not so convenient due to additional driver_data field attached.

Introduce PCI_DEVICE_DATA() macro to fully describe device ID entry in
shortest possible form. For example,

  before:

    { PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_MRFLD),
      (kernel_ulong_t) &dwc3_pci_mrfld_properties, },

  after:

    { PCI_DEVICE_DATA(INTEL, MRFLD, &dwc3_pci_mrfld_properties) },

Drivers can be converted later on in independent way.

While here, remove the unused macro with the same name from Ralink wireless
driver.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Kalle Valo <kvalo@codeaurora.org>	# for rt2x00
---
 drivers/net/wireless/ralink/rt2x00/rt2x00pci.h |  6 ------
 include/linux/pci.h                            | 15 +++++++++++++++
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h
index bc0ca5f58f38..283e2e607bba 100644
--- a/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h
+++ b/drivers/net/wireless/ralink/rt2x00/rt2x00pci.h
@@ -27,12 +27,6 @@
 #include <linux/io.h>
 #include <linux/pci.h>
 
-/*
- * This variable should be used with the
- * pci_driver structure initialization.
- */
-#define PCI_DEVICE_DATA(__ops)	.driver_data = (kernel_ulong_t)(__ops)
-
 /*
  * PCI driver handlers.
  */
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 340029b2fb38..bf3665c534c2 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -819,6 +819,21 @@ struct pci_driver {
 	.vendor = PCI_VENDOR_ID_##vend, .device = (dev), \
 	.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0
 
+/**
+ * PCI_DEVICE_DATA - macro used to describe a specific PCI device in very short form
+ * @vend: the vendor name (without PCI_VENDOR_ID_ prefix)
+ * @dev: the device name (without PCI_DEVICE_ID_<vend>_ prefix)
+ * @data: the driver data to be filled
+ *
+ * This macro is used to create a struct pci_device_id that matches a
+ * specific PCI device.  The subvendor, and subdevice fields will be set
+ * to PCI_ANY_ID.
+ */
+#define PCI_DEVICE_DATA(vend, dev, data) \
+	.vendor = PCI_VENDOR_ID_##vend, .device = PCI_DEVICE_ID_##vend##_##dev, \
+	.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0, \
+	.driver_data = (kernel_ulong_t)(data)
+
 enum {
 	PCI_REASSIGN_ALL_RSRC	= 0x00000001,	/* Ignore firmware setup */
 	PCI_REASSIGN_ALL_BUS	= 0x00000002,	/* Reassign all bus numbers */
-- 
cgit v1.2.3


From 6eaf2781137842429c447bb491402b231df8a0f1 Mon Sep 17 00:00:00 2001
From: Bert Kenward <bkenward@solarflare.com>
Date: Thu, 26 Jul 2018 16:21:29 +0100
Subject: PCI/VPD: Check for VPD access completion before checking for timeout

Previously we checked the timeout before checking the VPD access completion
bit.  On a very heavily loaded system this can cause VPD access to timeout.
Check the completion bit before checking the timeout.

Signed-off-by: Bert Kenward <bkenward@solarflare.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/vpd.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c
index 8617565ba561..4963c2e2bd4c 100644
--- a/drivers/pci/vpd.c
+++ b/drivers/pci/vpd.c
@@ -146,7 +146,7 @@ static int pci_vpd_wait(struct pci_dev *dev)
 	if (!vpd->busy)
 		return 0;
 
-	while (time_before(jiffies, timeout)) {
+	do {
 		ret = pci_user_read_config_word(dev, vpd->cap + PCI_VPD_ADDR,
 						&status);
 		if (ret < 0)
@@ -160,10 +160,13 @@ static int pci_vpd_wait(struct pci_dev *dev)
 		if (fatal_signal_pending(current))
 			return -EINTR;
 
+		if (time_after(jiffies, timeout))
+			break;
+
 		usleep_range(10, max_sleep);
 		if (max_sleep < 1024)
 			max_sleep *= 2;
-	}
+	} while (true);
 
 	pci_warn(dev, "VPD access failed.  This is likely a firmware bug on this device.  Contact the card vendor for a firmware update\n");
 	return -ETIMEDOUT;
-- 
cgit v1.2.3


From 923aa4c378f9c7bbe2dff6f5632f95815b7700e9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 5 Aug 2018 22:31:03 +0200
Subject: PCI/MSI: Set IRQCHIP_ONESHOT_SAFE for PCI-MSI irqchips

If flag IRQCHIP_ONESHOT_SAFE isn't set for an irqchip and we have a
threaded interrupt with no primary handler, flag IRQF_ONESHOT needs to be
set for the interrupt, causing some overhead in the threaded interrupt
handler.  For more detailed explanation also check following comment in
__setup_irq():

  The interrupt was requested with handler = NULL, so we use the default
  primary handler for it. But it does not have the oneshot flag set.  In
  combination with level interrupts this is deadly, because the default
  primary handler just wakes the thread, then the irq lines is reenabled,
  but the device still has the level irq asserted.  Rinse and repeat....

  While this works for edge type interrupts, we play it safe and reject
  unconditionally because we can't say for sure which type this interrupt
  really has.  The type flags are unreliable as the underlying chip
  implementation can override them.

Another comment in __setup_irq() gives a hint already that this
overhead can be avoided for PCI-MSI:

  Some irq chips like MSI based interrupts are per se one shot safe.  Check
  the chip flags, so we can avoid the unmask dance at the end of the
  threaded handler for those.

Following this let's mark all PCI-MSI irqchips as oneshot-safe.

See also discussion here:
https://lkml.kernel.org/r/alpine.DEB.2.21.1808032136490.1658@nanos.tec.linutronix.de

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/msi.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index 4d88afdfc843..f2ef896464b3 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -1446,6 +1446,9 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
 		info->flags |= MSI_FLAG_MUST_REACTIVATE;
 
+	/* PCI-MSI is oneshot-safe */
+	info->chip->flags |= IRQCHIP_ONESHOT_SAFE;
+
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (!domain)
 		return NULL;
-- 
cgit v1.2.3


From 269777aa530f3438ec1781586cdac0b5fe47b061 Mon Sep 17 00:00:00 2001
From: Abel Vesa <abelvesa@linux.com>
Date: Wed, 15 Aug 2018 00:26:00 +0300
Subject: cpu/hotplug: Non-SMP machines do not make use of booted_once

Commit 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once")
breaks non-SMP builds.

[ I suspect the 'bool' fields should just be made to be bitfields and be
  exposed regardless of configuration, but that's a separate cleanup
  that I'll leave to the owners of this file for later.   - Linus ]

Fixes: 0cc3cd21657b ("cpu/hotplug: Boot HT siblings at least once")
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Abel Vesa <abelvesa@linux.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 kernel/cpu.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 90ec528a6e32..ed44d7d34c2d 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2278,6 +2278,8 @@ void __init boot_cpu_init(void)
  */
 void __init boot_cpu_hotplug_init(void)
 {
+#ifdef CONFIG_SMP
 	this_cpu_write(cpuhp_state.booted_once, true);
+#endif
 	this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
 }
-- 
cgit v1.2.3


From d0055f351e647f33f3b0329bff022213bf8aa085 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 14 Aug 2018 23:38:57 +0200
Subject: x86/smp: fix non-SMP broken build due to redefinition of
 apic_id_is_primary_thread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The function has an inline "return false;" definition with CONFIG_SMP=n
but the "real" definition is also visible leading to "redefinition of
‘apic_id_is_primary_thread’" compiler error.

Guard it with #ifdef CONFIG_SMP

Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Fixes: 6a4d2657e048 ("x86/smp: Provide topology_is_primary_thread()")
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/apic/apic.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 87ff6235bbfe..84132eddb5a8 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -2193,6 +2193,7 @@ static int cpuid_to_apicid[] = {
 	[0 ... NR_CPUS - 1] = -1,
 };
 
+#ifdef CONFIG_SMP
 /**
  * apic_id_is_primary_thread - Check whether APIC ID belongs to a primary thread
  * @id:	APIC ID to check
@@ -2207,6 +2208,7 @@ bool apic_id_is_primary_thread(unsigned int apicid)
 	mask = (1U << (fls(smp_num_siblings) - 1)) - 1;
 	return !(apicid & mask);
 }
+#endif
 
 /*
  * Should use this API to allocate logical CPU IDs to keep nr_logical_cpuids
-- 
cgit v1.2.3


From 2538fb89b8f4ee9e1c1759cfb3c7989d9ef1f6e7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <jakub.kicinski@netronome.com>
Date: Tue, 14 Aug 2018 16:48:50 -0700
Subject: PCI: Limit config space size for Netronome NFP5000

Like the NFP4000 and NFP6000, the NFP5000 as an erratum where reading/
writing to PCI config space addresses above 0x600 can cause the NFP to
generate PCIe completion timeouts.

Limit the NFP5000's PF's config space size to 0x600 bytes as is already
done for the NFP4000 and NFP6000.

The NFP5000's VF is 0x6003 (PCI_DEVICE_ID_NETRONOME_NFP6000_VF), the same
device ID as the NFP6000's VF.  Thus, its config space is already limited
by the existing use of quirk_nfp6000().

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Tony Egan <tony.egan@netronome.com>
---
 drivers/pci/quirks.c    | 1 +
 include/linux/pci_ids.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 502275c092ae..7743cd56b89a 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -460,6 +460,7 @@ static void quirk_nfp6000(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP4000,	quirk_nfp6000);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP6000,	quirk_nfp6000);
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP5000,	quirk_nfp6000);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NETRONOME,	PCI_DEVICE_ID_NETRONOME_NFP6000_VF,	quirk_nfp6000);
 
 /*  On IBM Crocodile ipr SAS adapters, expand BAR to system page size */
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 29502238e510..381fc009551d 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2541,6 +2541,7 @@
 #define PCI_DEVICE_ID_NETRONOME_NFP3200	0x3200
 #define PCI_DEVICE_ID_NETRONOME_NFP3240	0x3240
 #define PCI_DEVICE_ID_NETRONOME_NFP4000	0x4000
+#define PCI_DEVICE_ID_NETRONOME_NFP5000	0x5000
 #define PCI_DEVICE_ID_NETRONOME_NFP6000	0x6000
 #define PCI_DEVICE_ID_NETRONOME_NFP6000_VF	0x6003
 
-- 
cgit v1.2.3


From c5f45fbb464e49d94fc5e53e7f7885bcbb5be545 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Tue, 7 Aug 2018 09:42:15 -0700
Subject: mailbox: add MODULE_LICENSE() for mtk-cmdq-mailbox.c

Fix missing MODULE_LICENSE() in mtk-cmdq-mailbox.c:

WARNING: modpost: missing MODULE_LICENSE() in drivers/mailbox/mtk-cmdq-mailbox.o

Fixes: 623a6143a845 ("mailbox: mediatek: Add Mediatek CMDQ driver")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Cc: <linux-mediatek@lists.infradead.org>
Cc: CK Hu <ck.hu@mediatek.com>
Cc: Houlong Wei <houlong.wei@mediatek.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/mtk-cmdq-mailbox.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 6f92c5ee12f7..aec46d5d3506 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -567,3 +567,5 @@ static void __exit cmdq_drv_exit(void)
 
 subsys_initcall(cmdq_drv_init);
 module_exit(cmdq_drv_exit);
+
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 480285bd11e63d9e225397516db39430f3e1b9c4 Mon Sep 17 00:00:00 2001
From: Dong Aisheng <aisheng.dong@nxp.com>
Date: Fri, 3 Aug 2018 07:29:16 +0200
Subject: dt-bindings: arm: fsl: add mu binding doc

The Messaging Unit module enables two processors within
the SoC to communicate and coordinate by passing messages
(e.g. data, status and control) through the MU interface.

Cc: Shawn Guo <shawnguo@kernel.org>
Cc: Sascha Hauer <kernel@pengutronix.de>
Cc: Fabio Estevam <fabio.estevam@nxp.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: devicetree@vger.kernel.org
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Dong Aisheng <aisheng.dong@nxp.com>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../devicetree/bindings/mailbox/fsl,mu.txt         | 34 ++++++++++++++++++++++
 1 file changed, 34 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/mailbox/fsl,mu.txt

diff --git a/Documentation/devicetree/bindings/mailbox/fsl,mu.txt b/Documentation/devicetree/bindings/mailbox/fsl,mu.txt
new file mode 100644
index 000000000000..90e4905dfc69
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/fsl,mu.txt
@@ -0,0 +1,34 @@
+NXP i.MX Messaging Unit (MU)
+--------------------------------------------------------------------
+
+The Messaging Unit module enables two processors within the SoC to
+communicate and coordinate by passing messages (e.g. data, status
+and control) through the MU interface. The MU also provides the ability
+for one processor to signal the other processor using interrupts.
+
+Because the MU manages the messaging between processors, the MU uses
+different clocks (from each side of the different peripheral buses).
+Therefore, the MU must synchronize the accesses from one side to the
+other. The MU accomplishes synchronization using two sets of matching
+registers (Processor A-facing, Processor B-facing).
+
+Messaging Unit Device Node:
+=============================
+
+Required properties:
+-------------------
+- compatible :	should be "fsl,<chip>-mu", the supported chips include
+		imx8qxp, imx8qm.
+- reg :		Should contain the registers location and length
+- interrupts :	Interrupt number. The interrupt specifier format depends
+		on the interrupt controller parent.
+- #mbox-cells:  Must be 0. Number of cells in a mailbox
+
+Examples:
+--------
+lsio_mu0: mailbox@5d1b0000 {
+	compatible = "fsl,imx8qxp-mu";
+	reg = <0x0 0x5d1b0000 0x0 0x10000>;
+	interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+	#mbox-cells = <0>;
+};
-- 
cgit v1.2.3


From d6ef139c83cc562b29a5cdac270f0a562c1c8eda Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 3 Aug 2018 07:29:17 +0200
Subject: dt-bindings: mailbox: imx-mu: add generic MU channel support

Each MU has four pairs of rx/tx data register with four rx/tx interrupts
which can also be used as a separate channel.

Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 .../devicetree/bindings/mailbox/fsl,mu.txt         | 26 +++++++++++++++++++---
 1 file changed, 23 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/mailbox/fsl,mu.txt b/Documentation/devicetree/bindings/mailbox/fsl,mu.txt
index 90e4905dfc69..f3cf77eb5ab4 100644
--- a/Documentation/devicetree/bindings/mailbox/fsl,mu.txt
+++ b/Documentation/devicetree/bindings/mailbox/fsl,mu.txt
@@ -18,11 +18,31 @@ Messaging Unit Device Node:
 Required properties:
 -------------------
 - compatible :	should be "fsl,<chip>-mu", the supported chips include
-		imx8qxp, imx8qm.
+		imx6sx, imx7s, imx8qxp, imx8qm.
+		The "fsl,imx6sx-mu" compatible is seen as generic and should
+		be included together with SoC specific compatible.
 - reg :		Should contain the registers location and length
 - interrupts :	Interrupt number. The interrupt specifier format depends
 		on the interrupt controller parent.
-- #mbox-cells:  Must be 0. Number of cells in a mailbox
+- #mbox-cells:  Must be 2.
+			  <&phandle type channel>
+			    phandle   : Label name of controller
+			    type      : Channel type
+			    channel   : Channel number
+
+		This MU support 4 type of unidirectional channels, each type
+		has 4 channels. A total of 16 channels. Following types are
+		supported:
+		0 - TX channel with 32bit transmit register and IRQ transmit
+		acknowledgment support.
+		1 - RX channel with 32bit receive register and IRQ support
+		2 - TX doorbell channel. Without own register and no ACK support.
+		3 - RX doorbell channel.
+
+Optional properties:
+-------------------
+- clocks :	phandle to the input clock.
+- fsl,mu-side-b : Should be set for side B MU.
 
 Examples:
 --------
@@ -30,5 +50,5 @@ lsio_mu0: mailbox@5d1b0000 {
 	compatible = "fsl,imx8qxp-mu";
 	reg = <0x0 0x5d1b0000 0x0 0x10000>;
 	interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
-	#mbox-cells = <0>;
+	#mbox-cells = <2>;
 };
-- 
cgit v1.2.3


From 2bb7005696e2246baa88772341ca032ff09a63cb Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 3 Aug 2018 07:29:19 +0200
Subject: mailbox: Add support for i.MX messaging unit

The i.MX Messaging Unit is a two side block which allows applications
implement communication over this sides.

The MU includes the following features:
- Messaging control by interrupts or by polling
- Four general-purpose interrupt requests reflected to the other side
- Three general-purpose flags reflected to the other side
- Four receive registers with maskable interrupt
- Four transmit registers with maskable interrupt

Reviewed-by: Vladimir Zapolskiy <vz@mleia.com>
Reviewed-by: Dong Aisheng <aisheng.dong@nxp.com>
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: Jassi Brar <jaswinder.singh@linaro.org>
---
 drivers/mailbox/Kconfig       |   6 +
 drivers/mailbox/Makefile      |   2 +
 drivers/mailbox/imx-mailbox.c | 358 ++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 366 insertions(+)
 create mode 100644 drivers/mailbox/imx-mailbox.c

diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index 2bbabc907add..841c005d8ebb 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -15,6 +15,12 @@ config ARM_MHU
 	  The controller has 3 mailbox channels, the last of which can be
 	  used in Secure mode only.
 
+config IMX_MBOX
+	tristate "i.MX Mailbox"
+	depends on ARCH_MXC || COMPILE_TEST
+	help
+	  Mailbox implementation for i.MX Messaging Unit (MU).
+
 config PLATFORM_MHU
 	tristate "Platform MHU Mailbox"
 	depends on OF
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index 4b0080480661..c818b5d011ae 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -7,6 +7,8 @@ obj-$(CONFIG_MAILBOX_TEST)	+= mailbox-test.o
 
 obj-$(CONFIG_ARM_MHU)	+= arm_mhu.o
 
+obj-$(CONFIG_IMX_MBOX)	+= imx-mailbox.o
+
 obj-$(CONFIG_PLATFORM_MHU)	+= platform_mhu.o
 
 obj-$(CONFIG_PL320_MBOX)	+= pl320-ipc.o
diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
new file mode 100644
index 000000000000..363d35d5e49d
--- /dev/null
+++ b/drivers/mailbox/imx-mailbox.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018 Pengutronix, Oleksij Rempel <o.rempel@pengutronix.de>
+ */
+
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_controller.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+
+/* Transmit Register */
+#define IMX_MU_xTRn(x)		(0x00 + 4 * (x))
+/* Receive Register */
+#define IMX_MU_xRRn(x)		(0x10 + 4 * (x))
+/* Status Register */
+#define IMX_MU_xSR		0x20
+#define IMX_MU_xSR_GIPn(x)	BIT(28 + (3 - (x)))
+#define IMX_MU_xSR_RFn(x)	BIT(24 + (3 - (x)))
+#define IMX_MU_xSR_TEn(x)	BIT(20 + (3 - (x)))
+#define IMX_MU_xSR_BRDIP	BIT(9)
+
+/* Control Register */
+#define IMX_MU_xCR		0x24
+/* General Purpose Interrupt Enable */
+#define IMX_MU_xCR_GIEn(x)	BIT(28 + (3 - (x)))
+/* Receive Interrupt Enable */
+#define IMX_MU_xCR_RIEn(x)	BIT(24 + (3 - (x)))
+/* Transmit Interrupt Enable */
+#define IMX_MU_xCR_TIEn(x)	BIT(20 + (3 - (x)))
+/* General Purpose Interrupt Request */
+#define IMX_MU_xCR_GIRn(x)	BIT(16 + (3 - (x)))
+
+#define IMX_MU_CHANS		16
+#define IMX_MU_CHAN_NAME_SIZE	20
+
+enum imx_mu_chan_type {
+	IMX_MU_TYPE_TX,		/* Tx */
+	IMX_MU_TYPE_RX,		/* Rx */
+	IMX_MU_TYPE_TXDB,	/* Tx doorbell */
+	IMX_MU_TYPE_RXDB,	/* Rx doorbell */
+};
+
+struct imx_mu_con_priv {
+	unsigned int		idx;
+	char			irq_desc[IMX_MU_CHAN_NAME_SIZE];
+	enum imx_mu_chan_type	type;
+	struct mbox_chan	*chan;
+	struct tasklet_struct	txdb_tasklet;
+};
+
+struct imx_mu_priv {
+	struct device		*dev;
+	void __iomem		*base;
+	spinlock_t		xcr_lock; /* control register lock */
+
+	struct mbox_controller	mbox;
+	struct mbox_chan	mbox_chans[IMX_MU_CHANS];
+
+	struct imx_mu_con_priv  con_priv[IMX_MU_CHANS];
+	struct clk		*clk;
+	int			irq;
+
+	bool			side_b;
+};
+
+static struct imx_mu_priv *to_imx_mu_priv(struct mbox_controller *mbox)
+{
+	return container_of(mbox, struct imx_mu_priv, mbox);
+}
+
+static void imx_mu_write(struct imx_mu_priv *priv, u32 val, u32 offs)
+{
+	iowrite32(val, priv->base + offs);
+}
+
+static u32 imx_mu_read(struct imx_mu_priv *priv, u32 offs)
+{
+	return ioread32(priv->base + offs);
+}
+
+static u32 imx_mu_xcr_rmw(struct imx_mu_priv *priv, u32 set, u32 clr)
+{
+	unsigned long flags;
+	u32 val;
+
+	spin_lock_irqsave(&priv->xcr_lock, flags);
+	val = imx_mu_read(priv, IMX_MU_xCR);
+	val &= ~clr;
+	val |= set;
+	imx_mu_write(priv, val, IMX_MU_xCR);
+	spin_unlock_irqrestore(&priv->xcr_lock, flags);
+
+	return val;
+}
+
+static void imx_mu_txdb_tasklet(unsigned long data)
+{
+	struct imx_mu_con_priv *cp = (struct imx_mu_con_priv *)data;
+
+	mbox_chan_txdone(cp->chan, 0);
+}
+
+static irqreturn_t imx_mu_isr(int irq, void *p)
+{
+	struct mbox_chan *chan = p;
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+	u32 val, ctrl, dat;
+
+	ctrl = imx_mu_read(priv, IMX_MU_xCR);
+	val = imx_mu_read(priv, IMX_MU_xSR);
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_TX:
+		val &= IMX_MU_xSR_TEn(cp->idx) &
+			(ctrl & IMX_MU_xCR_TIEn(cp->idx));
+		break;
+	case IMX_MU_TYPE_RX:
+		val &= IMX_MU_xSR_RFn(cp->idx) &
+			(ctrl & IMX_MU_xCR_RIEn(cp->idx));
+		break;
+	case IMX_MU_TYPE_RXDB:
+		val &= IMX_MU_xSR_GIPn(cp->idx) &
+			(ctrl & IMX_MU_xCR_GIEn(cp->idx));
+		break;
+	default:
+		break;
+	}
+
+	if (!val)
+		return IRQ_NONE;
+
+	if (val == IMX_MU_xSR_TEn(cp->idx)) {
+		imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_TIEn(cp->idx));
+		mbox_chan_txdone(chan, 0);
+	} else if (val == IMX_MU_xSR_RFn(cp->idx)) {
+		dat = imx_mu_read(priv, IMX_MU_xRRn(cp->idx));
+		mbox_chan_received_data(chan, (void *)&dat);
+	} else if (val == IMX_MU_xSR_GIPn(cp->idx)) {
+		imx_mu_write(priv, IMX_MU_xSR_GIPn(cp->idx), IMX_MU_xSR);
+		mbox_chan_received_data(chan, NULL);
+	} else {
+		dev_warn_ratelimited(priv->dev, "Not handled interrupt\n");
+		return IRQ_NONE;
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int imx_mu_send_data(struct mbox_chan *chan, void *data)
+{
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+	u32 *arg = data;
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_TX:
+		imx_mu_write(priv, *arg, IMX_MU_xTRn(cp->idx));
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_TIEn(cp->idx), 0);
+		break;
+	case IMX_MU_TYPE_TXDB:
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIRn(cp->idx), 0);
+		tasklet_schedule(&cp->txdb_tasklet);
+		break;
+	default:
+		dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int imx_mu_startup(struct mbox_chan *chan)
+{
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+	int ret;
+
+	if (cp->type == IMX_MU_TYPE_TXDB) {
+		/* Tx doorbell don't have ACK support */
+		tasklet_init(&cp->txdb_tasklet, imx_mu_txdb_tasklet,
+			     (unsigned long)cp);
+		return 0;
+	}
+
+	ret = request_irq(priv->irq, imx_mu_isr, IRQF_SHARED, cp->irq_desc,
+			  chan);
+	if (ret) {
+		dev_err(priv->dev,
+			"Unable to acquire IRQ %d\n", priv->irq);
+		return ret;
+	}
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_RX:
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_RIEn(cp->idx), 0);
+		break;
+	case IMX_MU_TYPE_RXDB:
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIEn(cp->idx), 0);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static void imx_mu_shutdown(struct mbox_chan *chan)
+{
+	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
+	struct imx_mu_con_priv *cp = chan->con_priv;
+
+	if (cp->type == IMX_MU_TYPE_TXDB)
+		tasklet_kill(&cp->txdb_tasklet);
+
+	imx_mu_xcr_rmw(priv, 0,
+		   IMX_MU_xCR_TIEn(cp->idx) | IMX_MU_xCR_RIEn(cp->idx));
+
+	free_irq(priv->irq, chan);
+}
+
+static const struct mbox_chan_ops imx_mu_ops = {
+	.send_data = imx_mu_send_data,
+	.startup = imx_mu_startup,
+	.shutdown = imx_mu_shutdown,
+};
+
+static struct mbox_chan * imx_mu_xlate(struct mbox_controller *mbox,
+				       const struct of_phandle_args *sp)
+{
+	u32 type, idx, chan;
+
+	if (sp->args_count != 2) {
+		dev_err(mbox->dev, "Invalid argument count %d\n", sp->args_count);
+		return ERR_PTR(-EINVAL);
+	}
+
+	type = sp->args[0]; /* channel type */
+	idx = sp->args[1]; /* index */
+	chan = type * 4 + idx;
+
+	if (chan >= mbox->num_chans) {
+		dev_err(mbox->dev, "Not supported channel number: %d. (type: %d, idx: %d)\n", chan, type, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &mbox->chans[chan];
+}
+
+static void imx_mu_init_generic(struct imx_mu_priv *priv)
+{
+	if (priv->side_b)
+		return;
+
+	/* Set default MU configuration */
+	imx_mu_write(priv, 0, IMX_MU_xCR);
+}
+
+static int imx_mu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	struct resource *iomem;
+	struct imx_mu_priv *priv;
+	unsigned int i;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = dev;
+
+	iomem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	priv->base = devm_ioremap_resource(&pdev->dev, iomem);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0)
+		return priv->irq;
+
+	priv->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		if (PTR_ERR(priv->clk) != -ENOENT)
+			return PTR_ERR(priv->clk);
+
+		priv->clk = NULL;
+	}
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret) {
+		dev_err(dev, "Failed to enable clock\n");
+		return ret;
+	}
+
+	for (i = 0; i < IMX_MU_CHANS; i++) {
+		struct imx_mu_con_priv *cp = &priv->con_priv[i];
+
+		cp->idx = i % 4;
+		cp->type = i >> 2;
+		cp->chan = &priv->mbox_chans[i];
+		priv->mbox_chans[i].con_priv = cp;
+		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
+			 "imx_mu_chan[%i-%i]", cp->type, cp->idx);
+	}
+
+	priv->side_b = of_property_read_bool(np, "fsl,mu-side-b");
+
+	spin_lock_init(&priv->xcr_lock);
+
+	priv->mbox.dev = dev;
+	priv->mbox.ops = &imx_mu_ops;
+	priv->mbox.chans = priv->mbox_chans;
+	priv->mbox.num_chans = IMX_MU_CHANS;
+	priv->mbox.of_xlate = imx_mu_xlate;
+	priv->mbox.txdone_irq = true;
+
+	platform_set_drvdata(pdev, priv);
+
+	imx_mu_init_generic(priv);
+
+	return mbox_controller_register(&priv->mbox);
+}
+
+static int imx_mu_remove(struct platform_device *pdev)
+{
+	struct imx_mu_priv *priv = platform_get_drvdata(pdev);
+
+	mbox_controller_unregister(&priv->mbox);
+	clk_disable_unprepare(priv->clk);
+
+	return 0;
+}
+
+static const struct of_device_id imx_mu_dt_ids[] = {
+	{ .compatible = "fsl,imx6sx-mu" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, imx_mu_dt_ids);
+
+static struct platform_driver imx_mu_driver = {
+	.probe		= imx_mu_probe,
+	.remove		= imx_mu_remove,
+	.driver = {
+		.name	= "imx_mu",
+		.of_match_table = imx_mu_dt_ids,
+	},
+};
+module_platform_driver(imx_mu_driver);
+
+MODULE_AUTHOR("Oleksij Rempel <o.rempel@pengutronix.de>");
+MODULE_DESCRIPTION("Message Unit driver for i.MX");
+MODULE_LICENSE("GPL v2");
-- 
cgit v1.2.3


From 1eb46908b35dfbac0ec1848d4b1e39667e0187e9 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 15 Aug 2018 08:38:33 -0700
Subject: x86/l1tf: Fix build error seen if CONFIG_KVM_INTEL is disabled

allmodconfig+CONFIG_INTEL_KVM=n results in the following build error.

  ERROR: "l1tf_vmx_mitigation" [arch/x86/kvm/kvm.ko] undefined!

Fixes: 5b76a3cff011 ("KVM: VMX: Tell the nested hypervisor to skip L1D flush on vmentry")
Reported-by: Meelis Roos <mroos@linux.ee>
Cc: Meelis Roos <mroos@linux.ee>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/cpu/bugs.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 27830880e7a7..cb4a16292aa7 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -664,10 +664,9 @@ void x86_spec_ctrl_setup_ap(void)
 enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH;
 #if IS_ENABLED(CONFIG_KVM_INTEL)
 EXPORT_SYMBOL_GPL(l1tf_mitigation);
-
+#endif
 enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
 EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
-#endif
 
 static void __init l1tf_select_mitigation(void)
 {
-- 
cgit v1.2.3


From 45687f96c112adda2f1d1f05b977661eb00d5a1c Mon Sep 17 00:00:00 2001
From: Alexandru Gagniuc <mr.nuke.me@gmail.com>
Date: Tue, 17 Jul 2018 10:31:23 -0500
Subject: PCI/AER: Don't clear AER bits if error handling is Firmware-First

If the platform requests Firmware-First error handling, firmware is
responsible for reading and clearing AER status bits.  If OSPM also clears
them, we may miss errors.  See ACPI v6.2, sec 18.3.2.5 and 18.4.

This race is mostly of theoretical significance, as it is not easy to
reasonably demonstrate it in testing.

Signed-off-by: Alexandru Gagniuc <mr.nuke.me@gmail.com>
[bhelgaas: add similar guards to pci_cleanup_aer_uncorrect_error_status()
and pci_aer_clear_fatal_status()]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aer.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index c6cc855bfa22..4e823ae051a7 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -397,6 +397,9 @@ int pci_cleanup_aer_uncorrect_error_status(struct pci_dev *dev)
 	if (!pos)
 		return -EIO;
 
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
 	/* Clear status bits for ERR_NONFATAL errors only */
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
@@ -417,6 +420,9 @@ void pci_aer_clear_fatal_status(struct pci_dev *dev)
 	if (!pos)
 		return;
 
+	if (pcie_aer_get_firmware_first(dev))
+		return;
+
 	/* Clear status bits for ERR_FATAL errors only */
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_STATUS, &status);
 	pci_read_config_dword(dev, pos + PCI_ERR_UNCOR_SEVER, &sev);
@@ -438,6 +444,9 @@ int pci_cleanup_aer_error_status_regs(struct pci_dev *dev)
 	if (!pos)
 		return -EIO;
 
+	if (pcie_aer_get_firmware_first(dev))
+		return -EIO;
+
 	port_type = pci_pcie_type(dev);
 	if (port_type == PCI_EXP_TYPE_ROOT_PORT) {
 		pci_read_config_dword(dev, pos + PCI_ERR_ROOT_STATUS, &status);
-- 
cgit v1.2.3


From 0a957467c5fd46142bc9c52758ffc552d4c5e2f7 Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 15 Aug 2018 13:22:27 -0700
Subject: x86: i8259: Add missing include file

i8259.h uses inb/outb and thus needs to include asm/io.h to avoid the
following build error, as seen with x86_64:defconfig and CONFIG_SMP=n.

  In file included from drivers/rtc/rtc-cmos.c:45:0:
  arch/x86/include/asm/i8259.h: In function 'inb_pic':
  arch/x86/include/asm/i8259.h:32:24: error:
	implicit declaration of function 'inb'

  arch/x86/include/asm/i8259.h: In function 'outb_pic':
  arch/x86/include/asm/i8259.h:45:2: error:
	implicit declaration of function 'outb'

Reported-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Suggested-by: Sebastian Gottschall <s.gottschall@dd-wrt.com>
Fixes: 447ae3166702 ("x86: Don't include linux/irq.h from asm/hardirq.h")
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/include/asm/i8259.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/include/asm/i8259.h b/arch/x86/include/asm/i8259.h
index 5cdcdbd4d892..89789e8c80f6 100644
--- a/arch/x86/include/asm/i8259.h
+++ b/arch/x86/include/asm/i8259.h
@@ -3,6 +3,7 @@
 #define _ASM_X86_I8259_H
 
 #include <linux/delay.h>
+#include <asm/io.h>
 
 extern unsigned int cached_irq_mask;
 
-- 
cgit v1.2.3


From 70b20dd7f897c6c14ab9e0d8400aed520ab5f09b Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 15 Aug 2018 19:08:10 -0700
Subject: ALSA: update dell-wmi mic-mute registration to new world order

Commit c647f806b8c2 ("ALSA: hda - Allow multiple ADCs for mic mute LED
controls") changed the return value of the snd_hda_gen_add_micmute_led()
without actually updating the callers.

Admittedly, almost no callers actually cared about the return value.
But one call site very much did: the Dell wmi code.  It would see the
registration return zero, which _used_ to mean "failed" but now means
"success", and clear the dell_micmute_led_set_func pointer.

End result: the successful registration would end up calling the Dell
code that thought it had all failed, and call through a NULL pointer.

To make matters worse, it ends up being a tail-call, and with the
retpoline sequence you don't even see the caller (dell_micmute_update())
in the stack trace, so the error ended up way less obvious than it
should have been.

Fixes: c647f806b8c2 "ALSA: hda - Allow multiple ADCs for mic mute LED controls"
Cc: Takashi Iwai <tiwai@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 sound/pci/hda/dell_wmi_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/pci/hda/dell_wmi_helper.c b/sound/pci/hda/dell_wmi_helper.c
index 8a7dbd1a7fbf..bbd6c87a4ed6 100644
--- a/sound/pci/hda/dell_wmi_helper.c
+++ b/sound/pci/hda/dell_wmi_helper.c
@@ -30,7 +30,7 @@ static void alc_fixup_dell_wmi(struct hda_codec *codec,
 
 		removefunc = (dell_micmute_led_set_func(false) < 0) ||
 			(snd_hda_gen_add_micmute_led(codec,
-						     dell_micmute_update) <= 0);
+						     dell_micmute_update) < 0);
 	}
 
 	if (dell_micmute_led_set_func && (action == HDA_FIXUP_ACT_FREE || removefunc)) {
-- 
cgit v1.2.3


From 817aef260037f33ee0f44c17fe341323d3aebd6d Mon Sep 17 00:00:00 2001
From: Yannik Sembritzki <yannik@sembritzki.me>
Date: Thu, 16 Aug 2018 14:05:10 +0100
Subject: Replace magic for trusting the secondary keyring with #define

Replace the use of a magic number that indicates that verify_*_signature()
should use the secondary keyring with a symbol.

Signed-off-by: Yannik Sembritzki <yannik@sembritzki.me>
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: keyrings@vger.kernel.org
Cc: linux-security-module@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 certs/system_keyring.c                  | 3 ++-
 crypto/asymmetric_keys/pkcs7_key_type.c | 2 +-
 include/linux/verification.h            | 6 ++++++
 3 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/certs/system_keyring.c b/certs/system_keyring.c
index 6251d1b27f0c..81728717523d 100644
--- a/certs/system_keyring.c
+++ b/certs/system_keyring.c
@@ -15,6 +15,7 @@
 #include <linux/cred.h>
 #include <linux/err.h>
 #include <linux/slab.h>
+#include <linux/verification.h>
 #include <keys/asymmetric-type.h>
 #include <keys/system_keyring.h>
 #include <crypto/pkcs7.h>
@@ -230,7 +231,7 @@ int verify_pkcs7_signature(const void *data, size_t len,
 
 	if (!trusted_keys) {
 		trusted_keys = builtin_trusted_keys;
-	} else if (trusted_keys == (void *)1UL) {
+	} else if (trusted_keys == VERIFY_USE_SECONDARY_KEYRING) {
 #ifdef CONFIG_SECONDARY_TRUSTED_KEYRING
 		trusted_keys = secondary_trusted_keys;
 #else
diff --git a/crypto/asymmetric_keys/pkcs7_key_type.c b/crypto/asymmetric_keys/pkcs7_key_type.c
index e284d9cb9237..5b2f6a2b5585 100644
--- a/crypto/asymmetric_keys/pkcs7_key_type.c
+++ b/crypto/asymmetric_keys/pkcs7_key_type.c
@@ -63,7 +63,7 @@ static int pkcs7_preparse(struct key_preparsed_payload *prep)
 
 	return verify_pkcs7_signature(NULL, 0,
 				      prep->data, prep->datalen,
-				      (void *)1UL, usage,
+				      VERIFY_USE_SECONDARY_KEYRING, usage,
 				      pkcs7_view_content, prep);
 }
 
diff --git a/include/linux/verification.h b/include/linux/verification.h
index a10549a6c7cd..cfa4730d607a 100644
--- a/include/linux/verification.h
+++ b/include/linux/verification.h
@@ -12,6 +12,12 @@
 #ifndef _LINUX_VERIFICATION_H
 #define _LINUX_VERIFICATION_H
 
+/*
+ * Indicate that both builtin trusted keys and secondary trusted keys
+ * should be used.
+ */
+#define VERIFY_USE_SECONDARY_KEYRING ((struct key *)1UL)
+
 /*
  * The use to which an asymmetric key is being put.
  */
-- 
cgit v1.2.3


From ea93102f32244e3f45c8b26260be77ed0cc1d16c Mon Sep 17 00:00:00 2001
From: Yannik Sembritzki <yannik@sembritzki.me>
Date: Thu, 16 Aug 2018 14:05:23 +0100
Subject: Fix kexec forbidding kernels signed with keys in the secondary
 keyring to boot

The split of .system_keyring into .builtin_trusted_keys and
.secondary_trusted_keys broke kexec, thereby preventing kernels signed by
keys which are now in the secondary keyring from being kexec'd.

Fix this by passing VERIFY_USE_SECONDARY_KEYRING to
verify_pefile_signature().

Fixes: d3bfe84129f6 ("certs: Add a secondary system keyring that can be added to dynamically")
Signed-off-by: Yannik Sembritzki <yannik@sembritzki.me>
Signed-off-by: David Howells <dhowells@redhat.com>
Cc: kexec@lists.infradead.org
Cc: keyrings@vger.kernel.org
Cc: linux-security-module@vger.kernel.org
Cc: stable@kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 arch/x86/kernel/kexec-bzimage64.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 7326078eaa7a..278cd07228dd 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -532,7 +532,7 @@ static int bzImage64_cleanup(void *loader_data)
 static int bzImage64_verify_sig(const char *kernel, unsigned long kernel_len)
 {
 	return verify_pefile_signature(kernel, kernel_len,
-				       NULL,
+				       VERIFY_USE_SECONDARY_KEYRING,
 				       VERIFYING_KEXEC_PE_SIGNATURE);
 }
 #endif
-- 
cgit v1.2.3